diff --git a/checkpoint-11700/config.json b/checkpoint-11700/config.json new file mode 100644 index 0000000000000000000000000000000000000000..7a738742a87b760472dac489c65d89b6e963ae2b --- /dev/null +++ b/checkpoint-11700/config.json @@ -0,0 +1,253 @@ +{ + "_name_or_path": "/lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-11700", + "architectures": [ + "LlavaLlamaModel" + ], + "drop_path_rate": 0.0, + "hidden_size": 2560, + "image_aspect_ratio": "resize", + "interpolate_mode": "linear", + "llm_cfg": { + "_name_or_path": "/lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-11700/llm", + "add_cross_attention": false, + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bad_words_ids": null, + "begin_suppress_tokens": null, + "bos_token_id": 1, + "chunk_size_feed_forward": 0, + "cross_attention_hidden_size": null, + "decoder_start_token_id": null, + "diversity_penalty": 0.0, + "do_sample": false, + "early_stopping": false, + "encoder_no_repeat_ngram_size": 0, + "eos_token_id": 2, + "exponential_decay_length_penalty": null, + "finetuning_task": null, + "forced_bos_token_id": null, + "forced_eos_token_id": null, + "hidden_act": "silu", + "hidden_size": 2560, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "initializer_range": 0.02, + "intermediate_size": 6912, + "is_decoder": false, + "is_encoder_decoder": false, + "label2id": { + "LABEL_0": 0, + "LABEL_1": 1 + }, + "length_penalty": 1.0, + "max_length": 20, + "max_position_embeddings": 4096, + "min_length": 0, + "model_max_length": 4096, + "model_type": "llama", + "no_repeat_ngram_size": 0, + "num_attention_heads": 20, + "num_beam_groups": 1, + "num_beams": 1, + "num_hidden_layers": 32, + "num_key_value_heads": 20, + "num_return_sequences": 1, + "output_attentions": false, + "output_hidden_states": false, + "output_scores": false, + "pad_token_id": 0, + "prefix": null, + "pretraining_tp": 1, + "problem_type": null, + "pruned_heads": {}, + "remove_invalid_values": false, + "repetition_penalty": 1.0, + "return_dict": true, + "return_dict_in_generate": false, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 10000.0, + "sep_token_id": null, + "suppress_tokens": null, + "task_specific_params": null, + "temperature": 1.0, + "tf_legacy_loss": false, + "tie_encoder_decoder": false, + "tie_word_embeddings": false, + "tokenizer_class": null, + "tokenizer_model_max_length": 4096, + "tokenizer_padding_side": "right", + "top_k": 50, + "top_p": 1.0, + "torch_dtype": "bfloat16", + "torchscript": false, + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": false, + "vocab_size": 32000 + }, + "mm_hidden_size": 1152, + "mm_projector_cfg": { + "_name_or_path": "/lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-11700/mm_projector", + "add_cross_attention": false, + "architectures": [ + "MultimodalProjector" + ], + "bad_words_ids": null, + "begin_suppress_tokens": null, + "bos_token_id": null, + "chunk_size_feed_forward": 0, + "cross_attention_hidden_size": null, + "decoder_start_token_id": null, + "diversity_penalty": 0.0, + "do_sample": false, + "early_stopping": false, + "encoder_no_repeat_ngram_size": 0, + "eos_token_id": null, + "exponential_decay_length_penalty": null, + "finetuning_task": null, + "forced_bos_token_id": null, + "forced_eos_token_id": null, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "is_decoder": false, + "is_encoder_decoder": false, + "label2id": { + "LABEL_0": 0, + "LABEL_1": 1 + }, + "length_penalty": 1.0, + "max_length": 20, + "min_length": 0, + "mm_projector_type": "mlp_downsample", + "model_type": "v2l_projector", + "no_repeat_ngram_size": 0, + "num_beam_groups": 1, + "num_beams": 1, + "num_return_sequences": 1, + "output_attentions": false, + "output_hidden_states": false, + "output_scores": false, + "pad_token_id": null, + "prefix": null, + "problem_type": null, + "pruned_heads": {}, + "remove_invalid_values": false, + "repetition_penalty": 1.0, + "return_dict": true, + "return_dict_in_generate": false, + "sep_token_id": null, + "suppress_tokens": null, + "task_specific_params": null, + "temperature": 1.0, + "tf_legacy_loss": false, + "tie_encoder_decoder": false, + "tie_word_embeddings": true, + "tokenizer_class": null, + "top_k": 50, + "top_p": 1.0, + "torch_dtype": "bfloat16", + "torchscript": false, + "typical_p": 1.0, + "use_bfloat16": false + }, + "mm_projector_lr": null, + "mm_use_im_patch_token": false, + "mm_use_im_start_end": false, + "mm_vision_select_feature": "cls_patch", + "mm_vision_select_layer": -2, + "model_dtype": "torch.bfloat16", + "model_type": "llava_llama", + "num_video_frames": 8, + "resume_path": "/lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/checkpoint-11500", + "s2": false, + "s2_max_split_size": 336, + "s2_scales": "336,672,1008", + "transformers_version": "4.36.2", + "tune_language_model": true, + "tune_mm_projector": true, + "tune_vision_tower": true, + "vision_resolution": -1, + "vision_tower_cfg": { + "_name_or_path": "/lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-11700/vision_tower", + "add_cross_attention": false, + "architectures": [ + "SiglipVisionModel" + ], + "attention_dropout": 0.0, + "bad_words_ids": null, + "begin_suppress_tokens": null, + "bos_token_id": null, + "chunk_size_feed_forward": 0, + "cross_attention_hidden_size": null, + "decoder_start_token_id": null, + "diversity_penalty": 0.0, + "do_sample": false, + "early_stopping": false, + "encoder_no_repeat_ngram_size": 0, + "eos_token_id": null, + "exponential_decay_length_penalty": null, + "finetuning_task": null, + "forced_bos_token_id": null, + "forced_eos_token_id": null, + "hidden_act": "gelu_pytorch_tanh", + "hidden_size": 1152, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "image_size": 384, + "intermediate_size": 4304, + "is_decoder": false, + "is_encoder_decoder": false, + "label2id": { + "LABEL_0": 0, + "LABEL_1": 1 + }, + "layer_norm_eps": 1e-06, + "length_penalty": 1.0, + "max_length": 20, + "min_length": 0, + "model_type": "siglip_vision_model", + "no_repeat_ngram_size": 0, + "num_attention_heads": 16, + "num_beam_groups": 1, + "num_beams": 1, + "num_channels": 3, + "num_hidden_layers": 27, + "num_return_sequences": 1, + "output_attentions": false, + "output_hidden_states": false, + "output_scores": false, + "pad_token_id": null, + "patch_size": 14, + "prefix": null, + "problem_type": null, + "pruned_heads": {}, + "remove_invalid_values": false, + "repetition_penalty": 1.0, + "return_dict": true, + "return_dict_in_generate": false, + "sep_token_id": null, + "suppress_tokens": null, + "task_specific_params": null, + "temperature": 1.0, + "tf_legacy_loss": false, + "tie_encoder_decoder": false, + "tie_word_embeddings": true, + "tokenizer_class": null, + "top_k": 50, + "top_p": 1.0, + "torch_dtype": "bfloat16", + "torchscript": false, + "typical_p": 1.0, + "use_bfloat16": false + } +} diff --git a/checkpoint-11700/global_step11700/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/checkpoint-11700/global_step11700/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..da4970eebe7dd05b9fc0c0dcf69167d2f5a8cd2c --- /dev/null +++ b/checkpoint-11700/global_step11700/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d4c5087dece6aa818a2018535bb69854b8bf0df00f830034ed415e2eb51ff6d +size 4722230103 diff --git a/checkpoint-11700/global_step11700/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/checkpoint-11700/global_step11700/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f6d4420bcfc95be9d5e45d810222547edce8a591 --- /dev/null +++ b/checkpoint-11700/global_step11700/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3db0aa24376f0ae9ffba86d1715ce69240043a0d474a7bb6ab812ac8278112a4 +size 4722230103 diff --git a/checkpoint-11700/global_step11700/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt b/checkpoint-11700/global_step11700/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..30e09a963f61cacbf82e1a9b27367a7321e9d9e7 --- /dev/null +++ b/checkpoint-11700/global_step11700/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f32ec49bdb49dd87e00153217eeb52bc2715727de96f48381971be72a5f23da9 +size 4722230103 diff --git a/checkpoint-11700/global_step11700/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt b/checkpoint-11700/global_step11700/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0907d020e8774548dfb8f0d87eec2e7980cb45c6 --- /dev/null +++ b/checkpoint-11700/global_step11700/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed6045ed0ea7ba6f6d7c116c698a2f15cae1137edbce53bf180cd93d48525252 +size 4722230103 diff --git a/checkpoint-11700/global_step11700/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt b/checkpoint-11700/global_step11700/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f9d51ab15120eccdfe698405b9614c22675d7760 --- /dev/null +++ b/checkpoint-11700/global_step11700/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1fa8999cf814c1f2981ef22abe2b02599f89783cb75358039c5151b335b3709 +size 4722230103 diff --git a/checkpoint-11700/global_step11700/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt b/checkpoint-11700/global_step11700/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d9a2d2905a67fa70772718459763910dd6211172 --- /dev/null +++ b/checkpoint-11700/global_step11700/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f2f2a5fbe3188869aa425153115ea9c280f721c0d7c6897742eee0be7e8847b +size 4722230103 diff --git a/checkpoint-11700/global_step11700/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt b/checkpoint-11700/global_step11700/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d968d8d884107afc33097f068d5b20ce6966d433 --- /dev/null +++ b/checkpoint-11700/global_step11700/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59a75b2d47d2687250f2a8659ee28d937132dc8be02a09b6327378153f4405f6 +size 4722230103 diff --git a/checkpoint-11700/global_step11700/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt b/checkpoint-11700/global_step11700/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ac7373537c0373e9ac08177139fe36c5dc441d3d --- /dev/null +++ b/checkpoint-11700/global_step11700/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab93a7a444767f29f5675db4cc5cae215b820550ee2ccaf0cbf1da986ff24ff2 +size 4722230103 diff --git a/checkpoint-11700/global_step11700/zero_pp_rank_0_mp_rank_00_model_states.pt b/checkpoint-11700/global_step11700/zero_pp_rank_0_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..93d422d3ab058fef1fa3793f908734f0e830e93f --- /dev/null +++ b/checkpoint-11700/global_step11700/zero_pp_rank_0_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b71aa4d4847862cfe6fefb23e0cc765a2e971671b0335587e3a75606d281651d +size 413988 diff --git a/checkpoint-11700/global_step11700/zero_pp_rank_1_mp_rank_00_model_states.pt b/checkpoint-11700/global_step11700/zero_pp_rank_1_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..8d2b0dd76a95933fabb2cf01e739624043649bb3 --- /dev/null +++ b/checkpoint-11700/global_step11700/zero_pp_rank_1_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e4a0a3121bb7d37df55dd9d3fd70c2f2aac82fe341ceff92b80149881e237ee +size 413988 diff --git a/checkpoint-11700/global_step11700/zero_pp_rank_2_mp_rank_00_model_states.pt b/checkpoint-11700/global_step11700/zero_pp_rank_2_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..871763943d7d0907f01e23916e2852ec438f3b0a --- /dev/null +++ b/checkpoint-11700/global_step11700/zero_pp_rank_2_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f96baa1ad9b505b997d2f1b7f467cfc703502ff373c1ca1e3c677fef8d1a0aa1 +size 413988 diff --git a/checkpoint-11700/global_step11700/zero_pp_rank_3_mp_rank_00_model_states.pt b/checkpoint-11700/global_step11700/zero_pp_rank_3_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2142d34dead98ff28f2486e8935a889ebadb8aba --- /dev/null +++ b/checkpoint-11700/global_step11700/zero_pp_rank_3_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f746454c1cd58587e497abd578374901cb1ef19f5c0115ff5d6c51994dfe764b +size 413988 diff --git a/checkpoint-11700/global_step11700/zero_pp_rank_4_mp_rank_00_model_states.pt b/checkpoint-11700/global_step11700/zero_pp_rank_4_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0f757a4c3f229ad60770a92ba696ad6fc88cfdf1 --- /dev/null +++ b/checkpoint-11700/global_step11700/zero_pp_rank_4_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fa2bff2477fe50c1844cbdc821a439f44224ba2066dcfc3c36f90bd707bef6c +size 413988 diff --git a/checkpoint-11700/global_step11700/zero_pp_rank_5_mp_rank_00_model_states.pt b/checkpoint-11700/global_step11700/zero_pp_rank_5_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..23a455bc8fda2d4c1cd30f79f67e9e3cedca34b9 --- /dev/null +++ b/checkpoint-11700/global_step11700/zero_pp_rank_5_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:beb49ce0fcfc5d7c2d340badabccc4e850e323e62b8311b73dc4462dd9843f14 +size 413988 diff --git a/checkpoint-11700/global_step11700/zero_pp_rank_6_mp_rank_00_model_states.pt b/checkpoint-11700/global_step11700/zero_pp_rank_6_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..7a99d78311e8d285fd4dad86e02f873b9c61217c --- /dev/null +++ b/checkpoint-11700/global_step11700/zero_pp_rank_6_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a19feb37cbe8929fb754d8b4b68b9610f70ace18456128cbf4188911563f830d +size 413988 diff --git a/checkpoint-11700/global_step11700/zero_pp_rank_7_mp_rank_00_model_states.pt b/checkpoint-11700/global_step11700/zero_pp_rank_7_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4758dd672b36ab50c48d04a496910a366ef334d3 --- /dev/null +++ b/checkpoint-11700/global_step11700/zero_pp_rank_7_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a04d15c175538bff2ddfe16b35a757e01b6626c2a56c772b24c803fcd99fe741 +size 413988 diff --git a/checkpoint-11700/latest b/checkpoint-11700/latest new file mode 100644 index 0000000000000000000000000000000000000000..ac5f8ee8cac7f7d2e6f590996fa11b4aee6a5278 --- /dev/null +++ b/checkpoint-11700/latest @@ -0,0 +1 @@ +global_step11700 \ No newline at end of file diff --git a/checkpoint-11700/llm/config.json b/checkpoint-11700/llm/config.json new file mode 100644 index 0000000000000000000000000000000000000000..4e4eba318b03bc4243e5592fe65c69f3e24c6e62 --- /dev/null +++ b/checkpoint-11700/llm/config.json @@ -0,0 +1,32 @@ +{ + "_name_or_path": "/lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-11700/llm", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 2560, + "initializer_range": 0.02, + "intermediate_size": 6912, + "max_position_embeddings": 4096, + "model_max_length": 4096, + "model_type": "llama", + "num_attention_heads": 20, + "num_hidden_layers": 32, + "num_key_value_heads": 20, + "pad_token_id": 0, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 10000.0, + "tie_word_embeddings": false, + "tokenizer_model_max_length": 4096, + "tokenizer_padding_side": "right", + "torch_dtype": "bfloat16", + "transformers_version": "4.36.2", + "use_cache": false, + "vocab_size": 32000 +} diff --git a/checkpoint-11700/llm/generation_config.json b/checkpoint-11700/llm/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..bf84ec1a28ba89feb07162d95b06633a40b4975f --- /dev/null +++ b/checkpoint-11700/llm/generation_config.json @@ -0,0 +1,7 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "pad_token_id": 0, + "transformers_version": "4.36.2" +} diff --git a/checkpoint-11700/llm/model-00001-of-00002.safetensors b/checkpoint-11700/llm/model-00001-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..10a0d4961612d5a26f5a80f200d59d1537d95b5f --- /dev/null +++ b/checkpoint-11700/llm/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df010b6f786890419aa51675bc7877784798654c0cfe5acf79630cbe60dff88d +size 4974521464 diff --git a/checkpoint-11700/llm/model-00002-of-00002.safetensors b/checkpoint-11700/llm/model-00002-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2d3030fb25528f7c02d8a3036179093be889a084 --- /dev/null +++ b/checkpoint-11700/llm/model-00002-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e95d9548a8854d3109fcd6d4f7195943d050cff4f41f8e77c21bf1fdbb77159 +size 428632856 diff --git a/checkpoint-11700/llm/model.safetensors.index.json b/checkpoint-11700/llm/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..8b173c9ac8194749df58c92051618c0ff74c4c20 --- /dev/null +++ b/checkpoint-11700/llm/model.safetensors.index.json @@ -0,0 +1,298 @@ +{ + "metadata": { + "total_size": 5403120640 + }, + "weight_map": { + "lm_head.weight": "model-00002-of-00002.safetensors", + "model.embed_tokens.weight": "model-00001-of-00002.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.norm.weight": "model-00002-of-00002.safetensors" + } +} diff --git a/checkpoint-11700/llm/special_tokens_map.json b/checkpoint-11700/llm/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..14761dcf1466dc232bd41de9c21d4c617b15755e --- /dev/null +++ b/checkpoint-11700/llm/special_tokens_map.json @@ -0,0 +1,24 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "", + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/checkpoint-11700/llm/tokenizer.model b/checkpoint-11700/llm/tokenizer.model new file mode 100644 index 0000000000000000000000000000000000000000..3b7eab905db502ae7629c8a3c1f8412a3178c4c2 --- /dev/null +++ b/checkpoint-11700/llm/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7aedb3582ecda9fa99ee9242c17a9658f6744db083ee6ebdc8fb14857f84d220 +size 499723 diff --git a/checkpoint-11700/llm/tokenizer_config.json b/checkpoint-11700/llm/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..47ab96cd62cc374653a0ea0fb77f9457e0f53481 --- /dev/null +++ b/checkpoint-11700/llm/tokenizer_config.json @@ -0,0 +1,43 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "add_prefix_space": true, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "legacy": false, + "model_max_length": 4096, + "pad_token": "", + "padding_side": "right", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "unk_token": "", + "use_default_system_prompt": false +} diff --git a/checkpoint-11700/mm_projector/config.json b/checkpoint-11700/mm_projector/config.json new file mode 100644 index 0000000000000000000000000000000000000000..a2b40395882fea87e9f48baf7d99fcb81e9c649d --- /dev/null +++ b/checkpoint-11700/mm_projector/config.json @@ -0,0 +1,10 @@ +{ + "_name_or_path": "/lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-11700/mm_projector", + "architectures": [ + "MultimodalProjector" + ], + "mm_projector_type": "mlp_downsample", + "model_type": "v2l_projector", + "torch_dtype": "bfloat16", + "transformers_version": "4.36.2" +} diff --git a/checkpoint-11700/mm_projector/model.safetensors b/checkpoint-11700/mm_projector/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..503e0c4ff0ac688380f246e1833045a853c96e64 --- /dev/null +++ b/checkpoint-11700/mm_projector/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10a0be95ba28fe3dc4dd72eb2054accd5c4bc0819941106898d1c1120625cc95 +size 36729360 diff --git a/checkpoint-11700/rng_state_0.pth b/checkpoint-11700/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..9b640410d7b647494224af1a270b0a59e08c6e1b --- /dev/null +++ b/checkpoint-11700/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b88e7e9e7eb6f17b46ae1b2f6d71ee5f8b3ecedf11230cff9fa02511058cc1d8 +size 21687 diff --git a/checkpoint-11700/rng_state_1.pth b/checkpoint-11700/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..9a9d3624a43db1e91dd7e6d8c219b564895de397 --- /dev/null +++ b/checkpoint-11700/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ea3f3f353be392bfb069c21fdd46f09718d40d780ae6fbe7bd151f165b62370 +size 21687 diff --git a/checkpoint-11700/rng_state_2.pth b/checkpoint-11700/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..7a4c8da2b306a0bc3215ac2ba4821b3b9f49dc31 --- /dev/null +++ b/checkpoint-11700/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a204a67e2f5f8ec65b2a6066b4386a8a859864aede55100514df60a8a2b14cd +size 21687 diff --git a/checkpoint-11700/rng_state_3.pth b/checkpoint-11700/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..bade5579eb49360f44f3ba6d1ae2dca89fd2b247 --- /dev/null +++ b/checkpoint-11700/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:997988b8f3c4fe430f038ba40a6dd78c6dd5687028289cd9a81a0a1fddbc0f56 +size 21687 diff --git a/checkpoint-11700/rng_state_4.pth b/checkpoint-11700/rng_state_4.pth new file mode 100644 index 0000000000000000000000000000000000000000..9bbc918061d714ce4e456ab3c8914a91b34fb1d5 --- /dev/null +++ b/checkpoint-11700/rng_state_4.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0054495356c900c3cb48ad0ca679459ba78753225b9f186a76eae361dfed7e9 +size 21687 diff --git a/checkpoint-11700/rng_state_5.pth b/checkpoint-11700/rng_state_5.pth new file mode 100644 index 0000000000000000000000000000000000000000..15a6198fd9e45411c68d993987286b04c18b2554 --- /dev/null +++ b/checkpoint-11700/rng_state_5.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5871472ac61879b97b2d787d38c79274434bdd2264531e14d2e8948ab44eb7b +size 21687 diff --git a/checkpoint-11700/rng_state_6.pth b/checkpoint-11700/rng_state_6.pth new file mode 100644 index 0000000000000000000000000000000000000000..33864e37f55fb8e4d400a29f8fb69df82359a9dc --- /dev/null +++ b/checkpoint-11700/rng_state_6.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20c527f6e30d3a3ba8386bed54d9e474a38f9c9efe212ba44015b764fa1277ba +size 21687 diff --git a/checkpoint-11700/rng_state_7.pth b/checkpoint-11700/rng_state_7.pth new file mode 100644 index 0000000000000000000000000000000000000000..dcf359e297ef40efd5099812211d4d8e20d8dce4 --- /dev/null +++ b/checkpoint-11700/rng_state_7.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8542ae578beb1589c1f47a016c7f4e1867bf67b1a0ab69e68813e3cf5536e7d8 +size 21687 diff --git a/checkpoint-11700/scheduler.pt b/checkpoint-11700/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..c3cb15d8f5087e41345308a9ed07658bc644676e --- /dev/null +++ b/checkpoint-11700/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2264d10497d11823bec0681131a053202e5f59c8018d09cea3c501563ff26206 +size 627 diff --git a/checkpoint-11700/trainer_state.json b/checkpoint-11700/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..128c53c283984f3673c4b325ae9039d787ea7c33 --- /dev/null +++ b/checkpoint-11700/trainer_state.json @@ -0,0 +1,70221 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 0.997612551159618, + "eval_steps": 500, + "global_step": 11700, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0, + "learning_rate": 5.681818181818182e-08, + "loss": 0.8037, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 1.1363636363636364e-07, + "loss": 0.8135, + "step": 2 + }, + { + "epoch": 0.0, + "learning_rate": 1.7045454545454545e-07, + "loss": 0.8006, + "step": 3 + }, + { + "epoch": 0.0, + "learning_rate": 2.2727272727272729e-07, + "loss": 0.8006, + "step": 4 + }, + { + "epoch": 0.0, + "learning_rate": 2.840909090909091e-07, + "loss": 0.7892, + "step": 5 + }, + { + "epoch": 0.0, + "learning_rate": 3.409090909090909e-07, + "loss": 0.8249, + "step": 6 + }, + { + "epoch": 0.0, + "learning_rate": 3.9772727272727276e-07, + "loss": 0.8055, + "step": 7 + }, + { + "epoch": 0.0, + "learning_rate": 4.5454545454545457e-07, + "loss": 0.7966, + "step": 8 + }, + { + "epoch": 0.0, + "learning_rate": 5.113636363636364e-07, + "loss": 0.7916, + "step": 9 + }, + { + "epoch": 0.0, + "learning_rate": 5.681818181818182e-07, + "loss": 0.8006, + "step": 10 + }, + { + "epoch": 0.0, + "learning_rate": 6.25e-07, + "loss": 0.7935, + "step": 11 + }, + { + "epoch": 0.0, + "learning_rate": 6.818181818181818e-07, + "loss": 0.7847, + "step": 12 + }, + { + "epoch": 0.0, + "learning_rate": 7.386363636363638e-07, + "loss": 0.8064, + "step": 13 + }, + { + "epoch": 0.0, + "learning_rate": 7.954545454545455e-07, + "loss": 0.7889, + "step": 14 + }, + { + "epoch": 0.0, + "learning_rate": 8.522727272727273e-07, + "loss": 0.7977, + "step": 15 + }, + { + "epoch": 0.0, + "learning_rate": 9.090909090909091e-07, + "loss": 0.7758, + "step": 16 + }, + { + "epoch": 0.0, + "learning_rate": 9.65909090909091e-07, + "loss": 0.7677, + "step": 17 + }, + { + "epoch": 0.0, + "learning_rate": 1.0227272727272729e-06, + "loss": 0.7571, + "step": 18 + }, + { + "epoch": 0.0, + "learning_rate": 1.0795454545454546e-06, + "loss": 0.7259, + "step": 19 + }, + { + "epoch": 0.0, + "learning_rate": 1.1363636363636364e-06, + "loss": 0.7316, + "step": 20 + }, + { + "epoch": 0.0, + "learning_rate": 1.1931818181818183e-06, + "loss": 0.7075, + "step": 21 + }, + { + "epoch": 0.0, + "learning_rate": 1.25e-06, + "loss": 0.7367, + "step": 22 + }, + { + "epoch": 0.0, + "learning_rate": 1.3068181818181819e-06, + "loss": 0.7138, + "step": 23 + }, + { + "epoch": 0.0, + "learning_rate": 1.3636363636363636e-06, + "loss": 0.7215, + "step": 24 + }, + { + "epoch": 0.0, + "learning_rate": 1.4204545454545458e-06, + "loss": 0.7192, + "step": 25 + }, + { + "epoch": 0.0, + "learning_rate": 1.4772727272727275e-06, + "loss": 0.6846, + "step": 26 + }, + { + "epoch": 0.0, + "learning_rate": 1.5340909090909093e-06, + "loss": 0.6809, + "step": 27 + }, + { + "epoch": 0.0, + "learning_rate": 1.590909090909091e-06, + "loss": 0.6759, + "step": 28 + }, + { + "epoch": 0.0, + "learning_rate": 1.6477272727272728e-06, + "loss": 0.6561, + "step": 29 + }, + { + "epoch": 0.0, + "learning_rate": 1.7045454545454546e-06, + "loss": 0.6765, + "step": 30 + }, + { + "epoch": 0.0, + "learning_rate": 1.7613636363636365e-06, + "loss": 0.697, + "step": 31 + }, + { + "epoch": 0.0, + "learning_rate": 1.8181818181818183e-06, + "loss": 0.6814, + "step": 32 + }, + { + "epoch": 0.0, + "learning_rate": 1.8750000000000003e-06, + "loss": 0.6704, + "step": 33 + }, + { + "epoch": 0.0, + "learning_rate": 1.931818181818182e-06, + "loss": 0.6773, + "step": 34 + }, + { + "epoch": 0.0, + "learning_rate": 1.9886363636363638e-06, + "loss": 0.661, + "step": 35 + }, + { + "epoch": 0.0, + "learning_rate": 2.0454545454545457e-06, + "loss": 0.6677, + "step": 36 + }, + { + "epoch": 0.0, + "learning_rate": 2.1022727272727277e-06, + "loss": 0.6812, + "step": 37 + }, + { + "epoch": 0.0, + "learning_rate": 2.1590909090909092e-06, + "loss": 0.6701, + "step": 38 + }, + { + "epoch": 0.0, + "learning_rate": 2.2159090909090912e-06, + "loss": 0.6468, + "step": 39 + }, + { + "epoch": 0.0, + "learning_rate": 2.2727272727272728e-06, + "loss": 0.6397, + "step": 40 + }, + { + "epoch": 0.0, + "learning_rate": 2.3295454545454547e-06, + "loss": 0.6453, + "step": 41 + }, + { + "epoch": 0.0, + "learning_rate": 2.3863636363636367e-06, + "loss": 0.655, + "step": 42 + }, + { + "epoch": 0.0, + "learning_rate": 2.4431818181818182e-06, + "loss": 0.6258, + "step": 43 + }, + { + "epoch": 0.0, + "learning_rate": 2.5e-06, + "loss": 0.6211, + "step": 44 + }, + { + "epoch": 0.0, + "learning_rate": 2.556818181818182e-06, + "loss": 0.6227, + "step": 45 + }, + { + "epoch": 0.0, + "learning_rate": 2.6136363636363637e-06, + "loss": 0.6075, + "step": 46 + }, + { + "epoch": 0.0, + "learning_rate": 2.6704545454545457e-06, + "loss": 0.6292, + "step": 47 + }, + { + "epoch": 0.0, + "learning_rate": 2.7272727272727272e-06, + "loss": 0.635, + "step": 48 + }, + { + "epoch": 0.0, + "learning_rate": 2.784090909090909e-06, + "loss": 0.6098, + "step": 49 + }, + { + "epoch": 0.0, + "learning_rate": 2.8409090909090916e-06, + "loss": 0.6265, + "step": 50 + }, + { + "epoch": 0.0, + "learning_rate": 2.897727272727273e-06, + "loss": 0.6112, + "step": 51 + }, + { + "epoch": 0.0, + "learning_rate": 2.954545454545455e-06, + "loss": 0.6133, + "step": 52 + }, + { + "epoch": 0.0, + "learning_rate": 3.0113636363636366e-06, + "loss": 0.6205, + "step": 53 + }, + { + "epoch": 0.0, + "learning_rate": 3.0681818181818186e-06, + "loss": 0.6149, + "step": 54 + }, + { + "epoch": 0.0, + "learning_rate": 3.125e-06, + "loss": 0.6106, + "step": 55 + }, + { + "epoch": 0.0, + "learning_rate": 3.181818181818182e-06, + "loss": 0.6134, + "step": 56 + }, + { + "epoch": 0.0, + "learning_rate": 3.2386363636363637e-06, + "loss": 0.6199, + "step": 57 + }, + { + "epoch": 0.0, + "learning_rate": 3.2954545454545456e-06, + "loss": 0.6179, + "step": 58 + }, + { + "epoch": 0.01, + "learning_rate": 3.352272727272727e-06, + "loss": 0.6011, + "step": 59 + }, + { + "epoch": 0.01, + "learning_rate": 3.409090909090909e-06, + "loss": 0.6031, + "step": 60 + }, + { + "epoch": 0.01, + "learning_rate": 3.4659090909090915e-06, + "loss": 0.6275, + "step": 61 + }, + { + "epoch": 0.01, + "learning_rate": 3.522727272727273e-06, + "loss": 0.6043, + "step": 62 + }, + { + "epoch": 0.01, + "learning_rate": 3.579545454545455e-06, + "loss": 0.6014, + "step": 63 + }, + { + "epoch": 0.01, + "learning_rate": 3.6363636363636366e-06, + "loss": 0.6035, + "step": 64 + }, + { + "epoch": 0.01, + "learning_rate": 3.6931818181818186e-06, + "loss": 0.6114, + "step": 65 + }, + { + "epoch": 0.01, + "learning_rate": 3.7500000000000005e-06, + "loss": 0.6079, + "step": 66 + }, + { + "epoch": 0.01, + "learning_rate": 3.806818181818182e-06, + "loss": 0.6123, + "step": 67 + }, + { + "epoch": 0.01, + "learning_rate": 3.863636363636364e-06, + "loss": 0.6146, + "step": 68 + }, + { + "epoch": 0.01, + "learning_rate": 3.9204545454545456e-06, + "loss": 0.5762, + "step": 69 + }, + { + "epoch": 0.01, + "learning_rate": 3.9772727272727275e-06, + "loss": 0.6178, + "step": 70 + }, + { + "epoch": 0.01, + "learning_rate": 4.0340909090909095e-06, + "loss": 0.6147, + "step": 71 + }, + { + "epoch": 0.01, + "learning_rate": 4.0909090909090915e-06, + "loss": 0.5981, + "step": 72 + }, + { + "epoch": 0.01, + "learning_rate": 4.1477272727272734e-06, + "loss": 0.6093, + "step": 73 + }, + { + "epoch": 0.01, + "learning_rate": 4.204545454545455e-06, + "loss": 0.5902, + "step": 74 + }, + { + "epoch": 0.01, + "learning_rate": 4.2613636363636365e-06, + "loss": 0.5914, + "step": 75 + }, + { + "epoch": 0.01, + "learning_rate": 4.3181818181818185e-06, + "loss": 0.6028, + "step": 76 + }, + { + "epoch": 0.01, + "learning_rate": 4.3750000000000005e-06, + "loss": 0.6019, + "step": 77 + }, + { + "epoch": 0.01, + "learning_rate": 4.4318181818181824e-06, + "loss": 0.5854, + "step": 78 + }, + { + "epoch": 0.01, + "learning_rate": 4.4886363636363636e-06, + "loss": 0.5936, + "step": 79 + }, + { + "epoch": 0.01, + "learning_rate": 4.5454545454545455e-06, + "loss": 0.5891, + "step": 80 + }, + { + "epoch": 0.01, + "learning_rate": 4.6022727272727275e-06, + "loss": 0.5948, + "step": 81 + }, + { + "epoch": 0.01, + "learning_rate": 4.6590909090909095e-06, + "loss": 0.5685, + "step": 82 + }, + { + "epoch": 0.01, + "learning_rate": 4.715909090909091e-06, + "loss": 0.6131, + "step": 83 + }, + { + "epoch": 0.01, + "learning_rate": 4.772727272727273e-06, + "loss": 0.5894, + "step": 84 + }, + { + "epoch": 0.01, + "learning_rate": 4.829545454545455e-06, + "loss": 0.5825, + "step": 85 + }, + { + "epoch": 0.01, + "learning_rate": 4.8863636363636365e-06, + "loss": 0.581, + "step": 86 + }, + { + "epoch": 0.01, + "learning_rate": 4.9431818181818184e-06, + "loss": 0.5935, + "step": 87 + }, + { + "epoch": 0.01, + "learning_rate": 5e-06, + "loss": 0.5734, + "step": 88 + }, + { + "epoch": 0.01, + "learning_rate": 5.056818181818182e-06, + "loss": 0.5867, + "step": 89 + }, + { + "epoch": 0.01, + "learning_rate": 5.113636363636364e-06, + "loss": 0.5854, + "step": 90 + }, + { + "epoch": 0.01, + "learning_rate": 5.170454545454546e-06, + "loss": 0.5709, + "step": 91 + }, + { + "epoch": 0.01, + "learning_rate": 5.2272727272727274e-06, + "loss": 0.594, + "step": 92 + }, + { + "epoch": 0.01, + "learning_rate": 5.28409090909091e-06, + "loss": 0.6087, + "step": 93 + }, + { + "epoch": 0.01, + "learning_rate": 5.340909090909091e-06, + "loss": 0.5841, + "step": 94 + }, + { + "epoch": 0.01, + "learning_rate": 5.397727272727273e-06, + "loss": 0.5794, + "step": 95 + }, + { + "epoch": 0.01, + "learning_rate": 5.4545454545454545e-06, + "loss": 0.6066, + "step": 96 + }, + { + "epoch": 0.01, + "learning_rate": 5.511363636363637e-06, + "loss": 0.6109, + "step": 97 + }, + { + "epoch": 0.01, + "learning_rate": 5.568181818181818e-06, + "loss": 0.5983, + "step": 98 + }, + { + "epoch": 0.01, + "learning_rate": 5.625e-06, + "loss": 0.5796, + "step": 99 + }, + { + "epoch": 0.01, + "learning_rate": 5.681818181818183e-06, + "loss": 0.5862, + "step": 100 + }, + { + "epoch": 0.01, + "learning_rate": 5.738636363636364e-06, + "loss": 0.5716, + "step": 101 + }, + { + "epoch": 0.01, + "learning_rate": 5.795454545454546e-06, + "loss": 0.6007, + "step": 102 + }, + { + "epoch": 0.01, + "learning_rate": 5.852272727272727e-06, + "loss": 0.5913, + "step": 103 + }, + { + "epoch": 0.01, + "learning_rate": 5.90909090909091e-06, + "loss": 0.5739, + "step": 104 + }, + { + "epoch": 0.01, + "learning_rate": 5.965909090909091e-06, + "loss": 0.5694, + "step": 105 + }, + { + "epoch": 0.01, + "learning_rate": 6.022727272727273e-06, + "loss": 0.5812, + "step": 106 + }, + { + "epoch": 0.01, + "learning_rate": 6.079545454545454e-06, + "loss": 0.5785, + "step": 107 + }, + { + "epoch": 0.01, + "learning_rate": 6.136363636363637e-06, + "loss": 0.5652, + "step": 108 + }, + { + "epoch": 0.01, + "learning_rate": 6.193181818181818e-06, + "loss": 0.6019, + "step": 109 + }, + { + "epoch": 0.01, + "learning_rate": 6.25e-06, + "loss": 0.5777, + "step": 110 + }, + { + "epoch": 0.01, + "learning_rate": 6.306818181818183e-06, + "loss": 0.5536, + "step": 111 + }, + { + "epoch": 0.01, + "learning_rate": 6.363636363636364e-06, + "loss": 0.5866, + "step": 112 + }, + { + "epoch": 0.01, + "learning_rate": 6.420454545454546e-06, + "loss": 0.5716, + "step": 113 + }, + { + "epoch": 0.01, + "learning_rate": 6.477272727272727e-06, + "loss": 0.575, + "step": 114 + }, + { + "epoch": 0.01, + "learning_rate": 6.53409090909091e-06, + "loss": 0.5753, + "step": 115 + }, + { + "epoch": 0.01, + "learning_rate": 6.590909090909091e-06, + "loss": 0.5849, + "step": 116 + }, + { + "epoch": 0.01, + "learning_rate": 6.647727272727273e-06, + "loss": 0.5734, + "step": 117 + }, + { + "epoch": 0.01, + "learning_rate": 6.704545454545454e-06, + "loss": 0.5642, + "step": 118 + }, + { + "epoch": 0.01, + "learning_rate": 6.761363636363637e-06, + "loss": 0.5778, + "step": 119 + }, + { + "epoch": 0.01, + "learning_rate": 6.818181818181818e-06, + "loss": 0.584, + "step": 120 + }, + { + "epoch": 0.01, + "learning_rate": 6.875e-06, + "loss": 0.5705, + "step": 121 + }, + { + "epoch": 0.01, + "learning_rate": 6.931818181818183e-06, + "loss": 0.5684, + "step": 122 + }, + { + "epoch": 0.01, + "learning_rate": 6.988636363636364e-06, + "loss": 0.5613, + "step": 123 + }, + { + "epoch": 0.01, + "learning_rate": 7.045454545454546e-06, + "loss": 0.5571, + "step": 124 + }, + { + "epoch": 0.01, + "learning_rate": 7.102272727272727e-06, + "loss": 0.5713, + "step": 125 + }, + { + "epoch": 0.01, + "learning_rate": 7.15909090909091e-06, + "loss": 0.575, + "step": 126 + }, + { + "epoch": 0.01, + "learning_rate": 7.215909090909091e-06, + "loss": 0.5605, + "step": 127 + }, + { + "epoch": 0.01, + "learning_rate": 7.272727272727273e-06, + "loss": 0.5699, + "step": 128 + }, + { + "epoch": 0.01, + "learning_rate": 7.329545454545455e-06, + "loss": 0.5753, + "step": 129 + }, + { + "epoch": 0.01, + "learning_rate": 7.386363636363637e-06, + "loss": 0.581, + "step": 130 + }, + { + "epoch": 0.01, + "learning_rate": 7.443181818181818e-06, + "loss": 0.5872, + "step": 131 + }, + { + "epoch": 0.01, + "learning_rate": 7.500000000000001e-06, + "loss": 0.5759, + "step": 132 + }, + { + "epoch": 0.01, + "learning_rate": 7.556818181818183e-06, + "loss": 0.5758, + "step": 133 + }, + { + "epoch": 0.01, + "learning_rate": 7.613636363636364e-06, + "loss": 0.5758, + "step": 134 + }, + { + "epoch": 0.01, + "learning_rate": 7.670454545454547e-06, + "loss": 0.5789, + "step": 135 + }, + { + "epoch": 0.01, + "learning_rate": 7.727272727272727e-06, + "loss": 0.5654, + "step": 136 + }, + { + "epoch": 0.01, + "learning_rate": 7.784090909090911e-06, + "loss": 0.5738, + "step": 137 + }, + { + "epoch": 0.01, + "learning_rate": 7.840909090909091e-06, + "loss": 0.5719, + "step": 138 + }, + { + "epoch": 0.01, + "learning_rate": 7.897727272727273e-06, + "loss": 0.5668, + "step": 139 + }, + { + "epoch": 0.01, + "learning_rate": 7.954545454545455e-06, + "loss": 0.5623, + "step": 140 + }, + { + "epoch": 0.01, + "learning_rate": 8.011363636363637e-06, + "loss": 0.5725, + "step": 141 + }, + { + "epoch": 0.01, + "learning_rate": 8.068181818181819e-06, + "loss": 0.5783, + "step": 142 + }, + { + "epoch": 0.01, + "learning_rate": 8.125000000000001e-06, + "loss": 0.5622, + "step": 143 + }, + { + "epoch": 0.01, + "learning_rate": 8.181818181818183e-06, + "loss": 0.5735, + "step": 144 + }, + { + "epoch": 0.01, + "learning_rate": 8.238636363636365e-06, + "loss": 0.5636, + "step": 145 + }, + { + "epoch": 0.01, + "learning_rate": 8.295454545454547e-06, + "loss": 0.5552, + "step": 146 + }, + { + "epoch": 0.01, + "learning_rate": 8.352272727272727e-06, + "loss": 0.5744, + "step": 147 + }, + { + "epoch": 0.01, + "learning_rate": 8.40909090909091e-06, + "loss": 0.5676, + "step": 148 + }, + { + "epoch": 0.01, + "learning_rate": 8.465909090909091e-06, + "loss": 0.5992, + "step": 149 + }, + { + "epoch": 0.01, + "learning_rate": 8.522727272727273e-06, + "loss": 0.555, + "step": 150 + }, + { + "epoch": 0.01, + "learning_rate": 8.579545454545455e-06, + "loss": 0.5702, + "step": 151 + }, + { + "epoch": 0.01, + "learning_rate": 8.636363636363637e-06, + "loss": 0.5572, + "step": 152 + }, + { + "epoch": 0.01, + "learning_rate": 8.693181818181819e-06, + "loss": 0.5449, + "step": 153 + }, + { + "epoch": 0.01, + "learning_rate": 8.750000000000001e-06, + "loss": 0.5715, + "step": 154 + }, + { + "epoch": 0.01, + "learning_rate": 8.806818181818183e-06, + "loss": 0.562, + "step": 155 + }, + { + "epoch": 0.01, + "learning_rate": 8.863636363636365e-06, + "loss": 0.5682, + "step": 156 + }, + { + "epoch": 0.01, + "learning_rate": 8.920454545454547e-06, + "loss": 0.5532, + "step": 157 + }, + { + "epoch": 0.01, + "learning_rate": 8.977272727272727e-06, + "loss": 0.5642, + "step": 158 + }, + { + "epoch": 0.01, + "learning_rate": 9.03409090909091e-06, + "loss": 0.5429, + "step": 159 + }, + { + "epoch": 0.01, + "learning_rate": 9.090909090909091e-06, + "loss": 0.5696, + "step": 160 + }, + { + "epoch": 0.01, + "learning_rate": 9.147727272727273e-06, + "loss": 0.5438, + "step": 161 + }, + { + "epoch": 0.01, + "learning_rate": 9.204545454545455e-06, + "loss": 0.5495, + "step": 162 + }, + { + "epoch": 0.01, + "learning_rate": 9.261363636363637e-06, + "loss": 0.5602, + "step": 163 + }, + { + "epoch": 0.01, + "learning_rate": 9.318181818181819e-06, + "loss": 0.553, + "step": 164 + }, + { + "epoch": 0.01, + "learning_rate": 9.375000000000001e-06, + "loss": 0.5841, + "step": 165 + }, + { + "epoch": 0.01, + "learning_rate": 9.431818181818183e-06, + "loss": 0.543, + "step": 166 + }, + { + "epoch": 0.01, + "learning_rate": 9.488636363636365e-06, + "loss": 0.5576, + "step": 167 + }, + { + "epoch": 0.01, + "learning_rate": 9.545454545454547e-06, + "loss": 0.5526, + "step": 168 + }, + { + "epoch": 0.01, + "learning_rate": 9.602272727272727e-06, + "loss": 0.5529, + "step": 169 + }, + { + "epoch": 0.01, + "learning_rate": 9.65909090909091e-06, + "loss": 0.5739, + "step": 170 + }, + { + "epoch": 0.01, + "learning_rate": 9.715909090909091e-06, + "loss": 0.5573, + "step": 171 + }, + { + "epoch": 0.01, + "learning_rate": 9.772727272727273e-06, + "loss": 0.5462, + "step": 172 + }, + { + "epoch": 0.01, + "learning_rate": 9.829545454545455e-06, + "loss": 0.5636, + "step": 173 + }, + { + "epoch": 0.01, + "learning_rate": 9.886363636363637e-06, + "loss": 0.5692, + "step": 174 + }, + { + "epoch": 0.01, + "learning_rate": 9.943181818181819e-06, + "loss": 0.5616, + "step": 175 + }, + { + "epoch": 0.02, + "learning_rate": 1e-05, + "loss": 0.5679, + "step": 176 + }, + { + "epoch": 0.02, + "learning_rate": 1.0056818181818183e-05, + "loss": 0.5425, + "step": 177 + }, + { + "epoch": 0.02, + "learning_rate": 1.0113636363636365e-05, + "loss": 0.5566, + "step": 178 + }, + { + "epoch": 0.02, + "learning_rate": 1.0170454545454547e-05, + "loss": 0.5492, + "step": 179 + }, + { + "epoch": 0.02, + "learning_rate": 1.0227272727272729e-05, + "loss": 0.5442, + "step": 180 + }, + { + "epoch": 0.02, + "learning_rate": 1.0284090909090909e-05, + "loss": 0.5288, + "step": 181 + }, + { + "epoch": 0.02, + "learning_rate": 1.0340909090909093e-05, + "loss": 0.5405, + "step": 182 + }, + { + "epoch": 0.02, + "learning_rate": 1.0397727272727275e-05, + "loss": 0.558, + "step": 183 + }, + { + "epoch": 0.02, + "learning_rate": 1.0454545454545455e-05, + "loss": 0.5499, + "step": 184 + }, + { + "epoch": 0.02, + "learning_rate": 1.0511363636363637e-05, + "loss": 0.5433, + "step": 185 + }, + { + "epoch": 0.02, + "learning_rate": 1.056818181818182e-05, + "loss": 0.5428, + "step": 186 + }, + { + "epoch": 0.02, + "learning_rate": 1.0625e-05, + "loss": 0.5537, + "step": 187 + }, + { + "epoch": 0.02, + "learning_rate": 1.0681818181818183e-05, + "loss": 0.5635, + "step": 188 + }, + { + "epoch": 0.02, + "learning_rate": 1.0738636363636365e-05, + "loss": 0.537, + "step": 189 + }, + { + "epoch": 0.02, + "learning_rate": 1.0795454545454547e-05, + "loss": 0.5639, + "step": 190 + }, + { + "epoch": 0.02, + "learning_rate": 1.0852272727272729e-05, + "loss": 0.5481, + "step": 191 + }, + { + "epoch": 0.02, + "learning_rate": 1.0909090909090909e-05, + "loss": 0.547, + "step": 192 + }, + { + "epoch": 0.02, + "learning_rate": 1.0965909090909093e-05, + "loss": 0.5489, + "step": 193 + }, + { + "epoch": 0.02, + "learning_rate": 1.1022727272727275e-05, + "loss": 0.5451, + "step": 194 + }, + { + "epoch": 0.02, + "learning_rate": 1.1079545454545455e-05, + "loss": 0.5368, + "step": 195 + }, + { + "epoch": 0.02, + "learning_rate": 1.1136363636363637e-05, + "loss": 0.5366, + "step": 196 + }, + { + "epoch": 0.02, + "learning_rate": 1.119318181818182e-05, + "loss": 0.5548, + "step": 197 + }, + { + "epoch": 0.02, + "learning_rate": 1.125e-05, + "loss": 0.5475, + "step": 198 + }, + { + "epoch": 0.02, + "learning_rate": 1.1306818181818183e-05, + "loss": 0.5395, + "step": 199 + }, + { + "epoch": 0.02, + "learning_rate": 1.1363636363636366e-05, + "loss": 0.5397, + "step": 200 + }, + { + "epoch": 0.02, + "learning_rate": 1.1420454545454547e-05, + "loss": 0.5541, + "step": 201 + }, + { + "epoch": 0.02, + "learning_rate": 1.1477272727272729e-05, + "loss": 0.5561, + "step": 202 + }, + { + "epoch": 0.02, + "learning_rate": 1.1534090909090909e-05, + "loss": 0.5546, + "step": 203 + }, + { + "epoch": 0.02, + "learning_rate": 1.1590909090909093e-05, + "loss": 0.5613, + "step": 204 + }, + { + "epoch": 0.02, + "learning_rate": 1.1647727272727274e-05, + "loss": 0.5476, + "step": 205 + }, + { + "epoch": 0.02, + "learning_rate": 1.1704545454545455e-05, + "loss": 0.5428, + "step": 206 + }, + { + "epoch": 0.02, + "learning_rate": 1.1761363636363637e-05, + "loss": 0.5587, + "step": 207 + }, + { + "epoch": 0.02, + "learning_rate": 1.181818181818182e-05, + "loss": 0.5443, + "step": 208 + }, + { + "epoch": 0.02, + "learning_rate": 1.1875e-05, + "loss": 0.5538, + "step": 209 + }, + { + "epoch": 0.02, + "learning_rate": 1.1931818181818183e-05, + "loss": 0.5526, + "step": 210 + }, + { + "epoch": 0.02, + "learning_rate": 1.1988636363636366e-05, + "loss": 0.5321, + "step": 211 + }, + { + "epoch": 0.02, + "learning_rate": 1.2045454545454547e-05, + "loss": 0.5506, + "step": 212 + }, + { + "epoch": 0.02, + "learning_rate": 1.2102272727272729e-05, + "loss": 0.5487, + "step": 213 + }, + { + "epoch": 0.02, + "learning_rate": 1.2159090909090909e-05, + "loss": 0.5541, + "step": 214 + }, + { + "epoch": 0.02, + "learning_rate": 1.2215909090909092e-05, + "loss": 0.5522, + "step": 215 + }, + { + "epoch": 0.02, + "learning_rate": 1.2272727272727274e-05, + "loss": 0.5632, + "step": 216 + }, + { + "epoch": 0.02, + "learning_rate": 1.2329545454545455e-05, + "loss": 0.5492, + "step": 217 + }, + { + "epoch": 0.02, + "learning_rate": 1.2386363636363637e-05, + "loss": 0.5523, + "step": 218 + }, + { + "epoch": 0.02, + "learning_rate": 1.244318181818182e-05, + "loss": 0.5413, + "step": 219 + }, + { + "epoch": 0.02, + "learning_rate": 1.25e-05, + "loss": 0.5394, + "step": 220 + }, + { + "epoch": 0.02, + "learning_rate": 1.2556818181818183e-05, + "loss": 0.5223, + "step": 221 + }, + { + "epoch": 0.02, + "learning_rate": 1.2613636363636366e-05, + "loss": 0.5449, + "step": 222 + }, + { + "epoch": 0.02, + "learning_rate": 1.2670454545454547e-05, + "loss": 0.5536, + "step": 223 + }, + { + "epoch": 0.02, + "learning_rate": 1.2727272727272728e-05, + "loss": 0.5287, + "step": 224 + }, + { + "epoch": 0.02, + "learning_rate": 1.2784090909090909e-05, + "loss": 0.5495, + "step": 225 + }, + { + "epoch": 0.02, + "learning_rate": 1.2840909090909092e-05, + "loss": 0.5416, + "step": 226 + }, + { + "epoch": 0.02, + "learning_rate": 1.2897727272727274e-05, + "loss": 0.5526, + "step": 227 + }, + { + "epoch": 0.02, + "learning_rate": 1.2954545454545455e-05, + "loss": 0.5432, + "step": 228 + }, + { + "epoch": 0.02, + "learning_rate": 1.3011363636363637e-05, + "loss": 0.5649, + "step": 229 + }, + { + "epoch": 0.02, + "learning_rate": 1.306818181818182e-05, + "loss": 0.5212, + "step": 230 + }, + { + "epoch": 0.02, + "learning_rate": 1.3125e-05, + "loss": 0.5274, + "step": 231 + }, + { + "epoch": 0.02, + "learning_rate": 1.3181818181818183e-05, + "loss": 0.5552, + "step": 232 + }, + { + "epoch": 0.02, + "learning_rate": 1.3238636363636366e-05, + "loss": 0.5465, + "step": 233 + }, + { + "epoch": 0.02, + "learning_rate": 1.3295454545454546e-05, + "loss": 0.5473, + "step": 234 + }, + { + "epoch": 0.02, + "learning_rate": 1.3352272727272728e-05, + "loss": 0.5296, + "step": 235 + }, + { + "epoch": 0.02, + "learning_rate": 1.3409090909090909e-05, + "loss": 0.5506, + "step": 236 + }, + { + "epoch": 0.02, + "learning_rate": 1.3465909090909092e-05, + "loss": 0.5579, + "step": 237 + }, + { + "epoch": 0.02, + "learning_rate": 1.3522727272727274e-05, + "loss": 0.5562, + "step": 238 + }, + { + "epoch": 0.02, + "learning_rate": 1.3579545454545455e-05, + "loss": 0.5507, + "step": 239 + }, + { + "epoch": 0.02, + "learning_rate": 1.3636363636363637e-05, + "loss": 0.544, + "step": 240 + }, + { + "epoch": 0.02, + "learning_rate": 1.369318181818182e-05, + "loss": 0.5348, + "step": 241 + }, + { + "epoch": 0.02, + "learning_rate": 1.375e-05, + "loss": 0.5234, + "step": 242 + }, + { + "epoch": 0.02, + "learning_rate": 1.3806818181818182e-05, + "loss": 0.5447, + "step": 243 + }, + { + "epoch": 0.02, + "learning_rate": 1.3863636363636366e-05, + "loss": 0.5387, + "step": 244 + }, + { + "epoch": 0.02, + "learning_rate": 1.3920454545454546e-05, + "loss": 0.5563, + "step": 245 + }, + { + "epoch": 0.02, + "learning_rate": 1.3977272727272728e-05, + "loss": 0.5345, + "step": 246 + }, + { + "epoch": 0.02, + "learning_rate": 1.4034090909090909e-05, + "loss": 0.5547, + "step": 247 + }, + { + "epoch": 0.02, + "learning_rate": 1.4090909090909092e-05, + "loss": 0.5493, + "step": 248 + }, + { + "epoch": 0.02, + "learning_rate": 1.4147727272727274e-05, + "loss": 0.5449, + "step": 249 + }, + { + "epoch": 0.02, + "learning_rate": 1.4204545454545455e-05, + "loss": 0.5397, + "step": 250 + }, + { + "epoch": 0.02, + "learning_rate": 1.4261363636363637e-05, + "loss": 0.5312, + "step": 251 + }, + { + "epoch": 0.02, + "learning_rate": 1.431818181818182e-05, + "loss": 0.5437, + "step": 252 + }, + { + "epoch": 0.02, + "learning_rate": 1.4375e-05, + "loss": 0.5498, + "step": 253 + }, + { + "epoch": 0.02, + "learning_rate": 1.4431818181818182e-05, + "loss": 0.5212, + "step": 254 + }, + { + "epoch": 0.02, + "learning_rate": 1.4488636363636366e-05, + "loss": 0.5433, + "step": 255 + }, + { + "epoch": 0.02, + "learning_rate": 1.4545454545454546e-05, + "loss": 0.5408, + "step": 256 + }, + { + "epoch": 0.02, + "learning_rate": 1.4602272727272728e-05, + "loss": 0.5386, + "step": 257 + }, + { + "epoch": 0.02, + "learning_rate": 1.465909090909091e-05, + "loss": 0.5239, + "step": 258 + }, + { + "epoch": 0.02, + "learning_rate": 1.4715909090909092e-05, + "loss": 0.55, + "step": 259 + }, + { + "epoch": 0.02, + "learning_rate": 1.4772727272727274e-05, + "loss": 0.5381, + "step": 260 + }, + { + "epoch": 0.02, + "learning_rate": 1.4829545454545456e-05, + "loss": 0.5224, + "step": 261 + }, + { + "epoch": 0.02, + "learning_rate": 1.4886363636363636e-05, + "loss": 0.5501, + "step": 262 + }, + { + "epoch": 0.02, + "learning_rate": 1.494318181818182e-05, + "loss": 0.5296, + "step": 263 + }, + { + "epoch": 0.02, + "learning_rate": 1.5000000000000002e-05, + "loss": 0.5506, + "step": 264 + }, + { + "epoch": 0.02, + "learning_rate": 1.5056818181818182e-05, + "loss": 0.5325, + "step": 265 + }, + { + "epoch": 0.02, + "learning_rate": 1.5113636363636366e-05, + "loss": 0.5264, + "step": 266 + }, + { + "epoch": 0.02, + "learning_rate": 1.5170454545454546e-05, + "loss": 0.5438, + "step": 267 + }, + { + "epoch": 0.02, + "learning_rate": 1.5227272727272728e-05, + "loss": 0.5364, + "step": 268 + }, + { + "epoch": 0.02, + "learning_rate": 1.528409090909091e-05, + "loss": 0.5476, + "step": 269 + }, + { + "epoch": 0.02, + "learning_rate": 1.5340909090909094e-05, + "loss": 0.5346, + "step": 270 + }, + { + "epoch": 0.02, + "learning_rate": 1.5397727272727276e-05, + "loss": 0.5485, + "step": 271 + }, + { + "epoch": 0.02, + "learning_rate": 1.5454545454545454e-05, + "loss": 0.5413, + "step": 272 + }, + { + "epoch": 0.02, + "learning_rate": 1.5511363636363636e-05, + "loss": 0.548, + "step": 273 + }, + { + "epoch": 0.02, + "learning_rate": 1.5568181818181822e-05, + "loss": 0.5313, + "step": 274 + }, + { + "epoch": 0.02, + "learning_rate": 1.5625e-05, + "loss": 0.5486, + "step": 275 + }, + { + "epoch": 0.02, + "learning_rate": 1.5681818181818182e-05, + "loss": 0.5158, + "step": 276 + }, + { + "epoch": 0.02, + "learning_rate": 1.5738636363636364e-05, + "loss": 0.5346, + "step": 277 + }, + { + "epoch": 0.02, + "learning_rate": 1.5795454545454546e-05, + "loss": 0.5429, + "step": 278 + }, + { + "epoch": 0.02, + "learning_rate": 1.5852272727272728e-05, + "loss": 0.5371, + "step": 279 + }, + { + "epoch": 0.02, + "learning_rate": 1.590909090909091e-05, + "loss": 0.5517, + "step": 280 + }, + { + "epoch": 0.02, + "learning_rate": 1.5965909090909092e-05, + "loss": 0.5342, + "step": 281 + }, + { + "epoch": 0.02, + "learning_rate": 1.6022727272727274e-05, + "loss": 0.5546, + "step": 282 + }, + { + "epoch": 0.02, + "learning_rate": 1.6079545454545456e-05, + "loss": 0.5241, + "step": 283 + }, + { + "epoch": 0.02, + "learning_rate": 1.6136363636363638e-05, + "loss": 0.5701, + "step": 284 + }, + { + "epoch": 0.02, + "learning_rate": 1.619318181818182e-05, + "loss": 0.5336, + "step": 285 + }, + { + "epoch": 0.02, + "learning_rate": 1.6250000000000002e-05, + "loss": 0.5454, + "step": 286 + }, + { + "epoch": 0.02, + "learning_rate": 1.6306818181818184e-05, + "loss": 0.5445, + "step": 287 + }, + { + "epoch": 0.02, + "learning_rate": 1.6363636363636366e-05, + "loss": 0.525, + "step": 288 + }, + { + "epoch": 0.02, + "learning_rate": 1.6420454545454548e-05, + "loss": 0.5247, + "step": 289 + }, + { + "epoch": 0.02, + "learning_rate": 1.647727272727273e-05, + "loss": 0.54, + "step": 290 + }, + { + "epoch": 0.02, + "learning_rate": 1.653409090909091e-05, + "loss": 0.5535, + "step": 291 + }, + { + "epoch": 0.02, + "learning_rate": 1.6590909090909094e-05, + "loss": 0.5158, + "step": 292 + }, + { + "epoch": 0.02, + "learning_rate": 1.6647727272727276e-05, + "loss": 0.5402, + "step": 293 + }, + { + "epoch": 0.03, + "learning_rate": 1.6704545454545454e-05, + "loss": 0.5376, + "step": 294 + }, + { + "epoch": 0.03, + "learning_rate": 1.6761363636363636e-05, + "loss": 0.5668, + "step": 295 + }, + { + "epoch": 0.03, + "learning_rate": 1.681818181818182e-05, + "loss": 0.5181, + "step": 296 + }, + { + "epoch": 0.03, + "learning_rate": 1.6875e-05, + "loss": 0.5252, + "step": 297 + }, + { + "epoch": 0.03, + "learning_rate": 1.6931818181818182e-05, + "loss": 0.5398, + "step": 298 + }, + { + "epoch": 0.03, + "learning_rate": 1.6988636363636368e-05, + "loss": 0.5433, + "step": 299 + }, + { + "epoch": 0.03, + "learning_rate": 1.7045454545454546e-05, + "loss": 0.5473, + "step": 300 + }, + { + "epoch": 0.03, + "learning_rate": 1.7102272727272728e-05, + "loss": 0.5447, + "step": 301 + }, + { + "epoch": 0.03, + "learning_rate": 1.715909090909091e-05, + "loss": 0.5267, + "step": 302 + }, + { + "epoch": 0.03, + "learning_rate": 1.7215909090909092e-05, + "loss": 0.546, + "step": 303 + }, + { + "epoch": 0.03, + "learning_rate": 1.7272727272727274e-05, + "loss": 0.5532, + "step": 304 + }, + { + "epoch": 0.03, + "learning_rate": 1.7329545454545456e-05, + "loss": 0.5355, + "step": 305 + }, + { + "epoch": 0.03, + "learning_rate": 1.7386363636363638e-05, + "loss": 0.5337, + "step": 306 + }, + { + "epoch": 0.03, + "learning_rate": 1.744318181818182e-05, + "loss": 0.5344, + "step": 307 + }, + { + "epoch": 0.03, + "learning_rate": 1.7500000000000002e-05, + "loss": 0.5528, + "step": 308 + }, + { + "epoch": 0.03, + "learning_rate": 1.7556818181818184e-05, + "loss": 0.529, + "step": 309 + }, + { + "epoch": 0.03, + "learning_rate": 1.7613636363636366e-05, + "loss": 0.5664, + "step": 310 + }, + { + "epoch": 0.03, + "learning_rate": 1.7670454545454548e-05, + "loss": 0.5523, + "step": 311 + }, + { + "epoch": 0.03, + "learning_rate": 1.772727272727273e-05, + "loss": 0.5322, + "step": 312 + }, + { + "epoch": 0.03, + "learning_rate": 1.7784090909090908e-05, + "loss": 0.5412, + "step": 313 + }, + { + "epoch": 0.03, + "learning_rate": 1.7840909090909094e-05, + "loss": 0.5576, + "step": 314 + }, + { + "epoch": 0.03, + "learning_rate": 1.7897727272727276e-05, + "loss": 0.5157, + "step": 315 + }, + { + "epoch": 0.03, + "learning_rate": 1.7954545454545454e-05, + "loss": 0.5177, + "step": 316 + }, + { + "epoch": 0.03, + "learning_rate": 1.8011363636363636e-05, + "loss": 0.5492, + "step": 317 + }, + { + "epoch": 0.03, + "learning_rate": 1.806818181818182e-05, + "loss": 0.538, + "step": 318 + }, + { + "epoch": 0.03, + "learning_rate": 1.8125e-05, + "loss": 0.5347, + "step": 319 + }, + { + "epoch": 0.03, + "learning_rate": 1.8181818181818182e-05, + "loss": 0.5379, + "step": 320 + }, + { + "epoch": 0.03, + "learning_rate": 1.8238636363636367e-05, + "loss": 0.5498, + "step": 321 + }, + { + "epoch": 0.03, + "learning_rate": 1.8295454545454546e-05, + "loss": 0.5177, + "step": 322 + }, + { + "epoch": 0.03, + "learning_rate": 1.8352272727272728e-05, + "loss": 0.5479, + "step": 323 + }, + { + "epoch": 0.03, + "learning_rate": 1.840909090909091e-05, + "loss": 0.5348, + "step": 324 + }, + { + "epoch": 0.03, + "learning_rate": 1.8465909090909092e-05, + "loss": 0.5255, + "step": 325 + }, + { + "epoch": 0.03, + "learning_rate": 1.8522727272727274e-05, + "loss": 0.5329, + "step": 326 + }, + { + "epoch": 0.03, + "learning_rate": 1.8579545454545456e-05, + "loss": 0.5169, + "step": 327 + }, + { + "epoch": 0.03, + "learning_rate": 1.8636363636363638e-05, + "loss": 0.5337, + "step": 328 + }, + { + "epoch": 0.03, + "learning_rate": 1.869318181818182e-05, + "loss": 0.5213, + "step": 329 + }, + { + "epoch": 0.03, + "learning_rate": 1.8750000000000002e-05, + "loss": 0.5306, + "step": 330 + }, + { + "epoch": 0.03, + "learning_rate": 1.8806818181818184e-05, + "loss": 0.5152, + "step": 331 + }, + { + "epoch": 0.03, + "learning_rate": 1.8863636363636366e-05, + "loss": 0.5274, + "step": 332 + }, + { + "epoch": 0.03, + "learning_rate": 1.8920454545454548e-05, + "loss": 0.5655, + "step": 333 + }, + { + "epoch": 0.03, + "learning_rate": 1.897727272727273e-05, + "loss": 0.5333, + "step": 334 + }, + { + "epoch": 0.03, + "learning_rate": 1.9034090909090908e-05, + "loss": 0.539, + "step": 335 + }, + { + "epoch": 0.03, + "learning_rate": 1.9090909090909094e-05, + "loss": 0.5406, + "step": 336 + }, + { + "epoch": 0.03, + "learning_rate": 1.9147727272727276e-05, + "loss": 0.5225, + "step": 337 + }, + { + "epoch": 0.03, + "learning_rate": 1.9204545454545454e-05, + "loss": 0.5217, + "step": 338 + }, + { + "epoch": 0.03, + "learning_rate": 1.9261363636363636e-05, + "loss": 0.5411, + "step": 339 + }, + { + "epoch": 0.03, + "learning_rate": 1.931818181818182e-05, + "loss": 0.5475, + "step": 340 + }, + { + "epoch": 0.03, + "learning_rate": 1.9375e-05, + "loss": 0.5134, + "step": 341 + }, + { + "epoch": 0.03, + "learning_rate": 1.9431818181818182e-05, + "loss": 0.53, + "step": 342 + }, + { + "epoch": 0.03, + "learning_rate": 1.9488636363636367e-05, + "loss": 0.525, + "step": 343 + }, + { + "epoch": 0.03, + "learning_rate": 1.9545454545454546e-05, + "loss": 0.5207, + "step": 344 + }, + { + "epoch": 0.03, + "learning_rate": 1.9602272727272728e-05, + "loss": 0.533, + "step": 345 + }, + { + "epoch": 0.03, + "learning_rate": 1.965909090909091e-05, + "loss": 0.537, + "step": 346 + }, + { + "epoch": 0.03, + "learning_rate": 1.9715909090909092e-05, + "loss": 0.5257, + "step": 347 + }, + { + "epoch": 0.03, + "learning_rate": 1.9772727272727274e-05, + "loss": 0.5183, + "step": 348 + }, + { + "epoch": 0.03, + "learning_rate": 1.9829545454545456e-05, + "loss": 0.5568, + "step": 349 + }, + { + "epoch": 0.03, + "learning_rate": 1.9886363636363638e-05, + "loss": 0.5157, + "step": 350 + }, + { + "epoch": 0.03, + "learning_rate": 1.994318181818182e-05, + "loss": 0.5258, + "step": 351 + }, + { + "epoch": 0.03, + "learning_rate": 2e-05, + "loss": 0.5288, + "step": 352 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999999618679128e-05, + "loss": 0.5422, + "step": 353 + }, + { + "epoch": 0.03, + "learning_rate": 1.999999847471653e-05, + "loss": 0.5247, + "step": 354 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999996568112307e-05, + "loss": 0.5432, + "step": 355 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999993898866596e-05, + "loss": 0.5414, + "step": 356 + }, + { + "epoch": 0.03, + "learning_rate": 1.99999904669796e-05, + "loss": 0.5223, + "step": 357 + }, + { + "epoch": 0.03, + "learning_rate": 1.999998627245158e-05, + "loss": 0.5115, + "step": 358 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999981315282857e-05, + "loss": 0.5522, + "step": 359 + }, + { + "epoch": 0.03, + "learning_rate": 1.999997559547381e-05, + "loss": 0.5417, + "step": 360 + }, + { + "epoch": 0.03, + "learning_rate": 1.999996911302488e-05, + "loss": 0.5268, + "step": 361 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999961867936556e-05, + "loss": 0.5403, + "step": 362 + }, + { + "epoch": 0.03, + "learning_rate": 1.999995386020939e-05, + "loss": 0.5553, + "step": 363 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999945089843996e-05, + "loss": 0.5201, + "step": 364 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999935556841035e-05, + "loss": 0.5359, + "step": 365 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999925261201247e-05, + "loss": 0.5344, + "step": 366 + }, + { + "epoch": 0.03, + "learning_rate": 1.999991420292541e-05, + "loss": 0.5377, + "step": 367 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999902382014363e-05, + "loss": 0.5263, + "step": 368 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999889798469016e-05, + "loss": 0.5297, + "step": 369 + }, + { + "epoch": 0.03, + "learning_rate": 1.999987645229032e-05, + "loss": 0.5363, + "step": 370 + }, + { + "epoch": 0.03, + "learning_rate": 1.99998623434793e-05, + "loss": 0.5441, + "step": 371 + }, + { + "epoch": 0.03, + "learning_rate": 1.999984747203703e-05, + "loss": 0.5328, + "step": 372 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999831837964646e-05, + "loss": 0.5177, + "step": 373 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999815441263334e-05, + "loss": 0.5125, + "step": 374 + }, + { + "epoch": 0.03, + "learning_rate": 1.999979828193435e-05, + "loss": 0.5295, + "step": 375 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999780359979e-05, + "loss": 0.5429, + "step": 376 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999761675398656e-05, + "loss": 0.5469, + "step": 377 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999742228194734e-05, + "loss": 0.5435, + "step": 378 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999722018368724e-05, + "loss": 0.5163, + "step": 379 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999701045922163e-05, + "loss": 0.5089, + "step": 380 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999679310856657e-05, + "loss": 0.5421, + "step": 381 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999656813173856e-05, + "loss": 0.5194, + "step": 382 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999633552875482e-05, + "loss": 0.5188, + "step": 383 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999609529963303e-05, + "loss": 0.5394, + "step": 384 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999584744439155e-05, + "loss": 0.5088, + "step": 385 + }, + { + "epoch": 0.03, + "learning_rate": 1.999955919630493e-05, + "loss": 0.5371, + "step": 386 + }, + { + "epoch": 0.03, + "learning_rate": 1.999953288556257e-05, + "loss": 0.5251, + "step": 387 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999505812214087e-05, + "loss": 0.5514, + "step": 388 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999477976261543e-05, + "loss": 0.5257, + "step": 389 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999449377707063e-05, + "loss": 0.5168, + "step": 390 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999420016552828e-05, + "loss": 0.5411, + "step": 391 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999389892801075e-05, + "loss": 0.5394, + "step": 392 + }, + { + "epoch": 0.03, + "learning_rate": 1.99993590064541e-05, + "loss": 0.51, + "step": 393 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999327357514268e-05, + "loss": 0.5648, + "step": 394 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999294945983984e-05, + "loss": 0.5399, + "step": 395 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999261771865716e-05, + "loss": 0.5459, + "step": 396 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999227835162e-05, + "loss": 0.5357, + "step": 397 + }, + { + "epoch": 0.03, + "learning_rate": 1.999919313587543e-05, + "loss": 0.5207, + "step": 398 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999157674008642e-05, + "loss": 0.5184, + "step": 399 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999121449564347e-05, + "loss": 0.5138, + "step": 400 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999084462545305e-05, + "loss": 0.5447, + "step": 401 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999046712954332e-05, + "loss": 0.5242, + "step": 402 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999008200794315e-05, + "loss": 0.5089, + "step": 403 + }, + { + "epoch": 0.03, + "learning_rate": 1.999896892606819e-05, + "loss": 0.5387, + "step": 404 + }, + { + "epoch": 0.03, + "learning_rate": 1.999892888877895e-05, + "loss": 0.5408, + "step": 405 + }, + { + "epoch": 0.03, + "learning_rate": 1.9998888088929647e-05, + "loss": 0.542, + "step": 406 + }, + { + "epoch": 0.03, + "learning_rate": 1.9998846526523393e-05, + "loss": 0.5237, + "step": 407 + }, + { + "epoch": 0.03, + "learning_rate": 1.9998804201563362e-05, + "loss": 0.534, + "step": 408 + }, + { + "epoch": 0.03, + "learning_rate": 1.9998761114052775e-05, + "loss": 0.5544, + "step": 409 + }, + { + "epoch": 0.03, + "learning_rate": 1.9998717263994923e-05, + "loss": 0.5352, + "step": 410 + }, + { + "epoch": 0.04, + "learning_rate": 1.9998672651393153e-05, + "loss": 0.5242, + "step": 411 + }, + { + "epoch": 0.04, + "learning_rate": 1.999862727625086e-05, + "loss": 0.5229, + "step": 412 + }, + { + "epoch": 0.04, + "learning_rate": 1.999858113857151e-05, + "loss": 0.5376, + "step": 413 + }, + { + "epoch": 0.04, + "learning_rate": 1.9998534238358617e-05, + "loss": 0.5456, + "step": 414 + }, + { + "epoch": 0.04, + "learning_rate": 1.999848657561576e-05, + "loss": 0.5349, + "step": 415 + }, + { + "epoch": 0.04, + "learning_rate": 1.9998438150346578e-05, + "loss": 0.5161, + "step": 416 + }, + { + "epoch": 0.04, + "learning_rate": 1.999838896255476e-05, + "loss": 0.5492, + "step": 417 + }, + { + "epoch": 0.04, + "learning_rate": 1.9998339012244052e-05, + "loss": 0.5328, + "step": 418 + }, + { + "epoch": 0.04, + "learning_rate": 1.9998288299418275e-05, + "loss": 0.5155, + "step": 419 + }, + { + "epoch": 0.04, + "learning_rate": 1.9998236824081288e-05, + "loss": 0.5225, + "step": 420 + }, + { + "epoch": 0.04, + "learning_rate": 1.9998184586237023e-05, + "loss": 0.5249, + "step": 421 + }, + { + "epoch": 0.04, + "learning_rate": 1.9998131585889456e-05, + "loss": 0.5125, + "step": 422 + }, + { + "epoch": 0.04, + "learning_rate": 1.9998077823042634e-05, + "loss": 0.5482, + "step": 423 + }, + { + "epoch": 0.04, + "learning_rate": 1.9998023297700656e-05, + "loss": 0.549, + "step": 424 + }, + { + "epoch": 0.04, + "learning_rate": 1.9997968009867683e-05, + "loss": 0.5196, + "step": 425 + }, + { + "epoch": 0.04, + "learning_rate": 1.999791195954793e-05, + "loss": 0.5317, + "step": 426 + }, + { + "epoch": 0.04, + "learning_rate": 1.9997855146745667e-05, + "loss": 0.5355, + "step": 427 + }, + { + "epoch": 0.04, + "learning_rate": 1.9997797571465234e-05, + "loss": 0.5124, + "step": 428 + }, + { + "epoch": 0.04, + "learning_rate": 1.9997739233711017e-05, + "loss": 0.4932, + "step": 429 + }, + { + "epoch": 0.04, + "learning_rate": 1.9997680133487468e-05, + "loss": 0.5316, + "step": 430 + }, + { + "epoch": 0.04, + "learning_rate": 1.999762027079909e-05, + "loss": 0.5079, + "step": 431 + }, + { + "epoch": 0.04, + "learning_rate": 1.999755964565046e-05, + "loss": 0.5117, + "step": 432 + }, + { + "epoch": 0.04, + "learning_rate": 1.9997498258046183e-05, + "loss": 0.5287, + "step": 433 + }, + { + "epoch": 0.04, + "learning_rate": 1.9997436107990956e-05, + "loss": 0.5346, + "step": 434 + }, + { + "epoch": 0.04, + "learning_rate": 1.9997373195489508e-05, + "loss": 0.5355, + "step": 435 + }, + { + "epoch": 0.04, + "learning_rate": 1.9997309520546646e-05, + "loss": 0.5103, + "step": 436 + }, + { + "epoch": 0.04, + "learning_rate": 1.9997245083167223e-05, + "loss": 0.5585, + "step": 437 + }, + { + "epoch": 0.04, + "learning_rate": 1.9997179883356154e-05, + "loss": 0.521, + "step": 438 + }, + { + "epoch": 0.04, + "learning_rate": 1.9997113921118404e-05, + "loss": 0.5316, + "step": 439 + }, + { + "epoch": 0.04, + "learning_rate": 1.9997047196459016e-05, + "loss": 0.5175, + "step": 440 + }, + { + "epoch": 0.04, + "learning_rate": 1.999697970938307e-05, + "loss": 0.5304, + "step": 441 + }, + { + "epoch": 0.04, + "learning_rate": 1.9996911459895717e-05, + "loss": 0.5203, + "step": 442 + }, + { + "epoch": 0.04, + "learning_rate": 1.9996842448002156e-05, + "loss": 0.5322, + "step": 443 + }, + { + "epoch": 0.04, + "learning_rate": 1.999677267370766e-05, + "loss": 0.5384, + "step": 444 + }, + { + "epoch": 0.04, + "learning_rate": 1.9996702137017537e-05, + "loss": 0.5369, + "step": 445 + }, + { + "epoch": 0.04, + "learning_rate": 1.9996630837937182e-05, + "loss": 0.5209, + "step": 446 + }, + { + "epoch": 0.04, + "learning_rate": 1.9996558776472022e-05, + "loss": 0.556, + "step": 447 + }, + { + "epoch": 0.04, + "learning_rate": 1.9996485952627554e-05, + "loss": 0.5256, + "step": 448 + }, + { + "epoch": 0.04, + "learning_rate": 1.9996412366409333e-05, + "loss": 0.5309, + "step": 449 + }, + { + "epoch": 0.04, + "learning_rate": 1.9996338017822973e-05, + "loss": 0.5546, + "step": 450 + }, + { + "epoch": 0.04, + "learning_rate": 1.999626290687414e-05, + "loss": 0.516, + "step": 451 + }, + { + "epoch": 0.04, + "learning_rate": 1.9996187033568567e-05, + "loss": 0.5216, + "step": 452 + }, + { + "epoch": 0.04, + "learning_rate": 1.9996110397912037e-05, + "loss": 0.5332, + "step": 453 + }, + { + "epoch": 0.04, + "learning_rate": 1.9996032999910394e-05, + "loss": 0.5255, + "step": 454 + }, + { + "epoch": 0.04, + "learning_rate": 1.9995954839569544e-05, + "loss": 0.538, + "step": 455 + }, + { + "epoch": 0.04, + "learning_rate": 1.9995875916895447e-05, + "loss": 0.5501, + "step": 456 + }, + { + "epoch": 0.04, + "learning_rate": 1.999579623189412e-05, + "loss": 0.5407, + "step": 457 + }, + { + "epoch": 0.04, + "learning_rate": 1.999571578457164e-05, + "loss": 0.5186, + "step": 458 + }, + { + "epoch": 0.04, + "learning_rate": 1.9995634574934145e-05, + "loss": 0.5404, + "step": 459 + }, + { + "epoch": 0.04, + "learning_rate": 1.9995552602987828e-05, + "loss": 0.5437, + "step": 460 + }, + { + "epoch": 0.04, + "learning_rate": 1.9995469868738936e-05, + "loss": 0.5418, + "step": 461 + }, + { + "epoch": 0.04, + "learning_rate": 1.9995386372193782e-05, + "loss": 0.5292, + "step": 462 + }, + { + "epoch": 0.04, + "learning_rate": 1.9995302113358735e-05, + "loss": 0.5239, + "step": 463 + }, + { + "epoch": 0.04, + "learning_rate": 1.999521709224022e-05, + "loss": 0.5442, + "step": 464 + }, + { + "epoch": 0.04, + "learning_rate": 1.9995131308844722e-05, + "loss": 0.5359, + "step": 465 + }, + { + "epoch": 0.04, + "learning_rate": 1.999504476317878e-05, + "loss": 0.5269, + "step": 466 + }, + { + "epoch": 0.04, + "learning_rate": 1.9994957455248994e-05, + "loss": 0.5233, + "step": 467 + }, + { + "epoch": 0.04, + "learning_rate": 1.999486938506203e-05, + "loss": 0.5268, + "step": 468 + }, + { + "epoch": 0.04, + "learning_rate": 1.9994780552624595e-05, + "loss": 0.5326, + "step": 469 + }, + { + "epoch": 0.04, + "learning_rate": 1.999469095794347e-05, + "loss": 0.5397, + "step": 470 + }, + { + "epoch": 0.04, + "learning_rate": 1.999460060102549e-05, + "loss": 0.5209, + "step": 471 + }, + { + "epoch": 0.04, + "learning_rate": 1.9994509481877536e-05, + "loss": 0.5209, + "step": 472 + }, + { + "epoch": 0.04, + "learning_rate": 1.9994417600506565e-05, + "loss": 0.5342, + "step": 473 + }, + { + "epoch": 0.04, + "learning_rate": 1.9994324956919583e-05, + "loss": 0.5177, + "step": 474 + }, + { + "epoch": 0.04, + "learning_rate": 1.9994231551123655e-05, + "loss": 0.5497, + "step": 475 + }, + { + "epoch": 0.04, + "learning_rate": 1.99941373831259e-05, + "loss": 0.5277, + "step": 476 + }, + { + "epoch": 0.04, + "learning_rate": 1.9994042452933508e-05, + "loss": 0.5228, + "step": 477 + }, + { + "epoch": 0.04, + "learning_rate": 1.9993946760553717e-05, + "loss": 0.5314, + "step": 478 + }, + { + "epoch": 0.04, + "learning_rate": 1.999385030599382e-05, + "loss": 0.5345, + "step": 479 + }, + { + "epoch": 0.04, + "learning_rate": 1.9993753089261175e-05, + "loss": 0.5337, + "step": 480 + }, + { + "epoch": 0.04, + "learning_rate": 1.9993655110363197e-05, + "loss": 0.5227, + "step": 481 + }, + { + "epoch": 0.04, + "learning_rate": 1.9993556369307355e-05, + "loss": 0.5244, + "step": 482 + }, + { + "epoch": 0.04, + "learning_rate": 1.9993456866101188e-05, + "loss": 0.5111, + "step": 483 + }, + { + "epoch": 0.04, + "learning_rate": 1.9993356600752277e-05, + "loss": 0.5316, + "step": 484 + }, + { + "epoch": 0.04, + "learning_rate": 1.9993255573268267e-05, + "loss": 0.537, + "step": 485 + }, + { + "epoch": 0.04, + "learning_rate": 1.999315378365687e-05, + "loss": 0.5425, + "step": 486 + }, + { + "epoch": 0.04, + "learning_rate": 1.9993051231925847e-05, + "loss": 0.5091, + "step": 487 + }, + { + "epoch": 0.04, + "learning_rate": 1.9992947918083014e-05, + "loss": 0.5313, + "step": 488 + }, + { + "epoch": 0.04, + "learning_rate": 1.9992843842136254e-05, + "loss": 0.5321, + "step": 489 + }, + { + "epoch": 0.04, + "learning_rate": 1.9992739004093503e-05, + "loss": 0.5362, + "step": 490 + }, + { + "epoch": 0.04, + "learning_rate": 1.999263340396276e-05, + "loss": 0.5339, + "step": 491 + }, + { + "epoch": 0.04, + "learning_rate": 1.9992527041752076e-05, + "loss": 0.5124, + "step": 492 + }, + { + "epoch": 0.04, + "learning_rate": 1.9992419917469558e-05, + "loss": 0.5102, + "step": 493 + }, + { + "epoch": 0.04, + "learning_rate": 1.9992312031123383e-05, + "loss": 0.5492, + "step": 494 + }, + { + "epoch": 0.04, + "learning_rate": 1.9992203382721774e-05, + "loss": 0.5252, + "step": 495 + }, + { + "epoch": 0.04, + "learning_rate": 1.999209397227302e-05, + "loss": 0.5385, + "step": 496 + }, + { + "epoch": 0.04, + "learning_rate": 1.9991983799785464e-05, + "loss": 0.5208, + "step": 497 + }, + { + "epoch": 0.04, + "learning_rate": 1.9991872865267508e-05, + "loss": 0.5383, + "step": 498 + }, + { + "epoch": 0.04, + "learning_rate": 1.9991761168727612e-05, + "loss": 0.5183, + "step": 499 + }, + { + "epoch": 0.04, + "learning_rate": 1.9991648710174295e-05, + "loss": 0.5354, + "step": 500 + }, + { + "epoch": 0.04, + "learning_rate": 1.9991535489616135e-05, + "loss": 0.5073, + "step": 501 + }, + { + "epoch": 0.04, + "learning_rate": 1.9991421507061763e-05, + "loss": 0.5302, + "step": 502 + }, + { + "epoch": 0.04, + "learning_rate": 1.9991306762519875e-05, + "loss": 0.5327, + "step": 503 + }, + { + "epoch": 0.04, + "learning_rate": 1.999119125599922e-05, + "loss": 0.5247, + "step": 504 + }, + { + "epoch": 0.04, + "learning_rate": 1.9991074987508613e-05, + "loss": 0.539, + "step": 505 + }, + { + "epoch": 0.04, + "learning_rate": 1.9990957957056907e-05, + "loss": 0.53, + "step": 506 + }, + { + "epoch": 0.04, + "learning_rate": 1.9990840164653042e-05, + "loss": 0.5364, + "step": 507 + }, + { + "epoch": 0.04, + "learning_rate": 1.9990721610305998e-05, + "loss": 0.5227, + "step": 508 + }, + { + "epoch": 0.04, + "learning_rate": 1.9990602294024808e-05, + "loss": 0.523, + "step": 509 + }, + { + "epoch": 0.04, + "learning_rate": 1.999048221581858e-05, + "loss": 0.5412, + "step": 510 + }, + { + "epoch": 0.04, + "learning_rate": 1.9990361375696467e-05, + "loss": 0.5176, + "step": 511 + }, + { + "epoch": 0.04, + "learning_rate": 1.999023977366769e-05, + "loss": 0.548, + "step": 512 + }, + { + "epoch": 0.04, + "learning_rate": 1.999011740974152e-05, + "loss": 0.5202, + "step": 513 + }, + { + "epoch": 0.04, + "learning_rate": 1.9989994283927287e-05, + "loss": 0.518, + "step": 514 + }, + { + "epoch": 0.04, + "learning_rate": 1.9989870396234384e-05, + "loss": 0.5218, + "step": 515 + }, + { + "epoch": 0.04, + "learning_rate": 1.9989745746672258e-05, + "loss": 0.5351, + "step": 516 + }, + { + "epoch": 0.04, + "learning_rate": 1.9989620335250413e-05, + "loss": 0.5408, + "step": 517 + }, + { + "epoch": 0.04, + "learning_rate": 1.998949416197842e-05, + "loss": 0.5218, + "step": 518 + }, + { + "epoch": 0.04, + "learning_rate": 1.9989367226865895e-05, + "loss": 0.5302, + "step": 519 + }, + { + "epoch": 0.04, + "learning_rate": 1.9989239529922523e-05, + "loss": 0.5254, + "step": 520 + }, + { + "epoch": 0.04, + "learning_rate": 1.9989111071158037e-05, + "loss": 0.5407, + "step": 521 + }, + { + "epoch": 0.04, + "learning_rate": 1.998898185058224e-05, + "loss": 0.5241, + "step": 522 + }, + { + "epoch": 0.04, + "learning_rate": 1.9988851868204983e-05, + "loss": 0.5225, + "step": 523 + }, + { + "epoch": 0.04, + "learning_rate": 1.9988721124036182e-05, + "loss": 0.5138, + "step": 524 + }, + { + "epoch": 0.04, + "learning_rate": 1.9988589618085807e-05, + "loss": 0.5183, + "step": 525 + }, + { + "epoch": 0.04, + "learning_rate": 1.9988457350363885e-05, + "loss": 0.5243, + "step": 526 + }, + { + "epoch": 0.04, + "learning_rate": 1.9988324320880504e-05, + "loss": 0.5215, + "step": 527 + }, + { + "epoch": 0.05, + "learning_rate": 1.998819052964581e-05, + "loss": 0.5329, + "step": 528 + }, + { + "epoch": 0.05, + "learning_rate": 1.9988055976670008e-05, + "loss": 0.5176, + "step": 529 + }, + { + "epoch": 0.05, + "learning_rate": 1.998792066196336e-05, + "loss": 0.5207, + "step": 530 + }, + { + "epoch": 0.05, + "learning_rate": 1.9987784585536182e-05, + "loss": 0.5312, + "step": 531 + }, + { + "epoch": 0.05, + "learning_rate": 1.9987647747398854e-05, + "loss": 0.5175, + "step": 532 + }, + { + "epoch": 0.05, + "learning_rate": 1.998751014756181e-05, + "loss": 0.5377, + "step": 533 + }, + { + "epoch": 0.05, + "learning_rate": 1.998737178603555e-05, + "loss": 0.5136, + "step": 534 + }, + { + "epoch": 0.05, + "learning_rate": 1.9987232662830618e-05, + "loss": 0.5381, + "step": 535 + }, + { + "epoch": 0.05, + "learning_rate": 1.998709277795763e-05, + "loss": 0.5257, + "step": 536 + }, + { + "epoch": 0.05, + "learning_rate": 1.998695213142725e-05, + "loss": 0.5279, + "step": 537 + }, + { + "epoch": 0.05, + "learning_rate": 1.9986810723250206e-05, + "loss": 0.4932, + "step": 538 + }, + { + "epoch": 0.05, + "learning_rate": 1.9986668553437283e-05, + "loss": 0.5141, + "step": 539 + }, + { + "epoch": 0.05, + "learning_rate": 1.9986525621999323e-05, + "loss": 0.5272, + "step": 540 + }, + { + "epoch": 0.05, + "learning_rate": 1.9986381928947227e-05, + "loss": 0.5381, + "step": 541 + }, + { + "epoch": 0.05, + "learning_rate": 1.9986237474291955e-05, + "loss": 0.5271, + "step": 542 + }, + { + "epoch": 0.05, + "learning_rate": 1.9986092258044518e-05, + "loss": 0.5215, + "step": 543 + }, + { + "epoch": 0.05, + "learning_rate": 1.9985946280215996e-05, + "loss": 0.5392, + "step": 544 + }, + { + "epoch": 0.05, + "learning_rate": 1.9985799540817525e-05, + "loss": 0.5294, + "step": 545 + }, + { + "epoch": 0.05, + "learning_rate": 1.9985652039860282e-05, + "loss": 0.5391, + "step": 546 + }, + { + "epoch": 0.05, + "learning_rate": 1.9985503777355534e-05, + "loss": 0.5257, + "step": 547 + }, + { + "epoch": 0.05, + "learning_rate": 1.998535475331458e-05, + "loss": 0.5378, + "step": 548 + }, + { + "epoch": 0.05, + "learning_rate": 1.998520496774878e-05, + "loss": 0.5317, + "step": 549 + }, + { + "epoch": 0.05, + "learning_rate": 1.9985054420669562e-05, + "loss": 0.5165, + "step": 550 + }, + { + "epoch": 0.05, + "learning_rate": 1.9984903112088413e-05, + "loss": 0.5301, + "step": 551 + }, + { + "epoch": 0.05, + "learning_rate": 1.998475104201686e-05, + "loss": 0.5224, + "step": 552 + }, + { + "epoch": 0.05, + "learning_rate": 1.998459821046651e-05, + "loss": 0.5309, + "step": 553 + }, + { + "epoch": 0.05, + "learning_rate": 1.9984444617449022e-05, + "loss": 0.5155, + "step": 554 + }, + { + "epoch": 0.05, + "learning_rate": 1.9984290262976097e-05, + "loss": 0.5376, + "step": 555 + }, + { + "epoch": 0.05, + "learning_rate": 1.9984135147059515e-05, + "loss": 0.5159, + "step": 556 + }, + { + "epoch": 0.05, + "learning_rate": 1.9983979269711106e-05, + "loss": 0.5342, + "step": 557 + }, + { + "epoch": 0.05, + "learning_rate": 1.9983822630942754e-05, + "loss": 0.516, + "step": 558 + }, + { + "epoch": 0.05, + "learning_rate": 1.9983665230766406e-05, + "loss": 0.5305, + "step": 559 + }, + { + "epoch": 0.05, + "learning_rate": 1.998350706919407e-05, + "loss": 0.5153, + "step": 560 + }, + { + "epoch": 0.05, + "learning_rate": 1.9983348146237806e-05, + "loss": 0.5297, + "step": 561 + }, + { + "epoch": 0.05, + "learning_rate": 1.998318846190973e-05, + "loss": 0.511, + "step": 562 + }, + { + "epoch": 0.05, + "learning_rate": 1.998302801622202e-05, + "loss": 0.5373, + "step": 563 + }, + { + "epoch": 0.05, + "learning_rate": 1.998286680918692e-05, + "loss": 0.5439, + "step": 564 + }, + { + "epoch": 0.05, + "learning_rate": 1.998270484081672e-05, + "loss": 0.5114, + "step": 565 + }, + { + "epoch": 0.05, + "learning_rate": 1.9982542111123772e-05, + "loss": 0.501, + "step": 566 + }, + { + "epoch": 0.05, + "learning_rate": 1.9982378620120485e-05, + "loss": 0.5305, + "step": 567 + }, + { + "epoch": 0.05, + "learning_rate": 1.998221436781933e-05, + "loss": 0.5171, + "step": 568 + }, + { + "epoch": 0.05, + "learning_rate": 1.9982049354232834e-05, + "loss": 0.5096, + "step": 569 + }, + { + "epoch": 0.05, + "learning_rate": 1.998188357937358e-05, + "loss": 0.532, + "step": 570 + }, + { + "epoch": 0.05, + "learning_rate": 1.998171704325421e-05, + "loss": 0.5121, + "step": 571 + }, + { + "epoch": 0.05, + "learning_rate": 1.998154974588743e-05, + "loss": 0.5303, + "step": 572 + }, + { + "epoch": 0.05, + "learning_rate": 1.9981381687285992e-05, + "loss": 0.5134, + "step": 573 + }, + { + "epoch": 0.05, + "learning_rate": 1.9981212867462715e-05, + "loss": 0.5155, + "step": 574 + }, + { + "epoch": 0.05, + "learning_rate": 1.9981043286430474e-05, + "loss": 0.503, + "step": 575 + }, + { + "epoch": 0.05, + "learning_rate": 1.9980872944202203e-05, + "loss": 0.5242, + "step": 576 + }, + { + "epoch": 0.05, + "learning_rate": 1.9980701840790893e-05, + "loss": 0.5397, + "step": 577 + }, + { + "epoch": 0.05, + "learning_rate": 1.998052997620959e-05, + "loss": 0.5254, + "step": 578 + }, + { + "epoch": 0.05, + "learning_rate": 1.9980357350471403e-05, + "loss": 0.5341, + "step": 579 + }, + { + "epoch": 0.05, + "learning_rate": 1.9980183963589505e-05, + "loss": 0.5229, + "step": 580 + }, + { + "epoch": 0.05, + "learning_rate": 1.9980009815577105e-05, + "loss": 0.5228, + "step": 581 + }, + { + "epoch": 0.05, + "learning_rate": 1.997983490644749e-05, + "loss": 0.5357, + "step": 582 + }, + { + "epoch": 0.05, + "learning_rate": 1.9979659236214005e-05, + "loss": 0.5245, + "step": 583 + }, + { + "epoch": 0.05, + "learning_rate": 1.997948280489004e-05, + "loss": 0.5141, + "step": 584 + }, + { + "epoch": 0.05, + "learning_rate": 1.9979305612489057e-05, + "loss": 0.5562, + "step": 585 + }, + { + "epoch": 0.05, + "learning_rate": 1.9979127659024563e-05, + "loss": 0.528, + "step": 586 + }, + { + "epoch": 0.05, + "learning_rate": 1.9978948944510133e-05, + "loss": 0.5169, + "step": 587 + }, + { + "epoch": 0.05, + "learning_rate": 1.9978769468959393e-05, + "loss": 0.5158, + "step": 588 + }, + { + "epoch": 0.05, + "learning_rate": 1.9978589232386036e-05, + "loss": 0.5187, + "step": 589 + }, + { + "epoch": 0.05, + "learning_rate": 1.9978408234803805e-05, + "loss": 0.5179, + "step": 590 + }, + { + "epoch": 0.05, + "learning_rate": 1.99782264762265e-05, + "loss": 0.5094, + "step": 591 + }, + { + "epoch": 0.05, + "learning_rate": 1.997804395666799e-05, + "loss": 0.525, + "step": 592 + }, + { + "epoch": 0.05, + "learning_rate": 1.9977860676142188e-05, + "loss": 0.5214, + "step": 593 + }, + { + "epoch": 0.05, + "learning_rate": 1.9977676634663076e-05, + "loss": 0.5176, + "step": 594 + }, + { + "epoch": 0.05, + "learning_rate": 1.997749183224469e-05, + "loss": 0.5363, + "step": 595 + }, + { + "epoch": 0.05, + "learning_rate": 1.997730626890112e-05, + "loss": 0.5173, + "step": 596 + }, + { + "epoch": 0.05, + "learning_rate": 1.997711994464652e-05, + "loss": 0.5193, + "step": 597 + }, + { + "epoch": 0.05, + "learning_rate": 1.99769328594951e-05, + "loss": 0.5202, + "step": 598 + }, + { + "epoch": 0.05, + "learning_rate": 1.9976745013461127e-05, + "loss": 0.5331, + "step": 599 + }, + { + "epoch": 0.05, + "learning_rate": 1.997655640655893e-05, + "loss": 0.5283, + "step": 600 + }, + { + "epoch": 0.05, + "learning_rate": 1.9976367038802888e-05, + "loss": 0.5234, + "step": 601 + }, + { + "epoch": 0.05, + "learning_rate": 1.9976176910207444e-05, + "loss": 0.5182, + "step": 602 + }, + { + "epoch": 0.05, + "learning_rate": 1.99759860207871e-05, + "loss": 0.5289, + "step": 603 + }, + { + "epoch": 0.05, + "learning_rate": 1.997579437055642e-05, + "loss": 0.5214, + "step": 604 + }, + { + "epoch": 0.05, + "learning_rate": 1.9975601959530007e-05, + "loss": 0.5256, + "step": 605 + }, + { + "epoch": 0.05, + "learning_rate": 1.9975408787722545e-05, + "loss": 0.5387, + "step": 606 + }, + { + "epoch": 0.05, + "learning_rate": 1.997521485514876e-05, + "loss": 0.5362, + "step": 607 + }, + { + "epoch": 0.05, + "learning_rate": 1.9975020161823445e-05, + "loss": 0.5215, + "step": 608 + }, + { + "epoch": 0.05, + "learning_rate": 1.9974824707761452e-05, + "loss": 0.5079, + "step": 609 + }, + { + "epoch": 0.05, + "learning_rate": 1.9974628492977678e-05, + "loss": 0.5185, + "step": 610 + }, + { + "epoch": 0.05, + "learning_rate": 1.9974431517487096e-05, + "loss": 0.5207, + "step": 611 + }, + { + "epoch": 0.05, + "learning_rate": 1.9974233781304725e-05, + "loss": 0.5274, + "step": 612 + }, + { + "epoch": 0.05, + "learning_rate": 1.9974035284445642e-05, + "loss": 0.5162, + "step": 613 + }, + { + "epoch": 0.05, + "learning_rate": 1.997383602692499e-05, + "loss": 0.5113, + "step": 614 + }, + { + "epoch": 0.05, + "learning_rate": 1.9973636008757958e-05, + "loss": 0.5404, + "step": 615 + }, + { + "epoch": 0.05, + "learning_rate": 1.9973435229959813e-05, + "loss": 0.5086, + "step": 616 + }, + { + "epoch": 0.05, + "learning_rate": 1.9973233690545854e-05, + "loss": 0.5533, + "step": 617 + }, + { + "epoch": 0.05, + "learning_rate": 1.9973031390531457e-05, + "loss": 0.5208, + "step": 618 + }, + { + "epoch": 0.05, + "learning_rate": 1.997282832993205e-05, + "loss": 0.5186, + "step": 619 + }, + { + "epoch": 0.05, + "learning_rate": 1.9972624508763125e-05, + "loss": 0.518, + "step": 620 + }, + { + "epoch": 0.05, + "learning_rate": 1.9972419927040214e-05, + "loss": 0.5217, + "step": 621 + }, + { + "epoch": 0.05, + "learning_rate": 1.997221458477893e-05, + "loss": 0.5318, + "step": 622 + }, + { + "epoch": 0.05, + "learning_rate": 1.9972008481994923e-05, + "loss": 0.5053, + "step": 623 + }, + { + "epoch": 0.05, + "learning_rate": 1.9971801618703924e-05, + "loss": 0.5236, + "step": 624 + }, + { + "epoch": 0.05, + "learning_rate": 1.99715939949217e-05, + "loss": 0.5219, + "step": 625 + }, + { + "epoch": 0.05, + "learning_rate": 1.9971385610664086e-05, + "loss": 0.513, + "step": 626 + }, + { + "epoch": 0.05, + "learning_rate": 1.9971176465946977e-05, + "loss": 0.508, + "step": 627 + }, + { + "epoch": 0.05, + "learning_rate": 1.9970966560786324e-05, + "loss": 0.5127, + "step": 628 + }, + { + "epoch": 0.05, + "learning_rate": 1.9970755895198133e-05, + "loss": 0.5124, + "step": 629 + }, + { + "epoch": 0.05, + "learning_rate": 1.997054446919847e-05, + "loss": 0.5194, + "step": 630 + }, + { + "epoch": 0.05, + "learning_rate": 1.997033228280346e-05, + "loss": 0.5396, + "step": 631 + }, + { + "epoch": 0.05, + "learning_rate": 1.9970119336029286e-05, + "loss": 0.5147, + "step": 632 + }, + { + "epoch": 0.05, + "learning_rate": 1.996990562889219e-05, + "loss": 0.5195, + "step": 633 + }, + { + "epoch": 0.05, + "learning_rate": 1.996969116140846e-05, + "loss": 0.5337, + "step": 634 + }, + { + "epoch": 0.05, + "learning_rate": 1.9969475933594467e-05, + "loss": 0.5267, + "step": 635 + }, + { + "epoch": 0.05, + "learning_rate": 1.9969259945466612e-05, + "loss": 0.5206, + "step": 636 + }, + { + "epoch": 0.05, + "learning_rate": 1.9969043197041377e-05, + "loss": 0.5152, + "step": 637 + }, + { + "epoch": 0.05, + "learning_rate": 1.996882568833529e-05, + "loss": 0.5045, + "step": 638 + }, + { + "epoch": 0.05, + "learning_rate": 1.9968607419364934e-05, + "loss": 0.5332, + "step": 639 + }, + { + "epoch": 0.05, + "learning_rate": 1.996838839014696e-05, + "loss": 0.5153, + "step": 640 + }, + { + "epoch": 0.05, + "learning_rate": 1.996816860069807e-05, + "loss": 0.5203, + "step": 641 + }, + { + "epoch": 0.05, + "learning_rate": 1.9967948051035026e-05, + "loss": 0.5355, + "step": 642 + }, + { + "epoch": 0.05, + "learning_rate": 1.9967726741174652e-05, + "loss": 0.5086, + "step": 643 + }, + { + "epoch": 0.05, + "learning_rate": 1.996750467113382e-05, + "loss": 0.5235, + "step": 644 + }, + { + "epoch": 0.05, + "learning_rate": 1.9967281840929467e-05, + "loss": 0.5313, + "step": 645 + }, + { + "epoch": 0.06, + "learning_rate": 1.9967058250578593e-05, + "loss": 0.5264, + "step": 646 + }, + { + "epoch": 0.06, + "learning_rate": 1.996683390009824e-05, + "loss": 0.5376, + "step": 647 + }, + { + "epoch": 0.06, + "learning_rate": 1.9966608789505527e-05, + "loss": 0.5145, + "step": 648 + }, + { + "epoch": 0.06, + "learning_rate": 1.996638291881762e-05, + "loss": 0.5169, + "step": 649 + }, + { + "epoch": 0.06, + "learning_rate": 1.9966156288051743e-05, + "loss": 0.5023, + "step": 650 + }, + { + "epoch": 0.06, + "learning_rate": 1.9965928897225177e-05, + "loss": 0.516, + "step": 651 + }, + { + "epoch": 0.06, + "learning_rate": 1.996570074635527e-05, + "loss": 0.5123, + "step": 652 + }, + { + "epoch": 0.06, + "learning_rate": 1.9965471835459416e-05, + "loss": 0.5384, + "step": 653 + }, + { + "epoch": 0.06, + "learning_rate": 1.9965242164555074e-05, + "loss": 0.5165, + "step": 654 + }, + { + "epoch": 0.06, + "learning_rate": 1.9965011733659762e-05, + "loss": 0.5071, + "step": 655 + }, + { + "epoch": 0.06, + "learning_rate": 1.9964780542791057e-05, + "loss": 0.5199, + "step": 656 + }, + { + "epoch": 0.06, + "learning_rate": 1.9964548591966583e-05, + "loss": 0.5239, + "step": 657 + }, + { + "epoch": 0.06, + "learning_rate": 1.996431588120403e-05, + "loss": 0.5081, + "step": 658 + }, + { + "epoch": 0.06, + "learning_rate": 1.996408241052115e-05, + "loss": 0.5183, + "step": 659 + }, + { + "epoch": 0.06, + "learning_rate": 1.996384817993575e-05, + "loss": 0.5179, + "step": 660 + }, + { + "epoch": 0.06, + "learning_rate": 1.9963613189465684e-05, + "loss": 0.5184, + "step": 661 + }, + { + "epoch": 0.06, + "learning_rate": 1.9963377439128883e-05, + "loss": 0.5093, + "step": 662 + }, + { + "epoch": 0.06, + "learning_rate": 1.996314092894332e-05, + "loss": 0.5273, + "step": 663 + }, + { + "epoch": 0.06, + "learning_rate": 1.9962903658927038e-05, + "loss": 0.5418, + "step": 664 + }, + { + "epoch": 0.06, + "learning_rate": 1.9962665629098128e-05, + "loss": 0.5089, + "step": 665 + }, + { + "epoch": 0.06, + "learning_rate": 1.9962426839474745e-05, + "loss": 0.5326, + "step": 666 + }, + { + "epoch": 0.06, + "learning_rate": 1.9962187290075097e-05, + "loss": 0.5149, + "step": 667 + }, + { + "epoch": 0.06, + "learning_rate": 1.9961946980917457e-05, + "loss": 0.5195, + "step": 668 + }, + { + "epoch": 0.06, + "learning_rate": 1.996170591202015e-05, + "loss": 0.5094, + "step": 669 + }, + { + "epoch": 0.06, + "learning_rate": 1.996146408340156e-05, + "loss": 0.5225, + "step": 670 + }, + { + "epoch": 0.06, + "learning_rate": 1.9961221495080135e-05, + "loss": 0.5159, + "step": 671 + }, + { + "epoch": 0.06, + "learning_rate": 1.9960978147074367e-05, + "loss": 0.5114, + "step": 672 + }, + { + "epoch": 0.06, + "learning_rate": 1.9960734039402824e-05, + "loss": 0.5342, + "step": 673 + }, + { + "epoch": 0.06, + "learning_rate": 1.9960489172084118e-05, + "loss": 0.5107, + "step": 674 + }, + { + "epoch": 0.06, + "learning_rate": 1.996024354513692e-05, + "loss": 0.5176, + "step": 675 + }, + { + "epoch": 0.06, + "learning_rate": 1.995999715857997e-05, + "loss": 0.5155, + "step": 676 + }, + { + "epoch": 0.06, + "learning_rate": 1.9959750012432053e-05, + "loss": 0.5296, + "step": 677 + }, + { + "epoch": 0.06, + "learning_rate": 1.9959502106712023e-05, + "loss": 0.5137, + "step": 678 + }, + { + "epoch": 0.06, + "learning_rate": 1.9959253441438778e-05, + "loss": 0.517, + "step": 679 + }, + { + "epoch": 0.06, + "learning_rate": 1.995900401663129e-05, + "loss": 0.5267, + "step": 680 + }, + { + "epoch": 0.06, + "learning_rate": 1.9958753832308575e-05, + "loss": 0.5097, + "step": 681 + }, + { + "epoch": 0.06, + "learning_rate": 1.995850288848972e-05, + "loss": 0.5279, + "step": 682 + }, + { + "epoch": 0.06, + "learning_rate": 1.9958251185193855e-05, + "loss": 0.5174, + "step": 683 + }, + { + "epoch": 0.06, + "learning_rate": 1.9957998722440183e-05, + "loss": 0.5169, + "step": 684 + }, + { + "epoch": 0.06, + "learning_rate": 1.9957745500247955e-05, + "loss": 0.5142, + "step": 685 + }, + { + "epoch": 0.06, + "learning_rate": 1.995749151863648e-05, + "loss": 0.5225, + "step": 686 + }, + { + "epoch": 0.06, + "learning_rate": 1.9957236777625134e-05, + "loss": 0.5233, + "step": 687 + }, + { + "epoch": 0.06, + "learning_rate": 1.9956981277233342e-05, + "loss": 0.5147, + "step": 688 + }, + { + "epoch": 0.06, + "learning_rate": 1.9956725017480585e-05, + "loss": 0.515, + "step": 689 + }, + { + "epoch": 0.06, + "learning_rate": 1.995646799838641e-05, + "loss": 0.5104, + "step": 690 + }, + { + "epoch": 0.06, + "learning_rate": 1.9956210219970422e-05, + "loss": 0.5172, + "step": 691 + }, + { + "epoch": 0.06, + "learning_rate": 1.9955951682252275e-05, + "loss": 0.5154, + "step": 692 + }, + { + "epoch": 0.06, + "learning_rate": 1.9955692385251687e-05, + "loss": 0.5117, + "step": 693 + }, + { + "epoch": 0.06, + "learning_rate": 1.9955432328988437e-05, + "loss": 0.5147, + "step": 694 + }, + { + "epoch": 0.06, + "learning_rate": 1.995517151348235e-05, + "loss": 0.5172, + "step": 695 + }, + { + "epoch": 0.06, + "learning_rate": 1.9954909938753326e-05, + "loss": 0.5162, + "step": 696 + }, + { + "epoch": 0.06, + "learning_rate": 1.9954647604821307e-05, + "loss": 0.5285, + "step": 697 + }, + { + "epoch": 0.06, + "learning_rate": 1.9954384511706305e-05, + "loss": 0.5088, + "step": 698 + }, + { + "epoch": 0.06, + "learning_rate": 1.995412065942838e-05, + "loss": 0.5185, + "step": 699 + }, + { + "epoch": 0.06, + "learning_rate": 1.9953856048007654e-05, + "loss": 0.5246, + "step": 700 + }, + { + "epoch": 0.06, + "learning_rate": 1.9953590677464314e-05, + "loss": 0.5075, + "step": 701 + }, + { + "epoch": 0.06, + "learning_rate": 1.9953324547818592e-05, + "loss": 0.5318, + "step": 702 + }, + { + "epoch": 0.06, + "learning_rate": 1.9953057659090783e-05, + "loss": 0.5232, + "step": 703 + }, + { + "epoch": 0.06, + "learning_rate": 1.9952790011301248e-05, + "loss": 0.5172, + "step": 704 + }, + { + "epoch": 0.06, + "learning_rate": 1.9952521604470396e-05, + "loss": 0.5188, + "step": 705 + }, + { + "epoch": 0.06, + "learning_rate": 1.9952252438618692e-05, + "loss": 0.514, + "step": 706 + }, + { + "epoch": 0.06, + "learning_rate": 1.995198251376667e-05, + "loss": 0.5086, + "step": 707 + }, + { + "epoch": 0.06, + "learning_rate": 1.9951711829934914e-05, + "loss": 0.5216, + "step": 708 + }, + { + "epoch": 0.06, + "learning_rate": 1.9951440387144065e-05, + "loss": 0.5227, + "step": 709 + }, + { + "epoch": 0.06, + "learning_rate": 1.9951168185414827e-05, + "loss": 0.5257, + "step": 710 + }, + { + "epoch": 0.06, + "learning_rate": 1.995089522476796e-05, + "loss": 0.5125, + "step": 711 + }, + { + "epoch": 0.06, + "learning_rate": 1.9950621505224276e-05, + "loss": 0.523, + "step": 712 + }, + { + "epoch": 0.06, + "learning_rate": 1.9950347026804655e-05, + "loss": 0.5088, + "step": 713 + }, + { + "epoch": 0.06, + "learning_rate": 1.9950071789530026e-05, + "loss": 0.5225, + "step": 714 + }, + { + "epoch": 0.06, + "learning_rate": 1.9949795793421386e-05, + "loss": 0.5142, + "step": 715 + }, + { + "epoch": 0.06, + "learning_rate": 1.994951903849978e-05, + "loss": 0.5172, + "step": 716 + }, + { + "epoch": 0.06, + "learning_rate": 1.994924152478631e-05, + "loss": 0.5279, + "step": 717 + }, + { + "epoch": 0.06, + "learning_rate": 1.9948963252302147e-05, + "loss": 0.5341, + "step": 718 + }, + { + "epoch": 0.06, + "learning_rate": 1.9948684221068512e-05, + "loss": 0.52, + "step": 719 + }, + { + "epoch": 0.06, + "learning_rate": 1.994840443110668e-05, + "loss": 0.509, + "step": 720 + }, + { + "epoch": 0.06, + "learning_rate": 1.9948123882437995e-05, + "loss": 0.5059, + "step": 721 + }, + { + "epoch": 0.06, + "learning_rate": 1.9947842575083852e-05, + "loss": 0.5256, + "step": 722 + }, + { + "epoch": 0.06, + "learning_rate": 1.99475605090657e-05, + "loss": 0.5409, + "step": 723 + }, + { + "epoch": 0.06, + "learning_rate": 1.9947277684405056e-05, + "loss": 0.5041, + "step": 724 + }, + { + "epoch": 0.06, + "learning_rate": 1.9946994101123483e-05, + "loss": 0.5233, + "step": 725 + }, + { + "epoch": 0.06, + "learning_rate": 1.994670975924262e-05, + "loss": 0.5258, + "step": 726 + }, + { + "epoch": 0.06, + "learning_rate": 1.9946424658784142e-05, + "loss": 0.5046, + "step": 727 + }, + { + "epoch": 0.06, + "learning_rate": 1.994613879976979e-05, + "loss": 0.525, + "step": 728 + }, + { + "epoch": 0.06, + "learning_rate": 1.994585218222137e-05, + "loss": 0.5399, + "step": 729 + }, + { + "epoch": 0.06, + "learning_rate": 1.9945564806160744e-05, + "loss": 0.5453, + "step": 730 + }, + { + "epoch": 0.06, + "learning_rate": 1.9945276671609823e-05, + "loss": 0.5086, + "step": 731 + }, + { + "epoch": 0.06, + "learning_rate": 1.9944987778590582e-05, + "loss": 0.5236, + "step": 732 + }, + { + "epoch": 0.06, + "learning_rate": 1.9944698127125053e-05, + "loss": 0.5115, + "step": 733 + }, + { + "epoch": 0.06, + "learning_rate": 1.9944407717235327e-05, + "loss": 0.5218, + "step": 734 + }, + { + "epoch": 0.06, + "learning_rate": 1.9944116548943552e-05, + "loss": 0.5261, + "step": 735 + }, + { + "epoch": 0.06, + "learning_rate": 1.9943824622271934e-05, + "loss": 0.5205, + "step": 736 + }, + { + "epoch": 0.06, + "learning_rate": 1.994353193724274e-05, + "loss": 0.5211, + "step": 737 + }, + { + "epoch": 0.06, + "learning_rate": 1.9943238493878284e-05, + "loss": 0.5267, + "step": 738 + }, + { + "epoch": 0.06, + "learning_rate": 1.9942944292200948e-05, + "loss": 0.5006, + "step": 739 + }, + { + "epoch": 0.06, + "learning_rate": 1.9942649332233168e-05, + "loss": 0.5045, + "step": 740 + }, + { + "epoch": 0.06, + "learning_rate": 1.994235361399744e-05, + "loss": 0.5197, + "step": 741 + }, + { + "epoch": 0.06, + "learning_rate": 1.9942057137516323e-05, + "loss": 0.5191, + "step": 742 + }, + { + "epoch": 0.06, + "learning_rate": 1.9941759902812422e-05, + "loss": 0.5105, + "step": 743 + }, + { + "epoch": 0.06, + "learning_rate": 1.9941461909908398e-05, + "loss": 0.5279, + "step": 744 + }, + { + "epoch": 0.06, + "learning_rate": 1.9941163158826992e-05, + "loss": 0.5014, + "step": 745 + }, + { + "epoch": 0.06, + "learning_rate": 1.9940863649590976e-05, + "loss": 0.5047, + "step": 746 + }, + { + "epoch": 0.06, + "learning_rate": 1.9940563382223196e-05, + "loss": 0.5231, + "step": 747 + }, + { + "epoch": 0.06, + "learning_rate": 1.9940262356746553e-05, + "loss": 0.5177, + "step": 748 + }, + { + "epoch": 0.06, + "learning_rate": 1.9939960573184007e-05, + "loss": 0.5326, + "step": 749 + }, + { + "epoch": 0.06, + "learning_rate": 1.9939658031558564e-05, + "loss": 0.5126, + "step": 750 + }, + { + "epoch": 0.06, + "learning_rate": 1.9939354731893304e-05, + "loss": 0.5214, + "step": 751 + }, + { + "epoch": 0.06, + "learning_rate": 1.9939050674211358e-05, + "loss": 0.531, + "step": 752 + }, + { + "epoch": 0.06, + "learning_rate": 1.993874585853591e-05, + "loss": 0.5296, + "step": 753 + }, + { + "epoch": 0.06, + "learning_rate": 1.9938440284890216e-05, + "loss": 0.5012, + "step": 754 + }, + { + "epoch": 0.06, + "learning_rate": 1.993813395329757e-05, + "loss": 0.5218, + "step": 755 + }, + { + "epoch": 0.06, + "learning_rate": 1.993782686378134e-05, + "loss": 0.5171, + "step": 756 + }, + { + "epoch": 0.06, + "learning_rate": 1.9937519016364943e-05, + "loss": 0.496, + "step": 757 + }, + { + "epoch": 0.06, + "learning_rate": 1.9937210411071856e-05, + "loss": 0.5207, + "step": 758 + }, + { + "epoch": 0.06, + "learning_rate": 1.9936901047925617e-05, + "loss": 0.4908, + "step": 759 + }, + { + "epoch": 0.06, + "learning_rate": 1.9936590926949822e-05, + "loss": 0.517, + "step": 760 + }, + { + "epoch": 0.06, + "learning_rate": 1.9936280048168117e-05, + "loss": 0.4964, + "step": 761 + }, + { + "epoch": 0.06, + "learning_rate": 1.9935968411604215e-05, + "loss": 0.5386, + "step": 762 + }, + { + "epoch": 0.07, + "learning_rate": 1.9935656017281877e-05, + "loss": 0.531, + "step": 763 + }, + { + "epoch": 0.07, + "learning_rate": 1.9935342865224935e-05, + "loss": 0.5259, + "step": 764 + }, + { + "epoch": 0.07, + "learning_rate": 1.9935028955457262e-05, + "loss": 0.5188, + "step": 765 + }, + { + "epoch": 0.07, + "learning_rate": 1.993471428800281e-05, + "loss": 0.527, + "step": 766 + }, + { + "epoch": 0.07, + "learning_rate": 1.9934398862885563e-05, + "loss": 0.5116, + "step": 767 + }, + { + "epoch": 0.07, + "learning_rate": 1.9934082680129588e-05, + "loss": 0.5169, + "step": 768 + }, + { + "epoch": 0.07, + "learning_rate": 1.9933765739758992e-05, + "loss": 0.5214, + "step": 769 + }, + { + "epoch": 0.07, + "learning_rate": 1.9933448041797948e-05, + "loss": 0.5024, + "step": 770 + }, + { + "epoch": 0.07, + "learning_rate": 1.993312958627069e-05, + "loss": 0.5314, + "step": 771 + }, + { + "epoch": 0.07, + "learning_rate": 1.9932810373201498e-05, + "loss": 0.512, + "step": 772 + }, + { + "epoch": 0.07, + "learning_rate": 1.9932490402614718e-05, + "loss": 0.522, + "step": 773 + }, + { + "epoch": 0.07, + "learning_rate": 1.9932169674534752e-05, + "loss": 0.5267, + "step": 774 + }, + { + "epoch": 0.07, + "learning_rate": 1.9931848188986063e-05, + "loss": 0.5178, + "step": 775 + }, + { + "epoch": 0.07, + "learning_rate": 1.9931525945993164e-05, + "loss": 0.5208, + "step": 776 + }, + { + "epoch": 0.07, + "learning_rate": 1.9931202945580635e-05, + "loss": 0.5206, + "step": 777 + }, + { + "epoch": 0.07, + "learning_rate": 1.9930879187773108e-05, + "loss": 0.5329, + "step": 778 + }, + { + "epoch": 0.07, + "learning_rate": 1.9930554672595276e-05, + "loss": 0.5281, + "step": 779 + }, + { + "epoch": 0.07, + "learning_rate": 1.9930229400071886e-05, + "loss": 0.5236, + "step": 780 + }, + { + "epoch": 0.07, + "learning_rate": 1.9929903370227742e-05, + "loss": 0.5122, + "step": 781 + }, + { + "epoch": 0.07, + "learning_rate": 1.9929576583087714e-05, + "loss": 0.5001, + "step": 782 + }, + { + "epoch": 0.07, + "learning_rate": 1.9929249038676713e-05, + "loss": 0.5368, + "step": 783 + }, + { + "epoch": 0.07, + "learning_rate": 1.9928920737019735e-05, + "loss": 0.5069, + "step": 784 + }, + { + "epoch": 0.07, + "learning_rate": 1.9928591678141807e-05, + "loss": 0.5173, + "step": 785 + }, + { + "epoch": 0.07, + "learning_rate": 1.9928261862068026e-05, + "loss": 0.5076, + "step": 786 + }, + { + "epoch": 0.07, + "learning_rate": 1.992793128882355e-05, + "loss": 0.5258, + "step": 787 + }, + { + "epoch": 0.07, + "learning_rate": 1.9927599958433585e-05, + "loss": 0.5248, + "step": 788 + }, + { + "epoch": 0.07, + "learning_rate": 1.9927267870923398e-05, + "loss": 0.5276, + "step": 789 + }, + { + "epoch": 0.07, + "learning_rate": 1.992693502631832e-05, + "loss": 0.5301, + "step": 790 + }, + { + "epoch": 0.07, + "learning_rate": 1.992660142464373e-05, + "loss": 0.5218, + "step": 791 + }, + { + "epoch": 0.07, + "learning_rate": 1.9926267065925075e-05, + "loss": 0.5263, + "step": 792 + }, + { + "epoch": 0.07, + "learning_rate": 1.9925931950187852e-05, + "loss": 0.5351, + "step": 793 + }, + { + "epoch": 0.07, + "learning_rate": 1.9925596077457623e-05, + "loss": 0.5293, + "step": 794 + }, + { + "epoch": 0.07, + "learning_rate": 1.9925259447759995e-05, + "loss": 0.5289, + "step": 795 + }, + { + "epoch": 0.07, + "learning_rate": 1.9924922061120644e-05, + "loss": 0.5162, + "step": 796 + }, + { + "epoch": 0.07, + "learning_rate": 1.9924583917565305e-05, + "loss": 0.5105, + "step": 797 + }, + { + "epoch": 0.07, + "learning_rate": 1.992424501711976e-05, + "loss": 0.5006, + "step": 798 + }, + { + "epoch": 0.07, + "learning_rate": 1.992390535980986e-05, + "loss": 0.5149, + "step": 799 + }, + { + "epoch": 0.07, + "learning_rate": 1.9923564945661506e-05, + "loss": 0.5183, + "step": 800 + }, + { + "epoch": 0.07, + "learning_rate": 1.9923223774700656e-05, + "loss": 0.5152, + "step": 801 + }, + { + "epoch": 0.07, + "learning_rate": 1.9922881846953333e-05, + "loss": 0.4956, + "step": 802 + }, + { + "epoch": 0.07, + "learning_rate": 1.9922539162445616e-05, + "loss": 0.5078, + "step": 803 + }, + { + "epoch": 0.07, + "learning_rate": 1.9922195721203638e-05, + "loss": 0.5344, + "step": 804 + }, + { + "epoch": 0.07, + "learning_rate": 1.992185152325359e-05, + "loss": 0.5006, + "step": 805 + }, + { + "epoch": 0.07, + "learning_rate": 1.9921506568621717e-05, + "loss": 0.5199, + "step": 806 + }, + { + "epoch": 0.07, + "learning_rate": 1.9921160857334337e-05, + "loss": 0.5235, + "step": 807 + }, + { + "epoch": 0.07, + "learning_rate": 1.992081438941781e-05, + "loss": 0.5145, + "step": 808 + }, + { + "epoch": 0.07, + "learning_rate": 1.9920467164898558e-05, + "loss": 0.5353, + "step": 809 + }, + { + "epoch": 0.07, + "learning_rate": 1.9920119183803064e-05, + "loss": 0.5082, + "step": 810 + }, + { + "epoch": 0.07, + "learning_rate": 1.9919770446157867e-05, + "loss": 0.5049, + "step": 811 + }, + { + "epoch": 0.07, + "learning_rate": 1.991942095198956e-05, + "loss": 0.5023, + "step": 812 + }, + { + "epoch": 0.07, + "learning_rate": 1.9919070701324803e-05, + "loss": 0.5214, + "step": 813 + }, + { + "epoch": 0.07, + "learning_rate": 1.99187196941903e-05, + "loss": 0.5158, + "step": 814 + }, + { + "epoch": 0.07, + "learning_rate": 1.9918367930612824e-05, + "loss": 0.5418, + "step": 815 + }, + { + "epoch": 0.07, + "learning_rate": 1.99180154106192e-05, + "loss": 0.5131, + "step": 816 + }, + { + "epoch": 0.07, + "learning_rate": 1.9917662134236318e-05, + "loss": 0.5084, + "step": 817 + }, + { + "epoch": 0.07, + "learning_rate": 1.9917308101491117e-05, + "loss": 0.5298, + "step": 818 + }, + { + "epoch": 0.07, + "learning_rate": 1.9916953312410593e-05, + "loss": 0.5194, + "step": 819 + }, + { + "epoch": 0.07, + "learning_rate": 1.991659776702181e-05, + "loss": 0.5171, + "step": 820 + }, + { + "epoch": 0.07, + "learning_rate": 1.9916241465351874e-05, + "loss": 0.5142, + "step": 821 + }, + { + "epoch": 0.07, + "learning_rate": 1.9915884407427974e-05, + "loss": 0.506, + "step": 822 + }, + { + "epoch": 0.07, + "learning_rate": 1.9915526593277327e-05, + "loss": 0.5324, + "step": 823 + }, + { + "epoch": 0.07, + "learning_rate": 1.9915168022927225e-05, + "loss": 0.5203, + "step": 824 + }, + { + "epoch": 0.07, + "learning_rate": 1.9914808696405017e-05, + "loss": 0.5265, + "step": 825 + }, + { + "epoch": 0.07, + "learning_rate": 1.9914448613738107e-05, + "loss": 0.5149, + "step": 826 + }, + { + "epoch": 0.07, + "learning_rate": 1.991408777495395e-05, + "loss": 0.5285, + "step": 827 + }, + { + "epoch": 0.07, + "learning_rate": 1.9913726180080072e-05, + "loss": 0.5169, + "step": 828 + }, + { + "epoch": 0.07, + "learning_rate": 1.9913363829144042e-05, + "loss": 0.5189, + "step": 829 + }, + { + "epoch": 0.07, + "learning_rate": 1.991300072217351e-05, + "loss": 0.5236, + "step": 830 + }, + { + "epoch": 0.07, + "learning_rate": 1.9912636859196145e-05, + "loss": 0.5167, + "step": 831 + }, + { + "epoch": 0.07, + "learning_rate": 1.9912272240239715e-05, + "loss": 0.5125, + "step": 832 + }, + { + "epoch": 0.07, + "learning_rate": 1.991190686533202e-05, + "loss": 0.5403, + "step": 833 + }, + { + "epoch": 0.07, + "learning_rate": 1.991154073450093e-05, + "loss": 0.5048, + "step": 834 + }, + { + "epoch": 0.07, + "learning_rate": 1.9911173847774365e-05, + "loss": 0.5121, + "step": 835 + }, + { + "epoch": 0.07, + "learning_rate": 1.9910806205180296e-05, + "loss": 0.5148, + "step": 836 + }, + { + "epoch": 0.07, + "learning_rate": 1.9910437806746776e-05, + "loss": 0.4887, + "step": 837 + }, + { + "epoch": 0.07, + "learning_rate": 1.9910068652501894e-05, + "loss": 0.5225, + "step": 838 + }, + { + "epoch": 0.07, + "learning_rate": 1.9909698742473802e-05, + "loss": 0.5013, + "step": 839 + }, + { + "epoch": 0.07, + "learning_rate": 1.990932807669071e-05, + "loss": 0.5091, + "step": 840 + }, + { + "epoch": 0.07, + "learning_rate": 1.9908956655180894e-05, + "loss": 0.5096, + "step": 841 + }, + { + "epoch": 0.07, + "learning_rate": 1.9908584477972666e-05, + "loss": 0.5263, + "step": 842 + }, + { + "epoch": 0.07, + "learning_rate": 1.9908211545094426e-05, + "loss": 0.5215, + "step": 843 + }, + { + "epoch": 0.07, + "learning_rate": 1.9907837856574608e-05, + "loss": 0.502, + "step": 844 + }, + { + "epoch": 0.07, + "learning_rate": 1.990746341244171e-05, + "loss": 0.526, + "step": 845 + }, + { + "epoch": 0.07, + "learning_rate": 1.990708821272429e-05, + "loss": 0.5016, + "step": 846 + }, + { + "epoch": 0.07, + "learning_rate": 1.9906712257450958e-05, + "loss": 0.5207, + "step": 847 + }, + { + "epoch": 0.07, + "learning_rate": 1.9906335546650394e-05, + "loss": 0.5097, + "step": 848 + }, + { + "epoch": 0.07, + "learning_rate": 1.990595808035132e-05, + "loss": 0.5322, + "step": 849 + }, + { + "epoch": 0.07, + "learning_rate": 1.990557985858253e-05, + "loss": 0.5107, + "step": 850 + }, + { + "epoch": 0.07, + "learning_rate": 1.9905200881372866e-05, + "loss": 0.5144, + "step": 851 + }, + { + "epoch": 0.07, + "learning_rate": 1.990482114875123e-05, + "loss": 0.5182, + "step": 852 + }, + { + "epoch": 0.07, + "learning_rate": 1.990444066074658e-05, + "loss": 0.5274, + "step": 853 + }, + { + "epoch": 0.07, + "learning_rate": 1.9904059417387932e-05, + "loss": 0.5003, + "step": 854 + }, + { + "epoch": 0.07, + "learning_rate": 1.990367741870437e-05, + "loss": 0.524, + "step": 855 + }, + { + "epoch": 0.07, + "learning_rate": 1.9903294664725023e-05, + "loss": 0.5406, + "step": 856 + }, + { + "epoch": 0.07, + "learning_rate": 1.9902911155479073e-05, + "loss": 0.5282, + "step": 857 + }, + { + "epoch": 0.07, + "learning_rate": 1.990252689099578e-05, + "loss": 0.5354, + "step": 858 + }, + { + "epoch": 0.07, + "learning_rate": 1.9902141871304442e-05, + "loss": 0.5418, + "step": 859 + }, + { + "epoch": 0.07, + "learning_rate": 1.9901756096434426e-05, + "loss": 0.5113, + "step": 860 + }, + { + "epoch": 0.07, + "learning_rate": 1.990136956641515e-05, + "loss": 0.5216, + "step": 861 + }, + { + "epoch": 0.07, + "learning_rate": 1.9900982281276096e-05, + "loss": 0.5289, + "step": 862 + }, + { + "epoch": 0.07, + "learning_rate": 1.9900594241046797e-05, + "loss": 0.5142, + "step": 863 + }, + { + "epoch": 0.07, + "learning_rate": 1.9900205445756845e-05, + "loss": 0.5077, + "step": 864 + }, + { + "epoch": 0.07, + "learning_rate": 1.98998158954359e-05, + "loss": 0.5306, + "step": 865 + }, + { + "epoch": 0.07, + "learning_rate": 1.9899425590113658e-05, + "loss": 0.5119, + "step": 866 + }, + { + "epoch": 0.07, + "learning_rate": 1.9899034529819895e-05, + "loss": 0.5115, + "step": 867 + }, + { + "epoch": 0.07, + "learning_rate": 1.989864271458443e-05, + "loss": 0.5074, + "step": 868 + }, + { + "epoch": 0.07, + "learning_rate": 1.9898250144437145e-05, + "loss": 0.5066, + "step": 869 + }, + { + "epoch": 0.07, + "learning_rate": 1.9897856819407982e-05, + "loss": 0.5316, + "step": 870 + }, + { + "epoch": 0.07, + "learning_rate": 1.9897462739526936e-05, + "loss": 0.5247, + "step": 871 + }, + { + "epoch": 0.07, + "learning_rate": 1.989706790482406e-05, + "loss": 0.5076, + "step": 872 + }, + { + "epoch": 0.07, + "learning_rate": 1.9896672315329467e-05, + "loss": 0.5192, + "step": 873 + }, + { + "epoch": 0.07, + "learning_rate": 1.9896275971073326e-05, + "loss": 0.5259, + "step": 874 + }, + { + "epoch": 0.07, + "learning_rate": 1.989587887208586e-05, + "loss": 0.5208, + "step": 875 + }, + { + "epoch": 0.07, + "learning_rate": 1.989548101839736e-05, + "loss": 0.504, + "step": 876 + }, + { + "epoch": 0.07, + "learning_rate": 1.9895082410038166e-05, + "loss": 0.5055, + "step": 877 + }, + { + "epoch": 0.07, + "learning_rate": 1.9894683047038675e-05, + "loss": 0.5184, + "step": 878 + }, + { + "epoch": 0.07, + "learning_rate": 1.989428292942935e-05, + "loss": 0.5179, + "step": 879 + }, + { + "epoch": 0.08, + "learning_rate": 1.9893882057240698e-05, + "loss": 0.528, + "step": 880 + }, + { + "epoch": 0.08, + "learning_rate": 1.9893480430503293e-05, + "loss": 0.521, + "step": 881 + }, + { + "epoch": 0.08, + "learning_rate": 1.989307804924777e-05, + "loss": 0.5243, + "step": 882 + }, + { + "epoch": 0.08, + "learning_rate": 1.989267491350481e-05, + "loss": 0.5042, + "step": 883 + }, + { + "epoch": 0.08, + "learning_rate": 1.989227102330516e-05, + "loss": 0.5142, + "step": 884 + }, + { + "epoch": 0.08, + "learning_rate": 1.9891866378679624e-05, + "loss": 0.518, + "step": 885 + }, + { + "epoch": 0.08, + "learning_rate": 1.989146097965906e-05, + "loss": 0.5141, + "step": 886 + }, + { + "epoch": 0.08, + "learning_rate": 1.989105482627439e-05, + "loss": 0.5215, + "step": 887 + }, + { + "epoch": 0.08, + "learning_rate": 1.989064791855658e-05, + "loss": 0.5159, + "step": 888 + }, + { + "epoch": 0.08, + "learning_rate": 1.989024025653667e-05, + "loss": 0.5265, + "step": 889 + }, + { + "epoch": 0.08, + "learning_rate": 1.9889831840245745e-05, + "loss": 0.5158, + "step": 890 + }, + { + "epoch": 0.08, + "learning_rate": 1.9889422669714958e-05, + "loss": 0.5201, + "step": 891 + }, + { + "epoch": 0.08, + "learning_rate": 1.9889012744975508e-05, + "loss": 0.5173, + "step": 892 + }, + { + "epoch": 0.08, + "learning_rate": 1.9888602066058663e-05, + "loss": 0.5167, + "step": 893 + }, + { + "epoch": 0.08, + "learning_rate": 1.988819063299574e-05, + "loss": 0.5189, + "step": 894 + }, + { + "epoch": 0.08, + "learning_rate": 1.988777844581812e-05, + "loss": 0.5376, + "step": 895 + }, + { + "epoch": 0.08, + "learning_rate": 1.988736550455723e-05, + "loss": 0.5304, + "step": 896 + }, + { + "epoch": 0.08, + "learning_rate": 1.9886951809244575e-05, + "loss": 0.5293, + "step": 897 + }, + { + "epoch": 0.08, + "learning_rate": 1.9886537359911694e-05, + "loss": 0.5298, + "step": 898 + }, + { + "epoch": 0.08, + "learning_rate": 1.98861221565902e-05, + "loss": 0.5142, + "step": 899 + }, + { + "epoch": 0.08, + "learning_rate": 1.9885706199311757e-05, + "loss": 0.5054, + "step": 900 + }, + { + "epoch": 0.08, + "learning_rate": 1.9885289488108086e-05, + "loss": 0.5035, + "step": 901 + }, + { + "epoch": 0.08, + "learning_rate": 1.988487202301097e-05, + "loss": 0.5316, + "step": 902 + }, + { + "epoch": 0.08, + "learning_rate": 1.9884453804052246e-05, + "loss": 0.5109, + "step": 903 + }, + { + "epoch": 0.08, + "learning_rate": 1.9884034831263807e-05, + "loss": 0.519, + "step": 904 + }, + { + "epoch": 0.08, + "learning_rate": 1.988361510467761e-05, + "loss": 0.5004, + "step": 905 + }, + { + "epoch": 0.08, + "learning_rate": 1.9883194624325658e-05, + "loss": 0.5246, + "step": 906 + }, + { + "epoch": 0.08, + "learning_rate": 1.9882773390240027e-05, + "loss": 0.504, + "step": 907 + }, + { + "epoch": 0.08, + "learning_rate": 1.9882351402452835e-05, + "loss": 0.5029, + "step": 908 + }, + { + "epoch": 0.08, + "learning_rate": 1.988192866099627e-05, + "loss": 0.5198, + "step": 909 + }, + { + "epoch": 0.08, + "learning_rate": 1.9881505165902566e-05, + "loss": 0.5318, + "step": 910 + }, + { + "epoch": 0.08, + "learning_rate": 1.9881080917204027e-05, + "loss": 0.5293, + "step": 911 + }, + { + "epoch": 0.08, + "learning_rate": 1.9880655914933003e-05, + "loss": 0.5033, + "step": 912 + }, + { + "epoch": 0.08, + "learning_rate": 1.988023015912191e-05, + "loss": 0.51, + "step": 913 + }, + { + "epoch": 0.08, + "learning_rate": 1.9879803649803217e-05, + "loss": 0.5355, + "step": 914 + }, + { + "epoch": 0.08, + "learning_rate": 1.9879376387009448e-05, + "loss": 0.494, + "step": 915 + }, + { + "epoch": 0.08, + "learning_rate": 1.9878948370773194e-05, + "loss": 0.5393, + "step": 916 + }, + { + "epoch": 0.08, + "learning_rate": 1.987851960112709e-05, + "loss": 0.5151, + "step": 917 + }, + { + "epoch": 0.08, + "learning_rate": 1.9878090078103846e-05, + "loss": 0.4995, + "step": 918 + }, + { + "epoch": 0.08, + "learning_rate": 1.9877659801736206e-05, + "loss": 0.528, + "step": 919 + }, + { + "epoch": 0.08, + "learning_rate": 1.9877228772056992e-05, + "loss": 0.5276, + "step": 920 + }, + { + "epoch": 0.08, + "learning_rate": 1.987679698909908e-05, + "loss": 0.5271, + "step": 921 + }, + { + "epoch": 0.08, + "learning_rate": 1.9876364452895394e-05, + "loss": 0.5033, + "step": 922 + }, + { + "epoch": 0.08, + "learning_rate": 1.987593116347892e-05, + "loss": 0.5267, + "step": 923 + }, + { + "epoch": 0.08, + "learning_rate": 1.9875497120882706e-05, + "loss": 0.523, + "step": 924 + }, + { + "epoch": 0.08, + "learning_rate": 1.9875062325139853e-05, + "loss": 0.5119, + "step": 925 + }, + { + "epoch": 0.08, + "learning_rate": 1.987462677628352e-05, + "loss": 0.5168, + "step": 926 + }, + { + "epoch": 0.08, + "learning_rate": 1.987419047434692e-05, + "loss": 0.5238, + "step": 927 + }, + { + "epoch": 0.08, + "learning_rate": 1.9873753419363336e-05, + "loss": 0.512, + "step": 928 + }, + { + "epoch": 0.08, + "learning_rate": 1.987331561136609e-05, + "loss": 0.5383, + "step": 929 + }, + { + "epoch": 0.08, + "learning_rate": 1.987287705038858e-05, + "loss": 0.5264, + "step": 930 + }, + { + "epoch": 0.08, + "learning_rate": 1.987243773646425e-05, + "loss": 0.5008, + "step": 931 + }, + { + "epoch": 0.08, + "learning_rate": 1.9871997669626596e-05, + "loss": 0.5127, + "step": 932 + }, + { + "epoch": 0.08, + "learning_rate": 1.9871556849909187e-05, + "loss": 0.5241, + "step": 933 + }, + { + "epoch": 0.08, + "learning_rate": 1.987111527734564e-05, + "loss": 0.5092, + "step": 934 + }, + { + "epoch": 0.08, + "learning_rate": 1.9870672951969632e-05, + "loss": 0.5229, + "step": 935 + }, + { + "epoch": 0.08, + "learning_rate": 1.9870229873814897e-05, + "loss": 0.5242, + "step": 936 + }, + { + "epoch": 0.08, + "learning_rate": 1.9869786042915225e-05, + "loss": 0.5134, + "step": 937 + }, + { + "epoch": 0.08, + "learning_rate": 1.9869341459304465e-05, + "loss": 0.5064, + "step": 938 + }, + { + "epoch": 0.08, + "learning_rate": 1.9868896123016517e-05, + "loss": 0.5173, + "step": 939 + }, + { + "epoch": 0.08, + "learning_rate": 1.9868450034085352e-05, + "loss": 0.4949, + "step": 940 + }, + { + "epoch": 0.08, + "learning_rate": 1.986800319254499e-05, + "loss": 0.5017, + "step": 941 + }, + { + "epoch": 0.08, + "learning_rate": 1.9867555598429505e-05, + "loss": 0.5093, + "step": 942 + }, + { + "epoch": 0.08, + "learning_rate": 1.9867107251773033e-05, + "loss": 0.5155, + "step": 943 + }, + { + "epoch": 0.08, + "learning_rate": 1.986665815260977e-05, + "loss": 0.511, + "step": 944 + }, + { + "epoch": 0.08, + "learning_rate": 1.9866208300973962e-05, + "loss": 0.5229, + "step": 945 + }, + { + "epoch": 0.08, + "learning_rate": 1.986575769689992e-05, + "loss": 0.5333, + "step": 946 + }, + { + "epoch": 0.08, + "learning_rate": 1.986530634042201e-05, + "loss": 0.5258, + "step": 947 + }, + { + "epoch": 0.08, + "learning_rate": 1.986485423157465e-05, + "loss": 0.5012, + "step": 948 + }, + { + "epoch": 0.08, + "learning_rate": 1.986440137039232e-05, + "loss": 0.5095, + "step": 949 + }, + { + "epoch": 0.08, + "learning_rate": 1.9863947756909563e-05, + "loss": 0.5248, + "step": 950 + }, + { + "epoch": 0.08, + "learning_rate": 1.986349339116097e-05, + "loss": 0.4988, + "step": 951 + }, + { + "epoch": 0.08, + "learning_rate": 1.9863038273181187e-05, + "loss": 0.5289, + "step": 952 + }, + { + "epoch": 0.08, + "learning_rate": 1.986258240300493e-05, + "loss": 0.534, + "step": 953 + }, + { + "epoch": 0.08, + "learning_rate": 1.9862125780666966e-05, + "loss": 0.4971, + "step": 954 + }, + { + "epoch": 0.08, + "learning_rate": 1.9861668406202116e-05, + "loss": 0.534, + "step": 955 + }, + { + "epoch": 0.08, + "learning_rate": 1.986121027964526e-05, + "loss": 0.5077, + "step": 956 + }, + { + "epoch": 0.08, + "learning_rate": 1.986075140103134e-05, + "loss": 0.5238, + "step": 957 + }, + { + "epoch": 0.08, + "learning_rate": 1.986029177039535e-05, + "loss": 0.5233, + "step": 958 + }, + { + "epoch": 0.08, + "learning_rate": 1.9859831387772345e-05, + "loss": 0.5189, + "step": 959 + }, + { + "epoch": 0.08, + "learning_rate": 1.9859370253197436e-05, + "loss": 0.5223, + "step": 960 + }, + { + "epoch": 0.08, + "learning_rate": 1.985890836670579e-05, + "loss": 0.4904, + "step": 961 + }, + { + "epoch": 0.08, + "learning_rate": 1.985844572833263e-05, + "loss": 0.5242, + "step": 962 + }, + { + "epoch": 0.08, + "learning_rate": 1.985798233811324e-05, + "loss": 0.5242, + "step": 963 + }, + { + "epoch": 0.08, + "learning_rate": 1.9857518196082964e-05, + "loss": 0.5254, + "step": 964 + }, + { + "epoch": 0.08, + "learning_rate": 1.9857053302277197e-05, + "loss": 0.5, + "step": 965 + }, + { + "epoch": 0.08, + "learning_rate": 1.9856587656731393e-05, + "loss": 0.5088, + "step": 966 + }, + { + "epoch": 0.08, + "learning_rate": 1.985612125948106e-05, + "loss": 0.5031, + "step": 967 + }, + { + "epoch": 0.08, + "learning_rate": 1.9855654110561775e-05, + "loss": 0.5181, + "step": 968 + }, + { + "epoch": 0.08, + "learning_rate": 1.9855186210009162e-05, + "loss": 0.5075, + "step": 969 + }, + { + "epoch": 0.08, + "learning_rate": 1.9854717557858906e-05, + "loss": 0.4901, + "step": 970 + }, + { + "epoch": 0.08, + "learning_rate": 1.9854248154146744e-05, + "loss": 0.5007, + "step": 971 + }, + { + "epoch": 0.08, + "learning_rate": 1.9853777998908475e-05, + "loss": 0.5079, + "step": 972 + }, + { + "epoch": 0.08, + "learning_rate": 1.9853307092179964e-05, + "loss": 0.512, + "step": 973 + }, + { + "epoch": 0.08, + "learning_rate": 1.985283543399711e-05, + "loss": 0.4978, + "step": 974 + }, + { + "epoch": 0.08, + "learning_rate": 1.9852363024395896e-05, + "loss": 0.514, + "step": 975 + }, + { + "epoch": 0.08, + "learning_rate": 1.9851889863412347e-05, + "loss": 0.5064, + "step": 976 + }, + { + "epoch": 0.08, + "learning_rate": 1.9851415951082544e-05, + "loss": 0.5073, + "step": 977 + }, + { + "epoch": 0.08, + "learning_rate": 1.9850941287442635e-05, + "loss": 0.5289, + "step": 978 + }, + { + "epoch": 0.08, + "learning_rate": 1.9850465872528812e-05, + "loss": 0.5027, + "step": 979 + }, + { + "epoch": 0.08, + "learning_rate": 1.984998970637734e-05, + "loss": 0.4954, + "step": 980 + }, + { + "epoch": 0.08, + "learning_rate": 1.9849512789024533e-05, + "loss": 0.5339, + "step": 981 + }, + { + "epoch": 0.08, + "learning_rate": 1.9849035120506756e-05, + "loss": 0.512, + "step": 982 + }, + { + "epoch": 0.08, + "learning_rate": 1.9848556700860446e-05, + "loss": 0.4935, + "step": 983 + }, + { + "epoch": 0.08, + "learning_rate": 1.9848077530122083e-05, + "loss": 0.5036, + "step": 984 + }, + { + "epoch": 0.08, + "learning_rate": 1.9847597608328212e-05, + "loss": 0.5259, + "step": 985 + }, + { + "epoch": 0.08, + "learning_rate": 1.9847116935515438e-05, + "loss": 0.5315, + "step": 986 + }, + { + "epoch": 0.08, + "learning_rate": 1.9846635511720413e-05, + "loss": 0.5134, + "step": 987 + }, + { + "epoch": 0.08, + "learning_rate": 1.9846153336979855e-05, + "loss": 0.5228, + "step": 988 + }, + { + "epoch": 0.08, + "learning_rate": 1.9845670411330543e-05, + "loss": 0.5135, + "step": 989 + }, + { + "epoch": 0.08, + "learning_rate": 1.9845186734809294e-05, + "loss": 0.5249, + "step": 990 + }, + { + "epoch": 0.08, + "learning_rate": 1.984470230745301e-05, + "loss": 0.5229, + "step": 991 + }, + { + "epoch": 0.08, + "learning_rate": 1.9844217129298616e-05, + "loss": 0.5244, + "step": 992 + }, + { + "epoch": 0.08, + "learning_rate": 1.9843731200383132e-05, + "loss": 0.4955, + "step": 993 + }, + { + "epoch": 0.08, + "learning_rate": 1.984324452074361e-05, + "loss": 0.5196, + "step": 994 + }, + { + "epoch": 0.08, + "learning_rate": 1.984275709041717e-05, + "loss": 0.5101, + "step": 995 + }, + { + "epoch": 0.08, + "learning_rate": 1.9842268909440977e-05, + "loss": 0.5101, + "step": 996 + }, + { + "epoch": 0.09, + "learning_rate": 1.9841779977852273e-05, + "loss": 0.5318, + "step": 997 + }, + { + "epoch": 0.09, + "learning_rate": 1.9841290295688335e-05, + "loss": 0.5031, + "step": 998 + }, + { + "epoch": 0.09, + "learning_rate": 1.9840799862986513e-05, + "loss": 0.4967, + "step": 999 + }, + { + "epoch": 0.09, + "learning_rate": 1.9840308679784207e-05, + "loss": 0.5151, + "step": 1000 + }, + { + "epoch": 0.09, + "learning_rate": 1.983981674611888e-05, + "loss": 0.5077, + "step": 1001 + }, + { + "epoch": 0.09, + "learning_rate": 1.983932406202805e-05, + "loss": 0.5123, + "step": 1002 + }, + { + "epoch": 0.09, + "learning_rate": 1.983883062754929e-05, + "loss": 0.5163, + "step": 1003 + }, + { + "epoch": 0.09, + "learning_rate": 1.983833644272023e-05, + "loss": 0.5279, + "step": 1004 + }, + { + "epoch": 0.09, + "learning_rate": 1.9837841507578558e-05, + "loss": 0.5259, + "step": 1005 + }, + { + "epoch": 0.09, + "learning_rate": 1.983734582216202e-05, + "loss": 0.4907, + "step": 1006 + }, + { + "epoch": 0.09, + "learning_rate": 1.9836849386508422e-05, + "loss": 0.5146, + "step": 1007 + }, + { + "epoch": 0.09, + "learning_rate": 1.983635220065562e-05, + "loss": 0.5151, + "step": 1008 + }, + { + "epoch": 0.09, + "learning_rate": 1.9835854264641538e-05, + "loss": 0.4935, + "step": 1009 + }, + { + "epoch": 0.09, + "learning_rate": 1.9835355578504143e-05, + "loss": 0.5231, + "step": 1010 + }, + { + "epoch": 0.09, + "learning_rate": 1.983485614228147e-05, + "loss": 0.5169, + "step": 1011 + }, + { + "epoch": 0.09, + "learning_rate": 1.9834355956011604e-05, + "loss": 0.4986, + "step": 1012 + }, + { + "epoch": 0.09, + "learning_rate": 1.9833855019732703e-05, + "loss": 0.5301, + "step": 1013 + }, + { + "epoch": 0.09, + "learning_rate": 1.983335333348296e-05, + "loss": 0.5129, + "step": 1014 + }, + { + "epoch": 0.09, + "learning_rate": 1.983285089730064e-05, + "loss": 0.5111, + "step": 1015 + }, + { + "epoch": 0.09, + "learning_rate": 1.9832347711224057e-05, + "loss": 0.492, + "step": 1016 + }, + { + "epoch": 0.09, + "learning_rate": 1.9831843775291594e-05, + "loss": 0.5054, + "step": 1017 + }, + { + "epoch": 0.09, + "learning_rate": 1.9831339089541673e-05, + "loss": 0.5046, + "step": 1018 + }, + { + "epoch": 0.09, + "learning_rate": 1.983083365401279e-05, + "loss": 0.5203, + "step": 1019 + }, + { + "epoch": 0.09, + "learning_rate": 1.983032746874349e-05, + "loss": 0.5157, + "step": 1020 + }, + { + "epoch": 0.09, + "learning_rate": 1.9829820533772376e-05, + "loss": 0.5186, + "step": 1021 + }, + { + "epoch": 0.09, + "learning_rate": 1.982931284913811e-05, + "loss": 0.5362, + "step": 1022 + }, + { + "epoch": 0.09, + "learning_rate": 1.982880441487941e-05, + "loss": 0.5075, + "step": 1023 + }, + { + "epoch": 0.09, + "learning_rate": 1.9828295231035054e-05, + "loss": 0.52, + "step": 1024 + }, + { + "epoch": 0.09, + "learning_rate": 1.982778529764387e-05, + "loss": 0.4912, + "step": 1025 + }, + { + "epoch": 0.09, + "learning_rate": 1.9827274614744747e-05, + "loss": 0.5365, + "step": 1026 + }, + { + "epoch": 0.09, + "learning_rate": 1.9826763182376636e-05, + "loss": 0.5306, + "step": 1027 + }, + { + "epoch": 0.09, + "learning_rate": 1.982625100057854e-05, + "loss": 0.5137, + "step": 1028 + }, + { + "epoch": 0.09, + "learning_rate": 1.9825738069389518e-05, + "loss": 0.5236, + "step": 1029 + }, + { + "epoch": 0.09, + "learning_rate": 1.9825224388848693e-05, + "loss": 0.5296, + "step": 1030 + }, + { + "epoch": 0.09, + "learning_rate": 1.982470995899523e-05, + "loss": 0.5291, + "step": 1031 + }, + { + "epoch": 0.09, + "learning_rate": 1.9824194779868377e-05, + "loss": 0.5146, + "step": 1032 + }, + { + "epoch": 0.09, + "learning_rate": 1.982367885150741e-05, + "loss": 0.515, + "step": 1033 + }, + { + "epoch": 0.09, + "learning_rate": 1.9823162173951683e-05, + "loss": 0.5439, + "step": 1034 + }, + { + "epoch": 0.09, + "learning_rate": 1.9822644747240597e-05, + "loss": 0.5, + "step": 1035 + }, + { + "epoch": 0.09, + "learning_rate": 1.9822126571413616e-05, + "loss": 0.5356, + "step": 1036 + }, + { + "epoch": 0.09, + "learning_rate": 1.9821607646510256e-05, + "loss": 0.4945, + "step": 1037 + }, + { + "epoch": 0.09, + "learning_rate": 1.982108797257009e-05, + "loss": 0.517, + "step": 1038 + }, + { + "epoch": 0.09, + "learning_rate": 1.9820567549632755e-05, + "loss": 0.5001, + "step": 1039 + }, + { + "epoch": 0.09, + "learning_rate": 1.9820046377737944e-05, + "loss": 0.5218, + "step": 1040 + }, + { + "epoch": 0.09, + "learning_rate": 1.9819524456925392e-05, + "loss": 0.516, + "step": 1041 + }, + { + "epoch": 0.09, + "learning_rate": 1.9819001787234912e-05, + "loss": 0.4994, + "step": 1042 + }, + { + "epoch": 0.09, + "learning_rate": 1.981847836870636e-05, + "loss": 0.5268, + "step": 1043 + }, + { + "epoch": 0.09, + "learning_rate": 1.9817954201379664e-05, + "loss": 0.5009, + "step": 1044 + }, + { + "epoch": 0.09, + "learning_rate": 1.9817429285294785e-05, + "loss": 0.5122, + "step": 1045 + }, + { + "epoch": 0.09, + "learning_rate": 1.9816903620491764e-05, + "loss": 0.5085, + "step": 1046 + }, + { + "epoch": 0.09, + "learning_rate": 1.981637720701069e-05, + "loss": 0.5147, + "step": 1047 + }, + { + "epoch": 0.09, + "learning_rate": 1.981585004489171e-05, + "loss": 0.4996, + "step": 1048 + }, + { + "epoch": 0.09, + "learning_rate": 1.981532213417502e-05, + "loss": 0.5244, + "step": 1049 + }, + { + "epoch": 0.09, + "learning_rate": 1.981479347490089e-05, + "loss": 0.5133, + "step": 1050 + }, + { + "epoch": 0.09, + "learning_rate": 1.9814264067109634e-05, + "loss": 0.4958, + "step": 1051 + }, + { + "epoch": 0.09, + "learning_rate": 1.9813733910841626e-05, + "loss": 0.492, + "step": 1052 + }, + { + "epoch": 0.09, + "learning_rate": 1.98132030061373e-05, + "loss": 0.5405, + "step": 1053 + }, + { + "epoch": 0.09, + "learning_rate": 1.981267135303714e-05, + "loss": 0.5359, + "step": 1054 + }, + { + "epoch": 0.09, + "learning_rate": 1.98121389515817e-05, + "loss": 0.4791, + "step": 1055 + }, + { + "epoch": 0.09, + "learning_rate": 1.9811605801811578e-05, + "loss": 0.5129, + "step": 1056 + }, + { + "epoch": 0.09, + "learning_rate": 1.9811071903767436e-05, + "loss": 0.5006, + "step": 1057 + }, + { + "epoch": 0.09, + "learning_rate": 1.9810537257489987e-05, + "loss": 0.5217, + "step": 1058 + }, + { + "epoch": 0.09, + "learning_rate": 1.9810001863020014e-05, + "loss": 0.5282, + "step": 1059 + }, + { + "epoch": 0.09, + "learning_rate": 1.980946572039834e-05, + "loss": 0.5196, + "step": 1060 + }, + { + "epoch": 0.09, + "learning_rate": 1.9808928829665857e-05, + "loss": 0.5017, + "step": 1061 + }, + { + "epoch": 0.09, + "learning_rate": 1.9808391190863513e-05, + "loss": 0.511, + "step": 1062 + }, + { + "epoch": 0.09, + "learning_rate": 1.9807852804032306e-05, + "loss": 0.5124, + "step": 1063 + }, + { + "epoch": 0.09, + "learning_rate": 1.98073136692133e-05, + "loss": 0.5042, + "step": 1064 + }, + { + "epoch": 0.09, + "learning_rate": 1.9806773786447605e-05, + "loss": 0.5294, + "step": 1065 + }, + { + "epoch": 0.09, + "learning_rate": 1.9806233155776403e-05, + "loss": 0.5382, + "step": 1066 + }, + { + "epoch": 0.09, + "learning_rate": 1.9805691777240917e-05, + "loss": 0.5212, + "step": 1067 + }, + { + "epoch": 0.09, + "learning_rate": 1.980514965088244e-05, + "loss": 0.5228, + "step": 1068 + }, + { + "epoch": 0.09, + "learning_rate": 1.9804606776742318e-05, + "loss": 0.5093, + "step": 1069 + }, + { + "epoch": 0.09, + "learning_rate": 1.9804063154861947e-05, + "loss": 0.5154, + "step": 1070 + }, + { + "epoch": 0.09, + "learning_rate": 1.980351878528279e-05, + "loss": 0.4891, + "step": 1071 + }, + { + "epoch": 0.09, + "learning_rate": 1.9802973668046364e-05, + "loss": 0.4991, + "step": 1072 + }, + { + "epoch": 0.09, + "learning_rate": 1.9802427803194238e-05, + "loss": 0.5134, + "step": 1073 + }, + { + "epoch": 0.09, + "learning_rate": 1.980188119076804e-05, + "loss": 0.5102, + "step": 1074 + }, + { + "epoch": 0.09, + "learning_rate": 1.9801333830809468e-05, + "loss": 0.5098, + "step": 1075 + }, + { + "epoch": 0.09, + "learning_rate": 1.9800785723360256e-05, + "loss": 0.5143, + "step": 1076 + }, + { + "epoch": 0.09, + "learning_rate": 1.9800236868462206e-05, + "loss": 0.5105, + "step": 1077 + }, + { + "epoch": 0.09, + "learning_rate": 1.979968726615718e-05, + "loss": 0.5076, + "step": 1078 + }, + { + "epoch": 0.09, + "learning_rate": 1.979913691648709e-05, + "loss": 0.5331, + "step": 1079 + }, + { + "epoch": 0.09, + "learning_rate": 1.9798585819493907e-05, + "loss": 0.5235, + "step": 1080 + }, + { + "epoch": 0.09, + "learning_rate": 1.979803397521966e-05, + "loss": 0.5152, + "step": 1081 + }, + { + "epoch": 0.09, + "learning_rate": 1.979748138370644e-05, + "loss": 0.5344, + "step": 1082 + }, + { + "epoch": 0.09, + "learning_rate": 1.9796928044996386e-05, + "loss": 0.5007, + "step": 1083 + }, + { + "epoch": 0.09, + "learning_rate": 1.97963739591317e-05, + "loss": 0.5165, + "step": 1084 + }, + { + "epoch": 0.09, + "learning_rate": 1.9795819126154634e-05, + "loss": 0.4915, + "step": 1085 + }, + { + "epoch": 0.09, + "learning_rate": 1.9795263546107507e-05, + "loss": 0.5352, + "step": 1086 + }, + { + "epoch": 0.09, + "learning_rate": 1.9794707219032686e-05, + "loss": 0.5152, + "step": 1087 + }, + { + "epoch": 0.09, + "learning_rate": 1.97941501449726e-05, + "loss": 0.5109, + "step": 1088 + }, + { + "epoch": 0.09, + "learning_rate": 1.979359232396974e-05, + "loss": 0.5096, + "step": 1089 + }, + { + "epoch": 0.09, + "learning_rate": 1.9793033756066635e-05, + "loss": 0.4935, + "step": 1090 + }, + { + "epoch": 0.09, + "learning_rate": 1.9792474441305896e-05, + "loss": 0.5331, + "step": 1091 + }, + { + "epoch": 0.09, + "learning_rate": 1.9791914379730174e-05, + "loss": 0.4988, + "step": 1092 + }, + { + "epoch": 0.09, + "learning_rate": 1.9791353571382178e-05, + "loss": 0.5234, + "step": 1093 + }, + { + "epoch": 0.09, + "learning_rate": 1.9790792016304685e-05, + "loss": 0.4935, + "step": 1094 + }, + { + "epoch": 0.09, + "learning_rate": 1.9790229714540513e-05, + "loss": 0.5209, + "step": 1095 + }, + { + "epoch": 0.09, + "learning_rate": 1.9789666666132553e-05, + "loss": 0.5117, + "step": 1096 + }, + { + "epoch": 0.09, + "learning_rate": 1.9789102871123745e-05, + "loss": 0.502, + "step": 1097 + }, + { + "epoch": 0.09, + "learning_rate": 1.978853832955708e-05, + "loss": 0.517, + "step": 1098 + }, + { + "epoch": 0.09, + "learning_rate": 1.9787973041475616e-05, + "loss": 0.5119, + "step": 1099 + }, + { + "epoch": 0.09, + "learning_rate": 1.9787407006922464e-05, + "loss": 0.5175, + "step": 1100 + }, + { + "epoch": 0.09, + "learning_rate": 1.9786840225940795e-05, + "loss": 0.5115, + "step": 1101 + }, + { + "epoch": 0.09, + "learning_rate": 1.978627269857383e-05, + "loss": 0.531, + "step": 1102 + }, + { + "epoch": 0.09, + "learning_rate": 1.9785704424864852e-05, + "loss": 0.495, + "step": 1103 + }, + { + "epoch": 0.09, + "learning_rate": 1.9785135404857202e-05, + "loss": 0.5128, + "step": 1104 + }, + { + "epoch": 0.09, + "learning_rate": 1.9784565638594274e-05, + "loss": 0.5277, + "step": 1105 + }, + { + "epoch": 0.09, + "learning_rate": 1.9783995126119518e-05, + "loss": 0.5047, + "step": 1106 + }, + { + "epoch": 0.09, + "learning_rate": 1.978342386747645e-05, + "loss": 0.4966, + "step": 1107 + }, + { + "epoch": 0.09, + "learning_rate": 1.9782851862708633e-05, + "loss": 0.5291, + "step": 1108 + }, + { + "epoch": 0.09, + "learning_rate": 1.978227911185969e-05, + "loss": 0.521, + "step": 1109 + }, + { + "epoch": 0.09, + "learning_rate": 1.97817056149733e-05, + "loss": 0.495, + "step": 1110 + }, + { + "epoch": 0.09, + "learning_rate": 1.9781131372093206e-05, + "loss": 0.5021, + "step": 1111 + }, + { + "epoch": 0.09, + "learning_rate": 1.97805563832632e-05, + "loss": 0.5245, + "step": 1112 + }, + { + "epoch": 0.09, + "learning_rate": 1.9779980648527126e-05, + "loss": 0.4986, + "step": 1113 + }, + { + "epoch": 0.09, + "learning_rate": 1.9779404167928903e-05, + "loss": 0.5174, + "step": 1114 + }, + { + "epoch": 0.1, + "learning_rate": 1.977882694151249e-05, + "loss": 0.5096, + "step": 1115 + }, + { + "epoch": 0.1, + "learning_rate": 1.9778248969321904e-05, + "loss": 0.5146, + "step": 1116 + }, + { + "epoch": 0.1, + "learning_rate": 1.9777670251401232e-05, + "loss": 0.4908, + "step": 1117 + }, + { + "epoch": 0.1, + "learning_rate": 1.9777090787794604e-05, + "loss": 0.518, + "step": 1118 + }, + { + "epoch": 0.1, + "learning_rate": 1.9776510578546217e-05, + "loss": 0.5145, + "step": 1119 + }, + { + "epoch": 0.1, + "learning_rate": 1.9775929623700318e-05, + "loss": 0.5137, + "step": 1120 + }, + { + "epoch": 0.1, + "learning_rate": 1.9775347923301212e-05, + "loss": 0.5191, + "step": 1121 + }, + { + "epoch": 0.1, + "learning_rate": 1.977476547739326e-05, + "loss": 0.5064, + "step": 1122 + }, + { + "epoch": 0.1, + "learning_rate": 1.9774182286020887e-05, + "loss": 0.503, + "step": 1123 + }, + { + "epoch": 0.1, + "learning_rate": 1.9773598349228568e-05, + "loss": 0.5156, + "step": 1124 + }, + { + "epoch": 0.1, + "learning_rate": 1.9773013667060832e-05, + "loss": 0.5395, + "step": 1125 + }, + { + "epoch": 0.1, + "learning_rate": 1.9772428239562273e-05, + "loss": 0.5049, + "step": 1126 + }, + { + "epoch": 0.1, + "learning_rate": 1.977184206677754e-05, + "loss": 0.5205, + "step": 1127 + }, + { + "epoch": 0.1, + "learning_rate": 1.977125514875133e-05, + "loss": 0.5174, + "step": 1128 + }, + { + "epoch": 0.1, + "learning_rate": 1.9770667485528413e-05, + "loss": 0.4972, + "step": 1129 + }, + { + "epoch": 0.1, + "learning_rate": 1.9770079077153604e-05, + "loss": 0.5308, + "step": 1130 + }, + { + "epoch": 0.1, + "learning_rate": 1.976948992367177e-05, + "loss": 0.5004, + "step": 1131 + }, + { + "epoch": 0.1, + "learning_rate": 1.9768900025127852e-05, + "loss": 0.523, + "step": 1132 + }, + { + "epoch": 0.1, + "learning_rate": 1.976830938156683e-05, + "loss": 0.5098, + "step": 1133 + }, + { + "epoch": 0.1, + "learning_rate": 1.976771799303376e-05, + "loss": 0.5335, + "step": 1134 + }, + { + "epoch": 0.1, + "learning_rate": 1.9767125859573735e-05, + "loss": 0.5213, + "step": 1135 + }, + { + "epoch": 0.1, + "learning_rate": 1.9766532981231913e-05, + "loss": 0.5005, + "step": 1136 + }, + { + "epoch": 0.1, + "learning_rate": 1.9765939358053512e-05, + "loss": 0.511, + "step": 1137 + }, + { + "epoch": 0.1, + "learning_rate": 1.9765344990083807e-05, + "loss": 0.4862, + "step": 1138 + }, + { + "epoch": 0.1, + "learning_rate": 1.976474987736812e-05, + "loss": 0.4992, + "step": 1139 + }, + { + "epoch": 0.1, + "learning_rate": 1.976415401995184e-05, + "loss": 0.5096, + "step": 1140 + }, + { + "epoch": 0.1, + "learning_rate": 1.9763557417880412e-05, + "loss": 0.499, + "step": 1141 + }, + { + "epoch": 0.1, + "learning_rate": 1.9762960071199334e-05, + "loss": 0.5044, + "step": 1142 + }, + { + "epoch": 0.1, + "learning_rate": 1.9762361979954164e-05, + "loss": 0.4965, + "step": 1143 + }, + { + "epoch": 0.1, + "learning_rate": 1.976176314419051e-05, + "loss": 0.5544, + "step": 1144 + }, + { + "epoch": 0.1, + "learning_rate": 1.9761163563954047e-05, + "loss": 0.5192, + "step": 1145 + }, + { + "epoch": 0.1, + "learning_rate": 1.9760563239290495e-05, + "loss": 0.5182, + "step": 1146 + }, + { + "epoch": 0.1, + "learning_rate": 1.9759962170245647e-05, + "loss": 0.5148, + "step": 1147 + }, + { + "epoch": 0.1, + "learning_rate": 1.9759360356865328e-05, + "loss": 0.5167, + "step": 1148 + }, + { + "epoch": 0.1, + "learning_rate": 1.9758757799195454e-05, + "loss": 0.5039, + "step": 1149 + }, + { + "epoch": 0.1, + "learning_rate": 1.975815449728196e-05, + "loss": 0.5091, + "step": 1150 + }, + { + "epoch": 0.1, + "learning_rate": 1.975755045117087e-05, + "loss": 0.4961, + "step": 1151 + }, + { + "epoch": 0.1, + "learning_rate": 1.975694566090825e-05, + "loss": 0.517, + "step": 1152 + }, + { + "epoch": 0.1, + "learning_rate": 1.9756340126540216e-05, + "loss": 0.5197, + "step": 1153 + }, + { + "epoch": 0.1, + "learning_rate": 1.9755733848112946e-05, + "loss": 0.511, + "step": 1154 + }, + { + "epoch": 0.1, + "learning_rate": 1.9755126825672692e-05, + "loss": 0.502, + "step": 1155 + }, + { + "epoch": 0.1, + "learning_rate": 1.9754519059265737e-05, + "loss": 0.503, + "step": 1156 + }, + { + "epoch": 0.1, + "learning_rate": 1.9753910548938436e-05, + "loss": 0.5168, + "step": 1157 + }, + { + "epoch": 0.1, + "learning_rate": 1.9753301294737195e-05, + "loss": 0.5187, + "step": 1158 + }, + { + "epoch": 0.1, + "learning_rate": 1.9752691296708476e-05, + "loss": 0.5103, + "step": 1159 + }, + { + "epoch": 0.1, + "learning_rate": 1.9752080554898808e-05, + "loss": 0.5246, + "step": 1160 + }, + { + "epoch": 0.1, + "learning_rate": 1.9751469069354757e-05, + "loss": 0.5179, + "step": 1161 + }, + { + "epoch": 0.1, + "learning_rate": 1.9750856840122968e-05, + "loss": 0.5008, + "step": 1162 + }, + { + "epoch": 0.1, + "learning_rate": 1.9750243867250127e-05, + "loss": 0.4984, + "step": 1163 + }, + { + "epoch": 0.1, + "learning_rate": 1.9749630150782978e-05, + "loss": 0.5235, + "step": 1164 + }, + { + "epoch": 0.1, + "learning_rate": 1.9749015690768333e-05, + "loss": 0.5074, + "step": 1165 + }, + { + "epoch": 0.1, + "learning_rate": 1.9748400487253052e-05, + "loss": 0.5156, + "step": 1166 + }, + { + "epoch": 0.1, + "learning_rate": 1.974778454028405e-05, + "loss": 0.5041, + "step": 1167 + }, + { + "epoch": 0.1, + "learning_rate": 1.9747167849908305e-05, + "loss": 0.4839, + "step": 1168 + }, + { + "epoch": 0.1, + "learning_rate": 1.9746550416172842e-05, + "loss": 0.5191, + "step": 1169 + }, + { + "epoch": 0.1, + "learning_rate": 1.9745932239124758e-05, + "loss": 0.5092, + "step": 1170 + }, + { + "epoch": 0.1, + "learning_rate": 1.9745313318811195e-05, + "loss": 0.5044, + "step": 1171 + }, + { + "epoch": 0.1, + "learning_rate": 1.9744693655279347e-05, + "loss": 0.5118, + "step": 1172 + }, + { + "epoch": 0.1, + "learning_rate": 1.9744073248576485e-05, + "loss": 0.4978, + "step": 1173 + }, + { + "epoch": 0.1, + "learning_rate": 1.974345209874991e-05, + "loss": 0.5016, + "step": 1174 + }, + { + "epoch": 0.1, + "learning_rate": 1.9742830205847006e-05, + "loss": 0.4913, + "step": 1175 + }, + { + "epoch": 0.1, + "learning_rate": 1.974220756991519e-05, + "loss": 0.5207, + "step": 1176 + }, + { + "epoch": 0.1, + "learning_rate": 1.9741584191001956e-05, + "loss": 0.5068, + "step": 1177 + }, + { + "epoch": 0.1, + "learning_rate": 1.974096006915484e-05, + "loss": 0.5258, + "step": 1178 + }, + { + "epoch": 0.1, + "learning_rate": 1.974033520442144e-05, + "loss": 0.5349, + "step": 1179 + }, + { + "epoch": 0.1, + "learning_rate": 1.9739709596849418e-05, + "loss": 0.5248, + "step": 1180 + }, + { + "epoch": 0.1, + "learning_rate": 1.9739083246486478e-05, + "loss": 0.5162, + "step": 1181 + }, + { + "epoch": 0.1, + "learning_rate": 1.9738456153380388e-05, + "loss": 0.4908, + "step": 1182 + }, + { + "epoch": 0.1, + "learning_rate": 1.9737828317578977e-05, + "loss": 0.5192, + "step": 1183 + }, + { + "epoch": 0.1, + "learning_rate": 1.9737199739130123e-05, + "loss": 0.5086, + "step": 1184 + }, + { + "epoch": 0.1, + "learning_rate": 1.9736570418081763e-05, + "loss": 0.5064, + "step": 1185 + }, + { + "epoch": 0.1, + "learning_rate": 1.97359403544819e-05, + "loss": 0.5058, + "step": 1186 + }, + { + "epoch": 0.1, + "learning_rate": 1.9735309548378575e-05, + "loss": 0.5141, + "step": 1187 + }, + { + "epoch": 0.1, + "learning_rate": 1.97346779998199e-05, + "loss": 0.5035, + "step": 1188 + }, + { + "epoch": 0.1, + "learning_rate": 1.9734045708854044e-05, + "loss": 0.5119, + "step": 1189 + }, + { + "epoch": 0.1, + "learning_rate": 1.973341267552922e-05, + "loss": 0.5479, + "step": 1190 + }, + { + "epoch": 0.1, + "learning_rate": 1.9732778899893707e-05, + "loss": 0.5206, + "step": 1191 + }, + { + "epoch": 0.1, + "learning_rate": 1.9732144381995848e-05, + "loss": 0.5172, + "step": 1192 + }, + { + "epoch": 0.1, + "learning_rate": 1.9731509121884023e-05, + "loss": 0.5162, + "step": 1193 + }, + { + "epoch": 0.1, + "learning_rate": 1.9730873119606687e-05, + "loss": 0.5044, + "step": 1194 + }, + { + "epoch": 0.1, + "learning_rate": 1.973023637521234e-05, + "loss": 0.5025, + "step": 1195 + }, + { + "epoch": 0.1, + "learning_rate": 1.972959888874955e-05, + "loss": 0.5075, + "step": 1196 + }, + { + "epoch": 0.1, + "learning_rate": 1.9728960660266923e-05, + "loss": 0.499, + "step": 1197 + }, + { + "epoch": 0.1, + "learning_rate": 1.9728321689813142e-05, + "loss": 0.5213, + "step": 1198 + }, + { + "epoch": 0.1, + "learning_rate": 1.972768197743693e-05, + "loss": 0.5083, + "step": 1199 + }, + { + "epoch": 0.1, + "learning_rate": 1.9727041523187083e-05, + "loss": 0.5068, + "step": 1200 + }, + { + "epoch": 0.1, + "learning_rate": 1.9726400327112437e-05, + "loss": 0.5045, + "step": 1201 + }, + { + "epoch": 0.1, + "learning_rate": 1.97257583892619e-05, + "loss": 0.5254, + "step": 1202 + }, + { + "epoch": 0.1, + "learning_rate": 1.972511570968442e-05, + "loss": 0.5036, + "step": 1203 + }, + { + "epoch": 0.1, + "learning_rate": 1.972447228842902e-05, + "loss": 0.5047, + "step": 1204 + }, + { + "epoch": 0.1, + "learning_rate": 1.972382812554476e-05, + "loss": 0.4964, + "step": 1205 + }, + { + "epoch": 0.1, + "learning_rate": 1.9723183221080774e-05, + "loss": 0.5211, + "step": 1206 + }, + { + "epoch": 0.1, + "learning_rate": 1.972253757508624e-05, + "loss": 0.4983, + "step": 1207 + }, + { + "epoch": 0.1, + "learning_rate": 1.97218911876104e-05, + "loss": 0.5293, + "step": 1208 + }, + { + "epoch": 0.1, + "learning_rate": 1.972124405870255e-05, + "loss": 0.5165, + "step": 1209 + }, + { + "epoch": 0.1, + "learning_rate": 1.972059618841205e-05, + "loss": 0.5102, + "step": 1210 + }, + { + "epoch": 0.1, + "learning_rate": 1.9719947576788298e-05, + "loss": 0.5116, + "step": 1211 + }, + { + "epoch": 0.1, + "learning_rate": 1.9719298223880763e-05, + "loss": 0.5192, + "step": 1212 + }, + { + "epoch": 0.1, + "learning_rate": 1.971864812973897e-05, + "loss": 0.5301, + "step": 1213 + }, + { + "epoch": 0.1, + "learning_rate": 1.9717997294412493e-05, + "loss": 0.4978, + "step": 1214 + }, + { + "epoch": 0.1, + "learning_rate": 1.9717345717950972e-05, + "loss": 0.509, + "step": 1215 + }, + { + "epoch": 0.1, + "learning_rate": 1.97166934004041e-05, + "loss": 0.5348, + "step": 1216 + }, + { + "epoch": 0.1, + "learning_rate": 1.971604034182162e-05, + "loss": 0.5146, + "step": 1217 + }, + { + "epoch": 0.1, + "learning_rate": 1.9715386542253348e-05, + "loss": 0.5086, + "step": 1218 + }, + { + "epoch": 0.1, + "learning_rate": 1.9714732001749134e-05, + "loss": 0.504, + "step": 1219 + }, + { + "epoch": 0.1, + "learning_rate": 1.9714076720358898e-05, + "loss": 0.4975, + "step": 1220 + }, + { + "epoch": 0.1, + "learning_rate": 1.9713420698132614e-05, + "loss": 0.5259, + "step": 1221 + }, + { + "epoch": 0.1, + "learning_rate": 1.971276393512032e-05, + "loss": 0.5166, + "step": 1222 + }, + { + "epoch": 0.1, + "learning_rate": 1.9712106431372095e-05, + "loss": 0.5211, + "step": 1223 + }, + { + "epoch": 0.1, + "learning_rate": 1.971144818693809e-05, + "loss": 0.5034, + "step": 1224 + }, + { + "epoch": 0.1, + "learning_rate": 1.97107892018685e-05, + "loss": 0.4949, + "step": 1225 + }, + { + "epoch": 0.1, + "learning_rate": 1.9710129476213587e-05, + "loss": 0.5245, + "step": 1226 + }, + { + "epoch": 0.1, + "learning_rate": 1.970946901002366e-05, + "loss": 0.5122, + "step": 1227 + }, + { + "epoch": 0.1, + "learning_rate": 1.970880780334909e-05, + "loss": 0.5051, + "step": 1228 + }, + { + "epoch": 0.1, + "learning_rate": 1.9708145856240302e-05, + "loss": 0.5143, + "step": 1229 + }, + { + "epoch": 0.1, + "learning_rate": 1.970748316874778e-05, + "loss": 0.5078, + "step": 1230 + }, + { + "epoch": 0.1, + "learning_rate": 1.9706819740922068e-05, + "loss": 0.513, + "step": 1231 + }, + { + "epoch": 0.11, + "learning_rate": 1.970615557281376e-05, + "loss": 0.5245, + "step": 1232 + }, + { + "epoch": 0.11, + "learning_rate": 1.97054906644735e-05, + "loss": 0.5292, + "step": 1233 + }, + { + "epoch": 0.11, + "learning_rate": 1.9704825015952005e-05, + "loss": 0.5095, + "step": 1234 + }, + { + "epoch": 0.11, + "learning_rate": 1.970415862730004e-05, + "loss": 0.5238, + "step": 1235 + }, + { + "epoch": 0.11, + "learning_rate": 1.970349149856842e-05, + "loss": 0.5118, + "step": 1236 + }, + { + "epoch": 0.11, + "learning_rate": 1.970282362980803e-05, + "loss": 0.5026, + "step": 1237 + }, + { + "epoch": 0.11, + "learning_rate": 1.97021550210698e-05, + "loss": 0.5219, + "step": 1238 + }, + { + "epoch": 0.11, + "learning_rate": 1.9701485672404725e-05, + "loss": 0.5132, + "step": 1239 + }, + { + "epoch": 0.11, + "learning_rate": 1.9700815583863853e-05, + "loss": 0.5056, + "step": 1240 + }, + { + "epoch": 0.11, + "learning_rate": 1.970014475549828e-05, + "loss": 0.51, + "step": 1241 + }, + { + "epoch": 0.11, + "learning_rate": 1.969947318735917e-05, + "loss": 0.5229, + "step": 1242 + }, + { + "epoch": 0.11, + "learning_rate": 1.9698800879497747e-05, + "loss": 0.5158, + "step": 1243 + }, + { + "epoch": 0.11, + "learning_rate": 1.9698127831965276e-05, + "loss": 0.5177, + "step": 1244 + }, + { + "epoch": 0.11, + "learning_rate": 1.969745404481308e-05, + "loss": 0.5248, + "step": 1245 + }, + { + "epoch": 0.11, + "learning_rate": 1.9696779518092564e-05, + "loss": 0.4828, + "step": 1246 + }, + { + "epoch": 0.11, + "learning_rate": 1.9696104251855154e-05, + "loss": 0.5141, + "step": 1247 + }, + { + "epoch": 0.11, + "learning_rate": 1.969542824615235e-05, + "loss": 0.5057, + "step": 1248 + }, + { + "epoch": 0.11, + "learning_rate": 1.9694751501035715e-05, + "loss": 0.504, + "step": 1249 + }, + { + "epoch": 0.11, + "learning_rate": 1.9694074016556855e-05, + "loss": 0.5431, + "step": 1250 + }, + { + "epoch": 0.11, + "learning_rate": 1.9693395792767443e-05, + "loss": 0.5062, + "step": 1251 + }, + { + "epoch": 0.11, + "learning_rate": 1.9692716829719197e-05, + "loss": 0.5028, + "step": 1252 + }, + { + "epoch": 0.11, + "learning_rate": 1.9692037127463898e-05, + "loss": 0.5105, + "step": 1253 + }, + { + "epoch": 0.11, + "learning_rate": 1.9691356686053386e-05, + "loss": 0.5041, + "step": 1254 + }, + { + "epoch": 0.11, + "learning_rate": 1.969067550553955e-05, + "loss": 0.5161, + "step": 1255 + }, + { + "epoch": 0.11, + "learning_rate": 1.9689993585974344e-05, + "loss": 0.5066, + "step": 1256 + }, + { + "epoch": 0.11, + "learning_rate": 1.9689310927409773e-05, + "loss": 0.5009, + "step": 1257 + }, + { + "epoch": 0.11, + "learning_rate": 1.96886275298979e-05, + "loss": 0.5185, + "step": 1258 + }, + { + "epoch": 0.11, + "learning_rate": 1.968794339349084e-05, + "loss": 0.5109, + "step": 1259 + }, + { + "epoch": 0.11, + "learning_rate": 1.9687258518240773e-05, + "loss": 0.4889, + "step": 1260 + }, + { + "epoch": 0.11, + "learning_rate": 1.9686572904199928e-05, + "loss": 0.5149, + "step": 1261 + }, + { + "epoch": 0.11, + "learning_rate": 1.9685886551420596e-05, + "loss": 0.5004, + "step": 1262 + }, + { + "epoch": 0.11, + "learning_rate": 1.9685199459955116e-05, + "loss": 0.52, + "step": 1263 + }, + { + "epoch": 0.11, + "learning_rate": 1.968451162985589e-05, + "loss": 0.5105, + "step": 1264 + }, + { + "epoch": 0.11, + "learning_rate": 1.9683823061175375e-05, + "loss": 0.5035, + "step": 1265 + }, + { + "epoch": 0.11, + "learning_rate": 1.9683133753966085e-05, + "loss": 0.5106, + "step": 1266 + }, + { + "epoch": 0.11, + "learning_rate": 1.968244370828059e-05, + "loss": 0.4906, + "step": 1267 + }, + { + "epoch": 0.11, + "learning_rate": 1.9681752924171513e-05, + "loss": 0.5295, + "step": 1268 + }, + { + "epoch": 0.11, + "learning_rate": 1.968106140169154e-05, + "loss": 0.5084, + "step": 1269 + }, + { + "epoch": 0.11, + "learning_rate": 1.9680369140893405e-05, + "loss": 0.5014, + "step": 1270 + }, + { + "epoch": 0.11, + "learning_rate": 1.9679676141829905e-05, + "loss": 0.4938, + "step": 1271 + }, + { + "epoch": 0.11, + "learning_rate": 1.9678982404553896e-05, + "loss": 0.5052, + "step": 1272 + }, + { + "epoch": 0.11, + "learning_rate": 1.9678287929118275e-05, + "loss": 0.5031, + "step": 1273 + }, + { + "epoch": 0.11, + "learning_rate": 1.9677592715576013e-05, + "loss": 0.52, + "step": 1274 + }, + { + "epoch": 0.11, + "learning_rate": 1.9676896763980127e-05, + "loss": 0.5125, + "step": 1275 + }, + { + "epoch": 0.11, + "learning_rate": 1.9676200074383692e-05, + "loss": 0.5117, + "step": 1276 + }, + { + "epoch": 0.11, + "learning_rate": 1.9675502646839848e-05, + "loss": 0.5305, + "step": 1277 + }, + { + "epoch": 0.11, + "learning_rate": 1.967480448140177e-05, + "loss": 0.5028, + "step": 1278 + }, + { + "epoch": 0.11, + "learning_rate": 1.967410557812272e-05, + "loss": 0.5002, + "step": 1279 + }, + { + "epoch": 0.11, + "learning_rate": 1.9673405937055986e-05, + "loss": 0.5264, + "step": 1280 + }, + { + "epoch": 0.11, + "learning_rate": 1.967270555825493e-05, + "loss": 0.5288, + "step": 1281 + }, + { + "epoch": 0.11, + "learning_rate": 1.9672004441772966e-05, + "loss": 0.5052, + "step": 1282 + }, + { + "epoch": 0.11, + "learning_rate": 1.9671302587663566e-05, + "loss": 0.514, + "step": 1283 + }, + { + "epoch": 0.11, + "learning_rate": 1.967059999598025e-05, + "loss": 0.5326, + "step": 1284 + }, + { + "epoch": 0.11, + "learning_rate": 1.9669896666776606e-05, + "loss": 0.4978, + "step": 1285 + }, + { + "epoch": 0.11, + "learning_rate": 1.9669192600106275e-05, + "loss": 0.5187, + "step": 1286 + }, + { + "epoch": 0.11, + "learning_rate": 1.9668487796022947e-05, + "loss": 0.5316, + "step": 1287 + }, + { + "epoch": 0.11, + "learning_rate": 1.9667782254580373e-05, + "loss": 0.4921, + "step": 1288 + }, + { + "epoch": 0.11, + "learning_rate": 1.9667075975832362e-05, + "loss": 0.5102, + "step": 1289 + }, + { + "epoch": 0.11, + "learning_rate": 1.9666368959832783e-05, + "loss": 0.5152, + "step": 1290 + }, + { + "epoch": 0.11, + "learning_rate": 1.9665661206635548e-05, + "loss": 0.5166, + "step": 1291 + }, + { + "epoch": 0.11, + "learning_rate": 1.9664952716294636e-05, + "loss": 0.4985, + "step": 1292 + }, + { + "epoch": 0.11, + "learning_rate": 1.9664243488864078e-05, + "loss": 0.5067, + "step": 1293 + }, + { + "epoch": 0.11, + "learning_rate": 1.9663533524397968e-05, + "loss": 0.4999, + "step": 1294 + }, + { + "epoch": 0.11, + "learning_rate": 1.9662822822950446e-05, + "loss": 0.4971, + "step": 1295 + }, + { + "epoch": 0.11, + "learning_rate": 1.9662111384575716e-05, + "loss": 0.4992, + "step": 1296 + }, + { + "epoch": 0.11, + "learning_rate": 1.966139920932803e-05, + "loss": 0.5099, + "step": 1297 + }, + { + "epoch": 0.11, + "learning_rate": 1.966068629726171e-05, + "loss": 0.5093, + "step": 1298 + }, + { + "epoch": 0.11, + "learning_rate": 1.965997264843112e-05, + "loss": 0.5167, + "step": 1299 + }, + { + "epoch": 0.11, + "learning_rate": 1.9659258262890683e-05, + "loss": 0.5118, + "step": 1300 + }, + { + "epoch": 0.11, + "learning_rate": 1.965854314069489e-05, + "loss": 0.496, + "step": 1301 + }, + { + "epoch": 0.11, + "learning_rate": 1.965782728189827e-05, + "loss": 0.5074, + "step": 1302 + }, + { + "epoch": 0.11, + "learning_rate": 1.965711068655542e-05, + "loss": 0.5143, + "step": 1303 + }, + { + "epoch": 0.11, + "learning_rate": 1.9656393354720994e-05, + "loss": 0.4998, + "step": 1304 + }, + { + "epoch": 0.11, + "learning_rate": 1.9655675286449697e-05, + "loss": 0.4935, + "step": 1305 + }, + { + "epoch": 0.11, + "learning_rate": 1.965495648179629e-05, + "loss": 0.5156, + "step": 1306 + }, + { + "epoch": 0.11, + "learning_rate": 1.9654236940815596e-05, + "loss": 0.5062, + "step": 1307 + }, + { + "epoch": 0.11, + "learning_rate": 1.9653516663562485e-05, + "loss": 0.4936, + "step": 1308 + }, + { + "epoch": 0.11, + "learning_rate": 1.965279565009189e-05, + "loss": 0.498, + "step": 1309 + }, + { + "epoch": 0.11, + "learning_rate": 1.9652073900458806e-05, + "loss": 0.5243, + "step": 1310 + }, + { + "epoch": 0.11, + "learning_rate": 1.9651351414718263e-05, + "loss": 0.5046, + "step": 1311 + }, + { + "epoch": 0.11, + "learning_rate": 1.9650628192925372e-05, + "loss": 0.5169, + "step": 1312 + }, + { + "epoch": 0.11, + "learning_rate": 1.9649904235135283e-05, + "loss": 0.5363, + "step": 1313 + }, + { + "epoch": 0.11, + "learning_rate": 1.964917954140321e-05, + "loss": 0.4991, + "step": 1314 + }, + { + "epoch": 0.11, + "learning_rate": 1.964845411178442e-05, + "loss": 0.5128, + "step": 1315 + }, + { + "epoch": 0.11, + "learning_rate": 1.964772794633424e-05, + "loss": 0.5141, + "step": 1316 + }, + { + "epoch": 0.11, + "learning_rate": 1.964700104510805e-05, + "loss": 0.4971, + "step": 1317 + }, + { + "epoch": 0.11, + "learning_rate": 1.9646273408161286e-05, + "loss": 0.5191, + "step": 1318 + }, + { + "epoch": 0.11, + "learning_rate": 1.9645545035549437e-05, + "loss": 0.5007, + "step": 1319 + }, + { + "epoch": 0.11, + "learning_rate": 1.9644815927328055e-05, + "loss": 0.5172, + "step": 1320 + }, + { + "epoch": 0.11, + "learning_rate": 1.9644086083552745e-05, + "loss": 0.512, + "step": 1321 + }, + { + "epoch": 0.11, + "learning_rate": 1.9643355504279164e-05, + "loss": 0.4929, + "step": 1322 + }, + { + "epoch": 0.11, + "learning_rate": 1.964262418956304e-05, + "loss": 0.5147, + "step": 1323 + }, + { + "epoch": 0.11, + "learning_rate": 1.9641892139460133e-05, + "loss": 0.5028, + "step": 1324 + }, + { + "epoch": 0.11, + "learning_rate": 1.964115935402628e-05, + "loss": 0.5183, + "step": 1325 + }, + { + "epoch": 0.11, + "learning_rate": 1.964042583331736e-05, + "loss": 0.5044, + "step": 1326 + }, + { + "epoch": 0.11, + "learning_rate": 1.9639691577389322e-05, + "loss": 0.4925, + "step": 1327 + }, + { + "epoch": 0.11, + "learning_rate": 1.963895658629816e-05, + "loss": 0.5059, + "step": 1328 + }, + { + "epoch": 0.11, + "learning_rate": 1.9638220860099927e-05, + "loss": 0.4974, + "step": 1329 + }, + { + "epoch": 0.11, + "learning_rate": 1.963748439885073e-05, + "loss": 0.5043, + "step": 1330 + }, + { + "epoch": 0.11, + "learning_rate": 1.963674720260674e-05, + "loss": 0.5343, + "step": 1331 + }, + { + "epoch": 0.11, + "learning_rate": 1.9636009271424177e-05, + "loss": 0.5099, + "step": 1332 + }, + { + "epoch": 0.11, + "learning_rate": 1.963527060535932e-05, + "loss": 0.5293, + "step": 1333 + }, + { + "epoch": 0.11, + "learning_rate": 1.9634531204468493e-05, + "loss": 0.5068, + "step": 1334 + }, + { + "epoch": 0.11, + "learning_rate": 1.96337910688081e-05, + "loss": 0.5242, + "step": 1335 + }, + { + "epoch": 0.11, + "learning_rate": 1.9633050198434578e-05, + "loss": 0.5008, + "step": 1336 + }, + { + "epoch": 0.11, + "learning_rate": 1.9632308593404432e-05, + "loss": 0.4987, + "step": 1337 + }, + { + "epoch": 0.11, + "learning_rate": 1.9631566253774216e-05, + "loss": 0.5042, + "step": 1338 + }, + { + "epoch": 0.11, + "learning_rate": 1.9630823179600548e-05, + "loss": 0.5238, + "step": 1339 + }, + { + "epoch": 0.11, + "learning_rate": 1.9630079370940098e-05, + "loss": 0.4805, + "step": 1340 + }, + { + "epoch": 0.11, + "learning_rate": 1.9629334827849594e-05, + "loss": 0.5075, + "step": 1341 + }, + { + "epoch": 0.11, + "learning_rate": 1.962858955038581e-05, + "loss": 0.5159, + "step": 1342 + }, + { + "epoch": 0.11, + "learning_rate": 1.9627843538605588e-05, + "loss": 0.5023, + "step": 1343 + }, + { + "epoch": 0.11, + "learning_rate": 1.9627096792565825e-05, + "loss": 0.5085, + "step": 1344 + }, + { + "epoch": 0.11, + "learning_rate": 1.962634931232347e-05, + "loss": 0.5054, + "step": 1345 + }, + { + "epoch": 0.11, + "learning_rate": 1.9625601097935525e-05, + "loss": 0.5219, + "step": 1346 + }, + { + "epoch": 0.11, + "learning_rate": 1.9624852149459056e-05, + "loss": 0.5131, + "step": 1347 + }, + { + "epoch": 0.11, + "learning_rate": 1.962410246695118e-05, + "loss": 0.5105, + "step": 1348 + }, + { + "epoch": 0.12, + "learning_rate": 1.962335205046907e-05, + "loss": 0.5056, + "step": 1349 + }, + { + "epoch": 0.12, + "learning_rate": 1.9622600900069953e-05, + "loss": 0.4835, + "step": 1350 + }, + { + "epoch": 0.12, + "learning_rate": 1.9621849015811123e-05, + "loss": 0.5335, + "step": 1351 + }, + { + "epoch": 0.12, + "learning_rate": 1.9621096397749918e-05, + "loss": 0.5174, + "step": 1352 + }, + { + "epoch": 0.12, + "learning_rate": 1.962034304594373e-05, + "loss": 0.4933, + "step": 1353 + }, + { + "epoch": 0.12, + "learning_rate": 1.961958896045002e-05, + "loss": 0.5122, + "step": 1354 + }, + { + "epoch": 0.12, + "learning_rate": 1.9618834141326294e-05, + "loss": 0.5301, + "step": 1355 + }, + { + "epoch": 0.12, + "learning_rate": 1.961807858863012e-05, + "loss": 0.5101, + "step": 1356 + }, + { + "epoch": 0.12, + "learning_rate": 1.961732230241912e-05, + "loss": 0.5144, + "step": 1357 + }, + { + "epoch": 0.12, + "learning_rate": 1.9616565282750967e-05, + "loss": 0.5231, + "step": 1358 + }, + { + "epoch": 0.12, + "learning_rate": 1.96158075296834e-05, + "loss": 0.5087, + "step": 1359 + }, + { + "epoch": 0.12, + "learning_rate": 1.9615049043274207e-05, + "loss": 0.4929, + "step": 1360 + }, + { + "epoch": 0.12, + "learning_rate": 1.961428982358123e-05, + "loss": 0.495, + "step": 1361 + }, + { + "epoch": 0.12, + "learning_rate": 1.9613529870662372e-05, + "loss": 0.5189, + "step": 1362 + }, + { + "epoch": 0.12, + "learning_rate": 1.9612769184575592e-05, + "loss": 0.4931, + "step": 1363 + }, + { + "epoch": 0.12, + "learning_rate": 1.9612007765378904e-05, + "loss": 0.5168, + "step": 1364 + }, + { + "epoch": 0.12, + "learning_rate": 1.961124561313037e-05, + "loss": 0.4977, + "step": 1365 + }, + { + "epoch": 0.12, + "learning_rate": 1.9610482727888126e-05, + "loss": 0.4949, + "step": 1366 + }, + { + "epoch": 0.12, + "learning_rate": 1.960971910971034e-05, + "loss": 0.5055, + "step": 1367 + }, + { + "epoch": 0.12, + "learning_rate": 1.960895475865526e-05, + "loss": 0.5141, + "step": 1368 + }, + { + "epoch": 0.12, + "learning_rate": 1.960818967478117e-05, + "loss": 0.4859, + "step": 1369 + }, + { + "epoch": 0.12, + "learning_rate": 1.9607423858146427e-05, + "loss": 0.5108, + "step": 1370 + }, + { + "epoch": 0.12, + "learning_rate": 1.9606657308809428e-05, + "loss": 0.5099, + "step": 1371 + }, + { + "epoch": 0.12, + "learning_rate": 1.9605890026828634e-05, + "loss": 0.5077, + "step": 1372 + }, + { + "epoch": 0.12, + "learning_rate": 1.9605122012262567e-05, + "loss": 0.4997, + "step": 1373 + }, + { + "epoch": 0.12, + "learning_rate": 1.9604353265169796e-05, + "loss": 0.5077, + "step": 1374 + }, + { + "epoch": 0.12, + "learning_rate": 1.9603583785608947e-05, + "loss": 0.5029, + "step": 1375 + }, + { + "epoch": 0.12, + "learning_rate": 1.9602813573638705e-05, + "loss": 0.5115, + "step": 1376 + }, + { + "epoch": 0.12, + "learning_rate": 1.9602042629317807e-05, + "loss": 0.5018, + "step": 1377 + }, + { + "epoch": 0.12, + "learning_rate": 1.960127095270505e-05, + "loss": 0.5299, + "step": 1378 + }, + { + "epoch": 0.12, + "learning_rate": 1.960049854385929e-05, + "loss": 0.4805, + "step": 1379 + }, + { + "epoch": 0.12, + "learning_rate": 1.9599725402839427e-05, + "loss": 0.5219, + "step": 1380 + }, + { + "epoch": 0.12, + "learning_rate": 1.9598951529704426e-05, + "loss": 0.5044, + "step": 1381 + }, + { + "epoch": 0.12, + "learning_rate": 1.959817692451331e-05, + "loss": 0.5166, + "step": 1382 + }, + { + "epoch": 0.12, + "learning_rate": 1.959740158732515e-05, + "loss": 0.5231, + "step": 1383 + }, + { + "epoch": 0.12, + "learning_rate": 1.9596625518199077e-05, + "loss": 0.5081, + "step": 1384 + }, + { + "epoch": 0.12, + "learning_rate": 1.9595848717194276e-05, + "loss": 0.4953, + "step": 1385 + }, + { + "epoch": 0.12, + "learning_rate": 1.9595071184369994e-05, + "loss": 0.4972, + "step": 1386 + }, + { + "epoch": 0.12, + "learning_rate": 1.9594292919785523e-05, + "loss": 0.5233, + "step": 1387 + }, + { + "epoch": 0.12, + "learning_rate": 1.959351392350022e-05, + "loss": 0.5184, + "step": 1388 + }, + { + "epoch": 0.12, + "learning_rate": 1.959273419557349e-05, + "loss": 0.4998, + "step": 1389 + }, + { + "epoch": 0.12, + "learning_rate": 1.9591953736064804e-05, + "loss": 0.5319, + "step": 1390 + }, + { + "epoch": 0.12, + "learning_rate": 1.959117254503368e-05, + "loss": 0.5126, + "step": 1391 + }, + { + "epoch": 0.12, + "learning_rate": 1.9590390622539696e-05, + "loss": 0.5247, + "step": 1392 + }, + { + "epoch": 0.12, + "learning_rate": 1.9589607968642483e-05, + "loss": 0.5052, + "step": 1393 + }, + { + "epoch": 0.12, + "learning_rate": 1.9588824583401735e-05, + "loss": 0.5061, + "step": 1394 + }, + { + "epoch": 0.12, + "learning_rate": 1.958804046687719e-05, + "loss": 0.4865, + "step": 1395 + }, + { + "epoch": 0.12, + "learning_rate": 1.9587255619128648e-05, + "loss": 0.5032, + "step": 1396 + }, + { + "epoch": 0.12, + "learning_rate": 1.958647004021597e-05, + "loss": 0.5219, + "step": 1397 + }, + { + "epoch": 0.12, + "learning_rate": 1.958568373019906e-05, + "loss": 0.4901, + "step": 1398 + }, + { + "epoch": 0.12, + "learning_rate": 1.9584896689137897e-05, + "loss": 0.5112, + "step": 1399 + }, + { + "epoch": 0.12, + "learning_rate": 1.9584108917092492e-05, + "loss": 0.5128, + "step": 1400 + }, + { + "epoch": 0.12, + "learning_rate": 1.958332041412293e-05, + "loss": 0.5305, + "step": 1401 + }, + { + "epoch": 0.12, + "learning_rate": 1.9582531180289342e-05, + "loss": 0.5034, + "step": 1402 + }, + { + "epoch": 0.12, + "learning_rate": 1.9581741215651923e-05, + "loss": 0.5128, + "step": 1403 + }, + { + "epoch": 0.12, + "learning_rate": 1.9580950520270914e-05, + "loss": 0.5049, + "step": 1404 + }, + { + "epoch": 0.12, + "learning_rate": 1.9580159094206622e-05, + "loss": 0.5127, + "step": 1405 + }, + { + "epoch": 0.12, + "learning_rate": 1.9579366937519398e-05, + "loss": 0.5143, + "step": 1406 + }, + { + "epoch": 0.12, + "learning_rate": 1.9578574050269662e-05, + "loss": 0.5137, + "step": 1407 + }, + { + "epoch": 0.12, + "learning_rate": 1.957778043251788e-05, + "loss": 0.5009, + "step": 1408 + }, + { + "epoch": 0.12, + "learning_rate": 1.957698608432457e-05, + "loss": 0.5156, + "step": 1409 + }, + { + "epoch": 0.12, + "learning_rate": 1.9576191005750323e-05, + "loss": 0.5194, + "step": 1410 + }, + { + "epoch": 0.12, + "learning_rate": 1.957539519685577e-05, + "loss": 0.4981, + "step": 1411 + }, + { + "epoch": 0.12, + "learning_rate": 1.9574598657701604e-05, + "loss": 0.5123, + "step": 1412 + }, + { + "epoch": 0.12, + "learning_rate": 1.9573801388348572e-05, + "loss": 0.5247, + "step": 1413 + }, + { + "epoch": 0.12, + "learning_rate": 1.9573003388857476e-05, + "loss": 0.511, + "step": 1414 + }, + { + "epoch": 0.12, + "learning_rate": 1.9572204659289175e-05, + "loss": 0.4892, + "step": 1415 + }, + { + "epoch": 0.12, + "learning_rate": 1.9571405199704583e-05, + "loss": 0.4881, + "step": 1416 + }, + { + "epoch": 0.12, + "learning_rate": 1.9570605010164676e-05, + "loss": 0.5239, + "step": 1417 + }, + { + "epoch": 0.12, + "learning_rate": 1.9569804090730467e-05, + "loss": 0.4915, + "step": 1418 + }, + { + "epoch": 0.12, + "learning_rate": 1.956900244146305e-05, + "loss": 0.5199, + "step": 1419 + }, + { + "epoch": 0.12, + "learning_rate": 1.9568200062423557e-05, + "loss": 0.5163, + "step": 1420 + }, + { + "epoch": 0.12, + "learning_rate": 1.956739695367318e-05, + "loss": 0.5048, + "step": 1421 + }, + { + "epoch": 0.12, + "learning_rate": 1.956659311527317e-05, + "loss": 0.5159, + "step": 1422 + }, + { + "epoch": 0.12, + "learning_rate": 1.956578854728483e-05, + "loss": 0.5132, + "step": 1423 + }, + { + "epoch": 0.12, + "learning_rate": 1.9564983249769518e-05, + "loss": 0.501, + "step": 1424 + }, + { + "epoch": 0.12, + "learning_rate": 1.956417722278865e-05, + "loss": 0.5169, + "step": 1425 + }, + { + "epoch": 0.12, + "learning_rate": 1.95633704664037e-05, + "loss": 0.5049, + "step": 1426 + }, + { + "epoch": 0.12, + "learning_rate": 1.956256298067619e-05, + "loss": 0.5289, + "step": 1427 + }, + { + "epoch": 0.12, + "learning_rate": 1.9561754765667705e-05, + "loss": 0.4981, + "step": 1428 + }, + { + "epoch": 0.12, + "learning_rate": 1.9560945821439885e-05, + "loss": 0.5076, + "step": 1429 + }, + { + "epoch": 0.12, + "learning_rate": 1.956013614805442e-05, + "loss": 0.5086, + "step": 1430 + }, + { + "epoch": 0.12, + "learning_rate": 1.955932574557306e-05, + "loss": 0.5008, + "step": 1431 + }, + { + "epoch": 0.12, + "learning_rate": 1.955851461405761e-05, + "loss": 0.5087, + "step": 1432 + }, + { + "epoch": 0.12, + "learning_rate": 1.955770275356993e-05, + "loss": 0.4964, + "step": 1433 + }, + { + "epoch": 0.12, + "learning_rate": 1.9556890164171934e-05, + "loss": 0.4778, + "step": 1434 + }, + { + "epoch": 0.12, + "learning_rate": 1.9556076845925596e-05, + "loss": 0.5298, + "step": 1435 + }, + { + "epoch": 0.12, + "learning_rate": 1.9555262798892943e-05, + "loss": 0.5146, + "step": 1436 + }, + { + "epoch": 0.12, + "learning_rate": 1.9554448023136056e-05, + "loss": 0.4963, + "step": 1437 + }, + { + "epoch": 0.12, + "learning_rate": 1.9553632518717074e-05, + "loss": 0.5254, + "step": 1438 + }, + { + "epoch": 0.12, + "learning_rate": 1.9552816285698193e-05, + "loss": 0.4904, + "step": 1439 + }, + { + "epoch": 0.12, + "learning_rate": 1.9551999324141656e-05, + "loss": 0.5027, + "step": 1440 + }, + { + "epoch": 0.12, + "learning_rate": 1.9551181634109774e-05, + "loss": 0.5009, + "step": 1441 + }, + { + "epoch": 0.12, + "learning_rate": 1.9550363215664906e-05, + "loss": 0.5114, + "step": 1442 + }, + { + "epoch": 0.12, + "learning_rate": 1.954954406886947e-05, + "loss": 0.5179, + "step": 1443 + }, + { + "epoch": 0.12, + "learning_rate": 1.9548724193785933e-05, + "loss": 0.4971, + "step": 1444 + }, + { + "epoch": 0.12, + "learning_rate": 1.9547903590476823e-05, + "loss": 0.5075, + "step": 1445 + }, + { + "epoch": 0.12, + "learning_rate": 1.9547082259004727e-05, + "loss": 0.5185, + "step": 1446 + }, + { + "epoch": 0.12, + "learning_rate": 1.9546260199432278e-05, + "loss": 0.5054, + "step": 1447 + }, + { + "epoch": 0.12, + "learning_rate": 1.9545437411822173e-05, + "loss": 0.4896, + "step": 1448 + }, + { + "epoch": 0.12, + "learning_rate": 1.954461389623716e-05, + "loss": 0.5216, + "step": 1449 + }, + { + "epoch": 0.12, + "learning_rate": 1.9543789652740043e-05, + "loss": 0.4931, + "step": 1450 + }, + { + "epoch": 0.12, + "learning_rate": 1.954296468139368e-05, + "loss": 0.5127, + "step": 1451 + }, + { + "epoch": 0.12, + "learning_rate": 1.9542138982260993e-05, + "loss": 0.5051, + "step": 1452 + }, + { + "epoch": 0.12, + "learning_rate": 1.954131255540495e-05, + "loss": 0.4972, + "step": 1453 + }, + { + "epoch": 0.12, + "learning_rate": 1.9540485400888577e-05, + "loss": 0.5035, + "step": 1454 + }, + { + "epoch": 0.12, + "learning_rate": 1.953965751877496e-05, + "loss": 0.5207, + "step": 1455 + }, + { + "epoch": 0.12, + "learning_rate": 1.953882890912723e-05, + "loss": 0.5301, + "step": 1456 + }, + { + "epoch": 0.12, + "learning_rate": 1.9537999572008585e-05, + "loss": 0.504, + "step": 1457 + }, + { + "epoch": 0.12, + "learning_rate": 1.953716950748227e-05, + "loss": 0.527, + "step": 1458 + }, + { + "epoch": 0.12, + "learning_rate": 1.9536338715611593e-05, + "loss": 0.5257, + "step": 1459 + }, + { + "epoch": 0.12, + "learning_rate": 1.9535507196459916e-05, + "loss": 0.4934, + "step": 1460 + }, + { + "epoch": 0.12, + "learning_rate": 1.953467495009065e-05, + "loss": 0.5234, + "step": 1461 + }, + { + "epoch": 0.12, + "learning_rate": 1.9533841976567265e-05, + "loss": 0.4902, + "step": 1462 + }, + { + "epoch": 0.12, + "learning_rate": 1.9533008275953288e-05, + "loss": 0.4986, + "step": 1463 + }, + { + "epoch": 0.12, + "learning_rate": 1.95321738483123e-05, + "loss": 0.5077, + "step": 1464 + }, + { + "epoch": 0.12, + "learning_rate": 1.953133869370794e-05, + "loss": 0.5161, + "step": 1465 + }, + { + "epoch": 0.12, + "learning_rate": 1.95305028122039e-05, + "loss": 0.5025, + "step": 1466 + }, + { + "epoch": 0.13, + "learning_rate": 1.9529666203863924e-05, + "loss": 0.5138, + "step": 1467 + }, + { + "epoch": 0.13, + "learning_rate": 1.952882886875182e-05, + "loss": 0.5163, + "step": 1468 + }, + { + "epoch": 0.13, + "learning_rate": 1.9527990806931446e-05, + "loss": 0.4974, + "step": 1469 + }, + { + "epoch": 0.13, + "learning_rate": 1.952715201846671e-05, + "loss": 0.514, + "step": 1470 + }, + { + "epoch": 0.13, + "learning_rate": 1.952631250342159e-05, + "loss": 0.4994, + "step": 1471 + }, + { + "epoch": 0.13, + "learning_rate": 1.9525472261860112e-05, + "loss": 0.5086, + "step": 1472 + }, + { + "epoch": 0.13, + "learning_rate": 1.9524631293846342e-05, + "loss": 0.4978, + "step": 1473 + }, + { + "epoch": 0.13, + "learning_rate": 1.952378959944443e-05, + "loss": 0.5133, + "step": 1474 + }, + { + "epoch": 0.13, + "learning_rate": 1.9522947178718566e-05, + "loss": 0.4913, + "step": 1475 + }, + { + "epoch": 0.13, + "learning_rate": 1.952210403173299e-05, + "loss": 0.5016, + "step": 1476 + }, + { + "epoch": 0.13, + "learning_rate": 1.9521260158552004e-05, + "loss": 0.5344, + "step": 1477 + }, + { + "epoch": 0.13, + "learning_rate": 1.9520415559239973e-05, + "loss": 0.5008, + "step": 1478 + }, + { + "epoch": 0.13, + "learning_rate": 1.9519570233861304e-05, + "loss": 0.5213, + "step": 1479 + }, + { + "epoch": 0.13, + "learning_rate": 1.951872418248046e-05, + "loss": 0.5094, + "step": 1480 + }, + { + "epoch": 0.13, + "learning_rate": 1.9517877405161976e-05, + "loss": 0.5254, + "step": 1481 + }, + { + "epoch": 0.13, + "learning_rate": 1.9517029901970426e-05, + "loss": 0.5087, + "step": 1482 + }, + { + "epoch": 0.13, + "learning_rate": 1.9516181672970444e-05, + "loss": 0.5104, + "step": 1483 + }, + { + "epoch": 0.13, + "learning_rate": 1.9515332718226714e-05, + "loss": 0.5344, + "step": 1484 + }, + { + "epoch": 0.13, + "learning_rate": 1.951448303780399e-05, + "loss": 0.5017, + "step": 1485 + }, + { + "epoch": 0.13, + "learning_rate": 1.9513632631767062e-05, + "loss": 0.5147, + "step": 1486 + }, + { + "epoch": 0.13, + "learning_rate": 1.9512781500180797e-05, + "loss": 0.4982, + "step": 1487 + }, + { + "epoch": 0.13, + "learning_rate": 1.9511929643110095e-05, + "loss": 0.5073, + "step": 1488 + }, + { + "epoch": 0.13, + "learning_rate": 1.9511077060619933e-05, + "loss": 0.4984, + "step": 1489 + }, + { + "epoch": 0.13, + "learning_rate": 1.9510223752775322e-05, + "loss": 0.5403, + "step": 1490 + }, + { + "epoch": 0.13, + "learning_rate": 1.9509369719641345e-05, + "loss": 0.5212, + "step": 1491 + }, + { + "epoch": 0.13, + "learning_rate": 1.950851496128314e-05, + "loss": 0.482, + "step": 1492 + }, + { + "epoch": 0.13, + "learning_rate": 1.9507659477765875e-05, + "loss": 0.4981, + "step": 1493 + }, + { + "epoch": 0.13, + "learning_rate": 1.950680326915481e-05, + "loss": 0.4959, + "step": 1494 + }, + { + "epoch": 0.13, + "learning_rate": 1.950594633551524e-05, + "loss": 0.5331, + "step": 1495 + }, + { + "epoch": 0.13, + "learning_rate": 1.9505088676912517e-05, + "loss": 0.5037, + "step": 1496 + }, + { + "epoch": 0.13, + "learning_rate": 1.9504230293412044e-05, + "loss": 0.5246, + "step": 1497 + }, + { + "epoch": 0.13, + "learning_rate": 1.9503371185079295e-05, + "loss": 0.5028, + "step": 1498 + }, + { + "epoch": 0.13, + "learning_rate": 1.9502511351979783e-05, + "loss": 0.5004, + "step": 1499 + }, + { + "epoch": 0.13, + "learning_rate": 1.950165079417908e-05, + "loss": 0.4949, + "step": 1500 + }, + { + "epoch": 0.13, + "learning_rate": 1.9500789511742824e-05, + "loss": 0.4884, + "step": 1501 + }, + { + "epoch": 0.13, + "learning_rate": 1.949992750473669e-05, + "loss": 0.5061, + "step": 1502 + }, + { + "epoch": 0.13, + "learning_rate": 1.949906477322643e-05, + "loss": 0.4889, + "step": 1503 + }, + { + "epoch": 0.13, + "learning_rate": 1.949820131727783e-05, + "loss": 0.5181, + "step": 1504 + }, + { + "epoch": 0.13, + "learning_rate": 1.949733713695674e-05, + "loss": 0.5214, + "step": 1505 + }, + { + "epoch": 0.13, + "learning_rate": 1.9496472232329075e-05, + "loss": 0.5063, + "step": 1506 + }, + { + "epoch": 0.13, + "learning_rate": 1.949560660346079e-05, + "loss": 0.5233, + "step": 1507 + }, + { + "epoch": 0.13, + "learning_rate": 1.9494740250417902e-05, + "loss": 0.4995, + "step": 1508 + }, + { + "epoch": 0.13, + "learning_rate": 1.949387317326648e-05, + "loss": 0.509, + "step": 1509 + }, + { + "epoch": 0.13, + "learning_rate": 1.9493005372072654e-05, + "loss": 0.5061, + "step": 1510 + }, + { + "epoch": 0.13, + "learning_rate": 1.949213684690261e-05, + "loss": 0.5161, + "step": 1511 + }, + { + "epoch": 0.13, + "learning_rate": 1.949126759782258e-05, + "loss": 0.5118, + "step": 1512 + }, + { + "epoch": 0.13, + "learning_rate": 1.949039762489886e-05, + "loss": 0.5203, + "step": 1513 + }, + { + "epoch": 0.13, + "learning_rate": 1.9489526928197794e-05, + "loss": 0.493, + "step": 1514 + }, + { + "epoch": 0.13, + "learning_rate": 1.9488655507785788e-05, + "loss": 0.5052, + "step": 1515 + }, + { + "epoch": 0.13, + "learning_rate": 1.9487783363729297e-05, + "loss": 0.5194, + "step": 1516 + }, + { + "epoch": 0.13, + "learning_rate": 1.9486910496094836e-05, + "loss": 0.5041, + "step": 1517 + }, + { + "epoch": 0.13, + "learning_rate": 1.948603690494898e-05, + "loss": 0.4879, + "step": 1518 + }, + { + "epoch": 0.13, + "learning_rate": 1.948516259035834e-05, + "loss": 0.5291, + "step": 1519 + }, + { + "epoch": 0.13, + "learning_rate": 1.9484287552389603e-05, + "loss": 0.5152, + "step": 1520 + }, + { + "epoch": 0.13, + "learning_rate": 1.94834117911095e-05, + "loss": 0.4992, + "step": 1521 + }, + { + "epoch": 0.13, + "learning_rate": 1.9482535306584826e-05, + "loss": 0.4955, + "step": 1522 + }, + { + "epoch": 0.13, + "learning_rate": 1.9481658098882418e-05, + "loss": 0.5095, + "step": 1523 + }, + { + "epoch": 0.13, + "learning_rate": 1.948078016806918e-05, + "loss": 0.5112, + "step": 1524 + }, + { + "epoch": 0.13, + "learning_rate": 1.9479901514212068e-05, + "loss": 0.4833, + "step": 1525 + }, + { + "epoch": 0.13, + "learning_rate": 1.9479022137378086e-05, + "loss": 0.5217, + "step": 1526 + }, + { + "epoch": 0.13, + "learning_rate": 1.94781420376343e-05, + "loss": 0.5116, + "step": 1527 + }, + { + "epoch": 0.13, + "learning_rate": 1.9477261215047836e-05, + "loss": 0.507, + "step": 1528 + }, + { + "epoch": 0.13, + "learning_rate": 1.9476379669685862e-05, + "loss": 0.507, + "step": 1529 + }, + { + "epoch": 0.13, + "learning_rate": 1.9475497401615615e-05, + "loss": 0.5229, + "step": 1530 + }, + { + "epoch": 0.13, + "learning_rate": 1.9474614410904373e-05, + "loss": 0.4816, + "step": 1531 + }, + { + "epoch": 0.13, + "learning_rate": 1.9473730697619485e-05, + "loss": 0.5025, + "step": 1532 + }, + { + "epoch": 0.13, + "learning_rate": 1.947284626182834e-05, + "loss": 0.5171, + "step": 1533 + }, + { + "epoch": 0.13, + "learning_rate": 1.947196110359839e-05, + "loss": 0.5344, + "step": 1534 + }, + { + "epoch": 0.13, + "learning_rate": 1.9471075222997147e-05, + "loss": 0.5041, + "step": 1535 + }, + { + "epoch": 0.13, + "learning_rate": 1.9470188620092162e-05, + "loss": 0.5024, + "step": 1536 + }, + { + "epoch": 0.13, + "learning_rate": 1.946930129495106e-05, + "loss": 0.5036, + "step": 1537 + }, + { + "epoch": 0.13, + "learning_rate": 1.9468413247641504e-05, + "loss": 0.4889, + "step": 1538 + }, + { + "epoch": 0.13, + "learning_rate": 1.9467524478231226e-05, + "loss": 0.5126, + "step": 1539 + }, + { + "epoch": 0.13, + "learning_rate": 1.9466634986788007e-05, + "loss": 0.5023, + "step": 1540 + }, + { + "epoch": 0.13, + "learning_rate": 1.946574477337968e-05, + "loss": 0.505, + "step": 1541 + }, + { + "epoch": 0.13, + "learning_rate": 1.946485383807414e-05, + "loss": 0.4907, + "step": 1542 + }, + { + "epoch": 0.13, + "learning_rate": 1.9463962180939327e-05, + "loss": 0.533, + "step": 1543 + }, + { + "epoch": 0.13, + "learning_rate": 1.946306980204325e-05, + "loss": 0.5035, + "step": 1544 + }, + { + "epoch": 0.13, + "learning_rate": 1.9462176701453966e-05, + "loss": 0.502, + "step": 1545 + }, + { + "epoch": 0.13, + "learning_rate": 1.946128287923958e-05, + "loss": 0.5216, + "step": 1546 + }, + { + "epoch": 0.13, + "learning_rate": 1.9460388335468264e-05, + "loss": 0.5006, + "step": 1547 + }, + { + "epoch": 0.13, + "learning_rate": 1.9459493070208237e-05, + "loss": 0.5169, + "step": 1548 + }, + { + "epoch": 0.13, + "learning_rate": 1.9458597083527774e-05, + "loss": 0.5176, + "step": 1549 + }, + { + "epoch": 0.13, + "learning_rate": 1.9457700375495213e-05, + "loss": 0.5154, + "step": 1550 + }, + { + "epoch": 0.13, + "learning_rate": 1.945680294617893e-05, + "loss": 0.5126, + "step": 1551 + }, + { + "epoch": 0.13, + "learning_rate": 1.945590479564738e-05, + "loss": 0.5286, + "step": 1552 + }, + { + "epoch": 0.13, + "learning_rate": 1.945500592396905e-05, + "loss": 0.4953, + "step": 1553 + }, + { + "epoch": 0.13, + "learning_rate": 1.9454106331212495e-05, + "loss": 0.4962, + "step": 1554 + }, + { + "epoch": 0.13, + "learning_rate": 1.9453206017446326e-05, + "loss": 0.5281, + "step": 1555 + }, + { + "epoch": 0.13, + "learning_rate": 1.9452304982739194e-05, + "loss": 0.4953, + "step": 1556 + }, + { + "epoch": 0.13, + "learning_rate": 1.9451403227159823e-05, + "loss": 0.5036, + "step": 1557 + }, + { + "epoch": 0.13, + "learning_rate": 1.9450500750776987e-05, + "loss": 0.5283, + "step": 1558 + }, + { + "epoch": 0.13, + "learning_rate": 1.9449597553659504e-05, + "loss": 0.521, + "step": 1559 + }, + { + "epoch": 0.13, + "learning_rate": 1.9448693635876266e-05, + "loss": 0.5128, + "step": 1560 + }, + { + "epoch": 0.13, + "learning_rate": 1.94477889974962e-05, + "loss": 0.5108, + "step": 1561 + }, + { + "epoch": 0.13, + "learning_rate": 1.9446883638588302e-05, + "loss": 0.5269, + "step": 1562 + }, + { + "epoch": 0.13, + "learning_rate": 1.944597755922162e-05, + "loss": 0.4938, + "step": 1563 + }, + { + "epoch": 0.13, + "learning_rate": 1.9445070759465254e-05, + "loss": 0.517, + "step": 1564 + }, + { + "epoch": 0.13, + "learning_rate": 1.9444163239388358e-05, + "loss": 0.4946, + "step": 1565 + }, + { + "epoch": 0.13, + "learning_rate": 1.9443254999060147e-05, + "loss": 0.5143, + "step": 1566 + }, + { + "epoch": 0.13, + "learning_rate": 1.9442346038549883e-05, + "loss": 0.492, + "step": 1567 + }, + { + "epoch": 0.13, + "learning_rate": 1.9441436357926892e-05, + "loss": 0.4882, + "step": 1568 + }, + { + "epoch": 0.13, + "learning_rate": 1.9440525957260546e-05, + "loss": 0.5047, + "step": 1569 + }, + { + "epoch": 0.13, + "learning_rate": 1.9439614836620277e-05, + "loss": 0.4896, + "step": 1570 + }, + { + "epoch": 0.13, + "learning_rate": 1.943870299607557e-05, + "loss": 0.5088, + "step": 1571 + }, + { + "epoch": 0.13, + "learning_rate": 1.9437790435695972e-05, + "loss": 0.4999, + "step": 1572 + }, + { + "epoch": 0.13, + "learning_rate": 1.943687715555107e-05, + "loss": 0.526, + "step": 1573 + }, + { + "epoch": 0.13, + "learning_rate": 1.943596315571052e-05, + "loss": 0.4953, + "step": 1574 + }, + { + "epoch": 0.13, + "learning_rate": 1.9435048436244025e-05, + "loss": 0.5021, + "step": 1575 + }, + { + "epoch": 0.13, + "learning_rate": 1.9434132997221347e-05, + "loss": 0.5087, + "step": 1576 + }, + { + "epoch": 0.13, + "learning_rate": 1.94332168387123e-05, + "loss": 0.4946, + "step": 1577 + }, + { + "epoch": 0.13, + "learning_rate": 1.9432299960786752e-05, + "loss": 0.5034, + "step": 1578 + }, + { + "epoch": 0.13, + "learning_rate": 1.9431382363514634e-05, + "loss": 0.4982, + "step": 1579 + }, + { + "epoch": 0.13, + "learning_rate": 1.943046404696592e-05, + "loss": 0.5016, + "step": 1580 + }, + { + "epoch": 0.13, + "learning_rate": 1.9429545011210648e-05, + "loss": 0.5052, + "step": 1581 + }, + { + "epoch": 0.13, + "learning_rate": 1.9428625256318906e-05, + "loss": 0.5365, + "step": 1582 + }, + { + "epoch": 0.13, + "learning_rate": 1.9427704782360838e-05, + "loss": 0.5022, + "step": 1583 + }, + { + "epoch": 0.14, + "learning_rate": 1.9426783589406645e-05, + "loss": 0.4963, + "step": 1584 + }, + { + "epoch": 0.14, + "learning_rate": 1.9425861677526577e-05, + "loss": 0.5082, + "step": 1585 + }, + { + "epoch": 0.14, + "learning_rate": 1.9424939046790948e-05, + "loss": 0.4982, + "step": 1586 + }, + { + "epoch": 0.14, + "learning_rate": 1.942401569727012e-05, + "loss": 0.5097, + "step": 1587 + }, + { + "epoch": 0.14, + "learning_rate": 1.9423091629034506e-05, + "loss": 0.505, + "step": 1588 + }, + { + "epoch": 0.14, + "learning_rate": 1.9422166842154592e-05, + "loss": 0.4979, + "step": 1589 + }, + { + "epoch": 0.14, + "learning_rate": 1.942124133670089e-05, + "loss": 0.5126, + "step": 1590 + }, + { + "epoch": 0.14, + "learning_rate": 1.9420315112743997e-05, + "loss": 0.5266, + "step": 1591 + }, + { + "epoch": 0.14, + "learning_rate": 1.9419388170354544e-05, + "loss": 0.5105, + "step": 1592 + }, + { + "epoch": 0.14, + "learning_rate": 1.941846050960322e-05, + "loss": 0.4983, + "step": 1593 + }, + { + "epoch": 0.14, + "learning_rate": 1.9417532130560784e-05, + "loss": 0.5085, + "step": 1594 + }, + { + "epoch": 0.14, + "learning_rate": 1.9416603033298025e-05, + "loss": 0.4955, + "step": 1595 + }, + { + "epoch": 0.14, + "learning_rate": 1.941567321788581e-05, + "loss": 0.5116, + "step": 1596 + }, + { + "epoch": 0.14, + "learning_rate": 1.941474268439504e-05, + "loss": 0.4856, + "step": 1597 + }, + { + "epoch": 0.14, + "learning_rate": 1.9413811432896693e-05, + "loss": 0.5122, + "step": 1598 + }, + { + "epoch": 0.14, + "learning_rate": 1.9412879463461783e-05, + "loss": 0.4962, + "step": 1599 + }, + { + "epoch": 0.14, + "learning_rate": 1.9411946776161388e-05, + "loss": 0.486, + "step": 1600 + }, + { + "epoch": 0.14, + "learning_rate": 1.9411013371066635e-05, + "loss": 0.519, + "step": 1601 + }, + { + "epoch": 0.14, + "learning_rate": 1.9410079248248716e-05, + "loss": 0.4986, + "step": 1602 + }, + { + "epoch": 0.14, + "learning_rate": 1.9409144407778866e-05, + "loss": 0.5251, + "step": 1603 + }, + { + "epoch": 0.14, + "learning_rate": 1.9408208849728382e-05, + "loss": 0.4898, + "step": 1604 + }, + { + "epoch": 0.14, + "learning_rate": 1.940727257416861e-05, + "loss": 0.5062, + "step": 1605 + }, + { + "epoch": 0.14, + "learning_rate": 1.9406335581170962e-05, + "loss": 0.4815, + "step": 1606 + }, + { + "epoch": 0.14, + "learning_rate": 1.9405397870806893e-05, + "loss": 0.5015, + "step": 1607 + }, + { + "epoch": 0.14, + "learning_rate": 1.9404459443147914e-05, + "loss": 0.5237, + "step": 1608 + }, + { + "epoch": 0.14, + "learning_rate": 1.9403520298265596e-05, + "loss": 0.4905, + "step": 1609 + }, + { + "epoch": 0.14, + "learning_rate": 1.940258043623156e-05, + "loss": 0.5201, + "step": 1610 + }, + { + "epoch": 0.14, + "learning_rate": 1.9401639857117485e-05, + "loss": 0.5019, + "step": 1611 + }, + { + "epoch": 0.14, + "learning_rate": 1.9400698560995105e-05, + "loss": 0.5239, + "step": 1612 + }, + { + "epoch": 0.14, + "learning_rate": 1.9399756547936205e-05, + "loss": 0.5036, + "step": 1613 + }, + { + "epoch": 0.14, + "learning_rate": 1.939881381801263e-05, + "loss": 0.4994, + "step": 1614 + }, + { + "epoch": 0.14, + "learning_rate": 1.9397870371296273e-05, + "loss": 0.4887, + "step": 1615 + }, + { + "epoch": 0.14, + "learning_rate": 1.9396926207859085e-05, + "loss": 0.487, + "step": 1616 + }, + { + "epoch": 0.14, + "learning_rate": 1.9395981327773077e-05, + "loss": 0.5184, + "step": 1617 + }, + { + "epoch": 0.14, + "learning_rate": 1.93950357311103e-05, + "loss": 0.5036, + "step": 1618 + }, + { + "epoch": 0.14, + "learning_rate": 1.939408941794288e-05, + "loss": 0.5139, + "step": 1619 + }, + { + "epoch": 0.14, + "learning_rate": 1.9393142388342984e-05, + "loss": 0.51, + "step": 1620 + }, + { + "epoch": 0.14, + "learning_rate": 1.939219464238283e-05, + "loss": 0.5078, + "step": 1621 + }, + { + "epoch": 0.14, + "learning_rate": 1.9391246180134703e-05, + "loss": 0.5102, + "step": 1622 + }, + { + "epoch": 0.14, + "learning_rate": 1.9390297001670933e-05, + "loss": 0.4985, + "step": 1623 + }, + { + "epoch": 0.14, + "learning_rate": 1.938934710706391e-05, + "loss": 0.5231, + "step": 1624 + }, + { + "epoch": 0.14, + "learning_rate": 1.9388396496386082e-05, + "loss": 0.478, + "step": 1625 + }, + { + "epoch": 0.14, + "learning_rate": 1.938744516970994e-05, + "loss": 0.5165, + "step": 1626 + }, + { + "epoch": 0.14, + "learning_rate": 1.9386493127108033e-05, + "loss": 0.4875, + "step": 1627 + }, + { + "epoch": 0.14, + "learning_rate": 1.9385540368652976e-05, + "loss": 0.5033, + "step": 1628 + }, + { + "epoch": 0.14, + "learning_rate": 1.9384586894417426e-05, + "loss": 0.4988, + "step": 1629 + }, + { + "epoch": 0.14, + "learning_rate": 1.9383632704474103e-05, + "loss": 0.5032, + "step": 1630 + }, + { + "epoch": 0.14, + "learning_rate": 1.9382677798895774e-05, + "loss": 0.5135, + "step": 1631 + }, + { + "epoch": 0.14, + "learning_rate": 1.9381722177755266e-05, + "loss": 0.4964, + "step": 1632 + }, + { + "epoch": 0.14, + "learning_rate": 1.938076584112545e-05, + "loss": 0.4969, + "step": 1633 + }, + { + "epoch": 0.14, + "learning_rate": 1.9379808789079274e-05, + "loss": 0.4942, + "step": 1634 + }, + { + "epoch": 0.14, + "learning_rate": 1.9378851021689716e-05, + "loss": 0.5281, + "step": 1635 + }, + { + "epoch": 0.14, + "learning_rate": 1.9377892539029827e-05, + "loss": 0.5014, + "step": 1636 + }, + { + "epoch": 0.14, + "learning_rate": 1.9376933341172702e-05, + "loss": 0.5078, + "step": 1637 + }, + { + "epoch": 0.14, + "learning_rate": 1.937597342819149e-05, + "loss": 0.5278, + "step": 1638 + }, + { + "epoch": 0.14, + "learning_rate": 1.9375012800159404e-05, + "loss": 0.4974, + "step": 1639 + }, + { + "epoch": 0.14, + "learning_rate": 1.93740514571497e-05, + "loss": 0.5041, + "step": 1640 + }, + { + "epoch": 0.14, + "learning_rate": 1.9373089399235697e-05, + "loss": 0.4875, + "step": 1641 + }, + { + "epoch": 0.14, + "learning_rate": 1.9372126626490763e-05, + "loss": 0.495, + "step": 1642 + }, + { + "epoch": 0.14, + "learning_rate": 1.937116313898833e-05, + "loss": 0.5046, + "step": 1643 + }, + { + "epoch": 0.14, + "learning_rate": 1.9370198936801866e-05, + "loss": 0.5349, + "step": 1644 + }, + { + "epoch": 0.14, + "learning_rate": 1.9369234020004916e-05, + "loss": 0.4882, + "step": 1645 + }, + { + "epoch": 0.14, + "learning_rate": 1.9368268388671064e-05, + "loss": 0.4977, + "step": 1646 + }, + { + "epoch": 0.14, + "learning_rate": 1.9367302042873954e-05, + "loss": 0.5019, + "step": 1647 + }, + { + "epoch": 0.14, + "learning_rate": 1.936633498268728e-05, + "loss": 0.4955, + "step": 1648 + }, + { + "epoch": 0.14, + "learning_rate": 1.93653672081848e-05, + "loss": 0.5078, + "step": 1649 + }, + { + "epoch": 0.14, + "learning_rate": 1.9364398719440314e-05, + "loss": 0.4849, + "step": 1650 + }, + { + "epoch": 0.14, + "learning_rate": 1.936342951652769e-05, + "loss": 0.4819, + "step": 1651 + }, + { + "epoch": 0.14, + "learning_rate": 1.9362459599520837e-05, + "loss": 0.5137, + "step": 1652 + }, + { + "epoch": 0.14, + "learning_rate": 1.936148896849373e-05, + "loss": 0.4875, + "step": 1653 + }, + { + "epoch": 0.14, + "learning_rate": 1.936051762352039e-05, + "loss": 0.5181, + "step": 1654 + }, + { + "epoch": 0.14, + "learning_rate": 1.9359545564674897e-05, + "loss": 0.4796, + "step": 1655 + }, + { + "epoch": 0.14, + "learning_rate": 1.9358572792031386e-05, + "loss": 0.5051, + "step": 1656 + }, + { + "epoch": 0.14, + "learning_rate": 1.935759930566404e-05, + "loss": 0.4987, + "step": 1657 + }, + { + "epoch": 0.14, + "learning_rate": 1.9356625105647108e-05, + "loss": 0.5108, + "step": 1658 + }, + { + "epoch": 0.14, + "learning_rate": 1.935565019205488e-05, + "loss": 0.5001, + "step": 1659 + }, + { + "epoch": 0.14, + "learning_rate": 1.935467456496171e-05, + "loss": 0.527, + "step": 1660 + }, + { + "epoch": 0.14, + "learning_rate": 1.9353698224442005e-05, + "loss": 0.5062, + "step": 1661 + }, + { + "epoch": 0.14, + "learning_rate": 1.935272117057022e-05, + "loss": 0.4892, + "step": 1662 + }, + { + "epoch": 0.14, + "learning_rate": 1.9351743403420875e-05, + "loss": 0.5036, + "step": 1663 + }, + { + "epoch": 0.14, + "learning_rate": 1.9350764923068533e-05, + "loss": 0.501, + "step": 1664 + }, + { + "epoch": 0.14, + "learning_rate": 1.934978572958782e-05, + "loss": 0.5058, + "step": 1665 + }, + { + "epoch": 0.14, + "learning_rate": 1.9348805823053415e-05, + "loss": 0.5021, + "step": 1666 + }, + { + "epoch": 0.14, + "learning_rate": 1.934782520354005e-05, + "loss": 0.515, + "step": 1667 + }, + { + "epoch": 0.14, + "learning_rate": 1.9346843871122503e-05, + "loss": 0.5095, + "step": 1668 + }, + { + "epoch": 0.14, + "learning_rate": 1.934586182587562e-05, + "loss": 0.5093, + "step": 1669 + }, + { + "epoch": 0.14, + "learning_rate": 1.93448790678743e-05, + "loss": 0.5019, + "step": 1670 + }, + { + "epoch": 0.14, + "learning_rate": 1.934389559719349e-05, + "loss": 0.4919, + "step": 1671 + }, + { + "epoch": 0.14, + "learning_rate": 1.934291141390819e-05, + "loss": 0.5212, + "step": 1672 + }, + { + "epoch": 0.14, + "learning_rate": 1.9341926518093462e-05, + "loss": 0.5049, + "step": 1673 + }, + { + "epoch": 0.14, + "learning_rate": 1.9340940909824414e-05, + "loss": 0.5141, + "step": 1674 + }, + { + "epoch": 0.14, + "learning_rate": 1.9339954589176215e-05, + "loss": 0.5037, + "step": 1675 + }, + { + "epoch": 0.14, + "learning_rate": 1.9338967556224085e-05, + "loss": 0.4966, + "step": 1676 + }, + { + "epoch": 0.14, + "learning_rate": 1.9337979811043303e-05, + "loss": 0.5076, + "step": 1677 + }, + { + "epoch": 0.14, + "learning_rate": 1.9336991353709195e-05, + "loss": 0.5042, + "step": 1678 + }, + { + "epoch": 0.14, + "learning_rate": 1.9336002184297145e-05, + "loss": 0.5344, + "step": 1679 + }, + { + "epoch": 0.14, + "learning_rate": 1.933501230288259e-05, + "loss": 0.5147, + "step": 1680 + }, + { + "epoch": 0.14, + "learning_rate": 1.9334021709541027e-05, + "loss": 0.4909, + "step": 1681 + }, + { + "epoch": 0.14, + "learning_rate": 1.9333030404348e-05, + "loss": 0.4842, + "step": 1682 + }, + { + "epoch": 0.14, + "learning_rate": 1.9332038387379112e-05, + "loss": 0.5004, + "step": 1683 + }, + { + "epoch": 0.14, + "learning_rate": 1.933104565871001e-05, + "loss": 0.5055, + "step": 1684 + }, + { + "epoch": 0.14, + "learning_rate": 1.9330052218416412e-05, + "loss": 0.4914, + "step": 1685 + }, + { + "epoch": 0.14, + "learning_rate": 1.9329058066574085e-05, + "loss": 0.5098, + "step": 1686 + }, + { + "epoch": 0.14, + "learning_rate": 1.932806320325884e-05, + "loss": 0.491, + "step": 1687 + }, + { + "epoch": 0.14, + "learning_rate": 1.932706762854655e-05, + "loss": 0.5093, + "step": 1688 + }, + { + "epoch": 0.14, + "learning_rate": 1.9326071342513143e-05, + "loss": 0.4916, + "step": 1689 + }, + { + "epoch": 0.14, + "learning_rate": 1.93250743452346e-05, + "loss": 0.5033, + "step": 1690 + }, + { + "epoch": 0.14, + "learning_rate": 1.932407663678696e-05, + "loss": 0.501, + "step": 1691 + }, + { + "epoch": 0.14, + "learning_rate": 1.9323078217246303e-05, + "loss": 0.494, + "step": 1692 + }, + { + "epoch": 0.14, + "learning_rate": 1.9322079086688786e-05, + "loss": 0.5108, + "step": 1693 + }, + { + "epoch": 0.14, + "learning_rate": 1.9321079245190596e-05, + "loss": 0.4903, + "step": 1694 + }, + { + "epoch": 0.14, + "learning_rate": 1.932007869282799e-05, + "loss": 0.5048, + "step": 1695 + }, + { + "epoch": 0.14, + "learning_rate": 1.931907742967727e-05, + "loss": 0.4966, + "step": 1696 + }, + { + "epoch": 0.14, + "learning_rate": 1.9318075455814798e-05, + "loss": 0.5033, + "step": 1697 + }, + { + "epoch": 0.14, + "learning_rate": 1.931707277131699e-05, + "loss": 0.5047, + "step": 1698 + }, + { + "epoch": 0.14, + "learning_rate": 1.9316069376260317e-05, + "loss": 0.5134, + "step": 1699 + }, + { + "epoch": 0.14, + "learning_rate": 1.93150652707213e-05, + "loss": 0.4979, + "step": 1700 + }, + { + "epoch": 0.15, + "learning_rate": 1.9314060454776515e-05, + "loss": 0.501, + "step": 1701 + }, + { + "epoch": 0.15, + "learning_rate": 1.9313054928502596e-05, + "loss": 0.5133, + "step": 1702 + }, + { + "epoch": 0.15, + "learning_rate": 1.9312048691976226e-05, + "loss": 0.4785, + "step": 1703 + }, + { + "epoch": 0.15, + "learning_rate": 1.9311041745274147e-05, + "loss": 0.5058, + "step": 1704 + }, + { + "epoch": 0.15, + "learning_rate": 1.9310034088473153e-05, + "loss": 0.4943, + "step": 1705 + }, + { + "epoch": 0.15, + "learning_rate": 1.9309025721650088e-05, + "loss": 0.512, + "step": 1706 + }, + { + "epoch": 0.15, + "learning_rate": 1.9308016644881862e-05, + "loss": 0.4938, + "step": 1707 + }, + { + "epoch": 0.15, + "learning_rate": 1.9307006858245424e-05, + "loss": 0.4792, + "step": 1708 + }, + { + "epoch": 0.15, + "learning_rate": 1.9305996361817788e-05, + "loss": 0.5187, + "step": 1709 + }, + { + "epoch": 0.15, + "learning_rate": 1.9304985155676017e-05, + "loss": 0.4903, + "step": 1710 + }, + { + "epoch": 0.15, + "learning_rate": 1.9303973239897233e-05, + "loss": 0.5133, + "step": 1711 + }, + { + "epoch": 0.15, + "learning_rate": 1.9302960614558604e-05, + "loss": 0.4935, + "step": 1712 + }, + { + "epoch": 0.15, + "learning_rate": 1.930194727973736e-05, + "loss": 0.495, + "step": 1713 + }, + { + "epoch": 0.15, + "learning_rate": 1.9300933235510786e-05, + "loss": 0.5201, + "step": 1714 + }, + { + "epoch": 0.15, + "learning_rate": 1.929991848195621e-05, + "loss": 0.4937, + "step": 1715 + }, + { + "epoch": 0.15, + "learning_rate": 1.9298903019151026e-05, + "loss": 0.5052, + "step": 1716 + }, + { + "epoch": 0.15, + "learning_rate": 1.9297886847172672e-05, + "loss": 0.5157, + "step": 1717 + }, + { + "epoch": 0.15, + "learning_rate": 1.9296869966098658e-05, + "loss": 0.5121, + "step": 1718 + }, + { + "epoch": 0.15, + "learning_rate": 1.9295852376006522e-05, + "loss": 0.5021, + "step": 1719 + }, + { + "epoch": 0.15, + "learning_rate": 1.9294834076973872e-05, + "loss": 0.4905, + "step": 1720 + }, + { + "epoch": 0.15, + "learning_rate": 1.9293815069078375e-05, + "loss": 0.5239, + "step": 1721 + }, + { + "epoch": 0.15, + "learning_rate": 1.9292795352397736e-05, + "loss": 0.4871, + "step": 1722 + }, + { + "epoch": 0.15, + "learning_rate": 1.9291774927009733e-05, + "loss": 0.5072, + "step": 1723 + }, + { + "epoch": 0.15, + "learning_rate": 1.9290753792992177e-05, + "loss": 0.4919, + "step": 1724 + }, + { + "epoch": 0.15, + "learning_rate": 1.928973195042295e-05, + "loss": 0.5225, + "step": 1725 + }, + { + "epoch": 0.15, + "learning_rate": 1.928870939937998e-05, + "loss": 0.4996, + "step": 1726 + }, + { + "epoch": 0.15, + "learning_rate": 1.9287686139941254e-05, + "loss": 0.5077, + "step": 1727 + }, + { + "epoch": 0.15, + "learning_rate": 1.928666217218481e-05, + "loss": 0.4987, + "step": 1728 + }, + { + "epoch": 0.15, + "learning_rate": 1.9285637496188734e-05, + "loss": 0.5089, + "step": 1729 + }, + { + "epoch": 0.15, + "learning_rate": 1.9284612112031177e-05, + "loss": 0.4908, + "step": 1730 + }, + { + "epoch": 0.15, + "learning_rate": 1.928358601979034e-05, + "loss": 0.5271, + "step": 1731 + }, + { + "epoch": 0.15, + "learning_rate": 1.9282559219544477e-05, + "loss": 0.521, + "step": 1732 + }, + { + "epoch": 0.15, + "learning_rate": 1.928153171137189e-05, + "loss": 0.5106, + "step": 1733 + }, + { + "epoch": 0.15, + "learning_rate": 1.928050349535095e-05, + "loss": 0.501, + "step": 1734 + }, + { + "epoch": 0.15, + "learning_rate": 1.9279474571560065e-05, + "loss": 0.5205, + "step": 1735 + }, + { + "epoch": 0.15, + "learning_rate": 1.927844494007771e-05, + "loss": 0.5125, + "step": 1736 + }, + { + "epoch": 0.15, + "learning_rate": 1.9277414600982406e-05, + "loss": 0.5279, + "step": 1737 + }, + { + "epoch": 0.15, + "learning_rate": 1.9276383554352734e-05, + "loss": 0.5009, + "step": 1738 + }, + { + "epoch": 0.15, + "learning_rate": 1.9275351800267324e-05, + "loss": 0.5015, + "step": 1739 + }, + { + "epoch": 0.15, + "learning_rate": 1.9274319338804862e-05, + "loss": 0.5024, + "step": 1740 + }, + { + "epoch": 0.15, + "learning_rate": 1.927328617004409e-05, + "loss": 0.5069, + "step": 1741 + }, + { + "epoch": 0.15, + "learning_rate": 1.92722522940638e-05, + "loss": 0.4976, + "step": 1742 + }, + { + "epoch": 0.15, + "learning_rate": 1.9271217710942836e-05, + "loss": 0.5267, + "step": 1743 + }, + { + "epoch": 0.15, + "learning_rate": 1.9270182420760104e-05, + "loss": 0.5467, + "step": 1744 + }, + { + "epoch": 0.15, + "learning_rate": 1.926914642359456e-05, + "loss": 0.5003, + "step": 1745 + }, + { + "epoch": 0.15, + "learning_rate": 1.9268109719525213e-05, + "loss": 0.5211, + "step": 1746 + }, + { + "epoch": 0.15, + "learning_rate": 1.9267072308631122e-05, + "loss": 0.5038, + "step": 1747 + }, + { + "epoch": 0.15, + "learning_rate": 1.9266034190991413e-05, + "loss": 0.5091, + "step": 1748 + }, + { + "epoch": 0.15, + "learning_rate": 1.9264995366685248e-05, + "loss": 0.4876, + "step": 1749 + }, + { + "epoch": 0.15, + "learning_rate": 1.926395583579186e-05, + "loss": 0.5159, + "step": 1750 + }, + { + "epoch": 0.15, + "learning_rate": 1.9262915598390518e-05, + "loss": 0.5073, + "step": 1751 + }, + { + "epoch": 0.15, + "learning_rate": 1.9261874654560565e-05, + "loss": 0.4935, + "step": 1752 + }, + { + "epoch": 0.15, + "learning_rate": 1.9260833004381384e-05, + "loss": 0.5116, + "step": 1753 + }, + { + "epoch": 0.15, + "learning_rate": 1.9259790647932416e-05, + "loss": 0.4953, + "step": 1754 + }, + { + "epoch": 0.15, + "learning_rate": 1.9258747585293154e-05, + "loss": 0.5114, + "step": 1755 + }, + { + "epoch": 0.15, + "learning_rate": 1.9257703816543144e-05, + "loss": 0.5212, + "step": 1756 + }, + { + "epoch": 0.15, + "learning_rate": 1.9256659341761995e-05, + "loss": 0.5111, + "step": 1757 + }, + { + "epoch": 0.15, + "learning_rate": 1.925561416102936e-05, + "loss": 0.5065, + "step": 1758 + }, + { + "epoch": 0.15, + "learning_rate": 1.9254568274424942e-05, + "loss": 0.5309, + "step": 1759 + }, + { + "epoch": 0.15, + "learning_rate": 1.9253521682028515e-05, + "loss": 0.4934, + "step": 1760 + }, + { + "epoch": 0.15, + "learning_rate": 1.9252474383919894e-05, + "loss": 0.4873, + "step": 1761 + }, + { + "epoch": 0.15, + "learning_rate": 1.9251426380178945e-05, + "loss": 0.502, + "step": 1762 + }, + { + "epoch": 0.15, + "learning_rate": 1.9250377670885597e-05, + "loss": 0.515, + "step": 1763 + }, + { + "epoch": 0.15, + "learning_rate": 1.924932825611983e-05, + "loss": 0.5066, + "step": 1764 + }, + { + "epoch": 0.15, + "learning_rate": 1.9248278135961676e-05, + "loss": 0.4908, + "step": 1765 + }, + { + "epoch": 0.15, + "learning_rate": 1.924722731049122e-05, + "loss": 0.5118, + "step": 1766 + }, + { + "epoch": 0.15, + "learning_rate": 1.9246175779788605e-05, + "loss": 0.501, + "step": 1767 + }, + { + "epoch": 0.15, + "learning_rate": 1.9245123543934017e-05, + "loss": 0.5069, + "step": 1768 + }, + { + "epoch": 0.15, + "learning_rate": 1.9244070603007718e-05, + "loss": 0.5065, + "step": 1769 + }, + { + "epoch": 0.15, + "learning_rate": 1.924301695709e-05, + "loss": 0.5097, + "step": 1770 + }, + { + "epoch": 0.15, + "learning_rate": 1.924196260626122e-05, + "loss": 0.4925, + "step": 1771 + }, + { + "epoch": 0.15, + "learning_rate": 1.9240907550601787e-05, + "loss": 0.4906, + "step": 1772 + }, + { + "epoch": 0.15, + "learning_rate": 1.9239851790192166e-05, + "loss": 0.5292, + "step": 1773 + }, + { + "epoch": 0.15, + "learning_rate": 1.9238795325112867e-05, + "loss": 0.4998, + "step": 1774 + }, + { + "epoch": 0.15, + "learning_rate": 1.9237738155444472e-05, + "loss": 0.4931, + "step": 1775 + }, + { + "epoch": 0.15, + "learning_rate": 1.9236680281267594e-05, + "loss": 0.5106, + "step": 1776 + }, + { + "epoch": 0.15, + "learning_rate": 1.923562170266292e-05, + "loss": 0.4995, + "step": 1777 + }, + { + "epoch": 0.15, + "learning_rate": 1.9234562419711178e-05, + "loss": 0.499, + "step": 1778 + }, + { + "epoch": 0.15, + "learning_rate": 1.9233502432493146e-05, + "loss": 0.4986, + "step": 1779 + }, + { + "epoch": 0.15, + "learning_rate": 1.923244174108968e-05, + "loss": 0.5201, + "step": 1780 + }, + { + "epoch": 0.15, + "learning_rate": 1.9231380345581655e-05, + "loss": 0.481, + "step": 1781 + }, + { + "epoch": 0.15, + "learning_rate": 1.9230318246050027e-05, + "loss": 0.4911, + "step": 1782 + }, + { + "epoch": 0.15, + "learning_rate": 1.9229255442575795e-05, + "loss": 0.5089, + "step": 1783 + }, + { + "epoch": 0.15, + "learning_rate": 1.922819193524001e-05, + "loss": 0.492, + "step": 1784 + }, + { + "epoch": 0.15, + "learning_rate": 1.922712772412378e-05, + "loss": 0.5152, + "step": 1785 + }, + { + "epoch": 0.15, + "learning_rate": 1.922606280930827e-05, + "loss": 0.4998, + "step": 1786 + }, + { + "epoch": 0.15, + "learning_rate": 1.9224997190874692e-05, + "loss": 0.5199, + "step": 1787 + }, + { + "epoch": 0.15, + "learning_rate": 1.9223930868904313e-05, + "loss": 0.5326, + "step": 1788 + }, + { + "epoch": 0.15, + "learning_rate": 1.9222863843478462e-05, + "loss": 0.5079, + "step": 1789 + }, + { + "epoch": 0.15, + "learning_rate": 1.922179611467851e-05, + "loss": 0.5275, + "step": 1790 + }, + { + "epoch": 0.15, + "learning_rate": 1.9220727682585882e-05, + "loss": 0.4877, + "step": 1791 + }, + { + "epoch": 0.15, + "learning_rate": 1.921965854728207e-05, + "loss": 0.5096, + "step": 1792 + }, + { + "epoch": 0.15, + "learning_rate": 1.9218588708848602e-05, + "loss": 0.5066, + "step": 1793 + }, + { + "epoch": 0.15, + "learning_rate": 1.9217518167367076e-05, + "loss": 0.508, + "step": 1794 + }, + { + "epoch": 0.15, + "learning_rate": 1.921644692291913e-05, + "loss": 0.5205, + "step": 1795 + }, + { + "epoch": 0.15, + "learning_rate": 1.9215374975586465e-05, + "loss": 0.5258, + "step": 1796 + }, + { + "epoch": 0.15, + "learning_rate": 1.9214302325450833e-05, + "loss": 0.4765, + "step": 1797 + }, + { + "epoch": 0.15, + "learning_rate": 1.9213228972594032e-05, + "loss": 0.5087, + "step": 1798 + }, + { + "epoch": 0.15, + "learning_rate": 1.921215491709793e-05, + "loss": 0.4979, + "step": 1799 + }, + { + "epoch": 0.15, + "learning_rate": 1.9211080159044434e-05, + "loss": 0.4964, + "step": 1800 + }, + { + "epoch": 0.15, + "learning_rate": 1.921000469851551e-05, + "loss": 0.4934, + "step": 1801 + }, + { + "epoch": 0.15, + "learning_rate": 1.9208928535593178e-05, + "loss": 0.4968, + "step": 1802 + }, + { + "epoch": 0.15, + "learning_rate": 1.920785167035951e-05, + "loss": 0.4921, + "step": 1803 + }, + { + "epoch": 0.15, + "learning_rate": 1.9206774102896627e-05, + "loss": 0.4859, + "step": 1804 + }, + { + "epoch": 0.15, + "learning_rate": 1.920569583328672e-05, + "loss": 0.5059, + "step": 1805 + }, + { + "epoch": 0.15, + "learning_rate": 1.9204616861612013e-05, + "loss": 0.5058, + "step": 1806 + }, + { + "epoch": 0.15, + "learning_rate": 1.9203537187954796e-05, + "loss": 0.4832, + "step": 1807 + }, + { + "epoch": 0.15, + "learning_rate": 1.920245681239741e-05, + "loss": 0.5292, + "step": 1808 + }, + { + "epoch": 0.15, + "learning_rate": 1.9201375735022246e-05, + "loss": 0.4827, + "step": 1809 + }, + { + "epoch": 0.15, + "learning_rate": 1.920029395591176e-05, + "loss": 0.5134, + "step": 1810 + }, + { + "epoch": 0.15, + "learning_rate": 1.9199211475148442e-05, + "loss": 0.5044, + "step": 1811 + }, + { + "epoch": 0.15, + "learning_rate": 1.919812829281485e-05, + "loss": 0.4999, + "step": 1812 + }, + { + "epoch": 0.15, + "learning_rate": 1.9197044408993595e-05, + "loss": 0.517, + "step": 1813 + }, + { + "epoch": 0.15, + "learning_rate": 1.919595982376734e-05, + "loss": 0.5089, + "step": 1814 + }, + { + "epoch": 0.15, + "learning_rate": 1.9194874537218792e-05, + "loss": 0.5008, + "step": 1815 + }, + { + "epoch": 0.15, + "learning_rate": 1.9193788549430726e-05, + "loss": 0.4982, + "step": 1816 + }, + { + "epoch": 0.15, + "learning_rate": 1.919270186048596e-05, + "loss": 0.5139, + "step": 1817 + }, + { + "epoch": 0.16, + "learning_rate": 1.919161447046738e-05, + "loss": 0.5119, + "step": 1818 + }, + { + "epoch": 0.16, + "learning_rate": 1.91905263794579e-05, + "loss": 0.5145, + "step": 1819 + }, + { + "epoch": 0.16, + "learning_rate": 1.918943758754051e-05, + "loss": 0.4907, + "step": 1820 + }, + { + "epoch": 0.16, + "learning_rate": 1.9188348094798245e-05, + "loss": 0.521, + "step": 1821 + }, + { + "epoch": 0.16, + "learning_rate": 1.9187257901314194e-05, + "loss": 0.5114, + "step": 1822 + }, + { + "epoch": 0.16, + "learning_rate": 1.91861670071715e-05, + "loss": 0.4843, + "step": 1823 + }, + { + "epoch": 0.16, + "learning_rate": 1.918507541245336e-05, + "loss": 0.5221, + "step": 1824 + }, + { + "epoch": 0.16, + "learning_rate": 1.9183983117243022e-05, + "loss": 0.49, + "step": 1825 + }, + { + "epoch": 0.16, + "learning_rate": 1.918289012162379e-05, + "loss": 0.5115, + "step": 1826 + }, + { + "epoch": 0.16, + "learning_rate": 1.9181796425679015e-05, + "loss": 0.4902, + "step": 1827 + }, + { + "epoch": 0.16, + "learning_rate": 1.9180702029492118e-05, + "loss": 0.5094, + "step": 1828 + }, + { + "epoch": 0.16, + "learning_rate": 1.9179606933146553e-05, + "loss": 0.5074, + "step": 1829 + }, + { + "epoch": 0.16, + "learning_rate": 1.9178511136725842e-05, + "loss": 0.4945, + "step": 1830 + }, + { + "epoch": 0.16, + "learning_rate": 1.917741464031355e-05, + "loss": 0.5097, + "step": 1831 + }, + { + "epoch": 0.16, + "learning_rate": 1.9176317443993303e-05, + "loss": 0.5015, + "step": 1832 + }, + { + "epoch": 0.16, + "learning_rate": 1.917521954784878e-05, + "loss": 0.5134, + "step": 1833 + }, + { + "epoch": 0.16, + "learning_rate": 1.9174120951963705e-05, + "loss": 0.498, + "step": 1834 + }, + { + "epoch": 0.16, + "learning_rate": 1.917302165642187e-05, + "loss": 0.5079, + "step": 1835 + }, + { + "epoch": 0.16, + "learning_rate": 1.9171921661307102e-05, + "loss": 0.5108, + "step": 1836 + }, + { + "epoch": 0.16, + "learning_rate": 1.91708209667033e-05, + "loss": 0.4983, + "step": 1837 + }, + { + "epoch": 0.16, + "learning_rate": 1.9169719572694404e-05, + "loss": 0.52, + "step": 1838 + }, + { + "epoch": 0.16, + "learning_rate": 1.916861747936441e-05, + "loss": 0.4885, + "step": 1839 + }, + { + "epoch": 0.16, + "learning_rate": 1.916751468679737e-05, + "loss": 0.4859, + "step": 1840 + }, + { + "epoch": 0.16, + "learning_rate": 1.9166411195077387e-05, + "loss": 0.5119, + "step": 1841 + }, + { + "epoch": 0.16, + "learning_rate": 1.916530700428862e-05, + "loss": 0.4982, + "step": 1842 + }, + { + "epoch": 0.16, + "learning_rate": 1.916420211451527e-05, + "loss": 0.4985, + "step": 1843 + }, + { + "epoch": 0.16, + "learning_rate": 1.916309652584161e-05, + "loss": 0.503, + "step": 1844 + }, + { + "epoch": 0.16, + "learning_rate": 1.916199023835196e-05, + "loss": 0.5275, + "step": 1845 + }, + { + "epoch": 0.16, + "learning_rate": 1.9160883252130678e-05, + "loss": 0.4892, + "step": 1846 + }, + { + "epoch": 0.16, + "learning_rate": 1.9159775567262194e-05, + "loss": 0.5243, + "step": 1847 + }, + { + "epoch": 0.16, + "learning_rate": 1.9158667183830988e-05, + "loss": 0.5119, + "step": 1848 + }, + { + "epoch": 0.16, + "learning_rate": 1.9157558101921583e-05, + "loss": 0.486, + "step": 1849 + }, + { + "epoch": 0.16, + "learning_rate": 1.915644832161857e-05, + "loss": 0.5315, + "step": 1850 + }, + { + "epoch": 0.16, + "learning_rate": 1.9155337843006573e-05, + "loss": 0.5227, + "step": 1851 + }, + { + "epoch": 0.16, + "learning_rate": 1.9154226666170296e-05, + "loss": 0.4747, + "step": 1852 + }, + { + "epoch": 0.16, + "learning_rate": 1.9153114791194475e-05, + "loss": 0.5011, + "step": 1853 + }, + { + "epoch": 0.16, + "learning_rate": 1.9152002218163904e-05, + "loss": 0.5114, + "step": 1854 + }, + { + "epoch": 0.16, + "learning_rate": 1.9150888947163436e-05, + "loss": 0.5104, + "step": 1855 + }, + { + "epoch": 0.16, + "learning_rate": 1.9149774978277975e-05, + "loss": 0.4996, + "step": 1856 + }, + { + "epoch": 0.16, + "learning_rate": 1.9148660311592477e-05, + "loss": 0.5015, + "step": 1857 + }, + { + "epoch": 0.16, + "learning_rate": 1.9147544947191943e-05, + "loss": 0.5146, + "step": 1858 + }, + { + "epoch": 0.16, + "learning_rate": 1.9146428885161444e-05, + "loss": 0.5187, + "step": 1859 + }, + { + "epoch": 0.16, + "learning_rate": 1.9145312125586096e-05, + "loss": 0.5148, + "step": 1860 + }, + { + "epoch": 0.16, + "learning_rate": 1.9144194668551063e-05, + "loss": 0.5021, + "step": 1861 + }, + { + "epoch": 0.16, + "learning_rate": 1.9143076514141566e-05, + "loss": 0.4934, + "step": 1862 + }, + { + "epoch": 0.16, + "learning_rate": 1.9141957662442885e-05, + "loss": 0.4961, + "step": 1863 + }, + { + "epoch": 0.16, + "learning_rate": 1.9140838113540347e-05, + "loss": 0.5006, + "step": 1864 + }, + { + "epoch": 0.16, + "learning_rate": 1.9139717867519332e-05, + "loss": 0.4907, + "step": 1865 + }, + { + "epoch": 0.16, + "learning_rate": 1.9138596924465276e-05, + "loss": 0.488, + "step": 1866 + }, + { + "epoch": 0.16, + "learning_rate": 1.9137475284463668e-05, + "loss": 0.5067, + "step": 1867 + }, + { + "epoch": 0.16, + "learning_rate": 1.913635294760004e-05, + "loss": 0.4889, + "step": 1868 + }, + { + "epoch": 0.16, + "learning_rate": 1.9135229913959997e-05, + "loss": 0.4955, + "step": 1869 + }, + { + "epoch": 0.16, + "learning_rate": 1.9134106183629184e-05, + "loss": 0.5049, + "step": 1870 + }, + { + "epoch": 0.16, + "learning_rate": 1.9132981756693298e-05, + "loss": 0.4995, + "step": 1871 + }, + { + "epoch": 0.16, + "learning_rate": 1.9131856633238096e-05, + "loss": 0.4981, + "step": 1872 + }, + { + "epoch": 0.16, + "learning_rate": 1.913073081334938e-05, + "loss": 0.5144, + "step": 1873 + }, + { + "epoch": 0.16, + "learning_rate": 1.9129604297113013e-05, + "loss": 0.5009, + "step": 1874 + }, + { + "epoch": 0.16, + "learning_rate": 1.912847708461491e-05, + "loss": 0.5003, + "step": 1875 + }, + { + "epoch": 0.16, + "learning_rate": 1.912734917594103e-05, + "loss": 0.5128, + "step": 1876 + }, + { + "epoch": 0.16, + "learning_rate": 1.91262205711774e-05, + "loss": 0.5375, + "step": 1877 + }, + { + "epoch": 0.16, + "learning_rate": 1.9125091270410088e-05, + "loss": 0.4824, + "step": 1878 + }, + { + "epoch": 0.16, + "learning_rate": 1.9123961273725218e-05, + "loss": 0.5201, + "step": 1879 + }, + { + "epoch": 0.16, + "learning_rate": 1.912283058120897e-05, + "loss": 0.5112, + "step": 1880 + }, + { + "epoch": 0.16, + "learning_rate": 1.9121699192947577e-05, + "loss": 0.5137, + "step": 1881 + }, + { + "epoch": 0.16, + "learning_rate": 1.912056710902732e-05, + "loss": 0.5029, + "step": 1882 + }, + { + "epoch": 0.16, + "learning_rate": 1.9119434329534538e-05, + "loss": 0.5111, + "step": 1883 + }, + { + "epoch": 0.16, + "learning_rate": 1.9118300854555626e-05, + "loss": 0.5002, + "step": 1884 + }, + { + "epoch": 0.16, + "learning_rate": 1.9117166684177017e-05, + "loss": 0.4839, + "step": 1885 + }, + { + "epoch": 0.16, + "learning_rate": 1.9116031818485216e-05, + "loss": 0.5315, + "step": 1886 + }, + { + "epoch": 0.16, + "learning_rate": 1.911489625756677e-05, + "loss": 0.4964, + "step": 1887 + }, + { + "epoch": 0.16, + "learning_rate": 1.911376000150828e-05, + "loss": 0.5012, + "step": 1888 + }, + { + "epoch": 0.16, + "learning_rate": 1.9112623050396407e-05, + "loss": 0.4984, + "step": 1889 + }, + { + "epoch": 0.16, + "learning_rate": 1.9111485404317852e-05, + "loss": 0.5186, + "step": 1890 + }, + { + "epoch": 0.16, + "learning_rate": 1.9110347063359383e-05, + "loss": 0.4986, + "step": 1891 + }, + { + "epoch": 0.16, + "learning_rate": 1.9109208027607814e-05, + "loss": 0.4944, + "step": 1892 + }, + { + "epoch": 0.16, + "learning_rate": 1.910806829715001e-05, + "loss": 0.4916, + "step": 1893 + }, + { + "epoch": 0.16, + "learning_rate": 1.910692787207289e-05, + "loss": 0.5037, + "step": 1894 + }, + { + "epoch": 0.16, + "learning_rate": 1.9105786752463434e-05, + "loss": 0.512, + "step": 1895 + }, + { + "epoch": 0.16, + "learning_rate": 1.9104644938408663e-05, + "loss": 0.501, + "step": 1896 + }, + { + "epoch": 0.16, + "learning_rate": 1.910350242999566e-05, + "loss": 0.5076, + "step": 1897 + }, + { + "epoch": 0.16, + "learning_rate": 1.9102359227311554e-05, + "loss": 0.4904, + "step": 1898 + }, + { + "epoch": 0.16, + "learning_rate": 1.910121533044353e-05, + "loss": 0.5125, + "step": 1899 + }, + { + "epoch": 0.16, + "learning_rate": 1.9100070739478833e-05, + "loss": 0.5132, + "step": 1900 + }, + { + "epoch": 0.16, + "learning_rate": 1.9098925454504747e-05, + "loss": 0.4918, + "step": 1901 + }, + { + "epoch": 0.16, + "learning_rate": 1.9097779475608618e-05, + "loss": 0.5235, + "step": 1902 + }, + { + "epoch": 0.16, + "learning_rate": 1.9096632802877845e-05, + "loss": 0.4912, + "step": 1903 + }, + { + "epoch": 0.16, + "learning_rate": 1.9095485436399878e-05, + "loss": 0.5099, + "step": 1904 + }, + { + "epoch": 0.16, + "learning_rate": 1.909433737626222e-05, + "loss": 0.4941, + "step": 1905 + }, + { + "epoch": 0.16, + "learning_rate": 1.9093188622552424e-05, + "loss": 0.5187, + "step": 1906 + }, + { + "epoch": 0.16, + "learning_rate": 1.90920391753581e-05, + "loss": 0.501, + "step": 1907 + }, + { + "epoch": 0.16, + "learning_rate": 1.909088903476691e-05, + "loss": 0.4979, + "step": 1908 + }, + { + "epoch": 0.16, + "learning_rate": 1.9089738200866574e-05, + "loss": 0.5073, + "step": 1909 + }, + { + "epoch": 0.16, + "learning_rate": 1.908858667374485e-05, + "loss": 0.5072, + "step": 1910 + }, + { + "epoch": 0.16, + "learning_rate": 1.9087434453489564e-05, + "loss": 0.4891, + "step": 1911 + }, + { + "epoch": 0.16, + "learning_rate": 1.908628154018859e-05, + "loss": 0.5014, + "step": 1912 + }, + { + "epoch": 0.16, + "learning_rate": 1.908512793392985e-05, + "loss": 0.5155, + "step": 1913 + }, + { + "epoch": 0.16, + "learning_rate": 1.908397363480132e-05, + "loss": 0.4976, + "step": 1914 + }, + { + "epoch": 0.16, + "learning_rate": 1.908281864289104e-05, + "loss": 0.4952, + "step": 1915 + }, + { + "epoch": 0.16, + "learning_rate": 1.908166295828709e-05, + "loss": 0.518, + "step": 1916 + }, + { + "epoch": 0.16, + "learning_rate": 1.9080506581077607e-05, + "loss": 0.4838, + "step": 1917 + }, + { + "epoch": 0.16, + "learning_rate": 1.9079349511350784e-05, + "loss": 0.4925, + "step": 1918 + }, + { + "epoch": 0.16, + "learning_rate": 1.907819174919486e-05, + "loss": 0.499, + "step": 1919 + }, + { + "epoch": 0.16, + "learning_rate": 1.9077033294698135e-05, + "loss": 0.5167, + "step": 1920 + }, + { + "epoch": 0.16, + "learning_rate": 1.9075874147948955e-05, + "loss": 0.4874, + "step": 1921 + }, + { + "epoch": 0.16, + "learning_rate": 1.9074714309035723e-05, + "loss": 0.5168, + "step": 1922 + }, + { + "epoch": 0.16, + "learning_rate": 1.907355377804689e-05, + "loss": 0.5439, + "step": 1923 + }, + { + "epoch": 0.16, + "learning_rate": 1.9072392555070965e-05, + "loss": 0.5062, + "step": 1924 + }, + { + "epoch": 0.16, + "learning_rate": 1.907123064019651e-05, + "loss": 0.527, + "step": 1925 + }, + { + "epoch": 0.16, + "learning_rate": 1.907006803351213e-05, + "loss": 0.5108, + "step": 1926 + }, + { + "epoch": 0.16, + "learning_rate": 1.9068904735106502e-05, + "loss": 0.5174, + "step": 1927 + }, + { + "epoch": 0.16, + "learning_rate": 1.9067740745068334e-05, + "loss": 0.4963, + "step": 1928 + }, + { + "epoch": 0.16, + "learning_rate": 1.90665760634864e-05, + "loss": 0.4976, + "step": 1929 + }, + { + "epoch": 0.16, + "learning_rate": 1.9065410690449525e-05, + "loss": 0.5104, + "step": 1930 + }, + { + "epoch": 0.16, + "learning_rate": 1.906424462604658e-05, + "loss": 0.4829, + "step": 1931 + }, + { + "epoch": 0.16, + "learning_rate": 1.9063077870366504e-05, + "loss": 0.5075, + "step": 1932 + }, + { + "epoch": 0.16, + "learning_rate": 1.9061910423498268e-05, + "loss": 0.5005, + "step": 1933 + }, + { + "epoch": 0.16, + "learning_rate": 1.906074228553091e-05, + "loss": 0.4836, + "step": 1934 + }, + { + "epoch": 0.16, + "learning_rate": 1.905957345655352e-05, + "loss": 0.4977, + "step": 1935 + }, + { + "epoch": 0.17, + "learning_rate": 1.9058403936655235e-05, + "loss": 0.496, + "step": 1936 + }, + { + "epoch": 0.17, + "learning_rate": 1.9057233725925245e-05, + "loss": 0.5125, + "step": 1937 + }, + { + "epoch": 0.17, + "learning_rate": 1.9056062824452802e-05, + "loss": 0.4984, + "step": 1938 + }, + { + "epoch": 0.17, + "learning_rate": 1.90548912323272e-05, + "loss": 0.522, + "step": 1939 + }, + { + "epoch": 0.17, + "learning_rate": 1.9053718949637788e-05, + "loss": 0.4909, + "step": 1940 + }, + { + "epoch": 0.17, + "learning_rate": 1.9052545976473972e-05, + "loss": 0.5169, + "step": 1941 + }, + { + "epoch": 0.17, + "learning_rate": 1.9051372312925208e-05, + "loss": 0.5063, + "step": 1942 + }, + { + "epoch": 0.17, + "learning_rate": 1.9050197959081e-05, + "loss": 0.513, + "step": 1943 + }, + { + "epoch": 0.17, + "learning_rate": 1.9049022915030916e-05, + "loss": 0.4878, + "step": 1944 + }, + { + "epoch": 0.17, + "learning_rate": 1.904784718086456e-05, + "loss": 0.4979, + "step": 1945 + }, + { + "epoch": 0.17, + "learning_rate": 1.904667075667161e-05, + "loss": 0.5115, + "step": 1946 + }, + { + "epoch": 0.17, + "learning_rate": 1.9045493642541775e-05, + "loss": 0.4901, + "step": 1947 + }, + { + "epoch": 0.17, + "learning_rate": 1.9044315838564835e-05, + "loss": 0.4972, + "step": 1948 + }, + { + "epoch": 0.17, + "learning_rate": 1.9043137344830608e-05, + "loss": 0.4924, + "step": 1949 + }, + { + "epoch": 0.17, + "learning_rate": 1.9041958161428976e-05, + "loss": 0.5042, + "step": 1950 + }, + { + "epoch": 0.17, + "learning_rate": 1.9040778288449862e-05, + "loss": 0.5015, + "step": 1951 + }, + { + "epoch": 0.17, + "learning_rate": 1.9039597725983254e-05, + "loss": 0.4963, + "step": 1952 + }, + { + "epoch": 0.17, + "learning_rate": 1.9038416474119182e-05, + "loss": 0.4869, + "step": 1953 + }, + { + "epoch": 0.17, + "learning_rate": 1.9037234532947737e-05, + "loss": 0.4995, + "step": 1954 + }, + { + "epoch": 0.17, + "learning_rate": 1.9036051902559055e-05, + "loss": 0.5222, + "step": 1955 + }, + { + "epoch": 0.17, + "learning_rate": 1.9034868583043334e-05, + "loss": 0.4972, + "step": 1956 + }, + { + "epoch": 0.17, + "learning_rate": 1.9033684574490813e-05, + "loss": 0.4951, + "step": 1957 + }, + { + "epoch": 0.17, + "learning_rate": 1.9032499876991793e-05, + "loss": 0.5051, + "step": 1958 + }, + { + "epoch": 0.17, + "learning_rate": 1.903131449063662e-05, + "loss": 0.5171, + "step": 1959 + }, + { + "epoch": 0.17, + "learning_rate": 1.9030128415515705e-05, + "loss": 0.4892, + "step": 1960 + }, + { + "epoch": 0.17, + "learning_rate": 1.902894165171949e-05, + "loss": 0.5088, + "step": 1961 + }, + { + "epoch": 0.17, + "learning_rate": 1.9027754199338496e-05, + "loss": 0.4883, + "step": 1962 + }, + { + "epoch": 0.17, + "learning_rate": 1.9026566058463277e-05, + "loss": 0.4899, + "step": 1963 + }, + { + "epoch": 0.17, + "learning_rate": 1.9025377229184442e-05, + "loss": 0.4995, + "step": 1964 + }, + { + "epoch": 0.17, + "learning_rate": 1.902418771159266e-05, + "loss": 0.4921, + "step": 1965 + }, + { + "epoch": 0.17, + "learning_rate": 1.9022997505778652e-05, + "loss": 0.5169, + "step": 1966 + }, + { + "epoch": 0.17, + "learning_rate": 1.902180661183318e-05, + "loss": 0.5107, + "step": 1967 + }, + { + "epoch": 0.17, + "learning_rate": 1.9020615029847073e-05, + "loss": 0.5267, + "step": 1968 + }, + { + "epoch": 0.17, + "learning_rate": 1.9019422759911204e-05, + "loss": 0.5001, + "step": 1969 + }, + { + "epoch": 0.17, + "learning_rate": 1.90182298021165e-05, + "loss": 0.4853, + "step": 1970 + }, + { + "epoch": 0.17, + "learning_rate": 1.901703615655394e-05, + "loss": 0.4888, + "step": 1971 + }, + { + "epoch": 0.17, + "learning_rate": 1.901584182331456e-05, + "loss": 0.4978, + "step": 1972 + }, + { + "epoch": 0.17, + "learning_rate": 1.901464680248944e-05, + "loss": 0.5072, + "step": 1973 + }, + { + "epoch": 0.17, + "learning_rate": 1.9013451094169724e-05, + "loss": 0.5154, + "step": 1974 + }, + { + "epoch": 0.17, + "learning_rate": 1.9012254698446595e-05, + "loss": 0.5041, + "step": 1975 + }, + { + "epoch": 0.17, + "learning_rate": 1.9011057615411297e-05, + "loss": 0.4964, + "step": 1976 + }, + { + "epoch": 0.17, + "learning_rate": 1.9009859845155126e-05, + "loss": 0.501, + "step": 1977 + }, + { + "epoch": 0.17, + "learning_rate": 1.9008661387769427e-05, + "loss": 0.5194, + "step": 1978 + }, + { + "epoch": 0.17, + "learning_rate": 1.9007462243345603e-05, + "loss": 0.4925, + "step": 1979 + }, + { + "epoch": 0.17, + "learning_rate": 1.90062624119751e-05, + "loss": 0.5081, + "step": 1980 + }, + { + "epoch": 0.17, + "learning_rate": 1.900506189374943e-05, + "loss": 0.4866, + "step": 1981 + }, + { + "epoch": 0.17, + "learning_rate": 1.9003860688760142e-05, + "loss": 0.4745, + "step": 1982 + }, + { + "epoch": 0.17, + "learning_rate": 1.9002658797098846e-05, + "loss": 0.4859, + "step": 1983 + }, + { + "epoch": 0.17, + "learning_rate": 1.9001456218857207e-05, + "loss": 0.4979, + "step": 1984 + }, + { + "epoch": 0.17, + "learning_rate": 1.9000252954126938e-05, + "loss": 0.4972, + "step": 1985 + }, + { + "epoch": 0.17, + "learning_rate": 1.8999049002999804e-05, + "loss": 0.498, + "step": 1986 + }, + { + "epoch": 0.17, + "learning_rate": 1.8997844365567623e-05, + "loss": 0.5133, + "step": 1987 + }, + { + "epoch": 0.17, + "learning_rate": 1.8996639041922263e-05, + "loss": 0.5196, + "step": 1988 + }, + { + "epoch": 0.17, + "learning_rate": 1.8995433032155652e-05, + "loss": 0.4824, + "step": 1989 + }, + { + "epoch": 0.17, + "learning_rate": 1.899422633635976e-05, + "loss": 0.4819, + "step": 1990 + }, + { + "epoch": 0.17, + "learning_rate": 1.899301895462662e-05, + "loss": 0.518, + "step": 1991 + }, + { + "epoch": 0.17, + "learning_rate": 1.8991810887048316e-05, + "loss": 0.49, + "step": 1992 + }, + { + "epoch": 0.17, + "learning_rate": 1.8990602133716968e-05, + "loss": 0.5008, + "step": 1993 + }, + { + "epoch": 0.17, + "learning_rate": 1.8989392694724764e-05, + "loss": 0.527, + "step": 1994 + }, + { + "epoch": 0.17, + "learning_rate": 1.8988182570163948e-05, + "loss": 0.4768, + "step": 1995 + }, + { + "epoch": 0.17, + "learning_rate": 1.8986971760126805e-05, + "loss": 0.5136, + "step": 1996 + }, + { + "epoch": 0.17, + "learning_rate": 1.8985760264705674e-05, + "loss": 0.4948, + "step": 1997 + }, + { + "epoch": 0.17, + "learning_rate": 1.898454808399295e-05, + "loss": 0.5084, + "step": 1998 + }, + { + "epoch": 0.17, + "learning_rate": 1.898333521808108e-05, + "loss": 0.5103, + "step": 1999 + }, + { + "epoch": 0.17, + "learning_rate": 1.8982121667062566e-05, + "loss": 0.5144, + "step": 2000 + }, + { + "epoch": 0.17, + "learning_rate": 1.898090743102995e-05, + "loss": 0.5238, + "step": 2001 + }, + { + "epoch": 0.17, + "learning_rate": 1.897969251007584e-05, + "loss": 0.4808, + "step": 2002 + }, + { + "epoch": 0.17, + "learning_rate": 1.8978476904292892e-05, + "loss": 0.4974, + "step": 2003 + }, + { + "epoch": 0.17, + "learning_rate": 1.897726061377381e-05, + "loss": 0.4833, + "step": 2004 + }, + { + "epoch": 0.17, + "learning_rate": 1.8976043638611353e-05, + "loss": 0.4994, + "step": 2005 + }, + { + "epoch": 0.17, + "learning_rate": 1.8974825978898337e-05, + "loss": 0.4966, + "step": 2006 + }, + { + "epoch": 0.17, + "learning_rate": 1.897360763472762e-05, + "loss": 0.5115, + "step": 2007 + }, + { + "epoch": 0.17, + "learning_rate": 1.8972388606192124e-05, + "loss": 0.4845, + "step": 2008 + }, + { + "epoch": 0.17, + "learning_rate": 1.8971168893384814e-05, + "loss": 0.5115, + "step": 2009 + }, + { + "epoch": 0.17, + "learning_rate": 1.896994849639871e-05, + "loss": 0.5277, + "step": 2010 + }, + { + "epoch": 0.17, + "learning_rate": 1.8968727415326885e-05, + "loss": 0.4887, + "step": 2011 + }, + { + "epoch": 0.17, + "learning_rate": 1.896750565026246e-05, + "loss": 0.5283, + "step": 2012 + }, + { + "epoch": 0.17, + "learning_rate": 1.8966283201298625e-05, + "loss": 0.4995, + "step": 2013 + }, + { + "epoch": 0.17, + "learning_rate": 1.8965060068528594e-05, + "loss": 0.4995, + "step": 2014 + }, + { + "epoch": 0.17, + "learning_rate": 1.8963836252045656e-05, + "loss": 0.5138, + "step": 2015 + }, + { + "epoch": 0.17, + "learning_rate": 1.8962611751943142e-05, + "loss": 0.5081, + "step": 2016 + }, + { + "epoch": 0.17, + "learning_rate": 1.8961386568314438e-05, + "loss": 0.5221, + "step": 2017 + }, + { + "epoch": 0.17, + "learning_rate": 1.8960160701252982e-05, + "loss": 0.4668, + "step": 2018 + }, + { + "epoch": 0.17, + "learning_rate": 1.895893415085226e-05, + "loss": 0.5072, + "step": 2019 + }, + { + "epoch": 0.17, + "learning_rate": 1.895770691720582e-05, + "loss": 0.4964, + "step": 2020 + }, + { + "epoch": 0.17, + "learning_rate": 1.8956479000407257e-05, + "loss": 0.5068, + "step": 2021 + }, + { + "epoch": 0.17, + "learning_rate": 1.8955250400550206e-05, + "loss": 0.5087, + "step": 2022 + }, + { + "epoch": 0.17, + "learning_rate": 1.8954021117728377e-05, + "loss": 0.5057, + "step": 2023 + }, + { + "epoch": 0.17, + "learning_rate": 1.8952791152035514e-05, + "loss": 0.508, + "step": 2024 + }, + { + "epoch": 0.17, + "learning_rate": 1.895156050356542e-05, + "loss": 0.4828, + "step": 2025 + }, + { + "epoch": 0.17, + "learning_rate": 1.8950329172411954e-05, + "loss": 0.5169, + "step": 2026 + }, + { + "epoch": 0.17, + "learning_rate": 1.8949097158669017e-05, + "loss": 0.5189, + "step": 2027 + }, + { + "epoch": 0.17, + "learning_rate": 1.8947864462430567e-05, + "loss": 0.4982, + "step": 2028 + }, + { + "epoch": 0.17, + "learning_rate": 1.894663108379062e-05, + "loss": 0.5082, + "step": 2029 + }, + { + "epoch": 0.17, + "learning_rate": 1.8945397022843233e-05, + "loss": 0.4912, + "step": 2030 + }, + { + "epoch": 0.17, + "learning_rate": 1.8944162279682524e-05, + "loss": 0.5246, + "step": 2031 + }, + { + "epoch": 0.17, + "learning_rate": 1.894292685440266e-05, + "loss": 0.5066, + "step": 2032 + }, + { + "epoch": 0.17, + "learning_rate": 1.8941690747097857e-05, + "loss": 0.503, + "step": 2033 + }, + { + "epoch": 0.17, + "learning_rate": 1.894045395786239e-05, + "loss": 0.4973, + "step": 2034 + }, + { + "epoch": 0.17, + "learning_rate": 1.8939216486790577e-05, + "loss": 0.5065, + "step": 2035 + }, + { + "epoch": 0.17, + "learning_rate": 1.8937978333976797e-05, + "loss": 0.4834, + "step": 2036 + }, + { + "epoch": 0.17, + "learning_rate": 1.893673949951547e-05, + "loss": 0.4906, + "step": 2037 + }, + { + "epoch": 0.17, + "learning_rate": 1.893549998350108e-05, + "loss": 0.5169, + "step": 2038 + }, + { + "epoch": 0.17, + "learning_rate": 1.8934259786028158e-05, + "loss": 0.4963, + "step": 2039 + }, + { + "epoch": 0.17, + "learning_rate": 1.8933018907191286e-05, + "loss": 0.5142, + "step": 2040 + }, + { + "epoch": 0.17, + "learning_rate": 1.8931777347085094e-05, + "loss": 0.4887, + "step": 2041 + }, + { + "epoch": 0.17, + "learning_rate": 1.8930535105804275e-05, + "loss": 0.5339, + "step": 2042 + }, + { + "epoch": 0.17, + "learning_rate": 1.8929292183443565e-05, + "loss": 0.4961, + "step": 2043 + }, + { + "epoch": 0.17, + "learning_rate": 1.8928048580097758e-05, + "loss": 0.5132, + "step": 2044 + }, + { + "epoch": 0.17, + "learning_rate": 1.8926804295861687e-05, + "loss": 0.4882, + "step": 2045 + }, + { + "epoch": 0.17, + "learning_rate": 1.8925559330830254e-05, + "loss": 0.4924, + "step": 2046 + }, + { + "epoch": 0.17, + "learning_rate": 1.8924313685098405e-05, + "loss": 0.4917, + "step": 2047 + }, + { + "epoch": 0.17, + "learning_rate": 1.8923067358761135e-05, + "loss": 0.4959, + "step": 2048 + }, + { + "epoch": 0.17, + "learning_rate": 1.8921820351913496e-05, + "loss": 0.4997, + "step": 2049 + }, + { + "epoch": 0.17, + "learning_rate": 1.892057266465059e-05, + "loss": 0.4814, + "step": 2050 + }, + { + "epoch": 0.17, + "learning_rate": 1.8919324297067566e-05, + "loss": 0.4939, + "step": 2051 + }, + { + "epoch": 0.17, + "learning_rate": 1.891807524925964e-05, + "loss": 0.5063, + "step": 2052 + }, + { + "epoch": 0.18, + "learning_rate": 1.8916825521322064e-05, + "loss": 0.4992, + "step": 2053 + }, + { + "epoch": 0.18, + "learning_rate": 1.8915575113350143e-05, + "loss": 0.5254, + "step": 2054 + }, + { + "epoch": 0.18, + "learning_rate": 1.891432402543924e-05, + "loss": 0.5021, + "step": 2055 + }, + { + "epoch": 0.18, + "learning_rate": 1.8913072257684777e-05, + "loss": 0.5118, + "step": 2056 + }, + { + "epoch": 0.18, + "learning_rate": 1.891181981018221e-05, + "loss": 0.4919, + "step": 2057 + }, + { + "epoch": 0.18, + "learning_rate": 1.891056668302706e-05, + "loss": 0.5033, + "step": 2058 + }, + { + "epoch": 0.18, + "learning_rate": 1.890931287631489e-05, + "loss": 0.4833, + "step": 2059 + }, + { + "epoch": 0.18, + "learning_rate": 1.8908058390141327e-05, + "loss": 0.4815, + "step": 2060 + }, + { + "epoch": 0.18, + "learning_rate": 1.8906803224602043e-05, + "loss": 0.5135, + "step": 2061 + }, + { + "epoch": 0.18, + "learning_rate": 1.890554737979276e-05, + "loss": 0.5008, + "step": 2062 + }, + { + "epoch": 0.18, + "learning_rate": 1.8904290855809253e-05, + "loss": 0.4931, + "step": 2063 + }, + { + "epoch": 0.18, + "learning_rate": 1.8903033652747352e-05, + "loss": 0.5106, + "step": 2064 + }, + { + "epoch": 0.18, + "learning_rate": 1.8901775770702933e-05, + "loss": 0.5136, + "step": 2065 + }, + { + "epoch": 0.18, + "learning_rate": 1.8900517209771934e-05, + "loss": 0.5042, + "step": 2066 + }, + { + "epoch": 0.18, + "learning_rate": 1.8899257970050333e-05, + "loss": 0.5155, + "step": 2067 + }, + { + "epoch": 0.18, + "learning_rate": 1.8897998051634165e-05, + "loss": 0.5149, + "step": 2068 + }, + { + "epoch": 0.18, + "learning_rate": 1.8896737454619516e-05, + "loss": 0.5164, + "step": 2069 + }, + { + "epoch": 0.18, + "learning_rate": 1.8895476179102528e-05, + "loss": 0.5075, + "step": 2070 + }, + { + "epoch": 0.18, + "learning_rate": 1.889421422517939e-05, + "loss": 0.4964, + "step": 2071 + }, + { + "epoch": 0.18, + "learning_rate": 1.8892951592946342e-05, + "loss": 0.4939, + "step": 2072 + }, + { + "epoch": 0.18, + "learning_rate": 1.8891688282499675e-05, + "loss": 0.4876, + "step": 2073 + }, + { + "epoch": 0.18, + "learning_rate": 1.8890424293935744e-05, + "loss": 0.4997, + "step": 2074 + }, + { + "epoch": 0.18, + "learning_rate": 1.8889159627350934e-05, + "loss": 0.5198, + "step": 2075 + }, + { + "epoch": 0.18, + "learning_rate": 1.8887894282841705e-05, + "loss": 0.4933, + "step": 2076 + }, + { + "epoch": 0.18, + "learning_rate": 1.888662826050455e-05, + "loss": 0.5136, + "step": 2077 + }, + { + "epoch": 0.18, + "learning_rate": 1.8885361560436023e-05, + "loss": 0.4673, + "step": 2078 + }, + { + "epoch": 0.18, + "learning_rate": 1.888409418273273e-05, + "loss": 0.4895, + "step": 2079 + }, + { + "epoch": 0.18, + "learning_rate": 1.888282612749132e-05, + "loss": 0.5115, + "step": 2080 + }, + { + "epoch": 0.18, + "learning_rate": 1.8881557394808506e-05, + "loss": 0.53, + "step": 2081 + }, + { + "epoch": 0.18, + "learning_rate": 1.888028798478105e-05, + "loss": 0.4987, + "step": 2082 + }, + { + "epoch": 0.18, + "learning_rate": 1.8879017897505757e-05, + "loss": 0.5061, + "step": 2083 + }, + { + "epoch": 0.18, + "learning_rate": 1.8877747133079487e-05, + "loss": 0.5213, + "step": 2084 + }, + { + "epoch": 0.18, + "learning_rate": 1.887647569159916e-05, + "loss": 0.5156, + "step": 2085 + }, + { + "epoch": 0.18, + "learning_rate": 1.8875203573161737e-05, + "loss": 0.51, + "step": 2086 + }, + { + "epoch": 0.18, + "learning_rate": 1.8873930777864234e-05, + "loss": 0.5011, + "step": 2087 + }, + { + "epoch": 0.18, + "learning_rate": 1.887265730580373e-05, + "loss": 0.5048, + "step": 2088 + }, + { + "epoch": 0.18, + "learning_rate": 1.887138315707733e-05, + "loss": 0.502, + "step": 2089 + }, + { + "epoch": 0.18, + "learning_rate": 1.887010833178222e-05, + "loss": 0.518, + "step": 2090 + }, + { + "epoch": 0.18, + "learning_rate": 1.8868832830015614e-05, + "loss": 0.5185, + "step": 2091 + }, + { + "epoch": 0.18, + "learning_rate": 1.886755665187479e-05, + "loss": 0.5118, + "step": 2092 + }, + { + "epoch": 0.18, + "learning_rate": 1.8866279797457073e-05, + "loss": 0.4843, + "step": 2093 + }, + { + "epoch": 0.18, + "learning_rate": 1.8865002266859846e-05, + "loss": 0.4954, + "step": 2094 + }, + { + "epoch": 0.18, + "learning_rate": 1.886372406018053e-05, + "loss": 0.519, + "step": 2095 + }, + { + "epoch": 0.18, + "learning_rate": 1.8862445177516622e-05, + "loss": 0.4876, + "step": 2096 + }, + { + "epoch": 0.18, + "learning_rate": 1.886116561896564e-05, + "loss": 0.49, + "step": 2097 + }, + { + "epoch": 0.18, + "learning_rate": 1.885988538462517e-05, + "loss": 0.5071, + "step": 2098 + }, + { + "epoch": 0.18, + "learning_rate": 1.885860447459286e-05, + "loss": 0.4765, + "step": 2099 + }, + { + "epoch": 0.18, + "learning_rate": 1.8857322888966384e-05, + "loss": 0.5007, + "step": 2100 + }, + { + "epoch": 0.18, + "learning_rate": 1.8856040627843484e-05, + "loss": 0.5, + "step": 2101 + }, + { + "epoch": 0.18, + "learning_rate": 1.8854757691321956e-05, + "loss": 0.4886, + "step": 2102 + }, + { + "epoch": 0.18, + "learning_rate": 1.885347407949964e-05, + "loss": 0.4963, + "step": 2103 + }, + { + "epoch": 0.18, + "learning_rate": 1.8852189792474426e-05, + "loss": 0.5024, + "step": 2104 + }, + { + "epoch": 0.18, + "learning_rate": 1.8850904830344264e-05, + "loss": 0.4854, + "step": 2105 + }, + { + "epoch": 0.18, + "learning_rate": 1.8849619193207143e-05, + "loss": 0.501, + "step": 2106 + }, + { + "epoch": 0.18, + "learning_rate": 1.8848332881161126e-05, + "loss": 0.4936, + "step": 2107 + }, + { + "epoch": 0.18, + "learning_rate": 1.8847045894304295e-05, + "loss": 0.5058, + "step": 2108 + }, + { + "epoch": 0.18, + "learning_rate": 1.884575823273481e-05, + "loss": 0.485, + "step": 2109 + }, + { + "epoch": 0.18, + "learning_rate": 1.8844469896550874e-05, + "loss": 0.4971, + "step": 2110 + }, + { + "epoch": 0.18, + "learning_rate": 1.8843180885850737e-05, + "loss": 0.5213, + "step": 2111 + }, + { + "epoch": 0.18, + "learning_rate": 1.8841891200732706e-05, + "loss": 0.4799, + "step": 2112 + }, + { + "epoch": 0.18, + "learning_rate": 1.8840600841295143e-05, + "loss": 0.5118, + "step": 2113 + }, + { + "epoch": 0.18, + "learning_rate": 1.883930980763645e-05, + "loss": 0.5144, + "step": 2114 + }, + { + "epoch": 0.18, + "learning_rate": 1.8838018099855085e-05, + "loss": 0.5252, + "step": 2115 + }, + { + "epoch": 0.18, + "learning_rate": 1.8836725718049562e-05, + "loss": 0.4834, + "step": 2116 + }, + { + "epoch": 0.18, + "learning_rate": 1.8835432662318446e-05, + "loss": 0.507, + "step": 2117 + }, + { + "epoch": 0.18, + "learning_rate": 1.883413893276035e-05, + "loss": 0.5095, + "step": 2118 + }, + { + "epoch": 0.18, + "learning_rate": 1.8832844529473933e-05, + "loss": 0.4972, + "step": 2119 + }, + { + "epoch": 0.18, + "learning_rate": 1.8831549452557918e-05, + "loss": 0.504, + "step": 2120 + }, + { + "epoch": 0.18, + "learning_rate": 1.883025370211107e-05, + "loss": 0.5052, + "step": 2121 + }, + { + "epoch": 0.18, + "learning_rate": 1.8828957278232215e-05, + "loss": 0.5034, + "step": 2122 + }, + { + "epoch": 0.18, + "learning_rate": 1.882766018102021e-05, + "loss": 0.5364, + "step": 2123 + }, + { + "epoch": 0.18, + "learning_rate": 1.882636241057399e-05, + "loss": 0.5123, + "step": 2124 + }, + { + "epoch": 0.18, + "learning_rate": 1.8825063966992524e-05, + "loss": 0.4931, + "step": 2125 + }, + { + "epoch": 0.18, + "learning_rate": 1.8823764850374834e-05, + "loss": 0.4918, + "step": 2126 + }, + { + "epoch": 0.18, + "learning_rate": 1.882246506082e-05, + "loss": 0.4919, + "step": 2127 + }, + { + "epoch": 0.18, + "learning_rate": 1.8821164598427148e-05, + "loss": 0.4965, + "step": 2128 + }, + { + "epoch": 0.18, + "learning_rate": 1.8819863463295456e-05, + "loss": 0.4966, + "step": 2129 + }, + { + "epoch": 0.18, + "learning_rate": 1.8818561655524154e-05, + "loss": 0.5108, + "step": 2130 + }, + { + "epoch": 0.18, + "learning_rate": 1.8817259175212524e-05, + "loss": 0.4824, + "step": 2131 + }, + { + "epoch": 0.18, + "learning_rate": 1.88159560224599e-05, + "loss": 0.5112, + "step": 2132 + }, + { + "epoch": 0.18, + "learning_rate": 1.881465219736566e-05, + "loss": 0.5038, + "step": 2133 + }, + { + "epoch": 0.18, + "learning_rate": 1.8813347700029244e-05, + "loss": 0.5138, + "step": 2134 + }, + { + "epoch": 0.18, + "learning_rate": 1.8812042530550142e-05, + "loss": 0.4822, + "step": 2135 + }, + { + "epoch": 0.18, + "learning_rate": 1.8810736689027887e-05, + "loss": 0.4924, + "step": 2136 + }, + { + "epoch": 0.18, + "learning_rate": 1.8809430175562068e-05, + "loss": 0.4809, + "step": 2137 + }, + { + "epoch": 0.18, + "learning_rate": 1.880812299025232e-05, + "loss": 0.4805, + "step": 2138 + }, + { + "epoch": 0.18, + "learning_rate": 1.8806815133198345e-05, + "loss": 0.5124, + "step": 2139 + }, + { + "epoch": 0.18, + "learning_rate": 1.880550660449988e-05, + "loss": 0.4811, + "step": 2140 + }, + { + "epoch": 0.18, + "learning_rate": 1.880419740425672e-05, + "loss": 0.4935, + "step": 2141 + }, + { + "epoch": 0.18, + "learning_rate": 1.8802887532568706e-05, + "loss": 0.5001, + "step": 2142 + }, + { + "epoch": 0.18, + "learning_rate": 1.8801576989535745e-05, + "loss": 0.5272, + "step": 2143 + }, + { + "epoch": 0.18, + "learning_rate": 1.8800265775257772e-05, + "loss": 0.4966, + "step": 2144 + }, + { + "epoch": 0.18, + "learning_rate": 1.879895388983479e-05, + "loss": 0.5253, + "step": 2145 + }, + { + "epoch": 0.18, + "learning_rate": 1.8797641333366852e-05, + "loss": 0.5176, + "step": 2146 + }, + { + "epoch": 0.18, + "learning_rate": 1.8796328105954055e-05, + "loss": 0.4923, + "step": 2147 + }, + { + "epoch": 0.18, + "learning_rate": 1.8795014207696555e-05, + "loss": 0.5136, + "step": 2148 + }, + { + "epoch": 0.18, + "learning_rate": 1.8793699638694555e-05, + "loss": 0.5009, + "step": 2149 + }, + { + "epoch": 0.18, + "learning_rate": 1.8792384399048303e-05, + "loss": 0.5141, + "step": 2150 + }, + { + "epoch": 0.18, + "learning_rate": 1.8791068488858113e-05, + "loss": 0.4933, + "step": 2151 + }, + { + "epoch": 0.18, + "learning_rate": 1.878975190822434e-05, + "loss": 0.5033, + "step": 2152 + }, + { + "epoch": 0.18, + "learning_rate": 1.8788434657247386e-05, + "loss": 0.5189, + "step": 2153 + }, + { + "epoch": 0.18, + "learning_rate": 1.878711673602772e-05, + "loss": 0.5032, + "step": 2154 + }, + { + "epoch": 0.18, + "learning_rate": 1.878579814466584e-05, + "loss": 0.5046, + "step": 2155 + }, + { + "epoch": 0.18, + "learning_rate": 1.8784478883262318e-05, + "loss": 0.4918, + "step": 2156 + }, + { + "epoch": 0.18, + "learning_rate": 1.8783158951917763e-05, + "loss": 0.497, + "step": 2157 + }, + { + "epoch": 0.18, + "learning_rate": 1.8781838350732834e-05, + "loss": 0.4805, + "step": 2158 + }, + { + "epoch": 0.18, + "learning_rate": 1.8780517079808255e-05, + "loss": 0.4968, + "step": 2159 + }, + { + "epoch": 0.18, + "learning_rate": 1.877919513924478e-05, + "loss": 0.509, + "step": 2160 + }, + { + "epoch": 0.18, + "learning_rate": 1.8777872529143236e-05, + "loss": 0.5096, + "step": 2161 + }, + { + "epoch": 0.18, + "learning_rate": 1.877654924960448e-05, + "loss": 0.497, + "step": 2162 + }, + { + "epoch": 0.18, + "learning_rate": 1.8775225300729444e-05, + "loss": 0.5192, + "step": 2163 + }, + { + "epoch": 0.18, + "learning_rate": 1.8773900682619092e-05, + "loss": 0.4834, + "step": 2164 + }, + { + "epoch": 0.18, + "learning_rate": 1.877257539537444e-05, + "loss": 0.4962, + "step": 2165 + }, + { + "epoch": 0.18, + "learning_rate": 1.8771249439096565e-05, + "loss": 0.4987, + "step": 2166 + }, + { + "epoch": 0.18, + "learning_rate": 1.8769922813886588e-05, + "loss": 0.5191, + "step": 2167 + }, + { + "epoch": 0.18, + "learning_rate": 1.8768595519845683e-05, + "loss": 0.5017, + "step": 2168 + }, + { + "epoch": 0.18, + "learning_rate": 1.876726755707508e-05, + "loss": 0.4995, + "step": 2169 + }, + { + "epoch": 0.19, + "learning_rate": 1.8765938925676046e-05, + "loss": 0.4902, + "step": 2170 + }, + { + "epoch": 0.19, + "learning_rate": 1.8764609625749918e-05, + "loss": 0.5379, + "step": 2171 + }, + { + "epoch": 0.19, + "learning_rate": 1.8763279657398062e-05, + "loss": 0.4787, + "step": 2172 + }, + { + "epoch": 0.19, + "learning_rate": 1.876194902072192e-05, + "loss": 0.5007, + "step": 2173 + }, + { + "epoch": 0.19, + "learning_rate": 1.8760617715822964e-05, + "loss": 0.4939, + "step": 2174 + }, + { + "epoch": 0.19, + "learning_rate": 1.8759285742802725e-05, + "loss": 0.5019, + "step": 2175 + }, + { + "epoch": 0.19, + "learning_rate": 1.8757953101762786e-05, + "loss": 0.5194, + "step": 2176 + }, + { + "epoch": 0.19, + "learning_rate": 1.875661979280478e-05, + "loss": 0.49, + "step": 2177 + }, + { + "epoch": 0.19, + "learning_rate": 1.8755285816030395e-05, + "loss": 0.4972, + "step": 2178 + }, + { + "epoch": 0.19, + "learning_rate": 1.875395117154136e-05, + "loss": 0.4957, + "step": 2179 + }, + { + "epoch": 0.19, + "learning_rate": 1.875261585943946e-05, + "loss": 0.5101, + "step": 2180 + }, + { + "epoch": 0.19, + "learning_rate": 1.8751279879826533e-05, + "loss": 0.488, + "step": 2181 + }, + { + "epoch": 0.19, + "learning_rate": 1.8749943232804467e-05, + "loss": 0.4988, + "step": 2182 + }, + { + "epoch": 0.19, + "learning_rate": 1.87486059184752e-05, + "loss": 0.505, + "step": 2183 + }, + { + "epoch": 0.19, + "learning_rate": 1.8747267936940723e-05, + "loss": 0.5058, + "step": 2184 + }, + { + "epoch": 0.19, + "learning_rate": 1.8745929288303075e-05, + "loss": 0.5037, + "step": 2185 + }, + { + "epoch": 0.19, + "learning_rate": 1.8744589972664345e-05, + "loss": 0.5127, + "step": 2186 + }, + { + "epoch": 0.19, + "learning_rate": 1.8743249990126676e-05, + "loss": 0.4789, + "step": 2187 + }, + { + "epoch": 0.19, + "learning_rate": 1.874190934079226e-05, + "loss": 0.4954, + "step": 2188 + }, + { + "epoch": 0.19, + "learning_rate": 1.8740568024763344e-05, + "loss": 0.5132, + "step": 2189 + }, + { + "epoch": 0.19, + "learning_rate": 1.8739226042142216e-05, + "loss": 0.4924, + "step": 2190 + }, + { + "epoch": 0.19, + "learning_rate": 1.873788339303123e-05, + "loss": 0.4984, + "step": 2191 + }, + { + "epoch": 0.19, + "learning_rate": 1.8736540077532773e-05, + "loss": 0.5179, + "step": 2192 + }, + { + "epoch": 0.19, + "learning_rate": 1.8735196095749298e-05, + "loss": 0.4941, + "step": 2193 + }, + { + "epoch": 0.19, + "learning_rate": 1.8733851447783296e-05, + "loss": 0.5079, + "step": 2194 + }, + { + "epoch": 0.19, + "learning_rate": 1.8732506133737324e-05, + "loss": 0.5, + "step": 2195 + }, + { + "epoch": 0.19, + "learning_rate": 1.8731160153713978e-05, + "loss": 0.5091, + "step": 2196 + }, + { + "epoch": 0.19, + "learning_rate": 1.8729813507815903e-05, + "loss": 0.4959, + "step": 2197 + }, + { + "epoch": 0.19, + "learning_rate": 1.8728466196145806e-05, + "loss": 0.4936, + "step": 2198 + }, + { + "epoch": 0.19, + "learning_rate": 1.8727118218806433e-05, + "loss": 0.5095, + "step": 2199 + }, + { + "epoch": 0.19, + "learning_rate": 1.87257695759006e-05, + "loss": 0.4934, + "step": 2200 + }, + { + "epoch": 0.19, + "learning_rate": 1.872442026753114e-05, + "loss": 0.5148, + "step": 2201 + }, + { + "epoch": 0.19, + "learning_rate": 1.8723070293800972e-05, + "loss": 0.5067, + "step": 2202 + }, + { + "epoch": 0.19, + "learning_rate": 1.8721719654813043e-05, + "loss": 0.5013, + "step": 2203 + }, + { + "epoch": 0.19, + "learning_rate": 1.8720368350670363e-05, + "loss": 0.5082, + "step": 2204 + }, + { + "epoch": 0.19, + "learning_rate": 1.8719016381475987e-05, + "loss": 0.531, + "step": 2205 + }, + { + "epoch": 0.19, + "learning_rate": 1.871766374733302e-05, + "loss": 0.5092, + "step": 2206 + }, + { + "epoch": 0.19, + "learning_rate": 1.871631044834462e-05, + "loss": 0.4989, + "step": 2207 + }, + { + "epoch": 0.19, + "learning_rate": 1.8714956484613996e-05, + "loss": 0.4956, + "step": 2208 + }, + { + "epoch": 0.19, + "learning_rate": 1.8713601856244406e-05, + "loss": 0.4939, + "step": 2209 + }, + { + "epoch": 0.19, + "learning_rate": 1.871224656333916e-05, + "loss": 0.5283, + "step": 2210 + }, + { + "epoch": 0.19, + "learning_rate": 1.8710890606001618e-05, + "loss": 0.4923, + "step": 2211 + }, + { + "epoch": 0.19, + "learning_rate": 1.8709533984335194e-05, + "loss": 0.5101, + "step": 2212 + }, + { + "epoch": 0.19, + "learning_rate": 1.8708176698443347e-05, + "loss": 0.5032, + "step": 2213 + }, + { + "epoch": 0.19, + "learning_rate": 1.8706818748429585e-05, + "loss": 0.5099, + "step": 2214 + }, + { + "epoch": 0.19, + "learning_rate": 1.870546013439748e-05, + "loss": 0.5116, + "step": 2215 + }, + { + "epoch": 0.19, + "learning_rate": 1.8704100856450642e-05, + "loss": 0.4842, + "step": 2216 + }, + { + "epoch": 0.19, + "learning_rate": 1.870274091469273e-05, + "loss": 0.5002, + "step": 2217 + }, + { + "epoch": 0.19, + "learning_rate": 1.8701380309227465e-05, + "loss": 0.4895, + "step": 2218 + }, + { + "epoch": 0.19, + "learning_rate": 1.8700019040158614e-05, + "loss": 0.4993, + "step": 2219 + }, + { + "epoch": 0.19, + "learning_rate": 1.8698657107589983e-05, + "loss": 0.4972, + "step": 2220 + }, + { + "epoch": 0.19, + "learning_rate": 1.869729451162545e-05, + "loss": 0.5157, + "step": 2221 + }, + { + "epoch": 0.19, + "learning_rate": 1.8695931252368923e-05, + "loss": 0.4967, + "step": 2222 + }, + { + "epoch": 0.19, + "learning_rate": 1.8694567329924376e-05, + "loss": 0.4995, + "step": 2223 + }, + { + "epoch": 0.19, + "learning_rate": 1.869320274439583e-05, + "loss": 0.497, + "step": 2224 + }, + { + "epoch": 0.19, + "learning_rate": 1.8691837495887345e-05, + "loss": 0.4833, + "step": 2225 + }, + { + "epoch": 0.19, + "learning_rate": 1.8690471584503045e-05, + "loss": 0.5104, + "step": 2226 + }, + { + "epoch": 0.19, + "learning_rate": 1.86891050103471e-05, + "loss": 0.4871, + "step": 2227 + }, + { + "epoch": 0.19, + "learning_rate": 1.8687737773523734e-05, + "loss": 0.5246, + "step": 2228 + }, + { + "epoch": 0.19, + "learning_rate": 1.8686369874137212e-05, + "loss": 0.4909, + "step": 2229 + }, + { + "epoch": 0.19, + "learning_rate": 1.8685001312291863e-05, + "loss": 0.5019, + "step": 2230 + }, + { + "epoch": 0.19, + "learning_rate": 1.8683632088092053e-05, + "loss": 0.5041, + "step": 2231 + }, + { + "epoch": 0.19, + "learning_rate": 1.8682262201642205e-05, + "loss": 0.4934, + "step": 2232 + }, + { + "epoch": 0.19, + "learning_rate": 1.8680891653046798e-05, + "loss": 0.5032, + "step": 2233 + }, + { + "epoch": 0.19, + "learning_rate": 1.8679520442410348e-05, + "loss": 0.5058, + "step": 2234 + }, + { + "epoch": 0.19, + "learning_rate": 1.8678148569837432e-05, + "loss": 0.5066, + "step": 2235 + }, + { + "epoch": 0.19, + "learning_rate": 1.867677603543268e-05, + "loss": 0.5195, + "step": 2236 + }, + { + "epoch": 0.19, + "learning_rate": 1.8675402839300763e-05, + "loss": 0.5057, + "step": 2237 + }, + { + "epoch": 0.19, + "learning_rate": 1.8674028981546405e-05, + "loss": 0.494, + "step": 2238 + }, + { + "epoch": 0.19, + "learning_rate": 1.8672654462274383e-05, + "loss": 0.489, + "step": 2239 + }, + { + "epoch": 0.19, + "learning_rate": 1.8671279281589528e-05, + "loss": 0.5029, + "step": 2240 + }, + { + "epoch": 0.19, + "learning_rate": 1.866990343959671e-05, + "loss": 0.5133, + "step": 2241 + }, + { + "epoch": 0.19, + "learning_rate": 1.8668526936400863e-05, + "loss": 0.5121, + "step": 2242 + }, + { + "epoch": 0.19, + "learning_rate": 1.866714977210696e-05, + "loss": 0.4737, + "step": 2243 + }, + { + "epoch": 0.19, + "learning_rate": 1.866577194682003e-05, + "loss": 0.5177, + "step": 2244 + }, + { + "epoch": 0.19, + "learning_rate": 1.8664393460645154e-05, + "loss": 0.4914, + "step": 2245 + }, + { + "epoch": 0.19, + "learning_rate": 1.8663014313687463e-05, + "loss": 0.5344, + "step": 2246 + }, + { + "epoch": 0.19, + "learning_rate": 1.866163450605213e-05, + "loss": 0.4913, + "step": 2247 + }, + { + "epoch": 0.19, + "learning_rate": 1.866025403784439e-05, + "loss": 0.5004, + "step": 2248 + }, + { + "epoch": 0.19, + "learning_rate": 1.8658872909169518e-05, + "loss": 0.4897, + "step": 2249 + }, + { + "epoch": 0.19, + "learning_rate": 1.865749112013285e-05, + "loss": 0.5, + "step": 2250 + }, + { + "epoch": 0.19, + "learning_rate": 1.8656108670839768e-05, + "loss": 0.4883, + "step": 2251 + }, + { + "epoch": 0.19, + "learning_rate": 1.86547255613957e-05, + "loss": 0.5137, + "step": 2252 + }, + { + "epoch": 0.19, + "learning_rate": 1.8653341791906124e-05, + "loss": 0.5233, + "step": 2253 + }, + { + "epoch": 0.19, + "learning_rate": 1.8651957362476582e-05, + "loss": 0.5055, + "step": 2254 + }, + { + "epoch": 0.19, + "learning_rate": 1.8650572273212646e-05, + "loss": 0.4814, + "step": 2255 + }, + { + "epoch": 0.19, + "learning_rate": 1.8649186524219956e-05, + "loss": 0.5084, + "step": 2256 + }, + { + "epoch": 0.19, + "learning_rate": 1.864780011560419e-05, + "loss": 0.508, + "step": 2257 + }, + { + "epoch": 0.19, + "learning_rate": 1.8646413047471084e-05, + "loss": 0.4876, + "step": 2258 + }, + { + "epoch": 0.19, + "learning_rate": 1.8645025319926425e-05, + "loss": 0.4898, + "step": 2259 + }, + { + "epoch": 0.19, + "learning_rate": 1.864363693307604e-05, + "loss": 0.5255, + "step": 2260 + }, + { + "epoch": 0.19, + "learning_rate": 1.8642247887025816e-05, + "loss": 0.5029, + "step": 2261 + }, + { + "epoch": 0.19, + "learning_rate": 1.8640858181881692e-05, + "loss": 0.505, + "step": 2262 + }, + { + "epoch": 0.19, + "learning_rate": 1.8639467817749642e-05, + "loss": 0.518, + "step": 2263 + }, + { + "epoch": 0.19, + "learning_rate": 1.8638076794735715e-05, + "loss": 0.4998, + "step": 2264 + }, + { + "epoch": 0.19, + "learning_rate": 1.863668511294598e-05, + "loss": 0.5184, + "step": 2265 + }, + { + "epoch": 0.19, + "learning_rate": 1.863529277248659e-05, + "loss": 0.494, + "step": 2266 + }, + { + "epoch": 0.19, + "learning_rate": 1.8633899773463716e-05, + "loss": 0.5021, + "step": 2267 + }, + { + "epoch": 0.19, + "learning_rate": 1.8632506115983603e-05, + "loss": 0.4742, + "step": 2268 + }, + { + "epoch": 0.19, + "learning_rate": 1.8631111800152532e-05, + "loss": 0.4952, + "step": 2269 + }, + { + "epoch": 0.19, + "learning_rate": 1.8629716826076843e-05, + "loss": 0.5019, + "step": 2270 + }, + { + "epoch": 0.19, + "learning_rate": 1.862832119386292e-05, + "loss": 0.5026, + "step": 2271 + }, + { + "epoch": 0.19, + "learning_rate": 1.86269249036172e-05, + "loss": 0.5068, + "step": 2272 + }, + { + "epoch": 0.19, + "learning_rate": 1.862552795544617e-05, + "loss": 0.5174, + "step": 2273 + }, + { + "epoch": 0.19, + "learning_rate": 1.8624130349456367e-05, + "loss": 0.4833, + "step": 2274 + }, + { + "epoch": 0.19, + "learning_rate": 1.8622732085754386e-05, + "loss": 0.495, + "step": 2275 + }, + { + "epoch": 0.19, + "learning_rate": 1.862133316444685e-05, + "loss": 0.5174, + "step": 2276 + }, + { + "epoch": 0.19, + "learning_rate": 1.8619933585640455e-05, + "loss": 0.4898, + "step": 2277 + }, + { + "epoch": 0.19, + "learning_rate": 1.861853334944194e-05, + "loss": 0.4926, + "step": 2278 + }, + { + "epoch": 0.19, + "learning_rate": 1.8617132455958085e-05, + "loss": 0.4977, + "step": 2279 + }, + { + "epoch": 0.19, + "learning_rate": 1.861573090529574e-05, + "loss": 0.4896, + "step": 2280 + }, + { + "epoch": 0.19, + "learning_rate": 1.8614328697561785e-05, + "loss": 0.4869, + "step": 2281 + }, + { + "epoch": 0.19, + "learning_rate": 1.8612925832863158e-05, + "loss": 0.4992, + "step": 2282 + }, + { + "epoch": 0.19, + "learning_rate": 1.8611522311306848e-05, + "loss": 0.504, + "step": 2283 + }, + { + "epoch": 0.19, + "learning_rate": 1.8610118132999896e-05, + "loss": 0.4848, + "step": 2284 + }, + { + "epoch": 0.19, + "learning_rate": 1.860871329804939e-05, + "loss": 0.4723, + "step": 2285 + }, + { + "epoch": 0.19, + "learning_rate": 1.8607307806562468e-05, + "loss": 0.504, + "step": 2286 + }, + { + "epoch": 0.2, + "learning_rate": 1.8605901658646318e-05, + "loss": 0.4878, + "step": 2287 + }, + { + "epoch": 0.2, + "learning_rate": 1.8604494854408176e-05, + "loss": 0.5208, + "step": 2288 + }, + { + "epoch": 0.2, + "learning_rate": 1.8603087393955338e-05, + "loss": 0.4942, + "step": 2289 + }, + { + "epoch": 0.2, + "learning_rate": 1.8601679277395136e-05, + "loss": 0.5078, + "step": 2290 + }, + { + "epoch": 0.2, + "learning_rate": 1.8600270504834964e-05, + "loss": 0.5138, + "step": 2291 + }, + { + "epoch": 0.2, + "learning_rate": 1.8598861076382252e-05, + "loss": 0.4908, + "step": 2292 + }, + { + "epoch": 0.2, + "learning_rate": 1.85974509921445e-05, + "loss": 0.5031, + "step": 2293 + }, + { + "epoch": 0.2, + "learning_rate": 1.8596040252229243e-05, + "loss": 0.4895, + "step": 2294 + }, + { + "epoch": 0.2, + "learning_rate": 1.8594628856744065e-05, + "loss": 0.506, + "step": 2295 + }, + { + "epoch": 0.2, + "learning_rate": 1.8593216805796612e-05, + "loss": 0.4751, + "step": 2296 + }, + { + "epoch": 0.2, + "learning_rate": 1.8591804099494572e-05, + "loss": 0.4875, + "step": 2297 + }, + { + "epoch": 0.2, + "learning_rate": 1.8590390737945675e-05, + "loss": 0.5114, + "step": 2298 + }, + { + "epoch": 0.2, + "learning_rate": 1.858897672125772e-05, + "loss": 0.5065, + "step": 2299 + }, + { + "epoch": 0.2, + "learning_rate": 1.858756204953854e-05, + "loss": 0.5082, + "step": 2300 + }, + { + "epoch": 0.2, + "learning_rate": 1.858614672289603e-05, + "loss": 0.5041, + "step": 2301 + }, + { + "epoch": 0.2, + "learning_rate": 1.8584730741438128e-05, + "loss": 0.4975, + "step": 2302 + }, + { + "epoch": 0.2, + "learning_rate": 1.8583314105272813e-05, + "loss": 0.4949, + "step": 2303 + }, + { + "epoch": 0.2, + "learning_rate": 1.858189681450813e-05, + "loss": 0.5121, + "step": 2304 + }, + { + "epoch": 0.2, + "learning_rate": 1.858047886925217e-05, + "loss": 0.5034, + "step": 2305 + }, + { + "epoch": 0.2, + "learning_rate": 1.857906026961307e-05, + "loss": 0.5087, + "step": 2306 + }, + { + "epoch": 0.2, + "learning_rate": 1.8577641015699016e-05, + "loss": 0.4966, + "step": 2307 + }, + { + "epoch": 0.2, + "learning_rate": 1.8576221107618244e-05, + "loss": 0.5216, + "step": 2308 + }, + { + "epoch": 0.2, + "learning_rate": 1.857480054547905e-05, + "loss": 0.5107, + "step": 2309 + }, + { + "epoch": 0.2, + "learning_rate": 1.8573379329389768e-05, + "loss": 0.4932, + "step": 2310 + }, + { + "epoch": 0.2, + "learning_rate": 1.8571957459458785e-05, + "loss": 0.5186, + "step": 2311 + }, + { + "epoch": 0.2, + "learning_rate": 1.8570534935794537e-05, + "loss": 0.5101, + "step": 2312 + }, + { + "epoch": 0.2, + "learning_rate": 1.8569111758505517e-05, + "loss": 0.4876, + "step": 2313 + }, + { + "epoch": 0.2, + "learning_rate": 1.8567687927700255e-05, + "loss": 0.4892, + "step": 2314 + }, + { + "epoch": 0.2, + "learning_rate": 1.8566263443487346e-05, + "loss": 0.4945, + "step": 2315 + }, + { + "epoch": 0.2, + "learning_rate": 1.8564838305975422e-05, + "loss": 0.5027, + "step": 2316 + }, + { + "epoch": 0.2, + "learning_rate": 1.8563412515273173e-05, + "loss": 0.5115, + "step": 2317 + }, + { + "epoch": 0.2, + "learning_rate": 1.8561986071489335e-05, + "loss": 0.5071, + "step": 2318 + }, + { + "epoch": 0.2, + "learning_rate": 1.8560558974732693e-05, + "loss": 0.5034, + "step": 2319 + }, + { + "epoch": 0.2, + "learning_rate": 1.8559131225112085e-05, + "loss": 0.4844, + "step": 2320 + }, + { + "epoch": 0.2, + "learning_rate": 1.85577028227364e-05, + "loss": 0.4914, + "step": 2321 + }, + { + "epoch": 0.2, + "learning_rate": 1.8556273767714563e-05, + "loss": 0.4977, + "step": 2322 + }, + { + "epoch": 0.2, + "learning_rate": 1.855484406015557e-05, + "loss": 0.5028, + "step": 2323 + }, + { + "epoch": 0.2, + "learning_rate": 1.8553413700168456e-05, + "loss": 0.4943, + "step": 2324 + }, + { + "epoch": 0.2, + "learning_rate": 1.85519826878623e-05, + "loss": 0.4963, + "step": 2325 + }, + { + "epoch": 0.2, + "learning_rate": 1.8550551023346245e-05, + "loss": 0.4902, + "step": 2326 + }, + { + "epoch": 0.2, + "learning_rate": 1.854911870672947e-05, + "loss": 0.5031, + "step": 2327 + }, + { + "epoch": 0.2, + "learning_rate": 1.8547685738121205e-05, + "loss": 0.5063, + "step": 2328 + }, + { + "epoch": 0.2, + "learning_rate": 1.8546252117630746e-05, + "loss": 0.4983, + "step": 2329 + }, + { + "epoch": 0.2, + "learning_rate": 1.8544817845367422e-05, + "loss": 0.4992, + "step": 2330 + }, + { + "epoch": 0.2, + "learning_rate": 1.8543382921440614e-05, + "loss": 0.5001, + "step": 2331 + }, + { + "epoch": 0.2, + "learning_rate": 1.8541947345959753e-05, + "loss": 0.5027, + "step": 2332 + }, + { + "epoch": 0.2, + "learning_rate": 1.8540511119034336e-05, + "loss": 0.4926, + "step": 2333 + }, + { + "epoch": 0.2, + "learning_rate": 1.8539074240773875e-05, + "loss": 0.5017, + "step": 2334 + }, + { + "epoch": 0.2, + "learning_rate": 1.8537636711287968e-05, + "loss": 0.5005, + "step": 2335 + }, + { + "epoch": 0.2, + "learning_rate": 1.853619853068624e-05, + "loss": 0.499, + "step": 2336 + }, + { + "epoch": 0.2, + "learning_rate": 1.8534759699078374e-05, + "loss": 0.5384, + "step": 2337 + }, + { + "epoch": 0.2, + "learning_rate": 1.8533320216574103e-05, + "loss": 0.5179, + "step": 2338 + }, + { + "epoch": 0.2, + "learning_rate": 1.8531880083283207e-05, + "loss": 0.5149, + "step": 2339 + }, + { + "epoch": 0.2, + "learning_rate": 1.8530439299315516e-05, + "loss": 0.4896, + "step": 2340 + }, + { + "epoch": 0.2, + "learning_rate": 1.852899786478091e-05, + "loss": 0.5104, + "step": 2341 + }, + { + "epoch": 0.2, + "learning_rate": 1.852755577978932e-05, + "loss": 0.4717, + "step": 2342 + }, + { + "epoch": 0.2, + "learning_rate": 1.8526113044450725e-05, + "loss": 0.5047, + "step": 2343 + }, + { + "epoch": 0.2, + "learning_rate": 1.8524669658875153e-05, + "loss": 0.4973, + "step": 2344 + }, + { + "epoch": 0.2, + "learning_rate": 1.8523225623172684e-05, + "loss": 0.5047, + "step": 2345 + }, + { + "epoch": 0.2, + "learning_rate": 1.8521780937453445e-05, + "loss": 0.5253, + "step": 2346 + }, + { + "epoch": 0.2, + "learning_rate": 1.8520335601827614e-05, + "loss": 0.4828, + "step": 2347 + }, + { + "epoch": 0.2, + "learning_rate": 1.851888961640542e-05, + "loss": 0.4913, + "step": 2348 + }, + { + "epoch": 0.2, + "learning_rate": 1.8517442981297137e-05, + "loss": 0.4896, + "step": 2349 + }, + { + "epoch": 0.2, + "learning_rate": 1.8515995696613096e-05, + "loss": 0.4904, + "step": 2350 + }, + { + "epoch": 0.2, + "learning_rate": 1.8514547762463666e-05, + "loss": 0.5155, + "step": 2351 + }, + { + "epoch": 0.2, + "learning_rate": 1.851309917895928e-05, + "loss": 0.4868, + "step": 2352 + }, + { + "epoch": 0.2, + "learning_rate": 1.8511649946210407e-05, + "loss": 0.4826, + "step": 2353 + }, + { + "epoch": 0.2, + "learning_rate": 1.8510200064327576e-05, + "loss": 0.5064, + "step": 2354 + }, + { + "epoch": 0.2, + "learning_rate": 1.850874953342136e-05, + "loss": 0.5015, + "step": 2355 + }, + { + "epoch": 0.2, + "learning_rate": 1.8507298353602373e-05, + "loss": 0.5003, + "step": 2356 + }, + { + "epoch": 0.2, + "learning_rate": 1.8505846524981304e-05, + "loss": 0.5148, + "step": 2357 + }, + { + "epoch": 0.2, + "learning_rate": 1.850439404766887e-05, + "loss": 0.4877, + "step": 2358 + }, + { + "epoch": 0.2, + "learning_rate": 1.8502940921775837e-05, + "loss": 0.5071, + "step": 2359 + }, + { + "epoch": 0.2, + "learning_rate": 1.8501487147413033e-05, + "loss": 0.5028, + "step": 2360 + }, + { + "epoch": 0.2, + "learning_rate": 1.8500032724691327e-05, + "loss": 0.5081, + "step": 2361 + }, + { + "epoch": 0.2, + "learning_rate": 1.8498577653721638e-05, + "loss": 0.4877, + "step": 2362 + }, + { + "epoch": 0.2, + "learning_rate": 1.8497121934614935e-05, + "loss": 0.4916, + "step": 2363 + }, + { + "epoch": 0.2, + "learning_rate": 1.849566556748224e-05, + "loss": 0.4967, + "step": 2364 + }, + { + "epoch": 0.2, + "learning_rate": 1.849420855243462e-05, + "loss": 0.4912, + "step": 2365 + }, + { + "epoch": 0.2, + "learning_rate": 1.8492750889583193e-05, + "loss": 0.5384, + "step": 2366 + }, + { + "epoch": 0.2, + "learning_rate": 1.8491292579039128e-05, + "loss": 0.5045, + "step": 2367 + }, + { + "epoch": 0.2, + "learning_rate": 1.8489833620913644e-05, + "loss": 0.5018, + "step": 2368 + }, + { + "epoch": 0.2, + "learning_rate": 1.8488374015317994e-05, + "loss": 0.5011, + "step": 2369 + }, + { + "epoch": 0.2, + "learning_rate": 1.8486913762363513e-05, + "loss": 0.4956, + "step": 2370 + }, + { + "epoch": 0.2, + "learning_rate": 1.8485452862161555e-05, + "loss": 0.5081, + "step": 2371 + }, + { + "epoch": 0.2, + "learning_rate": 1.8483991314823535e-05, + "loss": 0.5057, + "step": 2372 + }, + { + "epoch": 0.2, + "learning_rate": 1.848252912046092e-05, + "loss": 0.4943, + "step": 2373 + }, + { + "epoch": 0.2, + "learning_rate": 1.848106627918522e-05, + "loss": 0.4875, + "step": 2374 + }, + { + "epoch": 0.2, + "learning_rate": 1.8479602791107994e-05, + "loss": 0.4837, + "step": 2375 + }, + { + "epoch": 0.2, + "learning_rate": 1.847813865634086e-05, + "loss": 0.5053, + "step": 2376 + }, + { + "epoch": 0.2, + "learning_rate": 1.847667387499548e-05, + "loss": 0.5075, + "step": 2377 + }, + { + "epoch": 0.2, + "learning_rate": 1.8475208447183558e-05, + "loss": 0.508, + "step": 2378 + }, + { + "epoch": 0.2, + "learning_rate": 1.8473742373016858e-05, + "loss": 0.506, + "step": 2379 + }, + { + "epoch": 0.2, + "learning_rate": 1.8472275652607184e-05, + "loss": 0.5065, + "step": 2380 + }, + { + "epoch": 0.2, + "learning_rate": 1.8470808286066402e-05, + "loss": 0.4917, + "step": 2381 + }, + { + "epoch": 0.2, + "learning_rate": 1.846934027350642e-05, + "loss": 0.5121, + "step": 2382 + }, + { + "epoch": 0.2, + "learning_rate": 1.8467871615039182e-05, + "loss": 0.5014, + "step": 2383 + }, + { + "epoch": 0.2, + "learning_rate": 1.846640231077671e-05, + "loss": 0.4826, + "step": 2384 + }, + { + "epoch": 0.2, + "learning_rate": 1.8464932360831046e-05, + "loss": 0.5172, + "step": 2385 + }, + { + "epoch": 0.2, + "learning_rate": 1.8463461765314302e-05, + "loss": 0.5217, + "step": 2386 + }, + { + "epoch": 0.2, + "learning_rate": 1.8461990524338626e-05, + "loss": 0.5019, + "step": 2387 + }, + { + "epoch": 0.2, + "learning_rate": 1.846051863801623e-05, + "loss": 0.4985, + "step": 2388 + }, + { + "epoch": 0.2, + "learning_rate": 1.845904610645936e-05, + "loss": 0.4961, + "step": 2389 + }, + { + "epoch": 0.2, + "learning_rate": 1.8457572929780315e-05, + "loss": 0.5196, + "step": 2390 + }, + { + "epoch": 0.2, + "learning_rate": 1.8456099108091455e-05, + "loss": 0.512, + "step": 2391 + }, + { + "epoch": 0.2, + "learning_rate": 1.845462464150517e-05, + "loss": 0.504, + "step": 2392 + }, + { + "epoch": 0.2, + "learning_rate": 1.8453149530133912e-05, + "loss": 0.4946, + "step": 2393 + }, + { + "epoch": 0.2, + "learning_rate": 1.8451673774090184e-05, + "loss": 0.5097, + "step": 2394 + }, + { + "epoch": 0.2, + "learning_rate": 1.8450197373486527e-05, + "loss": 0.5103, + "step": 2395 + }, + { + "epoch": 0.2, + "learning_rate": 1.8448720328435538e-05, + "loss": 0.5079, + "step": 2396 + }, + { + "epoch": 0.2, + "learning_rate": 1.844724263904987e-05, + "loss": 0.49, + "step": 2397 + }, + { + "epoch": 0.2, + "learning_rate": 1.8445764305442205e-05, + "loss": 0.4892, + "step": 2398 + }, + { + "epoch": 0.2, + "learning_rate": 1.84442853277253e-05, + "loss": 0.4892, + "step": 2399 + }, + { + "epoch": 0.2, + "learning_rate": 1.8442805706011936e-05, + "loss": 0.5174, + "step": 2400 + }, + { + "epoch": 0.2, + "learning_rate": 1.8441325440414965e-05, + "loss": 0.488, + "step": 2401 + }, + { + "epoch": 0.2, + "learning_rate": 1.8439844531047275e-05, + "loss": 0.5001, + "step": 2402 + }, + { + "epoch": 0.2, + "learning_rate": 1.8438362978021804e-05, + "loss": 0.4919, + "step": 2403 + }, + { + "epoch": 0.2, + "learning_rate": 1.8436880781451545e-05, + "loss": 0.4784, + "step": 2404 + }, + { + "epoch": 0.21, + "learning_rate": 1.8435397941449533e-05, + "loss": 0.5088, + "step": 2405 + }, + { + "epoch": 0.21, + "learning_rate": 1.843391445812886e-05, + "loss": 0.503, + "step": 2406 + }, + { + "epoch": 0.21, + "learning_rate": 1.8432430331602654e-05, + "loss": 0.5201, + "step": 2407 + }, + { + "epoch": 0.21, + "learning_rate": 1.8430945561984114e-05, + "loss": 0.5311, + "step": 2408 + }, + { + "epoch": 0.21, + "learning_rate": 1.8429460149386462e-05, + "loss": 0.5133, + "step": 2409 + }, + { + "epoch": 0.21, + "learning_rate": 1.842797409392299e-05, + "loss": 0.4814, + "step": 2410 + }, + { + "epoch": 0.21, + "learning_rate": 1.842648739570703e-05, + "loss": 0.4991, + "step": 2411 + }, + { + "epoch": 0.21, + "learning_rate": 1.8425000054851954e-05, + "loss": 0.5014, + "step": 2412 + }, + { + "epoch": 0.21, + "learning_rate": 1.8423512071471207e-05, + "loss": 0.4861, + "step": 2413 + }, + { + "epoch": 0.21, + "learning_rate": 1.8422023445678258e-05, + "loss": 0.5131, + "step": 2414 + }, + { + "epoch": 0.21, + "learning_rate": 1.842053417758664e-05, + "loss": 0.5099, + "step": 2415 + }, + { + "epoch": 0.21, + "learning_rate": 1.841904426730994e-05, + "loss": 0.5113, + "step": 2416 + }, + { + "epoch": 0.21, + "learning_rate": 1.8417553714961767e-05, + "loss": 0.504, + "step": 2417 + }, + { + "epoch": 0.21, + "learning_rate": 1.8416062520655805e-05, + "loss": 0.5193, + "step": 2418 + }, + { + "epoch": 0.21, + "learning_rate": 1.8414570684505783e-05, + "loss": 0.5098, + "step": 2419 + }, + { + "epoch": 0.21, + "learning_rate": 1.841307820662547e-05, + "loss": 0.4953, + "step": 2420 + }, + { + "epoch": 0.21, + "learning_rate": 1.841158508712869e-05, + "loss": 0.5008, + "step": 2421 + }, + { + "epoch": 0.21, + "learning_rate": 1.841009132612931e-05, + "loss": 0.4836, + "step": 2422 + }, + { + "epoch": 0.21, + "learning_rate": 1.8408596923741258e-05, + "loss": 0.5008, + "step": 2423 + }, + { + "epoch": 0.21, + "learning_rate": 1.84071018800785e-05, + "loss": 0.5356, + "step": 2424 + }, + { + "epoch": 0.21, + "learning_rate": 1.8405606195255052e-05, + "loss": 0.5033, + "step": 2425 + }, + { + "epoch": 0.21, + "learning_rate": 1.8404109869384985e-05, + "loss": 0.4944, + "step": 2426 + }, + { + "epoch": 0.21, + "learning_rate": 1.840261290258241e-05, + "loss": 0.4778, + "step": 2427 + }, + { + "epoch": 0.21, + "learning_rate": 1.84011152949615e-05, + "loss": 0.5047, + "step": 2428 + }, + { + "epoch": 0.21, + "learning_rate": 1.839961704663646e-05, + "loss": 0.5011, + "step": 2429 + }, + { + "epoch": 0.21, + "learning_rate": 1.839811815772156e-05, + "loss": 0.4888, + "step": 2430 + }, + { + "epoch": 0.21, + "learning_rate": 1.8396618628331106e-05, + "loss": 0.5043, + "step": 2431 + }, + { + "epoch": 0.21, + "learning_rate": 1.839511845857946e-05, + "loss": 0.4998, + "step": 2432 + }, + { + "epoch": 0.21, + "learning_rate": 1.8393617648581035e-05, + "loss": 0.4753, + "step": 2433 + }, + { + "epoch": 0.21, + "learning_rate": 1.8392116198450282e-05, + "loss": 0.5063, + "step": 2434 + }, + { + "epoch": 0.21, + "learning_rate": 1.8390614108301715e-05, + "loss": 0.4999, + "step": 2435 + }, + { + "epoch": 0.21, + "learning_rate": 1.8389111378249884e-05, + "loss": 0.4904, + "step": 2436 + }, + { + "epoch": 0.21, + "learning_rate": 1.8387608008409396e-05, + "loss": 0.514, + "step": 2437 + }, + { + "epoch": 0.21, + "learning_rate": 1.8386103998894908e-05, + "loss": 0.4947, + "step": 2438 + }, + { + "epoch": 0.21, + "learning_rate": 1.838459934982111e-05, + "loss": 0.5258, + "step": 2439 + }, + { + "epoch": 0.21, + "learning_rate": 1.8383094061302767e-05, + "loss": 0.476, + "step": 2440 + }, + { + "epoch": 0.21, + "learning_rate": 1.838158813345467e-05, + "loss": 0.4872, + "step": 2441 + }, + { + "epoch": 0.21, + "learning_rate": 1.8380081566391672e-05, + "loss": 0.5008, + "step": 2442 + }, + { + "epoch": 0.21, + "learning_rate": 1.8378574360228668e-05, + "loss": 0.4901, + "step": 2443 + }, + { + "epoch": 0.21, + "learning_rate": 1.8377066515080604e-05, + "loss": 0.4983, + "step": 2444 + }, + { + "epoch": 0.21, + "learning_rate": 1.837555803106247e-05, + "loss": 0.4985, + "step": 2445 + }, + { + "epoch": 0.21, + "learning_rate": 1.8374048908289318e-05, + "loss": 0.5157, + "step": 2446 + }, + { + "epoch": 0.21, + "learning_rate": 1.8372539146876235e-05, + "loss": 0.5111, + "step": 2447 + }, + { + "epoch": 0.21, + "learning_rate": 1.837102874693836e-05, + "loss": 0.4898, + "step": 2448 + }, + { + "epoch": 0.21, + "learning_rate": 1.8369517708590888e-05, + "loss": 0.5008, + "step": 2449 + }, + { + "epoch": 0.21, + "learning_rate": 1.8368006031949054e-05, + "loss": 0.4893, + "step": 2450 + }, + { + "epoch": 0.21, + "learning_rate": 1.836649371712814e-05, + "loss": 0.4908, + "step": 2451 + }, + { + "epoch": 0.21, + "learning_rate": 1.836498076424349e-05, + "loss": 0.4923, + "step": 2452 + }, + { + "epoch": 0.21, + "learning_rate": 1.836346717341048e-05, + "loss": 0.4783, + "step": 2453 + }, + { + "epoch": 0.21, + "learning_rate": 1.8361952944744554e-05, + "loss": 0.5053, + "step": 2454 + }, + { + "epoch": 0.21, + "learning_rate": 1.836043807836118e-05, + "loss": 0.5041, + "step": 2455 + }, + { + "epoch": 0.21, + "learning_rate": 1.83589225743759e-05, + "loss": 0.4935, + "step": 2456 + }, + { + "epoch": 0.21, + "learning_rate": 1.8357406432904283e-05, + "loss": 0.4981, + "step": 2457 + }, + { + "epoch": 0.21, + "learning_rate": 1.835588965406196e-05, + "loss": 0.5098, + "step": 2458 + }, + { + "epoch": 0.21, + "learning_rate": 1.8354372237964608e-05, + "loss": 0.4813, + "step": 2459 + }, + { + "epoch": 0.21, + "learning_rate": 1.8352854184727954e-05, + "loss": 0.5296, + "step": 2460 + }, + { + "epoch": 0.21, + "learning_rate": 1.8351335494467762e-05, + "loss": 0.485, + "step": 2461 + }, + { + "epoch": 0.21, + "learning_rate": 1.834981616729986e-05, + "loss": 0.5007, + "step": 2462 + }, + { + "epoch": 0.21, + "learning_rate": 1.8348296203340123e-05, + "loss": 0.5022, + "step": 2463 + }, + { + "epoch": 0.21, + "learning_rate": 1.8346775602704464e-05, + "loss": 0.5271, + "step": 2464 + }, + { + "epoch": 0.21, + "learning_rate": 1.8345254365508848e-05, + "loss": 0.4861, + "step": 2465 + }, + { + "epoch": 0.21, + "learning_rate": 1.8343732491869294e-05, + "loss": 0.498, + "step": 2466 + }, + { + "epoch": 0.21, + "learning_rate": 1.8342209981901863e-05, + "loss": 0.5248, + "step": 2467 + }, + { + "epoch": 0.21, + "learning_rate": 1.8340686835722676e-05, + "loss": 0.498, + "step": 2468 + }, + { + "epoch": 0.21, + "learning_rate": 1.8339163053447885e-05, + "loss": 0.4975, + "step": 2469 + }, + { + "epoch": 0.21, + "learning_rate": 1.833763863519371e-05, + "loss": 0.4986, + "step": 2470 + }, + { + "epoch": 0.21, + "learning_rate": 1.83361135810764e-05, + "loss": 0.496, + "step": 2471 + }, + { + "epoch": 0.21, + "learning_rate": 1.833458789121227e-05, + "loss": 0.4811, + "step": 2472 + }, + { + "epoch": 0.21, + "learning_rate": 1.8333061565717668e-05, + "loss": 0.4913, + "step": 2473 + }, + { + "epoch": 0.21, + "learning_rate": 1.8331534604709e-05, + "loss": 0.5268, + "step": 2474 + }, + { + "epoch": 0.21, + "learning_rate": 1.8330007008302723e-05, + "loss": 0.4793, + "step": 2475 + }, + { + "epoch": 0.21, + "learning_rate": 1.8328478776615336e-05, + "loss": 0.5083, + "step": 2476 + }, + { + "epoch": 0.21, + "learning_rate": 1.8326949909763384e-05, + "loss": 0.5218, + "step": 2477 + }, + { + "epoch": 0.21, + "learning_rate": 1.832542040786347e-05, + "loss": 0.4874, + "step": 2478 + }, + { + "epoch": 0.21, + "learning_rate": 1.832389027103224e-05, + "loss": 0.4983, + "step": 2479 + }, + { + "epoch": 0.21, + "learning_rate": 1.832235949938638e-05, + "loss": 0.5161, + "step": 2480 + }, + { + "epoch": 0.21, + "learning_rate": 1.8320828093042645e-05, + "loss": 0.4899, + "step": 2481 + }, + { + "epoch": 0.21, + "learning_rate": 1.831929605211782e-05, + "loss": 0.4849, + "step": 2482 + }, + { + "epoch": 0.21, + "learning_rate": 1.8317763376728747e-05, + "loss": 0.4768, + "step": 2483 + }, + { + "epoch": 0.21, + "learning_rate": 1.8316230066992315e-05, + "loss": 0.4802, + "step": 2484 + }, + { + "epoch": 0.21, + "learning_rate": 1.8314696123025456e-05, + "loss": 0.5035, + "step": 2485 + }, + { + "epoch": 0.21, + "learning_rate": 1.8313161544945158e-05, + "loss": 0.5157, + "step": 2486 + }, + { + "epoch": 0.21, + "learning_rate": 1.831162633286845e-05, + "loss": 0.5136, + "step": 2487 + }, + { + "epoch": 0.21, + "learning_rate": 1.8310090486912423e-05, + "loss": 0.498, + "step": 2488 + }, + { + "epoch": 0.21, + "learning_rate": 1.83085540071942e-05, + "loss": 0.5017, + "step": 2489 + }, + { + "epoch": 0.21, + "learning_rate": 1.8307016893830965e-05, + "loss": 0.4953, + "step": 2490 + }, + { + "epoch": 0.21, + "learning_rate": 1.8305479146939937e-05, + "loss": 0.4974, + "step": 2491 + }, + { + "epoch": 0.21, + "learning_rate": 1.8303940766638396e-05, + "loss": 0.499, + "step": 2492 + }, + { + "epoch": 0.21, + "learning_rate": 1.8302401753043666e-05, + "loss": 0.5013, + "step": 2493 + }, + { + "epoch": 0.21, + "learning_rate": 1.8300862106273113e-05, + "loss": 0.4854, + "step": 2494 + }, + { + "epoch": 0.21, + "learning_rate": 1.8299321826444165e-05, + "loss": 0.5106, + "step": 2495 + }, + { + "epoch": 0.21, + "learning_rate": 1.8297780913674286e-05, + "loss": 0.4871, + "step": 2496 + }, + { + "epoch": 0.21, + "learning_rate": 1.829623936808099e-05, + "loss": 0.5011, + "step": 2497 + }, + { + "epoch": 0.21, + "learning_rate": 1.8294697189781843e-05, + "loss": 0.5145, + "step": 2498 + }, + { + "epoch": 0.21, + "learning_rate": 1.829315437889446e-05, + "loss": 0.5021, + "step": 2499 + }, + { + "epoch": 0.21, + "learning_rate": 1.8291610935536503e-05, + "loss": 0.4942, + "step": 2500 + }, + { + "epoch": 0.21, + "learning_rate": 1.8290066859825676e-05, + "loss": 0.4826, + "step": 2501 + }, + { + "epoch": 0.21, + "learning_rate": 1.8288522151879743e-05, + "loss": 0.5087, + "step": 2502 + }, + { + "epoch": 0.21, + "learning_rate": 1.8286976811816506e-05, + "loss": 0.4924, + "step": 2503 + }, + { + "epoch": 0.21, + "learning_rate": 1.828543083975382e-05, + "loss": 0.484, + "step": 2504 + }, + { + "epoch": 0.21, + "learning_rate": 1.8283884235809587e-05, + "loss": 0.4972, + "step": 2505 + }, + { + "epoch": 0.21, + "learning_rate": 1.8282337000101763e-05, + "loss": 0.5248, + "step": 2506 + }, + { + "epoch": 0.21, + "learning_rate": 1.8280789132748334e-05, + "loss": 0.4988, + "step": 2507 + }, + { + "epoch": 0.21, + "learning_rate": 1.8279240633867357e-05, + "loss": 0.4896, + "step": 2508 + }, + { + "epoch": 0.21, + "learning_rate": 1.8277691503576928e-05, + "loss": 0.4911, + "step": 2509 + }, + { + "epoch": 0.21, + "learning_rate": 1.8276141741995185e-05, + "loss": 0.4891, + "step": 2510 + }, + { + "epoch": 0.21, + "learning_rate": 1.8274591349240322e-05, + "loss": 0.5065, + "step": 2511 + }, + { + "epoch": 0.21, + "learning_rate": 1.8273040325430575e-05, + "loss": 0.4928, + "step": 2512 + }, + { + "epoch": 0.21, + "learning_rate": 1.8271488670684235e-05, + "loss": 0.4933, + "step": 2513 + }, + { + "epoch": 0.21, + "learning_rate": 1.8269936385119634e-05, + "loss": 0.4939, + "step": 2514 + }, + { + "epoch": 0.21, + "learning_rate": 1.826838346885516e-05, + "loss": 0.491, + "step": 2515 + }, + { + "epoch": 0.21, + "learning_rate": 1.8266829922009246e-05, + "loss": 0.4949, + "step": 2516 + }, + { + "epoch": 0.21, + "learning_rate": 1.8265275744700367e-05, + "loss": 0.4984, + "step": 2517 + }, + { + "epoch": 0.21, + "learning_rate": 1.826372093704705e-05, + "loss": 0.5044, + "step": 2518 + }, + { + "epoch": 0.21, + "learning_rate": 1.826216549916788e-05, + "loss": 0.487, + "step": 2519 + }, + { + "epoch": 0.21, + "learning_rate": 1.8260609431181472e-05, + "loss": 0.5158, + "step": 2520 + }, + { + "epoch": 0.21, + "learning_rate": 1.8259052733206503e-05, + "loss": 0.4994, + "step": 2521 + }, + { + "epoch": 0.22, + "learning_rate": 1.825749540536169e-05, + "loss": 0.4946, + "step": 2522 + }, + { + "epoch": 0.22, + "learning_rate": 1.8255937447765804e-05, + "loss": 0.4811, + "step": 2523 + }, + { + "epoch": 0.22, + "learning_rate": 1.8254378860537664e-05, + "loss": 0.4923, + "step": 2524 + }, + { + "epoch": 0.22, + "learning_rate": 1.825281964379613e-05, + "loss": 0.4797, + "step": 2525 + }, + { + "epoch": 0.22, + "learning_rate": 1.8251259797660112e-05, + "loss": 0.4966, + "step": 2526 + }, + { + "epoch": 0.22, + "learning_rate": 1.824969932224858e-05, + "loss": 0.5103, + "step": 2527 + }, + { + "epoch": 0.22, + "learning_rate": 1.824813821768053e-05, + "loss": 0.4775, + "step": 2528 + }, + { + "epoch": 0.22, + "learning_rate": 1.8246576484075027e-05, + "loss": 0.4906, + "step": 2529 + }, + { + "epoch": 0.22, + "learning_rate": 1.8245014121551173e-05, + "loss": 0.4816, + "step": 2530 + }, + { + "epoch": 0.22, + "learning_rate": 1.824345113022812e-05, + "loss": 0.501, + "step": 2531 + }, + { + "epoch": 0.22, + "learning_rate": 1.8241887510225068e-05, + "loss": 0.5113, + "step": 2532 + }, + { + "epoch": 0.22, + "learning_rate": 1.8240323261661266e-05, + "loss": 0.4829, + "step": 2533 + }, + { + "epoch": 0.22, + "learning_rate": 1.823875838465601e-05, + "loss": 0.4826, + "step": 2534 + }, + { + "epoch": 0.22, + "learning_rate": 1.8237192879328643e-05, + "loss": 0.4878, + "step": 2535 + }, + { + "epoch": 0.22, + "learning_rate": 1.823562674579856e-05, + "loss": 0.5107, + "step": 2536 + }, + { + "epoch": 0.22, + "learning_rate": 1.8234059984185196e-05, + "loss": 0.4894, + "step": 2537 + }, + { + "epoch": 0.22, + "learning_rate": 1.8232492594608042e-05, + "loss": 0.497, + "step": 2538 + }, + { + "epoch": 0.22, + "learning_rate": 1.8230924577186635e-05, + "loss": 0.5136, + "step": 2539 + }, + { + "epoch": 0.22, + "learning_rate": 1.8229355932040556e-05, + "loss": 0.499, + "step": 2540 + }, + { + "epoch": 0.22, + "learning_rate": 1.8227786659289436e-05, + "loss": 0.5103, + "step": 2541 + }, + { + "epoch": 0.22, + "learning_rate": 1.822621675905296e-05, + "loss": 0.4971, + "step": 2542 + }, + { + "epoch": 0.22, + "learning_rate": 1.8224646231450842e-05, + "loss": 0.4991, + "step": 2543 + }, + { + "epoch": 0.22, + "learning_rate": 1.822307507660287e-05, + "loss": 0.4924, + "step": 2544 + }, + { + "epoch": 0.22, + "learning_rate": 1.822150329462886e-05, + "loss": 0.4993, + "step": 2545 + }, + { + "epoch": 0.22, + "learning_rate": 1.8219930885648688e-05, + "loss": 0.5004, + "step": 2546 + }, + { + "epoch": 0.22, + "learning_rate": 1.821835784978227e-05, + "loss": 0.4848, + "step": 2547 + }, + { + "epoch": 0.22, + "learning_rate": 1.821678418714957e-05, + "loss": 0.5039, + "step": 2548 + }, + { + "epoch": 0.22, + "learning_rate": 1.8215209897870604e-05, + "loss": 0.5127, + "step": 2549 + }, + { + "epoch": 0.22, + "learning_rate": 1.8213634982065436e-05, + "loss": 0.4904, + "step": 2550 + }, + { + "epoch": 0.22, + "learning_rate": 1.821205943985417e-05, + "loss": 0.4989, + "step": 2551 + }, + { + "epoch": 0.22, + "learning_rate": 1.821048327135697e-05, + "loss": 0.4969, + "step": 2552 + }, + { + "epoch": 0.22, + "learning_rate": 1.8208906476694036e-05, + "loss": 0.48, + "step": 2553 + }, + { + "epoch": 0.22, + "learning_rate": 1.8207329055985622e-05, + "loss": 0.4891, + "step": 2554 + }, + { + "epoch": 0.22, + "learning_rate": 1.8205751009352034e-05, + "loss": 0.4979, + "step": 2555 + }, + { + "epoch": 0.22, + "learning_rate": 1.820417233691361e-05, + "loss": 0.4867, + "step": 2556 + }, + { + "epoch": 0.22, + "learning_rate": 1.8202593038790753e-05, + "loss": 0.4934, + "step": 2557 + }, + { + "epoch": 0.22, + "learning_rate": 1.820101311510391e-05, + "loss": 0.4995, + "step": 2558 + }, + { + "epoch": 0.22, + "learning_rate": 1.8199432565973566e-05, + "loss": 0.511, + "step": 2559 + }, + { + "epoch": 0.22, + "learning_rate": 1.8197851391520265e-05, + "loss": 0.4825, + "step": 2560 + }, + { + "epoch": 0.22, + "learning_rate": 1.8196269591864593e-05, + "loss": 0.5169, + "step": 2561 + }, + { + "epoch": 0.22, + "learning_rate": 1.8194687167127178e-05, + "loss": 0.5341, + "step": 2562 + }, + { + "epoch": 0.22, + "learning_rate": 1.8193104117428712e-05, + "loss": 0.4851, + "step": 2563 + }, + { + "epoch": 0.22, + "learning_rate": 1.819152044288992e-05, + "loss": 0.5096, + "step": 2564 + }, + { + "epoch": 0.22, + "learning_rate": 1.818993614363158e-05, + "loss": 0.4894, + "step": 2565 + }, + { + "epoch": 0.22, + "learning_rate": 1.818835121977452e-05, + "loss": 0.4903, + "step": 2566 + }, + { + "epoch": 0.22, + "learning_rate": 1.8186765671439606e-05, + "loss": 0.4943, + "step": 2567 + }, + { + "epoch": 0.22, + "learning_rate": 1.8185179498747767e-05, + "loss": 0.5053, + "step": 2568 + }, + { + "epoch": 0.22, + "learning_rate": 1.8183592701819965e-05, + "loss": 0.4878, + "step": 2569 + }, + { + "epoch": 0.22, + "learning_rate": 1.818200528077722e-05, + "loss": 0.4963, + "step": 2570 + }, + { + "epoch": 0.22, + "learning_rate": 1.8180417235740592e-05, + "loss": 0.5033, + "step": 2571 + }, + { + "epoch": 0.22, + "learning_rate": 1.8178828566831192e-05, + "loss": 0.501, + "step": 2572 + }, + { + "epoch": 0.22, + "learning_rate": 1.8177239274170185e-05, + "loss": 0.4886, + "step": 2573 + }, + { + "epoch": 0.22, + "learning_rate": 1.8175649357878766e-05, + "loss": 0.4815, + "step": 2574 + }, + { + "epoch": 0.22, + "learning_rate": 1.81740588180782e-05, + "loss": 0.4756, + "step": 2575 + }, + { + "epoch": 0.22, + "learning_rate": 1.817246765488978e-05, + "loss": 0.5031, + "step": 2576 + }, + { + "epoch": 0.22, + "learning_rate": 1.817087586843486e-05, + "loss": 0.4899, + "step": 2577 + }, + { + "epoch": 0.22, + "learning_rate": 1.816928345883483e-05, + "loss": 0.5092, + "step": 2578 + }, + { + "epoch": 0.22, + "learning_rate": 1.816769042621114e-05, + "loss": 0.4892, + "step": 2579 + }, + { + "epoch": 0.22, + "learning_rate": 1.8166096770685278e-05, + "loss": 0.5079, + "step": 2580 + }, + { + "epoch": 0.22, + "learning_rate": 1.8164502492378783e-05, + "loss": 0.5079, + "step": 2581 + }, + { + "epoch": 0.22, + "learning_rate": 1.8162907591413245e-05, + "loss": 0.51, + "step": 2582 + }, + { + "epoch": 0.22, + "learning_rate": 1.8161312067910292e-05, + "loss": 0.4946, + "step": 2583 + }, + { + "epoch": 0.22, + "learning_rate": 1.8159715921991612e-05, + "loss": 0.5401, + "step": 2584 + }, + { + "epoch": 0.22, + "learning_rate": 1.8158119153778927e-05, + "loss": 0.5024, + "step": 2585 + }, + { + "epoch": 0.22, + "learning_rate": 1.8156521763394016e-05, + "loss": 0.4958, + "step": 2586 + }, + { + "epoch": 0.22, + "learning_rate": 1.8154923750958704e-05, + "loss": 0.5058, + "step": 2587 + }, + { + "epoch": 0.22, + "learning_rate": 1.815332511659486e-05, + "loss": 0.4999, + "step": 2588 + }, + { + "epoch": 0.22, + "learning_rate": 1.8151725860424405e-05, + "loss": 0.5065, + "step": 2589 + }, + { + "epoch": 0.22, + "learning_rate": 1.8150125982569304e-05, + "loss": 0.4886, + "step": 2590 + }, + { + "epoch": 0.22, + "learning_rate": 1.814852548315157e-05, + "loss": 0.5025, + "step": 2591 + }, + { + "epoch": 0.22, + "learning_rate": 1.814692436229326e-05, + "loss": 0.4907, + "step": 2592 + }, + { + "epoch": 0.22, + "learning_rate": 1.814532262011649e-05, + "loss": 0.5077, + "step": 2593 + }, + { + "epoch": 0.22, + "learning_rate": 1.814372025674341e-05, + "loss": 0.5192, + "step": 2594 + }, + { + "epoch": 0.22, + "learning_rate": 1.8142117272296224e-05, + "loss": 0.5092, + "step": 2595 + }, + { + "epoch": 0.22, + "learning_rate": 1.814051366689718e-05, + "loss": 0.4969, + "step": 2596 + }, + { + "epoch": 0.22, + "learning_rate": 1.813890944066858e-05, + "loss": 0.5128, + "step": 2597 + }, + { + "epoch": 0.22, + "learning_rate": 1.8137304593732767e-05, + "loss": 0.4906, + "step": 2598 + }, + { + "epoch": 0.22, + "learning_rate": 1.8135699126212135e-05, + "loss": 0.5012, + "step": 2599 + }, + { + "epoch": 0.22, + "learning_rate": 1.8134093038229118e-05, + "loss": 0.5157, + "step": 2600 + }, + { + "epoch": 0.22, + "learning_rate": 1.8132486329906212e-05, + "loss": 0.5043, + "step": 2601 + }, + { + "epoch": 0.22, + "learning_rate": 1.8130879001365944e-05, + "loss": 0.4719, + "step": 2602 + }, + { + "epoch": 0.22, + "learning_rate": 1.8129271052730898e-05, + "loss": 0.4954, + "step": 2603 + }, + { + "epoch": 0.22, + "learning_rate": 1.8127662484123702e-05, + "loss": 0.4978, + "step": 2604 + }, + { + "epoch": 0.22, + "learning_rate": 1.8126053295667036e-05, + "loss": 0.4984, + "step": 2605 + }, + { + "epoch": 0.22, + "learning_rate": 1.812444348748362e-05, + "loss": 0.4923, + "step": 2606 + }, + { + "epoch": 0.22, + "learning_rate": 1.812283305969622e-05, + "loss": 0.5324, + "step": 2607 + }, + { + "epoch": 0.22, + "learning_rate": 1.8121222012427666e-05, + "loss": 0.4937, + "step": 2608 + }, + { + "epoch": 0.22, + "learning_rate": 1.811961034580081e-05, + "loss": 0.5119, + "step": 2609 + }, + { + "epoch": 0.22, + "learning_rate": 1.8117998059938575e-05, + "loss": 0.5162, + "step": 2610 + }, + { + "epoch": 0.22, + "learning_rate": 1.8116385154963913e-05, + "loss": 0.4701, + "step": 2611 + }, + { + "epoch": 0.22, + "learning_rate": 1.811477163099984e-05, + "loss": 0.5327, + "step": 2612 + }, + { + "epoch": 0.22, + "learning_rate": 1.8113157488169398e-05, + "loss": 0.5036, + "step": 2613 + }, + { + "epoch": 0.22, + "learning_rate": 1.81115427265957e-05, + "loss": 0.499, + "step": 2614 + }, + { + "epoch": 0.22, + "learning_rate": 1.8109927346401884e-05, + "loss": 0.4844, + "step": 2615 + }, + { + "epoch": 0.22, + "learning_rate": 1.8108311347711152e-05, + "loss": 0.4729, + "step": 2616 + }, + { + "epoch": 0.22, + "learning_rate": 1.8106694730646745e-05, + "loss": 0.4967, + "step": 2617 + }, + { + "epoch": 0.22, + "learning_rate": 1.8105077495331956e-05, + "loss": 0.4931, + "step": 2618 + }, + { + "epoch": 0.22, + "learning_rate": 1.8103459641890117e-05, + "loss": 0.5043, + "step": 2619 + }, + { + "epoch": 0.22, + "learning_rate": 1.8101841170444617e-05, + "loss": 0.5012, + "step": 2620 + }, + { + "epoch": 0.22, + "learning_rate": 1.8100222081118882e-05, + "loss": 0.5017, + "step": 2621 + }, + { + "epoch": 0.22, + "learning_rate": 1.8098602374036395e-05, + "loss": 0.527, + "step": 2622 + }, + { + "epoch": 0.22, + "learning_rate": 1.8096982049320683e-05, + "loss": 0.5048, + "step": 2623 + }, + { + "epoch": 0.22, + "learning_rate": 1.809536110709531e-05, + "loss": 0.5079, + "step": 2624 + }, + { + "epoch": 0.22, + "learning_rate": 1.809373954748391e-05, + "loss": 0.4918, + "step": 2625 + }, + { + "epoch": 0.22, + "learning_rate": 1.8092117370610137e-05, + "loss": 0.5065, + "step": 2626 + }, + { + "epoch": 0.22, + "learning_rate": 1.8090494576597712e-05, + "loss": 0.5019, + "step": 2627 + }, + { + "epoch": 0.22, + "learning_rate": 1.808887116557039e-05, + "loss": 0.4903, + "step": 2628 + }, + { + "epoch": 0.22, + "learning_rate": 1.8087247137651985e-05, + "loss": 0.4947, + "step": 2629 + }, + { + "epoch": 0.22, + "learning_rate": 1.8085622492966347e-05, + "loss": 0.5112, + "step": 2630 + }, + { + "epoch": 0.22, + "learning_rate": 1.8083997231637385e-05, + "loss": 0.5013, + "step": 2631 + }, + { + "epoch": 0.22, + "learning_rate": 1.8082371353789046e-05, + "loss": 0.4936, + "step": 2632 + }, + { + "epoch": 0.22, + "learning_rate": 1.8080744859545323e-05, + "loss": 0.4998, + "step": 2633 + }, + { + "epoch": 0.22, + "learning_rate": 1.8079117749030257e-05, + "loss": 0.4843, + "step": 2634 + }, + { + "epoch": 0.22, + "learning_rate": 1.8077490022367948e-05, + "loss": 0.4976, + "step": 2635 + }, + { + "epoch": 0.22, + "learning_rate": 1.8075861679682524e-05, + "loss": 0.51, + "step": 2636 + }, + { + "epoch": 0.22, + "learning_rate": 1.8074232721098174e-05, + "loss": 0.5108, + "step": 2637 + }, + { + "epoch": 0.22, + "learning_rate": 1.8072603146739126e-05, + "loss": 0.5001, + "step": 2638 + }, + { + "epoch": 0.23, + "learning_rate": 1.807097295672966e-05, + "loss": 0.5288, + "step": 2639 + }, + { + "epoch": 0.23, + "learning_rate": 1.8069342151194105e-05, + "loss": 0.5017, + "step": 2640 + }, + { + "epoch": 0.23, + "learning_rate": 1.8067710730256825e-05, + "loss": 0.4916, + "step": 2641 + }, + { + "epoch": 0.23, + "learning_rate": 1.8066078694042245e-05, + "loss": 0.5026, + "step": 2642 + }, + { + "epoch": 0.23, + "learning_rate": 1.806444604267483e-05, + "loss": 0.4967, + "step": 2643 + }, + { + "epoch": 0.23, + "learning_rate": 1.8062812776279085e-05, + "loss": 0.4987, + "step": 2644 + }, + { + "epoch": 0.23, + "learning_rate": 1.806117889497958e-05, + "loss": 0.5114, + "step": 2645 + }, + { + "epoch": 0.23, + "learning_rate": 1.8059544398900923e-05, + "loss": 0.495, + "step": 2646 + }, + { + "epoch": 0.23, + "learning_rate": 1.8057909288167758e-05, + "loss": 0.4907, + "step": 2647 + }, + { + "epoch": 0.23, + "learning_rate": 1.8056273562904793e-05, + "loss": 0.5021, + "step": 2648 + }, + { + "epoch": 0.23, + "learning_rate": 1.805463722323677e-05, + "loss": 0.5091, + "step": 2649 + }, + { + "epoch": 0.23, + "learning_rate": 1.8053000269288486e-05, + "loss": 0.4969, + "step": 2650 + }, + { + "epoch": 0.23, + "learning_rate": 1.8051362701184777e-05, + "loss": 0.4965, + "step": 2651 + }, + { + "epoch": 0.23, + "learning_rate": 1.8049724519050538e-05, + "loss": 0.4959, + "step": 2652 + }, + { + "epoch": 0.23, + "learning_rate": 1.80480857230107e-05, + "loss": 0.5135, + "step": 2653 + }, + { + "epoch": 0.23, + "learning_rate": 1.804644631319025e-05, + "loss": 0.4746, + "step": 2654 + }, + { + "epoch": 0.23, + "learning_rate": 1.8044806289714206e-05, + "loss": 0.5231, + "step": 2655 + }, + { + "epoch": 0.23, + "learning_rate": 1.804316565270765e-05, + "loss": 0.5009, + "step": 2656 + }, + { + "epoch": 0.23, + "learning_rate": 1.8041524402295702e-05, + "loss": 0.4917, + "step": 2657 + }, + { + "epoch": 0.23, + "learning_rate": 1.803988253860353e-05, + "loss": 0.5053, + "step": 2658 + }, + { + "epoch": 0.23, + "learning_rate": 1.8038240061756348e-05, + "loss": 0.5126, + "step": 2659 + }, + { + "epoch": 0.23, + "learning_rate": 1.8036596971879426e-05, + "loss": 0.5039, + "step": 2660 + }, + { + "epoch": 0.23, + "learning_rate": 1.8034953269098062e-05, + "loss": 0.4986, + "step": 2661 + }, + { + "epoch": 0.23, + "learning_rate": 1.8033308953537617e-05, + "loss": 0.501, + "step": 2662 + }, + { + "epoch": 0.23, + "learning_rate": 1.8031664025323497e-05, + "loss": 0.4959, + "step": 2663 + }, + { + "epoch": 0.23, + "learning_rate": 1.8030018484581147e-05, + "loss": 0.485, + "step": 2664 + }, + { + "epoch": 0.23, + "learning_rate": 1.802837233143606e-05, + "loss": 0.5101, + "step": 2665 + }, + { + "epoch": 0.23, + "learning_rate": 1.802672556601378e-05, + "loss": 0.488, + "step": 2666 + }, + { + "epoch": 0.23, + "learning_rate": 1.8025078188439905e-05, + "loss": 0.492, + "step": 2667 + }, + { + "epoch": 0.23, + "learning_rate": 1.8023430198840056e-05, + "loss": 0.4938, + "step": 2668 + }, + { + "epoch": 0.23, + "learning_rate": 1.802178159733993e-05, + "loss": 0.4931, + "step": 2669 + }, + { + "epoch": 0.23, + "learning_rate": 1.8020132384065245e-05, + "loss": 0.5101, + "step": 2670 + }, + { + "epoch": 0.23, + "learning_rate": 1.801848255914178e-05, + "loss": 0.4978, + "step": 2671 + }, + { + "epoch": 0.23, + "learning_rate": 1.801683212269536e-05, + "loss": 0.5024, + "step": 2672 + }, + { + "epoch": 0.23, + "learning_rate": 1.8015181074851856e-05, + "loss": 0.4894, + "step": 2673 + }, + { + "epoch": 0.23, + "learning_rate": 1.801352941573718e-05, + "loss": 0.5065, + "step": 2674 + }, + { + "epoch": 0.23, + "learning_rate": 1.8011877145477292e-05, + "loss": 0.4736, + "step": 2675 + }, + { + "epoch": 0.23, + "learning_rate": 1.8010224264198207e-05, + "loss": 0.5183, + "step": 2676 + }, + { + "epoch": 0.23, + "learning_rate": 1.8008570772025978e-05, + "loss": 0.4873, + "step": 2677 + }, + { + "epoch": 0.23, + "learning_rate": 1.8006916669086706e-05, + "loss": 0.5155, + "step": 2678 + }, + { + "epoch": 0.23, + "learning_rate": 1.800526195550654e-05, + "loss": 0.4921, + "step": 2679 + }, + { + "epoch": 0.23, + "learning_rate": 1.800360663141168e-05, + "loss": 0.48, + "step": 2680 + }, + { + "epoch": 0.23, + "learning_rate": 1.800195069692836e-05, + "loss": 0.4809, + "step": 2681 + }, + { + "epoch": 0.23, + "learning_rate": 1.8000294152182877e-05, + "loss": 0.494, + "step": 2682 + }, + { + "epoch": 0.23, + "learning_rate": 1.799863699730156e-05, + "loss": 0.4965, + "step": 2683 + }, + { + "epoch": 0.23, + "learning_rate": 1.799697923241079e-05, + "loss": 0.4777, + "step": 2684 + }, + { + "epoch": 0.23, + "learning_rate": 1.7995320857637e-05, + "loss": 0.4908, + "step": 2685 + }, + { + "epoch": 0.23, + "learning_rate": 1.799366187310666e-05, + "loss": 0.5068, + "step": 2686 + }, + { + "epoch": 0.23, + "learning_rate": 1.7992002278946295e-05, + "loss": 0.5081, + "step": 2687 + }, + { + "epoch": 0.23, + "learning_rate": 1.799034207528247e-05, + "loss": 0.4866, + "step": 2688 + }, + { + "epoch": 0.23, + "learning_rate": 1.7988681262241798e-05, + "loss": 0.4758, + "step": 2689 + }, + { + "epoch": 0.23, + "learning_rate": 1.7987019839950943e-05, + "loss": 0.4902, + "step": 2690 + }, + { + "epoch": 0.23, + "learning_rate": 1.798535780853661e-05, + "loss": 0.4911, + "step": 2691 + }, + { + "epoch": 0.23, + "learning_rate": 1.7983695168125552e-05, + "loss": 0.501, + "step": 2692 + }, + { + "epoch": 0.23, + "learning_rate": 1.798203191884457e-05, + "loss": 0.5023, + "step": 2693 + }, + { + "epoch": 0.23, + "learning_rate": 1.798036806082051e-05, + "loss": 0.4882, + "step": 2694 + }, + { + "epoch": 0.23, + "learning_rate": 1.7978703594180266e-05, + "loss": 0.5119, + "step": 2695 + }, + { + "epoch": 0.23, + "learning_rate": 1.7977038519050773e-05, + "loss": 0.4859, + "step": 2696 + }, + { + "epoch": 0.23, + "learning_rate": 1.7975372835559023e-05, + "loss": 0.5136, + "step": 2697 + }, + { + "epoch": 0.23, + "learning_rate": 1.797370654383204e-05, + "loss": 0.487, + "step": 2698 + }, + { + "epoch": 0.23, + "learning_rate": 1.797203964399691e-05, + "loss": 0.4911, + "step": 2699 + }, + { + "epoch": 0.23, + "learning_rate": 1.7970372136180753e-05, + "loss": 0.4985, + "step": 2700 + }, + { + "epoch": 0.23, + "learning_rate": 1.796870402051074e-05, + "loss": 0.5132, + "step": 2701 + }, + { + "epoch": 0.23, + "learning_rate": 1.7967035297114094e-05, + "loss": 0.4969, + "step": 2702 + }, + { + "epoch": 0.23, + "learning_rate": 1.7965365966118075e-05, + "loss": 0.4851, + "step": 2703 + }, + { + "epoch": 0.23, + "learning_rate": 1.796369602764999e-05, + "loss": 0.5085, + "step": 2704 + }, + { + "epoch": 0.23, + "learning_rate": 1.7962025481837196e-05, + "loss": 0.4907, + "step": 2705 + }, + { + "epoch": 0.23, + "learning_rate": 1.7960354328807103e-05, + "loss": 0.4809, + "step": 2706 + }, + { + "epoch": 0.23, + "learning_rate": 1.7958682568687152e-05, + "loss": 0.5071, + "step": 2707 + }, + { + "epoch": 0.23, + "learning_rate": 1.7957010201604844e-05, + "loss": 0.5138, + "step": 2708 + }, + { + "epoch": 0.23, + "learning_rate": 1.795533722768772e-05, + "loss": 0.4872, + "step": 2709 + }, + { + "epoch": 0.23, + "learning_rate": 1.7953663647063365e-05, + "loss": 0.5056, + "step": 2710 + }, + { + "epoch": 0.23, + "learning_rate": 1.7951989459859415e-05, + "loss": 0.5084, + "step": 2711 + }, + { + "epoch": 0.23, + "learning_rate": 1.795031466620355e-05, + "loss": 0.479, + "step": 2712 + }, + { + "epoch": 0.23, + "learning_rate": 1.7948639266223495e-05, + "loss": 0.5109, + "step": 2713 + }, + { + "epoch": 0.23, + "learning_rate": 1.7946963260047028e-05, + "loss": 0.4787, + "step": 2714 + }, + { + "epoch": 0.23, + "learning_rate": 1.7945286647801966e-05, + "loss": 0.4938, + "step": 2715 + }, + { + "epoch": 0.23, + "learning_rate": 1.794360942961617e-05, + "loss": 0.5091, + "step": 2716 + }, + { + "epoch": 0.23, + "learning_rate": 1.7941931605617556e-05, + "loss": 0.4926, + "step": 2717 + }, + { + "epoch": 0.23, + "learning_rate": 1.7940253175934083e-05, + "loss": 0.478, + "step": 2718 + }, + { + "epoch": 0.23, + "learning_rate": 1.793857414069375e-05, + "loss": 0.5188, + "step": 2719 + }, + { + "epoch": 0.23, + "learning_rate": 1.7936894500024614e-05, + "loss": 0.4989, + "step": 2720 + }, + { + "epoch": 0.23, + "learning_rate": 1.793521425405477e-05, + "loss": 0.4922, + "step": 2721 + }, + { + "epoch": 0.23, + "learning_rate": 1.7933533402912354e-05, + "loss": 0.5052, + "step": 2722 + }, + { + "epoch": 0.23, + "learning_rate": 1.7931851946725557e-05, + "loss": 0.514, + "step": 2723 + }, + { + "epoch": 0.23, + "learning_rate": 1.793016988562262e-05, + "loss": 0.4976, + "step": 2724 + }, + { + "epoch": 0.23, + "learning_rate": 1.792848721973182e-05, + "loss": 0.491, + "step": 2725 + }, + { + "epoch": 0.23, + "learning_rate": 1.7926803949181483e-05, + "loss": 0.4946, + "step": 2726 + }, + { + "epoch": 0.23, + "learning_rate": 1.7925120074099987e-05, + "loss": 0.5123, + "step": 2727 + }, + { + "epoch": 0.23, + "learning_rate": 1.7923435594615744e-05, + "loss": 0.4782, + "step": 2728 + }, + { + "epoch": 0.23, + "learning_rate": 1.7921750510857224e-05, + "loss": 0.5085, + "step": 2729 + }, + { + "epoch": 0.23, + "learning_rate": 1.792006482295294e-05, + "loss": 0.4957, + "step": 2730 + }, + { + "epoch": 0.23, + "learning_rate": 1.7918378531031444e-05, + "loss": 0.4946, + "step": 2731 + }, + { + "epoch": 0.23, + "learning_rate": 1.7916691635221343e-05, + "loss": 0.4981, + "step": 2732 + }, + { + "epoch": 0.23, + "learning_rate": 1.791500413565129e-05, + "loss": 0.4858, + "step": 2733 + }, + { + "epoch": 0.23, + "learning_rate": 1.7913316032449975e-05, + "loss": 0.4865, + "step": 2734 + }, + { + "epoch": 0.23, + "learning_rate": 1.791162732574614e-05, + "loss": 0.4774, + "step": 2735 + }, + { + "epoch": 0.23, + "learning_rate": 1.790993801566858e-05, + "loss": 0.5164, + "step": 2736 + }, + { + "epoch": 0.23, + "learning_rate": 1.790824810234612e-05, + "loss": 0.5118, + "step": 2737 + }, + { + "epoch": 0.23, + "learning_rate": 1.7906557585907646e-05, + "loss": 0.4989, + "step": 2738 + }, + { + "epoch": 0.23, + "learning_rate": 1.790486646648208e-05, + "loss": 0.4948, + "step": 2739 + }, + { + "epoch": 0.23, + "learning_rate": 1.7903174744198398e-05, + "loss": 0.5171, + "step": 2740 + }, + { + "epoch": 0.23, + "learning_rate": 1.7901482419185613e-05, + "loss": 0.4836, + "step": 2741 + }, + { + "epoch": 0.23, + "learning_rate": 1.7899789491572794e-05, + "loss": 0.4912, + "step": 2742 + }, + { + "epoch": 0.23, + "learning_rate": 1.7898095961489047e-05, + "loss": 0.5097, + "step": 2743 + }, + { + "epoch": 0.23, + "learning_rate": 1.7896401829063522e-05, + "loss": 0.4912, + "step": 2744 + }, + { + "epoch": 0.23, + "learning_rate": 1.7894707094425433e-05, + "loss": 0.5051, + "step": 2745 + }, + { + "epoch": 0.23, + "learning_rate": 1.7893011757704022e-05, + "loss": 0.4938, + "step": 2746 + }, + { + "epoch": 0.23, + "learning_rate": 1.789131581902858e-05, + "loss": 0.497, + "step": 2747 + }, + { + "epoch": 0.23, + "learning_rate": 1.788961927852845e-05, + "loss": 0.494, + "step": 2748 + }, + { + "epoch": 0.23, + "learning_rate": 1.7887922136333015e-05, + "loss": 0.4936, + "step": 2749 + }, + { + "epoch": 0.23, + "learning_rate": 1.7886224392571704e-05, + "loss": 0.4983, + "step": 2750 + }, + { + "epoch": 0.23, + "learning_rate": 1.7884526047374e-05, + "loss": 0.4887, + "step": 2751 + }, + { + "epoch": 0.23, + "learning_rate": 1.788282710086942e-05, + "loss": 0.507, + "step": 2752 + }, + { + "epoch": 0.23, + "learning_rate": 1.788112755318754e-05, + "loss": 0.5003, + "step": 2753 + }, + { + "epoch": 0.23, + "learning_rate": 1.7879427404457965e-05, + "loss": 0.492, + "step": 2754 + }, + { + "epoch": 0.23, + "learning_rate": 1.7877726654810364e-05, + "loss": 0.4927, + "step": 2755 + }, + { + "epoch": 0.23, + "learning_rate": 1.787602530437444e-05, + "loss": 0.5, + "step": 2756 + }, + { + "epoch": 0.24, + "learning_rate": 1.7874323353279945e-05, + "loss": 0.4836, + "step": 2757 + }, + { + "epoch": 0.24, + "learning_rate": 1.7872620801656674e-05, + "loss": 0.497, + "step": 2758 + }, + { + "epoch": 0.24, + "learning_rate": 1.7870917649634475e-05, + "loss": 0.5026, + "step": 2759 + }, + { + "epoch": 0.24, + "learning_rate": 1.7869213897343235e-05, + "loss": 0.5123, + "step": 2760 + }, + { + "epoch": 0.24, + "learning_rate": 1.7867509544912893e-05, + "loss": 0.5105, + "step": 2761 + }, + { + "epoch": 0.24, + "learning_rate": 1.7865804592473423e-05, + "loss": 0.5003, + "step": 2762 + }, + { + "epoch": 0.24, + "learning_rate": 1.786409904015486e-05, + "loss": 0.4912, + "step": 2763 + }, + { + "epoch": 0.24, + "learning_rate": 1.786239288808727e-05, + "loss": 0.5068, + "step": 2764 + }, + { + "epoch": 0.24, + "learning_rate": 1.7860686136400773e-05, + "loss": 0.4965, + "step": 2765 + }, + { + "epoch": 0.24, + "learning_rate": 1.7858978785225535e-05, + "loss": 0.5048, + "step": 2766 + }, + { + "epoch": 0.24, + "learning_rate": 1.7857270834691766e-05, + "loss": 0.4829, + "step": 2767 + }, + { + "epoch": 0.24, + "learning_rate": 1.785556228492972e-05, + "loss": 0.5034, + "step": 2768 + }, + { + "epoch": 0.24, + "learning_rate": 1.7853853136069697e-05, + "loss": 0.4914, + "step": 2769 + }, + { + "epoch": 0.24, + "learning_rate": 1.7852143388242046e-05, + "loss": 0.4989, + "step": 2770 + }, + { + "epoch": 0.24, + "learning_rate": 1.785043304157716e-05, + "loss": 0.501, + "step": 2771 + }, + { + "epoch": 0.24, + "learning_rate": 1.784872209620547e-05, + "loss": 0.4953, + "step": 2772 + }, + { + "epoch": 0.24, + "learning_rate": 1.784701055225747e-05, + "loss": 0.5186, + "step": 2773 + }, + { + "epoch": 0.24, + "learning_rate": 1.7845298409863683e-05, + "loss": 0.4717, + "step": 2774 + }, + { + "epoch": 0.24, + "learning_rate": 1.7843585669154685e-05, + "loss": 0.5163, + "step": 2775 + }, + { + "epoch": 0.24, + "learning_rate": 1.7841872330261103e-05, + "loss": 0.4986, + "step": 2776 + }, + { + "epoch": 0.24, + "learning_rate": 1.7840158393313594e-05, + "loss": 0.4864, + "step": 2777 + }, + { + "epoch": 0.24, + "learning_rate": 1.7838443858442877e-05, + "loss": 0.4913, + "step": 2778 + }, + { + "epoch": 0.24, + "learning_rate": 1.7836728725779705e-05, + "loss": 0.5062, + "step": 2779 + }, + { + "epoch": 0.24, + "learning_rate": 1.7835012995454882e-05, + "loss": 0.5083, + "step": 2780 + }, + { + "epoch": 0.24, + "learning_rate": 1.783329666759926e-05, + "loss": 0.5094, + "step": 2781 + }, + { + "epoch": 0.24, + "learning_rate": 1.783157974234373e-05, + "loss": 0.5117, + "step": 2782 + }, + { + "epoch": 0.24, + "learning_rate": 1.7829862219819235e-05, + "loss": 0.4651, + "step": 2783 + }, + { + "epoch": 0.24, + "learning_rate": 1.7828144100156754e-05, + "loss": 0.489, + "step": 2784 + }, + { + "epoch": 0.24, + "learning_rate": 1.7826425383487327e-05, + "loss": 0.4887, + "step": 2785 + }, + { + "epoch": 0.24, + "learning_rate": 1.7824706069942023e-05, + "loss": 0.4891, + "step": 2786 + }, + { + "epoch": 0.24, + "learning_rate": 1.782298615965197e-05, + "loss": 0.4961, + "step": 2787 + }, + { + "epoch": 0.24, + "learning_rate": 1.782126565274833e-05, + "loss": 0.4913, + "step": 2788 + }, + { + "epoch": 0.24, + "learning_rate": 1.7819544549362318e-05, + "loss": 0.4979, + "step": 2789 + }, + { + "epoch": 0.24, + "learning_rate": 1.7817822849625194e-05, + "loss": 0.4795, + "step": 2790 + }, + { + "epoch": 0.24, + "learning_rate": 1.781610055366826e-05, + "loss": 0.4804, + "step": 2791 + }, + { + "epoch": 0.24, + "learning_rate": 1.7814377661622867e-05, + "loss": 0.5145, + "step": 2792 + }, + { + "epoch": 0.24, + "learning_rate": 1.781265417362041e-05, + "loss": 0.4958, + "step": 2793 + }, + { + "epoch": 0.24, + "learning_rate": 1.7810930089792328e-05, + "loss": 0.4971, + "step": 2794 + }, + { + "epoch": 0.24, + "learning_rate": 1.780920541027011e-05, + "loss": 0.4791, + "step": 2795 + }, + { + "epoch": 0.24, + "learning_rate": 1.7807480135185283e-05, + "loss": 0.5015, + "step": 2796 + }, + { + "epoch": 0.24, + "learning_rate": 1.7805754264669426e-05, + "loss": 0.4876, + "step": 2797 + }, + { + "epoch": 0.24, + "learning_rate": 1.7804027798854165e-05, + "loss": 0.5028, + "step": 2798 + }, + { + "epoch": 0.24, + "learning_rate": 1.7802300737871157e-05, + "loss": 0.5031, + "step": 2799 + }, + { + "epoch": 0.24, + "learning_rate": 1.7800573081852124e-05, + "loss": 0.4789, + "step": 2800 + }, + { + "epoch": 0.24, + "learning_rate": 1.7798844830928818e-05, + "loss": 0.5082, + "step": 2801 + }, + { + "epoch": 0.24, + "learning_rate": 1.779711598523305e-05, + "loss": 0.4887, + "step": 2802 + }, + { + "epoch": 0.24, + "learning_rate": 1.779538654489666e-05, + "loss": 0.4828, + "step": 2803 + }, + { + "epoch": 0.24, + "learning_rate": 1.7793656510051557e-05, + "loss": 0.4924, + "step": 2804 + }, + { + "epoch": 0.24, + "learning_rate": 1.779192588082966e-05, + "loss": 0.5018, + "step": 2805 + }, + { + "epoch": 0.24, + "learning_rate": 1.7790194657362973e-05, + "loss": 0.49, + "step": 2806 + }, + { + "epoch": 0.24, + "learning_rate": 1.7788462839783514e-05, + "loss": 0.497, + "step": 2807 + }, + { + "epoch": 0.24, + "learning_rate": 1.7786730428223364e-05, + "loss": 0.5019, + "step": 2808 + }, + { + "epoch": 0.24, + "learning_rate": 1.7784997422814644e-05, + "loss": 0.4979, + "step": 2809 + }, + { + "epoch": 0.24, + "learning_rate": 1.778326382368952e-05, + "loss": 0.4985, + "step": 2810 + }, + { + "epoch": 0.24, + "learning_rate": 1.77815296309802e-05, + "loss": 0.4994, + "step": 2811 + }, + { + "epoch": 0.24, + "learning_rate": 1.7779794844818944e-05, + "loss": 0.5063, + "step": 2812 + }, + { + "epoch": 0.24, + "learning_rate": 1.7778059465338054e-05, + "loss": 0.49, + "step": 2813 + }, + { + "epoch": 0.24, + "learning_rate": 1.7776323492669877e-05, + "loss": 0.4971, + "step": 2814 + }, + { + "epoch": 0.24, + "learning_rate": 1.7774586926946805e-05, + "loss": 0.5009, + "step": 2815 + }, + { + "epoch": 0.24, + "learning_rate": 1.7772849768301273e-05, + "loss": 0.507, + "step": 2816 + }, + { + "epoch": 0.24, + "learning_rate": 1.7771112016865774e-05, + "loss": 0.4961, + "step": 2817 + }, + { + "epoch": 0.24, + "learning_rate": 1.7769373672772824e-05, + "loss": 0.5006, + "step": 2818 + }, + { + "epoch": 0.24, + "learning_rate": 1.7767634736155e-05, + "loss": 0.4821, + "step": 2819 + }, + { + "epoch": 0.24, + "learning_rate": 1.7765895207144928e-05, + "loss": 0.4697, + "step": 2820 + }, + { + "epoch": 0.24, + "learning_rate": 1.7764155085875262e-05, + "loss": 0.5086, + "step": 2821 + }, + { + "epoch": 0.24, + "learning_rate": 1.7762414372478716e-05, + "loss": 0.4969, + "step": 2822 + }, + { + "epoch": 0.24, + "learning_rate": 1.7760673067088042e-05, + "loss": 0.507, + "step": 2823 + }, + { + "epoch": 0.24, + "learning_rate": 1.775893116983604e-05, + "loss": 0.5063, + "step": 2824 + }, + { + "epoch": 0.24, + "learning_rate": 1.7757188680855556e-05, + "loss": 0.4905, + "step": 2825 + }, + { + "epoch": 0.24, + "learning_rate": 1.7755445600279476e-05, + "loss": 0.4887, + "step": 2826 + }, + { + "epoch": 0.24, + "learning_rate": 1.7753701928240735e-05, + "loss": 0.4723, + "step": 2827 + }, + { + "epoch": 0.24, + "learning_rate": 1.7751957664872316e-05, + "loss": 0.5225, + "step": 2828 + }, + { + "epoch": 0.24, + "learning_rate": 1.7750212810307243e-05, + "loss": 0.4877, + "step": 2829 + }, + { + "epoch": 0.24, + "learning_rate": 1.7748467364678585e-05, + "loss": 0.4995, + "step": 2830 + }, + { + "epoch": 0.24, + "learning_rate": 1.7746721328119457e-05, + "loss": 0.4931, + "step": 2831 + }, + { + "epoch": 0.24, + "learning_rate": 1.7744974700763018e-05, + "loss": 0.4803, + "step": 2832 + }, + { + "epoch": 0.24, + "learning_rate": 1.7743227482742475e-05, + "loss": 0.4933, + "step": 2833 + }, + { + "epoch": 0.24, + "learning_rate": 1.7741479674191075e-05, + "loss": 0.4879, + "step": 2834 + }, + { + "epoch": 0.24, + "learning_rate": 1.7739731275242117e-05, + "loss": 0.488, + "step": 2835 + }, + { + "epoch": 0.24, + "learning_rate": 1.7737982286028938e-05, + "loss": 0.4907, + "step": 2836 + }, + { + "epoch": 0.24, + "learning_rate": 1.773623270668493e-05, + "loss": 0.5206, + "step": 2837 + }, + { + "epoch": 0.24, + "learning_rate": 1.773448253734351e-05, + "loss": 0.5103, + "step": 2838 + }, + { + "epoch": 0.24, + "learning_rate": 1.773273177813817e-05, + "loss": 0.5068, + "step": 2839 + }, + { + "epoch": 0.24, + "learning_rate": 1.7730980429202415e-05, + "loss": 0.4993, + "step": 2840 + }, + { + "epoch": 0.24, + "learning_rate": 1.7729228490669818e-05, + "loss": 0.5001, + "step": 2841 + }, + { + "epoch": 0.24, + "learning_rate": 1.7727475962673986e-05, + "loss": 0.4989, + "step": 2842 + }, + { + "epoch": 0.24, + "learning_rate": 1.7725722845348577e-05, + "loss": 0.5169, + "step": 2843 + }, + { + "epoch": 0.24, + "learning_rate": 1.7723969138827294e-05, + "loss": 0.5081, + "step": 2844 + }, + { + "epoch": 0.24, + "learning_rate": 1.7722214843243874e-05, + "loss": 0.494, + "step": 2845 + }, + { + "epoch": 0.24, + "learning_rate": 1.772045995873211e-05, + "loss": 0.4921, + "step": 2846 + }, + { + "epoch": 0.24, + "learning_rate": 1.771870448542584e-05, + "loss": 0.4925, + "step": 2847 + }, + { + "epoch": 0.24, + "learning_rate": 1.771694842345894e-05, + "loss": 0.4896, + "step": 2848 + }, + { + "epoch": 0.24, + "learning_rate": 1.7715191772965335e-05, + "loss": 0.5037, + "step": 2849 + }, + { + "epoch": 0.24, + "learning_rate": 1.7713434534079e-05, + "loss": 0.5017, + "step": 2850 + }, + { + "epoch": 0.24, + "learning_rate": 1.771167670693394e-05, + "loss": 0.4904, + "step": 2851 + }, + { + "epoch": 0.24, + "learning_rate": 1.770991829166422e-05, + "loss": 0.4934, + "step": 2852 + }, + { + "epoch": 0.24, + "learning_rate": 1.7708159288403943e-05, + "loss": 0.4919, + "step": 2853 + }, + { + "epoch": 0.24, + "learning_rate": 1.770639969728726e-05, + "loss": 0.4823, + "step": 2854 + }, + { + "epoch": 0.24, + "learning_rate": 1.770463951844836e-05, + "loss": 0.5065, + "step": 2855 + }, + { + "epoch": 0.24, + "learning_rate": 1.7702878752021485e-05, + "loss": 0.5013, + "step": 2856 + }, + { + "epoch": 0.24, + "learning_rate": 1.770111739814092e-05, + "loss": 0.4807, + "step": 2857 + }, + { + "epoch": 0.24, + "learning_rate": 1.769935545694099e-05, + "loss": 0.4918, + "step": 2858 + }, + { + "epoch": 0.24, + "learning_rate": 1.769759292855607e-05, + "loss": 0.5014, + "step": 2859 + }, + { + "epoch": 0.24, + "learning_rate": 1.7695829813120574e-05, + "loss": 0.4927, + "step": 2860 + }, + { + "epoch": 0.24, + "learning_rate": 1.769406611076897e-05, + "loss": 0.4786, + "step": 2861 + }, + { + "epoch": 0.24, + "learning_rate": 1.769230182163576e-05, + "loss": 0.5103, + "step": 2862 + }, + { + "epoch": 0.24, + "learning_rate": 1.76905369458555e-05, + "loss": 0.5066, + "step": 2863 + }, + { + "epoch": 0.24, + "learning_rate": 1.7688771483562788e-05, + "loss": 0.4815, + "step": 2864 + }, + { + "epoch": 0.24, + "learning_rate": 1.768700543489226e-05, + "loss": 0.5088, + "step": 2865 + }, + { + "epoch": 0.24, + "learning_rate": 1.7685238799978605e-05, + "loss": 0.4864, + "step": 2866 + }, + { + "epoch": 0.24, + "learning_rate": 1.7683471578956555e-05, + "loss": 0.4959, + "step": 2867 + }, + { + "epoch": 0.24, + "learning_rate": 1.7681703771960887e-05, + "loss": 0.497, + "step": 2868 + }, + { + "epoch": 0.24, + "learning_rate": 1.7679935379126417e-05, + "loss": 0.5005, + "step": 2869 + }, + { + "epoch": 0.24, + "learning_rate": 1.767816640058801e-05, + "loss": 0.5087, + "step": 2870 + }, + { + "epoch": 0.24, + "learning_rate": 1.7676396836480582e-05, + "loss": 0.482, + "step": 2871 + }, + { + "epoch": 0.24, + "learning_rate": 1.767462668693908e-05, + "loss": 0.498, + "step": 2872 + }, + { + "epoch": 0.24, + "learning_rate": 1.767285595209851e-05, + "loss": 0.4871, + "step": 2873 + }, + { + "epoch": 0.25, + "learning_rate": 1.767108463209391e-05, + "loss": 0.4874, + "step": 2874 + }, + { + "epoch": 0.25, + "learning_rate": 1.766931272706037e-05, + "loss": 0.4954, + "step": 2875 + }, + { + "epoch": 0.25, + "learning_rate": 1.7667540237133022e-05, + "loss": 0.5046, + "step": 2876 + }, + { + "epoch": 0.25, + "learning_rate": 1.7665767162447044e-05, + "loss": 0.492, + "step": 2877 + }, + { + "epoch": 0.25, + "learning_rate": 1.766399350313766e-05, + "loss": 0.4828, + "step": 2878 + }, + { + "epoch": 0.25, + "learning_rate": 1.7662219259340137e-05, + "loss": 0.4981, + "step": 2879 + }, + { + "epoch": 0.25, + "learning_rate": 1.766044443118978e-05, + "loss": 0.4893, + "step": 2880 + }, + { + "epoch": 0.25, + "learning_rate": 1.7658669018821956e-05, + "loss": 0.4691, + "step": 2881 + }, + { + "epoch": 0.25, + "learning_rate": 1.7656893022372052e-05, + "loss": 0.4839, + "step": 2882 + }, + { + "epoch": 0.25, + "learning_rate": 1.7655116441975524e-05, + "loss": 0.5052, + "step": 2883 + }, + { + "epoch": 0.25, + "learning_rate": 1.7653339277767852e-05, + "loss": 0.4948, + "step": 2884 + }, + { + "epoch": 0.25, + "learning_rate": 1.765156152988458e-05, + "loss": 0.5022, + "step": 2885 + }, + { + "epoch": 0.25, + "learning_rate": 1.7649783198461278e-05, + "loss": 0.4975, + "step": 2886 + }, + { + "epoch": 0.25, + "learning_rate": 1.7648004283633575e-05, + "loss": 0.4835, + "step": 2887 + }, + { + "epoch": 0.25, + "learning_rate": 1.7646224785537135e-05, + "loss": 0.494, + "step": 2888 + }, + { + "epoch": 0.25, + "learning_rate": 1.764444470430767e-05, + "loss": 0.4985, + "step": 2889 + }, + { + "epoch": 0.25, + "learning_rate": 1.764266404008094e-05, + "loss": 0.4977, + "step": 2890 + }, + { + "epoch": 0.25, + "learning_rate": 1.764088279299274e-05, + "loss": 0.4818, + "step": 2891 + }, + { + "epoch": 0.25, + "learning_rate": 1.763910096317892e-05, + "loss": 0.4871, + "step": 2892 + }, + { + "epoch": 0.25, + "learning_rate": 1.7637318550775368e-05, + "loss": 0.5084, + "step": 2893 + }, + { + "epoch": 0.25, + "learning_rate": 1.7635535555918016e-05, + "loss": 0.5001, + "step": 2894 + }, + { + "epoch": 0.25, + "learning_rate": 1.7633751978742847e-05, + "loss": 0.4879, + "step": 2895 + }, + { + "epoch": 0.25, + "learning_rate": 1.7631967819385883e-05, + "loss": 0.4836, + "step": 2896 + }, + { + "epoch": 0.25, + "learning_rate": 1.7630183077983192e-05, + "loss": 0.5005, + "step": 2897 + }, + { + "epoch": 0.25, + "learning_rate": 1.762839775467088e-05, + "loss": 0.5006, + "step": 2898 + }, + { + "epoch": 0.25, + "learning_rate": 1.7626611849585113e-05, + "loss": 0.494, + "step": 2899 + }, + { + "epoch": 0.25, + "learning_rate": 1.7624825362862084e-05, + "loss": 0.4944, + "step": 2900 + }, + { + "epoch": 0.25, + "learning_rate": 1.7623038294638037e-05, + "loss": 0.4629, + "step": 2901 + }, + { + "epoch": 0.25, + "learning_rate": 1.7621250645049267e-05, + "loss": 0.5258, + "step": 2902 + }, + { + "epoch": 0.25, + "learning_rate": 1.7619462414232104e-05, + "loss": 0.4746, + "step": 2903 + }, + { + "epoch": 0.25, + "learning_rate": 1.761767360232293e-05, + "loss": 0.5124, + "step": 2904 + }, + { + "epoch": 0.25, + "learning_rate": 1.7615884209458164e-05, + "loss": 0.4992, + "step": 2905 + }, + { + "epoch": 0.25, + "learning_rate": 1.761409423577427e-05, + "loss": 0.4979, + "step": 2906 + }, + { + "epoch": 0.25, + "learning_rate": 1.761230368140776e-05, + "loss": 0.4785, + "step": 2907 + }, + { + "epoch": 0.25, + "learning_rate": 1.7610512546495195e-05, + "loss": 0.5121, + "step": 2908 + }, + { + "epoch": 0.25, + "learning_rate": 1.7608720831173168e-05, + "loss": 0.5076, + "step": 2909 + }, + { + "epoch": 0.25, + "learning_rate": 1.760692853557833e-05, + "loss": 0.472, + "step": 2910 + }, + { + "epoch": 0.25, + "learning_rate": 1.7605135659847357e-05, + "loss": 0.493, + "step": 2911 + }, + { + "epoch": 0.25, + "learning_rate": 1.760334220411699e-05, + "loss": 0.4972, + "step": 2912 + }, + { + "epoch": 0.25, + "learning_rate": 1.7601548168524007e-05, + "loss": 0.4959, + "step": 2913 + }, + { + "epoch": 0.25, + "learning_rate": 1.759975355320522e-05, + "loss": 0.4915, + "step": 2914 + }, + { + "epoch": 0.25, + "learning_rate": 1.75979583582975e-05, + "loss": 0.5031, + "step": 2915 + }, + { + "epoch": 0.25, + "learning_rate": 1.7596162583937757e-05, + "loss": 0.4689, + "step": 2916 + }, + { + "epoch": 0.25, + "learning_rate": 1.759436623026294e-05, + "loss": 0.5037, + "step": 2917 + }, + { + "epoch": 0.25, + "learning_rate": 1.7592569297410053e-05, + "loss": 0.4997, + "step": 2918 + }, + { + "epoch": 0.25, + "learning_rate": 1.759077178551613e-05, + "loss": 0.4943, + "step": 2919 + }, + { + "epoch": 0.25, + "learning_rate": 1.7588973694718263e-05, + "loss": 0.5025, + "step": 2920 + }, + { + "epoch": 0.25, + "learning_rate": 1.7587175025153577e-05, + "loss": 0.4937, + "step": 2921 + }, + { + "epoch": 0.25, + "learning_rate": 1.7585375776959247e-05, + "loss": 0.5089, + "step": 2922 + }, + { + "epoch": 0.25, + "learning_rate": 1.7583575950272495e-05, + "loss": 0.4887, + "step": 2923 + }, + { + "epoch": 0.25, + "learning_rate": 1.7581775545230578e-05, + "loss": 0.5052, + "step": 2924 + }, + { + "epoch": 0.25, + "learning_rate": 1.7579974561970805e-05, + "loss": 0.4958, + "step": 2925 + }, + { + "epoch": 0.25, + "learning_rate": 1.7578173000630528e-05, + "loss": 0.4902, + "step": 2926 + }, + { + "epoch": 0.25, + "learning_rate": 1.757637086134714e-05, + "loss": 0.4894, + "step": 2927 + }, + { + "epoch": 0.25, + "learning_rate": 1.7574568144258078e-05, + "loss": 0.5099, + "step": 2928 + }, + { + "epoch": 0.25, + "learning_rate": 1.757276484950083e-05, + "loss": 0.492, + "step": 2929 + }, + { + "epoch": 0.25, + "learning_rate": 1.7570960977212915e-05, + "loss": 0.4927, + "step": 2930 + }, + { + "epoch": 0.25, + "learning_rate": 1.756915652753191e-05, + "loss": 0.5155, + "step": 2931 + }, + { + "epoch": 0.25, + "learning_rate": 1.7567351500595428e-05, + "loss": 0.5025, + "step": 2932 + }, + { + "epoch": 0.25, + "learning_rate": 1.7565545896541128e-05, + "loss": 0.4901, + "step": 2933 + }, + { + "epoch": 0.25, + "learning_rate": 1.756373971550671e-05, + "loss": 0.4853, + "step": 2934 + }, + { + "epoch": 0.25, + "learning_rate": 1.7561932957629927e-05, + "loss": 0.4906, + "step": 2935 + }, + { + "epoch": 0.25, + "learning_rate": 1.7560125623048566e-05, + "loss": 0.4953, + "step": 2936 + }, + { + "epoch": 0.25, + "learning_rate": 1.7558317711900463e-05, + "loss": 0.4877, + "step": 2937 + }, + { + "epoch": 0.25, + "learning_rate": 1.7556509224323495e-05, + "loss": 0.5124, + "step": 2938 + }, + { + "epoch": 0.25, + "learning_rate": 1.7554700160455586e-05, + "loss": 0.4874, + "step": 2939 + }, + { + "epoch": 0.25, + "learning_rate": 1.7552890520434704e-05, + "loss": 0.5059, + "step": 2940 + }, + { + "epoch": 0.25, + "learning_rate": 1.7551080304398858e-05, + "loss": 0.5018, + "step": 2941 + }, + { + "epoch": 0.25, + "learning_rate": 1.75492695124861e-05, + "loss": 0.499, + "step": 2942 + }, + { + "epoch": 0.25, + "learning_rate": 1.7547458144834536e-05, + "loss": 0.5062, + "step": 2943 + }, + { + "epoch": 0.25, + "learning_rate": 1.7545646201582304e-05, + "loss": 0.4884, + "step": 2944 + }, + { + "epoch": 0.25, + "learning_rate": 1.7543833682867588e-05, + "loss": 0.4912, + "step": 2945 + }, + { + "epoch": 0.25, + "learning_rate": 1.754202058882862e-05, + "loss": 0.4859, + "step": 2946 + }, + { + "epoch": 0.25, + "learning_rate": 1.754020691960368e-05, + "loss": 0.5048, + "step": 2947 + }, + { + "epoch": 0.25, + "learning_rate": 1.7538392675331074e-05, + "loss": 0.4852, + "step": 2948 + }, + { + "epoch": 0.25, + "learning_rate": 1.7536577856149178e-05, + "loss": 0.4838, + "step": 2949 + }, + { + "epoch": 0.25, + "learning_rate": 1.7534762462196385e-05, + "loss": 0.4944, + "step": 2950 + }, + { + "epoch": 0.25, + "learning_rate": 1.7532946493611152e-05, + "loss": 0.4862, + "step": 2951 + }, + { + "epoch": 0.25, + "learning_rate": 1.7531129950531972e-05, + "loss": 0.5208, + "step": 2952 + }, + { + "epoch": 0.25, + "learning_rate": 1.752931283309738e-05, + "loss": 0.4941, + "step": 2953 + }, + { + "epoch": 0.25, + "learning_rate": 1.7527495141445955e-05, + "loss": 0.5136, + "step": 2954 + }, + { + "epoch": 0.25, + "learning_rate": 1.7525676875716327e-05, + "loss": 0.4543, + "step": 2955 + }, + { + "epoch": 0.25, + "learning_rate": 1.7523858036047156e-05, + "loss": 0.5183, + "step": 2956 + }, + { + "epoch": 0.25, + "learning_rate": 1.7522038622577168e-05, + "loss": 0.5007, + "step": 2957 + }, + { + "epoch": 0.25, + "learning_rate": 1.7520218635445108e-05, + "loss": 0.4877, + "step": 2958 + }, + { + "epoch": 0.25, + "learning_rate": 1.7518398074789776e-05, + "loss": 0.502, + "step": 2959 + }, + { + "epoch": 0.25, + "learning_rate": 1.751657694075002e-05, + "loss": 0.4978, + "step": 2960 + }, + { + "epoch": 0.25, + "learning_rate": 1.7514755233464727e-05, + "loss": 0.4861, + "step": 2961 + }, + { + "epoch": 0.25, + "learning_rate": 1.7512932953072826e-05, + "loss": 0.4821, + "step": 2962 + }, + { + "epoch": 0.25, + "learning_rate": 1.751111009971329e-05, + "loss": 0.4945, + "step": 2963 + }, + { + "epoch": 0.25, + "learning_rate": 1.7509286673525143e-05, + "loss": 0.5138, + "step": 2964 + }, + { + "epoch": 0.25, + "learning_rate": 1.7507462674647445e-05, + "loss": 0.4813, + "step": 2965 + }, + { + "epoch": 0.25, + "learning_rate": 1.7505638103219297e-05, + "loss": 0.498, + "step": 2966 + }, + { + "epoch": 0.25, + "learning_rate": 1.7503812959379856e-05, + "loss": 0.5059, + "step": 2967 + }, + { + "epoch": 0.25, + "learning_rate": 1.7501987243268307e-05, + "loss": 0.4842, + "step": 2968 + }, + { + "epoch": 0.25, + "learning_rate": 1.750016095502389e-05, + "loss": 0.4918, + "step": 2969 + }, + { + "epoch": 0.25, + "learning_rate": 1.7498334094785895e-05, + "loss": 0.5125, + "step": 2970 + }, + { + "epoch": 0.25, + "learning_rate": 1.7496506662693632e-05, + "loss": 0.498, + "step": 2971 + }, + { + "epoch": 0.25, + "learning_rate": 1.7494678658886472e-05, + "loss": 0.5034, + "step": 2972 + }, + { + "epoch": 0.25, + "learning_rate": 1.749285008350383e-05, + "loss": 0.5076, + "step": 2973 + }, + { + "epoch": 0.25, + "learning_rate": 1.7491020936685158e-05, + "loss": 0.4914, + "step": 2974 + }, + { + "epoch": 0.25, + "learning_rate": 1.7489191218569958e-05, + "loss": 0.4996, + "step": 2975 + }, + { + "epoch": 0.25, + "learning_rate": 1.7487360929297765e-05, + "loss": 0.4927, + "step": 2976 + }, + { + "epoch": 0.25, + "learning_rate": 1.7485530069008173e-05, + "loss": 0.523, + "step": 2977 + }, + { + "epoch": 0.25, + "learning_rate": 1.7483698637840805e-05, + "loss": 0.4618, + "step": 2978 + }, + { + "epoch": 0.25, + "learning_rate": 1.7481866635935335e-05, + "loss": 0.5065, + "step": 2979 + }, + { + "epoch": 0.25, + "learning_rate": 1.748003406343148e-05, + "loss": 0.5005, + "step": 2980 + }, + { + "epoch": 0.25, + "learning_rate": 1.7478200920469e-05, + "loss": 0.4876, + "step": 2981 + }, + { + "epoch": 0.25, + "learning_rate": 1.7476367207187695e-05, + "loss": 0.4853, + "step": 2982 + }, + { + "epoch": 0.25, + "learning_rate": 1.7474532923727418e-05, + "loss": 0.4811, + "step": 2983 + }, + { + "epoch": 0.25, + "learning_rate": 1.7472698070228048e-05, + "loss": 0.492, + "step": 2984 + }, + { + "epoch": 0.25, + "learning_rate": 1.747086264682953e-05, + "loss": 0.5013, + "step": 2985 + }, + { + "epoch": 0.25, + "learning_rate": 1.7469026653671835e-05, + "loss": 0.5021, + "step": 2986 + }, + { + "epoch": 0.25, + "learning_rate": 1.7467190090894987e-05, + "loss": 0.5169, + "step": 2987 + }, + { + "epoch": 0.25, + "learning_rate": 1.746535295863905e-05, + "loss": 0.4976, + "step": 2988 + }, + { + "epoch": 0.25, + "learning_rate": 1.746351525704413e-05, + "loss": 0.492, + "step": 2989 + }, + { + "epoch": 0.25, + "learning_rate": 1.746167698625037e-05, + "loss": 0.4891, + "step": 2990 + }, + { + "epoch": 0.26, + "learning_rate": 1.7459838146397975e-05, + "loss": 0.4946, + "step": 2991 + }, + { + "epoch": 0.26, + "learning_rate": 1.7457998737627183e-05, + "loss": 0.4972, + "step": 2992 + }, + { + "epoch": 0.26, + "learning_rate": 1.7456158760078265e-05, + "loss": 0.4902, + "step": 2993 + }, + { + "epoch": 0.26, + "learning_rate": 1.7454318213891556e-05, + "loss": 0.4917, + "step": 2994 + }, + { + "epoch": 0.26, + "learning_rate": 1.7452477099207416e-05, + "loss": 0.501, + "step": 2995 + }, + { + "epoch": 0.26, + "learning_rate": 1.745063541616626e-05, + "loss": 0.4786, + "step": 2996 + }, + { + "epoch": 0.26, + "learning_rate": 1.7448793164908545e-05, + "loss": 0.4899, + "step": 2997 + }, + { + "epoch": 0.26, + "learning_rate": 1.7446950345574762e-05, + "loss": 0.5043, + "step": 2998 + }, + { + "epoch": 0.26, + "learning_rate": 1.7445106958305456e-05, + "loss": 0.4925, + "step": 2999 + }, + { + "epoch": 0.26, + "learning_rate": 1.744326300324121e-05, + "loss": 0.4892, + "step": 3000 + }, + { + "epoch": 0.26, + "learning_rate": 1.7441418480522656e-05, + "loss": 0.4848, + "step": 3001 + }, + { + "epoch": 0.26, + "learning_rate": 1.743957339029046e-05, + "loss": 0.4981, + "step": 3002 + }, + { + "epoch": 0.26, + "learning_rate": 1.7437727732685337e-05, + "loss": 0.4871, + "step": 3003 + }, + { + "epoch": 0.26, + "learning_rate": 1.7435881507848048e-05, + "loss": 0.4847, + "step": 3004 + }, + { + "epoch": 0.26, + "learning_rate": 1.743403471591939e-05, + "loss": 0.496, + "step": 3005 + }, + { + "epoch": 0.26, + "learning_rate": 1.7432187357040206e-05, + "loss": 0.4899, + "step": 3006 + }, + { + "epoch": 0.26, + "learning_rate": 1.7430339431351388e-05, + "loss": 0.4847, + "step": 3007 + }, + { + "epoch": 0.26, + "learning_rate": 1.7428490938993864e-05, + "loss": 0.4932, + "step": 3008 + }, + { + "epoch": 0.26, + "learning_rate": 1.7426641880108607e-05, + "loss": 0.4687, + "step": 3009 + }, + { + "epoch": 0.26, + "learning_rate": 1.7424792254836636e-05, + "loss": 0.4908, + "step": 3010 + }, + { + "epoch": 0.26, + "learning_rate": 1.742294206331901e-05, + "loss": 0.5091, + "step": 3011 + }, + { + "epoch": 0.26, + "learning_rate": 1.7421091305696834e-05, + "loss": 0.5073, + "step": 3012 + }, + { + "epoch": 0.26, + "learning_rate": 1.741923998211125e-05, + "loss": 0.4988, + "step": 3013 + }, + { + "epoch": 0.26, + "learning_rate": 1.7417388092703454e-05, + "loss": 0.5117, + "step": 3014 + }, + { + "epoch": 0.26, + "learning_rate": 1.741553563761467e-05, + "loss": 0.487, + "step": 3015 + }, + { + "epoch": 0.26, + "learning_rate": 1.7413682616986185e-05, + "loss": 0.4897, + "step": 3016 + }, + { + "epoch": 0.26, + "learning_rate": 1.741182903095931e-05, + "loss": 0.4824, + "step": 3017 + }, + { + "epoch": 0.26, + "learning_rate": 1.7409974879675408e-05, + "loss": 0.4892, + "step": 3018 + }, + { + "epoch": 0.26, + "learning_rate": 1.740812016327589e-05, + "loss": 0.5085, + "step": 3019 + }, + { + "epoch": 0.26, + "learning_rate": 1.7406264881902195e-05, + "loss": 0.4745, + "step": 3020 + }, + { + "epoch": 0.26, + "learning_rate": 1.7404409035695825e-05, + "loss": 0.506, + "step": 3021 + }, + { + "epoch": 0.26, + "learning_rate": 1.7402552624798306e-05, + "loss": 0.4969, + "step": 3022 + }, + { + "epoch": 0.26, + "learning_rate": 1.740069564935122e-05, + "loss": 0.4911, + "step": 3023 + }, + { + "epoch": 0.26, + "learning_rate": 1.7398838109496187e-05, + "loss": 0.4857, + "step": 3024 + }, + { + "epoch": 0.26, + "learning_rate": 1.739698000537487e-05, + "loss": 0.4719, + "step": 3025 + }, + { + "epoch": 0.26, + "learning_rate": 1.739512133712898e-05, + "loss": 0.485, + "step": 3026 + }, + { + "epoch": 0.26, + "learning_rate": 1.7393262104900258e-05, + "loss": 0.4927, + "step": 3027 + }, + { + "epoch": 0.26, + "learning_rate": 1.7391402308830506e-05, + "loss": 0.4932, + "step": 3028 + }, + { + "epoch": 0.26, + "learning_rate": 1.738954194906155e-05, + "loss": 0.5002, + "step": 3029 + }, + { + "epoch": 0.26, + "learning_rate": 1.7387681025735278e-05, + "loss": 0.5022, + "step": 3030 + }, + { + "epoch": 0.26, + "learning_rate": 1.738581953899361e-05, + "loss": 0.486, + "step": 3031 + }, + { + "epoch": 0.26, + "learning_rate": 1.7383957488978508e-05, + "loss": 0.4951, + "step": 3032 + }, + { + "epoch": 0.26, + "learning_rate": 1.7382094875831984e-05, + "loss": 0.4997, + "step": 3033 + }, + { + "epoch": 0.26, + "learning_rate": 1.738023169969608e-05, + "loss": 0.4773, + "step": 3034 + }, + { + "epoch": 0.26, + "learning_rate": 1.7378367960712896e-05, + "loss": 0.5047, + "step": 3035 + }, + { + "epoch": 0.26, + "learning_rate": 1.737650365902457e-05, + "loss": 0.5053, + "step": 3036 + }, + { + "epoch": 0.26, + "learning_rate": 1.7374638794773276e-05, + "loss": 0.5004, + "step": 3037 + }, + { + "epoch": 0.26, + "learning_rate": 1.737277336810124e-05, + "loss": 0.4871, + "step": 3038 + }, + { + "epoch": 0.26, + "learning_rate": 1.737090737915073e-05, + "loss": 0.5066, + "step": 3039 + }, + { + "epoch": 0.26, + "learning_rate": 1.7369040828064046e-05, + "loss": 0.4948, + "step": 3040 + }, + { + "epoch": 0.26, + "learning_rate": 1.7367173714983548e-05, + "loss": 0.5184, + "step": 3041 + }, + { + "epoch": 0.26, + "learning_rate": 1.7365306040051622e-05, + "loss": 0.504, + "step": 3042 + }, + { + "epoch": 0.26, + "learning_rate": 1.7363437803410708e-05, + "loss": 0.4912, + "step": 3043 + }, + { + "epoch": 0.26, + "learning_rate": 1.7361569005203288e-05, + "loss": 0.5031, + "step": 3044 + }, + { + "epoch": 0.26, + "learning_rate": 1.7359699645571883e-05, + "loss": 0.4924, + "step": 3045 + }, + { + "epoch": 0.26, + "learning_rate": 1.7357829724659056e-05, + "loss": 0.4825, + "step": 3046 + }, + { + "epoch": 0.26, + "learning_rate": 1.7355959242607413e-05, + "loss": 0.5128, + "step": 3047 + }, + { + "epoch": 0.26, + "learning_rate": 1.735408819955961e-05, + "loss": 0.4949, + "step": 3048 + }, + { + "epoch": 0.26, + "learning_rate": 1.7352216595658343e-05, + "loss": 0.4836, + "step": 3049 + }, + { + "epoch": 0.26, + "learning_rate": 1.7350344431046338e-05, + "loss": 0.484, + "step": 3050 + }, + { + "epoch": 0.26, + "learning_rate": 1.734847170586638e-05, + "loss": 0.5041, + "step": 3051 + }, + { + "epoch": 0.26, + "learning_rate": 1.7346598420261294e-05, + "loss": 0.4879, + "step": 3052 + }, + { + "epoch": 0.26, + "learning_rate": 1.7344724574373942e-05, + "loss": 0.4923, + "step": 3053 + }, + { + "epoch": 0.26, + "learning_rate": 1.734285016834723e-05, + "loss": 0.5026, + "step": 3054 + }, + { + "epoch": 0.26, + "learning_rate": 1.7340975202324103e-05, + "loss": 0.5041, + "step": 3055 + }, + { + "epoch": 0.26, + "learning_rate": 1.7339099676447564e-05, + "loss": 0.5049, + "step": 3056 + }, + { + "epoch": 0.26, + "learning_rate": 1.7337223590860643e-05, + "loss": 0.4899, + "step": 3057 + }, + { + "epoch": 0.26, + "learning_rate": 1.733534694570642e-05, + "loss": 0.5149, + "step": 3058 + }, + { + "epoch": 0.26, + "learning_rate": 1.7333469741128016e-05, + "loss": 0.4866, + "step": 3059 + }, + { + "epoch": 0.26, + "learning_rate": 1.733159197726859e-05, + "loss": 0.5207, + "step": 3060 + }, + { + "epoch": 0.26, + "learning_rate": 1.7329713654271356e-05, + "loss": 0.4773, + "step": 3061 + }, + { + "epoch": 0.26, + "learning_rate": 1.732783477227955e-05, + "loss": 0.4879, + "step": 3062 + }, + { + "epoch": 0.26, + "learning_rate": 1.732595533143648e-05, + "loss": 0.4992, + "step": 3063 + }, + { + "epoch": 0.26, + "learning_rate": 1.7324075331885466e-05, + "loss": 0.5088, + "step": 3064 + }, + { + "epoch": 0.26, + "learning_rate": 1.732219477376989e-05, + "loss": 0.4841, + "step": 3065 + }, + { + "epoch": 0.26, + "learning_rate": 1.7320313657233175e-05, + "loss": 0.4898, + "step": 3066 + }, + { + "epoch": 0.26, + "learning_rate": 1.731843198241878e-05, + "loss": 0.5043, + "step": 3067 + }, + { + "epoch": 0.26, + "learning_rate": 1.7316549749470205e-05, + "loss": 0.4959, + "step": 3068 + }, + { + "epoch": 0.26, + "learning_rate": 1.7314666958531e-05, + "loss": 0.512, + "step": 3069 + }, + { + "epoch": 0.26, + "learning_rate": 1.7312783609744753e-05, + "loss": 0.4905, + "step": 3070 + }, + { + "epoch": 0.26, + "learning_rate": 1.7310899703255103e-05, + "loss": 0.5037, + "step": 3071 + }, + { + "epoch": 0.26, + "learning_rate": 1.7309015239205717e-05, + "loss": 0.4869, + "step": 3072 + }, + { + "epoch": 0.26, + "learning_rate": 1.7307130217740317e-05, + "loss": 0.4975, + "step": 3073 + }, + { + "epoch": 0.26, + "learning_rate": 1.7305244639002657e-05, + "loss": 0.4905, + "step": 3074 + }, + { + "epoch": 0.26, + "learning_rate": 1.7303358503136544e-05, + "loss": 0.4991, + "step": 3075 + }, + { + "epoch": 0.26, + "learning_rate": 1.7301471810285823e-05, + "loss": 0.495, + "step": 3076 + }, + { + "epoch": 0.26, + "learning_rate": 1.7299584560594376e-05, + "loss": 0.4924, + "step": 3077 + }, + { + "epoch": 0.26, + "learning_rate": 1.7297696754206137e-05, + "loss": 0.4816, + "step": 3078 + }, + { + "epoch": 0.26, + "learning_rate": 1.7295808391265074e-05, + "loss": 0.4917, + "step": 3079 + }, + { + "epoch": 0.26, + "learning_rate": 1.7293919471915207e-05, + "loss": 0.499, + "step": 3080 + }, + { + "epoch": 0.26, + "learning_rate": 1.729202999630059e-05, + "loss": 0.4946, + "step": 3081 + }, + { + "epoch": 0.26, + "learning_rate": 1.729013996456532e-05, + "loss": 0.4896, + "step": 3082 + }, + { + "epoch": 0.26, + "learning_rate": 1.7288249376853543e-05, + "loss": 0.4865, + "step": 3083 + }, + { + "epoch": 0.26, + "learning_rate": 1.7286358233309438e-05, + "loss": 0.5144, + "step": 3084 + }, + { + "epoch": 0.26, + "learning_rate": 1.728446653407724e-05, + "loss": 0.5058, + "step": 3085 + }, + { + "epoch": 0.26, + "learning_rate": 1.7282574279301205e-05, + "loss": 0.4927, + "step": 3086 + }, + { + "epoch": 0.26, + "learning_rate": 1.7280681469125657e-05, + "loss": 0.5008, + "step": 3087 + }, + { + "epoch": 0.26, + "learning_rate": 1.7278788103694944e-05, + "loss": 0.4769, + "step": 3088 + }, + { + "epoch": 0.26, + "learning_rate": 1.7276894183153457e-05, + "loss": 0.5025, + "step": 3089 + }, + { + "epoch": 0.26, + "learning_rate": 1.7274999707645646e-05, + "loss": 0.4839, + "step": 3090 + }, + { + "epoch": 0.26, + "learning_rate": 1.727310467731598e-05, + "loss": 0.4872, + "step": 3091 + }, + { + "epoch": 0.26, + "learning_rate": 1.7271209092308993e-05, + "loss": 0.4883, + "step": 3092 + }, + { + "epoch": 0.26, + "learning_rate": 1.726931295276924e-05, + "loss": 0.4906, + "step": 3093 + }, + { + "epoch": 0.26, + "learning_rate": 1.7267416258841333e-05, + "loss": 0.4939, + "step": 3094 + }, + { + "epoch": 0.26, + "learning_rate": 1.726551901066992e-05, + "loss": 0.5106, + "step": 3095 + }, + { + "epoch": 0.26, + "learning_rate": 1.7263621208399696e-05, + "loss": 0.5011, + "step": 3096 + }, + { + "epoch": 0.26, + "learning_rate": 1.7261722852175394e-05, + "loss": 0.4931, + "step": 3097 + }, + { + "epoch": 0.26, + "learning_rate": 1.7259823942141794e-05, + "loss": 0.4738, + "step": 3098 + }, + { + "epoch": 0.26, + "learning_rate": 1.725792447844371e-05, + "loss": 0.5066, + "step": 3099 + }, + { + "epoch": 0.26, + "learning_rate": 1.7256024461226002e-05, + "loss": 0.5124, + "step": 3100 + }, + { + "epoch": 0.26, + "learning_rate": 1.7254123890633576e-05, + "loss": 0.4834, + "step": 3101 + }, + { + "epoch": 0.26, + "learning_rate": 1.7252222766811376e-05, + "loss": 0.4883, + "step": 3102 + }, + { + "epoch": 0.26, + "learning_rate": 1.7250321089904393e-05, + "loss": 0.5048, + "step": 3103 + }, + { + "epoch": 0.26, + "learning_rate": 1.7248418860057653e-05, + "loss": 0.4912, + "step": 3104 + }, + { + "epoch": 0.26, + "learning_rate": 1.7246516077416232e-05, + "loss": 0.4864, + "step": 3105 + }, + { + "epoch": 0.26, + "learning_rate": 1.7244612742125237e-05, + "loss": 0.4934, + "step": 3106 + }, + { + "epoch": 0.26, + "learning_rate": 1.7242708854329833e-05, + "loss": 0.5087, + "step": 3107 + }, + { + "epoch": 0.27, + "learning_rate": 1.724080441417521e-05, + "loss": 0.4767, + "step": 3108 + }, + { + "epoch": 0.27, + "learning_rate": 1.7238899421806618e-05, + "loss": 0.4848, + "step": 3109 + }, + { + "epoch": 0.27, + "learning_rate": 1.7236993877369333e-05, + "loss": 0.4967, + "step": 3110 + }, + { + "epoch": 0.27, + "learning_rate": 1.723508778100868e-05, + "loss": 0.4954, + "step": 3111 + }, + { + "epoch": 0.27, + "learning_rate": 1.723318113287003e-05, + "loss": 0.4913, + "step": 3112 + }, + { + "epoch": 0.27, + "learning_rate": 1.7231273933098784e-05, + "loss": 0.4828, + "step": 3113 + }, + { + "epoch": 0.27, + "learning_rate": 1.7229366181840405e-05, + "loss": 0.4925, + "step": 3114 + }, + { + "epoch": 0.27, + "learning_rate": 1.7227457879240375e-05, + "loss": 0.5013, + "step": 3115 + }, + { + "epoch": 0.27, + "learning_rate": 1.7225549025444233e-05, + "loss": 0.5048, + "step": 3116 + }, + { + "epoch": 0.27, + "learning_rate": 1.7223639620597556e-05, + "loss": 0.5037, + "step": 3117 + }, + { + "epoch": 0.27, + "learning_rate": 1.7221729664845966e-05, + "loss": 0.4903, + "step": 3118 + }, + { + "epoch": 0.27, + "learning_rate": 1.7219819158335123e-05, + "loss": 0.4899, + "step": 3119 + }, + { + "epoch": 0.27, + "learning_rate": 1.7217908101210725e-05, + "loss": 0.4959, + "step": 3120 + }, + { + "epoch": 0.27, + "learning_rate": 1.7215996493618525e-05, + "loss": 0.4844, + "step": 3121 + }, + { + "epoch": 0.27, + "learning_rate": 1.7214084335704305e-05, + "loss": 0.5091, + "step": 3122 + }, + { + "epoch": 0.27, + "learning_rate": 1.7212171627613895e-05, + "loss": 0.4994, + "step": 3123 + }, + { + "epoch": 0.27, + "learning_rate": 1.721025836949317e-05, + "loss": 0.4843, + "step": 3124 + }, + { + "epoch": 0.27, + "learning_rate": 1.7208344561488037e-05, + "loss": 0.4854, + "step": 3125 + }, + { + "epoch": 0.27, + "learning_rate": 1.7206430203744455e-05, + "loss": 0.4778, + "step": 3126 + }, + { + "epoch": 0.27, + "learning_rate": 1.7204515296408418e-05, + "loss": 0.4773, + "step": 3127 + }, + { + "epoch": 0.27, + "learning_rate": 1.720259983962597e-05, + "loss": 0.4921, + "step": 3128 + }, + { + "epoch": 0.27, + "learning_rate": 1.7200683833543185e-05, + "loss": 0.5156, + "step": 3129 + }, + { + "epoch": 0.27, + "learning_rate": 1.719876727830619e-05, + "loss": 0.4991, + "step": 3130 + }, + { + "epoch": 0.27, + "learning_rate": 1.719685017406115e-05, + "loss": 0.4911, + "step": 3131 + }, + { + "epoch": 0.27, + "learning_rate": 1.7194932520954266e-05, + "loss": 0.4823, + "step": 3132 + }, + { + "epoch": 0.27, + "learning_rate": 1.7193014319131794e-05, + "loss": 0.5119, + "step": 3133 + }, + { + "epoch": 0.27, + "learning_rate": 1.7191095568740017e-05, + "loss": 0.4912, + "step": 3134 + }, + { + "epoch": 0.27, + "learning_rate": 1.7189176269925272e-05, + "loss": 0.4937, + "step": 3135 + }, + { + "epoch": 0.27, + "learning_rate": 1.7187256422833928e-05, + "loss": 0.5136, + "step": 3136 + }, + { + "epoch": 0.27, + "learning_rate": 1.7185336027612405e-05, + "loss": 0.4928, + "step": 3137 + }, + { + "epoch": 0.27, + "learning_rate": 1.7183415084407162e-05, + "loss": 0.5143, + "step": 3138 + }, + { + "epoch": 0.27, + "learning_rate": 1.7181493593364688e-05, + "loss": 0.4933, + "step": 3139 + }, + { + "epoch": 0.27, + "learning_rate": 1.7179571554631534e-05, + "loss": 0.5069, + "step": 3140 + }, + { + "epoch": 0.27, + "learning_rate": 1.717764896835428e-05, + "loss": 0.4969, + "step": 3141 + }, + { + "epoch": 0.27, + "learning_rate": 1.7175725834679552e-05, + "loss": 0.4992, + "step": 3142 + }, + { + "epoch": 0.27, + "learning_rate": 1.717380215375401e-05, + "loss": 0.5069, + "step": 3143 + }, + { + "epoch": 0.27, + "learning_rate": 1.7171877925724366e-05, + "loss": 0.4913, + "step": 3144 + }, + { + "epoch": 0.27, + "learning_rate": 1.7169953150737375e-05, + "loss": 0.4822, + "step": 3145 + }, + { + "epoch": 0.27, + "learning_rate": 1.7168027828939818e-05, + "loss": 0.4992, + "step": 3146 + }, + { + "epoch": 0.27, + "learning_rate": 1.7166101960478537e-05, + "loss": 0.4857, + "step": 3147 + }, + { + "epoch": 0.27, + "learning_rate": 1.71641755455004e-05, + "loss": 0.4978, + "step": 3148 + }, + { + "epoch": 0.27, + "learning_rate": 1.716224858415233e-05, + "loss": 0.4907, + "step": 3149 + }, + { + "epoch": 0.27, + "learning_rate": 1.7160321076581275e-05, + "loss": 0.496, + "step": 3150 + }, + { + "epoch": 0.27, + "learning_rate": 1.7158393022934246e-05, + "loss": 0.4861, + "step": 3151 + }, + { + "epoch": 0.27, + "learning_rate": 1.7156464423358277e-05, + "loss": 0.4912, + "step": 3152 + }, + { + "epoch": 0.27, + "learning_rate": 1.7154535278000458e-05, + "loss": 0.4858, + "step": 3153 + }, + { + "epoch": 0.27, + "learning_rate": 1.7152605587007906e-05, + "loss": 0.4921, + "step": 3154 + }, + { + "epoch": 0.27, + "learning_rate": 1.715067535052779e-05, + "loss": 0.4861, + "step": 3155 + }, + { + "epoch": 0.27, + "learning_rate": 1.714874456870732e-05, + "loss": 0.4735, + "step": 3156 + }, + { + "epoch": 0.27, + "learning_rate": 1.7146813241693742e-05, + "loss": 0.5134, + "step": 3157 + }, + { + "epoch": 0.27, + "learning_rate": 1.7144881369634354e-05, + "loss": 0.4862, + "step": 3158 + }, + { + "epoch": 0.27, + "learning_rate": 1.7142948952676478e-05, + "loss": 0.5313, + "step": 3159 + }, + { + "epoch": 0.27, + "learning_rate": 1.71410159909675e-05, + "loss": 0.4878, + "step": 3160 + }, + { + "epoch": 0.27, + "learning_rate": 1.7139082484654825e-05, + "loss": 0.5183, + "step": 3161 + }, + { + "epoch": 0.27, + "learning_rate": 1.713714843388592e-05, + "loss": 0.5032, + "step": 3162 + }, + { + "epoch": 0.27, + "learning_rate": 1.7135213838808275e-05, + "loss": 0.4872, + "step": 3163 + }, + { + "epoch": 0.27, + "learning_rate": 1.713327869956943e-05, + "loss": 0.4827, + "step": 3164 + }, + { + "epoch": 0.27, + "learning_rate": 1.7131343016316976e-05, + "loss": 0.497, + "step": 3165 + }, + { + "epoch": 0.27, + "learning_rate": 1.712940678919853e-05, + "loss": 0.4871, + "step": 3166 + }, + { + "epoch": 0.27, + "learning_rate": 1.712747001836176e-05, + "loss": 0.4855, + "step": 3167 + }, + { + "epoch": 0.27, + "learning_rate": 1.7125532703954366e-05, + "loss": 0.5069, + "step": 3168 + }, + { + "epoch": 0.27, + "learning_rate": 1.7123594846124105e-05, + "loss": 0.4639, + "step": 3169 + }, + { + "epoch": 0.27, + "learning_rate": 1.7121656445018756e-05, + "loss": 0.5106, + "step": 3170 + }, + { + "epoch": 0.27, + "learning_rate": 1.7119717500786158e-05, + "loss": 0.4764, + "step": 3171 + }, + { + "epoch": 0.27, + "learning_rate": 1.7117778013574174e-05, + "loss": 0.5048, + "step": 3172 + }, + { + "epoch": 0.27, + "learning_rate": 1.711583798353073e-05, + "loss": 0.4774, + "step": 3173 + }, + { + "epoch": 0.27, + "learning_rate": 1.7113897410803767e-05, + "loss": 0.4928, + "step": 3174 + }, + { + "epoch": 0.27, + "learning_rate": 1.7111956295541296e-05, + "loss": 0.4963, + "step": 3175 + }, + { + "epoch": 0.27, + "learning_rate": 1.711001463789134e-05, + "loss": 0.478, + "step": 3176 + }, + { + "epoch": 0.27, + "learning_rate": 1.7108072438001987e-05, + "loss": 0.4775, + "step": 3177 + }, + { + "epoch": 0.27, + "learning_rate": 1.7106129696021353e-05, + "loss": 0.5119, + "step": 3178 + }, + { + "epoch": 0.27, + "learning_rate": 1.71041864120976e-05, + "loss": 0.484, + "step": 3179 + }, + { + "epoch": 0.27, + "learning_rate": 1.7102242586378936e-05, + "loss": 0.503, + "step": 3180 + }, + { + "epoch": 0.27, + "learning_rate": 1.7100298219013597e-05, + "loss": 0.4702, + "step": 3181 + }, + { + "epoch": 0.27, + "learning_rate": 1.7098353310149876e-05, + "loss": 0.4989, + "step": 3182 + }, + { + "epoch": 0.27, + "learning_rate": 1.7096407859936095e-05, + "loss": 0.4991, + "step": 3183 + }, + { + "epoch": 0.27, + "learning_rate": 1.7094461868520625e-05, + "loss": 0.4967, + "step": 3184 + }, + { + "epoch": 0.27, + "learning_rate": 1.7092515336051872e-05, + "loss": 0.5047, + "step": 3185 + }, + { + "epoch": 0.27, + "learning_rate": 1.7090568262678294e-05, + "loss": 0.487, + "step": 3186 + }, + { + "epoch": 0.27, + "learning_rate": 1.7088620648548376e-05, + "loss": 0.5029, + "step": 3187 + }, + { + "epoch": 0.27, + "learning_rate": 1.708667249381065e-05, + "loss": 0.4998, + "step": 3188 + }, + { + "epoch": 0.27, + "learning_rate": 1.7084723798613697e-05, + "loss": 0.5008, + "step": 3189 + }, + { + "epoch": 0.27, + "learning_rate": 1.708277456310613e-05, + "loss": 0.4969, + "step": 3190 + }, + { + "epoch": 0.27, + "learning_rate": 1.7080824787436603e-05, + "loss": 0.5108, + "step": 3191 + }, + { + "epoch": 0.27, + "learning_rate": 1.7078874471753816e-05, + "loss": 0.4998, + "step": 3192 + }, + { + "epoch": 0.27, + "learning_rate": 1.707692361620651e-05, + "loss": 0.4907, + "step": 3193 + }, + { + "epoch": 0.27, + "learning_rate": 1.7074972220943464e-05, + "loss": 0.4924, + "step": 3194 + }, + { + "epoch": 0.27, + "learning_rate": 1.7073020286113498e-05, + "loss": 0.4852, + "step": 3195 + }, + { + "epoch": 0.27, + "learning_rate": 1.7071067811865477e-05, + "loss": 0.492, + "step": 3196 + }, + { + "epoch": 0.27, + "learning_rate": 1.7069114798348303e-05, + "loss": 0.4786, + "step": 3197 + }, + { + "epoch": 0.27, + "learning_rate": 1.7067161245710924e-05, + "loss": 0.5085, + "step": 3198 + }, + { + "epoch": 0.27, + "learning_rate": 1.706520715410232e-05, + "loss": 0.4917, + "step": 3199 + }, + { + "epoch": 0.27, + "learning_rate": 1.706325252367152e-05, + "loss": 0.4949, + "step": 3200 + }, + { + "epoch": 0.27, + "learning_rate": 1.7061297354567603e-05, + "loss": 0.4948, + "step": 3201 + }, + { + "epoch": 0.27, + "learning_rate": 1.7059341646939665e-05, + "loss": 0.4932, + "step": 3202 + }, + { + "epoch": 0.27, + "learning_rate": 1.705738540093686e-05, + "loss": 0.4996, + "step": 3203 + }, + { + "epoch": 0.27, + "learning_rate": 1.705542861670838e-05, + "loss": 0.5124, + "step": 3204 + }, + { + "epoch": 0.27, + "learning_rate": 1.7053471294403464e-05, + "loss": 0.4796, + "step": 3205 + }, + { + "epoch": 0.27, + "learning_rate": 1.7051513434171375e-05, + "loss": 0.4907, + "step": 3206 + }, + { + "epoch": 0.27, + "learning_rate": 1.7049555036161433e-05, + "loss": 0.5056, + "step": 3207 + }, + { + "epoch": 0.27, + "learning_rate": 1.7047596100522992e-05, + "loss": 0.4642, + "step": 3208 + }, + { + "epoch": 0.27, + "learning_rate": 1.704563662740545e-05, + "loss": 0.5044, + "step": 3209 + }, + { + "epoch": 0.27, + "learning_rate": 1.7043676616958245e-05, + "loss": 0.5, + "step": 3210 + }, + { + "epoch": 0.27, + "learning_rate": 1.7041716069330853e-05, + "loss": 0.4906, + "step": 3211 + }, + { + "epoch": 0.27, + "learning_rate": 1.70397549846728e-05, + "loss": 0.4824, + "step": 3212 + }, + { + "epoch": 0.27, + "learning_rate": 1.703779336313364e-05, + "loss": 0.5066, + "step": 3213 + }, + { + "epoch": 0.27, + "learning_rate": 1.703583120486297e-05, + "loss": 0.4909, + "step": 3214 + }, + { + "epoch": 0.27, + "learning_rate": 1.7033868510010446e-05, + "loss": 0.4549, + "step": 3215 + }, + { + "epoch": 0.27, + "learning_rate": 1.703190527872574e-05, + "loss": 0.4896, + "step": 3216 + }, + { + "epoch": 0.27, + "learning_rate": 1.702994151115858e-05, + "loss": 0.5149, + "step": 3217 + }, + { + "epoch": 0.27, + "learning_rate": 1.7027977207458732e-05, + "loss": 0.4926, + "step": 3218 + }, + { + "epoch": 0.27, + "learning_rate": 1.7026012367776002e-05, + "loss": 0.5133, + "step": 3219 + }, + { + "epoch": 0.27, + "learning_rate": 1.702404699226024e-05, + "loss": 0.4792, + "step": 3220 + }, + { + "epoch": 0.27, + "learning_rate": 1.7022081081061323e-05, + "loss": 0.4976, + "step": 3221 + }, + { + "epoch": 0.27, + "learning_rate": 1.702011463432919e-05, + "loss": 0.4901, + "step": 3222 + }, + { + "epoch": 0.27, + "learning_rate": 1.7018147652213805e-05, + "loss": 0.4886, + "step": 3223 + }, + { + "epoch": 0.27, + "learning_rate": 1.7016180134865182e-05, + "loss": 0.4995, + "step": 3224 + }, + { + "epoch": 0.27, + "learning_rate": 1.701421208243337e-05, + "loss": 0.5057, + "step": 3225 + }, + { + "epoch": 0.28, + "learning_rate": 1.701224349506846e-05, + "loss": 0.4833, + "step": 3226 + }, + { + "epoch": 0.28, + "learning_rate": 1.7010274372920584e-05, + "loss": 0.5102, + "step": 3227 + }, + { + "epoch": 0.28, + "learning_rate": 1.700830471613992e-05, + "loss": 0.4952, + "step": 3228 + }, + { + "epoch": 0.28, + "learning_rate": 1.700633452487668e-05, + "loss": 0.5003, + "step": 3229 + }, + { + "epoch": 0.28, + "learning_rate": 1.700436379928112e-05, + "loss": 0.4914, + "step": 3230 + }, + { + "epoch": 0.28, + "learning_rate": 1.700239253950353e-05, + "loss": 0.4846, + "step": 3231 + }, + { + "epoch": 0.28, + "learning_rate": 1.7000420745694256e-05, + "loss": 0.4989, + "step": 3232 + }, + { + "epoch": 0.28, + "learning_rate": 1.6998448418003666e-05, + "loss": 0.4913, + "step": 3233 + }, + { + "epoch": 0.28, + "learning_rate": 1.6996475556582182e-05, + "loss": 0.4775, + "step": 3234 + }, + { + "epoch": 0.28, + "learning_rate": 1.6994502161580263e-05, + "loss": 0.5046, + "step": 3235 + }, + { + "epoch": 0.28, + "learning_rate": 1.6992528233148414e-05, + "loss": 0.4768, + "step": 3236 + }, + { + "epoch": 0.28, + "learning_rate": 1.699055377143716e-05, + "loss": 0.4879, + "step": 3237 + }, + { + "epoch": 0.28, + "learning_rate": 1.6988578776597094e-05, + "loss": 0.475, + "step": 3238 + }, + { + "epoch": 0.28, + "learning_rate": 1.6986603248778838e-05, + "loss": 0.4954, + "step": 3239 + }, + { + "epoch": 0.28, + "learning_rate": 1.6984627188133045e-05, + "loss": 0.4972, + "step": 3240 + }, + { + "epoch": 0.28, + "learning_rate": 1.6982650594810424e-05, + "loss": 0.484, + "step": 3241 + }, + { + "epoch": 0.28, + "learning_rate": 1.6980673468961717e-05, + "loss": 0.5097, + "step": 3242 + }, + { + "epoch": 0.28, + "learning_rate": 1.6978695810737708e-05, + "loss": 0.4724, + "step": 3243 + }, + { + "epoch": 0.28, + "learning_rate": 1.697671762028922e-05, + "loss": 0.4885, + "step": 3244 + }, + { + "epoch": 0.28, + "learning_rate": 1.6974738897767123e-05, + "loss": 0.4736, + "step": 3245 + }, + { + "epoch": 0.28, + "learning_rate": 1.6972759643322315e-05, + "loss": 0.4777, + "step": 3246 + }, + { + "epoch": 0.28, + "learning_rate": 1.6970779857105747e-05, + "loss": 0.5144, + "step": 3247 + }, + { + "epoch": 0.28, + "learning_rate": 1.6968799539268408e-05, + "loss": 0.5038, + "step": 3248 + }, + { + "epoch": 0.28, + "learning_rate": 1.696681868996132e-05, + "loss": 0.5059, + "step": 3249 + }, + { + "epoch": 0.28, + "learning_rate": 1.6964837309335553e-05, + "loss": 0.4762, + "step": 3250 + }, + { + "epoch": 0.28, + "learning_rate": 1.6962855397542215e-05, + "loss": 0.5127, + "step": 3251 + }, + { + "epoch": 0.28, + "learning_rate": 1.6960872954732457e-05, + "loss": 0.4865, + "step": 3252 + }, + { + "epoch": 0.28, + "learning_rate": 1.6958889981057467e-05, + "loss": 0.491, + "step": 3253 + }, + { + "epoch": 0.28, + "learning_rate": 1.6956906476668472e-05, + "loss": 0.4641, + "step": 3254 + }, + { + "epoch": 0.28, + "learning_rate": 1.6954922441716745e-05, + "loss": 0.4878, + "step": 3255 + }, + { + "epoch": 0.28, + "learning_rate": 1.6952937876353595e-05, + "loss": 0.4793, + "step": 3256 + }, + { + "epoch": 0.28, + "learning_rate": 1.6950952780730382e-05, + "loss": 0.4844, + "step": 3257 + }, + { + "epoch": 0.28, + "learning_rate": 1.6948967154998487e-05, + "loss": 0.4966, + "step": 3258 + }, + { + "epoch": 0.28, + "learning_rate": 1.6946980999309343e-05, + "loss": 0.4844, + "step": 3259 + }, + { + "epoch": 0.28, + "learning_rate": 1.6944994313814426e-05, + "loss": 0.479, + "step": 3260 + }, + { + "epoch": 0.28, + "learning_rate": 1.6943007098665253e-05, + "loss": 0.4874, + "step": 3261 + }, + { + "epoch": 0.28, + "learning_rate": 1.694101935401337e-05, + "loss": 0.4953, + "step": 3262 + }, + { + "epoch": 0.28, + "learning_rate": 1.693903108001037e-05, + "loss": 0.4975, + "step": 3263 + }, + { + "epoch": 0.28, + "learning_rate": 1.6937042276807893e-05, + "loss": 0.4805, + "step": 3264 + }, + { + "epoch": 0.28, + "learning_rate": 1.693505294455761e-05, + "loss": 0.501, + "step": 3265 + }, + { + "epoch": 0.28, + "learning_rate": 1.6933063083411235e-05, + "loss": 0.4984, + "step": 3266 + }, + { + "epoch": 0.28, + "learning_rate": 1.6931072693520526e-05, + "loss": 0.4855, + "step": 3267 + }, + { + "epoch": 0.28, + "learning_rate": 1.6929081775037276e-05, + "loss": 0.4861, + "step": 3268 + }, + { + "epoch": 0.28, + "learning_rate": 1.6927090328113322e-05, + "loss": 0.4887, + "step": 3269 + }, + { + "epoch": 0.28, + "learning_rate": 1.6925098352900542e-05, + "loss": 0.4748, + "step": 3270 + }, + { + "epoch": 0.28, + "learning_rate": 1.692310584955085e-05, + "loss": 0.4997, + "step": 3271 + }, + { + "epoch": 0.28, + "learning_rate": 1.69211128182162e-05, + "loss": 0.4932, + "step": 3272 + }, + { + "epoch": 0.28, + "learning_rate": 1.6919119259048592e-05, + "loss": 0.48, + "step": 3273 + }, + { + "epoch": 0.28, + "learning_rate": 1.6917125172200066e-05, + "loss": 0.4874, + "step": 3274 + }, + { + "epoch": 0.28, + "learning_rate": 1.6915130557822698e-05, + "loss": 0.5077, + "step": 3275 + }, + { + "epoch": 0.28, + "learning_rate": 1.69131354160686e-05, + "loss": 0.492, + "step": 3276 + }, + { + "epoch": 0.28, + "learning_rate": 1.6911139747089932e-05, + "loss": 0.4833, + "step": 3277 + }, + { + "epoch": 0.28, + "learning_rate": 1.6909143551038895e-05, + "loss": 0.5251, + "step": 3278 + }, + { + "epoch": 0.28, + "learning_rate": 1.690714682806773e-05, + "loss": 0.5078, + "step": 3279 + }, + { + "epoch": 0.28, + "learning_rate": 1.6905149578328705e-05, + "loss": 0.4704, + "step": 3280 + }, + { + "epoch": 0.28, + "learning_rate": 1.690315180197415e-05, + "loss": 0.5008, + "step": 3281 + }, + { + "epoch": 0.28, + "learning_rate": 1.6901153499156416e-05, + "loss": 0.4727, + "step": 3282 + }, + { + "epoch": 0.28, + "learning_rate": 1.6899154670027903e-05, + "loss": 0.4981, + "step": 3283 + }, + { + "epoch": 0.28, + "learning_rate": 1.689715531474106e-05, + "loss": 0.495, + "step": 3284 + }, + { + "epoch": 0.28, + "learning_rate": 1.689515543344835e-05, + "loss": 0.5114, + "step": 3285 + }, + { + "epoch": 0.28, + "learning_rate": 1.68931550263023e-05, + "loss": 0.4781, + "step": 3286 + }, + { + "epoch": 0.28, + "learning_rate": 1.6891154093455475e-05, + "loss": 0.5025, + "step": 3287 + }, + { + "epoch": 0.28, + "learning_rate": 1.6889152635060465e-05, + "loss": 0.4908, + "step": 3288 + }, + { + "epoch": 0.28, + "learning_rate": 1.6887150651269918e-05, + "loss": 0.488, + "step": 3289 + }, + { + "epoch": 0.28, + "learning_rate": 1.6885148142236503e-05, + "loss": 0.4975, + "step": 3290 + }, + { + "epoch": 0.28, + "learning_rate": 1.6883145108112952e-05, + "loss": 0.5117, + "step": 3291 + }, + { + "epoch": 0.28, + "learning_rate": 1.6881141549052014e-05, + "loss": 0.4794, + "step": 3292 + }, + { + "epoch": 0.28, + "learning_rate": 1.68791374652065e-05, + "loss": 0.4683, + "step": 3293 + }, + { + "epoch": 0.28, + "learning_rate": 1.6877132856729237e-05, + "loss": 0.4869, + "step": 3294 + }, + { + "epoch": 0.28, + "learning_rate": 1.6875127723773114e-05, + "loss": 0.5074, + "step": 3295 + }, + { + "epoch": 0.28, + "learning_rate": 1.6873122066491046e-05, + "loss": 0.4828, + "step": 3296 + }, + { + "epoch": 0.28, + "learning_rate": 1.6871115885035995e-05, + "loss": 0.5033, + "step": 3297 + }, + { + "epoch": 0.28, + "learning_rate": 1.686910917956096e-05, + "loss": 0.4826, + "step": 3298 + }, + { + "epoch": 0.28, + "learning_rate": 1.6867101950218988e-05, + "loss": 0.4761, + "step": 3299 + }, + { + "epoch": 0.28, + "learning_rate": 1.6865094197163147e-05, + "loss": 0.4969, + "step": 3300 + }, + { + "epoch": 0.28, + "learning_rate": 1.686308592054656e-05, + "loss": 0.5012, + "step": 3301 + }, + { + "epoch": 0.28, + "learning_rate": 1.6861077120522387e-05, + "loss": 0.4716, + "step": 3302 + }, + { + "epoch": 0.28, + "learning_rate": 1.6859067797243835e-05, + "loss": 0.4718, + "step": 3303 + }, + { + "epoch": 0.28, + "learning_rate": 1.6857057950864134e-05, + "loss": 0.496, + "step": 3304 + }, + { + "epoch": 0.28, + "learning_rate": 1.6855047581536564e-05, + "loss": 0.4991, + "step": 3305 + }, + { + "epoch": 0.28, + "learning_rate": 1.685303668941445e-05, + "loss": 0.5157, + "step": 3306 + }, + { + "epoch": 0.28, + "learning_rate": 1.6851025274651145e-05, + "loss": 0.4962, + "step": 3307 + }, + { + "epoch": 0.28, + "learning_rate": 1.684901333740005e-05, + "loss": 0.5109, + "step": 3308 + }, + { + "epoch": 0.28, + "learning_rate": 1.684700087781461e-05, + "loss": 0.4991, + "step": 3309 + }, + { + "epoch": 0.28, + "learning_rate": 1.6844987896048287e-05, + "loss": 0.5133, + "step": 3310 + }, + { + "epoch": 0.28, + "learning_rate": 1.684297439225462e-05, + "loss": 0.5138, + "step": 3311 + }, + { + "epoch": 0.28, + "learning_rate": 1.6840960366587153e-05, + "loss": 0.5017, + "step": 3312 + }, + { + "epoch": 0.28, + "learning_rate": 1.6838945819199487e-05, + "loss": 0.4928, + "step": 3313 + }, + { + "epoch": 0.28, + "learning_rate": 1.6836930750245264e-05, + "loss": 0.5162, + "step": 3314 + }, + { + "epoch": 0.28, + "learning_rate": 1.6834915159878158e-05, + "loss": 0.5044, + "step": 3315 + }, + { + "epoch": 0.28, + "learning_rate": 1.6832899048251886e-05, + "loss": 0.4886, + "step": 3316 + }, + { + "epoch": 0.28, + "learning_rate": 1.6830882415520204e-05, + "loss": 0.5142, + "step": 3317 + }, + { + "epoch": 0.28, + "learning_rate": 1.6828865261836917e-05, + "loss": 0.4797, + "step": 3318 + }, + { + "epoch": 0.28, + "learning_rate": 1.682684758735585e-05, + "loss": 0.4888, + "step": 3319 + }, + { + "epoch": 0.28, + "learning_rate": 1.6824829392230886e-05, + "loss": 0.5033, + "step": 3320 + }, + { + "epoch": 0.28, + "learning_rate": 1.682281067661594e-05, + "loss": 0.4844, + "step": 3321 + }, + { + "epoch": 0.28, + "learning_rate": 1.682079144066497e-05, + "loss": 0.4765, + "step": 3322 + }, + { + "epoch": 0.28, + "learning_rate": 1.6818771684531966e-05, + "loss": 0.4843, + "step": 3323 + }, + { + "epoch": 0.28, + "learning_rate": 1.6816751408370966e-05, + "loss": 0.4879, + "step": 3324 + }, + { + "epoch": 0.28, + "learning_rate": 1.6814730612336044e-05, + "loss": 0.4909, + "step": 3325 + }, + { + "epoch": 0.28, + "learning_rate": 1.6812709296581316e-05, + "loss": 0.4837, + "step": 3326 + }, + { + "epoch": 0.28, + "learning_rate": 1.681068746126094e-05, + "loss": 0.5073, + "step": 3327 + }, + { + "epoch": 0.28, + "learning_rate": 1.6808665106529096e-05, + "loss": 0.498, + "step": 3328 + }, + { + "epoch": 0.28, + "learning_rate": 1.680664223254003e-05, + "loss": 0.4939, + "step": 3329 + }, + { + "epoch": 0.28, + "learning_rate": 1.680461883944801e-05, + "loss": 0.4766, + "step": 3330 + }, + { + "epoch": 0.28, + "learning_rate": 1.6802594927407346e-05, + "loss": 0.4794, + "step": 3331 + }, + { + "epoch": 0.28, + "learning_rate": 1.6800570496572395e-05, + "loss": 0.4947, + "step": 3332 + }, + { + "epoch": 0.28, + "learning_rate": 1.6798545547097546e-05, + "loss": 0.5021, + "step": 3333 + }, + { + "epoch": 0.28, + "learning_rate": 1.679652007913723e-05, + "loss": 0.5078, + "step": 3334 + }, + { + "epoch": 0.28, + "learning_rate": 1.6794494092845917e-05, + "loss": 0.4695, + "step": 3335 + }, + { + "epoch": 0.28, + "learning_rate": 1.6792467588378123e-05, + "loss": 0.4843, + "step": 3336 + }, + { + "epoch": 0.28, + "learning_rate": 1.679044056588839e-05, + "loss": 0.4836, + "step": 3337 + }, + { + "epoch": 0.28, + "learning_rate": 1.678841302553131e-05, + "loss": 0.4927, + "step": 3338 + }, + { + "epoch": 0.28, + "learning_rate": 1.6786384967461512e-05, + "loss": 0.4809, + "step": 3339 + }, + { + "epoch": 0.28, + "learning_rate": 1.6784356391833665e-05, + "loss": 0.5013, + "step": 3340 + }, + { + "epoch": 0.28, + "learning_rate": 1.6782327298802474e-05, + "loss": 0.5062, + "step": 3341 + }, + { + "epoch": 0.28, + "learning_rate": 1.6780297688522692e-05, + "loss": 0.4932, + "step": 3342 + }, + { + "epoch": 0.29, + "learning_rate": 1.6778267561149097e-05, + "loss": 0.5068, + "step": 3343 + }, + { + "epoch": 0.29, + "learning_rate": 1.6776236916836518e-05, + "loss": 0.4785, + "step": 3344 + }, + { + "epoch": 0.29, + "learning_rate": 1.6774205755739824e-05, + "loss": 0.4994, + "step": 3345 + }, + { + "epoch": 0.29, + "learning_rate": 1.677217407801392e-05, + "loss": 0.5011, + "step": 3346 + }, + { + "epoch": 0.29, + "learning_rate": 1.6770141883813746e-05, + "loss": 0.5109, + "step": 3347 + }, + { + "epoch": 0.29, + "learning_rate": 1.676810917329429e-05, + "loss": 0.4878, + "step": 3348 + }, + { + "epoch": 0.29, + "learning_rate": 1.6766075946610568e-05, + "loss": 0.5155, + "step": 3349 + }, + { + "epoch": 0.29, + "learning_rate": 1.6764042203917648e-05, + "loss": 0.5219, + "step": 3350 + }, + { + "epoch": 0.29, + "learning_rate": 1.6762007945370632e-05, + "loss": 0.4882, + "step": 3351 + }, + { + "epoch": 0.29, + "learning_rate": 1.675997317112466e-05, + "loss": 0.5143, + "step": 3352 + }, + { + "epoch": 0.29, + "learning_rate": 1.675793788133491e-05, + "loss": 0.4863, + "step": 3353 + }, + { + "epoch": 0.29, + "learning_rate": 1.6755902076156606e-05, + "loss": 0.4855, + "step": 3354 + }, + { + "epoch": 0.29, + "learning_rate": 1.6753865755745e-05, + "loss": 0.4875, + "step": 3355 + }, + { + "epoch": 0.29, + "learning_rate": 1.6751828920255396e-05, + "loss": 0.4809, + "step": 3356 + }, + { + "epoch": 0.29, + "learning_rate": 1.6749791569843135e-05, + "loss": 0.4927, + "step": 3357 + }, + { + "epoch": 0.29, + "learning_rate": 1.6747753704663586e-05, + "loss": 0.4887, + "step": 3358 + }, + { + "epoch": 0.29, + "learning_rate": 1.674571532487217e-05, + "loss": 0.5156, + "step": 3359 + }, + { + "epoch": 0.29, + "learning_rate": 1.674367643062434e-05, + "loss": 0.4967, + "step": 3360 + }, + { + "epoch": 0.29, + "learning_rate": 1.6741637022075593e-05, + "loss": 0.4782, + "step": 3361 + }, + { + "epoch": 0.29, + "learning_rate": 1.6739597099381457e-05, + "loss": 0.4934, + "step": 3362 + }, + { + "epoch": 0.29, + "learning_rate": 1.6737556662697514e-05, + "loss": 0.4974, + "step": 3363 + }, + { + "epoch": 0.29, + "learning_rate": 1.673551571217937e-05, + "loss": 0.5045, + "step": 3364 + }, + { + "epoch": 0.29, + "learning_rate": 1.6733474247982675e-05, + "loss": 0.5027, + "step": 3365 + }, + { + "epoch": 0.29, + "learning_rate": 1.6731432270263126e-05, + "loss": 0.5273, + "step": 3366 + }, + { + "epoch": 0.29, + "learning_rate": 1.6729389779176446e-05, + "loss": 0.4873, + "step": 3367 + }, + { + "epoch": 0.29, + "learning_rate": 1.672734677487841e-05, + "loss": 0.4849, + "step": 3368 + }, + { + "epoch": 0.29, + "learning_rate": 1.672530325752482e-05, + "loss": 0.5023, + "step": 3369 + }, + { + "epoch": 0.29, + "learning_rate": 1.6723259227271527e-05, + "loss": 0.4888, + "step": 3370 + }, + { + "epoch": 0.29, + "learning_rate": 1.672121468427442e-05, + "loss": 0.4845, + "step": 3371 + }, + { + "epoch": 0.29, + "learning_rate": 1.671916962868942e-05, + "loss": 0.4954, + "step": 3372 + }, + { + "epoch": 0.29, + "learning_rate": 1.671712406067249e-05, + "loss": 0.5072, + "step": 3373 + }, + { + "epoch": 0.29, + "learning_rate": 1.6715077980379636e-05, + "loss": 0.4873, + "step": 3374 + }, + { + "epoch": 0.29, + "learning_rate": 1.6713031387966903e-05, + "loss": 0.4931, + "step": 3375 + }, + { + "epoch": 0.29, + "learning_rate": 1.671098428359037e-05, + "loss": 0.4837, + "step": 3376 + }, + { + "epoch": 0.29, + "learning_rate": 1.6708936667406157e-05, + "loss": 0.4901, + "step": 3377 + }, + { + "epoch": 0.29, + "learning_rate": 1.6706888539570424e-05, + "loss": 0.4878, + "step": 3378 + }, + { + "epoch": 0.29, + "learning_rate": 1.6704839900239372e-05, + "loss": 0.4936, + "step": 3379 + }, + { + "epoch": 0.29, + "learning_rate": 1.6702790749569238e-05, + "loss": 0.4809, + "step": 3380 + }, + { + "epoch": 0.29, + "learning_rate": 1.6700741087716296e-05, + "loss": 0.4792, + "step": 3381 + }, + { + "epoch": 0.29, + "learning_rate": 1.6698690914836863e-05, + "loss": 0.5043, + "step": 3382 + }, + { + "epoch": 0.29, + "learning_rate": 1.6696640231087296e-05, + "loss": 0.4839, + "step": 3383 + }, + { + "epoch": 0.29, + "learning_rate": 1.6694589036623988e-05, + "loss": 0.4919, + "step": 3384 + }, + { + "epoch": 0.29, + "learning_rate": 1.6692537331603374e-05, + "loss": 0.488, + "step": 3385 + }, + { + "epoch": 0.29, + "learning_rate": 1.6690485116181917e-05, + "loss": 0.4939, + "step": 3386 + }, + { + "epoch": 0.29, + "learning_rate": 1.6688432390516136e-05, + "loss": 0.4763, + "step": 3387 + }, + { + "epoch": 0.29, + "learning_rate": 1.6686379154762575e-05, + "loss": 0.5006, + "step": 3388 + }, + { + "epoch": 0.29, + "learning_rate": 1.668432540907783e-05, + "loss": 0.4848, + "step": 3389 + }, + { + "epoch": 0.29, + "learning_rate": 1.6682271153618517e-05, + "loss": 0.4755, + "step": 3390 + }, + { + "epoch": 0.29, + "learning_rate": 1.668021638854131e-05, + "loss": 0.5049, + "step": 3391 + }, + { + "epoch": 0.29, + "learning_rate": 1.6678161114002916e-05, + "loss": 0.5004, + "step": 3392 + }, + { + "epoch": 0.29, + "learning_rate": 1.667610533016007e-05, + "loss": 0.4785, + "step": 3393 + }, + { + "epoch": 0.29, + "learning_rate": 1.6674049037169565e-05, + "loss": 0.5055, + "step": 3394 + }, + { + "epoch": 0.29, + "learning_rate": 1.6671992235188212e-05, + "loss": 0.4771, + "step": 3395 + }, + { + "epoch": 0.29, + "learning_rate": 1.666993492437288e-05, + "loss": 0.4854, + "step": 3396 + }, + { + "epoch": 0.29, + "learning_rate": 1.666787710488046e-05, + "loss": 0.4852, + "step": 3397 + }, + { + "epoch": 0.29, + "learning_rate": 1.66658187768679e-05, + "loss": 0.5219, + "step": 3398 + }, + { + "epoch": 0.29, + "learning_rate": 1.6663759940492166e-05, + "loss": 0.494, + "step": 3399 + }, + { + "epoch": 0.29, + "learning_rate": 1.6661700595910284e-05, + "loss": 0.5, + "step": 3400 + }, + { + "epoch": 0.29, + "learning_rate": 1.66596407432793e-05, + "loss": 0.488, + "step": 3401 + }, + { + "epoch": 0.29, + "learning_rate": 1.6657580382756306e-05, + "loss": 0.4824, + "step": 3402 + }, + { + "epoch": 0.29, + "learning_rate": 1.6655519514498443e-05, + "loss": 0.4928, + "step": 3403 + }, + { + "epoch": 0.29, + "learning_rate": 1.6653458138662872e-05, + "loss": 0.4834, + "step": 3404 + }, + { + "epoch": 0.29, + "learning_rate": 1.665139625540681e-05, + "loss": 0.5008, + "step": 3405 + }, + { + "epoch": 0.29, + "learning_rate": 1.6649333864887497e-05, + "loss": 0.4711, + "step": 3406 + }, + { + "epoch": 0.29, + "learning_rate": 1.6647270967262227e-05, + "loss": 0.5186, + "step": 3407 + }, + { + "epoch": 0.29, + "learning_rate": 1.664520756268832e-05, + "loss": 0.4872, + "step": 3408 + }, + { + "epoch": 0.29, + "learning_rate": 1.664314365132314e-05, + "loss": 0.5094, + "step": 3409 + }, + { + "epoch": 0.29, + "learning_rate": 1.664107923332409e-05, + "loss": 0.4886, + "step": 3410 + }, + { + "epoch": 0.29, + "learning_rate": 1.6639014308848615e-05, + "loss": 0.5191, + "step": 3411 + }, + { + "epoch": 0.29, + "learning_rate": 1.6636948878054192e-05, + "loss": 0.5101, + "step": 3412 + }, + { + "epoch": 0.29, + "learning_rate": 1.6634882941098338e-05, + "loss": 0.4758, + "step": 3413 + }, + { + "epoch": 0.29, + "learning_rate": 1.663281649813861e-05, + "loss": 0.4911, + "step": 3414 + }, + { + "epoch": 0.29, + "learning_rate": 1.6630749549332607e-05, + "loss": 0.4835, + "step": 3415 + }, + { + "epoch": 0.29, + "learning_rate": 1.662868209483796e-05, + "loss": 0.525, + "step": 3416 + }, + { + "epoch": 0.29, + "learning_rate": 1.6626614134812337e-05, + "loss": 0.5099, + "step": 3417 + }, + { + "epoch": 0.29, + "learning_rate": 1.662454566941346e-05, + "loss": 0.496, + "step": 3418 + }, + { + "epoch": 0.29, + "learning_rate": 1.6622476698799074e-05, + "loss": 0.4779, + "step": 3419 + }, + { + "epoch": 0.29, + "learning_rate": 1.6620407223126967e-05, + "loss": 0.5078, + "step": 3420 + }, + { + "epoch": 0.29, + "learning_rate": 1.6618337242554963e-05, + "loss": 0.4936, + "step": 3421 + }, + { + "epoch": 0.29, + "learning_rate": 1.6616266757240932e-05, + "loss": 0.4719, + "step": 3422 + }, + { + "epoch": 0.29, + "learning_rate": 1.6614195767342777e-05, + "loss": 0.4843, + "step": 3423 + }, + { + "epoch": 0.29, + "learning_rate": 1.661212427301844e-05, + "loss": 0.5118, + "step": 3424 + }, + { + "epoch": 0.29, + "learning_rate": 1.6610052274425896e-05, + "loss": 0.4855, + "step": 3425 + }, + { + "epoch": 0.29, + "learning_rate": 1.6607979771723173e-05, + "loss": 0.4627, + "step": 3426 + }, + { + "epoch": 0.29, + "learning_rate": 1.6605906765068326e-05, + "loss": 0.493, + "step": 3427 + }, + { + "epoch": 0.29, + "learning_rate": 1.660383325461945e-05, + "loss": 0.5094, + "step": 3428 + }, + { + "epoch": 0.29, + "learning_rate": 1.660175924053468e-05, + "loss": 0.4907, + "step": 3429 + }, + { + "epoch": 0.29, + "learning_rate": 1.6599684722972188e-05, + "loss": 0.4962, + "step": 3430 + }, + { + "epoch": 0.29, + "learning_rate": 1.6597609702090184e-05, + "loss": 0.4804, + "step": 3431 + }, + { + "epoch": 0.29, + "learning_rate": 1.6595534178046925e-05, + "loss": 0.498, + "step": 3432 + }, + { + "epoch": 0.29, + "learning_rate": 1.659345815100069e-05, + "loss": 0.4844, + "step": 3433 + }, + { + "epoch": 0.29, + "learning_rate": 1.659138162110981e-05, + "loss": 0.5161, + "step": 3434 + }, + { + "epoch": 0.29, + "learning_rate": 1.6589304588532652e-05, + "loss": 0.4909, + "step": 3435 + }, + { + "epoch": 0.29, + "learning_rate": 1.6587227053427613e-05, + "loss": 0.4828, + "step": 3436 + }, + { + "epoch": 0.29, + "learning_rate": 1.658514901595314e-05, + "loss": 0.4675, + "step": 3437 + }, + { + "epoch": 0.29, + "learning_rate": 1.6583070476267712e-05, + "loss": 0.4981, + "step": 3438 + }, + { + "epoch": 0.29, + "learning_rate": 1.658099143452984e-05, + "loss": 0.4904, + "step": 3439 + }, + { + "epoch": 0.29, + "learning_rate": 1.6578911890898095e-05, + "loss": 0.4966, + "step": 3440 + }, + { + "epoch": 0.29, + "learning_rate": 1.6576831845531058e-05, + "loss": 0.5002, + "step": 3441 + }, + { + "epoch": 0.29, + "learning_rate": 1.657475129858737e-05, + "loss": 0.467, + "step": 3442 + }, + { + "epoch": 0.29, + "learning_rate": 1.6572670250225695e-05, + "loss": 0.4815, + "step": 3443 + }, + { + "epoch": 0.29, + "learning_rate": 1.657058870060475e-05, + "loss": 0.5161, + "step": 3444 + }, + { + "epoch": 0.29, + "learning_rate": 1.6568506649883276e-05, + "loss": 0.4943, + "step": 3445 + }, + { + "epoch": 0.29, + "learning_rate": 1.6566424098220064e-05, + "loss": 0.4995, + "step": 3446 + }, + { + "epoch": 0.29, + "learning_rate": 1.656434104577394e-05, + "loss": 0.5063, + "step": 3447 + }, + { + "epoch": 0.29, + "learning_rate": 1.6562257492703756e-05, + "loss": 0.502, + "step": 3448 + }, + { + "epoch": 0.29, + "learning_rate": 1.6560173439168427e-05, + "loss": 0.5214, + "step": 3449 + }, + { + "epoch": 0.29, + "learning_rate": 1.6558088885326874e-05, + "loss": 0.5168, + "step": 3450 + }, + { + "epoch": 0.29, + "learning_rate": 1.655600383133809e-05, + "loss": 0.4778, + "step": 3451 + }, + { + "epoch": 0.29, + "learning_rate": 1.655391827736108e-05, + "loss": 0.4999, + "step": 3452 + }, + { + "epoch": 0.29, + "learning_rate": 1.6551832223554902e-05, + "loss": 0.5022, + "step": 3453 + }, + { + "epoch": 0.29, + "learning_rate": 1.654974567007865e-05, + "loss": 0.4931, + "step": 3454 + }, + { + "epoch": 0.29, + "learning_rate": 1.654765861709144e-05, + "loss": 0.4912, + "step": 3455 + }, + { + "epoch": 0.29, + "learning_rate": 1.6545571064752454e-05, + "loss": 0.5144, + "step": 3456 + }, + { + "epoch": 0.29, + "learning_rate": 1.654348301322089e-05, + "loss": 0.4898, + "step": 3457 + }, + { + "epoch": 0.29, + "learning_rate": 1.6541394462655997e-05, + "loss": 0.4884, + "step": 3458 + }, + { + "epoch": 0.29, + "learning_rate": 1.6539305413217044e-05, + "loss": 0.5088, + "step": 3459 + }, + { + "epoch": 0.3, + "learning_rate": 1.6537215865063364e-05, + "loss": 0.4895, + "step": 3460 + }, + { + "epoch": 0.3, + "learning_rate": 1.653512581835431e-05, + "loss": 0.4874, + "step": 3461 + }, + { + "epoch": 0.3, + "learning_rate": 1.653303527324928e-05, + "loss": 0.5069, + "step": 3462 + }, + { + "epoch": 0.3, + "learning_rate": 1.6530944229907705e-05, + "loss": 0.4897, + "step": 3463 + }, + { + "epoch": 0.3, + "learning_rate": 1.6528852688489053e-05, + "loss": 0.4779, + "step": 3464 + }, + { + "epoch": 0.3, + "learning_rate": 1.6526760649152843e-05, + "loss": 0.5167, + "step": 3465 + }, + { + "epoch": 0.3, + "learning_rate": 1.6524668112058617e-05, + "loss": 0.4799, + "step": 3466 + }, + { + "epoch": 0.3, + "learning_rate": 1.6522575077365958e-05, + "loss": 0.4842, + "step": 3467 + }, + { + "epoch": 0.3, + "learning_rate": 1.6520481545234495e-05, + "loss": 0.4795, + "step": 3468 + }, + { + "epoch": 0.3, + "learning_rate": 1.6518387515823887e-05, + "loss": 0.4809, + "step": 3469 + }, + { + "epoch": 0.3, + "learning_rate": 1.6516292989293833e-05, + "loss": 0.4925, + "step": 3470 + }, + { + "epoch": 0.3, + "learning_rate": 1.651419796580407e-05, + "loss": 0.4964, + "step": 3471 + }, + { + "epoch": 0.3, + "learning_rate": 1.6512102445514376e-05, + "loss": 0.4887, + "step": 3472 + }, + { + "epoch": 0.3, + "learning_rate": 1.651000642858456e-05, + "loss": 0.5238, + "step": 3473 + }, + { + "epoch": 0.3, + "learning_rate": 1.6507909915174477e-05, + "loss": 0.4817, + "step": 3474 + }, + { + "epoch": 0.3, + "learning_rate": 1.6505812905444014e-05, + "loss": 0.5013, + "step": 3475 + }, + { + "epoch": 0.3, + "learning_rate": 1.65037153995531e-05, + "loss": 0.4895, + "step": 3476 + }, + { + "epoch": 0.3, + "learning_rate": 1.6501617397661692e-05, + "loss": 0.4759, + "step": 3477 + }, + { + "epoch": 0.3, + "learning_rate": 1.6499518899929802e-05, + "loss": 0.4935, + "step": 3478 + }, + { + "epoch": 0.3, + "learning_rate": 1.6497419906517463e-05, + "loss": 0.486, + "step": 3479 + }, + { + "epoch": 0.3, + "learning_rate": 1.649532041758476e-05, + "loss": 0.4996, + "step": 3480 + }, + { + "epoch": 0.3, + "learning_rate": 1.64932204332918e-05, + "loss": 0.4863, + "step": 3481 + }, + { + "epoch": 0.3, + "learning_rate": 1.6491119953798747e-05, + "loss": 0.4903, + "step": 3482 + }, + { + "epoch": 0.3, + "learning_rate": 1.648901897926578e-05, + "loss": 0.5104, + "step": 3483 + }, + { + "epoch": 0.3, + "learning_rate": 1.648691750985314e-05, + "loss": 0.4817, + "step": 3484 + }, + { + "epoch": 0.3, + "learning_rate": 1.6484815545721088e-05, + "loss": 0.5008, + "step": 3485 + }, + { + "epoch": 0.3, + "learning_rate": 1.6482713087029928e-05, + "loss": 0.4994, + "step": 3486 + }, + { + "epoch": 0.3, + "learning_rate": 1.6480610133940005e-05, + "loss": 0.4838, + "step": 3487 + }, + { + "epoch": 0.3, + "learning_rate": 1.6478506686611698e-05, + "loss": 0.5133, + "step": 3488 + }, + { + "epoch": 0.3, + "learning_rate": 1.647640274520542e-05, + "loss": 0.4942, + "step": 3489 + }, + { + "epoch": 0.3, + "learning_rate": 1.6474298309881634e-05, + "loss": 0.5, + "step": 3490 + }, + { + "epoch": 0.3, + "learning_rate": 1.6472193380800828e-05, + "loss": 0.4879, + "step": 3491 + }, + { + "epoch": 0.3, + "learning_rate": 1.6470087958123535e-05, + "loss": 0.4993, + "step": 3492 + }, + { + "epoch": 0.3, + "learning_rate": 1.6467982042010323e-05, + "loss": 0.4875, + "step": 3493 + }, + { + "epoch": 0.3, + "learning_rate": 1.6465875632621796e-05, + "loss": 0.5033, + "step": 3494 + }, + { + "epoch": 0.3, + "learning_rate": 1.6463768730118598e-05, + "loss": 0.5012, + "step": 3495 + }, + { + "epoch": 0.3, + "learning_rate": 1.6461661334661415e-05, + "loss": 0.5151, + "step": 3496 + }, + { + "epoch": 0.3, + "learning_rate": 1.645955344641096e-05, + "loss": 0.487, + "step": 3497 + }, + { + "epoch": 0.3, + "learning_rate": 1.645744506552799e-05, + "loss": 0.5148, + "step": 3498 + }, + { + "epoch": 0.3, + "learning_rate": 1.64553361921733e-05, + "loss": 0.4776, + "step": 3499 + }, + { + "epoch": 0.3, + "learning_rate": 1.645322682650772e-05, + "loss": 0.4748, + "step": 3500 + }, + { + "epoch": 0.3, + "learning_rate": 1.6451116968692126e-05, + "loss": 0.5111, + "step": 3501 + }, + { + "epoch": 0.3, + "learning_rate": 1.644900661888742e-05, + "loss": 0.5106, + "step": 3502 + }, + { + "epoch": 0.3, + "learning_rate": 1.6446895777254542e-05, + "loss": 0.4926, + "step": 3503 + }, + { + "epoch": 0.3, + "learning_rate": 1.644478444395448e-05, + "loss": 0.5044, + "step": 3504 + }, + { + "epoch": 0.3, + "learning_rate": 1.6442672619148248e-05, + "loss": 0.4849, + "step": 3505 + }, + { + "epoch": 0.3, + "learning_rate": 1.6440560302996903e-05, + "loss": 0.5036, + "step": 3506 + }, + { + "epoch": 0.3, + "learning_rate": 1.6438447495661543e-05, + "loss": 0.4753, + "step": 3507 + }, + { + "epoch": 0.3, + "learning_rate": 1.6436334197303298e-05, + "loss": 0.4831, + "step": 3508 + }, + { + "epoch": 0.3, + "learning_rate": 1.6434220408083334e-05, + "loss": 0.5021, + "step": 3509 + }, + { + "epoch": 0.3, + "learning_rate": 1.6432106128162862e-05, + "loss": 0.4994, + "step": 3510 + }, + { + "epoch": 0.3, + "learning_rate": 1.642999135770312e-05, + "loss": 0.5114, + "step": 3511 + }, + { + "epoch": 0.3, + "learning_rate": 1.6427876096865394e-05, + "loss": 0.4894, + "step": 3512 + }, + { + "epoch": 0.3, + "learning_rate": 1.6425760345811004e-05, + "loss": 0.4998, + "step": 3513 + }, + { + "epoch": 0.3, + "learning_rate": 1.64236441047013e-05, + "loss": 0.4815, + "step": 3514 + }, + { + "epoch": 0.3, + "learning_rate": 1.642152737369768e-05, + "loss": 0.5114, + "step": 3515 + }, + { + "epoch": 0.3, + "learning_rate": 1.641941015296157e-05, + "loss": 0.4862, + "step": 3516 + }, + { + "epoch": 0.3, + "learning_rate": 1.6417292442654445e-05, + "loss": 0.4961, + "step": 3517 + }, + { + "epoch": 0.3, + "learning_rate": 1.641517424293781e-05, + "loss": 0.4744, + "step": 3518 + }, + { + "epoch": 0.3, + "learning_rate": 1.6413055553973202e-05, + "loss": 0.5083, + "step": 3519 + }, + { + "epoch": 0.3, + "learning_rate": 1.64109363759222e-05, + "loss": 0.4926, + "step": 3520 + }, + { + "epoch": 0.3, + "learning_rate": 1.6408816708946433e-05, + "loss": 0.4868, + "step": 3521 + }, + { + "epoch": 0.3, + "learning_rate": 1.640669655320754e-05, + "loss": 0.4966, + "step": 3522 + }, + { + "epoch": 0.3, + "learning_rate": 1.6404575908867224e-05, + "loss": 0.4748, + "step": 3523 + }, + { + "epoch": 0.3, + "learning_rate": 1.6402454776087214e-05, + "loss": 0.4964, + "step": 3524 + }, + { + "epoch": 0.3, + "learning_rate": 1.640033315502927e-05, + "loss": 0.4972, + "step": 3525 + }, + { + "epoch": 0.3, + "learning_rate": 1.6398211045855198e-05, + "loss": 0.4782, + "step": 3526 + }, + { + "epoch": 0.3, + "learning_rate": 1.6396088448726838e-05, + "loss": 0.4996, + "step": 3527 + }, + { + "epoch": 0.3, + "learning_rate": 1.6393965363806075e-05, + "loss": 0.4814, + "step": 3528 + }, + { + "epoch": 0.3, + "learning_rate": 1.6391841791254818e-05, + "loss": 0.4905, + "step": 3529 + }, + { + "epoch": 0.3, + "learning_rate": 1.638971773123502e-05, + "loss": 0.4779, + "step": 3530 + }, + { + "epoch": 0.3, + "learning_rate": 1.638759318390867e-05, + "loss": 0.4976, + "step": 3531 + }, + { + "epoch": 0.3, + "learning_rate": 1.63854681494378e-05, + "loss": 0.4943, + "step": 3532 + }, + { + "epoch": 0.3, + "learning_rate": 1.638334262798447e-05, + "loss": 0.4963, + "step": 3533 + }, + { + "epoch": 0.3, + "learning_rate": 1.638121661971078e-05, + "loss": 0.4844, + "step": 3534 + }, + { + "epoch": 0.3, + "learning_rate": 1.6379090124778866e-05, + "loss": 0.4864, + "step": 3535 + }, + { + "epoch": 0.3, + "learning_rate": 1.6376963143350915e-05, + "loss": 0.513, + "step": 3536 + }, + { + "epoch": 0.3, + "learning_rate": 1.6374835675589125e-05, + "loss": 0.4849, + "step": 3537 + }, + { + "epoch": 0.3, + "learning_rate": 1.6372707721655756e-05, + "loss": 0.4988, + "step": 3538 + }, + { + "epoch": 0.3, + "learning_rate": 1.6370579281713087e-05, + "loss": 0.4798, + "step": 3539 + }, + { + "epoch": 0.3, + "learning_rate": 1.6368450355923452e-05, + "loss": 0.5126, + "step": 3540 + }, + { + "epoch": 0.3, + "learning_rate": 1.63663209444492e-05, + "loss": 0.4893, + "step": 3541 + }, + { + "epoch": 0.3, + "learning_rate": 1.6364191047452734e-05, + "loss": 0.4933, + "step": 3542 + }, + { + "epoch": 0.3, + "learning_rate": 1.6362060665096495e-05, + "loss": 0.5033, + "step": 3543 + }, + { + "epoch": 0.3, + "learning_rate": 1.6359929797542945e-05, + "loss": 0.5084, + "step": 3544 + }, + { + "epoch": 0.3, + "learning_rate": 1.6357798444954595e-05, + "loss": 0.4998, + "step": 3545 + }, + { + "epoch": 0.3, + "learning_rate": 1.6355666607493995e-05, + "loss": 0.4772, + "step": 3546 + }, + { + "epoch": 0.3, + "learning_rate": 1.6353534285323724e-05, + "loss": 0.5003, + "step": 3547 + }, + { + "epoch": 0.3, + "learning_rate": 1.6351401478606406e-05, + "loss": 0.525, + "step": 3548 + }, + { + "epoch": 0.3, + "learning_rate": 1.634926818750469e-05, + "loss": 0.4865, + "step": 3549 + }, + { + "epoch": 0.3, + "learning_rate": 1.634713441218128e-05, + "loss": 0.522, + "step": 3550 + }, + { + "epoch": 0.3, + "learning_rate": 1.6345000152798896e-05, + "loss": 0.4815, + "step": 3551 + }, + { + "epoch": 0.3, + "learning_rate": 1.6342865409520318e-05, + "loss": 0.4746, + "step": 3552 + }, + { + "epoch": 0.3, + "learning_rate": 1.6340730182508332e-05, + "loss": 0.478, + "step": 3553 + }, + { + "epoch": 0.3, + "learning_rate": 1.6338594471925802e-05, + "loss": 0.4948, + "step": 3554 + }, + { + "epoch": 0.3, + "learning_rate": 1.6336458277935586e-05, + "loss": 0.4901, + "step": 3555 + }, + { + "epoch": 0.3, + "learning_rate": 1.6334321600700612e-05, + "loss": 0.5125, + "step": 3556 + }, + { + "epoch": 0.3, + "learning_rate": 1.633218444038383e-05, + "loss": 0.5111, + "step": 3557 + }, + { + "epoch": 0.3, + "learning_rate": 1.6330046797148226e-05, + "loss": 0.4802, + "step": 3558 + }, + { + "epoch": 0.3, + "learning_rate": 1.632790867115682e-05, + "loss": 0.4846, + "step": 3559 + }, + { + "epoch": 0.3, + "learning_rate": 1.6325770062572685e-05, + "loss": 0.4837, + "step": 3560 + }, + { + "epoch": 0.3, + "learning_rate": 1.6323630971558916e-05, + "loss": 0.4755, + "step": 3561 + }, + { + "epoch": 0.3, + "learning_rate": 1.6321491398278647e-05, + "loss": 0.4795, + "step": 3562 + }, + { + "epoch": 0.3, + "learning_rate": 1.6319351342895052e-05, + "loss": 0.5012, + "step": 3563 + }, + { + "epoch": 0.3, + "learning_rate": 1.6317210805571346e-05, + "loss": 0.4958, + "step": 3564 + }, + { + "epoch": 0.3, + "learning_rate": 1.6315069786470767e-05, + "loss": 0.4693, + "step": 3565 + }, + { + "epoch": 0.3, + "learning_rate": 1.6312928285756598e-05, + "loss": 0.49, + "step": 3566 + }, + { + "epoch": 0.3, + "learning_rate": 1.631078630359217e-05, + "loss": 0.4796, + "step": 3567 + }, + { + "epoch": 0.3, + "learning_rate": 1.630864384014083e-05, + "loss": 0.482, + "step": 3568 + }, + { + "epoch": 0.3, + "learning_rate": 1.6306500895565967e-05, + "loss": 0.4931, + "step": 3569 + }, + { + "epoch": 0.3, + "learning_rate": 1.6304357470031022e-05, + "loss": 0.4933, + "step": 3570 + }, + { + "epoch": 0.3, + "learning_rate": 1.630221356369945e-05, + "loss": 0.508, + "step": 3571 + }, + { + "epoch": 0.3, + "learning_rate": 1.6300069176734768e-05, + "loss": 0.4672, + "step": 3572 + }, + { + "epoch": 0.3, + "learning_rate": 1.6297924309300506e-05, + "loss": 0.491, + "step": 3573 + }, + { + "epoch": 0.3, + "learning_rate": 1.6295778961560242e-05, + "loss": 0.4824, + "step": 3574 + }, + { + "epoch": 0.3, + "learning_rate": 1.629363313367759e-05, + "loss": 0.4777, + "step": 3575 + }, + { + "epoch": 0.3, + "learning_rate": 1.6291486825816205e-05, + "loss": 0.4988, + "step": 3576 + }, + { + "epoch": 0.3, + "learning_rate": 1.6289340038139765e-05, + "loss": 0.4955, + "step": 3577 + }, + { + "epoch": 0.31, + "learning_rate": 1.6287192770811993e-05, + "loss": 0.4794, + "step": 3578 + }, + { + "epoch": 0.31, + "learning_rate": 1.6285045023996657e-05, + "loss": 0.5035, + "step": 3579 + }, + { + "epoch": 0.31, + "learning_rate": 1.6282896797857547e-05, + "loss": 0.4896, + "step": 3580 + }, + { + "epoch": 0.31, + "learning_rate": 1.6280748092558498e-05, + "loss": 0.4828, + "step": 3581 + }, + { + "epoch": 0.31, + "learning_rate": 1.6278598908263378e-05, + "loss": 0.5032, + "step": 3582 + }, + { + "epoch": 0.31, + "learning_rate": 1.627644924513609e-05, + "loss": 0.5017, + "step": 3583 + }, + { + "epoch": 0.31, + "learning_rate": 1.627429910334058e-05, + "loss": 0.4765, + "step": 3584 + }, + { + "epoch": 0.31, + "learning_rate": 1.6272148483040827e-05, + "loss": 0.5028, + "step": 3585 + }, + { + "epoch": 0.31, + "learning_rate": 1.6269997384400845e-05, + "loss": 0.4998, + "step": 3586 + }, + { + "epoch": 0.31, + "learning_rate": 1.626784580758469e-05, + "loss": 0.4968, + "step": 3587 + }, + { + "epoch": 0.31, + "learning_rate": 1.626569375275644e-05, + "loss": 0.4755, + "step": 3588 + }, + { + "epoch": 0.31, + "learning_rate": 1.6263541220080227e-05, + "loss": 0.4764, + "step": 3589 + }, + { + "epoch": 0.31, + "learning_rate": 1.626138820972021e-05, + "loss": 0.5065, + "step": 3590 + }, + { + "epoch": 0.31, + "learning_rate": 1.6259234721840595e-05, + "loss": 0.495, + "step": 3591 + }, + { + "epoch": 0.31, + "learning_rate": 1.62570807566056e-05, + "loss": 0.491, + "step": 3592 + }, + { + "epoch": 0.31, + "learning_rate": 1.625492631417951e-05, + "loss": 0.4948, + "step": 3593 + }, + { + "epoch": 0.31, + "learning_rate": 1.6252771394726622e-05, + "loss": 0.4784, + "step": 3594 + }, + { + "epoch": 0.31, + "learning_rate": 1.6250615998411285e-05, + "loss": 0.5088, + "step": 3595 + }, + { + "epoch": 0.31, + "learning_rate": 1.6248460125397874e-05, + "loss": 0.5011, + "step": 3596 + }, + { + "epoch": 0.31, + "learning_rate": 1.6246303775850808e-05, + "loss": 0.4822, + "step": 3597 + }, + { + "epoch": 0.31, + "learning_rate": 1.624414694993454e-05, + "loss": 0.5093, + "step": 3598 + }, + { + "epoch": 0.31, + "learning_rate": 1.6241989647813557e-05, + "loss": 0.483, + "step": 3599 + }, + { + "epoch": 0.31, + "learning_rate": 1.6239831869652384e-05, + "loss": 0.49, + "step": 3600 + }, + { + "epoch": 0.31, + "learning_rate": 1.6237673615615582e-05, + "loss": 0.4917, + "step": 3601 + }, + { + "epoch": 0.31, + "learning_rate": 1.6235514885867747e-05, + "loss": 0.4939, + "step": 3602 + }, + { + "epoch": 0.31, + "learning_rate": 1.6233355680573514e-05, + "loss": 0.4759, + "step": 3603 + }, + { + "epoch": 0.31, + "learning_rate": 1.6231195999897557e-05, + "loss": 0.478, + "step": 3604 + }, + { + "epoch": 0.31, + "learning_rate": 1.6229035844004573e-05, + "loss": 0.4925, + "step": 3605 + }, + { + "epoch": 0.31, + "learning_rate": 1.6226875213059314e-05, + "loss": 0.4857, + "step": 3606 + }, + { + "epoch": 0.31, + "learning_rate": 1.6224714107226557e-05, + "loss": 0.4895, + "step": 3607 + }, + { + "epoch": 0.31, + "learning_rate": 1.622255252667111e-05, + "loss": 0.4946, + "step": 3608 + }, + { + "epoch": 0.31, + "learning_rate": 1.6220390471557832e-05, + "loss": 0.4793, + "step": 3609 + }, + { + "epoch": 0.31, + "learning_rate": 1.6218227942051606e-05, + "loss": 0.4879, + "step": 3610 + }, + { + "epoch": 0.31, + "learning_rate": 1.6216064938317356e-05, + "loss": 0.4878, + "step": 3611 + }, + { + "epoch": 0.31, + "learning_rate": 1.6213901460520047e-05, + "loss": 0.4851, + "step": 3612 + }, + { + "epoch": 0.31, + "learning_rate": 1.6211737508824662e-05, + "loss": 0.5002, + "step": 3613 + }, + { + "epoch": 0.31, + "learning_rate": 1.620957308339625e-05, + "loss": 0.4949, + "step": 3614 + }, + { + "epoch": 0.31, + "learning_rate": 1.6207408184399864e-05, + "loss": 0.5118, + "step": 3615 + }, + { + "epoch": 0.31, + "learning_rate": 1.620524281200062e-05, + "loss": 0.4867, + "step": 3616 + }, + { + "epoch": 0.31, + "learning_rate": 1.620307696636365e-05, + "loss": 0.4668, + "step": 3617 + }, + { + "epoch": 0.31, + "learning_rate": 1.6200910647654134e-05, + "loss": 0.5009, + "step": 3618 + }, + { + "epoch": 0.31, + "learning_rate": 1.6198743856037286e-05, + "loss": 0.5067, + "step": 3619 + }, + { + "epoch": 0.31, + "learning_rate": 1.619657659167835e-05, + "loss": 0.4799, + "step": 3620 + }, + { + "epoch": 0.31, + "learning_rate": 1.619440885474261e-05, + "loss": 0.4986, + "step": 3621 + }, + { + "epoch": 0.31, + "learning_rate": 1.6192240645395396e-05, + "loss": 0.496, + "step": 3622 + }, + { + "epoch": 0.31, + "learning_rate": 1.6190071963802053e-05, + "loss": 0.4957, + "step": 3623 + }, + { + "epoch": 0.31, + "learning_rate": 1.6187902810127983e-05, + "loss": 0.4783, + "step": 3624 + }, + { + "epoch": 0.31, + "learning_rate": 1.6185733184538613e-05, + "loss": 0.4985, + "step": 3625 + }, + { + "epoch": 0.31, + "learning_rate": 1.6183563087199403e-05, + "loss": 0.4847, + "step": 3626 + }, + { + "epoch": 0.31, + "learning_rate": 1.6181392518275854e-05, + "loss": 0.4997, + "step": 3627 + }, + { + "epoch": 0.31, + "learning_rate": 1.617922147793351e-05, + "loss": 0.4932, + "step": 3628 + }, + { + "epoch": 0.31, + "learning_rate": 1.6177049966337933e-05, + "loss": 0.4862, + "step": 3629 + }, + { + "epoch": 0.31, + "learning_rate": 1.617487798365474e-05, + "loss": 0.4888, + "step": 3630 + }, + { + "epoch": 0.31, + "learning_rate": 1.6172705530049575e-05, + "loss": 0.5034, + "step": 3631 + }, + { + "epoch": 0.31, + "learning_rate": 1.6170532605688115e-05, + "loss": 0.4998, + "step": 3632 + }, + { + "epoch": 0.31, + "learning_rate": 1.6168359210736072e-05, + "loss": 0.49, + "step": 3633 + }, + { + "epoch": 0.31, + "learning_rate": 1.616618534535921e-05, + "loss": 0.4929, + "step": 3634 + }, + { + "epoch": 0.31, + "learning_rate": 1.6164011009723308e-05, + "loss": 0.5037, + "step": 3635 + }, + { + "epoch": 0.31, + "learning_rate": 1.616183620399419e-05, + "loss": 0.5016, + "step": 3636 + }, + { + "epoch": 0.31, + "learning_rate": 1.6159660928337723e-05, + "loss": 0.4892, + "step": 3637 + }, + { + "epoch": 0.31, + "learning_rate": 1.6157485182919795e-05, + "loss": 0.5075, + "step": 3638 + }, + { + "epoch": 0.31, + "learning_rate": 1.6155308967906344e-05, + "loss": 0.5042, + "step": 3639 + }, + { + "epoch": 0.31, + "learning_rate": 1.6153132283463327e-05, + "loss": 0.4821, + "step": 3640 + }, + { + "epoch": 0.31, + "learning_rate": 1.615095512975676e-05, + "loss": 0.4871, + "step": 3641 + }, + { + "epoch": 0.31, + "learning_rate": 1.6148777506952672e-05, + "loss": 0.4873, + "step": 3642 + }, + { + "epoch": 0.31, + "learning_rate": 1.614659941521714e-05, + "loss": 0.4749, + "step": 3643 + }, + { + "epoch": 0.31, + "learning_rate": 1.6144420854716277e-05, + "loss": 0.5205, + "step": 3644 + }, + { + "epoch": 0.31, + "learning_rate": 1.6142241825616226e-05, + "loss": 0.5013, + "step": 3645 + }, + { + "epoch": 0.31, + "learning_rate": 1.614006232808317e-05, + "loss": 0.4808, + "step": 3646 + }, + { + "epoch": 0.31, + "learning_rate": 1.6137882362283328e-05, + "loss": 0.4791, + "step": 3647 + }, + { + "epoch": 0.31, + "learning_rate": 1.6135701928382952e-05, + "loss": 0.5009, + "step": 3648 + }, + { + "epoch": 0.31, + "learning_rate": 1.613352102654833e-05, + "loss": 0.499, + "step": 3649 + }, + { + "epoch": 0.31, + "learning_rate": 1.613133965694579e-05, + "loss": 0.5008, + "step": 3650 + }, + { + "epoch": 0.31, + "learning_rate": 1.6129157819741692e-05, + "loss": 0.4856, + "step": 3651 + }, + { + "epoch": 0.31, + "learning_rate": 1.6126975515102424e-05, + "loss": 0.4889, + "step": 3652 + }, + { + "epoch": 0.31, + "learning_rate": 1.612479274319443e-05, + "loss": 0.4982, + "step": 3653 + }, + { + "epoch": 0.31, + "learning_rate": 1.6122609504184166e-05, + "loss": 0.4844, + "step": 3654 + }, + { + "epoch": 0.31, + "learning_rate": 1.6120425798238145e-05, + "loss": 0.5086, + "step": 3655 + }, + { + "epoch": 0.31, + "learning_rate": 1.6118241625522898e-05, + "loss": 0.4755, + "step": 3656 + }, + { + "epoch": 0.31, + "learning_rate": 1.6116056986205003e-05, + "loss": 0.5097, + "step": 3657 + }, + { + "epoch": 0.31, + "learning_rate": 1.6113871880451062e-05, + "loss": 0.4937, + "step": 3658 + }, + { + "epoch": 0.31, + "learning_rate": 1.6111686308427734e-05, + "loss": 0.4724, + "step": 3659 + }, + { + "epoch": 0.31, + "learning_rate": 1.6109500270301694e-05, + "loss": 0.4936, + "step": 3660 + }, + { + "epoch": 0.31, + "learning_rate": 1.610731376623965e-05, + "loss": 0.4695, + "step": 3661 + }, + { + "epoch": 0.31, + "learning_rate": 1.6105126796408367e-05, + "loss": 0.486, + "step": 3662 + }, + { + "epoch": 0.31, + "learning_rate": 1.610293936097462e-05, + "loss": 0.4706, + "step": 3663 + }, + { + "epoch": 0.31, + "learning_rate": 1.6100751460105244e-05, + "loss": 0.5029, + "step": 3664 + }, + { + "epoch": 0.31, + "learning_rate": 1.609856309396709e-05, + "loss": 0.5005, + "step": 3665 + }, + { + "epoch": 0.31, + "learning_rate": 1.6096374262727055e-05, + "loss": 0.5134, + "step": 3666 + }, + { + "epoch": 0.31, + "learning_rate": 1.6094184966552066e-05, + "loss": 0.4935, + "step": 3667 + }, + { + "epoch": 0.31, + "learning_rate": 1.609199520560909e-05, + "loss": 0.5092, + "step": 3668 + }, + { + "epoch": 0.31, + "learning_rate": 1.6089804980065124e-05, + "loss": 0.4606, + "step": 3669 + }, + { + "epoch": 0.31, + "learning_rate": 1.608761429008721e-05, + "loss": 0.4868, + "step": 3670 + }, + { + "epoch": 0.31, + "learning_rate": 1.608542313584241e-05, + "loss": 0.507, + "step": 3671 + }, + { + "epoch": 0.31, + "learning_rate": 1.608323151749784e-05, + "loss": 0.4625, + "step": 3672 + }, + { + "epoch": 0.31, + "learning_rate": 1.6081039435220637e-05, + "loss": 0.4879, + "step": 3673 + }, + { + "epoch": 0.31, + "learning_rate": 1.6078846889177978e-05, + "loss": 0.4934, + "step": 3674 + }, + { + "epoch": 0.31, + "learning_rate": 1.6076653879537074e-05, + "loss": 0.4729, + "step": 3675 + }, + { + "epoch": 0.31, + "learning_rate": 1.607446040646518e-05, + "loss": 0.4885, + "step": 3676 + }, + { + "epoch": 0.31, + "learning_rate": 1.6072266470129573e-05, + "loss": 0.4832, + "step": 3677 + }, + { + "epoch": 0.31, + "learning_rate": 1.607007207069758e-05, + "loss": 0.4898, + "step": 3678 + }, + { + "epoch": 0.31, + "learning_rate": 1.606787720833654e-05, + "loss": 0.4948, + "step": 3679 + }, + { + "epoch": 0.31, + "learning_rate": 1.6065681883213854e-05, + "loss": 0.5241, + "step": 3680 + }, + { + "epoch": 0.31, + "learning_rate": 1.606348609549695e-05, + "loss": 0.4878, + "step": 3681 + }, + { + "epoch": 0.31, + "learning_rate": 1.6061289845353276e-05, + "loss": 0.5015, + "step": 3682 + }, + { + "epoch": 0.31, + "learning_rate": 1.6059093132950336e-05, + "loss": 0.4908, + "step": 3683 + }, + { + "epoch": 0.31, + "learning_rate": 1.6056895958455657e-05, + "loss": 0.4874, + "step": 3684 + }, + { + "epoch": 0.31, + "learning_rate": 1.6054698322036806e-05, + "loss": 0.4719, + "step": 3685 + }, + { + "epoch": 0.31, + "learning_rate": 1.605250022386138e-05, + "loss": 0.496, + "step": 3686 + }, + { + "epoch": 0.31, + "learning_rate": 1.6050301664097023e-05, + "loss": 0.4999, + "step": 3687 + }, + { + "epoch": 0.31, + "learning_rate": 1.60481026429114e-05, + "loss": 0.5015, + "step": 3688 + }, + { + "epoch": 0.31, + "learning_rate": 1.6045903160472218e-05, + "loss": 0.5052, + "step": 3689 + }, + { + "epoch": 0.31, + "learning_rate": 1.6043703216947223e-05, + "loss": 0.4962, + "step": 3690 + }, + { + "epoch": 0.31, + "learning_rate": 1.6041502812504185e-05, + "loss": 0.457, + "step": 3691 + }, + { + "epoch": 0.31, + "learning_rate": 1.6039301947310925e-05, + "loss": 0.5011, + "step": 3692 + }, + { + "epoch": 0.31, + "learning_rate": 1.6037100621535283e-05, + "loss": 0.5002, + "step": 3693 + }, + { + "epoch": 0.31, + "learning_rate": 1.6034898835345142e-05, + "loss": 0.4836, + "step": 3694 + }, + { + "epoch": 0.32, + "learning_rate": 1.603269658890842e-05, + "loss": 0.476, + "step": 3695 + }, + { + "epoch": 0.32, + "learning_rate": 1.6030493882393076e-05, + "loss": 0.4848, + "step": 3696 + }, + { + "epoch": 0.32, + "learning_rate": 1.6028290715967087e-05, + "loss": 0.4908, + "step": 3697 + }, + { + "epoch": 0.32, + "learning_rate": 1.6026087089798483e-05, + "loss": 0.4754, + "step": 3698 + }, + { + "epoch": 0.32, + "learning_rate": 1.6023883004055317e-05, + "loss": 0.488, + "step": 3699 + }, + { + "epoch": 0.32, + "learning_rate": 1.6021678458905686e-05, + "loss": 0.46, + "step": 3700 + }, + { + "epoch": 0.32, + "learning_rate": 1.6019473454517714e-05, + "loss": 0.4774, + "step": 3701 + }, + { + "epoch": 0.32, + "learning_rate": 1.601726799105957e-05, + "loss": 0.4765, + "step": 3702 + }, + { + "epoch": 0.32, + "learning_rate": 1.6015062068699445e-05, + "loss": 0.503, + "step": 3703 + }, + { + "epoch": 0.32, + "learning_rate": 1.6012855687605572e-05, + "loss": 0.4927, + "step": 3704 + }, + { + "epoch": 0.32, + "learning_rate": 1.6010648847946225e-05, + "loss": 0.484, + "step": 3705 + }, + { + "epoch": 0.32, + "learning_rate": 1.6008441549889703e-05, + "loss": 0.5042, + "step": 3706 + }, + { + "epoch": 0.32, + "learning_rate": 1.600623379360434e-05, + "loss": 0.4921, + "step": 3707 + }, + { + "epoch": 0.32, + "learning_rate": 1.6004025579258517e-05, + "loss": 0.477, + "step": 3708 + }, + { + "epoch": 0.32, + "learning_rate": 1.6001816907020634e-05, + "loss": 0.4729, + "step": 3709 + }, + { + "epoch": 0.32, + "learning_rate": 1.599960777705914e-05, + "loss": 0.4977, + "step": 3710 + }, + { + "epoch": 0.32, + "learning_rate": 1.599739818954251e-05, + "loss": 0.4643, + "step": 3711 + }, + { + "epoch": 0.32, + "learning_rate": 1.599518814463925e-05, + "loss": 0.5209, + "step": 3712 + }, + { + "epoch": 0.32, + "learning_rate": 1.599297764251792e-05, + "loss": 0.494, + "step": 3713 + }, + { + "epoch": 0.32, + "learning_rate": 1.599076668334709e-05, + "loss": 0.4945, + "step": 3714 + }, + { + "epoch": 0.32, + "learning_rate": 1.5988555267295383e-05, + "loss": 0.4985, + "step": 3715 + }, + { + "epoch": 0.32, + "learning_rate": 1.598634339453145e-05, + "loss": 0.4985, + "step": 3716 + }, + { + "epoch": 0.32, + "learning_rate": 1.598413106522398e-05, + "loss": 0.4818, + "step": 3717 + }, + { + "epoch": 0.32, + "learning_rate": 1.598191827954169e-05, + "loss": 0.4968, + "step": 3718 + }, + { + "epoch": 0.32, + "learning_rate": 1.5979705037653338e-05, + "loss": 0.4894, + "step": 3719 + }, + { + "epoch": 0.32, + "learning_rate": 1.5977491339727716e-05, + "loss": 0.489, + "step": 3720 + }, + { + "epoch": 0.32, + "learning_rate": 1.597527718593365e-05, + "loss": 0.4743, + "step": 3721 + }, + { + "epoch": 0.32, + "learning_rate": 1.5973062576439996e-05, + "loss": 0.4853, + "step": 3722 + }, + { + "epoch": 0.32, + "learning_rate": 1.5970847511415656e-05, + "loss": 0.4798, + "step": 3723 + }, + { + "epoch": 0.32, + "learning_rate": 1.5968631991029554e-05, + "loss": 0.4723, + "step": 3724 + }, + { + "epoch": 0.32, + "learning_rate": 1.5966416015450664e-05, + "loss": 0.4883, + "step": 3725 + }, + { + "epoch": 0.32, + "learning_rate": 1.5964199584847975e-05, + "loss": 0.5237, + "step": 3726 + }, + { + "epoch": 0.32, + "learning_rate": 1.596198269939053e-05, + "loss": 0.4902, + "step": 3727 + }, + { + "epoch": 0.32, + "learning_rate": 1.595976535924739e-05, + "loss": 0.4902, + "step": 3728 + }, + { + "epoch": 0.32, + "learning_rate": 1.5957547564587662e-05, + "loss": 0.4797, + "step": 3729 + }, + { + "epoch": 0.32, + "learning_rate": 1.5955329315580487e-05, + "loss": 0.4649, + "step": 3730 + }, + { + "epoch": 0.32, + "learning_rate": 1.5953110612395035e-05, + "loss": 0.4917, + "step": 3731 + }, + { + "epoch": 0.32, + "learning_rate": 1.5950891455200516e-05, + "loss": 0.4746, + "step": 3732 + }, + { + "epoch": 0.32, + "learning_rate": 1.5948671844166167e-05, + "loss": 0.5044, + "step": 3733 + }, + { + "epoch": 0.32, + "learning_rate": 1.594645177946127e-05, + "loss": 0.4792, + "step": 3734 + }, + { + "epoch": 0.32, + "learning_rate": 1.5944231261255133e-05, + "loss": 0.465, + "step": 3735 + }, + { + "epoch": 0.32, + "learning_rate": 1.5942010289717108e-05, + "loss": 0.4843, + "step": 3736 + }, + { + "epoch": 0.32, + "learning_rate": 1.5939788865016565e-05, + "loss": 0.4572, + "step": 3737 + }, + { + "epoch": 0.32, + "learning_rate": 1.593756698732293e-05, + "loss": 0.4975, + "step": 3738 + }, + { + "epoch": 0.32, + "learning_rate": 1.5935344656805648e-05, + "loss": 0.5064, + "step": 3739 + }, + { + "epoch": 0.32, + "learning_rate": 1.5933121873634202e-05, + "loss": 0.5028, + "step": 3740 + }, + { + "epoch": 0.32, + "learning_rate": 1.593089863797811e-05, + "loss": 0.4851, + "step": 3741 + }, + { + "epoch": 0.32, + "learning_rate": 1.5928674950006927e-05, + "loss": 0.4951, + "step": 3742 + }, + { + "epoch": 0.32, + "learning_rate": 1.5926450809890245e-05, + "loss": 0.4764, + "step": 3743 + }, + { + "epoch": 0.32, + "learning_rate": 1.5924226217797677e-05, + "loss": 0.4835, + "step": 3744 + }, + { + "epoch": 0.32, + "learning_rate": 1.592200117389889e-05, + "loss": 0.4897, + "step": 3745 + }, + { + "epoch": 0.32, + "learning_rate": 1.5919775678363566e-05, + "loss": 0.4965, + "step": 3746 + }, + { + "epoch": 0.32, + "learning_rate": 1.5917549731361435e-05, + "loss": 0.4869, + "step": 3747 + }, + { + "epoch": 0.32, + "learning_rate": 1.5915323333062255e-05, + "loss": 0.4887, + "step": 3748 + }, + { + "epoch": 0.32, + "learning_rate": 1.5913096483635827e-05, + "loss": 0.4933, + "step": 3749 + }, + { + "epoch": 0.32, + "learning_rate": 1.591086918325197e-05, + "loss": 0.4755, + "step": 3750 + }, + { + "epoch": 0.32, + "learning_rate": 1.590864143208055e-05, + "loss": 0.4755, + "step": 3751 + }, + { + "epoch": 0.32, + "learning_rate": 1.5906413230291473e-05, + "loss": 0.4885, + "step": 3752 + }, + { + "epoch": 0.32, + "learning_rate": 1.5904184578054662e-05, + "loss": 0.4608, + "step": 3753 + }, + { + "epoch": 0.32, + "learning_rate": 1.5901955475540087e-05, + "loss": 0.5046, + "step": 3754 + }, + { + "epoch": 0.32, + "learning_rate": 1.5899725922917743e-05, + "loss": 0.4864, + "step": 3755 + }, + { + "epoch": 0.32, + "learning_rate": 1.5897495920357673e-05, + "loss": 0.483, + "step": 3756 + }, + { + "epoch": 0.32, + "learning_rate": 1.5895265468029943e-05, + "loss": 0.4855, + "step": 3757 + }, + { + "epoch": 0.32, + "learning_rate": 1.5893034566104656e-05, + "loss": 0.4861, + "step": 3758 + }, + { + "epoch": 0.32, + "learning_rate": 1.589080321475195e-05, + "loss": 0.4826, + "step": 3759 + }, + { + "epoch": 0.32, + "learning_rate": 1.5888571414141997e-05, + "loss": 0.488, + "step": 3760 + }, + { + "epoch": 0.32, + "learning_rate": 1.5886339164445007e-05, + "loss": 0.4954, + "step": 3761 + }, + { + "epoch": 0.32, + "learning_rate": 1.588410646583121e-05, + "loss": 0.4711, + "step": 3762 + }, + { + "epoch": 0.32, + "learning_rate": 1.5881873318470894e-05, + "loss": 0.469, + "step": 3763 + }, + { + "epoch": 0.32, + "learning_rate": 1.5879639722534364e-05, + "loss": 0.4839, + "step": 3764 + }, + { + "epoch": 0.32, + "learning_rate": 1.587740567819196e-05, + "loss": 0.4974, + "step": 3765 + }, + { + "epoch": 0.32, + "learning_rate": 1.587517118561406e-05, + "loss": 0.4736, + "step": 3766 + }, + { + "epoch": 0.32, + "learning_rate": 1.5872936244971083e-05, + "loss": 0.4785, + "step": 3767 + }, + { + "epoch": 0.32, + "learning_rate": 1.587070085643346e-05, + "loss": 0.488, + "step": 3768 + }, + { + "epoch": 0.32, + "learning_rate": 1.586846502017169e-05, + "loss": 0.4923, + "step": 3769 + }, + { + "epoch": 0.32, + "learning_rate": 1.5866228736356272e-05, + "loss": 0.4879, + "step": 3770 + }, + { + "epoch": 0.32, + "learning_rate": 1.5863992005157757e-05, + "loss": 0.4867, + "step": 3771 + }, + { + "epoch": 0.32, + "learning_rate": 1.5861754826746737e-05, + "loss": 0.5033, + "step": 3772 + }, + { + "epoch": 0.32, + "learning_rate": 1.585951720129382e-05, + "loss": 0.5014, + "step": 3773 + }, + { + "epoch": 0.32, + "learning_rate": 1.5857279128969657e-05, + "loss": 0.5109, + "step": 3774 + }, + { + "epoch": 0.32, + "learning_rate": 1.5855040609944935e-05, + "loss": 0.4924, + "step": 3775 + }, + { + "epoch": 0.32, + "learning_rate": 1.585280164439037e-05, + "loss": 0.4881, + "step": 3776 + }, + { + "epoch": 0.32, + "learning_rate": 1.585056223247672e-05, + "loss": 0.4854, + "step": 3777 + }, + { + "epoch": 0.32, + "learning_rate": 1.5848322374374765e-05, + "loss": 0.4924, + "step": 3778 + }, + { + "epoch": 0.32, + "learning_rate": 1.584608207025533e-05, + "loss": 0.4819, + "step": 3779 + }, + { + "epoch": 0.32, + "learning_rate": 1.5843841320289274e-05, + "loss": 0.485, + "step": 3780 + }, + { + "epoch": 0.32, + "learning_rate": 1.584160012464748e-05, + "loss": 0.5159, + "step": 3781 + }, + { + "epoch": 0.32, + "learning_rate": 1.583935848350087e-05, + "loss": 0.49, + "step": 3782 + }, + { + "epoch": 0.32, + "learning_rate": 1.5837116397020404e-05, + "loss": 0.4697, + "step": 3783 + }, + { + "epoch": 0.32, + "learning_rate": 1.5834873865377075e-05, + "loss": 0.5186, + "step": 3784 + }, + { + "epoch": 0.32, + "learning_rate": 1.5832630888741904e-05, + "loss": 0.4818, + "step": 3785 + }, + { + "epoch": 0.32, + "learning_rate": 1.583038746728595e-05, + "loss": 0.4848, + "step": 3786 + }, + { + "epoch": 0.32, + "learning_rate": 1.5828143601180306e-05, + "loss": 0.4849, + "step": 3787 + }, + { + "epoch": 0.32, + "learning_rate": 1.58258992905961e-05, + "loss": 0.5068, + "step": 3788 + }, + { + "epoch": 0.32, + "learning_rate": 1.582365453570449e-05, + "loss": 0.4916, + "step": 3789 + }, + { + "epoch": 0.32, + "learning_rate": 1.5821409336676676e-05, + "loss": 0.5017, + "step": 3790 + }, + { + "epoch": 0.32, + "learning_rate": 1.581916369368388e-05, + "loss": 0.4922, + "step": 3791 + }, + { + "epoch": 0.32, + "learning_rate": 1.581691760689737e-05, + "loss": 0.4639, + "step": 3792 + }, + { + "epoch": 0.32, + "learning_rate": 1.5814671076488434e-05, + "loss": 0.4832, + "step": 3793 + }, + { + "epoch": 0.32, + "learning_rate": 1.5812424102628406e-05, + "loss": 0.4823, + "step": 3794 + }, + { + "epoch": 0.32, + "learning_rate": 1.5810176685488654e-05, + "loss": 0.494, + "step": 3795 + }, + { + "epoch": 0.32, + "learning_rate": 1.5807928825240566e-05, + "loss": 0.4719, + "step": 3796 + }, + { + "epoch": 0.32, + "learning_rate": 1.5805680522055583e-05, + "loss": 0.4876, + "step": 3797 + }, + { + "epoch": 0.32, + "learning_rate": 1.5803431776105163e-05, + "loss": 0.4833, + "step": 3798 + }, + { + "epoch": 0.32, + "learning_rate": 1.5801182587560807e-05, + "loss": 0.4926, + "step": 3799 + }, + { + "epoch": 0.32, + "learning_rate": 1.579893295659405e-05, + "loss": 0.4871, + "step": 3800 + }, + { + "epoch": 0.32, + "learning_rate": 1.5796682883376453e-05, + "loss": 0.4909, + "step": 3801 + }, + { + "epoch": 0.32, + "learning_rate": 1.5794432368079617e-05, + "loss": 0.4862, + "step": 3802 + }, + { + "epoch": 0.32, + "learning_rate": 1.579218141087518e-05, + "loss": 0.5013, + "step": 3803 + }, + { + "epoch": 0.32, + "learning_rate": 1.5789930011934808e-05, + "loss": 0.4783, + "step": 3804 + }, + { + "epoch": 0.32, + "learning_rate": 1.57876781714302e-05, + "loss": 0.4821, + "step": 3805 + }, + { + "epoch": 0.32, + "learning_rate": 1.5785425889533094e-05, + "loss": 0.4831, + "step": 3806 + }, + { + "epoch": 0.32, + "learning_rate": 1.5783173166415253e-05, + "loss": 0.5084, + "step": 3807 + }, + { + "epoch": 0.32, + "learning_rate": 1.5780920002248484e-05, + "loss": 0.485, + "step": 3808 + }, + { + "epoch": 0.32, + "learning_rate": 1.5778666397204624e-05, + "loss": 0.4889, + "step": 3809 + }, + { + "epoch": 0.32, + "learning_rate": 1.5776412351455535e-05, + "loss": 0.5132, + "step": 3810 + }, + { + "epoch": 0.32, + "learning_rate": 1.5774157865173125e-05, + "loss": 0.4819, + "step": 3811 + }, + { + "epoch": 0.33, + "learning_rate": 1.577190293852933e-05, + "loss": 0.4774, + "step": 3812 + }, + { + "epoch": 0.33, + "learning_rate": 1.576964757169612e-05, + "loss": 0.4941, + "step": 3813 + }, + { + "epoch": 0.33, + "learning_rate": 1.5767391764845503e-05, + "loss": 0.4906, + "step": 3814 + }, + { + "epoch": 0.33, + "learning_rate": 1.5765135518149503e-05, + "loss": 0.4859, + "step": 3815 + }, + { + "epoch": 0.33, + "learning_rate": 1.5762878831780206e-05, + "loss": 0.4941, + "step": 3816 + }, + { + "epoch": 0.33, + "learning_rate": 1.5760621705909706e-05, + "loss": 0.4812, + "step": 3817 + }, + { + "epoch": 0.33, + "learning_rate": 1.575836414071015e-05, + "loss": 0.4954, + "step": 3818 + }, + { + "epoch": 0.33, + "learning_rate": 1.57561061363537e-05, + "loss": 0.4723, + "step": 3819 + }, + { + "epoch": 0.33, + "learning_rate": 1.5753847693012566e-05, + "loss": 0.4967, + "step": 3820 + }, + { + "epoch": 0.33, + "learning_rate": 1.5751588810858986e-05, + "loss": 0.4882, + "step": 3821 + }, + { + "epoch": 0.33, + "learning_rate": 1.574932949006523e-05, + "loss": 0.491, + "step": 3822 + }, + { + "epoch": 0.33, + "learning_rate": 1.5747069730803607e-05, + "loss": 0.4762, + "step": 3823 + }, + { + "epoch": 0.33, + "learning_rate": 1.574480953324645e-05, + "loss": 0.4798, + "step": 3824 + }, + { + "epoch": 0.33, + "learning_rate": 1.5742548897566135e-05, + "loss": 0.4884, + "step": 3825 + }, + { + "epoch": 0.33, + "learning_rate": 1.5740287823935067e-05, + "loss": 0.495, + "step": 3826 + }, + { + "epoch": 0.33, + "learning_rate": 1.5738026312525686e-05, + "loss": 0.4671, + "step": 3827 + }, + { + "epoch": 0.33, + "learning_rate": 1.573576436351046e-05, + "loss": 0.4837, + "step": 3828 + }, + { + "epoch": 0.33, + "learning_rate": 1.5733501977061904e-05, + "loss": 0.4931, + "step": 3829 + }, + { + "epoch": 0.33, + "learning_rate": 1.5731239153352543e-05, + "loss": 0.5012, + "step": 3830 + }, + { + "epoch": 0.33, + "learning_rate": 1.5728975892554957e-05, + "loss": 0.4917, + "step": 3831 + }, + { + "epoch": 0.33, + "learning_rate": 1.5726712194841758e-05, + "loss": 0.4935, + "step": 3832 + }, + { + "epoch": 0.33, + "learning_rate": 1.5724448060385574e-05, + "loss": 0.4869, + "step": 3833 + }, + { + "epoch": 0.33, + "learning_rate": 1.5722183489359082e-05, + "loss": 0.5089, + "step": 3834 + }, + { + "epoch": 0.33, + "learning_rate": 1.571991848193499e-05, + "loss": 0.4933, + "step": 3835 + }, + { + "epoch": 0.33, + "learning_rate": 1.5717653038286033e-05, + "loss": 0.4931, + "step": 3836 + }, + { + "epoch": 0.33, + "learning_rate": 1.5715387158584988e-05, + "loss": 0.4985, + "step": 3837 + }, + { + "epoch": 0.33, + "learning_rate": 1.5713120843004653e-05, + "loss": 0.4829, + "step": 3838 + }, + { + "epoch": 0.33, + "learning_rate": 1.5710854091717873e-05, + "loss": 0.4974, + "step": 3839 + }, + { + "epoch": 0.33, + "learning_rate": 1.5708586904897518e-05, + "loss": 0.4771, + "step": 3840 + }, + { + "epoch": 0.33, + "learning_rate": 1.5706319282716492e-05, + "loss": 0.4747, + "step": 3841 + }, + { + "epoch": 0.33, + "learning_rate": 1.5704051225347732e-05, + "loss": 0.5035, + "step": 3842 + }, + { + "epoch": 0.33, + "learning_rate": 1.5701782732964216e-05, + "loss": 0.4963, + "step": 3843 + }, + { + "epoch": 0.33, + "learning_rate": 1.5699513805738942e-05, + "loss": 0.4695, + "step": 3844 + }, + { + "epoch": 0.33, + "learning_rate": 1.5697244443844952e-05, + "loss": 0.4937, + "step": 3845 + }, + { + "epoch": 0.33, + "learning_rate": 1.5694974647455315e-05, + "loss": 0.4881, + "step": 3846 + }, + { + "epoch": 0.33, + "learning_rate": 1.5692704416743138e-05, + "loss": 0.4957, + "step": 3847 + }, + { + "epoch": 0.33, + "learning_rate": 1.569043375188155e-05, + "loss": 0.4859, + "step": 3848 + }, + { + "epoch": 0.33, + "learning_rate": 1.568816265304373e-05, + "loss": 0.4806, + "step": 3849 + }, + { + "epoch": 0.33, + "learning_rate": 1.568589112040288e-05, + "loss": 0.4801, + "step": 3850 + }, + { + "epoch": 0.33, + "learning_rate": 1.5683619154132236e-05, + "loss": 0.5217, + "step": 3851 + }, + { + "epoch": 0.33, + "learning_rate": 1.5681346754405064e-05, + "loss": 0.5026, + "step": 3852 + }, + { + "epoch": 0.33, + "learning_rate": 1.567907392139467e-05, + "loss": 0.4715, + "step": 3853 + }, + { + "epoch": 0.33, + "learning_rate": 1.5676800655274394e-05, + "loss": 0.48, + "step": 3854 + }, + { + "epoch": 0.33, + "learning_rate": 1.5674526956217596e-05, + "loss": 0.5089, + "step": 3855 + }, + { + "epoch": 0.33, + "learning_rate": 1.5672252824397683e-05, + "loss": 0.4783, + "step": 3856 + }, + { + "epoch": 0.33, + "learning_rate": 1.5669978259988087e-05, + "loss": 0.4678, + "step": 3857 + }, + { + "epoch": 0.33, + "learning_rate": 1.566770326316228e-05, + "loss": 0.4978, + "step": 3858 + }, + { + "epoch": 0.33, + "learning_rate": 1.5665427834093755e-05, + "loss": 0.4806, + "step": 3859 + }, + { + "epoch": 0.33, + "learning_rate": 1.5663151972956055e-05, + "loss": 0.4989, + "step": 3860 + }, + { + "epoch": 0.33, + "learning_rate": 1.566087567992274e-05, + "loss": 0.4873, + "step": 3861 + }, + { + "epoch": 0.33, + "learning_rate": 1.565859895516742e-05, + "loss": 0.4932, + "step": 3862 + }, + { + "epoch": 0.33, + "learning_rate": 1.565632179886371e-05, + "loss": 0.4853, + "step": 3863 + }, + { + "epoch": 0.33, + "learning_rate": 1.565404421118529e-05, + "loss": 0.4998, + "step": 3864 + }, + { + "epoch": 0.33, + "learning_rate": 1.5651766192305853e-05, + "loss": 0.4937, + "step": 3865 + }, + { + "epoch": 0.33, + "learning_rate": 1.564948774239913e-05, + "loss": 0.4985, + "step": 3866 + }, + { + "epoch": 0.33, + "learning_rate": 1.564720886163889e-05, + "loss": 0.4887, + "step": 3867 + }, + { + "epoch": 0.33, + "learning_rate": 1.564492955019892e-05, + "loss": 0.4811, + "step": 3868 + }, + { + "epoch": 0.33, + "learning_rate": 1.5642649808253057e-05, + "loss": 0.4725, + "step": 3869 + }, + { + "epoch": 0.33, + "learning_rate": 1.5640369635975165e-05, + "loss": 0.467, + "step": 3870 + }, + { + "epoch": 0.33, + "learning_rate": 1.5638089033539135e-05, + "loss": 0.4945, + "step": 3871 + }, + { + "epoch": 0.33, + "learning_rate": 1.56358080011189e-05, + "loss": 0.4852, + "step": 3872 + }, + { + "epoch": 0.33, + "learning_rate": 1.5633526538888412e-05, + "loss": 0.4932, + "step": 3873 + }, + { + "epoch": 0.33, + "learning_rate": 1.5631244647021672e-05, + "loss": 0.5103, + "step": 3874 + }, + { + "epoch": 0.33, + "learning_rate": 1.5628962325692708e-05, + "loss": 0.5069, + "step": 3875 + }, + { + "epoch": 0.33, + "learning_rate": 1.5626679575075577e-05, + "loss": 0.4724, + "step": 3876 + }, + { + "epoch": 0.33, + "learning_rate": 1.562439639534437e-05, + "loss": 0.4954, + "step": 3877 + }, + { + "epoch": 0.33, + "learning_rate": 1.5622112786673214e-05, + "loss": 0.5119, + "step": 3878 + }, + { + "epoch": 0.33, + "learning_rate": 1.561982874923626e-05, + "loss": 0.5031, + "step": 3879 + }, + { + "epoch": 0.33, + "learning_rate": 1.561754428320771e-05, + "loss": 0.4851, + "step": 3880 + }, + { + "epoch": 0.33, + "learning_rate": 1.5615259388761777e-05, + "loss": 0.4732, + "step": 3881 + }, + { + "epoch": 0.33, + "learning_rate": 1.561297406607272e-05, + "loss": 0.4796, + "step": 3882 + }, + { + "epoch": 0.33, + "learning_rate": 1.561068831531483e-05, + "loss": 0.471, + "step": 3883 + }, + { + "epoch": 0.33, + "learning_rate": 1.5608402136662423e-05, + "loss": 0.4978, + "step": 3884 + }, + { + "epoch": 0.33, + "learning_rate": 1.5606115530289856e-05, + "loss": 0.4962, + "step": 3885 + }, + { + "epoch": 0.33, + "learning_rate": 1.560382849637151e-05, + "loss": 0.4664, + "step": 3886 + }, + { + "epoch": 0.33, + "learning_rate": 1.5601541035081813e-05, + "loss": 0.4904, + "step": 3887 + }, + { + "epoch": 0.33, + "learning_rate": 1.559925314659521e-05, + "loss": 0.4981, + "step": 3888 + }, + { + "epoch": 0.33, + "learning_rate": 1.5596964831086185e-05, + "loss": 0.4821, + "step": 3889 + }, + { + "epoch": 0.33, + "learning_rate": 1.5594676088729252e-05, + "loss": 0.4915, + "step": 3890 + }, + { + "epoch": 0.33, + "learning_rate": 1.5592386919698967e-05, + "loss": 0.4787, + "step": 3891 + }, + { + "epoch": 0.33, + "learning_rate": 1.5590097324169907e-05, + "loss": 0.5092, + "step": 3892 + }, + { + "epoch": 0.33, + "learning_rate": 1.5587807302316687e-05, + "loss": 0.5037, + "step": 3893 + }, + { + "epoch": 0.33, + "learning_rate": 1.5585516854313957e-05, + "loss": 0.4937, + "step": 3894 + }, + { + "epoch": 0.33, + "learning_rate": 1.558322598033639e-05, + "loss": 0.4824, + "step": 3895 + }, + { + "epoch": 0.33, + "learning_rate": 1.5580934680558696e-05, + "loss": 0.4927, + "step": 3896 + }, + { + "epoch": 0.33, + "learning_rate": 1.5578642955155627e-05, + "loss": 0.4924, + "step": 3897 + }, + { + "epoch": 0.33, + "learning_rate": 1.557635080430196e-05, + "loss": 0.4804, + "step": 3898 + }, + { + "epoch": 0.33, + "learning_rate": 1.5574058228172498e-05, + "loss": 0.4863, + "step": 3899 + }, + { + "epoch": 0.33, + "learning_rate": 1.557176522694208e-05, + "loss": 0.4725, + "step": 3900 + }, + { + "epoch": 0.33, + "learning_rate": 1.556947180078559e-05, + "loss": 0.4919, + "step": 3901 + }, + { + "epoch": 0.33, + "learning_rate": 1.5567177949877925e-05, + "loss": 0.467, + "step": 3902 + }, + { + "epoch": 0.33, + "learning_rate": 1.556488367439403e-05, + "loss": 0.4995, + "step": 3903 + }, + { + "epoch": 0.33, + "learning_rate": 1.556258897450887e-05, + "loss": 0.4914, + "step": 3904 + }, + { + "epoch": 0.33, + "learning_rate": 1.5560293850397455e-05, + "loss": 0.4997, + "step": 3905 + }, + { + "epoch": 0.33, + "learning_rate": 1.5557998302234817e-05, + "loss": 0.4842, + "step": 3906 + }, + { + "epoch": 0.33, + "learning_rate": 1.5555702330196024e-05, + "loss": 0.4847, + "step": 3907 + }, + { + "epoch": 0.33, + "learning_rate": 1.555340593445618e-05, + "loss": 0.4927, + "step": 3908 + }, + { + "epoch": 0.33, + "learning_rate": 1.5551109115190408e-05, + "loss": 0.4821, + "step": 3909 + }, + { + "epoch": 0.33, + "learning_rate": 1.5548811872573883e-05, + "loss": 0.5074, + "step": 3910 + }, + { + "epoch": 0.33, + "learning_rate": 1.55465142067818e-05, + "loss": 0.4852, + "step": 3911 + }, + { + "epoch": 0.33, + "learning_rate": 1.554421611798939e-05, + "loss": 0.5034, + "step": 3912 + }, + { + "epoch": 0.33, + "learning_rate": 1.5541917606371904e-05, + "loss": 0.4716, + "step": 3913 + }, + { + "epoch": 0.33, + "learning_rate": 1.553961867210465e-05, + "loss": 0.4802, + "step": 3914 + }, + { + "epoch": 0.33, + "learning_rate": 1.553731931536295e-05, + "loss": 0.4795, + "step": 3915 + }, + { + "epoch": 0.33, + "learning_rate": 1.5535019536322158e-05, + "loss": 0.4816, + "step": 3916 + }, + { + "epoch": 0.33, + "learning_rate": 1.5532719335157673e-05, + "loss": 0.48, + "step": 3917 + }, + { + "epoch": 0.33, + "learning_rate": 1.5530418712044907e-05, + "loss": 0.488, + "step": 3918 + }, + { + "epoch": 0.33, + "learning_rate": 1.5528117667159325e-05, + "loss": 0.5021, + "step": 3919 + }, + { + "epoch": 0.33, + "learning_rate": 1.552581620067641e-05, + "loss": 0.4874, + "step": 3920 + }, + { + "epoch": 0.33, + "learning_rate": 1.5523514312771683e-05, + "loss": 0.4934, + "step": 3921 + }, + { + "epoch": 0.33, + "learning_rate": 1.5521212003620692e-05, + "loss": 0.4656, + "step": 3922 + }, + { + "epoch": 0.33, + "learning_rate": 1.5518909273399026e-05, + "loss": 0.4723, + "step": 3923 + }, + { + "epoch": 0.33, + "learning_rate": 1.5516606122282297e-05, + "loss": 0.5162, + "step": 3924 + }, + { + "epoch": 0.33, + "learning_rate": 1.5514302550446153e-05, + "loss": 0.4873, + "step": 3925 + }, + { + "epoch": 0.33, + "learning_rate": 1.5511998558066276e-05, + "loss": 0.4723, + "step": 3926 + }, + { + "epoch": 0.33, + "learning_rate": 1.5509694145318374e-05, + "loss": 0.4825, + "step": 3927 + }, + { + "epoch": 0.33, + "learning_rate": 1.55073893123782e-05, + "loss": 0.4861, + "step": 3928 + }, + { + "epoch": 0.34, + "learning_rate": 1.5505084059421517e-05, + "loss": 0.5117, + "step": 3929 + }, + { + "epoch": 0.34, + "learning_rate": 1.5502778386624147e-05, + "loss": 0.4805, + "step": 3930 + }, + { + "epoch": 0.34, + "learning_rate": 1.550047229416192e-05, + "loss": 0.5117, + "step": 3931 + }, + { + "epoch": 0.34, + "learning_rate": 1.5498165782210713e-05, + "loss": 0.4862, + "step": 3932 + }, + { + "epoch": 0.34, + "learning_rate": 1.5495858850946433e-05, + "loss": 0.5021, + "step": 3933 + }, + { + "epoch": 0.34, + "learning_rate": 1.549355150054501e-05, + "loss": 0.4936, + "step": 3934 + }, + { + "epoch": 0.34, + "learning_rate": 1.5491243731182414e-05, + "loss": 0.4881, + "step": 3935 + }, + { + "epoch": 0.34, + "learning_rate": 1.5488935543034644e-05, + "loss": 0.4771, + "step": 3936 + }, + { + "epoch": 0.34, + "learning_rate": 1.5486626936277737e-05, + "loss": 0.4806, + "step": 3937 + }, + { + "epoch": 0.34, + "learning_rate": 1.548431791108775e-05, + "loss": 0.4821, + "step": 3938 + }, + { + "epoch": 0.34, + "learning_rate": 1.548200846764079e-05, + "loss": 0.4909, + "step": 3939 + }, + { + "epoch": 0.34, + "learning_rate": 1.547969860611297e-05, + "loss": 0.5036, + "step": 3940 + }, + { + "epoch": 0.34, + "learning_rate": 1.547738832668046e-05, + "loss": 0.4715, + "step": 3941 + }, + { + "epoch": 0.34, + "learning_rate": 1.547507762951945e-05, + "loss": 0.492, + "step": 3942 + }, + { + "epoch": 0.34, + "learning_rate": 1.547276651480616e-05, + "loss": 0.4916, + "step": 3943 + }, + { + "epoch": 0.34, + "learning_rate": 1.5470454982716852e-05, + "loss": 0.4736, + "step": 3944 + }, + { + "epoch": 0.34, + "learning_rate": 1.5468143033427802e-05, + "loss": 0.5132, + "step": 3945 + }, + { + "epoch": 0.34, + "learning_rate": 1.546583066711534e-05, + "loss": 0.4813, + "step": 3946 + }, + { + "epoch": 0.34, + "learning_rate": 1.5463517883955813e-05, + "loss": 0.5018, + "step": 3947 + }, + { + "epoch": 0.34, + "learning_rate": 1.5461204684125595e-05, + "loss": 0.5026, + "step": 3948 + }, + { + "epoch": 0.34, + "learning_rate": 1.545889106780112e-05, + "loss": 0.5087, + "step": 3949 + }, + { + "epoch": 0.34, + "learning_rate": 1.5456577035158814e-05, + "loss": 0.4782, + "step": 3950 + }, + { + "epoch": 0.34, + "learning_rate": 1.5454262586375164e-05, + "loss": 0.4932, + "step": 3951 + }, + { + "epoch": 0.34, + "learning_rate": 1.5451947721626676e-05, + "loss": 0.4987, + "step": 3952 + }, + { + "epoch": 0.34, + "learning_rate": 1.5449632441089896e-05, + "loss": 0.4609, + "step": 3953 + }, + { + "epoch": 0.34, + "learning_rate": 1.54473167449414e-05, + "loss": 0.4951, + "step": 3954 + }, + { + "epoch": 0.34, + "learning_rate": 1.544500063335778e-05, + "loss": 0.4669, + "step": 3955 + }, + { + "epoch": 0.34, + "learning_rate": 1.544268410651568e-05, + "loss": 0.4875, + "step": 3956 + }, + { + "epoch": 0.34, + "learning_rate": 1.5440367164591768e-05, + "loss": 0.4614, + "step": 3957 + }, + { + "epoch": 0.34, + "learning_rate": 1.5438049807762746e-05, + "loss": 0.5078, + "step": 3958 + }, + { + "epoch": 0.34, + "learning_rate": 1.543573203620534e-05, + "loss": 0.4848, + "step": 3959 + }, + { + "epoch": 0.34, + "learning_rate": 1.5433413850096316e-05, + "loss": 0.5104, + "step": 3960 + }, + { + "epoch": 0.34, + "learning_rate": 1.5431095249612466e-05, + "loss": 0.4905, + "step": 3961 + }, + { + "epoch": 0.34, + "learning_rate": 1.542877623493062e-05, + "loss": 0.4738, + "step": 3962 + }, + { + "epoch": 0.34, + "learning_rate": 1.5426456806227635e-05, + "loss": 0.5096, + "step": 3963 + }, + { + "epoch": 0.34, + "learning_rate": 1.5424136963680398e-05, + "loss": 0.4681, + "step": 3964 + }, + { + "epoch": 0.34, + "learning_rate": 1.542181670746583e-05, + "loss": 0.5045, + "step": 3965 + }, + { + "epoch": 0.34, + "learning_rate": 1.5419496037760887e-05, + "loss": 0.4785, + "step": 3966 + }, + { + "epoch": 0.34, + "learning_rate": 1.541717495474255e-05, + "loss": 0.4973, + "step": 3967 + }, + { + "epoch": 0.34, + "learning_rate": 1.5414853458587834e-05, + "loss": 0.5206, + "step": 3968 + }, + { + "epoch": 0.34, + "learning_rate": 1.5412531549473786e-05, + "loss": 0.4829, + "step": 3969 + }, + { + "epoch": 0.34, + "learning_rate": 1.5410209227577487e-05, + "loss": 0.482, + "step": 3970 + }, + { + "epoch": 0.34, + "learning_rate": 1.5407886493076043e-05, + "loss": 0.4707, + "step": 3971 + }, + { + "epoch": 0.34, + "learning_rate": 1.5405563346146603e-05, + "loss": 0.4983, + "step": 3972 + }, + { + "epoch": 0.34, + "learning_rate": 1.540323978696633e-05, + "loss": 0.4918, + "step": 3973 + }, + { + "epoch": 0.34, + "learning_rate": 1.540091581571243e-05, + "loss": 0.4851, + "step": 3974 + }, + { + "epoch": 0.34, + "learning_rate": 1.539859143256215e-05, + "loss": 0.4815, + "step": 3975 + }, + { + "epoch": 0.34, + "learning_rate": 1.5396266637692746e-05, + "loss": 0.4675, + "step": 3976 + }, + { + "epoch": 0.34, + "learning_rate": 1.5393941431281513e-05, + "loss": 0.4791, + "step": 3977 + }, + { + "epoch": 0.34, + "learning_rate": 1.5391615813505792e-05, + "loss": 0.4986, + "step": 3978 + }, + { + "epoch": 0.34, + "learning_rate": 1.5389289784542944e-05, + "loss": 0.5028, + "step": 3979 + }, + { + "epoch": 0.34, + "learning_rate": 1.5386963344570352e-05, + "loss": 0.4713, + "step": 3980 + }, + { + "epoch": 0.34, + "learning_rate": 1.538463649376545e-05, + "loss": 0.4817, + "step": 3981 + }, + { + "epoch": 0.34, + "learning_rate": 1.5382309232305685e-05, + "loss": 0.531, + "step": 3982 + }, + { + "epoch": 0.34, + "learning_rate": 1.5379981560368548e-05, + "loss": 0.4811, + "step": 3983 + }, + { + "epoch": 0.34, + "learning_rate": 1.5377653478131557e-05, + "loss": 0.5003, + "step": 3984 + }, + { + "epoch": 0.34, + "learning_rate": 1.5375324985772262e-05, + "loss": 0.5037, + "step": 3985 + }, + { + "epoch": 0.34, + "learning_rate": 1.5372996083468242e-05, + "loss": 0.4701, + "step": 3986 + }, + { + "epoch": 0.34, + "learning_rate": 1.5370666771397105e-05, + "loss": 0.4726, + "step": 3987 + }, + { + "epoch": 0.34, + "learning_rate": 1.5368337049736505e-05, + "loss": 0.4815, + "step": 3988 + }, + { + "epoch": 0.34, + "learning_rate": 1.53660069186641e-05, + "loss": 0.4823, + "step": 3989 + }, + { + "epoch": 0.34, + "learning_rate": 1.5363676378357614e-05, + "loss": 0.4717, + "step": 3990 + }, + { + "epoch": 0.34, + "learning_rate": 1.5361345428994772e-05, + "loss": 0.4821, + "step": 3991 + }, + { + "epoch": 0.34, + "learning_rate": 1.5359014070753345e-05, + "loss": 0.4893, + "step": 3992 + }, + { + "epoch": 0.34, + "learning_rate": 1.535668230381113e-05, + "loss": 0.4779, + "step": 3993 + }, + { + "epoch": 0.34, + "learning_rate": 1.535435012834596e-05, + "loss": 0.4829, + "step": 3994 + }, + { + "epoch": 0.34, + "learning_rate": 1.5352017544535694e-05, + "loss": 0.4882, + "step": 3995 + }, + { + "epoch": 0.34, + "learning_rate": 1.5349684552558226e-05, + "loss": 0.4848, + "step": 3996 + }, + { + "epoch": 0.34, + "learning_rate": 1.5347351152591485e-05, + "loss": 0.5034, + "step": 3997 + }, + { + "epoch": 0.34, + "learning_rate": 1.5345017344813414e-05, + "loss": 0.4822, + "step": 3998 + }, + { + "epoch": 0.34, + "learning_rate": 1.534268312940201e-05, + "loss": 0.4887, + "step": 3999 + }, + { + "epoch": 0.34, + "learning_rate": 1.534034850653528e-05, + "loss": 0.4759, + "step": 4000 + }, + { + "epoch": 0.34, + "learning_rate": 1.5338013476391282e-05, + "loss": 0.4983, + "step": 4001 + }, + { + "epoch": 0.34, + "learning_rate": 1.5335678039148094e-05, + "loss": 0.4882, + "step": 4002 + }, + { + "epoch": 0.34, + "learning_rate": 1.533334219498382e-05, + "loss": 0.4814, + "step": 4003 + }, + { + "epoch": 0.34, + "learning_rate": 1.53310059440766e-05, + "loss": 0.5108, + "step": 4004 + }, + { + "epoch": 0.34, + "learning_rate": 1.5328669286604612e-05, + "loss": 0.4952, + "step": 4005 + }, + { + "epoch": 0.34, + "learning_rate": 1.532633222274606e-05, + "loss": 0.4661, + "step": 4006 + }, + { + "epoch": 0.34, + "learning_rate": 1.5323994752679174e-05, + "loss": 0.4965, + "step": 4007 + }, + { + "epoch": 0.34, + "learning_rate": 1.5321656876582226e-05, + "loss": 0.4918, + "step": 4008 + }, + { + "epoch": 0.34, + "learning_rate": 1.53193185946335e-05, + "loss": 0.4796, + "step": 4009 + }, + { + "epoch": 0.34, + "learning_rate": 1.5316979907011335e-05, + "loss": 0.4806, + "step": 4010 + }, + { + "epoch": 0.34, + "learning_rate": 1.5314640813894088e-05, + "loss": 0.4856, + "step": 4011 + }, + { + "epoch": 0.34, + "learning_rate": 1.531230131546014e-05, + "loss": 0.4891, + "step": 4012 + }, + { + "epoch": 0.34, + "learning_rate": 1.5309961411887915e-05, + "loss": 0.469, + "step": 4013 + }, + { + "epoch": 0.34, + "learning_rate": 1.5307621103355865e-05, + "loss": 0.499, + "step": 4014 + }, + { + "epoch": 0.34, + "learning_rate": 1.530528039004247e-05, + "loss": 0.5021, + "step": 4015 + }, + { + "epoch": 0.34, + "learning_rate": 1.5302939272126243e-05, + "loss": 0.4842, + "step": 4016 + }, + { + "epoch": 0.34, + "learning_rate": 1.530059774978573e-05, + "loss": 0.4744, + "step": 4017 + }, + { + "epoch": 0.34, + "learning_rate": 1.5298255823199503e-05, + "loss": 0.4916, + "step": 4018 + }, + { + "epoch": 0.34, + "learning_rate": 1.5295913492546168e-05, + "loss": 0.4613, + "step": 4019 + }, + { + "epoch": 0.34, + "learning_rate": 1.529357075800436e-05, + "loss": 0.5065, + "step": 4020 + }, + { + "epoch": 0.34, + "learning_rate": 1.5291227619752748e-05, + "loss": 0.4898, + "step": 4021 + }, + { + "epoch": 0.34, + "learning_rate": 1.5288884077970025e-05, + "loss": 0.4796, + "step": 4022 + }, + { + "epoch": 0.34, + "learning_rate": 1.528654013283492e-05, + "loss": 0.4845, + "step": 4023 + }, + { + "epoch": 0.34, + "learning_rate": 1.5284195784526196e-05, + "loss": 0.4808, + "step": 4024 + }, + { + "epoch": 0.34, + "learning_rate": 1.528185103322264e-05, + "loss": 0.4871, + "step": 4025 + }, + { + "epoch": 0.34, + "learning_rate": 1.5279505879103074e-05, + "loss": 0.4665, + "step": 4026 + }, + { + "epoch": 0.34, + "learning_rate": 1.527716032234635e-05, + "loss": 0.482, + "step": 4027 + }, + { + "epoch": 0.34, + "learning_rate": 1.5274814363131346e-05, + "loss": 0.4837, + "step": 4028 + }, + { + "epoch": 0.34, + "learning_rate": 1.5272468001636975e-05, + "loss": 0.4891, + "step": 4029 + }, + { + "epoch": 0.34, + "learning_rate": 1.5270121238042186e-05, + "loss": 0.5038, + "step": 4030 + }, + { + "epoch": 0.34, + "learning_rate": 1.5267774072525948e-05, + "loss": 0.4996, + "step": 4031 + }, + { + "epoch": 0.34, + "learning_rate": 1.5265426505267265e-05, + "loss": 0.4757, + "step": 4032 + }, + { + "epoch": 0.34, + "learning_rate": 1.5263078536445176e-05, + "loss": 0.5009, + "step": 4033 + }, + { + "epoch": 0.34, + "learning_rate": 1.5260730166238747e-05, + "loss": 0.4806, + "step": 4034 + }, + { + "epoch": 0.34, + "learning_rate": 1.525838139482707e-05, + "loss": 0.4717, + "step": 4035 + }, + { + "epoch": 0.34, + "learning_rate": 1.5256032222389276e-05, + "loss": 0.4881, + "step": 4036 + }, + { + "epoch": 0.34, + "learning_rate": 1.5253682649104519e-05, + "loss": 0.4827, + "step": 4037 + }, + { + "epoch": 0.34, + "learning_rate": 1.5251332675151993e-05, + "loss": 0.4975, + "step": 4038 + }, + { + "epoch": 0.34, + "learning_rate": 1.5248982300710913e-05, + "loss": 0.4933, + "step": 4039 + }, + { + "epoch": 0.34, + "learning_rate": 1.5246631525960527e-05, + "loss": 0.4836, + "step": 4040 + }, + { + "epoch": 0.34, + "learning_rate": 1.5244280351080121e-05, + "loss": 0.4989, + "step": 4041 + }, + { + "epoch": 0.34, + "learning_rate": 1.5241928776248993e-05, + "loss": 0.4815, + "step": 4042 + }, + { + "epoch": 0.34, + "learning_rate": 1.5239576801646501e-05, + "loss": 0.4577, + "step": 4043 + }, + { + "epoch": 0.34, + "learning_rate": 1.5237224427452002e-05, + "loss": 0.5196, + "step": 4044 + }, + { + "epoch": 0.34, + "learning_rate": 1.5234871653844904e-05, + "loss": 0.4694, + "step": 4045 + }, + { + "epoch": 0.34, + "learning_rate": 1.5232518481004642e-05, + "loss": 0.4869, + "step": 4046 + }, + { + "epoch": 0.35, + "learning_rate": 1.5230164909110674e-05, + "loss": 0.4875, + "step": 4047 + }, + { + "epoch": 0.35, + "learning_rate": 1.5227810938342493e-05, + "loss": 0.4796, + "step": 4048 + }, + { + "epoch": 0.35, + "learning_rate": 1.5225456568879624e-05, + "loss": 0.4726, + "step": 4049 + }, + { + "epoch": 0.35, + "learning_rate": 1.5223101800901625e-05, + "loss": 0.4954, + "step": 4050 + }, + { + "epoch": 0.35, + "learning_rate": 1.5220746634588076e-05, + "loss": 0.4922, + "step": 4051 + }, + { + "epoch": 0.35, + "learning_rate": 1.521839107011859e-05, + "loss": 0.4758, + "step": 4052 + }, + { + "epoch": 0.35, + "learning_rate": 1.5216035107672818e-05, + "loss": 0.4871, + "step": 4053 + }, + { + "epoch": 0.35, + "learning_rate": 1.5213678747430429e-05, + "loss": 0.4562, + "step": 4054 + }, + { + "epoch": 0.35, + "learning_rate": 1.5211321989571134e-05, + "loss": 0.4698, + "step": 4055 + }, + { + "epoch": 0.35, + "learning_rate": 1.5208964834274669e-05, + "loss": 0.4872, + "step": 4056 + }, + { + "epoch": 0.35, + "learning_rate": 1.5206607281720797e-05, + "loss": 0.5011, + "step": 4057 + }, + { + "epoch": 0.35, + "learning_rate": 1.5204249332089318e-05, + "loss": 0.4675, + "step": 4058 + }, + { + "epoch": 0.35, + "learning_rate": 1.5201890985560056e-05, + "loss": 0.4875, + "step": 4059 + }, + { + "epoch": 0.35, + "learning_rate": 1.5199532242312872e-05, + "loss": 0.4996, + "step": 4060 + }, + { + "epoch": 0.35, + "learning_rate": 1.5197173102527652e-05, + "loss": 0.4916, + "step": 4061 + }, + { + "epoch": 0.35, + "learning_rate": 1.5194813566384312e-05, + "loss": 0.4956, + "step": 4062 + }, + { + "epoch": 0.35, + "learning_rate": 1.51924536340628e-05, + "loss": 0.5038, + "step": 4063 + }, + { + "epoch": 0.35, + "learning_rate": 1.5190093305743103e-05, + "loss": 0.4761, + "step": 4064 + }, + { + "epoch": 0.35, + "learning_rate": 1.5187732581605217e-05, + "loss": 0.4839, + "step": 4065 + }, + { + "epoch": 0.35, + "learning_rate": 1.5185371461829186e-05, + "loss": 0.5018, + "step": 4066 + }, + { + "epoch": 0.35, + "learning_rate": 1.518300994659508e-05, + "loss": 0.5062, + "step": 4067 + }, + { + "epoch": 0.35, + "learning_rate": 1.5180648036082998e-05, + "loss": 0.4834, + "step": 4068 + }, + { + "epoch": 0.35, + "learning_rate": 1.5178285730473068e-05, + "loss": 0.5115, + "step": 4069 + }, + { + "epoch": 0.35, + "learning_rate": 1.5175923029945447e-05, + "loss": 0.491, + "step": 4070 + }, + { + "epoch": 0.35, + "learning_rate": 1.5173559934680331e-05, + "loss": 0.4844, + "step": 4071 + }, + { + "epoch": 0.35, + "learning_rate": 1.5171196444857933e-05, + "loss": 0.4752, + "step": 4072 + }, + { + "epoch": 0.35, + "learning_rate": 1.5168832560658506e-05, + "loss": 0.4653, + "step": 4073 + }, + { + "epoch": 0.35, + "learning_rate": 1.5166468282262327e-05, + "loss": 0.4915, + "step": 4074 + }, + { + "epoch": 0.35, + "learning_rate": 1.516410360984971e-05, + "loss": 0.4833, + "step": 4075 + }, + { + "epoch": 0.35, + "learning_rate": 1.516173854360099e-05, + "loss": 0.5093, + "step": 4076 + }, + { + "epoch": 0.35, + "learning_rate": 1.515937308369654e-05, + "loss": 0.4616, + "step": 4077 + }, + { + "epoch": 0.35, + "learning_rate": 1.5157007230316757e-05, + "loss": 0.5034, + "step": 4078 + }, + { + "epoch": 0.35, + "learning_rate": 1.5154640983642077e-05, + "loss": 0.4805, + "step": 4079 + }, + { + "epoch": 0.35, + "learning_rate": 1.5152274343852953e-05, + "loss": 0.4952, + "step": 4080 + }, + { + "epoch": 0.35, + "learning_rate": 1.5149907311129877e-05, + "loss": 0.4856, + "step": 4081 + }, + { + "epoch": 0.35, + "learning_rate": 1.514753988565337e-05, + "loss": 0.5014, + "step": 4082 + }, + { + "epoch": 0.35, + "learning_rate": 1.514517206760398e-05, + "loss": 0.4795, + "step": 4083 + }, + { + "epoch": 0.35, + "learning_rate": 1.5142803857162289e-05, + "loss": 0.4585, + "step": 4084 + }, + { + "epoch": 0.35, + "learning_rate": 1.5140435254508905e-05, + "loss": 0.4824, + "step": 4085 + }, + { + "epoch": 0.35, + "learning_rate": 1.5138066259824468e-05, + "loss": 0.4976, + "step": 4086 + }, + { + "epoch": 0.35, + "learning_rate": 1.5135696873289648e-05, + "loss": 0.4955, + "step": 4087 + }, + { + "epoch": 0.35, + "learning_rate": 1.5133327095085139e-05, + "loss": 0.5017, + "step": 4088 + }, + { + "epoch": 0.35, + "learning_rate": 1.5130956925391678e-05, + "loss": 0.4766, + "step": 4089 + }, + { + "epoch": 0.35, + "learning_rate": 1.5128586364390021e-05, + "loss": 0.4983, + "step": 4090 + }, + { + "epoch": 0.35, + "learning_rate": 1.5126215412260958e-05, + "loss": 0.4774, + "step": 4091 + }, + { + "epoch": 0.35, + "learning_rate": 1.5123844069185305e-05, + "loss": 0.4874, + "step": 4092 + }, + { + "epoch": 0.35, + "learning_rate": 1.5121472335343912e-05, + "loss": 0.474, + "step": 4093 + }, + { + "epoch": 0.35, + "learning_rate": 1.5119100210917657e-05, + "loss": 0.4971, + "step": 4094 + }, + { + "epoch": 0.35, + "learning_rate": 1.5116727696087447e-05, + "loss": 0.4915, + "step": 4095 + }, + { + "epoch": 0.35, + "learning_rate": 1.5114354791034225e-05, + "loss": 0.526, + "step": 4096 + }, + { + "epoch": 0.35, + "learning_rate": 1.511198149593895e-05, + "loss": 0.4803, + "step": 4097 + }, + { + "epoch": 0.35, + "learning_rate": 1.5109607810982628e-05, + "loss": 0.4991, + "step": 4098 + }, + { + "epoch": 0.35, + "learning_rate": 1.5107233736346278e-05, + "loss": 0.4992, + "step": 4099 + }, + { + "epoch": 0.35, + "learning_rate": 1.5104859272210966e-05, + "loss": 0.4661, + "step": 4100 + }, + { + "epoch": 0.35, + "learning_rate": 1.5102484418757772e-05, + "loss": 0.4967, + "step": 4101 + }, + { + "epoch": 0.35, + "learning_rate": 1.5100109176167814e-05, + "loss": 0.4959, + "step": 4102 + }, + { + "epoch": 0.35, + "learning_rate": 1.5097733544622239e-05, + "loss": 0.4841, + "step": 4103 + }, + { + "epoch": 0.35, + "learning_rate": 1.5095357524302219e-05, + "loss": 0.5046, + "step": 4104 + }, + { + "epoch": 0.35, + "learning_rate": 1.5092981115388963e-05, + "loss": 0.4772, + "step": 4105 + }, + { + "epoch": 0.35, + "learning_rate": 1.5090604318063704e-05, + "loss": 0.5079, + "step": 4106 + }, + { + "epoch": 0.35, + "learning_rate": 1.508822713250771e-05, + "loss": 0.4735, + "step": 4107 + }, + { + "epoch": 0.35, + "learning_rate": 1.5085849558902265e-05, + "loss": 0.4879, + "step": 4108 + }, + { + "epoch": 0.35, + "learning_rate": 1.5083471597428707e-05, + "loss": 0.4677, + "step": 4109 + }, + { + "epoch": 0.35, + "learning_rate": 1.5081093248268382e-05, + "loss": 0.4747, + "step": 4110 + }, + { + "epoch": 0.35, + "learning_rate": 1.5078714511602667e-05, + "loss": 0.4941, + "step": 4111 + }, + { + "epoch": 0.35, + "learning_rate": 1.5076335387612987e-05, + "loss": 0.4886, + "step": 4112 + }, + { + "epoch": 0.35, + "learning_rate": 1.5073955876480775e-05, + "loss": 0.4601, + "step": 4113 + }, + { + "epoch": 0.35, + "learning_rate": 1.5071575978387505e-05, + "loss": 0.4864, + "step": 4114 + }, + { + "epoch": 0.35, + "learning_rate": 1.5069195693514672e-05, + "loss": 0.4899, + "step": 4115 + }, + { + "epoch": 0.35, + "learning_rate": 1.506681502204382e-05, + "loss": 0.4747, + "step": 4116 + }, + { + "epoch": 0.35, + "learning_rate": 1.5064433964156497e-05, + "loss": 0.4746, + "step": 4117 + }, + { + "epoch": 0.35, + "learning_rate": 1.5062052520034299e-05, + "loss": 0.4935, + "step": 4118 + }, + { + "epoch": 0.35, + "learning_rate": 1.505967068985884e-05, + "loss": 0.508, + "step": 4119 + }, + { + "epoch": 0.35, + "learning_rate": 1.5057288473811773e-05, + "loss": 0.4801, + "step": 4120 + }, + { + "epoch": 0.35, + "learning_rate": 1.5054905872074772e-05, + "loss": 0.4712, + "step": 4121 + }, + { + "epoch": 0.35, + "learning_rate": 1.5052522884829543e-05, + "loss": 0.4951, + "step": 4122 + }, + { + "epoch": 0.35, + "learning_rate": 1.505013951225783e-05, + "loss": 0.4559, + "step": 4123 + }, + { + "epoch": 0.35, + "learning_rate": 1.5047755754541392e-05, + "loss": 0.5025, + "step": 4124 + }, + { + "epoch": 0.35, + "learning_rate": 1.5045371611862026e-05, + "loss": 0.4884, + "step": 4125 + }, + { + "epoch": 0.35, + "learning_rate": 1.5042987084401559e-05, + "loss": 0.4792, + "step": 4126 + }, + { + "epoch": 0.35, + "learning_rate": 1.504060217234184e-05, + "loss": 0.4933, + "step": 4127 + }, + { + "epoch": 0.35, + "learning_rate": 1.5038216875864758e-05, + "loss": 0.4999, + "step": 4128 + }, + { + "epoch": 0.35, + "learning_rate": 1.5035831195152221e-05, + "loss": 0.481, + "step": 4129 + }, + { + "epoch": 0.35, + "learning_rate": 1.5033445130386176e-05, + "loss": 0.5122, + "step": 4130 + }, + { + "epoch": 0.35, + "learning_rate": 1.5031058681748587e-05, + "loss": 0.4855, + "step": 4131 + }, + { + "epoch": 0.35, + "learning_rate": 1.5028671849421463e-05, + "loss": 0.4933, + "step": 4132 + }, + { + "epoch": 0.35, + "learning_rate": 1.5026284633586828e-05, + "loss": 0.4882, + "step": 4133 + }, + { + "epoch": 0.35, + "learning_rate": 1.5023897034426741e-05, + "loss": 0.5095, + "step": 4134 + }, + { + "epoch": 0.35, + "learning_rate": 1.5021509052123295e-05, + "loss": 0.4832, + "step": 4135 + }, + { + "epoch": 0.35, + "learning_rate": 1.5019120686858603e-05, + "loss": 0.4846, + "step": 4136 + }, + { + "epoch": 0.35, + "learning_rate": 1.5016731938814815e-05, + "loss": 0.4845, + "step": 4137 + }, + { + "epoch": 0.35, + "learning_rate": 1.5014342808174102e-05, + "loss": 0.4873, + "step": 4138 + }, + { + "epoch": 0.35, + "learning_rate": 1.5011953295118677e-05, + "loss": 0.4757, + "step": 4139 + }, + { + "epoch": 0.35, + "learning_rate": 1.5009563399830764e-05, + "loss": 0.5001, + "step": 4140 + }, + { + "epoch": 0.35, + "learning_rate": 1.5007173122492635e-05, + "loss": 0.4925, + "step": 4141 + }, + { + "epoch": 0.35, + "learning_rate": 1.500478246328658e-05, + "loss": 0.4902, + "step": 4142 + }, + { + "epoch": 0.35, + "learning_rate": 1.5002391422394915e-05, + "loss": 0.4812, + "step": 4143 + }, + { + "epoch": 0.35, + "learning_rate": 1.5000000000000002e-05, + "loss": 0.4955, + "step": 4144 + }, + { + "epoch": 0.35, + "learning_rate": 1.4997608196284212e-05, + "loss": 0.4899, + "step": 4145 + }, + { + "epoch": 0.35, + "learning_rate": 1.4995216011429956e-05, + "loss": 0.4917, + "step": 4146 + }, + { + "epoch": 0.35, + "learning_rate": 1.4992823445619672e-05, + "loss": 0.4926, + "step": 4147 + }, + { + "epoch": 0.35, + "learning_rate": 1.499043049903583e-05, + "loss": 0.4861, + "step": 4148 + }, + { + "epoch": 0.35, + "learning_rate": 1.498803717186092e-05, + "loss": 0.4845, + "step": 4149 + }, + { + "epoch": 0.35, + "learning_rate": 1.4985643464277475e-05, + "loss": 0.5006, + "step": 4150 + }, + { + "epoch": 0.35, + "learning_rate": 1.4983249376468045e-05, + "loss": 0.4962, + "step": 4151 + }, + { + "epoch": 0.35, + "learning_rate": 1.498085490861521e-05, + "loss": 0.4761, + "step": 4152 + }, + { + "epoch": 0.35, + "learning_rate": 1.4978460060901587e-05, + "loss": 0.4983, + "step": 4153 + }, + { + "epoch": 0.35, + "learning_rate": 1.4976064833509816e-05, + "loss": 0.513, + "step": 4154 + }, + { + "epoch": 0.35, + "learning_rate": 1.4973669226622564e-05, + "loss": 0.4689, + "step": 4155 + }, + { + "epoch": 0.35, + "learning_rate": 1.4971273240422534e-05, + "loss": 0.5088, + "step": 4156 + }, + { + "epoch": 0.35, + "learning_rate": 1.4968876875092453e-05, + "loss": 0.4796, + "step": 4157 + }, + { + "epoch": 0.35, + "learning_rate": 1.4966480130815076e-05, + "loss": 0.4866, + "step": 4158 + }, + { + "epoch": 0.35, + "learning_rate": 1.4964083007773189e-05, + "loss": 0.4754, + "step": 4159 + }, + { + "epoch": 0.35, + "learning_rate": 1.4961685506149608e-05, + "loss": 0.4874, + "step": 4160 + }, + { + "epoch": 0.35, + "learning_rate": 1.4959287626127175e-05, + "loss": 0.4878, + "step": 4161 + }, + { + "epoch": 0.35, + "learning_rate": 1.4956889367888765e-05, + "loss": 0.4681, + "step": 4162 + }, + { + "epoch": 0.35, + "learning_rate": 1.4954490731617278e-05, + "loss": 0.5002, + "step": 4163 + }, + { + "epoch": 0.36, + "learning_rate": 1.495209171749564e-05, + "loss": 0.4852, + "step": 4164 + }, + { + "epoch": 0.36, + "learning_rate": 1.4949692325706818e-05, + "loss": 0.4698, + "step": 4165 + }, + { + "epoch": 0.36, + "learning_rate": 1.494729255643379e-05, + "loss": 0.4824, + "step": 4166 + }, + { + "epoch": 0.36, + "learning_rate": 1.4944892409859581e-05, + "loss": 0.4883, + "step": 4167 + }, + { + "epoch": 0.36, + "learning_rate": 1.494249188616723e-05, + "loss": 0.4721, + "step": 4168 + }, + { + "epoch": 0.36, + "learning_rate": 1.4940090985539818e-05, + "loss": 0.4776, + "step": 4169 + }, + { + "epoch": 0.36, + "learning_rate": 1.4937689708160434e-05, + "loss": 0.502, + "step": 4170 + }, + { + "epoch": 0.36, + "learning_rate": 1.4935288054212228e-05, + "loss": 0.4907, + "step": 4171 + }, + { + "epoch": 0.36, + "learning_rate": 1.4932886023878346e-05, + "loss": 0.4949, + "step": 4172 + }, + { + "epoch": 0.36, + "learning_rate": 1.4930483617341982e-05, + "loss": 0.4996, + "step": 4173 + }, + { + "epoch": 0.36, + "learning_rate": 1.4928080834786356e-05, + "loss": 0.4723, + "step": 4174 + }, + { + "epoch": 0.36, + "learning_rate": 1.492567767639471e-05, + "loss": 0.4853, + "step": 4175 + }, + { + "epoch": 0.36, + "learning_rate": 1.492327414235032e-05, + "loss": 0.491, + "step": 4176 + }, + { + "epoch": 0.36, + "learning_rate": 1.4920870232836487e-05, + "loss": 0.5252, + "step": 4177 + }, + { + "epoch": 0.36, + "learning_rate": 1.491846594803655e-05, + "loss": 0.4961, + "step": 4178 + }, + { + "epoch": 0.36, + "learning_rate": 1.4916061288133862e-05, + "loss": 0.5273, + "step": 4179 + }, + { + "epoch": 0.36, + "learning_rate": 1.491365625331182e-05, + "loss": 0.4707, + "step": 4180 + }, + { + "epoch": 0.36, + "learning_rate": 1.4911250843753838e-05, + "loss": 0.4858, + "step": 4181 + }, + { + "epoch": 0.36, + "learning_rate": 1.490884505964336e-05, + "loss": 0.482, + "step": 4182 + }, + { + "epoch": 0.36, + "learning_rate": 1.490643890116387e-05, + "loss": 0.4765, + "step": 4183 + }, + { + "epoch": 0.36, + "learning_rate": 1.4904032368498857e-05, + "loss": 0.4932, + "step": 4184 + }, + { + "epoch": 0.36, + "learning_rate": 1.4901625461831868e-05, + "loss": 0.4823, + "step": 4185 + }, + { + "epoch": 0.36, + "learning_rate": 1.4899218181346453e-05, + "loss": 0.5056, + "step": 4186 + }, + { + "epoch": 0.36, + "learning_rate": 1.489681052722621e-05, + "loss": 0.4649, + "step": 4187 + }, + { + "epoch": 0.36, + "learning_rate": 1.489440249965475e-05, + "loss": 0.4853, + "step": 4188 + }, + { + "epoch": 0.36, + "learning_rate": 1.4891994098815725e-05, + "loss": 0.5137, + "step": 4189 + }, + { + "epoch": 0.36, + "learning_rate": 1.4889585324892803e-05, + "loss": 0.4911, + "step": 4190 + }, + { + "epoch": 0.36, + "learning_rate": 1.4887176178069693e-05, + "loss": 0.4914, + "step": 4191 + }, + { + "epoch": 0.36, + "learning_rate": 1.4884766658530126e-05, + "loss": 0.4816, + "step": 4192 + }, + { + "epoch": 0.36, + "learning_rate": 1.4882356766457857e-05, + "loss": 0.5093, + "step": 4193 + }, + { + "epoch": 0.36, + "learning_rate": 1.4879946502036677e-05, + "loss": 0.4758, + "step": 4194 + }, + { + "epoch": 0.36, + "learning_rate": 1.4877535865450405e-05, + "loss": 0.4775, + "step": 4195 + }, + { + "epoch": 0.36, + "learning_rate": 1.4875124856882885e-05, + "loss": 0.4707, + "step": 4196 + }, + { + "epoch": 0.36, + "learning_rate": 1.4872713476517993e-05, + "loss": 0.4757, + "step": 4197 + }, + { + "epoch": 0.36, + "learning_rate": 1.4870301724539627e-05, + "loss": 0.4965, + "step": 4198 + }, + { + "epoch": 0.36, + "learning_rate": 1.4867889601131716e-05, + "loss": 0.4694, + "step": 4199 + }, + { + "epoch": 0.36, + "learning_rate": 1.486547710647822e-05, + "loss": 0.4905, + "step": 4200 + }, + { + "epoch": 0.36, + "learning_rate": 1.4863064240763132e-05, + "loss": 0.4755, + "step": 4201 + }, + { + "epoch": 0.36, + "learning_rate": 1.486065100417046e-05, + "loss": 0.4777, + "step": 4202 + }, + { + "epoch": 0.36, + "learning_rate": 1.4858237396884249e-05, + "loss": 0.4904, + "step": 4203 + }, + { + "epoch": 0.36, + "learning_rate": 1.4855823419088576e-05, + "loss": 0.4618, + "step": 4204 + }, + { + "epoch": 0.36, + "learning_rate": 1.4853409070967528e-05, + "loss": 0.4889, + "step": 4205 + }, + { + "epoch": 0.36, + "learning_rate": 1.485099435270525e-05, + "loss": 0.5078, + "step": 4206 + }, + { + "epoch": 0.36, + "learning_rate": 1.4848579264485887e-05, + "loss": 0.5029, + "step": 4207 + }, + { + "epoch": 0.36, + "learning_rate": 1.4846163806493628e-05, + "loss": 0.4675, + "step": 4208 + }, + { + "epoch": 0.36, + "learning_rate": 1.4843747978912682e-05, + "loss": 0.5082, + "step": 4209 + }, + { + "epoch": 0.36, + "learning_rate": 1.4841331781927297e-05, + "loss": 0.4802, + "step": 4210 + }, + { + "epoch": 0.36, + "learning_rate": 1.4838915215721735e-05, + "loss": 0.5168, + "step": 4211 + }, + { + "epoch": 0.36, + "learning_rate": 1.48364982804803e-05, + "loss": 0.5006, + "step": 4212 + }, + { + "epoch": 0.36, + "learning_rate": 1.4834080976387316e-05, + "loss": 0.4968, + "step": 4213 + }, + { + "epoch": 0.36, + "learning_rate": 1.4831663303627128e-05, + "loss": 0.484, + "step": 4214 + }, + { + "epoch": 0.36, + "learning_rate": 1.482924526238413e-05, + "loss": 0.4848, + "step": 4215 + }, + { + "epoch": 0.36, + "learning_rate": 1.4826826852842725e-05, + "loss": 0.5118, + "step": 4216 + }, + { + "epoch": 0.36, + "learning_rate": 1.4824408075187352e-05, + "loss": 0.4698, + "step": 4217 + }, + { + "epoch": 0.36, + "learning_rate": 1.482198892960248e-05, + "loss": 0.4723, + "step": 4218 + }, + { + "epoch": 0.36, + "learning_rate": 1.4819569416272604e-05, + "loss": 0.4894, + "step": 4219 + }, + { + "epoch": 0.36, + "learning_rate": 1.4817149535382238e-05, + "loss": 0.4799, + "step": 4220 + }, + { + "epoch": 0.36, + "learning_rate": 1.481472928711594e-05, + "loss": 0.4946, + "step": 4221 + }, + { + "epoch": 0.36, + "learning_rate": 1.4812308671658285e-05, + "loss": 0.5066, + "step": 4222 + }, + { + "epoch": 0.36, + "learning_rate": 1.4809887689193878e-05, + "loss": 0.5022, + "step": 4223 + }, + { + "epoch": 0.36, + "learning_rate": 1.4807466339907358e-05, + "loss": 0.4772, + "step": 4224 + }, + { + "epoch": 0.36, + "learning_rate": 1.4805044623983382e-05, + "loss": 0.4973, + "step": 4225 + }, + { + "epoch": 0.36, + "learning_rate": 1.4802622541606644e-05, + "loss": 0.4783, + "step": 4226 + }, + { + "epoch": 0.36, + "learning_rate": 1.4800200092961859e-05, + "loss": 0.462, + "step": 4227 + }, + { + "epoch": 0.36, + "learning_rate": 1.4797777278233779e-05, + "loss": 0.4666, + "step": 4228 + }, + { + "epoch": 0.36, + "learning_rate": 1.4795354097607169e-05, + "loss": 0.4928, + "step": 4229 + }, + { + "epoch": 0.36, + "learning_rate": 1.4792930551266836e-05, + "loss": 0.4896, + "step": 4230 + }, + { + "epoch": 0.36, + "learning_rate": 1.4790506639397613e-05, + "loss": 0.4793, + "step": 4231 + }, + { + "epoch": 0.36, + "learning_rate": 1.4788082362184348e-05, + "loss": 0.5037, + "step": 4232 + }, + { + "epoch": 0.36, + "learning_rate": 1.4785657719811938e-05, + "loss": 0.4662, + "step": 4233 + }, + { + "epoch": 0.36, + "learning_rate": 1.4783232712465287e-05, + "loss": 0.4948, + "step": 4234 + }, + { + "epoch": 0.36, + "learning_rate": 1.4780807340329342e-05, + "loss": 0.4933, + "step": 4235 + }, + { + "epoch": 0.36, + "learning_rate": 1.477838160358907e-05, + "loss": 0.4839, + "step": 4236 + }, + { + "epoch": 0.36, + "learning_rate": 1.4775955502429467e-05, + "loss": 0.501, + "step": 4237 + }, + { + "epoch": 0.36, + "learning_rate": 1.477352903703556e-05, + "loss": 0.4713, + "step": 4238 + }, + { + "epoch": 0.36, + "learning_rate": 1.4771102207592395e-05, + "loss": 0.504, + "step": 4239 + }, + { + "epoch": 0.36, + "learning_rate": 1.4768675014285063e-05, + "loss": 0.4804, + "step": 4240 + }, + { + "epoch": 0.36, + "learning_rate": 1.4766247457298661e-05, + "loss": 0.516, + "step": 4241 + }, + { + "epoch": 0.36, + "learning_rate": 1.4763819536818331e-05, + "loss": 0.4655, + "step": 4242 + }, + { + "epoch": 0.36, + "learning_rate": 1.4761391253029236e-05, + "loss": 0.4868, + "step": 4243 + }, + { + "epoch": 0.36, + "learning_rate": 1.4758962606116565e-05, + "loss": 0.4729, + "step": 4244 + }, + { + "epoch": 0.36, + "learning_rate": 1.4756533596265538e-05, + "loss": 0.472, + "step": 4245 + }, + { + "epoch": 0.36, + "learning_rate": 1.47541042236614e-05, + "loss": 0.4785, + "step": 4246 + }, + { + "epoch": 0.36, + "learning_rate": 1.4751674488489427e-05, + "loss": 0.4747, + "step": 4247 + }, + { + "epoch": 0.36, + "learning_rate": 1.474924439093492e-05, + "loss": 0.4826, + "step": 4248 + }, + { + "epoch": 0.36, + "learning_rate": 1.4746813931183209e-05, + "loss": 0.4778, + "step": 4249 + }, + { + "epoch": 0.36, + "learning_rate": 1.4744383109419646e-05, + "loss": 0.5044, + "step": 4250 + }, + { + "epoch": 0.36, + "learning_rate": 1.4741951925829625e-05, + "loss": 0.4916, + "step": 4251 + }, + { + "epoch": 0.36, + "learning_rate": 1.473952038059855e-05, + "loss": 0.498, + "step": 4252 + }, + { + "epoch": 0.36, + "learning_rate": 1.4737088473911865e-05, + "loss": 0.4942, + "step": 4253 + }, + { + "epoch": 0.36, + "learning_rate": 1.4734656205955037e-05, + "loss": 0.4792, + "step": 4254 + }, + { + "epoch": 0.36, + "learning_rate": 1.473222357691356e-05, + "loss": 0.465, + "step": 4255 + }, + { + "epoch": 0.36, + "learning_rate": 1.4729790586972957e-05, + "loss": 0.4865, + "step": 4256 + }, + { + "epoch": 0.36, + "learning_rate": 1.4727357236318773e-05, + "loss": 0.4745, + "step": 4257 + }, + { + "epoch": 0.36, + "learning_rate": 1.4724923525136597e-05, + "loss": 0.4913, + "step": 4258 + }, + { + "epoch": 0.36, + "learning_rate": 1.4722489453612023e-05, + "loss": 0.4653, + "step": 4259 + }, + { + "epoch": 0.36, + "learning_rate": 1.4720055021930686e-05, + "loss": 0.4964, + "step": 4260 + }, + { + "epoch": 0.36, + "learning_rate": 1.4717620230278249e-05, + "loss": 0.4765, + "step": 4261 + }, + { + "epoch": 0.36, + "learning_rate": 1.4715185078840399e-05, + "loss": 0.514, + "step": 4262 + }, + { + "epoch": 0.36, + "learning_rate": 1.4712749567802849e-05, + "loss": 0.4778, + "step": 4263 + }, + { + "epoch": 0.36, + "learning_rate": 1.4710313697351342e-05, + "loss": 0.4844, + "step": 4264 + }, + { + "epoch": 0.36, + "learning_rate": 1.4707877467671648e-05, + "loss": 0.503, + "step": 4265 + }, + { + "epoch": 0.36, + "learning_rate": 1.470544087894956e-05, + "loss": 0.5028, + "step": 4266 + }, + { + "epoch": 0.36, + "learning_rate": 1.470300393137091e-05, + "loss": 0.5071, + "step": 4267 + }, + { + "epoch": 0.36, + "learning_rate": 1.4700566625121543e-05, + "loss": 0.4909, + "step": 4268 + }, + { + "epoch": 0.36, + "learning_rate": 1.469812896038734e-05, + "loss": 0.481, + "step": 4269 + }, + { + "epoch": 0.36, + "learning_rate": 1.4695690937354212e-05, + "loss": 0.5, + "step": 4270 + }, + { + "epoch": 0.36, + "learning_rate": 1.4693252556208089e-05, + "loss": 0.5149, + "step": 4271 + }, + { + "epoch": 0.36, + "learning_rate": 1.469081381713493e-05, + "loss": 0.4844, + "step": 4272 + }, + { + "epoch": 0.36, + "learning_rate": 1.4688374720320729e-05, + "loss": 0.4787, + "step": 4273 + }, + { + "epoch": 0.36, + "learning_rate": 1.4685935265951495e-05, + "loss": 0.4711, + "step": 4274 + }, + { + "epoch": 0.36, + "learning_rate": 1.4683495454213277e-05, + "loss": 0.4897, + "step": 4275 + }, + { + "epoch": 0.36, + "learning_rate": 1.4681055285292138e-05, + "loss": 0.5089, + "step": 4276 + }, + { + "epoch": 0.36, + "learning_rate": 1.4678614759374186e-05, + "loss": 0.4781, + "step": 4277 + }, + { + "epoch": 0.36, + "learning_rate": 1.4676173876645537e-05, + "loss": 0.5099, + "step": 4278 + }, + { + "epoch": 0.36, + "learning_rate": 1.4673732637292344e-05, + "loss": 0.4755, + "step": 4279 + }, + { + "epoch": 0.36, + "learning_rate": 1.4671291041500791e-05, + "loss": 0.4824, + "step": 4280 + }, + { + "epoch": 0.37, + "learning_rate": 1.466884908945708e-05, + "loss": 0.4791, + "step": 4281 + }, + { + "epoch": 0.37, + "learning_rate": 1.4666406781347443e-05, + "loss": 0.4878, + "step": 4282 + }, + { + "epoch": 0.37, + "learning_rate": 1.4663964117358147e-05, + "loss": 0.5064, + "step": 4283 + }, + { + "epoch": 0.37, + "learning_rate": 1.4661521097675478e-05, + "loss": 0.4797, + "step": 4284 + }, + { + "epoch": 0.37, + "learning_rate": 1.4659077722485741e-05, + "loss": 0.4636, + "step": 4285 + }, + { + "epoch": 0.37, + "learning_rate": 1.4656633991975294e-05, + "loss": 0.4779, + "step": 4286 + }, + { + "epoch": 0.37, + "learning_rate": 1.4654189906330491e-05, + "loss": 0.5072, + "step": 4287 + }, + { + "epoch": 0.37, + "learning_rate": 1.465174546573774e-05, + "loss": 0.4794, + "step": 4288 + }, + { + "epoch": 0.37, + "learning_rate": 1.4649300670383456e-05, + "loss": 0.4956, + "step": 4289 + }, + { + "epoch": 0.37, + "learning_rate": 1.4646855520454096e-05, + "loss": 0.4882, + "step": 4290 + }, + { + "epoch": 0.37, + "learning_rate": 1.4644410016136132e-05, + "loss": 0.4944, + "step": 4291 + }, + { + "epoch": 0.37, + "learning_rate": 1.4641964157616068e-05, + "loss": 0.47, + "step": 4292 + }, + { + "epoch": 0.37, + "learning_rate": 1.4639517945080444e-05, + "loss": 0.4619, + "step": 4293 + }, + { + "epoch": 0.37, + "learning_rate": 1.4637071378715807e-05, + "loss": 0.5072, + "step": 4294 + }, + { + "epoch": 0.37, + "learning_rate": 1.4634624458708749e-05, + "loss": 0.4646, + "step": 4295 + }, + { + "epoch": 0.37, + "learning_rate": 1.463217718524588e-05, + "loss": 0.4926, + "step": 4296 + }, + { + "epoch": 0.37, + "learning_rate": 1.4629729558513841e-05, + "loss": 0.4767, + "step": 4297 + }, + { + "epoch": 0.37, + "learning_rate": 1.4627281578699297e-05, + "loss": 0.4875, + "step": 4298 + }, + { + "epoch": 0.37, + "learning_rate": 1.462483324598894e-05, + "loss": 0.5112, + "step": 4299 + }, + { + "epoch": 0.37, + "learning_rate": 1.4622384560569493e-05, + "loss": 0.4949, + "step": 4300 + }, + { + "epoch": 0.37, + "learning_rate": 1.4619935522627702e-05, + "loss": 0.5029, + "step": 4301 + }, + { + "epoch": 0.37, + "learning_rate": 1.4617486132350343e-05, + "loss": 0.488, + "step": 4302 + }, + { + "epoch": 0.37, + "learning_rate": 1.4615036389924209e-05, + "loss": 0.475, + "step": 4303 + }, + { + "epoch": 0.37, + "learning_rate": 1.4612586295536136e-05, + "loss": 0.4874, + "step": 4304 + }, + { + "epoch": 0.37, + "learning_rate": 1.4610135849372972e-05, + "loss": 0.4854, + "step": 4305 + }, + { + "epoch": 0.37, + "learning_rate": 1.4607685051621603e-05, + "loss": 0.4774, + "step": 4306 + }, + { + "epoch": 0.37, + "learning_rate": 1.4605233902468939e-05, + "loss": 0.4818, + "step": 4307 + }, + { + "epoch": 0.37, + "learning_rate": 1.4602782402101908e-05, + "loss": 0.4863, + "step": 4308 + }, + { + "epoch": 0.37, + "learning_rate": 1.4600330550707473e-05, + "loss": 0.4921, + "step": 4309 + }, + { + "epoch": 0.37, + "learning_rate": 1.4597878348472625e-05, + "loss": 0.5017, + "step": 4310 + }, + { + "epoch": 0.37, + "learning_rate": 1.4595425795584384e-05, + "loss": 0.4833, + "step": 4311 + }, + { + "epoch": 0.37, + "learning_rate": 1.4592972892229779e-05, + "loss": 0.517, + "step": 4312 + }, + { + "epoch": 0.37, + "learning_rate": 1.4590519638595892e-05, + "loss": 0.5049, + "step": 4313 + }, + { + "epoch": 0.37, + "learning_rate": 1.458806603486981e-05, + "loss": 0.482, + "step": 4314 + }, + { + "epoch": 0.37, + "learning_rate": 1.4585612081238656e-05, + "loss": 0.4842, + "step": 4315 + }, + { + "epoch": 0.37, + "learning_rate": 1.4583157777889585e-05, + "loss": 0.4801, + "step": 4316 + }, + { + "epoch": 0.37, + "learning_rate": 1.4580703125009765e-05, + "loss": 0.4681, + "step": 4317 + }, + { + "epoch": 0.37, + "learning_rate": 1.4578248122786401e-05, + "loss": 0.5027, + "step": 4318 + }, + { + "epoch": 0.37, + "learning_rate": 1.4575792771406719e-05, + "loss": 0.4861, + "step": 4319 + }, + { + "epoch": 0.37, + "learning_rate": 1.457333707105798e-05, + "loss": 0.4941, + "step": 4320 + }, + { + "epoch": 0.37, + "learning_rate": 1.4570881021927461e-05, + "loss": 0.4864, + "step": 4321 + }, + { + "epoch": 0.37, + "learning_rate": 1.4568424624202475e-05, + "loss": 0.4937, + "step": 4322 + }, + { + "epoch": 0.37, + "learning_rate": 1.4565967878070351e-05, + "loss": 0.4825, + "step": 4323 + }, + { + "epoch": 0.37, + "learning_rate": 1.4563510783718457e-05, + "loss": 0.4843, + "step": 4324 + }, + { + "epoch": 0.37, + "learning_rate": 1.456105334133418e-05, + "loss": 0.476, + "step": 4325 + }, + { + "epoch": 0.37, + "learning_rate": 1.455859555110493e-05, + "loss": 0.4944, + "step": 4326 + }, + { + "epoch": 0.37, + "learning_rate": 1.4556137413218153e-05, + "loss": 0.4901, + "step": 4327 + }, + { + "epoch": 0.37, + "learning_rate": 1.4553678927861314e-05, + "loss": 0.4698, + "step": 4328 + }, + { + "epoch": 0.37, + "learning_rate": 1.4551220095221911e-05, + "loss": 0.4963, + "step": 4329 + }, + { + "epoch": 0.37, + "learning_rate": 1.4548760915487463e-05, + "loss": 0.4614, + "step": 4330 + }, + { + "epoch": 0.37, + "learning_rate": 1.4546301388845515e-05, + "loss": 0.4796, + "step": 4331 + }, + { + "epoch": 0.37, + "learning_rate": 1.4543841515483645e-05, + "loss": 0.4999, + "step": 4332 + }, + { + "epoch": 0.37, + "learning_rate": 1.454138129558945e-05, + "loss": 0.5036, + "step": 4333 + }, + { + "epoch": 0.37, + "learning_rate": 1.4538920729350559e-05, + "loss": 0.4533, + "step": 4334 + }, + { + "epoch": 0.37, + "learning_rate": 1.4536459816954623e-05, + "loss": 0.4986, + "step": 4335 + }, + { + "epoch": 0.37, + "learning_rate": 1.4533998558589319e-05, + "loss": 0.4806, + "step": 4336 + }, + { + "epoch": 0.37, + "learning_rate": 1.4531536954442363e-05, + "loss": 0.4931, + "step": 4337 + }, + { + "epoch": 0.37, + "learning_rate": 1.4529075004701474e-05, + "loss": 0.496, + "step": 4338 + }, + { + "epoch": 0.37, + "learning_rate": 1.452661270955442e-05, + "loss": 0.4814, + "step": 4339 + }, + { + "epoch": 0.37, + "learning_rate": 1.452415006918898e-05, + "loss": 0.4898, + "step": 4340 + }, + { + "epoch": 0.37, + "learning_rate": 1.452168708379297e-05, + "loss": 0.488, + "step": 4341 + }, + { + "epoch": 0.37, + "learning_rate": 1.4519223753554223e-05, + "loss": 0.5023, + "step": 4342 + }, + { + "epoch": 0.37, + "learning_rate": 1.451676007866061e-05, + "loss": 0.4861, + "step": 4343 + }, + { + "epoch": 0.37, + "learning_rate": 1.4514296059300014e-05, + "loss": 0.4874, + "step": 4344 + }, + { + "epoch": 0.37, + "learning_rate": 1.4511831695660354e-05, + "loss": 0.49, + "step": 4345 + }, + { + "epoch": 0.37, + "learning_rate": 1.4509366987929574e-05, + "loss": 0.4737, + "step": 4346 + }, + { + "epoch": 0.37, + "learning_rate": 1.4506901936295638e-05, + "loss": 0.4792, + "step": 4347 + }, + { + "epoch": 0.37, + "learning_rate": 1.4504436540946548e-05, + "loss": 0.4914, + "step": 4348 + }, + { + "epoch": 0.37, + "learning_rate": 1.450197080207032e-05, + "loss": 0.507, + "step": 4349 + }, + { + "epoch": 0.37, + "learning_rate": 1.4499504719855002e-05, + "loss": 0.4753, + "step": 4350 + }, + { + "epoch": 0.37, + "learning_rate": 1.449703829448867e-05, + "loss": 0.4912, + "step": 4351 + }, + { + "epoch": 0.37, + "learning_rate": 1.4494571526159427e-05, + "loss": 0.4964, + "step": 4352 + }, + { + "epoch": 0.37, + "learning_rate": 1.4492104415055393e-05, + "loss": 0.4775, + "step": 4353 + }, + { + "epoch": 0.37, + "learning_rate": 1.4489636961364719e-05, + "loss": 0.4802, + "step": 4354 + }, + { + "epoch": 0.37, + "learning_rate": 1.4487169165275592e-05, + "loss": 0.4754, + "step": 4355 + }, + { + "epoch": 0.37, + "learning_rate": 1.4484701026976207e-05, + "loss": 0.4595, + "step": 4356 + }, + { + "epoch": 0.37, + "learning_rate": 1.4482232546654799e-05, + "loss": 0.4892, + "step": 4357 + }, + { + "epoch": 0.37, + "learning_rate": 1.4479763724499627e-05, + "loss": 0.4908, + "step": 4358 + }, + { + "epoch": 0.37, + "learning_rate": 1.4477294560698968e-05, + "loss": 0.4801, + "step": 4359 + }, + { + "epoch": 0.37, + "learning_rate": 1.4474825055441135e-05, + "loss": 0.4719, + "step": 4360 + }, + { + "epoch": 0.37, + "learning_rate": 1.4472355208914462e-05, + "loss": 0.4755, + "step": 4361 + }, + { + "epoch": 0.37, + "learning_rate": 1.4469885021307308e-05, + "loss": 0.4928, + "step": 4362 + }, + { + "epoch": 0.37, + "learning_rate": 1.4467414492808061e-05, + "loss": 0.496, + "step": 4363 + }, + { + "epoch": 0.37, + "learning_rate": 1.4464943623605136e-05, + "loss": 0.4923, + "step": 4364 + }, + { + "epoch": 0.37, + "learning_rate": 1.4462472413886965e-05, + "loss": 0.4818, + "step": 4365 + }, + { + "epoch": 0.37, + "learning_rate": 1.4460000863842023e-05, + "loss": 0.4822, + "step": 4366 + }, + { + "epoch": 0.37, + "learning_rate": 1.4457528973658793e-05, + "loss": 0.4815, + "step": 4367 + }, + { + "epoch": 0.37, + "learning_rate": 1.4455056743525793e-05, + "loss": 0.492, + "step": 4368 + }, + { + "epoch": 0.37, + "learning_rate": 1.445258417363157e-05, + "loss": 0.4611, + "step": 4369 + }, + { + "epoch": 0.37, + "learning_rate": 1.4450111264164683e-05, + "loss": 0.4825, + "step": 4370 + }, + { + "epoch": 0.37, + "learning_rate": 1.4447638015313737e-05, + "loss": 0.4967, + "step": 4371 + }, + { + "epoch": 0.37, + "learning_rate": 1.4445164427267344e-05, + "loss": 0.528, + "step": 4372 + }, + { + "epoch": 0.37, + "learning_rate": 1.4442690500214158e-05, + "loss": 0.4656, + "step": 4373 + }, + { + "epoch": 0.37, + "learning_rate": 1.444021623434284e-05, + "loss": 0.4944, + "step": 4374 + }, + { + "epoch": 0.37, + "learning_rate": 1.4437741629842103e-05, + "loss": 0.4999, + "step": 4375 + }, + { + "epoch": 0.37, + "learning_rate": 1.443526668690066e-05, + "loss": 0.4789, + "step": 4376 + }, + { + "epoch": 0.37, + "learning_rate": 1.4432791405707257e-05, + "loss": 0.5054, + "step": 4377 + }, + { + "epoch": 0.37, + "learning_rate": 1.4430315786450683e-05, + "loss": 0.4885, + "step": 4378 + }, + { + "epoch": 0.37, + "learning_rate": 1.4427839829319728e-05, + "loss": 0.4687, + "step": 4379 + }, + { + "epoch": 0.37, + "learning_rate": 1.442536353450322e-05, + "loss": 0.5444, + "step": 4380 + }, + { + "epoch": 0.37, + "learning_rate": 1.4422886902190014e-05, + "loss": 0.494, + "step": 4381 + }, + { + "epoch": 0.37, + "learning_rate": 1.442040993256899e-05, + "loss": 0.4696, + "step": 4382 + }, + { + "epoch": 0.37, + "learning_rate": 1.4417932625829045e-05, + "loss": 0.5168, + "step": 4383 + }, + { + "epoch": 0.37, + "learning_rate": 1.4415454982159121e-05, + "loss": 0.5032, + "step": 4384 + }, + { + "epoch": 0.37, + "learning_rate": 1.4412977001748164e-05, + "loss": 0.4778, + "step": 4385 + }, + { + "epoch": 0.37, + "learning_rate": 1.4410498684785153e-05, + "loss": 0.4758, + "step": 4386 + }, + { + "epoch": 0.37, + "learning_rate": 1.4408020031459103e-05, + "loss": 0.4985, + "step": 4387 + }, + { + "epoch": 0.37, + "learning_rate": 1.440554104195904e-05, + "loss": 0.4866, + "step": 4388 + }, + { + "epoch": 0.37, + "learning_rate": 1.4403061716474026e-05, + "loss": 0.4645, + "step": 4389 + }, + { + "epoch": 0.37, + "learning_rate": 1.4400582055193143e-05, + "loss": 0.5033, + "step": 4390 + }, + { + "epoch": 0.37, + "learning_rate": 1.43981020583055e-05, + "loss": 0.503, + "step": 4391 + }, + { + "epoch": 0.37, + "learning_rate": 1.4395621726000232e-05, + "loss": 0.4919, + "step": 4392 + }, + { + "epoch": 0.37, + "learning_rate": 1.4393141058466502e-05, + "loss": 0.506, + "step": 4393 + }, + { + "epoch": 0.37, + "learning_rate": 1.4390660055893495e-05, + "loss": 0.4981, + "step": 4394 + }, + { + "epoch": 0.37, + "learning_rate": 1.4388178718470416e-05, + "loss": 0.4832, + "step": 4395 + }, + { + "epoch": 0.37, + "learning_rate": 1.4385697046386513e-05, + "loss": 0.4907, + "step": 4396 + }, + { + "epoch": 0.37, + "learning_rate": 1.4383215039831042e-05, + "loss": 0.5112, + "step": 4397 + }, + { + "epoch": 0.38, + "learning_rate": 1.4380732698993291e-05, + "loss": 0.4798, + "step": 4398 + }, + { + "epoch": 0.38, + "learning_rate": 1.4378250024062577e-05, + "loss": 0.4705, + "step": 4399 + }, + { + "epoch": 0.38, + "learning_rate": 1.437576701522824e-05, + "loss": 0.4889, + "step": 4400 + }, + { + "epoch": 0.38, + "learning_rate": 1.4373283672679638e-05, + "loss": 0.4848, + "step": 4401 + }, + { + "epoch": 0.38, + "learning_rate": 1.4370799996606169e-05, + "loss": 0.4846, + "step": 4402 + }, + { + "epoch": 0.38, + "learning_rate": 1.4368315987197244e-05, + "loss": 0.4869, + "step": 4403 + }, + { + "epoch": 0.38, + "learning_rate": 1.43658316446423e-05, + "loss": 0.4805, + "step": 4404 + }, + { + "epoch": 0.38, + "learning_rate": 1.4363346969130813e-05, + "loss": 0.4686, + "step": 4405 + }, + { + "epoch": 0.38, + "learning_rate": 1.4360861960852268e-05, + "loss": 0.4772, + "step": 4406 + }, + { + "epoch": 0.38, + "learning_rate": 1.4358376619996182e-05, + "loss": 0.4993, + "step": 4407 + }, + { + "epoch": 0.38, + "learning_rate": 1.4355890946752102e-05, + "loss": 0.4808, + "step": 4408 + }, + { + "epoch": 0.38, + "learning_rate": 1.4353404941309594e-05, + "loss": 0.4596, + "step": 4409 + }, + { + "epoch": 0.38, + "learning_rate": 1.4350918603858248e-05, + "loss": 0.4806, + "step": 4410 + }, + { + "epoch": 0.38, + "learning_rate": 1.4348431934587685e-05, + "loss": 0.4868, + "step": 4411 + }, + { + "epoch": 0.38, + "learning_rate": 1.4345944933687548e-05, + "loss": 0.4746, + "step": 4412 + }, + { + "epoch": 0.38, + "learning_rate": 1.4343457601347505e-05, + "loss": 0.4809, + "step": 4413 + }, + { + "epoch": 0.38, + "learning_rate": 1.4340969937757256e-05, + "loss": 0.499, + "step": 4414 + }, + { + "epoch": 0.38, + "learning_rate": 1.4338481943106516e-05, + "loss": 0.4808, + "step": 4415 + }, + { + "epoch": 0.38, + "learning_rate": 1.433599361758503e-05, + "loss": 0.4947, + "step": 4416 + }, + { + "epoch": 0.38, + "learning_rate": 1.4333504961382566e-05, + "loss": 0.4946, + "step": 4417 + }, + { + "epoch": 0.38, + "learning_rate": 1.4331015974688925e-05, + "loss": 0.4783, + "step": 4418 + }, + { + "epoch": 0.38, + "learning_rate": 1.4328526657693922e-05, + "loss": 0.4901, + "step": 4419 + }, + { + "epoch": 0.38, + "learning_rate": 1.4326037010587406e-05, + "loss": 0.4751, + "step": 4420 + }, + { + "epoch": 0.38, + "learning_rate": 1.4323547033559247e-05, + "loss": 0.4691, + "step": 4421 + }, + { + "epoch": 0.38, + "learning_rate": 1.4321056726799338e-05, + "loss": 0.4792, + "step": 4422 + }, + { + "epoch": 0.38, + "learning_rate": 1.4318566090497607e-05, + "loss": 0.4918, + "step": 4423 + }, + { + "epoch": 0.38, + "learning_rate": 1.4316075124843996e-05, + "loss": 0.4694, + "step": 4424 + }, + { + "epoch": 0.38, + "learning_rate": 1.4313583830028476e-05, + "loss": 0.4928, + "step": 4425 + }, + { + "epoch": 0.38, + "learning_rate": 1.4311092206241046e-05, + "loss": 0.506, + "step": 4426 + }, + { + "epoch": 0.38, + "learning_rate": 1.4308600253671725e-05, + "loss": 0.4898, + "step": 4427 + }, + { + "epoch": 0.38, + "learning_rate": 1.4306107972510559e-05, + "loss": 0.4629, + "step": 4428 + }, + { + "epoch": 0.38, + "learning_rate": 1.4303615362947623e-05, + "loss": 0.4889, + "step": 4429 + }, + { + "epoch": 0.38, + "learning_rate": 1.4301122425173014e-05, + "loss": 0.49, + "step": 4430 + }, + { + "epoch": 0.38, + "learning_rate": 1.4298629159376852e-05, + "loss": 0.4914, + "step": 4431 + }, + { + "epoch": 0.38, + "learning_rate": 1.429613556574928e-05, + "loss": 0.5174, + "step": 4432 + }, + { + "epoch": 0.38, + "learning_rate": 1.4293641644480478e-05, + "loss": 0.4693, + "step": 4433 + }, + { + "epoch": 0.38, + "learning_rate": 1.4291147395760637e-05, + "loss": 0.4629, + "step": 4434 + }, + { + "epoch": 0.38, + "learning_rate": 1.4288652819779982e-05, + "loss": 0.4888, + "step": 4435 + }, + { + "epoch": 0.38, + "learning_rate": 1.4286157916728756e-05, + "loss": 0.4962, + "step": 4436 + }, + { + "epoch": 0.38, + "learning_rate": 1.4283662686797236e-05, + "loss": 0.4732, + "step": 4437 + }, + { + "epoch": 0.38, + "learning_rate": 1.4281167130175712e-05, + "loss": 0.4731, + "step": 4438 + }, + { + "epoch": 0.38, + "learning_rate": 1.4278671247054511e-05, + "loss": 0.4913, + "step": 4439 + }, + { + "epoch": 0.38, + "learning_rate": 1.4276175037623981e-05, + "loss": 0.4853, + "step": 4440 + }, + { + "epoch": 0.38, + "learning_rate": 1.4273678502074487e-05, + "loss": 0.5042, + "step": 4441 + }, + { + "epoch": 0.38, + "learning_rate": 1.4271181640596428e-05, + "loss": 0.4729, + "step": 4442 + }, + { + "epoch": 0.38, + "learning_rate": 1.4268684453380227e-05, + "loss": 0.4701, + "step": 4443 + }, + { + "epoch": 0.38, + "learning_rate": 1.426618694061633e-05, + "loss": 0.4708, + "step": 4444 + }, + { + "epoch": 0.38, + "learning_rate": 1.42636891024952e-05, + "loss": 0.4743, + "step": 4445 + }, + { + "epoch": 0.38, + "learning_rate": 1.4261190939207343e-05, + "loss": 0.4837, + "step": 4446 + }, + { + "epoch": 0.38, + "learning_rate": 1.4258692450943276e-05, + "loss": 0.4758, + "step": 4447 + }, + { + "epoch": 0.38, + "learning_rate": 1.425619363789354e-05, + "loss": 0.5049, + "step": 4448 + }, + { + "epoch": 0.38, + "learning_rate": 1.4253694500248711e-05, + "loss": 0.4891, + "step": 4449 + }, + { + "epoch": 0.38, + "learning_rate": 1.425119503819938e-05, + "loss": 0.4915, + "step": 4450 + }, + { + "epoch": 0.38, + "learning_rate": 1.4248695251936167e-05, + "loss": 0.4923, + "step": 4451 + }, + { + "epoch": 0.38, + "learning_rate": 1.4246195141649715e-05, + "loss": 0.5001, + "step": 4452 + }, + { + "epoch": 0.38, + "learning_rate": 1.4243694707530696e-05, + "loss": 0.4767, + "step": 4453 + }, + { + "epoch": 0.38, + "learning_rate": 1.42411939497698e-05, + "loss": 0.478, + "step": 4454 + }, + { + "epoch": 0.38, + "learning_rate": 1.4238692868557748e-05, + "loss": 0.506, + "step": 4455 + }, + { + "epoch": 0.38, + "learning_rate": 1.4236191464085286e-05, + "loss": 0.4902, + "step": 4456 + }, + { + "epoch": 0.38, + "learning_rate": 1.4233689736543168e-05, + "loss": 0.4871, + "step": 4457 + }, + { + "epoch": 0.38, + "learning_rate": 1.4231187686122203e-05, + "loss": 0.4949, + "step": 4458 + }, + { + "epoch": 0.38, + "learning_rate": 1.4228685313013198e-05, + "loss": 0.4835, + "step": 4459 + }, + { + "epoch": 0.38, + "learning_rate": 1.4226182617406996e-05, + "loss": 0.4832, + "step": 4460 + }, + { + "epoch": 0.38, + "learning_rate": 1.4223679599494465e-05, + "loss": 0.4844, + "step": 4461 + }, + { + "epoch": 0.38, + "learning_rate": 1.4221176259466493e-05, + "loss": 0.4952, + "step": 4462 + }, + { + "epoch": 0.38, + "learning_rate": 1.4218672597513999e-05, + "loss": 0.473, + "step": 4463 + }, + { + "epoch": 0.38, + "learning_rate": 1.4216168613827918e-05, + "loss": 0.488, + "step": 4464 + }, + { + "epoch": 0.38, + "learning_rate": 1.421366430859922e-05, + "loss": 0.5054, + "step": 4465 + }, + { + "epoch": 0.38, + "learning_rate": 1.4211159682018884e-05, + "loss": 0.5021, + "step": 4466 + }, + { + "epoch": 0.38, + "learning_rate": 1.4208654734277936e-05, + "loss": 0.4831, + "step": 4467 + }, + { + "epoch": 0.38, + "learning_rate": 1.4206149465567402e-05, + "loss": 0.5069, + "step": 4468 + }, + { + "epoch": 0.38, + "learning_rate": 1.4203643876078354e-05, + "loss": 0.4841, + "step": 4469 + }, + { + "epoch": 0.38, + "learning_rate": 1.4201137966001874e-05, + "loss": 0.4932, + "step": 4470 + }, + { + "epoch": 0.38, + "learning_rate": 1.419863173552907e-05, + "loss": 0.4994, + "step": 4471 + }, + { + "epoch": 0.38, + "learning_rate": 1.4196125184851085e-05, + "loss": 0.4824, + "step": 4472 + }, + { + "epoch": 0.38, + "learning_rate": 1.4193618314159072e-05, + "loss": 0.4724, + "step": 4473 + }, + { + "epoch": 0.38, + "learning_rate": 1.419111112364422e-05, + "loss": 0.4785, + "step": 4474 + }, + { + "epoch": 0.38, + "learning_rate": 1.4188603613497735e-05, + "loss": 0.5023, + "step": 4475 + }, + { + "epoch": 0.38, + "learning_rate": 1.4186095783910854e-05, + "loss": 0.4858, + "step": 4476 + }, + { + "epoch": 0.38, + "learning_rate": 1.4183587635074831e-05, + "loss": 0.48, + "step": 4477 + }, + { + "epoch": 0.38, + "learning_rate": 1.4181079167180949e-05, + "loss": 0.5025, + "step": 4478 + }, + { + "epoch": 0.38, + "learning_rate": 1.4178570380420516e-05, + "loss": 0.4913, + "step": 4479 + }, + { + "epoch": 0.38, + "learning_rate": 1.4176061274984858e-05, + "loss": 0.4978, + "step": 4480 + }, + { + "epoch": 0.38, + "learning_rate": 1.4173551851065333e-05, + "loss": 0.4865, + "step": 4481 + }, + { + "epoch": 0.38, + "learning_rate": 1.4171042108853319e-05, + "loss": 0.4989, + "step": 4482 + }, + { + "epoch": 0.38, + "learning_rate": 1.4168532048540225e-05, + "loss": 0.5019, + "step": 4483 + }, + { + "epoch": 0.38, + "learning_rate": 1.4166021670317465e-05, + "loss": 0.5025, + "step": 4484 + }, + { + "epoch": 0.38, + "learning_rate": 1.4163510974376507e-05, + "loss": 0.4831, + "step": 4485 + }, + { + "epoch": 0.38, + "learning_rate": 1.4160999960908818e-05, + "loss": 0.4716, + "step": 4486 + }, + { + "epoch": 0.38, + "learning_rate": 1.4158488630105899e-05, + "loss": 0.5052, + "step": 4487 + }, + { + "epoch": 0.38, + "learning_rate": 1.415597698215928e-05, + "loss": 0.4896, + "step": 4488 + }, + { + "epoch": 0.38, + "learning_rate": 1.4153465017260504e-05, + "loss": 0.4702, + "step": 4489 + }, + { + "epoch": 0.38, + "learning_rate": 1.4150952735601143e-05, + "loss": 0.4665, + "step": 4490 + }, + { + "epoch": 0.38, + "learning_rate": 1.4148440137372799e-05, + "loss": 0.4865, + "step": 4491 + }, + { + "epoch": 0.38, + "learning_rate": 1.414592722276709e-05, + "loss": 0.494, + "step": 4492 + }, + { + "epoch": 0.38, + "learning_rate": 1.4143413991975663e-05, + "loss": 0.4633, + "step": 4493 + }, + { + "epoch": 0.38, + "learning_rate": 1.4140900445190187e-05, + "loss": 0.521, + "step": 4494 + }, + { + "epoch": 0.38, + "learning_rate": 1.4138386582602353e-05, + "loss": 0.4813, + "step": 4495 + }, + { + "epoch": 0.38, + "learning_rate": 1.4135872404403881e-05, + "loss": 0.4809, + "step": 4496 + }, + { + "epoch": 0.38, + "learning_rate": 1.4133357910786517e-05, + "loss": 0.4827, + "step": 4497 + }, + { + "epoch": 0.38, + "learning_rate": 1.4130843101942017e-05, + "loss": 0.4997, + "step": 4498 + }, + { + "epoch": 0.38, + "learning_rate": 1.412832797806218e-05, + "loss": 0.4967, + "step": 4499 + }, + { + "epoch": 0.38, + "learning_rate": 1.4125812539338814e-05, + "loss": 0.4881, + "step": 4500 + }, + { + "epoch": 0.38, + "learning_rate": 1.412329678596376e-05, + "loss": 0.4886, + "step": 4501 + }, + { + "epoch": 0.38, + "learning_rate": 1.4120780718128879e-05, + "loss": 0.4564, + "step": 4502 + }, + { + "epoch": 0.38, + "learning_rate": 1.4118264336026057e-05, + "loss": 0.4866, + "step": 4503 + }, + { + "epoch": 0.38, + "learning_rate": 1.4115747639847204e-05, + "loss": 0.4756, + "step": 4504 + }, + { + "epoch": 0.38, + "learning_rate": 1.411323062978425e-05, + "loss": 0.4915, + "step": 4505 + }, + { + "epoch": 0.38, + "learning_rate": 1.4110713306029161e-05, + "loss": 0.4586, + "step": 4506 + }, + { + "epoch": 0.38, + "learning_rate": 1.410819566877391e-05, + "loss": 0.4815, + "step": 4507 + }, + { + "epoch": 0.38, + "learning_rate": 1.4105677718210506e-05, + "loss": 0.4905, + "step": 4508 + }, + { + "epoch": 0.38, + "learning_rate": 1.4103159454530982e-05, + "loss": 0.4889, + "step": 4509 + }, + { + "epoch": 0.38, + "learning_rate": 1.4100640877927383e-05, + "loss": 0.4974, + "step": 4510 + }, + { + "epoch": 0.38, + "learning_rate": 1.4098121988591796e-05, + "loss": 0.4797, + "step": 4511 + }, + { + "epoch": 0.38, + "learning_rate": 1.4095602786716312e-05, + "loss": 0.482, + "step": 4512 + }, + { + "epoch": 0.38, + "learning_rate": 1.4093083272493061e-05, + "loss": 0.494, + "step": 4513 + }, + { + "epoch": 0.38, + "learning_rate": 1.4090563446114195e-05, + "loss": 0.5172, + "step": 4514 + }, + { + "epoch": 0.38, + "learning_rate": 1.4088043307771883e-05, + "loss": 0.486, + "step": 4515 + }, + { + "epoch": 0.39, + "learning_rate": 1.4085522857658321e-05, + "loss": 0.471, + "step": 4516 + }, + { + "epoch": 0.39, + "learning_rate": 1.4083002095965727e-05, + "loss": 0.4894, + "step": 4517 + }, + { + "epoch": 0.39, + "learning_rate": 1.4080481022886349e-05, + "loss": 0.491, + "step": 4518 + }, + { + "epoch": 0.39, + "learning_rate": 1.4077959638612451e-05, + "loss": 0.472, + "step": 4519 + }, + { + "epoch": 0.39, + "learning_rate": 1.4075437943336328e-05, + "loss": 0.4687, + "step": 4520 + }, + { + "epoch": 0.39, + "learning_rate": 1.4072915937250294e-05, + "loss": 0.5033, + "step": 4521 + }, + { + "epoch": 0.39, + "learning_rate": 1.4070393620546684e-05, + "loss": 0.4654, + "step": 4522 + }, + { + "epoch": 0.39, + "learning_rate": 1.4067870993417863e-05, + "loss": 0.5024, + "step": 4523 + }, + { + "epoch": 0.39, + "learning_rate": 1.4065348056056219e-05, + "loss": 0.4825, + "step": 4524 + }, + { + "epoch": 0.39, + "learning_rate": 1.4062824808654158e-05, + "loss": 0.4901, + "step": 4525 + }, + { + "epoch": 0.39, + "learning_rate": 1.4060301251404116e-05, + "loss": 0.4977, + "step": 4526 + }, + { + "epoch": 0.39, + "learning_rate": 1.4057777384498551e-05, + "loss": 0.4783, + "step": 4527 + }, + { + "epoch": 0.39, + "learning_rate": 1.405525320812994e-05, + "loss": 0.4708, + "step": 4528 + }, + { + "epoch": 0.39, + "learning_rate": 1.405272872249079e-05, + "loss": 0.4786, + "step": 4529 + }, + { + "epoch": 0.39, + "learning_rate": 1.4050203927773627e-05, + "loss": 0.4817, + "step": 4530 + }, + { + "epoch": 0.39, + "learning_rate": 1.4047678824171005e-05, + "loss": 0.4951, + "step": 4531 + }, + { + "epoch": 0.39, + "learning_rate": 1.4045153411875497e-05, + "loss": 0.4807, + "step": 4532 + }, + { + "epoch": 0.39, + "learning_rate": 1.4042627691079701e-05, + "loss": 0.4849, + "step": 4533 + }, + { + "epoch": 0.39, + "learning_rate": 1.4040101661976239e-05, + "loss": 0.5022, + "step": 4534 + }, + { + "epoch": 0.39, + "learning_rate": 1.4037575324757759e-05, + "loss": 0.4907, + "step": 4535 + }, + { + "epoch": 0.39, + "learning_rate": 1.403504867961693e-05, + "loss": 0.4671, + "step": 4536 + }, + { + "epoch": 0.39, + "learning_rate": 1.4032521726746438e-05, + "loss": 0.4994, + "step": 4537 + }, + { + "epoch": 0.39, + "learning_rate": 1.4029994466339007e-05, + "loss": 0.4623, + "step": 4538 + }, + { + "epoch": 0.39, + "learning_rate": 1.4027466898587375e-05, + "loss": 0.464, + "step": 4539 + }, + { + "epoch": 0.39, + "learning_rate": 1.4024939023684298e-05, + "loss": 0.5021, + "step": 4540 + }, + { + "epoch": 0.39, + "learning_rate": 1.4022410841822574e-05, + "loss": 0.4946, + "step": 4541 + }, + { + "epoch": 0.39, + "learning_rate": 1.4019882353195002e-05, + "loss": 0.4858, + "step": 4542 + }, + { + "epoch": 0.39, + "learning_rate": 1.401735355799442e-05, + "loss": 0.4913, + "step": 4543 + }, + { + "epoch": 0.39, + "learning_rate": 1.401482445641368e-05, + "loss": 0.4836, + "step": 4544 + }, + { + "epoch": 0.39, + "learning_rate": 1.4012295048645672e-05, + "loss": 0.4983, + "step": 4545 + }, + { + "epoch": 0.39, + "learning_rate": 1.4009765334883287e-05, + "loss": 0.4779, + "step": 4546 + }, + { + "epoch": 0.39, + "learning_rate": 1.4007235315319463e-05, + "loss": 0.4883, + "step": 4547 + }, + { + "epoch": 0.39, + "learning_rate": 1.4004704990147142e-05, + "loss": 0.4861, + "step": 4548 + }, + { + "epoch": 0.39, + "learning_rate": 1.4002174359559298e-05, + "loss": 0.4824, + "step": 4549 + }, + { + "epoch": 0.39, + "learning_rate": 1.399964342374893e-05, + "loss": 0.5008, + "step": 4550 + }, + { + "epoch": 0.39, + "learning_rate": 1.3997112182909053e-05, + "loss": 0.503, + "step": 4551 + }, + { + "epoch": 0.39, + "learning_rate": 1.3994580637232717e-05, + "loss": 0.5086, + "step": 4552 + }, + { + "epoch": 0.39, + "learning_rate": 1.3992048786912984e-05, + "loss": 0.4877, + "step": 4553 + }, + { + "epoch": 0.39, + "learning_rate": 1.3989516632142946e-05, + "loss": 0.4833, + "step": 4554 + }, + { + "epoch": 0.39, + "learning_rate": 1.3986984173115709e-05, + "loss": 0.4638, + "step": 4555 + }, + { + "epoch": 0.39, + "learning_rate": 1.398445141002442e-05, + "loss": 0.4678, + "step": 4556 + }, + { + "epoch": 0.39, + "learning_rate": 1.398191834306223e-05, + "loss": 0.4829, + "step": 4557 + }, + { + "epoch": 0.39, + "learning_rate": 1.397938497242232e-05, + "loss": 0.4961, + "step": 4558 + }, + { + "epoch": 0.39, + "learning_rate": 1.3976851298297902e-05, + "loss": 0.4826, + "step": 4559 + }, + { + "epoch": 0.39, + "learning_rate": 1.39743173208822e-05, + "loss": 0.4939, + "step": 4560 + }, + { + "epoch": 0.39, + "learning_rate": 1.3971783040368465e-05, + "loss": 0.4796, + "step": 4561 + }, + { + "epoch": 0.39, + "learning_rate": 1.3969248456949975e-05, + "loss": 0.4819, + "step": 4562 + }, + { + "epoch": 0.39, + "learning_rate": 1.3966713570820028e-05, + "loss": 0.4951, + "step": 4563 + }, + { + "epoch": 0.39, + "learning_rate": 1.3964178382171942e-05, + "loss": 0.4883, + "step": 4564 + }, + { + "epoch": 0.39, + "learning_rate": 1.3961642891199063e-05, + "loss": 0.4988, + "step": 4565 + }, + { + "epoch": 0.39, + "learning_rate": 1.3959107098094758e-05, + "loss": 0.4742, + "step": 4566 + }, + { + "epoch": 0.39, + "learning_rate": 1.3956571003052416e-05, + "loss": 0.474, + "step": 4567 + }, + { + "epoch": 0.39, + "learning_rate": 1.3954034606265452e-05, + "loss": 0.4725, + "step": 4568 + }, + { + "epoch": 0.39, + "learning_rate": 1.39514979079273e-05, + "loss": 0.488, + "step": 4569 + }, + { + "epoch": 0.39, + "learning_rate": 1.3948960908231422e-05, + "loss": 0.493, + "step": 4570 + }, + { + "epoch": 0.39, + "learning_rate": 1.3946423607371298e-05, + "loss": 0.4928, + "step": 4571 + }, + { + "epoch": 0.39, + "learning_rate": 1.3943886005540436e-05, + "loss": 0.4888, + "step": 4572 + }, + { + "epoch": 0.39, + "learning_rate": 1.394134810293236e-05, + "loss": 0.4999, + "step": 4573 + }, + { + "epoch": 0.39, + "learning_rate": 1.3938809899740622e-05, + "loss": 0.4565, + "step": 4574 + }, + { + "epoch": 0.39, + "learning_rate": 1.3936271396158798e-05, + "loss": 0.4858, + "step": 4575 + }, + { + "epoch": 0.39, + "learning_rate": 1.3933732592380485e-05, + "loss": 0.4879, + "step": 4576 + }, + { + "epoch": 0.39, + "learning_rate": 1.3931193488599301e-05, + "loss": 0.4873, + "step": 4577 + }, + { + "epoch": 0.39, + "learning_rate": 1.3928654085008887e-05, + "loss": 0.4896, + "step": 4578 + }, + { + "epoch": 0.39, + "learning_rate": 1.3926114381802915e-05, + "loss": 0.5055, + "step": 4579 + }, + { + "epoch": 0.39, + "learning_rate": 1.3923574379175068e-05, + "loss": 0.4847, + "step": 4580 + }, + { + "epoch": 0.39, + "learning_rate": 1.3921034077319057e-05, + "loss": 0.4963, + "step": 4581 + }, + { + "epoch": 0.39, + "learning_rate": 1.3918493476428618e-05, + "loss": 0.485, + "step": 4582 + }, + { + "epoch": 0.39, + "learning_rate": 1.3915952576697507e-05, + "loss": 0.4743, + "step": 4583 + }, + { + "epoch": 0.39, + "learning_rate": 1.3913411378319503e-05, + "loss": 0.4865, + "step": 4584 + }, + { + "epoch": 0.39, + "learning_rate": 1.391086988148841e-05, + "loss": 0.4739, + "step": 4585 + }, + { + "epoch": 0.39, + "learning_rate": 1.3908328086398055e-05, + "loss": 0.4952, + "step": 4586 + }, + { + "epoch": 0.39, + "learning_rate": 1.3905785993242283e-05, + "loss": 0.4671, + "step": 4587 + }, + { + "epoch": 0.39, + "learning_rate": 1.390324360221496e-05, + "loss": 0.4878, + "step": 4588 + }, + { + "epoch": 0.39, + "learning_rate": 1.3900700913509991e-05, + "loss": 0.4679, + "step": 4589 + }, + { + "epoch": 0.39, + "learning_rate": 1.3898157927321278e-05, + "loss": 0.4738, + "step": 4590 + }, + { + "epoch": 0.39, + "learning_rate": 1.3895614643842773e-05, + "loss": 0.5035, + "step": 4591 + }, + { + "epoch": 0.39, + "learning_rate": 1.3893071063268431e-05, + "loss": 0.4829, + "step": 4592 + }, + { + "epoch": 0.39, + "learning_rate": 1.3890527185792233e-05, + "loss": 0.4692, + "step": 4593 + }, + { + "epoch": 0.39, + "learning_rate": 1.3887983011608192e-05, + "loss": 0.4741, + "step": 4594 + }, + { + "epoch": 0.39, + "learning_rate": 1.3885438540910336e-05, + "loss": 0.4941, + "step": 4595 + }, + { + "epoch": 0.39, + "learning_rate": 1.3882893773892714e-05, + "loss": 0.4859, + "step": 4596 + }, + { + "epoch": 0.39, + "learning_rate": 1.3880348710749401e-05, + "loss": 0.4976, + "step": 4597 + }, + { + "epoch": 0.39, + "learning_rate": 1.3877803351674498e-05, + "loss": 0.4843, + "step": 4598 + }, + { + "epoch": 0.39, + "learning_rate": 1.3875257696862118e-05, + "loss": 0.4949, + "step": 4599 + }, + { + "epoch": 0.39, + "learning_rate": 1.3872711746506413e-05, + "loss": 0.4927, + "step": 4600 + }, + { + "epoch": 0.39, + "learning_rate": 1.3870165500801538e-05, + "loss": 0.4798, + "step": 4601 + }, + { + "epoch": 0.39, + "learning_rate": 1.3867618959941684e-05, + "loss": 0.4744, + "step": 4602 + }, + { + "epoch": 0.39, + "learning_rate": 1.3865072124121066e-05, + "loss": 0.4687, + "step": 4603 + }, + { + "epoch": 0.39, + "learning_rate": 1.3862524993533908e-05, + "loss": 0.5137, + "step": 4604 + }, + { + "epoch": 0.39, + "learning_rate": 1.3859977568374468e-05, + "loss": 0.4756, + "step": 4605 + }, + { + "epoch": 0.39, + "learning_rate": 1.3857429848837022e-05, + "loss": 0.4753, + "step": 4606 + }, + { + "epoch": 0.39, + "learning_rate": 1.3854881835115878e-05, + "loss": 0.4987, + "step": 4607 + }, + { + "epoch": 0.39, + "learning_rate": 1.3852333527405346e-05, + "loss": 0.4734, + "step": 4608 + }, + { + "epoch": 0.39, + "learning_rate": 1.3849784925899779e-05, + "loss": 0.4808, + "step": 4609 + }, + { + "epoch": 0.39, + "learning_rate": 1.3847236030793538e-05, + "loss": 0.4817, + "step": 4610 + }, + { + "epoch": 0.39, + "learning_rate": 1.384468684228102e-05, + "loss": 0.474, + "step": 4611 + }, + { + "epoch": 0.39, + "learning_rate": 1.3842137360556629e-05, + "loss": 0.5033, + "step": 4612 + }, + { + "epoch": 0.39, + "learning_rate": 1.3839587585814801e-05, + "loss": 0.4827, + "step": 4613 + }, + { + "epoch": 0.39, + "learning_rate": 1.3837037518249998e-05, + "loss": 0.4837, + "step": 4614 + }, + { + "epoch": 0.39, + "learning_rate": 1.3834487158056692e-05, + "loss": 0.5046, + "step": 4615 + }, + { + "epoch": 0.39, + "learning_rate": 1.383193650542939e-05, + "loss": 0.4856, + "step": 4616 + }, + { + "epoch": 0.39, + "learning_rate": 1.3829385560562607e-05, + "loss": 0.4951, + "step": 4617 + }, + { + "epoch": 0.39, + "learning_rate": 1.3826834323650899e-05, + "loss": 0.4891, + "step": 4618 + }, + { + "epoch": 0.39, + "learning_rate": 1.3824282794888828e-05, + "loss": 0.4747, + "step": 4619 + }, + { + "epoch": 0.39, + "learning_rate": 1.3821730974470981e-05, + "loss": 0.4878, + "step": 4620 + }, + { + "epoch": 0.39, + "learning_rate": 1.3819178862591982e-05, + "loss": 0.4925, + "step": 4621 + }, + { + "epoch": 0.39, + "learning_rate": 1.3816626459446451e-05, + "loss": 0.4945, + "step": 4622 + }, + { + "epoch": 0.39, + "learning_rate": 1.3814073765229056e-05, + "loss": 0.5084, + "step": 4623 + }, + { + "epoch": 0.39, + "learning_rate": 1.3811520780134471e-05, + "loss": 0.4922, + "step": 4624 + }, + { + "epoch": 0.39, + "learning_rate": 1.3808967504357402e-05, + "loss": 0.4896, + "step": 4625 + }, + { + "epoch": 0.39, + "learning_rate": 1.3806413938092566e-05, + "loss": 0.4777, + "step": 4626 + }, + { + "epoch": 0.39, + "learning_rate": 1.380386008153471e-05, + "loss": 0.4813, + "step": 4627 + }, + { + "epoch": 0.39, + "learning_rate": 1.3801305934878609e-05, + "loss": 0.4933, + "step": 4628 + }, + { + "epoch": 0.39, + "learning_rate": 1.379875149831904e-05, + "loss": 0.46, + "step": 4629 + }, + { + "epoch": 0.39, + "learning_rate": 1.3796196772050829e-05, + "loss": 0.4775, + "step": 4630 + }, + { + "epoch": 0.39, + "learning_rate": 1.3793641756268801e-05, + "loss": 0.4932, + "step": 4631 + }, + { + "epoch": 0.39, + "learning_rate": 1.3791086451167814e-05, + "loss": 0.4951, + "step": 4632 + }, + { + "epoch": 0.4, + "learning_rate": 1.3788530856942747e-05, + "loss": 0.4785, + "step": 4633 + }, + { + "epoch": 0.4, + "learning_rate": 1.3785974973788506e-05, + "loss": 0.4758, + "step": 4634 + }, + { + "epoch": 0.4, + "learning_rate": 1.3783418801900001e-05, + "loss": 0.5045, + "step": 4635 + }, + { + "epoch": 0.4, + "learning_rate": 1.3780862341472183e-05, + "loss": 0.4925, + "step": 4636 + }, + { + "epoch": 0.4, + "learning_rate": 1.3778305592700023e-05, + "loss": 0.4801, + "step": 4637 + }, + { + "epoch": 0.4, + "learning_rate": 1.3775748555778497e-05, + "loss": 0.4856, + "step": 4638 + }, + { + "epoch": 0.4, + "learning_rate": 1.3773191230902629e-05, + "loss": 0.4821, + "step": 4639 + }, + { + "epoch": 0.4, + "learning_rate": 1.3770633618267444e-05, + "loss": 0.4846, + "step": 4640 + }, + { + "epoch": 0.4, + "learning_rate": 1.3768075718067994e-05, + "loss": 0.4872, + "step": 4641 + }, + { + "epoch": 0.4, + "learning_rate": 1.3765517530499364e-05, + "loss": 0.4729, + "step": 4642 + }, + { + "epoch": 0.4, + "learning_rate": 1.3762959055756643e-05, + "loss": 0.4919, + "step": 4643 + }, + { + "epoch": 0.4, + "learning_rate": 1.3760400294034955e-05, + "loss": 0.4789, + "step": 4644 + }, + { + "epoch": 0.4, + "learning_rate": 1.3757841245529442e-05, + "loss": 0.4812, + "step": 4645 + }, + { + "epoch": 0.4, + "learning_rate": 1.3755281910435267e-05, + "loss": 0.4775, + "step": 4646 + }, + { + "epoch": 0.4, + "learning_rate": 1.3752722288947614e-05, + "loss": 0.4804, + "step": 4647 + }, + { + "epoch": 0.4, + "learning_rate": 1.3750162381261693e-05, + "loss": 0.4776, + "step": 4648 + }, + { + "epoch": 0.4, + "learning_rate": 1.3747602187572733e-05, + "loss": 0.4899, + "step": 4649 + }, + { + "epoch": 0.4, + "learning_rate": 1.3745041708075983e-05, + "loss": 0.5036, + "step": 4650 + }, + { + "epoch": 0.4, + "learning_rate": 1.3742480942966721e-05, + "loss": 0.4822, + "step": 4651 + }, + { + "epoch": 0.4, + "learning_rate": 1.3739919892440234e-05, + "loss": 0.4994, + "step": 4652 + }, + { + "epoch": 0.4, + "learning_rate": 1.3737358556691844e-05, + "loss": 0.4821, + "step": 4653 + }, + { + "epoch": 0.4, + "learning_rate": 1.3734796935916888e-05, + "loss": 0.4936, + "step": 4654 + }, + { + "epoch": 0.4, + "learning_rate": 1.3732235030310723e-05, + "loss": 0.4762, + "step": 4655 + }, + { + "epoch": 0.4, + "learning_rate": 1.3729672840068732e-05, + "loss": 0.4906, + "step": 4656 + }, + { + "epoch": 0.4, + "learning_rate": 1.3727110365386325e-05, + "loss": 0.4862, + "step": 4657 + }, + { + "epoch": 0.4, + "learning_rate": 1.3724547606458918e-05, + "loss": 0.4998, + "step": 4658 + }, + { + "epoch": 0.4, + "learning_rate": 1.3721984563481961e-05, + "loss": 0.5129, + "step": 4659 + }, + { + "epoch": 0.4, + "learning_rate": 1.3719421236650923e-05, + "loss": 0.4934, + "step": 4660 + }, + { + "epoch": 0.4, + "learning_rate": 1.3716857626161293e-05, + "loss": 0.4804, + "step": 4661 + }, + { + "epoch": 0.4, + "learning_rate": 1.3714293732208583e-05, + "loss": 0.4829, + "step": 4662 + }, + { + "epoch": 0.4, + "learning_rate": 1.3711729554988324e-05, + "loss": 0.4839, + "step": 4663 + }, + { + "epoch": 0.4, + "learning_rate": 1.3709165094696074e-05, + "loss": 0.4825, + "step": 4664 + }, + { + "epoch": 0.4, + "learning_rate": 1.3706600351527413e-05, + "loss": 0.4808, + "step": 4665 + }, + { + "epoch": 0.4, + "learning_rate": 1.3704035325677931e-05, + "loss": 0.4916, + "step": 4666 + }, + { + "epoch": 0.4, + "learning_rate": 1.370147001734325e-05, + "loss": 0.4924, + "step": 4667 + }, + { + "epoch": 0.4, + "learning_rate": 1.3698904426719015e-05, + "loss": 0.4743, + "step": 4668 + }, + { + "epoch": 0.4, + "learning_rate": 1.3696338554000885e-05, + "loss": 0.4799, + "step": 4669 + }, + { + "epoch": 0.4, + "learning_rate": 1.3693772399384547e-05, + "loss": 0.4681, + "step": 4670 + }, + { + "epoch": 0.4, + "learning_rate": 1.3691205963065701e-05, + "loss": 0.4699, + "step": 4671 + }, + { + "epoch": 0.4, + "learning_rate": 1.3688639245240078e-05, + "loss": 0.4747, + "step": 4672 + }, + { + "epoch": 0.4, + "learning_rate": 1.368607224610343e-05, + "loss": 0.5214, + "step": 4673 + }, + { + "epoch": 0.4, + "learning_rate": 1.3683504965851522e-05, + "loss": 0.4757, + "step": 4674 + }, + { + "epoch": 0.4, + "learning_rate": 1.3680937404680147e-05, + "loss": 0.4878, + "step": 4675 + }, + { + "epoch": 0.4, + "learning_rate": 1.3678369562785119e-05, + "loss": 0.4967, + "step": 4676 + }, + { + "epoch": 0.4, + "learning_rate": 1.3675801440362268e-05, + "loss": 0.4559, + "step": 4677 + }, + { + "epoch": 0.4, + "learning_rate": 1.3673233037607458e-05, + "loss": 0.4987, + "step": 4678 + }, + { + "epoch": 0.4, + "learning_rate": 1.3670664354716555e-05, + "loss": 0.4713, + "step": 4679 + }, + { + "epoch": 0.4, + "learning_rate": 1.3668095391885472e-05, + "loss": 0.5082, + "step": 4680 + }, + { + "epoch": 0.4, + "learning_rate": 1.3665526149310115e-05, + "loss": 0.4795, + "step": 4681 + }, + { + "epoch": 0.4, + "learning_rate": 1.3662956627186433e-05, + "loss": 0.4983, + "step": 4682 + }, + { + "epoch": 0.4, + "learning_rate": 1.3660386825710386e-05, + "loss": 0.4861, + "step": 4683 + }, + { + "epoch": 0.4, + "learning_rate": 1.3657816745077957e-05, + "loss": 0.4826, + "step": 4684 + }, + { + "epoch": 0.4, + "learning_rate": 1.365524638548515e-05, + "loss": 0.5044, + "step": 4685 + }, + { + "epoch": 0.4, + "learning_rate": 1.3652675747127995e-05, + "loss": 0.4642, + "step": 4686 + }, + { + "epoch": 0.4, + "learning_rate": 1.3650104830202542e-05, + "loss": 0.4712, + "step": 4687 + }, + { + "epoch": 0.4, + "learning_rate": 1.364753363490485e-05, + "loss": 0.4839, + "step": 4688 + }, + { + "epoch": 0.4, + "learning_rate": 1.3644962161431019e-05, + "loss": 0.4715, + "step": 4689 + }, + { + "epoch": 0.4, + "learning_rate": 1.3642390409977156e-05, + "loss": 0.4653, + "step": 4690 + }, + { + "epoch": 0.4, + "learning_rate": 1.363981838073939e-05, + "loss": 0.5033, + "step": 4691 + }, + { + "epoch": 0.4, + "learning_rate": 1.3637246073913884e-05, + "loss": 0.47, + "step": 4692 + }, + { + "epoch": 0.4, + "learning_rate": 1.3634673489696804e-05, + "loss": 0.4855, + "step": 4693 + }, + { + "epoch": 0.4, + "learning_rate": 1.363210062828435e-05, + "loss": 0.4846, + "step": 4694 + }, + { + "epoch": 0.4, + "learning_rate": 1.3629527489872738e-05, + "loss": 0.4924, + "step": 4695 + }, + { + "epoch": 0.4, + "learning_rate": 1.362695407465821e-05, + "loss": 0.4836, + "step": 4696 + }, + { + "epoch": 0.4, + "learning_rate": 1.3624380382837017e-05, + "loss": 0.4953, + "step": 4697 + }, + { + "epoch": 0.4, + "learning_rate": 1.3621806414605447e-05, + "loss": 0.4961, + "step": 4698 + }, + { + "epoch": 0.4, + "learning_rate": 1.3619232170159803e-05, + "loss": 0.496, + "step": 4699 + }, + { + "epoch": 0.4, + "learning_rate": 1.3616657649696397e-05, + "loss": 0.4832, + "step": 4700 + }, + { + "epoch": 0.4, + "learning_rate": 1.3614082853411583e-05, + "loss": 0.4704, + "step": 4701 + }, + { + "epoch": 0.4, + "learning_rate": 1.3611507781501722e-05, + "loss": 0.5002, + "step": 4702 + }, + { + "epoch": 0.4, + "learning_rate": 1.36089324341632e-05, + "loss": 0.485, + "step": 4703 + }, + { + "epoch": 0.4, + "learning_rate": 1.3606356811592427e-05, + "loss": 0.5011, + "step": 4704 + }, + { + "epoch": 0.4, + "learning_rate": 1.3603780913985825e-05, + "loss": 0.4817, + "step": 4705 + }, + { + "epoch": 0.4, + "learning_rate": 1.3601204741539843e-05, + "loss": 0.487, + "step": 4706 + }, + { + "epoch": 0.4, + "learning_rate": 1.3598628294450954e-05, + "loss": 0.4934, + "step": 4707 + }, + { + "epoch": 0.4, + "learning_rate": 1.359605157291565e-05, + "loss": 0.5068, + "step": 4708 + }, + { + "epoch": 0.4, + "learning_rate": 1.3593474577130434e-05, + "loss": 0.4801, + "step": 4709 + }, + { + "epoch": 0.4, + "learning_rate": 1.359089730729185e-05, + "loss": 0.485, + "step": 4710 + }, + { + "epoch": 0.4, + "learning_rate": 1.3588319763596443e-05, + "loss": 0.4812, + "step": 4711 + }, + { + "epoch": 0.4, + "learning_rate": 1.3585741946240792e-05, + "loss": 0.5057, + "step": 4712 + }, + { + "epoch": 0.4, + "learning_rate": 1.358316385542149e-05, + "loss": 0.4811, + "step": 4713 + }, + { + "epoch": 0.4, + "learning_rate": 1.3580585491335151e-05, + "loss": 0.5072, + "step": 4714 + }, + { + "epoch": 0.4, + "learning_rate": 1.3578006854178416e-05, + "loss": 0.4764, + "step": 4715 + }, + { + "epoch": 0.4, + "learning_rate": 1.3575427944147939e-05, + "loss": 0.4638, + "step": 4716 + }, + { + "epoch": 0.4, + "learning_rate": 1.3572848761440403e-05, + "loss": 0.5027, + "step": 4717 + }, + { + "epoch": 0.4, + "learning_rate": 1.3570269306252499e-05, + "loss": 0.4849, + "step": 4718 + }, + { + "epoch": 0.4, + "learning_rate": 1.3567689578780957e-05, + "loss": 0.4879, + "step": 4719 + }, + { + "epoch": 0.4, + "learning_rate": 1.3565109579222511e-05, + "loss": 0.4813, + "step": 4720 + }, + { + "epoch": 0.4, + "learning_rate": 1.3562529307773926e-05, + "loss": 0.4957, + "step": 4721 + }, + { + "epoch": 0.4, + "learning_rate": 1.3559948764631983e-05, + "loss": 0.5002, + "step": 4722 + }, + { + "epoch": 0.4, + "learning_rate": 1.3557367949993483e-05, + "loss": 0.5072, + "step": 4723 + }, + { + "epoch": 0.4, + "learning_rate": 1.3554786864055251e-05, + "loss": 0.501, + "step": 4724 + }, + { + "epoch": 0.4, + "learning_rate": 1.3552205507014133e-05, + "loss": 0.4712, + "step": 4725 + }, + { + "epoch": 0.4, + "learning_rate": 1.3549623879066996e-05, + "loss": 0.4742, + "step": 4726 + }, + { + "epoch": 0.4, + "learning_rate": 1.3547041980410717e-05, + "loss": 0.4639, + "step": 4727 + }, + { + "epoch": 0.4, + "learning_rate": 1.3544459811242212e-05, + "loss": 0.4974, + "step": 4728 + }, + { + "epoch": 0.4, + "learning_rate": 1.3541877371758405e-05, + "loss": 0.4975, + "step": 4729 + }, + { + "epoch": 0.4, + "learning_rate": 1.3539294662156239e-05, + "loss": 0.4945, + "step": 4730 + }, + { + "epoch": 0.4, + "learning_rate": 1.353671168263269e-05, + "loss": 0.4956, + "step": 4731 + }, + { + "epoch": 0.4, + "learning_rate": 1.3534128433384741e-05, + "loss": 0.4797, + "step": 4732 + }, + { + "epoch": 0.4, + "learning_rate": 1.3531544914609403e-05, + "loss": 0.4743, + "step": 4733 + }, + { + "epoch": 0.4, + "learning_rate": 1.3528961126503704e-05, + "loss": 0.4866, + "step": 4734 + }, + { + "epoch": 0.4, + "learning_rate": 1.35263770692647e-05, + "loss": 0.5015, + "step": 4735 + }, + { + "epoch": 0.4, + "learning_rate": 1.3523792743089457e-05, + "loss": 0.4637, + "step": 4736 + }, + { + "epoch": 0.4, + "learning_rate": 1.3521208148175067e-05, + "loss": 0.4894, + "step": 4737 + }, + { + "epoch": 0.4, + "learning_rate": 1.3518623284718644e-05, + "loss": 0.4783, + "step": 4738 + }, + { + "epoch": 0.4, + "learning_rate": 1.3516038152917319e-05, + "loss": 0.4791, + "step": 4739 + }, + { + "epoch": 0.4, + "learning_rate": 1.3513452752968248e-05, + "loss": 0.501, + "step": 4740 + }, + { + "epoch": 0.4, + "learning_rate": 1.3510867085068599e-05, + "loss": 0.4936, + "step": 4741 + }, + { + "epoch": 0.4, + "learning_rate": 1.350828114941557e-05, + "loss": 0.4751, + "step": 4742 + }, + { + "epoch": 0.4, + "learning_rate": 1.3505694946206374e-05, + "loss": 0.4832, + "step": 4743 + }, + { + "epoch": 0.4, + "learning_rate": 1.3503108475638244e-05, + "loss": 0.4969, + "step": 4744 + }, + { + "epoch": 0.4, + "learning_rate": 1.3500521737908439e-05, + "loss": 0.4877, + "step": 4745 + }, + { + "epoch": 0.4, + "learning_rate": 1.3497934733214231e-05, + "loss": 0.48, + "step": 4746 + }, + { + "epoch": 0.4, + "learning_rate": 1.3495347461752914e-05, + "loss": 0.4983, + "step": 4747 + }, + { + "epoch": 0.4, + "learning_rate": 1.349275992372181e-05, + "loss": 0.4647, + "step": 4748 + }, + { + "epoch": 0.4, + "learning_rate": 1.3490172119318252e-05, + "loss": 0.4772, + "step": 4749 + }, + { + "epoch": 0.41, + "learning_rate": 1.3487584048739598e-05, + "loss": 0.4758, + "step": 4750 + }, + { + "epoch": 0.41, + "learning_rate": 1.3484995712183222e-05, + "loss": 0.4814, + "step": 4751 + }, + { + "epoch": 0.41, + "learning_rate": 1.3482407109846527e-05, + "loss": 0.4819, + "step": 4752 + }, + { + "epoch": 0.41, + "learning_rate": 1.3479818241926921e-05, + "loss": 0.4744, + "step": 4753 + }, + { + "epoch": 0.41, + "learning_rate": 1.3477229108621855e-05, + "loss": 0.481, + "step": 4754 + }, + { + "epoch": 0.41, + "learning_rate": 1.3474639710128777e-05, + "loss": 0.4604, + "step": 4755 + }, + { + "epoch": 0.41, + "learning_rate": 1.3472050046645167e-05, + "loss": 0.4951, + "step": 4756 + }, + { + "epoch": 0.41, + "learning_rate": 1.3469460118368527e-05, + "loss": 0.4792, + "step": 4757 + }, + { + "epoch": 0.41, + "learning_rate": 1.3466869925496374e-05, + "loss": 0.5027, + "step": 4758 + }, + { + "epoch": 0.41, + "learning_rate": 1.3464279468226247e-05, + "loss": 0.4719, + "step": 4759 + }, + { + "epoch": 0.41, + "learning_rate": 1.3461688746755704e-05, + "loss": 0.4932, + "step": 4760 + }, + { + "epoch": 0.41, + "learning_rate": 1.3459097761282325e-05, + "loss": 0.4762, + "step": 4761 + }, + { + "epoch": 0.41, + "learning_rate": 1.3456506512003707e-05, + "loss": 0.4754, + "step": 4762 + }, + { + "epoch": 0.41, + "learning_rate": 1.3453914999117477e-05, + "loss": 0.4916, + "step": 4763 + }, + { + "epoch": 0.41, + "learning_rate": 1.3451323222821267e-05, + "loss": 0.4873, + "step": 4764 + }, + { + "epoch": 0.41, + "learning_rate": 1.3448731183312738e-05, + "loss": 0.4843, + "step": 4765 + }, + { + "epoch": 0.41, + "learning_rate": 1.3446138880789572e-05, + "loss": 0.4732, + "step": 4766 + }, + { + "epoch": 0.41, + "learning_rate": 1.344354631544947e-05, + "loss": 0.5267, + "step": 4767 + }, + { + "epoch": 0.41, + "learning_rate": 1.3440953487490145e-05, + "loss": 0.4614, + "step": 4768 + }, + { + "epoch": 0.41, + "learning_rate": 1.3438360397109345e-05, + "loss": 0.4992, + "step": 4769 + }, + { + "epoch": 0.41, + "learning_rate": 1.3435767044504826e-05, + "loss": 0.5083, + "step": 4770 + }, + { + "epoch": 0.41, + "learning_rate": 1.3433173429874367e-05, + "loss": 0.4868, + "step": 4771 + }, + { + "epoch": 0.41, + "learning_rate": 1.343057955341577e-05, + "loss": 0.4884, + "step": 4772 + }, + { + "epoch": 0.41, + "learning_rate": 1.3427985415326854e-05, + "loss": 0.4867, + "step": 4773 + }, + { + "epoch": 0.41, + "learning_rate": 1.3425391015805458e-05, + "loss": 0.4877, + "step": 4774 + }, + { + "epoch": 0.41, + "learning_rate": 1.3422796355049444e-05, + "loss": 0.4865, + "step": 4775 + }, + { + "epoch": 0.41, + "learning_rate": 1.342020143325669e-05, + "loss": 0.4749, + "step": 4776 + }, + { + "epoch": 0.41, + "learning_rate": 1.3417606250625096e-05, + "loss": 0.4847, + "step": 4777 + }, + { + "epoch": 0.41, + "learning_rate": 1.3415010807352578e-05, + "loss": 0.4661, + "step": 4778 + }, + { + "epoch": 0.41, + "learning_rate": 1.3412415103637081e-05, + "loss": 0.4953, + "step": 4779 + }, + { + "epoch": 0.41, + "learning_rate": 1.3409819139676562e-05, + "loss": 0.4864, + "step": 4780 + }, + { + "epoch": 0.41, + "learning_rate": 1.3407222915669e-05, + "loss": 0.4721, + "step": 4781 + }, + { + "epoch": 0.41, + "learning_rate": 1.3404626431812394e-05, + "loss": 0.4793, + "step": 4782 + }, + { + "epoch": 0.41, + "learning_rate": 1.340202968830476e-05, + "loss": 0.5013, + "step": 4783 + }, + { + "epoch": 0.41, + "learning_rate": 1.3399432685344143e-05, + "loss": 0.4808, + "step": 4784 + }, + { + "epoch": 0.41, + "learning_rate": 1.3396835423128596e-05, + "loss": 0.4715, + "step": 4785 + }, + { + "epoch": 0.41, + "learning_rate": 1.3394237901856195e-05, + "loss": 0.5003, + "step": 4786 + }, + { + "epoch": 0.41, + "learning_rate": 1.3391640121725043e-05, + "loss": 0.4803, + "step": 4787 + }, + { + "epoch": 0.41, + "learning_rate": 1.3389042082933257e-05, + "loss": 0.479, + "step": 4788 + }, + { + "epoch": 0.41, + "learning_rate": 1.3386443785678972e-05, + "loss": 0.4696, + "step": 4789 + }, + { + "epoch": 0.41, + "learning_rate": 1.3383845230160346e-05, + "loss": 0.4692, + "step": 4790 + }, + { + "epoch": 0.41, + "learning_rate": 1.3381246416575558e-05, + "loss": 0.4735, + "step": 4791 + }, + { + "epoch": 0.41, + "learning_rate": 1.3378647345122795e-05, + "loss": 0.4842, + "step": 4792 + }, + { + "epoch": 0.41, + "learning_rate": 1.3376048016000286e-05, + "loss": 0.4915, + "step": 4793 + }, + { + "epoch": 0.41, + "learning_rate": 1.3373448429406259e-05, + "loss": 0.4672, + "step": 4794 + }, + { + "epoch": 0.41, + "learning_rate": 1.337084858553897e-05, + "loss": 0.4895, + "step": 4795 + }, + { + "epoch": 0.41, + "learning_rate": 1.3368248484596697e-05, + "loss": 0.4942, + "step": 4796 + }, + { + "epoch": 0.41, + "learning_rate": 1.3365648126777733e-05, + "loss": 0.4899, + "step": 4797 + }, + { + "epoch": 0.41, + "learning_rate": 1.3363047512280391e-05, + "loss": 0.4797, + "step": 4798 + }, + { + "epoch": 0.41, + "learning_rate": 1.3360446641303004e-05, + "loss": 0.4788, + "step": 4799 + }, + { + "epoch": 0.41, + "learning_rate": 1.3357845514043927e-05, + "loss": 0.5046, + "step": 4800 + }, + { + "epoch": 0.41, + "learning_rate": 1.3355244130701532e-05, + "loss": 0.4787, + "step": 4801 + }, + { + "epoch": 0.41, + "learning_rate": 1.3352642491474215e-05, + "loss": 0.4841, + "step": 4802 + }, + { + "epoch": 0.41, + "learning_rate": 1.3350040596560382e-05, + "loss": 0.4767, + "step": 4803 + }, + { + "epoch": 0.41, + "learning_rate": 1.3347438446158467e-05, + "loss": 0.4893, + "step": 4804 + }, + { + "epoch": 0.41, + "learning_rate": 1.3344836040466923e-05, + "loss": 0.4539, + "step": 4805 + }, + { + "epoch": 0.41, + "learning_rate": 1.3342233379684217e-05, + "loss": 0.4858, + "step": 4806 + }, + { + "epoch": 0.41, + "learning_rate": 1.3339630464008838e-05, + "loss": 0.4907, + "step": 4807 + }, + { + "epoch": 0.41, + "learning_rate": 1.3337027293639303e-05, + "loss": 0.4691, + "step": 4808 + }, + { + "epoch": 0.41, + "learning_rate": 1.3334423868774128e-05, + "loss": 0.4868, + "step": 4809 + }, + { + "epoch": 0.41, + "learning_rate": 1.3331820189611872e-05, + "loss": 0.471, + "step": 4810 + }, + { + "epoch": 0.41, + "learning_rate": 1.33292162563511e-05, + "loss": 0.4988, + "step": 4811 + }, + { + "epoch": 0.41, + "learning_rate": 1.3326612069190394e-05, + "loss": 0.4863, + "step": 4812 + }, + { + "epoch": 0.41, + "learning_rate": 1.3324007628328363e-05, + "loss": 0.4908, + "step": 4813 + }, + { + "epoch": 0.41, + "learning_rate": 1.3321402933963637e-05, + "loss": 0.4609, + "step": 4814 + }, + { + "epoch": 0.41, + "learning_rate": 1.3318797986294854e-05, + "loss": 0.4997, + "step": 4815 + }, + { + "epoch": 0.41, + "learning_rate": 1.331619278552068e-05, + "loss": 0.4648, + "step": 4816 + }, + { + "epoch": 0.41, + "learning_rate": 1.33135873318398e-05, + "loss": 0.4772, + "step": 4817 + }, + { + "epoch": 0.41, + "learning_rate": 1.3310981625450915e-05, + "loss": 0.4835, + "step": 4818 + }, + { + "epoch": 0.41, + "learning_rate": 1.3308375666552752e-05, + "loss": 0.4796, + "step": 4819 + }, + { + "epoch": 0.41, + "learning_rate": 1.3305769455344049e-05, + "loss": 0.4776, + "step": 4820 + }, + { + "epoch": 0.41, + "learning_rate": 1.3303162992023562e-05, + "loss": 0.4811, + "step": 4821 + }, + { + "epoch": 0.41, + "learning_rate": 1.3300556276790078e-05, + "loss": 0.4979, + "step": 4822 + }, + { + "epoch": 0.41, + "learning_rate": 1.3297949309842393e-05, + "loss": 0.4752, + "step": 4823 + }, + { + "epoch": 0.41, + "learning_rate": 1.3295342091379322e-05, + "loss": 0.5128, + "step": 4824 + }, + { + "epoch": 0.41, + "learning_rate": 1.3292734621599708e-05, + "loss": 0.4985, + "step": 4825 + }, + { + "epoch": 0.41, + "learning_rate": 1.3290126900702403e-05, + "loss": 0.481, + "step": 4826 + }, + { + "epoch": 0.41, + "learning_rate": 1.3287518928886285e-05, + "loss": 0.4811, + "step": 4827 + }, + { + "epoch": 0.41, + "learning_rate": 1.3284910706350249e-05, + "loss": 0.4663, + "step": 4828 + }, + { + "epoch": 0.41, + "learning_rate": 1.3282302233293211e-05, + "loss": 0.4984, + "step": 4829 + }, + { + "epoch": 0.41, + "learning_rate": 1.32796935099141e-05, + "loss": 0.4642, + "step": 4830 + }, + { + "epoch": 0.41, + "learning_rate": 1.3277084536411869e-05, + "loss": 0.4886, + "step": 4831 + }, + { + "epoch": 0.41, + "learning_rate": 1.327447531298549e-05, + "loss": 0.491, + "step": 4832 + }, + { + "epoch": 0.41, + "learning_rate": 1.327186583983395e-05, + "loss": 0.4665, + "step": 4833 + }, + { + "epoch": 0.41, + "learning_rate": 1.326925611715627e-05, + "loss": 0.4761, + "step": 4834 + }, + { + "epoch": 0.41, + "learning_rate": 1.326664614515146e-05, + "loss": 0.4953, + "step": 4835 + }, + { + "epoch": 0.41, + "learning_rate": 1.3264035924018584e-05, + "loss": 0.4741, + "step": 4836 + }, + { + "epoch": 0.41, + "learning_rate": 1.3261425453956698e-05, + "loss": 0.4762, + "step": 4837 + }, + { + "epoch": 0.41, + "learning_rate": 1.3258814735164892e-05, + "loss": 0.481, + "step": 4838 + }, + { + "epoch": 0.41, + "learning_rate": 1.3256203767842268e-05, + "loss": 0.4811, + "step": 4839 + }, + { + "epoch": 0.41, + "learning_rate": 1.325359255218795e-05, + "loss": 0.4767, + "step": 4840 + }, + { + "epoch": 0.41, + "learning_rate": 1.3250981088401085e-05, + "loss": 0.493, + "step": 4841 + }, + { + "epoch": 0.41, + "learning_rate": 1.3248369376680824e-05, + "loss": 0.4946, + "step": 4842 + }, + { + "epoch": 0.41, + "learning_rate": 1.3245757417226356e-05, + "loss": 0.4695, + "step": 4843 + }, + { + "epoch": 0.41, + "learning_rate": 1.3243145210236876e-05, + "loss": 0.4697, + "step": 4844 + }, + { + "epoch": 0.41, + "learning_rate": 1.3240532755911603e-05, + "loss": 0.4853, + "step": 4845 + }, + { + "epoch": 0.41, + "learning_rate": 1.3237920054449775e-05, + "loss": 0.4571, + "step": 4846 + }, + { + "epoch": 0.41, + "learning_rate": 1.3235307106050644e-05, + "loss": 0.479, + "step": 4847 + }, + { + "epoch": 0.41, + "learning_rate": 1.3232693910913486e-05, + "loss": 0.487, + "step": 4848 + }, + { + "epoch": 0.41, + "learning_rate": 1.3230080469237592e-05, + "loss": 0.4722, + "step": 4849 + }, + { + "epoch": 0.41, + "learning_rate": 1.322746678122228e-05, + "loss": 0.5033, + "step": 4850 + }, + { + "epoch": 0.41, + "learning_rate": 1.322485284706687e-05, + "loss": 0.4904, + "step": 4851 + }, + { + "epoch": 0.41, + "learning_rate": 1.3222238666970728e-05, + "loss": 0.4878, + "step": 4852 + }, + { + "epoch": 0.41, + "learning_rate": 1.3219624241133211e-05, + "loss": 0.4579, + "step": 4853 + }, + { + "epoch": 0.41, + "learning_rate": 1.3217009569753702e-05, + "loss": 0.4701, + "step": 4854 + }, + { + "epoch": 0.41, + "learning_rate": 1.3214394653031616e-05, + "loss": 0.4777, + "step": 4855 + }, + { + "epoch": 0.41, + "learning_rate": 1.3211779491166375e-05, + "loss": 0.4997, + "step": 4856 + }, + { + "epoch": 0.41, + "learning_rate": 1.3209164084357423e-05, + "loss": 0.4786, + "step": 4857 + }, + { + "epoch": 0.41, + "learning_rate": 1.3206548432804213e-05, + "loss": 0.4865, + "step": 4858 + }, + { + "epoch": 0.41, + "learning_rate": 1.320393253670624e-05, + "loss": 0.4752, + "step": 4859 + }, + { + "epoch": 0.41, + "learning_rate": 1.3201316396262991e-05, + "loss": 0.4765, + "step": 4860 + }, + { + "epoch": 0.41, + "learning_rate": 1.319870001167399e-05, + "loss": 0.4651, + "step": 4861 + }, + { + "epoch": 0.41, + "learning_rate": 1.3196083383138776e-05, + "loss": 0.4694, + "step": 4862 + }, + { + "epoch": 0.41, + "learning_rate": 1.3193466510856894e-05, + "loss": 0.4818, + "step": 4863 + }, + { + "epoch": 0.41, + "learning_rate": 1.3190849395027926e-05, + "loss": 0.4908, + "step": 4864 + }, + { + "epoch": 0.41, + "learning_rate": 1.3188232035851463e-05, + "loss": 0.4895, + "step": 4865 + }, + { + "epoch": 0.41, + "learning_rate": 1.318561443352711e-05, + "loss": 0.4991, + "step": 4866 + }, + { + "epoch": 0.41, + "learning_rate": 1.3182996588254503e-05, + "loss": 0.4607, + "step": 4867 + }, + { + "epoch": 0.42, + "learning_rate": 1.3180378500233291e-05, + "loss": 0.4809, + "step": 4868 + }, + { + "epoch": 0.42, + "learning_rate": 1.3177760169663134e-05, + "loss": 0.4611, + "step": 4869 + }, + { + "epoch": 0.42, + "learning_rate": 1.317514159674372e-05, + "loss": 0.4697, + "step": 4870 + }, + { + "epoch": 0.42, + "learning_rate": 1.3172522781674753e-05, + "loss": 0.4867, + "step": 4871 + }, + { + "epoch": 0.42, + "learning_rate": 1.316990372465595e-05, + "loss": 0.4681, + "step": 4872 + }, + { + "epoch": 0.42, + "learning_rate": 1.316728442588706e-05, + "loss": 0.4846, + "step": 4873 + }, + { + "epoch": 0.42, + "learning_rate": 1.3164664885567833e-05, + "loss": 0.4927, + "step": 4874 + }, + { + "epoch": 0.42, + "learning_rate": 1.316204510389805e-05, + "loss": 0.4684, + "step": 4875 + }, + { + "epoch": 0.42, + "learning_rate": 1.315942508107751e-05, + "loss": 0.4723, + "step": 4876 + }, + { + "epoch": 0.42, + "learning_rate": 1.315680481730602e-05, + "loss": 0.4635, + "step": 4877 + }, + { + "epoch": 0.42, + "learning_rate": 1.3154184312783416e-05, + "loss": 0.4926, + "step": 4878 + }, + { + "epoch": 0.42, + "learning_rate": 1.3151563567709547e-05, + "loss": 0.4972, + "step": 4879 + }, + { + "epoch": 0.42, + "learning_rate": 1.3148942582284286e-05, + "loss": 0.4849, + "step": 4880 + }, + { + "epoch": 0.42, + "learning_rate": 1.3146321356707513e-05, + "loss": 0.4864, + "step": 4881 + }, + { + "epoch": 0.42, + "learning_rate": 1.314369989117914e-05, + "loss": 0.4864, + "step": 4882 + }, + { + "epoch": 0.42, + "learning_rate": 1.3141078185899088e-05, + "loss": 0.4954, + "step": 4883 + }, + { + "epoch": 0.42, + "learning_rate": 1.31384562410673e-05, + "loss": 0.4973, + "step": 4884 + }, + { + "epoch": 0.42, + "learning_rate": 1.3135834056883738e-05, + "loss": 0.4817, + "step": 4885 + }, + { + "epoch": 0.42, + "learning_rate": 1.313321163354838e-05, + "loss": 0.4864, + "step": 4886 + }, + { + "epoch": 0.42, + "learning_rate": 1.3130588971261218e-05, + "loss": 0.4729, + "step": 4887 + }, + { + "epoch": 0.42, + "learning_rate": 1.3127966070222273e-05, + "loss": 0.4721, + "step": 4888 + }, + { + "epoch": 0.42, + "learning_rate": 1.3125342930631577e-05, + "loss": 0.4717, + "step": 4889 + }, + { + "epoch": 0.42, + "learning_rate": 1.312271955268918e-05, + "loss": 0.4792, + "step": 4890 + }, + { + "epoch": 0.42, + "learning_rate": 1.3120095936595156e-05, + "loss": 0.4973, + "step": 4891 + }, + { + "epoch": 0.42, + "learning_rate": 1.3117472082549588e-05, + "loss": 0.4762, + "step": 4892 + }, + { + "epoch": 0.42, + "learning_rate": 1.3114847990752582e-05, + "loss": 0.4758, + "step": 4893 + }, + { + "epoch": 0.42, + "learning_rate": 1.3112223661404268e-05, + "loss": 0.4851, + "step": 4894 + }, + { + "epoch": 0.42, + "learning_rate": 1.3109599094704782e-05, + "loss": 0.4716, + "step": 4895 + }, + { + "epoch": 0.42, + "learning_rate": 1.3106974290854286e-05, + "loss": 0.4776, + "step": 4896 + }, + { + "epoch": 0.42, + "learning_rate": 1.310434925005296e-05, + "loss": 0.4895, + "step": 4897 + }, + { + "epoch": 0.42, + "learning_rate": 1.3101723972501002e-05, + "loss": 0.4703, + "step": 4898 + }, + { + "epoch": 0.42, + "learning_rate": 1.3099098458398623e-05, + "loss": 0.4688, + "step": 4899 + }, + { + "epoch": 0.42, + "learning_rate": 1.3096472707946057e-05, + "loss": 0.4883, + "step": 4900 + }, + { + "epoch": 0.42, + "learning_rate": 1.3093846721343555e-05, + "loss": 0.4801, + "step": 4901 + }, + { + "epoch": 0.42, + "learning_rate": 1.3091220498791386e-05, + "loss": 0.4714, + "step": 4902 + }, + { + "epoch": 0.42, + "learning_rate": 1.3088594040489837e-05, + "loss": 0.4879, + "step": 4903 + }, + { + "epoch": 0.42, + "learning_rate": 1.3085967346639212e-05, + "loss": 0.4714, + "step": 4904 + }, + { + "epoch": 0.42, + "learning_rate": 1.3083340417439832e-05, + "loss": 0.4709, + "step": 4905 + }, + { + "epoch": 0.42, + "learning_rate": 1.3080713253092039e-05, + "loss": 0.4761, + "step": 4906 + }, + { + "epoch": 0.42, + "learning_rate": 1.3078085853796192e-05, + "loss": 0.5103, + "step": 4907 + }, + { + "epoch": 0.42, + "learning_rate": 1.307545821975267e-05, + "loss": 0.4692, + "step": 4908 + }, + { + "epoch": 0.42, + "learning_rate": 1.3072830351161862e-05, + "loss": 0.4891, + "step": 4909 + }, + { + "epoch": 0.42, + "learning_rate": 1.3070202248224182e-05, + "loss": 0.504, + "step": 4910 + }, + { + "epoch": 0.42, + "learning_rate": 1.3067573911140061e-05, + "loss": 0.4726, + "step": 4911 + }, + { + "epoch": 0.42, + "learning_rate": 1.306494534010995e-05, + "loss": 0.5209, + "step": 4912 + }, + { + "epoch": 0.42, + "learning_rate": 1.306231653533431e-05, + "loss": 0.5102, + "step": 4913 + }, + { + "epoch": 0.42, + "learning_rate": 1.3059687497013625e-05, + "loss": 0.4857, + "step": 4914 + }, + { + "epoch": 0.42, + "learning_rate": 1.30570582253484e-05, + "loss": 0.4876, + "step": 4915 + }, + { + "epoch": 0.42, + "learning_rate": 1.3054428720539147e-05, + "loss": 0.4991, + "step": 4916 + }, + { + "epoch": 0.42, + "learning_rate": 1.3051798982786412e-05, + "loss": 0.4876, + "step": 4917 + }, + { + "epoch": 0.42, + "learning_rate": 1.3049169012290745e-05, + "loss": 0.4756, + "step": 4918 + }, + { + "epoch": 0.42, + "learning_rate": 1.3046538809252718e-05, + "loss": 0.4729, + "step": 4919 + }, + { + "epoch": 0.42, + "learning_rate": 1.3043908373872922e-05, + "loss": 0.484, + "step": 4920 + }, + { + "epoch": 0.42, + "learning_rate": 1.304127770635197e-05, + "loss": 0.4874, + "step": 4921 + }, + { + "epoch": 0.42, + "learning_rate": 1.3038646806890479e-05, + "loss": 0.4755, + "step": 4922 + }, + { + "epoch": 0.42, + "learning_rate": 1.3036015675689098e-05, + "loss": 0.5001, + "step": 4923 + }, + { + "epoch": 0.42, + "learning_rate": 1.3033384312948487e-05, + "loss": 0.472, + "step": 4924 + }, + { + "epoch": 0.42, + "learning_rate": 1.3030752718869321e-05, + "loss": 0.4872, + "step": 4925 + }, + { + "epoch": 0.42, + "learning_rate": 1.3028120893652305e-05, + "loss": 0.5004, + "step": 4926 + }, + { + "epoch": 0.42, + "learning_rate": 1.3025488837498144e-05, + "loss": 0.458, + "step": 4927 + }, + { + "epoch": 0.42, + "learning_rate": 1.3022856550607572e-05, + "loss": 0.47, + "step": 4928 + }, + { + "epoch": 0.42, + "learning_rate": 1.3020224033181342e-05, + "loss": 0.4942, + "step": 4929 + }, + { + "epoch": 0.42, + "learning_rate": 1.3017591285420219e-05, + "loss": 0.4969, + "step": 4930 + }, + { + "epoch": 0.42, + "learning_rate": 1.3014958307524985e-05, + "loss": 0.4778, + "step": 4931 + }, + { + "epoch": 0.42, + "learning_rate": 1.3012325099696443e-05, + "loss": 0.4782, + "step": 4932 + }, + { + "epoch": 0.42, + "learning_rate": 1.3009691662135415e-05, + "loss": 0.4787, + "step": 4933 + }, + { + "epoch": 0.42, + "learning_rate": 1.300705799504273e-05, + "loss": 0.476, + "step": 4934 + }, + { + "epoch": 0.42, + "learning_rate": 1.3004424098619254e-05, + "loss": 0.4792, + "step": 4935 + }, + { + "epoch": 0.42, + "learning_rate": 1.3001789973065852e-05, + "loss": 0.4992, + "step": 4936 + }, + { + "epoch": 0.42, + "learning_rate": 1.2999155618583414e-05, + "loss": 0.4897, + "step": 4937 + }, + { + "epoch": 0.42, + "learning_rate": 1.2996521035372847e-05, + "loss": 0.4771, + "step": 4938 + }, + { + "epoch": 0.42, + "learning_rate": 1.2993886223635076e-05, + "loss": 0.5054, + "step": 4939 + }, + { + "epoch": 0.42, + "learning_rate": 1.2991251183571043e-05, + "loss": 0.4941, + "step": 4940 + }, + { + "epoch": 0.42, + "learning_rate": 1.2988615915381707e-05, + "loss": 0.4895, + "step": 4941 + }, + { + "epoch": 0.42, + "learning_rate": 1.2985980419268045e-05, + "loss": 0.4878, + "step": 4942 + }, + { + "epoch": 0.42, + "learning_rate": 1.2983344695431046e-05, + "loss": 0.4724, + "step": 4943 + }, + { + "epoch": 0.42, + "learning_rate": 1.298070874407173e-05, + "loss": 0.4868, + "step": 4944 + }, + { + "epoch": 0.42, + "learning_rate": 1.2978072565391118e-05, + "loss": 0.4822, + "step": 4945 + }, + { + "epoch": 0.42, + "learning_rate": 1.297543615959026e-05, + "loss": 0.4788, + "step": 4946 + }, + { + "epoch": 0.42, + "learning_rate": 1.2972799526870219e-05, + "loss": 0.4807, + "step": 4947 + }, + { + "epoch": 0.42, + "learning_rate": 1.2970162667432075e-05, + "loss": 0.4807, + "step": 4948 + }, + { + "epoch": 0.42, + "learning_rate": 1.2967525581476925e-05, + "loss": 0.5076, + "step": 4949 + }, + { + "epoch": 0.42, + "learning_rate": 1.2964888269205886e-05, + "loss": 0.4714, + "step": 4950 + }, + { + "epoch": 0.42, + "learning_rate": 1.2962250730820092e-05, + "loss": 0.4841, + "step": 4951 + }, + { + "epoch": 0.42, + "learning_rate": 1.2959612966520683e-05, + "loss": 0.4883, + "step": 4952 + }, + { + "epoch": 0.42, + "learning_rate": 1.295697497650884e-05, + "loss": 0.4657, + "step": 4953 + }, + { + "epoch": 0.42, + "learning_rate": 1.2954336760985737e-05, + "loss": 0.483, + "step": 4954 + }, + { + "epoch": 0.42, + "learning_rate": 1.2951698320152578e-05, + "loss": 0.4747, + "step": 4955 + }, + { + "epoch": 0.42, + "learning_rate": 1.2949059654210587e-05, + "loss": 0.4767, + "step": 4956 + }, + { + "epoch": 0.42, + "learning_rate": 1.294642076336099e-05, + "loss": 0.4611, + "step": 4957 + }, + { + "epoch": 0.42, + "learning_rate": 1.2943781647805048e-05, + "loss": 0.4999, + "step": 4958 + }, + { + "epoch": 0.42, + "learning_rate": 1.2941142307744023e-05, + "loss": 0.5002, + "step": 4959 + }, + { + "epoch": 0.42, + "learning_rate": 1.2938502743379212e-05, + "loss": 0.4671, + "step": 4960 + }, + { + "epoch": 0.42, + "learning_rate": 1.2935862954911909e-05, + "loss": 0.4805, + "step": 4961 + }, + { + "epoch": 0.42, + "learning_rate": 1.2933222942543444e-05, + "loss": 0.482, + "step": 4962 + }, + { + "epoch": 0.42, + "learning_rate": 1.293058270647515e-05, + "loss": 0.4813, + "step": 4963 + }, + { + "epoch": 0.42, + "learning_rate": 1.2927942246908383e-05, + "loss": 0.4731, + "step": 4964 + }, + { + "epoch": 0.42, + "learning_rate": 1.2925301564044519e-05, + "loss": 0.4979, + "step": 4965 + }, + { + "epoch": 0.42, + "learning_rate": 1.2922660658084945e-05, + "loss": 0.4735, + "step": 4966 + }, + { + "epoch": 0.42, + "learning_rate": 1.2920019529231065e-05, + "loss": 0.4798, + "step": 4967 + }, + { + "epoch": 0.42, + "learning_rate": 1.2917378177684303e-05, + "loss": 0.4751, + "step": 4968 + }, + { + "epoch": 0.42, + "learning_rate": 1.2914736603646108e-05, + "loss": 0.4862, + "step": 4969 + }, + { + "epoch": 0.42, + "learning_rate": 1.2912094807317927e-05, + "loss": 0.4927, + "step": 4970 + }, + { + "epoch": 0.42, + "learning_rate": 1.2909452788901238e-05, + "loss": 0.4666, + "step": 4971 + }, + { + "epoch": 0.42, + "learning_rate": 1.2906810548597533e-05, + "loss": 0.4822, + "step": 4972 + }, + { + "epoch": 0.42, + "learning_rate": 1.290416808660832e-05, + "loss": 0.4719, + "step": 4973 + }, + { + "epoch": 0.42, + "learning_rate": 1.2901525403135126e-05, + "loss": 0.4987, + "step": 4974 + }, + { + "epoch": 0.42, + "learning_rate": 1.289888249837949e-05, + "loss": 0.4875, + "step": 4975 + }, + { + "epoch": 0.42, + "learning_rate": 1.2896239372542971e-05, + "loss": 0.4737, + "step": 4976 + }, + { + "epoch": 0.42, + "learning_rate": 1.2893596025827146e-05, + "loss": 0.4934, + "step": 4977 + }, + { + "epoch": 0.42, + "learning_rate": 1.289095245843361e-05, + "loss": 0.4864, + "step": 4978 + }, + { + "epoch": 0.42, + "learning_rate": 1.288830867056397e-05, + "loss": 0.4866, + "step": 4979 + }, + { + "epoch": 0.42, + "learning_rate": 1.288566466241985e-05, + "loss": 0.4631, + "step": 4980 + }, + { + "epoch": 0.42, + "learning_rate": 1.2883020434202897e-05, + "loss": 0.4846, + "step": 4981 + }, + { + "epoch": 0.42, + "learning_rate": 1.288037598611477e-05, + "loss": 0.4993, + "step": 4982 + }, + { + "epoch": 0.42, + "learning_rate": 1.2877731318357145e-05, + "loss": 0.498, + "step": 4983 + }, + { + "epoch": 0.42, + "learning_rate": 1.2875086431131716e-05, + "loss": 0.4905, + "step": 4984 + }, + { + "epoch": 0.43, + "learning_rate": 1.2872441324640191e-05, + "loss": 0.4845, + "step": 4985 + }, + { + "epoch": 0.43, + "learning_rate": 1.28697959990843e-05, + "loss": 0.476, + "step": 4986 + }, + { + "epoch": 0.43, + "learning_rate": 1.2867150454665783e-05, + "loss": 0.4825, + "step": 4987 + }, + { + "epoch": 0.43, + "learning_rate": 1.2864504691586404e-05, + "loss": 0.4991, + "step": 4988 + }, + { + "epoch": 0.43, + "learning_rate": 1.2861858710047938e-05, + "loss": 0.4624, + "step": 4989 + }, + { + "epoch": 0.43, + "learning_rate": 1.2859212510252176e-05, + "loss": 0.5, + "step": 4990 + }, + { + "epoch": 0.43, + "learning_rate": 1.2856566092400936e-05, + "loss": 0.4703, + "step": 4991 + }, + { + "epoch": 0.43, + "learning_rate": 1.2853919456696038e-05, + "loss": 0.4835, + "step": 4992 + }, + { + "epoch": 0.43, + "learning_rate": 1.2851272603339329e-05, + "loss": 0.4954, + "step": 4993 + }, + { + "epoch": 0.43, + "learning_rate": 1.2848625532532664e-05, + "loss": 0.4753, + "step": 4994 + }, + { + "epoch": 0.43, + "learning_rate": 1.2845978244477925e-05, + "loss": 0.4834, + "step": 4995 + }, + { + "epoch": 0.43, + "learning_rate": 1.2843330739377003e-05, + "loss": 0.4747, + "step": 4996 + }, + { + "epoch": 0.43, + "learning_rate": 1.284068301743181e-05, + "loss": 0.4894, + "step": 4997 + }, + { + "epoch": 0.43, + "learning_rate": 1.2838035078844268e-05, + "loss": 0.4821, + "step": 4998 + }, + { + "epoch": 0.43, + "learning_rate": 1.2835386923816324e-05, + "loss": 0.4585, + "step": 4999 + }, + { + "epoch": 0.43, + "learning_rate": 1.2832738552549935e-05, + "loss": 0.4873, + "step": 5000 + }, + { + "epoch": 0.43, + "learning_rate": 1.283008996524708e-05, + "loss": 0.4931, + "step": 5001 + }, + { + "epoch": 0.43, + "learning_rate": 1.2827441162109749e-05, + "loss": 0.455, + "step": 5002 + }, + { + "epoch": 0.43, + "learning_rate": 1.2824792143339948e-05, + "loss": 0.4789, + "step": 5003 + }, + { + "epoch": 0.43, + "learning_rate": 1.2822142909139707e-05, + "loss": 0.4613, + "step": 5004 + }, + { + "epoch": 0.43, + "learning_rate": 1.2819493459711061e-05, + "loss": 0.4629, + "step": 5005 + }, + { + "epoch": 0.43, + "learning_rate": 1.281684379525608e-05, + "loss": 0.4955, + "step": 5006 + }, + { + "epoch": 0.43, + "learning_rate": 1.2814193915976827e-05, + "loss": 0.4746, + "step": 5007 + }, + { + "epoch": 0.43, + "learning_rate": 1.2811543822075396e-05, + "loss": 0.4804, + "step": 5008 + }, + { + "epoch": 0.43, + "learning_rate": 1.28088935137539e-05, + "loss": 0.4897, + "step": 5009 + }, + { + "epoch": 0.43, + "learning_rate": 1.2806242991214454e-05, + "loss": 0.4676, + "step": 5010 + }, + { + "epoch": 0.43, + "learning_rate": 1.2803592254659202e-05, + "loss": 0.4783, + "step": 5011 + }, + { + "epoch": 0.43, + "learning_rate": 1.28009413042903e-05, + "loss": 0.4777, + "step": 5012 + }, + { + "epoch": 0.43, + "learning_rate": 1.2798290140309924e-05, + "loss": 0.4843, + "step": 5013 + }, + { + "epoch": 0.43, + "learning_rate": 1.2795638762920254e-05, + "loss": 0.5035, + "step": 5014 + }, + { + "epoch": 0.43, + "learning_rate": 1.2792987172323504e-05, + "loss": 0.4743, + "step": 5015 + }, + { + "epoch": 0.43, + "learning_rate": 1.2790335368721891e-05, + "loss": 0.5164, + "step": 5016 + }, + { + "epoch": 0.43, + "learning_rate": 1.2787683352317652e-05, + "loss": 0.5026, + "step": 5017 + }, + { + "epoch": 0.43, + "learning_rate": 1.2785031123313046e-05, + "loss": 0.4653, + "step": 5018 + }, + { + "epoch": 0.43, + "learning_rate": 1.2782378681910337e-05, + "loss": 0.4758, + "step": 5019 + }, + { + "epoch": 0.43, + "learning_rate": 1.2779726028311812e-05, + "loss": 0.5016, + "step": 5020 + }, + { + "epoch": 0.43, + "learning_rate": 1.2777073162719777e-05, + "loss": 0.468, + "step": 5021 + }, + { + "epoch": 0.43, + "learning_rate": 1.2774420085336549e-05, + "loss": 0.48, + "step": 5022 + }, + { + "epoch": 0.43, + "learning_rate": 1.2771766796364462e-05, + "loss": 0.4923, + "step": 5023 + }, + { + "epoch": 0.43, + "learning_rate": 1.2769113296005868e-05, + "loss": 0.4771, + "step": 5024 + }, + { + "epoch": 0.43, + "learning_rate": 1.2766459584463133e-05, + "loss": 0.4555, + "step": 5025 + }, + { + "epoch": 0.43, + "learning_rate": 1.276380566193864e-05, + "loss": 0.4728, + "step": 5026 + }, + { + "epoch": 0.43, + "learning_rate": 1.276115152863479e-05, + "loss": 0.5026, + "step": 5027 + }, + { + "epoch": 0.43, + "learning_rate": 1.2758497184753995e-05, + "loss": 0.4744, + "step": 5028 + }, + { + "epoch": 0.43, + "learning_rate": 1.2755842630498689e-05, + "loss": 0.4939, + "step": 5029 + }, + { + "epoch": 0.43, + "learning_rate": 1.2753187866071317e-05, + "loss": 0.4805, + "step": 5030 + }, + { + "epoch": 0.43, + "learning_rate": 1.2750532891674347e-05, + "loss": 0.4661, + "step": 5031 + }, + { + "epoch": 0.43, + "learning_rate": 1.2747877707510252e-05, + "loss": 0.475, + "step": 5032 + }, + { + "epoch": 0.43, + "learning_rate": 1.2745222313781536e-05, + "loss": 0.483, + "step": 5033 + }, + { + "epoch": 0.43, + "learning_rate": 1.2742566710690703e-05, + "loss": 0.4985, + "step": 5034 + }, + { + "epoch": 0.43, + "learning_rate": 1.2739910898440282e-05, + "loss": 0.479, + "step": 5035 + }, + { + "epoch": 0.43, + "learning_rate": 1.273725487723282e-05, + "loss": 0.4809, + "step": 5036 + }, + { + "epoch": 0.43, + "learning_rate": 1.273459864727087e-05, + "loss": 0.4705, + "step": 5037 + }, + { + "epoch": 0.43, + "learning_rate": 1.2731942208757012e-05, + "loss": 0.4948, + "step": 5038 + }, + { + "epoch": 0.43, + "learning_rate": 1.2729285561893833e-05, + "loss": 0.4835, + "step": 5039 + }, + { + "epoch": 0.43, + "learning_rate": 1.2726628706883947e-05, + "loss": 0.4517, + "step": 5040 + }, + { + "epoch": 0.43, + "learning_rate": 1.272397164392997e-05, + "loss": 0.4764, + "step": 5041 + }, + { + "epoch": 0.43, + "learning_rate": 1.2721314373234543e-05, + "loss": 0.4914, + "step": 5042 + }, + { + "epoch": 0.43, + "learning_rate": 1.271865689500032e-05, + "loss": 0.488, + "step": 5043 + }, + { + "epoch": 0.43, + "learning_rate": 1.2715999209429974e-05, + "loss": 0.4859, + "step": 5044 + }, + { + "epoch": 0.43, + "learning_rate": 1.2713341316726191e-05, + "loss": 0.4709, + "step": 5045 + }, + { + "epoch": 0.43, + "learning_rate": 1.2710683217091668e-05, + "loss": 0.4775, + "step": 5046 + }, + { + "epoch": 0.43, + "learning_rate": 1.2708024910729127e-05, + "loss": 0.4729, + "step": 5047 + }, + { + "epoch": 0.43, + "learning_rate": 1.2705366397841303e-05, + "loss": 0.5038, + "step": 5048 + }, + { + "epoch": 0.43, + "learning_rate": 1.2702707678630941e-05, + "loss": 0.4812, + "step": 5049 + }, + { + "epoch": 0.43, + "learning_rate": 1.2700048753300806e-05, + "loss": 0.4778, + "step": 5050 + }, + { + "epoch": 0.43, + "learning_rate": 1.2697389622053681e-05, + "loss": 0.4938, + "step": 5051 + }, + { + "epoch": 0.43, + "learning_rate": 1.2694730285092365e-05, + "loss": 0.4999, + "step": 5052 + }, + { + "epoch": 0.43, + "learning_rate": 1.2692070742619665e-05, + "loss": 0.4765, + "step": 5053 + }, + { + "epoch": 0.43, + "learning_rate": 1.2689410994838414e-05, + "loss": 0.4783, + "step": 5054 + }, + { + "epoch": 0.43, + "learning_rate": 1.2686751041951451e-05, + "loss": 0.4968, + "step": 5055 + }, + { + "epoch": 0.43, + "learning_rate": 1.2684090884161636e-05, + "loss": 0.4853, + "step": 5056 + }, + { + "epoch": 0.43, + "learning_rate": 1.2681430521671845e-05, + "loss": 0.4768, + "step": 5057 + }, + { + "epoch": 0.43, + "learning_rate": 1.2678769954684966e-05, + "loss": 0.4856, + "step": 5058 + }, + { + "epoch": 0.43, + "learning_rate": 1.2676109183403909e-05, + "loss": 0.4908, + "step": 5059 + }, + { + "epoch": 0.43, + "learning_rate": 1.2673448208031591e-05, + "loss": 0.4537, + "step": 5060 + }, + { + "epoch": 0.43, + "learning_rate": 1.2670787028770955e-05, + "loss": 0.4938, + "step": 5061 + }, + { + "epoch": 0.43, + "learning_rate": 1.2668125645824945e-05, + "loss": 0.4616, + "step": 5062 + }, + { + "epoch": 0.43, + "learning_rate": 1.266546405939654e-05, + "loss": 0.4728, + "step": 5063 + }, + { + "epoch": 0.43, + "learning_rate": 1.2662802269688715e-05, + "loss": 0.495, + "step": 5064 + }, + { + "epoch": 0.43, + "learning_rate": 1.2660140276904471e-05, + "loss": 0.4883, + "step": 5065 + }, + { + "epoch": 0.43, + "learning_rate": 1.2657478081246826e-05, + "loss": 0.4818, + "step": 5066 + }, + { + "epoch": 0.43, + "learning_rate": 1.2654815682918801e-05, + "loss": 0.4791, + "step": 5067 + }, + { + "epoch": 0.43, + "learning_rate": 1.2652153082123458e-05, + "loss": 0.4919, + "step": 5068 + }, + { + "epoch": 0.43, + "learning_rate": 1.2649490279063845e-05, + "loss": 0.4705, + "step": 5069 + }, + { + "epoch": 0.43, + "learning_rate": 1.2646827273943042e-05, + "loss": 0.4606, + "step": 5070 + }, + { + "epoch": 0.43, + "learning_rate": 1.2644164066964138e-05, + "loss": 0.4741, + "step": 5071 + }, + { + "epoch": 0.43, + "learning_rate": 1.2641500658330248e-05, + "loss": 0.4829, + "step": 5072 + }, + { + "epoch": 0.43, + "learning_rate": 1.2638837048244486e-05, + "loss": 0.4855, + "step": 5073 + }, + { + "epoch": 0.43, + "learning_rate": 1.2636173236909995e-05, + "loss": 0.4725, + "step": 5074 + }, + { + "epoch": 0.43, + "learning_rate": 1.263350922452993e-05, + "loss": 0.4829, + "step": 5075 + }, + { + "epoch": 0.43, + "learning_rate": 1.263084501130745e-05, + "loss": 0.4754, + "step": 5076 + }, + { + "epoch": 0.43, + "learning_rate": 1.2628180597445754e-05, + "loss": 0.4734, + "step": 5077 + }, + { + "epoch": 0.43, + "learning_rate": 1.2625515983148029e-05, + "loss": 0.4783, + "step": 5078 + }, + { + "epoch": 0.43, + "learning_rate": 1.2622851168617495e-05, + "loss": 0.4809, + "step": 5079 + }, + { + "epoch": 0.43, + "learning_rate": 1.2620186154057383e-05, + "loss": 0.4835, + "step": 5080 + }, + { + "epoch": 0.43, + "learning_rate": 1.2617520939670934e-05, + "loss": 0.4844, + "step": 5081 + }, + { + "epoch": 0.43, + "learning_rate": 1.2614855525661409e-05, + "loss": 0.5053, + "step": 5082 + }, + { + "epoch": 0.43, + "learning_rate": 1.2612189912232084e-05, + "loss": 0.4822, + "step": 5083 + }, + { + "epoch": 0.43, + "learning_rate": 1.2609524099586254e-05, + "loss": 0.4987, + "step": 5084 + }, + { + "epoch": 0.43, + "learning_rate": 1.2606858087927219e-05, + "loss": 0.4917, + "step": 5085 + }, + { + "epoch": 0.43, + "learning_rate": 1.2604191877458307e-05, + "loss": 0.4614, + "step": 5086 + }, + { + "epoch": 0.43, + "learning_rate": 1.2601525468382846e-05, + "loss": 0.4816, + "step": 5087 + }, + { + "epoch": 0.43, + "learning_rate": 1.2598858860904193e-05, + "loss": 0.4781, + "step": 5088 + }, + { + "epoch": 0.43, + "learning_rate": 1.2596192055225716e-05, + "loss": 0.4494, + "step": 5089 + }, + { + "epoch": 0.43, + "learning_rate": 1.259352505155079e-05, + "loss": 0.5084, + "step": 5090 + }, + { + "epoch": 0.43, + "learning_rate": 1.2590857850082819e-05, + "loss": 0.5017, + "step": 5091 + }, + { + "epoch": 0.43, + "learning_rate": 1.2588190451025209e-05, + "loss": 0.4863, + "step": 5092 + }, + { + "epoch": 0.43, + "learning_rate": 1.2585522854581393e-05, + "loss": 0.4782, + "step": 5093 + }, + { + "epoch": 0.43, + "learning_rate": 1.2582855060954806e-05, + "loss": 0.4817, + "step": 5094 + }, + { + "epoch": 0.43, + "learning_rate": 1.2580187070348913e-05, + "loss": 0.4796, + "step": 5095 + }, + { + "epoch": 0.43, + "learning_rate": 1.2577518882967182e-05, + "loss": 0.4734, + "step": 5096 + }, + { + "epoch": 0.43, + "learning_rate": 1.2574850499013093e-05, + "loss": 0.4798, + "step": 5097 + }, + { + "epoch": 0.43, + "learning_rate": 1.2572181918690162e-05, + "loss": 0.4942, + "step": 5098 + }, + { + "epoch": 0.43, + "learning_rate": 1.25695131422019e-05, + "loss": 0.4909, + "step": 5099 + }, + { + "epoch": 0.43, + "learning_rate": 1.2566844169751835e-05, + "loss": 0.4866, + "step": 5100 + }, + { + "epoch": 0.43, + "learning_rate": 1.2564175001543517e-05, + "loss": 0.4913, + "step": 5101 + }, + { + "epoch": 0.44, + "learning_rate": 1.2561505637780514e-05, + "loss": 0.4631, + "step": 5102 + }, + { + "epoch": 0.44, + "learning_rate": 1.2558836078666392e-05, + "loss": 0.4858, + "step": 5103 + }, + { + "epoch": 0.44, + "learning_rate": 1.2556166324404747e-05, + "loss": 0.4787, + "step": 5104 + }, + { + "epoch": 0.44, + "learning_rate": 1.255349637519919e-05, + "loss": 0.4943, + "step": 5105 + }, + { + "epoch": 0.44, + "learning_rate": 1.2550826231253335e-05, + "loss": 0.4899, + "step": 5106 + }, + { + "epoch": 0.44, + "learning_rate": 1.2548155892770825e-05, + "loss": 0.4757, + "step": 5107 + }, + { + "epoch": 0.44, + "learning_rate": 1.2545485359955309e-05, + "loss": 0.4945, + "step": 5108 + }, + { + "epoch": 0.44, + "learning_rate": 1.2542814633010452e-05, + "loss": 0.472, + "step": 5109 + }, + { + "epoch": 0.44, + "learning_rate": 1.2540143712139935e-05, + "loss": 0.4792, + "step": 5110 + }, + { + "epoch": 0.44, + "learning_rate": 1.2537472597547453e-05, + "loss": 0.48, + "step": 5111 + }, + { + "epoch": 0.44, + "learning_rate": 1.2534801289436715e-05, + "loss": 0.4794, + "step": 5112 + }, + { + "epoch": 0.44, + "learning_rate": 1.2532129788011452e-05, + "loss": 0.472, + "step": 5113 + }, + { + "epoch": 0.44, + "learning_rate": 1.25294580934754e-05, + "loss": 0.4812, + "step": 5114 + }, + { + "epoch": 0.44, + "learning_rate": 1.252678620603231e-05, + "loss": 0.4898, + "step": 5115 + }, + { + "epoch": 0.44, + "learning_rate": 1.2524114125885958e-05, + "loss": 0.5117, + "step": 5116 + }, + { + "epoch": 0.44, + "learning_rate": 1.2521441853240124e-05, + "loss": 0.4995, + "step": 5117 + }, + { + "epoch": 0.44, + "learning_rate": 1.2518769388298607e-05, + "loss": 0.4802, + "step": 5118 + }, + { + "epoch": 0.44, + "learning_rate": 1.2516096731265222e-05, + "loss": 0.479, + "step": 5119 + }, + { + "epoch": 0.44, + "learning_rate": 1.2513423882343797e-05, + "loss": 0.4817, + "step": 5120 + }, + { + "epoch": 0.44, + "learning_rate": 1.2510750841738168e-05, + "loss": 0.4853, + "step": 5121 + }, + { + "epoch": 0.44, + "learning_rate": 1.2508077609652203e-05, + "loss": 0.4534, + "step": 5122 + }, + { + "epoch": 0.44, + "learning_rate": 1.2505404186289765e-05, + "loss": 0.4729, + "step": 5123 + }, + { + "epoch": 0.44, + "learning_rate": 1.2502730571854747e-05, + "loss": 0.4949, + "step": 5124 + }, + { + "epoch": 0.44, + "learning_rate": 1.2500056766551047e-05, + "loss": 0.4736, + "step": 5125 + }, + { + "epoch": 0.44, + "learning_rate": 1.249738277058258e-05, + "loss": 0.4919, + "step": 5126 + }, + { + "epoch": 0.44, + "learning_rate": 1.2494708584153275e-05, + "loss": 0.4858, + "step": 5127 + }, + { + "epoch": 0.44, + "learning_rate": 1.2492034207467081e-05, + "loss": 0.4643, + "step": 5128 + }, + { + "epoch": 0.44, + "learning_rate": 1.2489359640727953e-05, + "loss": 0.4738, + "step": 5129 + }, + { + "epoch": 0.44, + "learning_rate": 1.2486684884139866e-05, + "loss": 0.4771, + "step": 5130 + }, + { + "epoch": 0.44, + "learning_rate": 1.2484009937906807e-05, + "loss": 0.4749, + "step": 5131 + }, + { + "epoch": 0.44, + "learning_rate": 1.248133480223278e-05, + "loss": 0.4969, + "step": 5132 + }, + { + "epoch": 0.44, + "learning_rate": 1.2478659477321801e-05, + "loss": 0.4861, + "step": 5133 + }, + { + "epoch": 0.44, + "learning_rate": 1.2475983963377907e-05, + "loss": 0.4833, + "step": 5134 + }, + { + "epoch": 0.44, + "learning_rate": 1.2473308260605134e-05, + "loss": 0.4801, + "step": 5135 + }, + { + "epoch": 0.44, + "learning_rate": 1.247063236920755e-05, + "loss": 0.4901, + "step": 5136 + }, + { + "epoch": 0.44, + "learning_rate": 1.2467956289389228e-05, + "loss": 0.4832, + "step": 5137 + }, + { + "epoch": 0.44, + "learning_rate": 1.2465280021354254e-05, + "loss": 0.4644, + "step": 5138 + }, + { + "epoch": 0.44, + "learning_rate": 1.2462603565306733e-05, + "loss": 0.4808, + "step": 5139 + }, + { + "epoch": 0.44, + "learning_rate": 1.245992692145078e-05, + "loss": 0.4836, + "step": 5140 + }, + { + "epoch": 0.44, + "learning_rate": 1.2457250089990534e-05, + "loss": 0.4697, + "step": 5141 + }, + { + "epoch": 0.44, + "learning_rate": 1.2454573071130138e-05, + "loss": 0.4976, + "step": 5142 + }, + { + "epoch": 0.44, + "learning_rate": 1.2451895865073751e-05, + "loss": 0.4706, + "step": 5143 + }, + { + "epoch": 0.44, + "learning_rate": 1.2449218472025548e-05, + "loss": 0.4734, + "step": 5144 + }, + { + "epoch": 0.44, + "learning_rate": 1.244654089218972e-05, + "loss": 0.4955, + "step": 5145 + }, + { + "epoch": 0.44, + "learning_rate": 1.2443863125770473e-05, + "loss": 0.4672, + "step": 5146 + }, + { + "epoch": 0.44, + "learning_rate": 1.2441185172972015e-05, + "loss": 0.5048, + "step": 5147 + }, + { + "epoch": 0.44, + "learning_rate": 1.2438507033998588e-05, + "loss": 0.4911, + "step": 5148 + }, + { + "epoch": 0.44, + "learning_rate": 1.2435828709054431e-05, + "loss": 0.4969, + "step": 5149 + }, + { + "epoch": 0.44, + "learning_rate": 1.2433150198343808e-05, + "loss": 0.4702, + "step": 5150 + }, + { + "epoch": 0.44, + "learning_rate": 1.2430471502070998e-05, + "loss": 0.4711, + "step": 5151 + }, + { + "epoch": 0.44, + "learning_rate": 1.242779262044028e-05, + "loss": 0.4722, + "step": 5152 + }, + { + "epoch": 0.44, + "learning_rate": 1.242511355365596e-05, + "loss": 0.5053, + "step": 5153 + }, + { + "epoch": 0.44, + "learning_rate": 1.2422434301922358e-05, + "loss": 0.4903, + "step": 5154 + }, + { + "epoch": 0.44, + "learning_rate": 1.2419754865443803e-05, + "loss": 0.4821, + "step": 5155 + }, + { + "epoch": 0.44, + "learning_rate": 1.2417075244424637e-05, + "loss": 0.4828, + "step": 5156 + }, + { + "epoch": 0.44, + "learning_rate": 1.2414395439069224e-05, + "loss": 0.4878, + "step": 5157 + }, + { + "epoch": 0.44, + "learning_rate": 1.2411715449581938e-05, + "loss": 0.4862, + "step": 5158 + }, + { + "epoch": 0.44, + "learning_rate": 1.2409035276167156e-05, + "loss": 0.4774, + "step": 5159 + }, + { + "epoch": 0.44, + "learning_rate": 1.2406354919029294e-05, + "loss": 0.4815, + "step": 5160 + }, + { + "epoch": 0.44, + "learning_rate": 1.2403674378372755e-05, + "loss": 0.4884, + "step": 5161 + }, + { + "epoch": 0.44, + "learning_rate": 1.2400993654401974e-05, + "loss": 0.4852, + "step": 5162 + }, + { + "epoch": 0.44, + "learning_rate": 1.239831274732139e-05, + "loss": 0.4771, + "step": 5163 + }, + { + "epoch": 0.44, + "learning_rate": 1.239563165733547e-05, + "loss": 0.4822, + "step": 5164 + }, + { + "epoch": 0.44, + "learning_rate": 1.2392950384648674e-05, + "loss": 0.4907, + "step": 5165 + }, + { + "epoch": 0.44, + "learning_rate": 1.2390268929465492e-05, + "loss": 0.4839, + "step": 5166 + }, + { + "epoch": 0.44, + "learning_rate": 1.2387587291990423e-05, + "loss": 0.4758, + "step": 5167 + }, + { + "epoch": 0.44, + "learning_rate": 1.2384905472427975e-05, + "loss": 0.4928, + "step": 5168 + }, + { + "epoch": 0.44, + "learning_rate": 1.2382223470982687e-05, + "loss": 0.5195, + "step": 5169 + }, + { + "epoch": 0.44, + "learning_rate": 1.2379541287859085e-05, + "loss": 0.4746, + "step": 5170 + }, + { + "epoch": 0.44, + "learning_rate": 1.2376858923261732e-05, + "loss": 0.4847, + "step": 5171 + }, + { + "epoch": 0.44, + "learning_rate": 1.2374176377395194e-05, + "loss": 0.5012, + "step": 5172 + }, + { + "epoch": 0.44, + "learning_rate": 1.2371493650464057e-05, + "loss": 0.4813, + "step": 5173 + }, + { + "epoch": 0.44, + "learning_rate": 1.236881074267291e-05, + "loss": 0.4832, + "step": 5174 + }, + { + "epoch": 0.44, + "learning_rate": 1.2366127654226365e-05, + "loss": 0.5043, + "step": 5175 + }, + { + "epoch": 0.44, + "learning_rate": 1.2363444385329052e-05, + "loss": 0.5132, + "step": 5176 + }, + { + "epoch": 0.44, + "learning_rate": 1.2360760936185599e-05, + "loss": 0.4537, + "step": 5177 + }, + { + "epoch": 0.44, + "learning_rate": 1.2358077307000663e-05, + "loss": 0.4834, + "step": 5178 + }, + { + "epoch": 0.44, + "learning_rate": 1.2355393497978904e-05, + "loss": 0.4782, + "step": 5179 + }, + { + "epoch": 0.44, + "learning_rate": 1.2352709509325005e-05, + "loss": 0.4679, + "step": 5180 + }, + { + "epoch": 0.44, + "learning_rate": 1.2350025341243659e-05, + "loss": 0.4611, + "step": 5181 + }, + { + "epoch": 0.44, + "learning_rate": 1.2347340993939567e-05, + "loss": 0.4859, + "step": 5182 + }, + { + "epoch": 0.44, + "learning_rate": 1.2344656467617451e-05, + "loss": 0.4629, + "step": 5183 + }, + { + "epoch": 0.44, + "learning_rate": 1.2341971762482043e-05, + "loss": 0.4946, + "step": 5184 + }, + { + "epoch": 0.44, + "learning_rate": 1.2339286878738094e-05, + "loss": 0.4836, + "step": 5185 + }, + { + "epoch": 0.44, + "learning_rate": 1.2336601816590359e-05, + "loss": 0.4887, + "step": 5186 + }, + { + "epoch": 0.44, + "learning_rate": 1.2333916576243617e-05, + "loss": 0.466, + "step": 5187 + }, + { + "epoch": 0.44, + "learning_rate": 1.233123115790265e-05, + "loss": 0.4798, + "step": 5188 + }, + { + "epoch": 0.44, + "learning_rate": 1.2328545561772263e-05, + "loss": 0.4669, + "step": 5189 + }, + { + "epoch": 0.44, + "learning_rate": 1.2325859788057273e-05, + "loss": 0.4695, + "step": 5190 + }, + { + "epoch": 0.44, + "learning_rate": 1.2323173836962502e-05, + "loss": 0.4829, + "step": 5191 + }, + { + "epoch": 0.44, + "learning_rate": 1.2320487708692797e-05, + "loss": 0.4831, + "step": 5192 + }, + { + "epoch": 0.44, + "learning_rate": 1.231780140345301e-05, + "loss": 0.4601, + "step": 5193 + }, + { + "epoch": 0.44, + "learning_rate": 1.2315114921448012e-05, + "loss": 0.4752, + "step": 5194 + }, + { + "epoch": 0.44, + "learning_rate": 1.2312428262882685e-05, + "loss": 0.5056, + "step": 5195 + }, + { + "epoch": 0.44, + "learning_rate": 1.2309741427961925e-05, + "loss": 0.4836, + "step": 5196 + }, + { + "epoch": 0.44, + "learning_rate": 1.230705441689064e-05, + "loss": 0.5092, + "step": 5197 + }, + { + "epoch": 0.44, + "learning_rate": 1.2304367229873754e-05, + "loss": 0.5142, + "step": 5198 + }, + { + "epoch": 0.44, + "learning_rate": 1.2301679867116206e-05, + "loss": 0.5103, + "step": 5199 + }, + { + "epoch": 0.44, + "learning_rate": 1.2298992328822937e-05, + "loss": 0.4613, + "step": 5200 + }, + { + "epoch": 0.44, + "learning_rate": 1.2296304615198915e-05, + "loss": 0.4854, + "step": 5201 + }, + { + "epoch": 0.44, + "learning_rate": 1.2293616726449117e-05, + "loss": 0.503, + "step": 5202 + }, + { + "epoch": 0.44, + "learning_rate": 1.2290928662778535e-05, + "loss": 0.4697, + "step": 5203 + }, + { + "epoch": 0.44, + "learning_rate": 1.2288240424392168e-05, + "loss": 0.4844, + "step": 5204 + }, + { + "epoch": 0.44, + "learning_rate": 1.228555201149503e-05, + "loss": 0.4622, + "step": 5205 + }, + { + "epoch": 0.44, + "learning_rate": 1.2282863424292155e-05, + "loss": 0.4678, + "step": 5206 + }, + { + "epoch": 0.44, + "learning_rate": 1.2280174662988587e-05, + "loss": 0.4795, + "step": 5207 + }, + { + "epoch": 0.44, + "learning_rate": 1.2277485727789378e-05, + "loss": 0.4671, + "step": 5208 + }, + { + "epoch": 0.44, + "learning_rate": 1.2274796618899599e-05, + "loss": 0.4825, + "step": 5209 + }, + { + "epoch": 0.44, + "learning_rate": 1.2272107336524333e-05, + "loss": 0.4869, + "step": 5210 + }, + { + "epoch": 0.44, + "learning_rate": 1.2269417880868674e-05, + "loss": 0.5037, + "step": 5211 + }, + { + "epoch": 0.44, + "learning_rate": 1.2266728252137735e-05, + "loss": 0.4696, + "step": 5212 + }, + { + "epoch": 0.44, + "learning_rate": 1.2264038450536637e-05, + "loss": 0.4804, + "step": 5213 + }, + { + "epoch": 0.44, + "learning_rate": 1.2261348476270514e-05, + "loss": 0.4933, + "step": 5214 + }, + { + "epoch": 0.44, + "learning_rate": 1.2258658329544513e-05, + "loss": 0.4851, + "step": 5215 + }, + { + "epoch": 0.44, + "learning_rate": 1.2255968010563799e-05, + "loss": 0.4731, + "step": 5216 + }, + { + "epoch": 0.44, + "learning_rate": 1.2253277519533549e-05, + "loss": 0.4949, + "step": 5217 + }, + { + "epoch": 0.44, + "learning_rate": 1.2250586856658946e-05, + "loss": 0.4768, + "step": 5218 + }, + { + "epoch": 0.45, + "learning_rate": 1.2247896022145194e-05, + "loss": 0.4697, + "step": 5219 + }, + { + "epoch": 0.45, + "learning_rate": 1.2245205016197507e-05, + "loss": 0.4778, + "step": 5220 + }, + { + "epoch": 0.45, + "learning_rate": 1.2242513839021109e-05, + "loss": 0.4798, + "step": 5221 + }, + { + "epoch": 0.45, + "learning_rate": 1.2239822490821247e-05, + "loss": 0.4923, + "step": 5222 + }, + { + "epoch": 0.45, + "learning_rate": 1.2237130971803171e-05, + "loss": 0.4716, + "step": 5223 + }, + { + "epoch": 0.45, + "learning_rate": 1.2234439282172144e-05, + "loss": 0.4978, + "step": 5224 + }, + { + "epoch": 0.45, + "learning_rate": 1.223174742213345e-05, + "loss": 0.4867, + "step": 5225 + }, + { + "epoch": 0.45, + "learning_rate": 1.2229055391892383e-05, + "loss": 0.4742, + "step": 5226 + }, + { + "epoch": 0.45, + "learning_rate": 1.2226363191654244e-05, + "loss": 0.4893, + "step": 5227 + }, + { + "epoch": 0.45, + "learning_rate": 1.2223670821624353e-05, + "loss": 0.4972, + "step": 5228 + }, + { + "epoch": 0.45, + "learning_rate": 1.2220978282008044e-05, + "loss": 0.4669, + "step": 5229 + }, + { + "epoch": 0.45, + "learning_rate": 1.2218285573010654e-05, + "loss": 0.4943, + "step": 5230 + }, + { + "epoch": 0.45, + "learning_rate": 1.221559269483755e-05, + "loss": 0.5037, + "step": 5231 + }, + { + "epoch": 0.45, + "learning_rate": 1.2212899647694094e-05, + "loss": 0.4796, + "step": 5232 + }, + { + "epoch": 0.45, + "learning_rate": 1.2210206431785674e-05, + "loss": 0.4678, + "step": 5233 + }, + { + "epoch": 0.45, + "learning_rate": 1.2207513047317683e-05, + "loss": 0.4901, + "step": 5234 + }, + { + "epoch": 0.45, + "learning_rate": 1.2204819494495531e-05, + "loss": 0.4742, + "step": 5235 + }, + { + "epoch": 0.45, + "learning_rate": 1.220212577352464e-05, + "loss": 0.4719, + "step": 5236 + }, + { + "epoch": 0.45, + "learning_rate": 1.2199431884610444e-05, + "loss": 0.4598, + "step": 5237 + }, + { + "epoch": 0.45, + "learning_rate": 1.2196737827958391e-05, + "loss": 0.4764, + "step": 5238 + }, + { + "epoch": 0.45, + "learning_rate": 1.2194043603773938e-05, + "loss": 0.485, + "step": 5239 + }, + { + "epoch": 0.45, + "learning_rate": 1.2191349212262562e-05, + "loss": 0.4743, + "step": 5240 + }, + { + "epoch": 0.45, + "learning_rate": 1.2188654653629745e-05, + "loss": 0.4614, + "step": 5241 + }, + { + "epoch": 0.45, + "learning_rate": 1.2185959928080988e-05, + "loss": 0.4958, + "step": 5242 + }, + { + "epoch": 0.45, + "learning_rate": 1.21832650358218e-05, + "loss": 0.4733, + "step": 5243 + }, + { + "epoch": 0.45, + "learning_rate": 1.2180569977057706e-05, + "loss": 0.4697, + "step": 5244 + }, + { + "epoch": 0.45, + "learning_rate": 1.217787475199424e-05, + "loss": 0.4722, + "step": 5245 + }, + { + "epoch": 0.45, + "learning_rate": 1.2175179360836955e-05, + "loss": 0.4834, + "step": 5246 + }, + { + "epoch": 0.45, + "learning_rate": 1.2172483803791413e-05, + "loss": 0.4832, + "step": 5247 + }, + { + "epoch": 0.45, + "learning_rate": 1.2169788081063181e-05, + "loss": 0.4899, + "step": 5248 + }, + { + "epoch": 0.45, + "learning_rate": 1.2167092192857854e-05, + "loss": 0.4883, + "step": 5249 + }, + { + "epoch": 0.45, + "learning_rate": 1.2164396139381029e-05, + "loss": 0.4794, + "step": 5250 + }, + { + "epoch": 0.45, + "learning_rate": 1.216169992083832e-05, + "loss": 0.4803, + "step": 5251 + }, + { + "epoch": 0.45, + "learning_rate": 1.2159003537435349e-05, + "loss": 0.4633, + "step": 5252 + }, + { + "epoch": 0.45, + "learning_rate": 1.2156306989377753e-05, + "loss": 0.4767, + "step": 5253 + }, + { + "epoch": 0.45, + "learning_rate": 1.2153610276871187e-05, + "loss": 0.4911, + "step": 5254 + }, + { + "epoch": 0.45, + "learning_rate": 1.2150913400121306e-05, + "loss": 0.4744, + "step": 5255 + }, + { + "epoch": 0.45, + "learning_rate": 1.2148216359333793e-05, + "loss": 0.4626, + "step": 5256 + }, + { + "epoch": 0.45, + "learning_rate": 1.214551915471433e-05, + "loss": 0.4809, + "step": 5257 + }, + { + "epoch": 0.45, + "learning_rate": 1.2142821786468619e-05, + "loss": 0.4779, + "step": 5258 + }, + { + "epoch": 0.45, + "learning_rate": 1.2140124254802374e-05, + "loss": 0.4864, + "step": 5259 + }, + { + "epoch": 0.45, + "learning_rate": 1.2137426559921317e-05, + "loss": 0.485, + "step": 5260 + }, + { + "epoch": 0.45, + "learning_rate": 1.2134728702031189e-05, + "loss": 0.4554, + "step": 5261 + }, + { + "epoch": 0.45, + "learning_rate": 1.2132030681337736e-05, + "loss": 0.4971, + "step": 5262 + }, + { + "epoch": 0.45, + "learning_rate": 1.2129332498046721e-05, + "loss": 0.489, + "step": 5263 + }, + { + "epoch": 0.45, + "learning_rate": 1.2126634152363924e-05, + "loss": 0.4771, + "step": 5264 + }, + { + "epoch": 0.45, + "learning_rate": 1.2123935644495127e-05, + "loss": 0.4823, + "step": 5265 + }, + { + "epoch": 0.45, + "learning_rate": 1.2121236974646127e-05, + "loss": 0.4765, + "step": 5266 + }, + { + "epoch": 0.45, + "learning_rate": 1.2118538143022743e-05, + "loss": 0.4677, + "step": 5267 + }, + { + "epoch": 0.45, + "learning_rate": 1.2115839149830798e-05, + "loss": 0.4582, + "step": 5268 + }, + { + "epoch": 0.45, + "learning_rate": 1.2113139995276118e-05, + "loss": 0.468, + "step": 5269 + }, + { + "epoch": 0.45, + "learning_rate": 1.2110440679564565e-05, + "loss": 0.4975, + "step": 5270 + }, + { + "epoch": 0.45, + "learning_rate": 1.2107741202901996e-05, + "loss": 0.4775, + "step": 5271 + }, + { + "epoch": 0.45, + "learning_rate": 1.210504156549428e-05, + "loss": 0.4867, + "step": 5272 + }, + { + "epoch": 0.45, + "learning_rate": 1.2102341767547308e-05, + "loss": 0.4667, + "step": 5273 + }, + { + "epoch": 0.45, + "learning_rate": 1.2099641809266978e-05, + "loss": 0.4791, + "step": 5274 + }, + { + "epoch": 0.45, + "learning_rate": 1.2096941690859194e-05, + "loss": 0.5093, + "step": 5275 + }, + { + "epoch": 0.45, + "learning_rate": 1.2094241412529883e-05, + "loss": 0.5009, + "step": 5276 + }, + { + "epoch": 0.45, + "learning_rate": 1.2091540974484979e-05, + "loss": 0.4899, + "step": 5277 + }, + { + "epoch": 0.45, + "learning_rate": 1.2088840376930429e-05, + "loss": 0.4956, + "step": 5278 + }, + { + "epoch": 0.45, + "learning_rate": 1.208613962007219e-05, + "loss": 0.4841, + "step": 5279 + }, + { + "epoch": 0.45, + "learning_rate": 1.2083438704116235e-05, + "loss": 0.5001, + "step": 5280 + }, + { + "epoch": 0.45, + "learning_rate": 1.2080737629268546e-05, + "loss": 0.4606, + "step": 5281 + }, + { + "epoch": 0.45, + "learning_rate": 1.2078036395735118e-05, + "loss": 0.4901, + "step": 5282 + }, + { + "epoch": 0.45, + "learning_rate": 1.2075335003721961e-05, + "loss": 0.4861, + "step": 5283 + }, + { + "epoch": 0.45, + "learning_rate": 1.2072633453435092e-05, + "loss": 0.4714, + "step": 5284 + }, + { + "epoch": 0.45, + "learning_rate": 1.206993174508054e-05, + "loss": 0.4869, + "step": 5285 + }, + { + "epoch": 0.45, + "learning_rate": 1.2067229878864355e-05, + "loss": 0.4907, + "step": 5286 + }, + { + "epoch": 0.45, + "learning_rate": 1.2064527854992587e-05, + "loss": 0.4733, + "step": 5287 + }, + { + "epoch": 0.45, + "learning_rate": 1.2061825673671307e-05, + "loss": 0.4775, + "step": 5288 + }, + { + "epoch": 0.45, + "learning_rate": 1.2059123335106592e-05, + "loss": 0.4748, + "step": 5289 + }, + { + "epoch": 0.45, + "learning_rate": 1.2056420839504535e-05, + "loss": 0.4836, + "step": 5290 + }, + { + "epoch": 0.45, + "learning_rate": 1.2053718187071242e-05, + "loss": 0.504, + "step": 5291 + }, + { + "epoch": 0.45, + "learning_rate": 1.2051015378012823e-05, + "loss": 0.4839, + "step": 5292 + }, + { + "epoch": 0.45, + "learning_rate": 1.2048312412535407e-05, + "loss": 0.5011, + "step": 5293 + }, + { + "epoch": 0.45, + "learning_rate": 1.2045609290845137e-05, + "loss": 0.4677, + "step": 5294 + }, + { + "epoch": 0.45, + "learning_rate": 1.2042906013148163e-05, + "loss": 0.4703, + "step": 5295 + }, + { + "epoch": 0.45, + "learning_rate": 1.2040202579650649e-05, + "loss": 0.4902, + "step": 5296 + }, + { + "epoch": 0.45, + "learning_rate": 1.2037498990558768e-05, + "loss": 0.4648, + "step": 5297 + }, + { + "epoch": 0.45, + "learning_rate": 1.2034795246078706e-05, + "loss": 0.5073, + "step": 5298 + }, + { + "epoch": 0.45, + "learning_rate": 1.2032091346416663e-05, + "loss": 0.4633, + "step": 5299 + }, + { + "epoch": 0.45, + "learning_rate": 1.2029387291778854e-05, + "loss": 0.4697, + "step": 5300 + }, + { + "epoch": 0.45, + "learning_rate": 1.202668308237149e-05, + "loss": 0.5039, + "step": 5301 + }, + { + "epoch": 0.45, + "learning_rate": 1.202397871840082e-05, + "loss": 0.4918, + "step": 5302 + }, + { + "epoch": 0.45, + "learning_rate": 1.202127420007308e-05, + "loss": 0.4794, + "step": 5303 + }, + { + "epoch": 0.45, + "learning_rate": 1.2018569527594533e-05, + "loss": 0.4577, + "step": 5304 + }, + { + "epoch": 0.45, + "learning_rate": 1.2015864701171444e-05, + "loss": 0.4847, + "step": 5305 + }, + { + "epoch": 0.45, + "learning_rate": 1.2013159721010101e-05, + "loss": 0.4638, + "step": 5306 + }, + { + "epoch": 0.45, + "learning_rate": 1.201045458731679e-05, + "loss": 0.4853, + "step": 5307 + }, + { + "epoch": 0.45, + "learning_rate": 1.2007749300297818e-05, + "loss": 0.4819, + "step": 5308 + }, + { + "epoch": 0.45, + "learning_rate": 1.2005043860159504e-05, + "loss": 0.4754, + "step": 5309 + }, + { + "epoch": 0.45, + "learning_rate": 1.2002338267108171e-05, + "loss": 0.4678, + "step": 5310 + }, + { + "epoch": 0.45, + "learning_rate": 1.1999632521350168e-05, + "loss": 0.4812, + "step": 5311 + }, + { + "epoch": 0.45, + "learning_rate": 1.1996926623091839e-05, + "loss": 0.4576, + "step": 5312 + }, + { + "epoch": 0.45, + "learning_rate": 1.1994220572539545e-05, + "loss": 0.4559, + "step": 5313 + }, + { + "epoch": 0.45, + "learning_rate": 1.1991514369899668e-05, + "loss": 0.4869, + "step": 5314 + }, + { + "epoch": 0.45, + "learning_rate": 1.1988808015378591e-05, + "loss": 0.4785, + "step": 5315 + }, + { + "epoch": 0.45, + "learning_rate": 1.198610150918271e-05, + "loss": 0.4779, + "step": 5316 + }, + { + "epoch": 0.45, + "learning_rate": 1.1983394851518435e-05, + "loss": 0.4831, + "step": 5317 + }, + { + "epoch": 0.45, + "learning_rate": 1.1980688042592192e-05, + "loss": 0.4924, + "step": 5318 + }, + { + "epoch": 0.45, + "learning_rate": 1.1977981082610406e-05, + "loss": 0.4654, + "step": 5319 + }, + { + "epoch": 0.45, + "learning_rate": 1.1975273971779528e-05, + "loss": 0.4428, + "step": 5320 + }, + { + "epoch": 0.45, + "learning_rate": 1.1972566710306009e-05, + "loss": 0.4799, + "step": 5321 + }, + { + "epoch": 0.45, + "learning_rate": 1.1969859298396317e-05, + "loss": 0.4704, + "step": 5322 + }, + { + "epoch": 0.45, + "learning_rate": 1.1967151736256932e-05, + "loss": 0.4747, + "step": 5323 + }, + { + "epoch": 0.45, + "learning_rate": 1.1964444024094344e-05, + "loss": 0.5067, + "step": 5324 + }, + { + "epoch": 0.45, + "learning_rate": 1.196173616211505e-05, + "loss": 0.5017, + "step": 5325 + }, + { + "epoch": 0.45, + "learning_rate": 1.195902815052557e-05, + "loss": 0.4818, + "step": 5326 + }, + { + "epoch": 0.45, + "learning_rate": 1.1956319989532422e-05, + "loss": 0.4796, + "step": 5327 + }, + { + "epoch": 0.45, + "learning_rate": 1.1953611679342144e-05, + "loss": 0.4995, + "step": 5328 + }, + { + "epoch": 0.45, + "learning_rate": 1.1950903220161286e-05, + "loss": 0.4829, + "step": 5329 + }, + { + "epoch": 0.45, + "learning_rate": 1.1948194612196402e-05, + "loss": 0.5035, + "step": 5330 + }, + { + "epoch": 0.45, + "learning_rate": 1.194548585565406e-05, + "loss": 0.4865, + "step": 5331 + }, + { + "epoch": 0.45, + "learning_rate": 1.1942776950740849e-05, + "loss": 0.4846, + "step": 5332 + }, + { + "epoch": 0.45, + "learning_rate": 1.1940067897663355e-05, + "loss": 0.4734, + "step": 5333 + }, + { + "epoch": 0.45, + "learning_rate": 1.1937358696628185e-05, + "loss": 0.4831, + "step": 5334 + }, + { + "epoch": 0.45, + "learning_rate": 1.193464934784195e-05, + "loss": 0.4863, + "step": 5335 + }, + { + "epoch": 0.45, + "learning_rate": 1.1931939851511283e-05, + "loss": 0.5031, + "step": 5336 + }, + { + "epoch": 0.46, + "learning_rate": 1.1929230207842815e-05, + "loss": 0.488, + "step": 5337 + }, + { + "epoch": 0.46, + "learning_rate": 1.1926520417043195e-05, + "loss": 0.4849, + "step": 5338 + }, + { + "epoch": 0.46, + "learning_rate": 1.1923810479319089e-05, + "loss": 0.476, + "step": 5339 + }, + { + "epoch": 0.46, + "learning_rate": 1.1921100394877158e-05, + "loss": 0.471, + "step": 5340 + }, + { + "epoch": 0.46, + "learning_rate": 1.1918390163924098e-05, + "loss": 0.4909, + "step": 5341 + }, + { + "epoch": 0.46, + "learning_rate": 1.1915679786666592e-05, + "loss": 0.4677, + "step": 5342 + }, + { + "epoch": 0.46, + "learning_rate": 1.1912969263311345e-05, + "loss": 0.4979, + "step": 5343 + }, + { + "epoch": 0.46, + "learning_rate": 1.1910258594065079e-05, + "loss": 0.464, + "step": 5344 + }, + { + "epoch": 0.46, + "learning_rate": 1.1907547779134518e-05, + "loss": 0.486, + "step": 5345 + }, + { + "epoch": 0.46, + "learning_rate": 1.1904836818726397e-05, + "loss": 0.4877, + "step": 5346 + }, + { + "epoch": 0.46, + "learning_rate": 1.1902125713047467e-05, + "loss": 0.4732, + "step": 5347 + }, + { + "epoch": 0.46, + "learning_rate": 1.1899414462304496e-05, + "loss": 0.469, + "step": 5348 + }, + { + "epoch": 0.46, + "learning_rate": 1.1896703066704238e-05, + "loss": 0.4561, + "step": 5349 + }, + { + "epoch": 0.46, + "learning_rate": 1.1893991526453493e-05, + "loss": 0.4831, + "step": 5350 + }, + { + "epoch": 0.46, + "learning_rate": 1.1891279841759044e-05, + "loss": 0.4953, + "step": 5351 + }, + { + "epoch": 0.46, + "learning_rate": 1.18885680128277e-05, + "loss": 0.4627, + "step": 5352 + }, + { + "epoch": 0.46, + "learning_rate": 1.1885856039866275e-05, + "loss": 0.498, + "step": 5353 + }, + { + "epoch": 0.46, + "learning_rate": 1.1883143923081592e-05, + "loss": 0.4707, + "step": 5354 + }, + { + "epoch": 0.46, + "learning_rate": 1.1880431662680494e-05, + "loss": 0.4781, + "step": 5355 + }, + { + "epoch": 0.46, + "learning_rate": 1.1877719258869827e-05, + "loss": 0.4689, + "step": 5356 + }, + { + "epoch": 0.46, + "learning_rate": 1.1875006711856452e-05, + "loss": 0.4966, + "step": 5357 + }, + { + "epoch": 0.46, + "learning_rate": 1.1872294021847231e-05, + "loss": 0.4923, + "step": 5358 + }, + { + "epoch": 0.46, + "learning_rate": 1.1869581189049057e-05, + "loss": 0.4654, + "step": 5359 + }, + { + "epoch": 0.46, + "learning_rate": 1.1866868213668813e-05, + "loss": 0.4936, + "step": 5360 + }, + { + "epoch": 0.46, + "learning_rate": 1.1864155095913407e-05, + "loss": 0.502, + "step": 5361 + }, + { + "epoch": 0.46, + "learning_rate": 1.1861441835989754e-05, + "loss": 0.4798, + "step": 5362 + }, + { + "epoch": 0.46, + "learning_rate": 1.1858728434104769e-05, + "loss": 0.467, + "step": 5363 + }, + { + "epoch": 0.46, + "learning_rate": 1.1856014890465396e-05, + "loss": 0.4784, + "step": 5364 + }, + { + "epoch": 0.46, + "learning_rate": 1.1853301205278579e-05, + "loss": 0.4778, + "step": 5365 + }, + { + "epoch": 0.46, + "learning_rate": 1.1850587378751274e-05, + "loss": 0.4733, + "step": 5366 + }, + { + "epoch": 0.46, + "learning_rate": 1.184787341109045e-05, + "loss": 0.5015, + "step": 5367 + }, + { + "epoch": 0.46, + "learning_rate": 1.1845159302503086e-05, + "loss": 0.4649, + "step": 5368 + }, + { + "epoch": 0.46, + "learning_rate": 1.184244505319617e-05, + "loss": 0.4803, + "step": 5369 + }, + { + "epoch": 0.46, + "learning_rate": 1.18397306633767e-05, + "loss": 0.4946, + "step": 5370 + }, + { + "epoch": 0.46, + "learning_rate": 1.1837016133251695e-05, + "loss": 0.4693, + "step": 5371 + }, + { + "epoch": 0.46, + "learning_rate": 1.1834301463028166e-05, + "loss": 0.4811, + "step": 5372 + }, + { + "epoch": 0.46, + "learning_rate": 1.1831586652913147e-05, + "loss": 0.4797, + "step": 5373 + }, + { + "epoch": 0.46, + "learning_rate": 1.1828871703113686e-05, + "loss": 0.4794, + "step": 5374 + }, + { + "epoch": 0.46, + "learning_rate": 1.1826156613836835e-05, + "loss": 0.4615, + "step": 5375 + }, + { + "epoch": 0.46, + "learning_rate": 1.1823441385289656e-05, + "loss": 0.4812, + "step": 5376 + }, + { + "epoch": 0.46, + "learning_rate": 1.1820726017679222e-05, + "loss": 0.4821, + "step": 5377 + }, + { + "epoch": 0.46, + "learning_rate": 1.1818010511212624e-05, + "loss": 0.4888, + "step": 5378 + }, + { + "epoch": 0.46, + "learning_rate": 1.181529486609695e-05, + "loss": 0.4973, + "step": 5379 + }, + { + "epoch": 0.46, + "learning_rate": 1.1812579082539317e-05, + "loss": 0.468, + "step": 5380 + }, + { + "epoch": 0.46, + "learning_rate": 1.180986316074683e-05, + "loss": 0.4945, + "step": 5381 + }, + { + "epoch": 0.46, + "learning_rate": 1.1807147100926626e-05, + "loss": 0.4886, + "step": 5382 + }, + { + "epoch": 0.46, + "learning_rate": 1.1804430903285837e-05, + "loss": 0.4783, + "step": 5383 + }, + { + "epoch": 0.46, + "learning_rate": 1.1801714568031615e-05, + "loss": 0.4909, + "step": 5384 + }, + { + "epoch": 0.46, + "learning_rate": 1.1798998095371119e-05, + "loss": 0.473, + "step": 5385 + }, + { + "epoch": 0.46, + "learning_rate": 1.1796281485511519e-05, + "loss": 0.4936, + "step": 5386 + }, + { + "epoch": 0.46, + "learning_rate": 1.1793564738659988e-05, + "loss": 0.4731, + "step": 5387 + }, + { + "epoch": 0.46, + "learning_rate": 1.1790847855023727e-05, + "loss": 0.4825, + "step": 5388 + }, + { + "epoch": 0.46, + "learning_rate": 1.1788130834809932e-05, + "loss": 0.4743, + "step": 5389 + }, + { + "epoch": 0.46, + "learning_rate": 1.178541367822581e-05, + "loss": 0.4848, + "step": 5390 + }, + { + "epoch": 0.46, + "learning_rate": 1.1782696385478593e-05, + "loss": 0.4619, + "step": 5391 + }, + { + "epoch": 0.46, + "learning_rate": 1.1779978956775507e-05, + "loss": 0.4866, + "step": 5392 + }, + { + "epoch": 0.46, + "learning_rate": 1.1777261392323789e-05, + "loss": 0.4843, + "step": 5393 + }, + { + "epoch": 0.46, + "learning_rate": 1.17745436923307e-05, + "loss": 0.4741, + "step": 5394 + }, + { + "epoch": 0.46, + "learning_rate": 1.17718258570035e-05, + "loss": 0.4986, + "step": 5395 + }, + { + "epoch": 0.46, + "learning_rate": 1.1769107886549465e-05, + "loss": 0.4614, + "step": 5396 + }, + { + "epoch": 0.46, + "learning_rate": 1.1766389781175876e-05, + "loss": 0.4716, + "step": 5397 + }, + { + "epoch": 0.46, + "learning_rate": 1.1763671541090027e-05, + "loss": 0.4846, + "step": 5398 + }, + { + "epoch": 0.46, + "learning_rate": 1.1760953166499221e-05, + "loss": 0.4808, + "step": 5399 + }, + { + "epoch": 0.46, + "learning_rate": 1.1758234657610778e-05, + "loss": 0.4841, + "step": 5400 + }, + { + "epoch": 0.46, + "learning_rate": 1.1755516014632023e-05, + "loss": 0.5047, + "step": 5401 + }, + { + "epoch": 0.46, + "learning_rate": 1.1752797237770279e-05, + "loss": 0.4813, + "step": 5402 + }, + { + "epoch": 0.46, + "learning_rate": 1.1750078327232908e-05, + "loss": 0.4736, + "step": 5403 + }, + { + "epoch": 0.46, + "learning_rate": 1.1747359283227251e-05, + "loss": 0.4669, + "step": 5404 + }, + { + "epoch": 0.46, + "learning_rate": 1.1744640105960683e-05, + "loss": 0.4718, + "step": 5405 + }, + { + "epoch": 0.46, + "learning_rate": 1.1741920795640578e-05, + "loss": 0.4925, + "step": 5406 + }, + { + "epoch": 0.46, + "learning_rate": 1.1739201352474322e-05, + "loss": 0.4518, + "step": 5407 + }, + { + "epoch": 0.46, + "learning_rate": 1.1736481776669307e-05, + "loss": 0.4872, + "step": 5408 + }, + { + "epoch": 0.46, + "learning_rate": 1.173376206843294e-05, + "loss": 0.5035, + "step": 5409 + }, + { + "epoch": 0.46, + "learning_rate": 1.1731042227972645e-05, + "loss": 0.473, + "step": 5410 + }, + { + "epoch": 0.46, + "learning_rate": 1.1728322255495836e-05, + "loss": 0.4834, + "step": 5411 + }, + { + "epoch": 0.46, + "learning_rate": 1.1725602151209962e-05, + "loss": 0.4818, + "step": 5412 + }, + { + "epoch": 0.46, + "learning_rate": 1.1722881915322462e-05, + "loss": 0.5011, + "step": 5413 + }, + { + "epoch": 0.46, + "learning_rate": 1.1720161548040793e-05, + "loss": 0.4643, + "step": 5414 + }, + { + "epoch": 0.46, + "learning_rate": 1.1717441049572427e-05, + "loss": 0.4882, + "step": 5415 + }, + { + "epoch": 0.46, + "learning_rate": 1.1714720420124833e-05, + "loss": 0.4793, + "step": 5416 + }, + { + "epoch": 0.46, + "learning_rate": 1.17119996599055e-05, + "loss": 0.4704, + "step": 5417 + }, + { + "epoch": 0.46, + "learning_rate": 1.1709278769121928e-05, + "loss": 0.4833, + "step": 5418 + }, + { + "epoch": 0.46, + "learning_rate": 1.1706557747981622e-05, + "loss": 0.4757, + "step": 5419 + }, + { + "epoch": 0.46, + "learning_rate": 1.1703836596692094e-05, + "loss": 0.4915, + "step": 5420 + }, + { + "epoch": 0.46, + "learning_rate": 1.1701115315460875e-05, + "loss": 0.4924, + "step": 5421 + }, + { + "epoch": 0.46, + "learning_rate": 1.16983939044955e-05, + "loss": 0.4657, + "step": 5422 + }, + { + "epoch": 0.46, + "learning_rate": 1.1695672364003516e-05, + "loss": 0.4985, + "step": 5423 + }, + { + "epoch": 0.46, + "learning_rate": 1.169295069419248e-05, + "loss": 0.4988, + "step": 5424 + }, + { + "epoch": 0.46, + "learning_rate": 1.1690228895269953e-05, + "loss": 0.5054, + "step": 5425 + }, + { + "epoch": 0.46, + "learning_rate": 1.1687506967443516e-05, + "loss": 0.4675, + "step": 5426 + }, + { + "epoch": 0.46, + "learning_rate": 1.168478491092075e-05, + "loss": 0.471, + "step": 5427 + }, + { + "epoch": 0.46, + "learning_rate": 1.1682062725909257e-05, + "loss": 0.5117, + "step": 5428 + }, + { + "epoch": 0.46, + "learning_rate": 1.1679340412616633e-05, + "loss": 0.4814, + "step": 5429 + }, + { + "epoch": 0.46, + "learning_rate": 1.1676617971250504e-05, + "loss": 0.4549, + "step": 5430 + }, + { + "epoch": 0.46, + "learning_rate": 1.1673895402018484e-05, + "loss": 0.4818, + "step": 5431 + }, + { + "epoch": 0.46, + "learning_rate": 1.1671172705128216e-05, + "loss": 0.4868, + "step": 5432 + }, + { + "epoch": 0.46, + "learning_rate": 1.1668449880787338e-05, + "loss": 0.4668, + "step": 5433 + }, + { + "epoch": 0.46, + "learning_rate": 1.1665726929203509e-05, + "loss": 0.4625, + "step": 5434 + }, + { + "epoch": 0.46, + "learning_rate": 1.1663003850584387e-05, + "loss": 0.4778, + "step": 5435 + }, + { + "epoch": 0.46, + "learning_rate": 1.166028064513765e-05, + "loss": 0.4708, + "step": 5436 + }, + { + "epoch": 0.46, + "learning_rate": 1.165755731307098e-05, + "loss": 0.4788, + "step": 5437 + }, + { + "epoch": 0.46, + "learning_rate": 1.1654833854592067e-05, + "loss": 0.484, + "step": 5438 + }, + { + "epoch": 0.46, + "learning_rate": 1.1652110269908618e-05, + "loss": 0.4788, + "step": 5439 + }, + { + "epoch": 0.46, + "learning_rate": 1.1649386559228342e-05, + "loss": 0.4546, + "step": 5440 + }, + { + "epoch": 0.46, + "learning_rate": 1.1646662722758961e-05, + "loss": 0.4895, + "step": 5441 + }, + { + "epoch": 0.46, + "learning_rate": 1.1643938760708207e-05, + "loss": 0.4755, + "step": 5442 + }, + { + "epoch": 0.46, + "learning_rate": 1.1641214673283818e-05, + "loss": 0.4876, + "step": 5443 + }, + { + "epoch": 0.46, + "learning_rate": 1.1638490460693546e-05, + "loss": 0.4713, + "step": 5444 + }, + { + "epoch": 0.46, + "learning_rate": 1.1635766123145151e-05, + "loss": 0.4917, + "step": 5445 + }, + { + "epoch": 0.46, + "learning_rate": 1.1633041660846405e-05, + "loss": 0.4667, + "step": 5446 + }, + { + "epoch": 0.46, + "learning_rate": 1.1630317074005082e-05, + "loss": 0.4812, + "step": 5447 + }, + { + "epoch": 0.46, + "learning_rate": 1.1627592362828972e-05, + "loss": 0.4897, + "step": 5448 + }, + { + "epoch": 0.46, + "learning_rate": 1.1624867527525876e-05, + "loss": 0.448, + "step": 5449 + }, + { + "epoch": 0.46, + "learning_rate": 1.1622142568303596e-05, + "loss": 0.5137, + "step": 5450 + }, + { + "epoch": 0.46, + "learning_rate": 1.1619417485369954e-05, + "loss": 0.4571, + "step": 5451 + }, + { + "epoch": 0.46, + "learning_rate": 1.1616692278932772e-05, + "loss": 0.4825, + "step": 5452 + }, + { + "epoch": 0.46, + "learning_rate": 1.1613966949199886e-05, + "loss": 0.4535, + "step": 5453 + }, + { + "epoch": 0.47, + "learning_rate": 1.1611241496379144e-05, + "loss": 0.4777, + "step": 5454 + }, + { + "epoch": 0.47, + "learning_rate": 1.1608515920678398e-05, + "loss": 0.4902, + "step": 5455 + }, + { + "epoch": 0.47, + "learning_rate": 1.1605790222305516e-05, + "loss": 0.4963, + "step": 5456 + }, + { + "epoch": 0.47, + "learning_rate": 1.1603064401468364e-05, + "loss": 0.5008, + "step": 5457 + }, + { + "epoch": 0.47, + "learning_rate": 1.1600338458374829e-05, + "loss": 0.5062, + "step": 5458 + }, + { + "epoch": 0.47, + "learning_rate": 1.1597612393232803e-05, + "loss": 0.508, + "step": 5459 + }, + { + "epoch": 0.47, + "learning_rate": 1.1594886206250186e-05, + "loss": 0.4816, + "step": 5460 + }, + { + "epoch": 0.47, + "learning_rate": 1.1592159897634887e-05, + "loss": 0.4905, + "step": 5461 + }, + { + "epoch": 0.47, + "learning_rate": 1.1589433467594826e-05, + "loss": 0.4678, + "step": 5462 + }, + { + "epoch": 0.47, + "learning_rate": 1.1586706916337937e-05, + "loss": 0.4969, + "step": 5463 + }, + { + "epoch": 0.47, + "learning_rate": 1.158398024407215e-05, + "loss": 0.4937, + "step": 5464 + }, + { + "epoch": 0.47, + "learning_rate": 1.158125345100542e-05, + "loss": 0.487, + "step": 5465 + }, + { + "epoch": 0.47, + "learning_rate": 1.1578526537345698e-05, + "loss": 0.4695, + "step": 5466 + }, + { + "epoch": 0.47, + "learning_rate": 1.1575799503300952e-05, + "loss": 0.4796, + "step": 5467 + }, + { + "epoch": 0.47, + "learning_rate": 1.157307234907916e-05, + "loss": 0.4897, + "step": 5468 + }, + { + "epoch": 0.47, + "learning_rate": 1.1570345074888304e-05, + "loss": 0.4688, + "step": 5469 + }, + { + "epoch": 0.47, + "learning_rate": 1.1567617680936372e-05, + "loss": 0.4739, + "step": 5470 + }, + { + "epoch": 0.47, + "learning_rate": 1.1564890167431372e-05, + "loss": 0.475, + "step": 5471 + }, + { + "epoch": 0.47, + "learning_rate": 1.1562162534581318e-05, + "loss": 0.4597, + "step": 5472 + }, + { + "epoch": 0.47, + "learning_rate": 1.1559434782594224e-05, + "loss": 0.4983, + "step": 5473 + }, + { + "epoch": 0.47, + "learning_rate": 1.1556706911678124e-05, + "loss": 0.4844, + "step": 5474 + }, + { + "epoch": 0.47, + "learning_rate": 1.1553978922041055e-05, + "loss": 0.4916, + "step": 5475 + }, + { + "epoch": 0.47, + "learning_rate": 1.1551250813891066e-05, + "loss": 0.4642, + "step": 5476 + }, + { + "epoch": 0.47, + "learning_rate": 1.1548522587436216e-05, + "loss": 0.4888, + "step": 5477 + }, + { + "epoch": 0.47, + "learning_rate": 1.1545794242884567e-05, + "loss": 0.4671, + "step": 5478 + }, + { + "epoch": 0.47, + "learning_rate": 1.1543065780444196e-05, + "loss": 0.4828, + "step": 5479 + }, + { + "epoch": 0.47, + "learning_rate": 1.1540337200323187e-05, + "loss": 0.4696, + "step": 5480 + }, + { + "epoch": 0.47, + "learning_rate": 1.153760850272963e-05, + "loss": 0.498, + "step": 5481 + }, + { + "epoch": 0.47, + "learning_rate": 1.1534879687871629e-05, + "loss": 0.4759, + "step": 5482 + }, + { + "epoch": 0.47, + "learning_rate": 1.15321507559573e-05, + "loss": 0.4896, + "step": 5483 + }, + { + "epoch": 0.47, + "learning_rate": 1.1529421707194753e-05, + "loss": 0.481, + "step": 5484 + }, + { + "epoch": 0.47, + "learning_rate": 1.1526692541792122e-05, + "loss": 0.4757, + "step": 5485 + }, + { + "epoch": 0.47, + "learning_rate": 1.1523963259957546e-05, + "loss": 0.4954, + "step": 5486 + }, + { + "epoch": 0.47, + "learning_rate": 1.1521233861899168e-05, + "loss": 0.4989, + "step": 5487 + }, + { + "epoch": 0.47, + "learning_rate": 1.1518504347825146e-05, + "loss": 0.4551, + "step": 5488 + }, + { + "epoch": 0.47, + "learning_rate": 1.1515774717943642e-05, + "loss": 0.479, + "step": 5489 + }, + { + "epoch": 0.47, + "learning_rate": 1.151304497246283e-05, + "loss": 0.4766, + "step": 5490 + }, + { + "epoch": 0.47, + "learning_rate": 1.151031511159089e-05, + "loss": 0.5058, + "step": 5491 + }, + { + "epoch": 0.47, + "learning_rate": 1.1507585135536017e-05, + "loss": 0.4571, + "step": 5492 + }, + { + "epoch": 0.47, + "learning_rate": 1.1504855044506407e-05, + "loss": 0.4647, + "step": 5493 + }, + { + "epoch": 0.47, + "learning_rate": 1.1502124838710268e-05, + "loss": 0.4953, + "step": 5494 + }, + { + "epoch": 0.47, + "learning_rate": 1.1499394518355818e-05, + "loss": 0.4736, + "step": 5495 + }, + { + "epoch": 0.47, + "learning_rate": 1.1496664083651281e-05, + "loss": 0.4839, + "step": 5496 + }, + { + "epoch": 0.47, + "learning_rate": 1.1493933534804892e-05, + "loss": 0.478, + "step": 5497 + }, + { + "epoch": 0.47, + "learning_rate": 1.1491202872024896e-05, + "loss": 0.4718, + "step": 5498 + }, + { + "epoch": 0.47, + "learning_rate": 1.1488472095519545e-05, + "loss": 0.4842, + "step": 5499 + }, + { + "epoch": 0.47, + "learning_rate": 1.1485741205497094e-05, + "loss": 0.4874, + "step": 5500 + }, + { + "epoch": 0.47, + "learning_rate": 1.1483010202165821e-05, + "loss": 0.4706, + "step": 5501 + }, + { + "epoch": 0.47, + "learning_rate": 1.1480279085733997e-05, + "loss": 0.4773, + "step": 5502 + }, + { + "epoch": 0.47, + "learning_rate": 1.1477547856409905e-05, + "loss": 0.4887, + "step": 5503 + }, + { + "epoch": 0.47, + "learning_rate": 1.1474816514401851e-05, + "loss": 0.4735, + "step": 5504 + }, + { + "epoch": 0.47, + "learning_rate": 1.147208505991813e-05, + "loss": 0.4806, + "step": 5505 + }, + { + "epoch": 0.47, + "learning_rate": 1.1469353493167056e-05, + "loss": 0.4702, + "step": 5506 + }, + { + "epoch": 0.47, + "learning_rate": 1.1466621814356951e-05, + "loss": 0.4772, + "step": 5507 + }, + { + "epoch": 0.47, + "learning_rate": 1.1463890023696145e-05, + "loss": 0.4817, + "step": 5508 + }, + { + "epoch": 0.47, + "learning_rate": 1.1461158121392972e-05, + "loss": 0.4944, + "step": 5509 + }, + { + "epoch": 0.47, + "learning_rate": 1.145842610765578e-05, + "loss": 0.4888, + "step": 5510 + }, + { + "epoch": 0.47, + "learning_rate": 1.1455693982692926e-05, + "loss": 0.4935, + "step": 5511 + }, + { + "epoch": 0.47, + "learning_rate": 1.1452961746712769e-05, + "loss": 0.4941, + "step": 5512 + }, + { + "epoch": 0.47, + "learning_rate": 1.1450229399923687e-05, + "loss": 0.4742, + "step": 5513 + }, + { + "epoch": 0.47, + "learning_rate": 1.1447496942534056e-05, + "loss": 0.4823, + "step": 5514 + }, + { + "epoch": 0.47, + "learning_rate": 1.1444764374752262e-05, + "loss": 0.4801, + "step": 5515 + }, + { + "epoch": 0.47, + "learning_rate": 1.1442031696786707e-05, + "loss": 0.4736, + "step": 5516 + }, + { + "epoch": 0.47, + "learning_rate": 1.1439298908845795e-05, + "loss": 0.4635, + "step": 5517 + }, + { + "epoch": 0.47, + "learning_rate": 1.143656601113794e-05, + "loss": 0.5015, + "step": 5518 + }, + { + "epoch": 0.47, + "learning_rate": 1.143383300387156e-05, + "loss": 0.4908, + "step": 5519 + }, + { + "epoch": 0.47, + "learning_rate": 1.143109988725509e-05, + "loss": 0.4615, + "step": 5520 + }, + { + "epoch": 0.47, + "learning_rate": 1.1428366661496971e-05, + "loss": 0.4867, + "step": 5521 + }, + { + "epoch": 0.47, + "learning_rate": 1.1425633326805645e-05, + "loss": 0.5, + "step": 5522 + }, + { + "epoch": 0.47, + "learning_rate": 1.1422899883389569e-05, + "loss": 0.5025, + "step": 5523 + }, + { + "epoch": 0.47, + "learning_rate": 1.1420166331457208e-05, + "loss": 0.4537, + "step": 5524 + }, + { + "epoch": 0.47, + "learning_rate": 1.1417432671217037e-05, + "loss": 0.49, + "step": 5525 + }, + { + "epoch": 0.47, + "learning_rate": 1.1414698902877528e-05, + "loss": 0.4957, + "step": 5526 + }, + { + "epoch": 0.47, + "learning_rate": 1.1411965026647177e-05, + "loss": 0.457, + "step": 5527 + }, + { + "epoch": 0.47, + "learning_rate": 1.1409231042734476e-05, + "loss": 0.4848, + "step": 5528 + }, + { + "epoch": 0.47, + "learning_rate": 1.1406496951347934e-05, + "loss": 0.4853, + "step": 5529 + }, + { + "epoch": 0.47, + "learning_rate": 1.140376275269606e-05, + "loss": 0.4578, + "step": 5530 + }, + { + "epoch": 0.47, + "learning_rate": 1.1401028446987384e-05, + "loss": 0.4907, + "step": 5531 + }, + { + "epoch": 0.47, + "learning_rate": 1.1398294034430423e-05, + "loss": 0.4982, + "step": 5532 + }, + { + "epoch": 0.47, + "learning_rate": 1.1395559515233726e-05, + "loss": 0.4857, + "step": 5533 + }, + { + "epoch": 0.47, + "learning_rate": 1.1392824889605834e-05, + "loss": 0.4717, + "step": 5534 + }, + { + "epoch": 0.47, + "learning_rate": 1.1390090157755298e-05, + "loss": 0.4959, + "step": 5535 + }, + { + "epoch": 0.47, + "learning_rate": 1.1387355319890685e-05, + "loss": 0.4895, + "step": 5536 + }, + { + "epoch": 0.47, + "learning_rate": 1.138462037622056e-05, + "loss": 0.4563, + "step": 5537 + }, + { + "epoch": 0.47, + "learning_rate": 1.1381885326953507e-05, + "loss": 0.4824, + "step": 5538 + }, + { + "epoch": 0.47, + "learning_rate": 1.137915017229811e-05, + "loss": 0.4826, + "step": 5539 + }, + { + "epoch": 0.47, + "learning_rate": 1.1376414912462964e-05, + "loss": 0.4932, + "step": 5540 + }, + { + "epoch": 0.47, + "learning_rate": 1.1373679547656669e-05, + "loss": 0.4733, + "step": 5541 + }, + { + "epoch": 0.47, + "learning_rate": 1.1370944078087837e-05, + "loss": 0.4793, + "step": 5542 + }, + { + "epoch": 0.47, + "learning_rate": 1.1368208503965087e-05, + "loss": 0.4749, + "step": 5543 + }, + { + "epoch": 0.47, + "learning_rate": 1.1365472825497041e-05, + "loss": 0.4744, + "step": 5544 + }, + { + "epoch": 0.47, + "learning_rate": 1.1362737042892342e-05, + "loss": 0.4788, + "step": 5545 + }, + { + "epoch": 0.47, + "learning_rate": 1.1360001156359623e-05, + "loss": 0.4729, + "step": 5546 + }, + { + "epoch": 0.47, + "learning_rate": 1.1357265166107538e-05, + "loss": 0.4772, + "step": 5547 + }, + { + "epoch": 0.47, + "learning_rate": 1.1354529072344749e-05, + "loss": 0.4866, + "step": 5548 + }, + { + "epoch": 0.47, + "learning_rate": 1.1351792875279914e-05, + "loss": 0.489, + "step": 5549 + }, + { + "epoch": 0.47, + "learning_rate": 1.1349056575121713e-05, + "loss": 0.4761, + "step": 5550 + }, + { + "epoch": 0.47, + "learning_rate": 1.1346320172078822e-05, + "loss": 0.4759, + "step": 5551 + }, + { + "epoch": 0.47, + "learning_rate": 1.1343583666359938e-05, + "loss": 0.4973, + "step": 5552 + }, + { + "epoch": 0.47, + "learning_rate": 1.1340847058173752e-05, + "loss": 0.4775, + "step": 5553 + }, + { + "epoch": 0.47, + "learning_rate": 1.1338110347728973e-05, + "loss": 0.491, + "step": 5554 + }, + { + "epoch": 0.47, + "learning_rate": 1.1335373535234312e-05, + "loss": 0.4867, + "step": 5555 + }, + { + "epoch": 0.47, + "learning_rate": 1.1332636620898487e-05, + "loss": 0.4774, + "step": 5556 + }, + { + "epoch": 0.47, + "learning_rate": 1.1329899604930235e-05, + "loss": 0.477, + "step": 5557 + }, + { + "epoch": 0.47, + "learning_rate": 1.1327162487538283e-05, + "loss": 0.4967, + "step": 5558 + }, + { + "epoch": 0.47, + "learning_rate": 1.132442526893138e-05, + "loss": 0.4683, + "step": 5559 + }, + { + "epoch": 0.47, + "learning_rate": 1.1321687949318276e-05, + "loss": 0.4716, + "step": 5560 + }, + { + "epoch": 0.47, + "learning_rate": 1.1318950528907734e-05, + "loss": 0.4754, + "step": 5561 + }, + { + "epoch": 0.47, + "learning_rate": 1.1316213007908514e-05, + "loss": 0.4879, + "step": 5562 + }, + { + "epoch": 0.47, + "learning_rate": 1.13134753865294e-05, + "loss": 0.4488, + "step": 5563 + }, + { + "epoch": 0.47, + "learning_rate": 1.1310737664979168e-05, + "loss": 0.4789, + "step": 5564 + }, + { + "epoch": 0.47, + "learning_rate": 1.1307999843466605e-05, + "loss": 0.4988, + "step": 5565 + }, + { + "epoch": 0.47, + "learning_rate": 1.130526192220052e-05, + "loss": 0.4812, + "step": 5566 + }, + { + "epoch": 0.47, + "learning_rate": 1.1302523901389706e-05, + "loss": 0.4726, + "step": 5567 + }, + { + "epoch": 0.47, + "learning_rate": 1.1299785781242982e-05, + "loss": 0.4716, + "step": 5568 + }, + { + "epoch": 0.47, + "learning_rate": 1.129704756196917e-05, + "loss": 0.4723, + "step": 5569 + }, + { + "epoch": 0.47, + "learning_rate": 1.1294309243777094e-05, + "loss": 0.4644, + "step": 5570 + }, + { + "epoch": 0.48, + "learning_rate": 1.1291570826875593e-05, + "loss": 0.4906, + "step": 5571 + }, + { + "epoch": 0.48, + "learning_rate": 1.1288832311473507e-05, + "loss": 0.4864, + "step": 5572 + }, + { + "epoch": 0.48, + "learning_rate": 1.1286093697779692e-05, + "loss": 0.4807, + "step": 5573 + }, + { + "epoch": 0.48, + "learning_rate": 1.1283354986002997e-05, + "loss": 0.4735, + "step": 5574 + }, + { + "epoch": 0.48, + "learning_rate": 1.1280616176352299e-05, + "loss": 0.472, + "step": 5575 + }, + { + "epoch": 0.48, + "learning_rate": 1.1277877269036461e-05, + "loss": 0.478, + "step": 5576 + }, + { + "epoch": 0.48, + "learning_rate": 1.1275138264264366e-05, + "loss": 0.4696, + "step": 5577 + }, + { + "epoch": 0.48, + "learning_rate": 1.1272399162244907e-05, + "loss": 0.4794, + "step": 5578 + }, + { + "epoch": 0.48, + "learning_rate": 1.1269659963186976e-05, + "loss": 0.4623, + "step": 5579 + }, + { + "epoch": 0.48, + "learning_rate": 1.1266920667299473e-05, + "loss": 0.4715, + "step": 5580 + }, + { + "epoch": 0.48, + "learning_rate": 1.1264181274791311e-05, + "loss": 0.4637, + "step": 5581 + }, + { + "epoch": 0.48, + "learning_rate": 1.126144178587141e-05, + "loss": 0.481, + "step": 5582 + }, + { + "epoch": 0.48, + "learning_rate": 1.1258702200748685e-05, + "loss": 0.4759, + "step": 5583 + }, + { + "epoch": 0.48, + "learning_rate": 1.1255962519632082e-05, + "loss": 0.4553, + "step": 5584 + }, + { + "epoch": 0.48, + "learning_rate": 1.1253222742730531e-05, + "loss": 0.4819, + "step": 5585 + }, + { + "epoch": 0.48, + "learning_rate": 1.1250482870252984e-05, + "loss": 0.4721, + "step": 5586 + }, + { + "epoch": 0.48, + "learning_rate": 1.1247742902408391e-05, + "loss": 0.4786, + "step": 5587 + }, + { + "epoch": 0.48, + "learning_rate": 1.1245002839405714e-05, + "loss": 0.4762, + "step": 5588 + }, + { + "epoch": 0.48, + "learning_rate": 1.1242262681453924e-05, + "loss": 0.4697, + "step": 5589 + }, + { + "epoch": 0.48, + "learning_rate": 1.1239522428761996e-05, + "loss": 0.4809, + "step": 5590 + }, + { + "epoch": 0.48, + "learning_rate": 1.1236782081538915e-05, + "loss": 0.476, + "step": 5591 + }, + { + "epoch": 0.48, + "learning_rate": 1.1234041639993663e-05, + "loss": 0.4662, + "step": 5592 + }, + { + "epoch": 0.48, + "learning_rate": 1.1231301104335248e-05, + "loss": 0.474, + "step": 5593 + }, + { + "epoch": 0.48, + "learning_rate": 1.122856047477267e-05, + "loss": 0.4922, + "step": 5594 + }, + { + "epoch": 0.48, + "learning_rate": 1.122581975151494e-05, + "loss": 0.4724, + "step": 5595 + }, + { + "epoch": 0.48, + "learning_rate": 1.1223078934771079e-05, + "loss": 0.495, + "step": 5596 + }, + { + "epoch": 0.48, + "learning_rate": 1.122033802475011e-05, + "loss": 0.5025, + "step": 5597 + }, + { + "epoch": 0.48, + "learning_rate": 1.1217597021661071e-05, + "loss": 0.4784, + "step": 5598 + }, + { + "epoch": 0.48, + "learning_rate": 1.1214855925712998e-05, + "loss": 0.4935, + "step": 5599 + }, + { + "epoch": 0.48, + "learning_rate": 1.1212114737114941e-05, + "loss": 0.4979, + "step": 5600 + }, + { + "epoch": 0.48, + "learning_rate": 1.1209373456075952e-05, + "loss": 0.478, + "step": 5601 + }, + { + "epoch": 0.48, + "learning_rate": 1.1206632082805099e-05, + "loss": 0.4863, + "step": 5602 + }, + { + "epoch": 0.48, + "learning_rate": 1.120389061751144e-05, + "loss": 0.4843, + "step": 5603 + }, + { + "epoch": 0.48, + "learning_rate": 1.120114906040406e-05, + "loss": 0.4644, + "step": 5604 + }, + { + "epoch": 0.48, + "learning_rate": 1.1198407411692041e-05, + "loss": 0.4508, + "step": 5605 + }, + { + "epoch": 0.48, + "learning_rate": 1.1195665671584463e-05, + "loss": 0.4908, + "step": 5606 + }, + { + "epoch": 0.48, + "learning_rate": 1.1192923840290433e-05, + "loss": 0.4698, + "step": 5607 + }, + { + "epoch": 0.48, + "learning_rate": 1.119018191801905e-05, + "loss": 0.4807, + "step": 5608 + }, + { + "epoch": 0.48, + "learning_rate": 1.1187439904979422e-05, + "loss": 0.4769, + "step": 5609 + }, + { + "epoch": 0.48, + "learning_rate": 1.1184697801380673e-05, + "loss": 0.4794, + "step": 5610 + }, + { + "epoch": 0.48, + "learning_rate": 1.1181955607431925e-05, + "loss": 0.4794, + "step": 5611 + }, + { + "epoch": 0.48, + "learning_rate": 1.1179213323342304e-05, + "loss": 0.4687, + "step": 5612 + }, + { + "epoch": 0.48, + "learning_rate": 1.1176470949320954e-05, + "loss": 0.4855, + "step": 5613 + }, + { + "epoch": 0.48, + "learning_rate": 1.117372848557702e-05, + "loss": 0.4826, + "step": 5614 + }, + { + "epoch": 0.48, + "learning_rate": 1.1170985932319647e-05, + "loss": 0.4861, + "step": 5615 + }, + { + "epoch": 0.48, + "learning_rate": 1.1168243289758001e-05, + "loss": 0.4895, + "step": 5616 + }, + { + "epoch": 0.48, + "learning_rate": 1.116550055810124e-05, + "loss": 0.4692, + "step": 5617 + }, + { + "epoch": 0.48, + "learning_rate": 1.1162757737558545e-05, + "loss": 0.4783, + "step": 5618 + }, + { + "epoch": 0.48, + "learning_rate": 1.1160014828339093e-05, + "loss": 0.4747, + "step": 5619 + }, + { + "epoch": 0.48, + "learning_rate": 1.1157271830652063e-05, + "loss": 0.4651, + "step": 5620 + }, + { + "epoch": 0.48, + "learning_rate": 1.1154528744706652e-05, + "loss": 0.4805, + "step": 5621 + }, + { + "epoch": 0.48, + "learning_rate": 1.115178557071206e-05, + "loss": 0.4824, + "step": 5622 + }, + { + "epoch": 0.48, + "learning_rate": 1.114904230887749e-05, + "loss": 0.4809, + "step": 5623 + }, + { + "epoch": 0.48, + "learning_rate": 1.1146298959412159e-05, + "loss": 0.4863, + "step": 5624 + }, + { + "epoch": 0.48, + "learning_rate": 1.1143555522525282e-05, + "loss": 0.4881, + "step": 5625 + }, + { + "epoch": 0.48, + "learning_rate": 1.1140811998426089e-05, + "loss": 0.4672, + "step": 5626 + }, + { + "epoch": 0.48, + "learning_rate": 1.1138068387323806e-05, + "loss": 0.4926, + "step": 5627 + }, + { + "epoch": 0.48, + "learning_rate": 1.113532468942768e-05, + "loss": 0.4646, + "step": 5628 + }, + { + "epoch": 0.48, + "learning_rate": 1.1132580904946952e-05, + "loss": 0.4726, + "step": 5629 + }, + { + "epoch": 0.48, + "learning_rate": 1.1129837034090876e-05, + "loss": 0.4764, + "step": 5630 + }, + { + "epoch": 0.48, + "learning_rate": 1.1127093077068712e-05, + "loss": 0.4672, + "step": 5631 + }, + { + "epoch": 0.48, + "learning_rate": 1.1124349034089724e-05, + "loss": 0.4821, + "step": 5632 + }, + { + "epoch": 0.48, + "learning_rate": 1.1121604905363181e-05, + "loss": 0.4693, + "step": 5633 + }, + { + "epoch": 0.48, + "learning_rate": 1.111886069109837e-05, + "loss": 0.4833, + "step": 5634 + }, + { + "epoch": 0.48, + "learning_rate": 1.1116116391504572e-05, + "loss": 0.4731, + "step": 5635 + }, + { + "epoch": 0.48, + "learning_rate": 1.1113372006791074e-05, + "loss": 0.4844, + "step": 5636 + }, + { + "epoch": 0.48, + "learning_rate": 1.1110627537167183e-05, + "loss": 0.4683, + "step": 5637 + }, + { + "epoch": 0.48, + "learning_rate": 1.1107882982842195e-05, + "loss": 0.4909, + "step": 5638 + }, + { + "epoch": 0.48, + "learning_rate": 1.1105138344025429e-05, + "loss": 0.4678, + "step": 5639 + }, + { + "epoch": 0.48, + "learning_rate": 1.1102393620926196e-05, + "loss": 0.4978, + "step": 5640 + }, + { + "epoch": 0.48, + "learning_rate": 1.1099648813753827e-05, + "loss": 0.4747, + "step": 5641 + }, + { + "epoch": 0.48, + "learning_rate": 1.1096903922717645e-05, + "loss": 0.4866, + "step": 5642 + }, + { + "epoch": 0.48, + "learning_rate": 1.1094158948026993e-05, + "loss": 0.4753, + "step": 5643 + }, + { + "epoch": 0.48, + "learning_rate": 1.1091413889891211e-05, + "loss": 0.4812, + "step": 5644 + }, + { + "epoch": 0.48, + "learning_rate": 1.1088668748519646e-05, + "loss": 0.4777, + "step": 5645 + }, + { + "epoch": 0.48, + "learning_rate": 1.1085923524121663e-05, + "loss": 0.4732, + "step": 5646 + }, + { + "epoch": 0.48, + "learning_rate": 1.1083178216906614e-05, + "loss": 0.4791, + "step": 5647 + }, + { + "epoch": 0.48, + "learning_rate": 1.1080432827083874e-05, + "loss": 0.4836, + "step": 5648 + }, + { + "epoch": 0.48, + "learning_rate": 1.1077687354862814e-05, + "loss": 0.4839, + "step": 5649 + }, + { + "epoch": 0.48, + "learning_rate": 1.1074941800452818e-05, + "loss": 0.4692, + "step": 5650 + }, + { + "epoch": 0.48, + "learning_rate": 1.1072196164063273e-05, + "loss": 0.5022, + "step": 5651 + }, + { + "epoch": 0.48, + "learning_rate": 1.1069450445903573e-05, + "loss": 0.4921, + "step": 5652 + }, + { + "epoch": 0.48, + "learning_rate": 1.1066704646183117e-05, + "loss": 0.4737, + "step": 5653 + }, + { + "epoch": 0.48, + "learning_rate": 1.1063958765111308e-05, + "loss": 0.4767, + "step": 5654 + }, + { + "epoch": 0.48, + "learning_rate": 1.1061212802897567e-05, + "loss": 0.4734, + "step": 5655 + }, + { + "epoch": 0.48, + "learning_rate": 1.1058466759751302e-05, + "loss": 0.4701, + "step": 5656 + }, + { + "epoch": 0.48, + "learning_rate": 1.1055720635881948e-05, + "loss": 0.4647, + "step": 5657 + }, + { + "epoch": 0.48, + "learning_rate": 1.1052974431498929e-05, + "loss": 0.4783, + "step": 5658 + }, + { + "epoch": 0.48, + "learning_rate": 1.1050228146811684e-05, + "loss": 0.4979, + "step": 5659 + }, + { + "epoch": 0.48, + "learning_rate": 1.1047481782029654e-05, + "loss": 0.4653, + "step": 5660 + }, + { + "epoch": 0.48, + "learning_rate": 1.1044735337362291e-05, + "loss": 0.4897, + "step": 5661 + }, + { + "epoch": 0.48, + "learning_rate": 1.1041988813019051e-05, + "loss": 0.4723, + "step": 5662 + }, + { + "epoch": 0.48, + "learning_rate": 1.103924220920939e-05, + "loss": 0.4611, + "step": 5663 + }, + { + "epoch": 0.48, + "learning_rate": 1.1036495526142784e-05, + "loss": 0.4732, + "step": 5664 + }, + { + "epoch": 0.48, + "learning_rate": 1.10337487640287e-05, + "loss": 0.477, + "step": 5665 + }, + { + "epoch": 0.48, + "learning_rate": 1.1031001923076619e-05, + "loss": 0.4958, + "step": 5666 + }, + { + "epoch": 0.48, + "learning_rate": 1.102825500349603e-05, + "loss": 0.4698, + "step": 5667 + }, + { + "epoch": 0.48, + "learning_rate": 1.1025508005496417e-05, + "loss": 0.4903, + "step": 5668 + }, + { + "epoch": 0.48, + "learning_rate": 1.1022760929287286e-05, + "loss": 0.4853, + "step": 5669 + }, + { + "epoch": 0.48, + "learning_rate": 1.1020013775078134e-05, + "loss": 0.4838, + "step": 5670 + }, + { + "epoch": 0.48, + "learning_rate": 1.1017266543078475e-05, + "loss": 0.4765, + "step": 5671 + }, + { + "epoch": 0.48, + "learning_rate": 1.101451923349782e-05, + "loss": 0.489, + "step": 5672 + }, + { + "epoch": 0.48, + "learning_rate": 1.1011771846545696e-05, + "loss": 0.4735, + "step": 5673 + }, + { + "epoch": 0.48, + "learning_rate": 1.1009024382431623e-05, + "loss": 0.4739, + "step": 5674 + }, + { + "epoch": 0.48, + "learning_rate": 1.1006276841365142e-05, + "loss": 0.4831, + "step": 5675 + }, + { + "epoch": 0.48, + "learning_rate": 1.1003529223555786e-05, + "loss": 0.4899, + "step": 5676 + }, + { + "epoch": 0.48, + "learning_rate": 1.1000781529213103e-05, + "loss": 0.4948, + "step": 5677 + }, + { + "epoch": 0.48, + "learning_rate": 1.099803375854664e-05, + "loss": 0.4833, + "step": 5678 + }, + { + "epoch": 0.48, + "learning_rate": 1.0995285911765958e-05, + "loss": 0.4806, + "step": 5679 + }, + { + "epoch": 0.48, + "learning_rate": 1.0992537989080618e-05, + "loss": 0.4624, + "step": 5680 + }, + { + "epoch": 0.48, + "learning_rate": 1.0989789990700187e-05, + "loss": 0.4773, + "step": 5681 + }, + { + "epoch": 0.48, + "learning_rate": 1.0987041916834236e-05, + "loss": 0.497, + "step": 5682 + }, + { + "epoch": 0.48, + "learning_rate": 1.0984293767692349e-05, + "loss": 0.4747, + "step": 5683 + }, + { + "epoch": 0.48, + "learning_rate": 1.0981545543484111e-05, + "loss": 0.457, + "step": 5684 + }, + { + "epoch": 0.48, + "learning_rate": 1.0978797244419113e-05, + "loss": 0.4927, + "step": 5685 + }, + { + "epoch": 0.48, + "learning_rate": 1.097604887070695e-05, + "loss": 0.4805, + "step": 5686 + }, + { + "epoch": 0.48, + "learning_rate": 1.0973300422557223e-05, + "loss": 0.4919, + "step": 5687 + }, + { + "epoch": 0.48, + "learning_rate": 1.0970551900179544e-05, + "loss": 0.4894, + "step": 5688 + }, + { + "epoch": 0.49, + "learning_rate": 1.0967803303783523e-05, + "loss": 0.4744, + "step": 5689 + }, + { + "epoch": 0.49, + "learning_rate": 1.0965054633578786e-05, + "loss": 0.4657, + "step": 5690 + }, + { + "epoch": 0.49, + "learning_rate": 1.0962305889774952e-05, + "loss": 0.4825, + "step": 5691 + }, + { + "epoch": 0.49, + "learning_rate": 1.0959557072581652e-05, + "loss": 0.489, + "step": 5692 + }, + { + "epoch": 0.49, + "learning_rate": 1.0956808182208525e-05, + "loss": 0.4609, + "step": 5693 + }, + { + "epoch": 0.49, + "learning_rate": 1.0954059218865211e-05, + "loss": 0.4786, + "step": 5694 + }, + { + "epoch": 0.49, + "learning_rate": 1.0951310182761358e-05, + "loss": 0.5028, + "step": 5695 + }, + { + "epoch": 0.49, + "learning_rate": 1.0948561074106618e-05, + "loss": 0.4925, + "step": 5696 + }, + { + "epoch": 0.49, + "learning_rate": 1.0945811893110653e-05, + "loss": 0.4811, + "step": 5697 + }, + { + "epoch": 0.49, + "learning_rate": 1.0943062639983119e-05, + "loss": 0.5011, + "step": 5698 + }, + { + "epoch": 0.49, + "learning_rate": 1.0940313314933697e-05, + "loss": 0.4558, + "step": 5699 + }, + { + "epoch": 0.49, + "learning_rate": 1.0937563918172052e-05, + "loss": 0.4797, + "step": 5700 + }, + { + "epoch": 0.49, + "learning_rate": 1.093481444990787e-05, + "loss": 0.4813, + "step": 5701 + }, + { + "epoch": 0.49, + "learning_rate": 1.0932064910350835e-05, + "loss": 0.4756, + "step": 5702 + }, + { + "epoch": 0.49, + "learning_rate": 1.092931529971064e-05, + "loss": 0.4821, + "step": 5703 + }, + { + "epoch": 0.49, + "learning_rate": 1.0926565618196978e-05, + "loss": 0.4959, + "step": 5704 + }, + { + "epoch": 0.49, + "learning_rate": 1.0923815866019553e-05, + "loss": 0.4749, + "step": 5705 + }, + { + "epoch": 0.49, + "learning_rate": 1.0921066043388078e-05, + "loss": 0.4654, + "step": 5706 + }, + { + "epoch": 0.49, + "learning_rate": 1.0918316150512256e-05, + "loss": 0.4731, + "step": 5707 + }, + { + "epoch": 0.49, + "learning_rate": 1.0915566187601814e-05, + "loss": 0.4834, + "step": 5708 + }, + { + "epoch": 0.49, + "learning_rate": 1.091281615486647e-05, + "loss": 0.4542, + "step": 5709 + }, + { + "epoch": 0.49, + "learning_rate": 1.0910066052515956e-05, + "loss": 0.4831, + "step": 5710 + }, + { + "epoch": 0.49, + "learning_rate": 1.0907315880760003e-05, + "loss": 0.4815, + "step": 5711 + }, + { + "epoch": 0.49, + "learning_rate": 1.0904565639808358e-05, + "loss": 0.4831, + "step": 5712 + }, + { + "epoch": 0.49, + "learning_rate": 1.0901815329870758e-05, + "loss": 0.4686, + "step": 5713 + }, + { + "epoch": 0.49, + "learning_rate": 1.0899064951156956e-05, + "loss": 0.484, + "step": 5714 + }, + { + "epoch": 0.49, + "learning_rate": 1.0896314503876708e-05, + "loss": 0.4713, + "step": 5715 + }, + { + "epoch": 0.49, + "learning_rate": 1.0893563988239773e-05, + "loss": 0.4793, + "step": 5716 + }, + { + "epoch": 0.49, + "learning_rate": 1.089081340445592e-05, + "loss": 0.4635, + "step": 5717 + }, + { + "epoch": 0.49, + "learning_rate": 1.0888062752734913e-05, + "loss": 0.4732, + "step": 5718 + }, + { + "epoch": 0.49, + "learning_rate": 1.0885312033286537e-05, + "loss": 0.4812, + "step": 5719 + }, + { + "epoch": 0.49, + "learning_rate": 1.088256124632057e-05, + "loss": 0.4738, + "step": 5720 + }, + { + "epoch": 0.49, + "learning_rate": 1.0879810392046795e-05, + "loss": 0.4799, + "step": 5721 + }, + { + "epoch": 0.49, + "learning_rate": 1.0877059470675007e-05, + "loss": 0.4749, + "step": 5722 + }, + { + "epoch": 0.49, + "learning_rate": 1.0874308482415002e-05, + "loss": 0.484, + "step": 5723 + }, + { + "epoch": 0.49, + "learning_rate": 1.0871557427476585e-05, + "loss": 0.4905, + "step": 5724 + }, + { + "epoch": 0.49, + "learning_rate": 1.0868806306069555e-05, + "loss": 0.4773, + "step": 5725 + }, + { + "epoch": 0.49, + "learning_rate": 1.0866055118403733e-05, + "loss": 0.5007, + "step": 5726 + }, + { + "epoch": 0.49, + "learning_rate": 1.086330386468893e-05, + "loss": 0.4807, + "step": 5727 + }, + { + "epoch": 0.49, + "learning_rate": 1.086055254513497e-05, + "loss": 0.4568, + "step": 5728 + }, + { + "epoch": 0.49, + "learning_rate": 1.0857801159951681e-05, + "loss": 0.4773, + "step": 5729 + }, + { + "epoch": 0.49, + "learning_rate": 1.0855049709348895e-05, + "loss": 0.486, + "step": 5730 + }, + { + "epoch": 0.49, + "learning_rate": 1.0852298193536446e-05, + "loss": 0.4701, + "step": 5731 + }, + { + "epoch": 0.49, + "learning_rate": 1.084954661272418e-05, + "loss": 0.4913, + "step": 5732 + }, + { + "epoch": 0.49, + "learning_rate": 1.0846794967121942e-05, + "loss": 0.4871, + "step": 5733 + }, + { + "epoch": 0.49, + "learning_rate": 1.0844043256939585e-05, + "loss": 0.473, + "step": 5734 + }, + { + "epoch": 0.49, + "learning_rate": 1.0841291482386967e-05, + "loss": 0.4978, + "step": 5735 + }, + { + "epoch": 0.49, + "learning_rate": 1.0838539643673948e-05, + "loss": 0.4952, + "step": 5736 + }, + { + "epoch": 0.49, + "learning_rate": 1.083578774101039e-05, + "loss": 0.4975, + "step": 5737 + }, + { + "epoch": 0.49, + "learning_rate": 1.0833035774606176e-05, + "loss": 0.4743, + "step": 5738 + }, + { + "epoch": 0.49, + "learning_rate": 1.0830283744671173e-05, + "loss": 0.4795, + "step": 5739 + }, + { + "epoch": 0.49, + "learning_rate": 1.0827531651415266e-05, + "loss": 0.5006, + "step": 5740 + }, + { + "epoch": 0.49, + "learning_rate": 1.082477949504834e-05, + "loss": 0.4663, + "step": 5741 + }, + { + "epoch": 0.49, + "learning_rate": 1.0822027275780287e-05, + "loss": 0.4914, + "step": 5742 + }, + { + "epoch": 0.49, + "learning_rate": 1.0819274993820998e-05, + "loss": 0.478, + "step": 5743 + }, + { + "epoch": 0.49, + "learning_rate": 1.0816522649380383e-05, + "loss": 0.4834, + "step": 5744 + }, + { + "epoch": 0.49, + "learning_rate": 1.081377024266834e-05, + "loss": 0.4558, + "step": 5745 + }, + { + "epoch": 0.49, + "learning_rate": 1.0811017773894781e-05, + "loss": 0.4946, + "step": 5746 + }, + { + "epoch": 0.49, + "learning_rate": 1.0808265243269623e-05, + "loss": 0.4661, + "step": 5747 + }, + { + "epoch": 0.49, + "learning_rate": 1.0805512651002779e-05, + "loss": 0.4491, + "step": 5748 + }, + { + "epoch": 0.49, + "learning_rate": 1.080275999730418e-05, + "loss": 0.4669, + "step": 5749 + }, + { + "epoch": 0.49, + "learning_rate": 1.0800007282383748e-05, + "loss": 0.4682, + "step": 5750 + }, + { + "epoch": 0.49, + "learning_rate": 1.0797254506451426e-05, + "loss": 0.4452, + "step": 5751 + }, + { + "epoch": 0.49, + "learning_rate": 1.0794501669717146e-05, + "loss": 0.4768, + "step": 5752 + }, + { + "epoch": 0.49, + "learning_rate": 1.0791748772390849e-05, + "loss": 0.4768, + "step": 5753 + }, + { + "epoch": 0.49, + "learning_rate": 1.0788995814682486e-05, + "loss": 0.4597, + "step": 5754 + }, + { + "epoch": 0.49, + "learning_rate": 1.078624279680201e-05, + "loss": 0.5029, + "step": 5755 + }, + { + "epoch": 0.49, + "learning_rate": 1.0783489718959376e-05, + "loss": 0.4747, + "step": 5756 + }, + { + "epoch": 0.49, + "learning_rate": 1.0780736581364543e-05, + "loss": 0.4768, + "step": 5757 + }, + { + "epoch": 0.49, + "learning_rate": 1.077798338422748e-05, + "loss": 0.4671, + "step": 5758 + }, + { + "epoch": 0.49, + "learning_rate": 1.0775230127758156e-05, + "loss": 0.4884, + "step": 5759 + }, + { + "epoch": 0.49, + "learning_rate": 1.0772476812166545e-05, + "loss": 0.4874, + "step": 5760 + }, + { + "epoch": 0.49, + "learning_rate": 1.076972343766263e-05, + "loss": 0.4696, + "step": 5761 + }, + { + "epoch": 0.49, + "learning_rate": 1.076697000445639e-05, + "loss": 0.468, + "step": 5762 + }, + { + "epoch": 0.49, + "learning_rate": 1.0764216512757815e-05, + "loss": 0.4809, + "step": 5763 + }, + { + "epoch": 0.49, + "learning_rate": 1.0761462962776896e-05, + "loss": 0.4819, + "step": 5764 + }, + { + "epoch": 0.49, + "learning_rate": 1.0758709354723638e-05, + "loss": 0.4698, + "step": 5765 + }, + { + "epoch": 0.49, + "learning_rate": 1.0755955688808035e-05, + "loss": 0.4655, + "step": 5766 + }, + { + "epoch": 0.49, + "learning_rate": 1.0753201965240095e-05, + "loss": 0.4545, + "step": 5767 + }, + { + "epoch": 0.49, + "learning_rate": 1.075044818422983e-05, + "loss": 0.4986, + "step": 5768 + }, + { + "epoch": 0.49, + "learning_rate": 1.0747694345987249e-05, + "loss": 0.4659, + "step": 5769 + }, + { + "epoch": 0.49, + "learning_rate": 1.0744940450722378e-05, + "loss": 0.4747, + "step": 5770 + }, + { + "epoch": 0.49, + "learning_rate": 1.074218649864524e-05, + "loss": 0.4648, + "step": 5771 + }, + { + "epoch": 0.49, + "learning_rate": 1.0739432489965858e-05, + "loss": 0.4835, + "step": 5772 + }, + { + "epoch": 0.49, + "learning_rate": 1.0736678424894269e-05, + "loss": 0.4749, + "step": 5773 + }, + { + "epoch": 0.49, + "learning_rate": 1.0733924303640508e-05, + "loss": 0.4702, + "step": 5774 + }, + { + "epoch": 0.49, + "learning_rate": 1.0731170126414617e-05, + "loss": 0.4724, + "step": 5775 + }, + { + "epoch": 0.49, + "learning_rate": 1.0728415893426636e-05, + "loss": 0.4789, + "step": 5776 + }, + { + "epoch": 0.49, + "learning_rate": 1.0725661604886622e-05, + "loss": 0.4774, + "step": 5777 + }, + { + "epoch": 0.49, + "learning_rate": 1.0722907261004618e-05, + "loss": 0.4819, + "step": 5778 + }, + { + "epoch": 0.49, + "learning_rate": 1.0720152861990693e-05, + "loss": 0.485, + "step": 5779 + }, + { + "epoch": 0.49, + "learning_rate": 1.0717398408054905e-05, + "loss": 0.4727, + "step": 5780 + }, + { + "epoch": 0.49, + "learning_rate": 1.0714643899407317e-05, + "loss": 0.4657, + "step": 5781 + }, + { + "epoch": 0.49, + "learning_rate": 1.0711889336258004e-05, + "loss": 0.477, + "step": 5782 + }, + { + "epoch": 0.49, + "learning_rate": 1.0709134718817038e-05, + "loss": 0.4857, + "step": 5783 + }, + { + "epoch": 0.49, + "learning_rate": 1.0706380047294496e-05, + "loss": 0.4833, + "step": 5784 + }, + { + "epoch": 0.49, + "learning_rate": 1.0703625321900462e-05, + "loss": 0.4604, + "step": 5785 + }, + { + "epoch": 0.49, + "learning_rate": 1.0700870542845026e-05, + "loss": 0.4889, + "step": 5786 + }, + { + "epoch": 0.49, + "learning_rate": 1.0698115710338273e-05, + "loss": 0.4878, + "step": 5787 + }, + { + "epoch": 0.49, + "learning_rate": 1.0695360824590304e-05, + "loss": 0.471, + "step": 5788 + }, + { + "epoch": 0.49, + "learning_rate": 1.0692605885811215e-05, + "loss": 0.4878, + "step": 5789 + }, + { + "epoch": 0.49, + "learning_rate": 1.068985089421111e-05, + "loss": 0.475, + "step": 5790 + }, + { + "epoch": 0.49, + "learning_rate": 1.0687095850000096e-05, + "loss": 0.4713, + "step": 5791 + }, + { + "epoch": 0.49, + "learning_rate": 1.0684340753388283e-05, + "loss": 0.4824, + "step": 5792 + }, + { + "epoch": 0.49, + "learning_rate": 1.0681585604585787e-05, + "loss": 0.4724, + "step": 5793 + }, + { + "epoch": 0.49, + "learning_rate": 1.0678830403802728e-05, + "loss": 0.49, + "step": 5794 + }, + { + "epoch": 0.49, + "learning_rate": 1.0676075151249228e-05, + "loss": 0.4836, + "step": 5795 + }, + { + "epoch": 0.49, + "learning_rate": 1.067331984713541e-05, + "loss": 0.4878, + "step": 5796 + }, + { + "epoch": 0.49, + "learning_rate": 1.0670564491671415e-05, + "loss": 0.4933, + "step": 5797 + }, + { + "epoch": 0.49, + "learning_rate": 1.0667809085067376e-05, + "loss": 0.4795, + "step": 5798 + }, + { + "epoch": 0.49, + "learning_rate": 1.066505362753342e-05, + "loss": 0.4966, + "step": 5799 + }, + { + "epoch": 0.49, + "learning_rate": 1.0662298119279702e-05, + "loss": 0.4772, + "step": 5800 + }, + { + "epoch": 0.49, + "learning_rate": 1.0659542560516364e-05, + "loss": 0.4927, + "step": 5801 + }, + { + "epoch": 0.49, + "learning_rate": 1.0656786951453556e-05, + "loss": 0.4727, + "step": 5802 + }, + { + "epoch": 0.49, + "learning_rate": 1.0654031292301432e-05, + "loss": 0.4756, + "step": 5803 + }, + { + "epoch": 0.49, + "learning_rate": 1.0651275583270153e-05, + "loss": 0.4787, + "step": 5804 + }, + { + "epoch": 0.49, + "learning_rate": 1.0648519824569876e-05, + "loss": 0.4832, + "step": 5805 + }, + { + "epoch": 0.5, + "learning_rate": 1.0645764016410776e-05, + "loss": 0.4551, + "step": 5806 + }, + { + "epoch": 0.5, + "learning_rate": 1.0643008159003012e-05, + "loss": 0.4906, + "step": 5807 + }, + { + "epoch": 0.5, + "learning_rate": 1.064025225255676e-05, + "loss": 0.4823, + "step": 5808 + }, + { + "epoch": 0.5, + "learning_rate": 1.0637496297282202e-05, + "loss": 0.4695, + "step": 5809 + }, + { + "epoch": 0.5, + "learning_rate": 1.0634740293389512e-05, + "loss": 0.4756, + "step": 5810 + }, + { + "epoch": 0.5, + "learning_rate": 1.0631984241088877e-05, + "loss": 0.477, + "step": 5811 + }, + { + "epoch": 0.5, + "learning_rate": 1.0629228140590486e-05, + "loss": 0.4646, + "step": 5812 + }, + { + "epoch": 0.5, + "learning_rate": 1.0626471992104532e-05, + "loss": 0.513, + "step": 5813 + }, + { + "epoch": 0.5, + "learning_rate": 1.0623715795841207e-05, + "loss": 0.4776, + "step": 5814 + }, + { + "epoch": 0.5, + "learning_rate": 1.062095955201071e-05, + "loss": 0.4818, + "step": 5815 + }, + { + "epoch": 0.5, + "learning_rate": 1.061820326082325e-05, + "loss": 0.4654, + "step": 5816 + }, + { + "epoch": 0.5, + "learning_rate": 1.0615446922489022e-05, + "loss": 0.4989, + "step": 5817 + }, + { + "epoch": 0.5, + "learning_rate": 1.0612690537218246e-05, + "loss": 0.4974, + "step": 5818 + }, + { + "epoch": 0.5, + "learning_rate": 1.0609934105221131e-05, + "loss": 0.4642, + "step": 5819 + }, + { + "epoch": 0.5, + "learning_rate": 1.0607177626707895e-05, + "loss": 0.4591, + "step": 5820 + }, + { + "epoch": 0.5, + "learning_rate": 1.0604421101888755e-05, + "loss": 0.4812, + "step": 5821 + }, + { + "epoch": 0.5, + "learning_rate": 1.0601664530973945e-05, + "loss": 0.4719, + "step": 5822 + }, + { + "epoch": 0.5, + "learning_rate": 1.0598907914173682e-05, + "loss": 0.4648, + "step": 5823 + }, + { + "epoch": 0.5, + "learning_rate": 1.05961512516982e-05, + "loss": 0.4978, + "step": 5824 + }, + { + "epoch": 0.5, + "learning_rate": 1.0593394543757738e-05, + "loss": 0.465, + "step": 5825 + }, + { + "epoch": 0.5, + "learning_rate": 1.0590637790562526e-05, + "loss": 0.474, + "step": 5826 + }, + { + "epoch": 0.5, + "learning_rate": 1.0587880992322814e-05, + "loss": 0.4761, + "step": 5827 + }, + { + "epoch": 0.5, + "learning_rate": 1.0585124149248842e-05, + "loss": 0.4705, + "step": 5828 + }, + { + "epoch": 0.5, + "learning_rate": 1.058236726155086e-05, + "loss": 0.4713, + "step": 5829 + }, + { + "epoch": 0.5, + "learning_rate": 1.0579610329439121e-05, + "loss": 0.4607, + "step": 5830 + }, + { + "epoch": 0.5, + "learning_rate": 1.0576853353123877e-05, + "loss": 0.5079, + "step": 5831 + }, + { + "epoch": 0.5, + "learning_rate": 1.0574096332815386e-05, + "loss": 0.4633, + "step": 5832 + }, + { + "epoch": 0.5, + "learning_rate": 1.0571339268723915e-05, + "loss": 0.4875, + "step": 5833 + }, + { + "epoch": 0.5, + "learning_rate": 1.0568582161059723e-05, + "loss": 0.492, + "step": 5834 + }, + { + "epoch": 0.5, + "learning_rate": 1.0565825010033085e-05, + "loss": 0.4629, + "step": 5835 + }, + { + "epoch": 0.5, + "learning_rate": 1.0563067815854266e-05, + "loss": 0.4791, + "step": 5836 + }, + { + "epoch": 0.5, + "learning_rate": 1.0560310578733549e-05, + "loss": 0.4766, + "step": 5837 + }, + { + "epoch": 0.5, + "learning_rate": 1.0557553298881202e-05, + "loss": 0.4906, + "step": 5838 + }, + { + "epoch": 0.5, + "learning_rate": 1.055479597650752e-05, + "loss": 0.4698, + "step": 5839 + }, + { + "epoch": 0.5, + "learning_rate": 1.0552038611822774e-05, + "loss": 0.5196, + "step": 5840 + }, + { + "epoch": 0.5, + "learning_rate": 1.0549281205037263e-05, + "loss": 0.469, + "step": 5841 + }, + { + "epoch": 0.5, + "learning_rate": 1.0546523756361271e-05, + "loss": 0.456, + "step": 5842 + }, + { + "epoch": 0.5, + "learning_rate": 1.0543766266005097e-05, + "loss": 0.4858, + "step": 5843 + }, + { + "epoch": 0.5, + "learning_rate": 1.0541008734179039e-05, + "loss": 0.4624, + "step": 5844 + }, + { + "epoch": 0.5, + "learning_rate": 1.0538251161093396e-05, + "loss": 0.4654, + "step": 5845 + }, + { + "epoch": 0.5, + "learning_rate": 1.0535493546958471e-05, + "loss": 0.4854, + "step": 5846 + }, + { + "epoch": 0.5, + "learning_rate": 1.0532735891984571e-05, + "loss": 0.484, + "step": 5847 + }, + { + "epoch": 0.5, + "learning_rate": 1.0529978196382011e-05, + "loss": 0.4737, + "step": 5848 + }, + { + "epoch": 0.5, + "learning_rate": 1.05272204603611e-05, + "loss": 0.4796, + "step": 5849 + }, + { + "epoch": 0.5, + "learning_rate": 1.0524462684132155e-05, + "loss": 0.4934, + "step": 5850 + }, + { + "epoch": 0.5, + "learning_rate": 1.0521704867905496e-05, + "loss": 0.4691, + "step": 5851 + }, + { + "epoch": 0.5, + "learning_rate": 1.0518947011891447e-05, + "loss": 0.4573, + "step": 5852 + }, + { + "epoch": 0.5, + "learning_rate": 1.0516189116300333e-05, + "loss": 0.4789, + "step": 5853 + }, + { + "epoch": 0.5, + "learning_rate": 1.051343118134248e-05, + "loss": 0.4811, + "step": 5854 + }, + { + "epoch": 0.5, + "learning_rate": 1.0510673207228222e-05, + "loss": 0.4703, + "step": 5855 + }, + { + "epoch": 0.5, + "learning_rate": 1.0507915194167893e-05, + "loss": 0.4957, + "step": 5856 + }, + { + "epoch": 0.5, + "learning_rate": 1.0505157142371832e-05, + "loss": 0.4904, + "step": 5857 + }, + { + "epoch": 0.5, + "learning_rate": 1.0502399052050378e-05, + "loss": 0.4705, + "step": 5858 + }, + { + "epoch": 0.5, + "learning_rate": 1.0499640923413874e-05, + "loss": 0.4955, + "step": 5859 + }, + { + "epoch": 0.5, + "learning_rate": 1.0496882756672667e-05, + "loss": 0.4891, + "step": 5860 + }, + { + "epoch": 0.5, + "learning_rate": 1.0494124552037105e-05, + "loss": 0.4745, + "step": 5861 + }, + { + "epoch": 0.5, + "learning_rate": 1.0491366309717548e-05, + "loss": 0.4567, + "step": 5862 + }, + { + "epoch": 0.5, + "learning_rate": 1.048860802992434e-05, + "loss": 0.4801, + "step": 5863 + }, + { + "epoch": 0.5, + "learning_rate": 1.0485849712867844e-05, + "loss": 0.4674, + "step": 5864 + }, + { + "epoch": 0.5, + "learning_rate": 1.048309135875842e-05, + "loss": 0.4784, + "step": 5865 + }, + { + "epoch": 0.5, + "learning_rate": 1.0480332967806435e-05, + "loss": 0.4672, + "step": 5866 + }, + { + "epoch": 0.5, + "learning_rate": 1.0477574540222249e-05, + "loss": 0.4818, + "step": 5867 + }, + { + "epoch": 0.5, + "learning_rate": 1.0474816076216237e-05, + "loss": 0.4754, + "step": 5868 + }, + { + "epoch": 0.5, + "learning_rate": 1.047205757599877e-05, + "loss": 0.4672, + "step": 5869 + }, + { + "epoch": 0.5, + "learning_rate": 1.0469299039780217e-05, + "loss": 0.4816, + "step": 5870 + }, + { + "epoch": 0.5, + "learning_rate": 1.0466540467770965e-05, + "loss": 0.4541, + "step": 5871 + }, + { + "epoch": 0.5, + "learning_rate": 1.0463781860181385e-05, + "loss": 0.4928, + "step": 5872 + }, + { + "epoch": 0.5, + "learning_rate": 1.0461023217221867e-05, + "loss": 0.4783, + "step": 5873 + }, + { + "epoch": 0.5, + "learning_rate": 1.0458264539102792e-05, + "loss": 0.4704, + "step": 5874 + }, + { + "epoch": 0.5, + "learning_rate": 1.045550582603455e-05, + "loss": 0.4591, + "step": 5875 + }, + { + "epoch": 0.5, + "learning_rate": 1.0452747078227534e-05, + "loss": 0.4808, + "step": 5876 + }, + { + "epoch": 0.5, + "learning_rate": 1.0449988295892134e-05, + "loss": 0.4666, + "step": 5877 + }, + { + "epoch": 0.5, + "learning_rate": 1.044722947923875e-05, + "loss": 0.4848, + "step": 5878 + }, + { + "epoch": 0.5, + "learning_rate": 1.0444470628477773e-05, + "loss": 0.4988, + "step": 5879 + }, + { + "epoch": 0.5, + "learning_rate": 1.0441711743819618e-05, + "loss": 0.4792, + "step": 5880 + }, + { + "epoch": 0.5, + "learning_rate": 1.0438952825474678e-05, + "loss": 0.4694, + "step": 5881 + }, + { + "epoch": 0.5, + "learning_rate": 1.0436193873653362e-05, + "loss": 0.4798, + "step": 5882 + }, + { + "epoch": 0.5, + "learning_rate": 1.0433434888566078e-05, + "loss": 0.4736, + "step": 5883 + }, + { + "epoch": 0.5, + "learning_rate": 1.0430675870423245e-05, + "loss": 0.4651, + "step": 5884 + }, + { + "epoch": 0.5, + "learning_rate": 1.0427916819435271e-05, + "loss": 0.4658, + "step": 5885 + }, + { + "epoch": 0.5, + "learning_rate": 1.0425157735812572e-05, + "loss": 0.4877, + "step": 5886 + }, + { + "epoch": 0.5, + "learning_rate": 1.0422398619765571e-05, + "loss": 0.4709, + "step": 5887 + }, + { + "epoch": 0.5, + "learning_rate": 1.0419639471504684e-05, + "loss": 0.4852, + "step": 5888 + }, + { + "epoch": 0.5, + "learning_rate": 1.0416880291240343e-05, + "loss": 0.4819, + "step": 5889 + }, + { + "epoch": 0.5, + "learning_rate": 1.0414121079182969e-05, + "loss": 0.4669, + "step": 5890 + }, + { + "epoch": 0.5, + "learning_rate": 1.0411361835542991e-05, + "loss": 0.4866, + "step": 5891 + }, + { + "epoch": 0.5, + "learning_rate": 1.0408602560530845e-05, + "loss": 0.4624, + "step": 5892 + }, + { + "epoch": 0.5, + "learning_rate": 1.0405843254356959e-05, + "loss": 0.4784, + "step": 5893 + }, + { + "epoch": 0.5, + "learning_rate": 1.0403083917231776e-05, + "loss": 0.4542, + "step": 5894 + }, + { + "epoch": 0.5, + "learning_rate": 1.0400324549365725e-05, + "loss": 0.4875, + "step": 5895 + }, + { + "epoch": 0.5, + "learning_rate": 1.039756515096926e-05, + "loss": 0.4798, + "step": 5896 + }, + { + "epoch": 0.5, + "learning_rate": 1.039480572225281e-05, + "loss": 0.4479, + "step": 5897 + }, + { + "epoch": 0.5, + "learning_rate": 1.0392046263426832e-05, + "loss": 0.4658, + "step": 5898 + }, + { + "epoch": 0.5, + "learning_rate": 1.0389286774701765e-05, + "loss": 0.4631, + "step": 5899 + }, + { + "epoch": 0.5, + "learning_rate": 1.0386527256288065e-05, + "loss": 0.4726, + "step": 5900 + }, + { + "epoch": 0.5, + "learning_rate": 1.0383767708396187e-05, + "loss": 0.4926, + "step": 5901 + }, + { + "epoch": 0.5, + "learning_rate": 1.0381008131236576e-05, + "loss": 0.4847, + "step": 5902 + }, + { + "epoch": 0.5, + "learning_rate": 1.0378248525019694e-05, + "loss": 0.4902, + "step": 5903 + }, + { + "epoch": 0.5, + "learning_rate": 1.0375488889956003e-05, + "loss": 0.4743, + "step": 5904 + }, + { + "epoch": 0.5, + "learning_rate": 1.0372729226255962e-05, + "loss": 0.4862, + "step": 5905 + }, + { + "epoch": 0.5, + "learning_rate": 1.0369969534130031e-05, + "loss": 0.4797, + "step": 5906 + }, + { + "epoch": 0.5, + "learning_rate": 1.036720981378868e-05, + "loss": 0.4779, + "step": 5907 + }, + { + "epoch": 0.5, + "learning_rate": 1.0364450065442377e-05, + "loss": 0.4875, + "step": 5908 + }, + { + "epoch": 0.5, + "learning_rate": 1.036169028930159e-05, + "loss": 0.483, + "step": 5909 + }, + { + "epoch": 0.5, + "learning_rate": 1.0358930485576793e-05, + "loss": 0.4764, + "step": 5910 + }, + { + "epoch": 0.5, + "learning_rate": 1.0356170654478457e-05, + "loss": 0.4863, + "step": 5911 + }, + { + "epoch": 0.5, + "learning_rate": 1.0353410796217058e-05, + "loss": 0.4921, + "step": 5912 + }, + { + "epoch": 0.5, + "learning_rate": 1.035065091100308e-05, + "loss": 0.4662, + "step": 5913 + }, + { + "epoch": 0.5, + "learning_rate": 1.0347890999046998e-05, + "loss": 0.4694, + "step": 5914 + }, + { + "epoch": 0.5, + "learning_rate": 1.0345131060559295e-05, + "loss": 0.4751, + "step": 5915 + }, + { + "epoch": 0.5, + "learning_rate": 1.0342371095750456e-05, + "loss": 0.4776, + "step": 5916 + }, + { + "epoch": 0.5, + "learning_rate": 1.033961110483097e-05, + "loss": 0.4798, + "step": 5917 + }, + { + "epoch": 0.5, + "learning_rate": 1.0336851088011321e-05, + "loss": 0.4751, + "step": 5918 + }, + { + "epoch": 0.5, + "learning_rate": 1.0334091045502005e-05, + "loss": 0.494, + "step": 5919 + }, + { + "epoch": 0.5, + "learning_rate": 1.033133097751351e-05, + "loss": 0.4639, + "step": 5920 + }, + { + "epoch": 0.5, + "learning_rate": 1.0328570884256328e-05, + "loss": 0.48, + "step": 5921 + }, + { + "epoch": 0.5, + "learning_rate": 1.0325810765940962e-05, + "loss": 0.4577, + "step": 5922 + }, + { + "epoch": 0.51, + "learning_rate": 1.0323050622777906e-05, + "loss": 0.4769, + "step": 5923 + }, + { + "epoch": 0.51, + "learning_rate": 1.0320290454977662e-05, + "loss": 0.4783, + "step": 5924 + }, + { + "epoch": 0.51, + "learning_rate": 1.0317530262750728e-05, + "loss": 0.4908, + "step": 5925 + }, + { + "epoch": 0.51, + "learning_rate": 1.0314770046307611e-05, + "loss": 0.4864, + "step": 5926 + }, + { + "epoch": 0.51, + "learning_rate": 1.0312009805858818e-05, + "loss": 0.4742, + "step": 5927 + }, + { + "epoch": 0.51, + "learning_rate": 1.0309249541614854e-05, + "loss": 0.4942, + "step": 5928 + }, + { + "epoch": 0.51, + "learning_rate": 1.030648925378623e-05, + "loss": 0.4652, + "step": 5929 + }, + { + "epoch": 0.51, + "learning_rate": 1.0303728942583454e-05, + "loss": 0.4767, + "step": 5930 + }, + { + "epoch": 0.51, + "learning_rate": 1.0300968608217042e-05, + "loss": 0.4827, + "step": 5931 + }, + { + "epoch": 0.51, + "learning_rate": 1.0298208250897504e-05, + "loss": 0.4854, + "step": 5932 + }, + { + "epoch": 0.51, + "learning_rate": 1.0295447870835364e-05, + "loss": 0.454, + "step": 5933 + }, + { + "epoch": 0.51, + "learning_rate": 1.0292687468241136e-05, + "loss": 0.4881, + "step": 5934 + }, + { + "epoch": 0.51, + "learning_rate": 1.0289927043325336e-05, + "loss": 0.4831, + "step": 5935 + }, + { + "epoch": 0.51, + "learning_rate": 1.0287166596298492e-05, + "loss": 0.452, + "step": 5936 + }, + { + "epoch": 0.51, + "learning_rate": 1.0284406127371125e-05, + "loss": 0.4944, + "step": 5937 + }, + { + "epoch": 0.51, + "learning_rate": 1.0281645636753758e-05, + "loss": 0.4721, + "step": 5938 + }, + { + "epoch": 0.51, + "learning_rate": 1.0278885124656919e-05, + "loss": 0.447, + "step": 5939 + }, + { + "epoch": 0.51, + "learning_rate": 1.027612459129114e-05, + "loss": 0.4795, + "step": 5940 + }, + { + "epoch": 0.51, + "learning_rate": 1.027336403686694e-05, + "loss": 0.4877, + "step": 5941 + }, + { + "epoch": 0.51, + "learning_rate": 1.0270603461594861e-05, + "loss": 0.4646, + "step": 5942 + }, + { + "epoch": 0.51, + "learning_rate": 1.0267842865685431e-05, + "loss": 0.484, + "step": 5943 + }, + { + "epoch": 0.51, + "learning_rate": 1.0265082249349188e-05, + "loss": 0.4707, + "step": 5944 + }, + { + "epoch": 0.51, + "learning_rate": 1.0262321612796662e-05, + "loss": 0.4819, + "step": 5945 + }, + { + "epoch": 0.51, + "learning_rate": 1.02595609562384e-05, + "loss": 0.4744, + "step": 5946 + }, + { + "epoch": 0.51, + "learning_rate": 1.0256800279884934e-05, + "loss": 0.4858, + "step": 5947 + }, + { + "epoch": 0.51, + "learning_rate": 1.0254039583946805e-05, + "loss": 0.49, + "step": 5948 + }, + { + "epoch": 0.51, + "learning_rate": 1.0251278868634557e-05, + "loss": 0.4667, + "step": 5949 + }, + { + "epoch": 0.51, + "learning_rate": 1.024851813415873e-05, + "loss": 0.4678, + "step": 5950 + }, + { + "epoch": 0.51, + "learning_rate": 1.024575738072988e-05, + "loss": 0.4741, + "step": 5951 + }, + { + "epoch": 0.51, + "learning_rate": 1.0242996608558542e-05, + "loss": 0.4744, + "step": 5952 + }, + { + "epoch": 0.51, + "learning_rate": 1.0240235817855269e-05, + "loss": 0.4753, + "step": 5953 + }, + { + "epoch": 0.51, + "learning_rate": 1.0237475008830608e-05, + "loss": 0.4863, + "step": 5954 + }, + { + "epoch": 0.51, + "learning_rate": 1.0234714181695115e-05, + "loss": 0.4726, + "step": 5955 + }, + { + "epoch": 0.51, + "learning_rate": 1.0231953336659334e-05, + "loss": 0.4596, + "step": 5956 + }, + { + "epoch": 0.51, + "learning_rate": 1.0229192473933826e-05, + "loss": 0.4995, + "step": 5957 + }, + { + "epoch": 0.51, + "learning_rate": 1.0226431593729144e-05, + "loss": 0.4677, + "step": 5958 + }, + { + "epoch": 0.51, + "learning_rate": 1.022367069625584e-05, + "loss": 0.4619, + "step": 5959 + }, + { + "epoch": 0.51, + "learning_rate": 1.0220909781724478e-05, + "loss": 0.48, + "step": 5960 + }, + { + "epoch": 0.51, + "learning_rate": 1.0218148850345613e-05, + "loss": 0.4743, + "step": 5961 + }, + { + "epoch": 0.51, + "learning_rate": 1.0215387902329806e-05, + "loss": 0.4804, + "step": 5962 + }, + { + "epoch": 0.51, + "learning_rate": 1.0212626937887618e-05, + "loss": 0.5004, + "step": 5963 + }, + { + "epoch": 0.51, + "learning_rate": 1.0209865957229612e-05, + "loss": 0.4797, + "step": 5964 + }, + { + "epoch": 0.51, + "learning_rate": 1.020710496056635e-05, + "loss": 0.4465, + "step": 5965 + }, + { + "epoch": 0.51, + "learning_rate": 1.0204343948108402e-05, + "loss": 0.4503, + "step": 5966 + }, + { + "epoch": 0.51, + "learning_rate": 1.020158292006633e-05, + "loss": 0.4827, + "step": 5967 + }, + { + "epoch": 0.51, + "learning_rate": 1.0198821876650702e-05, + "loss": 0.4637, + "step": 5968 + }, + { + "epoch": 0.51, + "learning_rate": 1.019606081807209e-05, + "loss": 0.4763, + "step": 5969 + }, + { + "epoch": 0.51, + "learning_rate": 1.0193299744541063e-05, + "loss": 0.4657, + "step": 5970 + }, + { + "epoch": 0.51, + "learning_rate": 1.0190538656268186e-05, + "loss": 0.4821, + "step": 5971 + }, + { + "epoch": 0.51, + "learning_rate": 1.0187777553464038e-05, + "loss": 0.4611, + "step": 5972 + }, + { + "epoch": 0.51, + "learning_rate": 1.0185016436339187e-05, + "loss": 0.4889, + "step": 5973 + }, + { + "epoch": 0.51, + "learning_rate": 1.0182255305104215e-05, + "loss": 0.4882, + "step": 5974 + }, + { + "epoch": 0.51, + "learning_rate": 1.0179494159969687e-05, + "loss": 0.4727, + "step": 5975 + }, + { + "epoch": 0.51, + "learning_rate": 1.017673300114619e-05, + "loss": 0.493, + "step": 5976 + }, + { + "epoch": 0.51, + "learning_rate": 1.017397182884429e-05, + "loss": 0.4503, + "step": 5977 + }, + { + "epoch": 0.51, + "learning_rate": 1.017121064327458e-05, + "loss": 0.4565, + "step": 5978 + }, + { + "epoch": 0.51, + "learning_rate": 1.016844944464763e-05, + "loss": 0.4727, + "step": 5979 + }, + { + "epoch": 0.51, + "learning_rate": 1.0165688233174019e-05, + "loss": 0.4753, + "step": 5980 + }, + { + "epoch": 0.51, + "learning_rate": 1.0162927009064331e-05, + "loss": 0.4681, + "step": 5981 + }, + { + "epoch": 0.51, + "learning_rate": 1.0160165772529151e-05, + "loss": 0.47, + "step": 5982 + }, + { + "epoch": 0.51, + "learning_rate": 1.015740452377906e-05, + "loss": 0.4869, + "step": 5983 + }, + { + "epoch": 0.51, + "learning_rate": 1.0154643263024644e-05, + "loss": 0.4813, + "step": 5984 + }, + { + "epoch": 0.51, + "learning_rate": 1.0151881990476486e-05, + "loss": 0.4657, + "step": 5985 + }, + { + "epoch": 0.51, + "learning_rate": 1.0149120706345175e-05, + "loss": 0.4751, + "step": 5986 + }, + { + "epoch": 0.51, + "learning_rate": 1.0146359410841292e-05, + "loss": 0.4792, + "step": 5987 + }, + { + "epoch": 0.51, + "learning_rate": 1.0143598104175434e-05, + "loss": 0.4794, + "step": 5988 + }, + { + "epoch": 0.51, + "learning_rate": 1.0140836786558184e-05, + "loss": 0.475, + "step": 5989 + }, + { + "epoch": 0.51, + "learning_rate": 1.0138075458200132e-05, + "loss": 0.4674, + "step": 5990 + }, + { + "epoch": 0.51, + "learning_rate": 1.013531411931187e-05, + "loss": 0.4528, + "step": 5991 + }, + { + "epoch": 0.51, + "learning_rate": 1.0132552770103987e-05, + "loss": 0.4912, + "step": 5992 + }, + { + "epoch": 0.51, + "learning_rate": 1.0129791410787076e-05, + "loss": 0.4553, + "step": 5993 + }, + { + "epoch": 0.51, + "learning_rate": 1.0127030041571733e-05, + "loss": 0.471, + "step": 5994 + }, + { + "epoch": 0.51, + "learning_rate": 1.0124268662668547e-05, + "loss": 0.466, + "step": 5995 + }, + { + "epoch": 0.51, + "learning_rate": 1.0121507274288112e-05, + "loss": 0.5047, + "step": 5996 + }, + { + "epoch": 0.51, + "learning_rate": 1.0118745876641025e-05, + "loss": 0.478, + "step": 5997 + }, + { + "epoch": 0.51, + "learning_rate": 1.0115984469937883e-05, + "loss": 0.4828, + "step": 5998 + }, + { + "epoch": 0.51, + "learning_rate": 1.0113223054389284e-05, + "loss": 0.4653, + "step": 5999 + }, + { + "epoch": 0.51, + "learning_rate": 1.0110461630205819e-05, + "loss": 0.4635, + "step": 6000 + }, + { + "epoch": 0.51, + "learning_rate": 1.0107700197598089e-05, + "loss": 0.4854, + "step": 6001 + }, + { + "epoch": 0.51, + "learning_rate": 1.0104938756776694e-05, + "loss": 0.466, + "step": 6002 + }, + { + "epoch": 0.51, + "learning_rate": 1.010217730795223e-05, + "loss": 0.473, + "step": 6003 + }, + { + "epoch": 0.51, + "learning_rate": 1.00994158513353e-05, + "loss": 0.4842, + "step": 6004 + }, + { + "epoch": 0.51, + "learning_rate": 1.0096654387136497e-05, + "loss": 0.4973, + "step": 6005 + }, + { + "epoch": 0.51, + "learning_rate": 1.009389291556643e-05, + "loss": 0.4845, + "step": 6006 + }, + { + "epoch": 0.51, + "learning_rate": 1.0091131436835698e-05, + "loss": 0.479, + "step": 6007 + }, + { + "epoch": 0.51, + "learning_rate": 1.0088369951154904e-05, + "loss": 0.5021, + "step": 6008 + }, + { + "epoch": 0.51, + "learning_rate": 1.0085608458734644e-05, + "loss": 0.4843, + "step": 6009 + }, + { + "epoch": 0.51, + "learning_rate": 1.0082846959785528e-05, + "loss": 0.4672, + "step": 6010 + }, + { + "epoch": 0.51, + "learning_rate": 1.0080085454518158e-05, + "loss": 0.4962, + "step": 6011 + }, + { + "epoch": 0.51, + "learning_rate": 1.0077323943143134e-05, + "loss": 0.4777, + "step": 6012 + }, + { + "epoch": 0.51, + "learning_rate": 1.0074562425871065e-05, + "loss": 0.515, + "step": 6013 + }, + { + "epoch": 0.51, + "learning_rate": 1.0071800902912553e-05, + "loss": 0.4822, + "step": 6014 + }, + { + "epoch": 0.51, + "learning_rate": 1.0069039374478207e-05, + "loss": 0.4878, + "step": 6015 + }, + { + "epoch": 0.51, + "learning_rate": 1.0066277840778626e-05, + "loss": 0.4842, + "step": 6016 + }, + { + "epoch": 0.51, + "learning_rate": 1.0063516302024425e-05, + "loss": 0.4827, + "step": 6017 + }, + { + "epoch": 0.51, + "learning_rate": 1.0060754758426204e-05, + "loss": 0.4626, + "step": 6018 + }, + { + "epoch": 0.51, + "learning_rate": 1.005799321019457e-05, + "loss": 0.4717, + "step": 6019 + }, + { + "epoch": 0.51, + "learning_rate": 1.0055231657540132e-05, + "loss": 0.4908, + "step": 6020 + }, + { + "epoch": 0.51, + "learning_rate": 1.0052470100673495e-05, + "loss": 0.4868, + "step": 6021 + }, + { + "epoch": 0.51, + "learning_rate": 1.0049708539805274e-05, + "loss": 0.4825, + "step": 6022 + }, + { + "epoch": 0.51, + "learning_rate": 1.004694697514607e-05, + "loss": 0.4784, + "step": 6023 + }, + { + "epoch": 0.51, + "learning_rate": 1.0044185406906493e-05, + "loss": 0.4917, + "step": 6024 + }, + { + "epoch": 0.51, + "learning_rate": 1.0041423835297155e-05, + "loss": 0.4768, + "step": 6025 + }, + { + "epoch": 0.51, + "learning_rate": 1.003866226052866e-05, + "loss": 0.4705, + "step": 6026 + }, + { + "epoch": 0.51, + "learning_rate": 1.0035900682811619e-05, + "loss": 0.4645, + "step": 6027 + }, + { + "epoch": 0.51, + "learning_rate": 1.0033139102356641e-05, + "loss": 0.4896, + "step": 6028 + }, + { + "epoch": 0.51, + "learning_rate": 1.0030377519374342e-05, + "loss": 0.4921, + "step": 6029 + }, + { + "epoch": 0.51, + "learning_rate": 1.0027615934075321e-05, + "loss": 0.4532, + "step": 6030 + }, + { + "epoch": 0.51, + "learning_rate": 1.0024854346670196e-05, + "loss": 0.4717, + "step": 6031 + }, + { + "epoch": 0.51, + "learning_rate": 1.0022092757369575e-05, + "loss": 0.4716, + "step": 6032 + }, + { + "epoch": 0.51, + "learning_rate": 1.0019331166384068e-05, + "loss": 0.465, + "step": 6033 + }, + { + "epoch": 0.51, + "learning_rate": 1.0016569573924287e-05, + "loss": 0.4817, + "step": 6034 + }, + { + "epoch": 0.51, + "learning_rate": 1.0013807980200838e-05, + "loss": 0.4805, + "step": 6035 + }, + { + "epoch": 0.51, + "learning_rate": 1.0011046385424335e-05, + "loss": 0.4853, + "step": 6036 + }, + { + "epoch": 0.51, + "learning_rate": 1.0008284789805389e-05, + "loss": 0.4745, + "step": 6037 + }, + { + "epoch": 0.51, + "learning_rate": 1.0005523193554613e-05, + "loss": 0.4858, + "step": 6038 + }, + { + "epoch": 0.51, + "learning_rate": 1.000276159688261e-05, + "loss": 0.4591, + "step": 6039 + }, + { + "epoch": 0.52, + "learning_rate": 1e-05, + "loss": 0.4665, + "step": 6040 + }, + { + "epoch": 0.52, + "learning_rate": 9.997238403117391e-06, + "loss": 0.4828, + "step": 6041 + }, + { + "epoch": 0.52, + "learning_rate": 9.994476806445392e-06, + "loss": 0.4682, + "step": 6042 + }, + { + "epoch": 0.52, + "learning_rate": 9.991715210194611e-06, + "loss": 0.476, + "step": 6043 + }, + { + "epoch": 0.52, + "learning_rate": 9.988953614575668e-06, + "loss": 0.492, + "step": 6044 + }, + { + "epoch": 0.52, + "learning_rate": 9.986192019799166e-06, + "loss": 0.4844, + "step": 6045 + }, + { + "epoch": 0.52, + "learning_rate": 9.98343042607572e-06, + "loss": 0.4737, + "step": 6046 + }, + { + "epoch": 0.52, + "learning_rate": 9.980668833615933e-06, + "loss": 0.4963, + "step": 6047 + }, + { + "epoch": 0.52, + "learning_rate": 9.977907242630425e-06, + "loss": 0.4672, + "step": 6048 + }, + { + "epoch": 0.52, + "learning_rate": 9.975145653329806e-06, + "loss": 0.4932, + "step": 6049 + }, + { + "epoch": 0.52, + "learning_rate": 9.972384065924684e-06, + "loss": 0.4732, + "step": 6050 + }, + { + "epoch": 0.52, + "learning_rate": 9.969622480625663e-06, + "loss": 0.4859, + "step": 6051 + }, + { + "epoch": 0.52, + "learning_rate": 9.966860897643359e-06, + "loss": 0.4964, + "step": 6052 + }, + { + "epoch": 0.52, + "learning_rate": 9.964099317188384e-06, + "loss": 0.4597, + "step": 6053 + }, + { + "epoch": 0.52, + "learning_rate": 9.961337739471344e-06, + "loss": 0.4657, + "step": 6054 + }, + { + "epoch": 0.52, + "learning_rate": 9.95857616470285e-06, + "loss": 0.4773, + "step": 6055 + }, + { + "epoch": 0.52, + "learning_rate": 9.95581459309351e-06, + "loss": 0.4645, + "step": 6056 + }, + { + "epoch": 0.52, + "learning_rate": 9.953053024853932e-06, + "loss": 0.5327, + "step": 6057 + }, + { + "epoch": 0.52, + "learning_rate": 9.950291460194729e-06, + "loss": 0.4825, + "step": 6058 + }, + { + "epoch": 0.52, + "learning_rate": 9.947529899326507e-06, + "loss": 0.47, + "step": 6059 + }, + { + "epoch": 0.52, + "learning_rate": 9.944768342459872e-06, + "loss": 0.4708, + "step": 6060 + }, + { + "epoch": 0.52, + "learning_rate": 9.942006789805432e-06, + "loss": 0.4622, + "step": 6061 + }, + { + "epoch": 0.52, + "learning_rate": 9.939245241573801e-06, + "loss": 0.4668, + "step": 6062 + }, + { + "epoch": 0.52, + "learning_rate": 9.936483697975578e-06, + "loss": 0.473, + "step": 6063 + }, + { + "epoch": 0.52, + "learning_rate": 9.933722159221375e-06, + "loss": 0.4742, + "step": 6064 + }, + { + "epoch": 0.52, + "learning_rate": 9.930960625521798e-06, + "loss": 0.4883, + "step": 6065 + }, + { + "epoch": 0.52, + "learning_rate": 9.928199097087447e-06, + "loss": 0.4683, + "step": 6066 + }, + { + "epoch": 0.52, + "learning_rate": 9.925437574128938e-06, + "loss": 0.4759, + "step": 6067 + }, + { + "epoch": 0.52, + "learning_rate": 9.92267605685687e-06, + "loss": 0.4885, + "step": 6068 + }, + { + "epoch": 0.52, + "learning_rate": 9.919914545481847e-06, + "loss": 0.4505, + "step": 6069 + }, + { + "epoch": 0.52, + "learning_rate": 9.917153040214473e-06, + "loss": 0.4669, + "step": 6070 + }, + { + "epoch": 0.52, + "learning_rate": 9.914391541265358e-06, + "loss": 0.4798, + "step": 6071 + }, + { + "epoch": 0.52, + "learning_rate": 9.9116300488451e-06, + "loss": 0.4624, + "step": 6072 + }, + { + "epoch": 0.52, + "learning_rate": 9.908868563164305e-06, + "loss": 0.4882, + "step": 6073 + }, + { + "epoch": 0.52, + "learning_rate": 9.906107084433573e-06, + "loss": 0.4799, + "step": 6074 + }, + { + "epoch": 0.52, + "learning_rate": 9.903345612863503e-06, + "loss": 0.4726, + "step": 6075 + }, + { + "epoch": 0.52, + "learning_rate": 9.900584148664705e-06, + "loss": 0.4645, + "step": 6076 + }, + { + "epoch": 0.52, + "learning_rate": 9.897822692047772e-06, + "loss": 0.4893, + "step": 6077 + }, + { + "epoch": 0.52, + "learning_rate": 9.895061243223311e-06, + "loss": 0.4651, + "step": 6078 + }, + { + "epoch": 0.52, + "learning_rate": 9.892299802401911e-06, + "loss": 0.4799, + "step": 6079 + }, + { + "epoch": 0.52, + "learning_rate": 9.889538369794185e-06, + "loss": 0.4726, + "step": 6080 + }, + { + "epoch": 0.52, + "learning_rate": 9.886776945610719e-06, + "loss": 0.4953, + "step": 6081 + }, + { + "epoch": 0.52, + "learning_rate": 9.884015530062119e-06, + "loss": 0.4747, + "step": 6082 + }, + { + "epoch": 0.52, + "learning_rate": 9.881254123358977e-06, + "loss": 0.4832, + "step": 6083 + }, + { + "epoch": 0.52, + "learning_rate": 9.87849272571189e-06, + "loss": 0.489, + "step": 6084 + }, + { + "epoch": 0.52, + "learning_rate": 9.875731337331458e-06, + "loss": 0.4612, + "step": 6085 + }, + { + "epoch": 0.52, + "learning_rate": 9.87296995842827e-06, + "loss": 0.4905, + "step": 6086 + }, + { + "epoch": 0.52, + "learning_rate": 9.870208589212928e-06, + "loss": 0.4682, + "step": 6087 + }, + { + "epoch": 0.52, + "learning_rate": 9.86744722989602e-06, + "loss": 0.4695, + "step": 6088 + }, + { + "epoch": 0.52, + "learning_rate": 9.864685880688134e-06, + "loss": 0.4961, + "step": 6089 + }, + { + "epoch": 0.52, + "learning_rate": 9.86192454179987e-06, + "loss": 0.4824, + "step": 6090 + }, + { + "epoch": 0.52, + "learning_rate": 9.85916321344182e-06, + "loss": 0.4904, + "step": 6091 + }, + { + "epoch": 0.52, + "learning_rate": 9.85640189582457e-06, + "loss": 0.4632, + "step": 6092 + }, + { + "epoch": 0.52, + "learning_rate": 9.853640589158706e-06, + "loss": 0.4639, + "step": 6093 + }, + { + "epoch": 0.52, + "learning_rate": 9.850879293654829e-06, + "loss": 0.4844, + "step": 6094 + }, + { + "epoch": 0.52, + "learning_rate": 9.848118009523516e-06, + "loss": 0.4678, + "step": 6095 + }, + { + "epoch": 0.52, + "learning_rate": 9.84535673697536e-06, + "loss": 0.4898, + "step": 6096 + }, + { + "epoch": 0.52, + "learning_rate": 9.842595476220945e-06, + "loss": 0.4592, + "step": 6097 + }, + { + "epoch": 0.52, + "learning_rate": 9.839834227470852e-06, + "loss": 0.4646, + "step": 6098 + }, + { + "epoch": 0.52, + "learning_rate": 9.83707299093567e-06, + "loss": 0.4695, + "step": 6099 + }, + { + "epoch": 0.52, + "learning_rate": 9.834311766825986e-06, + "loss": 0.4802, + "step": 6100 + }, + { + "epoch": 0.52, + "learning_rate": 9.831550555352375e-06, + "loss": 0.4689, + "step": 6101 + }, + { + "epoch": 0.52, + "learning_rate": 9.828789356725422e-06, + "loss": 0.4615, + "step": 6102 + }, + { + "epoch": 0.52, + "learning_rate": 9.82602817115571e-06, + "loss": 0.4817, + "step": 6103 + }, + { + "epoch": 0.52, + "learning_rate": 9.823266998853813e-06, + "loss": 0.4849, + "step": 6104 + }, + { + "epoch": 0.52, + "learning_rate": 9.820505840030315e-06, + "loss": 0.4638, + "step": 6105 + }, + { + "epoch": 0.52, + "learning_rate": 9.817744694895792e-06, + "loss": 0.4677, + "step": 6106 + }, + { + "epoch": 0.52, + "learning_rate": 9.814983563660814e-06, + "loss": 0.4951, + "step": 6107 + }, + { + "epoch": 0.52, + "learning_rate": 9.812222446535965e-06, + "loss": 0.4591, + "step": 6108 + }, + { + "epoch": 0.52, + "learning_rate": 9.80946134373182e-06, + "loss": 0.4686, + "step": 6109 + }, + { + "epoch": 0.52, + "learning_rate": 9.806700255458942e-06, + "loss": 0.4719, + "step": 6110 + }, + { + "epoch": 0.52, + "learning_rate": 9.803939181927914e-06, + "loss": 0.462, + "step": 6111 + }, + { + "epoch": 0.52, + "learning_rate": 9.801178123349298e-06, + "loss": 0.489, + "step": 6112 + }, + { + "epoch": 0.52, + "learning_rate": 9.798417079933672e-06, + "loss": 0.4787, + "step": 6113 + }, + { + "epoch": 0.52, + "learning_rate": 9.795656051891603e-06, + "loss": 0.4843, + "step": 6114 + }, + { + "epoch": 0.52, + "learning_rate": 9.792895039433655e-06, + "loss": 0.4689, + "step": 6115 + }, + { + "epoch": 0.52, + "learning_rate": 9.790134042770391e-06, + "loss": 0.4866, + "step": 6116 + }, + { + "epoch": 0.52, + "learning_rate": 9.787373062112386e-06, + "loss": 0.4888, + "step": 6117 + }, + { + "epoch": 0.52, + "learning_rate": 9.7846120976702e-06, + "loss": 0.466, + "step": 6118 + }, + { + "epoch": 0.52, + "learning_rate": 9.78185114965439e-06, + "loss": 0.4824, + "step": 6119 + }, + { + "epoch": 0.52, + "learning_rate": 9.779090218275527e-06, + "loss": 0.4744, + "step": 6120 + }, + { + "epoch": 0.52, + "learning_rate": 9.77632930374416e-06, + "loss": 0.482, + "step": 6121 + }, + { + "epoch": 0.52, + "learning_rate": 9.773568406270857e-06, + "loss": 0.471, + "step": 6122 + }, + { + "epoch": 0.52, + "learning_rate": 9.770807526066175e-06, + "loss": 0.4827, + "step": 6123 + }, + { + "epoch": 0.52, + "learning_rate": 9.76804666334067e-06, + "loss": 0.4614, + "step": 6124 + }, + { + "epoch": 0.52, + "learning_rate": 9.765285818304888e-06, + "loss": 0.4601, + "step": 6125 + }, + { + "epoch": 0.52, + "learning_rate": 9.762524991169392e-06, + "loss": 0.4441, + "step": 6126 + }, + { + "epoch": 0.52, + "learning_rate": 9.759764182144734e-06, + "loss": 0.47, + "step": 6127 + }, + { + "epoch": 0.52, + "learning_rate": 9.75700339144146e-06, + "loss": 0.4982, + "step": 6128 + }, + { + "epoch": 0.52, + "learning_rate": 9.754242619270125e-06, + "loss": 0.4736, + "step": 6129 + }, + { + "epoch": 0.52, + "learning_rate": 9.75148186584127e-06, + "loss": 0.4609, + "step": 6130 + }, + { + "epoch": 0.52, + "learning_rate": 9.748721131365445e-06, + "loss": 0.4577, + "step": 6131 + }, + { + "epoch": 0.52, + "learning_rate": 9.7459604160532e-06, + "loss": 0.4844, + "step": 6132 + }, + { + "epoch": 0.52, + "learning_rate": 9.743199720115071e-06, + "loss": 0.4672, + "step": 6133 + }, + { + "epoch": 0.52, + "learning_rate": 9.740439043761604e-06, + "loss": 0.4493, + "step": 6134 + }, + { + "epoch": 0.52, + "learning_rate": 9.737678387203337e-06, + "loss": 0.466, + "step": 6135 + }, + { + "epoch": 0.52, + "learning_rate": 9.734917750650817e-06, + "loss": 0.4834, + "step": 6136 + }, + { + "epoch": 0.52, + "learning_rate": 9.732157134314572e-06, + "loss": 0.4748, + "step": 6137 + }, + { + "epoch": 0.52, + "learning_rate": 9.729396538405144e-06, + "loss": 0.4591, + "step": 6138 + }, + { + "epoch": 0.52, + "learning_rate": 9.726635963133062e-06, + "loss": 0.4752, + "step": 6139 + }, + { + "epoch": 0.52, + "learning_rate": 9.723875408708866e-06, + "loss": 0.4606, + "step": 6140 + }, + { + "epoch": 0.52, + "learning_rate": 9.721114875343085e-06, + "loss": 0.48, + "step": 6141 + }, + { + "epoch": 0.52, + "learning_rate": 9.718354363246243e-06, + "loss": 0.4794, + "step": 6142 + }, + { + "epoch": 0.52, + "learning_rate": 9.71559387262888e-06, + "loss": 0.4598, + "step": 6143 + }, + { + "epoch": 0.52, + "learning_rate": 9.71283340370151e-06, + "loss": 0.4812, + "step": 6144 + }, + { + "epoch": 0.52, + "learning_rate": 9.710072956674666e-06, + "loss": 0.4644, + "step": 6145 + }, + { + "epoch": 0.52, + "learning_rate": 9.707312531758869e-06, + "loss": 0.4799, + "step": 6146 + }, + { + "epoch": 0.52, + "learning_rate": 9.704552129164641e-06, + "loss": 0.4598, + "step": 6147 + }, + { + "epoch": 0.52, + "learning_rate": 9.701791749102496e-06, + "loss": 0.4861, + "step": 6148 + }, + { + "epoch": 0.52, + "learning_rate": 9.69903139178296e-06, + "loss": 0.4861, + "step": 6149 + }, + { + "epoch": 0.52, + "learning_rate": 9.69627105741655e-06, + "loss": 0.4682, + "step": 6150 + }, + { + "epoch": 0.52, + "learning_rate": 9.693510746213774e-06, + "loss": 0.4756, + "step": 6151 + }, + { + "epoch": 0.52, + "learning_rate": 9.69075045838515e-06, + "loss": 0.4817, + "step": 6152 + }, + { + "epoch": 0.52, + "learning_rate": 9.687990194141183e-06, + "loss": 0.4685, + "step": 6153 + }, + { + "epoch": 0.52, + "learning_rate": 9.68522995369239e-06, + "loss": 0.4729, + "step": 6154 + }, + { + "epoch": 0.52, + "learning_rate": 9.682469737249274e-06, + "loss": 0.4664, + "step": 6155 + }, + { + "epoch": 0.52, + "learning_rate": 9.679709545022343e-06, + "loss": 0.4597, + "step": 6156 + }, + { + "epoch": 0.52, + "learning_rate": 9.676949377222096e-06, + "loss": 0.4712, + "step": 6157 + }, + { + "epoch": 0.53, + "learning_rate": 9.67418923405904e-06, + "loss": 0.4865, + "step": 6158 + }, + { + "epoch": 0.53, + "learning_rate": 9.671429115743674e-06, + "loss": 0.472, + "step": 6159 + }, + { + "epoch": 0.53, + "learning_rate": 9.668669022486495e-06, + "loss": 0.4792, + "step": 6160 + }, + { + "epoch": 0.53, + "learning_rate": 9.665908954498e-06, + "loss": 0.4724, + "step": 6161 + }, + { + "epoch": 0.53, + "learning_rate": 9.663148911988679e-06, + "loss": 0.486, + "step": 6162 + }, + { + "epoch": 0.53, + "learning_rate": 9.660388895169034e-06, + "loss": 0.4625, + "step": 6163 + }, + { + "epoch": 0.53, + "learning_rate": 9.657628904249546e-06, + "loss": 0.477, + "step": 6164 + }, + { + "epoch": 0.53, + "learning_rate": 9.65486893944071e-06, + "loss": 0.48, + "step": 6165 + }, + { + "epoch": 0.53, + "learning_rate": 9.652109000953007e-06, + "loss": 0.481, + "step": 6166 + }, + { + "epoch": 0.53, + "learning_rate": 9.649349088996922e-06, + "loss": 0.474, + "step": 6167 + }, + { + "epoch": 0.53, + "learning_rate": 9.646589203782944e-06, + "loss": 0.474, + "step": 6168 + }, + { + "epoch": 0.53, + "learning_rate": 9.643829345521546e-06, + "loss": 0.4812, + "step": 6169 + }, + { + "epoch": 0.53, + "learning_rate": 9.641069514423212e-06, + "loss": 0.4662, + "step": 6170 + }, + { + "epoch": 0.53, + "learning_rate": 9.63830971069841e-06, + "loss": 0.4751, + "step": 6171 + }, + { + "epoch": 0.53, + "learning_rate": 9.635549934557626e-06, + "loss": 0.4816, + "step": 6172 + }, + { + "epoch": 0.53, + "learning_rate": 9.632790186211321e-06, + "loss": 0.4732, + "step": 6173 + }, + { + "epoch": 0.53, + "learning_rate": 9.630030465869972e-06, + "loss": 0.4578, + "step": 6174 + }, + { + "epoch": 0.53, + "learning_rate": 9.627270773744043e-06, + "loss": 0.4806, + "step": 6175 + }, + { + "epoch": 0.53, + "learning_rate": 9.624511110043999e-06, + "loss": 0.4771, + "step": 6176 + }, + { + "epoch": 0.53, + "learning_rate": 9.621751474980308e-06, + "loss": 0.4751, + "step": 6177 + }, + { + "epoch": 0.53, + "learning_rate": 9.618991868763428e-06, + "loss": 0.4853, + "step": 6178 + }, + { + "epoch": 0.53, + "learning_rate": 9.61623229160382e-06, + "loss": 0.4701, + "step": 6179 + }, + { + "epoch": 0.53, + "learning_rate": 9.613472743711937e-06, + "loss": 0.4875, + "step": 6180 + }, + { + "epoch": 0.53, + "learning_rate": 9.610713225298238e-06, + "loss": 0.4865, + "step": 6181 + }, + { + "epoch": 0.53, + "learning_rate": 9.607953736573173e-06, + "loss": 0.4569, + "step": 6182 + }, + { + "epoch": 0.53, + "learning_rate": 9.605194277747193e-06, + "loss": 0.5042, + "step": 6183 + }, + { + "epoch": 0.53, + "learning_rate": 9.602434849030747e-06, + "loss": 0.4588, + "step": 6184 + }, + { + "epoch": 0.53, + "learning_rate": 9.599675450634273e-06, + "loss": 0.4904, + "step": 6185 + }, + { + "epoch": 0.53, + "learning_rate": 9.596916082768228e-06, + "loss": 0.4826, + "step": 6186 + }, + { + "epoch": 0.53, + "learning_rate": 9.594156745643043e-06, + "loss": 0.4766, + "step": 6187 + }, + { + "epoch": 0.53, + "learning_rate": 9.59139743946916e-06, + "loss": 0.4757, + "step": 6188 + }, + { + "epoch": 0.53, + "learning_rate": 9.58863816445701e-06, + "loss": 0.4814, + "step": 6189 + }, + { + "epoch": 0.53, + "learning_rate": 9.585878920817032e-06, + "loss": 0.4845, + "step": 6190 + }, + { + "epoch": 0.53, + "learning_rate": 9.58311970875966e-06, + "loss": 0.4909, + "step": 6191 + }, + { + "epoch": 0.53, + "learning_rate": 9.58036052849532e-06, + "loss": 0.4775, + "step": 6192 + }, + { + "epoch": 0.53, + "learning_rate": 9.577601380234434e-06, + "loss": 0.4571, + "step": 6193 + }, + { + "epoch": 0.53, + "learning_rate": 9.57484226418743e-06, + "loss": 0.4768, + "step": 6194 + }, + { + "epoch": 0.53, + "learning_rate": 9.572083180564734e-06, + "loss": 0.4771, + "step": 6195 + }, + { + "epoch": 0.53, + "learning_rate": 9.569324129576756e-06, + "loss": 0.4692, + "step": 6196 + }, + { + "epoch": 0.53, + "learning_rate": 9.566565111433923e-06, + "loss": 0.4704, + "step": 6197 + }, + { + "epoch": 0.53, + "learning_rate": 9.563806126346643e-06, + "loss": 0.4816, + "step": 6198 + }, + { + "epoch": 0.53, + "learning_rate": 9.561047174525324e-06, + "loss": 0.4768, + "step": 6199 + }, + { + "epoch": 0.53, + "learning_rate": 9.558288256180385e-06, + "loss": 0.466, + "step": 6200 + }, + { + "epoch": 0.53, + "learning_rate": 9.555529371522228e-06, + "loss": 0.4843, + "step": 6201 + }, + { + "epoch": 0.53, + "learning_rate": 9.552770520761256e-06, + "loss": 0.4738, + "step": 6202 + }, + { + "epoch": 0.53, + "learning_rate": 9.550011704107867e-06, + "loss": 0.4789, + "step": 6203 + }, + { + "epoch": 0.53, + "learning_rate": 9.54725292177247e-06, + "loss": 0.4887, + "step": 6204 + }, + { + "epoch": 0.53, + "learning_rate": 9.544494173965451e-06, + "loss": 0.4714, + "step": 6205 + }, + { + "epoch": 0.53, + "learning_rate": 9.541735460897211e-06, + "loss": 0.4918, + "step": 6206 + }, + { + "epoch": 0.53, + "learning_rate": 9.538976782778136e-06, + "loss": 0.4777, + "step": 6207 + }, + { + "epoch": 0.53, + "learning_rate": 9.536218139818615e-06, + "loss": 0.4894, + "step": 6208 + }, + { + "epoch": 0.53, + "learning_rate": 9.53345953222904e-06, + "loss": 0.4892, + "step": 6209 + }, + { + "epoch": 0.53, + "learning_rate": 9.530700960219787e-06, + "loss": 0.4747, + "step": 6210 + }, + { + "epoch": 0.53, + "learning_rate": 9.527942424001235e-06, + "loss": 0.449, + "step": 6211 + }, + { + "epoch": 0.53, + "learning_rate": 9.525183923783768e-06, + "loss": 0.4876, + "step": 6212 + }, + { + "epoch": 0.53, + "learning_rate": 9.522425459777753e-06, + "loss": 0.468, + "step": 6213 + }, + { + "epoch": 0.53, + "learning_rate": 9.519667032193569e-06, + "loss": 0.4926, + "step": 6214 + }, + { + "epoch": 0.53, + "learning_rate": 9.516908641241584e-06, + "loss": 0.4882, + "step": 6215 + }, + { + "epoch": 0.53, + "learning_rate": 9.51415028713216e-06, + "loss": 0.4694, + "step": 6216 + }, + { + "epoch": 0.53, + "learning_rate": 9.511391970075662e-06, + "loss": 0.4771, + "step": 6217 + }, + { + "epoch": 0.53, + "learning_rate": 9.508633690282456e-06, + "loss": 0.4454, + "step": 6218 + }, + { + "epoch": 0.53, + "learning_rate": 9.505875447962896e-06, + "loss": 0.4853, + "step": 6219 + }, + { + "epoch": 0.53, + "learning_rate": 9.503117243327336e-06, + "loss": 0.4843, + "step": 6220 + }, + { + "epoch": 0.53, + "learning_rate": 9.500359076586131e-06, + "loss": 0.4748, + "step": 6221 + }, + { + "epoch": 0.53, + "learning_rate": 9.497600947949625e-06, + "loss": 0.4751, + "step": 6222 + }, + { + "epoch": 0.53, + "learning_rate": 9.49484285762817e-06, + "loss": 0.467, + "step": 6223 + }, + { + "epoch": 0.53, + "learning_rate": 9.49208480583211e-06, + "loss": 0.4712, + "step": 6224 + }, + { + "epoch": 0.53, + "learning_rate": 9.489326792771781e-06, + "loss": 0.4563, + "step": 6225 + }, + { + "epoch": 0.53, + "learning_rate": 9.48656881865752e-06, + "loss": 0.4878, + "step": 6226 + }, + { + "epoch": 0.53, + "learning_rate": 9.48381088369967e-06, + "loss": 0.476, + "step": 6227 + }, + { + "epoch": 0.53, + "learning_rate": 9.481052988108556e-06, + "loss": 0.4657, + "step": 6228 + }, + { + "epoch": 0.53, + "learning_rate": 9.478295132094505e-06, + "loss": 0.4677, + "step": 6229 + }, + { + "epoch": 0.53, + "learning_rate": 9.47553731586785e-06, + "loss": 0.4587, + "step": 6230 + }, + { + "epoch": 0.53, + "learning_rate": 9.472779539638901e-06, + "loss": 0.4511, + "step": 6231 + }, + { + "epoch": 0.53, + "learning_rate": 9.47002180361799e-06, + "loss": 0.469, + "step": 6232 + }, + { + "epoch": 0.53, + "learning_rate": 9.46726410801543e-06, + "loss": 0.4849, + "step": 6233 + }, + { + "epoch": 0.53, + "learning_rate": 9.464506453041532e-06, + "loss": 0.4751, + "step": 6234 + }, + { + "epoch": 0.53, + "learning_rate": 9.461748838906606e-06, + "loss": 0.4923, + "step": 6235 + }, + { + "epoch": 0.53, + "learning_rate": 9.458991265820962e-06, + "loss": 0.4905, + "step": 6236 + }, + { + "epoch": 0.53, + "learning_rate": 9.456233733994906e-06, + "loss": 0.4865, + "step": 6237 + }, + { + "epoch": 0.53, + "learning_rate": 9.45347624363873e-06, + "loss": 0.4761, + "step": 6238 + }, + { + "epoch": 0.53, + "learning_rate": 9.450718794962742e-06, + "loss": 0.4512, + "step": 6239 + }, + { + "epoch": 0.53, + "learning_rate": 9.447961388177227e-06, + "loss": 0.4898, + "step": 6240 + }, + { + "epoch": 0.53, + "learning_rate": 9.445204023492484e-06, + "loss": 0.4407, + "step": 6241 + }, + { + "epoch": 0.53, + "learning_rate": 9.4424467011188e-06, + "loss": 0.4823, + "step": 6242 + }, + { + "epoch": 0.53, + "learning_rate": 9.439689421266456e-06, + "loss": 0.478, + "step": 6243 + }, + { + "epoch": 0.53, + "learning_rate": 9.436932184145737e-06, + "loss": 0.4615, + "step": 6244 + }, + { + "epoch": 0.53, + "learning_rate": 9.434174989966917e-06, + "loss": 0.4897, + "step": 6245 + }, + { + "epoch": 0.53, + "learning_rate": 9.43141783894028e-06, + "loss": 0.4927, + "step": 6246 + }, + { + "epoch": 0.53, + "learning_rate": 9.428660731276089e-06, + "loss": 0.4566, + "step": 6247 + }, + { + "epoch": 0.53, + "learning_rate": 9.425903667184619e-06, + "loss": 0.4581, + "step": 6248 + }, + { + "epoch": 0.53, + "learning_rate": 9.423146646876126e-06, + "loss": 0.4764, + "step": 6249 + }, + { + "epoch": 0.53, + "learning_rate": 9.42038967056088e-06, + "loss": 0.4642, + "step": 6250 + }, + { + "epoch": 0.53, + "learning_rate": 9.417632738449143e-06, + "loss": 0.4942, + "step": 6251 + }, + { + "epoch": 0.53, + "learning_rate": 9.41487585075116e-06, + "loss": 0.4767, + "step": 6252 + }, + { + "epoch": 0.53, + "learning_rate": 9.41211900767719e-06, + "loss": 0.4783, + "step": 6253 + }, + { + "epoch": 0.53, + "learning_rate": 9.409362209437474e-06, + "loss": 0.479, + "step": 6254 + }, + { + "epoch": 0.53, + "learning_rate": 9.406605456242265e-06, + "loss": 0.4639, + "step": 6255 + }, + { + "epoch": 0.53, + "learning_rate": 9.403848748301802e-06, + "loss": 0.4875, + "step": 6256 + }, + { + "epoch": 0.53, + "learning_rate": 9.401092085826325e-06, + "loss": 0.4694, + "step": 6257 + }, + { + "epoch": 0.53, + "learning_rate": 9.398335469026058e-06, + "loss": 0.4753, + "step": 6258 + }, + { + "epoch": 0.53, + "learning_rate": 9.395578898111243e-06, + "loss": 0.4751, + "step": 6259 + }, + { + "epoch": 0.53, + "learning_rate": 9.392822373292108e-06, + "loss": 0.4717, + "step": 6260 + }, + { + "epoch": 0.53, + "learning_rate": 9.390065894778872e-06, + "loss": 0.4929, + "step": 6261 + }, + { + "epoch": 0.53, + "learning_rate": 9.387309462781759e-06, + "loss": 0.475, + "step": 6262 + }, + { + "epoch": 0.53, + "learning_rate": 9.38455307751098e-06, + "loss": 0.4837, + "step": 6263 + }, + { + "epoch": 0.53, + "learning_rate": 9.381796739176754e-06, + "loss": 0.4673, + "step": 6264 + }, + { + "epoch": 0.53, + "learning_rate": 9.379040447989292e-06, + "loss": 0.4791, + "step": 6265 + }, + { + "epoch": 0.53, + "learning_rate": 9.3762842041588e-06, + "loss": 0.486, + "step": 6266 + }, + { + "epoch": 0.53, + "learning_rate": 9.373528007895473e-06, + "loss": 0.453, + "step": 6267 + }, + { + "epoch": 0.53, + "learning_rate": 9.370771859409514e-06, + "loss": 0.4836, + "step": 6268 + }, + { + "epoch": 0.53, + "learning_rate": 9.368015758911126e-06, + "loss": 0.4682, + "step": 6269 + }, + { + "epoch": 0.53, + "learning_rate": 9.365259706610491e-06, + "loss": 0.4841, + "step": 6270 + }, + { + "epoch": 0.53, + "learning_rate": 9.362503702717803e-06, + "loss": 0.4676, + "step": 6271 + }, + { + "epoch": 0.53, + "learning_rate": 9.359747747443241e-06, + "loss": 0.4645, + "step": 6272 + }, + { + "epoch": 0.53, + "learning_rate": 9.356991840996991e-06, + "loss": 0.4624, + "step": 6273 + }, + { + "epoch": 0.53, + "learning_rate": 9.354235983589229e-06, + "loss": 0.4834, + "step": 6274 + }, + { + "epoch": 0.54, + "learning_rate": 9.351480175430126e-06, + "loss": 0.4747, + "step": 6275 + }, + { + "epoch": 0.54, + "learning_rate": 9.348724416729852e-06, + "loss": 0.4625, + "step": 6276 + }, + { + "epoch": 0.54, + "learning_rate": 9.34596870769857e-06, + "loss": 0.4691, + "step": 6277 + }, + { + "epoch": 0.54, + "learning_rate": 9.34321304854645e-06, + "loss": 0.4711, + "step": 6278 + }, + { + "epoch": 0.54, + "learning_rate": 9.34045743948364e-06, + "loss": 0.4869, + "step": 6279 + }, + { + "epoch": 0.54, + "learning_rate": 9.337701880720303e-06, + "loss": 0.4757, + "step": 6280 + }, + { + "epoch": 0.54, + "learning_rate": 9.334946372466582e-06, + "loss": 0.5034, + "step": 6281 + }, + { + "epoch": 0.54, + "learning_rate": 9.332190914932629e-06, + "loss": 0.4926, + "step": 6282 + }, + { + "epoch": 0.54, + "learning_rate": 9.329435508328587e-06, + "loss": 0.4664, + "step": 6283 + }, + { + "epoch": 0.54, + "learning_rate": 9.326680152864592e-06, + "loss": 0.4675, + "step": 6284 + }, + { + "epoch": 0.54, + "learning_rate": 9.323924848750777e-06, + "loss": 0.4657, + "step": 6285 + }, + { + "epoch": 0.54, + "learning_rate": 9.321169596197274e-06, + "loss": 0.473, + "step": 6286 + }, + { + "epoch": 0.54, + "learning_rate": 9.318414395414216e-06, + "loss": 0.4819, + "step": 6287 + }, + { + "epoch": 0.54, + "learning_rate": 9.31565924661172e-06, + "loss": 0.464, + "step": 6288 + }, + { + "epoch": 0.54, + "learning_rate": 9.312904149999909e-06, + "loss": 0.4602, + "step": 6289 + }, + { + "epoch": 0.54, + "learning_rate": 9.310149105788892e-06, + "loss": 0.4684, + "step": 6290 + }, + { + "epoch": 0.54, + "learning_rate": 9.307394114188786e-06, + "loss": 0.4621, + "step": 6291 + }, + { + "epoch": 0.54, + "learning_rate": 9.304639175409699e-06, + "loss": 0.4903, + "step": 6292 + }, + { + "epoch": 0.54, + "learning_rate": 9.30188428966173e-06, + "loss": 0.4553, + "step": 6293 + }, + { + "epoch": 0.54, + "learning_rate": 9.299129457154979e-06, + "loss": 0.4692, + "step": 6294 + }, + { + "epoch": 0.54, + "learning_rate": 9.29637467809954e-06, + "loss": 0.4889, + "step": 6295 + }, + { + "epoch": 0.54, + "learning_rate": 9.293619952705509e-06, + "loss": 0.467, + "step": 6296 + }, + { + "epoch": 0.54, + "learning_rate": 9.290865281182965e-06, + "loss": 0.4887, + "step": 6297 + }, + { + "epoch": 0.54, + "learning_rate": 9.288110663742001e-06, + "loss": 0.4659, + "step": 6298 + }, + { + "epoch": 0.54, + "learning_rate": 9.285356100592685e-06, + "loss": 0.4666, + "step": 6299 + }, + { + "epoch": 0.54, + "learning_rate": 9.282601591945097e-06, + "loss": 0.4914, + "step": 6300 + }, + { + "epoch": 0.54, + "learning_rate": 9.279847138009308e-06, + "loss": 0.4639, + "step": 6301 + }, + { + "epoch": 0.54, + "learning_rate": 9.277092738995385e-06, + "loss": 0.4626, + "step": 6302 + }, + { + "epoch": 0.54, + "learning_rate": 9.274338395113383e-06, + "loss": 0.4678, + "step": 6303 + }, + { + "epoch": 0.54, + "learning_rate": 9.271584106573364e-06, + "loss": 0.4659, + "step": 6304 + }, + { + "epoch": 0.54, + "learning_rate": 9.268829873585388e-06, + "loss": 0.4773, + "step": 6305 + }, + { + "epoch": 0.54, + "learning_rate": 9.266075696359495e-06, + "loss": 0.4681, + "step": 6306 + }, + { + "epoch": 0.54, + "learning_rate": 9.263321575105734e-06, + "loss": 0.5068, + "step": 6307 + }, + { + "epoch": 0.54, + "learning_rate": 9.260567510034146e-06, + "loss": 0.4725, + "step": 6308 + }, + { + "epoch": 0.54, + "learning_rate": 9.257813501354761e-06, + "loss": 0.4658, + "step": 6309 + }, + { + "epoch": 0.54, + "learning_rate": 9.255059549277624e-06, + "loss": 0.4885, + "step": 6310 + }, + { + "epoch": 0.54, + "learning_rate": 9.252305654012753e-06, + "loss": 0.4594, + "step": 6311 + }, + { + "epoch": 0.54, + "learning_rate": 9.249551815770177e-06, + "loss": 0.4734, + "step": 6312 + }, + { + "epoch": 0.54, + "learning_rate": 9.246798034759907e-06, + "loss": 0.4914, + "step": 6313 + }, + { + "epoch": 0.54, + "learning_rate": 9.244044311191968e-06, + "loss": 0.4739, + "step": 6314 + }, + { + "epoch": 0.54, + "learning_rate": 9.241290645276364e-06, + "loss": 0.4776, + "step": 6315 + }, + { + "epoch": 0.54, + "learning_rate": 9.238537037223106e-06, + "loss": 0.4892, + "step": 6316 + }, + { + "epoch": 0.54, + "learning_rate": 9.235783487242188e-06, + "loss": 0.4576, + "step": 6317 + }, + { + "epoch": 0.54, + "learning_rate": 9.233029995543612e-06, + "loss": 0.4942, + "step": 6318 + }, + { + "epoch": 0.54, + "learning_rate": 9.230276562337374e-06, + "loss": 0.4477, + "step": 6319 + }, + { + "epoch": 0.54, + "learning_rate": 9.227523187833456e-06, + "loss": 0.4603, + "step": 6320 + }, + { + "epoch": 0.54, + "learning_rate": 9.224769872241848e-06, + "loss": 0.4894, + "step": 6321 + }, + { + "epoch": 0.54, + "learning_rate": 9.222016615772525e-06, + "loss": 0.4503, + "step": 6322 + }, + { + "epoch": 0.54, + "learning_rate": 9.21926341863546e-06, + "loss": 0.4716, + "step": 6323 + }, + { + "epoch": 0.54, + "learning_rate": 9.216510281040627e-06, + "loss": 0.4863, + "step": 6324 + }, + { + "epoch": 0.54, + "learning_rate": 9.213757203197994e-06, + "loss": 0.4874, + "step": 6325 + }, + { + "epoch": 0.54, + "learning_rate": 9.211004185317515e-06, + "loss": 0.4689, + "step": 6326 + }, + { + "epoch": 0.54, + "learning_rate": 9.208251227609151e-06, + "loss": 0.4886, + "step": 6327 + }, + { + "epoch": 0.54, + "learning_rate": 9.205498330282857e-06, + "loss": 0.4841, + "step": 6328 + }, + { + "epoch": 0.54, + "learning_rate": 9.202745493548576e-06, + "loss": 0.4793, + "step": 6329 + }, + { + "epoch": 0.54, + "learning_rate": 9.199992717616253e-06, + "loss": 0.4929, + "step": 6330 + }, + { + "epoch": 0.54, + "learning_rate": 9.197240002695826e-06, + "loss": 0.4762, + "step": 6331 + }, + { + "epoch": 0.54, + "learning_rate": 9.194487348997223e-06, + "loss": 0.4547, + "step": 6332 + }, + { + "epoch": 0.54, + "learning_rate": 9.19173475673038e-06, + "loss": 0.4797, + "step": 6333 + }, + { + "epoch": 0.54, + "learning_rate": 9.188982226105222e-06, + "loss": 0.4793, + "step": 6334 + }, + { + "epoch": 0.54, + "learning_rate": 9.186229757331663e-06, + "loss": 0.4631, + "step": 6335 + }, + { + "epoch": 0.54, + "learning_rate": 9.183477350619617e-06, + "loss": 0.4591, + "step": 6336 + }, + { + "epoch": 0.54, + "learning_rate": 9.180725006179002e-06, + "loss": 0.4615, + "step": 6337 + }, + { + "epoch": 0.54, + "learning_rate": 9.177972724219715e-06, + "loss": 0.4645, + "step": 6338 + }, + { + "epoch": 0.54, + "learning_rate": 9.175220504951664e-06, + "loss": 0.4772, + "step": 6339 + }, + { + "epoch": 0.54, + "learning_rate": 9.17246834858474e-06, + "loss": 0.4822, + "step": 6340 + }, + { + "epoch": 0.54, + "learning_rate": 9.16971625532883e-06, + "loss": 0.4534, + "step": 6341 + }, + { + "epoch": 0.54, + "learning_rate": 9.166964225393826e-06, + "loss": 0.4966, + "step": 6342 + }, + { + "epoch": 0.54, + "learning_rate": 9.164212258989611e-06, + "loss": 0.4871, + "step": 6343 + }, + { + "epoch": 0.54, + "learning_rate": 9.161460356326057e-06, + "loss": 0.4715, + "step": 6344 + }, + { + "epoch": 0.54, + "learning_rate": 9.158708517613038e-06, + "loss": 0.4875, + "step": 6345 + }, + { + "epoch": 0.54, + "learning_rate": 9.155956743060417e-06, + "loss": 0.4508, + "step": 6346 + }, + { + "epoch": 0.54, + "learning_rate": 9.15320503287806e-06, + "loss": 0.4629, + "step": 6347 + }, + { + "epoch": 0.54, + "learning_rate": 9.150453387275823e-06, + "loss": 0.4889, + "step": 6348 + }, + { + "epoch": 0.54, + "learning_rate": 9.147701806463559e-06, + "loss": 0.4862, + "step": 6349 + }, + { + "epoch": 0.54, + "learning_rate": 9.144950290651109e-06, + "loss": 0.502, + "step": 6350 + }, + { + "epoch": 0.54, + "learning_rate": 9.14219884004832e-06, + "loss": 0.4505, + "step": 6351 + }, + { + "epoch": 0.54, + "learning_rate": 9.139447454865034e-06, + "loss": 0.4658, + "step": 6352 + }, + { + "epoch": 0.54, + "learning_rate": 9.136696135311075e-06, + "loss": 0.4701, + "step": 6353 + }, + { + "epoch": 0.54, + "learning_rate": 9.133944881596273e-06, + "loss": 0.4701, + "step": 6354 + }, + { + "epoch": 0.54, + "learning_rate": 9.131193693930447e-06, + "loss": 0.4937, + "step": 6355 + }, + { + "epoch": 0.54, + "learning_rate": 9.128442572523418e-06, + "loss": 0.4526, + "step": 6356 + }, + { + "epoch": 0.54, + "learning_rate": 9.125691517585e-06, + "loss": 0.4731, + "step": 6357 + }, + { + "epoch": 0.54, + "learning_rate": 9.122940529324997e-06, + "loss": 0.4538, + "step": 6358 + }, + { + "epoch": 0.54, + "learning_rate": 9.120189607953206e-06, + "loss": 0.4788, + "step": 6359 + }, + { + "epoch": 0.54, + "learning_rate": 9.117438753679433e-06, + "loss": 0.4669, + "step": 6360 + }, + { + "epoch": 0.54, + "learning_rate": 9.114687966713465e-06, + "loss": 0.4699, + "step": 6361 + }, + { + "epoch": 0.54, + "learning_rate": 9.111937247265088e-06, + "loss": 0.4706, + "step": 6362 + }, + { + "epoch": 0.54, + "learning_rate": 9.109186595544085e-06, + "loss": 0.4566, + "step": 6363 + }, + { + "epoch": 0.54, + "learning_rate": 9.106436011760229e-06, + "loss": 0.4623, + "step": 6364 + }, + { + "epoch": 0.54, + "learning_rate": 9.103685496123294e-06, + "loss": 0.4611, + "step": 6365 + }, + { + "epoch": 0.54, + "learning_rate": 9.100935048843047e-06, + "loss": 0.4778, + "step": 6366 + }, + { + "epoch": 0.54, + "learning_rate": 9.098184670129244e-06, + "loss": 0.4588, + "step": 6367 + }, + { + "epoch": 0.54, + "learning_rate": 9.095434360191642e-06, + "loss": 0.467, + "step": 6368 + }, + { + "epoch": 0.54, + "learning_rate": 9.092684119239996e-06, + "loss": 0.4931, + "step": 6369 + }, + { + "epoch": 0.54, + "learning_rate": 9.089933947484048e-06, + "loss": 0.4698, + "step": 6370 + }, + { + "epoch": 0.54, + "learning_rate": 9.087183845133532e-06, + "loss": 0.4695, + "step": 6371 + }, + { + "epoch": 0.54, + "learning_rate": 9.084433812398191e-06, + "loss": 0.4704, + "step": 6372 + }, + { + "epoch": 0.54, + "learning_rate": 9.081683849487745e-06, + "loss": 0.4875, + "step": 6373 + }, + { + "epoch": 0.54, + "learning_rate": 9.078933956611925e-06, + "loss": 0.4816, + "step": 6374 + }, + { + "epoch": 0.54, + "learning_rate": 9.076184133980449e-06, + "loss": 0.4694, + "step": 6375 + }, + { + "epoch": 0.54, + "learning_rate": 9.073434381803025e-06, + "loss": 0.4893, + "step": 6376 + }, + { + "epoch": 0.54, + "learning_rate": 9.070684700289365e-06, + "loss": 0.4753, + "step": 6377 + }, + { + "epoch": 0.54, + "learning_rate": 9.067935089649167e-06, + "loss": 0.4821, + "step": 6378 + }, + { + "epoch": 0.54, + "learning_rate": 9.065185550092134e-06, + "loss": 0.4813, + "step": 6379 + }, + { + "epoch": 0.54, + "learning_rate": 9.06243608182795e-06, + "loss": 0.4646, + "step": 6380 + }, + { + "epoch": 0.54, + "learning_rate": 9.059686685066308e-06, + "loss": 0.4855, + "step": 6381 + }, + { + "epoch": 0.54, + "learning_rate": 9.056937360016881e-06, + "loss": 0.4576, + "step": 6382 + }, + { + "epoch": 0.54, + "learning_rate": 9.05418810688935e-06, + "loss": 0.4715, + "step": 6383 + }, + { + "epoch": 0.54, + "learning_rate": 9.051438925893385e-06, + "loss": 0.4708, + "step": 6384 + }, + { + "epoch": 0.54, + "learning_rate": 9.048689817238645e-06, + "loss": 0.4851, + "step": 6385 + }, + { + "epoch": 0.54, + "learning_rate": 9.045940781134794e-06, + "loss": 0.475, + "step": 6386 + }, + { + "epoch": 0.54, + "learning_rate": 9.043191817791476e-06, + "loss": 0.4602, + "step": 6387 + }, + { + "epoch": 0.54, + "learning_rate": 9.04044292741835e-06, + "loss": 0.4751, + "step": 6388 + }, + { + "epoch": 0.54, + "learning_rate": 9.03769411022505e-06, + "loss": 0.4812, + "step": 6389 + }, + { + "epoch": 0.54, + "learning_rate": 9.034945366421219e-06, + "loss": 0.4719, + "step": 6390 + }, + { + "epoch": 0.54, + "learning_rate": 9.032196696216477e-06, + "loss": 0.4703, + "step": 6391 + }, + { + "epoch": 0.55, + "learning_rate": 9.029448099820458e-06, + "loss": 0.4979, + "step": 6392 + }, + { + "epoch": 0.55, + "learning_rate": 9.026699577442779e-06, + "loss": 0.4843, + "step": 6393 + }, + { + "epoch": 0.55, + "learning_rate": 9.023951129293053e-06, + "loss": 0.482, + "step": 6394 + }, + { + "epoch": 0.55, + "learning_rate": 9.021202755580892e-06, + "loss": 0.492, + "step": 6395 + }, + { + "epoch": 0.55, + "learning_rate": 9.018454456515889e-06, + "loss": 0.4814, + "step": 6396 + }, + { + "epoch": 0.55, + "learning_rate": 9.015706232307653e-06, + "loss": 0.4877, + "step": 6397 + }, + { + "epoch": 0.55, + "learning_rate": 9.012958083165766e-06, + "loss": 0.4727, + "step": 6398 + }, + { + "epoch": 0.55, + "learning_rate": 9.010210009299818e-06, + "loss": 0.4699, + "step": 6399 + }, + { + "epoch": 0.55, + "learning_rate": 9.007462010919387e-06, + "loss": 0.4559, + "step": 6400 + }, + { + "epoch": 0.55, + "learning_rate": 9.004714088234042e-06, + "loss": 0.47, + "step": 6401 + }, + { + "epoch": 0.55, + "learning_rate": 9.001966241453362e-06, + "loss": 0.4718, + "step": 6402 + }, + { + "epoch": 0.55, + "learning_rate": 8.9992184707869e-06, + "loss": 0.4788, + "step": 6403 + }, + { + "epoch": 0.55, + "learning_rate": 8.996470776444217e-06, + "loss": 0.4702, + "step": 6404 + }, + { + "epoch": 0.55, + "learning_rate": 8.993723158634859e-06, + "loss": 0.4804, + "step": 6405 + }, + { + "epoch": 0.55, + "learning_rate": 8.990975617568379e-06, + "loss": 0.4839, + "step": 6406 + }, + { + "epoch": 0.55, + "learning_rate": 8.988228153454308e-06, + "loss": 0.4778, + "step": 6407 + }, + { + "epoch": 0.55, + "learning_rate": 8.985480766502183e-06, + "loss": 0.4814, + "step": 6408 + }, + { + "epoch": 0.55, + "learning_rate": 8.98273345692153e-06, + "loss": 0.4572, + "step": 6409 + }, + { + "epoch": 0.55, + "learning_rate": 8.979986224921868e-06, + "loss": 0.4853, + "step": 6410 + }, + { + "epoch": 0.55, + "learning_rate": 8.977239070712717e-06, + "loss": 0.4634, + "step": 6411 + }, + { + "epoch": 0.55, + "learning_rate": 8.974491994503585e-06, + "loss": 0.4664, + "step": 6412 + }, + { + "epoch": 0.55, + "learning_rate": 8.971744996503975e-06, + "loss": 0.4695, + "step": 6413 + }, + { + "epoch": 0.55, + "learning_rate": 8.968998076923381e-06, + "loss": 0.4595, + "step": 6414 + }, + { + "epoch": 0.55, + "learning_rate": 8.966251235971302e-06, + "loss": 0.4492, + "step": 6415 + }, + { + "epoch": 0.55, + "learning_rate": 8.963504473857218e-06, + "loss": 0.4637, + "step": 6416 + }, + { + "epoch": 0.55, + "learning_rate": 8.960757790790613e-06, + "loss": 0.4776, + "step": 6417 + }, + { + "epoch": 0.55, + "learning_rate": 8.958011186980954e-06, + "loss": 0.471, + "step": 6418 + }, + { + "epoch": 0.55, + "learning_rate": 8.95526466263771e-06, + "loss": 0.4739, + "step": 6419 + }, + { + "epoch": 0.55, + "learning_rate": 8.95251821797035e-06, + "loss": 0.5049, + "step": 6420 + }, + { + "epoch": 0.55, + "learning_rate": 8.94977185318832e-06, + "loss": 0.4594, + "step": 6421 + }, + { + "epoch": 0.55, + "learning_rate": 8.947025568501075e-06, + "loss": 0.464, + "step": 6422 + }, + { + "epoch": 0.55, + "learning_rate": 8.944279364118059e-06, + "loss": 0.4919, + "step": 6423 + }, + { + "epoch": 0.55, + "learning_rate": 8.9415332402487e-06, + "loss": 0.4861, + "step": 6424 + }, + { + "epoch": 0.55, + "learning_rate": 8.938787197102437e-06, + "loss": 0.4652, + "step": 6425 + }, + { + "epoch": 0.55, + "learning_rate": 8.936041234888693e-06, + "loss": 0.4617, + "step": 6426 + }, + { + "epoch": 0.55, + "learning_rate": 8.933295353816888e-06, + "loss": 0.4679, + "step": 6427 + }, + { + "epoch": 0.55, + "learning_rate": 8.930549554096429e-06, + "loss": 0.4842, + "step": 6428 + }, + { + "epoch": 0.55, + "learning_rate": 8.927803835936729e-06, + "loss": 0.4601, + "step": 6429 + }, + { + "epoch": 0.55, + "learning_rate": 8.925058199547183e-06, + "loss": 0.4781, + "step": 6430 + }, + { + "epoch": 0.55, + "learning_rate": 8.92231264513719e-06, + "loss": 0.5146, + "step": 6431 + }, + { + "epoch": 0.55, + "learning_rate": 8.91956717291613e-06, + "loss": 0.4532, + "step": 6432 + }, + { + "epoch": 0.55, + "learning_rate": 8.916821783093386e-06, + "loss": 0.4784, + "step": 6433 + }, + { + "epoch": 0.55, + "learning_rate": 8.914076475878342e-06, + "loss": 0.4695, + "step": 6434 + }, + { + "epoch": 0.55, + "learning_rate": 8.911331251480357e-06, + "loss": 0.466, + "step": 6435 + }, + { + "epoch": 0.55, + "learning_rate": 8.908586110108794e-06, + "loss": 0.488, + "step": 6436 + }, + { + "epoch": 0.55, + "learning_rate": 8.905841051973009e-06, + "loss": 0.4777, + "step": 6437 + }, + { + "epoch": 0.55, + "learning_rate": 8.903096077282356e-06, + "loss": 0.4698, + "step": 6438 + }, + { + "epoch": 0.55, + "learning_rate": 8.900351186246177e-06, + "loss": 0.4595, + "step": 6439 + }, + { + "epoch": 0.55, + "learning_rate": 8.897606379073806e-06, + "loss": 0.4815, + "step": 6440 + }, + { + "epoch": 0.55, + "learning_rate": 8.894861655974575e-06, + "loss": 0.4935, + "step": 6441 + }, + { + "epoch": 0.55, + "learning_rate": 8.892117017157805e-06, + "loss": 0.467, + "step": 6442 + }, + { + "epoch": 0.55, + "learning_rate": 8.88937246283282e-06, + "loss": 0.4759, + "step": 6443 + }, + { + "epoch": 0.55, + "learning_rate": 8.886627993208929e-06, + "loss": 0.4697, + "step": 6444 + }, + { + "epoch": 0.55, + "learning_rate": 8.883883608495433e-06, + "loss": 0.4691, + "step": 6445 + }, + { + "epoch": 0.55, + "learning_rate": 8.88113930890163e-06, + "loss": 0.4682, + "step": 6446 + }, + { + "epoch": 0.55, + "learning_rate": 8.87839509463682e-06, + "loss": 0.4867, + "step": 6447 + }, + { + "epoch": 0.55, + "learning_rate": 8.87565096591028e-06, + "loss": 0.457, + "step": 6448 + }, + { + "epoch": 0.55, + "learning_rate": 8.872906922931293e-06, + "loss": 0.492, + "step": 6449 + }, + { + "epoch": 0.55, + "learning_rate": 8.870162965909127e-06, + "loss": 0.4872, + "step": 6450 + }, + { + "epoch": 0.55, + "learning_rate": 8.867419095053047e-06, + "loss": 0.4781, + "step": 6451 + }, + { + "epoch": 0.55, + "learning_rate": 8.864675310572323e-06, + "loss": 0.4737, + "step": 6452 + }, + { + "epoch": 0.55, + "learning_rate": 8.861931612676197e-06, + "loss": 0.4543, + "step": 6453 + }, + { + "epoch": 0.55, + "learning_rate": 8.859188001573916e-06, + "loss": 0.4781, + "step": 6454 + }, + { + "epoch": 0.55, + "learning_rate": 8.856444477474723e-06, + "loss": 0.474, + "step": 6455 + }, + { + "epoch": 0.55, + "learning_rate": 8.853701040587843e-06, + "loss": 0.4575, + "step": 6456 + }, + { + "epoch": 0.55, + "learning_rate": 8.850957691122511e-06, + "loss": 0.4876, + "step": 6457 + }, + { + "epoch": 0.55, + "learning_rate": 8.848214429287945e-06, + "loss": 0.482, + "step": 6458 + }, + { + "epoch": 0.55, + "learning_rate": 8.845471255293351e-06, + "loss": 0.4941, + "step": 6459 + }, + { + "epoch": 0.55, + "learning_rate": 8.842728169347938e-06, + "loss": 0.4964, + "step": 6460 + }, + { + "epoch": 0.55, + "learning_rate": 8.83998517166091e-06, + "loss": 0.4641, + "step": 6461 + }, + { + "epoch": 0.55, + "learning_rate": 8.837242262441457e-06, + "loss": 0.4856, + "step": 6462 + }, + { + "epoch": 0.55, + "learning_rate": 8.834499441898761e-06, + "loss": 0.4629, + "step": 6463 + }, + { + "epoch": 0.55, + "learning_rate": 8.831756710242006e-06, + "loss": 0.4586, + "step": 6464 + }, + { + "epoch": 0.55, + "learning_rate": 8.829014067680355e-06, + "loss": 0.4664, + "step": 6465 + }, + { + "epoch": 0.55, + "learning_rate": 8.826271514422983e-06, + "loss": 0.4758, + "step": 6466 + }, + { + "epoch": 0.55, + "learning_rate": 8.823529050679049e-06, + "loss": 0.4693, + "step": 6467 + }, + { + "epoch": 0.55, + "learning_rate": 8.820786676657698e-06, + "loss": 0.4845, + "step": 6468 + }, + { + "epoch": 0.55, + "learning_rate": 8.818044392568076e-06, + "loss": 0.4707, + "step": 6469 + }, + { + "epoch": 0.55, + "learning_rate": 8.815302198619328e-06, + "loss": 0.4919, + "step": 6470 + }, + { + "epoch": 0.55, + "learning_rate": 8.81256009502058e-06, + "loss": 0.475, + "step": 6471 + }, + { + "epoch": 0.55, + "learning_rate": 8.809818081980954e-06, + "loss": 0.4698, + "step": 6472 + }, + { + "epoch": 0.55, + "learning_rate": 8.807076159709572e-06, + "loss": 0.4548, + "step": 6473 + }, + { + "epoch": 0.55, + "learning_rate": 8.804334328415539e-06, + "loss": 0.4612, + "step": 6474 + }, + { + "epoch": 0.55, + "learning_rate": 8.801592588307964e-06, + "loss": 0.4819, + "step": 6475 + }, + { + "epoch": 0.55, + "learning_rate": 8.798850939595942e-06, + "loss": 0.4632, + "step": 6476 + }, + { + "epoch": 0.55, + "learning_rate": 8.796109382488561e-06, + "loss": 0.4807, + "step": 6477 + }, + { + "epoch": 0.55, + "learning_rate": 8.793367917194906e-06, + "loss": 0.4627, + "step": 6478 + }, + { + "epoch": 0.55, + "learning_rate": 8.790626543924048e-06, + "loss": 0.4812, + "step": 6479 + }, + { + "epoch": 0.55, + "learning_rate": 8.787885262885062e-06, + "loss": 0.4797, + "step": 6480 + }, + { + "epoch": 0.55, + "learning_rate": 8.785144074287006e-06, + "loss": 0.4535, + "step": 6481 + }, + { + "epoch": 0.55, + "learning_rate": 8.782402978338936e-06, + "loss": 0.4688, + "step": 6482 + }, + { + "epoch": 0.55, + "learning_rate": 8.779661975249893e-06, + "loss": 0.4502, + "step": 6483 + }, + { + "epoch": 0.55, + "learning_rate": 8.776921065228924e-06, + "loss": 0.4625, + "step": 6484 + }, + { + "epoch": 0.55, + "learning_rate": 8.774180248485065e-06, + "loss": 0.4842, + "step": 6485 + }, + { + "epoch": 0.55, + "learning_rate": 8.771439525227335e-06, + "loss": 0.4588, + "step": 6486 + }, + { + "epoch": 0.55, + "learning_rate": 8.768698895664757e-06, + "loss": 0.459, + "step": 6487 + }, + { + "epoch": 0.55, + "learning_rate": 8.765958360006339e-06, + "loss": 0.4659, + "step": 6488 + }, + { + "epoch": 0.55, + "learning_rate": 8.763217918461089e-06, + "loss": 0.4895, + "step": 6489 + }, + { + "epoch": 0.55, + "learning_rate": 8.760477571238006e-06, + "loss": 0.4673, + "step": 6490 + }, + { + "epoch": 0.55, + "learning_rate": 8.75773731854608e-06, + "loss": 0.46, + "step": 6491 + }, + { + "epoch": 0.55, + "learning_rate": 8.754997160594288e-06, + "loss": 0.4705, + "step": 6492 + }, + { + "epoch": 0.55, + "learning_rate": 8.75225709759161e-06, + "loss": 0.5027, + "step": 6493 + }, + { + "epoch": 0.55, + "learning_rate": 8.74951712974702e-06, + "loss": 0.4413, + "step": 6494 + }, + { + "epoch": 0.55, + "learning_rate": 8.74677725726947e-06, + "loss": 0.4759, + "step": 6495 + }, + { + "epoch": 0.55, + "learning_rate": 8.744037480367922e-06, + "loss": 0.4763, + "step": 6496 + }, + { + "epoch": 0.55, + "learning_rate": 8.741297799251314e-06, + "loss": 0.4715, + "step": 6497 + }, + { + "epoch": 0.55, + "learning_rate": 8.738558214128594e-06, + "loss": 0.4616, + "step": 6498 + }, + { + "epoch": 0.55, + "learning_rate": 8.735818725208692e-06, + "loss": 0.4713, + "step": 6499 + }, + { + "epoch": 0.55, + "learning_rate": 8.733079332700532e-06, + "loss": 0.466, + "step": 6500 + }, + { + "epoch": 0.55, + "learning_rate": 8.73034003681303e-06, + "loss": 0.455, + "step": 6501 + }, + { + "epoch": 0.55, + "learning_rate": 8.727600837755095e-06, + "loss": 0.4792, + "step": 6502 + }, + { + "epoch": 0.55, + "learning_rate": 8.724861735735635e-06, + "loss": 0.4589, + "step": 6503 + }, + { + "epoch": 0.55, + "learning_rate": 8.722122730963542e-06, + "loss": 0.4549, + "step": 6504 + }, + { + "epoch": 0.55, + "learning_rate": 8.719383823647708e-06, + "loss": 0.4839, + "step": 6505 + }, + { + "epoch": 0.55, + "learning_rate": 8.716645013997003e-06, + "loss": 0.4589, + "step": 6506 + }, + { + "epoch": 0.55, + "learning_rate": 8.71390630222031e-06, + "loss": 0.4554, + "step": 6507 + }, + { + "epoch": 0.55, + "learning_rate": 8.711167688526495e-06, + "loss": 0.4523, + "step": 6508 + }, + { + "epoch": 0.55, + "learning_rate": 8.70842917312441e-06, + "loss": 0.4894, + "step": 6509 + }, + { + "epoch": 0.56, + "learning_rate": 8.705690756222909e-06, + "loss": 0.4456, + "step": 6510 + }, + { + "epoch": 0.56, + "learning_rate": 8.702952438030832e-06, + "loss": 0.4682, + "step": 6511 + }, + { + "epoch": 0.56, + "learning_rate": 8.700214218757021e-06, + "loss": 0.4607, + "step": 6512 + }, + { + "epoch": 0.56, + "learning_rate": 8.697476098610299e-06, + "loss": 0.4763, + "step": 6513 + }, + { + "epoch": 0.56, + "learning_rate": 8.694738077799487e-06, + "loss": 0.4783, + "step": 6514 + }, + { + "epoch": 0.56, + "learning_rate": 8.692000156533395e-06, + "loss": 0.4731, + "step": 6515 + }, + { + "epoch": 0.56, + "learning_rate": 8.689262335020836e-06, + "loss": 0.4767, + "step": 6516 + }, + { + "epoch": 0.56, + "learning_rate": 8.686524613470603e-06, + "loss": 0.4897, + "step": 6517 + }, + { + "epoch": 0.56, + "learning_rate": 8.683786992091488e-06, + "loss": 0.4802, + "step": 6518 + }, + { + "epoch": 0.56, + "learning_rate": 8.68104947109227e-06, + "loss": 0.4711, + "step": 6519 + }, + { + "epoch": 0.56, + "learning_rate": 8.678312050681724e-06, + "loss": 0.4675, + "step": 6520 + }, + { + "epoch": 0.56, + "learning_rate": 8.675574731068622e-06, + "loss": 0.467, + "step": 6521 + }, + { + "epoch": 0.56, + "learning_rate": 8.672837512461718e-06, + "loss": 0.4695, + "step": 6522 + }, + { + "epoch": 0.56, + "learning_rate": 8.67010039506977e-06, + "loss": 0.4702, + "step": 6523 + }, + { + "epoch": 0.56, + "learning_rate": 8.667363379101513e-06, + "loss": 0.4734, + "step": 6524 + }, + { + "epoch": 0.56, + "learning_rate": 8.66462646476569e-06, + "loss": 0.471, + "step": 6525 + }, + { + "epoch": 0.56, + "learning_rate": 8.66188965227103e-06, + "loss": 0.4577, + "step": 6526 + }, + { + "epoch": 0.56, + "learning_rate": 8.659152941826251e-06, + "loss": 0.4765, + "step": 6527 + }, + { + "epoch": 0.56, + "learning_rate": 8.656416333640067e-06, + "loss": 0.481, + "step": 6528 + }, + { + "epoch": 0.56, + "learning_rate": 8.653679827921178e-06, + "loss": 0.4779, + "step": 6529 + }, + { + "epoch": 0.56, + "learning_rate": 8.65094342487829e-06, + "loss": 0.4838, + "step": 6530 + }, + { + "epoch": 0.56, + "learning_rate": 8.648207124720088e-06, + "loss": 0.4801, + "step": 6531 + }, + { + "epoch": 0.56, + "learning_rate": 8.645470927655254e-06, + "loss": 0.4762, + "step": 6532 + }, + { + "epoch": 0.56, + "learning_rate": 8.642734833892463e-06, + "loss": 0.4342, + "step": 6533 + }, + { + "epoch": 0.56, + "learning_rate": 8.639998843640377e-06, + "loss": 0.4836, + "step": 6534 + }, + { + "epoch": 0.56, + "learning_rate": 8.637262957107661e-06, + "loss": 0.4752, + "step": 6535 + }, + { + "epoch": 0.56, + "learning_rate": 8.63452717450296e-06, + "loss": 0.4701, + "step": 6536 + }, + { + "epoch": 0.56, + "learning_rate": 8.631791496034916e-06, + "loss": 0.5, + "step": 6537 + }, + { + "epoch": 0.56, + "learning_rate": 8.629055921912164e-06, + "loss": 0.4719, + "step": 6538 + }, + { + "epoch": 0.56, + "learning_rate": 8.626320452343333e-06, + "loss": 0.485, + "step": 6539 + }, + { + "epoch": 0.56, + "learning_rate": 8.623585087537039e-06, + "loss": 0.474, + "step": 6540 + }, + { + "epoch": 0.56, + "learning_rate": 8.620849827701893e-06, + "loss": 0.5026, + "step": 6541 + }, + { + "epoch": 0.56, + "learning_rate": 8.618114673046494e-06, + "loss": 0.4622, + "step": 6542 + }, + { + "epoch": 0.56, + "learning_rate": 8.61537962377944e-06, + "loss": 0.4581, + "step": 6543 + }, + { + "epoch": 0.56, + "learning_rate": 8.61264468010932e-06, + "loss": 0.4798, + "step": 6544 + }, + { + "epoch": 0.56, + "learning_rate": 8.609909842244706e-06, + "loss": 0.4415, + "step": 6545 + }, + { + "epoch": 0.56, + "learning_rate": 8.607175110394171e-06, + "loss": 0.4686, + "step": 6546 + }, + { + "epoch": 0.56, + "learning_rate": 8.604440484766276e-06, + "loss": 0.4793, + "step": 6547 + }, + { + "epoch": 0.56, + "learning_rate": 8.601705965569579e-06, + "loss": 0.4844, + "step": 6548 + }, + { + "epoch": 0.56, + "learning_rate": 8.59897155301262e-06, + "loss": 0.4452, + "step": 6549 + }, + { + "epoch": 0.56, + "learning_rate": 8.596237247303941e-06, + "loss": 0.484, + "step": 6550 + }, + { + "epoch": 0.56, + "learning_rate": 8.59350304865207e-06, + "loss": 0.453, + "step": 6551 + }, + { + "epoch": 0.56, + "learning_rate": 8.590768957265525e-06, + "loss": 0.477, + "step": 6552 + }, + { + "epoch": 0.56, + "learning_rate": 8.588034973352827e-06, + "loss": 0.4824, + "step": 6553 + }, + { + "epoch": 0.56, + "learning_rate": 8.585301097122473e-06, + "loss": 0.4757, + "step": 6554 + }, + { + "epoch": 0.56, + "learning_rate": 8.58256732878297e-06, + "loss": 0.4603, + "step": 6555 + }, + { + "epoch": 0.56, + "learning_rate": 8.579833668542796e-06, + "loss": 0.4603, + "step": 6556 + }, + { + "epoch": 0.56, + "learning_rate": 8.577100116610433e-06, + "loss": 0.4858, + "step": 6557 + }, + { + "epoch": 0.56, + "learning_rate": 8.574366673194357e-06, + "loss": 0.4603, + "step": 6558 + }, + { + "epoch": 0.56, + "learning_rate": 8.571633338503034e-06, + "loss": 0.4658, + "step": 6559 + }, + { + "epoch": 0.56, + "learning_rate": 8.568900112744912e-06, + "loss": 0.4644, + "step": 6560 + }, + { + "epoch": 0.56, + "learning_rate": 8.56616699612844e-06, + "loss": 0.4797, + "step": 6561 + }, + { + "epoch": 0.56, + "learning_rate": 8.563433988862064e-06, + "loss": 0.4716, + "step": 6562 + }, + { + "epoch": 0.56, + "learning_rate": 8.560701091154208e-06, + "loss": 0.4762, + "step": 6563 + }, + { + "epoch": 0.56, + "learning_rate": 8.557968303213296e-06, + "loss": 0.4816, + "step": 6564 + }, + { + "epoch": 0.56, + "learning_rate": 8.555235625247743e-06, + "loss": 0.4797, + "step": 6565 + }, + { + "epoch": 0.56, + "learning_rate": 8.552503057465949e-06, + "loss": 0.4658, + "step": 6566 + }, + { + "epoch": 0.56, + "learning_rate": 8.549770600076314e-06, + "loss": 0.4652, + "step": 6567 + }, + { + "epoch": 0.56, + "learning_rate": 8.547038253287233e-06, + "loss": 0.4546, + "step": 6568 + }, + { + "epoch": 0.56, + "learning_rate": 8.544306017307077e-06, + "loss": 0.504, + "step": 6569 + }, + { + "epoch": 0.56, + "learning_rate": 8.54157389234422e-06, + "loss": 0.4872, + "step": 6570 + }, + { + "epoch": 0.56, + "learning_rate": 8.538841878607031e-06, + "loss": 0.4786, + "step": 6571 + }, + { + "epoch": 0.56, + "learning_rate": 8.536109976303859e-06, + "loss": 0.462, + "step": 6572 + }, + { + "epoch": 0.56, + "learning_rate": 8.533378185643052e-06, + "loss": 0.4752, + "step": 6573 + }, + { + "epoch": 0.56, + "learning_rate": 8.530646506832949e-06, + "loss": 0.4819, + "step": 6574 + }, + { + "epoch": 0.56, + "learning_rate": 8.527914940081873e-06, + "loss": 0.4623, + "step": 6575 + }, + { + "epoch": 0.56, + "learning_rate": 8.525183485598152e-06, + "loss": 0.4537, + "step": 6576 + }, + { + "epoch": 0.56, + "learning_rate": 8.522452143590096e-06, + "loss": 0.4649, + "step": 6577 + }, + { + "epoch": 0.56, + "learning_rate": 8.519720914266008e-06, + "loss": 0.4619, + "step": 6578 + }, + { + "epoch": 0.56, + "learning_rate": 8.51698979783418e-06, + "loss": 0.4587, + "step": 6579 + }, + { + "epoch": 0.56, + "learning_rate": 8.514258794502906e-06, + "loss": 0.4833, + "step": 6580 + }, + { + "epoch": 0.56, + "learning_rate": 8.511527904480457e-06, + "loss": 0.4489, + "step": 6581 + }, + { + "epoch": 0.56, + "learning_rate": 8.508797127975105e-06, + "loss": 0.4903, + "step": 6582 + }, + { + "epoch": 0.56, + "learning_rate": 8.506066465195113e-06, + "loss": 0.494, + "step": 6583 + }, + { + "epoch": 0.56, + "learning_rate": 8.503335916348722e-06, + "loss": 0.4848, + "step": 6584 + }, + { + "epoch": 0.56, + "learning_rate": 8.500605481644186e-06, + "loss": 0.4764, + "step": 6585 + }, + { + "epoch": 0.56, + "learning_rate": 8.497875161289737e-06, + "loss": 0.4725, + "step": 6586 + }, + { + "epoch": 0.56, + "learning_rate": 8.495144955493596e-06, + "loss": 0.4746, + "step": 6587 + }, + { + "epoch": 0.56, + "learning_rate": 8.492414864463988e-06, + "loss": 0.4752, + "step": 6588 + }, + { + "epoch": 0.56, + "learning_rate": 8.489684888409111e-06, + "loss": 0.4868, + "step": 6589 + }, + { + "epoch": 0.56, + "learning_rate": 8.486955027537172e-06, + "loss": 0.4674, + "step": 6590 + }, + { + "epoch": 0.56, + "learning_rate": 8.484225282056362e-06, + "loss": 0.4617, + "step": 6591 + }, + { + "epoch": 0.56, + "learning_rate": 8.481495652174859e-06, + "loss": 0.4826, + "step": 6592 + }, + { + "epoch": 0.56, + "learning_rate": 8.478766138100834e-06, + "loss": 0.477, + "step": 6593 + }, + { + "epoch": 0.56, + "learning_rate": 8.476036740042456e-06, + "loss": 0.4541, + "step": 6594 + }, + { + "epoch": 0.56, + "learning_rate": 8.47330745820788e-06, + "loss": 0.4799, + "step": 6595 + }, + { + "epoch": 0.56, + "learning_rate": 8.470578292805249e-06, + "loss": 0.4762, + "step": 6596 + }, + { + "epoch": 0.56, + "learning_rate": 8.467849244042706e-06, + "loss": 0.4511, + "step": 6597 + }, + { + "epoch": 0.56, + "learning_rate": 8.465120312128371e-06, + "loss": 0.4655, + "step": 6598 + }, + { + "epoch": 0.56, + "learning_rate": 8.46239149727037e-06, + "loss": 0.4695, + "step": 6599 + }, + { + "epoch": 0.56, + "learning_rate": 8.459662799676818e-06, + "loss": 0.4795, + "step": 6600 + }, + { + "epoch": 0.56, + "learning_rate": 8.456934219555809e-06, + "loss": 0.4736, + "step": 6601 + }, + { + "epoch": 0.56, + "learning_rate": 8.454205757115434e-06, + "loss": 0.461, + "step": 6602 + }, + { + "epoch": 0.56, + "learning_rate": 8.451477412563786e-06, + "loss": 0.4846, + "step": 6603 + }, + { + "epoch": 0.56, + "learning_rate": 8.448749186108936e-06, + "loss": 0.4655, + "step": 6604 + }, + { + "epoch": 0.56, + "learning_rate": 8.446021077958947e-06, + "loss": 0.4818, + "step": 6605 + }, + { + "epoch": 0.56, + "learning_rate": 8.44329308832188e-06, + "loss": 0.4734, + "step": 6606 + }, + { + "epoch": 0.56, + "learning_rate": 8.440565217405778e-06, + "loss": 0.4472, + "step": 6607 + }, + { + "epoch": 0.56, + "learning_rate": 8.437837465418684e-06, + "loss": 0.4825, + "step": 6608 + }, + { + "epoch": 0.56, + "learning_rate": 8.43510983256863e-06, + "loss": 0.4765, + "step": 6609 + }, + { + "epoch": 0.56, + "learning_rate": 8.43238231906363e-06, + "loss": 0.4571, + "step": 6610 + }, + { + "epoch": 0.56, + "learning_rate": 8.429654925111701e-06, + "loss": 0.4623, + "step": 6611 + }, + { + "epoch": 0.56, + "learning_rate": 8.426927650920842e-06, + "loss": 0.4825, + "step": 6612 + }, + { + "epoch": 0.56, + "learning_rate": 8.42420049669905e-06, + "loss": 0.4713, + "step": 6613 + }, + { + "epoch": 0.56, + "learning_rate": 8.421473462654304e-06, + "loss": 0.482, + "step": 6614 + }, + { + "epoch": 0.56, + "learning_rate": 8.418746548994585e-06, + "loss": 0.4756, + "step": 6615 + }, + { + "epoch": 0.56, + "learning_rate": 8.416019755927851e-06, + "loss": 0.4738, + "step": 6616 + }, + { + "epoch": 0.56, + "learning_rate": 8.413293083662065e-06, + "loss": 0.4676, + "step": 6617 + }, + { + "epoch": 0.56, + "learning_rate": 8.410566532405175e-06, + "loss": 0.4694, + "step": 6618 + }, + { + "epoch": 0.56, + "learning_rate": 8.407840102365116e-06, + "loss": 0.4742, + "step": 6619 + }, + { + "epoch": 0.56, + "learning_rate": 8.405113793749819e-06, + "loss": 0.4408, + "step": 6620 + }, + { + "epoch": 0.56, + "learning_rate": 8.402387606767199e-06, + "loss": 0.4845, + "step": 6621 + }, + { + "epoch": 0.56, + "learning_rate": 8.399661541625174e-06, + "loss": 0.4823, + "step": 6622 + }, + { + "epoch": 0.56, + "learning_rate": 8.396935598531637e-06, + "loss": 0.455, + "step": 6623 + }, + { + "epoch": 0.56, + "learning_rate": 8.39420977769449e-06, + "loss": 0.4928, + "step": 6624 + }, + { + "epoch": 0.56, + "learning_rate": 8.391484079321602e-06, + "loss": 0.4736, + "step": 6625 + }, + { + "epoch": 0.56, + "learning_rate": 8.388758503620856e-06, + "loss": 0.4567, + "step": 6626 + }, + { + "epoch": 0.57, + "learning_rate": 8.386033050800116e-06, + "loss": 0.4586, + "step": 6627 + }, + { + "epoch": 0.57, + "learning_rate": 8.383307721067231e-06, + "loss": 0.4745, + "step": 6628 + }, + { + "epoch": 0.57, + "learning_rate": 8.38058251463005e-06, + "loss": 0.4847, + "step": 6629 + }, + { + "epoch": 0.57, + "learning_rate": 8.377857431696405e-06, + "loss": 0.464, + "step": 6630 + }, + { + "epoch": 0.57, + "learning_rate": 8.375132472474127e-06, + "loss": 0.4792, + "step": 6631 + }, + { + "epoch": 0.57, + "learning_rate": 8.37240763717103e-06, + "loss": 0.4637, + "step": 6632 + }, + { + "epoch": 0.57, + "learning_rate": 8.369682925994922e-06, + "loss": 0.4667, + "step": 6633 + }, + { + "epoch": 0.57, + "learning_rate": 8.3669583391536e-06, + "loss": 0.4725, + "step": 6634 + }, + { + "epoch": 0.57, + "learning_rate": 8.364233876854848e-06, + "loss": 0.4778, + "step": 6635 + }, + { + "epoch": 0.57, + "learning_rate": 8.361509539306456e-06, + "loss": 0.4553, + "step": 6636 + }, + { + "epoch": 0.57, + "learning_rate": 8.358785326716184e-06, + "loss": 0.4799, + "step": 6637 + }, + { + "epoch": 0.57, + "learning_rate": 8.356061239291798e-06, + "loss": 0.4733, + "step": 6638 + }, + { + "epoch": 0.57, + "learning_rate": 8.35333727724104e-06, + "loss": 0.4771, + "step": 6639 + }, + { + "epoch": 0.57, + "learning_rate": 8.350613440771661e-06, + "loss": 0.4629, + "step": 6640 + }, + { + "epoch": 0.57, + "learning_rate": 8.347889730091384e-06, + "loss": 0.4828, + "step": 6641 + }, + { + "epoch": 0.57, + "learning_rate": 8.345166145407935e-06, + "loss": 0.4619, + "step": 6642 + }, + { + "epoch": 0.57, + "learning_rate": 8.342442686929024e-06, + "loss": 0.4621, + "step": 6643 + }, + { + "epoch": 0.57, + "learning_rate": 8.33971935486235e-06, + "loss": 0.4995, + "step": 6644 + }, + { + "epoch": 0.57, + "learning_rate": 8.336996149415616e-06, + "loss": 0.4787, + "step": 6645 + }, + { + "epoch": 0.57, + "learning_rate": 8.334273070796495e-06, + "loss": 0.4826, + "step": 6646 + }, + { + "epoch": 0.57, + "learning_rate": 8.331550119212665e-06, + "loss": 0.4721, + "step": 6647 + }, + { + "epoch": 0.57, + "learning_rate": 8.328827294871786e-06, + "loss": 0.455, + "step": 6648 + }, + { + "epoch": 0.57, + "learning_rate": 8.326104597981517e-06, + "loss": 0.4669, + "step": 6649 + }, + { + "epoch": 0.57, + "learning_rate": 8.323382028749499e-06, + "loss": 0.4655, + "step": 6650 + }, + { + "epoch": 0.57, + "learning_rate": 8.320659587383369e-06, + "loss": 0.4754, + "step": 6651 + }, + { + "epoch": 0.57, + "learning_rate": 8.317937274090748e-06, + "loss": 0.4737, + "step": 6652 + }, + { + "epoch": 0.57, + "learning_rate": 8.315215089079249e-06, + "loss": 0.4652, + "step": 6653 + }, + { + "epoch": 0.57, + "learning_rate": 8.312493032556489e-06, + "loss": 0.4893, + "step": 6654 + }, + { + "epoch": 0.57, + "learning_rate": 8.309771104730049e-06, + "loss": 0.4733, + "step": 6655 + }, + { + "epoch": 0.57, + "learning_rate": 8.307049305807525e-06, + "loss": 0.4832, + "step": 6656 + }, + { + "epoch": 0.57, + "learning_rate": 8.304327635996486e-06, + "loss": 0.4499, + "step": 6657 + }, + { + "epoch": 0.57, + "learning_rate": 8.301606095504501e-06, + "loss": 0.4876, + "step": 6658 + }, + { + "epoch": 0.57, + "learning_rate": 8.298884684539128e-06, + "loss": 0.4798, + "step": 6659 + }, + { + "epoch": 0.57, + "learning_rate": 8.296163403307912e-06, + "loss": 0.4653, + "step": 6660 + }, + { + "epoch": 0.57, + "learning_rate": 8.293442252018384e-06, + "loss": 0.4752, + "step": 6661 + }, + { + "epoch": 0.57, + "learning_rate": 8.290721230878074e-06, + "loss": 0.4627, + "step": 6662 + }, + { + "epoch": 0.57, + "learning_rate": 8.288000340094502e-06, + "loss": 0.4844, + "step": 6663 + }, + { + "epoch": 0.57, + "learning_rate": 8.28527957987517e-06, + "loss": 0.4664, + "step": 6664 + }, + { + "epoch": 0.57, + "learning_rate": 8.282558950427578e-06, + "loss": 0.484, + "step": 6665 + }, + { + "epoch": 0.57, + "learning_rate": 8.279838451959209e-06, + "loss": 0.4703, + "step": 6666 + }, + { + "epoch": 0.57, + "learning_rate": 8.277118084677538e-06, + "loss": 0.4982, + "step": 6667 + }, + { + "epoch": 0.57, + "learning_rate": 8.274397848790041e-06, + "loss": 0.4725, + "step": 6668 + }, + { + "epoch": 0.57, + "learning_rate": 8.271677744504166e-06, + "loss": 0.4418, + "step": 6669 + }, + { + "epoch": 0.57, + "learning_rate": 8.26895777202736e-06, + "loss": 0.4962, + "step": 6670 + }, + { + "epoch": 0.57, + "learning_rate": 8.26623793156706e-06, + "loss": 0.4764, + "step": 6671 + }, + { + "epoch": 0.57, + "learning_rate": 8.263518223330698e-06, + "loss": 0.465, + "step": 6672 + }, + { + "epoch": 0.57, + "learning_rate": 8.260798647525684e-06, + "loss": 0.4863, + "step": 6673 + }, + { + "epoch": 0.57, + "learning_rate": 8.258079204359427e-06, + "loss": 0.4664, + "step": 6674 + }, + { + "epoch": 0.57, + "learning_rate": 8.255359894039319e-06, + "loss": 0.4655, + "step": 6675 + }, + { + "epoch": 0.57, + "learning_rate": 8.252640716772748e-06, + "loss": 0.4635, + "step": 6676 + }, + { + "epoch": 0.57, + "learning_rate": 8.249921672767095e-06, + "loss": 0.4817, + "step": 6677 + }, + { + "epoch": 0.57, + "learning_rate": 8.247202762229723e-06, + "loss": 0.4589, + "step": 6678 + }, + { + "epoch": 0.57, + "learning_rate": 8.244483985367984e-06, + "loss": 0.4587, + "step": 6679 + }, + { + "epoch": 0.57, + "learning_rate": 8.241765342389222e-06, + "loss": 0.4611, + "step": 6680 + }, + { + "epoch": 0.57, + "learning_rate": 8.239046833500779e-06, + "loss": 0.4848, + "step": 6681 + }, + { + "epoch": 0.57, + "learning_rate": 8.236328458909975e-06, + "loss": 0.468, + "step": 6682 + }, + { + "epoch": 0.57, + "learning_rate": 8.233610218824129e-06, + "loss": 0.4642, + "step": 6683 + }, + { + "epoch": 0.57, + "learning_rate": 8.23089211345054e-06, + "loss": 0.4677, + "step": 6684 + }, + { + "epoch": 0.57, + "learning_rate": 8.2281741429965e-06, + "loss": 0.4519, + "step": 6685 + }, + { + "epoch": 0.57, + "learning_rate": 8.225456307669301e-06, + "loss": 0.4625, + "step": 6686 + }, + { + "epoch": 0.57, + "learning_rate": 8.222738607676214e-06, + "loss": 0.459, + "step": 6687 + }, + { + "epoch": 0.57, + "learning_rate": 8.2200210432245e-06, + "loss": 0.4463, + "step": 6688 + }, + { + "epoch": 0.57, + "learning_rate": 8.217303614521412e-06, + "loss": 0.4575, + "step": 6689 + }, + { + "epoch": 0.57, + "learning_rate": 8.214586321774189e-06, + "loss": 0.4783, + "step": 6690 + }, + { + "epoch": 0.57, + "learning_rate": 8.21186916519007e-06, + "loss": 0.5001, + "step": 6691 + }, + { + "epoch": 0.57, + "learning_rate": 8.209152144976275e-06, + "loss": 0.4659, + "step": 6692 + }, + { + "epoch": 0.57, + "learning_rate": 8.206435261340014e-06, + "loss": 0.4801, + "step": 6693 + }, + { + "epoch": 0.57, + "learning_rate": 8.203718514488483e-06, + "loss": 0.4836, + "step": 6694 + }, + { + "epoch": 0.57, + "learning_rate": 8.201001904628883e-06, + "loss": 0.4593, + "step": 6695 + }, + { + "epoch": 0.57, + "learning_rate": 8.198285431968388e-06, + "loss": 0.4809, + "step": 6696 + }, + { + "epoch": 0.57, + "learning_rate": 8.195569096714166e-06, + "loss": 0.4888, + "step": 6697 + }, + { + "epoch": 0.57, + "learning_rate": 8.19285289907338e-06, + "loss": 0.4812, + "step": 6698 + }, + { + "epoch": 0.57, + "learning_rate": 8.190136839253171e-06, + "loss": 0.4726, + "step": 6699 + }, + { + "epoch": 0.57, + "learning_rate": 8.187420917460686e-06, + "loss": 0.4823, + "step": 6700 + }, + { + "epoch": 0.57, + "learning_rate": 8.184705133903053e-06, + "loss": 0.4685, + "step": 6701 + }, + { + "epoch": 0.57, + "learning_rate": 8.181989488787381e-06, + "loss": 0.4827, + "step": 6702 + }, + { + "epoch": 0.57, + "learning_rate": 8.179273982320778e-06, + "loss": 0.4712, + "step": 6703 + }, + { + "epoch": 0.57, + "learning_rate": 8.176558614710347e-06, + "loss": 0.4858, + "step": 6704 + }, + { + "epoch": 0.57, + "learning_rate": 8.17384338616317e-06, + "loss": 0.4487, + "step": 6705 + }, + { + "epoch": 0.57, + "learning_rate": 8.171128296886316e-06, + "loss": 0.4683, + "step": 6706 + }, + { + "epoch": 0.57, + "learning_rate": 8.168413347086856e-06, + "loss": 0.4842, + "step": 6707 + }, + { + "epoch": 0.57, + "learning_rate": 8.165698536971838e-06, + "loss": 0.4556, + "step": 6708 + }, + { + "epoch": 0.57, + "learning_rate": 8.162983866748308e-06, + "loss": 0.475, + "step": 6709 + }, + { + "epoch": 0.57, + "learning_rate": 8.160269336623301e-06, + "loss": 0.4587, + "step": 6710 + }, + { + "epoch": 0.57, + "learning_rate": 8.157554946803832e-06, + "loss": 0.4697, + "step": 6711 + }, + { + "epoch": 0.57, + "learning_rate": 8.154840697496917e-06, + "loss": 0.4658, + "step": 6712 + }, + { + "epoch": 0.57, + "learning_rate": 8.15212658890955e-06, + "loss": 0.4598, + "step": 6713 + }, + { + "epoch": 0.57, + "learning_rate": 8.149412621248729e-06, + "loss": 0.4801, + "step": 6714 + }, + { + "epoch": 0.57, + "learning_rate": 8.146698794721423e-06, + "loss": 0.4554, + "step": 6715 + }, + { + "epoch": 0.57, + "learning_rate": 8.143985109534609e-06, + "loss": 0.4661, + "step": 6716 + }, + { + "epoch": 0.57, + "learning_rate": 8.141271565895233e-06, + "loss": 0.4831, + "step": 6717 + }, + { + "epoch": 0.57, + "learning_rate": 8.138558164010251e-06, + "loss": 0.4628, + "step": 6718 + }, + { + "epoch": 0.57, + "learning_rate": 8.135844904086596e-06, + "loss": 0.4667, + "step": 6719 + }, + { + "epoch": 0.57, + "learning_rate": 8.133131786331188e-06, + "loss": 0.4647, + "step": 6720 + }, + { + "epoch": 0.57, + "learning_rate": 8.130418810950948e-06, + "loss": 0.4694, + "step": 6721 + }, + { + "epoch": 0.57, + "learning_rate": 8.127705978152769e-06, + "loss": 0.4775, + "step": 6722 + }, + { + "epoch": 0.57, + "learning_rate": 8.124993288143553e-06, + "loss": 0.4702, + "step": 6723 + }, + { + "epoch": 0.57, + "learning_rate": 8.122280741130177e-06, + "loss": 0.4506, + "step": 6724 + }, + { + "epoch": 0.57, + "learning_rate": 8.11956833731951e-06, + "loss": 0.4709, + "step": 6725 + }, + { + "epoch": 0.57, + "learning_rate": 8.11685607691841e-06, + "loss": 0.4546, + "step": 6726 + }, + { + "epoch": 0.57, + "learning_rate": 8.114143960133728e-06, + "loss": 0.4746, + "step": 6727 + }, + { + "epoch": 0.57, + "learning_rate": 8.111431987172303e-06, + "loss": 0.4603, + "step": 6728 + }, + { + "epoch": 0.57, + "learning_rate": 8.10872015824096e-06, + "loss": 0.4722, + "step": 6729 + }, + { + "epoch": 0.57, + "learning_rate": 8.106008473546512e-06, + "loss": 0.4658, + "step": 6730 + }, + { + "epoch": 0.57, + "learning_rate": 8.103296933295762e-06, + "loss": 0.4835, + "step": 6731 + }, + { + "epoch": 0.57, + "learning_rate": 8.10058553769551e-06, + "loss": 0.4863, + "step": 6732 + }, + { + "epoch": 0.57, + "learning_rate": 8.097874286952534e-06, + "loss": 0.4719, + "step": 6733 + }, + { + "epoch": 0.57, + "learning_rate": 8.095163181273608e-06, + "loss": 0.4696, + "step": 6734 + }, + { + "epoch": 0.57, + "learning_rate": 8.092452220865485e-06, + "loss": 0.474, + "step": 6735 + }, + { + "epoch": 0.57, + "learning_rate": 8.089741405934923e-06, + "loss": 0.4813, + "step": 6736 + }, + { + "epoch": 0.57, + "learning_rate": 8.087030736688657e-06, + "loss": 0.4816, + "step": 6737 + }, + { + "epoch": 0.57, + "learning_rate": 8.084320213333413e-06, + "loss": 0.484, + "step": 6738 + }, + { + "epoch": 0.57, + "learning_rate": 8.081609836075907e-06, + "loss": 0.4835, + "step": 6739 + }, + { + "epoch": 0.57, + "learning_rate": 8.07889960512284e-06, + "loss": 0.4424, + "step": 6740 + }, + { + "epoch": 0.57, + "learning_rate": 8.076189520680914e-06, + "loss": 0.4822, + "step": 6741 + }, + { + "epoch": 0.57, + "learning_rate": 8.073479582956806e-06, + "loss": 0.4743, + "step": 6742 + }, + { + "epoch": 0.57, + "learning_rate": 8.070769792157192e-06, + "loss": 0.4684, + "step": 6743 + }, + { + "epoch": 0.58, + "learning_rate": 8.068060148488722e-06, + "loss": 0.4763, + "step": 6744 + }, + { + "epoch": 0.58, + "learning_rate": 8.065350652158051e-06, + "loss": 0.4825, + "step": 6745 + }, + { + "epoch": 0.58, + "learning_rate": 8.062641303371818e-06, + "loss": 0.4745, + "step": 6746 + }, + { + "epoch": 0.58, + "learning_rate": 8.059932102336647e-06, + "loss": 0.4657, + "step": 6747 + }, + { + "epoch": 0.58, + "learning_rate": 8.057223049259155e-06, + "loss": 0.4838, + "step": 6748 + }, + { + "epoch": 0.58, + "learning_rate": 8.054514144345941e-06, + "loss": 0.4686, + "step": 6749 + }, + { + "epoch": 0.58, + "learning_rate": 8.051805387803601e-06, + "loss": 0.4882, + "step": 6750 + }, + { + "epoch": 0.58, + "learning_rate": 8.04909677983872e-06, + "loss": 0.469, + "step": 6751 + }, + { + "epoch": 0.58, + "learning_rate": 8.046388320657861e-06, + "loss": 0.4728, + "step": 6752 + }, + { + "epoch": 0.58, + "learning_rate": 8.043680010467583e-06, + "loss": 0.451, + "step": 6753 + }, + { + "epoch": 0.58, + "learning_rate": 8.040971849474432e-06, + "loss": 0.4723, + "step": 6754 + }, + { + "epoch": 0.58, + "learning_rate": 8.038263837884952e-06, + "loss": 0.4777, + "step": 6755 + }, + { + "epoch": 0.58, + "learning_rate": 8.03555597590566e-06, + "loss": 0.4435, + "step": 6756 + }, + { + "epoch": 0.58, + "learning_rate": 8.032848263743071e-06, + "loss": 0.4769, + "step": 6757 + }, + { + "epoch": 0.58, + "learning_rate": 8.030140701603684e-06, + "loss": 0.4685, + "step": 6758 + }, + { + "epoch": 0.58, + "learning_rate": 8.027433289693991e-06, + "loss": 0.4958, + "step": 6759 + }, + { + "epoch": 0.58, + "learning_rate": 8.024726028220474e-06, + "loss": 0.4782, + "step": 6760 + }, + { + "epoch": 0.58, + "learning_rate": 8.022018917389597e-06, + "loss": 0.4655, + "step": 6761 + }, + { + "epoch": 0.58, + "learning_rate": 8.019311957407811e-06, + "loss": 0.4731, + "step": 6762 + }, + { + "epoch": 0.58, + "learning_rate": 8.016605148481565e-06, + "loss": 0.4586, + "step": 6763 + }, + { + "epoch": 0.58, + "learning_rate": 8.013898490817293e-06, + "loss": 0.4829, + "step": 6764 + }, + { + "epoch": 0.58, + "learning_rate": 8.011191984621412e-06, + "loss": 0.4623, + "step": 6765 + }, + { + "epoch": 0.58, + "learning_rate": 8.008485630100336e-06, + "loss": 0.4632, + "step": 6766 + }, + { + "epoch": 0.58, + "learning_rate": 8.005779427460457e-06, + "loss": 0.4899, + "step": 6767 + }, + { + "epoch": 0.58, + "learning_rate": 8.003073376908163e-06, + "loss": 0.4757, + "step": 6768 + }, + { + "epoch": 0.58, + "learning_rate": 8.000367478649835e-06, + "loss": 0.4571, + "step": 6769 + }, + { + "epoch": 0.58, + "learning_rate": 7.99766173289183e-06, + "loss": 0.4623, + "step": 6770 + }, + { + "epoch": 0.58, + "learning_rate": 7.9949561398405e-06, + "loss": 0.4867, + "step": 6771 + }, + { + "epoch": 0.58, + "learning_rate": 7.992250699702182e-06, + "loss": 0.4527, + "step": 6772 + }, + { + "epoch": 0.58, + "learning_rate": 7.989545412683214e-06, + "loss": 0.4685, + "step": 6773 + }, + { + "epoch": 0.58, + "learning_rate": 7.986840278989902e-06, + "loss": 0.4848, + "step": 6774 + }, + { + "epoch": 0.58, + "learning_rate": 7.98413529882856e-06, + "loss": 0.4639, + "step": 6775 + }, + { + "epoch": 0.58, + "learning_rate": 7.98143047240547e-06, + "loss": 0.4662, + "step": 6776 + }, + { + "epoch": 0.58, + "learning_rate": 7.97872579992692e-06, + "loss": 0.458, + "step": 6777 + }, + { + "epoch": 0.58, + "learning_rate": 7.976021281599182e-06, + "loss": 0.4792, + "step": 6778 + }, + { + "epoch": 0.58, + "learning_rate": 7.973316917628513e-06, + "loss": 0.4432, + "step": 6779 + }, + { + "epoch": 0.58, + "learning_rate": 7.970612708221153e-06, + "loss": 0.4887, + "step": 6780 + }, + { + "epoch": 0.58, + "learning_rate": 7.967908653583338e-06, + "loss": 0.4733, + "step": 6781 + }, + { + "epoch": 0.58, + "learning_rate": 7.9652047539213e-06, + "loss": 0.4818, + "step": 6782 + }, + { + "epoch": 0.58, + "learning_rate": 7.962501009441236e-06, + "loss": 0.4753, + "step": 6783 + }, + { + "epoch": 0.58, + "learning_rate": 7.959797420349356e-06, + "loss": 0.447, + "step": 6784 + }, + { + "epoch": 0.58, + "learning_rate": 7.957093986851839e-06, + "loss": 0.469, + "step": 6785 + }, + { + "epoch": 0.58, + "learning_rate": 7.954390709154863e-06, + "loss": 0.4612, + "step": 6786 + }, + { + "epoch": 0.58, + "learning_rate": 7.951687587464595e-06, + "loss": 0.4786, + "step": 6787 + }, + { + "epoch": 0.58, + "learning_rate": 7.94898462198718e-06, + "loss": 0.4595, + "step": 6788 + }, + { + "epoch": 0.58, + "learning_rate": 7.946281812928763e-06, + "loss": 0.4718, + "step": 6789 + }, + { + "epoch": 0.58, + "learning_rate": 7.943579160495466e-06, + "loss": 0.4945, + "step": 6790 + }, + { + "epoch": 0.58, + "learning_rate": 7.940876664893411e-06, + "loss": 0.4822, + "step": 6791 + }, + { + "epoch": 0.58, + "learning_rate": 7.938174326328696e-06, + "loss": 0.4711, + "step": 6792 + }, + { + "epoch": 0.58, + "learning_rate": 7.935472145007416e-06, + "loss": 0.4786, + "step": 6793 + }, + { + "epoch": 0.58, + "learning_rate": 7.932770121135648e-06, + "loss": 0.4609, + "step": 6794 + }, + { + "epoch": 0.58, + "learning_rate": 7.93006825491946e-06, + "loss": 0.4843, + "step": 6795 + }, + { + "epoch": 0.58, + "learning_rate": 7.927366546564911e-06, + "loss": 0.481, + "step": 6796 + }, + { + "epoch": 0.58, + "learning_rate": 7.92466499627804e-06, + "loss": 0.4788, + "step": 6797 + }, + { + "epoch": 0.58, + "learning_rate": 7.921963604264884e-06, + "loss": 0.4863, + "step": 6798 + }, + { + "epoch": 0.58, + "learning_rate": 7.919262370731459e-06, + "loss": 0.4495, + "step": 6799 + }, + { + "epoch": 0.58, + "learning_rate": 7.916561295883767e-06, + "loss": 0.4726, + "step": 6800 + }, + { + "epoch": 0.58, + "learning_rate": 7.913860379927812e-06, + "loss": 0.4844, + "step": 6801 + }, + { + "epoch": 0.58, + "learning_rate": 7.911159623069575e-06, + "loss": 0.4869, + "step": 6802 + }, + { + "epoch": 0.58, + "learning_rate": 7.908459025515024e-06, + "loss": 0.479, + "step": 6803 + }, + { + "epoch": 0.58, + "learning_rate": 7.905758587470119e-06, + "loss": 0.461, + "step": 6804 + }, + { + "epoch": 0.58, + "learning_rate": 7.903058309140809e-06, + "loss": 0.4597, + "step": 6805 + }, + { + "epoch": 0.58, + "learning_rate": 7.900358190733026e-06, + "loss": 0.4672, + "step": 6806 + }, + { + "epoch": 0.58, + "learning_rate": 7.897658232452696e-06, + "loss": 0.4806, + "step": 6807 + }, + { + "epoch": 0.58, + "learning_rate": 7.894958434505725e-06, + "loss": 0.4619, + "step": 6808 + }, + { + "epoch": 0.58, + "learning_rate": 7.892258797098008e-06, + "loss": 0.4651, + "step": 6809 + }, + { + "epoch": 0.58, + "learning_rate": 7.889559320435436e-06, + "loss": 0.4695, + "step": 6810 + }, + { + "epoch": 0.58, + "learning_rate": 7.886860004723885e-06, + "loss": 0.4835, + "step": 6811 + }, + { + "epoch": 0.58, + "learning_rate": 7.884160850169209e-06, + "loss": 0.4721, + "step": 6812 + }, + { + "epoch": 0.58, + "learning_rate": 7.881461856977259e-06, + "loss": 0.4731, + "step": 6813 + }, + { + "epoch": 0.58, + "learning_rate": 7.878763025353875e-06, + "loss": 0.495, + "step": 6814 + }, + { + "epoch": 0.58, + "learning_rate": 7.876064355504877e-06, + "loss": 0.4709, + "step": 6815 + }, + { + "epoch": 0.58, + "learning_rate": 7.873365847636081e-06, + "loss": 0.46, + "step": 6816 + }, + { + "epoch": 0.58, + "learning_rate": 7.870667501953284e-06, + "loss": 0.4856, + "step": 6817 + }, + { + "epoch": 0.58, + "learning_rate": 7.867969318662267e-06, + "loss": 0.4658, + "step": 6818 + }, + { + "epoch": 0.58, + "learning_rate": 7.865271297968815e-06, + "loss": 0.4894, + "step": 6819 + }, + { + "epoch": 0.58, + "learning_rate": 7.862573440078686e-06, + "loss": 0.4766, + "step": 6820 + }, + { + "epoch": 0.58, + "learning_rate": 7.85987574519763e-06, + "loss": 0.472, + "step": 6821 + }, + { + "epoch": 0.58, + "learning_rate": 7.857178213531385e-06, + "loss": 0.4764, + "step": 6822 + }, + { + "epoch": 0.58, + "learning_rate": 7.854480845285672e-06, + "loss": 0.4838, + "step": 6823 + }, + { + "epoch": 0.58, + "learning_rate": 7.851783640666209e-06, + "loss": 0.4739, + "step": 6824 + }, + { + "epoch": 0.58, + "learning_rate": 7.849086599878697e-06, + "loss": 0.4549, + "step": 6825 + }, + { + "epoch": 0.58, + "learning_rate": 7.846389723128819e-06, + "loss": 0.4616, + "step": 6826 + }, + { + "epoch": 0.58, + "learning_rate": 7.843693010622249e-06, + "loss": 0.4571, + "step": 6827 + }, + { + "epoch": 0.58, + "learning_rate": 7.840996462564654e-06, + "loss": 0.4682, + "step": 6828 + }, + { + "epoch": 0.58, + "learning_rate": 7.838300079161684e-06, + "loss": 0.4791, + "step": 6829 + }, + { + "epoch": 0.58, + "learning_rate": 7.835603860618973e-06, + "loss": 0.4546, + "step": 6830 + }, + { + "epoch": 0.58, + "learning_rate": 7.832907807142149e-06, + "loss": 0.4762, + "step": 6831 + }, + { + "epoch": 0.58, + "learning_rate": 7.83021191893682e-06, + "loss": 0.4588, + "step": 6832 + }, + { + "epoch": 0.58, + "learning_rate": 7.82751619620859e-06, + "loss": 0.4616, + "step": 6833 + }, + { + "epoch": 0.58, + "learning_rate": 7.824820639163047e-06, + "loss": 0.466, + "step": 6834 + }, + { + "epoch": 0.58, + "learning_rate": 7.822125248005764e-06, + "loss": 0.4598, + "step": 6835 + }, + { + "epoch": 0.58, + "learning_rate": 7.819430022942298e-06, + "loss": 0.4742, + "step": 6836 + }, + { + "epoch": 0.58, + "learning_rate": 7.816734964178202e-06, + "loss": 0.4715, + "step": 6837 + }, + { + "epoch": 0.58, + "learning_rate": 7.814040071919016e-06, + "loss": 0.4704, + "step": 6838 + }, + { + "epoch": 0.58, + "learning_rate": 7.811345346370257e-06, + "loss": 0.4686, + "step": 6839 + }, + { + "epoch": 0.58, + "learning_rate": 7.808650787737443e-06, + "loss": 0.4908, + "step": 6840 + }, + { + "epoch": 0.58, + "learning_rate": 7.805956396226064e-06, + "loss": 0.4551, + "step": 6841 + }, + { + "epoch": 0.58, + "learning_rate": 7.80326217204161e-06, + "loss": 0.4837, + "step": 6842 + }, + { + "epoch": 0.58, + "learning_rate": 7.800568115389559e-06, + "loss": 0.475, + "step": 6843 + }, + { + "epoch": 0.58, + "learning_rate": 7.797874226475362e-06, + "loss": 0.4791, + "step": 6844 + }, + { + "epoch": 0.58, + "learning_rate": 7.795180505504472e-06, + "loss": 0.4853, + "step": 6845 + }, + { + "epoch": 0.58, + "learning_rate": 7.792486952682319e-06, + "loss": 0.4614, + "step": 6846 + }, + { + "epoch": 0.58, + "learning_rate": 7.78979356821433e-06, + "loss": 0.4718, + "step": 6847 + }, + { + "epoch": 0.58, + "learning_rate": 7.78710035230591e-06, + "loss": 0.4769, + "step": 6848 + }, + { + "epoch": 0.58, + "learning_rate": 7.784407305162456e-06, + "loss": 0.4812, + "step": 6849 + }, + { + "epoch": 0.58, + "learning_rate": 7.781714426989346e-06, + "loss": 0.471, + "step": 6850 + }, + { + "epoch": 0.58, + "learning_rate": 7.779021717991959e-06, + "loss": 0.4658, + "step": 6851 + }, + { + "epoch": 0.58, + "learning_rate": 7.77632917837565e-06, + "loss": 0.462, + "step": 6852 + }, + { + "epoch": 0.58, + "learning_rate": 7.773636808345757e-06, + "loss": 0.4679, + "step": 6853 + }, + { + "epoch": 0.58, + "learning_rate": 7.770944608107622e-06, + "loss": 0.4648, + "step": 6854 + }, + { + "epoch": 0.58, + "learning_rate": 7.76825257786655e-06, + "loss": 0.4595, + "step": 6855 + }, + { + "epoch": 0.58, + "learning_rate": 7.765560717827857e-06, + "loss": 0.4763, + "step": 6856 + }, + { + "epoch": 0.58, + "learning_rate": 7.762869028196832e-06, + "loss": 0.4627, + "step": 6857 + }, + { + "epoch": 0.58, + "learning_rate": 7.760177509178756e-06, + "loss": 0.4843, + "step": 6858 + }, + { + "epoch": 0.58, + "learning_rate": 7.757486160978891e-06, + "loss": 0.4733, + "step": 6859 + }, + { + "epoch": 0.58, + "learning_rate": 7.754794983802494e-06, + "loss": 0.4763, + "step": 6860 + }, + { + "epoch": 0.59, + "learning_rate": 7.752103977854809e-06, + "loss": 0.4751, + "step": 6861 + }, + { + "epoch": 0.59, + "learning_rate": 7.749413143341056e-06, + "loss": 0.488, + "step": 6862 + }, + { + "epoch": 0.59, + "learning_rate": 7.746722480466456e-06, + "loss": 0.4751, + "step": 6863 + }, + { + "epoch": 0.59, + "learning_rate": 7.7440319894362e-06, + "loss": 0.4829, + "step": 6864 + }, + { + "epoch": 0.59, + "learning_rate": 7.741341670455489e-06, + "loss": 0.4892, + "step": 6865 + }, + { + "epoch": 0.59, + "learning_rate": 7.73865152372949e-06, + "loss": 0.4674, + "step": 6866 + }, + { + "epoch": 0.59, + "learning_rate": 7.735961549463368e-06, + "loss": 0.4575, + "step": 6867 + }, + { + "epoch": 0.59, + "learning_rate": 7.733271747862265e-06, + "loss": 0.4668, + "step": 6868 + }, + { + "epoch": 0.59, + "learning_rate": 7.730582119131328e-06, + "loss": 0.4634, + "step": 6869 + }, + { + "epoch": 0.59, + "learning_rate": 7.727892663475672e-06, + "loss": 0.4493, + "step": 6870 + }, + { + "epoch": 0.59, + "learning_rate": 7.725203381100403e-06, + "loss": 0.4587, + "step": 6871 + }, + { + "epoch": 0.59, + "learning_rate": 7.722514272210627e-06, + "loss": 0.4765, + "step": 6872 + }, + { + "epoch": 0.59, + "learning_rate": 7.719825337011415e-06, + "loss": 0.453, + "step": 6873 + }, + { + "epoch": 0.59, + "learning_rate": 7.717136575707846e-06, + "loss": 0.4642, + "step": 6874 + }, + { + "epoch": 0.59, + "learning_rate": 7.714447988504972e-06, + "loss": 0.4499, + "step": 6875 + }, + { + "epoch": 0.59, + "learning_rate": 7.711759575607838e-06, + "loss": 0.4527, + "step": 6876 + }, + { + "epoch": 0.59, + "learning_rate": 7.709071337221468e-06, + "loss": 0.4996, + "step": 6877 + }, + { + "epoch": 0.59, + "learning_rate": 7.706383273550883e-06, + "loss": 0.444, + "step": 6878 + }, + { + "epoch": 0.59, + "learning_rate": 7.703695384801086e-06, + "loss": 0.4797, + "step": 6879 + }, + { + "epoch": 0.59, + "learning_rate": 7.701007671177066e-06, + "loss": 0.4592, + "step": 6880 + }, + { + "epoch": 0.59, + "learning_rate": 7.698320132883801e-06, + "loss": 0.4791, + "step": 6881 + }, + { + "epoch": 0.59, + "learning_rate": 7.695632770126247e-06, + "loss": 0.4682, + "step": 6882 + }, + { + "epoch": 0.59, + "learning_rate": 7.692945583109362e-06, + "loss": 0.4499, + "step": 6883 + }, + { + "epoch": 0.59, + "learning_rate": 7.690258572038077e-06, + "loss": 0.5006, + "step": 6884 + }, + { + "epoch": 0.59, + "learning_rate": 7.687571737117318e-06, + "loss": 0.4488, + "step": 6885 + }, + { + "epoch": 0.59, + "learning_rate": 7.684885078551991e-06, + "loss": 0.4645, + "step": 6886 + }, + { + "epoch": 0.59, + "learning_rate": 7.682198596546992e-06, + "loss": 0.4467, + "step": 6887 + }, + { + "epoch": 0.59, + "learning_rate": 7.679512291307207e-06, + "loss": 0.4741, + "step": 6888 + }, + { + "epoch": 0.59, + "learning_rate": 7.6768261630375e-06, + "loss": 0.4323, + "step": 6889 + }, + { + "epoch": 0.59, + "learning_rate": 7.674140211942732e-06, + "loss": 0.4686, + "step": 6890 + }, + { + "epoch": 0.59, + "learning_rate": 7.671454438227739e-06, + "loss": 0.491, + "step": 6891 + }, + { + "epoch": 0.59, + "learning_rate": 7.668768842097353e-06, + "loss": 0.4935, + "step": 6892 + }, + { + "epoch": 0.59, + "learning_rate": 7.666083423756387e-06, + "loss": 0.4906, + "step": 6893 + }, + { + "epoch": 0.59, + "learning_rate": 7.663398183409645e-06, + "loss": 0.4721, + "step": 6894 + }, + { + "epoch": 0.59, + "learning_rate": 7.660713121261911e-06, + "loss": 0.4881, + "step": 6895 + }, + { + "epoch": 0.59, + "learning_rate": 7.658028237517957e-06, + "loss": 0.4548, + "step": 6896 + }, + { + "epoch": 0.59, + "learning_rate": 7.655343532382552e-06, + "loss": 0.4706, + "step": 6897 + }, + { + "epoch": 0.59, + "learning_rate": 7.652659006060436e-06, + "loss": 0.4598, + "step": 6898 + }, + { + "epoch": 0.59, + "learning_rate": 7.649974658756346e-06, + "loss": 0.4549, + "step": 6899 + }, + { + "epoch": 0.59, + "learning_rate": 7.647290490674997e-06, + "loss": 0.4681, + "step": 6900 + }, + { + "epoch": 0.59, + "learning_rate": 7.644606502021096e-06, + "loss": 0.4945, + "step": 6901 + }, + { + "epoch": 0.59, + "learning_rate": 7.64192269299934e-06, + "loss": 0.4756, + "step": 6902 + }, + { + "epoch": 0.59, + "learning_rate": 7.639239063814405e-06, + "loss": 0.4737, + "step": 6903 + }, + { + "epoch": 0.59, + "learning_rate": 7.636555614670953e-06, + "loss": 0.4772, + "step": 6904 + }, + { + "epoch": 0.59, + "learning_rate": 7.633872345773635e-06, + "loss": 0.4605, + "step": 6905 + }, + { + "epoch": 0.59, + "learning_rate": 7.631189257327092e-06, + "loss": 0.4439, + "step": 6906 + }, + { + "epoch": 0.59, + "learning_rate": 7.6285063495359465e-06, + "loss": 0.4784, + "step": 6907 + }, + { + "epoch": 0.59, + "learning_rate": 7.625823622604809e-06, + "loss": 0.4489, + "step": 6908 + }, + { + "epoch": 0.59, + "learning_rate": 7.623141076738271e-06, + "loss": 0.479, + "step": 6909 + }, + { + "epoch": 0.59, + "learning_rate": 7.620458712140916e-06, + "loss": 0.4775, + "step": 6910 + }, + { + "epoch": 0.59, + "learning_rate": 7.617776529017318e-06, + "loss": 0.4953, + "step": 6911 + }, + { + "epoch": 0.59, + "learning_rate": 7.615094527572027e-06, + "loss": 0.4493, + "step": 6912 + }, + { + "epoch": 0.59, + "learning_rate": 7.612412708009583e-06, + "loss": 0.4893, + "step": 6913 + }, + { + "epoch": 0.59, + "learning_rate": 7.6097310705345096e-06, + "loss": 0.4949, + "step": 6914 + }, + { + "epoch": 0.59, + "learning_rate": 7.607049615351329e-06, + "loss": 0.4539, + "step": 6915 + }, + { + "epoch": 0.59, + "learning_rate": 7.604368342664533e-06, + "loss": 0.475, + "step": 6916 + }, + { + "epoch": 0.59, + "learning_rate": 7.601687252678611e-06, + "loss": 0.469, + "step": 6917 + }, + { + "epoch": 0.59, + "learning_rate": 7.59900634559803e-06, + "loss": 0.4852, + "step": 6918 + }, + { + "epoch": 0.59, + "learning_rate": 7.596325621627247e-06, + "loss": 0.457, + "step": 6919 + }, + { + "epoch": 0.59, + "learning_rate": 7.5936450809707096e-06, + "loss": 0.5128, + "step": 6920 + }, + { + "epoch": 0.59, + "learning_rate": 7.590964723832846e-06, + "loss": 0.4803, + "step": 6921 + }, + { + "epoch": 0.59, + "learning_rate": 7.588284550418068e-06, + "loss": 0.4532, + "step": 6922 + }, + { + "epoch": 0.59, + "learning_rate": 7.58560456093078e-06, + "loss": 0.4716, + "step": 6923 + }, + { + "epoch": 0.59, + "learning_rate": 7.582924755575365e-06, + "loss": 0.4659, + "step": 6924 + }, + { + "epoch": 0.59, + "learning_rate": 7.5802451345562e-06, + "loss": 0.4564, + "step": 6925 + }, + { + "epoch": 0.59, + "learning_rate": 7.577565698077646e-06, + "loss": 0.473, + "step": 6926 + }, + { + "epoch": 0.59, + "learning_rate": 7.574886446344043e-06, + "loss": 0.4762, + "step": 6927 + }, + { + "epoch": 0.59, + "learning_rate": 7.572207379559722e-06, + "loss": 0.4768, + "step": 6928 + }, + { + "epoch": 0.59, + "learning_rate": 7.569528497929005e-06, + "loss": 0.498, + "step": 6929 + }, + { + "epoch": 0.59, + "learning_rate": 7.566849801656193e-06, + "loss": 0.4768, + "step": 6930 + }, + { + "epoch": 0.59, + "learning_rate": 7.564171290945571e-06, + "loss": 0.4731, + "step": 6931 + }, + { + "epoch": 0.59, + "learning_rate": 7.561492966001418e-06, + "loss": 0.4771, + "step": 6932 + }, + { + "epoch": 0.59, + "learning_rate": 7.558814827027987e-06, + "loss": 0.492, + "step": 6933 + }, + { + "epoch": 0.59, + "learning_rate": 7.556136874229532e-06, + "loss": 0.459, + "step": 6934 + }, + { + "epoch": 0.59, + "learning_rate": 7.5534591078102825e-06, + "loss": 0.4651, + "step": 6935 + }, + { + "epoch": 0.59, + "learning_rate": 7.550781527974455e-06, + "loss": 0.4632, + "step": 6936 + }, + { + "epoch": 0.59, + "learning_rate": 7.54810413492625e-06, + "loss": 0.4959, + "step": 6937 + }, + { + "epoch": 0.59, + "learning_rate": 7.545426928869863e-06, + "loss": 0.4589, + "step": 6938 + }, + { + "epoch": 0.59, + "learning_rate": 7.542749910009468e-06, + "loss": 0.4891, + "step": 6939 + }, + { + "epoch": 0.59, + "learning_rate": 7.540073078549221e-06, + "loss": 0.4659, + "step": 6940 + }, + { + "epoch": 0.59, + "learning_rate": 7.537396434693274e-06, + "loss": 0.458, + "step": 6941 + }, + { + "epoch": 0.59, + "learning_rate": 7.53471997864575e-06, + "loss": 0.4593, + "step": 6942 + }, + { + "epoch": 0.59, + "learning_rate": 7.5320437106107756e-06, + "loss": 0.4572, + "step": 6943 + }, + { + "epoch": 0.59, + "learning_rate": 7.5293676307924535e-06, + "loss": 0.4709, + "step": 6944 + }, + { + "epoch": 0.59, + "learning_rate": 7.526691739394868e-06, + "loss": 0.4619, + "step": 6945 + }, + { + "epoch": 0.59, + "learning_rate": 7.524016036622094e-06, + "loss": 0.4662, + "step": 6946 + }, + { + "epoch": 0.59, + "learning_rate": 7.521340522678199e-06, + "loss": 0.46, + "step": 6947 + }, + { + "epoch": 0.59, + "learning_rate": 7.518665197767223e-06, + "loss": 0.4735, + "step": 6948 + }, + { + "epoch": 0.59, + "learning_rate": 7.515990062093196e-06, + "loss": 0.4659, + "step": 6949 + }, + { + "epoch": 0.59, + "learning_rate": 7.51331511586014e-06, + "loss": 0.4698, + "step": 6950 + }, + { + "epoch": 0.59, + "learning_rate": 7.51064035927205e-06, + "loss": 0.4604, + "step": 6951 + }, + { + "epoch": 0.59, + "learning_rate": 7.507965792532922e-06, + "loss": 0.477, + "step": 6952 + }, + { + "epoch": 0.59, + "learning_rate": 7.505291415846728e-06, + "loss": 0.4657, + "step": 6953 + }, + { + "epoch": 0.59, + "learning_rate": 7.5026172294174234e-06, + "loss": 0.4592, + "step": 6954 + }, + { + "epoch": 0.59, + "learning_rate": 7.499943233448958e-06, + "loss": 0.4723, + "step": 6955 + }, + { + "epoch": 0.59, + "learning_rate": 7.497269428145255e-06, + "loss": 0.4477, + "step": 6956 + }, + { + "epoch": 0.59, + "learning_rate": 7.494595813710237e-06, + "loss": 0.473, + "step": 6957 + }, + { + "epoch": 0.59, + "learning_rate": 7.491922390347801e-06, + "loss": 0.4571, + "step": 6958 + }, + { + "epoch": 0.59, + "learning_rate": 7.489249158261836e-06, + "loss": 0.4726, + "step": 6959 + }, + { + "epoch": 0.59, + "learning_rate": 7.4865761176562075e-06, + "loss": 0.5043, + "step": 6960 + }, + { + "epoch": 0.59, + "learning_rate": 7.48390326873478e-06, + "loss": 0.4801, + "step": 6961 + }, + { + "epoch": 0.59, + "learning_rate": 7.4812306117013965e-06, + "loss": 0.4768, + "step": 6962 + }, + { + "epoch": 0.59, + "learning_rate": 7.47855814675988e-06, + "loss": 0.4697, + "step": 6963 + }, + { + "epoch": 0.59, + "learning_rate": 7.475885874114047e-06, + "loss": 0.4624, + "step": 6964 + }, + { + "epoch": 0.59, + "learning_rate": 7.473213793967692e-06, + "loss": 0.4642, + "step": 6965 + }, + { + "epoch": 0.59, + "learning_rate": 7.470541906524603e-06, + "loss": 0.4858, + "step": 6966 + }, + { + "epoch": 0.59, + "learning_rate": 7.467870211988551e-06, + "loss": 0.4619, + "step": 6967 + }, + { + "epoch": 0.59, + "learning_rate": 7.465198710563289e-06, + "loss": 0.4783, + "step": 6968 + }, + { + "epoch": 0.59, + "learning_rate": 7.4625274024525504e-06, + "loss": 0.4686, + "step": 6969 + }, + { + "epoch": 0.59, + "learning_rate": 7.459856287860068e-06, + "loss": 0.4775, + "step": 6970 + }, + { + "epoch": 0.59, + "learning_rate": 7.457185366989552e-06, + "loss": 0.462, + "step": 6971 + }, + { + "epoch": 0.59, + "learning_rate": 7.454514640044693e-06, + "loss": 0.4654, + "step": 6972 + }, + { + "epoch": 0.59, + "learning_rate": 7.451844107229178e-06, + "loss": 0.4869, + "step": 6973 + }, + { + "epoch": 0.59, + "learning_rate": 7.449173768746665e-06, + "loss": 0.4671, + "step": 6974 + }, + { + "epoch": 0.59, + "learning_rate": 7.446503624800811e-06, + "loss": 0.4952, + "step": 6975 + }, + { + "epoch": 0.59, + "learning_rate": 7.443833675595254e-06, + "loss": 0.475, + "step": 6976 + }, + { + "epoch": 0.59, + "learning_rate": 7.441163921333614e-06, + "loss": 0.46, + "step": 6977 + }, + { + "epoch": 0.59, + "learning_rate": 7.438494362219491e-06, + "loss": 0.4635, + "step": 6978 + }, + { + "epoch": 0.6, + "learning_rate": 7.4358249984564824e-06, + "loss": 0.4804, + "step": 6979 + }, + { + "epoch": 0.6, + "learning_rate": 7.4331558302481674e-06, + "loss": 0.4635, + "step": 6980 + }, + { + "epoch": 0.6, + "learning_rate": 7.430486857798104e-06, + "loss": 0.4668, + "step": 6981 + }, + { + "epoch": 0.6, + "learning_rate": 7.427818081309841e-06, + "loss": 0.5148, + "step": 6982 + }, + { + "epoch": 0.6, + "learning_rate": 7.425149500986906e-06, + "loss": 0.4784, + "step": 6983 + }, + { + "epoch": 0.6, + "learning_rate": 7.422481117032822e-06, + "loss": 0.4549, + "step": 6984 + }, + { + "epoch": 0.6, + "learning_rate": 7.419812929651091e-06, + "loss": 0.4743, + "step": 6985 + }, + { + "epoch": 0.6, + "learning_rate": 7.417144939045198e-06, + "loss": 0.4695, + "step": 6986 + }, + { + "epoch": 0.6, + "learning_rate": 7.4144771454186125e-06, + "loss": 0.4543, + "step": 6987 + }, + { + "epoch": 0.6, + "learning_rate": 7.411809548974792e-06, + "loss": 0.4601, + "step": 6988 + }, + { + "epoch": 0.6, + "learning_rate": 7.409142149917185e-06, + "loss": 0.468, + "step": 6989 + }, + { + "epoch": 0.6, + "learning_rate": 7.406474948449212e-06, + "loss": 0.4552, + "step": 6990 + }, + { + "epoch": 0.6, + "learning_rate": 7.403807944774291e-06, + "loss": 0.4726, + "step": 6991 + }, + { + "epoch": 0.6, + "learning_rate": 7.401141139095809e-06, + "loss": 0.4744, + "step": 6992 + }, + { + "epoch": 0.6, + "learning_rate": 7.398474531617155e-06, + "loss": 0.4529, + "step": 6993 + }, + { + "epoch": 0.6, + "learning_rate": 7.395808122541697e-06, + "loss": 0.5021, + "step": 6994 + }, + { + "epoch": 0.6, + "learning_rate": 7.393141912072783e-06, + "loss": 0.4773, + "step": 6995 + }, + { + "epoch": 0.6, + "learning_rate": 7.390475900413749e-06, + "loss": 0.4613, + "step": 6996 + }, + { + "epoch": 0.6, + "learning_rate": 7.387810087767916e-06, + "loss": 0.4757, + "step": 6997 + }, + { + "epoch": 0.6, + "learning_rate": 7.385144474338595e-06, + "loss": 0.4684, + "step": 6998 + }, + { + "epoch": 0.6, + "learning_rate": 7.38247906032907e-06, + "loss": 0.4837, + "step": 6999 + }, + { + "epoch": 0.6, + "learning_rate": 7.3798138459426225e-06, + "loss": 0.5051, + "step": 7000 + }, + { + "epoch": 0.6, + "learning_rate": 7.3771488313825055e-06, + "loss": 0.5016, + "step": 7001 + }, + { + "epoch": 0.6, + "learning_rate": 7.37448401685197e-06, + "loss": 0.472, + "step": 7002 + }, + { + "epoch": 0.6, + "learning_rate": 7.371819402554248e-06, + "loss": 0.4673, + "step": 7003 + }, + { + "epoch": 0.6, + "learning_rate": 7.3691549886925505e-06, + "loss": 0.4543, + "step": 7004 + }, + { + "epoch": 0.6, + "learning_rate": 7.366490775470074e-06, + "loss": 0.4724, + "step": 7005 + }, + { + "epoch": 0.6, + "learning_rate": 7.363826763090005e-06, + "loss": 0.464, + "step": 7006 + }, + { + "epoch": 0.6, + "learning_rate": 7.361162951755516e-06, + "loss": 0.4667, + "step": 7007 + }, + { + "epoch": 0.6, + "learning_rate": 7.358499341669756e-06, + "loss": 0.4725, + "step": 7008 + }, + { + "epoch": 0.6, + "learning_rate": 7.355835933035864e-06, + "loss": 0.4735, + "step": 7009 + }, + { + "epoch": 0.6, + "learning_rate": 7.353172726056963e-06, + "loss": 0.4715, + "step": 7010 + }, + { + "epoch": 0.6, + "learning_rate": 7.350509720936157e-06, + "loss": 0.4585, + "step": 7011 + }, + { + "epoch": 0.6, + "learning_rate": 7.3478469178765444e-06, + "loss": 0.4734, + "step": 7012 + }, + { + "epoch": 0.6, + "learning_rate": 7.3451843170812e-06, + "loss": 0.4667, + "step": 7013 + }, + { + "epoch": 0.6, + "learning_rate": 7.3425219187531805e-06, + "loss": 0.4747, + "step": 7014 + }, + { + "epoch": 0.6, + "learning_rate": 7.33985972309553e-06, + "loss": 0.4721, + "step": 7015 + }, + { + "epoch": 0.6, + "learning_rate": 7.3371977303112895e-06, + "loss": 0.4603, + "step": 7016 + }, + { + "epoch": 0.6, + "learning_rate": 7.3345359406034646e-06, + "loss": 0.4722, + "step": 7017 + }, + { + "epoch": 0.6, + "learning_rate": 7.331874354175057e-06, + "loss": 0.4826, + "step": 7018 + }, + { + "epoch": 0.6, + "learning_rate": 7.329212971229049e-06, + "loss": 0.4771, + "step": 7019 + }, + { + "epoch": 0.6, + "learning_rate": 7.326551791968408e-06, + "loss": 0.4637, + "step": 7020 + }, + { + "epoch": 0.6, + "learning_rate": 7.323890816596094e-06, + "loss": 0.467, + "step": 7021 + }, + { + "epoch": 0.6, + "learning_rate": 7.321230045315035e-06, + "loss": 0.4785, + "step": 7022 + }, + { + "epoch": 0.6, + "learning_rate": 7.31856947832816e-06, + "loss": 0.4739, + "step": 7023 + }, + { + "epoch": 0.6, + "learning_rate": 7.315909115838367e-06, + "loss": 0.4669, + "step": 7024 + }, + { + "epoch": 0.6, + "learning_rate": 7.313248958048553e-06, + "loss": 0.4623, + "step": 7025 + }, + { + "epoch": 0.6, + "learning_rate": 7.310589005161589e-06, + "loss": 0.4692, + "step": 7026 + }, + { + "epoch": 0.6, + "learning_rate": 7.307929257380337e-06, + "loss": 0.4864, + "step": 7027 + }, + { + "epoch": 0.6, + "learning_rate": 7.305269714907639e-06, + "loss": 0.4838, + "step": 7028 + }, + { + "epoch": 0.6, + "learning_rate": 7.302610377946319e-06, + "loss": 0.4516, + "step": 7029 + }, + { + "epoch": 0.6, + "learning_rate": 7.299951246699198e-06, + "loss": 0.4778, + "step": 7030 + }, + { + "epoch": 0.6, + "learning_rate": 7.297292321369062e-06, + "loss": 0.485, + "step": 7031 + }, + { + "epoch": 0.6, + "learning_rate": 7.294633602158703e-06, + "loss": 0.4598, + "step": 7032 + }, + { + "epoch": 0.6, + "learning_rate": 7.291975089270877e-06, + "loss": 0.4772, + "step": 7033 + }, + { + "epoch": 0.6, + "learning_rate": 7.289316782908334e-06, + "loss": 0.4718, + "step": 7034 + }, + { + "epoch": 0.6, + "learning_rate": 7.286658683273813e-06, + "loss": 0.4615, + "step": 7035 + }, + { + "epoch": 0.6, + "learning_rate": 7.284000790570029e-06, + "loss": 0.4815, + "step": 7036 + }, + { + "epoch": 0.6, + "learning_rate": 7.2813431049996816e-06, + "loss": 0.458, + "step": 7037 + }, + { + "epoch": 0.6, + "learning_rate": 7.278685626765458e-06, + "loss": 0.4624, + "step": 7038 + }, + { + "epoch": 0.6, + "learning_rate": 7.276028356070033e-06, + "loss": 0.4697, + "step": 7039 + }, + { + "epoch": 0.6, + "learning_rate": 7.273371293116056e-06, + "loss": 0.4718, + "step": 7040 + }, + { + "epoch": 0.6, + "learning_rate": 7.2707144381061686e-06, + "loss": 0.482, + "step": 7041 + }, + { + "epoch": 0.6, + "learning_rate": 7.268057791242994e-06, + "loss": 0.4633, + "step": 7042 + }, + { + "epoch": 0.6, + "learning_rate": 7.265401352729133e-06, + "loss": 0.463, + "step": 7043 + }, + { + "epoch": 0.6, + "learning_rate": 7.262745122767183e-06, + "loss": 0.482, + "step": 7044 + }, + { + "epoch": 0.6, + "learning_rate": 7.2600891015597206e-06, + "loss": 0.4727, + "step": 7045 + }, + { + "epoch": 0.6, + "learning_rate": 7.2574332893093e-06, + "loss": 0.4587, + "step": 7046 + }, + { + "epoch": 0.6, + "learning_rate": 7.2547776862184635e-06, + "loss": 0.4865, + "step": 7047 + }, + { + "epoch": 0.6, + "learning_rate": 7.252122292489747e-06, + "loss": 0.4537, + "step": 7048 + }, + { + "epoch": 0.6, + "learning_rate": 7.249467108325654e-06, + "loss": 0.4619, + "step": 7049 + }, + { + "epoch": 0.6, + "learning_rate": 7.246812133928685e-06, + "loss": 0.4715, + "step": 7050 + }, + { + "epoch": 0.6, + "learning_rate": 7.244157369501317e-06, + "loss": 0.4706, + "step": 7051 + }, + { + "epoch": 0.6, + "learning_rate": 7.241502815246009e-06, + "loss": 0.4447, + "step": 7052 + }, + { + "epoch": 0.6, + "learning_rate": 7.238848471365214e-06, + "loss": 0.4701, + "step": 7053 + }, + { + "epoch": 0.6, + "learning_rate": 7.236194338061364e-06, + "loss": 0.4722, + "step": 7054 + }, + { + "epoch": 0.6, + "learning_rate": 7.233540415536871e-06, + "loss": 0.459, + "step": 7055 + }, + { + "epoch": 0.6, + "learning_rate": 7.2308867039941366e-06, + "loss": 0.4838, + "step": 7056 + }, + { + "epoch": 0.6, + "learning_rate": 7.22823320363554e-06, + "loss": 0.4665, + "step": 7057 + }, + { + "epoch": 0.6, + "learning_rate": 7.225579914663452e-06, + "loss": 0.4713, + "step": 7058 + }, + { + "epoch": 0.6, + "learning_rate": 7.222926837280225e-06, + "loss": 0.4752, + "step": 7059 + }, + { + "epoch": 0.6, + "learning_rate": 7.220273971688192e-06, + "loss": 0.4613, + "step": 7060 + }, + { + "epoch": 0.6, + "learning_rate": 7.217621318089666e-06, + "loss": 0.4592, + "step": 7061 + }, + { + "epoch": 0.6, + "learning_rate": 7.214968876686956e-06, + "loss": 0.4633, + "step": 7062 + }, + { + "epoch": 0.6, + "learning_rate": 7.212316647682351e-06, + "loss": 0.4895, + "step": 7063 + }, + { + "epoch": 0.6, + "learning_rate": 7.209664631278113e-06, + "loss": 0.4762, + "step": 7064 + }, + { + "epoch": 0.6, + "learning_rate": 7.2070128276765005e-06, + "loss": 0.4768, + "step": 7065 + }, + { + "epoch": 0.6, + "learning_rate": 7.204361237079746e-06, + "loss": 0.4805, + "step": 7066 + }, + { + "epoch": 0.6, + "learning_rate": 7.201709859690081e-06, + "loss": 0.4902, + "step": 7067 + }, + { + "epoch": 0.6, + "learning_rate": 7.199058695709702e-06, + "loss": 0.4729, + "step": 7068 + }, + { + "epoch": 0.6, + "learning_rate": 7.1964077453408036e-06, + "loss": 0.4816, + "step": 7069 + }, + { + "epoch": 0.6, + "learning_rate": 7.193757008785549e-06, + "loss": 0.4656, + "step": 7070 + }, + { + "epoch": 0.6, + "learning_rate": 7.191106486246103e-06, + "loss": 0.4756, + "step": 7071 + }, + { + "epoch": 0.6, + "learning_rate": 7.1884561779246055e-06, + "loss": 0.4519, + "step": 7072 + }, + { + "epoch": 0.6, + "learning_rate": 7.185806084023177e-06, + "loss": 0.468, + "step": 7073 + }, + { + "epoch": 0.6, + "learning_rate": 7.183156204743926e-06, + "loss": 0.4603, + "step": 7074 + }, + { + "epoch": 0.6, + "learning_rate": 7.180506540288939e-06, + "loss": 0.4686, + "step": 7075 + }, + { + "epoch": 0.6, + "learning_rate": 7.177857090860296e-06, + "loss": 0.4932, + "step": 7076 + }, + { + "epoch": 0.6, + "learning_rate": 7.1752078566600556e-06, + "loss": 0.4775, + "step": 7077 + }, + { + "epoch": 0.6, + "learning_rate": 7.172558837890256e-06, + "loss": 0.4488, + "step": 7078 + }, + { + "epoch": 0.6, + "learning_rate": 7.16991003475292e-06, + "loss": 0.4812, + "step": 7079 + }, + { + "epoch": 0.6, + "learning_rate": 7.167261447450065e-06, + "loss": 0.4619, + "step": 7080 + }, + { + "epoch": 0.6, + "learning_rate": 7.164613076183678e-06, + "loss": 0.4535, + "step": 7081 + }, + { + "epoch": 0.6, + "learning_rate": 7.161964921155733e-06, + "loss": 0.462, + "step": 7082 + }, + { + "epoch": 0.6, + "learning_rate": 7.159316982568194e-06, + "loss": 0.4651, + "step": 7083 + }, + { + "epoch": 0.6, + "learning_rate": 7.156669260622997e-06, + "loss": 0.4614, + "step": 7084 + }, + { + "epoch": 0.6, + "learning_rate": 7.154021755522076e-06, + "loss": 0.4506, + "step": 7085 + }, + { + "epoch": 0.6, + "learning_rate": 7.151374467467338e-06, + "loss": 0.4623, + "step": 7086 + }, + { + "epoch": 0.6, + "learning_rate": 7.148727396660675e-06, + "loss": 0.4752, + "step": 7087 + }, + { + "epoch": 0.6, + "learning_rate": 7.146080543303966e-06, + "loss": 0.4874, + "step": 7088 + }, + { + "epoch": 0.6, + "learning_rate": 7.143433907599064e-06, + "loss": 0.4771, + "step": 7089 + }, + { + "epoch": 0.6, + "learning_rate": 7.140787489747824e-06, + "loss": 0.4533, + "step": 7090 + }, + { + "epoch": 0.6, + "learning_rate": 7.1381412899520655e-06, + "loss": 0.467, + "step": 7091 + }, + { + "epoch": 0.6, + "learning_rate": 7.1354953084136e-06, + "loss": 0.4473, + "step": 7092 + }, + { + "epoch": 0.6, + "learning_rate": 7.132849545334218e-06, + "loss": 0.4646, + "step": 7093 + }, + { + "epoch": 0.6, + "learning_rate": 7.130204000915701e-06, + "loss": 0.4741, + "step": 7094 + }, + { + "epoch": 0.6, + "learning_rate": 7.127558675359811e-06, + "loss": 0.4924, + "step": 7095 + }, + { + "epoch": 0.61, + "learning_rate": 7.124913568868288e-06, + "loss": 0.4614, + "step": 7096 + }, + { + "epoch": 0.61, + "learning_rate": 7.122268681642859e-06, + "loss": 0.4535, + "step": 7097 + }, + { + "epoch": 0.61, + "learning_rate": 7.119624013885231e-06, + "loss": 0.4723, + "step": 7098 + }, + { + "epoch": 0.61, + "learning_rate": 7.116979565797104e-06, + "loss": 0.4675, + "step": 7099 + }, + { + "epoch": 0.61, + "learning_rate": 7.114335337580152e-06, + "loss": 0.4548, + "step": 7100 + }, + { + "epoch": 0.61, + "learning_rate": 7.111691329436034e-06, + "loss": 0.4653, + "step": 7101 + }, + { + "epoch": 0.61, + "learning_rate": 7.109047541566392e-06, + "loss": 0.4659, + "step": 7102 + }, + { + "epoch": 0.61, + "learning_rate": 7.106403974172853e-06, + "loss": 0.4727, + "step": 7103 + }, + { + "epoch": 0.61, + "learning_rate": 7.10376062745703e-06, + "loss": 0.4844, + "step": 7104 + }, + { + "epoch": 0.61, + "learning_rate": 7.101117501620514e-06, + "loss": 0.4759, + "step": 7105 + }, + { + "epoch": 0.61, + "learning_rate": 7.098474596864878e-06, + "loss": 0.4783, + "step": 7106 + }, + { + "epoch": 0.61, + "learning_rate": 7.09583191339168e-06, + "loss": 0.4677, + "step": 7107 + }, + { + "epoch": 0.61, + "learning_rate": 7.0931894514024695e-06, + "loss": 0.4743, + "step": 7108 + }, + { + "epoch": 0.61, + "learning_rate": 7.090547211098765e-06, + "loss": 0.4795, + "step": 7109 + }, + { + "epoch": 0.61, + "learning_rate": 7.087905192682079e-06, + "loss": 0.4587, + "step": 7110 + }, + { + "epoch": 0.61, + "learning_rate": 7.085263396353897e-06, + "loss": 0.4788, + "step": 7111 + }, + { + "epoch": 0.61, + "learning_rate": 7.082621822315696e-06, + "loss": 0.4742, + "step": 7112 + }, + { + "epoch": 0.61, + "learning_rate": 7.079980470768939e-06, + "loss": 0.4988, + "step": 7113 + }, + { + "epoch": 0.61, + "learning_rate": 7.077339341915059e-06, + "loss": 0.4789, + "step": 7114 + }, + { + "epoch": 0.61, + "learning_rate": 7.074698435955485e-06, + "loss": 0.4631, + "step": 7115 + }, + { + "epoch": 0.61, + "learning_rate": 7.072057753091617e-06, + "loss": 0.4568, + "step": 7116 + }, + { + "epoch": 0.61, + "learning_rate": 7.069417293524854e-06, + "loss": 0.4637, + "step": 7117 + }, + { + "epoch": 0.61, + "learning_rate": 7.06677705745656e-06, + "loss": 0.4798, + "step": 7118 + }, + { + "epoch": 0.61, + "learning_rate": 7.064137045088094e-06, + "loss": 0.4595, + "step": 7119 + }, + { + "epoch": 0.61, + "learning_rate": 7.061497256620793e-06, + "loss": 0.4758, + "step": 7120 + }, + { + "epoch": 0.61, + "learning_rate": 7.058857692255977e-06, + "loss": 0.4923, + "step": 7121 + }, + { + "epoch": 0.61, + "learning_rate": 7.0562183521949565e-06, + "loss": 0.4658, + "step": 7122 + }, + { + "epoch": 0.61, + "learning_rate": 7.053579236639012e-06, + "loss": 0.4598, + "step": 7123 + }, + { + "epoch": 0.61, + "learning_rate": 7.0509403457894184e-06, + "loss": 0.4951, + "step": 7124 + }, + { + "epoch": 0.61, + "learning_rate": 7.0483016798474215e-06, + "loss": 0.4683, + "step": 7125 + }, + { + "epoch": 0.61, + "learning_rate": 7.045663239014265e-06, + "loss": 0.449, + "step": 7126 + }, + { + "epoch": 0.61, + "learning_rate": 7.043025023491163e-06, + "loss": 0.4779, + "step": 7127 + }, + { + "epoch": 0.61, + "learning_rate": 7.040387033479319e-06, + "loss": 0.5029, + "step": 7128 + }, + { + "epoch": 0.61, + "learning_rate": 7.037749269179914e-06, + "loss": 0.4777, + "step": 7129 + }, + { + "epoch": 0.61, + "learning_rate": 7.035111730794115e-06, + "loss": 0.471, + "step": 7130 + }, + { + "epoch": 0.61, + "learning_rate": 7.032474418523076e-06, + "loss": 0.4631, + "step": 7131 + }, + { + "epoch": 0.61, + "learning_rate": 7.029837332567928e-06, + "loss": 0.4786, + "step": 7132 + }, + { + "epoch": 0.61, + "learning_rate": 7.027200473129785e-06, + "loss": 0.4613, + "step": 7133 + }, + { + "epoch": 0.61, + "learning_rate": 7.024563840409745e-06, + "loss": 0.4675, + "step": 7134 + }, + { + "epoch": 0.61, + "learning_rate": 7.0219274346088835e-06, + "loss": 0.452, + "step": 7135 + }, + { + "epoch": 0.61, + "learning_rate": 7.019291255928274e-06, + "loss": 0.4652, + "step": 7136 + }, + { + "epoch": 0.61, + "learning_rate": 7.016655304568957e-06, + "loss": 0.4783, + "step": 7137 + }, + { + "epoch": 0.61, + "learning_rate": 7.01401958073196e-06, + "loss": 0.4883, + "step": 7138 + }, + { + "epoch": 0.61, + "learning_rate": 7.011384084618293e-06, + "loss": 0.4851, + "step": 7139 + }, + { + "epoch": 0.61, + "learning_rate": 7.008748816428958e-06, + "loss": 0.4709, + "step": 7140 + }, + { + "epoch": 0.61, + "learning_rate": 7.006113776364924e-06, + "loss": 0.4606, + "step": 7141 + }, + { + "epoch": 0.61, + "learning_rate": 7.003478964627156e-06, + "loss": 0.475, + "step": 7142 + }, + { + "epoch": 0.61, + "learning_rate": 7.000844381416589e-06, + "loss": 0.4691, + "step": 7143 + }, + { + "epoch": 0.61, + "learning_rate": 6.998210026934148e-06, + "loss": 0.4655, + "step": 7144 + }, + { + "epoch": 0.61, + "learning_rate": 6.9955759013807465e-06, + "loss": 0.4707, + "step": 7145 + }, + { + "epoch": 0.61, + "learning_rate": 6.992942004957271e-06, + "loss": 0.4756, + "step": 7146 + }, + { + "epoch": 0.61, + "learning_rate": 6.99030833786459e-06, + "loss": 0.451, + "step": 7147 + }, + { + "epoch": 0.61, + "learning_rate": 6.987674900303558e-06, + "loss": 0.474, + "step": 7148 + }, + { + "epoch": 0.61, + "learning_rate": 6.985041692475018e-06, + "loss": 0.461, + "step": 7149 + }, + { + "epoch": 0.61, + "learning_rate": 6.9824087145797825e-06, + "loss": 0.4798, + "step": 7150 + }, + { + "epoch": 0.61, + "learning_rate": 6.979775966818661e-06, + "loss": 0.4735, + "step": 7151 + }, + { + "epoch": 0.61, + "learning_rate": 6.9771434493924296e-06, + "loss": 0.441, + "step": 7152 + }, + { + "epoch": 0.61, + "learning_rate": 6.974511162501857e-06, + "loss": 0.4854, + "step": 7153 + }, + { + "epoch": 0.61, + "learning_rate": 6.971879106347699e-06, + "loss": 0.4784, + "step": 7154 + }, + { + "epoch": 0.61, + "learning_rate": 6.969247281130681e-06, + "loss": 0.4662, + "step": 7155 + }, + { + "epoch": 0.61, + "learning_rate": 6.966615687051517e-06, + "loss": 0.4777, + "step": 7156 + }, + { + "epoch": 0.61, + "learning_rate": 6.963984324310903e-06, + "loss": 0.4617, + "step": 7157 + }, + { + "epoch": 0.61, + "learning_rate": 6.961353193109524e-06, + "loss": 0.4737, + "step": 7158 + }, + { + "epoch": 0.61, + "learning_rate": 6.958722293648032e-06, + "loss": 0.4734, + "step": 7159 + }, + { + "epoch": 0.61, + "learning_rate": 6.95609162612708e-06, + "loss": 0.4703, + "step": 7160 + }, + { + "epoch": 0.61, + "learning_rate": 6.953461190747283e-06, + "loss": 0.4659, + "step": 7161 + }, + { + "epoch": 0.61, + "learning_rate": 6.9508309877092566e-06, + "loss": 0.4591, + "step": 7162 + }, + { + "epoch": 0.61, + "learning_rate": 6.948201017213589e-06, + "loss": 0.4782, + "step": 7163 + }, + { + "epoch": 0.61, + "learning_rate": 6.945571279460857e-06, + "loss": 0.474, + "step": 7164 + }, + { + "epoch": 0.61, + "learning_rate": 6.942941774651606e-06, + "loss": 0.4568, + "step": 7165 + }, + { + "epoch": 0.61, + "learning_rate": 6.94031250298638e-06, + "loss": 0.489, + "step": 7166 + }, + { + "epoch": 0.61, + "learning_rate": 6.937683464665694e-06, + "loss": 0.4452, + "step": 7167 + }, + { + "epoch": 0.61, + "learning_rate": 6.935054659890053e-06, + "loss": 0.4686, + "step": 7168 + }, + { + "epoch": 0.61, + "learning_rate": 6.9324260888599405e-06, + "loss": 0.4878, + "step": 7169 + }, + { + "epoch": 0.61, + "learning_rate": 6.92979775177582e-06, + "loss": 0.4582, + "step": 7170 + }, + { + "epoch": 0.61, + "learning_rate": 6.927169648838139e-06, + "loss": 0.4564, + "step": 7171 + }, + { + "epoch": 0.61, + "learning_rate": 6.9245417802473335e-06, + "loss": 0.4756, + "step": 7172 + }, + { + "epoch": 0.61, + "learning_rate": 6.92191414620381e-06, + "loss": 0.4696, + "step": 7173 + }, + { + "epoch": 0.61, + "learning_rate": 6.9192867469079625e-06, + "loss": 0.4593, + "step": 7174 + }, + { + "epoch": 0.61, + "learning_rate": 6.916659582560172e-06, + "loss": 0.4608, + "step": 7175 + }, + { + "epoch": 0.61, + "learning_rate": 6.914032653360792e-06, + "loss": 0.4474, + "step": 7176 + }, + { + "epoch": 0.61, + "learning_rate": 6.911405959510164e-06, + "loss": 0.4753, + "step": 7177 + }, + { + "epoch": 0.61, + "learning_rate": 6.9087795012086165e-06, + "loss": 0.4564, + "step": 7178 + }, + { + "epoch": 0.61, + "learning_rate": 6.9061532786564465e-06, + "loss": 0.4691, + "step": 7179 + }, + { + "epoch": 0.61, + "learning_rate": 6.903527292053942e-06, + "loss": 0.4677, + "step": 7180 + }, + { + "epoch": 0.61, + "learning_rate": 6.900901541601379e-06, + "loss": 0.472, + "step": 7181 + }, + { + "epoch": 0.61, + "learning_rate": 6.898276027499002e-06, + "loss": 0.4776, + "step": 7182 + }, + { + "epoch": 0.61, + "learning_rate": 6.895650749947041e-06, + "loss": 0.472, + "step": 7183 + }, + { + "epoch": 0.61, + "learning_rate": 6.8930257091457175e-06, + "loss": 0.4735, + "step": 7184 + }, + { + "epoch": 0.61, + "learning_rate": 6.89040090529522e-06, + "loss": 0.4534, + "step": 7185 + }, + { + "epoch": 0.61, + "learning_rate": 6.887776338595735e-06, + "loss": 0.4609, + "step": 7186 + }, + { + "epoch": 0.61, + "learning_rate": 6.88515200924742e-06, + "loss": 0.4705, + "step": 7187 + }, + { + "epoch": 0.61, + "learning_rate": 6.882527917450416e-06, + "loss": 0.4499, + "step": 7188 + }, + { + "epoch": 0.61, + "learning_rate": 6.8799040634048496e-06, + "loss": 0.4785, + "step": 7189 + }, + { + "epoch": 0.61, + "learning_rate": 6.877280447310821e-06, + "loss": 0.4729, + "step": 7190 + }, + { + "epoch": 0.61, + "learning_rate": 6.874657069368427e-06, + "loss": 0.4637, + "step": 7191 + }, + { + "epoch": 0.61, + "learning_rate": 6.872033929777731e-06, + "loss": 0.4524, + "step": 7192 + }, + { + "epoch": 0.61, + "learning_rate": 6.869411028738787e-06, + "loss": 0.4669, + "step": 7193 + }, + { + "epoch": 0.61, + "learning_rate": 6.866788366451624e-06, + "loss": 0.4662, + "step": 7194 + }, + { + "epoch": 0.61, + "learning_rate": 6.864165943116265e-06, + "loss": 0.4542, + "step": 7195 + }, + { + "epoch": 0.61, + "learning_rate": 6.861543758932703e-06, + "loss": 0.4613, + "step": 7196 + }, + { + "epoch": 0.61, + "learning_rate": 6.858921814100914e-06, + "loss": 0.4537, + "step": 7197 + }, + { + "epoch": 0.61, + "learning_rate": 6.856300108820865e-06, + "loss": 0.4646, + "step": 7198 + }, + { + "epoch": 0.61, + "learning_rate": 6.85367864329249e-06, + "loss": 0.4552, + "step": 7199 + }, + { + "epoch": 0.61, + "learning_rate": 6.851057417715719e-06, + "loss": 0.4608, + "step": 7200 + }, + { + "epoch": 0.61, + "learning_rate": 6.8484364322904565e-06, + "loss": 0.4525, + "step": 7201 + }, + { + "epoch": 0.61, + "learning_rate": 6.84581568721659e-06, + "loss": 0.4719, + "step": 7202 + }, + { + "epoch": 0.61, + "learning_rate": 6.843195182693982e-06, + "loss": 0.4724, + "step": 7203 + }, + { + "epoch": 0.61, + "learning_rate": 6.8405749189224935e-06, + "loss": 0.4686, + "step": 7204 + }, + { + "epoch": 0.61, + "learning_rate": 6.8379548961019526e-06, + "loss": 0.4788, + "step": 7205 + }, + { + "epoch": 0.61, + "learning_rate": 6.835335114432169e-06, + "loss": 0.4712, + "step": 7206 + }, + { + "epoch": 0.61, + "learning_rate": 6.832715574112946e-06, + "loss": 0.4788, + "step": 7207 + }, + { + "epoch": 0.61, + "learning_rate": 6.8300962753440514e-06, + "loss": 0.45, + "step": 7208 + }, + { + "epoch": 0.61, + "learning_rate": 6.82747721832525e-06, + "loss": 0.4753, + "step": 7209 + }, + { + "epoch": 0.61, + "learning_rate": 6.824858403256284e-06, + "loss": 0.4911, + "step": 7210 + }, + { + "epoch": 0.61, + "learning_rate": 6.8222398303368705e-06, + "loss": 0.4539, + "step": 7211 + }, + { + "epoch": 0.61, + "learning_rate": 6.819621499766713e-06, + "loss": 0.4847, + "step": 7212 + }, + { + "epoch": 0.62, + "learning_rate": 6.8170034117454965e-06, + "loss": 0.4658, + "step": 7213 + }, + { + "epoch": 0.62, + "learning_rate": 6.814385566472892e-06, + "loss": 0.4863, + "step": 7214 + }, + { + "epoch": 0.62, + "learning_rate": 6.811767964148542e-06, + "loss": 0.4729, + "step": 7215 + }, + { + "epoch": 0.62, + "learning_rate": 6.809150604972079e-06, + "loss": 0.47, + "step": 7216 + }, + { + "epoch": 0.62, + "learning_rate": 6.806533489143108e-06, + "loss": 0.4747, + "step": 7217 + }, + { + "epoch": 0.62, + "learning_rate": 6.803916616861228e-06, + "loss": 0.4496, + "step": 7218 + }, + { + "epoch": 0.62, + "learning_rate": 6.801299988326011e-06, + "loss": 0.4874, + "step": 7219 + }, + { + "epoch": 0.62, + "learning_rate": 6.798683603737013e-06, + "loss": 0.465, + "step": 7220 + }, + { + "epoch": 0.62, + "learning_rate": 6.796067463293765e-06, + "loss": 0.4711, + "step": 7221 + }, + { + "epoch": 0.62, + "learning_rate": 6.793451567195785e-06, + "loss": 0.4636, + "step": 7222 + }, + { + "epoch": 0.62, + "learning_rate": 6.7908359156425814e-06, + "loss": 0.4771, + "step": 7223 + }, + { + "epoch": 0.62, + "learning_rate": 6.788220508833627e-06, + "loss": 0.452, + "step": 7224 + }, + { + "epoch": 0.62, + "learning_rate": 6.785605346968387e-06, + "loss": 0.4823, + "step": 7225 + }, + { + "epoch": 0.62, + "learning_rate": 6.782990430246299e-06, + "loss": 0.4773, + "step": 7226 + }, + { + "epoch": 0.62, + "learning_rate": 6.780375758866793e-06, + "loss": 0.4534, + "step": 7227 + }, + { + "epoch": 0.62, + "learning_rate": 6.777761333029274e-06, + "loss": 0.4682, + "step": 7228 + }, + { + "epoch": 0.62, + "learning_rate": 6.77514715293313e-06, + "loss": 0.4712, + "step": 7229 + }, + { + "epoch": 0.62, + "learning_rate": 6.7725332187777244e-06, + "loss": 0.4672, + "step": 7230 + }, + { + "epoch": 0.62, + "learning_rate": 6.769919530762409e-06, + "loss": 0.4559, + "step": 7231 + }, + { + "epoch": 0.62, + "learning_rate": 6.7673060890865184e-06, + "loss": 0.4661, + "step": 7232 + }, + { + "epoch": 0.62, + "learning_rate": 6.764692893949361e-06, + "loss": 0.4826, + "step": 7233 + }, + { + "epoch": 0.62, + "learning_rate": 6.7620799455502305e-06, + "loss": 0.4486, + "step": 7234 + }, + { + "epoch": 0.62, + "learning_rate": 6.759467244088398e-06, + "loss": 0.4908, + "step": 7235 + }, + { + "epoch": 0.62, + "learning_rate": 6.756854789763123e-06, + "loss": 0.4563, + "step": 7236 + }, + { + "epoch": 0.62, + "learning_rate": 6.754242582773646e-06, + "loss": 0.4646, + "step": 7237 + }, + { + "epoch": 0.62, + "learning_rate": 6.751630623319179e-06, + "loss": 0.472, + "step": 7238 + }, + { + "epoch": 0.62, + "learning_rate": 6.74901891159892e-06, + "loss": 0.4628, + "step": 7239 + }, + { + "epoch": 0.62, + "learning_rate": 6.746407447812049e-06, + "loss": 0.4657, + "step": 7240 + }, + { + "epoch": 0.62, + "learning_rate": 6.743796232157734e-06, + "loss": 0.4669, + "step": 7241 + }, + { + "epoch": 0.62, + "learning_rate": 6.741185264835111e-06, + "loss": 0.4693, + "step": 7242 + }, + { + "epoch": 0.62, + "learning_rate": 6.738574546043306e-06, + "loss": 0.4596, + "step": 7243 + }, + { + "epoch": 0.62, + "learning_rate": 6.7359640759814204e-06, + "loss": 0.4815, + "step": 7244 + }, + { + "epoch": 0.62, + "learning_rate": 6.733353854848539e-06, + "loss": 0.4638, + "step": 7245 + }, + { + "epoch": 0.62, + "learning_rate": 6.730743882843736e-06, + "loss": 0.464, + "step": 7246 + }, + { + "epoch": 0.62, + "learning_rate": 6.728134160166051e-06, + "loss": 0.4748, + "step": 7247 + }, + { + "epoch": 0.62, + "learning_rate": 6.7255246870145144e-06, + "loss": 0.4637, + "step": 7248 + }, + { + "epoch": 0.62, + "learning_rate": 6.7229154635881334e-06, + "loss": 0.5037, + "step": 7249 + }, + { + "epoch": 0.62, + "learning_rate": 6.720306490085904e-06, + "loss": 0.4606, + "step": 7250 + }, + { + "epoch": 0.62, + "learning_rate": 6.717697766706792e-06, + "loss": 0.4594, + "step": 7251 + }, + { + "epoch": 0.62, + "learning_rate": 6.7150892936497525e-06, + "loss": 0.476, + "step": 7252 + }, + { + "epoch": 0.62, + "learning_rate": 6.712481071113717e-06, + "loss": 0.466, + "step": 7253 + }, + { + "epoch": 0.62, + "learning_rate": 6.709873099297597e-06, + "loss": 0.4744, + "step": 7254 + }, + { + "epoch": 0.62, + "learning_rate": 6.7072653784002965e-06, + "loss": 0.4767, + "step": 7255 + }, + { + "epoch": 0.62, + "learning_rate": 6.70465790862068e-06, + "loss": 0.4605, + "step": 7256 + }, + { + "epoch": 0.62, + "learning_rate": 6.702050690157614e-06, + "loss": 0.4643, + "step": 7257 + }, + { + "epoch": 0.62, + "learning_rate": 6.6994437232099245e-06, + "loss": 0.4666, + "step": 7258 + }, + { + "epoch": 0.62, + "learning_rate": 6.696837007976441e-06, + "loss": 0.4503, + "step": 7259 + }, + { + "epoch": 0.62, + "learning_rate": 6.694230544655955e-06, + "loss": 0.465, + "step": 7260 + }, + { + "epoch": 0.62, + "learning_rate": 6.691624333447252e-06, + "loss": 0.4635, + "step": 7261 + }, + { + "epoch": 0.62, + "learning_rate": 6.689018374549086e-06, + "loss": 0.474, + "step": 7262 + }, + { + "epoch": 0.62, + "learning_rate": 6.6864126681602e-06, + "loss": 0.4805, + "step": 7263 + }, + { + "epoch": 0.62, + "learning_rate": 6.683807214479323e-06, + "loss": 0.4749, + "step": 7264 + }, + { + "epoch": 0.62, + "learning_rate": 6.68120201370515e-06, + "loss": 0.4895, + "step": 7265 + }, + { + "epoch": 0.62, + "learning_rate": 6.678597066036368e-06, + "loss": 0.4519, + "step": 7266 + }, + { + "epoch": 0.62, + "learning_rate": 6.675992371671641e-06, + "loss": 0.4648, + "step": 7267 + }, + { + "epoch": 0.62, + "learning_rate": 6.67338793080961e-06, + "loss": 0.4745, + "step": 7268 + }, + { + "epoch": 0.62, + "learning_rate": 6.670783743648903e-06, + "loss": 0.4635, + "step": 7269 + }, + { + "epoch": 0.62, + "learning_rate": 6.668179810388131e-06, + "loss": 0.4641, + "step": 7270 + }, + { + "epoch": 0.62, + "learning_rate": 6.665576131225874e-06, + "loss": 0.4721, + "step": 7271 + }, + { + "epoch": 0.62, + "learning_rate": 6.6629727063607e-06, + "loss": 0.4617, + "step": 7272 + }, + { + "epoch": 0.62, + "learning_rate": 6.660369535991162e-06, + "loss": 0.4745, + "step": 7273 + }, + { + "epoch": 0.62, + "learning_rate": 6.6577666203157845e-06, + "loss": 0.4615, + "step": 7274 + }, + { + "epoch": 0.62, + "learning_rate": 6.655163959533081e-06, + "loss": 0.4699, + "step": 7275 + }, + { + "epoch": 0.62, + "learning_rate": 6.652561553841537e-06, + "loss": 0.4743, + "step": 7276 + }, + { + "epoch": 0.62, + "learning_rate": 6.649959403439621e-06, + "loss": 0.4768, + "step": 7277 + }, + { + "epoch": 0.62, + "learning_rate": 6.647357508525787e-06, + "loss": 0.4641, + "step": 7278 + }, + { + "epoch": 0.62, + "learning_rate": 6.64475586929847e-06, + "loss": 0.48, + "step": 7279 + }, + { + "epoch": 0.62, + "learning_rate": 6.642154485956076e-06, + "loss": 0.4646, + "step": 7280 + }, + { + "epoch": 0.62, + "learning_rate": 6.6395533586969975e-06, + "loss": 0.4739, + "step": 7281 + }, + { + "epoch": 0.62, + "learning_rate": 6.636952487719612e-06, + "loss": 0.4534, + "step": 7282 + }, + { + "epoch": 0.62, + "learning_rate": 6.634351873222269e-06, + "loss": 0.4682, + "step": 7283 + }, + { + "epoch": 0.62, + "learning_rate": 6.6317515154033064e-06, + "loss": 0.4725, + "step": 7284 + }, + { + "epoch": 0.62, + "learning_rate": 6.629151414461033e-06, + "loss": 0.4577, + "step": 7285 + }, + { + "epoch": 0.62, + "learning_rate": 6.6265515705937435e-06, + "loss": 0.4756, + "step": 7286 + }, + { + "epoch": 0.62, + "learning_rate": 6.623951983999717e-06, + "loss": 0.4639, + "step": 7287 + }, + { + "epoch": 0.62, + "learning_rate": 6.621352654877207e-06, + "loss": 0.4744, + "step": 7288 + }, + { + "epoch": 0.62, + "learning_rate": 6.618753583424449e-06, + "loss": 0.4638, + "step": 7289 + }, + { + "epoch": 0.62, + "learning_rate": 6.616154769839655e-06, + "loss": 0.4679, + "step": 7290 + }, + { + "epoch": 0.62, + "learning_rate": 6.613556214321031e-06, + "loss": 0.4565, + "step": 7291 + }, + { + "epoch": 0.62, + "learning_rate": 6.610957917066745e-06, + "loss": 0.485, + "step": 7292 + }, + { + "epoch": 0.62, + "learning_rate": 6.608359878274959e-06, + "loss": 0.482, + "step": 7293 + }, + { + "epoch": 0.62, + "learning_rate": 6.60576209814381e-06, + "loss": 0.468, + "step": 7294 + }, + { + "epoch": 0.62, + "learning_rate": 6.603164576871408e-06, + "loss": 0.4511, + "step": 7295 + }, + { + "epoch": 0.62, + "learning_rate": 6.600567314655859e-06, + "loss": 0.4872, + "step": 7296 + }, + { + "epoch": 0.62, + "learning_rate": 6.597970311695242e-06, + "loss": 0.4707, + "step": 7297 + }, + { + "epoch": 0.62, + "learning_rate": 6.5953735681876096e-06, + "loss": 0.4535, + "step": 7298 + }, + { + "epoch": 0.62, + "learning_rate": 6.5927770843310045e-06, + "loss": 0.4808, + "step": 7299 + }, + { + "epoch": 0.62, + "learning_rate": 6.59018086032344e-06, + "loss": 0.4957, + "step": 7300 + }, + { + "epoch": 0.62, + "learning_rate": 6.587584896362919e-06, + "loss": 0.448, + "step": 7301 + }, + { + "epoch": 0.62, + "learning_rate": 6.584989192647424e-06, + "loss": 0.471, + "step": 7302 + }, + { + "epoch": 0.62, + "learning_rate": 6.582393749374911e-06, + "loss": 0.46, + "step": 7303 + }, + { + "epoch": 0.62, + "learning_rate": 6.579798566743314e-06, + "loss": 0.4669, + "step": 7304 + }, + { + "epoch": 0.62, + "learning_rate": 6.5772036449505586e-06, + "loss": 0.4612, + "step": 7305 + }, + { + "epoch": 0.62, + "learning_rate": 6.574608984194546e-06, + "loss": 0.4498, + "step": 7306 + }, + { + "epoch": 0.62, + "learning_rate": 6.57201458467315e-06, + "loss": 0.4703, + "step": 7307 + }, + { + "epoch": 0.62, + "learning_rate": 6.569420446584235e-06, + "loss": 0.4439, + "step": 7308 + }, + { + "epoch": 0.62, + "learning_rate": 6.566826570125635e-06, + "loss": 0.48, + "step": 7309 + }, + { + "epoch": 0.62, + "learning_rate": 6.5642329554951754e-06, + "loss": 0.4747, + "step": 7310 + }, + { + "epoch": 0.62, + "learning_rate": 6.561639602890658e-06, + "loss": 0.4604, + "step": 7311 + }, + { + "epoch": 0.62, + "learning_rate": 6.559046512509859e-06, + "loss": 0.476, + "step": 7312 + }, + { + "epoch": 0.62, + "learning_rate": 6.556453684550534e-06, + "loss": 0.4784, + "step": 7313 + }, + { + "epoch": 0.62, + "learning_rate": 6.553861119210429e-06, + "loss": 0.4501, + "step": 7314 + }, + { + "epoch": 0.62, + "learning_rate": 6.551268816687265e-06, + "loss": 0.4541, + "step": 7315 + }, + { + "epoch": 0.62, + "learning_rate": 6.548676777178737e-06, + "loss": 0.4522, + "step": 7316 + }, + { + "epoch": 0.62, + "learning_rate": 6.546085000882528e-06, + "loss": 0.4658, + "step": 7317 + }, + { + "epoch": 0.62, + "learning_rate": 6.543493487996293e-06, + "loss": 0.464, + "step": 7318 + }, + { + "epoch": 0.62, + "learning_rate": 6.540902238717677e-06, + "loss": 0.4794, + "step": 7319 + }, + { + "epoch": 0.62, + "learning_rate": 6.5383112532443e-06, + "loss": 0.4678, + "step": 7320 + }, + { + "epoch": 0.62, + "learning_rate": 6.535720531773757e-06, + "loss": 0.4558, + "step": 7321 + }, + { + "epoch": 0.62, + "learning_rate": 6.533130074503631e-06, + "loss": 0.4602, + "step": 7322 + }, + { + "epoch": 0.62, + "learning_rate": 6.530539881631475e-06, + "loss": 0.4866, + "step": 7323 + }, + { + "epoch": 0.62, + "learning_rate": 6.527949953354835e-06, + "loss": 0.4976, + "step": 7324 + }, + { + "epoch": 0.62, + "learning_rate": 6.525360289871227e-06, + "loss": 0.4822, + "step": 7325 + }, + { + "epoch": 0.62, + "learning_rate": 6.522770891378151e-06, + "loss": 0.4624, + "step": 7326 + }, + { + "epoch": 0.62, + "learning_rate": 6.5201817580730786e-06, + "loss": 0.4796, + "step": 7327 + }, + { + "epoch": 0.62, + "learning_rate": 6.517592890153477e-06, + "loss": 0.4564, + "step": 7328 + }, + { + "epoch": 0.62, + "learning_rate": 6.515004287816781e-06, + "loss": 0.4655, + "step": 7329 + }, + { + "epoch": 0.62, + "learning_rate": 6.5124159512604055e-06, + "loss": 0.4818, + "step": 7330 + }, + { + "epoch": 0.63, + "learning_rate": 6.509827880681752e-06, + "loss": 0.4512, + "step": 7331 + }, + { + "epoch": 0.63, + "learning_rate": 6.507240076278192e-06, + "loss": 0.4831, + "step": 7332 + }, + { + "epoch": 0.63, + "learning_rate": 6.504652538247088e-06, + "loss": 0.4669, + "step": 7333 + }, + { + "epoch": 0.63, + "learning_rate": 6.502065266785773e-06, + "loss": 0.4661, + "step": 7334 + }, + { + "epoch": 0.63, + "learning_rate": 6.499478262091566e-06, + "loss": 0.454, + "step": 7335 + }, + { + "epoch": 0.63, + "learning_rate": 6.496891524361757e-06, + "loss": 0.4668, + "step": 7336 + }, + { + "epoch": 0.63, + "learning_rate": 6.494305053793628e-06, + "loss": 0.4545, + "step": 7337 + }, + { + "epoch": 0.63, + "learning_rate": 6.491718850584433e-06, + "loss": 0.4543, + "step": 7338 + }, + { + "epoch": 0.63, + "learning_rate": 6.489132914931403e-06, + "loss": 0.4686, + "step": 7339 + }, + { + "epoch": 0.63, + "learning_rate": 6.486547247031756e-06, + "loss": 0.4543, + "step": 7340 + }, + { + "epoch": 0.63, + "learning_rate": 6.48396184708268e-06, + "loss": 0.4571, + "step": 7341 + }, + { + "epoch": 0.63, + "learning_rate": 6.481376715281358e-06, + "loss": 0.4633, + "step": 7342 + }, + { + "epoch": 0.63, + "learning_rate": 6.478791851824935e-06, + "loss": 0.4608, + "step": 7343 + }, + { + "epoch": 0.63, + "learning_rate": 6.476207256910547e-06, + "loss": 0.4546, + "step": 7344 + }, + { + "epoch": 0.63, + "learning_rate": 6.4736229307353035e-06, + "loss": 0.4859, + "step": 7345 + }, + { + "epoch": 0.63, + "learning_rate": 6.4710388734962955e-06, + "loss": 0.4675, + "step": 7346 + }, + { + "epoch": 0.63, + "learning_rate": 6.468455085390601e-06, + "loss": 0.4662, + "step": 7347 + }, + { + "epoch": 0.63, + "learning_rate": 6.4658715666152625e-06, + "loss": 0.4873, + "step": 7348 + }, + { + "epoch": 0.63, + "learning_rate": 6.4632883173673145e-06, + "loss": 0.4568, + "step": 7349 + }, + { + "epoch": 0.63, + "learning_rate": 6.460705337843761e-06, + "loss": 0.481, + "step": 7350 + }, + { + "epoch": 0.63, + "learning_rate": 6.458122628241599e-06, + "loss": 0.4832, + "step": 7351 + }, + { + "epoch": 0.63, + "learning_rate": 6.4555401887577895e-06, + "loss": 0.4839, + "step": 7352 + }, + { + "epoch": 0.63, + "learning_rate": 6.452958019589286e-06, + "loss": 0.4547, + "step": 7353 + }, + { + "epoch": 0.63, + "learning_rate": 6.450376120933008e-06, + "loss": 0.4694, + "step": 7354 + }, + { + "epoch": 0.63, + "learning_rate": 6.447794492985867e-06, + "loss": 0.4642, + "step": 7355 + }, + { + "epoch": 0.63, + "learning_rate": 6.445213135944751e-06, + "loss": 0.4541, + "step": 7356 + }, + { + "epoch": 0.63, + "learning_rate": 6.4426320500065196e-06, + "loss": 0.4753, + "step": 7357 + }, + { + "epoch": 0.63, + "learning_rate": 6.440051235368022e-06, + "loss": 0.4713, + "step": 7358 + }, + { + "epoch": 0.63, + "learning_rate": 6.437470692226075e-06, + "loss": 0.4655, + "step": 7359 + }, + { + "epoch": 0.63, + "learning_rate": 6.434890420777491e-06, + "loss": 0.4501, + "step": 7360 + }, + { + "epoch": 0.63, + "learning_rate": 6.432310421219046e-06, + "loss": 0.4634, + "step": 7361 + }, + { + "epoch": 0.63, + "learning_rate": 6.429730693747503e-06, + "loss": 0.4731, + "step": 7362 + }, + { + "epoch": 0.63, + "learning_rate": 6.427151238559602e-06, + "loss": 0.4732, + "step": 7363 + }, + { + "epoch": 0.63, + "learning_rate": 6.424572055852062e-06, + "loss": 0.4837, + "step": 7364 + }, + { + "epoch": 0.63, + "learning_rate": 6.421993145821588e-06, + "loss": 0.4723, + "step": 7365 + }, + { + "epoch": 0.63, + "learning_rate": 6.419414508664851e-06, + "loss": 0.4705, + "step": 7366 + }, + { + "epoch": 0.63, + "learning_rate": 6.416836144578516e-06, + "loss": 0.4588, + "step": 7367 + }, + { + "epoch": 0.63, + "learning_rate": 6.41425805375921e-06, + "loss": 0.4721, + "step": 7368 + }, + { + "epoch": 0.63, + "learning_rate": 6.411680236403559e-06, + "loss": 0.4644, + "step": 7369 + }, + { + "epoch": 0.63, + "learning_rate": 6.409102692708154e-06, + "loss": 0.4564, + "step": 7370 + }, + { + "epoch": 0.63, + "learning_rate": 6.40652542286957e-06, + "loss": 0.4738, + "step": 7371 + }, + { + "epoch": 0.63, + "learning_rate": 6.403948427084356e-06, + "loss": 0.4707, + "step": 7372 + }, + { + "epoch": 0.63, + "learning_rate": 6.401371705549046e-06, + "loss": 0.4666, + "step": 7373 + }, + { + "epoch": 0.63, + "learning_rate": 6.39879525846016e-06, + "loss": 0.4768, + "step": 7374 + }, + { + "epoch": 0.63, + "learning_rate": 6.396219086014179e-06, + "loss": 0.4653, + "step": 7375 + }, + { + "epoch": 0.63, + "learning_rate": 6.393643188407579e-06, + "loss": 0.4499, + "step": 7376 + }, + { + "epoch": 0.63, + "learning_rate": 6.391067565836801e-06, + "loss": 0.47, + "step": 7377 + }, + { + "epoch": 0.63, + "learning_rate": 6.388492218498277e-06, + "loss": 0.4638, + "step": 7378 + }, + { + "epoch": 0.63, + "learning_rate": 6.385917146588419e-06, + "loss": 0.4686, + "step": 7379 + }, + { + "epoch": 0.63, + "learning_rate": 6.3833423503036054e-06, + "loss": 0.4671, + "step": 7380 + }, + { + "epoch": 0.63, + "learning_rate": 6.380767829840202e-06, + "loss": 0.4584, + "step": 7381 + }, + { + "epoch": 0.63, + "learning_rate": 6.378193585394552e-06, + "loss": 0.4632, + "step": 7382 + }, + { + "epoch": 0.63, + "learning_rate": 6.375619617162985e-06, + "loss": 0.4653, + "step": 7383 + }, + { + "epoch": 0.63, + "learning_rate": 6.373045925341794e-06, + "loss": 0.4634, + "step": 7384 + }, + { + "epoch": 0.63, + "learning_rate": 6.370472510127265e-06, + "loss": 0.4686, + "step": 7385 + }, + { + "epoch": 0.63, + "learning_rate": 6.367899371715653e-06, + "loss": 0.4537, + "step": 7386 + }, + { + "epoch": 0.63, + "learning_rate": 6.365326510303196e-06, + "loss": 0.4831, + "step": 7387 + }, + { + "epoch": 0.63, + "learning_rate": 6.362753926086118e-06, + "loss": 0.4752, + "step": 7388 + }, + { + "epoch": 0.63, + "learning_rate": 6.360181619260613e-06, + "loss": 0.4587, + "step": 7389 + }, + { + "epoch": 0.63, + "learning_rate": 6.357609590022849e-06, + "loss": 0.4686, + "step": 7390 + }, + { + "epoch": 0.63, + "learning_rate": 6.355037838568981e-06, + "loss": 0.4697, + "step": 7391 + }, + { + "epoch": 0.63, + "learning_rate": 6.352466365095151e-06, + "loss": 0.4603, + "step": 7392 + }, + { + "epoch": 0.63, + "learning_rate": 6.349895169797462e-06, + "loss": 0.4622, + "step": 7393 + }, + { + "epoch": 0.63, + "learning_rate": 6.3473242528720065e-06, + "loss": 0.4645, + "step": 7394 + }, + { + "epoch": 0.63, + "learning_rate": 6.3447536145148515e-06, + "loss": 0.4425, + "step": 7395 + }, + { + "epoch": 0.63, + "learning_rate": 6.342183254922045e-06, + "loss": 0.4701, + "step": 7396 + }, + { + "epoch": 0.63, + "learning_rate": 6.339613174289618e-06, + "loss": 0.4669, + "step": 7397 + }, + { + "epoch": 0.63, + "learning_rate": 6.337043372813572e-06, + "loss": 0.4684, + "step": 7398 + }, + { + "epoch": 0.63, + "learning_rate": 6.334473850689889e-06, + "loss": 0.4575, + "step": 7399 + }, + { + "epoch": 0.63, + "learning_rate": 6.331904608114534e-06, + "loss": 0.4699, + "step": 7400 + }, + { + "epoch": 0.63, + "learning_rate": 6.3293356452834445e-06, + "loss": 0.4708, + "step": 7401 + }, + { + "epoch": 0.63, + "learning_rate": 6.326766962392544e-06, + "loss": 0.4535, + "step": 7402 + }, + { + "epoch": 0.63, + "learning_rate": 6.324198559637733e-06, + "loss": 0.4785, + "step": 7403 + }, + { + "epoch": 0.63, + "learning_rate": 6.321630437214885e-06, + "loss": 0.4701, + "step": 7404 + }, + { + "epoch": 0.63, + "learning_rate": 6.319062595319853e-06, + "loss": 0.455, + "step": 7405 + }, + { + "epoch": 0.63, + "learning_rate": 6.31649503414848e-06, + "loss": 0.4513, + "step": 7406 + }, + { + "epoch": 0.63, + "learning_rate": 6.313927753896573e-06, + "loss": 0.4535, + "step": 7407 + }, + { + "epoch": 0.63, + "learning_rate": 6.311360754759923e-06, + "loss": 0.455, + "step": 7408 + }, + { + "epoch": 0.63, + "learning_rate": 6.308794036934304e-06, + "loss": 0.4531, + "step": 7409 + }, + { + "epoch": 0.63, + "learning_rate": 6.3062276006154576e-06, + "loss": 0.473, + "step": 7410 + }, + { + "epoch": 0.63, + "learning_rate": 6.303661445999116e-06, + "loss": 0.4723, + "step": 7411 + }, + { + "epoch": 0.63, + "learning_rate": 6.301095573280988e-06, + "loss": 0.4502, + "step": 7412 + }, + { + "epoch": 0.63, + "learning_rate": 6.298529982656752e-06, + "loss": 0.464, + "step": 7413 + }, + { + "epoch": 0.63, + "learning_rate": 6.295964674322069e-06, + "loss": 0.4805, + "step": 7414 + }, + { + "epoch": 0.63, + "learning_rate": 6.293399648472589e-06, + "loss": 0.4546, + "step": 7415 + }, + { + "epoch": 0.63, + "learning_rate": 6.290834905303926e-06, + "loss": 0.4502, + "step": 7416 + }, + { + "epoch": 0.63, + "learning_rate": 6.288270445011677e-06, + "loss": 0.4768, + "step": 7417 + }, + { + "epoch": 0.63, + "learning_rate": 6.2857062677914225e-06, + "loss": 0.4602, + "step": 7418 + }, + { + "epoch": 0.63, + "learning_rate": 6.2831423738387095e-06, + "loss": 0.4889, + "step": 7419 + }, + { + "epoch": 0.63, + "learning_rate": 6.280578763349079e-06, + "loss": 0.4852, + "step": 7420 + }, + { + "epoch": 0.63, + "learning_rate": 6.278015436518042e-06, + "loss": 0.451, + "step": 7421 + }, + { + "epoch": 0.63, + "learning_rate": 6.2754523935410845e-06, + "loss": 0.4817, + "step": 7422 + }, + { + "epoch": 0.63, + "learning_rate": 6.272889634613679e-06, + "loss": 0.4558, + "step": 7423 + }, + { + "epoch": 0.63, + "learning_rate": 6.270327159931267e-06, + "loss": 0.469, + "step": 7424 + }, + { + "epoch": 0.63, + "learning_rate": 6.26776496968928e-06, + "loss": 0.442, + "step": 7425 + }, + { + "epoch": 0.63, + "learning_rate": 6.265203064083117e-06, + "loss": 0.4801, + "step": 7426 + }, + { + "epoch": 0.63, + "learning_rate": 6.26264144330816e-06, + "loss": 0.4671, + "step": 7427 + }, + { + "epoch": 0.63, + "learning_rate": 6.260080107559767e-06, + "loss": 0.4644, + "step": 7428 + }, + { + "epoch": 0.63, + "learning_rate": 6.257519057033281e-06, + "loss": 0.4647, + "step": 7429 + }, + { + "epoch": 0.63, + "learning_rate": 6.254958291924018e-06, + "loss": 0.4747, + "step": 7430 + }, + { + "epoch": 0.63, + "learning_rate": 6.2523978124272686e-06, + "loss": 0.464, + "step": 7431 + }, + { + "epoch": 0.63, + "learning_rate": 6.24983761873831e-06, + "loss": 0.4348, + "step": 7432 + }, + { + "epoch": 0.63, + "learning_rate": 6.247277711052388e-06, + "loss": 0.4774, + "step": 7433 + }, + { + "epoch": 0.63, + "learning_rate": 6.244718089564735e-06, + "loss": 0.467, + "step": 7434 + }, + { + "epoch": 0.63, + "learning_rate": 6.242158754470562e-06, + "loss": 0.4658, + "step": 7435 + }, + { + "epoch": 0.63, + "learning_rate": 6.23959970596505e-06, + "loss": 0.4639, + "step": 7436 + }, + { + "epoch": 0.63, + "learning_rate": 6.23704094424336e-06, + "loss": 0.4804, + "step": 7437 + }, + { + "epoch": 0.63, + "learning_rate": 6.234482469500639e-06, + "loss": 0.4471, + "step": 7438 + }, + { + "epoch": 0.63, + "learning_rate": 6.231924281932007e-06, + "loss": 0.4842, + "step": 7439 + }, + { + "epoch": 0.63, + "learning_rate": 6.22936638173256e-06, + "loss": 0.4543, + "step": 7440 + }, + { + "epoch": 0.63, + "learning_rate": 6.226808769097376e-06, + "loss": 0.4732, + "step": 7441 + }, + { + "epoch": 0.63, + "learning_rate": 6.224251444221503e-06, + "loss": 0.4845, + "step": 7442 + }, + { + "epoch": 0.63, + "learning_rate": 6.221694407299981e-06, + "loss": 0.4512, + "step": 7443 + }, + { + "epoch": 0.63, + "learning_rate": 6.219137658527819e-06, + "loss": 0.4602, + "step": 7444 + }, + { + "epoch": 0.63, + "learning_rate": 6.216581198100005e-06, + "loss": 0.4607, + "step": 7445 + }, + { + "epoch": 0.63, + "learning_rate": 6.214025026211499e-06, + "loss": 0.4755, + "step": 7446 + }, + { + "epoch": 0.63, + "learning_rate": 6.211469143057252e-06, + "loss": 0.4757, + "step": 7447 + }, + { + "epoch": 0.64, + "learning_rate": 6.208913548832187e-06, + "loss": 0.4545, + "step": 7448 + }, + { + "epoch": 0.64, + "learning_rate": 6.206358243731201e-06, + "loss": 0.4562, + "step": 7449 + }, + { + "epoch": 0.64, + "learning_rate": 6.203803227949175e-06, + "loss": 0.4692, + "step": 7450 + }, + { + "epoch": 0.64, + "learning_rate": 6.201248501680959e-06, + "loss": 0.4364, + "step": 7451 + }, + { + "epoch": 0.64, + "learning_rate": 6.198694065121393e-06, + "loss": 0.4517, + "step": 7452 + }, + { + "epoch": 0.64, + "learning_rate": 6.196139918465291e-06, + "loss": 0.4785, + "step": 7453 + }, + { + "epoch": 0.64, + "learning_rate": 6.1935860619074396e-06, + "loss": 0.4574, + "step": 7454 + }, + { + "epoch": 0.64, + "learning_rate": 6.191032495642604e-06, + "loss": 0.4535, + "step": 7455 + }, + { + "epoch": 0.64, + "learning_rate": 6.188479219865529e-06, + "loss": 0.4751, + "step": 7456 + }, + { + "epoch": 0.64, + "learning_rate": 6.185926234770947e-06, + "loss": 0.4671, + "step": 7457 + }, + { + "epoch": 0.64, + "learning_rate": 6.18337354055355e-06, + "loss": 0.4668, + "step": 7458 + }, + { + "epoch": 0.64, + "learning_rate": 6.180821137408024e-06, + "loss": 0.4668, + "step": 7459 + }, + { + "epoch": 0.64, + "learning_rate": 6.178269025529018e-06, + "loss": 0.4711, + "step": 7460 + }, + { + "epoch": 0.64, + "learning_rate": 6.1757172051111736e-06, + "loss": 0.4716, + "step": 7461 + }, + { + "epoch": 0.64, + "learning_rate": 6.173165676349103e-06, + "loss": 0.4695, + "step": 7462 + }, + { + "epoch": 0.64, + "learning_rate": 6.1706144394373945e-06, + "loss": 0.467, + "step": 7463 + }, + { + "epoch": 0.64, + "learning_rate": 6.168063494570615e-06, + "loss": 0.4654, + "step": 7464 + }, + { + "epoch": 0.64, + "learning_rate": 6.165512841943308e-06, + "loss": 0.4691, + "step": 7465 + }, + { + "epoch": 0.64, + "learning_rate": 6.162962481750004e-06, + "loss": 0.4638, + "step": 7466 + }, + { + "epoch": 0.64, + "learning_rate": 6.160412414185199e-06, + "loss": 0.4521, + "step": 7467 + }, + { + "epoch": 0.64, + "learning_rate": 6.157862639443375e-06, + "loss": 0.4685, + "step": 7468 + }, + { + "epoch": 0.64, + "learning_rate": 6.155313157718983e-06, + "loss": 0.4675, + "step": 7469 + }, + { + "epoch": 0.64, + "learning_rate": 6.152763969206461e-06, + "loss": 0.4766, + "step": 7470 + }, + { + "epoch": 0.64, + "learning_rate": 6.1502150741002254e-06, + "loss": 0.4759, + "step": 7471 + }, + { + "epoch": 0.64, + "learning_rate": 6.147666472594658e-06, + "loss": 0.4727, + "step": 7472 + }, + { + "epoch": 0.64, + "learning_rate": 6.145118164884127e-06, + "loss": 0.4432, + "step": 7473 + }, + { + "epoch": 0.64, + "learning_rate": 6.142570151162977e-06, + "loss": 0.4741, + "step": 7474 + }, + { + "epoch": 0.64, + "learning_rate": 6.140022431625535e-06, + "loss": 0.473, + "step": 7475 + }, + { + "epoch": 0.64, + "learning_rate": 6.137475006466096e-06, + "loss": 0.4603, + "step": 7476 + }, + { + "epoch": 0.64, + "learning_rate": 6.13492787587894e-06, + "loss": 0.4723, + "step": 7477 + }, + { + "epoch": 0.64, + "learning_rate": 6.132381040058317e-06, + "loss": 0.4531, + "step": 7478 + }, + { + "epoch": 0.64, + "learning_rate": 6.129834499198464e-06, + "loss": 0.4802, + "step": 7479 + }, + { + "epoch": 0.64, + "learning_rate": 6.127288253493591e-06, + "loss": 0.4505, + "step": 7480 + }, + { + "epoch": 0.64, + "learning_rate": 6.124742303137885e-06, + "loss": 0.4772, + "step": 7481 + }, + { + "epoch": 0.64, + "learning_rate": 6.122196648325507e-06, + "loss": 0.473, + "step": 7482 + }, + { + "epoch": 0.64, + "learning_rate": 6.119651289250599e-06, + "loss": 0.4582, + "step": 7483 + }, + { + "epoch": 0.64, + "learning_rate": 6.11710622610729e-06, + "loss": 0.4759, + "step": 7484 + }, + { + "epoch": 0.64, + "learning_rate": 6.114561459089668e-06, + "loss": 0.4852, + "step": 7485 + }, + { + "epoch": 0.64, + "learning_rate": 6.1120169883918115e-06, + "loss": 0.4447, + "step": 7486 + }, + { + "epoch": 0.64, + "learning_rate": 6.109472814207768e-06, + "loss": 0.4776, + "step": 7487 + }, + { + "epoch": 0.64, + "learning_rate": 6.106928936731571e-06, + "loss": 0.4647, + "step": 7488 + }, + { + "epoch": 0.64, + "learning_rate": 6.10438535615723e-06, + "loss": 0.4573, + "step": 7489 + }, + { + "epoch": 0.64, + "learning_rate": 6.101842072678724e-06, + "loss": 0.4683, + "step": 7490 + }, + { + "epoch": 0.64, + "learning_rate": 6.099299086490015e-06, + "loss": 0.4427, + "step": 7491 + }, + { + "epoch": 0.64, + "learning_rate": 6.096756397785039e-06, + "loss": 0.4793, + "step": 7492 + }, + { + "epoch": 0.64, + "learning_rate": 6.094214006757721e-06, + "loss": 0.4602, + "step": 7493 + }, + { + "epoch": 0.64, + "learning_rate": 6.091671913601948e-06, + "loss": 0.4571, + "step": 7494 + }, + { + "epoch": 0.64, + "learning_rate": 6.089130118511593e-06, + "loss": 0.4543, + "step": 7495 + }, + { + "epoch": 0.64, + "learning_rate": 6.086588621680498e-06, + "loss": 0.4419, + "step": 7496 + }, + { + "epoch": 0.64, + "learning_rate": 6.0840474233024935e-06, + "loss": 0.4825, + "step": 7497 + }, + { + "epoch": 0.64, + "learning_rate": 6.081506523571384e-06, + "loss": 0.4746, + "step": 7498 + }, + { + "epoch": 0.64, + "learning_rate": 6.078965922680945e-06, + "loss": 0.4536, + "step": 7499 + }, + { + "epoch": 0.64, + "learning_rate": 6.0764256208249365e-06, + "loss": 0.4684, + "step": 7500 + }, + { + "epoch": 0.64, + "learning_rate": 6.0738856181970865e-06, + "loss": 0.4576, + "step": 7501 + }, + { + "epoch": 0.64, + "learning_rate": 6.071345914991113e-06, + "loss": 0.446, + "step": 7502 + }, + { + "epoch": 0.64, + "learning_rate": 6.0688065114007015e-06, + "loss": 0.453, + "step": 7503 + }, + { + "epoch": 0.64, + "learning_rate": 6.06626740761952e-06, + "loss": 0.4674, + "step": 7504 + }, + { + "epoch": 0.64, + "learning_rate": 6.063728603841203e-06, + "loss": 0.484, + "step": 7505 + }, + { + "epoch": 0.64, + "learning_rate": 6.061190100259377e-06, + "loss": 0.4723, + "step": 7506 + }, + { + "epoch": 0.64, + "learning_rate": 6.058651897067642e-06, + "loss": 0.4507, + "step": 7507 + }, + { + "epoch": 0.64, + "learning_rate": 6.056113994459567e-06, + "loss": 0.4738, + "step": 7508 + }, + { + "epoch": 0.64, + "learning_rate": 6.053576392628704e-06, + "loss": 0.4579, + "step": 7509 + }, + { + "epoch": 0.64, + "learning_rate": 6.051039091768582e-06, + "loss": 0.4689, + "step": 7510 + }, + { + "epoch": 0.64, + "learning_rate": 6.048502092072701e-06, + "loss": 0.4934, + "step": 7511 + }, + { + "epoch": 0.64, + "learning_rate": 6.04596539373455e-06, + "loss": 0.4406, + "step": 7512 + }, + { + "epoch": 0.64, + "learning_rate": 6.043428996947587e-06, + "loss": 0.4801, + "step": 7513 + }, + { + "epoch": 0.64, + "learning_rate": 6.040892901905247e-06, + "loss": 0.4859, + "step": 7514 + }, + { + "epoch": 0.64, + "learning_rate": 6.038357108800939e-06, + "loss": 0.4647, + "step": 7515 + }, + { + "epoch": 0.64, + "learning_rate": 6.03582161782806e-06, + "loss": 0.4816, + "step": 7516 + }, + { + "epoch": 0.64, + "learning_rate": 6.033286429179974e-06, + "loss": 0.4569, + "step": 7517 + }, + { + "epoch": 0.64, + "learning_rate": 6.030751543050028e-06, + "loss": 0.473, + "step": 7518 + }, + { + "epoch": 0.64, + "learning_rate": 6.02821695963154e-06, + "loss": 0.4612, + "step": 7519 + }, + { + "epoch": 0.64, + "learning_rate": 6.025682679117804e-06, + "loss": 0.4593, + "step": 7520 + }, + { + "epoch": 0.64, + "learning_rate": 6.023148701702102e-06, + "loss": 0.4592, + "step": 7521 + }, + { + "epoch": 0.64, + "learning_rate": 6.020615027577683e-06, + "loss": 0.4509, + "step": 7522 + }, + { + "epoch": 0.64, + "learning_rate": 6.018081656937775e-06, + "loss": 0.486, + "step": 7523 + }, + { + "epoch": 0.64, + "learning_rate": 6.0155485899755814e-06, + "loss": 0.4659, + "step": 7524 + }, + { + "epoch": 0.64, + "learning_rate": 6.013015826884291e-06, + "loss": 0.4626, + "step": 7525 + }, + { + "epoch": 0.64, + "learning_rate": 6.0104833678570565e-06, + "loss": 0.4608, + "step": 7526 + }, + { + "epoch": 0.64, + "learning_rate": 6.007951213087018e-06, + "loss": 0.4559, + "step": 7527 + }, + { + "epoch": 0.64, + "learning_rate": 6.005419362767286e-06, + "loss": 0.4569, + "step": 7528 + }, + { + "epoch": 0.64, + "learning_rate": 6.0028878170909475e-06, + "loss": 0.4784, + "step": 7529 + }, + { + "epoch": 0.64, + "learning_rate": 6.000356576251074e-06, + "loss": 0.4782, + "step": 7530 + }, + { + "epoch": 0.64, + "learning_rate": 5.997825640440706e-06, + "loss": 0.4829, + "step": 7531 + }, + { + "epoch": 0.64, + "learning_rate": 5.995295009852861e-06, + "loss": 0.4564, + "step": 7532 + }, + { + "epoch": 0.64, + "learning_rate": 5.992764684680542e-06, + "loss": 0.477, + "step": 7533 + }, + { + "epoch": 0.64, + "learning_rate": 5.990234665116713e-06, + "loss": 0.4829, + "step": 7534 + }, + { + "epoch": 0.64, + "learning_rate": 5.987704951354329e-06, + "loss": 0.4533, + "step": 7535 + }, + { + "epoch": 0.64, + "learning_rate": 5.985175543586321e-06, + "loss": 0.4549, + "step": 7536 + }, + { + "epoch": 0.64, + "learning_rate": 5.982646442005586e-06, + "loss": 0.4512, + "step": 7537 + }, + { + "epoch": 0.64, + "learning_rate": 5.980117646805002e-06, + "loss": 0.4744, + "step": 7538 + }, + { + "epoch": 0.64, + "learning_rate": 5.9775891581774305e-06, + "loss": 0.4759, + "step": 7539 + }, + { + "epoch": 0.64, + "learning_rate": 5.975060976315703e-06, + "loss": 0.4496, + "step": 7540 + }, + { + "epoch": 0.64, + "learning_rate": 5.97253310141263e-06, + "loss": 0.4676, + "step": 7541 + }, + { + "epoch": 0.64, + "learning_rate": 5.970005533660997e-06, + "loss": 0.4772, + "step": 7542 + }, + { + "epoch": 0.64, + "learning_rate": 5.967478273253562e-06, + "loss": 0.4969, + "step": 7543 + }, + { + "epoch": 0.64, + "learning_rate": 5.9649513203830724e-06, + "loss": 0.4735, + "step": 7544 + }, + { + "epoch": 0.64, + "learning_rate": 5.9624246752422435e-06, + "loss": 0.4823, + "step": 7545 + }, + { + "epoch": 0.64, + "learning_rate": 5.959898338023764e-06, + "loss": 0.4669, + "step": 7546 + }, + { + "epoch": 0.64, + "learning_rate": 5.957372308920302e-06, + "loss": 0.4563, + "step": 7547 + }, + { + "epoch": 0.64, + "learning_rate": 5.9548465881245055e-06, + "loss": 0.4763, + "step": 7548 + }, + { + "epoch": 0.64, + "learning_rate": 5.952321175828998e-06, + "loss": 0.4788, + "step": 7549 + }, + { + "epoch": 0.64, + "learning_rate": 5.949796072226375e-06, + "loss": 0.4563, + "step": 7550 + }, + { + "epoch": 0.64, + "learning_rate": 5.947271277509215e-06, + "loss": 0.4518, + "step": 7551 + }, + { + "epoch": 0.64, + "learning_rate": 5.944746791870062e-06, + "loss": 0.4617, + "step": 7552 + }, + { + "epoch": 0.64, + "learning_rate": 5.94222261550145e-06, + "loss": 0.4563, + "step": 7553 + }, + { + "epoch": 0.64, + "learning_rate": 5.939698748595885e-06, + "loss": 0.4703, + "step": 7554 + }, + { + "epoch": 0.64, + "learning_rate": 5.937175191345844e-06, + "loss": 0.4714, + "step": 7555 + }, + { + "epoch": 0.64, + "learning_rate": 5.934651943943785e-06, + "loss": 0.4601, + "step": 7556 + }, + { + "epoch": 0.64, + "learning_rate": 5.932129006582139e-06, + "loss": 0.4655, + "step": 7557 + }, + { + "epoch": 0.64, + "learning_rate": 5.92960637945332e-06, + "loss": 0.4535, + "step": 7558 + }, + { + "epoch": 0.64, + "learning_rate": 5.927084062749711e-06, + "loss": 0.4561, + "step": 7559 + }, + { + "epoch": 0.64, + "learning_rate": 5.924562056663676e-06, + "loss": 0.465, + "step": 7560 + }, + { + "epoch": 0.64, + "learning_rate": 5.92204036138755e-06, + "loss": 0.4693, + "step": 7561 + }, + { + "epoch": 0.64, + "learning_rate": 5.919518977113652e-06, + "loss": 0.4809, + "step": 7562 + }, + { + "epoch": 0.64, + "learning_rate": 5.916997904034276e-06, + "loss": 0.4661, + "step": 7563 + }, + { + "epoch": 0.64, + "learning_rate": 5.914477142341682e-06, + "loss": 0.4645, + "step": 7564 + }, + { + "epoch": 0.65, + "learning_rate": 5.91195669222812e-06, + "loss": 0.4744, + "step": 7565 + }, + { + "epoch": 0.65, + "learning_rate": 5.9094365538858055e-06, + "loss": 0.4678, + "step": 7566 + }, + { + "epoch": 0.65, + "learning_rate": 5.906916727506939e-06, + "loss": 0.4718, + "step": 7567 + }, + { + "epoch": 0.65, + "learning_rate": 5.9043972132836905e-06, + "loss": 0.4687, + "step": 7568 + }, + { + "epoch": 0.65, + "learning_rate": 5.901878011408211e-06, + "loss": 0.4823, + "step": 7569 + }, + { + "epoch": 0.65, + "learning_rate": 5.899359122072617e-06, + "loss": 0.4903, + "step": 7570 + }, + { + "epoch": 0.65, + "learning_rate": 5.89684054546902e-06, + "loss": 0.4538, + "step": 7571 + }, + { + "epoch": 0.65, + "learning_rate": 5.894322281789495e-06, + "loss": 0.4502, + "step": 7572 + }, + { + "epoch": 0.65, + "learning_rate": 5.891804331226092e-06, + "loss": 0.4794, + "step": 7573 + }, + { + "epoch": 0.65, + "learning_rate": 5.889286693970843e-06, + "loss": 0.4645, + "step": 7574 + }, + { + "epoch": 0.65, + "learning_rate": 5.88676937021575e-06, + "loss": 0.4587, + "step": 7575 + }, + { + "epoch": 0.65, + "learning_rate": 5.8842523601528e-06, + "loss": 0.457, + "step": 7576 + }, + { + "epoch": 0.65, + "learning_rate": 5.881735663973945e-06, + "loss": 0.4776, + "step": 7577 + }, + { + "epoch": 0.65, + "learning_rate": 5.879219281871125e-06, + "loss": 0.4755, + "step": 7578 + }, + { + "epoch": 0.65, + "learning_rate": 5.876703214036241e-06, + "loss": 0.4635, + "step": 7579 + }, + { + "epoch": 0.65, + "learning_rate": 5.874187460661187e-06, + "loss": 0.4642, + "step": 7580 + }, + { + "epoch": 0.65, + "learning_rate": 5.871672021937823e-06, + "loss": 0.4392, + "step": 7581 + }, + { + "epoch": 0.65, + "learning_rate": 5.869156898057983e-06, + "loss": 0.4767, + "step": 7582 + }, + { + "epoch": 0.65, + "learning_rate": 5.866642089213488e-06, + "loss": 0.4808, + "step": 7583 + }, + { + "epoch": 0.65, + "learning_rate": 5.864127595596119e-06, + "loss": 0.4655, + "step": 7584 + }, + { + "epoch": 0.65, + "learning_rate": 5.86161341739765e-06, + "loss": 0.4722, + "step": 7585 + }, + { + "epoch": 0.65, + "learning_rate": 5.859099554809817e-06, + "loss": 0.4795, + "step": 7586 + }, + { + "epoch": 0.65, + "learning_rate": 5.856586008024342e-06, + "loss": 0.4606, + "step": 7587 + }, + { + "epoch": 0.65, + "learning_rate": 5.854072777232914e-06, + "loss": 0.4616, + "step": 7588 + }, + { + "epoch": 0.65, + "learning_rate": 5.851559862627203e-06, + "loss": 0.4677, + "step": 7589 + }, + { + "epoch": 0.65, + "learning_rate": 5.849047264398859e-06, + "loss": 0.4836, + "step": 7590 + }, + { + "epoch": 0.65, + "learning_rate": 5.8465349827395e-06, + "loss": 0.4712, + "step": 7591 + }, + { + "epoch": 0.65, + "learning_rate": 5.8440230178407245e-06, + "loss": 0.4789, + "step": 7592 + }, + { + "epoch": 0.65, + "learning_rate": 5.841511369894099e-06, + "loss": 0.4617, + "step": 7593 + }, + { + "epoch": 0.65, + "learning_rate": 5.839000039091185e-06, + "loss": 0.4774, + "step": 7594 + }, + { + "epoch": 0.65, + "learning_rate": 5.836489025623495e-06, + "loss": 0.4586, + "step": 7595 + }, + { + "epoch": 0.65, + "learning_rate": 5.833978329682535e-06, + "loss": 0.501, + "step": 7596 + }, + { + "epoch": 0.65, + "learning_rate": 5.831467951459784e-06, + "loss": 0.4706, + "step": 7597 + }, + { + "epoch": 0.65, + "learning_rate": 5.828957891146682e-06, + "loss": 0.4598, + "step": 7598 + }, + { + "epoch": 0.65, + "learning_rate": 5.826448148934669e-06, + "loss": 0.4577, + "step": 7599 + }, + { + "epoch": 0.65, + "learning_rate": 5.823938725015148e-06, + "loss": 0.4667, + "step": 7600 + }, + { + "epoch": 0.65, + "learning_rate": 5.821429619579491e-06, + "loss": 0.4935, + "step": 7601 + }, + { + "epoch": 0.65, + "learning_rate": 5.818920832819051e-06, + "loss": 0.4675, + "step": 7602 + }, + { + "epoch": 0.65, + "learning_rate": 5.816412364925173e-06, + "loss": 0.4528, + "step": 7603 + }, + { + "epoch": 0.65, + "learning_rate": 5.813904216089148e-06, + "loss": 0.4495, + "step": 7604 + }, + { + "epoch": 0.65, + "learning_rate": 5.811396386502266e-06, + "loss": 0.4663, + "step": 7605 + }, + { + "epoch": 0.65, + "learning_rate": 5.808888876355785e-06, + "loss": 0.4606, + "step": 7606 + }, + { + "epoch": 0.65, + "learning_rate": 5.80638168584093e-06, + "loss": 0.4602, + "step": 7607 + }, + { + "epoch": 0.65, + "learning_rate": 5.803874815148916e-06, + "loss": 0.4841, + "step": 7608 + }, + { + "epoch": 0.65, + "learning_rate": 5.8013682644709335e-06, + "loss": 0.4419, + "step": 7609 + }, + { + "epoch": 0.65, + "learning_rate": 5.798862033998131e-06, + "loss": 0.4591, + "step": 7610 + }, + { + "epoch": 0.65, + "learning_rate": 5.796356123921649e-06, + "loss": 0.4564, + "step": 7611 + }, + { + "epoch": 0.65, + "learning_rate": 5.793850534432599e-06, + "loss": 0.4734, + "step": 7612 + }, + { + "epoch": 0.65, + "learning_rate": 5.791345265722068e-06, + "loss": 0.4679, + "step": 7613 + }, + { + "epoch": 0.65, + "learning_rate": 5.788840317981117e-06, + "loss": 0.4777, + "step": 7614 + }, + { + "epoch": 0.65, + "learning_rate": 5.786335691400789e-06, + "loss": 0.4747, + "step": 7615 + }, + { + "epoch": 0.65, + "learning_rate": 5.783831386172083e-06, + "loss": 0.4871, + "step": 7616 + }, + { + "epoch": 0.65, + "learning_rate": 5.781327402486002e-06, + "loss": 0.4711, + "step": 7617 + }, + { + "epoch": 0.65, + "learning_rate": 5.77882374053351e-06, + "loss": 0.4699, + "step": 7618 + }, + { + "epoch": 0.65, + "learning_rate": 5.776320400505539e-06, + "loss": 0.466, + "step": 7619 + }, + { + "epoch": 0.65, + "learning_rate": 5.773817382593008e-06, + "loss": 0.4612, + "step": 7620 + }, + { + "epoch": 0.65, + "learning_rate": 5.771314686986806e-06, + "loss": 0.4656, + "step": 7621 + }, + { + "epoch": 0.65, + "learning_rate": 5.7688123138778e-06, + "loss": 0.4497, + "step": 7622 + }, + { + "epoch": 0.65, + "learning_rate": 5.766310263456833e-06, + "loss": 0.4656, + "step": 7623 + }, + { + "epoch": 0.65, + "learning_rate": 5.7638085359147235e-06, + "loss": 0.4887, + "step": 7624 + }, + { + "epoch": 0.65, + "learning_rate": 5.761307131442253e-06, + "loss": 0.4927, + "step": 7625 + }, + { + "epoch": 0.65, + "learning_rate": 5.758806050230199e-06, + "loss": 0.4288, + "step": 7626 + }, + { + "epoch": 0.65, + "learning_rate": 5.756305292469308e-06, + "loss": 0.4697, + "step": 7627 + }, + { + "epoch": 0.65, + "learning_rate": 5.753804858350288e-06, + "loss": 0.4702, + "step": 7628 + }, + { + "epoch": 0.65, + "learning_rate": 5.751304748063838e-06, + "loss": 0.4366, + "step": 7629 + }, + { + "epoch": 0.65, + "learning_rate": 5.748804961800623e-06, + "loss": 0.504, + "step": 7630 + }, + { + "epoch": 0.65, + "learning_rate": 5.746305499751291e-06, + "loss": 0.4896, + "step": 7631 + }, + { + "epoch": 0.65, + "learning_rate": 5.743806362106461e-06, + "loss": 0.4486, + "step": 7632 + }, + { + "epoch": 0.65, + "learning_rate": 5.74130754905673e-06, + "loss": 0.4632, + "step": 7633 + }, + { + "epoch": 0.65, + "learning_rate": 5.7388090607926605e-06, + "loss": 0.4581, + "step": 7634 + }, + { + "epoch": 0.65, + "learning_rate": 5.736310897504799e-06, + "loss": 0.4628, + "step": 7635 + }, + { + "epoch": 0.65, + "learning_rate": 5.733813059383676e-06, + "loss": 0.4483, + "step": 7636 + }, + { + "epoch": 0.65, + "learning_rate": 5.7313155466197765e-06, + "loss": 0.4818, + "step": 7637 + }, + { + "epoch": 0.65, + "learning_rate": 5.728818359403574e-06, + "loss": 0.4653, + "step": 7638 + }, + { + "epoch": 0.65, + "learning_rate": 5.726321497925516e-06, + "loss": 0.4599, + "step": 7639 + }, + { + "epoch": 0.65, + "learning_rate": 5.7238249623760215e-06, + "loss": 0.461, + "step": 7640 + }, + { + "epoch": 0.65, + "learning_rate": 5.7213287529454885e-06, + "loss": 0.4727, + "step": 7641 + }, + { + "epoch": 0.65, + "learning_rate": 5.718832869824291e-06, + "loss": 0.4577, + "step": 7642 + }, + { + "epoch": 0.65, + "learning_rate": 5.71633731320277e-06, + "loss": 0.4788, + "step": 7643 + }, + { + "epoch": 0.65, + "learning_rate": 5.713842083271244e-06, + "loss": 0.4716, + "step": 7644 + }, + { + "epoch": 0.65, + "learning_rate": 5.711347180220023e-06, + "loss": 0.4453, + "step": 7645 + }, + { + "epoch": 0.65, + "learning_rate": 5.7088526042393665e-06, + "loss": 0.4669, + "step": 7646 + }, + { + "epoch": 0.65, + "learning_rate": 5.706358355519526e-06, + "loss": 0.4682, + "step": 7647 + }, + { + "epoch": 0.65, + "learning_rate": 5.703864434250721e-06, + "loss": 0.4513, + "step": 7648 + }, + { + "epoch": 0.65, + "learning_rate": 5.701370840623153e-06, + "loss": 0.4878, + "step": 7649 + }, + { + "epoch": 0.65, + "learning_rate": 5.698877574826989e-06, + "loss": 0.4843, + "step": 7650 + }, + { + "epoch": 0.65, + "learning_rate": 5.696384637052381e-06, + "loss": 0.4615, + "step": 7651 + }, + { + "epoch": 0.65, + "learning_rate": 5.693892027489445e-06, + "loss": 0.4413, + "step": 7652 + }, + { + "epoch": 0.65, + "learning_rate": 5.691399746328277e-06, + "loss": 0.4455, + "step": 7653 + }, + { + "epoch": 0.65, + "learning_rate": 5.688907793758959e-06, + "loss": 0.4689, + "step": 7654 + }, + { + "epoch": 0.65, + "learning_rate": 5.686416169971527e-06, + "loss": 0.4645, + "step": 7655 + }, + { + "epoch": 0.65, + "learning_rate": 5.683924875156006e-06, + "loss": 0.4688, + "step": 7656 + }, + { + "epoch": 0.65, + "learning_rate": 5.681433909502394e-06, + "loss": 0.4638, + "step": 7657 + }, + { + "epoch": 0.65, + "learning_rate": 5.678943273200661e-06, + "loss": 0.4515, + "step": 7658 + }, + { + "epoch": 0.65, + "learning_rate": 5.676452966440755e-06, + "loss": 0.4604, + "step": 7659 + }, + { + "epoch": 0.65, + "learning_rate": 5.673962989412599e-06, + "loss": 0.4829, + "step": 7660 + }, + { + "epoch": 0.65, + "learning_rate": 5.671473342306082e-06, + "loss": 0.4605, + "step": 7661 + }, + { + "epoch": 0.65, + "learning_rate": 5.6689840253110765e-06, + "loss": 0.4809, + "step": 7662 + }, + { + "epoch": 0.65, + "learning_rate": 5.666495038617437e-06, + "loss": 0.495, + "step": 7663 + }, + { + "epoch": 0.65, + "learning_rate": 5.664006382414975e-06, + "loss": 0.4793, + "step": 7664 + }, + { + "epoch": 0.65, + "learning_rate": 5.661518056893487e-06, + "loss": 0.4773, + "step": 7665 + }, + { + "epoch": 0.65, + "learning_rate": 5.659030062242746e-06, + "loss": 0.4622, + "step": 7666 + }, + { + "epoch": 0.65, + "learning_rate": 5.656542398652494e-06, + "loss": 0.4749, + "step": 7667 + }, + { + "epoch": 0.65, + "learning_rate": 5.6540550663124536e-06, + "loss": 0.4631, + "step": 7668 + }, + { + "epoch": 0.65, + "learning_rate": 5.65156806541232e-06, + "loss": 0.4786, + "step": 7669 + }, + { + "epoch": 0.65, + "learning_rate": 5.649081396141758e-06, + "loss": 0.4691, + "step": 7670 + }, + { + "epoch": 0.65, + "learning_rate": 5.646595058690407e-06, + "loss": 0.4736, + "step": 7671 + }, + { + "epoch": 0.65, + "learning_rate": 5.6441090532479016e-06, + "loss": 0.493, + "step": 7672 + }, + { + "epoch": 0.65, + "learning_rate": 5.64162338000382e-06, + "loss": 0.4682, + "step": 7673 + }, + { + "epoch": 0.65, + "learning_rate": 5.639138039147736e-06, + "loss": 0.446, + "step": 7674 + }, + { + "epoch": 0.65, + "learning_rate": 5.63665303086919e-06, + "loss": 0.4624, + "step": 7675 + }, + { + "epoch": 0.65, + "learning_rate": 5.634168355357701e-06, + "loss": 0.4831, + "step": 7676 + }, + { + "epoch": 0.65, + "learning_rate": 5.631684012802759e-06, + "loss": 0.4599, + "step": 7677 + }, + { + "epoch": 0.65, + "learning_rate": 5.629200003393838e-06, + "loss": 0.4499, + "step": 7678 + }, + { + "epoch": 0.65, + "learning_rate": 5.626716327320365e-06, + "loss": 0.4622, + "step": 7679 + }, + { + "epoch": 0.65, + "learning_rate": 5.62423298477176e-06, + "loss": 0.4684, + "step": 7680 + }, + { + "epoch": 0.65, + "learning_rate": 5.621749975937425e-06, + "loss": 0.4751, + "step": 7681 + }, + { + "epoch": 0.66, + "learning_rate": 5.61926730100671e-06, + "loss": 0.446, + "step": 7682 + }, + { + "epoch": 0.66, + "learning_rate": 5.616784960168962e-06, + "loss": 0.4736, + "step": 7683 + }, + { + "epoch": 0.66, + "learning_rate": 5.61430295361349e-06, + "loss": 0.4477, + "step": 7684 + }, + { + "epoch": 0.66, + "learning_rate": 5.611821281529585e-06, + "loss": 0.481, + "step": 7685 + }, + { + "epoch": 0.66, + "learning_rate": 5.609339944106509e-06, + "loss": 0.4722, + "step": 7686 + }, + { + "epoch": 0.66, + "learning_rate": 5.606858941533504e-06, + "loss": 0.4516, + "step": 7687 + }, + { + "epoch": 0.66, + "learning_rate": 5.604378273999772e-06, + "loss": 0.4712, + "step": 7688 + }, + { + "epoch": 0.66, + "learning_rate": 5.601897941694505e-06, + "loss": 0.4704, + "step": 7689 + }, + { + "epoch": 0.66, + "learning_rate": 5.5994179448068616e-06, + "loss": 0.4928, + "step": 7690 + }, + { + "epoch": 0.66, + "learning_rate": 5.596938283525978e-06, + "loss": 0.4583, + "step": 7691 + }, + { + "epoch": 0.66, + "learning_rate": 5.5944589580409625e-06, + "loss": 0.4855, + "step": 7692 + }, + { + "epoch": 0.66, + "learning_rate": 5.591979968540902e-06, + "loss": 0.4659, + "step": 7693 + }, + { + "epoch": 0.66, + "learning_rate": 5.589501315214849e-06, + "loss": 0.471, + "step": 7694 + }, + { + "epoch": 0.66, + "learning_rate": 5.58702299825184e-06, + "loss": 0.4608, + "step": 7695 + }, + { + "epoch": 0.66, + "learning_rate": 5.584545017840886e-06, + "loss": 0.4812, + "step": 7696 + }, + { + "epoch": 0.66, + "learning_rate": 5.5820673741709566e-06, + "loss": 0.4728, + "step": 7697 + }, + { + "epoch": 0.66, + "learning_rate": 5.579590067431016e-06, + "loss": 0.4619, + "step": 7698 + }, + { + "epoch": 0.66, + "learning_rate": 5.5771130978099896e-06, + "loss": 0.455, + "step": 7699 + }, + { + "epoch": 0.66, + "learning_rate": 5.5746364654967835e-06, + "loss": 0.4626, + "step": 7700 + }, + { + "epoch": 0.66, + "learning_rate": 5.572160170680277e-06, + "loss": 0.4842, + "step": 7701 + }, + { + "epoch": 0.66, + "learning_rate": 5.56968421354932e-06, + "loss": 0.4832, + "step": 7702 + }, + { + "epoch": 0.66, + "learning_rate": 5.5672085942927425e-06, + "loss": 0.4647, + "step": 7703 + }, + { + "epoch": 0.66, + "learning_rate": 5.564733313099343e-06, + "loss": 0.4511, + "step": 7704 + }, + { + "epoch": 0.66, + "learning_rate": 5.5622583701578984e-06, + "loss": 0.4716, + "step": 7705 + }, + { + "epoch": 0.66, + "learning_rate": 5.55978376565716e-06, + "loss": 0.481, + "step": 7706 + }, + { + "epoch": 0.66, + "learning_rate": 5.557309499785847e-06, + "loss": 0.4683, + "step": 7707 + }, + { + "epoch": 0.66, + "learning_rate": 5.554835572732658e-06, + "loss": 0.4779, + "step": 7708 + }, + { + "epoch": 0.66, + "learning_rate": 5.552361984686267e-06, + "loss": 0.4778, + "step": 7709 + }, + { + "epoch": 0.66, + "learning_rate": 5.549888735835318e-06, + "loss": 0.4589, + "step": 7710 + }, + { + "epoch": 0.66, + "learning_rate": 5.547415826368434e-06, + "loss": 0.4915, + "step": 7711 + }, + { + "epoch": 0.66, + "learning_rate": 5.5449432564742074e-06, + "loss": 0.4554, + "step": 7712 + }, + { + "epoch": 0.66, + "learning_rate": 5.542471026341207e-06, + "loss": 0.4667, + "step": 7713 + }, + { + "epoch": 0.66, + "learning_rate": 5.539999136157977e-06, + "loss": 0.4499, + "step": 7714 + }, + { + "epoch": 0.66, + "learning_rate": 5.537527586113036e-06, + "loss": 0.483, + "step": 7715 + }, + { + "epoch": 0.66, + "learning_rate": 5.535056376394868e-06, + "loss": 0.4548, + "step": 7716 + }, + { + "epoch": 0.66, + "learning_rate": 5.532585507191941e-06, + "loss": 0.4678, + "step": 7717 + }, + { + "epoch": 0.66, + "learning_rate": 5.530114978692695e-06, + "loss": 0.4557, + "step": 7718 + }, + { + "epoch": 0.66, + "learning_rate": 5.52764479108554e-06, + "loss": 0.4579, + "step": 7719 + }, + { + "epoch": 0.66, + "learning_rate": 5.525174944558866e-06, + "loss": 0.449, + "step": 7720 + }, + { + "epoch": 0.66, + "learning_rate": 5.522705439301037e-06, + "loss": 0.4502, + "step": 7721 + }, + { + "epoch": 0.66, + "learning_rate": 5.520236275500375e-06, + "loss": 0.4635, + "step": 7722 + }, + { + "epoch": 0.66, + "learning_rate": 5.517767453345199e-06, + "loss": 0.4588, + "step": 7723 + }, + { + "epoch": 0.66, + "learning_rate": 5.515298973023797e-06, + "loss": 0.4523, + "step": 7724 + }, + { + "epoch": 0.66, + "learning_rate": 5.512830834724413e-06, + "loss": 0.4661, + "step": 7725 + }, + { + "epoch": 0.66, + "learning_rate": 5.510363038635282e-06, + "loss": 0.4673, + "step": 7726 + }, + { + "epoch": 0.66, + "learning_rate": 5.5078955849446115e-06, + "loss": 0.4881, + "step": 7727 + }, + { + "epoch": 0.66, + "learning_rate": 5.505428473840576e-06, + "loss": 0.4662, + "step": 7728 + }, + { + "epoch": 0.66, + "learning_rate": 5.502961705511329e-06, + "loss": 0.475, + "step": 7729 + }, + { + "epoch": 0.66, + "learning_rate": 5.500495280145002e-06, + "loss": 0.4621, + "step": 7730 + }, + { + "epoch": 0.66, + "learning_rate": 5.498029197929682e-06, + "loss": 0.4706, + "step": 7731 + }, + { + "epoch": 0.66, + "learning_rate": 5.495563459053455e-06, + "loss": 0.4595, + "step": 7732 + }, + { + "epoch": 0.66, + "learning_rate": 5.493098063704367e-06, + "loss": 0.4655, + "step": 7733 + }, + { + "epoch": 0.66, + "learning_rate": 5.490633012070432e-06, + "loss": 0.4745, + "step": 7734 + }, + { + "epoch": 0.66, + "learning_rate": 5.48816830433965e-06, + "loss": 0.4519, + "step": 7735 + }, + { + "epoch": 0.66, + "learning_rate": 5.485703940699989e-06, + "loss": 0.4663, + "step": 7736 + }, + { + "epoch": 0.66, + "learning_rate": 5.483239921339393e-06, + "loss": 0.4785, + "step": 7737 + }, + { + "epoch": 0.66, + "learning_rate": 5.480776246445776e-06, + "loss": 0.4691, + "step": 7738 + }, + { + "epoch": 0.66, + "learning_rate": 5.478312916207036e-06, + "loss": 0.4627, + "step": 7739 + }, + { + "epoch": 0.66, + "learning_rate": 5.475849930811021e-06, + "loss": 0.481, + "step": 7740 + }, + { + "epoch": 0.66, + "learning_rate": 5.473387290445582e-06, + "loss": 0.4757, + "step": 7741 + }, + { + "epoch": 0.66, + "learning_rate": 5.47092499529853e-06, + "loss": 0.4474, + "step": 7742 + }, + { + "epoch": 0.66, + "learning_rate": 5.468463045557644e-06, + "loss": 0.4866, + "step": 7743 + }, + { + "epoch": 0.66, + "learning_rate": 5.4660014414106825e-06, + "loss": 0.4598, + "step": 7744 + }, + { + "epoch": 0.66, + "learning_rate": 5.4635401830453815e-06, + "loss": 0.4752, + "step": 7745 + }, + { + "epoch": 0.66, + "learning_rate": 5.461079270649444e-06, + "loss": 0.4592, + "step": 7746 + }, + { + "epoch": 0.66, + "learning_rate": 5.4586187044105524e-06, + "loss": 0.4732, + "step": 7747 + }, + { + "epoch": 0.66, + "learning_rate": 5.456158484516361e-06, + "loss": 0.4615, + "step": 7748 + }, + { + "epoch": 0.66, + "learning_rate": 5.453698611154485e-06, + "loss": 0.4495, + "step": 7749 + }, + { + "epoch": 0.66, + "learning_rate": 5.451239084512537e-06, + "loss": 0.4783, + "step": 7750 + }, + { + "epoch": 0.66, + "learning_rate": 5.448779904778092e-06, + "loss": 0.4756, + "step": 7751 + }, + { + "epoch": 0.66, + "learning_rate": 5.446321072138688e-06, + "loss": 0.4534, + "step": 7752 + }, + { + "epoch": 0.66, + "learning_rate": 5.44386258678185e-06, + "loss": 0.4677, + "step": 7753 + }, + { + "epoch": 0.66, + "learning_rate": 5.441404448895073e-06, + "loss": 0.4726, + "step": 7754 + }, + { + "epoch": 0.66, + "learning_rate": 5.438946658665823e-06, + "loss": 0.4431, + "step": 7755 + }, + { + "epoch": 0.66, + "learning_rate": 5.436489216281544e-06, + "loss": 0.4502, + "step": 7756 + }, + { + "epoch": 0.66, + "learning_rate": 5.434032121929653e-06, + "loss": 0.5031, + "step": 7757 + }, + { + "epoch": 0.66, + "learning_rate": 5.431575375797526e-06, + "loss": 0.4671, + "step": 7758 + }, + { + "epoch": 0.66, + "learning_rate": 5.4291189780725385e-06, + "loss": 0.4689, + "step": 7759 + }, + { + "epoch": 0.66, + "learning_rate": 5.426662928942024e-06, + "loss": 0.485, + "step": 7760 + }, + { + "epoch": 0.66, + "learning_rate": 5.424207228593283e-06, + "loss": 0.4834, + "step": 7761 + }, + { + "epoch": 0.66, + "learning_rate": 5.421751877213603e-06, + "loss": 0.4521, + "step": 7762 + }, + { + "epoch": 0.66, + "learning_rate": 5.4192968749902385e-06, + "loss": 0.4702, + "step": 7763 + }, + { + "epoch": 0.66, + "learning_rate": 5.416842222110419e-06, + "loss": 0.4633, + "step": 7764 + }, + { + "epoch": 0.66, + "learning_rate": 5.4143879187613435e-06, + "loss": 0.4602, + "step": 7765 + }, + { + "epoch": 0.66, + "learning_rate": 5.411933965130196e-06, + "loss": 0.4851, + "step": 7766 + }, + { + "epoch": 0.66, + "learning_rate": 5.409480361404113e-06, + "loss": 0.4616, + "step": 7767 + }, + { + "epoch": 0.66, + "learning_rate": 5.40702710777022e-06, + "loss": 0.4504, + "step": 7768 + }, + { + "epoch": 0.66, + "learning_rate": 5.404574204415622e-06, + "loss": 0.4815, + "step": 7769 + }, + { + "epoch": 0.66, + "learning_rate": 5.4021216515273765e-06, + "loss": 0.4535, + "step": 7770 + }, + { + "epoch": 0.66, + "learning_rate": 5.399669449292529e-06, + "loss": 0.4587, + "step": 7771 + }, + { + "epoch": 0.66, + "learning_rate": 5.397217597898097e-06, + "loss": 0.448, + "step": 7772 + }, + { + "epoch": 0.66, + "learning_rate": 5.394766097531066e-06, + "loss": 0.4758, + "step": 7773 + }, + { + "epoch": 0.66, + "learning_rate": 5.392314948378396e-06, + "loss": 0.4548, + "step": 7774 + }, + { + "epoch": 0.66, + "learning_rate": 5.389864150627032e-06, + "loss": 0.4632, + "step": 7775 + }, + { + "epoch": 0.66, + "learning_rate": 5.38741370446387e-06, + "loss": 0.4706, + "step": 7776 + }, + { + "epoch": 0.66, + "learning_rate": 5.384963610075791e-06, + "loss": 0.475, + "step": 7777 + }, + { + "epoch": 0.66, + "learning_rate": 5.382513867649663e-06, + "loss": 0.4755, + "step": 7778 + }, + { + "epoch": 0.66, + "learning_rate": 5.3800644773723e-06, + "loss": 0.453, + "step": 7779 + }, + { + "epoch": 0.66, + "learning_rate": 5.377615439430508e-06, + "loss": 0.4752, + "step": 7780 + }, + { + "epoch": 0.66, + "learning_rate": 5.375166754011061e-06, + "loss": 0.4444, + "step": 7781 + }, + { + "epoch": 0.66, + "learning_rate": 5.372718421300704e-06, + "loss": 0.4744, + "step": 7782 + }, + { + "epoch": 0.66, + "learning_rate": 5.37027044148616e-06, + "loss": 0.4599, + "step": 7783 + }, + { + "epoch": 0.66, + "learning_rate": 5.367822814754124e-06, + "loss": 0.4867, + "step": 7784 + }, + { + "epoch": 0.66, + "learning_rate": 5.365375541291255e-06, + "loss": 0.4551, + "step": 7785 + }, + { + "epoch": 0.66, + "learning_rate": 5.362928621284193e-06, + "loss": 0.4646, + "step": 7786 + }, + { + "epoch": 0.66, + "learning_rate": 5.360482054919561e-06, + "loss": 0.489, + "step": 7787 + }, + { + "epoch": 0.66, + "learning_rate": 5.358035842383933e-06, + "loss": 0.4433, + "step": 7788 + }, + { + "epoch": 0.66, + "learning_rate": 5.355589983863872e-06, + "loss": 0.4609, + "step": 7789 + }, + { + "epoch": 0.66, + "learning_rate": 5.3531444795459065e-06, + "loss": 0.4557, + "step": 7790 + }, + { + "epoch": 0.66, + "learning_rate": 5.350699329616544e-06, + "loss": 0.4574, + "step": 7791 + }, + { + "epoch": 0.66, + "learning_rate": 5.348254534262262e-06, + "loss": 0.4693, + "step": 7792 + }, + { + "epoch": 0.66, + "learning_rate": 5.345810093669512e-06, + "loss": 0.4643, + "step": 7793 + }, + { + "epoch": 0.66, + "learning_rate": 5.343366008024713e-06, + "loss": 0.4648, + "step": 7794 + }, + { + "epoch": 0.66, + "learning_rate": 5.340922277514258e-06, + "loss": 0.4442, + "step": 7795 + }, + { + "epoch": 0.66, + "learning_rate": 5.3384789023245285e-06, + "loss": 0.4526, + "step": 7796 + }, + { + "epoch": 0.66, + "learning_rate": 5.336035882641854e-06, + "loss": 0.4848, + "step": 7797 + }, + { + "epoch": 0.66, + "learning_rate": 5.333593218652557e-06, + "loss": 0.4442, + "step": 7798 + }, + { + "epoch": 0.66, + "learning_rate": 5.331150910542926e-06, + "loss": 0.4563, + "step": 7799 + }, + { + "epoch": 0.67, + "learning_rate": 5.3287089584992116e-06, + "loss": 0.4639, + "step": 7800 + }, + { + "epoch": 0.67, + "learning_rate": 5.3262673627076555e-06, + "loss": 0.4732, + "step": 7801 + }, + { + "epoch": 0.67, + "learning_rate": 5.323826123354469e-06, + "loss": 0.4686, + "step": 7802 + }, + { + "epoch": 0.67, + "learning_rate": 5.3213852406258195e-06, + "loss": 0.4654, + "step": 7803 + }, + { + "epoch": 0.67, + "learning_rate": 5.318944714707861e-06, + "loss": 0.4474, + "step": 7804 + }, + { + "epoch": 0.67, + "learning_rate": 5.316504545786728e-06, + "loss": 0.4678, + "step": 7805 + }, + { + "epoch": 0.67, + "learning_rate": 5.3140647340485086e-06, + "loss": 0.4512, + "step": 7806 + }, + { + "epoch": 0.67, + "learning_rate": 5.3116252796792755e-06, + "loss": 0.4694, + "step": 7807 + }, + { + "epoch": 0.67, + "learning_rate": 5.309186182865076e-06, + "loss": 0.4564, + "step": 7808 + }, + { + "epoch": 0.67, + "learning_rate": 5.306747443791913e-06, + "loss": 0.4624, + "step": 7809 + }, + { + "epoch": 0.67, + "learning_rate": 5.304309062645788e-06, + "loss": 0.4728, + "step": 7810 + }, + { + "epoch": 0.67, + "learning_rate": 5.301871039612663e-06, + "loss": 0.455, + "step": 7811 + }, + { + "epoch": 0.67, + "learning_rate": 5.299433374878461e-06, + "loss": 0.4702, + "step": 7812 + }, + { + "epoch": 0.67, + "learning_rate": 5.29699606862909e-06, + "loss": 0.4471, + "step": 7813 + }, + { + "epoch": 0.67, + "learning_rate": 5.294559121050442e-06, + "loss": 0.4643, + "step": 7814 + }, + { + "epoch": 0.67, + "learning_rate": 5.292122532328356e-06, + "loss": 0.4589, + "step": 7815 + }, + { + "epoch": 0.67, + "learning_rate": 5.289686302648661e-06, + "loss": 0.4743, + "step": 7816 + }, + { + "epoch": 0.67, + "learning_rate": 5.287250432197157e-06, + "loss": 0.471, + "step": 7817 + }, + { + "epoch": 0.67, + "learning_rate": 5.284814921159602e-06, + "loss": 0.4438, + "step": 7818 + }, + { + "epoch": 0.67, + "learning_rate": 5.28237976972175e-06, + "loss": 0.4683, + "step": 7819 + }, + { + "epoch": 0.67, + "learning_rate": 5.279944978069318e-06, + "loss": 0.4287, + "step": 7820 + }, + { + "epoch": 0.67, + "learning_rate": 5.277510546387982e-06, + "loss": 0.4834, + "step": 7821 + }, + { + "epoch": 0.67, + "learning_rate": 5.275076474863408e-06, + "loss": 0.4643, + "step": 7822 + }, + { + "epoch": 0.67, + "learning_rate": 5.272642763681228e-06, + "loss": 0.4664, + "step": 7823 + }, + { + "epoch": 0.67, + "learning_rate": 5.2702094130270476e-06, + "loss": 0.4532, + "step": 7824 + }, + { + "epoch": 0.67, + "learning_rate": 5.2677764230864434e-06, + "loss": 0.4671, + "step": 7825 + }, + { + "epoch": 0.67, + "learning_rate": 5.265343794044964e-06, + "loss": 0.4579, + "step": 7826 + }, + { + "epoch": 0.67, + "learning_rate": 5.262911526088136e-06, + "loss": 0.4437, + "step": 7827 + }, + { + "epoch": 0.67, + "learning_rate": 5.260479619401451e-06, + "loss": 0.4635, + "step": 7828 + }, + { + "epoch": 0.67, + "learning_rate": 5.258048074170379e-06, + "loss": 0.4748, + "step": 7829 + }, + { + "epoch": 0.67, + "learning_rate": 5.255616890580356e-06, + "loss": 0.4578, + "step": 7830 + }, + { + "epoch": 0.67, + "learning_rate": 5.253186068816795e-06, + "loss": 0.4496, + "step": 7831 + }, + { + "epoch": 0.67, + "learning_rate": 5.2507556090650835e-06, + "loss": 0.4578, + "step": 7832 + }, + { + "epoch": 0.67, + "learning_rate": 5.248325511510575e-06, + "loss": 0.4441, + "step": 7833 + }, + { + "epoch": 0.67, + "learning_rate": 5.2458957763386005e-06, + "loss": 0.479, + "step": 7834 + }, + { + "epoch": 0.67, + "learning_rate": 5.243466403734464e-06, + "loss": 0.4855, + "step": 7835 + }, + { + "epoch": 0.67, + "learning_rate": 5.241037393883436e-06, + "loss": 0.4729, + "step": 7836 + }, + { + "epoch": 0.67, + "learning_rate": 5.2386087469707644e-06, + "loss": 0.4586, + "step": 7837 + }, + { + "epoch": 0.67, + "learning_rate": 5.236180463181672e-06, + "loss": 0.4643, + "step": 7838 + }, + { + "epoch": 0.67, + "learning_rate": 5.233752542701342e-06, + "loss": 0.4643, + "step": 7839 + }, + { + "epoch": 0.67, + "learning_rate": 5.231324985714942e-06, + "loss": 0.4518, + "step": 7840 + }, + { + "epoch": 0.67, + "learning_rate": 5.228897792407607e-06, + "loss": 0.4925, + "step": 7841 + }, + { + "epoch": 0.67, + "learning_rate": 5.226470962964445e-06, + "loss": 0.4744, + "step": 7842 + }, + { + "epoch": 0.67, + "learning_rate": 5.224044497570535e-06, + "loss": 0.4445, + "step": 7843 + }, + { + "epoch": 0.67, + "learning_rate": 5.2216183964109325e-06, + "loss": 0.4934, + "step": 7844 + }, + { + "epoch": 0.67, + "learning_rate": 5.219192659670663e-06, + "loss": 0.466, + "step": 7845 + }, + { + "epoch": 0.67, + "learning_rate": 5.2167672875347135e-06, + "loss": 0.4567, + "step": 7846 + }, + { + "epoch": 0.67, + "learning_rate": 5.214342280188067e-06, + "loss": 0.4599, + "step": 7847 + }, + { + "epoch": 0.67, + "learning_rate": 5.211917637815654e-06, + "loss": 0.4662, + "step": 7848 + }, + { + "epoch": 0.67, + "learning_rate": 5.209493360602392e-06, + "loss": 0.4446, + "step": 7849 + }, + { + "epoch": 0.67, + "learning_rate": 5.207069448733166e-06, + "loss": 0.468, + "step": 7850 + }, + { + "epoch": 0.67, + "learning_rate": 5.204645902392834e-06, + "loss": 0.4688, + "step": 7851 + }, + { + "epoch": 0.67, + "learning_rate": 5.202222721766226e-06, + "loss": 0.4651, + "step": 7852 + }, + { + "epoch": 0.67, + "learning_rate": 5.199799907038141e-06, + "loss": 0.4859, + "step": 7853 + }, + { + "epoch": 0.67, + "learning_rate": 5.197377458393363e-06, + "loss": 0.4543, + "step": 7854 + }, + { + "epoch": 0.67, + "learning_rate": 5.19495537601662e-06, + "loss": 0.467, + "step": 7855 + }, + { + "epoch": 0.67, + "learning_rate": 5.192533660092647e-06, + "loss": 0.4517, + "step": 7856 + }, + { + "epoch": 0.67, + "learning_rate": 5.190112310806126e-06, + "loss": 0.449, + "step": 7857 + }, + { + "epoch": 0.67, + "learning_rate": 5.1876913283417196e-06, + "loss": 0.4859, + "step": 7858 + }, + { + "epoch": 0.67, + "learning_rate": 5.185270712884064e-06, + "loss": 0.4444, + "step": 7859 + }, + { + "epoch": 0.67, + "learning_rate": 5.1828504646177655e-06, + "loss": 0.4716, + "step": 7860 + }, + { + "epoch": 0.67, + "learning_rate": 5.180430583727401e-06, + "loss": 0.4688, + "step": 7861 + }, + { + "epoch": 0.67, + "learning_rate": 5.178011070397519e-06, + "loss": 0.4832, + "step": 7862 + }, + { + "epoch": 0.67, + "learning_rate": 5.175591924812651e-06, + "loss": 0.5115, + "step": 7863 + }, + { + "epoch": 0.67, + "learning_rate": 5.173173147157275e-06, + "loss": 0.4487, + "step": 7864 + }, + { + "epoch": 0.67, + "learning_rate": 5.170754737615874e-06, + "loss": 0.4689, + "step": 7865 + }, + { + "epoch": 0.67, + "learning_rate": 5.168336696372875e-06, + "loss": 0.4569, + "step": 7866 + }, + { + "epoch": 0.67, + "learning_rate": 5.165919023612691e-06, + "loss": 0.4613, + "step": 7867 + }, + { + "epoch": 0.67, + "learning_rate": 5.163501719519704e-06, + "loss": 0.463, + "step": 7868 + }, + { + "epoch": 0.67, + "learning_rate": 5.161084784278265e-06, + "loss": 0.4631, + "step": 7869 + }, + { + "epoch": 0.67, + "learning_rate": 5.158668218072706e-06, + "loss": 0.4755, + "step": 7870 + }, + { + "epoch": 0.67, + "learning_rate": 5.156252021087318e-06, + "loss": 0.4642, + "step": 7871 + }, + { + "epoch": 0.67, + "learning_rate": 5.153836193506378e-06, + "loss": 0.4928, + "step": 7872 + }, + { + "epoch": 0.67, + "learning_rate": 5.151420735514114e-06, + "loss": 0.4566, + "step": 7873 + }, + { + "epoch": 0.67, + "learning_rate": 5.149005647294755e-06, + "loss": 0.4818, + "step": 7874 + }, + { + "epoch": 0.67, + "learning_rate": 5.146590929032473e-06, + "loss": 0.4617, + "step": 7875 + }, + { + "epoch": 0.67, + "learning_rate": 5.144176580911431e-06, + "loss": 0.4803, + "step": 7876 + }, + { + "epoch": 0.67, + "learning_rate": 5.1417626031157534e-06, + "loss": 0.4733, + "step": 7877 + }, + { + "epoch": 0.67, + "learning_rate": 5.139348995829543e-06, + "loss": 0.4579, + "step": 7878 + }, + { + "epoch": 0.67, + "learning_rate": 5.13693575923687e-06, + "loss": 0.4465, + "step": 7879 + }, + { + "epoch": 0.67, + "learning_rate": 5.1345228935217796e-06, + "loss": 0.4485, + "step": 7880 + }, + { + "epoch": 0.67, + "learning_rate": 5.1321103988682894e-06, + "loss": 0.4834, + "step": 7881 + }, + { + "epoch": 0.67, + "learning_rate": 5.129698275460375e-06, + "loss": 0.449, + "step": 7882 + }, + { + "epoch": 0.67, + "learning_rate": 5.127286523482008e-06, + "loss": 0.4653, + "step": 7883 + }, + { + "epoch": 0.67, + "learning_rate": 5.124875143117116e-06, + "loss": 0.4598, + "step": 7884 + }, + { + "epoch": 0.67, + "learning_rate": 5.122464134549596e-06, + "loss": 0.4523, + "step": 7885 + }, + { + "epoch": 0.67, + "learning_rate": 5.120053497963324e-06, + "loss": 0.4924, + "step": 7886 + }, + { + "epoch": 0.67, + "learning_rate": 5.117643233542146e-06, + "loss": 0.4749, + "step": 7887 + }, + { + "epoch": 0.67, + "learning_rate": 5.1152333414698774e-06, + "loss": 0.4696, + "step": 7888 + }, + { + "epoch": 0.67, + "learning_rate": 5.1128238219303085e-06, + "loss": 0.4612, + "step": 7889 + }, + { + "epoch": 0.67, + "learning_rate": 5.110414675107201e-06, + "loss": 0.462, + "step": 7890 + }, + { + "epoch": 0.67, + "learning_rate": 5.1080059011842764e-06, + "loss": 0.4591, + "step": 7891 + }, + { + "epoch": 0.67, + "learning_rate": 5.105597500345249e-06, + "loss": 0.4662, + "step": 7892 + }, + { + "epoch": 0.67, + "learning_rate": 5.103189472773793e-06, + "loss": 0.4537, + "step": 7893 + }, + { + "epoch": 0.67, + "learning_rate": 5.100781818653549e-06, + "loss": 0.4519, + "step": 7894 + }, + { + "epoch": 0.67, + "learning_rate": 5.098374538168136e-06, + "loss": 0.4929, + "step": 7895 + }, + { + "epoch": 0.67, + "learning_rate": 5.0959676315011445e-06, + "loss": 0.4484, + "step": 7896 + }, + { + "epoch": 0.67, + "learning_rate": 5.093561098836135e-06, + "loss": 0.4603, + "step": 7897 + }, + { + "epoch": 0.67, + "learning_rate": 5.09115494035664e-06, + "loss": 0.4536, + "step": 7898 + }, + { + "epoch": 0.67, + "learning_rate": 5.0887491562461665e-06, + "loss": 0.4755, + "step": 7899 + }, + { + "epoch": 0.67, + "learning_rate": 5.086343746688184e-06, + "loss": 0.4463, + "step": 7900 + }, + { + "epoch": 0.67, + "learning_rate": 5.083938711866136e-06, + "loss": 0.4466, + "step": 7901 + }, + { + "epoch": 0.67, + "learning_rate": 5.081534051963455e-06, + "loss": 0.4882, + "step": 7902 + }, + { + "epoch": 0.67, + "learning_rate": 5.079129767163516e-06, + "loss": 0.48, + "step": 7903 + }, + { + "epoch": 0.67, + "learning_rate": 5.0767258576496846e-06, + "loss": 0.4664, + "step": 7904 + }, + { + "epoch": 0.67, + "learning_rate": 5.0743223236052944e-06, + "loss": 0.4402, + "step": 7905 + }, + { + "epoch": 0.67, + "learning_rate": 5.071919165213647e-06, + "loss": 0.4605, + "step": 7906 + }, + { + "epoch": 0.67, + "learning_rate": 5.069516382658017e-06, + "loss": 0.4594, + "step": 7907 + }, + { + "epoch": 0.67, + "learning_rate": 5.0671139761216585e-06, + "loss": 0.4767, + "step": 7908 + }, + { + "epoch": 0.67, + "learning_rate": 5.064711945787777e-06, + "loss": 0.4601, + "step": 7909 + }, + { + "epoch": 0.67, + "learning_rate": 5.062310291839563e-06, + "loss": 0.4781, + "step": 7910 + }, + { + "epoch": 0.67, + "learning_rate": 5.059909014460188e-06, + "loss": 0.4658, + "step": 7911 + }, + { + "epoch": 0.67, + "learning_rate": 5.057508113832772e-06, + "loss": 0.4704, + "step": 7912 + }, + { + "epoch": 0.67, + "learning_rate": 5.055107590140423e-06, + "loss": 0.4569, + "step": 7913 + }, + { + "epoch": 0.67, + "learning_rate": 5.052707443566212e-06, + "loss": 0.4485, + "step": 7914 + }, + { + "epoch": 0.67, + "learning_rate": 5.050307674293185e-06, + "loss": 0.4729, + "step": 7915 + }, + { + "epoch": 0.67, + "learning_rate": 5.0479082825043604e-06, + "loss": 0.465, + "step": 7916 + }, + { + "epoch": 0.68, + "learning_rate": 5.045509268382728e-06, + "loss": 0.48, + "step": 7917 + }, + { + "epoch": 0.68, + "learning_rate": 5.043110632111239e-06, + "loss": 0.4565, + "step": 7918 + }, + { + "epoch": 0.68, + "learning_rate": 5.040712373872824e-06, + "loss": 0.455, + "step": 7919 + }, + { + "epoch": 0.68, + "learning_rate": 5.038314493850396e-06, + "loss": 0.466, + "step": 7920 + }, + { + "epoch": 0.68, + "learning_rate": 5.035916992226814e-06, + "loss": 0.4452, + "step": 7921 + }, + { + "epoch": 0.68, + "learning_rate": 5.033519869184928e-06, + "loss": 0.4614, + "step": 7922 + }, + { + "epoch": 0.68, + "learning_rate": 5.031123124907553e-06, + "loss": 0.4527, + "step": 7923 + }, + { + "epoch": 0.68, + "learning_rate": 5.028726759577467e-06, + "loss": 0.4646, + "step": 7924 + }, + { + "epoch": 0.68, + "learning_rate": 5.026330773377437e-06, + "loss": 0.4446, + "step": 7925 + }, + { + "epoch": 0.68, + "learning_rate": 5.023935166490189e-06, + "loss": 0.4651, + "step": 7926 + }, + { + "epoch": 0.68, + "learning_rate": 5.021539939098416e-06, + "loss": 0.454, + "step": 7927 + }, + { + "epoch": 0.68, + "learning_rate": 5.019145091384789e-06, + "loss": 0.4625, + "step": 7928 + }, + { + "epoch": 0.68, + "learning_rate": 5.016750623531959e-06, + "loss": 0.4604, + "step": 7929 + }, + { + "epoch": 0.68, + "learning_rate": 5.014356535722527e-06, + "loss": 0.451, + "step": 7930 + }, + { + "epoch": 0.68, + "learning_rate": 5.01196282813908e-06, + "loss": 0.46, + "step": 7931 + }, + { + "epoch": 0.68, + "learning_rate": 5.009569500964175e-06, + "loss": 0.4807, + "step": 7932 + }, + { + "epoch": 0.68, + "learning_rate": 5.007176554380328e-06, + "loss": 0.4608, + "step": 7933 + }, + { + "epoch": 0.68, + "learning_rate": 5.004783988570045e-06, + "loss": 0.4509, + "step": 7934 + }, + { + "epoch": 0.68, + "learning_rate": 5.0023918037157926e-06, + "loss": 0.4399, + "step": 7935 + }, + { + "epoch": 0.68, + "learning_rate": 5.000000000000003e-06, + "loss": 0.471, + "step": 7936 + }, + { + "epoch": 0.68, + "learning_rate": 4.997608577605082e-06, + "loss": 0.4576, + "step": 7937 + }, + { + "epoch": 0.68, + "learning_rate": 4.995217536713425e-06, + "loss": 0.4666, + "step": 7938 + }, + { + "epoch": 0.68, + "learning_rate": 4.9928268775073675e-06, + "loss": 0.4601, + "step": 7939 + }, + { + "epoch": 0.68, + "learning_rate": 4.9904366001692375e-06, + "loss": 0.4568, + "step": 7940 + }, + { + "epoch": 0.68, + "learning_rate": 4.9880467048813305e-06, + "loss": 0.4607, + "step": 7941 + }, + { + "epoch": 0.68, + "learning_rate": 4.9856571918258976e-06, + "loss": 0.4529, + "step": 7942 + }, + { + "epoch": 0.68, + "learning_rate": 4.983268061185185e-06, + "loss": 0.4896, + "step": 7943 + }, + { + "epoch": 0.68, + "learning_rate": 4.9808793131414e-06, + "loss": 0.4501, + "step": 7944 + }, + { + "epoch": 0.68, + "learning_rate": 4.978490947876709e-06, + "loss": 0.4842, + "step": 7945 + }, + { + "epoch": 0.68, + "learning_rate": 4.976102965573258e-06, + "loss": 0.4715, + "step": 7946 + }, + { + "epoch": 0.68, + "learning_rate": 4.9737153664131754e-06, + "loss": 0.4911, + "step": 7947 + }, + { + "epoch": 0.68, + "learning_rate": 4.9713281505785404e-06, + "loss": 0.4748, + "step": 7948 + }, + { + "epoch": 0.68, + "learning_rate": 4.968941318251415e-06, + "loss": 0.4678, + "step": 7949 + }, + { + "epoch": 0.68, + "learning_rate": 4.966554869613831e-06, + "loss": 0.463, + "step": 7950 + }, + { + "epoch": 0.68, + "learning_rate": 4.96416880484778e-06, + "loss": 0.4803, + "step": 7951 + }, + { + "epoch": 0.68, + "learning_rate": 4.961783124135244e-06, + "loss": 0.4842, + "step": 7952 + }, + { + "epoch": 0.68, + "learning_rate": 4.959397827658164e-06, + "loss": 0.4624, + "step": 7953 + }, + { + "epoch": 0.68, + "learning_rate": 4.957012915598446e-06, + "loss": 0.4784, + "step": 7954 + }, + { + "epoch": 0.68, + "learning_rate": 4.9546283881379775e-06, + "loss": 0.4577, + "step": 7955 + }, + { + "epoch": 0.68, + "learning_rate": 4.952244245458612e-06, + "loss": 0.4523, + "step": 7956 + }, + { + "epoch": 0.68, + "learning_rate": 4.949860487742173e-06, + "loss": 0.4439, + "step": 7957 + }, + { + "epoch": 0.68, + "learning_rate": 4.947477115170457e-06, + "loss": 0.4627, + "step": 7958 + }, + { + "epoch": 0.68, + "learning_rate": 4.945094127925234e-06, + "loss": 0.4641, + "step": 7959 + }, + { + "epoch": 0.68, + "learning_rate": 4.94271152618823e-06, + "loss": 0.4555, + "step": 7960 + }, + { + "epoch": 0.68, + "learning_rate": 4.940329310141161e-06, + "loss": 0.4718, + "step": 7961 + }, + { + "epoch": 0.68, + "learning_rate": 4.937947479965705e-06, + "loss": 0.4685, + "step": 7962 + }, + { + "epoch": 0.68, + "learning_rate": 4.935566035843506e-06, + "loss": 0.4668, + "step": 7963 + }, + { + "epoch": 0.68, + "learning_rate": 4.933184977956184e-06, + "loss": 0.4751, + "step": 7964 + }, + { + "epoch": 0.68, + "learning_rate": 4.930804306485328e-06, + "loss": 0.4541, + "step": 7965 + }, + { + "epoch": 0.68, + "learning_rate": 4.928424021612499e-06, + "loss": 0.4778, + "step": 7966 + }, + { + "epoch": 0.68, + "learning_rate": 4.926044123519228e-06, + "loss": 0.4512, + "step": 7967 + }, + { + "epoch": 0.68, + "learning_rate": 4.9236646123870194e-06, + "loss": 0.4528, + "step": 7968 + }, + { + "epoch": 0.68, + "learning_rate": 4.921285488397332e-06, + "loss": 0.4455, + "step": 7969 + }, + { + "epoch": 0.68, + "learning_rate": 4.9189067517316205e-06, + "loss": 0.4561, + "step": 7970 + }, + { + "epoch": 0.68, + "learning_rate": 4.916528402571296e-06, + "loss": 0.4555, + "step": 7971 + }, + { + "epoch": 0.68, + "learning_rate": 4.914150441097736e-06, + "loss": 0.447, + "step": 7972 + }, + { + "epoch": 0.68, + "learning_rate": 4.911772867492295e-06, + "loss": 0.4443, + "step": 7973 + }, + { + "epoch": 0.68, + "learning_rate": 4.909395681936297e-06, + "loss": 0.4561, + "step": 7974 + }, + { + "epoch": 0.68, + "learning_rate": 4.907018884611039e-06, + "loss": 0.478, + "step": 7975 + }, + { + "epoch": 0.68, + "learning_rate": 4.904642475697783e-06, + "loss": 0.4489, + "step": 7976 + }, + { + "epoch": 0.68, + "learning_rate": 4.902266455377768e-06, + "loss": 0.4656, + "step": 7977 + }, + { + "epoch": 0.68, + "learning_rate": 4.899890823832191e-06, + "loss": 0.4582, + "step": 7978 + }, + { + "epoch": 0.68, + "learning_rate": 4.897515581242228e-06, + "loss": 0.4674, + "step": 7979 + }, + { + "epoch": 0.68, + "learning_rate": 4.895140727789037e-06, + "loss": 0.4538, + "step": 7980 + }, + { + "epoch": 0.68, + "learning_rate": 4.892766263653723e-06, + "loss": 0.473, + "step": 7981 + }, + { + "epoch": 0.68, + "learning_rate": 4.890392189017375e-06, + "loss": 0.4527, + "step": 7982 + }, + { + "epoch": 0.68, + "learning_rate": 4.888018504061051e-06, + "loss": 0.4441, + "step": 7983 + }, + { + "epoch": 0.68, + "learning_rate": 4.885645208965779e-06, + "loss": 0.4802, + "step": 7984 + }, + { + "epoch": 0.68, + "learning_rate": 4.883272303912554e-06, + "loss": 0.4553, + "step": 7985 + }, + { + "epoch": 0.68, + "learning_rate": 4.880899789082349e-06, + "loss": 0.4558, + "step": 7986 + }, + { + "epoch": 0.68, + "learning_rate": 4.8785276646560935e-06, + "loss": 0.4849, + "step": 7987 + }, + { + "epoch": 0.68, + "learning_rate": 4.876155930814696e-06, + "loss": 0.4425, + "step": 7988 + }, + { + "epoch": 0.68, + "learning_rate": 4.8737845877390455e-06, + "loss": 0.483, + "step": 7989 + }, + { + "epoch": 0.68, + "learning_rate": 4.871413635609981e-06, + "loss": 0.4682, + "step": 7990 + }, + { + "epoch": 0.68, + "learning_rate": 4.869043074608324e-06, + "loss": 0.462, + "step": 7991 + }, + { + "epoch": 0.68, + "learning_rate": 4.866672904914862e-06, + "loss": 0.4638, + "step": 7992 + }, + { + "epoch": 0.68, + "learning_rate": 4.8643031267103556e-06, + "loss": 0.4922, + "step": 7993 + }, + { + "epoch": 0.68, + "learning_rate": 4.861933740175534e-06, + "loss": 0.4696, + "step": 7994 + }, + { + "epoch": 0.68, + "learning_rate": 4.8595647454911e-06, + "loss": 0.4568, + "step": 7995 + }, + { + "epoch": 0.68, + "learning_rate": 4.857196142837716e-06, + "loss": 0.4821, + "step": 7996 + }, + { + "epoch": 0.68, + "learning_rate": 4.85482793239602e-06, + "loss": 0.4903, + "step": 7997 + }, + { + "epoch": 0.68, + "learning_rate": 4.852460114346634e-06, + "loss": 0.4738, + "step": 7998 + }, + { + "epoch": 0.68, + "learning_rate": 4.850092688870126e-06, + "loss": 0.4525, + "step": 7999 + }, + { + "epoch": 0.68, + "learning_rate": 4.847725656147051e-06, + "loss": 0.4585, + "step": 8000 + }, + { + "epoch": 0.68, + "learning_rate": 4.845359016357927e-06, + "loss": 0.4608, + "step": 8001 + }, + { + "epoch": 0.68, + "learning_rate": 4.8429927696832434e-06, + "loss": 0.4611, + "step": 8002 + }, + { + "epoch": 0.68, + "learning_rate": 4.840626916303461e-06, + "loss": 0.4714, + "step": 8003 + }, + { + "epoch": 0.68, + "learning_rate": 4.838261456399012e-06, + "loss": 0.4627, + "step": 8004 + }, + { + "epoch": 0.68, + "learning_rate": 4.835896390150295e-06, + "loss": 0.4661, + "step": 8005 + }, + { + "epoch": 0.68, + "learning_rate": 4.833531717737673e-06, + "loss": 0.4535, + "step": 8006 + }, + { + "epoch": 0.68, + "learning_rate": 4.831167439341499e-06, + "loss": 0.4654, + "step": 8007 + }, + { + "epoch": 0.68, + "learning_rate": 4.82880355514207e-06, + "loss": 0.4677, + "step": 8008 + }, + { + "epoch": 0.68, + "learning_rate": 4.826440065319672e-06, + "loss": 0.4673, + "step": 8009 + }, + { + "epoch": 0.68, + "learning_rate": 4.824076970054554e-06, + "loss": 0.4539, + "step": 8010 + }, + { + "epoch": 0.68, + "learning_rate": 4.821714269526935e-06, + "loss": 0.449, + "step": 8011 + }, + { + "epoch": 0.68, + "learning_rate": 4.819351963917004e-06, + "loss": 0.465, + "step": 8012 + }, + { + "epoch": 0.68, + "learning_rate": 4.816990053404921e-06, + "loss": 0.4646, + "step": 8013 + }, + { + "epoch": 0.68, + "learning_rate": 4.814628538170818e-06, + "loss": 0.4696, + "step": 8014 + }, + { + "epoch": 0.68, + "learning_rate": 4.812267418394784e-06, + "loss": 0.4641, + "step": 8015 + }, + { + "epoch": 0.68, + "learning_rate": 4.809906694256903e-06, + "loss": 0.4757, + "step": 8016 + }, + { + "epoch": 0.68, + "learning_rate": 4.807546365937201e-06, + "loss": 0.4756, + "step": 8017 + }, + { + "epoch": 0.68, + "learning_rate": 4.805186433615691e-06, + "loss": 0.4433, + "step": 8018 + }, + { + "epoch": 0.68, + "learning_rate": 4.802826897472351e-06, + "loss": 0.485, + "step": 8019 + }, + { + "epoch": 0.68, + "learning_rate": 4.800467757687131e-06, + "loss": 0.4495, + "step": 8020 + }, + { + "epoch": 0.68, + "learning_rate": 4.798109014439944e-06, + "loss": 0.4486, + "step": 8021 + }, + { + "epoch": 0.68, + "learning_rate": 4.795750667910684e-06, + "loss": 0.4622, + "step": 8022 + }, + { + "epoch": 0.68, + "learning_rate": 4.793392718279207e-06, + "loss": 0.4738, + "step": 8023 + }, + { + "epoch": 0.68, + "learning_rate": 4.791035165725332e-06, + "loss": 0.4648, + "step": 8024 + }, + { + "epoch": 0.68, + "learning_rate": 4.788678010428869e-06, + "loss": 0.4665, + "step": 8025 + }, + { + "epoch": 0.68, + "learning_rate": 4.786321252569574e-06, + "loss": 0.476, + "step": 8026 + }, + { + "epoch": 0.68, + "learning_rate": 4.7839648923271855e-06, + "loss": 0.4611, + "step": 8027 + }, + { + "epoch": 0.68, + "learning_rate": 4.781608929881412e-06, + "loss": 0.4643, + "step": 8028 + }, + { + "epoch": 0.68, + "learning_rate": 4.779253365411927e-06, + "loss": 0.4718, + "step": 8029 + }, + { + "epoch": 0.68, + "learning_rate": 4.776898199098377e-06, + "loss": 0.4773, + "step": 8030 + }, + { + "epoch": 0.68, + "learning_rate": 4.7745434311203755e-06, + "loss": 0.4748, + "step": 8031 + }, + { + "epoch": 0.68, + "learning_rate": 4.772189061657511e-06, + "loss": 0.4726, + "step": 8032 + }, + { + "epoch": 0.68, + "learning_rate": 4.769835090889331e-06, + "loss": 0.4732, + "step": 8033 + }, + { + "epoch": 0.69, + "learning_rate": 4.767481518995362e-06, + "loss": 0.4638, + "step": 8034 + }, + { + "epoch": 0.69, + "learning_rate": 4.765128346155098e-06, + "loss": 0.4623, + "step": 8035 + }, + { + "epoch": 0.69, + "learning_rate": 4.762775572547999e-06, + "loss": 0.489, + "step": 8036 + }, + { + "epoch": 0.69, + "learning_rate": 4.760423198353502e-06, + "loss": 0.4693, + "step": 8037 + }, + { + "epoch": 0.69, + "learning_rate": 4.758071223751006e-06, + "loss": 0.4573, + "step": 8038 + }, + { + "epoch": 0.69, + "learning_rate": 4.755719648919883e-06, + "loss": 0.4667, + "step": 8039 + }, + { + "epoch": 0.69, + "learning_rate": 4.753368474039473e-06, + "loss": 0.4563, + "step": 8040 + }, + { + "epoch": 0.69, + "learning_rate": 4.751017699289092e-06, + "loss": 0.4495, + "step": 8041 + }, + { + "epoch": 0.69, + "learning_rate": 4.748667324848011e-06, + "loss": 0.4822, + "step": 8042 + }, + { + "epoch": 0.69, + "learning_rate": 4.746317350895483e-06, + "loss": 0.464, + "step": 8043 + }, + { + "epoch": 0.69, + "learning_rate": 4.743967777610727e-06, + "loss": 0.4543, + "step": 8044 + }, + { + "epoch": 0.69, + "learning_rate": 4.741618605172933e-06, + "loss": 0.4586, + "step": 8045 + }, + { + "epoch": 0.69, + "learning_rate": 4.739269833761256e-06, + "loss": 0.4951, + "step": 8046 + }, + { + "epoch": 0.69, + "learning_rate": 4.736921463554824e-06, + "loss": 0.4435, + "step": 8047 + }, + { + "epoch": 0.69, + "learning_rate": 4.7345734947327345e-06, + "loss": 0.4808, + "step": 8048 + }, + { + "epoch": 0.69, + "learning_rate": 4.732225927474054e-06, + "loss": 0.4599, + "step": 8049 + }, + { + "epoch": 0.69, + "learning_rate": 4.729878761957819e-06, + "loss": 0.4483, + "step": 8050 + }, + { + "epoch": 0.69, + "learning_rate": 4.727531998363028e-06, + "loss": 0.4623, + "step": 8051 + }, + { + "epoch": 0.69, + "learning_rate": 4.725185636868659e-06, + "loss": 0.4533, + "step": 8052 + }, + { + "epoch": 0.69, + "learning_rate": 4.722839677653654e-06, + "loss": 0.4678, + "step": 8053 + }, + { + "epoch": 0.69, + "learning_rate": 4.720494120896928e-06, + "loss": 0.4704, + "step": 8054 + }, + { + "epoch": 0.69, + "learning_rate": 4.718148966777362e-06, + "loss": 0.4582, + "step": 8055 + }, + { + "epoch": 0.69, + "learning_rate": 4.7158042154738094e-06, + "loss": 0.4787, + "step": 8056 + }, + { + "epoch": 0.69, + "learning_rate": 4.713459867165081e-06, + "loss": 0.4461, + "step": 8057 + }, + { + "epoch": 0.69, + "learning_rate": 4.711115922029977e-06, + "loss": 0.4675, + "step": 8058 + }, + { + "epoch": 0.69, + "learning_rate": 4.708772380247257e-06, + "loss": 0.4611, + "step": 8059 + }, + { + "epoch": 0.69, + "learning_rate": 4.706429241995642e-06, + "loss": 0.4645, + "step": 8060 + }, + { + "epoch": 0.69, + "learning_rate": 4.70408650745383e-06, + "loss": 0.459, + "step": 8061 + }, + { + "epoch": 0.69, + "learning_rate": 4.701744176800498e-06, + "loss": 0.4799, + "step": 8062 + }, + { + "epoch": 0.69, + "learning_rate": 4.699402250214271e-06, + "loss": 0.4632, + "step": 8063 + }, + { + "epoch": 0.69, + "learning_rate": 4.697060727873757e-06, + "loss": 0.4618, + "step": 8064 + }, + { + "epoch": 0.69, + "learning_rate": 4.694719609957536e-06, + "loss": 0.4826, + "step": 8065 + }, + { + "epoch": 0.69, + "learning_rate": 4.692378896644137e-06, + "loss": 0.463, + "step": 8066 + }, + { + "epoch": 0.69, + "learning_rate": 4.690038588112087e-06, + "loss": 0.4741, + "step": 8067 + }, + { + "epoch": 0.69, + "learning_rate": 4.6876986845398665e-06, + "loss": 0.4609, + "step": 8068 + }, + { + "epoch": 0.69, + "learning_rate": 4.685359186105918e-06, + "loss": 0.4747, + "step": 8069 + }, + { + "epoch": 0.69, + "learning_rate": 4.683020092988662e-06, + "loss": 0.4398, + "step": 8070 + }, + { + "epoch": 0.69, + "learning_rate": 4.6806814053665e-06, + "loss": 0.4613, + "step": 8071 + }, + { + "epoch": 0.69, + "learning_rate": 4.678343123417778e-06, + "loss": 0.4769, + "step": 8072 + }, + { + "epoch": 0.69, + "learning_rate": 4.676005247320826e-06, + "loss": 0.4712, + "step": 8073 + }, + { + "epoch": 0.69, + "learning_rate": 4.673667777253944e-06, + "loss": 0.4532, + "step": 8074 + }, + { + "epoch": 0.69, + "learning_rate": 4.671330713395388e-06, + "loss": 0.4652, + "step": 8075 + }, + { + "epoch": 0.69, + "learning_rate": 4.6689940559234e-06, + "loss": 0.4776, + "step": 8076 + }, + { + "epoch": 0.69, + "learning_rate": 4.666657805016187e-06, + "loss": 0.4715, + "step": 8077 + }, + { + "epoch": 0.69, + "learning_rate": 4.664321960851912e-06, + "loss": 0.4542, + "step": 8078 + }, + { + "epoch": 0.69, + "learning_rate": 4.661986523608716e-06, + "loss": 0.4666, + "step": 8079 + }, + { + "epoch": 0.69, + "learning_rate": 4.659651493464721e-06, + "loss": 0.4417, + "step": 8080 + }, + { + "epoch": 0.69, + "learning_rate": 4.657316870597993e-06, + "loss": 0.4604, + "step": 8081 + }, + { + "epoch": 0.69, + "learning_rate": 4.6549826551865876e-06, + "loss": 0.4721, + "step": 8082 + }, + { + "epoch": 0.69, + "learning_rate": 4.652648847408523e-06, + "loss": 0.4648, + "step": 8083 + }, + { + "epoch": 0.69, + "learning_rate": 4.650315447441773e-06, + "loss": 0.477, + "step": 8084 + }, + { + "epoch": 0.69, + "learning_rate": 4.647982455464306e-06, + "loss": 0.4824, + "step": 8085 + }, + { + "epoch": 0.69, + "learning_rate": 4.645649871654045e-06, + "loss": 0.4671, + "step": 8086 + }, + { + "epoch": 0.69, + "learning_rate": 4.643317696188875e-06, + "loss": 0.4731, + "step": 8087 + }, + { + "epoch": 0.69, + "learning_rate": 4.64098592924666e-06, + "loss": 0.4705, + "step": 8088 + }, + { + "epoch": 0.69, + "learning_rate": 4.638654571005231e-06, + "loss": 0.4482, + "step": 8089 + }, + { + "epoch": 0.69, + "learning_rate": 4.636323621642389e-06, + "loss": 0.4656, + "step": 8090 + }, + { + "epoch": 0.69, + "learning_rate": 4.633993081335899e-06, + "loss": 0.4659, + "step": 8091 + }, + { + "epoch": 0.69, + "learning_rate": 4.631662950263502e-06, + "loss": 0.4631, + "step": 8092 + }, + { + "epoch": 0.69, + "learning_rate": 4.629333228602895e-06, + "loss": 0.4533, + "step": 8093 + }, + { + "epoch": 0.69, + "learning_rate": 4.627003916531761e-06, + "loss": 0.4518, + "step": 8094 + }, + { + "epoch": 0.69, + "learning_rate": 4.624675014227743e-06, + "loss": 0.4659, + "step": 8095 + }, + { + "epoch": 0.69, + "learning_rate": 4.622346521868446e-06, + "loss": 0.4559, + "step": 8096 + }, + { + "epoch": 0.69, + "learning_rate": 4.620018439631455e-06, + "loss": 0.4732, + "step": 8097 + }, + { + "epoch": 0.69, + "learning_rate": 4.617690767694319e-06, + "loss": 0.4735, + "step": 8098 + }, + { + "epoch": 0.69, + "learning_rate": 4.615363506234554e-06, + "loss": 0.4637, + "step": 8099 + }, + { + "epoch": 0.69, + "learning_rate": 4.613036655429649e-06, + "loss": 0.4685, + "step": 8100 + }, + { + "epoch": 0.69, + "learning_rate": 4.610710215457062e-06, + "loss": 0.4611, + "step": 8101 + }, + { + "epoch": 0.69, + "learning_rate": 4.608384186494205e-06, + "loss": 0.4721, + "step": 8102 + }, + { + "epoch": 0.69, + "learning_rate": 4.606058568718486e-06, + "loss": 0.4518, + "step": 8103 + }, + { + "epoch": 0.69, + "learning_rate": 4.603733362307261e-06, + "loss": 0.474, + "step": 8104 + }, + { + "epoch": 0.69, + "learning_rate": 4.601408567437855e-06, + "loss": 0.4691, + "step": 8105 + }, + { + "epoch": 0.69, + "learning_rate": 4.599084184287571e-06, + "loss": 0.4451, + "step": 8106 + }, + { + "epoch": 0.69, + "learning_rate": 4.596760213033674e-06, + "loss": 0.4609, + "step": 8107 + }, + { + "epoch": 0.69, + "learning_rate": 4.594436653853402e-06, + "loss": 0.4592, + "step": 8108 + }, + { + "epoch": 0.69, + "learning_rate": 4.592113506923959e-06, + "loss": 0.441, + "step": 8109 + }, + { + "epoch": 0.69, + "learning_rate": 4.589790772422519e-06, + "loss": 0.4817, + "step": 8110 + }, + { + "epoch": 0.69, + "learning_rate": 4.587468450526219e-06, + "loss": 0.4687, + "step": 8111 + }, + { + "epoch": 0.69, + "learning_rate": 4.585146541412168e-06, + "loss": 0.4516, + "step": 8112 + }, + { + "epoch": 0.69, + "learning_rate": 4.582825045257455e-06, + "loss": 0.4727, + "step": 8113 + }, + { + "epoch": 0.69, + "learning_rate": 4.580503962239117e-06, + "loss": 0.4703, + "step": 8114 + }, + { + "epoch": 0.69, + "learning_rate": 4.578183292534172e-06, + "loss": 0.4578, + "step": 8115 + }, + { + "epoch": 0.69, + "learning_rate": 4.575863036319604e-06, + "loss": 0.455, + "step": 8116 + }, + { + "epoch": 0.69, + "learning_rate": 4.573543193772368e-06, + "loss": 0.4772, + "step": 8117 + }, + { + "epoch": 0.69, + "learning_rate": 4.5712237650693806e-06, + "loss": 0.4722, + "step": 8118 + }, + { + "epoch": 0.69, + "learning_rate": 4.568904750387538e-06, + "loss": 0.4494, + "step": 8119 + }, + { + "epoch": 0.69, + "learning_rate": 4.566586149903689e-06, + "loss": 0.4573, + "step": 8120 + }, + { + "epoch": 0.69, + "learning_rate": 4.5642679637946605e-06, + "loss": 0.4571, + "step": 8121 + }, + { + "epoch": 0.69, + "learning_rate": 4.561950192237259e-06, + "loss": 0.453, + "step": 8122 + }, + { + "epoch": 0.69, + "learning_rate": 4.5596328354082344e-06, + "loss": 0.4636, + "step": 8123 + }, + { + "epoch": 0.69, + "learning_rate": 4.557315893484323e-06, + "loss": 0.4576, + "step": 8124 + }, + { + "epoch": 0.69, + "learning_rate": 4.554999366642225e-06, + "loss": 0.446, + "step": 8125 + }, + { + "epoch": 0.69, + "learning_rate": 4.552683255058605e-06, + "loss": 0.4691, + "step": 8126 + }, + { + "epoch": 0.69, + "learning_rate": 4.550367558910104e-06, + "loss": 0.4655, + "step": 8127 + }, + { + "epoch": 0.69, + "learning_rate": 4.548052278373327e-06, + "loss": 0.4687, + "step": 8128 + }, + { + "epoch": 0.69, + "learning_rate": 4.545737413624841e-06, + "loss": 0.4779, + "step": 8129 + }, + { + "epoch": 0.69, + "learning_rate": 4.543422964841188e-06, + "loss": 0.4832, + "step": 8130 + }, + { + "epoch": 0.69, + "learning_rate": 4.541108932198887e-06, + "loss": 0.454, + "step": 8131 + }, + { + "epoch": 0.69, + "learning_rate": 4.5387953158744045e-06, + "loss": 0.4472, + "step": 8132 + }, + { + "epoch": 0.69, + "learning_rate": 4.536482116044192e-06, + "loss": 0.4706, + "step": 8133 + }, + { + "epoch": 0.69, + "learning_rate": 4.534169332884662e-06, + "loss": 0.4714, + "step": 8134 + }, + { + "epoch": 0.69, + "learning_rate": 4.531856966572198e-06, + "loss": 0.4567, + "step": 8135 + }, + { + "epoch": 0.69, + "learning_rate": 4.529545017283151e-06, + "loss": 0.4601, + "step": 8136 + }, + { + "epoch": 0.69, + "learning_rate": 4.527233485193843e-06, + "loss": 0.4518, + "step": 8137 + }, + { + "epoch": 0.69, + "learning_rate": 4.524922370480554e-06, + "loss": 0.4582, + "step": 8138 + }, + { + "epoch": 0.69, + "learning_rate": 4.522611673319539e-06, + "loss": 0.4592, + "step": 8139 + }, + { + "epoch": 0.69, + "learning_rate": 4.520301393887032e-06, + "loss": 0.4805, + "step": 8140 + }, + { + "epoch": 0.69, + "learning_rate": 4.517991532359215e-06, + "loss": 0.4704, + "step": 8141 + }, + { + "epoch": 0.69, + "learning_rate": 4.51568208891225e-06, + "loss": 0.4505, + "step": 8142 + }, + { + "epoch": 0.69, + "learning_rate": 4.513373063722266e-06, + "loss": 0.4906, + "step": 8143 + }, + { + "epoch": 0.69, + "learning_rate": 4.511064456965357e-06, + "loss": 0.4612, + "step": 8144 + }, + { + "epoch": 0.69, + "learning_rate": 4.508756268817589e-06, + "loss": 0.439, + "step": 8145 + }, + { + "epoch": 0.69, + "learning_rate": 4.506448499454996e-06, + "loss": 0.4505, + "step": 8146 + }, + { + "epoch": 0.69, + "learning_rate": 4.504141149053572e-06, + "loss": 0.466, + "step": 8147 + }, + { + "epoch": 0.69, + "learning_rate": 4.5018342177892845e-06, + "loss": 0.4682, + "step": 8148 + }, + { + "epoch": 0.69, + "learning_rate": 4.499527705838081e-06, + "loss": 0.4636, + "step": 8149 + }, + { + "epoch": 0.69, + "learning_rate": 4.497221613375856e-06, + "loss": 0.4799, + "step": 8150 + }, + { + "epoch": 0.7, + "learning_rate": 4.4949159405784834e-06, + "loss": 0.4316, + "step": 8151 + }, + { + "epoch": 0.7, + "learning_rate": 4.492610687621805e-06, + "loss": 0.463, + "step": 8152 + }, + { + "epoch": 0.7, + "learning_rate": 4.490305854681627e-06, + "loss": 0.451, + "step": 8153 + }, + { + "epoch": 0.7, + "learning_rate": 4.488001441933727e-06, + "loss": 0.4684, + "step": 8154 + }, + { + "epoch": 0.7, + "learning_rate": 4.485697449553853e-06, + "loss": 0.4602, + "step": 8155 + }, + { + "epoch": 0.7, + "learning_rate": 4.483393877717709e-06, + "loss": 0.4833, + "step": 8156 + }, + { + "epoch": 0.7, + "learning_rate": 4.481090726600975e-06, + "loss": 0.4757, + "step": 8157 + }, + { + "epoch": 0.7, + "learning_rate": 4.478787996379311e-06, + "loss": 0.4567, + "step": 8158 + }, + { + "epoch": 0.7, + "learning_rate": 4.476485687228322e-06, + "loss": 0.4678, + "step": 8159 + }, + { + "epoch": 0.7, + "learning_rate": 4.4741837993235925e-06, + "loss": 0.4584, + "step": 8160 + }, + { + "epoch": 0.7, + "learning_rate": 4.471882332840677e-06, + "loss": 0.4429, + "step": 8161 + }, + { + "epoch": 0.7, + "learning_rate": 4.469581287955094e-06, + "loss": 0.4683, + "step": 8162 + }, + { + "epoch": 0.7, + "learning_rate": 4.467280664842331e-06, + "loss": 0.4654, + "step": 8163 + }, + { + "epoch": 0.7, + "learning_rate": 4.464980463677846e-06, + "loss": 0.4669, + "step": 8164 + }, + { + "epoch": 0.7, + "learning_rate": 4.4626806846370555e-06, + "loss": 0.468, + "step": 8165 + }, + { + "epoch": 0.7, + "learning_rate": 4.460381327895353e-06, + "loss": 0.4869, + "step": 8166 + }, + { + "epoch": 0.7, + "learning_rate": 4.458082393628098e-06, + "loss": 0.4581, + "step": 8167 + }, + { + "epoch": 0.7, + "learning_rate": 4.455783882010617e-06, + "loss": 0.483, + "step": 8168 + }, + { + "epoch": 0.7, + "learning_rate": 4.453485793218203e-06, + "loss": 0.4515, + "step": 8169 + }, + { + "epoch": 0.7, + "learning_rate": 4.451188127426119e-06, + "loss": 0.4773, + "step": 8170 + }, + { + "epoch": 0.7, + "learning_rate": 4.4488908848095935e-06, + "loss": 0.471, + "step": 8171 + }, + { + "epoch": 0.7, + "learning_rate": 4.446594065543825e-06, + "loss": 0.4517, + "step": 8172 + }, + { + "epoch": 0.7, + "learning_rate": 4.444297669803981e-06, + "loss": 0.4744, + "step": 8173 + }, + { + "epoch": 0.7, + "learning_rate": 4.442001697765187e-06, + "loss": 0.4399, + "step": 8174 + }, + { + "epoch": 0.7, + "learning_rate": 4.439706149602547e-06, + "loss": 0.4696, + "step": 8175 + }, + { + "epoch": 0.7, + "learning_rate": 4.437411025491131e-06, + "loss": 0.4586, + "step": 8176 + }, + { + "epoch": 0.7, + "learning_rate": 4.435116325605972e-06, + "loss": 0.4484, + "step": 8177 + }, + { + "epoch": 0.7, + "learning_rate": 4.432822050122076e-06, + "loss": 0.4558, + "step": 8178 + }, + { + "epoch": 0.7, + "learning_rate": 4.4305281992144125e-06, + "loss": 0.4654, + "step": 8179 + }, + { + "epoch": 0.7, + "learning_rate": 4.42823477305792e-06, + "loss": 0.4518, + "step": 8180 + }, + { + "epoch": 0.7, + "learning_rate": 4.425941771827506e-06, + "loss": 0.4594, + "step": 8181 + }, + { + "epoch": 0.7, + "learning_rate": 4.423649195698042e-06, + "loss": 0.463, + "step": 8182 + }, + { + "epoch": 0.7, + "learning_rate": 4.421357044844374e-06, + "loss": 0.4682, + "step": 8183 + }, + { + "epoch": 0.7, + "learning_rate": 4.419065319441306e-06, + "loss": 0.4551, + "step": 8184 + }, + { + "epoch": 0.7, + "learning_rate": 4.416774019663615e-06, + "loss": 0.4449, + "step": 8185 + }, + { + "epoch": 0.7, + "learning_rate": 4.414483145686048e-06, + "loss": 0.4786, + "step": 8186 + }, + { + "epoch": 0.7, + "learning_rate": 4.412192697683315e-06, + "loss": 0.462, + "step": 8187 + }, + { + "epoch": 0.7, + "learning_rate": 4.409902675830094e-06, + "loss": 0.4521, + "step": 8188 + }, + { + "epoch": 0.7, + "learning_rate": 4.407613080301037e-06, + "loss": 0.482, + "step": 8189 + }, + { + "epoch": 0.7, + "learning_rate": 4.405323911270748e-06, + "loss": 0.4624, + "step": 8190 + }, + { + "epoch": 0.7, + "learning_rate": 4.403035168913817e-06, + "loss": 0.4737, + "step": 8191 + }, + { + "epoch": 0.7, + "learning_rate": 4.400746853404795e-06, + "loss": 0.4733, + "step": 8192 + }, + { + "epoch": 0.7, + "learning_rate": 4.39845896491819e-06, + "loss": 0.4659, + "step": 8193 + }, + { + "epoch": 0.7, + "learning_rate": 4.39617150362849e-06, + "loss": 0.4415, + "step": 8194 + }, + { + "epoch": 0.7, + "learning_rate": 4.393884469710147e-06, + "loss": 0.4432, + "step": 8195 + }, + { + "epoch": 0.7, + "learning_rate": 4.391597863337579e-06, + "loss": 0.4787, + "step": 8196 + }, + { + "epoch": 0.7, + "learning_rate": 4.389311684685171e-06, + "loss": 0.4631, + "step": 8197 + }, + { + "epoch": 0.7, + "learning_rate": 4.387025933927282e-06, + "loss": 0.4618, + "step": 8198 + }, + { + "epoch": 0.7, + "learning_rate": 4.384740611238223e-06, + "loss": 0.4697, + "step": 8199 + }, + { + "epoch": 0.7, + "learning_rate": 4.382455716792291e-06, + "loss": 0.4635, + "step": 8200 + }, + { + "epoch": 0.7, + "learning_rate": 4.380171250763741e-06, + "loss": 0.4357, + "step": 8201 + }, + { + "epoch": 0.7, + "learning_rate": 4.377887213326791e-06, + "loss": 0.477, + "step": 8202 + }, + { + "epoch": 0.7, + "learning_rate": 4.375603604655634e-06, + "loss": 0.4729, + "step": 8203 + }, + { + "epoch": 0.7, + "learning_rate": 4.373320424924427e-06, + "loss": 0.4476, + "step": 8204 + }, + { + "epoch": 0.7, + "learning_rate": 4.371037674307294e-06, + "loss": 0.4701, + "step": 8205 + }, + { + "epoch": 0.7, + "learning_rate": 4.368755352978329e-06, + "loss": 0.4515, + "step": 8206 + }, + { + "epoch": 0.7, + "learning_rate": 4.366473461111593e-06, + "loss": 0.4954, + "step": 8207 + }, + { + "epoch": 0.7, + "learning_rate": 4.3641919988811045e-06, + "loss": 0.4725, + "step": 8208 + }, + { + "epoch": 0.7, + "learning_rate": 4.361910966460866e-06, + "loss": 0.4487, + "step": 8209 + }, + { + "epoch": 0.7, + "learning_rate": 4.3596303640248394e-06, + "loss": 0.4529, + "step": 8210 + }, + { + "epoch": 0.7, + "learning_rate": 4.357350191746945e-06, + "loss": 0.467, + "step": 8211 + }, + { + "epoch": 0.7, + "learning_rate": 4.355070449801083e-06, + "loss": 0.482, + "step": 8212 + }, + { + "epoch": 0.7, + "learning_rate": 4.352791138361115e-06, + "loss": 0.4477, + "step": 8213 + }, + { + "epoch": 0.7, + "learning_rate": 4.350512257600871e-06, + "loss": 0.4588, + "step": 8214 + }, + { + "epoch": 0.7, + "learning_rate": 4.348233807694147e-06, + "loss": 0.4447, + "step": 8215 + }, + { + "epoch": 0.7, + "learning_rate": 4.345955788814714e-06, + "loss": 0.4786, + "step": 8216 + }, + { + "epoch": 0.7, + "learning_rate": 4.343678201136289e-06, + "loss": 0.4425, + "step": 8217 + }, + { + "epoch": 0.7, + "learning_rate": 4.341401044832583e-06, + "loss": 0.4561, + "step": 8218 + }, + { + "epoch": 0.7, + "learning_rate": 4.33912432007726e-06, + "loss": 0.4446, + "step": 8219 + }, + { + "epoch": 0.7, + "learning_rate": 4.336848027043947e-06, + "loss": 0.4807, + "step": 8220 + }, + { + "epoch": 0.7, + "learning_rate": 4.334572165906247e-06, + "loss": 0.4801, + "step": 8221 + }, + { + "epoch": 0.7, + "learning_rate": 4.332296736837724e-06, + "loss": 0.4309, + "step": 8222 + }, + { + "epoch": 0.7, + "learning_rate": 4.330021740011916e-06, + "loss": 0.4704, + "step": 8223 + }, + { + "epoch": 0.7, + "learning_rate": 4.327747175602321e-06, + "loss": 0.4432, + "step": 8224 + }, + { + "epoch": 0.7, + "learning_rate": 4.32547304378241e-06, + "loss": 0.4727, + "step": 8225 + }, + { + "epoch": 0.7, + "learning_rate": 4.32319934472561e-06, + "loss": 0.4573, + "step": 8226 + }, + { + "epoch": 0.7, + "learning_rate": 4.320926078605328e-06, + "loss": 0.4591, + "step": 8227 + }, + { + "epoch": 0.7, + "learning_rate": 4.318653245594939e-06, + "loss": 0.469, + "step": 8228 + }, + { + "epoch": 0.7, + "learning_rate": 4.316380845867768e-06, + "loss": 0.443, + "step": 8229 + }, + { + "epoch": 0.7, + "learning_rate": 4.314108879597122e-06, + "loss": 0.4671, + "step": 8230 + }, + { + "epoch": 0.7, + "learning_rate": 4.311837346956271e-06, + "loss": 0.4544, + "step": 8231 + }, + { + "epoch": 0.7, + "learning_rate": 4.3095662481184505e-06, + "loss": 0.479, + "step": 8232 + }, + { + "epoch": 0.7, + "learning_rate": 4.307295583256866e-06, + "loss": 0.484, + "step": 8233 + }, + { + "epoch": 0.7, + "learning_rate": 4.3050253525446895e-06, + "loss": 0.4601, + "step": 8234 + }, + { + "epoch": 0.7, + "learning_rate": 4.302755556155048e-06, + "loss": 0.4684, + "step": 8235 + }, + { + "epoch": 0.7, + "learning_rate": 4.3004861942610575e-06, + "loss": 0.4523, + "step": 8236 + }, + { + "epoch": 0.7, + "learning_rate": 4.298217267035788e-06, + "loss": 0.4768, + "step": 8237 + }, + { + "epoch": 0.7, + "learning_rate": 4.2959487746522695e-06, + "loss": 0.4723, + "step": 8238 + }, + { + "epoch": 0.7, + "learning_rate": 4.293680717283512e-06, + "loss": 0.4606, + "step": 8239 + }, + { + "epoch": 0.7, + "learning_rate": 4.291413095102487e-06, + "loss": 0.4485, + "step": 8240 + }, + { + "epoch": 0.7, + "learning_rate": 4.289145908282131e-06, + "loss": 0.47, + "step": 8241 + }, + { + "epoch": 0.7, + "learning_rate": 4.286879156995349e-06, + "loss": 0.4482, + "step": 8242 + }, + { + "epoch": 0.7, + "learning_rate": 4.284612841415019e-06, + "loss": 0.4619, + "step": 8243 + }, + { + "epoch": 0.7, + "learning_rate": 4.282346961713971e-06, + "loss": 0.4641, + "step": 8244 + }, + { + "epoch": 0.7, + "learning_rate": 4.28008151806501e-06, + "loss": 0.4584, + "step": 8245 + }, + { + "epoch": 0.7, + "learning_rate": 4.27781651064092e-06, + "loss": 0.4759, + "step": 8246 + }, + { + "epoch": 0.7, + "learning_rate": 4.275551939614429e-06, + "loss": 0.4589, + "step": 8247 + }, + { + "epoch": 0.7, + "learning_rate": 4.273287805158245e-06, + "loss": 0.4548, + "step": 8248 + }, + { + "epoch": 0.7, + "learning_rate": 4.271024107445042e-06, + "loss": 0.4627, + "step": 8249 + }, + { + "epoch": 0.7, + "learning_rate": 4.268760846647459e-06, + "loss": 0.4656, + "step": 8250 + }, + { + "epoch": 0.7, + "learning_rate": 4.2664980229381e-06, + "loss": 0.4675, + "step": 8251 + }, + { + "epoch": 0.7, + "learning_rate": 4.264235636489542e-06, + "loss": 0.4619, + "step": 8252 + }, + { + "epoch": 0.7, + "learning_rate": 4.261973687474316e-06, + "loss": 0.462, + "step": 8253 + }, + { + "epoch": 0.7, + "learning_rate": 4.25971217606493e-06, + "loss": 0.4604, + "step": 8254 + }, + { + "epoch": 0.7, + "learning_rate": 4.257451102433866e-06, + "loss": 0.452, + "step": 8255 + }, + { + "epoch": 0.7, + "learning_rate": 4.255190466753551e-06, + "loss": 0.4715, + "step": 8256 + }, + { + "epoch": 0.7, + "learning_rate": 4.252930269196395e-06, + "loss": 0.4508, + "step": 8257 + }, + { + "epoch": 0.7, + "learning_rate": 4.25067050993477e-06, + "loss": 0.4451, + "step": 8258 + }, + { + "epoch": 0.7, + "learning_rate": 4.248411189141014e-06, + "loss": 0.4613, + "step": 8259 + }, + { + "epoch": 0.7, + "learning_rate": 4.246152306987434e-06, + "loss": 0.4637, + "step": 8260 + }, + { + "epoch": 0.7, + "learning_rate": 4.2438938636463035e-06, + "loss": 0.4555, + "step": 8261 + }, + { + "epoch": 0.7, + "learning_rate": 4.241635859289855e-06, + "loss": 0.4774, + "step": 8262 + }, + { + "epoch": 0.7, + "learning_rate": 4.239378294090292e-06, + "loss": 0.4609, + "step": 8263 + }, + { + "epoch": 0.7, + "learning_rate": 4.237121168219798e-06, + "loss": 0.4683, + "step": 8264 + }, + { + "epoch": 0.7, + "learning_rate": 4.234864481850499e-06, + "loss": 0.4613, + "step": 8265 + }, + { + "epoch": 0.7, + "learning_rate": 4.2326082351545025e-06, + "loss": 0.4716, + "step": 8266 + }, + { + "epoch": 0.7, + "learning_rate": 4.230352428303886e-06, + "loss": 0.4519, + "step": 8267 + }, + { + "epoch": 0.7, + "learning_rate": 4.228097061470672e-06, + "loss": 0.4408, + "step": 8268 + }, + { + "epoch": 0.71, + "learning_rate": 4.225842134826876e-06, + "loss": 0.4757, + "step": 8269 + }, + { + "epoch": 0.71, + "learning_rate": 4.223587648544471e-06, + "loss": 0.4578, + "step": 8270 + }, + { + "epoch": 0.71, + "learning_rate": 4.221333602795382e-06, + "loss": 0.4442, + "step": 8271 + }, + { + "epoch": 0.71, + "learning_rate": 4.219079997751515e-06, + "loss": 0.4486, + "step": 8272 + }, + { + "epoch": 0.71, + "learning_rate": 4.216826833584749e-06, + "loss": 0.4764, + "step": 8273 + }, + { + "epoch": 0.71, + "learning_rate": 4.214574110466909e-06, + "loss": 0.4755, + "step": 8274 + }, + { + "epoch": 0.71, + "learning_rate": 4.212321828569801e-06, + "loss": 0.4643, + "step": 8275 + }, + { + "epoch": 0.71, + "learning_rate": 4.210069988065197e-06, + "loss": 0.4737, + "step": 8276 + }, + { + "epoch": 0.71, + "learning_rate": 4.207818589124821e-06, + "loss": 0.4458, + "step": 8277 + }, + { + "epoch": 0.71, + "learning_rate": 4.2055676319203835e-06, + "loss": 0.4476, + "step": 8278 + }, + { + "epoch": 0.71, + "learning_rate": 4.203317116623553e-06, + "loss": 0.4696, + "step": 8279 + }, + { + "epoch": 0.71, + "learning_rate": 4.201067043405956e-06, + "loss": 0.4757, + "step": 8280 + }, + { + "epoch": 0.71, + "learning_rate": 4.198817412439194e-06, + "loss": 0.4597, + "step": 8281 + }, + { + "epoch": 0.71, + "learning_rate": 4.196568223894841e-06, + "loss": 0.4493, + "step": 8282 + }, + { + "epoch": 0.71, + "learning_rate": 4.1943194779444215e-06, + "loss": 0.471, + "step": 8283 + }, + { + "epoch": 0.71, + "learning_rate": 4.192071174759435e-06, + "loss": 0.4721, + "step": 8284 + }, + { + "epoch": 0.71, + "learning_rate": 4.1898233145113535e-06, + "loss": 0.4967, + "step": 8285 + }, + { + "epoch": 0.71, + "learning_rate": 4.1875758973715955e-06, + "loss": 0.4438, + "step": 8286 + }, + { + "epoch": 0.71, + "learning_rate": 4.185328923511568e-06, + "loss": 0.4577, + "step": 8287 + }, + { + "epoch": 0.71, + "learning_rate": 4.1830823931026365e-06, + "loss": 0.4686, + "step": 8288 + }, + { + "epoch": 0.71, + "learning_rate": 4.180836306316123e-06, + "loss": 0.4635, + "step": 8289 + }, + { + "epoch": 0.71, + "learning_rate": 4.178590663323323e-06, + "loss": 0.4602, + "step": 8290 + }, + { + "epoch": 0.71, + "learning_rate": 4.17634546429551e-06, + "loss": 0.4607, + "step": 8291 + }, + { + "epoch": 0.71, + "learning_rate": 4.174100709403902e-06, + "loss": 0.4646, + "step": 8292 + }, + { + "epoch": 0.71, + "learning_rate": 4.171856398819696e-06, + "loss": 0.4559, + "step": 8293 + }, + { + "epoch": 0.71, + "learning_rate": 4.169612532714052e-06, + "loss": 0.461, + "step": 8294 + }, + { + "epoch": 0.71, + "learning_rate": 4.167369111258098e-06, + "loss": 0.4686, + "step": 8295 + }, + { + "epoch": 0.71, + "learning_rate": 4.165126134622927e-06, + "loss": 0.468, + "step": 8296 + }, + { + "epoch": 0.71, + "learning_rate": 4.1628836029795995e-06, + "loss": 0.4625, + "step": 8297 + }, + { + "epoch": 0.71, + "learning_rate": 4.160641516499134e-06, + "loss": 0.4572, + "step": 8298 + }, + { + "epoch": 0.71, + "learning_rate": 4.158399875352525e-06, + "loss": 0.4628, + "step": 8299 + }, + { + "epoch": 0.71, + "learning_rate": 4.15615867971073e-06, + "loss": 0.4464, + "step": 8300 + }, + { + "epoch": 0.71, + "learning_rate": 4.153917929744671e-06, + "loss": 0.4625, + "step": 8301 + }, + { + "epoch": 0.71, + "learning_rate": 4.151677625625237e-06, + "loss": 0.4759, + "step": 8302 + }, + { + "epoch": 0.71, + "learning_rate": 4.149437767523284e-06, + "loss": 0.4625, + "step": 8303 + }, + { + "epoch": 0.71, + "learning_rate": 4.1471983556096316e-06, + "loss": 0.4569, + "step": 8304 + }, + { + "epoch": 0.71, + "learning_rate": 4.1449593900550686e-06, + "loss": 0.4452, + "step": 8305 + }, + { + "epoch": 0.71, + "learning_rate": 4.142720871030349e-06, + "loss": 0.4733, + "step": 8306 + }, + { + "epoch": 0.71, + "learning_rate": 4.140482798706186e-06, + "loss": 0.4471, + "step": 8307 + }, + { + "epoch": 0.71, + "learning_rate": 4.138245173253267e-06, + "loss": 0.4656, + "step": 8308 + }, + { + "epoch": 0.71, + "learning_rate": 4.136007994842244e-06, + "loss": 0.459, + "step": 8309 + }, + { + "epoch": 0.71, + "learning_rate": 4.133771263643732e-06, + "loss": 0.4702, + "step": 8310 + }, + { + "epoch": 0.71, + "learning_rate": 4.1315349798283145e-06, + "loss": 0.468, + "step": 8311 + }, + { + "epoch": 0.71, + "learning_rate": 4.129299143566538e-06, + "loss": 0.4627, + "step": 8312 + }, + { + "epoch": 0.71, + "learning_rate": 4.127063755028921e-06, + "loss": 0.456, + "step": 8313 + }, + { + "epoch": 0.71, + "learning_rate": 4.124828814385939e-06, + "loss": 0.4722, + "step": 8314 + }, + { + "epoch": 0.71, + "learning_rate": 4.122594321808044e-06, + "loss": 0.4567, + "step": 8315 + }, + { + "epoch": 0.71, + "learning_rate": 4.1203602774656405e-06, + "loss": 0.4587, + "step": 8316 + }, + { + "epoch": 0.71, + "learning_rate": 4.118126681529108e-06, + "loss": 0.4616, + "step": 8317 + }, + { + "epoch": 0.71, + "learning_rate": 4.115893534168791e-06, + "loss": 0.4709, + "step": 8318 + }, + { + "epoch": 0.71, + "learning_rate": 4.113660835554998e-06, + "loss": 0.4676, + "step": 8319 + }, + { + "epoch": 0.71, + "learning_rate": 4.111428585858005e-06, + "loss": 0.4577, + "step": 8320 + }, + { + "epoch": 0.71, + "learning_rate": 4.109196785248052e-06, + "loss": 0.4632, + "step": 8321 + }, + { + "epoch": 0.71, + "learning_rate": 4.106965433895349e-06, + "loss": 0.4804, + "step": 8322 + }, + { + "epoch": 0.71, + "learning_rate": 4.104734531970058e-06, + "loss": 0.4549, + "step": 8323 + }, + { + "epoch": 0.71, + "learning_rate": 4.10250407964233e-06, + "loss": 0.4712, + "step": 8324 + }, + { + "epoch": 0.71, + "learning_rate": 4.100274077082259e-06, + "loss": 0.4649, + "step": 8325 + }, + { + "epoch": 0.71, + "learning_rate": 4.0980445244599174e-06, + "loss": 0.4892, + "step": 8326 + }, + { + "epoch": 0.71, + "learning_rate": 4.09581542194534e-06, + "loss": 0.4664, + "step": 8327 + }, + { + "epoch": 0.71, + "learning_rate": 4.0935867697085285e-06, + "loss": 0.4757, + "step": 8328 + }, + { + "epoch": 0.71, + "learning_rate": 4.091358567919449e-06, + "loss": 0.4825, + "step": 8329 + }, + { + "epoch": 0.71, + "learning_rate": 4.089130816748031e-06, + "loss": 0.4659, + "step": 8330 + }, + { + "epoch": 0.71, + "learning_rate": 4.086903516364179e-06, + "loss": 0.4628, + "step": 8331 + }, + { + "epoch": 0.71, + "learning_rate": 4.084676666937745e-06, + "loss": 0.4713, + "step": 8332 + }, + { + "epoch": 0.71, + "learning_rate": 4.0824502686385696e-06, + "loss": 0.4427, + "step": 8333 + }, + { + "epoch": 0.71, + "learning_rate": 4.080224321636438e-06, + "loss": 0.4829, + "step": 8334 + }, + { + "epoch": 0.71, + "learning_rate": 4.077998826101115e-06, + "loss": 0.4551, + "step": 8335 + }, + { + "epoch": 0.71, + "learning_rate": 4.075773782202325e-06, + "loss": 0.4902, + "step": 8336 + }, + { + "epoch": 0.71, + "learning_rate": 4.073549190109759e-06, + "loss": 0.4636, + "step": 8337 + }, + { + "epoch": 0.71, + "learning_rate": 4.071325049993073e-06, + "loss": 0.457, + "step": 8338 + }, + { + "epoch": 0.71, + "learning_rate": 4.069101362021893e-06, + "loss": 0.4552, + "step": 8339 + }, + { + "epoch": 0.71, + "learning_rate": 4.066878126365804e-06, + "loss": 0.4619, + "step": 8340 + }, + { + "epoch": 0.71, + "learning_rate": 4.064655343194354e-06, + "loss": 0.4779, + "step": 8341 + }, + { + "epoch": 0.71, + "learning_rate": 4.062433012677074e-06, + "loss": 0.4646, + "step": 8342 + }, + { + "epoch": 0.71, + "learning_rate": 4.060211134983437e-06, + "loss": 0.4816, + "step": 8343 + }, + { + "epoch": 0.71, + "learning_rate": 4.057989710282897e-06, + "loss": 0.4757, + "step": 8344 + }, + { + "epoch": 0.71, + "learning_rate": 4.055768738744868e-06, + "loss": 0.4668, + "step": 8345 + }, + { + "epoch": 0.71, + "learning_rate": 4.053548220538732e-06, + "loss": 0.4774, + "step": 8346 + }, + { + "epoch": 0.71, + "learning_rate": 4.051328155833835e-06, + "loss": 0.4591, + "step": 8347 + }, + { + "epoch": 0.71, + "learning_rate": 4.049108544799487e-06, + "loss": 0.4415, + "step": 8348 + }, + { + "epoch": 0.71, + "learning_rate": 4.046889387604969e-06, + "loss": 0.4706, + "step": 8349 + }, + { + "epoch": 0.71, + "learning_rate": 4.044670684419513e-06, + "loss": 0.4648, + "step": 8350 + }, + { + "epoch": 0.71, + "learning_rate": 4.0424524354123375e-06, + "loss": 0.4628, + "step": 8351 + }, + { + "epoch": 0.71, + "learning_rate": 4.0402346407526135e-06, + "loss": 0.4473, + "step": 8352 + }, + { + "epoch": 0.71, + "learning_rate": 4.038017300609475e-06, + "loss": 0.4594, + "step": 8353 + }, + { + "epoch": 0.71, + "learning_rate": 4.035800415152027e-06, + "loss": 0.4624, + "step": 8354 + }, + { + "epoch": 0.71, + "learning_rate": 4.033583984549338e-06, + "loss": 0.445, + "step": 8355 + }, + { + "epoch": 0.71, + "learning_rate": 4.031368008970446e-06, + "loss": 0.4601, + "step": 8356 + }, + { + "epoch": 0.71, + "learning_rate": 4.029152488584346e-06, + "loss": 0.4663, + "step": 8357 + }, + { + "epoch": 0.71, + "learning_rate": 4.026937423560008e-06, + "loss": 0.4652, + "step": 8358 + }, + { + "epoch": 0.71, + "learning_rate": 4.024722814066353e-06, + "loss": 0.4519, + "step": 8359 + }, + { + "epoch": 0.71, + "learning_rate": 4.022508660272285e-06, + "loss": 0.4469, + "step": 8360 + }, + { + "epoch": 0.71, + "learning_rate": 4.020294962346666e-06, + "loss": 0.4816, + "step": 8361 + }, + { + "epoch": 0.71, + "learning_rate": 4.018081720458314e-06, + "loss": 0.4473, + "step": 8362 + }, + { + "epoch": 0.71, + "learning_rate": 4.015868934776023e-06, + "loss": 0.4895, + "step": 8363 + }, + { + "epoch": 0.71, + "learning_rate": 4.013656605468551e-06, + "loss": 0.467, + "step": 8364 + }, + { + "epoch": 0.71, + "learning_rate": 4.011444732704618e-06, + "loss": 0.4525, + "step": 8365 + }, + { + "epoch": 0.71, + "learning_rate": 4.009233316652911e-06, + "loss": 0.4818, + "step": 8366 + }, + { + "epoch": 0.71, + "learning_rate": 4.007022357482086e-06, + "loss": 0.4642, + "step": 8367 + }, + { + "epoch": 0.71, + "learning_rate": 4.0048118553607485e-06, + "loss": 0.4413, + "step": 8368 + }, + { + "epoch": 0.71, + "learning_rate": 4.002601810457492e-06, + "loss": 0.4669, + "step": 8369 + }, + { + "epoch": 0.71, + "learning_rate": 4.000392222940863e-06, + "loss": 0.4704, + "step": 8370 + }, + { + "epoch": 0.71, + "learning_rate": 3.998183092979368e-06, + "loss": 0.4707, + "step": 8371 + }, + { + "epoch": 0.71, + "learning_rate": 3.995974420741485e-06, + "loss": 0.4503, + "step": 8372 + }, + { + "epoch": 0.71, + "learning_rate": 3.99376620639566e-06, + "loss": 0.4791, + "step": 8373 + }, + { + "epoch": 0.71, + "learning_rate": 3.9915584501103e-06, + "loss": 0.4555, + "step": 8374 + }, + { + "epoch": 0.71, + "learning_rate": 3.9893511520537766e-06, + "loss": 0.4623, + "step": 8375 + }, + { + "epoch": 0.71, + "learning_rate": 3.987144312394432e-06, + "loss": 0.4503, + "step": 8376 + }, + { + "epoch": 0.71, + "learning_rate": 3.9849379313005605e-06, + "loss": 0.4463, + "step": 8377 + }, + { + "epoch": 0.71, + "learning_rate": 3.982732008940432e-06, + "loss": 0.466, + "step": 8378 + }, + { + "epoch": 0.71, + "learning_rate": 3.980526545482288e-06, + "loss": 0.4701, + "step": 8379 + }, + { + "epoch": 0.71, + "learning_rate": 3.978321541094318e-06, + "loss": 0.4727, + "step": 8380 + }, + { + "epoch": 0.71, + "learning_rate": 3.9761169959446855e-06, + "loss": 0.458, + "step": 8381 + }, + { + "epoch": 0.71, + "learning_rate": 3.973912910201521e-06, + "loss": 0.447, + "step": 8382 + }, + { + "epoch": 0.71, + "learning_rate": 3.9717092840329155e-06, + "loss": 0.4711, + "step": 8383 + }, + { + "epoch": 0.71, + "learning_rate": 3.969506117606927e-06, + "loss": 0.4494, + "step": 8384 + }, + { + "epoch": 0.71, + "learning_rate": 3.967303411091582e-06, + "loss": 0.4513, + "step": 8385 + }, + { + "epoch": 0.72, + "learning_rate": 3.965101164654862e-06, + "loss": 0.4885, + "step": 8386 + }, + { + "epoch": 0.72, + "learning_rate": 3.9628993784647186e-06, + "loss": 0.4463, + "step": 8387 + }, + { + "epoch": 0.72, + "learning_rate": 3.960698052689079e-06, + "loss": 0.4665, + "step": 8388 + }, + { + "epoch": 0.72, + "learning_rate": 3.958497187495815e-06, + "loss": 0.4819, + "step": 8389 + }, + { + "epoch": 0.72, + "learning_rate": 3.95629678305278e-06, + "loss": 0.4493, + "step": 8390 + }, + { + "epoch": 0.72, + "learning_rate": 3.954096839527784e-06, + "loss": 0.4862, + "step": 8391 + }, + { + "epoch": 0.72, + "learning_rate": 3.951897357088602e-06, + "loss": 0.4705, + "step": 8392 + }, + { + "epoch": 0.72, + "learning_rate": 3.9496983359029795e-06, + "loss": 0.4689, + "step": 8393 + }, + { + "epoch": 0.72, + "learning_rate": 3.947499776138624e-06, + "loss": 0.4579, + "step": 8394 + }, + { + "epoch": 0.72, + "learning_rate": 3.9453016779631995e-06, + "loss": 0.4646, + "step": 8395 + }, + { + "epoch": 0.72, + "learning_rate": 3.943104041544344e-06, + "loss": 0.4612, + "step": 8396 + }, + { + "epoch": 0.72, + "learning_rate": 3.940906867049668e-06, + "loss": 0.4738, + "step": 8397 + }, + { + "epoch": 0.72, + "learning_rate": 3.938710154646727e-06, + "loss": 0.4753, + "step": 8398 + }, + { + "epoch": 0.72, + "learning_rate": 3.9365139045030545e-06, + "loss": 0.4556, + "step": 8399 + }, + { + "epoch": 0.72, + "learning_rate": 3.934318116786149e-06, + "loss": 0.4746, + "step": 8400 + }, + { + "epoch": 0.72, + "learning_rate": 3.932122791663461e-06, + "loss": 0.4565, + "step": 8401 + }, + { + "epoch": 0.72, + "learning_rate": 3.929927929302425e-06, + "loss": 0.4575, + "step": 8402 + }, + { + "epoch": 0.72, + "learning_rate": 3.92773352987043e-06, + "loss": 0.4751, + "step": 8403 + }, + { + "epoch": 0.72, + "learning_rate": 3.925539593534824e-06, + "loss": 0.4472, + "step": 8404 + }, + { + "epoch": 0.72, + "learning_rate": 3.923346120462925e-06, + "loss": 0.4448, + "step": 8405 + }, + { + "epoch": 0.72, + "learning_rate": 3.921153110822027e-06, + "loss": 0.4315, + "step": 8406 + }, + { + "epoch": 0.72, + "learning_rate": 3.918960564779368e-06, + "loss": 0.4484, + "step": 8407 + }, + { + "epoch": 0.72, + "learning_rate": 3.916768482502164e-06, + "loss": 0.4536, + "step": 8408 + }, + { + "epoch": 0.72, + "learning_rate": 3.914576864157594e-06, + "loss": 0.4606, + "step": 8409 + }, + { + "epoch": 0.72, + "learning_rate": 3.912385709912794e-06, + "loss": 0.4524, + "step": 8410 + }, + { + "epoch": 0.72, + "learning_rate": 3.910195019934876e-06, + "loss": 0.4387, + "step": 8411 + }, + { + "epoch": 0.72, + "learning_rate": 3.908004794390915e-06, + "loss": 0.4759, + "step": 8412 + }, + { + "epoch": 0.72, + "learning_rate": 3.905815033447937e-06, + "loss": 0.4725, + "step": 8413 + }, + { + "epoch": 0.72, + "learning_rate": 3.903625737272944e-06, + "loss": 0.4551, + "step": 8414 + }, + { + "epoch": 0.72, + "learning_rate": 3.901436906032912e-06, + "loss": 0.4651, + "step": 8415 + }, + { + "epoch": 0.72, + "learning_rate": 3.899248539894756e-06, + "loss": 0.4667, + "step": 8416 + }, + { + "epoch": 0.72, + "learning_rate": 3.897060639025378e-06, + "loss": 0.4415, + "step": 8417 + }, + { + "epoch": 0.72, + "learning_rate": 3.894873203591639e-06, + "loss": 0.4789, + "step": 8418 + }, + { + "epoch": 0.72, + "learning_rate": 3.89268623376035e-06, + "loss": 0.4933, + "step": 8419 + }, + { + "epoch": 0.72, + "learning_rate": 3.89049972969831e-06, + "loss": 0.4612, + "step": 8420 + }, + { + "epoch": 0.72, + "learning_rate": 3.8883136915722685e-06, + "loss": 0.4432, + "step": 8421 + }, + { + "epoch": 0.72, + "learning_rate": 3.886128119548938e-06, + "loss": 0.4762, + "step": 8422 + }, + { + "epoch": 0.72, + "learning_rate": 3.883943013795e-06, + "loss": 0.4733, + "step": 8423 + }, + { + "epoch": 0.72, + "learning_rate": 3.8817583744771055e-06, + "loss": 0.4481, + "step": 8424 + }, + { + "epoch": 0.72, + "learning_rate": 3.879574201761859e-06, + "loss": 0.4835, + "step": 8425 + }, + { + "epoch": 0.72, + "learning_rate": 3.8773904958158345e-06, + "loss": 0.4849, + "step": 8426 + }, + { + "epoch": 0.72, + "learning_rate": 3.8752072568055764e-06, + "loss": 0.4541, + "step": 8427 + }, + { + "epoch": 0.72, + "learning_rate": 3.8730244848975766e-06, + "loss": 0.4439, + "step": 8428 + }, + { + "epoch": 0.72, + "learning_rate": 3.8708421802583116e-06, + "loss": 0.4501, + "step": 8429 + }, + { + "epoch": 0.72, + "learning_rate": 3.868660343054213e-06, + "loss": 0.4497, + "step": 8430 + }, + { + "epoch": 0.72, + "learning_rate": 3.866478973451673e-06, + "loss": 0.4718, + "step": 8431 + }, + { + "epoch": 0.72, + "learning_rate": 3.864298071617051e-06, + "loss": 0.4799, + "step": 8432 + }, + { + "epoch": 0.72, + "learning_rate": 3.862117637716675e-06, + "loss": 0.448, + "step": 8433 + }, + { + "epoch": 0.72, + "learning_rate": 3.859937671916833e-06, + "loss": 0.4655, + "step": 8434 + }, + { + "epoch": 0.72, + "learning_rate": 3.857758174383777e-06, + "loss": 0.4832, + "step": 8435 + }, + { + "epoch": 0.72, + "learning_rate": 3.85557914528373e-06, + "loss": 0.476, + "step": 8436 + }, + { + "epoch": 0.72, + "learning_rate": 3.853400584782862e-06, + "loss": 0.4486, + "step": 8437 + }, + { + "epoch": 0.72, + "learning_rate": 3.851222493047331e-06, + "loss": 0.4583, + "step": 8438 + }, + { + "epoch": 0.72, + "learning_rate": 3.849044870243246e-06, + "loss": 0.4501, + "step": 8439 + }, + { + "epoch": 0.72, + "learning_rate": 3.846867716536676e-06, + "loss": 0.4596, + "step": 8440 + }, + { + "epoch": 0.72, + "learning_rate": 3.844691032093662e-06, + "loss": 0.45, + "step": 8441 + }, + { + "epoch": 0.72, + "learning_rate": 3.842514817080206e-06, + "loss": 0.4652, + "step": 8442 + }, + { + "epoch": 0.72, + "learning_rate": 3.840339071662279e-06, + "loss": 0.4446, + "step": 8443 + }, + { + "epoch": 0.72, + "learning_rate": 3.838163796005809e-06, + "loss": 0.4673, + "step": 8444 + }, + { + "epoch": 0.72, + "learning_rate": 3.835988990276696e-06, + "loss": 0.4593, + "step": 8445 + }, + { + "epoch": 0.72, + "learning_rate": 3.83381465464079e-06, + "loss": 0.4701, + "step": 8446 + }, + { + "epoch": 0.72, + "learning_rate": 3.8316407892639265e-06, + "loss": 0.4671, + "step": 8447 + }, + { + "epoch": 0.72, + "learning_rate": 3.82946739431189e-06, + "loss": 0.4653, + "step": 8448 + }, + { + "epoch": 0.72, + "learning_rate": 3.8272944699504285e-06, + "loss": 0.4563, + "step": 8449 + }, + { + "epoch": 0.72, + "learning_rate": 3.825122016345261e-06, + "loss": 0.4512, + "step": 8450 + }, + { + "epoch": 0.72, + "learning_rate": 3.822950033662068e-06, + "loss": 0.4632, + "step": 8451 + }, + { + "epoch": 0.72, + "learning_rate": 3.8207785220664935e-06, + "loss": 0.4486, + "step": 8452 + }, + { + "epoch": 0.72, + "learning_rate": 3.818607481724147e-06, + "loss": 0.4607, + "step": 8453 + }, + { + "epoch": 0.72, + "learning_rate": 3.816436912800603e-06, + "loss": 0.4636, + "step": 8454 + }, + { + "epoch": 0.72, + "learning_rate": 3.8142668154613925e-06, + "loss": 0.4596, + "step": 8455 + }, + { + "epoch": 0.72, + "learning_rate": 3.812097189872016e-06, + "loss": 0.4554, + "step": 8456 + }, + { + "epoch": 0.72, + "learning_rate": 3.8099280361979484e-06, + "loss": 0.4619, + "step": 8457 + }, + { + "epoch": 0.72, + "learning_rate": 3.8077593546046087e-06, + "loss": 0.4573, + "step": 8458 + }, + { + "epoch": 0.72, + "learning_rate": 3.8055911452573913e-06, + "loss": 0.4287, + "step": 8459 + }, + { + "epoch": 0.72, + "learning_rate": 3.803423408321655e-06, + "loss": 0.4613, + "step": 8460 + }, + { + "epoch": 0.72, + "learning_rate": 3.801256143962719e-06, + "loss": 0.4817, + "step": 8461 + }, + { + "epoch": 0.72, + "learning_rate": 3.7990893523458682e-06, + "loss": 0.4501, + "step": 8462 + }, + { + "epoch": 0.72, + "learning_rate": 3.796923033636356e-06, + "loss": 0.4502, + "step": 8463 + }, + { + "epoch": 0.72, + "learning_rate": 3.794757187999386e-06, + "loss": 0.4691, + "step": 8464 + }, + { + "epoch": 0.72, + "learning_rate": 3.792591815600135e-06, + "loss": 0.4806, + "step": 8465 + }, + { + "epoch": 0.72, + "learning_rate": 3.7904269166037553e-06, + "loss": 0.4361, + "step": 8466 + }, + { + "epoch": 0.72, + "learning_rate": 3.7882624911753386e-06, + "loss": 0.4667, + "step": 8467 + }, + { + "epoch": 0.72, + "learning_rate": 3.786098539479959e-06, + "loss": 0.4574, + "step": 8468 + }, + { + "epoch": 0.72, + "learning_rate": 3.7839350616826454e-06, + "loss": 0.4634, + "step": 8469 + }, + { + "epoch": 0.72, + "learning_rate": 3.7817720579483962e-06, + "loss": 0.4614, + "step": 8470 + }, + { + "epoch": 0.72, + "learning_rate": 3.77960952844217e-06, + "loss": 0.4749, + "step": 8471 + }, + { + "epoch": 0.72, + "learning_rate": 3.7774474733288904e-06, + "loss": 0.4883, + "step": 8472 + }, + { + "epoch": 0.72, + "learning_rate": 3.7752858927734492e-06, + "loss": 0.4655, + "step": 8473 + }, + { + "epoch": 0.72, + "learning_rate": 3.773124786940685e-06, + "loss": 0.474, + "step": 8474 + }, + { + "epoch": 0.72, + "learning_rate": 3.770964155995428e-06, + "loss": 0.4605, + "step": 8475 + }, + { + "epoch": 0.72, + "learning_rate": 3.7688040001024473e-06, + "loss": 0.4522, + "step": 8476 + }, + { + "epoch": 0.72, + "learning_rate": 3.766644319426488e-06, + "loss": 0.445, + "step": 8477 + }, + { + "epoch": 0.72, + "learning_rate": 3.764485114132256e-06, + "loss": 0.4799, + "step": 8478 + }, + { + "epoch": 0.72, + "learning_rate": 3.7623263843844216e-06, + "loss": 0.461, + "step": 8479 + }, + { + "epoch": 0.72, + "learning_rate": 3.760168130347619e-06, + "loss": 0.4788, + "step": 8480 + }, + { + "epoch": 0.72, + "learning_rate": 3.7580103521864444e-06, + "loss": 0.4642, + "step": 8481 + }, + { + "epoch": 0.72, + "learning_rate": 3.7558530500654643e-06, + "loss": 0.4548, + "step": 8482 + }, + { + "epoch": 0.72, + "learning_rate": 3.7536962241491913e-06, + "loss": 0.4469, + "step": 8483 + }, + { + "epoch": 0.72, + "learning_rate": 3.751539874602129e-06, + "loss": 0.4592, + "step": 8484 + }, + { + "epoch": 0.72, + "learning_rate": 3.7493840015887196e-06, + "loss": 0.4599, + "step": 8485 + }, + { + "epoch": 0.72, + "learning_rate": 3.747228605273381e-06, + "loss": 0.452, + "step": 8486 + }, + { + "epoch": 0.72, + "learning_rate": 3.745073685820494e-06, + "loss": 0.478, + "step": 8487 + }, + { + "epoch": 0.72, + "learning_rate": 3.7429192433944016e-06, + "loss": 0.4648, + "step": 8488 + }, + { + "epoch": 0.72, + "learning_rate": 3.7407652781594094e-06, + "loss": 0.4532, + "step": 8489 + }, + { + "epoch": 0.72, + "learning_rate": 3.7386117902797892e-06, + "loss": 0.4692, + "step": 8490 + }, + { + "epoch": 0.72, + "learning_rate": 3.736458779919777e-06, + "loss": 0.4503, + "step": 8491 + }, + { + "epoch": 0.72, + "learning_rate": 3.734306247243562e-06, + "loss": 0.4537, + "step": 8492 + }, + { + "epoch": 0.72, + "learning_rate": 3.732154192415317e-06, + "loss": 0.4524, + "step": 8493 + }, + { + "epoch": 0.72, + "learning_rate": 3.7300026155991574e-06, + "loss": 0.4773, + "step": 8494 + }, + { + "epoch": 0.72, + "learning_rate": 3.7278515169591757e-06, + "loss": 0.4469, + "step": 8495 + }, + { + "epoch": 0.72, + "learning_rate": 3.725700896659422e-06, + "loss": 0.4772, + "step": 8496 + }, + { + "epoch": 0.72, + "learning_rate": 3.7235507548639127e-06, + "loss": 0.4719, + "step": 8497 + }, + { + "epoch": 0.72, + "learning_rate": 3.721401091736626e-06, + "loss": 0.4762, + "step": 8498 + }, + { + "epoch": 0.72, + "learning_rate": 3.7192519074415035e-06, + "loss": 0.4598, + "step": 8499 + }, + { + "epoch": 0.72, + "learning_rate": 3.717103202142457e-06, + "loss": 0.45, + "step": 8500 + }, + { + "epoch": 0.72, + "learning_rate": 3.714954976003342e-06, + "loss": 0.456, + "step": 8501 + }, + { + "epoch": 0.72, + "learning_rate": 3.712807229188008e-06, + "loss": 0.4442, + "step": 8502 + }, + { + "epoch": 0.73, + "learning_rate": 3.710659961860239e-06, + "loss": 0.466, + "step": 8503 + }, + { + "epoch": 0.73, + "learning_rate": 3.708513174183799e-06, + "loss": 0.4452, + "step": 8504 + }, + { + "epoch": 0.73, + "learning_rate": 3.7063668663224096e-06, + "loss": 0.4398, + "step": 8505 + }, + { + "epoch": 0.73, + "learning_rate": 3.704221038439759e-06, + "loss": 0.4685, + "step": 8506 + }, + { + "epoch": 0.73, + "learning_rate": 3.702075690699496e-06, + "loss": 0.4496, + "step": 8507 + }, + { + "epoch": 0.73, + "learning_rate": 3.699930823265233e-06, + "loss": 0.4598, + "step": 8508 + }, + { + "epoch": 0.73, + "learning_rate": 3.697786436300552e-06, + "loss": 0.4676, + "step": 8509 + }, + { + "epoch": 0.73, + "learning_rate": 3.6956425299689848e-06, + "loss": 0.4992, + "step": 8510 + }, + { + "epoch": 0.73, + "learning_rate": 3.6934991044340375e-06, + "loss": 0.4589, + "step": 8511 + }, + { + "epoch": 0.73, + "learning_rate": 3.6913561598591775e-06, + "loss": 0.4742, + "step": 8512 + }, + { + "epoch": 0.73, + "learning_rate": 3.689213696407834e-06, + "loss": 0.4788, + "step": 8513 + }, + { + "epoch": 0.73, + "learning_rate": 3.687071714243402e-06, + "loss": 0.4493, + "step": 8514 + }, + { + "epoch": 0.73, + "learning_rate": 3.6849302135292354e-06, + "loss": 0.4863, + "step": 8515 + }, + { + "epoch": 0.73, + "learning_rate": 3.6827891944286564e-06, + "loss": 0.4543, + "step": 8516 + }, + { + "epoch": 0.73, + "learning_rate": 3.680648657104946e-06, + "loss": 0.4791, + "step": 8517 + }, + { + "epoch": 0.73, + "learning_rate": 3.6785086017213555e-06, + "loss": 0.4495, + "step": 8518 + }, + { + "epoch": 0.73, + "learning_rate": 3.676369028441088e-06, + "loss": 0.4689, + "step": 8519 + }, + { + "epoch": 0.73, + "learning_rate": 3.674229937427317e-06, + "loss": 0.4696, + "step": 8520 + }, + { + "epoch": 0.73, + "learning_rate": 3.6720913288431813e-06, + "loss": 0.4558, + "step": 8521 + }, + { + "epoch": 0.73, + "learning_rate": 3.669953202851779e-06, + "loss": 0.4612, + "step": 8522 + }, + { + "epoch": 0.73, + "learning_rate": 3.6678155596161725e-06, + "loss": 0.469, + "step": 8523 + }, + { + "epoch": 0.73, + "learning_rate": 3.6656783992993885e-06, + "loss": 0.4486, + "step": 8524 + }, + { + "epoch": 0.73, + "learning_rate": 3.663541722064413e-06, + "loss": 0.4529, + "step": 8525 + }, + { + "epoch": 0.73, + "learning_rate": 3.6614055280742013e-06, + "loss": 0.467, + "step": 8526 + }, + { + "epoch": 0.73, + "learning_rate": 3.6592698174916687e-06, + "loss": 0.4655, + "step": 8527 + }, + { + "epoch": 0.73, + "learning_rate": 3.6571345904796896e-06, + "loss": 0.4464, + "step": 8528 + }, + { + "epoch": 0.73, + "learning_rate": 3.6549998472011027e-06, + "loss": 0.462, + "step": 8529 + }, + { + "epoch": 0.73, + "learning_rate": 3.6528655878187247e-06, + "loss": 0.4643, + "step": 8530 + }, + { + "epoch": 0.73, + "learning_rate": 3.6507318124953117e-06, + "loss": 0.4445, + "step": 8531 + }, + { + "epoch": 0.73, + "learning_rate": 3.648598521393598e-06, + "loss": 0.4493, + "step": 8532 + }, + { + "epoch": 0.73, + "learning_rate": 3.6464657146762805e-06, + "loss": 0.4809, + "step": 8533 + }, + { + "epoch": 0.73, + "learning_rate": 3.6443333925060065e-06, + "loss": 0.4414, + "step": 8534 + }, + { + "epoch": 0.73, + "learning_rate": 3.6422015550454046e-06, + "loss": 0.4437, + "step": 8535 + }, + { + "epoch": 0.73, + "learning_rate": 3.64007020245706e-06, + "loss": 0.473, + "step": 8536 + }, + { + "epoch": 0.73, + "learning_rate": 3.63793933490351e-06, + "loss": 0.4452, + "step": 8537 + }, + { + "epoch": 0.73, + "learning_rate": 3.6358089525472628e-06, + "loss": 0.4611, + "step": 8538 + }, + { + "epoch": 0.73, + "learning_rate": 3.6336790555508018e-06, + "loss": 0.4569, + "step": 8539 + }, + { + "epoch": 0.73, + "learning_rate": 3.631549644076552e-06, + "loss": 0.4523, + "step": 8540 + }, + { + "epoch": 0.73, + "learning_rate": 3.6294207182869124e-06, + "loss": 0.4494, + "step": 8541 + }, + { + "epoch": 0.73, + "learning_rate": 3.62729227834425e-06, + "loss": 0.4539, + "step": 8542 + }, + { + "epoch": 0.73, + "learning_rate": 3.625164324410876e-06, + "loss": 0.4922, + "step": 8543 + }, + { + "epoch": 0.73, + "learning_rate": 3.6230368566490883e-06, + "loss": 0.4539, + "step": 8544 + }, + { + "epoch": 0.73, + "learning_rate": 3.6209098752211356e-06, + "loss": 0.4739, + "step": 8545 + }, + { + "epoch": 0.73, + "learning_rate": 3.618783380289226e-06, + "loss": 0.4642, + "step": 8546 + }, + { + "epoch": 0.73, + "learning_rate": 3.6166573720155316e-06, + "loss": 0.4785, + "step": 8547 + }, + { + "epoch": 0.73, + "learning_rate": 3.614531850562203e-06, + "loss": 0.4535, + "step": 8548 + }, + { + "epoch": 0.73, + "learning_rate": 3.6124068160913306e-06, + "loss": 0.4585, + "step": 8549 + }, + { + "epoch": 0.73, + "learning_rate": 3.610282268764983e-06, + "loss": 0.4533, + "step": 8550 + }, + { + "epoch": 0.73, + "learning_rate": 3.608158208745187e-06, + "loss": 0.4622, + "step": 8551 + }, + { + "epoch": 0.73, + "learning_rate": 3.606034636193926e-06, + "loss": 0.4734, + "step": 8552 + }, + { + "epoch": 0.73, + "learning_rate": 3.6039115512731605e-06, + "loss": 0.4515, + "step": 8553 + }, + { + "epoch": 0.73, + "learning_rate": 3.601788954144807e-06, + "loss": 0.4747, + "step": 8554 + }, + { + "epoch": 0.73, + "learning_rate": 3.599666844970735e-06, + "loss": 0.4588, + "step": 8555 + }, + { + "epoch": 0.73, + "learning_rate": 3.5975452239127916e-06, + "loss": 0.4736, + "step": 8556 + }, + { + "epoch": 0.73, + "learning_rate": 3.5954240911327777e-06, + "loss": 0.4649, + "step": 8557 + }, + { + "epoch": 0.73, + "learning_rate": 3.593303446792461e-06, + "loss": 0.4619, + "step": 8558 + }, + { + "epoch": 0.73, + "learning_rate": 3.5911832910535703e-06, + "loss": 0.4636, + "step": 8559 + }, + { + "epoch": 0.73, + "learning_rate": 3.589063624077802e-06, + "loss": 0.458, + "step": 8560 + }, + { + "epoch": 0.73, + "learning_rate": 3.5869444460268e-06, + "loss": 0.467, + "step": 8561 + }, + { + "epoch": 0.73, + "learning_rate": 3.58482575706219e-06, + "loss": 0.4456, + "step": 8562 + }, + { + "epoch": 0.73, + "learning_rate": 3.582707557345555e-06, + "loss": 0.45, + "step": 8563 + }, + { + "epoch": 0.73, + "learning_rate": 3.5805898470384305e-06, + "loss": 0.4602, + "step": 8564 + }, + { + "epoch": 0.73, + "learning_rate": 3.5784726263023227e-06, + "loss": 0.4676, + "step": 8565 + }, + { + "epoch": 0.73, + "learning_rate": 3.576355895298702e-06, + "loss": 0.47, + "step": 8566 + }, + { + "epoch": 0.73, + "learning_rate": 3.574239654188999e-06, + "loss": 0.4396, + "step": 8567 + }, + { + "epoch": 0.73, + "learning_rate": 3.5721239031346067e-06, + "loss": 0.4783, + "step": 8568 + }, + { + "epoch": 0.73, + "learning_rate": 3.570008642296885e-06, + "loss": 0.4587, + "step": 8569 + }, + { + "epoch": 0.73, + "learning_rate": 3.5678938718371414e-06, + "loss": 0.4672, + "step": 8570 + }, + { + "epoch": 0.73, + "learning_rate": 3.565779591916667e-06, + "loss": 0.4694, + "step": 8571 + }, + { + "epoch": 0.73, + "learning_rate": 3.5636658026967076e-06, + "loss": 0.4774, + "step": 8572 + }, + { + "epoch": 0.73, + "learning_rate": 3.5615525043384604e-06, + "loss": 0.4727, + "step": 8573 + }, + { + "epoch": 0.73, + "learning_rate": 3.5594396970031e-06, + "loss": 0.4395, + "step": 8574 + }, + { + "epoch": 0.73, + "learning_rate": 3.557327380851756e-06, + "loss": 0.4731, + "step": 8575 + }, + { + "epoch": 0.73, + "learning_rate": 3.5552155560455237e-06, + "loss": 0.4467, + "step": 8576 + }, + { + "epoch": 0.73, + "learning_rate": 3.5531042227454595e-06, + "loss": 0.4318, + "step": 8577 + }, + { + "epoch": 0.73, + "learning_rate": 3.550993381112585e-06, + "loss": 0.4654, + "step": 8578 + }, + { + "epoch": 0.73, + "learning_rate": 3.5488830313078727e-06, + "loss": 0.4255, + "step": 8579 + }, + { + "epoch": 0.73, + "learning_rate": 3.546773173492276e-06, + "loss": 0.4689, + "step": 8580 + }, + { + "epoch": 0.73, + "learning_rate": 3.5446638078267027e-06, + "loss": 0.4469, + "step": 8581 + }, + { + "epoch": 0.73, + "learning_rate": 3.5425549344720133e-06, + "loss": 0.4615, + "step": 8582 + }, + { + "epoch": 0.73, + "learning_rate": 3.5404465535890443e-06, + "loss": 0.4724, + "step": 8583 + }, + { + "epoch": 0.73, + "learning_rate": 3.5383386653385888e-06, + "loss": 0.4693, + "step": 8584 + }, + { + "epoch": 0.73, + "learning_rate": 3.536231269881404e-06, + "loss": 0.4533, + "step": 8585 + }, + { + "epoch": 0.73, + "learning_rate": 3.5341243673782067e-06, + "loss": 0.4582, + "step": 8586 + }, + { + "epoch": 0.73, + "learning_rate": 3.532017957989684e-06, + "loss": 0.4555, + "step": 8587 + }, + { + "epoch": 0.73, + "learning_rate": 3.5299120418764697e-06, + "loss": 0.4652, + "step": 8588 + }, + { + "epoch": 0.73, + "learning_rate": 3.5278066191991733e-06, + "loss": 0.4637, + "step": 8589 + }, + { + "epoch": 0.73, + "learning_rate": 3.5257016901183707e-06, + "loss": 0.4498, + "step": 8590 + }, + { + "epoch": 0.73, + "learning_rate": 3.523597254794583e-06, + "loss": 0.4794, + "step": 8591 + }, + { + "epoch": 0.73, + "learning_rate": 3.521493313388307e-06, + "loss": 0.456, + "step": 8592 + }, + { + "epoch": 0.73, + "learning_rate": 3.519389866059998e-06, + "loss": 0.4701, + "step": 8593 + }, + { + "epoch": 0.73, + "learning_rate": 3.517286912970074e-06, + "loss": 0.4551, + "step": 8594 + }, + { + "epoch": 0.73, + "learning_rate": 3.515184454278914e-06, + "loss": 0.457, + "step": 8595 + }, + { + "epoch": 0.73, + "learning_rate": 3.513082490146864e-06, + "loss": 0.4645, + "step": 8596 + }, + { + "epoch": 0.73, + "learning_rate": 3.5109810207342222e-06, + "loss": 0.4607, + "step": 8597 + }, + { + "epoch": 0.73, + "learning_rate": 3.5088800462012553e-06, + "loss": 0.4743, + "step": 8598 + }, + { + "epoch": 0.73, + "learning_rate": 3.506779566708203e-06, + "loss": 0.4422, + "step": 8599 + }, + { + "epoch": 0.73, + "learning_rate": 3.5046795824152447e-06, + "loss": 0.4682, + "step": 8600 + }, + { + "epoch": 0.73, + "learning_rate": 3.5025800934825392e-06, + "loss": 0.4562, + "step": 8601 + }, + { + "epoch": 0.73, + "learning_rate": 3.500481100070201e-06, + "loss": 0.4467, + "step": 8602 + }, + { + "epoch": 0.73, + "learning_rate": 3.4983826023383105e-06, + "loss": 0.4707, + "step": 8603 + }, + { + "epoch": 0.73, + "learning_rate": 3.4962846004469042e-06, + "loss": 0.4611, + "step": 8604 + }, + { + "epoch": 0.73, + "learning_rate": 3.4941870945559906e-06, + "loss": 0.4725, + "step": 8605 + }, + { + "epoch": 0.73, + "learning_rate": 3.492090084825528e-06, + "loss": 0.4626, + "step": 8606 + }, + { + "epoch": 0.73, + "learning_rate": 3.489993571415441e-06, + "loss": 0.472, + "step": 8607 + }, + { + "epoch": 0.73, + "learning_rate": 3.4878975544856285e-06, + "loss": 0.4556, + "step": 8608 + }, + { + "epoch": 0.73, + "learning_rate": 3.4858020341959332e-06, + "loss": 0.4676, + "step": 8609 + }, + { + "epoch": 0.73, + "learning_rate": 3.483707010706171e-06, + "loss": 0.4583, + "step": 8610 + }, + { + "epoch": 0.73, + "learning_rate": 3.4816124841761157e-06, + "loss": 0.4556, + "step": 8611 + }, + { + "epoch": 0.73, + "learning_rate": 3.479518454765507e-06, + "loss": 0.4728, + "step": 8612 + }, + { + "epoch": 0.73, + "learning_rate": 3.477424922634043e-06, + "loss": 0.4607, + "step": 8613 + }, + { + "epoch": 0.73, + "learning_rate": 3.475331887941388e-06, + "loss": 0.4462, + "step": 8614 + }, + { + "epoch": 0.73, + "learning_rate": 3.4732393508471607e-06, + "loss": 0.4464, + "step": 8615 + }, + { + "epoch": 0.73, + "learning_rate": 3.471147311510944e-06, + "loss": 0.4772, + "step": 8616 + }, + { + "epoch": 0.73, + "learning_rate": 3.4690557700922976e-06, + "loss": 0.4812, + "step": 8617 + }, + { + "epoch": 0.73, + "learning_rate": 3.466964726750722e-06, + "loss": 0.4604, + "step": 8618 + }, + { + "epoch": 0.73, + "learning_rate": 3.4648741816456897e-06, + "loss": 0.4692, + "step": 8619 + }, + { + "epoch": 0.73, + "learning_rate": 3.4627841349366363e-06, + "loss": 0.4674, + "step": 8620 + }, + { + "epoch": 0.74, + "learning_rate": 3.460694586782957e-06, + "loss": 0.4474, + "step": 8621 + }, + { + "epoch": 0.74, + "learning_rate": 3.4586055373440075e-06, + "loss": 0.4779, + "step": 8622 + }, + { + "epoch": 0.74, + "learning_rate": 3.4565169867791147e-06, + "loss": 0.4697, + "step": 8623 + }, + { + "epoch": 0.74, + "learning_rate": 3.45442893524755e-06, + "loss": 0.4628, + "step": 8624 + }, + { + "epoch": 0.74, + "learning_rate": 3.4523413829085597e-06, + "loss": 0.4592, + "step": 8625 + }, + { + "epoch": 0.74, + "learning_rate": 3.4502543299213563e-06, + "loss": 0.4698, + "step": 8626 + }, + { + "epoch": 0.74, + "learning_rate": 3.448167776445099e-06, + "loss": 0.4655, + "step": 8627 + }, + { + "epoch": 0.74, + "learning_rate": 3.446081722638921e-06, + "loss": 0.4704, + "step": 8628 + }, + { + "epoch": 0.74, + "learning_rate": 3.443996168661912e-06, + "loss": 0.4605, + "step": 8629 + }, + { + "epoch": 0.74, + "learning_rate": 3.4419111146731255e-06, + "loss": 0.4582, + "step": 8630 + }, + { + "epoch": 0.74, + "learning_rate": 3.4398265608315774e-06, + "loss": 0.4345, + "step": 8631 + }, + { + "epoch": 0.74, + "learning_rate": 3.4377425072962467e-06, + "loss": 0.476, + "step": 8632 + }, + { + "epoch": 0.74, + "learning_rate": 3.4356589542260654e-06, + "loss": 0.4587, + "step": 8633 + }, + { + "epoch": 0.74, + "learning_rate": 3.4335759017799375e-06, + "loss": 0.4637, + "step": 8634 + }, + { + "epoch": 0.74, + "learning_rate": 3.4314933501167257e-06, + "loss": 0.4758, + "step": 8635 + }, + { + "epoch": 0.74, + "learning_rate": 3.4294112993952533e-06, + "loss": 0.4605, + "step": 8636 + }, + { + "epoch": 0.74, + "learning_rate": 3.4273297497743063e-06, + "loss": 0.4637, + "step": 8637 + }, + { + "epoch": 0.74, + "learning_rate": 3.4252487014126336e-06, + "loss": 0.4625, + "step": 8638 + }, + { + "epoch": 0.74, + "learning_rate": 3.4231681544689433e-06, + "loss": 0.4625, + "step": 8639 + }, + { + "epoch": 0.74, + "learning_rate": 3.4210881091019067e-06, + "loss": 0.4382, + "step": 8640 + }, + { + "epoch": 0.74, + "learning_rate": 3.419008565470161e-06, + "loss": 0.4758, + "step": 8641 + }, + { + "epoch": 0.74, + "learning_rate": 3.416929523732293e-06, + "loss": 0.4802, + "step": 8642 + }, + { + "epoch": 0.74, + "learning_rate": 3.4148509840468636e-06, + "loss": 0.4567, + "step": 8643 + }, + { + "epoch": 0.74, + "learning_rate": 3.412772946572389e-06, + "loss": 0.4313, + "step": 8644 + }, + { + "epoch": 0.74, + "learning_rate": 3.410695411467352e-06, + "loss": 0.4543, + "step": 8645 + }, + { + "epoch": 0.74, + "learning_rate": 3.4086183788901916e-06, + "loss": 0.4687, + "step": 8646 + }, + { + "epoch": 0.74, + "learning_rate": 3.4065418489993118e-06, + "loss": 0.4509, + "step": 8647 + }, + { + "epoch": 0.74, + "learning_rate": 3.404465821953078e-06, + "loss": 0.4513, + "step": 8648 + }, + { + "epoch": 0.74, + "learning_rate": 3.4023902979098155e-06, + "loss": 0.4507, + "step": 8649 + }, + { + "epoch": 0.74, + "learning_rate": 3.4003152770278124e-06, + "loss": 0.4653, + "step": 8650 + }, + { + "epoch": 0.74, + "learning_rate": 3.3982407594653244e-06, + "loss": 0.4582, + "step": 8651 + }, + { + "epoch": 0.74, + "learning_rate": 3.3961667453805526e-06, + "loss": 0.4521, + "step": 8652 + }, + { + "epoch": 0.74, + "learning_rate": 3.3940932349316757e-06, + "loss": 0.4456, + "step": 8653 + }, + { + "epoch": 0.74, + "learning_rate": 3.3920202282768277e-06, + "loss": 0.4505, + "step": 8654 + }, + { + "epoch": 0.74, + "learning_rate": 3.3899477255741043e-06, + "loss": 0.4809, + "step": 8655 + }, + { + "epoch": 0.74, + "learning_rate": 3.387875726981563e-06, + "loss": 0.4654, + "step": 8656 + }, + { + "epoch": 0.74, + "learning_rate": 3.385804232657224e-06, + "loss": 0.4645, + "step": 8657 + }, + { + "epoch": 0.74, + "learning_rate": 3.3837332427590673e-06, + "loss": 0.476, + "step": 8658 + }, + { + "epoch": 0.74, + "learning_rate": 3.3816627574450367e-06, + "loss": 0.4838, + "step": 8659 + }, + { + "epoch": 0.74, + "learning_rate": 3.3795927768730376e-06, + "loss": 0.4407, + "step": 8660 + }, + { + "epoch": 0.74, + "learning_rate": 3.377523301200929e-06, + "loss": 0.478, + "step": 8661 + }, + { + "epoch": 0.74, + "learning_rate": 3.3754543305865418e-06, + "loss": 0.4693, + "step": 8662 + }, + { + "epoch": 0.74, + "learning_rate": 3.373385865187664e-06, + "loss": 0.4397, + "step": 8663 + }, + { + "epoch": 0.74, + "learning_rate": 3.3713179051620457e-06, + "loss": 0.4343, + "step": 8664 + }, + { + "epoch": 0.74, + "learning_rate": 3.3692504506673973e-06, + "loss": 0.4699, + "step": 8665 + }, + { + "epoch": 0.74, + "learning_rate": 3.367183501861395e-06, + "loss": 0.454, + "step": 8666 + }, + { + "epoch": 0.74, + "learning_rate": 3.3651170589016645e-06, + "loss": 0.4531, + "step": 8667 + }, + { + "epoch": 0.74, + "learning_rate": 3.3630511219458093e-06, + "loss": 0.4706, + "step": 8668 + }, + { + "epoch": 0.74, + "learning_rate": 3.3609856911513885e-06, + "loss": 0.4758, + "step": 8669 + }, + { + "epoch": 0.74, + "learning_rate": 3.3589207666759114e-06, + "loss": 0.4533, + "step": 8670 + }, + { + "epoch": 0.74, + "learning_rate": 3.3568563486768636e-06, + "loss": 0.4733, + "step": 8671 + }, + { + "epoch": 0.74, + "learning_rate": 3.3547924373116836e-06, + "loss": 0.4577, + "step": 8672 + }, + { + "epoch": 0.74, + "learning_rate": 3.352729032737776e-06, + "loss": 0.4549, + "step": 8673 + }, + { + "epoch": 0.74, + "learning_rate": 3.350666135112504e-06, + "loss": 0.4629, + "step": 8674 + }, + { + "epoch": 0.74, + "learning_rate": 3.348603744593195e-06, + "loss": 0.4638, + "step": 8675 + }, + { + "epoch": 0.74, + "learning_rate": 3.346541861337127e-06, + "loss": 0.4643, + "step": 8676 + }, + { + "epoch": 0.74, + "learning_rate": 3.3444804855015576e-06, + "loss": 0.448, + "step": 8677 + }, + { + "epoch": 0.74, + "learning_rate": 3.342419617243695e-06, + "loss": 0.45, + "step": 8678 + }, + { + "epoch": 0.74, + "learning_rate": 3.3403592567207046e-06, + "loss": 0.4458, + "step": 8679 + }, + { + "epoch": 0.74, + "learning_rate": 3.3382994040897197e-06, + "loss": 0.4858, + "step": 8680 + }, + { + "epoch": 0.74, + "learning_rate": 3.336240059507835e-06, + "loss": 0.4802, + "step": 8681 + }, + { + "epoch": 0.74, + "learning_rate": 3.3341812231321024e-06, + "loss": 0.451, + "step": 8682 + }, + { + "epoch": 0.74, + "learning_rate": 3.3321228951195396e-06, + "loss": 0.4524, + "step": 8683 + }, + { + "epoch": 0.74, + "learning_rate": 3.330065075627126e-06, + "loss": 0.4542, + "step": 8684 + }, + { + "epoch": 0.74, + "learning_rate": 3.3280077648117883e-06, + "loss": 0.4669, + "step": 8685 + }, + { + "epoch": 0.74, + "learning_rate": 3.3259509628304364e-06, + "loss": 0.4493, + "step": 8686 + }, + { + "epoch": 0.74, + "learning_rate": 3.323894669839932e-06, + "loss": 0.4553, + "step": 8687 + }, + { + "epoch": 0.74, + "learning_rate": 3.3218388859970874e-06, + "loss": 0.4668, + "step": 8688 + }, + { + "epoch": 0.74, + "learning_rate": 3.3197836114586903e-06, + "loss": 0.4471, + "step": 8689 + }, + { + "epoch": 0.74, + "learning_rate": 3.317728846381484e-06, + "loss": 0.4548, + "step": 8690 + }, + { + "epoch": 0.74, + "learning_rate": 3.315674590922173e-06, + "loss": 0.4689, + "step": 8691 + }, + { + "epoch": 0.74, + "learning_rate": 3.313620845237425e-06, + "loss": 0.4556, + "step": 8692 + }, + { + "epoch": 0.74, + "learning_rate": 3.3115676094838687e-06, + "loss": 0.474, + "step": 8693 + }, + { + "epoch": 0.74, + "learning_rate": 3.3095148838180836e-06, + "loss": 0.4936, + "step": 8694 + }, + { + "epoch": 0.74, + "learning_rate": 3.307462668396628e-06, + "loss": 0.4576, + "step": 8695 + }, + { + "epoch": 0.74, + "learning_rate": 3.3054109633760147e-06, + "loss": 0.4727, + "step": 8696 + }, + { + "epoch": 0.74, + "learning_rate": 3.303359768912706e-06, + "loss": 0.4701, + "step": 8697 + }, + { + "epoch": 0.74, + "learning_rate": 3.3013090851631393e-06, + "loss": 0.4511, + "step": 8698 + }, + { + "epoch": 0.74, + "learning_rate": 3.2992589122837073e-06, + "loss": 0.4581, + "step": 8699 + }, + { + "epoch": 0.74, + "learning_rate": 3.297209250430766e-06, + "loss": 0.448, + "step": 8700 + }, + { + "epoch": 0.74, + "learning_rate": 3.2951600997606305e-06, + "loss": 0.4493, + "step": 8701 + }, + { + "epoch": 0.74, + "learning_rate": 3.29311146042958e-06, + "loss": 0.457, + "step": 8702 + }, + { + "epoch": 0.74, + "learning_rate": 3.2910633325938447e-06, + "loss": 0.4781, + "step": 8703 + }, + { + "epoch": 0.74, + "learning_rate": 3.2890157164096315e-06, + "loss": 0.4644, + "step": 8704 + }, + { + "epoch": 0.74, + "learning_rate": 3.2869686120331e-06, + "loss": 0.4547, + "step": 8705 + }, + { + "epoch": 0.74, + "learning_rate": 3.2849220196203657e-06, + "loss": 0.4526, + "step": 8706 + }, + { + "epoch": 0.74, + "learning_rate": 3.282875939327512e-06, + "loss": 0.4655, + "step": 8707 + }, + { + "epoch": 0.74, + "learning_rate": 3.2808303713105826e-06, + "loss": 0.4654, + "step": 8708 + }, + { + "epoch": 0.74, + "learning_rate": 3.278785315725581e-06, + "loss": 0.4413, + "step": 8709 + }, + { + "epoch": 0.74, + "learning_rate": 3.2767407727284716e-06, + "loss": 0.4655, + "step": 8710 + }, + { + "epoch": 0.74, + "learning_rate": 3.274696742475183e-06, + "loss": 0.4466, + "step": 8711 + }, + { + "epoch": 0.74, + "learning_rate": 3.2726532251215917e-06, + "loss": 0.4466, + "step": 8712 + }, + { + "epoch": 0.74, + "learning_rate": 3.2706102208235535e-06, + "loss": 0.4408, + "step": 8713 + }, + { + "epoch": 0.74, + "learning_rate": 3.268567729736879e-06, + "loss": 0.4482, + "step": 8714 + }, + { + "epoch": 0.74, + "learning_rate": 3.2665257520173276e-06, + "loss": 0.4648, + "step": 8715 + }, + { + "epoch": 0.74, + "learning_rate": 3.264484287820634e-06, + "loss": 0.464, + "step": 8716 + }, + { + "epoch": 0.74, + "learning_rate": 3.262443337302489e-06, + "loss": 0.4683, + "step": 8717 + }, + { + "epoch": 0.74, + "learning_rate": 3.2604029006185434e-06, + "loss": 0.4626, + "step": 8718 + }, + { + "epoch": 0.74, + "learning_rate": 3.2583629779244097e-06, + "loss": 0.4498, + "step": 8719 + }, + { + "epoch": 0.74, + "learning_rate": 3.2563235693756645e-06, + "loss": 0.4623, + "step": 8720 + }, + { + "epoch": 0.74, + "learning_rate": 3.2542846751278333e-06, + "loss": 0.4634, + "step": 8721 + }, + { + "epoch": 0.74, + "learning_rate": 3.252246295336413e-06, + "loss": 0.4632, + "step": 8722 + }, + { + "epoch": 0.74, + "learning_rate": 3.250208430156868e-06, + "loss": 0.4434, + "step": 8723 + }, + { + "epoch": 0.74, + "learning_rate": 3.248171079744604e-06, + "loss": 0.4682, + "step": 8724 + }, + { + "epoch": 0.74, + "learning_rate": 3.2461342442550017e-06, + "loss": 0.4583, + "step": 8725 + }, + { + "epoch": 0.74, + "learning_rate": 3.2440979238433977e-06, + "loss": 0.4545, + "step": 8726 + }, + { + "epoch": 0.74, + "learning_rate": 3.2420621186650927e-06, + "loss": 0.4596, + "step": 8727 + }, + { + "epoch": 0.74, + "learning_rate": 3.2400268288753423e-06, + "loss": 0.4418, + "step": 8728 + }, + { + "epoch": 0.74, + "learning_rate": 3.237992054629372e-06, + "loss": 0.4456, + "step": 8729 + }, + { + "epoch": 0.74, + "learning_rate": 3.235957796082355e-06, + "loss": 0.4698, + "step": 8730 + }, + { + "epoch": 0.74, + "learning_rate": 3.2339240533894323e-06, + "loss": 0.4736, + "step": 8731 + }, + { + "epoch": 0.74, + "learning_rate": 3.2318908267057147e-06, + "loss": 0.463, + "step": 8732 + }, + { + "epoch": 0.74, + "learning_rate": 3.2298581161862565e-06, + "loss": 0.4572, + "step": 8733 + }, + { + "epoch": 0.74, + "learning_rate": 3.227825921986082e-06, + "loss": 0.4789, + "step": 8734 + }, + { + "epoch": 0.74, + "learning_rate": 3.2257942442601755e-06, + "loss": 0.4718, + "step": 8735 + }, + { + "epoch": 0.74, + "learning_rate": 3.2237630831634816e-06, + "loss": 0.4571, + "step": 8736 + }, + { + "epoch": 0.74, + "learning_rate": 3.2217324388509053e-06, + "loss": 0.4508, + "step": 8737 + }, + { + "epoch": 0.75, + "learning_rate": 3.219702311477314e-06, + "loss": 0.4352, + "step": 8738 + }, + { + "epoch": 0.75, + "learning_rate": 3.2176727011975286e-06, + "loss": 0.4551, + "step": 8739 + }, + { + "epoch": 0.75, + "learning_rate": 3.2156436081663356e-06, + "loss": 0.4688, + "step": 8740 + }, + { + "epoch": 0.75, + "learning_rate": 3.2136150325384905e-06, + "loss": 0.4432, + "step": 8741 + }, + { + "epoch": 0.75, + "learning_rate": 3.2115869744686932e-06, + "loss": 0.4406, + "step": 8742 + }, + { + "epoch": 0.75, + "learning_rate": 3.2095594341116133e-06, + "loss": 0.4435, + "step": 8743 + }, + { + "epoch": 0.75, + "learning_rate": 3.2075324116218833e-06, + "loss": 0.434, + "step": 8744 + }, + { + "epoch": 0.75, + "learning_rate": 3.205505907154083e-06, + "loss": 0.4684, + "step": 8745 + }, + { + "epoch": 0.75, + "learning_rate": 3.203479920862772e-06, + "loss": 0.4459, + "step": 8746 + }, + { + "epoch": 0.75, + "learning_rate": 3.2014544529024595e-06, + "loss": 0.4621, + "step": 8747 + }, + { + "epoch": 0.75, + "learning_rate": 3.19942950342761e-06, + "loss": 0.4433, + "step": 8748 + }, + { + "epoch": 0.75, + "learning_rate": 3.1974050725926552e-06, + "loss": 0.4504, + "step": 8749 + }, + { + "epoch": 0.75, + "learning_rate": 3.1953811605519967e-06, + "loss": 0.4758, + "step": 8750 + }, + { + "epoch": 0.75, + "learning_rate": 3.193357767459975e-06, + "loss": 0.4469, + "step": 8751 + }, + { + "epoch": 0.75, + "learning_rate": 3.1913348934709076e-06, + "loss": 0.4507, + "step": 8752 + }, + { + "epoch": 0.75, + "learning_rate": 3.18931253873907e-06, + "loss": 0.4575, + "step": 8753 + }, + { + "epoch": 0.75, + "learning_rate": 3.1872907034186852e-06, + "loss": 0.4534, + "step": 8754 + }, + { + "epoch": 0.75, + "learning_rate": 3.1852693876639563e-06, + "loss": 0.4756, + "step": 8755 + }, + { + "epoch": 0.75, + "learning_rate": 3.183248591629038e-06, + "loss": 0.4652, + "step": 8756 + }, + { + "epoch": 0.75, + "learning_rate": 3.181228315468038e-06, + "loss": 0.4575, + "step": 8757 + }, + { + "epoch": 0.75, + "learning_rate": 3.179208559335031e-06, + "loss": 0.4567, + "step": 8758 + }, + { + "epoch": 0.75, + "learning_rate": 3.177189323384061e-06, + "loss": 0.4535, + "step": 8759 + }, + { + "epoch": 0.75, + "learning_rate": 3.175170607769116e-06, + "loss": 0.4488, + "step": 8760 + }, + { + "epoch": 0.75, + "learning_rate": 3.1731524126441513e-06, + "loss": 0.4496, + "step": 8761 + }, + { + "epoch": 0.75, + "learning_rate": 3.17113473816309e-06, + "loss": 0.4642, + "step": 8762 + }, + { + "epoch": 0.75, + "learning_rate": 3.169117584479795e-06, + "loss": 0.4516, + "step": 8763 + }, + { + "epoch": 0.75, + "learning_rate": 3.1671009517481155e-06, + "loss": 0.4451, + "step": 8764 + }, + { + "epoch": 0.75, + "learning_rate": 3.165084840121847e-06, + "loss": 0.4763, + "step": 8765 + }, + { + "epoch": 0.75, + "learning_rate": 3.16306924975474e-06, + "loss": 0.4518, + "step": 8766 + }, + { + "epoch": 0.75, + "learning_rate": 3.161054180800516e-06, + "loss": 0.431, + "step": 8767 + }, + { + "epoch": 0.75, + "learning_rate": 3.1590396334128505e-06, + "loss": 0.4677, + "step": 8768 + }, + { + "epoch": 0.75, + "learning_rate": 3.1570256077453833e-06, + "loss": 0.4677, + "step": 8769 + }, + { + "epoch": 0.75, + "learning_rate": 3.1550121039517125e-06, + "loss": 0.4652, + "step": 8770 + }, + { + "epoch": 0.75, + "learning_rate": 3.152999122185395e-06, + "loss": 0.4302, + "step": 8771 + }, + { + "epoch": 0.75, + "learning_rate": 3.1509866625999497e-06, + "loss": 0.4601, + "step": 8772 + }, + { + "epoch": 0.75, + "learning_rate": 3.1489747253488555e-06, + "loss": 0.4653, + "step": 8773 + }, + { + "epoch": 0.75, + "learning_rate": 3.1469633105855545e-06, + "loss": 0.4313, + "step": 8774 + }, + { + "epoch": 0.75, + "learning_rate": 3.1449524184634383e-06, + "loss": 0.4773, + "step": 8775 + }, + { + "epoch": 0.75, + "learning_rate": 3.1429420491358696e-06, + "loss": 0.4698, + "step": 8776 + }, + { + "epoch": 0.75, + "learning_rate": 3.1409322027561683e-06, + "loss": 0.4666, + "step": 8777 + }, + { + "epoch": 0.75, + "learning_rate": 3.138922879477613e-06, + "loss": 0.4545, + "step": 8778 + }, + { + "epoch": 0.75, + "learning_rate": 3.1369140794534412e-06, + "loss": 0.4613, + "step": 8779 + }, + { + "epoch": 0.75, + "learning_rate": 3.134905802836856e-06, + "loss": 0.4438, + "step": 8780 + }, + { + "epoch": 0.75, + "learning_rate": 3.1328980497810145e-06, + "loss": 0.4522, + "step": 8781 + }, + { + "epoch": 0.75, + "learning_rate": 3.1308908204390376e-06, + "loss": 0.4644, + "step": 8782 + }, + { + "epoch": 0.75, + "learning_rate": 3.128884114964007e-06, + "loss": 0.447, + "step": 8783 + }, + { + "epoch": 0.75, + "learning_rate": 3.126877933508957e-06, + "loss": 0.4593, + "step": 8784 + }, + { + "epoch": 0.75, + "learning_rate": 3.1248722762268902e-06, + "loss": 0.4514, + "step": 8785 + }, + { + "epoch": 0.75, + "learning_rate": 3.1228671432707656e-06, + "loss": 0.4645, + "step": 8786 + }, + { + "epoch": 0.75, + "learning_rate": 3.120862534793505e-06, + "loss": 0.4617, + "step": 8787 + }, + { + "epoch": 0.75, + "learning_rate": 3.1188584509479867e-06, + "loss": 0.4645, + "step": 8788 + }, + { + "epoch": 0.75, + "learning_rate": 3.11685489188705e-06, + "loss": 0.4819, + "step": 8789 + }, + { + "epoch": 0.75, + "learning_rate": 3.1148518577634966e-06, + "loss": 0.4467, + "step": 8790 + }, + { + "epoch": 0.75, + "learning_rate": 3.1128493487300847e-06, + "loss": 0.4641, + "step": 8791 + }, + { + "epoch": 0.75, + "learning_rate": 3.1108473649395376e-06, + "loss": 0.4544, + "step": 8792 + }, + { + "epoch": 0.75, + "learning_rate": 3.1088459065445288e-06, + "loss": 0.4611, + "step": 8793 + }, + { + "epoch": 0.75, + "learning_rate": 3.1068449736977015e-06, + "loss": 0.4543, + "step": 8794 + }, + { + "epoch": 0.75, + "learning_rate": 3.1048445665516535e-06, + "loss": 0.4512, + "step": 8795 + }, + { + "epoch": 0.75, + "learning_rate": 3.1028446852589456e-06, + "loss": 0.4532, + "step": 8796 + }, + { + "epoch": 0.75, + "learning_rate": 3.1008453299720965e-06, + "loss": 0.4544, + "step": 8797 + }, + { + "epoch": 0.75, + "learning_rate": 3.098846500843585e-06, + "loss": 0.4557, + "step": 8798 + }, + { + "epoch": 0.75, + "learning_rate": 3.096848198025856e-06, + "loss": 0.4627, + "step": 8799 + }, + { + "epoch": 0.75, + "learning_rate": 3.094850421671295e-06, + "loss": 0.4692, + "step": 8800 + }, + { + "epoch": 0.75, + "learning_rate": 3.0928531719322764e-06, + "loss": 0.4711, + "step": 8801 + }, + { + "epoch": 0.75, + "learning_rate": 3.0908564489611083e-06, + "loss": 0.4635, + "step": 8802 + }, + { + "epoch": 0.75, + "learning_rate": 3.088860252910071e-06, + "loss": 0.4437, + "step": 8803 + }, + { + "epoch": 0.75, + "learning_rate": 3.086864583931405e-06, + "loss": 0.4479, + "step": 8804 + }, + { + "epoch": 0.75, + "learning_rate": 3.0848694421773075e-06, + "loss": 0.4615, + "step": 8805 + }, + { + "epoch": 0.75, + "learning_rate": 3.0828748277999354e-06, + "loss": 0.4528, + "step": 8806 + }, + { + "epoch": 0.75, + "learning_rate": 3.0808807409514073e-06, + "loss": 0.5022, + "step": 8807 + }, + { + "epoch": 0.75, + "learning_rate": 3.078887181783803e-06, + "loss": 0.4642, + "step": 8808 + }, + { + "epoch": 0.75, + "learning_rate": 3.0768941504491514e-06, + "loss": 0.4613, + "step": 8809 + }, + { + "epoch": 0.75, + "learning_rate": 3.074901647099461e-06, + "loss": 0.466, + "step": 8810 + }, + { + "epoch": 0.75, + "learning_rate": 3.072909671886679e-06, + "loss": 0.4746, + "step": 8811 + }, + { + "epoch": 0.75, + "learning_rate": 3.0709182249627255e-06, + "loss": 0.4731, + "step": 8812 + }, + { + "epoch": 0.75, + "learning_rate": 3.0689273064794767e-06, + "loss": 0.437, + "step": 8813 + }, + { + "epoch": 0.75, + "learning_rate": 3.0669369165887674e-06, + "loss": 0.4854, + "step": 8814 + }, + { + "epoch": 0.75, + "learning_rate": 3.0649470554423932e-06, + "loss": 0.4686, + "step": 8815 + }, + { + "epoch": 0.75, + "learning_rate": 3.0629577231921102e-06, + "loss": 0.4559, + "step": 8816 + }, + { + "epoch": 0.75, + "learning_rate": 3.060968919989635e-06, + "loss": 0.4454, + "step": 8817 + }, + { + "epoch": 0.75, + "learning_rate": 3.0589806459866336e-06, + "loss": 0.4618, + "step": 8818 + }, + { + "epoch": 0.75, + "learning_rate": 3.056992901334752e-06, + "loss": 0.4544, + "step": 8819 + }, + { + "epoch": 0.75, + "learning_rate": 3.055005686185576e-06, + "loss": 0.4727, + "step": 8820 + }, + { + "epoch": 0.75, + "learning_rate": 3.053019000690659e-06, + "loss": 0.4515, + "step": 8821 + }, + { + "epoch": 0.75, + "learning_rate": 3.051032845001517e-06, + "loss": 0.4545, + "step": 8822 + }, + { + "epoch": 0.75, + "learning_rate": 3.0490472192696206e-06, + "loss": 0.4819, + "step": 8823 + }, + { + "epoch": 0.75, + "learning_rate": 3.047062123646404e-06, + "loss": 0.4496, + "step": 8824 + }, + { + "epoch": 0.75, + "learning_rate": 3.045077558283256e-06, + "loss": 0.4673, + "step": 8825 + }, + { + "epoch": 0.75, + "learning_rate": 3.043093523331533e-06, + "loss": 0.4584, + "step": 8826 + }, + { + "epoch": 0.75, + "learning_rate": 3.0411100189425356e-06, + "loss": 0.4612, + "step": 8827 + }, + { + "epoch": 0.75, + "learning_rate": 3.039127045267544e-06, + "loss": 0.4618, + "step": 8828 + }, + { + "epoch": 0.75, + "learning_rate": 3.0371446024577878e-06, + "loss": 0.4475, + "step": 8829 + }, + { + "epoch": 0.75, + "learning_rate": 3.0351626906644505e-06, + "loss": 0.4664, + "step": 8830 + }, + { + "epoch": 0.75, + "learning_rate": 3.033181310038683e-06, + "loss": 0.4719, + "step": 8831 + }, + { + "epoch": 0.75, + "learning_rate": 3.031200460731595e-06, + "loss": 0.4578, + "step": 8832 + }, + { + "epoch": 0.75, + "learning_rate": 3.0292201428942535e-06, + "loss": 0.4622, + "step": 8833 + }, + { + "epoch": 0.75, + "learning_rate": 3.0272403566776855e-06, + "loss": 0.4749, + "step": 8834 + }, + { + "epoch": 0.75, + "learning_rate": 3.0252611022328826e-06, + "loss": 0.4491, + "step": 8835 + }, + { + "epoch": 0.75, + "learning_rate": 3.0232823797107793e-06, + "loss": 0.4801, + "step": 8836 + }, + { + "epoch": 0.75, + "learning_rate": 3.021304189262293e-06, + "loss": 0.4469, + "step": 8837 + }, + { + "epoch": 0.75, + "learning_rate": 3.019326531038287e-06, + "loss": 0.4658, + "step": 8838 + }, + { + "epoch": 0.75, + "learning_rate": 3.017349405189579e-06, + "loss": 0.4408, + "step": 8839 + }, + { + "epoch": 0.75, + "learning_rate": 3.015372811866958e-06, + "loss": 0.4483, + "step": 8840 + }, + { + "epoch": 0.75, + "learning_rate": 3.013396751221166e-06, + "loss": 0.4716, + "step": 8841 + }, + { + "epoch": 0.75, + "learning_rate": 3.011421223402906e-06, + "loss": 0.4558, + "step": 8842 + }, + { + "epoch": 0.75, + "learning_rate": 3.00944622856284e-06, + "loss": 0.4927, + "step": 8843 + }, + { + "epoch": 0.75, + "learning_rate": 3.007471766851593e-06, + "loss": 0.4425, + "step": 8844 + }, + { + "epoch": 0.75, + "learning_rate": 3.0054978384197386e-06, + "loss": 0.4588, + "step": 8845 + }, + { + "epoch": 0.75, + "learning_rate": 3.0035244434178168e-06, + "loss": 0.459, + "step": 8846 + }, + { + "epoch": 0.75, + "learning_rate": 3.001551581996337e-06, + "loss": 0.4497, + "step": 8847 + }, + { + "epoch": 0.75, + "learning_rate": 2.999579254305748e-06, + "loss": 0.4583, + "step": 8848 + }, + { + "epoch": 0.75, + "learning_rate": 2.99760746049647e-06, + "loss": 0.4458, + "step": 8849 + }, + { + "epoch": 0.75, + "learning_rate": 2.995636200718882e-06, + "loss": 0.4516, + "step": 8850 + }, + { + "epoch": 0.75, + "learning_rate": 2.9936654751233196e-06, + "loss": 0.467, + "step": 8851 + }, + { + "epoch": 0.75, + "learning_rate": 2.991695283860079e-06, + "loss": 0.453, + "step": 8852 + }, + { + "epoch": 0.75, + "learning_rate": 2.9897256270794172e-06, + "loss": 0.4605, + "step": 8853 + }, + { + "epoch": 0.75, + "learning_rate": 2.9877565049315425e-06, + "loss": 0.4381, + "step": 8854 + }, + { + "epoch": 0.76, + "learning_rate": 2.9857879175666303e-06, + "loss": 0.453, + "step": 8855 + }, + { + "epoch": 0.76, + "learning_rate": 2.9838198651348206e-06, + "loss": 0.4523, + "step": 8856 + }, + { + "epoch": 0.76, + "learning_rate": 2.981852347786196e-06, + "loss": 0.4511, + "step": 8857 + }, + { + "epoch": 0.76, + "learning_rate": 2.9798853656708126e-06, + "loss": 0.4559, + "step": 8858 + }, + { + "epoch": 0.76, + "learning_rate": 2.9779189189386782e-06, + "loss": 0.4633, + "step": 8859 + }, + { + "epoch": 0.76, + "learning_rate": 2.9759530077397637e-06, + "loss": 0.4805, + "step": 8860 + }, + { + "epoch": 0.76, + "learning_rate": 2.973987632223997e-06, + "loss": 0.4393, + "step": 8861 + }, + { + "epoch": 0.76, + "learning_rate": 2.972022792541269e-06, + "loss": 0.4577, + "step": 8862 + }, + { + "epoch": 0.76, + "learning_rate": 2.9700584888414217e-06, + "loss": 0.4543, + "step": 8863 + }, + { + "epoch": 0.76, + "learning_rate": 2.9680947212742593e-06, + "loss": 0.4556, + "step": 8864 + }, + { + "epoch": 0.76, + "learning_rate": 2.9661314899895577e-06, + "loss": 0.4388, + "step": 8865 + }, + { + "epoch": 0.76, + "learning_rate": 2.96416879513703e-06, + "loss": 0.4711, + "step": 8866 + }, + { + "epoch": 0.76, + "learning_rate": 2.962206636866365e-06, + "loss": 0.4608, + "step": 8867 + }, + { + "epoch": 0.76, + "learning_rate": 2.9602450153272033e-06, + "loss": 0.4492, + "step": 8868 + }, + { + "epoch": 0.76, + "learning_rate": 2.9582839306691468e-06, + "loss": 0.4528, + "step": 8869 + }, + { + "epoch": 0.76, + "learning_rate": 2.956323383041756e-06, + "loss": 0.4653, + "step": 8870 + }, + { + "epoch": 0.76, + "learning_rate": 2.954363372594553e-06, + "loss": 0.4732, + "step": 8871 + }, + { + "epoch": 0.76, + "learning_rate": 2.952403899477011e-06, + "loss": 0.4398, + "step": 8872 + }, + { + "epoch": 0.76, + "learning_rate": 2.950444963838568e-06, + "loss": 0.4614, + "step": 8873 + }, + { + "epoch": 0.76, + "learning_rate": 2.9484865658286287e-06, + "loss": 0.4444, + "step": 8874 + }, + { + "epoch": 0.76, + "learning_rate": 2.94652870559654e-06, + "loss": 0.4676, + "step": 8875 + }, + { + "epoch": 0.76, + "learning_rate": 2.94457138329162e-06, + "loss": 0.4633, + "step": 8876 + }, + { + "epoch": 0.76, + "learning_rate": 2.942614599063144e-06, + "loss": 0.4569, + "step": 8877 + }, + { + "epoch": 0.76, + "learning_rate": 2.940658353060337e-06, + "loss": 0.4273, + "step": 8878 + }, + { + "epoch": 0.76, + "learning_rate": 2.9387026454323986e-06, + "loss": 0.45, + "step": 8879 + }, + { + "epoch": 0.76, + "learning_rate": 2.93674747632848e-06, + "loss": 0.4745, + "step": 8880 + }, + { + "epoch": 0.76, + "learning_rate": 2.934792845897684e-06, + "loss": 0.4388, + "step": 8881 + }, + { + "epoch": 0.76, + "learning_rate": 2.932838754289078e-06, + "loss": 0.4694, + "step": 8882 + }, + { + "epoch": 0.76, + "learning_rate": 2.9308852016516997e-06, + "loss": 0.4551, + "step": 8883 + }, + { + "epoch": 0.76, + "learning_rate": 2.9289321881345257e-06, + "loss": 0.434, + "step": 8884 + }, + { + "epoch": 0.76, + "learning_rate": 2.9269797138865044e-06, + "loss": 0.4501, + "step": 8885 + }, + { + "epoch": 0.76, + "learning_rate": 2.9250277790565407e-06, + "loss": 0.4532, + "step": 8886 + }, + { + "epoch": 0.76, + "learning_rate": 2.9230763837934907e-06, + "loss": 0.4596, + "step": 8887 + }, + { + "epoch": 0.76, + "learning_rate": 2.9211255282461835e-06, + "loss": 0.4621, + "step": 8888 + }, + { + "epoch": 0.76, + "learning_rate": 2.9191752125634e-06, + "loss": 0.4648, + "step": 8889 + }, + { + "epoch": 0.76, + "learning_rate": 2.9172254368938736e-06, + "loss": 0.4607, + "step": 8890 + }, + { + "epoch": 0.76, + "learning_rate": 2.9152762013863023e-06, + "loss": 0.4383, + "step": 8891 + }, + { + "epoch": 0.76, + "learning_rate": 2.9133275061893506e-06, + "loss": 0.4906, + "step": 8892 + }, + { + "epoch": 0.76, + "learning_rate": 2.9113793514516277e-06, + "loss": 0.4854, + "step": 8893 + }, + { + "epoch": 0.76, + "learning_rate": 2.9094317373217085e-06, + "loss": 0.4556, + "step": 8894 + }, + { + "epoch": 0.76, + "learning_rate": 2.90748466394813e-06, + "loss": 0.4595, + "step": 8895 + }, + { + "epoch": 0.76, + "learning_rate": 2.905538131479376e-06, + "loss": 0.4871, + "step": 8896 + }, + { + "epoch": 0.76, + "learning_rate": 2.9035921400639056e-06, + "loss": 0.4605, + "step": 8897 + }, + { + "epoch": 0.76, + "learning_rate": 2.901646689850128e-06, + "loss": 0.4805, + "step": 8898 + }, + { + "epoch": 0.76, + "learning_rate": 2.8997017809864068e-06, + "loss": 0.4772, + "step": 8899 + }, + { + "epoch": 0.76, + "learning_rate": 2.8977574136210696e-06, + "loss": 0.4258, + "step": 8900 + }, + { + "epoch": 0.76, + "learning_rate": 2.8958135879024028e-06, + "loss": 0.4555, + "step": 8901 + }, + { + "epoch": 0.76, + "learning_rate": 2.8938703039786507e-06, + "loss": 0.4563, + "step": 8902 + }, + { + "epoch": 0.76, + "learning_rate": 2.891927561998017e-06, + "loss": 0.4576, + "step": 8903 + }, + { + "epoch": 0.76, + "learning_rate": 2.889985362108666e-06, + "loss": 0.4509, + "step": 8904 + }, + { + "epoch": 0.76, + "learning_rate": 2.888043704458707e-06, + "loss": 0.45, + "step": 8905 + }, + { + "epoch": 0.76, + "learning_rate": 2.8861025891962314e-06, + "loss": 0.4526, + "step": 8906 + }, + { + "epoch": 0.76, + "learning_rate": 2.884162016469274e-06, + "loss": 0.4385, + "step": 8907 + }, + { + "epoch": 0.76, + "learning_rate": 2.8822219864258272e-06, + "loss": 0.495, + "step": 8908 + }, + { + "epoch": 0.76, + "learning_rate": 2.880282499213847e-06, + "loss": 0.4617, + "step": 8909 + }, + { + "epoch": 0.76, + "learning_rate": 2.8783435549812464e-06, + "loss": 0.4481, + "step": 8910 + }, + { + "epoch": 0.76, + "learning_rate": 2.8764051538758986e-06, + "loss": 0.4488, + "step": 8911 + }, + { + "epoch": 0.76, + "learning_rate": 2.8744672960456345e-06, + "loss": 0.4607, + "step": 8912 + }, + { + "epoch": 0.76, + "learning_rate": 2.8725299816382455e-06, + "loss": 0.4533, + "step": 8913 + }, + { + "epoch": 0.76, + "learning_rate": 2.87059321080147e-06, + "loss": 0.4615, + "step": 8914 + }, + { + "epoch": 0.76, + "learning_rate": 2.8686569836830246e-06, + "loss": 0.4671, + "step": 8915 + }, + { + "epoch": 0.76, + "learning_rate": 2.8667213004305716e-06, + "loss": 0.4389, + "step": 8916 + }, + { + "epoch": 0.76, + "learning_rate": 2.8647861611917303e-06, + "loss": 0.4446, + "step": 8917 + }, + { + "epoch": 0.76, + "learning_rate": 2.8628515661140856e-06, + "loss": 0.4605, + "step": 8918 + }, + { + "epoch": 0.76, + "learning_rate": 2.8609175153451775e-06, + "loss": 0.4721, + "step": 8919 + }, + { + "epoch": 0.76, + "learning_rate": 2.8589840090325028e-06, + "loss": 0.4704, + "step": 8920 + }, + { + "epoch": 0.76, + "learning_rate": 2.8570510473235214e-06, + "loss": 0.4442, + "step": 8921 + }, + { + "epoch": 0.76, + "learning_rate": 2.855118630365652e-06, + "loss": 0.4541, + "step": 8922 + }, + { + "epoch": 0.76, + "learning_rate": 2.8531867583062567e-06, + "loss": 0.4571, + "step": 8923 + }, + { + "epoch": 0.76, + "learning_rate": 2.851255431292681e-06, + "loss": 0.4655, + "step": 8924 + }, + { + "epoch": 0.76, + "learning_rate": 2.8493246494722136e-06, + "loss": 0.4777, + "step": 8925 + }, + { + "epoch": 0.76, + "learning_rate": 2.8473944129920985e-06, + "loss": 0.4571, + "step": 8926 + }, + { + "epoch": 0.76, + "learning_rate": 2.8454647219995467e-06, + "loss": 0.4512, + "step": 8927 + }, + { + "epoch": 0.76, + "learning_rate": 2.843535576641725e-06, + "loss": 0.4628, + "step": 8928 + }, + { + "epoch": 0.76, + "learning_rate": 2.841606977065757e-06, + "loss": 0.4564, + "step": 8929 + }, + { + "epoch": 0.76, + "learning_rate": 2.839678923418726e-06, + "loss": 0.4542, + "step": 8930 + }, + { + "epoch": 0.76, + "learning_rate": 2.837751415847678e-06, + "loss": 0.4552, + "step": 8931 + }, + { + "epoch": 0.76, + "learning_rate": 2.8358244544996038e-06, + "loss": 0.4351, + "step": 8932 + }, + { + "epoch": 0.76, + "learning_rate": 2.8338980395214643e-06, + "loss": 0.4699, + "step": 8933 + }, + { + "epoch": 0.76, + "learning_rate": 2.8319721710601843e-06, + "loss": 0.4771, + "step": 8934 + }, + { + "epoch": 0.76, + "learning_rate": 2.830046849262629e-06, + "loss": 0.459, + "step": 8935 + }, + { + "epoch": 0.76, + "learning_rate": 2.8281220742756333e-06, + "loss": 0.4416, + "step": 8936 + }, + { + "epoch": 0.76, + "learning_rate": 2.8261978462459917e-06, + "loss": 0.4561, + "step": 8937 + }, + { + "epoch": 0.76, + "learning_rate": 2.8242741653204508e-06, + "loss": 0.463, + "step": 8938 + }, + { + "epoch": 0.76, + "learning_rate": 2.8223510316457205e-06, + "loss": 0.4519, + "step": 8939 + }, + { + "epoch": 0.76, + "learning_rate": 2.820428445368468e-06, + "loss": 0.4593, + "step": 8940 + }, + { + "epoch": 0.76, + "learning_rate": 2.8185064066353153e-06, + "loss": 0.4539, + "step": 8941 + }, + { + "epoch": 0.76, + "learning_rate": 2.8165849155928416e-06, + "loss": 0.4595, + "step": 8942 + }, + { + "epoch": 0.76, + "learning_rate": 2.8146639723875977e-06, + "loss": 0.4684, + "step": 8943 + }, + { + "epoch": 0.76, + "learning_rate": 2.812743577166075e-06, + "loss": 0.4538, + "step": 8944 + }, + { + "epoch": 0.76, + "learning_rate": 2.810823730074732e-06, + "loss": 0.4637, + "step": 8945 + }, + { + "epoch": 0.76, + "learning_rate": 2.8089044312599857e-06, + "loss": 0.4672, + "step": 8946 + }, + { + "epoch": 0.76, + "learning_rate": 2.8069856808682093e-06, + "loss": 0.4651, + "step": 8947 + }, + { + "epoch": 0.76, + "learning_rate": 2.8050674790457355e-06, + "loss": 0.4473, + "step": 8948 + }, + { + "epoch": 0.76, + "learning_rate": 2.8031498259388535e-06, + "loss": 0.4549, + "step": 8949 + }, + { + "epoch": 0.76, + "learning_rate": 2.801232721693814e-06, + "loss": 0.4458, + "step": 8950 + }, + { + "epoch": 0.76, + "learning_rate": 2.799316166456816e-06, + "loss": 0.4386, + "step": 8951 + }, + { + "epoch": 0.76, + "learning_rate": 2.7974001603740343e-06, + "loss": 0.444, + "step": 8952 + }, + { + "epoch": 0.76, + "learning_rate": 2.7954847035915846e-06, + "loss": 0.4546, + "step": 8953 + }, + { + "epoch": 0.76, + "learning_rate": 2.7935697962555477e-06, + "loss": 0.5009, + "step": 8954 + }, + { + "epoch": 0.76, + "learning_rate": 2.7916554385119643e-06, + "loss": 0.4411, + "step": 8955 + }, + { + "epoch": 0.76, + "learning_rate": 2.7897416305068325e-06, + "loss": 0.4776, + "step": 8956 + }, + { + "epoch": 0.76, + "learning_rate": 2.7878283723861045e-06, + "loss": 0.4678, + "step": 8957 + }, + { + "epoch": 0.76, + "learning_rate": 2.7859156642956953e-06, + "loss": 0.4586, + "step": 8958 + }, + { + "epoch": 0.76, + "learning_rate": 2.7840035063814784e-06, + "loss": 0.4839, + "step": 8959 + }, + { + "epoch": 0.76, + "learning_rate": 2.7820918987892742e-06, + "loss": 0.4871, + "step": 8960 + }, + { + "epoch": 0.76, + "learning_rate": 2.7801808416648814e-06, + "loss": 0.4871, + "step": 8961 + }, + { + "epoch": 0.76, + "learning_rate": 2.778270335154036e-06, + "loss": 0.4467, + "step": 8962 + }, + { + "epoch": 0.76, + "learning_rate": 2.776360379402445e-06, + "loss": 0.4396, + "step": 8963 + }, + { + "epoch": 0.76, + "learning_rate": 2.774450974555769e-06, + "loss": 0.4697, + "step": 8964 + }, + { + "epoch": 0.76, + "learning_rate": 2.772542120759628e-06, + "loss": 0.4501, + "step": 8965 + }, + { + "epoch": 0.76, + "learning_rate": 2.7706338181595982e-06, + "loss": 0.4591, + "step": 8966 + }, + { + "epoch": 0.76, + "learning_rate": 2.768726066901216e-06, + "loss": 0.4576, + "step": 8967 + }, + { + "epoch": 0.76, + "learning_rate": 2.766818867129976e-06, + "loss": 0.4586, + "step": 8968 + }, + { + "epoch": 0.76, + "learning_rate": 2.7649122189913204e-06, + "loss": 0.4535, + "step": 8969 + }, + { + "epoch": 0.76, + "learning_rate": 2.7630061226306715e-06, + "loss": 0.4658, + "step": 8970 + }, + { + "epoch": 0.76, + "learning_rate": 2.761100578193385e-06, + "loss": 0.445, + "step": 8971 + }, + { + "epoch": 0.77, + "learning_rate": 2.759195585824791e-06, + "loss": 0.4533, + "step": 8972 + }, + { + "epoch": 0.77, + "learning_rate": 2.75729114567017e-06, + "loss": 0.4721, + "step": 8973 + }, + { + "epoch": 0.77, + "learning_rate": 2.755387257874764e-06, + "loss": 0.4496, + "step": 8974 + }, + { + "epoch": 0.77, + "learning_rate": 2.7534839225837716e-06, + "loss": 0.4489, + "step": 8975 + }, + { + "epoch": 0.77, + "learning_rate": 2.7515811399423486e-06, + "loss": 0.4745, + "step": 8976 + }, + { + "epoch": 0.77, + "learning_rate": 2.749678910095611e-06, + "loss": 0.4742, + "step": 8977 + }, + { + "epoch": 0.77, + "learning_rate": 2.7477772331886275e-06, + "loss": 0.4294, + "step": 8978 + }, + { + "epoch": 0.77, + "learning_rate": 2.745876109366429e-06, + "loss": 0.4613, + "step": 8979 + }, + { + "epoch": 0.77, + "learning_rate": 2.743975538774002e-06, + "loss": 0.4642, + "step": 8980 + }, + { + "epoch": 0.77, + "learning_rate": 2.7420755215562944e-06, + "loss": 0.4671, + "step": 8981 + }, + { + "epoch": 0.77, + "learning_rate": 2.740176057858208e-06, + "loss": 0.4622, + "step": 8982 + }, + { + "epoch": 0.77, + "learning_rate": 2.738277147824605e-06, + "loss": 0.4522, + "step": 8983 + }, + { + "epoch": 0.77, + "learning_rate": 2.7363787916003037e-06, + "loss": 0.4631, + "step": 8984 + }, + { + "epoch": 0.77, + "learning_rate": 2.7344809893300796e-06, + "loss": 0.4465, + "step": 8985 + }, + { + "epoch": 0.77, + "learning_rate": 2.732583741158671e-06, + "loss": 0.4843, + "step": 8986 + }, + { + "epoch": 0.77, + "learning_rate": 2.7306870472307645e-06, + "loss": 0.4494, + "step": 8987 + }, + { + "epoch": 0.77, + "learning_rate": 2.7287909076910114e-06, + "loss": 0.4534, + "step": 8988 + }, + { + "epoch": 0.77, + "learning_rate": 2.7268953226840213e-06, + "loss": 0.4683, + "step": 8989 + }, + { + "epoch": 0.77, + "learning_rate": 2.7250002923543575e-06, + "loss": 0.4573, + "step": 8990 + }, + { + "epoch": 0.77, + "learning_rate": 2.723105816846543e-06, + "loss": 0.4466, + "step": 8991 + }, + { + "epoch": 0.77, + "learning_rate": 2.721211896305059e-06, + "loss": 0.462, + "step": 8992 + }, + { + "epoch": 0.77, + "learning_rate": 2.7193185308743443e-06, + "loss": 0.4757, + "step": 8993 + }, + { + "epoch": 0.77, + "learning_rate": 2.7174257206987943e-06, + "loss": 0.4519, + "step": 8994 + }, + { + "epoch": 0.77, + "learning_rate": 2.715533465922766e-06, + "loss": 0.4613, + "step": 8995 + }, + { + "epoch": 0.77, + "learning_rate": 2.7136417666905646e-06, + "loss": 0.4566, + "step": 8996 + }, + { + "epoch": 0.77, + "learning_rate": 2.7117506231464606e-06, + "loss": 0.4771, + "step": 8997 + }, + { + "epoch": 0.77, + "learning_rate": 2.7098600354346826e-06, + "loss": 0.4494, + "step": 8998 + }, + { + "epoch": 0.77, + "learning_rate": 2.7079700036994128e-06, + "loss": 0.4638, + "step": 8999 + }, + { + "epoch": 0.77, + "learning_rate": 2.7060805280847947e-06, + "loss": 0.4599, + "step": 9000 + }, + { + "epoch": 0.77, + "learning_rate": 2.7041916087349264e-06, + "loss": 0.4475, + "step": 9001 + }, + { + "epoch": 0.77, + "learning_rate": 2.702303245793865e-06, + "loss": 0.4612, + "step": 9002 + }, + { + "epoch": 0.77, + "learning_rate": 2.700415439405625e-06, + "loss": 0.4478, + "step": 9003 + }, + { + "epoch": 0.77, + "learning_rate": 2.6985281897141815e-06, + "loss": 0.4417, + "step": 9004 + }, + { + "epoch": 0.77, + "learning_rate": 2.696641496863458e-06, + "loss": 0.453, + "step": 9005 + }, + { + "epoch": 0.77, + "learning_rate": 2.694755360997342e-06, + "loss": 0.4634, + "step": 9006 + }, + { + "epoch": 0.77, + "learning_rate": 2.6928697822596863e-06, + "loss": 0.4541, + "step": 9007 + }, + { + "epoch": 0.77, + "learning_rate": 2.690984760794284e-06, + "loss": 0.4571, + "step": 9008 + }, + { + "epoch": 0.77, + "learning_rate": 2.6891002967448986e-06, + "loss": 0.4585, + "step": 9009 + }, + { + "epoch": 0.77, + "learning_rate": 2.6872163902552494e-06, + "loss": 0.4494, + "step": 9010 + }, + { + "epoch": 0.77, + "learning_rate": 2.6853330414690016e-06, + "loss": 0.4605, + "step": 9011 + }, + { + "epoch": 0.77, + "learning_rate": 2.6834502505297975e-06, + "loss": 0.4566, + "step": 9012 + }, + { + "epoch": 0.77, + "learning_rate": 2.6815680175812266e-06, + "loss": 0.455, + "step": 9013 + }, + { + "epoch": 0.77, + "learning_rate": 2.6796863427668284e-06, + "loss": 0.4698, + "step": 9014 + }, + { + "epoch": 0.77, + "learning_rate": 2.677805226230108e-06, + "loss": 0.4569, + "step": 9015 + }, + { + "epoch": 0.77, + "learning_rate": 2.675924668114537e-06, + "loss": 0.4801, + "step": 9016 + }, + { + "epoch": 0.77, + "learning_rate": 2.6740446685635246e-06, + "loss": 0.4339, + "step": 9017 + }, + { + "epoch": 0.77, + "learning_rate": 2.67216522772045e-06, + "loss": 0.4612, + "step": 9018 + }, + { + "epoch": 0.77, + "learning_rate": 2.670286345728652e-06, + "loss": 0.4509, + "step": 9019 + }, + { + "epoch": 0.77, + "learning_rate": 2.6684080227314115e-06, + "loss": 0.4715, + "step": 9020 + }, + { + "epoch": 0.77, + "learning_rate": 2.6665302588719866e-06, + "loss": 0.4634, + "step": 9021 + }, + { + "epoch": 0.77, + "learning_rate": 2.664653054293583e-06, + "loss": 0.4485, + "step": 9022 + }, + { + "epoch": 0.77, + "learning_rate": 2.6627764091393594e-06, + "loss": 0.4647, + "step": 9023 + }, + { + "epoch": 0.77, + "learning_rate": 2.6609003235524355e-06, + "loss": 0.4643, + "step": 9024 + }, + { + "epoch": 0.77, + "learning_rate": 2.6590247976758988e-06, + "loss": 0.4521, + "step": 9025 + }, + { + "epoch": 0.77, + "learning_rate": 2.6571498316527756e-06, + "loss": 0.4538, + "step": 9026 + }, + { + "epoch": 0.77, + "learning_rate": 2.6552754256260614e-06, + "loss": 0.4474, + "step": 9027 + }, + { + "epoch": 0.77, + "learning_rate": 2.6534015797387103e-06, + "loss": 0.4624, + "step": 9028 + }, + { + "epoch": 0.77, + "learning_rate": 2.6515282941336197e-06, + "loss": 0.4697, + "step": 9029 + }, + { + "epoch": 0.77, + "learning_rate": 2.649655568953663e-06, + "loss": 0.4471, + "step": 9030 + }, + { + "epoch": 0.77, + "learning_rate": 2.647783404341663e-06, + "loss": 0.4595, + "step": 9031 + }, + { + "epoch": 0.77, + "learning_rate": 2.6459118004403915e-06, + "loss": 0.4501, + "step": 9032 + }, + { + "epoch": 0.77, + "learning_rate": 2.6440407573925887e-06, + "loss": 0.462, + "step": 9033 + }, + { + "epoch": 0.77, + "learning_rate": 2.6421702753409474e-06, + "loss": 0.4597, + "step": 9034 + }, + { + "epoch": 0.77, + "learning_rate": 2.640300354428119e-06, + "loss": 0.459, + "step": 9035 + }, + { + "epoch": 0.77, + "learning_rate": 2.6384309947967124e-06, + "loss": 0.4755, + "step": 9036 + }, + { + "epoch": 0.77, + "learning_rate": 2.636562196589294e-06, + "loss": 0.4556, + "step": 9037 + }, + { + "epoch": 0.77, + "learning_rate": 2.6346939599483776e-06, + "loss": 0.455, + "step": 9038 + }, + { + "epoch": 0.77, + "learning_rate": 2.632826285016453e-06, + "loss": 0.4748, + "step": 9039 + }, + { + "epoch": 0.77, + "learning_rate": 2.6309591719359563e-06, + "loss": 0.4471, + "step": 9040 + }, + { + "epoch": 0.77, + "learning_rate": 2.629092620849274e-06, + "loss": 0.4725, + "step": 9041 + }, + { + "epoch": 0.77, + "learning_rate": 2.6272266318987606e-06, + "loss": 0.4695, + "step": 9042 + }, + { + "epoch": 0.77, + "learning_rate": 2.6253612052267254e-06, + "loss": 0.4611, + "step": 9043 + }, + { + "epoch": 0.77, + "learning_rate": 2.623496340975433e-06, + "loss": 0.4645, + "step": 9044 + }, + { + "epoch": 0.77, + "learning_rate": 2.6216320392871055e-06, + "loss": 0.4606, + "step": 9045 + }, + { + "epoch": 0.77, + "learning_rate": 2.6197683003039253e-06, + "loss": 0.461, + "step": 9046 + }, + { + "epoch": 0.77, + "learning_rate": 2.61790512416802e-06, + "loss": 0.4812, + "step": 9047 + }, + { + "epoch": 0.77, + "learning_rate": 2.6160425110214915e-06, + "loss": 0.4764, + "step": 9048 + }, + { + "epoch": 0.77, + "learning_rate": 2.6141804610063926e-06, + "loss": 0.4786, + "step": 9049 + }, + { + "epoch": 0.77, + "learning_rate": 2.6123189742647227e-06, + "loss": 0.4533, + "step": 9050 + }, + { + "epoch": 0.77, + "learning_rate": 2.6104580509384514e-06, + "loss": 0.4555, + "step": 9051 + }, + { + "epoch": 0.77, + "learning_rate": 2.6085976911694986e-06, + "loss": 0.4497, + "step": 9052 + }, + { + "epoch": 0.77, + "learning_rate": 2.606737895099745e-06, + "loss": 0.4724, + "step": 9053 + }, + { + "epoch": 0.77, + "learning_rate": 2.6048786628710244e-06, + "loss": 0.4503, + "step": 9054 + }, + { + "epoch": 0.77, + "learning_rate": 2.6030199946251334e-06, + "loss": 0.4475, + "step": 9055 + }, + { + "epoch": 0.77, + "learning_rate": 2.601161890503817e-06, + "loss": 0.4588, + "step": 9056 + }, + { + "epoch": 0.77, + "learning_rate": 2.5993043506487812e-06, + "loss": 0.4777, + "step": 9057 + }, + { + "epoch": 0.77, + "learning_rate": 2.5974473752016984e-06, + "loss": 0.4613, + "step": 9058 + }, + { + "epoch": 0.77, + "learning_rate": 2.5955909643041797e-06, + "loss": 0.4543, + "step": 9059 + }, + { + "epoch": 0.77, + "learning_rate": 2.5937351180978077e-06, + "loss": 0.4765, + "step": 9060 + }, + { + "epoch": 0.77, + "learning_rate": 2.5918798367241147e-06, + "loss": 0.456, + "step": 9061 + }, + { + "epoch": 0.77, + "learning_rate": 2.590025120324594e-06, + "loss": 0.4559, + "step": 9062 + }, + { + "epoch": 0.77, + "learning_rate": 2.5881709690406933e-06, + "loss": 0.4647, + "step": 9063 + }, + { + "epoch": 0.77, + "learning_rate": 2.5863173830138212e-06, + "loss": 0.4664, + "step": 9064 + }, + { + "epoch": 0.77, + "learning_rate": 2.5844643623853327e-06, + "loss": 0.4693, + "step": 9065 + }, + { + "epoch": 0.77, + "learning_rate": 2.5826119072965494e-06, + "loss": 0.4408, + "step": 9066 + }, + { + "epoch": 0.77, + "learning_rate": 2.5807600178887536e-06, + "loss": 0.4609, + "step": 9067 + }, + { + "epoch": 0.77, + "learning_rate": 2.5789086943031704e-06, + "loss": 0.4532, + "step": 9068 + }, + { + "epoch": 0.77, + "learning_rate": 2.577057936680992e-06, + "loss": 0.4605, + "step": 9069 + }, + { + "epoch": 0.77, + "learning_rate": 2.575207745163366e-06, + "loss": 0.4667, + "step": 9070 + }, + { + "epoch": 0.77, + "learning_rate": 2.573358119891395e-06, + "loss": 0.4588, + "step": 9071 + }, + { + "epoch": 0.77, + "learning_rate": 2.5715090610061376e-06, + "loss": 0.4537, + "step": 9072 + }, + { + "epoch": 0.77, + "learning_rate": 2.5696605686486166e-06, + "loss": 0.4698, + "step": 9073 + }, + { + "epoch": 0.77, + "learning_rate": 2.567812642959798e-06, + "loss": 0.4588, + "step": 9074 + }, + { + "epoch": 0.77, + "learning_rate": 2.5659652840806125e-06, + "loss": 0.4423, + "step": 9075 + }, + { + "epoch": 0.77, + "learning_rate": 2.5641184921519568e-06, + "loss": 0.4588, + "step": 9076 + }, + { + "epoch": 0.77, + "learning_rate": 2.562272267314666e-06, + "loss": 0.4372, + "step": 9077 + }, + { + "epoch": 0.77, + "learning_rate": 2.5604266097095433e-06, + "loss": 0.4388, + "step": 9078 + }, + { + "epoch": 0.77, + "learning_rate": 2.5585815194773466e-06, + "loss": 0.4445, + "step": 9079 + }, + { + "epoch": 0.77, + "learning_rate": 2.5567369967587907e-06, + "loss": 0.461, + "step": 9080 + }, + { + "epoch": 0.77, + "learning_rate": 2.554893041694545e-06, + "loss": 0.4781, + "step": 9081 + }, + { + "epoch": 0.77, + "learning_rate": 2.5530496544252426e-06, + "loss": 0.4641, + "step": 9082 + }, + { + "epoch": 0.77, + "learning_rate": 2.55120683509146e-06, + "loss": 0.4695, + "step": 9083 + }, + { + "epoch": 0.77, + "learning_rate": 2.549364583833739e-06, + "loss": 0.4606, + "step": 9084 + }, + { + "epoch": 0.77, + "learning_rate": 2.5475229007925863e-06, + "loss": 0.4571, + "step": 9085 + }, + { + "epoch": 0.77, + "learning_rate": 2.545681786108447e-06, + "loss": 0.4563, + "step": 9086 + }, + { + "epoch": 0.77, + "learning_rate": 2.543841239921736e-06, + "loss": 0.463, + "step": 9087 + }, + { + "epoch": 0.77, + "learning_rate": 2.542001262372821e-06, + "loss": 0.4336, + "step": 9088 + }, + { + "epoch": 0.77, + "learning_rate": 2.5401618536020255e-06, + "loss": 0.4704, + "step": 9089 + }, + { + "epoch": 0.78, + "learning_rate": 2.5383230137496308e-06, + "loss": 0.4631, + "step": 9090 + }, + { + "epoch": 0.78, + "learning_rate": 2.536484742955878e-06, + "loss": 0.4746, + "step": 9091 + }, + { + "epoch": 0.78, + "learning_rate": 2.5346470413609547e-06, + "loss": 0.4745, + "step": 9092 + }, + { + "epoch": 0.78, + "learning_rate": 2.5328099091050117e-06, + "loss": 0.4609, + "step": 9093 + }, + { + "epoch": 0.78, + "learning_rate": 2.530973346328166e-06, + "loss": 0.4477, + "step": 9094 + }, + { + "epoch": 0.78, + "learning_rate": 2.5291373531704712e-06, + "loss": 0.4402, + "step": 9095 + }, + { + "epoch": 0.78, + "learning_rate": 2.5273019297719524e-06, + "loss": 0.4691, + "step": 9096 + }, + { + "epoch": 0.78, + "learning_rate": 2.5254670762725864e-06, + "loss": 0.4649, + "step": 9097 + }, + { + "epoch": 0.78, + "learning_rate": 2.523632792812306e-06, + "loss": 0.4491, + "step": 9098 + }, + { + "epoch": 0.78, + "learning_rate": 2.5217990795310023e-06, + "loss": 0.4578, + "step": 9099 + }, + { + "epoch": 0.78, + "learning_rate": 2.5199659365685235e-06, + "loss": 0.4518, + "step": 9100 + }, + { + "epoch": 0.78, + "learning_rate": 2.5181333640646676e-06, + "loss": 0.4506, + "step": 9101 + }, + { + "epoch": 0.78, + "learning_rate": 2.5163013621591948e-06, + "loss": 0.446, + "step": 9102 + }, + { + "epoch": 0.78, + "learning_rate": 2.5144699309918296e-06, + "loss": 0.4484, + "step": 9103 + }, + { + "epoch": 0.78, + "learning_rate": 2.512639070702235e-06, + "loss": 0.4688, + "step": 9104 + }, + { + "epoch": 0.78, + "learning_rate": 2.510808781430045e-06, + "loss": 0.4621, + "step": 9105 + }, + { + "epoch": 0.78, + "learning_rate": 2.5089790633148426e-06, + "loss": 0.4676, + "step": 9106 + }, + { + "epoch": 0.78, + "learning_rate": 2.507149916496171e-06, + "loss": 0.4747, + "step": 9107 + }, + { + "epoch": 0.78, + "learning_rate": 2.5053213411135293e-06, + "loss": 0.4594, + "step": 9108 + }, + { + "epoch": 0.78, + "learning_rate": 2.503493337306373e-06, + "loss": 0.4575, + "step": 9109 + }, + { + "epoch": 0.78, + "learning_rate": 2.50166590521411e-06, + "loss": 0.4553, + "step": 9110 + }, + { + "epoch": 0.78, + "learning_rate": 2.499839044976109e-06, + "loss": 0.4473, + "step": 9111 + }, + { + "epoch": 0.78, + "learning_rate": 2.4980127567316948e-06, + "loss": 0.4593, + "step": 9112 + }, + { + "epoch": 0.78, + "learning_rate": 2.4961870406201483e-06, + "loss": 0.4584, + "step": 9113 + }, + { + "epoch": 0.78, + "learning_rate": 2.494361896780705e-06, + "loss": 0.4459, + "step": 9114 + }, + { + "epoch": 0.78, + "learning_rate": 2.4925373253525584e-06, + "loss": 0.4743, + "step": 9115 + }, + { + "epoch": 0.78, + "learning_rate": 2.4907133264748585e-06, + "loss": 0.4455, + "step": 9116 + }, + { + "epoch": 0.78, + "learning_rate": 2.4888899002867094e-06, + "loss": 0.4507, + "step": 9117 + }, + { + "epoch": 0.78, + "learning_rate": 2.4870670469271783e-06, + "loss": 0.4421, + "step": 9118 + }, + { + "epoch": 0.78, + "learning_rate": 2.4852447665352773e-06, + "loss": 0.463, + "step": 9119 + }, + { + "epoch": 0.78, + "learning_rate": 2.4834230592499833e-06, + "loss": 0.4665, + "step": 9120 + }, + { + "epoch": 0.78, + "learning_rate": 2.4816019252102274e-06, + "loss": 0.4377, + "step": 9121 + }, + { + "epoch": 0.78, + "learning_rate": 2.4797813645548973e-06, + "loss": 0.454, + "step": 9122 + }, + { + "epoch": 0.78, + "learning_rate": 2.477961377422836e-06, + "loss": 0.4519, + "step": 9123 + }, + { + "epoch": 0.78, + "learning_rate": 2.476141963952844e-06, + "loss": 0.4658, + "step": 9124 + }, + { + "epoch": 0.78, + "learning_rate": 2.474323124283676e-06, + "loss": 0.4431, + "step": 9125 + }, + { + "epoch": 0.78, + "learning_rate": 2.4725048585540456e-06, + "loss": 0.4563, + "step": 9126 + }, + { + "epoch": 0.78, + "learning_rate": 2.470687166902622e-06, + "loss": 0.4411, + "step": 9127 + }, + { + "epoch": 0.78, + "learning_rate": 2.4688700494680317e-06, + "loss": 0.4721, + "step": 9128 + }, + { + "epoch": 0.78, + "learning_rate": 2.467053506388849e-06, + "loss": 0.4377, + "step": 9129 + }, + { + "epoch": 0.78, + "learning_rate": 2.4652375378036164e-06, + "loss": 0.44, + "step": 9130 + }, + { + "epoch": 0.78, + "learning_rate": 2.4634221438508242e-06, + "loss": 0.4547, + "step": 9131 + }, + { + "epoch": 0.78, + "learning_rate": 2.4616073246689254e-06, + "loss": 0.4403, + "step": 9132 + }, + { + "epoch": 0.78, + "learning_rate": 2.459793080396322e-06, + "loss": 0.4812, + "step": 9133 + }, + { + "epoch": 0.78, + "learning_rate": 2.4579794111713793e-06, + "loss": 0.4428, + "step": 9134 + }, + { + "epoch": 0.78, + "learning_rate": 2.4561663171324137e-06, + "loss": 0.4761, + "step": 9135 + }, + { + "epoch": 0.78, + "learning_rate": 2.454353798417698e-06, + "loss": 0.4536, + "step": 9136 + }, + { + "epoch": 0.78, + "learning_rate": 2.452541855165468e-06, + "loss": 0.4362, + "step": 9137 + }, + { + "epoch": 0.78, + "learning_rate": 2.4507304875139015e-06, + "loss": 0.4571, + "step": 9138 + }, + { + "epoch": 0.78, + "learning_rate": 2.4489196956011464e-06, + "loss": 0.4393, + "step": 9139 + }, + { + "epoch": 0.78, + "learning_rate": 2.4471094795652992e-06, + "loss": 0.479, + "step": 9140 + }, + { + "epoch": 0.78, + "learning_rate": 2.445299839544416e-06, + "loss": 0.4635, + "step": 9141 + }, + { + "epoch": 0.78, + "learning_rate": 2.443490775676507e-06, + "loss": 0.4633, + "step": 9142 + }, + { + "epoch": 0.78, + "learning_rate": 2.4416822880995416e-06, + "loss": 0.4642, + "step": 9143 + }, + { + "epoch": 0.78, + "learning_rate": 2.4398743769514344e-06, + "loss": 0.4611, + "step": 9144 + }, + { + "epoch": 0.78, + "learning_rate": 2.4380670423700726e-06, + "loss": 0.462, + "step": 9145 + }, + { + "epoch": 0.78, + "learning_rate": 2.4362602844932915e-06, + "loss": 0.4382, + "step": 9146 + }, + { + "epoch": 0.78, + "learning_rate": 2.4344541034588752e-06, + "loss": 0.4654, + "step": 9147 + }, + { + "epoch": 0.78, + "learning_rate": 2.432648499404575e-06, + "loss": 0.4695, + "step": 9148 + }, + { + "epoch": 0.78, + "learning_rate": 2.430843472468093e-06, + "loss": 0.4536, + "step": 9149 + }, + { + "epoch": 0.78, + "learning_rate": 2.4290390227870874e-06, + "loss": 0.4345, + "step": 9150 + }, + { + "epoch": 0.78, + "learning_rate": 2.4272351504991744e-06, + "loss": 0.4555, + "step": 9151 + }, + { + "epoch": 0.78, + "learning_rate": 2.4254318557419256e-06, + "loss": 0.4411, + "step": 9152 + }, + { + "epoch": 0.78, + "learning_rate": 2.423629138652862e-06, + "loss": 0.4462, + "step": 9153 + }, + { + "epoch": 0.78, + "learning_rate": 2.4218269993694733e-06, + "loss": 0.4592, + "step": 9154 + }, + { + "epoch": 0.78, + "learning_rate": 2.4200254380291975e-06, + "loss": 0.4657, + "step": 9155 + }, + { + "epoch": 0.78, + "learning_rate": 2.4182244547694256e-06, + "loss": 0.481, + "step": 9156 + }, + { + "epoch": 0.78, + "learning_rate": 2.416424049727509e-06, + "loss": 0.4479, + "step": 9157 + }, + { + "epoch": 0.78, + "learning_rate": 2.414624223040756e-06, + "loss": 0.4606, + "step": 9158 + }, + { + "epoch": 0.78, + "learning_rate": 2.4128249748464262e-06, + "loss": 0.4667, + "step": 9159 + }, + { + "epoch": 0.78, + "learning_rate": 2.4110263052817396e-06, + "loss": 0.4296, + "step": 9160 + }, + { + "epoch": 0.78, + "learning_rate": 2.409228214483873e-06, + "loss": 0.4583, + "step": 9161 + }, + { + "epoch": 0.78, + "learning_rate": 2.407430702589948e-06, + "loss": 0.4571, + "step": 9162 + }, + { + "epoch": 0.78, + "learning_rate": 2.405633769737059e-06, + "loss": 0.4581, + "step": 9163 + }, + { + "epoch": 0.78, + "learning_rate": 2.403837416062246e-06, + "loss": 0.4407, + "step": 9164 + }, + { + "epoch": 0.78, + "learning_rate": 2.402041641702502e-06, + "loss": 0.4563, + "step": 9165 + }, + { + "epoch": 0.78, + "learning_rate": 2.400246446794783e-06, + "loss": 0.4367, + "step": 9166 + }, + { + "epoch": 0.78, + "learning_rate": 2.3984518314759985e-06, + "loss": 0.462, + "step": 9167 + }, + { + "epoch": 0.78, + "learning_rate": 2.396657795883013e-06, + "loss": 0.4821, + "step": 9168 + }, + { + "epoch": 0.78, + "learning_rate": 2.3948643401526463e-06, + "loss": 0.4512, + "step": 9169 + }, + { + "epoch": 0.78, + "learning_rate": 2.393071464421678e-06, + "loss": 0.4596, + "step": 9170 + }, + { + "epoch": 0.78, + "learning_rate": 2.391279168826832e-06, + "loss": 0.4375, + "step": 9171 + }, + { + "epoch": 0.78, + "learning_rate": 2.389487453504806e-06, + "loss": 0.4629, + "step": 9172 + }, + { + "epoch": 0.78, + "learning_rate": 2.387696318592242e-06, + "loss": 0.4479, + "step": 9173 + }, + { + "epoch": 0.78, + "learning_rate": 2.3859057642257343e-06, + "loss": 0.4644, + "step": 9174 + }, + { + "epoch": 0.78, + "learning_rate": 2.384115790541841e-06, + "loss": 0.4608, + "step": 9175 + }, + { + "epoch": 0.78, + "learning_rate": 2.382326397677073e-06, + "loss": 0.4596, + "step": 9176 + }, + { + "epoch": 0.78, + "learning_rate": 2.380537585767897e-06, + "loss": 0.4831, + "step": 9177 + }, + { + "epoch": 0.78, + "learning_rate": 2.3787493549507346e-06, + "loss": 0.449, + "step": 9178 + }, + { + "epoch": 0.78, + "learning_rate": 2.3769617053619666e-06, + "loss": 0.4465, + "step": 9179 + }, + { + "epoch": 0.78, + "learning_rate": 2.3751746371379193e-06, + "loss": 0.4491, + "step": 9180 + }, + { + "epoch": 0.78, + "learning_rate": 2.373388150414889e-06, + "loss": 0.454, + "step": 9181 + }, + { + "epoch": 0.78, + "learning_rate": 2.371602245329121e-06, + "loss": 0.4425, + "step": 9182 + }, + { + "epoch": 0.78, + "learning_rate": 2.369816922016811e-06, + "loss": 0.4686, + "step": 9183 + }, + { + "epoch": 0.78, + "learning_rate": 2.3680321806141182e-06, + "loss": 0.4553, + "step": 9184 + }, + { + "epoch": 0.78, + "learning_rate": 2.3662480212571536e-06, + "loss": 0.4384, + "step": 9185 + }, + { + "epoch": 0.78, + "learning_rate": 2.364464444081984e-06, + "loss": 0.4366, + "step": 9186 + }, + { + "epoch": 0.78, + "learning_rate": 2.362681449224634e-06, + "loss": 0.452, + "step": 9187 + }, + { + "epoch": 0.78, + "learning_rate": 2.360899036821085e-06, + "loss": 0.4527, + "step": 9188 + }, + { + "epoch": 0.78, + "learning_rate": 2.3591172070072644e-06, + "loss": 0.4528, + "step": 9189 + }, + { + "epoch": 0.78, + "learning_rate": 2.3573359599190616e-06, + "loss": 0.4554, + "step": 9190 + }, + { + "epoch": 0.78, + "learning_rate": 2.355555295692332e-06, + "loss": 0.4667, + "step": 9191 + }, + { + "epoch": 0.78, + "learning_rate": 2.353775214462868e-06, + "loss": 0.4434, + "step": 9192 + }, + { + "epoch": 0.78, + "learning_rate": 2.3519957163664263e-06, + "loss": 0.4528, + "step": 9193 + }, + { + "epoch": 0.78, + "learning_rate": 2.350216801538723e-06, + "loss": 0.4495, + "step": 9194 + }, + { + "epoch": 0.78, + "learning_rate": 2.3484384701154216e-06, + "loss": 0.4591, + "step": 9195 + }, + { + "epoch": 0.78, + "learning_rate": 2.346660722232148e-06, + "loss": 0.4646, + "step": 9196 + }, + { + "epoch": 0.78, + "learning_rate": 2.344883558024481e-06, + "loss": 0.479, + "step": 9197 + }, + { + "epoch": 0.78, + "learning_rate": 2.3431069776279515e-06, + "loss": 0.4619, + "step": 9198 + }, + { + "epoch": 0.78, + "learning_rate": 2.341330981178046e-06, + "loss": 0.462, + "step": 9199 + }, + { + "epoch": 0.78, + "learning_rate": 2.339555568810221e-06, + "loss": 0.4798, + "step": 9200 + }, + { + "epoch": 0.78, + "learning_rate": 2.337780740659866e-06, + "loss": 0.4656, + "step": 9201 + }, + { + "epoch": 0.78, + "learning_rate": 2.336006496862342e-06, + "loss": 0.4697, + "step": 9202 + }, + { + "epoch": 0.78, + "learning_rate": 2.3342328375529567e-06, + "loss": 0.4662, + "step": 9203 + }, + { + "epoch": 0.78, + "learning_rate": 2.3324597628669798e-06, + "loss": 0.4717, + "step": 9204 + }, + { + "epoch": 0.78, + "learning_rate": 2.3306872729396323e-06, + "loss": 0.4693, + "step": 9205 + }, + { + "epoch": 0.78, + "learning_rate": 2.328915367906095e-06, + "loss": 0.4569, + "step": 9206 + }, + { + "epoch": 0.79, + "learning_rate": 2.327144047901495e-06, + "loss": 0.4818, + "step": 9207 + }, + { + "epoch": 0.79, + "learning_rate": 2.325373313060919e-06, + "loss": 0.4532, + "step": 9208 + }, + { + "epoch": 0.79, + "learning_rate": 2.323603163519421e-06, + "loss": 0.456, + "step": 9209 + }, + { + "epoch": 0.79, + "learning_rate": 2.3218335994119913e-06, + "loss": 0.4388, + "step": 9210 + }, + { + "epoch": 0.79, + "learning_rate": 2.3200646208735866e-06, + "loss": 0.4643, + "step": 9211 + }, + { + "epoch": 0.79, + "learning_rate": 2.318296228039116e-06, + "loss": 0.4592, + "step": 9212 + }, + { + "epoch": 0.79, + "learning_rate": 2.316528421043446e-06, + "loss": 0.4627, + "step": 9213 + }, + { + "epoch": 0.79, + "learning_rate": 2.3147612000213958e-06, + "loss": 0.4787, + "step": 9214 + }, + { + "epoch": 0.79, + "learning_rate": 2.3129945651077445e-06, + "loss": 0.4542, + "step": 9215 + }, + { + "epoch": 0.79, + "learning_rate": 2.3112285164372173e-06, + "loss": 0.4647, + "step": 9216 + }, + { + "epoch": 0.79, + "learning_rate": 2.3094630541444997e-06, + "loss": 0.4494, + "step": 9217 + }, + { + "epoch": 0.79, + "learning_rate": 2.3076981783642427e-06, + "loss": 0.4457, + "step": 9218 + }, + { + "epoch": 0.79, + "learning_rate": 2.3059338892310336e-06, + "loss": 0.4519, + "step": 9219 + }, + { + "epoch": 0.79, + "learning_rate": 2.3041701868794285e-06, + "loss": 0.4476, + "step": 9220 + }, + { + "epoch": 0.79, + "learning_rate": 2.302407071443936e-06, + "loss": 0.4583, + "step": 9221 + }, + { + "epoch": 0.79, + "learning_rate": 2.300644543059012e-06, + "loss": 0.4488, + "step": 9222 + }, + { + "epoch": 0.79, + "learning_rate": 2.2988826018590816e-06, + "loss": 0.4565, + "step": 9223 + }, + { + "epoch": 0.79, + "learning_rate": 2.2971212479785175e-06, + "loss": 0.4814, + "step": 9224 + }, + { + "epoch": 0.79, + "learning_rate": 2.2953604815516427e-06, + "loss": 0.4508, + "step": 9225 + }, + { + "epoch": 0.79, + "learning_rate": 2.2936003027127418e-06, + "loss": 0.447, + "step": 9226 + }, + { + "epoch": 0.79, + "learning_rate": 2.2918407115960594e-06, + "loss": 0.4666, + "step": 9227 + }, + { + "epoch": 0.79, + "learning_rate": 2.290081708335783e-06, + "loss": 0.4517, + "step": 9228 + }, + { + "epoch": 0.79, + "learning_rate": 2.2883232930660638e-06, + "loss": 0.4652, + "step": 9229 + }, + { + "epoch": 0.79, + "learning_rate": 2.2865654659210067e-06, + "loss": 0.4949, + "step": 9230 + }, + { + "epoch": 0.79, + "learning_rate": 2.284808227034666e-06, + "loss": 0.4434, + "step": 9231 + }, + { + "epoch": 0.79, + "learning_rate": 2.283051576541062e-06, + "loss": 0.4818, + "step": 9232 + }, + { + "epoch": 0.79, + "learning_rate": 2.2812955145741644e-06, + "loss": 0.4469, + "step": 9233 + }, + { + "epoch": 0.79, + "learning_rate": 2.2795400412678926e-06, + "loss": 0.441, + "step": 9234 + }, + { + "epoch": 0.79, + "learning_rate": 2.2777851567561272e-06, + "loss": 0.4437, + "step": 9235 + }, + { + "epoch": 0.79, + "learning_rate": 2.27603086117271e-06, + "loss": 0.4501, + "step": 9236 + }, + { + "epoch": 0.79, + "learning_rate": 2.274277154651424e-06, + "loss": 0.4637, + "step": 9237 + }, + { + "epoch": 0.79, + "learning_rate": 2.272524037326015e-06, + "loss": 0.4561, + "step": 9238 + }, + { + "epoch": 0.79, + "learning_rate": 2.2707715093301872e-06, + "loss": 0.4598, + "step": 9239 + }, + { + "epoch": 0.79, + "learning_rate": 2.269019570797588e-06, + "loss": 0.4426, + "step": 9240 + }, + { + "epoch": 0.79, + "learning_rate": 2.2672682218618337e-06, + "loss": 0.4496, + "step": 9241 + }, + { + "epoch": 0.79, + "learning_rate": 2.2655174626564914e-06, + "loss": 0.4335, + "step": 9242 + }, + { + "epoch": 0.79, + "learning_rate": 2.2637672933150756e-06, + "loss": 0.4738, + "step": 9243 + }, + { + "epoch": 0.79, + "learning_rate": 2.262017713971063e-06, + "loss": 0.4493, + "step": 9244 + }, + { + "epoch": 0.79, + "learning_rate": 2.2602687247578847e-06, + "loss": 0.4366, + "step": 9245 + }, + { + "epoch": 0.79, + "learning_rate": 2.258520325808926e-06, + "loss": 0.4611, + "step": 9246 + }, + { + "epoch": 0.79, + "learning_rate": 2.256772517257527e-06, + "loss": 0.4519, + "step": 9247 + }, + { + "epoch": 0.79, + "learning_rate": 2.2550252992369837e-06, + "loss": 0.4659, + "step": 9248 + }, + { + "epoch": 0.79, + "learning_rate": 2.2532786718805444e-06, + "loss": 0.4404, + "step": 9249 + }, + { + "epoch": 0.79, + "learning_rate": 2.251532635321415e-06, + "loss": 0.4711, + "step": 9250 + }, + { + "epoch": 0.79, + "learning_rate": 2.249787189692759e-06, + "loss": 0.4506, + "step": 9251 + }, + { + "epoch": 0.79, + "learning_rate": 2.248042335127685e-06, + "loss": 0.4539, + "step": 9252 + }, + { + "epoch": 0.79, + "learning_rate": 2.2462980717592662e-06, + "loss": 0.4761, + "step": 9253 + }, + { + "epoch": 0.79, + "learning_rate": 2.2445543997205277e-06, + "loss": 0.4632, + "step": 9254 + }, + { + "epoch": 0.79, + "learning_rate": 2.242811319144448e-06, + "loss": 0.4781, + "step": 9255 + }, + { + "epoch": 0.79, + "learning_rate": 2.2410688301639617e-06, + "loss": 0.4437, + "step": 9256 + }, + { + "epoch": 0.79, + "learning_rate": 2.2393269329119603e-06, + "loss": 0.4647, + "step": 9257 + }, + { + "epoch": 0.79, + "learning_rate": 2.237585627521286e-06, + "loss": 0.4539, + "step": 9258 + }, + { + "epoch": 0.79, + "learning_rate": 2.2358449141247395e-06, + "loss": 0.464, + "step": 9259 + }, + { + "epoch": 0.79, + "learning_rate": 2.2341047928550763e-06, + "loss": 0.4798, + "step": 9260 + }, + { + "epoch": 0.79, + "learning_rate": 2.2323652638450012e-06, + "loss": 0.4634, + "step": 9261 + }, + { + "epoch": 0.79, + "learning_rate": 2.2306263272271787e-06, + "loss": 0.4559, + "step": 9262 + }, + { + "epoch": 0.79, + "learning_rate": 2.2288879831342302e-06, + "loss": 0.457, + "step": 9263 + }, + { + "epoch": 0.79, + "learning_rate": 2.227150231698727e-06, + "loss": 0.4688, + "step": 9264 + }, + { + "epoch": 0.79, + "learning_rate": 2.2254130730531977e-06, + "loss": 0.4599, + "step": 9265 + }, + { + "epoch": 0.79, + "learning_rate": 2.2236765073301247e-06, + "loss": 0.4638, + "step": 9266 + }, + { + "epoch": 0.79, + "learning_rate": 2.2219405346619505e-06, + "loss": 0.4407, + "step": 9267 + }, + { + "epoch": 0.79, + "learning_rate": 2.2202051551810568e-06, + "loss": 0.4461, + "step": 9268 + }, + { + "epoch": 0.79, + "learning_rate": 2.218470369019804e-06, + "loss": 0.4681, + "step": 9269 + }, + { + "epoch": 0.79, + "learning_rate": 2.2167361763104844e-06, + "loss": 0.4531, + "step": 9270 + }, + { + "epoch": 0.79, + "learning_rate": 2.215002577185359e-06, + "loss": 0.4658, + "step": 9271 + }, + { + "epoch": 0.79, + "learning_rate": 2.213269571776637e-06, + "loss": 0.4593, + "step": 9272 + }, + { + "epoch": 0.79, + "learning_rate": 2.211537160216487e-06, + "loss": 0.4674, + "step": 9273 + }, + { + "epoch": 0.79, + "learning_rate": 2.209805342637029e-06, + "loss": 0.4637, + "step": 9274 + }, + { + "epoch": 0.79, + "learning_rate": 2.208074119170339e-06, + "loss": 0.4644, + "step": 9275 + }, + { + "epoch": 0.79, + "learning_rate": 2.206343489948449e-06, + "loss": 0.4714, + "step": 9276 + }, + { + "epoch": 0.79, + "learning_rate": 2.204613455103337e-06, + "loss": 0.4525, + "step": 9277 + }, + { + "epoch": 0.79, + "learning_rate": 2.2028840147669527e-06, + "loss": 0.4515, + "step": 9278 + }, + { + "epoch": 0.79, + "learning_rate": 2.201155169071184e-06, + "loss": 0.4359, + "step": 9279 + }, + { + "epoch": 0.79, + "learning_rate": 2.19942691814788e-06, + "loss": 0.4573, + "step": 9280 + }, + { + "epoch": 0.79, + "learning_rate": 2.1976992621288462e-06, + "loss": 0.4435, + "step": 9281 + }, + { + "epoch": 0.79, + "learning_rate": 2.1959722011458397e-06, + "loss": 0.4567, + "step": 9282 + }, + { + "epoch": 0.79, + "learning_rate": 2.1942457353305746e-06, + "loss": 0.4406, + "step": 9283 + }, + { + "epoch": 0.79, + "learning_rate": 2.192519864814717e-06, + "loss": 0.4613, + "step": 9284 + }, + { + "epoch": 0.79, + "learning_rate": 2.1907945897298934e-06, + "loss": 0.455, + "step": 9285 + }, + { + "epoch": 0.79, + "learning_rate": 2.1890699102076707e-06, + "loss": 0.4547, + "step": 9286 + }, + { + "epoch": 0.79, + "learning_rate": 2.187345826379592e-06, + "loss": 0.4761, + "step": 9287 + }, + { + "epoch": 0.79, + "learning_rate": 2.185622338377135e-06, + "loss": 0.4687, + "step": 9288 + }, + { + "epoch": 0.79, + "learning_rate": 2.183899446331742e-06, + "loss": 0.4569, + "step": 9289 + }, + { + "epoch": 0.79, + "learning_rate": 2.182177150374809e-06, + "loss": 0.4385, + "step": 9290 + }, + { + "epoch": 0.79, + "learning_rate": 2.180455450637684e-06, + "loss": 0.4512, + "step": 9291 + }, + { + "epoch": 0.79, + "learning_rate": 2.178734347251673e-06, + "loss": 0.4599, + "step": 9292 + }, + { + "epoch": 0.79, + "learning_rate": 2.1770138403480334e-06, + "loss": 0.4338, + "step": 9293 + }, + { + "epoch": 0.79, + "learning_rate": 2.17529393005798e-06, + "loss": 0.4587, + "step": 9294 + }, + { + "epoch": 0.79, + "learning_rate": 2.173574616512675e-06, + "loss": 0.4437, + "step": 9295 + }, + { + "epoch": 0.79, + "learning_rate": 2.171855899843248e-06, + "loss": 0.447, + "step": 9296 + }, + { + "epoch": 0.79, + "learning_rate": 2.1701377801807687e-06, + "loss": 0.4574, + "step": 9297 + }, + { + "epoch": 0.79, + "learning_rate": 2.1684202576562718e-06, + "loss": 0.489, + "step": 9298 + }, + { + "epoch": 0.79, + "learning_rate": 2.166703332400741e-06, + "loss": 0.4626, + "step": 9299 + }, + { + "epoch": 0.79, + "learning_rate": 2.164987004545118e-06, + "loss": 0.4477, + "step": 9300 + }, + { + "epoch": 0.79, + "learning_rate": 2.1632712742202966e-06, + "loss": 0.4506, + "step": 9301 + }, + { + "epoch": 0.79, + "learning_rate": 2.161556141557125e-06, + "loss": 0.4438, + "step": 9302 + }, + { + "epoch": 0.79, + "learning_rate": 2.1598416066864092e-06, + "loss": 0.4469, + "step": 9303 + }, + { + "epoch": 0.79, + "learning_rate": 2.1581276697388974e-06, + "loss": 0.4753, + "step": 9304 + }, + { + "epoch": 0.79, + "learning_rate": 2.156414330845312e-06, + "loss": 0.4514, + "step": 9305 + }, + { + "epoch": 0.79, + "learning_rate": 2.154701590136319e-06, + "loss": 0.4592, + "step": 9306 + }, + { + "epoch": 0.79, + "learning_rate": 2.1529894477425327e-06, + "loss": 0.4607, + "step": 9307 + }, + { + "epoch": 0.79, + "learning_rate": 2.1512779037945318e-06, + "loss": 0.4517, + "step": 9308 + }, + { + "epoch": 0.79, + "learning_rate": 2.149566958422845e-06, + "loss": 0.4652, + "step": 9309 + }, + { + "epoch": 0.79, + "learning_rate": 2.147856611757957e-06, + "loss": 0.461, + "step": 9310 + }, + { + "epoch": 0.79, + "learning_rate": 2.146146863930304e-06, + "loss": 0.4541, + "step": 9311 + }, + { + "epoch": 0.79, + "learning_rate": 2.1444377150702845e-06, + "loss": 0.457, + "step": 9312 + }, + { + "epoch": 0.79, + "learning_rate": 2.1427291653082337e-06, + "loss": 0.4875, + "step": 9313 + }, + { + "epoch": 0.79, + "learning_rate": 2.1410212147744634e-06, + "loss": 0.4579, + "step": 9314 + }, + { + "epoch": 0.79, + "learning_rate": 2.1393138635992296e-06, + "loss": 0.4781, + "step": 9315 + }, + { + "epoch": 0.79, + "learning_rate": 2.137607111912734e-06, + "loss": 0.4369, + "step": 9316 + }, + { + "epoch": 0.79, + "learning_rate": 2.135900959845144e-06, + "loss": 0.4767, + "step": 9317 + }, + { + "epoch": 0.79, + "learning_rate": 2.134195407526579e-06, + "loss": 0.4816, + "step": 9318 + }, + { + "epoch": 0.79, + "learning_rate": 2.1324904550871107e-06, + "loss": 0.4508, + "step": 9319 + }, + { + "epoch": 0.79, + "learning_rate": 2.1307861026567667e-06, + "loss": 0.4547, + "step": 9320 + }, + { + "epoch": 0.79, + "learning_rate": 2.12908235036553e-06, + "loss": 0.4423, + "step": 9321 + }, + { + "epoch": 0.79, + "learning_rate": 2.12737919834333e-06, + "loss": 0.4688, + "step": 9322 + }, + { + "epoch": 0.79, + "learning_rate": 2.1256766467200572e-06, + "loss": 0.4788, + "step": 9323 + }, + { + "epoch": 0.8, + "learning_rate": 2.1239746956255636e-06, + "loss": 0.4802, + "step": 9324 + }, + { + "epoch": 0.8, + "learning_rate": 2.122273345189638e-06, + "loss": 0.447, + "step": 9325 + }, + { + "epoch": 0.8, + "learning_rate": 2.1205725955420353e-06, + "loss": 0.4463, + "step": 9326 + }, + { + "epoch": 0.8, + "learning_rate": 2.1188724468124634e-06, + "loss": 0.4519, + "step": 9327 + }, + { + "epoch": 0.8, + "learning_rate": 2.1171728991305797e-06, + "loss": 0.425, + "step": 9328 + }, + { + "epoch": 0.8, + "learning_rate": 2.1154739526260017e-06, + "loss": 0.4693, + "step": 9329 + }, + { + "epoch": 0.8, + "learning_rate": 2.113775607428299e-06, + "loss": 0.4472, + "step": 9330 + }, + { + "epoch": 0.8, + "learning_rate": 2.1120778636669905e-06, + "loss": 0.4614, + "step": 9331 + }, + { + "epoch": 0.8, + "learning_rate": 2.110380721471551e-06, + "loss": 0.4521, + "step": 9332 + }, + { + "epoch": 0.8, + "learning_rate": 2.108684180971423e-06, + "loss": 0.452, + "step": 9333 + }, + { + "epoch": 0.8, + "learning_rate": 2.106988242295981e-06, + "loss": 0.4637, + "step": 9334 + }, + { + "epoch": 0.8, + "learning_rate": 2.1052929055745687e-06, + "loss": 0.4535, + "step": 9335 + }, + { + "epoch": 0.8, + "learning_rate": 2.1035981709364784e-06, + "loss": 0.4494, + "step": 9336 + }, + { + "epoch": 0.8, + "learning_rate": 2.101904038510958e-06, + "loss": 0.4616, + "step": 9337 + }, + { + "epoch": 0.8, + "learning_rate": 2.1002105084272085e-06, + "loss": 0.4648, + "step": 9338 + }, + { + "epoch": 0.8, + "learning_rate": 2.0985175808143897e-06, + "loss": 0.4693, + "step": 9339 + }, + { + "epoch": 0.8, + "learning_rate": 2.0968252558016055e-06, + "loss": 0.4628, + "step": 9340 + }, + { + "epoch": 0.8, + "learning_rate": 2.095133533517919e-06, + "loss": 0.4482, + "step": 9341 + }, + { + "epoch": 0.8, + "learning_rate": 2.093442414092356e-06, + "loss": 0.459, + "step": 9342 + }, + { + "epoch": 0.8, + "learning_rate": 2.091751897653881e-06, + "loss": 0.4564, + "step": 9343 + }, + { + "epoch": 0.8, + "learning_rate": 2.090061984331423e-06, + "loss": 0.4641, + "step": 9344 + }, + { + "epoch": 0.8, + "learning_rate": 2.0883726742538625e-06, + "loss": 0.4462, + "step": 9345 + }, + { + "epoch": 0.8, + "learning_rate": 2.086683967550027e-06, + "loss": 0.4473, + "step": 9346 + }, + { + "epoch": 0.8, + "learning_rate": 2.0849958643487122e-06, + "loss": 0.4616, + "step": 9347 + }, + { + "epoch": 0.8, + "learning_rate": 2.08330836477866e-06, + "loss": 0.448, + "step": 9348 + }, + { + "epoch": 0.8, + "learning_rate": 2.0816214689685598e-06, + "loss": 0.4605, + "step": 9349 + }, + { + "epoch": 0.8, + "learning_rate": 2.079935177047061e-06, + "loss": 0.4576, + "step": 9350 + }, + { + "epoch": 0.8, + "learning_rate": 2.0782494891427773e-06, + "loss": 0.4576, + "step": 9351 + }, + { + "epoch": 0.8, + "learning_rate": 2.0765644053842583e-06, + "loss": 0.4629, + "step": 9352 + }, + { + "epoch": 0.8, + "learning_rate": 2.074879925900015e-06, + "loss": 0.448, + "step": 9353 + }, + { + "epoch": 0.8, + "learning_rate": 2.073196050818519e-06, + "loss": 0.4535, + "step": 9354 + }, + { + "epoch": 0.8, + "learning_rate": 2.07151278026818e-06, + "loss": 0.4597, + "step": 9355 + }, + { + "epoch": 0.8, + "learning_rate": 2.0698301143773793e-06, + "loss": 0.4399, + "step": 9356 + }, + { + "epoch": 0.8, + "learning_rate": 2.0681480532744436e-06, + "loss": 0.4579, + "step": 9357 + }, + { + "epoch": 0.8, + "learning_rate": 2.0664665970876496e-06, + "loss": 0.4672, + "step": 9358 + }, + { + "epoch": 0.8, + "learning_rate": 2.0647857459452324e-06, + "loss": 0.4553, + "step": 9359 + }, + { + "epoch": 0.8, + "learning_rate": 2.0631054999753876e-06, + "loss": 0.4492, + "step": 9360 + }, + { + "epoch": 0.8, + "learning_rate": 2.0614258593062496e-06, + "loss": 0.4681, + "step": 9361 + }, + { + "epoch": 0.8, + "learning_rate": 2.059746824065919e-06, + "loss": 0.471, + "step": 9362 + }, + { + "epoch": 0.8, + "learning_rate": 2.0580683943824474e-06, + "loss": 0.4671, + "step": 9363 + }, + { + "epoch": 0.8, + "learning_rate": 2.0563905703838315e-06, + "loss": 0.4592, + "step": 9364 + }, + { + "epoch": 0.8, + "learning_rate": 2.054713352198037e-06, + "loss": 0.4687, + "step": 9365 + }, + { + "epoch": 0.8, + "learning_rate": 2.053036739952976e-06, + "loss": 0.4611, + "step": 9366 + }, + { + "epoch": 0.8, + "learning_rate": 2.0513607337765074e-06, + "loss": 0.4511, + "step": 9367 + }, + { + "epoch": 0.8, + "learning_rate": 2.0496853337964508e-06, + "loss": 0.4661, + "step": 9368 + }, + { + "epoch": 0.8, + "learning_rate": 2.0480105401405882e-06, + "loss": 0.4596, + "step": 9369 + }, + { + "epoch": 0.8, + "learning_rate": 2.0463363529366375e-06, + "loss": 0.4696, + "step": 9370 + }, + { + "epoch": 0.8, + "learning_rate": 2.0446627723122826e-06, + "loss": 0.4424, + "step": 9371 + }, + { + "epoch": 0.8, + "learning_rate": 2.0429897983951585e-06, + "loss": 0.4759, + "step": 9372 + }, + { + "epoch": 0.8, + "learning_rate": 2.0413174313128483e-06, + "loss": 0.4473, + "step": 9373 + }, + { + "epoch": 0.8, + "learning_rate": 2.039645671192898e-06, + "loss": 0.4675, + "step": 9374 + }, + { + "epoch": 0.8, + "learning_rate": 2.0379745181628064e-06, + "loss": 0.4592, + "step": 9375 + }, + { + "epoch": 0.8, + "learning_rate": 2.0363039723500155e-06, + "loss": 0.4586, + "step": 9376 + }, + { + "epoch": 0.8, + "learning_rate": 2.0346340338819316e-06, + "loss": 0.4529, + "step": 9377 + }, + { + "epoch": 0.8, + "learning_rate": 2.03296470288591e-06, + "loss": 0.4553, + "step": 9378 + }, + { + "epoch": 0.8, + "learning_rate": 2.0312959794892618e-06, + "loss": 0.4675, + "step": 9379 + }, + { + "epoch": 0.8, + "learning_rate": 2.0296278638192502e-06, + "loss": 0.4522, + "step": 9380 + }, + { + "epoch": 0.8, + "learning_rate": 2.027960356003096e-06, + "loss": 0.4567, + "step": 9381 + }, + { + "epoch": 0.8, + "learning_rate": 2.0262934561679615e-06, + "loss": 0.4598, + "step": 9382 + }, + { + "epoch": 0.8, + "learning_rate": 2.0246271644409797e-06, + "loss": 0.4842, + "step": 9383 + }, + { + "epoch": 0.8, + "learning_rate": 2.0229614809492304e-06, + "loss": 0.4418, + "step": 9384 + }, + { + "epoch": 0.8, + "learning_rate": 2.021296405819738e-06, + "loss": 0.4419, + "step": 9385 + }, + { + "epoch": 0.8, + "learning_rate": 2.0196319391794927e-06, + "loss": 0.4529, + "step": 9386 + }, + { + "epoch": 0.8, + "learning_rate": 2.0179680811554324e-06, + "loss": 0.4563, + "step": 9387 + }, + { + "epoch": 0.8, + "learning_rate": 2.016304831874449e-06, + "loss": 0.459, + "step": 9388 + }, + { + "epoch": 0.8, + "learning_rate": 2.014642191463392e-06, + "loss": 0.4517, + "step": 9389 + }, + { + "epoch": 0.8, + "learning_rate": 2.0129801600490606e-06, + "loss": 0.4634, + "step": 9390 + }, + { + "epoch": 0.8, + "learning_rate": 2.0113187377582023e-06, + "loss": 0.4708, + "step": 9391 + }, + { + "epoch": 0.8, + "learning_rate": 2.009657924717532e-06, + "loss": 0.4502, + "step": 9392 + }, + { + "epoch": 0.8, + "learning_rate": 2.0079977210537084e-06, + "loss": 0.4507, + "step": 9393 + }, + { + "epoch": 0.8, + "learning_rate": 2.0063381268933426e-06, + "loss": 0.4631, + "step": 9394 + }, + { + "epoch": 0.8, + "learning_rate": 2.004679142363003e-06, + "loss": 0.459, + "step": 9395 + }, + { + "epoch": 0.8, + "learning_rate": 2.003020767589212e-06, + "loss": 0.441, + "step": 9396 + }, + { + "epoch": 0.8, + "learning_rate": 2.0013630026984433e-06, + "loss": 0.4492, + "step": 9397 + }, + { + "epoch": 0.8, + "learning_rate": 1.999705847817126e-06, + "loss": 0.4739, + "step": 9398 + }, + { + "epoch": 0.8, + "learning_rate": 1.998049303071643e-06, + "loss": 0.4593, + "step": 9399 + }, + { + "epoch": 0.8, + "learning_rate": 1.996393368588325e-06, + "loss": 0.4443, + "step": 9400 + }, + { + "epoch": 0.8, + "learning_rate": 1.9947380444934595e-06, + "loss": 0.4505, + "step": 9401 + }, + { + "epoch": 0.8, + "learning_rate": 1.993083330913298e-06, + "loss": 0.4556, + "step": 9402 + }, + { + "epoch": 0.8, + "learning_rate": 1.9914292279740256e-06, + "loss": 0.455, + "step": 9403 + }, + { + "epoch": 0.8, + "learning_rate": 1.9897757358017956e-06, + "loss": 0.473, + "step": 9404 + }, + { + "epoch": 0.8, + "learning_rate": 1.9881228545227106e-06, + "loss": 0.4558, + "step": 9405 + }, + { + "epoch": 0.8, + "learning_rate": 1.986470584262824e-06, + "loss": 0.4535, + "step": 9406 + }, + { + "epoch": 0.8, + "learning_rate": 1.9848189251481465e-06, + "loss": 0.4525, + "step": 9407 + }, + { + "epoch": 0.8, + "learning_rate": 1.9831678773046424e-06, + "loss": 0.4699, + "step": 9408 + }, + { + "epoch": 0.8, + "learning_rate": 1.9815174408582237e-06, + "loss": 0.4786, + "step": 9409 + }, + { + "epoch": 0.8, + "learning_rate": 1.9798676159347574e-06, + "loss": 0.4519, + "step": 9410 + }, + { + "epoch": 0.8, + "learning_rate": 1.978218402660076e-06, + "loss": 0.4524, + "step": 9411 + }, + { + "epoch": 0.8, + "learning_rate": 1.9765698011599464e-06, + "loss": 0.4746, + "step": 9412 + }, + { + "epoch": 0.8, + "learning_rate": 1.9749218115601e-06, + "loss": 0.4575, + "step": 9413 + }, + { + "epoch": 0.8, + "learning_rate": 1.9732744339862197e-06, + "loss": 0.4603, + "step": 9414 + }, + { + "epoch": 0.8, + "learning_rate": 1.9716276685639426e-06, + "loss": 0.4594, + "step": 9415 + }, + { + "epoch": 0.8, + "learning_rate": 1.9699815154188563e-06, + "loss": 0.4591, + "step": 9416 + }, + { + "epoch": 0.8, + "learning_rate": 1.9683359746765063e-06, + "loss": 0.4641, + "step": 9417 + }, + { + "epoch": 0.8, + "learning_rate": 1.9666910464623844e-06, + "loss": 0.4524, + "step": 9418 + }, + { + "epoch": 0.8, + "learning_rate": 1.965046730901938e-06, + "loss": 0.4469, + "step": 9419 + }, + { + "epoch": 0.8, + "learning_rate": 1.9634030281205786e-06, + "loss": 0.4652, + "step": 9420 + }, + { + "epoch": 0.8, + "learning_rate": 1.9617599382436526e-06, + "loss": 0.4726, + "step": 9421 + }, + { + "epoch": 0.8, + "learning_rate": 1.960117461396472e-06, + "loss": 0.4701, + "step": 9422 + }, + { + "epoch": 0.8, + "learning_rate": 1.9584755977043014e-06, + "loss": 0.4558, + "step": 9423 + }, + { + "epoch": 0.8, + "learning_rate": 1.9568343472923524e-06, + "loss": 0.4593, + "step": 9424 + }, + { + "epoch": 0.8, + "learning_rate": 1.9551937102857955e-06, + "loss": 0.4488, + "step": 9425 + }, + { + "epoch": 0.8, + "learning_rate": 1.9535536868097526e-06, + "loss": 0.4398, + "step": 9426 + }, + { + "epoch": 0.8, + "learning_rate": 1.9519142769893006e-06, + "loss": 0.4689, + "step": 9427 + }, + { + "epoch": 0.8, + "learning_rate": 1.9502754809494606e-06, + "loss": 0.4578, + "step": 9428 + }, + { + "epoch": 0.8, + "learning_rate": 1.9486372988152246e-06, + "loss": 0.46, + "step": 9429 + }, + { + "epoch": 0.8, + "learning_rate": 1.9469997307115185e-06, + "loss": 0.4663, + "step": 9430 + }, + { + "epoch": 0.8, + "learning_rate": 1.9453627767632344e-06, + "loss": 0.4568, + "step": 9431 + }, + { + "epoch": 0.8, + "learning_rate": 1.94372643709521e-06, + "loss": 0.4572, + "step": 9432 + }, + { + "epoch": 0.8, + "learning_rate": 1.9420907118322428e-06, + "loss": 0.4527, + "step": 9433 + }, + { + "epoch": 0.8, + "learning_rate": 1.9404556010990792e-06, + "loss": 0.4484, + "step": 9434 + }, + { + "epoch": 0.8, + "learning_rate": 1.9388211050204175e-06, + "loss": 0.4733, + "step": 9435 + }, + { + "epoch": 0.8, + "learning_rate": 1.9371872237209167e-06, + "loss": 0.4445, + "step": 9436 + }, + { + "epoch": 0.8, + "learning_rate": 1.9355539573251737e-06, + "loss": 0.4551, + "step": 9437 + }, + { + "epoch": 0.8, + "learning_rate": 1.9339213059577587e-06, + "loss": 0.4505, + "step": 9438 + }, + { + "epoch": 0.8, + "learning_rate": 1.9322892697431783e-06, + "loss": 0.4513, + "step": 9439 + }, + { + "epoch": 0.8, + "learning_rate": 1.9306578488058993e-06, + "loss": 0.4682, + "step": 9440 + }, + { + "epoch": 0.8, + "learning_rate": 1.9290270432703408e-06, + "loss": 0.439, + "step": 9441 + }, + { + "epoch": 0.81, + "learning_rate": 1.9273968532608754e-06, + "loss": 0.4409, + "step": 9442 + }, + { + "epoch": 0.81, + "learning_rate": 1.925767278901828e-06, + "loss": 0.4516, + "step": 9443 + }, + { + "epoch": 0.81, + "learning_rate": 1.924138320317477e-06, + "loss": 0.4567, + "step": 9444 + }, + { + "epoch": 0.81, + "learning_rate": 1.9225099776320567e-06, + "loss": 0.4832, + "step": 9445 + }, + { + "epoch": 0.81, + "learning_rate": 1.920882250969742e-06, + "loss": 0.4588, + "step": 9446 + }, + { + "epoch": 0.81, + "learning_rate": 1.9192551404546812e-06, + "loss": 0.4671, + "step": 9447 + }, + { + "epoch": 0.81, + "learning_rate": 1.9176286462109574e-06, + "loss": 0.4322, + "step": 9448 + }, + { + "epoch": 0.81, + "learning_rate": 1.916002768362616e-06, + "loss": 0.4507, + "step": 9449 + }, + { + "epoch": 0.81, + "learning_rate": 1.9143775070336523e-06, + "loss": 0.474, + "step": 9450 + }, + { + "epoch": 0.81, + "learning_rate": 1.9127528623480175e-06, + "loss": 0.4534, + "step": 9451 + }, + { + "epoch": 0.81, + "learning_rate": 1.911128834429612e-06, + "loss": 0.4558, + "step": 9452 + }, + { + "epoch": 0.81, + "learning_rate": 1.9095054234022915e-06, + "loss": 0.4647, + "step": 9453 + }, + { + "epoch": 0.81, + "learning_rate": 1.9078826293898676e-06, + "loss": 0.4459, + "step": 9454 + }, + { + "epoch": 0.81, + "learning_rate": 1.9062604525160944e-06, + "loss": 0.4395, + "step": 9455 + }, + { + "epoch": 0.81, + "learning_rate": 1.90463889290469e-06, + "loss": 0.4563, + "step": 9456 + }, + { + "epoch": 0.81, + "learning_rate": 1.9030179506793201e-06, + "loss": 0.4521, + "step": 9457 + }, + { + "epoch": 0.81, + "learning_rate": 1.9013976259636057e-06, + "loss": 0.4436, + "step": 9458 + }, + { + "epoch": 0.81, + "learning_rate": 1.8997779188811194e-06, + "loss": 0.4585, + "step": 9459 + }, + { + "epoch": 0.81, + "learning_rate": 1.8981588295553855e-06, + "loss": 0.4432, + "step": 9460 + }, + { + "epoch": 0.81, + "learning_rate": 1.896540358109884e-06, + "loss": 0.4378, + "step": 9461 + }, + { + "epoch": 0.81, + "learning_rate": 1.8949225046680464e-06, + "loss": 0.4632, + "step": 9462 + }, + { + "epoch": 0.81, + "learning_rate": 1.893305269353257e-06, + "loss": 0.4764, + "step": 9463 + }, + { + "epoch": 0.81, + "learning_rate": 1.891688652288851e-06, + "loss": 0.463, + "step": 9464 + }, + { + "epoch": 0.81, + "learning_rate": 1.8900726535981195e-06, + "loss": 0.4429, + "step": 9465 + }, + { + "epoch": 0.81, + "learning_rate": 1.888457273404305e-06, + "loss": 0.477, + "step": 9466 + }, + { + "epoch": 0.81, + "learning_rate": 1.8868425118306033e-06, + "loss": 0.45, + "step": 9467 + }, + { + "epoch": 0.81, + "learning_rate": 1.8852283690001638e-06, + "loss": 0.4408, + "step": 9468 + }, + { + "epoch": 0.81, + "learning_rate": 1.883614845036087e-06, + "loss": 0.4774, + "step": 9469 + }, + { + "epoch": 0.81, + "learning_rate": 1.8820019400614264e-06, + "loss": 0.4479, + "step": 9470 + }, + { + "epoch": 0.81, + "learning_rate": 1.8803896541991895e-06, + "loss": 0.4524, + "step": 9471 + }, + { + "epoch": 0.81, + "learning_rate": 1.8787779875723389e-06, + "loss": 0.4599, + "step": 9472 + }, + { + "epoch": 0.81, + "learning_rate": 1.8771669403037807e-06, + "loss": 0.4606, + "step": 9473 + }, + { + "epoch": 0.81, + "learning_rate": 1.8755565125163844e-06, + "loss": 0.4372, + "step": 9474 + }, + { + "epoch": 0.81, + "learning_rate": 1.8739467043329663e-06, + "loss": 0.4452, + "step": 9475 + }, + { + "epoch": 0.81, + "learning_rate": 1.872337515876298e-06, + "loss": 0.4518, + "step": 9476 + }, + { + "epoch": 0.81, + "learning_rate": 1.8707289472691037e-06, + "loss": 0.474, + "step": 9477 + }, + { + "epoch": 0.81, + "learning_rate": 1.8691209986340598e-06, + "loss": 0.4501, + "step": 9478 + }, + { + "epoch": 0.81, + "learning_rate": 1.867513670093789e-06, + "loss": 0.4342, + "step": 9479 + }, + { + "epoch": 0.81, + "learning_rate": 1.8659069617708802e-06, + "loss": 0.4387, + "step": 9480 + }, + { + "epoch": 0.81, + "learning_rate": 1.8643008737878687e-06, + "loss": 0.4608, + "step": 9481 + }, + { + "epoch": 0.81, + "learning_rate": 1.8626954062672353e-06, + "loss": 0.4563, + "step": 9482 + }, + { + "epoch": 0.81, + "learning_rate": 1.8610905593314199e-06, + "loss": 0.4568, + "step": 9483 + }, + { + "epoch": 0.81, + "learning_rate": 1.8594863331028224e-06, + "loss": 0.4482, + "step": 9484 + }, + { + "epoch": 0.81, + "learning_rate": 1.8578827277037804e-06, + "loss": 0.4616, + "step": 9485 + }, + { + "epoch": 0.81, + "learning_rate": 1.8562797432565926e-06, + "loss": 0.4512, + "step": 9486 + }, + { + "epoch": 0.81, + "learning_rate": 1.8546773798835149e-06, + "loss": 0.4589, + "step": 9487 + }, + { + "epoch": 0.81, + "learning_rate": 1.8530756377067394e-06, + "loss": 0.4634, + "step": 9488 + }, + { + "epoch": 0.81, + "learning_rate": 1.8514745168484317e-06, + "loss": 0.4626, + "step": 9489 + }, + { + "epoch": 0.81, + "learning_rate": 1.8498740174306984e-06, + "loss": 0.4613, + "step": 9490 + }, + { + "epoch": 0.81, + "learning_rate": 1.8482741395755966e-06, + "loss": 0.4436, + "step": 9491 + }, + { + "epoch": 0.81, + "learning_rate": 1.8466748834051374e-06, + "loss": 0.4573, + "step": 9492 + }, + { + "epoch": 0.81, + "learning_rate": 1.8450762490412965e-06, + "loss": 0.4509, + "step": 9493 + }, + { + "epoch": 0.81, + "learning_rate": 1.8434782366059844e-06, + "loss": 0.451, + "step": 9494 + }, + { + "epoch": 0.81, + "learning_rate": 1.8418808462210746e-06, + "loss": 0.4434, + "step": 9495 + }, + { + "epoch": 0.81, + "learning_rate": 1.840284078008393e-06, + "loss": 0.4573, + "step": 9496 + }, + { + "epoch": 0.81, + "learning_rate": 1.8386879320897077e-06, + "loss": 0.4449, + "step": 9497 + }, + { + "epoch": 0.81, + "learning_rate": 1.8370924085867558e-06, + "loss": 0.4872, + "step": 9498 + }, + { + "epoch": 0.81, + "learning_rate": 1.8354975076212188e-06, + "loss": 0.4647, + "step": 9499 + }, + { + "epoch": 0.81, + "learning_rate": 1.8339032293147251e-06, + "loss": 0.4524, + "step": 9500 + }, + { + "epoch": 0.81, + "learning_rate": 1.8323095737888607e-06, + "loss": 0.4869, + "step": 9501 + }, + { + "epoch": 0.81, + "learning_rate": 1.8307165411651728e-06, + "loss": 0.4623, + "step": 9502 + }, + { + "epoch": 0.81, + "learning_rate": 1.8291241315651442e-06, + "loss": 0.4764, + "step": 9503 + }, + { + "epoch": 0.81, + "learning_rate": 1.8275323451102223e-06, + "loss": 0.4428, + "step": 9504 + }, + { + "epoch": 0.81, + "learning_rate": 1.8259411819218054e-06, + "loss": 0.4456, + "step": 9505 + }, + { + "epoch": 0.81, + "learning_rate": 1.8243506421212332e-06, + "loss": 0.46, + "step": 9506 + }, + { + "epoch": 0.81, + "learning_rate": 1.8227607258298175e-06, + "loss": 0.4379, + "step": 9507 + }, + { + "epoch": 0.81, + "learning_rate": 1.821171433168809e-06, + "loss": 0.4608, + "step": 9508 + }, + { + "epoch": 0.81, + "learning_rate": 1.819582764259411e-06, + "loss": 0.4485, + "step": 9509 + }, + { + "epoch": 0.81, + "learning_rate": 1.8179947192227832e-06, + "loss": 0.4567, + "step": 9510 + }, + { + "epoch": 0.81, + "learning_rate": 1.8164072981800374e-06, + "loss": 0.4567, + "step": 9511 + }, + { + "epoch": 0.81, + "learning_rate": 1.8148205012522357e-06, + "loss": 0.4681, + "step": 9512 + }, + { + "epoch": 0.81, + "learning_rate": 1.813234328560396e-06, + "loss": 0.4414, + "step": 9513 + }, + { + "epoch": 0.81, + "learning_rate": 1.8116487802254868e-06, + "loss": 0.4585, + "step": 9514 + }, + { + "epoch": 0.81, + "learning_rate": 1.8100638563684214e-06, + "loss": 0.4818, + "step": 9515 + }, + { + "epoch": 0.81, + "learning_rate": 1.808479557110081e-06, + "loss": 0.4604, + "step": 9516 + }, + { + "epoch": 0.81, + "learning_rate": 1.8068958825712912e-06, + "loss": 0.4641, + "step": 9517 + }, + { + "epoch": 0.81, + "learning_rate": 1.8053128328728243e-06, + "loss": 0.4766, + "step": 9518 + }, + { + "epoch": 0.81, + "learning_rate": 1.8037304081354124e-06, + "loss": 0.4568, + "step": 9519 + }, + { + "epoch": 0.81, + "learning_rate": 1.8021486084797368e-06, + "loss": 0.4428, + "step": 9520 + }, + { + "epoch": 0.81, + "learning_rate": 1.8005674340264346e-06, + "loss": 0.4558, + "step": 9521 + }, + { + "epoch": 0.81, + "learning_rate": 1.798986884896091e-06, + "loss": 0.4778, + "step": 9522 + }, + { + "epoch": 0.81, + "learning_rate": 1.7974069612092481e-06, + "loss": 0.442, + "step": 9523 + }, + { + "epoch": 0.81, + "learning_rate": 1.7958276630863903e-06, + "loss": 0.461, + "step": 9524 + }, + { + "epoch": 0.81, + "learning_rate": 1.7942489906479687e-06, + "loss": 0.451, + "step": 9525 + }, + { + "epoch": 0.81, + "learning_rate": 1.7926709440143797e-06, + "loss": 0.4485, + "step": 9526 + }, + { + "epoch": 0.81, + "learning_rate": 1.7910935233059667e-06, + "loss": 0.4493, + "step": 9527 + }, + { + "epoch": 0.81, + "learning_rate": 1.7895167286430326e-06, + "loss": 0.455, + "step": 9528 + }, + { + "epoch": 0.81, + "learning_rate": 1.7879405601458311e-06, + "loss": 0.4614, + "step": 9529 + }, + { + "epoch": 0.81, + "learning_rate": 1.786365017934566e-06, + "loss": 0.4534, + "step": 9530 + }, + { + "epoch": 0.81, + "learning_rate": 1.7847901021293956e-06, + "loss": 0.4658, + "step": 9531 + }, + { + "epoch": 0.81, + "learning_rate": 1.7832158128504328e-06, + "loss": 0.4644, + "step": 9532 + }, + { + "epoch": 0.81, + "learning_rate": 1.7816421502177328e-06, + "loss": 0.4563, + "step": 9533 + }, + { + "epoch": 0.81, + "learning_rate": 1.7800691143513104e-06, + "loss": 0.4533, + "step": 9534 + }, + { + "epoch": 0.81, + "learning_rate": 1.77849670537114e-06, + "loss": 0.4626, + "step": 9535 + }, + { + "epoch": 0.81, + "learning_rate": 1.776924923397132e-06, + "loss": 0.4632, + "step": 9536 + }, + { + "epoch": 0.81, + "learning_rate": 1.7753537685491596e-06, + "loss": 0.4541, + "step": 9537 + }, + { + "epoch": 0.81, + "learning_rate": 1.7737832409470458e-06, + "loss": 0.4541, + "step": 9538 + }, + { + "epoch": 0.81, + "learning_rate": 1.7722133407105656e-06, + "loss": 0.4439, + "step": 9539 + }, + { + "epoch": 0.81, + "learning_rate": 1.7706440679594462e-06, + "loss": 0.4606, + "step": 9540 + }, + { + "epoch": 0.81, + "learning_rate": 1.7690754228133688e-06, + "loss": 0.444, + "step": 9541 + }, + { + "epoch": 0.81, + "learning_rate": 1.7675074053919606e-06, + "loss": 0.4657, + "step": 9542 + }, + { + "epoch": 0.81, + "learning_rate": 1.7659400158148043e-06, + "loss": 0.4828, + "step": 9543 + }, + { + "epoch": 0.81, + "learning_rate": 1.7643732542014437e-06, + "loss": 0.4599, + "step": 9544 + }, + { + "epoch": 0.81, + "learning_rate": 1.7628071206713582e-06, + "loss": 0.4915, + "step": 9545 + }, + { + "epoch": 0.81, + "learning_rate": 1.7612416153439916e-06, + "loss": 0.438, + "step": 9546 + }, + { + "epoch": 0.81, + "learning_rate": 1.7596767383387359e-06, + "loss": 0.4686, + "step": 9547 + }, + { + "epoch": 0.81, + "learning_rate": 1.7581124897749335e-06, + "loss": 0.4649, + "step": 9548 + }, + { + "epoch": 0.81, + "learning_rate": 1.7565488697718814e-06, + "loss": 0.4428, + "step": 9549 + }, + { + "epoch": 0.81, + "learning_rate": 1.7549858784488317e-06, + "loss": 0.4537, + "step": 9550 + }, + { + "epoch": 0.81, + "learning_rate": 1.7534235159249768e-06, + "loss": 0.4468, + "step": 9551 + }, + { + "epoch": 0.81, + "learning_rate": 1.7518617823194705e-06, + "loss": 0.4437, + "step": 9552 + }, + { + "epoch": 0.81, + "learning_rate": 1.7503006777514254e-06, + "loss": 0.456, + "step": 9553 + }, + { + "epoch": 0.81, + "learning_rate": 1.7487402023398891e-06, + "loss": 0.4803, + "step": 9554 + }, + { + "epoch": 0.81, + "learning_rate": 1.7471803562038737e-06, + "loss": 0.453, + "step": 9555 + }, + { + "epoch": 0.81, + "learning_rate": 1.7456211394623379e-06, + "loss": 0.463, + "step": 9556 + }, + { + "epoch": 0.81, + "learning_rate": 1.7440625522341958e-06, + "loss": 0.4525, + "step": 9557 + }, + { + "epoch": 0.81, + "learning_rate": 1.74250459463831e-06, + "loss": 0.4537, + "step": 9558 + }, + { + "epoch": 0.82, + "learning_rate": 1.7409472667935012e-06, + "loss": 0.4485, + "step": 9559 + }, + { + "epoch": 0.82, + "learning_rate": 1.7393905688185319e-06, + "loss": 0.4626, + "step": 9560 + }, + { + "epoch": 0.82, + "learning_rate": 1.737834500832122e-06, + "loss": 0.4505, + "step": 9561 + }, + { + "epoch": 0.82, + "learning_rate": 1.7362790629529513e-06, + "loss": 0.4346, + "step": 9562 + }, + { + "epoch": 0.82, + "learning_rate": 1.734724255299637e-06, + "loss": 0.4916, + "step": 9563 + }, + { + "epoch": 0.82, + "learning_rate": 1.7331700779907579e-06, + "loss": 0.4376, + "step": 9564 + }, + { + "epoch": 0.82, + "learning_rate": 1.7316165311448407e-06, + "loss": 0.4482, + "step": 9565 + }, + { + "epoch": 0.82, + "learning_rate": 1.7300636148803674e-06, + "loss": 0.4717, + "step": 9566 + }, + { + "epoch": 0.82, + "learning_rate": 1.7285113293157673e-06, + "loss": 0.4583, + "step": 9567 + }, + { + "epoch": 0.82, + "learning_rate": 1.7269596745694295e-06, + "loss": 0.4456, + "step": 9568 + }, + { + "epoch": 0.82, + "learning_rate": 1.7254086507596834e-06, + "loss": 0.45, + "step": 9569 + }, + { + "epoch": 0.82, + "learning_rate": 1.7238582580048157e-06, + "loss": 0.4685, + "step": 9570 + }, + { + "epoch": 0.82, + "learning_rate": 1.722308496423074e-06, + "loss": 0.44, + "step": 9571 + }, + { + "epoch": 0.82, + "learning_rate": 1.7207593661326427e-06, + "loss": 0.4647, + "step": 9572 + }, + { + "epoch": 0.82, + "learning_rate": 1.7192108672516672e-06, + "loss": 0.4576, + "step": 9573 + }, + { + "epoch": 0.82, + "learning_rate": 1.7176629998982408e-06, + "loss": 0.4736, + "step": 9574 + }, + { + "epoch": 0.82, + "learning_rate": 1.7161157641904136e-06, + "loss": 0.4352, + "step": 9575 + }, + { + "epoch": 0.82, + "learning_rate": 1.7145691602461812e-06, + "loss": 0.4801, + "step": 9576 + }, + { + "epoch": 0.82, + "learning_rate": 1.713023188183498e-06, + "loss": 0.4572, + "step": 9577 + }, + { + "epoch": 0.82, + "learning_rate": 1.711477848120261e-06, + "loss": 0.4373, + "step": 9578 + }, + { + "epoch": 0.82, + "learning_rate": 1.7099331401743247e-06, + "loss": 0.4499, + "step": 9579 + }, + { + "epoch": 0.82, + "learning_rate": 1.7083890644635015e-06, + "loss": 0.4549, + "step": 9580 + }, + { + "epoch": 0.82, + "learning_rate": 1.706845621105543e-06, + "loss": 0.4578, + "step": 9581 + }, + { + "epoch": 0.82, + "learning_rate": 1.7053028102181601e-06, + "loss": 0.4566, + "step": 9582 + }, + { + "epoch": 0.82, + "learning_rate": 1.7037606319190137e-06, + "loss": 0.4669, + "step": 9583 + }, + { + "epoch": 0.82, + "learning_rate": 1.7022190863257182e-06, + "loss": 0.4483, + "step": 9584 + }, + { + "epoch": 0.82, + "learning_rate": 1.7006781735558364e-06, + "loss": 0.4351, + "step": 9585 + }, + { + "epoch": 0.82, + "learning_rate": 1.6991378937268888e-06, + "loss": 0.4479, + "step": 9586 + }, + { + "epoch": 0.82, + "learning_rate": 1.6975982469563369e-06, + "loss": 0.464, + "step": 9587 + }, + { + "epoch": 0.82, + "learning_rate": 1.6960592333616055e-06, + "loss": 0.4645, + "step": 9588 + }, + { + "epoch": 0.82, + "learning_rate": 1.6945208530600644e-06, + "loss": 0.4612, + "step": 9589 + }, + { + "epoch": 0.82, + "learning_rate": 1.6929831061690371e-06, + "loss": 0.4685, + "step": 9590 + }, + { + "epoch": 0.82, + "learning_rate": 1.6914459928057992e-06, + "loss": 0.4668, + "step": 9591 + }, + { + "epoch": 0.82, + "learning_rate": 1.6899095130875775e-06, + "loss": 0.4383, + "step": 9592 + }, + { + "epoch": 0.82, + "learning_rate": 1.6883736671315488e-06, + "loss": 0.4579, + "step": 9593 + }, + { + "epoch": 0.82, + "learning_rate": 1.6868384550548455e-06, + "loss": 0.4433, + "step": 9594 + }, + { + "epoch": 0.82, + "learning_rate": 1.6853038769745466e-06, + "loss": 0.4463, + "step": 9595 + }, + { + "epoch": 0.82, + "learning_rate": 1.6837699330076906e-06, + "loss": 0.4805, + "step": 9596 + }, + { + "epoch": 0.82, + "learning_rate": 1.682236623271256e-06, + "loss": 0.4571, + "step": 9597 + }, + { + "epoch": 0.82, + "learning_rate": 1.680703947882182e-06, + "loss": 0.4282, + "step": 9598 + }, + { + "epoch": 0.82, + "learning_rate": 1.6791719069573563e-06, + "loss": 0.4545, + "step": 9599 + }, + { + "epoch": 0.82, + "learning_rate": 1.6776405006136199e-06, + "loss": 0.4698, + "step": 9600 + }, + { + "epoch": 0.82, + "learning_rate": 1.6761097289677642e-06, + "loss": 0.4505, + "step": 9601 + }, + { + "epoch": 0.82, + "learning_rate": 1.6745795921365314e-06, + "loss": 0.4576, + "step": 9602 + }, + { + "epoch": 0.82, + "learning_rate": 1.6730500902366165e-06, + "loss": 0.4697, + "step": 9603 + }, + { + "epoch": 0.82, + "learning_rate": 1.6715212233846656e-06, + "loss": 0.4658, + "step": 9604 + }, + { + "epoch": 0.82, + "learning_rate": 1.669992991697279e-06, + "loss": 0.4696, + "step": 9605 + }, + { + "epoch": 0.82, + "learning_rate": 1.6684653952910013e-06, + "loss": 0.4627, + "step": 9606 + }, + { + "epoch": 0.82, + "learning_rate": 1.6669384342823347e-06, + "loss": 0.4384, + "step": 9607 + }, + { + "epoch": 0.82, + "learning_rate": 1.665412108787734e-06, + "loss": 0.4495, + "step": 9608 + }, + { + "epoch": 0.82, + "learning_rate": 1.6638864189236015e-06, + "loss": 0.4551, + "step": 9609 + }, + { + "epoch": 0.82, + "learning_rate": 1.662361364806292e-06, + "loss": 0.4489, + "step": 9610 + }, + { + "epoch": 0.82, + "learning_rate": 1.6608369465521169e-06, + "loss": 0.4356, + "step": 9611 + }, + { + "epoch": 0.82, + "learning_rate": 1.6593131642773252e-06, + "loss": 0.483, + "step": 9612 + }, + { + "epoch": 0.82, + "learning_rate": 1.6577900180981366e-06, + "loss": 0.464, + "step": 9613 + }, + { + "epoch": 0.82, + "learning_rate": 1.6562675081307101e-06, + "loss": 0.4644, + "step": 9614 + }, + { + "epoch": 0.82, + "learning_rate": 1.654745634491156e-06, + "loss": 0.4681, + "step": 9615 + }, + { + "epoch": 0.82, + "learning_rate": 1.6532243972955397e-06, + "loss": 0.459, + "step": 9616 + }, + { + "epoch": 0.82, + "learning_rate": 1.651703796659878e-06, + "loss": 0.4344, + "step": 9617 + }, + { + "epoch": 0.82, + "learning_rate": 1.6501838327001374e-06, + "loss": 0.478, + "step": 9618 + }, + { + "epoch": 0.82, + "learning_rate": 1.6486645055322381e-06, + "loss": 0.4612, + "step": 9619 + }, + { + "epoch": 0.82, + "learning_rate": 1.647145815272051e-06, + "loss": 0.4539, + "step": 9620 + }, + { + "epoch": 0.82, + "learning_rate": 1.645627762035391e-06, + "loss": 0.4436, + "step": 9621 + }, + { + "epoch": 0.82, + "learning_rate": 1.6441103459380392e-06, + "loss": 0.4543, + "step": 9622 + }, + { + "epoch": 0.82, + "learning_rate": 1.6425935670957194e-06, + "loss": 0.4554, + "step": 9623 + }, + { + "epoch": 0.82, + "learning_rate": 1.6410774256241036e-06, + "loss": 0.4553, + "step": 9624 + }, + { + "epoch": 0.82, + "learning_rate": 1.6395619216388204e-06, + "loss": 0.4561, + "step": 9625 + }, + { + "epoch": 0.82, + "learning_rate": 1.6380470552554483e-06, + "loss": 0.4668, + "step": 9626 + }, + { + "epoch": 0.82, + "learning_rate": 1.6365328265895186e-06, + "loss": 0.4517, + "step": 9627 + }, + { + "epoch": 0.82, + "learning_rate": 1.635019235756511e-06, + "loss": 0.4706, + "step": 9628 + }, + { + "epoch": 0.82, + "learning_rate": 1.633506282871863e-06, + "loss": 0.4543, + "step": 9629 + }, + { + "epoch": 0.82, + "learning_rate": 1.631993968050949e-06, + "loss": 0.4463, + "step": 9630 + }, + { + "epoch": 0.82, + "learning_rate": 1.6304822914091134e-06, + "loss": 0.4422, + "step": 9631 + }, + { + "epoch": 0.82, + "learning_rate": 1.628971253061642e-06, + "loss": 0.4495, + "step": 9632 + }, + { + "epoch": 0.82, + "learning_rate": 1.6274608531237679e-06, + "loss": 0.447, + "step": 9633 + }, + { + "epoch": 0.82, + "learning_rate": 1.6259510917106847e-06, + "loss": 0.4475, + "step": 9634 + }, + { + "epoch": 0.82, + "learning_rate": 1.6244419689375313e-06, + "loss": 0.4478, + "step": 9635 + }, + { + "epoch": 0.82, + "learning_rate": 1.6229334849194001e-06, + "loss": 0.4653, + "step": 9636 + }, + { + "epoch": 0.82, + "learning_rate": 1.6214256397713347e-06, + "loss": 0.4377, + "step": 9637 + }, + { + "epoch": 0.82, + "learning_rate": 1.6199184336083319e-06, + "loss": 0.462, + "step": 9638 + }, + { + "epoch": 0.82, + "learning_rate": 1.6184118665453296e-06, + "loss": 0.4546, + "step": 9639 + }, + { + "epoch": 0.82, + "learning_rate": 1.6169059386972342e-06, + "loss": 0.4544, + "step": 9640 + }, + { + "epoch": 0.82, + "learning_rate": 1.615400650178891e-06, + "loss": 0.4543, + "step": 9641 + }, + { + "epoch": 0.82, + "learning_rate": 1.6138960011050974e-06, + "loss": 0.4622, + "step": 9642 + }, + { + "epoch": 0.82, + "learning_rate": 1.612391991590606e-06, + "loss": 0.4656, + "step": 9643 + }, + { + "epoch": 0.82, + "learning_rate": 1.6108886217501184e-06, + "loss": 0.4641, + "step": 9644 + }, + { + "epoch": 0.82, + "learning_rate": 1.6093858916982884e-06, + "loss": 0.4585, + "step": 9645 + }, + { + "epoch": 0.82, + "learning_rate": 1.607883801549719e-06, + "loss": 0.434, + "step": 9646 + }, + { + "epoch": 0.82, + "learning_rate": 1.6063823514189703e-06, + "loss": 0.4595, + "step": 9647 + }, + { + "epoch": 0.82, + "learning_rate": 1.60488154142054e-06, + "loss": 0.4683, + "step": 9648 + }, + { + "epoch": 0.82, + "learning_rate": 1.603381371668895e-06, + "loss": 0.4717, + "step": 9649 + }, + { + "epoch": 0.82, + "learning_rate": 1.6018818422784433e-06, + "loss": 0.4232, + "step": 9650 + }, + { + "epoch": 0.82, + "learning_rate": 1.6003829533635417e-06, + "loss": 0.4502, + "step": 9651 + }, + { + "epoch": 0.82, + "learning_rate": 1.5988847050385037e-06, + "loss": 0.4503, + "step": 9652 + }, + { + "epoch": 0.82, + "learning_rate": 1.5973870974175909e-06, + "loss": 0.4496, + "step": 9653 + }, + { + "epoch": 0.82, + "learning_rate": 1.5958901306150177e-06, + "loss": 0.4682, + "step": 9654 + }, + { + "epoch": 0.82, + "learning_rate": 1.5943938047449493e-06, + "loss": 0.4697, + "step": 9655 + }, + { + "epoch": 0.82, + "learning_rate": 1.5928981199215044e-06, + "loss": 0.4554, + "step": 9656 + }, + { + "epoch": 0.82, + "learning_rate": 1.591403076258743e-06, + "loss": 0.4722, + "step": 9657 + }, + { + "epoch": 0.82, + "learning_rate": 1.5899086738706904e-06, + "loss": 0.4635, + "step": 9658 + }, + { + "epoch": 0.82, + "learning_rate": 1.5884149128713155e-06, + "loss": 0.4414, + "step": 9659 + }, + { + "epoch": 0.82, + "learning_rate": 1.586921793374534e-06, + "loss": 0.4438, + "step": 9660 + }, + { + "epoch": 0.82, + "learning_rate": 1.5854293154942203e-06, + "loss": 0.4594, + "step": 9661 + }, + { + "epoch": 0.82, + "learning_rate": 1.5839374793441964e-06, + "loss": 0.4457, + "step": 9662 + }, + { + "epoch": 0.82, + "learning_rate": 1.582446285038236e-06, + "loss": 0.4524, + "step": 9663 + }, + { + "epoch": 0.82, + "learning_rate": 1.580955732690065e-06, + "loss": 0.465, + "step": 9664 + }, + { + "epoch": 0.82, + "learning_rate": 1.5794658224133607e-06, + "loss": 0.4533, + "step": 9665 + }, + { + "epoch": 0.82, + "learning_rate": 1.577976554321745e-06, + "loss": 0.4443, + "step": 9666 + }, + { + "epoch": 0.82, + "learning_rate": 1.576487928528795e-06, + "loss": 0.4406, + "step": 9667 + }, + { + "epoch": 0.82, + "learning_rate": 1.574999945148048e-06, + "loss": 0.4724, + "step": 9668 + }, + { + "epoch": 0.82, + "learning_rate": 1.573512604292976e-06, + "loss": 0.4383, + "step": 9669 + }, + { + "epoch": 0.82, + "learning_rate": 1.5720259060770128e-06, + "loss": 0.4423, + "step": 9670 + }, + { + "epoch": 0.82, + "learning_rate": 1.5705398506135394e-06, + "loss": 0.4575, + "step": 9671 + }, + { + "epoch": 0.82, + "learning_rate": 1.569054438015889e-06, + "loss": 0.4356, + "step": 9672 + }, + { + "epoch": 0.82, + "learning_rate": 1.5675696683973452e-06, + "loss": 0.4755, + "step": 9673 + }, + { + "epoch": 0.82, + "learning_rate": 1.566085541871145e-06, + "loss": 0.4545, + "step": 9674 + }, + { + "epoch": 0.82, + "learning_rate": 1.5646020585504696e-06, + "loss": 0.4302, + "step": 9675 + }, + { + "epoch": 0.83, + "learning_rate": 1.5631192185484557e-06, + "loss": 0.4658, + "step": 9676 + }, + { + "epoch": 0.83, + "learning_rate": 1.5616370219781985e-06, + "loss": 0.4363, + "step": 9677 + }, + { + "epoch": 0.83, + "learning_rate": 1.5601554689527276e-06, + "loss": 0.4754, + "step": 9678 + }, + { + "epoch": 0.83, + "learning_rate": 1.558674559585036e-06, + "loss": 0.4362, + "step": 9679 + }, + { + "epoch": 0.83, + "learning_rate": 1.5571942939880646e-06, + "loss": 0.4706, + "step": 9680 + }, + { + "epoch": 0.83, + "learning_rate": 1.555714672274704e-06, + "loss": 0.4622, + "step": 9681 + }, + { + "epoch": 0.83, + "learning_rate": 1.5542356945577964e-06, + "loss": 0.4325, + "step": 9682 + }, + { + "epoch": 0.83, + "learning_rate": 1.5527573609501367e-06, + "loss": 0.4527, + "step": 9683 + }, + { + "epoch": 0.83, + "learning_rate": 1.551279671564464e-06, + "loss": 0.471, + "step": 9684 + }, + { + "epoch": 0.83, + "learning_rate": 1.5498026265134747e-06, + "loss": 0.4452, + "step": 9685 + }, + { + "epoch": 0.83, + "learning_rate": 1.5483262259098197e-06, + "loss": 0.4601, + "step": 9686 + }, + { + "epoch": 0.83, + "learning_rate": 1.546850469866089e-06, + "loss": 0.4403, + "step": 9687 + }, + { + "epoch": 0.83, + "learning_rate": 1.5453753584948329e-06, + "loss": 0.4305, + "step": 9688 + }, + { + "epoch": 0.83, + "learning_rate": 1.5439008919085507e-06, + "loss": 0.4624, + "step": 9689 + }, + { + "epoch": 0.83, + "learning_rate": 1.5424270702196841e-06, + "loss": 0.4576, + "step": 9690 + }, + { + "epoch": 0.83, + "learning_rate": 1.5409538935406422e-06, + "loss": 0.4678, + "step": 9691 + }, + { + "epoch": 0.83, + "learning_rate": 1.5394813619837734e-06, + "loss": 0.4725, + "step": 9692 + }, + { + "epoch": 0.83, + "learning_rate": 1.5380094756613761e-06, + "loss": 0.4353, + "step": 9693 + }, + { + "epoch": 0.83, + "learning_rate": 1.5365382346857005e-06, + "loss": 0.4687, + "step": 9694 + }, + { + "epoch": 0.83, + "learning_rate": 1.5350676391689578e-06, + "loss": 0.4656, + "step": 9695 + }, + { + "epoch": 0.83, + "learning_rate": 1.533597689223295e-06, + "loss": 0.4593, + "step": 9696 + }, + { + "epoch": 0.83, + "learning_rate": 1.5321283849608193e-06, + "loss": 0.4553, + "step": 9697 + }, + { + "epoch": 0.83, + "learning_rate": 1.5306597264935863e-06, + "loss": 0.4521, + "step": 9698 + }, + { + "epoch": 0.83, + "learning_rate": 1.5291917139335976e-06, + "loss": 0.4567, + "step": 9699 + }, + { + "epoch": 0.83, + "learning_rate": 1.527724347392815e-06, + "loss": 0.4507, + "step": 9700 + }, + { + "epoch": 0.83, + "learning_rate": 1.5262576269831464e-06, + "loss": 0.456, + "step": 9701 + }, + { + "epoch": 0.83, + "learning_rate": 1.5247915528164458e-06, + "loss": 0.4387, + "step": 9702 + }, + { + "epoch": 0.83, + "learning_rate": 1.5233261250045218e-06, + "loss": 0.4665, + "step": 9703 + }, + { + "epoch": 0.83, + "learning_rate": 1.5218613436591422e-06, + "loss": 0.462, + "step": 9704 + }, + { + "epoch": 0.83, + "learning_rate": 1.5203972088920082e-06, + "loss": 0.4564, + "step": 9705 + }, + { + "epoch": 0.83, + "learning_rate": 1.5189337208147848e-06, + "loss": 0.45, + "step": 9706 + }, + { + "epoch": 0.83, + "learning_rate": 1.5174708795390859e-06, + "loss": 0.4655, + "step": 9707 + }, + { + "epoch": 0.83, + "learning_rate": 1.5160086851764666e-06, + "loss": 0.4597, + "step": 9708 + }, + { + "epoch": 0.83, + "learning_rate": 1.5145471378384458e-06, + "loss": 0.4595, + "step": 9709 + }, + { + "epoch": 0.83, + "learning_rate": 1.5130862376364897e-06, + "loss": 0.4612, + "step": 9710 + }, + { + "epoch": 0.83, + "learning_rate": 1.5116259846820058e-06, + "loss": 0.4397, + "step": 9711 + }, + { + "epoch": 0.83, + "learning_rate": 1.5101663790863597e-06, + "loss": 0.4726, + "step": 9712 + }, + { + "epoch": 0.83, + "learning_rate": 1.5087074209608743e-06, + "loss": 0.4474, + "step": 9713 + }, + { + "epoch": 0.83, + "learning_rate": 1.5072491104168097e-06, + "loss": 0.4566, + "step": 9714 + }, + { + "epoch": 0.83, + "learning_rate": 1.5057914475653835e-06, + "loss": 0.4525, + "step": 9715 + }, + { + "epoch": 0.83, + "learning_rate": 1.5043344325177634e-06, + "loss": 0.4625, + "step": 9716 + }, + { + "epoch": 0.83, + "learning_rate": 1.502878065385067e-06, + "loss": 0.4653, + "step": 9717 + }, + { + "epoch": 0.83, + "learning_rate": 1.501422346278365e-06, + "loss": 0.4508, + "step": 9718 + }, + { + "epoch": 0.83, + "learning_rate": 1.499967275308678e-06, + "loss": 0.4811, + "step": 9719 + }, + { + "epoch": 0.83, + "learning_rate": 1.4985128525869697e-06, + "loss": 0.4527, + "step": 9720 + }, + { + "epoch": 0.83, + "learning_rate": 1.4970590782241645e-06, + "loss": 0.4539, + "step": 9721 + }, + { + "epoch": 0.83, + "learning_rate": 1.4956059523311328e-06, + "loss": 0.4766, + "step": 9722 + }, + { + "epoch": 0.83, + "learning_rate": 1.4941534750186958e-06, + "loss": 0.4401, + "step": 9723 + }, + { + "epoch": 0.83, + "learning_rate": 1.4927016463976262e-06, + "loss": 0.4386, + "step": 9724 + }, + { + "epoch": 0.83, + "learning_rate": 1.4912504665786454e-06, + "loss": 0.4572, + "step": 9725 + }, + { + "epoch": 0.83, + "learning_rate": 1.4897999356724268e-06, + "loss": 0.4579, + "step": 9726 + }, + { + "epoch": 0.83, + "learning_rate": 1.4883500537895946e-06, + "loss": 0.4428, + "step": 9727 + }, + { + "epoch": 0.83, + "learning_rate": 1.4869008210407243e-06, + "loss": 0.4686, + "step": 9728 + }, + { + "epoch": 0.83, + "learning_rate": 1.4854522375363367e-06, + "loss": 0.4554, + "step": 9729 + }, + { + "epoch": 0.83, + "learning_rate": 1.4840043033869079e-06, + "loss": 0.4484, + "step": 9730 + }, + { + "epoch": 0.83, + "learning_rate": 1.482557018702865e-06, + "loss": 0.4545, + "step": 9731 + }, + { + "epoch": 0.83, + "learning_rate": 1.4811103835945817e-06, + "loss": 0.4457, + "step": 9732 + }, + { + "epoch": 0.83, + "learning_rate": 1.479664398172387e-06, + "loss": 0.4756, + "step": 9733 + }, + { + "epoch": 0.83, + "learning_rate": 1.4782190625465565e-06, + "loss": 0.4317, + "step": 9734 + }, + { + "epoch": 0.83, + "learning_rate": 1.476774376827318e-06, + "loss": 0.4631, + "step": 9735 + }, + { + "epoch": 0.83, + "learning_rate": 1.4753303411248477e-06, + "loss": 0.4627, + "step": 9736 + }, + { + "epoch": 0.83, + "learning_rate": 1.4738869555492786e-06, + "loss": 0.4683, + "step": 9737 + }, + { + "epoch": 0.83, + "learning_rate": 1.4724442202106825e-06, + "loss": 0.4562, + "step": 9738 + }, + { + "epoch": 0.83, + "learning_rate": 1.4710021352190918e-06, + "loss": 0.4531, + "step": 9739 + }, + { + "epoch": 0.83, + "learning_rate": 1.4695607006844859e-06, + "loss": 0.4587, + "step": 9740 + }, + { + "epoch": 0.83, + "learning_rate": 1.4681199167167949e-06, + "loss": 0.4521, + "step": 9741 + }, + { + "epoch": 0.83, + "learning_rate": 1.4666797834258984e-06, + "loss": 0.4537, + "step": 9742 + }, + { + "epoch": 0.83, + "learning_rate": 1.4652403009216265e-06, + "loss": 0.4508, + "step": 9743 + }, + { + "epoch": 0.83, + "learning_rate": 1.4638014693137637e-06, + "loss": 0.4578, + "step": 9744 + }, + { + "epoch": 0.83, + "learning_rate": 1.4623632887120343e-06, + "loss": 0.4563, + "step": 9745 + }, + { + "epoch": 0.83, + "learning_rate": 1.4609257592261273e-06, + "loss": 0.4485, + "step": 9746 + }, + { + "epoch": 0.83, + "learning_rate": 1.4594888809656704e-06, + "loss": 0.4651, + "step": 9747 + }, + { + "epoch": 0.83, + "learning_rate": 1.4580526540402462e-06, + "loss": 0.4671, + "step": 9748 + }, + { + "epoch": 0.83, + "learning_rate": 1.456617078559389e-06, + "loss": 0.4713, + "step": 9749 + }, + { + "epoch": 0.83, + "learning_rate": 1.4551821546325806e-06, + "loss": 0.4405, + "step": 9750 + }, + { + "epoch": 0.83, + "learning_rate": 1.453747882369254e-06, + "loss": 0.4694, + "step": 9751 + }, + { + "epoch": 0.83, + "learning_rate": 1.4523142618787944e-06, + "loss": 0.4404, + "step": 9752 + }, + { + "epoch": 0.83, + "learning_rate": 1.4508812932705364e-06, + "loss": 0.4447, + "step": 9753 + }, + { + "epoch": 0.83, + "learning_rate": 1.4494489766537579e-06, + "loss": 0.4639, + "step": 9754 + }, + { + "epoch": 0.83, + "learning_rate": 1.4480173121377028e-06, + "loss": 0.4516, + "step": 9755 + }, + { + "epoch": 0.83, + "learning_rate": 1.4465862998315483e-06, + "loss": 0.4698, + "step": 9756 + }, + { + "epoch": 0.83, + "learning_rate": 1.4451559398444314e-06, + "loss": 0.4463, + "step": 9757 + }, + { + "epoch": 0.83, + "learning_rate": 1.4437262322854394e-06, + "loss": 0.4647, + "step": 9758 + }, + { + "epoch": 0.83, + "learning_rate": 1.442297177263605e-06, + "loss": 0.4467, + "step": 9759 + }, + { + "epoch": 0.83, + "learning_rate": 1.4408687748879157e-06, + "loss": 0.4589, + "step": 9760 + }, + { + "epoch": 0.83, + "learning_rate": 1.4394410252673075e-06, + "loss": 0.4596, + "step": 9761 + }, + { + "epoch": 0.83, + "learning_rate": 1.4380139285106676e-06, + "loss": 0.4483, + "step": 9762 + }, + { + "epoch": 0.83, + "learning_rate": 1.4365874847268257e-06, + "loss": 0.462, + "step": 9763 + }, + { + "epoch": 0.83, + "learning_rate": 1.4351616940245794e-06, + "loss": 0.4606, + "step": 9764 + }, + { + "epoch": 0.83, + "learning_rate": 1.433736556512656e-06, + "loss": 0.4535, + "step": 9765 + }, + { + "epoch": 0.83, + "learning_rate": 1.4323120722997463e-06, + "loss": 0.4621, + "step": 9766 + }, + { + "epoch": 0.83, + "learning_rate": 1.430888241494487e-06, + "loss": 0.4561, + "step": 9767 + }, + { + "epoch": 0.83, + "learning_rate": 1.4294650642054654e-06, + "loss": 0.4334, + "step": 9768 + }, + { + "epoch": 0.83, + "learning_rate": 1.428042540541218e-06, + "loss": 0.4649, + "step": 9769 + }, + { + "epoch": 0.83, + "learning_rate": 1.4266206706102337e-06, + "loss": 0.4577, + "step": 9770 + }, + { + "epoch": 0.83, + "learning_rate": 1.4251994545209524e-06, + "loss": 0.4642, + "step": 9771 + }, + { + "epoch": 0.83, + "learning_rate": 1.4237788923817553e-06, + "loss": 0.4707, + "step": 9772 + }, + { + "epoch": 0.83, + "learning_rate": 1.4223589843009866e-06, + "loss": 0.4413, + "step": 9773 + }, + { + "epoch": 0.83, + "learning_rate": 1.4209397303869343e-06, + "loss": 0.4575, + "step": 9774 + }, + { + "epoch": 0.83, + "learning_rate": 1.419521130747833e-06, + "loss": 0.4626, + "step": 9775 + }, + { + "epoch": 0.83, + "learning_rate": 1.4181031854918714e-06, + "loss": 0.4589, + "step": 9776 + }, + { + "epoch": 0.83, + "learning_rate": 1.41668589472719e-06, + "loss": 0.4456, + "step": 9777 + }, + { + "epoch": 0.83, + "learning_rate": 1.4152692585618767e-06, + "loss": 0.4548, + "step": 9778 + }, + { + "epoch": 0.83, + "learning_rate": 1.4138532771039703e-06, + "loss": 0.4304, + "step": 9779 + }, + { + "epoch": 0.83, + "learning_rate": 1.4124379504614604e-06, + "loss": 0.4421, + "step": 9780 + }, + { + "epoch": 0.83, + "learning_rate": 1.4110232787422807e-06, + "loss": 0.454, + "step": 9781 + }, + { + "epoch": 0.83, + "learning_rate": 1.4096092620543257e-06, + "loss": 0.46, + "step": 9782 + }, + { + "epoch": 0.83, + "learning_rate": 1.4081959005054335e-06, + "loss": 0.449, + "step": 9783 + }, + { + "epoch": 0.83, + "learning_rate": 1.4067831942033904e-06, + "loss": 0.4658, + "step": 9784 + }, + { + "epoch": 0.83, + "learning_rate": 1.4053711432559358e-06, + "loss": 0.4554, + "step": 9785 + }, + { + "epoch": 0.83, + "learning_rate": 1.40395974777076e-06, + "loss": 0.4737, + "step": 9786 + }, + { + "epoch": 0.83, + "learning_rate": 1.4025490078555015e-06, + "loss": 0.4556, + "step": 9787 + }, + { + "epoch": 0.83, + "learning_rate": 1.4011389236177476e-06, + "loss": 0.4773, + "step": 9788 + }, + { + "epoch": 0.83, + "learning_rate": 1.399729495165042e-06, + "loss": 0.4548, + "step": 9789 + }, + { + "epoch": 0.83, + "learning_rate": 1.3983207226048656e-06, + "loss": 0.4765, + "step": 9790 + }, + { + "epoch": 0.83, + "learning_rate": 1.3969126060446635e-06, + "loss": 0.4478, + "step": 9791 + }, + { + "epoch": 0.83, + "learning_rate": 1.3955051455918257e-06, + "loss": 0.444, + "step": 9792 + }, + { + "epoch": 0.84, + "learning_rate": 1.3940983413536847e-06, + "loss": 0.4817, + "step": 9793 + }, + { + "epoch": 0.84, + "learning_rate": 1.3926921934375338e-06, + "loss": 0.4511, + "step": 9794 + }, + { + "epoch": 0.84, + "learning_rate": 1.3912867019506105e-06, + "loss": 0.4459, + "step": 9795 + }, + { + "epoch": 0.84, + "learning_rate": 1.3898818670001035e-06, + "loss": 0.4512, + "step": 9796 + }, + { + "epoch": 0.84, + "learning_rate": 1.3884776886931517e-06, + "loss": 0.4541, + "step": 9797 + }, + { + "epoch": 0.84, + "learning_rate": 1.387074167136846e-06, + "loss": 0.455, + "step": 9798 + }, + { + "epoch": 0.84, + "learning_rate": 1.3856713024382195e-06, + "loss": 0.4504, + "step": 9799 + }, + { + "epoch": 0.84, + "learning_rate": 1.3842690947042604e-06, + "loss": 0.4715, + "step": 9800 + }, + { + "epoch": 0.84, + "learning_rate": 1.3828675440419147e-06, + "loss": 0.4287, + "step": 9801 + }, + { + "epoch": 0.84, + "learning_rate": 1.3814666505580632e-06, + "loss": 0.4433, + "step": 9802 + }, + { + "epoch": 0.84, + "learning_rate": 1.3800664143595465e-06, + "loss": 0.4546, + "step": 9803 + }, + { + "epoch": 0.84, + "learning_rate": 1.3786668355531518e-06, + "loss": 0.4411, + "step": 9804 + }, + { + "epoch": 0.84, + "learning_rate": 1.377267914245618e-06, + "loss": 0.4309, + "step": 9805 + }, + { + "epoch": 0.84, + "learning_rate": 1.3758696505436309e-06, + "loss": 0.4418, + "step": 9806 + }, + { + "epoch": 0.84, + "learning_rate": 1.3744720445538318e-06, + "loss": 0.4776, + "step": 9807 + }, + { + "epoch": 0.84, + "learning_rate": 1.3730750963828033e-06, + "loss": 0.4453, + "step": 9808 + }, + { + "epoch": 0.84, + "learning_rate": 1.3716788061370812e-06, + "loss": 0.4634, + "step": 9809 + }, + { + "epoch": 0.84, + "learning_rate": 1.3702831739231593e-06, + "loss": 0.464, + "step": 9810 + }, + { + "epoch": 0.84, + "learning_rate": 1.36888819984747e-06, + "loss": 0.4555, + "step": 9811 + }, + { + "epoch": 0.84, + "learning_rate": 1.3674938840163986e-06, + "loss": 0.4573, + "step": 9812 + }, + { + "epoch": 0.84, + "learning_rate": 1.3661002265362844e-06, + "loss": 0.4604, + "step": 9813 + }, + { + "epoch": 0.84, + "learning_rate": 1.3647072275134122e-06, + "loss": 0.467, + "step": 9814 + }, + { + "epoch": 0.84, + "learning_rate": 1.363314887054018e-06, + "loss": 0.4472, + "step": 9815 + }, + { + "epoch": 0.84, + "learning_rate": 1.3619232052642906e-06, + "loss": 0.4559, + "step": 9816 + }, + { + "epoch": 0.84, + "learning_rate": 1.3605321822503592e-06, + "loss": 0.4658, + "step": 9817 + }, + { + "epoch": 0.84, + "learning_rate": 1.3591418181183103e-06, + "loss": 0.4318, + "step": 9818 + }, + { + "epoch": 0.84, + "learning_rate": 1.3577521129741856e-06, + "loss": 0.4605, + "step": 9819 + }, + { + "epoch": 0.84, + "learning_rate": 1.3563630669239625e-06, + "loss": 0.4532, + "step": 9820 + }, + { + "epoch": 0.84, + "learning_rate": 1.3549746800735775e-06, + "loss": 0.4402, + "step": 9821 + }, + { + "epoch": 0.84, + "learning_rate": 1.353586952528918e-06, + "loss": 0.4527, + "step": 9822 + }, + { + "epoch": 0.84, + "learning_rate": 1.3521998843958117e-06, + "loss": 0.4683, + "step": 9823 + }, + { + "epoch": 0.84, + "learning_rate": 1.350813475780046e-06, + "loss": 0.4483, + "step": 9824 + }, + { + "epoch": 0.84, + "learning_rate": 1.349427726787358e-06, + "loss": 0.446, + "step": 9825 + }, + { + "epoch": 0.84, + "learning_rate": 1.3480426375234234e-06, + "loss": 0.4566, + "step": 9826 + }, + { + "epoch": 0.84, + "learning_rate": 1.3466582080938762e-06, + "loss": 0.4583, + "step": 9827 + }, + { + "epoch": 0.84, + "learning_rate": 1.345274438604305e-06, + "loss": 0.4518, + "step": 9828 + }, + { + "epoch": 0.84, + "learning_rate": 1.343891329160235e-06, + "loss": 0.4517, + "step": 9829 + }, + { + "epoch": 0.84, + "learning_rate": 1.3425088798671504e-06, + "loss": 0.4533, + "step": 9830 + }, + { + "epoch": 0.84, + "learning_rate": 1.3411270908304853e-06, + "loss": 0.4613, + "step": 9831 + }, + { + "epoch": 0.84, + "learning_rate": 1.339745962155613e-06, + "loss": 0.4678, + "step": 9832 + }, + { + "epoch": 0.84, + "learning_rate": 1.3383654939478718e-06, + "loss": 0.4508, + "step": 9833 + }, + { + "epoch": 0.84, + "learning_rate": 1.3369856863125418e-06, + "loss": 0.4559, + "step": 9834 + }, + { + "epoch": 0.84, + "learning_rate": 1.3356065393548467e-06, + "loss": 0.451, + "step": 9835 + }, + { + "epoch": 0.84, + "learning_rate": 1.334228053179969e-06, + "loss": 0.4573, + "step": 9836 + }, + { + "epoch": 0.84, + "learning_rate": 1.3328502278930422e-06, + "loss": 0.4644, + "step": 9837 + }, + { + "epoch": 0.84, + "learning_rate": 1.3314730635991391e-06, + "loss": 0.4305, + "step": 9838 + }, + { + "epoch": 0.84, + "learning_rate": 1.33009656040329e-06, + "loss": 0.4859, + "step": 9839 + }, + { + "epoch": 0.84, + "learning_rate": 1.3287207184104756e-06, + "loss": 0.4379, + "step": 9840 + }, + { + "epoch": 0.84, + "learning_rate": 1.3273455377256162e-06, + "loss": 0.4641, + "step": 9841 + }, + { + "epoch": 0.84, + "learning_rate": 1.3259710184535957e-06, + "loss": 0.4508, + "step": 9842 + }, + { + "epoch": 0.84, + "learning_rate": 1.3245971606992404e-06, + "loss": 0.4511, + "step": 9843 + }, + { + "epoch": 0.84, + "learning_rate": 1.3232239645673217e-06, + "loss": 0.444, + "step": 9844 + }, + { + "epoch": 0.84, + "learning_rate": 1.3218514301625662e-06, + "loss": 0.4654, + "step": 9845 + }, + { + "epoch": 0.84, + "learning_rate": 1.3204795575896545e-06, + "loss": 0.4728, + "step": 9846 + }, + { + "epoch": 0.84, + "learning_rate": 1.3191083469532062e-06, + "loss": 0.456, + "step": 9847 + }, + { + "epoch": 0.84, + "learning_rate": 1.3177377983577967e-06, + "loss": 0.4435, + "step": 9848 + }, + { + "epoch": 0.84, + "learning_rate": 1.316367911907952e-06, + "loss": 0.449, + "step": 9849 + }, + { + "epoch": 0.84, + "learning_rate": 1.31499868770814e-06, + "loss": 0.4654, + "step": 9850 + }, + { + "epoch": 0.84, + "learning_rate": 1.313630125862788e-06, + "loss": 0.4753, + "step": 9851 + }, + { + "epoch": 0.84, + "learning_rate": 1.3122622264762696e-06, + "loss": 0.4437, + "step": 9852 + }, + { + "epoch": 0.84, + "learning_rate": 1.3108949896529023e-06, + "loss": 0.4409, + "step": 9853 + }, + { + "epoch": 0.84, + "learning_rate": 1.3095284154969578e-06, + "loss": 0.4483, + "step": 9854 + }, + { + "epoch": 0.84, + "learning_rate": 1.308162504112659e-06, + "loss": 0.4571, + "step": 9855 + }, + { + "epoch": 0.84, + "learning_rate": 1.3067972556041753e-06, + "loss": 0.4534, + "step": 9856 + }, + { + "epoch": 0.84, + "learning_rate": 1.3054326700756248e-06, + "loss": 0.4332, + "step": 9857 + }, + { + "epoch": 0.84, + "learning_rate": 1.304068747631081e-06, + "loss": 0.4686, + "step": 9858 + }, + { + "epoch": 0.84, + "learning_rate": 1.3027054883745538e-06, + "loss": 0.4653, + "step": 9859 + }, + { + "epoch": 0.84, + "learning_rate": 1.301342892410018e-06, + "loss": 0.4306, + "step": 9860 + }, + { + "epoch": 0.84, + "learning_rate": 1.2999809598413927e-06, + "loss": 0.4545, + "step": 9861 + }, + { + "epoch": 0.84, + "learning_rate": 1.2986196907725368e-06, + "loss": 0.4501, + "step": 9862 + }, + { + "epoch": 0.84, + "learning_rate": 1.297259085307272e-06, + "loss": 0.454, + "step": 9863 + }, + { + "epoch": 0.84, + "learning_rate": 1.2958991435493618e-06, + "loss": 0.4417, + "step": 9864 + }, + { + "epoch": 0.84, + "learning_rate": 1.294539865602521e-06, + "loss": 0.4627, + "step": 9865 + }, + { + "epoch": 0.84, + "learning_rate": 1.2931812515704145e-06, + "loss": 0.4847, + "step": 9866 + }, + { + "epoch": 0.84, + "learning_rate": 1.2918233015566573e-06, + "loss": 0.4454, + "step": 9867 + }, + { + "epoch": 0.84, + "learning_rate": 1.2904660156648074e-06, + "loss": 0.4592, + "step": 9868 + }, + { + "epoch": 0.84, + "learning_rate": 1.2891093939983812e-06, + "loss": 0.4679, + "step": 9869 + }, + { + "epoch": 0.84, + "learning_rate": 1.2877534366608424e-06, + "loss": 0.4361, + "step": 9870 + }, + { + "epoch": 0.84, + "learning_rate": 1.2863981437555972e-06, + "loss": 0.4711, + "step": 9871 + }, + { + "epoch": 0.84, + "learning_rate": 1.2850435153860075e-06, + "loss": 0.4463, + "step": 9872 + }, + { + "epoch": 0.84, + "learning_rate": 1.2836895516553826e-06, + "loss": 0.4622, + "step": 9873 + }, + { + "epoch": 0.84, + "learning_rate": 1.2823362526669825e-06, + "loss": 0.4475, + "step": 9874 + }, + { + "epoch": 0.84, + "learning_rate": 1.2809836185240154e-06, + "loss": 0.4717, + "step": 9875 + }, + { + "epoch": 0.84, + "learning_rate": 1.2796316493296402e-06, + "loss": 0.464, + "step": 9876 + }, + { + "epoch": 0.84, + "learning_rate": 1.2782803451869597e-06, + "loss": 0.4456, + "step": 9877 + }, + { + "epoch": 0.84, + "learning_rate": 1.2769297061990294e-06, + "loss": 0.4655, + "step": 9878 + }, + { + "epoch": 0.84, + "learning_rate": 1.2755797324688622e-06, + "loss": 0.4649, + "step": 9879 + }, + { + "epoch": 0.84, + "learning_rate": 1.2742304240994053e-06, + "loss": 0.458, + "step": 9880 + }, + { + "epoch": 0.84, + "learning_rate": 1.2728817811935657e-06, + "loss": 0.4767, + "step": 9881 + }, + { + "epoch": 0.84, + "learning_rate": 1.2715338038541969e-06, + "loss": 0.4871, + "step": 9882 + }, + { + "epoch": 0.84, + "learning_rate": 1.2701864921840989e-06, + "loss": 0.4445, + "step": 9883 + }, + { + "epoch": 0.84, + "learning_rate": 1.2688398462860262e-06, + "loss": 0.4678, + "step": 9884 + }, + { + "epoch": 0.84, + "learning_rate": 1.26749386626268e-06, + "loss": 0.4655, + "step": 9885 + }, + { + "epoch": 0.84, + "learning_rate": 1.2661485522167062e-06, + "loss": 0.4521, + "step": 9886 + }, + { + "epoch": 0.84, + "learning_rate": 1.2648039042507043e-06, + "loss": 0.4751, + "step": 9887 + }, + { + "epoch": 0.84, + "learning_rate": 1.2634599224672295e-06, + "loss": 0.4386, + "step": 9888 + }, + { + "epoch": 0.84, + "learning_rate": 1.262116606968773e-06, + "loss": 0.4527, + "step": 9889 + }, + { + "epoch": 0.84, + "learning_rate": 1.2607739578577838e-06, + "loss": 0.4406, + "step": 9890 + }, + { + "epoch": 0.84, + "learning_rate": 1.2594319752366578e-06, + "loss": 0.4579, + "step": 9891 + }, + { + "epoch": 0.84, + "learning_rate": 1.2580906592077403e-06, + "loss": 0.4778, + "step": 9892 + }, + { + "epoch": 0.84, + "learning_rate": 1.2567500098733242e-06, + "loss": 0.4538, + "step": 9893 + }, + { + "epoch": 0.84, + "learning_rate": 1.2554100273356552e-06, + "loss": 0.4551, + "step": 9894 + }, + { + "epoch": 0.84, + "learning_rate": 1.2540707116969274e-06, + "loss": 0.4576, + "step": 9895 + }, + { + "epoch": 0.84, + "learning_rate": 1.2527320630592765e-06, + "loss": 0.4668, + "step": 9896 + }, + { + "epoch": 0.84, + "learning_rate": 1.2513940815248005e-06, + "loss": 0.457, + "step": 9897 + }, + { + "epoch": 0.84, + "learning_rate": 1.2500567671955345e-06, + "loss": 0.4352, + "step": 9898 + }, + { + "epoch": 0.84, + "learning_rate": 1.2487201201734689e-06, + "loss": 0.4651, + "step": 9899 + }, + { + "epoch": 0.84, + "learning_rate": 1.2473841405605424e-06, + "loss": 0.4441, + "step": 9900 + }, + { + "epoch": 0.84, + "learning_rate": 1.2460488284586437e-06, + "loss": 0.4704, + "step": 9901 + }, + { + "epoch": 0.84, + "learning_rate": 1.2447141839696065e-06, + "loss": 0.461, + "step": 9902 + }, + { + "epoch": 0.84, + "learning_rate": 1.2433802071952183e-06, + "loss": 0.4555, + "step": 9903 + }, + { + "epoch": 0.84, + "learning_rate": 1.2420468982372158e-06, + "loss": 0.4506, + "step": 9904 + }, + { + "epoch": 0.84, + "learning_rate": 1.2407142571972752e-06, + "loss": 0.4502, + "step": 9905 + }, + { + "epoch": 0.84, + "learning_rate": 1.2393822841770397e-06, + "loss": 0.4612, + "step": 9906 + }, + { + "epoch": 0.84, + "learning_rate": 1.2380509792780826e-06, + "loss": 0.4703, + "step": 9907 + }, + { + "epoch": 0.84, + "learning_rate": 1.236720342601938e-06, + "loss": 0.461, + "step": 9908 + }, + { + "epoch": 0.84, + "learning_rate": 1.2353903742500861e-06, + "loss": 0.4482, + "step": 9909 + }, + { + "epoch": 0.84, + "learning_rate": 1.2340610743239545e-06, + "loss": 0.4521, + "step": 9910 + }, + { + "epoch": 0.85, + "learning_rate": 1.2327324429249232e-06, + "loss": 0.4463, + "step": 9911 + }, + { + "epoch": 0.85, + "learning_rate": 1.2314044801543168e-06, + "loss": 0.454, + "step": 9912 + }, + { + "epoch": 0.85, + "learning_rate": 1.2300771861134153e-06, + "loss": 0.4607, + "step": 9913 + }, + { + "epoch": 0.85, + "learning_rate": 1.2287505609034367e-06, + "loss": 0.4397, + "step": 9914 + }, + { + "epoch": 0.85, + "learning_rate": 1.2274246046255633e-06, + "loss": 0.4569, + "step": 9915 + }, + { + "epoch": 0.85, + "learning_rate": 1.2260993173809122e-06, + "loss": 0.4646, + "step": 9916 + }, + { + "epoch": 0.85, + "learning_rate": 1.2247746992705566e-06, + "loss": 0.4804, + "step": 9917 + }, + { + "epoch": 0.85, + "learning_rate": 1.2234507503955185e-06, + "loss": 0.4593, + "step": 9918 + }, + { + "epoch": 0.85, + "learning_rate": 1.2221274708567664e-06, + "loss": 0.4363, + "step": 9919 + }, + { + "epoch": 0.85, + "learning_rate": 1.2208048607552214e-06, + "loss": 0.4444, + "step": 9920 + }, + { + "epoch": 0.85, + "learning_rate": 1.219482920191748e-06, + "loss": 0.4587, + "step": 9921 + }, + { + "epoch": 0.85, + "learning_rate": 1.2181616492671677e-06, + "loss": 0.4397, + "step": 9922 + }, + { + "epoch": 0.85, + "learning_rate": 1.216841048082239e-06, + "loss": 0.4531, + "step": 9923 + }, + { + "epoch": 0.85, + "learning_rate": 1.2155211167376835e-06, + "loss": 0.4686, + "step": 9924 + }, + { + "epoch": 0.85, + "learning_rate": 1.2142018553341607e-06, + "loss": 0.442, + "step": 9925 + }, + { + "epoch": 0.85, + "learning_rate": 1.2128832639722844e-06, + "loss": 0.4613, + "step": 9926 + }, + { + "epoch": 0.85, + "learning_rate": 1.2115653427526142e-06, + "loss": 0.4493, + "step": 9927 + }, + { + "epoch": 0.85, + "learning_rate": 1.2102480917756632e-06, + "loss": 0.4808, + "step": 9928 + }, + { + "epoch": 0.85, + "learning_rate": 1.2089315111418876e-06, + "loss": 0.4564, + "step": 9929 + }, + { + "epoch": 0.85, + "learning_rate": 1.2076156009516971e-06, + "loss": 0.4545, + "step": 9930 + }, + { + "epoch": 0.85, + "learning_rate": 1.2063003613054491e-06, + "loss": 0.4444, + "step": 9931 + }, + { + "epoch": 0.85, + "learning_rate": 1.2049857923034468e-06, + "loss": 0.4418, + "step": 9932 + }, + { + "epoch": 0.85, + "learning_rate": 1.2036718940459468e-06, + "loss": 0.4663, + "step": 9933 + }, + { + "epoch": 0.85, + "learning_rate": 1.202358666633151e-06, + "loss": 0.4584, + "step": 9934 + }, + { + "epoch": 0.85, + "learning_rate": 1.2010461101652127e-06, + "loss": 0.4271, + "step": 9935 + }, + { + "epoch": 0.85, + "learning_rate": 1.1997342247422317e-06, + "loss": 0.4541, + "step": 9936 + }, + { + "epoch": 0.85, + "learning_rate": 1.198423010464259e-06, + "loss": 0.4567, + "step": 9937 + }, + { + "epoch": 0.85, + "learning_rate": 1.1971124674312939e-06, + "loss": 0.4396, + "step": 9938 + }, + { + "epoch": 0.85, + "learning_rate": 1.1958025957432816e-06, + "loss": 0.4678, + "step": 9939 + }, + { + "epoch": 0.85, + "learning_rate": 1.1944933955001226e-06, + "loss": 0.4447, + "step": 9940 + }, + { + "epoch": 0.85, + "learning_rate": 1.1931848668016576e-06, + "loss": 0.4352, + "step": 9941 + }, + { + "epoch": 0.85, + "learning_rate": 1.1918770097476818e-06, + "loss": 0.4645, + "step": 9942 + }, + { + "epoch": 0.85, + "learning_rate": 1.190569824437937e-06, + "loss": 0.4762, + "step": 9943 + }, + { + "epoch": 0.85, + "learning_rate": 1.1892633109721163e-06, + "loss": 0.4612, + "step": 9944 + }, + { + "epoch": 0.85, + "learning_rate": 1.1879574694498597e-06, + "loss": 0.4469, + "step": 9945 + }, + { + "epoch": 0.85, + "learning_rate": 1.1866522999707553e-06, + "loss": 0.4616, + "step": 9946 + }, + { + "epoch": 0.85, + "learning_rate": 1.18534780263434e-06, + "loss": 0.4556, + "step": 9947 + }, + { + "epoch": 0.85, + "learning_rate": 1.1840439775401025e-06, + "loss": 0.4508, + "step": 9948 + }, + { + "epoch": 0.85, + "learning_rate": 1.1827408247874795e-06, + "loss": 0.4642, + "step": 9949 + }, + { + "epoch": 0.85, + "learning_rate": 1.1814383444758493e-06, + "loss": 0.4319, + "step": 9950 + }, + { + "epoch": 0.85, + "learning_rate": 1.1801365367045448e-06, + "loss": 0.4683, + "step": 9951 + }, + { + "epoch": 0.85, + "learning_rate": 1.1788354015728543e-06, + "loss": 0.4406, + "step": 9952 + }, + { + "epoch": 0.85, + "learning_rate": 1.1775349391800017e-06, + "loss": 0.4673, + "step": 9953 + }, + { + "epoch": 0.85, + "learning_rate": 1.1762351496251666e-06, + "loss": 0.4466, + "step": 9954 + }, + { + "epoch": 0.85, + "learning_rate": 1.1749360330074799e-06, + "loss": 0.4727, + "step": 9955 + }, + { + "epoch": 0.85, + "learning_rate": 1.173637589426011e-06, + "loss": 0.4624, + "step": 9956 + }, + { + "epoch": 0.85, + "learning_rate": 1.1723398189797897e-06, + "loss": 0.4744, + "step": 9957 + }, + { + "epoch": 0.85, + "learning_rate": 1.171042721767791e-06, + "loss": 0.4442, + "step": 9958 + }, + { + "epoch": 0.85, + "learning_rate": 1.1697462978889307e-06, + "loss": 0.4704, + "step": 9959 + }, + { + "epoch": 0.85, + "learning_rate": 1.1684505474420826e-06, + "loss": 0.4662, + "step": 9960 + }, + { + "epoch": 0.85, + "learning_rate": 1.167155470526069e-06, + "loss": 0.4331, + "step": 9961 + }, + { + "epoch": 0.85, + "learning_rate": 1.1658610672396543e-06, + "loss": 0.4693, + "step": 9962 + }, + { + "epoch": 0.85, + "learning_rate": 1.1645673376815558e-06, + "loss": 0.4713, + "step": 9963 + }, + { + "epoch": 0.85, + "learning_rate": 1.1632742819504406e-06, + "loss": 0.4438, + "step": 9964 + }, + { + "epoch": 0.85, + "learning_rate": 1.1619819001449162e-06, + "loss": 0.4595, + "step": 9965 + }, + { + "epoch": 0.85, + "learning_rate": 1.1606901923635526e-06, + "loss": 0.4424, + "step": 9966 + }, + { + "epoch": 0.85, + "learning_rate": 1.1593991587048604e-06, + "loss": 0.4604, + "step": 9967 + }, + { + "epoch": 0.85, + "learning_rate": 1.1581087992672936e-06, + "loss": 0.4678, + "step": 9968 + }, + { + "epoch": 0.85, + "learning_rate": 1.1568191141492624e-06, + "loss": 0.4613, + "step": 9969 + }, + { + "epoch": 0.85, + "learning_rate": 1.1555301034491284e-06, + "loss": 0.4602, + "step": 9970 + }, + { + "epoch": 0.85, + "learning_rate": 1.1542417672651917e-06, + "loss": 0.4431, + "step": 9971 + }, + { + "epoch": 0.85, + "learning_rate": 1.1529541056957072e-06, + "loss": 0.4528, + "step": 9972 + }, + { + "epoch": 0.85, + "learning_rate": 1.1516671188388805e-06, + "loss": 0.4677, + "step": 9973 + }, + { + "epoch": 0.85, + "learning_rate": 1.1503808067928557e-06, + "loss": 0.4563, + "step": 9974 + }, + { + "epoch": 0.85, + "learning_rate": 1.1490951696557385e-06, + "loss": 0.4433, + "step": 9975 + }, + { + "epoch": 0.85, + "learning_rate": 1.147810207525577e-06, + "loss": 0.4282, + "step": 9976 + }, + { + "epoch": 0.85, + "learning_rate": 1.146525920500363e-06, + "loss": 0.4705, + "step": 9977 + }, + { + "epoch": 0.85, + "learning_rate": 1.1452423086780463e-06, + "loss": 0.4594, + "step": 9978 + }, + { + "epoch": 0.85, + "learning_rate": 1.143959372156518e-06, + "loss": 0.4722, + "step": 9979 + }, + { + "epoch": 0.85, + "learning_rate": 1.14267711103362e-06, + "loss": 0.4484, + "step": 9980 + }, + { + "epoch": 0.85, + "learning_rate": 1.1413955254071441e-06, + "loss": 0.4551, + "step": 9981 + }, + { + "epoch": 0.85, + "learning_rate": 1.140114615374831e-06, + "loss": 0.4644, + "step": 9982 + }, + { + "epoch": 0.85, + "learning_rate": 1.1388343810343627e-06, + "loss": 0.4479, + "step": 9983 + }, + { + "epoch": 0.85, + "learning_rate": 1.137554822483381e-06, + "loss": 0.444, + "step": 9984 + }, + { + "epoch": 0.85, + "learning_rate": 1.136275939819469e-06, + "loss": 0.4556, + "step": 9985 + }, + { + "epoch": 0.85, + "learning_rate": 1.1349977331401573e-06, + "loss": 0.4528, + "step": 9986 + }, + { + "epoch": 0.85, + "learning_rate": 1.1337202025429295e-06, + "loss": 0.452, + "step": 9987 + }, + { + "epoch": 0.85, + "learning_rate": 1.132443348125214e-06, + "loss": 0.4551, + "step": 9988 + }, + { + "epoch": 0.85, + "learning_rate": 1.1311671699843896e-06, + "loss": 0.453, + "step": 9989 + }, + { + "epoch": 0.85, + "learning_rate": 1.129891668217783e-06, + "loss": 0.4525, + "step": 9990 + }, + { + "epoch": 0.85, + "learning_rate": 1.128616842922672e-06, + "loss": 0.4557, + "step": 9991 + }, + { + "epoch": 0.85, + "learning_rate": 1.1273426941962728e-06, + "loss": 0.4703, + "step": 9992 + }, + { + "epoch": 0.85, + "learning_rate": 1.1260692221357638e-06, + "loss": 0.4475, + "step": 9993 + }, + { + "epoch": 0.85, + "learning_rate": 1.1247964268382661e-06, + "loss": 0.4385, + "step": 9994 + }, + { + "epoch": 0.85, + "learning_rate": 1.123524308400844e-06, + "loss": 0.466, + "step": 9995 + }, + { + "epoch": 0.85, + "learning_rate": 1.1222528669205158e-06, + "loss": 0.4458, + "step": 9996 + }, + { + "epoch": 0.85, + "learning_rate": 1.120982102494247e-06, + "loss": 0.4526, + "step": 9997 + }, + { + "epoch": 0.85, + "learning_rate": 1.1197120152189522e-06, + "loss": 0.4408, + "step": 9998 + }, + { + "epoch": 0.85, + "learning_rate": 1.1184426051914932e-06, + "loss": 0.4658, + "step": 9999 + }, + { + "epoch": 0.85, + "learning_rate": 1.1171738725086833e-06, + "loss": 0.4664, + "step": 10000 + }, + { + "epoch": 0.85, + "learning_rate": 1.1159058172672732e-06, + "loss": 0.4579, + "step": 10001 + }, + { + "epoch": 0.85, + "learning_rate": 1.1146384395639786e-06, + "loss": 0.4572, + "step": 10002 + }, + { + "epoch": 0.85, + "learning_rate": 1.1133717394954536e-06, + "loss": 0.4424, + "step": 10003 + }, + { + "epoch": 0.85, + "learning_rate": 1.1121057171582984e-06, + "loss": 0.4572, + "step": 10004 + }, + { + "epoch": 0.85, + "learning_rate": 1.1108403726490669e-06, + "loss": 0.4548, + "step": 10005 + }, + { + "epoch": 0.85, + "learning_rate": 1.1095757060642588e-06, + "loss": 0.4449, + "step": 10006 + }, + { + "epoch": 0.85, + "learning_rate": 1.1083117175003245e-06, + "loss": 0.4556, + "step": 10007 + }, + { + "epoch": 0.85, + "learning_rate": 1.1070484070536613e-06, + "loss": 0.4641, + "step": 10008 + }, + { + "epoch": 0.85, + "learning_rate": 1.1057857748206148e-06, + "loss": 0.474, + "step": 10009 + }, + { + "epoch": 0.85, + "learning_rate": 1.104523820897474e-06, + "loss": 0.4553, + "step": 10010 + }, + { + "epoch": 0.85, + "learning_rate": 1.1032625453804835e-06, + "loss": 0.4554, + "step": 10011 + }, + { + "epoch": 0.85, + "learning_rate": 1.1020019483658385e-06, + "loss": 0.4509, + "step": 10012 + }, + { + "epoch": 0.85, + "learning_rate": 1.1007420299496696e-06, + "loss": 0.4401, + "step": 10013 + }, + { + "epoch": 0.85, + "learning_rate": 1.0994827902280681e-06, + "loss": 0.4813, + "step": 10014 + }, + { + "epoch": 0.85, + "learning_rate": 1.0982242292970668e-06, + "loss": 0.4585, + "step": 10015 + }, + { + "epoch": 0.85, + "learning_rate": 1.0969663472526492e-06, + "loss": 0.4447, + "step": 10016 + }, + { + "epoch": 0.85, + "learning_rate": 1.0957091441907475e-06, + "loss": 0.4292, + "step": 10017 + }, + { + "epoch": 0.85, + "learning_rate": 1.0944526202072424e-06, + "loss": 0.484, + "step": 10018 + }, + { + "epoch": 0.85, + "learning_rate": 1.093196775397959e-06, + "loss": 0.4516, + "step": 10019 + }, + { + "epoch": 0.85, + "learning_rate": 1.0919416098586711e-06, + "loss": 0.451, + "step": 10020 + }, + { + "epoch": 0.85, + "learning_rate": 1.0906871236851114e-06, + "loss": 0.4504, + "step": 10021 + }, + { + "epoch": 0.85, + "learning_rate": 1.0894333169729432e-06, + "loss": 0.4458, + "step": 10022 + }, + { + "epoch": 0.85, + "learning_rate": 1.0881801898177924e-06, + "loss": 0.455, + "step": 10023 + }, + { + "epoch": 0.85, + "learning_rate": 1.0869277423152248e-06, + "loss": 0.4511, + "step": 10024 + }, + { + "epoch": 0.85, + "learning_rate": 1.0856759745607592e-06, + "loss": 0.4793, + "step": 10025 + }, + { + "epoch": 0.85, + "learning_rate": 1.0844248866498598e-06, + "loss": 0.4239, + "step": 10026 + }, + { + "epoch": 0.85, + "learning_rate": 1.083174478677942e-06, + "loss": 0.4493, + "step": 10027 + }, + { + "epoch": 0.86, + "learning_rate": 1.0819247507403629e-06, + "loss": 0.4518, + "step": 10028 + }, + { + "epoch": 0.86, + "learning_rate": 1.0806757029324321e-06, + "loss": 0.457, + "step": 10029 + }, + { + "epoch": 0.86, + "learning_rate": 1.0794273353494144e-06, + "loss": 0.4613, + "step": 10030 + }, + { + "epoch": 0.86, + "learning_rate": 1.078179648086507e-06, + "loss": 0.4527, + "step": 10031 + }, + { + "epoch": 0.86, + "learning_rate": 1.076932641238868e-06, + "loss": 0.4446, + "step": 10032 + }, + { + "epoch": 0.86, + "learning_rate": 1.0756863149015972e-06, + "loss": 0.4473, + "step": 10033 + }, + { + "epoch": 0.86, + "learning_rate": 1.0744406691697474e-06, + "loss": 0.4778, + "step": 10034 + }, + { + "epoch": 0.86, + "learning_rate": 1.0731957041383146e-06, + "loss": 0.4777, + "step": 10035 + }, + { + "epoch": 0.86, + "learning_rate": 1.0719514199022473e-06, + "loss": 0.4481, + "step": 10036 + }, + { + "epoch": 0.86, + "learning_rate": 1.0707078165564366e-06, + "loss": 0.4598, + "step": 10037 + }, + { + "epoch": 0.86, + "learning_rate": 1.0694648941957241e-06, + "loss": 0.4915, + "step": 10038 + }, + { + "epoch": 0.86, + "learning_rate": 1.0682226529149076e-06, + "loss": 0.4472, + "step": 10039 + }, + { + "epoch": 0.86, + "learning_rate": 1.0669810928087176e-06, + "loss": 0.4595, + "step": 10040 + }, + { + "epoch": 0.86, + "learning_rate": 1.0657402139718442e-06, + "loss": 0.4385, + "step": 10041 + }, + { + "epoch": 0.86, + "learning_rate": 1.0645000164989217e-06, + "loss": 0.4318, + "step": 10042 + }, + { + "epoch": 0.86, + "learning_rate": 1.063260500484532e-06, + "loss": 0.4712, + "step": 10043 + }, + { + "epoch": 0.86, + "learning_rate": 1.0620216660232074e-06, + "loss": 0.4646, + "step": 10044 + }, + { + "epoch": 0.86, + "learning_rate": 1.0607835132094258e-06, + "loss": 0.4607, + "step": 10045 + }, + { + "epoch": 0.86, + "learning_rate": 1.0595460421376125e-06, + "loss": 0.4341, + "step": 10046 + }, + { + "epoch": 0.86, + "learning_rate": 1.0583092529021411e-06, + "loss": 0.4243, + "step": 10047 + }, + { + "epoch": 0.86, + "learning_rate": 1.0570731455973415e-06, + "loss": 0.4519, + "step": 10048 + }, + { + "epoch": 0.86, + "learning_rate": 1.0558377203174764e-06, + "loss": 0.4485, + "step": 10049 + }, + { + "epoch": 0.86, + "learning_rate": 1.054602977156768e-06, + "loss": 0.461, + "step": 10050 + }, + { + "epoch": 0.86, + "learning_rate": 1.053368916209382e-06, + "loss": 0.4834, + "step": 10051 + }, + { + "epoch": 0.86, + "learning_rate": 1.052135537569433e-06, + "loss": 0.4525, + "step": 10052 + }, + { + "epoch": 0.86, + "learning_rate": 1.0509028413309851e-06, + "loss": 0.4573, + "step": 10053 + }, + { + "epoch": 0.86, + "learning_rate": 1.0496708275880497e-06, + "loss": 0.4669, + "step": 10054 + }, + { + "epoch": 0.86, + "learning_rate": 1.0484394964345812e-06, + "loss": 0.4563, + "step": 10055 + }, + { + "epoch": 0.86, + "learning_rate": 1.0472088479644882e-06, + "loss": 0.447, + "step": 10056 + }, + { + "epoch": 0.86, + "learning_rate": 1.0459788822716255e-06, + "loss": 0.4527, + "step": 10057 + }, + { + "epoch": 0.86, + "learning_rate": 1.0447495994497958e-06, + "loss": 0.4441, + "step": 10058 + }, + { + "epoch": 0.86, + "learning_rate": 1.0435209995927476e-06, + "loss": 0.4777, + "step": 10059 + }, + { + "epoch": 0.86, + "learning_rate": 1.0422930827941803e-06, + "loss": 0.4445, + "step": 10060 + }, + { + "epoch": 0.86, + "learning_rate": 1.041065849147741e-06, + "loss": 0.4542, + "step": 10061 + }, + { + "epoch": 0.86, + "learning_rate": 1.0398392987470208e-06, + "loss": 0.479, + "step": 10062 + }, + { + "epoch": 0.86, + "learning_rate": 1.0386134316855667e-06, + "loss": 0.4476, + "step": 10063 + }, + { + "epoch": 0.86, + "learning_rate": 1.037388248056862e-06, + "loss": 0.4483, + "step": 10064 + }, + { + "epoch": 0.86, + "learning_rate": 1.0361637479543474e-06, + "loss": 0.4409, + "step": 10065 + }, + { + "epoch": 0.86, + "learning_rate": 1.034939931471408e-06, + "loss": 0.4653, + "step": 10066 + }, + { + "epoch": 0.86, + "learning_rate": 1.0337167987013785e-06, + "loss": 0.4398, + "step": 10067 + }, + { + "epoch": 0.86, + "learning_rate": 1.0324943497375383e-06, + "loss": 0.452, + "step": 10068 + }, + { + "epoch": 0.86, + "learning_rate": 1.0312725846731174e-06, + "loss": 0.4388, + "step": 10069 + }, + { + "epoch": 0.86, + "learning_rate": 1.0300515036012926e-06, + "loss": 0.4548, + "step": 10070 + }, + { + "epoch": 0.86, + "learning_rate": 1.028831106615188e-06, + "loss": 0.4606, + "step": 10071 + }, + { + "epoch": 0.86, + "learning_rate": 1.0276113938078768e-06, + "loss": 0.4446, + "step": 10072 + }, + { + "epoch": 0.86, + "learning_rate": 1.0263923652723816e-06, + "loss": 0.4434, + "step": 10073 + }, + { + "epoch": 0.86, + "learning_rate": 1.0251740211016658e-06, + "loss": 0.4432, + "step": 10074 + }, + { + "epoch": 0.86, + "learning_rate": 1.0239563613886495e-06, + "loss": 0.4612, + "step": 10075 + }, + { + "epoch": 0.86, + "learning_rate": 1.0227393862261937e-06, + "loss": 0.4573, + "step": 10076 + }, + { + "epoch": 0.86, + "learning_rate": 1.0215230957071108e-06, + "loss": 0.4421, + "step": 10077 + }, + { + "epoch": 0.86, + "learning_rate": 1.0203074899241616e-06, + "loss": 0.4483, + "step": 10078 + }, + { + "epoch": 0.86, + "learning_rate": 1.0190925689700514e-06, + "loss": 0.4615, + "step": 10079 + }, + { + "epoch": 0.86, + "learning_rate": 1.0178783329374363e-06, + "loss": 0.4921, + "step": 10080 + }, + { + "epoch": 0.86, + "learning_rate": 1.0166647819189202e-06, + "loss": 0.4654, + "step": 10081 + }, + { + "epoch": 0.86, + "learning_rate": 1.0154519160070519e-06, + "loss": 0.4454, + "step": 10082 + }, + { + "epoch": 0.86, + "learning_rate": 1.014239735294329e-06, + "loss": 0.4602, + "step": 10083 + }, + { + "epoch": 0.86, + "learning_rate": 1.0130282398731984e-06, + "loss": 0.4664, + "step": 10084 + }, + { + "epoch": 0.86, + "learning_rate": 1.011817429836054e-06, + "loss": 0.4709, + "step": 10085 + }, + { + "epoch": 0.86, + "learning_rate": 1.0106073052752364e-06, + "loss": 0.4568, + "step": 10086 + }, + { + "epoch": 0.86, + "learning_rate": 1.0093978662830351e-06, + "loss": 0.4502, + "step": 10087 + }, + { + "epoch": 0.86, + "learning_rate": 1.0081891129516896e-06, + "loss": 0.456, + "step": 10088 + }, + { + "epoch": 0.86, + "learning_rate": 1.0069810453733774e-06, + "loss": 0.4526, + "step": 10089 + }, + { + "epoch": 0.86, + "learning_rate": 1.0057736636402382e-06, + "loss": 0.4623, + "step": 10090 + }, + { + "epoch": 0.86, + "learning_rate": 1.0045669678443504e-06, + "loss": 0.4509, + "step": 10091 + }, + { + "epoch": 0.86, + "learning_rate": 1.0033609580777392e-06, + "loss": 0.4564, + "step": 10092 + }, + { + "epoch": 0.86, + "learning_rate": 1.0021556344323812e-06, + "loss": 0.4641, + "step": 10093 + }, + { + "epoch": 0.86, + "learning_rate": 1.0009509970001985e-06, + "loss": 0.4524, + "step": 10094 + }, + { + "epoch": 0.86, + "learning_rate": 9.99747045873063e-07, + "loss": 0.4484, + "step": 10095 + }, + { + "epoch": 0.86, + "learning_rate": 9.985437811427934e-07, + "loss": 0.4612, + "step": 10096 + }, + { + "epoch": 0.86, + "learning_rate": 9.973412029011564e-07, + "loss": 0.4455, + "step": 10097 + }, + { + "epoch": 0.86, + "learning_rate": 9.961393112398599e-07, + "loss": 0.4557, + "step": 10098 + }, + { + "epoch": 0.86, + "learning_rate": 9.949381062505726e-07, + "loss": 0.433, + "step": 10099 + }, + { + "epoch": 0.86, + "learning_rate": 9.937375880249012e-07, + "loss": 0.4749, + "step": 10100 + }, + { + "epoch": 0.86, + "learning_rate": 9.925377566544003e-07, + "loss": 0.4745, + "step": 10101 + }, + { + "epoch": 0.86, + "learning_rate": 9.913386122305747e-07, + "loss": 0.4432, + "step": 10102 + }, + { + "epoch": 0.86, + "learning_rate": 9.901401548448764e-07, + "loss": 0.466, + "step": 10103 + }, + { + "epoch": 0.86, + "learning_rate": 9.889423845887048e-07, + "loss": 0.4176, + "step": 10104 + }, + { + "epoch": 0.86, + "learning_rate": 9.877453015534066e-07, + "loss": 0.4752, + "step": 10105 + }, + { + "epoch": 0.86, + "learning_rate": 9.865489058302791e-07, + "loss": 0.4692, + "step": 10106 + }, + { + "epoch": 0.86, + "learning_rate": 9.85353197510559e-07, + "loss": 0.4506, + "step": 10107 + }, + { + "epoch": 0.86, + "learning_rate": 9.841581766854402e-07, + "loss": 0.4561, + "step": 10108 + }, + { + "epoch": 0.86, + "learning_rate": 9.829638434460609e-07, + "loss": 0.453, + "step": 10109 + }, + { + "epoch": 0.86, + "learning_rate": 9.817701978835026e-07, + "loss": 0.4542, + "step": 10110 + }, + { + "epoch": 0.86, + "learning_rate": 9.80577240088798e-07, + "loss": 0.4442, + "step": 10111 + }, + { + "epoch": 0.86, + "learning_rate": 9.79384970152928e-07, + "loss": 0.4604, + "step": 10112 + }, + { + "epoch": 0.86, + "learning_rate": 9.781933881668203e-07, + "loss": 0.4398, + "step": 10113 + }, + { + "epoch": 0.86, + "learning_rate": 9.770024942213507e-07, + "loss": 0.4777, + "step": 10114 + }, + { + "epoch": 0.86, + "learning_rate": 9.758122884073417e-07, + "loss": 0.4495, + "step": 10115 + }, + { + "epoch": 0.86, + "learning_rate": 9.746227708155586e-07, + "loss": 0.4469, + "step": 10116 + }, + { + "epoch": 0.86, + "learning_rate": 9.734339415367254e-07, + "loss": 0.4524, + "step": 10117 + }, + { + "epoch": 0.86, + "learning_rate": 9.722458006615066e-07, + "loss": 0.4559, + "step": 10118 + }, + { + "epoch": 0.86, + "learning_rate": 9.710583482805102e-07, + "loss": 0.4655, + "step": 10119 + }, + { + "epoch": 0.86, + "learning_rate": 9.698715844842988e-07, + "loss": 0.4364, + "step": 10120 + }, + { + "epoch": 0.86, + "learning_rate": 9.686855093633807e-07, + "loss": 0.455, + "step": 10121 + }, + { + "epoch": 0.86, + "learning_rate": 9.675001230082092e-07, + "loss": 0.4518, + "step": 10122 + }, + { + "epoch": 0.86, + "learning_rate": 9.663154255091889e-07, + "loss": 0.4498, + "step": 10123 + }, + { + "epoch": 0.86, + "learning_rate": 9.651314169566694e-07, + "loss": 0.4634, + "step": 10124 + }, + { + "epoch": 0.86, + "learning_rate": 9.639480974409453e-07, + "loss": 0.4433, + "step": 10125 + }, + { + "epoch": 0.86, + "learning_rate": 9.627654670522646e-07, + "loss": 0.4675, + "step": 10126 + }, + { + "epoch": 0.86, + "learning_rate": 9.615835258808203e-07, + "loss": 0.4464, + "step": 10127 + }, + { + "epoch": 0.86, + "learning_rate": 9.604022740167496e-07, + "loss": 0.4775, + "step": 10128 + }, + { + "epoch": 0.86, + "learning_rate": 9.5922171155014e-07, + "loss": 0.448, + "step": 10129 + }, + { + "epoch": 0.86, + "learning_rate": 9.580418385710278e-07, + "loss": 0.4555, + "step": 10130 + }, + { + "epoch": 0.86, + "learning_rate": 9.568626551693927e-07, + "loss": 0.4499, + "step": 10131 + }, + { + "epoch": 0.86, + "learning_rate": 9.556841614351664e-07, + "loss": 0.4456, + "step": 10132 + }, + { + "epoch": 0.86, + "learning_rate": 9.545063574582258e-07, + "loss": 0.4528, + "step": 10133 + }, + { + "epoch": 0.86, + "learning_rate": 9.533292433283914e-07, + "loss": 0.4586, + "step": 10134 + }, + { + "epoch": 0.86, + "learning_rate": 9.52152819135439e-07, + "loss": 0.4541, + "step": 10135 + }, + { + "epoch": 0.86, + "learning_rate": 9.50977084969088e-07, + "loss": 0.4389, + "step": 10136 + }, + { + "epoch": 0.86, + "learning_rate": 9.498020409190012e-07, + "loss": 0.4731, + "step": 10137 + }, + { + "epoch": 0.86, + "learning_rate": 9.486276870747946e-07, + "loss": 0.4401, + "step": 10138 + }, + { + "epoch": 0.86, + "learning_rate": 9.474540235260288e-07, + "loss": 0.446, + "step": 10139 + }, + { + "epoch": 0.86, + "learning_rate": 9.462810503622122e-07, + "loss": 0.4586, + "step": 10140 + }, + { + "epoch": 0.86, + "learning_rate": 9.45108767672801e-07, + "loss": 0.4445, + "step": 10141 + }, + { + "epoch": 0.86, + "learning_rate": 9.439371755472005e-07, + "loss": 0.4614, + "step": 10142 + }, + { + "epoch": 0.86, + "learning_rate": 9.427662740747567e-07, + "loss": 0.4439, + "step": 10143 + }, + { + "epoch": 0.86, + "learning_rate": 9.415960633447674e-07, + "loss": 0.4707, + "step": 10144 + }, + { + "epoch": 0.87, + "learning_rate": 9.404265434464844e-07, + "loss": 0.4491, + "step": 10145 + }, + { + "epoch": 0.87, + "learning_rate": 9.392577144690929e-07, + "loss": 0.4493, + "step": 10146 + }, + { + "epoch": 0.87, + "learning_rate": 9.380895765017361e-07, + "loss": 0.4598, + "step": 10147 + }, + { + "epoch": 0.87, + "learning_rate": 9.369221296335007e-07, + "loss": 0.4479, + "step": 10148 + }, + { + "epoch": 0.87, + "learning_rate": 9.357553739534208e-07, + "loss": 0.4593, + "step": 10149 + }, + { + "epoch": 0.87, + "learning_rate": 9.345893095504777e-07, + "loss": 0.4472, + "step": 10150 + }, + { + "epoch": 0.87, + "learning_rate": 9.334239365136033e-07, + "loss": 0.4895, + "step": 10151 + }, + { + "epoch": 0.87, + "learning_rate": 9.3225925493167e-07, + "loss": 0.4482, + "step": 10152 + }, + { + "epoch": 0.87, + "learning_rate": 9.310952648935001e-07, + "loss": 0.4599, + "step": 10153 + }, + { + "epoch": 0.87, + "learning_rate": 9.299319664878703e-07, + "loss": 0.4647, + "step": 10154 + }, + { + "epoch": 0.87, + "learning_rate": 9.28769359803493e-07, + "loss": 0.4689, + "step": 10155 + }, + { + "epoch": 0.87, + "learning_rate": 9.276074449290362e-07, + "loss": 0.4643, + "step": 10156 + }, + { + "epoch": 0.87, + "learning_rate": 9.264462219531112e-07, + "loss": 0.4412, + "step": 10157 + }, + { + "epoch": 0.87, + "learning_rate": 9.252856909642794e-07, + "loss": 0.4676, + "step": 10158 + }, + { + "epoch": 0.87, + "learning_rate": 9.241258520510454e-07, + "loss": 0.4388, + "step": 10159 + }, + { + "epoch": 0.87, + "learning_rate": 9.229667053018665e-07, + "loss": 0.4494, + "step": 10160 + }, + { + "epoch": 0.87, + "learning_rate": 9.218082508051407e-07, + "loss": 0.4549, + "step": 10161 + }, + { + "epoch": 0.87, + "learning_rate": 9.206504886492162e-07, + "loss": 0.455, + "step": 10162 + }, + { + "epoch": 0.87, + "learning_rate": 9.194934189223947e-07, + "loss": 0.4369, + "step": 10163 + }, + { + "epoch": 0.87, + "learning_rate": 9.183370417129122e-07, + "loss": 0.4478, + "step": 10164 + }, + { + "epoch": 0.87, + "learning_rate": 9.171813571089628e-07, + "loss": 0.4521, + "step": 10165 + }, + { + "epoch": 0.87, + "learning_rate": 9.160263651986834e-07, + "loss": 0.4531, + "step": 10166 + }, + { + "epoch": 0.87, + "learning_rate": 9.148720660701549e-07, + "loss": 0.4419, + "step": 10167 + }, + { + "epoch": 0.87, + "learning_rate": 9.137184598114135e-07, + "loss": 0.423, + "step": 10168 + }, + { + "epoch": 0.87, + "learning_rate": 9.125655465104388e-07, + "loss": 0.4534, + "step": 10169 + }, + { + "epoch": 0.87, + "learning_rate": 9.114133262551517e-07, + "loss": 0.4679, + "step": 10170 + }, + { + "epoch": 0.87, + "learning_rate": 9.102617991334273e-07, + "loss": 0.4643, + "step": 10171 + }, + { + "epoch": 0.87, + "learning_rate": 9.091109652330887e-07, + "loss": 0.4434, + "step": 10172 + }, + { + "epoch": 0.87, + "learning_rate": 9.079608246419003e-07, + "loss": 0.4431, + "step": 10173 + }, + { + "epoch": 0.87, + "learning_rate": 9.068113774475784e-07, + "loss": 0.463, + "step": 10174 + }, + { + "epoch": 0.87, + "learning_rate": 9.056626237377841e-07, + "loss": 0.4306, + "step": 10175 + }, + { + "epoch": 0.87, + "learning_rate": 9.045145636001229e-07, + "loss": 0.4532, + "step": 10176 + }, + { + "epoch": 0.87, + "learning_rate": 9.033671971221558e-07, + "loss": 0.4661, + "step": 10177 + }, + { + "epoch": 0.87, + "learning_rate": 9.022205243913851e-07, + "loss": 0.464, + "step": 10178 + }, + { + "epoch": 0.87, + "learning_rate": 9.010745454952563e-07, + "loss": 0.4397, + "step": 10179 + }, + { + "epoch": 0.87, + "learning_rate": 8.999292605211695e-07, + "loss": 0.4377, + "step": 10180 + }, + { + "epoch": 0.87, + "learning_rate": 8.987846695564717e-07, + "loss": 0.4348, + "step": 10181 + }, + { + "epoch": 0.87, + "learning_rate": 8.976407726884495e-07, + "loss": 0.4456, + "step": 10182 + }, + { + "epoch": 0.87, + "learning_rate": 8.964975700043433e-07, + "loss": 0.4446, + "step": 10183 + }, + { + "epoch": 0.87, + "learning_rate": 8.953550615913398e-07, + "loss": 0.4477, + "step": 10184 + }, + { + "epoch": 0.87, + "learning_rate": 8.942132475365672e-07, + "loss": 0.446, + "step": 10185 + }, + { + "epoch": 0.87, + "learning_rate": 8.930721279271093e-07, + "loss": 0.4606, + "step": 10186 + }, + { + "epoch": 0.87, + "learning_rate": 8.91931702849993e-07, + "loss": 0.4689, + "step": 10187 + }, + { + "epoch": 0.87, + "learning_rate": 8.907919723921888e-07, + "loss": 0.4585, + "step": 10188 + }, + { + "epoch": 0.87, + "learning_rate": 8.896529366406181e-07, + "loss": 0.4418, + "step": 10189 + }, + { + "epoch": 0.87, + "learning_rate": 8.885145956821495e-07, + "loss": 0.482, + "step": 10190 + }, + { + "epoch": 0.87, + "learning_rate": 8.873769496035966e-07, + "loss": 0.447, + "step": 10191 + }, + { + "epoch": 0.87, + "learning_rate": 8.862399984917214e-07, + "loss": 0.4593, + "step": 10192 + }, + { + "epoch": 0.87, + "learning_rate": 8.851037424332331e-07, + "loss": 0.4708, + "step": 10193 + }, + { + "epoch": 0.87, + "learning_rate": 8.839681815147871e-07, + "loss": 0.4309, + "step": 10194 + }, + { + "epoch": 0.87, + "learning_rate": 8.828333158229851e-07, + "loss": 0.4706, + "step": 10195 + }, + { + "epoch": 0.87, + "learning_rate": 8.816991454443802e-07, + "loss": 0.4564, + "step": 10196 + }, + { + "epoch": 0.87, + "learning_rate": 8.805656704654642e-07, + "loss": 0.4718, + "step": 10197 + }, + { + "epoch": 0.87, + "learning_rate": 8.794328909726823e-07, + "loss": 0.4562, + "step": 10198 + }, + { + "epoch": 0.87, + "learning_rate": 8.783008070524257e-07, + "loss": 0.4506, + "step": 10199 + }, + { + "epoch": 0.87, + "learning_rate": 8.771694187910307e-07, + "loss": 0.4562, + "step": 10200 + }, + { + "epoch": 0.87, + "learning_rate": 8.760387262747838e-07, + "loss": 0.4582, + "step": 10201 + }, + { + "epoch": 0.87, + "learning_rate": 8.749087295899139e-07, + "loss": 0.4717, + "step": 10202 + }, + { + "epoch": 0.87, + "learning_rate": 8.737794288226009e-07, + "loss": 0.4605, + "step": 10203 + }, + { + "epoch": 0.87, + "learning_rate": 8.726508240589693e-07, + "loss": 0.4481, + "step": 10204 + }, + { + "epoch": 0.87, + "learning_rate": 8.715229153850935e-07, + "loss": 0.492, + "step": 10205 + }, + { + "epoch": 0.87, + "learning_rate": 8.703957028869881e-07, + "loss": 0.4561, + "step": 10206 + }, + { + "epoch": 0.87, + "learning_rate": 8.69269186650622e-07, + "loss": 0.4396, + "step": 10207 + }, + { + "epoch": 0.87, + "learning_rate": 8.681433667619065e-07, + "loss": 0.4584, + "step": 10208 + }, + { + "epoch": 0.87, + "learning_rate": 8.670182433067031e-07, + "loss": 0.4572, + "step": 10209 + }, + { + "epoch": 0.87, + "learning_rate": 8.658938163708175e-07, + "loss": 0.4656, + "step": 10210 + }, + { + "epoch": 0.87, + "learning_rate": 8.647700860400032e-07, + "loss": 0.4721, + "step": 10211 + }, + { + "epoch": 0.87, + "learning_rate": 8.636470523999596e-07, + "loss": 0.4512, + "step": 10212 + }, + { + "epoch": 0.87, + "learning_rate": 8.625247155363358e-07, + "loss": 0.4604, + "step": 10213 + }, + { + "epoch": 0.87, + "learning_rate": 8.614030755347269e-07, + "loss": 0.4521, + "step": 10214 + }, + { + "epoch": 0.87, + "learning_rate": 8.602821324806698e-07, + "loss": 0.46, + "step": 10215 + }, + { + "epoch": 0.87, + "learning_rate": 8.591618864596541e-07, + "loss": 0.4613, + "step": 10216 + }, + { + "epoch": 0.87, + "learning_rate": 8.580423375571156e-07, + "loss": 0.4664, + "step": 10217 + }, + { + "epoch": 0.87, + "learning_rate": 8.569234858584341e-07, + "loss": 0.461, + "step": 10218 + }, + { + "epoch": 0.87, + "learning_rate": 8.5580533144894e-07, + "loss": 0.4491, + "step": 10219 + }, + { + "epoch": 0.87, + "learning_rate": 8.546878744139065e-07, + "loss": 0.4538, + "step": 10220 + }, + { + "epoch": 0.87, + "learning_rate": 8.535711148385572e-07, + "loss": 0.4588, + "step": 10221 + }, + { + "epoch": 0.87, + "learning_rate": 8.524550528080578e-07, + "loss": 0.4614, + "step": 10222 + }, + { + "epoch": 0.87, + "learning_rate": 8.513396884075287e-07, + "loss": 0.4553, + "step": 10223 + }, + { + "epoch": 0.87, + "learning_rate": 8.502250217220276e-07, + "loss": 0.4569, + "step": 10224 + }, + { + "epoch": 0.87, + "learning_rate": 8.491110528365653e-07, + "loss": 0.4723, + "step": 10225 + }, + { + "epoch": 0.87, + "learning_rate": 8.479977818360985e-07, + "loss": 0.4491, + "step": 10226 + }, + { + "epoch": 0.87, + "learning_rate": 8.468852088055291e-07, + "loss": 0.4433, + "step": 10227 + }, + { + "epoch": 0.87, + "learning_rate": 8.457733338297069e-07, + "loss": 0.4471, + "step": 10228 + }, + { + "epoch": 0.87, + "learning_rate": 8.446621569934276e-07, + "loss": 0.464, + "step": 10229 + }, + { + "epoch": 0.87, + "learning_rate": 8.435516783814368e-07, + "loss": 0.4409, + "step": 10230 + }, + { + "epoch": 0.87, + "learning_rate": 8.424418980784177e-07, + "loss": 0.4673, + "step": 10231 + }, + { + "epoch": 0.87, + "learning_rate": 8.413328161690159e-07, + "loss": 0.4807, + "step": 10232 + }, + { + "epoch": 0.87, + "learning_rate": 8.402244327378073e-07, + "loss": 0.4523, + "step": 10233 + }, + { + "epoch": 0.87, + "learning_rate": 8.391167478693241e-07, + "loss": 0.4505, + "step": 10234 + }, + { + "epoch": 0.87, + "learning_rate": 8.380097616480443e-07, + "loss": 0.451, + "step": 10235 + }, + { + "epoch": 0.87, + "learning_rate": 8.369034741583892e-07, + "loss": 0.4687, + "step": 10236 + }, + { + "epoch": 0.87, + "learning_rate": 8.357978854847304e-07, + "loss": 0.4402, + "step": 10237 + }, + { + "epoch": 0.87, + "learning_rate": 8.346929957113848e-07, + "loss": 0.4528, + "step": 10238 + }, + { + "epoch": 0.87, + "learning_rate": 8.335888049226159e-07, + "loss": 0.4608, + "step": 10239 + }, + { + "epoch": 0.87, + "learning_rate": 8.3248531320263e-07, + "loss": 0.4454, + "step": 10240 + }, + { + "epoch": 0.87, + "learning_rate": 8.313825206355919e-07, + "loss": 0.4538, + "step": 10241 + }, + { + "epoch": 0.87, + "learning_rate": 8.302804273055976e-07, + "loss": 0.446, + "step": 10242 + }, + { + "epoch": 0.87, + "learning_rate": 8.291790332967009e-07, + "loss": 0.452, + "step": 10243 + }, + { + "epoch": 0.87, + "learning_rate": 8.280783386928981e-07, + "loss": 0.4447, + "step": 10244 + }, + { + "epoch": 0.87, + "learning_rate": 8.269783435781331e-07, + "loss": 0.4816, + "step": 10245 + }, + { + "epoch": 0.87, + "learning_rate": 8.258790480362955e-07, + "loss": 0.4558, + "step": 10246 + }, + { + "epoch": 0.87, + "learning_rate": 8.247804521512237e-07, + "loss": 0.4583, + "step": 10247 + }, + { + "epoch": 0.87, + "learning_rate": 8.236825560066997e-07, + "loss": 0.4601, + "step": 10248 + }, + { + "epoch": 0.87, + "learning_rate": 8.225853596864519e-07, + "loss": 0.4598, + "step": 10249 + }, + { + "epoch": 0.87, + "learning_rate": 8.214888632741603e-07, + "loss": 0.4572, + "step": 10250 + }, + { + "epoch": 0.87, + "learning_rate": 8.203930668534488e-07, + "loss": 0.4711, + "step": 10251 + }, + { + "epoch": 0.87, + "learning_rate": 8.192979705078852e-07, + "loss": 0.4674, + "step": 10252 + }, + { + "epoch": 0.87, + "learning_rate": 8.182035743209848e-07, + "loss": 0.4322, + "step": 10253 + }, + { + "epoch": 0.87, + "learning_rate": 8.171098783762132e-07, + "loss": 0.4635, + "step": 10254 + }, + { + "epoch": 0.87, + "learning_rate": 8.160168827569804e-07, + "loss": 0.462, + "step": 10255 + }, + { + "epoch": 0.87, + "learning_rate": 8.149245875466416e-07, + "loss": 0.4446, + "step": 10256 + }, + { + "epoch": 0.87, + "learning_rate": 8.138329928285027e-07, + "loss": 0.4544, + "step": 10257 + }, + { + "epoch": 0.87, + "learning_rate": 8.12742098685807e-07, + "loss": 0.4608, + "step": 10258 + }, + { + "epoch": 0.87, + "learning_rate": 8.116519052017558e-07, + "loss": 0.4715, + "step": 10259 + }, + { + "epoch": 0.87, + "learning_rate": 8.105624124594924e-07, + "loss": 0.4478, + "step": 10260 + }, + { + "epoch": 0.87, + "learning_rate": 8.094736205421027e-07, + "loss": 0.4566, + "step": 10261 + }, + { + "epoch": 0.88, + "learning_rate": 8.083855295326237e-07, + "loss": 0.4485, + "step": 10262 + }, + { + "epoch": 0.88, + "learning_rate": 8.072981395140378e-07, + "loss": 0.4654, + "step": 10263 + }, + { + "epoch": 0.88, + "learning_rate": 8.062114505692742e-07, + "loss": 0.4516, + "step": 10264 + }, + { + "epoch": 0.88, + "learning_rate": 8.051254627812088e-07, + "loss": 0.4475, + "step": 10265 + }, + { + "epoch": 0.88, + "learning_rate": 8.040401762326655e-07, + "loss": 0.4618, + "step": 10266 + }, + { + "epoch": 0.88, + "learning_rate": 8.029555910064069e-07, + "loss": 0.4352, + "step": 10267 + }, + { + "epoch": 0.88, + "learning_rate": 8.018717071851512e-07, + "loss": 0.4856, + "step": 10268 + }, + { + "epoch": 0.88, + "learning_rate": 8.007885248515624e-07, + "loss": 0.4282, + "step": 10269 + }, + { + "epoch": 0.88, + "learning_rate": 7.997060440882453e-07, + "loss": 0.4323, + "step": 10270 + }, + { + "epoch": 0.88, + "learning_rate": 7.986242649777553e-07, + "loss": 0.4573, + "step": 10271 + }, + { + "epoch": 0.88, + "learning_rate": 7.97543187602593e-07, + "loss": 0.473, + "step": 10272 + }, + { + "epoch": 0.88, + "learning_rate": 7.964628120452067e-07, + "loss": 0.458, + "step": 10273 + }, + { + "epoch": 0.88, + "learning_rate": 7.953831383879895e-07, + "loss": 0.4484, + "step": 10274 + }, + { + "epoch": 0.88, + "learning_rate": 7.943041667132845e-07, + "loss": 0.4618, + "step": 10275 + }, + { + "epoch": 0.88, + "learning_rate": 7.932258971033746e-07, + "loss": 0.4482, + "step": 10276 + }, + { + "epoch": 0.88, + "learning_rate": 7.92148329640493e-07, + "loss": 0.4556, + "step": 10277 + }, + { + "epoch": 0.88, + "learning_rate": 7.910714644068251e-07, + "loss": 0.4721, + "step": 10278 + }, + { + "epoch": 0.88, + "learning_rate": 7.899953014844919e-07, + "loss": 0.4489, + "step": 10279 + }, + { + "epoch": 0.88, + "learning_rate": 7.889198409555665e-07, + "loss": 0.4547, + "step": 10280 + }, + { + "epoch": 0.88, + "learning_rate": 7.8784508290207e-07, + "loss": 0.45, + "step": 10281 + }, + { + "epoch": 0.88, + "learning_rate": 7.86771027405967e-07, + "loss": 0.448, + "step": 10282 + }, + { + "epoch": 0.88, + "learning_rate": 7.856976745491696e-07, + "loss": 0.4686, + "step": 10283 + }, + { + "epoch": 0.88, + "learning_rate": 7.846250244135378e-07, + "loss": 0.4561, + "step": 10284 + }, + { + "epoch": 0.88, + "learning_rate": 7.835530770808731e-07, + "loss": 0.4367, + "step": 10285 + }, + { + "epoch": 0.88, + "learning_rate": 7.824818326329264e-07, + "loss": 0.4654, + "step": 10286 + }, + { + "epoch": 0.88, + "learning_rate": 7.814112911514005e-07, + "loss": 0.4697, + "step": 10287 + }, + { + "epoch": 0.88, + "learning_rate": 7.803414527179343e-07, + "loss": 0.4761, + "step": 10288 + }, + { + "epoch": 0.88, + "learning_rate": 7.792723174141192e-07, + "loss": 0.4497, + "step": 10289 + }, + { + "epoch": 0.88, + "learning_rate": 7.782038853214935e-07, + "loss": 0.4412, + "step": 10290 + }, + { + "epoch": 0.88, + "learning_rate": 7.771361565215385e-07, + "loss": 0.4613, + "step": 10291 + }, + { + "epoch": 0.88, + "learning_rate": 7.760691310956847e-07, + "loss": 0.444, + "step": 10292 + }, + { + "epoch": 0.88, + "learning_rate": 7.750028091253104e-07, + "loss": 0.4478, + "step": 10293 + }, + { + "epoch": 0.88, + "learning_rate": 7.739371906917326e-07, + "loss": 0.4683, + "step": 10294 + }, + { + "epoch": 0.88, + "learning_rate": 7.728722758762208e-07, + "loss": 0.4348, + "step": 10295 + }, + { + "epoch": 0.88, + "learning_rate": 7.718080647599946e-07, + "loss": 0.4714, + "step": 10296 + }, + { + "epoch": 0.88, + "learning_rate": 7.7074455742421e-07, + "loss": 0.4445, + "step": 10297 + }, + { + "epoch": 0.88, + "learning_rate": 7.696817539499768e-07, + "loss": 0.449, + "step": 10298 + }, + { + "epoch": 0.88, + "learning_rate": 7.6861965441835e-07, + "loss": 0.4765, + "step": 10299 + }, + { + "epoch": 0.88, + "learning_rate": 7.675582589103248e-07, + "loss": 0.4489, + "step": 10300 + }, + { + "epoch": 0.88, + "learning_rate": 7.664975675068531e-07, + "loss": 0.4371, + "step": 10301 + }, + { + "epoch": 0.88, + "learning_rate": 7.65437580288827e-07, + "loss": 0.4474, + "step": 10302 + }, + { + "epoch": 0.88, + "learning_rate": 7.643782973370817e-07, + "loss": 0.4731, + "step": 10303 + }, + { + "epoch": 0.88, + "learning_rate": 7.633197187324048e-07, + "loss": 0.454, + "step": 10304 + }, + { + "epoch": 0.88, + "learning_rate": 7.622618445555308e-07, + "loss": 0.4405, + "step": 10305 + }, + { + "epoch": 0.88, + "learning_rate": 7.612046748871327e-07, + "loss": 0.4489, + "step": 10306 + }, + { + "epoch": 0.88, + "learning_rate": 7.601482098078372e-07, + "loss": 0.4645, + "step": 10307 + }, + { + "epoch": 0.88, + "learning_rate": 7.590924493982165e-07, + "loss": 0.4477, + "step": 10308 + }, + { + "epoch": 0.88, + "learning_rate": 7.580373937387819e-07, + "loss": 0.4528, + "step": 10309 + }, + { + "epoch": 0.88, + "learning_rate": 7.569830429100012e-07, + "loss": 0.4631, + "step": 10310 + }, + { + "epoch": 0.88, + "learning_rate": 7.559293969922843e-07, + "loss": 0.4534, + "step": 10311 + }, + { + "epoch": 0.88, + "learning_rate": 7.548764560659815e-07, + "loss": 0.4622, + "step": 10312 + }, + { + "epoch": 0.88, + "learning_rate": 7.538242202113965e-07, + "loss": 0.4412, + "step": 10313 + }, + { + "epoch": 0.88, + "learning_rate": 7.527726895087817e-07, + "loss": 0.447, + "step": 10314 + }, + { + "epoch": 0.88, + "learning_rate": 7.517218640383262e-07, + "loss": 0.4291, + "step": 10315 + }, + { + "epoch": 0.88, + "learning_rate": 7.506717438801703e-07, + "loss": 0.472, + "step": 10316 + }, + { + "epoch": 0.88, + "learning_rate": 7.496223291144045e-07, + "loss": 0.46, + "step": 10317 + }, + { + "epoch": 0.88, + "learning_rate": 7.485736198210559e-07, + "loss": 0.4336, + "step": 10318 + }, + { + "epoch": 0.88, + "learning_rate": 7.475256160801081e-07, + "loss": 0.4553, + "step": 10319 + }, + { + "epoch": 0.88, + "learning_rate": 7.464783179714863e-07, + "loss": 0.4685, + "step": 10320 + }, + { + "epoch": 0.88, + "learning_rate": 7.454317255750587e-07, + "loss": 0.4337, + "step": 10321 + }, + { + "epoch": 0.88, + "learning_rate": 7.443858389706449e-07, + "loss": 0.4493, + "step": 10322 + }, + { + "epoch": 0.88, + "learning_rate": 7.433406582380076e-07, + "loss": 0.4327, + "step": 10323 + }, + { + "epoch": 0.88, + "learning_rate": 7.422961834568565e-07, + "loss": 0.4466, + "step": 10324 + }, + { + "epoch": 0.88, + "learning_rate": 7.41252414706849e-07, + "loss": 0.461, + "step": 10325 + }, + { + "epoch": 0.88, + "learning_rate": 7.402093520675879e-07, + "loss": 0.456, + "step": 10326 + }, + { + "epoch": 0.88, + "learning_rate": 7.391669956186165e-07, + "loss": 0.4352, + "step": 10327 + }, + { + "epoch": 0.88, + "learning_rate": 7.381253454394343e-07, + "loss": 0.4514, + "step": 10328 + }, + { + "epoch": 0.88, + "learning_rate": 7.370844016094836e-07, + "loss": 0.4613, + "step": 10329 + }, + { + "epoch": 0.88, + "learning_rate": 7.36044164208145e-07, + "loss": 0.4518, + "step": 10330 + }, + { + "epoch": 0.88, + "learning_rate": 7.350046333147543e-07, + "loss": 0.439, + "step": 10331 + }, + { + "epoch": 0.88, + "learning_rate": 7.339658090085899e-07, + "loss": 0.4764, + "step": 10332 + }, + { + "epoch": 0.88, + "learning_rate": 7.329276913688788e-07, + "loss": 0.4693, + "step": 10333 + }, + { + "epoch": 0.88, + "learning_rate": 7.318902804747896e-07, + "loss": 0.4467, + "step": 10334 + }, + { + "epoch": 0.88, + "learning_rate": 7.308535764054437e-07, + "loss": 0.4763, + "step": 10335 + }, + { + "epoch": 0.88, + "learning_rate": 7.298175792398976e-07, + "loss": 0.4355, + "step": 10336 + }, + { + "epoch": 0.88, + "learning_rate": 7.287822890571661e-07, + "loss": 0.4473, + "step": 10337 + }, + { + "epoch": 0.88, + "learning_rate": 7.277477059362059e-07, + "loss": 0.4565, + "step": 10338 + }, + { + "epoch": 0.88, + "learning_rate": 7.267138299559129e-07, + "loss": 0.4501, + "step": 10339 + }, + { + "epoch": 0.88, + "learning_rate": 7.256806611951395e-07, + "loss": 0.4693, + "step": 10340 + }, + { + "epoch": 0.88, + "learning_rate": 7.246481997326782e-07, + "loss": 0.4588, + "step": 10341 + }, + { + "epoch": 0.88, + "learning_rate": 7.236164456472672e-07, + "loss": 0.4738, + "step": 10342 + }, + { + "epoch": 0.88, + "learning_rate": 7.225853990175946e-07, + "loss": 0.4685, + "step": 10343 + }, + { + "epoch": 0.88, + "learning_rate": 7.215550599222931e-07, + "loss": 0.4572, + "step": 10344 + }, + { + "epoch": 0.88, + "learning_rate": 7.205254284399366e-07, + "loss": 0.4299, + "step": 10345 + }, + { + "epoch": 0.88, + "learning_rate": 7.194965046490521e-07, + "loss": 0.4613, + "step": 10346 + }, + { + "epoch": 0.88, + "learning_rate": 7.184682886281114e-07, + "loss": 0.44, + "step": 10347 + }, + { + "epoch": 0.88, + "learning_rate": 7.174407804555261e-07, + "loss": 0.4391, + "step": 10348 + }, + { + "epoch": 0.88, + "learning_rate": 7.164139802096604e-07, + "loss": 0.4524, + "step": 10349 + }, + { + "epoch": 0.88, + "learning_rate": 7.153878879688225e-07, + "loss": 0.44, + "step": 10350 + }, + { + "epoch": 0.88, + "learning_rate": 7.143625038112667e-07, + "loss": 0.4359, + "step": 10351 + }, + { + "epoch": 0.88, + "learning_rate": 7.133378278151926e-07, + "loss": 0.4407, + "step": 10352 + }, + { + "epoch": 0.88, + "learning_rate": 7.123138600587476e-07, + "loss": 0.4496, + "step": 10353 + }, + { + "epoch": 0.88, + "learning_rate": 7.112906006200215e-07, + "loss": 0.4552, + "step": 10354 + }, + { + "epoch": 0.88, + "learning_rate": 7.102680495770509e-07, + "loss": 0.4759, + "step": 10355 + }, + { + "epoch": 0.88, + "learning_rate": 7.092462070078265e-07, + "loss": 0.4537, + "step": 10356 + }, + { + "epoch": 0.88, + "learning_rate": 7.082250729902718e-07, + "loss": 0.4146, + "step": 10357 + }, + { + "epoch": 0.88, + "learning_rate": 7.072046476022654e-07, + "loss": 0.4612, + "step": 10358 + }, + { + "epoch": 0.88, + "learning_rate": 7.061849309216285e-07, + "loss": 0.4493, + "step": 10359 + }, + { + "epoch": 0.88, + "learning_rate": 7.051659230261299e-07, + "loss": 0.4512, + "step": 10360 + }, + { + "epoch": 0.88, + "learning_rate": 7.041476239934819e-07, + "loss": 0.4521, + "step": 10361 + }, + { + "epoch": 0.88, + "learning_rate": 7.031300339013481e-07, + "loss": 0.4624, + "step": 10362 + }, + { + "epoch": 0.88, + "learning_rate": 7.021131528273284e-07, + "loss": 0.4513, + "step": 10363 + }, + { + "epoch": 0.88, + "learning_rate": 7.010969808489754e-07, + "loss": 0.4352, + "step": 10364 + }, + { + "epoch": 0.88, + "learning_rate": 7.000815180437925e-07, + "loss": 0.4605, + "step": 10365 + }, + { + "epoch": 0.88, + "learning_rate": 6.990667644892168e-07, + "loss": 0.4449, + "step": 10366 + }, + { + "epoch": 0.88, + "learning_rate": 6.980527202626397e-07, + "loss": 0.4461, + "step": 10367 + }, + { + "epoch": 0.88, + "learning_rate": 6.97039385441397e-07, + "loss": 0.4502, + "step": 10368 + }, + { + "epoch": 0.88, + "learning_rate": 6.960267601027693e-07, + "loss": 0.4718, + "step": 10369 + }, + { + "epoch": 0.88, + "learning_rate": 6.950148443239846e-07, + "loss": 0.4352, + "step": 10370 + }, + { + "epoch": 0.88, + "learning_rate": 6.940036381822135e-07, + "loss": 0.4505, + "step": 10371 + }, + { + "epoch": 0.88, + "learning_rate": 6.929931417545787e-07, + "loss": 0.4626, + "step": 10372 + }, + { + "epoch": 0.88, + "learning_rate": 6.919833551181399e-07, + "loss": 0.442, + "step": 10373 + }, + { + "epoch": 0.88, + "learning_rate": 6.909742783499129e-07, + "loss": 0.4644, + "step": 10374 + }, + { + "epoch": 0.88, + "learning_rate": 6.899659115268498e-07, + "loss": 0.4635, + "step": 10375 + }, + { + "epoch": 0.88, + "learning_rate": 6.889582547258545e-07, + "loss": 0.4532, + "step": 10376 + }, + { + "epoch": 0.88, + "learning_rate": 6.879513080237754e-07, + "loss": 0.4746, + "step": 10377 + }, + { + "epoch": 0.88, + "learning_rate": 6.869450714974058e-07, + "loss": 0.4474, + "step": 10378 + }, + { + "epoch": 0.88, + "learning_rate": 6.859395452234863e-07, + "loss": 0.4501, + "step": 10379 + }, + { + "epoch": 0.89, + "learning_rate": 6.849347292787012e-07, + "loss": 0.4744, + "step": 10380 + }, + { + "epoch": 0.89, + "learning_rate": 6.839306237396859e-07, + "loss": 0.4645, + "step": 10381 + }, + { + "epoch": 0.89, + "learning_rate": 6.829272286830102e-07, + "loss": 0.4603, + "step": 10382 + }, + { + "epoch": 0.89, + "learning_rate": 6.819245441852051e-07, + "loss": 0.4461, + "step": 10383 + }, + { + "epoch": 0.89, + "learning_rate": 6.809225703227352e-07, + "loss": 0.4318, + "step": 10384 + }, + { + "epoch": 0.89, + "learning_rate": 6.799213071720156e-07, + "loss": 0.447, + "step": 10385 + }, + { + "epoch": 0.89, + "learning_rate": 6.789207548094068e-07, + "loss": 0.4407, + "step": 10386 + }, + { + "epoch": 0.89, + "learning_rate": 6.779209133112164e-07, + "loss": 0.4659, + "step": 10387 + }, + { + "epoch": 0.89, + "learning_rate": 6.769217827536956e-07, + "loss": 0.4589, + "step": 10388 + }, + { + "epoch": 0.89, + "learning_rate": 6.759233632130413e-07, + "loss": 0.4557, + "step": 10389 + }, + { + "epoch": 0.89, + "learning_rate": 6.749256547654004e-07, + "loss": 0.4446, + "step": 10390 + }, + { + "epoch": 0.89, + "learning_rate": 6.739286574868575e-07, + "loss": 0.464, + "step": 10391 + }, + { + "epoch": 0.89, + "learning_rate": 6.72932371453453e-07, + "loss": 0.4395, + "step": 10392 + }, + { + "epoch": 0.89, + "learning_rate": 6.719367967411638e-07, + "loss": 0.4454, + "step": 10393 + }, + { + "epoch": 0.89, + "learning_rate": 6.70941933425917e-07, + "loss": 0.4568, + "step": 10394 + }, + { + "epoch": 0.89, + "learning_rate": 6.699477815835875e-07, + "loss": 0.4543, + "step": 10395 + }, + { + "epoch": 0.89, + "learning_rate": 6.689543412899913e-07, + "loss": 0.4547, + "step": 10396 + }, + { + "epoch": 0.89, + "learning_rate": 6.679616126208921e-07, + "loss": 0.4629, + "step": 10397 + }, + { + "epoch": 0.89, + "learning_rate": 6.669695956520017e-07, + "loss": 0.4627, + "step": 10398 + }, + { + "epoch": 0.89, + "learning_rate": 6.659782904589752e-07, + "loss": 0.4567, + "step": 10399 + }, + { + "epoch": 0.89, + "learning_rate": 6.649876971174118e-07, + "loss": 0.4556, + "step": 10400 + }, + { + "epoch": 0.89, + "learning_rate": 6.639978157028581e-07, + "loss": 0.4783, + "step": 10401 + }, + { + "epoch": 0.89, + "learning_rate": 6.630086462908081e-07, + "loss": 0.4499, + "step": 10402 + }, + { + "epoch": 0.89, + "learning_rate": 6.620201889566991e-07, + "loss": 0.4424, + "step": 10403 + }, + { + "epoch": 0.89, + "learning_rate": 6.610324437759153e-07, + "loss": 0.4446, + "step": 10404 + }, + { + "epoch": 0.89, + "learning_rate": 6.600454108237875e-07, + "loss": 0.4431, + "step": 10405 + }, + { + "epoch": 0.89, + "learning_rate": 6.590590901755889e-07, + "loss": 0.4559, + "step": 10406 + }, + { + "epoch": 0.89, + "learning_rate": 6.580734819065415e-07, + "loss": 0.4516, + "step": 10407 + }, + { + "epoch": 0.89, + "learning_rate": 6.57088586091813e-07, + "loss": 0.4536, + "step": 10408 + }, + { + "epoch": 0.89, + "learning_rate": 6.561044028065134e-07, + "loss": 0.4696, + "step": 10409 + }, + { + "epoch": 0.89, + "learning_rate": 6.551209321257013e-07, + "loss": 0.4421, + "step": 10410 + }, + { + "epoch": 0.89, + "learning_rate": 6.541381741243802e-07, + "loss": 0.4728, + "step": 10411 + }, + { + "epoch": 0.89, + "learning_rate": 6.531561288775001e-07, + "loss": 0.4338, + "step": 10412 + }, + { + "epoch": 0.89, + "learning_rate": 6.521747964599556e-07, + "loss": 0.4656, + "step": 10413 + }, + { + "epoch": 0.89, + "learning_rate": 6.51194176946588e-07, + "loss": 0.4815, + "step": 10414 + }, + { + "epoch": 0.89, + "learning_rate": 6.502142704121816e-07, + "loss": 0.4442, + "step": 10415 + }, + { + "epoch": 0.89, + "learning_rate": 6.492350769314693e-07, + "loss": 0.4304, + "step": 10416 + }, + { + "epoch": 0.89, + "learning_rate": 6.482565965791299e-07, + "loss": 0.4654, + "step": 10417 + }, + { + "epoch": 0.89, + "learning_rate": 6.472788294297827e-07, + "loss": 0.4649, + "step": 10418 + }, + { + "epoch": 0.89, + "learning_rate": 6.463017755579992e-07, + "loss": 0.4442, + "step": 10419 + }, + { + "epoch": 0.89, + "learning_rate": 6.453254350382921e-07, + "loss": 0.4444, + "step": 10420 + }, + { + "epoch": 0.89, + "learning_rate": 6.443498079451215e-07, + "loss": 0.4391, + "step": 10421 + }, + { + "epoch": 0.89, + "learning_rate": 6.43374894352895e-07, + "loss": 0.4546, + "step": 10422 + }, + { + "epoch": 0.89, + "learning_rate": 6.424006943359606e-07, + "loss": 0.4642, + "step": 10423 + }, + { + "epoch": 0.89, + "learning_rate": 6.414272079686157e-07, + "loss": 0.441, + "step": 10424 + }, + { + "epoch": 0.89, + "learning_rate": 6.404544353251041e-07, + "loss": 0.4428, + "step": 10425 + }, + { + "epoch": 0.89, + "learning_rate": 6.394823764796121e-07, + "loss": 0.4459, + "step": 10426 + }, + { + "epoch": 0.89, + "learning_rate": 6.385110315062725e-07, + "loss": 0.4438, + "step": 10427 + }, + { + "epoch": 0.89, + "learning_rate": 6.37540400479163e-07, + "loss": 0.4472, + "step": 10428 + }, + { + "epoch": 0.89, + "learning_rate": 6.36570483472313e-07, + "loss": 0.4709, + "step": 10429 + }, + { + "epoch": 0.89, + "learning_rate": 6.356012805596867e-07, + "loss": 0.459, + "step": 10430 + }, + { + "epoch": 0.89, + "learning_rate": 6.346327918152029e-07, + "loss": 0.453, + "step": 10431 + }, + { + "epoch": 0.89, + "learning_rate": 6.336650173127224e-07, + "loss": 0.4512, + "step": 10432 + }, + { + "epoch": 0.89, + "learning_rate": 6.326979571260483e-07, + "loss": 0.4729, + "step": 10433 + }, + { + "epoch": 0.89, + "learning_rate": 6.317316113289373e-07, + "loss": 0.4487, + "step": 10434 + }, + { + "epoch": 0.89, + "learning_rate": 6.30765979995086e-07, + "loss": 0.4295, + "step": 10435 + }, + { + "epoch": 0.89, + "learning_rate": 6.298010631981344e-07, + "loss": 0.4817, + "step": 10436 + }, + { + "epoch": 0.89, + "learning_rate": 6.288368610116724e-07, + "loss": 0.4512, + "step": 10437 + }, + { + "epoch": 0.89, + "learning_rate": 6.278733735092379e-07, + "loss": 0.4655, + "step": 10438 + }, + { + "epoch": 0.89, + "learning_rate": 6.269106007643056e-07, + "loss": 0.4545, + "step": 10439 + }, + { + "epoch": 0.89, + "learning_rate": 6.259485428503021e-07, + "loss": 0.4409, + "step": 10440 + }, + { + "epoch": 0.89, + "learning_rate": 6.249871998405998e-07, + "loss": 0.4529, + "step": 10441 + }, + { + "epoch": 0.89, + "learning_rate": 6.240265718085103e-07, + "loss": 0.4389, + "step": 10442 + }, + { + "epoch": 0.89, + "learning_rate": 6.230666588272993e-07, + "loss": 0.4616, + "step": 10443 + }, + { + "epoch": 0.89, + "learning_rate": 6.221074609701739e-07, + "loss": 0.4284, + "step": 10444 + }, + { + "epoch": 0.89, + "learning_rate": 6.211489783102831e-07, + "loss": 0.4473, + "step": 10445 + }, + { + "epoch": 0.89, + "learning_rate": 6.201912109207264e-07, + "loss": 0.4545, + "step": 10446 + }, + { + "epoch": 0.89, + "learning_rate": 6.192341588745498e-07, + "loss": 0.4512, + "step": 10447 + }, + { + "epoch": 0.89, + "learning_rate": 6.182778222447383e-07, + "loss": 0.4591, + "step": 10448 + }, + { + "epoch": 0.89, + "learning_rate": 6.173222011042279e-07, + "loss": 0.439, + "step": 10449 + }, + { + "epoch": 0.89, + "learning_rate": 6.163672955258982e-07, + "loss": 0.4696, + "step": 10450 + }, + { + "epoch": 0.89, + "learning_rate": 6.154131055825729e-07, + "loss": 0.4419, + "step": 10451 + }, + { + "epoch": 0.89, + "learning_rate": 6.144596313470241e-07, + "loss": 0.4718, + "step": 10452 + }, + { + "epoch": 0.89, + "learning_rate": 6.135068728919691e-07, + "loss": 0.4579, + "step": 10453 + }, + { + "epoch": 0.89, + "learning_rate": 6.125548302900653e-07, + "loss": 0.4768, + "step": 10454 + }, + { + "epoch": 0.89, + "learning_rate": 6.116035036139223e-07, + "loss": 0.4537, + "step": 10455 + }, + { + "epoch": 0.89, + "learning_rate": 6.106528929360911e-07, + "loss": 0.4519, + "step": 10456 + }, + { + "epoch": 0.89, + "learning_rate": 6.097029983290692e-07, + "loss": 0.4568, + "step": 10457 + }, + { + "epoch": 0.89, + "learning_rate": 6.087538198653009e-07, + "loss": 0.4504, + "step": 10458 + }, + { + "epoch": 0.89, + "learning_rate": 6.078053576171738e-07, + "loss": 0.4474, + "step": 10459 + }, + { + "epoch": 0.89, + "learning_rate": 6.06857611657019e-07, + "loss": 0.4472, + "step": 10460 + }, + { + "epoch": 0.89, + "learning_rate": 6.059105820571198e-07, + "loss": 0.4566, + "step": 10461 + }, + { + "epoch": 0.89, + "learning_rate": 6.049642688897007e-07, + "loss": 0.4761, + "step": 10462 + }, + { + "epoch": 0.89, + "learning_rate": 6.04018672226927e-07, + "loss": 0.456, + "step": 10463 + }, + { + "epoch": 0.89, + "learning_rate": 6.030737921409169e-07, + "loss": 0.4552, + "step": 10464 + }, + { + "epoch": 0.89, + "learning_rate": 6.021296287037304e-07, + "loss": 0.466, + "step": 10465 + }, + { + "epoch": 0.89, + "learning_rate": 6.011861819873732e-07, + "loss": 0.4564, + "step": 10466 + }, + { + "epoch": 0.89, + "learning_rate": 6.002434520637968e-07, + "loss": 0.4571, + "step": 10467 + }, + { + "epoch": 0.89, + "learning_rate": 5.99301439004899e-07, + "loss": 0.4487, + "step": 10468 + }, + { + "epoch": 0.89, + "learning_rate": 5.98360142882517e-07, + "loss": 0.4603, + "step": 10469 + }, + { + "epoch": 0.89, + "learning_rate": 5.974195637684422e-07, + "loss": 0.4677, + "step": 10470 + }, + { + "epoch": 0.89, + "learning_rate": 5.964797017344081e-07, + "loss": 0.4658, + "step": 10471 + }, + { + "epoch": 0.89, + "learning_rate": 5.955405568520889e-07, + "loss": 0.4387, + "step": 10472 + }, + { + "epoch": 0.89, + "learning_rate": 5.946021291931092e-07, + "loss": 0.4626, + "step": 10473 + }, + { + "epoch": 0.89, + "learning_rate": 5.936644188290386e-07, + "loss": 0.4465, + "step": 10474 + }, + { + "epoch": 0.89, + "learning_rate": 5.927274258313887e-07, + "loss": 0.4414, + "step": 10475 + }, + { + "epoch": 0.89, + "learning_rate": 5.91791150271619e-07, + "loss": 0.4511, + "step": 10476 + }, + { + "epoch": 0.89, + "learning_rate": 5.908555922211368e-07, + "loss": 0.4489, + "step": 10477 + }, + { + "epoch": 0.89, + "learning_rate": 5.899207517512873e-07, + "loss": 0.4597, + "step": 10478 + }, + { + "epoch": 0.89, + "learning_rate": 5.889866289333645e-07, + "loss": 0.4619, + "step": 10479 + }, + { + "epoch": 0.89, + "learning_rate": 5.880532238386161e-07, + "loss": 0.4463, + "step": 10480 + }, + { + "epoch": 0.89, + "learning_rate": 5.871205365382194e-07, + "loss": 0.4548, + "step": 10481 + }, + { + "epoch": 0.89, + "learning_rate": 5.861885671033097e-07, + "loss": 0.4476, + "step": 10482 + }, + { + "epoch": 0.89, + "learning_rate": 5.852573156049601e-07, + "loss": 0.4371, + "step": 10483 + }, + { + "epoch": 0.89, + "learning_rate": 5.84326782114194e-07, + "loss": 0.4544, + "step": 10484 + }, + { + "epoch": 0.89, + "learning_rate": 5.833969667019757e-07, + "loss": 0.4552, + "step": 10485 + }, + { + "epoch": 0.89, + "learning_rate": 5.824678694392194e-07, + "loss": 0.435, + "step": 10486 + }, + { + "epoch": 0.89, + "learning_rate": 5.815394903967797e-07, + "loss": 0.4524, + "step": 10487 + }, + { + "epoch": 0.89, + "learning_rate": 5.806118296454577e-07, + "loss": 0.4517, + "step": 10488 + }, + { + "epoch": 0.89, + "learning_rate": 5.796848872560045e-07, + "loss": 0.4508, + "step": 10489 + }, + { + "epoch": 0.89, + "learning_rate": 5.787586632991105e-07, + "loss": 0.4388, + "step": 10490 + }, + { + "epoch": 0.89, + "learning_rate": 5.778331578454121e-07, + "loss": 0.4773, + "step": 10491 + }, + { + "epoch": 0.89, + "learning_rate": 5.769083709654933e-07, + "loss": 0.4475, + "step": 10492 + }, + { + "epoch": 0.89, + "learning_rate": 5.759843027298828e-07, + "loss": 0.4611, + "step": 10493 + }, + { + "epoch": 0.89, + "learning_rate": 5.750609532090534e-07, + "loss": 0.4577, + "step": 10494 + }, + { + "epoch": 0.89, + "learning_rate": 5.741383224734254e-07, + "loss": 0.4496, + "step": 10495 + }, + { + "epoch": 0.89, + "learning_rate": 5.732164105933591e-07, + "loss": 0.4445, + "step": 10496 + }, + { + "epoch": 0.9, + "learning_rate": 5.722952176391639e-07, + "loss": 0.4429, + "step": 10497 + }, + { + "epoch": 0.9, + "learning_rate": 5.713747436810968e-07, + "loss": 0.4609, + "step": 10498 + }, + { + "epoch": 0.9, + "learning_rate": 5.70454988789354e-07, + "loss": 0.4463, + "step": 10499 + }, + { + "epoch": 0.9, + "learning_rate": 5.695359530340816e-07, + "loss": 0.4858, + "step": 10500 + }, + { + "epoch": 0.9, + "learning_rate": 5.68617636485368e-07, + "loss": 0.468, + "step": 10501 + }, + { + "epoch": 0.9, + "learning_rate": 5.677000392132481e-07, + "loss": 0.4637, + "step": 10502 + }, + { + "epoch": 0.9, + "learning_rate": 5.667831612877018e-07, + "loss": 0.4538, + "step": 10503 + }, + { + "epoch": 0.9, + "learning_rate": 5.658670027786561e-07, + "loss": 0.4407, + "step": 10504 + }, + { + "epoch": 0.9, + "learning_rate": 5.649515637559766e-07, + "loss": 0.467, + "step": 10505 + }, + { + "epoch": 0.9, + "learning_rate": 5.640368442894806e-07, + "loss": 0.4507, + "step": 10506 + }, + { + "epoch": 0.9, + "learning_rate": 5.631228444489312e-07, + "loss": 0.4645, + "step": 10507 + }, + { + "epoch": 0.9, + "learning_rate": 5.622095643040304e-07, + "loss": 0.4494, + "step": 10508 + }, + { + "epoch": 0.9, + "learning_rate": 5.612970039244292e-07, + "loss": 0.4516, + "step": 10509 + }, + { + "epoch": 0.9, + "learning_rate": 5.603851633797242e-07, + "loss": 0.4709, + "step": 10510 + }, + { + "epoch": 0.9, + "learning_rate": 5.594740427394562e-07, + "loss": 0.4396, + "step": 10511 + }, + { + "epoch": 0.9, + "learning_rate": 5.5856364207311e-07, + "loss": 0.4814, + "step": 10512 + }, + { + "epoch": 0.9, + "learning_rate": 5.576539614501197e-07, + "loss": 0.4567, + "step": 10513 + }, + { + "epoch": 0.9, + "learning_rate": 5.567450009398567e-07, + "loss": 0.4524, + "step": 10514 + }, + { + "epoch": 0.9, + "learning_rate": 5.558367606116433e-07, + "loss": 0.4323, + "step": 10515 + }, + { + "epoch": 0.9, + "learning_rate": 5.549292405347495e-07, + "loss": 0.4515, + "step": 10516 + }, + { + "epoch": 0.9, + "learning_rate": 5.540224407783823e-07, + "loss": 0.4616, + "step": 10517 + }, + { + "epoch": 0.9, + "learning_rate": 5.531163614116986e-07, + "loss": 0.4447, + "step": 10518 + }, + { + "epoch": 0.9, + "learning_rate": 5.522110025038019e-07, + "loss": 0.4713, + "step": 10519 + }, + { + "epoch": 0.9, + "learning_rate": 5.51306364123737e-07, + "loss": 0.4669, + "step": 10520 + }, + { + "epoch": 0.9, + "learning_rate": 5.504024463404967e-07, + "loss": 0.4422, + "step": 10521 + }, + { + "epoch": 0.9, + "learning_rate": 5.494992492230167e-07, + "loss": 0.4644, + "step": 10522 + }, + { + "epoch": 0.9, + "learning_rate": 5.485967728401786e-07, + "loss": 0.4608, + "step": 10523 + }, + { + "epoch": 0.9, + "learning_rate": 5.476950172608064e-07, + "loss": 0.4437, + "step": 10524 + }, + { + "epoch": 0.9, + "learning_rate": 5.467939825536783e-07, + "loss": 0.4377, + "step": 10525 + }, + { + "epoch": 0.9, + "learning_rate": 5.458936687875049e-07, + "loss": 0.4637, + "step": 10526 + }, + { + "epoch": 0.9, + "learning_rate": 5.449940760309502e-07, + "loss": 0.4928, + "step": 10527 + }, + { + "epoch": 0.9, + "learning_rate": 5.440952043526215e-07, + "loss": 0.4462, + "step": 10528 + }, + { + "epoch": 0.9, + "learning_rate": 5.431970538210685e-07, + "loss": 0.4474, + "step": 10529 + }, + { + "epoch": 0.9, + "learning_rate": 5.422996245047896e-07, + "loss": 0.4696, + "step": 10530 + }, + { + "epoch": 0.9, + "learning_rate": 5.414029164722279e-07, + "loss": 0.4761, + "step": 10531 + }, + { + "epoch": 0.9, + "learning_rate": 5.405069297917665e-07, + "loss": 0.4319, + "step": 10532 + }, + { + "epoch": 0.9, + "learning_rate": 5.396116645317384e-07, + "loss": 0.4523, + "step": 10533 + }, + { + "epoch": 0.9, + "learning_rate": 5.387171207604214e-07, + "loss": 0.4515, + "step": 10534 + }, + { + "epoch": 0.9, + "learning_rate": 5.378232985460363e-07, + "loss": 0.4462, + "step": 10535 + }, + { + "epoch": 0.9, + "learning_rate": 5.369301979567498e-07, + "loss": 0.4707, + "step": 10536 + }, + { + "epoch": 0.9, + "learning_rate": 5.36037819060673e-07, + "loss": 0.4835, + "step": 10537 + }, + { + "epoch": 0.9, + "learning_rate": 5.351461619258636e-07, + "loss": 0.4314, + "step": 10538 + }, + { + "epoch": 0.9, + "learning_rate": 5.342552266203227e-07, + "loss": 0.4716, + "step": 10539 + }, + { + "epoch": 0.9, + "learning_rate": 5.333650132119972e-07, + "loss": 0.4538, + "step": 10540 + }, + { + "epoch": 0.9, + "learning_rate": 5.32475521768776e-07, + "loss": 0.4565, + "step": 10541 + }, + { + "epoch": 0.9, + "learning_rate": 5.315867523584984e-07, + "loss": 0.4698, + "step": 10542 + }, + { + "epoch": 0.9, + "learning_rate": 5.306987050489442e-07, + "loss": 0.4589, + "step": 10543 + }, + { + "epoch": 0.9, + "learning_rate": 5.298113799078397e-07, + "loss": 0.4593, + "step": 10544 + }, + { + "epoch": 0.9, + "learning_rate": 5.28924777002856e-07, + "loss": 0.446, + "step": 10545 + }, + { + "epoch": 0.9, + "learning_rate": 5.280388964016093e-07, + "loss": 0.462, + "step": 10546 + }, + { + "epoch": 0.9, + "learning_rate": 5.271537381716607e-07, + "loss": 0.4715, + "step": 10547 + }, + { + "epoch": 0.9, + "learning_rate": 5.262693023805165e-07, + "loss": 0.4589, + "step": 10548 + }, + { + "epoch": 0.9, + "learning_rate": 5.253855890956272e-07, + "loss": 0.4726, + "step": 10549 + }, + { + "epoch": 0.9, + "learning_rate": 5.245025983843888e-07, + "loss": 0.4489, + "step": 10550 + }, + { + "epoch": 0.9, + "learning_rate": 5.236203303141396e-07, + "loss": 0.4665, + "step": 10551 + }, + { + "epoch": 0.9, + "learning_rate": 5.22738784952167e-07, + "loss": 0.4429, + "step": 10552 + }, + { + "epoch": 0.9, + "learning_rate": 5.218579623657016e-07, + "loss": 0.4751, + "step": 10553 + }, + { + "epoch": 0.9, + "learning_rate": 5.209778626219176e-07, + "loss": 0.4545, + "step": 10554 + }, + { + "epoch": 0.9, + "learning_rate": 5.200984857879355e-07, + "loss": 0.4494, + "step": 10555 + }, + { + "epoch": 0.9, + "learning_rate": 5.192198319308206e-07, + "loss": 0.4377, + "step": 10556 + }, + { + "epoch": 0.9, + "learning_rate": 5.183419011175817e-07, + "loss": 0.4402, + "step": 10557 + }, + { + "epoch": 0.9, + "learning_rate": 5.174646934151751e-07, + "loss": 0.4455, + "step": 10558 + }, + { + "epoch": 0.9, + "learning_rate": 5.165882088905005e-07, + "loss": 0.4509, + "step": 10559 + }, + { + "epoch": 0.9, + "learning_rate": 5.157124476103992e-07, + "loss": 0.4483, + "step": 10560 + }, + { + "epoch": 0.9, + "learning_rate": 5.14837409641663e-07, + "loss": 0.4432, + "step": 10561 + }, + { + "epoch": 0.9, + "learning_rate": 5.139630950510243e-07, + "loss": 0.453, + "step": 10562 + }, + { + "epoch": 0.9, + "learning_rate": 5.130895039051642e-07, + "loss": 0.4524, + "step": 10563 + }, + { + "epoch": 0.9, + "learning_rate": 5.122166362707048e-07, + "loss": 0.4533, + "step": 10564 + }, + { + "epoch": 0.9, + "learning_rate": 5.113444922142163e-07, + "loss": 0.4558, + "step": 10565 + }, + { + "epoch": 0.9, + "learning_rate": 5.104730718022077e-07, + "loss": 0.4676, + "step": 10566 + }, + { + "epoch": 0.9, + "learning_rate": 5.096023751011414e-07, + "loss": 0.4567, + "step": 10567 + }, + { + "epoch": 0.9, + "learning_rate": 5.087324021774209e-07, + "loss": 0.4788, + "step": 10568 + }, + { + "epoch": 0.9, + "learning_rate": 5.078631530973921e-07, + "loss": 0.4502, + "step": 10569 + }, + { + "epoch": 0.9, + "learning_rate": 5.069946279273464e-07, + "loss": 0.4363, + "step": 10570 + }, + { + "epoch": 0.9, + "learning_rate": 5.061268267335228e-07, + "loss": 0.4472, + "step": 10571 + }, + { + "epoch": 0.9, + "learning_rate": 5.052597495821032e-07, + "loss": 0.463, + "step": 10572 + }, + { + "epoch": 0.9, + "learning_rate": 5.043933965392134e-07, + "loss": 0.4596, + "step": 10573 + }, + { + "epoch": 0.9, + "learning_rate": 5.035277676709294e-07, + "loss": 0.4552, + "step": 10574 + }, + { + "epoch": 0.9, + "learning_rate": 5.026628630432607e-07, + "loss": 0.4732, + "step": 10575 + }, + { + "epoch": 0.9, + "learning_rate": 5.017986827221733e-07, + "loss": 0.493, + "step": 10576 + }, + { + "epoch": 0.9, + "learning_rate": 5.009352267735734e-07, + "loss": 0.4377, + "step": 10577 + }, + { + "epoch": 0.9, + "learning_rate": 5.000724952633096e-07, + "loss": 0.4587, + "step": 10578 + }, + { + "epoch": 0.9, + "learning_rate": 4.99210488257178e-07, + "loss": 0.4616, + "step": 10579 + }, + { + "epoch": 0.9, + "learning_rate": 4.983492058209194e-07, + "loss": 0.4479, + "step": 10580 + }, + { + "epoch": 0.9, + "learning_rate": 4.97488648020219e-07, + "loss": 0.4772, + "step": 10581 + }, + { + "epoch": 0.9, + "learning_rate": 4.966288149207055e-07, + "loss": 0.4649, + "step": 10582 + }, + { + "epoch": 0.9, + "learning_rate": 4.957697065879563e-07, + "loss": 0.4436, + "step": 10583 + }, + { + "epoch": 0.9, + "learning_rate": 4.949113230874846e-07, + "loss": 0.4639, + "step": 10584 + }, + { + "epoch": 0.9, + "learning_rate": 4.940536644847593e-07, + "loss": 0.4348, + "step": 10585 + }, + { + "epoch": 0.9, + "learning_rate": 4.931967308451891e-07, + "loss": 0.4544, + "step": 10586 + }, + { + "epoch": 0.9, + "learning_rate": 4.923405222341248e-07, + "loss": 0.4567, + "step": 10587 + }, + { + "epoch": 0.9, + "learning_rate": 4.914850387168657e-07, + "loss": 0.4472, + "step": 10588 + }, + { + "epoch": 0.9, + "learning_rate": 4.906302803586538e-07, + "loss": 0.4429, + "step": 10589 + }, + { + "epoch": 0.9, + "learning_rate": 4.897762472246781e-07, + "loss": 0.4335, + "step": 10590 + }, + { + "epoch": 0.9, + "learning_rate": 4.889229393800687e-07, + "loss": 0.4474, + "step": 10591 + }, + { + "epoch": 0.9, + "learning_rate": 4.880703568899047e-07, + "loss": 0.473, + "step": 10592 + }, + { + "epoch": 0.9, + "learning_rate": 4.872184998192053e-07, + "loss": 0.4456, + "step": 10593 + }, + { + "epoch": 0.9, + "learning_rate": 4.863673682329373e-07, + "loss": 0.4505, + "step": 10594 + }, + { + "epoch": 0.9, + "learning_rate": 4.855169621960143e-07, + "loss": 0.4486, + "step": 10595 + }, + { + "epoch": 0.9, + "learning_rate": 4.846672817732889e-07, + "loss": 0.4655, + "step": 10596 + }, + { + "epoch": 0.9, + "learning_rate": 4.838183270295604e-07, + "loss": 0.4487, + "step": 10597 + }, + { + "epoch": 0.9, + "learning_rate": 4.82970098029576e-07, + "loss": 0.4375, + "step": 10598 + }, + { + "epoch": 0.9, + "learning_rate": 4.821225948380237e-07, + "loss": 0.4485, + "step": 10599 + }, + { + "epoch": 0.9, + "learning_rate": 4.812758175195397e-07, + "loss": 0.4247, + "step": 10600 + }, + { + "epoch": 0.9, + "learning_rate": 4.804297661387014e-07, + "loss": 0.4539, + "step": 10601 + }, + { + "epoch": 0.9, + "learning_rate": 4.795844407600292e-07, + "loss": 0.4486, + "step": 10602 + }, + { + "epoch": 0.9, + "learning_rate": 4.78739841447996e-07, + "loss": 0.4438, + "step": 10603 + }, + { + "epoch": 0.9, + "learning_rate": 4.778959682670147e-07, + "loss": 0.4709, + "step": 10604 + }, + { + "epoch": 0.9, + "learning_rate": 4.770528212814385e-07, + "loss": 0.4342, + "step": 10605 + }, + { + "epoch": 0.9, + "learning_rate": 4.762104005555701e-07, + "loss": 0.4571, + "step": 10606 + }, + { + "epoch": 0.9, + "learning_rate": 4.7536870615365825e-07, + "loss": 0.4553, + "step": 10607 + }, + { + "epoch": 0.9, + "learning_rate": 4.7452773813989385e-07, + "loss": 0.4431, + "step": 10608 + }, + { + "epoch": 0.9, + "learning_rate": 4.7368749657840997e-07, + "loss": 0.4532, + "step": 10609 + }, + { + "epoch": 0.9, + "learning_rate": 4.728479815332909e-07, + "loss": 0.431, + "step": 10610 + }, + { + "epoch": 0.9, + "learning_rate": 4.7200919306855883e-07, + "loss": 0.4619, + "step": 10611 + }, + { + "epoch": 0.9, + "learning_rate": 4.711711312481815e-07, + "loss": 0.4673, + "step": 10612 + }, + { + "epoch": 0.9, + "learning_rate": 4.7033379613607876e-07, + "loss": 0.4507, + "step": 10613 + }, + { + "epoch": 0.91, + "learning_rate": 4.694971877961041e-07, + "loss": 0.4574, + "step": 10614 + }, + { + "epoch": 0.91, + "learning_rate": 4.68661306292062e-07, + "loss": 0.4703, + "step": 10615 + }, + { + "epoch": 0.91, + "learning_rate": 4.678261516877014e-07, + "loss": 0.4597, + "step": 10616 + }, + { + "epoch": 0.91, + "learning_rate": 4.669917240467148e-07, + "loss": 0.4583, + "step": 10617 + }, + { + "epoch": 0.91, + "learning_rate": 4.6615802343273787e-07, + "loss": 0.4646, + "step": 10618 + }, + { + "epoch": 0.91, + "learning_rate": 4.6532504990935423e-07, + "loss": 0.4227, + "step": 10619 + }, + { + "epoch": 0.91, + "learning_rate": 4.644928035400864e-07, + "loss": 0.4671, + "step": 10620 + }, + { + "epoch": 0.91, + "learning_rate": 4.6366128438840586e-07, + "loss": 0.4649, + "step": 10621 + }, + { + "epoch": 0.91, + "learning_rate": 4.628304925177318e-07, + "loss": 0.4622, + "step": 10622 + }, + { + "epoch": 0.91, + "learning_rate": 4.620004279914192e-07, + "loss": 0.423, + "step": 10623 + }, + { + "epoch": 0.91, + "learning_rate": 4.61171090872774e-07, + "loss": 0.4753, + "step": 10624 + }, + { + "epoch": 0.91, + "learning_rate": 4.6034248122504454e-07, + "loss": 0.4429, + "step": 10625 + }, + { + "epoch": 0.91, + "learning_rate": 4.595145991114247e-07, + "loss": 0.44, + "step": 10626 + }, + { + "epoch": 0.91, + "learning_rate": 4.5868744459505174e-07, + "loss": 0.4565, + "step": 10627 + }, + { + "epoch": 0.91, + "learning_rate": 4.578610177390086e-07, + "loss": 0.4567, + "step": 10628 + }, + { + "epoch": 0.91, + "learning_rate": 4.5703531860632146e-07, + "loss": 0.4397, + "step": 10629 + }, + { + "epoch": 0.91, + "learning_rate": 4.5621034725995994e-07, + "loss": 0.4619, + "step": 10630 + }, + { + "epoch": 0.91, + "learning_rate": 4.5538610376284375e-07, + "loss": 0.4436, + "step": 10631 + }, + { + "epoch": 0.91, + "learning_rate": 4.5456258817782925e-07, + "loss": 0.4591, + "step": 10632 + }, + { + "epoch": 0.91, + "learning_rate": 4.5373980056772405e-07, + "loss": 0.4296, + "step": 10633 + }, + { + "epoch": 0.91, + "learning_rate": 4.5291774099527453e-07, + "loss": 0.4542, + "step": 10634 + }, + { + "epoch": 0.91, + "learning_rate": 4.5209640952317723e-07, + "loss": 0.4529, + "step": 10635 + }, + { + "epoch": 0.91, + "learning_rate": 4.5127580621406877e-07, + "loss": 0.442, + "step": 10636 + }, + { + "epoch": 0.91, + "learning_rate": 4.504559311305323e-07, + "loss": 0.4564, + "step": 10637 + }, + { + "epoch": 0.91, + "learning_rate": 4.4963678433509463e-07, + "loss": 0.4336, + "step": 10638 + }, + { + "epoch": 0.91, + "learning_rate": 4.4881836589022566e-07, + "loss": 0.4216, + "step": 10639 + }, + { + "epoch": 0.91, + "learning_rate": 4.480006758583455e-07, + "loss": 0.451, + "step": 10640 + }, + { + "epoch": 0.91, + "learning_rate": 4.4718371430181095e-07, + "loss": 0.4667, + "step": 10641 + }, + { + "epoch": 0.91, + "learning_rate": 4.463674812829277e-07, + "loss": 0.4268, + "step": 10642 + }, + { + "epoch": 0.91, + "learning_rate": 4.455519768639471e-07, + "loss": 0.4817, + "step": 10643 + }, + { + "epoch": 0.91, + "learning_rate": 4.447372011070594e-07, + "loss": 0.4537, + "step": 10644 + }, + { + "epoch": 0.91, + "learning_rate": 4.43923154074406e-07, + "loss": 0.446, + "step": 10645 + }, + { + "epoch": 0.91, + "learning_rate": 4.4310983582806945e-07, + "loss": 0.4564, + "step": 10646 + }, + { + "epoch": 0.91, + "learning_rate": 4.4229724643007346e-07, + "loss": 0.4677, + "step": 10647 + }, + { + "epoch": 0.91, + "learning_rate": 4.4148538594239176e-07, + "loss": 0.4446, + "step": 10648 + }, + { + "epoch": 0.91, + "learning_rate": 4.4067425442694157e-07, + "loss": 0.4459, + "step": 10649 + }, + { + "epoch": 0.91, + "learning_rate": 4.398638519455811e-07, + "loss": 0.4697, + "step": 10650 + }, + { + "epoch": 0.91, + "learning_rate": 4.3905417856011543e-07, + "loss": 0.4594, + "step": 10651 + }, + { + "epoch": 0.91, + "learning_rate": 4.382452343322952e-07, + "loss": 0.4446, + "step": 10652 + }, + { + "epoch": 0.91, + "learning_rate": 4.3743701932380975e-07, + "loss": 0.4451, + "step": 10653 + }, + { + "epoch": 0.91, + "learning_rate": 4.366295335963011e-07, + "loss": 0.4482, + "step": 10654 + }, + { + "epoch": 0.91, + "learning_rate": 4.3582277721135104e-07, + "loss": 0.434, + "step": 10655 + }, + { + "epoch": 0.91, + "learning_rate": 4.350167502304847e-07, + "loss": 0.4512, + "step": 10656 + }, + { + "epoch": 0.91, + "learning_rate": 4.3421145271517193e-07, + "loss": 0.4759, + "step": 10657 + }, + { + "epoch": 0.91, + "learning_rate": 4.3340688472683245e-07, + "loss": 0.4336, + "step": 10658 + }, + { + "epoch": 0.91, + "learning_rate": 4.326030463268216e-07, + "loss": 0.4342, + "step": 10659 + }, + { + "epoch": 0.91, + "learning_rate": 4.317999375764459e-07, + "loss": 0.4388, + "step": 10660 + }, + { + "epoch": 0.91, + "learning_rate": 4.30997558536953e-07, + "loss": 0.444, + "step": 10661 + }, + { + "epoch": 0.91, + "learning_rate": 4.3019590926953405e-07, + "loss": 0.4589, + "step": 10662 + }, + { + "epoch": 0.91, + "learning_rate": 4.293949898353289e-07, + "loss": 0.4506, + "step": 10663 + }, + { + "epoch": 0.91, + "learning_rate": 4.285948002954199e-07, + "loss": 0.4598, + "step": 10664 + }, + { + "epoch": 0.91, + "learning_rate": 4.277953407108282e-07, + "loss": 0.4541, + "step": 10665 + }, + { + "epoch": 0.91, + "learning_rate": 4.269966111425272e-07, + "loss": 0.4549, + "step": 10666 + }, + { + "epoch": 0.91, + "learning_rate": 4.261986116514305e-07, + "loss": 0.4685, + "step": 10667 + }, + { + "epoch": 0.91, + "learning_rate": 4.2540134229839714e-07, + "loss": 0.4522, + "step": 10668 + }, + { + "epoch": 0.91, + "learning_rate": 4.246048031442307e-07, + "loss": 0.4596, + "step": 10669 + }, + { + "epoch": 0.91, + "learning_rate": 4.2380899424967814e-07, + "loss": 0.4591, + "step": 10670 + }, + { + "epoch": 0.91, + "learning_rate": 4.2301391567542983e-07, + "loss": 0.4545, + "step": 10671 + }, + { + "epoch": 0.91, + "learning_rate": 4.222195674821239e-07, + "loss": 0.4729, + "step": 10672 + }, + { + "epoch": 0.91, + "learning_rate": 4.2142594973034077e-07, + "loss": 0.4594, + "step": 10673 + }, + { + "epoch": 0.91, + "learning_rate": 4.2063306248060323e-07, + "loss": 0.4515, + "step": 10674 + }, + { + "epoch": 0.91, + "learning_rate": 4.1984090579338054e-07, + "loss": 0.4648, + "step": 10675 + }, + { + "epoch": 0.91, + "learning_rate": 4.1904947972908673e-07, + "loss": 0.4531, + "step": 10676 + }, + { + "epoch": 0.91, + "learning_rate": 4.18258784348079e-07, + "loss": 0.4437, + "step": 10677 + }, + { + "epoch": 0.91, + "learning_rate": 4.17468819710658e-07, + "loss": 0.449, + "step": 10678 + }, + { + "epoch": 0.91, + "learning_rate": 4.1667958587707226e-07, + "loss": 0.451, + "step": 10679 + }, + { + "epoch": 0.91, + "learning_rate": 4.1589108290750915e-07, + "loss": 0.4599, + "step": 10680 + }, + { + "epoch": 0.91, + "learning_rate": 4.15103310862105e-07, + "loss": 0.4504, + "step": 10681 + }, + { + "epoch": 0.91, + "learning_rate": 4.143162698009384e-07, + "loss": 0.4485, + "step": 10682 + }, + { + "epoch": 0.91, + "learning_rate": 4.135299597840325e-07, + "loss": 0.4672, + "step": 10683 + }, + { + "epoch": 0.91, + "learning_rate": 4.1274438087135273e-07, + "loss": 0.4541, + "step": 10684 + }, + { + "epoch": 0.91, + "learning_rate": 4.119595331228132e-07, + "loss": 0.444, + "step": 10685 + }, + { + "epoch": 0.91, + "learning_rate": 4.111754165982673e-07, + "loss": 0.4833, + "step": 10686 + }, + { + "epoch": 0.91, + "learning_rate": 4.1039203135751717e-07, + "loss": 0.445, + "step": 10687 + }, + { + "epoch": 0.91, + "learning_rate": 4.0960937746030607e-07, + "loss": 0.4548, + "step": 10688 + }, + { + "epoch": 0.91, + "learning_rate": 4.0882745496632406e-07, + "loss": 0.4462, + "step": 10689 + }, + { + "epoch": 0.91, + "learning_rate": 4.0804626393519897e-07, + "loss": 0.4486, + "step": 10690 + }, + { + "epoch": 0.91, + "learning_rate": 4.0726580442651433e-07, + "loss": 0.4505, + "step": 10691 + }, + { + "epoch": 0.91, + "learning_rate": 4.064860764997858e-07, + "loss": 0.4446, + "step": 10692 + }, + { + "epoch": 0.91, + "learning_rate": 4.0570708021448134e-07, + "loss": 0.4678, + "step": 10693 + }, + { + "epoch": 0.91, + "learning_rate": 4.049288156300102e-07, + "loss": 0.4449, + "step": 10694 + }, + { + "epoch": 0.91, + "learning_rate": 4.041512828057248e-07, + "loss": 0.4731, + "step": 10695 + }, + { + "epoch": 0.91, + "learning_rate": 4.0337448180092444e-07, + "loss": 0.4717, + "step": 10696 + }, + { + "epoch": 0.91, + "learning_rate": 4.0259841267485167e-07, + "loss": 0.4508, + "step": 10697 + }, + { + "epoch": 0.91, + "learning_rate": 4.0182307548669255e-07, + "loss": 0.4442, + "step": 10698 + }, + { + "epoch": 0.91, + "learning_rate": 4.010484702955741e-07, + "loss": 0.4498, + "step": 10699 + }, + { + "epoch": 0.91, + "learning_rate": 4.002745971605759e-07, + "loss": 0.4309, + "step": 10700 + }, + { + "epoch": 0.91, + "learning_rate": 3.99501456140714e-07, + "loss": 0.4489, + "step": 10701 + }, + { + "epoch": 0.91, + "learning_rate": 3.9872904729495123e-07, + "loss": 0.4606, + "step": 10702 + }, + { + "epoch": 0.91, + "learning_rate": 3.97957370682196e-07, + "loss": 0.4386, + "step": 10703 + }, + { + "epoch": 0.91, + "learning_rate": 3.97186426361299e-07, + "loss": 0.4226, + "step": 10704 + }, + { + "epoch": 0.91, + "learning_rate": 3.964162143910555e-07, + "loss": 0.4383, + "step": 10705 + }, + { + "epoch": 0.91, + "learning_rate": 3.956467348302062e-07, + "loss": 0.4636, + "step": 10706 + }, + { + "epoch": 0.91, + "learning_rate": 3.9487798773743425e-07, + "loss": 0.4384, + "step": 10707 + }, + { + "epoch": 0.91, + "learning_rate": 3.941099731713638e-07, + "loss": 0.4584, + "step": 10708 + }, + { + "epoch": 0.91, + "learning_rate": 3.9334269119057354e-07, + "loss": 0.4685, + "step": 10709 + }, + { + "epoch": 0.91, + "learning_rate": 3.925761418535756e-07, + "loss": 0.4457, + "step": 10710 + }, + { + "epoch": 0.91, + "learning_rate": 3.918103252188299e-07, + "loss": 0.4445, + "step": 10711 + }, + { + "epoch": 0.91, + "learning_rate": 3.9104524134474187e-07, + "loss": 0.4621, + "step": 10712 + }, + { + "epoch": 0.91, + "learning_rate": 3.902808902896604e-07, + "loss": 0.4157, + "step": 10713 + }, + { + "epoch": 0.91, + "learning_rate": 3.895172721118778e-07, + "loss": 0.4593, + "step": 10714 + }, + { + "epoch": 0.91, + "learning_rate": 3.8875438686962973e-07, + "loss": 0.4646, + "step": 10715 + }, + { + "epoch": 0.91, + "learning_rate": 3.879922346210996e-07, + "loss": 0.4533, + "step": 10716 + }, + { + "epoch": 0.91, + "learning_rate": 3.8723081542440866e-07, + "loss": 0.4384, + "step": 10717 + }, + { + "epoch": 0.91, + "learning_rate": 3.864701293376294e-07, + "loss": 0.4425, + "step": 10718 + }, + { + "epoch": 0.91, + "learning_rate": 3.8571017641877206e-07, + "loss": 0.438, + "step": 10719 + }, + { + "epoch": 0.91, + "learning_rate": 3.8495095672579584e-07, + "loss": 0.4424, + "step": 10720 + }, + { + "epoch": 0.91, + "learning_rate": 3.8419247031660113e-07, + "loss": 0.4705, + "step": 10721 + }, + { + "epoch": 0.91, + "learning_rate": 3.834347172490327e-07, + "loss": 0.4399, + "step": 10722 + }, + { + "epoch": 0.91, + "learning_rate": 3.826776975808821e-07, + "loss": 0.4824, + "step": 10723 + }, + { + "epoch": 0.91, + "learning_rate": 3.819214113698799e-07, + "loss": 0.4573, + "step": 10724 + }, + { + "epoch": 0.91, + "learning_rate": 3.811658586737077e-07, + "loss": 0.4359, + "step": 10725 + }, + { + "epoch": 0.91, + "learning_rate": 3.8041103954998046e-07, + "loss": 0.4514, + "step": 10726 + }, + { + "epoch": 0.91, + "learning_rate": 3.7965695405627e-07, + "loss": 0.4585, + "step": 10727 + }, + { + "epoch": 0.91, + "learning_rate": 3.789036022500858e-07, + "loss": 0.479, + "step": 10728 + }, + { + "epoch": 0.91, + "learning_rate": 3.781509841888775e-07, + "loss": 0.4538, + "step": 10729 + }, + { + "epoch": 0.91, + "learning_rate": 3.773990999300459e-07, + "loss": 0.4418, + "step": 10730 + }, + { + "epoch": 0.91, + "learning_rate": 3.7664794953093163e-07, + "loss": 0.4539, + "step": 10731 + }, + { + "epoch": 0.92, + "learning_rate": 3.7589753304882125e-07, + "loss": 0.4536, + "step": 10732 + }, + { + "epoch": 0.92, + "learning_rate": 3.7514785054094447e-07, + "loss": 0.4367, + "step": 10733 + }, + { + "epoch": 0.92, + "learning_rate": 3.7439890206447674e-07, + "loss": 0.4456, + "step": 10734 + }, + { + "epoch": 0.92, + "learning_rate": 3.736506876765311e-07, + "loss": 0.4632, + "step": 10735 + }, + { + "epoch": 0.92, + "learning_rate": 3.729032074341743e-07, + "loss": 0.4355, + "step": 10736 + }, + { + "epoch": 0.92, + "learning_rate": 3.7215646139441284e-07, + "loss": 0.4501, + "step": 10737 + }, + { + "epoch": 0.92, + "learning_rate": 3.714104496141924e-07, + "loss": 0.4501, + "step": 10738 + }, + { + "epoch": 0.92, + "learning_rate": 3.706651721504095e-07, + "loss": 0.4545, + "step": 10739 + }, + { + "epoch": 0.92, + "learning_rate": 3.6992062905990225e-07, + "loss": 0.4302, + "step": 10740 + }, + { + "epoch": 0.92, + "learning_rate": 3.6917682039945167e-07, + "loss": 0.4448, + "step": 10741 + }, + { + "epoch": 0.92, + "learning_rate": 3.6843374622578474e-07, + "loss": 0.4381, + "step": 10742 + }, + { + "epoch": 0.92, + "learning_rate": 3.676914065955717e-07, + "loss": 0.4291, + "step": 10743 + }, + { + "epoch": 0.92, + "learning_rate": 3.6694980156542494e-07, + "loss": 0.4577, + "step": 10744 + }, + { + "epoch": 0.92, + "learning_rate": 3.662089311919015e-07, + "loss": 0.4566, + "step": 10745 + }, + { + "epoch": 0.92, + "learning_rate": 3.6546879553150727e-07, + "loss": 0.4365, + "step": 10746 + }, + { + "epoch": 0.92, + "learning_rate": 3.647293946406849e-07, + "loss": 0.4389, + "step": 10747 + }, + { + "epoch": 0.92, + "learning_rate": 3.6399072857582487e-07, + "loss": 0.4798, + "step": 10748 + }, + { + "epoch": 0.92, + "learning_rate": 3.6325279739325983e-07, + "loss": 0.4492, + "step": 10749 + }, + { + "epoch": 0.92, + "learning_rate": 3.625156011492703e-07, + "loss": 0.456, + "step": 10750 + }, + { + "epoch": 0.92, + "learning_rate": 3.6177913990007473e-07, + "loss": 0.4598, + "step": 10751 + }, + { + "epoch": 0.92, + "learning_rate": 3.610434137018426e-07, + "loss": 0.437, + "step": 10752 + }, + { + "epoch": 0.92, + "learning_rate": 3.603084226106801e-07, + "loss": 0.4735, + "step": 10753 + }, + { + "epoch": 0.92, + "learning_rate": 3.595741666826402e-07, + "loss": 0.46, + "step": 10754 + }, + { + "epoch": 0.92, + "learning_rate": 3.588406459737237e-07, + "loss": 0.4639, + "step": 10755 + }, + { + "epoch": 0.92, + "learning_rate": 3.5810786053987025e-07, + "loss": 0.4394, + "step": 10756 + }, + { + "epoch": 0.92, + "learning_rate": 3.57375810436964e-07, + "loss": 0.4323, + "step": 10757 + }, + { + "epoch": 0.92, + "learning_rate": 3.5664449572083594e-07, + "loss": 0.4605, + "step": 10758 + }, + { + "epoch": 0.92, + "learning_rate": 3.5591391644725805e-07, + "loss": 0.4382, + "step": 10759 + }, + { + "epoch": 0.92, + "learning_rate": 3.55184072671948e-07, + "loss": 0.4762, + "step": 10760 + }, + { + "epoch": 0.92, + "learning_rate": 3.544549644505668e-07, + "loss": 0.4541, + "step": 10761 + }, + { + "epoch": 0.92, + "learning_rate": 3.5372659183871895e-07, + "loss": 0.4383, + "step": 10762 + }, + { + "epoch": 0.92, + "learning_rate": 3.52998954891951e-07, + "loss": 0.4489, + "step": 10763 + }, + { + "epoch": 0.92, + "learning_rate": 3.522720536657609e-07, + "loss": 0.4537, + "step": 10764 + }, + { + "epoch": 0.92, + "learning_rate": 3.515458882155798e-07, + "loss": 0.4424, + "step": 10765 + }, + { + "epoch": 0.92, + "learning_rate": 3.508204585967911e-07, + "loss": 0.4475, + "step": 10766 + }, + { + "epoch": 0.92, + "learning_rate": 3.500957648647196e-07, + "loss": 0.4645, + "step": 10767 + }, + { + "epoch": 0.92, + "learning_rate": 3.493718070746299e-07, + "loss": 0.4574, + "step": 10768 + }, + { + "epoch": 0.92, + "learning_rate": 3.486485852817378e-07, + "loss": 0.4375, + "step": 10769 + }, + { + "epoch": 0.92, + "learning_rate": 3.4792609954119815e-07, + "loss": 0.4703, + "step": 10770 + }, + { + "epoch": 0.92, + "learning_rate": 3.4720434990810904e-07, + "loss": 0.4444, + "step": 10771 + }, + { + "epoch": 0.92, + "learning_rate": 3.4648333643751533e-07, + "loss": 0.4494, + "step": 10772 + }, + { + "epoch": 0.92, + "learning_rate": 3.4576305918440635e-07, + "loss": 0.4395, + "step": 10773 + }, + { + "epoch": 0.92, + "learning_rate": 3.450435182037104e-07, + "loss": 0.4739, + "step": 10774 + }, + { + "epoch": 0.92, + "learning_rate": 3.443247135503036e-07, + "loss": 0.4394, + "step": 10775 + }, + { + "epoch": 0.92, + "learning_rate": 3.4360664527900767e-07, + "loss": 0.4625, + "step": 10776 + }, + { + "epoch": 0.92, + "learning_rate": 3.4288931344457987e-07, + "loss": 0.4538, + "step": 10777 + }, + { + "epoch": 0.92, + "learning_rate": 3.42172718101732e-07, + "loss": 0.4354, + "step": 10778 + }, + { + "epoch": 0.92, + "learning_rate": 3.4145685930511374e-07, + "loss": 0.4474, + "step": 10779 + }, + { + "epoch": 0.92, + "learning_rate": 3.4074173710931804e-07, + "loss": 0.448, + "step": 10780 + }, + { + "epoch": 0.92, + "learning_rate": 3.4002735156888234e-07, + "loss": 0.4528, + "step": 10781 + }, + { + "epoch": 0.92, + "learning_rate": 3.393137027382909e-07, + "loss": 0.4629, + "step": 10782 + }, + { + "epoch": 0.92, + "learning_rate": 3.3860079067196906e-07, + "loss": 0.4499, + "step": 10783 + }, + { + "epoch": 0.92, + "learning_rate": 3.3788861542428555e-07, + "loss": 0.4509, + "step": 10784 + }, + { + "epoch": 0.92, + "learning_rate": 3.3717717704955575e-07, + "loss": 0.4515, + "step": 10785 + }, + { + "epoch": 0.92, + "learning_rate": 3.3646647560203303e-07, + "loss": 0.4613, + "step": 10786 + }, + { + "epoch": 0.92, + "learning_rate": 3.3575651113592177e-07, + "loss": 0.4781, + "step": 10787 + }, + { + "epoch": 0.92, + "learning_rate": 3.3504728370536755e-07, + "loss": 0.4362, + "step": 10788 + }, + { + "epoch": 0.92, + "learning_rate": 3.3433879336445597e-07, + "loss": 0.4405, + "step": 10789 + }, + { + "epoch": 0.92, + "learning_rate": 3.3363104016721936e-07, + "loss": 0.4474, + "step": 10790 + }, + { + "epoch": 0.92, + "learning_rate": 3.329240241676379e-07, + "loss": 0.424, + "step": 10791 + }, + { + "epoch": 0.92, + "learning_rate": 3.322177454196285e-07, + "loss": 0.4486, + "step": 10792 + }, + { + "epoch": 0.92, + "learning_rate": 3.3151220397705577e-07, + "loss": 0.4524, + "step": 10793 + }, + { + "epoch": 0.92, + "learning_rate": 3.308073998937278e-07, + "loss": 0.45, + "step": 10794 + }, + { + "epoch": 0.92, + "learning_rate": 3.301033332233938e-07, + "loss": 0.4637, + "step": 10795 + }, + { + "epoch": 0.92, + "learning_rate": 3.2940000401975094e-07, + "loss": 0.4619, + "step": 10796 + }, + { + "epoch": 0.92, + "learning_rate": 3.2869741233643726e-07, + "loss": 0.47, + "step": 10797 + }, + { + "epoch": 0.92, + "learning_rate": 3.2799555822703554e-07, + "loss": 0.446, + "step": 10798 + }, + { + "epoch": 0.92, + "learning_rate": 3.2729444174507186e-07, + "loss": 0.4464, + "step": 10799 + }, + { + "epoch": 0.92, + "learning_rate": 3.2659406294401566e-07, + "loss": 0.4605, + "step": 10800 + }, + { + "epoch": 0.92, + "learning_rate": 3.2589442187728193e-07, + "loss": 0.4487, + "step": 10801 + }, + { + "epoch": 0.92, + "learning_rate": 3.2519551859822805e-07, + "loss": 0.4311, + "step": 10802 + }, + { + "epoch": 0.92, + "learning_rate": 3.2449735316015583e-07, + "loss": 0.4653, + "step": 10803 + }, + { + "epoch": 0.92, + "learning_rate": 3.237999256163071e-07, + "loss": 0.4293, + "step": 10804 + }, + { + "epoch": 0.92, + "learning_rate": 3.231032360198749e-07, + "loss": 0.4505, + "step": 10805 + }, + { + "epoch": 0.92, + "learning_rate": 3.2240728442399005e-07, + "loss": 0.4623, + "step": 10806 + }, + { + "epoch": 0.92, + "learning_rate": 3.2171207088172676e-07, + "loss": 0.4564, + "step": 10807 + }, + { + "epoch": 0.92, + "learning_rate": 3.210175954461081e-07, + "loss": 0.4688, + "step": 10808 + }, + { + "epoch": 0.92, + "learning_rate": 3.2032385817009514e-07, + "loss": 0.4513, + "step": 10809 + }, + { + "epoch": 0.92, + "learning_rate": 3.196308591065966e-07, + "loss": 0.47, + "step": 10810 + }, + { + "epoch": 0.92, + "learning_rate": 3.189385983084625e-07, + "loss": 0.4418, + "step": 10811 + }, + { + "epoch": 0.92, + "learning_rate": 3.1824707582848945e-07, + "loss": 0.4576, + "step": 10812 + }, + { + "epoch": 0.92, + "learning_rate": 3.1755629171941196e-07, + "loss": 0.4422, + "step": 10813 + }, + { + "epoch": 0.92, + "learning_rate": 3.168662460339167e-07, + "loss": 0.4553, + "step": 10814 + }, + { + "epoch": 0.92, + "learning_rate": 3.161769388246283e-07, + "loss": 0.4629, + "step": 10815 + }, + { + "epoch": 0.92, + "learning_rate": 3.154883701441136e-07, + "loss": 0.4626, + "step": 10816 + }, + { + "epoch": 0.92, + "learning_rate": 3.1480054004488723e-07, + "loss": 0.453, + "step": 10817 + }, + { + "epoch": 0.92, + "learning_rate": 3.141134485794073e-07, + "loss": 0.4488, + "step": 10818 + }, + { + "epoch": 0.92, + "learning_rate": 3.134270958000718e-07, + "loss": 0.4527, + "step": 10819 + }, + { + "epoch": 0.92, + "learning_rate": 3.127414817592278e-07, + "loss": 0.4499, + "step": 10820 + }, + { + "epoch": 0.92, + "learning_rate": 3.1205660650916127e-07, + "loss": 0.4657, + "step": 10821 + }, + { + "epoch": 0.92, + "learning_rate": 3.113724701021026e-07, + "loss": 0.453, + "step": 10822 + }, + { + "epoch": 0.92, + "learning_rate": 3.1068907259022786e-07, + "loss": 0.4477, + "step": 10823 + }, + { + "epoch": 0.92, + "learning_rate": 3.1000641402565866e-07, + "loss": 0.44, + "step": 10824 + }, + { + "epoch": 0.92, + "learning_rate": 3.093244944604523e-07, + "loss": 0.457, + "step": 10825 + }, + { + "epoch": 0.92, + "learning_rate": 3.086433139466183e-07, + "loss": 0.4296, + "step": 10826 + }, + { + "epoch": 0.92, + "learning_rate": 3.079628725361061e-07, + "loss": 0.4454, + "step": 10827 + }, + { + "epoch": 0.92, + "learning_rate": 3.0728317028080656e-07, + "loss": 0.4539, + "step": 10828 + }, + { + "epoch": 0.92, + "learning_rate": 3.066042072325592e-07, + "loss": 0.4594, + "step": 10829 + }, + { + "epoch": 0.92, + "learning_rate": 3.0592598344314495e-07, + "loss": 0.4462, + "step": 10830 + }, + { + "epoch": 0.92, + "learning_rate": 3.0524849896428567e-07, + "loss": 0.455, + "step": 10831 + }, + { + "epoch": 0.92, + "learning_rate": 3.0457175384764894e-07, + "loss": 0.4527, + "step": 10832 + }, + { + "epoch": 0.92, + "learning_rate": 3.0389574814485015e-07, + "loss": 0.4485, + "step": 10833 + }, + { + "epoch": 0.92, + "learning_rate": 3.0322048190744025e-07, + "loss": 0.4629, + "step": 10834 + }, + { + "epoch": 0.92, + "learning_rate": 3.025459551869192e-07, + "loss": 0.4724, + "step": 10835 + }, + { + "epoch": 0.92, + "learning_rate": 3.0187216803472805e-07, + "loss": 0.4465, + "step": 10836 + }, + { + "epoch": 0.92, + "learning_rate": 3.0119912050225576e-07, + "loss": 0.4374, + "step": 10837 + }, + { + "epoch": 0.92, + "learning_rate": 3.0052681264082895e-07, + "loss": 0.4513, + "step": 10838 + }, + { + "epoch": 0.92, + "learning_rate": 2.998552445017222e-07, + "loss": 0.4478, + "step": 10839 + }, + { + "epoch": 0.92, + "learning_rate": 2.991844161361512e-07, + "loss": 0.4462, + "step": 10840 + }, + { + "epoch": 0.92, + "learning_rate": 2.9851432759527397e-07, + "loss": 0.4585, + "step": 10841 + }, + { + "epoch": 0.92, + "learning_rate": 2.978449789301996e-07, + "loss": 0.4467, + "step": 10842 + }, + { + "epoch": 0.92, + "learning_rate": 2.9717637019197163e-07, + "loss": 0.4527, + "step": 10843 + }, + { + "epoch": 0.92, + "learning_rate": 2.965085014315816e-07, + "loss": 0.463, + "step": 10844 + }, + { + "epoch": 0.92, + "learning_rate": 2.958413726999632e-07, + "loss": 0.4577, + "step": 10845 + }, + { + "epoch": 0.92, + "learning_rate": 2.9517498404799674e-07, + "loss": 0.4464, + "step": 10846 + }, + { + "epoch": 0.92, + "learning_rate": 2.9450933552650163e-07, + "loss": 0.4518, + "step": 10847 + }, + { + "epoch": 0.92, + "learning_rate": 2.9384442718624397e-07, + "loss": 0.4506, + "step": 10848 + }, + { + "epoch": 0.93, + "learning_rate": 2.9318025907793314e-07, + "loss": 0.4628, + "step": 10849 + }, + { + "epoch": 0.93, + "learning_rate": 2.9251683125221864e-07, + "loss": 0.4484, + "step": 10850 + }, + { + "epoch": 0.93, + "learning_rate": 2.918541437597e-07, + "loss": 0.4432, + "step": 10851 + }, + { + "epoch": 0.93, + "learning_rate": 2.9119219665091345e-07, + "loss": 0.4581, + "step": 10852 + }, + { + "epoch": 0.93, + "learning_rate": 2.905309899763431e-07, + "loss": 0.4439, + "step": 10853 + }, + { + "epoch": 0.93, + "learning_rate": 2.898705237864152e-07, + "loss": 0.4493, + "step": 10854 + }, + { + "epoch": 0.93, + "learning_rate": 2.8921079813150066e-07, + "loss": 0.4408, + "step": 10855 + }, + { + "epoch": 0.93, + "learning_rate": 2.8855181306191137e-07, + "loss": 0.4507, + "step": 10856 + }, + { + "epoch": 0.93, + "learning_rate": 2.87893568627905e-07, + "loss": 0.4679, + "step": 10857 + }, + { + "epoch": 0.93, + "learning_rate": 2.8723606487968235e-07, + "loss": 0.4614, + "step": 10858 + }, + { + "epoch": 0.93, + "learning_rate": 2.865793018673857e-07, + "loss": 0.4448, + "step": 10859 + }, + { + "epoch": 0.93, + "learning_rate": 2.859232796411049e-07, + "loss": 0.4648, + "step": 10860 + }, + { + "epoch": 0.93, + "learning_rate": 2.8526799825086993e-07, + "loss": 0.4605, + "step": 10861 + }, + { + "epoch": 0.93, + "learning_rate": 2.8461345774665414e-07, + "loss": 0.4526, + "step": 10862 + }, + { + "epoch": 0.93, + "learning_rate": 2.8395965817837766e-07, + "loss": 0.453, + "step": 10863 + }, + { + "epoch": 0.93, + "learning_rate": 2.8330659959589944e-07, + "loss": 0.461, + "step": 10864 + }, + { + "epoch": 0.93, + "learning_rate": 2.8265428204902746e-07, + "loss": 0.4615, + "step": 10865 + }, + { + "epoch": 0.93, + "learning_rate": 2.8200270558750743e-07, + "loss": 0.4408, + "step": 10866 + }, + { + "epoch": 0.93, + "learning_rate": 2.8135187026103403e-07, + "loss": 0.4709, + "step": 10867 + }, + { + "epoch": 0.93, + "learning_rate": 2.807017761192399e-07, + "loss": 0.4721, + "step": 10868 + }, + { + "epoch": 0.93, + "learning_rate": 2.8005242321170633e-07, + "loss": 0.4391, + "step": 10869 + }, + { + "epoch": 0.93, + "learning_rate": 2.794038115879538e-07, + "loss": 0.4762, + "step": 10870 + }, + { + "epoch": 0.93, + "learning_rate": 2.787559412974483e-07, + "loss": 0.4436, + "step": 10871 + }, + { + "epoch": 0.93, + "learning_rate": 2.781088123896003e-07, + "loss": 0.4365, + "step": 10872 + }, + { + "epoch": 0.93, + "learning_rate": 2.774624249137614e-07, + "loss": 0.4727, + "step": 10873 + }, + { + "epoch": 0.93, + "learning_rate": 2.7681677891922887e-07, + "loss": 0.4587, + "step": 10874 + }, + { + "epoch": 0.93, + "learning_rate": 2.761718744552422e-07, + "loss": 0.4572, + "step": 10875 + }, + { + "epoch": 0.93, + "learning_rate": 2.755277115709842e-07, + "loss": 0.4392, + "step": 10876 + }, + { + "epoch": 0.93, + "learning_rate": 2.7488429031558016e-07, + "loss": 0.4541, + "step": 10877 + }, + { + "epoch": 0.93, + "learning_rate": 2.7424161073810183e-07, + "loss": 0.4473, + "step": 10878 + }, + { + "epoch": 0.93, + "learning_rate": 2.735996728875623e-07, + "loss": 0.4477, + "step": 10879 + }, + { + "epoch": 0.93, + "learning_rate": 2.7295847681291897e-07, + "loss": 0.4554, + "step": 10880 + }, + { + "epoch": 0.93, + "learning_rate": 2.723180225630695e-07, + "loss": 0.4646, + "step": 10881 + }, + { + "epoch": 0.93, + "learning_rate": 2.716783101868614e-07, + "loss": 0.4902, + "step": 10882 + }, + { + "epoch": 0.93, + "learning_rate": 2.7103933973307796e-07, + "loss": 0.4533, + "step": 10883 + }, + { + "epoch": 0.93, + "learning_rate": 2.7040111125045345e-07, + "loss": 0.4447, + "step": 10884 + }, + { + "epoch": 0.93, + "learning_rate": 2.6976362478766003e-07, + "loss": 0.4466, + "step": 10885 + }, + { + "epoch": 0.93, + "learning_rate": 2.691268803933145e-07, + "loss": 0.4382, + "step": 10886 + }, + { + "epoch": 0.93, + "learning_rate": 2.6849087811597787e-07, + "loss": 0.4655, + "step": 10887 + }, + { + "epoch": 0.93, + "learning_rate": 2.678556180041547e-07, + "loss": 0.4502, + "step": 10888 + }, + { + "epoch": 0.93, + "learning_rate": 2.67221100106293e-07, + "loss": 0.4517, + "step": 10889 + }, + { + "epoch": 0.93, + "learning_rate": 2.6658732447078286e-07, + "loss": 0.44, + "step": 10890 + }, + { + "epoch": 0.93, + "learning_rate": 2.6595429114595894e-07, + "loss": 0.4694, + "step": 10891 + }, + { + "epoch": 0.93, + "learning_rate": 2.653220001801005e-07, + "loss": 0.4388, + "step": 10892 + }, + { + "epoch": 0.93, + "learning_rate": 2.646904516214266e-07, + "loss": 0.4509, + "step": 10893 + }, + { + "epoch": 0.93, + "learning_rate": 2.6405964551810325e-07, + "loss": 0.4457, + "step": 10894 + }, + { + "epoch": 0.93, + "learning_rate": 2.6342958191823643e-07, + "loss": 0.4393, + "step": 10895 + }, + { + "epoch": 0.93, + "learning_rate": 2.6280026086987985e-07, + "loss": 0.4579, + "step": 10896 + }, + { + "epoch": 0.93, + "learning_rate": 2.621716824210263e-07, + "loss": 0.4432, + "step": 10897 + }, + { + "epoch": 0.93, + "learning_rate": 2.6154384661961405e-07, + "loss": 0.4409, + "step": 10898 + }, + { + "epoch": 0.93, + "learning_rate": 2.6091675351352485e-07, + "loss": 0.4484, + "step": 10899 + }, + { + "epoch": 0.93, + "learning_rate": 2.6029040315058487e-07, + "loss": 0.4707, + "step": 10900 + }, + { + "epoch": 0.93, + "learning_rate": 2.5966479557855914e-07, + "loss": 0.4309, + "step": 10901 + }, + { + "epoch": 0.93, + "learning_rate": 2.5903993084516077e-07, + "loss": 0.4475, + "step": 10902 + }, + { + "epoch": 0.93, + "learning_rate": 2.5841580899804706e-07, + "loss": 0.4383, + "step": 10903 + }, + { + "epoch": 0.93, + "learning_rate": 2.5779243008481114e-07, + "loss": 0.4722, + "step": 10904 + }, + { + "epoch": 0.93, + "learning_rate": 2.5716979415299714e-07, + "loss": 0.4388, + "step": 10905 + }, + { + "epoch": 0.93, + "learning_rate": 2.565479012500915e-07, + "loss": 0.4364, + "step": 10906 + }, + { + "epoch": 0.93, + "learning_rate": 2.5592675142351865e-07, + "loss": 0.4683, + "step": 10907 + }, + { + "epoch": 0.93, + "learning_rate": 2.553063447206527e-07, + "loss": 0.4362, + "step": 10908 + }, + { + "epoch": 0.93, + "learning_rate": 2.5468668118880935e-07, + "loss": 0.4706, + "step": 10909 + }, + { + "epoch": 0.93, + "learning_rate": 2.540677608752429e-07, + "loss": 0.4553, + "step": 10910 + }, + { + "epoch": 0.93, + "learning_rate": 2.534495838271578e-07, + "loss": 0.4531, + "step": 10911 + }, + { + "epoch": 0.93, + "learning_rate": 2.528321500916986e-07, + "loss": 0.4502, + "step": 10912 + }, + { + "epoch": 0.93, + "learning_rate": 2.5221545971595207e-07, + "loss": 0.4777, + "step": 10913 + }, + { + "epoch": 0.93, + "learning_rate": 2.5159951274694947e-07, + "loss": 0.445, + "step": 10914 + }, + { + "epoch": 0.93, + "learning_rate": 2.509843092316688e-07, + "loss": 0.4549, + "step": 10915 + }, + { + "epoch": 0.93, + "learning_rate": 2.503698492170237e-07, + "loss": 0.4535, + "step": 10916 + }, + { + "epoch": 0.93, + "learning_rate": 2.497561327498788e-07, + "loss": 0.4606, + "step": 10917 + }, + { + "epoch": 0.93, + "learning_rate": 2.4914315987703664e-07, + "loss": 0.4436, + "step": 10918 + }, + { + "epoch": 0.93, + "learning_rate": 2.4853093064524434e-07, + "loss": 0.452, + "step": 10919 + }, + { + "epoch": 0.93, + "learning_rate": 2.479194451011957e-07, + "loss": 0.4697, + "step": 10920 + }, + { + "epoch": 0.93, + "learning_rate": 2.4730870329152557e-07, + "loss": 0.4624, + "step": 10921 + }, + { + "epoch": 0.93, + "learning_rate": 2.466987052628078e-07, + "loss": 0.4499, + "step": 10922 + }, + { + "epoch": 0.93, + "learning_rate": 2.4608945106156524e-07, + "loss": 0.4677, + "step": 10923 + }, + { + "epoch": 0.93, + "learning_rate": 2.45480940734264e-07, + "loss": 0.4209, + "step": 10924 + }, + { + "epoch": 0.93, + "learning_rate": 2.4487317432730917e-07, + "loss": 0.4617, + "step": 10925 + }, + { + "epoch": 0.93, + "learning_rate": 2.442661518870526e-07, + "loss": 0.4745, + "step": 10926 + }, + { + "epoch": 0.93, + "learning_rate": 2.4365987345978946e-07, + "loss": 0.4456, + "step": 10927 + }, + { + "epoch": 0.93, + "learning_rate": 2.430543390917539e-07, + "loss": 0.4683, + "step": 10928 + }, + { + "epoch": 0.93, + "learning_rate": 2.4244954882912895e-07, + "loss": 0.4511, + "step": 10929 + }, + { + "epoch": 0.93, + "learning_rate": 2.418455027180389e-07, + "loss": 0.4572, + "step": 10930 + }, + { + "epoch": 0.93, + "learning_rate": 2.4124220080455006e-07, + "loss": 0.4276, + "step": 10931 + }, + { + "epoch": 0.93, + "learning_rate": 2.4063964313467135e-07, + "loss": 0.4566, + "step": 10932 + }, + { + "epoch": 0.93, + "learning_rate": 2.400378297543582e-07, + "loss": 0.4477, + "step": 10933 + }, + { + "epoch": 0.93, + "learning_rate": 2.3943676070950606e-07, + "loss": 0.4399, + "step": 10934 + }, + { + "epoch": 0.93, + "learning_rate": 2.3883643604595607e-07, + "loss": 0.4562, + "step": 10935 + }, + { + "epoch": 0.93, + "learning_rate": 2.3823685580949273e-07, + "loss": 0.4639, + "step": 10936 + }, + { + "epoch": 0.93, + "learning_rate": 2.3763802004583835e-07, + "loss": 0.4601, + "step": 10937 + }, + { + "epoch": 0.93, + "learning_rate": 2.370399288006664e-07, + "loss": 0.4415, + "step": 10938 + }, + { + "epoch": 0.93, + "learning_rate": 2.3644258211958926e-07, + "loss": 0.4355, + "step": 10939 + }, + { + "epoch": 0.93, + "learning_rate": 2.3584598004816162e-07, + "loss": 0.447, + "step": 10940 + }, + { + "epoch": 0.93, + "learning_rate": 2.3525012263188373e-07, + "loss": 0.4539, + "step": 10941 + }, + { + "epoch": 0.93, + "learning_rate": 2.3465500991619815e-07, + "loss": 0.4374, + "step": 10942 + }, + { + "epoch": 0.93, + "learning_rate": 2.340606419464897e-07, + "loss": 0.4357, + "step": 10943 + }, + { + "epoch": 0.93, + "learning_rate": 2.3346701876808987e-07, + "loss": 0.4678, + "step": 10944 + }, + { + "epoch": 0.93, + "learning_rate": 2.328741404262691e-07, + "loss": 0.4749, + "step": 10945 + }, + { + "epoch": 0.93, + "learning_rate": 2.3228200696624125e-07, + "loss": 0.4584, + "step": 10946 + }, + { + "epoch": 0.93, + "learning_rate": 2.3169061843316688e-07, + "loss": 0.4437, + "step": 10947 + }, + { + "epoch": 0.93, + "learning_rate": 2.3109997487214987e-07, + "loss": 0.4559, + "step": 10948 + }, + { + "epoch": 0.93, + "learning_rate": 2.3051007632823085e-07, + "loss": 0.4641, + "step": 10949 + }, + { + "epoch": 0.93, + "learning_rate": 2.2992092284639944e-07, + "loss": 0.4333, + "step": 10950 + }, + { + "epoch": 0.93, + "learning_rate": 2.2933251447158744e-07, + "loss": 0.4453, + "step": 10951 + }, + { + "epoch": 0.93, + "learning_rate": 2.2874485124867007e-07, + "loss": 0.4492, + "step": 10952 + }, + { + "epoch": 0.93, + "learning_rate": 2.281579332224626e-07, + "loss": 0.4592, + "step": 10953 + }, + { + "epoch": 0.93, + "learning_rate": 2.275717604377292e-07, + "loss": 0.4332, + "step": 10954 + }, + { + "epoch": 0.93, + "learning_rate": 2.2698633293917193e-07, + "loss": 0.4594, + "step": 10955 + }, + { + "epoch": 0.93, + "learning_rate": 2.2640165077143618e-07, + "loss": 0.4852, + "step": 10956 + }, + { + "epoch": 0.93, + "learning_rate": 2.2581771397911512e-07, + "loss": 0.4415, + "step": 10957 + }, + { + "epoch": 0.93, + "learning_rate": 2.2523452260674207e-07, + "loss": 0.4633, + "step": 10958 + }, + { + "epoch": 0.93, + "learning_rate": 2.246520766987914e-07, + "loss": 0.4636, + "step": 10959 + }, + { + "epoch": 0.93, + "learning_rate": 2.2407037629968431e-07, + "loss": 0.4401, + "step": 10960 + }, + { + "epoch": 0.93, + "learning_rate": 2.2348942145378415e-07, + "loss": 0.4451, + "step": 10961 + }, + { + "epoch": 0.93, + "learning_rate": 2.2290921220539662e-07, + "loss": 0.4524, + "step": 10962 + }, + { + "epoch": 0.93, + "learning_rate": 2.2232974859877076e-07, + "loss": 0.4527, + "step": 10963 + }, + { + "epoch": 0.93, + "learning_rate": 2.2175103067809788e-07, + "loss": 0.4699, + "step": 10964 + }, + { + "epoch": 0.93, + "learning_rate": 2.211730584875138e-07, + "loss": 0.4765, + "step": 10965 + }, + { + "epoch": 0.94, + "learning_rate": 2.2059583207109992e-07, + "loss": 0.4437, + "step": 10966 + }, + { + "epoch": 0.94, + "learning_rate": 2.2001935147287434e-07, + "loss": 0.4708, + "step": 10967 + }, + { + "epoch": 0.94, + "learning_rate": 2.1944361673680304e-07, + "loss": 0.4577, + "step": 10968 + }, + { + "epoch": 0.94, + "learning_rate": 2.188686279067942e-07, + "loss": 0.4519, + "step": 10969 + }, + { + "epoch": 0.94, + "learning_rate": 2.182943850266994e-07, + "loss": 0.4476, + "step": 10970 + }, + { + "epoch": 0.94, + "learning_rate": 2.1772088814031144e-07, + "loss": 0.451, + "step": 10971 + }, + { + "epoch": 0.94, + "learning_rate": 2.1714813729136975e-07, + "loss": 0.4642, + "step": 10972 + }, + { + "epoch": 0.94, + "learning_rate": 2.165761325235527e-07, + "loss": 0.4584, + "step": 10973 + }, + { + "epoch": 0.94, + "learning_rate": 2.160048738804821e-07, + "loss": 0.4681, + "step": 10974 + }, + { + "epoch": 0.94, + "learning_rate": 2.1543436140572972e-07, + "loss": 0.4437, + "step": 10975 + }, + { + "epoch": 0.94, + "learning_rate": 2.1486459514280078e-07, + "loss": 0.444, + "step": 10976 + }, + { + "epoch": 0.94, + "learning_rate": 2.1429557513514942e-07, + "loss": 0.479, + "step": 10977 + }, + { + "epoch": 0.94, + "learning_rate": 2.1372730142617205e-07, + "loss": 0.4597, + "step": 10978 + }, + { + "epoch": 0.94, + "learning_rate": 2.131597740592073e-07, + "loss": 0.4416, + "step": 10979 + }, + { + "epoch": 0.94, + "learning_rate": 2.1259299307753721e-07, + "loss": 0.4525, + "step": 10980 + }, + { + "epoch": 0.94, + "learning_rate": 2.1202695852438725e-07, + "loss": 0.4464, + "step": 10981 + }, + { + "epoch": 0.94, + "learning_rate": 2.11461670442924e-07, + "loss": 0.4404, + "step": 10982 + }, + { + "epoch": 0.94, + "learning_rate": 2.1089712887625847e-07, + "loss": 0.4468, + "step": 10983 + }, + { + "epoch": 0.94, + "learning_rate": 2.1033333386744848e-07, + "loss": 0.4434, + "step": 10984 + }, + { + "epoch": 0.94, + "learning_rate": 2.097702854594874e-07, + "loss": 0.4478, + "step": 10985 + }, + { + "epoch": 0.94, + "learning_rate": 2.092079836953176e-07, + "loss": 0.4562, + "step": 10986 + }, + { + "epoch": 0.94, + "learning_rate": 2.0864642861782246e-07, + "loss": 0.4505, + "step": 10987 + }, + { + "epoch": 0.94, + "learning_rate": 2.0808562026982894e-07, + "loss": 0.4579, + "step": 10988 + }, + { + "epoch": 0.94, + "learning_rate": 2.0752555869410495e-07, + "loss": 0.4424, + "step": 10989 + }, + { + "epoch": 0.94, + "learning_rate": 2.069662439333664e-07, + "loss": 0.4755, + "step": 10990 + }, + { + "epoch": 0.94, + "learning_rate": 2.064076760302647e-07, + "loss": 0.4535, + "step": 10991 + }, + { + "epoch": 0.94, + "learning_rate": 2.0584985502740018e-07, + "loss": 0.4339, + "step": 10992 + }, + { + "epoch": 0.94, + "learning_rate": 2.0529278096731664e-07, + "loss": 0.4365, + "step": 10993 + }, + { + "epoch": 0.94, + "learning_rate": 2.0473645389249674e-07, + "loss": 0.4527, + "step": 10994 + }, + { + "epoch": 0.94, + "learning_rate": 2.0418087384536878e-07, + "loss": 0.4547, + "step": 10995 + }, + { + "epoch": 0.94, + "learning_rate": 2.0362604086830328e-07, + "loss": 0.442, + "step": 10996 + }, + { + "epoch": 0.94, + "learning_rate": 2.0307195500361532e-07, + "loss": 0.4553, + "step": 10997 + }, + { + "epoch": 0.94, + "learning_rate": 2.0251861629356108e-07, + "loss": 0.4639, + "step": 10998 + }, + { + "epoch": 0.94, + "learning_rate": 2.0196602478034012e-07, + "loss": 0.4334, + "step": 10999 + }, + { + "epoch": 0.94, + "learning_rate": 2.014141805060954e-07, + "loss": 0.4603, + "step": 11000 + }, + { + "epoch": 0.94, + "learning_rate": 2.0086308351291328e-07, + "loss": 0.4658, + "step": 11001 + }, + { + "epoch": 0.94, + "learning_rate": 2.0031273384282347e-07, + "loss": 0.4344, + "step": 11002 + }, + { + "epoch": 0.94, + "learning_rate": 1.9976313153779568e-07, + "loss": 0.4628, + "step": 11003 + }, + { + "epoch": 0.94, + "learning_rate": 1.9921427663974646e-07, + "loss": 0.4693, + "step": 11004 + }, + { + "epoch": 0.94, + "learning_rate": 1.986661691905345e-07, + "loss": 0.4587, + "step": 11005 + }, + { + "epoch": 0.94, + "learning_rate": 1.981188092319586e-07, + "loss": 0.4865, + "step": 11006 + }, + { + "epoch": 0.94, + "learning_rate": 1.9757219680576422e-07, + "loss": 0.4623, + "step": 11007 + }, + { + "epoch": 0.94, + "learning_rate": 1.9702633195363918e-07, + "loss": 0.4291, + "step": 11008 + }, + { + "epoch": 0.94, + "learning_rate": 1.9648121471721126e-07, + "loss": 0.46, + "step": 11009 + }, + { + "epoch": 0.94, + "learning_rate": 1.95936845138055e-07, + "loss": 0.4559, + "step": 11010 + }, + { + "epoch": 0.94, + "learning_rate": 1.9539322325768494e-07, + "loss": 0.4591, + "step": 11011 + }, + { + "epoch": 0.94, + "learning_rate": 1.9485034911756018e-07, + "loss": 0.4236, + "step": 11012 + }, + { + "epoch": 0.94, + "learning_rate": 1.9430822275908423e-07, + "loss": 0.4554, + "step": 11013 + }, + { + "epoch": 0.94, + "learning_rate": 1.937668442235996e-07, + "loss": 0.441, + "step": 11014 + }, + { + "epoch": 0.94, + "learning_rate": 1.9322621355239658e-07, + "loss": 0.4628, + "step": 11015 + }, + { + "epoch": 0.94, + "learning_rate": 1.9268633078670328e-07, + "loss": 0.4591, + "step": 11016 + }, + { + "epoch": 0.94, + "learning_rate": 1.921471959676957e-07, + "loss": 0.462, + "step": 11017 + }, + { + "epoch": 0.94, + "learning_rate": 1.9160880913648983e-07, + "loss": 0.4692, + "step": 11018 + }, + { + "epoch": 0.94, + "learning_rate": 1.910711703341439e-07, + "loss": 0.4639, + "step": 11019 + }, + { + "epoch": 0.94, + "learning_rate": 1.9053427960166183e-07, + "loss": 0.4549, + "step": 11020 + }, + { + "epoch": 0.94, + "learning_rate": 1.8999813697998858e-07, + "loss": 0.435, + "step": 11021 + }, + { + "epoch": 0.94, + "learning_rate": 1.8946274251001373e-07, + "loss": 0.4579, + "step": 11022 + }, + { + "epoch": 0.94, + "learning_rate": 1.889280962325668e-07, + "loss": 0.4396, + "step": 11023 + }, + { + "epoch": 0.94, + "learning_rate": 1.8839419818842408e-07, + "loss": 0.4506, + "step": 11024 + }, + { + "epoch": 0.94, + "learning_rate": 1.8786104841830188e-07, + "loss": 0.4461, + "step": 11025 + }, + { + "epoch": 0.94, + "learning_rate": 1.87328646962861e-07, + "loss": 0.463, + "step": 11026 + }, + { + "epoch": 0.94, + "learning_rate": 1.8679699386270457e-07, + "loss": 0.4612, + "step": 11027 + }, + { + "epoch": 0.94, + "learning_rate": 1.8626608915837675e-07, + "loss": 0.4457, + "step": 11028 + }, + { + "epoch": 0.94, + "learning_rate": 1.857359328903685e-07, + "loss": 0.4449, + "step": 11029 + }, + { + "epoch": 0.94, + "learning_rate": 1.8520652509911196e-07, + "loss": 0.4326, + "step": 11030 + }, + { + "epoch": 0.94, + "learning_rate": 1.8467786582498147e-07, + "loss": 0.4674, + "step": 11031 + }, + { + "epoch": 0.94, + "learning_rate": 1.841499551082937e-07, + "loss": 0.4605, + "step": 11032 + }, + { + "epoch": 0.94, + "learning_rate": 1.8362279298931197e-07, + "loss": 0.4382, + "step": 11033 + }, + { + "epoch": 0.94, + "learning_rate": 1.8309637950823632e-07, + "loss": 0.4566, + "step": 11034 + }, + { + "epoch": 0.94, + "learning_rate": 1.825707147052147e-07, + "loss": 0.459, + "step": 11035 + }, + { + "epoch": 0.94, + "learning_rate": 1.8204579862033945e-07, + "loss": 0.4591, + "step": 11036 + }, + { + "epoch": 0.94, + "learning_rate": 1.8152163129363854e-07, + "loss": 0.4548, + "step": 11037 + }, + { + "epoch": 0.94, + "learning_rate": 1.8099821276508888e-07, + "loss": 0.4586, + "step": 11038 + }, + { + "epoch": 0.94, + "learning_rate": 1.8047554307460967e-07, + "loss": 0.4338, + "step": 11039 + }, + { + "epoch": 0.94, + "learning_rate": 1.7995362226206014e-07, + "loss": 0.4548, + "step": 11040 + }, + { + "epoch": 0.94, + "learning_rate": 1.7943245036724512e-07, + "loss": 0.4346, + "step": 11041 + }, + { + "epoch": 0.94, + "learning_rate": 1.7891202742991165e-07, + "loss": 0.4554, + "step": 11042 + }, + { + "epoch": 0.94, + "learning_rate": 1.7839235348974692e-07, + "loss": 0.4458, + "step": 11043 + }, + { + "epoch": 0.94, + "learning_rate": 1.7787342858638589e-07, + "loss": 0.4568, + "step": 11044 + }, + { + "epoch": 0.94, + "learning_rate": 1.773552527594047e-07, + "loss": 0.4612, + "step": 11045 + }, + { + "epoch": 0.94, + "learning_rate": 1.7683782604831946e-07, + "loss": 0.4704, + "step": 11046 + }, + { + "epoch": 0.94, + "learning_rate": 1.7632114849259197e-07, + "loss": 0.4416, + "step": 11047 + }, + { + "epoch": 0.94, + "learning_rate": 1.7580522013162626e-07, + "loss": 0.4583, + "step": 11048 + }, + { + "epoch": 0.94, + "learning_rate": 1.7529004100476866e-07, + "loss": 0.4331, + "step": 11049 + }, + { + "epoch": 0.94, + "learning_rate": 1.747756111513099e-07, + "loss": 0.4574, + "step": 11050 + }, + { + "epoch": 0.94, + "learning_rate": 1.7426193061048313e-07, + "loss": 0.4417, + "step": 11051 + }, + { + "epoch": 0.94, + "learning_rate": 1.7374899942146139e-07, + "loss": 0.466, + "step": 11052 + }, + { + "epoch": 0.94, + "learning_rate": 1.7323681762336453e-07, + "loss": 0.4488, + "step": 11053 + }, + { + "epoch": 0.94, + "learning_rate": 1.7272538525525462e-07, + "loss": 0.4597, + "step": 11054 + }, + { + "epoch": 0.94, + "learning_rate": 1.722147023561338e-07, + "loss": 0.4388, + "step": 11055 + }, + { + "epoch": 0.94, + "learning_rate": 1.717047689649487e-07, + "loss": 0.4611, + "step": 11056 + }, + { + "epoch": 0.94, + "learning_rate": 1.7119558512059044e-07, + "loss": 0.4352, + "step": 11057 + }, + { + "epoch": 0.94, + "learning_rate": 1.7068715086189124e-07, + "loss": 0.4608, + "step": 11058 + }, + { + "epoch": 0.94, + "learning_rate": 1.701794662276257e-07, + "loss": 0.454, + "step": 11059 + }, + { + "epoch": 0.94, + "learning_rate": 1.6967253125651284e-07, + "loss": 0.4486, + "step": 11060 + }, + { + "epoch": 0.94, + "learning_rate": 1.6916634598721283e-07, + "loss": 0.4516, + "step": 11061 + }, + { + "epoch": 0.94, + "learning_rate": 1.6866091045832923e-07, + "loss": 0.4441, + "step": 11062 + }, + { + "epoch": 0.94, + "learning_rate": 1.6815622470841008e-07, + "loss": 0.4722, + "step": 11063 + }, + { + "epoch": 0.94, + "learning_rate": 1.6765228877594352e-07, + "loss": 0.4273, + "step": 11064 + }, + { + "epoch": 0.94, + "learning_rate": 1.6714910269936213e-07, + "loss": 0.4615, + "step": 11065 + }, + { + "epoch": 0.94, + "learning_rate": 1.6664666651704075e-07, + "loss": 0.4544, + "step": 11066 + }, + { + "epoch": 0.94, + "learning_rate": 1.6614498026729876e-07, + "loss": 0.4181, + "step": 11067 + }, + { + "epoch": 0.94, + "learning_rate": 1.656440439883944e-07, + "loss": 0.4683, + "step": 11068 + }, + { + "epoch": 0.94, + "learning_rate": 1.651438577185338e-07, + "loss": 0.457, + "step": 11069 + }, + { + "epoch": 0.94, + "learning_rate": 1.646444214958598e-07, + "loss": 0.4588, + "step": 11070 + }, + { + "epoch": 0.94, + "learning_rate": 1.6414573535846523e-07, + "loss": 0.4582, + "step": 11071 + }, + { + "epoch": 0.94, + "learning_rate": 1.636477993443808e-07, + "loss": 0.4614, + "step": 11072 + }, + { + "epoch": 0.94, + "learning_rate": 1.6315061349157946e-07, + "loss": 0.4429, + "step": 11073 + }, + { + "epoch": 0.94, + "learning_rate": 1.6265417783798087e-07, + "loss": 0.434, + "step": 11074 + }, + { + "epoch": 0.94, + "learning_rate": 1.6215849242144365e-07, + "loss": 0.4679, + "step": 11075 + }, + { + "epoch": 0.94, + "learning_rate": 1.61663557279772e-07, + "loss": 0.4637, + "step": 11076 + }, + { + "epoch": 0.94, + "learning_rate": 1.6116937245071018e-07, + "loss": 0.4559, + "step": 11077 + }, + { + "epoch": 0.94, + "learning_rate": 1.6067593797195025e-07, + "loss": 0.475, + "step": 11078 + }, + { + "epoch": 0.94, + "learning_rate": 1.6018325388111876e-07, + "loss": 0.4626, + "step": 11079 + }, + { + "epoch": 0.94, + "learning_rate": 1.5969132021579347e-07, + "loss": 0.4456, + "step": 11080 + }, + { + "epoch": 0.94, + "learning_rate": 1.5920013701349103e-07, + "loss": 0.4441, + "step": 11081 + }, + { + "epoch": 0.94, + "learning_rate": 1.587097043116681e-07, + "loss": 0.4634, + "step": 11082 + }, + { + "epoch": 0.95, + "learning_rate": 1.5822002214773035e-07, + "loss": 0.437, + "step": 11083 + }, + { + "epoch": 0.95, + "learning_rate": 1.5773109055902235e-07, + "loss": 0.4629, + "step": 11084 + }, + { + "epoch": 0.95, + "learning_rate": 1.5724290958283094e-07, + "loss": 0.4376, + "step": 11085 + }, + { + "epoch": 0.95, + "learning_rate": 1.5675547925638856e-07, + "loss": 0.4558, + "step": 11086 + }, + { + "epoch": 0.95, + "learning_rate": 1.562687996168677e-07, + "loss": 0.4587, + "step": 11087 + }, + { + "epoch": 0.95, + "learning_rate": 1.5578287070138308e-07, + "loss": 0.4498, + "step": 11088 + }, + { + "epoch": 0.95, + "learning_rate": 1.5529769254699512e-07, + "loss": 0.4503, + "step": 11089 + }, + { + "epoch": 0.95, + "learning_rate": 1.5481326519070638e-07, + "loss": 0.4405, + "step": 11090 + }, + { + "epoch": 0.95, + "learning_rate": 1.543295886694607e-07, + "loss": 0.4704, + "step": 11091 + }, + { + "epoch": 0.95, + "learning_rate": 1.5384666302014407e-07, + "loss": 0.4414, + "step": 11092 + }, + { + "epoch": 0.95, + "learning_rate": 1.5336448827958815e-07, + "loss": 0.4426, + "step": 11093 + }, + { + "epoch": 0.95, + "learning_rate": 1.5288306448456468e-07, + "loss": 0.4727, + "step": 11094 + }, + { + "epoch": 0.95, + "learning_rate": 1.5240239167178872e-07, + "loss": 0.48, + "step": 11095 + }, + { + "epoch": 0.95, + "learning_rate": 1.519224698779198e-07, + "loss": 0.4368, + "step": 11096 + }, + { + "epoch": 0.95, + "learning_rate": 1.5144329913955759e-07, + "loss": 0.463, + "step": 11097 + }, + { + "epoch": 0.95, + "learning_rate": 1.50964879493245e-07, + "loss": 0.4582, + "step": 11098 + }, + { + "epoch": 0.95, + "learning_rate": 1.504872109754696e-07, + "loss": 0.4312, + "step": 11099 + }, + { + "epoch": 0.95, + "learning_rate": 1.5001029362265996e-07, + "loss": 0.4585, + "step": 11100 + }, + { + "epoch": 0.95, + "learning_rate": 1.4953412747118813e-07, + "loss": 0.4355, + "step": 11101 + }, + { + "epoch": 0.95, + "learning_rate": 1.4905871255736838e-07, + "loss": 0.4648, + "step": 11102 + }, + { + "epoch": 0.95, + "learning_rate": 1.4858404891745616e-07, + "loss": 0.4411, + "step": 11103 + }, + { + "epoch": 0.95, + "learning_rate": 1.4811013658765471e-07, + "loss": 0.4465, + "step": 11104 + }, + { + "epoch": 0.95, + "learning_rate": 1.4763697560410406e-07, + "loss": 0.4731, + "step": 11105 + }, + { + "epoch": 0.95, + "learning_rate": 1.4716456600288975e-07, + "loss": 0.4523, + "step": 11106 + }, + { + "epoch": 0.95, + "learning_rate": 1.4669290782003963e-07, + "loss": 0.4483, + "step": 11107 + }, + { + "epoch": 0.95, + "learning_rate": 1.4622200109152495e-07, + "loss": 0.4605, + "step": 11108 + }, + { + "epoch": 0.95, + "learning_rate": 1.4575184585325918e-07, + "loss": 0.4506, + "step": 11109 + }, + { + "epoch": 0.95, + "learning_rate": 1.452824421410981e-07, + "loss": 0.4615, + "step": 11110 + }, + { + "epoch": 0.95, + "learning_rate": 1.4481378999083973e-07, + "loss": 0.4493, + "step": 11111 + }, + { + "epoch": 0.95, + "learning_rate": 1.4434588943822547e-07, + "loss": 0.4284, + "step": 11112 + }, + { + "epoch": 0.95, + "learning_rate": 1.4387874051894013e-07, + "loss": 0.4511, + "step": 11113 + }, + { + "epoch": 0.95, + "learning_rate": 1.4341234326861076e-07, + "loss": 0.4698, + "step": 11114 + }, + { + "epoch": 0.95, + "learning_rate": 1.4294669772280556e-07, + "loss": 0.4439, + "step": 11115 + }, + { + "epoch": 0.95, + "learning_rate": 1.4248180391703614e-07, + "loss": 0.4508, + "step": 11116 + }, + { + "epoch": 0.95, + "learning_rate": 1.420176618867597e-07, + "loss": 0.4403, + "step": 11117 + }, + { + "epoch": 0.95, + "learning_rate": 1.4155427166737123e-07, + "loss": 0.479, + "step": 11118 + }, + { + "epoch": 0.95, + "learning_rate": 1.410916332942125e-07, + "loss": 0.443, + "step": 11119 + }, + { + "epoch": 0.95, + "learning_rate": 1.4062974680256635e-07, + "loss": 0.46, + "step": 11120 + }, + { + "epoch": 0.95, + "learning_rate": 1.4016861222765576e-07, + "loss": 0.4518, + "step": 11121 + }, + { + "epoch": 0.95, + "learning_rate": 1.3970822960465035e-07, + "loss": 0.4201, + "step": 11122 + }, + { + "epoch": 0.95, + "learning_rate": 1.3924859896866206e-07, + "loss": 0.4475, + "step": 11123 + }, + { + "epoch": 0.95, + "learning_rate": 1.387897203547417e-07, + "loss": 0.4447, + "step": 11124 + }, + { + "epoch": 0.95, + "learning_rate": 1.3833159379788686e-07, + "loss": 0.4459, + "step": 11125 + }, + { + "epoch": 0.95, + "learning_rate": 1.3787421933303735e-07, + "loss": 0.4391, + "step": 11126 + }, + { + "epoch": 0.95, + "learning_rate": 1.3741759699507084e-07, + "loss": 0.4734, + "step": 11127 + }, + { + "epoch": 0.95, + "learning_rate": 1.3696172681881504e-07, + "loss": 0.435, + "step": 11128 + }, + { + "epoch": 0.95, + "learning_rate": 1.3650660883903545e-07, + "loss": 0.4521, + "step": 11129 + }, + { + "epoch": 0.95, + "learning_rate": 1.3605224309043873e-07, + "loss": 0.4717, + "step": 11130 + }, + { + "epoch": 0.95, + "learning_rate": 1.3559862960767944e-07, + "loss": 0.4448, + "step": 11131 + }, + { + "epoch": 0.95, + "learning_rate": 1.351457684253521e-07, + "loss": 0.4376, + "step": 11132 + }, + { + "epoch": 0.95, + "learning_rate": 1.346936595779924e-07, + "loss": 0.4508, + "step": 11133 + }, + { + "epoch": 0.95, + "learning_rate": 1.3424230310007946e-07, + "loss": 0.4451, + "step": 11134 + }, + { + "epoch": 0.95, + "learning_rate": 1.3379169902603796e-07, + "loss": 0.4569, + "step": 11135 + }, + { + "epoch": 0.95, + "learning_rate": 1.3334184739023147e-07, + "loss": 0.4518, + "step": 11136 + }, + { + "epoch": 0.95, + "learning_rate": 1.3289274822696818e-07, + "loss": 0.4577, + "step": 11137 + }, + { + "epoch": 0.95, + "learning_rate": 1.3244440157049733e-07, + "loss": 0.4355, + "step": 11138 + }, + { + "epoch": 0.95, + "learning_rate": 1.3199680745501265e-07, + "loss": 0.4519, + "step": 11139 + }, + { + "epoch": 0.95, + "learning_rate": 1.315499659146491e-07, + "loss": 0.4451, + "step": 11140 + }, + { + "epoch": 0.95, + "learning_rate": 1.3110387698348493e-07, + "loss": 0.4382, + "step": 11141 + }, + { + "epoch": 0.95, + "learning_rate": 1.3065854069553963e-07, + "loss": 0.4723, + "step": 11142 + }, + { + "epoch": 0.95, + "learning_rate": 1.3021395708477824e-07, + "loss": 0.4612, + "step": 11143 + }, + { + "epoch": 0.95, + "learning_rate": 1.2977012618510477e-07, + "loss": 0.4486, + "step": 11144 + }, + { + "epoch": 0.95, + "learning_rate": 1.2932704803036877e-07, + "loss": 0.4362, + "step": 11145 + }, + { + "epoch": 0.95, + "learning_rate": 1.2888472265436104e-07, + "loss": 0.4738, + "step": 11146 + }, + { + "epoch": 0.95, + "learning_rate": 1.2844315009081453e-07, + "loss": 0.459, + "step": 11147 + }, + { + "epoch": 0.95, + "learning_rate": 1.280023303734057e-07, + "loss": 0.46, + "step": 11148 + }, + { + "epoch": 0.95, + "learning_rate": 1.2756226353575428e-07, + "loss": 0.4405, + "step": 11149 + }, + { + "epoch": 0.95, + "learning_rate": 1.2712294961142125e-07, + "loss": 0.4577, + "step": 11150 + }, + { + "epoch": 0.95, + "learning_rate": 1.2668438863390975e-07, + "loss": 0.4326, + "step": 11151 + }, + { + "epoch": 0.95, + "learning_rate": 1.262465806366664e-07, + "loss": 0.4452, + "step": 11152 + }, + { + "epoch": 0.95, + "learning_rate": 1.2580952565308002e-07, + "loss": 0.4548, + "step": 11153 + }, + { + "epoch": 0.95, + "learning_rate": 1.2537322371648286e-07, + "loss": 0.4275, + "step": 11154 + }, + { + "epoch": 0.95, + "learning_rate": 1.249376748601494e-07, + "loss": 0.4595, + "step": 11155 + }, + { + "epoch": 0.95, + "learning_rate": 1.245028791172964e-07, + "loss": 0.4445, + "step": 11156 + }, + { + "epoch": 0.95, + "learning_rate": 1.2406883652108182e-07, + "loss": 0.4728, + "step": 11157 + }, + { + "epoch": 0.95, + "learning_rate": 1.2363554710460913e-07, + "loss": 0.4463, + "step": 11158 + }, + { + "epoch": 0.95, + "learning_rate": 1.2320301090092301e-07, + "loss": 0.45, + "step": 11159 + }, + { + "epoch": 0.95, + "learning_rate": 1.2277122794300822e-07, + "loss": 0.4638, + "step": 11160 + }, + { + "epoch": 0.95, + "learning_rate": 1.2234019826379618e-07, + "loss": 0.4349, + "step": 11161 + }, + { + "epoch": 0.95, + "learning_rate": 1.2190992189615836e-07, + "loss": 0.4557, + "step": 11162 + }, + { + "epoch": 0.95, + "learning_rate": 1.2148039887290963e-07, + "loss": 0.4634, + "step": 11163 + }, + { + "epoch": 0.95, + "learning_rate": 1.2105162922680823e-07, + "loss": 0.4286, + "step": 11164 + }, + { + "epoch": 0.95, + "learning_rate": 1.2062361299055247e-07, + "loss": 0.4577, + "step": 11165 + }, + { + "epoch": 0.95, + "learning_rate": 1.201963501967851e-07, + "loss": 0.4493, + "step": 11166 + }, + { + "epoch": 0.95, + "learning_rate": 1.1976984087809007e-07, + "loss": 0.4532, + "step": 11167 + }, + { + "epoch": 0.95, + "learning_rate": 1.19344085066998e-07, + "loss": 0.4614, + "step": 11168 + }, + { + "epoch": 0.95, + "learning_rate": 1.1891908279597519e-07, + "loss": 0.4585, + "step": 11169 + }, + { + "epoch": 0.95, + "learning_rate": 1.1849483409743457e-07, + "loss": 0.4547, + "step": 11170 + }, + { + "epoch": 0.95, + "learning_rate": 1.1807133900373246e-07, + "loss": 0.4472, + "step": 11171 + }, + { + "epoch": 0.95, + "learning_rate": 1.176485975471664e-07, + "loss": 0.4495, + "step": 11172 + }, + { + "epoch": 0.95, + "learning_rate": 1.1722660975997501e-07, + "loss": 0.4726, + "step": 11173 + }, + { + "epoch": 0.95, + "learning_rate": 1.1680537567434259e-07, + "loss": 0.4655, + "step": 11174 + }, + { + "epoch": 0.95, + "learning_rate": 1.1638489532239339e-07, + "loss": 0.4449, + "step": 11175 + }, + { + "epoch": 0.95, + "learning_rate": 1.1596516873619401e-07, + "loss": 0.456, + "step": 11176 + }, + { + "epoch": 0.95, + "learning_rate": 1.1554619594775663e-07, + "loss": 0.4299, + "step": 11177 + }, + { + "epoch": 0.95, + "learning_rate": 1.1512797698903122e-07, + "loss": 0.4617, + "step": 11178 + }, + { + "epoch": 0.95, + "learning_rate": 1.1471051189191562e-07, + "loss": 0.4518, + "step": 11179 + }, + { + "epoch": 0.95, + "learning_rate": 1.1429380068824547e-07, + "loss": 0.4374, + "step": 11180 + }, + { + "epoch": 0.95, + "learning_rate": 1.1387784340980201e-07, + "loss": 0.4468, + "step": 11181 + }, + { + "epoch": 0.95, + "learning_rate": 1.1346264008830765e-07, + "loss": 0.4498, + "step": 11182 + }, + { + "epoch": 0.95, + "learning_rate": 1.1304819075542706e-07, + "loss": 0.4418, + "step": 11183 + }, + { + "epoch": 0.95, + "learning_rate": 1.1263449544276938e-07, + "loss": 0.428, + "step": 11184 + }, + { + "epoch": 0.95, + "learning_rate": 1.1222155418188163e-07, + "loss": 0.4761, + "step": 11185 + }, + { + "epoch": 0.95, + "learning_rate": 1.118093670042597e-07, + "loss": 0.4554, + "step": 11186 + }, + { + "epoch": 0.95, + "learning_rate": 1.1139793394133736e-07, + "loss": 0.4336, + "step": 11187 + }, + { + "epoch": 0.95, + "learning_rate": 1.109872550244917e-07, + "loss": 0.4504, + "step": 11188 + }, + { + "epoch": 0.95, + "learning_rate": 1.1057733028504325e-07, + "loss": 0.457, + "step": 11189 + }, + { + "epoch": 0.95, + "learning_rate": 1.1016815975425587e-07, + "loss": 0.447, + "step": 11190 + }, + { + "epoch": 0.95, + "learning_rate": 1.097597434633324e-07, + "loss": 0.4383, + "step": 11191 + }, + { + "epoch": 0.95, + "learning_rate": 1.0935208144342125e-07, + "loss": 0.4527, + "step": 11192 + }, + { + "epoch": 0.95, + "learning_rate": 1.089451737256142e-07, + "loss": 0.4472, + "step": 11193 + }, + { + "epoch": 0.95, + "learning_rate": 1.0853902034093977e-07, + "loss": 0.4591, + "step": 11194 + }, + { + "epoch": 0.95, + "learning_rate": 1.0813362132037652e-07, + "loss": 0.4611, + "step": 11195 + }, + { + "epoch": 0.95, + "learning_rate": 1.0772897669484084e-07, + "loss": 0.4541, + "step": 11196 + }, + { + "epoch": 0.95, + "learning_rate": 1.0732508649519247e-07, + "loss": 0.4464, + "step": 11197 + }, + { + "epoch": 0.95, + "learning_rate": 1.0692195075223233e-07, + "loss": 0.463, + "step": 11198 + }, + { + "epoch": 0.95, + "learning_rate": 1.0651956949670805e-07, + "loss": 0.4446, + "step": 11199 + }, + { + "epoch": 0.95, + "learning_rate": 1.0611794275930398e-07, + "loss": 0.4544, + "step": 11200 + }, + { + "epoch": 0.96, + "learning_rate": 1.0571707057065229e-07, + "loss": 0.4527, + "step": 11201 + }, + { + "epoch": 0.96, + "learning_rate": 1.0531695296132515e-07, + "loss": 0.4584, + "step": 11202 + }, + { + "epoch": 0.96, + "learning_rate": 1.0491758996183487e-07, + "loss": 0.442, + "step": 11203 + }, + { + "epoch": 0.96, + "learning_rate": 1.045189816026393e-07, + "loss": 0.4488, + "step": 11204 + }, + { + "epoch": 0.96, + "learning_rate": 1.0412112791414075e-07, + "loss": 0.4419, + "step": 11205 + }, + { + "epoch": 0.96, + "learning_rate": 1.0372402892667721e-07, + "loss": 0.4535, + "step": 11206 + }, + { + "epoch": 0.96, + "learning_rate": 1.0332768467053556e-07, + "loss": 0.4299, + "step": 11207 + }, + { + "epoch": 0.96, + "learning_rate": 1.029320951759416e-07, + "loss": 0.4473, + "step": 11208 + }, + { + "epoch": 0.96, + "learning_rate": 1.0253726047306567e-07, + "loss": 0.4606, + "step": 11209 + }, + { + "epoch": 0.96, + "learning_rate": 1.0214318059201922e-07, + "loss": 0.453, + "step": 11210 + }, + { + "epoch": 0.96, + "learning_rate": 1.01749855562856e-07, + "loss": 0.4488, + "step": 11211 + }, + { + "epoch": 0.96, + "learning_rate": 1.0135728541557199e-07, + "loss": 0.448, + "step": 11212 + }, + { + "epoch": 0.96, + "learning_rate": 1.009654701801066e-07, + "loss": 0.4661, + "step": 11213 + }, + { + "epoch": 0.96, + "learning_rate": 1.005744098863437e-07, + "loss": 0.4439, + "step": 11214 + }, + { + "epoch": 0.96, + "learning_rate": 1.0018410456410388e-07, + "loss": 0.4469, + "step": 11215 + }, + { + "epoch": 0.96, + "learning_rate": 9.979455424315442e-08, + "loss": 0.4398, + "step": 11216 + }, + { + "epoch": 0.96, + "learning_rate": 9.940575895320492e-08, + "loss": 0.4658, + "step": 11217 + }, + { + "epoch": 0.96, + "learning_rate": 9.901771872390497e-08, + "loss": 0.4472, + "step": 11218 + }, + { + "epoch": 0.96, + "learning_rate": 9.863043358485092e-08, + "loss": 0.4364, + "step": 11219 + }, + { + "epoch": 0.96, + "learning_rate": 9.824390356557578e-08, + "loss": 0.4682, + "step": 11220 + }, + { + "epoch": 0.96, + "learning_rate": 9.785812869555933e-08, + "loss": 0.4421, + "step": 11221 + }, + { + "epoch": 0.96, + "learning_rate": 9.747310900422136e-08, + "loss": 0.4712, + "step": 11222 + }, + { + "epoch": 0.96, + "learning_rate": 9.708884452092837e-08, + "loss": 0.4265, + "step": 11223 + }, + { + "epoch": 0.96, + "learning_rate": 9.670533527498139e-08, + "loss": 0.4718, + "step": 11224 + }, + { + "epoch": 0.96, + "learning_rate": 9.632258129563144e-08, + "loss": 0.4537, + "step": 11225 + }, + { + "epoch": 0.96, + "learning_rate": 9.59405826120674e-08, + "loss": 0.4379, + "step": 11226 + }, + { + "epoch": 0.96, + "learning_rate": 9.555933925342265e-08, + "loss": 0.4574, + "step": 11227 + }, + { + "epoch": 0.96, + "learning_rate": 9.517885124877279e-08, + "loss": 0.465, + "step": 11228 + }, + { + "epoch": 0.96, + "learning_rate": 9.479911862713576e-08, + "loss": 0.4393, + "step": 11229 + }, + { + "epoch": 0.96, + "learning_rate": 9.442014141747058e-08, + "loss": 0.4452, + "step": 11230 + }, + { + "epoch": 0.96, + "learning_rate": 9.40419196486786e-08, + "loss": 0.4504, + "step": 11231 + }, + { + "epoch": 0.96, + "learning_rate": 9.366445334960783e-08, + "loss": 0.4456, + "step": 11232 + }, + { + "epoch": 0.96, + "learning_rate": 9.328774254904305e-08, + "loss": 0.4754, + "step": 11233 + }, + { + "epoch": 0.96, + "learning_rate": 9.29117872757146e-08, + "loss": 0.4671, + "step": 11234 + }, + { + "epoch": 0.96, + "learning_rate": 9.253658755829286e-08, + "loss": 0.4556, + "step": 11235 + }, + { + "epoch": 0.96, + "learning_rate": 9.216214342539387e-08, + "loss": 0.4667, + "step": 11236 + }, + { + "epoch": 0.96, + "learning_rate": 9.178845490557475e-08, + "loss": 0.4531, + "step": 11237 + }, + { + "epoch": 0.96, + "learning_rate": 9.141552202733272e-08, + "loss": 0.4503, + "step": 11238 + }, + { + "epoch": 0.96, + "learning_rate": 9.104334481911059e-08, + "loss": 0.4469, + "step": 11239 + }, + { + "epoch": 0.96, + "learning_rate": 9.067192330929009e-08, + "loss": 0.4632, + "step": 11240 + }, + { + "epoch": 0.96, + "learning_rate": 9.030125752620078e-08, + "loss": 0.4466, + "step": 11241 + }, + { + "epoch": 0.96, + "learning_rate": 8.993134749810895e-08, + "loss": 0.44, + "step": 11242 + }, + { + "epoch": 0.96, + "learning_rate": 8.956219325322535e-08, + "loss": 0.4614, + "step": 11243 + }, + { + "epoch": 0.96, + "learning_rate": 8.919379481970414e-08, + "loss": 0.4487, + "step": 11244 + }, + { + "epoch": 0.96, + "learning_rate": 8.88261522256395e-08, + "loss": 0.4312, + "step": 11245 + }, + { + "epoch": 0.96, + "learning_rate": 8.845926549907125e-08, + "loss": 0.4475, + "step": 11246 + }, + { + "epoch": 0.96, + "learning_rate": 8.809313466798031e-08, + "loss": 0.4507, + "step": 11247 + }, + { + "epoch": 0.96, + "learning_rate": 8.772775976028547e-08, + "loss": 0.4456, + "step": 11248 + }, + { + "epoch": 0.96, + "learning_rate": 8.736314080385444e-08, + "loss": 0.4361, + "step": 11249 + }, + { + "epoch": 0.96, + "learning_rate": 8.699927782649609e-08, + "loss": 0.4718, + "step": 11250 + }, + { + "epoch": 0.96, + "learning_rate": 8.66361708559571e-08, + "loss": 0.4512, + "step": 11251 + }, + { + "epoch": 0.96, + "learning_rate": 8.627381991993089e-08, + "loss": 0.4457, + "step": 11252 + }, + { + "epoch": 0.96, + "learning_rate": 8.591222504605201e-08, + "loss": 0.447, + "step": 11253 + }, + { + "epoch": 0.96, + "learning_rate": 8.555138626189619e-08, + "loss": 0.4401, + "step": 11254 + }, + { + "epoch": 0.96, + "learning_rate": 8.519130359498362e-08, + "loss": 0.4421, + "step": 11255 + }, + { + "epoch": 0.96, + "learning_rate": 8.483197707277568e-08, + "loss": 0.4638, + "step": 11256 + }, + { + "epoch": 0.96, + "learning_rate": 8.44734067226749e-08, + "loss": 0.4506, + "step": 11257 + }, + { + "epoch": 0.96, + "learning_rate": 8.411559257202828e-08, + "loss": 0.4484, + "step": 11258 + }, + { + "epoch": 0.96, + "learning_rate": 8.37585346481251e-08, + "loss": 0.4468, + "step": 11259 + }, + { + "epoch": 0.96, + "learning_rate": 8.340223297819472e-08, + "loss": 0.446, + "step": 11260 + }, + { + "epoch": 0.96, + "learning_rate": 8.304668758941093e-08, + "loss": 0.4385, + "step": 11261 + }, + { + "epoch": 0.96, + "learning_rate": 8.26918985088887e-08, + "loss": 0.4606, + "step": 11262 + }, + { + "epoch": 0.96, + "learning_rate": 8.233786576368418e-08, + "loss": 0.4508, + "step": 11263 + }, + { + "epoch": 0.96, + "learning_rate": 8.198458938080023e-08, + "loss": 0.4615, + "step": 11264 + }, + { + "epoch": 0.96, + "learning_rate": 8.16320693871786e-08, + "loss": 0.4301, + "step": 11265 + }, + { + "epoch": 0.96, + "learning_rate": 8.128030580970336e-08, + "loss": 0.4524, + "step": 11266 + }, + { + "epoch": 0.96, + "learning_rate": 8.092929867519972e-08, + "loss": 0.4583, + "step": 11267 + }, + { + "epoch": 0.96, + "learning_rate": 8.05790480104407e-08, + "loss": 0.4411, + "step": 11268 + }, + { + "epoch": 0.96, + "learning_rate": 8.022955384213493e-08, + "loss": 0.4482, + "step": 11269 + }, + { + "epoch": 0.96, + "learning_rate": 7.988081619693666e-08, + "loss": 0.4485, + "step": 11270 + }, + { + "epoch": 0.96, + "learning_rate": 7.95328351014435e-08, + "loss": 0.4305, + "step": 11271 + }, + { + "epoch": 0.96, + "learning_rate": 7.918561058219198e-08, + "loss": 0.45, + "step": 11272 + }, + { + "epoch": 0.96, + "learning_rate": 7.883914266566427e-08, + "loss": 0.4578, + "step": 11273 + }, + { + "epoch": 0.96, + "learning_rate": 7.849343137828369e-08, + "loss": 0.4372, + "step": 11274 + }, + { + "epoch": 0.96, + "learning_rate": 7.814847674641468e-08, + "loss": 0.4456, + "step": 11275 + }, + { + "epoch": 0.96, + "learning_rate": 7.78042787963662e-08, + "loss": 0.463, + "step": 11276 + }, + { + "epoch": 0.96, + "learning_rate": 7.746083755438616e-08, + "loss": 0.4815, + "step": 11277 + }, + { + "epoch": 0.96, + "learning_rate": 7.711815304666804e-08, + "loss": 0.418, + "step": 11278 + }, + { + "epoch": 0.96, + "learning_rate": 7.677622529934648e-08, + "loss": 0.4534, + "step": 11279 + }, + { + "epoch": 0.96, + "learning_rate": 7.643505433849952e-08, + "loss": 0.4446, + "step": 11280 + }, + { + "epoch": 0.96, + "learning_rate": 7.609464019014301e-08, + "loss": 0.4393, + "step": 11281 + }, + { + "epoch": 0.96, + "learning_rate": 7.575498288024174e-08, + "loss": 0.4612, + "step": 11282 + }, + { + "epoch": 0.96, + "learning_rate": 7.541608243469723e-08, + "loss": 0.4473, + "step": 11283 + }, + { + "epoch": 0.96, + "learning_rate": 7.507793887935655e-08, + "loss": 0.4308, + "step": 11284 + }, + { + "epoch": 0.96, + "learning_rate": 7.474055224000688e-08, + "loss": 0.4453, + "step": 11285 + }, + { + "epoch": 0.96, + "learning_rate": 7.440392254237983e-08, + "loss": 0.4487, + "step": 11286 + }, + { + "epoch": 0.96, + "learning_rate": 7.406804981214822e-08, + "loss": 0.4492, + "step": 11287 + }, + { + "epoch": 0.96, + "learning_rate": 7.373293407492598e-08, + "loss": 0.4785, + "step": 11288 + }, + { + "epoch": 0.96, + "learning_rate": 7.33985753562716e-08, + "loss": 0.4528, + "step": 11289 + }, + { + "epoch": 0.96, + "learning_rate": 7.306497368168352e-08, + "loss": 0.4499, + "step": 11290 + }, + { + "epoch": 0.96, + "learning_rate": 7.273212907660476e-08, + "loss": 0.4408, + "step": 11291 + }, + { + "epoch": 0.96, + "learning_rate": 7.240004156641944e-08, + "loss": 0.4683, + "step": 11292 + }, + { + "epoch": 0.96, + "learning_rate": 7.206871117645286e-08, + "loss": 0.451, + "step": 11293 + }, + { + "epoch": 0.96, + "learning_rate": 7.17381379319737e-08, + "loss": 0.4402, + "step": 11294 + }, + { + "epoch": 0.96, + "learning_rate": 7.140832185819402e-08, + "loss": 0.4633, + "step": 11295 + }, + { + "epoch": 0.96, + "learning_rate": 7.10792629802659e-08, + "loss": 0.4634, + "step": 11296 + }, + { + "epoch": 0.96, + "learning_rate": 7.075096132328597e-08, + "loss": 0.4277, + "step": 11297 + }, + { + "epoch": 0.96, + "learning_rate": 7.042341691229082e-08, + "loss": 0.4409, + "step": 11298 + }, + { + "epoch": 0.96, + "learning_rate": 7.00966297722605e-08, + "loss": 0.4445, + "step": 11299 + }, + { + "epoch": 0.96, + "learning_rate": 6.977059992811619e-08, + "loss": 0.4304, + "step": 11300 + }, + { + "epoch": 0.96, + "learning_rate": 6.944532740472464e-08, + "loss": 0.4406, + "step": 11301 + }, + { + "epoch": 0.96, + "learning_rate": 6.91208122268916e-08, + "loss": 0.461, + "step": 11302 + }, + { + "epoch": 0.96, + "learning_rate": 6.879705441936502e-08, + "loss": 0.4427, + "step": 11303 + }, + { + "epoch": 0.96, + "learning_rate": 6.847405400683626e-08, + "loss": 0.4481, + "step": 11304 + }, + { + "epoch": 0.96, + "learning_rate": 6.815181101393898e-08, + "loss": 0.4703, + "step": 11305 + }, + { + "epoch": 0.96, + "learning_rate": 6.783032546524904e-08, + "loss": 0.4439, + "step": 11306 + }, + { + "epoch": 0.96, + "learning_rate": 6.750959738528462e-08, + "loss": 0.4347, + "step": 11307 + }, + { + "epoch": 0.96, + "learning_rate": 6.718962679850504e-08, + "loss": 0.4556, + "step": 11308 + }, + { + "epoch": 0.96, + "learning_rate": 6.687041372931192e-08, + "loss": 0.4536, + "step": 11309 + }, + { + "epoch": 0.96, + "learning_rate": 6.65519582020513e-08, + "loss": 0.4418, + "step": 11310 + }, + { + "epoch": 0.96, + "learning_rate": 6.623426024100931e-08, + "loss": 0.5019, + "step": 11311 + }, + { + "epoch": 0.96, + "learning_rate": 6.591731987041439e-08, + "loss": 0.4575, + "step": 11312 + }, + { + "epoch": 0.96, + "learning_rate": 6.560113711443938e-08, + "loss": 0.4517, + "step": 11313 + }, + { + "epoch": 0.96, + "learning_rate": 6.528571199719502e-08, + "loss": 0.4495, + "step": 11314 + }, + { + "epoch": 0.96, + "learning_rate": 6.497104454273872e-08, + "loss": 0.4403, + "step": 11315 + }, + { + "epoch": 0.96, + "learning_rate": 6.465713477506907e-08, + "loss": 0.4417, + "step": 11316 + }, + { + "epoch": 0.96, + "learning_rate": 6.43439827181247e-08, + "loss": 0.4425, + "step": 11317 + }, + { + "epoch": 0.97, + "learning_rate": 6.403158839578761e-08, + "loss": 0.4616, + "step": 11318 + }, + { + "epoch": 0.97, + "learning_rate": 6.371995183188429e-08, + "loss": 0.4299, + "step": 11319 + }, + { + "epoch": 0.97, + "learning_rate": 6.340907305017907e-08, + "loss": 0.4372, + "step": 11320 + }, + { + "epoch": 0.97, + "learning_rate": 6.309895207438188e-08, + "loss": 0.4676, + "step": 11321 + }, + { + "epoch": 0.97, + "learning_rate": 6.27895889281438e-08, + "loss": 0.4622, + "step": 11322 + }, + { + "epoch": 0.97, + "learning_rate": 6.248098363505928e-08, + "loss": 0.4506, + "step": 11323 + }, + { + "epoch": 0.97, + "learning_rate": 6.217313621866283e-08, + "loss": 0.4437, + "step": 11324 + }, + { + "epoch": 0.97, + "learning_rate": 6.186604670243124e-08, + "loss": 0.4586, + "step": 11325 + }, + { + "epoch": 0.97, + "learning_rate": 6.155971510978576e-08, + "loss": 0.4371, + "step": 11326 + }, + { + "epoch": 0.97, + "learning_rate": 6.12541414640877e-08, + "loss": 0.4586, + "step": 11327 + }, + { + "epoch": 0.97, + "learning_rate": 6.094932578864288e-08, + "loss": 0.4687, + "step": 11328 + }, + { + "epoch": 0.97, + "learning_rate": 6.064526810669602e-08, + "loss": 0.4497, + "step": 11329 + }, + { + "epoch": 0.97, + "learning_rate": 6.034196844143747e-08, + "loss": 0.4482, + "step": 11330 + }, + { + "epoch": 0.97, + "learning_rate": 6.00394268159965e-08, + "loss": 0.4623, + "step": 11331 + }, + { + "epoch": 0.97, + "learning_rate": 5.973764325344689e-08, + "loss": 0.4709, + "step": 11332 + }, + { + "epoch": 0.97, + "learning_rate": 5.943661777680354e-08, + "loss": 0.4272, + "step": 11333 + }, + { + "epoch": 0.97, + "learning_rate": 5.9136350409024766e-08, + "loss": 0.4487, + "step": 11334 + }, + { + "epoch": 0.97, + "learning_rate": 5.8836841173011136e-08, + "loss": 0.4666, + "step": 11335 + }, + { + "epoch": 0.97, + "learning_rate": 5.8538090091601055e-08, + "loss": 0.444, + "step": 11336 + }, + { + "epoch": 0.97, + "learning_rate": 5.824009718758184e-08, + "loss": 0.4706, + "step": 11337 + }, + { + "epoch": 0.97, + "learning_rate": 5.794286248367753e-08, + "loss": 0.4514, + "step": 11338 + }, + { + "epoch": 0.97, + "learning_rate": 5.7646386002557784e-08, + "loss": 0.4505, + "step": 11339 + }, + { + "epoch": 0.97, + "learning_rate": 5.735066776683229e-08, + "loss": 0.4496, + "step": 11340 + }, + { + "epoch": 0.97, + "learning_rate": 5.705570779905523e-08, + "loss": 0.4572, + "step": 11341 + }, + { + "epoch": 0.97, + "learning_rate": 5.676150612171971e-08, + "loss": 0.487, + "step": 11342 + }, + { + "epoch": 0.97, + "learning_rate": 5.6468062757263356e-08, + "loss": 0.4567, + "step": 11343 + }, + { + "epoch": 0.97, + "learning_rate": 5.617537772806603e-08, + "loss": 0.4512, + "step": 11344 + }, + { + "epoch": 0.97, + "learning_rate": 5.588345105644766e-08, + "loss": 0.4546, + "step": 11345 + }, + { + "epoch": 0.97, + "learning_rate": 5.5592282764673766e-08, + "loss": 0.4449, + "step": 11346 + }, + { + "epoch": 0.97, + "learning_rate": 5.530187287494882e-08, + "loss": 0.4558, + "step": 11347 + }, + { + "epoch": 0.97, + "learning_rate": 5.501222140942064e-08, + "loss": 0.4627, + "step": 11348 + }, + { + "epoch": 0.97, + "learning_rate": 5.472332839017935e-08, + "loss": 0.4498, + "step": 11349 + }, + { + "epoch": 0.97, + "learning_rate": 5.443519383925844e-08, + "loss": 0.4537, + "step": 11350 + }, + { + "epoch": 0.97, + "learning_rate": 5.414781777863032e-08, + "loss": 0.4606, + "step": 11351 + }, + { + "epoch": 0.97, + "learning_rate": 5.386120023021191e-08, + "loss": 0.4359, + "step": 11352 + }, + { + "epoch": 0.97, + "learning_rate": 5.3575341215863496e-08, + "loss": 0.4658, + "step": 11353 + }, + { + "epoch": 0.97, + "learning_rate": 5.3290240757383205e-08, + "loss": 0.4535, + "step": 11354 + }, + { + "epoch": 0.97, + "learning_rate": 5.300589887651586e-08, + "loss": 0.4505, + "step": 11355 + }, + { + "epoch": 0.97, + "learning_rate": 5.272231559494634e-08, + "loss": 0.4474, + "step": 11356 + }, + { + "epoch": 0.97, + "learning_rate": 5.243949093430179e-08, + "loss": 0.4632, + "step": 11357 + }, + { + "epoch": 0.97, + "learning_rate": 5.215742491615161e-08, + "loss": 0.4455, + "step": 11358 + }, + { + "epoch": 0.97, + "learning_rate": 5.187611756200639e-08, + "loss": 0.4412, + "step": 11359 + }, + { + "epoch": 0.97, + "learning_rate": 5.159556889332118e-08, + "loss": 0.4553, + "step": 11360 + }, + { + "epoch": 0.97, + "learning_rate": 5.131577893149109e-08, + "loss": 0.4621, + "step": 11361 + }, + { + "epoch": 0.97, + "learning_rate": 5.103674769785461e-08, + "loss": 0.4581, + "step": 11362 + }, + { + "epoch": 0.97, + "learning_rate": 5.075847521369137e-08, + "loss": 0.4511, + "step": 11363 + }, + { + "epoch": 0.97, + "learning_rate": 5.0480961500223306e-08, + "loss": 0.441, + "step": 11364 + }, + { + "epoch": 0.97, + "learning_rate": 5.020420657861569e-08, + "loss": 0.4531, + "step": 11365 + }, + { + "epoch": 0.97, + "learning_rate": 4.992821046997387e-08, + "loss": 0.488, + "step": 11366 + }, + { + "epoch": 0.97, + "learning_rate": 4.9652973195346566e-08, + "loss": 0.4575, + "step": 11367 + }, + { + "epoch": 0.97, + "learning_rate": 4.937849477572587e-08, + "loss": 0.4494, + "step": 11368 + }, + { + "epoch": 0.97, + "learning_rate": 4.910477523204282e-08, + "loss": 0.4377, + "step": 11369 + }, + { + "epoch": 0.97, + "learning_rate": 4.883181458517405e-08, + "loss": 0.4389, + "step": 11370 + }, + { + "epoch": 0.97, + "learning_rate": 4.8559612855936244e-08, + "loss": 0.4448, + "step": 11371 + }, + { + "epoch": 0.97, + "learning_rate": 4.8288170065088344e-08, + "loss": 0.4432, + "step": 11372 + }, + { + "epoch": 0.97, + "learning_rate": 4.801748623333047e-08, + "loss": 0.4414, + "step": 11373 + }, + { + "epoch": 0.97, + "learning_rate": 4.774756138130831e-08, + "loss": 0.4683, + "step": 11374 + }, + { + "epoch": 0.97, + "learning_rate": 4.7478395529606537e-08, + "loss": 0.4321, + "step": 11375 + }, + { + "epoch": 0.97, + "learning_rate": 4.720998869875315e-08, + "loss": 0.4525, + "step": 11376 + }, + { + "epoch": 0.97, + "learning_rate": 4.694234090921734e-08, + "loss": 0.4621, + "step": 11377 + }, + { + "epoch": 0.97, + "learning_rate": 4.6675452181410566e-08, + "loss": 0.4497, + "step": 11378 + }, + { + "epoch": 0.97, + "learning_rate": 4.640932253568875e-08, + "loss": 0.4468, + "step": 11379 + }, + { + "epoch": 0.97, + "learning_rate": 4.6143951992346783e-08, + "loss": 0.4702, + "step": 11380 + }, + { + "epoch": 0.97, + "learning_rate": 4.587934057162402e-08, + "loss": 0.4394, + "step": 11381 + }, + { + "epoch": 0.97, + "learning_rate": 4.561548829369766e-08, + "loss": 0.4459, + "step": 11382 + }, + { + "epoch": 0.97, + "learning_rate": 4.535239517869494e-08, + "loss": 0.4444, + "step": 11383 + }, + { + "epoch": 0.97, + "learning_rate": 4.5090061246676474e-08, + "loss": 0.468, + "step": 11384 + }, + { + "epoch": 0.97, + "learning_rate": 4.4828486517650705e-08, + "loss": 0.4568, + "step": 11385 + }, + { + "epoch": 0.97, + "learning_rate": 4.4567671011567224e-08, + "loss": 0.4554, + "step": 11386 + }, + { + "epoch": 0.97, + "learning_rate": 4.4307614748313466e-08, + "loss": 0.4414, + "step": 11387 + }, + { + "epoch": 0.97, + "learning_rate": 4.404831774772689e-08, + "loss": 0.4517, + "step": 11388 + }, + { + "epoch": 0.97, + "learning_rate": 4.3789780029579456e-08, + "loss": 0.458, + "step": 11389 + }, + { + "epoch": 0.97, + "learning_rate": 4.353200161358984e-08, + "loss": 0.4534, + "step": 11390 + }, + { + "epoch": 0.97, + "learning_rate": 4.327498251941564e-08, + "loss": 0.4464, + "step": 11391 + }, + { + "epoch": 0.97, + "learning_rate": 4.3018722766661194e-08, + "loss": 0.467, + "step": 11392 + }, + { + "epoch": 0.97, + "learning_rate": 4.276322237486752e-08, + "loss": 0.449, + "step": 11393 + }, + { + "epoch": 0.97, + "learning_rate": 4.250848136352015e-08, + "loss": 0.4514, + "step": 11394 + }, + { + "epoch": 0.97, + "learning_rate": 4.225449975204798e-08, + "loss": 0.4452, + "step": 11395 + }, + { + "epoch": 0.97, + "learning_rate": 4.2001277559818864e-08, + "loss": 0.4699, + "step": 11396 + }, + { + "epoch": 0.97, + "learning_rate": 4.174881480614623e-08, + "loss": 0.4764, + "step": 11397 + }, + { + "epoch": 0.97, + "learning_rate": 4.1497111510283574e-08, + "loss": 0.4519, + "step": 11398 + }, + { + "epoch": 0.97, + "learning_rate": 4.124616769142664e-08, + "loss": 0.4725, + "step": 11399 + }, + { + "epoch": 0.97, + "learning_rate": 4.0995983368713465e-08, + "loss": 0.4514, + "step": 11400 + }, + { + "epoch": 0.97, + "learning_rate": 4.0746558561224336e-08, + "loss": 0.4356, + "step": 11401 + }, + { + "epoch": 0.97, + "learning_rate": 4.0497893287980706e-08, + "loss": 0.4488, + "step": 11402 + }, + { + "epoch": 0.97, + "learning_rate": 4.0249987567948514e-08, + "loss": 0.4629, + "step": 11403 + }, + { + "epoch": 0.97, + "learning_rate": 4.000284142003264e-08, + "loss": 0.4369, + "step": 11404 + }, + { + "epoch": 0.97, + "learning_rate": 3.975645486308133e-08, + "loss": 0.4763, + "step": 11405 + }, + { + "epoch": 0.97, + "learning_rate": 3.951082791588512e-08, + "loss": 0.4791, + "step": 11406 + }, + { + "epoch": 0.97, + "learning_rate": 3.926596059717791e-08, + "loss": 0.4393, + "step": 11407 + }, + { + "epoch": 0.97, + "learning_rate": 3.902185292563365e-08, + "loss": 0.4591, + "step": 11408 + }, + { + "epoch": 0.97, + "learning_rate": 3.877850491986746e-08, + "loss": 0.4368, + "step": 11409 + }, + { + "epoch": 0.97, + "learning_rate": 3.853591659844003e-08, + "loss": 0.4642, + "step": 11410 + }, + { + "epoch": 0.97, + "learning_rate": 3.8294087979852124e-08, + "loss": 0.4469, + "step": 11411 + }, + { + "epoch": 0.97, + "learning_rate": 3.805301908254455e-08, + "loss": 0.4641, + "step": 11412 + }, + { + "epoch": 0.97, + "learning_rate": 3.781270992490482e-08, + "loss": 0.4522, + "step": 11413 + }, + { + "epoch": 0.97, + "learning_rate": 3.757316052525828e-08, + "loss": 0.4226, + "step": 11414 + }, + { + "epoch": 0.97, + "learning_rate": 3.733437090187364e-08, + "loss": 0.4431, + "step": 11415 + }, + { + "epoch": 0.97, + "learning_rate": 3.7096341072964116e-08, + "loss": 0.4488, + "step": 11416 + }, + { + "epoch": 0.97, + "learning_rate": 3.685907105668074e-08, + "loss": 0.4381, + "step": 11417 + }, + { + "epoch": 0.97, + "learning_rate": 3.662256087111904e-08, + "loss": 0.4556, + "step": 11418 + }, + { + "epoch": 0.97, + "learning_rate": 3.638681053431792e-08, + "loss": 0.4551, + "step": 11419 + }, + { + "epoch": 0.97, + "learning_rate": 3.615182006425411e-08, + "loss": 0.4431, + "step": 11420 + }, + { + "epoch": 0.97, + "learning_rate": 3.591758947885105e-08, + "loss": 0.4543, + "step": 11421 + }, + { + "epoch": 0.97, + "learning_rate": 3.568411879597111e-08, + "loss": 0.4599, + "step": 11422 + }, + { + "epoch": 0.97, + "learning_rate": 3.5451408033420064e-08, + "loss": 0.4489, + "step": 11423 + }, + { + "epoch": 0.97, + "learning_rate": 3.521945720894593e-08, + "loss": 0.4438, + "step": 11424 + }, + { + "epoch": 0.97, + "learning_rate": 3.498826634023789e-08, + "loss": 0.4479, + "step": 11425 + }, + { + "epoch": 0.97, + "learning_rate": 3.475783544492628e-08, + "loss": 0.4671, + "step": 11426 + }, + { + "epoch": 0.97, + "learning_rate": 3.452816454058594e-08, + "loss": 0.4335, + "step": 11427 + }, + { + "epoch": 0.97, + "learning_rate": 3.429925364473285e-08, + "loss": 0.4873, + "step": 11428 + }, + { + "epoch": 0.97, + "learning_rate": 3.407110277482417e-08, + "loss": 0.4519, + "step": 11429 + }, + { + "epoch": 0.97, + "learning_rate": 3.3843711948259306e-08, + "loss": 0.4255, + "step": 11430 + }, + { + "epoch": 0.97, + "learning_rate": 3.361708118238105e-08, + "loss": 0.4789, + "step": 11431 + }, + { + "epoch": 0.97, + "learning_rate": 3.339121049447225e-08, + "loss": 0.4506, + "step": 11432 + }, + { + "epoch": 0.97, + "learning_rate": 3.316609990175912e-08, + "loss": 0.4532, + "step": 11433 + }, + { + "epoch": 0.97, + "learning_rate": 3.294174942140904e-08, + "loss": 0.448, + "step": 11434 + }, + { + "epoch": 0.98, + "learning_rate": 3.2718159070532774e-08, + "loss": 0.4515, + "step": 11435 + }, + { + "epoch": 0.98, + "learning_rate": 3.249532886618223e-08, + "loss": 0.4485, + "step": 11436 + }, + { + "epoch": 0.98, + "learning_rate": 3.227325882535048e-08, + "loss": 0.452, + "step": 11437 + }, + { + "epoch": 0.98, + "learning_rate": 3.205194896497399e-08, + "loss": 0.441, + "step": 11438 + }, + { + "epoch": 0.98, + "learning_rate": 3.1831399301931466e-08, + "loss": 0.4686, + "step": 11439 + }, + { + "epoch": 0.98, + "learning_rate": 3.161160985304168e-08, + "loss": 0.4663, + "step": 11440 + }, + { + "epoch": 0.98, + "learning_rate": 3.1392580635067896e-08, + "loss": 0.4492, + "step": 11441 + }, + { + "epoch": 0.98, + "learning_rate": 3.1174311664712297e-08, + "loss": 0.4634, + "step": 11442 + }, + { + "epoch": 0.98, + "learning_rate": 3.09568029586238e-08, + "loss": 0.4366, + "step": 11443 + }, + { + "epoch": 0.98, + "learning_rate": 3.074005453338802e-08, + "loss": 0.4534, + "step": 11444 + }, + { + "epoch": 0.98, + "learning_rate": 3.052406640553618e-08, + "loss": 0.4614, + "step": 11445 + }, + { + "epoch": 0.98, + "learning_rate": 3.030883859154066e-08, + "loss": 0.4393, + "step": 11446 + }, + { + "epoch": 0.98, + "learning_rate": 3.009437110781499e-08, + "loss": 0.4571, + "step": 11447 + }, + { + "epoch": 0.98, + "learning_rate": 2.988066397071609e-08, + "loss": 0.4846, + "step": 11448 + }, + { + "epoch": 0.98, + "learning_rate": 2.9667717196542045e-08, + "loss": 0.4759, + "step": 11449 + }, + { + "epoch": 0.98, + "learning_rate": 2.9455530801532073e-08, + "loss": 0.4343, + "step": 11450 + }, + { + "epoch": 0.98, + "learning_rate": 2.924410480186879e-08, + "loss": 0.4581, + "step": 11451 + }, + { + "epoch": 0.98, + "learning_rate": 2.903343921367707e-08, + "loss": 0.4656, + "step": 11452 + }, + { + "epoch": 0.98, + "learning_rate": 2.882353405302296e-08, + "loss": 0.4307, + "step": 11453 + }, + { + "epoch": 0.98, + "learning_rate": 2.861438933591476e-08, + "loss": 0.4506, + "step": 11454 + }, + { + "epoch": 0.98, + "learning_rate": 2.8406005078301934e-08, + "loss": 0.44, + "step": 11455 + }, + { + "epoch": 0.98, + "learning_rate": 2.8198381296078436e-08, + "loss": 0.4332, + "step": 11456 + }, + { + "epoch": 0.98, + "learning_rate": 2.7991518005076045e-08, + "loss": 0.443, + "step": 11457 + }, + { + "epoch": 0.98, + "learning_rate": 2.7785415221073254e-08, + "loss": 0.4388, + "step": 11458 + }, + { + "epoch": 0.98, + "learning_rate": 2.7580072959787484e-08, + "loss": 0.4453, + "step": 11459 + }, + { + "epoch": 0.98, + "learning_rate": 2.7375491236878438e-08, + "loss": 0.4398, + "step": 11460 + }, + { + "epoch": 0.98, + "learning_rate": 2.7171670067949186e-08, + "loss": 0.4432, + "step": 11461 + }, + { + "epoch": 0.98, + "learning_rate": 2.696860946854396e-08, + "loss": 0.4499, + "step": 11462 + }, + { + "epoch": 0.98, + "learning_rate": 2.6766309454148155e-08, + "loss": 0.4526, + "step": 11463 + }, + { + "epoch": 0.98, + "learning_rate": 2.6564770040190535e-08, + "loss": 0.4434, + "step": 11464 + }, + { + "epoch": 0.98, + "learning_rate": 2.636399124204214e-08, + "loss": 0.4684, + "step": 11465 + }, + { + "epoch": 0.98, + "learning_rate": 2.616397307501295e-08, + "loss": 0.4388, + "step": 11466 + }, + { + "epoch": 0.98, + "learning_rate": 2.5964715554360753e-08, + "loss": 0.4385, + "step": 11467 + }, + { + "epoch": 0.98, + "learning_rate": 2.5766218695277843e-08, + "loss": 0.4614, + "step": 11468 + }, + { + "epoch": 0.98, + "learning_rate": 2.5568482512905445e-08, + "loss": 0.4535, + "step": 11469 + }, + { + "epoch": 0.98, + "learning_rate": 2.5371507022322606e-08, + "loss": 0.4548, + "step": 11470 + }, + { + "epoch": 0.98, + "learning_rate": 2.5175292238550643e-08, + "loss": 0.4366, + "step": 11471 + }, + { + "epoch": 0.98, + "learning_rate": 2.497983817655536e-08, + "loss": 0.46, + "step": 11472 + }, + { + "epoch": 0.98, + "learning_rate": 2.4785144851241506e-08, + "loss": 0.4415, + "step": 11473 + }, + { + "epoch": 0.98, + "learning_rate": 2.45912122774572e-08, + "loss": 0.4594, + "step": 11474 + }, + { + "epoch": 0.98, + "learning_rate": 2.4398040469993943e-08, + "loss": 0.4707, + "step": 11475 + }, + { + "epoch": 0.98, + "learning_rate": 2.420562944358329e-08, + "loss": 0.4245, + "step": 11476 + }, + { + "epoch": 0.98, + "learning_rate": 2.4013979212899054e-08, + "loss": 0.4685, + "step": 11477 + }, + { + "epoch": 0.98, + "learning_rate": 2.3823089792556208e-08, + "loss": 0.4465, + "step": 11478 + }, + { + "epoch": 0.98, + "learning_rate": 2.3632961197115335e-08, + "loss": 0.4637, + "step": 11479 + }, + { + "epoch": 0.98, + "learning_rate": 2.344359344107372e-08, + "loss": 0.4351, + "step": 11480 + }, + { + "epoch": 0.98, + "learning_rate": 2.325498653887426e-08, + "loss": 0.4798, + "step": 11481 + }, + { + "epoch": 0.98, + "learning_rate": 2.3067140504902108e-08, + "loss": 0.4461, + "step": 11482 + }, + { + "epoch": 0.98, + "learning_rate": 2.2880055353482477e-08, + "loss": 0.4584, + "step": 11483 + }, + { + "epoch": 0.98, + "learning_rate": 2.269373109888173e-08, + "loss": 0.4725, + "step": 11484 + }, + { + "epoch": 0.98, + "learning_rate": 2.250816775531295e-08, + "loss": 0.4325, + "step": 11485 + }, + { + "epoch": 0.98, + "learning_rate": 2.2323365336924806e-08, + "loss": 0.4578, + "step": 11486 + }, + { + "epoch": 0.98, + "learning_rate": 2.21393238578127e-08, + "loss": 0.4339, + "step": 11487 + }, + { + "epoch": 0.98, + "learning_rate": 2.1956043332010957e-08, + "loss": 0.4603, + "step": 11488 + }, + { + "epoch": 0.98, + "learning_rate": 2.1773523773499506e-08, + "loss": 0.4561, + "step": 11489 + }, + { + "epoch": 0.98, + "learning_rate": 2.1591765196197213e-08, + "loss": 0.464, + "step": 11490 + }, + { + "epoch": 0.98, + "learning_rate": 2.1410767613965212e-08, + "loss": 0.446, + "step": 11491 + }, + { + "epoch": 0.98, + "learning_rate": 2.1230531040606904e-08, + "loss": 0.4361, + "step": 11492 + }, + { + "epoch": 0.98, + "learning_rate": 2.1051055489869076e-08, + "loss": 0.4447, + "step": 11493 + }, + { + "epoch": 0.98, + "learning_rate": 2.0872340975438555e-08, + "loss": 0.4606, + "step": 11494 + }, + { + "epoch": 0.98, + "learning_rate": 2.0694387510944436e-08, + "loss": 0.4579, + "step": 11495 + }, + { + "epoch": 0.98, + "learning_rate": 2.0517195109959197e-08, + "loss": 0.4596, + "step": 11496 + }, + { + "epoch": 0.98, + "learning_rate": 2.0340763785995366e-08, + "loss": 0.4613, + "step": 11497 + }, + { + "epoch": 0.98, + "learning_rate": 2.016509355250884e-08, + "loss": 0.4544, + "step": 11498 + }, + { + "epoch": 0.98, + "learning_rate": 1.9990184422897797e-08, + "loss": 0.4425, + "step": 11499 + }, + { + "epoch": 0.98, + "learning_rate": 1.981603641049934e-08, + "loss": 0.4645, + "step": 11500 + }, + { + "epoch": 0.98, + "learning_rate": 1.964264952859618e-08, + "loss": 0.4567, + "step": 11501 + }, + { + "epoch": 0.98, + "learning_rate": 1.9470023790411073e-08, + "loss": 0.4512, + "step": 11502 + }, + { + "epoch": 0.98, + "learning_rate": 1.9298159209110157e-08, + "loss": 0.4379, + "step": 11503 + }, + { + "epoch": 0.98, + "learning_rate": 1.9127055797799608e-08, + "loss": 0.4652, + "step": 11504 + }, + { + "epoch": 0.98, + "learning_rate": 1.8956713569527884e-08, + "loss": 0.4532, + "step": 11505 + }, + { + "epoch": 0.98, + "learning_rate": 1.878713253728792e-08, + "loss": 0.47, + "step": 11506 + }, + { + "epoch": 0.98, + "learning_rate": 1.8618312714010488e-08, + "loss": 0.4697, + "step": 11507 + }, + { + "epoch": 0.98, + "learning_rate": 1.8450254112571954e-08, + "loss": 0.4473, + "step": 11508 + }, + { + "epoch": 0.98, + "learning_rate": 1.8282956745789837e-08, + "loss": 0.4569, + "step": 11509 + }, + { + "epoch": 0.98, + "learning_rate": 1.8116420626420605e-08, + "loss": 0.4434, + "step": 11510 + }, + { + "epoch": 0.98, + "learning_rate": 1.795064576716632e-08, + "loss": 0.4273, + "step": 11511 + }, + { + "epoch": 0.98, + "learning_rate": 1.77856321806702e-08, + "loss": 0.4583, + "step": 11512 + }, + { + "epoch": 0.98, + "learning_rate": 1.762137987951551e-08, + "loss": 0.4556, + "step": 11513 + }, + { + "epoch": 0.98, + "learning_rate": 1.745788887623001e-08, + "loss": 0.4628, + "step": 11514 + }, + { + "epoch": 0.98, + "learning_rate": 1.7295159183281507e-08, + "loss": 0.4279, + "step": 11515 + }, + { + "epoch": 0.98, + "learning_rate": 1.713319081308118e-08, + "loss": 0.4825, + "step": 11516 + }, + { + "epoch": 0.98, + "learning_rate": 1.697198377798026e-08, + "loss": 0.455, + "step": 11517 + }, + { + "epoch": 0.98, + "learning_rate": 1.6811538090274472e-08, + "loss": 0.4757, + "step": 11518 + }, + { + "epoch": 0.98, + "learning_rate": 1.6651853762198467e-08, + "loss": 0.4298, + "step": 11519 + }, + { + "epoch": 0.98, + "learning_rate": 1.6492930805932505e-08, + "loss": 0.4409, + "step": 11520 + }, + { + "epoch": 0.98, + "learning_rate": 1.6334769233594673e-08, + "loss": 0.4511, + "step": 11521 + }, + { + "epoch": 0.98, + "learning_rate": 1.6177369057247537e-08, + "loss": 0.4518, + "step": 11522 + }, + { + "epoch": 0.98, + "learning_rate": 1.6020730288897056e-08, + "loss": 0.4378, + "step": 11523 + }, + { + "epoch": 0.98, + "learning_rate": 1.5864852940485896e-08, + "loss": 0.4359, + "step": 11524 + }, + { + "epoch": 0.98, + "learning_rate": 1.570973702390455e-08, + "loss": 0.4657, + "step": 11525 + }, + { + "epoch": 0.98, + "learning_rate": 1.5555382550981325e-08, + "loss": 0.4496, + "step": 11526 + }, + { + "epoch": 0.98, + "learning_rate": 1.540178953348792e-08, + "loss": 0.4538, + "step": 11527 + }, + { + "epoch": 0.98, + "learning_rate": 1.5248957983139412e-08, + "loss": 0.4363, + "step": 11528 + }, + { + "epoch": 0.98, + "learning_rate": 1.5096887911589808e-08, + "loss": 0.4537, + "step": 11529 + }, + { + "epoch": 0.98, + "learning_rate": 1.494557933043761e-08, + "loss": 0.4481, + "step": 11530 + }, + { + "epoch": 0.98, + "learning_rate": 1.4795032251222474e-08, + "loss": 0.4501, + "step": 11531 + }, + { + "epoch": 0.98, + "learning_rate": 1.4645246685424109e-08, + "loss": 0.4691, + "step": 11532 + }, + { + "epoch": 0.98, + "learning_rate": 1.4496222644467816e-08, + "loss": 0.4464, + "step": 11533 + }, + { + "epoch": 0.98, + "learning_rate": 1.4347960139716732e-08, + "loss": 0.4428, + "step": 11534 + }, + { + "epoch": 0.98, + "learning_rate": 1.4200459182479587e-08, + "loss": 0.4629, + "step": 11535 + }, + { + "epoch": 0.98, + "learning_rate": 1.405371978400516e-08, + "loss": 0.4537, + "step": 11536 + }, + { + "epoch": 0.98, + "learning_rate": 1.390774195548339e-08, + "loss": 0.4565, + "step": 11537 + }, + { + "epoch": 0.98, + "learning_rate": 1.3762525708048702e-08, + "loss": 0.4652, + "step": 11538 + }, + { + "epoch": 0.98, + "learning_rate": 1.3618071052774462e-08, + "loss": 0.4787, + "step": 11539 + }, + { + "epoch": 0.98, + "learning_rate": 1.3474378000678523e-08, + "loss": 0.4417, + "step": 11540 + }, + { + "epoch": 0.98, + "learning_rate": 1.3331446562718787e-08, + "loss": 0.4548, + "step": 11541 + }, + { + "epoch": 0.98, + "learning_rate": 1.3189276749795421e-08, + "loss": 0.4518, + "step": 11542 + }, + { + "epoch": 0.98, + "learning_rate": 1.3047868572751976e-08, + "loss": 0.4695, + "step": 11543 + }, + { + "epoch": 0.98, + "learning_rate": 1.2907222042373158e-08, + "loss": 0.4452, + "step": 11544 + }, + { + "epoch": 0.98, + "learning_rate": 1.276733716938372e-08, + "loss": 0.4442, + "step": 11545 + }, + { + "epoch": 0.98, + "learning_rate": 1.2628213964452907e-08, + "loss": 0.4648, + "step": 11546 + }, + { + "epoch": 0.98, + "learning_rate": 1.2489852438190008e-08, + "loss": 0.4426, + "step": 11547 + }, + { + "epoch": 0.98, + "learning_rate": 1.2352252601147696e-08, + "loss": 0.4638, + "step": 11548 + }, + { + "epoch": 0.98, + "learning_rate": 1.2215414463819797e-08, + "loss": 0.4325, + "step": 11549 + }, + { + "epoch": 0.98, + "learning_rate": 1.2079338036642407e-08, + "loss": 0.4557, + "step": 11550 + }, + { + "epoch": 0.98, + "learning_rate": 1.1944023329992782e-08, + "loss": 0.4608, + "step": 11551 + }, + { + "epoch": 0.98, + "learning_rate": 1.1809470354190444e-08, + "loss": 0.464, + "step": 11552 + }, + { + "epoch": 0.99, + "learning_rate": 1.1675679119498295e-08, + "loss": 0.4542, + "step": 11553 + }, + { + "epoch": 0.99, + "learning_rate": 1.1542649636118175e-08, + "loss": 0.4611, + "step": 11554 + }, + { + "epoch": 0.99, + "learning_rate": 1.1410381914196411e-08, + "loss": 0.4467, + "step": 11555 + }, + { + "epoch": 0.99, + "learning_rate": 1.127887596381938e-08, + "loss": 0.493, + "step": 11556 + }, + { + "epoch": 0.99, + "learning_rate": 1.1148131795017946e-08, + "loss": 0.4415, + "step": 11557 + }, + { + "epoch": 0.99, + "learning_rate": 1.1018149417761915e-08, + "loss": 0.4367, + "step": 11558 + }, + { + "epoch": 0.99, + "learning_rate": 1.0888928841963353e-08, + "loss": 0.4371, + "step": 11559 + }, + { + "epoch": 0.99, + "learning_rate": 1.0760470077479934e-08, + "loss": 0.4454, + "step": 11560 + }, + { + "epoch": 0.99, + "learning_rate": 1.0632773134106045e-08, + "loss": 0.462, + "step": 11561 + }, + { + "epoch": 0.99, + "learning_rate": 1.0505838021581671e-08, + "loss": 0.4712, + "step": 11562 + }, + { + "epoch": 0.99, + "learning_rate": 1.0379664749586849e-08, + "loss": 0.454, + "step": 11563 + }, + { + "epoch": 0.99, + "learning_rate": 1.025425332774388e-08, + "loss": 0.4302, + "step": 11564 + }, + { + "epoch": 0.99, + "learning_rate": 1.0129603765617334e-08, + "loss": 0.4546, + "step": 11565 + }, + { + "epoch": 0.99, + "learning_rate": 1.0005716072714055e-08, + "loss": 0.4564, + "step": 11566 + }, + { + "epoch": 0.99, + "learning_rate": 9.882590258482038e-09, + "loss": 0.4533, + "step": 11567 + }, + { + "epoch": 0.99, + "learning_rate": 9.760226332311551e-09, + "loss": 0.4576, + "step": 11568 + }, + { + "epoch": 0.99, + "learning_rate": 9.638624303532907e-09, + "loss": 0.4559, + "step": 11569 + }, + { + "epoch": 0.99, + "learning_rate": 9.517784181422018e-09, + "loss": 0.4399, + "step": 11570 + }, + { + "epoch": 0.99, + "learning_rate": 9.397705975193738e-09, + "loss": 0.4356, + "step": 11571 + }, + { + "epoch": 0.99, + "learning_rate": 9.278389694006296e-09, + "loss": 0.4514, + "step": 11572 + }, + { + "epoch": 0.99, + "learning_rate": 9.15983534695908e-09, + "loss": 0.4741, + "step": 11573 + }, + { + "epoch": 0.99, + "learning_rate": 9.042042943092632e-09, + "loss": 0.4435, + "step": 11574 + }, + { + "epoch": 0.99, + "learning_rate": 8.925012491390882e-09, + "loss": 0.44, + "step": 11575 + }, + { + "epoch": 0.99, + "learning_rate": 8.808744000780022e-09, + "loss": 0.4388, + "step": 11576 + }, + { + "epoch": 0.99, + "learning_rate": 8.693237480126293e-09, + "loss": 0.4401, + "step": 11577 + }, + { + "epoch": 0.99, + "learning_rate": 8.578492938238203e-09, + "loss": 0.4739, + "step": 11578 + }, + { + "epoch": 0.99, + "learning_rate": 8.464510383866531e-09, + "loss": 0.4705, + "step": 11579 + }, + { + "epoch": 0.99, + "learning_rate": 8.351289825705433e-09, + "loss": 0.4578, + "step": 11580 + }, + { + "epoch": 0.99, + "learning_rate": 8.238831272389114e-09, + "loss": 0.4639, + "step": 11581 + }, + { + "epoch": 0.99, + "learning_rate": 8.127134732494047e-09, + "loss": 0.4579, + "step": 11582 + }, + { + "epoch": 0.99, + "learning_rate": 8.016200214537861e-09, + "loss": 0.4433, + "step": 11583 + }, + { + "epoch": 0.99, + "learning_rate": 7.906027726981568e-09, + "loss": 0.4538, + "step": 11584 + }, + { + "epoch": 0.99, + "learning_rate": 7.796617278227336e-09, + "loss": 0.4653, + "step": 11585 + }, + { + "epoch": 0.99, + "learning_rate": 7.6879688766196e-09, + "loss": 0.4401, + "step": 11586 + }, + { + "epoch": 0.99, + "learning_rate": 7.580082530443955e-09, + "loss": 0.4625, + "step": 11587 + }, + { + "epoch": 0.99, + "learning_rate": 7.472958247928264e-09, + "loss": 0.4264, + "step": 11588 + }, + { + "epoch": 0.99, + "learning_rate": 7.3665960372415465e-09, + "loss": 0.4482, + "step": 11589 + }, + { + "epoch": 0.99, + "learning_rate": 7.260995906497314e-09, + "loss": 0.4698, + "step": 11590 + }, + { + "epoch": 0.99, + "learning_rate": 7.156157863746904e-09, + "loss": 0.4539, + "step": 11591 + }, + { + "epoch": 0.99, + "learning_rate": 7.052081916988362e-09, + "loss": 0.4491, + "step": 11592 + }, + { + "epoch": 0.99, + "learning_rate": 6.9487680741553435e-09, + "loss": 0.4394, + "step": 11593 + }, + { + "epoch": 0.99, + "learning_rate": 6.84621634313043e-09, + "loss": 0.4726, + "step": 11594 + }, + { + "epoch": 0.99, + "learning_rate": 6.7444267317329225e-09, + "loss": 0.4347, + "step": 11595 + }, + { + "epoch": 0.99, + "learning_rate": 6.643399247725502e-09, + "loss": 0.4399, + "step": 11596 + }, + { + "epoch": 0.99, + "learning_rate": 6.543133898814225e-09, + "loss": 0.4466, + "step": 11597 + }, + { + "epoch": 0.99, + "learning_rate": 6.4436306926451974e-09, + "loss": 0.451, + "step": 11598 + }, + { + "epoch": 0.99, + "learning_rate": 6.3448896368056845e-09, + "loss": 0.4532, + "step": 11599 + }, + { + "epoch": 0.99, + "learning_rate": 6.246910738827439e-09, + "loss": 0.4451, + "step": 11600 + }, + { + "epoch": 0.99, + "learning_rate": 6.149694006183371e-09, + "loss": 0.4546, + "step": 11601 + }, + { + "epoch": 0.99, + "learning_rate": 6.05323944628533e-09, + "loss": 0.4414, + "step": 11602 + }, + { + "epoch": 0.99, + "learning_rate": 5.957547066491875e-09, + "loss": 0.4581, + "step": 11603 + }, + { + "epoch": 0.99, + "learning_rate": 5.862616874099391e-09, + "loss": 0.4359, + "step": 11604 + }, + { + "epoch": 0.99, + "learning_rate": 5.768448876347643e-09, + "loss": 0.45, + "step": 11605 + }, + { + "epoch": 0.99, + "learning_rate": 5.675043080418663e-09, + "loss": 0.4553, + "step": 11606 + }, + { + "epoch": 0.99, + "learning_rate": 5.582399493436752e-09, + "loss": 0.4635, + "step": 11607 + }, + { + "epoch": 0.99, + "learning_rate": 5.49051812246515e-09, + "loss": 0.4439, + "step": 11608 + }, + { + "epoch": 0.99, + "learning_rate": 5.399398974513803e-09, + "loss": 0.4433, + "step": 11609 + }, + { + "epoch": 0.99, + "learning_rate": 5.309042056529379e-09, + "loss": 0.4442, + "step": 11610 + }, + { + "epoch": 0.99, + "learning_rate": 5.219447375405251e-09, + "loss": 0.4826, + "step": 11611 + }, + { + "epoch": 0.99, + "learning_rate": 5.130614937971512e-09, + "loss": 0.4446, + "step": 11612 + }, + { + "epoch": 0.99, + "learning_rate": 5.042544751006073e-09, + "loss": 0.4689, + "step": 11613 + }, + { + "epoch": 0.99, + "learning_rate": 4.955236821222453e-09, + "loss": 0.4461, + "step": 11614 + }, + { + "epoch": 0.99, + "learning_rate": 4.86869115528088e-09, + "loss": 0.476, + "step": 11615 + }, + { + "epoch": 0.99, + "learning_rate": 4.78290775978163e-09, + "loss": 0.4392, + "step": 11616 + }, + { + "epoch": 0.99, + "learning_rate": 4.697886641266136e-09, + "loss": 0.4493, + "step": 11617 + }, + { + "epoch": 0.99, + "learning_rate": 4.613627806220322e-09, + "loss": 0.4398, + "step": 11618 + }, + { + "epoch": 0.99, + "learning_rate": 4.530131261066828e-09, + "loss": 0.4755, + "step": 11619 + }, + { + "epoch": 0.99, + "learning_rate": 4.447397012177224e-09, + "loss": 0.477, + "step": 11620 + }, + { + "epoch": 0.99, + "learning_rate": 4.3654250658575755e-09, + "loss": 0.4464, + "step": 11621 + }, + { + "epoch": 0.99, + "learning_rate": 4.284215428361771e-09, + "loss": 0.4343, + "step": 11622 + }, + { + "epoch": 0.99, + "learning_rate": 4.203768105882633e-09, + "loss": 0.4555, + "step": 11623 + }, + { + "epoch": 0.99, + "learning_rate": 4.124083104555254e-09, + "loss": 0.4582, + "step": 11624 + }, + { + "epoch": 0.99, + "learning_rate": 4.045160430456996e-09, + "loss": 0.4418, + "step": 11625 + }, + { + "epoch": 0.99, + "learning_rate": 3.9670000896074865e-09, + "loss": 0.4666, + "step": 11626 + }, + { + "epoch": 0.99, + "learning_rate": 3.889602087965294e-09, + "loss": 0.4556, + "step": 11627 + }, + { + "epoch": 0.99, + "learning_rate": 3.812966431435694e-09, + "loss": 0.4434, + "step": 11628 + }, + { + "epoch": 0.99, + "learning_rate": 3.73709312586068e-09, + "loss": 0.4644, + "step": 11629 + }, + { + "epoch": 0.99, + "learning_rate": 3.6619821770289554e-09, + "loss": 0.4443, + "step": 11630 + }, + { + "epoch": 0.99, + "learning_rate": 3.58763359066816e-09, + "loss": 0.4694, + "step": 11631 + }, + { + "epoch": 0.99, + "learning_rate": 3.514047372448204e-09, + "loss": 0.4286, + "step": 11632 + }, + { + "epoch": 0.99, + "learning_rate": 3.441223527980153e-09, + "loss": 0.4465, + "step": 11633 + }, + { + "epoch": 0.99, + "learning_rate": 3.3691620628195643e-09, + "loss": 0.4393, + "step": 11634 + }, + { + "epoch": 0.99, + "learning_rate": 3.297862982460931e-09, + "loss": 0.4381, + "step": 11635 + }, + { + "epoch": 0.99, + "learning_rate": 3.2273262923432357e-09, + "loss": 0.4644, + "step": 11636 + }, + { + "epoch": 0.99, + "learning_rate": 3.157551997844399e-09, + "loss": 0.4604, + "step": 11637 + }, + { + "epoch": 0.99, + "learning_rate": 3.0885401042857197e-09, + "loss": 0.4753, + "step": 11638 + }, + { + "epoch": 0.99, + "learning_rate": 3.0202906169307654e-09, + "loss": 0.4458, + "step": 11639 + }, + { + "epoch": 0.99, + "learning_rate": 2.9528035409853715e-09, + "loss": 0.4519, + "step": 11640 + }, + { + "epoch": 0.99, + "learning_rate": 2.886078881595422e-09, + "loss": 0.4505, + "step": 11641 + }, + { + "epoch": 0.99, + "learning_rate": 2.820116643849069e-09, + "loss": 0.4583, + "step": 11642 + }, + { + "epoch": 0.99, + "learning_rate": 2.754916832777843e-09, + "loss": 0.4366, + "step": 11643 + }, + { + "epoch": 0.99, + "learning_rate": 2.690479453354433e-09, + "loss": 0.4553, + "step": 11644 + }, + { + "epoch": 0.99, + "learning_rate": 2.6268045104926867e-09, + "loss": 0.4566, + "step": 11645 + }, + { + "epoch": 0.99, + "learning_rate": 2.5638920090476082e-09, + "loss": 0.4567, + "step": 11646 + }, + { + "epoch": 0.99, + "learning_rate": 2.501741953818693e-09, + "loss": 0.44, + "step": 11647 + }, + { + "epoch": 0.99, + "learning_rate": 2.440354349545482e-09, + "loss": 0.4438, + "step": 11648 + }, + { + "epoch": 0.99, + "learning_rate": 2.379729200908676e-09, + "loss": 0.4527, + "step": 11649 + }, + { + "epoch": 0.99, + "learning_rate": 2.319866512533464e-09, + "loss": 0.4653, + "step": 11650 + }, + { + "epoch": 0.99, + "learning_rate": 2.2607662889839733e-09, + "loss": 0.4687, + "step": 11651 + }, + { + "epoch": 0.99, + "learning_rate": 2.2024285347677087e-09, + "loss": 0.4547, + "step": 11652 + }, + { + "epoch": 0.99, + "learning_rate": 2.1448532543333344e-09, + "loss": 0.4516, + "step": 11653 + }, + { + "epoch": 0.99, + "learning_rate": 2.0880404520728926e-09, + "loss": 0.438, + "step": 11654 + }, + { + "epoch": 0.99, + "learning_rate": 2.031990132318473e-09, + "loss": 0.4563, + "step": 11655 + }, + { + "epoch": 0.99, + "learning_rate": 1.9767022993444353e-09, + "loss": 0.4392, + "step": 11656 + }, + { + "epoch": 0.99, + "learning_rate": 1.9221769573674052e-09, + "loss": 0.4443, + "step": 11657 + }, + { + "epoch": 0.99, + "learning_rate": 1.8684141105462792e-09, + "loss": 0.4505, + "step": 11658 + }, + { + "epoch": 0.99, + "learning_rate": 1.8154137629811108e-09, + "loss": 0.4485, + "step": 11659 + }, + { + "epoch": 0.99, + "learning_rate": 1.7631759187131114e-09, + "loss": 0.4457, + "step": 11660 + }, + { + "epoch": 0.99, + "learning_rate": 1.7117005817268718e-09, + "loss": 0.4553, + "step": 11661 + }, + { + "epoch": 0.99, + "learning_rate": 1.6609877559481402e-09, + "loss": 0.4558, + "step": 11662 + }, + { + "epoch": 0.99, + "learning_rate": 1.6110374452438238e-09, + "loss": 0.4636, + "step": 11663 + }, + { + "epoch": 0.99, + "learning_rate": 1.5618496534242079e-09, + "loss": 0.4553, + "step": 11664 + }, + { + "epoch": 0.99, + "learning_rate": 1.5134243842396257e-09, + "loss": 0.4525, + "step": 11665 + }, + { + "epoch": 0.99, + "learning_rate": 1.4657616413837894e-09, + "loss": 0.4532, + "step": 11666 + }, + { + "epoch": 0.99, + "learning_rate": 1.4188614284926794e-09, + "loss": 0.4655, + "step": 11667 + }, + { + "epoch": 0.99, + "learning_rate": 1.3727237491412138e-09, + "loss": 0.4546, + "step": 11668 + }, + { + "epoch": 0.99, + "learning_rate": 1.3273486068487996e-09, + "loss": 0.4393, + "step": 11669 + }, + { + "epoch": 1.0, + "learning_rate": 1.282736005076002e-09, + "loss": 0.4357, + "step": 11670 + }, + { + "epoch": 1.0, + "learning_rate": 1.2388859472256542e-09, + "loss": 0.4524, + "step": 11671 + }, + { + "epoch": 1.0, + "learning_rate": 1.1957984366406384e-09, + "loss": 0.4656, + "step": 11672 + }, + { + "epoch": 1.0, + "learning_rate": 1.1534734766083245e-09, + "loss": 0.4608, + "step": 11673 + }, + { + "epoch": 1.0, + "learning_rate": 1.111911070356131e-09, + "loss": 0.4582, + "step": 11674 + }, + { + "epoch": 1.0, + "learning_rate": 1.0711112210526342e-09, + "loss": 0.4546, + "step": 11675 + }, + { + "epoch": 1.0, + "learning_rate": 1.03107393181201e-09, + "loss": 0.4452, + "step": 11676 + }, + { + "epoch": 1.0, + "learning_rate": 9.917992056851511e-10, + "loss": 0.4634, + "step": 11677 + }, + { + "epoch": 1.0, + "learning_rate": 9.532870456685494e-10, + "loss": 0.4379, + "step": 11678 + }, + { + "epoch": 1.0, + "learning_rate": 9.15537454698745e-10, + "loss": 0.4631, + "step": 11679 + }, + { + "epoch": 1.0, + "learning_rate": 8.785504356556562e-10, + "loss": 0.4501, + "step": 11680 + }, + { + "epoch": 1.0, + "learning_rate": 8.423259913592496e-10, + "loss": 0.4584, + "step": 11681 + }, + { + "epoch": 1.0, + "learning_rate": 8.068641245717601e-10, + "loss": 0.4568, + "step": 11682 + }, + { + "epoch": 1.0, + "learning_rate": 7.721648379988011e-10, + "loss": 0.4362, + "step": 11683 + }, + { + "epoch": 1.0, + "learning_rate": 7.38228134284924e-10, + "loss": 0.4551, + "step": 11684 + }, + { + "epoch": 1.0, + "learning_rate": 7.050540160202791e-10, + "loss": 0.4358, + "step": 11685 + }, + { + "epoch": 1.0, + "learning_rate": 6.726424857339542e-10, + "loss": 0.4388, + "step": 11686 + }, + { + "epoch": 1.0, + "learning_rate": 6.409935458984162e-10, + "loss": 0.4521, + "step": 11687 + }, + { + "epoch": 1.0, + "learning_rate": 6.101071989261798e-10, + "loss": 0.4582, + "step": 11688 + }, + { + "epoch": 1.0, + "learning_rate": 5.79983447173138e-10, + "loss": 0.4294, + "step": 11689 + }, + { + "epoch": 1.0, + "learning_rate": 5.506222929374527e-10, + "loss": 0.4372, + "step": 11690 + }, + { + "epoch": 1.0, + "learning_rate": 5.220237384573334e-10, + "loss": 0.4632, + "step": 11691 + }, + { + "epoch": 1.0, + "learning_rate": 4.941877859143684e-10, + "loss": 0.4312, + "step": 11692 + }, + { + "epoch": 1.0, + "learning_rate": 4.671144374313041e-10, + "loss": 0.4253, + "step": 11693 + }, + { + "epoch": 1.0, + "learning_rate": 4.408036950731553e-10, + "loss": 0.455, + "step": 11694 + }, + { + "epoch": 1.0, + "learning_rate": 4.1525556084609507e-10, + "loss": 0.4803, + "step": 11695 + }, + { + "epoch": 1.0, + "learning_rate": 3.9047003669856477e-10, + "loss": 0.434, + "step": 11696 + }, + { + "epoch": 1.0, + "learning_rate": 3.6644712452127416e-10, + "loss": 0.4729, + "step": 11697 + }, + { + "epoch": 1.0, + "learning_rate": 3.4318682614498113e-10, + "loss": 0.4624, + "step": 11698 + }, + { + "epoch": 1.0, + "learning_rate": 3.206891433449322e-10, + "loss": 0.4577, + "step": 11699 + }, + { + "epoch": 1.0, + "learning_rate": 2.9895407783753214e-10, + "loss": 0.4491, + "step": 11700 + } + ], + "logging_steps": 1.0, + "max_steps": 11728, + "num_input_tokens_seen": 0, + "num_train_epochs": 1, + "save_steps": 100, + "total_flos": 0.0, + "train_batch_size": 16, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-11700/vision_tower/config.json b/checkpoint-11700/vision_tower/config.json new file mode 100644 index 0000000000000000000000000000000000000000..93337010fef23bbc1873aa07afab159f97b16bfd --- /dev/null +++ b/checkpoint-11700/vision_tower/config.json @@ -0,0 +1,19 @@ +{ + "_name_or_path": "/lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-11700/vision_tower", + "architectures": [ + "SiglipVisionModel" + ], + "attention_dropout": 0.0, + "hidden_act": "gelu_pytorch_tanh", + "hidden_size": 1152, + "image_size": 384, + "intermediate_size": 4304, + "layer_norm_eps": 1e-06, + "model_type": "siglip_vision_model", + "num_attention_heads": 16, + "num_channels": 3, + "num_hidden_layers": 27, + "patch_size": 14, + "torch_dtype": "bfloat16", + "transformers_version": "4.36.2" +} diff --git a/checkpoint-11700/vision_tower/model.safetensors b/checkpoint-11700/vision_tower/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..33888897d4c3331b842c0a91c1b01b1db74b9564 --- /dev/null +++ b/checkpoint-11700/vision_tower/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e876aa90ed51e8061cf67dd87c1e64177ca7e484de3c2dae15a09465a695154c +size 856506120 diff --git a/checkpoint-11700/vision_tower/preprocessor_config.json b/checkpoint-11700/vision_tower/preprocessor_config.json new file mode 100644 index 0000000000000000000000000000000000000000..0f13134ed29056f82f3ab7e0246f0ab973e7ecf3 --- /dev/null +++ b/checkpoint-11700/vision_tower/preprocessor_config.json @@ -0,0 +1,24 @@ +{ + "do_convert_rgb": true, + "do_normalize": true, + "do_rescale": true, + "do_resize": true, + "image_mean": [ + 0.5, + 0.5, + 0.5 + ], + "image_processor_type": "SiglipImageProcessor", + "image_std": [ + 0.5, + 0.5, + 0.5 + ], + "processor_class": "SiglipProcessor", + "resample": 3, + "rescale_factor": 0.00392156862745098, + "size": { + "height": 384, + "width": 384 + } +} diff --git a/checkpoint-11700/zero_to_fp32.py b/checkpoint-11700/zero_to_fp32.py new file mode 100644 index 0000000000000000000000000000000000000000..c5246ff52274e1d6142001ccf085186d3545ce57 --- /dev/null +++ b/checkpoint-11700/zero_to_fp32.py @@ -0,0 +1,578 @@ +#!/usr/bin/env python + +# Copyright (c) Microsoft Corporation. +# SPDX-License-Identifier: Apache-2.0 + +# DeepSpeed Team + +# This script extracts fp32 consolidated weights from a zero 2 and 3 DeepSpeed checkpoints. It gets +# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in +# the future. Once extracted, the weights don't require DeepSpeed and can be used in any +# application. +# +# example: python zero_to_fp32.py . pytorch_model.bin + +import argparse +import torch +import glob +import math +import os +import re +from collections import OrderedDict +from dataclasses import dataclass + +# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with +# DeepSpeed data structures it has to be available in the current python environment. +from deepspeed.utils import logger +from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS, + FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES, + FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS) + + +@dataclass +class zero_model_state: + buffers: dict() + param_shapes: dict() + shared_params: list + ds_version: int + frozen_param_shapes: dict() + frozen_param_fragments: dict() + + +debug = 0 + +# load to cpu +device = torch.device('cpu') + + +def atoi(text): + return int(text) if text.isdigit() else text + + +def natural_keys(text): + ''' + alist.sort(key=natural_keys) sorts in human order + http://nedbatchelder.com/blog/200712/human_sorting.html + (See Toothy's implementation in the comments) + ''' + return [atoi(c) for c in re.split(r'(\d+)', text)] + + +def get_model_state_file(checkpoint_dir, zero_stage): + if not os.path.isdir(checkpoint_dir): + raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist") + + # there should be only one file + if zero_stage == 2: + file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt") + elif zero_stage == 3: + file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt") + + if not os.path.exists(file): + raise FileNotFoundError(f"can't find model states file at '{file}'") + + return file + + +def get_checkpoint_files(checkpoint_dir, glob_pattern): + # XXX: need to test that this simple glob rule works for multi-node setup too + ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys) + + if len(ckpt_files) == 0: + raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'") + + return ckpt_files + + +def get_optim_files(checkpoint_dir): + return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt") + + +def get_model_state_files(checkpoint_dir): + return get_checkpoint_files(checkpoint_dir, "*_model_states.pt") + + +def parse_model_states(files): + zero_model_states = [] + for file in files: + state_dict = torch.load(file, map_location=device) + + if BUFFER_NAMES not in state_dict: + raise ValueError(f"{file} is not a model state checkpoint") + buffer_names = state_dict[BUFFER_NAMES] + if debug: + print("Found buffers:", buffer_names) + + # recover just the buffers while restoring them to fp32 if they were saved in fp16 + buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names} + param_shapes = state_dict[PARAM_SHAPES] + + # collect parameters that are included in param_shapes + param_names = [] + for s in param_shapes: + for name in s.keys(): + param_names.append(name) + + # update with frozen parameters + frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None) + if frozen_param_shapes is not None: + if debug: + print(f"Found frozen_param_shapes: {frozen_param_shapes}") + param_names += list(frozen_param_shapes.keys()) + + # handle shared params + shared_params = [[k, v] for k, v in state_dict["shared_params"].items()] + + ds_version = state_dict.get(DS_VERSION, None) + + frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None) + + z_model_state = zero_model_state(buffers=buffers, + param_shapes=param_shapes, + shared_params=shared_params, + ds_version=ds_version, + frozen_param_shapes=frozen_param_shapes, + frozen_param_fragments=frozen_param_fragments) + zero_model_states.append(z_model_state) + + return zero_model_states + + +def parse_optim_states(files, ds_checkpoint_dir): + + total_files = len(files) + state_dicts = [] + for f in files: + state_dicts.append(torch.load(f, map_location=device)) + + if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]: + raise ValueError(f"{files[0]} is not a zero checkpoint") + zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE] + world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT] + + # For ZeRO-2 each param group can have different partition_count as data parallelism for expert + # parameters can be different from data parallelism for non-expert parameters. So we can just + # use the max of the partition_count to get the dp world_size. + + if type(world_size) is list: + world_size = max(world_size) + + if world_size != total_files: + raise ValueError( + f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. " + "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes." + ) + + # the groups are named differently in each stage + if zero_stage == 2: + fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS + elif zero_stage == 3: + fp32_groups_key = FP32_FLAT_GROUPS + else: + raise ValueError(f"unknown zero stage {zero_stage}") + + if zero_stage == 2: + fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))] + elif zero_stage == 3: + # if there is more than one param group, there will be multiple flattened tensors - one + # flattened tensor per group - for simplicity merge them into a single tensor + # + # XXX: could make the script more memory efficient for when there are multiple groups - it + # will require matching the sub-lists of param_shapes for each param group flattened tensor + + fp32_flat_groups = [ + torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts)) + ] + + return zero_stage, world_size, fp32_flat_groups + + +def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir): + """ + Returns fp32 state_dict reconstructed from ds checkpoint + + Args: + - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are) + + """ + print(f"Processing zero checkpoint '{ds_checkpoint_dir}'") + + optim_files = get_optim_files(ds_checkpoint_dir) + zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir) + print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}") + + model_files = get_model_state_files(ds_checkpoint_dir) + + zero_model_states = parse_model_states(model_files) + print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}') + + if zero_stage == 2: + return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states) + elif zero_stage == 3: + return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states) + + +def _zero2_merge_frozen_params(state_dict, zero_model_states): + if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0: + return + + frozen_param_shapes = zero_model_states[0].frozen_param_shapes + frozen_param_fragments = zero_model_states[0].frozen_param_fragments + + if debug: + num_elem = sum(s.numel() for s in frozen_param_shapes.values()) + print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}') + + wanted_params = len(frozen_param_shapes) + wanted_numel = sum(s.numel() for s in frozen_param_shapes.values()) + avail_numel = sum([p.numel() for p in frozen_param_fragments.values()]) + print(f'Frozen params: Have {avail_numel} numels to process.') + print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params') + + total_params = 0 + total_numel = 0 + for name, shape in frozen_param_shapes.items(): + total_params += 1 + unpartitioned_numel = shape.numel() + total_numel += unpartitioned_numel + + state_dict[name] = frozen_param_fragments[name] + + if debug: + print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ") + + print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements") + + +def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states): + param_shapes = zero_model_states[0].param_shapes + + # Reconstruction protocol: + # + # XXX: document this + + if debug: + for i in range(world_size): + for j in range(len(fp32_flat_groups[0])): + print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}") + + # XXX: memory usage doubles here (zero2) + num_param_groups = len(fp32_flat_groups[0]) + merged_single_partition_of_fp32_groups = [] + for i in range(num_param_groups): + merged_partitions = [sd[i] for sd in fp32_flat_groups] + full_single_fp32_vector = torch.cat(merged_partitions, 0) + merged_single_partition_of_fp32_groups.append(full_single_fp32_vector) + avail_numel = sum( + [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups]) + + if debug: + wanted_params = sum([len(shapes) for shapes in param_shapes]) + wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes]) + # not asserting if there is a mismatch due to possible padding + print(f"Have {avail_numel} numels to process.") + print(f"Need {wanted_numel} numels in {wanted_params} params.") + + # params + # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support + # out-of-core computing solution + total_numel = 0 + total_params = 0 + for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups): + offset = 0 + avail_numel = full_single_fp32_vector.numel() + for name, shape in shapes.items(): + + unpartitioned_numel = shape.numel() + total_numel += unpartitioned_numel + total_params += 1 + + if debug: + print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ") + state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape) + offset += unpartitioned_numel + + # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and + # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex + # paddings performed in the code it's almost impossible to predict the exact numbers w/o the + # live optimizer object, so we are checking that the numbers are within the right range + align_to = 2 * world_size + + def zero2_align(x): + return align_to * math.ceil(x / align_to) + + if debug: + print(f"original offset={offset}, avail_numel={avail_numel}") + + offset = zero2_align(offset) + avail_numel = zero2_align(avail_numel) + + if debug: + print(f"aligned offset={offset}, avail_numel={avail_numel}") + + # Sanity check + if offset != avail_numel: + raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong") + + print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements") + + +def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states): + state_dict = OrderedDict() + + # buffers + buffers = zero_model_states[0].buffers + state_dict.update(buffers) + if debug: + print(f"added {len(buffers)} buffers") + + _zero2_merge_frozen_params(state_dict, zero_model_states) + + _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states) + + # recover shared parameters + for pair in zero_model_states[0].shared_params: + if pair[1] in state_dict: + state_dict[pair[0]] = state_dict[pair[1]] + + return state_dict + + +def zero3_partitioned_param_info(unpartitioned_numel, world_size): + remainder = unpartitioned_numel % world_size + padding_numel = (world_size - remainder) if remainder else 0 + partitioned_numel = math.ceil(unpartitioned_numel / world_size) + return partitioned_numel, padding_numel + + +def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states): + if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0: + return + + if debug: + for i in range(world_size): + num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values()) + print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}') + + frozen_param_shapes = zero_model_states[0].frozen_param_shapes + wanted_params = len(frozen_param_shapes) + wanted_numel = sum(s.numel() for s in frozen_param_shapes.values()) + avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size + print(f'Frozen params: Have {avail_numel} numels to process.') + print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params') + + total_params = 0 + total_numel = 0 + for name, shape in zero_model_states[0].frozen_param_shapes.items(): + total_params += 1 + unpartitioned_numel = shape.numel() + total_numel += unpartitioned_numel + + param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states) + state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape) + + partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size) + + if debug: + print( + f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}" + ) + + print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements") + + +def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states): + param_shapes = zero_model_states[0].param_shapes + avail_numel = fp32_flat_groups[0].numel() * world_size + # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each + # param, re-consolidating each param, while dealing with padding if any + + # merge list of dicts, preserving order + param_shapes = {k: v for d in param_shapes for k, v in d.items()} + + if debug: + for i in range(world_size): + print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}") + + wanted_params = len(param_shapes) + wanted_numel = sum(shape.numel() for shape in param_shapes.values()) + # not asserting if there is a mismatch due to possible padding + avail_numel = fp32_flat_groups[0].numel() * world_size + print(f"Trainable params: Have {avail_numel} numels to process.") + print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.") + + # params + # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support + # out-of-core computing solution + offset = 0 + total_numel = 0 + total_params = 0 + for name, shape in param_shapes.items(): + + unpartitioned_numel = shape.numel() + total_numel += unpartitioned_numel + total_params += 1 + + partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size) + + if debug: + print( + f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}" + ) + + # XXX: memory usage doubles here + state_dict[name] = torch.cat( + tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)), + 0).narrow(0, 0, unpartitioned_numel).view(shape) + offset += partitioned_numel + + offset *= world_size + + # Sanity check + if offset != avail_numel: + raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong") + + print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements") + + +def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states): + state_dict = OrderedDict() + + # buffers + buffers = zero_model_states[0].buffers + state_dict.update(buffers) + if debug: + print(f"added {len(buffers)} buffers") + + _zero3_merge_frozen_params(state_dict, world_size, zero_model_states) + + _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states) + + # recover shared parameters + for pair in zero_model_states[0].shared_params: + if pair[1] in state_dict: + state_dict[pair[0]] = state_dict[pair[1]] + + return state_dict + + +def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None): + """ + Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with + ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example + via a model hub. + + Args: + - ``checkpoint_dir``: path to the desired checkpoint folder + - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14`` + + Returns: + - pytorch ``state_dict`` + + Note: this approach may not work if your application doesn't have sufficient free CPU memory and + you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with + the checkpoint. + + A typical usage might be :: + + from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint + # do the training and checkpoint saving + state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu + model = model.cpu() # move to cpu + model.load_state_dict(state_dict) + # submit to model hub or save the model to share with others + + In this example the ``model`` will no longer be usable in the deepspeed context of the same + application. i.e. you will need to re-initialize the deepspeed engine, since + ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it. + + If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead. + + """ + if tag is None: + latest_path = os.path.join(checkpoint_dir, 'latest') + if os.path.isfile(latest_path): + with open(latest_path, 'r') as fd: + tag = fd.read().strip() + else: + raise ValueError(f"Unable to find 'latest' file at {latest_path}") + + ds_checkpoint_dir = os.path.join(checkpoint_dir, tag) + + if not os.path.isdir(ds_checkpoint_dir): + raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist") + + return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir) + + +def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None): + """ + Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be + loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed. + + Args: + - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``) + - ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin) + - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14`` + """ + + state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag) + print(f"Saving fp32 state dict to {output_file}") + torch.save(state_dict, output_file) + + +def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None): + """ + 1. Put the provided model to cpu + 2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` + 3. Load it into the provided model + + Args: + - ``model``: the model object to update + - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``) + - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14`` + + Returns: + - ``model`: modified model + + Make sure you have plenty of CPU memory available before you call this function. If you don't + have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it + conveniently placed for you in the checkpoint folder. + + A typical usage might be :: + + from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint + model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir) + # submit to model hub or save the model to share with others + + Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context + of the same application. i.e. you will need to re-initialize the deepspeed engine, since + ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it. + + """ + logger.info(f"Extracting fp32 weights") + state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag) + + logger.info(f"Overwriting model with fp32 weights") + model = model.cpu() + model.load_state_dict(state_dict, strict=False) + + return model + + +if __name__ == "__main__": + + parser = argparse.ArgumentParser() + parser.add_argument("checkpoint_dir", + type=str, + help="path to the desired checkpoint folder, e.g., path/checkpoint-12") + parser.add_argument( + "output_file", + type=str, + help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)") + parser.add_argument("-d", "--debug", action='store_true', help="enable debug") + args = parser.parse_args() + + debug = args.debug + + convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir, args.output_file) diff --git a/config.json b/config.json new file mode 100644 index 0000000000000000000000000000000000000000..9dadd95d54b5c8f938afebef5421299800c0dc19 --- /dev/null +++ b/config.json @@ -0,0 +1,253 @@ +{ + "_name_or_path": "/lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast", + "architectures": [ + "LlavaLlamaModel" + ], + "drop_path_rate": 0.0, + "hidden_size": 2560, + "image_aspect_ratio": "resize", + "interpolate_mode": "linear", + "llm_cfg": { + "_name_or_path": "/lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/llm", + "add_cross_attention": false, + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bad_words_ids": null, + "begin_suppress_tokens": null, + "bos_token_id": 1, + "chunk_size_feed_forward": 0, + "cross_attention_hidden_size": null, + "decoder_start_token_id": null, + "diversity_penalty": 0.0, + "do_sample": false, + "early_stopping": false, + "encoder_no_repeat_ngram_size": 0, + "eos_token_id": 2, + "exponential_decay_length_penalty": null, + "finetuning_task": null, + "forced_bos_token_id": null, + "forced_eos_token_id": null, + "hidden_act": "silu", + "hidden_size": 2560, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "initializer_range": 0.02, + "intermediate_size": 6912, + "is_decoder": false, + "is_encoder_decoder": false, + "label2id": { + "LABEL_0": 0, + "LABEL_1": 1 + }, + "length_penalty": 1.0, + "max_length": 20, + "max_position_embeddings": 4096, + "min_length": 0, + "model_max_length": 4096, + "model_type": "llama", + "no_repeat_ngram_size": 0, + "num_attention_heads": 20, + "num_beam_groups": 1, + "num_beams": 1, + "num_hidden_layers": 32, + "num_key_value_heads": 20, + "num_return_sequences": 1, + "output_attentions": false, + "output_hidden_states": false, + "output_scores": false, + "pad_token_id": 0, + "prefix": null, + "pretraining_tp": 1, + "problem_type": null, + "pruned_heads": {}, + "remove_invalid_values": false, + "repetition_penalty": 1.0, + "return_dict": true, + "return_dict_in_generate": false, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 10000.0, + "sep_token_id": null, + "suppress_tokens": null, + "task_specific_params": null, + "temperature": 1.0, + "tf_legacy_loss": false, + "tie_encoder_decoder": false, + "tie_word_embeddings": false, + "tokenizer_class": null, + "tokenizer_model_max_length": 4096, + "tokenizer_padding_side": "right", + "top_k": 50, + "top_p": 1.0, + "torch_dtype": "bfloat16", + "torchscript": false, + "typical_p": 1.0, + "use_bfloat16": false, + "use_cache": true, + "vocab_size": 32000 + }, + "mm_hidden_size": 1152, + "mm_projector_cfg": { + "_name_or_path": "/lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/mm_projector", + "add_cross_attention": false, + "architectures": [ + "MultimodalProjector" + ], + "bad_words_ids": null, + "begin_suppress_tokens": null, + "bos_token_id": null, + "chunk_size_feed_forward": 0, + "cross_attention_hidden_size": null, + "decoder_start_token_id": null, + "diversity_penalty": 0.0, + "do_sample": false, + "early_stopping": false, + "encoder_no_repeat_ngram_size": 0, + "eos_token_id": null, + "exponential_decay_length_penalty": null, + "finetuning_task": null, + "forced_bos_token_id": null, + "forced_eos_token_id": null, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "is_decoder": false, + "is_encoder_decoder": false, + "label2id": { + "LABEL_0": 0, + "LABEL_1": 1 + }, + "length_penalty": 1.0, + "max_length": 20, + "min_length": 0, + "mm_projector_type": "mlp_downsample", + "model_type": "v2l_projector", + "no_repeat_ngram_size": 0, + "num_beam_groups": 1, + "num_beams": 1, + "num_return_sequences": 1, + "output_attentions": false, + "output_hidden_states": false, + "output_scores": false, + "pad_token_id": null, + "prefix": null, + "problem_type": null, + "pruned_heads": {}, + "remove_invalid_values": false, + "repetition_penalty": 1.0, + "return_dict": true, + "return_dict_in_generate": false, + "sep_token_id": null, + "suppress_tokens": null, + "task_specific_params": null, + "temperature": 1.0, + "tf_legacy_loss": false, + "tie_encoder_decoder": false, + "tie_word_embeddings": true, + "tokenizer_class": null, + "top_k": 50, + "top_p": 1.0, + "torch_dtype": "bfloat16", + "torchscript": false, + "typical_p": 1.0, + "use_bfloat16": false + }, + "mm_projector_lr": null, + "mm_use_im_patch_token": false, + "mm_use_im_start_end": false, + "mm_vision_select_feature": "cls_patch", + "mm_vision_select_layer": -2, + "model_dtype": "torch.bfloat16", + "model_type": "llava_llama", + "num_video_frames": 8, + "resume_path": "/lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast", + "s2": false, + "s2_max_split_size": 336, + "s2_scales": "336,672,1008", + "transformers_version": "4.36.2", + "tune_language_model": true, + "tune_mm_projector": true, + "tune_vision_tower": true, + "vision_resolution": -1, + "vision_tower_cfg": { + "_name_or_path": "/lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/vision_tower", + "add_cross_attention": false, + "architectures": [ + "SiglipVisionModel" + ], + "attention_dropout": 0.0, + "bad_words_ids": null, + "begin_suppress_tokens": null, + "bos_token_id": null, + "chunk_size_feed_forward": 0, + "cross_attention_hidden_size": null, + "decoder_start_token_id": null, + "diversity_penalty": 0.0, + "do_sample": false, + "early_stopping": false, + "encoder_no_repeat_ngram_size": 0, + "eos_token_id": null, + "exponential_decay_length_penalty": null, + "finetuning_task": null, + "forced_bos_token_id": null, + "forced_eos_token_id": null, + "hidden_act": "gelu_pytorch_tanh", + "hidden_size": 1152, + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "image_size": 384, + "intermediate_size": 4304, + "is_decoder": false, + "is_encoder_decoder": false, + "label2id": { + "LABEL_0": 0, + "LABEL_1": 1 + }, + "layer_norm_eps": 1e-06, + "length_penalty": 1.0, + "max_length": 20, + "min_length": 0, + "model_type": "siglip_vision_model", + "no_repeat_ngram_size": 0, + "num_attention_heads": 16, + "num_beam_groups": 1, + "num_beams": 1, + "num_channels": 3, + "num_hidden_layers": 27, + "num_return_sequences": 1, + "output_attentions": false, + "output_hidden_states": false, + "output_scores": false, + "pad_token_id": null, + "patch_size": 14, + "prefix": null, + "problem_type": null, + "pruned_heads": {}, + "remove_invalid_values": false, + "repetition_penalty": 1.0, + "return_dict": true, + "return_dict_in_generate": false, + "sep_token_id": null, + "suppress_tokens": null, + "task_specific_params": null, + "temperature": 1.0, + "tf_legacy_loss": false, + "tie_encoder_decoder": false, + "tie_word_embeddings": true, + "tokenizer_class": null, + "top_k": 50, + "top_p": 1.0, + "torch_dtype": "bfloat16", + "torchscript": false, + "typical_p": 1.0, + "use_bfloat16": false + } +} diff --git a/llm/config.json b/llm/config.json new file mode 100644 index 0000000000000000000000000000000000000000..4322f106d09fdd68156605239384af82798d3ac4 --- /dev/null +++ b/llm/config.json @@ -0,0 +1,32 @@ +{ + "_name_or_path": "/lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/llm", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 2560, + "initializer_range": 0.02, + "intermediate_size": 6912, + "max_position_embeddings": 4096, + "model_max_length": 4096, + "model_type": "llama", + "num_attention_heads": 20, + "num_hidden_layers": 32, + "num_key_value_heads": 20, + "pad_token_id": 0, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 10000.0, + "tie_word_embeddings": false, + "tokenizer_model_max_length": 4096, + "tokenizer_padding_side": "right", + "torch_dtype": "bfloat16", + "transformers_version": "4.36.2", + "use_cache": true, + "vocab_size": 32000 +} diff --git a/llm/generation_config.json b/llm/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..bf84ec1a28ba89feb07162d95b06633a40b4975f --- /dev/null +++ b/llm/generation_config.json @@ -0,0 +1,7 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "pad_token_id": 0, + "transformers_version": "4.36.2" +} diff --git a/llm/model-00001-of-00002.safetensors b/llm/model-00001-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9ca1e33df448c6bd3cb82fd1b79d0017c0ec1452 --- /dev/null +++ b/llm/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80520c2448f9ac419e8ca92c3c904f45b6c91dcd6176a6ecf5a552c20d1db348 +size 4974521464 diff --git a/llm/model-00002-of-00002.safetensors b/llm/model-00002-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5565ff8c7769070ed4eb62cd6826a3ed228f70f1 --- /dev/null +++ b/llm/model-00002-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e94b7838b9530569911a62bc293328fa6345572c9945e121265f97a5c4bbfb89 +size 428632856 diff --git a/llm/model.safetensors.index.json b/llm/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..8b173c9ac8194749df58c92051618c0ff74c4c20 --- /dev/null +++ b/llm/model.safetensors.index.json @@ -0,0 +1,298 @@ +{ + "metadata": { + "total_size": 5403120640 + }, + "weight_map": { + "lm_head.weight": "model-00002-of-00002.safetensors", + "model.embed_tokens.weight": "model-00001-of-00002.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.norm.weight": "model-00002-of-00002.safetensors" + } +} diff --git a/llm/special_tokens_map.json b/llm/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..14761dcf1466dc232bd41de9c21d4c617b15755e --- /dev/null +++ b/llm/special_tokens_map.json @@ -0,0 +1,24 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "", + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/llm/tokenizer.model b/llm/tokenizer.model new file mode 100644 index 0000000000000000000000000000000000000000..3b7eab905db502ae7629c8a3c1f8412a3178c4c2 --- /dev/null +++ b/llm/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7aedb3582ecda9fa99ee9242c17a9658f6744db083ee6ebdc8fb14857f84d220 +size 499723 diff --git a/llm/tokenizer_config.json b/llm/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..47ab96cd62cc374653a0ea0fb77f9457e0f53481 --- /dev/null +++ b/llm/tokenizer_config.json @@ -0,0 +1,43 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "add_prefix_space": true, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "legacy": false, + "model_max_length": 4096, + "pad_token": "", + "padding_side": "right", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "unk_token": "", + "use_default_system_prompt": false +} diff --git a/mm_projector/config.json b/mm_projector/config.json new file mode 100644 index 0000000000000000000000000000000000000000..a58bb28b341c1ac459eaa2b66c8a7727f4cbf165 --- /dev/null +++ b/mm_projector/config.json @@ -0,0 +1,10 @@ +{ + "_name_or_path": "/lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/mm_projector", + "architectures": [ + "MultimodalProjector" + ], + "mm_projector_type": "mlp_downsample", + "model_type": "v2l_projector", + "torch_dtype": "bfloat16", + "transformers_version": "4.36.2" +} diff --git a/mm_projector/model.safetensors b/mm_projector/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c9d6c2cc630436d6e35b043566e177cc91b5ea79 --- /dev/null +++ b/mm_projector/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:644047d9ae6938fcda018311591033eb6c5415c49171c5547daef54a486a1147 +size 36729360 diff --git a/terminal.log b/terminal.log new file mode 100644 index 0000000000000000000000000000000000000000..990c7f29e7d8afbf7c2b26a55066fd79aa2695fa --- /dev/null +++ b/terminal.log @@ -0,0 +1,17741 @@ +srun: job 9363114 queued and waiting for resources +srun: job 9363114 has been allocated resources +wandb: Currently logged in as: memmelma. Use `wandb login --relogin` to force relogin +MASTER_ADDR=batch-block5-00391 +JobID: 9363114 | Full list: batch-block5-00391 +NETWORK=Efficient-Large-Model/VILA1.5-1b +WARNING:torch.distributed.run: +***************************************** +Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed. +***************************************** +Did not find AutoResume SDK! +Did not find AutoResume SDK! +Did not find AutoResume SDK! +Did not find AutoResume SDK! +Did not find AutoResume SDK! +Did not find AutoResume SDK! +Did not find AutoResume SDK! +Did not find AutoResume SDK! +[2025-06-27 11:09:34,309] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-27 11:09:34,309] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-27 11:09:34,309] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-27 11:09:34,309] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-27 11:09:34,309] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-27 11:09:34,309] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-27 11:09:34,309] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-27 11:09:34,309] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-27 11:09:36,613] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-27 11:09:36,613] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-27 11:09:36,613] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-27 11:09:36,613] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-27 11:09:36,613] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-27 11:09:36,613] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-27 11:09:36,613] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-27 11:09:36,613] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-27 11:09:36,613] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-27 11:09:36,613] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-27 11:09:36,613] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-27 11:09:36,613] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-27 11:09:36,613] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-27 11:09:36,613] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-27 11:09:36,613] [INFO] [comm.py:625:init_distributed] Initializing TorchBackend in DeepSpeed with backend nccl +[2025-06-27 11:09:36,614] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-27 11:09:36,614] [INFO] [comm.py:594:init_distributed] cdb=None +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py:795: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`. + warnings.warn( +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py:795: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`. + warnings.warn( +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py:795: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`. + warnings.warn( +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py:795: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`. + warnings.warn( +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py:795: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`. + warnings.warn( +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py:795: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`. + warnings.warn( +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py:795: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`. + warnings.warn( +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py:795: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`. + warnings.warn( +Traceback (most recent call last): + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_http.py", line 406, in hf_raise_for_status +Traceback (most recent call last): + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_http.py", line 406, in hf_raise_for_status +Traceback (most recent call last): + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_http.py", line 406, in hf_raise_for_status +Traceback (most recent call last): + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_http.py", line 406, in hf_raise_for_status +Traceback (most recent call last): + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_http.py", line 406, in hf_raise_for_status +Traceback (most recent call last): + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_http.py", line 406, in hf_raise_for_status + response.raise_for_status()response.raise_for_status() + + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/requests/models.py", line 1024, in raise_for_status +response.raise_for_status() File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/requests/models.py", line 1024, in raise_for_status + + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/requests/models.py", line 1024, in raise_for_status + response.raise_for_status() + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/requests/models.py", line 1024, in raise_for_status + response.raise_for_status() + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/requests/models.py", line 1024, in raise_for_status + response.raise_for_status() + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/requests/models.py", line 1024, in raise_for_status + raise HTTPError(http_error_msg, response=self)raise HTTPError(http_error_msg, response=self) + + raise HTTPError(http_error_msg, response=self)requests.exceptions +requests.exceptions.HTTPError.: requests.exceptionsHTTPError404 Client Error: Not Found for url: https://huggingface.co/Efficient-Large-Model/VILA1.5-1b/resolve/main/config.json. +: HTTPError +The above exception was the direct cause of the following exception: + +404 Client Error: Not Found for url: https://huggingface.co/Efficient-Large-Model/VILA1.5-1b/resolve/main/config.json: +404 Client Error: Not Found for url: https://huggingface.co/Efficient-Large-Model/VILA1.5-1b/resolve/main/config.jsonTraceback (most recent call last): + +The above exception was the direct cause of the following exception: + + + +The above exception was the direct cause of the following exception: + +Traceback (most recent call last): + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/utils/hub.py", line 389, in cached_file +Traceback (most recent call last): + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/utils/hub.py", line 389, in cached_file + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/utils/hub.py", line 389, in cached_file +raise HTTPError(http_error_msg, response=self) +raise HTTPError(http_error_msg, response=self) +requests.exceptions.HTTPError: 404 Client Error: Not Found for url: https://huggingface.co/Efficient-Large-Model/VILA1.5-1b/resolve/main/config.jsonrequests.exceptions +. +The above exception was the direct cause of the following exception: + +HTTPErrorTraceback (most recent call last): +: 404 Client Error: Not Found for url: https://huggingface.co/Efficient-Large-Model/VILA1.5-1b/resolve/main/config.json + +The above exception was the direct cause of the following exception: + + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/utils/hub.py", line 389, in cached_file +Traceback (most recent call last): + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/utils/hub.py", line 389, in cached_file +Traceback (most recent call last): + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_http.py", line 406, in hf_raise_for_status + raise HTTPError(http_error_msg, response=self) +requests.exceptions.HTTPError: 404 Client Error: Not Found for url: https://huggingface.co/Efficient-Large-Model/VILA1.5-1b/resolve/main/config.json + +The above exception was the direct cause of the following exception: + +Traceback (most recent call last): + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/utils/hub.py", line 389, in cached_file + response.raise_for_status() + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/requests/models.py", line 1024, in raise_for_status + raise HTTPError(http_error_msg, response=self) +requests.exceptions.HTTPError: 404 Client Error: Not Found for url: https://huggingface.co/Efficient-Large-Model/VILA1.5-1b/resolve/main/config.json + +The above exception was the direct cause of the following exception: + +Traceback (most recent call last): + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/utils/hub.py", line 389, in cached_file + resolved_file = hf_hub_download(resolved_file = hf_hub_download( + + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn + resolved_file = hf_hub_download(resolved_file = hf_hub_download( + + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn + resolved_file = hf_hub_download( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn + resolved_file = hf_hub_download( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn + resolved_file = hf_hub_download( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn + return fn(*args, **kwargs)return fn(*args, **kwargs) + + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 860, in hf_hub_download + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 860, in hf_hub_download + return fn(*args, **kwargs) +return fn(*args, **kwargs) return fn(*args, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 860, in hf_hub_download +return fn(*args, **kwargs) + + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 860, in hf_hub_download + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 860, in hf_hub_download + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 860, in hf_hub_download + return fn(*args, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 860, in hf_hub_download + return _hf_hub_download_to_cache_dir(return _hf_hub_download_to_cache_dir( + + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 967, in _hf_hub_download_to_cache_dir + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 967, in _hf_hub_download_to_cache_dir + return _hf_hub_download_to_cache_dir(return _hf_hub_download_to_cache_dir( + + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 967, in _hf_hub_download_to_cache_dir + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 967, in _hf_hub_download_to_cache_dir + return _hf_hub_download_to_cache_dir( + return _hf_hub_download_to_cache_dir( File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 967, in _hf_hub_download_to_cache_dir + + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 967, in _hf_hub_download_to_cache_dir + return _hf_hub_download_to_cache_dir( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 967, in _hf_hub_download_to_cache_dir + _raise_on_head_call_error(head_call_error, force_download, local_files_only)_raise_on_head_call_error(head_call_error, force_download, local_files_only) + + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1482, in _raise_on_head_call_error + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1482, in _raise_on_head_call_error + _raise_on_head_call_error(head_call_error, force_download, local_files_only)_raise_on_head_call_error(head_call_error, force_download, local_files_only)_raise_on_head_call_error(head_call_error, force_download, local_files_only) + + + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1482, in _raise_on_head_call_error + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1482, in _raise_on_head_call_error +_raise_on_head_call_error(head_call_error, force_download, local_files_only) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1482, in _raise_on_head_call_error + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1482, in _raise_on_head_call_error + _raise_on_head_call_error(head_call_error, force_download, local_files_only) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1482, in _raise_on_head_call_error + raise head_call_errorraise head_call_errorraise head_call_error + + + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1374, in _get_metadata_or_catch_error + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1374, in _get_metadata_or_catch_error +raise head_call_error File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1374, in _get_metadata_or_catch_error + + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1374, in _get_metadata_or_catch_error + raise head_call_error + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1374, in _get_metadata_or_catch_error + raise head_call_error + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1374, in _get_metadata_or_catch_error + raise head_call_error + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1374, in _get_metadata_or_catch_error + metadata = get_hf_file_metadata( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn + metadata = get_hf_file_metadata(metadata = get_hf_file_metadata( + + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn + metadata = get_hf_file_metadata( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn + metadata = get_hf_file_metadata(metadata = get_hf_file_metadata( + + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn + metadata = get_hf_file_metadata( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn + return fn(*args, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1294, in get_hf_file_metadata +return fn(*args, **kwargs) + return fn(*args, **kwargs) File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1294, in get_hf_file_metadata + + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1294, in get_hf_file_metadata + return fn(*args, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1294, in get_hf_file_metadata +return fn(*args, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1294, in get_hf_file_metadata + return fn(*args, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1294, in get_hf_file_metadata + return fn(*args, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1294, in get_hf_file_metadata + r = _request_wrapper( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 278, in _request_wrapper + r = _request_wrapper( +r = _request_wrapper( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 278, in _request_wrapper + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 278, in _request_wrapper +r = _request_wrapper( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 278, in _request_wrapper +r = _request_wrapper( + r = _request_wrapper( File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 278, in _request_wrapper + + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 278, in _request_wrapper + response = _request_wrapper(response = _request_wrapper( + + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 302, in _request_wrapper + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 302, in _request_wrapper + response = _request_wrapper( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 302, in _request_wrapper +response = _request_wrapper( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 302, in _request_wrapper + response = _request_wrapper( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 302, in _request_wrapper + response = _request_wrapper( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 302, in _request_wrapper + r = _request_wrapper( +hf_raise_for_status(response) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_http.py", line 454, in hf_raise_for_status + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 278, in _request_wrapper + hf_raise_for_status(response) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_http.py", line 454, in hf_raise_for_status + hf_raise_for_status(response) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_http.py", line 454, in hf_raise_for_status + hf_raise_for_status(response) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_http.py", line 454, in hf_raise_for_status + hf_raise_for_status(response)hf_raise_for_status(response) + + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_http.py", line 454, in hf_raise_for_status + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_http.py", line 454, in hf_raise_for_status + response = _request_wrapper( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 302, in _request_wrapper + hf_raise_for_status(response) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_http.py", line 454, in hf_raise_for_status + raise _format(RepositoryNotFoundError, message, response) from e +huggingface_hub.errors.RepositoryNotFoundError: 404 Client Error. (Request ID: Root=1-685ede60-428911ee60ea0338026c8b4e;53921fea-58db-4e3c-a839-bc234b24120e) + +Repository Not Found for url: https://huggingface.co/Efficient-Large-Model/VILA1.5-1b/resolve/main/config.json. +Please make sure you specified the correct `repo_id` and `repo_type`. +If you are trying to access a private or gated repo, make sure you are authenticated. +raise _format(RepositoryNotFoundError, message, response) from e +The above exception was the direct cause of the following exception: + + + Traceback (most recent call last): +huggingface_hub.errorsraise _format(RepositoryNotFoundError, message, response) from e. + File "/lustre/fs12/portfolios/nvr/projects/nvr_srl_simpler/users/mmemmel/projects/vila/VILA/llava/train/train_mem.py", line 36, in +RepositoryNotFoundError huggingface_hub.errors: raise _format(RepositoryNotFoundError, message, response) from e.404 Client Error. (Request ID: Root=1-685ede60-26f1c06167a32477504b3fa1;a3f9eef7-0bf5-4895-b99f-21f6bcf37243) + +Repository Not Found for url: https://huggingface.co/Efficient-Large-Model/VILA1.5-1b/resolve/main/config.json. +Please make sure you specified the correct `repo_id` and `repo_type`. +If you are trying to access a private or gated repo, make sure you are authenticated. + +RepositoryNotFoundErrorraise _format(RepositoryNotFoundError, message, response) from ehuggingface_hub.errors + +The above exception was the direct cause of the following exception: + +.: 404 Client Error. (Request ID: Root=1-685ede60-4a2437c93c2074e816a371d2;d69e1a96-a71a-4bcb-a71c-837ed9855bf2) + +Repository Not Found for url: https://huggingface.co/Efficient-Large-Model/VILA1.5-1b/resolve/main/config.json. +Please make sure you specified the correct `repo_id` and `repo_type`. +If you are trying to access a private or gated repo, make sure you are authenticated.huggingface_hub.errorsRepositoryNotFoundErrorTraceback (most recent call last): + +.: +The above exception was the direct cause of the following exception: + +RepositoryNotFoundError404 Client Error. (Request ID: Root=1-685ede60-72e54a54234a570970e96594;3c689aa0-577a-41ad-980d-aa08eff0ca8c) + +Repository Not Found for url: https://huggingface.co/Efficient-Large-Model/VILA1.5-1b/resolve/main/config.json. +Please make sure you specified the correct `repo_id` and `repo_type`. +If you are trying to access a private or gated repo, make sure you are authenticated. File "/lustre/fs12/portfolios/nvr/projects/nvr_srl_simpler/users/mmemmel/projects/vila/VILA/llava/train/train_mem.py", line 36, in +: Traceback (most recent call last): + +404 Client Error. (Request ID: Root=1-685ede60-56999711563fddaa30eea235;19812829-6741-40c2-8b9f-c1fea4c4e869) + +Repository Not Found for url: https://huggingface.co/Efficient-Large-Model/VILA1.5-1b/resolve/main/config.json. +Please make sure you specified the correct `repo_id` and `repo_type`. +If you are trying to access a private or gated repo, make sure you are authenticated. +The above exception was the direct cause of the following exception: + + + File "/lustre/fs12/portfolios/nvr/projects/nvr_srl_simpler/users/mmemmel/projects/vila/VILA/llava/train/train_mem.py", line 36, in + +The above exception was the direct cause of the following exception: + +Traceback (most recent call last): +Traceback (most recent call last): + File "/lustre/fs12/portfolios/nvr/projects/nvr_srl_simpler/users/mmemmel/projects/vila/VILA/llava/train/train_mem.py", line 36, in + File "/lustre/fs12/portfolios/nvr/projects/nvr_srl_simpler/users/mmemmel/projects/vila/VILA/llava/train/train_mem.py", line 36, in + raise _format(RepositoryNotFoundError, message, response) from e +huggingface_hub.errors.RepositoryNotFoundError: 404 Client Error. (Request ID: Root=1-685ede60-15005be73a40772e283b555a;edcbbeba-d56a-423f-94e5-2a150b4b6999) + +Repository Not Found for url: https://huggingface.co/Efficient-Large-Model/VILA1.5-1b/resolve/main/config.json. +Please make sure you specified the correct `repo_id` and `repo_type`. +If you are trying to access a private or gated repo, make sure you are authenticated. + +The above exception was the direct cause of the following exception: + +Traceback (most recent call last): + File "/lustre/fs12/portfolios/nvr/projects/nvr_srl_simpler/users/mmemmel/projects/vila/VILA/llava/train/train_mem.py", line 36, in + raise _format(RepositoryNotFoundError, message, response) from e +huggingface_hub.errors.RepositoryNotFoundError: 404 Client Error. (Request ID: Root=1-685ede61-2ef809b83fcb408d65a03fd7;88783d35-4f17-4f83-990e-1cd527de9aa9) + +Repository Not Found for url: https://huggingface.co/Efficient-Large-Model/VILA1.5-1b/resolve/main/config.json. +Please make sure you specified the correct `repo_id` and `repo_type`. +If you are trying to access a private or gated repo, make sure you are authenticated. + +The above exception was the direct cause of the following exception: + +Traceback (most recent call last): + File "/lustre/fs12/portfolios/nvr/projects/nvr_srl_simpler/users/mmemmel/projects/vila/VILA/llava/train/train_mem.py", line 36, in + train() + train() File "/lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/VILA/llava/train/train.py", line 247, in train +train() + + File "/lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/VILA/llava/train/train.py", line 247, in train + File "/lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/VILA/llava/train/train.py", line 247, in train +train() + File "/lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/VILA/llava/train/train.py", line 247, in train + train() + train() + File "/lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/VILA/llava/train/train.py", line 247, in train + File "/lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/VILA/llava/train/train.py", line 247, in train + train() + File "/lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/VILA/llava/train/train.py", line 247, in train + config = LlavaLlamaConfig.from_pretrained( + config = LlavaLlamaConfig.from_pretrained(config = LlavaLlamaConfig.from_pretrained( File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 615, in from_pretrained + + + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 615, in from_pretrained + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 615, in from_pretrained + config = LlavaLlamaConfig.from_pretrained( + config = LlavaLlamaConfig.from_pretrained( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 615, in from_pretrained + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 615, in from_pretrained + config = LlavaLlamaConfig.from_pretrained( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 615, in from_pretrained + config = LlavaLlamaConfig.from_pretrained( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 615, in from_pretrained + config_dict, kwargs = cls.get_config_dict(pretrained_model_name_or_path, **kwargs) +config_dict, kwargs = cls.get_config_dict(pretrained_model_name_or_path, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 644, in get_config_dict +config_dict, kwargs = cls.get_config_dict(pretrained_model_name_or_path, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 644, in get_config_dict +config_dict, kwargs = cls.get_config_dict(pretrained_model_name_or_path, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 644, in get_config_dict + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 644, in get_config_dict + config_dict, kwargs = cls.get_config_dict(pretrained_model_name_or_path, **kwargs)config_dict, kwargs = cls.get_config_dict(pretrained_model_name_or_path, **kwargs) + + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 644, in get_config_dict + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 644, in get_config_dict + config_dict, kwargs = cls.get_config_dict(pretrained_model_name_or_path, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 644, in get_config_dict + config_dict, kwargs = cls._get_config_dict(pretrained_model_name_or_path, **kwargs)config_dict, kwargs = cls._get_config_dict(pretrained_model_name_or_path, **kwargs) + + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 699, in _get_config_dict + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 699, in _get_config_dict + config_dict, kwargs = cls._get_config_dict(pretrained_model_name_or_path, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 699, in _get_config_dict + config_dict, kwargs = cls._get_config_dict(pretrained_model_name_or_path, **kwargs)config_dict, kwargs = cls._get_config_dict(pretrained_model_name_or_path, **kwargs)config_dict, kwargs = cls._get_config_dict(pretrained_model_name_or_path, **kwargs) + + + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 699, in _get_config_dict + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 699, in _get_config_dict + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 699, in _get_config_dict + config_dict, kwargs = cls._get_config_dict(pretrained_model_name_or_path, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 699, in _get_config_dict + resolved_config_file = cached_file( + resolved_config_file = cached_file( File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/utils/hub.py", line 410, in cached_file + + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/utils/hub.py", line 410, in cached_file +resolved_config_file = cached_file( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/utils/hub.py", line 410, in cached_file + resolved_config_file = cached_file(resolved_config_file = cached_file(resolved_config_file = cached_file( + + + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/utils/hub.py", line 410, in cached_file + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/utils/hub.py", line 410, in cached_file + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/utils/hub.py", line 410, in cached_file + resolved_config_file = cached_file( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/utils/hub.py", line 410, in cached_file + raise EnvironmentError( + OSErrorraise EnvironmentError(: +OSError raise EnvironmentError(: raise EnvironmentError(Efficient-Large-Model/VILA1.5-1b is not a local folder and is not a valid model identifier listed on 'https://huggingface.co/models' +If this is a private repository, make sure to pass a token having permission to this repo either by logging in with `huggingface-cli login` or by passing `token=` + + +raise EnvironmentError(OSErrorOSError +: : OSErrorEfficient-Large-Model/VILA1.5-1b is not a local folder and is not a valid model identifier listed on 'https://huggingface.co/models' +If this is a private repository, make sure to pass a token having permission to this repo either by logging in with `huggingface-cli login` or by passing `token=`: +Efficient-Large-Model/VILA1.5-1b is not a local folder and is not a valid model identifier listed on 'https://huggingface.co/models' +If this is a private repository, make sure to pass a token having permission to this repo either by logging in with `huggingface-cli login` or by passing `token=`Efficient-Large-Model/VILA1.5-1b is not a local folder and is not a valid model identifier listed on 'https://huggingface.co/models' +If this is a private repository, make sure to pass a token having permission to this repo either by logging in with `huggingface-cli login` or by passing `token=` + +Efficient-Large-Model/VILA1.5-1b is not a local folder and is not a valid model identifier listed on 'https://huggingface.co/models' +If this is a private repository, make sure to pass a token having permission to this repo either by logging in with `huggingface-cli login` or by passing `token=` + raise EnvironmentError( +OSError: Efficient-Large-Model/VILA1.5-1b is not a local folder and is not a valid model identifier listed on 'https://huggingface.co/models' +If this is a private repository, make sure to pass a token having permission to this repo either by logging in with `huggingface-cli login` or by passing `token=` + raise EnvironmentError( +OSError: Efficient-Large-Model/VILA1.5-1b is not a local folder and is not a valid model identifier listed on 'https://huggingface.co/models' +If this is a private repository, make sure to pass a token having permission to this repo either by logging in with `huggingface-cli login` or by passing `token=` +Traceback (most recent call last): + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_http.py", line 406, in hf_raise_for_status + response.raise_for_status() + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/requests/models.py", line 1024, in raise_for_status + raise HTTPError(http_error_msg, response=self) +requests.exceptions.HTTPError: 404 Client Error: Not Found for url: https://huggingface.co/Efficient-Large-Model/VILA1.5-1b/resolve/main/config.json + +The above exception was the direct cause of the following exception: + +Traceback (most recent call last): + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/utils/hub.py", line 389, in cached_file + resolved_file = hf_hub_download( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn + return fn(*args, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 860, in hf_hub_download + return _hf_hub_download_to_cache_dir( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 967, in _hf_hub_download_to_cache_dir + _raise_on_head_call_error(head_call_error, force_download, local_files_only) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1482, in _raise_on_head_call_error + raise head_call_error + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1374, in _get_metadata_or_catch_error + metadata = get_hf_file_metadata( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn + return fn(*args, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1294, in get_hf_file_metadata + r = _request_wrapper( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 278, in _request_wrapper + response = _request_wrapper( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 302, in _request_wrapper + hf_raise_for_status(response) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_http.py", line 454, in hf_raise_for_status + raise _format(RepositoryNotFoundError, message, response) from e +huggingface_hub.errors.RepositoryNotFoundError: 404 Client Error. (Request ID: Root=1-685ede61-2573732f4a958abc7f83e7d1;1794c90c-419e-4fbb-abf2-a9ad89e841d9) + +Repository Not Found for url: https://huggingface.co/Efficient-Large-Model/VILA1.5-1b/resolve/main/config.json. +Please make sure you specified the correct `repo_id` and `repo_type`. +If you are trying to access a private or gated repo, make sure you are authenticated. + +The above exception was the direct cause of the following exception: + +Traceback (most recent call last): + File "/lustre/fs12/portfolios/nvr/projects/nvr_srl_simpler/users/mmemmel/projects/vila/VILA/llava/train/train_mem.py", line 36, in + train() + File "/lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/VILA/llava/train/train.py", line 247, in train + config = LlavaLlamaConfig.from_pretrained( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 615, in from_pretrained + config_dict, kwargs = cls.get_config_dict(pretrained_model_name_or_path, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 644, in get_config_dict + config_dict, kwargs = cls._get_config_dict(pretrained_model_name_or_path, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 699, in _get_config_dict + resolved_config_file = cached_file( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/utils/hub.py", line 410, in cached_file + raise EnvironmentError( +OSError: Efficient-Large-Model/VILA1.5-1b is not a local folder and is not a valid model identifier listed on 'https://huggingface.co/models' +If this is a private repository, make sure to pass a token having permission to this repo either by logging in with `huggingface-cli login` or by passing `token=` +ERROR:torch.distributed.elastic.multiprocessing.api:failed (exitcode: 1) local_rank: 0 (pid: 3918408) of binary: /lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/bin/python3.10 +Traceback (most recent call last): + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/bin/torchrun", line 8, in + sys.exit(main()) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 346, in wrapper + return f(*args, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/torch/distributed/run.py", line 794, in main + run(args) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/torch/distributed/run.py", line 785, in run + elastic_launch( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 134, in __call__ + return launch_agent(self._config, self._entrypoint, list(args)) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 250, in launch_agent + raise ChildFailedError( +torch.distributed.elastic.multiprocessing.errors.ChildFailedError: +============================================================ +llava/train/train_mem.py FAILED +------------------------------------------------------------ +Failures: +[1]: + time : 2025-06-27_11:09:40 + host : batch-block5-00391.cm.cluster + rank : 1 (local_rank: 1) + exitcode : 1 (pid: 3918409) + error_file: + traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html +[2]: + time : 2025-06-27_11:09:40 + host : batch-block5-00391.cm.cluster + rank : 2 (local_rank: 2) + exitcode : 1 (pid: 3918410) + error_file: + traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html +[3]: + time : 2025-06-27_11:09:40 + host : batch-block5-00391.cm.cluster + rank : 3 (local_rank: 3) + exitcode : 1 (pid: 3918411) + error_file: + traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html +[4]: + time : 2025-06-27_11:09:40 + host : batch-block5-00391.cm.cluster + rank : 4 (local_rank: 4) + exitcode : 1 (pid: 3918412) + error_file: + traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html +[5]: + time : 2025-06-27_11:09:40 + host : batch-block5-00391.cm.cluster + rank : 5 (local_rank: 5) + exitcode : 1 (pid: 3918413) + error_file: + traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html +[6]: + time : 2025-06-27_11:09:40 + host : batch-block5-00391.cm.cluster + rank : 6 (local_rank: 6) + exitcode : 1 (pid: 3918414) + error_file: + traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html +[7]: + time : 2025-06-27_11:09:40 + host : batch-block5-00391.cm.cluster + rank : 7 (local_rank: 7) + exitcode : 1 (pid: 3918415) + error_file: + traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html +------------------------------------------------------------ +Root Cause (first observed failure): +[0]: + time : 2025-06-27_11:09:40 + host : batch-block5-00391.cm.cluster + rank : 0 (local_rank: 0) + exitcode : 1 (pid: 3918408) + error_file: + traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html +============================================================ +srun: error: batch-block5-00391: task 0: Exited with exit code 1 +srun: Terminating StepId=9363114.0 +srun: job 9363941 queued and waiting for resources +srun: job 9363941 has been allocated resources +wandb: Currently logged in as: memmelma. Use `wandb login --relogin` to force relogin +MASTER_ADDR=batch-block7-00766 +JobID: 9363941 | Full list: batch-block7-00766 +NETWORK=Efficient-Large-Model/VILA1.5-1b +WARNING:torch.distributed.run: +***************************************** +Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed. +***************************************** +Did not find AutoResume SDK! +Did not find AutoResume SDK! +Did not find AutoResume SDK! +Did not find AutoResume SDK! +Did not find AutoResume SDK! +Did not find AutoResume SDK! +Did not find AutoResume SDK! +Did not find AutoResume SDK! +[2025-06-27 11:11:42,363] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-27 11:11:42,363] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-27 11:11:42,363] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-27 11:11:42,363] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-27 11:11:42,363] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-27 11:11:42,363] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-27 11:11:42,363] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-27 11:11:42,363] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-27 11:11:44,084] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-27 11:11:44,084] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-27 11:11:44,084] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-27 11:11:44,084] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-27 11:11:44,084] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-27 11:11:44,084] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-27 11:11:44,084] [INFO] [comm.py:625:init_distributed] Initializing TorchBackend in DeepSpeed with backend nccl +[2025-06-27 11:11:44,084] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-27 11:11:44,084] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-27 11:11:44,167] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-27 11:11:44,167] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-27 11:11:44,169] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-27 11:11:44,169] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-27 11:11:44,169] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-27 11:11:44,169] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-27 11:11:44,169] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-27 11:11:44,169] [INFO] [comm.py:594:init_distributed] cdb=None +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py:795: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`. + warnings.warn( +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py:795: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`. + warnings.warn( +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py:795: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`. + warnings.warn( +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py:795: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`. + warnings.warn( +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py:795: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`. + warnings.warn( +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py:795: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`. + warnings.warn( +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py:795: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`. + warnings.warn( +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py:795: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`. + warnings.warn( +Traceback (most recent call last): + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_http.py", line 406, in hf_raise_for_status + response.raise_for_status() + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/requests/models.py", line 1024, in raise_for_status + raise HTTPError(http_error_msg, response=self) +requests.exceptions.HTTPError: 404 Client Error: Not Found for url: https://huggingface.co/Efficient-Large-Model/VILA1.5-1b/resolve/main/config.json + +The above exception was the direct cause of the following exception: + +Traceback (most recent call last): + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/utils/hub.py", line 389, in cached_file +Traceback (most recent call last): + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_http.py", line 406, in hf_raise_for_status + response.raise_for_status() + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/requests/models.py", line 1024, in raise_for_status + raise HTTPError(http_error_msg, response=self) +requests.exceptions.HTTPError: 404 Client Error: Not Found for url: https://huggingface.co/Efficient-Large-Model/VILA1.5-1b/resolve/main/config.json + +The above exception was the direct cause of the following exception: + +Traceback (most recent call last): + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/utils/hub.py", line 389, in cached_file + resolved_file = hf_hub_download( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn +Traceback (most recent call last): + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_http.py", line 406, in hf_raise_for_status + resolved_file = hf_hub_download( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn + response.raise_for_status() + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/requests/models.py", line 1024, in raise_for_status + return fn(*args, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 860, in hf_hub_download + raise HTTPError(http_error_msg, response=self) +requests.exceptions.HTTPError: 404 Client Error: Not Found for url: https://huggingface.co/Efficient-Large-Model/VILA1.5-1b/resolve/main/config.json + +The above exception was the direct cause of the following exception: + +Traceback (most recent call last): + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/utils/hub.py", line 389, in cached_file + return fn(*args, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 860, in hf_hub_download + return _hf_hub_download_to_cache_dir( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 967, in _hf_hub_download_to_cache_dir + return _hf_hub_download_to_cache_dir( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 967, in _hf_hub_download_to_cache_dir + _raise_on_head_call_error(head_call_error, force_download, local_files_only) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1482, in _raise_on_head_call_error + _raise_on_head_call_error(head_call_error, force_download, local_files_only) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1482, in _raise_on_head_call_error + resolved_file = hf_hub_download( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn + raise head_call_error + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1374, in _get_metadata_or_catch_error + raise head_call_error + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1374, in _get_metadata_or_catch_error + metadata = get_hf_file_metadata( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn + return fn(*args, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 860, in hf_hub_download + metadata = get_hf_file_metadata( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn + return fn(*args, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1294, in get_hf_file_metadata + return fn(*args, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1294, in get_hf_file_metadata + return _hf_hub_download_to_cache_dir( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 967, in _hf_hub_download_to_cache_dir + r = _request_wrapper( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 278, in _request_wrapper + response = _request_wrapper( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 302, in _request_wrapper + _raise_on_head_call_error(head_call_error, force_download, local_files_only) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1482, in _raise_on_head_call_error + hf_raise_for_status(response) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_http.py", line 454, in hf_raise_for_status + r = _request_wrapper( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 278, in _request_wrapper + response = _request_wrapper( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 302, in _request_wrapper + raise head_call_error + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1374, in _get_metadata_or_catch_error + hf_raise_for_status(response) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_http.py", line 454, in hf_raise_for_status + raise _format(RepositoryNotFoundError, message, response) from e +huggingface_hub.errors.RepositoryNotFoundError: 404 Client Error. (Request ID: Root=1-685edee0-4b260c604fc9da97093a4dc9;fd4ef183-11fe-4c63-9b81-fd991e03aee4) + +Repository Not Found for url: https://huggingface.co/Efficient-Large-Model/VILA1.5-1b/resolve/main/config.json. +Please make sure you specified the correct `repo_id` and `repo_type`. +If you are trying to access a private or gated repo, make sure you are authenticated. + +The above exception was the direct cause of the following exception: + +Traceback (most recent call last): + File "/lustre/fs12/portfolios/nvr/projects/nvr_srl_simpler/users/mmemmel/projects/vila/VILA/llava/train/train_mem.py", line 36, in + metadata = get_hf_file_metadata( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn + raise _format(RepositoryNotFoundError, message, response) from e +huggingface_hub.errors.RepositoryNotFoundError: 404 Client Error. (Request ID: Root=1-685edee0-4403ff35348ae90d0bff66ea;832cf112-d6de-4798-a02c-27b43fee27de) + +Repository Not Found for url: https://huggingface.co/Efficient-Large-Model/VILA1.5-1b/resolve/main/config.json. +Please make sure you specified the correct `repo_id` and `repo_type`. +If you are trying to access a private or gated repo, make sure you are authenticated. + +The above exception was the direct cause of the following exception: + +Traceback (most recent call last): + File "/lustre/fs12/portfolios/nvr/projects/nvr_srl_simpler/users/mmemmel/projects/vila/VILA/llava/train/train_mem.py", line 36, in + train() + File "/lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/VILA/llava/train/train.py", line 247, in train + return fn(*args, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1294, in get_hf_file_metadata + train() + File "/lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/VILA/llava/train/train.py", line 247, in train + config = LlavaLlamaConfig.from_pretrained( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 615, in from_pretrained + r = _request_wrapper( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 278, in _request_wrapper + config = LlavaLlamaConfig.from_pretrained( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 615, in from_pretrained + response = _request_wrapper( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 302, in _request_wrapper + hf_raise_for_status(response) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_http.py", line 454, in hf_raise_for_status + raise _format(RepositoryNotFoundError, message, response) from e +huggingface_hub.errors.RepositoryNotFoundError: 404 Client Error. (Request ID: Root=1-685edee0-4d458457539f3d4c5f66b2ea;f6d4f63a-bc7e-436f-b0d0-4559b5f21330) + +Repository Not Found for url: https://huggingface.co/Efficient-Large-Model/VILA1.5-1b/resolve/main/config.json. +Please make sure you specified the correct `repo_id` and `repo_type`. +If you are trying to access a private or gated repo, make sure you are authenticated. + +The above exception was the direct cause of the following exception: + +Traceback (most recent call last): + File "/lustre/fs12/portfolios/nvr/projects/nvr_srl_simpler/users/mmemmel/projects/vila/VILA/llava/train/train_mem.py", line 36, in + train() + File "/lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/VILA/llava/train/train.py", line 247, in train + config_dict, kwargs = cls.get_config_dict(pretrained_model_name_or_path, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 644, in get_config_dict + config_dict, kwargs = cls.get_config_dict(pretrained_model_name_or_path, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 644, in get_config_dict + config_dict, kwargs = cls._get_config_dict(pretrained_model_name_or_path, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 699, in _get_config_dict + config_dict, kwargs = cls._get_config_dict(pretrained_model_name_or_path, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 699, in _get_config_dict + config = LlavaLlamaConfig.from_pretrained( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 615, in from_pretrained + config_dict, kwargs = cls.get_config_dict(pretrained_model_name_or_path, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 644, in get_config_dict + resolved_config_file = cached_file(config_dict, kwargs = cls._get_config_dict(pretrained_model_name_or_path, **kwargs) + + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/utils/hub.py", line 410, in cached_file + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 699, in _get_config_dict + resolved_config_file = cached_file( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/utils/hub.py", line 410, in cached_file + resolved_config_file = cached_file( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/utils/hub.py", line 410, in cached_file + raise EnvironmentError( +OSError: Efficient-Large-Model/VILA1.5-1b is not a local folder and is not a valid model identifier listed on 'https://huggingface.co/models' +If this is a private repository, make sure to pass a token having permission to this repo either by logging in with `huggingface-cli login` or by passing `token=` + raise EnvironmentError( +OSError: Efficient-Large-Model/VILA1.5-1b is not a local folder and is not a valid model identifier listed on 'https://huggingface.co/models' +If this is a private repository, make sure to pass a token having permission to this repo either by logging in with `huggingface-cli login` or by passing `token=` + raise EnvironmentError( +OSError: Efficient-Large-Model/VILA1.5-1b is not a local folder and is not a valid model identifier listed on 'https://huggingface.co/models' +If this is a private repository, make sure to pass a token having permission to this repo either by logging in with `huggingface-cli login` or by passing `token=` +Traceback (most recent call last): + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_http.py", line 406, in hf_raise_for_status + response.raise_for_status() + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/requests/models.py", line 1024, in raise_for_status + raise HTTPError(http_error_msg, response=self) +requests.exceptions.HTTPError: 404 Client Error: Not Found for url: https://huggingface.co/Efficient-Large-Model/VILA1.5-1b/resolve/main/config.json + +The above exception was the direct cause of the following exception: + +Traceback (most recent call last): + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/utils/hub.py", line 389, in cached_file + resolved_file = hf_hub_download( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn + return fn(*args, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 860, in hf_hub_download + return _hf_hub_download_to_cache_dir( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 967, in _hf_hub_download_to_cache_dir + _raise_on_head_call_error(head_call_error, force_download, local_files_only) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1482, in _raise_on_head_call_error + raise head_call_error + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1374, in _get_metadata_or_catch_error + metadata = get_hf_file_metadata( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn + return fn(*args, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1294, in get_hf_file_metadata + r = _request_wrapper( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 278, in _request_wrapper + response = _request_wrapper( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 302, in _request_wrapper + hf_raise_for_status(response) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_http.py", line 454, in hf_raise_for_status + raise _format(RepositoryNotFoundError, message, response) from e +huggingface_hub.errors.RepositoryNotFoundError: 404 Client Error. (Request ID: Root=1-685edee0-1a41c2ec7b492433224a9619;f2e7d363-8101-437f-987b-99efe972cb59) + +Repository Not Found for url: https://huggingface.co/Efficient-Large-Model/VILA1.5-1b/resolve/main/config.json. +Please make sure you specified the correct `repo_id` and `repo_type`. +If you are trying to access a private or gated repo, make sure you are authenticated. + +The above exception was the direct cause of the following exception: + +Traceback (most recent call last): + File "/lustre/fs12/portfolios/nvr/projects/nvr_srl_simpler/users/mmemmel/projects/vila/VILA/llava/train/train_mem.py", line 36, in + train() + File "/lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/VILA/llava/train/train.py", line 247, in train +Traceback (most recent call last): + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_http.py", line 406, in hf_raise_for_status + config = LlavaLlamaConfig.from_pretrained( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 615, in from_pretrained + response.raise_for_status() + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/requests/models.py", line 1024, in raise_for_status + config_dict, kwargs = cls.get_config_dict(pretrained_model_name_or_path, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 644, in get_config_dict + raise HTTPError(http_error_msg, response=self) +requests.exceptions.HTTPError: 404 Client Error: Not Found for url: https://huggingface.co/Efficient-Large-Model/VILA1.5-1b/resolve/main/config.json + +The above exception was the direct cause of the following exception: + +Traceback (most recent call last): + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/utils/hub.py", line 389, in cached_file + config_dict, kwargs = cls._get_config_dict(pretrained_model_name_or_path, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 699, in _get_config_dict + resolved_file = hf_hub_download( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn + resolved_config_file = cached_file( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/utils/hub.py", line 410, in cached_file + return fn(*args, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 860, in hf_hub_download + raise EnvironmentError( +OSError: Efficient-Large-Model/VILA1.5-1b is not a local folder and is not a valid model identifier listed on 'https://huggingface.co/models' +If this is a private repository, make sure to pass a token having permission to this repo either by logging in with `huggingface-cli login` or by passing `token=` + return _hf_hub_download_to_cache_dir( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 967, in _hf_hub_download_to_cache_dir + _raise_on_head_call_error(head_call_error, force_download, local_files_only) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1482, in _raise_on_head_call_error +Traceback (most recent call last): + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_http.py", line 406, in hf_raise_for_status + raise head_call_error + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1374, in _get_metadata_or_catch_error +Traceback (most recent call last): + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_http.py", line 406, in hf_raise_for_status + response.raise_for_status() + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/requests/models.py", line 1024, in raise_for_status + metadata = get_hf_file_metadata( +response.raise_for_status() + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/requests/models.py", line 1024, in raise_for_status + raise HTTPError(http_error_msg, response=self) +requests.exceptions.HTTPError: 404 Client Error: Not Found for url: https://huggingface.co/Efficient-Large-Model/VILA1.5-1b/resolve/main/config.json + +The above exception was the direct cause of the following exception: + +Traceback (most recent call last): + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/utils/hub.py", line 389, in cached_file + raise HTTPError(http_error_msg, response=self) +requests.exceptions.HTTPError: 404 Client Error: Not Found for url: https://huggingface.co/Efficient-Large-Model/VILA1.5-1b/resolve/main/config.json + +The above exception was the direct cause of the following exception: + +Traceback (most recent call last): + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/utils/hub.py", line 389, in cached_file + return fn(*args, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1294, in get_hf_file_metadata + resolved_file = hf_hub_download( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn +Traceback (most recent call last): + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_http.py", line 406, in hf_raise_for_status + resolved_file = hf_hub_download( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn + return fn(*args, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 860, in hf_hub_download + r = _request_wrapper( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 278, in _request_wrapper + return fn(*args, **kwargs) + response = _request_wrapper( File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 860, in hf_hub_download + + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 302, in _request_wrapper + return _hf_hub_download_to_cache_dir( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 967, in _hf_hub_download_to_cache_dir + response.raise_for_status() + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/requests/models.py", line 1024, in raise_for_status + hf_raise_for_status(response) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_http.py", line 454, in hf_raise_for_status + return _hf_hub_download_to_cache_dir( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 967, in _hf_hub_download_to_cache_dir + raise HTTPError(http_error_msg, response=self) +requests.exceptions.HTTPError: 404 Client Error: Not Found for url: https://huggingface.co/Efficient-Large-Model/VILA1.5-1b/resolve/main/config.json + +The above exception was the direct cause of the following exception: + +Traceback (most recent call last): + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/utils/hub.py", line 389, in cached_file + _raise_on_head_call_error(head_call_error, force_download, local_files_only) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1482, in _raise_on_head_call_error + _raise_on_head_call_error(head_call_error, force_download, local_files_only) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1482, in _raise_on_head_call_error + raise head_call_error + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1374, in _get_metadata_or_catch_error + resolved_file = hf_hub_download( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn + raise _format(RepositoryNotFoundError, message, response) from e +huggingface_hub.errors.RepositoryNotFoundError: 404 Client Error. (Request ID: Root=1-685edee0-4859e3482e19be7e3baf2749;058be4f8-fb94-4c6d-8849-da34a21909e7) + +Repository Not Found for url: https://huggingface.co/Efficient-Large-Model/VILA1.5-1b/resolve/main/config.json. +Please make sure you specified the correct `repo_id` and `repo_type`. +If you are trying to access a private or gated repo, make sure you are authenticated. + +The above exception was the direct cause of the following exception: + +Traceback (most recent call last): + File "/lustre/fs12/portfolios/nvr/projects/nvr_srl_simpler/users/mmemmel/projects/vila/VILA/llava/train/train_mem.py", line 36, in +raise head_call_error + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1374, in _get_metadata_or_catch_error + metadata = get_hf_file_metadata( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn + return fn(*args, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 860, in hf_hub_download + metadata = get_hf_file_metadata( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn + train() + File "/lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/VILA/llava/train/train.py", line 247, in train + return fn(*args, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1294, in get_hf_file_metadata + return _hf_hub_download_to_cache_dir( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 967, in _hf_hub_download_to_cache_dir + return fn(*args, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1294, in get_hf_file_metadata + r = _request_wrapper( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 278, in _request_wrapper + response = _request_wrapper( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 302, in _request_wrapper + config = LlavaLlamaConfig.from_pretrained( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 615, in from_pretrained + hf_raise_for_status(response) +_raise_on_head_call_error(head_call_error, force_download, local_files_only) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_http.py", line 454, in hf_raise_for_status + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1482, in _raise_on_head_call_error + r = _request_wrapper( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 278, in _request_wrapper + response = _request_wrapper( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 302, in _request_wrapper + raise head_call_error + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1374, in _get_metadata_or_catch_error + raise _format(RepositoryNotFoundError, message, response) from e +huggingface_hub.errors.RepositoryNotFoundError: 404 Client Error. (Request ID: Root=1-685edee0-5bd327703e48a1b2456476e7;a0e5ac77-99f0-4525-af9b-92d336f744ad) + +Repository Not Found for url: https://huggingface.co/Efficient-Large-Model/VILA1.5-1b/resolve/main/config.json. +Please make sure you specified the correct `repo_id` and `repo_type`. +If you are trying to access a private or gated repo, make sure you are authenticated. + +The above exception was the direct cause of the following exception: + +Traceback (most recent call last): + File "/lustre/fs12/portfolios/nvr/projects/nvr_srl_simpler/users/mmemmel/projects/vila/VILA/llava/train/train_mem.py", line 36, in + config_dict, kwargs = cls.get_config_dict(pretrained_model_name_or_path, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 644, in get_config_dict + hf_raise_for_status(response) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_http.py", line 454, in hf_raise_for_status + metadata = get_hf_file_metadata( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn + config_dict, kwargs = cls._get_config_dict(pretrained_model_name_or_path, **kwargs)train() + + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 699, in _get_config_dict + File "/lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/VILA/llava/train/train.py", line 247, in train + raise _format(RepositoryNotFoundError, message, response) from e +huggingface_hub.errors.RepositoryNotFoundError: 404 Client Error. (Request ID: Root=1-685edee0-7ff9e0ec4487d8b147222794;cfc19306-f4b3-4c87-8234-bab1f9d3f2ef) + +Repository Not Found for url: https://huggingface.co/Efficient-Large-Model/VILA1.5-1b/resolve/main/config.json. +Please make sure you specified the correct `repo_id` and `repo_type`. +If you are trying to access a private or gated repo, make sure you are authenticated. + +The above exception was the direct cause of the following exception: + +Traceback (most recent call last): + File "/lustre/fs12/portfolios/nvr/projects/nvr_srl_simpler/users/mmemmel/projects/vila/VILA/llava/train/train_mem.py", line 36, in + return fn(*args, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1294, in get_hf_file_metadata + resolved_config_file = cached_file( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/utils/hub.py", line 410, in cached_file + train() + File "/lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/VILA/llava/train/train.py", line 247, in train + config = LlavaLlamaConfig.from_pretrained( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 615, in from_pretrained + r = _request_wrapper( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 278, in _request_wrapper + raise EnvironmentError( +OSError: Efficient-Large-Model/VILA1.5-1b is not a local folder and is not a valid model identifier listed on 'https://huggingface.co/models' +If this is a private repository, make sure to pass a token having permission to this repo either by logging in with `huggingface-cli login` or by passing `token=` + config_dict, kwargs = cls.get_config_dict(pretrained_model_name_or_path, **kwargs)response = _request_wrapper( + + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 644, in get_config_dict + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 302, in _request_wrapper + config = LlavaLlamaConfig.from_pretrained( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 615, in from_pretrained + hf_raise_for_status(response) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_http.py", line 454, in hf_raise_for_status + config_dict, kwargs = cls._get_config_dict(pretrained_model_name_or_path, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 699, in _get_config_dict + resolved_config_file = cached_file( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/utils/hub.py", line 410, in cached_file + config_dict, kwargs = cls.get_config_dict(pretrained_model_name_or_path, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 644, in get_config_dict + raise _format(RepositoryNotFoundError, message, response) from e +huggingface_hub.errors.RepositoryNotFoundError: 404 Client Error. (Request ID: Root=1-685edee0-5c4a30cc0f964dea6ada410b;1f7aaf91-5d42-4e24-9dde-e4a06e99f54c) + +Repository Not Found for url: https://huggingface.co/Efficient-Large-Model/VILA1.5-1b/resolve/main/config.json. +Please make sure you specified the correct `repo_id` and `repo_type`. +If you are trying to access a private or gated repo, make sure you are authenticated. + +The above exception was the direct cause of the following exception: + +Traceback (most recent call last): + File "/lustre/fs12/portfolios/nvr/projects/nvr_srl_simpler/users/mmemmel/projects/vila/VILA/llava/train/train_mem.py", line 36, in + raise EnvironmentError( +OSError: Efficient-Large-Model/VILA1.5-1b is not a local folder and is not a valid model identifier listed on 'https://huggingface.co/models' +If this is a private repository, make sure to pass a token having permission to this repo either by logging in with `huggingface-cli login` or by passing `token=` + config_dict, kwargs = cls._get_config_dict(pretrained_model_name_or_path, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 699, in _get_config_dict + train() + File "/lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/VILA/llava/train/train.py", line 247, in train + resolved_config_file = cached_file( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/utils/hub.py", line 410, in cached_file + config = LlavaLlamaConfig.from_pretrained( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 615, in from_pretrained + raise EnvironmentError( +OSError: Efficient-Large-Model/VILA1.5-1b is not a local folder and is not a valid model identifier listed on 'https://huggingface.co/models' +If this is a private repository, make sure to pass a token having permission to this repo either by logging in with `huggingface-cli login` or by passing `token=` + config_dict, kwargs = cls.get_config_dict(pretrained_model_name_or_path, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 644, in get_config_dict + config_dict, kwargs = cls._get_config_dict(pretrained_model_name_or_path, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 699, in _get_config_dict + resolved_config_file = cached_file( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/utils/hub.py", line 410, in cached_file + raise EnvironmentError( +OSError: Efficient-Large-Model/VILA1.5-1b is not a local folder and is not a valid model identifier listed on 'https://huggingface.co/models' +If this is a private repository, make sure to pass a token having permission to this repo either by logging in with `huggingface-cli login` or by passing `token=` +ERROR:torch.distributed.elastic.multiprocessing.api:failed (exitcode: 1) local_rank: 0 (pid: 3265642) of binary: /lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/bin/python3.10 +Traceback (most recent call last): + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/bin/torchrun", line 8, in + sys.exit(main()) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 346, in wrapper + return f(*args, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/torch/distributed/run.py", line 794, in main + run(args) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/torch/distributed/run.py", line 785, in run + elastic_launch( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 134, in __call__ + return launch_agent(self._config, self._entrypoint, list(args)) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 250, in launch_agent + raise ChildFailedError( +torch.distributed.elastic.multiprocessing.errors.ChildFailedError: +============================================================ +llava/train/train_mem.py FAILED +------------------------------------------------------------ +Failures: +[1]: + time : 2025-06-27_11:11:48 + host : batch-block7-00766.cm.cluster + rank : 1 (local_rank: 1) + exitcode : 1 (pid: 3265643) + error_file: + traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html +[2]: + time : 2025-06-27_11:11:48 + host : batch-block7-00766.cm.cluster + rank : 2 (local_rank: 2) + exitcode : 1 (pid: 3265644) + error_file: + traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html +[3]: + time : 2025-06-27_11:11:48 + host : batch-block7-00766.cm.cluster + rank : 3 (local_rank: 3) + exitcode : 1 (pid: 3265645) + error_file: + traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html +[4]: + time : 2025-06-27_11:11:48 + host : batch-block7-00766.cm.cluster + rank : 4 (local_rank: 4) + exitcode : 1 (pid: 3265646) + error_file: + traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html +[5]: + time : 2025-06-27_11:11:48 + host : batch-block7-00766.cm.cluster + rank : 5 (local_rank: 5) + exitcode : 1 (pid: 3265647) + error_file: + traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html +[6]: + time : 2025-06-27_11:11:48 + host : batch-block7-00766.cm.cluster + rank : 6 (local_rank: 6) + exitcode : 1 (pid: 3265648) + error_file: + traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html +[7]: + time : 2025-06-27_11:11:48 + host : batch-block7-00766.cm.cluster + rank : 7 (local_rank: 7) + exitcode : 1 (pid: 3265649) + error_file: + traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html +------------------------------------------------------------ +Root Cause (first observed failure): +[0]: + time : 2025-06-27_11:11:48 + host : batch-block7-00766.cm.cluster + rank : 0 (local_rank: 0) + exitcode : 1 (pid: 3265642) + error_file: + traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html +============================================================ +srun: error: batch-block7-00766: task 0: Exited with exit code 1 +srun: Terminating StepId=9363941.0 +srun: job 9364005 queued and waiting for resources +srun: job 9364005 has been allocated resources +wandb: Currently logged in as: memmelma. Use `wandb login --relogin` to force relogin +MASTER_ADDR=batch-block7-00766 +JobID: 9364005 | Full list: batch-block7-00766 +NETWORK=Efficient-Large-Model/VILA1.5-1b +WARNING:torch.distributed.run: +***************************************** +Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed. +***************************************** +Did not find AutoResume SDK! +Did not find AutoResume SDK! +Did not find AutoResume SDK! +Did not find AutoResume SDK! +Did not find AutoResume SDK! +Did not find AutoResume SDK! +Did not find AutoResume SDK! +Did not find AutoResume SDK! +[2025-06-27 11:13:18,032] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-27 11:13:18,076] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-27 11:13:18,077] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-27 11:13:18,078] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-27 11:13:18,078] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-27 11:13:18,079] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-27 11:13:18,080] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-27 11:13:18,081] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-27 11:13:18,299] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-27 11:13:18,299] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-27 11:13:18,299] [INFO] [comm.py:625:init_distributed] Initializing TorchBackend in DeepSpeed with backend nccl +[2025-06-27 11:13:18,340] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-27 11:13:18,340] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-27 11:13:18,340] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-27 11:13:18,340] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-27 11:13:18,342] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-27 11:13:18,342] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-27 11:13:18,342] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-27 11:13:18,343] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-27 11:13:18,343] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-27 11:13:18,343] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-27 11:13:18,344] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-27 11:13:18,344] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-27 11:13:18,346] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-27 11:13:18,346] [INFO] [comm.py:594:init_distributed] cdb=None +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py:795: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`. + warnings.warn( +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py:795: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`. + warnings.warn( +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py:795: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`. + warnings.warn( +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py:795: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`. + warnings.warn( +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py:795: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`. + warnings.warn( +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py:795: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`. + warnings.warn( +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py:795: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`. + warnings.warn( +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py:795: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`. + warnings.warn( +Traceback (most recent call last): + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_http.py", line 406, in hf_raise_for_status + response.raise_for_status() + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/requests/models.py", line 1024, in raise_for_status + raise HTTPError(http_error_msg, response=self) +requests.exceptions.HTTPError: 404 Client Error: Not Found for url: https://huggingface.co/Efficient-Large-Model/VILA1.5-1b/resolve/main/config.json + +The above exception was the direct cause of the following exception: + +Traceback (most recent call last): + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/utils/hub.py", line 389, in cached_file + resolved_file = hf_hub_download( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn + return fn(*args, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 860, in hf_hub_download + return _hf_hub_download_to_cache_dir( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 967, in _hf_hub_download_to_cache_dir + _raise_on_head_call_error(head_call_error, force_download, local_files_only) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1482, in _raise_on_head_call_error + raise head_call_error + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1374, in _get_metadata_or_catch_error + metadata = get_hf_file_metadata( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn + return fn(*args, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1294, in get_hf_file_metadata + r = _request_wrapper( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 278, in _request_wrapper + response = _request_wrapper( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 302, in _request_wrapper + hf_raise_for_status(response) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_http.py", line 454, in hf_raise_for_status + raise _format(RepositoryNotFoundError, message, response) from e +huggingface_hub.errors.RepositoryNotFoundError: 404 Client Error. (Request ID: Root=1-685edf3e-1da6d8504d1befdf7de1a7a3;dc0d1ac4-45dd-425d-8c88-3ce8a5ba93e0) + +Repository Not Found for url: https://huggingface.co/Efficient-Large-Model/VILA1.5-1b/resolve/main/config.json. +Please make sure you specified the correct `repo_id` and `repo_type`. +If you are trying to access a private or gated repo, make sure you are authenticated. + +The above exception was the direct cause of the following exception: + +Traceback (most recent call last): + File "/lustre/fs12/portfolios/nvr/projects/nvr_srl_simpler/users/mmemmel/projects/vila/VILA/llava/train/train_mem.py", line 36, in + train() + File "/lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/VILA/llava/train/train.py", line 247, in train + config = LlavaLlamaConfig.from_pretrained( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 615, in from_pretrained + config_dict, kwargs = cls.get_config_dict(pretrained_model_name_or_path, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 644, in get_config_dict + config_dict, kwargs = cls._get_config_dict(pretrained_model_name_or_path, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 699, in _get_config_dict + resolved_config_file = cached_file( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/utils/hub.py", line 410, in cached_file + raise EnvironmentError( +OSError: Efficient-Large-Model/VILA1.5-1b is not a local folder and is not a valid model identifier listed on 'https://huggingface.co/models' +If this is a private repository, make sure to pass a token having permission to this repo either by logging in with `huggingface-cli login` or by passing `token=` +Traceback (most recent call last): + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_http.py", line 406, in hf_raise_for_status + response.raise_for_status() + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/requests/models.py", line 1024, in raise_for_status + raise HTTPError(http_error_msg, response=self) +requests.exceptions.HTTPError: 404 Client Error: Not Found for url: https://huggingface.co/Efficient-Large-Model/VILA1.5-1b/resolve/main/config.json + +The above exception was the direct cause of the following exception: + +Traceback (most recent call last): + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/utils/hub.py", line 389, in cached_file + resolved_file = hf_hub_download( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn + return fn(*args, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 860, in hf_hub_download + return _hf_hub_download_to_cache_dir( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 967, in _hf_hub_download_to_cache_dir + _raise_on_head_call_error(head_call_error, force_download, local_files_only) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1482, in _raise_on_head_call_error + raise head_call_error + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1374, in _get_metadata_or_catch_error +Traceback (most recent call last): + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_http.py", line 406, in hf_raise_for_status + metadata = get_hf_file_metadata( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn + return fn(*args, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1294, in get_hf_file_metadata + response.raise_for_status() + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/requests/models.py", line 1024, in raise_for_status + r = _request_wrapper(raise HTTPError(http_error_msg, response=self) + + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 278, in _request_wrapper +requests.exceptions.HTTPError: 404 Client Error: Not Found for url: https://huggingface.co/Efficient-Large-Model/VILA1.5-1b/resolve/main/config.json + +The above exception was the direct cause of the following exception: + +Traceback (most recent call last): + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/utils/hub.py", line 389, in cached_file + response = _request_wrapper( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 302, in _request_wrapper + resolved_file = hf_hub_download( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn + hf_raise_for_status(response) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_http.py", line 454, in hf_raise_for_status + return fn(*args, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 860, in hf_hub_download + raise _format(RepositoryNotFoundError, message, response) from e +huggingface_hub.errors.RepositoryNotFoundError: 404 Client Error. (Request ID: Root=1-685edf3e-17bb7e5a19231f540c017db5;1a3c6981-d5c0-43d1-a129-5f539ccb6bd5) + +Repository Not Found for url: https://huggingface.co/Efficient-Large-Model/VILA1.5-1b/resolve/main/config.json. +Please make sure you specified the correct `repo_id` and `repo_type`. +If you are trying to access a private or gated repo, make sure you are authenticated. + +The above exception was the direct cause of the following exception: + +Traceback (most recent call last): + File "/lustre/fs12/portfolios/nvr/projects/nvr_srl_simpler/users/mmemmel/projects/vila/VILA/llava/train/train_mem.py", line 36, in + return _hf_hub_download_to_cache_dir( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 967, in _hf_hub_download_to_cache_dir +Traceback (most recent call last): + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_http.py", line 406, in hf_raise_for_status + train() + File "/lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/VILA/llava/train/train.py", line 247, in train + _raise_on_head_call_error(head_call_error, force_download, local_files_only) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1482, in _raise_on_head_call_error + response.raise_for_status() + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/requests/models.py", line 1024, in raise_for_status + raise head_call_error + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1374, in _get_metadata_or_catch_error +Traceback (most recent call last): + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_http.py", line 406, in hf_raise_for_status + config = LlavaLlamaConfig.from_pretrained( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 615, in from_pretrained + raise HTTPError(http_error_msg, response=self)metadata = get_hf_file_metadata( + + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn +requests.exceptions.HTTPError: 404 Client Error: Not Found for url: https://huggingface.co/Efficient-Large-Model/VILA1.5-1b/resolve/main/config.json + +The above exception was the direct cause of the following exception: + +Traceback (most recent call last): + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/utils/hub.py", line 389, in cached_file + response.raise_for_status() + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/requests/models.py", line 1024, in raise_for_status + config_dict, kwargs = cls.get_config_dict(pretrained_model_name_or_path, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 644, in get_config_dict + return fn(*args, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1294, in get_hf_file_metadata + raise HTTPError(http_error_msg, response=self) + config_dict, kwargs = cls._get_config_dict(pretrained_model_name_or_path, **kwargs) +requests.exceptions File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 699, in _get_config_dict +.HTTPError: 404 Client Error: Not Found for url: https://huggingface.co/Efficient-Large-Model/VILA1.5-1b/resolve/main/config.json + +The above exception was the direct cause of the following exception: + +Traceback (most recent call last): + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/utils/hub.py", line 389, in cached_file + resolved_file = hf_hub_download( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn + r = _request_wrapper( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 278, in _request_wrapper + resolved_file = hf_hub_download( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn + resolved_config_file = cached_file( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/utils/hub.py", line 410, in cached_file + return fn(*args, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 860, in hf_hub_download + return fn(*args, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 860, in hf_hub_download + response = _request_wrapper( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 302, in _request_wrapper + raise EnvironmentError( +OSError: Efficient-Large-Model/VILA1.5-1b is not a local folder and is not a valid model identifier listed on 'https://huggingface.co/models' +If this is a private repository, make sure to pass a token having permission to this repo either by logging in with `huggingface-cli login` or by passing `token=` + hf_raise_for_status(response) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_http.py", line 454, in hf_raise_for_status + return _hf_hub_download_to_cache_dir( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 967, in _hf_hub_download_to_cache_dir + return _hf_hub_download_to_cache_dir( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 967, in _hf_hub_download_to_cache_dir + _raise_on_head_call_error(head_call_error, force_download, local_files_only) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1482, in _raise_on_head_call_error + raise _format(RepositoryNotFoundError, message, response) from e +huggingface_hub.errors.RepositoryNotFoundError: 404 Client Error. (Request ID: Root=1-685edf3e-72b2ee924653e0f554e1904d;18b72055-4711-482c-b9a5-8cf16e7d071d) + +Repository Not Found for url: https://huggingface.co/Efficient-Large-Model/VILA1.5-1b/resolve/main/config.json. +Please make sure you specified the correct `repo_id` and `repo_type`. +If you are trying to access a private or gated repo, make sure you are authenticated. + +The above exception was the direct cause of the following exception: + +Traceback (most recent call last): + File "/lustre/fs12/portfolios/nvr/projects/nvr_srl_simpler/users/mmemmel/projects/vila/VILA/llava/train/train_mem.py", line 36, in + _raise_on_head_call_error(head_call_error, force_download, local_files_only) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1482, in _raise_on_head_call_error + raise head_call_error + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1374, in _get_metadata_or_catch_error + raise head_call_error + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1374, in _get_metadata_or_catch_error + train() + File "/lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/VILA/llava/train/train.py", line 247, in train + metadata = get_hf_file_metadata( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn + metadata = get_hf_file_metadata( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn + return fn(*args, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1294, in get_hf_file_metadata + return fn(*args, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1294, in get_hf_file_metadata + config = LlavaLlamaConfig.from_pretrained( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 615, in from_pretrained + r = _request_wrapper( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 278, in _request_wrapper + response = _request_wrapper( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 302, in _request_wrapper + config_dict, kwargs = cls.get_config_dict(pretrained_model_name_or_path, **kwargs) + hf_raise_for_status(response) File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 644, in get_config_dict + + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_http.py", line 454, in hf_raise_for_status + r = _request_wrapper( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 278, in _request_wrapper + config_dict, kwargs = cls._get_config_dict(pretrained_model_name_or_path, **kwargs)raise _format(RepositoryNotFoundError, message, response) from e + +huggingface_hub.errors File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 699, in _get_config_dict +.RepositoryNotFoundError: 404 Client Error. (Request ID: Root=1-685edf3e-1001320239cd46f0749cfdd9;1315e5de-2a0a-4ffa-b63e-62ee8cece90b) + +Repository Not Found for url: https://huggingface.co/Efficient-Large-Model/VILA1.5-1b/resolve/main/config.json. +Please make sure you specified the correct `repo_id` and `repo_type`. +If you are trying to access a private or gated repo, make sure you are authenticated. + +The above exception was the direct cause of the following exception: + +Traceback (most recent call last): + File "/lustre/fs12/portfolios/nvr/projects/nvr_srl_simpler/users/mmemmel/projects/vila/VILA/llava/train/train_mem.py", line 36, in + response = _request_wrapper( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 302, in _request_wrapper + train() + File "/lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/VILA/llava/train/train.py", line 247, in train + resolved_config_file = cached_file( + hf_raise_for_status(response) File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/utils/hub.py", line 410, in cached_file + + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_http.py", line 454, in hf_raise_for_status + raise EnvironmentError( +OSError : raise _format(RepositoryNotFoundError, message, response) from e +huggingface_hub.errorsEfficient-Large-Model/VILA1.5-1b is not a local folder and is not a valid model identifier listed on 'https://huggingface.co/models' +If this is a private repository, make sure to pass a token having permission to this repo either by logging in with `huggingface-cli login` or by passing `token=`. +RepositoryNotFoundError: 404 Client Error. (Request ID: Root=1-685edf3e-24154d7c363d3562696aee3d;b4e817eb-25a5-4563-8b0d-796eeabab0cc) + +Repository Not Found for url: https://huggingface.co/Efficient-Large-Model/VILA1.5-1b/resolve/main/config.json. +Please make sure you specified the correct `repo_id` and `repo_type`. +If you are trying to access a private or gated repo, make sure you are authenticated. + +The above exception was the direct cause of the following exception: + +Traceback (most recent call last): + File "/lustre/fs12/portfolios/nvr/projects/nvr_srl_simpler/users/mmemmel/projects/vila/VILA/llava/train/train_mem.py", line 36, in + config = LlavaLlamaConfig.from_pretrained( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 615, in from_pretrained + config_dict, kwargs = cls.get_config_dict(pretrained_model_name_or_path, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 644, in get_config_dict + train() + File "/lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/VILA/llava/train/train.py", line 247, in train + config_dict, kwargs = cls._get_config_dict(pretrained_model_name_or_path, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 699, in _get_config_dict + config = LlavaLlamaConfig.from_pretrained( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 615, in from_pretrained + resolved_config_file = cached_file( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/utils/hub.py", line 410, in cached_file + config_dict, kwargs = cls.get_config_dict(pretrained_model_name_or_path, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 644, in get_config_dict + raise EnvironmentError( +OSError: Efficient-Large-Model/VILA1.5-1b is not a local folder and is not a valid model identifier listed on 'https://huggingface.co/models' +If this is a private repository, make sure to pass a token having permission to this repo either by logging in with `huggingface-cli login` or by passing `token=` + config_dict, kwargs = cls._get_config_dict(pretrained_model_name_or_path, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 699, in _get_config_dict + resolved_config_file = cached_file( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/utils/hub.py", line 410, in cached_file + raise EnvironmentError( +OSError: Efficient-Large-Model/VILA1.5-1b is not a local folder and is not a valid model identifier listed on 'https://huggingface.co/models' +If this is a private repository, make sure to pass a token having permission to this repo either by logging in with `huggingface-cli login` or by passing `token=` +Traceback (most recent call last): + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_http.py", line 406, in hf_raise_for_status + response.raise_for_status() + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/requests/models.py", line 1024, in raise_for_status +Traceback (most recent call last): + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_http.py", line 406, in hf_raise_for_status + raise HTTPError(http_error_msg, response=self) +requests.exceptions.HTTPError: 404 Client Error: Not Found for url: https://huggingface.co/Efficient-Large-Model/VILA1.5-1b/resolve/main/config.json + +The above exception was the direct cause of the following exception: + +Traceback (most recent call last): + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/utils/hub.py", line 389, in cached_file + response.raise_for_status() + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/requests/models.py", line 1024, in raise_for_status + resolved_file = hf_hub_download( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn + raise HTTPError(http_error_msg, response=self) +requests.exceptions.HTTPError: 404 Client Error: Not Found for url: https://huggingface.co/Efficient-Large-Model/VILA1.5-1b/resolve/main/config.json + +The above exception was the direct cause of the following exception: + +Traceback (most recent call last): + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/utils/hub.py", line 389, in cached_file + return fn(*args, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 860, in hf_hub_download + resolved_file = hf_hub_download( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn + return _hf_hub_download_to_cache_dir( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 967, in _hf_hub_download_to_cache_dir + return fn(*args, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 860, in hf_hub_download + _raise_on_head_call_error(head_call_error, force_download, local_files_only) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1482, in _raise_on_head_call_error + return _hf_hub_download_to_cache_dir( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 967, in _hf_hub_download_to_cache_dir + raise head_call_error + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1374, in _get_metadata_or_catch_error + _raise_on_head_call_error(head_call_error, force_download, local_files_only) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1482, in _raise_on_head_call_error + metadata = get_hf_file_metadata( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn + raise head_call_error + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1374, in _get_metadata_or_catch_error + return fn(*args, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1294, in get_hf_file_metadata + metadata = get_hf_file_metadata( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn + r = _request_wrapper( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 278, in _request_wrapper + return fn(*args, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1294, in get_hf_file_metadata + response = _request_wrapper( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 302, in _request_wrapper + hf_raise_for_status(response) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_http.py", line 454, in hf_raise_for_status + r = _request_wrapper( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 278, in _request_wrapper + raise _format(RepositoryNotFoundError, message, response) from e +huggingface_hub.errors.RepositoryNotFoundError: 404 Client Error. (Request ID: Root=1-685edf3e-0650ec27228de45d4fe6e34d;756630ce-8a65-46ae-9d54-ca0eb2b62edb) + +Repository Not Found for url: https://huggingface.co/Efficient-Large-Model/VILA1.5-1b/resolve/main/config.json. +Please make sure you specified the correct `repo_id` and `repo_type`. +If you are trying to access a private or gated repo, make sure you are authenticated. + +The above exception was the direct cause of the following exception: + +Traceback (most recent call last): + File "/lustre/fs12/portfolios/nvr/projects/nvr_srl_simpler/users/mmemmel/projects/vila/VILA/llava/train/train_mem.py", line 36, in + response = _request_wrapper( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 302, in _request_wrapper + train() + File "/lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/VILA/llava/train/train.py", line 247, in train + hf_raise_for_status(response) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_http.py", line 454, in hf_raise_for_status + raise _format(RepositoryNotFoundError, message, response) from e +huggingface_hub.errors.RepositoryNotFoundError: 404 Client Error. (Request ID: Root=1-685edf3e-67223fea08b47a173a665a9d;f040c2d4-bae3-43bb-b383-0aadec87b968) + +Repository Not Found for url: https://huggingface.co/Efficient-Large-Model/VILA1.5-1b/resolve/main/config.json. +Please make sure you specified the correct `repo_id` and `repo_type`. +If you are trying to access a private or gated repo, make sure you are authenticated. + +The above exception was the direct cause of the following exception: + +Traceback (most recent call last): + File "/lustre/fs12/portfolios/nvr/projects/nvr_srl_simpler/users/mmemmel/projects/vila/VILA/llava/train/train_mem.py", line 36, in + config = LlavaLlamaConfig.from_pretrained( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 615, in from_pretrained + train() + File "/lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/VILA/llava/train/train.py", line 247, in train + config_dict, kwargs = cls.get_config_dict(pretrained_model_name_or_path, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 644, in get_config_dict + config = LlavaLlamaConfig.from_pretrained( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 615, in from_pretrained + config_dict, kwargs = cls._get_config_dict(pretrained_model_name_or_path, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 699, in _get_config_dict + config_dict, kwargs = cls.get_config_dict(pretrained_model_name_or_path, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 644, in get_config_dict + resolved_config_file = cached_file( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/utils/hub.py", line 410, in cached_file + config_dict, kwargs = cls._get_config_dict(pretrained_model_name_or_path, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 699, in _get_config_dict + raise EnvironmentError( +OSError: Efficient-Large-Model/VILA1.5-1b is not a local folder and is not a valid model identifier listed on 'https://huggingface.co/models' +If this is a private repository, make sure to pass a token having permission to this repo either by logging in with `huggingface-cli login` or by passing `token=` + resolved_config_file = cached_file( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/utils/hub.py", line 410, in cached_file + raise EnvironmentError( +OSError: Efficient-Large-Model/VILA1.5-1b is not a local folder and is not a valid model identifier listed on 'https://huggingface.co/models' +If this is a private repository, make sure to pass a token having permission to this repo either by logging in with `huggingface-cli login` or by passing `token=` +Traceback (most recent call last): + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_http.py", line 406, in hf_raise_for_status + response.raise_for_status() + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/requests/models.py", line 1024, in raise_for_status + raise HTTPError(http_error_msg, response=self) +requests.exceptions.HTTPError: 404 Client Error: Not Found for url: https://huggingface.co/Efficient-Large-Model/VILA1.5-1b/resolve/main/config.json + +The above exception was the direct cause of the following exception: + +Traceback (most recent call last): + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/utils/hub.py", line 389, in cached_file + resolved_file = hf_hub_download( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn + return fn(*args, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 860, in hf_hub_download + return _hf_hub_download_to_cache_dir( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 967, in _hf_hub_download_to_cache_dir + _raise_on_head_call_error(head_call_error, force_download, local_files_only) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1482, in _raise_on_head_call_error + raise head_call_error + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1374, in _get_metadata_or_catch_error + metadata = get_hf_file_metadata( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn + return fn(*args, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1294, in get_hf_file_metadata + r = _request_wrapper( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 278, in _request_wrapper + response = _request_wrapper( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 302, in _request_wrapper + hf_raise_for_status(response) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_http.py", line 454, in hf_raise_for_status + raise _format(RepositoryNotFoundError, message, response) from e +huggingface_hub.errors.RepositoryNotFoundError: 404 Client Error. (Request ID: Root=1-685edf3e-78e8aba862994a836392922c;27752d26-dac9-42b2-b557-f6390b6e1d5b) + +Repository Not Found for url: https://huggingface.co/Efficient-Large-Model/VILA1.5-1b/resolve/main/config.json. +Please make sure you specified the correct `repo_id` and `repo_type`. +If you are trying to access a private or gated repo, make sure you are authenticated. + +The above exception was the direct cause of the following exception: + +Traceback (most recent call last): + File "/lustre/fs12/portfolios/nvr/projects/nvr_srl_simpler/users/mmemmel/projects/vila/VILA/llava/train/train_mem.py", line 36, in + train() + File "/lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/VILA/llava/train/train.py", line 247, in train + config = LlavaLlamaConfig.from_pretrained( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 615, in from_pretrained + config_dict, kwargs = cls.get_config_dict(pretrained_model_name_or_path, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 644, in get_config_dict + config_dict, kwargs = cls._get_config_dict(pretrained_model_name_or_path, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/configuration_utils.py", line 699, in _get_config_dict + resolved_config_file = cached_file( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/transformers/utils/hub.py", line 410, in cached_file + raise EnvironmentError( +OSError: Efficient-Large-Model/VILA1.5-1b is not a local folder and is not a valid model identifier listed on 'https://huggingface.co/models' +If this is a private repository, make sure to pass a token having permission to this repo either by logging in with `huggingface-cli login` or by passing `token=` +ERROR:torch.distributed.elastic.multiprocessing.api:failed (exitcode: 1) local_rank: 0 (pid: 3268562) of binary: /lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/bin/python3.10 +Traceback (most recent call last): + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/bin/torchrun", line 8, in + sys.exit(main()) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 346, in wrapper + return f(*args, **kwargs) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/torch/distributed/run.py", line 794, in main + run(args) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/torch/distributed/run.py", line 785, in run + elastic_launch( + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 134, in __call__ + return launch_agent(self._config, self._entrypoint, list(args)) + File "/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 250, in launch_agent + raise ChildFailedError( +torch.distributed.elastic.multiprocessing.errors.ChildFailedError: +============================================================ +llava/train/train_mem.py FAILED +------------------------------------------------------------ +Failures: +[1]: + time : 2025-06-27_11:13:20 + host : batch-block7-00766.cm.cluster + rank : 1 (local_rank: 1) + exitcode : 1 (pid: 3268563) + error_file: + traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html +[2]: + time : 2025-06-27_11:13:20 + host : batch-block7-00766.cm.cluster + rank : 2 (local_rank: 2) + exitcode : 1 (pid: 3268564) + error_file: + traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html +[3]: + time : 2025-06-27_11:13:20 + host : batch-block7-00766.cm.cluster + rank : 3 (local_rank: 3) + exitcode : 1 (pid: 3268565) + error_file: + traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html +[4]: + time : 2025-06-27_11:13:20 + host : batch-block7-00766.cm.cluster + rank : 4 (local_rank: 4) + exitcode : 1 (pid: 3268566) + error_file: + traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html +[5]: + time : 2025-06-27_11:13:20 + host : batch-block7-00766.cm.cluster + rank : 5 (local_rank: 5) + exitcode : 1 (pid: 3268567) + error_file: + traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html +[6]: + time : 2025-06-27_11:13:20 + host : batch-block7-00766.cm.cluster + rank : 6 (local_rank: 6) + exitcode : 1 (pid: 3268568) + error_file: + traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html +[7]: + time : 2025-06-27_11:13:20 + host : batch-block7-00766.cm.cluster + rank : 7 (local_rank: 7) + exitcode : 1 (pid: 3268569) + error_file: + traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html +------------------------------------------------------------ +Root Cause (first observed failure): +[0]: + time : 2025-06-27_11:13:20 + host : batch-block7-00766.cm.cluster + rank : 0 (local_rank: 0) + exitcode : 1 (pid: 3268562) + error_file: + traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html +============================================================ +srun: error: batch-block7-00766: task 0: Exited with exit code 1 +srun: Terminating StepId=9364005.0 +srun: job 9364013 queued and waiting for resources +srun: job 9364013 has been allocated resources +wandb: Currently logged in as: memmelma. Use `wandb login --relogin` to force relogin +MASTER_ADDR=batch-block7-00766 +JobID: 9364013 | Full list: batch-block7-00766 +NETWORK=Efficient-Large-Model/VILA1.5-3b +WARNING:torch.distributed.run: +***************************************** +Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed. +***************************************** +Did not find AutoResume SDK! +Did not find AutoResume SDK! +Did not find AutoResume SDK! +Did not find AutoResume SDK! +Did not find AutoResume SDK! +Did not find AutoResume SDK! +Did not find AutoResume SDK! +Did not find AutoResume SDK! +[2025-06-27 11:14:18,375] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-27 11:14:18,376] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-27 11:14:18,486] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-27 11:14:18,487] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-27 11:14:18,487] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-27 11:14:18,488] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-27 11:14:18,496] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-27 11:14:18,515] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-27 11:14:18,638] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-27 11:14:18,638] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-27 11:14:18,640] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-27 11:14:18,640] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-27 11:14:18,640] [INFO] [comm.py:625:init_distributed] Initializing TorchBackend in DeepSpeed with backend nccl +[2025-06-27 11:14:18,744] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-27 11:14:18,744] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-27 11:14:18,744] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-27 11:14:18,744] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-27 11:14:18,746] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-27 11:14:18,746] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-27 11:14:18,760] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-27 11:14:18,760] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-27 11:14:18,761] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-27 11:14:18,761] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-27 11:14:18,767] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-27 11:14:18,768] [INFO] [comm.py:594:init_distributed] cdb=None +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py:795: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`. + warnings.warn( +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py:795: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`. + warnings.warn( +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py:795: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`. + warnings.warn( +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py:795: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`. + warnings.warn( +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py:795: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`. + warnings.warn( +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py:795: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`. + warnings.warn( +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py:795: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`. + warnings.warn( +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/huggingface_hub/file_download.py:795: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`. + warnings.warn( + Fetching 17 files: 0%| | 0/17 [00:00 4096). Running this sequence through the model will result in indexing errors + 29%|██▊ | 3358/11728 [1:47:22<13:14:40, 5.70s/it] {'loss': 0.4887, 'learning_rate': 1.6747753704663586e-05, 'epoch': 0.29} + 29%|██▊ | 3358/11728 [1:47:22<13:14:40, 5.70s/it] 29%|██▊ | 3359/11728 [1:47:27<13:23:19, 5.76s/it] {'loss': 0.5156, 'learning_rate': 1.674571532487217e-05, 'epoch': 0.29} + 29%|██▊ | 3359/11728 [1:47:27<13:23:19, 5.76s/it] 29%|██▊ | 3360/11728 [1:47:33<13:25:22, 5.77s/it] {'loss': 0.4967, 'learning_rate': 1.674367643062434e-05, 'epoch': 0.29} + 29%|██▊ | 3360/11728 [1:47:33<13:25:22, 5.77s/it] 29%|██▊ | 3361/11728 [1:47:39<13:27:29, 5.79s/it] {'loss': 0.4782, 'learning_rate': 1.6741637022075593e-05, 'epoch': 0.29} + 29%|██▊ | 3361/11728 [1:47:39<13:27:29, 5.79s/it] 29%|██▊ | 3362/11728 [1:47:45<13:28:18, 5.80s/it] {'loss': 0.4934, 'learning_rate': 1.6739597099381457e-05, 'epoch': 0.29} + 29%|██▊ | 3362/11728 [1:47:45<13:28:18, 5.80s/it] 29%|██▊ | 3363/11728 [1:47:51<13:32:47, 5.83s/it] {'loss': 0.4974, 'learning_rate': 1.6737556662697514e-05, 'epoch': 0.29} + 29%|██▊ | 3363/11728 [1:47:51<13:32:47, 5.83s/it] 29%|██▊ | 3364/11728 [1:47:57<13:48:41, 5.94s/it] {'loss': 0.5045, 'learning_rate': 1.673551571217937e-05, 'epoch': 0.29} + 29%|██▊ | 3364/11728 [1:47:57<13:48:41, 5.94s/it] 29%|██▊ | 3365/11728 [1:48:03<13:44:06, 5.91s/it] {'loss': 0.5027, 'learning_rate': 1.6733474247982675e-05, 'epoch': 0.29} + 29%|██▊ | 3365/11728 [1:48:03<13:44:06, 5.91s/it] 29%|██▊ | 3366/11728 [1:48:09<13:48:54, 5.95s/it] {'loss': 0.5273, 'learning_rate': 1.6731432270263126e-05, 'epoch': 0.29} + 29%|██▊ | 3366/11728 [1:48:09<13:48:54, 5.95s/it] 29%|██▊ | 3367/11728 [1:48:15<13:53:21, 5.98s/it] {'loss': 0.4873, 'learning_rate': 1.6729389779176446e-05, 'epoch': 0.29} + 29%|██▊ | 3367/11728 [1:48:15<13:53:21, 5.98s/it] 29%|██▊ | 3368/11728 [1:48:21<13:41:44, 5.90s/it] {'loss': 0.4849, 'learning_rate': 1.672734677487841e-05, 'epoch': 0.29} + 29%|██▊ | 3368/11728 [1:48:21<13:41:44, 5.90s/it] 29%|██▊ | 3369/11728 [1:48:27<13:44:15, 5.92s/it] {'loss': 0.5023, 'learning_rate': 1.672530325752482e-05, 'epoch': 0.29} + 29%|██▊ | 3369/11728 [1:48:27<13:44:15, 5.92s/it] 29%|██▊ | 3370/11728 [1:48:32<13:28:41, 5.81s/it] {'loss': 0.4888, 'learning_rate': 1.6723259227271527e-05, 'epoch': 0.29} + 29%|██▊ | 3370/11728 [1:48:32<13:28:41, 5.81s/it] 29%|██▊ | 3371/11728 [1:48:38<13:30:33, 5.82s/it] {'loss': 0.4845, 'learning_rate': 1.672121468427442e-05, 'epoch': 0.29} + 29%|██▊ | 3371/11728 [1:48:38<13:30:33, 5.82s/it] 29%|██▉ | 3372/11728 [1:48:44<13:26:01, 5.79s/it] {'loss': 0.4954, 'learning_rate': 1.671916962868942e-05, 'epoch': 0.29} + 29%|██▉ | 3372/11728 [1:48:44<13:26:01, 5.79s/it] 29%|██▉ | 3373/11728 [1:48:50<13:33:20, 5.84s/it] {'loss': 0.5072, 'learning_rate': 1.671712406067249e-05, 'epoch': 0.29} + 29%|██▉ | 3373/11728 [1:48:50<13:33:20, 5.84s/it]/lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/VILA/llava/model/llava_arch.py:397: UserWarning: Inputs truncated! + warnings.warn("Inputs truncated!") + 29%|██▉ | 3374/11728 [1:48:56<13:41:32, 5.90s/it] {'loss': 0.4873, 'learning_rate': 1.6715077980379636e-05, 'epoch': 0.29} + 29%|██▉ | 3374/11728 [1:48:56<13:41:32, 5.90s/it] 29%|██▉ | 3375/11728 [1:49:02<13:36:36, 5.87s/it] {'loss': 0.4931, 'learning_rate': 1.6713031387966903e-05, 'epoch': 0.29} + 29%|██▉ | 3375/11728 [1:49:02<13:36:36, 5.87s/it] 29%|██▉ | 3376/11728 [1:49:07<13:30:51, 5.83s/it] {'loss': 0.4837, 'learning_rate': 1.671098428359037e-05, 'epoch': 0.29} + 29%|██▉ | 3376/11728 [1:49:07<13:30:51, 5.83s/it] 29%|██▉ | 3377/11728 [1:49:13<13:25:21, 5.79s/it] {'loss': 0.4901, 'learning_rate': 1.6708936667406157e-05, 'epoch': 0.29} + 29%|██▉ | 3377/11728 [1:49:13<13:25:21, 5.79s/it] 29%|██▉ | 3378/11728 [1:49:19<13:18:16, 5.74s/it] {'loss': 0.4878, 'learning_rate': 1.6706888539570424e-05, 'epoch': 0.29} + 29%|██▉ | 3378/11728 [1:49:19<13:18:16, 5.74s/it] 29%|██▉ | 3379/11728 [1:49:24<13:05:38, 5.65s/it] {'loss': 0.4936, 'learning_rate': 1.6704839900239372e-05, 'epoch': 0.29} + 29%|██▉ | 3379/11728 [1:49:24<13:05:38, 5.65s/it] 29%|██▉ | 3380/11728 [1:49:30<13:07:53, 5.66s/it] {'loss': 0.4809, 'learning_rate': 1.6702790749569238e-05, 'epoch': 0.29} + 29%|██▉ | 3380/11728 [1:49:30<13:07:53, 5.66s/it] 29%|██▉ | 3381/11728 [1:49:36<13:15:03, 5.72s/it] {'loss': 0.4792, 'learning_rate': 1.6700741087716296e-05, 'epoch': 0.29} + 29%|██▉ | 3381/11728 [1:49:36<13:15:03, 5.72s/it] 29%|██▉ | 3382/11728 [1:49:42<13:30:30, 5.83s/it] {'loss': 0.5043, 'learning_rate': 1.6698690914836863e-05, 'epoch': 0.29} + 29%|██▉ | 3382/11728 [1:49:42<13:30:30, 5.83s/it] 29%|██▉ | 3383/11728 [1:49:48<13:32:13, 5.84s/it] {'loss': 0.4839, 'learning_rate': 1.6696640231087296e-05, 'epoch': 0.29} + 29%|██▉ | 3383/11728 [1:49:48<13:32:13, 5.84s/it] 29%|██▉ | 3384/11728 [1:49:54<13:45:31, 5.94s/it] {'loss': 0.4919, 'learning_rate': 1.6694589036623988e-05, 'epoch': 0.29} + 29%|██▉ | 3384/11728 [1:49:54<13:45:31, 5.94s/it] 29%|██▉ | 3385/11728 [1:49:59<13:38:28, 5.89s/it] {'loss': 0.488, 'learning_rate': 1.6692537331603374e-05, 'epoch': 0.29} + 29%|██▉ | 3385/11728 [1:49:59<13:38:28, 5.89s/it] 29%|██▉ | 3386/11728 [1:50:05<13:25:43, 5.80s/it] {'loss': 0.4939, 'learning_rate': 1.6690485116181917e-05, 'epoch': 0.29} + 29%|██▉ | 3386/11728 [1:50:05<13:25:43, 5.80s/it] 29%|██▉ | 3387/11728 [1:50:11<13:39:13, 5.89s/it] {'loss': 0.4763, 'learning_rate': 1.6688432390516136e-05, 'epoch': 0.29} + 29%|██▉ | 3387/11728 [1:50:11<13:39:13, 5.89s/it] 29%|██▉ | 3388/11728 [1:50:17<13:35:27, 5.87s/it] {'loss': 0.5006, 'learning_rate': 1.6686379154762575e-05, 'epoch': 0.29} + 29%|██▉ | 3388/11728 [1:50:17<13:35:27, 5.87s/it] 29%|██▉ | 3389/11728 [1:50:23<13:31:11, 5.84s/it] {'loss': 0.4848, 'learning_rate': 1.668432540907783e-05, 'epoch': 0.29} + 29%|██▉ | 3389/11728 [1:50:23<13:31:11, 5.84s/it] 29%|██▉ | 3390/11728 [1:50:29<13:51:44, 5.99s/it] {'loss': 0.4755, 'learning_rate': 1.6682271153618517e-05, 'epoch': 0.29} + 29%|██▉ | 3390/11728 [1:50:29<13:51:44, 5.99s/it] 29%|██▉ | 3391/11728 [1:50:35<13:55:33, 6.01s/it] {'loss': 0.5049, 'learning_rate': 1.668021638854131e-05, 'epoch': 0.29} + 29%|██▉ | 3391/11728 [1:50:35<13:55:33, 6.01s/it] 29%|██▉ | 3392/11728 [1:50:41<13:50:57, 5.98s/it] {'loss': 0.5004, 'learning_rate': 1.6678161114002916e-05, 'epoch': 0.29} + 29%|██▉ | 3392/11728 [1:50:41<13:50:57, 5.98s/it] 29%|██▉ | 3393/11728 [1:50:47<13:52:02, 5.99s/it] {'loss': 0.4785, 'learning_rate': 1.667610533016007e-05, 'epoch': 0.29} + 29%|██▉ | 3393/11728 [1:50:47<13:52:02, 5.99s/it] 29%|██▉ | 3394/11728 [1:50:53<13:43:02, 5.93s/it] {'loss': 0.5055, 'learning_rate': 1.6674049037169565e-05, 'epoch': 0.29} + 29%|██▉ | 3394/11728 [1:50:53<13:43:02, 5.93s/it] 29%|██▉ | 3395/11728 [1:50:58<13:30:36, 5.84s/it] {'loss': 0.4771, 'learning_rate': 1.6671992235188212e-05, 'epoch': 0.29} + 29%|██▉ | 3395/11728 [1:50:58<13:30:36, 5.84s/it] 29%|██▉ | 3396/11728 [1:51:04<13:35:08, 5.87s/it] {'loss': 0.4854, 'learning_rate': 1.666993492437288e-05, 'epoch': 0.29} + 29%|██▉ | 3396/11728 [1:51:04<13:35:08, 5.87s/it] 29%|██▉ | 3397/11728 [1:51:10<13:36:01, 5.88s/it] {'loss': 0.4852, 'learning_rate': 1.666787710488046e-05, 'epoch': 0.29} + 29%|██▉ | 3397/11728 [1:51:10<13:36:01, 5.88s/it] 29%|██▉ | 3398/11728 [1:51:16<13:25:43, 5.80s/it] {'loss': 0.5219, 'learning_rate': 1.66658187768679e-05, 'epoch': 0.29} + 29%|██▉ | 3398/11728 [1:51:16<13:25:43, 5.80s/it] 29%|██▉ | 3399/11728 [1:51:22<13:17:10, 5.74s/it] {'loss': 0.494, 'learning_rate': 1.6663759940492166e-05, 'epoch': 0.29} + 29%|██▉ | 3399/11728 [1:51:22<13:17:10, 5.74s/it]2 AutoResumeHook: Checking whether to suspend...1 + AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +0 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... + 29%|██▉ | 3400/11728 [1:51:28<13:33:25, 5.86s/it]6 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... + {'loss': 0.5, 'learning_rate': 1.6661700595910284e-05, 'epoch': 0.29} + 29%|██▉ | 3400/11728 [1:51:28<13:33:25, 5.86s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-3400/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-3400/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-3400/mm_projector +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/torch/nn/modules/module.py:1802: UserWarning: Positional args are being deprecated, use kwargs instead. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details. + warnings.warn( + 29%|██▉ | 3401/11728 [1:51:59<31:11:10, 13.48s/it] {'loss': 0.488, 'learning_rate': 1.66596407432793e-05, 'epoch': 0.29} + 29%|██▉ | 3401/11728 [1:51:59<31:11:10, 13.48s/it] 29%|██▉ | 3402/11728 [1:52:05<25:48:50, 11.16s/it] {'loss': 0.4824, 'learning_rate': 1.6657580382756306e-05, 'epoch': 0.29} + 29%|██▉ | 3402/11728 [1:52:05<25:48:50, 11.16s/it] 29%|██▉ | 3403/11728 [1:52:11<22:13:39, 9.61s/it] {'loss': 0.4928, 'learning_rate': 1.6655519514498443e-05, 'epoch': 0.29} + 29%|██▉ | 3403/11728 [1:52:11<22:13:39, 9.61s/it] 29%|██▉ | 3404/11728 [1:52:16<19:31:40, 8.45s/it] {'loss': 0.4834, 'learning_rate': 1.6653458138662872e-05, 'epoch': 0.29} + 29%|██▉ | 3404/11728 [1:52:16<19:31:40, 8.45s/it] 29%|██▉ | 3405/11728 [1:52:22<17:48:58, 7.71s/it] {'loss': 0.5008, 'learning_rate': 1.665139625540681e-05, 'epoch': 0.29} + 29%|██▉ | 3405/11728 [1:52:22<17:48:58, 7.71s/it] 29%|██▉ | 3406/11728 [1:52:28<16:36:57, 7.19s/it] {'loss': 0.4711, 'learning_rate': 1.6649333864887497e-05, 'epoch': 0.29} + 29%|██▉ | 3406/11728 [1:52:28<16:36:57, 7.19s/it] 29%|██▉ | 3407/11728 [1:52:34<15:37:02, 6.76s/it] {'loss': 0.5186, 'learning_rate': 1.6647270967262227e-05, 'epoch': 0.29} + 29%|██▉ | 3407/11728 [1:52:34<15:37:02, 6.76s/it] 29%|██▉ | 3408/11728 [1:52:40<15:09:48, 6.56s/it] {'loss': 0.4872, 'learning_rate': 1.664520756268832e-05, 'epoch': 0.29} + 29%|██▉ | 3408/11728 [1:52:40<15:09:48, 6.56s/it] 29%|██▉ | 3409/11728 [1:52:46<14:46:42, 6.40s/it] {'loss': 0.5094, 'learning_rate': 1.664314365132314e-05, 'epoch': 0.29} + 29%|██▉ | 3409/11728 [1:52:46<14:46:42, 6.40s/it] 29%|██▉ | 3410/11728 [1:52:52<14:19:27, 6.20s/it] {'loss': 0.4886, 'learning_rate': 1.664107923332409e-05, 'epoch': 0.29} + 29%|██▉ | 3410/11728 [1:52:52<14:19:27, 6.20s/it] 29%|██▉ | 3411/11728 [1:52:58<14:07:39, 6.12s/it] {'loss': 0.5191, 'learning_rate': 1.6639014308848615e-05, 'epoch': 0.29} + 29%|██▉ | 3411/11728 [1:52:58<14:07:39, 6.12s/it] 29%|██▉ | 3412/11728 [1:53:04<14:02:40, 6.08s/it] {'loss': 0.5101, 'learning_rate': 1.6636948878054192e-05, 'epoch': 0.29} + 29%|██▉ | 3412/11728 [1:53:04<14:02:40, 6.08s/it] 29%|██▉ | 3413/11728 [1:53:10<13:54:20, 6.02s/it] {'loss': 0.4758, 'learning_rate': 1.6634882941098338e-05, 'epoch': 0.29} + 29%|██▉ | 3413/11728 [1:53:10<13:54:20, 6.02s/it] 29%|██▉ | 3414/11728 [1:53:16<13:43:42, 5.94s/it] {'loss': 0.4911, 'learning_rate': 1.663281649813861e-05, 'epoch': 0.29} + 29%|██▉ | 3414/11728 [1:53:16<13:43:42, 5.94s/it] 29%|██▉ | 3415/11728 [1:53:21<13:29:50, 5.85s/it] {'loss': 0.4835, 'learning_rate': 1.6630749549332607e-05, 'epoch': 0.29} + 29%|██▉ | 3415/11728 [1:53:21<13:29:50, 5.85s/it] 29%|██▉ | 3416/11728 [1:53:27<13:25:43, 5.82s/it] {'loss': 0.525, 'learning_rate': 1.662868209483796e-05, 'epoch': 0.29} + 29%|██▉ | 3416/11728 [1:53:27<13:25:43, 5.82s/it] 29%|██▉ | 3417/11728 [1:53:33<13:32:51, 5.87s/it] {'loss': 0.5099, 'learning_rate': 1.6626614134812337e-05, 'epoch': 0.29} + 29%|██▉ | 3417/11728 [1:53:33<13:32:51, 5.87s/it] 29%|██▉ | 3418/11728 [1:53:39<13:27:09, 5.83s/it] {'loss': 0.496, 'learning_rate': 1.662454566941346e-05, 'epoch': 0.29} + 29%|██▉ | 3418/11728 [1:53:39<13:27:09, 5.83s/it] 29%|██▉ | 3419/11728 [1:53:44<13:16:09, 5.75s/it] {'loss': 0.4779, 'learning_rate': 1.6622476698799074e-05, 'epoch': 0.29} + 29%|██▉ | 3419/11728 [1:53:44<13:16:09, 5.75s/it] 29%|██▉ | 3420/11728 [1:53:50<13:19:40, 5.78s/it] {'loss': 0.5078, 'learning_rate': 1.6620407223126967e-05, 'epoch': 0.29} + 29%|██▉ | 3420/11728 [1:53:50<13:19:40, 5.78s/it] 29%|██▉ | 3421/11728 [1:53:56<13:22:57, 5.80s/it] {'loss': 0.4936, 'learning_rate': 1.6618337242554963e-05, 'epoch': 0.29} + 29%|██▉ | 3421/11728 [1:53:56<13:22:57, 5.80s/it] 29%|██▉ | 3422/11728 [1:54:02<13:28:56, 5.84s/it] {'loss': 0.4719, 'learning_rate': 1.6616266757240932e-05, 'epoch': 0.29} + 29%|██▉ | 3422/11728 [1:54:02<13:28:56, 5.84s/it] 29%|██▉ | 3423/11728 [1:54:07<13:18:57, 5.77s/it] {'loss': 0.4843, 'learning_rate': 1.6614195767342777e-05, 'epoch': 0.29} + 29%|██▉ | 3423/11728 [1:54:07<13:18:57, 5.77s/it] 29%|██▉ | 3424/11728 [1:54:13<13:21:22, 5.79s/it] {'loss': 0.5118, 'learning_rate': 1.661212427301844e-05, 'epoch': 0.29} + 29%|██▉ | 3424/11728 [1:54:13<13:21:22, 5.79s/it] 29%|██▉ | 3425/11728 [1:54:19<13:34:49, 5.89s/it] {'loss': 0.4855, 'learning_rate': 1.6610052274425896e-05, 'epoch': 0.29} + 29%|██▉ | 3425/11728 [1:54:19<13:34:49, 5.89s/it] 29%|██▉ | 3426/11728 [1:54:25<13:29:56, 5.85s/it] {'loss': 0.4627, 'learning_rate': 1.6607979771723173e-05, 'epoch': 0.29} + 29%|██▉ | 3426/11728 [1:54:25<13:29:56, 5.85s/it] 29%|██▉ | 3427/11728 [1:54:31<13:17:04, 5.76s/it] {'loss': 0.493, 'learning_rate': 1.6605906765068326e-05, 'epoch': 0.29} + 29%|██▉ | 3427/11728 [1:54:31<13:17:04, 5.76s/it] 29%|██▉ | 3428/11728 [1:54:36<13:18:04, 5.77s/it] {'loss': 0.5094, 'learning_rate': 1.660383325461945e-05, 'epoch': 0.29} + 29%|██▉ | 3428/11728 [1:54:36<13:18:04, 5.77s/it] 29%|██▉ | 3429/11728 [1:54:42<13:21:53, 5.80s/it] {'loss': 0.4907, 'learning_rate': 1.660175924053468e-05, 'epoch': 0.29} + 29%|██▉ | 3429/11728 [1:54:42<13:21:53, 5.80s/it] 29%|██▉ | 3430/11728 [1:54:48<13:15:41, 5.75s/it] {'loss': 0.4962, 'learning_rate': 1.6599684722972188e-05, 'epoch': 0.29} + 29%|██▉ | 3430/11728 [1:54:48<13:15:41, 5.75s/it] 29%|██▉ | 3431/11728 [1:54:54<13:19:26, 5.78s/it] {'loss': 0.4804, 'learning_rate': 1.6597609702090184e-05, 'epoch': 0.29} + 29%|██▉ | 3431/11728 [1:54:54<13:19:26, 5.78s/it] 29%|██▉ | 3432/11728 [1:55:00<13:20:29, 5.79s/it] {'loss': 0.498, 'learning_rate': 1.6595534178046925e-05, 'epoch': 0.29} + 29%|██▉ | 3432/11728 [1:55:00<13:20:29, 5.79s/it] 29%|██▉ | 3433/11728 [1:55:06<13:29:29, 5.86s/it] {'loss': 0.4844, 'learning_rate': 1.659345815100069e-05, 'epoch': 0.29} + 29%|██▉ | 3433/11728 [1:55:06<13:29:29, 5.86s/it] 29%|██▉ | 3434/11728 [1:55:11<13:18:19, 5.78s/it] {'loss': 0.5161, 'learning_rate': 1.659138162110981e-05, 'epoch': 0.29} + 29%|██▉ | 3434/11728 [1:55:11<13:18:19, 5.78s/it] 29%|██▉ | 3435/11728 [1:55:17<13:09:13, 5.71s/it] {'loss': 0.4909, 'learning_rate': 1.6589304588532652e-05, 'epoch': 0.29} + 29%|██▉ | 3435/11728 [1:55:17<13:09:13, 5.71s/it] 29%|██▉ | 3436/11728 [1:55:22<13:07:17, 5.70s/it] {'loss': 0.4828, 'learning_rate': 1.6587227053427613e-05, 'epoch': 0.29} + 29%|██▉ | 3436/11728 [1:55:22<13:07:17, 5.70s/it] 29%|██▉ | 3437/11728 [1:55:28<12:59:43, 5.64s/it] {'loss': 0.4675, 'learning_rate': 1.658514901595314e-05, 'epoch': 0.29} + 29%|██▉ | 3437/11728 [1:55:28<12:59:43, 5.64s/it] 29%|██▉ | 3438/11728 [1:55:34<13:04:59, 5.68s/it] {'loss': 0.4981, 'learning_rate': 1.6583070476267712e-05, 'epoch': 0.29} + 29%|██▉ | 3438/11728 [1:55:34<13:04:59, 5.68s/it] 29%|██▉ | 3439/11728 [1:55:40<13:14:37, 5.75s/it] {'loss': 0.4904, 'learning_rate': 1.658099143452984e-05, 'epoch': 0.29} + 29%|██▉ | 3439/11728 [1:55:40<13:14:37, 5.75s/it] 29%|██▉ | 3440/11728 [1:55:45<13:17:16, 5.77s/it] {'loss': 0.4966, 'learning_rate': 1.6578911890898095e-05, 'epoch': 0.29} + 29%|██▉ | 3440/11728 [1:55:45<13:17:16, 5.77s/it] 29%|██▉ | 3441/11728 [1:55:51<13:21:22, 5.80s/it] {'loss': 0.5002, 'learning_rate': 1.6576831845531058e-05, 'epoch': 0.29} + 29%|██▉ | 3441/11728 [1:55:51<13:21:22, 5.80s/it] 29%|██▉ | 3442/11728 [1:55:57<13:15:41, 5.76s/it] {'loss': 0.467, 'learning_rate': 1.657475129858737e-05, 'epoch': 0.29} + 29%|██▉ | 3442/11728 [1:55:57<13:15:41, 5.76s/it] 29%|██▉ | 3443/11728 [1:56:03<13:26:46, 5.84s/it] {'loss': 0.4815, 'learning_rate': 1.6572670250225695e-05, 'epoch': 0.29} + 29%|██▉ | 3443/11728 [1:56:03<13:26:46, 5.84s/it] 29%|██▉ | 3444/11728 [1:56:09<13:21:07, 5.80s/it] {'loss': 0.5161, 'learning_rate': 1.657058870060475e-05, 'epoch': 0.29} + 29%|██▉ | 3444/11728 [1:56:09<13:21:07, 5.80s/it] 29%|██▉ | 3445/11728 [1:56:15<13:25:40, 5.84s/it] {'loss': 0.4943, 'learning_rate': 1.6568506649883276e-05, 'epoch': 0.29} + 29%|██▉ | 3445/11728 [1:56:15<13:25:40, 5.84s/it] 29%|██▉ | 3446/11728 [1:56:21<13:25:20, 5.83s/it] {'loss': 0.4995, 'learning_rate': 1.6566424098220064e-05, 'epoch': 0.29} + 29%|██▉ | 3446/11728 [1:56:21<13:25:20, 5.83s/it] 29%|██▉ | 3447/11728 [1:56:26<13:24:49, 5.83s/it] {'loss': 0.5063, 'learning_rate': 1.656434104577394e-05, 'epoch': 0.29} + 29%|██▉ | 3447/11728 [1:56:26<13:24:49, 5.83s/it] 29%|██▉ | 3448/11728 [1:56:32<13:32:46, 5.89s/it] {'loss': 0.502, 'learning_rate': 1.6562257492703756e-05, 'epoch': 0.29} + 29%|██▉ | 3448/11728 [1:56:32<13:32:46, 5.89s/it] 29%|██▉ | 3449/11728 [1:56:38<13:30:50, 5.88s/it] {'loss': 0.5214, 'learning_rate': 1.6560173439168427e-05, 'epoch': 0.29} + 29%|██▉ | 3449/11728 [1:56:38<13:30:50, 5.88s/it]2 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +50 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +AutoResumeHook: Checking whether to suspend... + 29%|██▉ | 3450/11728 [1:56:44<13:34:37, 5.90s/it]3 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... + {'loss': 0.5168, 'learning_rate': 1.6558088885326874e-05, 'epoch': 0.29} + 29%|██▉ | 3450/11728 [1:56:44<13:34:37, 5.90s/it] 29%|██▉ | 3451/11728 [1:56:50<13:42:00, 5.96s/it] {'loss': 0.4778, 'learning_rate': 1.655600383133809e-05, 'epoch': 0.29} + 29%|██▉ | 3451/11728 [1:56:50<13:42:00, 5.96s/it] 29%|██▉ | 3452/11728 [1:56:56<13:36:32, 5.92s/it] {'loss': 0.4999, 'learning_rate': 1.655391827736108e-05, 'epoch': 0.29} + 29%|██▉ | 3452/11728 [1:56:56<13:36:32, 5.92s/it] 29%|██▉ | 3453/11728 [1:57:02<13:46:40, 5.99s/it] {'loss': 0.5022, 'learning_rate': 1.6551832223554902e-05, 'epoch': 0.29} + 29%|██▉ | 3453/11728 [1:57:02<13:46:40, 5.99s/it] 29%|██▉ | 3454/11728 [1:57:09<13:58:22, 6.08s/it] {'loss': 0.4931, 'learning_rate': 1.654974567007865e-05, 'epoch': 0.29} + 29%|██▉ | 3454/11728 [1:57:09<13:58:22, 6.08s/it] 29%|██▉ | 3455/11728 [1:57:14<13:48:15, 6.01s/it] {'loss': 0.4912, 'learning_rate': 1.654765861709144e-05, 'epoch': 0.29} + 29%|██▉ | 3455/11728 [1:57:14<13:48:15, 6.01s/it] 29%|██▉ | 3456/11728 [1:57:21<13:54:17, 6.05s/it] {'loss': 0.5144, 'learning_rate': 1.6545571064752454e-05, 'epoch': 0.29} + 29%|██▉ | 3456/11728 [1:57:21<13:54:17, 6.05s/it] 29%|██▉ | 3457/11728 [1:57:26<13:40:15, 5.95s/it] {'loss': 0.4898, 'learning_rate': 1.654348301322089e-05, 'epoch': 0.29} + 29%|██▉ | 3457/11728 [1:57:26<13:40:15, 5.95s/it] 29%|██▉ | 3458/11728 [1:57:32<13:33:15, 5.90s/it] {'loss': 0.4884, 'learning_rate': 1.6541394462655997e-05, 'epoch': 0.29} + 29%|██▉ | 3458/11728 [1:57:32<13:33:15, 5.90s/it] 29%|██▉ | 3459/11728 [1:57:38<13:24:32, 5.84s/it] {'loss': 0.5088, 'learning_rate': 1.6539305413217044e-05, 'epoch': 0.29} + 29%|██▉ | 3459/11728 [1:57:38<13:24:32, 5.84s/it] 30%|██▉ | 3460/11728 [1:57:43<13:15:35, 5.77s/it] {'loss': 0.4895, 'learning_rate': 1.6537215865063364e-05, 'epoch': 0.3} + 30%|██▉ | 3460/11728 [1:57:43<13:15:35, 5.77s/it] 30%|██▉ | 3461/11728 [1:57:50<13:32:48, 5.90s/it] {'loss': 0.4874, 'learning_rate': 1.653512581835431e-05, 'epoch': 0.3} + 30%|██▉ | 3461/11728 [1:57:50<13:32:48, 5.90s/it] 30%|██▉ | 3462/11728 [1:57:55<13:24:25, 5.84s/it] {'loss': 0.5069, 'learning_rate': 1.653303527324928e-05, 'epoch': 0.3} + 30%|██▉ | 3462/11728 [1:57:55<13:24:25, 5.84s/it] 30%|██▉ | 3463/11728 [1:58:02<13:43:00, 5.97s/it] {'loss': 0.4897, 'learning_rate': 1.6530944229907705e-05, 'epoch': 0.3} + 30%|██▉ | 3463/11728 [1:58:02<13:43:00, 5.97s/it] 30%|██▉ | 3464/11728 [1:58:07<13:39:57, 5.95s/it] {'loss': 0.4779, 'learning_rate': 1.6528852688489053e-05, 'epoch': 0.3} + 30%|██▉ | 3464/11728 [1:58:07<13:39:57, 5.95s/it] 30%|██▉ | 3465/11728 [1:58:14<13:46:43, 6.00s/it] {'loss': 0.5167, 'learning_rate': 1.6526760649152843e-05, 'epoch': 0.3} + 30%|██▉ | 3465/11728 [1:58:14<13:46:43, 6.00s/it] 30%|██▉ | 3466/11728 [1:58:19<13:42:40, 5.97s/it] {'loss': 0.4799, 'learning_rate': 1.6524668112058617e-05, 'epoch': 0.3} + 30%|██▉ | 3466/11728 [1:58:19<13:42:40, 5.97s/it] 30%|██▉ | 3467/11728 [1:58:25<13:27:24, 5.86s/it] {'loss': 0.4842, 'learning_rate': 1.6522575077365958e-05, 'epoch': 0.3} + 30%|██▉ | 3467/11728 [1:58:25<13:27:24, 5.86s/it] 30%|██▉ | 3468/11728 [1:58:31<13:38:29, 5.95s/it] {'loss': 0.4795, 'learning_rate': 1.6520481545234495e-05, 'epoch': 0.3} + 30%|██▉ | 3468/11728 [1:58:31<13:38:29, 5.95s/it] 30%|██▉ | 3469/11728 [1:58:37<13:27:36, 5.87s/it] {'loss': 0.4809, 'learning_rate': 1.6518387515823887e-05, 'epoch': 0.3} + 30%|██▉ | 3469/11728 [1:58:37<13:27:36, 5.87s/it] 30%|██▉ | 3470/11728 [1:58:43<13:23:22, 5.84s/it] {'loss': 0.4925, 'learning_rate': 1.6516292989293833e-05, 'epoch': 0.3} + 30%|██▉ | 3470/11728 [1:58:43<13:23:22, 5.84s/it] 30%|██▉ | 3471/11728 [1:58:48<13:20:43, 5.82s/it] {'loss': 0.4964, 'learning_rate': 1.651419796580407e-05, 'epoch': 0.3} + 30%|██▉ | 3471/11728 [1:58:48<13:20:43, 5.82s/it] 30%|██▉ | 3472/11728 [1:58:54<13:18:37, 5.80s/it] {'loss': 0.4887, 'learning_rate': 1.6512102445514376e-05, 'epoch': 0.3} + 30%|██▉ | 3472/11728 [1:58:54<13:18:37, 5.80s/it] 30%|██▉ | 3473/11728 [1:59:00<13:22:35, 5.83s/it] {'loss': 0.5238, 'learning_rate': 1.651000642858456e-05, 'epoch': 0.3} + 30%|██▉ | 3473/11728 [1:59:00<13:22:35, 5.83s/it] 30%|██▉ | 3474/11728 [1:59:06<13:17:47, 5.80s/it] {'loss': 0.4817, 'learning_rate': 1.6507909915174477e-05, 'epoch': 0.3} + 30%|██▉ | 3474/11728 [1:59:06<13:17:47, 5.80s/it] 30%|██▉ | 3475/11728 [1:59:12<13:27:42, 5.87s/it] {'loss': 0.5013, 'learning_rate': 1.6505812905444014e-05, 'epoch': 0.3} + 30%|██▉ | 3475/11728 [1:59:12<13:27:42, 5.87s/it] 30%|██▉ | 3476/11728 [1:59:18<13:39:54, 5.96s/it] {'loss': 0.4895, 'learning_rate': 1.65037153995531e-05, 'epoch': 0.3} + 30%|██▉ | 3476/11728 [1:59:18<13:39:54, 5.96s/it] 30%|██▉ | 3477/11728 [1:59:24<13:35:07, 5.93s/it] {'loss': 0.4759, 'learning_rate': 1.6501617397661692e-05, 'epoch': 0.3} + 30%|██▉ | 3477/11728 [1:59:24<13:35:07, 5.93s/it] 30%|██▉ | 3478/11728 [1:59:30<13:32:27, 5.91s/it] {'loss': 0.4935, 'learning_rate': 1.6499518899929802e-05, 'epoch': 0.3} + 30%|██▉ | 3478/11728 [1:59:30<13:32:27, 5.91s/it] 30%|██▉ | 3479/11728 [1:59:36<13:38:11, 5.95s/it] {'loss': 0.486, 'learning_rate': 1.6497419906517463e-05, 'epoch': 0.3} + 30%|██▉ | 3479/11728 [1:59:36<13:38:11, 5.95s/it] 30%|██▉ | 3480/11728 [1:59:41<13:25:22, 5.86s/it] {'loss': 0.4996, 'learning_rate': 1.649532041758476e-05, 'epoch': 0.3} + 30%|██▉ | 3480/11728 [1:59:41<13:25:22, 5.86s/it] 30%|██▉ | 3481/11728 [1:59:47<13:11:17, 5.76s/it] {'loss': 0.4863, 'learning_rate': 1.64932204332918e-05, 'epoch': 0.3} + 30%|██▉ | 3481/11728 [1:59:47<13:11:17, 5.76s/it] 30%|██▉ | 3482/11728 [1:59:53<13:14:53, 5.78s/it] {'loss': 0.4903, 'learning_rate': 1.6491119953798747e-05, 'epoch': 0.3} + 30%|██▉ | 3482/11728 [1:59:53<13:14:53, 5.78s/it] 30%|██▉ | 3483/11728 [1:59:59<13:18:32, 5.81s/it] {'loss': 0.5104, 'learning_rate': 1.648901897926578e-05, 'epoch': 0.3} + 30%|██▉ | 3483/11728 [1:59:59<13:18:32, 5.81s/it] 30%|██▉ | 3484/11728 [2:00:04<13:09:04, 5.74s/it] {'loss': 0.4817, 'learning_rate': 1.648691750985314e-05, 'epoch': 0.3} + 30%|██▉ | 3484/11728 [2:00:04<13:09:04, 5.74s/it] 30%|██▉ | 3485/11728 [2:00:10<13:19:59, 5.82s/it] {'loss': 0.5008, 'learning_rate': 1.6484815545721088e-05, 'epoch': 0.3} + 30%|██▉ | 3485/11728 [2:00:10<13:19:59, 5.82s/it] 30%|██▉ | 3486/11728 [2:00:16<13:16:27, 5.80s/it] {'loss': 0.4994, 'learning_rate': 1.6482713087029928e-05, 'epoch': 0.3} + 30%|██▉ | 3486/11728 [2:00:16<13:16:27, 5.80s/it] 30%|██▉ | 3487/11728 [2:00:22<13:14:12, 5.78s/it] {'loss': 0.4838, 'learning_rate': 1.6480610133940005e-05, 'epoch': 0.3} + 30%|██▉ | 3487/11728 [2:00:22<13:14:12, 5.78s/it] 30%|██▉ | 3488/11728 [2:00:28<13:38:56, 5.96s/it] {'loss': 0.5133, 'learning_rate': 1.6478506686611698e-05, 'epoch': 0.3} + 30%|██▉ | 3488/11728 [2:00:28<13:38:56, 5.96s/it] 30%|██▉ | 3489/11728 [2:00:34<13:31:53, 5.91s/it] {'loss': 0.4942, 'learning_rate': 1.647640274520542e-05, 'epoch': 0.3} + 30%|██▉ | 3489/11728 [2:00:34<13:31:53, 5.91s/it] 30%|██▉ | 3490/11728 [2:00:40<13:23:45, 5.85s/it] {'loss': 0.5, 'learning_rate': 1.6474298309881634e-05, 'epoch': 0.3} + 30%|██▉ | 3490/11728 [2:00:40<13:23:45, 5.85s/it] 30%|██▉ | 3491/11728 [2:00:45<13:18:40, 5.82s/it] {'loss': 0.4879, 'learning_rate': 1.6472193380800828e-05, 'epoch': 0.3} + 30%|██▉ | 3491/11728 [2:00:45<13:18:40, 5.82s/it] 30%|██▉ | 3492/11728 [2:00:51<13:10:57, 5.76s/it] {'loss': 0.4993, 'learning_rate': 1.6470087958123535e-05, 'epoch': 0.3} + 30%|██▉ | 3492/11728 [2:00:51<13:10:57, 5.76s/it] 30%|██▉ | 3493/11728 [2:00:57<13:25:35, 5.87s/it] {'loss': 0.4875, 'learning_rate': 1.6467982042010323e-05, 'epoch': 0.3} + 30%|██▉ | 3493/11728 [2:00:57<13:25:35, 5.87s/it] 30%|██▉ | 3494/11728 [2:01:03<13:25:59, 5.87s/it] {'loss': 0.5033, 'learning_rate': 1.6465875632621796e-05, 'epoch': 0.3} + 30%|██▉ | 3494/11728 [2:01:03<13:25:59, 5.87s/it] 30%|██▉ | 3495/11728 [2:01:09<13:31:00, 5.91s/it] {'loss': 0.5012, 'learning_rate': 1.6463768730118598e-05, 'epoch': 0.3} + 30%|██▉ | 3495/11728 [2:01:09<13:31:00, 5.91s/it] 30%|██▉ | 3496/11728 [2:01:15<13:33:24, 5.93s/it] {'loss': 0.5151, 'learning_rate': 1.6461661334661415e-05, 'epoch': 0.3} + 30%|██▉ | 3496/11728 [2:01:15<13:33:24, 5.93s/it] 30%|██▉ | 3497/11728 [2:01:21<13:35:30, 5.94s/it] {'loss': 0.487, 'learning_rate': 1.645955344641096e-05, 'epoch': 0.3} + 30%|██▉ | 3497/11728 [2:01:21<13:35:30, 5.94s/it] 30%|██▉ | 3498/11728 [2:01:27<13:22:48, 5.85s/it] {'loss': 0.5148, 'learning_rate': 1.645744506552799e-05, 'epoch': 0.3} + 30%|██▉ | 3498/11728 [2:01:27<13:22:48, 5.85s/it] 30%|██▉ | 3499/11728 [2:01:32<13:21:21, 5.84s/it] {'loss': 0.4776, 'learning_rate': 1.64553361921733e-05, 'epoch': 0.3} + 30%|██▉ | 3499/11728 [2:01:32<13:21:21, 5.84s/it]7 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... +01 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... + 30%|██▉ | 3500/11728 [2:01:38<13:26:03, 5.88s/it]6 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4748, 'learning_rate': 1.645322682650772e-05, 'epoch': 0.3} + 30%|██▉ | 3500/11728 [2:01:38<13:26:03, 5.88s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-3500/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-3500/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-3500/mm_projector +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/torch/nn/modules/module.py:1802: UserWarning: Positional args are being deprecated, use kwargs instead. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details. + warnings.warn( + 30%|██▉ | 3501/11728 [2:02:09<30:14:22, 13.23s/it] {'loss': 0.5111, 'learning_rate': 1.6451116968692126e-05, 'epoch': 0.3} + 30%|██▉ | 3501/11728 [2:02:09<30:14:22, 13.23s/it] 30%|██▉ | 3502/11728 [2:02:15<25:10:54, 11.02s/it] {'loss': 0.5106, 'learning_rate': 1.644900661888742e-05, 'epoch': 0.3} + 30%|██▉ | 3502/11728 [2:02:15<25:10:54, 11.02s/it] 30%|██▉ | 3503/11728 [2:02:21<21:49:23, 9.55s/it] {'loss': 0.4926, 'learning_rate': 1.6446895777254542e-05, 'epoch': 0.3} + 30%|██▉ | 3503/11728 [2:02:21<21:49:23, 9.55s/it] 30%|██▉ | 3504/11728 [2:02:27<19:18:30, 8.45s/it] {'loss': 0.5044, 'learning_rate': 1.644478444395448e-05, 'epoch': 0.3} + 30%|██▉ | 3504/11728 [2:02:27<19:18:30, 8.45s/it] 30%|██▉ | 3505/11728 [2:02:33<17:34:51, 7.70s/it] {'loss': 0.4849, 'learning_rate': 1.6442672619148248e-05, 'epoch': 0.3} + 30%|██▉ | 3505/11728 [2:02:33<17:34:51, 7.70s/it] 30%|██▉ | 3506/11728 [2:02:38<16:19:41, 7.15s/it] {'loss': 0.5036, 'learning_rate': 1.6440560302996903e-05, 'epoch': 0.3} + 30%|██▉ | 3506/11728 [2:02:38<16:19:41, 7.15s/it] 30%|██▉ | 3507/11728 [2:02:44<15:19:24, 6.71s/it] {'loss': 0.4753, 'learning_rate': 1.6438447495661543e-05, 'epoch': 0.3} + 30%|██▉ | 3507/11728 [2:02:44<15:19:24, 6.71s/it] 30%|██▉ | 3508/11728 [2:02:50<14:33:58, 6.38s/it] {'loss': 0.4831, 'learning_rate': 1.6436334197303298e-05, 'epoch': 0.3} + 30%|██▉ | 3508/11728 [2:02:50<14:33:58, 6.38s/it] 30%|██▉ | 3509/11728 [2:02:56<14:08:03, 6.19s/it] {'loss': 0.5021, 'learning_rate': 1.6434220408083334e-05, 'epoch': 0.3} + 30%|██▉ | 3509/11728 [2:02:56<14:08:03, 6.19s/it] 30%|██▉ | 3510/11728 [2:03:01<13:55:35, 6.10s/it] {'loss': 0.4994, 'learning_rate': 1.6432106128162862e-05, 'epoch': 0.3} + 30%|██▉ | 3510/11728 [2:03:01<13:55:35, 6.10s/it] 30%|██▉ | 3511/11728 [2:03:07<13:47:07, 6.04s/it] {'loss': 0.5114, 'learning_rate': 1.642999135770312e-05, 'epoch': 0.3} + 30%|██▉ | 3511/11728 [2:03:07<13:47:07, 6.04s/it] 30%|██▉ | 3512/11728 [2:03:13<13:38:23, 5.98s/it] {'loss': 0.4894, 'learning_rate': 1.6427876096865394e-05, 'epoch': 0.3} + 30%|██▉ | 3512/11728 [2:03:13<13:38:23, 5.98s/it] 30%|██▉ | 3513/11728 [2:03:19<13:38:55, 5.98s/it] {'loss': 0.4998, 'learning_rate': 1.6425760345811004e-05, 'epoch': 0.3} + 30%|██▉ | 3513/11728 [2:03:19<13:38:55, 5.98s/it] 30%|██▉ | 3514/11728 [2:03:25<13:28:40, 5.91s/it] {'loss': 0.4815, 'learning_rate': 1.64236441047013e-05, 'epoch': 0.3} + 30%|██▉ | 3514/11728 [2:03:25<13:28:40, 5.91s/it] 30%|██▉ | 3515/11728 [2:03:31<13:19:34, 5.84s/it] {'loss': 0.5114, 'learning_rate': 1.642152737369768e-05, 'epoch': 0.3} + 30%|██▉ | 3515/11728 [2:03:31<13:19:34, 5.84s/it] 30%|██▉ | 3516/11728 [2:03:36<13:14:29, 5.80s/it] {'loss': 0.4862, 'learning_rate': 1.641941015296157e-05, 'epoch': 0.3} + 30%|██▉ | 3516/11728 [2:03:36<13:14:29, 5.80s/it] 30%|██▉ | 3517/11728 [2:03:42<13:14:00, 5.80s/it] {'loss': 0.4961, 'learning_rate': 1.6417292442654445e-05, 'epoch': 0.3} + 30%|██▉ | 3517/11728 [2:03:42<13:14:00, 5.80s/it] 30%|██▉ | 3518/11728 [2:03:48<13:25:47, 5.89s/it] {'loss': 0.4744, 'learning_rate': 1.641517424293781e-05, 'epoch': 0.3} + 30%|██▉ | 3518/11728 [2:03:48<13:25:47, 5.89s/it] 30%|███ | 3519/11728 [2:03:54<13:22:09, 5.86s/it] {'loss': 0.5083, 'learning_rate': 1.6413055553973202e-05, 'epoch': 0.3} + 30%|███ | 3519/11728 [2:03:54<13:22:09, 5.86s/it] 30%|███ | 3520/11728 [2:04:00<13:26:01, 5.89s/it] {'loss': 0.4926, 'learning_rate': 1.64109363759222e-05, 'epoch': 0.3} + 30%|███ | 3520/11728 [2:04:00<13:26:01, 5.89s/it] 30%|███ | 3521/11728 [2:04:06<13:38:37, 5.98s/it] {'loss': 0.4868, 'learning_rate': 1.6408816708946433e-05, 'epoch': 0.3} + 30%|███ | 3521/11728 [2:04:06<13:38:37, 5.98s/it] 30%|███ | 3522/11728 [2:04:12<13:29:15, 5.92s/it] {'loss': 0.4966, 'learning_rate': 1.640669655320754e-05, 'epoch': 0.3} + 30%|███ | 3522/11728 [2:04:12<13:29:15, 5.92s/it] 30%|███ | 3523/11728 [2:04:18<13:28:06, 5.91s/it] {'loss': 0.4748, 'learning_rate': 1.6404575908867224e-05, 'epoch': 0.3} + 30%|███ | 3523/11728 [2:04:18<13:28:06, 5.91s/it] 30%|███ | 3524/11728 [2:04:23<13:12:09, 5.79s/it] {'loss': 0.4964, 'learning_rate': 1.6402454776087214e-05, 'epoch': 0.3} + 30%|███ | 3524/11728 [2:04:23<13:12:09, 5.79s/it] 30%|███ | 3525/11728 [2:04:29<13:14:16, 5.81s/it] {'loss': 0.4972, 'learning_rate': 1.640033315502927e-05, 'epoch': 0.3} + 30%|███ | 3525/11728 [2:04:29<13:14:16, 5.81s/it] 30%|███ | 3526/11728 [2:04:35<13:20:20, 5.85s/it] {'loss': 0.4782, 'learning_rate': 1.6398211045855198e-05, 'epoch': 0.3} + 30%|███ | 3526/11728 [2:04:35<13:20:20, 5.85s/it] 30%|███ | 3527/11728 [2:04:41<13:29:07, 5.92s/it] {'loss': 0.4996, 'learning_rate': 1.6396088448726838e-05, 'epoch': 0.3} + 30%|███ | 3527/11728 [2:04:41<13:29:07, 5.92s/it] 30%|███ | 3528/11728 [2:04:47<13:26:58, 5.90s/it] {'loss': 0.4814, 'learning_rate': 1.6393965363806075e-05, 'epoch': 0.3} + 30%|███ | 3528/11728 [2:04:47<13:26:58, 5.90s/it] 30%|███ | 3529/11728 [2:04:53<13:26:12, 5.90s/it] {'loss': 0.4905, 'learning_rate': 1.6391841791254818e-05, 'epoch': 0.3} + 30%|███ | 3529/11728 [2:04:53<13:26:12, 5.90s/it] 30%|███ | 3530/11728 [2:04:59<13:25:03, 5.89s/it] {'loss': 0.4779, 'learning_rate': 1.638971773123502e-05, 'epoch': 0.3} + 30%|███ | 3530/11728 [2:04:59<13:25:03, 5.89s/it] 30%|███ | 3531/11728 [2:05:05<13:19:52, 5.85s/it] {'loss': 0.4976, 'learning_rate': 1.638759318390867e-05, 'epoch': 0.3} + 30%|███ | 3531/11728 [2:05:05<13:19:52, 5.85s/it] 30%|███ | 3532/11728 [2:05:10<13:19:39, 5.85s/it] {'loss': 0.4943, 'learning_rate': 1.63854681494378e-05, 'epoch': 0.3} + 30%|███ | 3532/11728 [2:05:10<13:19:39, 5.85s/it] 30%|███ | 3533/11728 [2:05:16<13:22:46, 5.88s/it] {'loss': 0.4963, 'learning_rate': 1.638334262798447e-05, 'epoch': 0.3} + 30%|███ | 3533/11728 [2:05:16<13:22:46, 5.88s/it] 30%|███ | 3534/11728 [2:05:22<13:16:05, 5.83s/it] {'loss': 0.4844, 'learning_rate': 1.638121661971078e-05, 'epoch': 0.3} + 30%|███ | 3534/11728 [2:05:22<13:16:05, 5.83s/it] 30%|███ | 3535/11728 [2:05:28<13:12:34, 5.80s/it] {'loss': 0.4864, 'learning_rate': 1.6379090124778866e-05, 'epoch': 0.3} + 30%|███ | 3535/11728 [2:05:28<13:12:34, 5.80s/it] 30%|███ | 3536/11728 [2:05:34<13:18:24, 5.85s/it] {'loss': 0.513, 'learning_rate': 1.6376963143350915e-05, 'epoch': 0.3} + 30%|███ | 3536/11728 [2:05:34<13:18:24, 5.85s/it] 30%|███ | 3537/11728 [2:05:40<13:29:28, 5.93s/it] {'loss': 0.4849, 'learning_rate': 1.6374835675589125e-05, 'epoch': 0.3} + 30%|███ | 3537/11728 [2:05:40<13:29:28, 5.93s/it] 30%|███ | 3538/11728 [2:05:45<13:16:26, 5.83s/it] {'loss': 0.4988, 'learning_rate': 1.6372707721655756e-05, 'epoch': 0.3} + 30%|███ | 3538/11728 [2:05:45<13:16:26, 5.83s/it] 30%|███ | 3539/11728 [2:05:51<13:09:09, 5.78s/it] {'loss': 0.4798, 'learning_rate': 1.6370579281713087e-05, 'epoch': 0.3} + 30%|███ | 3539/11728 [2:05:51<13:09:09, 5.78s/it] 30%|███ | 3540/11728 [2:05:57<13:17:37, 5.84s/it] {'loss': 0.5126, 'learning_rate': 1.6368450355923452e-05, 'epoch': 0.3} + 30%|███ | 3540/11728 [2:05:57<13:17:37, 5.84s/it] 30%|███ | 3541/11728 [2:06:03<13:08:49, 5.78s/it] {'loss': 0.4893, 'learning_rate': 1.63663209444492e-05, 'epoch': 0.3} + 30%|███ | 3541/11728 [2:06:03<13:08:49, 5.78s/it] 30%|███ | 3542/11728 [2:06:09<13:09:59, 5.79s/it] {'loss': 0.4933, 'learning_rate': 1.6364191047452734e-05, 'epoch': 0.3} + 30%|███ | 3542/11728 [2:06:09<13:09:59, 5.79s/it] 30%|███ | 3543/11728 [2:06:14<13:14:41, 5.83s/it] {'loss': 0.5033, 'learning_rate': 1.6362060665096495e-05, 'epoch': 0.3} + 30%|███ | 3543/11728 [2:06:14<13:14:41, 5.83s/it] 30%|███ | 3544/11728 [2:06:21<13:24:42, 5.90s/it] {'loss': 0.5084, 'learning_rate': 1.6359929797542945e-05, 'epoch': 0.3} + 30%|███ | 3544/11728 [2:06:21<13:24:42, 5.90s/it] 30%|███ | 3545/11728 [2:06:26<13:18:21, 5.85s/it] {'loss': 0.4998, 'learning_rate': 1.6357798444954595e-05, 'epoch': 0.3} + 30%|███ | 3545/11728 [2:06:26<13:18:21, 5.85s/it] 30%|███ | 3546/11728 [2:06:32<13:27:56, 5.92s/it] {'loss': 0.4772, 'learning_rate': 1.6355666607493995e-05, 'epoch': 0.3} + 30%|███ | 3546/11728 [2:06:32<13:27:56, 5.92s/it] 30%|███ | 3547/11728 [2:06:38<13:20:42, 5.87s/it] {'loss': 0.5003, 'learning_rate': 1.6353534285323724e-05, 'epoch': 0.3} + 30%|███ | 3547/11728 [2:06:38<13:20:42, 5.87s/it] 30%|███ | 3548/11728 [2:06:44<13:29:34, 5.94s/it] {'loss': 0.525, 'learning_rate': 1.6351401478606406e-05, 'epoch': 0.3} + 30%|███ | 3548/11728 [2:06:44<13:29:34, 5.94s/it] 30%|███ | 3549/11728 [2:06:50<13:40:52, 6.02s/it] {'loss': 0.4865, 'learning_rate': 1.634926818750469e-05, 'epoch': 0.3} + 30%|███ | 3549/11728 [2:06:50<13:40:52, 6.02s/it]1 AutoResumeHook: Checking whether to suspend... +0 7AutoResumeHook: Checking whether to suspend... AutoResumeHook: Checking whether to suspend... + +2 AutoResumeHook: Checking whether to suspend... + 30%|███ | 3550/11728 [2:06:56<13:25:03, 5.91s/it]6 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... + {'loss': 0.522, 'learning_rate': 1.634713441218128e-05, 'epoch': 0.3} + 30%|███ | 3550/11728 [2:06:56<13:25:03, 5.91s/it] 30%|███ | 3551/11728 [2:07:02<13:29:53, 5.94s/it] {'loss': 0.4815, 'learning_rate': 1.6345000152798896e-05, 'epoch': 0.3} + 30%|███ | 3551/11728 [2:07:02<13:29:53, 5.94s/it] 30%|███ | 3552/11728 [2:07:08<13:20:24, 5.87s/it] {'loss': 0.4746, 'learning_rate': 1.6342865409520318e-05, 'epoch': 0.3} + 30%|███ | 3552/11728 [2:07:08<13:20:24, 5.87s/it] 30%|███ | 3553/11728 [2:07:14<13:18:31, 5.86s/it] {'loss': 0.478, 'learning_rate': 1.6340730182508332e-05, 'epoch': 0.3} + 30%|███ | 3553/11728 [2:07:14<13:18:31, 5.86s/it] 30%|███ | 3554/11728 [2:07:19<13:08:02, 5.78s/it] {'loss': 0.4948, 'learning_rate': 1.6338594471925802e-05, 'epoch': 0.3} + 30%|███ | 3554/11728 [2:07:19<13:08:02, 5.78s/it] 30%|███ | 3555/11728 [2:07:26<13:31:28, 5.96s/it] {'loss': 0.4901, 'learning_rate': 1.6336458277935586e-05, 'epoch': 0.3} + 30%|███ | 3555/11728 [2:07:26<13:31:28, 5.96s/it] 30%|███ | 3556/11728 [2:07:32<13:38:46, 6.01s/it] {'loss': 0.5125, 'learning_rate': 1.6334321600700612e-05, 'epoch': 0.3} + 30%|███ | 3556/11728 [2:07:32<13:38:46, 6.01s/it] 30%|███ | 3557/11728 [2:07:38<13:31:17, 5.96s/it] {'loss': 0.5111, 'learning_rate': 1.633218444038383e-05, 'epoch': 0.3} + 30%|███ | 3557/11728 [2:07:38<13:31:17, 5.96s/it] 30%|███ | 3558/11728 [2:07:44<13:38:03, 6.01s/it] {'loss': 0.4802, 'learning_rate': 1.6330046797148226e-05, 'epoch': 0.3} + 30%|███ | 3558/11728 [2:07:44<13:38:03, 6.01s/it] 30%|███ | 3559/11728 [2:07:49<13:23:52, 5.90s/it] {'loss': 0.4846, 'learning_rate': 1.632790867115682e-05, 'epoch': 0.3} + 30%|███ | 3559/11728 [2:07:49<13:23:52, 5.90s/it] 30%|███ | 3560/11728 [2:07:55<13:15:16, 5.84s/it] {'loss': 0.4837, 'learning_rate': 1.6325770062572685e-05, 'epoch': 0.3} + 30%|███ | 3560/11728 [2:07:55<13:15:16, 5.84s/it] 30%|███ | 3561/11728 [2:08:01<13:10:14, 5.81s/it] {'loss': 0.4755, 'learning_rate': 1.6323630971558916e-05, 'epoch': 0.3} + 30%|███ | 3561/11728 [2:08:01<13:10:14, 5.81s/it] 30%|███ | 3562/11728 [2:08:07<13:15:38, 5.85s/it] {'loss': 0.4795, 'learning_rate': 1.6321491398278647e-05, 'epoch': 0.3} + 30%|███ | 3562/11728 [2:08:07<13:15:38, 5.85s/it] 30%|███ | 3563/11728 [2:08:13<13:20:35, 5.88s/it] {'loss': 0.5012, 'learning_rate': 1.6319351342895052e-05, 'epoch': 0.3} + 30%|███ | 3563/11728 [2:08:13<13:20:35, 5.88s/it] 30%|███ | 3564/11728 [2:08:18<13:09:51, 5.80s/it] {'loss': 0.4958, 'learning_rate': 1.6317210805571346e-05, 'epoch': 0.3} + 30%|███ | 3564/11728 [2:08:18<13:09:51, 5.80s/it] 30%|███ | 3565/11728 [2:08:24<13:06:52, 5.78s/it] {'loss': 0.4693, 'learning_rate': 1.6315069786470767e-05, 'epoch': 0.3} + 30%|███ | 3565/11728 [2:08:24<13:06:52, 5.78s/it] 30%|███ | 3566/11728 [2:08:30<13:10:21, 5.81s/it] {'loss': 0.49, 'learning_rate': 1.6312928285756598e-05, 'epoch': 0.3} + 30%|███ | 3566/11728 [2:08:30<13:10:21, 5.81s/it] 30%|███ | 3567/11728 [2:08:36<13:02:24, 5.75s/it] {'loss': 0.4796, 'learning_rate': 1.631078630359217e-05, 'epoch': 0.3} + 30%|███ | 3567/11728 [2:08:36<13:02:24, 5.75s/it] 30%|███ | 3568/11728 [2:08:41<13:05:27, 5.78s/it] {'loss': 0.482, 'learning_rate': 1.630864384014083e-05, 'epoch': 0.3} + 30%|███ | 3568/11728 [2:08:41<13:05:27, 5.78s/it] 30%|███ | 3569/11728 [2:08:47<13:07:28, 5.79s/it] {'loss': 0.4931, 'learning_rate': 1.6306500895565967e-05, 'epoch': 0.3} + 30%|███ | 3569/11728 [2:08:47<13:07:28, 5.79s/it] 30%|███ | 3570/11728 [2:08:53<13:02:37, 5.76s/it] {'loss': 0.4933, 'learning_rate': 1.6304357470031022e-05, 'epoch': 0.3} + 30%|███ | 3570/11728 [2:08:53<13:02:37, 5.76s/it] 30%|███ | 3571/11728 [2:08:59<13:13:37, 5.84s/it] {'loss': 0.508, 'learning_rate': 1.630221356369945e-05, 'epoch': 0.3} + 30%|███ | 3571/11728 [2:08:59<13:13:37, 5.84s/it] 30%|███ | 3572/11728 [2:09:04<13:01:52, 5.75s/it] {'loss': 0.4672, 'learning_rate': 1.6300069176734768e-05, 'epoch': 0.3} + 30%|███ | 3572/11728 [2:09:04<13:01:52, 5.75s/it] 30%|███ | 3573/11728 [2:09:10<13:06:40, 5.79s/it] {'loss': 0.491, 'learning_rate': 1.6297924309300506e-05, 'epoch': 0.3} + 30%|███ | 3573/11728 [2:09:10<13:06:40, 5.79s/it] 30%|███ | 3574/11728 [2:09:16<13:06:58, 5.79s/it] {'loss': 0.4824, 'learning_rate': 1.6295778961560242e-05, 'epoch': 0.3} + 30%|███ | 3574/11728 [2:09:16<13:06:58, 5.79s/it] 30%|███ | 3575/11728 [2:09:22<13:08:47, 5.80s/it] {'loss': 0.4777, 'learning_rate': 1.629363313367759e-05, 'epoch': 0.3} + 30%|███ | 3575/11728 [2:09:22<13:08:47, 5.80s/it] 30%|███ | 3576/11728 [2:09:28<13:28:50, 5.95s/it] {'loss': 0.4988, 'learning_rate': 1.6291486825816205e-05, 'epoch': 0.3} + 30%|███ | 3576/11728 [2:09:28<13:28:50, 5.95s/it] 30%|███ | 3577/11728 [2:09:34<13:21:49, 5.90s/it] {'loss': 0.4955, 'learning_rate': 1.6289340038139765e-05, 'epoch': 0.3} + 30%|███ | 3577/11728 [2:09:34<13:21:49, 5.90s/it] 31%|███ | 3578/11728 [2:09:40<13:09:38, 5.81s/it] {'loss': 0.4794, 'learning_rate': 1.6287192770811993e-05, 'epoch': 0.31} + 31%|███ | 3578/11728 [2:09:40<13:09:38, 5.81s/it] 31%|███ | 3579/11728 [2:09:46<13:28:00, 5.95s/it] {'loss': 0.5035, 'learning_rate': 1.6285045023996657e-05, 'epoch': 0.31} + 31%|███ | 3579/11728 [2:09:46<13:28:00, 5.95s/it] 31%|███ | 3580/11728 [2:09:52<13:21:31, 5.90s/it] {'loss': 0.4896, 'learning_rate': 1.6282896797857547e-05, 'epoch': 0.31} + 31%|███ | 3580/11728 [2:09:52<13:21:31, 5.90s/it] 31%|███ | 3581/11728 [2:09:58<13:21:17, 5.90s/it] {'loss': 0.4828, 'learning_rate': 1.6280748092558498e-05, 'epoch': 0.31} + 31%|███ | 3581/11728 [2:09:58<13:21:17, 5.90s/it] 31%|███ | 3582/11728 [2:10:04<13:21:02, 5.90s/it] {'loss': 0.5032, 'learning_rate': 1.6278598908263378e-05, 'epoch': 0.31} + 31%|███ | 3582/11728 [2:10:04<13:21:02, 5.90s/it] 31%|███ | 3583/11728 [2:10:09<13:08:51, 5.81s/it] {'loss': 0.5017, 'learning_rate': 1.627644924513609e-05, 'epoch': 0.31} + 31%|███ | 3583/11728 [2:10:09<13:08:51, 5.81s/it] 31%|███ | 3584/11728 [2:10:15<12:58:54, 5.74s/it] {'loss': 0.4765, 'learning_rate': 1.627429910334058e-05, 'epoch': 0.31} + 31%|███ | 3584/11728 [2:10:15<12:58:54, 5.74s/it] 31%|███ | 3585/11728 [2:10:20<12:49:50, 5.67s/it] {'loss': 0.5028, 'learning_rate': 1.6272148483040827e-05, 'epoch': 0.31} + 31%|███ | 3585/11728 [2:10:20<12:49:50, 5.67s/it] 31%|███ | 3586/11728 [2:10:26<12:48:10, 5.66s/it] {'loss': 0.4998, 'learning_rate': 1.6269997384400845e-05, 'epoch': 0.31} + 31%|███ | 3586/11728 [2:10:26<12:48:10, 5.66s/it] 31%|███ | 3587/11728 [2:10:32<12:48:57, 5.67s/it] {'loss': 0.4968, 'learning_rate': 1.626784580758469e-05, 'epoch': 0.31} + 31%|███ | 3587/11728 [2:10:32<12:48:57, 5.67s/it] 31%|███ | 3588/11728 [2:10:38<13:13:56, 5.85s/it] {'loss': 0.4755, 'learning_rate': 1.626569375275644e-05, 'epoch': 0.31} + 31%|███ | 3588/11728 [2:10:38<13:13:56, 5.85s/it] 31%|███ | 3589/11728 [2:10:44<13:07:24, 5.80s/it] {'loss': 0.4764, 'learning_rate': 1.6263541220080227e-05, 'epoch': 0.31} + 31%|███ | 3589/11728 [2:10:44<13:07:24, 5.80s/it] 31%|███ | 3590/11728 [2:10:49<13:10:39, 5.83s/it] {'loss': 0.5065, 'learning_rate': 1.626138820972021e-05, 'epoch': 0.31} + 31%|███ | 3590/11728 [2:10:49<13:10:39, 5.83s/it] 31%|███ | 3591/11728 [2:10:55<13:16:47, 5.88s/it] {'loss': 0.495, 'learning_rate': 1.6259234721840595e-05, 'epoch': 0.31} + 31%|███ | 3591/11728 [2:10:55<13:16:47, 5.88s/it] 31%|███ | 3592/11728 [2:11:01<13:08:24, 5.81s/it] {'loss': 0.491, 'learning_rate': 1.62570807566056e-05, 'epoch': 0.31} + 31%|███ | 3592/11728 [2:11:01<13:08:24, 5.81s/it] 31%|███ | 3593/11728 [2:11:07<13:07:06, 5.81s/it] {'loss': 0.4948, 'learning_rate': 1.625492631417951e-05, 'epoch': 0.31} + 31%|███ | 3593/11728 [2:11:07<13:07:06, 5.81s/it] 31%|███ | 3594/11728 [2:11:13<13:07:55, 5.81s/it] {'loss': 0.4784, 'learning_rate': 1.6252771394726622e-05, 'epoch': 0.31} + 31%|███ | 3594/11728 [2:11:13<13:07:55, 5.81s/it] 31%|███ | 3595/11728 [2:11:19<13:22:44, 5.92s/it] {'loss': 0.5088, 'learning_rate': 1.6250615998411285e-05, 'epoch': 0.31} + 31%|███ | 3595/11728 [2:11:19<13:22:44, 5.92s/it] 31%|███ | 3596/11728 [2:11:25<13:12:33, 5.85s/it] {'loss': 0.5011, 'learning_rate': 1.6248460125397874e-05, 'epoch': 0.31} + 31%|███ | 3596/11728 [2:11:25<13:12:33, 5.85s/it] 31%|███ | 3597/11728 [2:11:30<13:11:30, 5.84s/it] {'loss': 0.4822, 'learning_rate': 1.6246303775850808e-05, 'epoch': 0.31} + 31%|███ | 3597/11728 [2:11:30<13:11:30, 5.84s/it] 31%|███ | 3598/11728 [2:11:36<13:08:42, 5.82s/it] {'loss': 0.5093, 'learning_rate': 1.624414694993454e-05, 'epoch': 0.31} + 31%|███ | 3598/11728 [2:11:36<13:08:42, 5.82s/it] 31%|███ | 3599/11728 [2:11:42<13:13:33, 5.86s/it] {'loss': 0.483, 'learning_rate': 1.6241989647813557e-05, 'epoch': 0.31} + 31%|███ | 3599/11728 [2:11:42<13:13:33, 5.86s/it]07 AutoResumeHook: Checking whether to suspend... + 1 AutoResumeHook: Checking whether to suspend... +AutoResumeHook: Checking whether to suspend...2 + AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... + 31%|███ | 3600/11728 [2:11:48<13:08:20, 5.82s/it]6 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... + {'loss': 0.49, 'learning_rate': 1.6239831869652384e-05, 'epoch': 0.31} + 31%|███ | 3600/11728 [2:11:48<13:08:20, 5.82s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-3600/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-3600/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-3600/mm_projector +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/torch/nn/modules/module.py:1802: UserWarning: Positional args are being deprecated, use kwargs instead. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details. + warnings.warn( + 31%|███ | 3601/11728 [2:12:19<30:11:28, 13.37s/it] {'loss': 0.4917, 'learning_rate': 1.6237673615615582e-05, 'epoch': 0.31} + 31%|███ | 3601/11728 [2:12:19<30:11:28, 13.37s/it] 31%|███ | 3602/11728 [2:12:25<25:05:41, 11.12s/it] {'loss': 0.4939, 'learning_rate': 1.6235514885867747e-05, 'epoch': 0.31} + 31%|███ | 3602/11728 [2:12:25<25:05:41, 11.12s/it] 31%|███ | 3603/11728 [2:12:30<21:22:58, 9.47s/it] {'loss': 0.4759, 'learning_rate': 1.6233355680573514e-05, 'epoch': 0.31} + 31%|███ | 3603/11728 [2:12:30<21:22:58, 9.47s/it] 31%|███ | 3604/11728 [2:12:36<18:50:02, 8.35s/it] {'loss': 0.478, 'learning_rate': 1.6231195999897557e-05, 'epoch': 0.31} + 31%|███ | 3604/11728 [2:12:36<18:50:02, 8.35s/it] 31%|███ | 3605/11728 [2:12:42<16:57:01, 7.51s/it] {'loss': 0.4925, 'learning_rate': 1.6229035844004573e-05, 'epoch': 0.31} + 31%|███ | 3605/11728 [2:12:42<16:57:01, 7.51s/it] 31%|███ | 3606/11728 [2:12:48<15:56:46, 7.07s/it] {'loss': 0.4857, 'learning_rate': 1.6226875213059314e-05, 'epoch': 0.31} + 31%|███ | 3606/11728 [2:12:48<15:56:46, 7.07s/it] 31%|███ | 3607/11728 [2:12:54<15:12:21, 6.74s/it] {'loss': 0.4895, 'learning_rate': 1.6224714107226557e-05, 'epoch': 0.31} + 31%|███ | 3607/11728 [2:12:54<15:12:21, 6.74s/it] 31%|███ | 3608/11728 [2:13:00<14:48:16, 6.56s/it] {'loss': 0.4946, 'learning_rate': 1.622255252667111e-05, 'epoch': 0.31} + 31%|███ | 3608/11728 [2:13:00<14:48:16, 6.56s/it] 31%|███ | 3609/11728 [2:13:05<14:08:05, 6.27s/it] {'loss': 0.4793, 'learning_rate': 1.6220390471557832e-05, 'epoch': 0.31} + 31%|███ | 3609/11728 [2:13:05<14:08:05, 6.27s/it] 31%|███ | 3610/11728 [2:13:11<13:55:06, 6.17s/it] {'loss': 0.4879, 'learning_rate': 1.6218227942051606e-05, 'epoch': 0.31} + 31%|███ | 3610/11728 [2:13:11<13:55:06, 6.17s/it] 31%|███ | 3611/11728 [2:13:17<13:48:04, 6.12s/it] {'loss': 0.4878, 'learning_rate': 1.6216064938317356e-05, 'epoch': 0.31} + 31%|███ | 3611/11728 [2:13:17<13:48:04, 6.12s/it] 31%|███ | 3612/11728 [2:13:23<13:35:03, 6.03s/it] {'loss': 0.4851, 'learning_rate': 1.6213901460520047e-05, 'epoch': 0.31} + 31%|███ | 3612/11728 [2:13:23<13:35:03, 6.03s/it] 31%|███ | 3613/11728 [2:13:29<13:25:44, 5.96s/it] {'loss': 0.5002, 'learning_rate': 1.6211737508824662e-05, 'epoch': 0.31} + 31%|███ | 3613/11728 [2:13:29<13:25:44, 5.96s/it] 31%|███ | 3614/11728 [2:13:35<13:24:30, 5.95s/it] {'loss': 0.4949, 'learning_rate': 1.620957308339625e-05, 'epoch': 0.31} + 31%|███ | 3614/11728 [2:13:35<13:24:30, 5.95s/it] 31%|███ | 3615/11728 [2:13:40<13:11:21, 5.85s/it] {'loss': 0.5118, 'learning_rate': 1.6207408184399864e-05, 'epoch': 0.31} + 31%|███ | 3615/11728 [2:13:40<13:11:21, 5.85s/it] 31%|███ | 3616/11728 [2:13:46<13:00:38, 5.77s/it] {'loss': 0.4867, 'learning_rate': 1.620524281200062e-05, 'epoch': 0.31} + 31%|███ | 3616/11728 [2:13:46<13:00:38, 5.77s/it] 31%|███ | 3617/11728 [2:13:52<12:54:08, 5.73s/it] {'loss': 0.4668, 'learning_rate': 1.620307696636365e-05, 'epoch': 0.31} + 31%|███ | 3617/11728 [2:13:52<12:54:08, 5.73s/it] 31%|███ | 3618/11728 [2:13:57<12:48:24, 5.68s/it] {'loss': 0.5009, 'learning_rate': 1.6200910647654134e-05, 'epoch': 0.31} + 31%|███ | 3618/11728 [2:13:57<12:48:24, 5.68s/it] 31%|███ | 3619/11728 [2:14:03<13:00:19, 5.77s/it] {'loss': 0.5067, 'learning_rate': 1.6198743856037286e-05, 'epoch': 0.31} + 31%|███ | 3619/11728 [2:14:03<13:00:19, 5.77s/it] 31%|███ | 3620/11728 [2:14:09<13:06:05, 5.82s/it] {'loss': 0.4799, 'learning_rate': 1.619657659167835e-05, 'epoch': 0.31} + 31%|███ | 3620/11728 [2:14:09<13:06:05, 5.82s/it] 31%|███ | 3621/11728 [2:14:15<13:00:47, 5.78s/it] {'loss': 0.4986, 'learning_rate': 1.619440885474261e-05, 'epoch': 0.31} + 31%|███ | 3621/11728 [2:14:15<13:00:47, 5.78s/it] 31%|███ | 3622/11728 [2:14:21<13:06:59, 5.83s/it] {'loss': 0.496, 'learning_rate': 1.6192240645395396e-05, 'epoch': 0.31} + 31%|███ | 3622/11728 [2:14:21<13:06:59, 5.83s/it] 31%|███ | 3623/11728 [2:14:27<13:07:03, 5.83s/it] {'loss': 0.4957, 'learning_rate': 1.6190071963802053e-05, 'epoch': 0.31} + 31%|███ | 3623/11728 [2:14:27<13:07:03, 5.83s/it] 31%|███ | 3624/11728 [2:14:32<13:04:31, 5.81s/it] {'loss': 0.4783, 'learning_rate': 1.6187902810127983e-05, 'epoch': 0.31} + 31%|███ | 3624/11728 [2:14:32<13:04:31, 5.81s/it] 31%|███ | 3625/11728 [2:14:38<13:11:57, 5.86s/it] {'loss': 0.4985, 'learning_rate': 1.6185733184538613e-05, 'epoch': 0.31} + 31%|███ | 3625/11728 [2:14:38<13:11:57, 5.86s/it] 31%|███ | 3626/11728 [2:14:44<13:11:45, 5.86s/it] {'loss': 0.4847, 'learning_rate': 1.6183563087199403e-05, 'epoch': 0.31} + 31%|███ | 3626/11728 [2:14:44<13:11:45, 5.86s/it] 31%|███ | 3627/11728 [2:14:50<13:20:36, 5.93s/it] {'loss': 0.4997, 'learning_rate': 1.6181392518275854e-05, 'epoch': 0.31} + 31%|███ | 3627/11728 [2:14:50<13:20:36, 5.93s/it] 31%|███ | 3628/11728 [2:14:56<13:08:18, 5.84s/it] {'loss': 0.4932, 'learning_rate': 1.617922147793351e-05, 'epoch': 0.31} + 31%|███ | 3628/11728 [2:14:56<13:08:18, 5.84s/it] 31%|███ | 3629/11728 [2:15:02<13:08:37, 5.84s/it] {'loss': 0.4862, 'learning_rate': 1.6177049966337933e-05, 'epoch': 0.31} + 31%|███ | 3629/11728 [2:15:02<13:08:37, 5.84s/it] 31%|███ | 3630/11728 [2:15:08<13:16:46, 5.90s/it] {'loss': 0.4888, 'learning_rate': 1.617487798365474e-05, 'epoch': 0.31} + 31%|███ | 3630/11728 [2:15:08<13:16:46, 5.90s/it] 31%|███ | 3631/11728 [2:15:13<13:04:36, 5.81s/it] {'loss': 0.5034, 'learning_rate': 1.6172705530049575e-05, 'epoch': 0.31} + 31%|███ | 3631/11728 [2:15:13<13:04:36, 5.81s/it] 31%|███ | 3632/11728 [2:15:19<13:01:33, 5.79s/it] {'loss': 0.4998, 'learning_rate': 1.6170532605688115e-05, 'epoch': 0.31} + 31%|███ | 3632/11728 [2:15:19<13:01:33, 5.79s/it] 31%|███ | 3633/11728 [2:15:26<13:26:26, 5.98s/it] {'loss': 0.49, 'learning_rate': 1.6168359210736072e-05, 'epoch': 0.31} + 31%|███ | 3633/11728 [2:15:26<13:26:26, 5.98s/it] 31%|███ | 3634/11728 [2:15:31<13:18:35, 5.92s/it] {'loss': 0.4929, 'learning_rate': 1.616618534535921e-05, 'epoch': 0.31} + 31%|███ | 3634/11728 [2:15:31<13:18:35, 5.92s/it] 31%|███ | 3635/11728 [2:15:37<13:12:47, 5.88s/it] {'loss': 0.5037, 'learning_rate': 1.6164011009723308e-05, 'epoch': 0.31} + 31%|███ | 3635/11728 [2:15:37<13:12:47, 5.88s/it] 31%|███ | 3636/11728 [2:15:43<13:16:56, 5.91s/it] {'loss': 0.5016, 'learning_rate': 1.616183620399419e-05, 'epoch': 0.31} + 31%|███ | 3636/11728 [2:15:43<13:16:56, 5.91s/it] 31%|███ | 3637/11728 [2:15:49<13:10:35, 5.86s/it] {'loss': 0.4892, 'learning_rate': 1.6159660928337723e-05, 'epoch': 0.31} + 31%|███ | 3637/11728 [2:15:49<13:10:35, 5.86s/it] 31%|███ | 3638/11728 [2:15:55<13:12:03, 5.87s/it] {'loss': 0.5075, 'learning_rate': 1.6157485182919795e-05, 'epoch': 0.31} + 31%|███ | 3638/11728 [2:15:55<13:12:03, 5.87s/it] 31%|███ | 3639/11728 [2:16:00<12:59:45, 5.78s/it] {'loss': 0.5042, 'learning_rate': 1.6155308967906344e-05, 'epoch': 0.31} + 31%|███ | 3639/11728 [2:16:00<12:59:45, 5.78s/it] 31%|███ | 3640/11728 [2:16:06<12:52:55, 5.73s/it] {'loss': 0.4821, 'learning_rate': 1.6153132283463327e-05, 'epoch': 0.31} + 31%|███ | 3640/11728 [2:16:06<12:52:55, 5.73s/it] 31%|███ | 3641/11728 [2:16:12<12:48:55, 5.70s/it] {'loss': 0.4871, 'learning_rate': 1.615095512975676e-05, 'epoch': 0.31} + 31%|███ | 3641/11728 [2:16:12<12:48:55, 5.70s/it] 31%|███ | 3642/11728 [2:16:17<12:47:24, 5.69s/it] {'loss': 0.4873, 'learning_rate': 1.6148777506952672e-05, 'epoch': 0.31} + 31%|███ | 3642/11728 [2:16:17<12:47:24, 5.69s/it] 31%|███ | 3643/11728 [2:16:23<12:58:05, 5.77s/it] {'loss': 0.4749, 'learning_rate': 1.614659941521714e-05, 'epoch': 0.31} + 31%|███ | 3643/11728 [2:16:23<12:58:05, 5.77s/it] 31%|███ | 3644/11728 [2:16:29<13:00:14, 5.79s/it] {'loss': 0.5205, 'learning_rate': 1.6144420854716277e-05, 'epoch': 0.31} + 31%|███ | 3644/11728 [2:16:29<13:00:14, 5.79s/it] 31%|███ | 3645/11728 [2:16:35<13:07:25, 5.85s/it] {'loss': 0.5013, 'learning_rate': 1.6142241825616226e-05, 'epoch': 0.31} + 31%|███ | 3645/11728 [2:16:35<13:07:25, 5.85s/it] 31%|███ | 3646/11728 [2:16:41<13:19:58, 5.94s/it] {'loss': 0.4808, 'learning_rate': 1.614006232808317e-05, 'epoch': 0.31} + 31%|███ | 3646/11728 [2:16:41<13:19:58, 5.94s/it] 31%|███ | 3647/11728 [2:16:47<13:14:50, 5.90s/it] {'loss': 0.4791, 'learning_rate': 1.6137882362283328e-05, 'epoch': 0.31} + 31%|███ | 3647/11728 [2:16:47<13:14:50, 5.90s/it] 31%|███ | 3648/11728 [2:16:53<13:06:30, 5.84s/it] {'loss': 0.5009, 'learning_rate': 1.6135701928382952e-05, 'epoch': 0.31} + 31%|███ | 3648/11728 [2:16:53<13:06:30, 5.84s/it] 31%|███ | 3649/11728 [2:16:58<12:53:15, 5.74s/it] {'loss': 0.499, 'learning_rate': 1.613352102654833e-05, 'epoch': 0.31} + 31%|███ | 3649/11728 [2:16:58<12:53:15, 5.74s/it]5 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +42 0 AutoResumeHook: Checking whether to suspend...AutoResumeHook: Checking whether to suspend... + + AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... + 31%|███ | 3650/11728 [2:17:04<12:58:15, 5.78s/it]6 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... + {'loss': 0.5008, 'learning_rate': 1.613133965694579e-05, 'epoch': 0.31} + 31%|███ | 3650/11728 [2:17:04<12:58:15, 5.78s/it] 31%|███ | 3651/11728 [2:17:10<12:54:32, 5.75s/it] {'loss': 0.4856, 'learning_rate': 1.6129157819741692e-05, 'epoch': 0.31} + 31%|███ | 3651/11728 [2:17:10<12:54:32, 5.75s/it] 31%|███ | 3652/11728 [2:17:15<12:49:14, 5.72s/it] {'loss': 0.4889, 'learning_rate': 1.6126975515102424e-05, 'epoch': 0.31} + 31%|███ | 3652/11728 [2:17:15<12:49:14, 5.72s/it] 31%|███ | 3653/11728 [2:17:22<13:17:56, 5.93s/it] {'loss': 0.4982, 'learning_rate': 1.612479274319443e-05, 'epoch': 0.31} + 31%|███ | 3653/11728 [2:17:22<13:17:56, 5.93s/it] 31%|███ | 3654/11728 [2:17:27<13:07:22, 5.85s/it] {'loss': 0.4844, 'learning_rate': 1.6122609504184166e-05, 'epoch': 0.31} + 31%|███ | 3654/11728 [2:17:27<13:07:22, 5.85s/it] 31%|███ | 3655/11728 [2:17:33<13:13:48, 5.90s/it] {'loss': 0.5086, 'learning_rate': 1.6120425798238145e-05, 'epoch': 0.31} + 31%|███ | 3655/11728 [2:17:33<13:13:48, 5.90s/it]WARNING: tokenization mismatch: 1 vs. 1419. [[{'from': 'human', 'value': 'ASSISTANT: You are an innovative tax advisory firm with the following knowledge and traits.\n\nKNOWLEDGE: Tax advisor, junior tax advisor, senior tax advisor, financial strategist, tax regulations.\n\nTRAITS: Empathy, innovation, solution orientation, professionalism, communication, client focus.\n\nTASK: Use your knowledge to develop an internal strategy document. We are a tax advisory firm looking to identify 10 creative ways to improve client satisfaction and loyalty. Focus on ideas that are tailored to the needs of tax advisors and enhance the overall client experience.\n\nOUTPUT: A table in German containing 10 creative strategies to improve client satisfaction and loyalty for a tax advisory firm, including a brief description for each.'}, {'from': 'gpt', 'value': 'Tabelle: 10 kreative Strategien zur Steigerung der Kundenzufriedenheit und -loyalität in einer Steuerberatungskanzlei\n\n| Nr. | Strategie | Beschreibung |\n| --- | --- | --- |\n| 1 | Personalisierter Service | Jeder Kunde erhält einen dedizierten Steuerberater, der auf seine individuellen Bedürfnisse und Anliegen eingeht. |\n| 2 | Proaktive Steuerplanung | Regelmäßige Updates und Empfehlungen zur Steueroptimierung, basierend auf aktuellen Gesetzesänderungen und Kundenzielen. |\n| 3 | Umfassende Schulungsangebote | Kostenlose Workshops und Webinare, um das Steuerwissen der Kunden zu erweitern und den Umgang mit Steuerthemen zu erleichtern. |\n| 4 | Digitale Plattform | Eine benutzerfreundliche Online-Plattform, die den Kunden den Zugriff auf ihre Steuerdokumente und den Kontakt zum Berater erleichtert. |\n| 5 | Einführung von Steuer-Coaching | Persönliche Coaching-Sitzungen, um den Kunden dabei zu unterstützen, ihre steuerlichen Ziele und Möglichkeiten besser zu verstehen. |\n| 6 | Schnelle Reaktionszeiten | Verbindliches Versprechen, innerhalb von 24 Stunden auf Kundenanfragen zu reagieren, um eine effiziente Kommunikation zu gewährleisten. |\n| 7 | Transparente Preisgestaltung | Klare und faire Preisstrukturen, die den Kunden im Voraus bekannt sind, um böse Überraschungen zu vermeiden. |\n| 8 | Individuelle Jahresgespräche | Regelmäßige persönliche Jahresgespräche, um auf die Bedürfnisse und Ziele der Kunden einzugehen und die Zusammenarbeit zu stärken. |\n| 9 | Kunden-Feedback-System | Einrichtung eines einfachen Feedback-Systems, um Kundenmeinungen und Verbesserungsvorschläge aktiv einzuholen und umzusetzen. |\n| 10 | Steuer-Newsletter und Informationsangebot | Monatlicher Newsletter mit aktuellen Steuerinformationen und Tipps, der den Kunden einen Mehrwert bietet und sie auf dem Laufenden hält. |'}, {'from': 'human', 'value': 'Bitte etwas kreativer und auf bezugnehmend auf die zwischenmenschliche Ebene.'}, {'from': 'gpt', 'value': 'Tabelle: 10 kreative Strategien zur Steigerung der Kundenzufriedenheit und -loyalität in einer Steuerberatungskanzlei mit Fokus auf zwischenmenschlicher Ebene\n\n| Nr. | Strategie | Beschreibung |\n| --- | --- | --- |\n| 1 | Kunden-Events | Organisation von regelmäßigen, informellen Veranstaltungen, um den persönlichen Kontakt zwischen Klienten und Beratern zu fördern. |\n| 2 | Persönliche Geburtstagsgrüße | Individuelle Geburtstagskarten oder -nachrichten für jeden Kunden, um Wertschätzung zu zeigen und Beziehungen zu stärken. |\n| 3 | Kundenbefragung & Anpassung | Aktives Einholen von Kundenmeinungen zur individuellen Betreuung und Anpassung unserer Leistungen entsprechend der Kundenbedürfnisse. |\n| 4 | Teamvorstellung & Empathie | Vorstellung unserer Berater auf der Firmenwebsite und in sozialen Medien, um eine persönliche und empathische Beziehung zum Kunden aufzubauen. |\n| 5 | Kunden-Mentoring-Programm | Schaffung eines Programms, bei dem langjährige Kunden als Mentoren für Neukunden fungieren, um Vertrauen und Loyalität zu fördern. |\n| 6 | "Tag der offenen Tür" | Einladung der Kunden zu einem "Tag der offenen Tür" in unserer Kanzlei, um ihnen einen persönlichen Einblick in unsere Arbeitsweise zu geben. |\n| 7 | Individuelle Erfolgsgeschichten | Erstellung von individuellen Erfolgsgeschichten für jeden Kunden, um ihre steuerlichen Erfolge hervorzuheben und ihre Loyalität zu stärken. |\n| 8 | Gemeinsame soziale Projekte | Zusammenarbeit mit Kunden an sozialen Projekten und Spendenaktionen, um gemeinsame Werte zu teilen und die Zusammenarbeit zu fördern. |\n| 9 | Flexibilität in der Kommunikation | Anbieten verschiedener Kommunikationswege (Telefon, E-Mail, Videoanruf, etc.), um auf die individuellen Bedürfnisse der Kunden einzugehen. |\n| 10 | Jährliches Kunden-Dankeschön | Überraschung der Kunden mit einer kleinen Aufmerksamkeit oder einem Dankeschön-Event, um die Wertschätzung für ihre Treue auszudrücken. |'}]] (ignored) + 31%|███ | 3656/11728 [2:17:39<13:08:17, 5.86s/it] {'loss': 0.4755, 'learning_rate': 1.6118241625522898e-05, 'epoch': 0.31} + 31%|███ | 3656/11728 [2:17:39<13:08:17, 5.86s/it] 31%|███ | 3657/11728 [2:17:45<13:05:27, 5.84s/it] {'loss': 0.5097, 'learning_rate': 1.6116056986205003e-05, 'epoch': 0.31} + 31%|███ | 3657/11728 [2:17:45<13:05:27, 5.84s/it] 31%|███ | 3658/11728 [2:17:51<13:05:27, 5.84s/it] {'loss': 0.4937, 'learning_rate': 1.6113871880451062e-05, 'epoch': 0.31} + 31%|███ | 3658/11728 [2:17:51<13:05:27, 5.84s/it] 31%|███ | 3659/11728 [2:17:57<13:05:20, 5.84s/it] {'loss': 0.4724, 'learning_rate': 1.6111686308427734e-05, 'epoch': 0.31} + 31%|███ | 3659/11728 [2:17:57<13:05:20, 5.84s/it] 31%|███ | 3660/11728 [2:18:03<13:08:19, 5.86s/it] {'loss': 0.4936, 'learning_rate': 1.6109500270301694e-05, 'epoch': 0.31} + 31%|███ | 3660/11728 [2:18:03<13:08:19, 5.86s/it] 31%|███ | 3661/11728 [2:18:08<13:04:52, 5.84s/it] {'loss': 0.4695, 'learning_rate': 1.610731376623965e-05, 'epoch': 0.31} + 31%|███ | 3661/11728 [2:18:08<13:04:52, 5.84s/it] 31%|███ | 3662/11728 [2:18:14<13:09:43, 5.87s/it] {'loss': 0.486, 'learning_rate': 1.6105126796408367e-05, 'epoch': 0.31} + 31%|███ | 3662/11728 [2:18:14<13:09:43, 5.87s/it] 31%|███ | 3663/11728 [2:18:20<13:03:09, 5.83s/it] {'loss': 0.4706, 'learning_rate': 1.610293936097462e-05, 'epoch': 0.31} + 31%|███ | 3663/11728 [2:18:20<13:03:09, 5.83s/it] 31%|███ | 3664/11728 [2:18:26<13:01:43, 5.82s/it] {'loss': 0.5029, 'learning_rate': 1.6100751460105244e-05, 'epoch': 0.31} + 31%|███ | 3664/11728 [2:18:26<13:01:43, 5.82s/it] 31%|███▏ | 3665/11728 [2:18:32<13:11:53, 5.89s/it] {'loss': 0.5005, 'learning_rate': 1.609856309396709e-05, 'epoch': 0.31} + 31%|███▏ | 3665/11728 [2:18:32<13:11:53, 5.89s/it] 31%|███▏ | 3666/11728 [2:18:38<13:09:49, 5.88s/it] {'loss': 0.5134, 'learning_rate': 1.6096374262727055e-05, 'epoch': 0.31} + 31%|███▏ | 3666/11728 [2:18:38<13:09:49, 5.88s/it] 31%|███▏ | 3667/11728 [2:18:44<13:05:03, 5.84s/it] {'loss': 0.4935, 'learning_rate': 1.6094184966552066e-05, 'epoch': 0.31} + 31%|███▏ | 3667/11728 [2:18:44<13:05:03, 5.84s/it] 31%|███▏ | 3668/11728 [2:18:49<13:03:12, 5.83s/it] {'loss': 0.5092, 'learning_rate': 1.609199520560909e-05, 'epoch': 0.31} + 31%|███▏ | 3668/11728 [2:18:49<13:03:12, 5.83s/it] 31%|███▏ | 3669/11728 [2:18:55<12:56:31, 5.78s/it] {'loss': 0.4606, 'learning_rate': 1.6089804980065124e-05, 'epoch': 0.31} + 31%|███▏ | 3669/11728 [2:18:55<12:56:31, 5.78s/it] 31%|███▏ | 3670/11728 [2:19:01<12:54:42, 5.77s/it] {'loss': 0.4868, 'learning_rate': 1.608761429008721e-05, 'epoch': 0.31} + 31%|███▏ | 3670/11728 [2:19:01<12:54:42, 5.77s/it] 31%|███▏ | 3671/11728 [2:19:06<12:46:53, 5.71s/it] {'loss': 0.507, 'learning_rate': 1.608542313584241e-05, 'epoch': 0.31} + 31%|███▏ | 3671/11728 [2:19:06<12:46:53, 5.71s/it] 31%|███▏ | 3672/11728 [2:19:12<12:58:52, 5.80s/it] {'loss': 0.4625, 'learning_rate': 1.608323151749784e-05, 'epoch': 0.31} + 31%|███▏ | 3672/11728 [2:19:12<12:58:52, 5.80s/it] 31%|███▏ | 3673/11728 [2:19:19<13:20:43, 5.96s/it] {'loss': 0.4879, 'learning_rate': 1.6081039435220637e-05, 'epoch': 0.31} + 31%|███▏ | 3673/11728 [2:19:19<13:20:43, 5.96s/it] 31%|███▏ | 3674/11728 [2:19:24<13:12:07, 5.90s/it] {'loss': 0.4934, 'learning_rate': 1.6078846889177978e-05, 'epoch': 0.31} + 31%|███▏ | 3674/11728 [2:19:24<13:12:07, 5.90s/it] 31%|███▏ | 3675/11728 [2:19:30<13:16:09, 5.93s/it] {'loss': 0.4729, 'learning_rate': 1.6076653879537074e-05, 'epoch': 0.31} + 31%|███▏ | 3675/11728 [2:19:30<13:16:09, 5.93s/it] 31%|███▏ | 3676/11728 [2:19:36<13:03:34, 5.84s/it] {'loss': 0.4885, 'learning_rate': 1.607446040646518e-05, 'epoch': 0.31} + 31%|███▏ | 3676/11728 [2:19:36<13:03:34, 5.84s/it] 31%|███▏ | 3677/11728 [2:19:42<12:55:51, 5.78s/it] {'loss': 0.4832, 'learning_rate': 1.6072266470129573e-05, 'epoch': 0.31} + 31%|███▏ | 3677/11728 [2:19:42<12:55:51, 5.78s/it] 31%|███▏ | 3678/11728 [2:19:48<13:02:38, 5.83s/it] {'loss': 0.4898, 'learning_rate': 1.607007207069758e-05, 'epoch': 0.31} + 31%|███▏ | 3678/11728 [2:19:48<13:02:38, 5.83s/it] 31%|███▏ | 3679/11728 [2:19:54<13:19:07, 5.96s/it] {'loss': 0.4948, 'learning_rate': 1.606787720833654e-05, 'epoch': 0.31} + 31%|███▏ | 3679/11728 [2:19:54<13:19:07, 5.96s/it] 31%|███▏ | 3680/11728 [2:20:00<13:30:14, 6.04s/it] {'loss': 0.5241, 'learning_rate': 1.6065681883213854e-05, 'epoch': 0.31} + 31%|███▏ | 3680/11728 [2:20:00<13:30:14, 6.04s/it] 31%|███▏ | 3681/11728 [2:20:06<13:15:20, 5.93s/it] {'loss': 0.4878, 'learning_rate': 1.606348609549695e-05, 'epoch': 0.31} + 31%|███▏ | 3681/11728 [2:20:06<13:15:20, 5.93s/it] 31%|███▏ | 3682/11728 [2:20:12<13:28:51, 6.03s/it] {'loss': 0.5015, 'learning_rate': 1.6061289845353276e-05, 'epoch': 0.31} + 31%|███▏ | 3682/11728 [2:20:12<13:28:51, 6.03s/it] 31%|███▏ | 3683/11728 [2:20:18<13:09:00, 5.88s/it] {'loss': 0.4908, 'learning_rate': 1.6059093132950336e-05, 'epoch': 0.31} + 31%|███▏ | 3683/11728 [2:20:18<13:09:00, 5.88s/it] 31%|███▏ | 3684/11728 [2:20:24<13:27:21, 6.02s/it] {'loss': 0.4874, 'learning_rate': 1.6056895958455657e-05, 'epoch': 0.31} + 31%|███▏ | 3684/11728 [2:20:24<13:27:21, 6.02s/it] 31%|███▏ | 3685/11728 [2:20:30<13:14:57, 5.93s/it] {'loss': 0.4719, 'learning_rate': 1.6054698322036806e-05, 'epoch': 0.31} + 31%|███▏ | 3685/11728 [2:20:30<13:14:57, 5.93s/it] 31%|███▏ | 3686/11728 [2:20:36<13:16:36, 5.94s/it] {'loss': 0.496, 'learning_rate': 1.605250022386138e-05, 'epoch': 0.31} + 31%|███▏ | 3686/11728 [2:20:36<13:16:36, 5.94s/it] 31%|███▏ | 3687/11728 [2:20:41<13:09:56, 5.89s/it] {'loss': 0.4999, 'learning_rate': 1.6050301664097023e-05, 'epoch': 0.31} + 31%|███▏ | 3687/11728 [2:20:41<13:09:56, 5.89s/it] 31%|███▏ | 3688/11728 [2:20:48<13:20:48, 5.98s/it] {'loss': 0.5015, 'learning_rate': 1.60481026429114e-05, 'epoch': 0.31} + 31%|███▏ | 3688/11728 [2:20:48<13:20:48, 5.98s/it] 31%|███▏ | 3689/11728 [2:20:53<13:07:26, 5.88s/it] {'loss': 0.5052, 'learning_rate': 1.6045903160472218e-05, 'epoch': 0.31} + 31%|███▏ | 3689/11728 [2:20:53<13:07:26, 5.88s/it] 31%|███▏ | 3690/11728 [2:20:59<12:59:40, 5.82s/it] {'loss': 0.4962, 'learning_rate': 1.6043703216947223e-05, 'epoch': 0.31} + 31%|███▏ | 3690/11728 [2:20:59<12:59:40, 5.82s/it] 31%|███▏ | 3691/11728 [2:21:05<12:54:26, 5.78s/it] {'loss': 0.457, 'learning_rate': 1.6041502812504185e-05, 'epoch': 0.31} + 31%|███▏ | 3691/11728 [2:21:05<12:54:26, 5.78s/it] 31%|███▏ | 3692/11728 [2:21:10<12:49:35, 5.75s/it] {'loss': 0.5011, 'learning_rate': 1.6039301947310925e-05, 'epoch': 0.31} + 31%|███▏ | 3692/11728 [2:21:10<12:49:35, 5.75s/it] 31%|███▏ | 3693/11728 [2:21:16<12:50:38, 5.75s/it] {'loss': 0.5002, 'learning_rate': 1.6037100621535283e-05, 'epoch': 0.31} + 31%|███▏ | 3693/11728 [2:21:16<12:50:38, 5.75s/it] 31%|███▏ | 3694/11728 [2:21:22<12:53:45, 5.78s/it] {'loss': 0.4836, 'learning_rate': 1.6034898835345142e-05, 'epoch': 0.31} + 31%|███▏ | 3694/11728 [2:21:22<12:53:45, 5.78s/it] 32%|███▏ | 3695/11728 [2:21:28<12:45:28, 5.72s/it] {'loss': 0.476, 'learning_rate': 1.603269658890842e-05, 'epoch': 0.32} + 32%|███▏ | 3695/11728 [2:21:28<12:45:28, 5.72s/it] 32%|███▏ | 3696/11728 [2:21:33<12:46:20, 5.72s/it] {'loss': 0.4848, 'learning_rate': 1.6030493882393076e-05, 'epoch': 0.32} + 32%|███▏ | 3696/11728 [2:21:33<12:46:20, 5.72s/it] 32%|███▏ | 3697/11728 [2:21:39<12:41:32, 5.69s/it] {'loss': 0.4908, 'learning_rate': 1.6028290715967087e-05, 'epoch': 0.32} + 32%|███▏ | 3697/11728 [2:21:39<12:41:32, 5.69s/it] 32%|███▏ | 3698/11728 [2:21:45<12:45:30, 5.72s/it] {'loss': 0.4754, 'learning_rate': 1.6026087089798483e-05, 'epoch': 0.32} + 32%|███▏ | 3698/11728 [2:21:45<12:45:30, 5.72s/it] 32%|███▏ | 3699/11728 [2:21:50<12:44:13, 5.71s/it] {'loss': 0.488, 'learning_rate': 1.6023883004055317e-05, 'epoch': 0.32} + 32%|███▏ | 3699/11728 [2:21:50<12:44:13, 5.71s/it]7 AutoResumeHook: Checking whether to suspend... +04 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... + 32%|███▏ | 3700/11728 [2:21:56<12:35:05, 5.64s/it]1 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... + {'loss': 0.46, 'learning_rate': 1.6021678458905686e-05, 'epoch': 0.32} + 32%|███▏ | 3700/11728 [2:21:56<12:35:05, 5.64s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-3700/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-3700/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-3700/mm_projector +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/torch/nn/modules/module.py:1802: UserWarning: Positional args are being deprecated, use kwargs instead. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details. + warnings.warn( + 32%|███▏ | 3701/11728 [2:22:25<28:32:44, 12.80s/it] {'loss': 0.4774, 'learning_rate': 1.6019473454517714e-05, 'epoch': 0.32} + 32%|███▏ | 3701/11728 [2:22:25<28:32:44, 12.80s/it] 32%|███▏ | 3702/11728 [2:22:31<23:51:51, 10.70s/it] {'loss': 0.4765, 'learning_rate': 1.601726799105957e-05, 'epoch': 0.32} + 32%|███▏ | 3702/11728 [2:22:31<23:51:51, 10.70s/it] 32%|███▏ | 3703/11728 [2:22:37<20:57:10, 9.40s/it] {'loss': 0.503, 'learning_rate': 1.6015062068699445e-05, 'epoch': 0.32} + 32%|███▏ | 3703/11728 [2:22:37<20:57:10, 9.40s/it] 32%|███▏ | 3704/11728 [2:22:43<18:23:23, 8.25s/it] {'loss': 0.4927, 'learning_rate': 1.6012855687605572e-05, 'epoch': 0.32} + 32%|███▏ | 3704/11728 [2:22:43<18:23:23, 8.25s/it] 32%|███▏ | 3705/11728 [2:22:49<16:41:57, 7.49s/it] {'loss': 0.484, 'learning_rate': 1.6010648847946225e-05, 'epoch': 0.32} + 32%|███▏ | 3705/11728 [2:22:49<16:41:57, 7.49s/it] 32%|███▏ | 3706/11728 [2:22:55<15:47:08, 7.08s/it] {'loss': 0.5042, 'learning_rate': 1.6008441549889703e-05, 'epoch': 0.32} + 32%|███▏ | 3706/11728 [2:22:55<15:47:08, 7.08s/it] 32%|███▏ | 3707/11728 [2:23:01<15:05:00, 6.77s/it] {'loss': 0.4921, 'learning_rate': 1.600623379360434e-05, 'epoch': 0.32} + 32%|███▏ | 3707/11728 [2:23:01<15:05:00, 6.77s/it] 32%|███▏ | 3708/11728 [2:23:07<14:20:14, 6.44s/it] {'loss': 0.477, 'learning_rate': 1.6004025579258517e-05, 'epoch': 0.32} + 32%|███▏ | 3708/11728 [2:23:07<14:20:14, 6.44s/it] 32%|███▏ | 3709/11728 [2:23:12<13:54:19, 6.24s/it] {'loss': 0.4729, 'learning_rate': 1.6001816907020634e-05, 'epoch': 0.32} + 32%|███▏ | 3709/11728 [2:23:12<13:54:19, 6.24s/it] 32%|███▏ | 3710/11728 [2:23:19<13:54:04, 6.24s/it] {'loss': 0.4977, 'learning_rate': 1.599960777705914e-05, 'epoch': 0.32} + 32%|███▏ | 3710/11728 [2:23:19<13:54:04, 6.24s/it] 32%|███▏ | 3711/11728 [2:23:25<13:40:55, 6.14s/it] {'loss': 0.4643, 'learning_rate': 1.599739818954251e-05, 'epoch': 0.32} + 32%|███▏ | 3711/11728 [2:23:25<13:40:55, 6.14s/it] 32%|███▏ | 3712/11728 [2:23:30<13:27:43, 6.05s/it] {'loss': 0.5209, 'learning_rate': 1.599518814463925e-05, 'epoch': 0.32} + 32%|███▏ | 3712/11728 [2:23:30<13:27:43, 6.05s/it] 32%|███▏ | 3713/11728 [2:23:36<13:26:14, 6.04s/it] {'loss': 0.494, 'learning_rate': 1.599297764251792e-05, 'epoch': 0.32} + 32%|███▏ | 3713/11728 [2:23:36<13:26:14, 6.04s/it] 32%|███▏ | 3714/11728 [2:23:42<13:26:54, 6.04s/it] {'loss': 0.4945, 'learning_rate': 1.599076668334709e-05, 'epoch': 0.32} + 32%|███▏ | 3714/11728 [2:23:42<13:26:54, 6.04s/it] 32%|███▏ | 3715/11728 [2:23:48<13:14:36, 5.95s/it] {'loss': 0.4985, 'learning_rate': 1.5988555267295383e-05, 'epoch': 0.32} + 32%|███▏ | 3715/11728 [2:23:48<13:14:36, 5.95s/it] 32%|███▏ | 3716/11728 [2:23:54<13:03:35, 5.87s/it] {'loss': 0.4985, 'learning_rate': 1.598634339453145e-05, 'epoch': 0.32} + 32%|███▏ | 3716/11728 [2:23:54<13:03:35, 5.87s/it] 32%|███▏ | 3717/11728 [2:24:00<13:13:35, 5.94s/it] {'loss': 0.4818, 'learning_rate': 1.598413106522398e-05, 'epoch': 0.32} + 32%|███▏ | 3717/11728 [2:24:00<13:13:35, 5.94s/it] 32%|███▏ | 3718/11728 [2:24:06<13:03:30, 5.87s/it] {'loss': 0.4968, 'learning_rate': 1.598191827954169e-05, 'epoch': 0.32} + 32%|███▏ | 3718/11728 [2:24:06<13:03:30, 5.87s/it] 32%|███▏ | 3719/11728 [2:24:12<13:19:42, 5.99s/it] {'loss': 0.4894, 'learning_rate': 1.5979705037653338e-05, 'epoch': 0.32} + 32%|███▏ | 3719/11728 [2:24:12<13:19:42, 5.99s/it] 32%|███▏ | 3720/11728 [2:24:18<13:16:31, 5.97s/it] {'loss': 0.489, 'learning_rate': 1.5977491339727716e-05, 'epoch': 0.32} + 32%|███▏ | 3720/11728 [2:24:18<13:16:31, 5.97s/it] 32%|███▏ | 3721/11728 [2:24:24<13:06:46, 5.90s/it] {'loss': 0.4743, 'learning_rate': 1.597527718593365e-05, 'epoch': 0.32} + 32%|███▏ | 3721/11728 [2:24:24<13:06:46, 5.90s/it] 32%|███▏ | 3722/11728 [2:24:29<13:01:08, 5.85s/it] {'loss': 0.4853, 'learning_rate': 1.5973062576439996e-05, 'epoch': 0.32} + 32%|███▏ | 3722/11728 [2:24:29<13:01:08, 5.85s/it] 32%|███▏ | 3723/11728 [2:24:35<13:06:58, 5.90s/it] {'loss': 0.4798, 'learning_rate': 1.5970847511415656e-05, 'epoch': 0.32} + 32%|███▏ | 3723/11728 [2:24:35<13:06:58, 5.90s/it] 32%|███▏ | 3724/11728 [2:24:41<13:00:46, 5.85s/it] {'loss': 0.4723, 'learning_rate': 1.5968631991029554e-05, 'epoch': 0.32} + 32%|███▏ | 3724/11728 [2:24:41<13:00:46, 5.85s/it] 32%|███▏ | 3725/11728 [2:24:47<12:55:42, 5.82s/it] {'loss': 0.4883, 'learning_rate': 1.5966416015450664e-05, 'epoch': 0.32} + 32%|███▏ | 3725/11728 [2:24:47<12:55:42, 5.82s/it] 32%|███▏ | 3726/11728 [2:24:53<13:05:13, 5.89s/it] {'loss': 0.5237, 'learning_rate': 1.5964199584847975e-05, 'epoch': 0.32} + 32%|███▏ | 3726/11728 [2:24:53<13:05:13, 5.89s/it] 32%|███▏ | 3727/11728 [2:24:59<13:04:03, 5.88s/it] {'loss': 0.4902, 'learning_rate': 1.596198269939053e-05, 'epoch': 0.32} + 32%|███▏ | 3727/11728 [2:24:59<13:04:03, 5.88s/it] 32%|███▏ | 3728/11728 [2:25:04<12:53:45, 5.80s/it] {'loss': 0.4902, 'learning_rate': 1.595976535924739e-05, 'epoch': 0.32} + 32%|███▏ | 3728/11728 [2:25:04<12:53:45, 5.80s/it] 32%|███▏ | 3729/11728 [2:25:10<12:44:25, 5.73s/it] {'loss': 0.4797, 'learning_rate': 1.5957547564587662e-05, 'epoch': 0.32} + 32%|███▏ | 3729/11728 [2:25:10<12:44:25, 5.73s/it] 32%|███▏ | 3730/11728 [2:25:15<12:37:20, 5.68s/it] {'loss': 0.4649, 'learning_rate': 1.5955329315580487e-05, 'epoch': 0.32} + 32%|███▏ | 3730/11728 [2:25:15<12:37:20, 5.68s/it] 32%|███▏ | 3731/11728 [2:25:21<12:35:42, 5.67s/it] {'loss': 0.4917, 'learning_rate': 1.5953110612395035e-05, 'epoch': 0.32} + 32%|███▏ | 3731/11728 [2:25:21<12:35:42, 5.67s/it] 32%|███▏ | 3732/11728 [2:25:27<12:32:56, 5.65s/it] {'loss': 0.4746, 'learning_rate': 1.5950891455200516e-05, 'epoch': 0.32} + 32%|███▏ | 3732/11728 [2:25:27<12:32:56, 5.65s/it] 32%|███▏ | 3733/11728 [2:25:33<12:38:59, 5.70s/it] {'loss': 0.5044, 'learning_rate': 1.5948671844166167e-05, 'epoch': 0.32} + 32%|███▏ | 3733/11728 [2:25:33<12:38:59, 5.70s/it] 32%|███▏ | 3734/11728 [2:25:38<12:49:10, 5.77s/it] {'loss': 0.4792, 'learning_rate': 1.594645177946127e-05, 'epoch': 0.32} + 32%|███▏ | 3734/11728 [2:25:38<12:49:10, 5.77s/it] 32%|███▏ | 3735/11728 [2:25:44<12:40:47, 5.71s/it] {'loss': 0.465, 'learning_rate': 1.5944231261255133e-05, 'epoch': 0.32} + 32%|███▏ | 3735/11728 [2:25:44<12:40:47, 5.71s/it] 32%|███▏ | 3736/11728 [2:25:50<12:37:10, 5.68s/it] {'loss': 0.4843, 'learning_rate': 1.5942010289717108e-05, 'epoch': 0.32} + 32%|███▏ | 3736/11728 [2:25:50<12:37:10, 5.68s/it] 32%|███▏ | 3737/11728 [2:25:55<12:41:47, 5.72s/it] {'loss': 0.4572, 'learning_rate': 1.5939788865016565e-05, 'epoch': 0.32} + 32%|███▏ | 3737/11728 [2:25:55<12:41:47, 5.72s/it] 32%|███▏ | 3738/11728 [2:26:02<12:58:29, 5.85s/it] {'loss': 0.4975, 'learning_rate': 1.593756698732293e-05, 'epoch': 0.32} + 32%|███▏ | 3738/11728 [2:26:02<12:58:29, 5.85s/it] 32%|███▏ | 3739/11728 [2:26:08<13:04:47, 5.89s/it] {'loss': 0.5064, 'learning_rate': 1.5935344656805648e-05, 'epoch': 0.32} + 32%|███▏ | 3739/11728 [2:26:08<13:04:47, 5.89s/it] 32%|███▏ | 3740/11728 [2:26:14<13:04:51, 5.90s/it] {'loss': 0.5028, 'learning_rate': 1.5933121873634202e-05, 'epoch': 0.32} + 32%|███▏ | 3740/11728 [2:26:14<13:04:51, 5.90s/it] 32%|███▏ | 3741/11728 [2:26:19<12:50:07, 5.79s/it] {'loss': 0.4851, 'learning_rate': 1.593089863797811e-05, 'epoch': 0.32} + 32%|███▏ | 3741/11728 [2:26:19<12:50:07, 5.79s/it] 32%|███▏ | 3742/11728 [2:26:25<12:53:48, 5.81s/it] {'loss': 0.4951, 'learning_rate': 1.5928674950006927e-05, 'epoch': 0.32} + 32%|███▏ | 3742/11728 [2:26:25<12:53:48, 5.81s/it] 32%|███▏ | 3743/11728 [2:26:31<12:52:56, 5.81s/it] {'loss': 0.4764, 'learning_rate': 1.5926450809890245e-05, 'epoch': 0.32} + 32%|███▏ | 3743/11728 [2:26:31<12:52:56, 5.81s/it] 32%|███▏ | 3744/11728 [2:26:36<12:43:58, 5.74s/it] {'loss': 0.4835, 'learning_rate': 1.5924226217797677e-05, 'epoch': 0.32} + 32%|███▏ | 3744/11728 [2:26:36<12:43:58, 5.74s/it] 32%|███▏ | 3745/11728 [2:26:42<12:40:07, 5.71s/it] {'loss': 0.4897, 'learning_rate': 1.592200117389889e-05, 'epoch': 0.32} + 32%|███▏ | 3745/11728 [2:26:42<12:40:07, 5.71s/it] 32%|███▏ | 3746/11728 [2:26:48<12:36:41, 5.69s/it] {'loss': 0.4965, 'learning_rate': 1.5919775678363566e-05, 'epoch': 0.32} + 32%|███▏ | 3746/11728 [2:26:48<12:36:41, 5.69s/it] 32%|███▏ | 3747/11728 [2:26:53<12:43:52, 5.74s/it] {'loss': 0.4869, 'learning_rate': 1.5917549731361435e-05, 'epoch': 0.32} + 32%|███▏ | 3747/11728 [2:26:53<12:43:52, 5.74s/it] 32%|███▏ | 3748/11728 [2:26:59<12:46:57, 5.77s/it] {'loss': 0.4887, 'learning_rate': 1.5915323333062255e-05, 'epoch': 0.32} + 32%|███▏ | 3748/11728 [2:26:59<12:46:57, 5.77s/it] 32%|███▏ | 3749/11728 [2:27:05<12:43:21, 5.74s/it] {'loss': 0.4933, 'learning_rate': 1.5913096483635827e-05, 'epoch': 0.32} + 32%|███▏ | 3749/11728 [2:27:05<12:43:21, 5.74s/it]2 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... +01 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... + 32%|███▏ | 3750/11728 [2:27:10<12:34:56, 5.68s/it] {'loss': 0.4755, 'learning_rate': 1.591086918325197e-05, 'epoch': 0.32} + 32%|███▏ | 3750/11728 [2:27:10<12:34:56, 5.68s/it] 32%|███▏ | 3751/11728 [2:27:16<12:46:26, 5.76s/it] {'loss': 0.4755, 'learning_rate': 1.590864143208055e-05, 'epoch': 0.32} + 32%|███▏ | 3751/11728 [2:27:16<12:46:26, 5.76s/it] 32%|███▏ | 3752/11728 [2:27:22<12:39:06, 5.71s/it] {'loss': 0.4885, 'learning_rate': 1.5906413230291473e-05, 'epoch': 0.32} + 32%|███▏ | 3752/11728 [2:27:22<12:39:06, 5.71s/it] 32%|███▏ | 3753/11728 [2:27:28<12:37:17, 5.70s/it] {'loss': 0.4608, 'learning_rate': 1.5904184578054662e-05, 'epoch': 0.32} + 32%|███▏ | 3753/11728 [2:27:28<12:37:17, 5.70s/it] 32%|███▏ | 3754/11728 [2:27:34<12:42:45, 5.74s/it] {'loss': 0.5046, 'learning_rate': 1.5901955475540087e-05, 'epoch': 0.32} + 32%|███▏ | 3754/11728 [2:27:34<12:42:45, 5.74s/it] 32%|███▏ | 3755/11728 [2:27:39<12:46:44, 5.77s/it] {'loss': 0.4864, 'learning_rate': 1.5899725922917743e-05, 'epoch': 0.32} + 32%|███▏ | 3755/11728 [2:27:39<12:46:44, 5.77s/it] 32%|███▏ | 3756/11728 [2:27:45<12:53:58, 5.83s/it] {'loss': 0.483, 'learning_rate': 1.5897495920357673e-05, 'epoch': 0.32} + 32%|███▏ | 3756/11728 [2:27:45<12:53:58, 5.83s/it] 32%|███▏ | 3757/11728 [2:27:51<12:48:29, 5.78s/it] {'loss': 0.4855, 'learning_rate': 1.5895265468029943e-05, 'epoch': 0.32} + 32%|███▏ | 3757/11728 [2:27:51<12:48:29, 5.78s/it] 32%|███▏ | 3758/11728 [2:27:57<12:45:53, 5.77s/it] {'loss': 0.4861, 'learning_rate': 1.5893034566104656e-05, 'epoch': 0.32} + 32%|███▏ | 3758/11728 [2:27:57<12:45:53, 5.77s/it] 32%|███▏ | 3759/11728 [2:28:02<12:38:53, 5.71s/it] {'loss': 0.4826, 'learning_rate': 1.589080321475195e-05, 'epoch': 0.32} + 32%|███▏ | 3759/11728 [2:28:02<12:38:53, 5.71s/it] 32%|███▏ | 3760/11728 [2:28:08<12:49:11, 5.79s/it] {'loss': 0.488, 'learning_rate': 1.5888571414141997e-05, 'epoch': 0.32} + 32%|███▏ | 3760/11728 [2:28:08<12:49:11, 5.79s/it] 32%|███▏ | 3761/11728 [2:28:14<12:43:28, 5.75s/it] {'loss': 0.4954, 'learning_rate': 1.5886339164445007e-05, 'epoch': 0.32} + 32%|███▏ | 3761/11728 [2:28:14<12:43:28, 5.75s/it] 32%|███▏ | 3762/11728 [2:28:20<12:54:28, 5.83s/it] {'loss': 0.4711, 'learning_rate': 1.588410646583121e-05, 'epoch': 0.32} + 32%|███▏ | 3762/11728 [2:28:20<12:54:28, 5.83s/it] 32%|███▏ | 3763/11728 [2:28:26<12:55:38, 5.84s/it] {'loss': 0.469, 'learning_rate': 1.5881873318470894e-05, 'epoch': 0.32} + 32%|███▏ | 3763/11728 [2:28:26<12:55:38, 5.84s/it] 32%|███▏ | 3764/11728 [2:28:32<13:08:23, 5.94s/it] {'loss': 0.4839, 'learning_rate': 1.5879639722534364e-05, 'epoch': 0.32} + 32%|███▏ | 3764/11728 [2:28:32<13:08:23, 5.94s/it] 32%|███▏ | 3765/11728 [2:28:38<12:58:38, 5.87s/it] {'loss': 0.4974, 'learning_rate': 1.587740567819196e-05, 'epoch': 0.32} + 32%|███▏ | 3765/11728 [2:28:38<12:58:38, 5.87s/it] 32%|███▏ | 3766/11728 [2:28:44<13:22:07, 6.04s/it] {'loss': 0.4736, 'learning_rate': 1.587517118561406e-05, 'epoch': 0.32} + 32%|███▏ | 3766/11728 [2:28:44<13:22:07, 6.04s/it] 32%|███▏ | 3767/11728 [2:28:50<13:10:53, 5.96s/it] {'loss': 0.4785, 'learning_rate': 1.5872936244971083e-05, 'epoch': 0.32} + 32%|███▏ | 3767/11728 [2:28:50<13:10:53, 5.96s/it] 32%|███▏ | 3768/11728 [2:28:56<13:12:39, 5.97s/it] {'loss': 0.488, 'learning_rate': 1.587070085643346e-05, 'epoch': 0.32} + 32%|███▏ | 3768/11728 [2:28:56<13:12:39, 5.97s/it] 32%|███▏ | 3769/11728 [2:29:02<13:20:40, 6.04s/it] {'loss': 0.4923, 'learning_rate': 1.586846502017169e-05, 'epoch': 0.32} + 32%|███▏ | 3769/11728 [2:29:02<13:20:40, 6.04s/it] 32%|███▏ | 3770/11728 [2:29:08<13:14:24, 5.99s/it] {'loss': 0.4879, 'learning_rate': 1.5866228736356272e-05, 'epoch': 0.32} + 32%|███▏ | 3770/11728 [2:29:08<13:14:24, 5.99s/it] 32%|███▏ | 3771/11728 [2:29:14<13:14:16, 5.99s/it] {'loss': 0.4867, 'learning_rate': 1.5863992005157757e-05, 'epoch': 0.32} + 32%|███▏ | 3771/11728 [2:29:14<13:14:16, 5.99s/it] 32%|███▏ | 3772/11728 [2:29:20<13:00:43, 5.89s/it] {'loss': 0.5033, 'learning_rate': 1.5861754826746737e-05, 'epoch': 0.32} + 32%|███▏ | 3772/11728 [2:29:20<13:00:43, 5.89s/it] 32%|███▏ | 3773/11728 [2:29:26<13:11:24, 5.97s/it] {'loss': 0.5014, 'learning_rate': 1.585951720129382e-05, 'epoch': 0.32} + 32%|███▏ | 3773/11728 [2:29:26<13:11:24, 5.97s/it] 32%|███▏ | 3774/11728 [2:29:32<13:17:02, 6.01s/it] {'loss': 0.5109, 'learning_rate': 1.5857279128969657e-05, 'epoch': 0.32} + 32%|███▏ | 3774/11728 [2:29:32<13:17:02, 6.01s/it] 32%|███▏ | 3775/11728 [2:29:38<13:11:18, 5.97s/it] {'loss': 0.4924, 'learning_rate': 1.5855040609944935e-05, 'epoch': 0.32} + 32%|███▏ | 3775/11728 [2:29:38<13:11:18, 5.97s/it] 32%|███▏ | 3776/11728 [2:29:43<12:55:03, 5.85s/it] {'loss': 0.4881, 'learning_rate': 1.585280164439037e-05, 'epoch': 0.32} + 32%|███▏ | 3776/11728 [2:29:43<12:55:03, 5.85s/it] 32%|███▏ | 3777/11728 [2:29:49<12:43:03, 5.76s/it] {'loss': 0.4854, 'learning_rate': 1.585056223247672e-05, 'epoch': 0.32} + 32%|███▏ | 3777/11728 [2:29:49<12:43:03, 5.76s/it] 32%|███▏ | 3778/11728 [2:29:55<12:56:47, 5.86s/it] {'loss': 0.4924, 'learning_rate': 1.5848322374374765e-05, 'epoch': 0.32} + 32%|███▏ | 3778/11728 [2:29:55<12:56:47, 5.86s/it] 32%|███▏ | 3779/11728 [2:30:01<12:52:20, 5.83s/it] {'loss': 0.4819, 'learning_rate': 1.584608207025533e-05, 'epoch': 0.32} + 32%|███▏ | 3779/11728 [2:30:01<12:52:20, 5.83s/it] 32%|███▏ | 3780/11728 [2:30:07<12:54:14, 5.84s/it] {'loss': 0.485, 'learning_rate': 1.5843841320289274e-05, 'epoch': 0.32} + 32%|███▏ | 3780/11728 [2:30:07<12:54:14, 5.84s/it] 32%|███▏ | 3781/11728 [2:30:13<13:01:20, 5.90s/it] {'loss': 0.5159, 'learning_rate': 1.584160012464748e-05, 'epoch': 0.32} + 32%|███▏ | 3781/11728 [2:30:13<13:01:20, 5.90s/it] 32%|███▏ | 3782/11728 [2:30:18<12:45:20, 5.78s/it] {'loss': 0.49, 'learning_rate': 1.583935848350087e-05, 'epoch': 0.32} + 32%|███▏ | 3782/11728 [2:30:18<12:45:20, 5.78s/it] 32%|███▏ | 3783/11728 [2:30:24<12:43:44, 5.77s/it] {'loss': 0.4697, 'learning_rate': 1.5837116397020404e-05, 'epoch': 0.32} + 32%|███▏ | 3783/11728 [2:30:24<12:43:44, 5.77s/it] 32%|███▏ | 3784/11728 [2:30:30<12:48:48, 5.81s/it] {'loss': 0.5186, 'learning_rate': 1.5834873865377075e-05, 'epoch': 0.32} + 32%|███▏ | 3784/11728 [2:30:30<12:48:48, 5.81s/it] 32%|███▏ | 3785/11728 [2:30:36<12:55:44, 5.86s/it] {'loss': 0.4818, 'learning_rate': 1.5832630888741904e-05, 'epoch': 0.32} + 32%|███▏ | 3785/11728 [2:30:36<12:55:44, 5.86s/it] 32%|███▏ | 3786/11728 [2:30:42<12:54:52, 5.85s/it] {'loss': 0.4848, 'learning_rate': 1.583038746728595e-05, 'epoch': 0.32} + 32%|███▏ | 3786/11728 [2:30:42<12:54:52, 5.85s/it] 32%|███▏ | 3787/11728 [2:30:48<13:02:35, 5.91s/it] {'loss': 0.4849, 'learning_rate': 1.5828143601180306e-05, 'epoch': 0.32} + 32%|███▏ | 3787/11728 [2:30:48<13:02:35, 5.91s/it] 32%|███▏ | 3788/11728 [2:30:54<13:03:59, 5.92s/it] {'loss': 0.5068, 'learning_rate': 1.58258992905961e-05, 'epoch': 0.32} + 32%|███▏ | 3788/11728 [2:30:54<13:03:59, 5.92s/it] 32%|███▏ | 3789/11728 [2:31:00<13:03:23, 5.92s/it] {'loss': 0.4916, 'learning_rate': 1.582365453570449e-05, 'epoch': 0.32} + 32%|███▏ | 3789/11728 [2:31:00<13:03:23, 5.92s/it] 32%|███▏ | 3790/11728 [2:31:06<13:05:29, 5.94s/it] {'loss': 0.5017, 'learning_rate': 1.5821409336676676e-05, 'epoch': 0.32} + 32%|███▏ | 3790/11728 [2:31:06<13:05:29, 5.94s/it] 32%|███▏ | 3791/11728 [2:31:11<12:56:42, 5.87s/it] {'loss': 0.4922, 'learning_rate': 1.581916369368388e-05, 'epoch': 0.32} + 32%|███▏ | 3791/11728 [2:31:11<12:56:42, 5.87s/it] 32%|███▏ | 3792/11728 [2:31:17<12:54:59, 5.86s/it] {'loss': 0.4639, 'learning_rate': 1.581691760689737e-05, 'epoch': 0.32} + 32%|███▏ | 3792/11728 [2:31:17<12:54:59, 5.86s/it] 32%|███▏ | 3793/11728 [2:31:23<12:53:47, 5.85s/it] {'loss': 0.4832, 'learning_rate': 1.5814671076488434e-05, 'epoch': 0.32} + 32%|███▏ | 3793/11728 [2:31:23<12:53:47, 5.85s/it] 32%|███▏ | 3794/11728 [2:31:29<12:48:44, 5.81s/it] {'loss': 0.4823, 'learning_rate': 1.5812424102628406e-05, 'epoch': 0.32} + 32%|███▏ | 3794/11728 [2:31:29<12:48:44, 5.81s/it] 32%|███▏ | 3795/11728 [2:31:35<12:50:27, 5.83s/it] {'loss': 0.494, 'learning_rate': 1.5810176685488654e-05, 'epoch': 0.32} + 32%|███▏ | 3795/11728 [2:31:35<12:50:27, 5.83s/it] 32%|███▏ | 3796/11728 [2:31:40<12:56:51, 5.88s/it] {'loss': 0.4719, 'learning_rate': 1.5807928825240566e-05, 'epoch': 0.32} + 32%|███▏ | 3796/11728 [2:31:40<12:56:51, 5.88s/it] 32%|███▏ | 3797/11728 [2:31:46<12:47:25, 5.81s/it] {'loss': 0.4876, 'learning_rate': 1.5805680522055583e-05, 'epoch': 0.32} + 32%|███▏ | 3797/11728 [2:31:46<12:47:25, 5.81s/it] 32%|███▏ | 3798/11728 [2:31:52<13:03:27, 5.93s/it] {'loss': 0.4833, 'learning_rate': 1.5803431776105163e-05, 'epoch': 0.32} + 32%|███▏ | 3798/11728 [2:31:52<13:03:27, 5.93s/it] 32%|███▏ | 3799/11728 [2:31:58<13:11:44, 5.99s/it] {'loss': 0.4926, 'learning_rate': 1.5801182587560807e-05, 'epoch': 0.32} + 32%|███▏ | 3799/11728 [2:31:58<13:11:44, 5.99s/it]4 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... +0 21 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... +AutoResumeHook: Checking whether to suspend... + 32%|███▏ | 3800/11728 [2:32:04<13:05:59, 5.95s/it]3 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4871, 'learning_rate': 1.579893295659405e-05, 'epoch': 0.32} + 32%|███▏ | 3800/11728 [2:32:04<13:05:59, 5.95s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-3800/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-3800/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-3800/mm_projector +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/torch/nn/modules/module.py:1802: UserWarning: Positional args are being deprecated, use kwargs instead. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details. + warnings.warn( + 32%|███▏ | 3801/11728 [2:32:34<28:46:11, 13.07s/it] {'loss': 0.4909, 'learning_rate': 1.5796682883376453e-05, 'epoch': 0.32} + 32%|███▏ | 3801/11728 [2:32:34<28:46:11, 13.07s/it] 32%|███▏ | 3802/11728 [2:32:40<24:12:59, 11.00s/it] {'loss': 0.4862, 'learning_rate': 1.5794432368079617e-05, 'epoch': 0.32} + 32%|███▏ | 3802/11728 [2:32:40<24:12:59, 11.00s/it] 32%|███▏ | 3803/11728 [2:32:46<20:46:43, 9.44s/it] {'loss': 0.5013, 'learning_rate': 1.579218141087518e-05, 'epoch': 0.32} + 32%|███▏ | 3803/11728 [2:32:46<20:46:43, 9.44s/it] 32%|███▏ | 3804/11728 [2:32:52<18:19:24, 8.32s/it] {'loss': 0.4783, 'learning_rate': 1.5789930011934808e-05, 'epoch': 0.32} + 32%|███▏ | 3804/11728 [2:32:52<18:19:24, 8.32s/it] 32%|███▏ | 3805/11728 [2:32:57<16:33:53, 7.53s/it] {'loss': 0.4821, 'learning_rate': 1.57876781714302e-05, 'epoch': 0.32} + 32%|███▏ | 3805/11728 [2:32:57<16:33:53, 7.53s/it] 32%|███▏ | 3806/11728 [2:33:03<15:29:32, 7.04s/it] {'loss': 0.4831, 'learning_rate': 1.5785425889533094e-05, 'epoch': 0.32} + 32%|███▏ | 3806/11728 [2:33:03<15:29:32, 7.04s/it] 32%|███▏ | 3807/11728 [2:33:09<14:51:48, 6.76s/it] {'loss': 0.5084, 'learning_rate': 1.5783173166415253e-05, 'epoch': 0.32} + 32%|███▏ | 3807/11728 [2:33:09<14:51:48, 6.76s/it] 32%|███▏ | 3808/11728 [2:33:16<14:42:11, 6.68s/it] {'loss': 0.485, 'learning_rate': 1.5780920002248484e-05, 'epoch': 0.32} + 32%|███▏ | 3808/11728 [2:33:16<14:42:11, 6.68s/it] 32%|███▏ | 3809/11728 [2:33:22<14:11:44, 6.45s/it] {'loss': 0.4889, 'learning_rate': 1.5778666397204624e-05, 'epoch': 0.32} + 32%|███▏ | 3809/11728 [2:33:22<14:11:44, 6.45s/it] 32%|███▏ | 3810/11728 [2:33:28<13:49:17, 6.28s/it] {'loss': 0.5132, 'learning_rate': 1.5776412351455535e-05, 'epoch': 0.32} + 32%|███▏ | 3810/11728 [2:33:28<13:49:17, 6.28s/it] 32%|███▏ | 3811/11728 [2:33:34<13:33:18, 6.16s/it] {'loss': 0.4819, 'learning_rate': 1.5774157865173125e-05, 'epoch': 0.32} + 32%|███▏ | 3811/11728 [2:33:34<13:33:18, 6.16s/it] 33%|███▎ | 3812/11728 [2:33:39<13:23:42, 6.09s/it] {'loss': 0.4774, 'learning_rate': 1.577190293852933e-05, 'epoch': 0.33} + 33%|███▎ | 3812/11728 [2:33:39<13:23:42, 6.09s/it] 33%|███▎ | 3813/11728 [2:33:45<13:18:50, 6.06s/it] {'loss': 0.4941, 'learning_rate': 1.576964757169612e-05, 'epoch': 0.33} + 33%|███▎ | 3813/11728 [2:33:45<13:18:50, 6.06s/it] 33%|███▎ | 3814/11728 [2:33:51<13:05:53, 5.96s/it] {'loss': 0.4906, 'learning_rate': 1.5767391764845503e-05, 'epoch': 0.33} + 33%|███▎ | 3814/11728 [2:33:51<13:05:53, 5.96s/it] 33%|███▎ | 3815/11728 [2:33:57<12:59:42, 5.91s/it] {'loss': 0.4859, 'learning_rate': 1.5765135518149503e-05, 'epoch': 0.33} + 33%|███▎ | 3815/11728 [2:33:57<12:59:42, 5.91s/it] 33%|███▎ | 3816/11728 [2:34:03<13:05:46, 5.96s/it] {'loss': 0.4941, 'learning_rate': 1.5762878831780206e-05, 'epoch': 0.33} + 33%|███▎ | 3816/11728 [2:34:03<13:05:46, 5.96s/it] 33%|███▎ | 3817/11728 [2:34:09<12:51:31, 5.85s/it] {'loss': 0.4812, 'learning_rate': 1.5760621705909706e-05, 'epoch': 0.33} + 33%|███▎ | 3817/11728 [2:34:09<12:51:31, 5.85s/it] 33%|███▎ | 3818/11728 [2:34:14<12:49:15, 5.84s/it] {'loss': 0.4954, 'learning_rate': 1.575836414071015e-05, 'epoch': 0.33} + 33%|███▎ | 3818/11728 [2:34:14<12:49:15, 5.84s/it] 33%|███▎ | 3819/11728 [2:34:20<12:51:38, 5.85s/it] {'loss': 0.4723, 'learning_rate': 1.57561061363537e-05, 'epoch': 0.33} + 33%|███▎ | 3819/11728 [2:34:20<12:51:38, 5.85s/it] 33%|███▎ | 3820/11728 [2:34:26<12:55:07, 5.88s/it] {'loss': 0.4967, 'learning_rate': 1.5753847693012566e-05, 'epoch': 0.33} + 33%|███▎ | 3820/11728 [2:34:26<12:55:07, 5.88s/it] 33%|███▎ | 3821/11728 [2:34:32<13:01:25, 5.93s/it] {'loss': 0.4882, 'learning_rate': 1.5751588810858986e-05, 'epoch': 0.33} + 33%|███▎ | 3821/11728 [2:34:32<13:01:25, 5.93s/it] 33%|███▎ | 3822/11728 [2:34:38<12:54:56, 5.88s/it] {'loss': 0.491, 'learning_rate': 1.574932949006523e-05, 'epoch': 0.33} + 33%|███▎ | 3822/11728 [2:34:38<12:54:56, 5.88s/it] 33%|███▎ | 3823/11728 [2:34:44<12:43:25, 5.79s/it] {'loss': 0.4762, 'learning_rate': 1.5747069730803607e-05, 'epoch': 0.33} + 33%|███▎ | 3823/11728 [2:34:44<12:43:25, 5.79s/it] 33%|███▎ | 3824/11728 [2:34:50<12:58:11, 5.91s/it] {'loss': 0.4798, 'learning_rate': 1.574480953324645e-05, 'epoch': 0.33} + 33%|███▎ | 3824/11728 [2:34:50<12:58:11, 5.91s/it] 33%|███▎ | 3825/11728 [2:34:55<12:46:10, 5.82s/it] {'loss': 0.4884, 'learning_rate': 1.5742548897566135e-05, 'epoch': 0.33} + 33%|███▎ | 3825/11728 [2:34:55<12:46:10, 5.82s/it] 33%|███▎ | 3826/11728 [2:35:01<12:48:20, 5.83s/it] {'loss': 0.495, 'learning_rate': 1.5740287823935067e-05, 'epoch': 0.33} + 33%|███▎ | 3826/11728 [2:35:01<12:48:20, 5.83s/it] 33%|███▎ | 3827/11728 [2:35:07<12:37:10, 5.75s/it] {'loss': 0.4671, 'learning_rate': 1.5738026312525686e-05, 'epoch': 0.33} + 33%|███▎ | 3827/11728 [2:35:07<12:37:10, 5.75s/it] 33%|███▎ | 3828/11728 [2:35:13<12:47:31, 5.83s/it] {'loss': 0.4837, 'learning_rate': 1.573576436351046e-05, 'epoch': 0.33} + 33%|███▎ | 3828/11728 [2:35:13<12:47:31, 5.83s/it] 33%|███▎ | 3829/11728 [2:35:19<12:55:24, 5.89s/it] {'loss': 0.4931, 'learning_rate': 1.5733501977061904e-05, 'epoch': 0.33} + 33%|███▎ | 3829/11728 [2:35:19<12:55:24, 5.89s/it] 33%|███▎ | 3830/11728 [2:35:25<13:09:36, 6.00s/it] {'loss': 0.5012, 'learning_rate': 1.5731239153352543e-05, 'epoch': 0.33} + 33%|███▎ | 3830/11728 [2:35:25<13:09:36, 6.00s/it] 33%|███▎ | 3831/11728 [2:35:31<13:09:13, 6.00s/it] {'loss': 0.4917, 'learning_rate': 1.5728975892554957e-05, 'epoch': 0.33} + 33%|███▎ | 3831/11728 [2:35:31<13:09:13, 6.00s/it] 33%|███▎ | 3832/11728 [2:35:37<13:05:43, 5.97s/it] {'loss': 0.4935, 'learning_rate': 1.5726712194841758e-05, 'epoch': 0.33} + 33%|███▎ | 3832/11728 [2:35:37<13:05:43, 5.97s/it] 33%|███▎ | 3833/11728 [2:35:43<13:02:50, 5.95s/it] {'loss': 0.4869, 'learning_rate': 1.5724448060385574e-05, 'epoch': 0.33} + 33%|███▎ | 3833/11728 [2:35:43<13:02:50, 5.95s/it] 33%|███▎ | 3834/11728 [2:35:49<13:02:49, 5.95s/it] {'loss': 0.5089, 'learning_rate': 1.5722183489359082e-05, 'epoch': 0.33} + 33%|███▎ | 3834/11728 [2:35:49<13:02:49, 5.95s/it]Token indices sequence length is longer than the specified maximum sequence length for this model (5014 > 4096). Running this sequence through the model will result in indexing errors + 33%|███▎ | 3835/11728 [2:35:55<12:53:45, 5.88s/it] {'loss': 0.4933, 'learning_rate': 1.571991848193499e-05, 'epoch': 0.33} + 33%|███▎ | 3835/11728 [2:35:55<12:53:45, 5.88s/it] 33%|███▎ | 3836/11728 [2:36:01<12:51:48, 5.87s/it] {'loss': 0.4931, 'learning_rate': 1.5717653038286033e-05, 'epoch': 0.33} + 33%|███▎ | 3836/11728 [2:36:01<12:51:48, 5.87s/it] 33%|███▎ | 3837/11728 [2:36:07<13:08:10, 5.99s/it] {'loss': 0.4985, 'learning_rate': 1.5715387158584988e-05, 'epoch': 0.33} + 33%|███▎ | 3837/11728 [2:36:07<13:08:10, 5.99s/it] 33%|███▎ | 3838/11728 [2:36:13<13:03:42, 5.96s/it] {'loss': 0.4829, 'learning_rate': 1.5713120843004653e-05, 'epoch': 0.33} + 33%|███▎ | 3838/11728 [2:36:13<13:03:42, 5.96s/it] 33%|███▎ | 3839/11728 [2:36:19<12:57:51, 5.92s/it] {'loss': 0.4974, 'learning_rate': 1.5710854091717873e-05, 'epoch': 0.33} + 33%|███▎ | 3839/11728 [2:36:19<12:57:51, 5.92s/it] 33%|███▎ | 3840/11728 [2:36:24<12:59:20, 5.93s/it] {'loss': 0.4771, 'learning_rate': 1.5708586904897518e-05, 'epoch': 0.33} + 33%|███▎ | 3840/11728 [2:36:24<12:59:20, 5.93s/it] 33%|███▎ | 3841/11728 [2:36:31<13:03:29, 5.96s/it] {'loss': 0.4747, 'learning_rate': 1.5706319282716492e-05, 'epoch': 0.33} + 33%|███▎ | 3841/11728 [2:36:31<13:03:29, 5.96s/it] 33%|███▎ | 3842/11728 [2:36:36<13:02:19, 5.95s/it] {'loss': 0.5035, 'learning_rate': 1.5704051225347732e-05, 'epoch': 0.33} + 33%|███▎ | 3842/11728 [2:36:36<13:02:19, 5.95s/it] 33%|███▎ | 3843/11728 [2:36:42<12:51:19, 5.87s/it] {'loss': 0.4963, 'learning_rate': 1.5701782732964216e-05, 'epoch': 0.33} + 33%|███▎ | 3843/11728 [2:36:42<12:51:19, 5.87s/it] 33%|███▎ | 3844/11728 [2:36:48<12:48:26, 5.85s/it] {'loss': 0.4695, 'learning_rate': 1.5699513805738942e-05, 'epoch': 0.33} + 33%|███▎ | 3844/11728 [2:36:48<12:48:26, 5.85s/it] 33%|███▎ | 3845/11728 [2:36:54<12:45:35, 5.83s/it] {'loss': 0.4937, 'learning_rate': 1.5697244443844952e-05, 'epoch': 0.33} + 33%|███▎ | 3845/11728 [2:36:54<12:45:35, 5.83s/it] 33%|███▎ | 3846/11728 [2:36:59<12:41:43, 5.80s/it] {'loss': 0.4881, 'learning_rate': 1.5694974647455315e-05, 'epoch': 0.33} + 33%|███▎ | 3846/11728 [2:36:59<12:41:43, 5.80s/it] 33%|███▎ | 3847/11728 [2:37:05<12:46:32, 5.84s/it] {'loss': 0.4957, 'learning_rate': 1.5692704416743138e-05, 'epoch': 0.33} + 33%|███▎ | 3847/11728 [2:37:05<12:46:32, 5.84s/it] 33%|███▎ | 3848/11728 [2:37:11<12:35:32, 5.75s/it] {'loss': 0.4859, 'learning_rate': 1.569043375188155e-05, 'epoch': 0.33} + 33%|███▎ | 3848/11728 [2:37:11<12:35:32, 5.75s/it] 33%|███▎ | 3849/11728 [2:37:17<12:48:58, 5.86s/it] {'loss': 0.4806, 'learning_rate': 1.568816265304373e-05, 'epoch': 0.33} + 33%|███▎ | 3849/11728 [2:37:17<12:48:58, 5.86s/it]4 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... +05 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... + 33%|███▎ | 3850/11728 [2:37:23<12:46:36, 5.84s/it]6 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4801, 'learning_rate': 1.568589112040288e-05, 'epoch': 0.33} + 33%|███▎ | 3850/11728 [2:37:23<12:46:36, 5.84s/it]/lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/VILA/llava/model/llava_arch.py:397: UserWarning: Inputs truncated! + warnings.warn("Inputs truncated!") + 33%|███▎ | 3851/11728 [2:37:29<12:54:54, 5.90s/it] {'loss': 0.5217, 'learning_rate': 1.5683619154132236e-05, 'epoch': 0.33} + 33%|███▎ | 3851/11728 [2:37:29<12:54:54, 5.90s/it] 33%|███▎ | 3852/11728 [2:37:35<12:55:44, 5.91s/it] {'loss': 0.5026, 'learning_rate': 1.5681346754405064e-05, 'epoch': 0.33} + 33%|███▎ | 3852/11728 [2:37:35<12:55:44, 5.91s/it] 33%|███▎ | 3853/11728 [2:37:40<12:48:24, 5.85s/it] {'loss': 0.4715, 'learning_rate': 1.567907392139467e-05, 'epoch': 0.33} + 33%|███▎ | 3853/11728 [2:37:41<12:48:24, 5.85s/it] 33%|███▎ | 3854/11728 [2:37:47<12:55:35, 5.91s/it] {'loss': 0.48, 'learning_rate': 1.5676800655274394e-05, 'epoch': 0.33} + 33%|███▎ | 3854/11728 [2:37:47<12:55:35, 5.91s/it] 33%|███▎ | 3855/11728 [2:37:52<12:53:55, 5.90s/it] {'loss': 0.5089, 'learning_rate': 1.5674526956217596e-05, 'epoch': 0.33} + 33%|███▎ | 3855/11728 [2:37:52<12:53:55, 5.90s/it] 33%|███▎ | 3856/11728 [2:37:58<12:53:34, 5.90s/it] {'loss': 0.4783, 'learning_rate': 1.5672252824397683e-05, 'epoch': 0.33} + 33%|███▎ | 3856/11728 [2:37:58<12:53:34, 5.90s/it] 33%|███▎ | 3857/11728 [2:38:04<12:43:52, 5.82s/it] {'loss': 0.4678, 'learning_rate': 1.5669978259988087e-05, 'epoch': 0.33} + 33%|███▎ | 3857/11728 [2:38:04<12:43:52, 5.82s/it] 33%|███▎ | 3858/11728 [2:38:10<12:36:39, 5.77s/it] {'loss': 0.4978, 'learning_rate': 1.566770326316228e-05, 'epoch': 0.33} + 33%|███▎ | 3858/11728 [2:38:10<12:36:39, 5.77s/it] 33%|███▎ | 3859/11728 [2:38:15<12:37:52, 5.78s/it] {'loss': 0.4806, 'learning_rate': 1.5665427834093755e-05, 'epoch': 0.33} + 33%|███▎ | 3859/11728 [2:38:15<12:37:52, 5.78s/it] 33%|███▎ | 3860/11728 [2:38:21<12:41:34, 5.81s/it] {'loss': 0.4989, 'learning_rate': 1.5663151972956055e-05, 'epoch': 0.33} + 33%|███▎ | 3860/11728 [2:38:21<12:41:34, 5.81s/it] 33%|███▎ | 3861/11728 [2:38:27<12:34:22, 5.75s/it] {'loss': 0.4873, 'learning_rate': 1.566087567992274e-05, 'epoch': 0.33} + 33%|███▎ | 3861/11728 [2:38:27<12:34:22, 5.75s/it] 33%|███▎ | 3862/11728 [2:38:33<12:49:03, 5.87s/it] {'loss': 0.4932, 'learning_rate': 1.565859895516742e-05, 'epoch': 0.33} + 33%|███▎ | 3862/11728 [2:38:33<12:49:03, 5.87s/it] 33%|███▎ | 3863/11728 [2:38:39<12:57:19, 5.93s/it] {'loss': 0.4853, 'learning_rate': 1.565632179886371e-05, 'epoch': 0.33} + 33%|███▎ | 3863/11728 [2:38:39<12:57:19, 5.93s/it] 33%|███▎ | 3864/11728 [2:38:45<12:51:22, 5.89s/it] {'loss': 0.4998, 'learning_rate': 1.565404421118529e-05, 'epoch': 0.33} + 33%|███▎ | 3864/11728 [2:38:45<12:51:22, 5.89s/it] 33%|███▎ | 3865/11728 [2:38:51<12:46:49, 5.85s/it] {'loss': 0.4937, 'learning_rate': 1.5651766192305853e-05, 'epoch': 0.33} + 33%|███▎ | 3865/11728 [2:38:51<12:46:49, 5.85s/it] 33%|███▎ | 3866/11728 [2:38:56<12:32:36, 5.74s/it] {'loss': 0.4985, 'learning_rate': 1.564948774239913e-05, 'epoch': 0.33} + 33%|███▎ | 3866/11728 [2:38:56<12:32:36, 5.74s/it] 33%|███▎ | 3867/11728 [2:39:02<12:31:48, 5.74s/it] {'loss': 0.4887, 'learning_rate': 1.564720886163889e-05, 'epoch': 0.33} + 33%|███▎ | 3867/11728 [2:39:02<12:31:48, 5.74s/it] 33%|███▎ | 3868/11728 [2:39:08<12:44:37, 5.84s/it] {'loss': 0.4811, 'learning_rate': 1.564492955019892e-05, 'epoch': 0.33} + 33%|███▎ | 3868/11728 [2:39:08<12:44:37, 5.84s/it] 33%|███▎ | 3869/11728 [2:39:14<12:41:40, 5.82s/it] {'loss': 0.4725, 'learning_rate': 1.5642649808253057e-05, 'epoch': 0.33} + 33%|███▎ | 3869/11728 [2:39:14<12:41:40, 5.82s/it] 33%|███▎ | 3870/11728 [2:39:20<12:49:52, 5.88s/it] {'loss': 0.467, 'learning_rate': 1.5640369635975165e-05, 'epoch': 0.33} + 33%|███▎ | 3870/11728 [2:39:20<12:49:52, 5.88s/it] 33%|███▎ | 3871/11728 [2:39:26<12:51:49, 5.89s/it] {'loss': 0.4945, 'learning_rate': 1.5638089033539135e-05, 'epoch': 0.33} + 33%|███▎ | 3871/11728 [2:39:26<12:51:49, 5.89s/it] 33%|███▎ | 3872/11728 [2:39:31<12:40:06, 5.81s/it] {'loss': 0.4852, 'learning_rate': 1.56358080011189e-05, 'epoch': 0.33} + 33%|███▎ | 3872/11728 [2:39:31<12:40:06, 5.81s/it] 33%|███▎ | 3873/11728 [2:39:37<12:42:20, 5.82s/it] {'loss': 0.4932, 'learning_rate': 1.5633526538888412e-05, 'epoch': 0.33} + 33%|███▎ | 3873/11728 [2:39:37<12:42:20, 5.82s/it] 33%|███▎ | 3874/11728 [2:39:43<12:57:27, 5.94s/it] {'loss': 0.5103, 'learning_rate': 1.5631244647021672e-05, 'epoch': 0.33} + 33%|███▎ | 3874/11728 [2:39:43<12:57:27, 5.94s/it] 33%|███▎ | 3875/11728 [2:39:49<12:46:36, 5.86s/it] {'loss': 0.5069, 'learning_rate': 1.5628962325692708e-05, 'epoch': 0.33} + 33%|███▎ | 3875/11728 [2:39:49<12:46:36, 5.86s/it] 33%|███▎ | 3876/11728 [2:39:55<12:40:39, 5.81s/it] {'loss': 0.4724, 'learning_rate': 1.5626679575075577e-05, 'epoch': 0.33} + 33%|███▎ | 3876/11728 [2:39:55<12:40:39, 5.81s/it] 33%|███▎ | 3877/11728 [2:40:00<12:36:30, 5.78s/it] {'loss': 0.4954, 'learning_rate': 1.562439639534437e-05, 'epoch': 0.33} + 33%|███▎ | 3877/11728 [2:40:00<12:36:30, 5.78s/it] 33%|███▎ | 3878/11728 [2:40:06<12:35:37, 5.78s/it] {'loss': 0.5119, 'learning_rate': 1.5622112786673214e-05, 'epoch': 0.33} + 33%|███▎ | 3878/11728 [2:40:06<12:35:37, 5.78s/it] 33%|███▎ | 3879/11728 [2:40:12<12:34:47, 5.77s/it] {'loss': 0.5031, 'learning_rate': 1.561982874923626e-05, 'epoch': 0.33} + 33%|███▎ | 3879/11728 [2:40:12<12:34:47, 5.77s/it] 33%|███▎ | 3880/11728 [2:40:18<12:33:32, 5.76s/it] {'loss': 0.4851, 'learning_rate': 1.561754428320771e-05, 'epoch': 0.33} + 33%|███▎ | 3880/11728 [2:40:18<12:33:32, 5.76s/it] 33%|███▎ | 3881/11728 [2:40:23<12:27:38, 5.72s/it] {'loss': 0.4732, 'learning_rate': 1.5615259388761777e-05, 'epoch': 0.33} + 33%|███▎ | 3881/11728 [2:40:23<12:27:38, 5.72s/it] 33%|███▎ | 3882/11728 [2:40:29<12:27:08, 5.71s/it] {'loss': 0.4796, 'learning_rate': 1.561297406607272e-05, 'epoch': 0.33} + 33%|███▎ | 3882/11728 [2:40:29<12:27:08, 5.71s/it] 33%|███▎ | 3883/11728 [2:40:35<12:22:04, 5.68s/it] {'loss': 0.471, 'learning_rate': 1.561068831531483e-05, 'epoch': 0.33} + 33%|███▎ | 3883/11728 [2:40:35<12:22:04, 5.68s/it] 33%|███▎ | 3884/11728 [2:40:41<12:34:23, 5.77s/it] {'loss': 0.4978, 'learning_rate': 1.5608402136662423e-05, 'epoch': 0.33} + 33%|███▎ | 3884/11728 [2:40:41<12:34:23, 5.77s/it] 33%|███▎ | 3885/11728 [2:40:46<12:38:18, 5.80s/it] {'loss': 0.4962, 'learning_rate': 1.5606115530289856e-05, 'epoch': 0.33} + 33%|███▎ | 3885/11728 [2:40:46<12:38:18, 5.80s/it] 33%|███▎ | 3886/11728 [2:40:52<12:36:50, 5.79s/it] {'loss': 0.4664, 'learning_rate': 1.560382849637151e-05, 'epoch': 0.33} + 33%|███▎ | 3886/11728 [2:40:52<12:36:50, 5.79s/it] 33%|███▎ | 3887/11728 [2:40:58<12:36:21, 5.79s/it] {'loss': 0.4904, 'learning_rate': 1.5601541035081813e-05, 'epoch': 0.33} + 33%|███▎ | 3887/11728 [2:40:58<12:36:21, 5.79s/it] 33%|███▎ | 3888/11728 [2:41:04<12:48:41, 5.88s/it] {'loss': 0.4981, 'learning_rate': 1.559925314659521e-05, 'epoch': 0.33} + 33%|███▎ | 3888/11728 [2:41:04<12:48:41, 5.88s/it] 33%|███▎ | 3889/11728 [2:41:10<12:51:56, 5.91s/it] {'loss': 0.4821, 'learning_rate': 1.5596964831086185e-05, 'epoch': 0.33} + 33%|███▎ | 3889/11728 [2:41:10<12:51:56, 5.91s/it] 33%|███▎ | 3890/11728 [2:41:16<12:49:36, 5.89s/it] {'loss': 0.4915, 'learning_rate': 1.5594676088729252e-05, 'epoch': 0.33} + 33%|███▎ | 3890/11728 [2:41:16<12:49:36, 5.89s/it] 33%|███▎ | 3891/11728 [2:41:22<12:50:51, 5.90s/it] {'loss': 0.4787, 'learning_rate': 1.5592386919698967e-05, 'epoch': 0.33} + 33%|███▎ | 3891/11728 [2:41:22<12:50:51, 5.90s/it] 33%|███▎ | 3892/11728 [2:41:28<12:48:07, 5.88s/it] {'loss': 0.5092, 'learning_rate': 1.5590097324169907e-05, 'epoch': 0.33} + 33%|███▎ | 3892/11728 [2:41:28<12:48:07, 5.88s/it] 33%|███▎ | 3893/11728 [2:41:33<12:37:37, 5.80s/it] {'loss': 0.5037, 'learning_rate': 1.5587807302316687e-05, 'epoch': 0.33} + 33%|███▎ | 3893/11728 [2:41:33<12:37:37, 5.80s/it] 33%|███▎ | 3894/11728 [2:41:39<12:30:48, 5.75s/it] {'loss': 0.4937, 'learning_rate': 1.5585516854313957e-05, 'epoch': 0.33} + 33%|███▎ | 3894/11728 [2:41:39<12:30:48, 5.75s/it] 33%|███▎ | 3895/11728 [2:41:45<12:27:08, 5.72s/it] {'loss': 0.4824, 'learning_rate': 1.558322598033639e-05, 'epoch': 0.33} + 33%|███▎ | 3895/11728 [2:41:45<12:27:08, 5.72s/it] 33%|███▎ | 3896/11728 [2:41:50<12:34:02, 5.78s/it] {'loss': 0.4927, 'learning_rate': 1.5580934680558696e-05, 'epoch': 0.33} + 33%|███▎ | 3896/11728 [2:41:50<12:34:02, 5.78s/it] 33%|███▎ | 3897/11728 [2:41:56<12:31:51, 5.76s/it] {'loss': 0.4924, 'learning_rate': 1.5578642955155627e-05, 'epoch': 0.33} + 33%|███▎ | 3897/11728 [2:41:56<12:31:51, 5.76s/it] 33%|███▎ | 3898/11728 [2:42:02<12:41:43, 5.84s/it] {'loss': 0.4804, 'learning_rate': 1.557635080430196e-05, 'epoch': 0.33} + 33%|███▎ | 3898/11728 [2:42:02<12:41:43, 5.84s/it] 33%|███▎ | 3899/11728 [2:42:08<12:37:30, 5.81s/it] {'loss': 0.4863, 'learning_rate': 1.5574058228172498e-05, 'epoch': 0.33} + 33%|███▎ | 3899/11728 [2:42:08<12:37:30, 5.81s/it]4 AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +50 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... + 3 AutoResumeHook: Checking whether to suspend... +AutoResumeHook: Checking whether to suspend... + 33%|███▎ | 3900/11728 [2:42:14<12:38:38, 5.81s/it]6 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4725, 'learning_rate': 1.557176522694208e-05, 'epoch': 0.33} + 33%|███▎ | 3900/11728 [2:42:14<12:38:38, 5.81s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-3900/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-3900/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-3900/mm_projector +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/torch/nn/modules/module.py:1802: UserWarning: Positional args are being deprecated, use kwargs instead. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details. + warnings.warn( + 33%|███▎ | 3901/11728 [2:42:45<29:14:42, 13.45s/it] {'loss': 0.4919, 'learning_rate': 1.556947180078559e-05, 'epoch': 0.33} + 33%|███▎ | 3901/11728 [2:42:45<29:14:42, 13.45s/it] 33%|███▎ | 3902/11728 [2:42:51<24:23:21, 11.22s/it] {'loss': 0.467, 'learning_rate': 1.5567177949877925e-05, 'epoch': 0.33} + 33%|███▎ | 3902/11728 [2:42:51<24:23:21, 11.22s/it] 33%|███▎ | 3903/11728 [2:42:57<20:50:46, 9.59s/it] {'loss': 0.4995, 'learning_rate': 1.556488367439403e-05, 'epoch': 0.33} + 33%|███▎ | 3903/11728 [2:42:57<20:50:46, 9.59s/it] 33%|███▎ | 3904/11728 [2:43:02<18:10:48, 8.37s/it] {'loss': 0.4914, 'learning_rate': 1.556258897450887e-05, 'epoch': 0.33} + 33%|███▎ | 3904/11728 [2:43:02<18:10:48, 8.37s/it] 33%|███▎ | 3905/11728 [2:43:08<16:36:37, 7.64s/it] {'loss': 0.4997, 'learning_rate': 1.5560293850397455e-05, 'epoch': 0.33} + 33%|███▎ | 3905/11728 [2:43:08<16:36:37, 7.64s/it] 33%|███▎ | 3906/11728 [2:43:14<15:23:21, 7.08s/it] {'loss': 0.4842, 'learning_rate': 1.5557998302234817e-05, 'epoch': 0.33} + 33%|███▎ | 3906/11728 [2:43:14<15:23:21, 7.08s/it] 33%|███▎ | 3907/11728 [2:43:20<14:37:19, 6.73s/it] {'loss': 0.4847, 'learning_rate': 1.5555702330196024e-05, 'epoch': 0.33} + 33%|███▎ | 3907/11728 [2:43:20<14:37:19, 6.73s/it] 33%|███▎ | 3908/11728 [2:43:26<14:10:11, 6.52s/it] {'loss': 0.4927, 'learning_rate': 1.555340593445618e-05, 'epoch': 0.33} + 33%|███▎ | 3908/11728 [2:43:26<14:10:11, 6.52s/it] 33%|███▎ | 3909/11728 [2:43:32<13:56:44, 6.42s/it] {'loss': 0.4821, 'learning_rate': 1.5551109115190408e-05, 'epoch': 0.33} + 33%|███▎ | 3909/11728 [2:43:32<13:56:44, 6.42s/it] 33%|███▎ | 3910/11728 [2:43:38<13:34:31, 6.25s/it] {'loss': 0.5074, 'learning_rate': 1.5548811872573883e-05, 'epoch': 0.33} + 33%|███▎ | 3910/11728 [2:43:38<13:34:31, 6.25s/it] 33%|███▎ | 3911/11728 [2:43:44<13:22:56, 6.16s/it] {'loss': 0.4852, 'learning_rate': 1.55465142067818e-05, 'epoch': 0.33} + 33%|███▎ | 3911/11728 [2:43:44<13:22:56, 6.16s/it] 33%|███▎ | 3912/11728 [2:43:50<13:22:50, 6.16s/it] {'loss': 0.5034, 'learning_rate': 1.554421611798939e-05, 'epoch': 0.33} + 33%|███▎ | 3912/11728 [2:43:50<13:22:50, 6.16s/it] 33%|███▎ | 3913/11728 [2:43:56<13:05:00, 6.03s/it] {'loss': 0.4716, 'learning_rate': 1.5541917606371904e-05, 'epoch': 0.33} + 33%|███▎ | 3913/11728 [2:43:56<13:05:00, 6.03s/it] 33%|███▎ | 3914/11728 [2:44:02<13:00:03, 5.99s/it] {'loss': 0.4802, 'learning_rate': 1.553961867210465e-05, 'epoch': 0.33} + 33%|███▎ | 3914/11728 [2:44:02<13:00:03, 5.99s/it] 33%|███▎ | 3915/11728 [2:44:08<12:49:20, 5.91s/it] {'loss': 0.4795, 'learning_rate': 1.553731931536295e-05, 'epoch': 0.33} + 33%|███▎ | 3915/11728 [2:44:08<12:49:20, 5.91s/it] 33%|███▎ | 3916/11728 [2:44:13<12:36:20, 5.81s/it] {'loss': 0.4816, 'learning_rate': 1.5535019536322158e-05, 'epoch': 0.33} + 33%|███▎ | 3916/11728 [2:44:13<12:36:20, 5.81s/it] 33%|███▎ | 3917/11728 [2:44:19<12:36:33, 5.81s/it] {'loss': 0.48, 'learning_rate': 1.5532719335157673e-05, 'epoch': 0.33} + 33%|███▎ | 3917/11728 [2:44:19<12:36:33, 5.81s/it] 33%|███▎ | 3918/11728 [2:44:25<12:33:53, 5.79s/it] {'loss': 0.488, 'learning_rate': 1.5530418712044907e-05, 'epoch': 0.33} + 33%|███▎ | 3918/11728 [2:44:25<12:33:53, 5.79s/it] 33%|███▎ | 3919/11728 [2:44:30<12:30:07, 5.76s/it] {'loss': 0.5021, 'learning_rate': 1.5528117667159325e-05, 'epoch': 0.33} + 33%|███▎ | 3919/11728 [2:44:30<12:30:07, 5.76s/it] 33%|███▎ | 3920/11728 [2:44:36<12:19:54, 5.69s/it] {'loss': 0.4874, 'learning_rate': 1.552581620067641e-05, 'epoch': 0.33} + 33%|███▎ | 3920/11728 [2:44:36<12:19:54, 5.69s/it] 33%|███▎ | 3921/11728 [2:44:42<12:30:03, 5.76s/it] {'loss': 0.4934, 'learning_rate': 1.5523514312771683e-05, 'epoch': 0.33} + 33%|███▎ | 3921/11728 [2:44:42<12:30:03, 5.76s/it] 33%|███▎ | 3922/11728 [2:44:47<12:24:22, 5.72s/it] {'loss': 0.4656, 'learning_rate': 1.5521212003620692e-05, 'epoch': 0.33} + 33%|███▎ | 3922/11728 [2:44:47<12:24:22, 5.72s/it] 33%|███▎ | 3923/11728 [2:44:53<12:19:51, 5.69s/it] {'loss': 0.4723, 'learning_rate': 1.5518909273399026e-05, 'epoch': 0.33} + 33%|███▎ | 3923/11728 [2:44:53<12:19:51, 5.69s/it] 33%|███▎ | 3924/11728 [2:44:59<12:31:24, 5.78s/it] {'loss': 0.5162, 'learning_rate': 1.5516606122282297e-05, 'epoch': 0.33} + 33%|███▎ | 3924/11728 [2:44:59<12:31:24, 5.78s/it] 33%|███▎ | 3925/11728 [2:45:05<12:28:07, 5.75s/it] {'loss': 0.4873, 'learning_rate': 1.5514302550446153e-05, 'epoch': 0.33} + 33%|███▎ | 3925/11728 [2:45:05<12:28:07, 5.75s/it] 33%|███▎ | 3926/11728 [2:45:10<12:20:02, 5.69s/it] {'loss': 0.4723, 'learning_rate': 1.5511998558066276e-05, 'epoch': 0.33} + 33%|███▎ | 3926/11728 [2:45:10<12:20:02, 5.69s/it] 33%|███▎ | 3927/11728 [2:45:16<12:14:59, 5.65s/it] {'loss': 0.4825, 'learning_rate': 1.5509694145318374e-05, 'epoch': 0.33} + 33%|███▎ | 3927/11728 [2:45:16<12:14:59, 5.65s/it] 33%|███▎ | 3928/11728 [2:45:21<12:14:02, 5.65s/it] {'loss': 0.4861, 'learning_rate': 1.55073893123782e-05, 'epoch': 0.33} + 33%|███▎ | 3928/11728 [2:45:21<12:14:02, 5.65s/it] 34%|███▎ | 3929/11728 [2:45:27<12:22:11, 5.71s/it] {'loss': 0.5117, 'learning_rate': 1.5505084059421517e-05, 'epoch': 0.34} + 34%|███▎ | 3929/11728 [2:45:27<12:22:11, 5.71s/it] 34%|███▎ | 3930/11728 [2:45:33<12:26:59, 5.75s/it] {'loss': 0.4805, 'learning_rate': 1.5502778386624147e-05, 'epoch': 0.34} + 34%|███▎ | 3930/11728 [2:45:33<12:26:59, 5.75s/it] 34%|███▎ | 3931/11728 [2:45:39<12:32:27, 5.79s/it] {'loss': 0.5117, 'learning_rate': 1.550047229416192e-05, 'epoch': 0.34} + 34%|███▎ | 3931/11728 [2:45:39<12:32:27, 5.79s/it] 34%|███▎ | 3932/11728 [2:45:45<12:41:18, 5.86s/it] {'loss': 0.4862, 'learning_rate': 1.5498165782210713e-05, 'epoch': 0.34} + 34%|███▎ | 3932/11728 [2:45:45<12:41:18, 5.86s/it] 34%|███▎ | 3933/11728 [2:45:51<12:43:14, 5.87s/it] {'loss': 0.5021, 'learning_rate': 1.5495858850946433e-05, 'epoch': 0.34} + 34%|███▎ | 3933/11728 [2:45:51<12:43:14, 5.87s/it] 34%|███▎ | 3934/11728 [2:45:57<12:42:29, 5.87s/it] {'loss': 0.4936, 'learning_rate': 1.549355150054501e-05, 'epoch': 0.34} + 34%|███▎ | 3934/11728 [2:45:57<12:42:29, 5.87s/it] 34%|███▎ | 3935/11728 [2:46:03<12:40:12, 5.85s/it] {'loss': 0.4881, 'learning_rate': 1.5491243731182414e-05, 'epoch': 0.34} + 34%|███▎ | 3935/11728 [2:46:03<12:40:12, 5.85s/it] 34%|███▎ | 3936/11728 [2:46:08<12:36:12, 5.82s/it] {'loss': 0.4771, 'learning_rate': 1.5488935543034644e-05, 'epoch': 0.34} + 34%|███▎ | 3936/11728 [2:46:08<12:36:12, 5.82s/it] 34%|███▎ | 3937/11728 [2:46:14<12:24:47, 5.74s/it] {'loss': 0.4806, 'learning_rate': 1.5486626936277737e-05, 'epoch': 0.34} + 34%|███▎ | 3937/11728 [2:46:14<12:24:47, 5.74s/it] 34%|███▎ | 3938/11728 [2:46:20<12:40:46, 5.86s/it] {'loss': 0.4821, 'learning_rate': 1.548431791108775e-05, 'epoch': 0.34} + 34%|███▎ | 3938/11728 [2:46:20<12:40:46, 5.86s/it] 34%|███▎ | 3939/11728 [2:46:26<12:35:56, 5.82s/it] {'loss': 0.4909, 'learning_rate': 1.548200846764079e-05, 'epoch': 0.34} + 34%|███▎ | 3939/11728 [2:46:26<12:35:56, 5.82s/it] 34%|███▎ | 3940/11728 [2:46:32<12:45:51, 5.90s/it] {'loss': 0.5036, 'learning_rate': 1.547969860611297e-05, 'epoch': 0.34} + 34%|███▎ | 3940/11728 [2:46:32<12:45:51, 5.90s/it] 34%|███▎ | 3941/11728 [2:46:38<12:48:00, 5.92s/it] {'loss': 0.4715, 'learning_rate': 1.547738832668046e-05, 'epoch': 0.34} + 34%|███▎ | 3941/11728 [2:46:38<12:48:00, 5.92s/it] 34%|███▎ | 3942/11728 [2:46:44<12:50:14, 5.94s/it] {'loss': 0.492, 'learning_rate': 1.547507762951945e-05, 'epoch': 0.34} + 34%|███▎ | 3942/11728 [2:46:44<12:50:14, 5.94s/it] 34%|███▎ | 3943/11728 [2:46:50<12:44:41, 5.89s/it] {'loss': 0.4916, 'learning_rate': 1.547276651480616e-05, 'epoch': 0.34} + 34%|███▎ | 3943/11728 [2:46:50<12:44:41, 5.89s/it] 34%|███▎ | 3944/11728 [2:46:55<12:38:42, 5.85s/it] {'loss': 0.4736, 'learning_rate': 1.5470454982716852e-05, 'epoch': 0.34} + 34%|███▎ | 3944/11728 [2:46:55<12:38:42, 5.85s/it] 34%|███▎ | 3945/11728 [2:47:01<12:46:09, 5.91s/it] {'loss': 0.5132, 'learning_rate': 1.5468143033427802e-05, 'epoch': 0.34} + 34%|███▎ | 3945/11728 [2:47:01<12:46:09, 5.91s/it] 34%|███▎ | 3946/11728 [2:47:07<12:45:50, 5.90s/it] {'loss': 0.4813, 'learning_rate': 1.546583066711534e-05, 'epoch': 0.34} + 34%|███▎ | 3946/11728 [2:47:07<12:45:50, 5.90s/it] 34%|███▎ | 3947/11728 [2:47:13<12:44:26, 5.89s/it] {'loss': 0.5018, 'learning_rate': 1.5463517883955813e-05, 'epoch': 0.34} + 34%|███▎ | 3947/11728 [2:47:13<12:44:26, 5.89s/it] 34%|███▎ | 3948/11728 [2:47:19<12:39:20, 5.86s/it] {'loss': 0.5026, 'learning_rate': 1.5461204684125595e-05, 'epoch': 0.34} + 34%|███▎ | 3948/11728 [2:47:19<12:39:20, 5.86s/it] 34%|███▎ | 3949/11728 [2:47:25<12:33:02, 5.81s/it] {'loss': 0.5087, 'learning_rate': 1.545889106780112e-05, 'epoch': 0.34} + 34%|███▎ | 3949/11728 [2:47:25<12:33:02, 5.81s/it]4 AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +0 AutoResumeHook: Checking whether to suspend... + 34%|███▎ | 3950/11728 [2:47:30<12:31:46, 5.80s/it]3 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4782, 'learning_rate': 1.5456577035158814e-05, 'epoch': 0.34} + 34%|███▎ | 3950/11728 [2:47:30<12:31:46, 5.80s/it] 34%|███▎ | 3951/11728 [2:47:37<12:48:27, 5.93s/it] {'loss': 0.4932, 'learning_rate': 1.5454262586375164e-05, 'epoch': 0.34} + 34%|███▎ | 3951/11728 [2:47:37<12:48:27, 5.93s/it] 34%|███▎ | 3952/11728 [2:47:42<12:43:12, 5.89s/it] {'loss': 0.4987, 'learning_rate': 1.5451947721626676e-05, 'epoch': 0.34} + 34%|███▎ | 3952/11728 [2:47:42<12:43:12, 5.89s/it] 34%|███▎ | 3953/11728 [2:47:48<12:30:54, 5.79s/it] {'loss': 0.4609, 'learning_rate': 1.5449632441089896e-05, 'epoch': 0.34} + 34%|███▎ | 3953/11728 [2:47:48<12:30:54, 5.79s/it] 34%|███▎ | 3954/11728 [2:47:54<12:42:05, 5.88s/it] {'loss': 0.4951, 'learning_rate': 1.54473167449414e-05, 'epoch': 0.34} + 34%|███▎ | 3954/11728 [2:47:54<12:42:05, 5.88s/it] 34%|███▎ | 3955/11728 [2:48:00<12:34:47, 5.83s/it] {'loss': 0.4669, 'learning_rate': 1.544500063335778e-05, 'epoch': 0.34} + 34%|███▎ | 3955/11728 [2:48:00<12:34:47, 5.83s/it] 34%|███▎ | 3956/11728 [2:48:05<12:27:55, 5.77s/it] {'loss': 0.4875, 'learning_rate': 1.544268410651568e-05, 'epoch': 0.34} + 34%|███▎ | 3956/11728 [2:48:05<12:27:55, 5.77s/it] 34%|███▎ | 3957/11728 [2:48:11<12:24:12, 5.75s/it] {'loss': 0.4614, 'learning_rate': 1.5440367164591768e-05, 'epoch': 0.34} + 34%|███▎ | 3957/11728 [2:48:11<12:24:12, 5.75s/it] 34%|███▎ | 3958/11728 [2:48:17<12:23:52, 5.74s/it] {'loss': 0.5078, 'learning_rate': 1.5438049807762746e-05, 'epoch': 0.34} + 34%|███▎ | 3958/11728 [2:48:17<12:23:52, 5.74s/it] 34%|███▍ | 3959/11728 [2:48:22<12:16:13, 5.69s/it] {'loss': 0.4848, 'learning_rate': 1.543573203620534e-05, 'epoch': 0.34} + 34%|███▍ | 3959/11728 [2:48:22<12:16:13, 5.69s/it] 34%|███▍ | 3960/11728 [2:48:29<12:34:20, 5.83s/it] {'loss': 0.5104, 'learning_rate': 1.5433413850096316e-05, 'epoch': 0.34} + 34%|███▍ | 3960/11728 [2:48:29<12:34:20, 5.83s/it] 34%|███▍ | 3961/11728 [2:48:34<12:23:25, 5.74s/it] {'loss': 0.4905, 'learning_rate': 1.5431095249612466e-05, 'epoch': 0.34} + 34%|███▍ | 3961/11728 [2:48:34<12:23:25, 5.74s/it] 34%|███▍ | 3962/11728 [2:48:40<12:25:19, 5.76s/it] {'loss': 0.4738, 'learning_rate': 1.542877623493062e-05, 'epoch': 0.34} + 34%|███▍ | 3962/11728 [2:48:40<12:25:19, 5.76s/it] 34%|███▍ | 3963/11728 [2:48:46<12:31:56, 5.81s/it] {'loss': 0.5096, 'learning_rate': 1.5426456806227635e-05, 'epoch': 0.34} + 34%|███▍ | 3963/11728 [2:48:46<12:31:56, 5.81s/it] 34%|███▍ | 3964/11728 [2:48:51<12:23:15, 5.74s/it] {'loss': 0.4681, 'learning_rate': 1.5424136963680398e-05, 'epoch': 0.34} + 34%|███▍ | 3964/11728 [2:48:51<12:23:15, 5.74s/it] 34%|███▍ | 3965/11728 [2:48:58<12:36:46, 5.85s/it] {'loss': 0.5045, 'learning_rate': 1.542181670746583e-05, 'epoch': 0.34} + 34%|███▍ | 3965/11728 [2:48:58<12:36:46, 5.85s/it] 34%|███▍ | 3966/11728 [2:49:03<12:34:02, 5.83s/it] {'loss': 0.4785, 'learning_rate': 1.5419496037760887e-05, 'epoch': 0.34} + 34%|███▍ | 3966/11728 [2:49:03<12:34:02, 5.83s/it] 34%|███▍ | 3967/11728 [2:49:09<12:31:27, 5.81s/it] {'loss': 0.4973, 'learning_rate': 1.541717495474255e-05, 'epoch': 0.34} + 34%|███▍ | 3967/11728 [2:49:09<12:31:27, 5.81s/it] 34%|███▍ | 3968/11728 [2:49:15<12:39:02, 5.87s/it] {'loss': 0.5206, 'learning_rate': 1.5414853458587834e-05, 'epoch': 0.34} + 34%|███▍ | 3968/11728 [2:49:15<12:39:02, 5.87s/it] 34%|███▍ | 3969/11728 [2:49:21<12:37:50, 5.86s/it] {'loss': 0.4829, 'learning_rate': 1.5412531549473786e-05, 'epoch': 0.34} + 34%|███▍ | 3969/11728 [2:49:21<12:37:50, 5.86s/it] 34%|███▍ | 3970/11728 [2:49:27<12:34:26, 5.83s/it] {'loss': 0.482, 'learning_rate': 1.5410209227577487e-05, 'epoch': 0.34} + 34%|███▍ | 3970/11728 [2:49:27<12:34:26, 5.83s/it] 34%|███▍ | 3971/11728 [2:49:32<12:24:20, 5.76s/it] {'loss': 0.4707, 'learning_rate': 1.5407886493076043e-05, 'epoch': 0.34} + 34%|███▍ | 3971/11728 [2:49:32<12:24:20, 5.76s/it] 34%|███▍ | 3972/11728 [2:49:38<12:17:29, 5.71s/it] {'loss': 0.4983, 'learning_rate': 1.5405563346146603e-05, 'epoch': 0.34} + 34%|███▍ | 3972/11728 [2:49:38<12:17:29, 5.71s/it] 34%|███▍ | 3973/11728 [2:49:44<12:29:22, 5.80s/it] {'loss': 0.4918, 'learning_rate': 1.540323978696633e-05, 'epoch': 0.34} + 34%|███▍ | 3973/11728 [2:49:44<12:29:22, 5.80s/it] 34%|███▍ | 3974/11728 [2:49:50<12:48:58, 5.95s/it] {'loss': 0.4851, 'learning_rate': 1.540091581571243e-05, 'epoch': 0.34} + 34%|███▍ | 3974/11728 [2:49:50<12:48:58, 5.95s/it] 34%|███▍ | 3975/11728 [2:49:56<12:34:07, 5.84s/it] {'loss': 0.4815, 'learning_rate': 1.539859143256215e-05, 'epoch': 0.34} + 34%|███▍ | 3975/11728 [2:49:56<12:34:07, 5.84s/it] 34%|███▍ | 3976/11728 [2:50:02<12:29:00, 5.80s/it] {'loss': 0.4675, 'learning_rate': 1.5396266637692746e-05, 'epoch': 0.34} + 34%|███▍ | 3976/11728 [2:50:02<12:29:00, 5.80s/it] 34%|███▍ | 3977/11728 [2:50:07<12:28:02, 5.79s/it] {'loss': 0.4791, 'learning_rate': 1.5393941431281513e-05, 'epoch': 0.34} + 34%|███▍ | 3977/11728 [2:50:07<12:28:02, 5.79s/it] 34%|███▍ | 3978/11728 [2:50:13<12:35:38, 5.85s/it] {'loss': 0.4986, 'learning_rate': 1.5391615813505792e-05, 'epoch': 0.34} + 34%|███▍ | 3978/11728 [2:50:13<12:35:38, 5.85s/it] 34%|███▍ | 3979/11728 [2:50:19<12:26:43, 5.78s/it] {'loss': 0.5028, 'learning_rate': 1.5389289784542944e-05, 'epoch': 0.34} + 34%|███▍ | 3979/11728 [2:50:19<12:26:43, 5.78s/it] 34%|███▍ | 3980/11728 [2:50:25<12:43:14, 5.91s/it] {'loss': 0.4713, 'learning_rate': 1.5386963344570352e-05, 'epoch': 0.34} + 34%|███▍ | 3980/11728 [2:50:25<12:43:14, 5.91s/it] 34%|███▍ | 3981/11728 [2:50:31<12:35:45, 5.85s/it] {'loss': 0.4817, 'learning_rate': 1.538463649376545e-05, 'epoch': 0.34} + 34%|███▍ | 3981/11728 [2:50:31<12:35:45, 5.85s/it] 34%|███▍ | 3982/11728 [2:50:37<12:33:17, 5.83s/it] {'loss': 0.531, 'learning_rate': 1.5382309232305685e-05, 'epoch': 0.34} + 34%|███▍ | 3982/11728 [2:50:37<12:33:17, 5.83s/it] 34%|███▍ | 3983/11728 [2:50:43<12:36:32, 5.86s/it] {'loss': 0.4811, 'learning_rate': 1.5379981560368548e-05, 'epoch': 0.34} + 34%|███▍ | 3983/11728 [2:50:43<12:36:32, 5.86s/it] 34%|███▍ | 3984/11728 [2:50:48<12:32:05, 5.83s/it] {'loss': 0.5003, 'learning_rate': 1.5377653478131557e-05, 'epoch': 0.34} + 34%|███▍ | 3984/11728 [2:50:48<12:32:05, 5.83s/it] 34%|███▍ | 3985/11728 [2:50:54<12:23:32, 5.76s/it] {'loss': 0.5037, 'learning_rate': 1.5375324985772262e-05, 'epoch': 0.34} + 34%|███▍ | 3985/11728 [2:50:54<12:23:32, 5.76s/it] 34%|███▍ | 3986/11728 [2:50:59<12:14:46, 5.69s/it] {'loss': 0.4701, 'learning_rate': 1.5372996083468242e-05, 'epoch': 0.34} + 34%|███▍ | 3986/11728 [2:50:59<12:14:46, 5.69s/it] 34%|███▍ | 3987/11728 [2:51:05<12:21:34, 5.75s/it] {'loss': 0.4726, 'learning_rate': 1.5370666771397105e-05, 'epoch': 0.34} + 34%|███▍ | 3987/11728 [2:51:05<12:21:34, 5.75s/it] 34%|███▍ | 3988/11728 [2:51:11<12:15:17, 5.70s/it] {'loss': 0.4815, 'learning_rate': 1.5368337049736505e-05, 'epoch': 0.34} + 34%|███▍ | 3988/11728 [2:51:11<12:15:17, 5.70s/it] 34%|███▍ | 3989/11728 [2:51:17<12:29:53, 5.81s/it] {'loss': 0.4823, 'learning_rate': 1.53660069186641e-05, 'epoch': 0.34} + 34%|███▍ | 3989/11728 [2:51:17<12:29:53, 5.81s/it] 34%|███▍ | 3990/11728 [2:51:23<12:36:52, 5.87s/it] {'loss': 0.4717, 'learning_rate': 1.5363676378357614e-05, 'epoch': 0.34} + 34%|███▍ | 3990/11728 [2:51:23<12:36:52, 5.87s/it] 34%|███▍ | 3991/11728 [2:51:29<12:32:05, 5.83s/it] {'loss': 0.4821, 'learning_rate': 1.5361345428994772e-05, 'epoch': 0.34} + 34%|███▍ | 3991/11728 [2:51:29<12:32:05, 5.83s/it] 34%|███▍ | 3992/11728 [2:51:34<12:22:55, 5.76s/it] {'loss': 0.4893, 'learning_rate': 1.5359014070753345e-05, 'epoch': 0.34} + 34%|███▍ | 3992/11728 [2:51:34<12:22:55, 5.76s/it] 34%|███▍ | 3993/11728 [2:51:40<12:25:44, 5.78s/it] {'loss': 0.4779, 'learning_rate': 1.535668230381113e-05, 'epoch': 0.34} + 34%|███▍ | 3993/11728 [2:51:40<12:25:44, 5.78s/it] 34%|███▍ | 3994/11728 [2:51:46<12:28:25, 5.81s/it] {'loss': 0.4829, 'learning_rate': 1.535435012834596e-05, 'epoch': 0.34} + 34%|███▍ | 3994/11728 [2:51:46<12:28:25, 5.81s/it] 34%|███▍ | 3995/11728 [2:51:52<12:17:14, 5.72s/it] {'loss': 0.4882, 'learning_rate': 1.5352017544535694e-05, 'epoch': 0.34} + 34%|███▍ | 3995/11728 [2:51:52<12:17:14, 5.72s/it] 34%|███▍ | 3996/11728 [2:51:58<12:29:13, 5.81s/it] {'loss': 0.4848, 'learning_rate': 1.5349684552558226e-05, 'epoch': 0.34} + 34%|███▍ | 3996/11728 [2:51:58<12:29:13, 5.81s/it] 34%|███▍ | 3997/11728 [2:52:03<12:19:15, 5.74s/it] {'loss': 0.5034, 'learning_rate': 1.5347351152591485e-05, 'epoch': 0.34} + 34%|███▍ | 3997/11728 [2:52:03<12:19:15, 5.74s/it] 34%|███▍ | 3998/11728 [2:52:09<12:36:26, 5.87s/it] {'loss': 0.4822, 'learning_rate': 1.5345017344813414e-05, 'epoch': 0.34} + 34%|███▍ | 3998/11728 [2:52:09<12:36:26, 5.87s/it] 34%|███▍ | 3999/11728 [2:52:15<12:35:47, 5.87s/it] {'loss': 0.4887, 'learning_rate': 1.534268312940201e-05, 'epoch': 0.34} + 34%|███▍ | 3999/11728 [2:52:15<12:35:47, 5.87s/it]2 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend...0 + AutoResumeHook: Checking whether to suspend... + 34%|███▍ | 4000/11728 [2:52:21<12:35:22, 5.86s/it]5 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4759, 'learning_rate': 1.534034850653528e-05, 'epoch': 0.34} + 34%|███▍ | 4000/11728 [2:52:21<12:35:22, 5.86s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-4000/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-4000/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-4000/mm_projector +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/torch/nn/modules/module.py:1802: UserWarning: Positional args are being deprecated, use kwargs instead. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details. + warnings.warn( + 34%|███▍ | 4001/11728 [2:52:52<28:50:19, 13.44s/it] {'loss': 0.4983, 'learning_rate': 1.5338013476391282e-05, 'epoch': 0.34} + 34%|███▍ | 4001/11728 [2:52:52<28:50:19, 13.44s/it] 34%|███▍ | 4002/11728 [2:52:58<24:01:35, 11.20s/it] {'loss': 0.4882, 'learning_rate': 1.5335678039148094e-05, 'epoch': 0.34} + 34%|███▍ | 4002/11728 [2:52:58<24:01:35, 11.20s/it] 34%|███▍ | 4003/11728 [2:53:04<20:32:00, 9.57s/it] {'loss': 0.4814, 'learning_rate': 1.533334219498382e-05, 'epoch': 0.34} + 34%|███▍ | 4003/11728 [2:53:04<20:32:00, 9.57s/it] 34%|███▍ | 4004/11728 [2:53:10<18:07:24, 8.45s/it] {'loss': 0.5108, 'learning_rate': 1.53310059440766e-05, 'epoch': 0.34} + 34%|███▍ | 4004/11728 [2:53:10<18:07:24, 8.45s/it] 34%|███▍ | 4005/11728 [2:53:16<16:28:21, 7.68s/it] {'loss': 0.4952, 'learning_rate': 1.5328669286604612e-05, 'epoch': 0.34} + 34%|███▍ | 4005/11728 [2:53:16<16:28:21, 7.68s/it] 34%|███▍ | 4006/11728 [2:53:22<15:28:48, 7.22s/it] {'loss': 0.4661, 'learning_rate': 1.532633222274606e-05, 'epoch': 0.34} + 34%|███▍ | 4006/11728 [2:53:22<15:28:48, 7.22s/it] 34%|███▍ | 4007/11728 [2:53:28<14:38:21, 6.83s/it] {'loss': 0.4965, 'learning_rate': 1.5323994752679174e-05, 'epoch': 0.34} + 34%|███▍ | 4007/11728 [2:53:28<14:38:21, 6.83s/it] 34%|███▍ | 4008/11728 [2:53:34<14:12:58, 6.63s/it] {'loss': 0.4918, 'learning_rate': 1.5321656876582226e-05, 'epoch': 0.34} + 34%|███▍ | 4008/11728 [2:53:34<14:12:58, 6.63s/it] 34%|███▍ | 4009/11728 [2:53:40<13:40:51, 6.38s/it] {'loss': 0.4796, 'learning_rate': 1.53193185946335e-05, 'epoch': 0.34} + 34%|███▍ | 4009/11728 [2:53:40<13:40:51, 6.38s/it] 34%|███▍ | 4010/11728 [2:53:45<13:06:27, 6.11s/it] {'loss': 0.4806, 'learning_rate': 1.5316979907011335e-05, 'epoch': 0.34} + 34%|███▍ | 4010/11728 [2:53:45<13:06:27, 6.11s/it] 34%|███▍ | 4011/11728 [2:53:51<13:04:21, 6.10s/it] {'loss': 0.4856, 'learning_rate': 1.5314640813894088e-05, 'epoch': 0.34} + 34%|███▍ | 4011/11728 [2:53:51<13:04:21, 6.10s/it] 34%|███▍ | 4012/11728 [2:53:57<12:57:48, 6.05s/it] {'loss': 0.4891, 'learning_rate': 1.531230131546014e-05, 'epoch': 0.34} + 34%|███▍ | 4012/11728 [2:53:57<12:57:48, 6.05s/it] 34%|███▍ | 4013/11728 [2:54:03<12:50:42, 5.99s/it] {'loss': 0.469, 'learning_rate': 1.5309961411887915e-05, 'epoch': 0.34} + 34%|███▍ | 4013/11728 [2:54:03<12:50:42, 5.99s/it] 34%|███▍ | 4014/11728 [2:54:09<12:42:34, 5.93s/it] {'loss': 0.499, 'learning_rate': 1.5307621103355865e-05, 'epoch': 0.34} + 34%|███▍ | 4014/11728 [2:54:09<12:42:34, 5.93s/it] 34%|███▍ | 4015/11728 [2:54:15<12:40:04, 5.91s/it] {'loss': 0.5021, 'learning_rate': 1.530528039004247e-05, 'epoch': 0.34} + 34%|███▍ | 4015/11728 [2:54:15<12:40:04, 5.91s/it] 34%|███▍ | 4016/11728 [2:54:20<12:38:35, 5.90s/it] {'loss': 0.4842, 'learning_rate': 1.5302939272126243e-05, 'epoch': 0.34} + 34%|███▍ | 4016/11728 [2:54:20<12:38:35, 5.90s/it] 34%|███▍ | 4017/11728 [2:54:26<12:32:10, 5.85s/it] {'loss': 0.4744, 'learning_rate': 1.530059774978573e-05, 'epoch': 0.34} + 34%|███▍ | 4017/11728 [2:54:26<12:32:10, 5.85s/it] 34%|███▍ | 4018/11728 [2:54:32<12:28:58, 5.83s/it] {'loss': 0.4916, 'learning_rate': 1.5298255823199503e-05, 'epoch': 0.34} + 34%|███▍ | 4018/11728 [2:54:32<12:28:58, 5.83s/it] 34%|███▍ | 4019/11728 [2:54:38<12:17:20, 5.74s/it] {'loss': 0.4613, 'learning_rate': 1.5295913492546168e-05, 'epoch': 0.34} + 34%|███▍ | 4019/11728 [2:54:38<12:17:20, 5.74s/it] 34%|███▍ | 4020/11728 [2:54:44<12:27:45, 5.82s/it] {'loss': 0.5065, 'learning_rate': 1.529357075800436e-05, 'epoch': 0.34} + 34%|███▍ | 4020/11728 [2:54:44<12:27:45, 5.82s/it] 34%|███▍ | 4021/11728 [2:54:49<12:17:30, 5.74s/it] {'loss': 0.4898, 'learning_rate': 1.5291227619752748e-05, 'epoch': 0.34} + 34%|███▍ | 4021/11728 [2:54:49<12:17:30, 5.74s/it] 34%|███▍ | 4022/11728 [2:54:55<12:14:07, 5.72s/it] {'loss': 0.4796, 'learning_rate': 1.5288884077970025e-05, 'epoch': 0.34} + 34%|███▍ | 4022/11728 [2:54:55<12:14:07, 5.72s/it] 34%|███▍ | 4023/11728 [2:55:00<12:15:16, 5.73s/it] {'loss': 0.4845, 'learning_rate': 1.528654013283492e-05, 'epoch': 0.34} + 34%|███▍ | 4023/11728 [2:55:00<12:15:16, 5.73s/it] 34%|███▍ | 4024/11728 [2:55:06<12:08:30, 5.67s/it] {'loss': 0.4808, 'learning_rate': 1.5284195784526196e-05, 'epoch': 0.34} + 34%|███▍ | 4024/11728 [2:55:06<12:08:30, 5.67s/it] 34%|███▍ | 4025/11728 [2:55:12<12:13:24, 5.71s/it] {'loss': 0.4871, 'learning_rate': 1.528185103322264e-05, 'epoch': 0.34} + 34%|███▍ | 4025/11728 [2:55:12<12:13:24, 5.71s/it] 34%|███▍ | 4026/11728 [2:55:17<12:10:05, 5.69s/it] {'loss': 0.4665, 'learning_rate': 1.5279505879103074e-05, 'epoch': 0.34} + 34%|███▍ | 4026/11728 [2:55:17<12:10:05, 5.69s/it] 34%|███▍ | 4027/11728 [2:55:23<12:12:18, 5.71s/it] {'loss': 0.482, 'learning_rate': 1.527716032234635e-05, 'epoch': 0.34} + 34%|███▍ | 4027/11728 [2:55:23<12:12:18, 5.71s/it] 34%|███▍ | 4028/11728 [2:55:29<12:14:23, 5.72s/it] {'loss': 0.4837, 'learning_rate': 1.5274814363131346e-05, 'epoch': 0.34} + 34%|███▍ | 4028/11728 [2:55:29<12:14:23, 5.72s/it] 34%|███▍ | 4029/11728 [2:55:35<12:13:26, 5.72s/it] {'loss': 0.4891, 'learning_rate': 1.5272468001636975e-05, 'epoch': 0.34} + 34%|███▍ | 4029/11728 [2:55:35<12:13:26, 5.72s/it] 34%|███▍ | 4030/11728 [2:55:41<12:17:24, 5.75s/it] {'loss': 0.5038, 'learning_rate': 1.5270121238042186e-05, 'epoch': 0.34} + 34%|███▍ | 4030/11728 [2:55:41<12:17:24, 5.75s/it] 34%|███▍ | 4031/11728 [2:55:46<12:12:04, 5.71s/it] {'loss': 0.4996, 'learning_rate': 1.5267774072525948e-05, 'epoch': 0.34} + 34%|███▍ | 4031/11728 [2:55:46<12:12:04, 5.71s/it] 34%|███▍ | 4032/11728 [2:55:52<12:23:38, 5.80s/it] {'loss': 0.4757, 'learning_rate': 1.5265426505267265e-05, 'epoch': 0.34} + 34%|███▍ | 4032/11728 [2:55:52<12:23:38, 5.80s/it] 34%|███▍ | 4033/11728 [2:55:58<12:24:32, 5.81s/it] {'loss': 0.5009, 'learning_rate': 1.5263078536445176e-05, 'epoch': 0.34} + 34%|███▍ | 4033/11728 [2:55:58<12:24:32, 5.81s/it] 34%|███▍ | 4034/11728 [2:56:04<12:26:55, 5.82s/it] {'loss': 0.4806, 'learning_rate': 1.5260730166238747e-05, 'epoch': 0.34} + 34%|███▍ | 4034/11728 [2:56:04<12:26:55, 5.82s/it] 34%|███▍ | 4035/11728 [2:56:10<12:23:13, 5.80s/it] {'loss': 0.4717, 'learning_rate': 1.525838139482707e-05, 'epoch': 0.34} + 34%|███▍ | 4035/11728 [2:56:10<12:23:13, 5.80s/it] 34%|███▍ | 4036/11728 [2:56:15<12:12:56, 5.72s/it] {'loss': 0.4881, 'learning_rate': 1.5256032222389276e-05, 'epoch': 0.34} + 34%|███▍ | 4036/11728 [2:56:15<12:12:56, 5.72s/it] 34%|███▍ | 4037/11728 [2:56:21<12:27:54, 5.83s/it] {'loss': 0.4827, 'learning_rate': 1.5253682649104519e-05, 'epoch': 0.34} + 34%|███▍ | 4037/11728 [2:56:21<12:27:54, 5.83s/it] 34%|███▍ | 4038/11728 [2:56:27<12:21:20, 5.78s/it] {'loss': 0.4975, 'learning_rate': 1.5251332675151993e-05, 'epoch': 0.34} + 34%|███▍ | 4038/11728 [2:56:27<12:21:20, 5.78s/it] 34%|███▍ | 4039/11728 [2:56:33<12:24:11, 5.81s/it] {'loss': 0.4933, 'learning_rate': 1.5248982300710913e-05, 'epoch': 0.34} + 34%|███▍ | 4039/11728 [2:56:33<12:24:11, 5.81s/it] 34%|███▍ | 4040/11728 [2:56:38<12:21:51, 5.79s/it] {'loss': 0.4836, 'learning_rate': 1.5246631525960527e-05, 'epoch': 0.34} + 34%|███▍ | 4040/11728 [2:56:38<12:21:51, 5.79s/it] 34%|███▍ | 4041/11728 [2:56:44<12:26:28, 5.83s/it] {'loss': 0.4989, 'learning_rate': 1.5244280351080121e-05, 'epoch': 0.34} + 34%|███▍ | 4041/11728 [2:56:44<12:26:28, 5.83s/it] 34%|███▍ | 4042/11728 [2:56:50<12:28:21, 5.84s/it] {'loss': 0.4815, 'learning_rate': 1.5241928776248993e-05, 'epoch': 0.34} + 34%|███▍ | 4042/11728 [2:56:50<12:28:21, 5.84s/it] 34%|███▍ | 4043/11728 [2:56:56<12:26:29, 5.83s/it] {'loss': 0.4577, 'learning_rate': 1.5239576801646501e-05, 'epoch': 0.34} + 34%|███▍ | 4043/11728 [2:56:56<12:26:29, 5.83s/it] 34%|███▍ | 4044/11728 [2:57:02<12:20:18, 5.78s/it] {'loss': 0.5196, 'learning_rate': 1.5237224427452002e-05, 'epoch': 0.34} + 34%|███▍ | 4044/11728 [2:57:02<12:20:18, 5.78s/it] 34%|███▍ | 4045/11728 [2:57:08<12:21:50, 5.79s/it] {'loss': 0.4694, 'learning_rate': 1.5234871653844904e-05, 'epoch': 0.34} + 34%|███▍ | 4045/11728 [2:57:08<12:21:50, 5.79s/it] 34%|███▍ | 4046/11728 [2:57:13<12:16:31, 5.75s/it] {'loss': 0.4869, 'learning_rate': 1.5232518481004642e-05, 'epoch': 0.34} + 34%|███▍ | 4046/11728 [2:57:13<12:16:31, 5.75s/it] 35%|███▍ | 4047/11728 [2:57:19<12:20:18, 5.78s/it] {'loss': 0.4875, 'learning_rate': 1.5230164909110674e-05, 'epoch': 0.35} + 35%|███▍ | 4047/11728 [2:57:19<12:20:18, 5.78s/it] 35%|███▍ | 4048/11728 [2:57:25<12:13:28, 5.73s/it] {'loss': 0.4796, 'learning_rate': 1.5227810938342493e-05, 'epoch': 0.35} + 35%|███▍ | 4048/11728 [2:57:25<12:13:28, 5.73s/it] 35%|███▍ | 4049/11728 [2:57:30<12:11:17, 5.71s/it] {'loss': 0.4726, 'learning_rate': 1.5225456568879624e-05, 'epoch': 0.35} + 35%|███▍ | 4049/11728 [2:57:30<12:11:17, 5.71s/it]4 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +51 0 AutoResumeHook: Checking whether to suspend...AutoResumeHook: Checking whether to suspend... + +2 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... + 35%|███▍ | 4050/11728 [2:57:36<12:15:02, 5.74s/it]3 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4954, 'learning_rate': 1.5223101800901625e-05, 'epoch': 0.35} + 35%|███▍ | 4050/11728 [2:57:36<12:15:02, 5.74s/it] 35%|███▍ | 4051/11728 [2:57:42<12:20:14, 5.79s/it] {'loss': 0.4922, 'learning_rate': 1.5220746634588076e-05, 'epoch': 0.35} + 35%|███▍ | 4051/11728 [2:57:42<12:20:14, 5.79s/it] 35%|███▍ | 4052/11728 [2:57:48<12:24:51, 5.82s/it] {'loss': 0.4758, 'learning_rate': 1.521839107011859e-05, 'epoch': 0.35} + 35%|███▍ | 4052/11728 [2:57:48<12:24:51, 5.82s/it] 35%|███▍ | 4053/11728 [2:57:54<12:26:37, 5.84s/it] {'loss': 0.4871, 'learning_rate': 1.5216035107672818e-05, 'epoch': 0.35} + 35%|███▍ | 4053/11728 [2:57:54<12:26:37, 5.84s/it] 35%|███▍ | 4054/11728 [2:57:59<12:18:25, 5.77s/it] {'loss': 0.4562, 'learning_rate': 1.5213678747430429e-05, 'epoch': 0.35} + 35%|███▍ | 4054/11728 [2:57:59<12:18:25, 5.77s/it] 35%|███▍ | 4055/11728 [2:58:05<12:14:06, 5.74s/it] {'loss': 0.4698, 'learning_rate': 1.5211321989571134e-05, 'epoch': 0.35} + 35%|███▍ | 4055/11728 [2:58:05<12:14:06, 5.74s/it] 35%|███▍ | 4056/11728 [2:58:11<12:17:31, 5.77s/it] {'loss': 0.4872, 'learning_rate': 1.5208964834274669e-05, 'epoch': 0.35} + 35%|███▍ | 4056/11728 [2:58:11<12:17:31, 5.77s/it] 35%|███▍ | 4057/11728 [2:58:17<12:26:07, 5.84s/it] {'loss': 0.5011, 'learning_rate': 1.5206607281720797e-05, 'epoch': 0.35} + 35%|███▍ | 4057/11728 [2:58:17<12:26:07, 5.84s/it] 35%|███▍ | 4058/11728 [2:58:23<12:17:34, 5.77s/it] {'loss': 0.4675, 'learning_rate': 1.5204249332089318e-05, 'epoch': 0.35} + 35%|███▍ | 4058/11728 [2:58:23<12:17:34, 5.77s/it]WARNING: tokenization mismatch: 1 vs. 1440. [[{'from': 'human', 'value': 'ASSISTANT: Du bist ein Personalmarketing-Experte mit den folgenden Kenntnissen und Eigenschaften.\n\nKENNTNISSE: Personalmarketing, Social Media Marketing, Facebook-Marketing, Kampagnenentwicklung, Zielgruppenanalyse, Content-Strategie, Werbeanzeigen, Performance-Messung, Personalgewinnung, Steuerfachangestellte.\n\nEIGENSCHAFTEN: Kreativ, strategisch, analytisch, kommunikativ, zielorientiert, detailverliebt, teamorientiert.\n\nAUFGABE: Entwickle eine erfolgreiche Personalmarketing-Strategie für die Gewinnung von Steuerfachangestellten über Facebook. Erstelle eine Tabelle mit allen Maßnahmen und weise jeder Maßnahme den zuständigen Spezialisten in einer Marketingagentur zu. Achte dabei auf Zielgruppenanalyse, Content-Strategie, Werbeanzeigen und Performance-Messung.\n\nOUTPUT: Eine Tabelle mit allen Maßnahmen für eine erfolgreiche Personalmarketing-Kampagne zur Gewinnung von Steuerfachangestellten auf Facebook, die die Verantwortlichkeiten der Spezialisten in einer Marketingagentur aufzeigt, einschließlich Zielgruppenanalyse, Content-Strategie, Werbeanzeigen und Performance-Messung.'}, {'from': 'gpt', 'value': '| Maßnahme | Beschreibung | Zuständiger Spezialist |\n| --- | --- | --- |\n| Zielgruppenanalyse | Analyse der demografischen Daten, Interessen und Verhaltensweisen der potenziellen Bewerber. | Marktanalyst |\n| Erstellung von Personas | Entwicklung von fiktiven, repräsentativen Bewerberprofilen zur besseren Zielgruppenansprache. | Personalmarketing-Experte |\n| Content-Strategie | Planung von relevantem, ansprechendem und zielgruppenspezifischem Content. | Content-Stratege |\n| Redaktionsplan | Erstellung eines Zeitplans für die Veröffentlichung von Inhalten auf Facebook. | Social Media Manager |\n| Erstellung von Werbeanzeigen | Design und Texten von ansprechenden, zielgruppenspezifischen Facebook-Werbeanzeigen. | Art Director & Copywriter |\n| Auswahl von Targeting-Optionen | Festlegung der Zielgruppenparameter für die Facebook-Werbekampagnen. | Facebook-Marketing-Experte |\n| Budgetierung und Zeitplanung | Festlegung des Budgets und der Laufzeit für die Facebook-Werbekampagnen. | Media Planner |\n| Erstellung von Landing Pages | Gestaltung und Implementierung von spezifischen Landing Pages für die Bewerbung. | Web-Designer |\n| Performance-Messung | Überwachung und Analyse der Kampagnenleistung, einschließlich KPIs wie Klicks und Bewerbungen. | Data Analyst |\n| A/B-Testing | Durchführung von A/B-Tests, um die Effektivität von Anzeigen und Landing Pages zu optimieren. | Conversion-Optimierungsexperte |\n| Community-Management | Interaktion mit der Zielgruppe auf Facebook, Beantwortung von Fragen und Moderation von Diskussionen. | Community Manager |\n| Reporting und Optimierung | Regelmäßige Berichterstattung über die Kampagnenergebnisse und Anpassung der Strategie. | Performance Marketing-Manager |'}, {'from': 'human', 'value': 'Weiter.'}, {'from': 'gpt', 'value': 'Hier sind einige zusätzliche Maßnahmen, die Sie in Ihre Personalmarketing-Strategie für die Gewinnung von Steuerfachangestellten über Facebook einbeziehen können:\n\n| Maßnahme | Beschreibung | Zuständiger Spezialist |\n| --- | --- | --- |\n| Video-Content | Erstellung von Video-Content, wie Interviews mit aktuellen Mitarbeitern oder Berufsalltagsvideos. | Videoproduzent |\n| Influencer-Marketing | Zusammenarbeit mit Influencern aus der Branche, um Ihre Arbeitgebermarke zu stärken. | Influencer-Marketing-Experte |\n| Anpassung von Stellenanzeigen | Anpassung der Stellenanzeigen auf Facebook, um die Zielgruppe besser anzusprechen. | Personalmarketing-Experte |\n| Mitarbeiter-Testimonials | Teilen von Erfahrungsberichten und Zitaten der Mitarbeiter auf Facebook, um Authentizität zu schaffen. | Content-Stratege |\n| Virtuelle Karriere-Events | Durchführung von virtuellen Karriere-Events oder Informationsveranstaltungen auf Facebook. | Event-Manager |\n| Interaktive Umfragen und Quiz | Nutzung von interaktiven Umfragen und Quiz auf Facebook, um das Engagement zu erhöhen. | Social Media Manager |\n| Remarketing-Kampagnen | Einsatz von Remarketing-Anzeigen, um die Personen erneut anzusprechen, die bereits interessiert waren. | Facebook-Marketing-Experte |\n| Monitoring von Wettbewerbern | Beobachtung der Personalmarketing-Aktivitäten der Wettbewerber auf Facebook und Ableitung von Optimierungspotenzialen. | Marktanalyst |\n| Integration von Chatbots | Implementierung von Chatbots auf der Facebook-Seite und der Landing Page zur Automatisierung des Bewerbungsprozesses. | Chatbot-Entwickler |\n| Employer Branding-Kampagne | Entwicklung einer Employer Branding-Kampagne, die die Unternehmenskultur und -werte hervorhebt. | Employer Branding-Experte |\n\nMit diesen erweiterten Maßnahmen können Sie eine noch umfassendere Personalmarketing-Strategie entwickeln, die die Chancen erhöht, qualifizierte Steuerfachangestellte über Facebook zu gewinnen.'}]] (ignored) + 35%|███▍ | 4059/11728 [2:58:28<12:20:53, 5.80s/it] {'loss': 0.4875, 'learning_rate': 1.5201890985560056e-05, 'epoch': 0.35} + 35%|███▍ | 4059/11728 [2:58:28<12:20:53, 5.80s/it] 35%|███▍ | 4060/11728 [2:58:34<12:18:23, 5.78s/it] {'loss': 0.4996, 'learning_rate': 1.5199532242312872e-05, 'epoch': 0.35} + 35%|███▍ | 4060/11728 [2:58:34<12:18:23, 5.78s/it] 35%|███▍ | 4061/11728 [2:58:40<12:18:58, 5.78s/it] {'loss': 0.4916, 'learning_rate': 1.5197173102527652e-05, 'epoch': 0.35} + 35%|███▍ | 4061/11728 [2:58:40<12:18:58, 5.78s/it] 35%|███▍ | 4062/11728 [2:58:46<12:11:22, 5.72s/it] {'loss': 0.4956, 'learning_rate': 1.5194813566384312e-05, 'epoch': 0.35} + 35%|███▍ | 4062/11728 [2:58:46<12:11:22, 5.72s/it] 35%|███▍ | 4063/11728 [2:58:52<12:31:58, 5.89s/it] {'loss': 0.5038, 'learning_rate': 1.51924536340628e-05, 'epoch': 0.35} + 35%|███▍ | 4063/11728 [2:58:52<12:31:58, 5.89s/it] 35%|███▍ | 4064/11728 [2:58:57<12:17:05, 5.77s/it] {'loss': 0.4761, 'learning_rate': 1.5190093305743103e-05, 'epoch': 0.35} + 35%|███▍ | 4064/11728 [2:58:57<12:17:05, 5.77s/it] 35%|███▍ | 4065/11728 [2:59:03<12:24:13, 5.83s/it] {'loss': 0.4839, 'learning_rate': 1.5187732581605217e-05, 'epoch': 0.35} + 35%|███▍ | 4065/11728 [2:59:03<12:24:13, 5.83s/it] 35%|███▍ | 4066/11728 [2:59:09<12:33:25, 5.90s/it] {'loss': 0.5018, 'learning_rate': 1.5185371461829186e-05, 'epoch': 0.35} + 35%|███▍ | 4066/11728 [2:59:09<12:33:25, 5.90s/it] 35%|███▍ | 4067/11728 [2:59:15<12:20:20, 5.80s/it] {'loss': 0.5062, 'learning_rate': 1.518300994659508e-05, 'epoch': 0.35} + 35%|███▍ | 4067/11728 [2:59:15<12:20:20, 5.80s/it] 35%|███▍ | 4068/11728 [2:59:21<12:41:47, 5.97s/it] {'loss': 0.4834, 'learning_rate': 1.5180648036082998e-05, 'epoch': 0.35} + 35%|███▍ | 4068/11728 [2:59:21<12:41:47, 5.97s/it] 35%|███▍ | 4069/11728 [2:59:27<12:45:05, 5.99s/it] {'loss': 0.5115, 'learning_rate': 1.5178285730473068e-05, 'epoch': 0.35} + 35%|███▍ | 4069/11728 [2:59:27<12:45:05, 5.99s/it] 35%|███▍ | 4070/11728 [2:59:33<12:35:13, 5.92s/it] {'loss': 0.491, 'learning_rate': 1.5175923029945447e-05, 'epoch': 0.35} + 35%|███▍ | 4070/11728 [2:59:33<12:35:13, 5.92s/it] 35%|███▍ | 4071/11728 [2:59:42<14:21:32, 6.75s/it] {'loss': 0.4844, 'learning_rate': 1.5173559934680331e-05, 'epoch': 0.35} + 35%|███▍ | 4071/11728 [2:59:42<14:21:32, 6.75s/it] 35%|███▍ | 4072/11728 [2:59:48<13:47:08, 6.48s/it] {'loss': 0.4752, 'learning_rate': 1.5171196444857933e-05, 'epoch': 0.35} + 35%|███▍ | 4072/11728 [2:59:48<13:47:08, 6.48s/it] 35%|███▍ | 4073/11728 [2:59:53<13:14:10, 6.22s/it] {'loss': 0.4653, 'learning_rate': 1.5168832560658506e-05, 'epoch': 0.35} + 35%|███▍ | 4073/11728 [2:59:53<13:14:10, 6.22s/it] 35%|███▍ | 4074/11728 [2:59:59<12:47:59, 6.02s/it] {'loss': 0.4915, 'learning_rate': 1.5166468282262327e-05, 'epoch': 0.35} + 35%|███▍ | 4074/11728 [2:59:59<12:47:59, 6.02s/it] 35%|███▍ | 4075/11728 [3:00:04<12:35:31, 5.92s/it] {'loss': 0.4833, 'learning_rate': 1.516410360984971e-05, 'epoch': 0.35} + 35%|███▍ | 4075/11728 [3:00:04<12:35:31, 5.92s/it] 35%|███▍ | 4076/11728 [3:00:10<12:32:08, 5.90s/it] {'loss': 0.5093, 'learning_rate': 1.516173854360099e-05, 'epoch': 0.35} + 35%|███▍ | 4076/11728 [3:00:10<12:32:08, 5.90s/it] 35%|███▍ | 4077/11728 [3:00:16<12:36:44, 5.93s/it] {'loss': 0.4616, 'learning_rate': 1.515937308369654e-05, 'epoch': 0.35} + 35%|███▍ | 4077/11728 [3:00:16<12:36:44, 5.93s/it] 35%|███▍ | 4078/11728 [3:00:22<12:28:27, 5.87s/it] {'loss': 0.5034, 'learning_rate': 1.5157007230316757e-05, 'epoch': 0.35} + 35%|███▍ | 4078/11728 [3:00:22<12:28:27, 5.87s/it] 35%|███▍ | 4079/11728 [3:00:28<12:22:35, 5.83s/it] {'loss': 0.4805, 'learning_rate': 1.5154640983642077e-05, 'epoch': 0.35} + 35%|███▍ | 4079/11728 [3:00:28<12:22:35, 5.83s/it] 35%|███▍ | 4080/11728 [3:00:34<12:20:59, 5.81s/it] {'loss': 0.4952, 'learning_rate': 1.5152274343852953e-05, 'epoch': 0.35} + 35%|███▍ | 4080/11728 [3:00:34<12:20:59, 5.81s/it] 35%|███▍ | 4081/11728 [3:00:39<12:21:00, 5.81s/it] {'loss': 0.4856, 'learning_rate': 1.5149907311129877e-05, 'epoch': 0.35} + 35%|███▍ | 4081/11728 [3:00:39<12:21:00, 5.81s/it]WARNING: tokenization mismatch: 1 vs. 64. [[{'from': 'human', 'value': '\nWhat vitamin is this vegetable associated with?\nAnswer the question using a single word or phrase.'}, {'from': 'gpt', 'value': ''}]] (ignored) + 35%|███▍ | 4082/11728 [3:00:45<12:19:14, 5.80s/it] {'loss': 0.5014, 'learning_rate': 1.514753988565337e-05, 'epoch': 0.35} + 35%|███▍ | 4082/11728 [3:00:45<12:19:14, 5.80s/it] 35%|███▍ | 4083/11728 [3:00:51<12:17:41, 5.79s/it] {'loss': 0.4795, 'learning_rate': 1.514517206760398e-05, 'epoch': 0.35} + 35%|███▍ | 4083/11728 [3:00:51<12:17:41, 5.79s/it] 35%|███▍ | 4084/11728 [3:00:56<12:07:58, 5.71s/it] {'loss': 0.4585, 'learning_rate': 1.5142803857162289e-05, 'epoch': 0.35} + 35%|███▍ | 4084/11728 [3:00:56<12:07:58, 5.71s/it] 35%|███▍ | 4085/11728 [3:01:02<11:59:01, 5.64s/it] {'loss': 0.4824, 'learning_rate': 1.5140435254508905e-05, 'epoch': 0.35} + 35%|███▍ | 4085/11728 [3:01:02<11:59:01, 5.64s/it] 35%|███▍ | 4086/11728 [3:01:08<11:59:34, 5.65s/it] {'loss': 0.4976, 'learning_rate': 1.5138066259824468e-05, 'epoch': 0.35} + 35%|███▍ | 4086/11728 [3:01:08<11:59:34, 5.65s/it] 35%|███▍ | 4087/11728 [3:01:13<12:08:15, 5.72s/it] {'loss': 0.4955, 'learning_rate': 1.5135696873289648e-05, 'epoch': 0.35} + 35%|███▍ | 4087/11728 [3:01:13<12:08:15, 5.72s/it] 35%|███▍ | 4088/11728 [3:01:19<12:17:47, 5.79s/it] {'loss': 0.5017, 'learning_rate': 1.5133327095085139e-05, 'epoch': 0.35} + 35%|███▍ | 4088/11728 [3:01:19<12:17:47, 5.79s/it] 35%|███▍ | 4089/11728 [3:01:25<12:12:30, 5.75s/it] {'loss': 0.4766, 'learning_rate': 1.5130956925391678e-05, 'epoch': 0.35} + 35%|███▍ | 4089/11728 [3:01:25<12:12:30, 5.75s/it] 35%|███▍ | 4090/11728 [3:01:31<12:16:11, 5.78s/it] {'loss': 0.4983, 'learning_rate': 1.5128586364390021e-05, 'epoch': 0.35} + 35%|███▍ | 4090/11728 [3:01:31<12:16:11, 5.78s/it] 35%|███▍ | 4091/11728 [3:01:37<12:27:30, 5.87s/it] {'loss': 0.4774, 'learning_rate': 1.5126215412260958e-05, 'epoch': 0.35} + 35%|███▍ | 4091/11728 [3:01:37<12:27:30, 5.87s/it] 35%|███▍ | 4092/11728 [3:01:43<12:28:28, 5.88s/it] {'loss': 0.4874, 'learning_rate': 1.5123844069185305e-05, 'epoch': 0.35} + 35%|███▍ | 4092/11728 [3:01:43<12:28:28, 5.88s/it] 35%|███▍ | 4093/11728 [3:01:49<12:22:29, 5.83s/it] {'loss': 0.474, 'learning_rate': 1.5121472335343912e-05, 'epoch': 0.35} + 35%|███▍ | 4093/11728 [3:01:49<12:22:29, 5.83s/it] 35%|███▍ | 4094/11728 [3:01:55<12:23:23, 5.84s/it] {'loss': 0.4971, 'learning_rate': 1.5119100210917657e-05, 'epoch': 0.35} + 35%|███▍ | 4094/11728 [3:01:55<12:23:23, 5.84s/it] 35%|███▍ | 4095/11728 [3:02:00<12:14:34, 5.77s/it] {'loss': 0.4915, 'learning_rate': 1.5116727696087447e-05, 'epoch': 0.35} + 35%|███▍ | 4095/11728 [3:02:00<12:14:34, 5.77s/it] 35%|███▍ | 4096/11728 [3:02:06<12:26:45, 5.87s/it] {'loss': 0.526, 'learning_rate': 1.5114354791034225e-05, 'epoch': 0.35} + 35%|███▍ | 4096/11728 [3:02:06<12:26:45, 5.87s/it] 35%|███▍ | 4097/11728 [3:02:12<12:29:50, 5.90s/it] {'loss': 0.4803, 'learning_rate': 1.511198149593895e-05, 'epoch': 0.35} + 35%|███▍ | 4097/11728 [3:02:12<12:29:50, 5.90s/it] 35%|███▍ | 4098/11728 [3:02:18<12:38:48, 5.97s/it] {'loss': 0.4991, 'learning_rate': 1.5109607810982628e-05, 'epoch': 0.35} + 35%|███▍ | 4098/11728 [3:02:18<12:38:48, 5.97s/it] 35%|███▍ | 4099/11728 [3:02:24<12:31:11, 5.91s/it] {'loss': 0.4992, 'learning_rate': 1.5107233736346278e-05, 'epoch': 0.35} + 35%|███▍ | 4099/11728 [3:02:24<12:31:11, 5.91s/it]4 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +0 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... + 35%|███▍ | 4100/11728 [3:02:30<12:18:41, 5.81s/it]3 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4661, 'learning_rate': 1.5104859272210966e-05, 'epoch': 0.35} + 35%|███▍ | 4100/11728 [3:02:30<12:18:41, 5.81s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-4100/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-4100/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-4100/mm_projector +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/torch/nn/modules/module.py:1802: UserWarning: Positional args are being deprecated, use kwargs instead. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details. + warnings.warn( + 35%|███▍ | 4101/11728 [3:03:03<29:30:07, 13.93s/it] {'loss': 0.4967, 'learning_rate': 1.5102484418757772e-05, 'epoch': 0.35} + 35%|███▍ | 4101/11728 [3:03:03<29:30:07, 13.93s/it] 35%|███▍ | 4102/11728 [3:03:08<24:16:29, 11.46s/it] {'loss': 0.4959, 'learning_rate': 1.5100109176167814e-05, 'epoch': 0.35} + 35%|███▍ | 4102/11728 [3:03:08<24:16:29, 11.46s/it] 35%|███▍ | 4103/11728 [3:03:14<20:32:06, 9.70s/it] {'loss': 0.4841, 'learning_rate': 1.5097733544622239e-05, 'epoch': 0.35} + 35%|███▍ | 4103/11728 [3:03:14<20:32:06, 9.70s/it] 35%|███▍ | 4104/11728 [3:03:20<18:10:20, 8.58s/it] {'loss': 0.5046, 'learning_rate': 1.5095357524302219e-05, 'epoch': 0.35} + 35%|███▍ | 4104/11728 [3:03:20<18:10:20, 8.58s/it] 35%|███▌ | 4105/11728 [3:03:25<16:17:54, 7.70s/it] {'loss': 0.4772, 'learning_rate': 1.5092981115388963e-05, 'epoch': 0.35} + 35%|███▌ | 4105/11728 [3:03:25<16:17:54, 7.70s/it] 35%|███▌ | 4106/11728 [3:03:31<15:08:16, 7.15s/it] {'loss': 0.5079, 'learning_rate': 1.5090604318063704e-05, 'epoch': 0.35} + 35%|███▌ | 4106/11728 [3:03:31<15:08:16, 7.15s/it] 35%|███▌ | 4107/11728 [3:03:40<16:15:53, 7.68s/it] {'loss': 0.4735, 'learning_rate': 1.508822713250771e-05, 'epoch': 0.35} + 35%|███▌ | 4107/11728 [3:03:40<16:15:53, 7.68s/it] 35%|███▌ | 4108/11728 [3:03:46<15:12:16, 7.18s/it] {'loss': 0.4879, 'learning_rate': 1.5085849558902265e-05, 'epoch': 0.35} + 35%|███▌ | 4108/11728 [3:03:46<15:12:16, 7.18s/it] 35%|███▌ | 4109/11728 [3:03:52<14:15:10, 6.73s/it] {'loss': 0.4677, 'learning_rate': 1.5083471597428707e-05, 'epoch': 0.35} + 35%|███▌ | 4109/11728 [3:03:52<14:15:10, 6.73s/it] 35%|███▌ | 4110/11728 [3:03:57<13:30:54, 6.39s/it] {'loss': 0.4747, 'learning_rate': 1.5081093248268382e-05, 'epoch': 0.35} + 35%|███▌ | 4110/11728 [3:03:57<13:30:54, 6.39s/it] 35%|███▌ | 4111/11728 [3:04:03<13:14:01, 6.25s/it] {'loss': 0.4941, 'learning_rate': 1.5078714511602667e-05, 'epoch': 0.35} + 35%|███▌ | 4111/11728 [3:04:03<13:14:01, 6.25s/it] 35%|███▌ | 4112/11728 [3:04:09<12:56:55, 6.12s/it] {'loss': 0.4886, 'learning_rate': 1.5076335387612987e-05, 'epoch': 0.35} + 35%|███▌ | 4112/11728 [3:04:09<12:56:55, 6.12s/it] 35%|███▌ | 4113/11728 [3:04:15<12:44:52, 6.03s/it] {'loss': 0.4601, 'learning_rate': 1.5073955876480775e-05, 'epoch': 0.35} + 35%|███▌ | 4113/11728 [3:04:15<12:44:52, 6.03s/it] 35%|███▌ | 4114/11728 [3:04:24<14:18:05, 6.76s/it] {'loss': 0.4864, 'learning_rate': 1.5071575978387505e-05, 'epoch': 0.35} + 35%|███▌ | 4114/11728 [3:04:24<14:18:05, 6.76s/it] 35%|███▌ | 4115/11728 [3:04:29<13:35:32, 6.43s/it] {'loss': 0.4899, 'learning_rate': 1.5069195693514672e-05, 'epoch': 0.35} + 35%|███▌ | 4115/11728 [3:04:29<13:35:32, 6.43s/it] 35%|███▌ | 4116/11728 [3:04:35<13:22:04, 6.32s/it] {'loss': 0.4747, 'learning_rate': 1.506681502204382e-05, 'epoch': 0.35} + 35%|███▌ | 4116/11728 [3:04:35<13:22:04, 6.32s/it] 35%|███▌ | 4117/11728 [3:04:44<15:02:31, 7.11s/it] {'loss': 0.4746, 'learning_rate': 1.5064433964156497e-05, 'epoch': 0.35} + 35%|███▌ | 4117/11728 [3:04:44<15:02:31, 7.11s/it] 35%|███▌ | 4118/11728 [3:04:50<14:20:18, 6.78s/it] {'loss': 0.4935, 'learning_rate': 1.5062052520034299e-05, 'epoch': 0.35} + 35%|███▌ | 4118/11728 [3:04:50<14:20:18, 6.78s/it] 35%|███▌ | 4119/11728 [3:05:02<17:25:30, 8.24s/it] {'loss': 0.508, 'learning_rate': 1.505967068985884e-05, 'epoch': 0.35} + 35%|███▌ | 4119/11728 [3:05:02<17:25:30, 8.24s/it] 35%|███▌ | 4120/11728 [3:05:08<15:53:20, 7.52s/it] {'loss': 0.4801, 'learning_rate': 1.5057288473811773e-05, 'epoch': 0.35} + 35%|███▌ | 4120/11728 [3:05:08<15:53:20, 7.52s/it] 35%|███▌ | 4121/11728 [3:05:14<14:51:45, 7.03s/it] {'loss': 0.4712, 'learning_rate': 1.5054905872074772e-05, 'epoch': 0.35} + 35%|███▌ | 4121/11728 [3:05:14<14:51:45, 7.03s/it] 35%|███▌ | 4122/11728 [3:05:20<14:12:35, 6.73s/it] {'loss': 0.4951, 'learning_rate': 1.5052522884829543e-05, 'epoch': 0.35} + 35%|███▌ | 4122/11728 [3:05:20<14:12:35, 6.73s/it] 35%|███▌ | 4123/11728 [3:05:25<13:31:21, 6.40s/it] {'loss': 0.4559, 'learning_rate': 1.505013951225783e-05, 'epoch': 0.35} + 35%|███▌ | 4123/11728 [3:05:25<13:31:21, 6.40s/it] 35%|███▌ | 4124/11728 [3:05:31<13:13:18, 6.26s/it] {'loss': 0.5025, 'learning_rate': 1.5047755754541392e-05, 'epoch': 0.35} + 35%|███▌ | 4124/11728 [3:05:31<13:13:18, 6.26s/it] 35%|███▌ | 4125/11728 [3:05:37<12:55:21, 6.12s/it] {'loss': 0.4884, 'learning_rate': 1.5045371611862026e-05, 'epoch': 0.35} + 35%|███▌ | 4125/11728 [3:05:37<12:55:21, 6.12s/it] 35%|███▌ | 4126/11728 [3:05:43<12:48:14, 6.06s/it] {'loss': 0.4792, 'learning_rate': 1.5042987084401559e-05, 'epoch': 0.35} + 35%|███▌ | 4126/11728 [3:05:43<12:48:14, 6.06s/it] 35%|███▌ | 4127/11728 [3:05:49<12:41:12, 6.01s/it] {'loss': 0.4933, 'learning_rate': 1.504060217234184e-05, 'epoch': 0.35} + 35%|███▌ | 4127/11728 [3:05:49<12:41:12, 6.01s/it] 35%|███▌ | 4128/11728 [3:05:54<12:27:26, 5.90s/it] {'loss': 0.4999, 'learning_rate': 1.5038216875864758e-05, 'epoch': 0.35} + 35%|███▌ | 4128/11728 [3:05:54<12:27:26, 5.90s/it] 35%|███▌ | 4129/11728 [3:06:00<12:14:36, 5.80s/it] {'loss': 0.481, 'learning_rate': 1.5035831195152221e-05, 'epoch': 0.35} + 35%|███▌ | 4129/11728 [3:06:00<12:14:36, 5.80s/it] 35%|███▌ | 4130/11728 [3:06:06<12:19:51, 5.84s/it] {'loss': 0.5122, 'learning_rate': 1.5033445130386176e-05, 'epoch': 0.35} + 35%|███▌ | 4130/11728 [3:06:06<12:19:51, 5.84s/it] 35%|███▌ | 4131/11728 [3:06:12<12:15:36, 5.81s/it] {'loss': 0.4855, 'learning_rate': 1.5031058681748587e-05, 'epoch': 0.35} + 35%|███▌ | 4131/11728 [3:06:12<12:15:36, 5.81s/it] 35%|███▌ | 4132/11728 [3:06:17<12:09:22, 5.76s/it] {'loss': 0.4933, 'learning_rate': 1.5028671849421463e-05, 'epoch': 0.35} + 35%|███▌ | 4132/11728 [3:06:17<12:09:22, 5.76s/it] 35%|███▌ | 4133/11728 [3:06:23<12:11:22, 5.78s/it] {'loss': 0.4882, 'learning_rate': 1.5026284633586828e-05, 'epoch': 0.35} + 35%|███▌ | 4133/11728 [3:06:23<12:11:22, 5.78s/it] 35%|███▌ | 4134/11728 [3:06:29<12:07:29, 5.75s/it] {'loss': 0.5095, 'learning_rate': 1.5023897034426741e-05, 'epoch': 0.35} + 35%|███▌ | 4134/11728 [3:06:29<12:07:29, 5.75s/it] 35%|███▌ | 4135/11728 [3:06:34<12:02:03, 5.71s/it] {'loss': 0.4832, 'learning_rate': 1.5021509052123295e-05, 'epoch': 0.35} + 35%|███▌ | 4135/11728 [3:06:34<12:02:03, 5.71s/it] 35%|███▌ | 4136/11728 [3:06:40<12:02:52, 5.71s/it] {'loss': 0.4846, 'learning_rate': 1.5019120686858603e-05, 'epoch': 0.35} + 35%|███▌ | 4136/11728 [3:06:40<12:02:52, 5.71s/it] 35%|███▌ | 4137/11728 [3:06:46<12:20:18, 5.85s/it] {'loss': 0.4845, 'learning_rate': 1.5016731938814815e-05, 'epoch': 0.35} + 35%|███▌ | 4137/11728 [3:06:46<12:20:18, 5.85s/it] 35%|███▌ | 4138/11728 [3:06:52<12:10:52, 5.78s/it] {'loss': 0.4873, 'learning_rate': 1.5014342808174102e-05, 'epoch': 0.35} + 35%|███▌ | 4138/11728 [3:06:52<12:10:52, 5.78s/it] 35%|███▌ | 4139/11728 [3:06:58<12:06:19, 5.74s/it] {'loss': 0.4757, 'learning_rate': 1.5011953295118677e-05, 'epoch': 0.35} + 35%|███▌ | 4139/11728 [3:06:58<12:06:19, 5.74s/it] 35%|███▌ | 4140/11728 [3:07:04<12:12:33, 5.79s/it] {'loss': 0.5001, 'learning_rate': 1.5009563399830764e-05, 'epoch': 0.35} + 35%|███▌ | 4140/11728 [3:07:04<12:12:33, 5.79s/it] 35%|███▌ | 4141/11728 [3:07:09<12:05:15, 5.74s/it] {'loss': 0.4925, 'learning_rate': 1.5007173122492635e-05, 'epoch': 0.35} + 35%|███▌ | 4141/11728 [3:07:09<12:05:15, 5.74s/it] 35%|███▌ | 4142/11728 [3:07:15<12:04:22, 5.73s/it] {'loss': 0.4902, 'learning_rate': 1.500478246328658e-05, 'epoch': 0.35} + 35%|███▌ | 4142/11728 [3:07:15<12:04:22, 5.73s/it] 35%|███▌ | 4143/11728 [3:07:20<12:00:58, 5.70s/it] {'loss': 0.4812, 'learning_rate': 1.5002391422394915e-05, 'epoch': 0.35} + 35%|███▌ | 4143/11728 [3:07:20<12:00:58, 5.70s/it] 35%|███▌ | 4144/11728 [3:07:26<11:59:10, 5.69s/it] {'loss': 0.4955, 'learning_rate': 1.5000000000000002e-05, 'epoch': 0.35} + 35%|███▌ | 4144/11728 [3:07:26<11:59:10, 5.69s/it] 35%|███▌ | 4145/11728 [3:07:32<11:58:28, 5.68s/it] {'loss': 0.4899, 'learning_rate': 1.4997608196284212e-05, 'epoch': 0.35} + 35%|███▌ | 4145/11728 [3:07:32<11:58:28, 5.68s/it] 35%|███▌ | 4146/11728 [3:07:38<12:00:51, 5.70s/it] {'loss': 0.4917, 'learning_rate': 1.4995216011429956e-05, 'epoch': 0.35} + 35%|███▌ | 4146/11728 [3:07:38<12:00:51, 5.70s/it] 35%|███▌ | 4147/11728 [3:07:43<11:58:24, 5.69s/it] {'loss': 0.4926, 'learning_rate': 1.4992823445619672e-05, 'epoch': 0.35} + 35%|███▌ | 4147/11728 [3:07:43<11:58:24, 5.69s/it] 35%|███▌ | 4148/11728 [3:07:49<12:02:55, 5.72s/it] {'loss': 0.4861, 'learning_rate': 1.499043049903583e-05, 'epoch': 0.35} + 35%|███▌ | 4148/11728 [3:07:49<12:02:55, 5.72s/it] 35%|███▌ | 4149/11728 [3:07:55<12:16:01, 5.83s/it] {'loss': 0.4845, 'learning_rate': 1.498803717186092e-05, 'epoch': 0.35} + 35%|███▌ | 4149/11728 [3:07:55<12:16:01, 5.83s/it]4 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +12 AutoResumeHook: Checking whether to suspend...AutoResumeHook: Checking whether to suspend... + +0 AutoResumeHook: Checking whether to suspend... + 35%|███▌ | 4150/11728 [3:08:01<12:21:41, 5.87s/it]3 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... + {'loss': 0.5006, 'learning_rate': 1.4985643464277475e-05, 'epoch': 0.35} + 35%|███▌ | 4150/11728 [3:08:01<12:21:41, 5.87s/it] 35%|███▌ | 4151/11728 [3:08:07<12:33:30, 5.97s/it] {'loss': 0.4962, 'learning_rate': 1.4983249376468045e-05, 'epoch': 0.35} + 35%|███▌ | 4151/11728 [3:08:07<12:33:30, 5.97s/it] 35%|███▌ | 4152/11728 [3:08:13<12:42:54, 6.04s/it] {'loss': 0.4761, 'learning_rate': 1.498085490861521e-05, 'epoch': 0.35} + 35%|███▌ | 4152/11728 [3:08:13<12:42:54, 6.04s/it] 35%|███▌ | 4153/11728 [3:08:19<12:31:24, 5.95s/it] {'loss': 0.4983, 'learning_rate': 1.4978460060901587e-05, 'epoch': 0.35} + 35%|███▌ | 4153/11728 [3:08:19<12:31:24, 5.95s/it] 35%|███▌ | 4154/11728 [3:08:25<12:28:45, 5.93s/it] {'loss': 0.513, 'learning_rate': 1.4976064833509816e-05, 'epoch': 0.35} + 35%|███▌ | 4154/11728 [3:08:25<12:28:45, 5.93s/it] 35%|███▌ | 4155/11728 [3:08:31<12:19:09, 5.86s/it] {'loss': 0.4689, 'learning_rate': 1.4973669226622564e-05, 'epoch': 0.35} + 35%|███▌ | 4155/11728 [3:08:31<12:19:09, 5.86s/it] 35%|███▌ | 4156/11728 [3:08:37<12:18:55, 5.86s/it] {'loss': 0.5088, 'learning_rate': 1.4971273240422534e-05, 'epoch': 0.35} + 35%|███▌ | 4156/11728 [3:08:37<12:18:55, 5.86s/it] 35%|███▌ | 4157/11728 [3:08:42<12:19:34, 5.86s/it] {'loss': 0.4796, 'learning_rate': 1.4968876875092453e-05, 'epoch': 0.35} + 35%|███▌ | 4157/11728 [3:08:42<12:19:34, 5.86s/it] 35%|███▌ | 4158/11728 [3:08:48<12:20:53, 5.87s/it] {'loss': 0.4866, 'learning_rate': 1.4966480130815076e-05, 'epoch': 0.35} + 35%|███▌ | 4158/11728 [3:08:48<12:20:53, 5.87s/it] 35%|███▌ | 4159/11728 [3:08:54<12:16:34, 5.84s/it] {'loss': 0.4754, 'learning_rate': 1.4964083007773189e-05, 'epoch': 0.35} + 35%|███▌ | 4159/11728 [3:08:54<12:16:34, 5.84s/it] 35%|███▌ | 4160/11728 [3:09:00<12:20:41, 5.87s/it] {'loss': 0.4874, 'learning_rate': 1.4961685506149608e-05, 'epoch': 0.35} + 35%|███▌ | 4160/11728 [3:09:00<12:20:41, 5.87s/it] 35%|███▌ | 4161/11728 [3:09:06<12:16:50, 5.84s/it] {'loss': 0.4878, 'learning_rate': 1.4959287626127175e-05, 'epoch': 0.35} + 35%|███▌ | 4161/11728 [3:09:06<12:16:50, 5.84s/it] 35%|███▌ | 4162/11728 [3:09:12<12:13:34, 5.82s/it] {'loss': 0.4681, 'learning_rate': 1.4956889367888765e-05, 'epoch': 0.35} + 35%|███▌ | 4162/11728 [3:09:12<12:13:34, 5.82s/it] 35%|███▌ | 4163/11728 [3:09:17<12:10:45, 5.80s/it] {'loss': 0.5002, 'learning_rate': 1.4954490731617278e-05, 'epoch': 0.35} + 35%|███▌ | 4163/11728 [3:09:17<12:10:45, 5.80s/it] 36%|███▌ | 4164/11728 [3:09:23<12:07:39, 5.77s/it] {'loss': 0.4852, 'learning_rate': 1.495209171749564e-05, 'epoch': 0.36} + 36%|███▌ | 4164/11728 [3:09:23<12:07:39, 5.77s/it] 36%|███▌ | 4165/11728 [3:09:29<11:59:06, 5.70s/it] {'loss': 0.4698, 'learning_rate': 1.4949692325706818e-05, 'epoch': 0.36} + 36%|███▌ | 4165/11728 [3:09:29<11:59:06, 5.70s/it] 36%|███▌ | 4166/11728 [3:09:34<12:04:30, 5.75s/it] {'loss': 0.4824, 'learning_rate': 1.494729255643379e-05, 'epoch': 0.36} + 36%|███▌ | 4166/11728 [3:09:34<12:04:30, 5.75s/it] 36%|███▌ | 4167/11728 [3:09:40<12:05:27, 5.76s/it] {'loss': 0.4883, 'learning_rate': 1.4944892409859581e-05, 'epoch': 0.36} + 36%|███▌ | 4167/11728 [3:09:40<12:05:27, 5.76s/it] 36%|███▌ | 4168/11728 [3:09:46<12:04:55, 5.75s/it] {'loss': 0.4721, 'learning_rate': 1.494249188616723e-05, 'epoch': 0.36} + 36%|███▌ | 4168/11728 [3:09:46<12:04:55, 5.75s/it] 36%|███▌ | 4169/11728 [3:09:52<12:10:17, 5.80s/it] {'loss': 0.4776, 'learning_rate': 1.4940090985539818e-05, 'epoch': 0.36} + 36%|███▌ | 4169/11728 [3:09:52<12:10:17, 5.80s/it] 36%|███▌ | 4170/11728 [3:09:58<12:19:37, 5.87s/it] {'loss': 0.502, 'learning_rate': 1.4937689708160434e-05, 'epoch': 0.36} + 36%|███▌ | 4170/11728 [3:09:58<12:19:37, 5.87s/it] 36%|███▌ | 4171/11728 [3:10:04<12:11:41, 5.81s/it] {'loss': 0.4907, 'learning_rate': 1.4935288054212228e-05, 'epoch': 0.36} + 36%|███▌ | 4171/11728 [3:10:04<12:11:41, 5.81s/it] 36%|███▌ | 4172/11728 [3:10:10<12:25:01, 5.92s/it] {'loss': 0.4949, 'learning_rate': 1.4932886023878346e-05, 'epoch': 0.36} + 36%|███▌ | 4172/11728 [3:10:10<12:25:01, 5.92s/it] 36%|███▌ | 4173/11728 [3:10:15<12:14:14, 5.83s/it] {'loss': 0.4996, 'learning_rate': 1.4930483617341982e-05, 'epoch': 0.36} + 36%|███▌ | 4173/11728 [3:10:15<12:14:14, 5.83s/it] 36%|███▌ | 4174/11728 [3:10:21<12:15:47, 5.84s/it] {'loss': 0.4723, 'learning_rate': 1.4928080834786356e-05, 'epoch': 0.36} + 36%|███▌ | 4174/11728 [3:10:21<12:15:47, 5.84s/it] 36%|███▌ | 4175/11728 [3:10:27<12:17:41, 5.86s/it] {'loss': 0.4853, 'learning_rate': 1.492567767639471e-05, 'epoch': 0.36} + 36%|███▌ | 4175/11728 [3:10:27<12:17:41, 5.86s/it] 36%|███▌ | 4176/11728 [3:10:33<12:27:43, 5.94s/it] {'loss': 0.491, 'learning_rate': 1.492327414235032e-05, 'epoch': 0.36} + 36%|███▌ | 4176/11728 [3:10:33<12:27:43, 5.94s/it] 36%|███▌ | 4177/11728 [3:10:39<12:18:23, 5.87s/it] {'loss': 0.5252, 'learning_rate': 1.4920870232836487e-05, 'epoch': 0.36} + 36%|███▌ | 4177/11728 [3:10:39<12:18:23, 5.87s/it] 36%|███▌ | 4178/11728 [3:10:45<12:29:08, 5.95s/it] {'loss': 0.4961, 'learning_rate': 1.491846594803655e-05, 'epoch': 0.36} + 36%|███▌ | 4178/11728 [3:10:45<12:29:08, 5.95s/it] 36%|███▌ | 4179/11728 [3:10:51<12:21:00, 5.89s/it] {'loss': 0.5273, 'learning_rate': 1.4916061288133862e-05, 'epoch': 0.36} + 36%|███▌ | 4179/11728 [3:10:51<12:21:00, 5.89s/it] 36%|███▌ | 4180/11728 [3:10:57<12:20:29, 5.89s/it] {'loss': 0.4707, 'learning_rate': 1.491365625331182e-05, 'epoch': 0.36} + 36%|███▌ | 4180/11728 [3:10:57<12:20:29, 5.89s/it] 36%|███▌ | 4181/11728 [3:11:03<12:17:51, 5.87s/it] {'loss': 0.4858, 'learning_rate': 1.4911250843753838e-05, 'epoch': 0.36} + 36%|███▌ | 4181/11728 [3:11:03<12:17:51, 5.87s/it] 36%|███▌ | 4182/11728 [3:11:09<12:22:52, 5.91s/it] {'loss': 0.482, 'learning_rate': 1.490884505964336e-05, 'epoch': 0.36} + 36%|███▌ | 4182/11728 [3:11:09<12:22:52, 5.91s/it] 36%|███▌ | 4183/11728 [3:11:14<12:19:09, 5.88s/it] {'loss': 0.4765, 'learning_rate': 1.490643890116387e-05, 'epoch': 0.36} + 36%|███▌ | 4183/11728 [3:11:14<12:19:09, 5.88s/it] 36%|███▌ | 4184/11728 [3:11:20<12:17:30, 5.87s/it] {'loss': 0.4932, 'learning_rate': 1.4904032368498857e-05, 'epoch': 0.36} + 36%|███▌ | 4184/11728 [3:11:20<12:17:30, 5.87s/it] 36%|███▌ | 4185/11728 [3:11:26<12:11:38, 5.82s/it] {'loss': 0.4823, 'learning_rate': 1.4901625461831868e-05, 'epoch': 0.36} + 36%|███▌ | 4185/11728 [3:11:26<12:11:38, 5.82s/it] 36%|███▌ | 4186/11728 [3:11:32<12:17:50, 5.87s/it] {'loss': 0.5056, 'learning_rate': 1.4899218181346453e-05, 'epoch': 0.36} + 36%|███▌ | 4186/11728 [3:11:32<12:17:50, 5.87s/it] 36%|███▌ | 4187/11728 [3:11:38<12:10:36, 5.81s/it] {'loss': 0.4649, 'learning_rate': 1.489681052722621e-05, 'epoch': 0.36} + 36%|███▌ | 4187/11728 [3:11:38<12:10:36, 5.81s/it] 36%|███▌ | 4188/11728 [3:11:44<12:13:24, 5.84s/it] {'loss': 0.4853, 'learning_rate': 1.489440249965475e-05, 'epoch': 0.36} + 36%|███▌ | 4188/11728 [3:11:44<12:13:24, 5.84s/it] 36%|███▌ | 4189/11728 [3:11:49<12:13:46, 5.84s/it] {'loss': 0.5137, 'learning_rate': 1.4891994098815725e-05, 'epoch': 0.36} + 36%|███▌ | 4189/11728 [3:11:49<12:13:46, 5.84s/it] 36%|███▌ | 4190/11728 [3:11:55<12:20:29, 5.89s/it] {'loss': 0.4911, 'learning_rate': 1.4889585324892803e-05, 'epoch': 0.36} + 36%|███▌ | 4190/11728 [3:11:55<12:20:29, 5.89s/it] 36%|███▌ | 4191/11728 [3:12:01<12:20:39, 5.90s/it] {'loss': 0.4914, 'learning_rate': 1.4887176178069693e-05, 'epoch': 0.36} + 36%|███▌ | 4191/11728 [3:12:01<12:20:39, 5.90s/it] 36%|███▌ | 4192/11728 [3:12:07<12:16:04, 5.86s/it] {'loss': 0.4816, 'learning_rate': 1.4884766658530126e-05, 'epoch': 0.36} + 36%|███▌ | 4192/11728 [3:12:07<12:16:04, 5.86s/it] 36%|███▌ | 4193/11728 [3:12:13<12:22:30, 5.91s/it] {'loss': 0.5093, 'learning_rate': 1.4882356766457857e-05, 'epoch': 0.36} + 36%|███▌ | 4193/11728 [3:12:13<12:22:30, 5.91s/it] 36%|███▌ | 4194/11728 [3:12:19<12:19:21, 5.89s/it] {'loss': 0.4758, 'learning_rate': 1.4879946502036677e-05, 'epoch': 0.36} + 36%|███▌ | 4194/11728 [3:12:19<12:19:21, 5.89s/it] 36%|███▌ | 4195/11728 [3:12:25<12:10:49, 5.82s/it] {'loss': 0.4775, 'learning_rate': 1.4877535865450405e-05, 'epoch': 0.36} + 36%|███▌ | 4195/11728 [3:12:25<12:10:49, 5.82s/it] 36%|███▌ | 4196/11728 [3:12:30<12:02:50, 5.76s/it] {'loss': 0.4707, 'learning_rate': 1.4875124856882885e-05, 'epoch': 0.36} + 36%|███▌ | 4196/11728 [3:12:30<12:02:50, 5.76s/it] 36%|███▌ | 4197/11728 [3:12:36<11:51:27, 5.67s/it] {'loss': 0.4757, 'learning_rate': 1.4872713476517993e-05, 'epoch': 0.36} + 36%|███▌ | 4197/11728 [3:12:36<11:51:27, 5.67s/it] 36%|███▌ | 4198/11728 [3:12:42<11:59:01, 5.73s/it] {'loss': 0.4965, 'learning_rate': 1.4870301724539627e-05, 'epoch': 0.36} + 36%|███▌ | 4198/11728 [3:12:42<11:59:01, 5.73s/it] 36%|███▌ | 4199/11728 [3:12:47<12:00:37, 5.74s/it] {'loss': 0.4694, 'learning_rate': 1.4867889601131716e-05, 'epoch': 0.36} + 36%|███▌ | 4199/11728 [3:12:47<12:00:37, 5.74s/it]05 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... + 36%|███▌ | 4200/11728 [3:12:54<12:17:40, 5.88s/it]6 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4905, 'learning_rate': 1.486547710647822e-05, 'epoch': 0.36} + 36%|███▌ | 4200/11728 [3:12:54<12:17:40, 5.88s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-4200/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-4200/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-4200/mm_projector +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/torch/nn/modules/module.py:1802: UserWarning: Positional args are being deprecated, use kwargs instead. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details. + warnings.warn( + 36%|███▌ | 4201/11728 [3:13:24<27:45:06, 13.27s/it] {'loss': 0.4755, 'learning_rate': 1.4863064240763132e-05, 'epoch': 0.36} + 36%|███▌ | 4201/11728 [3:13:24<27:45:06, 13.27s/it] 36%|███▌ | 4202/11728 [3:13:30<23:10:12, 11.08s/it] {'loss': 0.4777, 'learning_rate': 1.486065100417046e-05, 'epoch': 0.36} + 36%|███▌ | 4202/11728 [3:13:30<23:10:12, 11.08s/it] 36%|███▌ | 4203/11728 [3:13:36<19:52:41, 9.51s/it] {'loss': 0.4904, 'learning_rate': 1.4858237396884249e-05, 'epoch': 0.36} + 36%|███▌ | 4203/11728 [3:13:36<19:52:41, 9.51s/it] 36%|███▌ | 4204/11728 [3:13:42<17:45:01, 8.49s/it] {'loss': 0.4618, 'learning_rate': 1.4855823419088576e-05, 'epoch': 0.36} + 36%|███▌ | 4204/11728 [3:13:42<17:45:01, 8.49s/it] 36%|███▌ | 4205/11728 [3:13:48<16:02:36, 7.68s/it] {'loss': 0.4889, 'learning_rate': 1.4853409070967528e-05, 'epoch': 0.36} + 36%|███▌ | 4205/11728 [3:13:48<16:02:36, 7.68s/it] 36%|███▌ | 4206/11728 [3:13:54<14:50:25, 7.10s/it] {'loss': 0.5078, 'learning_rate': 1.485099435270525e-05, 'epoch': 0.36} + 36%|███▌ | 4206/11728 [3:13:54<14:50:25, 7.10s/it] 36%|███▌ | 4207/11728 [3:14:00<14:10:14, 6.78s/it] {'loss': 0.5029, 'learning_rate': 1.4848579264485887e-05, 'epoch': 0.36} + 36%|███▌ | 4207/11728 [3:14:00<14:10:14, 6.78s/it] 36%|███▌ | 4208/11728 [3:14:05<13:29:06, 6.46s/it] {'loss': 0.4675, 'learning_rate': 1.4846163806493628e-05, 'epoch': 0.36} + 36%|███▌ | 4208/11728 [3:14:05<13:29:06, 6.46s/it] 36%|███▌ | 4209/11728 [3:14:11<13:04:41, 6.26s/it] {'loss': 0.5082, 'learning_rate': 1.4843747978912682e-05, 'epoch': 0.36} + 36%|███▌ | 4209/11728 [3:14:11<13:04:41, 6.26s/it] 36%|███▌ | 4210/11728 [3:14:17<12:43:46, 6.10s/it] {'loss': 0.4802, 'learning_rate': 1.4841331781927297e-05, 'epoch': 0.36} + 36%|███▌ | 4210/11728 [3:14:17<12:43:46, 6.10s/it] 36%|███▌ | 4211/11728 [3:14:23<12:42:34, 6.09s/it] {'loss': 0.5168, 'learning_rate': 1.4838915215721735e-05, 'epoch': 0.36} + 36%|███▌ | 4211/11728 [3:14:23<12:42:34, 6.09s/it] 36%|███▌ | 4212/11728 [3:14:29<12:49:38, 6.14s/it] {'loss': 0.5006, 'learning_rate': 1.48364982804803e-05, 'epoch': 0.36} + 36%|███▌ | 4212/11728 [3:14:29<12:49:38, 6.14s/it] 36%|███▌ | 4213/11728 [3:14:35<12:29:17, 5.98s/it] {'loss': 0.4968, 'learning_rate': 1.4834080976387316e-05, 'epoch': 0.36} + 36%|███▌ | 4213/11728 [3:14:35<12:29:17, 5.98s/it] 36%|███▌ | 4214/11728 [3:14:40<12:20:28, 5.91s/it] {'loss': 0.484, 'learning_rate': 1.4831663303627128e-05, 'epoch': 0.36} + 36%|███▌ | 4214/11728 [3:14:40<12:20:28, 5.91s/it] 36%|███▌ | 4215/11728 [3:14:46<12:19:08, 5.90s/it] {'loss': 0.4848, 'learning_rate': 1.482924526238413e-05, 'epoch': 0.36} + 36%|███▌ | 4215/11728 [3:14:46<12:19:08, 5.90s/it] 36%|███▌ | 4216/11728 [3:14:52<12:20:12, 5.91s/it] {'loss': 0.5118, 'learning_rate': 1.4826826852842725e-05, 'epoch': 0.36} + 36%|███▌ | 4216/11728 [3:14:52<12:20:12, 5.91s/it] 36%|███▌ | 4217/11728 [3:14:58<12:15:35, 5.88s/it] {'loss': 0.4698, 'learning_rate': 1.4824408075187352e-05, 'epoch': 0.36} + 36%|███▌ | 4217/11728 [3:14:58<12:15:35, 5.88s/it] 36%|███▌ | 4218/11728 [3:15:04<12:06:41, 5.81s/it] {'loss': 0.4723, 'learning_rate': 1.482198892960248e-05, 'epoch': 0.36} + 36%|███▌ | 4218/11728 [3:15:04<12:06:41, 5.81s/it] 36%|███▌ | 4219/11728 [3:15:09<12:05:58, 5.80s/it] {'loss': 0.4894, 'learning_rate': 1.4819569416272604e-05, 'epoch': 0.36} + 36%|███▌ | 4219/11728 [3:15:10<12:05:58, 5.80s/it] 36%|███▌ | 4220/11728 [3:15:15<12:01:18, 5.76s/it] {'loss': 0.4799, 'learning_rate': 1.4817149535382238e-05, 'epoch': 0.36} + 36%|███▌ | 4220/11728 [3:15:15<12:01:18, 5.76s/it] 36%|███▌ | 4221/11728 [3:15:21<12:13:00, 5.86s/it] {'loss': 0.4946, 'learning_rate': 1.481472928711594e-05, 'epoch': 0.36} + 36%|███▌ | 4221/11728 [3:15:21<12:13:00, 5.86s/it] 36%|███▌ | 4222/11728 [3:15:27<12:13:56, 5.87s/it] {'loss': 0.5066, 'learning_rate': 1.4812308671658285e-05, 'epoch': 0.36} + 36%|███▌ | 4222/11728 [3:15:27<12:13:56, 5.87s/it] 36%|███▌ | 4223/11728 [3:15:33<12:19:14, 5.91s/it] {'loss': 0.5022, 'learning_rate': 1.4809887689193878e-05, 'epoch': 0.36} + 36%|███▌ | 4223/11728 [3:15:33<12:19:14, 5.91s/it] 36%|███▌ | 4224/11728 [3:15:39<12:13:43, 5.87s/it] {'loss': 0.4772, 'learning_rate': 1.4807466339907358e-05, 'epoch': 0.36} + 36%|███▌ | 4224/11728 [3:15:39<12:13:43, 5.87s/it] 36%|███▌ | 4225/11728 [3:15:45<12:19:02, 5.91s/it] {'loss': 0.4973, 'learning_rate': 1.4805044623983382e-05, 'epoch': 0.36} + 36%|███▌ | 4225/11728 [3:15:45<12:19:02, 5.91s/it] 36%|███▌ | 4226/11728 [3:15:51<12:09:32, 5.83s/it] {'loss': 0.4783, 'learning_rate': 1.4802622541606644e-05, 'epoch': 0.36} + 36%|███▌ | 4226/11728 [3:15:51<12:09:32, 5.83s/it] 36%|███▌ | 4227/11728 [3:15:56<12:01:19, 5.77s/it] {'loss': 0.462, 'learning_rate': 1.4800200092961859e-05, 'epoch': 0.36} + 36%|███▌ | 4227/11728 [3:15:56<12:01:19, 5.77s/it] 36%|███▌ | 4228/11728 [3:16:02<12:01:55, 5.78s/it] {'loss': 0.4666, 'learning_rate': 1.4797777278233779e-05, 'epoch': 0.36} + 36%|███▌ | 4228/11728 [3:16:02<12:01:55, 5.78s/it] 36%|███▌ | 4229/11728 [3:16:07<11:50:45, 5.69s/it] {'loss': 0.4928, 'learning_rate': 1.4795354097607169e-05, 'epoch': 0.36} + 36%|███▌ | 4229/11728 [3:16:07<11:50:45, 5.69s/it] 36%|███▌ | 4230/11728 [3:16:14<12:19:12, 5.92s/it] {'loss': 0.4896, 'learning_rate': 1.4792930551266836e-05, 'epoch': 0.36} + 36%|███▌ | 4230/11728 [3:16:14<12:19:12, 5.92s/it] 36%|███▌ | 4231/11728 [3:16:20<12:35:12, 6.04s/it] {'loss': 0.4793, 'learning_rate': 1.4790506639397613e-05, 'epoch': 0.36} + 36%|███▌ | 4231/11728 [3:16:20<12:35:12, 6.04s/it] 36%|███▌ | 4232/11728 [3:16:26<12:31:42, 6.02s/it] {'loss': 0.5037, 'learning_rate': 1.4788082362184348e-05, 'epoch': 0.36} + 36%|███▌ | 4232/11728 [3:16:26<12:31:42, 6.02s/it] 36%|███▌ | 4233/11728 [3:16:32<12:28:26, 5.99s/it] {'loss': 0.4662, 'learning_rate': 1.4785657719811938e-05, 'epoch': 0.36} + 36%|███▌ | 4233/11728 [3:16:32<12:28:26, 5.99s/it] 36%|███▌ | 4234/11728 [3:16:38<12:14:08, 5.88s/it] {'loss': 0.4948, 'learning_rate': 1.4783232712465287e-05, 'epoch': 0.36} + 36%|███▌ | 4234/11728 [3:16:38<12:14:08, 5.88s/it] 36%|███▌ | 4235/11728 [3:16:44<12:12:39, 5.87s/it] {'loss': 0.4933, 'learning_rate': 1.4780807340329342e-05, 'epoch': 0.36} + 36%|███▌ | 4235/11728 [3:16:44<12:12:39, 5.87s/it] 36%|███▌ | 4236/11728 [3:16:49<12:07:24, 5.83s/it] {'loss': 0.4839, 'learning_rate': 1.477838160358907e-05, 'epoch': 0.36} + 36%|███▌ | 4236/11728 [3:16:49<12:07:24, 5.83s/it] 36%|███▌ | 4237/11728 [3:16:55<12:03:47, 5.80s/it] {'loss': 0.501, 'learning_rate': 1.4775955502429467e-05, 'epoch': 0.36} + 36%|███▌ | 4237/11728 [3:16:55<12:03:47, 5.80s/it] 36%|███▌ | 4238/11728 [3:17:01<11:54:13, 5.72s/it] {'loss': 0.4713, 'learning_rate': 1.477352903703556e-05, 'epoch': 0.36} + 36%|███▌ | 4238/11728 [3:17:01<11:54:13, 5.72s/it] 36%|███▌ | 4239/11728 [3:17:06<11:56:49, 5.74s/it] {'loss': 0.504, 'learning_rate': 1.4771102207592395e-05, 'epoch': 0.36} + 36%|███▌ | 4239/11728 [3:17:06<11:56:49, 5.74s/it] 36%|███▌ | 4240/11728 [3:17:12<11:54:32, 5.73s/it] {'loss': 0.4804, 'learning_rate': 1.4768675014285063e-05, 'epoch': 0.36} + 36%|███▌ | 4240/11728 [3:17:12<11:54:32, 5.73s/it] 36%|███▌ | 4241/11728 [3:17:18<11:58:45, 5.76s/it] {'loss': 0.516, 'learning_rate': 1.4766247457298661e-05, 'epoch': 0.36} + 36%|███▌ | 4241/11728 [3:17:18<11:58:45, 5.76s/it] 36%|███▌ | 4242/11728 [3:17:24<11:57:33, 5.75s/it] {'loss': 0.4655, 'learning_rate': 1.4763819536818331e-05, 'epoch': 0.36} + 36%|███▌ | 4242/11728 [3:17:24<11:57:33, 5.75s/it] 36%|███▌ | 4243/11728 [3:17:30<12:05:20, 5.81s/it] {'loss': 0.4868, 'learning_rate': 1.4761391253029236e-05, 'epoch': 0.36} + 36%|███▌ | 4243/11728 [3:17:30<12:05:20, 5.81s/it] 36%|███▌ | 4244/11728 [3:17:35<12:04:44, 5.81s/it] {'loss': 0.4729, 'learning_rate': 1.4758962606116565e-05, 'epoch': 0.36} + 36%|███▌ | 4244/11728 [3:17:35<12:04:44, 5.81s/it] 36%|███▌ | 4245/11728 [3:17:41<11:57:45, 5.76s/it] {'loss': 0.472, 'learning_rate': 1.4756533596265538e-05, 'epoch': 0.36} + 36%|███▌ | 4245/11728 [3:17:41<11:57:45, 5.76s/it] 36%|███▌ | 4246/11728 [3:17:47<11:53:24, 5.72s/it] {'loss': 0.4785, 'learning_rate': 1.47541042236614e-05, 'epoch': 0.36} + 36%|███▌ | 4246/11728 [3:17:47<11:53:24, 5.72s/it] 36%|███▌ | 4247/11728 [3:17:52<11:49:42, 5.69s/it] {'loss': 0.4747, 'learning_rate': 1.4751674488489427e-05, 'epoch': 0.36} + 36%|███▌ | 4247/11728 [3:17:52<11:49:42, 5.69s/it] 36%|███▌ | 4248/11728 [3:17:58<11:51:34, 5.71s/it] {'loss': 0.4826, 'learning_rate': 1.474924439093492e-05, 'epoch': 0.36} + 36%|███▌ | 4248/11728 [3:17:58<11:51:34, 5.71s/it] 36%|███▌ | 4249/11728 [3:18:04<11:52:40, 5.72s/it] {'loss': 0.4778, 'learning_rate': 1.4746813931183209e-05, 'epoch': 0.36} + 36%|███▌ | 4249/11728 [3:18:04<11:52:40, 5.72s/it]4 AutoResumeHook: Checking whether to suspend... +05 AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... + 36%|███▌ | 4250/11728 [3:18:10<12:05:33, 5.82s/it]6 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... + {'loss': 0.5044, 'learning_rate': 1.4744383109419646e-05, 'epoch': 0.36} + 36%|███▌ | 4250/11728 [3:18:10<12:05:33, 5.82s/it] 36%|███▌ | 4251/11728 [3:18:16<12:23:01, 5.96s/it] {'loss': 0.4916, 'learning_rate': 1.4741951925829625e-05, 'epoch': 0.36} + 36%|███▌ | 4251/11728 [3:18:16<12:23:01, 5.96s/it] 36%|███▋ | 4252/11728 [3:18:22<12:18:06, 5.92s/it] {'loss': 0.498, 'learning_rate': 1.473952038059855e-05, 'epoch': 0.36} + 36%|███▋ | 4252/11728 [3:18:22<12:18:06, 5.92s/it] 36%|███▋ | 4253/11728 [3:18:28<12:07:04, 5.84s/it] {'loss': 0.4942, 'learning_rate': 1.4737088473911865e-05, 'epoch': 0.36} + 36%|███▋ | 4253/11728 [3:18:28<12:07:04, 5.84s/it] 36%|███▋ | 4254/11728 [3:18:33<12:00:16, 5.78s/it] {'loss': 0.4792, 'learning_rate': 1.4734656205955037e-05, 'epoch': 0.36} + 36%|███▋ | 4254/11728 [3:18:33<12:00:16, 5.78s/it] 36%|███▋ | 4255/11728 [3:18:39<11:51:36, 5.71s/it] {'loss': 0.465, 'learning_rate': 1.473222357691356e-05, 'epoch': 0.36} + 36%|███▋ | 4255/11728 [3:18:39<11:51:36, 5.71s/it] 36%|███▋ | 4256/11728 [3:18:45<11:55:22, 5.74s/it] {'loss': 0.4865, 'learning_rate': 1.4729790586972957e-05, 'epoch': 0.36} + 36%|███▋ | 4256/11728 [3:18:45<11:55:22, 5.74s/it] 36%|███▋ | 4257/11728 [3:18:50<11:49:53, 5.70s/it] {'loss': 0.4745, 'learning_rate': 1.4727357236318773e-05, 'epoch': 0.36} + 36%|███▋ | 4257/11728 [3:18:50<11:49:53, 5.70s/it] 36%|███▋ | 4258/11728 [3:18:56<11:58:36, 5.77s/it] {'loss': 0.4913, 'learning_rate': 1.4724923525136597e-05, 'epoch': 0.36} + 36%|███▋ | 4258/11728 [3:18:56<11:58:36, 5.77s/it] 36%|███▋ | 4259/11728 [3:19:02<12:10:36, 5.87s/it] {'loss': 0.4653, 'learning_rate': 1.4722489453612023e-05, 'epoch': 0.36} + 36%|███▋ | 4259/11728 [3:19:02<12:10:36, 5.87s/it] 36%|███▋ | 4260/11728 [3:19:09<12:25:04, 5.99s/it] {'loss': 0.4964, 'learning_rate': 1.4720055021930686e-05, 'epoch': 0.36} + 36%|███▋ | 4260/11728 [3:19:09<12:25:04, 5.99s/it] 36%|███▋ | 4261/11728 [3:19:15<12:24:03, 5.98s/it] {'loss': 0.4765, 'learning_rate': 1.4717620230278249e-05, 'epoch': 0.36} + 36%|███▋ | 4261/11728 [3:19:15<12:24:03, 5.98s/it] 36%|███▋ | 4262/11728 [3:19:21<12:28:31, 6.02s/it] {'loss': 0.514, 'learning_rate': 1.4715185078840399e-05, 'epoch': 0.36} + 36%|███▋ | 4262/11728 [3:19:21<12:28:31, 6.02s/it] 36%|███▋ | 4263/11728 [3:19:26<12:17:36, 5.93s/it] {'loss': 0.4778, 'learning_rate': 1.4712749567802849e-05, 'epoch': 0.36} + 36%|███▋ | 4263/11728 [3:19:26<12:17:36, 5.93s/it] 36%|███▋ | 4264/11728 [3:19:32<12:03:01, 5.81s/it] {'loss': 0.4844, 'learning_rate': 1.4710313697351342e-05, 'epoch': 0.36} + 36%|███▋ | 4264/11728 [3:19:32<12:03:01, 5.81s/it] 36%|███▋ | 4265/11728 [3:19:38<12:11:31, 5.88s/it] {'loss': 0.503, 'learning_rate': 1.4707877467671648e-05, 'epoch': 0.36} + 36%|███▋ | 4265/11728 [3:19:38<12:11:31, 5.88s/it] 36%|███▋ | 4266/11728 [3:19:44<12:09:28, 5.87s/it] {'loss': 0.5028, 'learning_rate': 1.470544087894956e-05, 'epoch': 0.36} + 36%|███▋ | 4266/11728 [3:19:44<12:09:28, 5.87s/it] 36%|███▋ | 4267/11728 [3:19:50<12:18:44, 5.94s/it] {'loss': 0.5071, 'learning_rate': 1.470300393137091e-05, 'epoch': 0.36} + 36%|███▋ | 4267/11728 [3:19:50<12:18:44, 5.94s/it] 36%|███▋ | 4268/11728 [3:19:56<12:21:45, 5.97s/it] {'loss': 0.4909, 'learning_rate': 1.4700566625121543e-05, 'epoch': 0.36} + 36%|███▋ | 4268/11728 [3:19:56<12:21:45, 5.97s/it] 36%|███▋ | 4269/11728 [3:20:02<12:21:57, 5.97s/it] {'loss': 0.481, 'learning_rate': 1.469812896038734e-05, 'epoch': 0.36} + 36%|███▋ | 4269/11728 [3:20:02<12:21:57, 5.97s/it] 36%|███▋ | 4270/11728 [3:20:08<12:25:50, 6.00s/it] {'loss': 0.5, 'learning_rate': 1.4695690937354212e-05, 'epoch': 0.36} + 36%|███▋ | 4270/11728 [3:20:08<12:25:50, 6.00s/it] 36%|███▋ | 4271/11728 [3:20:14<12:23:33, 5.98s/it] {'loss': 0.5149, 'learning_rate': 1.4693252556208089e-05, 'epoch': 0.36} + 36%|███▋ | 4271/11728 [3:20:14<12:23:33, 5.98s/it] 36%|███▋ | 4272/11728 [3:20:20<12:20:22, 5.96s/it] {'loss': 0.4844, 'learning_rate': 1.469081381713493e-05, 'epoch': 0.36} + 36%|███▋ | 4272/11728 [3:20:20<12:20:22, 5.96s/it] 36%|███▋ | 4273/11728 [3:20:25<12:10:54, 5.88s/it] {'loss': 0.4787, 'learning_rate': 1.4688374720320729e-05, 'epoch': 0.36} + 36%|███▋ | 4273/11728 [3:20:25<12:10:54, 5.88s/it] 36%|███▋ | 4274/11728 [3:20:31<12:02:41, 5.82s/it] {'loss': 0.4711, 'learning_rate': 1.4685935265951495e-05, 'epoch': 0.36} + 36%|███▋ | 4274/11728 [3:20:31<12:02:41, 5.82s/it] 36%|███▋ | 4275/11728 [3:20:37<12:02:40, 5.82s/it] {'loss': 0.4897, 'learning_rate': 1.4683495454213277e-05, 'epoch': 0.36} + 36%|███▋ | 4275/11728 [3:20:37<12:02:40, 5.82s/it] 36%|███▋ | 4276/11728 [3:20:43<12:08:29, 5.87s/it] {'loss': 0.5089, 'learning_rate': 1.4681055285292138e-05, 'epoch': 0.36} + 36%|███▋ | 4276/11728 [3:20:43<12:08:29, 5.87s/it] 36%|███▋ | 4277/11728 [3:20:49<12:05:24, 5.84s/it] {'loss': 0.4781, 'learning_rate': 1.4678614759374186e-05, 'epoch': 0.36} + 36%|███▋ | 4277/11728 [3:20:49<12:05:24, 5.84s/it] 36%|███▋ | 4278/11728 [3:20:55<12:03:46, 5.83s/it] {'loss': 0.5099, 'learning_rate': 1.4676173876645537e-05, 'epoch': 0.36} + 36%|███▋ | 4278/11728 [3:20:55<12:03:46, 5.83s/it] 36%|███▋ | 4279/11728 [3:21:00<12:00:24, 5.80s/it] {'loss': 0.4755, 'learning_rate': 1.4673732637292344e-05, 'epoch': 0.36} + 36%|███▋ | 4279/11728 [3:21:00<12:00:24, 5.80s/it] 36%|███▋ | 4280/11728 [3:21:06<12:07:57, 5.86s/it] {'loss': 0.4824, 'learning_rate': 1.4671291041500791e-05, 'epoch': 0.36} + 36%|███▋ | 4280/11728 [3:21:06<12:07:57, 5.86s/it] 37%|███▋ | 4281/11728 [3:21:12<12:05:31, 5.85s/it] {'loss': 0.4791, 'learning_rate': 1.466884908945708e-05, 'epoch': 0.37} + 37%|███▋ | 4281/11728 [3:21:12<12:05:31, 5.85s/it] 37%|███▋ | 4282/11728 [3:21:18<12:08:44, 5.87s/it] {'loss': 0.4878, 'learning_rate': 1.4666406781347443e-05, 'epoch': 0.37} + 37%|███▋ | 4282/11728 [3:21:18<12:08:44, 5.87s/it] 37%|███▋ | 4283/11728 [3:21:24<12:10:08, 5.88s/it] {'loss': 0.5064, 'learning_rate': 1.4663964117358147e-05, 'epoch': 0.37} + 37%|███▋ | 4283/11728 [3:21:24<12:10:08, 5.88s/it] 37%|███▋ | 4284/11728 [3:21:30<12:05:14, 5.85s/it] {'loss': 0.4797, 'learning_rate': 1.4661521097675478e-05, 'epoch': 0.37} + 37%|███▋ | 4284/11728 [3:21:30<12:05:14, 5.85s/it] 37%|███▋ | 4285/11728 [3:21:35<11:57:16, 5.78s/it] {'loss': 0.4636, 'learning_rate': 1.4659077722485741e-05, 'epoch': 0.37} + 37%|███▋ | 4285/11728 [3:21:35<11:57:16, 5.78s/it] 37%|███▋ | 4286/11728 [3:21:41<11:54:20, 5.76s/it] {'loss': 0.4779, 'learning_rate': 1.4656633991975294e-05, 'epoch': 0.37} + 37%|███▋ | 4286/11728 [3:21:41<11:54:20, 5.76s/it] 37%|███▋ | 4287/11728 [3:21:47<11:48:13, 5.71s/it] {'loss': 0.5072, 'learning_rate': 1.4654189906330491e-05, 'epoch': 0.37} + 37%|███▋ | 4287/11728 [3:21:47<11:48:13, 5.71s/it] 37%|███▋ | 4288/11728 [3:21:53<11:59:49, 5.81s/it] {'loss': 0.4794, 'learning_rate': 1.465174546573774e-05, 'epoch': 0.37} + 37%|███▋ | 4288/11728 [3:21:53<11:59:49, 5.81s/it] 37%|███▋ | 4289/11728 [3:21:59<12:03:49, 5.84s/it] {'loss': 0.4956, 'learning_rate': 1.4649300670383456e-05, 'epoch': 0.37} + 37%|███▋ | 4289/11728 [3:21:59<12:03:49, 5.84s/it] 37%|███▋ | 4290/11728 [3:22:04<11:53:58, 5.76s/it] {'loss': 0.4882, 'learning_rate': 1.4646855520454096e-05, 'epoch': 0.37} + 37%|███▋ | 4290/11728 [3:22:04<11:53:58, 5.76s/it] 37%|███▋ | 4291/11728 [3:22:10<11:53:52, 5.76s/it] {'loss': 0.4944, 'learning_rate': 1.4644410016136132e-05, 'epoch': 0.37} + 37%|███▋ | 4291/11728 [3:22:10<11:53:52, 5.76s/it] 37%|███▋ | 4292/11728 [3:22:16<11:49:04, 5.72s/it] {'loss': 0.47, 'learning_rate': 1.4641964157616068e-05, 'epoch': 0.37} + 37%|███▋ | 4292/11728 [3:22:16<11:49:04, 5.72s/it] 37%|███▋ | 4293/11728 [3:22:21<11:52:50, 5.75s/it] {'loss': 0.4619, 'learning_rate': 1.4639517945080444e-05, 'epoch': 0.37} + 37%|███▋ | 4293/11728 [3:22:21<11:52:50, 5.75s/it] 37%|███▋ | 4294/11728 [3:22:27<11:50:06, 5.73s/it] {'loss': 0.5072, 'learning_rate': 1.4637071378715807e-05, 'epoch': 0.37} + 37%|███▋ | 4294/11728 [3:22:27<11:50:06, 5.73s/it] 37%|███▋ | 4295/11728 [3:22:33<11:54:25, 5.77s/it] {'loss': 0.4646, 'learning_rate': 1.4634624458708749e-05, 'epoch': 0.37} + 37%|███▋ | 4295/11728 [3:22:33<11:54:25, 5.77s/it] 37%|███▋ | 4296/11728 [3:22:39<11:58:06, 5.80s/it] {'loss': 0.4926, 'learning_rate': 1.463217718524588e-05, 'epoch': 0.37} + 37%|███▋ | 4296/11728 [3:22:39<11:58:06, 5.80s/it] 37%|███▋ | 4297/11728 [3:22:45<11:59:59, 5.81s/it] {'loss': 0.4767, 'learning_rate': 1.4629729558513841e-05, 'epoch': 0.37} + 37%|███▋ | 4297/11728 [3:22:45<11:59:59, 5.81s/it] 37%|███▋ | 4298/11728 [3:22:51<12:09:31, 5.89s/it] {'loss': 0.4875, 'learning_rate': 1.4627281578699297e-05, 'epoch': 0.37} + 37%|███▋ | 4298/11728 [3:22:51<12:09:31, 5.89s/it] 37%|███▋ | 4299/11728 [3:22:57<12:09:25, 5.89s/it] {'loss': 0.5112, 'learning_rate': 1.462483324598894e-05, 'epoch': 0.37} + 37%|███▋ | 4299/11728 [3:22:57<12:09:25, 5.89s/it]2 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +01 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... + 37%|███▋ | 4300/11728 [3:23:02<12:07:26, 5.88s/it]3 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4949, 'learning_rate': 1.4622384560569493e-05, 'epoch': 0.37} + 37%|███▋ | 4300/11728 [3:23:02<12:07:26, 5.88s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-4300/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-4300/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-4300/mm_projector +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/torch/nn/modules/module.py:1802: UserWarning: Positional args are being deprecated, use kwargs instead. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details. + warnings.warn( + 37%|███▋ | 4301/11728 [3:23:36<29:05:52, 14.10s/it] {'loss': 0.5029, 'learning_rate': 1.4619935522627702e-05, 'epoch': 0.37} + 37%|███▋ | 4301/11728 [3:23:36<29:05:52, 14.10s/it] 37%|███▋ | 4302/11728 [3:23:42<24:05:35, 11.68s/it] {'loss': 0.488, 'learning_rate': 1.4617486132350343e-05, 'epoch': 0.37} + 37%|███▋ | 4302/11728 [3:23:42<24:05:35, 11.68s/it] 37%|███▋ | 4303/11728 [3:23:47<20:19:11, 9.85s/it] {'loss': 0.475, 'learning_rate': 1.4615036389924209e-05, 'epoch': 0.37} + 37%|███▋ | 4303/11728 [3:23:47<20:19:11, 9.85s/it] 37%|███▋ | 4304/11728 [3:23:53<17:44:34, 8.60s/it] {'loss': 0.4874, 'learning_rate': 1.4612586295536136e-05, 'epoch': 0.37} + 37%|███▋ | 4304/11728 [3:23:53<17:44:34, 8.60s/it] 37%|███▋ | 4305/11728 [3:23:59<16:00:15, 7.76s/it] {'loss': 0.4854, 'learning_rate': 1.4610135849372972e-05, 'epoch': 0.37} + 37%|███▋ | 4305/11728 [3:23:59<16:00:15, 7.76s/it] 37%|███▋ | 4306/11728 [3:24:05<14:43:51, 7.15s/it] {'loss': 0.4774, 'learning_rate': 1.4607685051621603e-05, 'epoch': 0.37} + 37%|███▋ | 4306/11728 [3:24:05<14:43:51, 7.15s/it] 37%|███▋ | 4307/11728 [3:24:10<13:46:55, 6.69s/it] {'loss': 0.4818, 'learning_rate': 1.4605233902468939e-05, 'epoch': 0.37} + 37%|███▋ | 4307/11728 [3:24:10<13:46:55, 6.69s/it] 37%|███▋ | 4308/11728 [3:24:16<13:07:05, 6.36s/it] {'loss': 0.4863, 'learning_rate': 1.4602782402101908e-05, 'epoch': 0.37} + 37%|███▋ | 4308/11728 [3:24:16<13:07:05, 6.36s/it] 37%|███▋ | 4309/11728 [3:24:22<12:47:33, 6.21s/it] {'loss': 0.4921, 'learning_rate': 1.4600330550707473e-05, 'epoch': 0.37} + 37%|███▋ | 4309/11728 [3:24:22<12:47:33, 6.21s/it] 37%|███▋ | 4310/11728 [3:24:27<12:34:36, 6.10s/it] {'loss': 0.5017, 'learning_rate': 1.4597878348472625e-05, 'epoch': 0.37} + 37%|███▋ | 4310/11728 [3:24:27<12:34:36, 6.10s/it] 37%|███▋ | 4311/11728 [3:24:33<12:15:35, 5.95s/it] {'loss': 0.4833, 'learning_rate': 1.4595425795584384e-05, 'epoch': 0.37} + 37%|███▋ | 4311/11728 [3:24:33<12:15:35, 5.95s/it] 37%|███▋ | 4312/11728 [3:24:39<12:05:08, 5.87s/it] {'loss': 0.517, 'learning_rate': 1.4592972892229779e-05, 'epoch': 0.37} + 37%|███▋ | 4312/11728 [3:24:39<12:05:08, 5.87s/it] 37%|███▋ | 4313/11728 [3:24:45<12:07:20, 5.89s/it] {'loss': 0.5049, 'learning_rate': 1.4590519638595892e-05, 'epoch': 0.37} + 37%|███▋ | 4313/11728 [3:24:45<12:07:20, 5.89s/it] 37%|███▋ | 4314/11728 [3:24:51<12:18:03, 5.97s/it] {'loss': 0.482, 'learning_rate': 1.458806603486981e-05, 'epoch': 0.37} + 37%|███▋ | 4314/11728 [3:24:51<12:18:03, 5.97s/it] 37%|███▋ | 4315/11728 [3:24:57<12:07:32, 5.89s/it] {'loss': 0.4842, 'learning_rate': 1.4585612081238656e-05, 'epoch': 0.37} + 37%|███▋ | 4315/11728 [3:24:57<12:07:32, 5.89s/it] 37%|███▋ | 4316/11728 [3:25:02<12:06:11, 5.88s/it] {'loss': 0.4801, 'learning_rate': 1.4583157777889585e-05, 'epoch': 0.37} + 37%|███▋ | 4316/11728 [3:25:02<12:06:11, 5.88s/it] 37%|███▋ | 4317/11728 [3:25:08<12:11:26, 5.92s/it] {'loss': 0.4681, 'learning_rate': 1.4580703125009765e-05, 'epoch': 0.37} + 37%|███▋ | 4317/11728 [3:25:08<12:11:26, 5.92s/it] 37%|███▋ | 4318/11728 [3:25:15<12:22:06, 6.01s/it] {'loss': 0.5027, 'learning_rate': 1.4578248122786401e-05, 'epoch': 0.37} + 37%|███▋ | 4318/11728 [3:25:15<12:22:06, 6.01s/it] 37%|███▋ | 4319/11728 [3:25:20<12:13:27, 5.94s/it] {'loss': 0.4861, 'learning_rate': 1.4575792771406719e-05, 'epoch': 0.37} + 37%|███▋ | 4319/11728 [3:25:20<12:13:27, 5.94s/it] 37%|███▋ | 4320/11728 [3:25:26<12:04:56, 5.87s/it] {'loss': 0.4941, 'learning_rate': 1.457333707105798e-05, 'epoch': 0.37} + 37%|███▋ | 4320/11728 [3:25:26<12:04:56, 5.87s/it] 37%|███▋ | 4321/11728 [3:25:33<12:25:33, 6.04s/it] {'loss': 0.4864, 'learning_rate': 1.4570881021927461e-05, 'epoch': 0.37} + 37%|███▋ | 4321/11728 [3:25:33<12:25:33, 6.04s/it] 37%|███▋ | 4322/11728 [3:25:38<12:09:42, 5.91s/it] {'loss': 0.4937, 'learning_rate': 1.4568424624202475e-05, 'epoch': 0.37} + 37%|███▋ | 4322/11728 [3:25:38<12:09:42, 5.91s/it] 37%|███▋ | 4323/11728 [3:25:44<12:04:16, 5.87s/it] {'loss': 0.4825, 'learning_rate': 1.4565967878070351e-05, 'epoch': 0.37} + 37%|███▋ | 4323/11728 [3:25:44<12:04:16, 5.87s/it] 37%|███▋ | 4324/11728 [3:25:49<11:53:32, 5.78s/it] {'loss': 0.4843, 'learning_rate': 1.4563510783718457e-05, 'epoch': 0.37} + 37%|███▋ | 4324/11728 [3:25:49<11:53:32, 5.78s/it] 37%|███▋ | 4325/11728 [3:25:55<11:45:59, 5.72s/it] {'loss': 0.476, 'learning_rate': 1.456105334133418e-05, 'epoch': 0.37} + 37%|███▋ | 4325/11728 [3:25:55<11:45:59, 5.72s/it] 37%|███▋ | 4326/11728 [3:26:01<11:49:41, 5.75s/it] {'loss': 0.4944, 'learning_rate': 1.455859555110493e-05, 'epoch': 0.37} + 37%|███▋ | 4326/11728 [3:26:01<11:49:41, 5.75s/it] 37%|███▋ | 4327/11728 [3:26:07<11:55:10, 5.80s/it] {'loss': 0.4901, 'learning_rate': 1.4556137413218153e-05, 'epoch': 0.37} + 37%|███▋ | 4327/11728 [3:26:07<11:55:10, 5.80s/it] 37%|███▋ | 4328/11728 [3:26:12<11:45:36, 5.72s/it] {'loss': 0.4698, 'learning_rate': 1.4553678927861314e-05, 'epoch': 0.37} + 37%|███▋ | 4328/11728 [3:26:12<11:45:36, 5.72s/it] 37%|███▋ | 4329/11728 [3:26:18<11:50:44, 5.76s/it] {'loss': 0.4963, 'learning_rate': 1.4551220095221911e-05, 'epoch': 0.37} + 37%|███▋ | 4329/11728 [3:26:18<11:50:44, 5.76s/it] 37%|███▋ | 4330/11728 [3:26:24<11:53:12, 5.78s/it] {'loss': 0.4614, 'learning_rate': 1.4548760915487463e-05, 'epoch': 0.37} + 37%|███▋ | 4330/11728 [3:26:24<11:53:12, 5.78s/it] 37%|███▋ | 4331/11728 [3:26:30<11:51:25, 5.77s/it] {'loss': 0.4796, 'learning_rate': 1.4546301388845515e-05, 'epoch': 0.37} + 37%|███▋ | 4331/11728 [3:26:30<11:51:25, 5.77s/it] 37%|███▋ | 4332/11728 [3:26:36<12:01:01, 5.85s/it] {'loss': 0.4999, 'learning_rate': 1.4543841515483645e-05, 'epoch': 0.37} + 37%|███▋ | 4332/11728 [3:26:36<12:01:01, 5.85s/it] 37%|███▋ | 4333/11728 [3:26:42<12:02:14, 5.86s/it] {'loss': 0.5036, 'learning_rate': 1.454138129558945e-05, 'epoch': 0.37} + 37%|███▋ | 4333/11728 [3:26:42<12:02:14, 5.86s/it] 37%|███▋ | 4334/11728 [3:26:47<11:56:38, 5.82s/it] {'loss': 0.4533, 'learning_rate': 1.4538920729350559e-05, 'epoch': 0.37} + 37%|███▋ | 4334/11728 [3:26:47<11:56:38, 5.82s/it] 37%|███▋ | 4335/11728 [3:26:53<11:52:51, 5.79s/it] {'loss': 0.4986, 'learning_rate': 1.4536459816954623e-05, 'epoch': 0.37} + 37%|███▋ | 4335/11728 [3:26:53<11:52:51, 5.79s/it] 37%|███▋ | 4336/11728 [3:26:59<11:55:27, 5.81s/it] {'loss': 0.4806, 'learning_rate': 1.4533998558589319e-05, 'epoch': 0.37} + 37%|███▋ | 4336/11728 [3:26:59<11:55:27, 5.81s/it] 37%|███▋ | 4337/11728 [3:27:05<12:10:41, 5.93s/it] {'loss': 0.4931, 'learning_rate': 1.4531536954442363e-05, 'epoch': 0.37} + 37%|███▋ | 4337/11728 [3:27:05<12:10:41, 5.93s/it] 37%|███▋ | 4338/11728 [3:27:11<12:00:48, 5.85s/it] {'loss': 0.496, 'learning_rate': 1.4529075004701474e-05, 'epoch': 0.37} + 37%|███▋ | 4338/11728 [3:27:11<12:00:48, 5.85s/it] 37%|███▋ | 4339/11728 [3:27:17<12:04:29, 5.88s/it] {'loss': 0.4814, 'learning_rate': 1.452661270955442e-05, 'epoch': 0.37} + 37%|███▋ | 4339/11728 [3:27:17<12:04:29, 5.88s/it] 37%|███▋ | 4340/11728 [3:27:23<12:05:35, 5.89s/it] {'loss': 0.4898, 'learning_rate': 1.452415006918898e-05, 'epoch': 0.37} + 37%|███▋ | 4340/11728 [3:27:23<12:05:35, 5.89s/it] 37%|███▋ | 4341/11728 [3:27:29<12:03:14, 5.87s/it] {'loss': 0.488, 'learning_rate': 1.452168708379297e-05, 'epoch': 0.37} + 37%|███▋ | 4341/11728 [3:27:29<12:03:14, 5.87s/it] 37%|███▋ | 4342/11728 [3:27:34<11:58:38, 5.84s/it] {'loss': 0.5023, 'learning_rate': 1.4519223753554223e-05, 'epoch': 0.37} + 37%|███▋ | 4342/11728 [3:27:34<11:58:38, 5.84s/it] 37%|███▋ | 4343/11728 [3:27:40<11:51:50, 5.78s/it] {'loss': 0.4861, 'learning_rate': 1.451676007866061e-05, 'epoch': 0.37} + 37%|███▋ | 4343/11728 [3:27:40<11:51:50, 5.78s/it] 37%|███▋ | 4344/11728 [3:27:46<11:46:36, 5.74s/it] {'loss': 0.4874, 'learning_rate': 1.4514296059300014e-05, 'epoch': 0.37} + 37%|███▋ | 4344/11728 [3:27:46<11:46:36, 5.74s/it] 37%|███▋ | 4345/11728 [3:27:51<11:51:11, 5.78s/it] {'loss': 0.49, 'learning_rate': 1.4511831695660354e-05, 'epoch': 0.37} + 37%|███▋ | 4345/11728 [3:27:51<11:51:11, 5.78s/it] 37%|███▋ | 4346/11728 [3:27:57<11:52:36, 5.79s/it] {'loss': 0.4737, 'learning_rate': 1.4509366987929574e-05, 'epoch': 0.37} + 37%|███▋ | 4346/11728 [3:27:57<11:52:36, 5.79s/it] 37%|███▋ | 4347/11728 [3:28:03<11:48:46, 5.76s/it] {'loss': 0.4792, 'learning_rate': 1.4506901936295638e-05, 'epoch': 0.37} + 37%|███▋ | 4347/11728 [3:28:03<11:48:46, 5.76s/it] 37%|███▋ | 4348/11728 [3:28:09<11:53:47, 5.80s/it] {'loss': 0.4914, 'learning_rate': 1.4504436540946548e-05, 'epoch': 0.37} + 37%|███▋ | 4348/11728 [3:28:09<11:53:47, 5.80s/it] 37%|███▋ | 4349/11728 [3:28:15<11:50:18, 5.78s/it] {'loss': 0.507, 'learning_rate': 1.450197080207032e-05, 'epoch': 0.37} + 37%|███▋ | 4349/11728 [3:28:15<11:50:18, 5.78s/it]2 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +0 6 AutoResumeHook: Checking whether to suspend... +AutoResumeHook: Checking whether to suspend...5 + AutoResumeHook: Checking whether to suspend... + 37%|███▋ | 4350/11728 [3:28:20<11:54:14, 5.81s/it]3 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4753, 'learning_rate': 1.4499504719855002e-05, 'epoch': 0.37} + 37%|███▋ | 4350/11728 [3:28:20<11:54:14, 5.81s/it] 37%|███▋ | 4351/11728 [3:28:26<11:54:29, 5.81s/it] {'loss': 0.4912, 'learning_rate': 1.449703829448867e-05, 'epoch': 0.37} + 37%|███▋ | 4351/11728 [3:28:26<11:54:29, 5.81s/it] 37%|███▋ | 4352/11728 [3:28:32<11:55:32, 5.82s/it] {'loss': 0.4964, 'learning_rate': 1.4494571526159427e-05, 'epoch': 0.37} + 37%|███▋ | 4352/11728 [3:28:32<11:55:32, 5.82s/it] 37%|███▋ | 4353/11728 [3:28:38<11:55:35, 5.82s/it] {'loss': 0.4775, 'learning_rate': 1.4492104415055393e-05, 'epoch': 0.37} + 37%|███▋ | 4353/11728 [3:28:38<11:55:35, 5.82s/it] 37%|███▋ | 4354/11728 [3:28:44<11:49:20, 5.77s/it] {'loss': 0.4802, 'learning_rate': 1.4489636961364719e-05, 'epoch': 0.37} + 37%|███▋ | 4354/11728 [3:28:44<11:49:20, 5.77s/it] 37%|███▋ | 4355/11728 [3:28:49<11:51:36, 5.79s/it] {'loss': 0.4754, 'learning_rate': 1.4487169165275592e-05, 'epoch': 0.37} + 37%|███▋ | 4355/11728 [3:28:49<11:51:36, 5.79s/it] 37%|███▋ | 4356/11728 [3:28:55<11:43:50, 5.73s/it] {'loss': 0.4595, 'learning_rate': 1.4484701026976207e-05, 'epoch': 0.37} + 37%|███▋ | 4356/11728 [3:28:55<11:43:50, 5.73s/it] 37%|███▋ | 4357/11728 [3:29:01<11:46:34, 5.75s/it] {'loss': 0.4892, 'learning_rate': 1.4482232546654799e-05, 'epoch': 0.37} + 37%|███▋ | 4357/11728 [3:29:01<11:46:34, 5.75s/it] 37%|███▋ | 4358/11728 [3:29:07<11:51:45, 5.79s/it] {'loss': 0.4908, 'learning_rate': 1.4479763724499627e-05, 'epoch': 0.37} + 37%|███▋ | 4358/11728 [3:29:07<11:51:45, 5.79s/it] 37%|███▋ | 4359/11728 [3:29:13<11:52:05, 5.80s/it] {'loss': 0.4801, 'learning_rate': 1.4477294560698968e-05, 'epoch': 0.37} + 37%|███▋ | 4359/11728 [3:29:13<11:52:05, 5.80s/it] 37%|███▋ | 4360/11728 [3:29:18<11:53:24, 5.81s/it] {'loss': 0.4719, 'learning_rate': 1.4474825055441135e-05, 'epoch': 0.37} + 37%|███▋ | 4360/11728 [3:29:18<11:53:24, 5.81s/it] 37%|███▋ | 4361/11728 [3:29:24<11:42:37, 5.72s/it] {'loss': 0.4755, 'learning_rate': 1.4472355208914462e-05, 'epoch': 0.37} + 37%|███▋ | 4361/11728 [3:29:24<11:42:37, 5.72s/it] 37%|███▋ | 4362/11728 [3:29:29<11:34:13, 5.65s/it] {'loss': 0.4928, 'learning_rate': 1.4469885021307308e-05, 'epoch': 0.37} + 37%|███▋ | 4362/11728 [3:29:29<11:34:13, 5.65s/it] 37%|███▋ | 4363/11728 [3:29:35<11:39:21, 5.70s/it] {'loss': 0.496, 'learning_rate': 1.4467414492808061e-05, 'epoch': 0.37} + 37%|███▋ | 4363/11728 [3:29:35<11:39:21, 5.70s/it] 37%|███▋ | 4364/11728 [3:29:41<11:57:26, 5.85s/it] {'loss': 0.4923, 'learning_rate': 1.4464943623605136e-05, 'epoch': 0.37} + 37%|███▋ | 4364/11728 [3:29:41<11:57:26, 5.85s/it] 37%|███▋ | 4365/11728 [3:29:47<11:46:04, 5.75s/it] {'loss': 0.4818, 'learning_rate': 1.4462472413886965e-05, 'epoch': 0.37} + 37%|███▋ | 4365/11728 [3:29:47<11:46:04, 5.75s/it] 37%|███▋ | 4366/11728 [3:29:53<11:45:06, 5.75s/it] {'loss': 0.4822, 'learning_rate': 1.4460000863842023e-05, 'epoch': 0.37} + 37%|███▋ | 4366/11728 [3:29:53<11:45:06, 5.75s/it] 37%|███▋ | 4367/11728 [3:29:58<11:42:16, 5.72s/it] {'loss': 0.4815, 'learning_rate': 1.4457528973658793e-05, 'epoch': 0.37} + 37%|███▋ | 4367/11728 [3:29:58<11:42:16, 5.72s/it] 37%|███▋ | 4368/11728 [3:30:04<11:39:06, 5.70s/it] {'loss': 0.492, 'learning_rate': 1.4455056743525793e-05, 'epoch': 0.37} + 37%|███▋ | 4368/11728 [3:30:04<11:39:06, 5.70s/it] 37%|███▋ | 4369/11728 [3:30:10<11:47:34, 5.77s/it] {'loss': 0.4611, 'learning_rate': 1.445258417363157e-05, 'epoch': 0.37} + 37%|███▋ | 4369/11728 [3:30:10<11:47:34, 5.77s/it] 37%|███▋ | 4370/11728 [3:30:15<11:39:18, 5.70s/it] {'loss': 0.4825, 'learning_rate': 1.4450111264164683e-05, 'epoch': 0.37} + 37%|███▋ | 4370/11728 [3:30:15<11:39:18, 5.70s/it] 37%|███▋ | 4371/11728 [3:30:21<11:49:23, 5.79s/it] {'loss': 0.4967, 'learning_rate': 1.4447638015313737e-05, 'epoch': 0.37} + 37%|███▋ | 4371/11728 [3:30:21<11:49:23, 5.79s/it] 37%|███▋ | 4372/11728 [3:30:27<11:58:14, 5.86s/it] {'loss': 0.528, 'learning_rate': 1.4445164427267344e-05, 'epoch': 0.37} + 37%|███▋ | 4372/11728 [3:30:27<11:58:14, 5.86s/it] 37%|███▋ | 4373/11728 [3:30:33<11:59:12, 5.87s/it] {'loss': 0.4656, 'learning_rate': 1.4442690500214158e-05, 'epoch': 0.37} + 37%|███▋ | 4373/11728 [3:30:33<11:59:12, 5.87s/it] 37%|███▋ | 4374/11728 [3:30:39<12:03:14, 5.90s/it] {'loss': 0.4944, 'learning_rate': 1.444021623434284e-05, 'epoch': 0.37} + 37%|███▋ | 4374/11728 [3:30:39<12:03:14, 5.90s/it] 37%|███▋ | 4375/11728 [3:30:45<11:52:30, 5.81s/it] {'loss': 0.4999, 'learning_rate': 1.4437741629842103e-05, 'epoch': 0.37} + 37%|███▋ | 4375/11728 [3:30:45<11:52:30, 5.81s/it] 37%|███▋ | 4376/11728 [3:30:51<11:55:04, 5.84s/it] {'loss': 0.4789, 'learning_rate': 1.443526668690066e-05, 'epoch': 0.37} + 37%|███▋ | 4376/11728 [3:30:51<11:55:04, 5.84s/it] 37%|███▋ | 4377/11728 [3:30:57<12:11:24, 5.97s/it] {'loss': 0.5054, 'learning_rate': 1.4432791405707257e-05, 'epoch': 0.37} + 37%|███▋ | 4377/11728 [3:30:57<12:11:24, 5.97s/it] 37%|███▋ | 4378/11728 [3:31:03<12:03:28, 5.91s/it] {'loss': 0.4885, 'learning_rate': 1.4430315786450683e-05, 'epoch': 0.37} + 37%|███▋ | 4378/11728 [3:31:03<12:03:28, 5.91s/it] 37%|███▋ | 4379/11728 [3:31:08<11:52:07, 5.81s/it] {'loss': 0.4687, 'learning_rate': 1.4427839829319728e-05, 'epoch': 0.37} + 37%|███▋ | 4379/11728 [3:31:08<11:52:07, 5.81s/it] 37%|███▋ | 4380/11728 [3:31:14<11:57:59, 5.86s/it] {'loss': 0.5444, 'learning_rate': 1.442536353450322e-05, 'epoch': 0.37} + 37%|███▋ | 4380/11728 [3:31:14<11:57:59, 5.86s/it] 37%|███▋ | 4381/11728 [3:31:20<11:58:57, 5.87s/it] {'loss': 0.494, 'learning_rate': 1.4422886902190014e-05, 'epoch': 0.37} + 37%|███▋ | 4381/11728 [3:31:20<11:58:57, 5.87s/it] 37%|███▋ | 4382/11728 [3:31:27<12:12:33, 5.98s/it] {'loss': 0.4696, 'learning_rate': 1.442040993256899e-05, 'epoch': 0.37} + 37%|███▋ | 4382/11728 [3:31:27<12:12:33, 5.98s/it] 37%|███▋ | 4383/11728 [3:31:33<12:11:14, 5.97s/it] {'loss': 0.5168, 'learning_rate': 1.4417932625829045e-05, 'epoch': 0.37} + 37%|███▋ | 4383/11728 [3:31:33<12:11:14, 5.97s/it] 37%|███▋ | 4384/11728 [3:31:38<12:03:01, 5.91s/it] {'loss': 0.5032, 'learning_rate': 1.4415454982159121e-05, 'epoch': 0.37} + 37%|███▋ | 4384/11728 [3:31:38<12:03:01, 5.91s/it] 37%|███▋ | 4385/11728 [3:31:44<11:56:42, 5.86s/it] {'loss': 0.4778, 'learning_rate': 1.4412977001748164e-05, 'epoch': 0.37} + 37%|███▋ | 4385/11728 [3:31:44<11:56:42, 5.86s/it] 37%|███▋ | 4386/11728 [3:31:50<12:00:34, 5.89s/it] {'loss': 0.4758, 'learning_rate': 1.4410498684785153e-05, 'epoch': 0.37} + 37%|███▋ | 4386/11728 [3:31:50<12:00:34, 5.89s/it] 37%|███▋ | 4387/11728 [3:31:56<11:52:30, 5.82s/it] {'loss': 0.4985, 'learning_rate': 1.4408020031459103e-05, 'epoch': 0.37} + 37%|███▋ | 4387/11728 [3:31:56<11:52:30, 5.82s/it] 37%|███▋ | 4388/11728 [3:32:02<11:53:47, 5.83s/it] {'loss': 0.4866, 'learning_rate': 1.440554104195904e-05, 'epoch': 0.37} + 37%|███▋ | 4388/11728 [3:32:02<11:53:47, 5.83s/it] 37%|███▋ | 4389/11728 [3:32:07<11:46:46, 5.78s/it] {'loss': 0.4645, 'learning_rate': 1.4403061716474026e-05, 'epoch': 0.37} + 37%|███▋ | 4389/11728 [3:32:07<11:46:46, 5.78s/it] 37%|███▋ | 4390/11728 [3:32:13<11:38:14, 5.71s/it] {'loss': 0.5033, 'learning_rate': 1.4400582055193143e-05, 'epoch': 0.37} + 37%|███▋ | 4390/11728 [3:32:13<11:38:14, 5.71s/it] 37%|███▋ | 4391/11728 [3:32:18<11:34:43, 5.68s/it] {'loss': 0.503, 'learning_rate': 1.43981020583055e-05, 'epoch': 0.37} + 37%|███▋ | 4391/11728 [3:32:18<11:34:43, 5.68s/it] 37%|███▋ | 4392/11728 [3:32:25<11:53:18, 5.83s/it] {'loss': 0.4919, 'learning_rate': 1.4395621726000232e-05, 'epoch': 0.37} + 37%|███▋ | 4392/11728 [3:32:25<11:53:18, 5.83s/it] 37%|███▋ | 4393/11728 [3:32:30<11:52:05, 5.82s/it] {'loss': 0.506, 'learning_rate': 1.4393141058466502e-05, 'epoch': 0.37} + 37%|███▋ | 4393/11728 [3:32:30<11:52:05, 5.82s/it] 37%|███▋ | 4394/11728 [3:32:36<11:58:59, 5.88s/it] {'loss': 0.4981, 'learning_rate': 1.4390660055893495e-05, 'epoch': 0.37} + 37%|███▋ | 4394/11728 [3:32:36<11:58:59, 5.88s/it] 37%|███▋ | 4395/11728 [3:32:42<11:48:54, 5.80s/it] {'loss': 0.4832, 'learning_rate': 1.4388178718470416e-05, 'epoch': 0.37} + 37%|███▋ | 4395/11728 [3:32:42<11:48:54, 5.80s/it] 37%|███▋ | 4396/11728 [3:32:48<11:53:01, 5.83s/it] {'loss': 0.4907, 'learning_rate': 1.4385697046386513e-05, 'epoch': 0.37} + 37%|███▋ | 4396/11728 [3:32:48<11:53:01, 5.83s/it] 37%|███▋ | 4397/11728 [3:32:54<11:52:44, 5.83s/it] {'loss': 0.5112, 'learning_rate': 1.4383215039831042e-05, 'epoch': 0.37} + 37%|███▋ | 4397/11728 [3:32:54<11:52:44, 5.83s/it] 38%|███▊ | 4398/11728 [3:33:00<11:57:34, 5.87s/it] {'loss': 0.4798, 'learning_rate': 1.4380732698993291e-05, 'epoch': 0.38} + 38%|███▊ | 4398/11728 [3:33:00<11:57:34, 5.87s/it] 38%|███▊ | 4399/11728 [3:33:06<11:57:46, 5.88s/it] {'loss': 0.4705, 'learning_rate': 1.4378250024062577e-05, 'epoch': 0.38} + 38%|███▊ | 4399/11728 [3:33:06<11:57:46, 5.88s/it]2 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +0 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... + 38%|███▊ | 4400/11728 [3:33:11<11:57:34, 5.88s/it]3 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4889, 'learning_rate': 1.437576701522824e-05, 'epoch': 0.38} + 38%|███▊ | 4400/11728 [3:33:11<11:57:34, 5.88s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-4400/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-4400/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-4400/mm_projector +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/torch/nn/modules/module.py:1802: UserWarning: Positional args are being deprecated, use kwargs instead. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details. + warnings.warn( + 38%|███▊ | 4401/11728 [3:33:42<27:11:52, 13.36s/it] {'loss': 0.4848, 'learning_rate': 1.4373283672679638e-05, 'epoch': 0.38} + 38%|███▊ | 4401/11728 [3:33:42<27:11:52, 13.36s/it] 38%|███▊ | 4402/11728 [3:33:48<22:20:15, 10.98s/it] {'loss': 0.4846, 'learning_rate': 1.4370799996606169e-05, 'epoch': 0.38} + 38%|███▊ | 4402/11728 [3:33:48<22:20:15, 10.98s/it] 38%|███▊ | 4403/11728 [3:33:54<19:16:22, 9.47s/it] {'loss': 0.4869, 'learning_rate': 1.4368315987197244e-05, 'epoch': 0.38} + 38%|███▊ | 4403/11728 [3:33:54<19:16:22, 9.47s/it] 38%|███▊ | 4404/11728 [3:33:59<17:02:17, 8.37s/it] {'loss': 0.4805, 'learning_rate': 1.43658316446423e-05, 'epoch': 0.38} + 38%|███▊ | 4404/11728 [3:33:59<17:02:17, 8.37s/it] 38%|███▊ | 4405/11728 [3:34:06<15:37:51, 7.68s/it] {'loss': 0.4686, 'learning_rate': 1.4363346969130813e-05, 'epoch': 0.38} + 38%|███▊ | 4405/11728 [3:34:06<15:37:51, 7.68s/it] 38%|███▊ | 4406/11728 [3:34:11<14:22:28, 7.07s/it] {'loss': 0.4772, 'learning_rate': 1.4360861960852268e-05, 'epoch': 0.38} + 38%|███▊ | 4406/11728 [3:34:11<14:22:28, 7.07s/it] 38%|███▊ | 4407/11728 [3:34:17<13:31:25, 6.65s/it] {'loss': 0.4993, 'learning_rate': 1.4358376619996182e-05, 'epoch': 0.38} + 38%|███▊ | 4407/11728 [3:34:17<13:31:25, 6.65s/it] 38%|███▊ | 4408/11728 [3:34:23<12:59:21, 6.39s/it] {'loss': 0.4808, 'learning_rate': 1.4355890946752102e-05, 'epoch': 0.38} + 38%|███▊ | 4408/11728 [3:34:23<12:59:21, 6.39s/it] 38%|███▊ | 4409/11728 [3:34:28<12:25:17, 6.11s/it] {'loss': 0.4596, 'learning_rate': 1.4353404941309594e-05, 'epoch': 0.38} + 38%|███▊ | 4409/11728 [3:34:28<12:25:17, 6.11s/it] 38%|███▊ | 4410/11728 [3:34:34<12:09:45, 5.98s/it] {'loss': 0.4806, 'learning_rate': 1.4350918603858248e-05, 'epoch': 0.38} + 38%|███▊ | 4410/11728 [3:34:34<12:09:45, 5.98s/it] 38%|███▊ | 4411/11728 [3:34:40<12:08:13, 5.97s/it] {'loss': 0.4868, 'learning_rate': 1.4348431934587685e-05, 'epoch': 0.38} + 38%|███▊ | 4411/11728 [3:34:40<12:08:13, 5.97s/it] 38%|███▊ | 4412/11728 [3:34:46<12:10:16, 5.99s/it] {'loss': 0.4746, 'learning_rate': 1.4345944933687548e-05, 'epoch': 0.38} + 38%|███▊ | 4412/11728 [3:34:46<12:10:16, 5.99s/it] 38%|███▊ | 4413/11728 [3:34:51<11:52:11, 5.84s/it] {'loss': 0.4809, 'learning_rate': 1.4343457601347505e-05, 'epoch': 0.38} + 38%|███▊ | 4413/11728 [3:34:51<11:52:11, 5.84s/it] 38%|███▊ | 4414/11728 [3:34:57<11:44:57, 5.78s/it] {'loss': 0.499, 'learning_rate': 1.4340969937757256e-05, 'epoch': 0.38} + 38%|███▊ | 4414/11728 [3:34:57<11:44:57, 5.78s/it] 38%|███▊ | 4415/11728 [3:35:03<11:56:43, 5.88s/it] {'loss': 0.4808, 'learning_rate': 1.4338481943106516e-05, 'epoch': 0.38} + 38%|███▊ | 4415/11728 [3:35:03<11:56:43, 5.88s/it] 38%|███▊ | 4416/11728 [3:35:09<11:48:07, 5.81s/it] {'loss': 0.4947, 'learning_rate': 1.433599361758503e-05, 'epoch': 0.38} + 38%|███▊ | 4416/11728 [3:35:09<11:48:07, 5.81s/it] 38%|███▊ | 4417/11728 [3:35:15<11:51:11, 5.84s/it] {'loss': 0.4946, 'learning_rate': 1.4333504961382566e-05, 'epoch': 0.38} + 38%|███▊ | 4417/11728 [3:35:15<11:51:11, 5.84s/it] 38%|███▊ | 4418/11728 [3:35:20<11:47:15, 5.81s/it] {'loss': 0.4783, 'learning_rate': 1.4331015974688925e-05, 'epoch': 0.38} + 38%|███▊ | 4418/11728 [3:35:20<11:47:15, 5.81s/it] 38%|███▊ | 4419/11728 [3:35:26<11:42:33, 5.77s/it] {'loss': 0.4901, 'learning_rate': 1.4328526657693922e-05, 'epoch': 0.38} + 38%|███▊ | 4419/11728 [3:35:26<11:42:33, 5.77s/it] 38%|███▊ | 4420/11728 [3:35:32<11:47:11, 5.81s/it] {'loss': 0.4751, 'learning_rate': 1.4326037010587406e-05, 'epoch': 0.38} + 38%|███▊ | 4420/11728 [3:35:32<11:47:11, 5.81s/it] 38%|███▊ | 4421/11728 [3:35:38<11:49:46, 5.83s/it] {'loss': 0.4691, 'learning_rate': 1.4323547033559247e-05, 'epoch': 0.38} + 38%|███▊ | 4421/11728 [3:35:38<11:49:46, 5.83s/it] 38%|███▊ | 4422/11728 [3:35:43<11:47:27, 5.81s/it] {'loss': 0.4792, 'learning_rate': 1.4321056726799338e-05, 'epoch': 0.38} + 38%|███▊ | 4422/11728 [3:35:43<11:47:27, 5.81s/it] 38%|███▊ | 4423/11728 [3:35:49<11:50:28, 5.84s/it] {'loss': 0.4918, 'learning_rate': 1.4318566090497607e-05, 'epoch': 0.38} + 38%|███▊ | 4423/11728 [3:35:49<11:50:28, 5.84s/it] 38%|███▊ | 4424/11728 [3:35:55<11:54:23, 5.87s/it] {'loss': 0.4694, 'learning_rate': 1.4316075124843996e-05, 'epoch': 0.38} + 38%|███▊ | 4424/11728 [3:35:55<11:54:23, 5.87s/it] 38%|███▊ | 4425/11728 [3:36:01<11:52:16, 5.85s/it] {'loss': 0.4928, 'learning_rate': 1.4313583830028476e-05, 'epoch': 0.38} + 38%|███▊ | 4425/11728 [3:36:01<11:52:16, 5.85s/it] 38%|███▊ | 4426/11728 [3:36:07<11:49:11, 5.83s/it] {'loss': 0.506, 'learning_rate': 1.4311092206241046e-05, 'epoch': 0.38} + 38%|███▊ | 4426/11728 [3:36:07<11:49:11, 5.83s/it] 38%|███▊ | 4427/11728 [3:36:13<11:47:04, 5.81s/it] {'loss': 0.4898, 'learning_rate': 1.4308600253671725e-05, 'epoch': 0.38} + 38%|███▊ | 4427/11728 [3:36:13<11:47:04, 5.81s/it] 38%|███▊ | 4428/11728 [3:36:19<11:54:16, 5.87s/it] {'loss': 0.4629, 'learning_rate': 1.4306107972510559e-05, 'epoch': 0.38} + 38%|███▊ | 4428/11728 [3:36:19<11:54:16, 5.87s/it] 38%|███▊ | 4429/11728 [3:36:25<11:54:09, 5.87s/it] {'loss': 0.4889, 'learning_rate': 1.4303615362947623e-05, 'epoch': 0.38} + 38%|███▊ | 4429/11728 [3:36:25<11:54:09, 5.87s/it] 38%|███▊ | 4430/11728 [3:36:30<11:52:44, 5.86s/it] {'loss': 0.49, 'learning_rate': 1.4301122425173014e-05, 'epoch': 0.38} + 38%|███▊ | 4430/11728 [3:36:30<11:52:44, 5.86s/it] 38%|███▊ | 4431/11728 [3:36:36<11:57:53, 5.90s/it] {'loss': 0.4914, 'learning_rate': 1.4298629159376852e-05, 'epoch': 0.38} + 38%|███▊ | 4431/11728 [3:36:36<11:57:53, 5.90s/it] 38%|███▊ | 4432/11728 [3:36:42<11:59:32, 5.92s/it] {'loss': 0.5174, 'learning_rate': 1.429613556574928e-05, 'epoch': 0.38} + 38%|███▊ | 4432/11728 [3:36:42<11:59:32, 5.92s/it] 38%|███▊ | 4433/11728 [3:36:48<11:54:30, 5.88s/it] {'loss': 0.4693, 'learning_rate': 1.4293641644480478e-05, 'epoch': 0.38} + 38%|███▊ | 4433/11728 [3:36:48<11:54:30, 5.88s/it] 38%|███▊ | 4434/11728 [3:36:54<11:55:15, 5.88s/it] {'loss': 0.4629, 'learning_rate': 1.4291147395760637e-05, 'epoch': 0.38} + 38%|███▊ | 4434/11728 [3:36:54<11:55:15, 5.88s/it] 38%|███▊ | 4435/11728 [3:37:00<12:04:24, 5.96s/it] {'loss': 0.4888, 'learning_rate': 1.4288652819779982e-05, 'epoch': 0.38} + 38%|███▊ | 4435/11728 [3:37:00<12:04:24, 5.96s/it] 38%|███▊ | 4436/11728 [3:37:06<11:58:23, 5.91s/it] {'loss': 0.4962, 'learning_rate': 1.4286157916728756e-05, 'epoch': 0.38} + 38%|███▊ | 4436/11728 [3:37:06<11:58:23, 5.91s/it] 38%|███▊ | 4437/11728 [3:37:12<11:53:05, 5.87s/it] {'loss': 0.4732, 'learning_rate': 1.4283662686797236e-05, 'epoch': 0.38} + 38%|███▊ | 4437/11728 [3:37:12<11:53:05, 5.87s/it] 38%|███▊ | 4438/11728 [3:37:18<11:54:51, 5.88s/it] {'loss': 0.4731, 'learning_rate': 1.4281167130175712e-05, 'epoch': 0.38} + 38%|███▊ | 4438/11728 [3:37:18<11:54:51, 5.88s/it] 38%|███▊ | 4439/11728 [3:37:23<11:47:52, 5.83s/it] {'loss': 0.4913, 'learning_rate': 1.4278671247054511e-05, 'epoch': 0.38} + 38%|███▊ | 4439/11728 [3:37:23<11:47:52, 5.83s/it] 38%|███▊ | 4440/11728 [3:37:29<11:39:54, 5.76s/it] {'loss': 0.4853, 'learning_rate': 1.4276175037623981e-05, 'epoch': 0.38} + 38%|███▊ | 4440/11728 [3:37:29<11:39:54, 5.76s/it] 38%|███▊ | 4441/11728 [3:37:35<11:33:45, 5.71s/it] {'loss': 0.5042, 'learning_rate': 1.4273678502074487e-05, 'epoch': 0.38} + 38%|███▊ | 4441/11728 [3:37:35<11:33:45, 5.71s/it] 38%|███▊ | 4442/11728 [3:37:40<11:37:36, 5.74s/it] {'loss': 0.4729, 'learning_rate': 1.4271181640596428e-05, 'epoch': 0.38} + 38%|███▊ | 4442/11728 [3:37:40<11:37:36, 5.74s/it] 38%|███▊ | 4443/11728 [3:37:46<11:31:49, 5.70s/it] {'loss': 0.4701, 'learning_rate': 1.4268684453380227e-05, 'epoch': 0.38} + 38%|███▊ | 4443/11728 [3:37:46<11:31:49, 5.70s/it] 38%|███▊ | 4444/11728 [3:37:52<11:51:56, 5.86s/it] {'loss': 0.4708, 'learning_rate': 1.426618694061633e-05, 'epoch': 0.38} + 38%|███▊ | 4444/11728 [3:37:52<11:51:56, 5.86s/it] 38%|███▊ | 4445/11728 [3:37:58<11:53:02, 5.87s/it] {'loss': 0.4743, 'learning_rate': 1.42636891024952e-05, 'epoch': 0.38} + 38%|███▊ | 4445/11728 [3:37:58<11:53:02, 5.87s/it] 38%|███▊ | 4446/11728 [3:38:04<11:50:31, 5.85s/it] {'loss': 0.4837, 'learning_rate': 1.4261190939207343e-05, 'epoch': 0.38} + 38%|███▊ | 4446/11728 [3:38:04<11:50:31, 5.85s/it] 38%|███▊ | 4447/11728 [3:38:10<11:46:38, 5.82s/it] {'loss': 0.4758, 'learning_rate': 1.4258692450943276e-05, 'epoch': 0.38} + 38%|███▊ | 4447/11728 [3:38:10<11:46:38, 5.82s/it] 38%|███▊ | 4448/11728 [3:38:16<11:49:14, 5.85s/it] {'loss': 0.5049, 'learning_rate': 1.425619363789354e-05, 'epoch': 0.38} + 38%|███▊ | 4448/11728 [3:38:16<11:49:14, 5.85s/it] 38%|███▊ | 4449/11728 [3:38:22<11:54:40, 5.89s/it] {'loss': 0.4891, 'learning_rate': 1.4253694500248711e-05, 'epoch': 0.38} + 38%|███▊ | 4449/11728 [3:38:22<11:54:40, 5.89s/it]2 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +0 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... + 38%|███▊ | 4450/11728 [3:38:28<12:04:03, 5.97s/it]3 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4915, 'learning_rate': 1.425119503819938e-05, 'epoch': 0.38} + 38%|███▊ | 4450/11728 [3:38:28<12:04:03, 5.97s/it] 38%|███▊ | 4451/11728 [3:38:34<12:01:31, 5.95s/it] {'loss': 0.4923, 'learning_rate': 1.4248695251936167e-05, 'epoch': 0.38} + 38%|███▊ | 4451/11728 [3:38:34<12:01:31, 5.95s/it] 38%|███▊ | 4452/11728 [3:38:40<12:02:37, 5.96s/it] {'loss': 0.5001, 'learning_rate': 1.4246195141649715e-05, 'epoch': 0.38} + 38%|███▊ | 4452/11728 [3:38:40<12:02:37, 5.96s/it] 38%|███▊ | 4453/11728 [3:38:45<11:50:11, 5.86s/it] {'loss': 0.4767, 'learning_rate': 1.4243694707530696e-05, 'epoch': 0.38} + 38%|███▊ | 4453/11728 [3:38:45<11:50:11, 5.86s/it] 38%|███▊ | 4454/11728 [3:38:51<12:02:47, 5.96s/it] {'loss': 0.478, 'learning_rate': 1.42411939497698e-05, 'epoch': 0.38} + 38%|███▊ | 4454/11728 [3:38:51<12:02:47, 5.96s/it] 38%|███▊ | 4455/11728 [3:38:57<12:06:12, 5.99s/it] {'loss': 0.506, 'learning_rate': 1.4238692868557748e-05, 'epoch': 0.38} + 38%|███▊ | 4455/11728 [3:38:57<12:06:12, 5.99s/it] 38%|███▊ | 4456/11728 [3:39:03<11:58:15, 5.93s/it] {'loss': 0.4902, 'learning_rate': 1.4236191464085286e-05, 'epoch': 0.38} + 38%|███▊ | 4456/11728 [3:39:03<11:58:15, 5.93s/it] 38%|███▊ | 4457/11728 [3:39:09<11:57:17, 5.92s/it] {'loss': 0.4871, 'learning_rate': 1.4233689736543168e-05, 'epoch': 0.38} + 38%|███▊ | 4457/11728 [3:39:09<11:57:17, 5.92s/it] 38%|███▊ | 4458/11728 [3:39:15<11:54:16, 5.90s/it] {'loss': 0.4949, 'learning_rate': 1.4231187686122203e-05, 'epoch': 0.38} + 38%|███▊ | 4458/11728 [3:39:15<11:54:16, 5.90s/it] 38%|███▊ | 4459/11728 [3:39:20<11:38:35, 5.77s/it] {'loss': 0.4835, 'learning_rate': 1.4228685313013198e-05, 'epoch': 0.38} + 38%|███▊ | 4459/11728 [3:39:20<11:38:35, 5.77s/it] 38%|███▊ | 4460/11728 [3:39:26<11:39:14, 5.77s/it] {'loss': 0.4832, 'learning_rate': 1.4226182617406996e-05, 'epoch': 0.38} + 38%|███▊ | 4460/11728 [3:39:26<11:39:14, 5.77s/it] 38%|███▊ | 4461/11728 [3:39:32<11:45:36, 5.83s/it] {'loss': 0.4844, 'learning_rate': 1.4223679599494465e-05, 'epoch': 0.38} + 38%|███▊ | 4461/11728 [3:39:32<11:45:36, 5.83s/it] 38%|███▊ | 4462/11728 [3:39:38<11:41:27, 5.79s/it] {'loss': 0.4952, 'learning_rate': 1.4221176259466493e-05, 'epoch': 0.38} + 38%|███▊ | 4462/11728 [3:39:38<11:41:27, 5.79s/it] 38%|███▊ | 4463/11728 [3:39:44<11:39:50, 5.78s/it] {'loss': 0.473, 'learning_rate': 1.4218672597513999e-05, 'epoch': 0.38} + 38%|███▊ | 4463/11728 [3:39:44<11:39:50, 5.78s/it] 38%|███▊ | 4464/11728 [3:39:49<11:36:57, 5.76s/it] {'loss': 0.488, 'learning_rate': 1.4216168613827918e-05, 'epoch': 0.38} + 38%|███▊ | 4464/11728 [3:39:49<11:36:57, 5.76s/it] 38%|███▊ | 4465/11728 [3:39:55<11:34:02, 5.73s/it] {'loss': 0.5054, 'learning_rate': 1.421366430859922e-05, 'epoch': 0.38} + 38%|███▊ | 4465/11728 [3:39:55<11:34:02, 5.73s/it] 38%|███▊ | 4466/11728 [3:40:01<11:53:44, 5.90s/it] {'loss': 0.5021, 'learning_rate': 1.4211159682018884e-05, 'epoch': 0.38} + 38%|███▊ | 4466/11728 [3:40:01<11:53:44, 5.90s/it] 38%|███▊ | 4467/11728 [3:40:07<11:45:53, 5.83s/it] {'loss': 0.4831, 'learning_rate': 1.4208654734277936e-05, 'epoch': 0.38} + 38%|███▊ | 4467/11728 [3:40:07<11:45:53, 5.83s/it] 38%|███▊ | 4468/11728 [3:40:13<11:58:29, 5.94s/it] {'loss': 0.5069, 'learning_rate': 1.4206149465567402e-05, 'epoch': 0.38} + 38%|███▊ | 4468/11728 [3:40:13<11:58:29, 5.94s/it] 38%|███▊ | 4469/11728 [3:40:19<11:50:42, 5.87s/it] {'loss': 0.4841, 'learning_rate': 1.4203643876078354e-05, 'epoch': 0.38} + 38%|███▊ | 4469/11728 [3:40:19<11:50:42, 5.87s/it] 38%|███▊ | 4470/11728 [3:40:25<11:41:09, 5.80s/it] {'loss': 0.4932, 'learning_rate': 1.4201137966001874e-05, 'epoch': 0.38} + 38%|███▊ | 4470/11728 [3:40:25<11:41:09, 5.80s/it] 38%|███▊ | 4471/11728 [3:40:30<11:36:26, 5.76s/it] {'loss': 0.4994, 'learning_rate': 1.419863173552907e-05, 'epoch': 0.38} + 38%|███▊ | 4471/11728 [3:40:30<11:36:26, 5.76s/it] 38%|███▊ | 4472/11728 [3:40:36<11:27:47, 5.69s/it] {'loss': 0.4824, 'learning_rate': 1.4196125184851085e-05, 'epoch': 0.38} + 38%|███▊ | 4472/11728 [3:40:36<11:27:47, 5.69s/it] 38%|███▊ | 4473/11728 [3:40:42<11:39:39, 5.79s/it] {'loss': 0.4724, 'learning_rate': 1.4193618314159072e-05, 'epoch': 0.38} + 38%|███▊ | 4473/11728 [3:40:42<11:39:39, 5.79s/it] 38%|███▊ | 4474/11728 [3:40:47<11:38:00, 5.77s/it] {'loss': 0.4785, 'learning_rate': 1.419111112364422e-05, 'epoch': 0.38} + 38%|███▊ | 4474/11728 [3:40:47<11:38:00, 5.77s/it] 38%|███▊ | 4475/11728 [3:40:54<11:53:28, 5.90s/it] {'loss': 0.5023, 'learning_rate': 1.4188603613497735e-05, 'epoch': 0.38} + 38%|███▊ | 4475/11728 [3:40:54<11:53:28, 5.90s/it] 38%|███▊ | 4476/11728 [3:40:59<11:45:27, 5.84s/it] {'loss': 0.4858, 'learning_rate': 1.4186095783910854e-05, 'epoch': 0.38} + 38%|███▊ | 4476/11728 [3:40:59<11:45:27, 5.84s/it] 38%|███▊ | 4477/11728 [3:41:05<11:56:17, 5.93s/it] {'loss': 0.48, 'learning_rate': 1.4183587635074831e-05, 'epoch': 0.38} + 38%|███▊ | 4477/11728 [3:41:05<11:56:17, 5.93s/it] 38%|███▊ | 4478/11728 [3:41:11<11:49:03, 5.87s/it] {'loss': 0.5025, 'learning_rate': 1.4181079167180949e-05, 'epoch': 0.38} + 38%|███▊ | 4478/11728 [3:41:11<11:49:03, 5.87s/it] 38%|███▊ | 4479/11728 [3:41:17<11:44:28, 5.83s/it] {'loss': 0.4913, 'learning_rate': 1.4178570380420516e-05, 'epoch': 0.38} + 38%|███▊ | 4479/11728 [3:41:17<11:44:28, 5.83s/it] 38%|███▊ | 4480/11728 [3:41:23<11:53:13, 5.90s/it] {'loss': 0.4978, 'learning_rate': 1.4176061274984858e-05, 'epoch': 0.38} + 38%|███▊ | 4480/11728 [3:41:23<11:53:13, 5.90s/it] 38%|███▊ | 4481/11728 [3:41:29<11:44:09, 5.83s/it] {'loss': 0.4865, 'learning_rate': 1.4173551851065333e-05, 'epoch': 0.38} + 38%|███▊ | 4481/11728 [3:41:29<11:44:09, 5.83s/it] 38%|███▊ | 4482/11728 [3:41:35<11:48:11, 5.86s/it] {'loss': 0.4989, 'learning_rate': 1.4171042108853319e-05, 'epoch': 0.38} + 38%|███▊ | 4482/11728 [3:41:35<11:48:11, 5.86s/it] 38%|███▊ | 4483/11728 [3:41:41<11:49:23, 5.87s/it] {'loss': 0.5019, 'learning_rate': 1.4168532048540225e-05, 'epoch': 0.38} + 38%|███▊ | 4483/11728 [3:41:41<11:49:23, 5.87s/it] 38%|███▊ | 4484/11728 [3:41:46<11:42:46, 5.82s/it] {'loss': 0.5025, 'learning_rate': 1.4166021670317465e-05, 'epoch': 0.38} + 38%|███▊ | 4484/11728 [3:41:46<11:42:46, 5.82s/it] 38%|███▊ | 4485/11728 [3:41:52<11:51:29, 5.89s/it] {'loss': 0.4831, 'learning_rate': 1.4163510974376507e-05, 'epoch': 0.38} + 38%|███▊ | 4485/11728 [3:41:52<11:51:29, 5.89s/it] 38%|███▊ | 4486/11728 [3:41:58<11:46:40, 5.85s/it] {'loss': 0.4716, 'learning_rate': 1.4160999960908818e-05, 'epoch': 0.38} + 38%|███▊ | 4486/11728 [3:41:58<11:46:40, 5.85s/it] 38%|███▊ | 4487/11728 [3:42:04<11:44:59, 5.84s/it] {'loss': 0.5052, 'learning_rate': 1.4158488630105899e-05, 'epoch': 0.38} + 38%|███▊ | 4487/11728 [3:42:04<11:44:59, 5.84s/it] 38%|███▊ | 4488/11728 [3:42:10<11:41:57, 5.82s/it] {'loss': 0.4896, 'learning_rate': 1.415597698215928e-05, 'epoch': 0.38} + 38%|███▊ | 4488/11728 [3:42:10<11:41:57, 5.82s/it] 38%|███▊ | 4489/11728 [3:42:15<11:38:39, 5.79s/it] {'loss': 0.4702, 'learning_rate': 1.4153465017260504e-05, 'epoch': 0.38} + 38%|███▊ | 4489/11728 [3:42:15<11:38:39, 5.79s/it] 38%|███▊ | 4490/11728 [3:42:21<11:49:20, 5.88s/it] {'loss': 0.4665, 'learning_rate': 1.4150952735601143e-05, 'epoch': 0.38} + 38%|███▊ | 4490/11728 [3:42:21<11:49:20, 5.88s/it] 38%|███▊ | 4491/11728 [3:42:27<11:47:19, 5.86s/it] {'loss': 0.4865, 'learning_rate': 1.4148440137372799e-05, 'epoch': 0.38} + 38%|███▊ | 4491/11728 [3:42:27<11:47:19, 5.86s/it] 38%|███▊ | 4492/11728 [3:42:33<11:41:21, 5.82s/it] {'loss': 0.494, 'learning_rate': 1.414592722276709e-05, 'epoch': 0.38} + 38%|███▊ | 4492/11728 [3:42:33<11:41:21, 5.82s/it] 38%|███▊ | 4493/11728 [3:42:39<11:47:11, 5.86s/it] {'loss': 0.4633, 'learning_rate': 1.4143413991975663e-05, 'epoch': 0.38} + 38%|███▊ | 4493/11728 [3:42:39<11:47:11, 5.86s/it] 38%|███▊ | 4494/11728 [3:42:45<11:49:24, 5.88s/it] {'loss': 0.521, 'learning_rate': 1.4140900445190187e-05, 'epoch': 0.38} + 38%|███▊ | 4494/11728 [3:42:45<11:49:24, 5.88s/it] 38%|███▊ | 4495/11728 [3:42:50<11:37:08, 5.78s/it] {'loss': 0.4813, 'learning_rate': 1.4138386582602353e-05, 'epoch': 0.38} + 38%|███▊ | 4495/11728 [3:42:50<11:37:08, 5.78s/it] 38%|███▊ | 4496/11728 [3:42:56<11:37:34, 5.79s/it] {'loss': 0.4809, 'learning_rate': 1.4135872404403881e-05, 'epoch': 0.38} + 38%|███▊ | 4496/11728 [3:42:56<11:37:34, 5.79s/it] 38%|███▊ | 4497/11728 [3:43:02<11:32:23, 5.75s/it] {'loss': 0.4827, 'learning_rate': 1.4133357910786517e-05, 'epoch': 0.38} + 38%|███▊ | 4497/11728 [3:43:02<11:32:23, 5.75s/it] 38%|███▊ | 4498/11728 [3:43:08<11:47:40, 5.87s/it] {'loss': 0.4997, 'learning_rate': 1.4130843101942017e-05, 'epoch': 0.38} + 38%|███▊ | 4498/11728 [3:43:08<11:47:40, 5.87s/it] 38%|███▊ | 4499/11728 [3:43:14<11:56:57, 5.95s/it] {'loss': 0.4967, 'learning_rate': 1.412832797806218e-05, 'epoch': 0.38} + 38%|███▊ | 4499/11728 [3:43:14<11:56:57, 5.95s/it]4 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +27 AutoResumeHook: Checking whether to suspend...AutoResumeHook: Checking whether to suspend... + +5 AutoResumeHook: Checking whether to suspend... +06 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... + 38%|███▊ | 4500/11728 [3:43:20<11:54:12, 5.93s/it]3 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4881, 'learning_rate': 1.4125812539338814e-05, 'epoch': 0.38} + 38%|███▊ | 4500/11728 [3:43:20<11:54:12, 5.93s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-4500/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-4500/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-4500/mm_projector +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/torch/nn/modules/module.py:1802: UserWarning: Positional args are being deprecated, use kwargs instead. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details. + warnings.warn( + 38%|███▊ | 4501/11728 [3:43:53<28:18:02, 14.10s/it] {'loss': 0.4886, 'learning_rate': 1.412329678596376e-05, 'epoch': 0.38} + 38%|███▊ | 4501/11728 [3:43:53<28:18:02, 14.10s/it] 38%|███▊ | 4502/11728 [3:43:59<23:13:39, 11.57s/it] {'loss': 0.4564, 'learning_rate': 1.4120780718128879e-05, 'epoch': 0.38} + 38%|███▊ | 4502/11728 [3:43:59<23:13:39, 11.57s/it] 38%|███▊ | 4503/11728 [3:44:05<19:44:54, 9.84s/it] {'loss': 0.4866, 'learning_rate': 1.4118264336026057e-05, 'epoch': 0.38} + 38%|███▊ | 4503/11728 [3:44:05<19:44:54, 9.84s/it] 38%|███▊ | 4504/11728 [3:44:10<17:10:30, 8.56s/it] {'loss': 0.4756, 'learning_rate': 1.4115747639847204e-05, 'epoch': 0.38} + 38%|███▊ | 4504/11728 [3:44:10<17:10:30, 8.56s/it] 38%|███▊ | 4505/11728 [3:44:16<15:27:56, 7.71s/it] {'loss': 0.4915, 'learning_rate': 1.411323062978425e-05, 'epoch': 0.38} + 38%|███▊ | 4505/11728 [3:44:16<15:27:56, 7.71s/it] 38%|███▊ | 4506/11728 [3:44:22<14:15:01, 7.10s/it] {'loss': 0.4586, 'learning_rate': 1.4110713306029161e-05, 'epoch': 0.38} + 38%|███▊ | 4506/11728 [3:44:22<14:15:01, 7.10s/it] 38%|███▊ | 4507/11728 [3:44:28<13:31:27, 6.74s/it] {'loss': 0.4815, 'learning_rate': 1.410819566877391e-05, 'epoch': 0.38} + 38%|███▊ | 4507/11728 [3:44:28<13:31:27, 6.74s/it] 38%|███▊ | 4508/11728 [3:44:33<12:45:25, 6.36s/it] {'loss': 0.4905, 'learning_rate': 1.4105677718210506e-05, 'epoch': 0.38} + 38%|███▊ | 4508/11728 [3:44:33<12:45:25, 6.36s/it] 38%|███▊ | 4509/11728 [3:44:39<12:23:56, 6.18s/it] {'loss': 0.4889, 'learning_rate': 1.4103159454530982e-05, 'epoch': 0.38} + 38%|███▊ | 4509/11728 [3:44:39<12:23:56, 6.18s/it] 38%|███▊ | 4510/11728 [3:44:45<12:10:06, 6.07s/it] {'loss': 0.4974, 'learning_rate': 1.4100640877927383e-05, 'epoch': 0.38} + 38%|███▊ | 4510/11728 [3:44:45<12:10:06, 6.07s/it] 38%|███▊ | 4511/11728 [3:44:50<12:00:33, 5.99s/it] {'loss': 0.4797, 'learning_rate': 1.4098121988591796e-05, 'epoch': 0.38} + 38%|███▊ | 4511/11728 [3:44:50<12:00:33, 5.99s/it] 38%|███▊ | 4512/11728 [3:44:56<11:58:35, 5.98s/it] {'loss': 0.482, 'learning_rate': 1.4095602786716312e-05, 'epoch': 0.38} + 38%|███▊ | 4512/11728 [3:44:56<11:58:35, 5.98s/it] 38%|███▊ | 4513/11728 [3:45:02<11:54:46, 5.94s/it] {'loss': 0.494, 'learning_rate': 1.4093083272493061e-05, 'epoch': 0.38} + 38%|███▊ | 4513/11728 [3:45:02<11:54:46, 5.94s/it] 38%|███▊ | 4514/11728 [3:45:08<11:54:24, 5.94s/it] {'loss': 0.5172, 'learning_rate': 1.4090563446114195e-05, 'epoch': 0.38} + 38%|███▊ | 4514/11728 [3:45:08<11:54:24, 5.94s/it] 38%|███▊ | 4515/11728 [3:45:14<11:54:55, 5.95s/it] {'loss': 0.486, 'learning_rate': 1.4088043307771883e-05, 'epoch': 0.38} + 38%|███▊ | 4515/11728 [3:45:14<11:54:55, 5.95s/it] 39%|███▊ | 4516/11728 [3:45:20<11:38:15, 5.81s/it] {'loss': 0.471, 'learning_rate': 1.4085522857658321e-05, 'epoch': 0.39} + 39%|███▊ | 4516/11728 [3:45:20<11:38:15, 5.81s/it] 39%|███▊ | 4517/11728 [3:45:25<11:35:29, 5.79s/it] {'loss': 0.4894, 'learning_rate': 1.4083002095965727e-05, 'epoch': 0.39} + 39%|███▊ | 4517/11728 [3:45:25<11:35:29, 5.79s/it] 39%|███▊ | 4518/11728 [3:45:31<11:38:54, 5.82s/it] {'loss': 0.491, 'learning_rate': 1.4080481022886349e-05, 'epoch': 0.39} + 39%|███▊ | 4518/11728 [3:45:31<11:38:54, 5.82s/it] 39%|███▊ | 4519/11728 [3:45:37<11:43:25, 5.85s/it] {'loss': 0.472, 'learning_rate': 1.4077959638612451e-05, 'epoch': 0.39} + 39%|███▊ | 4519/11728 [3:45:37<11:43:25, 5.85s/it] 39%|███▊ | 4520/11728 [3:45:43<11:38:10, 5.81s/it] {'loss': 0.4687, 'learning_rate': 1.4075437943336328e-05, 'epoch': 0.39} + 39%|███▊ | 4520/11728 [3:45:43<11:38:10, 5.81s/it] 39%|███▊ | 4521/11728 [3:45:49<11:37:22, 5.81s/it] {'loss': 0.5033, 'learning_rate': 1.4072915937250294e-05, 'epoch': 0.39} + 39%|███▊ | 4521/11728 [3:45:49<11:37:22, 5.81s/it] 39%|███▊ | 4522/11728 [3:45:54<11:32:50, 5.77s/it] {'loss': 0.4654, 'learning_rate': 1.4070393620546684e-05, 'epoch': 0.39} + 39%|███▊ | 4522/11728 [3:45:54<11:32:50, 5.77s/it] 39%|███▊ | 4523/11728 [3:46:00<11:31:57, 5.76s/it] {'loss': 0.5024, 'learning_rate': 1.4067870993417863e-05, 'epoch': 0.39} + 39%|███▊ | 4523/11728 [3:46:00<11:31:57, 5.76s/it] 39%|███▊ | 4524/11728 [3:46:06<11:35:48, 5.80s/it] {'loss': 0.4825, 'learning_rate': 1.4065348056056219e-05, 'epoch': 0.39} + 39%|███▊ | 4524/11728 [3:46:06<11:35:48, 5.80s/it] 39%|███▊ | 4525/11728 [3:46:12<11:52:21, 5.93s/it] {'loss': 0.4901, 'learning_rate': 1.4062824808654158e-05, 'epoch': 0.39} + 39%|███▊ | 4525/11728 [3:46:12<11:52:21, 5.93s/it] 39%|███▊ | 4526/11728 [3:46:18<11:51:44, 5.93s/it] {'loss': 0.4977, 'learning_rate': 1.4060301251404116e-05, 'epoch': 0.39} + 39%|███▊ | 4526/11728 [3:46:18<11:51:44, 5.93s/it] 39%|███▊ | 4527/11728 [3:46:24<11:51:21, 5.93s/it] {'loss': 0.4783, 'learning_rate': 1.4057777384498551e-05, 'epoch': 0.39} + 39%|███▊ | 4527/11728 [3:46:24<11:51:21, 5.93s/it] 39%|███▊ | 4528/11728 [3:46:30<11:52:12, 5.94s/it] {'loss': 0.4708, 'learning_rate': 1.405525320812994e-05, 'epoch': 0.39} + 39%|███▊ | 4528/11728 [3:46:30<11:52:12, 5.94s/it] 39%|███▊ | 4529/11728 [3:46:36<11:49:22, 5.91s/it] {'loss': 0.4786, 'learning_rate': 1.405272872249079e-05, 'epoch': 0.39} + 39%|███▊ | 4529/11728 [3:46:36<11:49:22, 5.91s/it] 39%|███▊ | 4530/11728 [3:46:42<11:40:05, 5.84s/it] {'loss': 0.4817, 'learning_rate': 1.4050203927773627e-05, 'epoch': 0.39} + 39%|███▊ | 4530/11728 [3:46:42<11:40:05, 5.84s/it] 39%|███▊ | 4531/11728 [3:46:48<11:46:40, 5.89s/it] {'loss': 0.4951, 'learning_rate': 1.4047678824171005e-05, 'epoch': 0.39} + 39%|███▊ | 4531/11728 [3:46:48<11:46:40, 5.89s/it] 39%|███▊ | 4532/11728 [3:46:54<11:47:23, 5.90s/it] {'loss': 0.4807, 'learning_rate': 1.4045153411875497e-05, 'epoch': 0.39} + 39%|███▊ | 4532/11728 [3:46:54<11:47:23, 5.90s/it] 39%|███▊ | 4533/11728 [3:46:59<11:46:32, 5.89s/it] {'loss': 0.4849, 'learning_rate': 1.4042627691079701e-05, 'epoch': 0.39} + 39%|███▊ | 4533/11728 [3:46:59<11:46:32, 5.89s/it] 39%|███▊ | 4534/11728 [3:47:06<12:00:08, 6.01s/it] {'loss': 0.5022, 'learning_rate': 1.4040101661976239e-05, 'epoch': 0.39} + 39%|███▊ | 4534/11728 [3:47:06<12:00:08, 6.01s/it] 39%|███▊ | 4535/11728 [3:47:12<11:56:30, 5.98s/it] {'loss': 0.4907, 'learning_rate': 1.4037575324757759e-05, 'epoch': 0.39} + 39%|███▊ | 4535/11728 [3:47:12<11:56:30, 5.98s/it] 39%|███▊ | 4536/11728 [3:47:17<11:38:18, 5.83s/it] {'loss': 0.4671, 'learning_rate': 1.403504867961693e-05, 'epoch': 0.39} + 39%|███▊ | 4536/11728 [3:47:17<11:38:18, 5.83s/it] 39%|███▊ | 4537/11728 [3:47:23<11:44:31, 5.88s/it] {'loss': 0.4994, 'learning_rate': 1.4032521726746438e-05, 'epoch': 0.39} + 39%|███▊ | 4537/11728 [3:47:23<11:44:31, 5.88s/it] 39%|███▊ | 4538/11728 [3:47:29<11:39:41, 5.84s/it] {'loss': 0.4623, 'learning_rate': 1.4029994466339007e-05, 'epoch': 0.39} + 39%|███▊ | 4538/11728 [3:47:29<11:39:41, 5.84s/it] 39%|███▊ | 4539/11728 [3:47:34<11:34:38, 5.80s/it] {'loss': 0.464, 'learning_rate': 1.4027466898587375e-05, 'epoch': 0.39} + 39%|███▊ | 4539/11728 [3:47:34<11:34:38, 5.80s/it] 39%|███▊ | 4540/11728 [3:47:40<11:36:43, 5.82s/it] {'loss': 0.5021, 'learning_rate': 1.4024939023684298e-05, 'epoch': 0.39} + 39%|███▊ | 4540/11728 [3:47:40<11:36:43, 5.82s/it] 39%|███▊ | 4541/11728 [3:47:47<11:49:18, 5.92s/it] {'loss': 0.4946, 'learning_rate': 1.4022410841822574e-05, 'epoch': 0.39} + 39%|███▊ | 4541/11728 [3:47:47<11:49:18, 5.92s/it] 39%|███▊ | 4542/11728 [3:47:52<11:45:26, 5.89s/it] {'loss': 0.4858, 'learning_rate': 1.4019882353195002e-05, 'epoch': 0.39} + 39%|███▊ | 4542/11728 [3:47:52<11:45:26, 5.89s/it] 39%|███▊ | 4543/11728 [3:47:58<11:34:39, 5.80s/it] {'loss': 0.4913, 'learning_rate': 1.401735355799442e-05, 'epoch': 0.39} + 39%|███▊ | 4543/11728 [3:47:58<11:34:39, 5.80s/it] 39%|███▊ | 4544/11728 [3:48:04<11:31:15, 5.77s/it] {'loss': 0.4836, 'learning_rate': 1.401482445641368e-05, 'epoch': 0.39} + 39%|███▊ | 4544/11728 [3:48:04<11:31:15, 5.77s/it] 39%|███▉ | 4545/11728 [3:48:10<11:49:10, 5.92s/it] {'loss': 0.4983, 'learning_rate': 1.4012295048645672e-05, 'epoch': 0.39} + 39%|███▉ | 4545/11728 [3:48:10<11:49:10, 5.92s/it] 39%|███▉ | 4546/11728 [3:48:15<11:34:20, 5.80s/it] {'loss': 0.4779, 'learning_rate': 1.4009765334883287e-05, 'epoch': 0.39} + 39%|███▉ | 4546/11728 [3:48:15<11:34:20, 5.80s/it] 39%|███▉ | 4547/11728 [3:48:22<11:46:16, 5.90s/it] {'loss': 0.4883, 'learning_rate': 1.4007235315319463e-05, 'epoch': 0.39} + 39%|███▉ | 4547/11728 [3:48:22<11:46:16, 5.90s/it] 39%|███▉ | 4548/11728 [3:48:28<12:00:02, 6.02s/it] {'loss': 0.4861, 'learning_rate': 1.4004704990147142e-05, 'epoch': 0.39} + 39%|███▉ | 4548/11728 [3:48:28<12:00:02, 6.02s/it] 39%|███▉ | 4549/11728 [3:48:34<11:58:18, 6.00s/it] {'loss': 0.4824, 'learning_rate': 1.4002174359559298e-05, 'epoch': 0.39} + 39%|███▉ | 4549/11728 [3:48:34<11:58:18, 6.00s/it]4 AutoResumeHook: Checking whether to suspend... +27 1 AutoResumeHook: Checking whether to suspend...AutoResumeHook: Checking whether to suspend... + +AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... +03 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... + 39%|███▉ | 4550/11728 [3:48:40<11:55:09, 5.98s/it] {'loss': 0.5008, 'learning_rate': 1.399964342374893e-05, 'epoch': 0.39} + 39%|███▉ | 4550/11728 [3:48:40<11:55:09, 5.98s/it] 39%|███▉ | 4551/11728 [3:48:46<12:08:33, 6.09s/it] {'loss': 0.503, 'learning_rate': 1.3997112182909053e-05, 'epoch': 0.39} + 39%|███▉ | 4551/11728 [3:48:46<12:08:33, 6.09s/it] 39%|███▉ | 4552/11728 [3:48:52<11:56:15, 5.99s/it] {'loss': 0.5086, 'learning_rate': 1.3994580637232717e-05, 'epoch': 0.39} + 39%|███▉ | 4552/11728 [3:48:52<11:56:15, 5.99s/it] 39%|███▉ | 4553/11728 [3:48:58<11:51:40, 5.95s/it] {'loss': 0.4877, 'learning_rate': 1.3992048786912984e-05, 'epoch': 0.39} + 39%|███▉ | 4553/11728 [3:48:58<11:51:40, 5.95s/it] 39%|███▉ | 4554/11728 [3:49:04<11:54:28, 5.98s/it] {'loss': 0.4833, 'learning_rate': 1.3989516632142946e-05, 'epoch': 0.39} + 39%|███▉ | 4554/11728 [3:49:04<11:54:28, 5.98s/it] 39%|███▉ | 4555/11728 [3:49:09<11:44:08, 5.89s/it] {'loss': 0.4638, 'learning_rate': 1.3986984173115709e-05, 'epoch': 0.39} + 39%|███▉ | 4555/11728 [3:49:09<11:44:08, 5.89s/it] 39%|███▉ | 4556/11728 [3:49:15<11:46:16, 5.91s/it] {'loss': 0.4678, 'learning_rate': 1.398445141002442e-05, 'epoch': 0.39} + 39%|███▉ | 4556/11728 [3:49:15<11:46:16, 5.91s/it] 39%|███▉ | 4557/11728 [3:49:22<11:57:39, 6.00s/it] {'loss': 0.4829, 'learning_rate': 1.398191834306223e-05, 'epoch': 0.39} + 39%|███▉ | 4557/11728 [3:49:22<11:57:39, 6.00s/it] 39%|███▉ | 4558/11728 [3:49:27<11:46:07, 5.91s/it] {'loss': 0.4961, 'learning_rate': 1.397938497242232e-05, 'epoch': 0.39} + 39%|███▉ | 4558/11728 [3:49:27<11:46:07, 5.91s/it] 39%|███▉ | 4559/11728 [3:49:33<11:44:39, 5.90s/it] {'loss': 0.4826, 'learning_rate': 1.3976851298297902e-05, 'epoch': 0.39} + 39%|███▉ | 4559/11728 [3:49:33<11:44:39, 5.90s/it] 39%|███▉ | 4560/11728 [3:49:39<11:32:02, 5.79s/it] {'loss': 0.4939, 'learning_rate': 1.39743173208822e-05, 'epoch': 0.39} + 39%|███▉ | 4560/11728 [3:49:39<11:32:02, 5.79s/it] 39%|███▉ | 4561/11728 [3:49:44<11:24:13, 5.73s/it] {'loss': 0.4796, 'learning_rate': 1.3971783040368465e-05, 'epoch': 0.39} + 39%|███▉ | 4561/11728 [3:49:44<11:24:13, 5.73s/it] 39%|███▉ | 4562/11728 [3:49:50<11:38:00, 5.84s/it] {'loss': 0.4819, 'learning_rate': 1.3969248456949975e-05, 'epoch': 0.39} + 39%|███▉ | 4562/11728 [3:49:50<11:38:00, 5.84s/it] 39%|███▉ | 4563/11728 [3:49:56<11:46:05, 5.91s/it] {'loss': 0.4951, 'learning_rate': 1.3966713570820028e-05, 'epoch': 0.39} + 39%|███▉ | 4563/11728 [3:49:56<11:46:05, 5.91s/it] 39%|███▉ | 4564/11728 [3:50:03<11:56:37, 6.00s/it] {'loss': 0.4883, 'learning_rate': 1.3964178382171942e-05, 'epoch': 0.39} + 39%|███▉ | 4564/11728 [3:50:03<11:56:37, 6.00s/it] 39%|███▉ | 4565/11728 [3:50:08<11:39:52, 5.86s/it] {'loss': 0.4988, 'learning_rate': 1.3961642891199063e-05, 'epoch': 0.39} + 39%|███▉ | 4565/11728 [3:50:08<11:39:52, 5.86s/it] 39%|███▉ | 4566/11728 [3:50:14<11:41:52, 5.88s/it] {'loss': 0.4742, 'learning_rate': 1.3959107098094758e-05, 'epoch': 0.39} + 39%|███▉ | 4566/11728 [3:50:14<11:41:52, 5.88s/it] 39%|███▉ | 4567/11728 [3:50:20<11:37:25, 5.84s/it] {'loss': 0.474, 'learning_rate': 1.3956571003052416e-05, 'epoch': 0.39} + 39%|███▉ | 4567/11728 [3:50:20<11:37:25, 5.84s/it] 39%|███▉ | 4568/11728 [3:50:26<11:38:40, 5.85s/it] {'loss': 0.4725, 'learning_rate': 1.3954034606265452e-05, 'epoch': 0.39} + 39%|███▉ | 4568/11728 [3:50:26<11:38:40, 5.85s/it] 39%|███▉ | 4569/11728 [3:50:31<11:29:41, 5.78s/it] {'loss': 0.488, 'learning_rate': 1.39514979079273e-05, 'epoch': 0.39} + 39%|███▉ | 4569/11728 [3:50:31<11:29:41, 5.78s/it] 39%|███▉ | 4570/11728 [3:50:37<11:33:50, 5.82s/it] {'loss': 0.493, 'learning_rate': 1.3948960908231422e-05, 'epoch': 0.39} + 39%|███▉ | 4570/11728 [3:50:37<11:33:50, 5.82s/it] 39%|███▉ | 4571/11728 [3:50:43<11:22:18, 5.72s/it] {'loss': 0.4928, 'learning_rate': 1.3946423607371298e-05, 'epoch': 0.39} + 39%|███▉ | 4571/11728 [3:50:43<11:22:18, 5.72s/it] 39%|███▉ | 4572/11728 [3:50:48<11:19:58, 5.70s/it] {'loss': 0.4888, 'learning_rate': 1.3943886005540436e-05, 'epoch': 0.39} + 39%|███▉ | 4572/11728 [3:50:48<11:19:58, 5.70s/it] 39%|███▉ | 4573/11728 [3:50:55<11:36:46, 5.84s/it] {'loss': 0.4999, 'learning_rate': 1.394134810293236e-05, 'epoch': 0.39} + 39%|███▉ | 4573/11728 [3:50:55<11:36:46, 5.84s/it] 39%|███▉ | 4574/11728 [3:51:01<11:41:52, 5.89s/it] {'loss': 0.4565, 'learning_rate': 1.3938809899740622e-05, 'epoch': 0.39} + 39%|███▉ | 4574/11728 [3:51:01<11:41:52, 5.89s/it] 39%|███▉ | 4575/11728 [3:51:07<11:44:40, 5.91s/it] {'loss': 0.4858, 'learning_rate': 1.3936271396158798e-05, 'epoch': 0.39} + 39%|███▉ | 4575/11728 [3:51:07<11:44:40, 5.91s/it] 39%|███▉ | 4576/11728 [3:51:12<11:35:03, 5.83s/it] {'loss': 0.4879, 'learning_rate': 1.3933732592380485e-05, 'epoch': 0.39} + 39%|███▉ | 4576/11728 [3:51:12<11:35:03, 5.83s/it] 39%|███▉ | 4577/11728 [3:51:18<11:28:53, 5.78s/it] {'loss': 0.4873, 'learning_rate': 1.3931193488599301e-05, 'epoch': 0.39} + 39%|███▉ | 4577/11728 [3:51:18<11:28:53, 5.78s/it] 39%|███▉ | 4578/11728 [3:51:24<11:28:58, 5.78s/it] {'loss': 0.4896, 'learning_rate': 1.3928654085008887e-05, 'epoch': 0.39} + 39%|███▉ | 4578/11728 [3:51:24<11:28:58, 5.78s/it] 39%|███▉ | 4579/11728 [3:51:29<11:25:55, 5.76s/it] {'loss': 0.5055, 'learning_rate': 1.3926114381802915e-05, 'epoch': 0.39} + 39%|███▉ | 4579/11728 [3:51:29<11:25:55, 5.76s/it] 39%|███▉ | 4580/11728 [3:51:35<11:23:56, 5.74s/it] {'loss': 0.4847, 'learning_rate': 1.3923574379175068e-05, 'epoch': 0.39} + 39%|███▉ | 4580/11728 [3:51:35<11:23:56, 5.74s/it] 39%|███▉ | 4581/11728 [3:51:41<11:26:09, 5.76s/it] {'loss': 0.4963, 'learning_rate': 1.3921034077319057e-05, 'epoch': 0.39} + 39%|███▉ | 4581/11728 [3:51:41<11:26:09, 5.76s/it] 39%|███▉ | 4582/11728 [3:51:47<11:21:49, 5.72s/it] {'loss': 0.485, 'learning_rate': 1.3918493476428618e-05, 'epoch': 0.39} + 39%|███▉ | 4582/11728 [3:51:47<11:21:49, 5.72s/it] 39%|███▉ | 4583/11728 [3:51:53<11:34:49, 5.83s/it] {'loss': 0.4743, 'learning_rate': 1.3915952576697507e-05, 'epoch': 0.39} + 39%|███▉ | 4583/11728 [3:51:53<11:34:49, 5.83s/it] 39%|███▉ | 4584/11728 [3:51:58<11:22:47, 5.73s/it] {'loss': 0.4865, 'learning_rate': 1.3913411378319503e-05, 'epoch': 0.39} + 39%|███▉ | 4584/11728 [3:51:58<11:22:47, 5.73s/it] 39%|███▉ | 4585/11728 [3:52:04<11:24:38, 5.75s/it] {'loss': 0.4739, 'learning_rate': 1.391086988148841e-05, 'epoch': 0.39} + 39%|███▉ | 4585/11728 [3:52:04<11:24:38, 5.75s/it] 39%|███▉ | 4586/11728 [3:52:10<11:25:20, 5.76s/it] {'loss': 0.4952, 'learning_rate': 1.3908328086398055e-05, 'epoch': 0.39} + 39%|███▉ | 4586/11728 [3:52:10<11:25:20, 5.76s/it] 39%|███▉ | 4587/11728 [3:52:16<11:33:03, 5.82s/it] {'loss': 0.4671, 'learning_rate': 1.3905785993242283e-05, 'epoch': 0.39} + 39%|███▉ | 4587/11728 [3:52:16<11:33:03, 5.82s/it] 39%|███▉ | 4588/11728 [3:52:22<11:40:48, 5.89s/it] {'loss': 0.4878, 'learning_rate': 1.390324360221496e-05, 'epoch': 0.39} + 39%|███▉ | 4588/11728 [3:52:22<11:40:48, 5.89s/it] 39%|███▉ | 4589/11728 [3:52:27<11:35:24, 5.84s/it] {'loss': 0.4679, 'learning_rate': 1.3900700913509991e-05, 'epoch': 0.39} + 39%|███▉ | 4589/11728 [3:52:27<11:35:24, 5.84s/it] 39%|███▉ | 4590/11728 [3:52:33<11:38:12, 5.87s/it] {'loss': 0.4738, 'learning_rate': 1.3898157927321278e-05, 'epoch': 0.39} + 39%|███▉ | 4590/11728 [3:52:33<11:38:12, 5.87s/it] 39%|███▉ | 4591/11728 [3:52:39<11:31:23, 5.81s/it] {'loss': 0.5035, 'learning_rate': 1.3895614643842773e-05, 'epoch': 0.39} + 39%|███▉ | 4591/11728 [3:52:39<11:31:23, 5.81s/it] 39%|███▉ | 4592/11728 [3:52:45<11:50:36, 5.97s/it] {'loss': 0.4829, 'learning_rate': 1.3893071063268431e-05, 'epoch': 0.39} + 39%|███▉ | 4592/11728 [3:52:45<11:50:36, 5.97s/it] 39%|███▉ | 4593/11728 [3:52:51<11:45:09, 5.93s/it] {'loss': 0.4692, 'learning_rate': 1.3890527185792233e-05, 'epoch': 0.39} + 39%|███▉ | 4593/11728 [3:52:51<11:45:09, 5.93s/it] 39%|███▉ | 4594/11728 [3:52:57<11:51:17, 5.98s/it] {'loss': 0.4741, 'learning_rate': 1.3887983011608192e-05, 'epoch': 0.39} + 39%|███▉ | 4594/11728 [3:52:57<11:51:17, 5.98s/it] 39%|███▉ | 4595/11728 [3:53:03<11:49:20, 5.97s/it] {'loss': 0.4941, 'learning_rate': 1.3885438540910336e-05, 'epoch': 0.39} + 39%|███▉ | 4595/11728 [3:53:03<11:49:20, 5.97s/it] 39%|███▉ | 4596/11728 [3:53:09<11:39:47, 5.89s/it] {'loss': 0.4859, 'learning_rate': 1.3882893773892714e-05, 'epoch': 0.39} + 39%|███▉ | 4596/11728 [3:53:09<11:39:47, 5.89s/it] 39%|███▉ | 4597/11728 [3:53:14<11:24:06, 5.76s/it] {'loss': 0.4976, 'learning_rate': 1.3880348710749401e-05, 'epoch': 0.39} + 39%|███▉ | 4597/11728 [3:53:14<11:24:06, 5.76s/it] 39%|███▉ | 4598/11728 [3:53:20<11:24:31, 5.76s/it] {'loss': 0.4843, 'learning_rate': 1.3877803351674498e-05, 'epoch': 0.39} + 39%|███▉ | 4598/11728 [3:53:20<11:24:31, 5.76s/it] 39%|███▉ | 4599/11728 [3:53:26<11:29:56, 5.81s/it] {'loss': 0.4949, 'learning_rate': 1.3875257696862118e-05, 'epoch': 0.39} + 39%|███▉ | 4599/11728 [3:53:26<11:29:56, 5.81s/it]1 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... +03 AutoResumeHook: Checking whether to suspend... +AutoResumeHook: Checking whether to suspend... + 39%|███▉ | 4600/11728 [3:53:32<11:37:17, 5.87s/it] {'loss': 0.4927, 'learning_rate': 1.3872711746506413e-05, 'epoch': 0.39} + 39%|███▉ | 4600/11728 [3:53:32<11:37:17, 5.87s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-4600/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-4600/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-4600/mm_projector +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/torch/nn/modules/module.py:1802: UserWarning: Positional args are being deprecated, use kwargs instead. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details. + warnings.warn( + 39%|███▉ | 4601/11728 [3:54:05<27:43:30, 14.00s/it] {'loss': 0.4798, 'learning_rate': 1.3870165500801538e-05, 'epoch': 0.39} + 39%|███▉ | 4601/11728 [3:54:05<27:43:30, 14.00s/it] 39%|███▉ | 4602/11728 [3:54:11<22:43:13, 11.48s/it] {'loss': 0.4743, 'learning_rate': 1.3867618959941684e-05, 'epoch': 0.39} + 39%|███▉ | 4602/11728 [3:54:11<22:43:13, 11.48s/it] 39%|███▉ | 4603/11728 [3:54:16<19:10:25, 9.69s/it] {'loss': 0.469, 'learning_rate': 1.3865072124121066e-05, 'epoch': 0.39} + 39%|███▉ | 4603/11728 [3:54:16<19:10:25, 9.69s/it] 39%|███▉ | 4604/11728 [3:54:22<16:52:31, 8.53s/it] {'loss': 0.5138, 'learning_rate': 1.3862524993533908e-05, 'epoch': 0.39} + 39%|███▉ | 4604/11728 [3:54:22<16:52:31, 8.53s/it] 39%|███▉ | 4605/11728 [3:54:28<15:10:51, 7.67s/it] {'loss': 0.4756, 'learning_rate': 1.3859977568374468e-05, 'epoch': 0.39} + 39%|███▉ | 4605/11728 [3:54:28<15:10:51, 7.67s/it] 39%|███▉ | 4606/11728 [3:54:34<14:06:29, 7.13s/it] {'loss': 0.4753, 'learning_rate': 1.3857429848837022e-05, 'epoch': 0.39} + 39%|███▉ | 4606/11728 [3:54:34<14:06:29, 7.13s/it] 39%|███▉ | 4607/11728 [3:54:39<13:12:28, 6.68s/it] {'loss': 0.4986, 'learning_rate': 1.3854881835115878e-05, 'epoch': 0.39} + 39%|███▉ | 4607/11728 [3:54:39<13:12:28, 6.68s/it] 39%|███▉ | 4608/11728 [3:54:45<12:38:43, 6.39s/it] {'loss': 0.4735, 'learning_rate': 1.3852333527405346e-05, 'epoch': 0.39} + 39%|███▉ | 4608/11728 [3:54:45<12:38:43, 6.39s/it] 39%|███▉ | 4609/11728 [3:54:51<12:14:18, 6.19s/it] {'loss': 0.4806, 'learning_rate': 1.3849784925899779e-05, 'epoch': 0.39} + 39%|███▉ | 4609/11728 [3:54:51<12:14:18, 6.19s/it] 39%|███▉ | 4610/11728 [3:54:56<11:48:29, 5.97s/it] {'loss': 0.4817, 'learning_rate': 1.3847236030793538e-05, 'epoch': 0.39} + 39%|███▉ | 4610/11728 [3:54:56<11:48:29, 5.97s/it] 39%|███▉ | 4611/11728 [3:55:02<11:36:56, 5.88s/it] {'loss': 0.474, 'learning_rate': 1.384468684228102e-05, 'epoch': 0.39} + 39%|███▉ | 4611/11728 [3:55:02<11:36:56, 5.88s/it] 39%|███▉ | 4612/11728 [3:55:08<11:46:17, 5.96s/it] {'loss': 0.5034, 'learning_rate': 1.3842137360556629e-05, 'epoch': 0.39} + 39%|███▉ | 4612/11728 [3:55:08<11:46:17, 5.96s/it] 39%|███▉ | 4613/11728 [3:55:14<11:48:28, 5.97s/it] {'loss': 0.4824, 'learning_rate': 1.3839587585814801e-05, 'epoch': 0.39} + 39%|███▉ | 4613/11728 [3:55:14<11:48:28, 5.97s/it] 39%|███▉ | 4614/11728 [3:55:20<11:43:37, 5.93s/it] {'loss': 0.4836, 'learning_rate': 1.3837037518249998e-05, 'epoch': 0.39} + 39%|███▉ | 4614/11728 [3:55:20<11:43:37, 5.93s/it] 39%|███▉ | 4615/11728 [3:55:25<11:36:15, 5.87s/it] {'loss': 0.5047, 'learning_rate': 1.3834487158056692e-05, 'epoch': 0.39} + 39%|███▉ | 4615/11728 [3:55:25<11:36:15, 5.87s/it] 39%|███▉ | 4616/11728 [3:55:31<11:28:22, 5.81s/it] {'loss': 0.4856, 'learning_rate': 1.383193650542939e-05, 'epoch': 0.39} + 39%|███▉ | 4616/11728 [3:55:31<11:28:22, 5.81s/it] 39%|███▉ | 4617/11728 [3:55:37<11:24:36, 5.78s/it] {'loss': 0.4951, 'learning_rate': 1.3829385560562607e-05, 'epoch': 0.39} + 39%|███▉ | 4617/11728 [3:55:37<11:24:36, 5.78s/it] 39%|███▉ | 4618/11728 [3:55:42<11:13:46, 5.69s/it] {'loss': 0.4892, 'learning_rate': 1.3826834323650899e-05, 'epoch': 0.39} + 39%|███▉ | 4618/11728 [3:55:42<11:13:46, 5.69s/it] 39%|███▉ | 4619/11728 [3:55:48<11:28:24, 5.81s/it] {'loss': 0.4749, 'learning_rate': 1.3824282794888828e-05, 'epoch': 0.39} + 39%|███▉ | 4619/11728 [3:55:48<11:28:24, 5.81s/it] 39%|███▉ | 4620/11728 [3:55:55<11:40:02, 5.91s/it] {'loss': 0.488, 'learning_rate': 1.3821730974470981e-05, 'epoch': 0.39} + 39%|███▉ | 4620/11728 [3:55:55<11:40:02, 5.91s/it] 39%|███▉ | 4621/11728 [3:56:00<11:38:59, 5.90s/it] {'loss': 0.4923, 'learning_rate': 1.3819178862591982e-05, 'epoch': 0.39} + 39%|███▉ | 4621/11728 [3:56:00<11:38:59, 5.90s/it] 39%|███▉ | 4622/11728 [3:56:06<11:44:06, 5.95s/it] {'loss': 0.4946, 'learning_rate': 1.3816626459446451e-05, 'epoch': 0.39} + 39%|███▉ | 4622/11728 [3:56:06<11:44:06, 5.95s/it] 39%|███▉ | 4623/11728 [3:56:12<11:35:35, 5.87s/it] {'loss': 0.5082, 'learning_rate': 1.3814073765229056e-05, 'epoch': 0.39} + 39%|███▉ | 4623/11728 [3:56:12<11:35:35, 5.87s/it] 39%|███▉ | 4624/11728 [3:56:18<11:41:06, 5.92s/it] {'loss': 0.4922, 'learning_rate': 1.3811520780134471e-05, 'epoch': 0.39} + 39%|███▉ | 4624/11728 [3:56:18<11:41:06, 5.92s/it] 39%|███▉ | 4625/11728 [3:56:24<11:38:26, 5.90s/it] {'loss': 0.4894, 'learning_rate': 1.3808967504357402e-05, 'epoch': 0.39} + 39%|███▉ | 4625/11728 [3:56:24<11:38:26, 5.90s/it] 39%|███▉ | 4626/11728 [3:56:30<11:37:41, 5.89s/it] {'loss': 0.4776, 'learning_rate': 1.3806413938092566e-05, 'epoch': 0.39} + 39%|███▉ | 4626/11728 [3:56:30<11:37:41, 5.89s/it] 39%|███▉ | 4627/11728 [3:56:36<11:29:39, 5.83s/it] {'loss': 0.4812, 'learning_rate': 1.380386008153471e-05, 'epoch': 0.39} + 39%|███▉ | 4627/11728 [3:56:36<11:29:39, 5.83s/it] 39%|███▉ | 4628/11728 [3:56:42<11:49:12, 5.99s/it] {'loss': 0.4935, 'learning_rate': 1.3801305934878609e-05, 'epoch': 0.39} + 39%|███▉ | 4628/11728 [3:56:42<11:49:12, 5.99s/it] 39%|███▉ | 4629/11728 [3:56:48<11:43:53, 5.95s/it] {'loss': 0.4598, 'learning_rate': 1.379875149831904e-05, 'epoch': 0.39} + 39%|███▉ | 4629/11728 [3:56:48<11:43:53, 5.95s/it] 39%|███▉ | 4630/11728 [3:56:54<11:50:53, 6.01s/it] {'loss': 0.4775, 'learning_rate': 1.3796196772050829e-05, 'epoch': 0.39} + 39%|███▉ | 4630/11728 [3:56:54<11:50:53, 6.01s/it] 39%|███▉ | 4631/11728 [3:57:00<11:37:25, 5.90s/it] {'loss': 0.4932, 'learning_rate': 1.3793641756268801e-05, 'epoch': 0.39} + 39%|███▉ | 4631/11728 [3:57:00<11:37:25, 5.90s/it] 39%|███▉ | 4632/11728 [3:57:05<11:34:16, 5.87s/it] {'loss': 0.4948, 'learning_rate': 1.3791086451167814e-05, 'epoch': 0.39} + 39%|███▉ | 4632/11728 [3:57:05<11:34:16, 5.87s/it] 40%|███▉ | 4633/11728 [3:57:11<11:24:38, 5.79s/it] {'loss': 0.4785, 'learning_rate': 1.3788530856942747e-05, 'epoch': 0.4} + 40%|███▉ | 4633/11728 [3:57:11<11:24:38, 5.79s/it] 40%|███▉ | 4634/11728 [3:57:17<11:23:51, 5.78s/it] {'loss': 0.4758, 'learning_rate': 1.3785974973788506e-05, 'epoch': 0.4} + 40%|███▉ | 4634/11728 [3:57:17<11:23:51, 5.78s/it] 40%|███▉ | 4635/11728 [3:57:23<11:39:36, 5.92s/it] {'loss': 0.5048, 'learning_rate': 1.3783418801900001e-05, 'epoch': 0.4} + 40%|███▉ | 4635/11728 [3:57:23<11:39:36, 5.92s/it] 40%|███▉ | 4636/11728 [3:57:29<11:39:02, 5.91s/it] {'loss': 0.4925, 'learning_rate': 1.3780862341472183e-05, 'epoch': 0.4} + 40%|███▉ | 4636/11728 [3:57:29<11:39:02, 5.91s/it] 40%|███▉ | 4637/11728 [3:57:35<11:32:36, 5.86s/it] {'loss': 0.4798, 'learning_rate': 1.3778305592700023e-05, 'epoch': 0.4} + 40%|███▉ | 4637/11728 [3:57:35<11:32:36, 5.86s/it] 40%|███▉ | 4638/11728 [3:57:40<11:27:51, 5.82s/it] {'loss': 0.4853, 'learning_rate': 1.3775748555778497e-05, 'epoch': 0.4} + 40%|███▉ | 4638/11728 [3:57:40<11:27:51, 5.82s/it]Jun 27 19:15:46.456641 3037871 slurmstepd 0x155550a06700: error: *** STEP 9369369.0 ON batch-block7-01179 CANCELLED AT 2025-06-27T19:15:46 DUE TO TIME LIMIT *** +srun: Job step aborted: Waiting up to 122 seconds for job step to finish. +srun: error: batch-block7-01179: task 0: Terminated +srun: Terminating StepId=9369369.0 +srun: job 9373138 queued and waiting for resources +srun: job 9373138 has been allocated resources +wandb: Currently logged in as: memmelma. Use `wandb login --relogin` to force relogin +MASTER_ADDR=batch-block4-2008 +JobID: 9373138 | Full list: batch-block4-2008 +NETWORK=Efficient-Large-Model/VILA1.5-3b +WARNING:torch.distributed.run: +***************************************** +Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed. +***************************************** +Did not find AutoResume SDK! +Did not find AutoResume SDK! +Did not find AutoResume SDK! +Did not find AutoResume SDK! +Did not find AutoResume SDK! +Did not find AutoResume SDK! +Did not find AutoResume SDK! +Did not find AutoResume SDK! +[2025-06-27 19:18:19,291] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-27 19:18:19,291] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-27 19:18:19,291] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-27 19:18:19,291] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-27 19:18:19,291] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-27 19:18:19,291] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-27 19:18:19,291] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-27 19:18:19,291] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-27 19:18:21,574] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-27 19:18:21,574] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-27 19:18:21,574] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-27 19:18:21,574] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-27 19:18:21,574] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-27 19:18:21,574] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-27 19:18:21,574] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-27 19:18:21,574] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-27 19:18:21,574] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-27 19:18:21,574] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-27 19:18:21,574] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-27 19:18:21,574] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-27 19:18:21,574] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-27 19:18:21,574] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-27 19:18:21,574] [INFO] [comm.py:625:init_distributed] Initializing TorchBackend in DeepSpeed with backend nccl +[2025-06-27 19:18:21,574] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-27 19:18:21,574] [INFO] [comm.py:594:init_distributed] cdb=None +You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`. +You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`. +You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`. +You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`. +You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`. +You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`. +You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`. +You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`. +[2025-06-27 19:18:32,352] [INFO] [partition_parameters.py:453:__exit__] finished initializing model with 2.70B parameters + Loading checkpoint shards: 0%| | 0/2 [00:00 4096). Running this sequence through the model will result in indexing errors + 45%|████▌ | 5312/11728 [1:11:52<10:43:06, 6.01s/it] {'loss': 0.4576, 'learning_rate': 1.1996926623091839e-05, 'epoch': 0.45} + 45%|████▌ | 5312/11728 [1:11:52<10:43:06, 6.01s/it] 45%|████▌ | 5313/11728 [1:11:57<10:34:52, 5.94s/it] {'loss': 0.4559, 'learning_rate': 1.1994220572539545e-05, 'epoch': 0.45} + 45%|████▌ | 5313/11728 [1:11:57<10:34:52, 5.94s/it] 45%|████▌ | 5314/11728 [1:12:03<10:29:40, 5.89s/it] {'loss': 0.4869, 'learning_rate': 1.1991514369899668e-05, 'epoch': 0.45} + 45%|████▌ | 5314/11728 [1:12:03<10:29:40, 5.89s/it] 45%|████▌ | 5315/11728 [1:12:09<10:18:29, 5.79s/it] {'loss': 0.4785, 'learning_rate': 1.1988808015378591e-05, 'epoch': 0.45} + 45%|████▌ | 5315/11728 [1:12:09<10:18:29, 5.79s/it] 45%|████▌ | 5316/11728 [1:12:14<10:14:52, 5.75s/it] {'loss': 0.4779, 'learning_rate': 1.198610150918271e-05, 'epoch': 0.45} + 45%|████▌ | 5316/11728 [1:12:14<10:14:52, 5.75s/it] 45%|████▌ | 5317/11728 [1:12:20<10:17:26, 5.78s/it] {'loss': 0.4831, 'learning_rate': 1.1983394851518435e-05, 'epoch': 0.45} + 45%|████▌ | 5317/11728 [1:12:20<10:17:26, 5.78s/it] 45%|████▌ | 5318/11728 [1:12:26<10:28:36, 5.88s/it] {'loss': 0.4924, 'learning_rate': 1.1980688042592192e-05, 'epoch': 0.45} + 45%|████▌ | 5318/11728 [1:12:26<10:28:36, 5.88s/it] 45%|████▌ | 5319/11728 [1:12:32<10:15:11, 5.76s/it] {'loss': 0.4654, 'learning_rate': 1.1977981082610406e-05, 'epoch': 0.45} + 45%|████▌ | 5319/11728 [1:12:32<10:15:11, 5.76s/it] 45%|████▌ | 5320/11728 [1:12:38<10:21:44, 5.82s/it] {'loss': 0.4428, 'learning_rate': 1.1975273971779528e-05, 'epoch': 0.45} + 45%|████▌ | 5320/11728 [1:12:38<10:21:44, 5.82s/it] 45%|████▌ | 5321/11728 [1:12:44<10:27:21, 5.88s/it] {'loss': 0.4799, 'learning_rate': 1.1972566710306009e-05, 'epoch': 0.45} + 45%|████▌ | 5321/11728 [1:12:44<10:27:21, 5.88s/it] 45%|████▌ | 5322/11728 [1:12:50<10:25:19, 5.86s/it] {'loss': 0.4704, 'learning_rate': 1.1969859298396317e-05, 'epoch': 0.45} + 45%|████▌ | 5322/11728 [1:12:50<10:25:19, 5.86s/it] 45%|████▌ | 5323/11728 [1:12:55<10:16:21, 5.77s/it] {'loss': 0.4747, 'learning_rate': 1.1967151736256932e-05, 'epoch': 0.45} + 45%|████▌ | 5323/11728 [1:12:55<10:16:21, 5.77s/it] 45%|████▌ | 5324/11728 [1:13:01<10:19:48, 5.81s/it] {'loss': 0.5067, 'learning_rate': 1.1964444024094344e-05, 'epoch': 0.45} + 45%|████▌ | 5324/11728 [1:13:01<10:19:48, 5.81s/it] 45%|████▌ | 5325/11728 [1:13:07<10:14:13, 5.76s/it] {'loss': 0.5017, 'learning_rate': 1.196173616211505e-05, 'epoch': 0.45} + 45%|████▌ | 5325/11728 [1:13:07<10:14:13, 5.76s/it] 45%|████▌ | 5326/11728 [1:13:12<10:09:45, 5.71s/it] {'loss': 0.4818, 'learning_rate': 1.195902815052557e-05, 'epoch': 0.45} + 45%|████▌ | 5326/11728 [1:13:12<10:09:45, 5.71s/it] 45%|████▌ | 5327/11728 [1:13:18<10:14:32, 5.76s/it] {'loss': 0.4796, 'learning_rate': 1.1956319989532422e-05, 'epoch': 0.45} + 45%|████▌ | 5327/11728 [1:13:18<10:14:32, 5.76s/it]/lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/VILA/llava/model/llava_arch.py:397: UserWarning: Inputs truncated! + warnings.warn("Inputs truncated!") + 45%|████▌ | 5328/11728 [1:13:24<10:22:04, 5.83s/it] {'loss': 0.4995, 'learning_rate': 1.1953611679342144e-05, 'epoch': 0.45} + 45%|████▌ | 5328/11728 [1:13:24<10:22:04, 5.83s/it] 45%|████▌ | 5329/11728 [1:13:30<10:18:51, 5.80s/it] {'loss': 0.4829, 'learning_rate': 1.1950903220161286e-05, 'epoch': 0.45} + 45%|████▌ | 5329/11728 [1:13:30<10:18:51, 5.80s/it] 45%|████▌ | 5330/11728 [1:13:36<10:15:19, 5.77s/it] {'loss': 0.5035, 'learning_rate': 1.1948194612196402e-05, 'epoch': 0.45} + 45%|████▌ | 5330/11728 [1:13:36<10:15:19, 5.77s/it] 45%|████▌ | 5331/11728 [1:13:41<10:14:58, 5.77s/it] {'loss': 0.4865, 'learning_rate': 1.194548585565406e-05, 'epoch': 0.45} + 45%|████▌ | 5331/11728 [1:13:41<10:14:58, 5.77s/it] 45%|████▌ | 5332/11728 [1:13:47<10:12:12, 5.74s/it] {'loss': 0.4846, 'learning_rate': 1.1942776950740849e-05, 'epoch': 0.45} + 45%|████▌ | 5332/11728 [1:13:47<10:12:12, 5.74s/it] 45%|████▌ | 5333/11728 [1:13:53<10:09:27, 5.72s/it] {'loss': 0.4734, 'learning_rate': 1.1940067897663355e-05, 'epoch': 0.45} + 45%|████▌ | 5333/11728 [1:13:53<10:09:27, 5.72s/it] 45%|████▌ | 5334/11728 [1:13:58<10:07:40, 5.70s/it] {'loss': 0.4831, 'learning_rate': 1.1937358696628185e-05, 'epoch': 0.45} + 45%|████▌ | 5334/11728 [1:13:58<10:07:40, 5.70s/it] 45%|████▌ | 5335/11728 [1:14:04<10:17:27, 5.79s/it] {'loss': 0.4863, 'learning_rate': 1.193464934784195e-05, 'epoch': 0.45} + 45%|████▌ | 5335/11728 [1:14:04<10:17:27, 5.79s/it] 45%|████▌ | 5336/11728 [1:14:10<10:18:16, 5.80s/it] {'loss': 0.5031, 'learning_rate': 1.1931939851511283e-05, 'epoch': 0.45} + 45%|████▌ | 5336/11728 [1:14:10<10:18:16, 5.80s/it] 46%|████▌ | 5337/11728 [1:14:16<10:16:27, 5.79s/it] {'loss': 0.488, 'learning_rate': 1.1929230207842815e-05, 'epoch': 0.46} + 46%|████▌ | 5337/11728 [1:14:16<10:16:27, 5.79s/it] 46%|████▌ | 5338/11728 [1:14:22<10:20:19, 5.82s/it] {'loss': 0.4849, 'learning_rate': 1.1926520417043195e-05, 'epoch': 0.46} + 46%|████▌ | 5338/11728 [1:14:22<10:20:19, 5.82s/it] 46%|████▌ | 5339/11728 [1:14:28<10:17:06, 5.80s/it] {'loss': 0.476, 'learning_rate': 1.1923810479319089e-05, 'epoch': 0.46} + 46%|████▌ | 5339/11728 [1:14:28<10:17:06, 5.80s/it] 46%|████▌ | 5340/11728 [1:14:33<10:11:04, 5.74s/it] {'loss': 0.471, 'learning_rate': 1.1921100394877158e-05, 'epoch': 0.46} + 46%|████▌ | 5340/11728 [1:14:33<10:11:04, 5.74s/it] 46%|████▌ | 5341/11728 [1:14:39<10:11:50, 5.75s/it] {'loss': 0.4909, 'learning_rate': 1.1918390163924098e-05, 'epoch': 0.46} + 46%|████▌ | 5341/11728 [1:14:39<10:11:50, 5.75s/it] 46%|████▌ | 5342/11728 [1:14:45<10:05:36, 5.69s/it] {'loss': 0.4677, 'learning_rate': 1.1915679786666592e-05, 'epoch': 0.46} + 46%|████▌ | 5342/11728 [1:14:45<10:05:36, 5.69s/it] 46%|████▌ | 5343/11728 [1:14:51<10:22:48, 5.85s/it] {'loss': 0.4979, 'learning_rate': 1.1912969263311345e-05, 'epoch': 0.46} + 46%|████▌ | 5343/11728 [1:14:51<10:22:48, 5.85s/it] 46%|████▌ | 5344/11728 [1:14:56<10:14:48, 5.78s/it] {'loss': 0.464, 'learning_rate': 1.1910258594065079e-05, 'epoch': 0.46} + 46%|████▌ | 5344/11728 [1:14:56<10:14:48, 5.78s/it] 46%|████▌ | 5345/11728 [1:15:02<10:08:02, 5.72s/it] {'loss': 0.486, 'learning_rate': 1.1907547779134518e-05, 'epoch': 0.46} + 46%|████▌ | 5345/11728 [1:15:02<10:08:02, 5.72s/it] 46%|████▌ | 5346/11728 [1:15:08<10:14:45, 5.78s/it] {'loss': 0.4877, 'learning_rate': 1.1904836818726397e-05, 'epoch': 0.46} + 46%|████▌ | 5346/11728 [1:15:08<10:14:45, 5.78s/it] 46%|████▌ | 5347/11728 [1:15:14<10:14:06, 5.77s/it] {'loss': 0.4732, 'learning_rate': 1.1902125713047467e-05, 'epoch': 0.46} + 46%|████▌ | 5347/11728 [1:15:14<10:14:06, 5.77s/it] 46%|████▌ | 5348/11728 [1:15:19<10:07:17, 5.71s/it] {'loss': 0.469, 'learning_rate': 1.1899414462304496e-05, 'epoch': 0.46} + 46%|████▌ | 5348/11728 [1:15:19<10:07:17, 5.71s/it] 46%|████▌ | 5349/11728 [1:15:25<10:03:03, 5.67s/it] {'loss': 0.4561, 'learning_rate': 1.1896703066704238e-05, 'epoch': 0.46} + 46%|████▌ | 5349/11728 [1:15:25<10:03:03, 5.67s/it]2 AutoResumeHook: Checking whether to suspend... +04 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... + 46%|████▌ | 5350/11728 [1:15:31<10:03:42, 5.68s/it]5 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4831, 'learning_rate': 1.1893991526453493e-05, 'epoch': 0.46} + 46%|████▌ | 5350/11728 [1:15:31<10:03:42, 5.68s/it] 46%|████▌ | 5351/11728 [1:15:37<10:13:25, 5.77s/it] {'loss': 0.4953, 'learning_rate': 1.1891279841759044e-05, 'epoch': 0.46} + 46%|████▌ | 5351/11728 [1:15:37<10:13:25, 5.77s/it] 46%|████▌ | 5352/11728 [1:15:43<10:18:53, 5.82s/it] {'loss': 0.4627, 'learning_rate': 1.18885680128277e-05, 'epoch': 0.46} + 46%|████▌ | 5352/11728 [1:15:43<10:18:53, 5.82s/it] 46%|████▌ | 5353/11728 [1:15:48<10:21:38, 5.85s/it] {'loss': 0.498, 'learning_rate': 1.1885856039866275e-05, 'epoch': 0.46} + 46%|████▌ | 5353/11728 [1:15:48<10:21:38, 5.85s/it] 46%|████▌ | 5354/11728 [1:15:54<10:18:22, 5.82s/it] {'loss': 0.4707, 'learning_rate': 1.1883143923081592e-05, 'epoch': 0.46} + 46%|████▌ | 5354/11728 [1:15:54<10:18:22, 5.82s/it] 46%|████▌ | 5355/11728 [1:16:00<10:07:00, 5.71s/it] {'loss': 0.4781, 'learning_rate': 1.1880431662680494e-05, 'epoch': 0.46} + 46%|████▌ | 5355/11728 [1:16:00<10:07:00, 5.71s/it] 46%|████▌ | 5356/11728 [1:16:05<9:57:37, 5.63s/it] {'loss': 0.4689, 'learning_rate': 1.1877719258869827e-05, 'epoch': 0.46} + 46%|████▌ | 5356/11728 [1:16:05<9:57:37, 5.63s/it] 46%|████▌ | 5357/11728 [1:16:11<10:06:15, 5.71s/it] {'loss': 0.4966, 'learning_rate': 1.1875006711856452e-05, 'epoch': 0.46} + 46%|████▌ | 5357/11728 [1:16:11<10:06:15, 5.71s/it] 46%|████▌ | 5358/11728 [1:16:17<10:09:44, 5.74s/it] {'loss': 0.4923, 'learning_rate': 1.1872294021847231e-05, 'epoch': 0.46} + 46%|████▌ | 5358/11728 [1:16:17<10:09:44, 5.74s/it] 46%|████▌ | 5359/11728 [1:16:22<10:07:29, 5.72s/it] {'loss': 0.4654, 'learning_rate': 1.1869581189049057e-05, 'epoch': 0.46} + 46%|████▌ | 5359/11728 [1:16:22<10:07:29, 5.72s/it] 46%|████▌ | 5360/11728 [1:16:28<10:16:36, 5.81s/it] {'loss': 0.4936, 'learning_rate': 1.1866868213668813e-05, 'epoch': 0.46} + 46%|████▌ | 5360/11728 [1:16:28<10:16:36, 5.81s/it] 46%|████▌ | 5361/11728 [1:16:34<10:09:24, 5.74s/it] {'loss': 0.502, 'learning_rate': 1.1864155095913407e-05, 'epoch': 0.46} + 46%|████▌ | 5361/11728 [1:16:34<10:09:24, 5.74s/it] 46%|████▌ | 5362/11728 [1:16:40<10:09:44, 5.75s/it] {'loss': 0.4798, 'learning_rate': 1.1861441835989754e-05, 'epoch': 0.46} + 46%|████▌ | 5362/11728 [1:16:40<10:09:44, 5.75s/it] 46%|████▌ | 5363/11728 [1:16:45<10:03:44, 5.69s/it] {'loss': 0.467, 'learning_rate': 1.1858728434104769e-05, 'epoch': 0.46} + 46%|████▌ | 5363/11728 [1:16:45<10:03:44, 5.69s/it] 46%|████▌ | 5364/11728 [1:16:51<10:03:58, 5.69s/it] {'loss': 0.4784, 'learning_rate': 1.1856014890465396e-05, 'epoch': 0.46} + 46%|████▌ | 5364/11728 [1:16:51<10:03:58, 5.69s/it] 46%|████▌ | 5365/11728 [1:16:57<10:12:32, 5.78s/it] {'loss': 0.4778, 'learning_rate': 1.1853301205278579e-05, 'epoch': 0.46} + 46%|████▌ | 5365/11728 [1:16:57<10:12:32, 5.78s/it] 46%|████▌ | 5366/11728 [1:17:03<10:03:47, 5.69s/it] {'loss': 0.4733, 'learning_rate': 1.1850587378751274e-05, 'epoch': 0.46} + 46%|████▌ | 5366/11728 [1:17:03<10:03:47, 5.69s/it] 46%|████▌ | 5367/11728 [1:17:08<9:59:42, 5.66s/it] {'loss': 0.5015, 'learning_rate': 1.184787341109045e-05, 'epoch': 0.46} + 46%|████▌ | 5367/11728 [1:17:08<9:59:42, 5.66s/it] 46%|████▌ | 5368/11728 [1:17:14<9:58:49, 5.65s/it] {'loss': 0.4649, 'learning_rate': 1.1845159302503086e-05, 'epoch': 0.46} + 46%|████▌ | 5368/11728 [1:17:14<9:58:49, 5.65s/it] 46%|████▌ | 5369/11728 [1:17:19<9:59:22, 5.66s/it] {'loss': 0.4803, 'learning_rate': 1.184244505319617e-05, 'epoch': 0.46} + 46%|████▌ | 5369/11728 [1:17:19<9:59:22, 5.66s/it]Token indices sequence length is longer than the specified maximum sequence length for this model (5158 > 4096). Running this sequence through the model will result in indexing errors + 46%|████▌ | 5370/11728 [1:17:25<9:59:21, 5.66s/it] {'loss': 0.4946, 'learning_rate': 1.18397306633767e-05, 'epoch': 0.46} + 46%|████▌ | 5370/11728 [1:17:25<9:59:21, 5.66s/it] 46%|████▌ | 5371/11728 [1:17:31<10:01:50, 5.68s/it] {'loss': 0.4693, 'learning_rate': 1.1837016133251695e-05, 'epoch': 0.46} + 46%|████▌ | 5371/11728 [1:17:31<10:01:50, 5.68s/it] 46%|████▌ | 5372/11728 [1:17:37<10:06:26, 5.72s/it] {'loss': 0.4811, 'learning_rate': 1.1834301463028166e-05, 'epoch': 0.46} + 46%|████▌ | 5372/11728 [1:17:37<10:06:26, 5.72s/it] 46%|████▌ | 5373/11728 [1:17:42<10:10:01, 5.76s/it] {'loss': 0.4797, 'learning_rate': 1.1831586652913147e-05, 'epoch': 0.46} + 46%|████▌ | 5373/11728 [1:17:42<10:10:01, 5.76s/it] 46%|████▌ | 5374/11728 [1:17:48<10:09:29, 5.76s/it] {'loss': 0.4794, 'learning_rate': 1.1828871703113686e-05, 'epoch': 0.46} + 46%|████▌ | 5374/11728 [1:17:48<10:09:29, 5.76s/it] 46%|████▌ | 5375/11728 [1:17:54<10:05:58, 5.72s/it] {'loss': 0.4615, 'learning_rate': 1.1826156613836835e-05, 'epoch': 0.46} + 46%|████▌ | 5375/11728 [1:17:54<10:05:58, 5.72s/it] 46%|████▌ | 5376/11728 [1:17:59<9:58:48, 5.66s/it] {'loss': 0.4812, 'learning_rate': 1.1823441385289656e-05, 'epoch': 0.46} + 46%|████▌ | 5376/11728 [1:17:59<9:58:48, 5.66s/it] 46%|████▌ | 5377/11728 [1:18:05<10:12:41, 5.79s/it] {'loss': 0.4821, 'learning_rate': 1.1820726017679222e-05, 'epoch': 0.46} + 46%|████▌ | 5377/11728 [1:18:05<10:12:41, 5.79s/it] 46%|████▌ | 5378/11728 [1:18:11<10:13:32, 5.80s/it] {'loss': 0.4888, 'learning_rate': 1.1818010511212624e-05, 'epoch': 0.46} + 46%|████▌ | 5378/11728 [1:18:11<10:13:32, 5.80s/it] 46%|████▌ | 5379/11728 [1:18:17<10:09:20, 5.76s/it] {'loss': 0.4973, 'learning_rate': 1.181529486609695e-05, 'epoch': 0.46} + 46%|████▌ | 5379/11728 [1:18:17<10:09:20, 5.76s/it] 46%|████▌ | 5380/11728 [1:18:23<10:04:32, 5.71s/it] {'loss': 0.468, 'learning_rate': 1.1812579082539317e-05, 'epoch': 0.46} + 46%|████▌ | 5380/11728 [1:18:23<10:04:32, 5.71s/it] 46%|████▌ | 5381/11728 [1:18:28<10:07:24, 5.74s/it] {'loss': 0.4945, 'learning_rate': 1.180986316074683e-05, 'epoch': 0.46} + 46%|████▌ | 5381/11728 [1:18:28<10:07:24, 5.74s/it] 46%|████▌ | 5382/11728 [1:18:34<10:09:18, 5.76s/it] {'loss': 0.4886, 'learning_rate': 1.1807147100926626e-05, 'epoch': 0.46} + 46%|████▌ | 5382/11728 [1:18:34<10:09:18, 5.76s/it] 46%|████▌ | 5383/11728 [1:18:40<10:05:17, 5.72s/it] {'loss': 0.4783, 'learning_rate': 1.1804430903285837e-05, 'epoch': 0.46} + 46%|████▌ | 5383/11728 [1:18:40<10:05:17, 5.72s/it] 46%|████▌ | 5384/11728 [1:18:46<10:11:57, 5.79s/it] {'loss': 0.4909, 'learning_rate': 1.1801714568031615e-05, 'epoch': 0.46} + 46%|████▌ | 5384/11728 [1:18:46<10:11:57, 5.79s/it] 46%|████▌ | 5385/11728 [1:18:51<10:06:57, 5.74s/it] {'loss': 0.473, 'learning_rate': 1.1798998095371119e-05, 'epoch': 0.46} + 46%|████▌ | 5385/11728 [1:18:51<10:06:57, 5.74s/it] 46%|████▌ | 5386/11728 [1:18:57<10:13:52, 5.81s/it] {'loss': 0.4936, 'learning_rate': 1.1796281485511519e-05, 'epoch': 0.46} + 46%|████▌ | 5386/11728 [1:18:57<10:13:52, 5.81s/it] 46%|████▌ | 5387/11728 [1:19:03<10:13:31, 5.81s/it] {'loss': 0.4731, 'learning_rate': 1.1793564738659988e-05, 'epoch': 0.46} + 46%|████▌ | 5387/11728 [1:19:03<10:13:31, 5.81s/it] 46%|████▌ | 5388/11728 [1:19:09<10:16:30, 5.83s/it] {'loss': 0.4825, 'learning_rate': 1.1790847855023727e-05, 'epoch': 0.46} + 46%|████▌ | 5388/11728 [1:19:09<10:16:30, 5.83s/it] 46%|████▌ | 5389/11728 [1:19:15<10:08:48, 5.76s/it] {'loss': 0.4743, 'learning_rate': 1.1788130834809932e-05, 'epoch': 0.46} + 46%|████▌ | 5389/11728 [1:19:15<10:08:48, 5.76s/it] 46%|████▌ | 5390/11728 [1:19:21<10:17:30, 5.85s/it] {'loss': 0.4848, 'learning_rate': 1.178541367822581e-05, 'epoch': 0.46} + 46%|████▌ | 5390/11728 [1:19:21<10:17:30, 5.85s/it] 46%|████▌ | 5391/11728 [1:19:27<10:23:25, 5.90s/it] {'loss': 0.4619, 'learning_rate': 1.1782696385478593e-05, 'epoch': 0.46} + 46%|████▌ | 5391/11728 [1:19:27<10:23:25, 5.90s/it] 46%|████▌ | 5392/11728 [1:19:32<10:17:03, 5.84s/it] {'loss': 0.4866, 'learning_rate': 1.1779978956775507e-05, 'epoch': 0.46} + 46%|████▌ | 5392/11728 [1:19:32<10:17:03, 5.84s/it] 46%|████▌ | 5393/11728 [1:19:38<10:06:26, 5.74s/it] {'loss': 0.4843, 'learning_rate': 1.1777261392323789e-05, 'epoch': 0.46} + 46%|████▌ | 5393/11728 [1:19:38<10:06:26, 5.74s/it] 46%|████▌ | 5394/11728 [1:19:44<10:12:30, 5.80s/it] {'loss': 0.4741, 'learning_rate': 1.17745436923307e-05, 'epoch': 0.46} + 46%|████▌ | 5394/11728 [1:19:44<10:12:30, 5.80s/it] 46%|████▌ | 5395/11728 [1:19:50<10:13:28, 5.81s/it] {'loss': 0.4986, 'learning_rate': 1.17718258570035e-05, 'epoch': 0.46} + 46%|████▌ | 5395/11728 [1:19:50<10:13:28, 5.81s/it] 46%|████▌ | 5396/11728 [1:19:56<10:15:47, 5.83s/it] {'loss': 0.4614, 'learning_rate': 1.1769107886549465e-05, 'epoch': 0.46} + 46%|████▌ | 5396/11728 [1:19:56<10:15:47, 5.83s/it] 46%|████▌ | 5397/11728 [1:20:01<10:15:27, 5.83s/it] {'loss': 0.4716, 'learning_rate': 1.1766389781175876e-05, 'epoch': 0.46} + 46%|████▌ | 5397/11728 [1:20:01<10:15:27, 5.83s/it] 46%|████▌ | 5398/11728 [1:20:07<10:14:47, 5.83s/it] {'loss': 0.4846, 'learning_rate': 1.1763671541090027e-05, 'epoch': 0.46} + 46%|████▌ | 5398/11728 [1:20:07<10:14:47, 5.83s/it] 46%|████▌ | 5399/11728 [1:20:13<10:06:48, 5.75s/it] {'loss': 0.4808, 'learning_rate': 1.1760953166499221e-05, 'epoch': 0.46} + 46%|████▌ | 5399/11728 [1:20:13<10:06:48, 5.75s/it]2 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +054 AutoResumeHook: Checking whether to suspend... +AutoResumeHook: Checking whether to suspend... +AutoResumeHook: Checking whether to suspend... + 46%|████▌ | 5400/11728 [1:20:19<10:09:57, 5.78s/it]6 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4841, 'learning_rate': 1.1758234657610778e-05, 'epoch': 0.46} + 46%|████▌ | 5400/11728 [1:20:19<10:09:57, 5.78s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-5400/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-5400/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-5400/mm_projector +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/torch/nn/modules/module.py:1802: UserWarning: Positional args are being deprecated, use kwargs instead. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details. + warnings.warn( + 46%|████▌ | 5401/11728 [1:20:50<23:36:34, 13.43s/it] {'loss': 0.5047, 'learning_rate': 1.1755516014632023e-05, 'epoch': 0.46} + 46%|████▌ | 5401/11728 [1:20:50<23:36:34, 13.43s/it] 46%|████▌ | 5402/11728 [1:20:56<19:37:04, 11.16s/it] {'loss': 0.4813, 'learning_rate': 1.1752797237770279e-05, 'epoch': 0.46} + 46%|████▌ | 5402/11728 [1:20:56<19:37:04, 11.16s/it] 46%|████▌ | 5403/11728 [1:21:02<16:47:44, 9.56s/it] {'loss': 0.4736, 'learning_rate': 1.1750078327232908e-05, 'epoch': 0.46} + 46%|████▌ | 5403/11728 [1:21:02<16:47:44, 9.56s/it] 46%|████▌ | 5404/11728 [1:21:07<14:49:43, 8.44s/it] {'loss': 0.4669, 'learning_rate': 1.1747359283227251e-05, 'epoch': 0.46} + 46%|████▌ | 5404/11728 [1:21:07<14:49:43, 8.44s/it] 46%|████▌ | 5405/11728 [1:21:13<13:19:22, 7.59s/it] {'loss': 0.4718, 'learning_rate': 1.1744640105960683e-05, 'epoch': 0.46} + 46%|████▌ | 5405/11728 [1:21:13<13:19:22, 7.59s/it] 46%|████▌ | 5406/11728 [1:21:19<12:16:51, 6.99s/it] {'loss': 0.4925, 'learning_rate': 1.1741920795640578e-05, 'epoch': 0.46} + 46%|████▌ | 5406/11728 [1:21:19<12:16:51, 6.99s/it] 46%|████▌ | 5407/11728 [1:21:24<11:36:59, 6.62s/it] {'loss': 0.4518, 'learning_rate': 1.1739201352474322e-05, 'epoch': 0.46} + 46%|████▌ | 5407/11728 [1:21:24<11:36:59, 6.62s/it] 46%|████▌ | 5408/11728 [1:21:30<11:00:28, 6.27s/it] {'loss': 0.4872, 'learning_rate': 1.1736481776669307e-05, 'epoch': 0.46} + 46%|████▌ | 5408/11728 [1:21:30<11:00:28, 6.27s/it] 46%|████▌ | 5409/11728 [1:21:36<10:42:56, 6.10s/it] {'loss': 0.5035, 'learning_rate': 1.173376206843294e-05, 'epoch': 0.46} + 46%|████▌ | 5409/11728 [1:21:36<10:42:56, 6.10s/it] 46%|████▌ | 5410/11728 [1:21:41<10:26:11, 5.95s/it] {'loss': 0.473, 'learning_rate': 1.1731042227972645e-05, 'epoch': 0.46} + 46%|████▌ | 5410/11728 [1:21:41<10:26:11, 5.95s/it] 46%|████▌ | 5411/11728 [1:21:47<10:15:55, 5.85s/it] {'loss': 0.4834, 'learning_rate': 1.1728322255495836e-05, 'epoch': 0.46} + 46%|████▌ | 5411/11728 [1:21:47<10:15:55, 5.85s/it] 46%|████▌ | 5412/11728 [1:21:53<10:11:45, 5.81s/it] {'loss': 0.4818, 'learning_rate': 1.1725602151209962e-05, 'epoch': 0.46} + 46%|████▌ | 5412/11728 [1:21:53<10:11:45, 5.81s/it] 46%|████▌ | 5413/11728 [1:21:58<10:10:39, 5.80s/it] {'loss': 0.5011, 'learning_rate': 1.1722881915322462e-05, 'epoch': 0.46} + 46%|████▌ | 5413/11728 [1:21:58<10:10:39, 5.80s/it] 46%|████▌ | 5414/11728 [1:22:04<10:11:42, 5.81s/it] {'loss': 0.4643, 'learning_rate': 1.1720161548040793e-05, 'epoch': 0.46} + 46%|████▌ | 5414/11728 [1:22:04<10:11:42, 5.81s/it] 46%|████▌ | 5415/11728 [1:22:10<10:04:41, 5.75s/it] {'loss': 0.4882, 'learning_rate': 1.1717441049572427e-05, 'epoch': 0.46} + 46%|████▌ | 5415/11728 [1:22:10<10:04:41, 5.75s/it] 46%|████▌ | 5416/11728 [1:22:16<10:08:36, 5.79s/it] {'loss': 0.4793, 'learning_rate': 1.1714720420124833e-05, 'epoch': 0.46} + 46%|████▌ | 5416/11728 [1:22:16<10:08:36, 5.79s/it] 46%|████▌ | 5417/11728 [1:22:22<10:17:05, 5.87s/it] {'loss': 0.4704, 'learning_rate': 1.17119996599055e-05, 'epoch': 0.46} + 46%|████▌ | 5417/11728 [1:22:22<10:17:05, 5.87s/it] 46%|████▌ | 5418/11728 [1:22:27<10:06:20, 5.77s/it] {'loss': 0.4833, 'learning_rate': 1.1709278769121928e-05, 'epoch': 0.46} + 46%|████▌ | 5418/11728 [1:22:27<10:06:20, 5.77s/it] 46%|████▌ | 5419/11728 [1:22:33<9:58:26, 5.69s/it] {'loss': 0.4757, 'learning_rate': 1.1706557747981622e-05, 'epoch': 0.46} + 46%|████▌ | 5419/11728 [1:22:33<9:58:26, 5.69s/it] 46%|████▌ | 5420/11728 [1:22:39<10:06:56, 5.77s/it] {'loss': 0.4915, 'learning_rate': 1.1703836596692094e-05, 'epoch': 0.46} + 46%|████▌ | 5420/11728 [1:22:39<10:06:56, 5.77s/it] 46%|████▌ | 5421/11728 [1:22:45<10:12:11, 5.82s/it] {'loss': 0.4924, 'learning_rate': 1.1701115315460875e-05, 'epoch': 0.46} + 46%|████▌ | 5421/11728 [1:22:45<10:12:11, 5.82s/it] 46%|████▌ | 5422/11728 [1:22:51<10:22:10, 5.92s/it] {'loss': 0.4657, 'learning_rate': 1.16983939044955e-05, 'epoch': 0.46} + 46%|████▌ | 5422/11728 [1:22:51<10:22:10, 5.92s/it] 46%|████▌ | 5423/11728 [1:22:57<10:17:38, 5.88s/it] {'loss': 0.4985, 'learning_rate': 1.1695672364003516e-05, 'epoch': 0.46} + 46%|████▌ | 5423/11728 [1:22:57<10:17:38, 5.88s/it] 46%|████▌ | 5424/11728 [1:23:02<10:14:56, 5.85s/it] {'loss': 0.4988, 'learning_rate': 1.169295069419248e-05, 'epoch': 0.46} + 46%|████▌ | 5424/11728 [1:23:02<10:14:56, 5.85s/it] 46%|████▋ | 5425/11728 [1:23:08<10:20:57, 5.91s/it] {'loss': 0.5054, 'learning_rate': 1.1690228895269953e-05, 'epoch': 0.46} + 46%|████▋ | 5425/11728 [1:23:08<10:20:57, 5.91s/it] 46%|████▋ | 5426/11728 [1:23:14<10:16:10, 5.87s/it] {'loss': 0.4675, 'learning_rate': 1.1687506967443516e-05, 'epoch': 0.46} + 46%|████▋ | 5426/11728 [1:23:14<10:16:10, 5.87s/it] 46%|████▋ | 5427/11728 [1:23:20<10:14:28, 5.85s/it] {'loss': 0.471, 'learning_rate': 1.168478491092075e-05, 'epoch': 0.46} + 46%|████▋ | 5427/11728 [1:23:20<10:14:28, 5.85s/it] 46%|████▋ | 5428/11728 [1:23:26<10:24:42, 5.95s/it] {'loss': 0.5117, 'learning_rate': 1.1682062725909257e-05, 'epoch': 0.46} + 46%|████▋ | 5428/11728 [1:23:26<10:24:42, 5.95s/it] 46%|████▋ | 5429/11728 [1:23:32<10:20:41, 5.91s/it] {'loss': 0.4814, 'learning_rate': 1.1679340412616633e-05, 'epoch': 0.46} + 46%|████▋ | 5429/11728 [1:23:32<10:20:41, 5.91s/it] 46%|████▋ | 5430/11728 [1:23:38<10:23:19, 5.94s/it] {'loss': 0.4549, 'learning_rate': 1.1676617971250504e-05, 'epoch': 0.46} + 46%|████▋ | 5430/11728 [1:23:38<10:23:19, 5.94s/it] 46%|████▋ | 5431/11728 [1:23:44<10:17:59, 5.89s/it] {'loss': 0.4818, 'learning_rate': 1.1673895402018484e-05, 'epoch': 0.46} + 46%|████▋ | 5431/11728 [1:23:44<10:17:59, 5.89s/it] 46%|████▋ | 5432/11728 [1:23:49<10:13:29, 5.85s/it] {'loss': 0.4868, 'learning_rate': 1.1671172705128216e-05, 'epoch': 0.46} + 46%|████▋ | 5432/11728 [1:23:49<10:13:29, 5.85s/it] 46%|████▋ | 5433/11728 [1:23:55<10:13:52, 5.85s/it] {'loss': 0.4668, 'learning_rate': 1.1668449880787338e-05, 'epoch': 0.46} + 46%|████▋ | 5433/11728 [1:23:55<10:13:52, 5.85s/it] 46%|████▋ | 5434/11728 [1:24:01<10:03:31, 5.75s/it] {'loss': 0.4625, 'learning_rate': 1.1665726929203509e-05, 'epoch': 0.46} + 46%|████▋ | 5434/11728 [1:24:01<10:03:31, 5.75s/it] 46%|████▋ | 5435/11728 [1:24:07<10:13:10, 5.85s/it] {'loss': 0.4778, 'learning_rate': 1.1663003850584387e-05, 'epoch': 0.46} + 46%|████▋ | 5435/11728 [1:24:07<10:13:10, 5.85s/it] 46%|████▋ | 5436/11728 [1:24:13<10:19:44, 5.91s/it] {'loss': 0.4708, 'learning_rate': 1.166028064513765e-05, 'epoch': 0.46} + 46%|████▋ | 5436/11728 [1:24:13<10:19:44, 5.91s/it] 46%|████▋ | 5437/11728 [1:24:19<10:10:39, 5.82s/it] {'loss': 0.4788, 'learning_rate': 1.165755731307098e-05, 'epoch': 0.46} + 46%|████▋ | 5437/11728 [1:24:19<10:10:39, 5.82s/it] 46%|████▋ | 5438/11728 [1:24:24<10:04:42, 5.77s/it] {'loss': 0.484, 'learning_rate': 1.1654833854592067e-05, 'epoch': 0.46} + 46%|████▋ | 5438/11728 [1:24:24<10:04:42, 5.77s/it] 46%|████▋ | 5439/11728 [1:24:30<10:16:14, 5.88s/it] {'loss': 0.4788, 'learning_rate': 1.1652110269908618e-05, 'epoch': 0.46} + 46%|████▋ | 5439/11728 [1:24:30<10:16:14, 5.88s/it] 46%|████▋ | 5440/11728 [1:24:36<10:01:59, 5.74s/it] {'loss': 0.4546, 'learning_rate': 1.1649386559228342e-05, 'epoch': 0.46} + 46%|████▋ | 5440/11728 [1:24:36<10:01:59, 5.74s/it] 46%|████▋ | 5441/11728 [1:24:42<10:01:06, 5.74s/it] {'loss': 0.4895, 'learning_rate': 1.1646662722758961e-05, 'epoch': 0.46} + 46%|████▋ | 5441/11728 [1:24:42<10:01:06, 5.74s/it] 46%|████▋ | 5442/11728 [1:24:47<10:03:17, 5.76s/it] {'loss': 0.4755, 'learning_rate': 1.1643938760708207e-05, 'epoch': 0.46} + 46%|████▋ | 5442/11728 [1:24:47<10:03:17, 5.76s/it] 46%|████▋ | 5443/11728 [1:24:53<9:56:16, 5.69s/it] {'loss': 0.4876, 'learning_rate': 1.1641214673283818e-05, 'epoch': 0.46} + 46%|████▋ | 5443/11728 [1:24:53<9:56:16, 5.69s/it] 46%|████▋ | 5444/11728 [1:24:59<9:57:16, 5.70s/it] {'loss': 0.4713, 'learning_rate': 1.1638490460693546e-05, 'epoch': 0.46} + 46%|████▋ | 5444/11728 [1:24:59<9:57:16, 5.70s/it] 46%|████▋ | 5445/11728 [1:25:04<9:51:56, 5.65s/it] {'loss': 0.4917, 'learning_rate': 1.1635766123145151e-05, 'epoch': 0.46} + 46%|████▋ | 5445/11728 [1:25:04<9:51:56, 5.65s/it] 46%|████▋ | 5446/11728 [1:25:10<9:56:50, 5.70s/it] {'loss': 0.4667, 'learning_rate': 1.1633041660846405e-05, 'epoch': 0.46} + 46%|████▋ | 5446/11728 [1:25:10<9:56:50, 5.70s/it] 46%|████▋ | 5447/11728 [1:25:16<10:07:37, 5.80s/it] {'loss': 0.4812, 'learning_rate': 1.1630317074005082e-05, 'epoch': 0.46} + 46%|████▋ | 5447/11728 [1:25:16<10:07:37, 5.80s/it] 46%|████▋ | 5448/11728 [1:25:22<10:15:36, 5.88s/it] {'loss': 0.4897, 'learning_rate': 1.1627592362828972e-05, 'epoch': 0.46} + 46%|████▋ | 5448/11728 [1:25:22<10:15:36, 5.88s/it] 46%|████▋ | 5449/11728 [1:25:28<10:13:11, 5.86s/it] {'loss': 0.448, 'learning_rate': 1.1624867527525876e-05, 'epoch': 0.46} + 46%|████▋ | 5449/11728 [1:25:28<10:13:11, 5.86s/it]2 AutoResumeHook: Checking whether to suspend... +0 7 AutoResumeHook: Checking whether to suspend... +AutoResumeHook: Checking whether to suspend... + 46%|████▋ | 5450/11728 [1:25:34<10:10:46, 5.84s/it]1 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... + {'loss': 0.5137, 'learning_rate': 1.1622142568303596e-05, 'epoch': 0.46} + 46%|████▋ | 5450/11728 [1:25:34<10:10:46, 5.84s/it] 46%|████▋ | 5451/11728 [1:25:39<10:06:51, 5.80s/it] {'loss': 0.4571, 'learning_rate': 1.1619417485369954e-05, 'epoch': 0.46} + 46%|████▋ | 5451/11728 [1:25:39<10:06:51, 5.80s/it] 46%|████▋ | 5452/11728 [1:25:45<10:09:08, 5.82s/it] {'loss': 0.4825, 'learning_rate': 1.1616692278932772e-05, 'epoch': 0.46} + 46%|████▋ | 5452/11728 [1:25:45<10:09:08, 5.82s/it] 46%|████▋ | 5453/11728 [1:25:51<10:12:38, 5.86s/it] {'loss': 0.4535, 'learning_rate': 1.1613966949199886e-05, 'epoch': 0.46} + 46%|████▋ | 5453/11728 [1:25:51<10:12:38, 5.86s/it] 47%|████▋ | 5454/11728 [1:25:57<10:04:13, 5.78s/it] {'loss': 0.4777, 'learning_rate': 1.1611241496379144e-05, 'epoch': 0.47} + 47%|████▋ | 5454/11728 [1:25:57<10:04:13, 5.78s/it] 47%|████▋ | 5455/11728 [1:26:02<9:57:26, 5.71s/it] {'loss': 0.4902, 'learning_rate': 1.1608515920678398e-05, 'epoch': 0.47} + 47%|████▋ | 5455/11728 [1:26:02<9:57:26, 5.71s/it] 47%|████▋ | 5456/11728 [1:26:08<10:03:18, 5.77s/it] {'loss': 0.4963, 'learning_rate': 1.1605790222305516e-05, 'epoch': 0.47} + 47%|████▋ | 5456/11728 [1:26:08<10:03:18, 5.77s/it] 47%|████▋ | 5457/11728 [1:26:14<10:01:55, 5.76s/it] {'loss': 0.5008, 'learning_rate': 1.1603064401468364e-05, 'epoch': 0.47} + 47%|████▋ | 5457/11728 [1:26:14<10:01:55, 5.76s/it]/lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/VILA/llava/model/llava_arch.py:397: UserWarning: Inputs truncated! + warnings.warn("Inputs truncated!") + 47%|████▋ | 5458/11728 [1:26:20<10:15:50, 5.89s/it] {'loss': 0.5062, 'learning_rate': 1.1600338458374829e-05, 'epoch': 0.47} + 47%|████▋ | 5458/11728 [1:26:20<10:15:50, 5.89s/it] 47%|████▋ | 5459/11728 [1:26:26<10:17:45, 5.91s/it] {'loss': 0.508, 'learning_rate': 1.1597612393232803e-05, 'epoch': 0.47} + 47%|████▋ | 5459/11728 [1:26:26<10:17:45, 5.91s/it] 47%|████▋ | 5460/11728 [1:26:32<10:19:35, 5.93s/it] {'loss': 0.4816, 'learning_rate': 1.1594886206250186e-05, 'epoch': 0.47} + 47%|████▋ | 5460/11728 [1:26:32<10:19:35, 5.93s/it] 47%|████▋ | 5461/11728 [1:26:38<10:20:34, 5.94s/it] {'loss': 0.4905, 'learning_rate': 1.1592159897634887e-05, 'epoch': 0.47} + 47%|████▋ | 5461/11728 [1:26:38<10:20:34, 5.94s/it] 47%|████▋ | 5462/11728 [1:26:44<10:22:56, 5.96s/it] {'loss': 0.4678, 'learning_rate': 1.1589433467594826e-05, 'epoch': 0.47} + 47%|████▋ | 5462/11728 [1:26:44<10:22:56, 5.96s/it] 47%|████▋ | 5463/11728 [1:26:50<10:10:00, 5.84s/it] {'loss': 0.4969, 'learning_rate': 1.1586706916337937e-05, 'epoch': 0.47} + 47%|████▋ | 5463/11728 [1:26:50<10:10:00, 5.84s/it] 47%|████▋ | 5464/11728 [1:26:55<10:04:55, 5.79s/it] {'loss': 0.4937, 'learning_rate': 1.158398024407215e-05, 'epoch': 0.47} + 47%|████▋ | 5464/11728 [1:26:55<10:04:55, 5.79s/it] 47%|████▋ | 5465/11728 [1:27:01<10:13:32, 5.88s/it] {'loss': 0.487, 'learning_rate': 1.158125345100542e-05, 'epoch': 0.47} + 47%|████▋ | 5465/11728 [1:27:01<10:13:32, 5.88s/it] 47%|████▋ | 5466/11728 [1:27:07<10:18:56, 5.93s/it] {'loss': 0.4695, 'learning_rate': 1.1578526537345698e-05, 'epoch': 0.47} + 47%|████▋ | 5466/11728 [1:27:07<10:18:56, 5.93s/it] 47%|████▋ | 5467/11728 [1:27:13<10:10:45, 5.85s/it] {'loss': 0.4796, 'learning_rate': 1.1575799503300952e-05, 'epoch': 0.47} + 47%|████▋ | 5467/11728 [1:27:13<10:10:45, 5.85s/it] 47%|████▋ | 5468/11728 [1:27:19<10:07:27, 5.82s/it] {'loss': 0.4897, 'learning_rate': 1.157307234907916e-05, 'epoch': 0.47} + 47%|████▋ | 5468/11728 [1:27:19<10:07:27, 5.82s/it] 47%|████▋ | 5469/11728 [1:27:25<10:19:18, 5.94s/it] {'loss': 0.4688, 'learning_rate': 1.1570345074888304e-05, 'epoch': 0.47} + 47%|████▋ | 5469/11728 [1:27:25<10:19:18, 5.94s/it] 47%|████▋ | 5470/11728 [1:27:31<10:11:59, 5.87s/it] {'loss': 0.4739, 'learning_rate': 1.1567617680936372e-05, 'epoch': 0.47} + 47%|████▋ | 5470/11728 [1:27:31<10:11:59, 5.87s/it] 47%|████▋ | 5471/11728 [1:27:36<10:05:26, 5.81s/it] {'loss': 0.475, 'learning_rate': 1.1564890167431372e-05, 'epoch': 0.47} + 47%|████▋ | 5471/11728 [1:27:36<10:05:26, 5.81s/it] 47%|████▋ | 5472/11728 [1:27:42<10:05:52, 5.81s/it] {'loss': 0.4597, 'learning_rate': 1.1562162534581318e-05, 'epoch': 0.47} + 47%|████▋ | 5472/11728 [1:27:42<10:05:52, 5.81s/it] 47%|████▋ | 5473/11728 [1:27:48<10:05:26, 5.81s/it] {'loss': 0.4983, 'learning_rate': 1.1559434782594224e-05, 'epoch': 0.47} + 47%|████▋ | 5473/11728 [1:27:48<10:05:26, 5.81s/it] 47%|████▋ | 5474/11728 [1:27:54<10:13:47, 5.89s/it] {'loss': 0.4844, 'learning_rate': 1.1556706911678124e-05, 'epoch': 0.47} + 47%|████▋ | 5474/11728 [1:27:54<10:13:47, 5.89s/it] 47%|████▋ | 5475/11728 [1:28:00<10:18:32, 5.94s/it] {'loss': 0.4916, 'learning_rate': 1.1553978922041055e-05, 'epoch': 0.47} + 47%|████▋ | 5475/11728 [1:28:00<10:18:32, 5.94s/it] 47%|████▋ | 5476/11728 [1:28:06<10:10:24, 5.86s/it] {'loss': 0.4642, 'learning_rate': 1.1551250813891066e-05, 'epoch': 0.47} + 47%|████▋ | 5476/11728 [1:28:06<10:10:24, 5.86s/it] 47%|████▋ | 5477/11728 [1:28:12<10:08:04, 5.84s/it] {'loss': 0.4888, 'learning_rate': 1.1548522587436216e-05, 'epoch': 0.47} + 47%|████▋ | 5477/11728 [1:28:12<10:08:04, 5.84s/it] 47%|████▋ | 5478/11728 [1:28:18<10:15:23, 5.91s/it] {'loss': 0.4671, 'learning_rate': 1.1545794242884567e-05, 'epoch': 0.47} + 47%|████▋ | 5478/11728 [1:28:18<10:15:23, 5.91s/it] 47%|████▋ | 5479/11728 [1:28:24<10:12:25, 5.88s/it] {'loss': 0.4828, 'learning_rate': 1.1543065780444196e-05, 'epoch': 0.47} + 47%|████▋ | 5479/11728 [1:28:24<10:12:25, 5.88s/it] 47%|████▋ | 5480/11728 [1:28:29<10:01:22, 5.78s/it] {'loss': 0.4696, 'learning_rate': 1.1540337200323187e-05, 'epoch': 0.47} + 47%|████▋ | 5480/11728 [1:28:29<10:01:22, 5.78s/it] 47%|████▋ | 5481/11728 [1:28:35<10:00:14, 5.77s/it] {'loss': 0.498, 'learning_rate': 1.153760850272963e-05, 'epoch': 0.47} + 47%|████▋ | 5481/11728 [1:28:35<10:00:14, 5.77s/it] 47%|████▋ | 5482/11728 [1:28:41<10:00:55, 5.77s/it] {'loss': 0.4759, 'learning_rate': 1.1534879687871629e-05, 'epoch': 0.47} + 47%|████▋ | 5482/11728 [1:28:41<10:00:55, 5.77s/it] 47%|████▋ | 5483/11728 [1:28:47<10:07:33, 5.84s/it] {'loss': 0.4896, 'learning_rate': 1.15321507559573e-05, 'epoch': 0.47} + 47%|████▋ | 5483/11728 [1:28:47<10:07:33, 5.84s/it] 47%|████▋ | 5484/11728 [1:28:52<10:07:34, 5.84s/it] {'loss': 0.481, 'learning_rate': 1.1529421707194753e-05, 'epoch': 0.47} + 47%|████▋ | 5484/11728 [1:28:52<10:07:34, 5.84s/it] 47%|████▋ | 5485/11728 [1:28:58<10:08:00, 5.84s/it] {'loss': 0.4757, 'learning_rate': 1.1526692541792122e-05, 'epoch': 0.47} + 47%|████▋ | 5485/11728 [1:28:58<10:08:00, 5.84s/it] 47%|████▋ | 5486/11728 [1:29:04<10:07:50, 5.84s/it] {'loss': 0.4954, 'learning_rate': 1.1523963259957546e-05, 'epoch': 0.47} + 47%|████▋ | 5486/11728 [1:29:04<10:07:50, 5.84s/it] 47%|████▋ | 5487/11728 [1:29:10<10:21:17, 5.97s/it] {'loss': 0.4989, 'learning_rate': 1.1521233861899168e-05, 'epoch': 0.47} + 47%|████▋ | 5487/11728 [1:29:10<10:21:17, 5.97s/it] 47%|████▋ | 5488/11728 [1:29:16<10:19:09, 5.95s/it] {'loss': 0.4551, 'learning_rate': 1.1518504347825146e-05, 'epoch': 0.47} + 47%|████▋ | 5488/11728 [1:29:16<10:19:09, 5.95s/it] 47%|████▋ | 5489/11728 [1:29:22<10:04:03, 5.81s/it] {'loss': 0.479, 'learning_rate': 1.1515774717943642e-05, 'epoch': 0.47} + 47%|████▋ | 5489/11728 [1:29:22<10:04:03, 5.81s/it] 47%|████▋ | 5490/11728 [1:29:27<9:53:48, 5.71s/it] {'loss': 0.4766, 'learning_rate': 1.151304497246283e-05, 'epoch': 0.47} + 47%|████▋ | 5490/11728 [1:29:27<9:53:48, 5.71s/it] 47%|████▋ | 5491/11728 [1:29:33<10:00:32, 5.78s/it] {'loss': 0.5058, 'learning_rate': 1.151031511159089e-05, 'epoch': 0.47} + 47%|████▋ | 5491/11728 [1:29:33<10:00:32, 5.78s/it] 47%|████▋ | 5492/11728 [1:29:39<10:04:26, 5.82s/it] {'loss': 0.4571, 'learning_rate': 1.1507585135536017e-05, 'epoch': 0.47} + 47%|████▋ | 5492/11728 [1:29:39<10:04:26, 5.82s/it] 47%|████▋ | 5493/11728 [1:29:45<9:50:36, 5.68s/it] {'loss': 0.4647, 'learning_rate': 1.1504855044506407e-05, 'epoch': 0.47} + 47%|████▋ | 5493/11728 [1:29:45<9:50:36, 5.68s/it] 47%|████▋ | 5494/11728 [1:29:50<9:56:39, 5.74s/it] {'loss': 0.4953, 'learning_rate': 1.1502124838710268e-05, 'epoch': 0.47} + 47%|████▋ | 5494/11728 [1:29:50<9:56:39, 5.74s/it] 47%|████▋ | 5495/11728 [1:29:56<10:04:47, 5.82s/it] {'loss': 0.4736, 'learning_rate': 1.1499394518355818e-05, 'epoch': 0.47} + 47%|████▋ | 5495/11728 [1:29:56<10:04:47, 5.82s/it] 47%|████▋ | 5496/11728 [1:30:02<10:02:43, 5.80s/it] {'loss': 0.4839, 'learning_rate': 1.1496664083651281e-05, 'epoch': 0.47} + 47%|████▋ | 5496/11728 [1:30:02<10:02:43, 5.80s/it] 47%|████▋ | 5497/11728 [1:30:08<9:51:27, 5.70s/it] {'loss': 0.478, 'learning_rate': 1.1493933534804892e-05, 'epoch': 0.47} + 47%|████▋ | 5497/11728 [1:30:08<9:51:27, 5.70s/it] 47%|████▋ | 5498/11728 [1:30:13<9:50:42, 5.69s/it] {'loss': 0.4718, 'learning_rate': 1.1491202872024896e-05, 'epoch': 0.47} + 47%|████▋ | 5498/11728 [1:30:13<9:50:42, 5.69s/it] 47%|████▋ | 5499/11728 [1:30:19<10:05:22, 5.83s/it] {'loss': 0.4842, 'learning_rate': 1.1488472095519545e-05, 'epoch': 0.47} + 47%|████▋ | 5499/11728 [1:30:19<10:05:22, 5.83s/it]2 AutoResumeHook: Checking whether to suspend... +0 7AutoResumeHook: Checking whether to suspend... AutoResumeHook: Checking whether to suspend... + +6 AutoResumeHook: Checking whether to suspend... + 47%|████▋ | 5500/11728 [1:30:25<9:59:00, 5.77s/it] 1 AutoResumeHook: Checking whether to suspend... +34 AutoResumeHook: Checking whether to suspend...AutoResumeHook: Checking whether to suspend... + +5 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4874, 'learning_rate': 1.1485741205497094e-05, 'epoch': 0.47} + 47%|████▋ | 5500/11728 [1:30:25<9:59:00, 5.77s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-5500/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-5500/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-5500/mm_projector +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/torch/nn/modules/module.py:1802: UserWarning: Positional args are being deprecated, use kwargs instead. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details. + warnings.warn( + 47%|████▋ | 5501/11728 [1:30:56<22:58:33, 13.28s/it] {'loss': 0.4706, 'learning_rate': 1.1483010202165821e-05, 'epoch': 0.47} + 47%|████▋ | 5501/11728 [1:30:56<22:58:33, 13.28s/it] 47%|████▋ | 5502/11728 [1:31:02<19:04:41, 11.03s/it] {'loss': 0.4773, 'learning_rate': 1.1480279085733997e-05, 'epoch': 0.47} + 47%|████▋ | 5502/11728 [1:31:02<19:04:41, 11.03s/it] 47%|████▋ | 5503/11728 [1:31:07<16:14:09, 9.39s/it] {'loss': 0.4887, 'learning_rate': 1.1477547856409905e-05, 'epoch': 0.47} + 47%|████▋ | 5503/11728 [1:31:07<16:14:09, 9.39s/it] 47%|████▋ | 5504/11728 [1:31:13<14:16:49, 8.26s/it] {'loss': 0.4735, 'learning_rate': 1.1474816514401851e-05, 'epoch': 0.47} + 47%|████▋ | 5504/11728 [1:31:13<14:16:49, 8.26s/it] 47%|████▋ | 5505/11728 [1:31:18<12:54:42, 7.47s/it] {'loss': 0.4806, 'learning_rate': 1.147208505991813e-05, 'epoch': 0.47} + 47%|████▋ | 5505/11728 [1:31:18<12:54:42, 7.47s/it] 47%|████▋ | 5506/11728 [1:31:24<11:58:09, 6.93s/it] {'loss': 0.4702, 'learning_rate': 1.1469353493167056e-05, 'epoch': 0.47} + 47%|████▋ | 5506/11728 [1:31:24<11:58:09, 6.93s/it] 47%|████▋ | 5507/11728 [1:31:30<11:15:48, 6.52s/it] {'loss': 0.4772, 'learning_rate': 1.1466621814356951e-05, 'epoch': 0.47} + 47%|████▋ | 5507/11728 [1:31:30<11:15:48, 6.52s/it] 47%|████▋ | 5508/11728 [1:31:35<10:51:38, 6.29s/it] {'loss': 0.4817, 'learning_rate': 1.1463890023696145e-05, 'epoch': 0.47} + 47%|████▋ | 5508/11728 [1:31:35<10:51:38, 6.29s/it] 47%|████▋ | 5509/11728 [1:31:41<10:25:37, 6.04s/it] {'loss': 0.4944, 'learning_rate': 1.1461158121392972e-05, 'epoch': 0.47} + 47%|████▋ | 5509/11728 [1:31:41<10:25:37, 6.04s/it] 47%|████▋ | 5510/11728 [1:31:47<10:14:18, 5.93s/it] {'loss': 0.4888, 'learning_rate': 1.145842610765578e-05, 'epoch': 0.47} + 47%|████▋ | 5510/11728 [1:31:47<10:14:18, 5.93s/it] 47%|████▋ | 5511/11728 [1:31:52<10:12:15, 5.91s/it] {'loss': 0.4935, 'learning_rate': 1.1455693982692926e-05, 'epoch': 0.47} + 47%|████▋ | 5511/11728 [1:31:52<10:12:15, 5.91s/it] 47%|████▋ | 5512/11728 [1:31:58<10:09:06, 5.88s/it] {'loss': 0.4941, 'learning_rate': 1.1452961746712769e-05, 'epoch': 0.47} + 47%|████▋ | 5512/11728 [1:31:58<10:09:06, 5.88s/it] 47%|████▋ | 5513/11728 [1:32:04<9:58:06, 5.77s/it] {'loss': 0.4742, 'learning_rate': 1.1450229399923687e-05, 'epoch': 0.47} + 47%|████▋ | 5513/11728 [1:32:04<9:58:06, 5.77s/it] 47%|████▋ | 5514/11728 [1:32:10<9:59:02, 5.78s/it] {'loss': 0.4823, 'learning_rate': 1.1447496942534056e-05, 'epoch': 0.47} + 47%|████▋ | 5514/11728 [1:32:10<9:59:02, 5.78s/it] 47%|████▋ | 5515/11728 [1:32:15<9:59:49, 5.79s/it] {'loss': 0.4801, 'learning_rate': 1.1444764374752262e-05, 'epoch': 0.47} + 47%|████▋ | 5515/11728 [1:32:15<9:59:49, 5.79s/it] 47%|████▋ | 5516/11728 [1:32:21<9:55:22, 5.75s/it] {'loss': 0.4736, 'learning_rate': 1.1442031696786707e-05, 'epoch': 0.47} + 47%|████▋ | 5516/11728 [1:32:21<9:55:22, 5.75s/it] 47%|████▋ | 5517/11728 [1:32:27<9:57:24, 5.77s/it] {'loss': 0.4635, 'learning_rate': 1.1439298908845795e-05, 'epoch': 0.47} + 47%|████▋ | 5517/11728 [1:32:27<9:57:24, 5.77s/it] 47%|████▋ | 5518/11728 [1:32:33<9:56:36, 5.76s/it] {'loss': 0.5015, 'learning_rate': 1.143656601113794e-05, 'epoch': 0.47} + 47%|████▋ | 5518/11728 [1:32:33<9:56:36, 5.76s/it] 47%|████▋ | 5519/11728 [1:32:38<9:52:08, 5.72s/it] {'loss': 0.4908, 'learning_rate': 1.143383300387156e-05, 'epoch': 0.47} + 47%|████▋ | 5519/11728 [1:32:38<9:52:08, 5.72s/it] 47%|████▋ | 5520/11728 [1:32:44<9:55:17, 5.75s/it] {'loss': 0.4615, 'learning_rate': 1.143109988725509e-05, 'epoch': 0.47} + 47%|████▋ | 5520/11728 [1:32:44<9:55:17, 5.75s/it] 47%|████▋ | 5521/11728 [1:32:50<9:59:25, 5.79s/it] {'loss': 0.4867, 'learning_rate': 1.1428366661496971e-05, 'epoch': 0.47} + 47%|████▋ | 5521/11728 [1:32:50<9:59:25, 5.79s/it] 47%|████▋ | 5522/11728 [1:32:56<10:10:29, 5.90s/it] {'loss': 0.5, 'learning_rate': 1.1425633326805645e-05, 'epoch': 0.47} + 47%|████▋ | 5522/11728 [1:32:56<10:10:29, 5.90s/it] 47%|████▋ | 5523/11728 [1:33:02<10:04:53, 5.85s/it] {'loss': 0.5025, 'learning_rate': 1.1422899883389569e-05, 'epoch': 0.47} + 47%|████▋ | 5523/11728 [1:33:02<10:04:53, 5.85s/it] 47%|████▋ | 5524/11728 [1:33:07<9:57:50, 5.78s/it] {'loss': 0.4537, 'learning_rate': 1.1420166331457208e-05, 'epoch': 0.47} + 47%|████▋ | 5524/11728 [1:33:07<9:57:50, 5.78s/it] 47%|████▋ | 5525/11728 [1:33:13<10:00:47, 5.81s/it] {'loss': 0.49, 'learning_rate': 1.1417432671217037e-05, 'epoch': 0.47} + 47%|████▋ | 5525/11728 [1:33:13<10:00:47, 5.81s/it] 47%|████▋ | 5526/11728 [1:33:19<9:51:20, 5.72s/it] {'loss': 0.4957, 'learning_rate': 1.1414698902877528e-05, 'epoch': 0.47} + 47%|████▋ | 5526/11728 [1:33:19<9:51:20, 5.72s/it] 47%|████▋ | 5527/11728 [1:33:24<9:45:20, 5.66s/it] {'loss': 0.457, 'learning_rate': 1.1411965026647177e-05, 'epoch': 0.47} + 47%|████▋ | 5527/11728 [1:33:24<9:45:20, 5.66s/it] 47%|████▋ | 5528/11728 [1:33:30<9:54:05, 5.75s/it] {'loss': 0.4848, 'learning_rate': 1.1409231042734476e-05, 'epoch': 0.47} + 47%|████▋ | 5528/11728 [1:33:30<9:54:05, 5.75s/it] 47%|████▋ | 5529/11728 [1:33:36<9:54:01, 5.75s/it] {'loss': 0.4853, 'learning_rate': 1.1406496951347934e-05, 'epoch': 0.47} + 47%|████▋ | 5529/11728 [1:33:36<9:54:01, 5.75s/it] 47%|████▋ | 5530/11728 [1:33:42<10:00:10, 5.81s/it] {'loss': 0.4578, 'learning_rate': 1.140376275269606e-05, 'epoch': 0.47} + 47%|████▋ | 5530/11728 [1:33:42<10:00:10, 5.81s/it] 47%|████▋ | 5531/11728 [1:33:48<10:00:07, 5.81s/it] {'loss': 0.4907, 'learning_rate': 1.1401028446987384e-05, 'epoch': 0.47} + 47%|████▋ | 5531/11728 [1:33:48<10:00:07, 5.81s/it] 47%|████▋ | 5532/11728 [1:33:54<9:56:06, 5.77s/it] {'loss': 0.4982, 'learning_rate': 1.1398294034430423e-05, 'epoch': 0.47} + 47%|████▋ | 5532/11728 [1:33:54<9:56:06, 5.77s/it] 47%|████▋ | 5533/11728 [1:33:59<9:49:33, 5.71s/it] {'loss': 0.4857, 'learning_rate': 1.1395559515233726e-05, 'epoch': 0.47} + 47%|████▋ | 5533/11728 [1:33:59<9:49:33, 5.71s/it] 47%|████▋ | 5534/11728 [1:34:05<9:52:09, 5.74s/it] {'loss': 0.4717, 'learning_rate': 1.1392824889605834e-05, 'epoch': 0.47} + 47%|████▋ | 5534/11728 [1:34:05<9:52:09, 5.74s/it] 47%|████▋ | 5535/11728 [1:34:11<9:57:32, 5.79s/it] {'loss': 0.4959, 'learning_rate': 1.1390090157755298e-05, 'epoch': 0.47} + 47%|████▋ | 5535/11728 [1:34:11<9:57:32, 5.79s/it] 47%|████▋ | 5536/11728 [1:34:16<9:52:56, 5.75s/it] {'loss': 0.4895, 'learning_rate': 1.1387355319890685e-05, 'epoch': 0.47} + 47%|████▋ | 5536/11728 [1:34:16<9:52:56, 5.75s/it] 47%|████▋ | 5537/11728 [1:34:22<9:47:59, 5.70s/it] {'loss': 0.4563, 'learning_rate': 1.138462037622056e-05, 'epoch': 0.47} + 47%|████▋ | 5537/11728 [1:34:22<9:47:59, 5.70s/it] 47%|████▋ | 5538/11728 [1:34:28<9:49:48, 5.72s/it] {'loss': 0.4824, 'learning_rate': 1.1381885326953507e-05, 'epoch': 0.47} + 47%|████▋ | 5538/11728 [1:34:28<9:49:48, 5.72s/it] 47%|████▋ | 5539/11728 [1:34:33<9:49:08, 5.71s/it] {'loss': 0.4826, 'learning_rate': 1.137915017229811e-05, 'epoch': 0.47} + 47%|████▋ | 5539/11728 [1:34:33<9:49:08, 5.71s/it] 47%|████▋ | 5540/11728 [1:34:39<9:54:55, 5.77s/it] {'loss': 0.4932, 'learning_rate': 1.1376414912462964e-05, 'epoch': 0.47} + 47%|████▋ | 5540/11728 [1:34:39<9:54:55, 5.77s/it] 47%|████▋ | 5541/11728 [1:34:45<9:45:37, 5.68s/it] {'loss': 0.4733, 'learning_rate': 1.1373679547656669e-05, 'epoch': 0.47} + 47%|████▋ | 5541/11728 [1:34:45<9:45:37, 5.68s/it] 47%|████▋ | 5542/11728 [1:34:50<9:43:51, 5.66s/it] {'loss': 0.4793, 'learning_rate': 1.1370944078087837e-05, 'epoch': 0.47} + 47%|████▋ | 5542/11728 [1:34:50<9:43:51, 5.66s/it] 47%|████▋ | 5543/11728 [1:34:56<9:46:12, 5.69s/it] {'loss': 0.4749, 'learning_rate': 1.1368208503965087e-05, 'epoch': 0.47} + 47%|████▋ | 5543/11728 [1:34:56<9:46:12, 5.69s/it] 47%|████▋ | 5544/11728 [1:35:02<9:41:10, 5.64s/it] {'loss': 0.4744, 'learning_rate': 1.1365472825497041e-05, 'epoch': 0.47} + 47%|████▋ | 5544/11728 [1:35:02<9:41:10, 5.64s/it] 47%|████▋ | 5545/11728 [1:35:07<9:43:29, 5.66s/it] {'loss': 0.4788, 'learning_rate': 1.1362737042892342e-05, 'epoch': 0.47} + 47%|████▋ | 5545/11728 [1:35:07<9:43:29, 5.66s/it] 47%|████▋ | 5546/11728 [1:35:13<9:41:12, 5.64s/it] {'loss': 0.4729, 'learning_rate': 1.1360001156359623e-05, 'epoch': 0.47} + 47%|████▋ | 5546/11728 [1:35:13<9:41:12, 5.64s/it] 47%|████▋ | 5547/11728 [1:35:19<9:35:28, 5.59s/it] {'loss': 0.4772, 'learning_rate': 1.1357265166107538e-05, 'epoch': 0.47} + 47%|████▋ | 5547/11728 [1:35:19<9:35:28, 5.59s/it] 47%|████▋ | 5548/11728 [1:35:24<9:37:25, 5.61s/it] {'loss': 0.4866, 'learning_rate': 1.1354529072344749e-05, 'epoch': 0.47} + 47%|████▋ | 5548/11728 [1:35:24<9:37:25, 5.61s/it] 47%|████▋ | 5549/11728 [1:35:30<9:46:12, 5.69s/it] {'loss': 0.489, 'learning_rate': 1.1351792875279914e-05, 'epoch': 0.47} + 47%|████▋ | 5549/11728 [1:35:30<9:46:12, 5.69s/it]2 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +0 AutoResumeHook: Checking whether to suspend...1 AutoResumeHook: Checking whether to suspend... + +6 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... + 47%|████▋ | 5550/11728 [1:35:36<10:00:00, 5.83s/it]3 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4761, 'learning_rate': 1.1349056575121713e-05, 'epoch': 0.47} + 47%|████▋ | 5550/11728 [1:35:36<10:00:00, 5.83s/it] 47%|████▋ | 5551/11728 [1:35:42<10:01:54, 5.85s/it] {'loss': 0.4759, 'learning_rate': 1.1346320172078822e-05, 'epoch': 0.47} + 47%|████▋ | 5551/11728 [1:35:42<10:01:54, 5.85s/it] 47%|████▋ | 5552/11728 [1:35:48<10:03:25, 5.86s/it] {'loss': 0.4973, 'learning_rate': 1.1343583666359938e-05, 'epoch': 0.47} + 47%|████▋ | 5552/11728 [1:35:48<10:03:25, 5.86s/it] 47%|████▋ | 5553/11728 [1:35:54<10:06:37, 5.89s/it] {'loss': 0.4775, 'learning_rate': 1.1340847058173752e-05, 'epoch': 0.47} + 47%|████▋ | 5553/11728 [1:35:54<10:06:37, 5.89s/it] 47%|████▋ | 5554/11728 [1:36:00<10:02:57, 5.86s/it] {'loss': 0.491, 'learning_rate': 1.1338110347728973e-05, 'epoch': 0.47} + 47%|████▋ | 5554/11728 [1:36:00<10:02:57, 5.86s/it] 47%|████▋ | 5555/11728 [1:36:06<10:03:07, 5.86s/it] {'loss': 0.4867, 'learning_rate': 1.1335373535234312e-05, 'epoch': 0.47} + 47%|████▋ | 5555/11728 [1:36:06<10:03:07, 5.86s/it] 47%|████▋ | 5556/11728 [1:36:11<10:00:59, 5.84s/it] {'loss': 0.4774, 'learning_rate': 1.1332636620898487e-05, 'epoch': 0.47} + 47%|████▋ | 5556/11728 [1:36:11<10:00:59, 5.84s/it] 47%|████▋ | 5557/11728 [1:36:17<10:01:18, 5.85s/it] {'loss': 0.477, 'learning_rate': 1.1329899604930235e-05, 'epoch': 0.47} + 47%|████▋ | 5557/11728 [1:36:17<10:01:18, 5.85s/it] 47%|████▋ | 5558/11728 [1:36:23<9:56:07, 5.80s/it] {'loss': 0.4967, 'learning_rate': 1.1327162487538283e-05, 'epoch': 0.47} + 47%|████▋ | 5558/11728 [1:36:23<9:56:07, 5.80s/it] 47%|████▋ | 5559/11728 [1:36:29<10:05:42, 5.89s/it] {'loss': 0.4683, 'learning_rate': 1.132442526893138e-05, 'epoch': 0.47} + 47%|████▋ | 5559/11728 [1:36:29<10:05:42, 5.89s/it] 47%|████▋ | 5560/11728 [1:36:35<10:07:57, 5.91s/it] {'loss': 0.4716, 'learning_rate': 1.1321687949318276e-05, 'epoch': 0.47} + 47%|████▋ | 5560/11728 [1:36:35<10:07:57, 5.91s/it] 47%|████▋ | 5561/11728 [1:36:41<10:03:14, 5.87s/it] {'loss': 0.4754, 'learning_rate': 1.1318950528907734e-05, 'epoch': 0.47} + 47%|████▋ | 5561/11728 [1:36:41<10:03:14, 5.87s/it] 47%|████▋ | 5562/11728 [1:36:46<9:52:58, 5.77s/it] {'loss': 0.4879, 'learning_rate': 1.1316213007908514e-05, 'epoch': 0.47} + 47%|████▋ | 5562/11728 [1:36:46<9:52:58, 5.77s/it] 47%|████▋ | 5563/11728 [1:36:52<9:55:33, 5.80s/it] {'loss': 0.4488, 'learning_rate': 1.13134753865294e-05, 'epoch': 0.47} + 47%|████▋ | 5563/11728 [1:36:52<9:55:33, 5.80s/it] 47%|████▋ | 5564/11728 [1:36:58<9:58:41, 5.83s/it] {'loss': 0.4789, 'learning_rate': 1.1310737664979168e-05, 'epoch': 0.47} + 47%|████▋ | 5564/11728 [1:36:58<9:58:41, 5.83s/it] 47%|████▋ | 5565/11728 [1:37:04<9:56:39, 5.81s/it] {'loss': 0.4988, 'learning_rate': 1.1307999843466605e-05, 'epoch': 0.47} + 47%|████▋ | 5565/11728 [1:37:04<9:56:39, 5.81s/it] 47%|████▋ | 5566/11728 [1:37:10<9:54:08, 5.79s/it] {'loss': 0.4812, 'learning_rate': 1.130526192220052e-05, 'epoch': 0.47} + 47%|████▋ | 5566/11728 [1:37:10<9:54:08, 5.79s/it] 47%|████▋ | 5567/11728 [1:37:16<10:07:31, 5.92s/it] {'loss': 0.4726, 'learning_rate': 1.1302523901389706e-05, 'epoch': 0.47} + 47%|████▋ | 5567/11728 [1:37:16<10:07:31, 5.92s/it] 47%|████▋ | 5568/11728 [1:37:22<10:00:53, 5.85s/it] {'loss': 0.4716, 'learning_rate': 1.1299785781242982e-05, 'epoch': 0.47} + 47%|████▋ | 5568/11728 [1:37:22<10:00:53, 5.85s/it] 47%|████▋ | 5569/11728 [1:37:27<10:00:35, 5.85s/it] {'loss': 0.4723, 'learning_rate': 1.129704756196917e-05, 'epoch': 0.47} + 47%|████▋ | 5569/11728 [1:37:27<10:00:35, 5.85s/it] 47%|████▋ | 5570/11728 [1:37:33<10:07:19, 5.92s/it] {'loss': 0.4644, 'learning_rate': 1.1294309243777094e-05, 'epoch': 0.47} + 47%|████▋ | 5570/11728 [1:37:33<10:07:19, 5.92s/it] 48%|████▊ | 5571/11728 [1:37:39<9:55:06, 5.80s/it] {'loss': 0.4906, 'learning_rate': 1.1291570826875593e-05, 'epoch': 0.48} + 48%|████▊ | 5571/11728 [1:37:39<9:55:06, 5.80s/it] 48%|████▊ | 5572/11728 [1:37:44<9:46:34, 5.72s/it] {'loss': 0.4864, 'learning_rate': 1.1288832311473507e-05, 'epoch': 0.48} + 48%|████▊ | 5572/11728 [1:37:44<9:46:34, 5.72s/it] 48%|████▊ | 5573/11728 [1:37:50<9:53:24, 5.78s/it] {'loss': 0.4807, 'learning_rate': 1.1286093697779692e-05, 'epoch': 0.48} + 48%|████▊ | 5573/11728 [1:37:50<9:53:24, 5.78s/it] 48%|████▊ | 5574/11728 [1:37:56<9:50:31, 5.76s/it] {'loss': 0.4735, 'learning_rate': 1.1283354986002997e-05, 'epoch': 0.48} + 48%|████▊ | 5574/11728 [1:37:56<9:50:31, 5.76s/it] 48%|████▊ | 5575/11728 [1:38:02<9:44:54, 5.70s/it] {'loss': 0.472, 'learning_rate': 1.1280616176352299e-05, 'epoch': 0.48} + 48%|████▊ | 5575/11728 [1:38:02<9:44:54, 5.70s/it] 48%|████▊ | 5576/11728 [1:38:08<9:50:45, 5.76s/it] {'loss': 0.478, 'learning_rate': 1.1277877269036461e-05, 'epoch': 0.48} + 48%|████▊ | 5576/11728 [1:38:08<9:50:45, 5.76s/it] 48%|████▊ | 5577/11728 [1:38:13<9:41:51, 5.68s/it] {'loss': 0.4696, 'learning_rate': 1.1275138264264366e-05, 'epoch': 0.48} + 48%|████▊ | 5577/11728 [1:38:13<9:41:51, 5.68s/it] 48%|████▊ | 5578/11728 [1:38:19<9:42:27, 5.68s/it] {'loss': 0.4794, 'learning_rate': 1.1272399162244907e-05, 'epoch': 0.48} + 48%|████▊ | 5578/11728 [1:38:19<9:42:27, 5.68s/it] 48%|████▊ | 5579/11728 [1:38:25<10:05:42, 5.91s/it] {'loss': 0.4623, 'learning_rate': 1.1269659963186976e-05, 'epoch': 0.48} + 48%|████▊ | 5579/11728 [1:38:25<10:05:42, 5.91s/it] 48%|████▊ | 5580/11728 [1:38:31<10:01:05, 5.87s/it] {'loss': 0.4715, 'learning_rate': 1.1266920667299473e-05, 'epoch': 0.48} + 48%|████▊ | 5580/11728 [1:38:31<10:01:05, 5.87s/it] 48%|████▊ | 5581/11728 [1:38:37<9:51:33, 5.77s/it] {'loss': 0.4637, 'learning_rate': 1.1264181274791311e-05, 'epoch': 0.48} + 48%|████▊ | 5581/11728 [1:38:37<9:51:33, 5.77s/it] 48%|████▊ | 5582/11728 [1:38:42<9:49:31, 5.76s/it] {'loss': 0.481, 'learning_rate': 1.126144178587141e-05, 'epoch': 0.48} + 48%|████▊ | 5582/11728 [1:38:42<9:49:31, 5.76s/it] 48%|████▊ | 5583/11728 [1:38:48<10:00:08, 5.86s/it] {'loss': 0.4759, 'learning_rate': 1.1258702200748685e-05, 'epoch': 0.48} + 48%|████▊ | 5583/11728 [1:38:48<10:00:08, 5.86s/it] 48%|████▊ | 5584/11728 [1:38:54<10:04:41, 5.91s/it] {'loss': 0.4553, 'learning_rate': 1.1255962519632082e-05, 'epoch': 0.48} + 48%|████▊ | 5584/11728 [1:38:54<10:04:41, 5.91s/it] 48%|████▊ | 5585/11728 [1:39:00<9:50:17, 5.77s/it] {'loss': 0.4819, 'learning_rate': 1.1253222742730531e-05, 'epoch': 0.48} + 48%|████▊ | 5585/11728 [1:39:00<9:50:17, 5.77s/it] 48%|████▊ | 5586/11728 [1:39:06<9:49:18, 5.76s/it] {'loss': 0.4721, 'learning_rate': 1.1250482870252984e-05, 'epoch': 0.48} + 48%|████▊ | 5586/11728 [1:39:06<9:49:18, 5.76s/it] 48%|████▊ | 5587/11728 [1:39:12<10:03:22, 5.90s/it] {'loss': 0.4786, 'learning_rate': 1.1247742902408391e-05, 'epoch': 0.48} + 48%|████▊ | 5587/11728 [1:39:12<10:03:22, 5.90s/it] 48%|████▊ | 5588/11728 [1:39:17<9:50:30, 5.77s/it] {'loss': 0.4762, 'learning_rate': 1.1245002839405714e-05, 'epoch': 0.48} + 48%|████▊ | 5588/11728 [1:39:17<9:50:30, 5.77s/it] 48%|████▊ | 5589/11728 [1:39:23<9:55:22, 5.82s/it] {'loss': 0.4697, 'learning_rate': 1.1242262681453924e-05, 'epoch': 0.48} + 48%|████▊ | 5589/11728 [1:39:23<9:55:22, 5.82s/it] 48%|████▊ | 5590/11728 [1:39:29<9:43:11, 5.70s/it] {'loss': 0.4809, 'learning_rate': 1.1239522428761996e-05, 'epoch': 0.48} + 48%|████▊ | 5590/11728 [1:39:29<9:43:11, 5.70s/it] 48%|████▊ | 5591/11728 [1:39:34<9:43:41, 5.71s/it] {'loss': 0.476, 'learning_rate': 1.1236782081538915e-05, 'epoch': 0.48} + 48%|████▊ | 5591/11728 [1:39:34<9:43:41, 5.71s/it] 48%|████▊ | 5592/11728 [1:39:40<9:44:59, 5.72s/it] {'loss': 0.4662, 'learning_rate': 1.1234041639993663e-05, 'epoch': 0.48} + 48%|████▊ | 5592/11728 [1:39:40<9:44:59, 5.72s/it] 48%|████▊ | 5593/11728 [1:39:46<9:45:48, 5.73s/it] {'loss': 0.474, 'learning_rate': 1.1231301104335248e-05, 'epoch': 0.48} + 48%|████▊ | 5593/11728 [1:39:46<9:45:48, 5.73s/it] 48%|████▊ | 5594/11728 [1:39:52<9:48:39, 5.76s/it] {'loss': 0.4922, 'learning_rate': 1.122856047477267e-05, 'epoch': 0.48} + 48%|████▊ | 5594/11728 [1:39:52<9:48:39, 5.76s/it] 48%|████▊ | 5595/11728 [1:39:58<10:02:39, 5.90s/it] {'loss': 0.4724, 'learning_rate': 1.122581975151494e-05, 'epoch': 0.48} + 48%|████▊ | 5595/11728 [1:39:58<10:02:39, 5.90s/it] 48%|████▊ | 5596/11728 [1:40:03<9:52:52, 5.80s/it] {'loss': 0.495, 'learning_rate': 1.1223078934771079e-05, 'epoch': 0.48} + 48%|████▊ | 5596/11728 [1:40:03<9:52:52, 5.80s/it] 48%|████▊ | 5597/11728 [1:40:09<9:44:49, 5.72s/it] {'loss': 0.5025, 'learning_rate': 1.122033802475011e-05, 'epoch': 0.48} + 48%|████▊ | 5597/11728 [1:40:09<9:44:49, 5.72s/it] 48%|████▊ | 5598/11728 [1:40:15<9:48:15, 5.76s/it] {'loss': 0.4784, 'learning_rate': 1.1217597021661071e-05, 'epoch': 0.48} + 48%|████▊ | 5598/11728 [1:40:15<9:48:15, 5.76s/it] 48%|████▊ | 5599/11728 [1:40:21<9:47:44, 5.75s/it] {'loss': 0.4935, 'learning_rate': 1.1214855925712998e-05, 'epoch': 0.48} + 48%|████▊ | 5599/11728 [1:40:21<9:47:44, 5.75s/it]2 AutoResumeHook: Checking whether to suspend... +075 AutoResumeHook: Checking whether to suspend... +AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... + 48%|████▊ | 5600/11728 [1:40:26<9:50:48, 5.78s/it]3 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4979, 'learning_rate': 1.1212114737114941e-05, 'epoch': 0.48} + 48%|████▊ | 5600/11728 [1:40:26<9:50:48, 5.78s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-5600/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-5600/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-5600/mm_projector +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/torch/nn/modules/module.py:1802: UserWarning: Positional args are being deprecated, use kwargs instead. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details. + warnings.warn( + 48%|████▊ | 5601/11728 [1:40:58<22:49:35, 13.41s/it] {'loss': 0.478, 'learning_rate': 1.1209373456075952e-05, 'epoch': 0.48} + 48%|████▊ | 5601/11728 [1:40:58<22:49:35, 13.41s/it] 48%|████▊ | 5602/11728 [1:41:03<18:57:46, 11.14s/it] {'loss': 0.4863, 'learning_rate': 1.1206632082805099e-05, 'epoch': 0.48} + 48%|████▊ | 5602/11728 [1:41:03<18:57:46, 11.14s/it] 48%|████▊ | 5603/11728 [1:41:09<16:09:57, 9.50s/it] {'loss': 0.4843, 'learning_rate': 1.120389061751144e-05, 'epoch': 0.48} + 48%|████▊ | 5603/11728 [1:41:09<16:09:57, 9.50s/it] 48%|████▊ | 5604/11728 [1:41:15<14:09:31, 8.32s/it] {'loss': 0.4644, 'learning_rate': 1.120114906040406e-05, 'epoch': 0.48} + 48%|████▊ | 5604/11728 [1:41:15<14:09:31, 8.32s/it] 48%|████▊ | 5605/11728 [1:41:20<12:47:43, 7.52s/it] {'loss': 0.4508, 'learning_rate': 1.1198407411692041e-05, 'epoch': 0.48} + 48%|████▊ | 5605/11728 [1:41:20<12:47:43, 7.52s/it] 48%|████▊ | 5606/11728 [1:41:26<11:58:56, 7.05s/it] {'loss': 0.4908, 'learning_rate': 1.1195665671584463e-05, 'epoch': 0.48} + 48%|████▊ | 5606/11728 [1:41:26<11:58:56, 7.05s/it] 48%|████▊ | 5607/11728 [1:41:32<11:12:37, 6.59s/it] {'loss': 0.4698, 'learning_rate': 1.1192923840290433e-05, 'epoch': 0.48} + 48%|████▊ | 5607/11728 [1:41:32<11:12:37, 6.59s/it] 48%|████▊ | 5608/11728 [1:41:38<10:45:59, 6.33s/it] {'loss': 0.4807, 'learning_rate': 1.119018191801905e-05, 'epoch': 0.48} + 48%|████▊ | 5608/11728 [1:41:38<10:45:59, 6.33s/it] 48%|████▊ | 5609/11728 [1:41:44<10:37:25, 6.25s/it] {'loss': 0.4769, 'learning_rate': 1.1187439904979422e-05, 'epoch': 0.48} + 48%|████▊ | 5609/11728 [1:41:44<10:37:25, 6.25s/it] 48%|████▊ | 5610/11728 [1:41:49<10:20:32, 6.09s/it] {'loss': 0.4794, 'learning_rate': 1.1184697801380673e-05, 'epoch': 0.48} + 48%|████▊ | 5610/11728 [1:41:49<10:20:32, 6.09s/it] 48%|████▊ | 5611/11728 [1:41:55<10:03:48, 5.92s/it] {'loss': 0.4794, 'learning_rate': 1.1181955607431925e-05, 'epoch': 0.48} + 48%|████▊ | 5611/11728 [1:41:55<10:03:48, 5.92s/it] 48%|████▊ | 5612/11728 [1:42:01<9:55:04, 5.84s/it] {'loss': 0.4687, 'learning_rate': 1.1179213323342304e-05, 'epoch': 0.48} + 48%|████▊ | 5612/11728 [1:42:01<9:55:04, 5.84s/it] 48%|████▊ | 5613/11728 [1:42:06<9:48:45, 5.78s/it] {'loss': 0.4855, 'learning_rate': 1.1176470949320954e-05, 'epoch': 0.48} + 48%|████▊ | 5613/11728 [1:42:06<9:48:45, 5.78s/it] 48%|████▊ | 5614/11728 [1:42:12<9:55:17, 5.84s/it] {'loss': 0.4826, 'learning_rate': 1.117372848557702e-05, 'epoch': 0.48} + 48%|████▊ | 5614/11728 [1:42:12<9:55:17, 5.84s/it] 48%|████▊ | 5615/11728 [1:42:18<10:00:12, 5.89s/it] {'loss': 0.4861, 'learning_rate': 1.1170985932319647e-05, 'epoch': 0.48} + 48%|████▊ | 5615/11728 [1:42:18<10:00:12, 5.89s/it] 48%|████▊ | 5616/11728 [1:42:24<9:51:06, 5.80s/it] {'loss': 0.4895, 'learning_rate': 1.1168243289758001e-05, 'epoch': 0.48} + 48%|████▊ | 5616/11728 [1:42:24<9:51:06, 5.80s/it] 48%|████▊ | 5617/11728 [1:42:29<9:40:33, 5.70s/it] {'loss': 0.4692, 'learning_rate': 1.116550055810124e-05, 'epoch': 0.48} + 48%|████▊ | 5617/11728 [1:42:29<9:40:33, 5.70s/it] 48%|████▊ | 5618/11728 [1:42:35<9:40:15, 5.70s/it] {'loss': 0.4783, 'learning_rate': 1.1162757737558545e-05, 'epoch': 0.48} + 48%|████▊ | 5618/11728 [1:42:35<9:40:15, 5.70s/it] 48%|████▊ | 5619/11728 [1:42:41<9:41:18, 5.71s/it] {'loss': 0.4747, 'learning_rate': 1.1160014828339093e-05, 'epoch': 0.48} + 48%|████▊ | 5619/11728 [1:42:41<9:41:18, 5.71s/it] 48%|████▊ | 5620/11728 [1:42:46<9:45:33, 5.75s/it] {'loss': 0.4651, 'learning_rate': 1.1157271830652063e-05, 'epoch': 0.48} + 48%|████▊ | 5620/11728 [1:42:46<9:45:33, 5.75s/it] 48%|████▊ | 5621/11728 [1:42:52<9:48:42, 5.78s/it] {'loss': 0.4805, 'learning_rate': 1.1154528744706652e-05, 'epoch': 0.48} + 48%|████▊ | 5621/11728 [1:42:52<9:48:42, 5.78s/it] 48%|████▊ | 5622/11728 [1:42:58<9:39:41, 5.70s/it] {'loss': 0.4824, 'learning_rate': 1.115178557071206e-05, 'epoch': 0.48} + 48%|████▊ | 5622/11728 [1:42:58<9:39:41, 5.70s/it] 48%|████▊ | 5623/11728 [1:43:03<9:38:03, 5.68s/it] {'loss': 0.4809, 'learning_rate': 1.114904230887749e-05, 'epoch': 0.48} + 48%|████▊ | 5623/11728 [1:43:03<9:38:03, 5.68s/it] 48%|████▊ | 5624/11728 [1:43:09<9:40:41, 5.71s/it] {'loss': 0.4863, 'learning_rate': 1.1146298959412159e-05, 'epoch': 0.48} + 48%|████▊ | 5624/11728 [1:43:09<9:40:41, 5.71s/it] 48%|████▊ | 5625/11728 [1:43:15<9:43:54, 5.74s/it] {'loss': 0.4881, 'learning_rate': 1.1143555522525282e-05, 'epoch': 0.48} + 48%|████▊ | 5625/11728 [1:43:15<9:43:54, 5.74s/it] 48%|████▊ | 5626/11728 [1:43:21<9:43:33, 5.74s/it] {'loss': 0.4672, 'learning_rate': 1.1140811998426089e-05, 'epoch': 0.48} + 48%|████▊ | 5626/11728 [1:43:21<9:43:33, 5.74s/it] 48%|████▊ | 5627/11728 [1:43:26<9:35:36, 5.66s/it] {'loss': 0.4926, 'learning_rate': 1.1138068387323806e-05, 'epoch': 0.48} + 48%|████▊ | 5627/11728 [1:43:26<9:35:36, 5.66s/it] 48%|████▊ | 5628/11728 [1:43:32<9:43:22, 5.74s/it] {'loss': 0.4646, 'learning_rate': 1.113532468942768e-05, 'epoch': 0.48} + 48%|████▊ | 5628/11728 [1:43:32<9:43:22, 5.74s/it] 48%|████▊ | 5629/11728 [1:43:38<9:37:32, 5.68s/it] {'loss': 0.4726, 'learning_rate': 1.1132580904946952e-05, 'epoch': 0.48} + 48%|████▊ | 5629/11728 [1:43:38<9:37:32, 5.68s/it] 48%|████▊ | 5630/11728 [1:43:44<9:44:47, 5.75s/it] {'loss': 0.4764, 'learning_rate': 1.1129837034090876e-05, 'epoch': 0.48} + 48%|████▊ | 5630/11728 [1:43:44<9:44:47, 5.75s/it] 48%|████▊ | 5631/11728 [1:43:49<9:40:43, 5.71s/it] {'loss': 0.4672, 'learning_rate': 1.1127093077068712e-05, 'epoch': 0.48} + 48%|████▊ | 5631/11728 [1:43:49<9:40:43, 5.71s/it]/lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/VILA/llava/model/llava_arch.py:397: UserWarning: Inputs truncated! + warnings.warn("Inputs truncated!") + 48%|████▊ | 5632/11728 [1:43:55<9:52:13, 5.83s/it] {'loss': 0.4821, 'learning_rate': 1.1124349034089724e-05, 'epoch': 0.48} + 48%|████▊ | 5632/11728 [1:43:55<9:52:13, 5.83s/it] 48%|████▊ | 5633/11728 [1:44:01<9:41:06, 5.72s/it] {'loss': 0.4693, 'learning_rate': 1.1121604905363181e-05, 'epoch': 0.48} + 48%|████▊ | 5633/11728 [1:44:01<9:41:06, 5.72s/it] 48%|████▊ | 5634/11728 [1:44:06<9:37:34, 5.69s/it] {'loss': 0.4833, 'learning_rate': 1.111886069109837e-05, 'epoch': 0.48} + 48%|████▊ | 5634/11728 [1:44:06<9:37:34, 5.69s/it] 48%|████▊ | 5635/11728 [1:44:12<9:42:12, 5.73s/it] {'loss': 0.4731, 'learning_rate': 1.1116116391504572e-05, 'epoch': 0.48} + 48%|████▊ | 5635/11728 [1:44:12<9:42:12, 5.73s/it] 48%|████▊ | 5636/11728 [1:44:18<9:52:46, 5.84s/it] {'loss': 0.4844, 'learning_rate': 1.1113372006791074e-05, 'epoch': 0.48} + 48%|████▊ | 5636/11728 [1:44:18<9:52:46, 5.84s/it] 48%|████▊ | 5637/11728 [1:44:24<9:43:18, 5.75s/it] {'loss': 0.4683, 'learning_rate': 1.1110627537167183e-05, 'epoch': 0.48} + 48%|████▊ | 5637/11728 [1:44:24<9:43:18, 5.75s/it] 48%|████▊ | 5638/11728 [1:44:30<9:43:19, 5.75s/it] {'loss': 0.4909, 'learning_rate': 1.1107882982842195e-05, 'epoch': 0.48} + 48%|████▊ | 5638/11728 [1:44:30<9:43:19, 5.75s/it] 48%|████▊ | 5639/11728 [1:44:35<9:44:19, 5.76s/it] {'loss': 0.4678, 'learning_rate': 1.1105138344025429e-05, 'epoch': 0.48} + 48%|████▊ | 5639/11728 [1:44:35<9:44:19, 5.76s/it] 48%|████▊ | 5640/11728 [1:44:41<9:43:07, 5.75s/it] {'loss': 0.4978, 'learning_rate': 1.1102393620926196e-05, 'epoch': 0.48} + 48%|████▊ | 5640/11728 [1:44:41<9:43:07, 5.75s/it] 48%|████▊ | 5641/11728 [1:44:47<9:56:26, 5.88s/it] {'loss': 0.4747, 'learning_rate': 1.1099648813753827e-05, 'epoch': 0.48} + 48%|████▊ | 5641/11728 [1:44:47<9:56:26, 5.88s/it] 48%|████▊ | 5642/11728 [1:44:53<9:56:18, 5.88s/it] {'loss': 0.4866, 'learning_rate': 1.1096903922717645e-05, 'epoch': 0.48} + 48%|████▊ | 5642/11728 [1:44:53<9:56:18, 5.88s/it] 48%|████▊ | 5643/11728 [1:44:59<9:47:34, 5.79s/it] {'loss': 0.4753, 'learning_rate': 1.1094158948026993e-05, 'epoch': 0.48} + 48%|████▊ | 5643/11728 [1:44:59<9:47:34, 5.79s/it] 48%|████▊ | 5644/11728 [1:45:05<9:51:12, 5.83s/it] {'loss': 0.4812, 'learning_rate': 1.1091413889891211e-05, 'epoch': 0.48} + 48%|████▊ | 5644/11728 [1:45:05<9:51:12, 5.83s/it] 48%|████▊ | 5645/11728 [1:45:11<10:09:31, 6.01s/it] {'loss': 0.4777, 'learning_rate': 1.1088668748519646e-05, 'epoch': 0.48} + 48%|████▊ | 5645/11728 [1:45:11<10:09:31, 6.01s/it] 48%|████▊ | 5646/11728 [1:45:17<9:56:31, 5.88s/it] {'loss': 0.4732, 'learning_rate': 1.1085923524121663e-05, 'epoch': 0.48} + 48%|████▊ | 5646/11728 [1:45:17<9:56:31, 5.88s/it] 48%|████▊ | 5647/11728 [1:45:23<9:52:31, 5.85s/it] {'loss': 0.4791, 'learning_rate': 1.1083178216906614e-05, 'epoch': 0.48} + 48%|████▊ | 5647/11728 [1:45:23<9:52:31, 5.85s/it] 48%|████▊ | 5648/11728 [1:45:28<9:50:58, 5.83s/it] {'loss': 0.4836, 'learning_rate': 1.1080432827083874e-05, 'epoch': 0.48} + 48%|████▊ | 5648/11728 [1:45:28<9:50:58, 5.83s/it] 48%|████▊ | 5649/11728 [1:45:34<9:43:20, 5.76s/it] {'loss': 0.4839, 'learning_rate': 1.1077687354862814e-05, 'epoch': 0.48} + 48%|████▊ | 5649/11728 [1:45:34<9:43:20, 5.76s/it]2 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +0 AutoResumeHook: Checking whether to suspend... + 48%|████▊ | 5650/11728 [1:45:40<9:47:43, 5.80s/it] {'loss': 0.4692, 'learning_rate': 1.1074941800452818e-05, 'epoch': 0.48} + 48%|████▊ | 5650/11728 [1:45:40<9:47:43, 5.80s/it] 48%|████▊ | 5651/11728 [1:45:45<9:42:54, 5.76s/it] {'loss': 0.5022, 'learning_rate': 1.1072196164063273e-05, 'epoch': 0.48} + 48%|████▊ | 5651/11728 [1:45:45<9:42:54, 5.76s/it] 48%|████▊ | 5652/11728 [1:45:51<9:44:06, 5.77s/it] {'loss': 0.4921, 'learning_rate': 1.1069450445903573e-05, 'epoch': 0.48} + 48%|████▊ | 5652/11728 [1:45:51<9:44:06, 5.77s/it] 48%|████▊ | 5653/11728 [1:45:57<9:42:59, 5.76s/it] {'loss': 0.4737, 'learning_rate': 1.1066704646183117e-05, 'epoch': 0.48} + 48%|████▊ | 5653/11728 [1:45:57<9:42:59, 5.76s/it] 48%|████▊ | 5654/11728 [1:46:03<9:59:06, 5.92s/it] {'loss': 0.4767, 'learning_rate': 1.1063958765111308e-05, 'epoch': 0.48} + 48%|████▊ | 5654/11728 [1:46:03<9:59:06, 5.92s/it] 48%|████▊ | 5655/11728 [1:46:09<9:51:04, 5.84s/it] {'loss': 0.4734, 'learning_rate': 1.1061212802897567e-05, 'epoch': 0.48} + 48%|████▊ | 5655/11728 [1:46:09<9:51:04, 5.84s/it] 48%|████▊ | 5656/11728 [1:46:15<9:46:17, 5.79s/it] {'loss': 0.4701, 'learning_rate': 1.1058466759751302e-05, 'epoch': 0.48} + 48%|████▊ | 5656/11728 [1:46:15<9:46:17, 5.79s/it] 48%|████▊ | 5657/11728 [1:46:20<9:47:36, 5.81s/it] {'loss': 0.4647, 'learning_rate': 1.1055720635881948e-05, 'epoch': 0.48} + 48%|████▊ | 5657/11728 [1:46:20<9:47:36, 5.81s/it] 48%|████▊ | 5658/11728 [1:46:26<9:45:22, 5.79s/it] {'loss': 0.4783, 'learning_rate': 1.1052974431498929e-05, 'epoch': 0.48} + 48%|████▊ | 5658/11728 [1:46:26<9:45:22, 5.79s/it] 48%|████▊ | 5659/11728 [1:46:32<9:54:49, 5.88s/it] {'loss': 0.4979, 'learning_rate': 1.1050228146811684e-05, 'epoch': 0.48} + 48%|████▊ | 5659/11728 [1:46:32<9:54:49, 5.88s/it] 48%|████▊ | 5660/11728 [1:46:38<9:51:35, 5.85s/it] {'loss': 0.4653, 'learning_rate': 1.1047481782029654e-05, 'epoch': 0.48} + 48%|████▊ | 5660/11728 [1:46:38<9:51:35, 5.85s/it] 48%|████▊ | 5661/11728 [1:46:44<9:48:19, 5.82s/it] {'loss': 0.4897, 'learning_rate': 1.1044735337362291e-05, 'epoch': 0.48} + 48%|████▊ | 5661/11728 [1:46:44<9:48:19, 5.82s/it] 48%|████▊ | 5662/11728 [1:46:50<9:47:20, 5.81s/it] {'loss': 0.4723, 'learning_rate': 1.1041988813019051e-05, 'epoch': 0.48} + 48%|████▊ | 5662/11728 [1:46:50<9:47:20, 5.81s/it] 48%|████▊ | 5663/11728 [1:46:55<9:44:11, 5.78s/it] {'loss': 0.4611, 'learning_rate': 1.103924220920939e-05, 'epoch': 0.48} + 48%|████▊ | 5663/11728 [1:46:55<9:44:11, 5.78s/it] 48%|████▊ | 5664/11728 [1:47:01<9:39:33, 5.73s/it] {'loss': 0.4732, 'learning_rate': 1.1036495526142784e-05, 'epoch': 0.48} + 48%|████▊ | 5664/11728 [1:47:01<9:39:33, 5.73s/it] 48%|████▊ | 5665/11728 [1:47:06<9:33:36, 5.68s/it] {'loss': 0.477, 'learning_rate': 1.10337487640287e-05, 'epoch': 0.48} + 48%|████▊ | 5665/11728 [1:47:06<9:33:36, 5.68s/it] 48%|████▊ | 5666/11728 [1:47:12<9:36:10, 5.70s/it] {'loss': 0.4958, 'learning_rate': 1.1031001923076619e-05, 'epoch': 0.48} + 48%|████▊ | 5666/11728 [1:47:12<9:36:10, 5.70s/it] 48%|████▊ | 5667/11728 [1:47:18<9:34:55, 5.69s/it] {'loss': 0.4698, 'learning_rate': 1.102825500349603e-05, 'epoch': 0.48} + 48%|████▊ | 5667/11728 [1:47:18<9:34:55, 5.69s/it] 48%|████▊ | 5668/11728 [1:47:23<9:31:00, 5.65s/it] {'loss': 0.4903, 'learning_rate': 1.1025508005496417e-05, 'epoch': 0.48} + 48%|████▊ | 5668/11728 [1:47:23<9:31:00, 5.65s/it] 48%|████▊ | 5669/11728 [1:47:29<9:27:31, 5.62s/it] {'loss': 0.4853, 'learning_rate': 1.1022760929287286e-05, 'epoch': 0.48} + 48%|████▊ | 5669/11728 [1:47:29<9:27:31, 5.62s/it] 48%|████▊ | 5670/11728 [1:47:35<9:40:35, 5.75s/it] {'loss': 0.4838, 'learning_rate': 1.1020013775078134e-05, 'epoch': 0.48} + 48%|████▊ | 5670/11728 [1:47:35<9:40:35, 5.75s/it] 48%|████▊ | 5671/11728 [1:47:41<9:40:21, 5.75s/it] {'loss': 0.4765, 'learning_rate': 1.1017266543078475e-05, 'epoch': 0.48} + 48%|████▊ | 5671/11728 [1:47:41<9:40:21, 5.75s/it] 48%|████▊ | 5672/11728 [1:47:47<9:40:26, 5.75s/it] {'loss': 0.489, 'learning_rate': 1.101451923349782e-05, 'epoch': 0.48} + 48%|████▊ | 5672/11728 [1:47:47<9:40:26, 5.75s/it] 48%|████▊ | 5673/11728 [1:47:52<9:39:42, 5.74s/it] {'loss': 0.4735, 'learning_rate': 1.1011771846545696e-05, 'epoch': 0.48} + 48%|████▊ | 5673/11728 [1:47:52<9:39:42, 5.74s/it] 48%|████▊ | 5674/11728 [1:47:58<9:40:12, 5.75s/it] {'loss': 0.4739, 'learning_rate': 1.1009024382431623e-05, 'epoch': 0.48} + 48%|████▊ | 5674/11728 [1:47:58<9:40:12, 5.75s/it] 48%|████▊ | 5675/11728 [1:48:04<9:38:45, 5.74s/it] {'loss': 0.4831, 'learning_rate': 1.1006276841365142e-05, 'epoch': 0.48} + 48%|████▊ | 5675/11728 [1:48:04<9:38:45, 5.74s/it] 48%|████▊ | 5676/11728 [1:48:10<9:42:27, 5.77s/it] {'loss': 0.4899, 'learning_rate': 1.1003529223555786e-05, 'epoch': 0.48} + 48%|████▊ | 5676/11728 [1:48:10<9:42:27, 5.77s/it] 48%|████▊ | 5677/11728 [1:48:15<9:36:48, 5.72s/it] {'loss': 0.4948, 'learning_rate': 1.1000781529213103e-05, 'epoch': 0.48} + 48%|████▊ | 5677/11728 [1:48:15<9:36:48, 5.72s/it] 48%|████▊ | 5678/11728 [1:48:21<9:37:18, 5.73s/it] {'loss': 0.4833, 'learning_rate': 1.099803375854664e-05, 'epoch': 0.48} + 48%|████▊ | 5678/11728 [1:48:21<9:37:18, 5.73s/it] 48%|████▊ | 5679/11728 [1:48:27<9:39:44, 5.75s/it] {'loss': 0.4806, 'learning_rate': 1.0995285911765958e-05, 'epoch': 0.48} + 48%|████▊ | 5679/11728 [1:48:27<9:39:44, 5.75s/it] 48%|████▊ | 5680/11728 [1:48:32<9:36:24, 5.72s/it] {'loss': 0.4624, 'learning_rate': 1.0992537989080618e-05, 'epoch': 0.48} + 48%|████▊ | 5680/11728 [1:48:32<9:36:24, 5.72s/it] 48%|████▊ | 5681/11728 [1:48:38<9:45:57, 5.81s/it] {'loss': 0.4773, 'learning_rate': 1.0989789990700187e-05, 'epoch': 0.48} + 48%|████▊ | 5681/11728 [1:48:38<9:45:57, 5.81s/it] 48%|████▊ | 5682/11728 [1:48:44<9:48:00, 5.84s/it] {'loss': 0.497, 'learning_rate': 1.0987041916834236e-05, 'epoch': 0.48} + 48%|████▊ | 5682/11728 [1:48:44<9:48:00, 5.84s/it] 48%|████▊ | 5683/11728 [1:48:50<9:54:12, 5.90s/it] {'loss': 0.4747, 'learning_rate': 1.0984293767692349e-05, 'epoch': 0.48} + 48%|████▊ | 5683/11728 [1:48:50<9:54:12, 5.90s/it] 48%|████▊ | 5684/11728 [1:48:56<9:44:36, 5.80s/it] {'loss': 0.457, 'learning_rate': 1.0981545543484111e-05, 'epoch': 0.48} + 48%|████▊ | 5684/11728 [1:48:56<9:44:36, 5.80s/it] 48%|████▊ | 5685/11728 [1:49:03<10:08:38, 6.04s/it] {'loss': 0.4927, 'learning_rate': 1.0978797244419113e-05, 'epoch': 0.48} + 48%|████▊ | 5685/11728 [1:49:03<10:08:38, 6.04s/it] 48%|████▊ | 5686/11728 [1:49:08<9:56:54, 5.93s/it] {'loss': 0.4805, 'learning_rate': 1.097604887070695e-05, 'epoch': 0.48} + 48%|████▊ | 5686/11728 [1:49:08<9:56:54, 5.93s/it] 48%|████▊ | 5687/11728 [1:49:14<9:53:33, 5.90s/it] {'loss': 0.4919, 'learning_rate': 1.0973300422557223e-05, 'epoch': 0.48} + 48%|████▊ | 5687/11728 [1:49:14<9:53:33, 5.90s/it] 48%|████▊ | 5688/11728 [1:49:20<9:44:31, 5.81s/it] {'loss': 0.4894, 'learning_rate': 1.0970551900179544e-05, 'epoch': 0.48} + 48%|████▊ | 5688/11728 [1:49:20<9:44:31, 5.81s/it] 49%|████▊ | 5689/11728 [1:49:25<9:38:12, 5.74s/it] {'loss': 0.4744, 'learning_rate': 1.0967803303783523e-05, 'epoch': 0.49} + 49%|████▊ | 5689/11728 [1:49:25<9:38:12, 5.74s/it] 49%|████▊ | 5690/11728 [1:49:31<9:35:47, 5.72s/it] {'loss': 0.4657, 'learning_rate': 1.0965054633578786e-05, 'epoch': 0.49} + 49%|████▊ | 5690/11728 [1:49:31<9:35:47, 5.72s/it] 49%|████▊ | 5691/11728 [1:49:37<9:41:49, 5.78s/it] {'loss': 0.4825, 'learning_rate': 1.0962305889774952e-05, 'epoch': 0.49} + 49%|████▊ | 5691/11728 [1:49:37<9:41:49, 5.78s/it] 49%|████▊ | 5692/11728 [1:49:43<9:43:12, 5.80s/it] {'loss': 0.489, 'learning_rate': 1.0959557072581652e-05, 'epoch': 0.49} + 49%|████▊ | 5692/11728 [1:49:43<9:43:12, 5.80s/it] 49%|████▊ | 5693/11728 [1:49:49<9:45:30, 5.82s/it] {'loss': 0.4609, 'learning_rate': 1.0956808182208525e-05, 'epoch': 0.49} + 49%|████▊ | 5693/11728 [1:49:49<9:45:30, 5.82s/it] 49%|████▊ | 5694/11728 [1:49:54<9:46:27, 5.83s/it] {'loss': 0.4786, 'learning_rate': 1.0954059218865211e-05, 'epoch': 0.49} + 49%|████▊ | 5694/11728 [1:49:54<9:46:27, 5.83s/it] 49%|████▊ | 5695/11728 [1:50:00<9:52:49, 5.90s/it] {'loss': 0.5028, 'learning_rate': 1.0951310182761358e-05, 'epoch': 0.49} + 49%|████▊ | 5695/11728 [1:50:00<9:52:49, 5.90s/it] 49%|████▊ | 5696/11728 [1:50:06<9:55:23, 5.92s/it] {'loss': 0.4925, 'learning_rate': 1.0948561074106618e-05, 'epoch': 0.49} + 49%|████▊ | 5696/11728 [1:50:06<9:55:23, 5.92s/it] 49%|████▊ | 5697/11728 [1:50:12<9:49:49, 5.87s/it] {'loss': 0.4811, 'learning_rate': 1.0945811893110653e-05, 'epoch': 0.49} + 49%|████▊ | 5697/11728 [1:50:12<9:49:49, 5.87s/it] 49%|████▊ | 5698/11728 [1:50:18<9:48:58, 5.86s/it] {'loss': 0.5011, 'learning_rate': 1.0943062639983119e-05, 'epoch': 0.49} + 49%|████▊ | 5698/11728 [1:50:18<9:48:58, 5.86s/it] 49%|████▊ | 5699/11728 [1:50:24<9:43:05, 5.80s/it] {'loss': 0.4558, 'learning_rate': 1.0940313314933697e-05, 'epoch': 0.49} + 49%|████▊ | 5699/11728 [1:50:24<9:43:05, 5.80s/it]2 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... +71 AutoResumeHook: Checking whether to suspend...AutoResumeHook: Checking whether to suspend... + +4 AutoResumeHook: Checking whether to suspend... +03 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... + 49%|████▊ | 5700/11728 [1:50:30<9:43:59, 5.81s/it] {'loss': 0.4797, 'learning_rate': 1.0937563918172052e-05, 'epoch': 0.49} + 49%|████▊ | 5700/11728 [1:50:30<9:43:59, 5.81s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-5700/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-5700/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-5700/mm_projector +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/torch/nn/modules/module.py:1802: UserWarning: Positional args are being deprecated, use kwargs instead. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details. + warnings.warn( + 49%|████▊ | 5701/11728 [1:51:01<22:35:02, 13.49s/it] {'loss': 0.4813, 'learning_rate': 1.093481444990787e-05, 'epoch': 0.49} + 49%|████▊ | 5701/11728 [1:51:01<22:35:02, 13.49s/it] 49%|████▊ | 5702/11728 [1:51:07<18:47:20, 11.22s/it] {'loss': 0.4756, 'learning_rate': 1.0932064910350835e-05, 'epoch': 0.49} + 49%|████▊ | 5702/11728 [1:51:07<18:47:20, 11.22s/it] 49%|████▊ | 5703/11728 [1:51:13<16:03:27, 9.59s/it] {'loss': 0.4821, 'learning_rate': 1.092931529971064e-05, 'epoch': 0.49} + 49%|████▊ | 5703/11728 [1:51:13<16:03:27, 9.59s/it] 49%|████▊ | 5704/11728 [1:51:19<14:12:37, 8.49s/it] {'loss': 0.4959, 'learning_rate': 1.0926565618196978e-05, 'epoch': 0.49} + 49%|████▊ | 5704/11728 [1:51:19<14:12:37, 8.49s/it] 49%|████▊ | 5705/11728 [1:51:24<12:47:28, 7.65s/it] {'loss': 0.4749, 'learning_rate': 1.0923815866019553e-05, 'epoch': 0.49} + 49%|████▊ | 5705/11728 [1:51:24<12:47:28, 7.65s/it] 49%|████▊ | 5706/11728 [1:51:30<11:55:04, 7.12s/it] {'loss': 0.4654, 'learning_rate': 1.0921066043388078e-05, 'epoch': 0.49} + 49%|████▊ | 5706/11728 [1:51:30<11:55:04, 7.12s/it] 49%|████▊ | 5707/11728 [1:51:36<11:07:35, 6.65s/it] {'loss': 0.4731, 'learning_rate': 1.0918316150512256e-05, 'epoch': 0.49} + 49%|████▊ | 5707/11728 [1:51:36<11:07:35, 6.65s/it] 49%|████▊ | 5708/11728 [1:51:41<10:39:27, 6.37s/it] {'loss': 0.4834, 'learning_rate': 1.0915566187601814e-05, 'epoch': 0.49} + 49%|████▊ | 5708/11728 [1:51:41<10:39:27, 6.37s/it] 49%|████▊ | 5709/11728 [1:51:47<10:21:28, 6.20s/it] {'loss': 0.4542, 'learning_rate': 1.091281615486647e-05, 'epoch': 0.49} + 49%|████▊ | 5709/11728 [1:51:47<10:21:28, 6.20s/it] 49%|████▊ | 5710/11728 [1:51:53<10:05:17, 6.03s/it] {'loss': 0.4831, 'learning_rate': 1.0910066052515956e-05, 'epoch': 0.49} + 49%|████▊ | 5710/11728 [1:51:53<10:05:17, 6.03s/it] 49%|████▊ | 5711/11728 [1:51:58<9:48:48, 5.87s/it] {'loss': 0.4815, 'learning_rate': 1.0907315880760003e-05, 'epoch': 0.49} + 49%|████▊ | 5711/11728 [1:51:58<9:48:48, 5.87s/it] 49%|████▊ | 5712/11728 [1:52:04<9:50:33, 5.89s/it] {'loss': 0.4831, 'learning_rate': 1.0904565639808358e-05, 'epoch': 0.49} + 49%|████▊ | 5712/11728 [1:52:04<9:50:33, 5.89s/it] 49%|████▊ | 5713/11728 [1:52:10<9:45:34, 5.84s/it] {'loss': 0.4686, 'learning_rate': 1.0901815329870758e-05, 'epoch': 0.49} + 49%|████▊ | 5713/11728 [1:52:10<9:45:34, 5.84s/it] 49%|████▊ | 5714/11728 [1:52:16<9:41:23, 5.80s/it] {'loss': 0.484, 'learning_rate': 1.0899064951156956e-05, 'epoch': 0.49} + 49%|████▊ | 5714/11728 [1:52:16<9:41:23, 5.80s/it] 49%|████▊ | 5715/11728 [1:52:21<9:36:43, 5.75s/it] {'loss': 0.4713, 'learning_rate': 1.0896314503876708e-05, 'epoch': 0.49} + 49%|████▊ | 5715/11728 [1:52:21<9:36:43, 5.75s/it] 49%|████▊ | 5716/11728 [1:52:27<9:27:56, 5.67s/it] {'loss': 0.4793, 'learning_rate': 1.0893563988239773e-05, 'epoch': 0.49} + 49%|████▊ | 5716/11728 [1:52:27<9:27:56, 5.67s/it] 49%|████▊ | 5717/11728 [1:52:33<9:31:26, 5.70s/it] {'loss': 0.4635, 'learning_rate': 1.089081340445592e-05, 'epoch': 0.49} + 49%|████▊ | 5717/11728 [1:52:33<9:31:26, 5.70s/it] 49%|████▉ | 5718/11728 [1:52:38<9:26:10, 5.65s/it] {'loss': 0.4732, 'learning_rate': 1.0888062752734913e-05, 'epoch': 0.49} + 49%|████▉ | 5718/11728 [1:52:38<9:26:10, 5.65s/it] 49%|████▉ | 5719/11728 [1:52:44<9:43:41, 5.83s/it] {'loss': 0.4812, 'learning_rate': 1.0885312033286537e-05, 'epoch': 0.49} + 49%|████▉ | 5719/11728 [1:52:44<9:43:41, 5.83s/it] 49%|████▉ | 5720/11728 [1:52:50<9:47:05, 5.86s/it] {'loss': 0.4738, 'learning_rate': 1.088256124632057e-05, 'epoch': 0.49} + 49%|████▉ | 5720/11728 [1:52:50<9:47:05, 5.86s/it] 49%|████▉ | 5721/11728 [1:52:56<9:39:22, 5.79s/it] {'loss': 0.4799, 'learning_rate': 1.0879810392046795e-05, 'epoch': 0.49} + 49%|████▉ | 5721/11728 [1:52:56<9:39:22, 5.79s/it] 49%|████▉ | 5722/11728 [1:53:02<9:34:24, 5.74s/it] {'loss': 0.4749, 'learning_rate': 1.0877059470675007e-05, 'epoch': 0.49} + 49%|████▉ | 5722/11728 [1:53:02<9:34:24, 5.74s/it] 49%|████▉ | 5723/11728 [1:53:07<9:35:03, 5.75s/it] {'loss': 0.484, 'learning_rate': 1.0874308482415002e-05, 'epoch': 0.49} + 49%|████▉ | 5723/11728 [1:53:07<9:35:03, 5.75s/it] 49%|████▉ | 5724/11728 [1:53:14<9:48:17, 5.88s/it] {'loss': 0.4905, 'learning_rate': 1.0871557427476585e-05, 'epoch': 0.49} + 49%|████▉ | 5724/11728 [1:53:14<9:48:17, 5.88s/it] 49%|████▉ | 5725/11728 [1:53:20<9:52:51, 5.93s/it] {'loss': 0.4773, 'learning_rate': 1.0868806306069555e-05, 'epoch': 0.49} + 49%|████▉ | 5725/11728 [1:53:20<9:52:51, 5.93s/it] 49%|████▉ | 5726/11728 [1:53:25<9:49:09, 5.89s/it] {'loss': 0.5007, 'learning_rate': 1.0866055118403733e-05, 'epoch': 0.49} + 49%|████▉ | 5726/11728 [1:53:25<9:49:09, 5.89s/it] 49%|████▉ | 5727/11728 [1:53:31<9:48:15, 5.88s/it] {'loss': 0.4807, 'learning_rate': 1.086330386468893e-05, 'epoch': 0.49} + 49%|████▉ | 5727/11728 [1:53:31<9:48:15, 5.88s/it] 49%|████▉ | 5728/11728 [1:53:37<9:34:52, 5.75s/it] {'loss': 0.4568, 'learning_rate': 1.086055254513497e-05, 'epoch': 0.49} + 49%|████▉ | 5728/11728 [1:53:37<9:34:52, 5.75s/it] 49%|████▉ | 5729/11728 [1:53:42<9:34:43, 5.75s/it] {'loss': 0.4773, 'learning_rate': 1.0857801159951681e-05, 'epoch': 0.49} + 49%|████▉ | 5729/11728 [1:53:42<9:34:43, 5.75s/it] 49%|████▉ | 5730/11728 [1:53:48<9:29:29, 5.70s/it] {'loss': 0.486, 'learning_rate': 1.0855049709348895e-05, 'epoch': 0.49} + 49%|████▉ | 5730/11728 [1:53:48<9:29:29, 5.70s/it] 49%|████▉ | 5731/11728 [1:53:54<9:31:31, 5.72s/it] {'loss': 0.4701, 'learning_rate': 1.0852298193536446e-05, 'epoch': 0.49} + 49%|████▉ | 5731/11728 [1:53:54<9:31:31, 5.72s/it] 49%|████▉ | 5732/11728 [1:54:00<9:41:58, 5.82s/it] {'loss': 0.4913, 'learning_rate': 1.084954661272418e-05, 'epoch': 0.49} + 49%|████▉ | 5732/11728 [1:54:00<9:41:58, 5.82s/it] 49%|████▉ | 5733/11728 [1:54:06<9:42:40, 5.83s/it] {'loss': 0.4871, 'learning_rate': 1.0846794967121942e-05, 'epoch': 0.49} + 49%|████▉ | 5733/11728 [1:54:06<9:42:40, 5.83s/it] 49%|████▉ | 5734/11728 [1:54:11<9:35:55, 5.77s/it] {'loss': 0.473, 'learning_rate': 1.0844043256939585e-05, 'epoch': 0.49} + 49%|████▉ | 5734/11728 [1:54:11<9:35:55, 5.77s/it] 49%|████▉ | 5735/11728 [1:54:17<9:34:07, 5.75s/it] {'loss': 0.4978, 'learning_rate': 1.0841291482386967e-05, 'epoch': 0.49} + 49%|████▉ | 5735/11728 [1:54:17<9:34:07, 5.75s/it] 49%|████▉ | 5736/11728 [1:54:23<9:33:17, 5.74s/it] {'loss': 0.4952, 'learning_rate': 1.0838539643673948e-05, 'epoch': 0.49} + 49%|████▉ | 5736/11728 [1:54:23<9:33:17, 5.74s/it] 49%|████▉ | 5737/11728 [1:54:29<9:36:11, 5.77s/it] {'loss': 0.4975, 'learning_rate': 1.083578774101039e-05, 'epoch': 0.49} + 49%|████▉ | 5737/11728 [1:54:29<9:36:11, 5.77s/it] 49%|████▉ | 5738/11728 [1:54:35<9:45:02, 5.86s/it] {'loss': 0.4743, 'learning_rate': 1.0833035774606176e-05, 'epoch': 0.49} + 49%|████▉ | 5738/11728 [1:54:35<9:45:02, 5.86s/it] 49%|████▉ | 5739/11728 [1:54:41<9:49:50, 5.91s/it] {'loss': 0.4795, 'learning_rate': 1.0830283744671173e-05, 'epoch': 0.49} + 49%|████▉ | 5739/11728 [1:54:41<9:49:50, 5.91s/it] 49%|████▉ | 5740/11728 [1:54:47<10:00:45, 6.02s/it] {'loss': 0.5006, 'learning_rate': 1.0827531651415266e-05, 'epoch': 0.49} + 49%|████▉ | 5740/11728 [1:54:47<10:00:45, 6.02s/it] 49%|████▉ | 5741/11728 [1:54:53<9:50:41, 5.92s/it] {'loss': 0.4663, 'learning_rate': 1.082477949504834e-05, 'epoch': 0.49} + 49%|████▉ | 5741/11728 [1:54:53<9:50:41, 5.92s/it] 49%|████▉ | 5742/11728 [1:54:58<9:46:24, 5.88s/it] {'loss': 0.4914, 'learning_rate': 1.0822027275780287e-05, 'epoch': 0.49} + 49%|████▉ | 5742/11728 [1:54:58<9:46:24, 5.88s/it] 49%|████▉ | 5743/11728 [1:55:04<9:41:05, 5.83s/it] {'loss': 0.478, 'learning_rate': 1.0819274993820998e-05, 'epoch': 0.49} + 49%|████▉ | 5743/11728 [1:55:04<9:41:05, 5.83s/it] 49%|████▉ | 5744/11728 [1:55:10<9:35:11, 5.77s/it] {'loss': 0.4834, 'learning_rate': 1.0816522649380383e-05, 'epoch': 0.49} + 49%|████▉ | 5744/11728 [1:55:10<9:35:11, 5.77s/it] 49%|████▉ | 5745/11728 [1:55:16<9:40:43, 5.82s/it] {'loss': 0.4558, 'learning_rate': 1.081377024266834e-05, 'epoch': 0.49} + 49%|████▉ | 5745/11728 [1:55:16<9:40:43, 5.82s/it] 49%|████▉ | 5746/11728 [1:55:21<9:39:38, 5.81s/it] {'loss': 0.4946, 'learning_rate': 1.0811017773894781e-05, 'epoch': 0.49} + 49%|████▉ | 5746/11728 [1:55:21<9:39:38, 5.81s/it] 49%|████▉ | 5747/11728 [1:55:27<9:35:21, 5.77s/it] {'loss': 0.4661, 'learning_rate': 1.0808265243269623e-05, 'epoch': 0.49} + 49%|████▉ | 5747/11728 [1:55:27<9:35:21, 5.77s/it] 49%|████▉ | 5748/11728 [1:55:33<9:31:12, 5.73s/it] {'loss': 0.4491, 'learning_rate': 1.0805512651002779e-05, 'epoch': 0.49} + 49%|████▉ | 5748/11728 [1:55:33<9:31:12, 5.73s/it] 49%|████▉ | 5749/11728 [1:55:38<9:28:02, 5.70s/it] {'loss': 0.4669, 'learning_rate': 1.080275999730418e-05, 'epoch': 0.49} + 49%|████▉ | 5749/11728 [1:55:38<9:28:02, 5.70s/it]2 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +03 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... + 49%|████▉ | 5750/11728 [1:55:44<9:26:46, 5.69s/it] {'loss': 0.4682, 'learning_rate': 1.0800007282383748e-05, 'epoch': 0.49} + 49%|████▉ | 5750/11728 [1:55:44<9:26:46, 5.69s/it] 49%|████▉ | 5751/11728 [1:55:50<9:24:21, 5.67s/it] {'loss': 0.4452, 'learning_rate': 1.0797254506451426e-05, 'epoch': 0.49} + 49%|████▉ | 5751/11728 [1:55:50<9:24:21, 5.67s/it] 49%|████▉ | 5752/11728 [1:55:56<9:30:41, 5.73s/it] {'loss': 0.4768, 'learning_rate': 1.0794501669717146e-05, 'epoch': 0.49} + 49%|████▉ | 5752/11728 [1:55:56<9:30:41, 5.73s/it] 49%|████▉ | 5753/11728 [1:56:01<9:33:00, 5.75s/it] {'loss': 0.4768, 'learning_rate': 1.0791748772390849e-05, 'epoch': 0.49} + 49%|████▉ | 5753/11728 [1:56:01<9:33:00, 5.75s/it] 49%|████▉ | 5754/11728 [1:56:07<9:35:14, 5.78s/it] {'loss': 0.4597, 'learning_rate': 1.0788995814682486e-05, 'epoch': 0.49} + 49%|████▉ | 5754/11728 [1:56:07<9:35:14, 5.78s/it] 49%|████▉ | 5755/11728 [1:56:13<9:39:19, 5.82s/it] {'loss': 0.5029, 'learning_rate': 1.078624279680201e-05, 'epoch': 0.49} + 49%|████▉ | 5755/11728 [1:56:13<9:39:19, 5.82s/it] 49%|████▉ | 5756/11728 [1:56:19<9:34:31, 5.77s/it] {'loss': 0.4747, 'learning_rate': 1.0783489718959376e-05, 'epoch': 0.49} + 49%|████▉ | 5756/11728 [1:56:19<9:34:31, 5.77s/it] 49%|████▉ | 5757/11728 [1:56:25<9:50:52, 5.94s/it] {'loss': 0.4768, 'learning_rate': 1.0780736581364543e-05, 'epoch': 0.49} + 49%|████▉ | 5757/11728 [1:56:25<9:50:52, 5.94s/it] 49%|████▉ | 5758/11728 [1:56:31<9:42:58, 5.86s/it] {'loss': 0.4671, 'learning_rate': 1.077798338422748e-05, 'epoch': 0.49} + 49%|████▉ | 5758/11728 [1:56:31<9:42:58, 5.86s/it] 49%|████▉ | 5759/11728 [1:56:37<9:38:49, 5.82s/it] {'loss': 0.4884, 'learning_rate': 1.0775230127758156e-05, 'epoch': 0.49} + 49%|████▉ | 5759/11728 [1:56:37<9:38:49, 5.82s/it] 49%|████▉ | 5760/11728 [1:56:42<9:33:42, 5.77s/it] {'loss': 0.4874, 'learning_rate': 1.0772476812166545e-05, 'epoch': 0.49} + 49%|████▉ | 5760/11728 [1:56:42<9:33:42, 5.77s/it] 49%|████▉ | 5761/11728 [1:56:48<9:38:56, 5.82s/it] {'loss': 0.4696, 'learning_rate': 1.076972343766263e-05, 'epoch': 0.49} + 49%|████▉ | 5761/11728 [1:56:48<9:38:56, 5.82s/it] 49%|████▉ | 5762/11728 [1:56:54<9:32:16, 5.76s/it] {'loss': 0.468, 'learning_rate': 1.076697000445639e-05, 'epoch': 0.49} + 49%|████▉ | 5762/11728 [1:56:54<9:32:16, 5.76s/it] 49%|████▉ | 5763/11728 [1:56:59<9:28:34, 5.72s/it] {'loss': 0.4809, 'learning_rate': 1.0764216512757815e-05, 'epoch': 0.49} + 49%|████▉ | 5763/11728 [1:56:59<9:28:34, 5.72s/it] 49%|████▉ | 5764/11728 [1:57:05<9:28:24, 5.72s/it] {'loss': 0.4819, 'learning_rate': 1.0761462962776896e-05, 'epoch': 0.49} + 49%|████▉ | 5764/11728 [1:57:05<9:28:24, 5.72s/it] 49%|████▉ | 5765/11728 [1:57:11<9:22:30, 5.66s/it] {'loss': 0.4698, 'learning_rate': 1.0758709354723638e-05, 'epoch': 0.49} + 49%|████▉ | 5765/11728 [1:57:11<9:22:30, 5.66s/it] 49%|████▉ | 5766/11728 [1:57:16<9:20:10, 5.64s/it] {'loss': 0.4655, 'learning_rate': 1.0755955688808035e-05, 'epoch': 0.49} + 49%|████▉ | 5766/11728 [1:57:16<9:20:10, 5.64s/it] 49%|████▉ | 5767/11728 [1:57:22<9:23:54, 5.68s/it] {'loss': 0.4545, 'learning_rate': 1.0753201965240095e-05, 'epoch': 0.49} + 49%|████▉ | 5767/11728 [1:57:22<9:23:54, 5.68s/it] 49%|████▉ | 5768/11728 [1:57:28<9:23:00, 5.67s/it] {'loss': 0.4986, 'learning_rate': 1.075044818422983e-05, 'epoch': 0.49} + 49%|████▉ | 5768/11728 [1:57:28<9:23:00, 5.67s/it] 49%|████▉ | 5769/11728 [1:57:33<9:23:58, 5.68s/it] {'loss': 0.4659, 'learning_rate': 1.0747694345987249e-05, 'epoch': 0.49} + 49%|████▉ | 5769/11728 [1:57:33<9:23:58, 5.68s/it] 49%|████▉ | 5770/11728 [1:57:39<9:22:55, 5.67s/it] {'loss': 0.4747, 'learning_rate': 1.0744940450722378e-05, 'epoch': 0.49} + 49%|████▉ | 5770/11728 [1:57:39<9:22:55, 5.67s/it] 49%|████▉ | 5771/11728 [1:57:45<9:21:43, 5.66s/it] {'loss': 0.4648, 'learning_rate': 1.074218649864524e-05, 'epoch': 0.49} + 49%|████▉ | 5771/11728 [1:57:45<9:21:43, 5.66s/it] 49%|████▉ | 5772/11728 [1:57:50<9:16:59, 5.61s/it] {'loss': 0.4835, 'learning_rate': 1.0739432489965858e-05, 'epoch': 0.49} + 49%|████▉ | 5772/11728 [1:57:50<9:16:59, 5.61s/it] 49%|████▉ | 5773/11728 [1:57:56<9:14:55, 5.59s/it] {'loss': 0.4749, 'learning_rate': 1.0736678424894269e-05, 'epoch': 0.49} + 49%|████▉ | 5773/11728 [1:57:56<9:14:55, 5.59s/it] 49%|████▉ | 5774/11728 [1:58:01<9:14:20, 5.59s/it] {'loss': 0.4702, 'learning_rate': 1.0733924303640508e-05, 'epoch': 0.49} + 49%|████▉ | 5774/11728 [1:58:01<9:14:20, 5.59s/it] 49%|████▉ | 5775/11728 [1:58:07<9:13:28, 5.58s/it] {'loss': 0.4724, 'learning_rate': 1.0731170126414617e-05, 'epoch': 0.49} + 49%|████▉ | 5775/11728 [1:58:07<9:13:28, 5.58s/it] 49%|████▉ | 5776/11728 [1:58:12<9:11:33, 5.56s/it] {'loss': 0.4789, 'learning_rate': 1.0728415893426636e-05, 'epoch': 0.49} + 49%|████▉ | 5776/11728 [1:58:12<9:11:33, 5.56s/it] 49%|████▉ | 5777/11728 [1:58:18<9:21:59, 5.67s/it] {'loss': 0.4774, 'learning_rate': 1.0725661604886622e-05, 'epoch': 0.49} + 49%|████▉ | 5777/11728 [1:58:18<9:21:59, 5.67s/it] 49%|████▉ | 5778/11728 [1:58:24<9:19:27, 5.64s/it] {'loss': 0.4819, 'learning_rate': 1.0722907261004618e-05, 'epoch': 0.49} + 49%|████▉ | 5778/11728 [1:58:24<9:19:27, 5.64s/it] 49%|████▉ | 5779/11728 [1:58:30<9:28:14, 5.73s/it] {'loss': 0.485, 'learning_rate': 1.0720152861990693e-05, 'epoch': 0.49} + 49%|████▉ | 5779/11728 [1:58:30<9:28:14, 5.73s/it] 49%|████▉ | 5780/11728 [1:58:35<9:19:54, 5.65s/it] {'loss': 0.4727, 'learning_rate': 1.0717398408054905e-05, 'epoch': 0.49} + 49%|████▉ | 5780/11728 [1:58:35<9:19:54, 5.65s/it] 49%|████▉ | 5781/11728 [1:58:41<9:19:13, 5.64s/it] {'loss': 0.4657, 'learning_rate': 1.0714643899407317e-05, 'epoch': 0.49} + 49%|████▉ | 5781/11728 [1:58:41<9:19:13, 5.64s/it] 49%|████▉ | 5782/11728 [1:58:47<9:23:08, 5.68s/it] {'loss': 0.477, 'learning_rate': 1.0711889336258004e-05, 'epoch': 0.49} + 49%|████▉ | 5782/11728 [1:58:47<9:23:08, 5.68s/it] 49%|████▉ | 5783/11728 [1:58:52<9:29:22, 5.75s/it] {'loss': 0.4857, 'learning_rate': 1.0709134718817038e-05, 'epoch': 0.49} + 49%|████▉ | 5783/11728 [1:58:52<9:29:22, 5.75s/it] 49%|████▉ | 5784/11728 [1:58:59<9:48:09, 5.94s/it] {'loss': 0.4833, 'learning_rate': 1.0706380047294496e-05, 'epoch': 0.49} + 49%|████▉ | 5784/11728 [1:58:59<9:48:09, 5.94s/it] 49%|████▉ | 5785/11728 [1:59:05<9:42:46, 5.88s/it] {'loss': 0.4604, 'learning_rate': 1.0703625321900462e-05, 'epoch': 0.49} + 49%|████▉ | 5785/11728 [1:59:05<9:42:46, 5.88s/it] 49%|████▉ | 5786/11728 [1:59:10<9:33:36, 5.79s/it] {'loss': 0.4889, 'learning_rate': 1.0700870542845026e-05, 'epoch': 0.49} + 49%|████▉ | 5786/11728 [1:59:10<9:33:36, 5.79s/it] 49%|████▉ | 5787/11728 [1:59:16<9:33:50, 5.80s/it] {'loss': 0.4878, 'learning_rate': 1.0698115710338273e-05, 'epoch': 0.49} + 49%|████▉ | 5787/11728 [1:59:16<9:33:50, 5.80s/it] 49%|████▉ | 5788/11728 [1:59:22<9:26:40, 5.72s/it] {'loss': 0.471, 'learning_rate': 1.0695360824590304e-05, 'epoch': 0.49} + 49%|████▉ | 5788/11728 [1:59:22<9:26:40, 5.72s/it] 49%|████▉ | 5789/11728 [1:59:27<9:27:56, 5.74s/it] {'loss': 0.4878, 'learning_rate': 1.0692605885811215e-05, 'epoch': 0.49} + 49%|████▉ | 5789/11728 [1:59:27<9:27:56, 5.74s/it] 49%|████▉ | 5790/11728 [1:59:33<9:27:11, 5.73s/it] {'loss': 0.475, 'learning_rate': 1.068985089421111e-05, 'epoch': 0.49} + 49%|████▉ | 5790/11728 [1:59:33<9:27:11, 5.73s/it] 49%|████▉ | 5791/11728 [1:59:39<9:33:13, 5.79s/it] {'loss': 0.4713, 'learning_rate': 1.0687095850000096e-05, 'epoch': 0.49} + 49%|████▉ | 5791/11728 [1:59:39<9:33:13, 5.79s/it] 49%|████▉ | 5792/11728 [1:59:45<9:40:04, 5.86s/it] {'loss': 0.4824, 'learning_rate': 1.0684340753388283e-05, 'epoch': 0.49} + 49%|████▉ | 5792/11728 [1:59:45<9:40:04, 5.86s/it] 49%|████▉ | 5793/11728 [1:59:51<9:33:12, 5.79s/it] {'loss': 0.4724, 'learning_rate': 1.0681585604585787e-05, 'epoch': 0.49} + 49%|████▉ | 5793/11728 [1:59:51<9:33:12, 5.79s/it] 49%|████▉ | 5794/11728 [1:59:56<9:26:04, 5.72s/it] {'loss': 0.49, 'learning_rate': 1.0678830403802728e-05, 'epoch': 0.49} + 49%|████▉ | 5794/11728 [1:59:56<9:26:04, 5.72s/it] 49%|████▉ | 5795/11728 [2:00:02<9:31:00, 5.77s/it] {'loss': 0.4836, 'learning_rate': 1.0676075151249228e-05, 'epoch': 0.49} + 49%|████▉ | 5795/11728 [2:00:02<9:31:00, 5.77s/it] 49%|████▉ | 5796/11728 [2:00:08<9:34:07, 5.81s/it] {'loss': 0.4878, 'learning_rate': 1.067331984713541e-05, 'epoch': 0.49} + 49%|████▉ | 5796/11728 [2:00:08<9:34:07, 5.81s/it] 49%|████▉ | 5797/11728 [2:00:14<9:38:21, 5.85s/it] {'loss': 0.4933, 'learning_rate': 1.0670564491671415e-05, 'epoch': 0.49} + 49%|████▉ | 5797/11728 [2:00:14<9:38:21, 5.85s/it] 49%|████▉ | 5798/11728 [2:00:20<9:37:15, 5.84s/it] {'loss': 0.4795, 'learning_rate': 1.0667809085067376e-05, 'epoch': 0.49} + 49%|████▉ | 5798/11728 [2:00:20<9:37:15, 5.84s/it] 49%|████▉ | 5799/11728 [2:00:26<9:49:03, 5.96s/it] {'loss': 0.4966, 'learning_rate': 1.066505362753342e-05, 'epoch': 0.49} + 49%|████▉ | 5799/11728 [2:00:26<9:49:03, 5.96s/it]2 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +0 AutoResumeHook: Checking whether to suspend... + 49%|████▉ | 5800/11728 [2:00:32<9:43:41, 5.91s/it]1 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4772, 'learning_rate': 1.0662298119279702e-05, 'epoch': 0.49} + 49%|████▉ | 5800/11728 [2:00:32<9:43:41, 5.91s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-5800/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-5800/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-5800/mm_projector +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/torch/nn/modules/module.py:1802: UserWarning: Positional args are being deprecated, use kwargs instead. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details. + warnings.warn( + 49%|████▉ | 5801/11728 [2:01:03<22:16:27, 13.53s/it] {'loss': 0.4927, 'learning_rate': 1.0659542560516364e-05, 'epoch': 0.49} + 49%|████▉ | 5801/11728 [2:01:03<22:16:27, 13.53s/it] 49%|████▉ | 5802/11728 [2:01:09<18:18:57, 11.13s/it] {'loss': 0.4727, 'learning_rate': 1.0656786951453556e-05, 'epoch': 0.49} + 49%|████▉ | 5802/11728 [2:01:09<18:18:57, 11.13s/it] 49%|████▉ | 5803/11728 [2:01:15<15:47:49, 9.60s/it] {'loss': 0.4756, 'learning_rate': 1.0654031292301432e-05, 'epoch': 0.49} + 49%|████▉ | 5803/11728 [2:01:15<15:47:49, 9.60s/it] 49%|████▉ | 5804/11728 [2:01:20<13:47:20, 8.38s/it] {'loss': 0.4787, 'learning_rate': 1.0651275583270153e-05, 'epoch': 0.49} + 49%|████▉ | 5804/11728 [2:01:20<13:47:20, 8.38s/it] 49%|████▉ | 5805/11728 [2:01:26<12:29:04, 7.59s/it] {'loss': 0.4832, 'learning_rate': 1.0648519824569876e-05, 'epoch': 0.49} + 49%|████▉ | 5805/11728 [2:01:26<12:29:04, 7.59s/it] 50%|████▉ | 5806/11728 [2:01:31<11:28:46, 6.98s/it] {'loss': 0.4551, 'learning_rate': 1.0645764016410776e-05, 'epoch': 0.5} + 50%|████▉ | 5806/11728 [2:01:31<11:28:46, 6.98s/it] 50%|████▉ | 5807/11728 [2:01:38<11:04:31, 6.73s/it] {'loss': 0.4906, 'learning_rate': 1.0643008159003012e-05, 'epoch': 0.5} + 50%|████▉ | 5807/11728 [2:01:38<11:04:31, 6.73s/it] 50%|████▉ | 5808/11728 [2:01:43<10:32:12, 6.41s/it] {'loss': 0.4823, 'learning_rate': 1.064025225255676e-05, 'epoch': 0.5} + 50%|████▉ | 5808/11728 [2:01:43<10:32:12, 6.41s/it] 50%|████▉ | 5809/11728 [2:01:49<10:04:14, 6.13s/it] {'loss': 0.4695, 'learning_rate': 1.0637496297282202e-05, 'epoch': 0.5} + 50%|████▉ | 5809/11728 [2:01:49<10:04:14, 6.13s/it] 50%|████▉ | 5810/11728 [2:01:54<9:51:57, 6.00s/it] {'loss': 0.4756, 'learning_rate': 1.0634740293389512e-05, 'epoch': 0.5} + 50%|████▉ | 5810/11728 [2:01:54<9:51:57, 6.00s/it] 50%|████▉ | 5811/11728 [2:02:00<9:40:54, 5.89s/it] {'loss': 0.477, 'learning_rate': 1.0631984241088877e-05, 'epoch': 0.5} + 50%|████▉ | 5811/11728 [2:02:00<9:40:54, 5.89s/it] 50%|████▉ | 5812/11728 [2:02:06<9:31:18, 5.79s/it] {'loss': 0.4646, 'learning_rate': 1.0629228140590486e-05, 'epoch': 0.5} + 50%|████▉ | 5812/11728 [2:02:06<9:31:18, 5.79s/it] 50%|████▉ | 5813/11728 [2:02:12<9:45:17, 5.94s/it] {'loss': 0.513, 'learning_rate': 1.0626471992104532e-05, 'epoch': 0.5} + 50%|████▉ | 5813/11728 [2:02:12<9:45:17, 5.94s/it] 50%|████▉ | 5814/11728 [2:02:18<9:41:09, 5.90s/it] {'loss': 0.4776, 'learning_rate': 1.0623715795841207e-05, 'epoch': 0.5} + 50%|████▉ | 5814/11728 [2:02:18<9:41:09, 5.90s/it] 50%|████▉ | 5815/11728 [2:02:23<9:29:56, 5.78s/it] {'loss': 0.4818, 'learning_rate': 1.062095955201071e-05, 'epoch': 0.5} + 50%|████▉ | 5815/11728 [2:02:23<9:29:56, 5.78s/it] 50%|████▉ | 5816/11728 [2:02:29<9:33:59, 5.83s/it] {'loss': 0.4654, 'learning_rate': 1.061820326082325e-05, 'epoch': 0.5} + 50%|████▉ | 5816/11728 [2:02:29<9:33:59, 5.83s/it] 50%|████▉ | 5817/11728 [2:02:35<9:41:13, 5.90s/it] {'loss': 0.4989, 'learning_rate': 1.0615446922489022e-05, 'epoch': 0.5} + 50%|████▉ | 5817/11728 [2:02:35<9:41:13, 5.90s/it] 50%|████▉ | 5818/11728 [2:02:41<9:39:24, 5.88s/it] {'loss': 0.4974, 'learning_rate': 1.0612690537218246e-05, 'epoch': 0.5} + 50%|████▉ | 5818/11728 [2:02:41<9:39:24, 5.88s/it] 50%|████▉ | 5819/11728 [2:02:47<9:27:33, 5.76s/it] {'loss': 0.4642, 'learning_rate': 1.0609934105221131e-05, 'epoch': 0.5} + 50%|████▉ | 5819/11728 [2:02:47<9:27:33, 5.76s/it] 50%|████▉ | 5820/11728 [2:02:52<9:19:48, 5.69s/it] {'loss': 0.4591, 'learning_rate': 1.0607177626707895e-05, 'epoch': 0.5} + 50%|████▉ | 5820/11728 [2:02:52<9:19:48, 5.69s/it] 50%|████▉ | 5821/11728 [2:02:58<9:17:27, 5.66s/it] {'loss': 0.4812, 'learning_rate': 1.0604421101888755e-05, 'epoch': 0.5} + 50%|████▉ | 5821/11728 [2:02:58<9:17:27, 5.66s/it] 50%|████▉ | 5822/11728 [2:03:04<9:24:48, 5.74s/it] {'loss': 0.4719, 'learning_rate': 1.0601664530973945e-05, 'epoch': 0.5} + 50%|████▉ | 5822/11728 [2:03:04<9:24:48, 5.74s/it] 50%|████▉ | 5823/11728 [2:03:09<9:16:42, 5.66s/it] {'loss': 0.4648, 'learning_rate': 1.0598907914173682e-05, 'epoch': 0.5} + 50%|████▉ | 5823/11728 [2:03:09<9:16:42, 5.66s/it] 50%|████▉ | 5824/11728 [2:03:15<9:34:13, 5.84s/it] {'loss': 0.4978, 'learning_rate': 1.05961512516982e-05, 'epoch': 0.5} + 50%|████▉ | 5824/11728 [2:03:15<9:34:13, 5.84s/it] 50%|████▉ | 5825/11728 [2:03:21<9:29:03, 5.78s/it] {'loss': 0.465, 'learning_rate': 1.0593394543757738e-05, 'epoch': 0.5} + 50%|████▉ | 5825/11728 [2:03:21<9:29:03, 5.78s/it] 50%|████▉ | 5826/11728 [2:03:27<9:37:13, 5.87s/it] {'loss': 0.474, 'learning_rate': 1.0590637790562526e-05, 'epoch': 0.5} + 50%|████▉ | 5826/11728 [2:03:27<9:37:13, 5.87s/it] 50%|████▉ | 5827/11728 [2:03:33<9:39:16, 5.89s/it] {'loss': 0.4761, 'learning_rate': 1.0587880992322814e-05, 'epoch': 0.5} + 50%|████▉ | 5827/11728 [2:03:33<9:39:16, 5.89s/it] 50%|████▉ | 5828/11728 [2:03:39<9:38:31, 5.88s/it] {'loss': 0.4705, 'learning_rate': 1.0585124149248842e-05, 'epoch': 0.5} + 50%|████▉ | 5828/11728 [2:03:39<9:38:31, 5.88s/it] 50%|████▉ | 5829/11728 [2:03:45<9:37:14, 5.87s/it] {'loss': 0.4713, 'learning_rate': 1.058236726155086e-05, 'epoch': 0.5} + 50%|████▉ | 5829/11728 [2:03:45<9:37:14, 5.87s/it] 50%|████▉ | 5830/11728 [2:03:50<9:24:38, 5.74s/it] {'loss': 0.4607, 'learning_rate': 1.0579610329439121e-05, 'epoch': 0.5} + 50%|████▉ | 5830/11728 [2:03:50<9:24:38, 5.74s/it] 50%|████▉ | 5831/11728 [2:03:56<9:31:08, 5.81s/it] {'loss': 0.5079, 'learning_rate': 1.0576853353123877e-05, 'epoch': 0.5} + 50%|████▉ | 5831/11728 [2:03:56<9:31:08, 5.81s/it] 50%|████▉ | 5832/11728 [2:04:02<9:23:48, 5.74s/it] {'loss': 0.4633, 'learning_rate': 1.0574096332815386e-05, 'epoch': 0.5} + 50%|████▉ | 5832/11728 [2:04:02<9:23:48, 5.74s/it] 50%|████▉ | 5833/11728 [2:04:07<9:24:32, 5.75s/it] {'loss': 0.4875, 'learning_rate': 1.0571339268723915e-05, 'epoch': 0.5} + 50%|████▉ | 5833/11728 [2:04:07<9:24:32, 5.75s/it] 50%|████▉ | 5834/11728 [2:04:13<9:21:47, 5.72s/it] {'loss': 0.492, 'learning_rate': 1.0568582161059723e-05, 'epoch': 0.5} + 50%|████▉ | 5834/11728 [2:04:13<9:21:47, 5.72s/it] 50%|████▉ | 5835/11728 [2:04:19<9:21:43, 5.72s/it] {'loss': 0.4629, 'learning_rate': 1.0565825010033085e-05, 'epoch': 0.5} + 50%|████▉ | 5835/11728 [2:04:19<9:21:43, 5.72s/it] 50%|████▉ | 5836/11728 [2:04:24<9:17:18, 5.68s/it] {'loss': 0.4791, 'learning_rate': 1.0563067815854266e-05, 'epoch': 0.5} + 50%|████▉ | 5836/11728 [2:04:24<9:17:18, 5.68s/it] 50%|████▉ | 5837/11728 [2:04:30<9:16:02, 5.66s/it] {'loss': 0.4766, 'learning_rate': 1.0560310578733549e-05, 'epoch': 0.5} + 50%|████▉ | 5837/11728 [2:04:30<9:16:02, 5.66s/it] 50%|████▉ | 5838/11728 [2:04:36<9:28:07, 5.79s/it] {'loss': 0.4906, 'learning_rate': 1.0557553298881202e-05, 'epoch': 0.5} + 50%|████▉ | 5838/11728 [2:04:36<9:28:07, 5.79s/it] 50%|████▉ | 5839/11728 [2:04:42<9:36:49, 5.88s/it] {'loss': 0.4698, 'learning_rate': 1.055479597650752e-05, 'epoch': 0.5} + 50%|████▉ | 5839/11728 [2:04:42<9:36:49, 5.88s/it] 50%|████▉ | 5840/11728 [2:04:48<9:35:57, 5.87s/it] {'loss': 0.5196, 'learning_rate': 1.0552038611822774e-05, 'epoch': 0.5} + 50%|████▉ | 5840/11728 [2:04:48<9:35:57, 5.87s/it] 50%|████▉ | 5841/11728 [2:04:54<9:29:55, 5.81s/it] {'loss': 0.469, 'learning_rate': 1.0549281205037263e-05, 'epoch': 0.5} + 50%|████▉ | 5841/11728 [2:04:54<9:29:55, 5.81s/it] 50%|████▉ | 5842/11728 [2:04:59<9:27:01, 5.78s/it] {'loss': 0.456, 'learning_rate': 1.0546523756361271e-05, 'epoch': 0.5} + 50%|████▉ | 5842/11728 [2:04:59<9:27:01, 5.78s/it] 50%|████▉ | 5843/11728 [2:05:05<9:28:08, 5.79s/it] {'loss': 0.4858, 'learning_rate': 1.0543766266005097e-05, 'epoch': 0.5} + 50%|████▉ | 5843/11728 [2:05:05<9:28:08, 5.79s/it] 50%|████▉ | 5844/11728 [2:05:11<9:20:47, 5.72s/it] {'loss': 0.4624, 'learning_rate': 1.0541008734179039e-05, 'epoch': 0.5} + 50%|████▉ | 5844/11728 [2:05:11<9:20:47, 5.72s/it] 50%|████▉ | 5845/11728 [2:05:16<9:16:48, 5.68s/it] {'loss': 0.4654, 'learning_rate': 1.0538251161093396e-05, 'epoch': 0.5} + 50%|████▉ | 5845/11728 [2:05:16<9:16:48, 5.68s/it] 50%|████▉ | 5846/11728 [2:05:22<9:23:19, 5.75s/it] {'loss': 0.4854, 'learning_rate': 1.0535493546958471e-05, 'epoch': 0.5} + 50%|████▉ | 5846/11728 [2:05:22<9:23:19, 5.75s/it] 50%|████▉ | 5847/11728 [2:05:28<9:18:24, 5.70s/it] {'loss': 0.484, 'learning_rate': 1.0532735891984571e-05, 'epoch': 0.5} + 50%|████▉ | 5847/11728 [2:05:28<9:18:24, 5.70s/it] 50%|████▉ | 5848/11728 [2:05:34<9:21:54, 5.73s/it] {'loss': 0.4737, 'learning_rate': 1.0529978196382011e-05, 'epoch': 0.5} + 50%|████▉ | 5848/11728 [2:05:34<9:21:54, 5.73s/it] 50%|████▉ | 5849/11728 [2:05:39<9:24:15, 5.76s/it] {'loss': 0.4796, 'learning_rate': 1.05272204603611e-05, 'epoch': 0.5} + 50%|████▉ | 5849/11728 [2:05:39<9:24:15, 5.76s/it]2 AutoResumeHook: Checking whether to suspend... +63 AutoResumeHook: Checking whether to suspend...AutoResumeHook: Checking whether to suspend... + +7 AutoResumeHook: Checking whether to suspend... +0 AutoResumeHook: Checking whether to suspend... + 50%|████▉ | 5850/11728 [2:05:45<9:21:29, 5.73s/it]5 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4934, 'learning_rate': 1.0524462684132155e-05, 'epoch': 0.5} + 50%|████▉ | 5850/11728 [2:05:45<9:21:29, 5.73s/it] 50%|████▉ | 5851/11728 [2:05:51<9:19:31, 5.71s/it] {'loss': 0.4691, 'learning_rate': 1.0521704867905496e-05, 'epoch': 0.5} + 50%|████▉ | 5851/11728 [2:05:51<9:19:31, 5.71s/it] 50%|████▉ | 5852/11728 [2:05:56<9:17:03, 5.69s/it] {'loss': 0.4573, 'learning_rate': 1.0518947011891447e-05, 'epoch': 0.5} + 50%|████▉ | 5852/11728 [2:05:56<9:17:03, 5.69s/it] 50%|████▉ | 5853/11728 [2:06:03<9:27:25, 5.79s/it] {'loss': 0.4789, 'learning_rate': 1.0516189116300333e-05, 'epoch': 0.5} + 50%|████▉ | 5853/11728 [2:06:03<9:27:25, 5.79s/it] 50%|████▉ | 5854/11728 [2:06:08<9:29:28, 5.82s/it] {'loss': 0.4811, 'learning_rate': 1.051343118134248e-05, 'epoch': 0.5} + 50%|████▉ | 5854/11728 [2:06:08<9:29:28, 5.82s/it] 50%|████▉ | 5855/11728 [2:06:14<9:25:50, 5.78s/it] {'loss': 0.4703, 'learning_rate': 1.0510673207228222e-05, 'epoch': 0.5} + 50%|████▉ | 5855/11728 [2:06:14<9:25:50, 5.78s/it] 50%|████▉ | 5856/11728 [2:06:20<9:24:50, 5.77s/it] {'loss': 0.4957, 'learning_rate': 1.0507915194167893e-05, 'epoch': 0.5} + 50%|████▉ | 5856/11728 [2:06:20<9:24:50, 5.77s/it] 50%|████▉ | 5857/11728 [2:06:26<9:26:21, 5.79s/it] {'loss': 0.4904, 'learning_rate': 1.0505157142371832e-05, 'epoch': 0.5} + 50%|████▉ | 5857/11728 [2:06:26<9:26:21, 5.79s/it] 50%|████▉ | 5858/11728 [2:06:32<9:30:51, 5.84s/it] {'loss': 0.4705, 'learning_rate': 1.0502399052050378e-05, 'epoch': 0.5} + 50%|████▉ | 5858/11728 [2:06:32<9:30:51, 5.84s/it] 50%|████▉ | 5859/11728 [2:06:37<9:29:22, 5.82s/it] {'loss': 0.4955, 'learning_rate': 1.0499640923413874e-05, 'epoch': 0.5} + 50%|████▉ | 5859/11728 [2:06:37<9:29:22, 5.82s/it] 50%|████▉ | 5860/11728 [2:06:43<9:22:36, 5.75s/it] {'loss': 0.4891, 'learning_rate': 1.0496882756672667e-05, 'epoch': 0.5} + 50%|████▉ | 5860/11728 [2:06:43<9:22:36, 5.75s/it] 50%|████▉ | 5861/11728 [2:06:49<9:19:21, 5.72s/it] {'loss': 0.4745, 'learning_rate': 1.0494124552037105e-05, 'epoch': 0.5} + 50%|████▉ | 5861/11728 [2:06:49<9:19:21, 5.72s/it] 50%|████▉ | 5862/11728 [2:06:54<9:19:09, 5.72s/it] {'loss': 0.4567, 'learning_rate': 1.0491366309717548e-05, 'epoch': 0.5} + 50%|████▉ | 5862/11728 [2:06:54<9:19:09, 5.72s/it] 50%|████▉ | 5863/11728 [2:07:00<9:24:05, 5.77s/it] {'loss': 0.4801, 'learning_rate': 1.048860802992434e-05, 'epoch': 0.5} + 50%|████▉ | 5863/11728 [2:07:00<9:24:05, 5.77s/it] 50%|█████ | 5864/11728 [2:07:06<9:25:49, 5.79s/it] {'loss': 0.4674, 'learning_rate': 1.0485849712867844e-05, 'epoch': 0.5} + 50%|█████ | 5864/11728 [2:07:06<9:25:49, 5.79s/it] 50%|█████ | 5865/11728 [2:07:12<9:18:39, 5.72s/it] {'loss': 0.4784, 'learning_rate': 1.048309135875842e-05, 'epoch': 0.5} + 50%|█████ | 5865/11728 [2:07:12<9:18:39, 5.72s/it] 50%|█████ | 5866/11728 [2:07:17<9:20:24, 5.74s/it] {'loss': 0.4672, 'learning_rate': 1.0480332967806435e-05, 'epoch': 0.5} + 50%|█████ | 5866/11728 [2:07:17<9:20:24, 5.74s/it] 50%|█████ | 5867/11728 [2:07:23<9:22:01, 5.75s/it] {'loss': 0.4818, 'learning_rate': 1.0477574540222249e-05, 'epoch': 0.5} + 50%|█████ | 5867/11728 [2:07:23<9:22:01, 5.75s/it] 50%|█████ | 5868/11728 [2:07:29<9:25:39, 5.79s/it] {'loss': 0.4754, 'learning_rate': 1.0474816076216237e-05, 'epoch': 0.5} + 50%|█████ | 5868/11728 [2:07:29<9:25:39, 5.79s/it] 50%|█████ | 5869/11728 [2:07:35<9:34:08, 5.88s/it] {'loss': 0.4672, 'learning_rate': 1.047205757599877e-05, 'epoch': 0.5} + 50%|█████ | 5869/11728 [2:07:35<9:34:08, 5.88s/it] 50%|█████ | 5870/11728 [2:07:42<10:00:45, 6.15s/it] {'loss': 0.4816, 'learning_rate': 1.0469299039780217e-05, 'epoch': 0.5} + 50%|█████ | 5870/11728 [2:07:42<10:00:45, 6.15s/it] 50%|█████ | 5871/11728 [2:07:48<9:43:56, 5.98s/it] {'loss': 0.4541, 'learning_rate': 1.0466540467770965e-05, 'epoch': 0.5} + 50%|█████ | 5871/11728 [2:07:48<9:43:56, 5.98s/it] 50%|█████ | 5872/11728 [2:07:53<9:39:21, 5.94s/it] {'loss': 0.4928, 'learning_rate': 1.0463781860181385e-05, 'epoch': 0.5} + 50%|█████ | 5872/11728 [2:07:53<9:39:21, 5.94s/it] 50%|█████ | 5873/11728 [2:07:59<9:35:23, 5.90s/it] {'loss': 0.4783, 'learning_rate': 1.0461023217221867e-05, 'epoch': 0.5} + 50%|█████ | 5873/11728 [2:07:59<9:35:23, 5.90s/it] 50%|█████ | 5874/11728 [2:08:05<9:32:14, 5.87s/it] {'loss': 0.4704, 'learning_rate': 1.0458264539102792e-05, 'epoch': 0.5} + 50%|█████ | 5874/11728 [2:08:05<9:32:14, 5.87s/it] 50%|█████ | 5875/11728 [2:08:11<9:29:30, 5.84s/it] {'loss': 0.4591, 'learning_rate': 1.045550582603455e-05, 'epoch': 0.5} + 50%|█████ | 5875/11728 [2:08:11<9:29:30, 5.84s/it] 50%|█████ | 5876/11728 [2:08:17<9:31:17, 5.86s/it] {'loss': 0.4808, 'learning_rate': 1.0452747078227534e-05, 'epoch': 0.5} + 50%|█████ | 5876/11728 [2:08:17<9:31:17, 5.86s/it] 50%|█████ | 5877/11728 [2:08:23<9:33:15, 5.88s/it] {'loss': 0.4666, 'learning_rate': 1.0449988295892134e-05, 'epoch': 0.5} + 50%|█████ | 5877/11728 [2:08:23<9:33:15, 5.88s/it] 50%|█████ | 5878/11728 [2:08:28<9:27:06, 5.82s/it] {'loss': 0.4848, 'learning_rate': 1.044722947923875e-05, 'epoch': 0.5} + 50%|█████ | 5878/11728 [2:08:28<9:27:06, 5.82s/it] 50%|█████ | 5879/11728 [2:08:34<9:28:00, 5.83s/it] {'loss': 0.4988, 'learning_rate': 1.0444470628477773e-05, 'epoch': 0.5} + 50%|█████ | 5879/11728 [2:08:34<9:28:00, 5.83s/it] 50%|█████ | 5880/11728 [2:08:40<9:29:41, 5.84s/it] {'loss': 0.4792, 'learning_rate': 1.0441711743819618e-05, 'epoch': 0.5} + 50%|█████ | 5880/11728 [2:08:40<9:29:41, 5.84s/it] 50%|█████ | 5881/11728 [2:08:46<9:34:06, 5.89s/it] {'loss': 0.4694, 'learning_rate': 1.0438952825474678e-05, 'epoch': 0.5} + 50%|█████ | 5881/11728 [2:08:46<9:34:06, 5.89s/it] 50%|█████ | 5882/11728 [2:08:52<9:32:15, 5.87s/it] {'loss': 0.4798, 'learning_rate': 1.0436193873653362e-05, 'epoch': 0.5} + 50%|█████ | 5882/11728 [2:08:52<9:32:15, 5.87s/it] 50%|█████ | 5883/11728 [2:08:58<9:28:47, 5.84s/it] {'loss': 0.4736, 'learning_rate': 1.0433434888566078e-05, 'epoch': 0.5} + 50%|█████ | 5883/11728 [2:08:58<9:28:47, 5.84s/it] 50%|█████ | 5884/11728 [2:09:04<9:37:16, 5.93s/it] {'loss': 0.4651, 'learning_rate': 1.0430675870423245e-05, 'epoch': 0.5} + 50%|█████ | 5884/11728 [2:09:04<9:37:16, 5.93s/it] 50%|█████ | 5885/11728 [2:09:09<9:25:14, 5.80s/it] {'loss': 0.4658, 'learning_rate': 1.0427916819435271e-05, 'epoch': 0.5} + 50%|█████ | 5885/11728 [2:09:09<9:25:14, 5.80s/it] 50%|█████ | 5886/11728 [2:09:15<9:27:39, 5.83s/it] {'loss': 0.4877, 'learning_rate': 1.0425157735812572e-05, 'epoch': 0.5} + 50%|█████ | 5886/11728 [2:09:15<9:27:39, 5.83s/it] 50%|█████ | 5887/11728 [2:09:21<9:22:45, 5.78s/it] {'loss': 0.4709, 'learning_rate': 1.0422398619765571e-05, 'epoch': 0.5} + 50%|█████ | 5887/11728 [2:09:21<9:22:45, 5.78s/it] 50%|█████ | 5888/11728 [2:09:27<9:22:00, 5.77s/it] {'loss': 0.4852, 'learning_rate': 1.0419639471504684e-05, 'epoch': 0.5} + 50%|█████ | 5888/11728 [2:09:27<9:22:00, 5.77s/it] 50%|█████ | 5889/11728 [2:09:33<9:29:45, 5.85s/it] {'loss': 0.4819, 'learning_rate': 1.0416880291240343e-05, 'epoch': 0.5} + 50%|█████ | 5889/11728 [2:09:33<9:29:45, 5.85s/it] 50%|█████ | 5890/11728 [2:09:38<9:23:36, 5.79s/it] {'loss': 0.4669, 'learning_rate': 1.0414121079182969e-05, 'epoch': 0.5} + 50%|█████ | 5890/11728 [2:09:38<9:23:36, 5.79s/it] 50%|█████ | 5891/11728 [2:09:44<9:30:59, 5.87s/it] {'loss': 0.4866, 'learning_rate': 1.0411361835542991e-05, 'epoch': 0.5} + 50%|█████ | 5891/11728 [2:09:44<9:30:59, 5.87s/it] 50%|█████ | 5892/11728 [2:09:50<9:23:07, 5.79s/it] {'loss': 0.4624, 'learning_rate': 1.0408602560530845e-05, 'epoch': 0.5} + 50%|█████ | 5892/11728 [2:09:50<9:23:07, 5.79s/it] 50%|█████ | 5893/11728 [2:09:56<9:19:14, 5.75s/it] {'loss': 0.4784, 'learning_rate': 1.0405843254356959e-05, 'epoch': 0.5} + 50%|█████ | 5893/11728 [2:09:56<9:19:14, 5.75s/it] 50%|█████ | 5894/11728 [2:10:01<9:19:46, 5.76s/it] {'loss': 0.4542, 'learning_rate': 1.0403083917231776e-05, 'epoch': 0.5} + 50%|█████ | 5894/11728 [2:10:01<9:19:46, 5.76s/it] 50%|█████ | 5895/11728 [2:10:07<9:19:44, 5.76s/it] {'loss': 0.4875, 'learning_rate': 1.0400324549365725e-05, 'epoch': 0.5} + 50%|█████ | 5895/11728 [2:10:07<9:19:44, 5.76s/it] 50%|█████ | 5896/11728 [2:10:13<9:24:27, 5.81s/it] {'loss': 0.4798, 'learning_rate': 1.039756515096926e-05, 'epoch': 0.5} + 50%|█████ | 5896/11728 [2:10:13<9:24:27, 5.81s/it] 50%|█████ | 5897/11728 [2:10:19<9:31:43, 5.88s/it] {'loss': 0.4479, 'learning_rate': 1.039480572225281e-05, 'epoch': 0.5} + 50%|█████ | 5897/11728 [2:10:19<9:31:43, 5.88s/it] 50%|█████ | 5898/11728 [2:10:25<9:31:48, 5.88s/it] {'loss': 0.4658, 'learning_rate': 1.0392046263426832e-05, 'epoch': 0.5} + 50%|█████ | 5898/11728 [2:10:25<9:31:48, 5.88s/it] 50%|█████ | 5899/11728 [2:10:30<9:22:26, 5.79s/it] {'loss': 0.4631, 'learning_rate': 1.0389286774701765e-05, 'epoch': 0.5} + 50%|█████ | 5899/11728 [2:10:30<9:22:26, 5.79s/it]2 AutoResumeHook: Checking whether to suspend... +0 AutoResumeHook: Checking whether to suspend... + 50%|█████ | 5900/11728 [2:10:37<9:29:46, 5.87s/it]6 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... +54 AutoResumeHook: Checking whether to suspend...AutoResumeHook: Checking whether to suspend... + +7 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4726, 'learning_rate': 1.0386527256288065e-05, 'epoch': 0.5} + 50%|█████ | 5900/11728 [2:10:37<9:29:46, 5.87s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-5900/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-5900/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-5900/mm_projector +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/torch/nn/modules/module.py:1802: UserWarning: Positional args are being deprecated, use kwargs instead. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details. + warnings.warn( + 50%|█████ | 5901/11728 [2:11:10<22:50:13, 14.11s/it] {'loss': 0.4926, 'learning_rate': 1.0383767708396187e-05, 'epoch': 0.5} + 50%|█████ | 5901/11728 [2:11:10<22:50:13, 14.11s/it] 50%|█████ | 5902/11728 [2:11:16<18:43:42, 11.57s/it] {'loss': 0.4847, 'learning_rate': 1.0381008131236576e-05, 'epoch': 0.5} + 50%|█████ | 5902/11728 [2:11:16<18:43:42, 11.57s/it] 50%|█████ | 5903/11728 [2:11:21<15:54:22, 9.83s/it] {'loss': 0.4902, 'learning_rate': 1.0378248525019694e-05, 'epoch': 0.5} + 50%|█████ | 5903/11728 [2:11:21<15:54:22, 9.83s/it] 50%|█████ | 5904/11728 [2:11:27<14:03:05, 8.69s/it] {'loss': 0.4743, 'learning_rate': 1.0375488889956003e-05, 'epoch': 0.5} + 50%|█████ | 5904/11728 [2:11:27<14:03:05, 8.69s/it] 50%|█████ | 5905/11728 [2:11:33<12:40:16, 7.83s/it] {'loss': 0.4862, 'learning_rate': 1.0372729226255962e-05, 'epoch': 0.5} + 50%|█████ | 5905/11728 [2:11:33<12:40:16, 7.83s/it] 50%|█████ | 5906/11728 [2:11:39<11:33:40, 7.15s/it] {'loss': 0.4797, 'learning_rate': 1.0369969534130031e-05, 'epoch': 0.5} + 50%|█████ | 5906/11728 [2:11:39<11:33:40, 7.15s/it] 50%|█████ | 5907/11728 [2:11:45<10:54:48, 6.75s/it] {'loss': 0.4779, 'learning_rate': 1.036720981378868e-05, 'epoch': 0.5} + 50%|█████ | 5907/11728 [2:11:45<10:54:48, 6.75s/it] 50%|█████ | 5908/11728 [2:11:50<10:24:18, 6.44s/it] {'loss': 0.4875, 'learning_rate': 1.0364450065442377e-05, 'epoch': 0.5} + 50%|█████ | 5908/11728 [2:11:50<10:24:18, 6.44s/it] 50%|█████ | 5909/11728 [2:11:56<9:57:30, 6.16s/it] {'loss': 0.483, 'learning_rate': 1.036169028930159e-05, 'epoch': 0.5} + 50%|█████ | 5909/11728 [2:11:56<9:57:30, 6.16s/it] 50%|█████ | 5910/11728 [2:12:01<9:44:22, 6.03s/it] {'loss': 0.4764, 'learning_rate': 1.0358930485576793e-05, 'epoch': 0.5} + 50%|█████ | 5910/11728 [2:12:01<9:44:22, 6.03s/it] 50%|█████ | 5911/11728 [2:12:07<9:32:48, 5.91s/it] {'loss': 0.4863, 'learning_rate': 1.0356170654478457e-05, 'epoch': 0.5} + 50%|█████ | 5911/11728 [2:12:07<9:32:48, 5.91s/it] 50%|█████ | 5912/11728 [2:12:13<9:30:01, 5.88s/it] {'loss': 0.4921, 'learning_rate': 1.0353410796217058e-05, 'epoch': 0.5} + 50%|█████ | 5912/11728 [2:12:13<9:30:01, 5.88s/it] 50%|█████ | 5913/11728 [2:12:19<9:29:54, 5.88s/it] {'loss': 0.4662, 'learning_rate': 1.035065091100308e-05, 'epoch': 0.5} + 50%|█████ | 5913/11728 [2:12:19<9:29:54, 5.88s/it] 50%|█████ | 5914/11728 [2:12:24<9:23:53, 5.82s/it] {'loss': 0.4694, 'learning_rate': 1.0347890999046998e-05, 'epoch': 0.5} + 50%|█████ | 5914/11728 [2:12:24<9:23:53, 5.82s/it] 50%|█████ | 5915/11728 [2:12:30<9:16:21, 5.74s/it] {'loss': 0.4751, 'learning_rate': 1.0345131060559295e-05, 'epoch': 0.5} + 50%|█████ | 5915/11728 [2:12:30<9:16:21, 5.74s/it] 50%|█████ | 5916/11728 [2:12:36<9:09:03, 5.67s/it] {'loss': 0.4776, 'learning_rate': 1.0342371095750456e-05, 'epoch': 0.5} + 50%|█████ | 5916/11728 [2:12:36<9:09:03, 5.67s/it] 50%|█████ | 5917/11728 [2:12:41<9:15:21, 5.73s/it] {'loss': 0.4798, 'learning_rate': 1.033961110483097e-05, 'epoch': 0.5} + 50%|█████ | 5917/11728 [2:12:41<9:15:21, 5.73s/it] 50%|█████ | 5918/11728 [2:12:47<9:22:14, 5.81s/it] {'loss': 0.4751, 'learning_rate': 1.0336851088011321e-05, 'epoch': 0.5} + 50%|█████ | 5918/11728 [2:12:47<9:22:14, 5.81s/it] 50%|█████ | 5919/11728 [2:12:53<9:14:35, 5.73s/it] {'loss': 0.494, 'learning_rate': 1.0334091045502005e-05, 'epoch': 0.5} + 50%|█████ | 5919/11728 [2:12:53<9:14:35, 5.73s/it] 50%|█████ | 5920/11728 [2:12:59<9:15:59, 5.74s/it] {'loss': 0.4639, 'learning_rate': 1.033133097751351e-05, 'epoch': 0.5} + 50%|█████ | 5920/11728 [2:12:59<9:15:59, 5.74s/it] 50%|█████ | 5921/11728 [2:13:05<9:20:04, 5.79s/it] {'loss': 0.48, 'learning_rate': 1.0328570884256328e-05, 'epoch': 0.5} + 50%|█████ | 5921/11728 [2:13:05<9:20:04, 5.79s/it] 50%|█████ | 5922/11728 [2:13:10<9:13:23, 5.72s/it] {'loss': 0.4577, 'learning_rate': 1.0325810765940962e-05, 'epoch': 0.5} + 50%|█████ | 5922/11728 [2:13:10<9:13:23, 5.72s/it] 51%|█████ | 5923/11728 [2:13:16<9:24:58, 5.84s/it] {'loss': 0.4769, 'learning_rate': 1.0323050622777906e-05, 'epoch': 0.51} + 51%|█████ | 5923/11728 [2:13:16<9:24:58, 5.84s/it] 51%|█████ | 5924/11728 [2:13:22<9:19:55, 5.79s/it] {'loss': 0.4783, 'learning_rate': 1.0320290454977662e-05, 'epoch': 0.51} + 51%|█████ | 5924/11728 [2:13:22<9:19:55, 5.79s/it] 51%|█████ | 5925/11728 [2:13:28<9:19:35, 5.79s/it] {'loss': 0.4908, 'learning_rate': 1.0317530262750728e-05, 'epoch': 0.51} + 51%|█████ | 5925/11728 [2:13:28<9:19:35, 5.79s/it] 51%|█████ | 5926/11728 [2:13:34<9:21:44, 5.81s/it] {'loss': 0.4864, 'learning_rate': 1.0314770046307611e-05, 'epoch': 0.51} + 51%|█████ | 5926/11728 [2:13:34<9:21:44, 5.81s/it] 51%|█████ | 5927/11728 [2:13:40<9:25:19, 5.85s/it] {'loss': 0.4742, 'learning_rate': 1.0312009805858818e-05, 'epoch': 0.51} + 51%|█████ | 5927/11728 [2:13:40<9:25:19, 5.85s/it] 51%|█████ | 5928/11728 [2:13:45<9:24:05, 5.84s/it] {'loss': 0.4942, 'learning_rate': 1.0309249541614854e-05, 'epoch': 0.51} + 51%|█████ | 5928/11728 [2:13:45<9:24:05, 5.84s/it] 51%|█████ | 5929/11728 [2:13:51<9:30:02, 5.90s/it] {'loss': 0.4652, 'learning_rate': 1.030648925378623e-05, 'epoch': 0.51} + 51%|█████ | 5929/11728 [2:13:51<9:30:02, 5.90s/it] 51%|█████ | 5930/11728 [2:13:57<9:28:28, 5.88s/it] {'loss': 0.4767, 'learning_rate': 1.0303728942583454e-05, 'epoch': 0.51} + 51%|█████ | 5930/11728 [2:13:57<9:28:28, 5.88s/it] 51%|█████ | 5931/11728 [2:14:03<9:23:38, 5.83s/it] {'loss': 0.4827, 'learning_rate': 1.0300968608217042e-05, 'epoch': 0.51} + 51%|█████ | 5931/11728 [2:14:03<9:23:38, 5.83s/it] 51%|█████ | 5932/11728 [2:14:09<9:23:33, 5.83s/it] {'loss': 0.4854, 'learning_rate': 1.0298208250897504e-05, 'epoch': 0.51} + 51%|█████ | 5932/11728 [2:14:09<9:23:33, 5.83s/it] 51%|█████ | 5933/11728 [2:14:15<9:27:21, 5.87s/it] {'loss': 0.454, 'learning_rate': 1.0295447870835364e-05, 'epoch': 0.51} + 51%|█████ | 5933/11728 [2:14:15<9:27:21, 5.87s/it] 51%|█████ | 5934/11728 [2:14:20<9:15:40, 5.75s/it] {'loss': 0.4881, 'learning_rate': 1.0292687468241136e-05, 'epoch': 0.51} + 51%|█████ | 5934/11728 [2:14:20<9:15:40, 5.75s/it] 51%|█████ | 5935/11728 [2:14:26<9:10:46, 5.70s/it] {'loss': 0.4831, 'learning_rate': 1.0289927043325336e-05, 'epoch': 0.51} + 51%|█████ | 5935/11728 [2:14:26<9:10:46, 5.70s/it] 51%|█████ | 5936/11728 [2:14:31<9:09:00, 5.69s/it] {'loss': 0.452, 'learning_rate': 1.0287166596298492e-05, 'epoch': 0.51} + 51%|█████ | 5936/11728 [2:14:31<9:09:00, 5.69s/it] 51%|█████ | 5937/11728 [2:14:37<9:09:34, 5.69s/it] {'loss': 0.4944, 'learning_rate': 1.0284406127371125e-05, 'epoch': 0.51} + 51%|█████ | 5937/11728 [2:14:37<9:09:34, 5.69s/it] 51%|█████ | 5938/11728 [2:14:43<9:17:23, 5.78s/it] {'loss': 0.4721, 'learning_rate': 1.0281645636753758e-05, 'epoch': 0.51} + 51%|█████ | 5938/11728 [2:14:43<9:17:23, 5.78s/it] 51%|█████ | 5939/11728 [2:14:49<9:12:39, 5.73s/it] {'loss': 0.447, 'learning_rate': 1.0278885124656919e-05, 'epoch': 0.51} + 51%|█████ | 5939/11728 [2:14:49<9:12:39, 5.73s/it] 51%|█████ | 5940/11728 [2:14:55<9:13:38, 5.74s/it] {'loss': 0.4795, 'learning_rate': 1.027612459129114e-05, 'epoch': 0.51} + 51%|█████ | 5940/11728 [2:14:55<9:13:38, 5.74s/it] 51%|█████ | 5941/11728 [2:15:00<9:17:18, 5.78s/it] {'loss': 0.4877, 'learning_rate': 1.027336403686694e-05, 'epoch': 0.51} + 51%|█████ | 5941/11728 [2:15:00<9:17:18, 5.78s/it] 51%|█████ | 5942/11728 [2:15:06<9:12:58, 5.73s/it] {'loss': 0.4646, 'learning_rate': 1.0270603461594861e-05, 'epoch': 0.51} + 51%|█████ | 5942/11728 [2:15:06<9:12:58, 5.73s/it] 51%|█████ | 5943/11728 [2:15:12<9:17:34, 5.78s/it] {'loss': 0.484, 'learning_rate': 1.0267842865685431e-05, 'epoch': 0.51} + 51%|█████ | 5943/11728 [2:15:12<9:17:34, 5.78s/it] 51%|█████ | 5944/11728 [2:15:18<9:19:26, 5.80s/it] {'loss': 0.4707, 'learning_rate': 1.0265082249349188e-05, 'epoch': 0.51} + 51%|█████ | 5944/11728 [2:15:18<9:19:26, 5.80s/it] 51%|█████ | 5945/11728 [2:15:24<9:17:55, 5.79s/it] {'loss': 0.4819, 'learning_rate': 1.0262321612796662e-05, 'epoch': 0.51} + 51%|█████ | 5945/11728 [2:15:24<9:17:55, 5.79s/it] 51%|█████ | 5946/11728 [2:15:29<9:22:53, 5.84s/it] {'loss': 0.4744, 'learning_rate': 1.02595609562384e-05, 'epoch': 0.51} + 51%|█████ | 5946/11728 [2:15:29<9:22:53, 5.84s/it] 51%|█████ | 5947/11728 [2:15:36<9:29:51, 5.91s/it] {'loss': 0.4858, 'learning_rate': 1.0256800279884934e-05, 'epoch': 0.51} + 51%|█████ | 5947/11728 [2:15:36<9:29:51, 5.91s/it] 51%|█████ | 5948/11728 [2:15:41<9:23:13, 5.85s/it] {'loss': 0.49, 'learning_rate': 1.0254039583946805e-05, 'epoch': 0.51} + 51%|█████ | 5948/11728 [2:15:41<9:23:13, 5.85s/it] 51%|█████ | 5949/11728 [2:15:47<9:15:19, 5.77s/it] {'loss': 0.4667, 'learning_rate': 1.0251278868634557e-05, 'epoch': 0.51} + 51%|█████ | 5949/11728 [2:15:47<9:15:19, 5.77s/it]2 AutoResumeHook: Checking whether to suspend... +06 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... + 51%|█████ | 5950/11728 [2:15:52<9:11:18, 5.72s/it]7 AutoResumeHook: Checking whether to suspend... +54 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4678, 'learning_rate': 1.024851813415873e-05, 'epoch': 0.51} + 51%|█████ | 5950/11728 [2:15:52<9:11:18, 5.72s/it] 51%|█████ | 5951/11728 [2:15:59<9:23:28, 5.85s/it] {'loss': 0.4741, 'learning_rate': 1.024575738072988e-05, 'epoch': 0.51} + 51%|█████ | 5951/11728 [2:15:59<9:23:28, 5.85s/it] 51%|█████ | 5952/11728 [2:16:04<9:15:17, 5.77s/it] {'loss': 0.4744, 'learning_rate': 1.0242996608558542e-05, 'epoch': 0.51} + 51%|█████ | 5952/11728 [2:16:04<9:15:17, 5.77s/it] 51%|█████ | 5953/11728 [2:16:10<9:07:52, 5.69s/it] {'loss': 0.4753, 'learning_rate': 1.0240235817855269e-05, 'epoch': 0.51} + 51%|█████ | 5953/11728 [2:16:10<9:07:52, 5.69s/it] 51%|█████ | 5954/11728 [2:16:16<9:13:24, 5.75s/it] {'loss': 0.4863, 'learning_rate': 1.0237475008830608e-05, 'epoch': 0.51} + 51%|█████ | 5954/11728 [2:16:16<9:13:24, 5.75s/it] 51%|█████ | 5955/11728 [2:16:22<9:20:37, 5.83s/it] {'loss': 0.4726, 'learning_rate': 1.0234714181695115e-05, 'epoch': 0.51} + 51%|█████ | 5955/11728 [2:16:22<9:20:37, 5.83s/it] 51%|█████ | 5956/11728 [2:16:28<9:28:32, 5.91s/it] {'loss': 0.4596, 'learning_rate': 1.0231953336659334e-05, 'epoch': 0.51} + 51%|█████ | 5956/11728 [2:16:28<9:28:32, 5.91s/it] 51%|█████ | 5957/11728 [2:16:34<9:36:24, 5.99s/it] {'loss': 0.4995, 'learning_rate': 1.0229192473933826e-05, 'epoch': 0.51} + 51%|█████ | 5957/11728 [2:16:34<9:36:24, 5.99s/it] 51%|█████ | 5958/11728 [2:16:40<9:31:52, 5.95s/it] {'loss': 0.4677, 'learning_rate': 1.0226431593729144e-05, 'epoch': 0.51} + 51%|█████ | 5958/11728 [2:16:40<9:31:52, 5.95s/it] 51%|█████ | 5959/11728 [2:16:46<9:39:22, 6.03s/it] {'loss': 0.4619, 'learning_rate': 1.022367069625584e-05, 'epoch': 0.51} + 51%|█████ | 5959/11728 [2:16:46<9:39:22, 6.03s/it] 51%|█████ | 5960/11728 [2:16:51<9:24:52, 5.88s/it] {'loss': 0.48, 'learning_rate': 1.0220909781724478e-05, 'epoch': 0.51} + 51%|█████ | 5960/11728 [2:16:51<9:24:52, 5.88s/it] 51%|█████ | 5961/11728 [2:16:57<9:15:52, 5.78s/it] {'loss': 0.4743, 'learning_rate': 1.0218148850345613e-05, 'epoch': 0.51} + 51%|█████ | 5961/11728 [2:16:57<9:15:52, 5.78s/it] 51%|█████ | 5962/11728 [2:17:03<9:12:06, 5.75s/it] {'loss': 0.4804, 'learning_rate': 1.0215387902329806e-05, 'epoch': 0.51} + 51%|█████ | 5962/11728 [2:17:03<9:12:06, 5.75s/it] 51%|█████ | 5963/11728 [2:17:09<9:24:09, 5.87s/it] {'loss': 0.5004, 'learning_rate': 1.0212626937887618e-05, 'epoch': 0.51} + 51%|█████ | 5963/11728 [2:17:09<9:24:09, 5.87s/it] 51%|█████ | 5964/11728 [2:17:15<9:20:25, 5.83s/it] {'loss': 0.4797, 'learning_rate': 1.0209865957229612e-05, 'epoch': 0.51} + 51%|█████ | 5964/11728 [2:17:15<9:20:25, 5.83s/it] 51%|█████ | 5965/11728 [2:17:20<9:11:30, 5.74s/it] {'loss': 0.4465, 'learning_rate': 1.020710496056635e-05, 'epoch': 0.51} + 51%|█████ | 5965/11728 [2:17:20<9:11:30, 5.74s/it] 51%|█████ | 5966/11728 [2:17:26<9:07:10, 5.70s/it] {'loss': 0.4503, 'learning_rate': 1.0204343948108402e-05, 'epoch': 0.51} + 51%|█████ | 5966/11728 [2:17:26<9:07:10, 5.70s/it] 51%|█████ | 5967/11728 [2:17:31<9:07:46, 5.71s/it] {'loss': 0.4827, 'learning_rate': 1.020158292006633e-05, 'epoch': 0.51} + 51%|█████ | 5967/11728 [2:17:31<9:07:46, 5.71s/it] 51%|█████ | 5968/11728 [2:17:37<9:08:10, 5.71s/it] {'loss': 0.4637, 'learning_rate': 1.0198821876650702e-05, 'epoch': 0.51} + 51%|█████ | 5968/11728 [2:17:37<9:08:10, 5.71s/it] 51%|█████ | 5969/11728 [2:17:43<9:04:11, 5.67s/it] {'loss': 0.4763, 'learning_rate': 1.019606081807209e-05, 'epoch': 0.51} + 51%|█████ | 5969/11728 [2:17:43<9:04:11, 5.67s/it] 51%|█████ | 5970/11728 [2:17:48<9:06:12, 5.69s/it] {'loss': 0.4657, 'learning_rate': 1.0193299744541063e-05, 'epoch': 0.51} + 51%|█████ | 5970/11728 [2:17:48<9:06:12, 5.69s/it] 51%|█████ | 5971/11728 [2:17:54<9:10:48, 5.74s/it] {'loss': 0.4821, 'learning_rate': 1.0190538656268186e-05, 'epoch': 0.51} + 51%|█████ | 5971/11728 [2:17:54<9:10:48, 5.74s/it] 51%|█████ | 5972/11728 [2:18:00<9:11:02, 5.74s/it] {'loss': 0.4611, 'learning_rate': 1.0187777553464038e-05, 'epoch': 0.51} + 51%|█████ | 5972/11728 [2:18:00<9:11:02, 5.74s/it] 51%|█████ | 5973/11728 [2:18:06<9:09:04, 5.72s/it] {'loss': 0.4889, 'learning_rate': 1.0185016436339187e-05, 'epoch': 0.51} + 51%|█████ | 5973/11728 [2:18:06<9:09:04, 5.72s/it] 51%|█████ | 5974/11728 [2:18:12<9:11:02, 5.75s/it] {'loss': 0.4882, 'learning_rate': 1.0182255305104215e-05, 'epoch': 0.51} + 51%|█████ | 5974/11728 [2:18:12<9:11:02, 5.75s/it] 51%|█████ | 5975/11728 [2:18:17<9:11:51, 5.76s/it] {'loss': 0.4727, 'learning_rate': 1.0179494159969687e-05, 'epoch': 0.51} + 51%|█████ | 5975/11728 [2:18:17<9:11:51, 5.76s/it] 51%|█████ | 5976/11728 [2:18:23<9:17:36, 5.82s/it] {'loss': 0.493, 'learning_rate': 1.017673300114619e-05, 'epoch': 0.51} + 51%|█████ | 5976/11728 [2:18:23<9:17:36, 5.82s/it] 51%|█████ | 5977/11728 [2:18:29<9:12:06, 5.76s/it] {'loss': 0.4503, 'learning_rate': 1.017397182884429e-05, 'epoch': 0.51} + 51%|█████ | 5977/11728 [2:18:29<9:12:06, 5.76s/it] 51%|█████ | 5978/11728 [2:18:34<9:03:35, 5.67s/it] {'loss': 0.4565, 'learning_rate': 1.017121064327458e-05, 'epoch': 0.51} + 51%|█████ | 5978/11728 [2:18:34<9:03:35, 5.67s/it] 51%|█████ | 5979/11728 [2:18:40<9:14:32, 5.79s/it] {'loss': 0.4727, 'learning_rate': 1.016844944464763e-05, 'epoch': 0.51} + 51%|█████ | 5979/11728 [2:18:40<9:14:32, 5.79s/it] 51%|█████ | 5980/11728 [2:18:46<9:16:50, 5.81s/it] {'loss': 0.4753, 'learning_rate': 1.0165688233174019e-05, 'epoch': 0.51} + 51%|█████ | 5980/11728 [2:18:46<9:16:50, 5.81s/it] 51%|█████ | 5981/11728 [2:18:52<9:12:22, 5.77s/it] {'loss': 0.4681, 'learning_rate': 1.0162927009064331e-05, 'epoch': 0.51} + 51%|█████ | 5981/11728 [2:18:52<9:12:22, 5.77s/it] 51%|█████ | 5982/11728 [2:18:58<9:12:55, 5.77s/it] {'loss': 0.47, 'learning_rate': 1.0160165772529151e-05, 'epoch': 0.51} + 51%|█████ | 5982/11728 [2:18:58<9:12:55, 5.77s/it] 51%|█████ | 5983/11728 [2:19:04<9:16:18, 5.81s/it] {'loss': 0.4869, 'learning_rate': 1.015740452377906e-05, 'epoch': 0.51} + 51%|█████ | 5983/11728 [2:19:04<9:16:18, 5.81s/it] 51%|█████ | 5984/11728 [2:19:10<9:17:45, 5.83s/it] {'loss': 0.4813, 'learning_rate': 1.0154643263024644e-05, 'epoch': 0.51} + 51%|█████ | 5984/11728 [2:19:10<9:17:45, 5.83s/it] 51%|█████ | 5985/11728 [2:19:15<9:17:24, 5.82s/it] {'loss': 0.4657, 'learning_rate': 1.0151881990476486e-05, 'epoch': 0.51} + 51%|█████ | 5985/11728 [2:19:15<9:17:24, 5.82s/it] 51%|█████ | 5986/11728 [2:19:21<9:19:16, 5.84s/it] {'loss': 0.4751, 'learning_rate': 1.0149120706345175e-05, 'epoch': 0.51} + 51%|█████ | 5986/11728 [2:19:21<9:19:16, 5.84s/it] 51%|█████ | 5987/11728 [2:19:27<9:20:52, 5.86s/it] {'loss': 0.4792, 'learning_rate': 1.0146359410841292e-05, 'epoch': 0.51} + 51%|█████ | 5987/11728 [2:19:27<9:20:52, 5.86s/it] 51%|█████ | 5988/11728 [2:19:33<9:14:15, 5.79s/it] {'loss': 0.4794, 'learning_rate': 1.0143598104175434e-05, 'epoch': 0.51} + 51%|█████ | 5988/11728 [2:19:33<9:14:15, 5.79s/it] 51%|█████ | 5989/11728 [2:19:38<9:06:32, 5.71s/it] {'loss': 0.475, 'learning_rate': 1.0140836786558184e-05, 'epoch': 0.51} + 51%|█████ | 5989/11728 [2:19:38<9:06:32, 5.71s/it] 51%|█████ | 5990/11728 [2:19:44<9:08:22, 5.73s/it] {'loss': 0.4674, 'learning_rate': 1.0138075458200132e-05, 'epoch': 0.51} + 51%|█████ | 5990/11728 [2:19:44<9:08:22, 5.73s/it] 51%|█████ | 5991/11728 [2:19:50<9:07:01, 5.72s/it] {'loss': 0.4528, 'learning_rate': 1.013531411931187e-05, 'epoch': 0.51} + 51%|█████ | 5991/11728 [2:19:50<9:07:01, 5.72s/it] 51%|█████ | 5992/11728 [2:19:56<9:16:46, 5.82s/it] {'loss': 0.4912, 'learning_rate': 1.0132552770103987e-05, 'epoch': 0.51} + 51%|█████ | 5992/11728 [2:19:56<9:16:46, 5.82s/it] 51%|█████ | 5993/11728 [2:20:02<9:17:17, 5.83s/it] {'loss': 0.4553, 'learning_rate': 1.0129791410787076e-05, 'epoch': 0.51} + 51%|█████ | 5993/11728 [2:20:02<9:17:17, 5.83s/it] 51%|█████ | 5994/11728 [2:20:07<9:08:44, 5.74s/it] {'loss': 0.471, 'learning_rate': 1.0127030041571733e-05, 'epoch': 0.51} + 51%|█████ | 5994/11728 [2:20:07<9:08:44, 5.74s/it] 51%|█████ | 5995/11728 [2:20:13<9:15:55, 5.82s/it] {'loss': 0.466, 'learning_rate': 1.0124268662668547e-05, 'epoch': 0.51} + 51%|█████ | 5995/11728 [2:20:13<9:15:55, 5.82s/it] 51%|█████ | 5996/11728 [2:20:19<9:25:26, 5.92s/it] {'loss': 0.5047, 'learning_rate': 1.0121507274288112e-05, 'epoch': 0.51} + 51%|█████ | 5996/11728 [2:20:19<9:25:26, 5.92s/it] 51%|█████ | 5997/11728 [2:20:25<9:29:23, 5.96s/it] {'loss': 0.478, 'learning_rate': 1.0118745876641025e-05, 'epoch': 0.51} + 51%|█████ | 5997/11728 [2:20:25<9:29:23, 5.96s/it] 51%|█████ | 5998/11728 [2:20:31<9:23:56, 5.91s/it] {'loss': 0.4828, 'learning_rate': 1.0115984469937883e-05, 'epoch': 0.51} + 51%|█████ | 5998/11728 [2:20:31<9:23:56, 5.91s/it] 51%|█████ | 5999/11728 [2:20:37<9:11:19, 5.77s/it] {'loss': 0.4653, 'learning_rate': 1.0113223054389284e-05, 'epoch': 0.51} + 51%|█████ | 5999/11728 [2:20:37<9:11:19, 5.77s/it]06 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... + 51%|█████ | 6000/11728 [2:20:42<9:04:21, 5.70s/it]73 AutoResumeHook: Checking whether to suspend... +AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4635, 'learning_rate': 1.0110461630205819e-05, 'epoch': 0.51} + 51%|█████ | 6000/11728 [2:20:42<9:04:21, 5.70s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-6000/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-6000/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-6000/mm_projector +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/torch/nn/modules/module.py:1802: UserWarning: Positional args are being deprecated, use kwargs instead. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details. + warnings.warn( + 51%|█████ | 6001/11728 [2:21:14<21:33:57, 13.56s/it] {'loss': 0.4854, 'learning_rate': 1.0107700197598089e-05, 'epoch': 0.51} + 51%|█████ | 6001/11728 [2:21:14<21:33:57, 13.56s/it] 51%|█████ | 6002/11728 [2:21:20<17:41:42, 11.13s/it] {'loss': 0.466, 'learning_rate': 1.0104938756776694e-05, 'epoch': 0.51} + 51%|█████ | 6002/11728 [2:21:20<17:41:42, 11.13s/it] 51%|█████ | 6003/11728 [2:21:26<15:14:37, 9.59s/it] {'loss': 0.473, 'learning_rate': 1.010217730795223e-05, 'epoch': 0.51} + 51%|█████ | 6003/11728 [2:21:26<15:14:37, 9.59s/it] 51%|█████ | 6004/11728 [2:21:32<13:35:12, 8.55s/it] {'loss': 0.4842, 'learning_rate': 1.00994158513353e-05, 'epoch': 0.51} + 51%|█████ | 6004/11728 [2:21:32<13:35:12, 8.55s/it] 51%|█████ | 6005/11728 [2:21:38<12:18:04, 7.74s/it] {'loss': 0.4973, 'learning_rate': 1.0096654387136497e-05, 'epoch': 0.51} + 51%|█████ | 6005/11728 [2:21:38<12:18:04, 7.74s/it] 51%|█████ | 6006/11728 [2:21:43<11:17:02, 7.10s/it] {'loss': 0.4845, 'learning_rate': 1.009389291556643e-05, 'epoch': 0.51} + 51%|█████ | 6006/11728 [2:21:43<11:17:02, 7.10s/it] 51%|█████ | 6007/11728 [2:21:49<10:42:54, 6.74s/it] {'loss': 0.479, 'learning_rate': 1.0091131436835698e-05, 'epoch': 0.51} + 51%|█████ | 6007/11728 [2:21:49<10:42:54, 6.74s/it] 51%|█████ | 6008/11728 [2:21:55<10:12:34, 6.43s/it] {'loss': 0.5021, 'learning_rate': 1.0088369951154904e-05, 'epoch': 0.51} + 51%|█████ | 6008/11728 [2:21:55<10:12:34, 6.43s/it] 51%|█████ | 6009/11728 [2:22:01<10:06:30, 6.36s/it] {'loss': 0.4843, 'learning_rate': 1.0085608458734644e-05, 'epoch': 0.51} + 51%|█████ | 6009/11728 [2:22:01<10:06:30, 6.36s/it] 51%|█████ | 6010/11728 [2:22:07<9:47:22, 6.16s/it] {'loss': 0.4672, 'learning_rate': 1.0082846959785528e-05, 'epoch': 0.51} + 51%|█████ | 6010/11728 [2:22:07<9:47:22, 6.16s/it] 51%|█████▏ | 6011/11728 [2:22:13<9:40:56, 6.10s/it] {'loss': 0.4962, 'learning_rate': 1.0080085454518158e-05, 'epoch': 0.51} + 51%|█████▏ | 6011/11728 [2:22:13<9:40:56, 6.10s/it] 51%|█████▏ | 6012/11728 [2:22:18<9:26:09, 5.94s/it] {'loss': 0.4777, 'learning_rate': 1.0077323943143134e-05, 'epoch': 0.51} + 51%|█████▏ | 6012/11728 [2:22:18<9:26:09, 5.94s/it] 51%|█████▏ | 6013/11728 [2:22:24<9:24:40, 5.93s/it] {'loss': 0.515, 'learning_rate': 1.0074562425871065e-05, 'epoch': 0.51} + 51%|█████▏ | 6013/11728 [2:22:24<9:24:40, 5.93s/it] 51%|█████▏ | 6014/11728 [2:22:30<9:16:22, 5.84s/it] {'loss': 0.4822, 'learning_rate': 1.0071800902912553e-05, 'epoch': 0.51} + 51%|█████▏ | 6014/11728 [2:22:30<9:16:22, 5.84s/it] 51%|█████▏ | 6015/11728 [2:22:36<9:17:45, 5.86s/it] {'loss': 0.4878, 'learning_rate': 1.0069039374478207e-05, 'epoch': 0.51} + 51%|█████▏ | 6015/11728 [2:22:36<9:17:45, 5.86s/it] 51%|█████▏ | 6016/11728 [2:22:41<9:16:04, 5.84s/it] {'loss': 0.4842, 'learning_rate': 1.0066277840778626e-05, 'epoch': 0.51} + 51%|█████▏ | 6016/11728 [2:22:41<9:16:04, 5.84s/it] 51%|█████▏ | 6017/11728 [2:22:47<9:09:40, 5.77s/it] {'loss': 0.4827, 'learning_rate': 1.0063516302024425e-05, 'epoch': 0.51} + 51%|█████▏ | 6017/11728 [2:22:47<9:09:40, 5.77s/it] 51%|█████▏ | 6018/11728 [2:22:53<9:12:07, 5.80s/it] {'loss': 0.4626, 'learning_rate': 1.0060754758426204e-05, 'epoch': 0.51} + 51%|█████▏ | 6018/11728 [2:22:53<9:12:07, 5.80s/it] 51%|█████▏ | 6019/11728 [2:22:58<9:04:09, 5.72s/it] {'loss': 0.4717, 'learning_rate': 1.005799321019457e-05, 'epoch': 0.51} + 51%|█████▏ | 6019/11728 [2:22:58<9:04:09, 5.72s/it] 51%|█████▏ | 6020/11728 [2:23:04<8:57:58, 5.66s/it] {'loss': 0.4908, 'learning_rate': 1.0055231657540132e-05, 'epoch': 0.51} + 51%|█████▏ | 6020/11728 [2:23:04<8:57:58, 5.66s/it] 51%|█████▏ | 6021/11728 [2:23:10<9:07:50, 5.76s/it] {'loss': 0.4868, 'learning_rate': 1.0052470100673495e-05, 'epoch': 0.51} + 51%|█████▏ | 6021/11728 [2:23:10<9:07:50, 5.76s/it] 51%|█████▏ | 6022/11728 [2:23:16<9:08:51, 5.77s/it] {'loss': 0.4825, 'learning_rate': 1.0049708539805274e-05, 'epoch': 0.51} + 51%|█████▏ | 6022/11728 [2:23:16<9:08:51, 5.77s/it] 51%|█████▏ | 6023/11728 [2:23:22<9:17:28, 5.86s/it] {'loss': 0.4784, 'learning_rate': 1.004694697514607e-05, 'epoch': 0.51} + 51%|█████▏ | 6023/11728 [2:23:22<9:17:28, 5.86s/it] 51%|█████▏ | 6024/11728 [2:23:27<9:07:59, 5.76s/it] {'loss': 0.4917, 'learning_rate': 1.0044185406906493e-05, 'epoch': 0.51} + 51%|█████▏ | 6024/11728 [2:23:27<9:07:59, 5.76s/it] 51%|█████▏ | 6025/11728 [2:23:33<9:04:26, 5.73s/it] {'loss': 0.4768, 'learning_rate': 1.0041423835297155e-05, 'epoch': 0.51} + 51%|█████▏ | 6025/11728 [2:23:33<9:04:26, 5.73s/it] 51%|█████▏ | 6026/11728 [2:23:39<9:07:58, 5.77s/it] {'loss': 0.4705, 'learning_rate': 1.003866226052866e-05, 'epoch': 0.51} + 51%|█████▏ | 6026/11728 [2:23:39<9:07:58, 5.77s/it] 51%|█████▏ | 6027/11728 [2:23:45<9:13:04, 5.82s/it] {'loss': 0.4645, 'learning_rate': 1.0035900682811619e-05, 'epoch': 0.51} + 51%|█████▏ | 6027/11728 [2:23:45<9:13:04, 5.82s/it] 51%|█████▏ | 6028/11728 [2:23:51<9:19:45, 5.89s/it] {'loss': 0.4896, 'learning_rate': 1.0033139102356641e-05, 'epoch': 0.51} + 51%|█████▏ | 6028/11728 [2:23:51<9:19:45, 5.89s/it] 51%|█████▏ | 6029/11728 [2:23:57<9:14:51, 5.84s/it] {'loss': 0.4921, 'learning_rate': 1.0030377519374342e-05, 'epoch': 0.51} + 51%|█████▏ | 6029/11728 [2:23:57<9:14:51, 5.84s/it] 51%|█████▏ | 6030/11728 [2:24:02<9:10:47, 5.80s/it] {'loss': 0.4532, 'learning_rate': 1.0027615934075321e-05, 'epoch': 0.51} + 51%|█████▏ | 6030/11728 [2:24:02<9:10:47, 5.80s/it] 51%|█████▏ | 6031/11728 [2:24:08<9:12:01, 5.81s/it] {'loss': 0.4717, 'learning_rate': 1.0024854346670196e-05, 'epoch': 0.51} + 51%|█████▏ | 6031/11728 [2:24:08<9:12:01, 5.81s/it] 51%|█████▏ | 6032/11728 [2:24:14<9:05:24, 5.75s/it] {'loss': 0.4716, 'learning_rate': 1.0022092757369575e-05, 'epoch': 0.51} + 51%|█████▏ | 6032/11728 [2:24:14<9:05:24, 5.75s/it] 51%|█████▏ | 6033/11728 [2:24:19<9:05:23, 5.75s/it] {'loss': 0.465, 'learning_rate': 1.0019331166384068e-05, 'epoch': 0.51} + 51%|█████▏ | 6033/11728 [2:24:19<9:05:23, 5.75s/it] 51%|█████▏ | 6034/11728 [2:24:25<9:05:39, 5.75s/it] {'loss': 0.4817, 'learning_rate': 1.0016569573924287e-05, 'epoch': 0.51} + 51%|█████▏ | 6034/11728 [2:24:25<9:05:39, 5.75s/it] 51%|█████▏ | 6035/11728 [2:24:31<9:09:35, 5.79s/it] {'loss': 0.4805, 'learning_rate': 1.0013807980200838e-05, 'epoch': 0.51} + 51%|█████▏ | 6035/11728 [2:24:31<9:09:35, 5.79s/it] 51%|█████▏ | 6036/11728 [2:24:37<9:09:29, 5.79s/it] {'loss': 0.4853, 'learning_rate': 1.0011046385424335e-05, 'epoch': 0.51} + 51%|█████▏ | 6036/11728 [2:24:37<9:09:29, 5.79s/it] 51%|█████▏ | 6037/11728 [2:24:42<9:04:31, 5.74s/it] {'loss': 0.4745, 'learning_rate': 1.0008284789805389e-05, 'epoch': 0.51} + 51%|█████▏ | 6037/11728 [2:24:42<9:04:31, 5.74s/it] 51%|█████▏ | 6038/11728 [2:24:48<9:03:44, 5.73s/it] {'loss': 0.4858, 'learning_rate': 1.0005523193554613e-05, 'epoch': 0.51} + 51%|█████▏ | 6038/11728 [2:24:48<9:03:44, 5.73s/it] 51%|█████▏ | 6039/11728 [2:24:54<9:09:12, 5.79s/it] {'loss': 0.4591, 'learning_rate': 1.000276159688261e-05, 'epoch': 0.51} + 51%|█████▏ | 6039/11728 [2:24:54<9:09:12, 5.79s/it] 52%|█████▏ | 6040/11728 [2:25:00<9:03:33, 5.73s/it] {'loss': 0.4665, 'learning_rate': 1e-05, 'epoch': 0.52} + 52%|█████▏ | 6040/11728 [2:25:00<9:03:33, 5.73s/it] 52%|█████▏ | 6041/11728 [2:25:05<8:59:51, 5.70s/it] {'loss': 0.4828, 'learning_rate': 9.997238403117391e-06, 'epoch': 0.52} + 52%|█████▏ | 6041/11728 [2:25:05<8:59:51, 5.70s/it] 52%|█████▏ | 6042/11728 [2:25:11<9:06:20, 5.77s/it] {'loss': 0.4682, 'learning_rate': 9.994476806445392e-06, 'epoch': 0.52} + 52%|█████▏ | 6042/11728 [2:25:11<9:06:20, 5.77s/it] 52%|█████▏ | 6043/11728 [2:25:17<8:59:57, 5.70s/it] {'loss': 0.476, 'learning_rate': 9.991715210194611e-06, 'epoch': 0.52} + 52%|█████▏ | 6043/11728 [2:25:17<8:59:57, 5.70s/it] 52%|█████▏ | 6044/11728 [2:25:22<8:56:41, 5.67s/it] {'loss': 0.492, 'learning_rate': 9.988953614575668e-06, 'epoch': 0.52} + 52%|█████▏ | 6044/11728 [2:25:22<8:56:41, 5.67s/it] 52%|█████▏ | 6045/11728 [2:25:28<8:53:06, 5.63s/it] {'loss': 0.4844, 'learning_rate': 9.986192019799166e-06, 'epoch': 0.52} + 52%|█████▏ | 6045/11728 [2:25:28<8:53:06, 5.63s/it] 52%|█████▏ | 6046/11728 [2:25:34<8:56:05, 5.66s/it] {'loss': 0.4737, 'learning_rate': 9.98343042607572e-06, 'epoch': 0.52} + 52%|█████▏ | 6046/11728 [2:25:34<8:56:05, 5.66s/it] 52%|█████▏ | 6047/11728 [2:25:39<8:54:35, 5.65s/it] {'loss': 0.4963, 'learning_rate': 9.980668833615933e-06, 'epoch': 0.52} + 52%|█████▏ | 6047/11728 [2:25:39<8:54:35, 5.65s/it] 52%|█████▏ | 6048/11728 [2:25:45<8:50:37, 5.61s/it] {'loss': 0.4672, 'learning_rate': 9.977907242630425e-06, 'epoch': 0.52} + 52%|█████▏ | 6048/11728 [2:25:45<8:50:37, 5.61s/it] 52%|█████▏ | 6049/11728 [2:25:51<9:00:05, 5.71s/it] {'loss': 0.4932, 'learning_rate': 9.975145653329806e-06, 'epoch': 0.52} + 52%|█████▏ | 6049/11728 [2:25:51<9:00:05, 5.71s/it]2 AutoResumeHook: Checking whether to suspend... +0 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... + 52%|█████▏ | 6050/11728 [2:25:56<8:56:21, 5.67s/it]4 AutoResumeHook: Checking whether to suspend... +37 AutoResumeHook: Checking whether to suspend...AutoResumeHook: Checking whether to suspend... + +1 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4732, 'learning_rate': 9.972384065924684e-06, 'epoch': 0.52} + 52%|█████▏ | 6050/11728 [2:25:56<8:56:21, 5.67s/it] 52%|█████▏ | 6051/11728 [2:26:02<8:58:07, 5.69s/it] {'loss': 0.4859, 'learning_rate': 9.969622480625663e-06, 'epoch': 0.52} + 52%|█████▏ | 6051/11728 [2:26:02<8:58:07, 5.69s/it] 52%|█████▏ | 6052/11728 [2:26:08<8:53:48, 5.64s/it] {'loss': 0.4964, 'learning_rate': 9.966860897643359e-06, 'epoch': 0.52} + 52%|█████▏ | 6052/11728 [2:26:08<8:53:48, 5.64s/it] 52%|█████▏ | 6053/11728 [2:26:14<9:05:36, 5.77s/it] {'loss': 0.4597, 'learning_rate': 9.964099317188384e-06, 'epoch': 0.52} + 52%|█████▏ | 6053/11728 [2:26:14<9:05:36, 5.77s/it] 52%|█████▏ | 6054/11728 [2:26:20<9:10:36, 5.82s/it] {'loss': 0.4657, 'learning_rate': 9.961337739471344e-06, 'epoch': 0.52} + 52%|█████▏ | 6054/11728 [2:26:20<9:10:36, 5.82s/it] 52%|█████▏ | 6055/11728 [2:26:25<9:07:26, 5.79s/it] {'loss': 0.4773, 'learning_rate': 9.95857616470285e-06, 'epoch': 0.52} + 52%|█████▏ | 6055/11728 [2:26:25<9:07:26, 5.79s/it] 52%|█████▏ | 6056/11728 [2:26:31<9:08:52, 5.81s/it] {'loss': 0.4645, 'learning_rate': 9.95581459309351e-06, 'epoch': 0.52} + 52%|█████▏ | 6056/11728 [2:26:31<9:08:52, 5.81s/it] 52%|█████▏ | 6057/11728 [2:26:37<9:13:17, 5.85s/it] {'loss': 0.5327, 'learning_rate': 9.953053024853932e-06, 'epoch': 0.52} + 52%|█████▏ | 6057/11728 [2:26:37<9:13:17, 5.85s/it] 52%|█████▏ | 6058/11728 [2:26:43<9:12:21, 5.85s/it] {'loss': 0.4825, 'learning_rate': 9.950291460194729e-06, 'epoch': 0.52} + 52%|█████▏ | 6058/11728 [2:26:43<9:12:21, 5.85s/it] 52%|█████▏ | 6059/11728 [2:26:49<9:20:25, 5.93s/it] {'loss': 0.47, 'learning_rate': 9.947529899326507e-06, 'epoch': 0.52} + 52%|█████▏ | 6059/11728 [2:26:49<9:20:25, 5.93s/it] 52%|█████▏ | 6060/11728 [2:26:55<9:09:23, 5.82s/it] {'loss': 0.4708, 'learning_rate': 9.944768342459872e-06, 'epoch': 0.52} + 52%|█████▏ | 6060/11728 [2:26:55<9:09:23, 5.82s/it] 52%|█████▏ | 6061/11728 [2:27:00<9:02:29, 5.74s/it] {'loss': 0.4622, 'learning_rate': 9.942006789805432e-06, 'epoch': 0.52} + 52%|█████▏ | 6061/11728 [2:27:00<9:02:29, 5.74s/it] 52%|█████▏ | 6062/11728 [2:27:06<8:57:40, 5.69s/it] {'loss': 0.4668, 'learning_rate': 9.939245241573801e-06, 'epoch': 0.52} + 52%|█████▏ | 6062/11728 [2:27:06<8:57:40, 5.69s/it] 52%|█████▏ | 6063/11728 [2:27:11<8:55:06, 5.67s/it] {'loss': 0.473, 'learning_rate': 9.936483697975578e-06, 'epoch': 0.52} + 52%|█████▏ | 6063/11728 [2:27:11<8:55:06, 5.67s/it] 52%|█████▏ | 6064/11728 [2:27:17<9:01:09, 5.73s/it] {'loss': 0.4742, 'learning_rate': 9.933722159221375e-06, 'epoch': 0.52} + 52%|█████▏ | 6064/11728 [2:27:17<9:01:09, 5.73s/it] 52%|█████▏ | 6065/11728 [2:27:24<9:21:09, 5.95s/it] {'loss': 0.4883, 'learning_rate': 9.930960625521798e-06, 'epoch': 0.52} + 52%|█████▏ | 6065/11728 [2:27:24<9:21:09, 5.95s/it] 52%|█████▏ | 6066/11728 [2:27:29<9:11:05, 5.84s/it] {'loss': 0.4683, 'learning_rate': 9.928199097087447e-06, 'epoch': 0.52} + 52%|█████▏ | 6066/11728 [2:27:29<9:11:05, 5.84s/it] 52%|█████▏ | 6067/11728 [2:27:35<9:11:16, 5.84s/it] {'loss': 0.4759, 'learning_rate': 9.925437574128938e-06, 'epoch': 0.52} + 52%|█████▏ | 6067/11728 [2:27:35<9:11:16, 5.84s/it] 52%|█████▏ | 6068/11728 [2:27:41<9:15:20, 5.89s/it] {'loss': 0.4885, 'learning_rate': 9.92267605685687e-06, 'epoch': 0.52} + 52%|█████▏ | 6068/11728 [2:27:41<9:15:20, 5.89s/it] 52%|█████▏ | 6069/11728 [2:27:47<9:06:53, 5.80s/it] {'loss': 0.4505, 'learning_rate': 9.919914545481847e-06, 'epoch': 0.52} + 52%|█████▏ | 6069/11728 [2:27:47<9:06:53, 5.80s/it] 52%|█████▏ | 6070/11728 [2:27:52<9:02:16, 5.75s/it] {'loss': 0.4669, 'learning_rate': 9.917153040214473e-06, 'epoch': 0.52} + 52%|█████▏ | 6070/11728 [2:27:52<9:02:16, 5.75s/it] 52%|█████▏ | 6071/11728 [2:27:58<9:02:35, 5.75s/it] {'loss': 0.4798, 'learning_rate': 9.914391541265358e-06, 'epoch': 0.52} + 52%|█████▏ | 6071/11728 [2:27:58<9:02:35, 5.75s/it] 52%|█████▏ | 6072/11728 [2:28:04<9:01:11, 5.74s/it] {'loss': 0.4624, 'learning_rate': 9.9116300488451e-06, 'epoch': 0.52} + 52%|█████▏ | 6072/11728 [2:28:04<9:01:11, 5.74s/it] 52%|█████▏ | 6073/11728 [2:28:10<9:01:53, 5.75s/it] {'loss': 0.4882, 'learning_rate': 9.908868563164305e-06, 'epoch': 0.52} + 52%|█████▏ | 6073/11728 [2:28:10<9:01:53, 5.75s/it] 52%|█████▏ | 6074/11728 [2:28:15<9:02:17, 5.75s/it] {'loss': 0.4799, 'learning_rate': 9.906107084433573e-06, 'epoch': 0.52} + 52%|█████▏ | 6074/11728 [2:28:15<9:02:17, 5.75s/it] 52%|█████▏ | 6075/11728 [2:28:21<9:01:58, 5.75s/it] {'loss': 0.4726, 'learning_rate': 9.903345612863503e-06, 'epoch': 0.52} + 52%|█████▏ | 6075/11728 [2:28:21<9:01:58, 5.75s/it] 52%|█████▏ | 6076/11728 [2:28:27<9:01:23, 5.75s/it] {'loss': 0.4645, 'learning_rate': 9.900584148664705e-06, 'epoch': 0.52} + 52%|█████▏ | 6076/11728 [2:28:27<9:01:23, 5.75s/it] 52%|█████▏ | 6077/11728 [2:28:33<9:05:30, 5.79s/it] {'loss': 0.4893, 'learning_rate': 9.897822692047772e-06, 'epoch': 0.52} + 52%|█████▏ | 6077/11728 [2:28:33<9:05:30, 5.79s/it] 52%|█████▏ | 6078/11728 [2:28:38<8:58:07, 5.71s/it] {'loss': 0.4651, 'learning_rate': 9.895061243223311e-06, 'epoch': 0.52} + 52%|█████▏ | 6078/11728 [2:28:38<8:58:07, 5.71s/it] 52%|█████▏ | 6079/11728 [2:28:44<8:59:17, 5.73s/it] {'loss': 0.4799, 'learning_rate': 9.892299802401911e-06, 'epoch': 0.52} + 52%|█████▏ | 6079/11728 [2:28:44<8:59:17, 5.73s/it] 52%|█████▏ | 6080/11728 [2:28:50<8:58:53, 5.72s/it] {'loss': 0.4726, 'learning_rate': 9.889538369794185e-06, 'epoch': 0.52} + 52%|█████▏ | 6080/11728 [2:28:50<8:58:53, 5.72s/it] 52%|█████▏ | 6081/11728 [2:28:55<8:58:17, 5.72s/it] {'loss': 0.4953, 'learning_rate': 9.886776945610719e-06, 'epoch': 0.52} + 52%|█████▏ | 6081/11728 [2:28:55<8:58:17, 5.72s/it] 52%|█████▏ | 6082/11728 [2:29:01<9:00:49, 5.75s/it] {'loss': 0.4747, 'learning_rate': 9.884015530062119e-06, 'epoch': 0.52} + 52%|█████▏ | 6082/11728 [2:29:01<9:00:49, 5.75s/it] 52%|█████▏ | 6083/11728 [2:29:07<8:59:53, 5.74s/it] {'loss': 0.4832, 'learning_rate': 9.881254123358977e-06, 'epoch': 0.52} + 52%|█████▏ | 6083/11728 [2:29:07<8:59:53, 5.74s/it] 52%|█████▏ | 6084/11728 [2:29:13<9:09:30, 5.84s/it] {'loss': 0.489, 'learning_rate': 9.87849272571189e-06, 'epoch': 0.52} + 52%|█████▏ | 6084/11728 [2:29:13<9:09:30, 5.84s/it] 52%|█████▏ | 6085/11728 [2:29:19<9:08:56, 5.84s/it] {'loss': 0.4612, 'learning_rate': 9.875731337331458e-06, 'epoch': 0.52} + 52%|█████▏ | 6085/11728 [2:29:19<9:08:56, 5.84s/it] 52%|█████▏ | 6086/11728 [2:29:25<9:16:21, 5.92s/it] {'loss': 0.4905, 'learning_rate': 9.87296995842827e-06, 'epoch': 0.52} + 52%|█████▏ | 6086/11728 [2:29:25<9:16:21, 5.92s/it] 52%|█████▏ | 6087/11728 [2:29:31<9:06:27, 5.81s/it] {'loss': 0.4682, 'learning_rate': 9.870208589212928e-06, 'epoch': 0.52} + 52%|█████▏ | 6087/11728 [2:29:31<9:06:27, 5.81s/it] 52%|█████▏ | 6088/11728 [2:29:36<9:07:54, 5.83s/it] {'loss': 0.4695, 'learning_rate': 9.86744722989602e-06, 'epoch': 0.52} + 52%|█████▏ | 6088/11728 [2:29:36<9:07:54, 5.83s/it] 52%|█████▏ | 6089/11728 [2:29:42<9:03:40, 5.78s/it] {'loss': 0.4961, 'learning_rate': 9.864685880688134e-06, 'epoch': 0.52} + 52%|█████▏ | 6089/11728 [2:29:42<9:03:40, 5.78s/it] 52%|█████▏ | 6090/11728 [2:29:48<8:59:20, 5.74s/it] {'loss': 0.4824, 'learning_rate': 9.86192454179987e-06, 'epoch': 0.52} + 52%|█████▏ | 6090/11728 [2:29:48<8:59:20, 5.74s/it] 52%|█████▏ | 6091/11728 [2:29:53<8:57:30, 5.72s/it] {'loss': 0.4904, 'learning_rate': 9.85916321344182e-06, 'epoch': 0.52} + 52%|█████▏ | 6091/11728 [2:29:53<8:57:30, 5.72s/it] 52%|█████▏ | 6092/11728 [2:29:59<9:00:30, 5.75s/it] {'loss': 0.4632, 'learning_rate': 9.85640189582457e-06, 'epoch': 0.52} + 52%|█████▏ | 6092/11728 [2:29:59<9:00:30, 5.75s/it] 52%|█████▏ | 6093/11728 [2:30:05<8:55:11, 5.70s/it] {'loss': 0.4639, 'learning_rate': 9.853640589158706e-06, 'epoch': 0.52} + 52%|█████▏ | 6093/11728 [2:30:05<8:55:11, 5.70s/it] 52%|█████▏ | 6094/11728 [2:30:11<8:56:26, 5.71s/it] {'loss': 0.4844, 'learning_rate': 9.850879293654829e-06, 'epoch': 0.52} + 52%|█████▏ | 6094/11728 [2:30:11<8:56:26, 5.71s/it] 52%|█████▏ | 6095/11728 [2:30:16<8:52:55, 5.68s/it] {'loss': 0.4678, 'learning_rate': 9.848118009523516e-06, 'epoch': 0.52} + 52%|█████▏ | 6095/11728 [2:30:16<8:52:55, 5.68s/it] 52%|█████▏ | 6096/11728 [2:30:22<8:54:46, 5.70s/it] {'loss': 0.4898, 'learning_rate': 9.84535673697536e-06, 'epoch': 0.52} + 52%|█████▏ | 6096/11728 [2:30:22<8:54:46, 5.70s/it] 52%|█████▏ | 6097/11728 [2:30:27<8:49:33, 5.64s/it] {'loss': 0.4592, 'learning_rate': 9.842595476220945e-06, 'epoch': 0.52} + 52%|█████▏ | 6097/11728 [2:30:27<8:49:33, 5.64s/it] 52%|█████▏ | 6098/11728 [2:30:33<8:44:50, 5.59s/it] {'loss': 0.4646, 'learning_rate': 9.839834227470852e-06, 'epoch': 0.52} + 52%|█████▏ | 6098/11728 [2:30:33<8:44:50, 5.59s/it] 52%|█████▏ | 6099/11728 [2:30:38<8:43:03, 5.58s/it] {'loss': 0.4695, 'learning_rate': 9.83707299093567e-06, 'epoch': 0.52} + 52%|█████▏ | 6099/11728 [2:30:38<8:43:03, 5.58s/it]2 AutoResumeHook: Checking whether to suspend... +05 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... + 52%|█████▏ | 6100/11728 [2:30:44<8:53:34, 5.69s/it]3 AutoResumeHook: Checking whether to suspend... +7 4AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4802, 'learning_rate': 9.834311766825986e-06, 'epoch': 0.52} + 52%|█████▏ | 6100/11728 [2:30:44<8:53:34, 5.69s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-6100/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-6100/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-6100/mm_projector +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/torch/nn/modules/module.py:1802: UserWarning: Positional args are being deprecated, use kwargs instead. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details. + warnings.warn( + 52%|█████▏ | 6101/11728 [2:31:16<21:11:23, 13.56s/it] {'loss': 0.4689, 'learning_rate': 9.831550555352375e-06, 'epoch': 0.52} + 52%|█████▏ | 6101/11728 [2:31:16<21:11:23, 13.56s/it] 52%|█████▏ | 6102/11728 [2:31:22<17:26:37, 11.16s/it] {'loss': 0.4615, 'learning_rate': 9.828789356725422e-06, 'epoch': 0.52} + 52%|█████▏ | 6102/11728 [2:31:22<17:26:37, 11.16s/it] 52%|█████▏ | 6103/11728 [2:31:28<14:54:42, 9.54s/it] {'loss': 0.4817, 'learning_rate': 9.82602817115571e-06, 'epoch': 0.52} + 52%|█████▏ | 6103/11728 [2:31:28<14:54:42, 9.54s/it] 52%|█████▏ | 6104/11728 [2:31:33<13:03:10, 8.36s/it] {'loss': 0.4849, 'learning_rate': 9.823266998853813e-06, 'epoch': 0.52} + 52%|█████▏ | 6104/11728 [2:31:33<13:03:10, 8.36s/it] 52%|█████▏ | 6105/11728 [2:31:39<11:49:07, 7.57s/it] {'loss': 0.4638, 'learning_rate': 9.820505840030315e-06, 'epoch': 0.52} + 52%|█████▏ | 6105/11728 [2:31:39<11:49:07, 7.57s/it] 52%|█████▏ | 6106/11728 [2:31:45<11:04:16, 7.09s/it] {'loss': 0.4677, 'learning_rate': 9.817744694895792e-06, 'epoch': 0.52} + 52%|█████▏ | 6106/11728 [2:31:45<11:04:16, 7.09s/it] 52%|█████▏ | 6107/11728 [2:31:51<10:33:15, 6.76s/it] {'loss': 0.4951, 'learning_rate': 9.814983563660814e-06, 'epoch': 0.52} + 52%|█████▏ | 6107/11728 [2:31:51<10:33:15, 6.76s/it] 52%|█████▏ | 6108/11728 [2:31:57<10:09:29, 6.51s/it] {'loss': 0.4591, 'learning_rate': 9.812222446535965e-06, 'epoch': 0.52} + 52%|█████▏ | 6108/11728 [2:31:57<10:09:29, 6.51s/it] 52%|█████▏ | 6109/11728 [2:32:02<9:40:34, 6.20s/it] {'loss': 0.4686, 'learning_rate': 9.80946134373182e-06, 'epoch': 0.52} + 52%|█████▏ | 6109/11728 [2:32:02<9:40:34, 6.20s/it] 52%|█████▏ | 6110/11728 [2:32:08<9:29:06, 6.08s/it] {'loss': 0.4719, 'learning_rate': 9.806700255458942e-06, 'epoch': 0.52} + 52%|█████▏ | 6110/11728 [2:32:08<9:29:06, 6.08s/it] 52%|█████▏ | 6111/11728 [2:32:14<9:17:46, 5.96s/it] {'loss': 0.462, 'learning_rate': 9.803939181927914e-06, 'epoch': 0.52} + 52%|█████▏ | 6111/11728 [2:32:14<9:17:46, 5.96s/it] 52%|█████▏ | 6112/11728 [2:32:20<9:22:13, 6.01s/it] {'loss': 0.489, 'learning_rate': 9.801178123349298e-06, 'epoch': 0.52} + 52%|█████▏ | 6112/11728 [2:32:20<9:22:13, 6.01s/it] 52%|█████▏ | 6113/11728 [2:32:25<9:08:13, 5.86s/it] {'loss': 0.4787, 'learning_rate': 9.798417079933672e-06, 'epoch': 0.52} + 52%|█████▏ | 6113/11728 [2:32:25<9:08:13, 5.86s/it] 52%|█████▏ | 6114/11728 [2:32:31<9:11:06, 5.89s/it] {'loss': 0.4843, 'learning_rate': 9.795656051891603e-06, 'epoch': 0.52} + 52%|█████▏ | 6114/11728 [2:32:31<9:11:06, 5.89s/it] 52%|█████▏ | 6115/11728 [2:32:37<9:10:45, 5.89s/it] {'loss': 0.4689, 'learning_rate': 9.792895039433655e-06, 'epoch': 0.52} + 52%|█████▏ | 6115/11728 [2:32:37<9:10:45, 5.89s/it] 52%|█████▏ | 6116/11728 [2:32:43<9:15:16, 5.94s/it] {'loss': 0.4866, 'learning_rate': 9.790134042770391e-06, 'epoch': 0.52} + 52%|█████▏ | 6116/11728 [2:32:43<9:15:16, 5.94s/it] 52%|█████▏ | 6117/11728 [2:32:49<9:13:34, 5.92s/it] {'loss': 0.4888, 'learning_rate': 9.787373062112386e-06, 'epoch': 0.52} + 52%|█████▏ | 6117/11728 [2:32:49<9:13:34, 5.92s/it] 52%|█████▏ | 6118/11728 [2:32:55<9:04:03, 5.82s/it] {'loss': 0.466, 'learning_rate': 9.7846120976702e-06, 'epoch': 0.52} + 52%|█████▏ | 6118/11728 [2:32:55<9:04:03, 5.82s/it] 52%|█████▏ | 6119/11728 [2:33:00<8:54:39, 5.72s/it] {'loss': 0.4824, 'learning_rate': 9.78185114965439e-06, 'epoch': 0.52} + 52%|█████▏ | 6119/11728 [2:33:00<8:54:39, 5.72s/it] 52%|█████▏ | 6120/11728 [2:33:06<9:00:21, 5.78s/it] {'loss': 0.4744, 'learning_rate': 9.779090218275527e-06, 'epoch': 0.52} + 52%|█████▏ | 6120/11728 [2:33:06<9:00:21, 5.78s/it] 52%|█████▏ | 6121/11728 [2:33:12<8:59:27, 5.77s/it] {'loss': 0.482, 'learning_rate': 9.77632930374416e-06, 'epoch': 0.52} + 52%|█████▏ | 6121/11728 [2:33:12<8:59:27, 5.77s/it] 52%|█████▏ | 6122/11728 [2:33:18<8:54:27, 5.72s/it] {'loss': 0.471, 'learning_rate': 9.773568406270857e-06, 'epoch': 0.52} + 52%|█████▏ | 6122/11728 [2:33:18<8:54:27, 5.72s/it] 52%|█████▏ | 6123/11728 [2:33:23<8:57:25, 5.75s/it] {'loss': 0.4827, 'learning_rate': 9.770807526066175e-06, 'epoch': 0.52} + 52%|█████▏ | 6123/11728 [2:33:23<8:57:25, 5.75s/it] 52%|█████▏ | 6124/11728 [2:33:29<9:00:46, 5.79s/it] {'loss': 0.4614, 'learning_rate': 9.76804666334067e-06, 'epoch': 0.52} + 52%|█████▏ | 6124/11728 [2:33:29<9:00:46, 5.79s/it] 52%|█████▏ | 6125/11728 [2:33:35<8:55:41, 5.74s/it] {'loss': 0.4601, 'learning_rate': 9.765285818304888e-06, 'epoch': 0.52} + 52%|█████▏ | 6125/11728 [2:33:35<8:55:41, 5.74s/it] 52%|█████▏ | 6126/11728 [2:33:41<8:58:56, 5.77s/it] {'loss': 0.4441, 'learning_rate': 9.762524991169392e-06, 'epoch': 0.52} + 52%|█████▏ | 6126/11728 [2:33:41<8:58:56, 5.77s/it] 52%|█████▏ | 6127/11728 [2:33:47<8:58:46, 5.77s/it] {'loss': 0.47, 'learning_rate': 9.759764182144734e-06, 'epoch': 0.52} + 52%|█████▏ | 6127/11728 [2:33:47<8:58:46, 5.77s/it] 52%|█████▏ | 6128/11728 [2:33:52<8:57:40, 5.76s/it] {'loss': 0.4982, 'learning_rate': 9.75700339144146e-06, 'epoch': 0.52} + 52%|█████▏ | 6128/11728 [2:33:52<8:57:40, 5.76s/it] 52%|█████▏ | 6129/11728 [2:33:58<8:53:45, 5.72s/it] {'loss': 0.4736, 'learning_rate': 9.754242619270125e-06, 'epoch': 0.52} + 52%|█████▏ | 6129/11728 [2:33:58<8:53:45, 5.72s/it] 52%|█████▏ | 6130/11728 [2:34:04<8:57:32, 5.76s/it] {'loss': 0.4609, 'learning_rate': 9.75148186584127e-06, 'epoch': 0.52} + 52%|█████▏ | 6130/11728 [2:34:04<8:57:32, 5.76s/it] 52%|█████▏ | 6131/11728 [2:34:10<8:59:57, 5.79s/it] {'loss': 0.4577, 'learning_rate': 9.748721131365445e-06, 'epoch': 0.52} + 52%|█████▏ | 6131/11728 [2:34:10<8:59:57, 5.79s/it] 52%|█████▏ | 6132/11728 [2:34:16<9:10:22, 5.90s/it] {'loss': 0.4844, 'learning_rate': 9.7459604160532e-06, 'epoch': 0.52} + 52%|█████▏ | 6132/11728 [2:34:16<9:10:22, 5.90s/it] 52%|█████▏ | 6133/11728 [2:34:22<9:06:52, 5.86s/it] {'loss': 0.4672, 'learning_rate': 9.743199720115071e-06, 'epoch': 0.52} + 52%|█████▏ | 6133/11728 [2:34:22<9:06:52, 5.86s/it] 52%|█████▏ | 6134/11728 [2:34:27<8:58:51, 5.78s/it] {'loss': 0.4493, 'learning_rate': 9.740439043761604e-06, 'epoch': 0.52} + 52%|█████▏ | 6134/11728 [2:34:27<8:58:51, 5.78s/it] 52%|█████▏ | 6135/11728 [2:34:33<8:50:33, 5.69s/it] {'loss': 0.466, 'learning_rate': 9.737678387203337e-06, 'epoch': 0.52} + 52%|█████▏ | 6135/11728 [2:34:33<8:50:33, 5.69s/it] 52%|█████▏ | 6136/11728 [2:34:38<8:54:31, 5.74s/it] {'loss': 0.4834, 'learning_rate': 9.734917750650817e-06, 'epoch': 0.52} + 52%|█████▏ | 6136/11728 [2:34:38<8:54:31, 5.74s/it] 52%|█████▏ | 6137/11728 [2:34:44<8:55:57, 5.75s/it] {'loss': 0.4748, 'learning_rate': 9.732157134314572e-06, 'epoch': 0.52} + 52%|█████▏ | 6137/11728 [2:34:44<8:55:57, 5.75s/it] 52%|█████▏ | 6138/11728 [2:34:50<8:57:09, 5.77s/it] {'loss': 0.4591, 'learning_rate': 9.729396538405144e-06, 'epoch': 0.52} + 52%|█████▏ | 6138/11728 [2:34:50<8:57:09, 5.77s/it] 52%|█████▏ | 6139/11728 [2:34:56<8:53:29, 5.73s/it] {'loss': 0.4752, 'learning_rate': 9.726635963133062e-06, 'epoch': 0.52} + 52%|█████▏ | 6139/11728 [2:34:56<8:53:29, 5.73s/it] 52%|█████▏ | 6140/11728 [2:35:01<8:54:24, 5.74s/it] {'loss': 0.4606, 'learning_rate': 9.723875408708866e-06, 'epoch': 0.52} + 52%|█████▏ | 6140/11728 [2:35:01<8:54:24, 5.74s/it] 52%|█████▏ | 6141/11728 [2:35:07<8:55:55, 5.76s/it] {'loss': 0.48, 'learning_rate': 9.721114875343085e-06, 'epoch': 0.52} + 52%|█████▏ | 6141/11728 [2:35:07<8:55:55, 5.76s/it] 52%|█████▏ | 6142/11728 [2:35:13<8:53:41, 5.73s/it] {'loss': 0.4794, 'learning_rate': 9.718354363246243e-06, 'epoch': 0.52} + 52%|█████▏ | 6142/11728 [2:35:13<8:53:41, 5.73s/it] 52%|█████▏ | 6143/11728 [2:35:18<8:47:16, 5.66s/it] {'loss': 0.4598, 'learning_rate': 9.71559387262888e-06, 'epoch': 0.52} + 52%|█████▏ | 6143/11728 [2:35:18<8:47:16, 5.66s/it] 52%|█████▏ | 6144/11728 [2:35:24<8:44:24, 5.63s/it] {'loss': 0.4812, 'learning_rate': 9.71283340370151e-06, 'epoch': 0.52} + 52%|█████▏ | 6144/11728 [2:35:24<8:44:24, 5.63s/it] 52%|█████▏ | 6145/11728 [2:35:30<8:51:12, 5.71s/it] {'loss': 0.4644, 'learning_rate': 9.710072956674666e-06, 'epoch': 0.52} + 52%|█████▏ | 6145/11728 [2:35:30<8:51:12, 5.71s/it] 52%|█████▏ | 6146/11728 [2:35:36<8:50:12, 5.70s/it] {'loss': 0.4799, 'learning_rate': 9.707312531758869e-06, 'epoch': 0.52} + 52%|█████▏ | 6146/11728 [2:35:36<8:50:12, 5.70s/it] 52%|█████▏ | 6147/11728 [2:35:41<8:53:22, 5.73s/it] {'loss': 0.4598, 'learning_rate': 9.704552129164641e-06, 'epoch': 0.52} + 52%|█████▏ | 6147/11728 [2:35:41<8:53:22, 5.73s/it] 52%|█████▏ | 6148/11728 [2:35:47<8:50:03, 5.70s/it] {'loss': 0.4861, 'learning_rate': 9.701791749102496e-06, 'epoch': 0.52} + 52%|█████▏ | 6148/11728 [2:35:47<8:50:03, 5.70s/it] 52%|█████▏ | 6149/11728 [2:35:53<8:54:52, 5.75s/it] {'loss': 0.4861, 'learning_rate': 9.69903139178296e-06, 'epoch': 0.52} + 52%|█████▏ | 6149/11728 [2:35:53<8:54:52, 5.75s/it]2 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend...5 + AutoResumeHook: Checking whether to suspend... +0 AutoResumeHook: Checking whether to suspend... + 52%|█████▏ | 6150/11728 [2:35:59<8:56:48, 5.77s/it]1 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4682, 'learning_rate': 9.69627105741655e-06, 'epoch': 0.52} + 52%|█████▏ | 6150/11728 [2:35:59<8:56:48, 5.77s/it] 52%|█████▏ | 6151/11728 [2:36:04<8:46:17, 5.66s/it] {'loss': 0.4756, 'learning_rate': 9.693510746213774e-06, 'epoch': 0.52} + 52%|█████▏ | 6151/11728 [2:36:04<8:46:17, 5.66s/it] 52%|█████▏ | 6152/11728 [2:36:10<8:48:51, 5.69s/it] {'loss': 0.4817, 'learning_rate': 9.69075045838515e-06, 'epoch': 0.52} + 52%|█████▏ | 6152/11728 [2:36:10<8:48:51, 5.69s/it] 52%|█████▏ | 6153/11728 [2:36:16<8:50:54, 5.71s/it] {'loss': 0.4685, 'learning_rate': 9.687990194141183e-06, 'epoch': 0.52} + 52%|█████▏ | 6153/11728 [2:36:16<8:50:54, 5.71s/it] 52%|█████▏ | 6154/11728 [2:36:21<8:54:20, 5.75s/it] {'loss': 0.4729, 'learning_rate': 9.68522995369239e-06, 'epoch': 0.52} + 52%|█████▏ | 6154/11728 [2:36:21<8:54:20, 5.75s/it] 52%|█████▏ | 6155/11728 [2:36:27<8:55:22, 5.76s/it] {'loss': 0.4664, 'learning_rate': 9.682469737249274e-06, 'epoch': 0.52} + 52%|█████▏ | 6155/11728 [2:36:27<8:55:22, 5.76s/it] 52%|█████▏ | 6156/11728 [2:36:33<8:59:46, 5.81s/it] {'loss': 0.4597, 'learning_rate': 9.679709545022343e-06, 'epoch': 0.52} + 52%|█████▏ | 6156/11728 [2:36:33<8:59:46, 5.81s/it] 52%|█████▏ | 6157/11728 [2:36:39<8:54:14, 5.75s/it] {'loss': 0.4712, 'learning_rate': 9.676949377222096e-06, 'epoch': 0.52} + 52%|█████▏ | 6157/11728 [2:36:39<8:54:14, 5.75s/it] 53%|█████▎ | 6158/11728 [2:36:45<8:55:01, 5.76s/it] {'loss': 0.4865, 'learning_rate': 9.67418923405904e-06, 'epoch': 0.53} + 53%|█████▎ | 6158/11728 [2:36:45<8:55:01, 5.76s/it] 53%|█████▎ | 6159/11728 [2:36:50<8:51:40, 5.73s/it] {'loss': 0.472, 'learning_rate': 9.671429115743674e-06, 'epoch': 0.53} + 53%|█████▎ | 6159/11728 [2:36:50<8:51:40, 5.73s/it] 53%|█████▎ | 6160/11728 [2:36:56<8:57:12, 5.79s/it] {'loss': 0.4792, 'learning_rate': 9.668669022486495e-06, 'epoch': 0.53} + 53%|█████▎ | 6160/11728 [2:36:56<8:57:12, 5.79s/it] 53%|█████▎ | 6161/11728 [2:37:02<8:49:20, 5.71s/it] {'loss': 0.4724, 'learning_rate': 9.665908954498e-06, 'epoch': 0.53} + 53%|█████▎ | 6161/11728 [2:37:02<8:49:20, 5.71s/it] 53%|█████▎ | 6162/11728 [2:37:08<8:58:49, 5.81s/it] {'loss': 0.486, 'learning_rate': 9.663148911988679e-06, 'epoch': 0.53} + 53%|█████▎ | 6162/11728 [2:37:08<8:58:49, 5.81s/it] 53%|█████▎ | 6163/11728 [2:37:13<8:53:39, 5.75s/it] {'loss': 0.4625, 'learning_rate': 9.660388895169034e-06, 'epoch': 0.53} + 53%|█████▎ | 6163/11728 [2:37:13<8:53:39, 5.75s/it] 53%|█████▎ | 6164/11728 [2:37:19<8:55:19, 5.77s/it] {'loss': 0.477, 'learning_rate': 9.657628904249546e-06, 'epoch': 0.53} + 53%|█████▎ | 6164/11728 [2:37:19<8:55:19, 5.77s/it] 53%|█████▎ | 6165/11728 [2:37:25<8:56:19, 5.78s/it] {'loss': 0.48, 'learning_rate': 9.65486893944071e-06, 'epoch': 0.53} + 53%|█████▎ | 6165/11728 [2:37:25<8:56:19, 5.78s/it] 53%|█████▎ | 6166/11728 [2:37:31<9:07:12, 5.90s/it] {'loss': 0.481, 'learning_rate': 9.652109000953007e-06, 'epoch': 0.53} + 53%|█████▎ | 6166/11728 [2:37:31<9:07:12, 5.90s/it] 53%|█████▎ | 6167/11728 [2:37:37<9:04:29, 5.87s/it] {'loss': 0.474, 'learning_rate': 9.649349088996922e-06, 'epoch': 0.53} + 53%|█████▎ | 6167/11728 [2:37:37<9:04:29, 5.87s/it] 53%|█████▎ | 6168/11728 [2:37:43<9:09:09, 5.93s/it] {'loss': 0.474, 'learning_rate': 9.646589203782944e-06, 'epoch': 0.53} + 53%|█████▎ | 6168/11728 [2:37:43<9:09:09, 5.93s/it] 53%|█████▎ | 6169/11728 [2:37:49<9:06:00, 5.89s/it] {'loss': 0.4812, 'learning_rate': 9.643829345521546e-06, 'epoch': 0.53} + 53%|█████▎ | 6169/11728 [2:37:49<9:06:00, 5.89s/it] 53%|█████▎ | 6170/11728 [2:37:55<9:04:03, 5.87s/it] {'loss': 0.4662, 'learning_rate': 9.641069514423212e-06, 'epoch': 0.53} + 53%|█████▎ | 6170/11728 [2:37:55<9:04:03, 5.87s/it] 53%|█████▎ | 6171/11728 [2:38:00<8:54:32, 5.77s/it] {'loss': 0.4751, 'learning_rate': 9.63830971069841e-06, 'epoch': 0.53} + 53%|█████▎ | 6171/11728 [2:38:00<8:54:32, 5.77s/it] 53%|█████▎ | 6172/11728 [2:38:06<8:58:18, 5.81s/it] {'loss': 0.4816, 'learning_rate': 9.635549934557626e-06, 'epoch': 0.53} + 53%|█████▎ | 6172/11728 [2:38:06<8:58:18, 5.81s/it] 53%|█████▎ | 6173/11728 [2:38:12<8:51:04, 5.74s/it] {'loss': 0.4732, 'learning_rate': 9.632790186211321e-06, 'epoch': 0.53} + 53%|█████▎ | 6173/11728 [2:38:12<8:51:04, 5.74s/it] 53%|█████▎ | 6174/11728 [2:38:17<8:50:39, 5.73s/it] {'loss': 0.4578, 'learning_rate': 9.630030465869972e-06, 'epoch': 0.53} + 53%|█████▎ | 6174/11728 [2:38:17<8:50:39, 5.73s/it] 53%|█████▎ | 6175/11728 [2:38:23<8:44:19, 5.67s/it] {'loss': 0.4806, 'learning_rate': 9.627270773744043e-06, 'epoch': 0.53} + 53%|█████▎ | 6175/11728 [2:38:23<8:44:19, 5.67s/it] 53%|█████▎ | 6176/11728 [2:38:29<8:52:14, 5.75s/it] {'loss': 0.4771, 'learning_rate': 9.624511110043999e-06, 'epoch': 0.53} + 53%|█████▎ | 6176/11728 [2:38:29<8:52:14, 5.75s/it] 53%|█████▎ | 6177/11728 [2:38:35<8:55:57, 5.79s/it] {'loss': 0.4751, 'learning_rate': 9.621751474980308e-06, 'epoch': 0.53} + 53%|█████▎ | 6177/11728 [2:38:35<8:55:57, 5.79s/it] 53%|█████▎ | 6178/11728 [2:38:40<8:53:41, 5.77s/it] {'loss': 0.4853, 'learning_rate': 9.618991868763428e-06, 'epoch': 0.53} + 53%|█████▎ | 6178/11728 [2:38:40<8:53:41, 5.77s/it] 53%|█████▎ | 6179/11728 [2:38:46<8:53:47, 5.77s/it] {'loss': 0.4701, 'learning_rate': 9.61623229160382e-06, 'epoch': 0.53} + 53%|█████▎ | 6179/11728 [2:38:46<8:53:47, 5.77s/it] 53%|█████▎ | 6180/11728 [2:38:52<8:53:43, 5.77s/it] {'loss': 0.4875, 'learning_rate': 9.613472743711937e-06, 'epoch': 0.53} + 53%|█████▎ | 6180/11728 [2:38:52<8:53:43, 5.77s/it] 53%|█████▎ | 6181/11728 [2:38:58<8:51:08, 5.75s/it] {'loss': 0.4865, 'learning_rate': 9.610713225298238e-06, 'epoch': 0.53} + 53%|█████▎ | 6181/11728 [2:38:58<8:51:08, 5.75s/it] 53%|█████▎ | 6182/11728 [2:39:03<8:43:06, 5.66s/it] {'loss': 0.4569, 'learning_rate': 9.607953736573173e-06, 'epoch': 0.53} + 53%|█████▎ | 6182/11728 [2:39:03<8:43:06, 5.66s/it] 53%|█████▎ | 6183/11728 [2:39:09<8:47:45, 5.71s/it] {'loss': 0.5042, 'learning_rate': 9.605194277747193e-06, 'epoch': 0.53} + 53%|█████▎ | 6183/11728 [2:39:09<8:47:45, 5.71s/it] 53%|█████▎ | 6184/11728 [2:39:15<8:49:38, 5.73s/it] {'loss': 0.4588, 'learning_rate': 9.602434849030747e-06, 'epoch': 0.53} + 53%|█████▎ | 6184/11728 [2:39:15<8:49:38, 5.73s/it] 53%|█████▎ | 6185/11728 [2:39:21<8:52:29, 5.76s/it] {'loss': 0.4904, 'learning_rate': 9.599675450634273e-06, 'epoch': 0.53} + 53%|█████▎ | 6185/11728 [2:39:21<8:52:29, 5.76s/it] 53%|█████▎ | 6186/11728 [2:39:26<8:48:15, 5.72s/it] {'loss': 0.4826, 'learning_rate': 9.596916082768228e-06, 'epoch': 0.53} + 53%|█████▎ | 6186/11728 [2:39:26<8:48:15, 5.72s/it] 53%|█████▎ | 6187/11728 [2:39:32<8:51:02, 5.75s/it] {'loss': 0.4766, 'learning_rate': 9.594156745643043e-06, 'epoch': 0.53} + 53%|█████▎ | 6187/11728 [2:39:32<8:51:02, 5.75s/it] 53%|█████▎ | 6188/11728 [2:39:38<9:02:32, 5.88s/it] {'loss': 0.4757, 'learning_rate': 9.59139743946916e-06, 'epoch': 0.53} + 53%|█████▎ | 6188/11728 [2:39:38<9:02:32, 5.88s/it] 53%|█████▎ | 6189/11728 [2:39:44<8:55:41, 5.80s/it] {'loss': 0.4814, 'learning_rate': 9.58863816445701e-06, 'epoch': 0.53} + 53%|█████▎ | 6189/11728 [2:39:44<8:55:41, 5.80s/it] 53%|█████▎ | 6190/11728 [2:39:50<9:02:38, 5.88s/it] {'loss': 0.4845, 'learning_rate': 9.585878920817032e-06, 'epoch': 0.53} + 53%|█████▎ | 6190/11728 [2:39:50<9:02:38, 5.88s/it] 53%|█████▎ | 6191/11728 [2:39:56<9:04:17, 5.90s/it] {'loss': 0.4909, 'learning_rate': 9.58311970875966e-06, 'epoch': 0.53} + 53%|█████▎ | 6191/11728 [2:39:56<9:04:17, 5.90s/it] 53%|█████▎ | 6192/11728 [2:40:01<8:56:11, 5.81s/it] {'loss': 0.4775, 'learning_rate': 9.58036052849532e-06, 'epoch': 0.53} + 53%|█████▎ | 6192/11728 [2:40:01<8:56:11, 5.81s/it] 53%|█████▎ | 6193/11728 [2:40:08<9:03:57, 5.90s/it] {'loss': 0.4571, 'learning_rate': 9.577601380234434e-06, 'epoch': 0.53} + 53%|█████▎ | 6193/11728 [2:40:08<9:03:57, 5.90s/it] 53%|█████▎ | 6194/11728 [2:40:13<9:06:08, 5.92s/it] {'loss': 0.4768, 'learning_rate': 9.57484226418743e-06, 'epoch': 0.53} + 53%|█████▎ | 6194/11728 [2:40:13<9:06:08, 5.92s/it] 53%|█████▎ | 6195/11728 [2:40:19<9:06:41, 5.93s/it] {'loss': 0.4771, 'learning_rate': 9.572083180564734e-06, 'epoch': 0.53} + 53%|█████▎ | 6195/11728 [2:40:19<9:06:41, 5.93s/it] 53%|█████▎ | 6196/11728 [2:40:25<8:55:53, 5.81s/it] {'loss': 0.4692, 'learning_rate': 9.569324129576756e-06, 'epoch': 0.53} + 53%|█████▎ | 6196/11728 [2:40:25<8:55:53, 5.81s/it] 53%|█████▎ | 6197/11728 [2:40:31<8:57:45, 5.83s/it] {'loss': 0.4704, 'learning_rate': 9.566565111433923e-06, 'epoch': 0.53} + 53%|█████▎ | 6197/11728 [2:40:31<8:57:45, 5.83s/it] 53%|█████▎ | 6198/11728 [2:40:37<9:01:38, 5.88s/it] {'loss': 0.4816, 'learning_rate': 9.563806126346643e-06, 'epoch': 0.53} + 53%|█████▎ | 6198/11728 [2:40:37<9:01:38, 5.88s/it] 53%|█████▎ | 6199/11728 [2:40:42<8:53:03, 5.78s/it] {'loss': 0.4768, 'learning_rate': 9.561047174525324e-06, 'epoch': 0.53} + 53%|█████▎ | 6199/11728 [2:40:42<8:53:03, 5.78s/it]2 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... +0 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... + 53%|█████▎ | 6200/11728 [2:40:48<8:49:11, 5.74s/it]4 AutoResumeHook: Checking whether to suspend... + {'loss': 0.466, 'learning_rate': 9.558288256180385e-06, 'epoch': 0.53} + 53%|█████▎ | 6200/11728 [2:40:48<8:49:11, 5.74s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-6200/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-6200/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-6200/mm_projector +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/torch/nn/modules/module.py:1802: UserWarning: Positional args are being deprecated, use kwargs instead. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details. + warnings.warn( + 53%|█████▎ | 6201/11728 [2:41:22<21:56:02, 14.29s/it] {'loss': 0.4843, 'learning_rate': 9.555529371522228e-06, 'epoch': 0.53} + 53%|█████▎ | 6201/11728 [2:41:22<21:56:02, 14.29s/it] 53%|█████▎ | 6202/11728 [2:41:28<18:09:52, 11.83s/it] {'loss': 0.4738, 'learning_rate': 9.552770520761256e-06, 'epoch': 0.53} + 53%|█████▎ | 6202/11728 [2:41:28<18:09:52, 11.83s/it] 53%|█████▎ | 6203/11728 [2:41:34<15:21:42, 10.01s/it] {'loss': 0.4789, 'learning_rate': 9.550011704107867e-06, 'epoch': 0.53} + 53%|█████▎ | 6203/11728 [2:41:34<15:21:42, 10.01s/it] 53%|█████▎ | 6204/11728 [2:41:40<13:19:26, 8.68s/it] {'loss': 0.4887, 'learning_rate': 9.54725292177247e-06, 'epoch': 0.53} + 53%|█████▎ | 6204/11728 [2:41:40<13:19:26, 8.68s/it] 53%|█████▎ | 6205/11728 [2:41:45<11:55:40, 7.77s/it] {'loss': 0.4714, 'learning_rate': 9.544494173965451e-06, 'epoch': 0.53} + 53%|█████▎ | 6205/11728 [2:41:45<11:55:40, 7.77s/it] 53%|█████▎ | 6206/11728 [2:41:51<10:56:48, 7.14s/it] {'loss': 0.4918, 'learning_rate': 9.541735460897211e-06, 'epoch': 0.53} + 53%|█████▎ | 6206/11728 [2:41:51<10:56:48, 7.14s/it] 53%|█████▎ | 6207/11728 [2:41:57<10:15:46, 6.69s/it] {'loss': 0.4777, 'learning_rate': 9.538976782778136e-06, 'epoch': 0.53} + 53%|█████▎ | 6207/11728 [2:41:57<10:15:46, 6.69s/it] 53%|█████▎ | 6208/11728 [2:42:03<9:58:18, 6.50s/it] {'loss': 0.4894, 'learning_rate': 9.536218139818615e-06, 'epoch': 0.53} + 53%|█████▎ | 6208/11728 [2:42:03<9:58:18, 6.50s/it] 53%|█████▎ | 6209/11728 [2:42:09<9:43:45, 6.35s/it] {'loss': 0.4892, 'learning_rate': 9.53345953222904e-06, 'epoch': 0.53} + 53%|█████▎ | 6209/11728 [2:42:09<9:43:45, 6.35s/it] 53%|█████▎ | 6210/11728 [2:42:14<9:23:11, 6.12s/it] {'loss': 0.4747, 'learning_rate': 9.530700960219787e-06, 'epoch': 0.53} + 53%|█████▎ | 6210/11728 [2:42:14<9:23:11, 6.12s/it] 53%|█████▎ | 6211/11728 [2:42:20<9:10:34, 5.99s/it] {'loss': 0.449, 'learning_rate': 9.527942424001235e-06, 'epoch': 0.53} + 53%|█████▎ | 6211/11728 [2:42:20<9:10:34, 5.99s/it] 53%|█████▎ | 6212/11728 [2:42:26<9:08:33, 5.97s/it] {'loss': 0.4876, 'learning_rate': 9.525183923783768e-06, 'epoch': 0.53} + 53%|█████▎ | 6212/11728 [2:42:26<9:08:33, 5.97s/it] 53%|█████▎ | 6213/11728 [2:42:32<9:01:15, 5.89s/it] {'loss': 0.468, 'learning_rate': 9.522425459777753e-06, 'epoch': 0.53} + 53%|█████▎ | 6213/11728 [2:42:32<9:01:15, 5.89s/it] 53%|█████▎ | 6214/11728 [2:42:37<8:59:22, 5.87s/it] {'loss': 0.4926, 'learning_rate': 9.519667032193569e-06, 'epoch': 0.53} + 53%|█████▎ | 6214/11728 [2:42:37<8:59:22, 5.87s/it] 53%|█████▎ | 6215/11728 [2:42:43<9:03:00, 5.91s/it] {'loss': 0.4882, 'learning_rate': 9.516908641241584e-06, 'epoch': 0.53} + 53%|█████▎ | 6215/11728 [2:42:43<9:03:00, 5.91s/it] 53%|█████▎ | 6216/11728 [2:42:49<8:53:04, 5.80s/it] {'loss': 0.4694, 'learning_rate': 9.51415028713216e-06, 'epoch': 0.53} + 53%|█████▎ | 6216/11728 [2:42:49<8:53:04, 5.80s/it] 53%|█████▎ | 6217/11728 [2:42:55<8:55:06, 5.83s/it] {'loss': 0.4771, 'learning_rate': 9.511391970075662e-06, 'epoch': 0.53} + 53%|█████▎ | 6217/11728 [2:42:55<8:55:06, 5.83s/it] 53%|█████▎ | 6218/11728 [2:43:00<8:47:42, 5.75s/it] {'loss': 0.4454, 'learning_rate': 9.508633690282456e-06, 'epoch': 0.53} + 53%|█████▎ | 6218/11728 [2:43:00<8:47:42, 5.75s/it] 53%|█████▎ | 6219/11728 [2:43:06<8:44:56, 5.72s/it] {'loss': 0.4853, 'learning_rate': 9.505875447962896e-06, 'epoch': 0.53} + 53%|█████▎ | 6219/11728 [2:43:06<8:44:56, 5.72s/it] 53%|█████▎ | 6220/11728 [2:43:12<8:51:14, 5.79s/it] {'loss': 0.4843, 'learning_rate': 9.503117243327336e-06, 'epoch': 0.53} + 53%|█████▎ | 6220/11728 [2:43:12<8:51:14, 5.79s/it] 53%|█████▎ | 6221/11728 [2:43:18<8:59:51, 5.88s/it] {'loss': 0.4748, 'learning_rate': 9.500359076586131e-06, 'epoch': 0.53} + 53%|█████▎ | 6221/11728 [2:43:18<8:59:51, 5.88s/it] 53%|█████▎ | 6222/11728 [2:43:24<8:57:10, 5.85s/it] {'loss': 0.4751, 'learning_rate': 9.497600947949625e-06, 'epoch': 0.53} + 53%|█████▎ | 6222/11728 [2:43:24<8:57:10, 5.85s/it] 53%|█████▎ | 6223/11728 [2:43:30<8:53:58, 5.82s/it] {'loss': 0.467, 'learning_rate': 9.49484285762817e-06, 'epoch': 0.53} + 53%|█████▎ | 6223/11728 [2:43:30<8:53:58, 5.82s/it] 53%|█████▎ | 6224/11728 [2:43:35<8:44:38, 5.72s/it] {'loss': 0.4712, 'learning_rate': 9.49208480583211e-06, 'epoch': 0.53} + 53%|█████▎ | 6224/11728 [2:43:35<8:44:38, 5.72s/it] 53%|█████▎ | 6225/11728 [2:43:41<8:50:12, 5.78s/it] {'loss': 0.4563, 'learning_rate': 9.489326792771781e-06, 'epoch': 0.53} + 53%|█████▎ | 6225/11728 [2:43:41<8:50:12, 5.78s/it] 53%|█████▎ | 6226/11728 [2:43:47<8:43:50, 5.71s/it] {'loss': 0.4878, 'learning_rate': 9.48656881865752e-06, 'epoch': 0.53} + 53%|█████▎ | 6226/11728 [2:43:47<8:43:50, 5.71s/it] 53%|█████▎ | 6227/11728 [2:43:52<8:43:06, 5.71s/it] {'loss': 0.476, 'learning_rate': 9.48381088369967e-06, 'epoch': 0.53} + 53%|█████▎ | 6227/11728 [2:43:52<8:43:06, 5.71s/it] 53%|█████▎ | 6228/11728 [2:43:58<8:44:57, 5.73s/it] {'loss': 0.4657, 'learning_rate': 9.481052988108556e-06, 'epoch': 0.53} + 53%|█████▎ | 6228/11728 [2:43:58<8:44:57, 5.73s/it] 53%|█████▎ | 6229/11728 [2:44:04<8:42:13, 5.70s/it] {'loss': 0.4677, 'learning_rate': 9.478295132094505e-06, 'epoch': 0.53} + 53%|█████▎ | 6229/11728 [2:44:04<8:42:13, 5.70s/it] 53%|█████▎ | 6230/11728 [2:44:09<8:40:21, 5.68s/it] {'loss': 0.4587, 'learning_rate': 9.47553731586785e-06, 'epoch': 0.53} + 53%|█████▎ | 6230/11728 [2:44:09<8:40:21, 5.68s/it] 53%|█████▎ | 6231/11728 [2:44:15<8:37:29, 5.65s/it] {'loss': 0.4511, 'learning_rate': 9.472779539638901e-06, 'epoch': 0.53} + 53%|█████▎ | 6231/11728 [2:44:15<8:37:29, 5.65s/it] 53%|█████▎ | 6232/11728 [2:44:21<8:37:23, 5.65s/it] {'loss': 0.469, 'learning_rate': 9.47002180361799e-06, 'epoch': 0.53} + 53%|█████▎ | 6232/11728 [2:44:21<8:37:23, 5.65s/it] 53%|█████▎ | 6233/11728 [2:44:26<8:33:19, 5.60s/it] {'loss': 0.4849, 'learning_rate': 9.46726410801543e-06, 'epoch': 0.53} + 53%|█████▎ | 6233/11728 [2:44:26<8:33:19, 5.60s/it] 53%|█████▎ | 6234/11728 [2:44:32<8:32:20, 5.60s/it] {'loss': 0.4751, 'learning_rate': 9.464506453041532e-06, 'epoch': 0.53} + 53%|█████▎ | 6234/11728 [2:44:32<8:32:20, 5.60s/it] 53%|█████▎ | 6235/11728 [2:44:37<8:35:17, 5.63s/it] {'loss': 0.4923, 'learning_rate': 9.461748838906606e-06, 'epoch': 0.53} + 53%|█████▎ | 6235/11728 [2:44:37<8:35:17, 5.63s/it] 53%|█████▎ | 6236/11728 [2:44:43<8:36:09, 5.64s/it] {'loss': 0.4905, 'learning_rate': 9.458991265820962e-06, 'epoch': 0.53} + 53%|█████▎ | 6236/11728 [2:44:43<8:36:09, 5.64s/it] 53%|█████▎ | 6237/11728 [2:44:49<8:47:53, 5.77s/it] {'loss': 0.4865, 'learning_rate': 9.456233733994906e-06, 'epoch': 0.53} + 53%|█████▎ | 6237/11728 [2:44:49<8:47:53, 5.77s/it] 53%|█████▎ | 6238/11728 [2:44:55<8:53:13, 5.83s/it] {'loss': 0.4761, 'learning_rate': 9.45347624363873e-06, 'epoch': 0.53} + 53%|█████▎ | 6238/11728 [2:44:55<8:53:13, 5.83s/it] 53%|█████▎ | 6239/11728 [2:45:01<8:44:59, 5.74s/it] {'loss': 0.4512, 'learning_rate': 9.450718794962742e-06, 'epoch': 0.53} + 53%|█████▎ | 6239/11728 [2:45:01<8:44:59, 5.74s/it] 53%|█████▎ | 6240/11728 [2:45:06<8:43:28, 5.72s/it] {'loss': 0.4898, 'learning_rate': 9.447961388177227e-06, 'epoch': 0.53} + 53%|█████▎ | 6240/11728 [2:45:06<8:43:28, 5.72s/it] 53%|█████▎ | 6241/11728 [2:45:12<8:37:55, 5.66s/it] {'loss': 0.4407, 'learning_rate': 9.445204023492484e-06, 'epoch': 0.53} + 53%|█████▎ | 6241/11728 [2:45:12<8:37:55, 5.66s/it] 53%|█████▎ | 6242/11728 [2:45:18<8:40:45, 5.70s/it] {'loss': 0.4823, 'learning_rate': 9.4424467011188e-06, 'epoch': 0.53} + 53%|█████▎ | 6242/11728 [2:45:18<8:40:45, 5.70s/it] 53%|█████▎ | 6243/11728 [2:45:23<8:38:12, 5.67s/it] {'loss': 0.478, 'learning_rate': 9.439689421266456e-06, 'epoch': 0.53} + 53%|█████▎ | 6243/11728 [2:45:23<8:38:12, 5.67s/it] 53%|█████▎ | 6244/11728 [2:45:29<8:36:47, 5.65s/it] {'loss': 0.4615, 'learning_rate': 9.436932184145737e-06, 'epoch': 0.53} + 53%|█████▎ | 6244/11728 [2:45:29<8:36:47, 5.65s/it] 53%|█████▎ | 6245/11728 [2:45:35<8:40:22, 5.69s/it] {'loss': 0.4897, 'learning_rate': 9.434174989966917e-06, 'epoch': 0.53} + 53%|█████▎ | 6245/11728 [2:45:35<8:40:22, 5.69s/it] 53%|█████▎ | 6246/11728 [2:45:40<8:38:47, 5.68s/it] {'loss': 0.4927, 'learning_rate': 9.43141783894028e-06, 'epoch': 0.53} + 53%|█████▎ | 6246/11728 [2:45:40<8:38:47, 5.68s/it] 53%|█████▎ | 6247/11728 [2:45:46<8:34:39, 5.63s/it] {'loss': 0.4566, 'learning_rate': 9.428660731276089e-06, 'epoch': 0.53} + 53%|█████▎ | 6247/11728 [2:45:46<8:34:39, 5.63s/it] 53%|█████▎ | 6248/11728 [2:45:52<8:38:22, 5.68s/it] {'loss': 0.4581, 'learning_rate': 9.425903667184619e-06, 'epoch': 0.53} + 53%|█████▎ | 6248/11728 [2:45:52<8:38:22, 5.68s/it] 53%|█████▎ | 6249/11728 [2:45:57<8:42:06, 5.72s/it] {'loss': 0.4764, 'learning_rate': 9.423146646876126e-06, 'epoch': 0.53} + 53%|█████▎ | 6249/11728 [2:45:57<8:42:06, 5.72s/it]7 AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +05 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... + 53%|█████▎ | 6250/11728 [2:46:03<8:42:38, 5.72s/it]4 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4642, 'learning_rate': 9.42038967056088e-06, 'epoch': 0.53} + 53%|█████▎ | 6250/11728 [2:46:03<8:42:38, 5.72s/it] 53%|█████▎ | 6251/11728 [2:46:09<8:40:38, 5.70s/it] {'loss': 0.4942, 'learning_rate': 9.417632738449143e-06, 'epoch': 0.53} + 53%|█████▎ | 6251/11728 [2:46:09<8:40:38, 5.70s/it] 53%|█████▎ | 6252/11728 [2:46:14<8:34:49, 5.64s/it] {'loss': 0.4767, 'learning_rate': 9.41487585075116e-06, 'epoch': 0.53} + 53%|█████▎ | 6252/11728 [2:46:14<8:34:49, 5.64s/it] 53%|█████▎ | 6253/11728 [2:46:20<8:38:46, 5.69s/it] {'loss': 0.4783, 'learning_rate': 9.41211900767719e-06, 'epoch': 0.53} + 53%|█████▎ | 6253/11728 [2:46:20<8:38:46, 5.69s/it] 53%|█████▎ | 6254/11728 [2:46:26<8:42:44, 5.73s/it] {'loss': 0.479, 'learning_rate': 9.409362209437474e-06, 'epoch': 0.53} + 53%|█████▎ | 6254/11728 [2:46:26<8:42:44, 5.73s/it] 53%|█████▎ | 6255/11728 [2:46:31<8:35:24, 5.65s/it] {'loss': 0.4639, 'learning_rate': 9.406605456242265e-06, 'epoch': 0.53} + 53%|█████▎ | 6255/11728 [2:46:31<8:35:24, 5.65s/it] 53%|█████▎ | 6256/11728 [2:46:37<8:36:23, 5.66s/it] {'loss': 0.4875, 'learning_rate': 9.403848748301802e-06, 'epoch': 0.53} + 53%|█████▎ | 6256/11728 [2:46:37<8:36:23, 5.66s/it] 53%|█████▎ | 6257/11728 [2:46:43<8:50:41, 5.82s/it] {'loss': 0.4694, 'learning_rate': 9.401092085826325e-06, 'epoch': 0.53} + 53%|█████▎ | 6257/11728 [2:46:43<8:50:41, 5.82s/it] 53%|█████▎ | 6258/11728 [2:46:49<8:43:14, 5.74s/it] {'loss': 0.4753, 'learning_rate': 9.398335469026058e-06, 'epoch': 0.53} + 53%|█████▎ | 6258/11728 [2:46:49<8:43:14, 5.74s/it] 53%|█████▎ | 6259/11728 [2:46:55<8:47:03, 5.78s/it] {'loss': 0.4751, 'learning_rate': 9.395578898111243e-06, 'epoch': 0.53} + 53%|█████▎ | 6259/11728 [2:46:55<8:47:03, 5.78s/it] 53%|█████▎ | 6260/11728 [2:47:01<8:49:00, 5.80s/it] {'loss': 0.4717, 'learning_rate': 9.392822373292108e-06, 'epoch': 0.53} + 53%|█████▎ | 6260/11728 [2:47:01<8:49:00, 5.80s/it] 53%|█████▎ | 6261/11728 [2:47:06<8:49:02, 5.81s/it] {'loss': 0.4929, 'learning_rate': 9.390065894778872e-06, 'epoch': 0.53} + 53%|█████▎ | 6261/11728 [2:47:06<8:49:02, 5.81s/it] 53%|█████▎ | 6262/11728 [2:47:12<8:52:46, 5.85s/it] {'loss': 0.475, 'learning_rate': 9.387309462781759e-06, 'epoch': 0.53} + 53%|█████▎ | 6262/11728 [2:47:12<8:52:46, 5.85s/it] 53%|█████▎ | 6263/11728 [2:47:18<8:47:55, 5.80s/it] {'loss': 0.4837, 'learning_rate': 9.38455307751098e-06, 'epoch': 0.53} + 53%|█████▎ | 6263/11728 [2:47:18<8:47:55, 5.80s/it] 53%|█████▎ | 6264/11728 [2:47:24<8:42:48, 5.74s/it] {'loss': 0.4673, 'learning_rate': 9.381796739176754e-06, 'epoch': 0.53} + 53%|█████▎ | 6264/11728 [2:47:24<8:42:48, 5.74s/it] 53%|█████▎ | 6265/11728 [2:47:29<8:47:03, 5.79s/it] {'loss': 0.4791, 'learning_rate': 9.379040447989292e-06, 'epoch': 0.53} + 53%|█████▎ | 6265/11728 [2:47:29<8:47:03, 5.79s/it] 53%|█████▎ | 6266/11728 [2:47:35<8:40:27, 5.72s/it] {'loss': 0.486, 'learning_rate': 9.3762842041588e-06, 'epoch': 0.53} + 53%|█████▎ | 6266/11728 [2:47:35<8:40:27, 5.72s/it] 53%|█████▎ | 6267/11728 [2:47:41<8:39:03, 5.70s/it] {'loss': 0.453, 'learning_rate': 9.373528007895473e-06, 'epoch': 0.53} + 53%|█████▎ | 6267/11728 [2:47:41<8:39:03, 5.70s/it] 53%|█████▎ | 6268/11728 [2:47:47<8:43:05, 5.75s/it] {'loss': 0.4836, 'learning_rate': 9.370771859409514e-06, 'epoch': 0.53} + 53%|█████▎ | 6268/11728 [2:47:47<8:43:05, 5.75s/it] 53%|█████▎ | 6269/11728 [2:47:52<8:39:35, 5.71s/it] {'loss': 0.4682, 'learning_rate': 9.368015758911126e-06, 'epoch': 0.53} + 53%|█████▎ | 6269/11728 [2:47:52<8:39:35, 5.71s/it] 53%|█████▎ | 6270/11728 [2:47:58<8:41:37, 5.73s/it] {'loss': 0.4841, 'learning_rate': 9.365259706610491e-06, 'epoch': 0.53} + 53%|█████▎ | 6270/11728 [2:47:58<8:41:37, 5.73s/it] 53%|█████▎ | 6271/11728 [2:48:04<8:41:55, 5.74s/it] {'loss': 0.4676, 'learning_rate': 9.362503702717803e-06, 'epoch': 0.53} + 53%|█████▎ | 6271/11728 [2:48:04<8:41:55, 5.74s/it] 53%|█████▎ | 6272/11728 [2:48:09<8:38:17, 5.70s/it] {'loss': 0.4645, 'learning_rate': 9.359747747443241e-06, 'epoch': 0.53} + 53%|█████▎ | 6272/11728 [2:48:09<8:38:17, 5.70s/it] 53%|█████▎ | 6273/11728 [2:48:15<8:34:20, 5.66s/it] {'loss': 0.4624, 'learning_rate': 9.356991840996991e-06, 'epoch': 0.53} + 53%|█████▎ | 6273/11728 [2:48:15<8:34:20, 5.66s/it] 53%|█████▎ | 6274/11728 [2:48:20<8:32:43, 5.64s/it] {'loss': 0.4834, 'learning_rate': 9.354235983589229e-06, 'epoch': 0.53} + 53%|█████▎ | 6274/11728 [2:48:20<8:32:43, 5.64s/it] 54%|█████▎ | 6275/11728 [2:48:26<8:36:26, 5.68s/it] {'loss': 0.4747, 'learning_rate': 9.351480175430126e-06, 'epoch': 0.54} + 54%|█████▎ | 6275/11728 [2:48:26<8:36:26, 5.68s/it] 54%|█████▎ | 6276/11728 [2:48:32<8:33:02, 5.65s/it] {'loss': 0.4625, 'learning_rate': 9.348724416729852e-06, 'epoch': 0.54} + 54%|█████▎ | 6276/11728 [2:48:32<8:33:02, 5.65s/it] 54%|█████▎ | 6277/11728 [2:48:37<8:25:59, 5.57s/it] {'loss': 0.4691, 'learning_rate': 9.34596870769857e-06, 'epoch': 0.54} + 54%|█████▎ | 6277/11728 [2:48:37<8:25:59, 5.57s/it] 54%|█████▎ | 6278/11728 [2:48:43<8:30:33, 5.62s/it] {'loss': 0.4711, 'learning_rate': 9.34321304854645e-06, 'epoch': 0.54} + 54%|█████▎ | 6278/11728 [2:48:43<8:30:33, 5.62s/it] 54%|█████▎ | 6279/11728 [2:48:48<8:27:35, 5.59s/it] {'loss': 0.4869, 'learning_rate': 9.34045743948364e-06, 'epoch': 0.54} + 54%|█████▎ | 6279/11728 [2:48:48<8:27:35, 5.59s/it] 54%|█████▎ | 6280/11728 [2:48:55<8:41:46, 5.75s/it] {'loss': 0.4757, 'learning_rate': 9.337701880720303e-06, 'epoch': 0.54} + 54%|█████▎ | 6280/11728 [2:48:55<8:41:46, 5.75s/it] 54%|█████▎ | 6281/11728 [2:49:00<8:38:38, 5.71s/it] {'loss': 0.5034, 'learning_rate': 9.334946372466582e-06, 'epoch': 0.54} + 54%|█████▎ | 6281/11728 [2:49:00<8:38:38, 5.71s/it] 54%|█████▎ | 6282/11728 [2:49:06<8:32:18, 5.64s/it] {'loss': 0.4926, 'learning_rate': 9.332190914932629e-06, 'epoch': 0.54} + 54%|█████▎ | 6282/11728 [2:49:06<8:32:18, 5.64s/it] 54%|█████▎ | 6283/11728 [2:49:11<8:35:05, 5.68s/it] {'loss': 0.4664, 'learning_rate': 9.329435508328587e-06, 'epoch': 0.54} + 54%|█████▎ | 6283/11728 [2:49:11<8:35:05, 5.68s/it] 54%|█████▎ | 6284/11728 [2:49:18<8:48:03, 5.82s/it] {'loss': 0.4675, 'learning_rate': 9.326680152864592e-06, 'epoch': 0.54} + 54%|█████▎ | 6284/11728 [2:49:18<8:48:03, 5.82s/it] 54%|█████▎ | 6285/11728 [2:49:23<8:45:40, 5.79s/it] {'loss': 0.4657, 'learning_rate': 9.323924848750777e-06, 'epoch': 0.54} + 54%|█████▎ | 6285/11728 [2:49:23<8:45:40, 5.79s/it] 54%|█████▎ | 6286/11728 [2:49:29<8:53:08, 5.88s/it] {'loss': 0.473, 'learning_rate': 9.321169596197274e-06, 'epoch': 0.54} + 54%|█████▎ | 6286/11728 [2:49:29<8:53:08, 5.88s/it] 54%|█████▎ | 6287/11728 [2:49:35<8:53:40, 5.88s/it] {'loss': 0.4819, 'learning_rate': 9.318414395414216e-06, 'epoch': 0.54} + 54%|█████▎ | 6287/11728 [2:49:35<8:53:40, 5.88s/it] 54%|█████▎ | 6288/11728 [2:49:41<8:49:09, 5.84s/it] {'loss': 0.464, 'learning_rate': 9.31565924661172e-06, 'epoch': 0.54} + 54%|█████▎ | 6288/11728 [2:49:41<8:49:09, 5.84s/it] 54%|█████▎ | 6289/11728 [2:49:47<8:45:54, 5.80s/it] {'loss': 0.4602, 'learning_rate': 9.312904149999909e-06, 'epoch': 0.54} + 54%|█████▎ | 6289/11728 [2:49:47<8:45:54, 5.80s/it] 54%|█████▎ | 6290/11728 [2:49:53<8:48:03, 5.83s/it] {'loss': 0.4684, 'learning_rate': 9.310149105788892e-06, 'epoch': 0.54} + 54%|█████▎ | 6290/11728 [2:49:53<8:48:03, 5.83s/it] 54%|█████▎ | 6291/11728 [2:49:58<8:41:58, 5.76s/it] {'loss': 0.4621, 'learning_rate': 9.307394114188786e-06, 'epoch': 0.54} + 54%|█████▎ | 6291/11728 [2:49:58<8:41:58, 5.76s/it] 54%|█████▎ | 6292/11728 [2:50:04<8:41:41, 5.76s/it] {'loss': 0.4903, 'learning_rate': 9.304639175409699e-06, 'epoch': 0.54} + 54%|█████▎ | 6292/11728 [2:50:04<8:41:41, 5.76s/it] 54%|█████▎ | 6293/11728 [2:50:10<8:43:09, 5.78s/it] {'loss': 0.4553, 'learning_rate': 9.30188428966173e-06, 'epoch': 0.54} + 54%|█████▎ | 6293/11728 [2:50:10<8:43:09, 5.78s/it] 54%|█████▎ | 6294/11728 [2:50:16<8:42:51, 5.77s/it] {'loss': 0.4692, 'learning_rate': 9.299129457154979e-06, 'epoch': 0.54} + 54%|█████▎ | 6294/11728 [2:50:16<8:42:51, 5.77s/it] 54%|█████▎ | 6295/11728 [2:50:21<8:36:31, 5.70s/it] {'loss': 0.4889, 'learning_rate': 9.29637467809954e-06, 'epoch': 0.54} + 54%|█████▎ | 6295/11728 [2:50:21<8:36:31, 5.70s/it] 54%|█████▎ | 6296/11728 [2:50:27<8:42:26, 5.77s/it] {'loss': 0.467, 'learning_rate': 9.293619952705509e-06, 'epoch': 0.54} + 54%|█████▎ | 6296/11728 [2:50:27<8:42:26, 5.77s/it] 54%|█████▎ | 6297/11728 [2:50:33<8:39:34, 5.74s/it] {'loss': 0.4887, 'learning_rate': 9.290865281182965e-06, 'epoch': 0.54} + 54%|█████▎ | 6297/11728 [2:50:33<8:39:34, 5.74s/it] 54%|█████▎ | 6298/11728 [2:50:39<8:47:02, 5.82s/it] {'loss': 0.4659, 'learning_rate': 9.288110663742001e-06, 'epoch': 0.54} + 54%|█████▎ | 6298/11728 [2:50:39<8:47:02, 5.82s/it] 54%|█████▎ | 6299/11728 [2:50:45<8:50:31, 5.86s/it] {'loss': 0.4666, 'learning_rate': 9.285356100592685e-06, 'epoch': 0.54} + 54%|█████▎ | 6299/11728 [2:50:45<8:50:31, 5.86s/it]2 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... +01 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... + 54%|█████▎ | 6300/11728 [2:50:51<8:52:06, 5.88s/it]4 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4914, 'learning_rate': 9.282601591945097e-06, 'epoch': 0.54} + 54%|█████▎ | 6300/11728 [2:50:51<8:52:06, 5.88s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-6300/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-6300/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-6300/mm_projector +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/torch/nn/modules/module.py:1802: UserWarning: Positional args are being deprecated, use kwargs instead. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details. + warnings.warn( + 54%|█████▎ | 6301/11728 [2:51:22<20:34:58, 13.65s/it] {'loss': 0.4639, 'learning_rate': 9.279847138009308e-06, 'epoch': 0.54} + 54%|█████▎ | 6301/11728 [2:51:22<20:34:58, 13.65s/it] 54%|█████▎ | 6302/11728 [2:51:28<16:56:04, 11.24s/it] {'loss': 0.4626, 'learning_rate': 9.277092738995385e-06, 'epoch': 0.54} + 54%|█████▎ | 6302/11728 [2:51:28<16:56:04, 11.24s/it] 54%|█████▎ | 6303/11728 [2:51:34<14:25:28, 9.57s/it] {'loss': 0.4678, 'learning_rate': 9.274338395113383e-06, 'epoch': 0.54} + 54%|█████▎ | 6303/11728 [2:51:34<14:25:28, 9.57s/it] 54%|█████▍ | 6304/11728 [2:51:39<12:38:43, 8.39s/it] {'loss': 0.4659, 'learning_rate': 9.271584106573364e-06, 'epoch': 0.54} + 54%|█████▍ | 6304/11728 [2:51:39<12:38:43, 8.39s/it] 54%|█████▍ | 6305/11728 [2:51:45<11:31:44, 7.65s/it] {'loss': 0.4773, 'learning_rate': 9.268829873585388e-06, 'epoch': 0.54} + 54%|█████▍ | 6305/11728 [2:51:45<11:31:44, 7.65s/it] 54%|█████▍ | 6306/11728 [2:51:51<10:43:52, 7.13s/it] {'loss': 0.4681, 'learning_rate': 9.266075696359495e-06, 'epoch': 0.54} + 54%|█████▍ | 6306/11728 [2:51:51<10:43:52, 7.13s/it] 54%|█████▍ | 6307/11728 [2:51:57<10:10:47, 6.76s/it] {'loss': 0.5068, 'learning_rate': 9.263321575105734e-06, 'epoch': 0.54} + 54%|█████▍ | 6307/11728 [2:51:57<10:10:47, 6.76s/it] 54%|█████▍ | 6308/11728 [2:52:03<9:44:02, 6.47s/it] {'loss': 0.4725, 'learning_rate': 9.260567510034146e-06, 'epoch': 0.54} + 54%|█████▍ | 6308/11728 [2:52:03<9:44:02, 6.47s/it] 54%|█████▍ | 6309/11728 [2:52:09<9:28:58, 6.30s/it] {'loss': 0.4658, 'learning_rate': 9.257813501354761e-06, 'epoch': 0.54} + 54%|█████▍ | 6309/11728 [2:52:09<9:28:58, 6.30s/it] 54%|█████▍ | 6310/11728 [2:52:15<9:18:26, 6.18s/it] {'loss': 0.4885, 'learning_rate': 9.255059549277624e-06, 'epoch': 0.54} + 54%|█████▍ | 6310/11728 [2:52:15<9:18:26, 6.18s/it] 54%|█████▍ | 6311/11728 [2:52:20<9:07:08, 6.06s/it] {'loss': 0.4594, 'learning_rate': 9.252305654012753e-06, 'epoch': 0.54} + 54%|█████▍ | 6311/11728 [2:52:20<9:07:08, 6.06s/it] 54%|█████▍ | 6312/11728 [2:52:26<8:56:39, 5.95s/it] {'loss': 0.4734, 'learning_rate': 9.249551815770177e-06, 'epoch': 0.54} + 54%|█████▍ | 6312/11728 [2:52:26<8:56:39, 5.95s/it] 54%|█████▍ | 6313/11728 [2:52:32<8:57:30, 5.96s/it] {'loss': 0.4914, 'learning_rate': 9.246798034759907e-06, 'epoch': 0.54} + 54%|█████▍ | 6313/11728 [2:52:32<8:57:30, 5.96s/it] 54%|█████▍ | 6314/11728 [2:52:38<8:50:43, 5.88s/it] {'loss': 0.4739, 'learning_rate': 9.244044311191968e-06, 'epoch': 0.54} + 54%|█████▍ | 6314/11728 [2:52:38<8:50:43, 5.88s/it] 54%|█████▍ | 6315/11728 [2:52:44<8:54:12, 5.92s/it] {'loss': 0.4776, 'learning_rate': 9.241290645276364e-06, 'epoch': 0.54} + 54%|█████▍ | 6315/11728 [2:52:44<8:54:12, 5.92s/it] 54%|█████▍ | 6316/11728 [2:52:50<8:56:27, 5.95s/it] {'loss': 0.4892, 'learning_rate': 9.238537037223106e-06, 'epoch': 0.54} + 54%|█████▍ | 6316/11728 [2:52:50<8:56:27, 5.95s/it] 54%|█████▍ | 6317/11728 [2:52:55<8:45:25, 5.83s/it] {'loss': 0.4576, 'learning_rate': 9.235783487242188e-06, 'epoch': 0.54} + 54%|█████▍ | 6317/11728 [2:52:55<8:45:25, 5.83s/it] 54%|█████▍ | 6318/11728 [2:53:01<8:43:23, 5.80s/it] {'loss': 0.4942, 'learning_rate': 9.233029995543612e-06, 'epoch': 0.54} + 54%|█████▍ | 6318/11728 [2:53:01<8:43:23, 5.80s/it] 54%|█████▍ | 6319/11728 [2:53:07<8:48:13, 5.86s/it] {'loss': 0.4477, 'learning_rate': 9.230276562337374e-06, 'epoch': 0.54} + 54%|█████▍ | 6319/11728 [2:53:07<8:48:13, 5.86s/it] 54%|█████▍ | 6320/11728 [2:53:13<8:44:39, 5.82s/it] {'loss': 0.4603, 'learning_rate': 9.227523187833456e-06, 'epoch': 0.54} + 54%|█████▍ | 6320/11728 [2:53:13<8:44:39, 5.82s/it] 54%|█████▍ | 6321/11728 [2:53:19<8:55:16, 5.94s/it] {'loss': 0.4894, 'learning_rate': 9.224769872241848e-06, 'epoch': 0.54} + 54%|█████▍ | 6321/11728 [2:53:19<8:55:16, 5.94s/it] 54%|█████▍ | 6322/11728 [2:53:25<8:51:04, 5.89s/it] {'loss': 0.4503, 'learning_rate': 9.222016615772525e-06, 'epoch': 0.54} + 54%|█████▍ | 6322/11728 [2:53:25<8:51:04, 5.89s/it] 54%|█████▍ | 6323/11728 [2:53:31<8:46:02, 5.84s/it] {'loss': 0.4716, 'learning_rate': 9.21926341863546e-06, 'epoch': 0.54} + 54%|█████▍ | 6323/11728 [2:53:31<8:46:02, 5.84s/it] 54%|█████▍ | 6324/11728 [2:53:36<8:45:21, 5.83s/it] {'loss': 0.4863, 'learning_rate': 9.216510281040627e-06, 'epoch': 0.54} + 54%|█████▍ | 6324/11728 [2:53:36<8:45:21, 5.83s/it] 54%|█████▍ | 6325/11728 [2:53:42<8:46:09, 5.84s/it] {'loss': 0.4874, 'learning_rate': 9.213757203197994e-06, 'epoch': 0.54} + 54%|█████▍ | 6325/11728 [2:53:42<8:46:09, 5.84s/it] 54%|█████▍ | 6326/11728 [2:53:48<8:40:51, 5.79s/it] {'loss': 0.4689, 'learning_rate': 9.211004185317515e-06, 'epoch': 0.54} + 54%|█████▍ | 6326/11728 [2:53:48<8:40:51, 5.79s/it] 54%|█████▍ | 6327/11728 [2:53:54<8:38:24, 5.76s/it] {'loss': 0.4886, 'learning_rate': 9.208251227609151e-06, 'epoch': 0.54} + 54%|█████▍ | 6327/11728 [2:53:54<8:38:24, 5.76s/it] 54%|█████▍ | 6328/11728 [2:53:59<8:42:00, 5.80s/it] {'loss': 0.4841, 'learning_rate': 9.205498330282857e-06, 'epoch': 0.54} + 54%|█████▍ | 6328/11728 [2:53:59<8:42:00, 5.80s/it] 54%|█████▍ | 6329/11728 [2:54:05<8:43:14, 5.81s/it] {'loss': 0.4793, 'learning_rate': 9.202745493548576e-06, 'epoch': 0.54} + 54%|█████▍ | 6329/11728 [2:54:05<8:43:14, 5.81s/it] 54%|█████▍ | 6330/11728 [2:54:11<8:44:00, 5.82s/it] {'loss': 0.4929, 'learning_rate': 9.199992717616253e-06, 'epoch': 0.54} + 54%|█████▍ | 6330/11728 [2:54:11<8:44:00, 5.82s/it] 54%|█████▍ | 6331/11728 [2:54:17<8:36:18, 5.74s/it] {'loss': 0.4762, 'learning_rate': 9.197240002695826e-06, 'epoch': 0.54} + 54%|█████▍ | 6331/11728 [2:54:17<8:36:18, 5.74s/it] 54%|█████▍ | 6332/11728 [2:54:23<8:48:29, 5.88s/it] {'loss': 0.4547, 'learning_rate': 9.194487348997223e-06, 'epoch': 0.54} + 54%|█████▍ | 6332/11728 [2:54:23<8:48:29, 5.88s/it] 54%|█████▍ | 6333/11728 [2:54:29<8:54:29, 5.94s/it] {'loss': 0.4797, 'learning_rate': 9.19173475673038e-06, 'epoch': 0.54} + 54%|█████▍ | 6333/11728 [2:54:29<8:54:29, 5.94s/it] 54%|█████▍ | 6334/11728 [2:54:35<8:48:22, 5.88s/it] {'loss': 0.4793, 'learning_rate': 9.188982226105222e-06, 'epoch': 0.54} + 54%|█████▍ | 6334/11728 [2:54:35<8:48:22, 5.88s/it] 54%|█████▍ | 6335/11728 [2:54:41<8:45:48, 5.85s/it] {'loss': 0.4631, 'learning_rate': 9.186229757331663e-06, 'epoch': 0.54} + 54%|█████▍ | 6335/11728 [2:54:41<8:45:48, 5.85s/it] 54%|█████▍ | 6336/11728 [2:54:46<8:46:43, 5.86s/it] {'loss': 0.4591, 'learning_rate': 9.183477350619617e-06, 'epoch': 0.54} + 54%|█████▍ | 6336/11728 [2:54:46<8:46:43, 5.86s/it] 54%|█████▍ | 6337/11728 [2:54:52<8:38:36, 5.77s/it] {'loss': 0.4615, 'learning_rate': 9.180725006179002e-06, 'epoch': 0.54} + 54%|█████▍ | 6337/11728 [2:54:52<8:38:36, 5.77s/it] 54%|█████▍ | 6338/11728 [2:54:58<8:34:03, 5.72s/it] {'loss': 0.4645, 'learning_rate': 9.177972724219715e-06, 'epoch': 0.54} + 54%|█████▍ | 6338/11728 [2:54:58<8:34:03, 5.72s/it] 54%|█████▍ | 6339/11728 [2:55:03<8:32:42, 5.71s/it] {'loss': 0.4772, 'learning_rate': 9.175220504951664e-06, 'epoch': 0.54} + 54%|█████▍ | 6339/11728 [2:55:03<8:32:42, 5.71s/it] 54%|█████▍ | 6340/11728 [2:55:09<8:32:51, 5.71s/it] {'loss': 0.4822, 'learning_rate': 9.17246834858474e-06, 'epoch': 0.54} + 54%|█████▍ | 6340/11728 [2:55:09<8:32:51, 5.71s/it] 54%|█████▍ | 6341/11728 [2:55:15<8:44:47, 5.85s/it] {'loss': 0.4534, 'learning_rate': 9.16971625532883e-06, 'epoch': 0.54} + 54%|█████▍ | 6341/11728 [2:55:15<8:44:47, 5.85s/it] 54%|█████▍ | 6342/11728 [2:55:21<8:44:03, 5.84s/it] {'loss': 0.4966, 'learning_rate': 9.166964225393826e-06, 'epoch': 0.54} + 54%|█████▍ | 6342/11728 [2:55:21<8:44:03, 5.84s/it] 54%|█████▍ | 6343/11728 [2:55:27<8:45:32, 5.86s/it] {'loss': 0.4871, 'learning_rate': 9.164212258989611e-06, 'epoch': 0.54} + 54%|█████▍ | 6343/11728 [2:55:27<8:45:32, 5.86s/it] 54%|█████▍ | 6344/11728 [2:55:32<8:39:54, 5.79s/it] {'loss': 0.4715, 'learning_rate': 9.161460356326057e-06, 'epoch': 0.54} + 54%|█████▍ | 6344/11728 [2:55:32<8:39:54, 5.79s/it] 54%|█████▍ | 6345/11728 [2:55:38<8:36:47, 5.76s/it] {'loss': 0.4875, 'learning_rate': 9.158708517613038e-06, 'epoch': 0.54} + 54%|█████▍ | 6345/11728 [2:55:38<8:36:47, 5.76s/it] 54%|█████▍ | 6346/11728 [2:55:44<8:27:17, 5.66s/it] {'loss': 0.4508, 'learning_rate': 9.155956743060417e-06, 'epoch': 0.54} + 54%|█████▍ | 6346/11728 [2:55:44<8:27:17, 5.66s/it] 54%|█████▍ | 6347/11728 [2:55:49<8:32:04, 5.71s/it] {'loss': 0.4629, 'learning_rate': 9.15320503287806e-06, 'epoch': 0.54} + 54%|█████▍ | 6347/11728 [2:55:49<8:32:04, 5.71s/it] 54%|█████▍ | 6348/11728 [2:55:56<8:44:51, 5.85s/it] {'loss': 0.4889, 'learning_rate': 9.150453387275823e-06, 'epoch': 0.54} + 54%|█████▍ | 6348/11728 [2:55:56<8:44:51, 5.85s/it] 54%|█████▍ | 6349/11728 [2:56:01<8:41:26, 5.82s/it] {'loss': 0.4862, 'learning_rate': 9.147701806463559e-06, 'epoch': 0.54} + 54%|█████▍ | 6349/11728 [2:56:01<8:41:26, 5.82s/it]27 AutoResumeHook: Checking whether to suspend... +AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +03 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend...1 + AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... + 54%|█████▍ | 6350/11728 [2:56:07<8:48:24, 5.90s/it] {'loss': 0.502, 'learning_rate': 9.144950290651109e-06, 'epoch': 0.54} + 54%|█████▍ | 6350/11728 [2:56:07<8:48:24, 5.90s/it] 54%|█████▍ | 6351/11728 [2:56:13<8:42:01, 5.83s/it] {'loss': 0.4505, 'learning_rate': 9.14219884004832e-06, 'epoch': 0.54} + 54%|█████▍ | 6351/11728 [2:56:13<8:42:01, 5.83s/it] 54%|█████▍ | 6352/11728 [2:56:19<8:40:51, 5.81s/it] {'loss': 0.4658, 'learning_rate': 9.139447454865034e-06, 'epoch': 0.54} + 54%|█████▍ | 6352/11728 [2:56:19<8:40:51, 5.81s/it] 54%|█████▍ | 6353/11728 [2:56:24<8:34:46, 5.75s/it] {'loss': 0.4701, 'learning_rate': 9.136696135311075e-06, 'epoch': 0.54} + 54%|█████▍ | 6353/11728 [2:56:24<8:34:46, 5.75s/it] 54%|█████▍ | 6354/11728 [2:56:30<8:40:22, 5.81s/it] {'loss': 0.4701, 'learning_rate': 9.133944881596273e-06, 'epoch': 0.54} + 54%|█████▍ | 6354/11728 [2:56:30<8:40:22, 5.81s/it] 54%|█████▍ | 6355/11728 [2:56:36<8:45:18, 5.87s/it] {'loss': 0.4937, 'learning_rate': 9.131193693930447e-06, 'epoch': 0.54} + 54%|█████▍ | 6355/11728 [2:56:36<8:45:18, 5.87s/it] 54%|█████▍ | 6356/11728 [2:56:42<8:42:57, 5.84s/it] {'loss': 0.4526, 'learning_rate': 9.128442572523418e-06, 'epoch': 0.54} + 54%|█████▍ | 6356/11728 [2:56:42<8:42:57, 5.84s/it] 54%|█████▍ | 6357/11728 [2:56:48<8:39:54, 5.81s/it] {'loss': 0.4731, 'learning_rate': 9.125691517585e-06, 'epoch': 0.54} + 54%|█████▍ | 6357/11728 [2:56:48<8:39:54, 5.81s/it] 54%|█████▍ | 6358/11728 [2:56:54<8:34:41, 5.75s/it] {'loss': 0.4538, 'learning_rate': 9.122940529324997e-06, 'epoch': 0.54} + 54%|█████▍ | 6358/11728 [2:56:54<8:34:41, 5.75s/it] 54%|█████▍ | 6359/11728 [2:56:59<8:28:44, 5.69s/it] {'loss': 0.4788, 'learning_rate': 9.120189607953206e-06, 'epoch': 0.54} + 54%|█████▍ | 6359/11728 [2:56:59<8:28:44, 5.69s/it] 54%|█████▍ | 6360/11728 [2:57:05<8:31:01, 5.71s/it] {'loss': 0.4669, 'learning_rate': 9.117438753679433e-06, 'epoch': 0.54} + 54%|█████▍ | 6360/11728 [2:57:05<8:31:01, 5.71s/it] 54%|█████▍ | 6361/11728 [2:57:11<8:35:40, 5.76s/it] {'loss': 0.4699, 'learning_rate': 9.114687966713465e-06, 'epoch': 0.54} + 54%|█████▍ | 6361/11728 [2:57:11<8:35:40, 5.76s/it] 54%|█████▍ | 6362/11728 [2:57:16<8:31:06, 5.71s/it] {'loss': 0.4706, 'learning_rate': 9.111937247265088e-06, 'epoch': 0.54} + 54%|█████▍ | 6362/11728 [2:57:16<8:31:06, 5.71s/it] 54%|█████▍ | 6363/11728 [2:57:22<8:29:13, 5.69s/it] {'loss': 0.4566, 'learning_rate': 9.109186595544085e-06, 'epoch': 0.54} + 54%|█████▍ | 6363/11728 [2:57:22<8:29:13, 5.69s/it] 54%|█████▍ | 6364/11728 [2:57:28<8:25:52, 5.66s/it] {'loss': 0.4623, 'learning_rate': 9.106436011760229e-06, 'epoch': 0.54} + 54%|█████▍ | 6364/11728 [2:57:28<8:25:52, 5.66s/it] 54%|█████▍ | 6365/11728 [2:57:34<8:43:28, 5.86s/it] {'loss': 0.4611, 'learning_rate': 9.103685496123294e-06, 'epoch': 0.54} + 54%|█████▍ | 6365/11728 [2:57:34<8:43:28, 5.86s/it] 54%|█████▍ | 6366/11728 [2:57:39<8:35:14, 5.77s/it] {'loss': 0.4778, 'learning_rate': 9.100935048843047e-06, 'epoch': 0.54} + 54%|█████▍ | 6366/11728 [2:57:39<8:35:14, 5.77s/it] 54%|█████▍ | 6367/11728 [2:57:45<8:40:01, 5.82s/it] {'loss': 0.4588, 'learning_rate': 9.098184670129244e-06, 'epoch': 0.54} + 54%|█████▍ | 6367/11728 [2:57:45<8:40:01, 5.82s/it] 54%|█████▍ | 6368/11728 [2:57:51<8:36:50, 5.79s/it] {'loss': 0.467, 'learning_rate': 9.095434360191642e-06, 'epoch': 0.54} + 54%|█████▍ | 6368/11728 [2:57:51<8:36:50, 5.79s/it] 54%|█████▍ | 6369/11728 [2:57:57<8:38:20, 5.80s/it] {'loss': 0.4931, 'learning_rate': 9.092684119239996e-06, 'epoch': 0.54} + 54%|█████▍ | 6369/11728 [2:57:57<8:38:20, 5.80s/it] 54%|█████▍ | 6370/11728 [2:58:07<10:26:08, 7.01s/it] {'loss': 0.4698, 'learning_rate': 9.089933947484048e-06, 'epoch': 0.54} + 54%|█████▍ | 6370/11728 [2:58:07<10:26:08, 7.01s/it] 54%|█████▍ | 6371/11728 [2:58:12<9:47:41, 6.58s/it] {'loss': 0.4695, 'learning_rate': 9.087183845133532e-06, 'epoch': 0.54} + 54%|█████▍ | 6371/11728 [2:58:12<9:47:41, 6.58s/it] 54%|█████▍ | 6372/11728 [2:58:18<9:19:59, 6.27s/it] {'loss': 0.4704, 'learning_rate': 9.084433812398191e-06, 'epoch': 0.54} + 54%|█████▍ | 6372/11728 [2:58:18<9:19:59, 6.27s/it] 54%|█████▍ | 6373/11728 [2:58:24<9:03:34, 6.09s/it] {'loss': 0.4875, 'learning_rate': 9.081683849487745e-06, 'epoch': 0.54} + 54%|█████▍ | 6373/11728 [2:58:24<9:03:34, 6.09s/it] 54%|█████▍ | 6374/11728 [2:58:29<8:48:00, 5.92s/it] {'loss': 0.4816, 'learning_rate': 9.078933956611925e-06, 'epoch': 0.54} + 54%|█████▍ | 6374/11728 [2:58:29<8:48:00, 5.92s/it] 54%|█████▍ | 6375/11728 [2:58:35<8:44:37, 5.88s/it] {'loss': 0.4694, 'learning_rate': 9.076184133980449e-06, 'epoch': 0.54} + 54%|█████▍ | 6375/11728 [2:58:35<8:44:37, 5.88s/it] 54%|█████▍ | 6376/11728 [2:58:41<8:47:44, 5.92s/it] {'loss': 0.4893, 'learning_rate': 9.073434381803025e-06, 'epoch': 0.54} + 54%|█████▍ | 6376/11728 [2:58:41<8:47:44, 5.92s/it] 54%|█████▍ | 6377/11728 [2:58:47<8:41:22, 5.85s/it] {'loss': 0.4753, 'learning_rate': 9.070684700289365e-06, 'epoch': 0.54} + 54%|█████▍ | 6377/11728 [2:58:47<8:41:22, 5.85s/it] 54%|█████▍ | 6378/11728 [2:58:52<8:39:22, 5.82s/it] {'loss': 0.4821, 'learning_rate': 9.067935089649167e-06, 'epoch': 0.54} + 54%|█████▍ | 6378/11728 [2:58:52<8:39:22, 5.82s/it] 54%|█████▍ | 6379/11728 [2:58:58<8:32:33, 5.75s/it] {'loss': 0.4813, 'learning_rate': 9.065185550092134e-06, 'epoch': 0.54} + 54%|█████▍ | 6379/11728 [2:58:58<8:32:33, 5.75s/it] 54%|█████▍ | 6380/11728 [2:59:04<8:40:02, 5.83s/it] {'loss': 0.4646, 'learning_rate': 9.06243608182795e-06, 'epoch': 0.54} + 54%|█████▍ | 6380/11728 [2:59:04<8:40:02, 5.83s/it] 54%|█████▍ | 6381/11728 [2:59:10<8:34:33, 5.77s/it] {'loss': 0.4855, 'learning_rate': 9.059686685066308e-06, 'epoch': 0.54} + 54%|█████▍ | 6381/11728 [2:59:10<8:34:33, 5.77s/it] 54%|█████▍ | 6382/11728 [2:59:15<8:32:18, 5.75s/it] {'loss': 0.4576, 'learning_rate': 9.056937360016881e-06, 'epoch': 0.54} + 54%|█████▍ | 6382/11728 [2:59:15<8:32:18, 5.75s/it] 54%|█████▍ | 6383/11728 [2:59:21<8:33:54, 5.77s/it] {'loss': 0.4715, 'learning_rate': 9.05418810688935e-06, 'epoch': 0.54} + 54%|█████▍ | 6383/11728 [2:59:21<8:33:54, 5.77s/it] 54%|█████▍ | 6384/11728 [2:59:27<8:34:34, 5.78s/it] {'loss': 0.4708, 'learning_rate': 9.051438925893385e-06, 'epoch': 0.54} + 54%|█████▍ | 6384/11728 [2:59:27<8:34:34, 5.78s/it] 54%|█████▍ | 6385/11728 [2:59:33<8:34:54, 5.78s/it] {'loss': 0.4851, 'learning_rate': 9.048689817238645e-06, 'epoch': 0.54} + 54%|█████▍ | 6385/11728 [2:59:33<8:34:54, 5.78s/it] 54%|█████▍ | 6386/11728 [2:59:39<8:36:40, 5.80s/it] {'loss': 0.475, 'learning_rate': 9.045940781134794e-06, 'epoch': 0.54} + 54%|█████▍ | 6386/11728 [2:59:39<8:36:40, 5.80s/it] 54%|█████▍ | 6387/11728 [2:59:44<8:32:01, 5.75s/it] {'loss': 0.4602, 'learning_rate': 9.043191817791476e-06, 'epoch': 0.54} + 54%|█████▍ | 6387/11728 [2:59:44<8:32:01, 5.75s/it] 54%|█████▍ | 6388/11728 [2:59:50<8:35:57, 5.80s/it] {'loss': 0.4751, 'learning_rate': 9.04044292741835e-06, 'epoch': 0.54} + 54%|█████▍ | 6388/11728 [2:59:50<8:35:57, 5.80s/it] 54%|█████▍ | 6389/11728 [2:59:56<8:34:40, 5.78s/it] {'loss': 0.4812, 'learning_rate': 9.03769411022505e-06, 'epoch': 0.54} + 54%|█████▍ | 6389/11728 [2:59:56<8:34:40, 5.78s/it] 54%|█████▍ | 6390/11728 [3:00:02<8:36:01, 5.80s/it] {'loss': 0.4719, 'learning_rate': 9.034945366421219e-06, 'epoch': 0.54} + 54%|█████▍ | 6390/11728 [3:00:02<8:36:01, 5.80s/it] 54%|█████▍ | 6391/11728 [3:00:08<8:40:17, 5.85s/it] {'loss': 0.4703, 'learning_rate': 9.032196696216477e-06, 'epoch': 0.54} + 54%|█████▍ | 6391/11728 [3:00:08<8:40:17, 5.85s/it] 55%|█████▍ | 6392/11728 [3:00:14<8:44:19, 5.90s/it] {'loss': 0.4979, 'learning_rate': 9.029448099820458e-06, 'epoch': 0.55} + 55%|█████▍ | 6392/11728 [3:00:14<8:44:19, 5.90s/it] 55%|█████▍ | 6393/11728 [3:00:19<8:43:46, 5.89s/it] {'loss': 0.4843, 'learning_rate': 9.026699577442779e-06, 'epoch': 0.55} + 55%|█████▍ | 6393/11728 [3:00:19<8:43:46, 5.89s/it] 55%|█████▍ | 6394/11728 [3:00:25<8:37:39, 5.82s/it] {'loss': 0.482, 'learning_rate': 9.023951129293053e-06, 'epoch': 0.55} + 55%|█████▍ | 6394/11728 [3:00:25<8:37:39, 5.82s/it] 55%|█████▍ | 6395/11728 [3:00:31<8:30:12, 5.74s/it] {'loss': 0.492, 'learning_rate': 9.021202755580892e-06, 'epoch': 0.55} + 55%|█████▍ | 6395/11728 [3:00:31<8:30:12, 5.74s/it] 55%|█████▍ | 6396/11728 [3:00:37<8:36:49, 5.82s/it] {'loss': 0.4814, 'learning_rate': 9.018454456515889e-06, 'epoch': 0.55} + 55%|█████▍ | 6396/11728 [3:00:37<8:36:49, 5.82s/it] 55%|█████▍ | 6397/11728 [3:00:42<8:34:39, 5.79s/it] {'loss': 0.4877, 'learning_rate': 9.015706232307653e-06, 'epoch': 0.55} + 55%|█████▍ | 6397/11728 [3:00:42<8:34:39, 5.79s/it] 55%|█████▍ | 6398/11728 [3:00:48<8:30:14, 5.74s/it] {'loss': 0.4727, 'learning_rate': 9.012958083165766e-06, 'epoch': 0.55} + 55%|█████▍ | 6398/11728 [3:00:48<8:30:14, 5.74s/it] 55%|█████▍ | 6399/11728 [3:00:54<8:28:02, 5.72s/it] {'loss': 0.4699, 'learning_rate': 9.010210009299818e-06, 'epoch': 0.55} + 55%|█████▍ | 6399/11728 [3:00:54<8:28:02, 5.72s/it]2 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... +03 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... +54 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... + 55%|█████▍ | 6400/11728 [3:01:00<8:33:19, 5.78s/it] {'loss': 0.4559, 'learning_rate': 9.007462010919387e-06, 'epoch': 0.55} + 55%|█████▍ | 6400/11728 [3:01:00<8:33:19, 5.78s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-6400/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-6400/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-6400/mm_projector +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/torch/nn/modules/module.py:1802: UserWarning: Positional args are being deprecated, use kwargs instead. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details. + warnings.warn( + 55%|█████▍ | 6401/11728 [3:01:32<20:27:26, 13.83s/it] {'loss': 0.47, 'learning_rate': 9.004714088234042e-06, 'epoch': 0.55} + 55%|█████▍ | 6401/11728 [3:01:32<20:27:26, 13.83s/it] 55%|█████▍ | 6402/11728 [3:01:38<16:54:18, 11.43s/it] {'loss': 0.4718, 'learning_rate': 9.001966241453362e-06, 'epoch': 0.55} + 55%|█████▍ | 6402/11728 [3:01:38<16:54:18, 11.43s/it] 55%|█████▍ | 6403/11728 [3:01:44<14:26:36, 9.76s/it] {'loss': 0.4788, 'learning_rate': 8.9992184707869e-06, 'epoch': 0.55} + 55%|█████▍ | 6403/11728 [3:01:44<14:26:36, 9.76s/it] 55%|█████▍ | 6404/11728 [3:01:50<12:43:19, 8.60s/it] {'loss': 0.4702, 'learning_rate': 8.996470776444217e-06, 'epoch': 0.55} + 55%|█████▍ | 6404/11728 [3:01:50<12:43:19, 8.60s/it] 55%|█████▍ | 6405/11728 [3:01:56<11:28:51, 7.76s/it] {'loss': 0.4804, 'learning_rate': 8.993723158634859e-06, 'epoch': 0.55} + 55%|█████▍ | 6405/11728 [3:01:56<11:28:51, 7.76s/it] 55%|█████▍ | 6406/11728 [3:02:05<12:02:39, 8.15s/it] {'loss': 0.4839, 'learning_rate': 8.990975617568379e-06, 'epoch': 0.55} + 55%|█████▍ | 6406/11728 [3:02:05<12:02:39, 8.15s/it] 55%|█████▍ | 6407/11728 [3:02:11<11:06:23, 7.51s/it] {'loss': 0.4778, 'learning_rate': 8.988228153454308e-06, 'epoch': 0.55} + 55%|█████▍ | 6407/11728 [3:02:11<11:06:23, 7.51s/it] 55%|█████▍ | 6408/11728 [3:02:16<10:18:15, 6.97s/it] {'loss': 0.4814, 'learning_rate': 8.985480766502183e-06, 'epoch': 0.55} + 55%|█████▍ | 6408/11728 [3:02:16<10:18:15, 6.97s/it] 55%|█████▍ | 6409/11728 [3:02:22<9:49:57, 6.65s/it] {'loss': 0.4572, 'learning_rate': 8.98273345692153e-06, 'epoch': 0.55} + 55%|█████▍ | 6409/11728 [3:02:22<9:49:57, 6.65s/it] 55%|█████▍ | 6410/11728 [3:02:28<9:22:23, 6.35s/it] {'loss': 0.4853, 'learning_rate': 8.979986224921868e-06, 'epoch': 0.55} + 55%|█████▍ | 6410/11728 [3:02:28<9:22:23, 6.35s/it] 55%|█████▍ | 6411/11728 [3:02:34<9:06:52, 6.17s/it] {'loss': 0.4634, 'learning_rate': 8.977239070712717e-06, 'epoch': 0.55} + 55%|█████▍ | 6411/11728 [3:02:34<9:06:52, 6.17s/it] 55%|█████▍ | 6412/11728 [3:02:40<9:00:00, 6.09s/it] {'loss': 0.4664, 'learning_rate': 8.974491994503585e-06, 'epoch': 0.55} + 55%|█████▍ | 6412/11728 [3:02:40<9:00:00, 6.09s/it] 55%|█████▍ | 6413/11728 [3:02:48<10:02:51, 6.81s/it] {'loss': 0.4695, 'learning_rate': 8.971744996503975e-06, 'epoch': 0.55} + 55%|█████▍ | 6413/11728 [3:02:48<10:02:51, 6.81s/it] 55%|█████▍ | 6414/11728 [3:02:54<9:31:59, 6.46s/it] {'loss': 0.4595, 'learning_rate': 8.968998076923381e-06, 'epoch': 0.55} + 55%|█████▍ | 6414/11728 [3:02:54<9:31:59, 6.46s/it] 55%|█████▍ | 6415/11728 [3:02:59<9:09:41, 6.21s/it] {'loss': 0.4492, 'learning_rate': 8.966251235971302e-06, 'epoch': 0.55} + 55%|█████▍ | 6415/11728 [3:02:59<9:09:41, 6.21s/it] 55%|█████▍ | 6416/11728 [3:03:05<8:57:21, 6.07s/it] {'loss': 0.4637, 'learning_rate': 8.963504473857218e-06, 'epoch': 0.55} + 55%|█████▍ | 6416/11728 [3:03:05<8:57:21, 6.07s/it] 55%|█████▍ | 6417/11728 [3:03:14<9:58:54, 6.77s/it] {'loss': 0.4776, 'learning_rate': 8.960757790790613e-06, 'epoch': 0.55} + 55%|█████▍ | 6417/11728 [3:03:14<9:58:54, 6.77s/it] 55%|█████▍ | 6418/11728 [3:03:22<10:54:09, 7.39s/it] {'loss': 0.471, 'learning_rate': 8.958011186980954e-06, 'epoch': 0.55} + 55%|█████▍ | 6418/11728 [3:03:22<10:54:09, 7.39s/it] 55%|█████▍ | 6419/11728 [3:03:28<10:15:14, 6.95s/it] {'loss': 0.4739, 'learning_rate': 8.95526466263771e-06, 'epoch': 0.55} + 55%|█████▍ | 6419/11728 [3:03:28<10:15:14, 6.95s/it] 55%|█████▍ | 6420/11728 [3:03:34<9:46:14, 6.63s/it] {'loss': 0.5049, 'learning_rate': 8.95251821797035e-06, 'epoch': 0.55} + 55%|█████▍ | 6420/11728 [3:03:34<9:46:14, 6.63s/it] 55%|█████▍ | 6421/11728 [3:03:40<9:19:25, 6.32s/it] {'loss': 0.4594, 'learning_rate': 8.94977185318832e-06, 'epoch': 0.55} + 55%|█████▍ | 6421/11728 [3:03:40<9:19:25, 6.32s/it] 55%|█████▍ | 6422/11728 [3:03:45<9:01:21, 6.12s/it] {'loss': 0.464, 'learning_rate': 8.947025568501075e-06, 'epoch': 0.55} + 55%|█████▍ | 6422/11728 [3:03:45<9:01:21, 6.12s/it] 55%|█████▍ | 6423/11728 [3:03:54<10:01:02, 6.80s/it] {'loss': 0.4919, 'learning_rate': 8.944279364118059e-06, 'epoch': 0.55} + 55%|█████▍ | 6423/11728 [3:03:54<10:01:02, 6.80s/it] 55%|█████▍ | 6424/11728 [3:03:59<9:27:16, 6.42s/it] {'loss': 0.4861, 'learning_rate': 8.9415332402487e-06, 'epoch': 0.55} + 55%|█████▍ | 6424/11728 [3:03:59<9:27:16, 6.42s/it] 55%|█████▍ | 6425/11728 [3:04:05<9:09:36, 6.22s/it] {'loss': 0.4652, 'learning_rate': 8.938787197102437e-06, 'epoch': 0.55} + 55%|█████▍ | 6425/11728 [3:04:05<9:09:36, 6.22s/it] 55%|█████▍ | 6426/11728 [3:04:11<8:52:37, 6.03s/it] {'loss': 0.4617, 'learning_rate': 8.936041234888693e-06, 'epoch': 0.55} + 55%|█████▍ | 6426/11728 [3:04:11<8:52:37, 6.03s/it] 55%|█████▍ | 6427/11728 [3:04:19<9:54:16, 6.73s/it] {'loss': 0.4679, 'learning_rate': 8.933295353816888e-06, 'epoch': 0.55} + 55%|█████▍ | 6427/11728 [3:04:19<9:54:16, 6.73s/it] 55%|█████▍ | 6428/11728 [3:04:27<10:36:38, 7.21s/it] {'loss': 0.4842, 'learning_rate': 8.930549554096429e-06, 'epoch': 0.55} + 55%|█████▍ | 6428/11728 [3:04:27<10:36:38, 7.21s/it] 55%|█████▍ | 6429/11728 [3:04:33<9:53:10, 6.72s/it] {'loss': 0.4601, 'learning_rate': 8.927803835936729e-06, 'epoch': 0.55} + 55%|█████▍ | 6429/11728 [3:04:33<9:53:10, 6.72s/it] 55%|█████▍ | 6430/11728 [3:04:39<9:22:54, 6.38s/it] {'loss': 0.4781, 'learning_rate': 8.925058199547183e-06, 'epoch': 0.55} + 55%|█████▍ | 6430/11728 [3:04:39<9:22:54, 6.38s/it] 55%|█████▍ | 6431/11728 [3:04:44<9:11:25, 6.25s/it] {'loss': 0.5146, 'learning_rate': 8.92231264513719e-06, 'epoch': 0.55} + 55%|█████▍ | 6431/11728 [3:04:44<9:11:25, 6.25s/it] 55%|█████▍ | 6432/11728 [3:04:50<9:02:39, 6.15s/it] {'loss': 0.4532, 'learning_rate': 8.91956717291613e-06, 'epoch': 0.55} + 55%|█████▍ | 6432/11728 [3:04:50<9:02:39, 6.15s/it] 55%|█████▍ | 6433/11728 [3:04:57<9:02:10, 6.14s/it] {'loss': 0.4784, 'learning_rate': 8.916821783093386e-06, 'epoch': 0.55} + 55%|█████▍ | 6433/11728 [3:04:57<9:02:10, 6.14s/it] 55%|█████▍ | 6434/11728 [3:05:02<8:53:23, 6.05s/it] {'loss': 0.4695, 'learning_rate': 8.914076475878342e-06, 'epoch': 0.55} + 55%|█████▍ | 6434/11728 [3:05:02<8:53:23, 6.05s/it] 55%|█████▍ | 6435/11728 [3:05:08<8:48:24, 5.99s/it] {'loss': 0.466, 'learning_rate': 8.911331251480357e-06, 'epoch': 0.55} + 55%|█████▍ | 6435/11728 [3:05:08<8:48:24, 5.99s/it] 55%|█████▍ | 6436/11728 [3:05:14<8:50:12, 6.01s/it] {'loss': 0.488, 'learning_rate': 8.908586110108794e-06, 'epoch': 0.55} + 55%|█████▍ | 6436/11728 [3:05:14<8:50:12, 6.01s/it] 55%|█████▍ | 6437/11728 [3:05:20<8:48:48, 6.00s/it] {'loss': 0.4777, 'learning_rate': 8.905841051973009e-06, 'epoch': 0.55} + 55%|█████▍ | 6437/11728 [3:05:20<8:48:48, 6.00s/it] 55%|█████▍ | 6438/11728 [3:05:26<8:40:02, 5.90s/it] {'loss': 0.4698, 'learning_rate': 8.903096077282356e-06, 'epoch': 0.55} + 55%|█████▍ | 6438/11728 [3:05:26<8:40:02, 5.90s/it] 55%|█████▍ | 6439/11728 [3:05:32<8:46:17, 5.97s/it] {'loss': 0.4595, 'learning_rate': 8.900351186246177e-06, 'epoch': 0.55} + 55%|█████▍ | 6439/11728 [3:05:32<8:46:17, 5.97s/it] 55%|█████▍ | 6440/11728 [3:05:38<8:37:20, 5.87s/it] {'loss': 0.4815, 'learning_rate': 8.897606379073806e-06, 'epoch': 0.55} + 55%|█████▍ | 6440/11728 [3:05:38<8:37:20, 5.87s/it] 55%|█████▍ | 6441/11728 [3:05:44<8:37:31, 5.87s/it] {'loss': 0.4935, 'learning_rate': 8.894861655974575e-06, 'epoch': 0.55} + 55%|█████▍ | 6441/11728 [3:05:44<8:37:31, 5.87s/it] 55%|█████▍ | 6442/11728 [3:05:49<8:35:33, 5.85s/it] {'loss': 0.467, 'learning_rate': 8.892117017157805e-06, 'epoch': 0.55} + 55%|█████▍ | 6442/11728 [3:05:49<8:35:33, 5.85s/it] 55%|█████▍ | 6443/11728 [3:05:55<8:29:38, 5.79s/it] {'loss': 0.4759, 'learning_rate': 8.88937246283282e-06, 'epoch': 0.55} + 55%|█████▍ | 6443/11728 [3:05:55<8:29:38, 5.79s/it] 55%|█████▍ | 6444/11728 [3:06:01<8:26:32, 5.75s/it] {'loss': 0.4697, 'learning_rate': 8.886627993208929e-06, 'epoch': 0.55} + 55%|█████▍ | 6444/11728 [3:06:01<8:26:32, 5.75s/it] 55%|█████▍ | 6445/11728 [3:06:06<8:20:51, 5.69s/it] {'loss': 0.4691, 'learning_rate': 8.883883608495433e-06, 'epoch': 0.55} + 55%|█████▍ | 6445/11728 [3:06:06<8:20:51, 5.69s/it] 55%|█████▍ | 6446/11728 [3:06:12<8:22:25, 5.71s/it] {'loss': 0.4682, 'learning_rate': 8.88113930890163e-06, 'epoch': 0.55} + 55%|█████▍ | 6446/11728 [3:06:12<8:22:25, 5.71s/it] 55%|█████▍ | 6447/11728 [3:06:18<8:20:07, 5.68s/it] {'loss': 0.4867, 'learning_rate': 8.87839509463682e-06, 'epoch': 0.55} + 55%|█████▍ | 6447/11728 [3:06:18<8:20:07, 5.68s/it] 55%|█████▍ | 6448/11728 [3:06:23<8:17:37, 5.65s/it] {'loss': 0.457, 'learning_rate': 8.87565096591028e-06, 'epoch': 0.55} + 55%|█████▍ | 6448/11728 [3:06:23<8:17:37, 5.65s/it] 55%|█████▍ | 6449/11728 [3:06:29<8:23:52, 5.73s/it] {'loss': 0.492, 'learning_rate': 8.872906922931293e-06, 'epoch': 0.55} + 55%|█████▍ | 6449/11728 [3:06:29<8:23:52, 5.73s/it]3 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend...7 + AutoResumeHook: Checking whether to suspend... +06 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... + 55%|█████▍ | 6450/11728 [3:06:35<8:28:28, 5.78s/it] {'loss': 0.4872, 'learning_rate': 8.870162965909127e-06, 'epoch': 0.55} + 55%|█████▍ | 6450/11728 [3:06:35<8:28:28, 5.78s/it] 55%|█████▌ | 6451/11728 [3:06:41<8:28:29, 5.78s/it] {'loss': 0.4781, 'learning_rate': 8.867419095053047e-06, 'epoch': 0.55} + 55%|█████▌ | 6451/11728 [3:06:41<8:28:29, 5.78s/it] 55%|█████▌ | 6452/11728 [3:06:47<8:30:35, 5.81s/it] {'loss': 0.4737, 'learning_rate': 8.864675310572323e-06, 'epoch': 0.55} + 55%|█████▌ | 6452/11728 [3:06:47<8:30:35, 5.81s/it] 55%|█████▌ | 6453/11728 [3:06:52<8:20:37, 5.69s/it] {'loss': 0.4543, 'learning_rate': 8.861931612676197e-06, 'epoch': 0.55} + 55%|█████▌ | 6453/11728 [3:06:52<8:20:37, 5.69s/it] 55%|█████▌ | 6454/11728 [3:06:58<8:17:01, 5.65s/it] {'loss': 0.4781, 'learning_rate': 8.859188001573916e-06, 'epoch': 0.55} + 55%|█████▌ | 6454/11728 [3:06:58<8:17:01, 5.65s/it] 55%|█████▌ | 6455/11728 [3:07:04<8:28:04, 5.78s/it] {'loss': 0.474, 'learning_rate': 8.856444477474723e-06, 'epoch': 0.55} + 55%|█████▌ | 6455/11728 [3:07:04<8:28:04, 5.78s/it] 55%|█████▌ | 6456/11728 [3:07:09<8:22:26, 5.72s/it] {'loss': 0.4575, 'learning_rate': 8.853701040587843e-06, 'epoch': 0.55} + 55%|█████▌ | 6456/11728 [3:07:09<8:22:26, 5.72s/it] 55%|█████▌ | 6457/11728 [3:07:15<8:22:19, 5.72s/it] {'loss': 0.4876, 'learning_rate': 8.850957691122511e-06, 'epoch': 0.55} + 55%|█████▌ | 6457/11728 [3:07:15<8:22:19, 5.72s/it] 55%|█████▌ | 6458/11728 [3:07:21<8:24:51, 5.75s/it] {'loss': 0.482, 'learning_rate': 8.848214429287945e-06, 'epoch': 0.55} + 55%|█████▌ | 6458/11728 [3:07:21<8:24:51, 5.75s/it] 55%|█████▌ | 6459/11728 [3:07:27<8:27:51, 5.78s/it] {'loss': 0.4941, 'learning_rate': 8.845471255293351e-06, 'epoch': 0.55} + 55%|█████▌ | 6459/11728 [3:07:27<8:27:51, 5.78s/it] 55%|█████▌ | 6460/11728 [3:07:33<8:30:36, 5.82s/it] {'loss': 0.4964, 'learning_rate': 8.842728169347938e-06, 'epoch': 0.55} + 55%|█████▌ | 6460/11728 [3:07:33<8:30:36, 5.82s/it] 55%|█████▌ | 6461/11728 [3:07:38<8:26:09, 5.77s/it] {'loss': 0.4641, 'learning_rate': 8.83998517166091e-06, 'epoch': 0.55} + 55%|█████▌ | 6461/11728 [3:07:38<8:26:09, 5.77s/it] 55%|█████▌ | 6462/11728 [3:07:44<8:20:01, 5.70s/it] {'loss': 0.4856, 'learning_rate': 8.837242262441457e-06, 'epoch': 0.55} + 55%|█████▌ | 6462/11728 [3:07:44<8:20:01, 5.70s/it] 55%|█████▌ | 6463/11728 [3:07:49<8:15:34, 5.65s/it] {'loss': 0.4629, 'learning_rate': 8.834499441898761e-06, 'epoch': 0.55} + 55%|█████▌ | 6463/11728 [3:07:49<8:15:34, 5.65s/it] 55%|█████▌ | 6464/11728 [3:07:55<8:23:55, 5.74s/it] {'loss': 0.4586, 'learning_rate': 8.831756710242006e-06, 'epoch': 0.55} + 55%|█████▌ | 6464/11728 [3:07:55<8:23:55, 5.74s/it] 55%|█████▌ | 6465/11728 [3:08:01<8:19:24, 5.69s/it] {'loss': 0.4664, 'learning_rate': 8.829014067680355e-06, 'epoch': 0.55} + 55%|█████▌ | 6465/11728 [3:08:01<8:19:24, 5.69s/it] 55%|█████▌ | 6466/11728 [3:08:07<8:26:13, 5.77s/it] {'loss': 0.4758, 'learning_rate': 8.826271514422983e-06, 'epoch': 0.55} + 55%|█████▌ | 6466/11728 [3:08:07<8:26:13, 5.77s/it] 55%|█████▌ | 6467/11728 [3:08:12<8:20:27, 5.71s/it] {'loss': 0.4693, 'learning_rate': 8.823529050679049e-06, 'epoch': 0.55} + 55%|█████▌ | 6467/11728 [3:08:12<8:20:27, 5.71s/it] 55%|█████▌ | 6468/11728 [3:08:18<8:31:46, 5.84s/it] {'loss': 0.4845, 'learning_rate': 8.820786676657698e-06, 'epoch': 0.55} + 55%|█████▌ | 6468/11728 [3:08:18<8:31:46, 5.84s/it] 55%|█████▌ | 6469/11728 [3:08:24<8:32:07, 5.84s/it] {'loss': 0.4707, 'learning_rate': 8.818044392568076e-06, 'epoch': 0.55} + 55%|█████▌ | 6469/11728 [3:08:24<8:32:07, 5.84s/it] 55%|█████▌ | 6470/11728 [3:08:30<8:23:46, 5.75s/it] {'loss': 0.4919, 'learning_rate': 8.815302198619328e-06, 'epoch': 0.55} + 55%|█████▌ | 6470/11728 [3:08:30<8:23:46, 5.75s/it] 55%|█████▌ | 6471/11728 [3:08:35<8:19:42, 5.70s/it] {'loss': 0.475, 'learning_rate': 8.81256009502058e-06, 'epoch': 0.55} + 55%|█████▌ | 6471/11728 [3:08:35<8:19:42, 5.70s/it] 55%|█████▌ | 6472/11728 [3:08:41<8:19:19, 5.70s/it] {'loss': 0.4698, 'learning_rate': 8.809818081980954e-06, 'epoch': 0.55} + 55%|█████▌ | 6472/11728 [3:08:41<8:19:19, 5.70s/it] 55%|█████▌ | 6473/11728 [3:08:47<8:18:36, 5.69s/it] {'loss': 0.4548, 'learning_rate': 8.807076159709572e-06, 'epoch': 0.55} + 55%|█████▌ | 6473/11728 [3:08:47<8:18:36, 5.69s/it] 55%|█████▌ | 6474/11728 [3:08:53<8:19:05, 5.70s/it] {'loss': 0.4612, 'learning_rate': 8.804334328415539e-06, 'epoch': 0.55} + 55%|█████▌ | 6474/11728 [3:08:53<8:19:05, 5.70s/it] 55%|█████▌ | 6475/11728 [3:08:58<8:19:42, 5.71s/it] {'loss': 0.4819, 'learning_rate': 8.801592588307964e-06, 'epoch': 0.55} + 55%|█████▌ | 6475/11728 [3:08:58<8:19:42, 5.71s/it] 55%|█████▌ | 6476/11728 [3:09:04<8:27:51, 5.80s/it] {'loss': 0.4632, 'learning_rate': 8.798850939595942e-06, 'epoch': 0.55} + 55%|█████▌ | 6476/11728 [3:09:04<8:27:51, 5.80s/it] 55%|█████▌ | 6477/11728 [3:09:10<8:32:37, 5.86s/it] {'loss': 0.4807, 'learning_rate': 8.796109382488561e-06, 'epoch': 0.55} + 55%|█████▌ | 6477/11728 [3:09:10<8:32:37, 5.86s/it] 55%|█████▌ | 6478/11728 [3:09:16<8:36:30, 5.90s/it] {'loss': 0.4627, 'learning_rate': 8.793367917194906e-06, 'epoch': 0.55} + 55%|█████▌ | 6478/11728 [3:09:16<8:36:30, 5.90s/it] 55%|█████▌ | 6479/11728 [3:09:22<8:32:01, 5.85s/it] {'loss': 0.4812, 'learning_rate': 8.790626543924048e-06, 'epoch': 0.55} + 55%|█████▌ | 6479/11728 [3:09:22<8:32:01, 5.85s/it] 55%|█████▌ | 6480/11728 [3:09:28<8:25:38, 5.78s/it] {'loss': 0.4797, 'learning_rate': 8.787885262885062e-06, 'epoch': 0.55} + 55%|█████▌ | 6480/11728 [3:09:28<8:25:38, 5.78s/it] 55%|█████▌ | 6481/11728 [3:09:33<8:26:32, 5.79s/it] {'loss': 0.4535, 'learning_rate': 8.785144074287006e-06, 'epoch': 0.55} + 55%|█████▌ | 6481/11728 [3:09:33<8:26:32, 5.79s/it] 55%|█████▌ | 6482/11728 [3:09:39<8:20:23, 5.72s/it] {'loss': 0.4688, 'learning_rate': 8.782402978338936e-06, 'epoch': 0.55} + 55%|█████▌ | 6482/11728 [3:09:39<8:20:23, 5.72s/it] 55%|█████▌ | 6483/11728 [3:09:45<8:26:54, 5.80s/it] {'loss': 0.4502, 'learning_rate': 8.779661975249893e-06, 'epoch': 0.55} + 55%|█████▌ | 6483/11728 [3:09:45<8:26:54, 5.80s/it] 55%|█████▌ | 6484/11728 [3:09:51<8:27:09, 5.80s/it] {'loss': 0.4625, 'learning_rate': 8.776921065228924e-06, 'epoch': 0.55} + 55%|█████▌ | 6484/11728 [3:09:51<8:27:09, 5.80s/it] 55%|█████▌ | 6485/11728 [3:09:57<8:30:48, 5.85s/it] {'loss': 0.4842, 'learning_rate': 8.774180248485065e-06, 'epoch': 0.55} + 55%|█████▌ | 6485/11728 [3:09:57<8:30:48, 5.85s/it] 55%|█████▌ | 6486/11728 [3:10:03<8:29:27, 5.83s/it] {'loss': 0.4588, 'learning_rate': 8.771439525227335e-06, 'epoch': 0.55} + 55%|█████▌ | 6486/11728 [3:10:03<8:29:27, 5.83s/it] 55%|█████▌ | 6487/11728 [3:10:08<8:27:45, 5.81s/it] {'loss': 0.459, 'learning_rate': 8.768698895664757e-06, 'epoch': 0.55} + 55%|█████▌ | 6487/11728 [3:10:08<8:27:45, 5.81s/it] 55%|█████▌ | 6488/11728 [3:10:14<8:21:48, 5.75s/it] {'loss': 0.4659, 'learning_rate': 8.765958360006339e-06, 'epoch': 0.55} + 55%|█████▌ | 6488/11728 [3:10:14<8:21:48, 5.75s/it] 55%|█████▌ | 6489/11728 [3:10:20<8:23:14, 5.76s/it] {'loss': 0.4895, 'learning_rate': 8.763217918461089e-06, 'epoch': 0.55} + 55%|█████▌ | 6489/11728 [3:10:20<8:23:14, 5.76s/it] 55%|█████▌ | 6490/11728 [3:10:26<8:31:27, 5.86s/it] {'loss': 0.4673, 'learning_rate': 8.760477571238006e-06, 'epoch': 0.55} + 55%|█████▌ | 6490/11728 [3:10:26<8:31:27, 5.86s/it] 55%|█████▌ | 6491/11728 [3:10:31<8:25:38, 5.79s/it] {'loss': 0.46, 'learning_rate': 8.75773731854608e-06, 'epoch': 0.55} + 55%|█████▌ | 6491/11728 [3:10:31<8:25:38, 5.79s/it] 55%|█████▌ | 6492/11728 [3:10:37<8:30:17, 5.85s/it] {'loss': 0.4705, 'learning_rate': 8.754997160594288e-06, 'epoch': 0.55} + 55%|█████▌ | 6492/11728 [3:10:37<8:30:17, 5.85s/it] 55%|█████▌ | 6493/11728 [3:10:44<8:38:20, 5.94s/it] {'loss': 0.5027, 'learning_rate': 8.75225709759161e-06, 'epoch': 0.55} + 55%|█████▌ | 6493/11728 [3:10:44<8:38:20, 5.94s/it] 55%|█████▌ | 6494/11728 [3:10:49<8:30:23, 5.85s/it] {'loss': 0.4413, 'learning_rate': 8.74951712974702e-06, 'epoch': 0.55} + 55%|█████▌ | 6494/11728 [3:10:49<8:30:23, 5.85s/it] 55%|█████▌ | 6495/11728 [3:10:55<8:27:19, 5.82s/it] {'loss': 0.4759, 'learning_rate': 8.74677725726947e-06, 'epoch': 0.55} + 55%|█████▌ | 6495/11728 [3:10:55<8:27:19, 5.82s/it] 55%|█████▌ | 6496/11728 [3:11:01<8:27:22, 5.82s/it] {'loss': 0.4763, 'learning_rate': 8.744037480367922e-06, 'epoch': 0.55} + 55%|█████▌ | 6496/11728 [3:11:01<8:27:22, 5.82s/it] 55%|█████▌ | 6497/11728 [3:11:06<8:20:07, 5.74s/it] {'loss': 0.4715, 'learning_rate': 8.741297799251314e-06, 'epoch': 0.55} + 55%|█████▌ | 6497/11728 [3:11:06<8:20:07, 5.74s/it] 55%|█████▌ | 6498/11728 [3:11:12<8:16:39, 5.70s/it] {'loss': 0.4616, 'learning_rate': 8.738558214128594e-06, 'epoch': 0.55} + 55%|█████▌ | 6498/11728 [3:11:12<8:16:39, 5.70s/it] 55%|█████▌ | 6499/11728 [3:11:18<8:19:54, 5.74s/it] {'loss': 0.4713, 'learning_rate': 8.735818725208692e-06, 'epoch': 0.55} + 55%|█████▌ | 6499/11728 [3:11:18<8:19:54, 5.74s/it]2 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... +10 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... + 55%|█████▌ | 6500/11728 [3:11:23<8:17:33, 5.71s/it] {'loss': 0.466, 'learning_rate': 8.733079332700532e-06, 'epoch': 0.55} + 55%|█████▌ | 6500/11728 [3:11:23<8:17:33, 5.71s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-6500/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-6500/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-6500/mm_projector +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/torch/nn/modules/module.py:1802: UserWarning: Positional args are being deprecated, use kwargs instead. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details. + warnings.warn( + 55%|█████▌ | 6501/11728 [3:11:59<21:07:10, 14.55s/it] {'loss': 0.455, 'learning_rate': 8.73034003681303e-06, 'epoch': 0.55} + 55%|█████▌ | 6501/11728 [3:11:59<21:07:10, 14.55s/it] 55%|█████▌ | 6502/11728 [3:12:04<17:12:26, 11.85s/it] {'loss': 0.4792, 'learning_rate': 8.727600837755095e-06, 'epoch': 0.55} + 55%|█████▌ | 6502/11728 [3:12:04<17:12:26, 11.85s/it] 55%|█████▌ | 6503/11728 [3:12:10<14:30:34, 10.00s/it] {'loss': 0.4589, 'learning_rate': 8.724861735735635e-06, 'epoch': 0.55} + 55%|█████▌ | 6503/11728 [3:12:10<14:30:34, 10.00s/it] 55%|█████▌ | 6504/11728 [3:12:15<12:33:42, 8.66s/it] {'loss': 0.4549, 'learning_rate': 8.722122730963542e-06, 'epoch': 0.55} + 55%|█████▌ | 6504/11728 [3:12:15<12:33:42, 8.66s/it] 55%|█████▌ | 6505/11728 [3:12:21<11:19:50, 7.81s/it] {'loss': 0.4839, 'learning_rate': 8.719383823647708e-06, 'epoch': 0.55} + 55%|█████▌ | 6505/11728 [3:12:21<11:19:50, 7.81s/it] 55%|█████▌ | 6506/11728 [3:12:27<10:24:06, 7.17s/it] {'loss': 0.4589, 'learning_rate': 8.716645013997003e-06, 'epoch': 0.55} + 55%|█████▌ | 6506/11728 [3:12:27<10:24:06, 7.17s/it] 55%|█████▌ | 6507/11728 [3:12:32<9:44:44, 6.72s/it] {'loss': 0.4554, 'learning_rate': 8.71390630222031e-06, 'epoch': 0.55} + 55%|█████▌ | 6507/11728 [3:12:33<9:44:44, 6.72s/it] 55%|█████▌ | 6508/11728 [3:12:39<9:30:14, 6.55s/it] {'loss': 0.4523, 'learning_rate': 8.711167688526495e-06, 'epoch': 0.55} + 55%|█████▌ | 6508/11728 [3:12:39<9:30:14, 6.55s/it] 55%|█████▌ | 6509/11728 [3:12:44<9:09:13, 6.31s/it] {'loss': 0.4894, 'learning_rate': 8.70842917312441e-06, 'epoch': 0.55} + 55%|█████▌ | 6509/11728 [3:12:44<9:09:13, 6.31s/it] 56%|█████▌ | 6510/11728 [3:12:50<8:49:44, 6.09s/it] {'loss': 0.4456, 'learning_rate': 8.705690756222909e-06, 'epoch': 0.56} + 56%|█████▌ | 6510/11728 [3:12:50<8:49:44, 6.09s/it] 56%|█████▌ | 6511/11728 [3:12:56<8:45:02, 6.04s/it] {'loss': 0.4682, 'learning_rate': 8.702952438030832e-06, 'epoch': 0.56} + 56%|█████▌ | 6511/11728 [3:12:56<8:45:02, 6.04s/it] 56%|█████▌ | 6512/11728 [3:13:02<8:45:36, 6.05s/it] {'loss': 0.4607, 'learning_rate': 8.700214218757021e-06, 'epoch': 0.56} + 56%|█████▌ | 6512/11728 [3:13:02<8:45:36, 6.05s/it] 56%|█████▌ | 6513/11728 [3:13:08<8:34:19, 5.92s/it] {'loss': 0.4763, 'learning_rate': 8.697476098610299e-06, 'epoch': 0.56} + 56%|█████▌ | 6513/11728 [3:13:08<8:34:19, 5.92s/it] 56%|█████▌ | 6514/11728 [3:13:13<8:26:56, 5.83s/it] {'loss': 0.4783, 'learning_rate': 8.694738077799487e-06, 'epoch': 0.56} + 56%|█████▌ | 6514/11728 [3:13:13<8:26:56, 5.83s/it] 56%|█████▌ | 6515/11728 [3:13:19<8:36:49, 5.95s/it] {'loss': 0.4731, 'learning_rate': 8.692000156533395e-06, 'epoch': 0.56} + 56%|█████▌ | 6515/11728 [3:13:19<8:36:49, 5.95s/it] 56%|█████▌ | 6516/11728 [3:13:25<8:24:01, 5.80s/it] {'loss': 0.4767, 'learning_rate': 8.689262335020836e-06, 'epoch': 0.56} + 56%|█████▌ | 6516/11728 [3:13:25<8:24:01, 5.80s/it] 56%|█████▌ | 6517/11728 [3:13:31<8:25:20, 5.82s/it] {'loss': 0.4897, 'learning_rate': 8.686524613470603e-06, 'epoch': 0.56} + 56%|█████▌ | 6517/11728 [3:13:31<8:25:20, 5.82s/it] 56%|█████▌ | 6518/11728 [3:13:37<8:26:45, 5.84s/it] {'loss': 0.4802, 'learning_rate': 8.683786992091488e-06, 'epoch': 0.56} + 56%|█████▌ | 6518/11728 [3:13:37<8:26:45, 5.84s/it] 56%|█████▌ | 6519/11728 [3:13:42<8:25:36, 5.82s/it] {'loss': 0.4711, 'learning_rate': 8.68104947109227e-06, 'epoch': 0.56} + 56%|█████▌ | 6519/11728 [3:13:42<8:25:36, 5.82s/it] 56%|█████▌ | 6520/11728 [3:13:48<8:20:46, 5.77s/it] {'loss': 0.4675, 'learning_rate': 8.678312050681724e-06, 'epoch': 0.56} + 56%|█████▌ | 6520/11728 [3:13:48<8:20:46, 5.77s/it] 56%|█████▌ | 6521/11728 [3:13:54<8:16:16, 5.72s/it] {'loss': 0.467, 'learning_rate': 8.675574731068622e-06, 'epoch': 0.56} + 56%|█████▌ | 6521/11728 [3:13:54<8:16:16, 5.72s/it] 56%|█████▌ | 6522/11728 [3:13:59<8:19:04, 5.75s/it] {'loss': 0.4695, 'learning_rate': 8.672837512461718e-06, 'epoch': 0.56} + 56%|█████▌ | 6522/11728 [3:13:59<8:19:04, 5.75s/it] 56%|█████▌ | 6523/11728 [3:14:05<8:22:40, 5.79s/it] {'loss': 0.4702, 'learning_rate': 8.67010039506977e-06, 'epoch': 0.56} + 56%|█████▌ | 6523/11728 [3:14:05<8:22:40, 5.79s/it] 56%|█████▌ | 6524/11728 [3:14:12<8:31:23, 5.90s/it] {'loss': 0.4734, 'learning_rate': 8.667363379101513e-06, 'epoch': 0.56} + 56%|█████▌ | 6524/11728 [3:14:12<8:31:23, 5.90s/it] 56%|█████▌ | 6525/11728 [3:14:17<8:32:08, 5.91s/it] {'loss': 0.471, 'learning_rate': 8.66462646476569e-06, 'epoch': 0.56} + 56%|█████▌ | 6525/11728 [3:14:17<8:32:08, 5.91s/it] 56%|█████▌ | 6526/11728 [3:14:23<8:26:23, 5.84s/it] {'loss': 0.4577, 'learning_rate': 8.66188965227103e-06, 'epoch': 0.56} + 56%|█████▌ | 6526/11728 [3:14:23<8:26:23, 5.84s/it] 56%|█████▌ | 6527/11728 [3:14:29<8:29:34, 5.88s/it] {'loss': 0.4765, 'learning_rate': 8.659152941826251e-06, 'epoch': 0.56} + 56%|█████▌ | 6527/11728 [3:14:29<8:29:34, 5.88s/it] 56%|█████▌ | 6528/11728 [3:14:35<8:20:27, 5.77s/it] {'loss': 0.481, 'learning_rate': 8.656416333640067e-06, 'epoch': 0.56} + 56%|█████▌ | 6528/11728 [3:14:35<8:20:27, 5.77s/it] 56%|█████▌ | 6529/11728 [3:14:41<8:23:17, 5.81s/it] {'loss': 0.4779, 'learning_rate': 8.653679827921178e-06, 'epoch': 0.56} + 56%|█████▌ | 6529/11728 [3:14:41<8:23:17, 5.81s/it] 56%|█████▌ | 6530/11728 [3:14:46<8:25:17, 5.83s/it] {'loss': 0.4838, 'learning_rate': 8.65094342487829e-06, 'epoch': 0.56} + 56%|█████▌ | 6530/11728 [3:14:46<8:25:17, 5.83s/it] 56%|█████▌ | 6531/11728 [3:14:52<8:21:26, 5.79s/it] {'loss': 0.4801, 'learning_rate': 8.648207124720088e-06, 'epoch': 0.56} + 56%|█████▌ | 6531/11728 [3:14:52<8:21:26, 5.79s/it] 56%|█████▌ | 6532/11728 [3:14:58<8:17:10, 5.74s/it] {'loss': 0.4762, 'learning_rate': 8.645470927655254e-06, 'epoch': 0.56} + 56%|█████▌ | 6532/11728 [3:14:58<8:17:10, 5.74s/it] 56%|█████▌ | 6533/11728 [3:15:03<8:10:48, 5.67s/it] {'loss': 0.4342, 'learning_rate': 8.642734833892463e-06, 'epoch': 0.56} + 56%|█████▌ | 6533/11728 [3:15:03<8:10:48, 5.67s/it] 56%|█████▌ | 6534/11728 [3:15:09<8:15:20, 5.72s/it] {'loss': 0.4836, 'learning_rate': 8.639998843640377e-06, 'epoch': 0.56} + 56%|█████▌ | 6534/11728 [3:15:09<8:15:20, 5.72s/it] 56%|█████▌ | 6535/11728 [3:15:15<8:14:50, 5.72s/it] {'loss': 0.4752, 'learning_rate': 8.637262957107661e-06, 'epoch': 0.56} + 56%|█████▌ | 6535/11728 [3:15:15<8:14:50, 5.72s/it] 56%|█████▌ | 6536/11728 [3:15:20<8:12:28, 5.69s/it] {'loss': 0.4701, 'learning_rate': 8.63452717450296e-06, 'epoch': 0.56} + 56%|█████▌ | 6536/11728 [3:15:20<8:12:28, 5.69s/it] 56%|█████▌ | 6537/11728 [3:15:26<8:15:52, 5.73s/it] {'loss': 0.5, 'learning_rate': 8.631791496034916e-06, 'epoch': 0.56} + 56%|█████▌ | 6537/11728 [3:15:26<8:15:52, 5.73s/it] 56%|█████▌ | 6538/11728 [3:15:32<8:18:20, 5.76s/it] {'loss': 0.4719, 'learning_rate': 8.629055921912164e-06, 'epoch': 0.56} + 56%|█████▌ | 6538/11728 [3:15:32<8:18:20, 5.76s/it] 56%|█████▌ | 6539/11728 [3:15:38<8:16:37, 5.74s/it] {'loss': 0.485, 'learning_rate': 8.626320452343333e-06, 'epoch': 0.56} + 56%|█████▌ | 6539/11728 [3:15:38<8:16:37, 5.74s/it] 56%|█████▌ | 6540/11728 [3:15:44<8:21:19, 5.80s/it] {'loss': 0.474, 'learning_rate': 8.623585087537039e-06, 'epoch': 0.56} + 56%|█████▌ | 6540/11728 [3:15:44<8:21:19, 5.80s/it] 56%|█████▌ | 6541/11728 [3:15:50<8:24:38, 5.84s/it] {'loss': 0.5026, 'learning_rate': 8.620849827701893e-06, 'epoch': 0.56} + 56%|█████▌ | 6541/11728 [3:15:50<8:24:38, 5.84s/it] 56%|█████▌ | 6542/11728 [3:15:56<8:29:32, 5.90s/it] {'loss': 0.4622, 'learning_rate': 8.618114673046494e-06, 'epoch': 0.56} + 56%|█████▌ | 6542/11728 [3:15:56<8:29:32, 5.90s/it] 56%|█████▌ | 6543/11728 [3:16:01<8:19:21, 5.78s/it] {'loss': 0.4581, 'learning_rate': 8.61537962377944e-06, 'epoch': 0.56} + 56%|█████▌ | 6543/11728 [3:16:01<8:19:21, 5.78s/it] 56%|█████▌ | 6544/11728 [3:16:07<8:20:49, 5.80s/it] {'loss': 0.4798, 'learning_rate': 8.61264468010932e-06, 'epoch': 0.56} + 56%|█████▌ | 6544/11728 [3:16:07<8:20:49, 5.80s/it] 56%|█████▌ | 6545/11728 [3:16:13<8:16:47, 5.75s/it] {'loss': 0.4415, 'learning_rate': 8.609909842244706e-06, 'epoch': 0.56} + 56%|█████▌ | 6545/11728 [3:16:13<8:16:47, 5.75s/it] 56%|█████▌ | 6546/11728 [3:16:19<8:20:50, 5.80s/it] {'loss': 0.4686, 'learning_rate': 8.607175110394171e-06, 'epoch': 0.56} + 56%|█████▌ | 6546/11728 [3:16:19<8:20:50, 5.80s/it] 56%|█████▌ | 6547/11728 [3:16:25<8:30:37, 5.91s/it] {'loss': 0.4793, 'learning_rate': 8.604440484766276e-06, 'epoch': 0.56} + 56%|█████▌ | 6547/11728 [3:16:25<8:30:37, 5.91s/it] 56%|█████▌ | 6548/11728 [3:16:31<8:31:12, 5.92s/it] {'loss': 0.4844, 'learning_rate': 8.601705965569579e-06, 'epoch': 0.56} + 56%|█████▌ | 6548/11728 [3:16:31<8:31:12, 5.92s/it] 56%|█████▌ | 6549/11728 [3:16:37<8:32:45, 5.94s/it] {'loss': 0.4452, 'learning_rate': 8.59897155301262e-06, 'epoch': 0.56} + 56%|█████▌ | 6549/11728 [3:16:37<8:32:45, 5.94s/it]2 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +0 AutoResumeHook: Checking whether to suspend... + 56%|█████▌ | 6550/11728 [3:16:43<8:35:45, 5.98s/it] {'loss': 0.484, 'learning_rate': 8.596237247303941e-06, 'epoch': 0.56} + 56%|█████▌ | 6550/11728 [3:16:43<8:35:45, 5.98s/it] 56%|█████▌ | 6551/11728 [3:16:48<8:22:52, 5.83s/it] {'loss': 0.453, 'learning_rate': 8.59350304865207e-06, 'epoch': 0.56} + 56%|█████▌ | 6551/11728 [3:16:48<8:22:52, 5.83s/it] 56%|█████▌ | 6552/11728 [3:16:54<8:35:10, 5.97s/it] {'loss': 0.477, 'learning_rate': 8.590768957265525e-06, 'epoch': 0.56} + 56%|█████▌ | 6552/11728 [3:16:55<8:35:10, 5.97s/it] 56%|█████▌ | 6553/11728 [3:17:00<8:34:16, 5.96s/it] {'loss': 0.4824, 'learning_rate': 8.588034973352827e-06, 'epoch': 0.56} + 56%|█████▌ | 6553/11728 [3:17:00<8:34:16, 5.96s/it] 56%|█████▌ | 6554/11728 [3:17:06<8:27:29, 5.89s/it] {'loss': 0.4757, 'learning_rate': 8.585301097122473e-06, 'epoch': 0.56} + 56%|█████▌ | 6554/11728 [3:17:06<8:27:29, 5.89s/it] 56%|█████▌ | 6555/11728 [3:17:12<8:35:40, 5.98s/it] {'loss': 0.4603, 'learning_rate': 8.58256732878297e-06, 'epoch': 0.56} + 56%|█████▌ | 6555/11728 [3:17:12<8:35:40, 5.98s/it] 56%|█████▌ | 6556/11728 [3:17:18<8:27:43, 5.89s/it] {'loss': 0.4603, 'learning_rate': 8.579833668542796e-06, 'epoch': 0.56} + 56%|█████▌ | 6556/11728 [3:17:18<8:27:43, 5.89s/it] 56%|█████▌ | 6557/11728 [3:17:24<8:25:08, 5.86s/it] {'loss': 0.4858, 'learning_rate': 8.577100116610433e-06, 'epoch': 0.56} + 56%|█████▌ | 6557/11728 [3:17:24<8:25:08, 5.86s/it] 56%|█████▌ | 6558/11728 [3:17:30<8:23:50, 5.85s/it] {'loss': 0.4603, 'learning_rate': 8.574366673194357e-06, 'epoch': 0.56} + 56%|█████▌ | 6558/11728 [3:17:30<8:23:50, 5.85s/it] 56%|█████▌ | 6559/11728 [3:17:35<8:18:41, 5.79s/it] {'loss': 0.4658, 'learning_rate': 8.571633338503034e-06, 'epoch': 0.56} + 56%|█████▌ | 6559/11728 [3:17:35<8:18:41, 5.79s/it] 56%|█████▌ | 6560/11728 [3:17:41<8:28:50, 5.91s/it] {'loss': 0.4644, 'learning_rate': 8.568900112744912e-06, 'epoch': 0.56} + 56%|█████▌ | 6560/11728 [3:17:41<8:28:50, 5.91s/it] 56%|█████▌ | 6561/11728 [3:17:47<8:29:58, 5.92s/it] {'loss': 0.4797, 'learning_rate': 8.56616699612844e-06, 'epoch': 0.56} + 56%|█████▌ | 6561/11728 [3:17:47<8:29:58, 5.92s/it] 56%|█████▌ | 6562/11728 [3:17:53<8:27:04, 5.89s/it] {'loss': 0.4716, 'learning_rate': 8.563433988862064e-06, 'epoch': 0.56} + 56%|█████▌ | 6562/11728 [3:17:53<8:27:04, 5.89s/it] 56%|█████▌ | 6563/11728 [3:17:59<8:25:14, 5.87s/it] {'loss': 0.4762, 'learning_rate': 8.560701091154208e-06, 'epoch': 0.56} + 56%|█████▌ | 6563/11728 [3:17:59<8:25:14, 5.87s/it] 56%|█████▌ | 6564/11728 [3:18:05<8:20:30, 5.82s/it] {'loss': 0.4816, 'learning_rate': 8.557968303213296e-06, 'epoch': 0.56} + 56%|█████▌ | 6564/11728 [3:18:05<8:20:30, 5.82s/it] 56%|█████▌ | 6565/11728 [3:18:11<8:36:36, 6.00s/it] {'loss': 0.4797, 'learning_rate': 8.555235625247743e-06, 'epoch': 0.56} + 56%|█████▌ | 6565/11728 [3:18:11<8:36:36, 6.00s/it] 56%|█████▌ | 6566/11728 [3:18:17<8:27:12, 5.90s/it] {'loss': 0.4658, 'learning_rate': 8.552503057465949e-06, 'epoch': 0.56} + 56%|█████▌ | 6566/11728 [3:18:17<8:27:12, 5.90s/it] 56%|█████▌ | 6567/11728 [3:18:23<8:28:36, 5.91s/it] {'loss': 0.4652, 'learning_rate': 8.549770600076314e-06, 'epoch': 0.56} + 56%|█████▌ | 6567/11728 [3:18:23<8:28:36, 5.91s/it] 56%|█████▌ | 6568/11728 [3:18:28<8:20:48, 5.82s/it] {'loss': 0.4546, 'learning_rate': 8.547038253287233e-06, 'epoch': 0.56} + 56%|█████▌ | 6568/11728 [3:18:28<8:20:48, 5.82s/it] 56%|█████▌ | 6569/11728 [3:18:34<8:18:23, 5.80s/it] {'loss': 0.504, 'learning_rate': 8.544306017307077e-06, 'epoch': 0.56} + 56%|█████▌ | 6569/11728 [3:18:34<8:18:23, 5.80s/it] 56%|█████▌ | 6570/11728 [3:18:40<8:13:54, 5.75s/it] {'loss': 0.4872, 'learning_rate': 8.54157389234422e-06, 'epoch': 0.56} + 56%|█████▌ | 6570/11728 [3:18:40<8:13:54, 5.75s/it] 56%|█████▌ | 6571/11728 [3:18:46<8:20:12, 5.82s/it] {'loss': 0.4786, 'learning_rate': 8.538841878607031e-06, 'epoch': 0.56} + 56%|█████▌ | 6571/11728 [3:18:46<8:20:12, 5.82s/it] 56%|█████▌ | 6572/11728 [3:18:51<8:15:15, 5.76s/it] {'loss': 0.462, 'learning_rate': 8.536109976303859e-06, 'epoch': 0.56} + 56%|█████▌ | 6572/11728 [3:18:51<8:15:15, 5.76s/it] 56%|█████▌ | 6573/11728 [3:18:57<8:05:12, 5.65s/it] {'loss': 0.4752, 'learning_rate': 8.533378185643052e-06, 'epoch': 0.56} + 56%|█████▌ | 6573/11728 [3:18:57<8:05:12, 5.65s/it] 56%|█████▌ | 6574/11728 [3:19:02<8:03:55, 5.63s/it] {'loss': 0.4819, 'learning_rate': 8.530646506832949e-06, 'epoch': 0.56} + 56%|█████▌ | 6574/11728 [3:19:02<8:03:55, 5.63s/it] 56%|█████▌ | 6575/11728 [3:19:08<8:03:51, 5.63s/it] {'loss': 0.4623, 'learning_rate': 8.527914940081873e-06, 'epoch': 0.56} + 56%|█████▌ | 6575/11728 [3:19:08<8:03:51, 5.63s/it] 56%|█████▌ | 6576/11728 [3:19:14<8:02:59, 5.62s/it] {'loss': 0.4537, 'learning_rate': 8.525183485598152e-06, 'epoch': 0.56} + 56%|█████▌ | 6576/11728 [3:19:14<8:02:59, 5.62s/it] 56%|█████▌ | 6577/11728 [3:19:19<8:03:27, 5.63s/it] {'loss': 0.4649, 'learning_rate': 8.522452143590096e-06, 'epoch': 0.56} + 56%|█████▌ | 6577/11728 [3:19:19<8:03:27, 5.63s/it] 56%|█████▌ | 6578/11728 [3:19:25<8:15:32, 5.77s/it] {'loss': 0.4619, 'learning_rate': 8.519720914266008e-06, 'epoch': 0.56} + 56%|█████▌ | 6578/11728 [3:19:25<8:15:32, 5.77s/it] 56%|█████▌ | 6579/11728 [3:19:31<8:11:43, 5.73s/it] {'loss': 0.4587, 'learning_rate': 8.51698979783418e-06, 'epoch': 0.56} + 56%|█████▌ | 6579/11728 [3:19:31<8:11:43, 5.73s/it] 56%|█████▌ | 6580/11728 [3:19:37<8:18:51, 5.81s/it] {'loss': 0.4833, 'learning_rate': 8.514258794502906e-06, 'epoch': 0.56} + 56%|█████▌ | 6580/11728 [3:19:37<8:18:51, 5.81s/it] 56%|█████▌ | 6581/11728 [3:19:43<8:14:42, 5.77s/it] {'loss': 0.4489, 'learning_rate': 8.511527904480457e-06, 'epoch': 0.56} + 56%|█████▌ | 6581/11728 [3:19:43<8:14:42, 5.77s/it] 56%|█████▌ | 6582/11728 [3:19:48<8:11:42, 5.73s/it] {'loss': 0.4903, 'learning_rate': 8.508797127975105e-06, 'epoch': 0.56} + 56%|█████▌ | 6582/11728 [3:19:48<8:11:42, 5.73s/it] 56%|█████▌ | 6583/11728 [3:19:54<8:13:58, 5.76s/it] {'loss': 0.494, 'learning_rate': 8.506066465195113e-06, 'epoch': 0.56} + 56%|█████▌ | 6583/11728 [3:19:54<8:13:58, 5.76s/it] 56%|█████▌ | 6584/11728 [3:20:00<8:25:34, 5.90s/it] {'loss': 0.4848, 'learning_rate': 8.503335916348722e-06, 'epoch': 0.56} + 56%|█████▌ | 6584/11728 [3:20:00<8:25:34, 5.90s/it] 56%|█████▌ | 6585/11728 [3:20:06<8:22:54, 5.87s/it] {'loss': 0.4764, 'learning_rate': 8.500605481644186e-06, 'epoch': 0.56} + 56%|█████▌ | 6585/11728 [3:20:06<8:22:54, 5.87s/it] 56%|█████▌ | 6586/11728 [3:20:12<8:22:29, 5.86s/it] {'loss': 0.4725, 'learning_rate': 8.497875161289737e-06, 'epoch': 0.56} + 56%|█████▌ | 6586/11728 [3:20:12<8:22:29, 5.86s/it] 56%|█████▌ | 6587/11728 [3:20:18<8:19:07, 5.83s/it] {'loss': 0.4746, 'learning_rate': 8.495144955493596e-06, 'epoch': 0.56} + 56%|█████▌ | 6587/11728 [3:20:18<8:19:07, 5.83s/it] 56%|█████▌ | 6588/11728 [3:20:23<8:12:57, 5.75s/it] {'loss': 0.4752, 'learning_rate': 8.492414864463988e-06, 'epoch': 0.56} + 56%|█████▌ | 6588/11728 [3:20:23<8:12:57, 5.75s/it] 56%|█████▌ | 6589/11728 [3:20:29<8:15:50, 5.79s/it] {'loss': 0.4868, 'learning_rate': 8.489684888409111e-06, 'epoch': 0.56} + 56%|█████▌ | 6589/11728 [3:20:29<8:15:50, 5.79s/it] 56%|█████▌ | 6590/11728 [3:20:35<8:17:49, 5.81s/it] {'loss': 0.4674, 'learning_rate': 8.486955027537172e-06, 'epoch': 0.56} + 56%|█████▌ | 6590/11728 [3:20:35<8:17:49, 5.81s/it] 56%|█████▌ | 6591/11728 [3:20:41<8:11:29, 5.74s/it] {'loss': 0.4617, 'learning_rate': 8.484225282056362e-06, 'epoch': 0.56} + 56%|█████▌ | 6591/11728 [3:20:41<8:11:29, 5.74s/it] 56%|█████▌ | 6592/11728 [3:20:46<8:11:14, 5.74s/it] {'loss': 0.4826, 'learning_rate': 8.481495652174859e-06, 'epoch': 0.56} + 56%|█████▌ | 6592/11728 [3:20:46<8:11:14, 5.74s/it] 56%|█████▌ | 6593/11728 [3:20:52<8:07:39, 5.70s/it] {'loss': 0.477, 'learning_rate': 8.478766138100834e-06, 'epoch': 0.56} + 56%|█████▌ | 6593/11728 [3:20:52<8:07:39, 5.70s/it] 56%|█████▌ | 6594/11728 [3:20:57<8:01:36, 5.63s/it] {'loss': 0.4541, 'learning_rate': 8.476036740042456e-06, 'epoch': 0.56} + 56%|█████▌ | 6594/11728 [3:20:57<8:01:36, 5.63s/it] 56%|█████▌ | 6595/11728 [3:21:03<8:05:28, 5.67s/it] {'loss': 0.4799, 'learning_rate': 8.47330745820788e-06, 'epoch': 0.56} + 56%|█████▌ | 6595/11728 [3:21:03<8:05:28, 5.67s/it] 56%|█████▌ | 6596/11728 [3:21:09<8:05:38, 5.68s/it] {'loss': 0.4762, 'learning_rate': 8.470578292805249e-06, 'epoch': 0.56} + 56%|█████▌ | 6596/11728 [3:21:09<8:05:38, 5.68s/it] 56%|█████▋ | 6597/11728 [3:21:15<8:05:07, 5.67s/it] {'loss': 0.4511, 'learning_rate': 8.467849244042706e-06, 'epoch': 0.56} + 56%|█████▋ | 6597/11728 [3:21:15<8:05:07, 5.67s/it] 56%|█████▋ | 6598/11728 [3:21:21<8:12:15, 5.76s/it] {'loss': 0.4655, 'learning_rate': 8.465120312128371e-06, 'epoch': 0.56} + 56%|█████▋ | 6598/11728 [3:21:21<8:12:15, 5.76s/it] 56%|█████▋ | 6599/11728 [3:21:26<8:15:55, 5.80s/it] {'loss': 0.4695, 'learning_rate': 8.46239149727037e-06, 'epoch': 0.56} + 56%|█████▋ | 6599/11728 [3:21:26<8:15:55, 5.80s/it]2 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... +0 1 AutoResumeHook: Checking whether to suspend...AutoResumeHook: Checking whether to suspend... + + 56%|█████▋ | 6600/11728 [3:21:32<8:09:12, 5.72s/it] {'loss': 0.4795, 'learning_rate': 8.459662799676818e-06, 'epoch': 0.56} + 56%|█████▋ | 6600/11728 [3:21:32<8:09:12, 5.72s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-6600/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-6600/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-6600/mm_projector +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/torch/nn/modules/module.py:1802: UserWarning: Positional args are being deprecated, use kwargs instead. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details. + warnings.warn( + 56%|█████▋ | 6601/11728 [3:22:05<19:57:59, 14.02s/it] {'loss': 0.4736, 'learning_rate': 8.456934219555809e-06, 'epoch': 0.56} + 56%|█████▋ | 6601/11728 [3:22:05<19:57:59, 14.02s/it] 56%|█████▋ | 6602/11728 [3:22:11<16:24:09, 11.52s/it] {'loss': 0.461, 'learning_rate': 8.454205757115434e-06, 'epoch': 0.56} + 56%|█████▋ | 6602/11728 [3:22:11<16:24:09, 11.52s/it] 56%|█████▋ | 6603/11728 [3:22:17<13:56:01, 9.79s/it] {'loss': 0.4846, 'learning_rate': 8.451477412563786e-06, 'epoch': 0.56} + 56%|█████▋ | 6603/11728 [3:22:17<13:56:01, 9.79s/it] 56%|█████▋ | 6604/11728 [3:22:22<12:06:47, 8.51s/it] {'loss': 0.4655, 'learning_rate': 8.448749186108936e-06, 'epoch': 0.56} + 56%|█████▋ | 6604/11728 [3:22:22<12:06:47, 8.51s/it] 56%|█████▋ | 6605/11728 [3:22:28<10:49:52, 7.61s/it] {'loss': 0.4818, 'learning_rate': 8.446021077958947e-06, 'epoch': 0.56} + 56%|█████▋ | 6605/11728 [3:22:28<10:49:52, 7.61s/it] 56%|█████▋ | 6606/11728 [3:22:34<10:03:25, 7.07s/it] {'loss': 0.4734, 'learning_rate': 8.44329308832188e-06, 'epoch': 0.56} + 56%|█████▋ | 6606/11728 [3:22:34<10:03:25, 7.07s/it] 56%|█████▋ | 6607/11728 [3:22:39<9:25:57, 6.63s/it] {'loss': 0.4472, 'learning_rate': 8.440565217405778e-06, 'epoch': 0.56} + 56%|█████▋ | 6607/11728 [3:22:39<9:25:57, 6.63s/it] 56%|█████▋ | 6608/11728 [3:22:45<9:03:24, 6.37s/it] {'loss': 0.4825, 'learning_rate': 8.437837465418684e-06, 'epoch': 0.56} + 56%|█████▋ | 6608/11728 [3:22:45<9:03:24, 6.37s/it] 56%|█████▋ | 6609/11728 [3:22:51<8:41:48, 6.12s/it] {'loss': 0.4765, 'learning_rate': 8.43510983256863e-06, 'epoch': 0.56} + 56%|█████▋ | 6609/11728 [3:22:51<8:41:48, 6.12s/it] 56%|█████▋ | 6610/11728 [3:22:56<8:28:46, 5.96s/it] {'loss': 0.4571, 'learning_rate': 8.43238231906363e-06, 'epoch': 0.56} + 56%|█████▋ | 6610/11728 [3:22:56<8:28:46, 5.96s/it] 56%|█████▋ | 6611/11728 [3:23:02<8:21:53, 5.88s/it] {'loss': 0.4623, 'learning_rate': 8.429654925111701e-06, 'epoch': 0.56} + 56%|█████▋ | 6611/11728 [3:23:02<8:21:53, 5.88s/it] 56%|█████▋ | 6612/11728 [3:23:07<8:14:21, 5.80s/it] {'loss': 0.4825, 'learning_rate': 8.426927650920842e-06, 'epoch': 0.56} + 56%|█████▋ | 6612/11728 [3:23:07<8:14:21, 5.80s/it] 56%|█████▋ | 6613/11728 [3:23:13<8:08:26, 5.73s/it] {'loss': 0.4713, 'learning_rate': 8.42420049669905e-06, 'epoch': 0.56} + 56%|█████▋ | 6613/11728 [3:23:13<8:08:26, 5.73s/it] 56%|█████▋ | 6614/11728 [3:23:19<8:11:32, 5.77s/it] {'loss': 0.482, 'learning_rate': 8.421473462654304e-06, 'epoch': 0.56} + 56%|█████▋ | 6614/11728 [3:23:19<8:11:32, 5.77s/it] 56%|█████▋ | 6615/11728 [3:23:24<8:03:36, 5.68s/it] {'loss': 0.4756, 'learning_rate': 8.418746548994585e-06, 'epoch': 0.56} + 56%|█████▋ | 6615/11728 [3:23:24<8:03:36, 5.68s/it] 56%|█████▋ | 6616/11728 [3:23:30<8:07:21, 5.72s/it] {'loss': 0.4738, 'learning_rate': 8.416019755927851e-06, 'epoch': 0.56} + 56%|█████▋ | 6616/11728 [3:23:30<8:07:21, 5.72s/it] 56%|█████▋ | 6617/11728 [3:23:36<8:14:15, 5.80s/it] {'loss': 0.4676, 'learning_rate': 8.413293083662065e-06, 'epoch': 0.56} + 56%|█████▋ | 6617/11728 [3:23:36<8:14:15, 5.80s/it] 56%|█████▋ | 6618/11728 [3:23:42<8:11:21, 5.77s/it] {'loss': 0.4694, 'learning_rate': 8.410566532405175e-06, 'epoch': 0.56} + 56%|█████▋ | 6618/11728 [3:23:42<8:11:21, 5.77s/it] 56%|█████▋ | 6619/11728 [3:23:48<8:11:26, 5.77s/it] {'loss': 0.4742, 'learning_rate': 8.407840102365116e-06, 'epoch': 0.56} + 56%|█████▋ | 6619/11728 [3:23:48<8:11:26, 5.77s/it] 56%|█████▋ | 6620/11728 [3:23:53<8:02:41, 5.67s/it] {'loss': 0.4408, 'learning_rate': 8.405113793749819e-06, 'epoch': 0.56} + 56%|█████▋ | 6620/11728 [3:23:53<8:02:41, 5.67s/it] 56%|█████▋ | 6621/11728 [3:23:59<8:01:10, 5.65s/it] {'loss': 0.4845, 'learning_rate': 8.402387606767199e-06, 'epoch': 0.56} + 56%|█████▋ | 6621/11728 [3:23:59<8:01:10, 5.65s/it] 56%|█████▋ | 6622/11728 [3:24:04<8:05:37, 5.71s/it] {'loss': 0.4823, 'learning_rate': 8.399661541625174e-06, 'epoch': 0.56} + 56%|█████▋ | 6622/11728 [3:24:04<8:05:37, 5.71s/it] 56%|█████▋ | 6623/11728 [3:24:10<7:59:33, 5.64s/it] {'loss': 0.455, 'learning_rate': 8.396935598531637e-06, 'epoch': 0.56} + 56%|█████▋ | 6623/11728 [3:24:10<7:59:33, 5.64s/it] 56%|█████▋ | 6624/11728 [3:24:16<8:03:53, 5.69s/it] {'loss': 0.4928, 'learning_rate': 8.39420977769449e-06, 'epoch': 0.56} + 56%|█████▋ | 6624/11728 [3:24:16<8:03:53, 5.69s/it] 56%|█████▋ | 6625/11728 [3:24:22<8:07:09, 5.73s/it] {'loss': 0.4736, 'learning_rate': 8.391484079321602e-06, 'epoch': 0.56} + 56%|█████▋ | 6625/11728 [3:24:22<8:07:09, 5.73s/it] 56%|█████▋ | 6626/11728 [3:24:27<8:05:21, 5.71s/it] {'loss': 0.4567, 'learning_rate': 8.388758503620856e-06, 'epoch': 0.56} + 56%|█████▋ | 6626/11728 [3:24:27<8:05:21, 5.71s/it] 57%|█████▋ | 6627/11728 [3:24:33<8:00:29, 5.65s/it] {'loss': 0.4586, 'learning_rate': 8.386033050800116e-06, 'epoch': 0.57} + 57%|█████▋ | 6627/11728 [3:24:33<8:00:29, 5.65s/it] 57%|█████▋ | 6628/11728 [3:24:38<8:02:35, 5.68s/it] {'loss': 0.4745, 'learning_rate': 8.383307721067231e-06, 'epoch': 0.57} + 57%|█████▋ | 6628/11728 [3:24:39<8:02:35, 5.68s/it] 57%|█████▋ | 6629/11728 [3:24:44<8:09:10, 5.76s/it] {'loss': 0.4847, 'learning_rate': 8.38058251463005e-06, 'epoch': 0.57} + 57%|█████▋ | 6629/11728 [3:24:44<8:09:10, 5.76s/it] 57%|█████▋ | 6630/11728 [3:24:50<8:05:45, 5.72s/it] {'loss': 0.464, 'learning_rate': 8.377857431696405e-06, 'epoch': 0.57} + 57%|█████▋ | 6630/11728 [3:24:50<8:05:45, 5.72s/it] 57%|█████▋ | 6631/11728 [3:24:56<8:08:46, 5.75s/it] {'loss': 0.4792, 'learning_rate': 8.375132472474127e-06, 'epoch': 0.57} + 57%|█████▋ | 6631/11728 [3:24:56<8:08:46, 5.75s/it] 57%|█████▋ | 6632/11728 [3:25:02<8:10:47, 5.78s/it] {'loss': 0.4637, 'learning_rate': 8.37240763717103e-06, 'epoch': 0.57} + 57%|█████▋ | 6632/11728 [3:25:02<8:10:47, 5.78s/it] 57%|█████▋ | 6633/11728 [3:25:08<8:14:20, 5.82s/it] {'loss': 0.4667, 'learning_rate': 8.369682925994922e-06, 'epoch': 0.57} + 57%|█████▋ | 6633/11728 [3:25:08<8:14:20, 5.82s/it] 57%|█████▋ | 6634/11728 [3:25:14<8:15:38, 5.84s/it] {'loss': 0.4725, 'learning_rate': 8.3669583391536e-06, 'epoch': 0.57} + 57%|█████▋ | 6634/11728 [3:25:14<8:15:38, 5.84s/it] 57%|█████▋ | 6635/11728 [3:25:19<8:16:42, 5.85s/it] {'loss': 0.4778, 'learning_rate': 8.364233876854848e-06, 'epoch': 0.57} + 57%|█████▋ | 6635/11728 [3:25:19<8:16:42, 5.85s/it] 57%|█████▋ | 6636/11728 [3:25:25<8:09:04, 5.76s/it] {'loss': 0.4553, 'learning_rate': 8.361509539306456e-06, 'epoch': 0.57} + 57%|█████▋ | 6636/11728 [3:25:25<8:09:04, 5.76s/it] 57%|█████▋ | 6637/11728 [3:25:31<8:16:10, 5.85s/it] {'loss': 0.4799, 'learning_rate': 8.358785326716184e-06, 'epoch': 0.57} + 57%|█████▋ | 6637/11728 [3:25:31<8:16:10, 5.85s/it] 57%|█████▋ | 6638/11728 [3:25:37<8:12:22, 5.80s/it] {'loss': 0.4733, 'learning_rate': 8.356061239291798e-06, 'epoch': 0.57} + 57%|█████▋ | 6638/11728 [3:25:37<8:12:22, 5.80s/it] 57%|█████▋ | 6639/11728 [3:25:43<8:18:51, 5.88s/it] {'loss': 0.4771, 'learning_rate': 8.35333727724104e-06, 'epoch': 0.57} + 57%|█████▋ | 6639/11728 [3:25:43<8:18:51, 5.88s/it] 57%|█████▋ | 6640/11728 [3:25:49<8:17:52, 5.87s/it] {'loss': 0.4629, 'learning_rate': 8.350613440771661e-06, 'epoch': 0.57} + 57%|█████▋ | 6640/11728 [3:25:49<8:17:52, 5.87s/it] 57%|█████▋ | 6641/11728 [3:25:55<8:20:46, 5.91s/it] {'loss': 0.4828, 'learning_rate': 8.347889730091384e-06, 'epoch': 0.57} + 57%|█████▋ | 6641/11728 [3:25:55<8:20:46, 5.91s/it] 57%|█████▋ | 6642/11728 [3:26:00<8:09:13, 5.77s/it] {'loss': 0.4619, 'learning_rate': 8.345166145407935e-06, 'epoch': 0.57} + 57%|█████▋ | 6642/11728 [3:26:00<8:09:13, 5.77s/it] 57%|█████▋ | 6643/11728 [3:26:06<8:06:21, 5.74s/it] {'loss': 0.4621, 'learning_rate': 8.342442686929024e-06, 'epoch': 0.57} + 57%|█████▋ | 6643/11728 [3:26:06<8:06:21, 5.74s/it] 57%|█████▋ | 6644/11728 [3:26:12<8:08:27, 5.76s/it] {'loss': 0.4995, 'learning_rate': 8.33971935486235e-06, 'epoch': 0.57} + 57%|█████▋ | 6644/11728 [3:26:12<8:08:27, 5.76s/it] 57%|█████▋ | 6645/11728 [3:26:17<8:08:39, 5.77s/it] {'loss': 0.4787, 'learning_rate': 8.336996149415616e-06, 'epoch': 0.57} + 57%|█████▋ | 6645/11728 [3:26:17<8:08:39, 5.77s/it] 57%|█████▋ | 6646/11728 [3:26:23<8:10:57, 5.80s/it] {'loss': 0.4826, 'learning_rate': 8.334273070796495e-06, 'epoch': 0.57} + 57%|█████▋ | 6646/11728 [3:26:23<8:10:57, 5.80s/it] 57%|█████▋ | 6647/11728 [3:26:29<8:07:23, 5.76s/it] {'loss': 0.4721, 'learning_rate': 8.331550119212665e-06, 'epoch': 0.57} + 57%|█████▋ | 6647/11728 [3:26:29<8:07:23, 5.76s/it] 57%|█████▋ | 6648/11728 [3:26:35<8:07:30, 5.76s/it] {'loss': 0.455, 'learning_rate': 8.328827294871786e-06, 'epoch': 0.57} + 57%|█████▋ | 6648/11728 [3:26:35<8:07:30, 5.76s/it] 57%|█████▋ | 6649/11728 [3:26:41<8:10:33, 5.80s/it] {'loss': 0.4669, 'learning_rate': 8.326104597981517e-06, 'epoch': 0.57} + 57%|█████▋ | 6649/11728 [3:26:41<8:10:33, 5.80s/it]2 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... +0 AutoResumeHook: Checking whether to suspend... + 57%|█████▋ | 6650/11728 [3:26:46<8:10:11, 5.79s/it] {'loss': 0.4655, 'learning_rate': 8.323382028749499e-06, 'epoch': 0.57} + 57%|█████▋ | 6650/11728 [3:26:46<8:10:11, 5.79s/it] 57%|█████▋ | 6651/11728 [3:26:52<8:13:21, 5.83s/it] {'loss': 0.4754, 'learning_rate': 8.320659587383369e-06, 'epoch': 0.57} + 57%|█████▋ | 6651/11728 [3:26:52<8:13:21, 5.83s/it] 57%|█████▋ | 6652/11728 [3:26:58<8:10:05, 5.79s/it] {'loss': 0.4737, 'learning_rate': 8.317937274090748e-06, 'epoch': 0.57} + 57%|█████▋ | 6652/11728 [3:26:58<8:10:05, 5.79s/it] 57%|█████▋ | 6653/11728 [3:27:04<8:15:44, 5.86s/it] {'loss': 0.4652, 'learning_rate': 8.315215089079249e-06, 'epoch': 0.57} + 57%|█████▋ | 6653/11728 [3:27:04<8:15:44, 5.86s/it] 57%|█████▋ | 6654/11728 [3:27:10<8:13:03, 5.83s/it] {'loss': 0.4893, 'learning_rate': 8.312493032556489e-06, 'epoch': 0.57} + 57%|█████▋ | 6654/11728 [3:27:10<8:13:03, 5.83s/it] 57%|█████▋ | 6655/11728 [3:27:16<8:20:16, 5.92s/it] {'loss': 0.4733, 'learning_rate': 8.309771104730049e-06, 'epoch': 0.57} + 57%|█████▋ | 6655/11728 [3:27:16<8:20:16, 5.92s/it] 57%|█████▋ | 6656/11728 [3:27:22<8:24:24, 5.97s/it] {'loss': 0.4832, 'learning_rate': 8.307049305807525e-06, 'epoch': 0.57} + 57%|█████▋ | 6656/11728 [3:27:22<8:24:24, 5.97s/it] 57%|█████▋ | 6657/11728 [3:27:27<8:12:32, 5.83s/it] {'loss': 0.4499, 'learning_rate': 8.304327635996486e-06, 'epoch': 0.57} + 57%|█████▋ | 6657/11728 [3:27:27<8:12:32, 5.83s/it] 57%|█████▋ | 6658/11728 [3:27:33<8:17:34, 5.89s/it] {'loss': 0.4876, 'learning_rate': 8.301606095504501e-06, 'epoch': 0.57} + 57%|█████▋ | 6658/11728 [3:27:33<8:17:34, 5.89s/it] 57%|█████▋ | 6659/11728 [3:27:40<8:23:29, 5.96s/it] {'loss': 0.4798, 'learning_rate': 8.298884684539128e-06, 'epoch': 0.57} + 57%|█████▋ | 6659/11728 [3:27:40<8:23:29, 5.96s/it] 57%|█████▋ | 6660/11728 [3:27:45<8:18:27, 5.90s/it] {'loss': 0.4653, 'learning_rate': 8.296163403307912e-06, 'epoch': 0.57} + 57%|█████▋ | 6660/11728 [3:27:45<8:18:27, 5.90s/it] 57%|█████▋ | 6661/11728 [3:27:51<8:19:16, 5.91s/it] {'loss': 0.4752, 'learning_rate': 8.293442252018384e-06, 'epoch': 0.57} + 57%|█████▋ | 6661/11728 [3:27:51<8:19:16, 5.91s/it] 57%|█████▋ | 6662/11728 [3:27:57<8:19:45, 5.92s/it] {'loss': 0.4627, 'learning_rate': 8.290721230878074e-06, 'epoch': 0.57} + 57%|█████▋ | 6662/11728 [3:27:57<8:19:45, 5.92s/it] 57%|█████▋ | 6663/11728 [3:28:03<8:11:21, 5.82s/it] {'loss': 0.4844, 'learning_rate': 8.288000340094502e-06, 'epoch': 0.57} + 57%|█████▋ | 6663/11728 [3:28:03<8:11:21, 5.82s/it] 57%|█████▋ | 6664/11728 [3:28:08<8:04:30, 5.74s/it] {'loss': 0.4664, 'learning_rate': 8.28527957987517e-06, 'epoch': 0.57} + 57%|█████▋ | 6664/11728 [3:28:08<8:04:30, 5.74s/it] 57%|█████▋ | 6665/11728 [3:28:14<7:59:02, 5.68s/it] {'loss': 0.484, 'learning_rate': 8.282558950427578e-06, 'epoch': 0.57} + 57%|█████▋ | 6665/11728 [3:28:14<7:59:02, 5.68s/it] 57%|█████▋ | 6666/11728 [3:28:20<7:58:29, 5.67s/it] {'loss': 0.4703, 'learning_rate': 8.279838451959209e-06, 'epoch': 0.57} + 57%|█████▋ | 6666/11728 [3:28:20<7:58:29, 5.67s/it] 57%|█████▋ | 6667/11728 [3:28:25<7:53:22, 5.61s/it] {'loss': 0.4982, 'learning_rate': 8.277118084677538e-06, 'epoch': 0.57} + 57%|█████▋ | 6667/11728 [3:28:25<7:53:22, 5.61s/it] 57%|█████▋ | 6668/11728 [3:28:31<8:04:45, 5.75s/it] {'loss': 0.4725, 'learning_rate': 8.274397848790041e-06, 'epoch': 0.57} + 57%|█████▋ | 6668/11728 [3:28:31<8:04:45, 5.75s/it] 57%|█████▋ | 6669/11728 [3:28:37<8:01:20, 5.71s/it] {'loss': 0.4418, 'learning_rate': 8.271677744504166e-06, 'epoch': 0.57} + 57%|█████▋ | 6669/11728 [3:28:37<8:01:20, 5.71s/it] 57%|█████▋ | 6670/11728 [3:28:43<8:04:11, 5.74s/it] {'loss': 0.4962, 'learning_rate': 8.26895777202736e-06, 'epoch': 0.57} + 57%|█████▋ | 6670/11728 [3:28:43<8:04:11, 5.74s/it] 57%|█████▋ | 6671/11728 [3:28:48<8:09:57, 5.81s/it] {'loss': 0.4764, 'learning_rate': 8.26623793156706e-06, 'epoch': 0.57} + 57%|█████▋ | 6671/11728 [3:28:48<8:09:57, 5.81s/it] 57%|█████▋ | 6672/11728 [3:28:54<8:07:08, 5.78s/it] {'loss': 0.465, 'learning_rate': 8.263518223330698e-06, 'epoch': 0.57} + 57%|█████▋ | 6672/11728 [3:28:54<8:07:08, 5.78s/it] 57%|█████▋ | 6673/11728 [3:29:00<8:05:57, 5.77s/it] {'loss': 0.4863, 'learning_rate': 8.260798647525684e-06, 'epoch': 0.57} + 57%|█████▋ | 6673/11728 [3:29:00<8:05:57, 5.77s/it] 57%|█████▋ | 6674/11728 [3:29:06<8:12:23, 5.85s/it] {'loss': 0.4664, 'learning_rate': 8.258079204359427e-06, 'epoch': 0.57} + 57%|█████▋ | 6674/11728 [3:29:06<8:12:23, 5.85s/it] 57%|█████▋ | 6675/11728 [3:29:12<8:10:15, 5.82s/it] {'loss': 0.4655, 'learning_rate': 8.255359894039319e-06, 'epoch': 0.57} + 57%|█████▋ | 6675/11728 [3:29:12<8:10:15, 5.82s/it] 57%|█████▋ | 6676/11728 [3:29:18<8:22:14, 5.96s/it] {'loss': 0.4635, 'learning_rate': 8.252640716772748e-06, 'epoch': 0.57} + 57%|█████▋ | 6676/11728 [3:29:18<8:22:14, 5.96s/it] 57%|█████▋ | 6677/11728 [3:29:24<8:19:11, 5.93s/it] {'loss': 0.4817, 'learning_rate': 8.249921672767095e-06, 'epoch': 0.57} + 57%|█████▋ | 6677/11728 [3:29:24<8:19:11, 5.93s/it] 57%|█████▋ | 6678/11728 [3:29:30<8:12:43, 5.85s/it] {'loss': 0.4589, 'learning_rate': 8.247202762229723e-06, 'epoch': 0.57} + 57%|█████▋ | 6678/11728 [3:29:30<8:12:43, 5.85s/it] 57%|█████▋ | 6679/11728 [3:29:36<8:15:30, 5.89s/it] {'loss': 0.4587, 'learning_rate': 8.244483985367984e-06, 'epoch': 0.57} + 57%|█████▋ | 6679/11728 [3:29:36<8:15:30, 5.89s/it] 57%|█████▋ | 6680/11728 [3:29:41<8:09:59, 5.82s/it] {'loss': 0.4611, 'learning_rate': 8.241765342389222e-06, 'epoch': 0.57} + 57%|█████▋ | 6680/11728 [3:29:41<8:09:59, 5.82s/it] 57%|█████▋ | 6681/11728 [3:29:47<8:08:03, 5.80s/it] {'loss': 0.4848, 'learning_rate': 8.239046833500779e-06, 'epoch': 0.57} + 57%|█████▋ | 6681/11728 [3:29:47<8:08:03, 5.80s/it] 57%|█████▋ | 6682/11728 [3:29:53<8:09:24, 5.82s/it] {'loss': 0.468, 'learning_rate': 8.236328458909975e-06, 'epoch': 0.57} + 57%|█████▋ | 6682/11728 [3:29:53<8:09:24, 5.82s/it] 57%|█████▋ | 6683/11728 [3:29:58<8:02:51, 5.74s/it] {'loss': 0.4642, 'learning_rate': 8.233610218824129e-06, 'epoch': 0.57} + 57%|█████▋ | 6683/11728 [3:29:58<8:02:51, 5.74s/it] 57%|█████▋ | 6684/11728 [3:30:04<8:01:35, 5.73s/it] {'loss': 0.4677, 'learning_rate': 8.23089211345054e-06, 'epoch': 0.57} + 57%|█████▋ | 6684/11728 [3:30:04<8:01:35, 5.73s/it] 57%|█████▋ | 6685/11728 [3:30:10<8:06:52, 5.79s/it] {'loss': 0.4519, 'learning_rate': 8.2281741429965e-06, 'epoch': 0.57} + 57%|█████▋ | 6685/11728 [3:30:10<8:06:52, 5.79s/it] 57%|█████▋ | 6686/11728 [3:30:16<8:06:09, 5.79s/it] {'loss': 0.4625, 'learning_rate': 8.225456307669301e-06, 'epoch': 0.57} + 57%|█████▋ | 6686/11728 [3:30:16<8:06:09, 5.79s/it] 57%|█████▋ | 6687/11728 [3:30:21<8:01:18, 5.73s/it] {'loss': 0.459, 'learning_rate': 8.222738607676214e-06, 'epoch': 0.57} + 57%|█████▋ | 6687/11728 [3:30:21<8:01:18, 5.73s/it] 57%|█████▋ | 6688/11728 [3:30:27<8:03:25, 5.76s/it] {'loss': 0.4463, 'learning_rate': 8.2200210432245e-06, 'epoch': 0.57} + 57%|█████▋ | 6688/11728 [3:30:27<8:03:25, 5.76s/it] 57%|█████▋ | 6689/11728 [3:30:33<8:01:17, 5.73s/it] {'loss': 0.4575, 'learning_rate': 8.217303614521412e-06, 'epoch': 0.57} + 57%|█████▋ | 6689/11728 [3:30:33<8:01:17, 5.73s/it] 57%|█████▋ | 6690/11728 [3:30:39<8:07:59, 5.81s/it] {'loss': 0.4783, 'learning_rate': 8.214586321774189e-06, 'epoch': 0.57} + 57%|█████▋ | 6690/11728 [3:30:39<8:07:59, 5.81s/it] 57%|█████▋ | 6691/11728 [3:30:45<8:12:43, 5.87s/it] {'loss': 0.5001, 'learning_rate': 8.21186916519007e-06, 'epoch': 0.57} + 57%|█████▋ | 6691/11728 [3:30:45<8:12:43, 5.87s/it] 57%|█████▋ | 6692/11728 [3:30:51<8:09:44, 5.83s/it] {'loss': 0.4659, 'learning_rate': 8.209152144976275e-06, 'epoch': 0.57} + 57%|█████▋ | 6692/11728 [3:30:51<8:09:44, 5.83s/it] 57%|█████▋ | 6693/11728 [3:30:56<8:01:07, 5.73s/it] {'loss': 0.4801, 'learning_rate': 8.206435261340014e-06, 'epoch': 0.57} + 57%|█████▋ | 6693/11728 [3:30:56<8:01:07, 5.73s/it] 57%|█████▋ | 6694/11728 [3:31:02<7:57:28, 5.69s/it] {'loss': 0.4836, 'learning_rate': 8.203718514488483e-06, 'epoch': 0.57} + 57%|█████▋ | 6694/11728 [3:31:02<7:57:28, 5.69s/it] 57%|█████▋ | 6695/11728 [3:31:08<8:05:08, 5.78s/it] {'loss': 0.4593, 'learning_rate': 8.201001904628883e-06, 'epoch': 0.57} + 57%|█████▋ | 6695/11728 [3:31:08<8:05:08, 5.78s/it] 57%|█████▋ | 6696/11728 [3:31:13<8:04:05, 5.77s/it] {'loss': 0.4809, 'learning_rate': 8.198285431968388e-06, 'epoch': 0.57} + 57%|█████▋ | 6696/11728 [3:31:13<8:04:05, 5.77s/it] 57%|█████▋ | 6697/11728 [3:31:19<8:03:03, 5.76s/it] {'loss': 0.4888, 'learning_rate': 8.195569096714166e-06, 'epoch': 0.57} + 57%|█████▋ | 6697/11728 [3:31:19<8:03:03, 5.76s/it] 57%|█████▋ | 6698/11728 [3:31:25<8:04:54, 5.78s/it] {'loss': 0.4812, 'learning_rate': 8.19285289907338e-06, 'epoch': 0.57} + 57%|█████▋ | 6698/11728 [3:31:25<8:04:54, 5.78s/it] 57%|█████▋ | 6699/11728 [3:31:31<8:07:22, 5.81s/it] {'loss': 0.4726, 'learning_rate': 8.190136839253171e-06, 'epoch': 0.57} + 57%|█████▋ | 6699/11728 [3:31:31<8:07:22, 5.81s/it]2 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +63 AutoResumeHook: Checking whether to suspend...AutoResumeHook: Checking whether to suspend... + +5 AutoResumeHook: Checking whether to suspend... +0 AutoResumeHook: Checking whether to suspend... + 57%|█████▋ | 6700/11728 [3:31:37<8:05:12, 5.79s/it] {'loss': 0.4823, 'learning_rate': 8.187420917460686e-06, 'epoch': 0.57} + 57%|█████▋ | 6700/11728 [3:31:37<8:05:12, 5.79s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-6700/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-6700/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-6700/mm_projector +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/torch/nn/modules/module.py:1802: UserWarning: Positional args are being deprecated, use kwargs instead. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details. + warnings.warn( + 57%|█████▋ | 6701/11728 [3:32:08<19:00:18, 13.61s/it] {'loss': 0.4685, 'learning_rate': 8.184705133903053e-06, 'epoch': 0.57} + 57%|█████▋ | 6701/11728 [3:32:09<19:00:18, 13.61s/it] 57%|█████▋ | 6702/11728 [3:32:14<15:44:05, 11.27s/it] {'loss': 0.4827, 'learning_rate': 8.181989488787381e-06, 'epoch': 0.57} + 57%|█████▋ | 6702/11728 [3:32:14<15:44:05, 11.27s/it] 57%|█████▋ | 6703/11728 [3:32:20<13:24:36, 9.61s/it] {'loss': 0.4712, 'learning_rate': 8.179273982320778e-06, 'epoch': 0.57} + 57%|█████▋ | 6703/11728 [3:32:20<13:24:36, 9.61s/it] 57%|█████▋ | 6704/11728 [3:32:26<11:47:38, 8.45s/it] {'loss': 0.4858, 'learning_rate': 8.176558614710347e-06, 'epoch': 0.57} + 57%|█████▋ | 6704/11728 [3:32:26<11:47:38, 8.45s/it] 57%|█████▋ | 6705/11728 [3:32:32<10:47:46, 7.74s/it] {'loss': 0.4487, 'learning_rate': 8.17384338616317e-06, 'epoch': 0.57} + 57%|█████▋ | 6705/11728 [3:32:32<10:47:46, 7.74s/it] 57%|█████▋ | 6706/11728 [3:32:38<9:56:09, 7.12s/it] {'loss': 0.4683, 'learning_rate': 8.171128296886316e-06, 'epoch': 0.57} + 57%|█████▋ | 6706/11728 [3:32:38<9:56:09, 7.12s/it] 57%|█████▋ | 6707/11728 [3:32:43<9:16:54, 6.65s/it] {'loss': 0.4842, 'learning_rate': 8.168413347086856e-06, 'epoch': 0.57} + 57%|█████▋ | 6707/11728 [3:32:43<9:16:54, 6.65s/it] 57%|█████▋ | 6708/11728 [3:32:49<8:57:52, 6.43s/it] {'loss': 0.4556, 'learning_rate': 8.165698536971838e-06, 'epoch': 0.57} + 57%|█████▋ | 6708/11728 [3:32:49<8:57:52, 6.43s/it] 57%|█████▋ | 6709/11728 [3:32:55<8:41:03, 6.23s/it] {'loss': 0.475, 'learning_rate': 8.162983866748308e-06, 'epoch': 0.57} + 57%|█████▋ | 6709/11728 [3:32:55<8:41:03, 6.23s/it] 57%|█████▋ | 6710/11728 [3:33:01<8:28:34, 6.08s/it] {'loss': 0.4587, 'learning_rate': 8.160269336623301e-06, 'epoch': 0.57} + 57%|█████▋ | 6710/11728 [3:33:01<8:28:34, 6.08s/it] 57%|█████▋ | 6711/11728 [3:33:06<8:18:33, 5.96s/it] {'loss': 0.4697, 'learning_rate': 8.157554946803832e-06, 'epoch': 0.57} + 57%|█████▋ | 6711/11728 [3:33:06<8:18:33, 5.96s/it] 57%|█████▋ | 6712/11728 [3:33:12<8:09:38, 5.86s/it] {'loss': 0.4658, 'learning_rate': 8.154840697496917e-06, 'epoch': 0.57} + 57%|█████▋ | 6712/11728 [3:33:12<8:09:38, 5.86s/it] 57%|█████▋ | 6713/11728 [3:33:18<8:16:23, 5.94s/it] {'loss': 0.4598, 'learning_rate': 8.15212658890955e-06, 'epoch': 0.57} + 57%|█████▋ | 6713/11728 [3:33:18<8:16:23, 5.94s/it] 57%|█████▋ | 6714/11728 [3:33:24<8:15:21, 5.93s/it] {'loss': 0.4801, 'learning_rate': 8.149412621248729e-06, 'epoch': 0.57} + 57%|█████▋ | 6714/11728 [3:33:24<8:15:21, 5.93s/it] 57%|█████▋ | 6715/11728 [3:33:29<8:07:52, 5.84s/it] {'loss': 0.4554, 'learning_rate': 8.146698794721423e-06, 'epoch': 0.57} + 57%|█████▋ | 6715/11728 [3:33:29<8:07:52, 5.84s/it] 57%|█████▋ | 6716/11728 [3:33:35<8:09:33, 5.86s/it] {'loss': 0.4661, 'learning_rate': 8.143985109534609e-06, 'epoch': 0.57} + 57%|█████▋ | 6716/11728 [3:33:35<8:09:33, 5.86s/it] 57%|█████▋ | 6717/11728 [3:33:41<8:10:17, 5.87s/it] {'loss': 0.4831, 'learning_rate': 8.141271565895233e-06, 'epoch': 0.57} + 57%|█████▋ | 6717/11728 [3:33:41<8:10:17, 5.87s/it] 57%|█████▋ | 6718/11728 [3:33:47<8:10:26, 5.87s/it] {'loss': 0.4628, 'learning_rate': 8.138558164010251e-06, 'epoch': 0.57} + 57%|█████▋ | 6718/11728 [3:33:47<8:10:26, 5.87s/it] 57%|█████▋ | 6719/11728 [3:33:53<8:13:24, 5.91s/it] {'loss': 0.4667, 'learning_rate': 8.135844904086596e-06, 'epoch': 0.57} + 57%|█████▋ | 6719/11728 [3:33:53<8:13:24, 5.91s/it] 57%|█████▋ | 6720/11728 [3:33:59<8:11:01, 5.88s/it] {'loss': 0.4647, 'learning_rate': 8.133131786331188e-06, 'epoch': 0.57} + 57%|█████▋ | 6720/11728 [3:33:59<8:11:01, 5.88s/it] 57%|█████▋ | 6721/11728 [3:34:05<8:13:49, 5.92s/it] {'loss': 0.4694, 'learning_rate': 8.130418810950948e-06, 'epoch': 0.57} + 57%|█████▋ | 6721/11728 [3:34:05<8:13:49, 5.92s/it] 57%|█████▋ | 6722/11728 [3:34:11<8:13:35, 5.92s/it] {'loss': 0.4775, 'learning_rate': 8.127705978152769e-06, 'epoch': 0.57} + 57%|█████▋ | 6722/11728 [3:34:11<8:13:35, 5.92s/it] 57%|█████▋ | 6723/11728 [3:34:17<8:06:08, 5.83s/it] {'loss': 0.4702, 'learning_rate': 8.124993288143553e-06, 'epoch': 0.57} + 57%|█████▋ | 6723/11728 [3:34:17<8:06:08, 5.83s/it] 57%|█████▋ | 6724/11728 [3:34:22<8:09:01, 5.86s/it] {'loss': 0.4506, 'learning_rate': 8.122280741130177e-06, 'epoch': 0.57} + 57%|█████▋ | 6724/11728 [3:34:22<8:09:01, 5.86s/it] 57%|█████▋ | 6725/11728 [3:34:28<8:05:43, 5.83s/it] {'loss': 0.4709, 'learning_rate': 8.11956833731951e-06, 'epoch': 0.57} + 57%|█████▋ | 6725/11728 [3:34:28<8:05:43, 5.83s/it] 57%|█████▋ | 6726/11728 [3:34:34<8:02:00, 5.78s/it] {'loss': 0.4546, 'learning_rate': 8.11685607691841e-06, 'epoch': 0.57} + 57%|█████▋ | 6726/11728 [3:34:34<8:02:00, 5.78s/it] 57%|█████▋ | 6727/11728 [3:34:40<8:01:50, 5.78s/it] {'loss': 0.4746, 'learning_rate': 8.114143960133728e-06, 'epoch': 0.57} + 57%|█████▋ | 6727/11728 [3:34:40<8:01:50, 5.78s/it] 57%|█████▋ | 6728/11728 [3:34:45<7:59:50, 5.76s/it] {'loss': 0.4603, 'learning_rate': 8.111431987172303e-06, 'epoch': 0.57} + 57%|█████▋ | 6728/11728 [3:34:45<7:59:50, 5.76s/it] 57%|█████▋ | 6729/11728 [3:34:51<7:58:59, 5.75s/it] {'loss': 0.4722, 'learning_rate': 8.10872015824096e-06, 'epoch': 0.57} + 57%|█████▋ | 6729/11728 [3:34:51<7:58:59, 5.75s/it] 57%|█████▋ | 6730/11728 [3:34:57<7:52:31, 5.67s/it] {'loss': 0.4658, 'learning_rate': 8.106008473546512e-06, 'epoch': 0.57} + 57%|█████▋ | 6730/11728 [3:34:57<7:52:31, 5.67s/it] 57%|█████▋ | 6731/11728 [3:35:02<7:57:18, 5.73s/it] {'loss': 0.4835, 'learning_rate': 8.103296933295762e-06, 'epoch': 0.57} + 57%|█████▋ | 6731/11728 [3:35:02<7:57:18, 5.73s/it] 57%|█████▋ | 6732/11728 [3:35:08<7:51:22, 5.66s/it] {'loss': 0.4863, 'learning_rate': 8.10058553769551e-06, 'epoch': 0.57} + 57%|█████▋ | 6732/11728 [3:35:08<7:51:22, 5.66s/it] 57%|█████▋ | 6733/11728 [3:35:14<7:54:36, 5.70s/it] {'loss': 0.4719, 'learning_rate': 8.097874286952534e-06, 'epoch': 0.57} + 57%|█████▋ | 6733/11728 [3:35:14<7:54:36, 5.70s/it] 57%|█████▋ | 6734/11728 [3:35:19<7:55:32, 5.71s/it] {'loss': 0.4696, 'learning_rate': 8.095163181273608e-06, 'epoch': 0.57} + 57%|█████▋ | 6734/11728 [3:35:19<7:55:32, 5.71s/it] 57%|█████▋ | 6735/11728 [3:35:25<7:55:55, 5.72s/it] {'loss': 0.474, 'learning_rate': 8.092452220865485e-06, 'epoch': 0.57} + 57%|█████▋ | 6735/11728 [3:35:25<7:55:55, 5.72s/it] 57%|█████▋ | 6736/11728 [3:35:31<7:55:54, 5.72s/it] {'loss': 0.4813, 'learning_rate': 8.089741405934923e-06, 'epoch': 0.57} + 57%|█████▋ | 6736/11728 [3:35:31<7:55:54, 5.72s/it] 57%|█████▋ | 6737/11728 [3:35:37<7:56:06, 5.72s/it] {'loss': 0.4816, 'learning_rate': 8.087030736688657e-06, 'epoch': 0.57} + 57%|█████▋ | 6737/11728 [3:35:37<7:56:06, 5.72s/it] 57%|█████▋ | 6738/11728 [3:35:43<8:01:19, 5.79s/it] {'loss': 0.484, 'learning_rate': 8.084320213333413e-06, 'epoch': 0.57} + 57%|█████▋ | 6738/11728 [3:35:43<8:01:19, 5.79s/it] 57%|█████▋ | 6739/11728 [3:35:48<8:01:30, 5.79s/it] {'loss': 0.4835, 'learning_rate': 8.081609836075907e-06, 'epoch': 0.57} + 57%|█████▋ | 6739/11728 [3:35:48<8:01:30, 5.79s/it] 57%|█████▋ | 6740/11728 [3:35:54<8:00:30, 5.78s/it] {'loss': 0.4424, 'learning_rate': 8.07889960512284e-06, 'epoch': 0.57} + 57%|█████▋ | 6740/11728 [3:35:54<8:00:30, 5.78s/it] 57%|█████▋ | 6741/11728 [3:36:00<8:00:34, 5.78s/it] {'loss': 0.4822, 'learning_rate': 8.076189520680914e-06, 'epoch': 0.57} + 57%|█████▋ | 6741/11728 [3:36:00<8:00:34, 5.78s/it] 57%|█████▋ | 6742/11728 [3:36:06<8:05:24, 5.84s/it] {'loss': 0.4743, 'learning_rate': 8.073479582956806e-06, 'epoch': 0.57} + 57%|█████▋ | 6742/11728 [3:36:06<8:05:24, 5.84s/it] 57%|█████▋ | 6743/11728 [3:36:12<8:08:34, 5.88s/it] {'loss': 0.4684, 'learning_rate': 8.070769792157192e-06, 'epoch': 0.57} + 57%|█████▋ | 6743/11728 [3:36:12<8:08:34, 5.88s/it] 58%|█████▊ | 6744/11728 [3:36:18<8:04:51, 5.84s/it] {'loss': 0.4763, 'learning_rate': 8.068060148488722e-06, 'epoch': 0.58} + 58%|█████▊ | 6744/11728 [3:36:18<8:04:51, 5.84s/it] 58%|█████▊ | 6745/11728 [3:36:23<7:56:22, 5.74s/it] {'loss': 0.4825, 'learning_rate': 8.065350652158051e-06, 'epoch': 0.58} + 58%|█████▊ | 6745/11728 [3:36:23<7:56:22, 5.74s/it] 58%|█████▊ | 6746/11728 [3:36:29<7:58:54, 5.77s/it] {'loss': 0.4745, 'learning_rate': 8.062641303371818e-06, 'epoch': 0.58} + 58%|█████▊ | 6746/11728 [3:36:29<7:58:54, 5.77s/it] 58%|█████▊ | 6747/11728 [3:36:35<7:55:22, 5.73s/it] {'loss': 0.4657, 'learning_rate': 8.059932102336647e-06, 'epoch': 0.58} + 58%|█████▊ | 6747/11728 [3:36:35<7:55:22, 5.73s/it] 58%|█████▊ | 6748/11728 [3:36:40<7:59:03, 5.77s/it] {'loss': 0.4838, 'learning_rate': 8.057223049259155e-06, 'epoch': 0.58} + 58%|█████▊ | 6748/11728 [3:36:40<7:59:03, 5.77s/it] 58%|█████▊ | 6749/11728 [3:36:46<7:55:03, 5.72s/it] {'loss': 0.4686, 'learning_rate': 8.054514144345941e-06, 'epoch': 0.58} + 58%|█████▊ | 6749/11728 [3:36:46<7:55:03, 5.72s/it]2 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend...5 + AutoResumeHook: Checking whether to suspend... +01 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... + 58%|█████▊ | 6750/11728 [3:36:52<8:03:42, 5.83s/it] {'loss': 0.4882, 'learning_rate': 8.051805387803601e-06, 'epoch': 0.58} + 58%|█████▊ | 6750/11728 [3:36:52<8:03:42, 5.83s/it] 58%|█████▊ | 6751/11728 [3:36:58<8:00:47, 5.80s/it] {'loss': 0.469, 'learning_rate': 8.04909677983872e-06, 'epoch': 0.58} + 58%|█████▊ | 6751/11728 [3:36:58<8:00:47, 5.80s/it] 58%|█████▊ | 6752/11728 [3:37:03<7:55:47, 5.74s/it] {'loss': 0.4728, 'learning_rate': 8.046388320657861e-06, 'epoch': 0.58} + 58%|█████▊ | 6752/11728 [3:37:03<7:55:47, 5.74s/it] 58%|█████▊ | 6753/11728 [3:37:09<7:53:24, 5.71s/it] {'loss': 0.451, 'learning_rate': 8.043680010467583e-06, 'epoch': 0.58} + 58%|█████▊ | 6753/11728 [3:37:09<7:53:24, 5.71s/it] 58%|█████▊ | 6754/11728 [3:37:15<7:47:47, 5.64s/it] {'loss': 0.4723, 'learning_rate': 8.040971849474432e-06, 'epoch': 0.58} + 58%|█████▊ | 6754/11728 [3:37:15<7:47:47, 5.64s/it] 58%|█████▊ | 6755/11728 [3:37:20<7:53:31, 5.71s/it] {'loss': 0.4777, 'learning_rate': 8.038263837884952e-06, 'epoch': 0.58} + 58%|█████▊ | 6755/11728 [3:37:20<7:53:31, 5.71s/it] 58%|█████▊ | 6756/11728 [3:37:26<7:47:38, 5.64s/it] {'loss': 0.4435, 'learning_rate': 8.03555597590566e-06, 'epoch': 0.58} + 58%|█████▊ | 6756/11728 [3:37:26<7:47:38, 5.64s/it] 58%|█████▊ | 6757/11728 [3:37:32<7:50:26, 5.68s/it] {'loss': 0.4769, 'learning_rate': 8.032848263743071e-06, 'epoch': 0.58} + 58%|█████▊ | 6757/11728 [3:37:32<7:50:26, 5.68s/it] 58%|█████▊ | 6758/11728 [3:37:37<7:50:03, 5.67s/it] {'loss': 0.4685, 'learning_rate': 8.030140701603684e-06, 'epoch': 0.58} + 58%|█████▊ | 6758/11728 [3:37:37<7:50:03, 5.67s/it] 58%|█████▊ | 6759/11728 [3:37:43<7:49:19, 5.67s/it] {'loss': 0.4958, 'learning_rate': 8.027433289693991e-06, 'epoch': 0.58} + 58%|█████▊ | 6759/11728 [3:37:43<7:49:19, 5.67s/it] 58%|█████▊ | 6760/11728 [3:37:49<7:47:08, 5.64s/it] {'loss': 0.4782, 'learning_rate': 8.024726028220474e-06, 'epoch': 0.58} + 58%|█████▊ | 6760/11728 [3:37:49<7:47:08, 5.64s/it] 58%|█████▊ | 6761/11728 [3:37:55<8:00:25, 5.80s/it] {'loss': 0.4655, 'learning_rate': 8.022018917389597e-06, 'epoch': 0.58} + 58%|█████▊ | 6761/11728 [3:37:55<8:00:25, 5.80s/it] 58%|█████▊ | 6762/11728 [3:38:00<7:52:41, 5.71s/it] {'loss': 0.4731, 'learning_rate': 8.019311957407811e-06, 'epoch': 0.58} + 58%|█████▊ | 6762/11728 [3:38:00<7:52:41, 5.71s/it] 58%|█████▊ | 6763/11728 [3:38:06<7:49:54, 5.68s/it] {'loss': 0.4586, 'learning_rate': 8.016605148481565e-06, 'epoch': 0.58} + 58%|█████▊ | 6763/11728 [3:38:06<7:49:54, 5.68s/it] 58%|█████▊ | 6764/11728 [3:38:12<7:49:47, 5.68s/it] {'loss': 0.4829, 'learning_rate': 8.013898490817293e-06, 'epoch': 0.58} + 58%|█████▊ | 6764/11728 [3:38:12<7:49:47, 5.68s/it] 58%|█████▊ | 6765/11728 [3:38:18<7:55:50, 5.75s/it] {'loss': 0.4623, 'learning_rate': 8.011191984621412e-06, 'epoch': 0.58} + 58%|█████▊ | 6765/11728 [3:38:18<7:55:50, 5.75s/it] 58%|█████▊ | 6766/11728 [3:38:23<7:49:32, 5.68s/it] {'loss': 0.4632, 'learning_rate': 8.008485630100336e-06, 'epoch': 0.58} + 58%|█████▊ | 6766/11728 [3:38:23<7:49:32, 5.68s/it] 58%|█████▊ | 6767/11728 [3:38:29<7:49:36, 5.68s/it] {'loss': 0.4899, 'learning_rate': 8.005779427460457e-06, 'epoch': 0.58} + 58%|█████▊ | 6767/11728 [3:38:29<7:49:36, 5.68s/it] 58%|█████▊ | 6768/11728 [3:38:35<7:59:53, 5.81s/it] {'loss': 0.4757, 'learning_rate': 8.003073376908163e-06, 'epoch': 0.58} + 58%|█████▊ | 6768/11728 [3:38:35<7:59:53, 5.81s/it] 58%|█████▊ | 6769/11728 [3:38:40<7:54:50, 5.75s/it] {'loss': 0.4571, 'learning_rate': 8.000367478649835e-06, 'epoch': 0.58} + 58%|█████▊ | 6769/11728 [3:38:40<7:54:50, 5.75s/it] 58%|█████▊ | 6770/11728 [3:38:46<7:55:12, 5.75s/it] {'loss': 0.4623, 'learning_rate': 7.99766173289183e-06, 'epoch': 0.58} + 58%|█████▊ | 6770/11728 [3:38:46<7:55:12, 5.75s/it] 58%|█████▊ | 6771/11728 [3:38:52<7:47:40, 5.66s/it] {'loss': 0.4867, 'learning_rate': 7.9949561398405e-06, 'epoch': 0.58} + 58%|█████▊ | 6771/11728 [3:38:52<7:47:40, 5.66s/it] 58%|█████▊ | 6772/11728 [3:38:57<7:50:13, 5.69s/it] {'loss': 0.4527, 'learning_rate': 7.992250699702182e-06, 'epoch': 0.58} + 58%|█████▊ | 6772/11728 [3:38:57<7:50:13, 5.69s/it] 58%|█████▊ | 6773/11728 [3:39:03<7:55:48, 5.76s/it] {'loss': 0.4685, 'learning_rate': 7.989545412683214e-06, 'epoch': 0.58} + 58%|█████▊ | 6773/11728 [3:39:03<7:55:48, 5.76s/it] 58%|█████▊ | 6774/11728 [3:39:09<7:55:12, 5.76s/it] {'loss': 0.4848, 'learning_rate': 7.986840278989902e-06, 'epoch': 0.58} + 58%|█████▊ | 6774/11728 [3:39:09<7:55:12, 5.76s/it] 58%|█████▊ | 6775/11728 [3:39:15<8:05:19, 5.88s/it] {'loss': 0.4639, 'learning_rate': 7.98413529882856e-06, 'epoch': 0.58} + 58%|█████▊ | 6775/11728 [3:39:15<8:05:19, 5.88s/it] 58%|█████▊ | 6776/11728 [3:39:21<7:56:08, 5.77s/it] {'loss': 0.4662, 'learning_rate': 7.98143047240547e-06, 'epoch': 0.58} + 58%|█████▊ | 6776/11728 [3:39:21<7:56:08, 5.77s/it] 58%|█████▊ | 6777/11728 [3:39:26<7:53:26, 5.74s/it] {'loss': 0.458, 'learning_rate': 7.97872579992692e-06, 'epoch': 0.58} + 58%|█████▊ | 6777/11728 [3:39:26<7:53:26, 5.74s/it] 58%|█████▊ | 6778/11728 [3:39:32<7:52:45, 5.73s/it] {'loss': 0.4792, 'learning_rate': 7.976021281599182e-06, 'epoch': 0.58} + 58%|█████▊ | 6778/11728 [3:39:32<7:52:45, 5.73s/it] 58%|█████▊ | 6779/11728 [3:39:38<7:52:45, 5.73s/it] {'loss': 0.4432, 'learning_rate': 7.973316917628513e-06, 'epoch': 0.58} + 58%|█████▊ | 6779/11728 [3:39:38<7:52:45, 5.73s/it] 58%|█████▊ | 6780/11728 [3:39:43<7:48:31, 5.68s/it] {'loss': 0.4887, 'learning_rate': 7.970612708221153e-06, 'epoch': 0.58} + 58%|█████▊ | 6780/11728 [3:39:43<7:48:31, 5.68s/it] 58%|█████▊ | 6781/11728 [3:39:49<7:46:36, 5.66s/it] {'loss': 0.4733, 'learning_rate': 7.967908653583338e-06, 'epoch': 0.58} + 58%|█████▊ | 6781/11728 [3:39:49<7:46:36, 5.66s/it] 58%|█████▊ | 6782/11728 [3:39:55<7:58:07, 5.80s/it] {'loss': 0.4818, 'learning_rate': 7.9652047539213e-06, 'epoch': 0.58} + 58%|█████▊ | 6782/11728 [3:39:55<7:58:07, 5.80s/it] 58%|█████▊ | 6783/11728 [3:40:01<8:03:17, 5.86s/it] {'loss': 0.4753, 'learning_rate': 7.962501009441236e-06, 'epoch': 0.58} + 58%|█████▊ | 6783/11728 [3:40:01<8:03:17, 5.86s/it] 58%|█████▊ | 6784/11728 [3:40:07<7:56:17, 5.78s/it] {'loss': 0.447, 'learning_rate': 7.959797420349356e-06, 'epoch': 0.58} + 58%|█████▊ | 6784/11728 [3:40:07<7:56:17, 5.78s/it] 58%|█████▊ | 6785/11728 [3:40:12<7:51:54, 5.73s/it] {'loss': 0.469, 'learning_rate': 7.957093986851839e-06, 'epoch': 0.58} + 58%|█████▊ | 6785/11728 [3:40:12<7:51:54, 5.73s/it] 58%|█████▊ | 6786/11728 [3:40:18<7:51:34, 5.73s/it] {'loss': 0.4612, 'learning_rate': 7.954390709154863e-06, 'epoch': 0.58} + 58%|█████▊ | 6786/11728 [3:40:18<7:51:34, 5.73s/it] 58%|█████▊ | 6787/11728 [3:40:24<7:52:39, 5.74s/it] {'loss': 0.4786, 'learning_rate': 7.951687587464595e-06, 'epoch': 0.58} + 58%|█████▊ | 6787/11728 [3:40:24<7:52:39, 5.74s/it] 58%|█████▊ | 6788/11728 [3:40:30<7:51:22, 5.73s/it] {'loss': 0.4595, 'learning_rate': 7.94898462198718e-06, 'epoch': 0.58} + 58%|█████▊ | 6788/11728 [3:40:30<7:51:22, 5.73s/it] 58%|█████▊ | 6789/11728 [3:40:35<7:52:46, 5.74s/it] {'loss': 0.4718, 'learning_rate': 7.946281812928763e-06, 'epoch': 0.58} + 58%|█████▊ | 6789/11728 [3:40:35<7:52:46, 5.74s/it] 58%|█████▊ | 6790/11728 [3:40:41<7:52:53, 5.75s/it] {'loss': 0.4945, 'learning_rate': 7.943579160495466e-06, 'epoch': 0.58} + 58%|█████▊ | 6790/11728 [3:40:41<7:52:53, 5.75s/it] 58%|█████▊ | 6791/11728 [3:40:47<7:53:47, 5.76s/it] {'loss': 0.4822, 'learning_rate': 7.940876664893411e-06, 'epoch': 0.58} + 58%|█████▊ | 6791/11728 [3:40:47<7:53:47, 5.76s/it] 58%|█████▊ | 6792/11728 [3:40:53<7:55:53, 5.78s/it] {'loss': 0.4711, 'learning_rate': 7.938174326328696e-06, 'epoch': 0.58} + 58%|█████▊ | 6792/11728 [3:40:53<7:55:53, 5.78s/it] 58%|█████▊ | 6793/11728 [3:40:58<7:50:07, 5.72s/it] {'loss': 0.4786, 'learning_rate': 7.935472145007416e-06, 'epoch': 0.58} + 58%|█████▊ | 6793/11728 [3:40:58<7:50:07, 5.72s/it] 58%|█████▊ | 6794/11728 [3:41:04<7:49:47, 5.71s/it] {'loss': 0.4609, 'learning_rate': 7.932770121135648e-06, 'epoch': 0.58} + 58%|█████▊ | 6794/11728 [3:41:04<7:49:47, 5.71s/it] 58%|█████▊ | 6795/11728 [3:41:10<7:58:25, 5.82s/it] {'loss': 0.4843, 'learning_rate': 7.93006825491946e-06, 'epoch': 0.58} + 58%|█████▊ | 6795/11728 [3:41:10<7:58:25, 5.82s/it] 58%|█████▊ | 6796/11728 [3:41:16<8:02:32, 5.87s/it] {'loss': 0.481, 'learning_rate': 7.927366546564911e-06, 'epoch': 0.58} + 58%|█████▊ | 6796/11728 [3:41:16<8:02:32, 5.87s/it] 58%|█████▊ | 6797/11728 [3:41:22<8:04:47, 5.90s/it] {'loss': 0.4788, 'learning_rate': 7.92466499627804e-06, 'epoch': 0.58} + 58%|█████▊ | 6797/11728 [3:41:22<8:04:47, 5.90s/it] 58%|█████▊ | 6798/11728 [3:41:28<7:57:11, 5.81s/it] {'loss': 0.4863, 'learning_rate': 7.921963604264884e-06, 'epoch': 0.58} + 58%|█████▊ | 6798/11728 [3:41:28<7:57:11, 5.81s/it] 58%|█████▊ | 6799/11728 [3:41:33<7:56:26, 5.80s/it] {'loss': 0.4495, 'learning_rate': 7.919262370731459e-06, 'epoch': 0.58} + 58%|█████▊ | 6799/11728 [3:41:33<7:56:26, 5.80s/it]2 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... +0 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... + 58%|█████▊ | 6800/11728 [3:41:39<7:56:12, 5.80s/it] {'loss': 0.4726, 'learning_rate': 7.916561295883767e-06, 'epoch': 0.58} + 58%|█████▊ | 6800/11728 [3:41:39<7:56:12, 5.80s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-6800/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-6800/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-6800/mm_projector +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/torch/nn/modules/module.py:1802: UserWarning: Positional args are being deprecated, use kwargs instead. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details. + warnings.warn( + 58%|█████▊ | 6801/11728 [3:42:12<19:06:42, 13.96s/it] {'loss': 0.4844, 'learning_rate': 7.913860379927812e-06, 'epoch': 0.58} + 58%|█████▊ | 6801/11728 [3:42:12<19:06:42, 13.96s/it] 58%|█████▊ | 6802/11728 [3:42:18<15:45:11, 11.51s/it] {'loss': 0.4869, 'learning_rate': 7.911159623069575e-06, 'epoch': 0.58} + 58%|█████▊ | 6802/11728 [3:42:18<15:45:11, 11.51s/it] 58%|█████▊ | 6803/11728 [3:42:24<13:24:42, 9.80s/it] {'loss': 0.479, 'learning_rate': 7.908459025515024e-06, 'epoch': 0.58} + 58%|█████▊ | 6803/11728 [3:42:24<13:24:42, 9.80s/it] 58%|█████▊ | 6804/11728 [3:42:30<11:44:55, 8.59s/it] {'loss': 0.461, 'learning_rate': 7.905758587470119e-06, 'epoch': 0.58} + 58%|█████▊ | 6804/11728 [3:42:30<11:44:55, 8.59s/it] 58%|█████▊ | 6805/11728 [3:42:35<10:28:29, 7.66s/it] {'loss': 0.4597, 'learning_rate': 7.903058309140809e-06, 'epoch': 0.58} + 58%|█████▊ | 6805/11728 [3:42:35<10:28:29, 7.66s/it] 58%|█████▊ | 6806/11728 [3:42:41<9:38:27, 7.05s/it] {'loss': 0.4672, 'learning_rate': 7.900358190733026e-06, 'epoch': 0.58} + 58%|█████▊ | 6806/11728 [3:42:41<9:38:27, 7.05s/it] 58%|█████▊ | 6807/11728 [3:42:47<9:12:31, 6.74s/it] {'loss': 0.4806, 'learning_rate': 7.897658232452696e-06, 'epoch': 0.58} + 58%|█████▊ | 6807/11728 [3:42:47<9:12:31, 6.74s/it] 58%|█████▊ | 6808/11728 [3:42:52<8:49:52, 6.46s/it] {'loss': 0.4619, 'learning_rate': 7.894958434505725e-06, 'epoch': 0.58} + 58%|█████▊ | 6808/11728 [3:42:52<8:49:52, 6.46s/it] 58%|█████▊ | 6809/11728 [3:42:58<8:29:37, 6.22s/it] {'loss': 0.4651, 'learning_rate': 7.892258797098008e-06, 'epoch': 0.58} + 58%|█████▊ | 6809/11728 [3:42:58<8:29:37, 6.22s/it] 58%|█████▊ | 6810/11728 [3:43:04<8:21:51, 6.12s/it] {'loss': 0.4695, 'learning_rate': 7.889559320435436e-06, 'epoch': 0.58} + 58%|█████▊ | 6810/11728 [3:43:04<8:21:51, 6.12s/it] 58%|█████▊ | 6811/11728 [3:43:10<8:18:50, 6.09s/it] {'loss': 0.4835, 'learning_rate': 7.886860004723885e-06, 'epoch': 0.58} + 58%|█████▊ | 6811/11728 [3:43:10<8:18:50, 6.09s/it] 58%|█████▊ | 6812/11728 [3:43:16<8:10:00, 5.98s/it] {'loss': 0.4721, 'learning_rate': 7.884160850169209e-06, 'epoch': 0.58} + 58%|█████▊ | 6812/11728 [3:43:16<8:10:00, 5.98s/it] 58%|█████▊ | 6813/11728 [3:43:22<8:05:21, 5.92s/it] {'loss': 0.4731, 'learning_rate': 7.881461856977259e-06, 'epoch': 0.58} + 58%|█████▊ | 6813/11728 [3:43:22<8:05:21, 5.92s/it] 58%|█████▊ | 6814/11728 [3:43:27<7:53:59, 5.79s/it] {'loss': 0.495, 'learning_rate': 7.878763025353875e-06, 'epoch': 0.58} + 58%|█████▊ | 6814/11728 [3:43:27<7:53:59, 5.79s/it] 58%|█████▊ | 6815/11728 [3:43:33<7:56:29, 5.82s/it] {'loss': 0.4709, 'learning_rate': 7.876064355504877e-06, 'epoch': 0.58} + 58%|█████▊ | 6815/11728 [3:43:33<7:56:29, 5.82s/it] 58%|█████▊ | 6816/11728 [3:43:39<7:53:12, 5.78s/it] {'loss': 0.46, 'learning_rate': 7.873365847636081e-06, 'epoch': 0.58} + 58%|█████▊ | 6816/11728 [3:43:39<7:53:12, 5.78s/it] 58%|█████▊ | 6817/11728 [3:43:44<7:49:27, 5.74s/it] {'loss': 0.4856, 'learning_rate': 7.870667501953284e-06, 'epoch': 0.58} + 58%|█████▊ | 6817/11728 [3:43:44<7:49:27, 5.74s/it] 58%|█████▊ | 6818/11728 [3:43:50<7:49:07, 5.73s/it] {'loss': 0.4658, 'learning_rate': 7.867969318662267e-06, 'epoch': 0.58} + 58%|█████▊ | 6818/11728 [3:43:50<7:49:07, 5.73s/it] 58%|█████▊ | 6819/11728 [3:43:56<7:51:56, 5.77s/it] {'loss': 0.4894, 'learning_rate': 7.865271297968815e-06, 'epoch': 0.58} + 58%|█████▊ | 6819/11728 [3:43:56<7:51:56, 5.77s/it] 58%|█████▊ | 6820/11728 [3:44:02<7:54:05, 5.80s/it] {'loss': 0.4766, 'learning_rate': 7.862573440078686e-06, 'epoch': 0.58} + 58%|█████▊ | 6820/11728 [3:44:02<7:54:05, 5.80s/it] 58%|█████▊ | 6821/11728 [3:44:07<7:50:20, 5.75s/it] {'loss': 0.472, 'learning_rate': 7.85987574519763e-06, 'epoch': 0.58} + 58%|█████▊ | 6821/11728 [3:44:07<7:50:20, 5.75s/it] 58%|█████▊ | 6822/11728 [3:44:13<7:49:18, 5.74s/it] {'loss': 0.4764, 'learning_rate': 7.857178213531385e-06, 'epoch': 0.58} + 58%|█████▊ | 6822/11728 [3:44:13<7:49:18, 5.74s/it] 58%|█████▊ | 6823/11728 [3:44:19<7:46:51, 5.71s/it] {'loss': 0.4838, 'learning_rate': 7.854480845285672e-06, 'epoch': 0.58} + 58%|█████▊ | 6823/11728 [3:44:19<7:46:51, 5.71s/it] 58%|█████▊ | 6824/11728 [3:44:24<7:42:43, 5.66s/it] {'loss': 0.4739, 'learning_rate': 7.851783640666209e-06, 'epoch': 0.58} + 58%|█████▊ | 6824/11728 [3:44:24<7:42:43, 5.66s/it] 58%|█████▊ | 6825/11728 [3:44:30<7:46:30, 5.71s/it] {'loss': 0.4549, 'learning_rate': 7.849086599878697e-06, 'epoch': 0.58} + 58%|█████▊ | 6825/11728 [3:44:30<7:46:30, 5.71s/it] 58%|█████▊ | 6826/11728 [3:44:36<7:47:59, 5.73s/it] {'loss': 0.4616, 'learning_rate': 7.846389723128819e-06, 'epoch': 0.58} + 58%|█████▊ | 6826/11728 [3:44:36<7:47:59, 5.73s/it] 58%|█████▊ | 6827/11728 [3:44:42<7:49:03, 5.74s/it] {'loss': 0.4571, 'learning_rate': 7.843693010622249e-06, 'epoch': 0.58} + 58%|█████▊ | 6827/11728 [3:44:42<7:49:03, 5.74s/it] 58%|█████▊ | 6828/11728 [3:44:47<7:50:54, 5.77s/it] {'loss': 0.4682, 'learning_rate': 7.840996462564654e-06, 'epoch': 0.58} + 58%|█████▊ | 6828/11728 [3:44:47<7:50:54, 5.77s/it] 58%|█████▊ | 6829/11728 [3:44:53<7:57:37, 5.85s/it] {'loss': 0.4791, 'learning_rate': 7.838300079161684e-06, 'epoch': 0.58} + 58%|█████▊ | 6829/11728 [3:44:53<7:57:37, 5.85s/it] 58%|█████▊ | 6830/11728 [3:44:59<7:52:00, 5.78s/it] {'loss': 0.4546, 'learning_rate': 7.835603860618973e-06, 'epoch': 0.58} + 58%|█████▊ | 6830/11728 [3:44:59<7:52:00, 5.78s/it] 58%|█████▊ | 6831/11728 [3:45:05<7:47:28, 5.73s/it] {'loss': 0.4762, 'learning_rate': 7.832907807142149e-06, 'epoch': 0.58} + 58%|█████▊ | 6831/11728 [3:45:05<7:47:28, 5.73s/it] 58%|█████▊ | 6832/11728 [3:45:10<7:46:45, 5.72s/it] {'loss': 0.4588, 'learning_rate': 7.83021191893682e-06, 'epoch': 0.58} + 58%|█████▊ | 6832/11728 [3:45:10<7:46:45, 5.72s/it] 58%|█████▊ | 6833/11728 [3:45:16<7:43:35, 5.68s/it] {'loss': 0.4616, 'learning_rate': 7.82751619620859e-06, 'epoch': 0.58} + 58%|█████▊ | 6833/11728 [3:45:16<7:43:35, 5.68s/it] 58%|█████▊ | 6834/11728 [3:45:22<7:46:34, 5.72s/it] {'loss': 0.466, 'learning_rate': 7.824820639163047e-06, 'epoch': 0.58} + 58%|█████▊ | 6834/11728 [3:45:22<7:46:34, 5.72s/it] 58%|█████▊ | 6835/11728 [3:45:28<7:49:49, 5.76s/it] {'loss': 0.4598, 'learning_rate': 7.822125248005764e-06, 'epoch': 0.58} + 58%|█████▊ | 6835/11728 [3:45:28<7:49:49, 5.76s/it] 58%|█████▊ | 6836/11728 [3:45:33<7:48:40, 5.75s/it] {'loss': 0.4742, 'learning_rate': 7.819430022942298e-06, 'epoch': 0.58} + 58%|█████▊ | 6836/11728 [3:45:33<7:48:40, 5.75s/it] 58%|█████▊ | 6837/11728 [3:45:39<7:41:29, 5.66s/it] {'loss': 0.4715, 'learning_rate': 7.816734964178202e-06, 'epoch': 0.58} + 58%|█████▊ | 6837/11728 [3:45:39<7:41:29, 5.66s/it] 58%|█████▊ | 6838/11728 [3:45:44<7:40:37, 5.65s/it] {'loss': 0.4704, 'learning_rate': 7.814040071919016e-06, 'epoch': 0.58} + 58%|█████▊ | 6838/11728 [3:45:44<7:40:37, 5.65s/it] 58%|█████▊ | 6839/11728 [3:45:50<7:43:00, 5.68s/it] {'loss': 0.4686, 'learning_rate': 7.811345346370257e-06, 'epoch': 0.58} + 58%|█████▊ | 6839/11728 [3:45:50<7:43:00, 5.68s/it] 58%|█████▊ | 6840/11728 [3:45:56<7:49:38, 5.76s/it] {'loss': 0.4908, 'learning_rate': 7.808650787737443e-06, 'epoch': 0.58} + 58%|█████▊ | 6840/11728 [3:45:56<7:49:38, 5.76s/it] 58%|█████▊ | 6841/11728 [3:46:02<7:48:26, 5.75s/it] {'loss': 0.4551, 'learning_rate': 7.805956396226064e-06, 'epoch': 0.58} + 58%|█████▊ | 6841/11728 [3:46:02<7:48:26, 5.75s/it] 58%|█████▊ | 6842/11728 [3:46:08<7:58:11, 5.87s/it] {'loss': 0.4837, 'learning_rate': 7.80326217204161e-06, 'epoch': 0.58} + 58%|█████▊ | 6842/11728 [3:46:08<7:58:11, 5.87s/it] 58%|█████▊ | 6843/11728 [3:46:14<7:53:45, 5.82s/it] {'loss': 0.475, 'learning_rate': 7.800568115389559e-06, 'epoch': 0.58} + 58%|█████▊ | 6843/11728 [3:46:14<7:53:45, 5.82s/it] 58%|█████▊ | 6844/11728 [3:46:19<7:50:03, 5.77s/it] {'loss': 0.4791, 'learning_rate': 7.797874226475362e-06, 'epoch': 0.58} + 58%|█████▊ | 6844/11728 [3:46:19<7:50:03, 5.77s/it] 58%|█████▊ | 6845/11728 [3:46:25<7:49:07, 5.76s/it] {'loss': 0.4853, 'learning_rate': 7.795180505504472e-06, 'epoch': 0.58} + 58%|█████▊ | 6845/11728 [3:46:25<7:49:07, 5.76s/it] 58%|█████▊ | 6846/11728 [3:46:31<7:44:49, 5.71s/it] {'loss': 0.4614, 'learning_rate': 7.792486952682319e-06, 'epoch': 0.58} + 58%|█████▊ | 6846/11728 [3:46:31<7:44:49, 5.71s/it] 58%|█████▊ | 6847/11728 [3:46:36<7:44:18, 5.71s/it] {'loss': 0.4718, 'learning_rate': 7.78979356821433e-06, 'epoch': 0.58} + 58%|█████▊ | 6847/11728 [3:46:36<7:44:18, 5.71s/it] 58%|█████▊ | 6848/11728 [3:46:42<7:42:56, 5.69s/it] {'loss': 0.4769, 'learning_rate': 7.78710035230591e-06, 'epoch': 0.58} + 58%|█████▊ | 6848/11728 [3:46:42<7:42:56, 5.69s/it] 58%|█████▊ | 6849/11728 [3:46:48<7:46:43, 5.74s/it] {'loss': 0.4812, 'learning_rate': 7.784407305162456e-06, 'epoch': 0.58} + 58%|█████▊ | 6849/11728 [3:46:48<7:46:43, 5.74s/it]2 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... +0 AutoResumeHook: Checking whether to suspend... + 58%|█████▊ | 6850/11728 [3:46:54<7:54:05, 5.83s/it] {'loss': 0.471, 'learning_rate': 7.781714426989346e-06, 'epoch': 0.58} + 58%|█████▊ | 6850/11728 [3:46:54<7:54:05, 5.83s/it] 58%|█████▊ | 6851/11728 [3:47:00<7:52:55, 5.82s/it] {'loss': 0.4658, 'learning_rate': 7.779021717991959e-06, 'epoch': 0.58} + 58%|█████▊ | 6851/11728 [3:47:00<7:52:55, 5.82s/it] 58%|█████▊ | 6852/11728 [3:47:06<7:51:48, 5.81s/it] {'loss': 0.462, 'learning_rate': 7.77632917837565e-06, 'epoch': 0.58} + 58%|█████▊ | 6852/11728 [3:47:06<7:51:48, 5.81s/it] 58%|█████▊ | 6853/11728 [3:47:12<7:58:41, 5.89s/it] {'loss': 0.4679, 'learning_rate': 7.773636808345757e-06, 'epoch': 0.58} + 58%|█████▊ | 6853/11728 [3:47:12<7:58:41, 5.89s/it] 58%|█████▊ | 6854/11728 [3:47:17<7:57:18, 5.88s/it] {'loss': 0.4648, 'learning_rate': 7.770944608107622e-06, 'epoch': 0.58} + 58%|█████▊ | 6854/11728 [3:47:17<7:57:18, 5.88s/it] 58%|█████▊ | 6855/11728 [3:47:23<7:56:18, 5.86s/it] {'loss': 0.4595, 'learning_rate': 7.76825257786655e-06, 'epoch': 0.58} + 58%|█████▊ | 6855/11728 [3:47:23<7:56:18, 5.86s/it] 58%|█████▊ | 6856/11728 [3:47:29<7:56:52, 5.87s/it] {'loss': 0.4763, 'learning_rate': 7.765560717827857e-06, 'epoch': 0.58} + 58%|█████▊ | 6856/11728 [3:47:29<7:56:52, 5.87s/it] 58%|█████▊ | 6857/11728 [3:47:35<7:53:36, 5.83s/it] {'loss': 0.4627, 'learning_rate': 7.762869028196832e-06, 'epoch': 0.58} + 58%|█████▊ | 6857/11728 [3:47:35<7:53:36, 5.83s/it] 58%|█████▊ | 6858/11728 [3:47:41<7:51:15, 5.81s/it] {'loss': 0.4843, 'learning_rate': 7.760177509178756e-06, 'epoch': 0.58} + 58%|█████▊ | 6858/11728 [3:47:41<7:51:15, 5.81s/it] 58%|█████▊ | 6859/11728 [3:47:46<7:49:22, 5.78s/it] {'loss': 0.4733, 'learning_rate': 7.757486160978891e-06, 'epoch': 0.58} + 58%|█████▊ | 6859/11728 [3:47:46<7:49:22, 5.78s/it] 58%|█████▊ | 6860/11728 [3:47:53<7:57:34, 5.89s/it] {'loss': 0.4763, 'learning_rate': 7.754794983802494e-06, 'epoch': 0.58} + 58%|█████▊ | 6860/11728 [3:47:53<7:57:34, 5.89s/it] 59%|█████▊ | 6861/11728 [3:47:58<7:47:53, 5.77s/it] {'loss': 0.4751, 'learning_rate': 7.752103977854809e-06, 'epoch': 0.59} + 59%|█████▊ | 6861/11728 [3:47:58<7:47:53, 5.77s/it] 59%|█████▊ | 6862/11728 [3:48:04<7:50:21, 5.80s/it] {'loss': 0.488, 'learning_rate': 7.749413143341056e-06, 'epoch': 0.59} + 59%|█████▊ | 6862/11728 [3:48:04<7:50:21, 5.80s/it] 59%|█████▊ | 6863/11728 [3:48:10<7:51:57, 5.82s/it] {'loss': 0.4751, 'learning_rate': 7.746722480466456e-06, 'epoch': 0.59} + 59%|█████▊ | 6863/11728 [3:48:10<7:51:57, 5.82s/it] 59%|█████▊ | 6864/11728 [3:48:16<7:54:19, 5.85s/it] {'loss': 0.4829, 'learning_rate': 7.7440319894362e-06, 'epoch': 0.59} + 59%|█████▊ | 6864/11728 [3:48:16<7:54:19, 5.85s/it] 59%|█████▊ | 6865/11728 [3:48:21<7:50:17, 5.80s/it] {'loss': 0.4892, 'learning_rate': 7.741341670455489e-06, 'epoch': 0.59} + 59%|█████▊ | 6865/11728 [3:48:21<7:50:17, 5.80s/it] 59%|█████▊ | 6866/11728 [3:48:27<7:44:46, 5.74s/it] {'loss': 0.4674, 'learning_rate': 7.73865152372949e-06, 'epoch': 0.59} + 59%|█████▊ | 6866/11728 [3:48:27<7:44:46, 5.74s/it] 59%|█████▊ | 6867/11728 [3:48:32<7:38:40, 5.66s/it] {'loss': 0.4575, 'learning_rate': 7.735961549463368e-06, 'epoch': 0.59} + 59%|█████▊ | 6867/11728 [3:48:32<7:38:40, 5.66s/it] 59%|█████▊ | 6868/11728 [3:48:38<7:45:47, 5.75s/it] {'loss': 0.4668, 'learning_rate': 7.733271747862265e-06, 'epoch': 0.59} + 59%|█████▊ | 6868/11728 [3:48:38<7:45:47, 5.75s/it] 59%|█████▊ | 6869/11728 [3:48:44<7:45:59, 5.75s/it] {'loss': 0.4634, 'learning_rate': 7.730582119131328e-06, 'epoch': 0.59} + 59%|█████▊ | 6869/11728 [3:48:44<7:45:59, 5.75s/it] 59%|█████▊ | 6870/11728 [3:48:50<7:54:06, 5.86s/it] {'loss': 0.4493, 'learning_rate': 7.727892663475672e-06, 'epoch': 0.59} + 59%|█████▊ | 6870/11728 [3:48:50<7:54:06, 5.86s/it] 59%|█████▊ | 6871/11728 [3:48:56<7:47:23, 5.77s/it] {'loss': 0.4587, 'learning_rate': 7.725203381100403e-06, 'epoch': 0.59} + 59%|█████▊ | 6871/11728 [3:48:56<7:47:23, 5.77s/it] 59%|█████▊ | 6872/11728 [3:49:02<7:47:23, 5.78s/it] {'loss': 0.4765, 'learning_rate': 7.722514272210627e-06, 'epoch': 0.59} + 59%|█████▊ | 6872/11728 [3:49:02<7:47:23, 5.78s/it] 59%|█████▊ | 6873/11728 [3:49:08<7:50:06, 5.81s/it] {'loss': 0.453, 'learning_rate': 7.719825337011415e-06, 'epoch': 0.59} + 59%|█████▊ | 6873/11728 [3:49:08<7:50:06, 5.81s/it] 59%|█████▊ | 6874/11728 [3:49:13<7:47:18, 5.78s/it] {'loss': 0.4642, 'learning_rate': 7.717136575707846e-06, 'epoch': 0.59} + 59%|█████▊ | 6874/11728 [3:49:13<7:47:18, 5.78s/it] 59%|█████▊ | 6875/11728 [3:49:19<7:42:28, 5.72s/it] {'loss': 0.4499, 'learning_rate': 7.714447988504972e-06, 'epoch': 0.59} + 59%|█████▊ | 6875/11728 [3:49:19<7:42:28, 5.72s/it] 59%|█████▊ | 6876/11728 [3:49:24<7:40:46, 5.70s/it] {'loss': 0.4527, 'learning_rate': 7.711759575607838e-06, 'epoch': 0.59} + 59%|█████▊ | 6876/11728 [3:49:24<7:40:46, 5.70s/it] 59%|█████▊ | 6877/11728 [3:49:30<7:43:53, 5.74s/it] {'loss': 0.4996, 'learning_rate': 7.709071337221468e-06, 'epoch': 0.59} + 59%|█████▊ | 6877/11728 [3:49:30<7:43:53, 5.74s/it] 59%|█████▊ | 6878/11728 [3:49:36<7:45:24, 5.76s/it] {'loss': 0.444, 'learning_rate': 7.706383273550883e-06, 'epoch': 0.59} + 59%|█████▊ | 6878/11728 [3:49:36<7:45:24, 5.76s/it] 59%|█████▊ | 6879/11728 [3:49:42<7:40:16, 5.70s/it] {'loss': 0.4797, 'learning_rate': 7.703695384801086e-06, 'epoch': 0.59} + 59%|█████▊ | 6879/11728 [3:49:42<7:40:16, 5.70s/it] 59%|█████▊ | 6880/11728 [3:49:48<7:48:40, 5.80s/it] {'loss': 0.4592, 'learning_rate': 7.701007671177066e-06, 'epoch': 0.59} + 59%|█████▊ | 6880/11728 [3:49:48<7:48:40, 5.80s/it] 59%|█████▊ | 6881/11728 [3:49:53<7:44:24, 5.75s/it] {'loss': 0.4791, 'learning_rate': 7.698320132883801e-06, 'epoch': 0.59} + 59%|█████▊ | 6881/11728 [3:49:53<7:44:24, 5.75s/it] 59%|█████▊ | 6882/11728 [3:49:59<7:40:06, 5.70s/it] {'loss': 0.4682, 'learning_rate': 7.695632770126247e-06, 'epoch': 0.59} + 59%|█████▊ | 6882/11728 [3:49:59<7:40:06, 5.70s/it] 59%|█████▊ | 6883/11728 [3:50:04<7:36:57, 5.66s/it] {'loss': 0.4499, 'learning_rate': 7.692945583109362e-06, 'epoch': 0.59} + 59%|█████▊ | 6883/11728 [3:50:04<7:36:57, 5.66s/it] 59%|█████▊ | 6884/11728 [3:50:10<7:44:48, 5.76s/it] {'loss': 0.5006, 'learning_rate': 7.690258572038077e-06, 'epoch': 0.59} + 59%|█████▊ | 6884/11728 [3:50:10<7:44:48, 5.76s/it] 59%|█████▊ | 6885/11728 [3:50:16<7:42:49, 5.73s/it] {'loss': 0.4488, 'learning_rate': 7.687571737117318e-06, 'epoch': 0.59} + 59%|█████▊ | 6885/11728 [3:50:16<7:42:49, 5.73s/it] 59%|█████▊ | 6886/11728 [3:50:22<7:43:09, 5.74s/it] {'loss': 0.4645, 'learning_rate': 7.684885078551991e-06, 'epoch': 0.59} + 59%|█████▊ | 6886/11728 [3:50:22<7:43:09, 5.74s/it] 59%|█████▊ | 6887/11728 [3:50:27<7:34:40, 5.64s/it] {'loss': 0.4467, 'learning_rate': 7.682198596546992e-06, 'epoch': 0.59} + 59%|█████▊ | 6887/11728 [3:50:27<7:34:40, 5.64s/it] 59%|█████▊ | 6888/11728 [3:50:33<7:37:21, 5.67s/it] {'loss': 0.4741, 'learning_rate': 7.679512291307207e-06, 'epoch': 0.59} + 59%|█████▊ | 6888/11728 [3:50:33<7:37:21, 5.67s/it] 59%|█████▊ | 6889/11728 [3:50:39<7:40:46, 5.71s/it] {'loss': 0.4323, 'learning_rate': 7.6768261630375e-06, 'epoch': 0.59} + 59%|█████▊ | 6889/11728 [3:50:39<7:40:46, 5.71s/it] 59%|█████▊ | 6890/11728 [3:50:44<7:37:26, 5.67s/it] {'loss': 0.4686, 'learning_rate': 7.674140211942732e-06, 'epoch': 0.59} + 59%|█████▊ | 6890/11728 [3:50:44<7:37:26, 5.67s/it] 59%|█████▉ | 6891/11728 [3:50:50<7:41:16, 5.72s/it] {'loss': 0.491, 'learning_rate': 7.671454438227739e-06, 'epoch': 0.59} + 59%|█████▉ | 6891/11728 [3:50:50<7:41:16, 5.72s/it] 59%|█████▉ | 6892/11728 [3:50:56<7:43:53, 5.76s/it] {'loss': 0.4935, 'learning_rate': 7.668768842097353e-06, 'epoch': 0.59} + 59%|█████▉ | 6892/11728 [3:50:56<7:43:53, 5.76s/it] 59%|█████▉ | 6893/11728 [3:51:02<7:42:53, 5.74s/it] {'loss': 0.4906, 'learning_rate': 7.666083423756387e-06, 'epoch': 0.59} + 59%|█████▉ | 6893/11728 [3:51:02<7:42:53, 5.74s/it] 59%|█████▉ | 6894/11728 [3:51:08<7:46:00, 5.78s/it] {'loss': 0.4721, 'learning_rate': 7.663398183409645e-06, 'epoch': 0.59} + 59%|█████▉ | 6894/11728 [3:51:08<7:46:00, 5.78s/it] 59%|█████▉ | 6895/11728 [3:51:14<7:46:52, 5.80s/it] {'loss': 0.4881, 'learning_rate': 7.660713121261911e-06, 'epoch': 0.59} + 59%|█████▉ | 6895/11728 [3:51:14<7:46:52, 5.80s/it] 59%|█████▉ | 6896/11728 [3:51:19<7:49:00, 5.82s/it] {'loss': 0.4548, 'learning_rate': 7.658028237517957e-06, 'epoch': 0.59} + 59%|█████▉ | 6896/11728 [3:51:19<7:49:00, 5.82s/it] 59%|█████▉ | 6897/11728 [3:51:25<7:49:24, 5.83s/it] {'loss': 0.4706, 'learning_rate': 7.655343532382552e-06, 'epoch': 0.59} + 59%|█████▉ | 6897/11728 [3:51:25<7:49:24, 5.83s/it] 59%|█████▉ | 6898/11728 [3:51:31<7:52:31, 5.87s/it] {'loss': 0.4598, 'learning_rate': 7.652659006060436e-06, 'epoch': 0.59} + 59%|█████▉ | 6898/11728 [3:51:31<7:52:31, 5.87s/it] 59%|█████▉ | 6899/11728 [3:51:37<7:52:26, 5.87s/it] {'loss': 0.4549, 'learning_rate': 7.649974658756346e-06, 'epoch': 0.59} + 59%|█████▉ | 6899/11728 [3:51:37<7:52:26, 5.87s/it]2 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... +0 AutoResumeHook: Checking whether to suspend... + 59%|█████▉ | 6900/11728 [3:51:43<7:44:13, 5.77s/it] {'loss': 0.4681, 'learning_rate': 7.647290490674997e-06, 'epoch': 0.59} + 59%|█████▉ | 6900/11728 [3:51:43<7:44:13, 5.77s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-6900/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-6900/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-6900/mm_projector +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/torch/nn/modules/module.py:1802: UserWarning: Positional args are being deprecated, use kwargs instead. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details. + warnings.warn( + 59%|█████▉ | 6901/11728 [3:52:13<17:33:19, 13.09s/it] {'loss': 0.4945, 'learning_rate': 7.644606502021096e-06, 'epoch': 0.59} + 59%|█████▉ | 6901/11728 [3:52:13<17:33:19, 13.09s/it] 59%|█████▉ | 6902/11728 [3:52:19<14:40:50, 10.95s/it] {'loss': 0.4755, 'learning_rate': 7.64192269299934e-06, 'epoch': 0.59} + 59%|█████▉ | 6902/11728 [3:52:19<14:40:50, 10.95s/it] 59%|█████▉ | 6903/11728 [3:52:25<12:38:22, 9.43s/it] {'loss': 0.4738, 'learning_rate': 7.639239063814405e-06, 'epoch': 0.59} + 59%|█████▉ | 6903/11728 [3:52:25<12:38:22, 9.43s/it] 59%|█████▉ | 6904/11728 [3:52:30<11:07:05, 8.30s/it] {'loss': 0.4773, 'learning_rate': 7.636555614670953e-06, 'epoch': 0.59} + 59%|█████▉ | 6904/11728 [3:52:30<11:07:05, 8.30s/it] 59%|█████▉ | 6905/11728 [3:52:36<10:05:46, 7.54s/it] {'loss': 0.4604, 'learning_rate': 7.633872345773635e-06, 'epoch': 0.59} + 59%|█████▉ | 6905/11728 [3:52:36<10:05:46, 7.54s/it] 59%|█████▉ | 6906/11728 [3:52:42<9:23:55, 7.02s/it] {'loss': 0.4439, 'learning_rate': 7.631189257327092e-06, 'epoch': 0.59} + 59%|█████▉ | 6906/11728 [3:52:42<9:23:55, 7.02s/it] 59%|█████▉ | 6907/11728 [3:52:48<9:01:07, 6.73s/it] {'loss': 0.4783, 'learning_rate': 7.6285063495359465e-06, 'epoch': 0.59} + 59%|█████▉ | 6907/11728 [3:52:48<9:01:07, 6.73s/it] 59%|█████▉ | 6908/11728 [3:52:54<8:33:59, 6.40s/it] {'loss': 0.4488, 'learning_rate': 7.625823622604809e-06, 'epoch': 0.59} + 59%|█████▉ | 6908/11728 [3:52:54<8:33:59, 6.40s/it] 59%|█████▉ | 6909/11728 [3:52:59<8:14:09, 6.15s/it] {'loss': 0.4788, 'learning_rate': 7.623141076738271e-06, 'epoch': 0.59} + 59%|█████▉ | 6909/11728 [3:52:59<8:14:09, 6.15s/it] 59%|█████▉ | 6910/11728 [3:53:05<8:06:11, 6.05s/it] {'loss': 0.4774, 'learning_rate': 7.620458712140916e-06, 'epoch': 0.59} + 59%|█████▉ | 6910/11728 [3:53:05<8:06:11, 6.05s/it] 59%|█████▉ | 6911/11728 [3:53:11<7:56:35, 5.94s/it] {'loss': 0.4951, 'learning_rate': 7.617776529017318e-06, 'epoch': 0.59} + 59%|█████▉ | 6911/11728 [3:53:11<7:56:35, 5.94s/it] 59%|█████▉ | 6912/11728 [3:53:16<7:55:02, 5.92s/it] {'loss': 0.4491, 'learning_rate': 7.615094527572027e-06, 'epoch': 0.59} + 59%|█████▉ | 6912/11728 [3:53:16<7:55:02, 5.92s/it] 59%|█████▉ | 6913/11728 [3:53:22<7:55:52, 5.93s/it] {'loss': 0.4892, 'learning_rate': 7.612412708009583e-06, 'epoch': 0.59} + 59%|█████▉ | 6913/11728 [3:53:22<7:55:52, 5.93s/it] 59%|█████▉ | 6914/11728 [3:53:28<7:54:47, 5.92s/it] {'loss': 0.4947, 'learning_rate': 7.6097310705345096e-06, 'epoch': 0.59} + 59%|█████▉ | 6914/11728 [3:53:28<7:54:47, 5.92s/it] 59%|█████▉ | 6915/11728 [3:53:34<7:51:19, 5.88s/it] {'loss': 0.4537, 'learning_rate': 7.607049615351329e-06, 'epoch': 0.59} + 59%|█████▉ | 6915/11728 [3:53:34<7:51:19, 5.88s/it] 59%|█████▉ | 6916/11728 [3:53:40<7:44:22, 5.79s/it] {'loss': 0.475, 'learning_rate': 7.604368342664533e-06, 'epoch': 0.59} + 59%|█████▉ | 6916/11728 [3:53:40<7:44:22, 5.79s/it] 59%|█████▉ | 6917/11728 [3:53:46<7:47:08, 5.83s/it] {'loss': 0.4691, 'learning_rate': 7.601687252678611e-06, 'epoch': 0.59} + 59%|█████▉ | 6917/11728 [3:53:46<7:47:08, 5.83s/it] 59%|█████▉ | 6918/11728 [3:53:52<7:55:05, 5.93s/it] {'loss': 0.4853, 'learning_rate': 7.59900634559803e-06, 'epoch': 0.59} + 59%|█████▉ | 6918/11728 [3:53:52<7:55:05, 5.93s/it] 59%|█████▉ | 6919/11728 [3:53:58<7:56:28, 5.94s/it] {'loss': 0.4568, 'learning_rate': 7.596325621627247e-06, 'epoch': 0.59} + 59%|█████▉ | 6919/11728 [3:53:58<7:56:28, 5.94s/it] 59%|█████▉ | 6920/11728 [3:54:04<8:05:30, 6.06s/it] {'loss': 0.513, 'learning_rate': 7.5936450809707096e-06, 'epoch': 0.59} + 59%|█████▉ | 6920/11728 [3:54:04<8:05:30, 6.06s/it] 59%|█████▉ | 6921/11728 [3:54:10<7:53:32, 5.91s/it] {'loss': 0.4804, 'learning_rate': 7.590964723832846e-06, 'epoch': 0.59} + 59%|█████▉ | 6921/11728 [3:54:10<7:53:32, 5.91s/it] 59%|█████▉ | 6922/11728 [3:54:15<7:46:58, 5.83s/it] {'loss': 0.4532, 'learning_rate': 7.588284550418068e-06, 'epoch': 0.59} + 59%|█████▉ | 6922/11728 [3:54:15<7:46:58, 5.83s/it] 59%|█████▉ | 6923/11728 [3:54:21<7:51:52, 5.89s/it] {'loss': 0.4717, 'learning_rate': 7.58560456093078e-06, 'epoch': 0.59} + 59%|█████▉ | 6923/11728 [3:54:21<7:51:52, 5.89s/it] 59%|█████▉ | 6924/11728 [3:54:27<7:46:48, 5.83s/it] {'loss': 0.4658, 'learning_rate': 7.582924755575365e-06, 'epoch': 0.59} + 59%|█████▉ | 6924/11728 [3:54:27<7:46:48, 5.83s/it] 59%|█████▉ | 6925/11728 [3:54:33<7:46:19, 5.83s/it] {'loss': 0.4563, 'learning_rate': 7.5802451345562e-06, 'epoch': 0.59} + 59%|█████▉ | 6925/11728 [3:54:33<7:46:19, 5.83s/it] 59%|█████▉ | 6926/11728 [3:54:38<7:40:28, 5.75s/it] {'loss': 0.4731, 'learning_rate': 7.577565698077646e-06, 'epoch': 0.59} + 59%|█████▉ | 6926/11728 [3:54:38<7:40:28, 5.75s/it] 59%|█████▉ | 6927/11728 [3:54:44<7:42:54, 5.79s/it] {'loss': 0.476, 'learning_rate': 7.574886446344043e-06, 'epoch': 0.59} + 59%|█████▉ | 6927/11728 [3:54:44<7:42:54, 5.79s/it] 59%|█████▉ | 6928/11728 [3:54:50<7:48:18, 5.85s/it] {'loss': 0.4769, 'learning_rate': 7.572207379559722e-06, 'epoch': 0.59} + 59%|█████▉ | 6928/11728 [3:54:50<7:48:18, 5.85s/it] 59%|█████▉ | 6929/11728 [3:54:56<7:41:43, 5.77s/it] {'loss': 0.4979, 'learning_rate': 7.569528497929005e-06, 'epoch': 0.59} + 59%|█████▉ | 6929/11728 [3:54:56<7:41:43, 5.77s/it] 59%|█████▉ | 6930/11728 [3:55:01<7:37:36, 5.72s/it] {'loss': 0.4768, 'learning_rate': 7.566849801656193e-06, 'epoch': 0.59} + 59%|█████▉ | 6930/11728 [3:55:01<7:37:36, 5.72s/it] 59%|█████▉ | 6931/11728 [3:55:08<7:45:11, 5.82s/it] {'loss': 0.4733, 'learning_rate': 7.564171290945571e-06, 'epoch': 0.59} + 59%|█████▉ | 6931/11728 [3:55:08<7:45:11, 5.82s/it] 59%|█████▉ | 6932/11728 [3:55:13<7:43:24, 5.80s/it] {'loss': 0.477, 'learning_rate': 7.561492966001418e-06, 'epoch': 0.59} + 59%|█████▉ | 6932/11728 [3:55:13<7:43:24, 5.80s/it] 59%|█████▉ | 6933/11728 [3:55:19<7:53:10, 5.92s/it] {'loss': 0.4921, 'learning_rate': 7.558814827027987e-06, 'epoch': 0.59} + 59%|█████▉ | 6933/11728 [3:55:19<7:53:10, 5.92s/it] 59%|█████▉ | 6934/11728 [3:55:25<7:45:57, 5.83s/it] {'loss': 0.4591, 'learning_rate': 7.556136874229532e-06, 'epoch': 0.59} + 59%|█████▉ | 6934/11728 [3:55:25<7:45:57, 5.83s/it] 59%|█████▉ | 6935/11728 [3:55:31<7:40:59, 5.77s/it] {'loss': 0.465, 'learning_rate': 7.5534591078102825e-06, 'epoch': 0.59} + 59%|█████▉ | 6935/11728 [3:55:31<7:40:59, 5.77s/it] 59%|█████▉ | 6936/11728 [3:55:36<7:39:51, 5.76s/it] {'loss': 0.4631, 'learning_rate': 7.550781527974455e-06, 'epoch': 0.59} + 59%|█████▉ | 6936/11728 [3:55:36<7:39:51, 5.76s/it] 59%|█████▉ | 6937/11728 [3:55:42<7:44:47, 5.82s/it] {'loss': 0.4959, 'learning_rate': 7.54810413492625e-06, 'epoch': 0.59} + 59%|█████▉ | 6937/11728 [3:55:42<7:44:47, 5.82s/it] 59%|█████▉ | 6938/11728 [3:55:48<7:39:57, 5.76s/it] {'loss': 0.4591, 'learning_rate': 7.545426928869863e-06, 'epoch': 0.59} + 59%|█████▉ | 6938/11728 [3:55:48<7:39:57, 5.76s/it] 59%|█████▉ | 6939/11728 [3:55:54<7:39:00, 5.75s/it] {'loss': 0.4892, 'learning_rate': 7.542749910009468e-06, 'epoch': 0.59} + 59%|█████▉ | 6939/11728 [3:55:54<7:39:00, 5.75s/it] 59%|█████▉ | 6940/11728 [3:55:59<7:36:08, 5.72s/it] {'loss': 0.466, 'learning_rate': 7.540073078549221e-06, 'epoch': 0.59} + 59%|█████▉ | 6940/11728 [3:55:59<7:36:08, 5.72s/it] 59%|█████▉ | 6941/11728 [3:56:05<7:37:24, 5.73s/it] {'loss': 0.4582, 'learning_rate': 7.537396434693274e-06, 'epoch': 0.59} + 59%|█████▉ | 6941/11728 [3:56:05<7:37:24, 5.73s/it] 59%|█████▉ | 6942/11728 [3:56:11<7:38:50, 5.75s/it] {'loss': 0.4593, 'learning_rate': 7.53471997864575e-06, 'epoch': 0.59} + 59%|█████▉ | 6942/11728 [3:56:11<7:38:50, 5.75s/it] 59%|█████▉ | 6943/11728 [3:56:17<7:35:31, 5.71s/it] {'loss': 0.4571, 'learning_rate': 7.5320437106107756e-06, 'epoch': 0.59} + 59%|█████▉ | 6943/11728 [3:56:17<7:35:31, 5.71s/it] 59%|█████▉ | 6944/11728 [3:56:22<7:34:39, 5.70s/it] {'loss': 0.471, 'learning_rate': 7.5293676307924535e-06, 'epoch': 0.59} + 59%|█████▉ | 6944/11728 [3:56:22<7:34:39, 5.70s/it]WARNING: tokenization mismatch: 1 vs. 789. [[{'from': 'human', 'value': 'ASSISTANT: You are a forward-thinking HR consultancy with the following knowledge and traits.\n\nKNOWLEDGE: HR management, employee satisfaction, talent retention, team building, workplace culture.\n\nTRAITS: Innovation, empathy, solution orientation, creativity, understanding, teamwork.\n\nTASK: Use your knowledge to create an internal strategy document. We are an HR consultancy looking to develop 10 creative ways to improve employee satisfaction. Focus on ideas that are innovative and engaging, and cater to the needs of HR managers and company leaders.\n\nOUTPUT: A table in German containing 10 creative strategies to improve employee satisfaction, including a brief description for each.'}, {'from': 'gpt', 'value': '| Nr. | Strategie | Beschreibung |\n| --- | --- | --- |\n| 1. | "Wertschätzungswand" | Eine Wand im Büro, auf der Mitarbeiter anonym ihre Kollegen für ihre Leistungen und Beiträge loben und anerkennen können. |\n| 2. | Flexible Arbeitsmodelle | Einführung von flexiblen Arbeitszeiten und Homeoffice-Optionen, um Work-Life-Balance zu verbessern und individuelle Bedürfnisse zu berücksichtigen. |\n| 3. | Mitarbeiter-Workshops für persönliche Entwicklung | Organisieren von internen Workshops und Schulungen, um persönliche und berufliche Fähigkeiten der Mitarbeiter zu fördern. |\n| 4. | Team-Building-Aktivitäten außerhalb des Arbeitsplatzes | Regelmäßige Veranstaltungen wie Escape Rooms, Sportevents oder Kochkurse, um den Zusammenhalt und die Kommunikation im Team zu stärken. |\n| 5. | Gesundheits- und Wellness-Programme | Einführung von Fitness- und Entspannungskursen wie Yoga, Meditation oder Massagen, um das Wohlbefinden der Mitarbeiter zu fördern. |\n| 6. | Feedback-Kultur und transparente Kommunikation | Etablierung einer offenen Feedback-Kultur und transparenter Kommunikation, um die Mitarbeiter in Entscheidungsprozesse einzubinden. |\n| 7. | Mitarbeiter-Mentoring-Programm | Einführung eines Mentoring-Programms, bei dem erfahrene Mitarbeiter ihr Wissen und ihre Erfahrungen mit jüngeren Kollegen teilen. |\n| 8. | "Innovationstage" | Einrichtung von speziellen Tagen, an denen Mitarbeiter an eigenen Projekten arbeiten oder innovative Ideen für das Unternehmen entwickeln können. |\n| 9. | Individuelle Karriereentwicklungspläne | Erstellung von personalisierten Karriereplänen in Zusammenarbeit mit den Mitarbeitern, um ihre berufliche Entwicklung zu unterstützen. |\n| 10. | Gemeinschaftliche soziale Verantwortung (CSR) Initiativen | Organisation von Freiwilligenprojekten und CSR-Aktivitäten, um den Mitarbeitern die Möglichkeit zu geben, sozialen Einfluss zu nehmen. |'}]] (ignored) + 59%|█████▉ | 6945/11728 [3:56:28<7:35:44, 5.72s/it] {'loss': 0.462, 'learning_rate': 7.526691739394868e-06, 'epoch': 0.59} + 59%|█████▉ | 6945/11728 [3:56:28<7:35:44, 5.72s/it] 59%|█████▉ | 6946/11728 [3:56:34<7:37:27, 5.74s/it] {'loss': 0.4662, 'learning_rate': 7.524016036622094e-06, 'epoch': 0.59} + 59%|█████▉ | 6946/11728 [3:56:34<7:37:27, 5.74s/it] 59%|█████▉ | 6947/11728 [3:56:39<7:32:12, 5.68s/it] {'loss': 0.4598, 'learning_rate': 7.521340522678199e-06, 'epoch': 0.59} + 59%|█████▉ | 6947/11728 [3:56:39<7:32:12, 5.68s/it] 59%|█████▉ | 6948/11728 [3:56:45<7:38:09, 5.75s/it] {'loss': 0.4734, 'learning_rate': 7.518665197767223e-06, 'epoch': 0.59} + 59%|█████▉ | 6948/11728 [3:56:45<7:38:09, 5.75s/it] 59%|█████▉ | 6949/11728 [3:56:51<7:33:50, 5.70s/it] {'loss': 0.4659, 'learning_rate': 7.515990062093196e-06, 'epoch': 0.59} + 59%|█████▉ | 6949/11728 [3:56:51<7:33:50, 5.70s/it]7 AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +0 4 AutoResumeHook: Checking whether to suspend... +AutoResumeHook: Checking whether to suspend... + 59%|█████▉ | 6950/11728 [3:56:57<7:34:36, 5.71s/it]3 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4698, 'learning_rate': 7.51331511586014e-06, 'epoch': 0.59} + 59%|█████▉ | 6950/11728 [3:56:57<7:34:36, 5.71s/it] 59%|█████▉ | 6951/11728 [3:57:02<7:38:47, 5.76s/it] {'loss': 0.4604, 'learning_rate': 7.51064035927205e-06, 'epoch': 0.59} + 59%|█████▉ | 6951/11728 [3:57:02<7:38:47, 5.76s/it] 59%|█████▉ | 6952/11728 [3:57:08<7:39:05, 5.77s/it] {'loss': 0.4771, 'learning_rate': 7.507965792532922e-06, 'epoch': 0.59} + 59%|█████▉ | 6952/11728 [3:57:08<7:39:05, 5.77s/it] 59%|█████▉ | 6953/11728 [3:57:14<7:41:15, 5.80s/it] {'loss': 0.4658, 'learning_rate': 7.505291415846728e-06, 'epoch': 0.59} + 59%|█████▉ | 6953/11728 [3:57:14<7:41:15, 5.80s/it] 59%|█████▉ | 6954/11728 [3:57:20<7:39:52, 5.78s/it] {'loss': 0.4594, 'learning_rate': 7.5026172294174234e-06, 'epoch': 0.59} + 59%|█████▉ | 6954/11728 [3:57:20<7:39:52, 5.78s/it] 59%|█████▉ | 6955/11728 [3:57:26<7:39:00, 5.77s/it] {'loss': 0.4724, 'learning_rate': 7.499943233448958e-06, 'epoch': 0.59} + 59%|█████▉ | 6955/11728 [3:57:26<7:39:00, 5.77s/it] 59%|█████▉ | 6956/11728 [3:57:31<7:41:11, 5.80s/it] {'loss': 0.4476, 'learning_rate': 7.497269428145255e-06, 'epoch': 0.59} + 59%|█████▉ | 6956/11728 [3:57:31<7:41:11, 5.80s/it]Jun 27 23:17:27.317877 825571 slurmstepd 0x155550ab8700: error: *** STEP 9373138.0 ON batch-block4-2008 CANCELLED AT 2025-06-27T23:17:27 DUE TO TIME LIMIT *** +srun: Job step aborted: Waiting up to 122 seconds for job step to finish. + 59%|█████▉ | 6957/11728 [3:57:37<7:40:02, 5.79s/it] {'loss': 0.4728, 'learning_rate': 7.494595813710237e-06, 'epoch': 0.59} + 59%|█████▉ | 6957/11728 [3:57:37<7:40:02, 5.79s/it]srun: error: batch-block4-2008: task 0: Terminated +srun: Terminating StepId=9373138.0 +wandb: Currently logged in as: memmelma. Use `wandb login --relogin` to force relogin +MASTER_ADDR=batch-block1-0005 +JobID: 9378399 | Full list: batch-block1-0005 +NETWORK=Efficient-Large-Model/VILA1.5-3b +WARNING:torch.distributed.run: +***************************************** +Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed. +***************************************** +Did not find AutoResume SDK! +Did not find AutoResume SDK! +Did not find AutoResume SDK! +Did not find AutoResume SDK! +Did not find AutoResume SDK! +Did not find AutoResume SDK! +Did not find AutoResume SDK! +Did not find AutoResume SDK! +[2025-06-27 23:19:35,157] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-27 23:19:35,157] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-27 23:19:35,157] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-27 23:19:35,157] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-27 23:19:35,157] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-27 23:19:35,157] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-27 23:19:35,157] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-27 23:19:35,157] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-27 23:19:36,946] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-27 23:19:36,946] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-27 23:19:36,946] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-27 23:19:36,946] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-27 23:19:36,946] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-27 23:19:36,946] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-27 23:19:36,946] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-27 23:19:36,946] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-27 23:19:36,946] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-27 23:19:36,946] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-27 23:19:36,946] [INFO] [comm.py:625:init_distributed] Initializing TorchBackend in DeepSpeed with backend nccl +[2025-06-27 23:19:36,946] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-27 23:19:36,946] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-27 23:19:36,946] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-27 23:19:36,946] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-27 23:19:36,946] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-27 23:19:36,946] [INFO] [comm.py:594:init_distributed] cdb=None +You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`. +You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`. +You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`. +You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`. +You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`. +You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`. +You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`. +You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`. +[2025-06-27 23:19:47,099] [INFO] [partition_parameters.py:453:__exit__] finished initializing model with 2.70B parameters + Loading checkpoint shards: 0%| | 0/2 [00:00\nWould this person be more likely to be a type a or b person?\nAnswer the question using a single word or phrase.'}, {'from': 'gpt', 'value': ''}]] (ignored) + 80%|████████ | 9437/11728 [24:35<3:39:51, 5.76s/it] {'loss': 0.4551, 'learning_rate': 1.9355539573251737e-06, 'epoch': 0.8} + 80%|████████ | 9437/11728 [24:35<3:39:51, 5.76s/it] 80%|████████ | 9438/11728 [24:41<3:39:48, 5.76s/it] {'loss': 0.4505, 'learning_rate': 1.9339213059577587e-06, 'epoch': 0.8} + 80%|████████ | 9438/11728 [24:41<3:39:48, 5.76s/it] 80%|████████ | 9439/11728 [24:47<3:44:58, 5.90s/it] {'loss': 0.4513, 'learning_rate': 1.9322892697431783e-06, 'epoch': 0.8} + 80%|████████ | 9439/11728 [24:47<3:44:58, 5.90s/it] 80%|████████ | 9440/11728 [24:53<3:43:25, 5.86s/it] {'loss': 0.4682, 'learning_rate': 1.9306578488058993e-06, 'epoch': 0.8} + 80%|████████ | 9440/11728 [24:53<3:43:25, 5.86s/it] 80%|████████ | 9441/11728 [24:58<3:40:34, 5.79s/it] {'loss': 0.439, 'learning_rate': 1.9290270432703408e-06, 'epoch': 0.8} + 80%|████████ | 9441/11728 [24:58<3:40:34, 5.79s/it] 81%|████████ | 9442/11728 [25:04<3:40:31, 5.79s/it] {'loss': 0.4409, 'learning_rate': 1.9273968532608754e-06, 'epoch': 0.81} + 81%|████████ | 9442/11728 [25:04<3:40:31, 5.79s/it] 81%|████████ | 9443/11728 [25:10<3:39:40, 5.77s/it] {'loss': 0.4516, 'learning_rate': 1.925767278901828e-06, 'epoch': 0.81} + 81%|████████ | 9443/11728 [25:10<3:39:40, 5.77s/it] 81%|████████ | 9444/11728 [25:16<3:38:44, 5.75s/it] {'loss': 0.4567, 'learning_rate': 1.924138320317477e-06, 'epoch': 0.81} + 81%|████████ | 9444/11728 [25:16<3:38:44, 5.75s/it] 81%|████████ | 9445/11728 [25:21<3:37:23, 5.71s/it] {'loss': 0.4832, 'learning_rate': 1.9225099776320567e-06, 'epoch': 0.81} + 81%|████████ | 9445/11728 [25:21<3:37:23, 5.71s/it] 81%|████████ | 9446/11728 [25:27<3:38:16, 5.74s/it] {'loss': 0.4588, 'learning_rate': 1.920882250969742e-06, 'epoch': 0.81} + 81%|████████ | 9446/11728 [25:27<3:38:16, 5.74s/it] 81%|████████ | 9447/11728 [25:33<3:37:31, 5.72s/it] {'loss': 0.4671, 'learning_rate': 1.9192551404546812e-06, 'epoch': 0.81} + 81%|████████ | 9447/11728 [25:33<3:37:31, 5.72s/it] 81%|████████ | 9448/11728 [25:39<3:41:18, 5.82s/it] {'loss': 0.4322, 'learning_rate': 1.9176286462109574e-06, 'epoch': 0.81} + 81%|████████ | 9448/11728 [25:39<3:41:18, 5.82s/it] 81%|████████ | 9449/11728 [25:45<3:40:51, 5.81s/it] {'loss': 0.4507, 'learning_rate': 1.916002768362616e-06, 'epoch': 0.81} + 81%|████████ | 9449/11728 [25:45<3:40:51, 5.81s/it]3 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +0 AutoResumeHook: Checking whether to suspend... + 81%|████████ | 9450/11728 [25:50<3:39:28, 5.78s/it] {'loss': 0.474, 'learning_rate': 1.9143775070336523e-06, 'epoch': 0.81} + 81%|████████ | 9450/11728 [25:50<3:39:28, 5.78s/it] 81%|████████ | 9451/11728 [25:56<3:37:45, 5.74s/it] {'loss': 0.4534, 'learning_rate': 1.9127528623480175e-06, 'epoch': 0.81} + 81%|████████ | 9451/11728 [25:56<3:37:45, 5.74s/it] 81%|████████ | 9452/11728 [26:02<3:37:16, 5.73s/it] {'loss': 0.4558, 'learning_rate': 1.911128834429612e-06, 'epoch': 0.81} + 81%|████████ | 9452/11728 [26:02<3:37:16, 5.73s/it] 81%|████████ | 9453/11728 [26:07<3:35:57, 5.70s/it] {'loss': 0.4647, 'learning_rate': 1.9095054234022915e-06, 'epoch': 0.81} + 81%|████████ | 9453/11728 [26:07<3:35:57, 5.70s/it] 81%|████████ | 9454/11728 [26:13<3:34:33, 5.66s/it] {'loss': 0.4459, 'learning_rate': 1.9078826293898676e-06, 'epoch': 0.81} + 81%|████████ | 9454/11728 [26:13<3:34:33, 5.66s/it] 81%|████████ | 9455/11728 [26:19<3:37:23, 5.74s/it] {'loss': 0.4395, 'learning_rate': 1.9062604525160944e-06, 'epoch': 0.81} + 81%|████████ | 9455/11728 [26:19<3:37:23, 5.74s/it] 81%|████████ | 9456/11728 [26:25<3:39:32, 5.80s/it] {'loss': 0.4563, 'learning_rate': 1.90463889290469e-06, 'epoch': 0.81} + 81%|████████ | 9456/11728 [26:25<3:39:32, 5.80s/it] 81%|████████ | 9457/11728 [26:30<3:38:43, 5.78s/it] {'loss': 0.4521, 'learning_rate': 1.9030179506793201e-06, 'epoch': 0.81} + 81%|████████ | 9457/11728 [26:30<3:38:43, 5.78s/it] 81%|████████ | 9458/11728 [26:36<3:36:34, 5.72s/it] {'loss': 0.4436, 'learning_rate': 1.9013976259636057e-06, 'epoch': 0.81} + 81%|████████ | 9458/11728 [26:36<3:36:34, 5.72s/it] 81%|████████ | 9459/11728 [26:42<3:38:39, 5.78s/it] {'loss': 0.4585, 'learning_rate': 1.8997779188811194e-06, 'epoch': 0.81} + 81%|████████ | 9459/11728 [26:42<3:38:39, 5.78s/it] 81%|████████ | 9460/11728 [26:48<3:36:29, 5.73s/it] {'loss': 0.4432, 'learning_rate': 1.8981588295553855e-06, 'epoch': 0.81} + 81%|████████ | 9460/11728 [26:48<3:36:29, 5.73s/it] 81%|████████ | 9461/11728 [26:53<3:36:39, 5.73s/it] {'loss': 0.4378, 'learning_rate': 1.896540358109884e-06, 'epoch': 0.81} + 81%|████████ | 9461/11728 [26:53<3:36:39, 5.73s/it] 81%|████████ | 9462/11728 [26:59<3:40:38, 5.84s/it] {'loss': 0.4632, 'learning_rate': 1.8949225046680464e-06, 'epoch': 0.81} + 81%|████████ | 9462/11728 [26:59<3:40:38, 5.84s/it] 81%|████████ | 9463/11728 [27:05<3:37:50, 5.77s/it] {'loss': 0.4764, 'learning_rate': 1.893305269353257e-06, 'epoch': 0.81} + 81%|████████ | 9463/11728 [27:05<3:37:50, 5.77s/it] 81%|████████ | 9464/11728 [27:11<3:38:30, 5.79s/it] {'loss': 0.463, 'learning_rate': 1.891688652288851e-06, 'epoch': 0.81} + 81%|████████ | 9464/11728 [27:11<3:38:30, 5.79s/it] 81%|████████ | 9465/11728 [27:16<3:36:29, 5.74s/it] {'loss': 0.4429, 'learning_rate': 1.8900726535981195e-06, 'epoch': 0.81} + 81%|████████ | 9465/11728 [27:16<3:36:29, 5.74s/it] 81%|████████ | 9466/11728 [27:22<3:38:14, 5.79s/it] {'loss': 0.477, 'learning_rate': 1.888457273404305e-06, 'epoch': 0.81} + 81%|████████ | 9466/11728 [27:22<3:38:14, 5.79s/it] 81%|████████ | 9467/11728 [27:28<3:38:30, 5.80s/it] {'loss': 0.45, 'learning_rate': 1.8868425118306033e-06, 'epoch': 0.81} + 81%|████████ | 9467/11728 [27:28<3:38:30, 5.80s/it] 81%|████████ | 9468/11728 [27:34<3:35:50, 5.73s/it] {'loss': 0.4408, 'learning_rate': 1.8852283690001638e-06, 'epoch': 0.81} + 81%|████████ | 9468/11728 [27:34<3:35:50, 5.73s/it] 81%|████████ | 9469/11728 [27:40<3:37:35, 5.78s/it] {'loss': 0.4774, 'learning_rate': 1.883614845036087e-06, 'epoch': 0.81} + 81%|████████ | 9469/11728 [27:40<3:37:35, 5.78s/it] 81%|████████ | 9470/11728 [27:45<3:35:36, 5.73s/it] {'loss': 0.4479, 'learning_rate': 1.8820019400614264e-06, 'epoch': 0.81} + 81%|████████ | 9470/11728 [27:45<3:35:36, 5.73s/it] 81%|████████ | 9471/11728 [27:51<3:36:36, 5.76s/it] {'loss': 0.4524, 'learning_rate': 1.8803896541991895e-06, 'epoch': 0.81} + 81%|████████ | 9471/11728 [27:51<3:36:36, 5.76s/it] 81%|████████ | 9472/11728 [27:57<3:39:00, 5.82s/it] {'loss': 0.4599, 'learning_rate': 1.8787779875723389e-06, 'epoch': 0.81} + 81%|████████ | 9472/11728 [27:57<3:39:00, 5.82s/it] 81%|████████ | 9473/11728 [28:03<3:41:24, 5.89s/it] {'loss': 0.4606, 'learning_rate': 1.8771669403037807e-06, 'epoch': 0.81} + 81%|████████ | 9473/11728 [28:03<3:41:24, 5.89s/it] 81%|████████ | 9474/11728 [28:09<3:41:33, 5.90s/it] {'loss': 0.4372, 'learning_rate': 1.8755565125163844e-06, 'epoch': 0.81} + 81%|████████ | 9474/11728 [28:09<3:41:33, 5.90s/it] 81%|████████ | 9475/11728 [28:15<3:38:09, 5.81s/it] {'loss': 0.4452, 'learning_rate': 1.8739467043329663e-06, 'epoch': 0.81} + 81%|████████ | 9475/11728 [28:15<3:38:09, 5.81s/it] 81%|████████ | 9476/11728 [28:20<3:35:26, 5.74s/it] {'loss': 0.4518, 'learning_rate': 1.872337515876298e-06, 'epoch': 0.81} + 81%|████████ | 9476/11728 [28:20<3:35:26, 5.74s/it] 81%|████████ | 9477/11728 [28:26<3:38:14, 5.82s/it] {'loss': 0.474, 'learning_rate': 1.8707289472691037e-06, 'epoch': 0.81} + 81%|████████ | 9477/11728 [28:26<3:38:14, 5.82s/it] 81%|████████ | 9478/11728 [28:32<3:40:48, 5.89s/it] {'loss': 0.4501, 'learning_rate': 1.8691209986340598e-06, 'epoch': 0.81} + 81%|████████ | 9478/11728 [28:32<3:40:48, 5.89s/it] 81%|████████ | 9479/11728 [28:38<3:38:01, 5.82s/it] {'loss': 0.4342, 'learning_rate': 1.867513670093789e-06, 'epoch': 0.81} + 81%|████████ | 9479/11728 [28:38<3:38:01, 5.82s/it] 81%|████████ | 9480/11728 [28:44<3:35:58, 5.76s/it] {'loss': 0.4387, 'learning_rate': 1.8659069617708802e-06, 'epoch': 0.81} + 81%|████████ | 9480/11728 [28:44<3:35:58, 5.76s/it] 81%|████████ | 9481/11728 [28:50<3:39:57, 5.87s/it] {'loss': 0.4608, 'learning_rate': 1.8643008737878687e-06, 'epoch': 0.81} + 81%|████████ | 9481/11728 [28:50<3:39:57, 5.87s/it] 81%|████████ | 9482/11728 [28:56<3:41:50, 5.93s/it] {'loss': 0.4563, 'learning_rate': 1.8626954062672353e-06, 'epoch': 0.81} + 81%|████████ | 9482/11728 [28:56<3:41:50, 5.93s/it] 81%|████████ | 9483/11728 [29:02<3:42:28, 5.95s/it] {'loss': 0.4568, 'learning_rate': 1.8610905593314199e-06, 'epoch': 0.81} + 81%|████████ | 9483/11728 [29:02<3:42:28, 5.95s/it] 81%|████████ | 9484/11728 [29:07<3:39:02, 5.86s/it] {'loss': 0.4482, 'learning_rate': 1.8594863331028224e-06, 'epoch': 0.81} + 81%|████████ | 9484/11728 [29:07<3:39:02, 5.86s/it] 81%|████████ | 9485/11728 [29:13<3:36:23, 5.79s/it] {'loss': 0.4616, 'learning_rate': 1.8578827277037804e-06, 'epoch': 0.81} + 81%|████████ | 9485/11728 [29:13<3:36:23, 5.79s/it] 81%|████████ | 9486/11728 [29:19<3:33:49, 5.72s/it] {'loss': 0.4512, 'learning_rate': 1.8562797432565926e-06, 'epoch': 0.81} + 81%|████████ | 9486/11728 [29:19<3:33:49, 5.72s/it] 81%|████████ | 9487/11728 [29:25<3:37:05, 5.81s/it] {'loss': 0.4589, 'learning_rate': 1.8546773798835149e-06, 'epoch': 0.81} + 81%|████████ | 9487/11728 [29:25<3:37:05, 5.81s/it] 81%|████████ | 9488/11728 [29:30<3:35:25, 5.77s/it] {'loss': 0.4634, 'learning_rate': 1.8530756377067394e-06, 'epoch': 0.81} + 81%|████████ | 9488/11728 [29:30<3:35:25, 5.77s/it] 81%|████████ | 9489/11728 [29:36<3:34:09, 5.74s/it] {'loss': 0.4626, 'learning_rate': 1.8514745168484317e-06, 'epoch': 0.81} + 81%|████████ | 9489/11728 [29:36<3:34:09, 5.74s/it] 81%|████████ | 9490/11728 [29:42<3:35:44, 5.78s/it] {'loss': 0.4613, 'learning_rate': 1.8498740174306984e-06, 'epoch': 0.81} + 81%|████████ | 9490/11728 [29:42<3:35:44, 5.78s/it] 81%|████████ | 9491/11728 [29:48<3:35:16, 5.77s/it] {'loss': 0.4436, 'learning_rate': 1.8482741395755966e-06, 'epoch': 0.81} + 81%|████████ | 9491/11728 [29:48<3:35:16, 5.77s/it] 81%|████████ | 9492/11728 [29:53<3:36:30, 5.81s/it] {'loss': 0.4573, 'learning_rate': 1.8466748834051374e-06, 'epoch': 0.81} + 81%|████████ | 9492/11728 [29:53<3:36:30, 5.81s/it] 81%|████████ | 9493/11728 [29:59<3:34:53, 5.77s/it] {'loss': 0.4509, 'learning_rate': 1.8450762490412965e-06, 'epoch': 0.81} + 81%|████████ | 9493/11728 [29:59<3:34:53, 5.77s/it] 81%|████████ | 9494/11728 [30:05<3:34:28, 5.76s/it] {'loss': 0.451, 'learning_rate': 1.8434782366059844e-06, 'epoch': 0.81} + 81%|████████ | 9494/11728 [30:05<3:34:28, 5.76s/it] 81%|████████ | 9495/11728 [30:11<3:33:35, 5.74s/it] {'loss': 0.4434, 'learning_rate': 1.8418808462210746e-06, 'epoch': 0.81} + 81%|████████ | 9495/11728 [30:11<3:33:35, 5.74s/it] 81%|████████ | 9496/11728 [30:17<3:37:46, 5.85s/it] {'loss': 0.4573, 'learning_rate': 1.840284078008393e-06, 'epoch': 0.81} + 81%|████████ | 9496/11728 [30:17<3:37:46, 5.85s/it] 81%|████████ | 9497/11728 [30:23<3:39:14, 5.90s/it] {'loss': 0.4449, 'learning_rate': 1.8386879320897077e-06, 'epoch': 0.81} + 81%|████████ | 9497/11728 [30:23<3:39:14, 5.90s/it] 81%|████████ | 9498/11728 [30:29<3:39:08, 5.90s/it] {'loss': 0.4872, 'learning_rate': 1.8370924085867558e-06, 'epoch': 0.81} + 81%|████████ | 9498/11728 [30:29<3:39:08, 5.90s/it] 81%|████████ | 9499/11728 [30:34<3:36:45, 5.83s/it] {'loss': 0.4647, 'learning_rate': 1.8354975076212188e-06, 'epoch': 0.81} + 81%|████████ | 9499/11728 [30:34<3:36:45, 5.83s/it]3 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... +76 AutoResumeHook: Checking whether to suspend...AutoResumeHook: Checking whether to suspend... + +1 AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +0 AutoResumeHook: Checking whether to suspend... + 81%|████████ | 9500/11728 [30:40<3:37:37, 5.86s/it] {'loss': 0.4524, 'learning_rate': 1.8339032293147251e-06, 'epoch': 0.81} + 81%|████████ | 9500/11728 [30:40<3:37:37, 5.86s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-9500/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-9500/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-9500/mm_projector +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/torch/nn/modules/module.py:1802: UserWarning: Positional args are being deprecated, use kwargs instead. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details. + warnings.warn( + 81%|████████ | 9501/11728 [31:16<9:08:36, 14.78s/it] {'loss': 0.4869, 'learning_rate': 1.8323095737888607e-06, 'epoch': 0.81} + 81%|████████ | 9501/11728 [31:16<9:08:36, 14.78s/it] 81%|████████ | 9502/11728 [31:22<7:29:07, 12.11s/it] {'loss': 0.4623, 'learning_rate': 1.8307165411651728e-06, 'epoch': 0.81} + 81%|████████ | 9502/11728 [31:22<7:29:07, 12.11s/it] 81%|████████ | 9503/11728 [31:28<6:20:55, 10.27s/it] {'loss': 0.4764, 'learning_rate': 1.8291241315651442e-06, 'epoch': 0.81} + 81%|████████ | 9503/11728 [31:28<6:20:55, 10.27s/it] 81%|████████ | 9504/11728 [31:34<5:31:56, 8.96s/it] {'loss': 0.4428, 'learning_rate': 1.8275323451102223e-06, 'epoch': 0.81} + 81%|████████ | 9504/11728 [31:34<5:31:56, 8.96s/it] 81%|████████ | 9505/11728 [31:39<4:53:41, 7.93s/it] {'loss': 0.4456, 'learning_rate': 1.8259411819218054e-06, 'epoch': 0.81} + 81%|████████ | 9505/11728 [31:39<4:53:41, 7.93s/it] 81%|████████ | 9506/11728 [31:45<4:28:17, 7.24s/it] {'loss': 0.46, 'learning_rate': 1.8243506421212332e-06, 'epoch': 0.81} + 81%|████████ | 9506/11728 [31:45<4:28:17, 7.24s/it] 81%|████████ | 9507/11728 [31:51<4:12:22, 6.82s/it] {'loss': 0.4379, 'learning_rate': 1.8227607258298175e-06, 'epoch': 0.81} + 81%|████████ | 9507/11728 [31:51<4:12:22, 6.82s/it] 81%|████████ | 9508/11728 [31:56<4:01:52, 6.54s/it] {'loss': 0.4608, 'learning_rate': 1.821171433168809e-06, 'epoch': 0.81} + 81%|████████ | 9508/11728 [31:56<4:01:52, 6.54s/it] 81%|████████ | 9509/11728 [32:02<3:50:55, 6.24s/it] {'loss': 0.4485, 'learning_rate': 1.819582764259411e-06, 'epoch': 0.81} + 81%|████████ | 9509/11728 [32:02<3:50:55, 6.24s/it] 81%|████████ | 9510/11728 [32:08<3:43:56, 6.06s/it] {'loss': 0.4567, 'learning_rate': 1.8179947192227832e-06, 'epoch': 0.81} + 81%|████████ | 9510/11728 [32:08<3:43:56, 6.06s/it] 81%|████████ | 9511/11728 [32:14<3:44:00, 6.06s/it] {'loss': 0.4567, 'learning_rate': 1.8164072981800374e-06, 'epoch': 0.81} + 81%|████████ | 9511/11728 [32:14<3:44:00, 6.06s/it] 81%|████████ | 9512/11728 [32:19<3:40:05, 5.96s/it] {'loss': 0.4681, 'learning_rate': 1.8148205012522357e-06, 'epoch': 0.81} + 81%|████████ | 9512/11728 [32:19<3:40:05, 5.96s/it] 81%|████████ | 9513/11728 [32:25<3:38:50, 5.93s/it] {'loss': 0.4414, 'learning_rate': 1.813234328560396e-06, 'epoch': 0.81} + 81%|████████ | 9513/11728 [32:25<3:38:50, 5.93s/it] 81%|████████ | 9514/11728 [32:31<3:35:36, 5.84s/it] {'loss': 0.4585, 'learning_rate': 1.8116487802254868e-06, 'epoch': 0.81} + 81%|████████ | 9514/11728 [32:31<3:35:36, 5.84s/it] 81%|████████ | 9515/11728 [32:37<3:37:16, 5.89s/it] {'loss': 0.4818, 'learning_rate': 1.8100638563684214e-06, 'epoch': 0.81} + 81%|████████ | 9515/11728 [32:37<3:37:16, 5.89s/it] 81%|████████ | 9516/11728 [32:43<3:36:41, 5.88s/it] {'loss': 0.4604, 'learning_rate': 1.808479557110081e-06, 'epoch': 0.81} + 81%|████████ | 9516/11728 [32:43<3:36:41, 5.88s/it] 81%|████████ | 9517/11728 [32:48<3:32:41, 5.77s/it] {'loss': 0.4641, 'learning_rate': 1.8068958825712912e-06, 'epoch': 0.81} + 81%|████████ | 9517/11728 [32:48<3:32:41, 5.77s/it] 81%|████████ | 9518/11728 [32:54<3:36:04, 5.87s/it] {'loss': 0.4766, 'learning_rate': 1.8053128328728243e-06, 'epoch': 0.81} + 81%|████████ | 9518/11728 [32:54<3:36:04, 5.87s/it] 81%|████████ | 9519/11728 [33:00<3:38:19, 5.93s/it] {'loss': 0.4568, 'learning_rate': 1.8037304081354124e-06, 'epoch': 0.81} + 81%|████████ | 9519/11728 [33:00<3:38:19, 5.93s/it] 81%|████████ | 9520/11728 [33:06<3:35:54, 5.87s/it] {'loss': 0.4428, 'learning_rate': 1.8021486084797368e-06, 'epoch': 0.81} + 81%|████████ | 9520/11728 [33:06<3:35:54, 5.87s/it] 81%|████████ | 9521/11728 [33:12<3:31:12, 5.74s/it] {'loss': 0.4558, 'learning_rate': 1.8005674340264346e-06, 'epoch': 0.81} + 81%|████████ | 9521/11728 [33:12<3:31:12, 5.74s/it] 81%|████████ | 9522/11728 [33:18<3:33:55, 5.82s/it] {'loss': 0.4778, 'learning_rate': 1.798986884896091e-06, 'epoch': 0.81} + 81%|████████ | 9522/11728 [33:18<3:33:55, 5.82s/it] 81%|████████ | 9523/11728 [33:24<3:36:45, 5.90s/it] {'loss': 0.442, 'learning_rate': 1.7974069612092481e-06, 'epoch': 0.81} + 81%|████████ | 9523/11728 [33:24<3:36:45, 5.90s/it] 81%|████████ | 9524/11728 [33:29<3:34:25, 5.84s/it] {'loss': 0.461, 'learning_rate': 1.7958276630863903e-06, 'epoch': 0.81} + 81%|████████ | 9524/11728 [33:29<3:34:25, 5.84s/it] 81%|████████ | 9525/11728 [33:35<3:36:00, 5.88s/it] {'loss': 0.451, 'learning_rate': 1.7942489906479687e-06, 'epoch': 0.81} + 81%|████████ | 9525/11728 [33:35<3:36:00, 5.88s/it] 81%|████████ | 9526/11728 [33:41<3:34:38, 5.85s/it] {'loss': 0.4485, 'learning_rate': 1.7926709440143797e-06, 'epoch': 0.81} + 81%|████████ | 9526/11728 [33:41<3:34:38, 5.85s/it] 81%|████████ | 9527/11728 [33:47<3:35:12, 5.87s/it] {'loss': 0.4493, 'learning_rate': 1.7910935233059667e-06, 'epoch': 0.81} + 81%|████████ | 9527/11728 [33:47<3:35:12, 5.87s/it] 81%|████████ | 9528/11728 [33:53<3:33:56, 5.83s/it] {'loss': 0.455, 'learning_rate': 1.7895167286430326e-06, 'epoch': 0.81} + 81%|████████ | 9528/11728 [33:53<3:33:56, 5.83s/it] 81%|████████▏ | 9529/11728 [33:59<3:34:00, 5.84s/it] {'loss': 0.4614, 'learning_rate': 1.7879405601458311e-06, 'epoch': 0.81} + 81%|████████▏ | 9529/11728 [33:59<3:34:00, 5.84s/it] 81%|████████▏ | 9530/11728 [34:05<3:35:08, 5.87s/it] {'loss': 0.4534, 'learning_rate': 1.786365017934566e-06, 'epoch': 0.81} + 81%|████████▏ | 9530/11728 [34:05<3:35:08, 5.87s/it] 81%|████████▏ | 9531/11728 [34:10<3:33:16, 5.82s/it] {'loss': 0.4658, 'learning_rate': 1.7847901021293956e-06, 'epoch': 0.81} + 81%|████████▏ | 9531/11728 [34:10<3:33:16, 5.82s/it] 81%|████████▏ | 9532/11728 [34:16<3:32:55, 5.82s/it] {'loss': 0.4644, 'learning_rate': 1.7832158128504328e-06, 'epoch': 0.81} + 81%|████████▏ | 9532/11728 [34:16<3:32:55, 5.82s/it] 81%|████████▏ | 9533/11728 [34:22<3:29:15, 5.72s/it] {'loss': 0.4563, 'learning_rate': 1.7816421502177328e-06, 'epoch': 0.81} + 81%|████████▏ | 9533/11728 [34:22<3:29:15, 5.72s/it] 81%|████████▏ | 9534/11728 [34:27<3:30:07, 5.75s/it] {'loss': 0.4533, 'learning_rate': 1.7800691143513104e-06, 'epoch': 0.81} + 81%|████████▏ | 9534/11728 [34:27<3:30:07, 5.75s/it] 81%|████████▏ | 9535/11728 [34:33<3:28:44, 5.71s/it] {'loss': 0.4626, 'learning_rate': 1.77849670537114e-06, 'epoch': 0.81} + 81%|████████▏ | 9535/11728 [34:33<3:28:44, 5.71s/it] 81%|████████▏ | 9536/11728 [34:39<3:27:41, 5.68s/it] {'loss': 0.4632, 'learning_rate': 1.776924923397132e-06, 'epoch': 0.81} + 81%|████████▏ | 9536/11728 [34:39<3:27:41, 5.68s/it] 81%|████████▏ | 9537/11728 [34:44<3:28:09, 5.70s/it] {'loss': 0.4541, 'learning_rate': 1.7753537685491596e-06, 'epoch': 0.81} + 81%|████████▏ | 9537/11728 [34:44<3:28:09, 5.70s/it] 81%|████████▏ | 9538/11728 [34:50<3:26:56, 5.67s/it] {'loss': 0.4541, 'learning_rate': 1.7737832409470458e-06, 'epoch': 0.81} + 81%|████████▏ | 9538/11728 [34:50<3:26:56, 5.67s/it] 81%|████████▏ | 9539/11728 [34:56<3:26:45, 5.67s/it] {'loss': 0.4439, 'learning_rate': 1.7722133407105656e-06, 'epoch': 0.81} + 81%|████████▏ | 9539/11728 [34:56<3:26:45, 5.67s/it] 81%|████████▏ | 9540/11728 [35:01<3:27:54, 5.70s/it] {'loss': 0.4606, 'learning_rate': 1.7706440679594462e-06, 'epoch': 0.81} + 81%|████████▏ | 9540/11728 [35:01<3:27:54, 5.70s/it] 81%|████████▏ | 9541/11728 [35:08<3:31:26, 5.80s/it] {'loss': 0.444, 'learning_rate': 1.7690754228133688e-06, 'epoch': 0.81} + 81%|████████▏ | 9541/11728 [35:08<3:31:26, 5.80s/it] 81%|████████▏ | 9542/11728 [35:13<3:30:22, 5.77s/it] {'loss': 0.4657, 'learning_rate': 1.7675074053919606e-06, 'epoch': 0.81} + 81%|████████▏ | 9542/11728 [35:13<3:30:22, 5.77s/it] 81%|████████▏ | 9543/11728 [35:19<3:31:16, 5.80s/it] {'loss': 0.4828, 'learning_rate': 1.7659400158148043e-06, 'epoch': 0.81} + 81%|████████▏ | 9543/11728 [35:19<3:31:16, 5.80s/it] 81%|████████▏ | 9544/11728 [35:25<3:30:59, 5.80s/it] {'loss': 0.4599, 'learning_rate': 1.7643732542014437e-06, 'epoch': 0.81} + 81%|████████▏ | 9544/11728 [35:25<3:30:59, 5.80s/it] 81%|████████▏ | 9545/11728 [35:30<3:28:57, 5.74s/it] {'loss': 0.4915, 'learning_rate': 1.7628071206713582e-06, 'epoch': 0.81} + 81%|████████▏ | 9545/11728 [35:30<3:28:57, 5.74s/it] 81%|████████▏ | 9546/11728 [35:36<3:27:35, 5.71s/it] {'loss': 0.438, 'learning_rate': 1.7612416153439916e-06, 'epoch': 0.81} + 81%|████████▏ | 9546/11728 [35:36<3:27:35, 5.71s/it] 81%|████████▏ | 9547/11728 [35:42<3:27:27, 5.71s/it] {'loss': 0.4686, 'learning_rate': 1.7596767383387359e-06, 'epoch': 0.81} + 81%|████████▏ | 9547/11728 [35:42<3:27:27, 5.71s/it] 81%|████████▏ | 9548/11728 [35:47<3:25:41, 5.66s/it] {'loss': 0.4649, 'learning_rate': 1.7581124897749335e-06, 'epoch': 0.81} + 81%|████████▏ | 9548/11728 [35:47<3:25:41, 5.66s/it] 81%|████████▏ | 9549/11728 [35:53<3:27:41, 5.72s/it] {'loss': 0.4428, 'learning_rate': 1.7565488697718814e-06, 'epoch': 0.81} + 81%|████████▏ | 9549/11728 [35:53<3:27:41, 5.72s/it]6 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +20 AutoResumeHook: Checking whether to suspend... + 7 AutoResumeHook: Checking whether to suspend... +AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... + 81%|████████▏ | 9550/11728 [35:59<3:26:46, 5.70s/it] {'loss': 0.4537, 'learning_rate': 1.7549858784488317e-06, 'epoch': 0.81} + 81%|████████▏ | 9550/11728 [35:59<3:26:46, 5.70s/it] 81%|████████▏ | 9551/11728 [36:04<3:25:23, 5.66s/it] {'loss': 0.4468, 'learning_rate': 1.7534235159249768e-06, 'epoch': 0.81} + 81%|████████▏ | 9551/11728 [36:04<3:25:23, 5.66s/it] 81%|████████▏ | 9552/11728 [36:11<3:30:12, 5.80s/it] {'loss': 0.4437, 'learning_rate': 1.7518617823194705e-06, 'epoch': 0.81} + 81%|████████▏ | 9552/11728 [36:11<3:30:12, 5.80s/it] 81%|████████▏ | 9553/11728 [36:16<3:26:36, 5.70s/it] {'loss': 0.456, 'learning_rate': 1.7503006777514254e-06, 'epoch': 0.81} + 81%|████████▏ | 9553/11728 [36:16<3:26:36, 5.70s/it] 81%|████████▏ | 9554/11728 [36:22<3:28:13, 5.75s/it] {'loss': 0.4803, 'learning_rate': 1.7487402023398891e-06, 'epoch': 0.81} + 81%|████████▏ | 9554/11728 [36:22<3:28:13, 5.75s/it] 81%|████████▏ | 9555/11728 [36:28<3:32:36, 5.87s/it] {'loss': 0.453, 'learning_rate': 1.7471803562038737e-06, 'epoch': 0.81} + 81%|████████▏ | 9555/11728 [36:28<3:32:36, 5.87s/it] 81%|████████▏ | 9556/11728 [36:34<3:32:49, 5.88s/it] {'loss': 0.463, 'learning_rate': 1.7456211394623379e-06, 'epoch': 0.81} + 81%|████████▏ | 9556/11728 [36:34<3:32:49, 5.88s/it] 81%|████████▏ | 9557/11728 [36:40<3:31:08, 5.84s/it] {'loss': 0.4525, 'learning_rate': 1.7440625522341958e-06, 'epoch': 0.81} + 81%|████████▏ | 9557/11728 [36:40<3:31:08, 5.84s/it] 81%|████████▏ | 9558/11728 [36:46<3:31:10, 5.84s/it] {'loss': 0.4537, 'learning_rate': 1.74250459463831e-06, 'epoch': 0.81} + 81%|████████▏ | 9558/11728 [36:46<3:31:10, 5.84s/it] 82%|████████▏ | 9559/11728 [36:51<3:30:27, 5.82s/it] {'loss': 0.4485, 'learning_rate': 1.7409472667935012e-06, 'epoch': 0.82} + 82%|████████▏ | 9559/11728 [36:51<3:30:27, 5.82s/it] 82%|████████▏ | 9560/11728 [36:57<3:28:20, 5.77s/it] {'loss': 0.4626, 'learning_rate': 1.7393905688185319e-06, 'epoch': 0.82} + 82%|████████▏ | 9560/11728 [36:57<3:28:20, 5.77s/it] 82%|████████▏ | 9561/11728 [37:02<3:25:41, 5.70s/it] {'loss': 0.4505, 'learning_rate': 1.737834500832122e-06, 'epoch': 0.82} + 82%|████████▏ | 9561/11728 [37:02<3:25:41, 5.70s/it] 82%|████████▏ | 9562/11728 [37:08<3:26:54, 5.73s/it] {'loss': 0.4346, 'learning_rate': 1.7362790629529513e-06, 'epoch': 0.82} + 82%|████████▏ | 9562/11728 [37:08<3:26:54, 5.73s/it] 82%|████████▏ | 9563/11728 [37:14<3:27:39, 5.75s/it] {'loss': 0.4916, 'learning_rate': 1.734724255299637e-06, 'epoch': 0.82} + 82%|████████▏ | 9563/11728 [37:14<3:27:39, 5.75s/it] 82%|████████▏ | 9564/11728 [37:20<3:27:53, 5.76s/it] {'loss': 0.4376, 'learning_rate': 1.7331700779907579e-06, 'epoch': 0.82} + 82%|████████▏ | 9564/11728 [37:20<3:27:53, 5.76s/it] 82%|████████▏ | 9565/11728 [37:26<3:27:00, 5.74s/it] {'loss': 0.4482, 'learning_rate': 1.7316165311448407e-06, 'epoch': 0.82} + 82%|████████▏ | 9565/11728 [37:26<3:27:00, 5.74s/it] 82%|████████▏ | 9566/11728 [37:31<3:25:31, 5.70s/it] {'loss': 0.4717, 'learning_rate': 1.7300636148803674e-06, 'epoch': 0.82} + 82%|████████▏ | 9566/11728 [37:31<3:25:31, 5.70s/it] 82%|████████▏ | 9567/11728 [37:37<3:25:18, 5.70s/it] {'loss': 0.4583, 'learning_rate': 1.7285113293157673e-06, 'epoch': 0.82} + 82%|████████▏ | 9567/11728 [37:37<3:25:18, 5.70s/it] 82%|████████▏ | 9568/11728 [37:43<3:29:19, 5.81s/it] {'loss': 0.4456, 'learning_rate': 1.7269596745694295e-06, 'epoch': 0.82} + 82%|████████▏ | 9568/11728 [37:43<3:29:19, 5.81s/it] 82%|████████▏ | 9569/11728 [37:49<3:34:20, 5.96s/it] {'loss': 0.45, 'learning_rate': 1.7254086507596834e-06, 'epoch': 0.82} + 82%|████████▏ | 9569/11728 [37:49<3:34:20, 5.96s/it] 82%|████████▏ | 9570/11728 [37:55<3:34:46, 5.97s/it] {'loss': 0.4685, 'learning_rate': 1.7238582580048157e-06, 'epoch': 0.82} + 82%|████████▏ | 9570/11728 [37:55<3:34:46, 5.97s/it] 82%|████████▏ | 9571/11728 [38:01<3:30:59, 5.87s/it] {'loss': 0.44, 'learning_rate': 1.722308496423074e-06, 'epoch': 0.82} + 82%|████████▏ | 9571/11728 [38:01<3:30:59, 5.87s/it] 82%|████████▏ | 9572/11728 [38:07<3:34:48, 5.98s/it] {'loss': 0.4647, 'learning_rate': 1.7207593661326427e-06, 'epoch': 0.82} + 82%|████████▏ | 9572/11728 [38:07<3:34:48, 5.98s/it] 82%|████████▏ | 9573/11728 [38:13<3:34:20, 5.97s/it] {'loss': 0.4576, 'learning_rate': 1.7192108672516672e-06, 'epoch': 0.82} + 82%|████████▏ | 9573/11728 [38:13<3:34:20, 5.97s/it] 82%|████████▏ | 9574/11728 [38:19<3:36:23, 6.03s/it] {'loss': 0.4736, 'learning_rate': 1.7176629998982408e-06, 'epoch': 0.82} + 82%|████████▏ | 9574/11728 [38:19<3:36:23, 6.03s/it] 82%|████████▏ | 9575/11728 [38:25<3:35:29, 6.01s/it] {'loss': 0.4352, 'learning_rate': 1.7161157641904136e-06, 'epoch': 0.82} + 82%|████████▏ | 9575/11728 [38:25<3:35:29, 6.01s/it] 82%|████████▏ | 9576/11728 [38:31<3:32:49, 5.93s/it] {'loss': 0.4801, 'learning_rate': 1.7145691602461812e-06, 'epoch': 0.82} + 82%|████████▏ | 9576/11728 [38:31<3:32:49, 5.93s/it] 82%|████████▏ | 9577/11728 [38:37<3:30:08, 5.86s/it] {'loss': 0.4572, 'learning_rate': 1.713023188183498e-06, 'epoch': 0.82} + 82%|████████▏ | 9577/11728 [38:37<3:30:08, 5.86s/it] 82%|████████▏ | 9578/11728 [38:42<3:27:43, 5.80s/it] {'loss': 0.4373, 'learning_rate': 1.711477848120261e-06, 'epoch': 0.82} + 82%|████████▏ | 9578/11728 [38:42<3:27:43, 5.80s/it] 82%|████████▏ | 9579/11728 [38:48<3:25:25, 5.74s/it] {'loss': 0.4499, 'learning_rate': 1.7099331401743247e-06, 'epoch': 0.82} + 82%|████████▏ | 9579/11728 [38:48<3:25:25, 5.74s/it] 82%|████████▏ | 9580/11728 [38:54<3:27:38, 5.80s/it] {'loss': 0.4549, 'learning_rate': 1.7083890644635015e-06, 'epoch': 0.82} + 82%|████████▏ | 9580/11728 [38:54<3:27:38, 5.80s/it] 82%|████████▏ | 9581/11728 [39:00<3:28:27, 5.83s/it] {'loss': 0.4578, 'learning_rate': 1.706845621105543e-06, 'epoch': 0.82} + 82%|████████▏ | 9581/11728 [39:00<3:28:27, 5.83s/it] 82%|████████▏ | 9582/11728 [39:06<3:30:40, 5.89s/it] {'loss': 0.4566, 'learning_rate': 1.7053028102181601e-06, 'epoch': 0.82} + 82%|████████▏ | 9582/11728 [39:06<3:30:40, 5.89s/it] 82%|████████▏ | 9583/11728 [39:12<3:29:00, 5.85s/it] {'loss': 0.4669, 'learning_rate': 1.7037606319190137e-06, 'epoch': 0.82} + 82%|████████▏ | 9583/11728 [39:12<3:29:00, 5.85s/it] 82%|████████▏ | 9584/11728 [39:17<3:24:46, 5.73s/it] {'loss': 0.4483, 'learning_rate': 1.7022190863257182e-06, 'epoch': 0.82} + 82%|████████▏ | 9584/11728 [39:17<3:24:46, 5.73s/it] 82%|████████▏ | 9585/11728 [39:23<3:25:24, 5.75s/it] {'loss': 0.4351, 'learning_rate': 1.7006781735558364e-06, 'epoch': 0.82} + 82%|████████▏ | 9585/11728 [39:23<3:25:24, 5.75s/it] 82%|████████▏ | 9586/11728 [39:28<3:24:09, 5.72s/it] {'loss': 0.4479, 'learning_rate': 1.6991378937268888e-06, 'epoch': 0.82} + 82%|████████▏ | 9586/11728 [39:28<3:24:09, 5.72s/it] 82%|████████▏ | 9587/11728 [39:34<3:21:15, 5.64s/it] {'loss': 0.464, 'learning_rate': 1.6975982469563369e-06, 'epoch': 0.82} + 82%|████████▏ | 9587/11728 [39:34<3:21:15, 5.64s/it] 82%|████████▏ | 9588/11728 [39:40<3:24:31, 5.73s/it] {'loss': 0.4645, 'learning_rate': 1.6960592333616055e-06, 'epoch': 0.82} + 82%|████████▏ | 9588/11728 [39:40<3:24:31, 5.73s/it] 82%|████████▏ | 9589/11728 [39:45<3:22:39, 5.68s/it] {'loss': 0.4612, 'learning_rate': 1.6945208530600644e-06, 'epoch': 0.82} + 82%|████████▏ | 9589/11728 [39:45<3:22:39, 5.68s/it] 82%|████████▏ | 9590/11728 [39:51<3:25:18, 5.76s/it] {'loss': 0.4685, 'learning_rate': 1.6929831061690371e-06, 'epoch': 0.82} + 82%|████████▏ | 9590/11728 [39:51<3:25:18, 5.76s/it] 82%|████████▏ | 9591/11728 [39:57<3:24:18, 5.74s/it] {'loss': 0.4668, 'learning_rate': 1.6914459928057992e-06, 'epoch': 0.82} + 82%|████████▏ | 9591/11728 [39:57<3:24:18, 5.74s/it] 82%|████████▏ | 9592/11728 [40:03<3:23:50, 5.73s/it] {'loss': 0.4383, 'learning_rate': 1.6899095130875775e-06, 'epoch': 0.82} + 82%|████████▏ | 9592/11728 [40:03<3:23:50, 5.73s/it] 82%|████████▏ | 9593/11728 [40:08<3:22:39, 5.70s/it] {'loss': 0.4579, 'learning_rate': 1.6883736671315488e-06, 'epoch': 0.82} + 82%|████████▏ | 9593/11728 [40:08<3:22:39, 5.70s/it] 82%|████████▏ | 9594/11728 [40:14<3:23:46, 5.73s/it] {'loss': 0.4433, 'learning_rate': 1.6868384550548455e-06, 'epoch': 0.82} + 82%|████████▏ | 9594/11728 [40:14<3:23:46, 5.73s/it] 82%|████████▏ | 9595/11728 [40:20<3:25:21, 5.78s/it] {'loss': 0.4463, 'learning_rate': 1.6853038769745466e-06, 'epoch': 0.82} + 82%|████████▏ | 9595/11728 [40:20<3:25:21, 5.78s/it] 82%|████████▏ | 9596/11728 [40:26<3:27:23, 5.84s/it] {'loss': 0.4805, 'learning_rate': 1.6837699330076906e-06, 'epoch': 0.82} + 82%|████████▏ | 9596/11728 [40:26<3:27:23, 5.84s/it] 82%|████████▏ | 9597/11728 [40:32<3:29:10, 5.89s/it] {'loss': 0.4571, 'learning_rate': 1.682236623271256e-06, 'epoch': 0.82} + 82%|████████▏ | 9597/11728 [40:32<3:29:10, 5.89s/it] 82%|████████▏ | 9598/11728 [40:38<3:28:03, 5.86s/it] {'loss': 0.4282, 'learning_rate': 1.680703947882182e-06, 'epoch': 0.82} + 82%|████████▏ | 9598/11728 [40:38<3:28:03, 5.86s/it] 82%|████████▏ | 9599/11728 [40:43<3:25:45, 5.80s/it] {'loss': 0.4545, 'learning_rate': 1.6791719069573563e-06, 'epoch': 0.82} + 82%|████████▏ | 9599/11728 [40:43<3:25:45, 5.80s/it]5 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend...3 + AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +0 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... + 82%|████████▏ | 9600/11728 [40:50<3:28:21, 5.87s/it] {'loss': 0.4698, 'learning_rate': 1.6776405006136199e-06, 'epoch': 0.82} + 82%|████████▏ | 9600/11728 [40:50<3:28:21, 5.87s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-9600/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-9600/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-9600/mm_projector +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/torch/nn/modules/module.py:1802: UserWarning: Positional args are being deprecated, use kwargs instead. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details. + warnings.warn( + 82%|████████▏ | 9601/11728 [41:22<8:08:01, 13.77s/it] {'loss': 0.4505, 'learning_rate': 1.6761097289677642e-06, 'epoch': 0.82} + 82%|████████▏ | 9601/11728 [41:22<8:08:01, 13.77s/it] 82%|████████▏ | 9602/11728 [41:27<6:42:06, 11.35s/it] {'loss': 0.4576, 'learning_rate': 1.6745795921365314e-06, 'epoch': 0.82} + 82%|████████▏ | 9602/11728 [41:27<6:42:06, 11.35s/it] 82%|████████▏ | 9603/11728 [41:33<5:45:23, 9.75s/it] {'loss': 0.4697, 'learning_rate': 1.6730500902366165e-06, 'epoch': 0.82} + 82%|████████▏ | 9603/11728 [41:33<5:45:23, 9.75s/it] 82%|████████▏ | 9604/11728 [41:39<5:03:17, 8.57s/it] {'loss': 0.4658, 'learning_rate': 1.6715212233846656e-06, 'epoch': 0.82} + 82%|████████▏ | 9604/11728 [41:39<5:03:17, 8.57s/it] 82%|████████▏ | 9605/11728 [41:45<4:36:53, 7.83s/it] {'loss': 0.4696, 'learning_rate': 1.669992991697279e-06, 'epoch': 0.82} + 82%|████████▏ | 9605/11728 [41:45<4:36:53, 7.83s/it] 82%|████████▏ | 9606/11728 [41:51<4:12:46, 7.15s/it] {'loss': 0.4627, 'learning_rate': 1.6684653952910013e-06, 'epoch': 0.82} + 82%|████████▏ | 9606/11728 [41:51<4:12:46, 7.15s/it] 82%|████████▏ | 9607/11728 [41:57<4:00:15, 6.80s/it] {'loss': 0.4384, 'learning_rate': 1.6669384342823347e-06, 'epoch': 0.82} + 82%|████████▏ | 9607/11728 [41:57<4:00:15, 6.80s/it] 82%|████████▏ | 9608/11728 [42:03<3:50:54, 6.54s/it] {'loss': 0.4495, 'learning_rate': 1.665412108787734e-06, 'epoch': 0.82} + 82%|████████▏ | 9608/11728 [42:03<3:50:54, 6.54s/it] 82%|████████▏ | 9609/11728 [42:08<3:41:41, 6.28s/it] {'loss': 0.4551, 'learning_rate': 1.6638864189236015e-06, 'epoch': 0.82} + 82%|████████▏ | 9609/11728 [42:08<3:41:41, 6.28s/it] 82%|████████▏ | 9610/11728 [42:14<3:34:02, 6.06s/it] {'loss': 0.4489, 'learning_rate': 1.662361364806292e-06, 'epoch': 0.82} + 82%|████████▏ | 9610/11728 [42:14<3:34:02, 6.06s/it] 82%|████████▏ | 9611/11728 [42:20<3:28:22, 5.91s/it] {'loss': 0.4356, 'learning_rate': 1.6608369465521169e-06, 'epoch': 0.82} + 82%|████████▏ | 9611/11728 [42:20<3:28:22, 5.91s/it] 82%|████████▏ | 9612/11728 [42:25<3:28:24, 5.91s/it] {'loss': 0.483, 'learning_rate': 1.6593131642773252e-06, 'epoch': 0.82} + 82%|████████▏ | 9612/11728 [42:26<3:28:24, 5.91s/it] 82%|████████▏ | 9613/11728 [42:31<3:25:48, 5.84s/it] {'loss': 0.464, 'learning_rate': 1.6577900180981366e-06, 'epoch': 0.82} + 82%|████████▏ | 9613/11728 [42:31<3:25:48, 5.84s/it] 82%|████████▏ | 9614/11728 [42:37<3:24:15, 5.80s/it] {'loss': 0.4644, 'learning_rate': 1.6562675081307101e-06, 'epoch': 0.82} + 82%|████████▏ | 9614/11728 [42:37<3:24:15, 5.80s/it] 82%|████████▏ | 9615/11728 [42:43<3:24:28, 5.81s/it] {'loss': 0.4681, 'learning_rate': 1.654745634491156e-06, 'epoch': 0.82} + 82%|████████▏ | 9615/11728 [42:43<3:24:28, 5.81s/it] 82%|████████▏ | 9616/11728 [42:49<3:24:56, 5.82s/it] {'loss': 0.459, 'learning_rate': 1.6532243972955397e-06, 'epoch': 0.82} + 82%|████████▏ | 9616/11728 [42:49<3:24:56, 5.82s/it] 82%|████████▏ | 9617/11728 [42:54<3:21:57, 5.74s/it] {'loss': 0.4344, 'learning_rate': 1.651703796659878e-06, 'epoch': 0.82} + 82%|████████▏ | 9617/11728 [42:54<3:21:57, 5.74s/it] 82%|████████▏ | 9618/11728 [43:00<3:23:19, 5.78s/it] {'loss': 0.478, 'learning_rate': 1.6501838327001374e-06, 'epoch': 0.82} + 82%|████████▏ | 9618/11728 [43:00<3:23:19, 5.78s/it] 82%|████████▏ | 9619/11728 [43:06<3:24:07, 5.81s/it] {'loss': 0.4612, 'learning_rate': 1.6486645055322381e-06, 'epoch': 0.82} + 82%|████████▏ | 9619/11728 [43:06<3:24:07, 5.81s/it] 82%|████████▏ | 9620/11728 [43:11<3:22:01, 5.75s/it] {'loss': 0.4539, 'learning_rate': 1.647145815272051e-06, 'epoch': 0.82} + 82%|████████▏ | 9620/11728 [43:11<3:22:01, 5.75s/it] 82%|████████▏ | 9621/11728 [43:17<3:21:38, 5.74s/it] {'loss': 0.4436, 'learning_rate': 1.645627762035391e-06, 'epoch': 0.82} + 82%|████████▏ | 9621/11728 [43:17<3:21:38, 5.74s/it] 82%|████████▏ | 9622/11728 [43:23<3:18:26, 5.65s/it] {'loss': 0.4543, 'learning_rate': 1.6441103459380392e-06, 'epoch': 0.82} + 82%|████████▏ | 9622/11728 [43:23<3:18:26, 5.65s/it] 82%|████████▏ | 9623/11728 [43:28<3:17:08, 5.62s/it] {'loss': 0.4554, 'learning_rate': 1.6425935670957194e-06, 'epoch': 0.82} + 82%|████████▏ | 9623/11728 [43:28<3:17:08, 5.62s/it] 82%|████████▏ | 9624/11728 [43:34<3:19:28, 5.69s/it] {'loss': 0.4553, 'learning_rate': 1.6410774256241036e-06, 'epoch': 0.82} + 82%|████████▏ | 9624/11728 [43:34<3:19:28, 5.69s/it] 82%|████████▏ | 9625/11728 [43:40<3:23:45, 5.81s/it] {'loss': 0.4561, 'learning_rate': 1.6395619216388204e-06, 'epoch': 0.82} + 82%|████████▏ | 9625/11728 [43:40<3:23:45, 5.81s/it] 82%|████████▏ | 9626/11728 [43:46<3:24:12, 5.83s/it] {'loss': 0.4668, 'learning_rate': 1.6380470552554483e-06, 'epoch': 0.82} + 82%|████████▏ | 9626/11728 [43:46<3:24:12, 5.83s/it] 82%|████████▏ | 9627/11728 [43:52<3:25:47, 5.88s/it] {'loss': 0.4517, 'learning_rate': 1.6365328265895186e-06, 'epoch': 0.82} + 82%|████████▏ | 9627/11728 [43:52<3:25:47, 5.88s/it] 82%|████████▏ | 9628/11728 [43:58<3:26:50, 5.91s/it] {'loss': 0.4706, 'learning_rate': 1.635019235756511e-06, 'epoch': 0.82} + 82%|████████▏ | 9628/11728 [43:58<3:26:50, 5.91s/it] 82%|████████▏ | 9629/11728 [44:04<3:23:41, 5.82s/it] {'loss': 0.4543, 'learning_rate': 1.633506282871863e-06, 'epoch': 0.82} + 82%|████████▏ | 9629/11728 [44:04<3:23:41, 5.82s/it] 82%|████████▏ | 9630/11728 [44:09<3:21:43, 5.77s/it] {'loss': 0.4463, 'learning_rate': 1.631993968050949e-06, 'epoch': 0.82} + 82%|████████▏ | 9630/11728 [44:09<3:21:43, 5.77s/it] 82%|████████▏ | 9631/11728 [44:15<3:21:23, 5.76s/it] {'loss': 0.4422, 'learning_rate': 1.6304822914091134e-06, 'epoch': 0.82} + 82%|████████▏ | 9631/11728 [44:15<3:21:23, 5.76s/it] 82%|████████▏ | 9632/11728 [44:21<3:21:46, 5.78s/it] {'loss': 0.4495, 'learning_rate': 1.628971253061642e-06, 'epoch': 0.82} + 82%|████████▏ | 9632/11728 [44:21<3:21:46, 5.78s/it] 82%|████████▏ | 9633/11728 [44:27<3:21:08, 5.76s/it] {'loss': 0.447, 'learning_rate': 1.6274608531237679e-06, 'epoch': 0.82} + 82%|████████▏ | 9633/11728 [44:27<3:21:08, 5.76s/it] 82%|████████▏ | 9634/11728 [44:32<3:20:29, 5.74s/it] {'loss': 0.4475, 'learning_rate': 1.6259510917106847e-06, 'epoch': 0.82} + 82%|████████▏ | 9634/11728 [44:32<3:20:29, 5.74s/it] 82%|████████▏ | 9635/11728 [44:38<3:19:21, 5.72s/it] {'loss': 0.4478, 'learning_rate': 1.6244419689375313e-06, 'epoch': 0.82} + 82%|████████▏ | 9635/11728 [44:38<3:19:21, 5.72s/it] 82%|████████▏ | 9636/11728 [44:44<3:18:36, 5.70s/it] {'loss': 0.4653, 'learning_rate': 1.6229334849194001e-06, 'epoch': 0.82} + 82%|████████▏ | 9636/11728 [44:44<3:18:36, 5.70s/it] 82%|████████▏ | 9637/11728 [44:49<3:19:09, 5.71s/it] {'loss': 0.4377, 'learning_rate': 1.6214256397713347e-06, 'epoch': 0.82} + 82%|████████▏ | 9637/11728 [44:49<3:19:09, 5.71s/it] 82%|████████▏ | 9638/11728 [44:55<3:21:12, 5.78s/it] {'loss': 0.462, 'learning_rate': 1.6199184336083319e-06, 'epoch': 0.82} + 82%|████████▏ | 9638/11728 [44:55<3:21:12, 5.78s/it] 82%|████████▏ | 9639/11728 [45:01<3:21:50, 5.80s/it] {'loss': 0.4546, 'learning_rate': 1.6184118665453296e-06, 'epoch': 0.82} + 82%|████████▏ | 9639/11728 [45:01<3:21:50, 5.80s/it] 82%|████████▏ | 9640/11728 [45:07<3:22:21, 5.82s/it] {'loss': 0.4544, 'learning_rate': 1.6169059386972342e-06, 'epoch': 0.82} + 82%|████████▏ | 9640/11728 [45:07<3:22:21, 5.82s/it] 82%|████████▏ | 9641/11728 [45:13<3:20:36, 5.77s/it] {'loss': 0.4543, 'learning_rate': 1.615400650178891e-06, 'epoch': 0.82} + 82%|████████▏ | 9641/11728 [45:13<3:20:36, 5.77s/it] 82%|████████▏ | 9642/11728 [45:19<3:22:41, 5.83s/it] {'loss': 0.4622, 'learning_rate': 1.6138960011050974e-06, 'epoch': 0.82} + 82%|████████▏ | 9642/11728 [45:19<3:22:41, 5.83s/it] 82%|████████▏ | 9643/11728 [45:25<3:24:25, 5.88s/it] {'loss': 0.4656, 'learning_rate': 1.612391991590606e-06, 'epoch': 0.82} + 82%|████████▏ | 9643/11728 [45:25<3:24:25, 5.88s/it] 82%|████████▏ | 9644/11728 [45:30<3:21:32, 5.80s/it] {'loss': 0.4641, 'learning_rate': 1.6108886217501184e-06, 'epoch': 0.82} + 82%|████████▏ | 9644/11728 [45:30<3:21:32, 5.80s/it] 82%|████████▏ | 9645/11728 [45:36<3:20:49, 5.78s/it] {'loss': 0.4585, 'learning_rate': 1.6093858916982884e-06, 'epoch': 0.82} + 82%|████████▏ | 9645/11728 [45:36<3:20:49, 5.78s/it] 82%|████████▏ | 9646/11728 [45:42<3:21:22, 5.80s/it] {'loss': 0.434, 'learning_rate': 1.607883801549719e-06, 'epoch': 0.82} + 82%|████████▏ | 9646/11728 [45:42<3:21:22, 5.80s/it] 82%|████████▏ | 9647/11728 [45:48<3:21:14, 5.80s/it] {'loss': 0.4595, 'learning_rate': 1.6063823514189703e-06, 'epoch': 0.82} + 82%|████████▏ | 9647/11728 [45:48<3:21:14, 5.80s/it] 82%|████████▏ | 9648/11728 [45:53<3:20:17, 5.78s/it] {'loss': 0.4683, 'learning_rate': 1.60488154142054e-06, 'epoch': 0.82} + 82%|████████▏ | 9648/11728 [45:53<3:20:17, 5.78s/it] 82%|████████▏ | 9649/11728 [45:59<3:19:36, 5.76s/it] {'loss': 0.4717, 'learning_rate': 1.603381371668895e-06, 'epoch': 0.82} + 82%|████████▏ | 9649/11728 [45:59<3:19:36, 5.76s/it]56 AutoResumeHook: Checking whether to suspend...AutoResumeHook: Checking whether to suspend... + +7 AutoResumeHook: Checking whether to suspend... +03 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... + 82%|████████▏ | 9650/11728 [46:04<3:16:48, 5.68s/it]1 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4232, 'learning_rate': 1.6018818422784433e-06, 'epoch': 0.82} + 82%|████████▏ | 9650/11728 [46:04<3:16:48, 5.68s/it] 82%|████████▏ | 9651/11728 [46:10<3:18:33, 5.74s/it] {'loss': 0.4502, 'learning_rate': 1.6003829533635417e-06, 'epoch': 0.82} + 82%|████████▏ | 9651/11728 [46:10<3:18:33, 5.74s/it] 82%|████████▏ | 9652/11728 [46:16<3:17:44, 5.72s/it] {'loss': 0.4503, 'learning_rate': 1.5988847050385037e-06, 'epoch': 0.82} + 82%|████████▏ | 9652/11728 [46:16<3:17:44, 5.72s/it] 82%|████████▏ | 9653/11728 [46:22<3:18:43, 5.75s/it] {'loss': 0.4496, 'learning_rate': 1.5973870974175909e-06, 'epoch': 0.82} + 82%|████████▏ | 9653/11728 [46:22<3:18:43, 5.75s/it] 82%|████████▏ | 9654/11728 [46:28<3:18:29, 5.74s/it] {'loss': 0.4682, 'learning_rate': 1.5958901306150177e-06, 'epoch': 0.82} + 82%|████████▏ | 9654/11728 [46:28<3:18:29, 5.74s/it] 82%|████████▏ | 9655/11728 [46:34<3:21:01, 5.82s/it] {'loss': 0.4697, 'learning_rate': 1.5943938047449493e-06, 'epoch': 0.82} + 82%|████████▏ | 9655/11728 [46:34<3:21:01, 5.82s/it] 82%|████████▏ | 9656/11728 [46:39<3:20:35, 5.81s/it] {'loss': 0.4554, 'learning_rate': 1.5928981199215044e-06, 'epoch': 0.82} + 82%|████████▏ | 9656/11728 [46:39<3:20:35, 5.81s/it] 82%|████████▏ | 9657/11728 [46:45<3:19:19, 5.77s/it] {'loss': 0.4722, 'learning_rate': 1.591403076258743e-06, 'epoch': 0.82} + 82%|████████▏ | 9657/11728 [46:45<3:19:19, 5.77s/it] 82%|████████▏ | 9658/11728 [46:51<3:23:32, 5.90s/it] {'loss': 0.4635, 'learning_rate': 1.5899086738706904e-06, 'epoch': 0.82} + 82%|████████▏ | 9658/11728 [46:51<3:23:32, 5.90s/it] 82%|████████▏ | 9659/11728 [46:57<3:24:04, 5.92s/it] {'loss': 0.4414, 'learning_rate': 1.5884149128713155e-06, 'epoch': 0.82} + 82%|████████▏ | 9659/11728 [46:57<3:24:04, 5.92s/it] 82%|████████▏ | 9660/11728 [47:03<3:22:46, 5.88s/it] {'loss': 0.4438, 'learning_rate': 1.586921793374534e-06, 'epoch': 0.82} + 82%|████████▏ | 9660/11728 [47:03<3:22:46, 5.88s/it] 82%|████████▏ | 9661/11728 [47:09<3:20:53, 5.83s/it] {'loss': 0.4594, 'learning_rate': 1.5854293154942203e-06, 'epoch': 0.82} + 82%|████████▏ | 9661/11728 [47:09<3:20:53, 5.83s/it] 82%|████████▏ | 9662/11728 [47:15<3:21:52, 5.86s/it] {'loss': 0.4457, 'learning_rate': 1.5839374793441964e-06, 'epoch': 0.82} + 82%|████████▏ | 9662/11728 [47:15<3:21:52, 5.86s/it] 82%|████████▏ | 9663/11728 [47:20<3:19:43, 5.80s/it] {'loss': 0.4524, 'learning_rate': 1.582446285038236e-06, 'epoch': 0.82} + 82%|████████▏ | 9663/11728 [47:20<3:19:43, 5.80s/it] 82%|████████▏ | 9664/11728 [47:26<3:19:06, 5.79s/it] {'loss': 0.465, 'learning_rate': 1.580955732690065e-06, 'epoch': 0.82} + 82%|████████▏ | 9664/11728 [47:26<3:19:06, 5.79s/it] 82%|████████▏ | 9665/11728 [47:32<3:23:25, 5.92s/it] {'loss': 0.4533, 'learning_rate': 1.5794658224133607e-06, 'epoch': 0.82} + 82%|████████▏ | 9665/11728 [47:32<3:23:25, 5.92s/it] 82%|████████▏ | 9666/11728 [47:38<3:21:28, 5.86s/it] {'loss': 0.4443, 'learning_rate': 1.577976554321745e-06, 'epoch': 0.82} + 82%|████████▏ | 9666/11728 [47:38<3:21:28, 5.86s/it] 82%|████████▏ | 9667/11728 [47:44<3:19:48, 5.82s/it] {'loss': 0.4406, 'learning_rate': 1.576487928528795e-06, 'epoch': 0.82} + 82%|████████▏ | 9667/11728 [47:44<3:19:48, 5.82s/it] 82%|████████▏ | 9668/11728 [47:50<3:21:19, 5.86s/it] {'loss': 0.4724, 'learning_rate': 1.574999945148048e-06, 'epoch': 0.82} + 82%|████████▏ | 9668/11728 [47:50<3:21:19, 5.86s/it] 82%|████████▏ | 9669/11728 [47:55<3:19:37, 5.82s/it] {'loss': 0.4383, 'learning_rate': 1.573512604292976e-06, 'epoch': 0.82} + 82%|████████▏ | 9669/11728 [47:55<3:19:37, 5.82s/it] 82%|████████▏ | 9670/11728 [48:01<3:18:23, 5.78s/it] {'loss': 0.4423, 'learning_rate': 1.5720259060770128e-06, 'epoch': 0.82} + 82%|████████▏ | 9670/11728 [48:01<3:18:23, 5.78s/it] 82%|████████▏ | 9671/11728 [48:07<3:15:44, 5.71s/it] {'loss': 0.4575, 'learning_rate': 1.5705398506135394e-06, 'epoch': 0.82} + 82%|████████▏ | 9671/11728 [48:07<3:15:44, 5.71s/it] 82%|████████▏ | 9672/11728 [48:13<3:18:44, 5.80s/it] {'loss': 0.4356, 'learning_rate': 1.569054438015889e-06, 'epoch': 0.82} + 82%|████████▏ | 9672/11728 [48:13<3:18:44, 5.80s/it] 82%|████████▏ | 9673/11728 [48:18<3:18:39, 5.80s/it] {'loss': 0.4755, 'learning_rate': 1.5675696683973452e-06, 'epoch': 0.82} + 82%|████████▏ | 9673/11728 [48:18<3:18:39, 5.80s/it] 82%|████████▏ | 9674/11728 [48:24<3:16:24, 5.74s/it] {'loss': 0.4545, 'learning_rate': 1.566085541871145e-06, 'epoch': 0.82} + 82%|████████▏ | 9674/11728 [48:24<3:16:24, 5.74s/it] 82%|████████▏ | 9675/11728 [48:30<3:15:07, 5.70s/it] {'loss': 0.4302, 'learning_rate': 1.5646020585504696e-06, 'epoch': 0.82} + 82%|████████▏ | 9675/11728 [48:30<3:15:07, 5.70s/it] 83%|████████▎ | 9676/11728 [48:35<3:13:43, 5.66s/it] {'loss': 0.4658, 'learning_rate': 1.5631192185484557e-06, 'epoch': 0.83} + 83%|████████▎ | 9676/11728 [48:35<3:13:43, 5.66s/it] 83%|████████▎ | 9677/11728 [48:41<3:16:49, 5.76s/it] {'loss': 0.4363, 'learning_rate': 1.5616370219781985e-06, 'epoch': 0.83} + 83%|████████▎ | 9677/11728 [48:41<3:16:49, 5.76s/it] 83%|████████▎ | 9678/11728 [48:47<3:16:17, 5.75s/it] {'loss': 0.4754, 'learning_rate': 1.5601554689527276e-06, 'epoch': 0.83} + 83%|████████▎ | 9678/11728 [48:47<3:16:17, 5.75s/it] 83%|████████▎ | 9679/11728 [48:53<3:17:55, 5.80s/it] {'loss': 0.4362, 'learning_rate': 1.558674559585036e-06, 'epoch': 0.83} + 83%|████████▎ | 9679/11728 [48:53<3:17:55, 5.80s/it] 83%|████████▎ | 9680/11728 [48:59<3:19:30, 5.84s/it] {'loss': 0.4706, 'learning_rate': 1.5571942939880646e-06, 'epoch': 0.83} + 83%|████████▎ | 9680/11728 [48:59<3:19:30, 5.84s/it] 83%|████████▎ | 9681/11728 [49:04<3:17:22, 5.79s/it] {'loss': 0.4622, 'learning_rate': 1.555714672274704e-06, 'epoch': 0.83} + 83%|████████▎ | 9681/11728 [49:04<3:17:22, 5.79s/it] 83%|████████▎ | 9682/11728 [49:10<3:16:05, 5.75s/it] {'loss': 0.4325, 'learning_rate': 1.5542356945577964e-06, 'epoch': 0.83} + 83%|████████▎ | 9682/11728 [49:10<3:16:05, 5.75s/it] 83%|████████▎ | 9683/11728 [49:16<3:16:15, 5.76s/it] {'loss': 0.4527, 'learning_rate': 1.5527573609501367e-06, 'epoch': 0.83} + 83%|████████▎ | 9683/11728 [49:16<3:16:15, 5.76s/it] 83%|████████▎ | 9684/11728 [49:22<3:17:53, 5.81s/it] {'loss': 0.471, 'learning_rate': 1.551279671564464e-06, 'epoch': 0.83} + 83%|████████▎ | 9684/11728 [49:22<3:17:53, 5.81s/it] 83%|████████▎ | 9685/11728 [49:27<3:15:25, 5.74s/it] {'loss': 0.4452, 'learning_rate': 1.5498026265134747e-06, 'epoch': 0.83} + 83%|████████▎ | 9685/11728 [49:27<3:15:25, 5.74s/it] 83%|████████▎ | 9686/11728 [49:33<3:15:13, 5.74s/it] {'loss': 0.4601, 'learning_rate': 1.5483262259098197e-06, 'epoch': 0.83} + 83%|████████▎ | 9686/11728 [49:33<3:15:13, 5.74s/it] 83%|████████▎ | 9687/11728 [49:39<3:13:37, 5.69s/it] {'loss': 0.4403, 'learning_rate': 1.546850469866089e-06, 'epoch': 0.83} + 83%|████████▎ | 9687/11728 [49:39<3:13:37, 5.69s/it] 83%|████████▎ | 9688/11728 [49:45<3:15:39, 5.75s/it] {'loss': 0.4305, 'learning_rate': 1.5453753584948329e-06, 'epoch': 0.83} + 83%|████████▎ | 9688/11728 [49:45<3:15:39, 5.75s/it] 83%|████████▎ | 9689/11728 [49:51<3:19:02, 5.86s/it] {'loss': 0.4624, 'learning_rate': 1.5439008919085507e-06, 'epoch': 0.83} + 83%|████████▎ | 9689/11728 [49:51<3:19:02, 5.86s/it] 83%|████████▎ | 9690/11728 [49:56<3:16:59, 5.80s/it] {'loss': 0.4576, 'learning_rate': 1.5424270702196841e-06, 'epoch': 0.83} + 83%|████████▎ | 9690/11728 [49:56<3:16:59, 5.80s/it] 83%|████████▎ | 9691/11728 [50:03<3:21:23, 5.93s/it] {'loss': 0.4678, 'learning_rate': 1.5409538935406422e-06, 'epoch': 0.83} + 83%|████████▎ | 9691/11728 [50:03<3:21:23, 5.93s/it] 83%|████████▎ | 9692/11728 [50:08<3:19:36, 5.88s/it] {'loss': 0.4725, 'learning_rate': 1.5394813619837734e-06, 'epoch': 0.83} + 83%|████████▎ | 9692/11728 [50:08<3:19:36, 5.88s/it] 83%|████████▎ | 9693/11728 [50:14<3:21:38, 5.95s/it] {'loss': 0.4353, 'learning_rate': 1.5380094756613761e-06, 'epoch': 0.83} + 83%|████████▎ | 9693/11728 [50:14<3:21:38, 5.95s/it] 83%|████████▎ | 9694/11728 [50:20<3:20:09, 5.90s/it] {'loss': 0.4687, 'learning_rate': 1.5365382346857005e-06, 'epoch': 0.83} + 83%|████████▎ | 9694/11728 [50:20<3:20:09, 5.90s/it] 83%|████████▎ | 9695/11728 [50:26<3:18:55, 5.87s/it] {'loss': 0.4656, 'learning_rate': 1.5350676391689578e-06, 'epoch': 0.83} + 83%|████████▎ | 9695/11728 [50:26<3:18:55, 5.87s/it] 83%|████████▎ | 9696/11728 [50:32<3:17:14, 5.82s/it] {'loss': 0.4593, 'learning_rate': 1.533597689223295e-06, 'epoch': 0.83} + 83%|████████▎ | 9696/11728 [50:32<3:17:14, 5.82s/it] 83%|████████▎ | 9697/11728 [50:38<3:16:10, 5.80s/it] {'loss': 0.4553, 'learning_rate': 1.5321283849608193e-06, 'epoch': 0.83} + 83%|████████▎ | 9697/11728 [50:38<3:16:10, 5.80s/it] 83%|████████▎ | 9698/11728 [50:43<3:17:07, 5.83s/it] {'loss': 0.4521, 'learning_rate': 1.5306597264935863e-06, 'epoch': 0.83} + 83%|████████▎ | 9698/11728 [50:43<3:17:07, 5.83s/it] 83%|████████▎ | 9699/11728 [50:49<3:15:32, 5.78s/it] {'loss': 0.4567, 'learning_rate': 1.5291917139335976e-06, 'epoch': 0.83} + 83%|████████▎ | 9699/11728 [50:49<3:15:32, 5.78s/it]6 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +0 AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... + 83%|████████▎ | 9700/11728 [50:55<3:14:03, 5.74s/it]3 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4507, 'learning_rate': 1.527724347392815e-06, 'epoch': 0.83} + 83%|████████▎ | 9700/11728 [50:55<3:14:03, 5.74s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-9700/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-9700/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-9700/mm_projector +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/torch/nn/modules/module.py:1802: UserWarning: Positional args are being deprecated, use kwargs instead. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details. + warnings.warn( + 83%|████████▎ | 9701/11728 [51:32<8:30:12, 15.10s/it] {'loss': 0.456, 'learning_rate': 1.5262576269831464e-06, 'epoch': 0.83} + 83%|████████▎ | 9701/11728 [51:32<8:30:12, 15.10s/it] 83%|████████▎ | 9702/11728 [51:37<6:53:27, 12.24s/it] {'loss': 0.4387, 'learning_rate': 1.5247915528164458e-06, 'epoch': 0.83} + 83%|████████▎ | 9702/11728 [51:37<6:53:27, 12.24s/it] 83%|████████▎ | 9703/11728 [51:43<5:47:02, 10.28s/it] {'loss': 0.4665, 'learning_rate': 1.5233261250045218e-06, 'epoch': 0.83} + 83%|████████▎ | 9703/11728 [51:43<5:47:02, 10.28s/it] 83%|████████▎ | 9704/11728 [51:49<5:05:13, 9.05s/it] {'loss': 0.462, 'learning_rate': 1.5218613436591422e-06, 'epoch': 0.83} + 83%|████████▎ | 9704/11728 [51:49<5:05:13, 9.05s/it] 83%|████████▎ | 9705/11728 [51:55<4:34:59, 8.16s/it] {'loss': 0.4564, 'learning_rate': 1.5203972088920082e-06, 'epoch': 0.83} + 83%|████████▎ | 9705/11728 [51:55<4:34:59, 8.16s/it] 83%|████████▎ | 9706/11728 [52:01<4:12:36, 7.50s/it] {'loss': 0.45, 'learning_rate': 1.5189337208147848e-06, 'epoch': 0.83} + 83%|████████▎ | 9706/11728 [52:01<4:12:36, 7.50s/it] 83%|████████▎ | 9707/11728 [52:07<3:55:56, 7.00s/it] {'loss': 0.4655, 'learning_rate': 1.5174708795390859e-06, 'epoch': 0.83} + 83%|████████▎ | 9707/11728 [52:07<3:55:56, 7.00s/it] 83%|████████▎ | 9708/11728 [52:13<3:44:15, 6.66s/it] {'loss': 0.4597, 'learning_rate': 1.5160086851764666e-06, 'epoch': 0.83} + 83%|████████▎ | 9708/11728 [52:13<3:44:15, 6.66s/it] 83%|████████▎ | 9709/11728 [52:19<3:37:44, 6.47s/it] {'loss': 0.4595, 'learning_rate': 1.5145471378384458e-06, 'epoch': 0.83} + 83%|████████▎ | 9709/11728 [52:19<3:37:44, 6.47s/it] 83%|████████▎ | 9710/11728 [52:25<3:36:59, 6.45s/it] {'loss': 0.4612, 'learning_rate': 1.5130862376364897e-06, 'epoch': 0.83} + 83%|████████▎ | 9710/11728 [52:25<3:36:59, 6.45s/it] 83%|████████▎ | 9711/11728 [52:31<3:28:59, 6.22s/it] {'loss': 0.4397, 'learning_rate': 1.5116259846820058e-06, 'epoch': 0.83} + 83%|████████▎ | 9711/11728 [52:31<3:28:59, 6.22s/it] 83%|████████▎ | 9712/11728 [52:37<3:25:23, 6.11s/it] {'loss': 0.4726, 'learning_rate': 1.5101663790863597e-06, 'epoch': 0.83} + 83%|████████▎ | 9712/11728 [52:37<3:25:23, 6.11s/it] 83%|████████▎ | 9713/11728 [52:43<3:24:50, 6.10s/it] {'loss': 0.4474, 'learning_rate': 1.5087074209608743e-06, 'epoch': 0.83} + 83%|████████▎ | 9713/11728 [52:43<3:24:50, 6.10s/it] 83%|████████▎ | 9714/11728 [52:49<3:24:42, 6.10s/it] {'loss': 0.4566, 'learning_rate': 1.5072491104168097e-06, 'epoch': 0.83} + 83%|████████▎ | 9714/11728 [52:49<3:24:42, 6.10s/it] 83%|████████▎ | 9715/11728 [52:55<3:21:39, 6.01s/it] {'loss': 0.4525, 'learning_rate': 1.5057914475653835e-06, 'epoch': 0.83} + 83%|████████▎ | 9715/11728 [52:55<3:21:39, 6.01s/it] 83%|████████▎ | 9716/11728 [53:01<3:21:34, 6.01s/it] {'loss': 0.4625, 'learning_rate': 1.5043344325177634e-06, 'epoch': 0.83} + 83%|████████▎ | 9716/11728 [53:01<3:21:34, 6.01s/it] 83%|████████▎ | 9717/11728 [53:07<3:18:33, 5.92s/it] {'loss': 0.4653, 'learning_rate': 1.502878065385067e-06, 'epoch': 0.83} + 83%|████████▎ | 9717/11728 [53:07<3:18:33, 5.92s/it] 83%|████████▎ | 9718/11728 [53:12<3:15:53, 5.85s/it] {'loss': 0.4508, 'learning_rate': 1.501422346278365e-06, 'epoch': 0.83} + 83%|████████▎ | 9718/11728 [53:12<3:15:53, 5.85s/it] 83%|████████▎ | 9719/11728 [53:18<3:13:44, 5.79s/it] {'loss': 0.4811, 'learning_rate': 1.499967275308678e-06, 'epoch': 0.83} + 83%|████████▎ | 9719/11728 [53:18<3:13:44, 5.79s/it] 83%|████████▎ | 9720/11728 [53:24<3:15:44, 5.85s/it] {'loss': 0.4527, 'learning_rate': 1.4985128525869697e-06, 'epoch': 0.83} + 83%|████████▎ | 9720/11728 [53:24<3:15:44, 5.85s/it] 83%|████████▎ | 9721/11728 [53:30<3:15:44, 5.85s/it] {'loss': 0.4539, 'learning_rate': 1.4970590782241645e-06, 'epoch': 0.83} + 83%|████████▎ | 9721/11728 [53:30<3:15:44, 5.85s/it] 83%|████████▎ | 9722/11728 [53:35<3:14:11, 5.81s/it] {'loss': 0.4766, 'learning_rate': 1.4956059523311328e-06, 'epoch': 0.83} + 83%|████████▎ | 9722/11728 [53:35<3:14:11, 5.81s/it] 83%|████████▎ | 9723/11728 [53:41<3:11:49, 5.74s/it] {'loss': 0.4401, 'learning_rate': 1.4941534750186958e-06, 'epoch': 0.83} + 83%|████████▎ | 9723/11728 [53:41<3:11:49, 5.74s/it] 83%|████████▎ | 9724/11728 [53:47<3:12:45, 5.77s/it] {'loss': 0.4386, 'learning_rate': 1.4927016463976262e-06, 'epoch': 0.83} + 83%|████████▎ | 9724/11728 [53:47<3:12:45, 5.77s/it] 83%|████████▎ | 9725/11728 [53:53<3:13:36, 5.80s/it] {'loss': 0.4572, 'learning_rate': 1.4912504665786454e-06, 'epoch': 0.83} + 83%|████████▎ | 9725/11728 [53:53<3:13:36, 5.80s/it] 83%|████████▎ | 9726/11728 [53:59<3:15:10, 5.85s/it] {'loss': 0.4579, 'learning_rate': 1.4897999356724268e-06, 'epoch': 0.83} + 83%|████████▎ | 9726/11728 [53:59<3:15:10, 5.85s/it] 83%|████████▎ | 9727/11728 [54:05<3:16:35, 5.89s/it] {'loss': 0.4428, 'learning_rate': 1.4883500537895946e-06, 'epoch': 0.83} + 83%|████████▎ | 9727/11728 [54:05<3:16:35, 5.89s/it] 83%|████████▎ | 9728/11728 [54:11<3:16:20, 5.89s/it] {'loss': 0.4686, 'learning_rate': 1.4869008210407243e-06, 'epoch': 0.83} + 83%|████████▎ | 9728/11728 [54:11<3:16:20, 5.89s/it] 83%|████████▎ | 9729/11728 [54:16<3:13:38, 5.81s/it] {'loss': 0.4554, 'learning_rate': 1.4854522375363367e-06, 'epoch': 0.83} + 83%|████████▎ | 9729/11728 [54:16<3:13:38, 5.81s/it] 83%|████████▎ | 9730/11728 [54:22<3:14:51, 5.85s/it] {'loss': 0.4484, 'learning_rate': 1.4840043033869079e-06, 'epoch': 0.83} + 83%|████████▎ | 9730/11728 [54:22<3:14:51, 5.85s/it] 83%|████████▎ | 9731/11728 [54:28<3:15:23, 5.87s/it] {'loss': 0.4545, 'learning_rate': 1.482557018702865e-06, 'epoch': 0.83} + 83%|████████▎ | 9731/11728 [54:28<3:15:23, 5.87s/it] 83%|████████▎ | 9732/11728 [54:34<3:15:04, 5.86s/it] {'loss': 0.4457, 'learning_rate': 1.4811103835945817e-06, 'epoch': 0.83} + 83%|████████▎ | 9732/11728 [54:34<3:15:04, 5.86s/it] 83%|████████▎ | 9733/11728 [54:40<3:14:19, 5.84s/it] {'loss': 0.4756, 'learning_rate': 1.479664398172387e-06, 'epoch': 0.83} + 83%|████████▎ | 9733/11728 [54:40<3:14:19, 5.84s/it] 83%|████████▎ | 9734/11728 [54:46<3:13:42, 5.83s/it] {'loss': 0.4317, 'learning_rate': 1.4782190625465565e-06, 'epoch': 0.83} + 83%|████████▎ | 9734/11728 [54:46<3:13:42, 5.83s/it] 83%|████████▎ | 9735/11728 [54:52<3:15:36, 5.89s/it] {'loss': 0.4631, 'learning_rate': 1.476774376827318e-06, 'epoch': 0.83} + 83%|████████▎ | 9735/11728 [54:52<3:15:36, 5.89s/it] 83%|████████▎ | 9736/11728 [54:58<3:17:50, 5.96s/it] {'loss': 0.4627, 'learning_rate': 1.4753303411248477e-06, 'epoch': 0.83} + 83%|████████▎ | 9736/11728 [54:58<3:17:50, 5.96s/it] 83%|████████▎ | 9737/11728 [55:04<3:18:02, 5.97s/it] {'loss': 0.4683, 'learning_rate': 1.4738869555492786e-06, 'epoch': 0.83} + 83%|████████▎ | 9737/11728 [55:04<3:18:02, 5.97s/it] 83%|████████▎ | 9738/11728 [55:10<3:18:25, 5.98s/it] {'loss': 0.4562, 'learning_rate': 1.4724442202106825e-06, 'epoch': 0.83} + 83%|████████▎ | 9738/11728 [55:10<3:18:25, 5.98s/it] 83%|████████▎ | 9739/11728 [55:16<3:16:51, 5.94s/it] {'loss': 0.4531, 'learning_rate': 1.4710021352190918e-06, 'epoch': 0.83} + 83%|████████▎ | 9739/11728 [55:16<3:16:51, 5.94s/it] 83%|████████▎ | 9740/11728 [55:21<3:13:52, 5.85s/it] {'loss': 0.4587, 'learning_rate': 1.4695607006844859e-06, 'epoch': 0.83} + 83%|████████▎ | 9740/11728 [55:21<3:13:52, 5.85s/it] 83%|████████▎ | 9741/11728 [55:27<3:09:54, 5.73s/it] {'loss': 0.4521, 'learning_rate': 1.4681199167167949e-06, 'epoch': 0.83} + 83%|████████▎ | 9741/11728 [55:27<3:09:54, 5.73s/it] 83%|████████▎ | 9742/11728 [55:33<3:11:48, 5.79s/it] {'loss': 0.4537, 'learning_rate': 1.4666797834258984e-06, 'epoch': 0.83} + 83%|████████▎ | 9742/11728 [55:33<3:11:48, 5.79s/it] 83%|████████▎ | 9743/11728 [55:38<3:10:22, 5.75s/it] {'loss': 0.4508, 'learning_rate': 1.4652403009216265e-06, 'epoch': 0.83} + 83%|████████▎ | 9743/11728 [55:38<3:10:22, 5.75s/it] 83%|████████▎ | 9744/11728 [55:44<3:12:56, 5.84s/it] {'loss': 0.4578, 'learning_rate': 1.4638014693137637e-06, 'epoch': 0.83} + 83%|████████▎ | 9744/11728 [55:44<3:12:56, 5.84s/it] 83%|████████▎ | 9745/11728 [55:50<3:12:28, 5.82s/it] {'loss': 0.4563, 'learning_rate': 1.4623632887120343e-06, 'epoch': 0.83} + 83%|████████▎ | 9745/11728 [55:50<3:12:28, 5.82s/it] 83%|████████▎ | 9746/11728 [55:56<3:10:26, 5.77s/it] {'loss': 0.4485, 'learning_rate': 1.4609257592261273e-06, 'epoch': 0.83} + 83%|████████▎ | 9746/11728 [55:56<3:10:26, 5.77s/it] 83%|████████▎ | 9747/11728 [56:01<3:10:32, 5.77s/it] {'loss': 0.4651, 'learning_rate': 1.4594888809656704e-06, 'epoch': 0.83} + 83%|████████▎ | 9747/11728 [56:01<3:10:32, 5.77s/it] 83%|████████▎ | 9748/11728 [56:07<3:12:10, 5.82s/it] {'loss': 0.4671, 'learning_rate': 1.4580526540402462e-06, 'epoch': 0.83} + 83%|████████▎ | 9748/11728 [56:07<3:12:10, 5.82s/it] 83%|████████▎ | 9749/11728 [56:13<3:13:11, 5.86s/it] {'loss': 0.4713, 'learning_rate': 1.456617078559389e-06, 'epoch': 0.83} + 83%|████████▎ | 9749/11728 [56:13<3:13:11, 5.86s/it]6 AutoResumeHook: Checking whether to suspend... +0 AutoResumeHook: Checking whether to suspend... +57 AutoResumeHook: Checking whether to suspend... +AutoResumeHook: Checking whether to suspend... + 83%|████████▎ | 9750/11728 [56:19<3:15:42, 5.94s/it]2 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +34 AutoResumeHook: Checking whether to suspend... +AutoResumeHook: Checking whether to suspend... + {'loss': 0.4405, 'learning_rate': 1.4551821546325806e-06, 'epoch': 0.83} + 83%|████████▎ | 9750/11728 [56:19<3:15:42, 5.94s/it] 83%|████████▎ | 9751/11728 [56:25<3:14:50, 5.91s/it] {'loss': 0.4694, 'learning_rate': 1.453747882369254e-06, 'epoch': 0.83} + 83%|████████▎ | 9751/11728 [56:25<3:14:50, 5.91s/it] 83%|████████▎ | 9752/11728 [56:31<3:13:00, 5.86s/it] {'loss': 0.4404, 'learning_rate': 1.4523142618787944e-06, 'epoch': 0.83} + 83%|████████▎ | 9752/11728 [56:31<3:13:00, 5.86s/it] 83%|████████▎ | 9753/11728 [56:37<3:12:45, 5.86s/it] {'loss': 0.4447, 'learning_rate': 1.4508812932705364e-06, 'epoch': 0.83} + 83%|████████▎ | 9753/11728 [56:37<3:12:45, 5.86s/it] 83%|████████▎ | 9754/11728 [56:43<3:10:54, 5.80s/it] {'loss': 0.4639, 'learning_rate': 1.4494489766537579e-06, 'epoch': 0.83} + 83%|████████▎ | 9754/11728 [56:43<3:10:54, 5.80s/it] 83%|████████▎ | 9755/11728 [56:49<3:15:51, 5.96s/it] {'loss': 0.4516, 'learning_rate': 1.4480173121377028e-06, 'epoch': 0.83} + 83%|████████▎ | 9755/11728 [56:49<3:15:51, 5.96s/it] 83%|████████▎ | 9756/11728 [56:55<3:13:29, 5.89s/it] {'loss': 0.4698, 'learning_rate': 1.4465862998315483e-06, 'epoch': 0.83} + 83%|████████▎ | 9756/11728 [56:55<3:13:29, 5.89s/it] 83%|████████▎ | 9757/11728 [57:00<3:12:25, 5.86s/it] {'loss': 0.4463, 'learning_rate': 1.4451559398444314e-06, 'epoch': 0.83} + 83%|████████▎ | 9757/11728 [57:00<3:12:25, 5.86s/it] 83%|████████▎ | 9758/11728 [57:06<3:09:34, 5.77s/it] {'loss': 0.4647, 'learning_rate': 1.4437262322854394e-06, 'epoch': 0.83} + 83%|████████▎ | 9758/11728 [57:06<3:09:34, 5.77s/it] 83%|████████▎ | 9759/11728 [57:12<3:09:16, 5.77s/it] {'loss': 0.4467, 'learning_rate': 1.442297177263605e-06, 'epoch': 0.83} + 83%|████████▎ | 9759/11728 [57:12<3:09:16, 5.77s/it] 83%|████████▎ | 9760/11728 [57:18<3:10:13, 5.80s/it] {'loss': 0.4589, 'learning_rate': 1.4408687748879157e-06, 'epoch': 0.83} + 83%|████████▎ | 9760/11728 [57:18<3:10:13, 5.80s/it] 83%|████████▎ | 9761/11728 [57:23<3:07:45, 5.73s/it] {'loss': 0.4596, 'learning_rate': 1.4394410252673075e-06, 'epoch': 0.83} + 83%|████████▎ | 9761/11728 [57:23<3:07:45, 5.73s/it] 83%|████████▎ | 9762/11728 [57:29<3:08:13, 5.74s/it] {'loss': 0.4483, 'learning_rate': 1.4380139285106676e-06, 'epoch': 0.83} + 83%|████████▎ | 9762/11728 [57:29<3:08:13, 5.74s/it] 83%|████████▎ | 9763/11728 [57:35<3:07:00, 5.71s/it] {'loss': 0.462, 'learning_rate': 1.4365874847268257e-06, 'epoch': 0.83} + 83%|████████▎ | 9763/11728 [57:35<3:07:00, 5.71s/it] 83%|████████▎ | 9764/11728 [57:41<3:15:26, 5.97s/it] {'loss': 0.4606, 'learning_rate': 1.4351616940245794e-06, 'epoch': 0.83} + 83%|████████▎ | 9764/11728 [57:41<3:15:26, 5.97s/it] 83%|████████▎ | 9765/11728 [57:47<3:13:50, 5.93s/it] {'loss': 0.4535, 'learning_rate': 1.433736556512656e-06, 'epoch': 0.83} + 83%|████████▎ | 9765/11728 [57:47<3:13:50, 5.93s/it] 83%|████████▎ | 9766/11728 [57:53<3:14:14, 5.94s/it] {'loss': 0.4621, 'learning_rate': 1.4323120722997463e-06, 'epoch': 0.83} + 83%|████████▎ | 9766/11728 [57:53<3:14:14, 5.94s/it] 83%|████████▎ | 9767/11728 [57:59<3:14:29, 5.95s/it] {'loss': 0.4561, 'learning_rate': 1.430888241494487e-06, 'epoch': 0.83} + 83%|████████▎ | 9767/11728 [57:59<3:14:29, 5.95s/it] 83%|████████▎ | 9768/11728 [58:04<3:10:03, 5.82s/it] {'loss': 0.4334, 'learning_rate': 1.4294650642054654e-06, 'epoch': 0.83} + 83%|████████▎ | 9768/11728 [58:04<3:10:03, 5.82s/it] 83%|████████▎ | 9769/11728 [58:10<3:09:48, 5.81s/it] {'loss': 0.4649, 'learning_rate': 1.428042540541218e-06, 'epoch': 0.83} + 83%|████████▎ | 9769/11728 [58:10<3:09:48, 5.81s/it] 83%|████████▎ | 9770/11728 [58:16<3:07:28, 5.74s/it] {'loss': 0.4577, 'learning_rate': 1.4266206706102337e-06, 'epoch': 0.83} + 83%|████████▎ | 9770/11728 [58:16<3:07:28, 5.74s/it] 83%|████████▎ | 9771/11728 [58:22<3:06:45, 5.73s/it] {'loss': 0.4642, 'learning_rate': 1.4251994545209524e-06, 'epoch': 0.83} + 83%|████████▎ | 9771/11728 [58:22<3:06:45, 5.73s/it] 83%|████████▎ | 9772/11728 [58:27<3:06:36, 5.72s/it] {'loss': 0.4707, 'learning_rate': 1.4237788923817553e-06, 'epoch': 0.83} + 83%|████████▎ | 9772/11728 [58:27<3:06:36, 5.72s/it] 83%|████████▎ | 9773/11728 [58:33<3:05:40, 5.70s/it] {'loss': 0.4413, 'learning_rate': 1.4223589843009866e-06, 'epoch': 0.83} + 83%|████████▎ | 9773/11728 [58:33<3:05:40, 5.70s/it] 83%|████████▎ | 9774/11728 [58:39<3:07:10, 5.75s/it] {'loss': 0.4575, 'learning_rate': 1.4209397303869343e-06, 'epoch': 0.83} + 83%|████████▎ | 9774/11728 [58:39<3:07:10, 5.75s/it] 83%|████████▎ | 9775/11728 [58:45<3:08:03, 5.78s/it] {'loss': 0.4626, 'learning_rate': 1.419521130747833e-06, 'epoch': 0.83} + 83%|████████▎ | 9775/11728 [58:45<3:08:03, 5.78s/it] 83%|████████▎ | 9776/11728 [58:50<3:08:48, 5.80s/it] {'loss': 0.4589, 'learning_rate': 1.4181031854918714e-06, 'epoch': 0.83} + 83%|████████▎ | 9776/11728 [58:50<3:08:48, 5.80s/it] 83%|████████▎ | 9777/11728 [58:56<3:07:25, 5.76s/it] {'loss': 0.4456, 'learning_rate': 1.41668589472719e-06, 'epoch': 0.83} + 83%|████████▎ | 9777/11728 [58:56<3:07:25, 5.76s/it] 83%|████████▎ | 9778/11728 [59:02<3:08:35, 5.80s/it] {'loss': 0.4548, 'learning_rate': 1.4152692585618767e-06, 'epoch': 0.83} + 83%|████████▎ | 9778/11728 [59:02<3:08:35, 5.80s/it] 83%|████████▎ | 9779/11728 [59:08<3:06:08, 5.73s/it] {'loss': 0.4304, 'learning_rate': 1.4138532771039703e-06, 'epoch': 0.83} + 83%|████████▎ | 9779/11728 [59:08<3:06:08, 5.73s/it] 83%|████████▎ | 9780/11728 [59:13<3:06:56, 5.76s/it] {'loss': 0.4421, 'learning_rate': 1.4124379504614604e-06, 'epoch': 0.83} + 83%|████████▎ | 9780/11728 [59:13<3:06:56, 5.76s/it] 83%|████████▎ | 9781/11728 [59:19<3:06:05, 5.73s/it] {'loss': 0.454, 'learning_rate': 1.4110232787422807e-06, 'epoch': 0.83} + 83%|████████▎ | 9781/11728 [59:19<3:06:05, 5.73s/it] 83%|████████▎ | 9782/11728 [59:25<3:05:54, 5.73s/it] {'loss': 0.46, 'learning_rate': 1.4096092620543257e-06, 'epoch': 0.83} + 83%|████████▎ | 9782/11728 [59:25<3:05:54, 5.73s/it] 83%|████████▎ | 9783/11728 [59:30<3:03:01, 5.65s/it] {'loss': 0.449, 'learning_rate': 1.4081959005054335e-06, 'epoch': 0.83} + 83%|████████▎ | 9783/11728 [59:30<3:03:01, 5.65s/it] 83%|████████▎ | 9784/11728 [59:36<3:05:52, 5.74s/it] {'loss': 0.4658, 'learning_rate': 1.4067831942033904e-06, 'epoch': 0.83} + 83%|████████▎ | 9784/11728 [59:36<3:05:52, 5.74s/it] 83%|████████▎ | 9785/11728 [59:42<3:08:57, 5.84s/it] {'loss': 0.4554, 'learning_rate': 1.4053711432559358e-06, 'epoch': 0.83} + 83%|████████▎ | 9785/11728 [59:42<3:08:57, 5.84s/it] 83%|████████▎ | 9786/11728 [59:48<3:07:11, 5.78s/it] {'loss': 0.4737, 'learning_rate': 1.40395974777076e-06, 'epoch': 0.83} + 83%|████████▎ | 9786/11728 [59:48<3:07:11, 5.78s/it] 83%|████████▎ | 9787/11728 [59:54<3:08:24, 5.82s/it] {'loss': 0.4556, 'learning_rate': 1.4025490078555015e-06, 'epoch': 0.83} + 83%|████████▎ | 9787/11728 [59:54<3:08:24, 5.82s/it] 83%|████████▎ | 9788/11728 [1:00:00<3:09:38, 5.87s/it] {'loss': 0.4773, 'learning_rate': 1.4011389236177476e-06, 'epoch': 0.83} + 83%|████████▎ | 9788/11728 [1:00:00<3:09:38, 5.87s/it] 83%|████████▎ | 9789/11728 [1:00:06<3:08:06, 5.82s/it] {'loss': 0.4548, 'learning_rate': 1.399729495165042e-06, 'epoch': 0.83} + 83%|████████▎ | 9789/11728 [1:00:06<3:08:06, 5.82s/it] 83%|████████▎ | 9790/11728 [1:00:11<3:06:16, 5.77s/it] {'loss': 0.4765, 'learning_rate': 1.3983207226048656e-06, 'epoch': 0.83} + 83%|████████▎ | 9790/11728 [1:00:11<3:06:16, 5.77s/it] 83%|████████▎ | 9791/11728 [1:00:17<3:05:26, 5.74s/it] {'loss': 0.4478, 'learning_rate': 1.3969126060446635e-06, 'epoch': 0.83} + 83%|████████▎ | 9791/11728 [1:00:17<3:05:26, 5.74s/it] 83%|████████▎ | 9792/11728 [1:00:23<3:07:21, 5.81s/it] {'loss': 0.444, 'learning_rate': 1.3955051455918257e-06, 'epoch': 0.83} + 83%|████████▎ | 9792/11728 [1:00:23<3:07:21, 5.81s/it] 84%|████████▎ | 9793/11728 [1:00:29<3:07:56, 5.83s/it] {'loss': 0.4817, 'learning_rate': 1.3940983413536847e-06, 'epoch': 0.84} + 84%|████████▎ | 9793/11728 [1:00:29<3:07:56, 5.83s/it] 84%|████████▎ | 9794/11728 [1:00:35<3:10:10, 5.90s/it] {'loss': 0.4511, 'learning_rate': 1.3926921934375338e-06, 'epoch': 0.84} + 84%|████████▎ | 9794/11728 [1:00:35<3:10:10, 5.90s/it] 84%|████████▎ | 9795/11728 [1:00:41<3:11:42, 5.95s/it] {'loss': 0.4459, 'learning_rate': 1.3912867019506105e-06, 'epoch': 0.84} + 84%|████████▎ | 9795/11728 [1:00:41<3:11:42, 5.95s/it] 84%|████████▎ | 9796/11728 [1:00:47<3:11:13, 5.94s/it] {'loss': 0.4512, 'learning_rate': 1.3898818670001035e-06, 'epoch': 0.84} + 84%|████████▎ | 9796/11728 [1:00:47<3:11:13, 5.94s/it] 84%|████████▎ | 9797/11728 [1:00:52<3:07:54, 5.84s/it] {'loss': 0.4541, 'learning_rate': 1.3884776886931517e-06, 'epoch': 0.84} + 84%|████████▎ | 9797/11728 [1:00:52<3:07:54, 5.84s/it] 84%|████████▎ | 9798/11728 [1:00:58<3:06:28, 5.80s/it] {'loss': 0.455, 'learning_rate': 1.387074167136846e-06, 'epoch': 0.84} + 84%|████████▎ | 9798/11728 [1:00:58<3:06:28, 5.80s/it] 84%|████████▎ | 9799/11728 [1:01:04<3:08:17, 5.86s/it] {'loss': 0.4504, 'learning_rate': 1.3856713024382195e-06, 'epoch': 0.84} + 84%|████████▎ | 9799/11728 [1:01:04<3:08:17, 5.86s/it]6 AutoResumeHook: Checking whether to suspend... +52 AutoResumeHook: Checking whether to suspend... +AutoResumeHook: Checking whether to suspend... +01 AutoResumeHook: Checking whether to suspend... +AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... + 84%|████████▎ | 9800/11728 [1:01:10<3:07:28, 5.83s/it]3 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4715, 'learning_rate': 1.3842690947042604e-06, 'epoch': 0.84} + 84%|████████▎ | 9800/11728 [1:01:10<3:07:28, 5.83s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-9800/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-9800/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-9800/mm_projector +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/torch/nn/modules/module.py:1802: UserWarning: Positional args are being deprecated, use kwargs instead. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details. + warnings.warn( + 84%|████████▎ | 9801/11728 [1:01:46<8:01:06, 14.98s/it] {'loss': 0.4287, 'learning_rate': 1.3828675440419147e-06, 'epoch': 0.84} + 84%|████████▎ | 9801/11728 [1:01:46<8:01:06, 14.98s/it] 84%|████████▎ | 9802/11728 [1:01:52<6:33:28, 12.26s/it] {'loss': 0.4433, 'learning_rate': 1.3814666505580632e-06, 'epoch': 0.84} + 84%|████████▎ | 9802/11728 [1:01:52<6:33:28, 12.26s/it] 84%|████████▎ | 9803/11728 [1:01:58<5:31:06, 10.32s/it] {'loss': 0.4546, 'learning_rate': 1.3800664143595465e-06, 'epoch': 0.84} + 84%|████████▎ | 9803/11728 [1:01:58<5:31:06, 10.32s/it] 84%|████████▎ | 9804/11728 [1:02:04<4:47:19, 8.96s/it] {'loss': 0.4411, 'learning_rate': 1.3786668355531518e-06, 'epoch': 0.84} + 84%|████████▎ | 9804/11728 [1:02:04<4:47:19, 8.96s/it] 84%|████████▎ | 9805/11728 [1:02:10<4:18:14, 8.06s/it] {'loss': 0.4309, 'learning_rate': 1.377267914245618e-06, 'epoch': 0.84} + 84%|████████▎ | 9805/11728 [1:02:10<4:18:14, 8.06s/it] 84%|████████▎ | 9806/11728 [1:02:15<3:56:36, 7.39s/it] {'loss': 0.4418, 'learning_rate': 1.3758696505436309e-06, 'epoch': 0.84} + 84%|████████▎ | 9806/11728 [1:02:15<3:56:36, 7.39s/it] 84%|████████▎ | 9807/11728 [1:02:21<3:43:53, 6.99s/it] {'loss': 0.4776, 'learning_rate': 1.3744720445538318e-06, 'epoch': 0.84} + 84%|████████▎ | 9807/11728 [1:02:21<3:43:53, 6.99s/it] 84%|████████▎ | 9808/11728 [1:02:28<3:34:48, 6.71s/it] {'loss': 0.4453, 'learning_rate': 1.3730750963828033e-06, 'epoch': 0.84} + 84%|████████▎ | 9808/11728 [1:02:28<3:34:48, 6.71s/it] 84%|████████▎ | 9809/11728 [1:02:33<3:25:47, 6.43s/it] {'loss': 0.4634, 'learning_rate': 1.3716788061370812e-06, 'epoch': 0.84} + 84%|████████▎ | 9809/11728 [1:02:33<3:25:47, 6.43s/it] 84%|████████▎ | 9810/11728 [1:02:39<3:19:33, 6.24s/it] {'loss': 0.464, 'learning_rate': 1.3702831739231593e-06, 'epoch': 0.84} + 84%|████████▎ | 9810/11728 [1:02:39<3:19:33, 6.24s/it] 84%|████████▎ | 9811/11728 [1:02:45<3:17:07, 6.17s/it] {'loss': 0.4555, 'learning_rate': 1.36888819984747e-06, 'epoch': 0.84} + 84%|████████▎ | 9811/11728 [1:02:45<3:17:07, 6.17s/it] 84%|████████▎ | 9812/11728 [1:02:51<3:14:08, 6.08s/it] {'loss': 0.4573, 'learning_rate': 1.3674938840163986e-06, 'epoch': 0.84} + 84%|████████▎ | 9812/11728 [1:02:51<3:14:08, 6.08s/it] 84%|████████▎ | 9813/11728 [1:02:57<3:10:43, 5.98s/it] {'loss': 0.4604, 'learning_rate': 1.3661002265362844e-06, 'epoch': 0.84} + 84%|████████▎ | 9813/11728 [1:02:57<3:10:43, 5.98s/it] 84%|████████▎ | 9814/11728 [1:03:03<3:10:06, 5.96s/it] {'loss': 0.467, 'learning_rate': 1.3647072275134122e-06, 'epoch': 0.84} + 84%|████████▎ | 9814/11728 [1:03:03<3:10:06, 5.96s/it] 84%|████████▎ | 9815/11728 [1:03:08<3:07:55, 5.89s/it] {'loss': 0.4472, 'learning_rate': 1.363314887054018e-06, 'epoch': 0.84} + 84%|████████▎ | 9815/11728 [1:03:08<3:07:55, 5.89s/it] 84%|████████▎ | 9816/11728 [1:03:14<3:04:57, 5.80s/it] {'loss': 0.4559, 'learning_rate': 1.3619232052642906e-06, 'epoch': 0.84} + 84%|████████▎ | 9816/11728 [1:03:14<3:04:57, 5.80s/it] 84%|████████▎ | 9817/11728 [1:03:20<3:08:27, 5.92s/it] {'loss': 0.4658, 'learning_rate': 1.3605321822503592e-06, 'epoch': 0.84} + 84%|████████▎ | 9817/11728 [1:03:20<3:08:27, 5.92s/it] 84%|████████▎ | 9818/11728 [1:03:26<3:04:04, 5.78s/it] {'loss': 0.4318, 'learning_rate': 1.3591418181183103e-06, 'epoch': 0.84} + 84%|████████▎ | 9818/11728 [1:03:26<3:04:04, 5.78s/it] 84%|████████▎ | 9819/11728 [1:03:32<3:05:23, 5.83s/it] {'loss': 0.4605, 'learning_rate': 1.3577521129741856e-06, 'epoch': 0.84} + 84%|████████▎ | 9819/11728 [1:03:32<3:05:23, 5.83s/it] 84%|████████▎ | 9820/11728 [1:03:37<3:04:28, 5.80s/it] {'loss': 0.4532, 'learning_rate': 1.3563630669239625e-06, 'epoch': 0.84} + 84%|████████▎ | 9820/11728 [1:03:37<3:04:28, 5.80s/it] 84%|████████▎ | 9821/11728 [1:03:43<3:04:42, 5.81s/it] {'loss': 0.4402, 'learning_rate': 1.3549746800735775e-06, 'epoch': 0.84} + 84%|████████▎ | 9821/11728 [1:03:43<3:04:42, 5.81s/it] 84%|████████▎ | 9822/11728 [1:03:49<3:06:02, 5.86s/it] {'loss': 0.4527, 'learning_rate': 1.353586952528918e-06, 'epoch': 0.84} + 84%|████████▎ | 9822/11728 [1:03:49<3:06:02, 5.86s/it] 84%|████████▍ | 9823/11728 [1:03:55<3:07:05, 5.89s/it] {'loss': 0.4683, 'learning_rate': 1.3521998843958117e-06, 'epoch': 0.84} + 84%|████████▍ | 9823/11728 [1:03:55<3:07:05, 5.89s/it] 84%|████████▍ | 9824/11728 [1:04:01<3:04:33, 5.82s/it] {'loss': 0.4483, 'learning_rate': 1.350813475780046e-06, 'epoch': 0.84} + 84%|████████▍ | 9824/11728 [1:04:01<3:04:33, 5.82s/it] 84%|████████▍ | 9825/11728 [1:04:06<3:02:17, 5.75s/it] {'loss': 0.446, 'learning_rate': 1.349427726787358e-06, 'epoch': 0.84} + 84%|████████▍ | 9825/11728 [1:04:06<3:02:17, 5.75s/it] 84%|████████▍ | 9826/11728 [1:04:12<3:01:39, 5.73s/it] {'loss': 0.4566, 'learning_rate': 1.3480426375234234e-06, 'epoch': 0.84} + 84%|████████▍ | 9826/11728 [1:04:12<3:01:39, 5.73s/it] 84%|████████▍ | 9827/11728 [1:04:18<3:01:14, 5.72s/it] {'loss': 0.4583, 'learning_rate': 1.3466582080938762e-06, 'epoch': 0.84} + 84%|████████▍ | 9827/11728 [1:04:18<3:01:14, 5.72s/it] 84%|████████▍ | 9828/11728 [1:04:23<2:59:14, 5.66s/it] {'loss': 0.4518, 'learning_rate': 1.345274438604305e-06, 'epoch': 0.84} + 84%|████████▍ | 9828/11728 [1:04:23<2:59:14, 5.66s/it] 84%|████████▍ | 9829/11728 [1:04:29<3:01:41, 5.74s/it] {'loss': 0.4517, 'learning_rate': 1.343891329160235e-06, 'epoch': 0.84} + 84%|████████▍ | 9829/11728 [1:04:29<3:01:41, 5.74s/it] 84%|████████▍ | 9830/11728 [1:04:35<3:02:04, 5.76s/it] {'loss': 0.4533, 'learning_rate': 1.3425088798671504e-06, 'epoch': 0.84} + 84%|████████▍ | 9830/11728 [1:04:35<3:02:04, 5.76s/it] 84%|████████▍ | 9831/11728 [1:04:41<3:03:09, 5.79s/it] {'loss': 0.4613, 'learning_rate': 1.3411270908304853e-06, 'epoch': 0.84} + 84%|████████▍ | 9831/11728 [1:04:41<3:03:09, 5.79s/it] 84%|████████▍ | 9832/11728 [1:04:47<3:03:40, 5.81s/it] {'loss': 0.4678, 'learning_rate': 1.339745962155613e-06, 'epoch': 0.84} + 84%|████████▍ | 9832/11728 [1:04:47<3:03:40, 5.81s/it] 84%|████████▍ | 9833/11728 [1:04:53<3:05:35, 5.88s/it] {'loss': 0.4508, 'learning_rate': 1.3383654939478718e-06, 'epoch': 0.84} + 84%|████████▍ | 9833/11728 [1:04:53<3:05:35, 5.88s/it] 84%|████████▍ | 9834/11728 [1:04:58<3:04:51, 5.86s/it] {'loss': 0.4559, 'learning_rate': 1.3369856863125418e-06, 'epoch': 0.84} + 84%|████████▍ | 9834/11728 [1:04:58<3:04:51, 5.86s/it] 84%|████████▍ | 9835/11728 [1:05:04<3:03:25, 5.81s/it] {'loss': 0.451, 'learning_rate': 1.3356065393548467e-06, 'epoch': 0.84} + 84%|████████▍ | 9835/11728 [1:05:04<3:03:25, 5.81s/it] 84%|████████▍ | 9836/11728 [1:05:10<3:02:51, 5.80s/it] {'loss': 0.4573, 'learning_rate': 1.334228053179969e-06, 'epoch': 0.84} + 84%|████████▍ | 9836/11728 [1:05:10<3:02:51, 5.80s/it] 84%|████████▍ | 9837/11728 [1:05:16<3:07:40, 5.95s/it] {'loss': 0.4644, 'learning_rate': 1.3328502278930422e-06, 'epoch': 0.84} + 84%|████████▍ | 9837/11728 [1:05:16<3:07:40, 5.95s/it] 84%|████████▍ | 9838/11728 [1:05:22<3:03:39, 5.83s/it] {'loss': 0.4305, 'learning_rate': 1.3314730635991391e-06, 'epoch': 0.84} + 84%|████████▍ | 9838/11728 [1:05:22<3:03:39, 5.83s/it] 84%|████████▍ | 9839/11728 [1:05:28<3:02:19, 5.79s/it] {'loss': 0.4859, 'learning_rate': 1.33009656040329e-06, 'epoch': 0.84} + 84%|████████▍ | 9839/11728 [1:05:28<3:02:19, 5.79s/it] 84%|████████▍ | 9840/11728 [1:05:33<3:01:49, 5.78s/it] {'loss': 0.4379, 'learning_rate': 1.3287207184104756e-06, 'epoch': 0.84} + 84%|████████▍ | 9840/11728 [1:05:33<3:01:49, 5.78s/it] 84%|████████▍ | 9841/11728 [1:05:39<3:04:53, 5.88s/it] {'loss': 0.4641, 'learning_rate': 1.3273455377256162e-06, 'epoch': 0.84} + 84%|████████▍ | 9841/11728 [1:05:39<3:04:53, 5.88s/it] 84%|████████▍ | 9842/11728 [1:05:45<3:04:51, 5.88s/it] {'loss': 0.4508, 'learning_rate': 1.3259710184535957e-06, 'epoch': 0.84} + 84%|████████▍ | 9842/11728 [1:05:45<3:04:51, 5.88s/it] 84%|████████▍ | 9843/11728 [1:05:51<3:04:30, 5.87s/it] {'loss': 0.4511, 'learning_rate': 1.3245971606992404e-06, 'epoch': 0.84} + 84%|████████▍ | 9843/11728 [1:05:51<3:04:30, 5.87s/it] 84%|████████▍ | 9844/11728 [1:05:57<3:01:51, 5.79s/it] {'loss': 0.444, 'learning_rate': 1.3232239645673217e-06, 'epoch': 0.84} + 84%|████████▍ | 9844/11728 [1:05:57<3:01:51, 5.79s/it] 84%|████████▍ | 9845/11728 [1:06:03<3:05:33, 5.91s/it] {'loss': 0.4654, 'learning_rate': 1.3218514301625662e-06, 'epoch': 0.84} + 84%|████████▍ | 9845/11728 [1:06:03<3:05:33, 5.91s/it] 84%|████████▍ | 9846/11728 [1:06:09<3:03:36, 5.85s/it] {'loss': 0.4728, 'learning_rate': 1.3204795575896545e-06, 'epoch': 0.84} + 84%|████████▍ | 9846/11728 [1:06:09<3:03:36, 5.85s/it] 84%|████████▍ | 9847/11728 [1:06:14<3:01:52, 5.80s/it] {'loss': 0.456, 'learning_rate': 1.3191083469532062e-06, 'epoch': 0.84} + 84%|████████▍ | 9847/11728 [1:06:14<3:01:52, 5.80s/it] 84%|████████▍ | 9848/11728 [1:06:20<3:00:23, 5.76s/it] {'loss': 0.4435, 'learning_rate': 1.3177377983577967e-06, 'epoch': 0.84} + 84%|████████▍ | 9848/11728 [1:06:20<3:00:23, 5.76s/it] 84%|████████▍ | 9849/11728 [1:06:26<3:01:39, 5.80s/it] {'loss': 0.449, 'learning_rate': 1.316367911907952e-06, 'epoch': 0.84} + 84%|████████▍ | 9849/11728 [1:06:26<3:01:39, 5.80s/it]6 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +70 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... +2AutoResumeHook: Checking whether to suspend... AutoResumeHook: Checking whether to suspend... + + 84%|████████▍ | 9850/11728 [1:06:32<3:00:39, 5.77s/it]4 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4654, 'learning_rate': 1.31499868770814e-06, 'epoch': 0.84} + 84%|████████▍ | 9850/11728 [1:06:32<3:00:39, 5.77s/it] 84%|████████▍ | 9851/11728 [1:06:38<3:03:20, 5.86s/it] {'loss': 0.4753, 'learning_rate': 1.313630125862788e-06, 'epoch': 0.84} + 84%|████████▍ | 9851/11728 [1:06:38<3:03:20, 5.86s/it] 84%|████████▍ | 9852/11728 [1:06:44<3:04:07, 5.89s/it] {'loss': 0.4437, 'learning_rate': 1.3122622264762696e-06, 'epoch': 0.84} + 84%|████████▍ | 9852/11728 [1:06:44<3:04:07, 5.89s/it] 84%|████████▍ | 9853/11728 [1:06:49<3:02:44, 5.85s/it] {'loss': 0.4409, 'learning_rate': 1.3108949896529023e-06, 'epoch': 0.84} + 84%|████████▍ | 9853/11728 [1:06:49<3:02:44, 5.85s/it] 84%|████████▍ | 9854/11728 [1:06:55<3:01:23, 5.81s/it] {'loss': 0.4483, 'learning_rate': 1.3095284154969578e-06, 'epoch': 0.84} + 84%|████████▍ | 9854/11728 [1:06:55<3:01:23, 5.81s/it] 84%|████████▍ | 9855/11728 [1:07:01<2:59:45, 5.76s/it] {'loss': 0.4571, 'learning_rate': 1.308162504112659e-06, 'epoch': 0.84} + 84%|████████▍ | 9855/11728 [1:07:01<2:59:45, 5.76s/it] 84%|████████▍ | 9856/11728 [1:07:07<3:03:11, 5.87s/it] {'loss': 0.4534, 'learning_rate': 1.3067972556041753e-06, 'epoch': 0.84} + 84%|████████▍ | 9856/11728 [1:07:07<3:03:11, 5.87s/it] 84%|████████▍ | 9857/11728 [1:07:13<3:04:34, 5.92s/it] {'loss': 0.4332, 'learning_rate': 1.3054326700756248e-06, 'epoch': 0.84} + 84%|████████▍ | 9857/11728 [1:07:13<3:04:34, 5.92s/it] 84%|████████▍ | 9858/11728 [1:07:19<3:05:38, 5.96s/it] {'loss': 0.4686, 'learning_rate': 1.304068747631081e-06, 'epoch': 0.84} + 84%|████████▍ | 9858/11728 [1:07:19<3:05:38, 5.96s/it] 84%|████████▍ | 9859/11728 [1:07:25<3:04:05, 5.91s/it] {'loss': 0.4653, 'learning_rate': 1.3027054883745538e-06, 'epoch': 0.84} + 84%|████████▍ | 9859/11728 [1:07:25<3:04:05, 5.91s/it] 84%|████████▍ | 9860/11728 [1:07:30<3:02:47, 5.87s/it] {'loss': 0.4306, 'learning_rate': 1.301342892410018e-06, 'epoch': 0.84} + 84%|████████▍ | 9860/11728 [1:07:30<3:02:47, 5.87s/it] 84%|████████▍ | 9861/11728 [1:07:36<3:00:21, 5.80s/it] {'loss': 0.4545, 'learning_rate': 1.2999809598413927e-06, 'epoch': 0.84} + 84%|████████▍ | 9861/11728 [1:07:36<3:00:21, 5.80s/it] 84%|████████▍ | 9862/11728 [1:07:42<2:58:21, 5.73s/it] {'loss': 0.4501, 'learning_rate': 1.2986196907725368e-06, 'epoch': 0.84} + 84%|████████▍ | 9862/11728 [1:07:42<2:58:21, 5.73s/it] 84%|████████▍ | 9863/11728 [1:07:47<2:58:14, 5.73s/it] {'loss': 0.454, 'learning_rate': 1.297259085307272e-06, 'epoch': 0.84} + 84%|████████▍ | 9863/11728 [1:07:47<2:58:14, 5.73s/it] 84%|████████▍ | 9864/11728 [1:07:53<2:57:35, 5.72s/it] {'loss': 0.4417, 'learning_rate': 1.2958991435493618e-06, 'epoch': 0.84} + 84%|████████▍ | 9864/11728 [1:07:53<2:57:35, 5.72s/it] 84%|████████▍ | 9865/11728 [1:07:59<2:56:34, 5.69s/it] {'loss': 0.4627, 'learning_rate': 1.294539865602521e-06, 'epoch': 0.84} + 84%|████████▍ | 9865/11728 [1:07:59<2:56:34, 5.69s/it] 84%|████████▍ | 9866/11728 [1:08:05<3:01:42, 5.86s/it] {'loss': 0.4847, 'learning_rate': 1.2931812515704145e-06, 'epoch': 0.84} + 84%|████████▍ | 9866/11728 [1:08:05<3:01:42, 5.86s/it] 84%|████████▍ | 9867/11728 [1:08:11<3:03:11, 5.91s/it] {'loss': 0.4454, 'learning_rate': 1.2918233015566573e-06, 'epoch': 0.84} + 84%|████████▍ | 9867/11728 [1:08:11<3:03:11, 5.91s/it] 84%|████████▍ | 9868/11728 [1:08:17<2:59:35, 5.79s/it] {'loss': 0.4592, 'learning_rate': 1.2904660156648074e-06, 'epoch': 0.84} + 84%|████████▍ | 9868/11728 [1:08:17<2:59:35, 5.79s/it] 84%|████████▍ | 9869/11728 [1:08:22<3:00:21, 5.82s/it] {'loss': 0.4679, 'learning_rate': 1.2891093939983812e-06, 'epoch': 0.84} + 84%|████████▍ | 9869/11728 [1:08:22<3:00:21, 5.82s/it] 84%|████████▍ | 9870/11728 [1:08:28<3:00:53, 5.84s/it] {'loss': 0.4361, 'learning_rate': 1.2877534366608424e-06, 'epoch': 0.84} + 84%|████████▍ | 9870/11728 [1:08:28<3:00:53, 5.84s/it] 84%|████████▍ | 9871/11728 [1:08:35<3:04:16, 5.95s/it] {'loss': 0.4711, 'learning_rate': 1.2863981437555972e-06, 'epoch': 0.84} + 84%|████████▍ | 9871/11728 [1:08:35<3:04:16, 5.95s/it] 84%|████████▍ | 9872/11728 [1:08:40<3:01:45, 5.88s/it] {'loss': 0.4463, 'learning_rate': 1.2850435153860075e-06, 'epoch': 0.84} + 84%|████████▍ | 9872/11728 [1:08:40<3:01:45, 5.88s/it] 84%|████████▍ | 9873/11728 [1:08:46<3:02:47, 5.91s/it] {'loss': 0.4622, 'learning_rate': 1.2836895516553826e-06, 'epoch': 0.84} + 84%|████████▍ | 9873/11728 [1:08:46<3:02:47, 5.91s/it] 84%|████████▍ | 9874/11728 [1:08:52<3:03:49, 5.95s/it] {'loss': 0.4475, 'learning_rate': 1.2823362526669825e-06, 'epoch': 0.84} + 84%|████████▍ | 9874/11728 [1:08:52<3:03:49, 5.95s/it] 84%|████████▍ | 9875/11728 [1:08:58<3:04:12, 5.96s/it] {'loss': 0.4717, 'learning_rate': 1.2809836185240154e-06, 'epoch': 0.84} + 84%|████████▍ | 9875/11728 [1:08:58<3:04:12, 5.96s/it] 84%|████████▍ | 9876/11728 [1:09:04<3:02:55, 5.93s/it] {'loss': 0.464, 'learning_rate': 1.2796316493296402e-06, 'epoch': 0.84} + 84%|████████▍ | 9876/11728 [1:09:04<3:02:55, 5.93s/it] 84%|████████▍ | 9877/11728 [1:09:10<3:03:41, 5.95s/it] {'loss': 0.4456, 'learning_rate': 1.2782803451869597e-06, 'epoch': 0.84} + 84%|████████▍ | 9877/11728 [1:09:10<3:03:41, 5.95s/it] 84%|████████▍ | 9878/11728 [1:09:16<3:04:27, 5.98s/it] {'loss': 0.4655, 'learning_rate': 1.2769297061990294e-06, 'epoch': 0.84} + 84%|████████▍ | 9878/11728 [1:09:16<3:04:27, 5.98s/it] 84%|████████▍ | 9879/11728 [1:09:22<3:01:39, 5.90s/it] {'loss': 0.4649, 'learning_rate': 1.2755797324688622e-06, 'epoch': 0.84} + 84%|████████▍ | 9879/11728 [1:09:22<3:01:39, 5.90s/it] 84%|████████▍ | 9880/11728 [1:09:28<3:00:44, 5.87s/it] {'loss': 0.458, 'learning_rate': 1.2742304240994053e-06, 'epoch': 0.84} + 84%|████████▍ | 9880/11728 [1:09:28<3:00:44, 5.87s/it] 84%|████████▍ | 9881/11728 [1:09:34<3:01:22, 5.89s/it] {'loss': 0.4767, 'learning_rate': 1.2728817811935657e-06, 'epoch': 0.84} + 84%|████████▍ | 9881/11728 [1:09:34<3:01:22, 5.89s/it] 84%|████████▍ | 9882/11728 [1:09:40<3:01:51, 5.91s/it] {'loss': 0.4871, 'learning_rate': 1.2715338038541969e-06, 'epoch': 0.84} + 84%|████████▍ | 9882/11728 [1:09:40<3:01:51, 5.91s/it] 84%|████████▍ | 9883/11728 [1:09:45<2:59:47, 5.85s/it] {'loss': 0.4445, 'learning_rate': 1.2701864921840989e-06, 'epoch': 0.84} + 84%|████████▍ | 9883/11728 [1:09:45<2:59:47, 5.85s/it] 84%|████████▍ | 9884/11728 [1:09:51<3:01:51, 5.92s/it] {'loss': 0.4678, 'learning_rate': 1.2688398462860262e-06, 'epoch': 0.84} + 84%|████████▍ | 9884/11728 [1:09:51<3:01:51, 5.92s/it] 84%|████████▍ | 9885/11728 [1:09:57<2:58:55, 5.82s/it] {'loss': 0.4655, 'learning_rate': 1.26749386626268e-06, 'epoch': 0.84} + 84%|████████▍ | 9885/11728 [1:09:57<2:58:55, 5.82s/it] 84%|████████▍ | 9886/11728 [1:10:03<2:58:47, 5.82s/it] {'loss': 0.4521, 'learning_rate': 1.2661485522167062e-06, 'epoch': 0.84} + 84%|████████▍ | 9886/11728 [1:10:03<2:58:47, 5.82s/it] 84%|████████▍ | 9887/11728 [1:10:09<2:59:17, 5.84s/it] {'loss': 0.4751, 'learning_rate': 1.2648039042507043e-06, 'epoch': 0.84} + 84%|████████▍ | 9887/11728 [1:10:09<2:59:17, 5.84s/it] 84%|████████▍ | 9888/11728 [1:10:14<2:57:15, 5.78s/it] {'loss': 0.4386, 'learning_rate': 1.2634599224672295e-06, 'epoch': 0.84} + 84%|████████▍ | 9888/11728 [1:10:14<2:57:15, 5.78s/it] 84%|████████▍ | 9889/11728 [1:10:20<2:57:01, 5.78s/it] {'loss': 0.4527, 'learning_rate': 1.262116606968773e-06, 'epoch': 0.84} + 84%|████████▍ | 9889/11728 [1:10:20<2:57:01, 5.78s/it] 84%|████████▍ | 9890/11728 [1:10:26<2:56:46, 5.77s/it] {'loss': 0.4406, 'learning_rate': 1.2607739578577838e-06, 'epoch': 0.84} + 84%|████████▍ | 9890/11728 [1:10:26<2:56:46, 5.77s/it] 84%|████████▍ | 9891/11728 [1:10:32<2:58:15, 5.82s/it] {'loss': 0.4579, 'learning_rate': 1.2594319752366578e-06, 'epoch': 0.84} + 84%|████████▍ | 9891/11728 [1:10:32<2:58:15, 5.82s/it] 84%|████████▍ | 9892/11728 [1:10:38<3:04:00, 6.01s/it] {'loss': 0.4778, 'learning_rate': 1.2580906592077403e-06, 'epoch': 0.84} + 84%|████████▍ | 9892/11728 [1:10:38<3:04:00, 6.01s/it] 84%|████████▍ | 9893/11728 [1:10:44<3:04:32, 6.03s/it] {'loss': 0.4538, 'learning_rate': 1.2567500098733242e-06, 'epoch': 0.84} + 84%|████████▍ | 9893/11728 [1:10:44<3:04:32, 6.03s/it] 84%|████████▍ | 9894/11728 [1:10:50<3:03:28, 6.00s/it] {'loss': 0.4551, 'learning_rate': 1.2554100273356552e-06, 'epoch': 0.84} + 84%|████████▍ | 9894/11728 [1:10:50<3:03:28, 6.00s/it] 84%|████████▍ | 9895/11728 [1:10:56<3:01:54, 5.95s/it] {'loss': 0.4576, 'learning_rate': 1.2540707116969274e-06, 'epoch': 0.84} + 84%|████████▍ | 9895/11728 [1:10:56<3:01:54, 5.95s/it] 84%|████████▍ | 9896/11728 [1:11:02<3:00:36, 5.91s/it] {'loss': 0.4668, 'learning_rate': 1.2527320630592765e-06, 'epoch': 0.84} + 84%|████████▍ | 9896/11728 [1:11:02<3:00:36, 5.91s/it] 84%|████████▍ | 9897/11728 [1:11:08<3:02:06, 5.97s/it] {'loss': 0.457, 'learning_rate': 1.2513940815248005e-06, 'epoch': 0.84} + 84%|████████▍ | 9897/11728 [1:11:08<3:02:06, 5.97s/it] 84%|████████▍ | 9898/11728 [1:11:14<2:58:14, 5.84s/it] {'loss': 0.4352, 'learning_rate': 1.2500567671955345e-06, 'epoch': 0.84} + 84%|████████▍ | 9898/11728 [1:11:14<2:58:14, 5.84s/it] 84%|████████▍ | 9899/11728 [1:11:19<2:57:44, 5.83s/it] {'loss': 0.4651, 'learning_rate': 1.2487201201734689e-06, 'epoch': 0.84} + 84%|████████▍ | 9899/11728 [1:11:19<2:57:44, 5.83s/it]6 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... +0275 AutoResumeHook: Checking whether to suspend...AutoResumeHook: Checking whether to suspend... + + AutoResumeHook: Checking whether to suspend... +AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... + 84%|████████▍ | 9900/11728 [1:11:25<2:57:12, 5.82s/it]4 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4441, 'learning_rate': 1.2473841405605424e-06, 'epoch': 0.84} + 84%|████████▍ | 9900/11728 [1:11:25<2:57:12, 5.82s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-9900/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-9900/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-9900/mm_projector +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/torch/nn/modules/module.py:1802: UserWarning: Positional args are being deprecated, use kwargs instead. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details. + warnings.warn( + 84%|████████▍ | 9901/11728 [1:11:58<7:04:32, 13.94s/it] {'loss': 0.4704, 'learning_rate': 1.2460488284586437e-06, 'epoch': 0.84} + 84%|████████▍ | 9901/11728 [1:11:58<7:04:32, 13.94s/it] 84%|████████▍ | 9902/11728 [1:12:04<5:49:38, 11.49s/it] {'loss': 0.461, 'learning_rate': 1.2447141839696065e-06, 'epoch': 0.84} + 84%|████████▍ | 9902/11728 [1:12:04<5:49:38, 11.49s/it] 84%|████████▍ | 9903/11728 [1:12:09<4:54:52, 9.69s/it] {'loss': 0.4555, 'learning_rate': 1.2433802071952183e-06, 'epoch': 0.84} + 84%|████████▍ | 9903/11728 [1:12:09<4:54:52, 9.69s/it] 84%|████████▍ | 9904/11728 [1:12:15<4:20:31, 8.57s/it] {'loss': 0.4506, 'learning_rate': 1.2420468982372158e-06, 'epoch': 0.84} + 84%|████████▍ | 9904/11728 [1:12:15<4:20:31, 8.57s/it] 84%|████████▍ | 9905/11728 [1:12:21<3:53:05, 7.67s/it] {'loss': 0.4502, 'learning_rate': 1.2407142571972752e-06, 'epoch': 0.84} + 84%|████████▍ | 9905/11728 [1:12:21<3:53:05, 7.67s/it] 84%|████████▍ | 9906/11728 [1:12:27<3:38:22, 7.19s/it] {'loss': 0.4612, 'learning_rate': 1.2393822841770397e-06, 'epoch': 0.84} + 84%|████████▍ | 9906/11728 [1:12:27<3:38:22, 7.19s/it] 84%|████████▍ | 9907/11728 [1:12:33<3:27:05, 6.82s/it] {'loss': 0.4703, 'learning_rate': 1.2380509792780826e-06, 'epoch': 0.84} + 84%|████████▍ | 9907/11728 [1:12:33<3:27:05, 6.82s/it] 84%|████████▍ | 9908/11728 [1:12:39<3:19:14, 6.57s/it] {'loss': 0.461, 'learning_rate': 1.236720342601938e-06, 'epoch': 0.84} + 84%|████████▍ | 9908/11728 [1:12:39<3:19:14, 6.57s/it] 84%|████████▍ | 9909/11728 [1:12:45<3:11:50, 6.33s/it] {'loss': 0.4482, 'learning_rate': 1.2353903742500861e-06, 'epoch': 0.84} + 84%|████████▍ | 9909/11728 [1:12:45<3:11:50, 6.33s/it] 84%|████████▍ | 9910/11728 [1:12:51<3:07:54, 6.20s/it] {'loss': 0.4521, 'learning_rate': 1.2340610743239545e-06, 'epoch': 0.84} + 84%|████████▍ | 9910/11728 [1:12:51<3:07:54, 6.20s/it] 85%|████████▍ | 9911/11728 [1:12:56<3:04:57, 6.11s/it] {'loss': 0.4463, 'learning_rate': 1.2327324429249232e-06, 'epoch': 0.85} + 85%|████████▍ | 9911/11728 [1:12:56<3:04:57, 6.11s/it] 85%|████████▍ | 9912/11728 [1:13:02<3:00:41, 5.97s/it] {'loss': 0.454, 'learning_rate': 1.2314044801543168e-06, 'epoch': 0.85} + 85%|████████▍ | 9912/11728 [1:13:02<3:00:41, 5.97s/it] 85%|████████▍ | 9913/11728 [1:13:08<2:59:06, 5.92s/it] {'loss': 0.4607, 'learning_rate': 1.2300771861134153e-06, 'epoch': 0.85} + 85%|████████▍ | 9913/11728 [1:13:08<2:59:06, 5.92s/it] 85%|████████▍ | 9914/11728 [1:13:13<2:56:34, 5.84s/it] {'loss': 0.4397, 'learning_rate': 1.2287505609034367e-06, 'epoch': 0.85} + 85%|████████▍ | 9914/11728 [1:13:14<2:56:34, 5.84s/it] 85%|████████▍ | 9915/11728 [1:13:19<2:56:31, 5.84s/it] {'loss': 0.4569, 'learning_rate': 1.2274246046255633e-06, 'epoch': 0.85} + 85%|████████▍ | 9915/11728 [1:13:19<2:56:31, 5.84s/it] 85%|████████▍ | 9916/11728 [1:13:25<2:57:19, 5.87s/it] {'loss': 0.4646, 'learning_rate': 1.2260993173809122e-06, 'epoch': 0.85} + 85%|████████▍ | 9916/11728 [1:13:25<2:57:19, 5.87s/it] 85%|████████▍ | 9917/11728 [1:13:31<2:57:14, 5.87s/it] {'loss': 0.4804, 'learning_rate': 1.2247746992705566e-06, 'epoch': 0.85} + 85%|████████▍ | 9917/11728 [1:13:31<2:57:14, 5.87s/it] 85%|████████▍ | 9918/11728 [1:13:37<3:00:21, 5.98s/it] {'loss': 0.4593, 'learning_rate': 1.2234507503955185e-06, 'epoch': 0.85} + 85%|████████▍ | 9918/11728 [1:13:37<3:00:21, 5.98s/it] 85%|████████▍ | 9919/11728 [1:13:43<2:58:03, 5.91s/it] {'loss': 0.4363, 'learning_rate': 1.2221274708567664e-06, 'epoch': 0.85} + 85%|████████▍ | 9919/11728 [1:13:43<2:58:03, 5.91s/it] 85%|████████▍ | 9920/11728 [1:13:49<3:01:50, 6.03s/it] {'loss': 0.4444, 'learning_rate': 1.2208048607552214e-06, 'epoch': 0.85} + 85%|████████▍ | 9920/11728 [1:13:49<3:01:50, 6.03s/it] 85%|████████▍ | 9921/11728 [1:13:55<3:00:06, 5.98s/it] {'loss': 0.4587, 'learning_rate': 1.219482920191748e-06, 'epoch': 0.85} + 85%|████████▍ | 9921/11728 [1:13:55<3:00:06, 5.98s/it] 85%|████████▍ | 9922/11728 [1:14:01<3:00:05, 5.98s/it] {'loss': 0.4397, 'learning_rate': 1.2181616492671677e-06, 'epoch': 0.85} + 85%|████████▍ | 9922/11728 [1:14:01<3:00:05, 5.98s/it] 85%|████████▍ | 9923/11728 [1:14:07<2:57:59, 5.92s/it] {'loss': 0.4531, 'learning_rate': 1.216841048082239e-06, 'epoch': 0.85} + 85%|████████▍ | 9923/11728 [1:14:07<2:57:59, 5.92s/it] 85%|████████▍ | 9924/11728 [1:14:13<2:55:31, 5.84s/it] {'loss': 0.4686, 'learning_rate': 1.2155211167376835e-06, 'epoch': 0.85} + 85%|████████▍ | 9924/11728 [1:14:13<2:55:31, 5.84s/it] 85%|████████▍ | 9925/11728 [1:14:18<2:54:33, 5.81s/it] {'loss': 0.442, 'learning_rate': 1.2142018553341607e-06, 'epoch': 0.85} + 85%|████████▍ | 9925/11728 [1:14:18<2:54:33, 5.81s/it] 85%|████████▍ | 9926/11728 [1:14:24<2:54:07, 5.80s/it] {'loss': 0.4613, 'learning_rate': 1.2128832639722844e-06, 'epoch': 0.85} + 85%|████████▍ | 9926/11728 [1:14:24<2:54:07, 5.80s/it] 85%|████████▍ | 9927/11728 [1:14:30<2:52:51, 5.76s/it] {'loss': 0.4493, 'learning_rate': 1.2115653427526142e-06, 'epoch': 0.85} + 85%|████████▍ | 9927/11728 [1:14:30<2:52:51, 5.76s/it] 85%|████████▍ | 9928/11728 [1:14:36<2:54:25, 5.81s/it] {'loss': 0.4808, 'learning_rate': 1.2102480917756632e-06, 'epoch': 0.85} + 85%|████████▍ | 9928/11728 [1:14:36<2:54:25, 5.81s/it] 85%|████████▍ | 9929/11728 [1:14:42<2:55:15, 5.85s/it] {'loss': 0.4564, 'learning_rate': 1.2089315111418876e-06, 'epoch': 0.85} + 85%|████████▍ | 9929/11728 [1:14:42<2:55:15, 5.85s/it] 85%|████████▍ | 9930/11728 [1:14:47<2:54:00, 5.81s/it] {'loss': 0.4545, 'learning_rate': 1.2076156009516971e-06, 'epoch': 0.85} + 85%|████████▍ | 9930/11728 [1:14:47<2:54:00, 5.81s/it] 85%|████████▍ | 9931/11728 [1:14:53<2:54:21, 5.82s/it] {'loss': 0.4444, 'learning_rate': 1.2063003613054491e-06, 'epoch': 0.85} + 85%|████████▍ | 9931/11728 [1:14:53<2:54:21, 5.82s/it] 85%|████████▍ | 9932/11728 [1:14:59<2:53:30, 5.80s/it] {'loss': 0.4418, 'learning_rate': 1.2049857923034468e-06, 'epoch': 0.85} + 85%|████████▍ | 9932/11728 [1:14:59<2:53:30, 5.80s/it] 85%|████████▍ | 9933/11728 [1:15:05<2:53:43, 5.81s/it] {'loss': 0.4663, 'learning_rate': 1.2036718940459468e-06, 'epoch': 0.85} + 85%|████████▍ | 9933/11728 [1:15:05<2:53:43, 5.81s/it] 85%|████████▍ | 9934/11728 [1:15:11<2:52:25, 5.77s/it] {'loss': 0.4584, 'learning_rate': 1.202358666633151e-06, 'epoch': 0.85} + 85%|████████▍ | 9934/11728 [1:15:11<2:52:25, 5.77s/it] 85%|████████▍ | 9935/11728 [1:15:16<2:52:21, 5.77s/it] {'loss': 0.4271, 'learning_rate': 1.2010461101652127e-06, 'epoch': 0.85} + 85%|████████▍ | 9935/11728 [1:15:16<2:52:21, 5.77s/it] 85%|████████▍ | 9936/11728 [1:15:22<2:50:00, 5.69s/it] {'loss': 0.4541, 'learning_rate': 1.1997342247422317e-06, 'epoch': 0.85} + 85%|████████▍ | 9936/11728 [1:15:22<2:50:00, 5.69s/it] 85%|████████▍ | 9937/11728 [1:15:28<2:50:16, 5.70s/it] {'loss': 0.4567, 'learning_rate': 1.198423010464259e-06, 'epoch': 0.85} + 85%|████████▍ | 9937/11728 [1:15:28<2:50:16, 5.70s/it] 85%|████████▍ | 9938/11728 [1:15:33<2:50:21, 5.71s/it] {'loss': 0.4396, 'learning_rate': 1.1971124674312939e-06, 'epoch': 0.85} + 85%|████████▍ | 9938/11728 [1:15:33<2:50:21, 5.71s/it] 85%|████████▍ | 9939/11728 [1:15:39<2:51:22, 5.75s/it] {'loss': 0.4678, 'learning_rate': 1.1958025957432816e-06, 'epoch': 0.85} + 85%|████████▍ | 9939/11728 [1:15:39<2:51:22, 5.75s/it] 85%|████████▍ | 9940/11728 [1:15:45<2:49:19, 5.68s/it] {'loss': 0.4447, 'learning_rate': 1.1944933955001226e-06, 'epoch': 0.85} + 85%|████████▍ | 9940/11728 [1:15:45<2:49:19, 5.68s/it] 85%|████████▍ | 9941/11728 [1:15:51<2:50:34, 5.73s/it] {'loss': 0.4352, 'learning_rate': 1.1931848668016576e-06, 'epoch': 0.85} + 85%|████████▍ | 9941/11728 [1:15:51<2:50:34, 5.73s/it] 85%|████████▍ | 9942/11728 [1:15:56<2:52:08, 5.78s/it] {'loss': 0.4645, 'learning_rate': 1.1918770097476818e-06, 'epoch': 0.85} + 85%|████████▍ | 9942/11728 [1:15:56<2:52:08, 5.78s/it] 85%|████████▍ | 9943/11728 [1:16:03<2:55:46, 5.91s/it] {'loss': 0.4762, 'learning_rate': 1.190569824437937e-06, 'epoch': 0.85} + 85%|████████▍ | 9943/11728 [1:16:03<2:55:46, 5.91s/it] 85%|████████▍ | 9944/11728 [1:16:08<2:53:05, 5.82s/it] {'loss': 0.4612, 'learning_rate': 1.1892633109721163e-06, 'epoch': 0.85} + 85%|████████▍ | 9944/11728 [1:16:08<2:53:05, 5.82s/it] 85%|████████▍ | 9945/11728 [1:16:14<2:54:26, 5.87s/it] {'loss': 0.4469, 'learning_rate': 1.1879574694498597e-06, 'epoch': 0.85} + 85%|████████▍ | 9945/11728 [1:16:14<2:54:26, 5.87s/it] 85%|████████▍ | 9946/11728 [1:16:20<2:54:21, 5.87s/it] {'loss': 0.4616, 'learning_rate': 1.1866522999707553e-06, 'epoch': 0.85} + 85%|████████▍ | 9946/11728 [1:16:20<2:54:21, 5.87s/it] 85%|████████▍ | 9947/11728 [1:16:26<2:53:17, 5.84s/it] {'loss': 0.4556, 'learning_rate': 1.18534780263434e-06, 'epoch': 0.85} + 85%|████████▍ | 9947/11728 [1:16:26<2:53:17, 5.84s/it] 85%|████████▍ | 9948/11728 [1:16:32<2:52:45, 5.82s/it] {'loss': 0.4508, 'learning_rate': 1.1840439775401025e-06, 'epoch': 0.85} + 85%|████████▍ | 9948/11728 [1:16:32<2:52:45, 5.82s/it] 85%|████████▍ | 9949/11728 [1:16:37<2:51:42, 5.79s/it] {'loss': 0.4642, 'learning_rate': 1.1827408247874795e-06, 'epoch': 0.85} + 85%|████████▍ | 9949/11728 [1:16:37<2:51:42, 5.79s/it]6 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +0 1 AutoResumeHook: Checking whether to suspend... +AutoResumeHook: Checking whether to suspend... + 85%|████████▍ | 9950/11728 [1:16:43<2:51:01, 5.77s/it] {'loss': 0.4319, 'learning_rate': 1.1814383444758493e-06, 'epoch': 0.85} + 85%|████████▍ | 9950/11728 [1:16:43<2:51:01, 5.77s/it] 85%|████████▍ | 9951/11728 [1:16:49<2:52:53, 5.84s/it] {'loss': 0.4683, 'learning_rate': 1.1801365367045448e-06, 'epoch': 0.85} + 85%|████████▍ | 9951/11728 [1:16:49<2:52:53, 5.84s/it] 85%|████████▍ | 9952/11728 [1:16:55<2:52:17, 5.82s/it] {'loss': 0.4406, 'learning_rate': 1.1788354015728543e-06, 'epoch': 0.85} + 85%|████████▍ | 9952/11728 [1:16:55<2:52:17, 5.82s/it] 85%|████████▍ | 9953/11728 [1:17:01<2:52:48, 5.84s/it] {'loss': 0.4673, 'learning_rate': 1.1775349391800017e-06, 'epoch': 0.85} + 85%|████████▍ | 9953/11728 [1:17:01<2:52:48, 5.84s/it] 85%|████████▍ | 9954/11728 [1:17:07<2:53:11, 5.86s/it] {'loss': 0.4466, 'learning_rate': 1.1762351496251666e-06, 'epoch': 0.85} + 85%|████████▍ | 9954/11728 [1:17:07<2:53:11, 5.86s/it] 85%|████████▍ | 9955/11728 [1:17:13<2:53:59, 5.89s/it] {'loss': 0.4727, 'learning_rate': 1.1749360330074799e-06, 'epoch': 0.85} + 85%|████████▍ | 9955/11728 [1:17:13<2:53:59, 5.89s/it] 85%|████████▍ | 9956/11728 [1:17:19<2:54:50, 5.92s/it] {'loss': 0.4624, 'learning_rate': 1.173637589426011e-06, 'epoch': 0.85} + 85%|████████▍ | 9956/11728 [1:17:19<2:54:50, 5.92s/it] 85%|████████▍ | 9957/11728 [1:17:24<2:53:42, 5.88s/it] {'loss': 0.4744, 'learning_rate': 1.1723398189797897e-06, 'epoch': 0.85} + 85%|████████▍ | 9957/11728 [1:17:24<2:53:42, 5.88s/it] 85%|████████▍ | 9958/11728 [1:17:30<2:51:59, 5.83s/it] {'loss': 0.4442, 'learning_rate': 1.171042721767791e-06, 'epoch': 0.85} + 85%|████████▍ | 9958/11728 [1:17:30<2:51:59, 5.83s/it] 85%|████████▍ | 9959/11728 [1:17:36<2:51:47, 5.83s/it] {'loss': 0.4704, 'learning_rate': 1.1697462978889307e-06, 'epoch': 0.85} + 85%|████████▍ | 9959/11728 [1:17:36<2:51:47, 5.83s/it] 85%|████████▍ | 9960/11728 [1:17:42<2:50:31, 5.79s/it] {'loss': 0.4662, 'learning_rate': 1.1684505474420826e-06, 'epoch': 0.85} + 85%|████████▍ | 9960/11728 [1:17:42<2:50:31, 5.79s/it] 85%|████████▍ | 9961/11728 [1:17:48<2:52:08, 5.85s/it] {'loss': 0.4331, 'learning_rate': 1.167155470526069e-06, 'epoch': 0.85} + 85%|████████▍ | 9961/11728 [1:17:48<2:52:08, 5.85s/it] 85%|████████▍ | 9962/11728 [1:17:53<2:51:44, 5.83s/it] {'loss': 0.4693, 'learning_rate': 1.1658610672396543e-06, 'epoch': 0.85} + 85%|████████▍ | 9962/11728 [1:17:53<2:51:44, 5.83s/it] 85%|████████▍ | 9963/11728 [1:17:59<2:49:13, 5.75s/it] {'loss': 0.4713, 'learning_rate': 1.1645673376815558e-06, 'epoch': 0.85} + 85%|████████▍ | 9963/11728 [1:17:59<2:49:13, 5.75s/it] 85%|████████▍ | 9964/11728 [1:18:05<2:47:53, 5.71s/it] {'loss': 0.4438, 'learning_rate': 1.1632742819504406e-06, 'epoch': 0.85} + 85%|████████▍ | 9964/11728 [1:18:05<2:47:53, 5.71s/it] 85%|████████▍ | 9965/11728 [1:18:10<2:48:23, 5.73s/it] {'loss': 0.4595, 'learning_rate': 1.1619819001449162e-06, 'epoch': 0.85} + 85%|████████▍ | 9965/11728 [1:18:10<2:48:23, 5.73s/it] 85%|████████▍ | 9966/11728 [1:18:17<2:52:21, 5.87s/it] {'loss': 0.4424, 'learning_rate': 1.1606901923635526e-06, 'epoch': 0.85} + 85%|████████▍ | 9966/11728 [1:18:17<2:52:21, 5.87s/it] 85%|████████▍ | 9967/11728 [1:18:22<2:51:27, 5.84s/it] {'loss': 0.4604, 'learning_rate': 1.1593991587048604e-06, 'epoch': 0.85} + 85%|████████▍ | 9967/11728 [1:18:22<2:51:27, 5.84s/it] 85%|████████▍ | 9968/11728 [1:18:28<2:49:24, 5.78s/it] {'loss': 0.4678, 'learning_rate': 1.1581087992672936e-06, 'epoch': 0.85} + 85%|████████▍ | 9968/11728 [1:18:28<2:49:24, 5.78s/it] 85%|████████▌ | 9969/11728 [1:18:34<2:48:52, 5.76s/it] {'loss': 0.4613, 'learning_rate': 1.1568191141492624e-06, 'epoch': 0.85} + 85%|████████▌ | 9969/11728 [1:18:34<2:48:52, 5.76s/it] 85%|████████▌ | 9970/11728 [1:18:39<2:48:40, 5.76s/it] {'loss': 0.4602, 'learning_rate': 1.1555301034491284e-06, 'epoch': 0.85} + 85%|████████▌ | 9970/11728 [1:18:39<2:48:40, 5.76s/it] 85%|████████▌ | 9971/11728 [1:18:45<2:47:21, 5.72s/it] {'loss': 0.4431, 'learning_rate': 1.1542417672651917e-06, 'epoch': 0.85} + 85%|████████▌ | 9971/11728 [1:18:45<2:47:21, 5.72s/it] 85%|████████▌ | 9972/11728 [1:18:51<2:47:31, 5.72s/it] {'loss': 0.4528, 'learning_rate': 1.1529541056957072e-06, 'epoch': 0.85} + 85%|████████▌ | 9972/11728 [1:18:51<2:47:31, 5.72s/it] 85%|████████▌ | 9973/11728 [1:18:57<2:47:17, 5.72s/it] {'loss': 0.4677, 'learning_rate': 1.1516671188388805e-06, 'epoch': 0.85} + 85%|████████▌ | 9973/11728 [1:18:57<2:47:17, 5.72s/it] 85%|████████▌ | 9974/11728 [1:19:02<2:47:51, 5.74s/it] {'loss': 0.4563, 'learning_rate': 1.1503808067928557e-06, 'epoch': 0.85} + 85%|████████▌ | 9974/11728 [1:19:02<2:47:51, 5.74s/it] 85%|████████▌ | 9975/11728 [1:19:08<2:49:17, 5.79s/it] {'loss': 0.4433, 'learning_rate': 1.1490951696557385e-06, 'epoch': 0.85} + 85%|████████▌ | 9975/11728 [1:19:08<2:49:17, 5.79s/it] 85%|████████▌ | 9976/11728 [1:19:14<2:45:45, 5.68s/it] {'loss': 0.4282, 'learning_rate': 1.147810207525577e-06, 'epoch': 0.85} + 85%|████████▌ | 9976/11728 [1:19:14<2:45:45, 5.68s/it] 85%|████████▌ | 9977/11728 [1:19:20<2:49:35, 5.81s/it] {'loss': 0.4705, 'learning_rate': 1.146525920500363e-06, 'epoch': 0.85} + 85%|████████▌ | 9977/11728 [1:19:20<2:49:35, 5.81s/it] 85%|████████▌ | 9978/11728 [1:19:26<2:51:55, 5.89s/it] {'loss': 0.4594, 'learning_rate': 1.1452423086780463e-06, 'epoch': 0.85} + 85%|████████▌ | 9978/11728 [1:19:26<2:51:55, 5.89s/it] 85%|████████▌ | 9979/11728 [1:19:32<2:50:11, 5.84s/it] {'loss': 0.4722, 'learning_rate': 1.143959372156518e-06, 'epoch': 0.85} + 85%|████████▌ | 9979/11728 [1:19:32<2:50:11, 5.84s/it] 85%|████████▌ | 9980/11728 [1:19:37<2:49:14, 5.81s/it] {'loss': 0.4484, 'learning_rate': 1.14267711103362e-06, 'epoch': 0.85} + 85%|████████▌ | 9980/11728 [1:19:37<2:49:14, 5.81s/it] 85%|████████▌ | 9981/11728 [1:19:43<2:48:38, 5.79s/it] {'loss': 0.4551, 'learning_rate': 1.1413955254071441e-06, 'epoch': 0.85} + 85%|████████▌ | 9981/11728 [1:19:43<2:48:38, 5.79s/it] 85%|████████▌ | 9982/11728 [1:19:49<2:48:41, 5.80s/it] {'loss': 0.4644, 'learning_rate': 1.140114615374831e-06, 'epoch': 0.85} + 85%|████████▌ | 9982/11728 [1:19:49<2:48:41, 5.80s/it] 85%|████████▌ | 9983/11728 [1:19:54<2:47:24, 5.76s/it] {'loss': 0.4479, 'learning_rate': 1.1388343810343627e-06, 'epoch': 0.85} + 85%|████████▌ | 9983/11728 [1:19:55<2:47:24, 5.76s/it] 85%|████████▌ | 9984/11728 [1:20:00<2:47:47, 5.77s/it] {'loss': 0.444, 'learning_rate': 1.137554822483381e-06, 'epoch': 0.85} + 85%|████████▌ | 9984/11728 [1:20:00<2:47:47, 5.77s/it] 85%|████████▌ | 9985/11728 [1:20:06<2:49:18, 5.83s/it] {'loss': 0.4556, 'learning_rate': 1.136275939819469e-06, 'epoch': 0.85} + 85%|████████▌ | 9985/11728 [1:20:06<2:49:18, 5.83s/it] 85%|████████▌ | 9986/11728 [1:20:13<2:53:07, 5.96s/it] {'loss': 0.4528, 'learning_rate': 1.1349977331401573e-06, 'epoch': 0.85} + 85%|████████▌ | 9986/11728 [1:20:13<2:53:07, 5.96s/it] 85%|████████▌ | 9987/11728 [1:20:18<2:52:44, 5.95s/it] {'loss': 0.452, 'learning_rate': 1.1337202025429295e-06, 'epoch': 0.85} + 85%|████████▌ | 9987/11728 [1:20:18<2:52:44, 5.95s/it] 85%|████████▌ | 9988/11728 [1:20:24<2:50:19, 5.87s/it] {'loss': 0.4551, 'learning_rate': 1.132443348125214e-06, 'epoch': 0.85} + 85%|████████▌ | 9988/11728 [1:20:24<2:50:19, 5.87s/it] 85%|████████▌ | 9989/11728 [1:20:30<2:49:33, 5.85s/it] {'loss': 0.453, 'learning_rate': 1.1311671699843896e-06, 'epoch': 0.85} + 85%|████████▌ | 9989/11728 [1:20:30<2:49:33, 5.85s/it] 85%|████████▌ | 9990/11728 [1:20:36<2:48:25, 5.81s/it] {'loss': 0.4525, 'learning_rate': 1.129891668217783e-06, 'epoch': 0.85} + 85%|████████▌ | 9990/11728 [1:20:36<2:48:25, 5.81s/it] 85%|████████▌ | 9991/11728 [1:20:42<2:49:05, 5.84s/it] {'loss': 0.4557, 'learning_rate': 1.128616842922672e-06, 'epoch': 0.85} + 85%|████████▌ | 9991/11728 [1:20:42<2:49:05, 5.84s/it] 85%|████████▌ | 9992/11728 [1:20:47<2:49:20, 5.85s/it] {'loss': 0.4703, 'learning_rate': 1.1273426941962728e-06, 'epoch': 0.85} + 85%|████████▌ | 9992/11728 [1:20:47<2:49:20, 5.85s/it] 85%|████████▌ | 9993/11728 [1:20:53<2:47:18, 5.79s/it] {'loss': 0.4475, 'learning_rate': 1.1260692221357638e-06, 'epoch': 0.85} + 85%|████████▌ | 9993/11728 [1:20:53<2:47:18, 5.79s/it] 85%|████████▌ | 9994/11728 [1:20:59<2:46:29, 5.76s/it] {'loss': 0.4385, 'learning_rate': 1.1247964268382661e-06, 'epoch': 0.85} + 85%|████████▌ | 9994/11728 [1:20:59<2:46:29, 5.76s/it] 85%|████████▌ | 9995/11728 [1:21:05<2:46:05, 5.75s/it] {'loss': 0.466, 'learning_rate': 1.123524308400844e-06, 'epoch': 0.85} + 85%|████████▌ | 9995/11728 [1:21:05<2:46:05, 5.75s/it] 85%|████████▌ | 9996/11728 [1:21:10<2:44:39, 5.70s/it] {'loss': 0.4458, 'learning_rate': 1.1222528669205158e-06, 'epoch': 0.85} + 85%|████████▌ | 9996/11728 [1:21:10<2:44:39, 5.70s/it] 85%|████████▌ | 9997/11728 [1:21:16<2:43:32, 5.67s/it] {'loss': 0.4526, 'learning_rate': 1.120982102494247e-06, 'epoch': 0.85} + 85%|████████▌ | 9997/11728 [1:21:16<2:43:32, 5.67s/it] 85%|████████▌ | 9998/11728 [1:21:22<2:46:04, 5.76s/it] {'loss': 0.4408, 'learning_rate': 1.1197120152189522e-06, 'epoch': 0.85} + 85%|████████▌ | 9998/11728 [1:21:22<2:46:04, 5.76s/it] 85%|████████▌ | 9999/11728 [1:21:27<2:44:09, 5.70s/it] {'loss': 0.4658, 'learning_rate': 1.1184426051914932e-06, 'epoch': 0.85} + 85%|████████▌ | 9999/11728 [1:21:27<2:44:09, 5.70s/it]3 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... +0 7 AutoResumeHook: Checking whether to suspend...AutoResumeHook: Checking whether to suspend... + + 85%|████████▌ | 10000/11728 [1:21:33<2:44:35, 5.72s/it]1 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4664, 'learning_rate': 1.1171738725086833e-06, 'epoch': 0.85} + 85%|████████▌ | 10000/11728 [1:21:33<2:44:35, 5.72s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-10000/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-10000/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-10000/mm_projector +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/torch/nn/modules/module.py:1802: UserWarning: Positional args are being deprecated, use kwargs instead. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details. + warnings.warn( + 85%|████████▌ | 10001/11728 [1:22:09<7:08:15, 14.88s/it] {'loss': 0.4579, 'learning_rate': 1.1159058172672732e-06, 'epoch': 0.85} + 85%|████████▌ | 10001/11728 [1:22:09<7:08:15, 14.88s/it] 85%|████████▌ | 10002/11728 [1:22:15<5:51:40, 12.23s/it] {'loss': 0.4572, 'learning_rate': 1.1146384395639786e-06, 'epoch': 0.85} + 85%|████████▌ | 10002/11728 [1:22:15<5:51:40, 12.23s/it] 85%|████████▌ | 10003/11728 [1:22:21<4:55:09, 10.27s/it] {'loss': 0.4424, 'learning_rate': 1.1133717394954536e-06, 'epoch': 0.85} + 85%|████████▌ | 10003/11728 [1:22:21<4:55:09, 10.27s/it] 85%|████████▌ | 10004/11728 [1:22:27<4:15:52, 8.91s/it] {'loss': 0.4572, 'learning_rate': 1.1121057171582984e-06, 'epoch': 0.85} + 85%|████████▌ | 10004/11728 [1:22:27<4:15:52, 8.91s/it] 85%|████████▌ | 10005/11728 [1:22:32<3:48:08, 7.94s/it] {'loss': 0.4548, 'learning_rate': 1.1108403726490669e-06, 'epoch': 0.85} + 85%|████████▌ | 10005/11728 [1:22:32<3:48:08, 7.94s/it] 85%|████████▌ | 10006/11728 [1:22:38<3:29:30, 7.30s/it] {'loss': 0.4449, 'learning_rate': 1.1095757060642588e-06, 'epoch': 0.85} + 85%|████████▌ | 10006/11728 [1:22:38<3:29:30, 7.30s/it] 85%|████████▌ | 10007/11728 [1:22:44<3:17:44, 6.89s/it] {'loss': 0.4556, 'learning_rate': 1.1083117175003245e-06, 'epoch': 0.85} + 85%|████████▌ | 10007/11728 [1:22:44<3:17:44, 6.89s/it] 85%|████████▌ | 10008/11728 [1:22:50<3:07:18, 6.53s/it] {'loss': 0.4641, 'learning_rate': 1.1070484070536613e-06, 'epoch': 0.85} + 85%|████████▌ | 10008/11728 [1:22:50<3:07:18, 6.53s/it] 85%|████████▌ | 10009/11728 [1:22:56<3:00:24, 6.30s/it] {'loss': 0.474, 'learning_rate': 1.1057857748206148e-06, 'epoch': 0.85} + 85%|████████▌ | 10009/11728 [1:22:56<3:00:24, 6.30s/it] 85%|████████▌ | 10010/11728 [1:23:02<2:59:24, 6.27s/it] {'loss': 0.4553, 'learning_rate': 1.104523820897474e-06, 'epoch': 0.85} + 85%|████████▌ | 10010/11728 [1:23:02<2:59:24, 6.27s/it] 85%|████████▌ | 10011/11728 [1:23:08<2:56:01, 6.15s/it] {'loss': 0.4554, 'learning_rate': 1.1032625453804835e-06, 'epoch': 0.85} + 85%|████████▌ | 10011/11728 [1:23:08<2:56:01, 6.15s/it] 85%|████████▌ | 10012/11728 [1:23:14<2:55:05, 6.12s/it] {'loss': 0.4509, 'learning_rate': 1.1020019483658385e-06, 'epoch': 0.85} + 85%|████████▌ | 10012/11728 [1:23:14<2:55:05, 6.12s/it] 85%|████████▌ | 10013/11728 [1:23:19<2:50:03, 5.95s/it] {'loss': 0.4401, 'learning_rate': 1.1007420299496696e-06, 'epoch': 0.85} + 85%|████████▌ | 10013/11728 [1:23:19<2:50:03, 5.95s/it] 85%|████████▌ | 10014/11728 [1:23:25<2:49:59, 5.95s/it] {'loss': 0.4813, 'learning_rate': 1.0994827902280681e-06, 'epoch': 0.85} + 85%|████████▌ | 10014/11728 [1:23:25<2:49:59, 5.95s/it] 85%|████████▌ | 10015/11728 [1:23:31<2:48:39, 5.91s/it] {'loss': 0.4585, 'learning_rate': 1.0982242292970668e-06, 'epoch': 0.85} + 85%|████████▌ | 10015/11728 [1:23:31<2:48:39, 5.91s/it] 85%|████████▌ | 10016/11728 [1:23:37<2:49:01, 5.92s/it] {'loss': 0.4447, 'learning_rate': 1.0969663472526492e-06, 'epoch': 0.85} + 85%|████████▌ | 10016/11728 [1:23:37<2:49:01, 5.92s/it] 85%|████████▌ | 10017/11728 [1:23:43<2:47:40, 5.88s/it] {'loss': 0.4292, 'learning_rate': 1.0957091441907475e-06, 'epoch': 0.85} + 85%|████████▌ | 10017/11728 [1:23:43<2:47:40, 5.88s/it] 85%|████████▌ | 10018/11728 [1:23:49<2:49:00, 5.93s/it] {'loss': 0.484, 'learning_rate': 1.0944526202072424e-06, 'epoch': 0.85} + 85%|████████▌ | 10018/11728 [1:23:49<2:49:00, 5.93s/it] 85%|████████▌ | 10019/11728 [1:23:55<2:50:02, 5.97s/it] {'loss': 0.4516, 'learning_rate': 1.093196775397959e-06, 'epoch': 0.85} + 85%|████████▌ | 10019/11728 [1:23:55<2:50:02, 5.97s/it] 85%|████████▌ | 10020/11728 [1:24:01<2:49:45, 5.96s/it] {'loss': 0.451, 'learning_rate': 1.0919416098586711e-06, 'epoch': 0.85} + 85%|████████▌ | 10020/11728 [1:24:01<2:49:45, 5.96s/it] 85%|████████▌ | 10021/11728 [1:24:06<2:45:32, 5.82s/it] {'loss': 0.4504, 'learning_rate': 1.0906871236851114e-06, 'epoch': 0.85} + 85%|████████▌ | 10021/11728 [1:24:06<2:45:32, 5.82s/it] 85%|████████▌ | 10022/11728 [1:24:12<2:44:56, 5.80s/it] {'loss': 0.4458, 'learning_rate': 1.0894333169729432e-06, 'epoch': 0.85} + 85%|████████▌ | 10022/11728 [1:24:12<2:44:56, 5.80s/it] 85%|████████▌ | 10023/11728 [1:24:18<2:42:49, 5.73s/it] {'loss': 0.455, 'learning_rate': 1.0881801898177924e-06, 'epoch': 0.85} + 85%|████████▌ | 10023/11728 [1:24:18<2:42:49, 5.73s/it] 85%|████████▌ | 10024/11728 [1:24:24<2:46:01, 5.85s/it] {'loss': 0.4511, 'learning_rate': 1.0869277423152248e-06, 'epoch': 0.85} + 85%|████████▌ | 10024/11728 [1:24:24<2:46:01, 5.85s/it] 85%|████████▌ | 10025/11728 [1:24:30<2:47:06, 5.89s/it] {'loss': 0.4793, 'learning_rate': 1.0856759745607592e-06, 'epoch': 0.85} + 85%|████████▌ | 10025/11728 [1:24:30<2:47:06, 5.89s/it] 85%|████████▌ | 10026/11728 [1:24:35<2:45:06, 5.82s/it] {'loss': 0.4239, 'learning_rate': 1.0844248866498598e-06, 'epoch': 0.85} + 85%|████████▌ | 10026/11728 [1:24:35<2:45:06, 5.82s/it] 85%|████████▌ | 10027/11728 [1:24:41<2:42:04, 5.72s/it] {'loss': 0.4493, 'learning_rate': 1.083174478677942e-06, 'epoch': 0.85} + 85%|████████▌ | 10027/11728 [1:24:41<2:42:04, 5.72s/it] 86%|████████▌ | 10028/11728 [1:24:47<2:42:30, 5.74s/it] {'loss': 0.4518, 'learning_rate': 1.0819247507403629e-06, 'epoch': 0.86} + 86%|████████▌ | 10028/11728 [1:24:47<2:42:30, 5.74s/it] 86%|████████▌ | 10029/11728 [1:24:52<2:43:11, 5.76s/it] {'loss': 0.457, 'learning_rate': 1.0806757029324321e-06, 'epoch': 0.86} + 86%|████████▌ | 10029/11728 [1:24:52<2:43:11, 5.76s/it] 86%|████████▌ | 10030/11728 [1:24:58<2:43:29, 5.78s/it] {'loss': 0.4613, 'learning_rate': 1.0794273353494144e-06, 'epoch': 0.86} + 86%|████████▌ | 10030/11728 [1:24:58<2:43:29, 5.78s/it] 86%|████████▌ | 10031/11728 [1:25:04<2:43:21, 5.78s/it] {'loss': 0.4527, 'learning_rate': 1.078179648086507e-06, 'epoch': 0.86} + 86%|████████▌ | 10031/11728 [1:25:04<2:43:21, 5.78s/it] 86%|████████▌ | 10032/11728 [1:25:10<2:44:51, 5.83s/it] {'loss': 0.4446, 'learning_rate': 1.076932641238868e-06, 'epoch': 0.86} + 86%|████████▌ | 10032/11728 [1:25:10<2:44:51, 5.83s/it] 86%|████████▌ | 10033/11728 [1:25:16<2:44:24, 5.82s/it] {'loss': 0.4473, 'learning_rate': 1.0756863149015972e-06, 'epoch': 0.86} + 86%|████████▌ | 10033/11728 [1:25:16<2:44:24, 5.82s/it] 86%|████████▌ | 10034/11728 [1:25:22<2:43:51, 5.80s/it] {'loss': 0.4778, 'learning_rate': 1.0744406691697474e-06, 'epoch': 0.86} + 86%|████████▌ | 10034/11728 [1:25:22<2:43:51, 5.80s/it] 86%|████████▌ | 10035/11728 [1:25:28<2:44:47, 5.84s/it] {'loss': 0.4777, 'learning_rate': 1.0731957041383146e-06, 'epoch': 0.86} + 86%|████████▌ | 10035/11728 [1:25:28<2:44:47, 5.84s/it] 86%|████████▌ | 10036/11728 [1:25:33<2:42:25, 5.76s/it] {'loss': 0.4481, 'learning_rate': 1.0719514199022473e-06, 'epoch': 0.86} + 86%|████████▌ | 10036/11728 [1:25:33<2:42:25, 5.76s/it] 86%|████████▌ | 10037/11728 [1:25:39<2:43:37, 5.81s/it] {'loss': 0.4598, 'learning_rate': 1.0707078165564366e-06, 'epoch': 0.86} + 86%|████████▌ | 10037/11728 [1:25:39<2:43:37, 5.81s/it] 86%|████████▌ | 10038/11728 [1:25:45<2:46:18, 5.90s/it] {'loss': 0.4915, 'learning_rate': 1.0694648941957241e-06, 'epoch': 0.86} + 86%|████████▌ | 10038/11728 [1:25:45<2:46:18, 5.90s/it] 86%|████████▌ | 10039/11728 [1:25:51<2:49:41, 6.03s/it] {'loss': 0.4472, 'learning_rate': 1.0682226529149076e-06, 'epoch': 0.86} + 86%|████████▌ | 10039/11728 [1:25:51<2:49:41, 6.03s/it] 86%|████████▌ | 10040/11728 [1:25:57<2:46:36, 5.92s/it] {'loss': 0.4595, 'learning_rate': 1.0669810928087176e-06, 'epoch': 0.86} + 86%|████████▌ | 10040/11728 [1:25:57<2:46:36, 5.92s/it] 86%|████████▌ | 10041/11728 [1:26:03<2:45:38, 5.89s/it] {'loss': 0.4385, 'learning_rate': 1.0657402139718442e-06, 'epoch': 0.86} + 86%|████████▌ | 10041/11728 [1:26:03<2:45:38, 5.89s/it] 86%|████████▌ | 10042/11728 [1:26:09<2:43:57, 5.84s/it] {'loss': 0.4318, 'learning_rate': 1.0645000164989217e-06, 'epoch': 0.86} + 86%|████████▌ | 10042/11728 [1:26:09<2:43:57, 5.84s/it] 86%|████████▌ | 10043/11728 [1:26:14<2:43:56, 5.84s/it] {'loss': 0.4712, 'learning_rate': 1.063260500484532e-06, 'epoch': 0.86} + 86%|████████▌ | 10043/11728 [1:26:14<2:43:56, 5.84s/it] 86%|████████▌ | 10044/11728 [1:26:20<2:43:21, 5.82s/it] {'loss': 0.4646, 'learning_rate': 1.0620216660232074e-06, 'epoch': 0.86} + 86%|████████▌ | 10044/11728 [1:26:20<2:43:21, 5.82s/it] 86%|████████▌ | 10045/11728 [1:26:27<2:46:53, 5.95s/it] {'loss': 0.4607, 'learning_rate': 1.0607835132094258e-06, 'epoch': 0.86} + 86%|████████▌ | 10045/11728 [1:26:27<2:46:53, 5.95s/it] 86%|████████▌ | 10046/11728 [1:26:32<2:43:50, 5.84s/it] {'loss': 0.4341, 'learning_rate': 1.0595460421376125e-06, 'epoch': 0.86} + 86%|████████▌ | 10046/11728 [1:26:32<2:43:50, 5.84s/it] 86%|████████▌ | 10047/11728 [1:26:38<2:42:30, 5.80s/it] {'loss': 0.4243, 'learning_rate': 1.0583092529021411e-06, 'epoch': 0.86} + 86%|████████▌ | 10047/11728 [1:26:38<2:42:30, 5.80s/it] 86%|████████▌ | 10048/11728 [1:26:43<2:40:21, 5.73s/it] {'loss': 0.4519, 'learning_rate': 1.0570731455973415e-06, 'epoch': 0.86} + 86%|████████▌ | 10048/11728 [1:26:43<2:40:21, 5.73s/it] 86%|████████▌ | 10049/11728 [1:26:49<2:40:15, 5.73s/it] {'loss': 0.4485, 'learning_rate': 1.0558377203174764e-06, 'epoch': 0.86} + 86%|████████▌ | 10049/11728 [1:26:49<2:40:15, 5.73s/it]5 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... +02 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... + 86%|████████▌ | 10050/11728 [1:26:55<2:39:10, 5.69s/it]4 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... + {'loss': 0.461, 'learning_rate': 1.054602977156768e-06, 'epoch': 0.86} + 86%|████████▌ | 10050/11728 [1:26:55<2:39:10, 5.69s/it] 86%|████████▌ | 10051/11728 [1:27:01<2:43:15, 5.84s/it] {'loss': 0.4834, 'learning_rate': 1.053368916209382e-06, 'epoch': 0.86} + 86%|████████▌ | 10051/11728 [1:27:01<2:43:15, 5.84s/it] 86%|████████▌ | 10052/11728 [1:27:07<2:41:21, 5.78s/it] {'loss': 0.4525, 'learning_rate': 1.052135537569433e-06, 'epoch': 0.86} + 86%|████████▌ | 10052/11728 [1:27:07<2:41:21, 5.78s/it] 86%|████████▌ | 10053/11728 [1:27:12<2:41:43, 5.79s/it] {'loss': 0.4573, 'learning_rate': 1.0509028413309851e-06, 'epoch': 0.86} + 86%|████████▌ | 10053/11728 [1:27:12<2:41:43, 5.79s/it] 86%|████████▌ | 10054/11728 [1:27:18<2:40:24, 5.75s/it] {'loss': 0.4669, 'learning_rate': 1.0496708275880497e-06, 'epoch': 0.86} + 86%|████████▌ | 10054/11728 [1:27:18<2:40:24, 5.75s/it] 86%|████████▌ | 10055/11728 [1:27:24<2:43:00, 5.85s/it] {'loss': 0.4563, 'learning_rate': 1.0484394964345812e-06, 'epoch': 0.86} + 86%|████████▌ | 10055/11728 [1:27:24<2:43:00, 5.85s/it] 86%|████████▌ | 10056/11728 [1:27:30<2:41:47, 5.81s/it] {'loss': 0.447, 'learning_rate': 1.0472088479644882e-06, 'epoch': 0.86} + 86%|████████▌ | 10056/11728 [1:27:30<2:41:47, 5.81s/it] 86%|████████▌ | 10057/11728 [1:27:36<2:41:58, 5.82s/it] {'loss': 0.4527, 'learning_rate': 1.0459788822716255e-06, 'epoch': 0.86} + 86%|████████▌ | 10057/11728 [1:27:36<2:41:58, 5.82s/it] 86%|████████▌ | 10058/11728 [1:27:41<2:41:24, 5.80s/it] {'loss': 0.4441, 'learning_rate': 1.0447495994497958e-06, 'epoch': 0.86} + 86%|████████▌ | 10058/11728 [1:27:41<2:41:24, 5.80s/it] 86%|████████▌ | 10059/11728 [1:27:47<2:43:18, 5.87s/it] {'loss': 0.4777, 'learning_rate': 1.0435209995927476e-06, 'epoch': 0.86} + 86%|████████▌ | 10059/11728 [1:27:47<2:43:18, 5.87s/it] 86%|████████▌ | 10060/11728 [1:27:53<2:40:56, 5.79s/it] {'loss': 0.4445, 'learning_rate': 1.0422930827941803e-06, 'epoch': 0.86} + 86%|████████▌ | 10060/11728 [1:27:53<2:40:56, 5.79s/it] 86%|████████▌ | 10061/11728 [1:27:59<2:41:09, 5.80s/it] {'loss': 0.4542, 'learning_rate': 1.041065849147741e-06, 'epoch': 0.86} + 86%|████████▌ | 10061/11728 [1:27:59<2:41:09, 5.80s/it] 86%|████████▌ | 10062/11728 [1:28:05<2:41:17, 5.81s/it] {'loss': 0.479, 'learning_rate': 1.0398392987470208e-06, 'epoch': 0.86} + 86%|████████▌ | 10062/11728 [1:28:05<2:41:17, 5.81s/it] 86%|████████▌ | 10063/11728 [1:28:10<2:40:44, 5.79s/it] {'loss': 0.4476, 'learning_rate': 1.0386134316855667e-06, 'epoch': 0.86} + 86%|████████▌ | 10063/11728 [1:28:10<2:40:44, 5.79s/it] 86%|████████▌ | 10064/11728 [1:28:16<2:39:59, 5.77s/it] {'loss': 0.4483, 'learning_rate': 1.037388248056862e-06, 'epoch': 0.86} + 86%|████████▌ | 10064/11728 [1:28:16<2:39:59, 5.77s/it] 86%|████████▌ | 10065/11728 [1:28:22<2:38:38, 5.72s/it] {'loss': 0.4409, 'learning_rate': 1.0361637479543474e-06, 'epoch': 0.86} + 86%|████████▌ | 10065/11728 [1:28:22<2:38:38, 5.72s/it] 86%|████████▌ | 10066/11728 [1:28:28<2:39:52, 5.77s/it] {'loss': 0.4653, 'learning_rate': 1.034939931471408e-06, 'epoch': 0.86} + 86%|████████▌ | 10066/11728 [1:28:28<2:39:52, 5.77s/it] 86%|████████▌ | 10067/11728 [1:28:34<2:41:39, 5.84s/it] {'loss': 0.4398, 'learning_rate': 1.0337167987013785e-06, 'epoch': 0.86} + 86%|████████▌ | 10067/11728 [1:28:34<2:41:39, 5.84s/it] 86%|████████▌ | 10068/11728 [1:28:39<2:41:05, 5.82s/it] {'loss': 0.452, 'learning_rate': 1.0324943497375383e-06, 'epoch': 0.86} + 86%|████████▌ | 10068/11728 [1:28:39<2:41:05, 5.82s/it] 86%|████████▌ | 10069/11728 [1:28:45<2:39:21, 5.76s/it] {'loss': 0.4388, 'learning_rate': 1.0312725846731174e-06, 'epoch': 0.86} + 86%|████████▌ | 10069/11728 [1:28:45<2:39:21, 5.76s/it] 86%|████████▌ | 10070/11728 [1:28:51<2:40:39, 5.81s/it] {'loss': 0.4548, 'learning_rate': 1.0300515036012926e-06, 'epoch': 0.86} + 86%|████████▌ | 10070/11728 [1:28:51<2:40:39, 5.81s/it] 86%|████████▌ | 10071/11728 [1:28:57<2:40:31, 5.81s/it] {'loss': 0.4606, 'learning_rate': 1.028831106615188e-06, 'epoch': 0.86} + 86%|████████▌ | 10071/11728 [1:28:57<2:40:31, 5.81s/it] 86%|████████▌ | 10072/11728 [1:29:02<2:38:58, 5.76s/it] {'loss': 0.4446, 'learning_rate': 1.0276113938078768e-06, 'epoch': 0.86} + 86%|████████▌ | 10072/11728 [1:29:02<2:38:58, 5.76s/it] 86%|████████▌ | 10073/11728 [1:29:08<2:36:55, 5.69s/it] {'loss': 0.4434, 'learning_rate': 1.0263923652723816e-06, 'epoch': 0.86} + 86%|████████▌ | 10073/11728 [1:29:08<2:36:55, 5.69s/it] 86%|████████▌ | 10074/11728 [1:29:14<2:36:34, 5.68s/it] {'loss': 0.4432, 'learning_rate': 1.0251740211016658e-06, 'epoch': 0.86} + 86%|████████▌ | 10074/11728 [1:29:14<2:36:34, 5.68s/it] 86%|████████▌ | 10075/11728 [1:29:20<2:38:25, 5.75s/it] {'loss': 0.4612, 'learning_rate': 1.0239563613886495e-06, 'epoch': 0.86} + 86%|████████▌ | 10075/11728 [1:29:20<2:38:25, 5.75s/it] 86%|████████▌ | 10076/11728 [1:29:25<2:36:21, 5.68s/it] {'loss': 0.4573, 'learning_rate': 1.0227393862261937e-06, 'epoch': 0.86} + 86%|████████▌ | 10076/11728 [1:29:25<2:36:21, 5.68s/it] 86%|████████▌ | 10077/11728 [1:29:31<2:35:58, 5.67s/it] {'loss': 0.4421, 'learning_rate': 1.0215230957071108e-06, 'epoch': 0.86} + 86%|████████▌ | 10077/11728 [1:29:31<2:35:58, 5.67s/it] 86%|████████▌ | 10078/11728 [1:29:37<2:38:56, 5.78s/it] {'loss': 0.4483, 'learning_rate': 1.0203074899241616e-06, 'epoch': 0.86} + 86%|████████▌ | 10078/11728 [1:29:37<2:38:56, 5.78s/it] 86%|████████▌ | 10079/11728 [1:29:43<2:39:44, 5.81s/it] {'loss': 0.4615, 'learning_rate': 1.0190925689700514e-06, 'epoch': 0.86} + 86%|████████▌ | 10079/11728 [1:29:43<2:39:44, 5.81s/it] 86%|████████▌ | 10080/11728 [1:29:48<2:39:27, 5.81s/it] {'loss': 0.4921, 'learning_rate': 1.0178783329374363e-06, 'epoch': 0.86} + 86%|████████▌ | 10080/11728 [1:29:48<2:39:27, 5.81s/it] 86%|████████▌ | 10081/11728 [1:29:54<2:40:51, 5.86s/it] {'loss': 0.4654, 'learning_rate': 1.0166647819189202e-06, 'epoch': 0.86} + 86%|████████▌ | 10081/11728 [1:29:54<2:40:51, 5.86s/it] 86%|████████▌ | 10082/11728 [1:30:00<2:41:11, 5.88s/it] {'loss': 0.4454, 'learning_rate': 1.0154519160070519e-06, 'epoch': 0.86} + 86%|████████▌ | 10082/11728 [1:30:00<2:41:11, 5.88s/it] 86%|████████▌ | 10083/11728 [1:30:06<2:39:39, 5.82s/it] {'loss': 0.4602, 'learning_rate': 1.014239735294329e-06, 'epoch': 0.86} + 86%|████████▌ | 10083/11728 [1:30:06<2:39:39, 5.82s/it] 86%|████████▌ | 10084/11728 [1:30:12<2:40:21, 5.85s/it] {'loss': 0.4664, 'learning_rate': 1.0130282398731984e-06, 'epoch': 0.86} + 86%|████████▌ | 10084/11728 [1:30:12<2:40:21, 5.85s/it] 86%|████████▌ | 10085/11728 [1:30:18<2:40:01, 5.84s/it] {'loss': 0.4709, 'learning_rate': 1.011817429836054e-06, 'epoch': 0.86} + 86%|████████▌ | 10085/11728 [1:30:18<2:40:01, 5.84s/it] 86%|████████▌ | 10086/11728 [1:30:24<2:41:20, 5.90s/it] {'loss': 0.4568, 'learning_rate': 1.0106073052752364e-06, 'epoch': 0.86} + 86%|████████▌ | 10086/11728 [1:30:24<2:41:20, 5.90s/it] 86%|████████▌ | 10087/11728 [1:30:30<2:41:20, 5.90s/it] {'loss': 0.4502, 'learning_rate': 1.0093978662830351e-06, 'epoch': 0.86} + 86%|████████▌ | 10087/11728 [1:30:30<2:41:20, 5.90s/it] 86%|████████▌ | 10088/11728 [1:30:35<2:40:23, 5.87s/it] {'loss': 0.456, 'learning_rate': 1.0081891129516896e-06, 'epoch': 0.86} + 86%|████████▌ | 10088/11728 [1:30:35<2:40:23, 5.87s/it] 86%|████████▌ | 10089/11728 [1:30:41<2:39:07, 5.82s/it] {'loss': 0.4526, 'learning_rate': 1.0069810453733774e-06, 'epoch': 0.86} + 86%|████████▌ | 10089/11728 [1:30:41<2:39:07, 5.82s/it] 86%|████████▌ | 10090/11728 [1:30:47<2:38:46, 5.82s/it] {'loss': 0.4623, 'learning_rate': 1.0057736636402382e-06, 'epoch': 0.86} + 86%|████████▌ | 10090/11728 [1:30:47<2:38:46, 5.82s/it] 86%|████████▌ | 10091/11728 [1:30:53<2:41:11, 5.91s/it] {'loss': 0.4509, 'learning_rate': 1.0045669678443504e-06, 'epoch': 0.86} + 86%|████████▌ | 10091/11728 [1:30:53<2:41:11, 5.91s/it] 86%|████████▌ | 10092/11728 [1:30:59<2:39:19, 5.84s/it] {'loss': 0.4564, 'learning_rate': 1.0033609580777392e-06, 'epoch': 0.86} + 86%|████████▌ | 10092/11728 [1:30:59<2:39:19, 5.84s/it] 86%|████████▌ | 10093/11728 [1:31:04<2:36:27, 5.74s/it] {'loss': 0.4641, 'learning_rate': 1.0021556344323812e-06, 'epoch': 0.86} + 86%|████████▌ | 10093/11728 [1:31:04<2:36:27, 5.74s/it] 86%|████████▌ | 10094/11728 [1:31:10<2:35:34, 5.71s/it] {'loss': 0.4524, 'learning_rate': 1.0009509970001985e-06, 'epoch': 0.86} + 86%|████████▌ | 10094/11728 [1:31:10<2:35:34, 5.71s/it] 86%|████████▌ | 10095/11728 [1:31:16<2:37:09, 5.77s/it] {'loss': 0.4484, 'learning_rate': 9.99747045873063e-07, 'epoch': 0.86} + 86%|████████▌ | 10095/11728 [1:31:16<2:37:09, 5.77s/it] 86%|████████▌ | 10096/11728 [1:31:22<2:36:25, 5.75s/it] {'loss': 0.4612, 'learning_rate': 9.985437811427934e-07, 'epoch': 0.86} + 86%|████████▌ | 10096/11728 [1:31:22<2:36:25, 5.75s/it] 86%|████████▌ | 10097/11728 [1:31:27<2:35:21, 5.72s/it] {'loss': 0.4455, 'learning_rate': 9.973412029011564e-07, 'epoch': 0.86} + 86%|████████▌ | 10097/11728 [1:31:27<2:35:21, 5.72s/it] 86%|████████▌ | 10098/11728 [1:31:33<2:36:23, 5.76s/it] {'loss': 0.4557, 'learning_rate': 9.961393112398599e-07, 'epoch': 0.86} + 86%|████████▌ | 10098/11728 [1:31:33<2:36:23, 5.76s/it] 86%|████████▌ | 10099/11728 [1:31:39<2:35:38, 5.73s/it] {'loss': 0.433, 'learning_rate': 9.949381062505726e-07, 'epoch': 0.86} + 86%|████████▌ | 10099/11728 [1:31:39<2:35:38, 5.73s/it]6 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... +04 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... + 86%|████████▌ | 10100/11728 [1:31:45<2:36:24, 5.76s/it]1 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4749, 'learning_rate': 9.937375880249012e-07, 'epoch': 0.86} + 86%|████████▌ | 10100/11728 [1:31:45<2:36:24, 5.76s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-10100/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-10100/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-10100/mm_projector +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/torch/nn/modules/module.py:1802: UserWarning: Positional args are being deprecated, use kwargs instead. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details. + warnings.warn( + 86%|████████▌ | 10101/11728 [1:32:18<6:17:21, 13.92s/it] {'loss': 0.4745, 'learning_rate': 9.925377566544003e-07, 'epoch': 0.86} + 86%|████████▌ | 10101/11728 [1:32:18<6:17:21, 13.92s/it] 86%|████████▌ | 10102/11728 [1:32:23<5:09:40, 11.43s/it] {'loss': 0.4432, 'learning_rate': 9.913386122305747e-07, 'epoch': 0.86} + 86%|████████▌ | 10102/11728 [1:32:23<5:09:40, 11.43s/it] 86%|████████▌ | 10103/11728 [1:32:29<4:25:05, 9.79s/it] {'loss': 0.466, 'learning_rate': 9.901401548448764e-07, 'epoch': 0.86} + 86%|████████▌ | 10103/11728 [1:32:29<4:25:05, 9.79s/it] 86%|████████▌ | 10104/11728 [1:32:35<3:54:10, 8.65s/it] {'loss': 0.4176, 'learning_rate': 9.889423845887048e-07, 'epoch': 0.86} + 86%|████████▌ | 10104/11728 [1:32:35<3:54:10, 8.65s/it] 86%|████████▌ | 10105/11728 [1:32:41<3:29:47, 7.76s/it] {'loss': 0.4752, 'learning_rate': 9.877453015534066e-07, 'epoch': 0.86} + 86%|████████▌ | 10105/11728 [1:32:41<3:29:47, 7.76s/it] 86%|████████▌ | 10106/11728 [1:32:47<3:13:53, 7.17s/it] {'loss': 0.4692, 'learning_rate': 9.865489058302791e-07, 'epoch': 0.86} + 86%|████████▌ | 10106/11728 [1:32:47<3:13:53, 7.17s/it] 86%|████████▌ | 10107/11728 [1:32:52<3:03:30, 6.79s/it] {'loss': 0.4506, 'learning_rate': 9.85353197510559e-07, 'epoch': 0.86} + 86%|████████▌ | 10107/11728 [1:32:52<3:03:30, 6.79s/it] 86%|████████▌ | 10108/11728 [1:32:58<2:55:05, 6.49s/it] {'loss': 0.4561, 'learning_rate': 9.841581766854402e-07, 'epoch': 0.86} + 86%|████████▌ | 10108/11728 [1:32:58<2:55:05, 6.49s/it] 86%|████████▌ | 10109/11728 [1:33:04<2:47:03, 6.19s/it] {'loss': 0.453, 'learning_rate': 9.829638434460609e-07, 'epoch': 0.86} + 86%|████████▌ | 10109/11728 [1:33:04<2:47:03, 6.19s/it] 86%|████████▌ | 10110/11728 [1:33:09<2:41:36, 5.99s/it] {'loss': 0.4542, 'learning_rate': 9.817701978835026e-07, 'epoch': 0.86} + 86%|████████▌ | 10110/11728 [1:33:09<2:41:36, 5.99s/it] 86%|████████▌ | 10111/11728 [1:33:15<2:41:53, 6.01s/it] {'loss': 0.4442, 'learning_rate': 9.80577240088798e-07, 'epoch': 0.86} + 86%|████████▌ | 10111/11728 [1:33:15<2:41:53, 6.01s/it] 86%|████████▌ | 10112/11728 [1:33:21<2:38:45, 5.89s/it] {'loss': 0.4604, 'learning_rate': 9.79384970152928e-07, 'epoch': 0.86} + 86%|████████▌ | 10112/11728 [1:33:21<2:38:45, 5.89s/it] 86%|████████▌ | 10113/11728 [1:33:27<2:37:49, 5.86s/it] {'loss': 0.4398, 'learning_rate': 9.781933881668203e-07, 'epoch': 0.86} + 86%|████████▌ | 10113/11728 [1:33:27<2:37:49, 5.86s/it] 86%|████████▌ | 10114/11728 [1:33:33<2:37:43, 5.86s/it] {'loss': 0.4777, 'learning_rate': 9.770024942213507e-07, 'epoch': 0.86} + 86%|████████▌ | 10114/11728 [1:33:33<2:37:43, 5.86s/it] 86%|████████▌ | 10115/11728 [1:33:38<2:37:05, 5.84s/it] {'loss': 0.4495, 'learning_rate': 9.758122884073417e-07, 'epoch': 0.86} + 86%|████████▌ | 10115/11728 [1:33:38<2:37:05, 5.84s/it] 86%|████████▋ | 10116/11728 [1:33:44<2:39:02, 5.92s/it] {'loss': 0.4469, 'learning_rate': 9.746227708155586e-07, 'epoch': 0.86} + 86%|████████▋ | 10116/11728 [1:33:44<2:39:02, 5.92s/it] 86%|████████▋ | 10117/11728 [1:33:51<2:39:54, 5.96s/it] {'loss': 0.4524, 'learning_rate': 9.734339415367254e-07, 'epoch': 0.86} + 86%|████████▋ | 10117/11728 [1:33:51<2:39:54, 5.96s/it] 86%|████████▋ | 10118/11728 [1:33:57<2:40:39, 5.99s/it] {'loss': 0.4559, 'learning_rate': 9.722458006615066e-07, 'epoch': 0.86} + 86%|████████▋ | 10118/11728 [1:33:57<2:40:39, 5.99s/it] 86%|████████▋ | 10119/11728 [1:34:02<2:38:18, 5.90s/it] {'loss': 0.4655, 'learning_rate': 9.710583482805102e-07, 'epoch': 0.86} + 86%|████████▋ | 10119/11728 [1:34:02<2:38:18, 5.90s/it] 86%|████████▋ | 10120/11728 [1:34:08<2:35:29, 5.80s/it] {'loss': 0.4364, 'learning_rate': 9.698715844842988e-07, 'epoch': 0.86} + 86%|████████▋ | 10120/11728 [1:34:08<2:35:29, 5.80s/it] 86%|████████▋ | 10121/11728 [1:34:14<2:35:53, 5.82s/it] {'loss': 0.455, 'learning_rate': 9.686855093633807e-07, 'epoch': 0.86} + 86%|████████▋ | 10121/11728 [1:34:14<2:35:53, 5.82s/it] 86%|████████▋ | 10122/11728 [1:34:20<2:35:40, 5.82s/it] {'loss': 0.4518, 'learning_rate': 9.675001230082092e-07, 'epoch': 0.86} + 86%|████████▋ | 10122/11728 [1:34:20<2:35:40, 5.82s/it] 86%|████████▋ | 10123/11728 [1:34:25<2:33:39, 5.74s/it] {'loss': 0.4498, 'learning_rate': 9.663154255091889e-07, 'epoch': 0.86} + 86%|████████▋ | 10123/11728 [1:34:25<2:33:39, 5.74s/it] 86%|████████▋ | 10124/11728 [1:34:31<2:33:48, 5.75s/it] {'loss': 0.4634, 'learning_rate': 9.651314169566694e-07, 'epoch': 0.86} + 86%|████████▋ | 10124/11728 [1:34:31<2:33:48, 5.75s/it] 86%|████████▋ | 10125/11728 [1:34:37<2:33:02, 5.73s/it] {'loss': 0.4433, 'learning_rate': 9.639480974409453e-07, 'epoch': 0.86} + 86%|████████▋ | 10125/11728 [1:34:37<2:33:02, 5.73s/it] 86%|████████▋ | 10126/11728 [1:34:42<2:33:32, 5.75s/it] {'loss': 0.4675, 'learning_rate': 9.627654670522646e-07, 'epoch': 0.86} + 86%|████████▋ | 10126/11728 [1:34:42<2:33:32, 5.75s/it] 86%|████████▋ | 10127/11728 [1:34:48<2:33:18, 5.75s/it] {'loss': 0.4464, 'learning_rate': 9.615835258808203e-07, 'epoch': 0.86} + 86%|████████▋ | 10127/11728 [1:34:48<2:33:18, 5.75s/it] 86%|████████▋ | 10128/11728 [1:34:54<2:34:10, 5.78s/it] {'loss': 0.4775, 'learning_rate': 9.604022740167496e-07, 'epoch': 0.86} + 86%|████████▋ | 10128/11728 [1:34:54<2:34:10, 5.78s/it] 86%|████████▋ | 10129/11728 [1:35:00<2:35:32, 5.84s/it] {'loss': 0.448, 'learning_rate': 9.5922171155014e-07, 'epoch': 0.86} + 86%|████████▋ | 10129/11728 [1:35:00<2:35:32, 5.84s/it] 86%|████████▋ | 10130/11728 [1:35:06<2:35:27, 5.84s/it] {'loss': 0.4555, 'learning_rate': 9.580418385710278e-07, 'epoch': 0.86} + 86%|████████▋ | 10130/11728 [1:35:06<2:35:27, 5.84s/it] 86%|████████▋ | 10131/11728 [1:35:11<2:33:31, 5.77s/it] {'loss': 0.4499, 'learning_rate': 9.568626551693927e-07, 'epoch': 0.86} + 86%|████████▋ | 10131/11728 [1:35:11<2:33:31, 5.77s/it] 86%|████████▋ | 10132/11728 [1:35:17<2:34:57, 5.83s/it] {'loss': 0.4456, 'learning_rate': 9.556841614351664e-07, 'epoch': 0.86} + 86%|████████▋ | 10132/11728 [1:35:17<2:34:57, 5.83s/it] 86%|████████▋ | 10133/11728 [1:35:23<2:34:53, 5.83s/it] {'loss': 0.4528, 'learning_rate': 9.545063574582258e-07, 'epoch': 0.86} + 86%|████████▋ | 10133/11728 [1:35:23<2:34:53, 5.83s/it] 86%|████████▋ | 10134/11728 [1:35:29<2:38:35, 5.97s/it] {'loss': 0.4586, 'learning_rate': 9.533292433283914e-07, 'epoch': 0.86} + 86%|████████▋ | 10134/11728 [1:35:29<2:38:35, 5.97s/it] 86%|████████▋ | 10135/11728 [1:35:35<2:38:27, 5.97s/it] {'loss': 0.4541, 'learning_rate': 9.52152819135439e-07, 'epoch': 0.86} + 86%|████████▋ | 10135/11728 [1:35:35<2:38:27, 5.97s/it] 86%|████████▋ | 10136/11728 [1:35:41<2:36:11, 5.89s/it] {'loss': 0.4389, 'learning_rate': 9.50977084969088e-07, 'epoch': 0.86} + 86%|████████▋ | 10136/11728 [1:35:41<2:36:11, 5.89s/it] 86%|████████▋ | 10137/11728 [1:35:47<2:35:15, 5.86s/it] {'loss': 0.4731, 'learning_rate': 9.498020409190012e-07, 'epoch': 0.86} + 86%|████████▋ | 10137/11728 [1:35:47<2:35:15, 5.86s/it] 86%|████████▋ | 10138/11728 [1:35:53<2:33:11, 5.78s/it] {'loss': 0.4401, 'learning_rate': 9.486276870747946e-07, 'epoch': 0.86} + 86%|████████▋ | 10138/11728 [1:35:53<2:33:11, 5.78s/it] 86%|████████▋ | 10139/11728 [1:35:58<2:32:00, 5.74s/it] {'loss': 0.446, 'learning_rate': 9.474540235260288e-07, 'epoch': 0.86} + 86%|████████▋ | 10139/11728 [1:35:58<2:32:00, 5.74s/it] 86%|████████▋ | 10140/11728 [1:36:04<2:32:35, 5.77s/it] {'loss': 0.4586, 'learning_rate': 9.462810503622122e-07, 'epoch': 0.86} + 86%|████████▋ | 10140/11728 [1:36:04<2:32:35, 5.77s/it] 86%|████████▋ | 10141/11728 [1:36:10<2:32:10, 5.75s/it] {'loss': 0.4445, 'learning_rate': 9.45108767672801e-07, 'epoch': 0.86} + 86%|████████▋ | 10141/11728 [1:36:10<2:32:10, 5.75s/it] 86%|████████▋ | 10142/11728 [1:36:16<2:33:42, 5.82s/it] {'loss': 0.4614, 'learning_rate': 9.439371755472005e-07, 'epoch': 0.86} + 86%|████████▋ | 10142/11728 [1:36:16<2:33:42, 5.82s/it] 86%|████████▋ | 10143/11728 [1:36:21<2:33:13, 5.80s/it] {'loss': 0.4439, 'learning_rate': 9.427662740747567e-07, 'epoch': 0.86} + 86%|████████▋ | 10143/11728 [1:36:21<2:33:13, 5.80s/it] 86%|████████▋ | 10144/11728 [1:36:27<2:34:12, 5.84s/it] {'loss': 0.4707, 'learning_rate': 9.415960633447674e-07, 'epoch': 0.86} + 86%|████████▋ | 10144/11728 [1:36:27<2:34:12, 5.84s/it] 87%|████████▋ | 10145/11728 [1:36:33<2:34:18, 5.85s/it] {'loss': 0.4491, 'learning_rate': 9.404265434464844e-07, 'epoch': 0.87} + 87%|████████▋ | 10145/11728 [1:36:33<2:34:18, 5.85s/it] 87%|████████▋ | 10146/11728 [1:36:39<2:34:57, 5.88s/it] {'loss': 0.4493, 'learning_rate': 9.392577144690929e-07, 'epoch': 0.87} + 87%|████████▋ | 10146/11728 [1:36:39<2:34:57, 5.88s/it] 87%|████████▋ | 10147/11728 [1:36:45<2:33:56, 5.84s/it] {'loss': 0.4598, 'learning_rate': 9.380895765017361e-07, 'epoch': 0.87} + 87%|████████▋ | 10147/11728 [1:36:45<2:33:56, 5.84s/it] 87%|████████▋ | 10148/11728 [1:36:51<2:32:46, 5.80s/it] {'loss': 0.4479, 'learning_rate': 9.369221296335007e-07, 'epoch': 0.87} + 87%|████████▋ | 10148/11728 [1:36:51<2:32:46, 5.80s/it] 87%|████████▋ | 10149/11728 [1:36:56<2:32:38, 5.80s/it] {'loss': 0.4593, 'learning_rate': 9.357553739534208e-07, 'epoch': 0.87} + 87%|████████▋ | 10149/11728 [1:36:56<2:32:38, 5.80s/it]6 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... +04 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend...1 AutoResumeHook: Checking whether to suspend... + +3 AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... + 87%|████████▋ | 10150/11728 [1:37:02<2:30:51, 5.74s/it]7 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4472, 'learning_rate': 9.345893095504777e-07, 'epoch': 0.87} + 87%|████████▋ | 10150/11728 [1:37:02<2:30:51, 5.74s/it] 87%|████████▋ | 10151/11728 [1:37:08<2:30:25, 5.72s/it] {'loss': 0.4895, 'learning_rate': 9.334239365136033e-07, 'epoch': 0.87} + 87%|████████▋ | 10151/11728 [1:37:08<2:30:25, 5.72s/it] 87%|████████▋ | 10152/11728 [1:37:14<2:30:59, 5.75s/it] {'loss': 0.4482, 'learning_rate': 9.3225925493167e-07, 'epoch': 0.87} + 87%|████████▋ | 10152/11728 [1:37:14<2:30:59, 5.75s/it] 87%|████████▋ | 10153/11728 [1:37:19<2:30:55, 5.75s/it] {'loss': 0.4599, 'learning_rate': 9.310952648935001e-07, 'epoch': 0.87} + 87%|████████▋ | 10153/11728 [1:37:19<2:30:55, 5.75s/it] 87%|████████▋ | 10154/11728 [1:37:25<2:30:11, 5.73s/it] {'loss': 0.4647, 'learning_rate': 9.299319664878703e-07, 'epoch': 0.87} + 87%|████████▋ | 10154/11728 [1:37:25<2:30:11, 5.73s/it] 87%|████████▋ | 10155/11728 [1:37:31<2:32:20, 5.81s/it] {'loss': 0.4689, 'learning_rate': 9.28769359803493e-07, 'epoch': 0.87} + 87%|████████▋ | 10155/11728 [1:37:31<2:32:20, 5.81s/it] 87%|████████▋ | 10156/11728 [1:37:37<2:34:11, 5.88s/it] {'loss': 0.4643, 'learning_rate': 9.276074449290362e-07, 'epoch': 0.87} + 87%|████████▋ | 10156/11728 [1:37:37<2:34:11, 5.88s/it] 87%|████████▋ | 10157/11728 [1:37:43<2:34:19, 5.89s/it] {'loss': 0.4412, 'learning_rate': 9.264462219531112e-07, 'epoch': 0.87} + 87%|████████▋ | 10157/11728 [1:37:43<2:34:19, 5.89s/it] 87%|████████▋ | 10158/11728 [1:37:49<2:33:12, 5.85s/it] {'loss': 0.4676, 'learning_rate': 9.252856909642794e-07, 'epoch': 0.87} + 87%|████████▋ | 10158/11728 [1:37:49<2:33:12, 5.85s/it] 87%|████████▋ | 10159/11728 [1:37:55<2:36:04, 5.97s/it] {'loss': 0.4388, 'learning_rate': 9.241258520510454e-07, 'epoch': 0.87} + 87%|████████▋ | 10159/11728 [1:37:55<2:36:04, 5.97s/it] 87%|████████▋ | 10160/11728 [1:38:01<2:34:12, 5.90s/it] {'loss': 0.4494, 'learning_rate': 9.229667053018665e-07, 'epoch': 0.87} + 87%|████████▋ | 10160/11728 [1:38:01<2:34:12, 5.90s/it] 87%|████████▋ | 10161/11728 [1:38:07<2:35:28, 5.95s/it] {'loss': 0.4549, 'learning_rate': 9.218082508051407e-07, 'epoch': 0.87} + 87%|████████▋ | 10161/11728 [1:38:07<2:35:28, 5.95s/it] 87%|████████▋ | 10162/11728 [1:38:13<2:34:37, 5.92s/it] {'loss': 0.455, 'learning_rate': 9.206504886492162e-07, 'epoch': 0.87} + 87%|████████▋ | 10162/11728 [1:38:13<2:34:37, 5.92s/it] 87%|████████▋ | 10163/11728 [1:38:19<2:34:30, 5.92s/it] {'loss': 0.4369, 'learning_rate': 9.194934189223947e-07, 'epoch': 0.87} + 87%|████████▋ | 10163/11728 [1:38:19<2:34:30, 5.92s/it] 87%|████████▋ | 10164/11728 [1:38:24<2:31:29, 5.81s/it] {'loss': 0.4478, 'learning_rate': 9.183370417129122e-07, 'epoch': 0.87} + 87%|████████▋ | 10164/11728 [1:38:24<2:31:29, 5.81s/it] 87%|████████▋ | 10165/11728 [1:38:30<2:32:28, 5.85s/it] {'loss': 0.4521, 'learning_rate': 9.171813571089628e-07, 'epoch': 0.87} + 87%|████████▋ | 10165/11728 [1:38:30<2:32:28, 5.85s/it] 87%|████████▋ | 10166/11728 [1:38:36<2:31:58, 5.84s/it] {'loss': 0.4531, 'learning_rate': 9.160263651986834e-07, 'epoch': 0.87} + 87%|████████▋ | 10166/11728 [1:38:36<2:31:58, 5.84s/it] 87%|████████▋ | 10167/11728 [1:38:42<2:31:22, 5.82s/it] {'loss': 0.4419, 'learning_rate': 9.148720660701549e-07, 'epoch': 0.87} + 87%|████████▋ | 10167/11728 [1:38:42<2:31:22, 5.82s/it] 87%|████████▋ | 10168/11728 [1:38:47<2:30:33, 5.79s/it] {'loss': 0.423, 'learning_rate': 9.137184598114135e-07, 'epoch': 0.87} + 87%|████████▋ | 10168/11728 [1:38:47<2:30:33, 5.79s/it] 87%|████████▋ | 10169/11728 [1:38:53<2:30:12, 5.78s/it] {'loss': 0.4534, 'learning_rate': 9.125655465104388e-07, 'epoch': 0.87} + 87%|████████▋ | 10169/11728 [1:38:53<2:30:12, 5.78s/it] 87%|████████▋ | 10170/11728 [1:38:59<2:33:10, 5.90s/it] {'loss': 0.4679, 'learning_rate': 9.114133262551517e-07, 'epoch': 0.87} + 87%|████████▋ | 10170/11728 [1:38:59<2:33:10, 5.90s/it] 87%|████████▋ | 10171/11728 [1:39:06<2:37:05, 6.05s/it] {'loss': 0.4643, 'learning_rate': 9.102617991334273e-07, 'epoch': 0.87} + 87%|████████▋ | 10171/11728 [1:39:06<2:37:05, 6.05s/it] 87%|████████▋ | 10172/11728 [1:39:12<2:35:39, 6.00s/it] {'loss': 0.4434, 'learning_rate': 9.091109652330887e-07, 'epoch': 0.87} + 87%|████████▋ | 10172/11728 [1:39:12<2:35:39, 6.00s/it] 87%|████████▋ | 10173/11728 [1:39:17<2:34:05, 5.95s/it] {'loss': 0.4431, 'learning_rate': 9.079608246419003e-07, 'epoch': 0.87} + 87%|████████▋ | 10173/11728 [1:39:17<2:34:05, 5.95s/it] 87%|████████▋ | 10174/11728 [1:39:23<2:34:52, 5.98s/it] {'loss': 0.463, 'learning_rate': 9.068113774475784e-07, 'epoch': 0.87} + 87%|████████▋ | 10174/11728 [1:39:23<2:34:52, 5.98s/it] 87%|████████▋ | 10175/11728 [1:39:29<2:35:18, 6.00s/it] {'loss': 0.4306, 'learning_rate': 9.056626237377841e-07, 'epoch': 0.87} + 87%|████████▋ | 10175/11728 [1:39:29<2:35:18, 6.00s/it] 87%|████████▋ | 10176/11728 [1:39:35<2:33:56, 5.95s/it] {'loss': 0.4532, 'learning_rate': 9.045145636001229e-07, 'epoch': 0.87} + 87%|████████▋ | 10176/11728 [1:39:35<2:33:56, 5.95s/it] 87%|████████▋ | 10177/11728 [1:39:41<2:34:21, 5.97s/it] {'loss': 0.4661, 'learning_rate': 9.033671971221558e-07, 'epoch': 0.87} + 87%|████████▋ | 10177/11728 [1:39:41<2:34:21, 5.97s/it] 87%|████████▋ | 10178/11728 [1:39:47<2:34:06, 5.97s/it] {'loss': 0.464, 'learning_rate': 9.022205243913851e-07, 'epoch': 0.87} + 87%|████████▋ | 10178/11728 [1:39:47<2:34:06, 5.97s/it] 87%|████████▋ | 10179/11728 [1:39:53<2:32:26, 5.91s/it] {'loss': 0.4397, 'learning_rate': 9.010745454952563e-07, 'epoch': 0.87} + 87%|████████▋ | 10179/11728 [1:39:53<2:32:26, 5.91s/it] 87%|████████▋ | 10180/11728 [1:39:59<2:30:29, 5.83s/it] {'loss': 0.4377, 'learning_rate': 8.999292605211695e-07, 'epoch': 0.87} + 87%|████████▋ | 10180/11728 [1:39:59<2:30:29, 5.83s/it] 87%|████████▋ | 10181/11728 [1:40:04<2:29:06, 5.78s/it] {'loss': 0.4348, 'learning_rate': 8.987846695564717e-07, 'epoch': 0.87} + 87%|████████▋ | 10181/11728 [1:40:04<2:29:06, 5.78s/it] 87%|████████▋ | 10182/11728 [1:40:11<2:32:59, 5.94s/it] {'loss': 0.4456, 'learning_rate': 8.976407726884495e-07, 'epoch': 0.87} + 87%|████████▋ | 10182/11728 [1:40:11<2:32:59, 5.94s/it] 87%|████████▋ | 10183/11728 [1:40:16<2:31:43, 5.89s/it] {'loss': 0.4446, 'learning_rate': 8.964975700043433e-07, 'epoch': 0.87} + 87%|████████▋ | 10183/11728 [1:40:17<2:31:43, 5.89s/it] 87%|████████▋ | 10184/11728 [1:40:22<2:31:46, 5.90s/it] {'loss': 0.4477, 'learning_rate': 8.953550615913398e-07, 'epoch': 0.87} + 87%|████████▋ | 10184/11728 [1:40:22<2:31:46, 5.90s/it] 87%|████████▋ | 10185/11728 [1:40:28<2:31:24, 5.89s/it] {'loss': 0.446, 'learning_rate': 8.942132475365672e-07, 'epoch': 0.87} + 87%|████████▋ | 10185/11728 [1:40:28<2:31:24, 5.89s/it] 87%|████████▋ | 10186/11728 [1:40:34<2:31:32, 5.90s/it] {'loss': 0.4606, 'learning_rate': 8.930721279271093e-07, 'epoch': 0.87} + 87%|████████▋ | 10186/11728 [1:40:34<2:31:32, 5.90s/it] 87%|████████▋ | 10187/11728 [1:40:40<2:30:51, 5.87s/it] {'loss': 0.4689, 'learning_rate': 8.91931702849993e-07, 'epoch': 0.87} + 87%|████████▋ | 10187/11728 [1:40:40<2:30:51, 5.87s/it] 87%|████████▋ | 10188/11728 [1:40:46<2:30:30, 5.86s/it] {'loss': 0.4585, 'learning_rate': 8.907919723921888e-07, 'epoch': 0.87} + 87%|████████▋ | 10188/11728 [1:40:46<2:30:30, 5.86s/it] 87%|████████▋ | 10189/11728 [1:40:52<2:29:00, 5.81s/it] {'loss': 0.4418, 'learning_rate': 8.896529366406181e-07, 'epoch': 0.87} + 87%|████████▋ | 10189/11728 [1:40:52<2:29:00, 5.81s/it] 87%|████████▋ | 10190/11728 [1:40:58<2:31:12, 5.90s/it] {'loss': 0.482, 'learning_rate': 8.885145956821495e-07, 'epoch': 0.87} + 87%|████████▋ | 10190/11728 [1:40:58<2:31:12, 5.90s/it] 87%|████████▋ | 10191/11728 [1:41:03<2:30:07, 5.86s/it] {'loss': 0.447, 'learning_rate': 8.873769496035966e-07, 'epoch': 0.87} + 87%|████████▋ | 10191/11728 [1:41:03<2:30:07, 5.86s/it] 87%|████████▋ | 10192/11728 [1:41:09<2:29:42, 5.85s/it] {'loss': 0.4593, 'learning_rate': 8.862399984917214e-07, 'epoch': 0.87} + 87%|████████▋ | 10192/11728 [1:41:09<2:29:42, 5.85s/it] 87%|████████▋ | 10193/11728 [1:41:15<2:30:41, 5.89s/it] {'loss': 0.4708, 'learning_rate': 8.851037424332331e-07, 'epoch': 0.87} + 87%|████████▋ | 10193/11728 [1:41:15<2:30:41, 5.89s/it] 87%|████████▋ | 10194/11728 [1:41:21<2:31:59, 5.94s/it] {'loss': 0.4309, 'learning_rate': 8.839681815147871e-07, 'epoch': 0.87} + 87%|████████▋ | 10194/11728 [1:41:21<2:31:59, 5.94s/it] 87%|████████▋ | 10195/11728 [1:41:27<2:31:50, 5.94s/it] {'loss': 0.4706, 'learning_rate': 8.828333158229851e-07, 'epoch': 0.87} + 87%|████████▋ | 10195/11728 [1:41:27<2:31:50, 5.94s/it] 87%|████████▋ | 10196/11728 [1:41:33<2:30:05, 5.88s/it] {'loss': 0.4564, 'learning_rate': 8.816991454443802e-07, 'epoch': 0.87} + 87%|████████▋ | 10196/11728 [1:41:33<2:30:05, 5.88s/it] 87%|████████▋ | 10197/11728 [1:41:39<2:31:12, 5.93s/it] {'loss': 0.4718, 'learning_rate': 8.805656704654642e-07, 'epoch': 0.87} + 87%|████████▋ | 10197/11728 [1:41:39<2:31:12, 5.93s/it] 87%|████████▋ | 10198/11728 [1:41:45<2:29:51, 5.88s/it] {'loss': 0.4562, 'learning_rate': 8.794328909726823e-07, 'epoch': 0.87} + 87%|████████▋ | 10198/11728 [1:41:45<2:29:51, 5.88s/it] 87%|████████▋ | 10199/11728 [1:41:51<2:30:23, 5.90s/it] {'loss': 0.4506, 'learning_rate': 8.783008070524257e-07, 'epoch': 0.87} + 87%|████████▋ | 10199/11728 [1:41:51<2:30:23, 5.90s/it]06 AutoResumeHook: Checking whether to suspend... +AutoResumeHook: Checking whether to suspend... + 87%|████████▋ | 10200/11728 [1:41:57<2:31:28, 5.95s/it]5 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4562, 'learning_rate': 8.771694187910307e-07, 'epoch': 0.87} + 87%|████████▋ | 10200/11728 [1:41:57<2:31:28, 5.95s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-10200/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-10200/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-10200/mm_projector +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/torch/nn/modules/module.py:1802: UserWarning: Positional args are being deprecated, use kwargs instead. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details. + warnings.warn( + 87%|████████▋ | 10201/11728 [1:42:31<6:10:50, 14.57s/it] {'loss': 0.4582, 'learning_rate': 8.760387262747838e-07, 'epoch': 0.87} + 87%|████████▋ | 10201/11728 [1:42:31<6:10:50, 14.57s/it] 87%|████████▋ | 10202/11728 [1:42:37<5:04:00, 11.95s/it] {'loss': 0.4717, 'learning_rate': 8.749087295899139e-07, 'epoch': 0.87} + 87%|████████▋ | 10202/11728 [1:42:37<5:04:00, 11.95s/it] 87%|████████▋ | 10203/11728 [1:42:43<4:17:22, 10.13s/it] {'loss': 0.4605, 'learning_rate': 8.737794288226009e-07, 'epoch': 0.87} + 87%|████████▋ | 10203/11728 [1:42:43<4:17:22, 10.13s/it] 87%|████████▋ | 10204/11728 [1:42:49<3:46:20, 8.91s/it] {'loss': 0.4481, 'learning_rate': 8.726508240589693e-07, 'epoch': 0.87} + 87%|████████▋ | 10204/11728 [1:42:49<3:46:20, 8.91s/it] 87%|████████▋ | 10205/11728 [1:42:55<3:24:16, 8.05s/it] {'loss': 0.492, 'learning_rate': 8.715229153850935e-07, 'epoch': 0.87} + 87%|████████▋ | 10205/11728 [1:42:55<3:24:16, 8.05s/it] 87%|████████▋ | 10206/11728 [1:43:01<3:07:05, 7.38s/it] {'loss': 0.4561, 'learning_rate': 8.703957028869881e-07, 'epoch': 0.87} + 87%|████████▋ | 10206/11728 [1:43:01<3:07:05, 7.38s/it] 87%|████████▋ | 10207/11728 [1:43:07<2:54:11, 6.87s/it] {'loss': 0.4396, 'learning_rate': 8.69269186650622e-07, 'epoch': 0.87} + 87%|████████▋ | 10207/11728 [1:43:07<2:54:11, 6.87s/it] 87%|████████▋ | 10208/11728 [1:43:13<2:46:11, 6.56s/it] {'loss': 0.4584, 'learning_rate': 8.681433667619065e-07, 'epoch': 0.87} + 87%|████████▋ | 10208/11728 [1:43:13<2:46:11, 6.56s/it] 87%|████████▋ | 10209/11728 [1:43:19<2:42:08, 6.40s/it] {'loss': 0.4572, 'learning_rate': 8.670182433067031e-07, 'epoch': 0.87} + 87%|████████▋ | 10209/11728 [1:43:19<2:42:08, 6.40s/it] 87%|████████▋ | 10210/11728 [1:43:25<2:38:33, 6.27s/it] {'loss': 0.4656, 'learning_rate': 8.658938163708175e-07, 'epoch': 0.87} + 87%|████████▋ | 10210/11728 [1:43:25<2:38:33, 6.27s/it] 87%|████████▋ | 10211/11728 [1:43:31<2:36:26, 6.19s/it] {'loss': 0.4721, 'learning_rate': 8.647700860400032e-07, 'epoch': 0.87} + 87%|████████▋ | 10211/11728 [1:43:31<2:36:26, 6.19s/it] 87%|████████▋ | 10212/11728 [1:43:37<2:34:37, 6.12s/it] {'loss': 0.4512, 'learning_rate': 8.636470523999596e-07, 'epoch': 0.87} + 87%|████████▋ | 10212/11728 [1:43:37<2:34:37, 6.12s/it] 87%|████████▋ | 10213/11728 [1:43:42<2:31:36, 6.00s/it] {'loss': 0.4604, 'learning_rate': 8.625247155363358e-07, 'epoch': 0.87} + 87%|████████▋ | 10213/11728 [1:43:42<2:31:36, 6.00s/it] 87%|████████▋ | 10214/11728 [1:43:48<2:31:02, 5.99s/it] {'loss': 0.4521, 'learning_rate': 8.614030755347269e-07, 'epoch': 0.87} + 87%|████████▋ | 10214/11728 [1:43:48<2:31:02, 5.99s/it] 87%|████████▋ | 10215/11728 [1:43:54<2:28:58, 5.91s/it] {'loss': 0.46, 'learning_rate': 8.602821324806698e-07, 'epoch': 0.87} + 87%|████████▋ | 10215/11728 [1:43:54<2:28:58, 5.91s/it] 87%|████████▋ | 10216/11728 [1:44:00<2:28:32, 5.89s/it] {'loss': 0.4613, 'learning_rate': 8.591618864596541e-07, 'epoch': 0.87} + 87%|████████▋ | 10216/11728 [1:44:00<2:28:32, 5.89s/it] 87%|████████▋ | 10217/11728 [1:44:06<2:29:26, 5.93s/it] {'loss': 0.4664, 'learning_rate': 8.580423375571156e-07, 'epoch': 0.87} + 87%|████████▋ | 10217/11728 [1:44:06<2:29:26, 5.93s/it] 87%|████████▋ | 10218/11728 [1:44:12<2:29:48, 5.95s/it] {'loss': 0.461, 'learning_rate': 8.569234858584341e-07, 'epoch': 0.87} + 87%|████████▋ | 10218/11728 [1:44:12<2:29:48, 5.95s/it] 87%|████████▋ | 10219/11728 [1:44:18<2:28:42, 5.91s/it] {'loss': 0.4491, 'learning_rate': 8.5580533144894e-07, 'epoch': 0.87} + 87%|████████▋ | 10219/11728 [1:44:18<2:28:42, 5.91s/it] 87%|████████▋ | 10220/11728 [1:44:24<2:31:00, 6.01s/it] {'loss': 0.4538, 'learning_rate': 8.546878744139065e-07, 'epoch': 0.87} + 87%|████████▋ | 10220/11728 [1:44:24<2:31:00, 6.01s/it] 87%|████████▋ | 10221/11728 [1:44:30<2:33:28, 6.11s/it] {'loss': 0.4588, 'learning_rate': 8.535711148385572e-07, 'epoch': 0.87} + 87%|████████▋ | 10221/11728 [1:44:30<2:33:28, 6.11s/it] 87%|████████▋ | 10222/11728 [1:44:36<2:31:23, 6.03s/it] {'loss': 0.4614, 'learning_rate': 8.524550528080578e-07, 'epoch': 0.87} + 87%|████████▋ | 10222/11728 [1:44:36<2:31:23, 6.03s/it] 87%|████████▋ | 10223/11728 [1:44:42<2:33:34, 6.12s/it] {'loss': 0.4553, 'learning_rate': 8.513396884075287e-07, 'epoch': 0.87} + 87%|████████▋ | 10223/11728 [1:44:42<2:33:34, 6.12s/it] 87%|████████▋ | 10224/11728 [1:44:49<2:33:39, 6.13s/it] {'loss': 0.4569, 'learning_rate': 8.502250217220276e-07, 'epoch': 0.87} + 87%|████████▋ | 10224/11728 [1:44:49<2:33:39, 6.13s/it] 87%|████████▋ | 10225/11728 [1:44:54<2:31:15, 6.04s/it] {'loss': 0.4723, 'learning_rate': 8.491110528365653e-07, 'epoch': 0.87} + 87%|████████▋ | 10225/11728 [1:44:54<2:31:15, 6.04s/it] 87%|████████▋ | 10226/11728 [1:45:00<2:28:35, 5.94s/it] {'loss': 0.4491, 'learning_rate': 8.479977818360985e-07, 'epoch': 0.87} + 87%|████████▋ | 10226/11728 [1:45:00<2:28:35, 5.94s/it] 87%|████████▋ | 10227/11728 [1:45:06<2:26:31, 5.86s/it] {'loss': 0.4433, 'learning_rate': 8.468852088055291e-07, 'epoch': 0.87} + 87%|████████▋ | 10227/11728 [1:45:06<2:26:31, 5.86s/it] 87%|████████▋ | 10228/11728 [1:45:12<2:26:07, 5.85s/it] {'loss': 0.4471, 'learning_rate': 8.457733338297069e-07, 'epoch': 0.87} + 87%|████████▋ | 10228/11728 [1:45:12<2:26:07, 5.85s/it] 87%|████████▋ | 10229/11728 [1:45:17<2:24:31, 5.78s/it] {'loss': 0.464, 'learning_rate': 8.446621569934276e-07, 'epoch': 0.87} + 87%|████████▋ | 10229/11728 [1:45:17<2:24:31, 5.78s/it] 87%|████████▋ | 10230/11728 [1:45:23<2:25:05, 5.81s/it] {'loss': 0.4409, 'learning_rate': 8.435516783814368e-07, 'epoch': 0.87} + 87%|████████▋ | 10230/11728 [1:45:23<2:25:05, 5.81s/it] 87%|████████▋ | 10231/11728 [1:45:29<2:27:02, 5.89s/it] {'loss': 0.4673, 'learning_rate': 8.424418980784177e-07, 'epoch': 0.87} + 87%|████████▋ | 10231/11728 [1:45:29<2:27:02, 5.89s/it] 87%|████████▋ | 10232/11728 [1:45:35<2:24:46, 5.81s/it] {'loss': 0.4807, 'learning_rate': 8.413328161690159e-07, 'epoch': 0.87} + 87%|████████▋ | 10232/11728 [1:45:35<2:24:46, 5.81s/it] 87%|████████▋ | 10233/11728 [1:45:41<2:25:20, 5.83s/it] {'loss': 0.4523, 'learning_rate': 8.402244327378073e-07, 'epoch': 0.87} + 87%|████████▋ | 10233/11728 [1:45:41<2:25:20, 5.83s/it] 87%|████████▋ | 10234/11728 [1:45:47<2:25:59, 5.86s/it] {'loss': 0.4505, 'learning_rate': 8.391167478693241e-07, 'epoch': 0.87} + 87%|████████▋ | 10234/11728 [1:45:47<2:25:59, 5.86s/it] 87%|████████▋ | 10235/11728 [1:45:52<2:25:13, 5.84s/it] {'loss': 0.451, 'learning_rate': 8.380097616480443e-07, 'epoch': 0.87} + 87%|████████▋ | 10235/11728 [1:45:52<2:25:13, 5.84s/it] 87%|████████▋ | 10236/11728 [1:45:58<2:25:02, 5.83s/it] {'loss': 0.4687, 'learning_rate': 8.369034741583892e-07, 'epoch': 0.87} + 87%|████████▋ | 10236/11728 [1:45:58<2:25:02, 5.83s/it] 87%|████████▋ | 10237/11728 [1:46:04<2:24:48, 5.83s/it] {'loss': 0.4402, 'learning_rate': 8.357978854847304e-07, 'epoch': 0.87} + 87%|████████▋ | 10237/11728 [1:46:04<2:24:48, 5.83s/it] 87%|████████▋ | 10238/11728 [1:46:10<2:24:16, 5.81s/it] {'loss': 0.4528, 'learning_rate': 8.346929957113848e-07, 'epoch': 0.87} + 87%|████████▋ | 10238/11728 [1:46:10<2:24:16, 5.81s/it] 87%|████████▋ | 10239/11728 [1:46:15<2:22:18, 5.73s/it] {'loss': 0.4608, 'learning_rate': 8.335888049226159e-07, 'epoch': 0.87} + 87%|████████▋ | 10239/11728 [1:46:15<2:22:18, 5.73s/it] 87%|████████▋ | 10240/11728 [1:46:21<2:22:23, 5.74s/it] {'loss': 0.4454, 'learning_rate': 8.3248531320263e-07, 'epoch': 0.87} + 87%|████████▋ | 10240/11728 [1:46:21<2:22:23, 5.74s/it] 87%|████████▋ | 10241/11728 [1:46:27<2:22:20, 5.74s/it] {'loss': 0.4538, 'learning_rate': 8.313825206355919e-07, 'epoch': 0.87} + 87%|████████▋ | 10241/11728 [1:46:27<2:22:20, 5.74s/it] 87%|████████▋ | 10242/11728 [1:46:33<2:23:56, 5.81s/it] {'loss': 0.446, 'learning_rate': 8.302804273055976e-07, 'epoch': 0.87} + 87%|████████▋ | 10242/11728 [1:46:33<2:23:56, 5.81s/it] 87%|████████▋ | 10243/11728 [1:46:39<2:24:16, 5.83s/it] {'loss': 0.452, 'learning_rate': 8.291790332967009e-07, 'epoch': 0.87} + 87%|████████▋ | 10243/11728 [1:46:39<2:24:16, 5.83s/it] 87%|████████▋ | 10244/11728 [1:46:44<2:21:55, 5.74s/it] {'loss': 0.4447, 'learning_rate': 8.280783386928981e-07, 'epoch': 0.87} + 87%|████████▋ | 10244/11728 [1:46:44<2:21:55, 5.74s/it] 87%|████████▋ | 10245/11728 [1:46:50<2:22:27, 5.76s/it] {'loss': 0.4816, 'learning_rate': 8.269783435781331e-07, 'epoch': 0.87} + 87%|████████▋ | 10245/11728 [1:46:50<2:22:27, 5.76s/it] 87%|████████▋ | 10246/11728 [1:46:56<2:23:13, 5.80s/it] {'loss': 0.4558, 'learning_rate': 8.258790480362955e-07, 'epoch': 0.87} + 87%|████████▋ | 10246/11728 [1:46:56<2:23:13, 5.80s/it] 87%|████████▋ | 10247/11728 [1:47:02<2:22:35, 5.78s/it] {'loss': 0.4583, 'learning_rate': 8.247804521512237e-07, 'epoch': 0.87} + 87%|████████▋ | 10247/11728 [1:47:02<2:22:35, 5.78s/it] 87%|████████▋ | 10248/11728 [1:47:07<2:21:33, 5.74s/it] {'loss': 0.4601, 'learning_rate': 8.236825560066997e-07, 'epoch': 0.87} + 87%|████████▋ | 10248/11728 [1:47:07<2:21:33, 5.74s/it] 87%|████████▋ | 10249/11728 [1:47:13<2:20:30, 5.70s/it] {'loss': 0.4598, 'learning_rate': 8.225853596864519e-07, 'epoch': 0.87} + 87%|████████▋ | 10249/11728 [1:47:13<2:20:30, 5.70s/it]06 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +35 AutoResumeHook: Checking whether to suspend... +AutoResumeHook: Checking whether to suspend... + 87%|████████▋ | 10250/11728 [1:47:19<2:21:28, 5.74s/it]1 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4572, 'learning_rate': 8.214888632741603e-07, 'epoch': 0.87} + 87%|████████▋ | 10250/11728 [1:47:19<2:21:28, 5.74s/it] 87%|████████▋ | 10251/11728 [1:47:25<2:23:55, 5.85s/it] {'loss': 0.4711, 'learning_rate': 8.203930668534488e-07, 'epoch': 0.87} + 87%|████████▋ | 10251/11728 [1:47:25<2:23:55, 5.85s/it] 87%|████████▋ | 10252/11728 [1:47:31<2:22:31, 5.79s/it] {'loss': 0.4674, 'learning_rate': 8.192979705078852e-07, 'epoch': 0.87} + 87%|████████▋ | 10252/11728 [1:47:31<2:22:31, 5.79s/it] 87%|████████▋ | 10253/11728 [1:47:36<2:22:01, 5.78s/it] {'loss': 0.4322, 'learning_rate': 8.182035743209848e-07, 'epoch': 0.87} + 87%|████████▋ | 10253/11728 [1:47:36<2:22:01, 5.78s/it] 87%|████████▋ | 10254/11728 [1:47:42<2:21:23, 5.76s/it] {'loss': 0.4635, 'learning_rate': 8.171098783762132e-07, 'epoch': 0.87} + 87%|████████▋ | 10254/11728 [1:47:42<2:21:23, 5.76s/it] 87%|████████▋ | 10255/11728 [1:47:48<2:22:37, 5.81s/it] {'loss': 0.462, 'learning_rate': 8.160168827569804e-07, 'epoch': 0.87} + 87%|████████▋ | 10255/11728 [1:47:48<2:22:37, 5.81s/it] 87%|████████▋ | 10256/11728 [1:47:54<2:22:01, 5.79s/it] {'loss': 0.4446, 'learning_rate': 8.149245875466416e-07, 'epoch': 0.87} + 87%|████████▋ | 10256/11728 [1:47:54<2:22:01, 5.79s/it] 87%|████████▋ | 10257/11728 [1:47:59<2:22:14, 5.80s/it] {'loss': 0.4544, 'learning_rate': 8.138329928285027e-07, 'epoch': 0.87} + 87%|████████▋ | 10257/11728 [1:47:59<2:22:14, 5.80s/it] 87%|████████▋ | 10258/11728 [1:48:06<2:24:01, 5.88s/it] {'loss': 0.4608, 'learning_rate': 8.12742098685807e-07, 'epoch': 0.87} + 87%|████████▋ | 10258/11728 [1:48:06<2:24:01, 5.88s/it] 87%|████████▋ | 10259/11728 [1:48:12<2:25:38, 5.95s/it] {'loss': 0.4715, 'learning_rate': 8.116519052017558e-07, 'epoch': 0.87} + 87%|████████▋ | 10259/11728 [1:48:12<2:25:38, 5.95s/it] 87%|████████▋ | 10260/11728 [1:48:18<2:25:08, 5.93s/it] {'loss': 0.4478, 'learning_rate': 8.105624124594924e-07, 'epoch': 0.87} + 87%|████████▋ | 10260/11728 [1:48:18<2:25:08, 5.93s/it] 87%|████████▋ | 10261/11728 [1:48:23<2:22:27, 5.83s/it] {'loss': 0.4566, 'learning_rate': 8.094736205421027e-07, 'epoch': 0.87} + 87%|████████▋ | 10261/11728 [1:48:23<2:22:27, 5.83s/it] 88%|████████▊ | 10262/11728 [1:48:29<2:20:49, 5.76s/it] {'loss': 0.4485, 'learning_rate': 8.083855295326237e-07, 'epoch': 0.88} + 88%|████████▊ | 10262/11728 [1:48:29<2:20:49, 5.76s/it] 88%|████████▊ | 10263/11728 [1:48:35<2:24:09, 5.90s/it] {'loss': 0.4654, 'learning_rate': 8.072981395140378e-07, 'epoch': 0.88} + 88%|████████▊ | 10263/11728 [1:48:35<2:24:09, 5.90s/it] 88%|████████▊ | 10264/11728 [1:48:41<2:24:08, 5.91s/it] {'loss': 0.4516, 'learning_rate': 8.062114505692742e-07, 'epoch': 0.88} + 88%|████████▊ | 10264/11728 [1:48:41<2:24:08, 5.91s/it] 88%|████████▊ | 10265/11728 [1:48:47<2:24:04, 5.91s/it] {'loss': 0.4475, 'learning_rate': 8.051254627812088e-07, 'epoch': 0.88} + 88%|████████▊ | 10265/11728 [1:48:47<2:24:04, 5.91s/it] 88%|████████▊ | 10266/11728 [1:48:53<2:23:39, 5.90s/it] {'loss': 0.4618, 'learning_rate': 8.040401762326655e-07, 'epoch': 0.88} + 88%|████████▊ | 10266/11728 [1:48:53<2:23:39, 5.90s/it] 88%|████████▊ | 10267/11728 [1:48:58<2:21:10, 5.80s/it] {'loss': 0.4352, 'learning_rate': 8.029555910064069e-07, 'epoch': 0.88} + 88%|████████▊ | 10267/11728 [1:48:58<2:21:10, 5.80s/it] 88%|████████▊ | 10268/11728 [1:49:04<2:21:31, 5.82s/it] {'loss': 0.4856, 'learning_rate': 8.018717071851512e-07, 'epoch': 0.88} + 88%|████████▊ | 10268/11728 [1:49:04<2:21:31, 5.82s/it] 88%|████████▊ | 10269/11728 [1:49:10<2:20:08, 5.76s/it] {'loss': 0.4282, 'learning_rate': 8.007885248515624e-07, 'epoch': 0.88} + 88%|████████▊ | 10269/11728 [1:49:10<2:20:08, 5.76s/it] 88%|████████▊ | 10270/11728 [1:49:16<2:21:05, 5.81s/it] {'loss': 0.4323, 'learning_rate': 7.997060440882453e-07, 'epoch': 0.88} + 88%|████████▊ | 10270/11728 [1:49:16<2:21:05, 5.81s/it] 88%|████████▊ | 10271/11728 [1:49:22<2:23:15, 5.90s/it] {'loss': 0.4573, 'learning_rate': 7.986242649777553e-07, 'epoch': 0.88} + 88%|████████▊ | 10271/11728 [1:49:22<2:23:15, 5.90s/it] 88%|████████▊ | 10272/11728 [1:49:27<2:22:05, 5.86s/it] {'loss': 0.473, 'learning_rate': 7.97543187602593e-07, 'epoch': 0.88} + 88%|████████▊ | 10272/11728 [1:49:28<2:22:05, 5.86s/it] 88%|████████▊ | 10273/11728 [1:49:33<2:22:45, 5.89s/it] {'loss': 0.458, 'learning_rate': 7.964628120452067e-07, 'epoch': 0.88} + 88%|████████▊ | 10273/11728 [1:49:33<2:22:45, 5.89s/it] 88%|████████▊ | 10274/11728 [1:49:39<2:23:07, 5.91s/it] {'loss': 0.4484, 'learning_rate': 7.953831383879895e-07, 'epoch': 0.88} + 88%|████████▊ | 10274/11728 [1:49:39<2:23:07, 5.91s/it] 88%|████████▊ | 10275/11728 [1:49:45<2:23:20, 5.92s/it] {'loss': 0.4618, 'learning_rate': 7.943041667132845e-07, 'epoch': 0.88} + 88%|████████▊ | 10275/11728 [1:49:45<2:23:20, 5.92s/it] 88%|████████▊ | 10276/11728 [1:49:52<2:24:57, 5.99s/it] {'loss': 0.4482, 'learning_rate': 7.932258971033746e-07, 'epoch': 0.88} + 88%|████████▊ | 10276/11728 [1:49:52<2:24:57, 5.99s/it] 88%|████████▊ | 10277/11728 [1:49:57<2:23:50, 5.95s/it] {'loss': 0.4556, 'learning_rate': 7.92148329640493e-07, 'epoch': 0.88} + 88%|████████▊ | 10277/11728 [1:49:57<2:23:50, 5.95s/it] 88%|████████▊ | 10278/11728 [1:50:03<2:23:31, 5.94s/it] {'loss': 0.4721, 'learning_rate': 7.910714644068251e-07, 'epoch': 0.88} + 88%|████████▊ | 10278/11728 [1:50:03<2:23:31, 5.94s/it] 88%|████████▊ | 10279/11728 [1:50:09<2:21:11, 5.85s/it] {'loss': 0.4489, 'learning_rate': 7.899953014844919e-07, 'epoch': 0.88} + 88%|████████▊ | 10279/11728 [1:50:09<2:21:11, 5.85s/it] 88%|████████▊ | 10280/11728 [1:50:15<2:22:46, 5.92s/it] {'loss': 0.4547, 'learning_rate': 7.889198409555665e-07, 'epoch': 0.88} + 88%|████████▊ | 10280/11728 [1:50:15<2:22:46, 5.92s/it] 88%|████████▊ | 10281/11728 [1:50:21<2:22:39, 5.92s/it] {'loss': 0.45, 'learning_rate': 7.8784508290207e-07, 'epoch': 0.88} + 88%|████████▊ | 10281/11728 [1:50:21<2:22:39, 5.92s/it] 88%|████████▊ | 10282/11728 [1:50:27<2:21:49, 5.88s/it] {'loss': 0.448, 'learning_rate': 7.86771027405967e-07, 'epoch': 0.88} + 88%|████████▊ | 10282/11728 [1:50:27<2:21:49, 5.88s/it] 88%|████████▊ | 10283/11728 [1:50:33<2:24:50, 6.01s/it] {'loss': 0.4686, 'learning_rate': 7.856976745491696e-07, 'epoch': 0.88} + 88%|████████▊ | 10283/11728 [1:50:33<2:24:50, 6.01s/it] 88%|████████▊ | 10284/11728 [1:50:39<2:25:41, 6.05s/it] {'loss': 0.4561, 'learning_rate': 7.846250244135378e-07, 'epoch': 0.88} + 88%|████████▊ | 10284/11728 [1:50:39<2:25:41, 6.05s/it] 88%|████████▊ | 10285/11728 [1:50:45<2:23:40, 5.97s/it] {'loss': 0.4367, 'learning_rate': 7.835530770808731e-07, 'epoch': 0.88} + 88%|████████▊ | 10285/11728 [1:50:45<2:23:40, 5.97s/it] 88%|████████▊ | 10286/11728 [1:50:51<2:22:58, 5.95s/it] {'loss': 0.4654, 'learning_rate': 7.824818326329264e-07, 'epoch': 0.88} + 88%|████████▊ | 10286/11728 [1:50:51<2:22:58, 5.95s/it] 88%|████████▊ | 10287/11728 [1:50:57<2:22:09, 5.92s/it] {'loss': 0.4697, 'learning_rate': 7.814112911514005e-07, 'epoch': 0.88} + 88%|████████▊ | 10287/11728 [1:50:57<2:22:09, 5.92s/it] 88%|████████▊ | 10288/11728 [1:51:03<2:22:43, 5.95s/it] {'loss': 0.4761, 'learning_rate': 7.803414527179343e-07, 'epoch': 0.88} + 88%|████████▊ | 10288/11728 [1:51:03<2:22:43, 5.95s/it] 88%|████████▊ | 10289/11728 [1:51:08<2:21:27, 5.90s/it] {'loss': 0.4497, 'learning_rate': 7.792723174141192e-07, 'epoch': 0.88} + 88%|████████▊ | 10289/11728 [1:51:08<2:21:27, 5.90s/it] 88%|████████▊ | 10290/11728 [1:51:14<2:20:19, 5.86s/it] {'loss': 0.4412, 'learning_rate': 7.782038853214935e-07, 'epoch': 0.88} + 88%|████████▊ | 10290/11728 [1:51:14<2:20:19, 5.86s/it] 88%|████████▊ | 10291/11728 [1:51:20<2:18:44, 5.79s/it] {'loss': 0.4613, 'learning_rate': 7.771361565215385e-07, 'epoch': 0.88} + 88%|████████▊ | 10291/11728 [1:51:20<2:18:44, 5.79s/it] 88%|████████▊ | 10292/11728 [1:51:26<2:21:15, 5.90s/it] {'loss': 0.444, 'learning_rate': 7.760691310956847e-07, 'epoch': 0.88} + 88%|████████▊ | 10292/11728 [1:51:26<2:21:15, 5.90s/it] 88%|████████▊ | 10293/11728 [1:51:32<2:18:48, 5.80s/it] {'loss': 0.4478, 'learning_rate': 7.750028091253104e-07, 'epoch': 0.88} + 88%|████████▊ | 10293/11728 [1:51:32<2:18:48, 5.80s/it] 88%|████████▊ | 10294/11728 [1:51:37<2:18:56, 5.81s/it] {'loss': 0.4683, 'learning_rate': 7.739371906917326e-07, 'epoch': 0.88} + 88%|████████▊ | 10294/11728 [1:51:37<2:18:56, 5.81s/it] 88%|████████▊ | 10295/11728 [1:51:43<2:19:26, 5.84s/it] {'loss': 0.4348, 'learning_rate': 7.728722758762208e-07, 'epoch': 0.88} + 88%|████████▊ | 10295/11728 [1:51:43<2:19:26, 5.84s/it] 88%|████████▊ | 10296/11728 [1:51:49<2:19:33, 5.85s/it] {'loss': 0.4714, 'learning_rate': 7.718080647599946e-07, 'epoch': 0.88} + 88%|████████▊ | 10296/11728 [1:51:49<2:19:33, 5.85s/it] 88%|████████▊ | 10297/11728 [1:51:55<2:18:44, 5.82s/it] {'loss': 0.4445, 'learning_rate': 7.7074455742421e-07, 'epoch': 0.88} + 88%|████████▊ | 10297/11728 [1:51:55<2:18:44, 5.82s/it] 88%|████████▊ | 10298/11728 [1:52:01<2:17:04, 5.75s/it] {'loss': 0.449, 'learning_rate': 7.696817539499768e-07, 'epoch': 0.88} + 88%|████████▊ | 10298/11728 [1:52:01<2:17:04, 5.75s/it] 88%|████████▊ | 10299/11728 [1:52:07<2:18:18, 5.81s/it] {'loss': 0.4765, 'learning_rate': 7.6861965441835e-07, 'epoch': 0.88} + 88%|████████▊ | 10299/11728 [1:52:07<2:18:18, 5.81s/it]6 AutoResumeHook: Checking whether to suspend... +04 AutoResumeHook: Checking whether to suspend... + 5AutoResumeHook: Checking whether to suspend... AutoResumeHook: Checking whether to suspend... + +2 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... +1 88%|████████▊ | 10300/11728 [1:52:12<2:18:25, 5.82s/it]AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4489, 'learning_rate': 7.675582589103248e-07, 'epoch': 0.88} + 88%|████████▊ | 10300/11728 [1:52:12<2:18:25, 5.82s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-10300/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-10300/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-10300/mm_projector +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/torch/nn/modules/module.py:1802: UserWarning: Positional args are being deprecated, use kwargs instead. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details. + warnings.warn( + 88%|████████▊ | 10301/11728 [1:52:44<5:24:35, 13.65s/it] {'loss': 0.4371, 'learning_rate': 7.664975675068531e-07, 'epoch': 0.88} + 88%|████████▊ | 10301/11728 [1:52:44<5:24:35, 13.65s/it] 88%|████████▊ | 10302/11728 [1:52:50<4:29:23, 11.34s/it] {'loss': 0.4474, 'learning_rate': 7.65437580288827e-07, 'epoch': 0.88} + 88%|████████▊ | 10302/11728 [1:52:50<4:29:23, 11.34s/it] 88%|████████▊ | 10303/11728 [1:52:56<3:49:44, 9.67s/it] {'loss': 0.4731, 'learning_rate': 7.643782973370817e-07, 'epoch': 0.88} + 88%|████████▊ | 10303/11728 [1:52:56<3:49:44, 9.67s/it] 88%|████████▊ | 10304/11728 [1:53:02<3:21:43, 8.50s/it] {'loss': 0.454, 'learning_rate': 7.633197187324048e-07, 'epoch': 0.88} + 88%|████████▊ | 10304/11728 [1:53:02<3:21:43, 8.50s/it] 88%|████████▊ | 10305/11728 [1:53:08<3:07:44, 7.92s/it] {'loss': 0.4405, 'learning_rate': 7.622618445555308e-07, 'epoch': 0.88} + 88%|████████▊ | 10305/11728 [1:53:08<3:07:44, 7.92s/it] 88%|████████▊ | 10306/11728 [1:53:14<2:50:58, 7.21s/it] {'loss': 0.4489, 'learning_rate': 7.612046748871327e-07, 'epoch': 0.88} + 88%|████████▊ | 10306/11728 [1:53:14<2:50:58, 7.21s/it] 88%|████████▊ | 10307/11728 [1:53:20<2:43:15, 6.89s/it] {'loss': 0.4645, 'learning_rate': 7.601482098078372e-07, 'epoch': 0.88} + 88%|████████▊ | 10307/11728 [1:53:20<2:43:15, 6.89s/it] 88%|████████▊ | 10308/11728 [1:53:26<2:36:05, 6.60s/it] {'loss': 0.4477, 'learning_rate': 7.590924493982165e-07, 'epoch': 0.88} + 88%|████████▊ | 10308/11728 [1:53:26<2:36:05, 6.60s/it] 88%|████████▊ | 10309/11728 [1:53:32<2:30:12, 6.35s/it] {'loss': 0.4528, 'learning_rate': 7.580373937387819e-07, 'epoch': 0.88} + 88%|████████▊ | 10309/11728 [1:53:32<2:30:12, 6.35s/it] 88%|████████▊ | 10310/11728 [1:53:38<2:27:03, 6.22s/it] {'loss': 0.4631, 'learning_rate': 7.569830429100012e-07, 'epoch': 0.88} + 88%|████████▊ | 10310/11728 [1:53:38<2:27:03, 6.22s/it] 88%|████████▊ | 10311/11728 [1:53:43<2:23:28, 6.08s/it] {'loss': 0.4534, 'learning_rate': 7.559293969922843e-07, 'epoch': 0.88} + 88%|████████▊ | 10311/11728 [1:53:43<2:23:28, 6.08s/it] 88%|████████▊ | 10312/11728 [1:53:49<2:20:04, 5.94s/it] {'loss': 0.4622, 'learning_rate': 7.548764560659815e-07, 'epoch': 0.88} + 88%|████████▊ | 10312/11728 [1:53:49<2:20:04, 5.94s/it] 88%|████████▊ | 10313/11728 [1:53:55<2:18:53, 5.89s/it] {'loss': 0.4412, 'learning_rate': 7.538242202113965e-07, 'epoch': 0.88} + 88%|████████▊ | 10313/11728 [1:53:55<2:18:53, 5.89s/it] 88%|████████▊ | 10314/11728 [1:54:01<2:18:44, 5.89s/it] {'loss': 0.447, 'learning_rate': 7.527726895087817e-07, 'epoch': 0.88} + 88%|████████▊ | 10314/11728 [1:54:01<2:18:44, 5.89s/it] 88%|████████▊ | 10315/11728 [1:54:06<2:15:24, 5.75s/it] {'loss': 0.4291, 'learning_rate': 7.517218640383262e-07, 'epoch': 0.88} + 88%|████████▊ | 10315/11728 [1:54:06<2:15:24, 5.75s/it] 88%|████████▊ | 10316/11728 [1:54:12<2:15:29, 5.76s/it] {'loss': 0.472, 'learning_rate': 7.506717438801703e-07, 'epoch': 0.88} + 88%|████████▊ | 10316/11728 [1:54:12<2:15:29, 5.76s/it] 88%|████████▊ | 10317/11728 [1:54:18<2:15:56, 5.78s/it] {'loss': 0.46, 'learning_rate': 7.496223291144045e-07, 'epoch': 0.88} + 88%|████████▊ | 10317/11728 [1:54:18<2:15:56, 5.78s/it] 88%|████████▊ | 10318/11728 [1:54:24<2:16:35, 5.81s/it] {'loss': 0.4336, 'learning_rate': 7.485736198210559e-07, 'epoch': 0.88} + 88%|████████▊ | 10318/11728 [1:54:24<2:16:35, 5.81s/it] 88%|████████▊ | 10319/11728 [1:54:29<2:15:32, 5.77s/it] {'loss': 0.4553, 'learning_rate': 7.475256160801081e-07, 'epoch': 0.88} + 88%|████████▊ | 10319/11728 [1:54:29<2:15:32, 5.77s/it] 88%|████████▊ | 10320/11728 [1:54:35<2:17:42, 5.87s/it] {'loss': 0.4685, 'learning_rate': 7.464783179714863e-07, 'epoch': 0.88} + 88%|████████▊ | 10320/11728 [1:54:35<2:17:42, 5.87s/it] 88%|████████▊ | 10321/11728 [1:54:41<2:19:19, 5.94s/it] {'loss': 0.4337, 'learning_rate': 7.454317255750587e-07, 'epoch': 0.88} + 88%|████████▊ | 10321/11728 [1:54:41<2:19:19, 5.94s/it] 88%|████████▊ | 10322/11728 [1:54:47<2:18:54, 5.93s/it] {'loss': 0.4493, 'learning_rate': 7.443858389706449e-07, 'epoch': 0.88} + 88%|████████▊ | 10322/11728 [1:54:47<2:18:54, 5.93s/it] 88%|████████▊ | 10323/11728 [1:54:53<2:16:48, 5.84s/it] {'loss': 0.4327, 'learning_rate': 7.433406582380076e-07, 'epoch': 0.88} + 88%|████████▊ | 10323/11728 [1:54:53<2:16:48, 5.84s/it] 88%|████████▊ | 10324/11728 [1:54:59<2:15:14, 5.78s/it] {'loss': 0.4466, 'learning_rate': 7.422961834568565e-07, 'epoch': 0.88} + 88%|████████▊ | 10324/11728 [1:54:59<2:15:14, 5.78s/it] 88%|████████▊ | 10325/11728 [1:55:04<2:14:16, 5.74s/it] {'loss': 0.461, 'learning_rate': 7.41252414706849e-07, 'epoch': 0.88} + 88%|████████▊ | 10325/11728 [1:55:04<2:14:16, 5.74s/it] 88%|████████▊ | 10326/11728 [1:55:10<2:14:02, 5.74s/it] {'loss': 0.456, 'learning_rate': 7.402093520675879e-07, 'epoch': 0.88} + 88%|████████▊ | 10326/11728 [1:55:10<2:14:02, 5.74s/it] 88%|████████▊ | 10327/11728 [1:55:16<2:13:13, 5.71s/it] {'loss': 0.4352, 'learning_rate': 7.391669956186165e-07, 'epoch': 0.88} + 88%|████████▊ | 10327/11728 [1:55:16<2:13:13, 5.71s/it] 88%|████████▊ | 10328/11728 [1:55:21<2:14:07, 5.75s/it] {'loss': 0.4514, 'learning_rate': 7.381253454394343e-07, 'epoch': 0.88} + 88%|████████▊ | 10328/11728 [1:55:21<2:14:07, 5.75s/it] 88%|████████▊ | 10329/11728 [1:55:27<2:13:42, 5.73s/it] {'loss': 0.4613, 'learning_rate': 7.370844016094836e-07, 'epoch': 0.88} + 88%|████████▊ | 10329/11728 [1:55:27<2:13:42, 5.73s/it] 88%|████████▊ | 10330/11728 [1:55:33<2:14:21, 5.77s/it] {'loss': 0.4518, 'learning_rate': 7.36044164208145e-07, 'epoch': 0.88} + 88%|████████▊ | 10330/11728 [1:55:33<2:14:21, 5.77s/it] 88%|████████▊ | 10331/11728 [1:55:39<2:13:21, 5.73s/it] {'loss': 0.439, 'learning_rate': 7.350046333147543e-07, 'epoch': 0.88} + 88%|████████▊ | 10331/11728 [1:55:39<2:13:21, 5.73s/it] 88%|████████▊ | 10332/11728 [1:55:44<2:13:42, 5.75s/it] {'loss': 0.4764, 'learning_rate': 7.339658090085899e-07, 'epoch': 0.88} + 88%|████████▊ | 10332/11728 [1:55:44<2:13:42, 5.75s/it] 88%|████████▊ | 10333/11728 [1:55:50<2:14:01, 5.76s/it] {'loss': 0.4693, 'learning_rate': 7.329276913688788e-07, 'epoch': 0.88} + 88%|████████▊ | 10333/11728 [1:55:50<2:14:01, 5.76s/it] 88%|████████▊ | 10334/11728 [1:55:56<2:13:28, 5.75s/it] {'loss': 0.4467, 'learning_rate': 7.318902804747896e-07, 'epoch': 0.88} + 88%|████████▊ | 10334/11728 [1:55:56<2:13:28, 5.75s/it] 88%|████████▊ | 10335/11728 [1:56:02<2:13:26, 5.75s/it] {'loss': 0.4763, 'learning_rate': 7.308535764054437e-07, 'epoch': 0.88} + 88%|████████▊ | 10335/11728 [1:56:02<2:13:26, 5.75s/it] 88%|████████▊ | 10336/11728 [1:56:08<2:13:44, 5.76s/it] {'loss': 0.4355, 'learning_rate': 7.298175792398976e-07, 'epoch': 0.88} + 88%|████████▊ | 10336/11728 [1:56:08<2:13:44, 5.76s/it] 88%|████████▊ | 10337/11728 [1:56:13<2:14:00, 5.78s/it] {'loss': 0.4473, 'learning_rate': 7.287822890571661e-07, 'epoch': 0.88} + 88%|████████▊ | 10337/11728 [1:56:13<2:14:00, 5.78s/it] 88%|████████▊ | 10338/11728 [1:56:19<2:16:19, 5.88s/it] {'loss': 0.4565, 'learning_rate': 7.277477059362059e-07, 'epoch': 0.88} + 88%|████████▊ | 10338/11728 [1:56:19<2:16:19, 5.88s/it] 88%|████████▊ | 10339/11728 [1:56:25<2:16:58, 5.92s/it] {'loss': 0.4501, 'learning_rate': 7.267138299559129e-07, 'epoch': 0.88} + 88%|████████▊ | 10339/11728 [1:56:25<2:16:58, 5.92s/it] 88%|████████▊ | 10340/11728 [1:56:31<2:16:33, 5.90s/it] {'loss': 0.4693, 'learning_rate': 7.256806611951395e-07, 'epoch': 0.88} + 88%|████████▊ | 10340/11728 [1:56:31<2:16:33, 5.90s/it] 88%|████████▊ | 10341/11728 [1:56:37<2:14:32, 5.82s/it] {'loss': 0.4588, 'learning_rate': 7.246481997326782e-07, 'epoch': 0.88} + 88%|████████▊ | 10341/11728 [1:56:37<2:14:32, 5.82s/it] 88%|████████▊ | 10342/11728 [1:56:43<2:12:55, 5.75s/it] {'loss': 0.4738, 'learning_rate': 7.236164456472672e-07, 'epoch': 0.88} + 88%|████████▊ | 10342/11728 [1:56:43<2:12:55, 5.75s/it] 88%|████████▊ | 10343/11728 [1:56:48<2:13:58, 5.80s/it] {'loss': 0.4685, 'learning_rate': 7.225853990175946e-07, 'epoch': 0.88} + 88%|████████▊ | 10343/11728 [1:56:48<2:13:58, 5.80s/it] 88%|████████▊ | 10344/11728 [1:56:54<2:12:55, 5.76s/it] {'loss': 0.4572, 'learning_rate': 7.215550599222931e-07, 'epoch': 0.88} + 88%|████████▊ | 10344/11728 [1:56:54<2:12:55, 5.76s/it] 88%|████████▊ | 10345/11728 [1:57:00<2:10:57, 5.68s/it] {'loss': 0.4299, 'learning_rate': 7.205254284399366e-07, 'epoch': 0.88} + 88%|████████▊ | 10345/11728 [1:57:00<2:10:57, 5.68s/it] 88%|████████▊ | 10346/11728 [1:57:05<2:11:43, 5.72s/it] {'loss': 0.4613, 'learning_rate': 7.194965046490521e-07, 'epoch': 0.88} + 88%|████████▊ | 10346/11728 [1:57:05<2:11:43, 5.72s/it] 88%|████████▊ | 10347/11728 [1:57:11<2:12:07, 5.74s/it] {'loss': 0.44, 'learning_rate': 7.184682886281114e-07, 'epoch': 0.88} + 88%|████████▊ | 10347/11728 [1:57:11<2:12:07, 5.74s/it] 88%|████████▊ | 10348/11728 [1:57:17<2:11:14, 5.71s/it] {'loss': 0.4391, 'learning_rate': 7.174407804555261e-07, 'epoch': 0.88} + 88%|████████▊ | 10348/11728 [1:57:17<2:11:14, 5.71s/it] 88%|████████▊ | 10349/11728 [1:57:23<2:11:46, 5.73s/it] {'loss': 0.4524, 'learning_rate': 7.164139802096604e-07, 'epoch': 0.88} + 88%|████████▊ | 10349/11728 [1:57:23<2:11:46, 5.73s/it]7 AutoResumeHook: Checking whether to suspend... +6 5AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... +0 AutoResumeHook: Checking whether to suspend... + 88%|████████▊ | 10350/11728 [1:57:29<2:12:44, 5.78s/it]1 AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... + {'loss': 0.44, 'learning_rate': 7.153878879688225e-07, 'epoch': 0.88} + 88%|████████▊ | 10350/11728 [1:57:29<2:12:44, 5.78s/it] 88%|████████▊ | 10351/11728 [1:57:34<2:12:47, 5.79s/it] {'loss': 0.4359, 'learning_rate': 7.143625038112667e-07, 'epoch': 0.88} + 88%|████████▊ | 10351/11728 [1:57:34<2:12:47, 5.79s/it] 88%|████████▊ | 10352/11728 [1:57:40<2:13:20, 5.81s/it] {'loss': 0.4407, 'learning_rate': 7.133378278151926e-07, 'epoch': 0.88} + 88%|████████▊ | 10352/11728 [1:57:40<2:13:20, 5.81s/it] 88%|████████▊ | 10353/11728 [1:57:46<2:12:52, 5.80s/it] {'loss': 0.4496, 'learning_rate': 7.123138600587476e-07, 'epoch': 0.88} + 88%|████████▊ | 10353/11728 [1:57:46<2:12:52, 5.80s/it] 88%|████████▊ | 10354/11728 [1:57:52<2:14:01, 5.85s/it] {'loss': 0.4552, 'learning_rate': 7.112906006200215e-07, 'epoch': 0.88} + 88%|████████▊ | 10354/11728 [1:57:52<2:14:01, 5.85s/it] 88%|████████▊ | 10355/11728 [1:57:58<2:13:47, 5.85s/it] {'loss': 0.4759, 'learning_rate': 7.102680495770509e-07, 'epoch': 0.88} + 88%|████████▊ | 10355/11728 [1:57:58<2:13:47, 5.85s/it] 88%|████████▊ | 10356/11728 [1:58:04<2:13:30, 5.84s/it] {'loss': 0.4537, 'learning_rate': 7.092462070078265e-07, 'epoch': 0.88} + 88%|████████▊ | 10356/11728 [1:58:04<2:13:30, 5.84s/it] 88%|████████▊ | 10357/11728 [1:58:10<2:15:24, 5.93s/it] {'loss': 0.4146, 'learning_rate': 7.082250729902718e-07, 'epoch': 0.88} + 88%|████████▊ | 10357/11728 [1:58:10<2:15:24, 5.93s/it] 88%|████████▊ | 10358/11728 [1:58:16<2:16:14, 5.97s/it] {'loss': 0.4612, 'learning_rate': 7.072046476022654e-07, 'epoch': 0.88} + 88%|████████▊ | 10358/11728 [1:58:16<2:16:14, 5.97s/it] 88%|████████▊ | 10359/11728 [1:58:21<2:13:27, 5.85s/it] {'loss': 0.4493, 'learning_rate': 7.061849309216285e-07, 'epoch': 0.88} + 88%|████████▊ | 10359/11728 [1:58:21<2:13:27, 5.85s/it] 88%|████████▊ | 10360/11728 [1:58:27<2:12:56, 5.83s/it] {'loss': 0.4512, 'learning_rate': 7.051659230261299e-07, 'epoch': 0.88} + 88%|████████▊ | 10360/11728 [1:58:27<2:12:56, 5.83s/it] 88%|████████▊ | 10361/11728 [1:58:33<2:11:52, 5.79s/it] {'loss': 0.4521, 'learning_rate': 7.041476239934819e-07, 'epoch': 0.88} + 88%|████████▊ | 10361/11728 [1:58:33<2:11:52, 5.79s/it] 88%|████████▊ | 10362/11728 [1:58:39<2:13:06, 5.85s/it] {'loss': 0.4624, 'learning_rate': 7.031300339013481e-07, 'epoch': 0.88} + 88%|████████▊ | 10362/11728 [1:58:39<2:13:06, 5.85s/it] 88%|████████▊ | 10363/11728 [1:58:45<2:13:03, 5.85s/it] {'loss': 0.4513, 'learning_rate': 7.021131528273284e-07, 'epoch': 0.88} + 88%|████████▊ | 10363/11728 [1:58:45<2:13:03, 5.85s/it] 88%|████████▊ | 10364/11728 [1:58:50<2:10:34, 5.74s/it] {'loss': 0.4352, 'learning_rate': 7.010969808489754e-07, 'epoch': 0.88} + 88%|████████▊ | 10364/11728 [1:58:50<2:10:34, 5.74s/it] 88%|████████▊ | 10365/11728 [1:58:56<2:11:12, 5.78s/it] {'loss': 0.4605, 'learning_rate': 7.000815180437925e-07, 'epoch': 0.88} + 88%|████████▊ | 10365/11728 [1:58:56<2:11:12, 5.78s/it] 88%|████████▊ | 10366/11728 [1:59:02<2:11:29, 5.79s/it] {'loss': 0.4449, 'learning_rate': 6.990667644892168e-07, 'epoch': 0.88} + 88%|████████▊ | 10366/11728 [1:59:02<2:11:29, 5.79s/it] 88%|████████▊ | 10367/11728 [1:59:08<2:13:26, 5.88s/it] {'loss': 0.4461, 'learning_rate': 6.980527202626397e-07, 'epoch': 0.88} + 88%|████████▊ | 10367/11728 [1:59:08<2:13:26, 5.88s/it] 88%|████████▊ | 10368/11728 [1:59:14<2:13:16, 5.88s/it] {'loss': 0.4502, 'learning_rate': 6.97039385441397e-07, 'epoch': 0.88} + 88%|████████▊ | 10368/11728 [1:59:14<2:13:16, 5.88s/it] 88%|████████▊ | 10369/11728 [1:59:19<2:10:29, 5.76s/it] {'loss': 0.4718, 'learning_rate': 6.960267601027693e-07, 'epoch': 0.88} + 88%|████████▊ | 10369/11728 [1:59:19<2:10:29, 5.76s/it] 88%|████████▊ | 10370/11728 [1:59:25<2:09:25, 5.72s/it] {'loss': 0.4352, 'learning_rate': 6.950148443239846e-07, 'epoch': 0.88} + 88%|████████▊ | 10370/11728 [1:59:25<2:09:25, 5.72s/it] 88%|████████▊ | 10371/11728 [1:59:31<2:10:04, 5.75s/it] {'loss': 0.4505, 'learning_rate': 6.940036381822135e-07, 'epoch': 0.88} + 88%|████████▊ | 10371/11728 [1:59:31<2:10:04, 5.75s/it] 88%|████████▊ | 10372/11728 [1:59:36<2:09:28, 5.73s/it] {'loss': 0.4626, 'learning_rate': 6.929931417545787e-07, 'epoch': 0.88} + 88%|████████▊ | 10372/11728 [1:59:36<2:09:28, 5.73s/it] 88%|████████▊ | 10373/11728 [1:59:42<2:10:16, 5.77s/it] {'loss': 0.442, 'learning_rate': 6.919833551181399e-07, 'epoch': 0.88} + 88%|████████▊ | 10373/11728 [1:59:42<2:10:16, 5.77s/it] 88%|████████▊ | 10374/11728 [1:59:48<2:10:13, 5.77s/it] {'loss': 0.4644, 'learning_rate': 6.909742783499129e-07, 'epoch': 0.88} + 88%|████████▊ | 10374/11728 [1:59:48<2:10:13, 5.77s/it] 88%|████████▊ | 10375/11728 [1:59:54<2:10:02, 5.77s/it] {'loss': 0.4635, 'learning_rate': 6.899659115268498e-07, 'epoch': 0.88} + 88%|████████▊ | 10375/11728 [1:59:54<2:10:02, 5.77s/it] 88%|████████▊ | 10376/11728 [2:00:00<2:09:51, 5.76s/it] {'loss': 0.4532, 'learning_rate': 6.889582547258545e-07, 'epoch': 0.88} + 88%|████████▊ | 10376/11728 [2:00:00<2:09:51, 5.76s/it] 88%|████████▊ | 10377/11728 [2:00:05<2:10:09, 5.78s/it] {'loss': 0.4746, 'learning_rate': 6.879513080237754e-07, 'epoch': 0.88} + 88%|████████▊ | 10377/11728 [2:00:05<2:10:09, 5.78s/it] 88%|████████▊ | 10378/11728 [2:00:11<2:08:45, 5.72s/it] {'loss': 0.4474, 'learning_rate': 6.869450714974058e-07, 'epoch': 0.88} + 88%|████████▊ | 10378/11728 [2:00:11<2:08:45, 5.72s/it] 88%|████████▊ | 10379/11728 [2:00:17<2:08:23, 5.71s/it] {'loss': 0.4501, 'learning_rate': 6.859395452234863e-07, 'epoch': 0.88} + 88%|████████▊ | 10379/11728 [2:00:17<2:08:23, 5.71s/it] 89%|████████▊ | 10380/11728 [2:00:22<2:08:34, 5.72s/it] {'loss': 0.4744, 'learning_rate': 6.849347292787012e-07, 'epoch': 0.89} + 89%|████████▊ | 10380/11728 [2:00:22<2:08:34, 5.72s/it] 89%|████████▊ | 10381/11728 [2:00:28<2:08:44, 5.73s/it] {'loss': 0.4645, 'learning_rate': 6.839306237396859e-07, 'epoch': 0.89} + 89%|████████▊ | 10381/11728 [2:00:28<2:08:44, 5.73s/it] 89%|████████▊ | 10382/11728 [2:00:34<2:07:53, 5.70s/it] {'loss': 0.4603, 'learning_rate': 6.829272286830102e-07, 'epoch': 0.89} + 89%|████████▊ | 10382/11728 [2:00:34<2:07:53, 5.70s/it] 89%|████████▊ | 10383/11728 [2:00:40<2:10:33, 5.82s/it] {'loss': 0.4461, 'learning_rate': 6.819245441852051e-07, 'epoch': 0.89} + 89%|████████▊ | 10383/11728 [2:00:40<2:10:33, 5.82s/it] 89%|████████▊ | 10384/11728 [2:00:46<2:09:00, 5.76s/it] {'loss': 0.4318, 'learning_rate': 6.809225703227352e-07, 'epoch': 0.89} + 89%|████████▊ | 10384/11728 [2:00:46<2:09:00, 5.76s/it] 89%|████████▊ | 10385/11728 [2:00:51<2:08:43, 5.75s/it] {'loss': 0.447, 'learning_rate': 6.799213071720156e-07, 'epoch': 0.89} + 89%|████████▊ | 10385/11728 [2:00:51<2:08:43, 5.75s/it] 89%|████████▊ | 10386/11728 [2:00:57<2:08:50, 5.76s/it] {'loss': 0.4407, 'learning_rate': 6.789207548094068e-07, 'epoch': 0.89} + 89%|████████▊ | 10386/11728 [2:00:57<2:08:50, 5.76s/it] 89%|████████▊ | 10387/11728 [2:01:03<2:09:11, 5.78s/it] {'loss': 0.4659, 'learning_rate': 6.779209133112164e-07, 'epoch': 0.89} + 89%|████████▊ | 10387/11728 [2:01:03<2:09:11, 5.78s/it] 89%|████████▊ | 10388/11728 [2:01:09<2:07:56, 5.73s/it] {'loss': 0.4589, 'learning_rate': 6.769217827536956e-07, 'epoch': 0.89} + 89%|████████▊ | 10388/11728 [2:01:09<2:07:56, 5.73s/it] 89%|████████▊ | 10389/11728 [2:01:15<2:09:51, 5.82s/it] {'loss': 0.4557, 'learning_rate': 6.759233632130413e-07, 'epoch': 0.89} + 89%|████████▊ | 10389/11728 [2:01:15<2:09:51, 5.82s/it] 89%|████████▊ | 10390/11728 [2:01:20<2:08:52, 5.78s/it] {'loss': 0.4446, 'learning_rate': 6.749256547654004e-07, 'epoch': 0.89} + 89%|████████▊ | 10390/11728 [2:01:20<2:08:52, 5.78s/it] 89%|████████▊ | 10391/11728 [2:01:26<2:08:00, 5.74s/it] {'loss': 0.464, 'learning_rate': 6.739286574868575e-07, 'epoch': 0.89} + 89%|████████▊ | 10391/11728 [2:01:26<2:08:00, 5.74s/it] 89%|████████▊ | 10392/11728 [2:01:32<2:07:31, 5.73s/it] {'loss': 0.4395, 'learning_rate': 6.72932371453453e-07, 'epoch': 0.89} + 89%|████████▊ | 10392/11728 [2:01:32<2:07:31, 5.73s/it] 89%|████████▊ | 10393/11728 [2:01:37<2:07:06, 5.71s/it] {'loss': 0.4454, 'learning_rate': 6.719367967411638e-07, 'epoch': 0.89} + 89%|████████▊ | 10393/11728 [2:01:37<2:07:06, 5.71s/it]WARNING: tokenization mismatch: 1 vs. 737. [[{'from': 'human', 'value': 'ASSISTANT: You are a top consultant specialising in advising tax firms and have the following skills and qualities.\n\nKNOWLEDGE: Consultant in a top consulting firm specialising in tax consulting, senior strategist, digital expert.\n\nCHARACTERISTICS: Customer-focused, empathetic, solution-oriented, personable, persuasive, creative.\n\nTASK: Use your knowledge to develop 10 measures to encourage clients to submit their documents digitally instead of by post. The measures should be formulated in such a way that the client recognises the advantages of digital filing. The law firm is digitised and can accept digital documents.\n\nOUTPUT: A list of the 10 actions, each with the name of the action as a heading and 2 short additional bullet points.\n\nOUTPUT LANGUAGE: German'}, {'from': 'gpt', 'value': '1. Persönlicher Kontakt und Beratung:\n\t* Persönliche Beratung und Unterstützung bei der Umstellung auf digitales Einreichen\n\t* Betonung der Vorteile, wie Zeit- und Kosteneinsparungen\n2. Schulung und Unterstützung:\n\t* Schulungen für die digitale Einreichung von Dokumenten\n\t* Anleitung zur Nutzung von Tools und Software\n3. Anreize schaffen:\n\t* Ermäßigung bei der Beauftragung digitaler Dienstleistungen\n\t* Sonderangebote für Kunden, die ihre Dokumente digital einreichen\n4. Informationen bereitstellen:\n\t* Veröffentlichung von Leitfäden und Handbüchern für die digitale Einreichung von Dokumenten\n\t* FAQ-Liste für häufig gestellte Fragen zum digitalen Einreichen\n5. Klare Kommunikation:\n\t* Verständliche Kommunikation der Vorteile der digitalen Einreichung\n\t* Bereitstellung von Informationen über die Sicherheit der digitalen Übermittlung\n6. Einfache Zugänglichkeit:\n\t* Vereinfachung des digitalen Einreichungsprozesses durch intuitive Online-Plattformen\n\t* Bereitstellung von Unterstützung für den Fall technischer Schwierigkeiten\n7. Zeitersparnis betonen:\n\t* Betonung der Vorteile von Zeitersparnis durch digitales Einreichen\n\t* Erinnerungen an Fristen und den Nutzen der pünktlichen Einreichung\n8. Umweltbewusstsein:\n\t* Betonung des Umweltvorteils durch digitales Einreichen von Dokumenten\n\t* Verweis auf die Möglichkeit, Papierverbrauch zu reduzieren\n9. Kosteneffizienz:\n\t* Betonung der Vorteile von Kosteneinsparungen durch digitales Einreichen\n\t* Verweis auf die Möglichkeit, Papier- und Portokosten zu sparen\n10. Feedback einholen:\n* Umfrage zur Bewertung des digitalen Einreichungsprozesses\n* Analyse der Ergebnisse zur Verbesserung der digitalen Dienstleistungen'}]] (ignored) + 89%|████████▊ | 10394/11728 [2:01:43<2:08:49, 5.79s/it] {'loss': 0.4568, 'learning_rate': 6.70941933425917e-07, 'epoch': 0.89} + 89%|████████▊ | 10394/11728 [2:01:43<2:08:49, 5.79s/it] 89%|████████▊ | 10395/11728 [2:01:49<2:08:14, 5.77s/it] {'loss': 0.4543, 'learning_rate': 6.699477815835875e-07, 'epoch': 0.89} + 89%|████████▊ | 10395/11728 [2:01:49<2:08:14, 5.77s/it] 89%|████████▊ | 10396/11728 [2:01:55<2:08:44, 5.80s/it] {'loss': 0.4547, 'learning_rate': 6.689543412899913e-07, 'epoch': 0.89} + 89%|████████▊ | 10396/11728 [2:01:55<2:08:44, 5.80s/it] 89%|████████▊ | 10397/11728 [2:02:01<2:08:32, 5.79s/it] {'loss': 0.4629, 'learning_rate': 6.679616126208921e-07, 'epoch': 0.89} + 89%|████████▊ | 10397/11728 [2:02:01<2:08:32, 5.79s/it] 89%|████████▊ | 10398/11728 [2:02:07<2:09:39, 5.85s/it] {'loss': 0.4627, 'learning_rate': 6.669695956520017e-07, 'epoch': 0.89} + 89%|████████▊ | 10398/11728 [2:02:07<2:09:39, 5.85s/it] 89%|████████▊ | 10399/11728 [2:02:12<2:09:25, 5.84s/it] {'loss': 0.4567, 'learning_rate': 6.659782904589752e-07, 'epoch': 0.89} + 89%|████████▊ | 10399/11728 [2:02:12<2:09:25, 5.84s/it]3 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +06 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... + 89%|████████▊ | 10400/11728 [2:02:18<2:07:43, 5.77s/it]2 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4556, 'learning_rate': 6.649876971174118e-07, 'epoch': 0.89} + 89%|████████▊ | 10400/11728 [2:02:18<2:07:43, 5.77s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-10400/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-10400/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-10400/mm_projector +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/torch/nn/modules/module.py:1802: UserWarning: Positional args are being deprecated, use kwargs instead. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details. + warnings.warn( + 89%|████████▊ | 10401/11728 [2:02:53<5:20:00, 14.47s/it] {'loss': 0.4783, 'learning_rate': 6.639978157028581e-07, 'epoch': 0.89} + 89%|████████▊ | 10401/11728 [2:02:53<5:20:00, 14.47s/it] 89%|████████▊ | 10402/11728 [2:02:58<4:20:31, 11.79s/it] {'loss': 0.4499, 'learning_rate': 6.630086462908081e-07, 'epoch': 0.89} + 89%|████████▊ | 10402/11728 [2:02:58<4:20:31, 11.79s/it] 89%|████████▊ | 10403/11728 [2:03:04<3:40:49, 10.00s/it] {'loss': 0.4424, 'learning_rate': 6.620201889566991e-07, 'epoch': 0.89} + 89%|████████▊ | 10403/11728 [2:03:04<3:40:49, 10.00s/it] 89%|████████▊ | 10404/11728 [2:03:10<3:12:41, 8.73s/it] {'loss': 0.4446, 'learning_rate': 6.610324437759153e-07, 'epoch': 0.89} + 89%|████████▊ | 10404/11728 [2:03:10<3:12:41, 8.73s/it] 89%|████████▊ | 10405/11728 [2:03:16<2:52:58, 7.84s/it] {'loss': 0.4431, 'learning_rate': 6.600454108237875e-07, 'epoch': 0.89} + 89%|████████▊ | 10405/11728 [2:03:16<2:52:58, 7.84s/it] 89%|████████▊ | 10406/11728 [2:03:22<2:39:59, 7.26s/it] {'loss': 0.4559, 'learning_rate': 6.590590901755889e-07, 'epoch': 0.89} + 89%|████████▊ | 10406/11728 [2:03:22<2:39:59, 7.26s/it] 89%|████████▊ | 10407/11728 [2:03:27<2:28:19, 6.74s/it] {'loss': 0.4516, 'learning_rate': 6.580734819065415e-07, 'epoch': 0.89} + 89%|████████▊ | 10407/11728 [2:03:27<2:28:19, 6.74s/it] 89%|████████▊ | 10408/11728 [2:03:33<2:23:01, 6.50s/it] {'loss': 0.4536, 'learning_rate': 6.57088586091813e-07, 'epoch': 0.89} + 89%|████████▊ | 10408/11728 [2:03:33<2:23:01, 6.50s/it] 89%|████████▉ | 10409/11728 [2:03:39<2:20:24, 6.39s/it] {'loss': 0.4696, 'learning_rate': 6.561044028065134e-07, 'epoch': 0.89} + 89%|████████▉ | 10409/11728 [2:03:39<2:20:24, 6.39s/it] 89%|████████▉ | 10410/11728 [2:03:45<2:18:00, 6.28s/it] {'loss': 0.4421, 'learning_rate': 6.551209321257013e-07, 'epoch': 0.89} + 89%|████████▉ | 10410/11728 [2:03:45<2:18:00, 6.28s/it] 89%|████████▉ | 10411/11728 [2:03:51<2:13:42, 6.09s/it] {'loss': 0.4728, 'learning_rate': 6.541381741243802e-07, 'epoch': 0.89} + 89%|████████▉ | 10411/11728 [2:03:51<2:13:42, 6.09s/it] 89%|████████▉ | 10412/11728 [2:03:57<2:10:58, 5.97s/it] {'loss': 0.4338, 'learning_rate': 6.531561288775001e-07, 'epoch': 0.89} + 89%|████████▉ | 10412/11728 [2:03:57<2:10:58, 5.97s/it] 89%|████████▉ | 10413/11728 [2:04:02<2:09:48, 5.92s/it] {'loss': 0.4656, 'learning_rate': 6.521747964599556e-07, 'epoch': 0.89} + 89%|████████▉ | 10413/11728 [2:04:02<2:09:48, 5.92s/it] 89%|████████▉ | 10414/11728 [2:04:08<2:09:31, 5.91s/it] {'loss': 0.4815, 'learning_rate': 6.51194176946588e-07, 'epoch': 0.89} + 89%|████████▉ | 10414/11728 [2:04:08<2:09:31, 5.91s/it] 89%|████████▉ | 10415/11728 [2:04:14<2:10:27, 5.96s/it] {'loss': 0.4442, 'learning_rate': 6.502142704121816e-07, 'epoch': 0.89} + 89%|████████▉ | 10415/11728 [2:04:14<2:10:27, 5.96s/it] 89%|████████▉ | 10416/11728 [2:04:20<2:09:17, 5.91s/it] {'loss': 0.4304, 'learning_rate': 6.492350769314693e-07, 'epoch': 0.89} + 89%|████████▉ | 10416/11728 [2:04:20<2:09:17, 5.91s/it] 89%|████████▉ | 10417/11728 [2:04:26<2:08:07, 5.86s/it] {'loss': 0.4654, 'learning_rate': 6.482565965791299e-07, 'epoch': 0.89} + 89%|████████▉ | 10417/11728 [2:04:26<2:08:07, 5.86s/it] 89%|████████▉ | 10418/11728 [2:04:32<2:10:03, 5.96s/it] {'loss': 0.4649, 'learning_rate': 6.472788294297827e-07, 'epoch': 0.89} + 89%|████████▉ | 10418/11728 [2:04:32<2:10:03, 5.96s/it] 89%|████████▉ | 10419/11728 [2:04:38<2:09:15, 5.93s/it] {'loss': 0.4442, 'learning_rate': 6.463017755579992e-07, 'epoch': 0.89} + 89%|████████▉ | 10419/11728 [2:04:38<2:09:15, 5.93s/it] 89%|████████▉ | 10420/11728 [2:04:44<2:08:58, 5.92s/it] {'loss': 0.4444, 'learning_rate': 6.453254350382921e-07, 'epoch': 0.89} + 89%|████████▉ | 10420/11728 [2:04:44<2:08:58, 5.92s/it] 89%|████████▉ | 10421/11728 [2:04:49<2:06:12, 5.79s/it] {'loss': 0.4391, 'learning_rate': 6.443498079451215e-07, 'epoch': 0.89} + 89%|████████▉ | 10421/11728 [2:04:49<2:06:12, 5.79s/it] 89%|████████▉ | 10422/11728 [2:04:55<2:07:01, 5.84s/it] {'loss': 0.4546, 'learning_rate': 6.43374894352895e-07, 'epoch': 0.89} + 89%|████████▉ | 10422/11728 [2:04:55<2:07:01, 5.84s/it] 89%|████████▉ | 10423/11728 [2:05:01<2:06:06, 5.80s/it] {'loss': 0.4642, 'learning_rate': 6.424006943359606e-07, 'epoch': 0.89} + 89%|████████▉ | 10423/11728 [2:05:01<2:06:06, 5.80s/it] 89%|████████▉ | 10424/11728 [2:05:07<2:06:24, 5.82s/it] {'loss': 0.441, 'learning_rate': 6.414272079686157e-07, 'epoch': 0.89} + 89%|████████▉ | 10424/11728 [2:05:07<2:06:24, 5.82s/it] 89%|████████▉ | 10425/11728 [2:05:13<2:06:05, 5.81s/it] {'loss': 0.4428, 'learning_rate': 6.404544353251041e-07, 'epoch': 0.89} + 89%|████████▉ | 10425/11728 [2:05:13<2:06:05, 5.81s/it] 89%|████████▉ | 10426/11728 [2:05:18<2:05:55, 5.80s/it] {'loss': 0.4459, 'learning_rate': 6.394823764796121e-07, 'epoch': 0.89} + 89%|████████▉ | 10426/11728 [2:05:18<2:05:55, 5.80s/it] 89%|████████▉ | 10427/11728 [2:05:24<2:04:46, 5.75s/it] {'loss': 0.4438, 'learning_rate': 6.385110315062725e-07, 'epoch': 0.89} + 89%|████████▉ | 10427/11728 [2:05:24<2:04:46, 5.75s/it] 89%|████████▉ | 10428/11728 [2:05:30<2:06:01, 5.82s/it] {'loss': 0.4472, 'learning_rate': 6.37540400479163e-07, 'epoch': 0.89} + 89%|████████▉ | 10428/11728 [2:05:30<2:06:01, 5.82s/it] 89%|████████▉ | 10429/11728 [2:05:36<2:06:39, 5.85s/it] {'loss': 0.4709, 'learning_rate': 6.36570483472313e-07, 'epoch': 0.89} + 89%|████████▉ | 10429/11728 [2:05:36<2:06:39, 5.85s/it] 89%|████████▉ | 10430/11728 [2:05:42<2:05:30, 5.80s/it] {'loss': 0.459, 'learning_rate': 6.356012805596867e-07, 'epoch': 0.89} + 89%|████████▉ | 10430/11728 [2:05:42<2:05:30, 5.80s/it] 89%|████████▉ | 10431/11728 [2:05:48<2:06:21, 5.85s/it] {'loss': 0.453, 'learning_rate': 6.346327918152029e-07, 'epoch': 0.89} + 89%|████████▉ | 10431/11728 [2:05:48<2:06:21, 5.85s/it] 89%|████████▉ | 10432/11728 [2:05:53<2:06:13, 5.84s/it] {'loss': 0.4512, 'learning_rate': 6.336650173127224e-07, 'epoch': 0.89} + 89%|████████▉ | 10432/11728 [2:05:53<2:06:13, 5.84s/it] 89%|████████▉ | 10433/11728 [2:05:59<2:06:31, 5.86s/it] {'loss': 0.4729, 'learning_rate': 6.326979571260483e-07, 'epoch': 0.89} + 89%|████████▉ | 10433/11728 [2:05:59<2:06:31, 5.86s/it] 89%|████████▉ | 10434/11728 [2:06:05<2:07:14, 5.90s/it] {'loss': 0.4487, 'learning_rate': 6.317316113289373e-07, 'epoch': 0.89} + 89%|████████▉ | 10434/11728 [2:06:05<2:07:14, 5.90s/it] 89%|████████▉ | 10435/11728 [2:06:11<2:06:18, 5.86s/it] {'loss': 0.4295, 'learning_rate': 6.30765979995086e-07, 'epoch': 0.89} + 89%|████████▉ | 10435/11728 [2:06:11<2:06:18, 5.86s/it] 89%|████████▉ | 10436/11728 [2:06:17<2:04:31, 5.78s/it] {'loss': 0.4817, 'learning_rate': 6.298010631981344e-07, 'epoch': 0.89} + 89%|████████▉ | 10436/11728 [2:06:17<2:04:31, 5.78s/it] 89%|████████▉ | 10437/11728 [2:06:23<2:05:05, 5.81s/it] {'loss': 0.4512, 'learning_rate': 6.288368610116724e-07, 'epoch': 0.89} + 89%|████████▉ | 10437/11728 [2:06:23<2:05:05, 5.81s/it] 89%|████████▉ | 10438/11728 [2:06:28<2:03:54, 5.76s/it] {'loss': 0.4655, 'learning_rate': 6.278733735092379e-07, 'epoch': 0.89} + 89%|████████▉ | 10438/11728 [2:06:28<2:03:54, 5.76s/it] 89%|████████▉ | 10439/11728 [2:06:34<2:02:24, 5.70s/it] {'loss': 0.4545, 'learning_rate': 6.269106007643056e-07, 'epoch': 0.89} + 89%|████████▉ | 10439/11728 [2:06:34<2:02:24, 5.70s/it] 89%|████████▉ | 10440/11728 [2:06:39<2:02:26, 5.70s/it] {'loss': 0.4409, 'learning_rate': 6.259485428503021e-07, 'epoch': 0.89} + 89%|████████▉ | 10440/11728 [2:06:39<2:02:26, 5.70s/it] 89%|████████▉ | 10441/11728 [2:06:45<2:02:39, 5.72s/it] {'loss': 0.4529, 'learning_rate': 6.249871998405998e-07, 'epoch': 0.89} + 89%|████████▉ | 10441/11728 [2:06:45<2:02:39, 5.72s/it] 89%|████████▉ | 10442/11728 [2:06:51<2:04:43, 5.82s/it] {'loss': 0.4389, 'learning_rate': 6.240265718085103e-07, 'epoch': 0.89} + 89%|████████▉ | 10442/11728 [2:06:51<2:04:43, 5.82s/it] 89%|████████▉ | 10443/11728 [2:06:57<2:05:07, 5.84s/it] {'loss': 0.4616, 'learning_rate': 6.230666588272993e-07, 'epoch': 0.89} + 89%|████████▉ | 10443/11728 [2:06:57<2:05:07, 5.84s/it] 89%|████████▉ | 10444/11728 [2:07:03<2:03:50, 5.79s/it] {'loss': 0.4284, 'learning_rate': 6.221074609701739e-07, 'epoch': 0.89} + 89%|████████▉ | 10444/11728 [2:07:03<2:03:50, 5.79s/it] 89%|████████▉ | 10445/11728 [2:07:09<2:04:16, 5.81s/it] {'loss': 0.4473, 'learning_rate': 6.211489783102831e-07, 'epoch': 0.89} + 89%|████████▉ | 10445/11728 [2:07:09<2:04:16, 5.81s/it] 89%|████████▉ | 10446/11728 [2:07:14<2:03:13, 5.77s/it] {'loss': 0.4545, 'learning_rate': 6.201912109207264e-07, 'epoch': 0.89} + 89%|████████▉ | 10446/11728 [2:07:14<2:03:13, 5.77s/it] 89%|████████▉ | 10447/11728 [2:07:20<2:03:36, 5.79s/it] {'loss': 0.4512, 'learning_rate': 6.192341588745498e-07, 'epoch': 0.89} + 89%|████████▉ | 10447/11728 [2:07:20<2:03:36, 5.79s/it] 89%|████████▉ | 10448/11728 [2:07:26<2:03:02, 5.77s/it] {'loss': 0.4591, 'learning_rate': 6.182778222447383e-07, 'epoch': 0.89} + 89%|████████▉ | 10448/11728 [2:07:26<2:03:02, 5.77s/it] 89%|████████▉ | 10449/11728 [2:07:32<2:02:59, 5.77s/it] {'loss': 0.439, 'learning_rate': 6.173222011042279e-07, 'epoch': 0.89} + 89%|████████▉ | 10449/11728 [2:07:32<2:02:59, 5.77s/it]3 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... +70 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... + 89%|████████▉ | 10450/11728 [2:07:37<2:02:18, 5.74s/it] {'loss': 0.4696, 'learning_rate': 6.163672955258982e-07, 'epoch': 0.89} + 89%|████████▉ | 10450/11728 [2:07:37<2:02:18, 5.74s/it] 89%|████████▉ | 10451/11728 [2:07:43<2:03:34, 5.81s/it] {'loss': 0.4419, 'learning_rate': 6.154131055825729e-07, 'epoch': 0.89} + 89%|████████▉ | 10451/11728 [2:07:43<2:03:34, 5.81s/it] 89%|████████▉ | 10452/11728 [2:07:49<2:04:38, 5.86s/it] {'loss': 0.4718, 'learning_rate': 6.144596313470241e-07, 'epoch': 0.89} + 89%|████████▉ | 10452/11728 [2:07:49<2:04:38, 5.86s/it] 89%|████████▉ | 10453/11728 [2:07:55<2:02:40, 5.77s/it] {'loss': 0.4579, 'learning_rate': 6.135068728919691e-07, 'epoch': 0.89} + 89%|████████▉ | 10453/11728 [2:07:55<2:02:40, 5.77s/it] 89%|████████▉ | 10454/11728 [2:08:00<2:01:39, 5.73s/it] {'loss': 0.4768, 'learning_rate': 6.125548302900653e-07, 'epoch': 0.89} + 89%|████████▉ | 10454/11728 [2:08:00<2:01:39, 5.73s/it] 89%|████████▉ | 10455/11728 [2:08:06<2:02:25, 5.77s/it] {'loss': 0.4537, 'learning_rate': 6.116035036139223e-07, 'epoch': 0.89} + 89%|████████▉ | 10455/11728 [2:08:06<2:02:25, 5.77s/it] 89%|████████▉ | 10456/11728 [2:08:12<2:02:53, 5.80s/it] {'loss': 0.4519, 'learning_rate': 6.106528929360911e-07, 'epoch': 0.89} + 89%|████████▉ | 10456/11728 [2:08:12<2:02:53, 5.80s/it] 89%|████████▉ | 10457/11728 [2:08:18<2:02:34, 5.79s/it] {'loss': 0.4568, 'learning_rate': 6.097029983290692e-07, 'epoch': 0.89} + 89%|████████▉ | 10457/11728 [2:08:18<2:02:34, 5.79s/it] 89%|████████▉ | 10458/11728 [2:08:24<2:04:24, 5.88s/it] {'loss': 0.4504, 'learning_rate': 6.087538198653009e-07, 'epoch': 0.89} + 89%|████████▉ | 10458/11728 [2:08:24<2:04:24, 5.88s/it] 89%|████████▉ | 10459/11728 [2:08:30<2:02:50, 5.81s/it] {'loss': 0.4474, 'learning_rate': 6.078053576171738e-07, 'epoch': 0.89} + 89%|████████▉ | 10459/11728 [2:08:30<2:02:50, 5.81s/it] 89%|████████▉ | 10460/11728 [2:08:36<2:02:48, 5.81s/it] {'loss': 0.4472, 'learning_rate': 6.06857611657019e-07, 'epoch': 0.89} + 89%|████████▉ | 10460/11728 [2:08:36<2:02:48, 5.81s/it] 89%|████████▉ | 10461/11728 [2:08:41<2:03:05, 5.83s/it] {'loss': 0.4566, 'learning_rate': 6.059105820571198e-07, 'epoch': 0.89} + 89%|████████▉ | 10461/11728 [2:08:41<2:03:05, 5.83s/it] 89%|████████▉ | 10462/11728 [2:08:47<2:03:28, 5.85s/it] {'loss': 0.4761, 'learning_rate': 6.049642688897007e-07, 'epoch': 0.89} + 89%|████████▉ | 10462/11728 [2:08:47<2:03:28, 5.85s/it] 89%|████████▉ | 10463/11728 [2:08:53<2:04:14, 5.89s/it] {'loss': 0.456, 'learning_rate': 6.04018672226927e-07, 'epoch': 0.89} + 89%|████████▉ | 10463/11728 [2:08:53<2:04:14, 5.89s/it] 89%|████████▉ | 10464/11728 [2:08:59<2:03:12, 5.85s/it] {'loss': 0.4552, 'learning_rate': 6.030737921409169e-07, 'epoch': 0.89} + 89%|████████▉ | 10464/11728 [2:08:59<2:03:12, 5.85s/it] 89%|████████▉ | 10465/11728 [2:09:05<2:03:54, 5.89s/it] {'loss': 0.466, 'learning_rate': 6.021296287037304e-07, 'epoch': 0.89} + 89%|████████▉ | 10465/11728 [2:09:05<2:03:54, 5.89s/it] 89%|████████▉ | 10466/11728 [2:09:11<2:04:00, 5.90s/it] {'loss': 0.4564, 'learning_rate': 6.011861819873732e-07, 'epoch': 0.89} + 89%|████████▉ | 10466/11728 [2:09:11<2:04:00, 5.90s/it] 89%|████████▉ | 10467/11728 [2:09:17<2:07:25, 6.06s/it] {'loss': 0.4571, 'learning_rate': 6.002434520637968e-07, 'epoch': 0.89} + 89%|████████▉ | 10467/11728 [2:09:17<2:07:25, 6.06s/it] 89%|████████▉ | 10468/11728 [2:09:23<2:05:20, 5.97s/it] {'loss': 0.4487, 'learning_rate': 5.99301439004899e-07, 'epoch': 0.89} + 89%|████████▉ | 10468/11728 [2:09:23<2:05:20, 5.97s/it] 89%|████████▉ | 10469/11728 [2:09:29<2:02:40, 5.85s/it] {'loss': 0.4603, 'learning_rate': 5.98360142882517e-07, 'epoch': 0.89} + 89%|████████▉ | 10469/11728 [2:09:29<2:02:40, 5.85s/it] 89%|████████▉ | 10470/11728 [2:09:35<2:03:48, 5.90s/it] {'loss': 0.4677, 'learning_rate': 5.974195637684422e-07, 'epoch': 0.89} + 89%|████████▉ | 10470/11728 [2:09:35<2:03:48, 5.90s/it] 89%|████████▉ | 10471/11728 [2:09:40<2:01:59, 5.82s/it] {'loss': 0.4658, 'learning_rate': 5.964797017344081e-07, 'epoch': 0.89} + 89%|████████▉ | 10471/11728 [2:09:40<2:01:59, 5.82s/it] 89%|████████▉ | 10472/11728 [2:09:46<2:01:01, 5.78s/it] {'loss': 0.4387, 'learning_rate': 5.955405568520889e-07, 'epoch': 0.89} + 89%|████████▉ | 10472/11728 [2:09:46<2:01:01, 5.78s/it] 89%|████████▉ | 10473/11728 [2:09:52<2:00:45, 5.77s/it] {'loss': 0.4626, 'learning_rate': 5.946021291931092e-07, 'epoch': 0.89} + 89%|████████▉ | 10473/11728 [2:09:52<2:00:45, 5.77s/it] 89%|████████▉ | 10474/11728 [2:09:58<2:00:47, 5.78s/it] {'loss': 0.4465, 'learning_rate': 5.936644188290386e-07, 'epoch': 0.89} + 89%|████████▉ | 10474/11728 [2:09:58<2:00:47, 5.78s/it] 89%|████████▉ | 10475/11728 [2:10:03<1:59:48, 5.74s/it] {'loss': 0.4414, 'learning_rate': 5.927274258313887e-07, 'epoch': 0.89} + 89%|████████▉ | 10475/11728 [2:10:03<1:59:48, 5.74s/it] 89%|████████▉ | 10476/11728 [2:10:09<2:00:50, 5.79s/it] {'loss': 0.4511, 'learning_rate': 5.91791150271619e-07, 'epoch': 0.89} + 89%|████████▉ | 10476/11728 [2:10:09<2:00:50, 5.79s/it] 89%|████████▉ | 10477/11728 [2:10:15<2:01:40, 5.84s/it] {'loss': 0.4489, 'learning_rate': 5.908555922211368e-07, 'epoch': 0.89} + 89%|████████▉ | 10477/11728 [2:10:15<2:01:40, 5.84s/it] 89%|████████▉ | 10478/11728 [2:10:21<2:00:40, 5.79s/it] {'loss': 0.4597, 'learning_rate': 5.899207517512873e-07, 'epoch': 0.89} + 89%|████████▉ | 10478/11728 [2:10:21<2:00:40, 5.79s/it] 89%|████████▉ | 10479/11728 [2:10:27<2:00:40, 5.80s/it] {'loss': 0.4619, 'learning_rate': 5.889866289333645e-07, 'epoch': 0.89} + 89%|████████▉ | 10479/11728 [2:10:27<2:00:40, 5.80s/it] 89%|████████▉ | 10480/11728 [2:10:32<2:00:40, 5.80s/it] {'loss': 0.4463, 'learning_rate': 5.880532238386161e-07, 'epoch': 0.89} + 89%|████████▉ | 10480/11728 [2:10:32<2:00:40, 5.80s/it] 89%|████████▉ | 10481/11728 [2:10:38<2:02:02, 5.87s/it] {'loss': 0.4548, 'learning_rate': 5.871205365382194e-07, 'epoch': 0.89} + 89%|████████▉ | 10481/11728 [2:10:38<2:02:02, 5.87s/it] 89%|████████▉ | 10482/11728 [2:10:44<2:00:56, 5.82s/it] {'loss': 0.4476, 'learning_rate': 5.861885671033097e-07, 'epoch': 0.89} + 89%|████████▉ | 10482/11728 [2:10:44<2:00:56, 5.82s/it] 89%|████████▉ | 10483/11728 [2:10:50<2:02:46, 5.92s/it] {'loss': 0.4371, 'learning_rate': 5.852573156049601e-07, 'epoch': 0.89} + 89%|████████▉ | 10483/11728 [2:10:50<2:02:46, 5.92s/it] 89%|████████▉ | 10484/11728 [2:10:56<2:02:19, 5.90s/it] {'loss': 0.4544, 'learning_rate': 5.84326782114194e-07, 'epoch': 0.89} + 89%|████████▉ | 10484/11728 [2:10:56<2:02:19, 5.90s/it] 89%|████████▉ | 10485/11728 [2:11:02<2:02:25, 5.91s/it] {'loss': 0.4552, 'learning_rate': 5.833969667019757e-07, 'epoch': 0.89} + 89%|████████▉ | 10485/11728 [2:11:02<2:02:25, 5.91s/it] 89%|████████▉ | 10486/11728 [2:11:08<2:00:50, 5.84s/it] {'loss': 0.435, 'learning_rate': 5.824678694392194e-07, 'epoch': 0.89} + 89%|████████▉ | 10486/11728 [2:11:08<2:00:50, 5.84s/it] 89%|████████▉ | 10487/11728 [2:11:13<1:59:24, 5.77s/it] {'loss': 0.4524, 'learning_rate': 5.815394903967797e-07, 'epoch': 0.89} + 89%|████████▉ | 10487/11728 [2:11:13<1:59:24, 5.77s/it] 89%|████████▉ | 10488/11728 [2:11:19<2:00:01, 5.81s/it] {'loss': 0.4517, 'learning_rate': 5.806118296454577e-07, 'epoch': 0.89} + 89%|████████▉ | 10488/11728 [2:11:19<2:00:01, 5.81s/it] 89%|████████▉ | 10489/11728 [2:11:25<1:58:21, 5.73s/it] {'loss': 0.4508, 'learning_rate': 5.796848872560045e-07, 'epoch': 0.89} + 89%|████████▉ | 10489/11728 [2:11:25<1:58:21, 5.73s/it] 89%|████████▉ | 10490/11728 [2:11:31<2:01:59, 5.91s/it] {'loss': 0.4388, 'learning_rate': 5.787586632991105e-07, 'epoch': 0.89} + 89%|████████▉ | 10490/11728 [2:11:31<2:01:59, 5.91s/it] 89%|████████▉ | 10491/11728 [2:11:37<2:00:38, 5.85s/it] {'loss': 0.4773, 'learning_rate': 5.778331578454121e-07, 'epoch': 0.89} + 89%|████████▉ | 10491/11728 [2:11:37<2:00:38, 5.85s/it] 89%|████████▉ | 10492/11728 [2:11:42<1:59:03, 5.78s/it] {'loss': 0.4475, 'learning_rate': 5.769083709654933e-07, 'epoch': 0.89} + 89%|████████▉ | 10492/11728 [2:11:42<1:59:03, 5.78s/it] 89%|████████▉ | 10493/11728 [2:11:48<2:00:16, 5.84s/it] {'loss': 0.4611, 'learning_rate': 5.759843027298828e-07, 'epoch': 0.89} + 89%|████████▉ | 10493/11728 [2:11:48<2:00:16, 5.84s/it] 89%|████████▉ | 10494/11728 [2:11:54<1:58:21, 5.75s/it] {'loss': 0.4577, 'learning_rate': 5.750609532090534e-07, 'epoch': 0.89} + 89%|████████▉ | 10494/11728 [2:11:54<1:58:21, 5.75s/it] 89%|████████▉ | 10495/11728 [2:12:00<2:00:05, 5.84s/it] {'loss': 0.4496, 'learning_rate': 5.741383224734254e-07, 'epoch': 0.89} + 89%|████████▉ | 10495/11728 [2:12:00<2:00:05, 5.84s/it] 89%|████████▉ | 10496/11728 [2:12:06<1:58:41, 5.78s/it] {'loss': 0.4445, 'learning_rate': 5.732164105933591e-07, 'epoch': 0.89} + 89%|████████▉ | 10496/11728 [2:12:06<1:58:41, 5.78s/it] 90%|████████▉ | 10497/11728 [2:12:11<1:57:48, 5.74s/it] {'loss': 0.4429, 'learning_rate': 5.722952176391639e-07, 'epoch': 0.9} + 90%|████████▉ | 10497/11728 [2:12:11<1:57:48, 5.74s/it] 90%|████████▉ | 10498/11728 [2:12:17<2:00:09, 5.86s/it] {'loss': 0.4609, 'learning_rate': 5.713747436810968e-07, 'epoch': 0.9} + 90%|████████▉ | 10498/11728 [2:12:17<2:00:09, 5.86s/it] 90%|████████▉ | 10499/11728 [2:12:24<2:02:15, 5.97s/it] {'loss': 0.4463, 'learning_rate': 5.70454988789354e-07, 'epoch': 0.9} + 90%|████████▉ | 10499/11728 [2:12:24<2:02:15, 5.97s/it]3 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... +04 AutoResumeHook: Checking whether to suspend... +AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... + 90%|████████▉ | 10500/11728 [2:12:30<2:02:16, 5.97s/it]1 AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4858, 'learning_rate': 5.695359530340816e-07, 'epoch': 0.9} + 90%|████████▉ | 10500/11728 [2:12:30<2:02:16, 5.97s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-10500/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-10500/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-10500/mm_projector +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/torch/nn/modules/module.py:1802: UserWarning: Positional args are being deprecated, use kwargs instead. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details. + warnings.warn( + 90%|████████▉ | 10501/11728 [2:13:04<4:56:50, 14.52s/it] {'loss': 0.468, 'learning_rate': 5.68617636485368e-07, 'epoch': 0.9} + 90%|████████▉ | 10501/11728 [2:13:04<4:56:50, 14.52s/it] 90%|████████▉ | 10502/11728 [2:13:10<4:01:48, 11.83s/it] {'loss': 0.4637, 'learning_rate': 5.677000392132481e-07, 'epoch': 0.9} + 90%|████████▉ | 10502/11728 [2:13:10<4:01:48, 11.83s/it] 90%|████████▉ | 10503/11728 [2:13:15<3:24:05, 10.00s/it] {'loss': 0.4538, 'learning_rate': 5.667831612877018e-07, 'epoch': 0.9} + 90%|████████▉ | 10503/11728 [2:13:15<3:24:05, 10.00s/it] 90%|████████▉ | 10504/11728 [2:13:21<2:57:24, 8.70s/it] {'loss': 0.4407, 'learning_rate': 5.658670027786561e-07, 'epoch': 0.9} + 90%|████████▉ | 10504/11728 [2:13:21<2:57:24, 8.70s/it] 90%|████████▉ | 10505/11728 [2:13:27<2:41:33, 7.93s/it] {'loss': 0.467, 'learning_rate': 5.649515637559766e-07, 'epoch': 0.9} + 90%|████████▉ | 10505/11728 [2:13:27<2:41:33, 7.93s/it] 90%|████████▉ | 10506/11728 [2:13:33<2:29:25, 7.34s/it] {'loss': 0.4507, 'learning_rate': 5.640368442894806e-07, 'epoch': 0.9} + 90%|████████▉ | 10506/11728 [2:13:33<2:29:25, 7.34s/it] 90%|████████▉ | 10507/11728 [2:13:39<2:21:51, 6.97s/it] {'loss': 0.4645, 'learning_rate': 5.631228444489312e-07, 'epoch': 0.9} + 90%|████████▉ | 10507/11728 [2:13:39<2:21:51, 6.97s/it] 90%|████████▉ | 10508/11728 [2:13:45<2:13:06, 6.55s/it] {'loss': 0.4494, 'learning_rate': 5.622095643040304e-07, 'epoch': 0.9} + 90%|████████▉ | 10508/11728 [2:13:45<2:13:06, 6.55s/it] 90%|████████▉ | 10509/11728 [2:13:51<2:08:30, 6.33s/it] {'loss': 0.4516, 'learning_rate': 5.612970039244292e-07, 'epoch': 0.9} + 90%|████████▉ | 10509/11728 [2:13:51<2:08:30, 6.33s/it] 90%|████████▉ | 10510/11728 [2:13:56<2:05:15, 6.17s/it] {'loss': 0.4709, 'learning_rate': 5.603851633797242e-07, 'epoch': 0.9} + 90%|████████▉ | 10510/11728 [2:13:56<2:05:15, 6.17s/it] 90%|████████▉ | 10511/11728 [2:14:02<2:03:53, 6.11s/it] {'loss': 0.4396, 'learning_rate': 5.594740427394562e-07, 'epoch': 0.9} + 90%|████████▉ | 10511/11728 [2:14:02<2:03:53, 6.11s/it] 90%|████████▉ | 10512/11728 [2:14:08<2:01:44, 6.01s/it] {'loss': 0.4814, 'learning_rate': 5.5856364207311e-07, 'epoch': 0.9} + 90%|████████▉ | 10512/11728 [2:14:08<2:01:44, 6.01s/it] 90%|████████▉ | 10513/11728 [2:14:14<2:01:12, 5.99s/it] {'loss': 0.4567, 'learning_rate': 5.576539614501197e-07, 'epoch': 0.9} + 90%|████████▉ | 10513/11728 [2:14:14<2:01:12, 5.99s/it] 90%|████████▉ | 10514/11728 [2:14:20<2:00:03, 5.93s/it] {'loss': 0.4524, 'learning_rate': 5.567450009398567e-07, 'epoch': 0.9} + 90%|████████▉ | 10514/11728 [2:14:20<2:00:03, 5.93s/it] 90%|████████▉ | 10515/11728 [2:14:26<1:58:03, 5.84s/it] {'loss': 0.4323, 'learning_rate': 5.558367606116433e-07, 'epoch': 0.9} + 90%|████████▉ | 10515/11728 [2:14:26<1:58:03, 5.84s/it] 90%|████████▉ | 10516/11728 [2:14:32<1:59:08, 5.90s/it] {'loss': 0.4515, 'learning_rate': 5.549292405347495e-07, 'epoch': 0.9} + 90%|████████▉ | 10516/11728 [2:14:32<1:59:08, 5.90s/it] 90%|████████▉ | 10517/11728 [2:14:38<1:59:19, 5.91s/it] {'loss': 0.4616, 'learning_rate': 5.540224407783823e-07, 'epoch': 0.9} + 90%|████████▉ | 10517/11728 [2:14:38<1:59:19, 5.91s/it] 90%|████████▉ | 10518/11728 [2:14:43<1:59:19, 5.92s/it] {'loss': 0.4447, 'learning_rate': 5.531163614116986e-07, 'epoch': 0.9} + 90%|████████▉ | 10518/11728 [2:14:43<1:59:19, 5.92s/it] 90%|████████▉ | 10519/11728 [2:14:49<1:58:35, 5.89s/it] {'loss': 0.4713, 'learning_rate': 5.522110025038019e-07, 'epoch': 0.9} + 90%|████████▉ | 10519/11728 [2:14:49<1:58:35, 5.89s/it] 90%|████████▉ | 10520/11728 [2:14:55<1:58:21, 5.88s/it] {'loss': 0.4669, 'learning_rate': 5.51306364123737e-07, 'epoch': 0.9} + 90%|████████▉ | 10520/11728 [2:14:55<1:58:21, 5.88s/it] 90%|████████▉ | 10521/11728 [2:15:01<1:55:54, 5.76s/it] {'loss': 0.4422, 'learning_rate': 5.504024463404967e-07, 'epoch': 0.9} + 90%|████████▉ | 10521/11728 [2:15:01<1:55:54, 5.76s/it] 90%|████████▉ | 10522/11728 [2:15:07<1:57:08, 5.83s/it] {'loss': 0.4644, 'learning_rate': 5.494992492230167e-07, 'epoch': 0.9} + 90%|████████▉ | 10522/11728 [2:15:07<1:57:08, 5.83s/it] 90%|████████▉ | 10523/11728 [2:15:12<1:56:43, 5.81s/it] {'loss': 0.4608, 'learning_rate': 5.485967728401786e-07, 'epoch': 0.9} + 90%|████████▉ | 10523/11728 [2:15:12<1:56:43, 5.81s/it] 90%|████████▉ | 10524/11728 [2:15:18<1:54:39, 5.71s/it] {'loss': 0.4437, 'learning_rate': 5.476950172608064e-07, 'epoch': 0.9} + 90%|████████▉ | 10524/11728 [2:15:18<1:54:39, 5.71s/it] 90%|████████▉ | 10525/11728 [2:15:24<1:55:15, 5.75s/it] {'loss': 0.4377, 'learning_rate': 5.467939825536783e-07, 'epoch': 0.9} + 90%|████████▉ | 10525/11728 [2:15:24<1:55:15, 5.75s/it] 90%|████████▉ | 10526/11728 [2:15:30<1:56:58, 5.84s/it] {'loss': 0.4637, 'learning_rate': 5.458936687875049e-07, 'epoch': 0.9} + 90%|████████▉ | 10526/11728 [2:15:30<1:56:58, 5.84s/it] 90%|████████▉ | 10527/11728 [2:15:36<1:57:29, 5.87s/it] {'loss': 0.4928, 'learning_rate': 5.449940760309502e-07, 'epoch': 0.9} + 90%|████████▉ | 10527/11728 [2:15:36<1:57:29, 5.87s/it] 90%|████████▉ | 10528/11728 [2:15:42<1:57:38, 5.88s/it] {'loss': 0.4462, 'learning_rate': 5.440952043526215e-07, 'epoch': 0.9} + 90%|████████▉ | 10528/11728 [2:15:42<1:57:38, 5.88s/it] 90%|████████▉ | 10529/11728 [2:15:48<1:57:50, 5.90s/it] {'loss': 0.4474, 'learning_rate': 5.431970538210685e-07, 'epoch': 0.9} + 90%|████████▉ | 10529/11728 [2:15:48<1:57:50, 5.90s/it] 90%|████████▉ | 10530/11728 [2:15:53<1:56:47, 5.85s/it] {'loss': 0.4696, 'learning_rate': 5.422996245047896e-07, 'epoch': 0.9} + 90%|████████▉ | 10530/11728 [2:15:53<1:56:47, 5.85s/it] 90%|████████▉ | 10531/11728 [2:15:59<1:56:39, 5.85s/it] {'loss': 0.4761, 'learning_rate': 5.414029164722279e-07, 'epoch': 0.9} + 90%|████████▉ | 10531/11728 [2:15:59<1:56:39, 5.85s/it] 90%|████████▉ | 10532/11728 [2:16:05<1:56:06, 5.82s/it] {'loss': 0.4319, 'learning_rate': 5.405069297917665e-07, 'epoch': 0.9} + 90%|████████▉ | 10532/11728 [2:16:05<1:56:06, 5.82s/it] 90%|████████▉ | 10533/11728 [2:16:11<1:54:44, 5.76s/it] {'loss': 0.4523, 'learning_rate': 5.396116645317384e-07, 'epoch': 0.9} + 90%|████████▉ | 10533/11728 [2:16:11<1:54:44, 5.76s/it] 90%|████████▉ | 10534/11728 [2:16:16<1:54:04, 5.73s/it] {'loss': 0.4515, 'learning_rate': 5.387171207604214e-07, 'epoch': 0.9} + 90%|████████▉ | 10534/11728 [2:16:16<1:54:04, 5.73s/it] 90%|████████▉ | 10535/11728 [2:16:22<1:54:45, 5.77s/it] {'loss': 0.4462, 'learning_rate': 5.378232985460363e-07, 'epoch': 0.9} + 90%|████████▉ | 10535/11728 [2:16:22<1:54:45, 5.77s/it] 90%|████████▉ | 10536/11728 [2:16:28<1:54:05, 5.74s/it] {'loss': 0.4707, 'learning_rate': 5.369301979567498e-07, 'epoch': 0.9} + 90%|████████▉ | 10536/11728 [2:16:28<1:54:05, 5.74s/it] 90%|████████▉ | 10537/11728 [2:16:34<1:55:07, 5.80s/it] {'loss': 0.4835, 'learning_rate': 5.36037819060673e-07, 'epoch': 0.9} + 90%|████████▉ | 10537/11728 [2:16:34<1:55:07, 5.80s/it] 90%|████████▉ | 10538/11728 [2:16:39<1:53:03, 5.70s/it] {'loss': 0.4314, 'learning_rate': 5.351461619258636e-07, 'epoch': 0.9} + 90%|████████▉ | 10538/11728 [2:16:39<1:53:03, 5.70s/it] 90%|████████▉ | 10539/11728 [2:16:45<1:52:07, 5.66s/it] {'loss': 0.4716, 'learning_rate': 5.342552266203227e-07, 'epoch': 0.9} + 90%|████████▉ | 10539/11728 [2:16:45<1:52:07, 5.66s/it] 90%|████████▉ | 10540/11728 [2:16:50<1:52:19, 5.67s/it] {'loss': 0.4538, 'learning_rate': 5.333650132119972e-07, 'epoch': 0.9} + 90%|████████▉ | 10540/11728 [2:16:50<1:52:19, 5.67s/it] 90%|████████▉ | 10541/11728 [2:16:56<1:54:07, 5.77s/it] {'loss': 0.4565, 'learning_rate': 5.32475521768776e-07, 'epoch': 0.9} + 90%|████████▉ | 10541/11728 [2:16:56<1:54:07, 5.77s/it] 90%|████████▉ | 10542/11728 [2:17:02<1:55:36, 5.85s/it] {'loss': 0.4698, 'learning_rate': 5.315867523584984e-07, 'epoch': 0.9} + 90%|████████▉ | 10542/11728 [2:17:02<1:55:36, 5.85s/it] 90%|████████▉ | 10543/11728 [2:17:08<1:55:38, 5.85s/it] {'loss': 0.4589, 'learning_rate': 5.306987050489442e-07, 'epoch': 0.9} + 90%|████████▉ | 10543/11728 [2:17:08<1:55:38, 5.85s/it] 90%|████████▉ | 10544/11728 [2:17:14<1:56:18, 5.89s/it] {'loss': 0.4593, 'learning_rate': 5.298113799078397e-07, 'epoch': 0.9} + 90%|████████▉ | 10544/11728 [2:17:14<1:56:18, 5.89s/it] 90%|████████▉ | 10545/11728 [2:17:20<1:54:55, 5.83s/it] {'loss': 0.446, 'learning_rate': 5.28924777002856e-07, 'epoch': 0.9} + 90%|████████▉ | 10545/11728 [2:17:20<1:54:55, 5.83s/it] 90%|████████▉ | 10546/11728 [2:17:25<1:53:12, 5.75s/it] {'loss': 0.462, 'learning_rate': 5.280388964016093e-07, 'epoch': 0.9} + 90%|████████▉ | 10546/11728 [2:17:25<1:53:12, 5.75s/it] 90%|████████▉ | 10547/11728 [2:17:32<1:54:52, 5.84s/it] {'loss': 0.4715, 'learning_rate': 5.271537381716607e-07, 'epoch': 0.9} + 90%|████████▉ | 10547/11728 [2:17:32<1:54:52, 5.84s/it] 90%|████████▉ | 10548/11728 [2:17:37<1:53:41, 5.78s/it] {'loss': 0.4589, 'learning_rate': 5.262693023805165e-07, 'epoch': 0.9} + 90%|████████▉ | 10548/11728 [2:17:37<1:53:41, 5.78s/it] 90%|████████▉ | 10549/11728 [2:17:43<1:52:36, 5.73s/it] {'loss': 0.4726, 'learning_rate': 5.253855890956272e-07, 'epoch': 0.9} + 90%|████████▉ | 10549/11728 [2:17:43<1:52:36, 5.73s/it]3 AutoResumeHook: Checking whether to suspend... +06 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... + 90%|████████▉ | 10550/11728 [2:17:49<1:54:59, 5.86s/it]5 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4489, 'learning_rate': 5.245025983843888e-07, 'epoch': 0.9} + 90%|████████▉ | 10550/11728 [2:17:49<1:54:59, 5.86s/it] 90%|████████▉ | 10551/11728 [2:17:55<1:55:19, 5.88s/it] {'loss': 0.4665, 'learning_rate': 5.236203303141396e-07, 'epoch': 0.9} + 90%|████████▉ | 10551/11728 [2:17:55<1:55:19, 5.88s/it] 90%|████████▉ | 10552/11728 [2:18:01<1:54:55, 5.86s/it] {'loss': 0.4429, 'learning_rate': 5.22738784952167e-07, 'epoch': 0.9} + 90%|████████▉ | 10552/11728 [2:18:01<1:54:55, 5.86s/it] 90%|████████▉ | 10553/11728 [2:18:07<1:56:05, 5.93s/it] {'loss': 0.4751, 'learning_rate': 5.218579623657016e-07, 'epoch': 0.9} + 90%|████████▉ | 10553/11728 [2:18:07<1:56:05, 5.93s/it] 90%|████████▉ | 10554/11728 [2:18:13<1:55:42, 5.91s/it] {'loss': 0.4545, 'learning_rate': 5.209778626219176e-07, 'epoch': 0.9} + 90%|████████▉ | 10554/11728 [2:18:13<1:55:42, 5.91s/it] 90%|████████▉ | 10555/11728 [2:18:18<1:53:28, 5.80s/it] {'loss': 0.4494, 'learning_rate': 5.200984857879355e-07, 'epoch': 0.9} + 90%|████████▉ | 10555/11728 [2:18:18<1:53:28, 5.80s/it] 90%|█████████ | 10556/11728 [2:18:24<1:54:16, 5.85s/it] {'loss': 0.4377, 'learning_rate': 5.192198319308206e-07, 'epoch': 0.9} + 90%|█████████ | 10556/11728 [2:18:24<1:54:16, 5.85s/it] 90%|█████████ | 10557/11728 [2:18:30<1:52:38, 5.77s/it] {'loss': 0.4402, 'learning_rate': 5.183419011175817e-07, 'epoch': 0.9} + 90%|█████████ | 10557/11728 [2:18:30<1:52:38, 5.77s/it] 90%|█████████ | 10558/11728 [2:18:36<1:53:04, 5.80s/it] {'loss': 0.4455, 'learning_rate': 5.174646934151751e-07, 'epoch': 0.9} + 90%|█████████ | 10558/11728 [2:18:36<1:53:04, 5.80s/it] 90%|█████████ | 10559/11728 [2:18:41<1:53:10, 5.81s/it] {'loss': 0.4509, 'learning_rate': 5.165882088905005e-07, 'epoch': 0.9} + 90%|█████████ | 10559/11728 [2:18:41<1:53:10, 5.81s/it] 90%|█████████ | 10560/11728 [2:18:47<1:51:31, 5.73s/it] {'loss': 0.4483, 'learning_rate': 5.157124476103992e-07, 'epoch': 0.9} + 90%|█████████ | 10560/11728 [2:18:47<1:51:31, 5.73s/it] 90%|█████████ | 10561/11728 [2:18:53<1:53:37, 5.84s/it] {'loss': 0.4432, 'learning_rate': 5.14837409641663e-07, 'epoch': 0.9} + 90%|█████████ | 10561/11728 [2:18:53<1:53:37, 5.84s/it] 90%|█████████ | 10562/11728 [2:18:59<1:54:44, 5.90s/it] {'loss': 0.453, 'learning_rate': 5.139630950510243e-07, 'epoch': 0.9} + 90%|█████████ | 10562/11728 [2:18:59<1:54:44, 5.90s/it] 90%|█████████ | 10563/11728 [2:19:05<1:53:27, 5.84s/it] {'loss': 0.4524, 'learning_rate': 5.130895039051642e-07, 'epoch': 0.9} + 90%|█████████ | 10563/11728 [2:19:05<1:53:27, 5.84s/it] 90%|█████████ | 10564/11728 [2:19:11<1:54:38, 5.91s/it] {'loss': 0.4533, 'learning_rate': 5.122166362707048e-07, 'epoch': 0.9} + 90%|█████████ | 10564/11728 [2:19:11<1:54:38, 5.91s/it] 90%|█████████ | 10565/11728 [2:19:17<1:52:57, 5.83s/it] {'loss': 0.4558, 'learning_rate': 5.113444922142163e-07, 'epoch': 0.9} + 90%|█████████ | 10565/11728 [2:19:17<1:52:57, 5.83s/it] 90%|█████████ | 10566/11728 [2:19:23<1:54:10, 5.90s/it] {'loss': 0.4676, 'learning_rate': 5.104730718022077e-07, 'epoch': 0.9} + 90%|█████████ | 10566/11728 [2:19:23<1:54:10, 5.90s/it] 90%|█████████ | 10567/11728 [2:19:29<1:54:20, 5.91s/it] {'loss': 0.4567, 'learning_rate': 5.096023751011414e-07, 'epoch': 0.9} + 90%|█████████ | 10567/11728 [2:19:29<1:54:20, 5.91s/it] 90%|█████████ | 10568/11728 [2:19:35<1:54:41, 5.93s/it] {'loss': 0.4788, 'learning_rate': 5.087324021774209e-07, 'epoch': 0.9} + 90%|█████████ | 10568/11728 [2:19:35<1:54:41, 5.93s/it] 90%|█████████ | 10569/11728 [2:19:40<1:53:08, 5.86s/it] {'loss': 0.4502, 'learning_rate': 5.078631530973921e-07, 'epoch': 0.9} + 90%|█████████ | 10569/11728 [2:19:40<1:53:08, 5.86s/it] 90%|█████████ | 10570/11728 [2:19:46<1:52:02, 5.81s/it] {'loss': 0.4363, 'learning_rate': 5.069946279273464e-07, 'epoch': 0.9} + 90%|█████████ | 10570/11728 [2:19:46<1:52:02, 5.81s/it] 90%|█████████ | 10571/11728 [2:19:52<1:53:25, 5.88s/it] {'loss': 0.4472, 'learning_rate': 5.061268267335228e-07, 'epoch': 0.9} + 90%|█████████ | 10571/11728 [2:19:52<1:53:25, 5.88s/it] 90%|█████████ | 10572/11728 [2:19:58<1:52:01, 5.81s/it] {'loss': 0.463, 'learning_rate': 5.052597495821032e-07, 'epoch': 0.9} + 90%|█████████ | 10572/11728 [2:19:58<1:52:01, 5.81s/it] 90%|█████████ | 10573/11728 [2:20:04<1:52:35, 5.85s/it] {'loss': 0.4596, 'learning_rate': 5.043933965392134e-07, 'epoch': 0.9} + 90%|█████████ | 10573/11728 [2:20:04<1:52:35, 5.85s/it] 90%|█████████ | 10574/11728 [2:20:09<1:52:14, 5.84s/it] {'loss': 0.4552, 'learning_rate': 5.035277676709294e-07, 'epoch': 0.9} + 90%|█████████ | 10574/11728 [2:20:09<1:52:14, 5.84s/it] 90%|█████████ | 10575/11728 [2:20:15<1:53:16, 5.89s/it] {'loss': 0.4732, 'learning_rate': 5.026628630432607e-07, 'epoch': 0.9} + 90%|█████████ | 10575/11728 [2:20:15<1:53:16, 5.89s/it] 90%|█████████ | 10576/11728 [2:20:21<1:54:09, 5.95s/it] {'loss': 0.493, 'learning_rate': 5.017986827221733e-07, 'epoch': 0.9} + 90%|█████████ | 10576/11728 [2:20:21<1:54:09, 5.95s/it] 90%|█████████ | 10577/11728 [2:20:27<1:53:26, 5.91s/it] {'loss': 0.4377, 'learning_rate': 5.009352267735734e-07, 'epoch': 0.9} + 90%|█████████ | 10577/11728 [2:20:27<1:53:26, 5.91s/it] 90%|█████████ | 10578/11728 [2:20:33<1:52:36, 5.88s/it] {'loss': 0.4587, 'learning_rate': 5.000724952633096e-07, 'epoch': 0.9} + 90%|█████████ | 10578/11728 [2:20:33<1:52:36, 5.88s/it] 90%|█████████ | 10579/11728 [2:20:39<1:51:40, 5.83s/it] {'loss': 0.4616, 'learning_rate': 4.99210488257178e-07, 'epoch': 0.9} + 90%|█████████ | 10579/11728 [2:20:39<1:51:40, 5.83s/it] 90%|█████████ | 10580/11728 [2:20:45<1:52:45, 5.89s/it] {'loss': 0.4479, 'learning_rate': 4.983492058209194e-07, 'epoch': 0.9} + 90%|█████████ | 10580/11728 [2:20:45<1:52:45, 5.89s/it] 90%|█████████ | 10581/11728 [2:20:51<1:51:23, 5.83s/it] {'loss': 0.4772, 'learning_rate': 4.97488648020219e-07, 'epoch': 0.9} + 90%|█████████ | 10581/11728 [2:20:51<1:51:23, 5.83s/it] 90%|█████████ | 10582/11728 [2:20:57<1:52:09, 5.87s/it] {'loss': 0.4649, 'learning_rate': 4.966288149207055e-07, 'epoch': 0.9} + 90%|█████████ | 10582/11728 [2:20:57<1:52:09, 5.87s/it] 90%|█████████ | 10583/11728 [2:21:02<1:51:36, 5.85s/it] {'loss': 0.4436, 'learning_rate': 4.957697065879563e-07, 'epoch': 0.9} + 90%|█████████ | 10583/11728 [2:21:02<1:51:36, 5.85s/it] 90%|█████████ | 10584/11728 [2:21:08<1:51:35, 5.85s/it] {'loss': 0.4639, 'learning_rate': 4.949113230874846e-07, 'epoch': 0.9} + 90%|█████████ | 10584/11728 [2:21:08<1:51:35, 5.85s/it] 90%|█████████ | 10585/11728 [2:21:14<1:49:52, 5.77s/it] {'loss': 0.4348, 'learning_rate': 4.940536644847593e-07, 'epoch': 0.9} + 90%|█████████ | 10585/11728 [2:21:14<1:49:52, 5.77s/it] 90%|█████████ | 10586/11728 [2:21:19<1:49:36, 5.76s/it] {'loss': 0.4544, 'learning_rate': 4.931967308451891e-07, 'epoch': 0.9} + 90%|█████████ | 10586/11728 [2:21:19<1:49:36, 5.76s/it] 90%|█████████ | 10587/11728 [2:21:25<1:50:38, 5.82s/it] {'loss': 0.4567, 'learning_rate': 4.923405222341248e-07, 'epoch': 0.9} + 90%|█████████ | 10587/11728 [2:21:25<1:50:38, 5.82s/it] 90%|█████████ | 10588/11728 [2:21:31<1:51:00, 5.84s/it] {'loss': 0.4472, 'learning_rate': 4.914850387168657e-07, 'epoch': 0.9} + 90%|█████████ | 10588/11728 [2:21:31<1:51:00, 5.84s/it] 90%|█████████ | 10589/11728 [2:21:37<1:51:43, 5.89s/it] {'loss': 0.4429, 'learning_rate': 4.906302803586538e-07, 'epoch': 0.9} + 90%|█████████ | 10589/11728 [2:21:37<1:51:43, 5.89s/it] 90%|█████████ | 10590/11728 [2:21:43<1:50:29, 5.83s/it] {'loss': 0.4335, 'learning_rate': 4.897762472246781e-07, 'epoch': 0.9} + 90%|█████████ | 10590/11728 [2:21:43<1:50:29, 5.83s/it] 90%|█████████ | 10591/11728 [2:21:49<1:52:43, 5.95s/it] {'loss': 0.4474, 'learning_rate': 4.889229393800687e-07, 'epoch': 0.9} + 90%|█████████ | 10591/11728 [2:21:49<1:52:43, 5.95s/it] 90%|█████████ | 10592/11728 [2:21:55<1:51:54, 5.91s/it] {'loss': 0.473, 'learning_rate': 4.880703568899047e-07, 'epoch': 0.9} + 90%|█████████ | 10592/11728 [2:21:55<1:51:54, 5.91s/it] 90%|█████████ | 10593/11728 [2:22:01<1:51:44, 5.91s/it] {'loss': 0.4456, 'learning_rate': 4.872184998192053e-07, 'epoch': 0.9} + 90%|█████████ | 10593/11728 [2:22:01<1:51:44, 5.91s/it] 90%|█████████ | 10594/11728 [2:22:07<1:50:48, 5.86s/it] {'loss': 0.4505, 'learning_rate': 4.863673682329373e-07, 'epoch': 0.9} + 90%|█████████ | 10594/11728 [2:22:07<1:50:48, 5.86s/it] 90%|█████████ | 10595/11728 [2:22:12<1:49:15, 5.79s/it] {'loss': 0.4486, 'learning_rate': 4.855169621960143e-07, 'epoch': 0.9} + 90%|█████████ | 10595/11728 [2:22:12<1:49:15, 5.79s/it] 90%|█████████ | 10596/11728 [2:22:18<1:50:20, 5.85s/it] {'loss': 0.4655, 'learning_rate': 4.846672817732889e-07, 'epoch': 0.9} + 90%|█████████ | 10596/11728 [2:22:18<1:50:20, 5.85s/it] 90%|█████████ | 10597/11728 [2:22:24<1:50:07, 5.84s/it] {'loss': 0.4487, 'learning_rate': 4.838183270295604e-07, 'epoch': 0.9} + 90%|█████████ | 10597/11728 [2:22:24<1:50:07, 5.84s/it] 90%|█████████ | 10598/11728 [2:22:30<1:48:26, 5.76s/it] {'loss': 0.4375, 'learning_rate': 4.82970098029576e-07, 'epoch': 0.9} + 90%|█████████ | 10598/11728 [2:22:30<1:48:26, 5.76s/it] 90%|█████████ | 10599/11728 [2:22:35<1:46:40, 5.67s/it] {'loss': 0.4485, 'learning_rate': 4.821225948380237e-07, 'epoch': 0.9} + 90%|█████████ | 10599/11728 [2:22:35<1:46:40, 5.67s/it]1 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... +05 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... + 90%|█████████ | 10600/11728 [2:22:41<1:47:36, 5.72s/it]6 AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4247, 'learning_rate': 4.812758175195397e-07, 'epoch': 0.9} + 90%|█████████ | 10600/11728 [2:22:41<1:47:36, 5.72s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-10600/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-10600/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-10600/mm_projector +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/torch/nn/modules/module.py:1802: UserWarning: Positional args are being deprecated, use kwargs instead. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details. + warnings.warn( + 90%|█████████ | 10601/11728 [2:23:15<4:28:25, 14.29s/it] {'loss': 0.4539, 'learning_rate': 4.804297661387014e-07, 'epoch': 0.9} + 90%|█████████ | 10601/11728 [2:23:15<4:28:25, 14.29s/it] 90%|█████████ | 10602/11728 [2:23:21<3:37:52, 11.61s/it] {'loss': 0.4486, 'learning_rate': 4.795844407600292e-07, 'epoch': 0.9} + 90%|█████████ | 10602/11728 [2:23:21<3:37:52, 11.61s/it] 90%|█████████ | 10603/11728 [2:23:27<3:05:51, 9.91s/it] {'loss': 0.4438, 'learning_rate': 4.78739841447996e-07, 'epoch': 0.9} + 90%|█████████ | 10603/11728 [2:23:27<3:05:51, 9.91s/it] 90%|█████████ | 10604/11728 [2:23:33<2:45:42, 8.85s/it] {'loss': 0.4709, 'learning_rate': 4.778959682670147e-07, 'epoch': 0.9} + 90%|█████████ | 10604/11728 [2:23:33<2:45:42, 8.85s/it] 90%|█████████ | 10605/11728 [2:23:39<2:27:22, 7.87s/it] {'loss': 0.4342, 'learning_rate': 4.770528212814385e-07, 'epoch': 0.9} + 90%|█████████ | 10605/11728 [2:23:39<2:27:22, 7.87s/it] 90%|█████████ | 10606/11728 [2:23:44<2:14:17, 7.18s/it] {'loss': 0.4571, 'learning_rate': 4.762104005555701e-07, 'epoch': 0.9} + 90%|█████████ | 10606/11728 [2:23:44<2:14:17, 7.18s/it] 90%|█████████ | 10607/11728 [2:23:50<2:06:52, 6.79s/it] {'loss': 0.4553, 'learning_rate': 4.7536870615365825e-07, 'epoch': 0.9} + 90%|█████████ | 10607/11728 [2:23:50<2:06:52, 6.79s/it] 90%|█████████ | 10608/11728 [2:23:56<2:00:58, 6.48s/it] {'loss': 0.4431, 'learning_rate': 4.7452773813989385e-07, 'epoch': 0.9} + 90%|█████████ | 10608/11728 [2:23:56<2:00:58, 6.48s/it] 90%|█████████ | 10609/11728 [2:24:02<1:58:04, 6.33s/it] {'loss': 0.4532, 'learning_rate': 4.7368749657840997e-07, 'epoch': 0.9} + 90%|█████████ | 10609/11728 [2:24:02<1:58:04, 6.33s/it] 90%|█████████ | 10610/11728 [2:24:08<1:56:55, 6.28s/it] {'loss': 0.431, 'learning_rate': 4.728479815332909e-07, 'epoch': 0.9} + 90%|█████████ | 10610/11728 [2:24:08<1:56:55, 6.28s/it] 90%|█████████ | 10611/11728 [2:24:14<1:53:18, 6.09s/it] {'loss': 0.4619, 'learning_rate': 4.7200919306855883e-07, 'epoch': 0.9} + 90%|█████████ | 10611/11728 [2:24:14<1:53:18, 6.09s/it] 90%|█████████ | 10612/11728 [2:24:19<1:51:39, 6.00s/it] {'loss': 0.4673, 'learning_rate': 4.711711312481815e-07, 'epoch': 0.9} + 90%|█████████ | 10612/11728 [2:24:19<1:51:39, 6.00s/it] 90%|█████████ | 10613/11728 [2:24:25<1:51:34, 6.00s/it] {'loss': 0.4507, 'learning_rate': 4.7033379613607876e-07, 'epoch': 0.9} + 90%|█████████ | 10613/11728 [2:24:25<1:51:34, 6.00s/it] 91%|█████████ | 10614/11728 [2:24:31<1:51:04, 5.98s/it] {'loss': 0.4574, 'learning_rate': 4.694971877961041e-07, 'epoch': 0.91} + 91%|█████████ | 10614/11728 [2:24:31<1:51:04, 5.98s/it] 91%|█████████ | 10615/11728 [2:24:37<1:49:27, 5.90s/it] {'loss': 0.4703, 'learning_rate': 4.68661306292062e-07, 'epoch': 0.91} + 91%|█████████ | 10615/11728 [2:24:37<1:49:27, 5.90s/it] 91%|█████████ | 10616/11728 [2:24:43<1:51:31, 6.02s/it] {'loss': 0.4597, 'learning_rate': 4.678261516877014e-07, 'epoch': 0.91} + 91%|█████████ | 10616/11728 [2:24:43<1:51:31, 6.02s/it] 91%|█████████ | 10617/11728 [2:24:49<1:50:33, 5.97s/it] {'loss': 0.4583, 'learning_rate': 4.669917240467148e-07, 'epoch': 0.91} + 91%|█████████ | 10617/11728 [2:24:49<1:50:33, 5.97s/it] 91%|█████████ | 10618/11728 [2:24:55<1:49:31, 5.92s/it] {'loss': 0.4646, 'learning_rate': 4.6615802343273787e-07, 'epoch': 0.91} + 91%|█████████ | 10618/11728 [2:24:55<1:49:31, 5.92s/it] 91%|█████████ | 10619/11728 [2:25:01<1:48:52, 5.89s/it] {'loss': 0.4227, 'learning_rate': 4.6532504990935423e-07, 'epoch': 0.91} + 91%|█████████ | 10619/11728 [2:25:01<1:48:52, 5.89s/it] 91%|█████████ | 10620/11728 [2:25:06<1:47:16, 5.81s/it] {'loss': 0.4671, 'learning_rate': 4.644928035400864e-07, 'epoch': 0.91} + 91%|█████████ | 10620/11728 [2:25:06<1:47:16, 5.81s/it] 91%|█████████ | 10621/11728 [2:25:12<1:47:07, 5.81s/it] {'loss': 0.4649, 'learning_rate': 4.6366128438840586e-07, 'epoch': 0.91} + 91%|█████████ | 10621/11728 [2:25:12<1:47:07, 5.81s/it] 91%|█████████ | 10622/11728 [2:25:19<1:50:02, 5.97s/it] {'loss': 0.4622, 'learning_rate': 4.628304925177318e-07, 'epoch': 0.91} + 91%|█████████ | 10622/11728 [2:25:19<1:50:02, 5.97s/it] 91%|█████████ | 10623/11728 [2:25:24<1:47:01, 5.81s/it] {'loss': 0.423, 'learning_rate': 4.620004279914192e-07, 'epoch': 0.91} + 91%|█████████ | 10623/11728 [2:25:24<1:47:01, 5.81s/it] 91%|█████████ | 10624/11728 [2:25:30<1:47:11, 5.83s/it] {'loss': 0.4753, 'learning_rate': 4.61171090872774e-07, 'epoch': 0.91} + 91%|█████████ | 10624/11728 [2:25:30<1:47:11, 5.83s/it] 91%|█████████ | 10625/11728 [2:25:36<1:46:41, 5.80s/it] {'loss': 0.4429, 'learning_rate': 4.6034248122504454e-07, 'epoch': 0.91} + 91%|█████████ | 10625/11728 [2:25:36<1:46:41, 5.80s/it] 91%|█████████ | 10626/11728 [2:25:41<1:46:32, 5.80s/it] {'loss': 0.44, 'learning_rate': 4.595145991114247e-07, 'epoch': 0.91} + 91%|█████████ | 10626/11728 [2:25:41<1:46:32, 5.80s/it] 91%|█████████ | 10627/11728 [2:25:47<1:44:35, 5.70s/it] {'loss': 0.4565, 'learning_rate': 4.5868744459505174e-07, 'epoch': 0.91} + 91%|█████████ | 10627/11728 [2:25:47<1:44:35, 5.70s/it] 91%|█████████ | 10628/11728 [2:25:53<1:44:46, 5.72s/it] {'loss': 0.4567, 'learning_rate': 4.578610177390086e-07, 'epoch': 0.91} + 91%|█████████ | 10628/11728 [2:25:53<1:44:46, 5.72s/it] 91%|█████████ | 10629/11728 [2:25:58<1:44:12, 5.69s/it] {'loss': 0.4397, 'learning_rate': 4.5703531860632146e-07, 'epoch': 0.91} + 91%|█████████ | 10629/11728 [2:25:58<1:44:12, 5.69s/it] 91%|█████████ | 10630/11728 [2:26:04<1:45:01, 5.74s/it] {'loss': 0.4619, 'learning_rate': 4.5621034725995994e-07, 'epoch': 0.91} + 91%|█████████ | 10630/11728 [2:26:04<1:45:01, 5.74s/it] 91%|█████████ | 10631/11728 [2:26:10<1:44:39, 5.72s/it] {'loss': 0.4436, 'learning_rate': 4.5538610376284375e-07, 'epoch': 0.91} + 91%|█████████ | 10631/11728 [2:26:10<1:44:39, 5.72s/it] 91%|█████████ | 10632/11728 [2:26:16<1:45:40, 5.78s/it] {'loss': 0.4591, 'learning_rate': 4.5456258817782925e-07, 'epoch': 0.91} + 91%|█████████ | 10632/11728 [2:26:16<1:45:40, 5.78s/it] 91%|█████████ | 10633/11728 [2:26:22<1:46:07, 5.82s/it] {'loss': 0.4296, 'learning_rate': 4.5373980056772405e-07, 'epoch': 0.91} + 91%|█████████ | 10633/11728 [2:26:22<1:46:07, 5.82s/it] 91%|█████████ | 10634/11728 [2:26:27<1:46:01, 5.82s/it] {'loss': 0.4542, 'learning_rate': 4.5291774099527453e-07, 'epoch': 0.91} + 91%|█████████ | 10634/11728 [2:26:27<1:46:01, 5.82s/it] 91%|█████████ | 10635/11728 [2:26:33<1:45:51, 5.81s/it] {'loss': 0.4529, 'learning_rate': 4.5209640952317723e-07, 'epoch': 0.91} + 91%|█████████ | 10635/11728 [2:26:33<1:45:51, 5.81s/it] 91%|█████████ | 10636/11728 [2:26:39<1:46:29, 5.85s/it] {'loss': 0.442, 'learning_rate': 4.5127580621406877e-07, 'epoch': 0.91} + 91%|█████████ | 10636/11728 [2:26:39<1:46:29, 5.85s/it] 91%|█████████ | 10637/11728 [2:26:45<1:46:15, 5.84s/it] {'loss': 0.4564, 'learning_rate': 4.504559311305323e-07, 'epoch': 0.91} + 91%|█████████ | 10637/11728 [2:26:45<1:46:15, 5.84s/it] 91%|█████████ | 10638/11728 [2:26:51<1:44:55, 5.78s/it] {'loss': 0.4336, 'learning_rate': 4.4963678433509463e-07, 'epoch': 0.91} + 91%|█████████ | 10638/11728 [2:26:51<1:44:55, 5.78s/it] 91%|█████████ | 10639/11728 [2:26:56<1:43:38, 5.71s/it] {'loss': 0.4216, 'learning_rate': 4.4881836589022566e-07, 'epoch': 0.91} + 91%|█████████ | 10639/11728 [2:26:56<1:43:38, 5.71s/it] 91%|█████████ | 10640/11728 [2:27:02<1:44:04, 5.74s/it] {'loss': 0.451, 'learning_rate': 4.480006758583455e-07, 'epoch': 0.91} + 91%|█████████ | 10640/11728 [2:27:02<1:44:04, 5.74s/it] 91%|█████████ | 10641/11728 [2:27:08<1:43:22, 5.71s/it] {'loss': 0.4667, 'learning_rate': 4.4718371430181095e-07, 'epoch': 0.91} + 91%|█████████ | 10641/11728 [2:27:08<1:43:22, 5.71s/it] 91%|█████████ | 10642/11728 [2:27:14<1:44:28, 5.77s/it] {'loss': 0.4268, 'learning_rate': 4.463674812829277e-07, 'epoch': 0.91} + 91%|█████████ | 10642/11728 [2:27:14<1:44:28, 5.77s/it] 91%|█████████ | 10643/11728 [2:27:20<1:46:06, 5.87s/it] {'loss': 0.4817, 'learning_rate': 4.455519768639471e-07, 'epoch': 0.91} + 91%|█████████ | 10643/11728 [2:27:20<1:46:06, 5.87s/it] 91%|█████████ | 10644/11728 [2:27:25<1:45:16, 5.83s/it] {'loss': 0.4537, 'learning_rate': 4.447372011070594e-07, 'epoch': 0.91} + 91%|█████████ | 10644/11728 [2:27:25<1:45:16, 5.83s/it] 91%|█████████ | 10645/11728 [2:27:31<1:45:03, 5.82s/it] {'loss': 0.446, 'learning_rate': 4.43923154074406e-07, 'epoch': 0.91} + 91%|█████████ | 10645/11728 [2:27:31<1:45:03, 5.82s/it] 91%|█████████ | 10646/11728 [2:27:37<1:45:36, 5.86s/it] {'loss': 0.4564, 'learning_rate': 4.4310983582806945e-07, 'epoch': 0.91} + 91%|█████████ | 10646/11728 [2:27:37<1:45:36, 5.86s/it] 91%|█████████ | 10647/11728 [2:27:43<1:46:45, 5.93s/it] {'loss': 0.4677, 'learning_rate': 4.4229724643007346e-07, 'epoch': 0.91} + 91%|█████████ | 10647/11728 [2:27:43<1:46:45, 5.93s/it] 91%|█████████ | 10648/11728 [2:27:49<1:46:04, 5.89s/it] {'loss': 0.4446, 'learning_rate': 4.4148538594239176e-07, 'epoch': 0.91} + 91%|█████████ | 10648/11728 [2:27:49<1:46:04, 5.89s/it] 91%|█████████ | 10649/11728 [2:27:55<1:45:55, 5.89s/it] {'loss': 0.4459, 'learning_rate': 4.4067425442694157e-07, 'epoch': 0.91} + 91%|█████████ | 10649/11728 [2:27:55<1:45:55, 5.89s/it]3 AutoResumeHook: Checking whether to suspend... +01 AutoResumeHook: Checking whether to suspend... + 5AutoResumeHook: Checking whether to suspend... AutoResumeHook: Checking whether to suspend... + +4 AutoResumeHook: Checking whether to suspend... + 91%|█████████ | 10650/11728 [2:28:01<1:46:05, 5.91s/it]6 AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4697, 'learning_rate': 4.398638519455811e-07, 'epoch': 0.91} + 91%|█████████ | 10650/11728 [2:28:01<1:46:05, 5.91s/it] 91%|█████████ | 10651/11728 [2:28:07<1:44:55, 5.85s/it] {'loss': 0.4594, 'learning_rate': 4.3905417856011543e-07, 'epoch': 0.91} + 91%|█████████ | 10651/11728 [2:28:07<1:44:55, 5.85s/it] 91%|█████████ | 10652/11728 [2:28:12<1:43:44, 5.79s/it] {'loss': 0.4446, 'learning_rate': 4.382452343322952e-07, 'epoch': 0.91} + 91%|█████████ | 10652/11728 [2:28:12<1:43:44, 5.79s/it] 91%|█████████ | 10653/11728 [2:28:18<1:46:27, 5.94s/it] {'loss': 0.4451, 'learning_rate': 4.3743701932380975e-07, 'epoch': 0.91} + 91%|█████████ | 10653/11728 [2:28:18<1:46:27, 5.94s/it] 91%|█████████ | 10654/11728 [2:28:24<1:44:31, 5.84s/it] {'loss': 0.4482, 'learning_rate': 4.366295335963011e-07, 'epoch': 0.91} + 91%|█████████ | 10654/11728 [2:28:24<1:44:31, 5.84s/it] 91%|█████████ | 10655/11728 [2:28:30<1:44:46, 5.86s/it] {'loss': 0.434, 'learning_rate': 4.3582277721135104e-07, 'epoch': 0.91} + 91%|█████████ | 10655/11728 [2:28:30<1:44:46, 5.86s/it] 91%|█████████ | 10656/11728 [2:28:36<1:43:58, 5.82s/it] {'loss': 0.4512, 'learning_rate': 4.350167502304847e-07, 'epoch': 0.91} + 91%|█████████ | 10656/11728 [2:28:36<1:43:58, 5.82s/it] 91%|█████████ | 10657/11728 [2:28:42<1:44:36, 5.86s/it] {'loss': 0.4759, 'learning_rate': 4.3421145271517193e-07, 'epoch': 0.91} + 91%|█████████ | 10657/11728 [2:28:42<1:44:36, 5.86s/it] 91%|█████████ | 10658/11728 [2:28:47<1:42:48, 5.76s/it] {'loss': 0.4336, 'learning_rate': 4.3340688472683245e-07, 'epoch': 0.91} + 91%|█████████ | 10658/11728 [2:28:47<1:42:48, 5.76s/it] 91%|█████████ | 10659/11728 [2:28:53<1:42:12, 5.74s/it] {'loss': 0.4342, 'learning_rate': 4.326030463268216e-07, 'epoch': 0.91} + 91%|█████████ | 10659/11728 [2:28:53<1:42:12, 5.74s/it] 91%|█████████ | 10660/11728 [2:28:59<1:41:37, 5.71s/it] {'loss': 0.4388, 'learning_rate': 4.317999375764459e-07, 'epoch': 0.91} + 91%|█████████ | 10660/11728 [2:28:59<1:41:37, 5.71s/it] 91%|█████████ | 10661/11728 [2:29:04<1:41:48, 5.72s/it] {'loss': 0.444, 'learning_rate': 4.30997558536953e-07, 'epoch': 0.91} + 91%|█████████ | 10661/11728 [2:29:04<1:41:48, 5.72s/it] 91%|█████████ | 10662/11728 [2:29:10<1:42:18, 5.76s/it] {'loss': 0.4589, 'learning_rate': 4.3019590926953405e-07, 'epoch': 0.91} + 91%|█████████ | 10662/11728 [2:29:10<1:42:18, 5.76s/it] 91%|█████████ | 10663/11728 [2:29:16<1:42:01, 5.75s/it] {'loss': 0.4506, 'learning_rate': 4.293949898353289e-07, 'epoch': 0.91} + 91%|█████████ | 10663/11728 [2:29:16<1:42:01, 5.75s/it] 91%|█████████ | 10664/11728 [2:29:22<1:42:16, 5.77s/it] {'loss': 0.4598, 'learning_rate': 4.285948002954199e-07, 'epoch': 0.91} + 91%|█████████ | 10664/11728 [2:29:22<1:42:16, 5.77s/it] 91%|█████████ | 10665/11728 [2:29:27<1:41:28, 5.73s/it] {'loss': 0.4541, 'learning_rate': 4.277953407108282e-07, 'epoch': 0.91} + 91%|█████████ | 10665/11728 [2:29:27<1:41:28, 5.73s/it] 91%|█████████ | 10666/11728 [2:29:33<1:43:01, 5.82s/it] {'loss': 0.4549, 'learning_rate': 4.269966111425272e-07, 'epoch': 0.91} + 91%|█████████ | 10666/11728 [2:29:33<1:43:01, 5.82s/it] 91%|█████████ | 10667/11728 [2:29:39<1:44:04, 5.89s/it] {'loss': 0.4685, 'learning_rate': 4.261986116514305e-07, 'epoch': 0.91} + 91%|█████████ | 10667/11728 [2:29:39<1:44:04, 5.89s/it] 91%|█████████ | 10668/11728 [2:29:45<1:42:30, 5.80s/it] {'loss': 0.4522, 'learning_rate': 4.2540134229839714e-07, 'epoch': 0.91} + 91%|█████████ | 10668/11728 [2:29:45<1:42:30, 5.80s/it] 91%|█████████ | 10669/11728 [2:29:51<1:42:22, 5.80s/it] {'loss': 0.4596, 'learning_rate': 4.246048031442307e-07, 'epoch': 0.91} + 91%|█████████ | 10669/11728 [2:29:51<1:42:22, 5.80s/it] 91%|█████████ | 10670/11728 [2:29:57<1:42:43, 5.83s/it] {'loss': 0.4591, 'learning_rate': 4.2380899424967814e-07, 'epoch': 0.91} + 91%|█████████ | 10670/11728 [2:29:57<1:42:43, 5.83s/it] 91%|█████████ | 10671/11728 [2:30:03<1:43:58, 5.90s/it] {'loss': 0.4545, 'learning_rate': 4.2301391567542983e-07, 'epoch': 0.91} + 91%|█████████ | 10671/11728 [2:30:03<1:43:58, 5.90s/it] 91%|█████████ | 10672/11728 [2:30:09<1:46:28, 6.05s/it] {'loss': 0.4729, 'learning_rate': 4.222195674821239e-07, 'epoch': 0.91} + 91%|█████████ | 10672/11728 [2:30:09<1:46:28, 6.05s/it] 91%|█████████ | 10673/11728 [2:30:15<1:45:45, 6.01s/it] {'loss': 0.4594, 'learning_rate': 4.2142594973034077e-07, 'epoch': 0.91} + 91%|█████████ | 10673/11728 [2:30:15<1:45:45, 6.01s/it] 91%|█████████ | 10674/11728 [2:30:21<1:45:43, 6.02s/it] {'loss': 0.4515, 'learning_rate': 4.2063306248060323e-07, 'epoch': 0.91} + 91%|█████████ | 10674/11728 [2:30:21<1:45:43, 6.02s/it] 91%|█████████ | 10675/11728 [2:30:27<1:44:35, 5.96s/it] {'loss': 0.4648, 'learning_rate': 4.1984090579338054e-07, 'epoch': 0.91} + 91%|█████████ | 10675/11728 [2:30:27<1:44:35, 5.96s/it] 91%|█████████ | 10676/11728 [2:30:33<1:44:02, 5.93s/it] {'loss': 0.4531, 'learning_rate': 4.1904947972908673e-07, 'epoch': 0.91} + 91%|█████████ | 10676/11728 [2:30:33<1:44:02, 5.93s/it] 91%|█████████ | 10677/11728 [2:30:38<1:42:01, 5.82s/it] {'loss': 0.4437, 'learning_rate': 4.18258784348079e-07, 'epoch': 0.91} + 91%|█████████ | 10677/11728 [2:30:38<1:42:01, 5.82s/it] 91%|█████████ | 10678/11728 [2:30:44<1:41:09, 5.78s/it] {'loss': 0.449, 'learning_rate': 4.17468819710658e-07, 'epoch': 0.91} + 91%|█████████ | 10678/11728 [2:30:44<1:41:09, 5.78s/it] 91%|█████████ | 10679/11728 [2:30:50<1:42:08, 5.84s/it] {'loss': 0.451, 'learning_rate': 4.1667958587707226e-07, 'epoch': 0.91} + 91%|█████████ | 10679/11728 [2:30:50<1:42:08, 5.84s/it] 91%|█████████ | 10680/11728 [2:30:56<1:41:59, 5.84s/it] {'loss': 0.4599, 'learning_rate': 4.1589108290750915e-07, 'epoch': 0.91} + 91%|█████████ | 10680/11728 [2:30:56<1:41:59, 5.84s/it] 91%|█████████ | 10681/11728 [2:31:02<1:42:11, 5.86s/it] {'loss': 0.4504, 'learning_rate': 4.15103310862105e-07, 'epoch': 0.91} + 91%|█████████ | 10681/11728 [2:31:02<1:42:11, 5.86s/it] 91%|█████████ | 10682/11728 [2:31:07<1:41:13, 5.81s/it] {'loss': 0.4485, 'learning_rate': 4.143162698009384e-07, 'epoch': 0.91} + 91%|█████████ | 10682/11728 [2:31:07<1:41:13, 5.81s/it] 91%|█████████ | 10683/11728 [2:31:13<1:41:07, 5.81s/it] {'loss': 0.4672, 'learning_rate': 4.135299597840325e-07, 'epoch': 0.91} + 91%|█████████ | 10683/11728 [2:31:13<1:41:07, 5.81s/it] 91%|█████████ | 10684/11728 [2:31:19<1:42:14, 5.88s/it] {'loss': 0.4541, 'learning_rate': 4.1274438087135273e-07, 'epoch': 0.91} + 91%|█████████ | 10684/11728 [2:31:19<1:42:14, 5.88s/it] 91%|█████████ | 10685/11728 [2:31:25<1:41:08, 5.82s/it] {'loss': 0.444, 'learning_rate': 4.119595331228132e-07, 'epoch': 0.91} + 91%|█████████ | 10685/11728 [2:31:25<1:41:08, 5.82s/it] 91%|█████████ | 10686/11728 [2:31:31<1:41:45, 5.86s/it] {'loss': 0.4833, 'learning_rate': 4.111754165982673e-07, 'epoch': 0.91} + 91%|█████████ | 10686/11728 [2:31:31<1:41:45, 5.86s/it] 91%|█████████ | 10687/11728 [2:31:37<1:40:22, 5.79s/it] {'loss': 0.445, 'learning_rate': 4.1039203135751717e-07, 'epoch': 0.91} + 91%|█████████ | 10687/11728 [2:31:37<1:40:22, 5.79s/it] 91%|█████████ | 10688/11728 [2:31:42<1:40:44, 5.81s/it] {'loss': 0.4548, 'learning_rate': 4.0960937746030607e-07, 'epoch': 0.91} + 91%|█████████ | 10688/11728 [2:31:42<1:40:44, 5.81s/it] 91%|█████████ | 10689/11728 [2:31:48<1:38:59, 5.72s/it] {'loss': 0.4462, 'learning_rate': 4.0882745496632406e-07, 'epoch': 0.91} + 91%|█████████ | 10689/11728 [2:31:48<1:38:59, 5.72s/it] 91%|█████████ | 10690/11728 [2:31:54<1:39:03, 5.73s/it] {'loss': 0.4486, 'learning_rate': 4.0804626393519897e-07, 'epoch': 0.91} + 91%|█████████ | 10690/11728 [2:31:54<1:39:03, 5.73s/it] 91%|█████████ | 10691/11728 [2:31:59<1:39:19, 5.75s/it] {'loss': 0.4505, 'learning_rate': 4.0726580442651433e-07, 'epoch': 0.91} + 91%|█████████ | 10691/11728 [2:31:59<1:39:19, 5.75s/it] 91%|█████████ | 10692/11728 [2:32:05<1:39:10, 5.74s/it] {'loss': 0.4446, 'learning_rate': 4.064860764997858e-07, 'epoch': 0.91} + 91%|█████████ | 10692/11728 [2:32:05<1:39:10, 5.74s/it] 91%|█████████ | 10693/11728 [2:32:11<1:39:26, 5.76s/it] {'loss': 0.4678, 'learning_rate': 4.0570708021448134e-07, 'epoch': 0.91} + 91%|█████████ | 10693/11728 [2:32:11<1:39:26, 5.76s/it] 91%|█████████ | 10694/11728 [2:32:17<1:40:28, 5.83s/it] {'loss': 0.4449, 'learning_rate': 4.049288156300102e-07, 'epoch': 0.91} + 91%|█████████ | 10694/11728 [2:32:17<1:40:28, 5.83s/it] 91%|█████████ | 10695/11728 [2:32:23<1:39:18, 5.77s/it] {'loss': 0.4731, 'learning_rate': 4.041512828057248e-07, 'epoch': 0.91} + 91%|█████████ | 10695/11728 [2:32:23<1:39:18, 5.77s/it] 91%|█████████ | 10696/11728 [2:32:29<1:40:14, 5.83s/it] {'loss': 0.4717, 'learning_rate': 4.0337448180092444e-07, 'epoch': 0.91} + 91%|█████████ | 10696/11728 [2:32:29<1:40:14, 5.83s/it] 91%|█████████ | 10697/11728 [2:32:34<1:40:34, 5.85s/it] {'loss': 0.4508, 'learning_rate': 4.0259841267485167e-07, 'epoch': 0.91} + 91%|█████████ | 10697/11728 [2:32:34<1:40:34, 5.85s/it] 91%|█████████ | 10698/11728 [2:32:40<1:38:30, 5.74s/it] {'loss': 0.4442, 'learning_rate': 4.0182307548669255e-07, 'epoch': 0.91} + 91%|█████████ | 10698/11728 [2:32:40<1:38:30, 5.74s/it] 91%|█████████ | 10699/11728 [2:32:46<1:38:06, 5.72s/it] {'loss': 0.4498, 'learning_rate': 4.010484702955741e-07, 'epoch': 0.91} + 91%|█████████ | 10699/11728 [2:32:46<1:38:06, 5.72s/it]3 AutoResumeHook: Checking whether to suspend... +01 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... + 91%|█████████ | 10700/11728 [2:32:52<1:39:26, 5.80s/it]4 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4309, 'learning_rate': 4.002745971605759e-07, 'epoch': 0.91} + 91%|█████████ | 10700/11728 [2:32:52<1:39:26, 5.80s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-10700/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-10700/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-10700/mm_projector +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/torch/nn/modules/module.py:1802: UserWarning: Positional args are being deprecated, use kwargs instead. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details. + warnings.warn( + 91%|█████████ | 10701/11728 [2:33:25<4:01:22, 14.10s/it] {'loss': 0.4489, 'learning_rate': 3.99501456140714e-07, 'epoch': 0.91} + 91%|█████████ | 10701/11728 [2:33:25<4:01:22, 14.10s/it] 91%|█████████▏| 10702/11728 [2:33:31<3:17:03, 11.52s/it] {'loss': 0.4606, 'learning_rate': 3.9872904729495123e-07, 'epoch': 0.91} + 91%|█████████▏| 10702/11728 [2:33:31<3:17:03, 11.52s/it] 91%|█████████▏| 10703/11728 [2:33:37<2:48:32, 9.87s/it] {'loss': 0.4386, 'learning_rate': 3.97957370682196e-07, 'epoch': 0.91} + 91%|█████████▏| 10703/11728 [2:33:37<2:48:32, 9.87s/it] 91%|█████████▏| 10704/11728 [2:33:42<2:27:05, 8.62s/it] {'loss': 0.4226, 'learning_rate': 3.97186426361299e-07, 'epoch': 0.91} + 91%|█████████▏| 10704/11728 [2:33:42<2:27:05, 8.62s/it] 91%|█████████▏| 10705/11728 [2:33:48<2:10:54, 7.68s/it] {'loss': 0.4383, 'learning_rate': 3.964162143910555e-07, 'epoch': 0.91} + 91%|█████████▏| 10705/11728 [2:33:48<2:10:54, 7.68s/it] 91%|█████████▏| 10706/11728 [2:33:54<2:00:56, 7.10s/it] {'loss': 0.4636, 'learning_rate': 3.956467348302062e-07, 'epoch': 0.91} + 91%|█████████▏| 10706/11728 [2:33:54<2:00:56, 7.10s/it] 91%|█████████▏| 10707/11728 [2:33:59<1:53:14, 6.65s/it] {'loss': 0.4384, 'learning_rate': 3.9487798773743425e-07, 'epoch': 0.91} + 91%|█████████▏| 10707/11728 [2:33:59<1:53:14, 6.65s/it] 91%|█████████▏| 10708/11728 [2:34:05<1:48:28, 6.38s/it] {'loss': 0.4584, 'learning_rate': 3.941099731713638e-07, 'epoch': 0.91} + 91%|█████████▏| 10708/11728 [2:34:05<1:48:28, 6.38s/it] 91%|█████████▏| 10709/11728 [2:34:11<1:46:00, 6.24s/it] {'loss': 0.4685, 'learning_rate': 3.9334269119057354e-07, 'epoch': 0.91} + 91%|█████████▏| 10709/11728 [2:34:11<1:46:00, 6.24s/it] 91%|█████████▏| 10710/11728 [2:34:17<1:43:18, 6.09s/it] {'loss': 0.4457, 'learning_rate': 3.925761418535756e-07, 'epoch': 0.91} + 91%|█████████▏| 10710/11728 [2:34:17<1:43:18, 6.09s/it] 91%|█████████▏| 10711/11728 [2:34:22<1:41:48, 6.01s/it] {'loss': 0.4445, 'learning_rate': 3.918103252188299e-07, 'epoch': 0.91} + 91%|█████████▏| 10711/11728 [2:34:22<1:41:48, 6.01s/it] 91%|█████████▏| 10712/11728 [2:34:28<1:39:32, 5.88s/it] {'loss': 0.4621, 'learning_rate': 3.9104524134474187e-07, 'epoch': 0.91} + 91%|█████████▏| 10712/11728 [2:34:28<1:39:32, 5.88s/it] 91%|█████████▏| 10713/11728 [2:34:34<1:40:35, 5.95s/it] {'loss': 0.4157, 'learning_rate': 3.902808902896604e-07, 'epoch': 0.91} + 91%|█████████▏| 10713/11728 [2:34:34<1:40:35, 5.95s/it] 91%|█████████▏| 10714/11728 [2:34:40<1:40:28, 5.94s/it] {'loss': 0.4593, 'learning_rate': 3.895172721118778e-07, 'epoch': 0.91} + 91%|█████████▏| 10714/11728 [2:34:40<1:40:28, 5.94s/it] 91%|█████████▏| 10715/11728 [2:34:46<1:39:44, 5.91s/it] {'loss': 0.4646, 'learning_rate': 3.8875438686962973e-07, 'epoch': 0.91} + 91%|█████████▏| 10715/11728 [2:34:46<1:39:44, 5.91s/it] 91%|█████████▏| 10716/11728 [2:34:52<1:39:58, 5.93s/it] {'loss': 0.4533, 'learning_rate': 3.879922346210996e-07, 'epoch': 0.91} + 91%|█████████▏| 10716/11728 [2:34:52<1:39:58, 5.93s/it] 91%|█████████▏| 10717/11728 [2:34:57<1:38:35, 5.85s/it] {'loss': 0.4384, 'learning_rate': 3.8723081542440866e-07, 'epoch': 0.91} + 91%|█████████▏| 10717/11728 [2:34:57<1:38:35, 5.85s/it] 91%|█████████▏| 10718/11728 [2:35:03<1:38:13, 5.84s/it] {'loss': 0.4425, 'learning_rate': 3.864701293376294e-07, 'epoch': 0.91} + 91%|█████████▏| 10718/11728 [2:35:03<1:38:13, 5.84s/it] 91%|█████████▏| 10719/11728 [2:35:09<1:36:59, 5.77s/it] {'loss': 0.438, 'learning_rate': 3.8571017641877206e-07, 'epoch': 0.91} + 91%|█████████▏| 10719/11728 [2:35:09<1:36:59, 5.77s/it] 91%|█████████▏| 10720/11728 [2:35:15<1:40:00, 5.95s/it] {'loss': 0.4424, 'learning_rate': 3.8495095672579584e-07, 'epoch': 0.91} + 91%|█████████▏| 10720/11728 [2:35:15<1:40:00, 5.95s/it] 91%|█████████▏| 10721/11728 [2:35:21<1:41:11, 6.03s/it] {'loss': 0.4705, 'learning_rate': 3.8419247031660113e-07, 'epoch': 0.91} + 91%|█████████▏| 10721/11728 [2:35:21<1:41:11, 6.03s/it] 91%|█████████▏| 10722/11728 [2:35:27<1:41:04, 6.03s/it] {'loss': 0.4399, 'learning_rate': 3.834347172490327e-07, 'epoch': 0.91} + 91%|█████████▏| 10722/11728 [2:35:27<1:41:04, 6.03s/it] 91%|█████████▏| 10723/11728 [2:35:33<1:40:44, 6.01s/it] {'loss': 0.4824, 'learning_rate': 3.826776975808821e-07, 'epoch': 0.91} + 91%|█████████▏| 10723/11728 [2:35:33<1:40:44, 6.01s/it] 91%|█████████▏| 10724/11728 [2:35:39<1:39:46, 5.96s/it] {'loss': 0.4573, 'learning_rate': 3.819214113698799e-07, 'epoch': 0.91} + 91%|█████████▏| 10724/11728 [2:35:39<1:39:46, 5.96s/it] 91%|█████████▏| 10725/11728 [2:35:45<1:37:19, 5.82s/it] {'loss': 0.4359, 'learning_rate': 3.811658586737077e-07, 'epoch': 0.91} + 91%|█████████▏| 10725/11728 [2:35:45<1:37:19, 5.82s/it] 91%|█████████▏| 10726/11728 [2:35:50<1:36:32, 5.78s/it] {'loss': 0.4514, 'learning_rate': 3.8041103954998046e-07, 'epoch': 0.91} + 91%|█████████▏| 10726/11728 [2:35:50<1:36:32, 5.78s/it] 91%|█████████▏| 10727/11728 [2:35:57<1:39:16, 5.95s/it] {'loss': 0.4585, 'learning_rate': 3.7965695405627e-07, 'epoch': 0.91} + 91%|█████████▏| 10727/11728 [2:35:57<1:39:16, 5.95s/it] 91%|█████████▏| 10728/11728 [2:36:03<1:38:35, 5.92s/it] {'loss': 0.479, 'learning_rate': 3.789036022500858e-07, 'epoch': 0.91} + 91%|█████████▏| 10728/11728 [2:36:03<1:38:35, 5.92s/it] 91%|█████████▏| 10729/11728 [2:36:09<1:39:02, 5.95s/it] {'loss': 0.4538, 'learning_rate': 3.781509841888775e-07, 'epoch': 0.91} + 91%|█████████▏| 10729/11728 [2:36:09<1:39:02, 5.95s/it] 91%|█████████▏| 10730/11728 [2:36:14<1:37:35, 5.87s/it] {'loss': 0.4418, 'learning_rate': 3.773990999300459e-07, 'epoch': 0.91} + 91%|█████████▏| 10730/11728 [2:36:14<1:37:35, 5.87s/it] 91%|█████████▏| 10731/11728 [2:36:20<1:36:19, 5.80s/it] {'loss': 0.4539, 'learning_rate': 3.7664794953093163e-07, 'epoch': 0.91} + 91%|█████████▏| 10731/11728 [2:36:20<1:36:19, 5.80s/it] 92%|█████████▏| 10732/11728 [2:36:26<1:35:07, 5.73s/it] {'loss': 0.4536, 'learning_rate': 3.7589753304882125e-07, 'epoch': 0.92} + 92%|█████████▏| 10732/11728 [2:36:26<1:35:07, 5.73s/it] 92%|█████████▏| 10733/11728 [2:36:32<1:37:22, 5.87s/it] {'loss': 0.4367, 'learning_rate': 3.7514785054094447e-07, 'epoch': 0.92} + 92%|█████████▏| 10733/11728 [2:36:32<1:37:22, 5.87s/it] 92%|█████████▏| 10734/11728 [2:36:38<1:36:45, 5.84s/it] {'loss': 0.4456, 'learning_rate': 3.7439890206447674e-07, 'epoch': 0.92} + 92%|█████████▏| 10734/11728 [2:36:38<1:36:45, 5.84s/it] 92%|█████████▏| 10735/11728 [2:36:43<1:36:23, 5.82s/it] {'loss': 0.4632, 'learning_rate': 3.736506876765311e-07, 'epoch': 0.92} + 92%|█████████▏| 10735/11728 [2:36:43<1:36:23, 5.82s/it] 92%|█████████▏| 10736/11728 [2:36:49<1:36:46, 5.85s/it] {'loss': 0.4355, 'learning_rate': 3.729032074341743e-07, 'epoch': 0.92} + 92%|█████████▏| 10736/11728 [2:36:49<1:36:46, 5.85s/it] 92%|█████████▏| 10737/11728 [2:36:55<1:37:45, 5.92s/it] {'loss': 0.4501, 'learning_rate': 3.7215646139441284e-07, 'epoch': 0.92} + 92%|█████████▏| 10737/11728 [2:36:55<1:37:45, 5.92s/it] 92%|█████████▏| 10738/11728 [2:37:01<1:37:44, 5.92s/it] {'loss': 0.4501, 'learning_rate': 3.714104496141924e-07, 'epoch': 0.92} + 92%|█████████▏| 10738/11728 [2:37:01<1:37:44, 5.92s/it] 92%|█████████▏| 10739/11728 [2:37:07<1:38:47, 5.99s/it] {'loss': 0.4545, 'learning_rate': 3.706651721504095e-07, 'epoch': 0.92} + 92%|█████████▏| 10739/11728 [2:37:07<1:38:47, 5.99s/it] 92%|█████████▏| 10740/11728 [2:37:13<1:36:35, 5.87s/it] {'loss': 0.4302, 'learning_rate': 3.6992062905990225e-07, 'epoch': 0.92} + 92%|█████████▏| 10740/11728 [2:37:13<1:36:35, 5.87s/it] 92%|█████████▏| 10741/11728 [2:37:19<1:37:22, 5.92s/it] {'loss': 0.4448, 'learning_rate': 3.6917682039945167e-07, 'epoch': 0.92} + 92%|█████████▏| 10741/11728 [2:37:19<1:37:22, 5.92s/it] 92%|█████████▏| 10742/11728 [2:37:25<1:35:33, 5.82s/it] {'loss': 0.4381, 'learning_rate': 3.6843374622578474e-07, 'epoch': 0.92} + 92%|█████████▏| 10742/11728 [2:37:25<1:35:33, 5.82s/it] 92%|█████████▏| 10743/11728 [2:37:31<1:36:20, 5.87s/it] {'loss': 0.4291, 'learning_rate': 3.676914065955717e-07, 'epoch': 0.92} + 92%|█████████▏| 10743/11728 [2:37:31<1:36:20, 5.87s/it] 92%|█████████▏| 10744/11728 [2:37:36<1:36:04, 5.86s/it] {'loss': 0.4577, 'learning_rate': 3.6694980156542494e-07, 'epoch': 0.92} + 92%|█████████▏| 10744/11728 [2:37:36<1:36:04, 5.86s/it] 92%|█████████▏| 10745/11728 [2:37:42<1:35:08, 5.81s/it] {'loss': 0.4566, 'learning_rate': 3.662089311919015e-07, 'epoch': 0.92} + 92%|█████████▏| 10745/11728 [2:37:42<1:35:08, 5.81s/it] 92%|█████████▏| 10746/11728 [2:37:48<1:35:55, 5.86s/it] {'loss': 0.4365, 'learning_rate': 3.6546879553150727e-07, 'epoch': 0.92} + 92%|█████████▏| 10746/11728 [2:37:48<1:35:55, 5.86s/it] 92%|█████████▏| 10747/11728 [2:37:54<1:35:24, 5.84s/it] {'loss': 0.4389, 'learning_rate': 3.647293946406849e-07, 'epoch': 0.92} + 92%|█████████▏| 10747/11728 [2:37:54<1:35:24, 5.84s/it] 92%|█████████▏| 10748/11728 [2:38:00<1:36:49, 5.93s/it] {'loss': 0.4798, 'learning_rate': 3.6399072857582487e-07, 'epoch': 0.92} + 92%|█████████▏| 10748/11728 [2:38:00<1:36:49, 5.93s/it] 92%|█████████▏| 10749/11728 [2:38:06<1:35:26, 5.85s/it] {'loss': 0.4492, 'learning_rate': 3.6325279739325983e-07, 'epoch': 0.92} + 92%|█████████▏| 10749/11728 [2:38:06<1:35:26, 5.85s/it]5 AutoResumeHook: Checking whether to suspend... +30 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... + 92%|█████████▏| 10750/11728 [2:38:12<1:35:40, 5.87s/it]2 AutoResumeHook: Checking whether to suspend... + {'loss': 0.456, 'learning_rate': 3.625156011492703e-07, 'epoch': 0.92} + 92%|█████████▏| 10750/11728 [2:38:12<1:35:40, 5.87s/it] 92%|█████████▏| 10751/11728 [2:38:17<1:35:03, 5.84s/it] {'loss': 0.4598, 'learning_rate': 3.6177913990007473e-07, 'epoch': 0.92} + 92%|█████████▏| 10751/11728 [2:38:17<1:35:03, 5.84s/it] 92%|█████████▏| 10752/11728 [2:38:23<1:34:23, 5.80s/it] {'loss': 0.437, 'learning_rate': 3.610434137018426e-07, 'epoch': 0.92} + 92%|█████████▏| 10752/11728 [2:38:23<1:34:23, 5.80s/it] 92%|█████████▏| 10753/11728 [2:38:29<1:33:27, 5.75s/it] {'loss': 0.4735, 'learning_rate': 3.603084226106801e-07, 'epoch': 0.92} + 92%|█████████▏| 10753/11728 [2:38:29<1:33:27, 5.75s/it] 92%|█████████▏| 10754/11728 [2:38:34<1:33:21, 5.75s/it] {'loss': 0.46, 'learning_rate': 3.595741666826402e-07, 'epoch': 0.92} + 92%|█████████▏| 10754/11728 [2:38:34<1:33:21, 5.75s/it] 92%|█████████▏| 10755/11728 [2:38:40<1:34:03, 5.80s/it] {'loss': 0.4639, 'learning_rate': 3.588406459737237e-07, 'epoch': 0.92} + 92%|█████████▏| 10755/11728 [2:38:40<1:34:03, 5.80s/it] 92%|█████████▏| 10756/11728 [2:38:46<1:34:11, 5.81s/it] {'loss': 0.4394, 'learning_rate': 3.5810786053987025e-07, 'epoch': 0.92} + 92%|█████████▏| 10756/11728 [2:38:46<1:34:11, 5.81s/it] 92%|█████████▏| 10757/11728 [2:38:52<1:32:31, 5.72s/it] {'loss': 0.4323, 'learning_rate': 3.57375810436964e-07, 'epoch': 0.92} + 92%|█████████▏| 10757/11728 [2:38:52<1:32:31, 5.72s/it] 92%|█████████▏| 10758/11728 [2:38:57<1:31:28, 5.66s/it] {'loss': 0.4605, 'learning_rate': 3.5664449572083594e-07, 'epoch': 0.92} + 92%|█████████▏| 10758/11728 [2:38:57<1:31:28, 5.66s/it] 92%|█████████▏| 10759/11728 [2:39:03<1:32:22, 5.72s/it] {'loss': 0.4382, 'learning_rate': 3.5591391644725805e-07, 'epoch': 0.92} + 92%|█████████▏| 10759/11728 [2:39:03<1:32:22, 5.72s/it] 92%|█████████▏| 10760/11728 [2:39:09<1:33:22, 5.79s/it] {'loss': 0.4762, 'learning_rate': 3.55184072671948e-07, 'epoch': 0.92} + 92%|█████████▏| 10760/11728 [2:39:09<1:33:22, 5.79s/it] 92%|█████████▏| 10761/11728 [2:39:15<1:33:59, 5.83s/it] {'loss': 0.4541, 'learning_rate': 3.544549644505668e-07, 'epoch': 0.92} + 92%|█████████▏| 10761/11728 [2:39:15<1:33:59, 5.83s/it] 92%|█████████▏| 10762/11728 [2:39:21<1:32:29, 5.74s/it] {'loss': 0.4383, 'learning_rate': 3.5372659183871895e-07, 'epoch': 0.92} + 92%|█████████▏| 10762/11728 [2:39:21<1:32:29, 5.74s/it] 92%|█████████▏| 10763/11728 [2:39:26<1:33:17, 5.80s/it] {'loss': 0.4489, 'learning_rate': 3.52998954891951e-07, 'epoch': 0.92} + 92%|█████████▏| 10763/11728 [2:39:26<1:33:17, 5.80s/it] 92%|█████████▏| 10764/11728 [2:39:32<1:34:16, 5.87s/it] {'loss': 0.4537, 'learning_rate': 3.522720536657609e-07, 'epoch': 0.92} + 92%|█████████▏| 10764/11728 [2:39:32<1:34:16, 5.87s/it] 92%|█████████▏| 10765/11728 [2:39:38<1:32:39, 5.77s/it] {'loss': 0.4424, 'learning_rate': 3.515458882155798e-07, 'epoch': 0.92} + 92%|█████████▏| 10765/11728 [2:39:38<1:32:39, 5.77s/it] 92%|█████████▏| 10766/11728 [2:39:44<1:34:05, 5.87s/it] {'loss': 0.4475, 'learning_rate': 3.508204585967911e-07, 'epoch': 0.92} + 92%|█████████▏| 10766/11728 [2:39:44<1:34:05, 5.87s/it] 92%|█████████▏| 10767/11728 [2:39:50<1:33:44, 5.85s/it] {'loss': 0.4645, 'learning_rate': 3.500957648647196e-07, 'epoch': 0.92} + 92%|█████████▏| 10767/11728 [2:39:50<1:33:44, 5.85s/it] 92%|█████████▏| 10768/11728 [2:39:56<1:33:24, 5.84s/it] {'loss': 0.4574, 'learning_rate': 3.493718070746299e-07, 'epoch': 0.92} + 92%|█████████▏| 10768/11728 [2:39:56<1:33:24, 5.84s/it] 92%|█████████▏| 10769/11728 [2:40:01<1:31:36, 5.73s/it] {'loss': 0.4375, 'learning_rate': 3.486485852817378e-07, 'epoch': 0.92} + 92%|█████████▏| 10769/11728 [2:40:01<1:31:36, 5.73s/it] 92%|█████████▏| 10770/11728 [2:40:07<1:32:30, 5.79s/it] {'loss': 0.4703, 'learning_rate': 3.4792609954119815e-07, 'epoch': 0.92} + 92%|█████████▏| 10770/11728 [2:40:07<1:32:30, 5.79s/it] 92%|█████████▏| 10771/11728 [2:40:13<1:31:52, 5.76s/it] {'loss': 0.4444, 'learning_rate': 3.4720434990810904e-07, 'epoch': 0.92} + 92%|█████████▏| 10771/11728 [2:40:13<1:31:52, 5.76s/it] 92%|█████████▏| 10772/11728 [2:40:19<1:32:18, 5.79s/it] {'loss': 0.4494, 'learning_rate': 3.4648333643751533e-07, 'epoch': 0.92} + 92%|█████████▏| 10772/11728 [2:40:19<1:32:18, 5.79s/it] 92%|█████████▏| 10773/11728 [2:40:24<1:31:23, 5.74s/it] {'loss': 0.4395, 'learning_rate': 3.4576305918440635e-07, 'epoch': 0.92} + 92%|█████████▏| 10773/11728 [2:40:24<1:31:23, 5.74s/it] 92%|█████████▏| 10774/11728 [2:40:30<1:31:30, 5.76s/it] {'loss': 0.4739, 'learning_rate': 3.450435182037104e-07, 'epoch': 0.92} + 92%|█████████▏| 10774/11728 [2:40:30<1:31:30, 5.76s/it] 92%|█████████▏| 10775/11728 [2:40:36<1:31:16, 5.75s/it] {'loss': 0.4394, 'learning_rate': 3.443247135503036e-07, 'epoch': 0.92} + 92%|█████████▏| 10775/11728 [2:40:36<1:31:16, 5.75s/it] 92%|█████████▏| 10776/11728 [2:40:42<1:31:21, 5.76s/it] {'loss': 0.4625, 'learning_rate': 3.4360664527900767e-07, 'epoch': 0.92} + 92%|█████████▏| 10776/11728 [2:40:42<1:31:21, 5.76s/it] 92%|█████████▏| 10777/11728 [2:40:48<1:32:08, 5.81s/it] {'loss': 0.4538, 'learning_rate': 3.4288931344457987e-07, 'epoch': 0.92} + 92%|█████████▏| 10777/11728 [2:40:48<1:32:08, 5.81s/it] 92%|█████████▏| 10778/11728 [2:40:53<1:30:45, 5.73s/it] {'loss': 0.4354, 'learning_rate': 3.42172718101732e-07, 'epoch': 0.92} + 92%|█████████▏| 10778/11728 [2:40:53<1:30:45, 5.73s/it] 92%|█████████▏| 10779/11728 [2:40:59<1:30:24, 5.72s/it] {'loss': 0.4474, 'learning_rate': 3.4145685930511374e-07, 'epoch': 0.92} + 92%|█████████▏| 10779/11728 [2:40:59<1:30:24, 5.72s/it] 92%|█████████▏| 10780/11728 [2:41:05<1:32:32, 5.86s/it] {'loss': 0.448, 'learning_rate': 3.4074173710931804e-07, 'epoch': 0.92} + 92%|█████████▏| 10780/11728 [2:41:05<1:32:32, 5.86s/it] 92%|█████████▏| 10781/11728 [2:41:11<1:34:56, 6.02s/it] {'loss': 0.4528, 'learning_rate': 3.4002735156888234e-07, 'epoch': 0.92} + 92%|█████████▏| 10781/11728 [2:41:11<1:34:56, 6.02s/it] 92%|█████████▏| 10782/11728 [2:41:17<1:34:06, 5.97s/it] {'loss': 0.4629, 'learning_rate': 3.393137027382909e-07, 'epoch': 0.92} + 92%|█████████▏| 10782/11728 [2:41:17<1:34:06, 5.97s/it] 92%|█████████▏| 10783/11728 [2:41:23<1:31:54, 5.84s/it] {'loss': 0.4499, 'learning_rate': 3.3860079067196906e-07, 'epoch': 0.92} + 92%|█████████▏| 10783/11728 [2:41:23<1:31:54, 5.84s/it] 92%|█████████▏| 10784/11728 [2:41:28<1:30:59, 5.78s/it] {'loss': 0.4509, 'learning_rate': 3.3788861542428555e-07, 'epoch': 0.92} + 92%|█████████▏| 10784/11728 [2:41:28<1:30:59, 5.78s/it] 92%|█████████▏| 10785/11728 [2:41:34<1:32:08, 5.86s/it] {'loss': 0.4515, 'learning_rate': 3.3717717704955575e-07, 'epoch': 0.92} + 92%|█████████▏| 10785/11728 [2:41:34<1:32:08, 5.86s/it] 92%|█████████▏| 10786/11728 [2:41:40<1:31:41, 5.84s/it] {'loss': 0.4613, 'learning_rate': 3.3646647560203303e-07, 'epoch': 0.92} + 92%|█████████▏| 10786/11728 [2:41:40<1:31:41, 5.84s/it] 92%|█████████▏| 10787/11728 [2:41:46<1:30:56, 5.80s/it] {'loss': 0.4781, 'learning_rate': 3.3575651113592177e-07, 'epoch': 0.92} + 92%|█████████▏| 10787/11728 [2:41:46<1:30:56, 5.80s/it] 92%|█████████▏| 10788/11728 [2:41:52<1:30:33, 5.78s/it] {'loss': 0.4362, 'learning_rate': 3.3504728370536755e-07, 'epoch': 0.92} + 92%|█████████▏| 10788/11728 [2:41:52<1:30:33, 5.78s/it] 92%|█████████▏| 10789/11728 [2:41:58<1:30:50, 5.80s/it] {'loss': 0.4405, 'learning_rate': 3.3433879336445597e-07, 'epoch': 0.92} + 92%|█████████▏| 10789/11728 [2:41:58<1:30:50, 5.80s/it] 92%|█████████▏| 10790/11728 [2:42:03<1:31:15, 5.84s/it] {'loss': 0.4474, 'learning_rate': 3.3363104016721936e-07, 'epoch': 0.92} + 92%|█████████▏| 10790/11728 [2:42:03<1:31:15, 5.84s/it] 92%|█████████▏| 10791/11728 [2:42:09<1:30:10, 5.77s/it] {'loss': 0.424, 'learning_rate': 3.329240241676379e-07, 'epoch': 0.92} + 92%|█████████▏| 10791/11728 [2:42:09<1:30:10, 5.77s/it] 92%|█████████▏| 10792/11728 [2:42:15<1:30:37, 5.81s/it] {'loss': 0.4486, 'learning_rate': 3.322177454196285e-07, 'epoch': 0.92} + 92%|█████████▏| 10792/11728 [2:42:15<1:30:37, 5.81s/it] 92%|█████████▏| 10793/11728 [2:42:22<1:34:09, 6.04s/it] {'loss': 0.4524, 'learning_rate': 3.3151220397705577e-07, 'epoch': 0.92} + 92%|█████████▏| 10793/11728 [2:42:22<1:34:09, 6.04s/it] 92%|█████████▏| 10794/11728 [2:42:28<1:33:37, 6.01s/it] {'loss': 0.45, 'learning_rate': 3.308073998937278e-07, 'epoch': 0.92} + 92%|█████████▏| 10794/11728 [2:42:28<1:33:37, 6.01s/it] 92%|█████████▏| 10795/11728 [2:42:33<1:33:22, 6.00s/it] {'loss': 0.4637, 'learning_rate': 3.301033332233938e-07, 'epoch': 0.92} + 92%|█████████▏| 10795/11728 [2:42:33<1:33:22, 6.00s/it] 92%|█████████▏| 10796/11728 [2:42:39<1:33:10, 6.00s/it] {'loss': 0.4619, 'learning_rate': 3.2940000401975094e-07, 'epoch': 0.92} + 92%|█████████▏| 10796/11728 [2:42:39<1:33:10, 6.00s/it] 92%|█████████▏| 10797/11728 [2:42:46<1:33:12, 6.01s/it] {'loss': 0.47, 'learning_rate': 3.2869741233643726e-07, 'epoch': 0.92} + 92%|█████████▏| 10797/11728 [2:42:46<1:33:12, 6.01s/it] 92%|█████████▏| 10798/11728 [2:42:52<1:35:22, 6.15s/it] {'loss': 0.446, 'learning_rate': 3.2799555822703554e-07, 'epoch': 0.92} + 92%|█████████▏| 10798/11728 [2:42:52<1:35:22, 6.15s/it] 92%|█████████▏| 10799/11728 [2:42:58<1:32:59, 6.01s/it] {'loss': 0.4464, 'learning_rate': 3.2729444174507186e-07, 'epoch': 0.92} + 92%|█████████▏| 10799/11728 [2:42:58<1:32:59, 6.01s/it]1 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... +06 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... +47 AutoResumeHook: Checking whether to suspend...AutoResumeHook: Checking whether to suspend... + + 92%|█████████▏| 10800/11728 [2:43:03<1:31:00, 5.88s/it]2 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4605, 'learning_rate': 3.2659406294401566e-07, 'epoch': 0.92} + 92%|█████████▏| 10800/11728 [2:43:03<1:31:00, 5.88s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-10800/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-10800/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-10800/mm_projector +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/torch/nn/modules/module.py:1802: UserWarning: Positional args are being deprecated, use kwargs instead. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details. + warnings.warn( + 92%|█████████▏| 10801/11728 [2:43:36<3:35:10, 13.93s/it] {'loss': 0.4487, 'learning_rate': 3.2589442187728193e-07, 'epoch': 0.92} + 92%|█████████▏| 10801/11728 [2:43:36<3:35:10, 13.93s/it] 92%|█████████▏| 10802/11728 [2:43:42<2:56:35, 11.44s/it] {'loss': 0.4311, 'learning_rate': 3.2519551859822805e-07, 'epoch': 0.92} + 92%|█████████▏| 10802/11728 [2:43:42<2:56:35, 11.44s/it] 92%|█████████▏| 10803/11728 [2:43:48<2:32:16, 9.88s/it] {'loss': 0.4653, 'learning_rate': 3.2449735316015583e-07, 'epoch': 0.92} + 92%|█████████▏| 10803/11728 [2:43:48<2:32:16, 9.88s/it] 92%|█████████▏| 10804/11728 [2:43:53<2:12:33, 8.61s/it] {'loss': 0.4293, 'learning_rate': 3.237999256163071e-07, 'epoch': 0.92} + 92%|█████████▏| 10804/11728 [2:43:53<2:12:33, 8.61s/it] 92%|█████████▏| 10805/11728 [2:43:59<2:00:22, 7.83s/it] {'loss': 0.4505, 'learning_rate': 3.231032360198749e-07, 'epoch': 0.92} + 92%|█████████▏| 10805/11728 [2:43:59<2:00:22, 7.83s/it] 92%|█████████▏| 10806/11728 [2:44:05<1:51:28, 7.25s/it] {'loss': 0.4623, 'learning_rate': 3.2240728442399005e-07, 'epoch': 0.92} + 92%|█████████▏| 10806/11728 [2:44:05<1:51:28, 7.25s/it] 92%|█████████▏| 10807/11728 [2:44:11<1:45:04, 6.84s/it] {'loss': 0.4564, 'learning_rate': 3.2171207088172676e-07, 'epoch': 0.92} + 92%|█████████▏| 10807/11728 [2:44:11<1:45:04, 6.84s/it] 92%|█████████▏| 10808/11728 [2:44:17<1:40:44, 6.57s/it] {'loss': 0.4688, 'learning_rate': 3.210175954461081e-07, 'epoch': 0.92} + 92%|█████████▏| 10808/11728 [2:44:17<1:40:44, 6.57s/it] 92%|█████████▏| 10809/11728 [2:44:23<1:37:58, 6.40s/it] {'loss': 0.4513, 'learning_rate': 3.2032385817009514e-07, 'epoch': 0.92} + 92%|█████████▏| 10809/11728 [2:44:23<1:37:58, 6.40s/it] 92%|█████████▏| 10810/11728 [2:44:29<1:35:19, 6.23s/it] {'loss': 0.47, 'learning_rate': 3.196308591065966e-07, 'epoch': 0.92} + 92%|█████████▏| 10810/11728 [2:44:29<1:35:19, 6.23s/it] 92%|█████████▏| 10811/11728 [2:44:35<1:32:55, 6.08s/it] {'loss': 0.4418, 'learning_rate': 3.189385983084625e-07, 'epoch': 0.92} + 92%|█████████▏| 10811/11728 [2:44:35<1:32:55, 6.08s/it] 92%|█████████▏| 10812/11728 [2:44:41<1:33:02, 6.09s/it] {'loss': 0.4576, 'learning_rate': 3.1824707582848945e-07, 'epoch': 0.92} + 92%|█████████▏| 10812/11728 [2:44:41<1:33:02, 6.09s/it] 92%|█████████▏| 10813/11728 [2:44:47<1:30:49, 5.96s/it] {'loss': 0.4422, 'learning_rate': 3.1755629171941196e-07, 'epoch': 0.92} + 92%|█████████▏| 10813/11728 [2:44:47<1:30:49, 5.96s/it] 92%|█████████▏| 10814/11728 [2:44:53<1:31:07, 5.98s/it] {'loss': 0.4553, 'learning_rate': 3.168662460339167e-07, 'epoch': 0.92} + 92%|█████████▏| 10814/11728 [2:44:53<1:31:07, 5.98s/it] 92%|█████████▏| 10815/11728 [2:44:58<1:30:42, 5.96s/it] {'loss': 0.4629, 'learning_rate': 3.161769388246283e-07, 'epoch': 0.92} + 92%|█████████▏| 10815/11728 [2:44:58<1:30:42, 5.96s/it] 92%|█████████▏| 10816/11728 [2:45:04<1:29:50, 5.91s/it] {'loss': 0.4626, 'learning_rate': 3.154883701441136e-07, 'epoch': 0.92} + 92%|█████████▏| 10816/11728 [2:45:04<1:29:50, 5.91s/it] 92%|█████████▏| 10817/11728 [2:45:10<1:28:57, 5.86s/it] {'loss': 0.453, 'learning_rate': 3.1480054004488723e-07, 'epoch': 0.92} + 92%|█████████▏| 10817/11728 [2:45:10<1:28:57, 5.86s/it] 92%|█████████▏| 10818/11728 [2:45:16<1:27:58, 5.80s/it] {'loss': 0.4488, 'learning_rate': 3.141134485794073e-07, 'epoch': 0.92} + 92%|█████████▏| 10818/11728 [2:45:16<1:27:58, 5.80s/it] 92%|█████████▏| 10819/11728 [2:45:22<1:28:07, 5.82s/it] {'loss': 0.4527, 'learning_rate': 3.134270958000718e-07, 'epoch': 0.92} + 92%|█████████▏| 10819/11728 [2:45:22<1:28:07, 5.82s/it] 92%|█████████▏| 10820/11728 [2:45:27<1:27:09, 5.76s/it] {'loss': 0.4499, 'learning_rate': 3.127414817592278e-07, 'epoch': 0.92} + 92%|█████████▏| 10820/11728 [2:45:27<1:27:09, 5.76s/it] 92%|█████████▏| 10821/11728 [2:45:33<1:26:59, 5.75s/it] {'loss': 0.4657, 'learning_rate': 3.1205660650916127e-07, 'epoch': 0.92} + 92%|█████████▏| 10821/11728 [2:45:33<1:26:59, 5.75s/it] 92%|█████████▏| 10822/11728 [2:45:38<1:25:57, 5.69s/it] {'loss': 0.453, 'learning_rate': 3.113724701021026e-07, 'epoch': 0.92} + 92%|█████████▏| 10822/11728 [2:45:38<1:25:57, 5.69s/it] 92%|█████████▏| 10823/11728 [2:45:44<1:25:48, 5.69s/it] {'loss': 0.4477, 'learning_rate': 3.1068907259022786e-07, 'epoch': 0.92} + 92%|█████████▏| 10823/11728 [2:45:44<1:25:48, 5.69s/it] 92%|█████████▏| 10824/11728 [2:45:50<1:26:16, 5.73s/it] {'loss': 0.44, 'learning_rate': 3.1000641402565866e-07, 'epoch': 0.92} + 92%|█████████▏| 10824/11728 [2:45:50<1:26:16, 5.73s/it] 92%|█████████▏| 10825/11728 [2:45:56<1:27:39, 5.82s/it] {'loss': 0.457, 'learning_rate': 3.093244944604523e-07, 'epoch': 0.92} + 92%|█████████▏| 10825/11728 [2:45:56<1:27:39, 5.82s/it] 92%|█████████▏| 10826/11728 [2:46:02<1:26:07, 5.73s/it] {'loss': 0.4296, 'learning_rate': 3.086433139466183e-07, 'epoch': 0.92} + 92%|█████████▏| 10826/11728 [2:46:02<1:26:07, 5.73s/it] 92%|█████████▏| 10827/11728 [2:46:07<1:26:15, 5.74s/it] {'loss': 0.4454, 'learning_rate': 3.079628725361061e-07, 'epoch': 0.92} + 92%|█████████▏| 10827/11728 [2:46:07<1:26:15, 5.74s/it] 92%|█████████▏| 10828/11728 [2:46:14<1:28:21, 5.89s/it] {'loss': 0.4539, 'learning_rate': 3.0728317028080656e-07, 'epoch': 0.92} + 92%|█████████▏| 10828/11728 [2:46:14<1:28:21, 5.89s/it] 92%|█████████▏| 10829/11728 [2:46:19<1:27:59, 5.87s/it] {'loss': 0.4594, 'learning_rate': 3.066042072325592e-07, 'epoch': 0.92} + 92%|█████████▏| 10829/11728 [2:46:19<1:27:59, 5.87s/it] 92%|█████████▏| 10830/11728 [2:46:25<1:28:49, 5.93s/it] {'loss': 0.4462, 'learning_rate': 3.0592598344314495e-07, 'epoch': 0.92} + 92%|█████████▏| 10830/11728 [2:46:25<1:28:49, 5.93s/it] 92%|█████████▏| 10831/11728 [2:46:31<1:26:55, 5.81s/it] {'loss': 0.455, 'learning_rate': 3.0524849896428567e-07, 'epoch': 0.92} + 92%|█████████▏| 10831/11728 [2:46:31<1:26:55, 5.81s/it] 92%|█████████▏| 10832/11728 [2:46:37<1:27:03, 5.83s/it] {'loss': 0.4527, 'learning_rate': 3.0457175384764894e-07, 'epoch': 0.92} + 92%|█████████▏| 10832/11728 [2:46:37<1:27:03, 5.83s/it] 92%|█████████▏| 10833/11728 [2:46:43<1:27:24, 5.86s/it] {'loss': 0.4485, 'learning_rate': 3.0389574814485015e-07, 'epoch': 0.92} + 92%|█████████▏| 10833/11728 [2:46:43<1:27:24, 5.86s/it] 92%|█████████▏| 10834/11728 [2:46:49<1:27:50, 5.90s/it] {'loss': 0.4629, 'learning_rate': 3.0322048190744025e-07, 'epoch': 0.92} + 92%|█████████▏| 10834/11728 [2:46:49<1:27:50, 5.90s/it] 92%|█████████▏| 10835/11728 [2:46:55<1:28:04, 5.92s/it] {'loss': 0.4724, 'learning_rate': 3.025459551869192e-07, 'epoch': 0.92} + 92%|█████████▏| 10835/11728 [2:46:55<1:28:04, 5.92s/it] 92%|█████████▏| 10836/11728 [2:47:01<1:27:58, 5.92s/it] {'loss': 0.4465, 'learning_rate': 3.0187216803472805e-07, 'epoch': 0.92} + 92%|█████████▏| 10836/11728 [2:47:01<1:27:58, 5.92s/it] 92%|█████████▏| 10837/11728 [2:47:06<1:26:29, 5.82s/it] {'loss': 0.4374, 'learning_rate': 3.0119912050225576e-07, 'epoch': 0.92} + 92%|█████████▏| 10837/11728 [2:47:06<1:26:29, 5.82s/it] 92%|█████████▏| 10838/11728 [2:47:12<1:26:38, 5.84s/it] {'loss': 0.4513, 'learning_rate': 3.0052681264082895e-07, 'epoch': 0.92} + 92%|█████████▏| 10838/11728 [2:47:12<1:26:38, 5.84s/it] 92%|█████████▏| 10839/11728 [2:47:18<1:27:16, 5.89s/it] {'loss': 0.4478, 'learning_rate': 2.998552445017222e-07, 'epoch': 0.92} + 92%|█████████▏| 10839/11728 [2:47:18<1:27:16, 5.89s/it] 92%|█████████▏| 10840/11728 [2:47:24<1:26:09, 5.82s/it] {'loss': 0.4462, 'learning_rate': 2.991844161361512e-07, 'epoch': 0.92} + 92%|█████████▏| 10840/11728 [2:47:24<1:26:09, 5.82s/it] 92%|█████████▏| 10841/11728 [2:47:30<1:25:44, 5.80s/it] {'loss': 0.4585, 'learning_rate': 2.9851432759527397e-07, 'epoch': 0.92} + 92%|█████████▏| 10841/11728 [2:47:30<1:25:44, 5.80s/it] 92%|█████████▏| 10842/11728 [2:47:35<1:25:29, 5.79s/it] {'loss': 0.4467, 'learning_rate': 2.978449789301996e-07, 'epoch': 0.92} + 92%|█████████▏| 10842/11728 [2:47:35<1:25:29, 5.79s/it] 92%|█████████▏| 10843/11728 [2:47:41<1:25:09, 5.77s/it] {'loss': 0.4527, 'learning_rate': 2.9717637019197163e-07, 'epoch': 0.92} + 92%|█████████▏| 10843/11728 [2:47:41<1:25:09, 5.77s/it] 92%|█████████▏| 10844/11728 [2:47:47<1:26:19, 5.86s/it] {'loss': 0.463, 'learning_rate': 2.965085014315816e-07, 'epoch': 0.92} + 92%|█████████▏| 10844/11728 [2:47:47<1:26:19, 5.86s/it] 92%|█████████▏| 10845/11728 [2:47:53<1:26:12, 5.86s/it] {'loss': 0.4577, 'learning_rate': 2.958413726999632e-07, 'epoch': 0.92} + 92%|█████████▏| 10845/11728 [2:47:53<1:26:12, 5.86s/it] 92%|█████████▏| 10846/11728 [2:47:59<1:26:36, 5.89s/it] {'loss': 0.4464, 'learning_rate': 2.9517498404799674e-07, 'epoch': 0.92} + 92%|█████████▏| 10846/11728 [2:47:59<1:26:36, 5.89s/it] 92%|█████████▏| 10847/11728 [2:48:05<1:25:35, 5.83s/it] {'loss': 0.4518, 'learning_rate': 2.9450933552650163e-07, 'epoch': 0.92} + 92%|█████████▏| 10847/11728 [2:48:05<1:25:35, 5.83s/it] 92%|█████████▏| 10848/11728 [2:48:11<1:25:53, 5.86s/it] {'loss': 0.4506, 'learning_rate': 2.9384442718624397e-07, 'epoch': 0.92} + 92%|█████████▏| 10848/11728 [2:48:11<1:25:53, 5.86s/it] 93%|█████████▎| 10849/11728 [2:48:16<1:25:26, 5.83s/it] {'loss': 0.4628, 'learning_rate': 2.9318025907793314e-07, 'epoch': 0.93} + 93%|█████████▎| 10849/11728 [2:48:16<1:25:26, 5.83s/it]54 AutoResumeHook: Checking whether to suspend... +AutoResumeHook: Checking whether to suspend... +17 AutoResumeHook: Checking whether to suspend...AutoResumeHook: Checking whether to suspend... + +6 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... +0 AutoResumeHook: Checking whether to suspend... + 93%|█████████▎| 10850/11728 [2:48:22<1:26:52, 5.94s/it]2 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4484, 'learning_rate': 2.9251683125221864e-07, 'epoch': 0.93} + 93%|█████████▎| 10850/11728 [2:48:22<1:26:52, 5.94s/it] 93%|█████████▎| 10851/11728 [2:48:28<1:25:52, 5.87s/it] {'loss': 0.4432, 'learning_rate': 2.918541437597e-07, 'epoch': 0.93} + 93%|█████████▎| 10851/11728 [2:48:28<1:25:52, 5.87s/it] 93%|█████████▎| 10852/11728 [2:48:34<1:24:30, 5.79s/it] {'loss': 0.4581, 'learning_rate': 2.9119219665091345e-07, 'epoch': 0.93} + 93%|█████████▎| 10852/11728 [2:48:34<1:24:30, 5.79s/it] 93%|█████████▎| 10853/11728 [2:48:40<1:25:38, 5.87s/it] {'loss': 0.4439, 'learning_rate': 2.905309899763431e-07, 'epoch': 0.93} + 93%|█████████▎| 10853/11728 [2:48:40<1:25:38, 5.87s/it] 93%|█████████▎| 10854/11728 [2:48:46<1:26:08, 5.91s/it] {'loss': 0.4493, 'learning_rate': 2.898705237864152e-07, 'epoch': 0.93} + 93%|█████████▎| 10854/11728 [2:48:46<1:26:08, 5.91s/it] 93%|█████████▎| 10855/11728 [2:48:52<1:25:22, 5.87s/it] {'loss': 0.4408, 'learning_rate': 2.8921079813150066e-07, 'epoch': 0.93} + 93%|█████████▎| 10855/11728 [2:48:52<1:25:22, 5.87s/it] 93%|█████████▎| 10856/11728 [2:48:58<1:26:35, 5.96s/it] {'loss': 0.4507, 'learning_rate': 2.8855181306191137e-07, 'epoch': 0.93} + 93%|█████████▎| 10856/11728 [2:48:58<1:26:35, 5.96s/it] 93%|█████████▎| 10857/11728 [2:49:04<1:26:02, 5.93s/it] {'loss': 0.4679, 'learning_rate': 2.87893568627905e-07, 'epoch': 0.93} + 93%|█████████▎| 10857/11728 [2:49:04<1:26:02, 5.93s/it] 93%|█████████▎| 10858/11728 [2:49:10<1:28:07, 6.08s/it] {'loss': 0.4614, 'learning_rate': 2.8723606487968235e-07, 'epoch': 0.93} + 93%|█████████▎| 10858/11728 [2:49:10<1:28:07, 6.08s/it] 93%|█████████▎| 10859/11728 [2:49:16<1:27:21, 6.03s/it] {'loss': 0.4448, 'learning_rate': 2.865793018673857e-07, 'epoch': 0.93} + 93%|█████████▎| 10859/11728 [2:49:16<1:27:21, 6.03s/it] 93%|█████████▎| 10860/11728 [2:49:22<1:26:20, 5.97s/it] {'loss': 0.4648, 'learning_rate': 2.859232796411049e-07, 'epoch': 0.93} + 93%|█████████▎| 10860/11728 [2:49:22<1:26:20, 5.97s/it] 93%|█████████▎| 10861/11728 [2:49:27<1:23:50, 5.80s/it] {'loss': 0.4605, 'learning_rate': 2.8526799825086993e-07, 'epoch': 0.93} + 93%|█████████▎| 10861/11728 [2:49:27<1:23:50, 5.80s/it] 93%|█████████▎| 10862/11728 [2:49:33<1:23:51, 5.81s/it] {'loss': 0.4526, 'learning_rate': 2.8461345774665414e-07, 'epoch': 0.93} + 93%|█████████▎| 10862/11728 [2:49:33<1:23:51, 5.81s/it] 93%|█████████▎| 10863/11728 [2:49:39<1:23:37, 5.80s/it] {'loss': 0.453, 'learning_rate': 2.8395965817837766e-07, 'epoch': 0.93} + 93%|█████████▎| 10863/11728 [2:49:39<1:23:37, 5.80s/it] 93%|█████████▎| 10864/11728 [2:49:44<1:22:22, 5.72s/it] {'loss': 0.461, 'learning_rate': 2.8330659959589944e-07, 'epoch': 0.93} + 93%|█████████▎| 10864/11728 [2:49:44<1:22:22, 5.72s/it] 93%|█████████▎| 10865/11728 [2:49:50<1:22:48, 5.76s/it] {'loss': 0.4615, 'learning_rate': 2.8265428204902746e-07, 'epoch': 0.93} + 93%|█████████▎| 10865/11728 [2:49:50<1:22:48, 5.76s/it] 93%|█████████▎| 10866/11728 [2:49:56<1:24:04, 5.85s/it] {'loss': 0.4408, 'learning_rate': 2.8200270558750743e-07, 'epoch': 0.93} + 93%|█████████▎| 10866/11728 [2:49:56<1:24:04, 5.85s/it] 93%|█████████▎| 10867/11728 [2:50:02<1:23:35, 5.83s/it] {'loss': 0.4709, 'learning_rate': 2.8135187026103403e-07, 'epoch': 0.93} + 93%|█████████▎| 10867/11728 [2:50:02<1:23:35, 5.83s/it] 93%|█████████▎| 10868/11728 [2:50:08<1:23:44, 5.84s/it] {'loss': 0.4721, 'learning_rate': 2.807017761192399e-07, 'epoch': 0.93} + 93%|█████████▎| 10868/11728 [2:50:08<1:23:44, 5.84s/it] 93%|█████████▎| 10869/11728 [2:50:13<1:21:45, 5.71s/it] {'loss': 0.4391, 'learning_rate': 2.8005242321170633e-07, 'epoch': 0.93} + 93%|█████████▎| 10869/11728 [2:50:13<1:21:45, 5.71s/it] 93%|█████████▎| 10870/11728 [2:50:19<1:22:32, 5.77s/it] {'loss': 0.4762, 'learning_rate': 2.794038115879538e-07, 'epoch': 0.93} + 93%|█████████▎| 10870/11728 [2:50:19<1:22:32, 5.77s/it] 93%|█████████▎| 10871/11728 [2:50:25<1:22:32, 5.78s/it] {'loss': 0.4436, 'learning_rate': 2.787559412974483e-07, 'epoch': 0.93} + 93%|█████████▎| 10871/11728 [2:50:25<1:22:32, 5.78s/it] 93%|█████████▎| 10872/11728 [2:50:31<1:22:53, 5.81s/it] {'loss': 0.4365, 'learning_rate': 2.781088123896003e-07, 'epoch': 0.93} + 93%|█████████▎| 10872/11728 [2:50:31<1:22:53, 5.81s/it] 93%|█████████▎| 10873/11728 [2:50:37<1:22:31, 5.79s/it] {'loss': 0.4727, 'learning_rate': 2.774624249137614e-07, 'epoch': 0.93} + 93%|█████████▎| 10873/11728 [2:50:37<1:22:31, 5.79s/it] 93%|█████████▎| 10874/11728 [2:50:42<1:21:51, 5.75s/it] {'loss': 0.4587, 'learning_rate': 2.7681677891922887e-07, 'epoch': 0.93} + 93%|█████████▎| 10874/11728 [2:50:42<1:21:51, 5.75s/it] 93%|█████████▎| 10875/11728 [2:50:48<1:20:45, 5.68s/it] {'loss': 0.4572, 'learning_rate': 2.761718744552422e-07, 'epoch': 0.93} + 93%|█████████▎| 10875/11728 [2:50:48<1:20:45, 5.68s/it] 93%|█████████▎| 10876/11728 [2:50:54<1:22:46, 5.83s/it] {'loss': 0.4392, 'learning_rate': 2.755277115709842e-07, 'epoch': 0.93} + 93%|█████████▎| 10876/11728 [2:50:54<1:22:46, 5.83s/it] 93%|█████████▎| 10877/11728 [2:51:00<1:24:10, 5.94s/it] {'loss': 0.4541, 'learning_rate': 2.7488429031558016e-07, 'epoch': 0.93} + 93%|█████████▎| 10877/11728 [2:51:00<1:24:10, 5.94s/it] 93%|█████████▎| 10878/11728 [2:51:06<1:23:17, 5.88s/it] {'loss': 0.4473, 'learning_rate': 2.7424161073810183e-07, 'epoch': 0.93} + 93%|█████████▎| 10878/11728 [2:51:06<1:23:17, 5.88s/it] 93%|█████████▎| 10879/11728 [2:51:12<1:22:38, 5.84s/it] {'loss': 0.4477, 'learning_rate': 2.735996728875623e-07, 'epoch': 0.93} + 93%|█████████▎| 10879/11728 [2:51:12<1:22:38, 5.84s/it] 93%|█████████▎| 10880/11728 [2:51:17<1:21:51, 5.79s/it] {'loss': 0.4554, 'learning_rate': 2.7295847681291897e-07, 'epoch': 0.93} + 93%|█████████▎| 10880/11728 [2:51:17<1:21:51, 5.79s/it] 93%|█████████▎| 10881/11728 [2:51:23<1:21:09, 5.75s/it] {'loss': 0.4646, 'learning_rate': 2.723180225630695e-07, 'epoch': 0.93} + 93%|█████████▎| 10881/11728 [2:51:23<1:21:09, 5.75s/it] 93%|█████████▎| 10882/11728 [2:51:29<1:20:44, 5.73s/it] {'loss': 0.4902, 'learning_rate': 2.716783101868614e-07, 'epoch': 0.93} + 93%|█████████▎| 10882/11728 [2:51:29<1:20:44, 5.73s/it] 93%|█████████▎| 10883/11728 [2:51:34<1:20:33, 5.72s/it] {'loss': 0.4533, 'learning_rate': 2.7103933973307796e-07, 'epoch': 0.93} + 93%|█████████▎| 10883/11728 [2:51:34<1:20:33, 5.72s/it] 93%|█████████▎| 10884/11728 [2:51:41<1:22:23, 5.86s/it] {'loss': 0.4447, 'learning_rate': 2.7040111125045345e-07, 'epoch': 0.93} + 93%|█████████▎| 10884/11728 [2:51:41<1:22:23, 5.86s/it] 93%|█████████▎| 10885/11728 [2:51:47<1:22:45, 5.89s/it] {'loss': 0.4466, 'learning_rate': 2.6976362478766003e-07, 'epoch': 0.93} + 93%|█████████▎| 10885/11728 [2:51:47<1:22:45, 5.89s/it] 93%|█████████▎| 10886/11728 [2:51:52<1:21:45, 5.83s/it] {'loss': 0.4382, 'learning_rate': 2.691268803933145e-07, 'epoch': 0.93} + 93%|█████████▎| 10886/11728 [2:51:52<1:21:45, 5.83s/it] 93%|█████████▎| 10887/11728 [2:51:58<1:21:25, 5.81s/it] {'loss': 0.4655, 'learning_rate': 2.6849087811597787e-07, 'epoch': 0.93} + 93%|█████████▎| 10887/11728 [2:51:58<1:21:25, 5.81s/it] 93%|█████████▎| 10888/11728 [2:52:04<1:21:19, 5.81s/it] {'loss': 0.4502, 'learning_rate': 2.678556180041547e-07, 'epoch': 0.93} + 93%|█████████▎| 10888/11728 [2:52:04<1:21:19, 5.81s/it] 93%|█████████▎| 10889/11728 [2:52:10<1:20:57, 5.79s/it] {'loss': 0.4517, 'learning_rate': 2.67221100106293e-07, 'epoch': 0.93} + 93%|█████████▎| 10889/11728 [2:52:10<1:20:57, 5.79s/it] 93%|█████████▎| 10890/11728 [2:52:16<1:23:37, 5.99s/it] {'loss': 0.44, 'learning_rate': 2.6658732447078286e-07, 'epoch': 0.93} + 93%|█████████▎| 10890/11728 [2:52:16<1:23:37, 5.99s/it] 93%|█████████▎| 10891/11728 [2:52:22<1:23:02, 5.95s/it] {'loss': 0.4694, 'learning_rate': 2.6595429114595894e-07, 'epoch': 0.93} + 93%|█████████▎| 10891/11728 [2:52:22<1:23:02, 5.95s/it] 93%|█████████▎| 10892/11728 [2:52:28<1:22:10, 5.90s/it] {'loss': 0.4388, 'learning_rate': 2.653220001801005e-07, 'epoch': 0.93} + 93%|█████████▎| 10892/11728 [2:52:28<1:22:10, 5.90s/it] 93%|█████████▎| 10893/11728 [2:52:33<1:20:59, 5.82s/it] {'loss': 0.4509, 'learning_rate': 2.646904516214266e-07, 'epoch': 0.93} + 93%|█████████▎| 10893/11728 [2:52:33<1:20:59, 5.82s/it] 93%|█████████▎| 10894/11728 [2:52:39<1:21:44, 5.88s/it] {'loss': 0.4457, 'learning_rate': 2.6405964551810325e-07, 'epoch': 0.93} + 93%|█████████▎| 10894/11728 [2:52:39<1:21:44, 5.88s/it] 93%|█████████▎| 10895/11728 [2:52:45<1:21:44, 5.89s/it] {'loss': 0.4393, 'learning_rate': 2.6342958191823643e-07, 'epoch': 0.93} + 93%|█████████▎| 10895/11728 [2:52:45<1:21:44, 5.89s/it] 93%|█████████▎| 10896/11728 [2:52:51<1:20:41, 5.82s/it] {'loss': 0.4579, 'learning_rate': 2.6280026086987985e-07, 'epoch': 0.93} + 93%|█████████▎| 10896/11728 [2:52:51<1:20:41, 5.82s/it] 93%|█████████▎| 10897/11728 [2:52:57<1:20:09, 5.79s/it] {'loss': 0.4432, 'learning_rate': 2.621716824210263e-07, 'epoch': 0.93} + 93%|█████████▎| 10897/11728 [2:52:57<1:20:09, 5.79s/it] 93%|█████████▎| 10898/11728 [2:53:02<1:19:15, 5.73s/it] {'loss': 0.4409, 'learning_rate': 2.6154384661961405e-07, 'epoch': 0.93} + 93%|█████████▎| 10898/11728 [2:53:02<1:19:15, 5.73s/it] 93%|█████████▎| 10899/11728 [2:53:08<1:18:42, 5.70s/it] {'loss': 0.4484, 'learning_rate': 2.6091675351352485e-07, 'epoch': 0.93} + 93%|█████████▎| 10899/11728 [2:53:08<1:18:42, 5.70s/it]0 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... + 93%|█████████▎| 10900/11728 [2:53:14<1:18:56, 5.72s/it]1 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend...7 + AutoResumeHook: Checking whether to suspend... + {'loss': 0.4707, 'learning_rate': 2.6029040315058487e-07, 'epoch': 0.93} + 93%|█████████▎| 10900/11728 [2:53:14<1:18:56, 5.72s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-10900/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-10900/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-10900/mm_projector +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/torch/nn/modules/module.py:1802: UserWarning: Positional args are being deprecated, use kwargs instead. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details. + warnings.warn( + 93%|█████████▎| 10901/11728 [2:53:49<3:20:34, 14.55s/it] {'loss': 0.4309, 'learning_rate': 2.5966479557855914e-07, 'epoch': 0.93} + 93%|█████████▎| 10901/11728 [2:53:49<3:20:34, 14.55s/it] 93%|█████████▎| 10902/11728 [2:53:55<2:45:25, 12.02s/it] {'loss': 0.4475, 'learning_rate': 2.5903993084516077e-07, 'epoch': 0.93} + 93%|█████████▎| 10902/11728 [2:53:55<2:45:25, 12.02s/it] 93%|█████████▎| 10903/11728 [2:54:01<2:19:17, 10.13s/it] {'loss': 0.4383, 'learning_rate': 2.5841580899804706e-07, 'epoch': 0.93} + 93%|█████████▎| 10903/11728 [2:54:01<2:19:17, 10.13s/it] 93%|█████████▎| 10904/11728 [2:54:06<2:00:56, 8.81s/it] {'loss': 0.4722, 'learning_rate': 2.5779243008481114e-07, 'epoch': 0.93} + 93%|█████████▎| 10904/11728 [2:54:06<2:00:56, 8.81s/it] 93%|█████████▎| 10905/11728 [2:54:12<1:47:45, 7.86s/it] {'loss': 0.4388, 'learning_rate': 2.5716979415299714e-07, 'epoch': 0.93} + 93%|█████████▎| 10905/11728 [2:54:12<1:47:45, 7.86s/it] 93%|█████████▎| 10906/11728 [2:54:18<1:39:11, 7.24s/it] {'loss': 0.4364, 'learning_rate': 2.565479012500915e-07, 'epoch': 0.93} + 93%|█████████▎| 10906/11728 [2:54:18<1:39:11, 7.24s/it] 93%|█████████▎| 10907/11728 [2:54:24<1:33:04, 6.80s/it] {'loss': 0.4683, 'learning_rate': 2.5592675142351865e-07, 'epoch': 0.93} + 93%|█████████▎| 10907/11728 [2:54:24<1:33:04, 6.80s/it] 93%|█████████▎| 10908/11728 [2:54:29<1:28:35, 6.48s/it] {'loss': 0.4362, 'learning_rate': 2.553063447206527e-07, 'epoch': 0.93} + 93%|█████████▎| 10908/11728 [2:54:29<1:28:35, 6.48s/it] 93%|█████████▎| 10909/11728 [2:54:35<1:25:34, 6.27s/it] {'loss': 0.4706, 'learning_rate': 2.5468668118880935e-07, 'epoch': 0.93} + 93%|█████████▎| 10909/11728 [2:54:35<1:25:34, 6.27s/it] 93%|█████████▎| 10910/11728 [2:54:41<1:23:18, 6.11s/it] {'loss': 0.4553, 'learning_rate': 2.540677608752429e-07, 'epoch': 0.93} + 93%|█████████▎| 10910/11728 [2:54:41<1:23:18, 6.11s/it] 93%|█████████▎| 10911/11728 [2:54:46<1:21:30, 5.99s/it] {'loss': 0.4531, 'learning_rate': 2.534495838271578e-07, 'epoch': 0.93} + 93%|█████████▎| 10911/11728 [2:54:46<1:21:30, 5.99s/it] 93%|█████████▎| 10912/11728 [2:54:52<1:20:49, 5.94s/it] {'loss': 0.4502, 'learning_rate': 2.528321500916986e-07, 'epoch': 0.93} + 93%|█████████▎| 10912/11728 [2:54:52<1:20:49, 5.94s/it] 93%|█████████▎| 10913/11728 [2:54:58<1:20:33, 5.93s/it] {'loss': 0.4777, 'learning_rate': 2.5221545971595207e-07, 'epoch': 0.93} + 93%|█████████▎| 10913/11728 [2:54:58<1:20:33, 5.93s/it] 93%|█████████▎| 10914/11728 [2:55:04<1:19:43, 5.88s/it] {'loss': 0.445, 'learning_rate': 2.5159951274694947e-07, 'epoch': 0.93} + 93%|█████████▎| 10914/11728 [2:55:04<1:19:43, 5.88s/it] 93%|█████████▎| 10915/11728 [2:55:09<1:18:13, 5.77s/it] {'loss': 0.4549, 'learning_rate': 2.509843092316688e-07, 'epoch': 0.93} + 93%|█████████▎| 10915/11728 [2:55:09<1:18:13, 5.77s/it] 93%|█████████▎| 10916/11728 [2:55:15<1:17:34, 5.73s/it] {'loss': 0.4535, 'learning_rate': 2.503698492170237e-07, 'epoch': 0.93} + 93%|█████████▎| 10916/11728 [2:55:15<1:17:34, 5.73s/it] 93%|█████████▎| 10917/11728 [2:55:21<1:17:09, 5.71s/it] {'loss': 0.4606, 'learning_rate': 2.497561327498788e-07, 'epoch': 0.93} + 93%|█████████▎| 10917/11728 [2:55:21<1:17:09, 5.71s/it] 93%|█████████▎| 10918/11728 [2:55:27<1:17:33, 5.75s/it] {'loss': 0.4436, 'learning_rate': 2.4914315987703664e-07, 'epoch': 0.93} + 93%|█████████▎| 10918/11728 [2:55:27<1:17:33, 5.75s/it] 93%|█████████▎| 10919/11728 [2:55:33<1:19:10, 5.87s/it] {'loss': 0.452, 'learning_rate': 2.4853093064524434e-07, 'epoch': 0.93} + 93%|█████████▎| 10919/11728 [2:55:33<1:19:10, 5.87s/it] 93%|█████████▎| 10920/11728 [2:55:39<1:18:48, 5.85s/it] {'loss': 0.4697, 'learning_rate': 2.479194451011957e-07, 'epoch': 0.93} + 93%|█████████▎| 10920/11728 [2:55:39<1:18:48, 5.85s/it] 93%|█████████▎| 10921/11728 [2:55:44<1:17:52, 5.79s/it] {'loss': 0.4624, 'learning_rate': 2.4730870329152557e-07, 'epoch': 0.93} + 93%|█████████▎| 10921/11728 [2:55:44<1:17:52, 5.79s/it] 93%|█████████▎| 10922/11728 [2:55:50<1:18:17, 5.83s/it] {'loss': 0.4499, 'learning_rate': 2.466987052628078e-07, 'epoch': 0.93} + 93%|█████████▎| 10922/11728 [2:55:50<1:18:17, 5.83s/it] 93%|█████████▎| 10923/11728 [2:55:56<1:17:23, 5.77s/it] {'loss': 0.4677, 'learning_rate': 2.4608945106156524e-07, 'epoch': 0.93} + 93%|█████████▎| 10923/11728 [2:55:56<1:17:23, 5.77s/it] 93%|█████████▎| 10924/11728 [2:56:02<1:18:06, 5.83s/it] {'loss': 0.4209, 'learning_rate': 2.45480940734264e-07, 'epoch': 0.93} + 93%|█████████▎| 10924/11728 [2:56:02<1:18:06, 5.83s/it] 93%|█████████▎| 10925/11728 [2:56:08<1:18:26, 5.86s/it] {'loss': 0.4617, 'learning_rate': 2.4487317432730917e-07, 'epoch': 0.93} + 93%|█████████▎| 10925/11728 [2:56:08<1:18:26, 5.86s/it] 93%|█████████▎| 10926/11728 [2:56:13<1:17:16, 5.78s/it] {'loss': 0.4745, 'learning_rate': 2.442661518870526e-07, 'epoch': 0.93} + 93%|█████████▎| 10926/11728 [2:56:13<1:17:16, 5.78s/it] 93%|█████████▎| 10927/11728 [2:56:19<1:16:28, 5.73s/it] {'loss': 0.4456, 'learning_rate': 2.4365987345978946e-07, 'epoch': 0.93} + 93%|█████████▎| 10927/11728 [2:56:19<1:16:28, 5.73s/it] 93%|█████████▎| 10928/11728 [2:56:25<1:16:28, 5.74s/it] {'loss': 0.4683, 'learning_rate': 2.430543390917539e-07, 'epoch': 0.93} + 93%|█████████▎| 10928/11728 [2:56:25<1:16:28, 5.74s/it] 93%|█████████▎| 10929/11728 [2:56:31<1:17:14, 5.80s/it] {'loss': 0.4511, 'learning_rate': 2.4244954882912895e-07, 'epoch': 0.93} + 93%|█████████▎| 10929/11728 [2:56:31<1:17:14, 5.80s/it] 93%|█████████▎| 10930/11728 [2:56:36<1:17:26, 5.82s/it] {'loss': 0.4572, 'learning_rate': 2.418455027180389e-07, 'epoch': 0.93} + 93%|█████████▎| 10930/11728 [2:56:36<1:17:26, 5.82s/it] 93%|█████████▎| 10931/11728 [2:56:43<1:18:47, 5.93s/it] {'loss': 0.4276, 'learning_rate': 2.4124220080455006e-07, 'epoch': 0.93} + 93%|█████████▎| 10931/11728 [2:56:43<1:18:47, 5.93s/it] 93%|█████████▎| 10932/11728 [2:56:49<1:18:46, 5.94s/it] {'loss': 0.4566, 'learning_rate': 2.4063964313467135e-07, 'epoch': 0.93} + 93%|█████████▎| 10932/11728 [2:56:49<1:18:46, 5.94s/it] 93%|█████████▎| 10933/11728 [2:56:55<1:18:46, 5.94s/it] {'loss': 0.4477, 'learning_rate': 2.400378297543582e-07, 'epoch': 0.93} + 93%|█████████▎| 10933/11728 [2:56:55<1:18:46, 5.94s/it] 93%|█████████▎| 10934/11728 [2:57:00<1:18:18, 5.92s/it] {'loss': 0.4399, 'learning_rate': 2.3943676070950606e-07, 'epoch': 0.93} + 93%|█████████▎| 10934/11728 [2:57:00<1:18:18, 5.92s/it] 93%|█████████▎| 10935/11728 [2:57:06<1:16:52, 5.82s/it] {'loss': 0.4562, 'learning_rate': 2.3883643604595607e-07, 'epoch': 0.93} + 93%|█████████▎| 10935/11728 [2:57:06<1:16:52, 5.82s/it] 93%|█████████▎| 10936/11728 [2:57:12<1:17:45, 5.89s/it] {'loss': 0.4639, 'learning_rate': 2.3823685580949273e-07, 'epoch': 0.93} + 93%|█████████▎| 10936/11728 [2:57:12<1:17:45, 5.89s/it] 93%|█████████▎| 10937/11728 [2:57:18<1:16:39, 5.81s/it] {'loss': 0.4601, 'learning_rate': 2.3763802004583835e-07, 'epoch': 0.93} + 93%|█████████▎| 10937/11728 [2:57:18<1:16:39, 5.81s/it] 93%|█████████▎| 10938/11728 [2:57:24<1:16:38, 5.82s/it] {'loss': 0.4415, 'learning_rate': 2.370399288006664e-07, 'epoch': 0.93} + 93%|█████████▎| 10938/11728 [2:57:24<1:16:38, 5.82s/it] 93%|█████████▎| 10939/11728 [2:57:30<1:17:09, 5.87s/it] {'loss': 0.4355, 'learning_rate': 2.3644258211958926e-07, 'epoch': 0.93} + 93%|█████████▎| 10939/11728 [2:57:30<1:17:09, 5.87s/it] 93%|█████████▎| 10940/11728 [2:57:36<1:18:22, 5.97s/it] {'loss': 0.447, 'learning_rate': 2.3584598004816162e-07, 'epoch': 0.93} + 93%|█████████▎| 10940/11728 [2:57:36<1:18:22, 5.97s/it] 93%|█████████▎| 10941/11728 [2:57:41<1:16:49, 5.86s/it] {'loss': 0.4539, 'learning_rate': 2.3525012263188373e-07, 'epoch': 0.93} + 93%|█████████▎| 10941/11728 [2:57:41<1:16:49, 5.86s/it] 93%|█████████▎| 10942/11728 [2:57:47<1:15:20, 5.75s/it] {'loss': 0.4374, 'learning_rate': 2.3465500991619815e-07, 'epoch': 0.93} + 93%|█████████▎| 10942/11728 [2:57:47<1:15:20, 5.75s/it] 93%|█████████▎| 10943/11728 [2:57:53<1:15:06, 5.74s/it] {'loss': 0.4357, 'learning_rate': 2.340606419464897e-07, 'epoch': 0.93} + 93%|█████████▎| 10943/11728 [2:57:53<1:15:06, 5.74s/it] 93%|█████████▎| 10944/11728 [2:57:58<1:14:42, 5.72s/it] {'loss': 0.4678, 'learning_rate': 2.3346701876808987e-07, 'epoch': 0.93} + 93%|█████████▎| 10944/11728 [2:57:58<1:14:42, 5.72s/it] 93%|█████████▎| 10945/11728 [2:58:04<1:13:59, 5.67s/it] {'loss': 0.4749, 'learning_rate': 2.328741404262691e-07, 'epoch': 0.93} + 93%|█████████▎| 10945/11728 [2:58:04<1:13:59, 5.67s/it] 93%|█████████▎| 10946/11728 [2:58:09<1:13:18, 5.62s/it] {'loss': 0.4584, 'learning_rate': 2.3228200696624125e-07, 'epoch': 0.93} + 93%|█████████▎| 10946/11728 [2:58:09<1:13:18, 5.62s/it] 93%|█████████▎| 10947/11728 [2:58:15<1:14:56, 5.76s/it] {'loss': 0.4437, 'learning_rate': 2.3169061843316688e-07, 'epoch': 0.93} + 93%|█████████▎| 10947/11728 [2:58:15<1:14:56, 5.76s/it] 93%|█████████▎| 10948/11728 [2:58:21<1:15:14, 5.79s/it] {'loss': 0.4559, 'learning_rate': 2.3109997487214987e-07, 'epoch': 0.93} + 93%|█████████▎| 10948/11728 [2:58:21<1:15:14, 5.79s/it] 93%|█████████▎| 10949/11728 [2:58:27<1:14:18, 5.72s/it] {'loss': 0.4641, 'learning_rate': 2.3051007632823085e-07, 'epoch': 0.93} + 93%|█████████▎| 10949/11728 [2:58:27<1:14:18, 5.72s/it]32 AutoResumeHook: Checking whether to suspend...AutoResumeHook: Checking whether to suspend... + +04 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... + 93%|█████████▎| 10950/11728 [2:58:33<1:15:54, 5.85s/it]1 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4333, 'learning_rate': 2.2992092284639944e-07, 'epoch': 0.93} + 93%|█████████▎| 10950/11728 [2:58:33<1:15:54, 5.85s/it] 93%|█████████▎| 10951/11728 [2:58:39<1:15:00, 5.79s/it] {'loss': 0.4453, 'learning_rate': 2.2933251447158744e-07, 'epoch': 0.93} + 93%|█████████▎| 10951/11728 [2:58:39<1:15:00, 5.79s/it] 93%|█████████▎| 10952/11728 [2:58:44<1:14:55, 5.79s/it] {'loss': 0.4492, 'learning_rate': 2.2874485124867007e-07, 'epoch': 0.93} + 93%|█████████▎| 10952/11728 [2:58:44<1:14:55, 5.79s/it] 93%|█████████▎| 10953/11728 [2:58:50<1:15:18, 5.83s/it] {'loss': 0.4592, 'learning_rate': 2.281579332224626e-07, 'epoch': 0.93} + 93%|█████████▎| 10953/11728 [2:58:50<1:15:18, 5.83s/it] 93%|█████████▎| 10954/11728 [2:58:56<1:14:33, 5.78s/it] {'loss': 0.4332, 'learning_rate': 2.275717604377292e-07, 'epoch': 0.93} + 93%|█████████▎| 10954/11728 [2:58:56<1:14:33, 5.78s/it] 93%|█████████▎| 10955/11728 [2:59:02<1:15:30, 5.86s/it] {'loss': 0.4594, 'learning_rate': 2.2698633293917193e-07, 'epoch': 0.93} + 93%|█████████▎| 10955/11728 [2:59:02<1:15:30, 5.86s/it] 93%|█████████▎| 10956/11728 [2:59:08<1:15:36, 5.88s/it] {'loss': 0.4852, 'learning_rate': 2.2640165077143618e-07, 'epoch': 0.93} + 93%|█████████▎| 10956/11728 [2:59:08<1:15:36, 5.88s/it] 93%|█████████▎| 10957/11728 [2:59:14<1:16:48, 5.98s/it] {'loss': 0.4415, 'learning_rate': 2.2581771397911512e-07, 'epoch': 0.93} + 93%|█████████▎| 10957/11728 [2:59:14<1:16:48, 5.98s/it] 93%|█████████▎| 10958/11728 [2:59:20<1:16:11, 5.94s/it] {'loss': 0.4633, 'learning_rate': 2.2523452260674207e-07, 'epoch': 0.93} + 93%|█████████▎| 10958/11728 [2:59:20<1:16:11, 5.94s/it] 93%|█████████▎| 10959/11728 [2:59:26<1:16:13, 5.95s/it] {'loss': 0.4636, 'learning_rate': 2.246520766987914e-07, 'epoch': 0.93} + 93%|█████████▎| 10959/11728 [2:59:26<1:16:13, 5.95s/it] 93%|█████████▎| 10960/11728 [2:59:32<1:15:46, 5.92s/it] {'loss': 0.4401, 'learning_rate': 2.2407037629968431e-07, 'epoch': 0.93} + 93%|█████████▎| 10960/11728 [2:59:32<1:15:46, 5.92s/it] 93%|█████████▎| 10961/11728 [2:59:37<1:14:37, 5.84s/it] {'loss': 0.4451, 'learning_rate': 2.2348942145378415e-07, 'epoch': 0.93} + 93%|█████████▎| 10961/11728 [2:59:37<1:14:37, 5.84s/it] 93%|█████████▎| 10962/11728 [2:59:43<1:13:22, 5.75s/it] {'loss': 0.4524, 'learning_rate': 2.2290921220539662e-07, 'epoch': 0.93} + 93%|█████████▎| 10962/11728 [2:59:43<1:13:22, 5.75s/it] 93%|█████████▎| 10963/11728 [2:59:49<1:13:31, 5.77s/it] {'loss': 0.4527, 'learning_rate': 2.2232974859877076e-07, 'epoch': 0.93} + 93%|█████████▎| 10963/11728 [2:59:49<1:13:31, 5.77s/it] 93%|█████████▎| 10964/11728 [2:59:58<1:25:54, 6.75s/it] {'loss': 0.4699, 'learning_rate': 2.2175103067809788e-07, 'epoch': 0.93} + 93%|█████████▎| 10964/11728 [2:59:58<1:25:54, 6.75s/it] 93%|█████████▎| 10965/11728 [3:00:04<1:22:14, 6.47s/it] {'loss': 0.4765, 'learning_rate': 2.211730584875138e-07, 'epoch': 0.93} + 93%|█████████▎| 10965/11728 [3:00:04<1:22:14, 6.47s/it] 94%|█████████▎| 10966/11728 [3:00:10<1:20:03, 6.30s/it] {'loss': 0.4437, 'learning_rate': 2.2059583207109992e-07, 'epoch': 0.94} + 94%|█████████▎| 10966/11728 [3:00:10<1:20:03, 6.30s/it] 94%|█████████▎| 10967/11728 [3:00:16<1:19:05, 6.24s/it] {'loss': 0.4708, 'learning_rate': 2.2001935147287434e-07, 'epoch': 0.94} + 94%|█████████▎| 10967/11728 [3:00:16<1:19:05, 6.24s/it] 94%|█████████▎| 10968/11728 [3:00:21<1:16:37, 6.05s/it] {'loss': 0.4577, 'learning_rate': 2.1944361673680304e-07, 'epoch': 0.94} + 94%|█████████▎| 10968/11728 [3:00:21<1:16:37, 6.05s/it] 94%|█████████▎| 10969/11728 [3:00:27<1:15:04, 5.94s/it] {'loss': 0.4519, 'learning_rate': 2.188686279067942e-07, 'epoch': 0.94} + 94%|█████████▎| 10969/11728 [3:00:27<1:15:04, 5.94s/it] 94%|█████████▎| 10970/11728 [3:00:33<1:14:52, 5.93s/it] {'loss': 0.4476, 'learning_rate': 2.182943850266994e-07, 'epoch': 0.94} + 94%|█████████▎| 10970/11728 [3:00:33<1:14:52, 5.93s/it] 94%|█████████▎| 10971/11728 [3:00:38<1:13:33, 5.83s/it] {'loss': 0.451, 'learning_rate': 2.1772088814031144e-07, 'epoch': 0.94} + 94%|█████████▎| 10971/11728 [3:00:38<1:13:33, 5.83s/it] 94%|█████████▎| 10972/11728 [3:00:44<1:13:00, 5.79s/it] {'loss': 0.4642, 'learning_rate': 2.1714813729136975e-07, 'epoch': 0.94} + 94%|█████████▎| 10972/11728 [3:00:44<1:13:00, 5.79s/it] 94%|█████████▎| 10973/11728 [3:00:50<1:13:15, 5.82s/it] {'loss': 0.4584, 'learning_rate': 2.165761325235527e-07, 'epoch': 0.94} + 94%|█████████▎| 10973/11728 [3:00:50<1:13:15, 5.82s/it] 94%|█████████▎| 10974/11728 [3:00:56<1:12:34, 5.78s/it] {'loss': 0.4681, 'learning_rate': 2.160048738804821e-07, 'epoch': 0.94} + 94%|█████████▎| 10974/11728 [3:00:56<1:12:34, 5.78s/it] 94%|█████████▎| 10975/11728 [3:01:01<1:12:15, 5.76s/it] {'loss': 0.4437, 'learning_rate': 2.1543436140572972e-07, 'epoch': 0.94} + 94%|█████████▎| 10975/11728 [3:01:01<1:12:15, 5.76s/it] 94%|█████████▎| 10976/11728 [3:01:07<1:12:19, 5.77s/it] {'loss': 0.444, 'learning_rate': 2.1486459514280078e-07, 'epoch': 0.94} + 94%|█████████▎| 10976/11728 [3:01:07<1:12:19, 5.77s/it] 94%|█████████▎| 10977/11728 [3:01:13<1:12:43, 5.81s/it] {'loss': 0.479, 'learning_rate': 2.1429557513514942e-07, 'epoch': 0.94} + 94%|█████████▎| 10977/11728 [3:01:13<1:12:43, 5.81s/it] 94%|█████████▎| 10978/11728 [3:01:19<1:11:41, 5.74s/it] {'loss': 0.4597, 'learning_rate': 2.1372730142617205e-07, 'epoch': 0.94} + 94%|█████████▎| 10978/11728 [3:01:19<1:11:41, 5.74s/it] 94%|█████████▎| 10979/11728 [3:01:24<1:11:26, 5.72s/it] {'loss': 0.4416, 'learning_rate': 2.131597740592073e-07, 'epoch': 0.94} + 94%|█████████▎| 10979/11728 [3:01:24<1:11:26, 5.72s/it] 94%|█████████▎| 10980/11728 [3:01:30<1:11:59, 5.78s/it] {'loss': 0.4525, 'learning_rate': 2.1259299307753721e-07, 'epoch': 0.94} + 94%|█████████▎| 10980/11728 [3:01:30<1:11:59, 5.78s/it] 94%|█████████▎| 10981/11728 [3:01:36<1:12:24, 5.82s/it] {'loss': 0.4464, 'learning_rate': 2.1202695852438725e-07, 'epoch': 0.94} + 94%|█████████▎| 10981/11728 [3:01:36<1:12:24, 5.82s/it] 94%|█████████▎| 10982/11728 [3:01:42<1:11:53, 5.78s/it] {'loss': 0.4404, 'learning_rate': 2.11461670442924e-07, 'epoch': 0.94} + 94%|█████████▎| 10982/11728 [3:01:42<1:11:53, 5.78s/it] 94%|█████████▎| 10983/11728 [3:01:48<1:11:20, 5.75s/it] {'loss': 0.4468, 'learning_rate': 2.1089712887625847e-07, 'epoch': 0.94} + 94%|█████████▎| 10983/11728 [3:01:48<1:11:20, 5.75s/it] 94%|█████████▎| 10984/11728 [3:01:53<1:11:57, 5.80s/it] {'loss': 0.4434, 'learning_rate': 2.1033333386744848e-07, 'epoch': 0.94} + 94%|█████████▎| 10984/11728 [3:01:53<1:11:57, 5.80s/it] 94%|█████████▎| 10985/11728 [3:01:59<1:11:34, 5.78s/it] {'loss': 0.4478, 'learning_rate': 2.097702854594874e-07, 'epoch': 0.94} + 94%|█████████▎| 10985/11728 [3:01:59<1:11:34, 5.78s/it] 94%|█████████▎| 10986/11728 [3:02:05<1:11:17, 5.77s/it] {'loss': 0.4562, 'learning_rate': 2.092079836953176e-07, 'epoch': 0.94} + 94%|█████████▎| 10986/11728 [3:02:05<1:11:17, 5.77s/it] 94%|█████████▎| 10987/11728 [3:02:11<1:11:40, 5.80s/it] {'loss': 0.4505, 'learning_rate': 2.0864642861782246e-07, 'epoch': 0.94} + 94%|█████████▎| 10987/11728 [3:02:11<1:11:40, 5.80s/it] 94%|█████████▎| 10988/11728 [3:02:16<1:10:34, 5.72s/it] {'loss': 0.4579, 'learning_rate': 2.0808562026982894e-07, 'epoch': 0.94} + 94%|█████████▎| 10988/11728 [3:02:16<1:10:34, 5.72s/it] 94%|█████████▎| 10989/11728 [3:02:22<1:11:37, 5.81s/it] {'loss': 0.4424, 'learning_rate': 2.0752555869410495e-07, 'epoch': 0.94} + 94%|█████████▎| 10989/11728 [3:02:22<1:11:37, 5.81s/it] 94%|█████████▎| 10990/11728 [3:02:28<1:10:56, 5.77s/it] {'loss': 0.4755, 'learning_rate': 2.069662439333664e-07, 'epoch': 0.94} + 94%|█████████▎| 10990/11728 [3:02:28<1:10:56, 5.77s/it] 94%|█████████▎| 10991/11728 [3:02:34<1:10:26, 5.73s/it] {'loss': 0.4535, 'learning_rate': 2.064076760302647e-07, 'epoch': 0.94} + 94%|█████████▎| 10991/11728 [3:02:34<1:10:26, 5.73s/it] 94%|█████████▎| 10992/11728 [3:02:40<1:12:49, 5.94s/it] {'loss': 0.4339, 'learning_rate': 2.0584985502740018e-07, 'epoch': 0.94} + 94%|█████████▎| 10992/11728 [3:02:40<1:12:49, 5.94s/it] 94%|█████████▎| 10993/11728 [3:02:46<1:11:06, 5.80s/it] {'loss': 0.4365, 'learning_rate': 2.0529278096731664e-07, 'epoch': 0.94} + 94%|█████████▎| 10993/11728 [3:02:46<1:11:06, 5.80s/it] 94%|█████████▎| 10994/11728 [3:02:51<1:11:19, 5.83s/it] {'loss': 0.4527, 'learning_rate': 2.0473645389249674e-07, 'epoch': 0.94} + 94%|█████████▎| 10994/11728 [3:02:52<1:11:19, 5.83s/it] 94%|█████████▍| 10995/11728 [3:02:57<1:11:13, 5.83s/it] {'loss': 0.4547, 'learning_rate': 2.0418087384536878e-07, 'epoch': 0.94} + 94%|█████████▍| 10995/11728 [3:02:57<1:11:13, 5.83s/it] 94%|█████████▍| 10996/11728 [3:03:03<1:11:25, 5.85s/it] {'loss': 0.442, 'learning_rate': 2.0362604086830328e-07, 'epoch': 0.94} + 94%|█████████▍| 10996/11728 [3:03:03<1:11:25, 5.85s/it] 94%|█████████▍| 10997/11728 [3:03:09<1:10:10, 5.76s/it] {'loss': 0.4553, 'learning_rate': 2.0307195500361532e-07, 'epoch': 0.94} + 94%|█████████▍| 10997/11728 [3:03:09<1:10:10, 5.76s/it] 94%|█████████▍| 10998/11728 [3:03:14<1:09:48, 5.74s/it] {'loss': 0.4639, 'learning_rate': 2.0251861629356108e-07, 'epoch': 0.94} + 94%|█████████▍| 10998/11728 [3:03:14<1:09:48, 5.74s/it] 94%|█████████▍| 10999/11728 [3:03:20<1:10:22, 5.79s/it] {'loss': 0.4334, 'learning_rate': 2.0196602478034012e-07, 'epoch': 0.94} + 94%|█████████▍| 10999/11728 [3:03:20<1:10:22, 5.79s/it]2 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... +07 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... + 94%|█████████▍| 11000/11728 [3:03:29<1:19:59, 6.59s/it]4 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4603, 'learning_rate': 2.014141805060954e-07, 'epoch': 0.94} + 94%|█████████▍| 11000/11728 [3:03:29<1:19:59, 6.59s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-11000/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-11000/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-11000/mm_projector +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/torch/nn/modules/module.py:1802: UserWarning: Positional args are being deprecated, use kwargs instead. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details. + warnings.warn( + 94%|█████████▍| 11001/11728 [3:04:05<3:08:18, 15.54s/it] {'loss': 0.4658, 'learning_rate': 2.0086308351291328e-07, 'epoch': 0.94} + 94%|█████████▍| 11001/11728 [3:04:05<3:08:18, 15.54s/it] 94%|█████████▍| 11002/11728 [3:04:14<2:41:38, 13.36s/it] {'loss': 0.4344, 'learning_rate': 2.0031273384282347e-07, 'epoch': 0.94} + 94%|█████████▍| 11002/11728 [3:04:14<2:41:38, 13.36s/it] 94%|█████████▍| 11003/11728 [3:04:19<2:13:28, 11.05s/it] {'loss': 0.4628, 'learning_rate': 1.9976313153779568e-07, 'epoch': 0.94} + 94%|█████████▍| 11003/11728 [3:04:19<2:13:28, 11.05s/it] 94%|█████████▍| 11004/11728 [3:04:25<1:53:42, 9.42s/it] {'loss': 0.4693, 'learning_rate': 1.9921427663974646e-07, 'epoch': 0.94} + 94%|█████████▍| 11004/11728 [3:04:25<1:53:42, 9.42s/it] 94%|█████████▍| 11005/11728 [3:04:33<1:50:12, 9.15s/it] {'loss': 0.4587, 'learning_rate': 1.986661691905345e-07, 'epoch': 0.94} + 94%|█████████▍| 11005/11728 [3:04:33<1:50:12, 9.15s/it] 94%|█████████▍| 11006/11728 [3:04:39<1:38:07, 8.15s/it] {'loss': 0.4865, 'learning_rate': 1.981188092319586e-07, 'epoch': 0.94} + 94%|█████████▍| 11006/11728 [3:04:39<1:38:07, 8.15s/it] 94%|█████████▍| 11007/11728 [3:04:51<1:50:32, 9.20s/it] {'loss': 0.4623, 'learning_rate': 1.9757219680576422e-07, 'epoch': 0.94} + 94%|█████████▍| 11007/11728 [3:04:51<1:50:32, 9.20s/it] 94%|█████████▍| 11008/11728 [3:04:57<1:38:37, 8.22s/it] {'loss': 0.4291, 'learning_rate': 1.9702633195363918e-07, 'epoch': 0.94} + 94%|█████████▍| 11008/11728 [3:04:57<1:38:37, 8.22s/it] 94%|█████████▍| 11009/11728 [3:05:02<1:29:02, 7.43s/it] {'loss': 0.46, 'learning_rate': 1.9648121471721126e-07, 'epoch': 0.94} + 94%|█████████▍| 11009/11728 [3:05:02<1:29:02, 7.43s/it] 94%|█████████▍| 11010/11728 [3:05:08<1:23:03, 6.94s/it] {'loss': 0.4559, 'learning_rate': 1.95936845138055e-07, 'epoch': 0.94} + 94%|█████████▍| 11010/11728 [3:05:08<1:23:03, 6.94s/it] 94%|█████████▍| 11011/11728 [3:05:14<1:19:55, 6.69s/it] {'loss': 0.4591, 'learning_rate': 1.9539322325768494e-07, 'epoch': 0.94} + 94%|█████████▍| 11011/11728 [3:05:14<1:19:55, 6.69s/it] 94%|█████████▍| 11012/11728 [3:05:20<1:15:46, 6.35s/it] {'loss': 0.4236, 'learning_rate': 1.9485034911756018e-07, 'epoch': 0.94} + 94%|█████████▍| 11012/11728 [3:05:20<1:15:46, 6.35s/it] 94%|█████████▍| 11013/11728 [3:05:28<1:24:02, 7.05s/it] {'loss': 0.4554, 'learning_rate': 1.9430822275908423e-07, 'epoch': 0.94} + 94%|█████████▍| 11013/11728 [3:05:28<1:24:02, 7.05s/it] 94%|█████████▍| 11014/11728 [3:05:34<1:18:27, 6.59s/it] {'loss': 0.441, 'learning_rate': 1.937668442235996e-07, 'epoch': 0.94} + 94%|█████████▍| 11014/11728 [3:05:34<1:18:27, 6.59s/it] 94%|█████████▍| 11015/11728 [3:05:40<1:15:22, 6.34s/it] {'loss': 0.4628, 'learning_rate': 1.9322621355239658e-07, 'epoch': 0.94} + 94%|█████████▍| 11015/11728 [3:05:40<1:15:22, 6.34s/it] 94%|█████████▍| 11016/11728 [3:05:49<1:24:17, 7.10s/it] {'loss': 0.4591, 'learning_rate': 1.9268633078670328e-07, 'epoch': 0.94} + 94%|█████████▍| 11016/11728 [3:05:49<1:24:17, 7.10s/it] 94%|█████████▍| 11017/11728 [3:05:54<1:19:39, 6.72s/it] {'loss': 0.462, 'learning_rate': 1.921471959676957e-07, 'epoch': 0.94} + 94%|█████████▍| 11017/11728 [3:05:54<1:19:39, 6.72s/it] 94%|█████████▍| 11018/11728 [3:06:01<1:17:25, 6.54s/it] {'loss': 0.4692, 'learning_rate': 1.9160880913648983e-07, 'epoch': 0.94} + 94%|█████████▍| 11018/11728 [3:06:01<1:17:25, 6.54s/it] 94%|█████████▍| 11019/11728 [3:06:06<1:14:22, 6.29s/it] {'loss': 0.4639, 'learning_rate': 1.910711703341439e-07, 'epoch': 0.94} + 94%|█████████▍| 11019/11728 [3:06:06<1:14:22, 6.29s/it] 94%|█████████▍| 11020/11728 [3:06:12<1:12:21, 6.13s/it] {'loss': 0.4549, 'learning_rate': 1.9053427960166183e-07, 'epoch': 0.94} + 94%|█████████▍| 11020/11728 [3:06:12<1:12:21, 6.13s/it] 94%|█████████▍| 11021/11728 [3:06:18<1:11:29, 6.07s/it] {'loss': 0.435, 'learning_rate': 1.8999813697998858e-07, 'epoch': 0.94} + 94%|█████████▍| 11021/11728 [3:06:18<1:11:29, 6.07s/it] 94%|█████████▍| 11022/11728 [3:06:24<1:11:14, 6.05s/it] {'loss': 0.4579, 'learning_rate': 1.8946274251001373e-07, 'epoch': 0.94} + 94%|█████████▍| 11022/11728 [3:06:24<1:11:14, 6.05s/it] 94%|█████████▍| 11023/11728 [3:06:30<1:10:23, 5.99s/it] {'loss': 0.4396, 'learning_rate': 1.889280962325668e-07, 'epoch': 0.94} + 94%|█████████▍| 11023/11728 [3:06:30<1:10:23, 5.99s/it] 94%|█████████▍| 11024/11728 [3:06:36<1:09:25, 5.92s/it] {'loss': 0.4506, 'learning_rate': 1.8839419818842408e-07, 'epoch': 0.94} + 94%|█████████▍| 11024/11728 [3:06:36<1:09:25, 5.92s/it] 94%|█████████▍| 11025/11728 [3:06:41<1:09:13, 5.91s/it] {'loss': 0.4461, 'learning_rate': 1.8786104841830188e-07, 'epoch': 0.94} + 94%|█████████▍| 11025/11728 [3:06:41<1:09:13, 5.91s/it] 94%|█████████▍| 11026/11728 [3:06:47<1:09:18, 5.92s/it] {'loss': 0.463, 'learning_rate': 1.87328646962861e-07, 'epoch': 0.94} + 94%|█████████▍| 11026/11728 [3:06:47<1:09:18, 5.92s/it] 94%|█████████▍| 11027/11728 [3:06:53<1:09:08, 5.92s/it] {'loss': 0.4612, 'learning_rate': 1.8679699386270457e-07, 'epoch': 0.94} + 94%|█████████▍| 11027/11728 [3:06:53<1:09:08, 5.92s/it] 94%|█████████▍| 11028/11728 [3:06:59<1:07:43, 5.81s/it] {'loss': 0.4457, 'learning_rate': 1.8626608915837675e-07, 'epoch': 0.94} + 94%|█████████▍| 11028/11728 [3:06:59<1:07:43, 5.81s/it] 94%|█████████▍| 11029/11728 [3:07:05<1:08:18, 5.86s/it] {'loss': 0.4449, 'learning_rate': 1.857359328903685e-07, 'epoch': 0.94} + 94%|█████████▍| 11029/11728 [3:07:05<1:08:18, 5.86s/it] 94%|█████████▍| 11030/11728 [3:07:10<1:07:05, 5.77s/it] {'loss': 0.4326, 'learning_rate': 1.8520652509911196e-07, 'epoch': 0.94} + 94%|█████████▍| 11030/11728 [3:07:10<1:07:05, 5.77s/it] 94%|█████████▍| 11031/11728 [3:07:16<1:07:24, 5.80s/it] {'loss': 0.4674, 'learning_rate': 1.8467786582498147e-07, 'epoch': 0.94} + 94%|█████████▍| 11031/11728 [3:07:16<1:07:24, 5.80s/it] 94%|█████████▍| 11032/11728 [3:07:23<1:09:10, 5.96s/it] {'loss': 0.4605, 'learning_rate': 1.841499551082937e-07, 'epoch': 0.94} + 94%|█████████▍| 11032/11728 [3:07:23<1:09:10, 5.96s/it] 94%|█████████▍| 11033/11728 [3:07:28<1:08:17, 5.90s/it] {'loss': 0.4382, 'learning_rate': 1.8362279298931197e-07, 'epoch': 0.94} + 94%|█████████▍| 11033/11728 [3:07:28<1:08:17, 5.90s/it] 94%|█████████▍| 11034/11728 [3:07:34<1:08:02, 5.88s/it] {'loss': 0.4566, 'learning_rate': 1.8309637950823632e-07, 'epoch': 0.94} + 94%|█████████▍| 11034/11728 [3:07:34<1:08:02, 5.88s/it] 94%|█████████▍| 11035/11728 [3:07:40<1:08:27, 5.93s/it] {'loss': 0.459, 'learning_rate': 1.825707147052147e-07, 'epoch': 0.94} + 94%|█████████▍| 11035/11728 [3:07:40<1:08:27, 5.93s/it] 94%|█████████▍| 11036/11728 [3:07:46<1:08:30, 5.94s/it] {'loss': 0.4591, 'learning_rate': 1.8204579862033945e-07, 'epoch': 0.94} + 94%|█████████▍| 11036/11728 [3:07:46<1:08:30, 5.94s/it] 94%|█████████▍| 11037/11728 [3:07:52<1:08:12, 5.92s/it] {'loss': 0.4548, 'learning_rate': 1.8152163129363854e-07, 'epoch': 0.94} + 94%|█████████▍| 11037/11728 [3:07:52<1:08:12, 5.92s/it] 94%|█████████▍| 11038/11728 [3:07:58<1:06:38, 5.79s/it] {'loss': 0.4586, 'learning_rate': 1.8099821276508888e-07, 'epoch': 0.94} + 94%|█████████▍| 11038/11728 [3:07:58<1:06:38, 5.79s/it] 94%|█████████▍| 11039/11728 [3:08:04<1:07:21, 5.87s/it] {'loss': 0.4338, 'learning_rate': 1.8047554307460967e-07, 'epoch': 0.94} + 94%|█████████▍| 11039/11728 [3:08:04<1:07:21, 5.87s/it] 94%|█████████▍| 11040/11728 [3:08:09<1:06:55, 5.84s/it] {'loss': 0.4548, 'learning_rate': 1.7995362226206014e-07, 'epoch': 0.94} + 94%|█████████▍| 11040/11728 [3:08:09<1:06:55, 5.84s/it] 94%|█████████▍| 11041/11728 [3:08:15<1:07:31, 5.90s/it] {'loss': 0.4346, 'learning_rate': 1.7943245036724512e-07, 'epoch': 0.94} + 94%|█████████▍| 11041/11728 [3:08:15<1:07:31, 5.90s/it] 94%|█████████▍| 11042/11728 [3:08:21<1:06:20, 5.80s/it] {'loss': 0.4554, 'learning_rate': 1.7891202742991165e-07, 'epoch': 0.94} + 94%|█████████▍| 11042/11728 [3:08:21<1:06:20, 5.80s/it] 94%|█████████▍| 11043/11728 [3:08:26<1:04:59, 5.69s/it] {'loss': 0.4458, 'learning_rate': 1.7839235348974692e-07, 'epoch': 0.94} + 94%|█████████▍| 11043/11728 [3:08:26<1:04:59, 5.69s/it] 94%|█████████▍| 11044/11728 [3:08:32<1:04:41, 5.68s/it] {'loss': 0.4568, 'learning_rate': 1.7787342858638589e-07, 'epoch': 0.94} + 94%|█████████▍| 11044/11728 [3:08:32<1:04:41, 5.68s/it] 94%|█████████▍| 11045/11728 [3:08:38<1:05:09, 5.72s/it] {'loss': 0.4612, 'learning_rate': 1.773552527594047e-07, 'epoch': 0.94} + 94%|█████████▍| 11045/11728 [3:08:38<1:05:09, 5.72s/it] 94%|█████████▍| 11046/11728 [3:08:44<1:05:59, 5.81s/it] {'loss': 0.4704, 'learning_rate': 1.7683782604831946e-07, 'epoch': 0.94} + 94%|█████████▍| 11046/11728 [3:08:44<1:05:59, 5.81s/it] 94%|█████████▍| 11047/11728 [3:08:50<1:06:02, 5.82s/it] {'loss': 0.4416, 'learning_rate': 1.7632114849259197e-07, 'epoch': 0.94} + 94%|█████████▍| 11047/11728 [3:08:50<1:06:02, 5.82s/it] 94%|█████████▍| 11048/11728 [3:08:56<1:06:18, 5.85s/it] {'loss': 0.4583, 'learning_rate': 1.7580522013162626e-07, 'epoch': 0.94} + 94%|█████████▍| 11048/11728 [3:08:56<1:06:18, 5.85s/it] 94%|█████████▍| 11049/11728 [3:09:02<1:06:06, 5.84s/it] {'loss': 0.4331, 'learning_rate': 1.7529004100476866e-07, 'epoch': 0.94} + 94%|█████████▍| 11049/11728 [3:09:02<1:06:06, 5.84s/it]2 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... +0 AutoResumeHook: Checking whether to suspend... + 94%|█████████▍| 11050/11728 [3:09:08<1:06:40, 5.90s/it]4 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4574, 'learning_rate': 1.747756111513099e-07, 'epoch': 0.94} + 94%|█████████▍| 11050/11728 [3:09:08<1:06:40, 5.90s/it] 94%|█████████▍| 11051/11728 [3:09:13<1:06:12, 5.87s/it] {'loss': 0.4417, 'learning_rate': 1.7426193061048313e-07, 'epoch': 0.94} + 94%|█████████▍| 11051/11728 [3:09:13<1:06:12, 5.87s/it] 94%|█████████▍| 11052/11728 [3:09:19<1:05:34, 5.82s/it] {'loss': 0.466, 'learning_rate': 1.7374899942146139e-07, 'epoch': 0.94} + 94%|█████████▍| 11052/11728 [3:09:19<1:05:34, 5.82s/it] 94%|█████████▍| 11053/11728 [3:09:25<1:04:55, 5.77s/it] {'loss': 0.4488, 'learning_rate': 1.7323681762336453e-07, 'epoch': 0.94} + 94%|█████████▍| 11053/11728 [3:09:25<1:04:55, 5.77s/it] 94%|█████████▍| 11054/11728 [3:09:31<1:04:52, 5.77s/it] {'loss': 0.4597, 'learning_rate': 1.7272538525525462e-07, 'epoch': 0.94} + 94%|█████████▍| 11054/11728 [3:09:31<1:04:52, 5.77s/it] 94%|█████████▍| 11055/11728 [3:09:36<1:05:03, 5.80s/it] {'loss': 0.4388, 'learning_rate': 1.722147023561338e-07, 'epoch': 0.94} + 94%|█████████▍| 11055/11728 [3:09:36<1:05:03, 5.80s/it] 94%|█████████▍| 11056/11728 [3:09:42<1:04:10, 5.73s/it] {'loss': 0.4611, 'learning_rate': 1.717047689649487e-07, 'epoch': 0.94} + 94%|█████████▍| 11056/11728 [3:09:42<1:04:10, 5.73s/it] 94%|█████████▍| 11057/11728 [3:09:47<1:03:29, 5.68s/it] {'loss': 0.4352, 'learning_rate': 1.7119558512059044e-07, 'epoch': 0.94} + 94%|█████████▍| 11057/11728 [3:09:47<1:03:29, 5.68s/it] 94%|█████████▍| 11058/11728 [3:09:53<1:03:16, 5.67s/it] {'loss': 0.4608, 'learning_rate': 1.7068715086189124e-07, 'epoch': 0.94} + 94%|█████████▍| 11058/11728 [3:09:53<1:03:16, 5.67s/it] 94%|█████████▍| 11059/11728 [3:09:59<1:03:33, 5.70s/it] {'loss': 0.454, 'learning_rate': 1.701794662276257e-07, 'epoch': 0.94} + 94%|█████████▍| 11059/11728 [3:09:59<1:03:33, 5.70s/it] 94%|█████████▍| 11060/11728 [3:10:05<1:03:51, 5.74s/it] {'loss': 0.4486, 'learning_rate': 1.6967253125651284e-07, 'epoch': 0.94} + 94%|█████████▍| 11060/11728 [3:10:05<1:03:51, 5.74s/it] 94%|█████████▍| 11061/11728 [3:10:10<1:03:44, 5.73s/it] {'loss': 0.4516, 'learning_rate': 1.6916634598721283e-07, 'epoch': 0.94} + 94%|█████████▍| 11061/11728 [3:10:10<1:03:44, 5.73s/it] 94%|█████████▍| 11062/11728 [3:10:17<1:05:48, 5.93s/it] {'loss': 0.4441, 'learning_rate': 1.6866091045832923e-07, 'epoch': 0.94} + 94%|█████████▍| 11062/11728 [3:10:17<1:05:48, 5.93s/it] 94%|█████████▍| 11063/11728 [3:10:23<1:06:37, 6.01s/it] {'loss': 0.4722, 'learning_rate': 1.6815622470841008e-07, 'epoch': 0.94} + 94%|█████████▍| 11063/11728 [3:10:23<1:06:37, 6.01s/it] 94%|█████████▍| 11064/11728 [3:10:29<1:06:02, 5.97s/it] {'loss': 0.4273, 'learning_rate': 1.6765228877594352e-07, 'epoch': 0.94} + 94%|█████████▍| 11064/11728 [3:10:29<1:06:02, 5.97s/it] 94%|█████████▍| 11065/11728 [3:10:35<1:05:11, 5.90s/it] {'loss': 0.4615, 'learning_rate': 1.6714910269936213e-07, 'epoch': 0.94} + 94%|█████████▍| 11065/11728 [3:10:35<1:05:11, 5.90s/it] 94%|█████████▍| 11066/11728 [3:10:41<1:06:01, 5.98s/it] {'loss': 0.4544, 'learning_rate': 1.6664666651704075e-07, 'epoch': 0.94} + 94%|█████████▍| 11066/11728 [3:10:41<1:06:01, 5.98s/it] 94%|█████████▍| 11067/11728 [3:10:47<1:07:21, 6.11s/it] {'loss': 0.4181, 'learning_rate': 1.6614498026729876e-07, 'epoch': 0.94} + 94%|█████████▍| 11067/11728 [3:10:47<1:07:21, 6.11s/it] 94%|█████████▍| 11068/11728 [3:10:53<1:05:31, 5.96s/it] {'loss': 0.4683, 'learning_rate': 1.656440439883944e-07, 'epoch': 0.94} + 94%|█████████▍| 11068/11728 [3:10:53<1:05:31, 5.96s/it] 94%|█████████▍| 11069/11728 [3:10:59<1:05:18, 5.95s/it] {'loss': 0.457, 'learning_rate': 1.651438577185338e-07, 'epoch': 0.94} + 94%|█████████▍| 11069/11728 [3:10:59<1:05:18, 5.95s/it] 94%|█████████▍| 11070/11728 [3:11:05<1:04:50, 5.91s/it] {'loss': 0.4588, 'learning_rate': 1.646444214958598e-07, 'epoch': 0.94} + 94%|█████████▍| 11070/11728 [3:11:05<1:04:50, 5.91s/it] 94%|█████████▍| 11071/11728 [3:11:11<1:05:01, 5.94s/it] {'loss': 0.4582, 'learning_rate': 1.6414573535846523e-07, 'epoch': 0.94} + 94%|█████████▍| 11071/11728 [3:11:11<1:05:01, 5.94s/it] 94%|█████████▍| 11072/11728 [3:11:16<1:04:40, 5.92s/it] {'loss': 0.4614, 'learning_rate': 1.636477993443808e-07, 'epoch': 0.94} + 94%|█████████▍| 11072/11728 [3:11:16<1:04:40, 5.92s/it] 94%|█████████▍| 11073/11728 [3:11:22<1:04:21, 5.90s/it] {'loss': 0.4429, 'learning_rate': 1.6315061349157946e-07, 'epoch': 0.94} + 94%|█████████▍| 11073/11728 [3:11:22<1:04:21, 5.90s/it] 94%|█████████▍| 11074/11728 [3:11:28<1:03:22, 5.81s/it] {'loss': 0.434, 'learning_rate': 1.6265417783798087e-07, 'epoch': 0.94} + 94%|█████████▍| 11074/11728 [3:11:28<1:03:22, 5.81s/it] 94%|█████████▍| 11075/11728 [3:11:34<1:02:43, 5.76s/it] {'loss': 0.4679, 'learning_rate': 1.6215849242144365e-07, 'epoch': 0.94} + 94%|█████████▍| 11075/11728 [3:11:34<1:02:43, 5.76s/it] 94%|█████████▍| 11076/11728 [3:11:39<1:03:05, 5.81s/it] {'loss': 0.4637, 'learning_rate': 1.61663557279772e-07, 'epoch': 0.94} + 94%|█████████▍| 11076/11728 [3:11:39<1:03:05, 5.81s/it] 94%|█████████▍| 11077/11728 [3:11:45<1:02:52, 5.80s/it] {'loss': 0.4559, 'learning_rate': 1.6116937245071018e-07, 'epoch': 0.94} + 94%|█████████▍| 11077/11728 [3:11:45<1:02:52, 5.80s/it] 94%|█████████▍| 11078/11728 [3:11:51<1:02:31, 5.77s/it] {'loss': 0.475, 'learning_rate': 1.6067593797195025e-07, 'epoch': 0.94} + 94%|█████████▍| 11078/11728 [3:11:51<1:02:31, 5.77s/it] 94%|█████████▍| 11079/11728 [3:11:57<1:01:49, 5.72s/it] {'loss': 0.4626, 'learning_rate': 1.6018325388111876e-07, 'epoch': 0.94} + 94%|█████████▍| 11079/11728 [3:11:57<1:01:49, 5.72s/it] 94%|█████████▍| 11080/11728 [3:12:03<1:03:38, 5.89s/it] {'loss': 0.4456, 'learning_rate': 1.5969132021579347e-07, 'epoch': 0.94} + 94%|█████████▍| 11080/11728 [3:12:03<1:03:38, 5.89s/it] 94%|█████████▍| 11081/11728 [3:12:09<1:04:13, 5.96s/it] {'loss': 0.4441, 'learning_rate': 1.5920013701349103e-07, 'epoch': 0.94} + 94%|█████████▍| 11081/11728 [3:12:09<1:04:13, 5.96s/it] 94%|█████████▍| 11082/11728 [3:12:15<1:03:06, 5.86s/it] {'loss': 0.4634, 'learning_rate': 1.587097043116681e-07, 'epoch': 0.94} + 94%|█████████▍| 11082/11728 [3:12:15<1:03:06, 5.86s/it] 95%|█████████▍| 11083/11728 [3:12:20<1:02:40, 5.83s/it] {'loss': 0.437, 'learning_rate': 1.5822002214773035e-07, 'epoch': 0.95} + 95%|█████████▍| 11083/11728 [3:12:20<1:02:40, 5.83s/it] 95%|█████████▍| 11084/11728 [3:12:26<1:01:46, 5.76s/it] {'loss': 0.4629, 'learning_rate': 1.5773109055902235e-07, 'epoch': 0.95} + 95%|█████████▍| 11084/11728 [3:12:26<1:01:46, 5.76s/it] 95%|█████████▍| 11085/11728 [3:12:32<1:01:52, 5.77s/it] {'loss': 0.4376, 'learning_rate': 1.5724290958283094e-07, 'epoch': 0.95} + 95%|█████████▍| 11085/11728 [3:12:32<1:01:52, 5.77s/it] 95%|█████████▍| 11086/11728 [3:12:37<1:01:23, 5.74s/it] {'loss': 0.4558, 'learning_rate': 1.5675547925638856e-07, 'epoch': 0.95} + 95%|█████████▍| 11086/11728 [3:12:37<1:01:23, 5.74s/it] 95%|█████████▍| 11087/11728 [3:12:43<1:01:25, 5.75s/it] {'loss': 0.4587, 'learning_rate': 1.562687996168677e-07, 'epoch': 0.95} + 95%|█████████▍| 11087/11728 [3:12:43<1:01:25, 5.75s/it] 95%|█████████▍| 11088/11728 [3:12:49<1:01:59, 5.81s/it] {'loss': 0.4498, 'learning_rate': 1.5578287070138308e-07, 'epoch': 0.95} + 95%|█████████▍| 11088/11728 [3:12:49<1:01:59, 5.81s/it] 95%|█████████▍| 11089/11728 [3:12:55<1:01:13, 5.75s/it] {'loss': 0.4503, 'learning_rate': 1.5529769254699512e-07, 'epoch': 0.95} + 95%|█████████▍| 11089/11728 [3:12:55<1:01:13, 5.75s/it] 95%|█████████▍| 11090/11728 [3:13:01<1:01:28, 5.78s/it] {'loss': 0.4405, 'learning_rate': 1.5481326519070638e-07, 'epoch': 0.95} + 95%|█████████▍| 11090/11728 [3:13:01<1:01:28, 5.78s/it] 95%|█████████▍| 11091/11728 [3:13:06<1:01:36, 5.80s/it] {'loss': 0.4704, 'learning_rate': 1.543295886694607e-07, 'epoch': 0.95} + 95%|█████████▍| 11091/11728 [3:13:06<1:01:36, 5.80s/it] 95%|█████████▍| 11092/11728 [3:13:12<1:01:29, 5.80s/it] {'loss': 0.4414, 'learning_rate': 1.5384666302014407e-07, 'epoch': 0.95} + 95%|█████████▍| 11092/11728 [3:13:12<1:01:29, 5.80s/it] 95%|█████████▍| 11093/11728 [3:13:18<1:01:40, 5.83s/it] {'loss': 0.4426, 'learning_rate': 1.5336448827958815e-07, 'epoch': 0.95} + 95%|█████████▍| 11093/11728 [3:13:18<1:01:40, 5.83s/it] 95%|█████████▍| 11094/11728 [3:13:24<1:01:52, 5.86s/it] {'loss': 0.4727, 'learning_rate': 1.5288306448456468e-07, 'epoch': 0.95} + 95%|█████████▍| 11094/11728 [3:13:24<1:01:52, 5.86s/it] 95%|█████████▍| 11095/11728 [3:13:30<1:01:51, 5.86s/it] {'loss': 0.48, 'learning_rate': 1.5240239167178872e-07, 'epoch': 0.95} + 95%|█████████▍| 11095/11728 [3:13:30<1:01:51, 5.86s/it] 95%|█████████▍| 11096/11728 [3:13:36<1:01:20, 5.82s/it] {'loss': 0.4368, 'learning_rate': 1.519224698779198e-07, 'epoch': 0.95} + 95%|█████████▍| 11096/11728 [3:13:36<1:01:20, 5.82s/it] 95%|█████████▍| 11097/11728 [3:13:42<1:01:33, 5.85s/it] {'loss': 0.463, 'learning_rate': 1.5144329913955759e-07, 'epoch': 0.95} + 95%|█████████▍| 11097/11728 [3:13:42<1:01:33, 5.85s/it] 95%|█████████▍| 11098/11728 [3:13:47<1:01:18, 5.84s/it] {'loss': 0.4582, 'learning_rate': 1.50964879493245e-07, 'epoch': 0.95} + 95%|█████████▍| 11098/11728 [3:13:47<1:01:18, 5.84s/it] 95%|█████████▍| 11099/11728 [3:13:53<1:01:17, 5.85s/it] {'loss': 0.4312, 'learning_rate': 1.504872109754696e-07, 'epoch': 0.95} + 95%|█████████▍| 11099/11728 [3:13:53<1:01:17, 5.85s/it]57 AutoResumeHook: Checking whether to suspend...AutoResumeHook: Checking whether to suspend... + +2 AutoResumeHook: Checking whether to suspend... +36 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... +04 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... + 95%|█████████▍| 11100/11728 [3:13:59<1:01:30, 5.88s/it] {'loss': 0.4585, 'learning_rate': 1.5001029362265996e-07, 'epoch': 0.95} + 95%|█████████▍| 11100/11728 [3:13:59<1:01:30, 5.88s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-11100/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-11100/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-11100/mm_projector +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/torch/nn/modules/module.py:1802: UserWarning: Positional args are being deprecated, use kwargs instead. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details. + warnings.warn( + 95%|█████████▍| 11101/11728 [3:14:33<2:30:03, 14.36s/it] {'loss': 0.4355, 'learning_rate': 1.4953412747118813e-07, 'epoch': 0.95} + 95%|█████████▍| 11101/11728 [3:14:33<2:30:03, 14.36s/it] 95%|█████████▍| 11102/11728 [3:14:39<2:02:35, 11.75s/it] {'loss': 0.4648, 'learning_rate': 1.4905871255736838e-07, 'epoch': 0.95} + 95%|█████████▍| 11102/11728 [3:14:39<2:02:35, 11.75s/it] 95%|█████████▍| 11103/11728 [3:14:45<1:43:48, 9.97s/it] {'loss': 0.4411, 'learning_rate': 1.4858404891745616e-07, 'epoch': 0.95} + 95%|█████████▍| 11103/11728 [3:14:45<1:43:48, 9.97s/it] 95%|█████████▍| 11104/11728 [3:14:51<1:31:30, 8.80s/it] {'loss': 0.4465, 'learning_rate': 1.4811013658765471e-07, 'epoch': 0.95} + 95%|█████████▍| 11104/11728 [3:14:51<1:31:30, 8.80s/it] 95%|█████████▍| 11105/11728 [3:14:57<1:22:45, 7.97s/it] {'loss': 0.4731, 'learning_rate': 1.4763697560410406e-07, 'epoch': 0.95} + 95%|█████████▍| 11105/11728 [3:14:57<1:22:45, 7.97s/it] 95%|█████████▍| 11106/11728 [3:15:03<1:15:23, 7.27s/it] {'loss': 0.4523, 'learning_rate': 1.4716456600288975e-07, 'epoch': 0.95} + 95%|█████████▍| 11106/11728 [3:15:03<1:15:23, 7.27s/it] 95%|█████████▍| 11107/11728 [3:15:08<1:10:31, 6.81s/it] {'loss': 0.4483, 'learning_rate': 1.4669290782003963e-07, 'epoch': 0.95} + 95%|█████████▍| 11107/11728 [3:15:08<1:10:31, 6.81s/it] 95%|█████████▍| 11108/11728 [3:15:14<1:07:41, 6.55s/it] {'loss': 0.4605, 'learning_rate': 1.4622200109152495e-07, 'epoch': 0.95} + 95%|█████████▍| 11108/11728 [3:15:14<1:07:41, 6.55s/it] 95%|█████████▍| 11109/11728 [3:15:20<1:05:13, 6.32s/it] {'loss': 0.4506, 'learning_rate': 1.4575184585325918e-07, 'epoch': 0.95} + 95%|█████████▍| 11109/11728 [3:15:20<1:05:13, 6.32s/it] 95%|█████████▍| 11110/11728 [3:15:26<1:03:13, 6.14s/it] {'loss': 0.4615, 'learning_rate': 1.452824421410981e-07, 'epoch': 0.95} + 95%|█████████▍| 11110/11728 [3:15:26<1:03:13, 6.14s/it] 95%|█████████▍| 11111/11728 [3:15:32<1:02:17, 6.06s/it] {'loss': 0.4493, 'learning_rate': 1.4481378999083973e-07, 'epoch': 0.95} + 95%|█████████▍| 11111/11728 [3:15:32<1:02:17, 6.06s/it] 95%|█████████▍| 11112/11728 [3:15:37<1:00:35, 5.90s/it] {'loss': 0.4284, 'learning_rate': 1.4434588943822547e-07, 'epoch': 0.95} + 95%|█████████▍| 11112/11728 [3:15:37<1:00:35, 5.90s/it] 95%|█████████▍| 11113/11728 [3:15:43<59:50, 5.84s/it] {'loss': 0.4511, 'learning_rate': 1.4387874051894013e-07, 'epoch': 0.95} + 95%|█████████▍| 11113/11728 [3:15:43<59:50, 5.84s/it] 95%|█████████▍| 11114/11728 [3:15:49<1:00:01, 5.87s/it] {'loss': 0.4698, 'learning_rate': 1.4341234326861076e-07, 'epoch': 0.95} + 95%|█████████▍| 11114/11728 [3:15:49<1:00:01, 5.87s/it] 95%|█████████▍| 11115/11728 [3:15:55<1:00:15, 5.90s/it] {'loss': 0.4439, 'learning_rate': 1.4294669772280556e-07, 'epoch': 0.95} + 95%|█████████▍| 11115/11728 [3:15:55<1:00:15, 5.90s/it] 95%|█████████▍| 11116/11728 [3:16:01<1:00:48, 5.96s/it] {'loss': 0.4508, 'learning_rate': 1.4248180391703614e-07, 'epoch': 0.95} + 95%|█████████▍| 11116/11728 [3:16:01<1:00:48, 5.96s/it] 95%|█████████▍| 11117/11728 [3:16:07<59:47, 5.87s/it] {'loss': 0.4403, 'learning_rate': 1.420176618867597e-07, 'epoch': 0.95} + 95%|█████████▍| 11117/11728 [3:16:07<59:47, 5.87s/it] 95%|█████████▍| 11118/11728 [3:16:12<59:12, 5.82s/it] {'loss': 0.479, 'learning_rate': 1.4155427166737123e-07, 'epoch': 0.95} + 95%|█████████▍| 11118/11728 [3:16:12<59:12, 5.82s/it] 95%|█████████▍| 11119/11728 [3:16:18<58:31, 5.77s/it] {'loss': 0.443, 'learning_rate': 1.410916332942125e-07, 'epoch': 0.95} + 95%|█████████▍| 11119/11728 [3:16:18<58:31, 5.77s/it] 95%|█████████▍| 11120/11728 [3:16:24<58:19, 5.76s/it] {'loss': 0.46, 'learning_rate': 1.4062974680256635e-07, 'epoch': 0.95} + 95%|█████████▍| 11120/11728 [3:16:24<58:19, 5.76s/it] 95%|█████████▍| 11121/11728 [3:16:29<57:44, 5.71s/it] {'loss': 0.4518, 'learning_rate': 1.4016861222765576e-07, 'epoch': 0.95} + 95%|█████████▍| 11121/11728 [3:16:29<57:44, 5.71s/it] 95%|█████████▍| 11122/11728 [3:16:35<57:30, 5.69s/it] {'loss': 0.4201, 'learning_rate': 1.3970822960465035e-07, 'epoch': 0.95} + 95%|█████████▍| 11122/11728 [3:16:35<57:30, 5.69s/it] 95%|█████████▍| 11123/11728 [3:16:41<57:18, 5.68s/it] {'loss': 0.4475, 'learning_rate': 1.3924859896866206e-07, 'epoch': 0.95} + 95%|█████████▍| 11123/11728 [3:16:41<57:18, 5.68s/it]Token indices sequence length is longer than the specified maximum sequence length for this model (4901 > 4096). Running this sequence through the model will result in indexing errors + 95%|█████████▍| 11124/11728 [3:16:46<57:44, 5.74s/it] {'loss': 0.4447, 'learning_rate': 1.387897203547417e-07, 'epoch': 0.95} + 95%|█████████▍| 11124/11728 [3:16:46<57:44, 5.74s/it] 95%|█████████▍| 11125/11728 [3:16:52<58:26, 5.82s/it] {'loss': 0.4459, 'learning_rate': 1.3833159379788686e-07, 'epoch': 0.95} + 95%|█████████▍| 11125/11728 [3:16:52<58:26, 5.82s/it] 95%|█████████▍| 11126/11728 [3:16:58<58:13, 5.80s/it] {'loss': 0.4391, 'learning_rate': 1.3787421933303735e-07, 'epoch': 0.95} + 95%|█████████▍| 11126/11728 [3:16:58<58:13, 5.80s/it] 95%|█████████▍| 11127/11728 [3:17:04<58:49, 5.87s/it] {'loss': 0.4734, 'learning_rate': 1.3741759699507084e-07, 'epoch': 0.95} + 95%|█████████▍| 11127/11728 [3:17:04<58:49, 5.87s/it] 95%|█████████▍| 11128/11728 [3:17:10<57:52, 5.79s/it] {'loss': 0.435, 'learning_rate': 1.3696172681881504e-07, 'epoch': 0.95} + 95%|█████████▍| 11128/11728 [3:17:10<57:52, 5.79s/it] 95%|█████████▍| 11129/11728 [3:17:16<57:44, 5.78s/it] {'loss': 0.4521, 'learning_rate': 1.3650660883903545e-07, 'epoch': 0.95} + 95%|█████████▍| 11129/11728 [3:17:16<57:44, 5.78s/it] 95%|█████████▍| 11130/11728 [3:17:22<58:19, 5.85s/it] {'loss': 0.4717, 'learning_rate': 1.3605224309043873e-07, 'epoch': 0.95} + 95%|█████████▍| 11130/11728 [3:17:22<58:19, 5.85s/it] 95%|█████████▍| 11131/11728 [3:17:28<59:04, 5.94s/it] {'loss': 0.4448, 'learning_rate': 1.3559862960767944e-07, 'epoch': 0.95} + 95%|█████████▍| 11131/11728 [3:17:28<59:04, 5.94s/it] 95%|█████████▍| 11132/11728 [3:17:33<58:00, 5.84s/it] {'loss': 0.4376, 'learning_rate': 1.351457684253521e-07, 'epoch': 0.95} + 95%|█████████▍| 11132/11728 [3:17:33<58:00, 5.84s/it] 95%|█████████▍| 11133/11728 [3:17:39<57:00, 5.75s/it] {'loss': 0.4508, 'learning_rate': 1.346936595779924e-07, 'epoch': 0.95} + 95%|█████████▍| 11133/11728 [3:17:39<57:00, 5.75s/it] 95%|█████████▍| 11134/11728 [3:17:45<57:22, 5.80s/it] {'loss': 0.4451, 'learning_rate': 1.3424230310007946e-07, 'epoch': 0.95} + 95%|█████████▍| 11134/11728 [3:17:45<57:22, 5.80s/it] 95%|█████████▍| 11135/11728 [3:17:51<57:33, 5.82s/it] {'loss': 0.4569, 'learning_rate': 1.3379169902603796e-07, 'epoch': 0.95} + 95%|█████████▍| 11135/11728 [3:17:51<57:33, 5.82s/it] 95%|█████████▍| 11136/11728 [3:17:57<57:43, 5.85s/it] {'loss': 0.4518, 'learning_rate': 1.3334184739023147e-07, 'epoch': 0.95} + 95%|█████████▍| 11136/11728 [3:17:57<57:43, 5.85s/it] 95%|█████████▍| 11137/11728 [3:18:02<57:14, 5.81s/it] {'loss': 0.4577, 'learning_rate': 1.3289274822696818e-07, 'epoch': 0.95} + 95%|█████████▍| 11137/11728 [3:18:02<57:14, 5.81s/it] 95%|█████████▍| 11138/11728 [3:18:08<56:45, 5.77s/it] {'loss': 0.4355, 'learning_rate': 1.3244440157049733e-07, 'epoch': 0.95} + 95%|█████████▍| 11138/11728 [3:18:08<56:45, 5.77s/it] 95%|█████████▍| 11139/11728 [3:18:14<56:08, 5.72s/it] {'loss': 0.4519, 'learning_rate': 1.3199680745501265e-07, 'epoch': 0.95} + 95%|█████████▍| 11139/11728 [3:18:14<56:08, 5.72s/it]/lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/VILA/llava/model/llava_arch.py:397: UserWarning: Inputs truncated! + warnings.warn("Inputs truncated!") + 95%|█████████▍| 11140/11728 [3:18:20<57:25, 5.86s/it] {'loss': 0.4451, 'learning_rate': 1.315499659146491e-07, 'epoch': 0.95} + 95%|█████████▍| 11140/11728 [3:18:20<57:25, 5.86s/it] 95%|█████████▍| 11141/11728 [3:18:25<56:33, 5.78s/it] {'loss': 0.4382, 'learning_rate': 1.3110387698348493e-07, 'epoch': 0.95} + 95%|█████████▍| 11141/11728 [3:18:25<56:33, 5.78s/it] 95%|█████████▌| 11142/11728 [3:18:31<56:14, 5.76s/it] {'loss': 0.4723, 'learning_rate': 1.3065854069553963e-07, 'epoch': 0.95} + 95%|█████████▌| 11142/11728 [3:18:31<56:14, 5.76s/it] 95%|█████████▌| 11143/11728 [3:18:37<56:38, 5.81s/it] {'loss': 0.4612, 'learning_rate': 1.3021395708477824e-07, 'epoch': 0.95} + 95%|█████████▌| 11143/11728 [3:18:37<56:38, 5.81s/it] 95%|█████████▌| 11144/11728 [3:18:43<56:31, 5.81s/it] {'loss': 0.4486, 'learning_rate': 1.2977012618510477e-07, 'epoch': 0.95} + 95%|█████████▌| 11144/11728 [3:18:43<56:31, 5.81s/it] 95%|█████████▌| 11145/11728 [3:18:49<56:55, 5.86s/it] {'loss': 0.4362, 'learning_rate': 1.2932704803036877e-07, 'epoch': 0.95} + 95%|█████████▌| 11145/11728 [3:18:49<56:55, 5.86s/it] 95%|█████████▌| 11146/11728 [3:18:54<56:25, 5.82s/it] {'loss': 0.4738, 'learning_rate': 1.2888472265436104e-07, 'epoch': 0.95} + 95%|█████████▌| 11146/11728 [3:18:54<56:25, 5.82s/it] 95%|█████████▌| 11147/11728 [3:19:00<56:23, 5.82s/it] {'loss': 0.459, 'learning_rate': 1.2844315009081453e-07, 'epoch': 0.95} + 95%|█████████▌| 11147/11728 [3:19:00<56:23, 5.82s/it] 95%|█████████▌| 11148/11728 [3:19:06<56:45, 5.87s/it] {'loss': 0.46, 'learning_rate': 1.280023303734057e-07, 'epoch': 0.95} + 95%|█████████▌| 11148/11728 [3:19:06<56:45, 5.87s/it] 95%|█████████▌| 11149/11728 [3:19:12<56:31, 5.86s/it] {'loss': 0.4405, 'learning_rate': 1.2756226353575428e-07, 'epoch': 0.95} + 95%|█████████▌| 11149/11728 [3:19:12<56:31, 5.86s/it]6 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +52 AutoResumeHook: Checking whether to suspend... 0AutoResumeHook: Checking whether to suspend... + + AutoResumeHook: Checking whether to suspend... + 95%|█████████▌| 11150/11728 [3:19:18<56:15, 5.84s/it] {'loss': 0.4577, 'learning_rate': 1.2712294961142125e-07, 'epoch': 0.95} + 95%|█████████▌| 11150/11728 [3:19:18<56:15, 5.84s/it] 95%|█████████▌| 11151/11728 [3:19:24<55:45, 5.80s/it] {'loss': 0.4326, 'learning_rate': 1.2668438863390975e-07, 'epoch': 0.95} + 95%|█████████▌| 11151/11728 [3:19:24<55:45, 5.80s/it] 95%|█████████▌| 11152/11728 [3:19:29<55:15, 5.76s/it] {'loss': 0.4452, 'learning_rate': 1.262465806366664e-07, 'epoch': 0.95} + 95%|█████████▌| 11152/11728 [3:19:29<55:15, 5.76s/it] 95%|█████████▌| 11153/11728 [3:19:35<55:24, 5.78s/it] {'loss': 0.4548, 'learning_rate': 1.2580952565308002e-07, 'epoch': 0.95} + 95%|█████████▌| 11153/11728 [3:19:35<55:24, 5.78s/it] 95%|█████████▌| 11154/11728 [3:19:41<55:17, 5.78s/it] {'loss': 0.4275, 'learning_rate': 1.2537322371648286e-07, 'epoch': 0.95} + 95%|█████████▌| 11154/11728 [3:19:41<55:17, 5.78s/it] 95%|█████████▌| 11155/11728 [3:19:46<54:27, 5.70s/it] {'loss': 0.4595, 'learning_rate': 1.249376748601494e-07, 'epoch': 0.95} + 95%|█████████▌| 11155/11728 [3:19:46<54:27, 5.70s/it] 95%|█████████▌| 11156/11728 [3:19:52<54:51, 5.75s/it] {'loss': 0.4445, 'learning_rate': 1.245028791172964e-07, 'epoch': 0.95} + 95%|█████████▌| 11156/11728 [3:19:52<54:51, 5.75s/it] 95%|█████████▌| 11157/11728 [3:19:58<55:18, 5.81s/it] {'loss': 0.4728, 'learning_rate': 1.2406883652108182e-07, 'epoch': 0.95} + 95%|█████████▌| 11157/11728 [3:19:58<55:18, 5.81s/it] 95%|█████████▌| 11158/11728 [3:20:04<56:19, 5.93s/it] {'loss': 0.4463, 'learning_rate': 1.2363554710460913e-07, 'epoch': 0.95} + 95%|█████████▌| 11158/11728 [3:20:04<56:19, 5.93s/it] 95%|█████████▌| 11159/11728 [3:20:10<55:27, 5.85s/it] {'loss': 0.45, 'learning_rate': 1.2320301090092301e-07, 'epoch': 0.95} + 95%|█████████▌| 11159/11728 [3:20:10<55:27, 5.85s/it] 95%|█████████▌| 11160/11728 [3:20:16<55:28, 5.86s/it] {'loss': 0.4638, 'learning_rate': 1.2277122794300822e-07, 'epoch': 0.95} + 95%|█████████▌| 11160/11728 [3:20:16<55:28, 5.86s/it] 95%|█████████▌| 11161/11728 [3:20:22<54:57, 5.82s/it] {'loss': 0.4349, 'learning_rate': 1.2234019826379618e-07, 'epoch': 0.95} + 95%|█████████▌| 11161/11728 [3:20:22<54:57, 5.82s/it] 95%|█████████▌| 11162/11728 [3:20:28<55:24, 5.87s/it] {'loss': 0.4557, 'learning_rate': 1.2190992189615836e-07, 'epoch': 0.95} + 95%|█████████▌| 11162/11728 [3:20:28<55:24, 5.87s/it] 95%|█████████▌| 11163/11728 [3:20:33<54:50, 5.82s/it] {'loss': 0.4634, 'learning_rate': 1.2148039887290963e-07, 'epoch': 0.95} + 95%|█████████▌| 11163/11728 [3:20:33<54:50, 5.82s/it] 95%|█████████▌| 11164/11728 [3:20:39<54:38, 5.81s/it] {'loss': 0.4286, 'learning_rate': 1.2105162922680823e-07, 'epoch': 0.95} + 95%|█████████▌| 11164/11728 [3:20:39<54:38, 5.81s/it] 95%|█████████▌| 11165/11728 [3:20:45<54:57, 5.86s/it] {'loss': 0.4577, 'learning_rate': 1.2062361299055247e-07, 'epoch': 0.95} + 95%|█████████▌| 11165/11728 [3:20:45<54:57, 5.86s/it] 95%|█████████▌| 11166/11728 [3:20:51<55:04, 5.88s/it] {'loss': 0.4493, 'learning_rate': 1.201963501967851e-07, 'epoch': 0.95} + 95%|█████████▌| 11166/11728 [3:20:51<55:04, 5.88s/it] 95%|█████████▌| 11167/11728 [3:20:57<54:40, 5.85s/it] {'loss': 0.4532, 'learning_rate': 1.1976984087809007e-07, 'epoch': 0.95} + 95%|█████████▌| 11167/11728 [3:20:57<54:40, 5.85s/it] 95%|█████████▌| 11168/11728 [3:21:02<53:56, 5.78s/it] {'loss': 0.4614, 'learning_rate': 1.19344085066998e-07, 'epoch': 0.95} + 95%|█████████▌| 11168/11728 [3:21:02<53:56, 5.78s/it] 95%|█████████▌| 11169/11728 [3:21:08<53:15, 5.72s/it] {'loss': 0.4585, 'learning_rate': 1.1891908279597519e-07, 'epoch': 0.95} + 95%|█████████▌| 11169/11728 [3:21:08<53:15, 5.72s/it] 95%|█████████▌| 11170/11728 [3:21:14<52:59, 5.70s/it] {'loss': 0.4547, 'learning_rate': 1.1849483409743457e-07, 'epoch': 0.95} + 95%|█████████▌| 11170/11728 [3:21:14<52:59, 5.70s/it] 95%|█████████▌| 11171/11728 [3:21:19<52:39, 5.67s/it] {'loss': 0.4472, 'learning_rate': 1.1807133900373246e-07, 'epoch': 0.95} + 95%|█████████▌| 11171/11728 [3:21:19<52:39, 5.67s/it] 95%|█████████▌| 11172/11728 [3:21:25<52:55, 5.71s/it] {'loss': 0.4495, 'learning_rate': 1.176485975471664e-07, 'epoch': 0.95} + 95%|█████████▌| 11172/11728 [3:21:25<52:55, 5.71s/it] 95%|█████████▌| 11173/11728 [3:21:31<53:19, 5.76s/it] {'loss': 0.4726, 'learning_rate': 1.1722660975997501e-07, 'epoch': 0.95} + 95%|█████████▌| 11173/11728 [3:21:31<53:19, 5.76s/it] 95%|█████████▌| 11174/11728 [3:21:37<54:00, 5.85s/it] {'loss': 0.4655, 'learning_rate': 1.1680537567434259e-07, 'epoch': 0.95} + 95%|█████████▌| 11174/11728 [3:21:37<54:00, 5.85s/it] 95%|█████████▌| 11175/11728 [3:21:43<54:04, 5.87s/it] {'loss': 0.4449, 'learning_rate': 1.1638489532239339e-07, 'epoch': 0.95} + 95%|█████████▌| 11175/11728 [3:21:43<54:04, 5.87s/it] 95%|█████████▌| 11176/11728 [3:21:49<53:10, 5.78s/it] {'loss': 0.456, 'learning_rate': 1.1596516873619401e-07, 'epoch': 0.95} + 95%|█████████▌| 11176/11728 [3:21:49<53:10, 5.78s/it] 95%|█████████▌| 11177/11728 [3:21:55<54:20, 5.92s/it] {'loss': 0.4299, 'learning_rate': 1.1554619594775663e-07, 'epoch': 0.95} + 95%|█████████▌| 11177/11728 [3:21:55<54:20, 5.92s/it] 95%|█████████▌| 11178/11728 [3:22:00<53:33, 5.84s/it] {'loss': 0.4617, 'learning_rate': 1.1512797698903122e-07, 'epoch': 0.95} + 95%|█████████▌| 11178/11728 [3:22:00<53:33, 5.84s/it] 95%|█████████▌| 11179/11728 [3:22:06<52:55, 5.78s/it] {'loss': 0.4518, 'learning_rate': 1.1471051189191562e-07, 'epoch': 0.95} + 95%|█████████▌| 11179/11728 [3:22:06<52:55, 5.78s/it] 95%|█████████▌| 11180/11728 [3:22:12<53:05, 5.81s/it] {'loss': 0.4374, 'learning_rate': 1.1429380068824547e-07, 'epoch': 0.95} + 95%|█████████▌| 11180/11728 [3:22:12<53:05, 5.81s/it] 95%|█████████▌| 11181/11728 [3:22:18<52:15, 5.73s/it] {'loss': 0.4468, 'learning_rate': 1.1387784340980201e-07, 'epoch': 0.95} + 95%|█████████▌| 11181/11728 [3:22:18<52:15, 5.73s/it] 95%|█████████▌| 11182/11728 [3:22:23<52:28, 5.77s/it] {'loss': 0.4498, 'learning_rate': 1.1346264008830765e-07, 'epoch': 0.95} + 95%|█████████▌| 11182/11728 [3:22:23<52:28, 5.77s/it] 95%|█████████▌| 11183/11728 [3:22:29<52:16, 5.76s/it] {'loss': 0.4418, 'learning_rate': 1.1304819075542706e-07, 'epoch': 0.95} + 95%|█████████▌| 11183/11728 [3:22:29<52:16, 5.76s/it] 95%|█████████▌| 11184/11728 [3:22:35<52:53, 5.83s/it] {'loss': 0.428, 'learning_rate': 1.1263449544276938e-07, 'epoch': 0.95} + 95%|█████████▌| 11184/11728 [3:22:35<52:53, 5.83s/it] 95%|█████████▌| 11185/11728 [3:22:41<52:45, 5.83s/it] {'loss': 0.4761, 'learning_rate': 1.1222155418188163e-07, 'epoch': 0.95} + 95%|█████████▌| 11185/11728 [3:22:41<52:45, 5.83s/it] 95%|█████████▌| 11186/11728 [3:22:47<52:37, 5.83s/it] {'loss': 0.4554, 'learning_rate': 1.118093670042597e-07, 'epoch': 0.95} + 95%|█████████▌| 11186/11728 [3:22:47<52:37, 5.83s/it] 95%|█████████▌| 11187/11728 [3:22:52<52:04, 5.78s/it] {'loss': 0.4336, 'learning_rate': 1.1139793394133736e-07, 'epoch': 0.95} + 95%|█████████▌| 11187/11728 [3:22:52<52:04, 5.78s/it] 95%|█████████▌| 11188/11728 [3:22:58<52:27, 5.83s/it] {'loss': 0.4504, 'learning_rate': 1.109872550244917e-07, 'epoch': 0.95} + 95%|█████████▌| 11188/11728 [3:22:58<52:27, 5.83s/it] 95%|█████████▌| 11189/11728 [3:23:04<51:40, 5.75s/it] {'loss': 0.457, 'learning_rate': 1.1057733028504325e-07, 'epoch': 0.95} + 95%|█████████▌| 11189/11728 [3:23:04<51:40, 5.75s/it] 95%|█████████▌| 11190/11728 [3:23:09<50:55, 5.68s/it] {'loss': 0.447, 'learning_rate': 1.1016815975425587e-07, 'epoch': 0.95} + 95%|█████████▌| 11190/11728 [3:23:09<50:55, 5.68s/it] 95%|█████████▌| 11191/11728 [3:23:15<50:57, 5.69s/it] {'loss': 0.4383, 'learning_rate': 1.097597434633324e-07, 'epoch': 0.95} + 95%|█████████▌| 11191/11728 [3:23:15<50:57, 5.69s/it] 95%|█████████▌| 11192/11728 [3:23:21<50:42, 5.68s/it] {'loss': 0.4527, 'learning_rate': 1.0935208144342125e-07, 'epoch': 0.95} + 95%|█████████▌| 11192/11728 [3:23:21<50:42, 5.68s/it] 95%|█████████▌| 11193/11728 [3:23:27<52:05, 5.84s/it] {'loss': 0.4472, 'learning_rate': 1.089451737256142e-07, 'epoch': 0.95} + 95%|█████████▌| 11193/11728 [3:23:27<52:05, 5.84s/it] 95%|█████████▌| 11194/11728 [3:23:33<51:26, 5.78s/it] {'loss': 0.4591, 'learning_rate': 1.0853902034093977e-07, 'epoch': 0.95} + 95%|█████████▌| 11194/11728 [3:23:33<51:26, 5.78s/it] 95%|█████████▌| 11195/11728 [3:23:39<51:53, 5.84s/it] {'loss': 0.4611, 'learning_rate': 1.0813362132037652e-07, 'epoch': 0.95} + 95%|█████████▌| 11195/11728 [3:23:39<51:53, 5.84s/it] 95%|█████████▌| 11196/11728 [3:23:44<51:23, 5.80s/it] {'loss': 0.4541, 'learning_rate': 1.0772897669484084e-07, 'epoch': 0.95} + 95%|█████████▌| 11196/11728 [3:23:44<51:23, 5.80s/it] 95%|█████████▌| 11197/11728 [3:23:50<51:37, 5.83s/it] {'loss': 0.4464, 'learning_rate': 1.0732508649519247e-07, 'epoch': 0.95} + 95%|█████████▌| 11197/11728 [3:23:50<51:37, 5.83s/it] 95%|█████████▌| 11198/11728 [3:23:56<51:43, 5.85s/it] {'loss': 0.463, 'learning_rate': 1.0692195075223233e-07, 'epoch': 0.95} + 95%|█████████▌| 11198/11728 [3:23:56<51:43, 5.85s/it] 95%|█████████▌| 11199/11728 [3:24:02<50:53, 5.77s/it] {'loss': 0.4446, 'learning_rate': 1.0651956949670805e-07, 'epoch': 0.95} + 95%|█████████▌| 11199/11728 [3:24:02<50:53, 5.77s/it]6 AutoResumeHook: Checking whether to suspend... +53 AutoResumeHook: Checking whether to suspend... +AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +0 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... + 95%|█████████▌| 11200/11728 [3:24:08<51:23, 5.84s/it]2 AutoResumeHook: Checking whether to suspend...7 + AutoResumeHook: Checking whether to suspend... + {'loss': 0.4544, 'learning_rate': 1.0611794275930398e-07, 'epoch': 0.95} + 95%|█████████▌| 11200/11728 [3:24:08<51:23, 5.84s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-11200/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-11200/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-11200/mm_projector +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/torch/nn/modules/module.py:1802: UserWarning: Positional args are being deprecated, use kwargs instead. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details. + warnings.warn( + 96%|█████████▌| 11201/11728 [3:24:41<2:02:24, 13.94s/it] {'loss': 0.4527, 'learning_rate': 1.0571707057065229e-07, 'epoch': 0.96} + 96%|█████████▌| 11201/11728 [3:24:41<2:02:24, 13.94s/it] 96%|█████████▌| 11202/11728 [3:24:46<1:40:28, 11.46s/it] {'loss': 0.4584, 'learning_rate': 1.0531695296132515e-07, 'epoch': 0.96} + 96%|█████████▌| 11202/11728 [3:24:46<1:40:28, 11.46s/it] 96%|█████████▌| 11203/11728 [3:24:52<1:25:22, 9.76s/it] {'loss': 0.442, 'learning_rate': 1.0491758996183487e-07, 'epoch': 0.96} + 96%|█████████▌| 11203/11728 [3:24:52<1:25:22, 9.76s/it] 96%|█████████▌| 11204/11728 [3:24:58<1:14:17, 8.51s/it] {'loss': 0.4488, 'learning_rate': 1.045189816026393e-07, 'epoch': 0.96} + 96%|█████████▌| 11204/11728 [3:24:58<1:14:17, 8.51s/it] 96%|█████████▌| 11205/11728 [3:25:04<1:07:47, 7.78s/it] {'loss': 0.4419, 'learning_rate': 1.0412112791414075e-07, 'epoch': 0.96} + 96%|█████████▌| 11205/11728 [3:25:04<1:07:47, 7.78s/it] 96%|█████████▌| 11206/11728 [3:25:09<1:02:25, 7.18s/it] {'loss': 0.4535, 'learning_rate': 1.0372402892667721e-07, 'epoch': 0.96} + 96%|█████████▌| 11206/11728 [3:25:09<1:02:25, 7.18s/it] 96%|█████████▌| 11207/11728 [3:25:16<59:44, 6.88s/it] {'loss': 0.4299, 'learning_rate': 1.0332768467053556e-07, 'epoch': 0.96} + 96%|█████████▌| 11207/11728 [3:25:16<59:44, 6.88s/it] 96%|█████████▌| 11208/11728 [3:25:21<55:54, 6.45s/it] {'loss': 0.4473, 'learning_rate': 1.029320951759416e-07, 'epoch': 0.96} + 96%|█████████▌| 11208/11728 [3:25:21<55:54, 6.45s/it] 96%|█████████▌| 11209/11728 [3:25:27<53:55, 6.23s/it] {'loss': 0.4606, 'learning_rate': 1.0253726047306567e-07, 'epoch': 0.96} + 96%|█████████▌| 11209/11728 [3:25:27<53:55, 6.23s/it] 96%|█████████▌| 11210/11728 [3:25:33<53:07, 6.15s/it] {'loss': 0.453, 'learning_rate': 1.0214318059201922e-07, 'epoch': 0.96} + 96%|█████████▌| 11210/11728 [3:25:33<53:07, 6.15s/it] 96%|█████████▌| 11211/11728 [3:25:39<52:03, 6.04s/it] {'loss': 0.4488, 'learning_rate': 1.01749855562856e-07, 'epoch': 0.96} + 96%|█████████▌| 11211/11728 [3:25:39<52:03, 6.04s/it] 96%|█████████▌| 11212/11728 [3:25:44<50:59, 5.93s/it] {'loss': 0.448, 'learning_rate': 1.0135728541557199e-07, 'epoch': 0.96} + 96%|█████████▌| 11212/11728 [3:25:44<50:59, 5.93s/it] 96%|█████████▌| 11213/11728 [3:25:50<50:37, 5.90s/it] {'loss': 0.4661, 'learning_rate': 1.009654701801066e-07, 'epoch': 0.96} + 96%|█████████▌| 11213/11728 [3:25:50<50:37, 5.90s/it] 96%|█████████▌| 11214/11728 [3:25:57<51:56, 6.06s/it] {'loss': 0.4439, 'learning_rate': 1.005744098863437e-07, 'epoch': 0.96} + 96%|█████████▌| 11214/11728 [3:25:57<51:56, 6.06s/it] 96%|█████████▌| 11215/11728 [3:26:02<51:11, 5.99s/it] {'loss': 0.4469, 'learning_rate': 1.0018410456410388e-07, 'epoch': 0.96} + 96%|█████████▌| 11215/11728 [3:26:02<51:11, 5.99s/it] 96%|█████████▌| 11216/11728 [3:26:08<50:54, 5.97s/it] {'loss': 0.4398, 'learning_rate': 9.979455424315442e-08, 'epoch': 0.96} + 96%|█████████▌| 11216/11728 [3:26:08<50:54, 5.97s/it] 96%|█████████▌| 11217/11728 [3:26:14<50:17, 5.91s/it] {'loss': 0.4658, 'learning_rate': 9.940575895320492e-08, 'epoch': 0.96} + 96%|█████████▌| 11217/11728 [3:26:14<50:17, 5.91s/it] 96%|█████████▌| 11218/11728 [3:26:20<49:40, 5.84s/it] {'loss': 0.4472, 'learning_rate': 9.901771872390497e-08, 'epoch': 0.96} + 96%|█████████▌| 11218/11728 [3:26:20<49:40, 5.84s/it] 96%|█████████▌| 11219/11728 [3:26:25<49:13, 5.80s/it] {'loss': 0.4364, 'learning_rate': 9.863043358485092e-08, 'epoch': 0.96} + 96%|█████████▌| 11219/11728 [3:26:25<49:13, 5.80s/it] 96%|█████████▌| 11220/11728 [3:26:31<49:05, 5.80s/it] {'loss': 0.4682, 'learning_rate': 9.824390356557578e-08, 'epoch': 0.96} + 96%|█████████▌| 11220/11728 [3:26:31<49:05, 5.80s/it] 96%|█████████▌| 11221/11728 [3:26:37<48:53, 5.79s/it] {'loss': 0.4421, 'learning_rate': 9.785812869555933e-08, 'epoch': 0.96} + 96%|█████████▌| 11221/11728 [3:26:37<48:53, 5.79s/it] 96%|█████████▌| 11222/11728 [3:26:43<48:42, 5.78s/it] {'loss': 0.4712, 'learning_rate': 9.747310900422136e-08, 'epoch': 0.96} + 96%|█████████▌| 11222/11728 [3:26:43<48:42, 5.78s/it] 96%|█████████▌| 11223/11728 [3:26:48<48:09, 5.72s/it] {'loss': 0.4265, 'learning_rate': 9.708884452092837e-08, 'epoch': 0.96} + 96%|█████████▌| 11223/11728 [3:26:48<48:09, 5.72s/it] 96%|█████████▌| 11224/11728 [3:26:54<48:21, 5.76s/it] {'loss': 0.4718, 'learning_rate': 9.670533527498139e-08, 'epoch': 0.96} + 96%|█████████▌| 11224/11728 [3:26:54<48:21, 5.76s/it] 96%|█████████▌| 11225/11728 [3:27:00<49:03, 5.85s/it] {'loss': 0.4537, 'learning_rate': 9.632258129563144e-08, 'epoch': 0.96} + 96%|█████████▌| 11225/11728 [3:27:00<49:03, 5.85s/it] 96%|█████████▌| 11226/11728 [3:27:06<49:31, 5.92s/it] {'loss': 0.4379, 'learning_rate': 9.59405826120674e-08, 'epoch': 0.96} + 96%|█████████▌| 11226/11728 [3:27:06<49:31, 5.92s/it] 96%|█████████▌| 11227/11728 [3:27:12<48:56, 5.86s/it] {'loss': 0.4574, 'learning_rate': 9.555933925342265e-08, 'epoch': 0.96} + 96%|█████████▌| 11227/11728 [3:27:12<48:56, 5.86s/it] 96%|█████████▌| 11228/11728 [3:27:18<48:50, 5.86s/it] {'loss': 0.465, 'learning_rate': 9.517885124877279e-08, 'epoch': 0.96} + 96%|█████████▌| 11228/11728 [3:27:18<48:50, 5.86s/it] 96%|█████████▌| 11229/11728 [3:27:24<48:09, 5.79s/it] {'loss': 0.4393, 'learning_rate': 9.479911862713576e-08, 'epoch': 0.96} + 96%|█████████▌| 11229/11728 [3:27:24<48:09, 5.79s/it] 96%|█████████▌| 11230/11728 [3:27:29<48:27, 5.84s/it] {'loss': 0.4452, 'learning_rate': 9.442014141747058e-08, 'epoch': 0.96} + 96%|█████████▌| 11230/11728 [3:27:29<48:27, 5.84s/it] 96%|█████████▌| 11231/11728 [3:27:35<48:21, 5.84s/it] {'loss': 0.4504, 'learning_rate': 9.40419196486786e-08, 'epoch': 0.96} + 96%|█████████▌| 11231/11728 [3:27:35<48:21, 5.84s/it] 96%|█████████▌| 11232/11728 [3:27:41<48:26, 5.86s/it] {'loss': 0.4456, 'learning_rate': 9.366445334960783e-08, 'epoch': 0.96} + 96%|█████████▌| 11232/11728 [3:27:41<48:26, 5.86s/it] 96%|█████████▌| 11233/11728 [3:27:47<47:57, 5.81s/it] {'loss': 0.4754, 'learning_rate': 9.328774254904305e-08, 'epoch': 0.96} + 96%|█████████▌| 11233/11728 [3:27:47<47:57, 5.81s/it] 96%|█████████▌| 11234/11728 [3:27:53<48:11, 5.85s/it] {'loss': 0.4671, 'learning_rate': 9.29117872757146e-08, 'epoch': 0.96} + 96%|█████████▌| 11234/11728 [3:27:53<48:11, 5.85s/it] 96%|█████████▌| 11235/11728 [3:27:59<48:18, 5.88s/it] {'loss': 0.4556, 'learning_rate': 9.253658755829286e-08, 'epoch': 0.96} + 96%|█████████▌| 11235/11728 [3:27:59<48:18, 5.88s/it] 96%|█████████▌| 11236/11728 [3:28:05<47:47, 5.83s/it] {'loss': 0.4667, 'learning_rate': 9.216214342539387e-08, 'epoch': 0.96} + 96%|█████████▌| 11236/11728 [3:28:05<47:47, 5.83s/it] 96%|█████████▌| 11237/11728 [3:28:11<48:18, 5.90s/it] {'loss': 0.4531, 'learning_rate': 9.178845490557475e-08, 'epoch': 0.96} + 96%|█████████▌| 11237/11728 [3:28:11<48:18, 5.90s/it] 96%|█████████▌| 11238/11728 [3:28:17<48:17, 5.91s/it] {'loss': 0.4503, 'learning_rate': 9.141552202733272e-08, 'epoch': 0.96} + 96%|█████████▌| 11238/11728 [3:28:17<48:17, 5.91s/it] 96%|█████████▌| 11239/11728 [3:28:22<47:46, 5.86s/it] {'loss': 0.4469, 'learning_rate': 9.104334481911059e-08, 'epoch': 0.96} + 96%|█████████▌| 11239/11728 [3:28:22<47:46, 5.86s/it] 96%|█████████▌| 11240/11728 [3:28:28<48:08, 5.92s/it] {'loss': 0.4632, 'learning_rate': 9.067192330929009e-08, 'epoch': 0.96} + 96%|█████████▌| 11240/11728 [3:28:28<48:08, 5.92s/it] 96%|█████████▌| 11241/11728 [3:28:34<48:26, 5.97s/it] {'loss': 0.4466, 'learning_rate': 9.030125752620078e-08, 'epoch': 0.96} + 96%|█████████▌| 11241/11728 [3:28:34<48:26, 5.97s/it] 96%|█████████▌| 11242/11728 [3:28:40<48:29, 5.99s/it] {'loss': 0.44, 'learning_rate': 8.993134749810895e-08, 'epoch': 0.96} + 96%|█████████▌| 11242/11728 [3:28:40<48:29, 5.99s/it] 96%|█████████▌| 11243/11728 [3:28:46<48:14, 5.97s/it] {'loss': 0.4614, 'learning_rate': 8.956219325322535e-08, 'epoch': 0.96} + 96%|█████████▌| 11243/11728 [3:28:46<48:14, 5.97s/it] 96%|█████████▌| 11244/11728 [3:28:52<47:14, 5.86s/it] {'loss': 0.4487, 'learning_rate': 8.919379481970414e-08, 'epoch': 0.96} + 96%|█████████▌| 11244/11728 [3:28:52<47:14, 5.86s/it] 96%|█████████▌| 11245/11728 [3:28:58<46:45, 5.81s/it] {'loss': 0.4312, 'learning_rate': 8.88261522256395e-08, 'epoch': 0.96} + 96%|█████████▌| 11245/11728 [3:28:58<46:45, 5.81s/it] 96%|█████████▌| 11246/11728 [3:29:03<46:17, 5.76s/it] {'loss': 0.4475, 'learning_rate': 8.845926549907125e-08, 'epoch': 0.96} + 96%|█████████▌| 11246/11728 [3:29:03<46:17, 5.76s/it] 96%|█████████▌| 11247/11728 [3:29:09<46:57, 5.86s/it] {'loss': 0.4507, 'learning_rate': 8.809313466798031e-08, 'epoch': 0.96} + 96%|█████████▌| 11247/11728 [3:29:09<46:57, 5.86s/it] 96%|█████████▌| 11248/11728 [3:29:15<46:25, 5.80s/it] {'loss': 0.4456, 'learning_rate': 8.772775976028547e-08, 'epoch': 0.96} + 96%|█████████▌| 11248/11728 [3:29:15<46:25, 5.80s/it] 96%|█████████▌| 11249/11728 [3:29:21<46:49, 5.87s/it] {'loss': 0.4361, 'learning_rate': 8.736314080385444e-08, 'epoch': 0.96} + 96%|█████████▌| 11249/11728 [3:29:21<46:49, 5.87s/it]06 AutoResumeHook: Checking whether to suspend... + 7 AutoResumeHook: Checking whether to suspend... +AutoResumeHook: Checking whether to suspend...3 AutoResumeHook: Checking whether to suspend... + +4 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... + 96%|█████████▌| 11250/11728 [3:29:27<46:59, 5.90s/it]1 AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4718, 'learning_rate': 8.699927782649609e-08, 'epoch': 0.96} + 96%|█████████▌| 11250/11728 [3:29:27<46:59, 5.90s/it] 96%|█████████▌| 11251/11728 [3:29:33<46:56, 5.91s/it] {'loss': 0.4512, 'learning_rate': 8.66361708559571e-08, 'epoch': 0.96} + 96%|█████████▌| 11251/11728 [3:29:33<46:56, 5.91s/it] 96%|█████████▌| 11252/11728 [3:29:39<46:20, 5.84s/it] {'loss': 0.4457, 'learning_rate': 8.627381991993089e-08, 'epoch': 0.96} + 96%|█████████▌| 11252/11728 [3:29:39<46:20, 5.84s/it] 96%|█████████▌| 11253/11728 [3:29:45<46:46, 5.91s/it] {'loss': 0.447, 'learning_rate': 8.591222504605201e-08, 'epoch': 0.96} + 96%|█████████▌| 11253/11728 [3:29:45<46:46, 5.91s/it] 96%|█████████▌| 11254/11728 [3:29:50<45:43, 5.79s/it] {'loss': 0.4401, 'learning_rate': 8.555138626189619e-08, 'epoch': 0.96} + 96%|█████████▌| 11254/11728 [3:29:50<45:43, 5.79s/it] 96%|█████████▌| 11255/11728 [3:29:57<47:05, 5.97s/it] {'loss': 0.4421, 'learning_rate': 8.519130359498362e-08, 'epoch': 0.96} + 96%|█████████▌| 11255/11728 [3:29:57<47:05, 5.97s/it] 96%|█████████▌| 11256/11728 [3:30:02<46:38, 5.93s/it] {'loss': 0.4638, 'learning_rate': 8.483197707277568e-08, 'epoch': 0.96} + 96%|█████████▌| 11256/11728 [3:30:02<46:38, 5.93s/it] 96%|█████████▌| 11257/11728 [3:30:09<46:45, 5.96s/it] {'loss': 0.4506, 'learning_rate': 8.44734067226749e-08, 'epoch': 0.96} + 96%|█████████▌| 11257/11728 [3:30:09<46:45, 5.96s/it] 96%|█████████▌| 11258/11728 [3:30:14<46:19, 5.91s/it] {'loss': 0.4484, 'learning_rate': 8.411559257202828e-08, 'epoch': 0.96} + 96%|█████████▌| 11258/11728 [3:30:14<46:19, 5.91s/it] 96%|█████████▌| 11259/11728 [3:30:20<45:43, 5.85s/it] {'loss': 0.4468, 'learning_rate': 8.37585346481251e-08, 'epoch': 0.96} + 96%|█████████▌| 11259/11728 [3:30:20<45:43, 5.85s/it] 96%|█████████▌| 11260/11728 [3:30:26<45:17, 5.81s/it] {'loss': 0.446, 'learning_rate': 8.340223297819472e-08, 'epoch': 0.96} + 96%|█████████▌| 11260/11728 [3:30:26<45:17, 5.81s/it] 96%|█████████▌| 11261/11728 [3:30:31<44:40, 5.74s/it] {'loss': 0.4385, 'learning_rate': 8.304668758941093e-08, 'epoch': 0.96} + 96%|█████████▌| 11261/11728 [3:30:31<44:40, 5.74s/it] 96%|█████████▌| 11262/11728 [3:30:37<44:42, 5.76s/it] {'loss': 0.4606, 'learning_rate': 8.26918985088887e-08, 'epoch': 0.96} + 96%|█████████▌| 11262/11728 [3:30:37<44:42, 5.76s/it] 96%|█████████▌| 11263/11728 [3:30:43<44:27, 5.74s/it] {'loss': 0.4508, 'learning_rate': 8.233786576368418e-08, 'epoch': 0.96} + 96%|█████████▌| 11263/11728 [3:30:43<44:27, 5.74s/it] 96%|█████████▌| 11264/11728 [3:30:49<44:22, 5.74s/it] {'loss': 0.4615, 'learning_rate': 8.198458938080023e-08, 'epoch': 0.96} + 96%|█████████▌| 11264/11728 [3:30:49<44:22, 5.74s/it] 96%|█████████▌| 11265/11728 [3:30:54<44:12, 5.73s/it] {'loss': 0.4301, 'learning_rate': 8.16320693871786e-08, 'epoch': 0.96} + 96%|█████████▌| 11265/11728 [3:30:54<44:12, 5.73s/it] 96%|█████████▌| 11266/11728 [3:31:00<44:29, 5.78s/it] {'loss': 0.4524, 'learning_rate': 8.128030580970336e-08, 'epoch': 0.96} + 96%|█████████▌| 11266/11728 [3:31:00<44:29, 5.78s/it] 96%|█████████▌| 11267/11728 [3:31:06<44:36, 5.81s/it] {'loss': 0.4583, 'learning_rate': 8.092929867519972e-08, 'epoch': 0.96} + 96%|█████████▌| 11267/11728 [3:31:06<44:36, 5.81s/it] 96%|█████████▌| 11268/11728 [3:31:12<44:24, 5.79s/it] {'loss': 0.4411, 'learning_rate': 8.05790480104407e-08, 'epoch': 0.96} + 96%|█████████▌| 11268/11728 [3:31:12<44:24, 5.79s/it] 96%|█████████▌| 11269/11728 [3:31:17<44:02, 5.76s/it] {'loss': 0.4482, 'learning_rate': 8.022955384213493e-08, 'epoch': 0.96} + 96%|█████████▌| 11269/11728 [3:31:17<44:02, 5.76s/it] 96%|█████████▌| 11270/11728 [3:31:23<43:57, 5.76s/it] {'loss': 0.4485, 'learning_rate': 7.988081619693666e-08, 'epoch': 0.96} + 96%|█████████▌| 11270/11728 [3:31:23<43:57, 5.76s/it] 96%|█████████▌| 11271/11728 [3:31:29<43:35, 5.72s/it] {'loss': 0.4305, 'learning_rate': 7.95328351014435e-08, 'epoch': 0.96} + 96%|█████████▌| 11271/11728 [3:31:29<43:35, 5.72s/it] 96%|█████████▌| 11272/11728 [3:31:35<43:37, 5.74s/it] {'loss': 0.45, 'learning_rate': 7.918561058219198e-08, 'epoch': 0.96} + 96%|█████████▌| 11272/11728 [3:31:35<43:37, 5.74s/it] 96%|█████████▌| 11273/11728 [3:31:40<43:28, 5.73s/it] {'loss': 0.4578, 'learning_rate': 7.883914266566427e-08, 'epoch': 0.96} + 96%|█████████▌| 11273/11728 [3:31:40<43:28, 5.73s/it] 96%|█████████▌| 11274/11728 [3:31:46<43:37, 5.77s/it] {'loss': 0.4372, 'learning_rate': 7.849343137828369e-08, 'epoch': 0.96} + 96%|█████████▌| 11274/11728 [3:31:46<43:37, 5.77s/it] 96%|█████████▌| 11275/11728 [3:31:52<43:13, 5.73s/it] {'loss': 0.4456, 'learning_rate': 7.814847674641468e-08, 'epoch': 0.96} + 96%|█████████▌| 11275/11728 [3:31:52<43:13, 5.73s/it] 96%|█████████▌| 11276/11728 [3:31:58<43:12, 5.74s/it] {'loss': 0.463, 'learning_rate': 7.78042787963662e-08, 'epoch': 0.96} + 96%|█████████▌| 11276/11728 [3:31:58<43:12, 5.74s/it] 96%|█████████▌| 11277/11728 [3:32:04<43:40, 5.81s/it] {'loss': 0.4815, 'learning_rate': 7.746083755438616e-08, 'epoch': 0.96} + 96%|█████████▌| 11277/11728 [3:32:04<43:40, 5.81s/it] 96%|█████████▌| 11278/11728 [3:32:10<43:53, 5.85s/it] {'loss': 0.418, 'learning_rate': 7.711815304666804e-08, 'epoch': 0.96} + 96%|█████████▌| 11278/11728 [3:32:10<43:53, 5.85s/it] 96%|█████████▌| 11279/11728 [3:32:15<43:54, 5.87s/it] {'loss': 0.4534, 'learning_rate': 7.677622529934648e-08, 'epoch': 0.96} + 96%|█████████▌| 11279/11728 [3:32:15<43:54, 5.87s/it] 96%|█████████▌| 11280/11728 [3:32:21<44:05, 5.91s/it] {'loss': 0.4446, 'learning_rate': 7.643505433849952e-08, 'epoch': 0.96} + 96%|█████████▌| 11280/11728 [3:32:21<44:05, 5.91s/it] 96%|█████████▌| 11281/11728 [3:32:27<43:47, 5.88s/it] {'loss': 0.4393, 'learning_rate': 7.609464019014301e-08, 'epoch': 0.96} + 96%|█████████▌| 11281/11728 [3:32:27<43:47, 5.88s/it] 96%|█████████▌| 11282/11728 [3:32:33<43:31, 5.86s/it] {'loss': 0.4612, 'learning_rate': 7.575498288024174e-08, 'epoch': 0.96} + 96%|█████████▌| 11282/11728 [3:32:33<43:31, 5.86s/it] 96%|█████████▌| 11283/11728 [3:32:39<42:41, 5.76s/it] {'loss': 0.4473, 'learning_rate': 7.541608243469723e-08, 'epoch': 0.96} + 96%|█████████▌| 11283/11728 [3:32:39<42:41, 5.76s/it] 96%|█████████▌| 11284/11728 [3:32:44<42:50, 5.79s/it] {'loss': 0.4308, 'learning_rate': 7.507793887935655e-08, 'epoch': 0.96} + 96%|█████████▌| 11284/11728 [3:32:44<42:50, 5.79s/it] 96%|█████████▌| 11285/11728 [3:32:50<43:18, 5.87s/it] {'loss': 0.4453, 'learning_rate': 7.474055224000688e-08, 'epoch': 0.96} + 96%|█████████▌| 11285/11728 [3:32:50<43:18, 5.87s/it] 96%|█████████▌| 11286/11728 [3:32:56<42:49, 5.81s/it] {'loss': 0.4487, 'learning_rate': 7.440392254237983e-08, 'epoch': 0.96} + 96%|█████████▌| 11286/11728 [3:32:56<42:49, 5.81s/it][2025-06-28 06:56:08,961] [WARNING] [stage3.py:1850:step] 1 pytorch allocator cache flushes since last step. this happens when there is high memory pressure and is detrimental to performance. if this is happening frequently consider adjusting settings to reduce memory consumption. If you are unable to make the cache flushes go away consider adding get_accelerator().empty_cache() calls in your training loop to ensure that all ranks flush their caches at the same time + 96%|█████████▌| 11287/11728 [3:33:03<44:12, 6.01s/it] {'loss': 0.4492, 'learning_rate': 7.406804981214822e-08, 'epoch': 0.96} + 96%|█████████▌| 11287/11728 [3:33:03<44:12, 6.01s/it] 96%|█████████▌| 11288/11728 [3:33:08<43:25, 5.92s/it] {'loss': 0.4785, 'learning_rate': 7.373293407492598e-08, 'epoch': 0.96} + 96%|█████████▌| 11288/11728 [3:33:08<43:25, 5.92s/it] 96%|█████████▋| 11289/11728 [3:33:14<42:23, 5.79s/it] {'loss': 0.4528, 'learning_rate': 7.33985753562716e-08, 'epoch': 0.96} + 96%|█████████▋| 11289/11728 [3:33:14<42:23, 5.79s/it] 96%|█████████▋| 11290/11728 [3:33:19<41:52, 5.74s/it] {'loss': 0.4499, 'learning_rate': 7.306497368168352e-08, 'epoch': 0.96} + 96%|█████████▋| 11290/11728 [3:33:19<41:52, 5.74s/it] 96%|█████████▋| 11291/11728 [3:33:25<41:37, 5.72s/it] {'loss': 0.4408, 'learning_rate': 7.273212907660476e-08, 'epoch': 0.96} + 96%|█████████▋| 11291/11728 [3:33:25<41:37, 5.72s/it] 96%|█████████▋| 11292/11728 [3:33:31<41:44, 5.74s/it] {'loss': 0.4683, 'learning_rate': 7.240004156641944e-08, 'epoch': 0.96} + 96%|█████████▋| 11292/11728 [3:33:31<41:44, 5.74s/it] 96%|█████████▋| 11293/11728 [3:33:37<41:41, 5.75s/it] {'loss': 0.451, 'learning_rate': 7.206871117645286e-08, 'epoch': 0.96} + 96%|█████████▋| 11293/11728 [3:33:37<41:41, 5.75s/it] 96%|█████████▋| 11294/11728 [3:33:43<41:50, 5.79s/it] {'loss': 0.4402, 'learning_rate': 7.17381379319737e-08, 'epoch': 0.96} + 96%|█████████▋| 11294/11728 [3:33:43<41:50, 5.79s/it] 96%|█████████▋| 11295/11728 [3:33:49<42:46, 5.93s/it] {'loss': 0.4633, 'learning_rate': 7.140832185819402e-08, 'epoch': 0.96} + 96%|█████████▋| 11295/11728 [3:33:49<42:46, 5.93s/it] 96%|█████████▋| 11296/11728 [3:33:55<42:37, 5.92s/it] {'loss': 0.4634, 'learning_rate': 7.10792629802659e-08, 'epoch': 0.96} + 96%|█████████▋| 11296/11728 [3:33:55<42:37, 5.92s/it] 96%|█████████▋| 11297/11728 [3:34:00<42:09, 5.87s/it] {'loss': 0.4277, 'learning_rate': 7.075096132328597e-08, 'epoch': 0.96} + 96%|█████████▋| 11297/11728 [3:34:00<42:09, 5.87s/it] 96%|█████████▋| 11298/11728 [3:34:06<41:21, 5.77s/it] {'loss': 0.4409, 'learning_rate': 7.042341691229082e-08, 'epoch': 0.96} + 96%|█████████▋| 11298/11728 [3:34:06<41:21, 5.77s/it] 96%|█████████▋| 11299/11728 [3:34:12<40:46, 5.70s/it] {'loss': 0.4445, 'learning_rate': 7.00966297722605e-08, 'epoch': 0.96} + 96%|█████████▋| 11299/11728 [3:34:12<40:46, 5.70s/it]064 AutoResumeHook: Checking whether to suspend... +AutoResumeHook: Checking whether to suspend... + 3 AutoResumeHook: Checking whether to suspend... +AutoResumeHook: Checking whether to suspend... + 96%|█████████▋| 11300/11728 [3:34:17<40:47, 5.72s/it]7 AutoResumeHook: Checking whether to suspend... +52 AutoResumeHook: Checking whether to suspend...AutoResumeHook: Checking whether to suspend... + +1 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4304, 'learning_rate': 6.977059992811619e-08, 'epoch': 0.96} + 96%|█████████▋| 11300/11728 [3:34:17<40:47, 5.72s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-11300/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-11300/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-11300/mm_projector +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/torch/nn/modules/module.py:1802: UserWarning: Positional args are being deprecated, use kwargs instead. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details. + warnings.warn( + 96%|█████████▋| 11301/11728 [3:34:52<1:42:18, 14.38s/it] {'loss': 0.4406, 'learning_rate': 6.944532740472464e-08, 'epoch': 0.96} + 96%|█████████▋| 11301/11728 [3:34:52<1:42:18, 14.38s/it] 96%|█████████▋| 11302/11728 [3:34:57<1:23:16, 11.73s/it] {'loss': 0.461, 'learning_rate': 6.91208122268916e-08, 'epoch': 0.96} + 96%|█████████▋| 11302/11728 [3:34:57<1:23:16, 11.73s/it] 96%|█████████▋| 11303/11728 [3:35:03<1:10:13, 9.91s/it] {'loss': 0.4427, 'learning_rate': 6.879705441936502e-08, 'epoch': 0.96} + 96%|█████████▋| 11303/11728 [3:35:03<1:10:13, 9.91s/it] 96%|█████████▋| 11304/11728 [3:35:09<1:02:25, 8.83s/it] {'loss': 0.4481, 'learning_rate': 6.847405400683626e-08, 'epoch': 0.96} + 96%|█████████▋| 11304/11728 [3:35:09<1:02:25, 8.83s/it] 96%|█████████▋| 11305/11728 [3:35:15<55:52, 7.93s/it] {'loss': 0.4703, 'learning_rate': 6.815181101393898e-08, 'epoch': 0.96} + 96%|█████████▋| 11305/11728 [3:35:15<55:52, 7.93s/it] 96%|█████████▋| 11306/11728 [3:35:21<51:25, 7.31s/it] {'loss': 0.4439, 'learning_rate': 6.783032546524904e-08, 'epoch': 0.96} + 96%|█████████▋| 11306/11728 [3:35:21<51:25, 7.31s/it] 96%|█████████▋| 11307/11728 [3:35:27<47:44, 6.80s/it] {'loss': 0.4347, 'learning_rate': 6.750959738528462e-08, 'epoch': 0.96} + 96%|█████████▋| 11307/11728 [3:35:27<47:44, 6.80s/it] 96%|█████████▋| 11308/11728 [3:35:32<45:27, 6.49s/it] {'loss': 0.4556, 'learning_rate': 6.718962679850504e-08, 'epoch': 0.96} + 96%|█████████▋| 11308/11728 [3:35:32<45:27, 6.49s/it] 96%|█████████▋| 11309/11728 [3:35:38<43:53, 6.29s/it] {'loss': 0.4536, 'learning_rate': 6.687041372931192e-08, 'epoch': 0.96} + 96%|█████████▋| 11309/11728 [3:35:38<43:53, 6.29s/it] 96%|█████████▋| 11310/11728 [3:35:44<43:18, 6.22s/it] {'loss': 0.4418, 'learning_rate': 6.65519582020513e-08, 'epoch': 0.96} + 96%|█████████▋| 11310/11728 [3:35:44<43:18, 6.22s/it] 96%|█████████▋| 11311/11728 [3:35:50<41:59, 6.04s/it] {'loss': 0.5019, 'learning_rate': 6.623426024100931e-08, 'epoch': 0.96} + 96%|█████████▋| 11311/11728 [3:35:50<41:59, 6.04s/it] 96%|█████████▋| 11312/11728 [3:35:56<42:05, 6.07s/it] {'loss': 0.4575, 'learning_rate': 6.591731987041439e-08, 'epoch': 0.96} + 96%|█████████▋| 11312/11728 [3:35:56<42:05, 6.07s/it] 96%|█████████▋| 11313/11728 [3:36:02<41:35, 6.01s/it] {'loss': 0.4517, 'learning_rate': 6.560113711443938e-08, 'epoch': 0.96} + 96%|█████████▋| 11313/11728 [3:36:02<41:35, 6.01s/it] 96%|█████████▋| 11314/11728 [3:36:08<40:37, 5.89s/it] {'loss': 0.4495, 'learning_rate': 6.528571199719502e-08, 'epoch': 0.96} + 96%|█████████▋| 11314/11728 [3:36:08<40:37, 5.89s/it] 96%|█████████▋| 11315/11728 [3:36:13<40:31, 5.89s/it] {'loss': 0.4403, 'learning_rate': 6.497104454273872e-08, 'epoch': 0.96} + 96%|█████████▋| 11315/11728 [3:36:13<40:31, 5.89s/it] 96%|█████████▋| 11316/11728 [3:36:19<40:23, 5.88s/it] {'loss': 0.4417, 'learning_rate': 6.465713477506907e-08, 'epoch': 0.96} + 96%|█████████▋| 11316/11728 [3:36:19<40:23, 5.88s/it] 96%|█████████▋| 11317/11728 [3:36:25<40:19, 5.89s/it] {'loss': 0.4425, 'learning_rate': 6.43439827181247e-08, 'epoch': 0.96} + 96%|█████████▋| 11317/11728 [3:36:25<40:19, 5.89s/it] 97%|█████████▋| 11318/11728 [3:36:31<39:44, 5.81s/it] {'loss': 0.4616, 'learning_rate': 6.403158839578761e-08, 'epoch': 0.97} + 97%|█████████▋| 11318/11728 [3:36:31<39:44, 5.81s/it] 97%|█████████▋| 11319/11728 [3:36:36<39:06, 5.74s/it] {'loss': 0.4299, 'learning_rate': 6.371995183188429e-08, 'epoch': 0.97} + 97%|█████████▋| 11319/11728 [3:36:36<39:06, 5.74s/it] 97%|█████████▋| 11320/11728 [3:36:42<39:24, 5.80s/it] {'loss': 0.4372, 'learning_rate': 6.340907305017907e-08, 'epoch': 0.97} + 97%|█████████▋| 11320/11728 [3:36:42<39:24, 5.80s/it] 97%|█████████▋| 11321/11728 [3:36:48<39:05, 5.76s/it] {'loss': 0.4676, 'learning_rate': 6.309895207438188e-08, 'epoch': 0.97} + 97%|█████████▋| 11321/11728 [3:36:48<39:05, 5.76s/it] 97%|█████████▋| 11322/11728 [3:36:54<39:04, 5.77s/it] {'loss': 0.4622, 'learning_rate': 6.27895889281438e-08, 'epoch': 0.97} + 97%|█████████▋| 11322/11728 [3:36:54<39:04, 5.77s/it] 97%|█████████▋| 11323/11728 [3:37:00<39:06, 5.79s/it] {'loss': 0.4506, 'learning_rate': 6.248098363505928e-08, 'epoch': 0.97} + 97%|█████████▋| 11323/11728 [3:37:00<39:06, 5.79s/it] 97%|█████████▋| 11324/11728 [3:37:05<38:49, 5.77s/it] {'loss': 0.4437, 'learning_rate': 6.217313621866283e-08, 'epoch': 0.97} + 97%|█████████▋| 11324/11728 [3:37:05<38:49, 5.77s/it] 97%|█████████▋| 11325/11728 [3:37:11<38:34, 5.74s/it] {'loss': 0.4586, 'learning_rate': 6.186604670243124e-08, 'epoch': 0.97} + 97%|█████████▋| 11325/11728 [3:37:11<38:34, 5.74s/it] 97%|█████████▋| 11326/11728 [3:37:17<38:22, 5.73s/it] {'loss': 0.4371, 'learning_rate': 6.155971510978576e-08, 'epoch': 0.97} + 97%|█████████▋| 11326/11728 [3:37:17<38:22, 5.73s/it] 97%|█████████▋| 11327/11728 [3:37:23<38:21, 5.74s/it] {'loss': 0.4586, 'learning_rate': 6.12541414640877e-08, 'epoch': 0.97} + 97%|█████████▋| 11327/11728 [3:37:23<38:21, 5.74s/it] 97%|█████████▋| 11328/11728 [3:37:28<38:28, 5.77s/it] {'loss': 0.4687, 'learning_rate': 6.094932578864288e-08, 'epoch': 0.97} + 97%|█████████▋| 11328/11728 [3:37:28<38:28, 5.77s/it] 97%|█████████▋| 11329/11728 [3:37:35<39:16, 5.91s/it] {'loss': 0.4497, 'learning_rate': 6.064526810669602e-08, 'epoch': 0.97} + 97%|█████████▋| 11329/11728 [3:37:35<39:16, 5.91s/it] 97%|█████████▋| 11330/11728 [3:37:40<38:26, 5.79s/it] {'loss': 0.4482, 'learning_rate': 6.034196844143747e-08, 'epoch': 0.97} + 97%|█████████▋| 11330/11728 [3:37:40<38:26, 5.79s/it] 97%|█████████▋| 11331/11728 [3:37:46<38:45, 5.86s/it] {'loss': 0.4623, 'learning_rate': 6.00394268159965e-08, 'epoch': 0.97} + 97%|█████████▋| 11331/11728 [3:37:46<38:45, 5.86s/it] 97%|█████████▋| 11332/11728 [3:37:52<39:13, 5.94s/it] {'loss': 0.4709, 'learning_rate': 5.973764325344689e-08, 'epoch': 0.97} + 97%|█████████▋| 11332/11728 [3:37:52<39:13, 5.94s/it] 97%|█████████▋| 11333/11728 [3:37:58<39:04, 5.93s/it] {'loss': 0.4272, 'learning_rate': 5.943661777680354e-08, 'epoch': 0.97} + 97%|█████████▋| 11333/11728 [3:37:58<39:04, 5.93s/it] 97%|█████████▋| 11334/11728 [3:38:04<39:02, 5.94s/it] {'loss': 0.4487, 'learning_rate': 5.9136350409024766e-08, 'epoch': 0.97} + 97%|█████████▋| 11334/11728 [3:38:04<39:02, 5.94s/it] 97%|█████████▋| 11335/11728 [3:38:10<38:17, 5.85s/it] {'loss': 0.4666, 'learning_rate': 5.8836841173011136e-08, 'epoch': 0.97} + 97%|█████████▋| 11335/11728 [3:38:10<38:17, 5.85s/it] 97%|█████████▋| 11336/11728 [3:38:16<38:20, 5.87s/it] {'loss': 0.444, 'learning_rate': 5.8538090091601055e-08, 'epoch': 0.97} + 97%|█████████▋| 11336/11728 [3:38:16<38:20, 5.87s/it] 97%|█████████▋| 11337/11728 [3:38:22<38:17, 5.88s/it] {'loss': 0.4706, 'learning_rate': 5.824009718758184e-08, 'epoch': 0.97} + 97%|█████████▋| 11337/11728 [3:38:22<38:17, 5.88s/it] 97%|█████████▋| 11338/11728 [3:38:28<38:16, 5.89s/it] {'loss': 0.4514, 'learning_rate': 5.794286248367753e-08, 'epoch': 0.97} + 97%|█████████▋| 11338/11728 [3:38:28<38:16, 5.89s/it] 97%|█████████▋| 11339/11728 [3:38:34<38:26, 5.93s/it] {'loss': 0.4505, 'learning_rate': 5.7646386002557784e-08, 'epoch': 0.97} + 97%|█████████▋| 11339/11728 [3:38:34<38:26, 5.93s/it] 97%|█████████▋| 11340/11728 [3:38:39<38:04, 5.89s/it] {'loss': 0.4496, 'learning_rate': 5.735066776683229e-08, 'epoch': 0.97} + 97%|█████████▋| 11340/11728 [3:38:39<38:04, 5.89s/it] 97%|█████████▋| 11341/11728 [3:38:45<37:51, 5.87s/it] {'loss': 0.4572, 'learning_rate': 5.705570779905523e-08, 'epoch': 0.97} + 97%|█████████▋| 11341/11728 [3:38:45<37:51, 5.87s/it] 97%|█████████▋| 11342/11728 [3:38:51<38:32, 5.99s/it] {'loss': 0.487, 'learning_rate': 5.676150612171971e-08, 'epoch': 0.97} + 97%|█████████▋| 11342/11728 [3:38:51<38:32, 5.99s/it] 97%|█████████▋| 11343/11728 [3:38:57<38:26, 5.99s/it] {'loss': 0.4567, 'learning_rate': 5.6468062757263356e-08, 'epoch': 0.97} + 97%|█████████▋| 11343/11728 [3:38:57<38:26, 5.99s/it] 97%|█████████▋| 11344/11728 [3:39:04<38:34, 6.03s/it] {'loss': 0.4512, 'learning_rate': 5.617537772806603e-08, 'epoch': 0.97} + 97%|█████████▋| 11344/11728 [3:39:04<38:34, 6.03s/it] 97%|█████████▋| 11345/11728 [3:39:09<37:47, 5.92s/it] {'loss': 0.4546, 'learning_rate': 5.588345105644766e-08, 'epoch': 0.97} + 97%|█████████▋| 11345/11728 [3:39:09<37:47, 5.92s/it] 97%|█████████▋| 11346/11728 [3:39:15<37:35, 5.91s/it] {'loss': 0.4449, 'learning_rate': 5.5592282764673766e-08, 'epoch': 0.97} + 97%|█████████▋| 11346/11728 [3:39:15<37:35, 5.91s/it] 97%|█████████▋| 11347/11728 [3:39:21<37:33, 5.91s/it] {'loss': 0.4558, 'learning_rate': 5.530187287494882e-08, 'epoch': 0.97} + 97%|█████████▋| 11347/11728 [3:39:21<37:33, 5.91s/it] 97%|█████████▋| 11348/11728 [3:39:27<37:04, 5.85s/it] {'loss': 0.4627, 'learning_rate': 5.501222140942064e-08, 'epoch': 0.97} + 97%|█████████▋| 11348/11728 [3:39:27<37:04, 5.85s/it] 97%|█████████▋| 11349/11728 [3:39:33<36:57, 5.85s/it] {'loss': 0.4498, 'learning_rate': 5.472332839017935e-08, 'epoch': 0.97} + 97%|█████████▋| 11349/11728 [3:39:33<36:57, 5.85s/it]5 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... +03 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... + 97%|█████████▋| 11350/11728 [3:39:38<36:25, 5.78s/it]12 AutoResumeHook: Checking whether to suspend... +AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4537, 'learning_rate': 5.443519383925844e-08, 'epoch': 0.97} + 97%|█████████▋| 11350/11728 [3:39:38<36:25, 5.78s/it] 97%|█████████▋| 11351/11728 [3:39:44<36:05, 5.74s/it] {'loss': 0.4606, 'learning_rate': 5.414781777863032e-08, 'epoch': 0.97} + 97%|█████████▋| 11351/11728 [3:39:44<36:05, 5.74s/it] 97%|█████████▋| 11352/11728 [3:39:50<36:16, 5.79s/it] {'loss': 0.4359, 'learning_rate': 5.386120023021191e-08, 'epoch': 0.97} + 97%|█████████▋| 11352/11728 [3:39:50<36:16, 5.79s/it] 97%|█████████▋| 11353/11728 [3:39:56<36:24, 5.83s/it] {'loss': 0.4658, 'learning_rate': 5.3575341215863496e-08, 'epoch': 0.97} + 97%|█████████▋| 11353/11728 [3:39:56<36:24, 5.83s/it] 97%|█████████▋| 11354/11728 [3:40:01<36:00, 5.78s/it] {'loss': 0.4535, 'learning_rate': 5.3290240757383205e-08, 'epoch': 0.97} + 97%|█████████▋| 11354/11728 [3:40:01<36:00, 5.78s/it] 97%|█████████▋| 11355/11728 [3:40:07<36:03, 5.80s/it] {'loss': 0.4505, 'learning_rate': 5.300589887651586e-08, 'epoch': 0.97} + 97%|█████████▋| 11355/11728 [3:40:07<36:03, 5.80s/it] 97%|█████████▋| 11356/11728 [3:40:13<36:00, 5.81s/it] {'loss': 0.4474, 'learning_rate': 5.272231559494634e-08, 'epoch': 0.97} + 97%|█████████▋| 11356/11728 [3:40:13<36:00, 5.81s/it] 97%|█████████▋| 11357/11728 [3:40:19<36:12, 5.86s/it] {'loss': 0.4632, 'learning_rate': 5.243949093430179e-08, 'epoch': 0.97} + 97%|█████████▋| 11357/11728 [3:40:19<36:12, 5.86s/it] 97%|█████████▋| 11358/11728 [3:40:25<35:54, 5.82s/it] {'loss': 0.4455, 'learning_rate': 5.215742491615161e-08, 'epoch': 0.97} + 97%|█████████▋| 11358/11728 [3:40:25<35:54, 5.82s/it] 97%|█████████▋| 11359/11728 [3:40:30<35:32, 5.78s/it] {'loss': 0.4412, 'learning_rate': 5.187611756200639e-08, 'epoch': 0.97} + 97%|█████████▋| 11359/11728 [3:40:30<35:32, 5.78s/it] 97%|█████████▋| 11360/11728 [3:40:36<35:36, 5.80s/it] {'loss': 0.4553, 'learning_rate': 5.159556889332118e-08, 'epoch': 0.97} + 97%|█████████▋| 11360/11728 [3:40:36<35:36, 5.80s/it] 97%|█████████▋| 11361/11728 [3:40:43<36:18, 5.94s/it] {'loss': 0.4621, 'learning_rate': 5.131577893149109e-08, 'epoch': 0.97} + 97%|█████████▋| 11361/11728 [3:40:43<36:18, 5.94s/it] 97%|█████████▋| 11362/11728 [3:40:48<35:55, 5.89s/it] {'loss': 0.4581, 'learning_rate': 5.103674769785461e-08, 'epoch': 0.97} + 97%|█████████▋| 11362/11728 [3:40:48<35:55, 5.89s/it] 97%|█████████▋| 11363/11728 [3:40:54<36:08, 5.94s/it] {'loss': 0.4511, 'learning_rate': 5.075847521369137e-08, 'epoch': 0.97} + 97%|█████████▋| 11363/11728 [3:40:54<36:08, 5.94s/it] 97%|█████████▋| 11364/11728 [3:41:00<35:43, 5.89s/it] {'loss': 0.441, 'learning_rate': 5.0480961500223306e-08, 'epoch': 0.97} + 97%|█████████▋| 11364/11728 [3:41:00<35:43, 5.89s/it] 97%|█████████▋| 11365/11728 [3:41:06<35:41, 5.90s/it] {'loss': 0.4531, 'learning_rate': 5.020420657861569e-08, 'epoch': 0.97} + 97%|█████████▋| 11365/11728 [3:41:06<35:41, 5.90s/it] 97%|█████████▋| 11366/11728 [3:41:12<35:20, 5.86s/it] {'loss': 0.488, 'learning_rate': 4.992821046997387e-08, 'epoch': 0.97} + 97%|█████████▋| 11366/11728 [3:41:12<35:20, 5.86s/it] 97%|█████████▋| 11367/11728 [3:41:17<34:51, 5.79s/it] {'loss': 0.4575, 'learning_rate': 4.9652973195346566e-08, 'epoch': 0.97} + 97%|█████████▋| 11367/11728 [3:41:17<34:51, 5.79s/it] 97%|█████████▋| 11368/11728 [3:41:23<34:53, 5.81s/it] {'loss': 0.4494, 'learning_rate': 4.937849477572587e-08, 'epoch': 0.97} + 97%|█████████▋| 11368/11728 [3:41:23<34:53, 5.81s/it] 97%|█████████▋| 11369/11728 [3:41:29<34:43, 5.80s/it] {'loss': 0.4377, 'learning_rate': 4.910477523204282e-08, 'epoch': 0.97} + 97%|█████████▋| 11369/11728 [3:41:29<34:43, 5.80s/it] 97%|█████████▋| 11370/11728 [3:41:35<34:13, 5.74s/it] {'loss': 0.4389, 'learning_rate': 4.883181458517405e-08, 'epoch': 0.97} + 97%|█████████▋| 11370/11728 [3:41:35<34:13, 5.74s/it] 97%|█████████▋| 11371/11728 [3:41:40<33:49, 5.69s/it] {'loss': 0.4448, 'learning_rate': 4.8559612855936244e-08, 'epoch': 0.97} + 97%|█████████▋| 11371/11728 [3:41:40<33:49, 5.69s/it] 97%|█████████▋| 11372/11728 [3:41:46<33:39, 5.67s/it] {'loss': 0.4432, 'learning_rate': 4.8288170065088344e-08, 'epoch': 0.97} + 97%|█████████▋| 11372/11728 [3:41:46<33:39, 5.67s/it] 97%|█████████▋| 11373/11728 [3:41:52<33:57, 5.74s/it] {'loss': 0.4414, 'learning_rate': 4.801748623333047e-08, 'epoch': 0.97} + 97%|█████████▋| 11373/11728 [3:41:52<33:57, 5.74s/it] 97%|█████████▋| 11374/11728 [3:41:57<33:26, 5.67s/it] {'loss': 0.4683, 'learning_rate': 4.774756138130831e-08, 'epoch': 0.97} + 97%|█████████▋| 11374/11728 [3:41:57<33:26, 5.67s/it] 97%|█████████▋| 11375/11728 [3:42:03<33:36, 5.71s/it] {'loss': 0.4321, 'learning_rate': 4.7478395529606537e-08, 'epoch': 0.97} + 97%|█████████▋| 11375/11728 [3:42:03<33:36, 5.71s/it] 97%|█████████▋| 11376/11728 [3:42:09<33:30, 5.71s/it] {'loss': 0.4525, 'learning_rate': 4.720998869875315e-08, 'epoch': 0.97} + 97%|█████████▋| 11376/11728 [3:42:09<33:30, 5.71s/it] 97%|█████████▋| 11377/11728 [3:42:14<33:03, 5.65s/it] {'loss': 0.4621, 'learning_rate': 4.694234090921734e-08, 'epoch': 0.97} + 97%|█████████▋| 11377/11728 [3:42:14<33:03, 5.65s/it] 97%|█████████▋| 11378/11728 [3:42:20<33:19, 5.71s/it] {'loss': 0.4497, 'learning_rate': 4.6675452181410566e-08, 'epoch': 0.97} + 97%|█████████▋| 11378/11728 [3:42:20<33:19, 5.71s/it] 97%|█████████▋| 11379/11728 [3:42:26<33:13, 5.71s/it] {'loss': 0.4468, 'learning_rate': 4.640932253568875e-08, 'epoch': 0.97} + 97%|█████████▋| 11379/11728 [3:42:26<33:13, 5.71s/it] 97%|█████████▋| 11380/11728 [3:42:32<33:02, 5.70s/it] {'loss': 0.4702, 'learning_rate': 4.6143951992346783e-08, 'epoch': 0.97} + 97%|█████████▋| 11380/11728 [3:42:32<33:02, 5.70s/it] 97%|█████████▋| 11381/11728 [3:42:37<33:12, 5.74s/it] {'loss': 0.4394, 'learning_rate': 4.587934057162402e-08, 'epoch': 0.97} + 97%|█████████▋| 11381/11728 [3:42:37<33:12, 5.74s/it] 97%|█████████▋| 11382/11728 [3:42:43<33:15, 5.77s/it] {'loss': 0.4459, 'learning_rate': 4.561548829369766e-08, 'epoch': 0.97} + 97%|█████████▋| 11382/11728 [3:42:43<33:15, 5.77s/it] 97%|█████████▋| 11383/11728 [3:42:49<33:00, 5.74s/it] {'loss': 0.4444, 'learning_rate': 4.535239517869494e-08, 'epoch': 0.97} + 97%|█████████▋| 11383/11728 [3:42:49<33:00, 5.74s/it] 97%|█████████▋| 11384/11728 [3:42:55<32:45, 5.71s/it] {'loss': 0.468, 'learning_rate': 4.5090061246676474e-08, 'epoch': 0.97} + 97%|█████████▋| 11384/11728 [3:42:55<32:45, 5.71s/it] 97%|█████████▋| 11385/11728 [3:43:00<32:24, 5.67s/it] {'loss': 0.4568, 'learning_rate': 4.4828486517650705e-08, 'epoch': 0.97} + 97%|█████████▋| 11385/11728 [3:43:00<32:24, 5.67s/it] 97%|█████████▋| 11386/11728 [3:43:06<32:33, 5.71s/it] {'loss': 0.4554, 'learning_rate': 4.4567671011567224e-08, 'epoch': 0.97} + 97%|█████████▋| 11386/11728 [3:43:06<32:33, 5.71s/it] 97%|█████████▋| 11387/11728 [3:43:12<32:25, 5.71s/it] {'loss': 0.4414, 'learning_rate': 4.4307614748313466e-08, 'epoch': 0.97} + 97%|█████████▋| 11387/11728 [3:43:12<32:25, 5.71s/it] 97%|█████████▋| 11388/11728 [3:43:18<32:46, 5.78s/it] {'loss': 0.4517, 'learning_rate': 4.404831774772689e-08, 'epoch': 0.97} + 97%|█████████▋| 11388/11728 [3:43:18<32:46, 5.78s/it] 97%|█████████▋| 11389/11728 [3:43:24<33:01, 5.85s/it] {'loss': 0.458, 'learning_rate': 4.3789780029579456e-08, 'epoch': 0.97} + 97%|█████████▋| 11389/11728 [3:43:24<33:01, 5.85s/it] 97%|█████████▋| 11390/11728 [3:43:29<33:00, 5.86s/it] {'loss': 0.4534, 'learning_rate': 4.353200161358984e-08, 'epoch': 0.97} + 97%|█████████▋| 11390/11728 [3:43:29<33:00, 5.86s/it] 97%|█████████▋| 11391/11728 [3:43:36<33:19, 5.93s/it] {'loss': 0.4464, 'learning_rate': 4.327498251941564e-08, 'epoch': 0.97} + 97%|█████████▋| 11391/11728 [3:43:36<33:19, 5.93s/it] 97%|█████████▋| 11392/11728 [3:43:41<32:28, 5.80s/it] {'loss': 0.467, 'learning_rate': 4.3018722766661194e-08, 'epoch': 0.97} + 97%|█████████▋| 11392/11728 [3:43:41<32:28, 5.80s/it] 97%|█████████▋| 11393/11728 [3:43:47<32:17, 5.78s/it] {'loss': 0.449, 'learning_rate': 4.276322237486752e-08, 'epoch': 0.97} + 97%|█████████▋| 11393/11728 [3:43:47<32:17, 5.78s/it] 97%|█████████▋| 11394/11728 [3:43:53<32:31, 5.84s/it] {'loss': 0.4514, 'learning_rate': 4.250848136352015e-08, 'epoch': 0.97} + 97%|█████████▋| 11394/11728 [3:43:53<32:31, 5.84s/it] 97%|█████████▋| 11395/11728 [3:43:58<32:05, 5.78s/it] {'loss': 0.4452, 'learning_rate': 4.225449975204798e-08, 'epoch': 0.97} + 97%|█████████▋| 11395/11728 [3:43:58<32:05, 5.78s/it] 97%|█████████▋| 11396/11728 [3:44:04<31:42, 5.73s/it] {'loss': 0.4699, 'learning_rate': 4.2001277559818864e-08, 'epoch': 0.97} + 97%|█████████▋| 11396/11728 [3:44:04<31:42, 5.73s/it] 97%|█████████▋| 11397/11728 [3:44:10<31:30, 5.71s/it] {'loss': 0.4764, 'learning_rate': 4.174881480614623e-08, 'epoch': 0.97} + 97%|█████████▋| 11397/11728 [3:44:10<31:30, 5.71s/it] 97%|█████████▋| 11398/11728 [3:44:15<31:20, 5.70s/it] {'loss': 0.4519, 'learning_rate': 4.1497111510283574e-08, 'epoch': 0.97} + 97%|█████████▋| 11398/11728 [3:44:15<31:20, 5.70s/it] 97%|█████████▋| 11399/11728 [3:44:21<31:33, 5.75s/it] {'loss': 0.4725, 'learning_rate': 4.124616769142664e-08, 'epoch': 0.97} + 97%|█████████▋| 11399/11728 [3:44:21<31:33, 5.75s/it]5 AutoResumeHook: Checking whether to suspend... +023 AutoResumeHook: Checking whether to suspend... +AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... + 97%|█████████▋| 11400/11728 [3:44:27<31:06, 5.69s/it]1 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4514, 'learning_rate': 4.0995983368713465e-08, 'epoch': 0.97} + 97%|█████████▋| 11400/11728 [3:44:27<31:06, 5.69s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-11400/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-11400/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-11400/mm_projector +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/torch/nn/modules/module.py:1802: UserWarning: Positional args are being deprecated, use kwargs instead. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details. + warnings.warn( + 97%|█████████▋| 11401/11728 [3:45:01<1:17:14, 14.17s/it] {'loss': 0.4356, 'learning_rate': 4.0746558561224336e-08, 'epoch': 0.97} + 97%|█████████▋| 11401/11728 [3:45:01<1:17:14, 14.17s/it] 97%|█████████▋| 11402/11728 [3:45:06<1:03:15, 11.64s/it] {'loss': 0.4488, 'learning_rate': 4.0497893287980706e-08, 'epoch': 0.97} + 97%|█████████▋| 11402/11728 [3:45:06<1:03:15, 11.64s/it] 97%|█████████▋| 11403/11728 [3:45:12<53:47, 9.93s/it] {'loss': 0.4629, 'learning_rate': 4.0249987567948514e-08, 'epoch': 0.97} + 97%|█████████▋| 11403/11728 [3:45:12<53:47, 9.93s/it] 97%|█████████▋| 11404/11728 [3:45:18<46:43, 8.65s/it] {'loss': 0.4369, 'learning_rate': 4.000284142003264e-08, 'epoch': 0.97} + 97%|█████████▋| 11404/11728 [3:45:18<46:43, 8.65s/it] 97%|█████████▋| 11405/11728 [3:45:24<42:05, 7.82s/it] {'loss': 0.4763, 'learning_rate': 3.975645486308133e-08, 'epoch': 0.97} + 97%|█████████▋| 11405/11728 [3:45:24<42:05, 7.82s/it] 97%|█████████▋| 11406/11728 [3:45:30<38:18, 7.14s/it] {'loss': 0.4791, 'learning_rate': 3.951082791588512e-08, 'epoch': 0.97} + 97%|█████████▋| 11406/11728 [3:45:30<38:18, 7.14s/it] 97%|█████████▋| 11407/11728 [3:45:35<35:52, 6.71s/it] {'loss': 0.4393, 'learning_rate': 3.926596059717791e-08, 'epoch': 0.97} + 97%|█████████▋| 11407/11728 [3:45:35<35:52, 6.71s/it] 97%|█████████▋| 11408/11728 [3:45:41<34:20, 6.44s/it] {'loss': 0.4591, 'learning_rate': 3.902185292563365e-08, 'epoch': 0.97} + 97%|█████████▋| 11408/11728 [3:45:41<34:20, 6.44s/it] 97%|█████████▋| 11409/11728 [3:45:47<33:27, 6.29s/it] {'loss': 0.4368, 'learning_rate': 3.877850491986746e-08, 'epoch': 0.97} + 97%|█████████▋| 11409/11728 [3:45:47<33:27, 6.29s/it] 97%|█████████▋| 11410/11728 [3:45:53<32:32, 6.14s/it] {'loss': 0.4642, 'learning_rate': 3.853591659844003e-08, 'epoch': 0.97} + 97%|█████████▋| 11410/11728 [3:45:53<32:32, 6.14s/it] 97%|█████████▋| 11411/11728 [3:45:59<32:01, 6.06s/it] {'loss': 0.4469, 'learning_rate': 3.8294087979852124e-08, 'epoch': 0.97} + 97%|█████████▋| 11411/11728 [3:45:59<32:01, 6.06s/it] 97%|█████████▋| 11412/11728 [3:46:05<31:36, 6.00s/it] {'loss': 0.4641, 'learning_rate': 3.805301908254455e-08, 'epoch': 0.97} + 97%|█████████▋| 11412/11728 [3:46:05<31:36, 6.00s/it] 97%|█████████▋| 11413/11728 [3:46:10<31:28, 6.00s/it] {'loss': 0.4522, 'learning_rate': 3.781270992490482e-08, 'epoch': 0.97} + 97%|█████████▋| 11413/11728 [3:46:11<31:28, 6.00s/it] 97%|█████████▋| 11414/11728 [3:46:16<30:37, 5.85s/it] {'loss': 0.4226, 'learning_rate': 3.757316052525828e-08, 'epoch': 0.97} + 97%|█████████▋| 11414/11728 [3:46:16<30:37, 5.85s/it] 97%|█████████▋| 11415/11728 [3:46:22<30:12, 5.79s/it] {'loss': 0.4431, 'learning_rate': 3.733437090187364e-08, 'epoch': 0.97} + 97%|█████████▋| 11415/11728 [3:46:22<30:12, 5.79s/it] 97%|█████████▋| 11416/11728 [3:46:28<30:12, 5.81s/it] {'loss': 0.4488, 'learning_rate': 3.7096341072964116e-08, 'epoch': 0.97} + 97%|█████████▋| 11416/11728 [3:46:28<30:12, 5.81s/it] 97%|█████████▋| 11417/11728 [3:46:33<29:55, 5.77s/it] {'loss': 0.4381, 'learning_rate': 3.685907105668074e-08, 'epoch': 0.97} + 97%|█████████▋| 11417/11728 [3:46:33<29:55, 5.77s/it] 97%|█████████▋| 11418/11728 [3:46:39<29:39, 5.74s/it] {'loss': 0.4556, 'learning_rate': 3.662256087111904e-08, 'epoch': 0.97} + 97%|█████████▋| 11418/11728 [3:46:39<29:39, 5.74s/it] 97%|█████████▋| 11419/11728 [3:46:44<29:15, 5.68s/it] {'loss': 0.4551, 'learning_rate': 3.638681053431792e-08, 'epoch': 0.97} + 97%|█████████▋| 11419/11728 [3:46:44<29:15, 5.68s/it] 97%|█████████▋| 11420/11728 [3:46:50<29:43, 5.79s/it] {'loss': 0.4431, 'learning_rate': 3.615182006425411e-08, 'epoch': 0.97} + 97%|█████████▋| 11420/11728 [3:46:50<29:43, 5.79s/it] 97%|█████████▋| 11421/11728 [3:46:56<29:55, 5.85s/it] {'loss': 0.4543, 'learning_rate': 3.591758947885105e-08, 'epoch': 0.97} + 97%|█████████▋| 11421/11728 [3:46:56<29:55, 5.85s/it] 97%|█████████▋| 11422/11728 [3:47:02<29:29, 5.78s/it] {'loss': 0.4599, 'learning_rate': 3.568411879597111e-08, 'epoch': 0.97} + 97%|█████████▋| 11422/11728 [3:47:02<29:29, 5.78s/it] 97%|█████████▋| 11423/11728 [3:47:08<28:59, 5.70s/it] {'loss': 0.4489, 'learning_rate': 3.5451408033420064e-08, 'epoch': 0.97} + 97%|█████████▋| 11423/11728 [3:47:08<28:59, 5.70s/it] 97%|█████████▋| 11424/11728 [3:47:13<28:55, 5.71s/it] {'loss': 0.4438, 'learning_rate': 3.521945720894593e-08, 'epoch': 0.97} + 97%|█████████▋| 11424/11728 [3:47:13<28:55, 5.71s/it] 97%|█████████▋| 11425/11728 [3:47:19<28:37, 5.67s/it] {'loss': 0.4479, 'learning_rate': 3.498826634023789e-08, 'epoch': 0.97} + 97%|█████████▋| 11425/11728 [3:47:19<28:37, 5.67s/it] 97%|█████████▋| 11426/11728 [3:47:25<29:01, 5.77s/it] {'loss': 0.4671, 'learning_rate': 3.475783544492628e-08, 'epoch': 0.97} + 97%|█████████▋| 11426/11728 [3:47:25<29:01, 5.77s/it] 97%|█████████▋| 11427/11728 [3:47:30<28:38, 5.71s/it] {'loss': 0.4335, 'learning_rate': 3.452816454058594e-08, 'epoch': 0.97} + 97%|█████████▋| 11427/11728 [3:47:30<28:38, 5.71s/it] 97%|█████████▋| 11428/11728 [3:47:36<28:58, 5.80s/it] {'loss': 0.4873, 'learning_rate': 3.429925364473285e-08, 'epoch': 0.97} + 97%|█████████▋| 11428/11728 [3:47:36<28:58, 5.80s/it] 97%|█████████▋| 11429/11728 [3:47:42<29:12, 5.86s/it] {'loss': 0.4519, 'learning_rate': 3.407110277482417e-08, 'epoch': 0.97} + 97%|█████████▋| 11429/11728 [3:47:42<29:12, 5.86s/it] 97%|█████████▋| 11430/11728 [3:47:48<29:16, 5.89s/it] {'loss': 0.4255, 'learning_rate': 3.3843711948259306e-08, 'epoch': 0.97} + 97%|█████████▋| 11430/11728 [3:47:48<29:16, 5.89s/it] 97%|█████████▋| 11431/11728 [3:47:54<29:08, 5.89s/it] {'loss': 0.4789, 'learning_rate': 3.361708118238105e-08, 'epoch': 0.97} + 97%|█████████▋| 11431/11728 [3:47:54<29:08, 5.89s/it] 97%|█████████▋| 11432/11728 [3:48:00<28:47, 5.84s/it] {'loss': 0.4506, 'learning_rate': 3.339121049447225e-08, 'epoch': 0.97} + 97%|█████████▋| 11432/11728 [3:48:00<28:47, 5.84s/it] 97%|█████████▋| 11433/11728 [3:48:06<29:05, 5.92s/it] {'loss': 0.4532, 'learning_rate': 3.316609990175912e-08, 'epoch': 0.97} + 97%|█████████▋| 11433/11728 [3:48:06<29:05, 5.92s/it] 97%|█████████▋| 11434/11728 [3:48:12<28:48, 5.88s/it] {'loss': 0.448, 'learning_rate': 3.294174942140904e-08, 'epoch': 0.97} + 97%|█████████▋| 11434/11728 [3:48:12<28:48, 5.88s/it] 98%|█████████▊| 11435/11728 [3:48:18<28:18, 5.80s/it] {'loss': 0.4515, 'learning_rate': 3.2718159070532774e-08, 'epoch': 0.98} + 98%|█████████▊| 11435/11728 [3:48:18<28:18, 5.80s/it] 98%|█████████▊| 11436/11728 [3:48:23<28:13, 5.80s/it] {'loss': 0.4485, 'learning_rate': 3.249532886618223e-08, 'epoch': 0.98} + 98%|█████████▊| 11436/11728 [3:48:23<28:13, 5.80s/it] 98%|█████████▊| 11437/11728 [3:48:29<28:05, 5.79s/it] {'loss': 0.452, 'learning_rate': 3.227325882535048e-08, 'epoch': 0.98} + 98%|█████████▊| 11437/11728 [3:48:29<28:05, 5.79s/it] 98%|█████████▊| 11438/11728 [3:48:35<27:43, 5.74s/it] {'loss': 0.441, 'learning_rate': 3.205194896497399e-08, 'epoch': 0.98} + 98%|█████████▊| 11438/11728 [3:48:35<27:43, 5.74s/it] 98%|█████████▊| 11439/11728 [3:48:41<27:58, 5.81s/it] {'loss': 0.4686, 'learning_rate': 3.1831399301931466e-08, 'epoch': 0.98} + 98%|█████████▊| 11439/11728 [3:48:41<27:58, 5.81s/it] 98%|█████████▊| 11440/11728 [3:48:47<27:57, 5.83s/it] {'loss': 0.4663, 'learning_rate': 3.161160985304168e-08, 'epoch': 0.98} + 98%|█████████▊| 11440/11728 [3:48:47<27:57, 5.83s/it] 98%|█████████▊| 11441/11728 [3:48:53<28:12, 5.90s/it] {'loss': 0.4492, 'learning_rate': 3.1392580635067896e-08, 'epoch': 0.98} + 98%|█████████▊| 11441/11728 [3:48:53<28:12, 5.90s/it] 98%|█████████▊| 11442/11728 [3:48:58<27:48, 5.83s/it] {'loss': 0.4634, 'learning_rate': 3.1174311664712297e-08, 'epoch': 0.98} + 98%|█████████▊| 11442/11728 [3:48:58<27:48, 5.83s/it] 98%|█████████▊| 11443/11728 [3:49:04<27:17, 5.74s/it] {'loss': 0.4366, 'learning_rate': 3.09568029586238e-08, 'epoch': 0.98} + 98%|█████████▊| 11443/11728 [3:49:04<27:17, 5.74s/it] 98%|█████████▊| 11444/11728 [3:49:10<27:39, 5.84s/it] {'loss': 0.4534, 'learning_rate': 3.074005453338802e-08, 'epoch': 0.98} + 98%|█████████▊| 11444/11728 [3:49:10<27:39, 5.84s/it] 98%|█████████▊| 11445/11728 [3:49:16<27:37, 5.86s/it] {'loss': 0.4614, 'learning_rate': 3.052406640553618e-08, 'epoch': 0.98} + 98%|█████████▊| 11445/11728 [3:49:16<27:37, 5.86s/it] 98%|█████████▊| 11446/11728 [3:49:22<27:40, 5.89s/it] {'loss': 0.4393, 'learning_rate': 3.030883859154066e-08, 'epoch': 0.98} + 98%|█████████▊| 11446/11728 [3:49:22<27:40, 5.89s/it] 98%|█████████▊| 11447/11728 [3:49:27<27:19, 5.84s/it] {'loss': 0.4571, 'learning_rate': 3.009437110781499e-08, 'epoch': 0.98} + 98%|█████████▊| 11447/11728 [3:49:27<27:19, 5.84s/it] 98%|█████████▊| 11448/11728 [3:49:33<27:28, 5.89s/it] {'loss': 0.4846, 'learning_rate': 2.988066397071609e-08, 'epoch': 0.98} + 98%|█████████▊| 11448/11728 [3:49:33<27:28, 5.89s/it] 98%|█████████▊| 11449/11728 [3:49:39<27:05, 5.82s/it] {'loss': 0.4759, 'learning_rate': 2.9667717196542045e-08, 'epoch': 0.98} + 98%|█████████▊| 11449/11728 [3:49:39<27:05, 5.82s/it]6 AutoResumeHook: Checking whether to suspend... +30 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... + 98%|█████████▊| 11450/11728 [3:49:45<27:06, 5.85s/it]5 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4343, 'learning_rate': 2.9455530801532073e-08, 'epoch': 0.98} + 98%|█████████▊| 11450/11728 [3:49:45<27:06, 5.85s/it] 98%|█████████▊| 11451/11728 [3:49:51<26:45, 5.80s/it] {'loss': 0.4581, 'learning_rate': 2.924410480186879e-08, 'epoch': 0.98} + 98%|█████████▊| 11451/11728 [3:49:51<26:45, 5.80s/it] 98%|█████████▊| 11452/11728 [3:49:56<26:35, 5.78s/it] {'loss': 0.4656, 'learning_rate': 2.903343921367707e-08, 'epoch': 0.98} + 98%|█████████▊| 11452/11728 [3:49:56<26:35, 5.78s/it] 98%|█████████▊| 11453/11728 [3:50:02<26:15, 5.73s/it] {'loss': 0.4307, 'learning_rate': 2.882353405302296e-08, 'epoch': 0.98} + 98%|█████████▊| 11453/11728 [3:50:02<26:15, 5.73s/it] 98%|█████████▊| 11454/11728 [3:50:08<26:26, 5.79s/it] {'loss': 0.4506, 'learning_rate': 2.861438933591476e-08, 'epoch': 0.98} + 98%|█████████▊| 11454/11728 [3:50:08<26:26, 5.79s/it] 98%|█████████▊| 11455/11728 [3:50:14<26:15, 5.77s/it] {'loss': 0.44, 'learning_rate': 2.8406005078301934e-08, 'epoch': 0.98} + 98%|█████████▊| 11455/11728 [3:50:14<26:15, 5.77s/it] 98%|█████████▊| 11456/11728 [3:50:20<26:10, 5.77s/it] {'loss': 0.4332, 'learning_rate': 2.8198381296078436e-08, 'epoch': 0.98} + 98%|█████████▊| 11456/11728 [3:50:20<26:10, 5.77s/it] 98%|█████████▊| 11457/11728 [3:50:25<26:10, 5.79s/it] {'loss': 0.443, 'learning_rate': 2.7991518005076045e-08, 'epoch': 0.98} + 98%|█████████▊| 11457/11728 [3:50:25<26:10, 5.79s/it] 98%|█████████▊| 11458/11728 [3:50:31<25:54, 5.76s/it] {'loss': 0.4388, 'learning_rate': 2.7785415221073254e-08, 'epoch': 0.98} + 98%|█████████▊| 11458/11728 [3:50:31<25:54, 5.76s/it] 98%|█████████▊| 11459/11728 [3:50:37<26:33, 5.92s/it] {'loss': 0.4453, 'learning_rate': 2.7580072959787484e-08, 'epoch': 0.98} + 98%|█████████▊| 11459/11728 [3:50:37<26:33, 5.92s/it] 98%|█████████▊| 11460/11728 [3:50:43<26:09, 5.86s/it] {'loss': 0.4398, 'learning_rate': 2.7375491236878438e-08, 'epoch': 0.98} + 98%|█████████▊| 11460/11728 [3:50:43<26:09, 5.86s/it] 98%|█████████▊| 11461/11728 [3:50:49<26:01, 5.85s/it] {'loss': 0.4432, 'learning_rate': 2.7171670067949186e-08, 'epoch': 0.98} + 98%|█████████▊| 11461/11728 [3:50:49<26:01, 5.85s/it] 98%|█████████▊| 11462/11728 [3:50:55<25:38, 5.78s/it] {'loss': 0.4499, 'learning_rate': 2.696860946854396e-08, 'epoch': 0.98} + 98%|█████████▊| 11462/11728 [3:50:55<25:38, 5.78s/it] 98%|█████████▊| 11463/11728 [3:51:00<25:37, 5.80s/it] {'loss': 0.4526, 'learning_rate': 2.6766309454148155e-08, 'epoch': 0.98} + 98%|█████████▊| 11463/11728 [3:51:00<25:37, 5.80s/it] 98%|█████████▊| 11464/11728 [3:51:06<25:36, 5.82s/it] {'loss': 0.4434, 'learning_rate': 2.6564770040190535e-08, 'epoch': 0.98} + 98%|█████████▊| 11464/11728 [3:51:06<25:36, 5.82s/it] 98%|█████████▊| 11465/11728 [3:51:12<25:39, 5.85s/it] {'loss': 0.4684, 'learning_rate': 2.636399124204214e-08, 'epoch': 0.98} + 98%|█████████▊| 11465/11728 [3:51:12<25:39, 5.85s/it] 98%|█████████▊| 11466/11728 [3:51:18<25:50, 5.92s/it] {'loss': 0.4388, 'learning_rate': 2.616397307501295e-08, 'epoch': 0.98} + 98%|█████████▊| 11466/11728 [3:51:18<25:50, 5.92s/it] 98%|█████████▊| 11467/11728 [3:51:24<25:19, 5.82s/it] {'loss': 0.4385, 'learning_rate': 2.5964715554360753e-08, 'epoch': 0.98} + 98%|█████████▊| 11467/11728 [3:51:24<25:19, 5.82s/it] 98%|█████████▊| 11468/11728 [3:51:30<25:19, 5.84s/it] {'loss': 0.4614, 'learning_rate': 2.5766218695277843e-08, 'epoch': 0.98} + 98%|█████████▊| 11468/11728 [3:51:30<25:19, 5.84s/it] 98%|█████████▊| 11469/11728 [3:51:36<25:23, 5.88s/it] {'loss': 0.4535, 'learning_rate': 2.5568482512905445e-08, 'epoch': 0.98} + 98%|█████████▊| 11469/11728 [3:51:36<25:23, 5.88s/it] 98%|█████████▊| 11470/11728 [3:51:42<25:14, 5.87s/it] {'loss': 0.4548, 'learning_rate': 2.5371507022322606e-08, 'epoch': 0.98} + 98%|█████████▊| 11470/11728 [3:51:42<25:14, 5.87s/it] 98%|█████████▊| 11471/11728 [3:51:48<25:16, 5.90s/it] {'loss': 0.4366, 'learning_rate': 2.5175292238550643e-08, 'epoch': 0.98} + 98%|█████████▊| 11471/11728 [3:51:48<25:16, 5.90s/it] 98%|█████████▊| 11472/11728 [3:51:53<24:56, 5.85s/it] {'loss': 0.46, 'learning_rate': 2.497983817655536e-08, 'epoch': 0.98} + 98%|█████████▊| 11472/11728 [3:51:53<24:56, 5.85s/it] 98%|█████████▊| 11473/11728 [3:51:59<24:51, 5.85s/it] {'loss': 0.4415, 'learning_rate': 2.4785144851241506e-08, 'epoch': 0.98} + 98%|█████████▊| 11473/11728 [3:51:59<24:51, 5.85s/it] 98%|█████████▊| 11474/11728 [3:52:05<24:18, 5.74s/it] {'loss': 0.4594, 'learning_rate': 2.45912122774572e-08, 'epoch': 0.98} + 98%|█████████▊| 11474/11728 [3:52:05<24:18, 5.74s/it] 98%|█████████▊| 11475/11728 [3:52:10<24:15, 5.75s/it] {'loss': 0.4707, 'learning_rate': 2.4398040469993943e-08, 'epoch': 0.98} + 98%|█████████▊| 11475/11728 [3:52:10<24:15, 5.75s/it] 98%|█████████▊| 11476/11728 [3:52:16<24:37, 5.86s/it] {'loss': 0.4245, 'learning_rate': 2.420562944358329e-08, 'epoch': 0.98} + 98%|█████████▊| 11476/11728 [3:52:16<24:37, 5.86s/it] 98%|█████████▊| 11477/11728 [3:52:22<24:23, 5.83s/it] {'loss': 0.4685, 'learning_rate': 2.4013979212899054e-08, 'epoch': 0.98} + 98%|█████████▊| 11477/11728 [3:52:22<24:23, 5.83s/it] 98%|█████████▊| 11478/11728 [3:52:28<24:49, 5.96s/it] {'loss': 0.4465, 'learning_rate': 2.3823089792556208e-08, 'epoch': 0.98} + 98%|█████████▊| 11478/11728 [3:52:28<24:49, 5.96s/it] 98%|█████████▊| 11479/11728 [3:52:34<24:18, 5.86s/it] {'loss': 0.4637, 'learning_rate': 2.3632961197115335e-08, 'epoch': 0.98} + 98%|█████████▊| 11479/11728 [3:52:34<24:18, 5.86s/it] 98%|█████████▊| 11480/11728 [3:52:40<24:12, 5.86s/it] {'loss': 0.4351, 'learning_rate': 2.344359344107372e-08, 'epoch': 0.98} + 98%|█████████▊| 11480/11728 [3:52:40<24:12, 5.86s/it] 98%|█████████▊| 11481/11728 [3:52:46<24:00, 5.83s/it] {'loss': 0.4798, 'learning_rate': 2.325498653887426e-08, 'epoch': 0.98} + 98%|█████████▊| 11481/11728 [3:52:46<24:00, 5.83s/it] 98%|█████████▊| 11482/11728 [3:52:51<23:42, 5.78s/it] {'loss': 0.4461, 'learning_rate': 2.3067140504902108e-08, 'epoch': 0.98} + 98%|█████████▊| 11482/11728 [3:52:51<23:42, 5.78s/it] 98%|█████████▊| 11483/11728 [3:52:57<23:37, 5.79s/it] {'loss': 0.4584, 'learning_rate': 2.2880055353482477e-08, 'epoch': 0.98} + 98%|█████████▊| 11483/11728 [3:52:57<23:37, 5.79s/it] 98%|█████████▊| 11484/11728 [3:53:03<23:22, 5.75s/it] {'loss': 0.4725, 'learning_rate': 2.269373109888173e-08, 'epoch': 0.98} + 98%|█████████▊| 11484/11728 [3:53:03<23:22, 5.75s/it] 98%|█████████▊| 11485/11728 [3:53:09<23:28, 5.80s/it] {'loss': 0.4325, 'learning_rate': 2.250816775531295e-08, 'epoch': 0.98} + 98%|█████████▊| 11485/11728 [3:53:09<23:28, 5.80s/it] 98%|█████████▊| 11486/11728 [3:53:14<23:04, 5.72s/it] {'loss': 0.4578, 'learning_rate': 2.2323365336924806e-08, 'epoch': 0.98} + 98%|█████████▊| 11486/11728 [3:53:14<23:04, 5.72s/it] 98%|█████████▊| 11487/11728 [3:53:20<22:55, 5.71s/it] {'loss': 0.4339, 'learning_rate': 2.21393238578127e-08, 'epoch': 0.98} + 98%|█████████▊| 11487/11728 [3:53:20<22:55, 5.71s/it] 98%|█████████▊| 11488/11728 [3:53:26<23:00, 5.75s/it] {'loss': 0.4603, 'learning_rate': 2.1956043332010957e-08, 'epoch': 0.98} + 98%|█████████▊| 11488/11728 [3:53:26<23:00, 5.75s/it] 98%|█████████▊| 11489/11728 [3:53:31<22:47, 5.72s/it] {'loss': 0.4561, 'learning_rate': 2.1773523773499506e-08, 'epoch': 0.98} + 98%|█████████▊| 11489/11728 [3:53:31<22:47, 5.72s/it] 98%|█████████▊| 11490/11728 [3:53:37<22:55, 5.78s/it] {'loss': 0.464, 'learning_rate': 2.1591765196197213e-08, 'epoch': 0.98} + 98%|█████████▊| 11490/11728 [3:53:37<22:55, 5.78s/it] 98%|█████████▊| 11491/11728 [3:53:43<22:37, 5.73s/it] {'loss': 0.446, 'learning_rate': 2.1410767613965212e-08, 'epoch': 0.98} + 98%|█████████▊| 11491/11728 [3:53:43<22:37, 5.73s/it] 98%|█████████▊| 11492/11728 [3:53:49<22:25, 5.70s/it] {'loss': 0.4361, 'learning_rate': 2.1230531040606904e-08, 'epoch': 0.98} + 98%|█████████▊| 11492/11728 [3:53:49<22:25, 5.70s/it] 98%|█████████▊| 11493/11728 [3:53:54<22:15, 5.68s/it] {'loss': 0.4447, 'learning_rate': 2.1051055489869076e-08, 'epoch': 0.98} + 98%|█████████▊| 11493/11728 [3:53:54<22:15, 5.68s/it] 98%|█████████▊| 11494/11728 [3:54:00<22:17, 5.71s/it] {'loss': 0.4606, 'learning_rate': 2.0872340975438555e-08, 'epoch': 0.98} + 98%|█████████▊| 11494/11728 [3:54:00<22:17, 5.71s/it] 98%|█████████▊| 11495/11728 [3:54:06<22:28, 5.79s/it] {'loss': 0.4579, 'learning_rate': 2.0694387510944436e-08, 'epoch': 0.98} + 98%|█████████▊| 11495/11728 [3:54:06<22:28, 5.79s/it] 98%|█████████▊| 11496/11728 [3:54:12<22:39, 5.86s/it] {'loss': 0.4596, 'learning_rate': 2.0517195109959197e-08, 'epoch': 0.98} + 98%|█████████▊| 11496/11728 [3:54:12<22:39, 5.86s/it] 98%|█████████▊| 11497/11728 [3:54:18<22:22, 5.81s/it] {'loss': 0.4613, 'learning_rate': 2.0340763785995366e-08, 'epoch': 0.98} + 98%|█████████▊| 11497/11728 [3:54:18<22:22, 5.81s/it] 98%|█████████▊| 11498/11728 [3:54:23<22:09, 5.78s/it] {'loss': 0.4544, 'learning_rate': 2.016509355250884e-08, 'epoch': 0.98} + 98%|█████████▊| 11498/11728 [3:54:23<22:09, 5.78s/it] 98%|█████████▊| 11499/11728 [3:54:29<22:07, 5.79s/it] {'loss': 0.4425, 'learning_rate': 1.9990184422897797e-08, 'epoch': 0.98} + 98%|█████████▊| 11499/11728 [3:54:29<22:07, 5.79s/it]07 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend...3 AutoResumeHook: Checking whether to suspend... + +5 AutoResumeHook: Checking whether to suspend... + 98%|█████████▊| 11500/11728 [3:54:35<21:45, 5.73s/it]4 AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4645, 'learning_rate': 1.981603641049934e-08, 'epoch': 0.98} + 98%|█████████▊| 11500/11728 [3:54:35<21:45, 5.73s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-11500/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-11500/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-11500/mm_projector +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/torch/nn/modules/module.py:1802: UserWarning: Positional args are being deprecated, use kwargs instead. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details. + warnings.warn( + 98%|█████████▊| 11501/11728 [3:55:10<55:00, 14.54s/it] {'loss': 0.4567, 'learning_rate': 1.964264952859618e-08, 'epoch': 0.98} + 98%|█████████▊| 11501/11728 [3:55:10<55:00, 14.54s/it] 98%|█████████▊| 11502/11728 [3:55:16<45:02, 11.96s/it] {'loss': 0.4512, 'learning_rate': 1.9470023790411073e-08, 'epoch': 0.98} + 98%|█████████▊| 11502/11728 [3:55:16<45:02, 11.96s/it] 98%|█████████▊| 11503/11728 [3:55:22<37:44, 10.07s/it] {'loss': 0.4381, 'learning_rate': 1.9298159209110157e-08, 'epoch': 0.98} + 98%|█████████▊| 11503/11728 [3:55:22<37:44, 10.07s/it] 98%|█████████▊| 11504/11728 [3:55:27<32:48, 8.79s/it] {'loss': 0.4651, 'learning_rate': 1.9127055797799608e-08, 'epoch': 0.98} + 98%|█████████▊| 11504/11728 [3:55:27<32:48, 8.79s/it] 98%|█████████▊| 11505/11728 [3:55:33<29:06, 7.83s/it] {'loss': 0.4533, 'learning_rate': 1.8956713569527884e-08, 'epoch': 0.98} + 98%|█████████▊| 11505/11728 [3:55:33<29:06, 7.83s/it] 98%|█████████▊| 11506/11728 [3:55:39<26:50, 7.26s/it] {'loss': 0.4698, 'learning_rate': 1.878713253728792e-08, 'epoch': 0.98} + 98%|█████████▊| 11506/11728 [3:55:39<26:50, 7.26s/it] 98%|█████████▊| 11507/11728 [3:55:45<25:00, 6.79s/it] {'loss': 0.4699, 'learning_rate': 1.8618312714010488e-08, 'epoch': 0.98} + 98%|█████████▊| 11507/11728 [3:55:45<25:00, 6.79s/it] 98%|█████████▊| 11508/11728 [3:55:50<23:51, 6.51s/it] {'loss': 0.4474, 'learning_rate': 1.8450254112571954e-08, 'epoch': 0.98} + 98%|█████████▊| 11508/11728 [3:55:50<23:51, 6.51s/it] 98%|█████████▊| 11509/11728 [3:55:56<22:47, 6.24s/it] {'loss': 0.457, 'learning_rate': 1.8282956745789837e-08, 'epoch': 0.98} + 98%|█████████▊| 11509/11728 [3:55:56<22:47, 6.24s/it] 98%|█████████▊| 11510/11728 [3:56:02<22:19, 6.14s/it] {'loss': 0.4435, 'learning_rate': 1.8116420626420605e-08, 'epoch': 0.98} + 98%|█████████▊| 11510/11728 [3:56:02<22:19, 6.14s/it] 98%|█████████▊| 11511/11728 [3:56:08<21:49, 6.03s/it] {'loss': 0.4274, 'learning_rate': 1.795064576716632e-08, 'epoch': 0.98} + 98%|█████████▊| 11511/11728 [3:56:08<21:49, 6.03s/it] 98%|█████████▊| 11512/11728 [3:56:13<21:16, 5.91s/it] {'loss': 0.4583, 'learning_rate': 1.77856321806702e-08, 'epoch': 0.98} + 98%|█████████▊| 11512/11728 [3:56:13<21:16, 5.91s/it] 98%|█████████▊| 11513/11728 [3:56:20<21:27, 5.99s/it] {'loss': 0.4557, 'learning_rate': 1.762137987951551e-08, 'epoch': 0.98} + 98%|█████████▊| 11513/11728 [3:56:20<21:27, 5.99s/it] 98%|█████████▊| 11514/11728 [3:56:25<21:17, 5.97s/it] {'loss': 0.4628, 'learning_rate': 1.745788887623001e-08, 'epoch': 0.98} + 98%|█████████▊| 11514/11728 [3:56:25<21:17, 5.97s/it] 98%|█████████▊| 11515/11728 [3:56:31<20:44, 5.84s/it] {'loss': 0.428, 'learning_rate': 1.7295159183281507e-08, 'epoch': 0.98} + 98%|█████████▊| 11515/11728 [3:56:31<20:44, 5.84s/it] 98%|█████████▊| 11516/11728 [3:56:37<20:41, 5.86s/it] {'loss': 0.4825, 'learning_rate': 1.713319081308118e-08, 'epoch': 0.98} + 98%|█████████▊| 11516/11728 [3:56:37<20:41, 5.86s/it] 98%|█████████▊| 11517/11728 [3:56:43<20:35, 5.85s/it] {'loss': 0.455, 'learning_rate': 1.697198377798026e-08, 'epoch': 0.98} + 98%|█████████▊| 11517/11728 [3:56:43<20:35, 5.85s/it] 98%|█████████▊| 11518/11728 [3:56:49<20:38, 5.90s/it] {'loss': 0.4757, 'learning_rate': 1.6811538090274472e-08, 'epoch': 0.98} + 98%|█████████▊| 11518/11728 [3:56:49<20:38, 5.90s/it] 98%|█████████▊| 11519/11728 [3:56:55<20:25, 5.86s/it] {'loss': 0.4298, 'learning_rate': 1.6651853762198467e-08, 'epoch': 0.98} + 98%|█████████▊| 11519/11728 [3:56:55<20:25, 5.86s/it]Jun 28 07:20:02.726355 3872432 slurmstepd 0x155550ab8700: error: *** STEP 9381995.0 ON batch-block4-0047 CANCELLED AT 2025-06-28T07:20:02 DUE TO TIME LIMIT *** +srun: Job step aborted: Waiting up to 122 seconds for job step to finish. +srun: error: batch-block4-0047: task 0: Terminated +srun: Terminating StepId=9381995.0 +wandb: Currently logged in as: memmelma. Use `wandb login --relogin` to force relogin +MASTER_ADDR=batch-block7-00179 +JobID: 9383006 | Full list: batch-block7-00179 +NETWORK=Efficient-Large-Model/VILA1.5-3b +WARNING:torch.distributed.run: +***************************************** +Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed. +***************************************** +Did not find AutoResume SDK! +Did not find AutoResume SDK! +Did not find AutoResume SDK! +Did not find AutoResume SDK! +Did not find AutoResume SDK! +Did not find AutoResume SDK! +Did not find AutoResume SDK! +Did not find AutoResume SDK! +[2025-06-28 07:23:01,926] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-28 07:23:01,926] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-28 07:23:01,926] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-28 07:23:01,926] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-28 07:23:01,926] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-28 07:23:01,926] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-28 07:23:01,926] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-28 07:23:01,926] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-28 07:23:02,962] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-28 07:23:02,962] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-28 07:23:02,962] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-28 07:23:02,962] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-28 07:23:02,962] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-28 07:23:02,962] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-28 07:23:02,962] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-28 07:23:02,962] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-28 07:23:02,962] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-28 07:23:02,962] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-28 07:23:02,962] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-28 07:23:02,962] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-28 07:23:02,962] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-28 07:23:02,962] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-28 07:23:02,962] [INFO] [comm.py:625:init_distributed] Initializing TorchBackend in DeepSpeed with backend nccl +[2025-06-28 07:23:02,962] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-28 07:23:02,962] [INFO] [comm.py:594:init_distributed] cdb=None +You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`. +You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`. +You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`. +You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`. +You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`. +You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`. +You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`. +You are attempting to use Flash Attention 2.0 with a model not initialized on GPU. Make sure to move the model to GPU after initializing it on CPU with `model.to('cuda')`. +[2025-06-28 07:23:11,238] [INFO] [partition_parameters.py:453:__exit__] finished initializing model with 2.70B parameters + Loading checkpoint shards: 0%| | 0/2 [00:00 4096). Running this sequence through the model will result in indexing errors + 100%|█████████▉| 11682/11728 [18:27<04:25, 5.78s/it] {'loss': 0.4568, 'learning_rate': 8.068641245717601e-10, 'epoch': 1.0} + 100%|█████████▉| 11682/11728 [18:27<04:25, 5.78s/it] 100%|█████████▉| 11683/11728 [18:33<04:21, 5.80s/it] {'loss': 0.4362, 'learning_rate': 7.721648379988011e-10, 'epoch': 1.0} + 100%|█████████▉| 11683/11728 [18:33<04:21, 5.80s/it] 100%|█████████▉| 11684/11728 [18:38<04:12, 5.73s/it] {'loss': 0.4551, 'learning_rate': 7.38228134284924e-10, 'epoch': 1.0} + 100%|█████████▉| 11684/11728 [18:38<04:12, 5.73s/it] 100%|█████████▉| 11685/11728 [18:44<04:06, 5.73s/it] {'loss': 0.4358, 'learning_rate': 7.050540160202791e-10, 'epoch': 1.0} + 100%|█████████▉| 11685/11728 [18:44<04:06, 5.73s/it] 100%|█████████▉| 11686/11728 [18:49<03:59, 5.70s/it] {'loss': 0.4388, 'learning_rate': 6.726424857339542e-10, 'epoch': 1.0} + 100%|█████████▉| 11686/11728 [18:49<03:59, 5.70s/it] 100%|█████████▉| 11687/11728 [18:56<03:58, 5.81s/it] {'loss': 0.4521, 'learning_rate': 6.409935458984162e-10, 'epoch': 1.0} + 100%|█████████▉| 11687/11728 [18:56<03:58, 5.81s/it] 100%|█████████▉| 11688/11728 [19:02<03:54, 5.86s/it] {'loss': 0.4582, 'learning_rate': 6.101071989261798e-10, 'epoch': 1.0} + 100%|█████████▉| 11688/11728 [19:02<03:54, 5.86s/it] 100%|█████████▉| 11689/11728 [19:07<03:47, 5.84s/it] {'loss': 0.4294, 'learning_rate': 5.79983447173138e-10, 'epoch': 1.0} + 100%|█████████▉| 11689/11728 [19:07<03:47, 5.84s/it] 100%|█████████▉| 11690/11728 [19:13<03:38, 5.74s/it] {'loss': 0.4372, 'learning_rate': 5.506222929374527e-10, 'epoch': 1.0} + 100%|█████████▉| 11690/11728 [19:13<03:38, 5.74s/it] 100%|█████████▉| 11691/11728 [19:18<03:31, 5.70s/it] {'loss': 0.4632, 'learning_rate': 5.220237384573334e-10, 'epoch': 1.0} + 100%|█████████▉| 11691/11728 [19:18<03:31, 5.70s/it] 100%|█████████▉| 11692/11728 [19:24<03:24, 5.67s/it] {'loss': 0.4312, 'learning_rate': 4.941877859143684e-10, 'epoch': 1.0} + 100%|█████████▉| 11692/11728 [19:24<03:24, 5.67s/it] 100%|█████████▉| 11693/11728 [19:30<03:21, 5.75s/it] {'loss': 0.4253, 'learning_rate': 4.671144374313041e-10, 'epoch': 1.0} + 100%|█████████▉| 11693/11728 [19:30<03:21, 5.75s/it] 100%|█████████▉| 11694/11728 [19:36<03:17, 5.80s/it] {'loss': 0.455, 'learning_rate': 4.408036950731553e-10, 'epoch': 1.0} + 100%|█████████▉| 11694/11728 [19:36<03:17, 5.80s/it] 100%|█████████▉| 11695/11728 [19:42<03:11, 5.81s/it] {'loss': 0.4803, 'learning_rate': 4.1525556084609507e-10, 'epoch': 1.0} + 100%|█████████▉| 11695/11728 [19:42<03:11, 5.81s/it] 100%|█████████▉| 11696/11728 [19:48<03:07, 5.86s/it] {'loss': 0.434, 'learning_rate': 3.9047003669856477e-10, 'epoch': 1.0} + 100%|█████████▉| 11696/11728 [19:48<03:07, 5.86s/it] 100%|█████████▉| 11697/11728 [19:53<03:00, 5.82s/it] {'loss': 0.4729, 'learning_rate': 3.6644712452127416e-10, 'epoch': 1.0} + 100%|█████████▉| 11697/11728 [19:53<03:00, 5.82s/it] 100%|█████████▉| 11698/11728 [19:59<02:53, 5.77s/it] {'loss': 0.4624, 'learning_rate': 3.4318682614498113e-10, 'epoch': 1.0} + 100%|█████████▉| 11698/11728 [19:59<02:53, 5.77s/it]/lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/VILA/llava/model/llava_arch.py:397: UserWarning: Inputs truncated! + warnings.warn("Inputs truncated!") + 100%|█████████▉| 11699/11728 [20:05<02:50, 5.89s/it] {'loss': 0.4577, 'learning_rate': 3.206891433449322e-10, 'epoch': 1.0} + 100%|█████████▉| 11699/11728 [20:05<02:50, 5.89s/it]5 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... +0 AutoResumeHook: Checking whether to suspend... + 100%|█████████▉| 11700/11728 [20:11<02:44, 5.86s/it]7 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4491, 'learning_rate': 2.9895407783753214e-10, 'epoch': 1.0} + 100%|█████████▉| 11700/11728 [20:11<02:44, 5.86s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-11700/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-11700/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/tmp-checkpoint-11700/mm_projector +/lustre/fs12/portfolios/nvr/users/mmemmel/miniforge3/envs/vila/lib/python3.10/site-packages/torch/nn/modules/module.py:1802: UserWarning: Positional args are being deprecated, use kwargs instead. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details. + warnings.warn( + 100%|█████████▉| 11701/11728 [20:44<06:16, 13.96s/it] {'loss': 0.4496, 'learning_rate': 2.7798163127812363e-10, 'epoch': 1.0} + 100%|█████████▉| 11701/11728 [20:44<06:16, 13.96s/it] 100%|█████████▉| 11702/11728 [20:50<04:58, 11.50s/it] {'loss': 0.4709, 'learning_rate': 2.577718052676481e-10, 'epoch': 1.0} + 100%|█████████▉| 11702/11728 [20:50<04:58, 11.50s/it] 100%|█████████▉| 11703/11728 [20:56<04:06, 9.88s/it] {'loss': 0.4615, 'learning_rate': 2.383246013482055e-10, 'epoch': 1.0} + 100%|█████████▉| 11703/11728 [20:56<04:06, 9.88s/it] 100%|█████████▉| 11704/11728 [21:02<03:28, 8.69s/it] {'loss': 0.4575, 'learning_rate': 2.1964002100083314e-10, 'epoch': 1.0} + 100%|█████████▉| 11704/11728 [21:02<03:28, 8.69s/it] 100%|█████████▉| 11705/11728 [21:07<02:58, 7.77s/it] {'loss': 0.4535, 'learning_rate': 2.0171806565216777e-10, 'epoch': 1.0} + 100%|█████████▉| 11705/11728 [21:07<02:58, 7.77s/it] 100%|█████████▉| 11706/11728 [21:13<02:38, 7.22s/it] {'loss': 0.4559, 'learning_rate': 1.8455873666778368e-10, 'epoch': 1.0} + 100%|█████████▉| 11706/11728 [21:13<02:38, 7.22s/it] 100%|█████████▉| 11707/11728 [21:19<02:21, 6.74s/it] {'loss': 0.4666, 'learning_rate': 1.6816203535663379e-10, 'epoch': 1.0} + 100%|█████████▉| 11707/11728 [21:19<02:21, 6.74s/it] 100%|█████████▉| 11708/11728 [21:24<02:07, 6.37s/it] {'loss': 0.4451, 'learning_rate': 1.5252796296993944e-10, 'epoch': 1.0} + 100%|█████████▉| 11708/11728 [21:24<02:07, 6.37s/it] 100%|█████████▉| 11709/11728 [21:30<01:57, 6.20s/it] {'loss': 0.4496, 'learning_rate': 1.3765652070008018e-10, 'epoch': 1.0} + 100%|█████████▉| 11709/11728 [21:30<01:57, 6.20s/it] 100%|█████████▉| 11710/11728 [21:36<01:50, 6.12s/it] {'loss': 0.4415, 'learning_rate': 1.235477096805937e-10, 'epoch': 1.0} + 100%|█████████▉| 11710/11728 [21:36<01:50, 6.12s/it] 100%|█████████▉| 11711/11728 [21:42<01:42, 6.06s/it] {'loss': 0.4597, 'learning_rate': 1.1020153098728615e-10, 'epoch': 1.0} + 100%|█████████▉| 11711/11728 [21:42<01:42, 6.06s/it] 100%|█████████▉| 11712/11728 [21:48<01:35, 5.95s/it] {'loss': 0.4478, 'learning_rate': 9.7617985638232e-11, 'epoch': 1.0} + 100%|█████████▉| 11712/11728 [21:48<01:35, 5.95s/it] 100%|█████████▉| 11713/11728 [21:53<01:28, 5.88s/it] {'loss': 0.4584, 'learning_rate': 8.579707459266396e-11, 'epoch': 1.0} + 100%|█████████▉| 11713/11728 [21:53<01:28, 5.88s/it] 100%|█████████▉| 11714/11728 [21:59<01:22, 5.89s/it] {'loss': 0.4665, 'learning_rate': 7.473879875319335e-11, 'epoch': 1.0} + 100%|█████████▉| 11714/11728 [21:59<01:22, 5.89s/it] 100%|█████████▉| 11715/11728 [22:05<01:16, 5.91s/it] {'loss': 0.4562, 'learning_rate': 6.444315896358966e-11, 'epoch': 1.0} + 100%|█████████▉| 11715/11728 [22:05<01:16, 5.91s/it] 100%|█████████▉| 11716/11728 [22:11<01:09, 5.83s/it] {'loss': 0.4494, 'learning_rate': 5.491015600656013e-11, 'epoch': 1.0} + 100%|█████████▉| 11716/11728 [22:11<01:09, 5.83s/it] 100%|█████████▉| 11717/11728 [22:17<01:03, 5.81s/it] {'loss': 0.4701, 'learning_rate': 4.6139790610411073e-11, 'epoch': 1.0} + 100%|█████████▉| 11717/11728 [22:17<01:03, 5.81s/it] 100%|█████████▉| 11718/11728 [22:22<00:57, 5.79s/it] {'loss': 0.4639, 'learning_rate': 3.8132063445717184e-11, 'epoch': 1.0} + 100%|█████████▉| 11718/11728 [22:22<00:57, 5.79s/it] 100%|█████████▉| 11719/11728 [22:28<00:52, 5.84s/it] {'loss': 0.4618, 'learning_rate': 3.088697512088068e-11, 'epoch': 1.0} + 100%|█████████▉| 11719/11728 [22:28<00:52, 5.84s/it] 100%|█████████▉| 11720/11728 [22:34<00:46, 5.83s/it] {'loss': 0.4717, 'learning_rate': 2.4404526188792633e-11, 'epoch': 1.0} + 100%|█████████▉| 11720/11728 [22:34<00:46, 5.83s/it] 100%|█████████▉| 11721/11728 [22:40<00:40, 5.79s/it] {'loss': 0.454, 'learning_rate': 1.8684717144612506e-11, 'epoch': 1.0} + 100%|█████████▉| 11721/11728 [22:40<00:40, 5.79s/it] 100%|█████████▉| 11722/11728 [22:45<00:34, 5.73s/it] {'loss': 0.4375, 'learning_rate': 1.3727548423547732e-11, 'epoch': 1.0} + 100%|█████████▉| 11722/11728 [22:45<00:34, 5.73s/it] 100%|█████████▉| 11723/11728 [22:51<00:28, 5.71s/it] {'loss': 0.4485, 'learning_rate': 9.53302040529458e-12, 'epoch': 1.0} + 100%|█████████▉| 11723/11728 [22:51<00:28, 5.71s/it] 100%|█████████▉| 11724/11728 [22:57<00:22, 5.71s/it] {'loss': 0.4612, 'learning_rate': 6.101133408487059e-12, 'epoch': 1.0} + 100%|█████████▉| 11724/11728 [22:57<00:22, 5.71s/it] 100%|█████████▉| 11725/11728 [23:03<00:17, 5.78s/it] {'loss': 0.4539, 'learning_rate': 3.4318876951378034e-12, 'epoch': 1.0} + 100%|█████████▉| 11725/11728 [23:03<00:17, 5.78s/it] 100%|█████████▉| 11726/11728 [23:09<00:11, 5.85s/it] {'loss': 0.4449, 'learning_rate': 1.5252834684176266e-12, 'epoch': 1.0} + 100%|█████████▉| 11726/11728 [23:09<00:11, 5.85s/it] 100%|█████████▉| 11727/11728 [23:15<00:05, 5.84s/it] {'loss': 0.4445, 'learning_rate': 3.8132087487596783e-13, 'epoch': 1.0} + 100%|█████████▉| 11727/11728 [23:15<00:05, 5.84s/it] 100%|██████████| 11728/11728 [23:22<00:00, 6.21s/it] {'loss': 0.4591, 'learning_rate': 0.0, 'epoch': 1.0} + 100%|██████████| 11728/11728 [23:22<00:00, 6.21s/it] {'train_runtime': 1404.9182, 'train_samples_per_second': 2137.167, 'train_steps_per_second': 8.348, 'train_loss': 0.00880163661769679, 'epoch': 1.0} + 100%|██████████| 11728/11728 [23:22<00:00, 6.21s/it] 100%|██████████| 11728/11728 [23:22<00:00, 8.36it/s] +saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/mm_projector +wandb: 🚀 View run vila_3b_path_mask_fast at: https://wandb.ai/memmelma/VILA/runs/op066dyn +wandb: Find logs at: ../../../../../../../../fs12/portfolios/nvr/projects/nvr_srl_simpler/users/mmemmel/projects/vila/VILA/wandb/run-20250628_072428-op066dyn/logs +wandb: Currently logged in as: memmelma. Use `wandb login --relogin` to force relogin +MASTER_ADDR=batch-block7-01181 +JobID: 9383118 | Full list: batch-block7-01181 +NETWORK=Efficient-Large-Model/VILA1.5-3b +WARNING:torch.distributed.run: +***************************************** +Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed. +***************************************** +Did not find AutoResume SDK! +Did not find AutoResume SDK! +Did not find AutoResume SDK! +Did not find AutoResume SDK! +Did not find AutoResume SDK! +Did not find AutoResume SDK! +Did not find AutoResume SDK! +Did not find AutoResume SDK! +[2025-06-28 07:50:13,750] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-28 07:50:13,750] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-28 07:50:13,750] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-28 07:50:13,750] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-28 07:50:13,750] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-28 07:50:13,750] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-28 07:50:13,750] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-28 07:50:13,750] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-28 07:50:14,747] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-28 07:50:14,747] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-28 07:50:14,747] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-28 07:50:14,747] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-28 07:50:14,747] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-28 07:50:14,747] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-28 07:50:14,747] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-28 07:50:14,747] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-28 07:50:14,747] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-28 07:50:14,747] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-28 07:50:14,747] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-28 07:50:14,747] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-28 07:50:14,747] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-28 07:50:14,747] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-28 07:50:14,747] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-28 07:50:14,747] [INFO] [comm.py:625:init_distributed] Initializing TorchBackend in DeepSpeed with backend nccl +[2025-06-28 07:50:14,747] [INFO] [comm.py:594:init_distributed] cdb=None +Models has been ready under /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast. Skipp training +Models has been ready under /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast. Skipp training +Models has been ready under /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast. Skipp training +Models has been ready under /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast. Skipp training +Models has been ready under /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast. Skipp training +Models has been ready under /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast. Skipp training +Models has been ready under /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast. Skipp training +Models has been ready under /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast. Skipp training diff --git a/trainer_state.json b/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..a9af0506d2c5da24e2939a2f49b9995c1e0bf326 --- /dev/null +++ b/trainer_state.json @@ -0,0 +1,70398 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 1.0, + "eval_steps": 500, + "global_step": 11728, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0, + "learning_rate": 5.681818181818182e-08, + "loss": 0.8037, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 1.1363636363636364e-07, + "loss": 0.8135, + "step": 2 + }, + { + "epoch": 0.0, + "learning_rate": 1.7045454545454545e-07, + "loss": 0.8006, + "step": 3 + }, + { + "epoch": 0.0, + "learning_rate": 2.2727272727272729e-07, + "loss": 0.8006, + "step": 4 + }, + { + "epoch": 0.0, + "learning_rate": 2.840909090909091e-07, + "loss": 0.7892, + "step": 5 + }, + { + "epoch": 0.0, + "learning_rate": 3.409090909090909e-07, + "loss": 0.8249, + "step": 6 + }, + { + "epoch": 0.0, + "learning_rate": 3.9772727272727276e-07, + "loss": 0.8055, + "step": 7 + }, + { + "epoch": 0.0, + "learning_rate": 4.5454545454545457e-07, + "loss": 0.7966, + "step": 8 + }, + { + "epoch": 0.0, + "learning_rate": 5.113636363636364e-07, + "loss": 0.7916, + "step": 9 + }, + { + "epoch": 0.0, + "learning_rate": 5.681818181818182e-07, + "loss": 0.8006, + "step": 10 + }, + { + "epoch": 0.0, + "learning_rate": 6.25e-07, + "loss": 0.7935, + "step": 11 + }, + { + "epoch": 0.0, + "learning_rate": 6.818181818181818e-07, + "loss": 0.7847, + "step": 12 + }, + { + "epoch": 0.0, + "learning_rate": 7.386363636363638e-07, + "loss": 0.8064, + "step": 13 + }, + { + "epoch": 0.0, + "learning_rate": 7.954545454545455e-07, + "loss": 0.7889, + "step": 14 + }, + { + "epoch": 0.0, + "learning_rate": 8.522727272727273e-07, + "loss": 0.7977, + "step": 15 + }, + { + "epoch": 0.0, + "learning_rate": 9.090909090909091e-07, + "loss": 0.7758, + "step": 16 + }, + { + "epoch": 0.0, + "learning_rate": 9.65909090909091e-07, + "loss": 0.7677, + "step": 17 + }, + { + "epoch": 0.0, + "learning_rate": 1.0227272727272729e-06, + "loss": 0.7571, + "step": 18 + }, + { + "epoch": 0.0, + "learning_rate": 1.0795454545454546e-06, + "loss": 0.7259, + "step": 19 + }, + { + "epoch": 0.0, + "learning_rate": 1.1363636363636364e-06, + "loss": 0.7316, + "step": 20 + }, + { + "epoch": 0.0, + "learning_rate": 1.1931818181818183e-06, + "loss": 0.7075, + "step": 21 + }, + { + "epoch": 0.0, + "learning_rate": 1.25e-06, + "loss": 0.7367, + "step": 22 + }, + { + "epoch": 0.0, + "learning_rate": 1.3068181818181819e-06, + "loss": 0.7138, + "step": 23 + }, + { + "epoch": 0.0, + "learning_rate": 1.3636363636363636e-06, + "loss": 0.7215, + "step": 24 + }, + { + "epoch": 0.0, + "learning_rate": 1.4204545454545458e-06, + "loss": 0.7192, + "step": 25 + }, + { + "epoch": 0.0, + "learning_rate": 1.4772727272727275e-06, + "loss": 0.6846, + "step": 26 + }, + { + "epoch": 0.0, + "learning_rate": 1.5340909090909093e-06, + "loss": 0.6809, + "step": 27 + }, + { + "epoch": 0.0, + "learning_rate": 1.590909090909091e-06, + "loss": 0.6759, + "step": 28 + }, + { + "epoch": 0.0, + "learning_rate": 1.6477272727272728e-06, + "loss": 0.6561, + "step": 29 + }, + { + "epoch": 0.0, + "learning_rate": 1.7045454545454546e-06, + "loss": 0.6765, + "step": 30 + }, + { + "epoch": 0.0, + "learning_rate": 1.7613636363636365e-06, + "loss": 0.697, + "step": 31 + }, + { + "epoch": 0.0, + "learning_rate": 1.8181818181818183e-06, + "loss": 0.6814, + "step": 32 + }, + { + "epoch": 0.0, + "learning_rate": 1.8750000000000003e-06, + "loss": 0.6704, + "step": 33 + }, + { + "epoch": 0.0, + "learning_rate": 1.931818181818182e-06, + "loss": 0.6773, + "step": 34 + }, + { + "epoch": 0.0, + "learning_rate": 1.9886363636363638e-06, + "loss": 0.661, + "step": 35 + }, + { + "epoch": 0.0, + "learning_rate": 2.0454545454545457e-06, + "loss": 0.6677, + "step": 36 + }, + { + "epoch": 0.0, + "learning_rate": 2.1022727272727277e-06, + "loss": 0.6812, + "step": 37 + }, + { + "epoch": 0.0, + "learning_rate": 2.1590909090909092e-06, + "loss": 0.6701, + "step": 38 + }, + { + "epoch": 0.0, + "learning_rate": 2.2159090909090912e-06, + "loss": 0.6468, + "step": 39 + }, + { + "epoch": 0.0, + "learning_rate": 2.2727272727272728e-06, + "loss": 0.6397, + "step": 40 + }, + { + "epoch": 0.0, + "learning_rate": 2.3295454545454547e-06, + "loss": 0.6453, + "step": 41 + }, + { + "epoch": 0.0, + "learning_rate": 2.3863636363636367e-06, + "loss": 0.655, + "step": 42 + }, + { + "epoch": 0.0, + "learning_rate": 2.4431818181818182e-06, + "loss": 0.6258, + "step": 43 + }, + { + "epoch": 0.0, + "learning_rate": 2.5e-06, + "loss": 0.6211, + "step": 44 + }, + { + "epoch": 0.0, + "learning_rate": 2.556818181818182e-06, + "loss": 0.6227, + "step": 45 + }, + { + "epoch": 0.0, + "learning_rate": 2.6136363636363637e-06, + "loss": 0.6075, + "step": 46 + }, + { + "epoch": 0.0, + "learning_rate": 2.6704545454545457e-06, + "loss": 0.6292, + "step": 47 + }, + { + "epoch": 0.0, + "learning_rate": 2.7272727272727272e-06, + "loss": 0.635, + "step": 48 + }, + { + "epoch": 0.0, + "learning_rate": 2.784090909090909e-06, + "loss": 0.6098, + "step": 49 + }, + { + "epoch": 0.0, + "learning_rate": 2.8409090909090916e-06, + "loss": 0.6265, + "step": 50 + }, + { + "epoch": 0.0, + "learning_rate": 2.897727272727273e-06, + "loss": 0.6112, + "step": 51 + }, + { + "epoch": 0.0, + "learning_rate": 2.954545454545455e-06, + "loss": 0.6133, + "step": 52 + }, + { + "epoch": 0.0, + "learning_rate": 3.0113636363636366e-06, + "loss": 0.6205, + "step": 53 + }, + { + "epoch": 0.0, + "learning_rate": 3.0681818181818186e-06, + "loss": 0.6149, + "step": 54 + }, + { + "epoch": 0.0, + "learning_rate": 3.125e-06, + "loss": 0.6106, + "step": 55 + }, + { + "epoch": 0.0, + "learning_rate": 3.181818181818182e-06, + "loss": 0.6134, + "step": 56 + }, + { + "epoch": 0.0, + "learning_rate": 3.2386363636363637e-06, + "loss": 0.6199, + "step": 57 + }, + { + "epoch": 0.0, + "learning_rate": 3.2954545454545456e-06, + "loss": 0.6179, + "step": 58 + }, + { + "epoch": 0.01, + "learning_rate": 3.352272727272727e-06, + "loss": 0.6011, + "step": 59 + }, + { + "epoch": 0.01, + "learning_rate": 3.409090909090909e-06, + "loss": 0.6031, + "step": 60 + }, + { + "epoch": 0.01, + "learning_rate": 3.4659090909090915e-06, + "loss": 0.6275, + "step": 61 + }, + { + "epoch": 0.01, + "learning_rate": 3.522727272727273e-06, + "loss": 0.6043, + "step": 62 + }, + { + "epoch": 0.01, + "learning_rate": 3.579545454545455e-06, + "loss": 0.6014, + "step": 63 + }, + { + "epoch": 0.01, + "learning_rate": 3.6363636363636366e-06, + "loss": 0.6035, + "step": 64 + }, + { + "epoch": 0.01, + "learning_rate": 3.6931818181818186e-06, + "loss": 0.6114, + "step": 65 + }, + { + "epoch": 0.01, + "learning_rate": 3.7500000000000005e-06, + "loss": 0.6079, + "step": 66 + }, + { + "epoch": 0.01, + "learning_rate": 3.806818181818182e-06, + "loss": 0.6123, + "step": 67 + }, + { + "epoch": 0.01, + "learning_rate": 3.863636363636364e-06, + "loss": 0.6146, + "step": 68 + }, + { + "epoch": 0.01, + "learning_rate": 3.9204545454545456e-06, + "loss": 0.5762, + "step": 69 + }, + { + "epoch": 0.01, + "learning_rate": 3.9772727272727275e-06, + "loss": 0.6178, + "step": 70 + }, + { + "epoch": 0.01, + "learning_rate": 4.0340909090909095e-06, + "loss": 0.6147, + "step": 71 + }, + { + "epoch": 0.01, + "learning_rate": 4.0909090909090915e-06, + "loss": 0.5981, + "step": 72 + }, + { + "epoch": 0.01, + "learning_rate": 4.1477272727272734e-06, + "loss": 0.6093, + "step": 73 + }, + { + "epoch": 0.01, + "learning_rate": 4.204545454545455e-06, + "loss": 0.5902, + "step": 74 + }, + { + "epoch": 0.01, + "learning_rate": 4.2613636363636365e-06, + "loss": 0.5914, + "step": 75 + }, + { + "epoch": 0.01, + "learning_rate": 4.3181818181818185e-06, + "loss": 0.6028, + "step": 76 + }, + { + "epoch": 0.01, + "learning_rate": 4.3750000000000005e-06, + "loss": 0.6019, + "step": 77 + }, + { + "epoch": 0.01, + "learning_rate": 4.4318181818181824e-06, + "loss": 0.5854, + "step": 78 + }, + { + "epoch": 0.01, + "learning_rate": 4.4886363636363636e-06, + "loss": 0.5936, + "step": 79 + }, + { + "epoch": 0.01, + "learning_rate": 4.5454545454545455e-06, + "loss": 0.5891, + "step": 80 + }, + { + "epoch": 0.01, + "learning_rate": 4.6022727272727275e-06, + "loss": 0.5948, + "step": 81 + }, + { + "epoch": 0.01, + "learning_rate": 4.6590909090909095e-06, + "loss": 0.5685, + "step": 82 + }, + { + "epoch": 0.01, + "learning_rate": 4.715909090909091e-06, + "loss": 0.6131, + "step": 83 + }, + { + "epoch": 0.01, + "learning_rate": 4.772727272727273e-06, + "loss": 0.5894, + "step": 84 + }, + { + "epoch": 0.01, + "learning_rate": 4.829545454545455e-06, + "loss": 0.5825, + "step": 85 + }, + { + "epoch": 0.01, + "learning_rate": 4.8863636363636365e-06, + "loss": 0.581, + "step": 86 + }, + { + "epoch": 0.01, + "learning_rate": 4.9431818181818184e-06, + "loss": 0.5935, + "step": 87 + }, + { + "epoch": 0.01, + "learning_rate": 5e-06, + "loss": 0.5734, + "step": 88 + }, + { + "epoch": 0.01, + "learning_rate": 5.056818181818182e-06, + "loss": 0.5867, + "step": 89 + }, + { + "epoch": 0.01, + "learning_rate": 5.113636363636364e-06, + "loss": 0.5854, + "step": 90 + }, + { + "epoch": 0.01, + "learning_rate": 5.170454545454546e-06, + "loss": 0.5709, + "step": 91 + }, + { + "epoch": 0.01, + "learning_rate": 5.2272727272727274e-06, + "loss": 0.594, + "step": 92 + }, + { + "epoch": 0.01, + "learning_rate": 5.28409090909091e-06, + "loss": 0.6087, + "step": 93 + }, + { + "epoch": 0.01, + "learning_rate": 5.340909090909091e-06, + "loss": 0.5841, + "step": 94 + }, + { + "epoch": 0.01, + "learning_rate": 5.397727272727273e-06, + "loss": 0.5794, + "step": 95 + }, + { + "epoch": 0.01, + "learning_rate": 5.4545454545454545e-06, + "loss": 0.6066, + "step": 96 + }, + { + "epoch": 0.01, + "learning_rate": 5.511363636363637e-06, + "loss": 0.6109, + "step": 97 + }, + { + "epoch": 0.01, + "learning_rate": 5.568181818181818e-06, + "loss": 0.5983, + "step": 98 + }, + { + "epoch": 0.01, + "learning_rate": 5.625e-06, + "loss": 0.5796, + "step": 99 + }, + { + "epoch": 0.01, + "learning_rate": 5.681818181818183e-06, + "loss": 0.5862, + "step": 100 + }, + { + "epoch": 0.01, + "learning_rate": 5.738636363636364e-06, + "loss": 0.5716, + "step": 101 + }, + { + "epoch": 0.01, + "learning_rate": 5.795454545454546e-06, + "loss": 0.6007, + "step": 102 + }, + { + "epoch": 0.01, + "learning_rate": 5.852272727272727e-06, + "loss": 0.5913, + "step": 103 + }, + { + "epoch": 0.01, + "learning_rate": 5.90909090909091e-06, + "loss": 0.5739, + "step": 104 + }, + { + "epoch": 0.01, + "learning_rate": 5.965909090909091e-06, + "loss": 0.5694, + "step": 105 + }, + { + "epoch": 0.01, + "learning_rate": 6.022727272727273e-06, + "loss": 0.5812, + "step": 106 + }, + { + "epoch": 0.01, + "learning_rate": 6.079545454545454e-06, + "loss": 0.5785, + "step": 107 + }, + { + "epoch": 0.01, + "learning_rate": 6.136363636363637e-06, + "loss": 0.5652, + "step": 108 + }, + { + "epoch": 0.01, + "learning_rate": 6.193181818181818e-06, + "loss": 0.6019, + "step": 109 + }, + { + "epoch": 0.01, + "learning_rate": 6.25e-06, + "loss": 0.5777, + "step": 110 + }, + { + "epoch": 0.01, + "learning_rate": 6.306818181818183e-06, + "loss": 0.5536, + "step": 111 + }, + { + "epoch": 0.01, + "learning_rate": 6.363636363636364e-06, + "loss": 0.5866, + "step": 112 + }, + { + "epoch": 0.01, + "learning_rate": 6.420454545454546e-06, + "loss": 0.5716, + "step": 113 + }, + { + "epoch": 0.01, + "learning_rate": 6.477272727272727e-06, + "loss": 0.575, + "step": 114 + }, + { + "epoch": 0.01, + "learning_rate": 6.53409090909091e-06, + "loss": 0.5753, + "step": 115 + }, + { + "epoch": 0.01, + "learning_rate": 6.590909090909091e-06, + "loss": 0.5849, + "step": 116 + }, + { + "epoch": 0.01, + "learning_rate": 6.647727272727273e-06, + "loss": 0.5734, + "step": 117 + }, + { + "epoch": 0.01, + "learning_rate": 6.704545454545454e-06, + "loss": 0.5642, + "step": 118 + }, + { + "epoch": 0.01, + "learning_rate": 6.761363636363637e-06, + "loss": 0.5778, + "step": 119 + }, + { + "epoch": 0.01, + "learning_rate": 6.818181818181818e-06, + "loss": 0.584, + "step": 120 + }, + { + "epoch": 0.01, + "learning_rate": 6.875e-06, + "loss": 0.5705, + "step": 121 + }, + { + "epoch": 0.01, + "learning_rate": 6.931818181818183e-06, + "loss": 0.5684, + "step": 122 + }, + { + "epoch": 0.01, + "learning_rate": 6.988636363636364e-06, + "loss": 0.5613, + "step": 123 + }, + { + "epoch": 0.01, + "learning_rate": 7.045454545454546e-06, + "loss": 0.5571, + "step": 124 + }, + { + "epoch": 0.01, + "learning_rate": 7.102272727272727e-06, + "loss": 0.5713, + "step": 125 + }, + { + "epoch": 0.01, + "learning_rate": 7.15909090909091e-06, + "loss": 0.575, + "step": 126 + }, + { + "epoch": 0.01, + "learning_rate": 7.215909090909091e-06, + "loss": 0.5605, + "step": 127 + }, + { + "epoch": 0.01, + "learning_rate": 7.272727272727273e-06, + "loss": 0.5699, + "step": 128 + }, + { + "epoch": 0.01, + "learning_rate": 7.329545454545455e-06, + "loss": 0.5753, + "step": 129 + }, + { + "epoch": 0.01, + "learning_rate": 7.386363636363637e-06, + "loss": 0.581, + "step": 130 + }, + { + "epoch": 0.01, + "learning_rate": 7.443181818181818e-06, + "loss": 0.5872, + "step": 131 + }, + { + "epoch": 0.01, + "learning_rate": 7.500000000000001e-06, + "loss": 0.5759, + "step": 132 + }, + { + "epoch": 0.01, + "learning_rate": 7.556818181818183e-06, + "loss": 0.5758, + "step": 133 + }, + { + "epoch": 0.01, + "learning_rate": 7.613636363636364e-06, + "loss": 0.5758, + "step": 134 + }, + { + "epoch": 0.01, + "learning_rate": 7.670454545454547e-06, + "loss": 0.5789, + "step": 135 + }, + { + "epoch": 0.01, + "learning_rate": 7.727272727272727e-06, + "loss": 0.5654, + "step": 136 + }, + { + "epoch": 0.01, + "learning_rate": 7.784090909090911e-06, + "loss": 0.5738, + "step": 137 + }, + { + "epoch": 0.01, + "learning_rate": 7.840909090909091e-06, + "loss": 0.5719, + "step": 138 + }, + { + "epoch": 0.01, + "learning_rate": 7.897727272727273e-06, + "loss": 0.5668, + "step": 139 + }, + { + "epoch": 0.01, + "learning_rate": 7.954545454545455e-06, + "loss": 0.5623, + "step": 140 + }, + { + "epoch": 0.01, + "learning_rate": 8.011363636363637e-06, + "loss": 0.5725, + "step": 141 + }, + { + "epoch": 0.01, + "learning_rate": 8.068181818181819e-06, + "loss": 0.5783, + "step": 142 + }, + { + "epoch": 0.01, + "learning_rate": 8.125000000000001e-06, + "loss": 0.5622, + "step": 143 + }, + { + "epoch": 0.01, + "learning_rate": 8.181818181818183e-06, + "loss": 0.5735, + "step": 144 + }, + { + "epoch": 0.01, + "learning_rate": 8.238636363636365e-06, + "loss": 0.5636, + "step": 145 + }, + { + "epoch": 0.01, + "learning_rate": 8.295454545454547e-06, + "loss": 0.5552, + "step": 146 + }, + { + "epoch": 0.01, + "learning_rate": 8.352272727272727e-06, + "loss": 0.5744, + "step": 147 + }, + { + "epoch": 0.01, + "learning_rate": 8.40909090909091e-06, + "loss": 0.5676, + "step": 148 + }, + { + "epoch": 0.01, + "learning_rate": 8.465909090909091e-06, + "loss": 0.5992, + "step": 149 + }, + { + "epoch": 0.01, + "learning_rate": 8.522727272727273e-06, + "loss": 0.555, + "step": 150 + }, + { + "epoch": 0.01, + "learning_rate": 8.579545454545455e-06, + "loss": 0.5702, + "step": 151 + }, + { + "epoch": 0.01, + "learning_rate": 8.636363636363637e-06, + "loss": 0.5572, + "step": 152 + }, + { + "epoch": 0.01, + "learning_rate": 8.693181818181819e-06, + "loss": 0.5449, + "step": 153 + }, + { + "epoch": 0.01, + "learning_rate": 8.750000000000001e-06, + "loss": 0.5715, + "step": 154 + }, + { + "epoch": 0.01, + "learning_rate": 8.806818181818183e-06, + "loss": 0.562, + "step": 155 + }, + { + "epoch": 0.01, + "learning_rate": 8.863636363636365e-06, + "loss": 0.5682, + "step": 156 + }, + { + "epoch": 0.01, + "learning_rate": 8.920454545454547e-06, + "loss": 0.5532, + "step": 157 + }, + { + "epoch": 0.01, + "learning_rate": 8.977272727272727e-06, + "loss": 0.5642, + "step": 158 + }, + { + "epoch": 0.01, + "learning_rate": 9.03409090909091e-06, + "loss": 0.5429, + "step": 159 + }, + { + "epoch": 0.01, + "learning_rate": 9.090909090909091e-06, + "loss": 0.5696, + "step": 160 + }, + { + "epoch": 0.01, + "learning_rate": 9.147727272727273e-06, + "loss": 0.5438, + "step": 161 + }, + { + "epoch": 0.01, + "learning_rate": 9.204545454545455e-06, + "loss": 0.5495, + "step": 162 + }, + { + "epoch": 0.01, + "learning_rate": 9.261363636363637e-06, + "loss": 0.5602, + "step": 163 + }, + { + "epoch": 0.01, + "learning_rate": 9.318181818181819e-06, + "loss": 0.553, + "step": 164 + }, + { + "epoch": 0.01, + "learning_rate": 9.375000000000001e-06, + "loss": 0.5841, + "step": 165 + }, + { + "epoch": 0.01, + "learning_rate": 9.431818181818183e-06, + "loss": 0.543, + "step": 166 + }, + { + "epoch": 0.01, + "learning_rate": 9.488636363636365e-06, + "loss": 0.5576, + "step": 167 + }, + { + "epoch": 0.01, + "learning_rate": 9.545454545454547e-06, + "loss": 0.5526, + "step": 168 + }, + { + "epoch": 0.01, + "learning_rate": 9.602272727272727e-06, + "loss": 0.5529, + "step": 169 + }, + { + "epoch": 0.01, + "learning_rate": 9.65909090909091e-06, + "loss": 0.5739, + "step": 170 + }, + { + "epoch": 0.01, + "learning_rate": 9.715909090909091e-06, + "loss": 0.5573, + "step": 171 + }, + { + "epoch": 0.01, + "learning_rate": 9.772727272727273e-06, + "loss": 0.5462, + "step": 172 + }, + { + "epoch": 0.01, + "learning_rate": 9.829545454545455e-06, + "loss": 0.5636, + "step": 173 + }, + { + "epoch": 0.01, + "learning_rate": 9.886363636363637e-06, + "loss": 0.5692, + "step": 174 + }, + { + "epoch": 0.01, + "learning_rate": 9.943181818181819e-06, + "loss": 0.5616, + "step": 175 + }, + { + "epoch": 0.02, + "learning_rate": 1e-05, + "loss": 0.5679, + "step": 176 + }, + { + "epoch": 0.02, + "learning_rate": 1.0056818181818183e-05, + "loss": 0.5425, + "step": 177 + }, + { + "epoch": 0.02, + "learning_rate": 1.0113636363636365e-05, + "loss": 0.5566, + "step": 178 + }, + { + "epoch": 0.02, + "learning_rate": 1.0170454545454547e-05, + "loss": 0.5492, + "step": 179 + }, + { + "epoch": 0.02, + "learning_rate": 1.0227272727272729e-05, + "loss": 0.5442, + "step": 180 + }, + { + "epoch": 0.02, + "learning_rate": 1.0284090909090909e-05, + "loss": 0.5288, + "step": 181 + }, + { + "epoch": 0.02, + "learning_rate": 1.0340909090909093e-05, + "loss": 0.5405, + "step": 182 + }, + { + "epoch": 0.02, + "learning_rate": 1.0397727272727275e-05, + "loss": 0.558, + "step": 183 + }, + { + "epoch": 0.02, + "learning_rate": 1.0454545454545455e-05, + "loss": 0.5499, + "step": 184 + }, + { + "epoch": 0.02, + "learning_rate": 1.0511363636363637e-05, + "loss": 0.5433, + "step": 185 + }, + { + "epoch": 0.02, + "learning_rate": 1.056818181818182e-05, + "loss": 0.5428, + "step": 186 + }, + { + "epoch": 0.02, + "learning_rate": 1.0625e-05, + "loss": 0.5537, + "step": 187 + }, + { + "epoch": 0.02, + "learning_rate": 1.0681818181818183e-05, + "loss": 0.5635, + "step": 188 + }, + { + "epoch": 0.02, + "learning_rate": 1.0738636363636365e-05, + "loss": 0.537, + "step": 189 + }, + { + "epoch": 0.02, + "learning_rate": 1.0795454545454547e-05, + "loss": 0.5639, + "step": 190 + }, + { + "epoch": 0.02, + "learning_rate": 1.0852272727272729e-05, + "loss": 0.5481, + "step": 191 + }, + { + "epoch": 0.02, + "learning_rate": 1.0909090909090909e-05, + "loss": 0.547, + "step": 192 + }, + { + "epoch": 0.02, + "learning_rate": 1.0965909090909093e-05, + "loss": 0.5489, + "step": 193 + }, + { + "epoch": 0.02, + "learning_rate": 1.1022727272727275e-05, + "loss": 0.5451, + "step": 194 + }, + { + "epoch": 0.02, + "learning_rate": 1.1079545454545455e-05, + "loss": 0.5368, + "step": 195 + }, + { + "epoch": 0.02, + "learning_rate": 1.1136363636363637e-05, + "loss": 0.5366, + "step": 196 + }, + { + "epoch": 0.02, + "learning_rate": 1.119318181818182e-05, + "loss": 0.5548, + "step": 197 + }, + { + "epoch": 0.02, + "learning_rate": 1.125e-05, + "loss": 0.5475, + "step": 198 + }, + { + "epoch": 0.02, + "learning_rate": 1.1306818181818183e-05, + "loss": 0.5395, + "step": 199 + }, + { + "epoch": 0.02, + "learning_rate": 1.1363636363636366e-05, + "loss": 0.5397, + "step": 200 + }, + { + "epoch": 0.02, + "learning_rate": 1.1420454545454547e-05, + "loss": 0.5541, + "step": 201 + }, + { + "epoch": 0.02, + "learning_rate": 1.1477272727272729e-05, + "loss": 0.5561, + "step": 202 + }, + { + "epoch": 0.02, + "learning_rate": 1.1534090909090909e-05, + "loss": 0.5546, + "step": 203 + }, + { + "epoch": 0.02, + "learning_rate": 1.1590909090909093e-05, + "loss": 0.5613, + "step": 204 + }, + { + "epoch": 0.02, + "learning_rate": 1.1647727272727274e-05, + "loss": 0.5476, + "step": 205 + }, + { + "epoch": 0.02, + "learning_rate": 1.1704545454545455e-05, + "loss": 0.5428, + "step": 206 + }, + { + "epoch": 0.02, + "learning_rate": 1.1761363636363637e-05, + "loss": 0.5587, + "step": 207 + }, + { + "epoch": 0.02, + "learning_rate": 1.181818181818182e-05, + "loss": 0.5443, + "step": 208 + }, + { + "epoch": 0.02, + "learning_rate": 1.1875e-05, + "loss": 0.5538, + "step": 209 + }, + { + "epoch": 0.02, + "learning_rate": 1.1931818181818183e-05, + "loss": 0.5526, + "step": 210 + }, + { + "epoch": 0.02, + "learning_rate": 1.1988636363636366e-05, + "loss": 0.5321, + "step": 211 + }, + { + "epoch": 0.02, + "learning_rate": 1.2045454545454547e-05, + "loss": 0.5506, + "step": 212 + }, + { + "epoch": 0.02, + "learning_rate": 1.2102272727272729e-05, + "loss": 0.5487, + "step": 213 + }, + { + "epoch": 0.02, + "learning_rate": 1.2159090909090909e-05, + "loss": 0.5541, + "step": 214 + }, + { + "epoch": 0.02, + "learning_rate": 1.2215909090909092e-05, + "loss": 0.5522, + "step": 215 + }, + { + "epoch": 0.02, + "learning_rate": 1.2272727272727274e-05, + "loss": 0.5632, + "step": 216 + }, + { + "epoch": 0.02, + "learning_rate": 1.2329545454545455e-05, + "loss": 0.5492, + "step": 217 + }, + { + "epoch": 0.02, + "learning_rate": 1.2386363636363637e-05, + "loss": 0.5523, + "step": 218 + }, + { + "epoch": 0.02, + "learning_rate": 1.244318181818182e-05, + "loss": 0.5413, + "step": 219 + }, + { + "epoch": 0.02, + "learning_rate": 1.25e-05, + "loss": 0.5394, + "step": 220 + }, + { + "epoch": 0.02, + "learning_rate": 1.2556818181818183e-05, + "loss": 0.5223, + "step": 221 + }, + { + "epoch": 0.02, + "learning_rate": 1.2613636363636366e-05, + "loss": 0.5449, + "step": 222 + }, + { + "epoch": 0.02, + "learning_rate": 1.2670454545454547e-05, + "loss": 0.5536, + "step": 223 + }, + { + "epoch": 0.02, + "learning_rate": 1.2727272727272728e-05, + "loss": 0.5287, + "step": 224 + }, + { + "epoch": 0.02, + "learning_rate": 1.2784090909090909e-05, + "loss": 0.5495, + "step": 225 + }, + { + "epoch": 0.02, + "learning_rate": 1.2840909090909092e-05, + "loss": 0.5416, + "step": 226 + }, + { + "epoch": 0.02, + "learning_rate": 1.2897727272727274e-05, + "loss": 0.5526, + "step": 227 + }, + { + "epoch": 0.02, + "learning_rate": 1.2954545454545455e-05, + "loss": 0.5432, + "step": 228 + }, + { + "epoch": 0.02, + "learning_rate": 1.3011363636363637e-05, + "loss": 0.5649, + "step": 229 + }, + { + "epoch": 0.02, + "learning_rate": 1.306818181818182e-05, + "loss": 0.5212, + "step": 230 + }, + { + "epoch": 0.02, + "learning_rate": 1.3125e-05, + "loss": 0.5274, + "step": 231 + }, + { + "epoch": 0.02, + "learning_rate": 1.3181818181818183e-05, + "loss": 0.5552, + "step": 232 + }, + { + "epoch": 0.02, + "learning_rate": 1.3238636363636366e-05, + "loss": 0.5465, + "step": 233 + }, + { + "epoch": 0.02, + "learning_rate": 1.3295454545454546e-05, + "loss": 0.5473, + "step": 234 + }, + { + "epoch": 0.02, + "learning_rate": 1.3352272727272728e-05, + "loss": 0.5296, + "step": 235 + }, + { + "epoch": 0.02, + "learning_rate": 1.3409090909090909e-05, + "loss": 0.5506, + "step": 236 + }, + { + "epoch": 0.02, + "learning_rate": 1.3465909090909092e-05, + "loss": 0.5579, + "step": 237 + }, + { + "epoch": 0.02, + "learning_rate": 1.3522727272727274e-05, + "loss": 0.5562, + "step": 238 + }, + { + "epoch": 0.02, + "learning_rate": 1.3579545454545455e-05, + "loss": 0.5507, + "step": 239 + }, + { + "epoch": 0.02, + "learning_rate": 1.3636363636363637e-05, + "loss": 0.544, + "step": 240 + }, + { + "epoch": 0.02, + "learning_rate": 1.369318181818182e-05, + "loss": 0.5348, + "step": 241 + }, + { + "epoch": 0.02, + "learning_rate": 1.375e-05, + "loss": 0.5234, + "step": 242 + }, + { + "epoch": 0.02, + "learning_rate": 1.3806818181818182e-05, + "loss": 0.5447, + "step": 243 + }, + { + "epoch": 0.02, + "learning_rate": 1.3863636363636366e-05, + "loss": 0.5387, + "step": 244 + }, + { + "epoch": 0.02, + "learning_rate": 1.3920454545454546e-05, + "loss": 0.5563, + "step": 245 + }, + { + "epoch": 0.02, + "learning_rate": 1.3977272727272728e-05, + "loss": 0.5345, + "step": 246 + }, + { + "epoch": 0.02, + "learning_rate": 1.4034090909090909e-05, + "loss": 0.5547, + "step": 247 + }, + { + "epoch": 0.02, + "learning_rate": 1.4090909090909092e-05, + "loss": 0.5493, + "step": 248 + }, + { + "epoch": 0.02, + "learning_rate": 1.4147727272727274e-05, + "loss": 0.5449, + "step": 249 + }, + { + "epoch": 0.02, + "learning_rate": 1.4204545454545455e-05, + "loss": 0.5397, + "step": 250 + }, + { + "epoch": 0.02, + "learning_rate": 1.4261363636363637e-05, + "loss": 0.5312, + "step": 251 + }, + { + "epoch": 0.02, + "learning_rate": 1.431818181818182e-05, + "loss": 0.5437, + "step": 252 + }, + { + "epoch": 0.02, + "learning_rate": 1.4375e-05, + "loss": 0.5498, + "step": 253 + }, + { + "epoch": 0.02, + "learning_rate": 1.4431818181818182e-05, + "loss": 0.5212, + "step": 254 + }, + { + "epoch": 0.02, + "learning_rate": 1.4488636363636366e-05, + "loss": 0.5433, + "step": 255 + }, + { + "epoch": 0.02, + "learning_rate": 1.4545454545454546e-05, + "loss": 0.5408, + "step": 256 + }, + { + "epoch": 0.02, + "learning_rate": 1.4602272727272728e-05, + "loss": 0.5386, + "step": 257 + }, + { + "epoch": 0.02, + "learning_rate": 1.465909090909091e-05, + "loss": 0.5239, + "step": 258 + }, + { + "epoch": 0.02, + "learning_rate": 1.4715909090909092e-05, + "loss": 0.55, + "step": 259 + }, + { + "epoch": 0.02, + "learning_rate": 1.4772727272727274e-05, + "loss": 0.5381, + "step": 260 + }, + { + "epoch": 0.02, + "learning_rate": 1.4829545454545456e-05, + "loss": 0.5224, + "step": 261 + }, + { + "epoch": 0.02, + "learning_rate": 1.4886363636363636e-05, + "loss": 0.5501, + "step": 262 + }, + { + "epoch": 0.02, + "learning_rate": 1.494318181818182e-05, + "loss": 0.5296, + "step": 263 + }, + { + "epoch": 0.02, + "learning_rate": 1.5000000000000002e-05, + "loss": 0.5506, + "step": 264 + }, + { + "epoch": 0.02, + "learning_rate": 1.5056818181818182e-05, + "loss": 0.5325, + "step": 265 + }, + { + "epoch": 0.02, + "learning_rate": 1.5113636363636366e-05, + "loss": 0.5264, + "step": 266 + }, + { + "epoch": 0.02, + "learning_rate": 1.5170454545454546e-05, + "loss": 0.5438, + "step": 267 + }, + { + "epoch": 0.02, + "learning_rate": 1.5227272727272728e-05, + "loss": 0.5364, + "step": 268 + }, + { + "epoch": 0.02, + "learning_rate": 1.528409090909091e-05, + "loss": 0.5476, + "step": 269 + }, + { + "epoch": 0.02, + "learning_rate": 1.5340909090909094e-05, + "loss": 0.5346, + "step": 270 + }, + { + "epoch": 0.02, + "learning_rate": 1.5397727272727276e-05, + "loss": 0.5485, + "step": 271 + }, + { + "epoch": 0.02, + "learning_rate": 1.5454545454545454e-05, + "loss": 0.5413, + "step": 272 + }, + { + "epoch": 0.02, + "learning_rate": 1.5511363636363636e-05, + "loss": 0.548, + "step": 273 + }, + { + "epoch": 0.02, + "learning_rate": 1.5568181818181822e-05, + "loss": 0.5313, + "step": 274 + }, + { + "epoch": 0.02, + "learning_rate": 1.5625e-05, + "loss": 0.5486, + "step": 275 + }, + { + "epoch": 0.02, + "learning_rate": 1.5681818181818182e-05, + "loss": 0.5158, + "step": 276 + }, + { + "epoch": 0.02, + "learning_rate": 1.5738636363636364e-05, + "loss": 0.5346, + "step": 277 + }, + { + "epoch": 0.02, + "learning_rate": 1.5795454545454546e-05, + "loss": 0.5429, + "step": 278 + }, + { + "epoch": 0.02, + "learning_rate": 1.5852272727272728e-05, + "loss": 0.5371, + "step": 279 + }, + { + "epoch": 0.02, + "learning_rate": 1.590909090909091e-05, + "loss": 0.5517, + "step": 280 + }, + { + "epoch": 0.02, + "learning_rate": 1.5965909090909092e-05, + "loss": 0.5342, + "step": 281 + }, + { + "epoch": 0.02, + "learning_rate": 1.6022727272727274e-05, + "loss": 0.5546, + "step": 282 + }, + { + "epoch": 0.02, + "learning_rate": 1.6079545454545456e-05, + "loss": 0.5241, + "step": 283 + }, + { + "epoch": 0.02, + "learning_rate": 1.6136363636363638e-05, + "loss": 0.5701, + "step": 284 + }, + { + "epoch": 0.02, + "learning_rate": 1.619318181818182e-05, + "loss": 0.5336, + "step": 285 + }, + { + "epoch": 0.02, + "learning_rate": 1.6250000000000002e-05, + "loss": 0.5454, + "step": 286 + }, + { + "epoch": 0.02, + "learning_rate": 1.6306818181818184e-05, + "loss": 0.5445, + "step": 287 + }, + { + "epoch": 0.02, + "learning_rate": 1.6363636363636366e-05, + "loss": 0.525, + "step": 288 + }, + { + "epoch": 0.02, + "learning_rate": 1.6420454545454548e-05, + "loss": 0.5247, + "step": 289 + }, + { + "epoch": 0.02, + "learning_rate": 1.647727272727273e-05, + "loss": 0.54, + "step": 290 + }, + { + "epoch": 0.02, + "learning_rate": 1.653409090909091e-05, + "loss": 0.5535, + "step": 291 + }, + { + "epoch": 0.02, + "learning_rate": 1.6590909090909094e-05, + "loss": 0.5158, + "step": 292 + }, + { + "epoch": 0.02, + "learning_rate": 1.6647727272727276e-05, + "loss": 0.5402, + "step": 293 + }, + { + "epoch": 0.03, + "learning_rate": 1.6704545454545454e-05, + "loss": 0.5376, + "step": 294 + }, + { + "epoch": 0.03, + "learning_rate": 1.6761363636363636e-05, + "loss": 0.5668, + "step": 295 + }, + { + "epoch": 0.03, + "learning_rate": 1.681818181818182e-05, + "loss": 0.5181, + "step": 296 + }, + { + "epoch": 0.03, + "learning_rate": 1.6875e-05, + "loss": 0.5252, + "step": 297 + }, + { + "epoch": 0.03, + "learning_rate": 1.6931818181818182e-05, + "loss": 0.5398, + "step": 298 + }, + { + "epoch": 0.03, + "learning_rate": 1.6988636363636368e-05, + "loss": 0.5433, + "step": 299 + }, + { + "epoch": 0.03, + "learning_rate": 1.7045454545454546e-05, + "loss": 0.5473, + "step": 300 + }, + { + "epoch": 0.03, + "learning_rate": 1.7102272727272728e-05, + "loss": 0.5447, + "step": 301 + }, + { + "epoch": 0.03, + "learning_rate": 1.715909090909091e-05, + "loss": 0.5267, + "step": 302 + }, + { + "epoch": 0.03, + "learning_rate": 1.7215909090909092e-05, + "loss": 0.546, + "step": 303 + }, + { + "epoch": 0.03, + "learning_rate": 1.7272727272727274e-05, + "loss": 0.5532, + "step": 304 + }, + { + "epoch": 0.03, + "learning_rate": 1.7329545454545456e-05, + "loss": 0.5355, + "step": 305 + }, + { + "epoch": 0.03, + "learning_rate": 1.7386363636363638e-05, + "loss": 0.5337, + "step": 306 + }, + { + "epoch": 0.03, + "learning_rate": 1.744318181818182e-05, + "loss": 0.5344, + "step": 307 + }, + { + "epoch": 0.03, + "learning_rate": 1.7500000000000002e-05, + "loss": 0.5528, + "step": 308 + }, + { + "epoch": 0.03, + "learning_rate": 1.7556818181818184e-05, + "loss": 0.529, + "step": 309 + }, + { + "epoch": 0.03, + "learning_rate": 1.7613636363636366e-05, + "loss": 0.5664, + "step": 310 + }, + { + "epoch": 0.03, + "learning_rate": 1.7670454545454548e-05, + "loss": 0.5523, + "step": 311 + }, + { + "epoch": 0.03, + "learning_rate": 1.772727272727273e-05, + "loss": 0.5322, + "step": 312 + }, + { + "epoch": 0.03, + "learning_rate": 1.7784090909090908e-05, + "loss": 0.5412, + "step": 313 + }, + { + "epoch": 0.03, + "learning_rate": 1.7840909090909094e-05, + "loss": 0.5576, + "step": 314 + }, + { + "epoch": 0.03, + "learning_rate": 1.7897727272727276e-05, + "loss": 0.5157, + "step": 315 + }, + { + "epoch": 0.03, + "learning_rate": 1.7954545454545454e-05, + "loss": 0.5177, + "step": 316 + }, + { + "epoch": 0.03, + "learning_rate": 1.8011363636363636e-05, + "loss": 0.5492, + "step": 317 + }, + { + "epoch": 0.03, + "learning_rate": 1.806818181818182e-05, + "loss": 0.538, + "step": 318 + }, + { + "epoch": 0.03, + "learning_rate": 1.8125e-05, + "loss": 0.5347, + "step": 319 + }, + { + "epoch": 0.03, + "learning_rate": 1.8181818181818182e-05, + "loss": 0.5379, + "step": 320 + }, + { + "epoch": 0.03, + "learning_rate": 1.8238636363636367e-05, + "loss": 0.5498, + "step": 321 + }, + { + "epoch": 0.03, + "learning_rate": 1.8295454545454546e-05, + "loss": 0.5177, + "step": 322 + }, + { + "epoch": 0.03, + "learning_rate": 1.8352272727272728e-05, + "loss": 0.5479, + "step": 323 + }, + { + "epoch": 0.03, + "learning_rate": 1.840909090909091e-05, + "loss": 0.5348, + "step": 324 + }, + { + "epoch": 0.03, + "learning_rate": 1.8465909090909092e-05, + "loss": 0.5255, + "step": 325 + }, + { + "epoch": 0.03, + "learning_rate": 1.8522727272727274e-05, + "loss": 0.5329, + "step": 326 + }, + { + "epoch": 0.03, + "learning_rate": 1.8579545454545456e-05, + "loss": 0.5169, + "step": 327 + }, + { + "epoch": 0.03, + "learning_rate": 1.8636363636363638e-05, + "loss": 0.5337, + "step": 328 + }, + { + "epoch": 0.03, + "learning_rate": 1.869318181818182e-05, + "loss": 0.5213, + "step": 329 + }, + { + "epoch": 0.03, + "learning_rate": 1.8750000000000002e-05, + "loss": 0.5306, + "step": 330 + }, + { + "epoch": 0.03, + "learning_rate": 1.8806818181818184e-05, + "loss": 0.5152, + "step": 331 + }, + { + "epoch": 0.03, + "learning_rate": 1.8863636363636366e-05, + "loss": 0.5274, + "step": 332 + }, + { + "epoch": 0.03, + "learning_rate": 1.8920454545454548e-05, + "loss": 0.5655, + "step": 333 + }, + { + "epoch": 0.03, + "learning_rate": 1.897727272727273e-05, + "loss": 0.5333, + "step": 334 + }, + { + "epoch": 0.03, + "learning_rate": 1.9034090909090908e-05, + "loss": 0.539, + "step": 335 + }, + { + "epoch": 0.03, + "learning_rate": 1.9090909090909094e-05, + "loss": 0.5406, + "step": 336 + }, + { + "epoch": 0.03, + "learning_rate": 1.9147727272727276e-05, + "loss": 0.5225, + "step": 337 + }, + { + "epoch": 0.03, + "learning_rate": 1.9204545454545454e-05, + "loss": 0.5217, + "step": 338 + }, + { + "epoch": 0.03, + "learning_rate": 1.9261363636363636e-05, + "loss": 0.5411, + "step": 339 + }, + { + "epoch": 0.03, + "learning_rate": 1.931818181818182e-05, + "loss": 0.5475, + "step": 340 + }, + { + "epoch": 0.03, + "learning_rate": 1.9375e-05, + "loss": 0.5134, + "step": 341 + }, + { + "epoch": 0.03, + "learning_rate": 1.9431818181818182e-05, + "loss": 0.53, + "step": 342 + }, + { + "epoch": 0.03, + "learning_rate": 1.9488636363636367e-05, + "loss": 0.525, + "step": 343 + }, + { + "epoch": 0.03, + "learning_rate": 1.9545454545454546e-05, + "loss": 0.5207, + "step": 344 + }, + { + "epoch": 0.03, + "learning_rate": 1.9602272727272728e-05, + "loss": 0.533, + "step": 345 + }, + { + "epoch": 0.03, + "learning_rate": 1.965909090909091e-05, + "loss": 0.537, + "step": 346 + }, + { + "epoch": 0.03, + "learning_rate": 1.9715909090909092e-05, + "loss": 0.5257, + "step": 347 + }, + { + "epoch": 0.03, + "learning_rate": 1.9772727272727274e-05, + "loss": 0.5183, + "step": 348 + }, + { + "epoch": 0.03, + "learning_rate": 1.9829545454545456e-05, + "loss": 0.5568, + "step": 349 + }, + { + "epoch": 0.03, + "learning_rate": 1.9886363636363638e-05, + "loss": 0.5157, + "step": 350 + }, + { + "epoch": 0.03, + "learning_rate": 1.994318181818182e-05, + "loss": 0.5258, + "step": 351 + }, + { + "epoch": 0.03, + "learning_rate": 2e-05, + "loss": 0.5288, + "step": 352 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999999618679128e-05, + "loss": 0.5422, + "step": 353 + }, + { + "epoch": 0.03, + "learning_rate": 1.999999847471653e-05, + "loss": 0.5247, + "step": 354 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999996568112307e-05, + "loss": 0.5432, + "step": 355 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999993898866596e-05, + "loss": 0.5414, + "step": 356 + }, + { + "epoch": 0.03, + "learning_rate": 1.99999904669796e-05, + "loss": 0.5223, + "step": 357 + }, + { + "epoch": 0.03, + "learning_rate": 1.999998627245158e-05, + "loss": 0.5115, + "step": 358 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999981315282857e-05, + "loss": 0.5522, + "step": 359 + }, + { + "epoch": 0.03, + "learning_rate": 1.999997559547381e-05, + "loss": 0.5417, + "step": 360 + }, + { + "epoch": 0.03, + "learning_rate": 1.999996911302488e-05, + "loss": 0.5268, + "step": 361 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999961867936556e-05, + "loss": 0.5403, + "step": 362 + }, + { + "epoch": 0.03, + "learning_rate": 1.999995386020939e-05, + "loss": 0.5553, + "step": 363 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999945089843996e-05, + "loss": 0.5201, + "step": 364 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999935556841035e-05, + "loss": 0.5359, + "step": 365 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999925261201247e-05, + "loss": 0.5344, + "step": 366 + }, + { + "epoch": 0.03, + "learning_rate": 1.999991420292541e-05, + "loss": 0.5377, + "step": 367 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999902382014363e-05, + "loss": 0.5263, + "step": 368 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999889798469016e-05, + "loss": 0.5297, + "step": 369 + }, + { + "epoch": 0.03, + "learning_rate": 1.999987645229032e-05, + "loss": 0.5363, + "step": 370 + }, + { + "epoch": 0.03, + "learning_rate": 1.99998623434793e-05, + "loss": 0.5441, + "step": 371 + }, + { + "epoch": 0.03, + "learning_rate": 1.999984747203703e-05, + "loss": 0.5328, + "step": 372 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999831837964646e-05, + "loss": 0.5177, + "step": 373 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999815441263334e-05, + "loss": 0.5125, + "step": 374 + }, + { + "epoch": 0.03, + "learning_rate": 1.999979828193435e-05, + "loss": 0.5295, + "step": 375 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999780359979e-05, + "loss": 0.5429, + "step": 376 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999761675398656e-05, + "loss": 0.5469, + "step": 377 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999742228194734e-05, + "loss": 0.5435, + "step": 378 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999722018368724e-05, + "loss": 0.5163, + "step": 379 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999701045922163e-05, + "loss": 0.5089, + "step": 380 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999679310856657e-05, + "loss": 0.5421, + "step": 381 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999656813173856e-05, + "loss": 0.5194, + "step": 382 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999633552875482e-05, + "loss": 0.5188, + "step": 383 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999609529963303e-05, + "loss": 0.5394, + "step": 384 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999584744439155e-05, + "loss": 0.5088, + "step": 385 + }, + { + "epoch": 0.03, + "learning_rate": 1.999955919630493e-05, + "loss": 0.5371, + "step": 386 + }, + { + "epoch": 0.03, + "learning_rate": 1.999953288556257e-05, + "loss": 0.5251, + "step": 387 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999505812214087e-05, + "loss": 0.5514, + "step": 388 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999477976261543e-05, + "loss": 0.5257, + "step": 389 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999449377707063e-05, + "loss": 0.5168, + "step": 390 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999420016552828e-05, + "loss": 0.5411, + "step": 391 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999389892801075e-05, + "loss": 0.5394, + "step": 392 + }, + { + "epoch": 0.03, + "learning_rate": 1.99993590064541e-05, + "loss": 0.51, + "step": 393 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999327357514268e-05, + "loss": 0.5648, + "step": 394 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999294945983984e-05, + "loss": 0.5399, + "step": 395 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999261771865716e-05, + "loss": 0.5459, + "step": 396 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999227835162e-05, + "loss": 0.5357, + "step": 397 + }, + { + "epoch": 0.03, + "learning_rate": 1.999919313587543e-05, + "loss": 0.5207, + "step": 398 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999157674008642e-05, + "loss": 0.5184, + "step": 399 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999121449564347e-05, + "loss": 0.5138, + "step": 400 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999084462545305e-05, + "loss": 0.5447, + "step": 401 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999046712954332e-05, + "loss": 0.5242, + "step": 402 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999008200794315e-05, + "loss": 0.5089, + "step": 403 + }, + { + "epoch": 0.03, + "learning_rate": 1.999896892606819e-05, + "loss": 0.5387, + "step": 404 + }, + { + "epoch": 0.03, + "learning_rate": 1.999892888877895e-05, + "loss": 0.5408, + "step": 405 + }, + { + "epoch": 0.03, + "learning_rate": 1.9998888088929647e-05, + "loss": 0.542, + "step": 406 + }, + { + "epoch": 0.03, + "learning_rate": 1.9998846526523393e-05, + "loss": 0.5237, + "step": 407 + }, + { + "epoch": 0.03, + "learning_rate": 1.9998804201563362e-05, + "loss": 0.534, + "step": 408 + }, + { + "epoch": 0.03, + "learning_rate": 1.9998761114052775e-05, + "loss": 0.5544, + "step": 409 + }, + { + "epoch": 0.03, + "learning_rate": 1.9998717263994923e-05, + "loss": 0.5352, + "step": 410 + }, + { + "epoch": 0.04, + "learning_rate": 1.9998672651393153e-05, + "loss": 0.5242, + "step": 411 + }, + { + "epoch": 0.04, + "learning_rate": 1.999862727625086e-05, + "loss": 0.5229, + "step": 412 + }, + { + "epoch": 0.04, + "learning_rate": 1.999858113857151e-05, + "loss": 0.5376, + "step": 413 + }, + { + "epoch": 0.04, + "learning_rate": 1.9998534238358617e-05, + "loss": 0.5456, + "step": 414 + }, + { + "epoch": 0.04, + "learning_rate": 1.999848657561576e-05, + "loss": 0.5349, + "step": 415 + }, + { + "epoch": 0.04, + "learning_rate": 1.9998438150346578e-05, + "loss": 0.5161, + "step": 416 + }, + { + "epoch": 0.04, + "learning_rate": 1.999838896255476e-05, + "loss": 0.5492, + "step": 417 + }, + { + "epoch": 0.04, + "learning_rate": 1.9998339012244052e-05, + "loss": 0.5328, + "step": 418 + }, + { + "epoch": 0.04, + "learning_rate": 1.9998288299418275e-05, + "loss": 0.5155, + "step": 419 + }, + { + "epoch": 0.04, + "learning_rate": 1.9998236824081288e-05, + "loss": 0.5225, + "step": 420 + }, + { + "epoch": 0.04, + "learning_rate": 1.9998184586237023e-05, + "loss": 0.5249, + "step": 421 + }, + { + "epoch": 0.04, + "learning_rate": 1.9998131585889456e-05, + "loss": 0.5125, + "step": 422 + }, + { + "epoch": 0.04, + "learning_rate": 1.9998077823042634e-05, + "loss": 0.5482, + "step": 423 + }, + { + "epoch": 0.04, + "learning_rate": 1.9998023297700656e-05, + "loss": 0.549, + "step": 424 + }, + { + "epoch": 0.04, + "learning_rate": 1.9997968009867683e-05, + "loss": 0.5196, + "step": 425 + }, + { + "epoch": 0.04, + "learning_rate": 1.999791195954793e-05, + "loss": 0.5317, + "step": 426 + }, + { + "epoch": 0.04, + "learning_rate": 1.9997855146745667e-05, + "loss": 0.5355, + "step": 427 + }, + { + "epoch": 0.04, + "learning_rate": 1.9997797571465234e-05, + "loss": 0.5124, + "step": 428 + }, + { + "epoch": 0.04, + "learning_rate": 1.9997739233711017e-05, + "loss": 0.4932, + "step": 429 + }, + { + "epoch": 0.04, + "learning_rate": 1.9997680133487468e-05, + "loss": 0.5316, + "step": 430 + }, + { + "epoch": 0.04, + "learning_rate": 1.999762027079909e-05, + "loss": 0.5079, + "step": 431 + }, + { + "epoch": 0.04, + "learning_rate": 1.999755964565046e-05, + "loss": 0.5117, + "step": 432 + }, + { + "epoch": 0.04, + "learning_rate": 1.9997498258046183e-05, + "loss": 0.5287, + "step": 433 + }, + { + "epoch": 0.04, + "learning_rate": 1.9997436107990956e-05, + "loss": 0.5346, + "step": 434 + }, + { + "epoch": 0.04, + "learning_rate": 1.9997373195489508e-05, + "loss": 0.5355, + "step": 435 + }, + { + "epoch": 0.04, + "learning_rate": 1.9997309520546646e-05, + "loss": 0.5103, + "step": 436 + }, + { + "epoch": 0.04, + "learning_rate": 1.9997245083167223e-05, + "loss": 0.5585, + "step": 437 + }, + { + "epoch": 0.04, + "learning_rate": 1.9997179883356154e-05, + "loss": 0.521, + "step": 438 + }, + { + "epoch": 0.04, + "learning_rate": 1.9997113921118404e-05, + "loss": 0.5316, + "step": 439 + }, + { + "epoch": 0.04, + "learning_rate": 1.9997047196459016e-05, + "loss": 0.5175, + "step": 440 + }, + { + "epoch": 0.04, + "learning_rate": 1.999697970938307e-05, + "loss": 0.5304, + "step": 441 + }, + { + "epoch": 0.04, + "learning_rate": 1.9996911459895717e-05, + "loss": 0.5203, + "step": 442 + }, + { + "epoch": 0.04, + "learning_rate": 1.9996842448002156e-05, + "loss": 0.5322, + "step": 443 + }, + { + "epoch": 0.04, + "learning_rate": 1.999677267370766e-05, + "loss": 0.5384, + "step": 444 + }, + { + "epoch": 0.04, + "learning_rate": 1.9996702137017537e-05, + "loss": 0.5369, + "step": 445 + }, + { + "epoch": 0.04, + "learning_rate": 1.9996630837937182e-05, + "loss": 0.5209, + "step": 446 + }, + { + "epoch": 0.04, + "learning_rate": 1.9996558776472022e-05, + "loss": 0.556, + "step": 447 + }, + { + "epoch": 0.04, + "learning_rate": 1.9996485952627554e-05, + "loss": 0.5256, + "step": 448 + }, + { + "epoch": 0.04, + "learning_rate": 1.9996412366409333e-05, + "loss": 0.5309, + "step": 449 + }, + { + "epoch": 0.04, + "learning_rate": 1.9996338017822973e-05, + "loss": 0.5546, + "step": 450 + }, + { + "epoch": 0.04, + "learning_rate": 1.999626290687414e-05, + "loss": 0.516, + "step": 451 + }, + { + "epoch": 0.04, + "learning_rate": 1.9996187033568567e-05, + "loss": 0.5216, + "step": 452 + }, + { + "epoch": 0.04, + "learning_rate": 1.9996110397912037e-05, + "loss": 0.5332, + "step": 453 + }, + { + "epoch": 0.04, + "learning_rate": 1.9996032999910394e-05, + "loss": 0.5255, + "step": 454 + }, + { + "epoch": 0.04, + "learning_rate": 1.9995954839569544e-05, + "loss": 0.538, + "step": 455 + }, + { + "epoch": 0.04, + "learning_rate": 1.9995875916895447e-05, + "loss": 0.5501, + "step": 456 + }, + { + "epoch": 0.04, + "learning_rate": 1.999579623189412e-05, + "loss": 0.5407, + "step": 457 + }, + { + "epoch": 0.04, + "learning_rate": 1.999571578457164e-05, + "loss": 0.5186, + "step": 458 + }, + { + "epoch": 0.04, + "learning_rate": 1.9995634574934145e-05, + "loss": 0.5404, + "step": 459 + }, + { + "epoch": 0.04, + "learning_rate": 1.9995552602987828e-05, + "loss": 0.5437, + "step": 460 + }, + { + "epoch": 0.04, + "learning_rate": 1.9995469868738936e-05, + "loss": 0.5418, + "step": 461 + }, + { + "epoch": 0.04, + "learning_rate": 1.9995386372193782e-05, + "loss": 0.5292, + "step": 462 + }, + { + "epoch": 0.04, + "learning_rate": 1.9995302113358735e-05, + "loss": 0.5239, + "step": 463 + }, + { + "epoch": 0.04, + "learning_rate": 1.999521709224022e-05, + "loss": 0.5442, + "step": 464 + }, + { + "epoch": 0.04, + "learning_rate": 1.9995131308844722e-05, + "loss": 0.5359, + "step": 465 + }, + { + "epoch": 0.04, + "learning_rate": 1.999504476317878e-05, + "loss": 0.5269, + "step": 466 + }, + { + "epoch": 0.04, + "learning_rate": 1.9994957455248994e-05, + "loss": 0.5233, + "step": 467 + }, + { + "epoch": 0.04, + "learning_rate": 1.999486938506203e-05, + "loss": 0.5268, + "step": 468 + }, + { + "epoch": 0.04, + "learning_rate": 1.9994780552624595e-05, + "loss": 0.5326, + "step": 469 + }, + { + "epoch": 0.04, + "learning_rate": 1.999469095794347e-05, + "loss": 0.5397, + "step": 470 + }, + { + "epoch": 0.04, + "learning_rate": 1.999460060102549e-05, + "loss": 0.5209, + "step": 471 + }, + { + "epoch": 0.04, + "learning_rate": 1.9994509481877536e-05, + "loss": 0.5209, + "step": 472 + }, + { + "epoch": 0.04, + "learning_rate": 1.9994417600506565e-05, + "loss": 0.5342, + "step": 473 + }, + { + "epoch": 0.04, + "learning_rate": 1.9994324956919583e-05, + "loss": 0.5177, + "step": 474 + }, + { + "epoch": 0.04, + "learning_rate": 1.9994231551123655e-05, + "loss": 0.5497, + "step": 475 + }, + { + "epoch": 0.04, + "learning_rate": 1.99941373831259e-05, + "loss": 0.5277, + "step": 476 + }, + { + "epoch": 0.04, + "learning_rate": 1.9994042452933508e-05, + "loss": 0.5228, + "step": 477 + }, + { + "epoch": 0.04, + "learning_rate": 1.9993946760553717e-05, + "loss": 0.5314, + "step": 478 + }, + { + "epoch": 0.04, + "learning_rate": 1.999385030599382e-05, + "loss": 0.5345, + "step": 479 + }, + { + "epoch": 0.04, + "learning_rate": 1.9993753089261175e-05, + "loss": 0.5337, + "step": 480 + }, + { + "epoch": 0.04, + "learning_rate": 1.9993655110363197e-05, + "loss": 0.5227, + "step": 481 + }, + { + "epoch": 0.04, + "learning_rate": 1.9993556369307355e-05, + "loss": 0.5244, + "step": 482 + }, + { + "epoch": 0.04, + "learning_rate": 1.9993456866101188e-05, + "loss": 0.5111, + "step": 483 + }, + { + "epoch": 0.04, + "learning_rate": 1.9993356600752277e-05, + "loss": 0.5316, + "step": 484 + }, + { + "epoch": 0.04, + "learning_rate": 1.9993255573268267e-05, + "loss": 0.537, + "step": 485 + }, + { + "epoch": 0.04, + "learning_rate": 1.999315378365687e-05, + "loss": 0.5425, + "step": 486 + }, + { + "epoch": 0.04, + "learning_rate": 1.9993051231925847e-05, + "loss": 0.5091, + "step": 487 + }, + { + "epoch": 0.04, + "learning_rate": 1.9992947918083014e-05, + "loss": 0.5313, + "step": 488 + }, + { + "epoch": 0.04, + "learning_rate": 1.9992843842136254e-05, + "loss": 0.5321, + "step": 489 + }, + { + "epoch": 0.04, + "learning_rate": 1.9992739004093503e-05, + "loss": 0.5362, + "step": 490 + }, + { + "epoch": 0.04, + "learning_rate": 1.999263340396276e-05, + "loss": 0.5339, + "step": 491 + }, + { + "epoch": 0.04, + "learning_rate": 1.9992527041752076e-05, + "loss": 0.5124, + "step": 492 + }, + { + "epoch": 0.04, + "learning_rate": 1.9992419917469558e-05, + "loss": 0.5102, + "step": 493 + }, + { + "epoch": 0.04, + "learning_rate": 1.9992312031123383e-05, + "loss": 0.5492, + "step": 494 + }, + { + "epoch": 0.04, + "learning_rate": 1.9992203382721774e-05, + "loss": 0.5252, + "step": 495 + }, + { + "epoch": 0.04, + "learning_rate": 1.999209397227302e-05, + "loss": 0.5385, + "step": 496 + }, + { + "epoch": 0.04, + "learning_rate": 1.9991983799785464e-05, + "loss": 0.5208, + "step": 497 + }, + { + "epoch": 0.04, + "learning_rate": 1.9991872865267508e-05, + "loss": 0.5383, + "step": 498 + }, + { + "epoch": 0.04, + "learning_rate": 1.9991761168727612e-05, + "loss": 0.5183, + "step": 499 + }, + { + "epoch": 0.04, + "learning_rate": 1.9991648710174295e-05, + "loss": 0.5354, + "step": 500 + }, + { + "epoch": 0.04, + "learning_rate": 1.9991535489616135e-05, + "loss": 0.5073, + "step": 501 + }, + { + "epoch": 0.04, + "learning_rate": 1.9991421507061763e-05, + "loss": 0.5302, + "step": 502 + }, + { + "epoch": 0.04, + "learning_rate": 1.9991306762519875e-05, + "loss": 0.5327, + "step": 503 + }, + { + "epoch": 0.04, + "learning_rate": 1.999119125599922e-05, + "loss": 0.5247, + "step": 504 + }, + { + "epoch": 0.04, + "learning_rate": 1.9991074987508613e-05, + "loss": 0.539, + "step": 505 + }, + { + "epoch": 0.04, + "learning_rate": 1.9990957957056907e-05, + "loss": 0.53, + "step": 506 + }, + { + "epoch": 0.04, + "learning_rate": 1.9990840164653042e-05, + "loss": 0.5364, + "step": 507 + }, + { + "epoch": 0.04, + "learning_rate": 1.9990721610305998e-05, + "loss": 0.5227, + "step": 508 + }, + { + "epoch": 0.04, + "learning_rate": 1.9990602294024808e-05, + "loss": 0.523, + "step": 509 + }, + { + "epoch": 0.04, + "learning_rate": 1.999048221581858e-05, + "loss": 0.5412, + "step": 510 + }, + { + "epoch": 0.04, + "learning_rate": 1.9990361375696467e-05, + "loss": 0.5176, + "step": 511 + }, + { + "epoch": 0.04, + "learning_rate": 1.999023977366769e-05, + "loss": 0.548, + "step": 512 + }, + { + "epoch": 0.04, + "learning_rate": 1.999011740974152e-05, + "loss": 0.5202, + "step": 513 + }, + { + "epoch": 0.04, + "learning_rate": 1.9989994283927287e-05, + "loss": 0.518, + "step": 514 + }, + { + "epoch": 0.04, + "learning_rate": 1.9989870396234384e-05, + "loss": 0.5218, + "step": 515 + }, + { + "epoch": 0.04, + "learning_rate": 1.9989745746672258e-05, + "loss": 0.5351, + "step": 516 + }, + { + "epoch": 0.04, + "learning_rate": 1.9989620335250413e-05, + "loss": 0.5408, + "step": 517 + }, + { + "epoch": 0.04, + "learning_rate": 1.998949416197842e-05, + "loss": 0.5218, + "step": 518 + }, + { + "epoch": 0.04, + "learning_rate": 1.9989367226865895e-05, + "loss": 0.5302, + "step": 519 + }, + { + "epoch": 0.04, + "learning_rate": 1.9989239529922523e-05, + "loss": 0.5254, + "step": 520 + }, + { + "epoch": 0.04, + "learning_rate": 1.9989111071158037e-05, + "loss": 0.5407, + "step": 521 + }, + { + "epoch": 0.04, + "learning_rate": 1.998898185058224e-05, + "loss": 0.5241, + "step": 522 + }, + { + "epoch": 0.04, + "learning_rate": 1.9988851868204983e-05, + "loss": 0.5225, + "step": 523 + }, + { + "epoch": 0.04, + "learning_rate": 1.9988721124036182e-05, + "loss": 0.5138, + "step": 524 + }, + { + "epoch": 0.04, + "learning_rate": 1.9988589618085807e-05, + "loss": 0.5183, + "step": 525 + }, + { + "epoch": 0.04, + "learning_rate": 1.9988457350363885e-05, + "loss": 0.5243, + "step": 526 + }, + { + "epoch": 0.04, + "learning_rate": 1.9988324320880504e-05, + "loss": 0.5215, + "step": 527 + }, + { + "epoch": 0.05, + "learning_rate": 1.998819052964581e-05, + "loss": 0.5329, + "step": 528 + }, + { + "epoch": 0.05, + "learning_rate": 1.9988055976670008e-05, + "loss": 0.5176, + "step": 529 + }, + { + "epoch": 0.05, + "learning_rate": 1.998792066196336e-05, + "loss": 0.5207, + "step": 530 + }, + { + "epoch": 0.05, + "learning_rate": 1.9987784585536182e-05, + "loss": 0.5312, + "step": 531 + }, + { + "epoch": 0.05, + "learning_rate": 1.9987647747398854e-05, + "loss": 0.5175, + "step": 532 + }, + { + "epoch": 0.05, + "learning_rate": 1.998751014756181e-05, + "loss": 0.5377, + "step": 533 + }, + { + "epoch": 0.05, + "learning_rate": 1.998737178603555e-05, + "loss": 0.5136, + "step": 534 + }, + { + "epoch": 0.05, + "learning_rate": 1.9987232662830618e-05, + "loss": 0.5381, + "step": 535 + }, + { + "epoch": 0.05, + "learning_rate": 1.998709277795763e-05, + "loss": 0.5257, + "step": 536 + }, + { + "epoch": 0.05, + "learning_rate": 1.998695213142725e-05, + "loss": 0.5279, + "step": 537 + }, + { + "epoch": 0.05, + "learning_rate": 1.9986810723250206e-05, + "loss": 0.4932, + "step": 538 + }, + { + "epoch": 0.05, + "learning_rate": 1.9986668553437283e-05, + "loss": 0.5141, + "step": 539 + }, + { + "epoch": 0.05, + "learning_rate": 1.9986525621999323e-05, + "loss": 0.5272, + "step": 540 + }, + { + "epoch": 0.05, + "learning_rate": 1.9986381928947227e-05, + "loss": 0.5381, + "step": 541 + }, + { + "epoch": 0.05, + "learning_rate": 1.9986237474291955e-05, + "loss": 0.5271, + "step": 542 + }, + { + "epoch": 0.05, + "learning_rate": 1.9986092258044518e-05, + "loss": 0.5215, + "step": 543 + }, + { + "epoch": 0.05, + "learning_rate": 1.9985946280215996e-05, + "loss": 0.5392, + "step": 544 + }, + { + "epoch": 0.05, + "learning_rate": 1.9985799540817525e-05, + "loss": 0.5294, + "step": 545 + }, + { + "epoch": 0.05, + "learning_rate": 1.9985652039860282e-05, + "loss": 0.5391, + "step": 546 + }, + { + "epoch": 0.05, + "learning_rate": 1.9985503777355534e-05, + "loss": 0.5257, + "step": 547 + }, + { + "epoch": 0.05, + "learning_rate": 1.998535475331458e-05, + "loss": 0.5378, + "step": 548 + }, + { + "epoch": 0.05, + "learning_rate": 1.998520496774878e-05, + "loss": 0.5317, + "step": 549 + }, + { + "epoch": 0.05, + "learning_rate": 1.9985054420669562e-05, + "loss": 0.5165, + "step": 550 + }, + { + "epoch": 0.05, + "learning_rate": 1.9984903112088413e-05, + "loss": 0.5301, + "step": 551 + }, + { + "epoch": 0.05, + "learning_rate": 1.998475104201686e-05, + "loss": 0.5224, + "step": 552 + }, + { + "epoch": 0.05, + "learning_rate": 1.998459821046651e-05, + "loss": 0.5309, + "step": 553 + }, + { + "epoch": 0.05, + "learning_rate": 1.9984444617449022e-05, + "loss": 0.5155, + "step": 554 + }, + { + "epoch": 0.05, + "learning_rate": 1.9984290262976097e-05, + "loss": 0.5376, + "step": 555 + }, + { + "epoch": 0.05, + "learning_rate": 1.9984135147059515e-05, + "loss": 0.5159, + "step": 556 + }, + { + "epoch": 0.05, + "learning_rate": 1.9983979269711106e-05, + "loss": 0.5342, + "step": 557 + }, + { + "epoch": 0.05, + "learning_rate": 1.9983822630942754e-05, + "loss": 0.516, + "step": 558 + }, + { + "epoch": 0.05, + "learning_rate": 1.9983665230766406e-05, + "loss": 0.5305, + "step": 559 + }, + { + "epoch": 0.05, + "learning_rate": 1.998350706919407e-05, + "loss": 0.5153, + "step": 560 + }, + { + "epoch": 0.05, + "learning_rate": 1.9983348146237806e-05, + "loss": 0.5297, + "step": 561 + }, + { + "epoch": 0.05, + "learning_rate": 1.998318846190973e-05, + "loss": 0.511, + "step": 562 + }, + { + "epoch": 0.05, + "learning_rate": 1.998302801622202e-05, + "loss": 0.5373, + "step": 563 + }, + { + "epoch": 0.05, + "learning_rate": 1.998286680918692e-05, + "loss": 0.5439, + "step": 564 + }, + { + "epoch": 0.05, + "learning_rate": 1.998270484081672e-05, + "loss": 0.5114, + "step": 565 + }, + { + "epoch": 0.05, + "learning_rate": 1.9982542111123772e-05, + "loss": 0.501, + "step": 566 + }, + { + "epoch": 0.05, + "learning_rate": 1.9982378620120485e-05, + "loss": 0.5305, + "step": 567 + }, + { + "epoch": 0.05, + "learning_rate": 1.998221436781933e-05, + "loss": 0.5171, + "step": 568 + }, + { + "epoch": 0.05, + "learning_rate": 1.9982049354232834e-05, + "loss": 0.5096, + "step": 569 + }, + { + "epoch": 0.05, + "learning_rate": 1.998188357937358e-05, + "loss": 0.532, + "step": 570 + }, + { + "epoch": 0.05, + "learning_rate": 1.998171704325421e-05, + "loss": 0.5121, + "step": 571 + }, + { + "epoch": 0.05, + "learning_rate": 1.998154974588743e-05, + "loss": 0.5303, + "step": 572 + }, + { + "epoch": 0.05, + "learning_rate": 1.9981381687285992e-05, + "loss": 0.5134, + "step": 573 + }, + { + "epoch": 0.05, + "learning_rate": 1.9981212867462715e-05, + "loss": 0.5155, + "step": 574 + }, + { + "epoch": 0.05, + "learning_rate": 1.9981043286430474e-05, + "loss": 0.503, + "step": 575 + }, + { + "epoch": 0.05, + "learning_rate": 1.9980872944202203e-05, + "loss": 0.5242, + "step": 576 + }, + { + "epoch": 0.05, + "learning_rate": 1.9980701840790893e-05, + "loss": 0.5397, + "step": 577 + }, + { + "epoch": 0.05, + "learning_rate": 1.998052997620959e-05, + "loss": 0.5254, + "step": 578 + }, + { + "epoch": 0.05, + "learning_rate": 1.9980357350471403e-05, + "loss": 0.5341, + "step": 579 + }, + { + "epoch": 0.05, + "learning_rate": 1.9980183963589505e-05, + "loss": 0.5229, + "step": 580 + }, + { + "epoch": 0.05, + "learning_rate": 1.9980009815577105e-05, + "loss": 0.5228, + "step": 581 + }, + { + "epoch": 0.05, + "learning_rate": 1.997983490644749e-05, + "loss": 0.5357, + "step": 582 + }, + { + "epoch": 0.05, + "learning_rate": 1.9979659236214005e-05, + "loss": 0.5245, + "step": 583 + }, + { + "epoch": 0.05, + "learning_rate": 1.997948280489004e-05, + "loss": 0.5141, + "step": 584 + }, + { + "epoch": 0.05, + "learning_rate": 1.9979305612489057e-05, + "loss": 0.5562, + "step": 585 + }, + { + "epoch": 0.05, + "learning_rate": 1.9979127659024563e-05, + "loss": 0.528, + "step": 586 + }, + { + "epoch": 0.05, + "learning_rate": 1.9978948944510133e-05, + "loss": 0.5169, + "step": 587 + }, + { + "epoch": 0.05, + "learning_rate": 1.9978769468959393e-05, + "loss": 0.5158, + "step": 588 + }, + { + "epoch": 0.05, + "learning_rate": 1.9978589232386036e-05, + "loss": 0.5187, + "step": 589 + }, + { + "epoch": 0.05, + "learning_rate": 1.9978408234803805e-05, + "loss": 0.5179, + "step": 590 + }, + { + "epoch": 0.05, + "learning_rate": 1.99782264762265e-05, + "loss": 0.5094, + "step": 591 + }, + { + "epoch": 0.05, + "learning_rate": 1.997804395666799e-05, + "loss": 0.525, + "step": 592 + }, + { + "epoch": 0.05, + "learning_rate": 1.9977860676142188e-05, + "loss": 0.5214, + "step": 593 + }, + { + "epoch": 0.05, + "learning_rate": 1.9977676634663076e-05, + "loss": 0.5176, + "step": 594 + }, + { + "epoch": 0.05, + "learning_rate": 1.997749183224469e-05, + "loss": 0.5363, + "step": 595 + }, + { + "epoch": 0.05, + "learning_rate": 1.997730626890112e-05, + "loss": 0.5173, + "step": 596 + }, + { + "epoch": 0.05, + "learning_rate": 1.997711994464652e-05, + "loss": 0.5193, + "step": 597 + }, + { + "epoch": 0.05, + "learning_rate": 1.99769328594951e-05, + "loss": 0.5202, + "step": 598 + }, + { + "epoch": 0.05, + "learning_rate": 1.9976745013461127e-05, + "loss": 0.5331, + "step": 599 + }, + { + "epoch": 0.05, + "learning_rate": 1.997655640655893e-05, + "loss": 0.5283, + "step": 600 + }, + { + "epoch": 0.05, + "learning_rate": 1.9976367038802888e-05, + "loss": 0.5234, + "step": 601 + }, + { + "epoch": 0.05, + "learning_rate": 1.9976176910207444e-05, + "loss": 0.5182, + "step": 602 + }, + { + "epoch": 0.05, + "learning_rate": 1.99759860207871e-05, + "loss": 0.5289, + "step": 603 + }, + { + "epoch": 0.05, + "learning_rate": 1.997579437055642e-05, + "loss": 0.5214, + "step": 604 + }, + { + "epoch": 0.05, + "learning_rate": 1.9975601959530007e-05, + "loss": 0.5256, + "step": 605 + }, + { + "epoch": 0.05, + "learning_rate": 1.9975408787722545e-05, + "loss": 0.5387, + "step": 606 + }, + { + "epoch": 0.05, + "learning_rate": 1.997521485514876e-05, + "loss": 0.5362, + "step": 607 + }, + { + "epoch": 0.05, + "learning_rate": 1.9975020161823445e-05, + "loss": 0.5215, + "step": 608 + }, + { + "epoch": 0.05, + "learning_rate": 1.9974824707761452e-05, + "loss": 0.5079, + "step": 609 + }, + { + "epoch": 0.05, + "learning_rate": 1.9974628492977678e-05, + "loss": 0.5185, + "step": 610 + }, + { + "epoch": 0.05, + "learning_rate": 1.9974431517487096e-05, + "loss": 0.5207, + "step": 611 + }, + { + "epoch": 0.05, + "learning_rate": 1.9974233781304725e-05, + "loss": 0.5274, + "step": 612 + }, + { + "epoch": 0.05, + "learning_rate": 1.9974035284445642e-05, + "loss": 0.5162, + "step": 613 + }, + { + "epoch": 0.05, + "learning_rate": 1.997383602692499e-05, + "loss": 0.5113, + "step": 614 + }, + { + "epoch": 0.05, + "learning_rate": 1.9973636008757958e-05, + "loss": 0.5404, + "step": 615 + }, + { + "epoch": 0.05, + "learning_rate": 1.9973435229959813e-05, + "loss": 0.5086, + "step": 616 + }, + { + "epoch": 0.05, + "learning_rate": 1.9973233690545854e-05, + "loss": 0.5533, + "step": 617 + }, + { + "epoch": 0.05, + "learning_rate": 1.9973031390531457e-05, + "loss": 0.5208, + "step": 618 + }, + { + "epoch": 0.05, + "learning_rate": 1.997282832993205e-05, + "loss": 0.5186, + "step": 619 + }, + { + "epoch": 0.05, + "learning_rate": 1.9972624508763125e-05, + "loss": 0.518, + "step": 620 + }, + { + "epoch": 0.05, + "learning_rate": 1.9972419927040214e-05, + "loss": 0.5217, + "step": 621 + }, + { + "epoch": 0.05, + "learning_rate": 1.997221458477893e-05, + "loss": 0.5318, + "step": 622 + }, + { + "epoch": 0.05, + "learning_rate": 1.9972008481994923e-05, + "loss": 0.5053, + "step": 623 + }, + { + "epoch": 0.05, + "learning_rate": 1.9971801618703924e-05, + "loss": 0.5236, + "step": 624 + }, + { + "epoch": 0.05, + "learning_rate": 1.99715939949217e-05, + "loss": 0.5219, + "step": 625 + }, + { + "epoch": 0.05, + "learning_rate": 1.9971385610664086e-05, + "loss": 0.513, + "step": 626 + }, + { + "epoch": 0.05, + "learning_rate": 1.9971176465946977e-05, + "loss": 0.508, + "step": 627 + }, + { + "epoch": 0.05, + "learning_rate": 1.9970966560786324e-05, + "loss": 0.5127, + "step": 628 + }, + { + "epoch": 0.05, + "learning_rate": 1.9970755895198133e-05, + "loss": 0.5124, + "step": 629 + }, + { + "epoch": 0.05, + "learning_rate": 1.997054446919847e-05, + "loss": 0.5194, + "step": 630 + }, + { + "epoch": 0.05, + "learning_rate": 1.997033228280346e-05, + "loss": 0.5396, + "step": 631 + }, + { + "epoch": 0.05, + "learning_rate": 1.9970119336029286e-05, + "loss": 0.5147, + "step": 632 + }, + { + "epoch": 0.05, + "learning_rate": 1.996990562889219e-05, + "loss": 0.5195, + "step": 633 + }, + { + "epoch": 0.05, + "learning_rate": 1.996969116140846e-05, + "loss": 0.5337, + "step": 634 + }, + { + "epoch": 0.05, + "learning_rate": 1.9969475933594467e-05, + "loss": 0.5267, + "step": 635 + }, + { + "epoch": 0.05, + "learning_rate": 1.9969259945466612e-05, + "loss": 0.5206, + "step": 636 + }, + { + "epoch": 0.05, + "learning_rate": 1.9969043197041377e-05, + "loss": 0.5152, + "step": 637 + }, + { + "epoch": 0.05, + "learning_rate": 1.996882568833529e-05, + "loss": 0.5045, + "step": 638 + }, + { + "epoch": 0.05, + "learning_rate": 1.9968607419364934e-05, + "loss": 0.5332, + "step": 639 + }, + { + "epoch": 0.05, + "learning_rate": 1.996838839014696e-05, + "loss": 0.5153, + "step": 640 + }, + { + "epoch": 0.05, + "learning_rate": 1.996816860069807e-05, + "loss": 0.5203, + "step": 641 + }, + { + "epoch": 0.05, + "learning_rate": 1.9967948051035026e-05, + "loss": 0.5355, + "step": 642 + }, + { + "epoch": 0.05, + "learning_rate": 1.9967726741174652e-05, + "loss": 0.5086, + "step": 643 + }, + { + "epoch": 0.05, + "learning_rate": 1.996750467113382e-05, + "loss": 0.5235, + "step": 644 + }, + { + "epoch": 0.05, + "learning_rate": 1.9967281840929467e-05, + "loss": 0.5313, + "step": 645 + }, + { + "epoch": 0.06, + "learning_rate": 1.9967058250578593e-05, + "loss": 0.5264, + "step": 646 + }, + { + "epoch": 0.06, + "learning_rate": 1.996683390009824e-05, + "loss": 0.5376, + "step": 647 + }, + { + "epoch": 0.06, + "learning_rate": 1.9966608789505527e-05, + "loss": 0.5145, + "step": 648 + }, + { + "epoch": 0.06, + "learning_rate": 1.996638291881762e-05, + "loss": 0.5169, + "step": 649 + }, + { + "epoch": 0.06, + "learning_rate": 1.9966156288051743e-05, + "loss": 0.5023, + "step": 650 + }, + { + "epoch": 0.06, + "learning_rate": 1.9965928897225177e-05, + "loss": 0.516, + "step": 651 + }, + { + "epoch": 0.06, + "learning_rate": 1.996570074635527e-05, + "loss": 0.5123, + "step": 652 + }, + { + "epoch": 0.06, + "learning_rate": 1.9965471835459416e-05, + "loss": 0.5384, + "step": 653 + }, + { + "epoch": 0.06, + "learning_rate": 1.9965242164555074e-05, + "loss": 0.5165, + "step": 654 + }, + { + "epoch": 0.06, + "learning_rate": 1.9965011733659762e-05, + "loss": 0.5071, + "step": 655 + }, + { + "epoch": 0.06, + "learning_rate": 1.9964780542791057e-05, + "loss": 0.5199, + "step": 656 + }, + { + "epoch": 0.06, + "learning_rate": 1.9964548591966583e-05, + "loss": 0.5239, + "step": 657 + }, + { + "epoch": 0.06, + "learning_rate": 1.996431588120403e-05, + "loss": 0.5081, + "step": 658 + }, + { + "epoch": 0.06, + "learning_rate": 1.996408241052115e-05, + "loss": 0.5183, + "step": 659 + }, + { + "epoch": 0.06, + "learning_rate": 1.996384817993575e-05, + "loss": 0.5179, + "step": 660 + }, + { + "epoch": 0.06, + "learning_rate": 1.9963613189465684e-05, + "loss": 0.5184, + "step": 661 + }, + { + "epoch": 0.06, + "learning_rate": 1.9963377439128883e-05, + "loss": 0.5093, + "step": 662 + }, + { + "epoch": 0.06, + "learning_rate": 1.996314092894332e-05, + "loss": 0.5273, + "step": 663 + }, + { + "epoch": 0.06, + "learning_rate": 1.9962903658927038e-05, + "loss": 0.5418, + "step": 664 + }, + { + "epoch": 0.06, + "learning_rate": 1.9962665629098128e-05, + "loss": 0.5089, + "step": 665 + }, + { + "epoch": 0.06, + "learning_rate": 1.9962426839474745e-05, + "loss": 0.5326, + "step": 666 + }, + { + "epoch": 0.06, + "learning_rate": 1.9962187290075097e-05, + "loss": 0.5149, + "step": 667 + }, + { + "epoch": 0.06, + "learning_rate": 1.9961946980917457e-05, + "loss": 0.5195, + "step": 668 + }, + { + "epoch": 0.06, + "learning_rate": 1.996170591202015e-05, + "loss": 0.5094, + "step": 669 + }, + { + "epoch": 0.06, + "learning_rate": 1.996146408340156e-05, + "loss": 0.5225, + "step": 670 + }, + { + "epoch": 0.06, + "learning_rate": 1.9961221495080135e-05, + "loss": 0.5159, + "step": 671 + }, + { + "epoch": 0.06, + "learning_rate": 1.9960978147074367e-05, + "loss": 0.5114, + "step": 672 + }, + { + "epoch": 0.06, + "learning_rate": 1.9960734039402824e-05, + "loss": 0.5342, + "step": 673 + }, + { + "epoch": 0.06, + "learning_rate": 1.9960489172084118e-05, + "loss": 0.5107, + "step": 674 + }, + { + "epoch": 0.06, + "learning_rate": 1.996024354513692e-05, + "loss": 0.5176, + "step": 675 + }, + { + "epoch": 0.06, + "learning_rate": 1.995999715857997e-05, + "loss": 0.5155, + "step": 676 + }, + { + "epoch": 0.06, + "learning_rate": 1.9959750012432053e-05, + "loss": 0.5296, + "step": 677 + }, + { + "epoch": 0.06, + "learning_rate": 1.9959502106712023e-05, + "loss": 0.5137, + "step": 678 + }, + { + "epoch": 0.06, + "learning_rate": 1.9959253441438778e-05, + "loss": 0.517, + "step": 679 + }, + { + "epoch": 0.06, + "learning_rate": 1.995900401663129e-05, + "loss": 0.5267, + "step": 680 + }, + { + "epoch": 0.06, + "learning_rate": 1.9958753832308575e-05, + "loss": 0.5097, + "step": 681 + }, + { + "epoch": 0.06, + "learning_rate": 1.995850288848972e-05, + "loss": 0.5279, + "step": 682 + }, + { + "epoch": 0.06, + "learning_rate": 1.9958251185193855e-05, + "loss": 0.5174, + "step": 683 + }, + { + "epoch": 0.06, + "learning_rate": 1.9957998722440183e-05, + "loss": 0.5169, + "step": 684 + }, + { + "epoch": 0.06, + "learning_rate": 1.9957745500247955e-05, + "loss": 0.5142, + "step": 685 + }, + { + "epoch": 0.06, + "learning_rate": 1.995749151863648e-05, + "loss": 0.5225, + "step": 686 + }, + { + "epoch": 0.06, + "learning_rate": 1.9957236777625134e-05, + "loss": 0.5233, + "step": 687 + }, + { + "epoch": 0.06, + "learning_rate": 1.9956981277233342e-05, + "loss": 0.5147, + "step": 688 + }, + { + "epoch": 0.06, + "learning_rate": 1.9956725017480585e-05, + "loss": 0.515, + "step": 689 + }, + { + "epoch": 0.06, + "learning_rate": 1.995646799838641e-05, + "loss": 0.5104, + "step": 690 + }, + { + "epoch": 0.06, + "learning_rate": 1.9956210219970422e-05, + "loss": 0.5172, + "step": 691 + }, + { + "epoch": 0.06, + "learning_rate": 1.9955951682252275e-05, + "loss": 0.5154, + "step": 692 + }, + { + "epoch": 0.06, + "learning_rate": 1.9955692385251687e-05, + "loss": 0.5117, + "step": 693 + }, + { + "epoch": 0.06, + "learning_rate": 1.9955432328988437e-05, + "loss": 0.5147, + "step": 694 + }, + { + "epoch": 0.06, + "learning_rate": 1.995517151348235e-05, + "loss": 0.5172, + "step": 695 + }, + { + "epoch": 0.06, + "learning_rate": 1.9954909938753326e-05, + "loss": 0.5162, + "step": 696 + }, + { + "epoch": 0.06, + "learning_rate": 1.9954647604821307e-05, + "loss": 0.5285, + "step": 697 + }, + { + "epoch": 0.06, + "learning_rate": 1.9954384511706305e-05, + "loss": 0.5088, + "step": 698 + }, + { + "epoch": 0.06, + "learning_rate": 1.995412065942838e-05, + "loss": 0.5185, + "step": 699 + }, + { + "epoch": 0.06, + "learning_rate": 1.9953856048007654e-05, + "loss": 0.5246, + "step": 700 + }, + { + "epoch": 0.06, + "learning_rate": 1.9953590677464314e-05, + "loss": 0.5075, + "step": 701 + }, + { + "epoch": 0.06, + "learning_rate": 1.9953324547818592e-05, + "loss": 0.5318, + "step": 702 + }, + { + "epoch": 0.06, + "learning_rate": 1.9953057659090783e-05, + "loss": 0.5232, + "step": 703 + }, + { + "epoch": 0.06, + "learning_rate": 1.9952790011301248e-05, + "loss": 0.5172, + "step": 704 + }, + { + "epoch": 0.06, + "learning_rate": 1.9952521604470396e-05, + "loss": 0.5188, + "step": 705 + }, + { + "epoch": 0.06, + "learning_rate": 1.9952252438618692e-05, + "loss": 0.514, + "step": 706 + }, + { + "epoch": 0.06, + "learning_rate": 1.995198251376667e-05, + "loss": 0.5086, + "step": 707 + }, + { + "epoch": 0.06, + "learning_rate": 1.9951711829934914e-05, + "loss": 0.5216, + "step": 708 + }, + { + "epoch": 0.06, + "learning_rate": 1.9951440387144065e-05, + "loss": 0.5227, + "step": 709 + }, + { + "epoch": 0.06, + "learning_rate": 1.9951168185414827e-05, + "loss": 0.5257, + "step": 710 + }, + { + "epoch": 0.06, + "learning_rate": 1.995089522476796e-05, + "loss": 0.5125, + "step": 711 + }, + { + "epoch": 0.06, + "learning_rate": 1.9950621505224276e-05, + "loss": 0.523, + "step": 712 + }, + { + "epoch": 0.06, + "learning_rate": 1.9950347026804655e-05, + "loss": 0.5088, + "step": 713 + }, + { + "epoch": 0.06, + "learning_rate": 1.9950071789530026e-05, + "loss": 0.5225, + "step": 714 + }, + { + "epoch": 0.06, + "learning_rate": 1.9949795793421386e-05, + "loss": 0.5142, + "step": 715 + }, + { + "epoch": 0.06, + "learning_rate": 1.994951903849978e-05, + "loss": 0.5172, + "step": 716 + }, + { + "epoch": 0.06, + "learning_rate": 1.994924152478631e-05, + "loss": 0.5279, + "step": 717 + }, + { + "epoch": 0.06, + "learning_rate": 1.9948963252302147e-05, + "loss": 0.5341, + "step": 718 + }, + { + "epoch": 0.06, + "learning_rate": 1.9948684221068512e-05, + "loss": 0.52, + "step": 719 + }, + { + "epoch": 0.06, + "learning_rate": 1.994840443110668e-05, + "loss": 0.509, + "step": 720 + }, + { + "epoch": 0.06, + "learning_rate": 1.9948123882437995e-05, + "loss": 0.5059, + "step": 721 + }, + { + "epoch": 0.06, + "learning_rate": 1.9947842575083852e-05, + "loss": 0.5256, + "step": 722 + }, + { + "epoch": 0.06, + "learning_rate": 1.99475605090657e-05, + "loss": 0.5409, + "step": 723 + }, + { + "epoch": 0.06, + "learning_rate": 1.9947277684405056e-05, + "loss": 0.5041, + "step": 724 + }, + { + "epoch": 0.06, + "learning_rate": 1.9946994101123483e-05, + "loss": 0.5233, + "step": 725 + }, + { + "epoch": 0.06, + "learning_rate": 1.994670975924262e-05, + "loss": 0.5258, + "step": 726 + }, + { + "epoch": 0.06, + "learning_rate": 1.9946424658784142e-05, + "loss": 0.5046, + "step": 727 + }, + { + "epoch": 0.06, + "learning_rate": 1.994613879976979e-05, + "loss": 0.525, + "step": 728 + }, + { + "epoch": 0.06, + "learning_rate": 1.994585218222137e-05, + "loss": 0.5399, + "step": 729 + }, + { + "epoch": 0.06, + "learning_rate": 1.9945564806160744e-05, + "loss": 0.5453, + "step": 730 + }, + { + "epoch": 0.06, + "learning_rate": 1.9945276671609823e-05, + "loss": 0.5086, + "step": 731 + }, + { + "epoch": 0.06, + "learning_rate": 1.9944987778590582e-05, + "loss": 0.5236, + "step": 732 + }, + { + "epoch": 0.06, + "learning_rate": 1.9944698127125053e-05, + "loss": 0.5115, + "step": 733 + }, + { + "epoch": 0.06, + "learning_rate": 1.9944407717235327e-05, + "loss": 0.5218, + "step": 734 + }, + { + "epoch": 0.06, + "learning_rate": 1.9944116548943552e-05, + "loss": 0.5261, + "step": 735 + }, + { + "epoch": 0.06, + "learning_rate": 1.9943824622271934e-05, + "loss": 0.5205, + "step": 736 + }, + { + "epoch": 0.06, + "learning_rate": 1.994353193724274e-05, + "loss": 0.5211, + "step": 737 + }, + { + "epoch": 0.06, + "learning_rate": 1.9943238493878284e-05, + "loss": 0.5267, + "step": 738 + }, + { + "epoch": 0.06, + "learning_rate": 1.9942944292200948e-05, + "loss": 0.5006, + "step": 739 + }, + { + "epoch": 0.06, + "learning_rate": 1.9942649332233168e-05, + "loss": 0.5045, + "step": 740 + }, + { + "epoch": 0.06, + "learning_rate": 1.994235361399744e-05, + "loss": 0.5197, + "step": 741 + }, + { + "epoch": 0.06, + "learning_rate": 1.9942057137516323e-05, + "loss": 0.5191, + "step": 742 + }, + { + "epoch": 0.06, + "learning_rate": 1.9941759902812422e-05, + "loss": 0.5105, + "step": 743 + }, + { + "epoch": 0.06, + "learning_rate": 1.9941461909908398e-05, + "loss": 0.5279, + "step": 744 + }, + { + "epoch": 0.06, + "learning_rate": 1.9941163158826992e-05, + "loss": 0.5014, + "step": 745 + }, + { + "epoch": 0.06, + "learning_rate": 1.9940863649590976e-05, + "loss": 0.5047, + "step": 746 + }, + { + "epoch": 0.06, + "learning_rate": 1.9940563382223196e-05, + "loss": 0.5231, + "step": 747 + }, + { + "epoch": 0.06, + "learning_rate": 1.9940262356746553e-05, + "loss": 0.5177, + "step": 748 + }, + { + "epoch": 0.06, + "learning_rate": 1.9939960573184007e-05, + "loss": 0.5326, + "step": 749 + }, + { + "epoch": 0.06, + "learning_rate": 1.9939658031558564e-05, + "loss": 0.5126, + "step": 750 + }, + { + "epoch": 0.06, + "learning_rate": 1.9939354731893304e-05, + "loss": 0.5214, + "step": 751 + }, + { + "epoch": 0.06, + "learning_rate": 1.9939050674211358e-05, + "loss": 0.531, + "step": 752 + }, + { + "epoch": 0.06, + "learning_rate": 1.993874585853591e-05, + "loss": 0.5296, + "step": 753 + }, + { + "epoch": 0.06, + "learning_rate": 1.9938440284890216e-05, + "loss": 0.5012, + "step": 754 + }, + { + "epoch": 0.06, + "learning_rate": 1.993813395329757e-05, + "loss": 0.5218, + "step": 755 + }, + { + "epoch": 0.06, + "learning_rate": 1.993782686378134e-05, + "loss": 0.5171, + "step": 756 + }, + { + "epoch": 0.06, + "learning_rate": 1.9937519016364943e-05, + "loss": 0.496, + "step": 757 + }, + { + "epoch": 0.06, + "learning_rate": 1.9937210411071856e-05, + "loss": 0.5207, + "step": 758 + }, + { + "epoch": 0.06, + "learning_rate": 1.9936901047925617e-05, + "loss": 0.4908, + "step": 759 + }, + { + "epoch": 0.06, + "learning_rate": 1.9936590926949822e-05, + "loss": 0.517, + "step": 760 + }, + { + "epoch": 0.06, + "learning_rate": 1.9936280048168117e-05, + "loss": 0.4964, + "step": 761 + }, + { + "epoch": 0.06, + "learning_rate": 1.9935968411604215e-05, + "loss": 0.5386, + "step": 762 + }, + { + "epoch": 0.07, + "learning_rate": 1.9935656017281877e-05, + "loss": 0.531, + "step": 763 + }, + { + "epoch": 0.07, + "learning_rate": 1.9935342865224935e-05, + "loss": 0.5259, + "step": 764 + }, + { + "epoch": 0.07, + "learning_rate": 1.9935028955457262e-05, + "loss": 0.5188, + "step": 765 + }, + { + "epoch": 0.07, + "learning_rate": 1.993471428800281e-05, + "loss": 0.527, + "step": 766 + }, + { + "epoch": 0.07, + "learning_rate": 1.9934398862885563e-05, + "loss": 0.5116, + "step": 767 + }, + { + "epoch": 0.07, + "learning_rate": 1.9934082680129588e-05, + "loss": 0.5169, + "step": 768 + }, + { + "epoch": 0.07, + "learning_rate": 1.9933765739758992e-05, + "loss": 0.5214, + "step": 769 + }, + { + "epoch": 0.07, + "learning_rate": 1.9933448041797948e-05, + "loss": 0.5024, + "step": 770 + }, + { + "epoch": 0.07, + "learning_rate": 1.993312958627069e-05, + "loss": 0.5314, + "step": 771 + }, + { + "epoch": 0.07, + "learning_rate": 1.9932810373201498e-05, + "loss": 0.512, + "step": 772 + }, + { + "epoch": 0.07, + "learning_rate": 1.9932490402614718e-05, + "loss": 0.522, + "step": 773 + }, + { + "epoch": 0.07, + "learning_rate": 1.9932169674534752e-05, + "loss": 0.5267, + "step": 774 + }, + { + "epoch": 0.07, + "learning_rate": 1.9931848188986063e-05, + "loss": 0.5178, + "step": 775 + }, + { + "epoch": 0.07, + "learning_rate": 1.9931525945993164e-05, + "loss": 0.5208, + "step": 776 + }, + { + "epoch": 0.07, + "learning_rate": 1.9931202945580635e-05, + "loss": 0.5206, + "step": 777 + }, + { + "epoch": 0.07, + "learning_rate": 1.9930879187773108e-05, + "loss": 0.5329, + "step": 778 + }, + { + "epoch": 0.07, + "learning_rate": 1.9930554672595276e-05, + "loss": 0.5281, + "step": 779 + }, + { + "epoch": 0.07, + "learning_rate": 1.9930229400071886e-05, + "loss": 0.5236, + "step": 780 + }, + { + "epoch": 0.07, + "learning_rate": 1.9929903370227742e-05, + "loss": 0.5122, + "step": 781 + }, + { + "epoch": 0.07, + "learning_rate": 1.9929576583087714e-05, + "loss": 0.5001, + "step": 782 + }, + { + "epoch": 0.07, + "learning_rate": 1.9929249038676713e-05, + "loss": 0.5368, + "step": 783 + }, + { + "epoch": 0.07, + "learning_rate": 1.9928920737019735e-05, + "loss": 0.5069, + "step": 784 + }, + { + "epoch": 0.07, + "learning_rate": 1.9928591678141807e-05, + "loss": 0.5173, + "step": 785 + }, + { + "epoch": 0.07, + "learning_rate": 1.9928261862068026e-05, + "loss": 0.5076, + "step": 786 + }, + { + "epoch": 0.07, + "learning_rate": 1.992793128882355e-05, + "loss": 0.5258, + "step": 787 + }, + { + "epoch": 0.07, + "learning_rate": 1.9927599958433585e-05, + "loss": 0.5248, + "step": 788 + }, + { + "epoch": 0.07, + "learning_rate": 1.9927267870923398e-05, + "loss": 0.5276, + "step": 789 + }, + { + "epoch": 0.07, + "learning_rate": 1.992693502631832e-05, + "loss": 0.5301, + "step": 790 + }, + { + "epoch": 0.07, + "learning_rate": 1.992660142464373e-05, + "loss": 0.5218, + "step": 791 + }, + { + "epoch": 0.07, + "learning_rate": 1.9926267065925075e-05, + "loss": 0.5263, + "step": 792 + }, + { + "epoch": 0.07, + "learning_rate": 1.9925931950187852e-05, + "loss": 0.5351, + "step": 793 + }, + { + "epoch": 0.07, + "learning_rate": 1.9925596077457623e-05, + "loss": 0.5293, + "step": 794 + }, + { + "epoch": 0.07, + "learning_rate": 1.9925259447759995e-05, + "loss": 0.5289, + "step": 795 + }, + { + "epoch": 0.07, + "learning_rate": 1.9924922061120644e-05, + "loss": 0.5162, + "step": 796 + }, + { + "epoch": 0.07, + "learning_rate": 1.9924583917565305e-05, + "loss": 0.5105, + "step": 797 + }, + { + "epoch": 0.07, + "learning_rate": 1.992424501711976e-05, + "loss": 0.5006, + "step": 798 + }, + { + "epoch": 0.07, + "learning_rate": 1.992390535980986e-05, + "loss": 0.5149, + "step": 799 + }, + { + "epoch": 0.07, + "learning_rate": 1.9923564945661506e-05, + "loss": 0.5183, + "step": 800 + }, + { + "epoch": 0.07, + "learning_rate": 1.9923223774700656e-05, + "loss": 0.5152, + "step": 801 + }, + { + "epoch": 0.07, + "learning_rate": 1.9922881846953333e-05, + "loss": 0.4956, + "step": 802 + }, + { + "epoch": 0.07, + "learning_rate": 1.9922539162445616e-05, + "loss": 0.5078, + "step": 803 + }, + { + "epoch": 0.07, + "learning_rate": 1.9922195721203638e-05, + "loss": 0.5344, + "step": 804 + }, + { + "epoch": 0.07, + "learning_rate": 1.992185152325359e-05, + "loss": 0.5006, + "step": 805 + }, + { + "epoch": 0.07, + "learning_rate": 1.9921506568621717e-05, + "loss": 0.5199, + "step": 806 + }, + { + "epoch": 0.07, + "learning_rate": 1.9921160857334337e-05, + "loss": 0.5235, + "step": 807 + }, + { + "epoch": 0.07, + "learning_rate": 1.992081438941781e-05, + "loss": 0.5145, + "step": 808 + }, + { + "epoch": 0.07, + "learning_rate": 1.9920467164898558e-05, + "loss": 0.5353, + "step": 809 + }, + { + "epoch": 0.07, + "learning_rate": 1.9920119183803064e-05, + "loss": 0.5082, + "step": 810 + }, + { + "epoch": 0.07, + "learning_rate": 1.9919770446157867e-05, + "loss": 0.5049, + "step": 811 + }, + { + "epoch": 0.07, + "learning_rate": 1.991942095198956e-05, + "loss": 0.5023, + "step": 812 + }, + { + "epoch": 0.07, + "learning_rate": 1.9919070701324803e-05, + "loss": 0.5214, + "step": 813 + }, + { + "epoch": 0.07, + "learning_rate": 1.99187196941903e-05, + "loss": 0.5158, + "step": 814 + }, + { + "epoch": 0.07, + "learning_rate": 1.9918367930612824e-05, + "loss": 0.5418, + "step": 815 + }, + { + "epoch": 0.07, + "learning_rate": 1.99180154106192e-05, + "loss": 0.5131, + "step": 816 + }, + { + "epoch": 0.07, + "learning_rate": 1.9917662134236318e-05, + "loss": 0.5084, + "step": 817 + }, + { + "epoch": 0.07, + "learning_rate": 1.9917308101491117e-05, + "loss": 0.5298, + "step": 818 + }, + { + "epoch": 0.07, + "learning_rate": 1.9916953312410593e-05, + "loss": 0.5194, + "step": 819 + }, + { + "epoch": 0.07, + "learning_rate": 1.991659776702181e-05, + "loss": 0.5171, + "step": 820 + }, + { + "epoch": 0.07, + "learning_rate": 1.9916241465351874e-05, + "loss": 0.5142, + "step": 821 + }, + { + "epoch": 0.07, + "learning_rate": 1.9915884407427974e-05, + "loss": 0.506, + "step": 822 + }, + { + "epoch": 0.07, + "learning_rate": 1.9915526593277327e-05, + "loss": 0.5324, + "step": 823 + }, + { + "epoch": 0.07, + "learning_rate": 1.9915168022927225e-05, + "loss": 0.5203, + "step": 824 + }, + { + "epoch": 0.07, + "learning_rate": 1.9914808696405017e-05, + "loss": 0.5265, + "step": 825 + }, + { + "epoch": 0.07, + "learning_rate": 1.9914448613738107e-05, + "loss": 0.5149, + "step": 826 + }, + { + "epoch": 0.07, + "learning_rate": 1.991408777495395e-05, + "loss": 0.5285, + "step": 827 + }, + { + "epoch": 0.07, + "learning_rate": 1.9913726180080072e-05, + "loss": 0.5169, + "step": 828 + }, + { + "epoch": 0.07, + "learning_rate": 1.9913363829144042e-05, + "loss": 0.5189, + "step": 829 + }, + { + "epoch": 0.07, + "learning_rate": 1.991300072217351e-05, + "loss": 0.5236, + "step": 830 + }, + { + "epoch": 0.07, + "learning_rate": 1.9912636859196145e-05, + "loss": 0.5167, + "step": 831 + }, + { + "epoch": 0.07, + "learning_rate": 1.9912272240239715e-05, + "loss": 0.5125, + "step": 832 + }, + { + "epoch": 0.07, + "learning_rate": 1.991190686533202e-05, + "loss": 0.5403, + "step": 833 + }, + { + "epoch": 0.07, + "learning_rate": 1.991154073450093e-05, + "loss": 0.5048, + "step": 834 + }, + { + "epoch": 0.07, + "learning_rate": 1.9911173847774365e-05, + "loss": 0.5121, + "step": 835 + }, + { + "epoch": 0.07, + "learning_rate": 1.9910806205180296e-05, + "loss": 0.5148, + "step": 836 + }, + { + "epoch": 0.07, + "learning_rate": 1.9910437806746776e-05, + "loss": 0.4887, + "step": 837 + }, + { + "epoch": 0.07, + "learning_rate": 1.9910068652501894e-05, + "loss": 0.5225, + "step": 838 + }, + { + "epoch": 0.07, + "learning_rate": 1.9909698742473802e-05, + "loss": 0.5013, + "step": 839 + }, + { + "epoch": 0.07, + "learning_rate": 1.990932807669071e-05, + "loss": 0.5091, + "step": 840 + }, + { + "epoch": 0.07, + "learning_rate": 1.9908956655180894e-05, + "loss": 0.5096, + "step": 841 + }, + { + "epoch": 0.07, + "learning_rate": 1.9908584477972666e-05, + "loss": 0.5263, + "step": 842 + }, + { + "epoch": 0.07, + "learning_rate": 1.9908211545094426e-05, + "loss": 0.5215, + "step": 843 + }, + { + "epoch": 0.07, + "learning_rate": 1.9907837856574608e-05, + "loss": 0.502, + "step": 844 + }, + { + "epoch": 0.07, + "learning_rate": 1.990746341244171e-05, + "loss": 0.526, + "step": 845 + }, + { + "epoch": 0.07, + "learning_rate": 1.990708821272429e-05, + "loss": 0.5016, + "step": 846 + }, + { + "epoch": 0.07, + "learning_rate": 1.9906712257450958e-05, + "loss": 0.5207, + "step": 847 + }, + { + "epoch": 0.07, + "learning_rate": 1.9906335546650394e-05, + "loss": 0.5097, + "step": 848 + }, + { + "epoch": 0.07, + "learning_rate": 1.990595808035132e-05, + "loss": 0.5322, + "step": 849 + }, + { + "epoch": 0.07, + "learning_rate": 1.990557985858253e-05, + "loss": 0.5107, + "step": 850 + }, + { + "epoch": 0.07, + "learning_rate": 1.9905200881372866e-05, + "loss": 0.5144, + "step": 851 + }, + { + "epoch": 0.07, + "learning_rate": 1.990482114875123e-05, + "loss": 0.5182, + "step": 852 + }, + { + "epoch": 0.07, + "learning_rate": 1.990444066074658e-05, + "loss": 0.5274, + "step": 853 + }, + { + "epoch": 0.07, + "learning_rate": 1.9904059417387932e-05, + "loss": 0.5003, + "step": 854 + }, + { + "epoch": 0.07, + "learning_rate": 1.990367741870437e-05, + "loss": 0.524, + "step": 855 + }, + { + "epoch": 0.07, + "learning_rate": 1.9903294664725023e-05, + "loss": 0.5406, + "step": 856 + }, + { + "epoch": 0.07, + "learning_rate": 1.9902911155479073e-05, + "loss": 0.5282, + "step": 857 + }, + { + "epoch": 0.07, + "learning_rate": 1.990252689099578e-05, + "loss": 0.5354, + "step": 858 + }, + { + "epoch": 0.07, + "learning_rate": 1.9902141871304442e-05, + "loss": 0.5418, + "step": 859 + }, + { + "epoch": 0.07, + "learning_rate": 1.9901756096434426e-05, + "loss": 0.5113, + "step": 860 + }, + { + "epoch": 0.07, + "learning_rate": 1.990136956641515e-05, + "loss": 0.5216, + "step": 861 + }, + { + "epoch": 0.07, + "learning_rate": 1.9900982281276096e-05, + "loss": 0.5289, + "step": 862 + }, + { + "epoch": 0.07, + "learning_rate": 1.9900594241046797e-05, + "loss": 0.5142, + "step": 863 + }, + { + "epoch": 0.07, + "learning_rate": 1.9900205445756845e-05, + "loss": 0.5077, + "step": 864 + }, + { + "epoch": 0.07, + "learning_rate": 1.98998158954359e-05, + "loss": 0.5306, + "step": 865 + }, + { + "epoch": 0.07, + "learning_rate": 1.9899425590113658e-05, + "loss": 0.5119, + "step": 866 + }, + { + "epoch": 0.07, + "learning_rate": 1.9899034529819895e-05, + "loss": 0.5115, + "step": 867 + }, + { + "epoch": 0.07, + "learning_rate": 1.989864271458443e-05, + "loss": 0.5074, + "step": 868 + }, + { + "epoch": 0.07, + "learning_rate": 1.9898250144437145e-05, + "loss": 0.5066, + "step": 869 + }, + { + "epoch": 0.07, + "learning_rate": 1.9897856819407982e-05, + "loss": 0.5316, + "step": 870 + }, + { + "epoch": 0.07, + "learning_rate": 1.9897462739526936e-05, + "loss": 0.5247, + "step": 871 + }, + { + "epoch": 0.07, + "learning_rate": 1.989706790482406e-05, + "loss": 0.5076, + "step": 872 + }, + { + "epoch": 0.07, + "learning_rate": 1.9896672315329467e-05, + "loss": 0.5192, + "step": 873 + }, + { + "epoch": 0.07, + "learning_rate": 1.9896275971073326e-05, + "loss": 0.5259, + "step": 874 + }, + { + "epoch": 0.07, + "learning_rate": 1.989587887208586e-05, + "loss": 0.5208, + "step": 875 + }, + { + "epoch": 0.07, + "learning_rate": 1.989548101839736e-05, + "loss": 0.504, + "step": 876 + }, + { + "epoch": 0.07, + "learning_rate": 1.9895082410038166e-05, + "loss": 0.5055, + "step": 877 + }, + { + "epoch": 0.07, + "learning_rate": 1.9894683047038675e-05, + "loss": 0.5184, + "step": 878 + }, + { + "epoch": 0.07, + "learning_rate": 1.989428292942935e-05, + "loss": 0.5179, + "step": 879 + }, + { + "epoch": 0.08, + "learning_rate": 1.9893882057240698e-05, + "loss": 0.528, + "step": 880 + }, + { + "epoch": 0.08, + "learning_rate": 1.9893480430503293e-05, + "loss": 0.521, + "step": 881 + }, + { + "epoch": 0.08, + "learning_rate": 1.989307804924777e-05, + "loss": 0.5243, + "step": 882 + }, + { + "epoch": 0.08, + "learning_rate": 1.989267491350481e-05, + "loss": 0.5042, + "step": 883 + }, + { + "epoch": 0.08, + "learning_rate": 1.989227102330516e-05, + "loss": 0.5142, + "step": 884 + }, + { + "epoch": 0.08, + "learning_rate": 1.9891866378679624e-05, + "loss": 0.518, + "step": 885 + }, + { + "epoch": 0.08, + "learning_rate": 1.989146097965906e-05, + "loss": 0.5141, + "step": 886 + }, + { + "epoch": 0.08, + "learning_rate": 1.989105482627439e-05, + "loss": 0.5215, + "step": 887 + }, + { + "epoch": 0.08, + "learning_rate": 1.989064791855658e-05, + "loss": 0.5159, + "step": 888 + }, + { + "epoch": 0.08, + "learning_rate": 1.989024025653667e-05, + "loss": 0.5265, + "step": 889 + }, + { + "epoch": 0.08, + "learning_rate": 1.9889831840245745e-05, + "loss": 0.5158, + "step": 890 + }, + { + "epoch": 0.08, + "learning_rate": 1.9889422669714958e-05, + "loss": 0.5201, + "step": 891 + }, + { + "epoch": 0.08, + "learning_rate": 1.9889012744975508e-05, + "loss": 0.5173, + "step": 892 + }, + { + "epoch": 0.08, + "learning_rate": 1.9888602066058663e-05, + "loss": 0.5167, + "step": 893 + }, + { + "epoch": 0.08, + "learning_rate": 1.988819063299574e-05, + "loss": 0.5189, + "step": 894 + }, + { + "epoch": 0.08, + "learning_rate": 1.988777844581812e-05, + "loss": 0.5376, + "step": 895 + }, + { + "epoch": 0.08, + "learning_rate": 1.988736550455723e-05, + "loss": 0.5304, + "step": 896 + }, + { + "epoch": 0.08, + "learning_rate": 1.9886951809244575e-05, + "loss": 0.5293, + "step": 897 + }, + { + "epoch": 0.08, + "learning_rate": 1.9886537359911694e-05, + "loss": 0.5298, + "step": 898 + }, + { + "epoch": 0.08, + "learning_rate": 1.98861221565902e-05, + "loss": 0.5142, + "step": 899 + }, + { + "epoch": 0.08, + "learning_rate": 1.9885706199311757e-05, + "loss": 0.5054, + "step": 900 + }, + { + "epoch": 0.08, + "learning_rate": 1.9885289488108086e-05, + "loss": 0.5035, + "step": 901 + }, + { + "epoch": 0.08, + "learning_rate": 1.988487202301097e-05, + "loss": 0.5316, + "step": 902 + }, + { + "epoch": 0.08, + "learning_rate": 1.9884453804052246e-05, + "loss": 0.5109, + "step": 903 + }, + { + "epoch": 0.08, + "learning_rate": 1.9884034831263807e-05, + "loss": 0.519, + "step": 904 + }, + { + "epoch": 0.08, + "learning_rate": 1.988361510467761e-05, + "loss": 0.5004, + "step": 905 + }, + { + "epoch": 0.08, + "learning_rate": 1.9883194624325658e-05, + "loss": 0.5246, + "step": 906 + }, + { + "epoch": 0.08, + "learning_rate": 1.9882773390240027e-05, + "loss": 0.504, + "step": 907 + }, + { + "epoch": 0.08, + "learning_rate": 1.9882351402452835e-05, + "loss": 0.5029, + "step": 908 + }, + { + "epoch": 0.08, + "learning_rate": 1.988192866099627e-05, + "loss": 0.5198, + "step": 909 + }, + { + "epoch": 0.08, + "learning_rate": 1.9881505165902566e-05, + "loss": 0.5318, + "step": 910 + }, + { + "epoch": 0.08, + "learning_rate": 1.9881080917204027e-05, + "loss": 0.5293, + "step": 911 + }, + { + "epoch": 0.08, + "learning_rate": 1.9880655914933003e-05, + "loss": 0.5033, + "step": 912 + }, + { + "epoch": 0.08, + "learning_rate": 1.988023015912191e-05, + "loss": 0.51, + "step": 913 + }, + { + "epoch": 0.08, + "learning_rate": 1.9879803649803217e-05, + "loss": 0.5355, + "step": 914 + }, + { + "epoch": 0.08, + "learning_rate": 1.9879376387009448e-05, + "loss": 0.494, + "step": 915 + }, + { + "epoch": 0.08, + "learning_rate": 1.9878948370773194e-05, + "loss": 0.5393, + "step": 916 + }, + { + "epoch": 0.08, + "learning_rate": 1.987851960112709e-05, + "loss": 0.5151, + "step": 917 + }, + { + "epoch": 0.08, + "learning_rate": 1.9878090078103846e-05, + "loss": 0.4995, + "step": 918 + }, + { + "epoch": 0.08, + "learning_rate": 1.9877659801736206e-05, + "loss": 0.528, + "step": 919 + }, + { + "epoch": 0.08, + "learning_rate": 1.9877228772056992e-05, + "loss": 0.5276, + "step": 920 + }, + { + "epoch": 0.08, + "learning_rate": 1.987679698909908e-05, + "loss": 0.5271, + "step": 921 + }, + { + "epoch": 0.08, + "learning_rate": 1.9876364452895394e-05, + "loss": 0.5033, + "step": 922 + }, + { + "epoch": 0.08, + "learning_rate": 1.987593116347892e-05, + "loss": 0.5267, + "step": 923 + }, + { + "epoch": 0.08, + "learning_rate": 1.9875497120882706e-05, + "loss": 0.523, + "step": 924 + }, + { + "epoch": 0.08, + "learning_rate": 1.9875062325139853e-05, + "loss": 0.5119, + "step": 925 + }, + { + "epoch": 0.08, + "learning_rate": 1.987462677628352e-05, + "loss": 0.5168, + "step": 926 + }, + { + "epoch": 0.08, + "learning_rate": 1.987419047434692e-05, + "loss": 0.5238, + "step": 927 + }, + { + "epoch": 0.08, + "learning_rate": 1.9873753419363336e-05, + "loss": 0.512, + "step": 928 + }, + { + "epoch": 0.08, + "learning_rate": 1.987331561136609e-05, + "loss": 0.5383, + "step": 929 + }, + { + "epoch": 0.08, + "learning_rate": 1.987287705038858e-05, + "loss": 0.5264, + "step": 930 + }, + { + "epoch": 0.08, + "learning_rate": 1.987243773646425e-05, + "loss": 0.5008, + "step": 931 + }, + { + "epoch": 0.08, + "learning_rate": 1.9871997669626596e-05, + "loss": 0.5127, + "step": 932 + }, + { + "epoch": 0.08, + "learning_rate": 1.9871556849909187e-05, + "loss": 0.5241, + "step": 933 + }, + { + "epoch": 0.08, + "learning_rate": 1.987111527734564e-05, + "loss": 0.5092, + "step": 934 + }, + { + "epoch": 0.08, + "learning_rate": 1.9870672951969632e-05, + "loss": 0.5229, + "step": 935 + }, + { + "epoch": 0.08, + "learning_rate": 1.9870229873814897e-05, + "loss": 0.5242, + "step": 936 + }, + { + "epoch": 0.08, + "learning_rate": 1.9869786042915225e-05, + "loss": 0.5134, + "step": 937 + }, + { + "epoch": 0.08, + "learning_rate": 1.9869341459304465e-05, + "loss": 0.5064, + "step": 938 + }, + { + "epoch": 0.08, + "learning_rate": 1.9868896123016517e-05, + "loss": 0.5173, + "step": 939 + }, + { + "epoch": 0.08, + "learning_rate": 1.9868450034085352e-05, + "loss": 0.4949, + "step": 940 + }, + { + "epoch": 0.08, + "learning_rate": 1.986800319254499e-05, + "loss": 0.5017, + "step": 941 + }, + { + "epoch": 0.08, + "learning_rate": 1.9867555598429505e-05, + "loss": 0.5093, + "step": 942 + }, + { + "epoch": 0.08, + "learning_rate": 1.9867107251773033e-05, + "loss": 0.5155, + "step": 943 + }, + { + "epoch": 0.08, + "learning_rate": 1.986665815260977e-05, + "loss": 0.511, + "step": 944 + }, + { + "epoch": 0.08, + "learning_rate": 1.9866208300973962e-05, + "loss": 0.5229, + "step": 945 + }, + { + "epoch": 0.08, + "learning_rate": 1.986575769689992e-05, + "loss": 0.5333, + "step": 946 + }, + { + "epoch": 0.08, + "learning_rate": 1.986530634042201e-05, + "loss": 0.5258, + "step": 947 + }, + { + "epoch": 0.08, + "learning_rate": 1.986485423157465e-05, + "loss": 0.5012, + "step": 948 + }, + { + "epoch": 0.08, + "learning_rate": 1.986440137039232e-05, + "loss": 0.5095, + "step": 949 + }, + { + "epoch": 0.08, + "learning_rate": 1.9863947756909563e-05, + "loss": 0.5248, + "step": 950 + }, + { + "epoch": 0.08, + "learning_rate": 1.986349339116097e-05, + "loss": 0.4988, + "step": 951 + }, + { + "epoch": 0.08, + "learning_rate": 1.9863038273181187e-05, + "loss": 0.5289, + "step": 952 + }, + { + "epoch": 0.08, + "learning_rate": 1.986258240300493e-05, + "loss": 0.534, + "step": 953 + }, + { + "epoch": 0.08, + "learning_rate": 1.9862125780666966e-05, + "loss": 0.4971, + "step": 954 + }, + { + "epoch": 0.08, + "learning_rate": 1.9861668406202116e-05, + "loss": 0.534, + "step": 955 + }, + { + "epoch": 0.08, + "learning_rate": 1.986121027964526e-05, + "loss": 0.5077, + "step": 956 + }, + { + "epoch": 0.08, + "learning_rate": 1.986075140103134e-05, + "loss": 0.5238, + "step": 957 + }, + { + "epoch": 0.08, + "learning_rate": 1.986029177039535e-05, + "loss": 0.5233, + "step": 958 + }, + { + "epoch": 0.08, + "learning_rate": 1.9859831387772345e-05, + "loss": 0.5189, + "step": 959 + }, + { + "epoch": 0.08, + "learning_rate": 1.9859370253197436e-05, + "loss": 0.5223, + "step": 960 + }, + { + "epoch": 0.08, + "learning_rate": 1.985890836670579e-05, + "loss": 0.4904, + "step": 961 + }, + { + "epoch": 0.08, + "learning_rate": 1.985844572833263e-05, + "loss": 0.5242, + "step": 962 + }, + { + "epoch": 0.08, + "learning_rate": 1.985798233811324e-05, + "loss": 0.5242, + "step": 963 + }, + { + "epoch": 0.08, + "learning_rate": 1.9857518196082964e-05, + "loss": 0.5254, + "step": 964 + }, + { + "epoch": 0.08, + "learning_rate": 1.9857053302277197e-05, + "loss": 0.5, + "step": 965 + }, + { + "epoch": 0.08, + "learning_rate": 1.9856587656731393e-05, + "loss": 0.5088, + "step": 966 + }, + { + "epoch": 0.08, + "learning_rate": 1.985612125948106e-05, + "loss": 0.5031, + "step": 967 + }, + { + "epoch": 0.08, + "learning_rate": 1.9855654110561775e-05, + "loss": 0.5181, + "step": 968 + }, + { + "epoch": 0.08, + "learning_rate": 1.9855186210009162e-05, + "loss": 0.5075, + "step": 969 + }, + { + "epoch": 0.08, + "learning_rate": 1.9854717557858906e-05, + "loss": 0.4901, + "step": 970 + }, + { + "epoch": 0.08, + "learning_rate": 1.9854248154146744e-05, + "loss": 0.5007, + "step": 971 + }, + { + "epoch": 0.08, + "learning_rate": 1.9853777998908475e-05, + "loss": 0.5079, + "step": 972 + }, + { + "epoch": 0.08, + "learning_rate": 1.9853307092179964e-05, + "loss": 0.512, + "step": 973 + }, + { + "epoch": 0.08, + "learning_rate": 1.985283543399711e-05, + "loss": 0.4978, + "step": 974 + }, + { + "epoch": 0.08, + "learning_rate": 1.9852363024395896e-05, + "loss": 0.514, + "step": 975 + }, + { + "epoch": 0.08, + "learning_rate": 1.9851889863412347e-05, + "loss": 0.5064, + "step": 976 + }, + { + "epoch": 0.08, + "learning_rate": 1.9851415951082544e-05, + "loss": 0.5073, + "step": 977 + }, + { + "epoch": 0.08, + "learning_rate": 1.9850941287442635e-05, + "loss": 0.5289, + "step": 978 + }, + { + "epoch": 0.08, + "learning_rate": 1.9850465872528812e-05, + "loss": 0.5027, + "step": 979 + }, + { + "epoch": 0.08, + "learning_rate": 1.984998970637734e-05, + "loss": 0.4954, + "step": 980 + }, + { + "epoch": 0.08, + "learning_rate": 1.9849512789024533e-05, + "loss": 0.5339, + "step": 981 + }, + { + "epoch": 0.08, + "learning_rate": 1.9849035120506756e-05, + "loss": 0.512, + "step": 982 + }, + { + "epoch": 0.08, + "learning_rate": 1.9848556700860446e-05, + "loss": 0.4935, + "step": 983 + }, + { + "epoch": 0.08, + "learning_rate": 1.9848077530122083e-05, + "loss": 0.5036, + "step": 984 + }, + { + "epoch": 0.08, + "learning_rate": 1.9847597608328212e-05, + "loss": 0.5259, + "step": 985 + }, + { + "epoch": 0.08, + "learning_rate": 1.9847116935515438e-05, + "loss": 0.5315, + "step": 986 + }, + { + "epoch": 0.08, + "learning_rate": 1.9846635511720413e-05, + "loss": 0.5134, + "step": 987 + }, + { + "epoch": 0.08, + "learning_rate": 1.9846153336979855e-05, + "loss": 0.5228, + "step": 988 + }, + { + "epoch": 0.08, + "learning_rate": 1.9845670411330543e-05, + "loss": 0.5135, + "step": 989 + }, + { + "epoch": 0.08, + "learning_rate": 1.9845186734809294e-05, + "loss": 0.5249, + "step": 990 + }, + { + "epoch": 0.08, + "learning_rate": 1.984470230745301e-05, + "loss": 0.5229, + "step": 991 + }, + { + "epoch": 0.08, + "learning_rate": 1.9844217129298616e-05, + "loss": 0.5244, + "step": 992 + }, + { + "epoch": 0.08, + "learning_rate": 1.9843731200383132e-05, + "loss": 0.4955, + "step": 993 + }, + { + "epoch": 0.08, + "learning_rate": 1.984324452074361e-05, + "loss": 0.5196, + "step": 994 + }, + { + "epoch": 0.08, + "learning_rate": 1.984275709041717e-05, + "loss": 0.5101, + "step": 995 + }, + { + "epoch": 0.08, + "learning_rate": 1.9842268909440977e-05, + "loss": 0.5101, + "step": 996 + }, + { + "epoch": 0.09, + "learning_rate": 1.9841779977852273e-05, + "loss": 0.5318, + "step": 997 + }, + { + "epoch": 0.09, + "learning_rate": 1.9841290295688335e-05, + "loss": 0.5031, + "step": 998 + }, + { + "epoch": 0.09, + "learning_rate": 1.9840799862986513e-05, + "loss": 0.4967, + "step": 999 + }, + { + "epoch": 0.09, + "learning_rate": 1.9840308679784207e-05, + "loss": 0.5151, + "step": 1000 + }, + { + "epoch": 0.09, + "learning_rate": 1.983981674611888e-05, + "loss": 0.5077, + "step": 1001 + }, + { + "epoch": 0.09, + "learning_rate": 1.983932406202805e-05, + "loss": 0.5123, + "step": 1002 + }, + { + "epoch": 0.09, + "learning_rate": 1.983883062754929e-05, + "loss": 0.5163, + "step": 1003 + }, + { + "epoch": 0.09, + "learning_rate": 1.983833644272023e-05, + "loss": 0.5279, + "step": 1004 + }, + { + "epoch": 0.09, + "learning_rate": 1.9837841507578558e-05, + "loss": 0.5259, + "step": 1005 + }, + { + "epoch": 0.09, + "learning_rate": 1.983734582216202e-05, + "loss": 0.4907, + "step": 1006 + }, + { + "epoch": 0.09, + "learning_rate": 1.9836849386508422e-05, + "loss": 0.5146, + "step": 1007 + }, + { + "epoch": 0.09, + "learning_rate": 1.983635220065562e-05, + "loss": 0.5151, + "step": 1008 + }, + { + "epoch": 0.09, + "learning_rate": 1.9835854264641538e-05, + "loss": 0.4935, + "step": 1009 + }, + { + "epoch": 0.09, + "learning_rate": 1.9835355578504143e-05, + "loss": 0.5231, + "step": 1010 + }, + { + "epoch": 0.09, + "learning_rate": 1.983485614228147e-05, + "loss": 0.5169, + "step": 1011 + }, + { + "epoch": 0.09, + "learning_rate": 1.9834355956011604e-05, + "loss": 0.4986, + "step": 1012 + }, + { + "epoch": 0.09, + "learning_rate": 1.9833855019732703e-05, + "loss": 0.5301, + "step": 1013 + }, + { + "epoch": 0.09, + "learning_rate": 1.983335333348296e-05, + "loss": 0.5129, + "step": 1014 + }, + { + "epoch": 0.09, + "learning_rate": 1.983285089730064e-05, + "loss": 0.5111, + "step": 1015 + }, + { + "epoch": 0.09, + "learning_rate": 1.9832347711224057e-05, + "loss": 0.492, + "step": 1016 + }, + { + "epoch": 0.09, + "learning_rate": 1.9831843775291594e-05, + "loss": 0.5054, + "step": 1017 + }, + { + "epoch": 0.09, + "learning_rate": 1.9831339089541673e-05, + "loss": 0.5046, + "step": 1018 + }, + { + "epoch": 0.09, + "learning_rate": 1.983083365401279e-05, + "loss": 0.5203, + "step": 1019 + }, + { + "epoch": 0.09, + "learning_rate": 1.983032746874349e-05, + "loss": 0.5157, + "step": 1020 + }, + { + "epoch": 0.09, + "learning_rate": 1.9829820533772376e-05, + "loss": 0.5186, + "step": 1021 + }, + { + "epoch": 0.09, + "learning_rate": 1.982931284913811e-05, + "loss": 0.5362, + "step": 1022 + }, + { + "epoch": 0.09, + "learning_rate": 1.982880441487941e-05, + "loss": 0.5075, + "step": 1023 + }, + { + "epoch": 0.09, + "learning_rate": 1.9828295231035054e-05, + "loss": 0.52, + "step": 1024 + }, + { + "epoch": 0.09, + "learning_rate": 1.982778529764387e-05, + "loss": 0.4912, + "step": 1025 + }, + { + "epoch": 0.09, + "learning_rate": 1.9827274614744747e-05, + "loss": 0.5365, + "step": 1026 + }, + { + "epoch": 0.09, + "learning_rate": 1.9826763182376636e-05, + "loss": 0.5306, + "step": 1027 + }, + { + "epoch": 0.09, + "learning_rate": 1.982625100057854e-05, + "loss": 0.5137, + "step": 1028 + }, + { + "epoch": 0.09, + "learning_rate": 1.9825738069389518e-05, + "loss": 0.5236, + "step": 1029 + }, + { + "epoch": 0.09, + "learning_rate": 1.9825224388848693e-05, + "loss": 0.5296, + "step": 1030 + }, + { + "epoch": 0.09, + "learning_rate": 1.982470995899523e-05, + "loss": 0.5291, + "step": 1031 + }, + { + "epoch": 0.09, + "learning_rate": 1.9824194779868377e-05, + "loss": 0.5146, + "step": 1032 + }, + { + "epoch": 0.09, + "learning_rate": 1.982367885150741e-05, + "loss": 0.515, + "step": 1033 + }, + { + "epoch": 0.09, + "learning_rate": 1.9823162173951683e-05, + "loss": 0.5439, + "step": 1034 + }, + { + "epoch": 0.09, + "learning_rate": 1.9822644747240597e-05, + "loss": 0.5, + "step": 1035 + }, + { + "epoch": 0.09, + "learning_rate": 1.9822126571413616e-05, + "loss": 0.5356, + "step": 1036 + }, + { + "epoch": 0.09, + "learning_rate": 1.9821607646510256e-05, + "loss": 0.4945, + "step": 1037 + }, + { + "epoch": 0.09, + "learning_rate": 1.982108797257009e-05, + "loss": 0.517, + "step": 1038 + }, + { + "epoch": 0.09, + "learning_rate": 1.9820567549632755e-05, + "loss": 0.5001, + "step": 1039 + }, + { + "epoch": 0.09, + "learning_rate": 1.9820046377737944e-05, + "loss": 0.5218, + "step": 1040 + }, + { + "epoch": 0.09, + "learning_rate": 1.9819524456925392e-05, + "loss": 0.516, + "step": 1041 + }, + { + "epoch": 0.09, + "learning_rate": 1.9819001787234912e-05, + "loss": 0.4994, + "step": 1042 + }, + { + "epoch": 0.09, + "learning_rate": 1.981847836870636e-05, + "loss": 0.5268, + "step": 1043 + }, + { + "epoch": 0.09, + "learning_rate": 1.9817954201379664e-05, + "loss": 0.5009, + "step": 1044 + }, + { + "epoch": 0.09, + "learning_rate": 1.9817429285294785e-05, + "loss": 0.5122, + "step": 1045 + }, + { + "epoch": 0.09, + "learning_rate": 1.9816903620491764e-05, + "loss": 0.5085, + "step": 1046 + }, + { + "epoch": 0.09, + "learning_rate": 1.981637720701069e-05, + "loss": 0.5147, + "step": 1047 + }, + { + "epoch": 0.09, + "learning_rate": 1.981585004489171e-05, + "loss": 0.4996, + "step": 1048 + }, + { + "epoch": 0.09, + "learning_rate": 1.981532213417502e-05, + "loss": 0.5244, + "step": 1049 + }, + { + "epoch": 0.09, + "learning_rate": 1.981479347490089e-05, + "loss": 0.5133, + "step": 1050 + }, + { + "epoch": 0.09, + "learning_rate": 1.9814264067109634e-05, + "loss": 0.4958, + "step": 1051 + }, + { + "epoch": 0.09, + "learning_rate": 1.9813733910841626e-05, + "loss": 0.492, + "step": 1052 + }, + { + "epoch": 0.09, + "learning_rate": 1.98132030061373e-05, + "loss": 0.5405, + "step": 1053 + }, + { + "epoch": 0.09, + "learning_rate": 1.981267135303714e-05, + "loss": 0.5359, + "step": 1054 + }, + { + "epoch": 0.09, + "learning_rate": 1.98121389515817e-05, + "loss": 0.4791, + "step": 1055 + }, + { + "epoch": 0.09, + "learning_rate": 1.9811605801811578e-05, + "loss": 0.5129, + "step": 1056 + }, + { + "epoch": 0.09, + "learning_rate": 1.9811071903767436e-05, + "loss": 0.5006, + "step": 1057 + }, + { + "epoch": 0.09, + "learning_rate": 1.9810537257489987e-05, + "loss": 0.5217, + "step": 1058 + }, + { + "epoch": 0.09, + "learning_rate": 1.9810001863020014e-05, + "loss": 0.5282, + "step": 1059 + }, + { + "epoch": 0.09, + "learning_rate": 1.980946572039834e-05, + "loss": 0.5196, + "step": 1060 + }, + { + "epoch": 0.09, + "learning_rate": 1.9808928829665857e-05, + "loss": 0.5017, + "step": 1061 + }, + { + "epoch": 0.09, + "learning_rate": 1.9808391190863513e-05, + "loss": 0.511, + "step": 1062 + }, + { + "epoch": 0.09, + "learning_rate": 1.9807852804032306e-05, + "loss": 0.5124, + "step": 1063 + }, + { + "epoch": 0.09, + "learning_rate": 1.98073136692133e-05, + "loss": 0.5042, + "step": 1064 + }, + { + "epoch": 0.09, + "learning_rate": 1.9806773786447605e-05, + "loss": 0.5294, + "step": 1065 + }, + { + "epoch": 0.09, + "learning_rate": 1.9806233155776403e-05, + "loss": 0.5382, + "step": 1066 + }, + { + "epoch": 0.09, + "learning_rate": 1.9805691777240917e-05, + "loss": 0.5212, + "step": 1067 + }, + { + "epoch": 0.09, + "learning_rate": 1.980514965088244e-05, + "loss": 0.5228, + "step": 1068 + }, + { + "epoch": 0.09, + "learning_rate": 1.9804606776742318e-05, + "loss": 0.5093, + "step": 1069 + }, + { + "epoch": 0.09, + "learning_rate": 1.9804063154861947e-05, + "loss": 0.5154, + "step": 1070 + }, + { + "epoch": 0.09, + "learning_rate": 1.980351878528279e-05, + "loss": 0.4891, + "step": 1071 + }, + { + "epoch": 0.09, + "learning_rate": 1.9802973668046364e-05, + "loss": 0.4991, + "step": 1072 + }, + { + "epoch": 0.09, + "learning_rate": 1.9802427803194238e-05, + "loss": 0.5134, + "step": 1073 + }, + { + "epoch": 0.09, + "learning_rate": 1.980188119076804e-05, + "loss": 0.5102, + "step": 1074 + }, + { + "epoch": 0.09, + "learning_rate": 1.9801333830809468e-05, + "loss": 0.5098, + "step": 1075 + }, + { + "epoch": 0.09, + "learning_rate": 1.9800785723360256e-05, + "loss": 0.5143, + "step": 1076 + }, + { + "epoch": 0.09, + "learning_rate": 1.9800236868462206e-05, + "loss": 0.5105, + "step": 1077 + }, + { + "epoch": 0.09, + "learning_rate": 1.979968726615718e-05, + "loss": 0.5076, + "step": 1078 + }, + { + "epoch": 0.09, + "learning_rate": 1.979913691648709e-05, + "loss": 0.5331, + "step": 1079 + }, + { + "epoch": 0.09, + "learning_rate": 1.9798585819493907e-05, + "loss": 0.5235, + "step": 1080 + }, + { + "epoch": 0.09, + "learning_rate": 1.979803397521966e-05, + "loss": 0.5152, + "step": 1081 + }, + { + "epoch": 0.09, + "learning_rate": 1.979748138370644e-05, + "loss": 0.5344, + "step": 1082 + }, + { + "epoch": 0.09, + "learning_rate": 1.9796928044996386e-05, + "loss": 0.5007, + "step": 1083 + }, + { + "epoch": 0.09, + "learning_rate": 1.97963739591317e-05, + "loss": 0.5165, + "step": 1084 + }, + { + "epoch": 0.09, + "learning_rate": 1.9795819126154634e-05, + "loss": 0.4915, + "step": 1085 + }, + { + "epoch": 0.09, + "learning_rate": 1.9795263546107507e-05, + "loss": 0.5352, + "step": 1086 + }, + { + "epoch": 0.09, + "learning_rate": 1.9794707219032686e-05, + "loss": 0.5152, + "step": 1087 + }, + { + "epoch": 0.09, + "learning_rate": 1.97941501449726e-05, + "loss": 0.5109, + "step": 1088 + }, + { + "epoch": 0.09, + "learning_rate": 1.979359232396974e-05, + "loss": 0.5096, + "step": 1089 + }, + { + "epoch": 0.09, + "learning_rate": 1.9793033756066635e-05, + "loss": 0.4935, + "step": 1090 + }, + { + "epoch": 0.09, + "learning_rate": 1.9792474441305896e-05, + "loss": 0.5331, + "step": 1091 + }, + { + "epoch": 0.09, + "learning_rate": 1.9791914379730174e-05, + "loss": 0.4988, + "step": 1092 + }, + { + "epoch": 0.09, + "learning_rate": 1.9791353571382178e-05, + "loss": 0.5234, + "step": 1093 + }, + { + "epoch": 0.09, + "learning_rate": 1.9790792016304685e-05, + "loss": 0.4935, + "step": 1094 + }, + { + "epoch": 0.09, + "learning_rate": 1.9790229714540513e-05, + "loss": 0.5209, + "step": 1095 + }, + { + "epoch": 0.09, + "learning_rate": 1.9789666666132553e-05, + "loss": 0.5117, + "step": 1096 + }, + { + "epoch": 0.09, + "learning_rate": 1.9789102871123745e-05, + "loss": 0.502, + "step": 1097 + }, + { + "epoch": 0.09, + "learning_rate": 1.978853832955708e-05, + "loss": 0.517, + "step": 1098 + }, + { + "epoch": 0.09, + "learning_rate": 1.9787973041475616e-05, + "loss": 0.5119, + "step": 1099 + }, + { + "epoch": 0.09, + "learning_rate": 1.9787407006922464e-05, + "loss": 0.5175, + "step": 1100 + }, + { + "epoch": 0.09, + "learning_rate": 1.9786840225940795e-05, + "loss": 0.5115, + "step": 1101 + }, + { + "epoch": 0.09, + "learning_rate": 1.978627269857383e-05, + "loss": 0.531, + "step": 1102 + }, + { + "epoch": 0.09, + "learning_rate": 1.9785704424864852e-05, + "loss": 0.495, + "step": 1103 + }, + { + "epoch": 0.09, + "learning_rate": 1.9785135404857202e-05, + "loss": 0.5128, + "step": 1104 + }, + { + "epoch": 0.09, + "learning_rate": 1.9784565638594274e-05, + "loss": 0.5277, + "step": 1105 + }, + { + "epoch": 0.09, + "learning_rate": 1.9783995126119518e-05, + "loss": 0.5047, + "step": 1106 + }, + { + "epoch": 0.09, + "learning_rate": 1.978342386747645e-05, + "loss": 0.4966, + "step": 1107 + }, + { + "epoch": 0.09, + "learning_rate": 1.9782851862708633e-05, + "loss": 0.5291, + "step": 1108 + }, + { + "epoch": 0.09, + "learning_rate": 1.978227911185969e-05, + "loss": 0.521, + "step": 1109 + }, + { + "epoch": 0.09, + "learning_rate": 1.97817056149733e-05, + "loss": 0.495, + "step": 1110 + }, + { + "epoch": 0.09, + "learning_rate": 1.9781131372093206e-05, + "loss": 0.5021, + "step": 1111 + }, + { + "epoch": 0.09, + "learning_rate": 1.97805563832632e-05, + "loss": 0.5245, + "step": 1112 + }, + { + "epoch": 0.09, + "learning_rate": 1.9779980648527126e-05, + "loss": 0.4986, + "step": 1113 + }, + { + "epoch": 0.09, + "learning_rate": 1.9779404167928903e-05, + "loss": 0.5174, + "step": 1114 + }, + { + "epoch": 0.1, + "learning_rate": 1.977882694151249e-05, + "loss": 0.5096, + "step": 1115 + }, + { + "epoch": 0.1, + "learning_rate": 1.9778248969321904e-05, + "loss": 0.5146, + "step": 1116 + }, + { + "epoch": 0.1, + "learning_rate": 1.9777670251401232e-05, + "loss": 0.4908, + "step": 1117 + }, + { + "epoch": 0.1, + "learning_rate": 1.9777090787794604e-05, + "loss": 0.518, + "step": 1118 + }, + { + "epoch": 0.1, + "learning_rate": 1.9776510578546217e-05, + "loss": 0.5145, + "step": 1119 + }, + { + "epoch": 0.1, + "learning_rate": 1.9775929623700318e-05, + "loss": 0.5137, + "step": 1120 + }, + { + "epoch": 0.1, + "learning_rate": 1.9775347923301212e-05, + "loss": 0.5191, + "step": 1121 + }, + { + "epoch": 0.1, + "learning_rate": 1.977476547739326e-05, + "loss": 0.5064, + "step": 1122 + }, + { + "epoch": 0.1, + "learning_rate": 1.9774182286020887e-05, + "loss": 0.503, + "step": 1123 + }, + { + "epoch": 0.1, + "learning_rate": 1.9773598349228568e-05, + "loss": 0.5156, + "step": 1124 + }, + { + "epoch": 0.1, + "learning_rate": 1.9773013667060832e-05, + "loss": 0.5395, + "step": 1125 + }, + { + "epoch": 0.1, + "learning_rate": 1.9772428239562273e-05, + "loss": 0.5049, + "step": 1126 + }, + { + "epoch": 0.1, + "learning_rate": 1.977184206677754e-05, + "loss": 0.5205, + "step": 1127 + }, + { + "epoch": 0.1, + "learning_rate": 1.977125514875133e-05, + "loss": 0.5174, + "step": 1128 + }, + { + "epoch": 0.1, + "learning_rate": 1.9770667485528413e-05, + "loss": 0.4972, + "step": 1129 + }, + { + "epoch": 0.1, + "learning_rate": 1.9770079077153604e-05, + "loss": 0.5308, + "step": 1130 + }, + { + "epoch": 0.1, + "learning_rate": 1.976948992367177e-05, + "loss": 0.5004, + "step": 1131 + }, + { + "epoch": 0.1, + "learning_rate": 1.9768900025127852e-05, + "loss": 0.523, + "step": 1132 + }, + { + "epoch": 0.1, + "learning_rate": 1.976830938156683e-05, + "loss": 0.5098, + "step": 1133 + }, + { + "epoch": 0.1, + "learning_rate": 1.976771799303376e-05, + "loss": 0.5335, + "step": 1134 + }, + { + "epoch": 0.1, + "learning_rate": 1.9767125859573735e-05, + "loss": 0.5213, + "step": 1135 + }, + { + "epoch": 0.1, + "learning_rate": 1.9766532981231913e-05, + "loss": 0.5005, + "step": 1136 + }, + { + "epoch": 0.1, + "learning_rate": 1.9765939358053512e-05, + "loss": 0.511, + "step": 1137 + }, + { + "epoch": 0.1, + "learning_rate": 1.9765344990083807e-05, + "loss": 0.4862, + "step": 1138 + }, + { + "epoch": 0.1, + "learning_rate": 1.976474987736812e-05, + "loss": 0.4992, + "step": 1139 + }, + { + "epoch": 0.1, + "learning_rate": 1.976415401995184e-05, + "loss": 0.5096, + "step": 1140 + }, + { + "epoch": 0.1, + "learning_rate": 1.9763557417880412e-05, + "loss": 0.499, + "step": 1141 + }, + { + "epoch": 0.1, + "learning_rate": 1.9762960071199334e-05, + "loss": 0.5044, + "step": 1142 + }, + { + "epoch": 0.1, + "learning_rate": 1.9762361979954164e-05, + "loss": 0.4965, + "step": 1143 + }, + { + "epoch": 0.1, + "learning_rate": 1.976176314419051e-05, + "loss": 0.5544, + "step": 1144 + }, + { + "epoch": 0.1, + "learning_rate": 1.9761163563954047e-05, + "loss": 0.5192, + "step": 1145 + }, + { + "epoch": 0.1, + "learning_rate": 1.9760563239290495e-05, + "loss": 0.5182, + "step": 1146 + }, + { + "epoch": 0.1, + "learning_rate": 1.9759962170245647e-05, + "loss": 0.5148, + "step": 1147 + }, + { + "epoch": 0.1, + "learning_rate": 1.9759360356865328e-05, + "loss": 0.5167, + "step": 1148 + }, + { + "epoch": 0.1, + "learning_rate": 1.9758757799195454e-05, + "loss": 0.5039, + "step": 1149 + }, + { + "epoch": 0.1, + "learning_rate": 1.975815449728196e-05, + "loss": 0.5091, + "step": 1150 + }, + { + "epoch": 0.1, + "learning_rate": 1.975755045117087e-05, + "loss": 0.4961, + "step": 1151 + }, + { + "epoch": 0.1, + "learning_rate": 1.975694566090825e-05, + "loss": 0.517, + "step": 1152 + }, + { + "epoch": 0.1, + "learning_rate": 1.9756340126540216e-05, + "loss": 0.5197, + "step": 1153 + }, + { + "epoch": 0.1, + "learning_rate": 1.9755733848112946e-05, + "loss": 0.511, + "step": 1154 + }, + { + "epoch": 0.1, + "learning_rate": 1.9755126825672692e-05, + "loss": 0.502, + "step": 1155 + }, + { + "epoch": 0.1, + "learning_rate": 1.9754519059265737e-05, + "loss": 0.503, + "step": 1156 + }, + { + "epoch": 0.1, + "learning_rate": 1.9753910548938436e-05, + "loss": 0.5168, + "step": 1157 + }, + { + "epoch": 0.1, + "learning_rate": 1.9753301294737195e-05, + "loss": 0.5187, + "step": 1158 + }, + { + "epoch": 0.1, + "learning_rate": 1.9752691296708476e-05, + "loss": 0.5103, + "step": 1159 + }, + { + "epoch": 0.1, + "learning_rate": 1.9752080554898808e-05, + "loss": 0.5246, + "step": 1160 + }, + { + "epoch": 0.1, + "learning_rate": 1.9751469069354757e-05, + "loss": 0.5179, + "step": 1161 + }, + { + "epoch": 0.1, + "learning_rate": 1.9750856840122968e-05, + "loss": 0.5008, + "step": 1162 + }, + { + "epoch": 0.1, + "learning_rate": 1.9750243867250127e-05, + "loss": 0.4984, + "step": 1163 + }, + { + "epoch": 0.1, + "learning_rate": 1.9749630150782978e-05, + "loss": 0.5235, + "step": 1164 + }, + { + "epoch": 0.1, + "learning_rate": 1.9749015690768333e-05, + "loss": 0.5074, + "step": 1165 + }, + { + "epoch": 0.1, + "learning_rate": 1.9748400487253052e-05, + "loss": 0.5156, + "step": 1166 + }, + { + "epoch": 0.1, + "learning_rate": 1.974778454028405e-05, + "loss": 0.5041, + "step": 1167 + }, + { + "epoch": 0.1, + "learning_rate": 1.9747167849908305e-05, + "loss": 0.4839, + "step": 1168 + }, + { + "epoch": 0.1, + "learning_rate": 1.9746550416172842e-05, + "loss": 0.5191, + "step": 1169 + }, + { + "epoch": 0.1, + "learning_rate": 1.9745932239124758e-05, + "loss": 0.5092, + "step": 1170 + }, + { + "epoch": 0.1, + "learning_rate": 1.9745313318811195e-05, + "loss": 0.5044, + "step": 1171 + }, + { + "epoch": 0.1, + "learning_rate": 1.9744693655279347e-05, + "loss": 0.5118, + "step": 1172 + }, + { + "epoch": 0.1, + "learning_rate": 1.9744073248576485e-05, + "loss": 0.4978, + "step": 1173 + }, + { + "epoch": 0.1, + "learning_rate": 1.974345209874991e-05, + "loss": 0.5016, + "step": 1174 + }, + { + "epoch": 0.1, + "learning_rate": 1.9742830205847006e-05, + "loss": 0.4913, + "step": 1175 + }, + { + "epoch": 0.1, + "learning_rate": 1.974220756991519e-05, + "loss": 0.5207, + "step": 1176 + }, + { + "epoch": 0.1, + "learning_rate": 1.9741584191001956e-05, + "loss": 0.5068, + "step": 1177 + }, + { + "epoch": 0.1, + "learning_rate": 1.974096006915484e-05, + "loss": 0.5258, + "step": 1178 + }, + { + "epoch": 0.1, + "learning_rate": 1.974033520442144e-05, + "loss": 0.5349, + "step": 1179 + }, + { + "epoch": 0.1, + "learning_rate": 1.9739709596849418e-05, + "loss": 0.5248, + "step": 1180 + }, + { + "epoch": 0.1, + "learning_rate": 1.9739083246486478e-05, + "loss": 0.5162, + "step": 1181 + }, + { + "epoch": 0.1, + "learning_rate": 1.9738456153380388e-05, + "loss": 0.4908, + "step": 1182 + }, + { + "epoch": 0.1, + "learning_rate": 1.9737828317578977e-05, + "loss": 0.5192, + "step": 1183 + }, + { + "epoch": 0.1, + "learning_rate": 1.9737199739130123e-05, + "loss": 0.5086, + "step": 1184 + }, + { + "epoch": 0.1, + "learning_rate": 1.9736570418081763e-05, + "loss": 0.5064, + "step": 1185 + }, + { + "epoch": 0.1, + "learning_rate": 1.97359403544819e-05, + "loss": 0.5058, + "step": 1186 + }, + { + "epoch": 0.1, + "learning_rate": 1.9735309548378575e-05, + "loss": 0.5141, + "step": 1187 + }, + { + "epoch": 0.1, + "learning_rate": 1.97346779998199e-05, + "loss": 0.5035, + "step": 1188 + }, + { + "epoch": 0.1, + "learning_rate": 1.9734045708854044e-05, + "loss": 0.5119, + "step": 1189 + }, + { + "epoch": 0.1, + "learning_rate": 1.973341267552922e-05, + "loss": 0.5479, + "step": 1190 + }, + { + "epoch": 0.1, + "learning_rate": 1.9732778899893707e-05, + "loss": 0.5206, + "step": 1191 + }, + { + "epoch": 0.1, + "learning_rate": 1.9732144381995848e-05, + "loss": 0.5172, + "step": 1192 + }, + { + "epoch": 0.1, + "learning_rate": 1.9731509121884023e-05, + "loss": 0.5162, + "step": 1193 + }, + { + "epoch": 0.1, + "learning_rate": 1.9730873119606687e-05, + "loss": 0.5044, + "step": 1194 + }, + { + "epoch": 0.1, + "learning_rate": 1.973023637521234e-05, + "loss": 0.5025, + "step": 1195 + }, + { + "epoch": 0.1, + "learning_rate": 1.972959888874955e-05, + "loss": 0.5075, + "step": 1196 + }, + { + "epoch": 0.1, + "learning_rate": 1.9728960660266923e-05, + "loss": 0.499, + "step": 1197 + }, + { + "epoch": 0.1, + "learning_rate": 1.9728321689813142e-05, + "loss": 0.5213, + "step": 1198 + }, + { + "epoch": 0.1, + "learning_rate": 1.972768197743693e-05, + "loss": 0.5083, + "step": 1199 + }, + { + "epoch": 0.1, + "learning_rate": 1.9727041523187083e-05, + "loss": 0.5068, + "step": 1200 + }, + { + "epoch": 0.1, + "learning_rate": 1.9726400327112437e-05, + "loss": 0.5045, + "step": 1201 + }, + { + "epoch": 0.1, + "learning_rate": 1.97257583892619e-05, + "loss": 0.5254, + "step": 1202 + }, + { + "epoch": 0.1, + "learning_rate": 1.972511570968442e-05, + "loss": 0.5036, + "step": 1203 + }, + { + "epoch": 0.1, + "learning_rate": 1.972447228842902e-05, + "loss": 0.5047, + "step": 1204 + }, + { + "epoch": 0.1, + "learning_rate": 1.972382812554476e-05, + "loss": 0.4964, + "step": 1205 + }, + { + "epoch": 0.1, + "learning_rate": 1.9723183221080774e-05, + "loss": 0.5211, + "step": 1206 + }, + { + "epoch": 0.1, + "learning_rate": 1.972253757508624e-05, + "loss": 0.4983, + "step": 1207 + }, + { + "epoch": 0.1, + "learning_rate": 1.97218911876104e-05, + "loss": 0.5293, + "step": 1208 + }, + { + "epoch": 0.1, + "learning_rate": 1.972124405870255e-05, + "loss": 0.5165, + "step": 1209 + }, + { + "epoch": 0.1, + "learning_rate": 1.972059618841205e-05, + "loss": 0.5102, + "step": 1210 + }, + { + "epoch": 0.1, + "learning_rate": 1.9719947576788298e-05, + "loss": 0.5116, + "step": 1211 + }, + { + "epoch": 0.1, + "learning_rate": 1.9719298223880763e-05, + "loss": 0.5192, + "step": 1212 + }, + { + "epoch": 0.1, + "learning_rate": 1.971864812973897e-05, + "loss": 0.5301, + "step": 1213 + }, + { + "epoch": 0.1, + "learning_rate": 1.9717997294412493e-05, + "loss": 0.4978, + "step": 1214 + }, + { + "epoch": 0.1, + "learning_rate": 1.9717345717950972e-05, + "loss": 0.509, + "step": 1215 + }, + { + "epoch": 0.1, + "learning_rate": 1.97166934004041e-05, + "loss": 0.5348, + "step": 1216 + }, + { + "epoch": 0.1, + "learning_rate": 1.971604034182162e-05, + "loss": 0.5146, + "step": 1217 + }, + { + "epoch": 0.1, + "learning_rate": 1.9715386542253348e-05, + "loss": 0.5086, + "step": 1218 + }, + { + "epoch": 0.1, + "learning_rate": 1.9714732001749134e-05, + "loss": 0.504, + "step": 1219 + }, + { + "epoch": 0.1, + "learning_rate": 1.9714076720358898e-05, + "loss": 0.4975, + "step": 1220 + }, + { + "epoch": 0.1, + "learning_rate": 1.9713420698132614e-05, + "loss": 0.5259, + "step": 1221 + }, + { + "epoch": 0.1, + "learning_rate": 1.971276393512032e-05, + "loss": 0.5166, + "step": 1222 + }, + { + "epoch": 0.1, + "learning_rate": 1.9712106431372095e-05, + "loss": 0.5211, + "step": 1223 + }, + { + "epoch": 0.1, + "learning_rate": 1.971144818693809e-05, + "loss": 0.5034, + "step": 1224 + }, + { + "epoch": 0.1, + "learning_rate": 1.97107892018685e-05, + "loss": 0.4949, + "step": 1225 + }, + { + "epoch": 0.1, + "learning_rate": 1.9710129476213587e-05, + "loss": 0.5245, + "step": 1226 + }, + { + "epoch": 0.1, + "learning_rate": 1.970946901002366e-05, + "loss": 0.5122, + "step": 1227 + }, + { + "epoch": 0.1, + "learning_rate": 1.970880780334909e-05, + "loss": 0.5051, + "step": 1228 + }, + { + "epoch": 0.1, + "learning_rate": 1.9708145856240302e-05, + "loss": 0.5143, + "step": 1229 + }, + { + "epoch": 0.1, + "learning_rate": 1.970748316874778e-05, + "loss": 0.5078, + "step": 1230 + }, + { + "epoch": 0.1, + "learning_rate": 1.9706819740922068e-05, + "loss": 0.513, + "step": 1231 + }, + { + "epoch": 0.11, + "learning_rate": 1.970615557281376e-05, + "loss": 0.5245, + "step": 1232 + }, + { + "epoch": 0.11, + "learning_rate": 1.97054906644735e-05, + "loss": 0.5292, + "step": 1233 + }, + { + "epoch": 0.11, + "learning_rate": 1.9704825015952005e-05, + "loss": 0.5095, + "step": 1234 + }, + { + "epoch": 0.11, + "learning_rate": 1.970415862730004e-05, + "loss": 0.5238, + "step": 1235 + }, + { + "epoch": 0.11, + "learning_rate": 1.970349149856842e-05, + "loss": 0.5118, + "step": 1236 + }, + { + "epoch": 0.11, + "learning_rate": 1.970282362980803e-05, + "loss": 0.5026, + "step": 1237 + }, + { + "epoch": 0.11, + "learning_rate": 1.97021550210698e-05, + "loss": 0.5219, + "step": 1238 + }, + { + "epoch": 0.11, + "learning_rate": 1.9701485672404725e-05, + "loss": 0.5132, + "step": 1239 + }, + { + "epoch": 0.11, + "learning_rate": 1.9700815583863853e-05, + "loss": 0.5056, + "step": 1240 + }, + { + "epoch": 0.11, + "learning_rate": 1.970014475549828e-05, + "loss": 0.51, + "step": 1241 + }, + { + "epoch": 0.11, + "learning_rate": 1.969947318735917e-05, + "loss": 0.5229, + "step": 1242 + }, + { + "epoch": 0.11, + "learning_rate": 1.9698800879497747e-05, + "loss": 0.5158, + "step": 1243 + }, + { + "epoch": 0.11, + "learning_rate": 1.9698127831965276e-05, + "loss": 0.5177, + "step": 1244 + }, + { + "epoch": 0.11, + "learning_rate": 1.969745404481308e-05, + "loss": 0.5248, + "step": 1245 + }, + { + "epoch": 0.11, + "learning_rate": 1.9696779518092564e-05, + "loss": 0.4828, + "step": 1246 + }, + { + "epoch": 0.11, + "learning_rate": 1.9696104251855154e-05, + "loss": 0.5141, + "step": 1247 + }, + { + "epoch": 0.11, + "learning_rate": 1.969542824615235e-05, + "loss": 0.5057, + "step": 1248 + }, + { + "epoch": 0.11, + "learning_rate": 1.9694751501035715e-05, + "loss": 0.504, + "step": 1249 + }, + { + "epoch": 0.11, + "learning_rate": 1.9694074016556855e-05, + "loss": 0.5431, + "step": 1250 + }, + { + "epoch": 0.11, + "learning_rate": 1.9693395792767443e-05, + "loss": 0.5062, + "step": 1251 + }, + { + "epoch": 0.11, + "learning_rate": 1.9692716829719197e-05, + "loss": 0.5028, + "step": 1252 + }, + { + "epoch": 0.11, + "learning_rate": 1.9692037127463898e-05, + "loss": 0.5105, + "step": 1253 + }, + { + "epoch": 0.11, + "learning_rate": 1.9691356686053386e-05, + "loss": 0.5041, + "step": 1254 + }, + { + "epoch": 0.11, + "learning_rate": 1.969067550553955e-05, + "loss": 0.5161, + "step": 1255 + }, + { + "epoch": 0.11, + "learning_rate": 1.9689993585974344e-05, + "loss": 0.5066, + "step": 1256 + }, + { + "epoch": 0.11, + "learning_rate": 1.9689310927409773e-05, + "loss": 0.5009, + "step": 1257 + }, + { + "epoch": 0.11, + "learning_rate": 1.96886275298979e-05, + "loss": 0.5185, + "step": 1258 + }, + { + "epoch": 0.11, + "learning_rate": 1.968794339349084e-05, + "loss": 0.5109, + "step": 1259 + }, + { + "epoch": 0.11, + "learning_rate": 1.9687258518240773e-05, + "loss": 0.4889, + "step": 1260 + }, + { + "epoch": 0.11, + "learning_rate": 1.9686572904199928e-05, + "loss": 0.5149, + "step": 1261 + }, + { + "epoch": 0.11, + "learning_rate": 1.9685886551420596e-05, + "loss": 0.5004, + "step": 1262 + }, + { + "epoch": 0.11, + "learning_rate": 1.9685199459955116e-05, + "loss": 0.52, + "step": 1263 + }, + { + "epoch": 0.11, + "learning_rate": 1.968451162985589e-05, + "loss": 0.5105, + "step": 1264 + }, + { + "epoch": 0.11, + "learning_rate": 1.9683823061175375e-05, + "loss": 0.5035, + "step": 1265 + }, + { + "epoch": 0.11, + "learning_rate": 1.9683133753966085e-05, + "loss": 0.5106, + "step": 1266 + }, + { + "epoch": 0.11, + "learning_rate": 1.968244370828059e-05, + "loss": 0.4906, + "step": 1267 + }, + { + "epoch": 0.11, + "learning_rate": 1.9681752924171513e-05, + "loss": 0.5295, + "step": 1268 + }, + { + "epoch": 0.11, + "learning_rate": 1.968106140169154e-05, + "loss": 0.5084, + "step": 1269 + }, + { + "epoch": 0.11, + "learning_rate": 1.9680369140893405e-05, + "loss": 0.5014, + "step": 1270 + }, + { + "epoch": 0.11, + "learning_rate": 1.9679676141829905e-05, + "loss": 0.4938, + "step": 1271 + }, + { + "epoch": 0.11, + "learning_rate": 1.9678982404553896e-05, + "loss": 0.5052, + "step": 1272 + }, + { + "epoch": 0.11, + "learning_rate": 1.9678287929118275e-05, + "loss": 0.5031, + "step": 1273 + }, + { + "epoch": 0.11, + "learning_rate": 1.9677592715576013e-05, + "loss": 0.52, + "step": 1274 + }, + { + "epoch": 0.11, + "learning_rate": 1.9676896763980127e-05, + "loss": 0.5125, + "step": 1275 + }, + { + "epoch": 0.11, + "learning_rate": 1.9676200074383692e-05, + "loss": 0.5117, + "step": 1276 + }, + { + "epoch": 0.11, + "learning_rate": 1.9675502646839848e-05, + "loss": 0.5305, + "step": 1277 + }, + { + "epoch": 0.11, + "learning_rate": 1.967480448140177e-05, + "loss": 0.5028, + "step": 1278 + }, + { + "epoch": 0.11, + "learning_rate": 1.967410557812272e-05, + "loss": 0.5002, + "step": 1279 + }, + { + "epoch": 0.11, + "learning_rate": 1.9673405937055986e-05, + "loss": 0.5264, + "step": 1280 + }, + { + "epoch": 0.11, + "learning_rate": 1.967270555825493e-05, + "loss": 0.5288, + "step": 1281 + }, + { + "epoch": 0.11, + "learning_rate": 1.9672004441772966e-05, + "loss": 0.5052, + "step": 1282 + }, + { + "epoch": 0.11, + "learning_rate": 1.9671302587663566e-05, + "loss": 0.514, + "step": 1283 + }, + { + "epoch": 0.11, + "learning_rate": 1.967059999598025e-05, + "loss": 0.5326, + "step": 1284 + }, + { + "epoch": 0.11, + "learning_rate": 1.9669896666776606e-05, + "loss": 0.4978, + "step": 1285 + }, + { + "epoch": 0.11, + "learning_rate": 1.9669192600106275e-05, + "loss": 0.5187, + "step": 1286 + }, + { + "epoch": 0.11, + "learning_rate": 1.9668487796022947e-05, + "loss": 0.5316, + "step": 1287 + }, + { + "epoch": 0.11, + "learning_rate": 1.9667782254580373e-05, + "loss": 0.4921, + "step": 1288 + }, + { + "epoch": 0.11, + "learning_rate": 1.9667075975832362e-05, + "loss": 0.5102, + "step": 1289 + }, + { + "epoch": 0.11, + "learning_rate": 1.9666368959832783e-05, + "loss": 0.5152, + "step": 1290 + }, + { + "epoch": 0.11, + "learning_rate": 1.9665661206635548e-05, + "loss": 0.5166, + "step": 1291 + }, + { + "epoch": 0.11, + "learning_rate": 1.9664952716294636e-05, + "loss": 0.4985, + "step": 1292 + }, + { + "epoch": 0.11, + "learning_rate": 1.9664243488864078e-05, + "loss": 0.5067, + "step": 1293 + }, + { + "epoch": 0.11, + "learning_rate": 1.9663533524397968e-05, + "loss": 0.4999, + "step": 1294 + }, + { + "epoch": 0.11, + "learning_rate": 1.9662822822950446e-05, + "loss": 0.4971, + "step": 1295 + }, + { + "epoch": 0.11, + "learning_rate": 1.9662111384575716e-05, + "loss": 0.4992, + "step": 1296 + }, + { + "epoch": 0.11, + "learning_rate": 1.966139920932803e-05, + "loss": 0.5099, + "step": 1297 + }, + { + "epoch": 0.11, + "learning_rate": 1.966068629726171e-05, + "loss": 0.5093, + "step": 1298 + }, + { + "epoch": 0.11, + "learning_rate": 1.965997264843112e-05, + "loss": 0.5167, + "step": 1299 + }, + { + "epoch": 0.11, + "learning_rate": 1.9659258262890683e-05, + "loss": 0.5118, + "step": 1300 + }, + { + "epoch": 0.11, + "learning_rate": 1.965854314069489e-05, + "loss": 0.496, + "step": 1301 + }, + { + "epoch": 0.11, + "learning_rate": 1.965782728189827e-05, + "loss": 0.5074, + "step": 1302 + }, + { + "epoch": 0.11, + "learning_rate": 1.965711068655542e-05, + "loss": 0.5143, + "step": 1303 + }, + { + "epoch": 0.11, + "learning_rate": 1.9656393354720994e-05, + "loss": 0.4998, + "step": 1304 + }, + { + "epoch": 0.11, + "learning_rate": 1.9655675286449697e-05, + "loss": 0.4935, + "step": 1305 + }, + { + "epoch": 0.11, + "learning_rate": 1.965495648179629e-05, + "loss": 0.5156, + "step": 1306 + }, + { + "epoch": 0.11, + "learning_rate": 1.9654236940815596e-05, + "loss": 0.5062, + "step": 1307 + }, + { + "epoch": 0.11, + "learning_rate": 1.9653516663562485e-05, + "loss": 0.4936, + "step": 1308 + }, + { + "epoch": 0.11, + "learning_rate": 1.965279565009189e-05, + "loss": 0.498, + "step": 1309 + }, + { + "epoch": 0.11, + "learning_rate": 1.9652073900458806e-05, + "loss": 0.5243, + "step": 1310 + }, + { + "epoch": 0.11, + "learning_rate": 1.9651351414718263e-05, + "loss": 0.5046, + "step": 1311 + }, + { + "epoch": 0.11, + "learning_rate": 1.9650628192925372e-05, + "loss": 0.5169, + "step": 1312 + }, + { + "epoch": 0.11, + "learning_rate": 1.9649904235135283e-05, + "loss": 0.5363, + "step": 1313 + }, + { + "epoch": 0.11, + "learning_rate": 1.964917954140321e-05, + "loss": 0.4991, + "step": 1314 + }, + { + "epoch": 0.11, + "learning_rate": 1.964845411178442e-05, + "loss": 0.5128, + "step": 1315 + }, + { + "epoch": 0.11, + "learning_rate": 1.964772794633424e-05, + "loss": 0.5141, + "step": 1316 + }, + { + "epoch": 0.11, + "learning_rate": 1.964700104510805e-05, + "loss": 0.4971, + "step": 1317 + }, + { + "epoch": 0.11, + "learning_rate": 1.9646273408161286e-05, + "loss": 0.5191, + "step": 1318 + }, + { + "epoch": 0.11, + "learning_rate": 1.9645545035549437e-05, + "loss": 0.5007, + "step": 1319 + }, + { + "epoch": 0.11, + "learning_rate": 1.9644815927328055e-05, + "loss": 0.5172, + "step": 1320 + }, + { + "epoch": 0.11, + "learning_rate": 1.9644086083552745e-05, + "loss": 0.512, + "step": 1321 + }, + { + "epoch": 0.11, + "learning_rate": 1.9643355504279164e-05, + "loss": 0.4929, + "step": 1322 + }, + { + "epoch": 0.11, + "learning_rate": 1.964262418956304e-05, + "loss": 0.5147, + "step": 1323 + }, + { + "epoch": 0.11, + "learning_rate": 1.9641892139460133e-05, + "loss": 0.5028, + "step": 1324 + }, + { + "epoch": 0.11, + "learning_rate": 1.964115935402628e-05, + "loss": 0.5183, + "step": 1325 + }, + { + "epoch": 0.11, + "learning_rate": 1.964042583331736e-05, + "loss": 0.5044, + "step": 1326 + }, + { + "epoch": 0.11, + "learning_rate": 1.9639691577389322e-05, + "loss": 0.4925, + "step": 1327 + }, + { + "epoch": 0.11, + "learning_rate": 1.963895658629816e-05, + "loss": 0.5059, + "step": 1328 + }, + { + "epoch": 0.11, + "learning_rate": 1.9638220860099927e-05, + "loss": 0.4974, + "step": 1329 + }, + { + "epoch": 0.11, + "learning_rate": 1.963748439885073e-05, + "loss": 0.5043, + "step": 1330 + }, + { + "epoch": 0.11, + "learning_rate": 1.963674720260674e-05, + "loss": 0.5343, + "step": 1331 + }, + { + "epoch": 0.11, + "learning_rate": 1.9636009271424177e-05, + "loss": 0.5099, + "step": 1332 + }, + { + "epoch": 0.11, + "learning_rate": 1.963527060535932e-05, + "loss": 0.5293, + "step": 1333 + }, + { + "epoch": 0.11, + "learning_rate": 1.9634531204468493e-05, + "loss": 0.5068, + "step": 1334 + }, + { + "epoch": 0.11, + "learning_rate": 1.96337910688081e-05, + "loss": 0.5242, + "step": 1335 + }, + { + "epoch": 0.11, + "learning_rate": 1.9633050198434578e-05, + "loss": 0.5008, + "step": 1336 + }, + { + "epoch": 0.11, + "learning_rate": 1.9632308593404432e-05, + "loss": 0.4987, + "step": 1337 + }, + { + "epoch": 0.11, + "learning_rate": 1.9631566253774216e-05, + "loss": 0.5042, + "step": 1338 + }, + { + "epoch": 0.11, + "learning_rate": 1.9630823179600548e-05, + "loss": 0.5238, + "step": 1339 + }, + { + "epoch": 0.11, + "learning_rate": 1.9630079370940098e-05, + "loss": 0.4805, + "step": 1340 + }, + { + "epoch": 0.11, + "learning_rate": 1.9629334827849594e-05, + "loss": 0.5075, + "step": 1341 + }, + { + "epoch": 0.11, + "learning_rate": 1.962858955038581e-05, + "loss": 0.5159, + "step": 1342 + }, + { + "epoch": 0.11, + "learning_rate": 1.9627843538605588e-05, + "loss": 0.5023, + "step": 1343 + }, + { + "epoch": 0.11, + "learning_rate": 1.9627096792565825e-05, + "loss": 0.5085, + "step": 1344 + }, + { + "epoch": 0.11, + "learning_rate": 1.962634931232347e-05, + "loss": 0.5054, + "step": 1345 + }, + { + "epoch": 0.11, + "learning_rate": 1.9625601097935525e-05, + "loss": 0.5219, + "step": 1346 + }, + { + "epoch": 0.11, + "learning_rate": 1.9624852149459056e-05, + "loss": 0.5131, + "step": 1347 + }, + { + "epoch": 0.11, + "learning_rate": 1.962410246695118e-05, + "loss": 0.5105, + "step": 1348 + }, + { + "epoch": 0.12, + "learning_rate": 1.962335205046907e-05, + "loss": 0.5056, + "step": 1349 + }, + { + "epoch": 0.12, + "learning_rate": 1.9622600900069953e-05, + "loss": 0.4835, + "step": 1350 + }, + { + "epoch": 0.12, + "learning_rate": 1.9621849015811123e-05, + "loss": 0.5335, + "step": 1351 + }, + { + "epoch": 0.12, + "learning_rate": 1.9621096397749918e-05, + "loss": 0.5174, + "step": 1352 + }, + { + "epoch": 0.12, + "learning_rate": 1.962034304594373e-05, + "loss": 0.4933, + "step": 1353 + }, + { + "epoch": 0.12, + "learning_rate": 1.961958896045002e-05, + "loss": 0.5122, + "step": 1354 + }, + { + "epoch": 0.12, + "learning_rate": 1.9618834141326294e-05, + "loss": 0.5301, + "step": 1355 + }, + { + "epoch": 0.12, + "learning_rate": 1.961807858863012e-05, + "loss": 0.5101, + "step": 1356 + }, + { + "epoch": 0.12, + "learning_rate": 1.961732230241912e-05, + "loss": 0.5144, + "step": 1357 + }, + { + "epoch": 0.12, + "learning_rate": 1.9616565282750967e-05, + "loss": 0.5231, + "step": 1358 + }, + { + "epoch": 0.12, + "learning_rate": 1.96158075296834e-05, + "loss": 0.5087, + "step": 1359 + }, + { + "epoch": 0.12, + "learning_rate": 1.9615049043274207e-05, + "loss": 0.4929, + "step": 1360 + }, + { + "epoch": 0.12, + "learning_rate": 1.961428982358123e-05, + "loss": 0.495, + "step": 1361 + }, + { + "epoch": 0.12, + "learning_rate": 1.9613529870662372e-05, + "loss": 0.5189, + "step": 1362 + }, + { + "epoch": 0.12, + "learning_rate": 1.9612769184575592e-05, + "loss": 0.4931, + "step": 1363 + }, + { + "epoch": 0.12, + "learning_rate": 1.9612007765378904e-05, + "loss": 0.5168, + "step": 1364 + }, + { + "epoch": 0.12, + "learning_rate": 1.961124561313037e-05, + "loss": 0.4977, + "step": 1365 + }, + { + "epoch": 0.12, + "learning_rate": 1.9610482727888126e-05, + "loss": 0.4949, + "step": 1366 + }, + { + "epoch": 0.12, + "learning_rate": 1.960971910971034e-05, + "loss": 0.5055, + "step": 1367 + }, + { + "epoch": 0.12, + "learning_rate": 1.960895475865526e-05, + "loss": 0.5141, + "step": 1368 + }, + { + "epoch": 0.12, + "learning_rate": 1.960818967478117e-05, + "loss": 0.4859, + "step": 1369 + }, + { + "epoch": 0.12, + "learning_rate": 1.9607423858146427e-05, + "loss": 0.5108, + "step": 1370 + }, + { + "epoch": 0.12, + "learning_rate": 1.9606657308809428e-05, + "loss": 0.5099, + "step": 1371 + }, + { + "epoch": 0.12, + "learning_rate": 1.9605890026828634e-05, + "loss": 0.5077, + "step": 1372 + }, + { + "epoch": 0.12, + "learning_rate": 1.9605122012262567e-05, + "loss": 0.4997, + "step": 1373 + }, + { + "epoch": 0.12, + "learning_rate": 1.9604353265169796e-05, + "loss": 0.5077, + "step": 1374 + }, + { + "epoch": 0.12, + "learning_rate": 1.9603583785608947e-05, + "loss": 0.5029, + "step": 1375 + }, + { + "epoch": 0.12, + "learning_rate": 1.9602813573638705e-05, + "loss": 0.5115, + "step": 1376 + }, + { + "epoch": 0.12, + "learning_rate": 1.9602042629317807e-05, + "loss": 0.5018, + "step": 1377 + }, + { + "epoch": 0.12, + "learning_rate": 1.960127095270505e-05, + "loss": 0.5299, + "step": 1378 + }, + { + "epoch": 0.12, + "learning_rate": 1.960049854385929e-05, + "loss": 0.4805, + "step": 1379 + }, + { + "epoch": 0.12, + "learning_rate": 1.9599725402839427e-05, + "loss": 0.5219, + "step": 1380 + }, + { + "epoch": 0.12, + "learning_rate": 1.9598951529704426e-05, + "loss": 0.5044, + "step": 1381 + }, + { + "epoch": 0.12, + "learning_rate": 1.959817692451331e-05, + "loss": 0.5166, + "step": 1382 + }, + { + "epoch": 0.12, + "learning_rate": 1.959740158732515e-05, + "loss": 0.5231, + "step": 1383 + }, + { + "epoch": 0.12, + "learning_rate": 1.9596625518199077e-05, + "loss": 0.5081, + "step": 1384 + }, + { + "epoch": 0.12, + "learning_rate": 1.9595848717194276e-05, + "loss": 0.4953, + "step": 1385 + }, + { + "epoch": 0.12, + "learning_rate": 1.9595071184369994e-05, + "loss": 0.4972, + "step": 1386 + }, + { + "epoch": 0.12, + "learning_rate": 1.9594292919785523e-05, + "loss": 0.5233, + "step": 1387 + }, + { + "epoch": 0.12, + "learning_rate": 1.959351392350022e-05, + "loss": 0.5184, + "step": 1388 + }, + { + "epoch": 0.12, + "learning_rate": 1.959273419557349e-05, + "loss": 0.4998, + "step": 1389 + }, + { + "epoch": 0.12, + "learning_rate": 1.9591953736064804e-05, + "loss": 0.5319, + "step": 1390 + }, + { + "epoch": 0.12, + "learning_rate": 1.959117254503368e-05, + "loss": 0.5126, + "step": 1391 + }, + { + "epoch": 0.12, + "learning_rate": 1.9590390622539696e-05, + "loss": 0.5247, + "step": 1392 + }, + { + "epoch": 0.12, + "learning_rate": 1.9589607968642483e-05, + "loss": 0.5052, + "step": 1393 + }, + { + "epoch": 0.12, + "learning_rate": 1.9588824583401735e-05, + "loss": 0.5061, + "step": 1394 + }, + { + "epoch": 0.12, + "learning_rate": 1.958804046687719e-05, + "loss": 0.4865, + "step": 1395 + }, + { + "epoch": 0.12, + "learning_rate": 1.9587255619128648e-05, + "loss": 0.5032, + "step": 1396 + }, + { + "epoch": 0.12, + "learning_rate": 1.958647004021597e-05, + "loss": 0.5219, + "step": 1397 + }, + { + "epoch": 0.12, + "learning_rate": 1.958568373019906e-05, + "loss": 0.4901, + "step": 1398 + }, + { + "epoch": 0.12, + "learning_rate": 1.9584896689137897e-05, + "loss": 0.5112, + "step": 1399 + }, + { + "epoch": 0.12, + "learning_rate": 1.9584108917092492e-05, + "loss": 0.5128, + "step": 1400 + }, + { + "epoch": 0.12, + "learning_rate": 1.958332041412293e-05, + "loss": 0.5305, + "step": 1401 + }, + { + "epoch": 0.12, + "learning_rate": 1.9582531180289342e-05, + "loss": 0.5034, + "step": 1402 + }, + { + "epoch": 0.12, + "learning_rate": 1.9581741215651923e-05, + "loss": 0.5128, + "step": 1403 + }, + { + "epoch": 0.12, + "learning_rate": 1.9580950520270914e-05, + "loss": 0.5049, + "step": 1404 + }, + { + "epoch": 0.12, + "learning_rate": 1.9580159094206622e-05, + "loss": 0.5127, + "step": 1405 + }, + { + "epoch": 0.12, + "learning_rate": 1.9579366937519398e-05, + "loss": 0.5143, + "step": 1406 + }, + { + "epoch": 0.12, + "learning_rate": 1.9578574050269662e-05, + "loss": 0.5137, + "step": 1407 + }, + { + "epoch": 0.12, + "learning_rate": 1.957778043251788e-05, + "loss": 0.5009, + "step": 1408 + }, + { + "epoch": 0.12, + "learning_rate": 1.957698608432457e-05, + "loss": 0.5156, + "step": 1409 + }, + { + "epoch": 0.12, + "learning_rate": 1.9576191005750323e-05, + "loss": 0.5194, + "step": 1410 + }, + { + "epoch": 0.12, + "learning_rate": 1.957539519685577e-05, + "loss": 0.4981, + "step": 1411 + }, + { + "epoch": 0.12, + "learning_rate": 1.9574598657701604e-05, + "loss": 0.5123, + "step": 1412 + }, + { + "epoch": 0.12, + "learning_rate": 1.9573801388348572e-05, + "loss": 0.5247, + "step": 1413 + }, + { + "epoch": 0.12, + "learning_rate": 1.9573003388857476e-05, + "loss": 0.511, + "step": 1414 + }, + { + "epoch": 0.12, + "learning_rate": 1.9572204659289175e-05, + "loss": 0.4892, + "step": 1415 + }, + { + "epoch": 0.12, + "learning_rate": 1.9571405199704583e-05, + "loss": 0.4881, + "step": 1416 + }, + { + "epoch": 0.12, + "learning_rate": 1.9570605010164676e-05, + "loss": 0.5239, + "step": 1417 + }, + { + "epoch": 0.12, + "learning_rate": 1.9569804090730467e-05, + "loss": 0.4915, + "step": 1418 + }, + { + "epoch": 0.12, + "learning_rate": 1.956900244146305e-05, + "loss": 0.5199, + "step": 1419 + }, + { + "epoch": 0.12, + "learning_rate": 1.9568200062423557e-05, + "loss": 0.5163, + "step": 1420 + }, + { + "epoch": 0.12, + "learning_rate": 1.956739695367318e-05, + "loss": 0.5048, + "step": 1421 + }, + { + "epoch": 0.12, + "learning_rate": 1.956659311527317e-05, + "loss": 0.5159, + "step": 1422 + }, + { + "epoch": 0.12, + "learning_rate": 1.956578854728483e-05, + "loss": 0.5132, + "step": 1423 + }, + { + "epoch": 0.12, + "learning_rate": 1.9564983249769518e-05, + "loss": 0.501, + "step": 1424 + }, + { + "epoch": 0.12, + "learning_rate": 1.956417722278865e-05, + "loss": 0.5169, + "step": 1425 + }, + { + "epoch": 0.12, + "learning_rate": 1.95633704664037e-05, + "loss": 0.5049, + "step": 1426 + }, + { + "epoch": 0.12, + "learning_rate": 1.956256298067619e-05, + "loss": 0.5289, + "step": 1427 + }, + { + "epoch": 0.12, + "learning_rate": 1.9561754765667705e-05, + "loss": 0.4981, + "step": 1428 + }, + { + "epoch": 0.12, + "learning_rate": 1.9560945821439885e-05, + "loss": 0.5076, + "step": 1429 + }, + { + "epoch": 0.12, + "learning_rate": 1.956013614805442e-05, + "loss": 0.5086, + "step": 1430 + }, + { + "epoch": 0.12, + "learning_rate": 1.955932574557306e-05, + "loss": 0.5008, + "step": 1431 + }, + { + "epoch": 0.12, + "learning_rate": 1.955851461405761e-05, + "loss": 0.5087, + "step": 1432 + }, + { + "epoch": 0.12, + "learning_rate": 1.955770275356993e-05, + "loss": 0.4964, + "step": 1433 + }, + { + "epoch": 0.12, + "learning_rate": 1.9556890164171934e-05, + "loss": 0.4778, + "step": 1434 + }, + { + "epoch": 0.12, + "learning_rate": 1.9556076845925596e-05, + "loss": 0.5298, + "step": 1435 + }, + { + "epoch": 0.12, + "learning_rate": 1.9555262798892943e-05, + "loss": 0.5146, + "step": 1436 + }, + { + "epoch": 0.12, + "learning_rate": 1.9554448023136056e-05, + "loss": 0.4963, + "step": 1437 + }, + { + "epoch": 0.12, + "learning_rate": 1.9553632518717074e-05, + "loss": 0.5254, + "step": 1438 + }, + { + "epoch": 0.12, + "learning_rate": 1.9552816285698193e-05, + "loss": 0.4904, + "step": 1439 + }, + { + "epoch": 0.12, + "learning_rate": 1.9551999324141656e-05, + "loss": 0.5027, + "step": 1440 + }, + { + "epoch": 0.12, + "learning_rate": 1.9551181634109774e-05, + "loss": 0.5009, + "step": 1441 + }, + { + "epoch": 0.12, + "learning_rate": 1.9550363215664906e-05, + "loss": 0.5114, + "step": 1442 + }, + { + "epoch": 0.12, + "learning_rate": 1.954954406886947e-05, + "loss": 0.5179, + "step": 1443 + }, + { + "epoch": 0.12, + "learning_rate": 1.9548724193785933e-05, + "loss": 0.4971, + "step": 1444 + }, + { + "epoch": 0.12, + "learning_rate": 1.9547903590476823e-05, + "loss": 0.5075, + "step": 1445 + }, + { + "epoch": 0.12, + "learning_rate": 1.9547082259004727e-05, + "loss": 0.5185, + "step": 1446 + }, + { + "epoch": 0.12, + "learning_rate": 1.9546260199432278e-05, + "loss": 0.5054, + "step": 1447 + }, + { + "epoch": 0.12, + "learning_rate": 1.9545437411822173e-05, + "loss": 0.4896, + "step": 1448 + }, + { + "epoch": 0.12, + "learning_rate": 1.954461389623716e-05, + "loss": 0.5216, + "step": 1449 + }, + { + "epoch": 0.12, + "learning_rate": 1.9543789652740043e-05, + "loss": 0.4931, + "step": 1450 + }, + { + "epoch": 0.12, + "learning_rate": 1.954296468139368e-05, + "loss": 0.5127, + "step": 1451 + }, + { + "epoch": 0.12, + "learning_rate": 1.9542138982260993e-05, + "loss": 0.5051, + "step": 1452 + }, + { + "epoch": 0.12, + "learning_rate": 1.954131255540495e-05, + "loss": 0.4972, + "step": 1453 + }, + { + "epoch": 0.12, + "learning_rate": 1.9540485400888577e-05, + "loss": 0.5035, + "step": 1454 + }, + { + "epoch": 0.12, + "learning_rate": 1.953965751877496e-05, + "loss": 0.5207, + "step": 1455 + }, + { + "epoch": 0.12, + "learning_rate": 1.953882890912723e-05, + "loss": 0.5301, + "step": 1456 + }, + { + "epoch": 0.12, + "learning_rate": 1.9537999572008585e-05, + "loss": 0.504, + "step": 1457 + }, + { + "epoch": 0.12, + "learning_rate": 1.953716950748227e-05, + "loss": 0.527, + "step": 1458 + }, + { + "epoch": 0.12, + "learning_rate": 1.9536338715611593e-05, + "loss": 0.5257, + "step": 1459 + }, + { + "epoch": 0.12, + "learning_rate": 1.9535507196459916e-05, + "loss": 0.4934, + "step": 1460 + }, + { + "epoch": 0.12, + "learning_rate": 1.953467495009065e-05, + "loss": 0.5234, + "step": 1461 + }, + { + "epoch": 0.12, + "learning_rate": 1.9533841976567265e-05, + "loss": 0.4902, + "step": 1462 + }, + { + "epoch": 0.12, + "learning_rate": 1.9533008275953288e-05, + "loss": 0.4986, + "step": 1463 + }, + { + "epoch": 0.12, + "learning_rate": 1.95321738483123e-05, + "loss": 0.5077, + "step": 1464 + }, + { + "epoch": 0.12, + "learning_rate": 1.953133869370794e-05, + "loss": 0.5161, + "step": 1465 + }, + { + "epoch": 0.12, + "learning_rate": 1.95305028122039e-05, + "loss": 0.5025, + "step": 1466 + }, + { + "epoch": 0.13, + "learning_rate": 1.9529666203863924e-05, + "loss": 0.5138, + "step": 1467 + }, + { + "epoch": 0.13, + "learning_rate": 1.952882886875182e-05, + "loss": 0.5163, + "step": 1468 + }, + { + "epoch": 0.13, + "learning_rate": 1.9527990806931446e-05, + "loss": 0.4974, + "step": 1469 + }, + { + "epoch": 0.13, + "learning_rate": 1.952715201846671e-05, + "loss": 0.514, + "step": 1470 + }, + { + "epoch": 0.13, + "learning_rate": 1.952631250342159e-05, + "loss": 0.4994, + "step": 1471 + }, + { + "epoch": 0.13, + "learning_rate": 1.9525472261860112e-05, + "loss": 0.5086, + "step": 1472 + }, + { + "epoch": 0.13, + "learning_rate": 1.9524631293846342e-05, + "loss": 0.4978, + "step": 1473 + }, + { + "epoch": 0.13, + "learning_rate": 1.952378959944443e-05, + "loss": 0.5133, + "step": 1474 + }, + { + "epoch": 0.13, + "learning_rate": 1.9522947178718566e-05, + "loss": 0.4913, + "step": 1475 + }, + { + "epoch": 0.13, + "learning_rate": 1.952210403173299e-05, + "loss": 0.5016, + "step": 1476 + }, + { + "epoch": 0.13, + "learning_rate": 1.9521260158552004e-05, + "loss": 0.5344, + "step": 1477 + }, + { + "epoch": 0.13, + "learning_rate": 1.9520415559239973e-05, + "loss": 0.5008, + "step": 1478 + }, + { + "epoch": 0.13, + "learning_rate": 1.9519570233861304e-05, + "loss": 0.5213, + "step": 1479 + }, + { + "epoch": 0.13, + "learning_rate": 1.951872418248046e-05, + "loss": 0.5094, + "step": 1480 + }, + { + "epoch": 0.13, + "learning_rate": 1.9517877405161976e-05, + "loss": 0.5254, + "step": 1481 + }, + { + "epoch": 0.13, + "learning_rate": 1.9517029901970426e-05, + "loss": 0.5087, + "step": 1482 + }, + { + "epoch": 0.13, + "learning_rate": 1.9516181672970444e-05, + "loss": 0.5104, + "step": 1483 + }, + { + "epoch": 0.13, + "learning_rate": 1.9515332718226714e-05, + "loss": 0.5344, + "step": 1484 + }, + { + "epoch": 0.13, + "learning_rate": 1.951448303780399e-05, + "loss": 0.5017, + "step": 1485 + }, + { + "epoch": 0.13, + "learning_rate": 1.9513632631767062e-05, + "loss": 0.5147, + "step": 1486 + }, + { + "epoch": 0.13, + "learning_rate": 1.9512781500180797e-05, + "loss": 0.4982, + "step": 1487 + }, + { + "epoch": 0.13, + "learning_rate": 1.9511929643110095e-05, + "loss": 0.5073, + "step": 1488 + }, + { + "epoch": 0.13, + "learning_rate": 1.9511077060619933e-05, + "loss": 0.4984, + "step": 1489 + }, + { + "epoch": 0.13, + "learning_rate": 1.9510223752775322e-05, + "loss": 0.5403, + "step": 1490 + }, + { + "epoch": 0.13, + "learning_rate": 1.9509369719641345e-05, + "loss": 0.5212, + "step": 1491 + }, + { + "epoch": 0.13, + "learning_rate": 1.950851496128314e-05, + "loss": 0.482, + "step": 1492 + }, + { + "epoch": 0.13, + "learning_rate": 1.9507659477765875e-05, + "loss": 0.4981, + "step": 1493 + }, + { + "epoch": 0.13, + "learning_rate": 1.950680326915481e-05, + "loss": 0.4959, + "step": 1494 + }, + { + "epoch": 0.13, + "learning_rate": 1.950594633551524e-05, + "loss": 0.5331, + "step": 1495 + }, + { + "epoch": 0.13, + "learning_rate": 1.9505088676912517e-05, + "loss": 0.5037, + "step": 1496 + }, + { + "epoch": 0.13, + "learning_rate": 1.9504230293412044e-05, + "loss": 0.5246, + "step": 1497 + }, + { + "epoch": 0.13, + "learning_rate": 1.9503371185079295e-05, + "loss": 0.5028, + "step": 1498 + }, + { + "epoch": 0.13, + "learning_rate": 1.9502511351979783e-05, + "loss": 0.5004, + "step": 1499 + }, + { + "epoch": 0.13, + "learning_rate": 1.950165079417908e-05, + "loss": 0.4949, + "step": 1500 + }, + { + "epoch": 0.13, + "learning_rate": 1.9500789511742824e-05, + "loss": 0.4884, + "step": 1501 + }, + { + "epoch": 0.13, + "learning_rate": 1.949992750473669e-05, + "loss": 0.5061, + "step": 1502 + }, + { + "epoch": 0.13, + "learning_rate": 1.949906477322643e-05, + "loss": 0.4889, + "step": 1503 + }, + { + "epoch": 0.13, + "learning_rate": 1.949820131727783e-05, + "loss": 0.5181, + "step": 1504 + }, + { + "epoch": 0.13, + "learning_rate": 1.949733713695674e-05, + "loss": 0.5214, + "step": 1505 + }, + { + "epoch": 0.13, + "learning_rate": 1.9496472232329075e-05, + "loss": 0.5063, + "step": 1506 + }, + { + "epoch": 0.13, + "learning_rate": 1.949560660346079e-05, + "loss": 0.5233, + "step": 1507 + }, + { + "epoch": 0.13, + "learning_rate": 1.9494740250417902e-05, + "loss": 0.4995, + "step": 1508 + }, + { + "epoch": 0.13, + "learning_rate": 1.949387317326648e-05, + "loss": 0.509, + "step": 1509 + }, + { + "epoch": 0.13, + "learning_rate": 1.9493005372072654e-05, + "loss": 0.5061, + "step": 1510 + }, + { + "epoch": 0.13, + "learning_rate": 1.949213684690261e-05, + "loss": 0.5161, + "step": 1511 + }, + { + "epoch": 0.13, + "learning_rate": 1.949126759782258e-05, + "loss": 0.5118, + "step": 1512 + }, + { + "epoch": 0.13, + "learning_rate": 1.949039762489886e-05, + "loss": 0.5203, + "step": 1513 + }, + { + "epoch": 0.13, + "learning_rate": 1.9489526928197794e-05, + "loss": 0.493, + "step": 1514 + }, + { + "epoch": 0.13, + "learning_rate": 1.9488655507785788e-05, + "loss": 0.5052, + "step": 1515 + }, + { + "epoch": 0.13, + "learning_rate": 1.9487783363729297e-05, + "loss": 0.5194, + "step": 1516 + }, + { + "epoch": 0.13, + "learning_rate": 1.9486910496094836e-05, + "loss": 0.5041, + "step": 1517 + }, + { + "epoch": 0.13, + "learning_rate": 1.948603690494898e-05, + "loss": 0.4879, + "step": 1518 + }, + { + "epoch": 0.13, + "learning_rate": 1.948516259035834e-05, + "loss": 0.5291, + "step": 1519 + }, + { + "epoch": 0.13, + "learning_rate": 1.9484287552389603e-05, + "loss": 0.5152, + "step": 1520 + }, + { + "epoch": 0.13, + "learning_rate": 1.94834117911095e-05, + "loss": 0.4992, + "step": 1521 + }, + { + "epoch": 0.13, + "learning_rate": 1.9482535306584826e-05, + "loss": 0.4955, + "step": 1522 + }, + { + "epoch": 0.13, + "learning_rate": 1.9481658098882418e-05, + "loss": 0.5095, + "step": 1523 + }, + { + "epoch": 0.13, + "learning_rate": 1.948078016806918e-05, + "loss": 0.5112, + "step": 1524 + }, + { + "epoch": 0.13, + "learning_rate": 1.9479901514212068e-05, + "loss": 0.4833, + "step": 1525 + }, + { + "epoch": 0.13, + "learning_rate": 1.9479022137378086e-05, + "loss": 0.5217, + "step": 1526 + }, + { + "epoch": 0.13, + "learning_rate": 1.94781420376343e-05, + "loss": 0.5116, + "step": 1527 + }, + { + "epoch": 0.13, + "learning_rate": 1.9477261215047836e-05, + "loss": 0.507, + "step": 1528 + }, + { + "epoch": 0.13, + "learning_rate": 1.9476379669685862e-05, + "loss": 0.507, + "step": 1529 + }, + { + "epoch": 0.13, + "learning_rate": 1.9475497401615615e-05, + "loss": 0.5229, + "step": 1530 + }, + { + "epoch": 0.13, + "learning_rate": 1.9474614410904373e-05, + "loss": 0.4816, + "step": 1531 + }, + { + "epoch": 0.13, + "learning_rate": 1.9473730697619485e-05, + "loss": 0.5025, + "step": 1532 + }, + { + "epoch": 0.13, + "learning_rate": 1.947284626182834e-05, + "loss": 0.5171, + "step": 1533 + }, + { + "epoch": 0.13, + "learning_rate": 1.947196110359839e-05, + "loss": 0.5344, + "step": 1534 + }, + { + "epoch": 0.13, + "learning_rate": 1.9471075222997147e-05, + "loss": 0.5041, + "step": 1535 + }, + { + "epoch": 0.13, + "learning_rate": 1.9470188620092162e-05, + "loss": 0.5024, + "step": 1536 + }, + { + "epoch": 0.13, + "learning_rate": 1.946930129495106e-05, + "loss": 0.5036, + "step": 1537 + }, + { + "epoch": 0.13, + "learning_rate": 1.9468413247641504e-05, + "loss": 0.4889, + "step": 1538 + }, + { + "epoch": 0.13, + "learning_rate": 1.9467524478231226e-05, + "loss": 0.5126, + "step": 1539 + }, + { + "epoch": 0.13, + "learning_rate": 1.9466634986788007e-05, + "loss": 0.5023, + "step": 1540 + }, + { + "epoch": 0.13, + "learning_rate": 1.946574477337968e-05, + "loss": 0.505, + "step": 1541 + }, + { + "epoch": 0.13, + "learning_rate": 1.946485383807414e-05, + "loss": 0.4907, + "step": 1542 + }, + { + "epoch": 0.13, + "learning_rate": 1.9463962180939327e-05, + "loss": 0.533, + "step": 1543 + }, + { + "epoch": 0.13, + "learning_rate": 1.946306980204325e-05, + "loss": 0.5035, + "step": 1544 + }, + { + "epoch": 0.13, + "learning_rate": 1.9462176701453966e-05, + "loss": 0.502, + "step": 1545 + }, + { + "epoch": 0.13, + "learning_rate": 1.946128287923958e-05, + "loss": 0.5216, + "step": 1546 + }, + { + "epoch": 0.13, + "learning_rate": 1.9460388335468264e-05, + "loss": 0.5006, + "step": 1547 + }, + { + "epoch": 0.13, + "learning_rate": 1.9459493070208237e-05, + "loss": 0.5169, + "step": 1548 + }, + { + "epoch": 0.13, + "learning_rate": 1.9458597083527774e-05, + "loss": 0.5176, + "step": 1549 + }, + { + "epoch": 0.13, + "learning_rate": 1.9457700375495213e-05, + "loss": 0.5154, + "step": 1550 + }, + { + "epoch": 0.13, + "learning_rate": 1.945680294617893e-05, + "loss": 0.5126, + "step": 1551 + }, + { + "epoch": 0.13, + "learning_rate": 1.945590479564738e-05, + "loss": 0.5286, + "step": 1552 + }, + { + "epoch": 0.13, + "learning_rate": 1.945500592396905e-05, + "loss": 0.4953, + "step": 1553 + }, + { + "epoch": 0.13, + "learning_rate": 1.9454106331212495e-05, + "loss": 0.4962, + "step": 1554 + }, + { + "epoch": 0.13, + "learning_rate": 1.9453206017446326e-05, + "loss": 0.5281, + "step": 1555 + }, + { + "epoch": 0.13, + "learning_rate": 1.9452304982739194e-05, + "loss": 0.4953, + "step": 1556 + }, + { + "epoch": 0.13, + "learning_rate": 1.9451403227159823e-05, + "loss": 0.5036, + "step": 1557 + }, + { + "epoch": 0.13, + "learning_rate": 1.9450500750776987e-05, + "loss": 0.5283, + "step": 1558 + }, + { + "epoch": 0.13, + "learning_rate": 1.9449597553659504e-05, + "loss": 0.521, + "step": 1559 + }, + { + "epoch": 0.13, + "learning_rate": 1.9448693635876266e-05, + "loss": 0.5128, + "step": 1560 + }, + { + "epoch": 0.13, + "learning_rate": 1.94477889974962e-05, + "loss": 0.5108, + "step": 1561 + }, + { + "epoch": 0.13, + "learning_rate": 1.9446883638588302e-05, + "loss": 0.5269, + "step": 1562 + }, + { + "epoch": 0.13, + "learning_rate": 1.944597755922162e-05, + "loss": 0.4938, + "step": 1563 + }, + { + "epoch": 0.13, + "learning_rate": 1.9445070759465254e-05, + "loss": 0.517, + "step": 1564 + }, + { + "epoch": 0.13, + "learning_rate": 1.9444163239388358e-05, + "loss": 0.4946, + "step": 1565 + }, + { + "epoch": 0.13, + "learning_rate": 1.9443254999060147e-05, + "loss": 0.5143, + "step": 1566 + }, + { + "epoch": 0.13, + "learning_rate": 1.9442346038549883e-05, + "loss": 0.492, + "step": 1567 + }, + { + "epoch": 0.13, + "learning_rate": 1.9441436357926892e-05, + "loss": 0.4882, + "step": 1568 + }, + { + "epoch": 0.13, + "learning_rate": 1.9440525957260546e-05, + "loss": 0.5047, + "step": 1569 + }, + { + "epoch": 0.13, + "learning_rate": 1.9439614836620277e-05, + "loss": 0.4896, + "step": 1570 + }, + { + "epoch": 0.13, + "learning_rate": 1.943870299607557e-05, + "loss": 0.5088, + "step": 1571 + }, + { + "epoch": 0.13, + "learning_rate": 1.9437790435695972e-05, + "loss": 0.4999, + "step": 1572 + }, + { + "epoch": 0.13, + "learning_rate": 1.943687715555107e-05, + "loss": 0.526, + "step": 1573 + }, + { + "epoch": 0.13, + "learning_rate": 1.943596315571052e-05, + "loss": 0.4953, + "step": 1574 + }, + { + "epoch": 0.13, + "learning_rate": 1.9435048436244025e-05, + "loss": 0.5021, + "step": 1575 + }, + { + "epoch": 0.13, + "learning_rate": 1.9434132997221347e-05, + "loss": 0.5087, + "step": 1576 + }, + { + "epoch": 0.13, + "learning_rate": 1.94332168387123e-05, + "loss": 0.4946, + "step": 1577 + }, + { + "epoch": 0.13, + "learning_rate": 1.9432299960786752e-05, + "loss": 0.5034, + "step": 1578 + }, + { + "epoch": 0.13, + "learning_rate": 1.9431382363514634e-05, + "loss": 0.4982, + "step": 1579 + }, + { + "epoch": 0.13, + "learning_rate": 1.943046404696592e-05, + "loss": 0.5016, + "step": 1580 + }, + { + "epoch": 0.13, + "learning_rate": 1.9429545011210648e-05, + "loss": 0.5052, + "step": 1581 + }, + { + "epoch": 0.13, + "learning_rate": 1.9428625256318906e-05, + "loss": 0.5365, + "step": 1582 + }, + { + "epoch": 0.13, + "learning_rate": 1.9427704782360838e-05, + "loss": 0.5022, + "step": 1583 + }, + { + "epoch": 0.14, + "learning_rate": 1.9426783589406645e-05, + "loss": 0.4963, + "step": 1584 + }, + { + "epoch": 0.14, + "learning_rate": 1.9425861677526577e-05, + "loss": 0.5082, + "step": 1585 + }, + { + "epoch": 0.14, + "learning_rate": 1.9424939046790948e-05, + "loss": 0.4982, + "step": 1586 + }, + { + "epoch": 0.14, + "learning_rate": 1.942401569727012e-05, + "loss": 0.5097, + "step": 1587 + }, + { + "epoch": 0.14, + "learning_rate": 1.9423091629034506e-05, + "loss": 0.505, + "step": 1588 + }, + { + "epoch": 0.14, + "learning_rate": 1.9422166842154592e-05, + "loss": 0.4979, + "step": 1589 + }, + { + "epoch": 0.14, + "learning_rate": 1.942124133670089e-05, + "loss": 0.5126, + "step": 1590 + }, + { + "epoch": 0.14, + "learning_rate": 1.9420315112743997e-05, + "loss": 0.5266, + "step": 1591 + }, + { + "epoch": 0.14, + "learning_rate": 1.9419388170354544e-05, + "loss": 0.5105, + "step": 1592 + }, + { + "epoch": 0.14, + "learning_rate": 1.941846050960322e-05, + "loss": 0.4983, + "step": 1593 + }, + { + "epoch": 0.14, + "learning_rate": 1.9417532130560784e-05, + "loss": 0.5085, + "step": 1594 + }, + { + "epoch": 0.14, + "learning_rate": 1.9416603033298025e-05, + "loss": 0.4955, + "step": 1595 + }, + { + "epoch": 0.14, + "learning_rate": 1.941567321788581e-05, + "loss": 0.5116, + "step": 1596 + }, + { + "epoch": 0.14, + "learning_rate": 1.941474268439504e-05, + "loss": 0.4856, + "step": 1597 + }, + { + "epoch": 0.14, + "learning_rate": 1.9413811432896693e-05, + "loss": 0.5122, + "step": 1598 + }, + { + "epoch": 0.14, + "learning_rate": 1.9412879463461783e-05, + "loss": 0.4962, + "step": 1599 + }, + { + "epoch": 0.14, + "learning_rate": 1.9411946776161388e-05, + "loss": 0.486, + "step": 1600 + }, + { + "epoch": 0.14, + "learning_rate": 1.9411013371066635e-05, + "loss": 0.519, + "step": 1601 + }, + { + "epoch": 0.14, + "learning_rate": 1.9410079248248716e-05, + "loss": 0.4986, + "step": 1602 + }, + { + "epoch": 0.14, + "learning_rate": 1.9409144407778866e-05, + "loss": 0.5251, + "step": 1603 + }, + { + "epoch": 0.14, + "learning_rate": 1.9408208849728382e-05, + "loss": 0.4898, + "step": 1604 + }, + { + "epoch": 0.14, + "learning_rate": 1.940727257416861e-05, + "loss": 0.5062, + "step": 1605 + }, + { + "epoch": 0.14, + "learning_rate": 1.9406335581170962e-05, + "loss": 0.4815, + "step": 1606 + }, + { + "epoch": 0.14, + "learning_rate": 1.9405397870806893e-05, + "loss": 0.5015, + "step": 1607 + }, + { + "epoch": 0.14, + "learning_rate": 1.9404459443147914e-05, + "loss": 0.5237, + "step": 1608 + }, + { + "epoch": 0.14, + "learning_rate": 1.9403520298265596e-05, + "loss": 0.4905, + "step": 1609 + }, + { + "epoch": 0.14, + "learning_rate": 1.940258043623156e-05, + "loss": 0.5201, + "step": 1610 + }, + { + "epoch": 0.14, + "learning_rate": 1.9401639857117485e-05, + "loss": 0.5019, + "step": 1611 + }, + { + "epoch": 0.14, + "learning_rate": 1.9400698560995105e-05, + "loss": 0.5239, + "step": 1612 + }, + { + "epoch": 0.14, + "learning_rate": 1.9399756547936205e-05, + "loss": 0.5036, + "step": 1613 + }, + { + "epoch": 0.14, + "learning_rate": 1.939881381801263e-05, + "loss": 0.4994, + "step": 1614 + }, + { + "epoch": 0.14, + "learning_rate": 1.9397870371296273e-05, + "loss": 0.4887, + "step": 1615 + }, + { + "epoch": 0.14, + "learning_rate": 1.9396926207859085e-05, + "loss": 0.487, + "step": 1616 + }, + { + "epoch": 0.14, + "learning_rate": 1.9395981327773077e-05, + "loss": 0.5184, + "step": 1617 + }, + { + "epoch": 0.14, + "learning_rate": 1.93950357311103e-05, + "loss": 0.5036, + "step": 1618 + }, + { + "epoch": 0.14, + "learning_rate": 1.939408941794288e-05, + "loss": 0.5139, + "step": 1619 + }, + { + "epoch": 0.14, + "learning_rate": 1.9393142388342984e-05, + "loss": 0.51, + "step": 1620 + }, + { + "epoch": 0.14, + "learning_rate": 1.939219464238283e-05, + "loss": 0.5078, + "step": 1621 + }, + { + "epoch": 0.14, + "learning_rate": 1.9391246180134703e-05, + "loss": 0.5102, + "step": 1622 + }, + { + "epoch": 0.14, + "learning_rate": 1.9390297001670933e-05, + "loss": 0.4985, + "step": 1623 + }, + { + "epoch": 0.14, + "learning_rate": 1.938934710706391e-05, + "loss": 0.5231, + "step": 1624 + }, + { + "epoch": 0.14, + "learning_rate": 1.9388396496386082e-05, + "loss": 0.478, + "step": 1625 + }, + { + "epoch": 0.14, + "learning_rate": 1.938744516970994e-05, + "loss": 0.5165, + "step": 1626 + }, + { + "epoch": 0.14, + "learning_rate": 1.9386493127108033e-05, + "loss": 0.4875, + "step": 1627 + }, + { + "epoch": 0.14, + "learning_rate": 1.9385540368652976e-05, + "loss": 0.5033, + "step": 1628 + }, + { + "epoch": 0.14, + "learning_rate": 1.9384586894417426e-05, + "loss": 0.4988, + "step": 1629 + }, + { + "epoch": 0.14, + "learning_rate": 1.9383632704474103e-05, + "loss": 0.5032, + "step": 1630 + }, + { + "epoch": 0.14, + "learning_rate": 1.9382677798895774e-05, + "loss": 0.5135, + "step": 1631 + }, + { + "epoch": 0.14, + "learning_rate": 1.9381722177755266e-05, + "loss": 0.4964, + "step": 1632 + }, + { + "epoch": 0.14, + "learning_rate": 1.938076584112545e-05, + "loss": 0.4969, + "step": 1633 + }, + { + "epoch": 0.14, + "learning_rate": 1.9379808789079274e-05, + "loss": 0.4942, + "step": 1634 + }, + { + "epoch": 0.14, + "learning_rate": 1.9378851021689716e-05, + "loss": 0.5281, + "step": 1635 + }, + { + "epoch": 0.14, + "learning_rate": 1.9377892539029827e-05, + "loss": 0.5014, + "step": 1636 + }, + { + "epoch": 0.14, + "learning_rate": 1.9376933341172702e-05, + "loss": 0.5078, + "step": 1637 + }, + { + "epoch": 0.14, + "learning_rate": 1.937597342819149e-05, + "loss": 0.5278, + "step": 1638 + }, + { + "epoch": 0.14, + "learning_rate": 1.9375012800159404e-05, + "loss": 0.4974, + "step": 1639 + }, + { + "epoch": 0.14, + "learning_rate": 1.93740514571497e-05, + "loss": 0.5041, + "step": 1640 + }, + { + "epoch": 0.14, + "learning_rate": 1.9373089399235697e-05, + "loss": 0.4875, + "step": 1641 + }, + { + "epoch": 0.14, + "learning_rate": 1.9372126626490763e-05, + "loss": 0.495, + "step": 1642 + }, + { + "epoch": 0.14, + "learning_rate": 1.937116313898833e-05, + "loss": 0.5046, + "step": 1643 + }, + { + "epoch": 0.14, + "learning_rate": 1.9370198936801866e-05, + "loss": 0.5349, + "step": 1644 + }, + { + "epoch": 0.14, + "learning_rate": 1.9369234020004916e-05, + "loss": 0.4882, + "step": 1645 + }, + { + "epoch": 0.14, + "learning_rate": 1.9368268388671064e-05, + "loss": 0.4977, + "step": 1646 + }, + { + "epoch": 0.14, + "learning_rate": 1.9367302042873954e-05, + "loss": 0.5019, + "step": 1647 + }, + { + "epoch": 0.14, + "learning_rate": 1.936633498268728e-05, + "loss": 0.4955, + "step": 1648 + }, + { + "epoch": 0.14, + "learning_rate": 1.93653672081848e-05, + "loss": 0.5078, + "step": 1649 + }, + { + "epoch": 0.14, + "learning_rate": 1.9364398719440314e-05, + "loss": 0.4849, + "step": 1650 + }, + { + "epoch": 0.14, + "learning_rate": 1.936342951652769e-05, + "loss": 0.4819, + "step": 1651 + }, + { + "epoch": 0.14, + "learning_rate": 1.9362459599520837e-05, + "loss": 0.5137, + "step": 1652 + }, + { + "epoch": 0.14, + "learning_rate": 1.936148896849373e-05, + "loss": 0.4875, + "step": 1653 + }, + { + "epoch": 0.14, + "learning_rate": 1.936051762352039e-05, + "loss": 0.5181, + "step": 1654 + }, + { + "epoch": 0.14, + "learning_rate": 1.9359545564674897e-05, + "loss": 0.4796, + "step": 1655 + }, + { + "epoch": 0.14, + "learning_rate": 1.9358572792031386e-05, + "loss": 0.5051, + "step": 1656 + }, + { + "epoch": 0.14, + "learning_rate": 1.935759930566404e-05, + "loss": 0.4987, + "step": 1657 + }, + { + "epoch": 0.14, + "learning_rate": 1.9356625105647108e-05, + "loss": 0.5108, + "step": 1658 + }, + { + "epoch": 0.14, + "learning_rate": 1.935565019205488e-05, + "loss": 0.5001, + "step": 1659 + }, + { + "epoch": 0.14, + "learning_rate": 1.935467456496171e-05, + "loss": 0.527, + "step": 1660 + }, + { + "epoch": 0.14, + "learning_rate": 1.9353698224442005e-05, + "loss": 0.5062, + "step": 1661 + }, + { + "epoch": 0.14, + "learning_rate": 1.935272117057022e-05, + "loss": 0.4892, + "step": 1662 + }, + { + "epoch": 0.14, + "learning_rate": 1.9351743403420875e-05, + "loss": 0.5036, + "step": 1663 + }, + { + "epoch": 0.14, + "learning_rate": 1.9350764923068533e-05, + "loss": 0.501, + "step": 1664 + }, + { + "epoch": 0.14, + "learning_rate": 1.934978572958782e-05, + "loss": 0.5058, + "step": 1665 + }, + { + "epoch": 0.14, + "learning_rate": 1.9348805823053415e-05, + "loss": 0.5021, + "step": 1666 + }, + { + "epoch": 0.14, + "learning_rate": 1.934782520354005e-05, + "loss": 0.515, + "step": 1667 + }, + { + "epoch": 0.14, + "learning_rate": 1.9346843871122503e-05, + "loss": 0.5095, + "step": 1668 + }, + { + "epoch": 0.14, + "learning_rate": 1.934586182587562e-05, + "loss": 0.5093, + "step": 1669 + }, + { + "epoch": 0.14, + "learning_rate": 1.93448790678743e-05, + "loss": 0.5019, + "step": 1670 + }, + { + "epoch": 0.14, + "learning_rate": 1.934389559719349e-05, + "loss": 0.4919, + "step": 1671 + }, + { + "epoch": 0.14, + "learning_rate": 1.934291141390819e-05, + "loss": 0.5212, + "step": 1672 + }, + { + "epoch": 0.14, + "learning_rate": 1.9341926518093462e-05, + "loss": 0.5049, + "step": 1673 + }, + { + "epoch": 0.14, + "learning_rate": 1.9340940909824414e-05, + "loss": 0.5141, + "step": 1674 + }, + { + "epoch": 0.14, + "learning_rate": 1.9339954589176215e-05, + "loss": 0.5037, + "step": 1675 + }, + { + "epoch": 0.14, + "learning_rate": 1.9338967556224085e-05, + "loss": 0.4966, + "step": 1676 + }, + { + "epoch": 0.14, + "learning_rate": 1.9337979811043303e-05, + "loss": 0.5076, + "step": 1677 + }, + { + "epoch": 0.14, + "learning_rate": 1.9336991353709195e-05, + "loss": 0.5042, + "step": 1678 + }, + { + "epoch": 0.14, + "learning_rate": 1.9336002184297145e-05, + "loss": 0.5344, + "step": 1679 + }, + { + "epoch": 0.14, + "learning_rate": 1.933501230288259e-05, + "loss": 0.5147, + "step": 1680 + }, + { + "epoch": 0.14, + "learning_rate": 1.9334021709541027e-05, + "loss": 0.4909, + "step": 1681 + }, + { + "epoch": 0.14, + "learning_rate": 1.9333030404348e-05, + "loss": 0.4842, + "step": 1682 + }, + { + "epoch": 0.14, + "learning_rate": 1.9332038387379112e-05, + "loss": 0.5004, + "step": 1683 + }, + { + "epoch": 0.14, + "learning_rate": 1.933104565871001e-05, + "loss": 0.5055, + "step": 1684 + }, + { + "epoch": 0.14, + "learning_rate": 1.9330052218416412e-05, + "loss": 0.4914, + "step": 1685 + }, + { + "epoch": 0.14, + "learning_rate": 1.9329058066574085e-05, + "loss": 0.5098, + "step": 1686 + }, + { + "epoch": 0.14, + "learning_rate": 1.932806320325884e-05, + "loss": 0.491, + "step": 1687 + }, + { + "epoch": 0.14, + "learning_rate": 1.932706762854655e-05, + "loss": 0.5093, + "step": 1688 + }, + { + "epoch": 0.14, + "learning_rate": 1.9326071342513143e-05, + "loss": 0.4916, + "step": 1689 + }, + { + "epoch": 0.14, + "learning_rate": 1.93250743452346e-05, + "loss": 0.5033, + "step": 1690 + }, + { + "epoch": 0.14, + "learning_rate": 1.932407663678696e-05, + "loss": 0.501, + "step": 1691 + }, + { + "epoch": 0.14, + "learning_rate": 1.9323078217246303e-05, + "loss": 0.494, + "step": 1692 + }, + { + "epoch": 0.14, + "learning_rate": 1.9322079086688786e-05, + "loss": 0.5108, + "step": 1693 + }, + { + "epoch": 0.14, + "learning_rate": 1.9321079245190596e-05, + "loss": 0.4903, + "step": 1694 + }, + { + "epoch": 0.14, + "learning_rate": 1.932007869282799e-05, + "loss": 0.5048, + "step": 1695 + }, + { + "epoch": 0.14, + "learning_rate": 1.931907742967727e-05, + "loss": 0.4966, + "step": 1696 + }, + { + "epoch": 0.14, + "learning_rate": 1.9318075455814798e-05, + "loss": 0.5033, + "step": 1697 + }, + { + "epoch": 0.14, + "learning_rate": 1.931707277131699e-05, + "loss": 0.5047, + "step": 1698 + }, + { + "epoch": 0.14, + "learning_rate": 1.9316069376260317e-05, + "loss": 0.5134, + "step": 1699 + }, + { + "epoch": 0.14, + "learning_rate": 1.93150652707213e-05, + "loss": 0.4979, + "step": 1700 + }, + { + "epoch": 0.15, + "learning_rate": 1.9314060454776515e-05, + "loss": 0.501, + "step": 1701 + }, + { + "epoch": 0.15, + "learning_rate": 1.9313054928502596e-05, + "loss": 0.5133, + "step": 1702 + }, + { + "epoch": 0.15, + "learning_rate": 1.9312048691976226e-05, + "loss": 0.4785, + "step": 1703 + }, + { + "epoch": 0.15, + "learning_rate": 1.9311041745274147e-05, + "loss": 0.5058, + "step": 1704 + }, + { + "epoch": 0.15, + "learning_rate": 1.9310034088473153e-05, + "loss": 0.4943, + "step": 1705 + }, + { + "epoch": 0.15, + "learning_rate": 1.9309025721650088e-05, + "loss": 0.512, + "step": 1706 + }, + { + "epoch": 0.15, + "learning_rate": 1.9308016644881862e-05, + "loss": 0.4938, + "step": 1707 + }, + { + "epoch": 0.15, + "learning_rate": 1.9307006858245424e-05, + "loss": 0.4792, + "step": 1708 + }, + { + "epoch": 0.15, + "learning_rate": 1.9305996361817788e-05, + "loss": 0.5187, + "step": 1709 + }, + { + "epoch": 0.15, + "learning_rate": 1.9304985155676017e-05, + "loss": 0.4903, + "step": 1710 + }, + { + "epoch": 0.15, + "learning_rate": 1.9303973239897233e-05, + "loss": 0.5133, + "step": 1711 + }, + { + "epoch": 0.15, + "learning_rate": 1.9302960614558604e-05, + "loss": 0.4935, + "step": 1712 + }, + { + "epoch": 0.15, + "learning_rate": 1.930194727973736e-05, + "loss": 0.495, + "step": 1713 + }, + { + "epoch": 0.15, + "learning_rate": 1.9300933235510786e-05, + "loss": 0.5201, + "step": 1714 + }, + { + "epoch": 0.15, + "learning_rate": 1.929991848195621e-05, + "loss": 0.4937, + "step": 1715 + }, + { + "epoch": 0.15, + "learning_rate": 1.9298903019151026e-05, + "loss": 0.5052, + "step": 1716 + }, + { + "epoch": 0.15, + "learning_rate": 1.9297886847172672e-05, + "loss": 0.5157, + "step": 1717 + }, + { + "epoch": 0.15, + "learning_rate": 1.9296869966098658e-05, + "loss": 0.5121, + "step": 1718 + }, + { + "epoch": 0.15, + "learning_rate": 1.9295852376006522e-05, + "loss": 0.5021, + "step": 1719 + }, + { + "epoch": 0.15, + "learning_rate": 1.9294834076973872e-05, + "loss": 0.4905, + "step": 1720 + }, + { + "epoch": 0.15, + "learning_rate": 1.9293815069078375e-05, + "loss": 0.5239, + "step": 1721 + }, + { + "epoch": 0.15, + "learning_rate": 1.9292795352397736e-05, + "loss": 0.4871, + "step": 1722 + }, + { + "epoch": 0.15, + "learning_rate": 1.9291774927009733e-05, + "loss": 0.5072, + "step": 1723 + }, + { + "epoch": 0.15, + "learning_rate": 1.9290753792992177e-05, + "loss": 0.4919, + "step": 1724 + }, + { + "epoch": 0.15, + "learning_rate": 1.928973195042295e-05, + "loss": 0.5225, + "step": 1725 + }, + { + "epoch": 0.15, + "learning_rate": 1.928870939937998e-05, + "loss": 0.4996, + "step": 1726 + }, + { + "epoch": 0.15, + "learning_rate": 1.9287686139941254e-05, + "loss": 0.5077, + "step": 1727 + }, + { + "epoch": 0.15, + "learning_rate": 1.928666217218481e-05, + "loss": 0.4987, + "step": 1728 + }, + { + "epoch": 0.15, + "learning_rate": 1.9285637496188734e-05, + "loss": 0.5089, + "step": 1729 + }, + { + "epoch": 0.15, + "learning_rate": 1.9284612112031177e-05, + "loss": 0.4908, + "step": 1730 + }, + { + "epoch": 0.15, + "learning_rate": 1.928358601979034e-05, + "loss": 0.5271, + "step": 1731 + }, + { + "epoch": 0.15, + "learning_rate": 1.9282559219544477e-05, + "loss": 0.521, + "step": 1732 + }, + { + "epoch": 0.15, + "learning_rate": 1.928153171137189e-05, + "loss": 0.5106, + "step": 1733 + }, + { + "epoch": 0.15, + "learning_rate": 1.928050349535095e-05, + "loss": 0.501, + "step": 1734 + }, + { + "epoch": 0.15, + "learning_rate": 1.9279474571560065e-05, + "loss": 0.5205, + "step": 1735 + }, + { + "epoch": 0.15, + "learning_rate": 1.927844494007771e-05, + "loss": 0.5125, + "step": 1736 + }, + { + "epoch": 0.15, + "learning_rate": 1.9277414600982406e-05, + "loss": 0.5279, + "step": 1737 + }, + { + "epoch": 0.15, + "learning_rate": 1.9276383554352734e-05, + "loss": 0.5009, + "step": 1738 + }, + { + "epoch": 0.15, + "learning_rate": 1.9275351800267324e-05, + "loss": 0.5015, + "step": 1739 + }, + { + "epoch": 0.15, + "learning_rate": 1.9274319338804862e-05, + "loss": 0.5024, + "step": 1740 + }, + { + "epoch": 0.15, + "learning_rate": 1.927328617004409e-05, + "loss": 0.5069, + "step": 1741 + }, + { + "epoch": 0.15, + "learning_rate": 1.92722522940638e-05, + "loss": 0.4976, + "step": 1742 + }, + { + "epoch": 0.15, + "learning_rate": 1.9271217710942836e-05, + "loss": 0.5267, + "step": 1743 + }, + { + "epoch": 0.15, + "learning_rate": 1.9270182420760104e-05, + "loss": 0.5467, + "step": 1744 + }, + { + "epoch": 0.15, + "learning_rate": 1.926914642359456e-05, + "loss": 0.5003, + "step": 1745 + }, + { + "epoch": 0.15, + "learning_rate": 1.9268109719525213e-05, + "loss": 0.5211, + "step": 1746 + }, + { + "epoch": 0.15, + "learning_rate": 1.9267072308631122e-05, + "loss": 0.5038, + "step": 1747 + }, + { + "epoch": 0.15, + "learning_rate": 1.9266034190991413e-05, + "loss": 0.5091, + "step": 1748 + }, + { + "epoch": 0.15, + "learning_rate": 1.9264995366685248e-05, + "loss": 0.4876, + "step": 1749 + }, + { + "epoch": 0.15, + "learning_rate": 1.926395583579186e-05, + "loss": 0.5159, + "step": 1750 + }, + { + "epoch": 0.15, + "learning_rate": 1.9262915598390518e-05, + "loss": 0.5073, + "step": 1751 + }, + { + "epoch": 0.15, + "learning_rate": 1.9261874654560565e-05, + "loss": 0.4935, + "step": 1752 + }, + { + "epoch": 0.15, + "learning_rate": 1.9260833004381384e-05, + "loss": 0.5116, + "step": 1753 + }, + { + "epoch": 0.15, + "learning_rate": 1.9259790647932416e-05, + "loss": 0.4953, + "step": 1754 + }, + { + "epoch": 0.15, + "learning_rate": 1.9258747585293154e-05, + "loss": 0.5114, + "step": 1755 + }, + { + "epoch": 0.15, + "learning_rate": 1.9257703816543144e-05, + "loss": 0.5212, + "step": 1756 + }, + { + "epoch": 0.15, + "learning_rate": 1.9256659341761995e-05, + "loss": 0.5111, + "step": 1757 + }, + { + "epoch": 0.15, + "learning_rate": 1.925561416102936e-05, + "loss": 0.5065, + "step": 1758 + }, + { + "epoch": 0.15, + "learning_rate": 1.9254568274424942e-05, + "loss": 0.5309, + "step": 1759 + }, + { + "epoch": 0.15, + "learning_rate": 1.9253521682028515e-05, + "loss": 0.4934, + "step": 1760 + }, + { + "epoch": 0.15, + "learning_rate": 1.9252474383919894e-05, + "loss": 0.4873, + "step": 1761 + }, + { + "epoch": 0.15, + "learning_rate": 1.9251426380178945e-05, + "loss": 0.502, + "step": 1762 + }, + { + "epoch": 0.15, + "learning_rate": 1.9250377670885597e-05, + "loss": 0.515, + "step": 1763 + }, + { + "epoch": 0.15, + "learning_rate": 1.924932825611983e-05, + "loss": 0.5066, + "step": 1764 + }, + { + "epoch": 0.15, + "learning_rate": 1.9248278135961676e-05, + "loss": 0.4908, + "step": 1765 + }, + { + "epoch": 0.15, + "learning_rate": 1.924722731049122e-05, + "loss": 0.5118, + "step": 1766 + }, + { + "epoch": 0.15, + "learning_rate": 1.9246175779788605e-05, + "loss": 0.501, + "step": 1767 + }, + { + "epoch": 0.15, + "learning_rate": 1.9245123543934017e-05, + "loss": 0.5069, + "step": 1768 + }, + { + "epoch": 0.15, + "learning_rate": 1.9244070603007718e-05, + "loss": 0.5065, + "step": 1769 + }, + { + "epoch": 0.15, + "learning_rate": 1.924301695709e-05, + "loss": 0.5097, + "step": 1770 + }, + { + "epoch": 0.15, + "learning_rate": 1.924196260626122e-05, + "loss": 0.4925, + "step": 1771 + }, + { + "epoch": 0.15, + "learning_rate": 1.9240907550601787e-05, + "loss": 0.4906, + "step": 1772 + }, + { + "epoch": 0.15, + "learning_rate": 1.9239851790192166e-05, + "loss": 0.5292, + "step": 1773 + }, + { + "epoch": 0.15, + "learning_rate": 1.9238795325112867e-05, + "loss": 0.4998, + "step": 1774 + }, + { + "epoch": 0.15, + "learning_rate": 1.9237738155444472e-05, + "loss": 0.4931, + "step": 1775 + }, + { + "epoch": 0.15, + "learning_rate": 1.9236680281267594e-05, + "loss": 0.5106, + "step": 1776 + }, + { + "epoch": 0.15, + "learning_rate": 1.923562170266292e-05, + "loss": 0.4995, + "step": 1777 + }, + { + "epoch": 0.15, + "learning_rate": 1.9234562419711178e-05, + "loss": 0.499, + "step": 1778 + }, + { + "epoch": 0.15, + "learning_rate": 1.9233502432493146e-05, + "loss": 0.4986, + "step": 1779 + }, + { + "epoch": 0.15, + "learning_rate": 1.923244174108968e-05, + "loss": 0.5201, + "step": 1780 + }, + { + "epoch": 0.15, + "learning_rate": 1.9231380345581655e-05, + "loss": 0.481, + "step": 1781 + }, + { + "epoch": 0.15, + "learning_rate": 1.9230318246050027e-05, + "loss": 0.4911, + "step": 1782 + }, + { + "epoch": 0.15, + "learning_rate": 1.9229255442575795e-05, + "loss": 0.5089, + "step": 1783 + }, + { + "epoch": 0.15, + "learning_rate": 1.922819193524001e-05, + "loss": 0.492, + "step": 1784 + }, + { + "epoch": 0.15, + "learning_rate": 1.922712772412378e-05, + "loss": 0.5152, + "step": 1785 + }, + { + "epoch": 0.15, + "learning_rate": 1.922606280930827e-05, + "loss": 0.4998, + "step": 1786 + }, + { + "epoch": 0.15, + "learning_rate": 1.9224997190874692e-05, + "loss": 0.5199, + "step": 1787 + }, + { + "epoch": 0.15, + "learning_rate": 1.9223930868904313e-05, + "loss": 0.5326, + "step": 1788 + }, + { + "epoch": 0.15, + "learning_rate": 1.9222863843478462e-05, + "loss": 0.5079, + "step": 1789 + }, + { + "epoch": 0.15, + "learning_rate": 1.922179611467851e-05, + "loss": 0.5275, + "step": 1790 + }, + { + "epoch": 0.15, + "learning_rate": 1.9220727682585882e-05, + "loss": 0.4877, + "step": 1791 + }, + { + "epoch": 0.15, + "learning_rate": 1.921965854728207e-05, + "loss": 0.5096, + "step": 1792 + }, + { + "epoch": 0.15, + "learning_rate": 1.9218588708848602e-05, + "loss": 0.5066, + "step": 1793 + }, + { + "epoch": 0.15, + "learning_rate": 1.9217518167367076e-05, + "loss": 0.508, + "step": 1794 + }, + { + "epoch": 0.15, + "learning_rate": 1.921644692291913e-05, + "loss": 0.5205, + "step": 1795 + }, + { + "epoch": 0.15, + "learning_rate": 1.9215374975586465e-05, + "loss": 0.5258, + "step": 1796 + }, + { + "epoch": 0.15, + "learning_rate": 1.9214302325450833e-05, + "loss": 0.4765, + "step": 1797 + }, + { + "epoch": 0.15, + "learning_rate": 1.9213228972594032e-05, + "loss": 0.5087, + "step": 1798 + }, + { + "epoch": 0.15, + "learning_rate": 1.921215491709793e-05, + "loss": 0.4979, + "step": 1799 + }, + { + "epoch": 0.15, + "learning_rate": 1.9211080159044434e-05, + "loss": 0.4964, + "step": 1800 + }, + { + "epoch": 0.15, + "learning_rate": 1.921000469851551e-05, + "loss": 0.4934, + "step": 1801 + }, + { + "epoch": 0.15, + "learning_rate": 1.9208928535593178e-05, + "loss": 0.4968, + "step": 1802 + }, + { + "epoch": 0.15, + "learning_rate": 1.920785167035951e-05, + "loss": 0.4921, + "step": 1803 + }, + { + "epoch": 0.15, + "learning_rate": 1.9206774102896627e-05, + "loss": 0.4859, + "step": 1804 + }, + { + "epoch": 0.15, + "learning_rate": 1.920569583328672e-05, + "loss": 0.5059, + "step": 1805 + }, + { + "epoch": 0.15, + "learning_rate": 1.9204616861612013e-05, + "loss": 0.5058, + "step": 1806 + }, + { + "epoch": 0.15, + "learning_rate": 1.9203537187954796e-05, + "loss": 0.4832, + "step": 1807 + }, + { + "epoch": 0.15, + "learning_rate": 1.920245681239741e-05, + "loss": 0.5292, + "step": 1808 + }, + { + "epoch": 0.15, + "learning_rate": 1.9201375735022246e-05, + "loss": 0.4827, + "step": 1809 + }, + { + "epoch": 0.15, + "learning_rate": 1.920029395591176e-05, + "loss": 0.5134, + "step": 1810 + }, + { + "epoch": 0.15, + "learning_rate": 1.9199211475148442e-05, + "loss": 0.5044, + "step": 1811 + }, + { + "epoch": 0.15, + "learning_rate": 1.919812829281485e-05, + "loss": 0.4999, + "step": 1812 + }, + { + "epoch": 0.15, + "learning_rate": 1.9197044408993595e-05, + "loss": 0.517, + "step": 1813 + }, + { + "epoch": 0.15, + "learning_rate": 1.919595982376734e-05, + "loss": 0.5089, + "step": 1814 + }, + { + "epoch": 0.15, + "learning_rate": 1.9194874537218792e-05, + "loss": 0.5008, + "step": 1815 + }, + { + "epoch": 0.15, + "learning_rate": 1.9193788549430726e-05, + "loss": 0.4982, + "step": 1816 + }, + { + "epoch": 0.15, + "learning_rate": 1.919270186048596e-05, + "loss": 0.5139, + "step": 1817 + }, + { + "epoch": 0.16, + "learning_rate": 1.919161447046738e-05, + "loss": 0.5119, + "step": 1818 + }, + { + "epoch": 0.16, + "learning_rate": 1.91905263794579e-05, + "loss": 0.5145, + "step": 1819 + }, + { + "epoch": 0.16, + "learning_rate": 1.918943758754051e-05, + "loss": 0.4907, + "step": 1820 + }, + { + "epoch": 0.16, + "learning_rate": 1.9188348094798245e-05, + "loss": 0.521, + "step": 1821 + }, + { + "epoch": 0.16, + "learning_rate": 1.9187257901314194e-05, + "loss": 0.5114, + "step": 1822 + }, + { + "epoch": 0.16, + "learning_rate": 1.91861670071715e-05, + "loss": 0.4843, + "step": 1823 + }, + { + "epoch": 0.16, + "learning_rate": 1.918507541245336e-05, + "loss": 0.5221, + "step": 1824 + }, + { + "epoch": 0.16, + "learning_rate": 1.9183983117243022e-05, + "loss": 0.49, + "step": 1825 + }, + { + "epoch": 0.16, + "learning_rate": 1.918289012162379e-05, + "loss": 0.5115, + "step": 1826 + }, + { + "epoch": 0.16, + "learning_rate": 1.9181796425679015e-05, + "loss": 0.4902, + "step": 1827 + }, + { + "epoch": 0.16, + "learning_rate": 1.9180702029492118e-05, + "loss": 0.5094, + "step": 1828 + }, + { + "epoch": 0.16, + "learning_rate": 1.9179606933146553e-05, + "loss": 0.5074, + "step": 1829 + }, + { + "epoch": 0.16, + "learning_rate": 1.9178511136725842e-05, + "loss": 0.4945, + "step": 1830 + }, + { + "epoch": 0.16, + "learning_rate": 1.917741464031355e-05, + "loss": 0.5097, + "step": 1831 + }, + { + "epoch": 0.16, + "learning_rate": 1.9176317443993303e-05, + "loss": 0.5015, + "step": 1832 + }, + { + "epoch": 0.16, + "learning_rate": 1.917521954784878e-05, + "loss": 0.5134, + "step": 1833 + }, + { + "epoch": 0.16, + "learning_rate": 1.9174120951963705e-05, + "loss": 0.498, + "step": 1834 + }, + { + "epoch": 0.16, + "learning_rate": 1.917302165642187e-05, + "loss": 0.5079, + "step": 1835 + }, + { + "epoch": 0.16, + "learning_rate": 1.9171921661307102e-05, + "loss": 0.5108, + "step": 1836 + }, + { + "epoch": 0.16, + "learning_rate": 1.91708209667033e-05, + "loss": 0.4983, + "step": 1837 + }, + { + "epoch": 0.16, + "learning_rate": 1.9169719572694404e-05, + "loss": 0.52, + "step": 1838 + }, + { + "epoch": 0.16, + "learning_rate": 1.916861747936441e-05, + "loss": 0.4885, + "step": 1839 + }, + { + "epoch": 0.16, + "learning_rate": 1.916751468679737e-05, + "loss": 0.4859, + "step": 1840 + }, + { + "epoch": 0.16, + "learning_rate": 1.9166411195077387e-05, + "loss": 0.5119, + "step": 1841 + }, + { + "epoch": 0.16, + "learning_rate": 1.916530700428862e-05, + "loss": 0.4982, + "step": 1842 + }, + { + "epoch": 0.16, + "learning_rate": 1.916420211451527e-05, + "loss": 0.4985, + "step": 1843 + }, + { + "epoch": 0.16, + "learning_rate": 1.916309652584161e-05, + "loss": 0.503, + "step": 1844 + }, + { + "epoch": 0.16, + "learning_rate": 1.916199023835196e-05, + "loss": 0.5275, + "step": 1845 + }, + { + "epoch": 0.16, + "learning_rate": 1.9160883252130678e-05, + "loss": 0.4892, + "step": 1846 + }, + { + "epoch": 0.16, + "learning_rate": 1.9159775567262194e-05, + "loss": 0.5243, + "step": 1847 + }, + { + "epoch": 0.16, + "learning_rate": 1.9158667183830988e-05, + "loss": 0.5119, + "step": 1848 + }, + { + "epoch": 0.16, + "learning_rate": 1.9157558101921583e-05, + "loss": 0.486, + "step": 1849 + }, + { + "epoch": 0.16, + "learning_rate": 1.915644832161857e-05, + "loss": 0.5315, + "step": 1850 + }, + { + "epoch": 0.16, + "learning_rate": 1.9155337843006573e-05, + "loss": 0.5227, + "step": 1851 + }, + { + "epoch": 0.16, + "learning_rate": 1.9154226666170296e-05, + "loss": 0.4747, + "step": 1852 + }, + { + "epoch": 0.16, + "learning_rate": 1.9153114791194475e-05, + "loss": 0.5011, + "step": 1853 + }, + { + "epoch": 0.16, + "learning_rate": 1.9152002218163904e-05, + "loss": 0.5114, + "step": 1854 + }, + { + "epoch": 0.16, + "learning_rate": 1.9150888947163436e-05, + "loss": 0.5104, + "step": 1855 + }, + { + "epoch": 0.16, + "learning_rate": 1.9149774978277975e-05, + "loss": 0.4996, + "step": 1856 + }, + { + "epoch": 0.16, + "learning_rate": 1.9148660311592477e-05, + "loss": 0.5015, + "step": 1857 + }, + { + "epoch": 0.16, + "learning_rate": 1.9147544947191943e-05, + "loss": 0.5146, + "step": 1858 + }, + { + "epoch": 0.16, + "learning_rate": 1.9146428885161444e-05, + "loss": 0.5187, + "step": 1859 + }, + { + "epoch": 0.16, + "learning_rate": 1.9145312125586096e-05, + "loss": 0.5148, + "step": 1860 + }, + { + "epoch": 0.16, + "learning_rate": 1.9144194668551063e-05, + "loss": 0.5021, + "step": 1861 + }, + { + "epoch": 0.16, + "learning_rate": 1.9143076514141566e-05, + "loss": 0.4934, + "step": 1862 + }, + { + "epoch": 0.16, + "learning_rate": 1.9141957662442885e-05, + "loss": 0.4961, + "step": 1863 + }, + { + "epoch": 0.16, + "learning_rate": 1.9140838113540347e-05, + "loss": 0.5006, + "step": 1864 + }, + { + "epoch": 0.16, + "learning_rate": 1.9139717867519332e-05, + "loss": 0.4907, + "step": 1865 + }, + { + "epoch": 0.16, + "learning_rate": 1.9138596924465276e-05, + "loss": 0.488, + "step": 1866 + }, + { + "epoch": 0.16, + "learning_rate": 1.9137475284463668e-05, + "loss": 0.5067, + "step": 1867 + }, + { + "epoch": 0.16, + "learning_rate": 1.913635294760004e-05, + "loss": 0.4889, + "step": 1868 + }, + { + "epoch": 0.16, + "learning_rate": 1.9135229913959997e-05, + "loss": 0.4955, + "step": 1869 + }, + { + "epoch": 0.16, + "learning_rate": 1.9134106183629184e-05, + "loss": 0.5049, + "step": 1870 + }, + { + "epoch": 0.16, + "learning_rate": 1.9132981756693298e-05, + "loss": 0.4995, + "step": 1871 + }, + { + "epoch": 0.16, + "learning_rate": 1.9131856633238096e-05, + "loss": 0.4981, + "step": 1872 + }, + { + "epoch": 0.16, + "learning_rate": 1.913073081334938e-05, + "loss": 0.5144, + "step": 1873 + }, + { + "epoch": 0.16, + "learning_rate": 1.9129604297113013e-05, + "loss": 0.5009, + "step": 1874 + }, + { + "epoch": 0.16, + "learning_rate": 1.912847708461491e-05, + "loss": 0.5003, + "step": 1875 + }, + { + "epoch": 0.16, + "learning_rate": 1.912734917594103e-05, + "loss": 0.5128, + "step": 1876 + }, + { + "epoch": 0.16, + "learning_rate": 1.91262205711774e-05, + "loss": 0.5375, + "step": 1877 + }, + { + "epoch": 0.16, + "learning_rate": 1.9125091270410088e-05, + "loss": 0.4824, + "step": 1878 + }, + { + "epoch": 0.16, + "learning_rate": 1.9123961273725218e-05, + "loss": 0.5201, + "step": 1879 + }, + { + "epoch": 0.16, + "learning_rate": 1.912283058120897e-05, + "loss": 0.5112, + "step": 1880 + }, + { + "epoch": 0.16, + "learning_rate": 1.9121699192947577e-05, + "loss": 0.5137, + "step": 1881 + }, + { + "epoch": 0.16, + "learning_rate": 1.912056710902732e-05, + "loss": 0.5029, + "step": 1882 + }, + { + "epoch": 0.16, + "learning_rate": 1.9119434329534538e-05, + "loss": 0.5111, + "step": 1883 + }, + { + "epoch": 0.16, + "learning_rate": 1.9118300854555626e-05, + "loss": 0.5002, + "step": 1884 + }, + { + "epoch": 0.16, + "learning_rate": 1.9117166684177017e-05, + "loss": 0.4839, + "step": 1885 + }, + { + "epoch": 0.16, + "learning_rate": 1.9116031818485216e-05, + "loss": 0.5315, + "step": 1886 + }, + { + "epoch": 0.16, + "learning_rate": 1.911489625756677e-05, + "loss": 0.4964, + "step": 1887 + }, + { + "epoch": 0.16, + "learning_rate": 1.911376000150828e-05, + "loss": 0.5012, + "step": 1888 + }, + { + "epoch": 0.16, + "learning_rate": 1.9112623050396407e-05, + "loss": 0.4984, + "step": 1889 + }, + { + "epoch": 0.16, + "learning_rate": 1.9111485404317852e-05, + "loss": 0.5186, + "step": 1890 + }, + { + "epoch": 0.16, + "learning_rate": 1.9110347063359383e-05, + "loss": 0.4986, + "step": 1891 + }, + { + "epoch": 0.16, + "learning_rate": 1.9109208027607814e-05, + "loss": 0.4944, + "step": 1892 + }, + { + "epoch": 0.16, + "learning_rate": 1.910806829715001e-05, + "loss": 0.4916, + "step": 1893 + }, + { + "epoch": 0.16, + "learning_rate": 1.910692787207289e-05, + "loss": 0.5037, + "step": 1894 + }, + { + "epoch": 0.16, + "learning_rate": 1.9105786752463434e-05, + "loss": 0.512, + "step": 1895 + }, + { + "epoch": 0.16, + "learning_rate": 1.9104644938408663e-05, + "loss": 0.501, + "step": 1896 + }, + { + "epoch": 0.16, + "learning_rate": 1.910350242999566e-05, + "loss": 0.5076, + "step": 1897 + }, + { + "epoch": 0.16, + "learning_rate": 1.9102359227311554e-05, + "loss": 0.4904, + "step": 1898 + }, + { + "epoch": 0.16, + "learning_rate": 1.910121533044353e-05, + "loss": 0.5125, + "step": 1899 + }, + { + "epoch": 0.16, + "learning_rate": 1.9100070739478833e-05, + "loss": 0.5132, + "step": 1900 + }, + { + "epoch": 0.16, + "learning_rate": 1.9098925454504747e-05, + "loss": 0.4918, + "step": 1901 + }, + { + "epoch": 0.16, + "learning_rate": 1.9097779475608618e-05, + "loss": 0.5235, + "step": 1902 + }, + { + "epoch": 0.16, + "learning_rate": 1.9096632802877845e-05, + "loss": 0.4912, + "step": 1903 + }, + { + "epoch": 0.16, + "learning_rate": 1.9095485436399878e-05, + "loss": 0.5099, + "step": 1904 + }, + { + "epoch": 0.16, + "learning_rate": 1.909433737626222e-05, + "loss": 0.4941, + "step": 1905 + }, + { + "epoch": 0.16, + "learning_rate": 1.9093188622552424e-05, + "loss": 0.5187, + "step": 1906 + }, + { + "epoch": 0.16, + "learning_rate": 1.90920391753581e-05, + "loss": 0.501, + "step": 1907 + }, + { + "epoch": 0.16, + "learning_rate": 1.909088903476691e-05, + "loss": 0.4979, + "step": 1908 + }, + { + "epoch": 0.16, + "learning_rate": 1.9089738200866574e-05, + "loss": 0.5073, + "step": 1909 + }, + { + "epoch": 0.16, + "learning_rate": 1.908858667374485e-05, + "loss": 0.5072, + "step": 1910 + }, + { + "epoch": 0.16, + "learning_rate": 1.9087434453489564e-05, + "loss": 0.4891, + "step": 1911 + }, + { + "epoch": 0.16, + "learning_rate": 1.908628154018859e-05, + "loss": 0.5014, + "step": 1912 + }, + { + "epoch": 0.16, + "learning_rate": 1.908512793392985e-05, + "loss": 0.5155, + "step": 1913 + }, + { + "epoch": 0.16, + "learning_rate": 1.908397363480132e-05, + "loss": 0.4976, + "step": 1914 + }, + { + "epoch": 0.16, + "learning_rate": 1.908281864289104e-05, + "loss": 0.4952, + "step": 1915 + }, + { + "epoch": 0.16, + "learning_rate": 1.908166295828709e-05, + "loss": 0.518, + "step": 1916 + }, + { + "epoch": 0.16, + "learning_rate": 1.9080506581077607e-05, + "loss": 0.4838, + "step": 1917 + }, + { + "epoch": 0.16, + "learning_rate": 1.9079349511350784e-05, + "loss": 0.4925, + "step": 1918 + }, + { + "epoch": 0.16, + "learning_rate": 1.907819174919486e-05, + "loss": 0.499, + "step": 1919 + }, + { + "epoch": 0.16, + "learning_rate": 1.9077033294698135e-05, + "loss": 0.5167, + "step": 1920 + }, + { + "epoch": 0.16, + "learning_rate": 1.9075874147948955e-05, + "loss": 0.4874, + "step": 1921 + }, + { + "epoch": 0.16, + "learning_rate": 1.9074714309035723e-05, + "loss": 0.5168, + "step": 1922 + }, + { + "epoch": 0.16, + "learning_rate": 1.907355377804689e-05, + "loss": 0.5439, + "step": 1923 + }, + { + "epoch": 0.16, + "learning_rate": 1.9072392555070965e-05, + "loss": 0.5062, + "step": 1924 + }, + { + "epoch": 0.16, + "learning_rate": 1.907123064019651e-05, + "loss": 0.527, + "step": 1925 + }, + { + "epoch": 0.16, + "learning_rate": 1.907006803351213e-05, + "loss": 0.5108, + "step": 1926 + }, + { + "epoch": 0.16, + "learning_rate": 1.9068904735106502e-05, + "loss": 0.5174, + "step": 1927 + }, + { + "epoch": 0.16, + "learning_rate": 1.9067740745068334e-05, + "loss": 0.4963, + "step": 1928 + }, + { + "epoch": 0.16, + "learning_rate": 1.90665760634864e-05, + "loss": 0.4976, + "step": 1929 + }, + { + "epoch": 0.16, + "learning_rate": 1.9065410690449525e-05, + "loss": 0.5104, + "step": 1930 + }, + { + "epoch": 0.16, + "learning_rate": 1.906424462604658e-05, + "loss": 0.4829, + "step": 1931 + }, + { + "epoch": 0.16, + "learning_rate": 1.9063077870366504e-05, + "loss": 0.5075, + "step": 1932 + }, + { + "epoch": 0.16, + "learning_rate": 1.9061910423498268e-05, + "loss": 0.5005, + "step": 1933 + }, + { + "epoch": 0.16, + "learning_rate": 1.906074228553091e-05, + "loss": 0.4836, + "step": 1934 + }, + { + "epoch": 0.16, + "learning_rate": 1.905957345655352e-05, + "loss": 0.4977, + "step": 1935 + }, + { + "epoch": 0.17, + "learning_rate": 1.9058403936655235e-05, + "loss": 0.496, + "step": 1936 + }, + { + "epoch": 0.17, + "learning_rate": 1.9057233725925245e-05, + "loss": 0.5125, + "step": 1937 + }, + { + "epoch": 0.17, + "learning_rate": 1.9056062824452802e-05, + "loss": 0.4984, + "step": 1938 + }, + { + "epoch": 0.17, + "learning_rate": 1.90548912323272e-05, + "loss": 0.522, + "step": 1939 + }, + { + "epoch": 0.17, + "learning_rate": 1.9053718949637788e-05, + "loss": 0.4909, + "step": 1940 + }, + { + "epoch": 0.17, + "learning_rate": 1.9052545976473972e-05, + "loss": 0.5169, + "step": 1941 + }, + { + "epoch": 0.17, + "learning_rate": 1.9051372312925208e-05, + "loss": 0.5063, + "step": 1942 + }, + { + "epoch": 0.17, + "learning_rate": 1.9050197959081e-05, + "loss": 0.513, + "step": 1943 + }, + { + "epoch": 0.17, + "learning_rate": 1.9049022915030916e-05, + "loss": 0.4878, + "step": 1944 + }, + { + "epoch": 0.17, + "learning_rate": 1.904784718086456e-05, + "loss": 0.4979, + "step": 1945 + }, + { + "epoch": 0.17, + "learning_rate": 1.904667075667161e-05, + "loss": 0.5115, + "step": 1946 + }, + { + "epoch": 0.17, + "learning_rate": 1.9045493642541775e-05, + "loss": 0.4901, + "step": 1947 + }, + { + "epoch": 0.17, + "learning_rate": 1.9044315838564835e-05, + "loss": 0.4972, + "step": 1948 + }, + { + "epoch": 0.17, + "learning_rate": 1.9043137344830608e-05, + "loss": 0.4924, + "step": 1949 + }, + { + "epoch": 0.17, + "learning_rate": 1.9041958161428976e-05, + "loss": 0.5042, + "step": 1950 + }, + { + "epoch": 0.17, + "learning_rate": 1.9040778288449862e-05, + "loss": 0.5015, + "step": 1951 + }, + { + "epoch": 0.17, + "learning_rate": 1.9039597725983254e-05, + "loss": 0.4963, + "step": 1952 + }, + { + "epoch": 0.17, + "learning_rate": 1.9038416474119182e-05, + "loss": 0.4869, + "step": 1953 + }, + { + "epoch": 0.17, + "learning_rate": 1.9037234532947737e-05, + "loss": 0.4995, + "step": 1954 + }, + { + "epoch": 0.17, + "learning_rate": 1.9036051902559055e-05, + "loss": 0.5222, + "step": 1955 + }, + { + "epoch": 0.17, + "learning_rate": 1.9034868583043334e-05, + "loss": 0.4972, + "step": 1956 + }, + { + "epoch": 0.17, + "learning_rate": 1.9033684574490813e-05, + "loss": 0.4951, + "step": 1957 + }, + { + "epoch": 0.17, + "learning_rate": 1.9032499876991793e-05, + "loss": 0.5051, + "step": 1958 + }, + { + "epoch": 0.17, + "learning_rate": 1.903131449063662e-05, + "loss": 0.5171, + "step": 1959 + }, + { + "epoch": 0.17, + "learning_rate": 1.9030128415515705e-05, + "loss": 0.4892, + "step": 1960 + }, + { + "epoch": 0.17, + "learning_rate": 1.902894165171949e-05, + "loss": 0.5088, + "step": 1961 + }, + { + "epoch": 0.17, + "learning_rate": 1.9027754199338496e-05, + "loss": 0.4883, + "step": 1962 + }, + { + "epoch": 0.17, + "learning_rate": 1.9026566058463277e-05, + "loss": 0.4899, + "step": 1963 + }, + { + "epoch": 0.17, + "learning_rate": 1.9025377229184442e-05, + "loss": 0.4995, + "step": 1964 + }, + { + "epoch": 0.17, + "learning_rate": 1.902418771159266e-05, + "loss": 0.4921, + "step": 1965 + }, + { + "epoch": 0.17, + "learning_rate": 1.9022997505778652e-05, + "loss": 0.5169, + "step": 1966 + }, + { + "epoch": 0.17, + "learning_rate": 1.902180661183318e-05, + "loss": 0.5107, + "step": 1967 + }, + { + "epoch": 0.17, + "learning_rate": 1.9020615029847073e-05, + "loss": 0.5267, + "step": 1968 + }, + { + "epoch": 0.17, + "learning_rate": 1.9019422759911204e-05, + "loss": 0.5001, + "step": 1969 + }, + { + "epoch": 0.17, + "learning_rate": 1.90182298021165e-05, + "loss": 0.4853, + "step": 1970 + }, + { + "epoch": 0.17, + "learning_rate": 1.901703615655394e-05, + "loss": 0.4888, + "step": 1971 + }, + { + "epoch": 0.17, + "learning_rate": 1.901584182331456e-05, + "loss": 0.4978, + "step": 1972 + }, + { + "epoch": 0.17, + "learning_rate": 1.901464680248944e-05, + "loss": 0.5072, + "step": 1973 + }, + { + "epoch": 0.17, + "learning_rate": 1.9013451094169724e-05, + "loss": 0.5154, + "step": 1974 + }, + { + "epoch": 0.17, + "learning_rate": 1.9012254698446595e-05, + "loss": 0.5041, + "step": 1975 + }, + { + "epoch": 0.17, + "learning_rate": 1.9011057615411297e-05, + "loss": 0.4964, + "step": 1976 + }, + { + "epoch": 0.17, + "learning_rate": 1.9009859845155126e-05, + "loss": 0.501, + "step": 1977 + }, + { + "epoch": 0.17, + "learning_rate": 1.9008661387769427e-05, + "loss": 0.5194, + "step": 1978 + }, + { + "epoch": 0.17, + "learning_rate": 1.9007462243345603e-05, + "loss": 0.4925, + "step": 1979 + }, + { + "epoch": 0.17, + "learning_rate": 1.90062624119751e-05, + "loss": 0.5081, + "step": 1980 + }, + { + "epoch": 0.17, + "learning_rate": 1.900506189374943e-05, + "loss": 0.4866, + "step": 1981 + }, + { + "epoch": 0.17, + "learning_rate": 1.9003860688760142e-05, + "loss": 0.4745, + "step": 1982 + }, + { + "epoch": 0.17, + "learning_rate": 1.9002658797098846e-05, + "loss": 0.4859, + "step": 1983 + }, + { + "epoch": 0.17, + "learning_rate": 1.9001456218857207e-05, + "loss": 0.4979, + "step": 1984 + }, + { + "epoch": 0.17, + "learning_rate": 1.9000252954126938e-05, + "loss": 0.4972, + "step": 1985 + }, + { + "epoch": 0.17, + "learning_rate": 1.8999049002999804e-05, + "loss": 0.498, + "step": 1986 + }, + { + "epoch": 0.17, + "learning_rate": 1.8997844365567623e-05, + "loss": 0.5133, + "step": 1987 + }, + { + "epoch": 0.17, + "learning_rate": 1.8996639041922263e-05, + "loss": 0.5196, + "step": 1988 + }, + { + "epoch": 0.17, + "learning_rate": 1.8995433032155652e-05, + "loss": 0.4824, + "step": 1989 + }, + { + "epoch": 0.17, + "learning_rate": 1.899422633635976e-05, + "loss": 0.4819, + "step": 1990 + }, + { + "epoch": 0.17, + "learning_rate": 1.899301895462662e-05, + "loss": 0.518, + "step": 1991 + }, + { + "epoch": 0.17, + "learning_rate": 1.8991810887048316e-05, + "loss": 0.49, + "step": 1992 + }, + { + "epoch": 0.17, + "learning_rate": 1.8990602133716968e-05, + "loss": 0.5008, + "step": 1993 + }, + { + "epoch": 0.17, + "learning_rate": 1.8989392694724764e-05, + "loss": 0.527, + "step": 1994 + }, + { + "epoch": 0.17, + "learning_rate": 1.8988182570163948e-05, + "loss": 0.4768, + "step": 1995 + }, + { + "epoch": 0.17, + "learning_rate": 1.8986971760126805e-05, + "loss": 0.5136, + "step": 1996 + }, + { + "epoch": 0.17, + "learning_rate": 1.8985760264705674e-05, + "loss": 0.4948, + "step": 1997 + }, + { + "epoch": 0.17, + "learning_rate": 1.898454808399295e-05, + "loss": 0.5084, + "step": 1998 + }, + { + "epoch": 0.17, + "learning_rate": 1.898333521808108e-05, + "loss": 0.5103, + "step": 1999 + }, + { + "epoch": 0.17, + "learning_rate": 1.8982121667062566e-05, + "loss": 0.5144, + "step": 2000 + }, + { + "epoch": 0.17, + "learning_rate": 1.898090743102995e-05, + "loss": 0.5238, + "step": 2001 + }, + { + "epoch": 0.17, + "learning_rate": 1.897969251007584e-05, + "loss": 0.4808, + "step": 2002 + }, + { + "epoch": 0.17, + "learning_rate": 1.8978476904292892e-05, + "loss": 0.4974, + "step": 2003 + }, + { + "epoch": 0.17, + "learning_rate": 1.897726061377381e-05, + "loss": 0.4833, + "step": 2004 + }, + { + "epoch": 0.17, + "learning_rate": 1.8976043638611353e-05, + "loss": 0.4994, + "step": 2005 + }, + { + "epoch": 0.17, + "learning_rate": 1.8974825978898337e-05, + "loss": 0.4966, + "step": 2006 + }, + { + "epoch": 0.17, + "learning_rate": 1.897360763472762e-05, + "loss": 0.5115, + "step": 2007 + }, + { + "epoch": 0.17, + "learning_rate": 1.8972388606192124e-05, + "loss": 0.4845, + "step": 2008 + }, + { + "epoch": 0.17, + "learning_rate": 1.8971168893384814e-05, + "loss": 0.5115, + "step": 2009 + }, + { + "epoch": 0.17, + "learning_rate": 1.896994849639871e-05, + "loss": 0.5277, + "step": 2010 + }, + { + "epoch": 0.17, + "learning_rate": 1.8968727415326885e-05, + "loss": 0.4887, + "step": 2011 + }, + { + "epoch": 0.17, + "learning_rate": 1.896750565026246e-05, + "loss": 0.5283, + "step": 2012 + }, + { + "epoch": 0.17, + "learning_rate": 1.8966283201298625e-05, + "loss": 0.4995, + "step": 2013 + }, + { + "epoch": 0.17, + "learning_rate": 1.8965060068528594e-05, + "loss": 0.4995, + "step": 2014 + }, + { + "epoch": 0.17, + "learning_rate": 1.8963836252045656e-05, + "loss": 0.5138, + "step": 2015 + }, + { + "epoch": 0.17, + "learning_rate": 1.8962611751943142e-05, + "loss": 0.5081, + "step": 2016 + }, + { + "epoch": 0.17, + "learning_rate": 1.8961386568314438e-05, + "loss": 0.5221, + "step": 2017 + }, + { + "epoch": 0.17, + "learning_rate": 1.8960160701252982e-05, + "loss": 0.4668, + "step": 2018 + }, + { + "epoch": 0.17, + "learning_rate": 1.895893415085226e-05, + "loss": 0.5072, + "step": 2019 + }, + { + "epoch": 0.17, + "learning_rate": 1.895770691720582e-05, + "loss": 0.4964, + "step": 2020 + }, + { + "epoch": 0.17, + "learning_rate": 1.8956479000407257e-05, + "loss": 0.5068, + "step": 2021 + }, + { + "epoch": 0.17, + "learning_rate": 1.8955250400550206e-05, + "loss": 0.5087, + "step": 2022 + }, + { + "epoch": 0.17, + "learning_rate": 1.8954021117728377e-05, + "loss": 0.5057, + "step": 2023 + }, + { + "epoch": 0.17, + "learning_rate": 1.8952791152035514e-05, + "loss": 0.508, + "step": 2024 + }, + { + "epoch": 0.17, + "learning_rate": 1.895156050356542e-05, + "loss": 0.4828, + "step": 2025 + }, + { + "epoch": 0.17, + "learning_rate": 1.8950329172411954e-05, + "loss": 0.5169, + "step": 2026 + }, + { + "epoch": 0.17, + "learning_rate": 1.8949097158669017e-05, + "loss": 0.5189, + "step": 2027 + }, + { + "epoch": 0.17, + "learning_rate": 1.8947864462430567e-05, + "loss": 0.4982, + "step": 2028 + }, + { + "epoch": 0.17, + "learning_rate": 1.894663108379062e-05, + "loss": 0.5082, + "step": 2029 + }, + { + "epoch": 0.17, + "learning_rate": 1.8945397022843233e-05, + "loss": 0.4912, + "step": 2030 + }, + { + "epoch": 0.17, + "learning_rate": 1.8944162279682524e-05, + "loss": 0.5246, + "step": 2031 + }, + { + "epoch": 0.17, + "learning_rate": 1.894292685440266e-05, + "loss": 0.5066, + "step": 2032 + }, + { + "epoch": 0.17, + "learning_rate": 1.8941690747097857e-05, + "loss": 0.503, + "step": 2033 + }, + { + "epoch": 0.17, + "learning_rate": 1.894045395786239e-05, + "loss": 0.4973, + "step": 2034 + }, + { + "epoch": 0.17, + "learning_rate": 1.8939216486790577e-05, + "loss": 0.5065, + "step": 2035 + }, + { + "epoch": 0.17, + "learning_rate": 1.8937978333976797e-05, + "loss": 0.4834, + "step": 2036 + }, + { + "epoch": 0.17, + "learning_rate": 1.893673949951547e-05, + "loss": 0.4906, + "step": 2037 + }, + { + "epoch": 0.17, + "learning_rate": 1.893549998350108e-05, + "loss": 0.5169, + "step": 2038 + }, + { + "epoch": 0.17, + "learning_rate": 1.8934259786028158e-05, + "loss": 0.4963, + "step": 2039 + }, + { + "epoch": 0.17, + "learning_rate": 1.8933018907191286e-05, + "loss": 0.5142, + "step": 2040 + }, + { + "epoch": 0.17, + "learning_rate": 1.8931777347085094e-05, + "loss": 0.4887, + "step": 2041 + }, + { + "epoch": 0.17, + "learning_rate": 1.8930535105804275e-05, + "loss": 0.5339, + "step": 2042 + }, + { + "epoch": 0.17, + "learning_rate": 1.8929292183443565e-05, + "loss": 0.4961, + "step": 2043 + }, + { + "epoch": 0.17, + "learning_rate": 1.8928048580097758e-05, + "loss": 0.5132, + "step": 2044 + }, + { + "epoch": 0.17, + "learning_rate": 1.8926804295861687e-05, + "loss": 0.4882, + "step": 2045 + }, + { + "epoch": 0.17, + "learning_rate": 1.8925559330830254e-05, + "loss": 0.4924, + "step": 2046 + }, + { + "epoch": 0.17, + "learning_rate": 1.8924313685098405e-05, + "loss": 0.4917, + "step": 2047 + }, + { + "epoch": 0.17, + "learning_rate": 1.8923067358761135e-05, + "loss": 0.4959, + "step": 2048 + }, + { + "epoch": 0.17, + "learning_rate": 1.8921820351913496e-05, + "loss": 0.4997, + "step": 2049 + }, + { + "epoch": 0.17, + "learning_rate": 1.892057266465059e-05, + "loss": 0.4814, + "step": 2050 + }, + { + "epoch": 0.17, + "learning_rate": 1.8919324297067566e-05, + "loss": 0.4939, + "step": 2051 + }, + { + "epoch": 0.17, + "learning_rate": 1.891807524925964e-05, + "loss": 0.5063, + "step": 2052 + }, + { + "epoch": 0.18, + "learning_rate": 1.8916825521322064e-05, + "loss": 0.4992, + "step": 2053 + }, + { + "epoch": 0.18, + "learning_rate": 1.8915575113350143e-05, + "loss": 0.5254, + "step": 2054 + }, + { + "epoch": 0.18, + "learning_rate": 1.891432402543924e-05, + "loss": 0.5021, + "step": 2055 + }, + { + "epoch": 0.18, + "learning_rate": 1.8913072257684777e-05, + "loss": 0.5118, + "step": 2056 + }, + { + "epoch": 0.18, + "learning_rate": 1.891181981018221e-05, + "loss": 0.4919, + "step": 2057 + }, + { + "epoch": 0.18, + "learning_rate": 1.891056668302706e-05, + "loss": 0.5033, + "step": 2058 + }, + { + "epoch": 0.18, + "learning_rate": 1.890931287631489e-05, + "loss": 0.4833, + "step": 2059 + }, + { + "epoch": 0.18, + "learning_rate": 1.8908058390141327e-05, + "loss": 0.4815, + "step": 2060 + }, + { + "epoch": 0.18, + "learning_rate": 1.8906803224602043e-05, + "loss": 0.5135, + "step": 2061 + }, + { + "epoch": 0.18, + "learning_rate": 1.890554737979276e-05, + "loss": 0.5008, + "step": 2062 + }, + { + "epoch": 0.18, + "learning_rate": 1.8904290855809253e-05, + "loss": 0.4931, + "step": 2063 + }, + { + "epoch": 0.18, + "learning_rate": 1.8903033652747352e-05, + "loss": 0.5106, + "step": 2064 + }, + { + "epoch": 0.18, + "learning_rate": 1.8901775770702933e-05, + "loss": 0.5136, + "step": 2065 + }, + { + "epoch": 0.18, + "learning_rate": 1.8900517209771934e-05, + "loss": 0.5042, + "step": 2066 + }, + { + "epoch": 0.18, + "learning_rate": 1.8899257970050333e-05, + "loss": 0.5155, + "step": 2067 + }, + { + "epoch": 0.18, + "learning_rate": 1.8897998051634165e-05, + "loss": 0.5149, + "step": 2068 + }, + { + "epoch": 0.18, + "learning_rate": 1.8896737454619516e-05, + "loss": 0.5164, + "step": 2069 + }, + { + "epoch": 0.18, + "learning_rate": 1.8895476179102528e-05, + "loss": 0.5075, + "step": 2070 + }, + { + "epoch": 0.18, + "learning_rate": 1.889421422517939e-05, + "loss": 0.4964, + "step": 2071 + }, + { + "epoch": 0.18, + "learning_rate": 1.8892951592946342e-05, + "loss": 0.4939, + "step": 2072 + }, + { + "epoch": 0.18, + "learning_rate": 1.8891688282499675e-05, + "loss": 0.4876, + "step": 2073 + }, + { + "epoch": 0.18, + "learning_rate": 1.8890424293935744e-05, + "loss": 0.4997, + "step": 2074 + }, + { + "epoch": 0.18, + "learning_rate": 1.8889159627350934e-05, + "loss": 0.5198, + "step": 2075 + }, + { + "epoch": 0.18, + "learning_rate": 1.8887894282841705e-05, + "loss": 0.4933, + "step": 2076 + }, + { + "epoch": 0.18, + "learning_rate": 1.888662826050455e-05, + "loss": 0.5136, + "step": 2077 + }, + { + "epoch": 0.18, + "learning_rate": 1.8885361560436023e-05, + "loss": 0.4673, + "step": 2078 + }, + { + "epoch": 0.18, + "learning_rate": 1.888409418273273e-05, + "loss": 0.4895, + "step": 2079 + }, + { + "epoch": 0.18, + "learning_rate": 1.888282612749132e-05, + "loss": 0.5115, + "step": 2080 + }, + { + "epoch": 0.18, + "learning_rate": 1.8881557394808506e-05, + "loss": 0.53, + "step": 2081 + }, + { + "epoch": 0.18, + "learning_rate": 1.888028798478105e-05, + "loss": 0.4987, + "step": 2082 + }, + { + "epoch": 0.18, + "learning_rate": 1.8879017897505757e-05, + "loss": 0.5061, + "step": 2083 + }, + { + "epoch": 0.18, + "learning_rate": 1.8877747133079487e-05, + "loss": 0.5213, + "step": 2084 + }, + { + "epoch": 0.18, + "learning_rate": 1.887647569159916e-05, + "loss": 0.5156, + "step": 2085 + }, + { + "epoch": 0.18, + "learning_rate": 1.8875203573161737e-05, + "loss": 0.51, + "step": 2086 + }, + { + "epoch": 0.18, + "learning_rate": 1.8873930777864234e-05, + "loss": 0.5011, + "step": 2087 + }, + { + "epoch": 0.18, + "learning_rate": 1.887265730580373e-05, + "loss": 0.5048, + "step": 2088 + }, + { + "epoch": 0.18, + "learning_rate": 1.887138315707733e-05, + "loss": 0.502, + "step": 2089 + }, + { + "epoch": 0.18, + "learning_rate": 1.887010833178222e-05, + "loss": 0.518, + "step": 2090 + }, + { + "epoch": 0.18, + "learning_rate": 1.8868832830015614e-05, + "loss": 0.5185, + "step": 2091 + }, + { + "epoch": 0.18, + "learning_rate": 1.886755665187479e-05, + "loss": 0.5118, + "step": 2092 + }, + { + "epoch": 0.18, + "learning_rate": 1.8866279797457073e-05, + "loss": 0.4843, + "step": 2093 + }, + { + "epoch": 0.18, + "learning_rate": 1.8865002266859846e-05, + "loss": 0.4954, + "step": 2094 + }, + { + "epoch": 0.18, + "learning_rate": 1.886372406018053e-05, + "loss": 0.519, + "step": 2095 + }, + { + "epoch": 0.18, + "learning_rate": 1.8862445177516622e-05, + "loss": 0.4876, + "step": 2096 + }, + { + "epoch": 0.18, + "learning_rate": 1.886116561896564e-05, + "loss": 0.49, + "step": 2097 + }, + { + "epoch": 0.18, + "learning_rate": 1.885988538462517e-05, + "loss": 0.5071, + "step": 2098 + }, + { + "epoch": 0.18, + "learning_rate": 1.885860447459286e-05, + "loss": 0.4765, + "step": 2099 + }, + { + "epoch": 0.18, + "learning_rate": 1.8857322888966384e-05, + "loss": 0.5007, + "step": 2100 + }, + { + "epoch": 0.18, + "learning_rate": 1.8856040627843484e-05, + "loss": 0.5, + "step": 2101 + }, + { + "epoch": 0.18, + "learning_rate": 1.8854757691321956e-05, + "loss": 0.4886, + "step": 2102 + }, + { + "epoch": 0.18, + "learning_rate": 1.885347407949964e-05, + "loss": 0.4963, + "step": 2103 + }, + { + "epoch": 0.18, + "learning_rate": 1.8852189792474426e-05, + "loss": 0.5024, + "step": 2104 + }, + { + "epoch": 0.18, + "learning_rate": 1.8850904830344264e-05, + "loss": 0.4854, + "step": 2105 + }, + { + "epoch": 0.18, + "learning_rate": 1.8849619193207143e-05, + "loss": 0.501, + "step": 2106 + }, + { + "epoch": 0.18, + "learning_rate": 1.8848332881161126e-05, + "loss": 0.4936, + "step": 2107 + }, + { + "epoch": 0.18, + "learning_rate": 1.8847045894304295e-05, + "loss": 0.5058, + "step": 2108 + }, + { + "epoch": 0.18, + "learning_rate": 1.884575823273481e-05, + "loss": 0.485, + "step": 2109 + }, + { + "epoch": 0.18, + "learning_rate": 1.8844469896550874e-05, + "loss": 0.4971, + "step": 2110 + }, + { + "epoch": 0.18, + "learning_rate": 1.8843180885850737e-05, + "loss": 0.5213, + "step": 2111 + }, + { + "epoch": 0.18, + "learning_rate": 1.8841891200732706e-05, + "loss": 0.4799, + "step": 2112 + }, + { + "epoch": 0.18, + "learning_rate": 1.8840600841295143e-05, + "loss": 0.5118, + "step": 2113 + }, + { + "epoch": 0.18, + "learning_rate": 1.883930980763645e-05, + "loss": 0.5144, + "step": 2114 + }, + { + "epoch": 0.18, + "learning_rate": 1.8838018099855085e-05, + "loss": 0.5252, + "step": 2115 + }, + { + "epoch": 0.18, + "learning_rate": 1.8836725718049562e-05, + "loss": 0.4834, + "step": 2116 + }, + { + "epoch": 0.18, + "learning_rate": 1.8835432662318446e-05, + "loss": 0.507, + "step": 2117 + }, + { + "epoch": 0.18, + "learning_rate": 1.883413893276035e-05, + "loss": 0.5095, + "step": 2118 + }, + { + "epoch": 0.18, + "learning_rate": 1.8832844529473933e-05, + "loss": 0.4972, + "step": 2119 + }, + { + "epoch": 0.18, + "learning_rate": 1.8831549452557918e-05, + "loss": 0.504, + "step": 2120 + }, + { + "epoch": 0.18, + "learning_rate": 1.883025370211107e-05, + "loss": 0.5052, + "step": 2121 + }, + { + "epoch": 0.18, + "learning_rate": 1.8828957278232215e-05, + "loss": 0.5034, + "step": 2122 + }, + { + "epoch": 0.18, + "learning_rate": 1.882766018102021e-05, + "loss": 0.5364, + "step": 2123 + }, + { + "epoch": 0.18, + "learning_rate": 1.882636241057399e-05, + "loss": 0.5123, + "step": 2124 + }, + { + "epoch": 0.18, + "learning_rate": 1.8825063966992524e-05, + "loss": 0.4931, + "step": 2125 + }, + { + "epoch": 0.18, + "learning_rate": 1.8823764850374834e-05, + "loss": 0.4918, + "step": 2126 + }, + { + "epoch": 0.18, + "learning_rate": 1.882246506082e-05, + "loss": 0.4919, + "step": 2127 + }, + { + "epoch": 0.18, + "learning_rate": 1.8821164598427148e-05, + "loss": 0.4965, + "step": 2128 + }, + { + "epoch": 0.18, + "learning_rate": 1.8819863463295456e-05, + "loss": 0.4966, + "step": 2129 + }, + { + "epoch": 0.18, + "learning_rate": 1.8818561655524154e-05, + "loss": 0.5108, + "step": 2130 + }, + { + "epoch": 0.18, + "learning_rate": 1.8817259175212524e-05, + "loss": 0.4824, + "step": 2131 + }, + { + "epoch": 0.18, + "learning_rate": 1.88159560224599e-05, + "loss": 0.5112, + "step": 2132 + }, + { + "epoch": 0.18, + "learning_rate": 1.881465219736566e-05, + "loss": 0.5038, + "step": 2133 + }, + { + "epoch": 0.18, + "learning_rate": 1.8813347700029244e-05, + "loss": 0.5138, + "step": 2134 + }, + { + "epoch": 0.18, + "learning_rate": 1.8812042530550142e-05, + "loss": 0.4822, + "step": 2135 + }, + { + "epoch": 0.18, + "learning_rate": 1.8810736689027887e-05, + "loss": 0.4924, + "step": 2136 + }, + { + "epoch": 0.18, + "learning_rate": 1.8809430175562068e-05, + "loss": 0.4809, + "step": 2137 + }, + { + "epoch": 0.18, + "learning_rate": 1.880812299025232e-05, + "loss": 0.4805, + "step": 2138 + }, + { + "epoch": 0.18, + "learning_rate": 1.8806815133198345e-05, + "loss": 0.5124, + "step": 2139 + }, + { + "epoch": 0.18, + "learning_rate": 1.880550660449988e-05, + "loss": 0.4811, + "step": 2140 + }, + { + "epoch": 0.18, + "learning_rate": 1.880419740425672e-05, + "loss": 0.4935, + "step": 2141 + }, + { + "epoch": 0.18, + "learning_rate": 1.8802887532568706e-05, + "loss": 0.5001, + "step": 2142 + }, + { + "epoch": 0.18, + "learning_rate": 1.8801576989535745e-05, + "loss": 0.5272, + "step": 2143 + }, + { + "epoch": 0.18, + "learning_rate": 1.8800265775257772e-05, + "loss": 0.4966, + "step": 2144 + }, + { + "epoch": 0.18, + "learning_rate": 1.879895388983479e-05, + "loss": 0.5253, + "step": 2145 + }, + { + "epoch": 0.18, + "learning_rate": 1.8797641333366852e-05, + "loss": 0.5176, + "step": 2146 + }, + { + "epoch": 0.18, + "learning_rate": 1.8796328105954055e-05, + "loss": 0.4923, + "step": 2147 + }, + { + "epoch": 0.18, + "learning_rate": 1.8795014207696555e-05, + "loss": 0.5136, + "step": 2148 + }, + { + "epoch": 0.18, + "learning_rate": 1.8793699638694555e-05, + "loss": 0.5009, + "step": 2149 + }, + { + "epoch": 0.18, + "learning_rate": 1.8792384399048303e-05, + "loss": 0.5141, + "step": 2150 + }, + { + "epoch": 0.18, + "learning_rate": 1.8791068488858113e-05, + "loss": 0.4933, + "step": 2151 + }, + { + "epoch": 0.18, + "learning_rate": 1.878975190822434e-05, + "loss": 0.5033, + "step": 2152 + }, + { + "epoch": 0.18, + "learning_rate": 1.8788434657247386e-05, + "loss": 0.5189, + "step": 2153 + }, + { + "epoch": 0.18, + "learning_rate": 1.878711673602772e-05, + "loss": 0.5032, + "step": 2154 + }, + { + "epoch": 0.18, + "learning_rate": 1.878579814466584e-05, + "loss": 0.5046, + "step": 2155 + }, + { + "epoch": 0.18, + "learning_rate": 1.8784478883262318e-05, + "loss": 0.4918, + "step": 2156 + }, + { + "epoch": 0.18, + "learning_rate": 1.8783158951917763e-05, + "loss": 0.497, + "step": 2157 + }, + { + "epoch": 0.18, + "learning_rate": 1.8781838350732834e-05, + "loss": 0.4805, + "step": 2158 + }, + { + "epoch": 0.18, + "learning_rate": 1.8780517079808255e-05, + "loss": 0.4968, + "step": 2159 + }, + { + "epoch": 0.18, + "learning_rate": 1.877919513924478e-05, + "loss": 0.509, + "step": 2160 + }, + { + "epoch": 0.18, + "learning_rate": 1.8777872529143236e-05, + "loss": 0.5096, + "step": 2161 + }, + { + "epoch": 0.18, + "learning_rate": 1.877654924960448e-05, + "loss": 0.497, + "step": 2162 + }, + { + "epoch": 0.18, + "learning_rate": 1.8775225300729444e-05, + "loss": 0.5192, + "step": 2163 + }, + { + "epoch": 0.18, + "learning_rate": 1.8773900682619092e-05, + "loss": 0.4834, + "step": 2164 + }, + { + "epoch": 0.18, + "learning_rate": 1.877257539537444e-05, + "loss": 0.4962, + "step": 2165 + }, + { + "epoch": 0.18, + "learning_rate": 1.8771249439096565e-05, + "loss": 0.4987, + "step": 2166 + }, + { + "epoch": 0.18, + "learning_rate": 1.8769922813886588e-05, + "loss": 0.5191, + "step": 2167 + }, + { + "epoch": 0.18, + "learning_rate": 1.8768595519845683e-05, + "loss": 0.5017, + "step": 2168 + }, + { + "epoch": 0.18, + "learning_rate": 1.876726755707508e-05, + "loss": 0.4995, + "step": 2169 + }, + { + "epoch": 0.19, + "learning_rate": 1.8765938925676046e-05, + "loss": 0.4902, + "step": 2170 + }, + { + "epoch": 0.19, + "learning_rate": 1.8764609625749918e-05, + "loss": 0.5379, + "step": 2171 + }, + { + "epoch": 0.19, + "learning_rate": 1.8763279657398062e-05, + "loss": 0.4787, + "step": 2172 + }, + { + "epoch": 0.19, + "learning_rate": 1.876194902072192e-05, + "loss": 0.5007, + "step": 2173 + }, + { + "epoch": 0.19, + "learning_rate": 1.8760617715822964e-05, + "loss": 0.4939, + "step": 2174 + }, + { + "epoch": 0.19, + "learning_rate": 1.8759285742802725e-05, + "loss": 0.5019, + "step": 2175 + }, + { + "epoch": 0.19, + "learning_rate": 1.8757953101762786e-05, + "loss": 0.5194, + "step": 2176 + }, + { + "epoch": 0.19, + "learning_rate": 1.875661979280478e-05, + "loss": 0.49, + "step": 2177 + }, + { + "epoch": 0.19, + "learning_rate": 1.8755285816030395e-05, + "loss": 0.4972, + "step": 2178 + }, + { + "epoch": 0.19, + "learning_rate": 1.875395117154136e-05, + "loss": 0.4957, + "step": 2179 + }, + { + "epoch": 0.19, + "learning_rate": 1.875261585943946e-05, + "loss": 0.5101, + "step": 2180 + }, + { + "epoch": 0.19, + "learning_rate": 1.8751279879826533e-05, + "loss": 0.488, + "step": 2181 + }, + { + "epoch": 0.19, + "learning_rate": 1.8749943232804467e-05, + "loss": 0.4988, + "step": 2182 + }, + { + "epoch": 0.19, + "learning_rate": 1.87486059184752e-05, + "loss": 0.505, + "step": 2183 + }, + { + "epoch": 0.19, + "learning_rate": 1.8747267936940723e-05, + "loss": 0.5058, + "step": 2184 + }, + { + "epoch": 0.19, + "learning_rate": 1.8745929288303075e-05, + "loss": 0.5037, + "step": 2185 + }, + { + "epoch": 0.19, + "learning_rate": 1.8744589972664345e-05, + "loss": 0.5127, + "step": 2186 + }, + { + "epoch": 0.19, + "learning_rate": 1.8743249990126676e-05, + "loss": 0.4789, + "step": 2187 + }, + { + "epoch": 0.19, + "learning_rate": 1.874190934079226e-05, + "loss": 0.4954, + "step": 2188 + }, + { + "epoch": 0.19, + "learning_rate": 1.8740568024763344e-05, + "loss": 0.5132, + "step": 2189 + }, + { + "epoch": 0.19, + "learning_rate": 1.8739226042142216e-05, + "loss": 0.4924, + "step": 2190 + }, + { + "epoch": 0.19, + "learning_rate": 1.873788339303123e-05, + "loss": 0.4984, + "step": 2191 + }, + { + "epoch": 0.19, + "learning_rate": 1.8736540077532773e-05, + "loss": 0.5179, + "step": 2192 + }, + { + "epoch": 0.19, + "learning_rate": 1.8735196095749298e-05, + "loss": 0.4941, + "step": 2193 + }, + { + "epoch": 0.19, + "learning_rate": 1.8733851447783296e-05, + "loss": 0.5079, + "step": 2194 + }, + { + "epoch": 0.19, + "learning_rate": 1.8732506133737324e-05, + "loss": 0.5, + "step": 2195 + }, + { + "epoch": 0.19, + "learning_rate": 1.8731160153713978e-05, + "loss": 0.5091, + "step": 2196 + }, + { + "epoch": 0.19, + "learning_rate": 1.8729813507815903e-05, + "loss": 0.4959, + "step": 2197 + }, + { + "epoch": 0.19, + "learning_rate": 1.8728466196145806e-05, + "loss": 0.4936, + "step": 2198 + }, + { + "epoch": 0.19, + "learning_rate": 1.8727118218806433e-05, + "loss": 0.5095, + "step": 2199 + }, + { + "epoch": 0.19, + "learning_rate": 1.87257695759006e-05, + "loss": 0.4934, + "step": 2200 + }, + { + "epoch": 0.19, + "learning_rate": 1.872442026753114e-05, + "loss": 0.5148, + "step": 2201 + }, + { + "epoch": 0.19, + "learning_rate": 1.8723070293800972e-05, + "loss": 0.5067, + "step": 2202 + }, + { + "epoch": 0.19, + "learning_rate": 1.8721719654813043e-05, + "loss": 0.5013, + "step": 2203 + }, + { + "epoch": 0.19, + "learning_rate": 1.8720368350670363e-05, + "loss": 0.5082, + "step": 2204 + }, + { + "epoch": 0.19, + "learning_rate": 1.8719016381475987e-05, + "loss": 0.531, + "step": 2205 + }, + { + "epoch": 0.19, + "learning_rate": 1.871766374733302e-05, + "loss": 0.5092, + "step": 2206 + }, + { + "epoch": 0.19, + "learning_rate": 1.871631044834462e-05, + "loss": 0.4989, + "step": 2207 + }, + { + "epoch": 0.19, + "learning_rate": 1.8714956484613996e-05, + "loss": 0.4956, + "step": 2208 + }, + { + "epoch": 0.19, + "learning_rate": 1.8713601856244406e-05, + "loss": 0.4939, + "step": 2209 + }, + { + "epoch": 0.19, + "learning_rate": 1.871224656333916e-05, + "loss": 0.5283, + "step": 2210 + }, + { + "epoch": 0.19, + "learning_rate": 1.8710890606001618e-05, + "loss": 0.4923, + "step": 2211 + }, + { + "epoch": 0.19, + "learning_rate": 1.8709533984335194e-05, + "loss": 0.5101, + "step": 2212 + }, + { + "epoch": 0.19, + "learning_rate": 1.8708176698443347e-05, + "loss": 0.5032, + "step": 2213 + }, + { + "epoch": 0.19, + "learning_rate": 1.8706818748429585e-05, + "loss": 0.5099, + "step": 2214 + }, + { + "epoch": 0.19, + "learning_rate": 1.870546013439748e-05, + "loss": 0.5116, + "step": 2215 + }, + { + "epoch": 0.19, + "learning_rate": 1.8704100856450642e-05, + "loss": 0.4842, + "step": 2216 + }, + { + "epoch": 0.19, + "learning_rate": 1.870274091469273e-05, + "loss": 0.5002, + "step": 2217 + }, + { + "epoch": 0.19, + "learning_rate": 1.8701380309227465e-05, + "loss": 0.4895, + "step": 2218 + }, + { + "epoch": 0.19, + "learning_rate": 1.8700019040158614e-05, + "loss": 0.4993, + "step": 2219 + }, + { + "epoch": 0.19, + "learning_rate": 1.8698657107589983e-05, + "loss": 0.4972, + "step": 2220 + }, + { + "epoch": 0.19, + "learning_rate": 1.869729451162545e-05, + "loss": 0.5157, + "step": 2221 + }, + { + "epoch": 0.19, + "learning_rate": 1.8695931252368923e-05, + "loss": 0.4967, + "step": 2222 + }, + { + "epoch": 0.19, + "learning_rate": 1.8694567329924376e-05, + "loss": 0.4995, + "step": 2223 + }, + { + "epoch": 0.19, + "learning_rate": 1.869320274439583e-05, + "loss": 0.497, + "step": 2224 + }, + { + "epoch": 0.19, + "learning_rate": 1.8691837495887345e-05, + "loss": 0.4833, + "step": 2225 + }, + { + "epoch": 0.19, + "learning_rate": 1.8690471584503045e-05, + "loss": 0.5104, + "step": 2226 + }, + { + "epoch": 0.19, + "learning_rate": 1.86891050103471e-05, + "loss": 0.4871, + "step": 2227 + }, + { + "epoch": 0.19, + "learning_rate": 1.8687737773523734e-05, + "loss": 0.5246, + "step": 2228 + }, + { + "epoch": 0.19, + "learning_rate": 1.8686369874137212e-05, + "loss": 0.4909, + "step": 2229 + }, + { + "epoch": 0.19, + "learning_rate": 1.8685001312291863e-05, + "loss": 0.5019, + "step": 2230 + }, + { + "epoch": 0.19, + "learning_rate": 1.8683632088092053e-05, + "loss": 0.5041, + "step": 2231 + }, + { + "epoch": 0.19, + "learning_rate": 1.8682262201642205e-05, + "loss": 0.4934, + "step": 2232 + }, + { + "epoch": 0.19, + "learning_rate": 1.8680891653046798e-05, + "loss": 0.5032, + "step": 2233 + }, + { + "epoch": 0.19, + "learning_rate": 1.8679520442410348e-05, + "loss": 0.5058, + "step": 2234 + }, + { + "epoch": 0.19, + "learning_rate": 1.8678148569837432e-05, + "loss": 0.5066, + "step": 2235 + }, + { + "epoch": 0.19, + "learning_rate": 1.867677603543268e-05, + "loss": 0.5195, + "step": 2236 + }, + { + "epoch": 0.19, + "learning_rate": 1.8675402839300763e-05, + "loss": 0.5057, + "step": 2237 + }, + { + "epoch": 0.19, + "learning_rate": 1.8674028981546405e-05, + "loss": 0.494, + "step": 2238 + }, + { + "epoch": 0.19, + "learning_rate": 1.8672654462274383e-05, + "loss": 0.489, + "step": 2239 + }, + { + "epoch": 0.19, + "learning_rate": 1.8671279281589528e-05, + "loss": 0.5029, + "step": 2240 + }, + { + "epoch": 0.19, + "learning_rate": 1.866990343959671e-05, + "loss": 0.5133, + "step": 2241 + }, + { + "epoch": 0.19, + "learning_rate": 1.8668526936400863e-05, + "loss": 0.5121, + "step": 2242 + }, + { + "epoch": 0.19, + "learning_rate": 1.866714977210696e-05, + "loss": 0.4737, + "step": 2243 + }, + { + "epoch": 0.19, + "learning_rate": 1.866577194682003e-05, + "loss": 0.5177, + "step": 2244 + }, + { + "epoch": 0.19, + "learning_rate": 1.8664393460645154e-05, + "loss": 0.4914, + "step": 2245 + }, + { + "epoch": 0.19, + "learning_rate": 1.8663014313687463e-05, + "loss": 0.5344, + "step": 2246 + }, + { + "epoch": 0.19, + "learning_rate": 1.866163450605213e-05, + "loss": 0.4913, + "step": 2247 + }, + { + "epoch": 0.19, + "learning_rate": 1.866025403784439e-05, + "loss": 0.5004, + "step": 2248 + }, + { + "epoch": 0.19, + "learning_rate": 1.8658872909169518e-05, + "loss": 0.4897, + "step": 2249 + }, + { + "epoch": 0.19, + "learning_rate": 1.865749112013285e-05, + "loss": 0.5, + "step": 2250 + }, + { + "epoch": 0.19, + "learning_rate": 1.8656108670839768e-05, + "loss": 0.4883, + "step": 2251 + }, + { + "epoch": 0.19, + "learning_rate": 1.86547255613957e-05, + "loss": 0.5137, + "step": 2252 + }, + { + "epoch": 0.19, + "learning_rate": 1.8653341791906124e-05, + "loss": 0.5233, + "step": 2253 + }, + { + "epoch": 0.19, + "learning_rate": 1.8651957362476582e-05, + "loss": 0.5055, + "step": 2254 + }, + { + "epoch": 0.19, + "learning_rate": 1.8650572273212646e-05, + "loss": 0.4814, + "step": 2255 + }, + { + "epoch": 0.19, + "learning_rate": 1.8649186524219956e-05, + "loss": 0.5084, + "step": 2256 + }, + { + "epoch": 0.19, + "learning_rate": 1.864780011560419e-05, + "loss": 0.508, + "step": 2257 + }, + { + "epoch": 0.19, + "learning_rate": 1.8646413047471084e-05, + "loss": 0.4876, + "step": 2258 + }, + { + "epoch": 0.19, + "learning_rate": 1.8645025319926425e-05, + "loss": 0.4898, + "step": 2259 + }, + { + "epoch": 0.19, + "learning_rate": 1.864363693307604e-05, + "loss": 0.5255, + "step": 2260 + }, + { + "epoch": 0.19, + "learning_rate": 1.8642247887025816e-05, + "loss": 0.5029, + "step": 2261 + }, + { + "epoch": 0.19, + "learning_rate": 1.8640858181881692e-05, + "loss": 0.505, + "step": 2262 + }, + { + "epoch": 0.19, + "learning_rate": 1.8639467817749642e-05, + "loss": 0.518, + "step": 2263 + }, + { + "epoch": 0.19, + "learning_rate": 1.8638076794735715e-05, + "loss": 0.4998, + "step": 2264 + }, + { + "epoch": 0.19, + "learning_rate": 1.863668511294598e-05, + "loss": 0.5184, + "step": 2265 + }, + { + "epoch": 0.19, + "learning_rate": 1.863529277248659e-05, + "loss": 0.494, + "step": 2266 + }, + { + "epoch": 0.19, + "learning_rate": 1.8633899773463716e-05, + "loss": 0.5021, + "step": 2267 + }, + { + "epoch": 0.19, + "learning_rate": 1.8632506115983603e-05, + "loss": 0.4742, + "step": 2268 + }, + { + "epoch": 0.19, + "learning_rate": 1.8631111800152532e-05, + "loss": 0.4952, + "step": 2269 + }, + { + "epoch": 0.19, + "learning_rate": 1.8629716826076843e-05, + "loss": 0.5019, + "step": 2270 + }, + { + "epoch": 0.19, + "learning_rate": 1.862832119386292e-05, + "loss": 0.5026, + "step": 2271 + }, + { + "epoch": 0.19, + "learning_rate": 1.86269249036172e-05, + "loss": 0.5068, + "step": 2272 + }, + { + "epoch": 0.19, + "learning_rate": 1.862552795544617e-05, + "loss": 0.5174, + "step": 2273 + }, + { + "epoch": 0.19, + "learning_rate": 1.8624130349456367e-05, + "loss": 0.4833, + "step": 2274 + }, + { + "epoch": 0.19, + "learning_rate": 1.8622732085754386e-05, + "loss": 0.495, + "step": 2275 + }, + { + "epoch": 0.19, + "learning_rate": 1.862133316444685e-05, + "loss": 0.5174, + "step": 2276 + }, + { + "epoch": 0.19, + "learning_rate": 1.8619933585640455e-05, + "loss": 0.4898, + "step": 2277 + }, + { + "epoch": 0.19, + "learning_rate": 1.861853334944194e-05, + "loss": 0.4926, + "step": 2278 + }, + { + "epoch": 0.19, + "learning_rate": 1.8617132455958085e-05, + "loss": 0.4977, + "step": 2279 + }, + { + "epoch": 0.19, + "learning_rate": 1.861573090529574e-05, + "loss": 0.4896, + "step": 2280 + }, + { + "epoch": 0.19, + "learning_rate": 1.8614328697561785e-05, + "loss": 0.4869, + "step": 2281 + }, + { + "epoch": 0.19, + "learning_rate": 1.8612925832863158e-05, + "loss": 0.4992, + "step": 2282 + }, + { + "epoch": 0.19, + "learning_rate": 1.8611522311306848e-05, + "loss": 0.504, + "step": 2283 + }, + { + "epoch": 0.19, + "learning_rate": 1.8610118132999896e-05, + "loss": 0.4848, + "step": 2284 + }, + { + "epoch": 0.19, + "learning_rate": 1.860871329804939e-05, + "loss": 0.4723, + "step": 2285 + }, + { + "epoch": 0.19, + "learning_rate": 1.8607307806562468e-05, + "loss": 0.504, + "step": 2286 + }, + { + "epoch": 0.2, + "learning_rate": 1.8605901658646318e-05, + "loss": 0.4878, + "step": 2287 + }, + { + "epoch": 0.2, + "learning_rate": 1.8604494854408176e-05, + "loss": 0.5208, + "step": 2288 + }, + { + "epoch": 0.2, + "learning_rate": 1.8603087393955338e-05, + "loss": 0.4942, + "step": 2289 + }, + { + "epoch": 0.2, + "learning_rate": 1.8601679277395136e-05, + "loss": 0.5078, + "step": 2290 + }, + { + "epoch": 0.2, + "learning_rate": 1.8600270504834964e-05, + "loss": 0.5138, + "step": 2291 + }, + { + "epoch": 0.2, + "learning_rate": 1.8598861076382252e-05, + "loss": 0.4908, + "step": 2292 + }, + { + "epoch": 0.2, + "learning_rate": 1.85974509921445e-05, + "loss": 0.5031, + "step": 2293 + }, + { + "epoch": 0.2, + "learning_rate": 1.8596040252229243e-05, + "loss": 0.4895, + "step": 2294 + }, + { + "epoch": 0.2, + "learning_rate": 1.8594628856744065e-05, + "loss": 0.506, + "step": 2295 + }, + { + "epoch": 0.2, + "learning_rate": 1.8593216805796612e-05, + "loss": 0.4751, + "step": 2296 + }, + { + "epoch": 0.2, + "learning_rate": 1.8591804099494572e-05, + "loss": 0.4875, + "step": 2297 + }, + { + "epoch": 0.2, + "learning_rate": 1.8590390737945675e-05, + "loss": 0.5114, + "step": 2298 + }, + { + "epoch": 0.2, + "learning_rate": 1.858897672125772e-05, + "loss": 0.5065, + "step": 2299 + }, + { + "epoch": 0.2, + "learning_rate": 1.858756204953854e-05, + "loss": 0.5082, + "step": 2300 + }, + { + "epoch": 0.2, + "learning_rate": 1.858614672289603e-05, + "loss": 0.5041, + "step": 2301 + }, + { + "epoch": 0.2, + "learning_rate": 1.8584730741438128e-05, + "loss": 0.4975, + "step": 2302 + }, + { + "epoch": 0.2, + "learning_rate": 1.8583314105272813e-05, + "loss": 0.4949, + "step": 2303 + }, + { + "epoch": 0.2, + "learning_rate": 1.858189681450813e-05, + "loss": 0.5121, + "step": 2304 + }, + { + "epoch": 0.2, + "learning_rate": 1.858047886925217e-05, + "loss": 0.5034, + "step": 2305 + }, + { + "epoch": 0.2, + "learning_rate": 1.857906026961307e-05, + "loss": 0.5087, + "step": 2306 + }, + { + "epoch": 0.2, + "learning_rate": 1.8577641015699016e-05, + "loss": 0.4966, + "step": 2307 + }, + { + "epoch": 0.2, + "learning_rate": 1.8576221107618244e-05, + "loss": 0.5216, + "step": 2308 + }, + { + "epoch": 0.2, + "learning_rate": 1.857480054547905e-05, + "loss": 0.5107, + "step": 2309 + }, + { + "epoch": 0.2, + "learning_rate": 1.8573379329389768e-05, + "loss": 0.4932, + "step": 2310 + }, + { + "epoch": 0.2, + "learning_rate": 1.8571957459458785e-05, + "loss": 0.5186, + "step": 2311 + }, + { + "epoch": 0.2, + "learning_rate": 1.8570534935794537e-05, + "loss": 0.5101, + "step": 2312 + }, + { + "epoch": 0.2, + "learning_rate": 1.8569111758505517e-05, + "loss": 0.4876, + "step": 2313 + }, + { + "epoch": 0.2, + "learning_rate": 1.8567687927700255e-05, + "loss": 0.4892, + "step": 2314 + }, + { + "epoch": 0.2, + "learning_rate": 1.8566263443487346e-05, + "loss": 0.4945, + "step": 2315 + }, + { + "epoch": 0.2, + "learning_rate": 1.8564838305975422e-05, + "loss": 0.5027, + "step": 2316 + }, + { + "epoch": 0.2, + "learning_rate": 1.8563412515273173e-05, + "loss": 0.5115, + "step": 2317 + }, + { + "epoch": 0.2, + "learning_rate": 1.8561986071489335e-05, + "loss": 0.5071, + "step": 2318 + }, + { + "epoch": 0.2, + "learning_rate": 1.8560558974732693e-05, + "loss": 0.5034, + "step": 2319 + }, + { + "epoch": 0.2, + "learning_rate": 1.8559131225112085e-05, + "loss": 0.4844, + "step": 2320 + }, + { + "epoch": 0.2, + "learning_rate": 1.85577028227364e-05, + "loss": 0.4914, + "step": 2321 + }, + { + "epoch": 0.2, + "learning_rate": 1.8556273767714563e-05, + "loss": 0.4977, + "step": 2322 + }, + { + "epoch": 0.2, + "learning_rate": 1.855484406015557e-05, + "loss": 0.5028, + "step": 2323 + }, + { + "epoch": 0.2, + "learning_rate": 1.8553413700168456e-05, + "loss": 0.4943, + "step": 2324 + }, + { + "epoch": 0.2, + "learning_rate": 1.85519826878623e-05, + "loss": 0.4963, + "step": 2325 + }, + { + "epoch": 0.2, + "learning_rate": 1.8550551023346245e-05, + "loss": 0.4902, + "step": 2326 + }, + { + "epoch": 0.2, + "learning_rate": 1.854911870672947e-05, + "loss": 0.5031, + "step": 2327 + }, + { + "epoch": 0.2, + "learning_rate": 1.8547685738121205e-05, + "loss": 0.5063, + "step": 2328 + }, + { + "epoch": 0.2, + "learning_rate": 1.8546252117630746e-05, + "loss": 0.4983, + "step": 2329 + }, + { + "epoch": 0.2, + "learning_rate": 1.8544817845367422e-05, + "loss": 0.4992, + "step": 2330 + }, + { + "epoch": 0.2, + "learning_rate": 1.8543382921440614e-05, + "loss": 0.5001, + "step": 2331 + }, + { + "epoch": 0.2, + "learning_rate": 1.8541947345959753e-05, + "loss": 0.5027, + "step": 2332 + }, + { + "epoch": 0.2, + "learning_rate": 1.8540511119034336e-05, + "loss": 0.4926, + "step": 2333 + }, + { + "epoch": 0.2, + "learning_rate": 1.8539074240773875e-05, + "loss": 0.5017, + "step": 2334 + }, + { + "epoch": 0.2, + "learning_rate": 1.8537636711287968e-05, + "loss": 0.5005, + "step": 2335 + }, + { + "epoch": 0.2, + "learning_rate": 1.853619853068624e-05, + "loss": 0.499, + "step": 2336 + }, + { + "epoch": 0.2, + "learning_rate": 1.8534759699078374e-05, + "loss": 0.5384, + "step": 2337 + }, + { + "epoch": 0.2, + "learning_rate": 1.8533320216574103e-05, + "loss": 0.5179, + "step": 2338 + }, + { + "epoch": 0.2, + "learning_rate": 1.8531880083283207e-05, + "loss": 0.5149, + "step": 2339 + }, + { + "epoch": 0.2, + "learning_rate": 1.8530439299315516e-05, + "loss": 0.4896, + "step": 2340 + }, + { + "epoch": 0.2, + "learning_rate": 1.852899786478091e-05, + "loss": 0.5104, + "step": 2341 + }, + { + "epoch": 0.2, + "learning_rate": 1.852755577978932e-05, + "loss": 0.4717, + "step": 2342 + }, + { + "epoch": 0.2, + "learning_rate": 1.8526113044450725e-05, + "loss": 0.5047, + "step": 2343 + }, + { + "epoch": 0.2, + "learning_rate": 1.8524669658875153e-05, + "loss": 0.4973, + "step": 2344 + }, + { + "epoch": 0.2, + "learning_rate": 1.8523225623172684e-05, + "loss": 0.5047, + "step": 2345 + }, + { + "epoch": 0.2, + "learning_rate": 1.8521780937453445e-05, + "loss": 0.5253, + "step": 2346 + }, + { + "epoch": 0.2, + "learning_rate": 1.8520335601827614e-05, + "loss": 0.4828, + "step": 2347 + }, + { + "epoch": 0.2, + "learning_rate": 1.851888961640542e-05, + "loss": 0.4913, + "step": 2348 + }, + { + "epoch": 0.2, + "learning_rate": 1.8517442981297137e-05, + "loss": 0.4896, + "step": 2349 + }, + { + "epoch": 0.2, + "learning_rate": 1.8515995696613096e-05, + "loss": 0.4904, + "step": 2350 + }, + { + "epoch": 0.2, + "learning_rate": 1.8514547762463666e-05, + "loss": 0.5155, + "step": 2351 + }, + { + "epoch": 0.2, + "learning_rate": 1.851309917895928e-05, + "loss": 0.4868, + "step": 2352 + }, + { + "epoch": 0.2, + "learning_rate": 1.8511649946210407e-05, + "loss": 0.4826, + "step": 2353 + }, + { + "epoch": 0.2, + "learning_rate": 1.8510200064327576e-05, + "loss": 0.5064, + "step": 2354 + }, + { + "epoch": 0.2, + "learning_rate": 1.850874953342136e-05, + "loss": 0.5015, + "step": 2355 + }, + { + "epoch": 0.2, + "learning_rate": 1.8507298353602373e-05, + "loss": 0.5003, + "step": 2356 + }, + { + "epoch": 0.2, + "learning_rate": 1.8505846524981304e-05, + "loss": 0.5148, + "step": 2357 + }, + { + "epoch": 0.2, + "learning_rate": 1.850439404766887e-05, + "loss": 0.4877, + "step": 2358 + }, + { + "epoch": 0.2, + "learning_rate": 1.8502940921775837e-05, + "loss": 0.5071, + "step": 2359 + }, + { + "epoch": 0.2, + "learning_rate": 1.8501487147413033e-05, + "loss": 0.5028, + "step": 2360 + }, + { + "epoch": 0.2, + "learning_rate": 1.8500032724691327e-05, + "loss": 0.5081, + "step": 2361 + }, + { + "epoch": 0.2, + "learning_rate": 1.8498577653721638e-05, + "loss": 0.4877, + "step": 2362 + }, + { + "epoch": 0.2, + "learning_rate": 1.8497121934614935e-05, + "loss": 0.4916, + "step": 2363 + }, + { + "epoch": 0.2, + "learning_rate": 1.849566556748224e-05, + "loss": 0.4967, + "step": 2364 + }, + { + "epoch": 0.2, + "learning_rate": 1.849420855243462e-05, + "loss": 0.4912, + "step": 2365 + }, + { + "epoch": 0.2, + "learning_rate": 1.8492750889583193e-05, + "loss": 0.5384, + "step": 2366 + }, + { + "epoch": 0.2, + "learning_rate": 1.8491292579039128e-05, + "loss": 0.5045, + "step": 2367 + }, + { + "epoch": 0.2, + "learning_rate": 1.8489833620913644e-05, + "loss": 0.5018, + "step": 2368 + }, + { + "epoch": 0.2, + "learning_rate": 1.8488374015317994e-05, + "loss": 0.5011, + "step": 2369 + }, + { + "epoch": 0.2, + "learning_rate": 1.8486913762363513e-05, + "loss": 0.4956, + "step": 2370 + }, + { + "epoch": 0.2, + "learning_rate": 1.8485452862161555e-05, + "loss": 0.5081, + "step": 2371 + }, + { + "epoch": 0.2, + "learning_rate": 1.8483991314823535e-05, + "loss": 0.5057, + "step": 2372 + }, + { + "epoch": 0.2, + "learning_rate": 1.848252912046092e-05, + "loss": 0.4943, + "step": 2373 + }, + { + "epoch": 0.2, + "learning_rate": 1.848106627918522e-05, + "loss": 0.4875, + "step": 2374 + }, + { + "epoch": 0.2, + "learning_rate": 1.8479602791107994e-05, + "loss": 0.4837, + "step": 2375 + }, + { + "epoch": 0.2, + "learning_rate": 1.847813865634086e-05, + "loss": 0.5053, + "step": 2376 + }, + { + "epoch": 0.2, + "learning_rate": 1.847667387499548e-05, + "loss": 0.5075, + "step": 2377 + }, + { + "epoch": 0.2, + "learning_rate": 1.8475208447183558e-05, + "loss": 0.508, + "step": 2378 + }, + { + "epoch": 0.2, + "learning_rate": 1.8473742373016858e-05, + "loss": 0.506, + "step": 2379 + }, + { + "epoch": 0.2, + "learning_rate": 1.8472275652607184e-05, + "loss": 0.5065, + "step": 2380 + }, + { + "epoch": 0.2, + "learning_rate": 1.8470808286066402e-05, + "loss": 0.4917, + "step": 2381 + }, + { + "epoch": 0.2, + "learning_rate": 1.846934027350642e-05, + "loss": 0.5121, + "step": 2382 + }, + { + "epoch": 0.2, + "learning_rate": 1.8467871615039182e-05, + "loss": 0.5014, + "step": 2383 + }, + { + "epoch": 0.2, + "learning_rate": 1.846640231077671e-05, + "loss": 0.4826, + "step": 2384 + }, + { + "epoch": 0.2, + "learning_rate": 1.8464932360831046e-05, + "loss": 0.5172, + "step": 2385 + }, + { + "epoch": 0.2, + "learning_rate": 1.8463461765314302e-05, + "loss": 0.5217, + "step": 2386 + }, + { + "epoch": 0.2, + "learning_rate": 1.8461990524338626e-05, + "loss": 0.5019, + "step": 2387 + }, + { + "epoch": 0.2, + "learning_rate": 1.846051863801623e-05, + "loss": 0.4985, + "step": 2388 + }, + { + "epoch": 0.2, + "learning_rate": 1.845904610645936e-05, + "loss": 0.4961, + "step": 2389 + }, + { + "epoch": 0.2, + "learning_rate": 1.8457572929780315e-05, + "loss": 0.5196, + "step": 2390 + }, + { + "epoch": 0.2, + "learning_rate": 1.8456099108091455e-05, + "loss": 0.512, + "step": 2391 + }, + { + "epoch": 0.2, + "learning_rate": 1.845462464150517e-05, + "loss": 0.504, + "step": 2392 + }, + { + "epoch": 0.2, + "learning_rate": 1.8453149530133912e-05, + "loss": 0.4946, + "step": 2393 + }, + { + "epoch": 0.2, + "learning_rate": 1.8451673774090184e-05, + "loss": 0.5097, + "step": 2394 + }, + { + "epoch": 0.2, + "learning_rate": 1.8450197373486527e-05, + "loss": 0.5103, + "step": 2395 + }, + { + "epoch": 0.2, + "learning_rate": 1.8448720328435538e-05, + "loss": 0.5079, + "step": 2396 + }, + { + "epoch": 0.2, + "learning_rate": 1.844724263904987e-05, + "loss": 0.49, + "step": 2397 + }, + { + "epoch": 0.2, + "learning_rate": 1.8445764305442205e-05, + "loss": 0.4892, + "step": 2398 + }, + { + "epoch": 0.2, + "learning_rate": 1.84442853277253e-05, + "loss": 0.4892, + "step": 2399 + }, + { + "epoch": 0.2, + "learning_rate": 1.8442805706011936e-05, + "loss": 0.5174, + "step": 2400 + }, + { + "epoch": 0.2, + "learning_rate": 1.8441325440414965e-05, + "loss": 0.488, + "step": 2401 + }, + { + "epoch": 0.2, + "learning_rate": 1.8439844531047275e-05, + "loss": 0.5001, + "step": 2402 + }, + { + "epoch": 0.2, + "learning_rate": 1.8438362978021804e-05, + "loss": 0.4919, + "step": 2403 + }, + { + "epoch": 0.2, + "learning_rate": 1.8436880781451545e-05, + "loss": 0.4784, + "step": 2404 + }, + { + "epoch": 0.21, + "learning_rate": 1.8435397941449533e-05, + "loss": 0.5088, + "step": 2405 + }, + { + "epoch": 0.21, + "learning_rate": 1.843391445812886e-05, + "loss": 0.503, + "step": 2406 + }, + { + "epoch": 0.21, + "learning_rate": 1.8432430331602654e-05, + "loss": 0.5201, + "step": 2407 + }, + { + "epoch": 0.21, + "learning_rate": 1.8430945561984114e-05, + "loss": 0.5311, + "step": 2408 + }, + { + "epoch": 0.21, + "learning_rate": 1.8429460149386462e-05, + "loss": 0.5133, + "step": 2409 + }, + { + "epoch": 0.21, + "learning_rate": 1.842797409392299e-05, + "loss": 0.4814, + "step": 2410 + }, + { + "epoch": 0.21, + "learning_rate": 1.842648739570703e-05, + "loss": 0.4991, + "step": 2411 + }, + { + "epoch": 0.21, + "learning_rate": 1.8425000054851954e-05, + "loss": 0.5014, + "step": 2412 + }, + { + "epoch": 0.21, + "learning_rate": 1.8423512071471207e-05, + "loss": 0.4861, + "step": 2413 + }, + { + "epoch": 0.21, + "learning_rate": 1.8422023445678258e-05, + "loss": 0.5131, + "step": 2414 + }, + { + "epoch": 0.21, + "learning_rate": 1.842053417758664e-05, + "loss": 0.5099, + "step": 2415 + }, + { + "epoch": 0.21, + "learning_rate": 1.841904426730994e-05, + "loss": 0.5113, + "step": 2416 + }, + { + "epoch": 0.21, + "learning_rate": 1.8417553714961767e-05, + "loss": 0.504, + "step": 2417 + }, + { + "epoch": 0.21, + "learning_rate": 1.8416062520655805e-05, + "loss": 0.5193, + "step": 2418 + }, + { + "epoch": 0.21, + "learning_rate": 1.8414570684505783e-05, + "loss": 0.5098, + "step": 2419 + }, + { + "epoch": 0.21, + "learning_rate": 1.841307820662547e-05, + "loss": 0.4953, + "step": 2420 + }, + { + "epoch": 0.21, + "learning_rate": 1.841158508712869e-05, + "loss": 0.5008, + "step": 2421 + }, + { + "epoch": 0.21, + "learning_rate": 1.841009132612931e-05, + "loss": 0.4836, + "step": 2422 + }, + { + "epoch": 0.21, + "learning_rate": 1.8408596923741258e-05, + "loss": 0.5008, + "step": 2423 + }, + { + "epoch": 0.21, + "learning_rate": 1.84071018800785e-05, + "loss": 0.5356, + "step": 2424 + }, + { + "epoch": 0.21, + "learning_rate": 1.8405606195255052e-05, + "loss": 0.5033, + "step": 2425 + }, + { + "epoch": 0.21, + "learning_rate": 1.8404109869384985e-05, + "loss": 0.4944, + "step": 2426 + }, + { + "epoch": 0.21, + "learning_rate": 1.840261290258241e-05, + "loss": 0.4778, + "step": 2427 + }, + { + "epoch": 0.21, + "learning_rate": 1.84011152949615e-05, + "loss": 0.5047, + "step": 2428 + }, + { + "epoch": 0.21, + "learning_rate": 1.839961704663646e-05, + "loss": 0.5011, + "step": 2429 + }, + { + "epoch": 0.21, + "learning_rate": 1.839811815772156e-05, + "loss": 0.4888, + "step": 2430 + }, + { + "epoch": 0.21, + "learning_rate": 1.8396618628331106e-05, + "loss": 0.5043, + "step": 2431 + }, + { + "epoch": 0.21, + "learning_rate": 1.839511845857946e-05, + "loss": 0.4998, + "step": 2432 + }, + { + "epoch": 0.21, + "learning_rate": 1.8393617648581035e-05, + "loss": 0.4753, + "step": 2433 + }, + { + "epoch": 0.21, + "learning_rate": 1.8392116198450282e-05, + "loss": 0.5063, + "step": 2434 + }, + { + "epoch": 0.21, + "learning_rate": 1.8390614108301715e-05, + "loss": 0.4999, + "step": 2435 + }, + { + "epoch": 0.21, + "learning_rate": 1.8389111378249884e-05, + "loss": 0.4904, + "step": 2436 + }, + { + "epoch": 0.21, + "learning_rate": 1.8387608008409396e-05, + "loss": 0.514, + "step": 2437 + }, + { + "epoch": 0.21, + "learning_rate": 1.8386103998894908e-05, + "loss": 0.4947, + "step": 2438 + }, + { + "epoch": 0.21, + "learning_rate": 1.838459934982111e-05, + "loss": 0.5258, + "step": 2439 + }, + { + "epoch": 0.21, + "learning_rate": 1.8383094061302767e-05, + "loss": 0.476, + "step": 2440 + }, + { + "epoch": 0.21, + "learning_rate": 1.838158813345467e-05, + "loss": 0.4872, + "step": 2441 + }, + { + "epoch": 0.21, + "learning_rate": 1.8380081566391672e-05, + "loss": 0.5008, + "step": 2442 + }, + { + "epoch": 0.21, + "learning_rate": 1.8378574360228668e-05, + "loss": 0.4901, + "step": 2443 + }, + { + "epoch": 0.21, + "learning_rate": 1.8377066515080604e-05, + "loss": 0.4983, + "step": 2444 + }, + { + "epoch": 0.21, + "learning_rate": 1.837555803106247e-05, + "loss": 0.4985, + "step": 2445 + }, + { + "epoch": 0.21, + "learning_rate": 1.8374048908289318e-05, + "loss": 0.5157, + "step": 2446 + }, + { + "epoch": 0.21, + "learning_rate": 1.8372539146876235e-05, + "loss": 0.5111, + "step": 2447 + }, + { + "epoch": 0.21, + "learning_rate": 1.837102874693836e-05, + "loss": 0.4898, + "step": 2448 + }, + { + "epoch": 0.21, + "learning_rate": 1.8369517708590888e-05, + "loss": 0.5008, + "step": 2449 + }, + { + "epoch": 0.21, + "learning_rate": 1.8368006031949054e-05, + "loss": 0.4893, + "step": 2450 + }, + { + "epoch": 0.21, + "learning_rate": 1.836649371712814e-05, + "loss": 0.4908, + "step": 2451 + }, + { + "epoch": 0.21, + "learning_rate": 1.836498076424349e-05, + "loss": 0.4923, + "step": 2452 + }, + { + "epoch": 0.21, + "learning_rate": 1.836346717341048e-05, + "loss": 0.4783, + "step": 2453 + }, + { + "epoch": 0.21, + "learning_rate": 1.8361952944744554e-05, + "loss": 0.5053, + "step": 2454 + }, + { + "epoch": 0.21, + "learning_rate": 1.836043807836118e-05, + "loss": 0.5041, + "step": 2455 + }, + { + "epoch": 0.21, + "learning_rate": 1.83589225743759e-05, + "loss": 0.4935, + "step": 2456 + }, + { + "epoch": 0.21, + "learning_rate": 1.8357406432904283e-05, + "loss": 0.4981, + "step": 2457 + }, + { + "epoch": 0.21, + "learning_rate": 1.835588965406196e-05, + "loss": 0.5098, + "step": 2458 + }, + { + "epoch": 0.21, + "learning_rate": 1.8354372237964608e-05, + "loss": 0.4813, + "step": 2459 + }, + { + "epoch": 0.21, + "learning_rate": 1.8352854184727954e-05, + "loss": 0.5296, + "step": 2460 + }, + { + "epoch": 0.21, + "learning_rate": 1.8351335494467762e-05, + "loss": 0.485, + "step": 2461 + }, + { + "epoch": 0.21, + "learning_rate": 1.834981616729986e-05, + "loss": 0.5007, + "step": 2462 + }, + { + "epoch": 0.21, + "learning_rate": 1.8348296203340123e-05, + "loss": 0.5022, + "step": 2463 + }, + { + "epoch": 0.21, + "learning_rate": 1.8346775602704464e-05, + "loss": 0.5271, + "step": 2464 + }, + { + "epoch": 0.21, + "learning_rate": 1.8345254365508848e-05, + "loss": 0.4861, + "step": 2465 + }, + { + "epoch": 0.21, + "learning_rate": 1.8343732491869294e-05, + "loss": 0.498, + "step": 2466 + }, + { + "epoch": 0.21, + "learning_rate": 1.8342209981901863e-05, + "loss": 0.5248, + "step": 2467 + }, + { + "epoch": 0.21, + "learning_rate": 1.8340686835722676e-05, + "loss": 0.498, + "step": 2468 + }, + { + "epoch": 0.21, + "learning_rate": 1.8339163053447885e-05, + "loss": 0.4975, + "step": 2469 + }, + { + "epoch": 0.21, + "learning_rate": 1.833763863519371e-05, + "loss": 0.4986, + "step": 2470 + }, + { + "epoch": 0.21, + "learning_rate": 1.83361135810764e-05, + "loss": 0.496, + "step": 2471 + }, + { + "epoch": 0.21, + "learning_rate": 1.833458789121227e-05, + "loss": 0.4811, + "step": 2472 + }, + { + "epoch": 0.21, + "learning_rate": 1.8333061565717668e-05, + "loss": 0.4913, + "step": 2473 + }, + { + "epoch": 0.21, + "learning_rate": 1.8331534604709e-05, + "loss": 0.5268, + "step": 2474 + }, + { + "epoch": 0.21, + "learning_rate": 1.8330007008302723e-05, + "loss": 0.4793, + "step": 2475 + }, + { + "epoch": 0.21, + "learning_rate": 1.8328478776615336e-05, + "loss": 0.5083, + "step": 2476 + }, + { + "epoch": 0.21, + "learning_rate": 1.8326949909763384e-05, + "loss": 0.5218, + "step": 2477 + }, + { + "epoch": 0.21, + "learning_rate": 1.832542040786347e-05, + "loss": 0.4874, + "step": 2478 + }, + { + "epoch": 0.21, + "learning_rate": 1.832389027103224e-05, + "loss": 0.4983, + "step": 2479 + }, + { + "epoch": 0.21, + "learning_rate": 1.832235949938638e-05, + "loss": 0.5161, + "step": 2480 + }, + { + "epoch": 0.21, + "learning_rate": 1.8320828093042645e-05, + "loss": 0.4899, + "step": 2481 + }, + { + "epoch": 0.21, + "learning_rate": 1.831929605211782e-05, + "loss": 0.4849, + "step": 2482 + }, + { + "epoch": 0.21, + "learning_rate": 1.8317763376728747e-05, + "loss": 0.4768, + "step": 2483 + }, + { + "epoch": 0.21, + "learning_rate": 1.8316230066992315e-05, + "loss": 0.4802, + "step": 2484 + }, + { + "epoch": 0.21, + "learning_rate": 1.8314696123025456e-05, + "loss": 0.5035, + "step": 2485 + }, + { + "epoch": 0.21, + "learning_rate": 1.8313161544945158e-05, + "loss": 0.5157, + "step": 2486 + }, + { + "epoch": 0.21, + "learning_rate": 1.831162633286845e-05, + "loss": 0.5136, + "step": 2487 + }, + { + "epoch": 0.21, + "learning_rate": 1.8310090486912423e-05, + "loss": 0.498, + "step": 2488 + }, + { + "epoch": 0.21, + "learning_rate": 1.83085540071942e-05, + "loss": 0.5017, + "step": 2489 + }, + { + "epoch": 0.21, + "learning_rate": 1.8307016893830965e-05, + "loss": 0.4953, + "step": 2490 + }, + { + "epoch": 0.21, + "learning_rate": 1.8305479146939937e-05, + "loss": 0.4974, + "step": 2491 + }, + { + "epoch": 0.21, + "learning_rate": 1.8303940766638396e-05, + "loss": 0.499, + "step": 2492 + }, + { + "epoch": 0.21, + "learning_rate": 1.8302401753043666e-05, + "loss": 0.5013, + "step": 2493 + }, + { + "epoch": 0.21, + "learning_rate": 1.8300862106273113e-05, + "loss": 0.4854, + "step": 2494 + }, + { + "epoch": 0.21, + "learning_rate": 1.8299321826444165e-05, + "loss": 0.5106, + "step": 2495 + }, + { + "epoch": 0.21, + "learning_rate": 1.8297780913674286e-05, + "loss": 0.4871, + "step": 2496 + }, + { + "epoch": 0.21, + "learning_rate": 1.829623936808099e-05, + "loss": 0.5011, + "step": 2497 + }, + { + "epoch": 0.21, + "learning_rate": 1.8294697189781843e-05, + "loss": 0.5145, + "step": 2498 + }, + { + "epoch": 0.21, + "learning_rate": 1.829315437889446e-05, + "loss": 0.5021, + "step": 2499 + }, + { + "epoch": 0.21, + "learning_rate": 1.8291610935536503e-05, + "loss": 0.4942, + "step": 2500 + }, + { + "epoch": 0.21, + "learning_rate": 1.8290066859825676e-05, + "loss": 0.4826, + "step": 2501 + }, + { + "epoch": 0.21, + "learning_rate": 1.8288522151879743e-05, + "loss": 0.5087, + "step": 2502 + }, + { + "epoch": 0.21, + "learning_rate": 1.8286976811816506e-05, + "loss": 0.4924, + "step": 2503 + }, + { + "epoch": 0.21, + "learning_rate": 1.828543083975382e-05, + "loss": 0.484, + "step": 2504 + }, + { + "epoch": 0.21, + "learning_rate": 1.8283884235809587e-05, + "loss": 0.4972, + "step": 2505 + }, + { + "epoch": 0.21, + "learning_rate": 1.8282337000101763e-05, + "loss": 0.5248, + "step": 2506 + }, + { + "epoch": 0.21, + "learning_rate": 1.8280789132748334e-05, + "loss": 0.4988, + "step": 2507 + }, + { + "epoch": 0.21, + "learning_rate": 1.8279240633867357e-05, + "loss": 0.4896, + "step": 2508 + }, + { + "epoch": 0.21, + "learning_rate": 1.8277691503576928e-05, + "loss": 0.4911, + "step": 2509 + }, + { + "epoch": 0.21, + "learning_rate": 1.8276141741995185e-05, + "loss": 0.4891, + "step": 2510 + }, + { + "epoch": 0.21, + "learning_rate": 1.8274591349240322e-05, + "loss": 0.5065, + "step": 2511 + }, + { + "epoch": 0.21, + "learning_rate": 1.8273040325430575e-05, + "loss": 0.4928, + "step": 2512 + }, + { + "epoch": 0.21, + "learning_rate": 1.8271488670684235e-05, + "loss": 0.4933, + "step": 2513 + }, + { + "epoch": 0.21, + "learning_rate": 1.8269936385119634e-05, + "loss": 0.4939, + "step": 2514 + }, + { + "epoch": 0.21, + "learning_rate": 1.826838346885516e-05, + "loss": 0.491, + "step": 2515 + }, + { + "epoch": 0.21, + "learning_rate": 1.8266829922009246e-05, + "loss": 0.4949, + "step": 2516 + }, + { + "epoch": 0.21, + "learning_rate": 1.8265275744700367e-05, + "loss": 0.4984, + "step": 2517 + }, + { + "epoch": 0.21, + "learning_rate": 1.826372093704705e-05, + "loss": 0.5044, + "step": 2518 + }, + { + "epoch": 0.21, + "learning_rate": 1.826216549916788e-05, + "loss": 0.487, + "step": 2519 + }, + { + "epoch": 0.21, + "learning_rate": 1.8260609431181472e-05, + "loss": 0.5158, + "step": 2520 + }, + { + "epoch": 0.21, + "learning_rate": 1.8259052733206503e-05, + "loss": 0.4994, + "step": 2521 + }, + { + "epoch": 0.22, + "learning_rate": 1.825749540536169e-05, + "loss": 0.4946, + "step": 2522 + }, + { + "epoch": 0.22, + "learning_rate": 1.8255937447765804e-05, + "loss": 0.4811, + "step": 2523 + }, + { + "epoch": 0.22, + "learning_rate": 1.8254378860537664e-05, + "loss": 0.4923, + "step": 2524 + }, + { + "epoch": 0.22, + "learning_rate": 1.825281964379613e-05, + "loss": 0.4797, + "step": 2525 + }, + { + "epoch": 0.22, + "learning_rate": 1.8251259797660112e-05, + "loss": 0.4966, + "step": 2526 + }, + { + "epoch": 0.22, + "learning_rate": 1.824969932224858e-05, + "loss": 0.5103, + "step": 2527 + }, + { + "epoch": 0.22, + "learning_rate": 1.824813821768053e-05, + "loss": 0.4775, + "step": 2528 + }, + { + "epoch": 0.22, + "learning_rate": 1.8246576484075027e-05, + "loss": 0.4906, + "step": 2529 + }, + { + "epoch": 0.22, + "learning_rate": 1.8245014121551173e-05, + "loss": 0.4816, + "step": 2530 + }, + { + "epoch": 0.22, + "learning_rate": 1.824345113022812e-05, + "loss": 0.501, + "step": 2531 + }, + { + "epoch": 0.22, + "learning_rate": 1.8241887510225068e-05, + "loss": 0.5113, + "step": 2532 + }, + { + "epoch": 0.22, + "learning_rate": 1.8240323261661266e-05, + "loss": 0.4829, + "step": 2533 + }, + { + "epoch": 0.22, + "learning_rate": 1.823875838465601e-05, + "loss": 0.4826, + "step": 2534 + }, + { + "epoch": 0.22, + "learning_rate": 1.8237192879328643e-05, + "loss": 0.4878, + "step": 2535 + }, + { + "epoch": 0.22, + "learning_rate": 1.823562674579856e-05, + "loss": 0.5107, + "step": 2536 + }, + { + "epoch": 0.22, + "learning_rate": 1.8234059984185196e-05, + "loss": 0.4894, + "step": 2537 + }, + { + "epoch": 0.22, + "learning_rate": 1.8232492594608042e-05, + "loss": 0.497, + "step": 2538 + }, + { + "epoch": 0.22, + "learning_rate": 1.8230924577186635e-05, + "loss": 0.5136, + "step": 2539 + }, + { + "epoch": 0.22, + "learning_rate": 1.8229355932040556e-05, + "loss": 0.499, + "step": 2540 + }, + { + "epoch": 0.22, + "learning_rate": 1.8227786659289436e-05, + "loss": 0.5103, + "step": 2541 + }, + { + "epoch": 0.22, + "learning_rate": 1.822621675905296e-05, + "loss": 0.4971, + "step": 2542 + }, + { + "epoch": 0.22, + "learning_rate": 1.8224646231450842e-05, + "loss": 0.4991, + "step": 2543 + }, + { + "epoch": 0.22, + "learning_rate": 1.822307507660287e-05, + "loss": 0.4924, + "step": 2544 + }, + { + "epoch": 0.22, + "learning_rate": 1.822150329462886e-05, + "loss": 0.4993, + "step": 2545 + }, + { + "epoch": 0.22, + "learning_rate": 1.8219930885648688e-05, + "loss": 0.5004, + "step": 2546 + }, + { + "epoch": 0.22, + "learning_rate": 1.821835784978227e-05, + "loss": 0.4848, + "step": 2547 + }, + { + "epoch": 0.22, + "learning_rate": 1.821678418714957e-05, + "loss": 0.5039, + "step": 2548 + }, + { + "epoch": 0.22, + "learning_rate": 1.8215209897870604e-05, + "loss": 0.5127, + "step": 2549 + }, + { + "epoch": 0.22, + "learning_rate": 1.8213634982065436e-05, + "loss": 0.4904, + "step": 2550 + }, + { + "epoch": 0.22, + "learning_rate": 1.821205943985417e-05, + "loss": 0.4989, + "step": 2551 + }, + { + "epoch": 0.22, + "learning_rate": 1.821048327135697e-05, + "loss": 0.4969, + "step": 2552 + }, + { + "epoch": 0.22, + "learning_rate": 1.8208906476694036e-05, + "loss": 0.48, + "step": 2553 + }, + { + "epoch": 0.22, + "learning_rate": 1.8207329055985622e-05, + "loss": 0.4891, + "step": 2554 + }, + { + "epoch": 0.22, + "learning_rate": 1.8205751009352034e-05, + "loss": 0.4979, + "step": 2555 + }, + { + "epoch": 0.22, + "learning_rate": 1.820417233691361e-05, + "loss": 0.4867, + "step": 2556 + }, + { + "epoch": 0.22, + "learning_rate": 1.8202593038790753e-05, + "loss": 0.4934, + "step": 2557 + }, + { + "epoch": 0.22, + "learning_rate": 1.820101311510391e-05, + "loss": 0.4995, + "step": 2558 + }, + { + "epoch": 0.22, + "learning_rate": 1.8199432565973566e-05, + "loss": 0.511, + "step": 2559 + }, + { + "epoch": 0.22, + "learning_rate": 1.8197851391520265e-05, + "loss": 0.4825, + "step": 2560 + }, + { + "epoch": 0.22, + "learning_rate": 1.8196269591864593e-05, + "loss": 0.5169, + "step": 2561 + }, + { + "epoch": 0.22, + "learning_rate": 1.8194687167127178e-05, + "loss": 0.5341, + "step": 2562 + }, + { + "epoch": 0.22, + "learning_rate": 1.8193104117428712e-05, + "loss": 0.4851, + "step": 2563 + }, + { + "epoch": 0.22, + "learning_rate": 1.819152044288992e-05, + "loss": 0.5096, + "step": 2564 + }, + { + "epoch": 0.22, + "learning_rate": 1.818993614363158e-05, + "loss": 0.4894, + "step": 2565 + }, + { + "epoch": 0.22, + "learning_rate": 1.818835121977452e-05, + "loss": 0.4903, + "step": 2566 + }, + { + "epoch": 0.22, + "learning_rate": 1.8186765671439606e-05, + "loss": 0.4943, + "step": 2567 + }, + { + "epoch": 0.22, + "learning_rate": 1.8185179498747767e-05, + "loss": 0.5053, + "step": 2568 + }, + { + "epoch": 0.22, + "learning_rate": 1.8183592701819965e-05, + "loss": 0.4878, + "step": 2569 + }, + { + "epoch": 0.22, + "learning_rate": 1.818200528077722e-05, + "loss": 0.4963, + "step": 2570 + }, + { + "epoch": 0.22, + "learning_rate": 1.8180417235740592e-05, + "loss": 0.5033, + "step": 2571 + }, + { + "epoch": 0.22, + "learning_rate": 1.8178828566831192e-05, + "loss": 0.501, + "step": 2572 + }, + { + "epoch": 0.22, + "learning_rate": 1.8177239274170185e-05, + "loss": 0.4886, + "step": 2573 + }, + { + "epoch": 0.22, + "learning_rate": 1.8175649357878766e-05, + "loss": 0.4815, + "step": 2574 + }, + { + "epoch": 0.22, + "learning_rate": 1.81740588180782e-05, + "loss": 0.4756, + "step": 2575 + }, + { + "epoch": 0.22, + "learning_rate": 1.817246765488978e-05, + "loss": 0.5031, + "step": 2576 + }, + { + "epoch": 0.22, + "learning_rate": 1.817087586843486e-05, + "loss": 0.4899, + "step": 2577 + }, + { + "epoch": 0.22, + "learning_rate": 1.816928345883483e-05, + "loss": 0.5092, + "step": 2578 + }, + { + "epoch": 0.22, + "learning_rate": 1.816769042621114e-05, + "loss": 0.4892, + "step": 2579 + }, + { + "epoch": 0.22, + "learning_rate": 1.8166096770685278e-05, + "loss": 0.5079, + "step": 2580 + }, + { + "epoch": 0.22, + "learning_rate": 1.8164502492378783e-05, + "loss": 0.5079, + "step": 2581 + }, + { + "epoch": 0.22, + "learning_rate": 1.8162907591413245e-05, + "loss": 0.51, + "step": 2582 + }, + { + "epoch": 0.22, + "learning_rate": 1.8161312067910292e-05, + "loss": 0.4946, + "step": 2583 + }, + { + "epoch": 0.22, + "learning_rate": 1.8159715921991612e-05, + "loss": 0.5401, + "step": 2584 + }, + { + "epoch": 0.22, + "learning_rate": 1.8158119153778927e-05, + "loss": 0.5024, + "step": 2585 + }, + { + "epoch": 0.22, + "learning_rate": 1.8156521763394016e-05, + "loss": 0.4958, + "step": 2586 + }, + { + "epoch": 0.22, + "learning_rate": 1.8154923750958704e-05, + "loss": 0.5058, + "step": 2587 + }, + { + "epoch": 0.22, + "learning_rate": 1.815332511659486e-05, + "loss": 0.4999, + "step": 2588 + }, + { + "epoch": 0.22, + "learning_rate": 1.8151725860424405e-05, + "loss": 0.5065, + "step": 2589 + }, + { + "epoch": 0.22, + "learning_rate": 1.8150125982569304e-05, + "loss": 0.4886, + "step": 2590 + }, + { + "epoch": 0.22, + "learning_rate": 1.814852548315157e-05, + "loss": 0.5025, + "step": 2591 + }, + { + "epoch": 0.22, + "learning_rate": 1.814692436229326e-05, + "loss": 0.4907, + "step": 2592 + }, + { + "epoch": 0.22, + "learning_rate": 1.814532262011649e-05, + "loss": 0.5077, + "step": 2593 + }, + { + "epoch": 0.22, + "learning_rate": 1.814372025674341e-05, + "loss": 0.5192, + "step": 2594 + }, + { + "epoch": 0.22, + "learning_rate": 1.8142117272296224e-05, + "loss": 0.5092, + "step": 2595 + }, + { + "epoch": 0.22, + "learning_rate": 1.814051366689718e-05, + "loss": 0.4969, + "step": 2596 + }, + { + "epoch": 0.22, + "learning_rate": 1.813890944066858e-05, + "loss": 0.5128, + "step": 2597 + }, + { + "epoch": 0.22, + "learning_rate": 1.8137304593732767e-05, + "loss": 0.4906, + "step": 2598 + }, + { + "epoch": 0.22, + "learning_rate": 1.8135699126212135e-05, + "loss": 0.5012, + "step": 2599 + }, + { + "epoch": 0.22, + "learning_rate": 1.8134093038229118e-05, + "loss": 0.5157, + "step": 2600 + }, + { + "epoch": 0.22, + "learning_rate": 1.8132486329906212e-05, + "loss": 0.5043, + "step": 2601 + }, + { + "epoch": 0.22, + "learning_rate": 1.8130879001365944e-05, + "loss": 0.4719, + "step": 2602 + }, + { + "epoch": 0.22, + "learning_rate": 1.8129271052730898e-05, + "loss": 0.4954, + "step": 2603 + }, + { + "epoch": 0.22, + "learning_rate": 1.8127662484123702e-05, + "loss": 0.4978, + "step": 2604 + }, + { + "epoch": 0.22, + "learning_rate": 1.8126053295667036e-05, + "loss": 0.4984, + "step": 2605 + }, + { + "epoch": 0.22, + "learning_rate": 1.812444348748362e-05, + "loss": 0.4923, + "step": 2606 + }, + { + "epoch": 0.22, + "learning_rate": 1.812283305969622e-05, + "loss": 0.5324, + "step": 2607 + }, + { + "epoch": 0.22, + "learning_rate": 1.8121222012427666e-05, + "loss": 0.4937, + "step": 2608 + }, + { + "epoch": 0.22, + "learning_rate": 1.811961034580081e-05, + "loss": 0.5119, + "step": 2609 + }, + { + "epoch": 0.22, + "learning_rate": 1.8117998059938575e-05, + "loss": 0.5162, + "step": 2610 + }, + { + "epoch": 0.22, + "learning_rate": 1.8116385154963913e-05, + "loss": 0.4701, + "step": 2611 + }, + { + "epoch": 0.22, + "learning_rate": 1.811477163099984e-05, + "loss": 0.5327, + "step": 2612 + }, + { + "epoch": 0.22, + "learning_rate": 1.8113157488169398e-05, + "loss": 0.5036, + "step": 2613 + }, + { + "epoch": 0.22, + "learning_rate": 1.81115427265957e-05, + "loss": 0.499, + "step": 2614 + }, + { + "epoch": 0.22, + "learning_rate": 1.8109927346401884e-05, + "loss": 0.4844, + "step": 2615 + }, + { + "epoch": 0.22, + "learning_rate": 1.8108311347711152e-05, + "loss": 0.4729, + "step": 2616 + }, + { + "epoch": 0.22, + "learning_rate": 1.8106694730646745e-05, + "loss": 0.4967, + "step": 2617 + }, + { + "epoch": 0.22, + "learning_rate": 1.8105077495331956e-05, + "loss": 0.4931, + "step": 2618 + }, + { + "epoch": 0.22, + "learning_rate": 1.8103459641890117e-05, + "loss": 0.5043, + "step": 2619 + }, + { + "epoch": 0.22, + "learning_rate": 1.8101841170444617e-05, + "loss": 0.5012, + "step": 2620 + }, + { + "epoch": 0.22, + "learning_rate": 1.8100222081118882e-05, + "loss": 0.5017, + "step": 2621 + }, + { + "epoch": 0.22, + "learning_rate": 1.8098602374036395e-05, + "loss": 0.527, + "step": 2622 + }, + { + "epoch": 0.22, + "learning_rate": 1.8096982049320683e-05, + "loss": 0.5048, + "step": 2623 + }, + { + "epoch": 0.22, + "learning_rate": 1.809536110709531e-05, + "loss": 0.5079, + "step": 2624 + }, + { + "epoch": 0.22, + "learning_rate": 1.809373954748391e-05, + "loss": 0.4918, + "step": 2625 + }, + { + "epoch": 0.22, + "learning_rate": 1.8092117370610137e-05, + "loss": 0.5065, + "step": 2626 + }, + { + "epoch": 0.22, + "learning_rate": 1.8090494576597712e-05, + "loss": 0.5019, + "step": 2627 + }, + { + "epoch": 0.22, + "learning_rate": 1.808887116557039e-05, + "loss": 0.4903, + "step": 2628 + }, + { + "epoch": 0.22, + "learning_rate": 1.8087247137651985e-05, + "loss": 0.4947, + "step": 2629 + }, + { + "epoch": 0.22, + "learning_rate": 1.8085622492966347e-05, + "loss": 0.5112, + "step": 2630 + }, + { + "epoch": 0.22, + "learning_rate": 1.8083997231637385e-05, + "loss": 0.5013, + "step": 2631 + }, + { + "epoch": 0.22, + "learning_rate": 1.8082371353789046e-05, + "loss": 0.4936, + "step": 2632 + }, + { + "epoch": 0.22, + "learning_rate": 1.8080744859545323e-05, + "loss": 0.4998, + "step": 2633 + }, + { + "epoch": 0.22, + "learning_rate": 1.8079117749030257e-05, + "loss": 0.4843, + "step": 2634 + }, + { + "epoch": 0.22, + "learning_rate": 1.8077490022367948e-05, + "loss": 0.4976, + "step": 2635 + }, + { + "epoch": 0.22, + "learning_rate": 1.8075861679682524e-05, + "loss": 0.51, + "step": 2636 + }, + { + "epoch": 0.22, + "learning_rate": 1.8074232721098174e-05, + "loss": 0.5108, + "step": 2637 + }, + { + "epoch": 0.22, + "learning_rate": 1.8072603146739126e-05, + "loss": 0.5001, + "step": 2638 + }, + { + "epoch": 0.23, + "learning_rate": 1.807097295672966e-05, + "loss": 0.5288, + "step": 2639 + }, + { + "epoch": 0.23, + "learning_rate": 1.8069342151194105e-05, + "loss": 0.5017, + "step": 2640 + }, + { + "epoch": 0.23, + "learning_rate": 1.8067710730256825e-05, + "loss": 0.4916, + "step": 2641 + }, + { + "epoch": 0.23, + "learning_rate": 1.8066078694042245e-05, + "loss": 0.5026, + "step": 2642 + }, + { + "epoch": 0.23, + "learning_rate": 1.806444604267483e-05, + "loss": 0.4967, + "step": 2643 + }, + { + "epoch": 0.23, + "learning_rate": 1.8062812776279085e-05, + "loss": 0.4987, + "step": 2644 + }, + { + "epoch": 0.23, + "learning_rate": 1.806117889497958e-05, + "loss": 0.5114, + "step": 2645 + }, + { + "epoch": 0.23, + "learning_rate": 1.8059544398900923e-05, + "loss": 0.495, + "step": 2646 + }, + { + "epoch": 0.23, + "learning_rate": 1.8057909288167758e-05, + "loss": 0.4907, + "step": 2647 + }, + { + "epoch": 0.23, + "learning_rate": 1.8056273562904793e-05, + "loss": 0.5021, + "step": 2648 + }, + { + "epoch": 0.23, + "learning_rate": 1.805463722323677e-05, + "loss": 0.5091, + "step": 2649 + }, + { + "epoch": 0.23, + "learning_rate": 1.8053000269288486e-05, + "loss": 0.4969, + "step": 2650 + }, + { + "epoch": 0.23, + "learning_rate": 1.8051362701184777e-05, + "loss": 0.4965, + "step": 2651 + }, + { + "epoch": 0.23, + "learning_rate": 1.8049724519050538e-05, + "loss": 0.4959, + "step": 2652 + }, + { + "epoch": 0.23, + "learning_rate": 1.80480857230107e-05, + "loss": 0.5135, + "step": 2653 + }, + { + "epoch": 0.23, + "learning_rate": 1.804644631319025e-05, + "loss": 0.4746, + "step": 2654 + }, + { + "epoch": 0.23, + "learning_rate": 1.8044806289714206e-05, + "loss": 0.5231, + "step": 2655 + }, + { + "epoch": 0.23, + "learning_rate": 1.804316565270765e-05, + "loss": 0.5009, + "step": 2656 + }, + { + "epoch": 0.23, + "learning_rate": 1.8041524402295702e-05, + "loss": 0.4917, + "step": 2657 + }, + { + "epoch": 0.23, + "learning_rate": 1.803988253860353e-05, + "loss": 0.5053, + "step": 2658 + }, + { + "epoch": 0.23, + "learning_rate": 1.8038240061756348e-05, + "loss": 0.5126, + "step": 2659 + }, + { + "epoch": 0.23, + "learning_rate": 1.8036596971879426e-05, + "loss": 0.5039, + "step": 2660 + }, + { + "epoch": 0.23, + "learning_rate": 1.8034953269098062e-05, + "loss": 0.4986, + "step": 2661 + }, + { + "epoch": 0.23, + "learning_rate": 1.8033308953537617e-05, + "loss": 0.501, + "step": 2662 + }, + { + "epoch": 0.23, + "learning_rate": 1.8031664025323497e-05, + "loss": 0.4959, + "step": 2663 + }, + { + "epoch": 0.23, + "learning_rate": 1.8030018484581147e-05, + "loss": 0.485, + "step": 2664 + }, + { + "epoch": 0.23, + "learning_rate": 1.802837233143606e-05, + "loss": 0.5101, + "step": 2665 + }, + { + "epoch": 0.23, + "learning_rate": 1.802672556601378e-05, + "loss": 0.488, + "step": 2666 + }, + { + "epoch": 0.23, + "learning_rate": 1.8025078188439905e-05, + "loss": 0.492, + "step": 2667 + }, + { + "epoch": 0.23, + "learning_rate": 1.8023430198840056e-05, + "loss": 0.4938, + "step": 2668 + }, + { + "epoch": 0.23, + "learning_rate": 1.802178159733993e-05, + "loss": 0.4931, + "step": 2669 + }, + { + "epoch": 0.23, + "learning_rate": 1.8020132384065245e-05, + "loss": 0.5101, + "step": 2670 + }, + { + "epoch": 0.23, + "learning_rate": 1.801848255914178e-05, + "loss": 0.4978, + "step": 2671 + }, + { + "epoch": 0.23, + "learning_rate": 1.801683212269536e-05, + "loss": 0.5024, + "step": 2672 + }, + { + "epoch": 0.23, + "learning_rate": 1.8015181074851856e-05, + "loss": 0.4894, + "step": 2673 + }, + { + "epoch": 0.23, + "learning_rate": 1.801352941573718e-05, + "loss": 0.5065, + "step": 2674 + }, + { + "epoch": 0.23, + "learning_rate": 1.8011877145477292e-05, + "loss": 0.4736, + "step": 2675 + }, + { + "epoch": 0.23, + "learning_rate": 1.8010224264198207e-05, + "loss": 0.5183, + "step": 2676 + }, + { + "epoch": 0.23, + "learning_rate": 1.8008570772025978e-05, + "loss": 0.4873, + "step": 2677 + }, + { + "epoch": 0.23, + "learning_rate": 1.8006916669086706e-05, + "loss": 0.5155, + "step": 2678 + }, + { + "epoch": 0.23, + "learning_rate": 1.800526195550654e-05, + "loss": 0.4921, + "step": 2679 + }, + { + "epoch": 0.23, + "learning_rate": 1.800360663141168e-05, + "loss": 0.48, + "step": 2680 + }, + { + "epoch": 0.23, + "learning_rate": 1.800195069692836e-05, + "loss": 0.4809, + "step": 2681 + }, + { + "epoch": 0.23, + "learning_rate": 1.8000294152182877e-05, + "loss": 0.494, + "step": 2682 + }, + { + "epoch": 0.23, + "learning_rate": 1.799863699730156e-05, + "loss": 0.4965, + "step": 2683 + }, + { + "epoch": 0.23, + "learning_rate": 1.799697923241079e-05, + "loss": 0.4777, + "step": 2684 + }, + { + "epoch": 0.23, + "learning_rate": 1.7995320857637e-05, + "loss": 0.4908, + "step": 2685 + }, + { + "epoch": 0.23, + "learning_rate": 1.799366187310666e-05, + "loss": 0.5068, + "step": 2686 + }, + { + "epoch": 0.23, + "learning_rate": 1.7992002278946295e-05, + "loss": 0.5081, + "step": 2687 + }, + { + "epoch": 0.23, + "learning_rate": 1.799034207528247e-05, + "loss": 0.4866, + "step": 2688 + }, + { + "epoch": 0.23, + "learning_rate": 1.7988681262241798e-05, + "loss": 0.4758, + "step": 2689 + }, + { + "epoch": 0.23, + "learning_rate": 1.7987019839950943e-05, + "loss": 0.4902, + "step": 2690 + }, + { + "epoch": 0.23, + "learning_rate": 1.798535780853661e-05, + "loss": 0.4911, + "step": 2691 + }, + { + "epoch": 0.23, + "learning_rate": 1.7983695168125552e-05, + "loss": 0.501, + "step": 2692 + }, + { + "epoch": 0.23, + "learning_rate": 1.798203191884457e-05, + "loss": 0.5023, + "step": 2693 + }, + { + "epoch": 0.23, + "learning_rate": 1.798036806082051e-05, + "loss": 0.4882, + "step": 2694 + }, + { + "epoch": 0.23, + "learning_rate": 1.7978703594180266e-05, + "loss": 0.5119, + "step": 2695 + }, + { + "epoch": 0.23, + "learning_rate": 1.7977038519050773e-05, + "loss": 0.4859, + "step": 2696 + }, + { + "epoch": 0.23, + "learning_rate": 1.7975372835559023e-05, + "loss": 0.5136, + "step": 2697 + }, + { + "epoch": 0.23, + "learning_rate": 1.797370654383204e-05, + "loss": 0.487, + "step": 2698 + }, + { + "epoch": 0.23, + "learning_rate": 1.797203964399691e-05, + "loss": 0.4911, + "step": 2699 + }, + { + "epoch": 0.23, + "learning_rate": 1.7970372136180753e-05, + "loss": 0.4985, + "step": 2700 + }, + { + "epoch": 0.23, + "learning_rate": 1.796870402051074e-05, + "loss": 0.5132, + "step": 2701 + }, + { + "epoch": 0.23, + "learning_rate": 1.7967035297114094e-05, + "loss": 0.4969, + "step": 2702 + }, + { + "epoch": 0.23, + "learning_rate": 1.7965365966118075e-05, + "loss": 0.4851, + "step": 2703 + }, + { + "epoch": 0.23, + "learning_rate": 1.796369602764999e-05, + "loss": 0.5085, + "step": 2704 + }, + { + "epoch": 0.23, + "learning_rate": 1.7962025481837196e-05, + "loss": 0.4907, + "step": 2705 + }, + { + "epoch": 0.23, + "learning_rate": 1.7960354328807103e-05, + "loss": 0.4809, + "step": 2706 + }, + { + "epoch": 0.23, + "learning_rate": 1.7958682568687152e-05, + "loss": 0.5071, + "step": 2707 + }, + { + "epoch": 0.23, + "learning_rate": 1.7957010201604844e-05, + "loss": 0.5138, + "step": 2708 + }, + { + "epoch": 0.23, + "learning_rate": 1.795533722768772e-05, + "loss": 0.4872, + "step": 2709 + }, + { + "epoch": 0.23, + "learning_rate": 1.7953663647063365e-05, + "loss": 0.5056, + "step": 2710 + }, + { + "epoch": 0.23, + "learning_rate": 1.7951989459859415e-05, + "loss": 0.5084, + "step": 2711 + }, + { + "epoch": 0.23, + "learning_rate": 1.795031466620355e-05, + "loss": 0.479, + "step": 2712 + }, + { + "epoch": 0.23, + "learning_rate": 1.7948639266223495e-05, + "loss": 0.5109, + "step": 2713 + }, + { + "epoch": 0.23, + "learning_rate": 1.7946963260047028e-05, + "loss": 0.4787, + "step": 2714 + }, + { + "epoch": 0.23, + "learning_rate": 1.7945286647801966e-05, + "loss": 0.4938, + "step": 2715 + }, + { + "epoch": 0.23, + "learning_rate": 1.794360942961617e-05, + "loss": 0.5091, + "step": 2716 + }, + { + "epoch": 0.23, + "learning_rate": 1.7941931605617556e-05, + "loss": 0.4926, + "step": 2717 + }, + { + "epoch": 0.23, + "learning_rate": 1.7940253175934083e-05, + "loss": 0.478, + "step": 2718 + }, + { + "epoch": 0.23, + "learning_rate": 1.793857414069375e-05, + "loss": 0.5188, + "step": 2719 + }, + { + "epoch": 0.23, + "learning_rate": 1.7936894500024614e-05, + "loss": 0.4989, + "step": 2720 + }, + { + "epoch": 0.23, + "learning_rate": 1.793521425405477e-05, + "loss": 0.4922, + "step": 2721 + }, + { + "epoch": 0.23, + "learning_rate": 1.7933533402912354e-05, + "loss": 0.5052, + "step": 2722 + }, + { + "epoch": 0.23, + "learning_rate": 1.7931851946725557e-05, + "loss": 0.514, + "step": 2723 + }, + { + "epoch": 0.23, + "learning_rate": 1.793016988562262e-05, + "loss": 0.4976, + "step": 2724 + }, + { + "epoch": 0.23, + "learning_rate": 1.792848721973182e-05, + "loss": 0.491, + "step": 2725 + }, + { + "epoch": 0.23, + "learning_rate": 1.7926803949181483e-05, + "loss": 0.4946, + "step": 2726 + }, + { + "epoch": 0.23, + "learning_rate": 1.7925120074099987e-05, + "loss": 0.5123, + "step": 2727 + }, + { + "epoch": 0.23, + "learning_rate": 1.7923435594615744e-05, + "loss": 0.4782, + "step": 2728 + }, + { + "epoch": 0.23, + "learning_rate": 1.7921750510857224e-05, + "loss": 0.5085, + "step": 2729 + }, + { + "epoch": 0.23, + "learning_rate": 1.792006482295294e-05, + "loss": 0.4957, + "step": 2730 + }, + { + "epoch": 0.23, + "learning_rate": 1.7918378531031444e-05, + "loss": 0.4946, + "step": 2731 + }, + { + "epoch": 0.23, + "learning_rate": 1.7916691635221343e-05, + "loss": 0.4981, + "step": 2732 + }, + { + "epoch": 0.23, + "learning_rate": 1.791500413565129e-05, + "loss": 0.4858, + "step": 2733 + }, + { + "epoch": 0.23, + "learning_rate": 1.7913316032449975e-05, + "loss": 0.4865, + "step": 2734 + }, + { + "epoch": 0.23, + "learning_rate": 1.791162732574614e-05, + "loss": 0.4774, + "step": 2735 + }, + { + "epoch": 0.23, + "learning_rate": 1.790993801566858e-05, + "loss": 0.5164, + "step": 2736 + }, + { + "epoch": 0.23, + "learning_rate": 1.790824810234612e-05, + "loss": 0.5118, + "step": 2737 + }, + { + "epoch": 0.23, + "learning_rate": 1.7906557585907646e-05, + "loss": 0.4989, + "step": 2738 + }, + { + "epoch": 0.23, + "learning_rate": 1.790486646648208e-05, + "loss": 0.4948, + "step": 2739 + }, + { + "epoch": 0.23, + "learning_rate": 1.7903174744198398e-05, + "loss": 0.5171, + "step": 2740 + }, + { + "epoch": 0.23, + "learning_rate": 1.7901482419185613e-05, + "loss": 0.4836, + "step": 2741 + }, + { + "epoch": 0.23, + "learning_rate": 1.7899789491572794e-05, + "loss": 0.4912, + "step": 2742 + }, + { + "epoch": 0.23, + "learning_rate": 1.7898095961489047e-05, + "loss": 0.5097, + "step": 2743 + }, + { + "epoch": 0.23, + "learning_rate": 1.7896401829063522e-05, + "loss": 0.4912, + "step": 2744 + }, + { + "epoch": 0.23, + "learning_rate": 1.7894707094425433e-05, + "loss": 0.5051, + "step": 2745 + }, + { + "epoch": 0.23, + "learning_rate": 1.7893011757704022e-05, + "loss": 0.4938, + "step": 2746 + }, + { + "epoch": 0.23, + "learning_rate": 1.789131581902858e-05, + "loss": 0.497, + "step": 2747 + }, + { + "epoch": 0.23, + "learning_rate": 1.788961927852845e-05, + "loss": 0.494, + "step": 2748 + }, + { + "epoch": 0.23, + "learning_rate": 1.7887922136333015e-05, + "loss": 0.4936, + "step": 2749 + }, + { + "epoch": 0.23, + "learning_rate": 1.7886224392571704e-05, + "loss": 0.4983, + "step": 2750 + }, + { + "epoch": 0.23, + "learning_rate": 1.7884526047374e-05, + "loss": 0.4887, + "step": 2751 + }, + { + "epoch": 0.23, + "learning_rate": 1.788282710086942e-05, + "loss": 0.507, + "step": 2752 + }, + { + "epoch": 0.23, + "learning_rate": 1.788112755318754e-05, + "loss": 0.5003, + "step": 2753 + }, + { + "epoch": 0.23, + "learning_rate": 1.7879427404457965e-05, + "loss": 0.492, + "step": 2754 + }, + { + "epoch": 0.23, + "learning_rate": 1.7877726654810364e-05, + "loss": 0.4927, + "step": 2755 + }, + { + "epoch": 0.23, + "learning_rate": 1.787602530437444e-05, + "loss": 0.5, + "step": 2756 + }, + { + "epoch": 0.24, + "learning_rate": 1.7874323353279945e-05, + "loss": 0.4836, + "step": 2757 + }, + { + "epoch": 0.24, + "learning_rate": 1.7872620801656674e-05, + "loss": 0.497, + "step": 2758 + }, + { + "epoch": 0.24, + "learning_rate": 1.7870917649634475e-05, + "loss": 0.5026, + "step": 2759 + }, + { + "epoch": 0.24, + "learning_rate": 1.7869213897343235e-05, + "loss": 0.5123, + "step": 2760 + }, + { + "epoch": 0.24, + "learning_rate": 1.7867509544912893e-05, + "loss": 0.5105, + "step": 2761 + }, + { + "epoch": 0.24, + "learning_rate": 1.7865804592473423e-05, + "loss": 0.5003, + "step": 2762 + }, + { + "epoch": 0.24, + "learning_rate": 1.786409904015486e-05, + "loss": 0.4912, + "step": 2763 + }, + { + "epoch": 0.24, + "learning_rate": 1.786239288808727e-05, + "loss": 0.5068, + "step": 2764 + }, + { + "epoch": 0.24, + "learning_rate": 1.7860686136400773e-05, + "loss": 0.4965, + "step": 2765 + }, + { + "epoch": 0.24, + "learning_rate": 1.7858978785225535e-05, + "loss": 0.5048, + "step": 2766 + }, + { + "epoch": 0.24, + "learning_rate": 1.7857270834691766e-05, + "loss": 0.4829, + "step": 2767 + }, + { + "epoch": 0.24, + "learning_rate": 1.785556228492972e-05, + "loss": 0.5034, + "step": 2768 + }, + { + "epoch": 0.24, + "learning_rate": 1.7853853136069697e-05, + "loss": 0.4914, + "step": 2769 + }, + { + "epoch": 0.24, + "learning_rate": 1.7852143388242046e-05, + "loss": 0.4989, + "step": 2770 + }, + { + "epoch": 0.24, + "learning_rate": 1.785043304157716e-05, + "loss": 0.501, + "step": 2771 + }, + { + "epoch": 0.24, + "learning_rate": 1.784872209620547e-05, + "loss": 0.4953, + "step": 2772 + }, + { + "epoch": 0.24, + "learning_rate": 1.784701055225747e-05, + "loss": 0.5186, + "step": 2773 + }, + { + "epoch": 0.24, + "learning_rate": 1.7845298409863683e-05, + "loss": 0.4717, + "step": 2774 + }, + { + "epoch": 0.24, + "learning_rate": 1.7843585669154685e-05, + "loss": 0.5163, + "step": 2775 + }, + { + "epoch": 0.24, + "learning_rate": 1.7841872330261103e-05, + "loss": 0.4986, + "step": 2776 + }, + { + "epoch": 0.24, + "learning_rate": 1.7840158393313594e-05, + "loss": 0.4864, + "step": 2777 + }, + { + "epoch": 0.24, + "learning_rate": 1.7838443858442877e-05, + "loss": 0.4913, + "step": 2778 + }, + { + "epoch": 0.24, + "learning_rate": 1.7836728725779705e-05, + "loss": 0.5062, + "step": 2779 + }, + { + "epoch": 0.24, + "learning_rate": 1.7835012995454882e-05, + "loss": 0.5083, + "step": 2780 + }, + { + "epoch": 0.24, + "learning_rate": 1.783329666759926e-05, + "loss": 0.5094, + "step": 2781 + }, + { + "epoch": 0.24, + "learning_rate": 1.783157974234373e-05, + "loss": 0.5117, + "step": 2782 + }, + { + "epoch": 0.24, + "learning_rate": 1.7829862219819235e-05, + "loss": 0.4651, + "step": 2783 + }, + { + "epoch": 0.24, + "learning_rate": 1.7828144100156754e-05, + "loss": 0.489, + "step": 2784 + }, + { + "epoch": 0.24, + "learning_rate": 1.7826425383487327e-05, + "loss": 0.4887, + "step": 2785 + }, + { + "epoch": 0.24, + "learning_rate": 1.7824706069942023e-05, + "loss": 0.4891, + "step": 2786 + }, + { + "epoch": 0.24, + "learning_rate": 1.782298615965197e-05, + "loss": 0.4961, + "step": 2787 + }, + { + "epoch": 0.24, + "learning_rate": 1.782126565274833e-05, + "loss": 0.4913, + "step": 2788 + }, + { + "epoch": 0.24, + "learning_rate": 1.7819544549362318e-05, + "loss": 0.4979, + "step": 2789 + }, + { + "epoch": 0.24, + "learning_rate": 1.7817822849625194e-05, + "loss": 0.4795, + "step": 2790 + }, + { + "epoch": 0.24, + "learning_rate": 1.781610055366826e-05, + "loss": 0.4804, + "step": 2791 + }, + { + "epoch": 0.24, + "learning_rate": 1.7814377661622867e-05, + "loss": 0.5145, + "step": 2792 + }, + { + "epoch": 0.24, + "learning_rate": 1.781265417362041e-05, + "loss": 0.4958, + "step": 2793 + }, + { + "epoch": 0.24, + "learning_rate": 1.7810930089792328e-05, + "loss": 0.4971, + "step": 2794 + }, + { + "epoch": 0.24, + "learning_rate": 1.780920541027011e-05, + "loss": 0.4791, + "step": 2795 + }, + { + "epoch": 0.24, + "learning_rate": 1.7807480135185283e-05, + "loss": 0.5015, + "step": 2796 + }, + { + "epoch": 0.24, + "learning_rate": 1.7805754264669426e-05, + "loss": 0.4876, + "step": 2797 + }, + { + "epoch": 0.24, + "learning_rate": 1.7804027798854165e-05, + "loss": 0.5028, + "step": 2798 + }, + { + "epoch": 0.24, + "learning_rate": 1.7802300737871157e-05, + "loss": 0.5031, + "step": 2799 + }, + { + "epoch": 0.24, + "learning_rate": 1.7800573081852124e-05, + "loss": 0.4789, + "step": 2800 + }, + { + "epoch": 0.24, + "learning_rate": 1.7798844830928818e-05, + "loss": 0.5082, + "step": 2801 + }, + { + "epoch": 0.24, + "learning_rate": 1.779711598523305e-05, + "loss": 0.4887, + "step": 2802 + }, + { + "epoch": 0.24, + "learning_rate": 1.779538654489666e-05, + "loss": 0.4828, + "step": 2803 + }, + { + "epoch": 0.24, + "learning_rate": 1.7793656510051557e-05, + "loss": 0.4924, + "step": 2804 + }, + { + "epoch": 0.24, + "learning_rate": 1.779192588082966e-05, + "loss": 0.5018, + "step": 2805 + }, + { + "epoch": 0.24, + "learning_rate": 1.7790194657362973e-05, + "loss": 0.49, + "step": 2806 + }, + { + "epoch": 0.24, + "learning_rate": 1.7788462839783514e-05, + "loss": 0.497, + "step": 2807 + }, + { + "epoch": 0.24, + "learning_rate": 1.7786730428223364e-05, + "loss": 0.5019, + "step": 2808 + }, + { + "epoch": 0.24, + "learning_rate": 1.7784997422814644e-05, + "loss": 0.4979, + "step": 2809 + }, + { + "epoch": 0.24, + "learning_rate": 1.778326382368952e-05, + "loss": 0.4985, + "step": 2810 + }, + { + "epoch": 0.24, + "learning_rate": 1.77815296309802e-05, + "loss": 0.4994, + "step": 2811 + }, + { + "epoch": 0.24, + "learning_rate": 1.7779794844818944e-05, + "loss": 0.5063, + "step": 2812 + }, + { + "epoch": 0.24, + "learning_rate": 1.7778059465338054e-05, + "loss": 0.49, + "step": 2813 + }, + { + "epoch": 0.24, + "learning_rate": 1.7776323492669877e-05, + "loss": 0.4971, + "step": 2814 + }, + { + "epoch": 0.24, + "learning_rate": 1.7774586926946805e-05, + "loss": 0.5009, + "step": 2815 + }, + { + "epoch": 0.24, + "learning_rate": 1.7772849768301273e-05, + "loss": 0.507, + "step": 2816 + }, + { + "epoch": 0.24, + "learning_rate": 1.7771112016865774e-05, + "loss": 0.4961, + "step": 2817 + }, + { + "epoch": 0.24, + "learning_rate": 1.7769373672772824e-05, + "loss": 0.5006, + "step": 2818 + }, + { + "epoch": 0.24, + "learning_rate": 1.7767634736155e-05, + "loss": 0.4821, + "step": 2819 + }, + { + "epoch": 0.24, + "learning_rate": 1.7765895207144928e-05, + "loss": 0.4697, + "step": 2820 + }, + { + "epoch": 0.24, + "learning_rate": 1.7764155085875262e-05, + "loss": 0.5086, + "step": 2821 + }, + { + "epoch": 0.24, + "learning_rate": 1.7762414372478716e-05, + "loss": 0.4969, + "step": 2822 + }, + { + "epoch": 0.24, + "learning_rate": 1.7760673067088042e-05, + "loss": 0.507, + "step": 2823 + }, + { + "epoch": 0.24, + "learning_rate": 1.775893116983604e-05, + "loss": 0.5063, + "step": 2824 + }, + { + "epoch": 0.24, + "learning_rate": 1.7757188680855556e-05, + "loss": 0.4905, + "step": 2825 + }, + { + "epoch": 0.24, + "learning_rate": 1.7755445600279476e-05, + "loss": 0.4887, + "step": 2826 + }, + { + "epoch": 0.24, + "learning_rate": 1.7753701928240735e-05, + "loss": 0.4723, + "step": 2827 + }, + { + "epoch": 0.24, + "learning_rate": 1.7751957664872316e-05, + "loss": 0.5225, + "step": 2828 + }, + { + "epoch": 0.24, + "learning_rate": 1.7750212810307243e-05, + "loss": 0.4877, + "step": 2829 + }, + { + "epoch": 0.24, + "learning_rate": 1.7748467364678585e-05, + "loss": 0.4995, + "step": 2830 + }, + { + "epoch": 0.24, + "learning_rate": 1.7746721328119457e-05, + "loss": 0.4931, + "step": 2831 + }, + { + "epoch": 0.24, + "learning_rate": 1.7744974700763018e-05, + "loss": 0.4803, + "step": 2832 + }, + { + "epoch": 0.24, + "learning_rate": 1.7743227482742475e-05, + "loss": 0.4933, + "step": 2833 + }, + { + "epoch": 0.24, + "learning_rate": 1.7741479674191075e-05, + "loss": 0.4879, + "step": 2834 + }, + { + "epoch": 0.24, + "learning_rate": 1.7739731275242117e-05, + "loss": 0.488, + "step": 2835 + }, + { + "epoch": 0.24, + "learning_rate": 1.7737982286028938e-05, + "loss": 0.4907, + "step": 2836 + }, + { + "epoch": 0.24, + "learning_rate": 1.773623270668493e-05, + "loss": 0.5206, + "step": 2837 + }, + { + "epoch": 0.24, + "learning_rate": 1.773448253734351e-05, + "loss": 0.5103, + "step": 2838 + }, + { + "epoch": 0.24, + "learning_rate": 1.773273177813817e-05, + "loss": 0.5068, + "step": 2839 + }, + { + "epoch": 0.24, + "learning_rate": 1.7730980429202415e-05, + "loss": 0.4993, + "step": 2840 + }, + { + "epoch": 0.24, + "learning_rate": 1.7729228490669818e-05, + "loss": 0.5001, + "step": 2841 + }, + { + "epoch": 0.24, + "learning_rate": 1.7727475962673986e-05, + "loss": 0.4989, + "step": 2842 + }, + { + "epoch": 0.24, + "learning_rate": 1.7725722845348577e-05, + "loss": 0.5169, + "step": 2843 + }, + { + "epoch": 0.24, + "learning_rate": 1.7723969138827294e-05, + "loss": 0.5081, + "step": 2844 + }, + { + "epoch": 0.24, + "learning_rate": 1.7722214843243874e-05, + "loss": 0.494, + "step": 2845 + }, + { + "epoch": 0.24, + "learning_rate": 1.772045995873211e-05, + "loss": 0.4921, + "step": 2846 + }, + { + "epoch": 0.24, + "learning_rate": 1.771870448542584e-05, + "loss": 0.4925, + "step": 2847 + }, + { + "epoch": 0.24, + "learning_rate": 1.771694842345894e-05, + "loss": 0.4896, + "step": 2848 + }, + { + "epoch": 0.24, + "learning_rate": 1.7715191772965335e-05, + "loss": 0.5037, + "step": 2849 + }, + { + "epoch": 0.24, + "learning_rate": 1.7713434534079e-05, + "loss": 0.5017, + "step": 2850 + }, + { + "epoch": 0.24, + "learning_rate": 1.771167670693394e-05, + "loss": 0.4904, + "step": 2851 + }, + { + "epoch": 0.24, + "learning_rate": 1.770991829166422e-05, + "loss": 0.4934, + "step": 2852 + }, + { + "epoch": 0.24, + "learning_rate": 1.7708159288403943e-05, + "loss": 0.4919, + "step": 2853 + }, + { + "epoch": 0.24, + "learning_rate": 1.770639969728726e-05, + "loss": 0.4823, + "step": 2854 + }, + { + "epoch": 0.24, + "learning_rate": 1.770463951844836e-05, + "loss": 0.5065, + "step": 2855 + }, + { + "epoch": 0.24, + "learning_rate": 1.7702878752021485e-05, + "loss": 0.5013, + "step": 2856 + }, + { + "epoch": 0.24, + "learning_rate": 1.770111739814092e-05, + "loss": 0.4807, + "step": 2857 + }, + { + "epoch": 0.24, + "learning_rate": 1.769935545694099e-05, + "loss": 0.4918, + "step": 2858 + }, + { + "epoch": 0.24, + "learning_rate": 1.769759292855607e-05, + "loss": 0.5014, + "step": 2859 + }, + { + "epoch": 0.24, + "learning_rate": 1.7695829813120574e-05, + "loss": 0.4927, + "step": 2860 + }, + { + "epoch": 0.24, + "learning_rate": 1.769406611076897e-05, + "loss": 0.4786, + "step": 2861 + }, + { + "epoch": 0.24, + "learning_rate": 1.769230182163576e-05, + "loss": 0.5103, + "step": 2862 + }, + { + "epoch": 0.24, + "learning_rate": 1.76905369458555e-05, + "loss": 0.5066, + "step": 2863 + }, + { + "epoch": 0.24, + "learning_rate": 1.7688771483562788e-05, + "loss": 0.4815, + "step": 2864 + }, + { + "epoch": 0.24, + "learning_rate": 1.768700543489226e-05, + "loss": 0.5088, + "step": 2865 + }, + { + "epoch": 0.24, + "learning_rate": 1.7685238799978605e-05, + "loss": 0.4864, + "step": 2866 + }, + { + "epoch": 0.24, + "learning_rate": 1.7683471578956555e-05, + "loss": 0.4959, + "step": 2867 + }, + { + "epoch": 0.24, + "learning_rate": 1.7681703771960887e-05, + "loss": 0.497, + "step": 2868 + }, + { + "epoch": 0.24, + "learning_rate": 1.7679935379126417e-05, + "loss": 0.5005, + "step": 2869 + }, + { + "epoch": 0.24, + "learning_rate": 1.767816640058801e-05, + "loss": 0.5087, + "step": 2870 + }, + { + "epoch": 0.24, + "learning_rate": 1.7676396836480582e-05, + "loss": 0.482, + "step": 2871 + }, + { + "epoch": 0.24, + "learning_rate": 1.767462668693908e-05, + "loss": 0.498, + "step": 2872 + }, + { + "epoch": 0.24, + "learning_rate": 1.767285595209851e-05, + "loss": 0.4871, + "step": 2873 + }, + { + "epoch": 0.25, + "learning_rate": 1.767108463209391e-05, + "loss": 0.4874, + "step": 2874 + }, + { + "epoch": 0.25, + "learning_rate": 1.766931272706037e-05, + "loss": 0.4954, + "step": 2875 + }, + { + "epoch": 0.25, + "learning_rate": 1.7667540237133022e-05, + "loss": 0.5046, + "step": 2876 + }, + { + "epoch": 0.25, + "learning_rate": 1.7665767162447044e-05, + "loss": 0.492, + "step": 2877 + }, + { + "epoch": 0.25, + "learning_rate": 1.766399350313766e-05, + "loss": 0.4828, + "step": 2878 + }, + { + "epoch": 0.25, + "learning_rate": 1.7662219259340137e-05, + "loss": 0.4981, + "step": 2879 + }, + { + "epoch": 0.25, + "learning_rate": 1.766044443118978e-05, + "loss": 0.4893, + "step": 2880 + }, + { + "epoch": 0.25, + "learning_rate": 1.7658669018821956e-05, + "loss": 0.4691, + "step": 2881 + }, + { + "epoch": 0.25, + "learning_rate": 1.7656893022372052e-05, + "loss": 0.4839, + "step": 2882 + }, + { + "epoch": 0.25, + "learning_rate": 1.7655116441975524e-05, + "loss": 0.5052, + "step": 2883 + }, + { + "epoch": 0.25, + "learning_rate": 1.7653339277767852e-05, + "loss": 0.4948, + "step": 2884 + }, + { + "epoch": 0.25, + "learning_rate": 1.765156152988458e-05, + "loss": 0.5022, + "step": 2885 + }, + { + "epoch": 0.25, + "learning_rate": 1.7649783198461278e-05, + "loss": 0.4975, + "step": 2886 + }, + { + "epoch": 0.25, + "learning_rate": 1.7648004283633575e-05, + "loss": 0.4835, + "step": 2887 + }, + { + "epoch": 0.25, + "learning_rate": 1.7646224785537135e-05, + "loss": 0.494, + "step": 2888 + }, + { + "epoch": 0.25, + "learning_rate": 1.764444470430767e-05, + "loss": 0.4985, + "step": 2889 + }, + { + "epoch": 0.25, + "learning_rate": 1.764266404008094e-05, + "loss": 0.4977, + "step": 2890 + }, + { + "epoch": 0.25, + "learning_rate": 1.764088279299274e-05, + "loss": 0.4818, + "step": 2891 + }, + { + "epoch": 0.25, + "learning_rate": 1.763910096317892e-05, + "loss": 0.4871, + "step": 2892 + }, + { + "epoch": 0.25, + "learning_rate": 1.7637318550775368e-05, + "loss": 0.5084, + "step": 2893 + }, + { + "epoch": 0.25, + "learning_rate": 1.7635535555918016e-05, + "loss": 0.5001, + "step": 2894 + }, + { + "epoch": 0.25, + "learning_rate": 1.7633751978742847e-05, + "loss": 0.4879, + "step": 2895 + }, + { + "epoch": 0.25, + "learning_rate": 1.7631967819385883e-05, + "loss": 0.4836, + "step": 2896 + }, + { + "epoch": 0.25, + "learning_rate": 1.7630183077983192e-05, + "loss": 0.5005, + "step": 2897 + }, + { + "epoch": 0.25, + "learning_rate": 1.762839775467088e-05, + "loss": 0.5006, + "step": 2898 + }, + { + "epoch": 0.25, + "learning_rate": 1.7626611849585113e-05, + "loss": 0.494, + "step": 2899 + }, + { + "epoch": 0.25, + "learning_rate": 1.7624825362862084e-05, + "loss": 0.4944, + "step": 2900 + }, + { + "epoch": 0.25, + "learning_rate": 1.7623038294638037e-05, + "loss": 0.4629, + "step": 2901 + }, + { + "epoch": 0.25, + "learning_rate": 1.7621250645049267e-05, + "loss": 0.5258, + "step": 2902 + }, + { + "epoch": 0.25, + "learning_rate": 1.7619462414232104e-05, + "loss": 0.4746, + "step": 2903 + }, + { + "epoch": 0.25, + "learning_rate": 1.761767360232293e-05, + "loss": 0.5124, + "step": 2904 + }, + { + "epoch": 0.25, + "learning_rate": 1.7615884209458164e-05, + "loss": 0.4992, + "step": 2905 + }, + { + "epoch": 0.25, + "learning_rate": 1.761409423577427e-05, + "loss": 0.4979, + "step": 2906 + }, + { + "epoch": 0.25, + "learning_rate": 1.761230368140776e-05, + "loss": 0.4785, + "step": 2907 + }, + { + "epoch": 0.25, + "learning_rate": 1.7610512546495195e-05, + "loss": 0.5121, + "step": 2908 + }, + { + "epoch": 0.25, + "learning_rate": 1.7608720831173168e-05, + "loss": 0.5076, + "step": 2909 + }, + { + "epoch": 0.25, + "learning_rate": 1.760692853557833e-05, + "loss": 0.472, + "step": 2910 + }, + { + "epoch": 0.25, + "learning_rate": 1.7605135659847357e-05, + "loss": 0.493, + "step": 2911 + }, + { + "epoch": 0.25, + "learning_rate": 1.760334220411699e-05, + "loss": 0.4972, + "step": 2912 + }, + { + "epoch": 0.25, + "learning_rate": 1.7601548168524007e-05, + "loss": 0.4959, + "step": 2913 + }, + { + "epoch": 0.25, + "learning_rate": 1.759975355320522e-05, + "loss": 0.4915, + "step": 2914 + }, + { + "epoch": 0.25, + "learning_rate": 1.75979583582975e-05, + "loss": 0.5031, + "step": 2915 + }, + { + "epoch": 0.25, + "learning_rate": 1.7596162583937757e-05, + "loss": 0.4689, + "step": 2916 + }, + { + "epoch": 0.25, + "learning_rate": 1.759436623026294e-05, + "loss": 0.5037, + "step": 2917 + }, + { + "epoch": 0.25, + "learning_rate": 1.7592569297410053e-05, + "loss": 0.4997, + "step": 2918 + }, + { + "epoch": 0.25, + "learning_rate": 1.759077178551613e-05, + "loss": 0.4943, + "step": 2919 + }, + { + "epoch": 0.25, + "learning_rate": 1.7588973694718263e-05, + "loss": 0.5025, + "step": 2920 + }, + { + "epoch": 0.25, + "learning_rate": 1.7587175025153577e-05, + "loss": 0.4937, + "step": 2921 + }, + { + "epoch": 0.25, + "learning_rate": 1.7585375776959247e-05, + "loss": 0.5089, + "step": 2922 + }, + { + "epoch": 0.25, + "learning_rate": 1.7583575950272495e-05, + "loss": 0.4887, + "step": 2923 + }, + { + "epoch": 0.25, + "learning_rate": 1.7581775545230578e-05, + "loss": 0.5052, + "step": 2924 + }, + { + "epoch": 0.25, + "learning_rate": 1.7579974561970805e-05, + "loss": 0.4958, + "step": 2925 + }, + { + "epoch": 0.25, + "learning_rate": 1.7578173000630528e-05, + "loss": 0.4902, + "step": 2926 + }, + { + "epoch": 0.25, + "learning_rate": 1.757637086134714e-05, + "loss": 0.4894, + "step": 2927 + }, + { + "epoch": 0.25, + "learning_rate": 1.7574568144258078e-05, + "loss": 0.5099, + "step": 2928 + }, + { + "epoch": 0.25, + "learning_rate": 1.757276484950083e-05, + "loss": 0.492, + "step": 2929 + }, + { + "epoch": 0.25, + "learning_rate": 1.7570960977212915e-05, + "loss": 0.4927, + "step": 2930 + }, + { + "epoch": 0.25, + "learning_rate": 1.756915652753191e-05, + "loss": 0.5155, + "step": 2931 + }, + { + "epoch": 0.25, + "learning_rate": 1.7567351500595428e-05, + "loss": 0.5025, + "step": 2932 + }, + { + "epoch": 0.25, + "learning_rate": 1.7565545896541128e-05, + "loss": 0.4901, + "step": 2933 + }, + { + "epoch": 0.25, + "learning_rate": 1.756373971550671e-05, + "loss": 0.4853, + "step": 2934 + }, + { + "epoch": 0.25, + "learning_rate": 1.7561932957629927e-05, + "loss": 0.4906, + "step": 2935 + }, + { + "epoch": 0.25, + "learning_rate": 1.7560125623048566e-05, + "loss": 0.4953, + "step": 2936 + }, + { + "epoch": 0.25, + "learning_rate": 1.7558317711900463e-05, + "loss": 0.4877, + "step": 2937 + }, + { + "epoch": 0.25, + "learning_rate": 1.7556509224323495e-05, + "loss": 0.5124, + "step": 2938 + }, + { + "epoch": 0.25, + "learning_rate": 1.7554700160455586e-05, + "loss": 0.4874, + "step": 2939 + }, + { + "epoch": 0.25, + "learning_rate": 1.7552890520434704e-05, + "loss": 0.5059, + "step": 2940 + }, + { + "epoch": 0.25, + "learning_rate": 1.7551080304398858e-05, + "loss": 0.5018, + "step": 2941 + }, + { + "epoch": 0.25, + "learning_rate": 1.75492695124861e-05, + "loss": 0.499, + "step": 2942 + }, + { + "epoch": 0.25, + "learning_rate": 1.7547458144834536e-05, + "loss": 0.5062, + "step": 2943 + }, + { + "epoch": 0.25, + "learning_rate": 1.7545646201582304e-05, + "loss": 0.4884, + "step": 2944 + }, + { + "epoch": 0.25, + "learning_rate": 1.7543833682867588e-05, + "loss": 0.4912, + "step": 2945 + }, + { + "epoch": 0.25, + "learning_rate": 1.754202058882862e-05, + "loss": 0.4859, + "step": 2946 + }, + { + "epoch": 0.25, + "learning_rate": 1.754020691960368e-05, + "loss": 0.5048, + "step": 2947 + }, + { + "epoch": 0.25, + "learning_rate": 1.7538392675331074e-05, + "loss": 0.4852, + "step": 2948 + }, + { + "epoch": 0.25, + "learning_rate": 1.7536577856149178e-05, + "loss": 0.4838, + "step": 2949 + }, + { + "epoch": 0.25, + "learning_rate": 1.7534762462196385e-05, + "loss": 0.4944, + "step": 2950 + }, + { + "epoch": 0.25, + "learning_rate": 1.7532946493611152e-05, + "loss": 0.4862, + "step": 2951 + }, + { + "epoch": 0.25, + "learning_rate": 1.7531129950531972e-05, + "loss": 0.5208, + "step": 2952 + }, + { + "epoch": 0.25, + "learning_rate": 1.752931283309738e-05, + "loss": 0.4941, + "step": 2953 + }, + { + "epoch": 0.25, + "learning_rate": 1.7527495141445955e-05, + "loss": 0.5136, + "step": 2954 + }, + { + "epoch": 0.25, + "learning_rate": 1.7525676875716327e-05, + "loss": 0.4543, + "step": 2955 + }, + { + "epoch": 0.25, + "learning_rate": 1.7523858036047156e-05, + "loss": 0.5183, + "step": 2956 + }, + { + "epoch": 0.25, + "learning_rate": 1.7522038622577168e-05, + "loss": 0.5007, + "step": 2957 + }, + { + "epoch": 0.25, + "learning_rate": 1.7520218635445108e-05, + "loss": 0.4877, + "step": 2958 + }, + { + "epoch": 0.25, + "learning_rate": 1.7518398074789776e-05, + "loss": 0.502, + "step": 2959 + }, + { + "epoch": 0.25, + "learning_rate": 1.751657694075002e-05, + "loss": 0.4978, + "step": 2960 + }, + { + "epoch": 0.25, + "learning_rate": 1.7514755233464727e-05, + "loss": 0.4861, + "step": 2961 + }, + { + "epoch": 0.25, + "learning_rate": 1.7512932953072826e-05, + "loss": 0.4821, + "step": 2962 + }, + { + "epoch": 0.25, + "learning_rate": 1.751111009971329e-05, + "loss": 0.4945, + "step": 2963 + }, + { + "epoch": 0.25, + "learning_rate": 1.7509286673525143e-05, + "loss": 0.5138, + "step": 2964 + }, + { + "epoch": 0.25, + "learning_rate": 1.7507462674647445e-05, + "loss": 0.4813, + "step": 2965 + }, + { + "epoch": 0.25, + "learning_rate": 1.7505638103219297e-05, + "loss": 0.498, + "step": 2966 + }, + { + "epoch": 0.25, + "learning_rate": 1.7503812959379856e-05, + "loss": 0.5059, + "step": 2967 + }, + { + "epoch": 0.25, + "learning_rate": 1.7501987243268307e-05, + "loss": 0.4842, + "step": 2968 + }, + { + "epoch": 0.25, + "learning_rate": 1.750016095502389e-05, + "loss": 0.4918, + "step": 2969 + }, + { + "epoch": 0.25, + "learning_rate": 1.7498334094785895e-05, + "loss": 0.5125, + "step": 2970 + }, + { + "epoch": 0.25, + "learning_rate": 1.7496506662693632e-05, + "loss": 0.498, + "step": 2971 + }, + { + "epoch": 0.25, + "learning_rate": 1.7494678658886472e-05, + "loss": 0.5034, + "step": 2972 + }, + { + "epoch": 0.25, + "learning_rate": 1.749285008350383e-05, + "loss": 0.5076, + "step": 2973 + }, + { + "epoch": 0.25, + "learning_rate": 1.7491020936685158e-05, + "loss": 0.4914, + "step": 2974 + }, + { + "epoch": 0.25, + "learning_rate": 1.7489191218569958e-05, + "loss": 0.4996, + "step": 2975 + }, + { + "epoch": 0.25, + "learning_rate": 1.7487360929297765e-05, + "loss": 0.4927, + "step": 2976 + }, + { + "epoch": 0.25, + "learning_rate": 1.7485530069008173e-05, + "loss": 0.523, + "step": 2977 + }, + { + "epoch": 0.25, + "learning_rate": 1.7483698637840805e-05, + "loss": 0.4618, + "step": 2978 + }, + { + "epoch": 0.25, + "learning_rate": 1.7481866635935335e-05, + "loss": 0.5065, + "step": 2979 + }, + { + "epoch": 0.25, + "learning_rate": 1.748003406343148e-05, + "loss": 0.5005, + "step": 2980 + }, + { + "epoch": 0.25, + "learning_rate": 1.7478200920469e-05, + "loss": 0.4876, + "step": 2981 + }, + { + "epoch": 0.25, + "learning_rate": 1.7476367207187695e-05, + "loss": 0.4853, + "step": 2982 + }, + { + "epoch": 0.25, + "learning_rate": 1.7474532923727418e-05, + "loss": 0.4811, + "step": 2983 + }, + { + "epoch": 0.25, + "learning_rate": 1.7472698070228048e-05, + "loss": 0.492, + "step": 2984 + }, + { + "epoch": 0.25, + "learning_rate": 1.747086264682953e-05, + "loss": 0.5013, + "step": 2985 + }, + { + "epoch": 0.25, + "learning_rate": 1.7469026653671835e-05, + "loss": 0.5021, + "step": 2986 + }, + { + "epoch": 0.25, + "learning_rate": 1.7467190090894987e-05, + "loss": 0.5169, + "step": 2987 + }, + { + "epoch": 0.25, + "learning_rate": 1.746535295863905e-05, + "loss": 0.4976, + "step": 2988 + }, + { + "epoch": 0.25, + "learning_rate": 1.746351525704413e-05, + "loss": 0.492, + "step": 2989 + }, + { + "epoch": 0.25, + "learning_rate": 1.746167698625037e-05, + "loss": 0.4891, + "step": 2990 + }, + { + "epoch": 0.26, + "learning_rate": 1.7459838146397975e-05, + "loss": 0.4946, + "step": 2991 + }, + { + "epoch": 0.26, + "learning_rate": 1.7457998737627183e-05, + "loss": 0.4972, + "step": 2992 + }, + { + "epoch": 0.26, + "learning_rate": 1.7456158760078265e-05, + "loss": 0.4902, + "step": 2993 + }, + { + "epoch": 0.26, + "learning_rate": 1.7454318213891556e-05, + "loss": 0.4917, + "step": 2994 + }, + { + "epoch": 0.26, + "learning_rate": 1.7452477099207416e-05, + "loss": 0.501, + "step": 2995 + }, + { + "epoch": 0.26, + "learning_rate": 1.745063541616626e-05, + "loss": 0.4786, + "step": 2996 + }, + { + "epoch": 0.26, + "learning_rate": 1.7448793164908545e-05, + "loss": 0.4899, + "step": 2997 + }, + { + "epoch": 0.26, + "learning_rate": 1.7446950345574762e-05, + "loss": 0.5043, + "step": 2998 + }, + { + "epoch": 0.26, + "learning_rate": 1.7445106958305456e-05, + "loss": 0.4925, + "step": 2999 + }, + { + "epoch": 0.26, + "learning_rate": 1.744326300324121e-05, + "loss": 0.4892, + "step": 3000 + }, + { + "epoch": 0.26, + "learning_rate": 1.7441418480522656e-05, + "loss": 0.4848, + "step": 3001 + }, + { + "epoch": 0.26, + "learning_rate": 1.743957339029046e-05, + "loss": 0.4981, + "step": 3002 + }, + { + "epoch": 0.26, + "learning_rate": 1.7437727732685337e-05, + "loss": 0.4871, + "step": 3003 + }, + { + "epoch": 0.26, + "learning_rate": 1.7435881507848048e-05, + "loss": 0.4847, + "step": 3004 + }, + { + "epoch": 0.26, + "learning_rate": 1.743403471591939e-05, + "loss": 0.496, + "step": 3005 + }, + { + "epoch": 0.26, + "learning_rate": 1.7432187357040206e-05, + "loss": 0.4899, + "step": 3006 + }, + { + "epoch": 0.26, + "learning_rate": 1.7430339431351388e-05, + "loss": 0.4847, + "step": 3007 + }, + { + "epoch": 0.26, + "learning_rate": 1.7428490938993864e-05, + "loss": 0.4932, + "step": 3008 + }, + { + "epoch": 0.26, + "learning_rate": 1.7426641880108607e-05, + "loss": 0.4687, + "step": 3009 + }, + { + "epoch": 0.26, + "learning_rate": 1.7424792254836636e-05, + "loss": 0.4908, + "step": 3010 + }, + { + "epoch": 0.26, + "learning_rate": 1.742294206331901e-05, + "loss": 0.5091, + "step": 3011 + }, + { + "epoch": 0.26, + "learning_rate": 1.7421091305696834e-05, + "loss": 0.5073, + "step": 3012 + }, + { + "epoch": 0.26, + "learning_rate": 1.741923998211125e-05, + "loss": 0.4988, + "step": 3013 + }, + { + "epoch": 0.26, + "learning_rate": 1.7417388092703454e-05, + "loss": 0.5117, + "step": 3014 + }, + { + "epoch": 0.26, + "learning_rate": 1.741553563761467e-05, + "loss": 0.487, + "step": 3015 + }, + { + "epoch": 0.26, + "learning_rate": 1.7413682616986185e-05, + "loss": 0.4897, + "step": 3016 + }, + { + "epoch": 0.26, + "learning_rate": 1.741182903095931e-05, + "loss": 0.4824, + "step": 3017 + }, + { + "epoch": 0.26, + "learning_rate": 1.7409974879675408e-05, + "loss": 0.4892, + "step": 3018 + }, + { + "epoch": 0.26, + "learning_rate": 1.740812016327589e-05, + "loss": 0.5085, + "step": 3019 + }, + { + "epoch": 0.26, + "learning_rate": 1.7406264881902195e-05, + "loss": 0.4745, + "step": 3020 + }, + { + "epoch": 0.26, + "learning_rate": 1.7404409035695825e-05, + "loss": 0.506, + "step": 3021 + }, + { + "epoch": 0.26, + "learning_rate": 1.7402552624798306e-05, + "loss": 0.4969, + "step": 3022 + }, + { + "epoch": 0.26, + "learning_rate": 1.740069564935122e-05, + "loss": 0.4911, + "step": 3023 + }, + { + "epoch": 0.26, + "learning_rate": 1.7398838109496187e-05, + "loss": 0.4857, + "step": 3024 + }, + { + "epoch": 0.26, + "learning_rate": 1.739698000537487e-05, + "loss": 0.4719, + "step": 3025 + }, + { + "epoch": 0.26, + "learning_rate": 1.739512133712898e-05, + "loss": 0.485, + "step": 3026 + }, + { + "epoch": 0.26, + "learning_rate": 1.7393262104900258e-05, + "loss": 0.4927, + "step": 3027 + }, + { + "epoch": 0.26, + "learning_rate": 1.7391402308830506e-05, + "loss": 0.4932, + "step": 3028 + }, + { + "epoch": 0.26, + "learning_rate": 1.738954194906155e-05, + "loss": 0.5002, + "step": 3029 + }, + { + "epoch": 0.26, + "learning_rate": 1.7387681025735278e-05, + "loss": 0.5022, + "step": 3030 + }, + { + "epoch": 0.26, + "learning_rate": 1.738581953899361e-05, + "loss": 0.486, + "step": 3031 + }, + { + "epoch": 0.26, + "learning_rate": 1.7383957488978508e-05, + "loss": 0.4951, + "step": 3032 + }, + { + "epoch": 0.26, + "learning_rate": 1.7382094875831984e-05, + "loss": 0.4997, + "step": 3033 + }, + { + "epoch": 0.26, + "learning_rate": 1.738023169969608e-05, + "loss": 0.4773, + "step": 3034 + }, + { + "epoch": 0.26, + "learning_rate": 1.7378367960712896e-05, + "loss": 0.5047, + "step": 3035 + }, + { + "epoch": 0.26, + "learning_rate": 1.737650365902457e-05, + "loss": 0.5053, + "step": 3036 + }, + { + "epoch": 0.26, + "learning_rate": 1.7374638794773276e-05, + "loss": 0.5004, + "step": 3037 + }, + { + "epoch": 0.26, + "learning_rate": 1.737277336810124e-05, + "loss": 0.4871, + "step": 3038 + }, + { + "epoch": 0.26, + "learning_rate": 1.737090737915073e-05, + "loss": 0.5066, + "step": 3039 + }, + { + "epoch": 0.26, + "learning_rate": 1.7369040828064046e-05, + "loss": 0.4948, + "step": 3040 + }, + { + "epoch": 0.26, + "learning_rate": 1.7367173714983548e-05, + "loss": 0.5184, + "step": 3041 + }, + { + "epoch": 0.26, + "learning_rate": 1.7365306040051622e-05, + "loss": 0.504, + "step": 3042 + }, + { + "epoch": 0.26, + "learning_rate": 1.7363437803410708e-05, + "loss": 0.4912, + "step": 3043 + }, + { + "epoch": 0.26, + "learning_rate": 1.7361569005203288e-05, + "loss": 0.5031, + "step": 3044 + }, + { + "epoch": 0.26, + "learning_rate": 1.7359699645571883e-05, + "loss": 0.4924, + "step": 3045 + }, + { + "epoch": 0.26, + "learning_rate": 1.7357829724659056e-05, + "loss": 0.4825, + "step": 3046 + }, + { + "epoch": 0.26, + "learning_rate": 1.7355959242607413e-05, + "loss": 0.5128, + "step": 3047 + }, + { + "epoch": 0.26, + "learning_rate": 1.735408819955961e-05, + "loss": 0.4949, + "step": 3048 + }, + { + "epoch": 0.26, + "learning_rate": 1.7352216595658343e-05, + "loss": 0.4836, + "step": 3049 + }, + { + "epoch": 0.26, + "learning_rate": 1.7350344431046338e-05, + "loss": 0.484, + "step": 3050 + }, + { + "epoch": 0.26, + "learning_rate": 1.734847170586638e-05, + "loss": 0.5041, + "step": 3051 + }, + { + "epoch": 0.26, + "learning_rate": 1.7346598420261294e-05, + "loss": 0.4879, + "step": 3052 + }, + { + "epoch": 0.26, + "learning_rate": 1.7344724574373942e-05, + "loss": 0.4923, + "step": 3053 + }, + { + "epoch": 0.26, + "learning_rate": 1.734285016834723e-05, + "loss": 0.5026, + "step": 3054 + }, + { + "epoch": 0.26, + "learning_rate": 1.7340975202324103e-05, + "loss": 0.5041, + "step": 3055 + }, + { + "epoch": 0.26, + "learning_rate": 1.7339099676447564e-05, + "loss": 0.5049, + "step": 3056 + }, + { + "epoch": 0.26, + "learning_rate": 1.7337223590860643e-05, + "loss": 0.4899, + "step": 3057 + }, + { + "epoch": 0.26, + "learning_rate": 1.733534694570642e-05, + "loss": 0.5149, + "step": 3058 + }, + { + "epoch": 0.26, + "learning_rate": 1.7333469741128016e-05, + "loss": 0.4866, + "step": 3059 + }, + { + "epoch": 0.26, + "learning_rate": 1.733159197726859e-05, + "loss": 0.5207, + "step": 3060 + }, + { + "epoch": 0.26, + "learning_rate": 1.7329713654271356e-05, + "loss": 0.4773, + "step": 3061 + }, + { + "epoch": 0.26, + "learning_rate": 1.732783477227955e-05, + "loss": 0.4879, + "step": 3062 + }, + { + "epoch": 0.26, + "learning_rate": 1.732595533143648e-05, + "loss": 0.4992, + "step": 3063 + }, + { + "epoch": 0.26, + "learning_rate": 1.7324075331885466e-05, + "loss": 0.5088, + "step": 3064 + }, + { + "epoch": 0.26, + "learning_rate": 1.732219477376989e-05, + "loss": 0.4841, + "step": 3065 + }, + { + "epoch": 0.26, + "learning_rate": 1.7320313657233175e-05, + "loss": 0.4898, + "step": 3066 + }, + { + "epoch": 0.26, + "learning_rate": 1.731843198241878e-05, + "loss": 0.5043, + "step": 3067 + }, + { + "epoch": 0.26, + "learning_rate": 1.7316549749470205e-05, + "loss": 0.4959, + "step": 3068 + }, + { + "epoch": 0.26, + "learning_rate": 1.7314666958531e-05, + "loss": 0.512, + "step": 3069 + }, + { + "epoch": 0.26, + "learning_rate": 1.7312783609744753e-05, + "loss": 0.4905, + "step": 3070 + }, + { + "epoch": 0.26, + "learning_rate": 1.7310899703255103e-05, + "loss": 0.5037, + "step": 3071 + }, + { + "epoch": 0.26, + "learning_rate": 1.7309015239205717e-05, + "loss": 0.4869, + "step": 3072 + }, + { + "epoch": 0.26, + "learning_rate": 1.7307130217740317e-05, + "loss": 0.4975, + "step": 3073 + }, + { + "epoch": 0.26, + "learning_rate": 1.7305244639002657e-05, + "loss": 0.4905, + "step": 3074 + }, + { + "epoch": 0.26, + "learning_rate": 1.7303358503136544e-05, + "loss": 0.4991, + "step": 3075 + }, + { + "epoch": 0.26, + "learning_rate": 1.7301471810285823e-05, + "loss": 0.495, + "step": 3076 + }, + { + "epoch": 0.26, + "learning_rate": 1.7299584560594376e-05, + "loss": 0.4924, + "step": 3077 + }, + { + "epoch": 0.26, + "learning_rate": 1.7297696754206137e-05, + "loss": 0.4816, + "step": 3078 + }, + { + "epoch": 0.26, + "learning_rate": 1.7295808391265074e-05, + "loss": 0.4917, + "step": 3079 + }, + { + "epoch": 0.26, + "learning_rate": 1.7293919471915207e-05, + "loss": 0.499, + "step": 3080 + }, + { + "epoch": 0.26, + "learning_rate": 1.729202999630059e-05, + "loss": 0.4946, + "step": 3081 + }, + { + "epoch": 0.26, + "learning_rate": 1.729013996456532e-05, + "loss": 0.4896, + "step": 3082 + }, + { + "epoch": 0.26, + "learning_rate": 1.7288249376853543e-05, + "loss": 0.4865, + "step": 3083 + }, + { + "epoch": 0.26, + "learning_rate": 1.7286358233309438e-05, + "loss": 0.5144, + "step": 3084 + }, + { + "epoch": 0.26, + "learning_rate": 1.728446653407724e-05, + "loss": 0.5058, + "step": 3085 + }, + { + "epoch": 0.26, + "learning_rate": 1.7282574279301205e-05, + "loss": 0.4927, + "step": 3086 + }, + { + "epoch": 0.26, + "learning_rate": 1.7280681469125657e-05, + "loss": 0.5008, + "step": 3087 + }, + { + "epoch": 0.26, + "learning_rate": 1.7278788103694944e-05, + "loss": 0.4769, + "step": 3088 + }, + { + "epoch": 0.26, + "learning_rate": 1.7276894183153457e-05, + "loss": 0.5025, + "step": 3089 + }, + { + "epoch": 0.26, + "learning_rate": 1.7274999707645646e-05, + "loss": 0.4839, + "step": 3090 + }, + { + "epoch": 0.26, + "learning_rate": 1.727310467731598e-05, + "loss": 0.4872, + "step": 3091 + }, + { + "epoch": 0.26, + "learning_rate": 1.7271209092308993e-05, + "loss": 0.4883, + "step": 3092 + }, + { + "epoch": 0.26, + "learning_rate": 1.726931295276924e-05, + "loss": 0.4906, + "step": 3093 + }, + { + "epoch": 0.26, + "learning_rate": 1.7267416258841333e-05, + "loss": 0.4939, + "step": 3094 + }, + { + "epoch": 0.26, + "learning_rate": 1.726551901066992e-05, + "loss": 0.5106, + "step": 3095 + }, + { + "epoch": 0.26, + "learning_rate": 1.7263621208399696e-05, + "loss": 0.5011, + "step": 3096 + }, + { + "epoch": 0.26, + "learning_rate": 1.7261722852175394e-05, + "loss": 0.4931, + "step": 3097 + }, + { + "epoch": 0.26, + "learning_rate": 1.7259823942141794e-05, + "loss": 0.4738, + "step": 3098 + }, + { + "epoch": 0.26, + "learning_rate": 1.725792447844371e-05, + "loss": 0.5066, + "step": 3099 + }, + { + "epoch": 0.26, + "learning_rate": 1.7256024461226002e-05, + "loss": 0.5124, + "step": 3100 + }, + { + "epoch": 0.26, + "learning_rate": 1.7254123890633576e-05, + "loss": 0.4834, + "step": 3101 + }, + { + "epoch": 0.26, + "learning_rate": 1.7252222766811376e-05, + "loss": 0.4883, + "step": 3102 + }, + { + "epoch": 0.26, + "learning_rate": 1.7250321089904393e-05, + "loss": 0.5048, + "step": 3103 + }, + { + "epoch": 0.26, + "learning_rate": 1.7248418860057653e-05, + "loss": 0.4912, + "step": 3104 + }, + { + "epoch": 0.26, + "learning_rate": 1.7246516077416232e-05, + "loss": 0.4864, + "step": 3105 + }, + { + "epoch": 0.26, + "learning_rate": 1.7244612742125237e-05, + "loss": 0.4934, + "step": 3106 + }, + { + "epoch": 0.26, + "learning_rate": 1.7242708854329833e-05, + "loss": 0.5087, + "step": 3107 + }, + { + "epoch": 0.27, + "learning_rate": 1.724080441417521e-05, + "loss": 0.4767, + "step": 3108 + }, + { + "epoch": 0.27, + "learning_rate": 1.7238899421806618e-05, + "loss": 0.4848, + "step": 3109 + }, + { + "epoch": 0.27, + "learning_rate": 1.7236993877369333e-05, + "loss": 0.4967, + "step": 3110 + }, + { + "epoch": 0.27, + "learning_rate": 1.723508778100868e-05, + "loss": 0.4954, + "step": 3111 + }, + { + "epoch": 0.27, + "learning_rate": 1.723318113287003e-05, + "loss": 0.4913, + "step": 3112 + }, + { + "epoch": 0.27, + "learning_rate": 1.7231273933098784e-05, + "loss": 0.4828, + "step": 3113 + }, + { + "epoch": 0.27, + "learning_rate": 1.7229366181840405e-05, + "loss": 0.4925, + "step": 3114 + }, + { + "epoch": 0.27, + "learning_rate": 1.7227457879240375e-05, + "loss": 0.5013, + "step": 3115 + }, + { + "epoch": 0.27, + "learning_rate": 1.7225549025444233e-05, + "loss": 0.5048, + "step": 3116 + }, + { + "epoch": 0.27, + "learning_rate": 1.7223639620597556e-05, + "loss": 0.5037, + "step": 3117 + }, + { + "epoch": 0.27, + "learning_rate": 1.7221729664845966e-05, + "loss": 0.4903, + "step": 3118 + }, + { + "epoch": 0.27, + "learning_rate": 1.7219819158335123e-05, + "loss": 0.4899, + "step": 3119 + }, + { + "epoch": 0.27, + "learning_rate": 1.7217908101210725e-05, + "loss": 0.4959, + "step": 3120 + }, + { + "epoch": 0.27, + "learning_rate": 1.7215996493618525e-05, + "loss": 0.4844, + "step": 3121 + }, + { + "epoch": 0.27, + "learning_rate": 1.7214084335704305e-05, + "loss": 0.5091, + "step": 3122 + }, + { + "epoch": 0.27, + "learning_rate": 1.7212171627613895e-05, + "loss": 0.4994, + "step": 3123 + }, + { + "epoch": 0.27, + "learning_rate": 1.721025836949317e-05, + "loss": 0.4843, + "step": 3124 + }, + { + "epoch": 0.27, + "learning_rate": 1.7208344561488037e-05, + "loss": 0.4854, + "step": 3125 + }, + { + "epoch": 0.27, + "learning_rate": 1.7206430203744455e-05, + "loss": 0.4778, + "step": 3126 + }, + { + "epoch": 0.27, + "learning_rate": 1.7204515296408418e-05, + "loss": 0.4773, + "step": 3127 + }, + { + "epoch": 0.27, + "learning_rate": 1.720259983962597e-05, + "loss": 0.4921, + "step": 3128 + }, + { + "epoch": 0.27, + "learning_rate": 1.7200683833543185e-05, + "loss": 0.5156, + "step": 3129 + }, + { + "epoch": 0.27, + "learning_rate": 1.719876727830619e-05, + "loss": 0.4991, + "step": 3130 + }, + { + "epoch": 0.27, + "learning_rate": 1.719685017406115e-05, + "loss": 0.4911, + "step": 3131 + }, + { + "epoch": 0.27, + "learning_rate": 1.7194932520954266e-05, + "loss": 0.4823, + "step": 3132 + }, + { + "epoch": 0.27, + "learning_rate": 1.7193014319131794e-05, + "loss": 0.5119, + "step": 3133 + }, + { + "epoch": 0.27, + "learning_rate": 1.7191095568740017e-05, + "loss": 0.4912, + "step": 3134 + }, + { + "epoch": 0.27, + "learning_rate": 1.7189176269925272e-05, + "loss": 0.4937, + "step": 3135 + }, + { + "epoch": 0.27, + "learning_rate": 1.7187256422833928e-05, + "loss": 0.5136, + "step": 3136 + }, + { + "epoch": 0.27, + "learning_rate": 1.7185336027612405e-05, + "loss": 0.4928, + "step": 3137 + }, + { + "epoch": 0.27, + "learning_rate": 1.7183415084407162e-05, + "loss": 0.5143, + "step": 3138 + }, + { + "epoch": 0.27, + "learning_rate": 1.7181493593364688e-05, + "loss": 0.4933, + "step": 3139 + }, + { + "epoch": 0.27, + "learning_rate": 1.7179571554631534e-05, + "loss": 0.5069, + "step": 3140 + }, + { + "epoch": 0.27, + "learning_rate": 1.717764896835428e-05, + "loss": 0.4969, + "step": 3141 + }, + { + "epoch": 0.27, + "learning_rate": 1.7175725834679552e-05, + "loss": 0.4992, + "step": 3142 + }, + { + "epoch": 0.27, + "learning_rate": 1.717380215375401e-05, + "loss": 0.5069, + "step": 3143 + }, + { + "epoch": 0.27, + "learning_rate": 1.7171877925724366e-05, + "loss": 0.4913, + "step": 3144 + }, + { + "epoch": 0.27, + "learning_rate": 1.7169953150737375e-05, + "loss": 0.4822, + "step": 3145 + }, + { + "epoch": 0.27, + "learning_rate": 1.7168027828939818e-05, + "loss": 0.4992, + "step": 3146 + }, + { + "epoch": 0.27, + "learning_rate": 1.7166101960478537e-05, + "loss": 0.4857, + "step": 3147 + }, + { + "epoch": 0.27, + "learning_rate": 1.71641755455004e-05, + "loss": 0.4978, + "step": 3148 + }, + { + "epoch": 0.27, + "learning_rate": 1.716224858415233e-05, + "loss": 0.4907, + "step": 3149 + }, + { + "epoch": 0.27, + "learning_rate": 1.7160321076581275e-05, + "loss": 0.496, + "step": 3150 + }, + { + "epoch": 0.27, + "learning_rate": 1.7158393022934246e-05, + "loss": 0.4861, + "step": 3151 + }, + { + "epoch": 0.27, + "learning_rate": 1.7156464423358277e-05, + "loss": 0.4912, + "step": 3152 + }, + { + "epoch": 0.27, + "learning_rate": 1.7154535278000458e-05, + "loss": 0.4858, + "step": 3153 + }, + { + "epoch": 0.27, + "learning_rate": 1.7152605587007906e-05, + "loss": 0.4921, + "step": 3154 + }, + { + "epoch": 0.27, + "learning_rate": 1.715067535052779e-05, + "loss": 0.4861, + "step": 3155 + }, + { + "epoch": 0.27, + "learning_rate": 1.714874456870732e-05, + "loss": 0.4735, + "step": 3156 + }, + { + "epoch": 0.27, + "learning_rate": 1.7146813241693742e-05, + "loss": 0.5134, + "step": 3157 + }, + { + "epoch": 0.27, + "learning_rate": 1.7144881369634354e-05, + "loss": 0.4862, + "step": 3158 + }, + { + "epoch": 0.27, + "learning_rate": 1.7142948952676478e-05, + "loss": 0.5313, + "step": 3159 + }, + { + "epoch": 0.27, + "learning_rate": 1.71410159909675e-05, + "loss": 0.4878, + "step": 3160 + }, + { + "epoch": 0.27, + "learning_rate": 1.7139082484654825e-05, + "loss": 0.5183, + "step": 3161 + }, + { + "epoch": 0.27, + "learning_rate": 1.713714843388592e-05, + "loss": 0.5032, + "step": 3162 + }, + { + "epoch": 0.27, + "learning_rate": 1.7135213838808275e-05, + "loss": 0.4872, + "step": 3163 + }, + { + "epoch": 0.27, + "learning_rate": 1.713327869956943e-05, + "loss": 0.4827, + "step": 3164 + }, + { + "epoch": 0.27, + "learning_rate": 1.7131343016316976e-05, + "loss": 0.497, + "step": 3165 + }, + { + "epoch": 0.27, + "learning_rate": 1.712940678919853e-05, + "loss": 0.4871, + "step": 3166 + }, + { + "epoch": 0.27, + "learning_rate": 1.712747001836176e-05, + "loss": 0.4855, + "step": 3167 + }, + { + "epoch": 0.27, + "learning_rate": 1.7125532703954366e-05, + "loss": 0.5069, + "step": 3168 + }, + { + "epoch": 0.27, + "learning_rate": 1.7123594846124105e-05, + "loss": 0.4639, + "step": 3169 + }, + { + "epoch": 0.27, + "learning_rate": 1.7121656445018756e-05, + "loss": 0.5106, + "step": 3170 + }, + { + "epoch": 0.27, + "learning_rate": 1.7119717500786158e-05, + "loss": 0.4764, + "step": 3171 + }, + { + "epoch": 0.27, + "learning_rate": 1.7117778013574174e-05, + "loss": 0.5048, + "step": 3172 + }, + { + "epoch": 0.27, + "learning_rate": 1.711583798353073e-05, + "loss": 0.4774, + "step": 3173 + }, + { + "epoch": 0.27, + "learning_rate": 1.7113897410803767e-05, + "loss": 0.4928, + "step": 3174 + }, + { + "epoch": 0.27, + "learning_rate": 1.7111956295541296e-05, + "loss": 0.4963, + "step": 3175 + }, + { + "epoch": 0.27, + "learning_rate": 1.711001463789134e-05, + "loss": 0.478, + "step": 3176 + }, + { + "epoch": 0.27, + "learning_rate": 1.7108072438001987e-05, + "loss": 0.4775, + "step": 3177 + }, + { + "epoch": 0.27, + "learning_rate": 1.7106129696021353e-05, + "loss": 0.5119, + "step": 3178 + }, + { + "epoch": 0.27, + "learning_rate": 1.71041864120976e-05, + "loss": 0.484, + "step": 3179 + }, + { + "epoch": 0.27, + "learning_rate": 1.7102242586378936e-05, + "loss": 0.503, + "step": 3180 + }, + { + "epoch": 0.27, + "learning_rate": 1.7100298219013597e-05, + "loss": 0.4702, + "step": 3181 + }, + { + "epoch": 0.27, + "learning_rate": 1.7098353310149876e-05, + "loss": 0.4989, + "step": 3182 + }, + { + "epoch": 0.27, + "learning_rate": 1.7096407859936095e-05, + "loss": 0.4991, + "step": 3183 + }, + { + "epoch": 0.27, + "learning_rate": 1.7094461868520625e-05, + "loss": 0.4967, + "step": 3184 + }, + { + "epoch": 0.27, + "learning_rate": 1.7092515336051872e-05, + "loss": 0.5047, + "step": 3185 + }, + { + "epoch": 0.27, + "learning_rate": 1.7090568262678294e-05, + "loss": 0.487, + "step": 3186 + }, + { + "epoch": 0.27, + "learning_rate": 1.7088620648548376e-05, + "loss": 0.5029, + "step": 3187 + }, + { + "epoch": 0.27, + "learning_rate": 1.708667249381065e-05, + "loss": 0.4998, + "step": 3188 + }, + { + "epoch": 0.27, + "learning_rate": 1.7084723798613697e-05, + "loss": 0.5008, + "step": 3189 + }, + { + "epoch": 0.27, + "learning_rate": 1.708277456310613e-05, + "loss": 0.4969, + "step": 3190 + }, + { + "epoch": 0.27, + "learning_rate": 1.7080824787436603e-05, + "loss": 0.5108, + "step": 3191 + }, + { + "epoch": 0.27, + "learning_rate": 1.7078874471753816e-05, + "loss": 0.4998, + "step": 3192 + }, + { + "epoch": 0.27, + "learning_rate": 1.707692361620651e-05, + "loss": 0.4907, + "step": 3193 + }, + { + "epoch": 0.27, + "learning_rate": 1.7074972220943464e-05, + "loss": 0.4924, + "step": 3194 + }, + { + "epoch": 0.27, + "learning_rate": 1.7073020286113498e-05, + "loss": 0.4852, + "step": 3195 + }, + { + "epoch": 0.27, + "learning_rate": 1.7071067811865477e-05, + "loss": 0.492, + "step": 3196 + }, + { + "epoch": 0.27, + "learning_rate": 1.7069114798348303e-05, + "loss": 0.4786, + "step": 3197 + }, + { + "epoch": 0.27, + "learning_rate": 1.7067161245710924e-05, + "loss": 0.5085, + "step": 3198 + }, + { + "epoch": 0.27, + "learning_rate": 1.706520715410232e-05, + "loss": 0.4917, + "step": 3199 + }, + { + "epoch": 0.27, + "learning_rate": 1.706325252367152e-05, + "loss": 0.4949, + "step": 3200 + }, + { + "epoch": 0.27, + "learning_rate": 1.7061297354567603e-05, + "loss": 0.4948, + "step": 3201 + }, + { + "epoch": 0.27, + "learning_rate": 1.7059341646939665e-05, + "loss": 0.4932, + "step": 3202 + }, + { + "epoch": 0.27, + "learning_rate": 1.705738540093686e-05, + "loss": 0.4996, + "step": 3203 + }, + { + "epoch": 0.27, + "learning_rate": 1.705542861670838e-05, + "loss": 0.5124, + "step": 3204 + }, + { + "epoch": 0.27, + "learning_rate": 1.7053471294403464e-05, + "loss": 0.4796, + "step": 3205 + }, + { + "epoch": 0.27, + "learning_rate": 1.7051513434171375e-05, + "loss": 0.4907, + "step": 3206 + }, + { + "epoch": 0.27, + "learning_rate": 1.7049555036161433e-05, + "loss": 0.5056, + "step": 3207 + }, + { + "epoch": 0.27, + "learning_rate": 1.7047596100522992e-05, + "loss": 0.4642, + "step": 3208 + }, + { + "epoch": 0.27, + "learning_rate": 1.704563662740545e-05, + "loss": 0.5044, + "step": 3209 + }, + { + "epoch": 0.27, + "learning_rate": 1.7043676616958245e-05, + "loss": 0.5, + "step": 3210 + }, + { + "epoch": 0.27, + "learning_rate": 1.7041716069330853e-05, + "loss": 0.4906, + "step": 3211 + }, + { + "epoch": 0.27, + "learning_rate": 1.70397549846728e-05, + "loss": 0.4824, + "step": 3212 + }, + { + "epoch": 0.27, + "learning_rate": 1.703779336313364e-05, + "loss": 0.5066, + "step": 3213 + }, + { + "epoch": 0.27, + "learning_rate": 1.703583120486297e-05, + "loss": 0.4909, + "step": 3214 + }, + { + "epoch": 0.27, + "learning_rate": 1.7033868510010446e-05, + "loss": 0.4549, + "step": 3215 + }, + { + "epoch": 0.27, + "learning_rate": 1.703190527872574e-05, + "loss": 0.4896, + "step": 3216 + }, + { + "epoch": 0.27, + "learning_rate": 1.702994151115858e-05, + "loss": 0.5149, + "step": 3217 + }, + { + "epoch": 0.27, + "learning_rate": 1.7027977207458732e-05, + "loss": 0.4926, + "step": 3218 + }, + { + "epoch": 0.27, + "learning_rate": 1.7026012367776002e-05, + "loss": 0.5133, + "step": 3219 + }, + { + "epoch": 0.27, + "learning_rate": 1.702404699226024e-05, + "loss": 0.4792, + "step": 3220 + }, + { + "epoch": 0.27, + "learning_rate": 1.7022081081061323e-05, + "loss": 0.4976, + "step": 3221 + }, + { + "epoch": 0.27, + "learning_rate": 1.702011463432919e-05, + "loss": 0.4901, + "step": 3222 + }, + { + "epoch": 0.27, + "learning_rate": 1.7018147652213805e-05, + "loss": 0.4886, + "step": 3223 + }, + { + "epoch": 0.27, + "learning_rate": 1.7016180134865182e-05, + "loss": 0.4995, + "step": 3224 + }, + { + "epoch": 0.27, + "learning_rate": 1.701421208243337e-05, + "loss": 0.5057, + "step": 3225 + }, + { + "epoch": 0.28, + "learning_rate": 1.701224349506846e-05, + "loss": 0.4833, + "step": 3226 + }, + { + "epoch": 0.28, + "learning_rate": 1.7010274372920584e-05, + "loss": 0.5102, + "step": 3227 + }, + { + "epoch": 0.28, + "learning_rate": 1.700830471613992e-05, + "loss": 0.4952, + "step": 3228 + }, + { + "epoch": 0.28, + "learning_rate": 1.700633452487668e-05, + "loss": 0.5003, + "step": 3229 + }, + { + "epoch": 0.28, + "learning_rate": 1.700436379928112e-05, + "loss": 0.4914, + "step": 3230 + }, + { + "epoch": 0.28, + "learning_rate": 1.700239253950353e-05, + "loss": 0.4846, + "step": 3231 + }, + { + "epoch": 0.28, + "learning_rate": 1.7000420745694256e-05, + "loss": 0.4989, + "step": 3232 + }, + { + "epoch": 0.28, + "learning_rate": 1.6998448418003666e-05, + "loss": 0.4913, + "step": 3233 + }, + { + "epoch": 0.28, + "learning_rate": 1.6996475556582182e-05, + "loss": 0.4775, + "step": 3234 + }, + { + "epoch": 0.28, + "learning_rate": 1.6994502161580263e-05, + "loss": 0.5046, + "step": 3235 + }, + { + "epoch": 0.28, + "learning_rate": 1.6992528233148414e-05, + "loss": 0.4768, + "step": 3236 + }, + { + "epoch": 0.28, + "learning_rate": 1.699055377143716e-05, + "loss": 0.4879, + "step": 3237 + }, + { + "epoch": 0.28, + "learning_rate": 1.6988578776597094e-05, + "loss": 0.475, + "step": 3238 + }, + { + "epoch": 0.28, + "learning_rate": 1.6986603248778838e-05, + "loss": 0.4954, + "step": 3239 + }, + { + "epoch": 0.28, + "learning_rate": 1.6984627188133045e-05, + "loss": 0.4972, + "step": 3240 + }, + { + "epoch": 0.28, + "learning_rate": 1.6982650594810424e-05, + "loss": 0.484, + "step": 3241 + }, + { + "epoch": 0.28, + "learning_rate": 1.6980673468961717e-05, + "loss": 0.5097, + "step": 3242 + }, + { + "epoch": 0.28, + "learning_rate": 1.6978695810737708e-05, + "loss": 0.4724, + "step": 3243 + }, + { + "epoch": 0.28, + "learning_rate": 1.697671762028922e-05, + "loss": 0.4885, + "step": 3244 + }, + { + "epoch": 0.28, + "learning_rate": 1.6974738897767123e-05, + "loss": 0.4736, + "step": 3245 + }, + { + "epoch": 0.28, + "learning_rate": 1.6972759643322315e-05, + "loss": 0.4777, + "step": 3246 + }, + { + "epoch": 0.28, + "learning_rate": 1.6970779857105747e-05, + "loss": 0.5144, + "step": 3247 + }, + { + "epoch": 0.28, + "learning_rate": 1.6968799539268408e-05, + "loss": 0.5038, + "step": 3248 + }, + { + "epoch": 0.28, + "learning_rate": 1.696681868996132e-05, + "loss": 0.5059, + "step": 3249 + }, + { + "epoch": 0.28, + "learning_rate": 1.6964837309335553e-05, + "loss": 0.4762, + "step": 3250 + }, + { + "epoch": 0.28, + "learning_rate": 1.6962855397542215e-05, + "loss": 0.5127, + "step": 3251 + }, + { + "epoch": 0.28, + "learning_rate": 1.6960872954732457e-05, + "loss": 0.4865, + "step": 3252 + }, + { + "epoch": 0.28, + "learning_rate": 1.6958889981057467e-05, + "loss": 0.491, + "step": 3253 + }, + { + "epoch": 0.28, + "learning_rate": 1.6956906476668472e-05, + "loss": 0.4641, + "step": 3254 + }, + { + "epoch": 0.28, + "learning_rate": 1.6954922441716745e-05, + "loss": 0.4878, + "step": 3255 + }, + { + "epoch": 0.28, + "learning_rate": 1.6952937876353595e-05, + "loss": 0.4793, + "step": 3256 + }, + { + "epoch": 0.28, + "learning_rate": 1.6950952780730382e-05, + "loss": 0.4844, + "step": 3257 + }, + { + "epoch": 0.28, + "learning_rate": 1.6948967154998487e-05, + "loss": 0.4966, + "step": 3258 + }, + { + "epoch": 0.28, + "learning_rate": 1.6946980999309343e-05, + "loss": 0.4844, + "step": 3259 + }, + { + "epoch": 0.28, + "learning_rate": 1.6944994313814426e-05, + "loss": 0.479, + "step": 3260 + }, + { + "epoch": 0.28, + "learning_rate": 1.6943007098665253e-05, + "loss": 0.4874, + "step": 3261 + }, + { + "epoch": 0.28, + "learning_rate": 1.694101935401337e-05, + "loss": 0.4953, + "step": 3262 + }, + { + "epoch": 0.28, + "learning_rate": 1.693903108001037e-05, + "loss": 0.4975, + "step": 3263 + }, + { + "epoch": 0.28, + "learning_rate": 1.6937042276807893e-05, + "loss": 0.4805, + "step": 3264 + }, + { + "epoch": 0.28, + "learning_rate": 1.693505294455761e-05, + "loss": 0.501, + "step": 3265 + }, + { + "epoch": 0.28, + "learning_rate": 1.6933063083411235e-05, + "loss": 0.4984, + "step": 3266 + }, + { + "epoch": 0.28, + "learning_rate": 1.6931072693520526e-05, + "loss": 0.4855, + "step": 3267 + }, + { + "epoch": 0.28, + "learning_rate": 1.6929081775037276e-05, + "loss": 0.4861, + "step": 3268 + }, + { + "epoch": 0.28, + "learning_rate": 1.6927090328113322e-05, + "loss": 0.4887, + "step": 3269 + }, + { + "epoch": 0.28, + "learning_rate": 1.6925098352900542e-05, + "loss": 0.4748, + "step": 3270 + }, + { + "epoch": 0.28, + "learning_rate": 1.692310584955085e-05, + "loss": 0.4997, + "step": 3271 + }, + { + "epoch": 0.28, + "learning_rate": 1.69211128182162e-05, + "loss": 0.4932, + "step": 3272 + }, + { + "epoch": 0.28, + "learning_rate": 1.6919119259048592e-05, + "loss": 0.48, + "step": 3273 + }, + { + "epoch": 0.28, + "learning_rate": 1.6917125172200066e-05, + "loss": 0.4874, + "step": 3274 + }, + { + "epoch": 0.28, + "learning_rate": 1.6915130557822698e-05, + "loss": 0.5077, + "step": 3275 + }, + { + "epoch": 0.28, + "learning_rate": 1.69131354160686e-05, + "loss": 0.492, + "step": 3276 + }, + { + "epoch": 0.28, + "learning_rate": 1.6911139747089932e-05, + "loss": 0.4833, + "step": 3277 + }, + { + "epoch": 0.28, + "learning_rate": 1.6909143551038895e-05, + "loss": 0.5251, + "step": 3278 + }, + { + "epoch": 0.28, + "learning_rate": 1.690714682806773e-05, + "loss": 0.5078, + "step": 3279 + }, + { + "epoch": 0.28, + "learning_rate": 1.6905149578328705e-05, + "loss": 0.4704, + "step": 3280 + }, + { + "epoch": 0.28, + "learning_rate": 1.690315180197415e-05, + "loss": 0.5008, + "step": 3281 + }, + { + "epoch": 0.28, + "learning_rate": 1.6901153499156416e-05, + "loss": 0.4727, + "step": 3282 + }, + { + "epoch": 0.28, + "learning_rate": 1.6899154670027903e-05, + "loss": 0.4981, + "step": 3283 + }, + { + "epoch": 0.28, + "learning_rate": 1.689715531474106e-05, + "loss": 0.495, + "step": 3284 + }, + { + "epoch": 0.28, + "learning_rate": 1.689515543344835e-05, + "loss": 0.5114, + "step": 3285 + }, + { + "epoch": 0.28, + "learning_rate": 1.68931550263023e-05, + "loss": 0.4781, + "step": 3286 + }, + { + "epoch": 0.28, + "learning_rate": 1.6891154093455475e-05, + "loss": 0.5025, + "step": 3287 + }, + { + "epoch": 0.28, + "learning_rate": 1.6889152635060465e-05, + "loss": 0.4908, + "step": 3288 + }, + { + "epoch": 0.28, + "learning_rate": 1.6887150651269918e-05, + "loss": 0.488, + "step": 3289 + }, + { + "epoch": 0.28, + "learning_rate": 1.6885148142236503e-05, + "loss": 0.4975, + "step": 3290 + }, + { + "epoch": 0.28, + "learning_rate": 1.6883145108112952e-05, + "loss": 0.5117, + "step": 3291 + }, + { + "epoch": 0.28, + "learning_rate": 1.6881141549052014e-05, + "loss": 0.4794, + "step": 3292 + }, + { + "epoch": 0.28, + "learning_rate": 1.68791374652065e-05, + "loss": 0.4683, + "step": 3293 + }, + { + "epoch": 0.28, + "learning_rate": 1.6877132856729237e-05, + "loss": 0.4869, + "step": 3294 + }, + { + "epoch": 0.28, + "learning_rate": 1.6875127723773114e-05, + "loss": 0.5074, + "step": 3295 + }, + { + "epoch": 0.28, + "learning_rate": 1.6873122066491046e-05, + "loss": 0.4828, + "step": 3296 + }, + { + "epoch": 0.28, + "learning_rate": 1.6871115885035995e-05, + "loss": 0.5033, + "step": 3297 + }, + { + "epoch": 0.28, + "learning_rate": 1.686910917956096e-05, + "loss": 0.4826, + "step": 3298 + }, + { + "epoch": 0.28, + "learning_rate": 1.6867101950218988e-05, + "loss": 0.4761, + "step": 3299 + }, + { + "epoch": 0.28, + "learning_rate": 1.6865094197163147e-05, + "loss": 0.4969, + "step": 3300 + }, + { + "epoch": 0.28, + "learning_rate": 1.686308592054656e-05, + "loss": 0.5012, + "step": 3301 + }, + { + "epoch": 0.28, + "learning_rate": 1.6861077120522387e-05, + "loss": 0.4716, + "step": 3302 + }, + { + "epoch": 0.28, + "learning_rate": 1.6859067797243835e-05, + "loss": 0.4718, + "step": 3303 + }, + { + "epoch": 0.28, + "learning_rate": 1.6857057950864134e-05, + "loss": 0.496, + "step": 3304 + }, + { + "epoch": 0.28, + "learning_rate": 1.6855047581536564e-05, + "loss": 0.4991, + "step": 3305 + }, + { + "epoch": 0.28, + "learning_rate": 1.685303668941445e-05, + "loss": 0.5157, + "step": 3306 + }, + { + "epoch": 0.28, + "learning_rate": 1.6851025274651145e-05, + "loss": 0.4962, + "step": 3307 + }, + { + "epoch": 0.28, + "learning_rate": 1.684901333740005e-05, + "loss": 0.5109, + "step": 3308 + }, + { + "epoch": 0.28, + "learning_rate": 1.684700087781461e-05, + "loss": 0.4991, + "step": 3309 + }, + { + "epoch": 0.28, + "learning_rate": 1.6844987896048287e-05, + "loss": 0.5133, + "step": 3310 + }, + { + "epoch": 0.28, + "learning_rate": 1.684297439225462e-05, + "loss": 0.5138, + "step": 3311 + }, + { + "epoch": 0.28, + "learning_rate": 1.6840960366587153e-05, + "loss": 0.5017, + "step": 3312 + }, + { + "epoch": 0.28, + "learning_rate": 1.6838945819199487e-05, + "loss": 0.4928, + "step": 3313 + }, + { + "epoch": 0.28, + "learning_rate": 1.6836930750245264e-05, + "loss": 0.5162, + "step": 3314 + }, + { + "epoch": 0.28, + "learning_rate": 1.6834915159878158e-05, + "loss": 0.5044, + "step": 3315 + }, + { + "epoch": 0.28, + "learning_rate": 1.6832899048251886e-05, + "loss": 0.4886, + "step": 3316 + }, + { + "epoch": 0.28, + "learning_rate": 1.6830882415520204e-05, + "loss": 0.5142, + "step": 3317 + }, + { + "epoch": 0.28, + "learning_rate": 1.6828865261836917e-05, + "loss": 0.4797, + "step": 3318 + }, + { + "epoch": 0.28, + "learning_rate": 1.682684758735585e-05, + "loss": 0.4888, + "step": 3319 + }, + { + "epoch": 0.28, + "learning_rate": 1.6824829392230886e-05, + "loss": 0.5033, + "step": 3320 + }, + { + "epoch": 0.28, + "learning_rate": 1.682281067661594e-05, + "loss": 0.4844, + "step": 3321 + }, + { + "epoch": 0.28, + "learning_rate": 1.682079144066497e-05, + "loss": 0.4765, + "step": 3322 + }, + { + "epoch": 0.28, + "learning_rate": 1.6818771684531966e-05, + "loss": 0.4843, + "step": 3323 + }, + { + "epoch": 0.28, + "learning_rate": 1.6816751408370966e-05, + "loss": 0.4879, + "step": 3324 + }, + { + "epoch": 0.28, + "learning_rate": 1.6814730612336044e-05, + "loss": 0.4909, + "step": 3325 + }, + { + "epoch": 0.28, + "learning_rate": 1.6812709296581316e-05, + "loss": 0.4837, + "step": 3326 + }, + { + "epoch": 0.28, + "learning_rate": 1.681068746126094e-05, + "loss": 0.5073, + "step": 3327 + }, + { + "epoch": 0.28, + "learning_rate": 1.6808665106529096e-05, + "loss": 0.498, + "step": 3328 + }, + { + "epoch": 0.28, + "learning_rate": 1.680664223254003e-05, + "loss": 0.4939, + "step": 3329 + }, + { + "epoch": 0.28, + "learning_rate": 1.680461883944801e-05, + "loss": 0.4766, + "step": 3330 + }, + { + "epoch": 0.28, + "learning_rate": 1.6802594927407346e-05, + "loss": 0.4794, + "step": 3331 + }, + { + "epoch": 0.28, + "learning_rate": 1.6800570496572395e-05, + "loss": 0.4947, + "step": 3332 + }, + { + "epoch": 0.28, + "learning_rate": 1.6798545547097546e-05, + "loss": 0.5021, + "step": 3333 + }, + { + "epoch": 0.28, + "learning_rate": 1.679652007913723e-05, + "loss": 0.5078, + "step": 3334 + }, + { + "epoch": 0.28, + "learning_rate": 1.6794494092845917e-05, + "loss": 0.4695, + "step": 3335 + }, + { + "epoch": 0.28, + "learning_rate": 1.6792467588378123e-05, + "loss": 0.4843, + "step": 3336 + }, + { + "epoch": 0.28, + "learning_rate": 1.679044056588839e-05, + "loss": 0.4836, + "step": 3337 + }, + { + "epoch": 0.28, + "learning_rate": 1.678841302553131e-05, + "loss": 0.4927, + "step": 3338 + }, + { + "epoch": 0.28, + "learning_rate": 1.6786384967461512e-05, + "loss": 0.4809, + "step": 3339 + }, + { + "epoch": 0.28, + "learning_rate": 1.6784356391833665e-05, + "loss": 0.5013, + "step": 3340 + }, + { + "epoch": 0.28, + "learning_rate": 1.6782327298802474e-05, + "loss": 0.5062, + "step": 3341 + }, + { + "epoch": 0.28, + "learning_rate": 1.6780297688522692e-05, + "loss": 0.4932, + "step": 3342 + }, + { + "epoch": 0.29, + "learning_rate": 1.6778267561149097e-05, + "loss": 0.5068, + "step": 3343 + }, + { + "epoch": 0.29, + "learning_rate": 1.6776236916836518e-05, + "loss": 0.4785, + "step": 3344 + }, + { + "epoch": 0.29, + "learning_rate": 1.6774205755739824e-05, + "loss": 0.4994, + "step": 3345 + }, + { + "epoch": 0.29, + "learning_rate": 1.677217407801392e-05, + "loss": 0.5011, + "step": 3346 + }, + { + "epoch": 0.29, + "learning_rate": 1.6770141883813746e-05, + "loss": 0.5109, + "step": 3347 + }, + { + "epoch": 0.29, + "learning_rate": 1.676810917329429e-05, + "loss": 0.4878, + "step": 3348 + }, + { + "epoch": 0.29, + "learning_rate": 1.6766075946610568e-05, + "loss": 0.5155, + "step": 3349 + }, + { + "epoch": 0.29, + "learning_rate": 1.6764042203917648e-05, + "loss": 0.5219, + "step": 3350 + }, + { + "epoch": 0.29, + "learning_rate": 1.6762007945370632e-05, + "loss": 0.4882, + "step": 3351 + }, + { + "epoch": 0.29, + "learning_rate": 1.675997317112466e-05, + "loss": 0.5143, + "step": 3352 + }, + { + "epoch": 0.29, + "learning_rate": 1.675793788133491e-05, + "loss": 0.4863, + "step": 3353 + }, + { + "epoch": 0.29, + "learning_rate": 1.6755902076156606e-05, + "loss": 0.4855, + "step": 3354 + }, + { + "epoch": 0.29, + "learning_rate": 1.6753865755745e-05, + "loss": 0.4875, + "step": 3355 + }, + { + "epoch": 0.29, + "learning_rate": 1.6751828920255396e-05, + "loss": 0.4809, + "step": 3356 + }, + { + "epoch": 0.29, + "learning_rate": 1.6749791569843135e-05, + "loss": 0.4927, + "step": 3357 + }, + { + "epoch": 0.29, + "learning_rate": 1.6747753704663586e-05, + "loss": 0.4887, + "step": 3358 + }, + { + "epoch": 0.29, + "learning_rate": 1.674571532487217e-05, + "loss": 0.5156, + "step": 3359 + }, + { + "epoch": 0.29, + "learning_rate": 1.674367643062434e-05, + "loss": 0.4967, + "step": 3360 + }, + { + "epoch": 0.29, + "learning_rate": 1.6741637022075593e-05, + "loss": 0.4782, + "step": 3361 + }, + { + "epoch": 0.29, + "learning_rate": 1.6739597099381457e-05, + "loss": 0.4934, + "step": 3362 + }, + { + "epoch": 0.29, + "learning_rate": 1.6737556662697514e-05, + "loss": 0.4974, + "step": 3363 + }, + { + "epoch": 0.29, + "learning_rate": 1.673551571217937e-05, + "loss": 0.5045, + "step": 3364 + }, + { + "epoch": 0.29, + "learning_rate": 1.6733474247982675e-05, + "loss": 0.5027, + "step": 3365 + }, + { + "epoch": 0.29, + "learning_rate": 1.6731432270263126e-05, + "loss": 0.5273, + "step": 3366 + }, + { + "epoch": 0.29, + "learning_rate": 1.6729389779176446e-05, + "loss": 0.4873, + "step": 3367 + }, + { + "epoch": 0.29, + "learning_rate": 1.672734677487841e-05, + "loss": 0.4849, + "step": 3368 + }, + { + "epoch": 0.29, + "learning_rate": 1.672530325752482e-05, + "loss": 0.5023, + "step": 3369 + }, + { + "epoch": 0.29, + "learning_rate": 1.6723259227271527e-05, + "loss": 0.4888, + "step": 3370 + }, + { + "epoch": 0.29, + "learning_rate": 1.672121468427442e-05, + "loss": 0.4845, + "step": 3371 + }, + { + "epoch": 0.29, + "learning_rate": 1.671916962868942e-05, + "loss": 0.4954, + "step": 3372 + }, + { + "epoch": 0.29, + "learning_rate": 1.671712406067249e-05, + "loss": 0.5072, + "step": 3373 + }, + { + "epoch": 0.29, + "learning_rate": 1.6715077980379636e-05, + "loss": 0.4873, + "step": 3374 + }, + { + "epoch": 0.29, + "learning_rate": 1.6713031387966903e-05, + "loss": 0.4931, + "step": 3375 + }, + { + "epoch": 0.29, + "learning_rate": 1.671098428359037e-05, + "loss": 0.4837, + "step": 3376 + }, + { + "epoch": 0.29, + "learning_rate": 1.6708936667406157e-05, + "loss": 0.4901, + "step": 3377 + }, + { + "epoch": 0.29, + "learning_rate": 1.6706888539570424e-05, + "loss": 0.4878, + "step": 3378 + }, + { + "epoch": 0.29, + "learning_rate": 1.6704839900239372e-05, + "loss": 0.4936, + "step": 3379 + }, + { + "epoch": 0.29, + "learning_rate": 1.6702790749569238e-05, + "loss": 0.4809, + "step": 3380 + }, + { + "epoch": 0.29, + "learning_rate": 1.6700741087716296e-05, + "loss": 0.4792, + "step": 3381 + }, + { + "epoch": 0.29, + "learning_rate": 1.6698690914836863e-05, + "loss": 0.5043, + "step": 3382 + }, + { + "epoch": 0.29, + "learning_rate": 1.6696640231087296e-05, + "loss": 0.4839, + "step": 3383 + }, + { + "epoch": 0.29, + "learning_rate": 1.6694589036623988e-05, + "loss": 0.4919, + "step": 3384 + }, + { + "epoch": 0.29, + "learning_rate": 1.6692537331603374e-05, + "loss": 0.488, + "step": 3385 + }, + { + "epoch": 0.29, + "learning_rate": 1.6690485116181917e-05, + "loss": 0.4939, + "step": 3386 + }, + { + "epoch": 0.29, + "learning_rate": 1.6688432390516136e-05, + "loss": 0.4763, + "step": 3387 + }, + { + "epoch": 0.29, + "learning_rate": 1.6686379154762575e-05, + "loss": 0.5006, + "step": 3388 + }, + { + "epoch": 0.29, + "learning_rate": 1.668432540907783e-05, + "loss": 0.4848, + "step": 3389 + }, + { + "epoch": 0.29, + "learning_rate": 1.6682271153618517e-05, + "loss": 0.4755, + "step": 3390 + }, + { + "epoch": 0.29, + "learning_rate": 1.668021638854131e-05, + "loss": 0.5049, + "step": 3391 + }, + { + "epoch": 0.29, + "learning_rate": 1.6678161114002916e-05, + "loss": 0.5004, + "step": 3392 + }, + { + "epoch": 0.29, + "learning_rate": 1.667610533016007e-05, + "loss": 0.4785, + "step": 3393 + }, + { + "epoch": 0.29, + "learning_rate": 1.6674049037169565e-05, + "loss": 0.5055, + "step": 3394 + }, + { + "epoch": 0.29, + "learning_rate": 1.6671992235188212e-05, + "loss": 0.4771, + "step": 3395 + }, + { + "epoch": 0.29, + "learning_rate": 1.666993492437288e-05, + "loss": 0.4854, + "step": 3396 + }, + { + "epoch": 0.29, + "learning_rate": 1.666787710488046e-05, + "loss": 0.4852, + "step": 3397 + }, + { + "epoch": 0.29, + "learning_rate": 1.66658187768679e-05, + "loss": 0.5219, + "step": 3398 + }, + { + "epoch": 0.29, + "learning_rate": 1.6663759940492166e-05, + "loss": 0.494, + "step": 3399 + }, + { + "epoch": 0.29, + "learning_rate": 1.6661700595910284e-05, + "loss": 0.5, + "step": 3400 + }, + { + "epoch": 0.29, + "learning_rate": 1.66596407432793e-05, + "loss": 0.488, + "step": 3401 + }, + { + "epoch": 0.29, + "learning_rate": 1.6657580382756306e-05, + "loss": 0.4824, + "step": 3402 + }, + { + "epoch": 0.29, + "learning_rate": 1.6655519514498443e-05, + "loss": 0.4928, + "step": 3403 + }, + { + "epoch": 0.29, + "learning_rate": 1.6653458138662872e-05, + "loss": 0.4834, + "step": 3404 + }, + { + "epoch": 0.29, + "learning_rate": 1.665139625540681e-05, + "loss": 0.5008, + "step": 3405 + }, + { + "epoch": 0.29, + "learning_rate": 1.6649333864887497e-05, + "loss": 0.4711, + "step": 3406 + }, + { + "epoch": 0.29, + "learning_rate": 1.6647270967262227e-05, + "loss": 0.5186, + "step": 3407 + }, + { + "epoch": 0.29, + "learning_rate": 1.664520756268832e-05, + "loss": 0.4872, + "step": 3408 + }, + { + "epoch": 0.29, + "learning_rate": 1.664314365132314e-05, + "loss": 0.5094, + "step": 3409 + }, + { + "epoch": 0.29, + "learning_rate": 1.664107923332409e-05, + "loss": 0.4886, + "step": 3410 + }, + { + "epoch": 0.29, + "learning_rate": 1.6639014308848615e-05, + "loss": 0.5191, + "step": 3411 + }, + { + "epoch": 0.29, + "learning_rate": 1.6636948878054192e-05, + "loss": 0.5101, + "step": 3412 + }, + { + "epoch": 0.29, + "learning_rate": 1.6634882941098338e-05, + "loss": 0.4758, + "step": 3413 + }, + { + "epoch": 0.29, + "learning_rate": 1.663281649813861e-05, + "loss": 0.4911, + "step": 3414 + }, + { + "epoch": 0.29, + "learning_rate": 1.6630749549332607e-05, + "loss": 0.4835, + "step": 3415 + }, + { + "epoch": 0.29, + "learning_rate": 1.662868209483796e-05, + "loss": 0.525, + "step": 3416 + }, + { + "epoch": 0.29, + "learning_rate": 1.6626614134812337e-05, + "loss": 0.5099, + "step": 3417 + }, + { + "epoch": 0.29, + "learning_rate": 1.662454566941346e-05, + "loss": 0.496, + "step": 3418 + }, + { + "epoch": 0.29, + "learning_rate": 1.6622476698799074e-05, + "loss": 0.4779, + "step": 3419 + }, + { + "epoch": 0.29, + "learning_rate": 1.6620407223126967e-05, + "loss": 0.5078, + "step": 3420 + }, + { + "epoch": 0.29, + "learning_rate": 1.6618337242554963e-05, + "loss": 0.4936, + "step": 3421 + }, + { + "epoch": 0.29, + "learning_rate": 1.6616266757240932e-05, + "loss": 0.4719, + "step": 3422 + }, + { + "epoch": 0.29, + "learning_rate": 1.6614195767342777e-05, + "loss": 0.4843, + "step": 3423 + }, + { + "epoch": 0.29, + "learning_rate": 1.661212427301844e-05, + "loss": 0.5118, + "step": 3424 + }, + { + "epoch": 0.29, + "learning_rate": 1.6610052274425896e-05, + "loss": 0.4855, + "step": 3425 + }, + { + "epoch": 0.29, + "learning_rate": 1.6607979771723173e-05, + "loss": 0.4627, + "step": 3426 + }, + { + "epoch": 0.29, + "learning_rate": 1.6605906765068326e-05, + "loss": 0.493, + "step": 3427 + }, + { + "epoch": 0.29, + "learning_rate": 1.660383325461945e-05, + "loss": 0.5094, + "step": 3428 + }, + { + "epoch": 0.29, + "learning_rate": 1.660175924053468e-05, + "loss": 0.4907, + "step": 3429 + }, + { + "epoch": 0.29, + "learning_rate": 1.6599684722972188e-05, + "loss": 0.4962, + "step": 3430 + }, + { + "epoch": 0.29, + "learning_rate": 1.6597609702090184e-05, + "loss": 0.4804, + "step": 3431 + }, + { + "epoch": 0.29, + "learning_rate": 1.6595534178046925e-05, + "loss": 0.498, + "step": 3432 + }, + { + "epoch": 0.29, + "learning_rate": 1.659345815100069e-05, + "loss": 0.4844, + "step": 3433 + }, + { + "epoch": 0.29, + "learning_rate": 1.659138162110981e-05, + "loss": 0.5161, + "step": 3434 + }, + { + "epoch": 0.29, + "learning_rate": 1.6589304588532652e-05, + "loss": 0.4909, + "step": 3435 + }, + { + "epoch": 0.29, + "learning_rate": 1.6587227053427613e-05, + "loss": 0.4828, + "step": 3436 + }, + { + "epoch": 0.29, + "learning_rate": 1.658514901595314e-05, + "loss": 0.4675, + "step": 3437 + }, + { + "epoch": 0.29, + "learning_rate": 1.6583070476267712e-05, + "loss": 0.4981, + "step": 3438 + }, + { + "epoch": 0.29, + "learning_rate": 1.658099143452984e-05, + "loss": 0.4904, + "step": 3439 + }, + { + "epoch": 0.29, + "learning_rate": 1.6578911890898095e-05, + "loss": 0.4966, + "step": 3440 + }, + { + "epoch": 0.29, + "learning_rate": 1.6576831845531058e-05, + "loss": 0.5002, + "step": 3441 + }, + { + "epoch": 0.29, + "learning_rate": 1.657475129858737e-05, + "loss": 0.467, + "step": 3442 + }, + { + "epoch": 0.29, + "learning_rate": 1.6572670250225695e-05, + "loss": 0.4815, + "step": 3443 + }, + { + "epoch": 0.29, + "learning_rate": 1.657058870060475e-05, + "loss": 0.5161, + "step": 3444 + }, + { + "epoch": 0.29, + "learning_rate": 1.6568506649883276e-05, + "loss": 0.4943, + "step": 3445 + }, + { + "epoch": 0.29, + "learning_rate": 1.6566424098220064e-05, + "loss": 0.4995, + "step": 3446 + }, + { + "epoch": 0.29, + "learning_rate": 1.656434104577394e-05, + "loss": 0.5063, + "step": 3447 + }, + { + "epoch": 0.29, + "learning_rate": 1.6562257492703756e-05, + "loss": 0.502, + "step": 3448 + }, + { + "epoch": 0.29, + "learning_rate": 1.6560173439168427e-05, + "loss": 0.5214, + "step": 3449 + }, + { + "epoch": 0.29, + "learning_rate": 1.6558088885326874e-05, + "loss": 0.5168, + "step": 3450 + }, + { + "epoch": 0.29, + "learning_rate": 1.655600383133809e-05, + "loss": 0.4778, + "step": 3451 + }, + { + "epoch": 0.29, + "learning_rate": 1.655391827736108e-05, + "loss": 0.4999, + "step": 3452 + }, + { + "epoch": 0.29, + "learning_rate": 1.6551832223554902e-05, + "loss": 0.5022, + "step": 3453 + }, + { + "epoch": 0.29, + "learning_rate": 1.654974567007865e-05, + "loss": 0.4931, + "step": 3454 + }, + { + "epoch": 0.29, + "learning_rate": 1.654765861709144e-05, + "loss": 0.4912, + "step": 3455 + }, + { + "epoch": 0.29, + "learning_rate": 1.6545571064752454e-05, + "loss": 0.5144, + "step": 3456 + }, + { + "epoch": 0.29, + "learning_rate": 1.654348301322089e-05, + "loss": 0.4898, + "step": 3457 + }, + { + "epoch": 0.29, + "learning_rate": 1.6541394462655997e-05, + "loss": 0.4884, + "step": 3458 + }, + { + "epoch": 0.29, + "learning_rate": 1.6539305413217044e-05, + "loss": 0.5088, + "step": 3459 + }, + { + "epoch": 0.3, + "learning_rate": 1.6537215865063364e-05, + "loss": 0.4895, + "step": 3460 + }, + { + "epoch": 0.3, + "learning_rate": 1.653512581835431e-05, + "loss": 0.4874, + "step": 3461 + }, + { + "epoch": 0.3, + "learning_rate": 1.653303527324928e-05, + "loss": 0.5069, + "step": 3462 + }, + { + "epoch": 0.3, + "learning_rate": 1.6530944229907705e-05, + "loss": 0.4897, + "step": 3463 + }, + { + "epoch": 0.3, + "learning_rate": 1.6528852688489053e-05, + "loss": 0.4779, + "step": 3464 + }, + { + "epoch": 0.3, + "learning_rate": 1.6526760649152843e-05, + "loss": 0.5167, + "step": 3465 + }, + { + "epoch": 0.3, + "learning_rate": 1.6524668112058617e-05, + "loss": 0.4799, + "step": 3466 + }, + { + "epoch": 0.3, + "learning_rate": 1.6522575077365958e-05, + "loss": 0.4842, + "step": 3467 + }, + { + "epoch": 0.3, + "learning_rate": 1.6520481545234495e-05, + "loss": 0.4795, + "step": 3468 + }, + { + "epoch": 0.3, + "learning_rate": 1.6518387515823887e-05, + "loss": 0.4809, + "step": 3469 + }, + { + "epoch": 0.3, + "learning_rate": 1.6516292989293833e-05, + "loss": 0.4925, + "step": 3470 + }, + { + "epoch": 0.3, + "learning_rate": 1.651419796580407e-05, + "loss": 0.4964, + "step": 3471 + }, + { + "epoch": 0.3, + "learning_rate": 1.6512102445514376e-05, + "loss": 0.4887, + "step": 3472 + }, + { + "epoch": 0.3, + "learning_rate": 1.651000642858456e-05, + "loss": 0.5238, + "step": 3473 + }, + { + "epoch": 0.3, + "learning_rate": 1.6507909915174477e-05, + "loss": 0.4817, + "step": 3474 + }, + { + "epoch": 0.3, + "learning_rate": 1.6505812905444014e-05, + "loss": 0.5013, + "step": 3475 + }, + { + "epoch": 0.3, + "learning_rate": 1.65037153995531e-05, + "loss": 0.4895, + "step": 3476 + }, + { + "epoch": 0.3, + "learning_rate": 1.6501617397661692e-05, + "loss": 0.4759, + "step": 3477 + }, + { + "epoch": 0.3, + "learning_rate": 1.6499518899929802e-05, + "loss": 0.4935, + "step": 3478 + }, + { + "epoch": 0.3, + "learning_rate": 1.6497419906517463e-05, + "loss": 0.486, + "step": 3479 + }, + { + "epoch": 0.3, + "learning_rate": 1.649532041758476e-05, + "loss": 0.4996, + "step": 3480 + }, + { + "epoch": 0.3, + "learning_rate": 1.64932204332918e-05, + "loss": 0.4863, + "step": 3481 + }, + { + "epoch": 0.3, + "learning_rate": 1.6491119953798747e-05, + "loss": 0.4903, + "step": 3482 + }, + { + "epoch": 0.3, + "learning_rate": 1.648901897926578e-05, + "loss": 0.5104, + "step": 3483 + }, + { + "epoch": 0.3, + "learning_rate": 1.648691750985314e-05, + "loss": 0.4817, + "step": 3484 + }, + { + "epoch": 0.3, + "learning_rate": 1.6484815545721088e-05, + "loss": 0.5008, + "step": 3485 + }, + { + "epoch": 0.3, + "learning_rate": 1.6482713087029928e-05, + "loss": 0.4994, + "step": 3486 + }, + { + "epoch": 0.3, + "learning_rate": 1.6480610133940005e-05, + "loss": 0.4838, + "step": 3487 + }, + { + "epoch": 0.3, + "learning_rate": 1.6478506686611698e-05, + "loss": 0.5133, + "step": 3488 + }, + { + "epoch": 0.3, + "learning_rate": 1.647640274520542e-05, + "loss": 0.4942, + "step": 3489 + }, + { + "epoch": 0.3, + "learning_rate": 1.6474298309881634e-05, + "loss": 0.5, + "step": 3490 + }, + { + "epoch": 0.3, + "learning_rate": 1.6472193380800828e-05, + "loss": 0.4879, + "step": 3491 + }, + { + "epoch": 0.3, + "learning_rate": 1.6470087958123535e-05, + "loss": 0.4993, + "step": 3492 + }, + { + "epoch": 0.3, + "learning_rate": 1.6467982042010323e-05, + "loss": 0.4875, + "step": 3493 + }, + { + "epoch": 0.3, + "learning_rate": 1.6465875632621796e-05, + "loss": 0.5033, + "step": 3494 + }, + { + "epoch": 0.3, + "learning_rate": 1.6463768730118598e-05, + "loss": 0.5012, + "step": 3495 + }, + { + "epoch": 0.3, + "learning_rate": 1.6461661334661415e-05, + "loss": 0.5151, + "step": 3496 + }, + { + "epoch": 0.3, + "learning_rate": 1.645955344641096e-05, + "loss": 0.487, + "step": 3497 + }, + { + "epoch": 0.3, + "learning_rate": 1.645744506552799e-05, + "loss": 0.5148, + "step": 3498 + }, + { + "epoch": 0.3, + "learning_rate": 1.64553361921733e-05, + "loss": 0.4776, + "step": 3499 + }, + { + "epoch": 0.3, + "learning_rate": 1.645322682650772e-05, + "loss": 0.4748, + "step": 3500 + }, + { + "epoch": 0.3, + "learning_rate": 1.6451116968692126e-05, + "loss": 0.5111, + "step": 3501 + }, + { + "epoch": 0.3, + "learning_rate": 1.644900661888742e-05, + "loss": 0.5106, + "step": 3502 + }, + { + "epoch": 0.3, + "learning_rate": 1.6446895777254542e-05, + "loss": 0.4926, + "step": 3503 + }, + { + "epoch": 0.3, + "learning_rate": 1.644478444395448e-05, + "loss": 0.5044, + "step": 3504 + }, + { + "epoch": 0.3, + "learning_rate": 1.6442672619148248e-05, + "loss": 0.4849, + "step": 3505 + }, + { + "epoch": 0.3, + "learning_rate": 1.6440560302996903e-05, + "loss": 0.5036, + "step": 3506 + }, + { + "epoch": 0.3, + "learning_rate": 1.6438447495661543e-05, + "loss": 0.4753, + "step": 3507 + }, + { + "epoch": 0.3, + "learning_rate": 1.6436334197303298e-05, + "loss": 0.4831, + "step": 3508 + }, + { + "epoch": 0.3, + "learning_rate": 1.6434220408083334e-05, + "loss": 0.5021, + "step": 3509 + }, + { + "epoch": 0.3, + "learning_rate": 1.6432106128162862e-05, + "loss": 0.4994, + "step": 3510 + }, + { + "epoch": 0.3, + "learning_rate": 1.642999135770312e-05, + "loss": 0.5114, + "step": 3511 + }, + { + "epoch": 0.3, + "learning_rate": 1.6427876096865394e-05, + "loss": 0.4894, + "step": 3512 + }, + { + "epoch": 0.3, + "learning_rate": 1.6425760345811004e-05, + "loss": 0.4998, + "step": 3513 + }, + { + "epoch": 0.3, + "learning_rate": 1.64236441047013e-05, + "loss": 0.4815, + "step": 3514 + }, + { + "epoch": 0.3, + "learning_rate": 1.642152737369768e-05, + "loss": 0.5114, + "step": 3515 + }, + { + "epoch": 0.3, + "learning_rate": 1.641941015296157e-05, + "loss": 0.4862, + "step": 3516 + }, + { + "epoch": 0.3, + "learning_rate": 1.6417292442654445e-05, + "loss": 0.4961, + "step": 3517 + }, + { + "epoch": 0.3, + "learning_rate": 1.641517424293781e-05, + "loss": 0.4744, + "step": 3518 + }, + { + "epoch": 0.3, + "learning_rate": 1.6413055553973202e-05, + "loss": 0.5083, + "step": 3519 + }, + { + "epoch": 0.3, + "learning_rate": 1.64109363759222e-05, + "loss": 0.4926, + "step": 3520 + }, + { + "epoch": 0.3, + "learning_rate": 1.6408816708946433e-05, + "loss": 0.4868, + "step": 3521 + }, + { + "epoch": 0.3, + "learning_rate": 1.640669655320754e-05, + "loss": 0.4966, + "step": 3522 + }, + { + "epoch": 0.3, + "learning_rate": 1.6404575908867224e-05, + "loss": 0.4748, + "step": 3523 + }, + { + "epoch": 0.3, + "learning_rate": 1.6402454776087214e-05, + "loss": 0.4964, + "step": 3524 + }, + { + "epoch": 0.3, + "learning_rate": 1.640033315502927e-05, + "loss": 0.4972, + "step": 3525 + }, + { + "epoch": 0.3, + "learning_rate": 1.6398211045855198e-05, + "loss": 0.4782, + "step": 3526 + }, + { + "epoch": 0.3, + "learning_rate": 1.6396088448726838e-05, + "loss": 0.4996, + "step": 3527 + }, + { + "epoch": 0.3, + "learning_rate": 1.6393965363806075e-05, + "loss": 0.4814, + "step": 3528 + }, + { + "epoch": 0.3, + "learning_rate": 1.6391841791254818e-05, + "loss": 0.4905, + "step": 3529 + }, + { + "epoch": 0.3, + "learning_rate": 1.638971773123502e-05, + "loss": 0.4779, + "step": 3530 + }, + { + "epoch": 0.3, + "learning_rate": 1.638759318390867e-05, + "loss": 0.4976, + "step": 3531 + }, + { + "epoch": 0.3, + "learning_rate": 1.63854681494378e-05, + "loss": 0.4943, + "step": 3532 + }, + { + "epoch": 0.3, + "learning_rate": 1.638334262798447e-05, + "loss": 0.4963, + "step": 3533 + }, + { + "epoch": 0.3, + "learning_rate": 1.638121661971078e-05, + "loss": 0.4844, + "step": 3534 + }, + { + "epoch": 0.3, + "learning_rate": 1.6379090124778866e-05, + "loss": 0.4864, + "step": 3535 + }, + { + "epoch": 0.3, + "learning_rate": 1.6376963143350915e-05, + "loss": 0.513, + "step": 3536 + }, + { + "epoch": 0.3, + "learning_rate": 1.6374835675589125e-05, + "loss": 0.4849, + "step": 3537 + }, + { + "epoch": 0.3, + "learning_rate": 1.6372707721655756e-05, + "loss": 0.4988, + "step": 3538 + }, + { + "epoch": 0.3, + "learning_rate": 1.6370579281713087e-05, + "loss": 0.4798, + "step": 3539 + }, + { + "epoch": 0.3, + "learning_rate": 1.6368450355923452e-05, + "loss": 0.5126, + "step": 3540 + }, + { + "epoch": 0.3, + "learning_rate": 1.63663209444492e-05, + "loss": 0.4893, + "step": 3541 + }, + { + "epoch": 0.3, + "learning_rate": 1.6364191047452734e-05, + "loss": 0.4933, + "step": 3542 + }, + { + "epoch": 0.3, + "learning_rate": 1.6362060665096495e-05, + "loss": 0.5033, + "step": 3543 + }, + { + "epoch": 0.3, + "learning_rate": 1.6359929797542945e-05, + "loss": 0.5084, + "step": 3544 + }, + { + "epoch": 0.3, + "learning_rate": 1.6357798444954595e-05, + "loss": 0.4998, + "step": 3545 + }, + { + "epoch": 0.3, + "learning_rate": 1.6355666607493995e-05, + "loss": 0.4772, + "step": 3546 + }, + { + "epoch": 0.3, + "learning_rate": 1.6353534285323724e-05, + "loss": 0.5003, + "step": 3547 + }, + { + "epoch": 0.3, + "learning_rate": 1.6351401478606406e-05, + "loss": 0.525, + "step": 3548 + }, + { + "epoch": 0.3, + "learning_rate": 1.634926818750469e-05, + "loss": 0.4865, + "step": 3549 + }, + { + "epoch": 0.3, + "learning_rate": 1.634713441218128e-05, + "loss": 0.522, + "step": 3550 + }, + { + "epoch": 0.3, + "learning_rate": 1.6345000152798896e-05, + "loss": 0.4815, + "step": 3551 + }, + { + "epoch": 0.3, + "learning_rate": 1.6342865409520318e-05, + "loss": 0.4746, + "step": 3552 + }, + { + "epoch": 0.3, + "learning_rate": 1.6340730182508332e-05, + "loss": 0.478, + "step": 3553 + }, + { + "epoch": 0.3, + "learning_rate": 1.6338594471925802e-05, + "loss": 0.4948, + "step": 3554 + }, + { + "epoch": 0.3, + "learning_rate": 1.6336458277935586e-05, + "loss": 0.4901, + "step": 3555 + }, + { + "epoch": 0.3, + "learning_rate": 1.6334321600700612e-05, + "loss": 0.5125, + "step": 3556 + }, + { + "epoch": 0.3, + "learning_rate": 1.633218444038383e-05, + "loss": 0.5111, + "step": 3557 + }, + { + "epoch": 0.3, + "learning_rate": 1.6330046797148226e-05, + "loss": 0.4802, + "step": 3558 + }, + { + "epoch": 0.3, + "learning_rate": 1.632790867115682e-05, + "loss": 0.4846, + "step": 3559 + }, + { + "epoch": 0.3, + "learning_rate": 1.6325770062572685e-05, + "loss": 0.4837, + "step": 3560 + }, + { + "epoch": 0.3, + "learning_rate": 1.6323630971558916e-05, + "loss": 0.4755, + "step": 3561 + }, + { + "epoch": 0.3, + "learning_rate": 1.6321491398278647e-05, + "loss": 0.4795, + "step": 3562 + }, + { + "epoch": 0.3, + "learning_rate": 1.6319351342895052e-05, + "loss": 0.5012, + "step": 3563 + }, + { + "epoch": 0.3, + "learning_rate": 1.6317210805571346e-05, + "loss": 0.4958, + "step": 3564 + }, + { + "epoch": 0.3, + "learning_rate": 1.6315069786470767e-05, + "loss": 0.4693, + "step": 3565 + }, + { + "epoch": 0.3, + "learning_rate": 1.6312928285756598e-05, + "loss": 0.49, + "step": 3566 + }, + { + "epoch": 0.3, + "learning_rate": 1.631078630359217e-05, + "loss": 0.4796, + "step": 3567 + }, + { + "epoch": 0.3, + "learning_rate": 1.630864384014083e-05, + "loss": 0.482, + "step": 3568 + }, + { + "epoch": 0.3, + "learning_rate": 1.6306500895565967e-05, + "loss": 0.4931, + "step": 3569 + }, + { + "epoch": 0.3, + "learning_rate": 1.6304357470031022e-05, + "loss": 0.4933, + "step": 3570 + }, + { + "epoch": 0.3, + "learning_rate": 1.630221356369945e-05, + "loss": 0.508, + "step": 3571 + }, + { + "epoch": 0.3, + "learning_rate": 1.6300069176734768e-05, + "loss": 0.4672, + "step": 3572 + }, + { + "epoch": 0.3, + "learning_rate": 1.6297924309300506e-05, + "loss": 0.491, + "step": 3573 + }, + { + "epoch": 0.3, + "learning_rate": 1.6295778961560242e-05, + "loss": 0.4824, + "step": 3574 + }, + { + "epoch": 0.3, + "learning_rate": 1.629363313367759e-05, + "loss": 0.4777, + "step": 3575 + }, + { + "epoch": 0.3, + "learning_rate": 1.6291486825816205e-05, + "loss": 0.4988, + "step": 3576 + }, + { + "epoch": 0.3, + "learning_rate": 1.6289340038139765e-05, + "loss": 0.4955, + "step": 3577 + }, + { + "epoch": 0.31, + "learning_rate": 1.6287192770811993e-05, + "loss": 0.4794, + "step": 3578 + }, + { + "epoch": 0.31, + "learning_rate": 1.6285045023996657e-05, + "loss": 0.5035, + "step": 3579 + }, + { + "epoch": 0.31, + "learning_rate": 1.6282896797857547e-05, + "loss": 0.4896, + "step": 3580 + }, + { + "epoch": 0.31, + "learning_rate": 1.6280748092558498e-05, + "loss": 0.4828, + "step": 3581 + }, + { + "epoch": 0.31, + "learning_rate": 1.6278598908263378e-05, + "loss": 0.5032, + "step": 3582 + }, + { + "epoch": 0.31, + "learning_rate": 1.627644924513609e-05, + "loss": 0.5017, + "step": 3583 + }, + { + "epoch": 0.31, + "learning_rate": 1.627429910334058e-05, + "loss": 0.4765, + "step": 3584 + }, + { + "epoch": 0.31, + "learning_rate": 1.6272148483040827e-05, + "loss": 0.5028, + "step": 3585 + }, + { + "epoch": 0.31, + "learning_rate": 1.6269997384400845e-05, + "loss": 0.4998, + "step": 3586 + }, + { + "epoch": 0.31, + "learning_rate": 1.626784580758469e-05, + "loss": 0.4968, + "step": 3587 + }, + { + "epoch": 0.31, + "learning_rate": 1.626569375275644e-05, + "loss": 0.4755, + "step": 3588 + }, + { + "epoch": 0.31, + "learning_rate": 1.6263541220080227e-05, + "loss": 0.4764, + "step": 3589 + }, + { + "epoch": 0.31, + "learning_rate": 1.626138820972021e-05, + "loss": 0.5065, + "step": 3590 + }, + { + "epoch": 0.31, + "learning_rate": 1.6259234721840595e-05, + "loss": 0.495, + "step": 3591 + }, + { + "epoch": 0.31, + "learning_rate": 1.62570807566056e-05, + "loss": 0.491, + "step": 3592 + }, + { + "epoch": 0.31, + "learning_rate": 1.625492631417951e-05, + "loss": 0.4948, + "step": 3593 + }, + { + "epoch": 0.31, + "learning_rate": 1.6252771394726622e-05, + "loss": 0.4784, + "step": 3594 + }, + { + "epoch": 0.31, + "learning_rate": 1.6250615998411285e-05, + "loss": 0.5088, + "step": 3595 + }, + { + "epoch": 0.31, + "learning_rate": 1.6248460125397874e-05, + "loss": 0.5011, + "step": 3596 + }, + { + "epoch": 0.31, + "learning_rate": 1.6246303775850808e-05, + "loss": 0.4822, + "step": 3597 + }, + { + "epoch": 0.31, + "learning_rate": 1.624414694993454e-05, + "loss": 0.5093, + "step": 3598 + }, + { + "epoch": 0.31, + "learning_rate": 1.6241989647813557e-05, + "loss": 0.483, + "step": 3599 + }, + { + "epoch": 0.31, + "learning_rate": 1.6239831869652384e-05, + "loss": 0.49, + "step": 3600 + }, + { + "epoch": 0.31, + "learning_rate": 1.6237673615615582e-05, + "loss": 0.4917, + "step": 3601 + }, + { + "epoch": 0.31, + "learning_rate": 1.6235514885867747e-05, + "loss": 0.4939, + "step": 3602 + }, + { + "epoch": 0.31, + "learning_rate": 1.6233355680573514e-05, + "loss": 0.4759, + "step": 3603 + }, + { + "epoch": 0.31, + "learning_rate": 1.6231195999897557e-05, + "loss": 0.478, + "step": 3604 + }, + { + "epoch": 0.31, + "learning_rate": 1.6229035844004573e-05, + "loss": 0.4925, + "step": 3605 + }, + { + "epoch": 0.31, + "learning_rate": 1.6226875213059314e-05, + "loss": 0.4857, + "step": 3606 + }, + { + "epoch": 0.31, + "learning_rate": 1.6224714107226557e-05, + "loss": 0.4895, + "step": 3607 + }, + { + "epoch": 0.31, + "learning_rate": 1.622255252667111e-05, + "loss": 0.4946, + "step": 3608 + }, + { + "epoch": 0.31, + "learning_rate": 1.6220390471557832e-05, + "loss": 0.4793, + "step": 3609 + }, + { + "epoch": 0.31, + "learning_rate": 1.6218227942051606e-05, + "loss": 0.4879, + "step": 3610 + }, + { + "epoch": 0.31, + "learning_rate": 1.6216064938317356e-05, + "loss": 0.4878, + "step": 3611 + }, + { + "epoch": 0.31, + "learning_rate": 1.6213901460520047e-05, + "loss": 0.4851, + "step": 3612 + }, + { + "epoch": 0.31, + "learning_rate": 1.6211737508824662e-05, + "loss": 0.5002, + "step": 3613 + }, + { + "epoch": 0.31, + "learning_rate": 1.620957308339625e-05, + "loss": 0.4949, + "step": 3614 + }, + { + "epoch": 0.31, + "learning_rate": 1.6207408184399864e-05, + "loss": 0.5118, + "step": 3615 + }, + { + "epoch": 0.31, + "learning_rate": 1.620524281200062e-05, + "loss": 0.4867, + "step": 3616 + }, + { + "epoch": 0.31, + "learning_rate": 1.620307696636365e-05, + "loss": 0.4668, + "step": 3617 + }, + { + "epoch": 0.31, + "learning_rate": 1.6200910647654134e-05, + "loss": 0.5009, + "step": 3618 + }, + { + "epoch": 0.31, + "learning_rate": 1.6198743856037286e-05, + "loss": 0.5067, + "step": 3619 + }, + { + "epoch": 0.31, + "learning_rate": 1.619657659167835e-05, + "loss": 0.4799, + "step": 3620 + }, + { + "epoch": 0.31, + "learning_rate": 1.619440885474261e-05, + "loss": 0.4986, + "step": 3621 + }, + { + "epoch": 0.31, + "learning_rate": 1.6192240645395396e-05, + "loss": 0.496, + "step": 3622 + }, + { + "epoch": 0.31, + "learning_rate": 1.6190071963802053e-05, + "loss": 0.4957, + "step": 3623 + }, + { + "epoch": 0.31, + "learning_rate": 1.6187902810127983e-05, + "loss": 0.4783, + "step": 3624 + }, + { + "epoch": 0.31, + "learning_rate": 1.6185733184538613e-05, + "loss": 0.4985, + "step": 3625 + }, + { + "epoch": 0.31, + "learning_rate": 1.6183563087199403e-05, + "loss": 0.4847, + "step": 3626 + }, + { + "epoch": 0.31, + "learning_rate": 1.6181392518275854e-05, + "loss": 0.4997, + "step": 3627 + }, + { + "epoch": 0.31, + "learning_rate": 1.617922147793351e-05, + "loss": 0.4932, + "step": 3628 + }, + { + "epoch": 0.31, + "learning_rate": 1.6177049966337933e-05, + "loss": 0.4862, + "step": 3629 + }, + { + "epoch": 0.31, + "learning_rate": 1.617487798365474e-05, + "loss": 0.4888, + "step": 3630 + }, + { + "epoch": 0.31, + "learning_rate": 1.6172705530049575e-05, + "loss": 0.5034, + "step": 3631 + }, + { + "epoch": 0.31, + "learning_rate": 1.6170532605688115e-05, + "loss": 0.4998, + "step": 3632 + }, + { + "epoch": 0.31, + "learning_rate": 1.6168359210736072e-05, + "loss": 0.49, + "step": 3633 + }, + { + "epoch": 0.31, + "learning_rate": 1.616618534535921e-05, + "loss": 0.4929, + "step": 3634 + }, + { + "epoch": 0.31, + "learning_rate": 1.6164011009723308e-05, + "loss": 0.5037, + "step": 3635 + }, + { + "epoch": 0.31, + "learning_rate": 1.616183620399419e-05, + "loss": 0.5016, + "step": 3636 + }, + { + "epoch": 0.31, + "learning_rate": 1.6159660928337723e-05, + "loss": 0.4892, + "step": 3637 + }, + { + "epoch": 0.31, + "learning_rate": 1.6157485182919795e-05, + "loss": 0.5075, + "step": 3638 + }, + { + "epoch": 0.31, + "learning_rate": 1.6155308967906344e-05, + "loss": 0.5042, + "step": 3639 + }, + { + "epoch": 0.31, + "learning_rate": 1.6153132283463327e-05, + "loss": 0.4821, + "step": 3640 + }, + { + "epoch": 0.31, + "learning_rate": 1.615095512975676e-05, + "loss": 0.4871, + "step": 3641 + }, + { + "epoch": 0.31, + "learning_rate": 1.6148777506952672e-05, + "loss": 0.4873, + "step": 3642 + }, + { + "epoch": 0.31, + "learning_rate": 1.614659941521714e-05, + "loss": 0.4749, + "step": 3643 + }, + { + "epoch": 0.31, + "learning_rate": 1.6144420854716277e-05, + "loss": 0.5205, + "step": 3644 + }, + { + "epoch": 0.31, + "learning_rate": 1.6142241825616226e-05, + "loss": 0.5013, + "step": 3645 + }, + { + "epoch": 0.31, + "learning_rate": 1.614006232808317e-05, + "loss": 0.4808, + "step": 3646 + }, + { + "epoch": 0.31, + "learning_rate": 1.6137882362283328e-05, + "loss": 0.4791, + "step": 3647 + }, + { + "epoch": 0.31, + "learning_rate": 1.6135701928382952e-05, + "loss": 0.5009, + "step": 3648 + }, + { + "epoch": 0.31, + "learning_rate": 1.613352102654833e-05, + "loss": 0.499, + "step": 3649 + }, + { + "epoch": 0.31, + "learning_rate": 1.613133965694579e-05, + "loss": 0.5008, + "step": 3650 + }, + { + "epoch": 0.31, + "learning_rate": 1.6129157819741692e-05, + "loss": 0.4856, + "step": 3651 + }, + { + "epoch": 0.31, + "learning_rate": 1.6126975515102424e-05, + "loss": 0.4889, + "step": 3652 + }, + { + "epoch": 0.31, + "learning_rate": 1.612479274319443e-05, + "loss": 0.4982, + "step": 3653 + }, + { + "epoch": 0.31, + "learning_rate": 1.6122609504184166e-05, + "loss": 0.4844, + "step": 3654 + }, + { + "epoch": 0.31, + "learning_rate": 1.6120425798238145e-05, + "loss": 0.5086, + "step": 3655 + }, + { + "epoch": 0.31, + "learning_rate": 1.6118241625522898e-05, + "loss": 0.4755, + "step": 3656 + }, + { + "epoch": 0.31, + "learning_rate": 1.6116056986205003e-05, + "loss": 0.5097, + "step": 3657 + }, + { + "epoch": 0.31, + "learning_rate": 1.6113871880451062e-05, + "loss": 0.4937, + "step": 3658 + }, + { + "epoch": 0.31, + "learning_rate": 1.6111686308427734e-05, + "loss": 0.4724, + "step": 3659 + }, + { + "epoch": 0.31, + "learning_rate": 1.6109500270301694e-05, + "loss": 0.4936, + "step": 3660 + }, + { + "epoch": 0.31, + "learning_rate": 1.610731376623965e-05, + "loss": 0.4695, + "step": 3661 + }, + { + "epoch": 0.31, + "learning_rate": 1.6105126796408367e-05, + "loss": 0.486, + "step": 3662 + }, + { + "epoch": 0.31, + "learning_rate": 1.610293936097462e-05, + "loss": 0.4706, + "step": 3663 + }, + { + "epoch": 0.31, + "learning_rate": 1.6100751460105244e-05, + "loss": 0.5029, + "step": 3664 + }, + { + "epoch": 0.31, + "learning_rate": 1.609856309396709e-05, + "loss": 0.5005, + "step": 3665 + }, + { + "epoch": 0.31, + "learning_rate": 1.6096374262727055e-05, + "loss": 0.5134, + "step": 3666 + }, + { + "epoch": 0.31, + "learning_rate": 1.6094184966552066e-05, + "loss": 0.4935, + "step": 3667 + }, + { + "epoch": 0.31, + "learning_rate": 1.609199520560909e-05, + "loss": 0.5092, + "step": 3668 + }, + { + "epoch": 0.31, + "learning_rate": 1.6089804980065124e-05, + "loss": 0.4606, + "step": 3669 + }, + { + "epoch": 0.31, + "learning_rate": 1.608761429008721e-05, + "loss": 0.4868, + "step": 3670 + }, + { + "epoch": 0.31, + "learning_rate": 1.608542313584241e-05, + "loss": 0.507, + "step": 3671 + }, + { + "epoch": 0.31, + "learning_rate": 1.608323151749784e-05, + "loss": 0.4625, + "step": 3672 + }, + { + "epoch": 0.31, + "learning_rate": 1.6081039435220637e-05, + "loss": 0.4879, + "step": 3673 + }, + { + "epoch": 0.31, + "learning_rate": 1.6078846889177978e-05, + "loss": 0.4934, + "step": 3674 + }, + { + "epoch": 0.31, + "learning_rate": 1.6076653879537074e-05, + "loss": 0.4729, + "step": 3675 + }, + { + "epoch": 0.31, + "learning_rate": 1.607446040646518e-05, + "loss": 0.4885, + "step": 3676 + }, + { + "epoch": 0.31, + "learning_rate": 1.6072266470129573e-05, + "loss": 0.4832, + "step": 3677 + }, + { + "epoch": 0.31, + "learning_rate": 1.607007207069758e-05, + "loss": 0.4898, + "step": 3678 + }, + { + "epoch": 0.31, + "learning_rate": 1.606787720833654e-05, + "loss": 0.4948, + "step": 3679 + }, + { + "epoch": 0.31, + "learning_rate": 1.6065681883213854e-05, + "loss": 0.5241, + "step": 3680 + }, + { + "epoch": 0.31, + "learning_rate": 1.606348609549695e-05, + "loss": 0.4878, + "step": 3681 + }, + { + "epoch": 0.31, + "learning_rate": 1.6061289845353276e-05, + "loss": 0.5015, + "step": 3682 + }, + { + "epoch": 0.31, + "learning_rate": 1.6059093132950336e-05, + "loss": 0.4908, + "step": 3683 + }, + { + "epoch": 0.31, + "learning_rate": 1.6056895958455657e-05, + "loss": 0.4874, + "step": 3684 + }, + { + "epoch": 0.31, + "learning_rate": 1.6054698322036806e-05, + "loss": 0.4719, + "step": 3685 + }, + { + "epoch": 0.31, + "learning_rate": 1.605250022386138e-05, + "loss": 0.496, + "step": 3686 + }, + { + "epoch": 0.31, + "learning_rate": 1.6050301664097023e-05, + "loss": 0.4999, + "step": 3687 + }, + { + "epoch": 0.31, + "learning_rate": 1.60481026429114e-05, + "loss": 0.5015, + "step": 3688 + }, + { + "epoch": 0.31, + "learning_rate": 1.6045903160472218e-05, + "loss": 0.5052, + "step": 3689 + }, + { + "epoch": 0.31, + "learning_rate": 1.6043703216947223e-05, + "loss": 0.4962, + "step": 3690 + }, + { + "epoch": 0.31, + "learning_rate": 1.6041502812504185e-05, + "loss": 0.457, + "step": 3691 + }, + { + "epoch": 0.31, + "learning_rate": 1.6039301947310925e-05, + "loss": 0.5011, + "step": 3692 + }, + { + "epoch": 0.31, + "learning_rate": 1.6037100621535283e-05, + "loss": 0.5002, + "step": 3693 + }, + { + "epoch": 0.31, + "learning_rate": 1.6034898835345142e-05, + "loss": 0.4836, + "step": 3694 + }, + { + "epoch": 0.32, + "learning_rate": 1.603269658890842e-05, + "loss": 0.476, + "step": 3695 + }, + { + "epoch": 0.32, + "learning_rate": 1.6030493882393076e-05, + "loss": 0.4848, + "step": 3696 + }, + { + "epoch": 0.32, + "learning_rate": 1.6028290715967087e-05, + "loss": 0.4908, + "step": 3697 + }, + { + "epoch": 0.32, + "learning_rate": 1.6026087089798483e-05, + "loss": 0.4754, + "step": 3698 + }, + { + "epoch": 0.32, + "learning_rate": 1.6023883004055317e-05, + "loss": 0.488, + "step": 3699 + }, + { + "epoch": 0.32, + "learning_rate": 1.6021678458905686e-05, + "loss": 0.46, + "step": 3700 + }, + { + "epoch": 0.32, + "learning_rate": 1.6019473454517714e-05, + "loss": 0.4774, + "step": 3701 + }, + { + "epoch": 0.32, + "learning_rate": 1.601726799105957e-05, + "loss": 0.4765, + "step": 3702 + }, + { + "epoch": 0.32, + "learning_rate": 1.6015062068699445e-05, + "loss": 0.503, + "step": 3703 + }, + { + "epoch": 0.32, + "learning_rate": 1.6012855687605572e-05, + "loss": 0.4927, + "step": 3704 + }, + { + "epoch": 0.32, + "learning_rate": 1.6010648847946225e-05, + "loss": 0.484, + "step": 3705 + }, + { + "epoch": 0.32, + "learning_rate": 1.6008441549889703e-05, + "loss": 0.5042, + "step": 3706 + }, + { + "epoch": 0.32, + "learning_rate": 1.600623379360434e-05, + "loss": 0.4921, + "step": 3707 + }, + { + "epoch": 0.32, + "learning_rate": 1.6004025579258517e-05, + "loss": 0.477, + "step": 3708 + }, + { + "epoch": 0.32, + "learning_rate": 1.6001816907020634e-05, + "loss": 0.4729, + "step": 3709 + }, + { + "epoch": 0.32, + "learning_rate": 1.599960777705914e-05, + "loss": 0.4977, + "step": 3710 + }, + { + "epoch": 0.32, + "learning_rate": 1.599739818954251e-05, + "loss": 0.4643, + "step": 3711 + }, + { + "epoch": 0.32, + "learning_rate": 1.599518814463925e-05, + "loss": 0.5209, + "step": 3712 + }, + { + "epoch": 0.32, + "learning_rate": 1.599297764251792e-05, + "loss": 0.494, + "step": 3713 + }, + { + "epoch": 0.32, + "learning_rate": 1.599076668334709e-05, + "loss": 0.4945, + "step": 3714 + }, + { + "epoch": 0.32, + "learning_rate": 1.5988555267295383e-05, + "loss": 0.4985, + "step": 3715 + }, + { + "epoch": 0.32, + "learning_rate": 1.598634339453145e-05, + "loss": 0.4985, + "step": 3716 + }, + { + "epoch": 0.32, + "learning_rate": 1.598413106522398e-05, + "loss": 0.4818, + "step": 3717 + }, + { + "epoch": 0.32, + "learning_rate": 1.598191827954169e-05, + "loss": 0.4968, + "step": 3718 + }, + { + "epoch": 0.32, + "learning_rate": 1.5979705037653338e-05, + "loss": 0.4894, + "step": 3719 + }, + { + "epoch": 0.32, + "learning_rate": 1.5977491339727716e-05, + "loss": 0.489, + "step": 3720 + }, + { + "epoch": 0.32, + "learning_rate": 1.597527718593365e-05, + "loss": 0.4743, + "step": 3721 + }, + { + "epoch": 0.32, + "learning_rate": 1.5973062576439996e-05, + "loss": 0.4853, + "step": 3722 + }, + { + "epoch": 0.32, + "learning_rate": 1.5970847511415656e-05, + "loss": 0.4798, + "step": 3723 + }, + { + "epoch": 0.32, + "learning_rate": 1.5968631991029554e-05, + "loss": 0.4723, + "step": 3724 + }, + { + "epoch": 0.32, + "learning_rate": 1.5966416015450664e-05, + "loss": 0.4883, + "step": 3725 + }, + { + "epoch": 0.32, + "learning_rate": 1.5964199584847975e-05, + "loss": 0.5237, + "step": 3726 + }, + { + "epoch": 0.32, + "learning_rate": 1.596198269939053e-05, + "loss": 0.4902, + "step": 3727 + }, + { + "epoch": 0.32, + "learning_rate": 1.595976535924739e-05, + "loss": 0.4902, + "step": 3728 + }, + { + "epoch": 0.32, + "learning_rate": 1.5957547564587662e-05, + "loss": 0.4797, + "step": 3729 + }, + { + "epoch": 0.32, + "learning_rate": 1.5955329315580487e-05, + "loss": 0.4649, + "step": 3730 + }, + { + "epoch": 0.32, + "learning_rate": 1.5953110612395035e-05, + "loss": 0.4917, + "step": 3731 + }, + { + "epoch": 0.32, + "learning_rate": 1.5950891455200516e-05, + "loss": 0.4746, + "step": 3732 + }, + { + "epoch": 0.32, + "learning_rate": 1.5948671844166167e-05, + "loss": 0.5044, + "step": 3733 + }, + { + "epoch": 0.32, + "learning_rate": 1.594645177946127e-05, + "loss": 0.4792, + "step": 3734 + }, + { + "epoch": 0.32, + "learning_rate": 1.5944231261255133e-05, + "loss": 0.465, + "step": 3735 + }, + { + "epoch": 0.32, + "learning_rate": 1.5942010289717108e-05, + "loss": 0.4843, + "step": 3736 + }, + { + "epoch": 0.32, + "learning_rate": 1.5939788865016565e-05, + "loss": 0.4572, + "step": 3737 + }, + { + "epoch": 0.32, + "learning_rate": 1.593756698732293e-05, + "loss": 0.4975, + "step": 3738 + }, + { + "epoch": 0.32, + "learning_rate": 1.5935344656805648e-05, + "loss": 0.5064, + "step": 3739 + }, + { + "epoch": 0.32, + "learning_rate": 1.5933121873634202e-05, + "loss": 0.5028, + "step": 3740 + }, + { + "epoch": 0.32, + "learning_rate": 1.593089863797811e-05, + "loss": 0.4851, + "step": 3741 + }, + { + "epoch": 0.32, + "learning_rate": 1.5928674950006927e-05, + "loss": 0.4951, + "step": 3742 + }, + { + "epoch": 0.32, + "learning_rate": 1.5926450809890245e-05, + "loss": 0.4764, + "step": 3743 + }, + { + "epoch": 0.32, + "learning_rate": 1.5924226217797677e-05, + "loss": 0.4835, + "step": 3744 + }, + { + "epoch": 0.32, + "learning_rate": 1.592200117389889e-05, + "loss": 0.4897, + "step": 3745 + }, + { + "epoch": 0.32, + "learning_rate": 1.5919775678363566e-05, + "loss": 0.4965, + "step": 3746 + }, + { + "epoch": 0.32, + "learning_rate": 1.5917549731361435e-05, + "loss": 0.4869, + "step": 3747 + }, + { + "epoch": 0.32, + "learning_rate": 1.5915323333062255e-05, + "loss": 0.4887, + "step": 3748 + }, + { + "epoch": 0.32, + "learning_rate": 1.5913096483635827e-05, + "loss": 0.4933, + "step": 3749 + }, + { + "epoch": 0.32, + "learning_rate": 1.591086918325197e-05, + "loss": 0.4755, + "step": 3750 + }, + { + "epoch": 0.32, + "learning_rate": 1.590864143208055e-05, + "loss": 0.4755, + "step": 3751 + }, + { + "epoch": 0.32, + "learning_rate": 1.5906413230291473e-05, + "loss": 0.4885, + "step": 3752 + }, + { + "epoch": 0.32, + "learning_rate": 1.5904184578054662e-05, + "loss": 0.4608, + "step": 3753 + }, + { + "epoch": 0.32, + "learning_rate": 1.5901955475540087e-05, + "loss": 0.5046, + "step": 3754 + }, + { + "epoch": 0.32, + "learning_rate": 1.5899725922917743e-05, + "loss": 0.4864, + "step": 3755 + }, + { + "epoch": 0.32, + "learning_rate": 1.5897495920357673e-05, + "loss": 0.483, + "step": 3756 + }, + { + "epoch": 0.32, + "learning_rate": 1.5895265468029943e-05, + "loss": 0.4855, + "step": 3757 + }, + { + "epoch": 0.32, + "learning_rate": 1.5893034566104656e-05, + "loss": 0.4861, + "step": 3758 + }, + { + "epoch": 0.32, + "learning_rate": 1.589080321475195e-05, + "loss": 0.4826, + "step": 3759 + }, + { + "epoch": 0.32, + "learning_rate": 1.5888571414141997e-05, + "loss": 0.488, + "step": 3760 + }, + { + "epoch": 0.32, + "learning_rate": 1.5886339164445007e-05, + "loss": 0.4954, + "step": 3761 + }, + { + "epoch": 0.32, + "learning_rate": 1.588410646583121e-05, + "loss": 0.4711, + "step": 3762 + }, + { + "epoch": 0.32, + "learning_rate": 1.5881873318470894e-05, + "loss": 0.469, + "step": 3763 + }, + { + "epoch": 0.32, + "learning_rate": 1.5879639722534364e-05, + "loss": 0.4839, + "step": 3764 + }, + { + "epoch": 0.32, + "learning_rate": 1.587740567819196e-05, + "loss": 0.4974, + "step": 3765 + }, + { + "epoch": 0.32, + "learning_rate": 1.587517118561406e-05, + "loss": 0.4736, + "step": 3766 + }, + { + "epoch": 0.32, + "learning_rate": 1.5872936244971083e-05, + "loss": 0.4785, + "step": 3767 + }, + { + "epoch": 0.32, + "learning_rate": 1.587070085643346e-05, + "loss": 0.488, + "step": 3768 + }, + { + "epoch": 0.32, + "learning_rate": 1.586846502017169e-05, + "loss": 0.4923, + "step": 3769 + }, + { + "epoch": 0.32, + "learning_rate": 1.5866228736356272e-05, + "loss": 0.4879, + "step": 3770 + }, + { + "epoch": 0.32, + "learning_rate": 1.5863992005157757e-05, + "loss": 0.4867, + "step": 3771 + }, + { + "epoch": 0.32, + "learning_rate": 1.5861754826746737e-05, + "loss": 0.5033, + "step": 3772 + }, + { + "epoch": 0.32, + "learning_rate": 1.585951720129382e-05, + "loss": 0.5014, + "step": 3773 + }, + { + "epoch": 0.32, + "learning_rate": 1.5857279128969657e-05, + "loss": 0.5109, + "step": 3774 + }, + { + "epoch": 0.32, + "learning_rate": 1.5855040609944935e-05, + "loss": 0.4924, + "step": 3775 + }, + { + "epoch": 0.32, + "learning_rate": 1.585280164439037e-05, + "loss": 0.4881, + "step": 3776 + }, + { + "epoch": 0.32, + "learning_rate": 1.585056223247672e-05, + "loss": 0.4854, + "step": 3777 + }, + { + "epoch": 0.32, + "learning_rate": 1.5848322374374765e-05, + "loss": 0.4924, + "step": 3778 + }, + { + "epoch": 0.32, + "learning_rate": 1.584608207025533e-05, + "loss": 0.4819, + "step": 3779 + }, + { + "epoch": 0.32, + "learning_rate": 1.5843841320289274e-05, + "loss": 0.485, + "step": 3780 + }, + { + "epoch": 0.32, + "learning_rate": 1.584160012464748e-05, + "loss": 0.5159, + "step": 3781 + }, + { + "epoch": 0.32, + "learning_rate": 1.583935848350087e-05, + "loss": 0.49, + "step": 3782 + }, + { + "epoch": 0.32, + "learning_rate": 1.5837116397020404e-05, + "loss": 0.4697, + "step": 3783 + }, + { + "epoch": 0.32, + "learning_rate": 1.5834873865377075e-05, + "loss": 0.5186, + "step": 3784 + }, + { + "epoch": 0.32, + "learning_rate": 1.5832630888741904e-05, + "loss": 0.4818, + "step": 3785 + }, + { + "epoch": 0.32, + "learning_rate": 1.583038746728595e-05, + "loss": 0.4848, + "step": 3786 + }, + { + "epoch": 0.32, + "learning_rate": 1.5828143601180306e-05, + "loss": 0.4849, + "step": 3787 + }, + { + "epoch": 0.32, + "learning_rate": 1.58258992905961e-05, + "loss": 0.5068, + "step": 3788 + }, + { + "epoch": 0.32, + "learning_rate": 1.582365453570449e-05, + "loss": 0.4916, + "step": 3789 + }, + { + "epoch": 0.32, + "learning_rate": 1.5821409336676676e-05, + "loss": 0.5017, + "step": 3790 + }, + { + "epoch": 0.32, + "learning_rate": 1.581916369368388e-05, + "loss": 0.4922, + "step": 3791 + }, + { + "epoch": 0.32, + "learning_rate": 1.581691760689737e-05, + "loss": 0.4639, + "step": 3792 + }, + { + "epoch": 0.32, + "learning_rate": 1.5814671076488434e-05, + "loss": 0.4832, + "step": 3793 + }, + { + "epoch": 0.32, + "learning_rate": 1.5812424102628406e-05, + "loss": 0.4823, + "step": 3794 + }, + { + "epoch": 0.32, + "learning_rate": 1.5810176685488654e-05, + "loss": 0.494, + "step": 3795 + }, + { + "epoch": 0.32, + "learning_rate": 1.5807928825240566e-05, + "loss": 0.4719, + "step": 3796 + }, + { + "epoch": 0.32, + "learning_rate": 1.5805680522055583e-05, + "loss": 0.4876, + "step": 3797 + }, + { + "epoch": 0.32, + "learning_rate": 1.5803431776105163e-05, + "loss": 0.4833, + "step": 3798 + }, + { + "epoch": 0.32, + "learning_rate": 1.5801182587560807e-05, + "loss": 0.4926, + "step": 3799 + }, + { + "epoch": 0.32, + "learning_rate": 1.579893295659405e-05, + "loss": 0.4871, + "step": 3800 + }, + { + "epoch": 0.32, + "learning_rate": 1.5796682883376453e-05, + "loss": 0.4909, + "step": 3801 + }, + { + "epoch": 0.32, + "learning_rate": 1.5794432368079617e-05, + "loss": 0.4862, + "step": 3802 + }, + { + "epoch": 0.32, + "learning_rate": 1.579218141087518e-05, + "loss": 0.5013, + "step": 3803 + }, + { + "epoch": 0.32, + "learning_rate": 1.5789930011934808e-05, + "loss": 0.4783, + "step": 3804 + }, + { + "epoch": 0.32, + "learning_rate": 1.57876781714302e-05, + "loss": 0.4821, + "step": 3805 + }, + { + "epoch": 0.32, + "learning_rate": 1.5785425889533094e-05, + "loss": 0.4831, + "step": 3806 + }, + { + "epoch": 0.32, + "learning_rate": 1.5783173166415253e-05, + "loss": 0.5084, + "step": 3807 + }, + { + "epoch": 0.32, + "learning_rate": 1.5780920002248484e-05, + "loss": 0.485, + "step": 3808 + }, + { + "epoch": 0.32, + "learning_rate": 1.5778666397204624e-05, + "loss": 0.4889, + "step": 3809 + }, + { + "epoch": 0.32, + "learning_rate": 1.5776412351455535e-05, + "loss": 0.5132, + "step": 3810 + }, + { + "epoch": 0.32, + "learning_rate": 1.5774157865173125e-05, + "loss": 0.4819, + "step": 3811 + }, + { + "epoch": 0.33, + "learning_rate": 1.577190293852933e-05, + "loss": 0.4774, + "step": 3812 + }, + { + "epoch": 0.33, + "learning_rate": 1.576964757169612e-05, + "loss": 0.4941, + "step": 3813 + }, + { + "epoch": 0.33, + "learning_rate": 1.5767391764845503e-05, + "loss": 0.4906, + "step": 3814 + }, + { + "epoch": 0.33, + "learning_rate": 1.5765135518149503e-05, + "loss": 0.4859, + "step": 3815 + }, + { + "epoch": 0.33, + "learning_rate": 1.5762878831780206e-05, + "loss": 0.4941, + "step": 3816 + }, + { + "epoch": 0.33, + "learning_rate": 1.5760621705909706e-05, + "loss": 0.4812, + "step": 3817 + }, + { + "epoch": 0.33, + "learning_rate": 1.575836414071015e-05, + "loss": 0.4954, + "step": 3818 + }, + { + "epoch": 0.33, + "learning_rate": 1.57561061363537e-05, + "loss": 0.4723, + "step": 3819 + }, + { + "epoch": 0.33, + "learning_rate": 1.5753847693012566e-05, + "loss": 0.4967, + "step": 3820 + }, + { + "epoch": 0.33, + "learning_rate": 1.5751588810858986e-05, + "loss": 0.4882, + "step": 3821 + }, + { + "epoch": 0.33, + "learning_rate": 1.574932949006523e-05, + "loss": 0.491, + "step": 3822 + }, + { + "epoch": 0.33, + "learning_rate": 1.5747069730803607e-05, + "loss": 0.4762, + "step": 3823 + }, + { + "epoch": 0.33, + "learning_rate": 1.574480953324645e-05, + "loss": 0.4798, + "step": 3824 + }, + { + "epoch": 0.33, + "learning_rate": 1.5742548897566135e-05, + "loss": 0.4884, + "step": 3825 + }, + { + "epoch": 0.33, + "learning_rate": 1.5740287823935067e-05, + "loss": 0.495, + "step": 3826 + }, + { + "epoch": 0.33, + "learning_rate": 1.5738026312525686e-05, + "loss": 0.4671, + "step": 3827 + }, + { + "epoch": 0.33, + "learning_rate": 1.573576436351046e-05, + "loss": 0.4837, + "step": 3828 + }, + { + "epoch": 0.33, + "learning_rate": 1.5733501977061904e-05, + "loss": 0.4931, + "step": 3829 + }, + { + "epoch": 0.33, + "learning_rate": 1.5731239153352543e-05, + "loss": 0.5012, + "step": 3830 + }, + { + "epoch": 0.33, + "learning_rate": 1.5728975892554957e-05, + "loss": 0.4917, + "step": 3831 + }, + { + "epoch": 0.33, + "learning_rate": 1.5726712194841758e-05, + "loss": 0.4935, + "step": 3832 + }, + { + "epoch": 0.33, + "learning_rate": 1.5724448060385574e-05, + "loss": 0.4869, + "step": 3833 + }, + { + "epoch": 0.33, + "learning_rate": 1.5722183489359082e-05, + "loss": 0.5089, + "step": 3834 + }, + { + "epoch": 0.33, + "learning_rate": 1.571991848193499e-05, + "loss": 0.4933, + "step": 3835 + }, + { + "epoch": 0.33, + "learning_rate": 1.5717653038286033e-05, + "loss": 0.4931, + "step": 3836 + }, + { + "epoch": 0.33, + "learning_rate": 1.5715387158584988e-05, + "loss": 0.4985, + "step": 3837 + }, + { + "epoch": 0.33, + "learning_rate": 1.5713120843004653e-05, + "loss": 0.4829, + "step": 3838 + }, + { + "epoch": 0.33, + "learning_rate": 1.5710854091717873e-05, + "loss": 0.4974, + "step": 3839 + }, + { + "epoch": 0.33, + "learning_rate": 1.5708586904897518e-05, + "loss": 0.4771, + "step": 3840 + }, + { + "epoch": 0.33, + "learning_rate": 1.5706319282716492e-05, + "loss": 0.4747, + "step": 3841 + }, + { + "epoch": 0.33, + "learning_rate": 1.5704051225347732e-05, + "loss": 0.5035, + "step": 3842 + }, + { + "epoch": 0.33, + "learning_rate": 1.5701782732964216e-05, + "loss": 0.4963, + "step": 3843 + }, + { + "epoch": 0.33, + "learning_rate": 1.5699513805738942e-05, + "loss": 0.4695, + "step": 3844 + }, + { + "epoch": 0.33, + "learning_rate": 1.5697244443844952e-05, + "loss": 0.4937, + "step": 3845 + }, + { + "epoch": 0.33, + "learning_rate": 1.5694974647455315e-05, + "loss": 0.4881, + "step": 3846 + }, + { + "epoch": 0.33, + "learning_rate": 1.5692704416743138e-05, + "loss": 0.4957, + "step": 3847 + }, + { + "epoch": 0.33, + "learning_rate": 1.569043375188155e-05, + "loss": 0.4859, + "step": 3848 + }, + { + "epoch": 0.33, + "learning_rate": 1.568816265304373e-05, + "loss": 0.4806, + "step": 3849 + }, + { + "epoch": 0.33, + "learning_rate": 1.568589112040288e-05, + "loss": 0.4801, + "step": 3850 + }, + { + "epoch": 0.33, + "learning_rate": 1.5683619154132236e-05, + "loss": 0.5217, + "step": 3851 + }, + { + "epoch": 0.33, + "learning_rate": 1.5681346754405064e-05, + "loss": 0.5026, + "step": 3852 + }, + { + "epoch": 0.33, + "learning_rate": 1.567907392139467e-05, + "loss": 0.4715, + "step": 3853 + }, + { + "epoch": 0.33, + "learning_rate": 1.5676800655274394e-05, + "loss": 0.48, + "step": 3854 + }, + { + "epoch": 0.33, + "learning_rate": 1.5674526956217596e-05, + "loss": 0.5089, + "step": 3855 + }, + { + "epoch": 0.33, + "learning_rate": 1.5672252824397683e-05, + "loss": 0.4783, + "step": 3856 + }, + { + "epoch": 0.33, + "learning_rate": 1.5669978259988087e-05, + "loss": 0.4678, + "step": 3857 + }, + { + "epoch": 0.33, + "learning_rate": 1.566770326316228e-05, + "loss": 0.4978, + "step": 3858 + }, + { + "epoch": 0.33, + "learning_rate": 1.5665427834093755e-05, + "loss": 0.4806, + "step": 3859 + }, + { + "epoch": 0.33, + "learning_rate": 1.5663151972956055e-05, + "loss": 0.4989, + "step": 3860 + }, + { + "epoch": 0.33, + "learning_rate": 1.566087567992274e-05, + "loss": 0.4873, + "step": 3861 + }, + { + "epoch": 0.33, + "learning_rate": 1.565859895516742e-05, + "loss": 0.4932, + "step": 3862 + }, + { + "epoch": 0.33, + "learning_rate": 1.565632179886371e-05, + "loss": 0.4853, + "step": 3863 + }, + { + "epoch": 0.33, + "learning_rate": 1.565404421118529e-05, + "loss": 0.4998, + "step": 3864 + }, + { + "epoch": 0.33, + "learning_rate": 1.5651766192305853e-05, + "loss": 0.4937, + "step": 3865 + }, + { + "epoch": 0.33, + "learning_rate": 1.564948774239913e-05, + "loss": 0.4985, + "step": 3866 + }, + { + "epoch": 0.33, + "learning_rate": 1.564720886163889e-05, + "loss": 0.4887, + "step": 3867 + }, + { + "epoch": 0.33, + "learning_rate": 1.564492955019892e-05, + "loss": 0.4811, + "step": 3868 + }, + { + "epoch": 0.33, + "learning_rate": 1.5642649808253057e-05, + "loss": 0.4725, + "step": 3869 + }, + { + "epoch": 0.33, + "learning_rate": 1.5640369635975165e-05, + "loss": 0.467, + "step": 3870 + }, + { + "epoch": 0.33, + "learning_rate": 1.5638089033539135e-05, + "loss": 0.4945, + "step": 3871 + }, + { + "epoch": 0.33, + "learning_rate": 1.56358080011189e-05, + "loss": 0.4852, + "step": 3872 + }, + { + "epoch": 0.33, + "learning_rate": 1.5633526538888412e-05, + "loss": 0.4932, + "step": 3873 + }, + { + "epoch": 0.33, + "learning_rate": 1.5631244647021672e-05, + "loss": 0.5103, + "step": 3874 + }, + { + "epoch": 0.33, + "learning_rate": 1.5628962325692708e-05, + "loss": 0.5069, + "step": 3875 + }, + { + "epoch": 0.33, + "learning_rate": 1.5626679575075577e-05, + "loss": 0.4724, + "step": 3876 + }, + { + "epoch": 0.33, + "learning_rate": 1.562439639534437e-05, + "loss": 0.4954, + "step": 3877 + }, + { + "epoch": 0.33, + "learning_rate": 1.5622112786673214e-05, + "loss": 0.5119, + "step": 3878 + }, + { + "epoch": 0.33, + "learning_rate": 1.561982874923626e-05, + "loss": 0.5031, + "step": 3879 + }, + { + "epoch": 0.33, + "learning_rate": 1.561754428320771e-05, + "loss": 0.4851, + "step": 3880 + }, + { + "epoch": 0.33, + "learning_rate": 1.5615259388761777e-05, + "loss": 0.4732, + "step": 3881 + }, + { + "epoch": 0.33, + "learning_rate": 1.561297406607272e-05, + "loss": 0.4796, + "step": 3882 + }, + { + "epoch": 0.33, + "learning_rate": 1.561068831531483e-05, + "loss": 0.471, + "step": 3883 + }, + { + "epoch": 0.33, + "learning_rate": 1.5608402136662423e-05, + "loss": 0.4978, + "step": 3884 + }, + { + "epoch": 0.33, + "learning_rate": 1.5606115530289856e-05, + "loss": 0.4962, + "step": 3885 + }, + { + "epoch": 0.33, + "learning_rate": 1.560382849637151e-05, + "loss": 0.4664, + "step": 3886 + }, + { + "epoch": 0.33, + "learning_rate": 1.5601541035081813e-05, + "loss": 0.4904, + "step": 3887 + }, + { + "epoch": 0.33, + "learning_rate": 1.559925314659521e-05, + "loss": 0.4981, + "step": 3888 + }, + { + "epoch": 0.33, + "learning_rate": 1.5596964831086185e-05, + "loss": 0.4821, + "step": 3889 + }, + { + "epoch": 0.33, + "learning_rate": 1.5594676088729252e-05, + "loss": 0.4915, + "step": 3890 + }, + { + "epoch": 0.33, + "learning_rate": 1.5592386919698967e-05, + "loss": 0.4787, + "step": 3891 + }, + { + "epoch": 0.33, + "learning_rate": 1.5590097324169907e-05, + "loss": 0.5092, + "step": 3892 + }, + { + "epoch": 0.33, + "learning_rate": 1.5587807302316687e-05, + "loss": 0.5037, + "step": 3893 + }, + { + "epoch": 0.33, + "learning_rate": 1.5585516854313957e-05, + "loss": 0.4937, + "step": 3894 + }, + { + "epoch": 0.33, + "learning_rate": 1.558322598033639e-05, + "loss": 0.4824, + "step": 3895 + }, + { + "epoch": 0.33, + "learning_rate": 1.5580934680558696e-05, + "loss": 0.4927, + "step": 3896 + }, + { + "epoch": 0.33, + "learning_rate": 1.5578642955155627e-05, + "loss": 0.4924, + "step": 3897 + }, + { + "epoch": 0.33, + "learning_rate": 1.557635080430196e-05, + "loss": 0.4804, + "step": 3898 + }, + { + "epoch": 0.33, + "learning_rate": 1.5574058228172498e-05, + "loss": 0.4863, + "step": 3899 + }, + { + "epoch": 0.33, + "learning_rate": 1.557176522694208e-05, + "loss": 0.4725, + "step": 3900 + }, + { + "epoch": 0.33, + "learning_rate": 1.556947180078559e-05, + "loss": 0.4919, + "step": 3901 + }, + { + "epoch": 0.33, + "learning_rate": 1.5567177949877925e-05, + "loss": 0.467, + "step": 3902 + }, + { + "epoch": 0.33, + "learning_rate": 1.556488367439403e-05, + "loss": 0.4995, + "step": 3903 + }, + { + "epoch": 0.33, + "learning_rate": 1.556258897450887e-05, + "loss": 0.4914, + "step": 3904 + }, + { + "epoch": 0.33, + "learning_rate": 1.5560293850397455e-05, + "loss": 0.4997, + "step": 3905 + }, + { + "epoch": 0.33, + "learning_rate": 1.5557998302234817e-05, + "loss": 0.4842, + "step": 3906 + }, + { + "epoch": 0.33, + "learning_rate": 1.5555702330196024e-05, + "loss": 0.4847, + "step": 3907 + }, + { + "epoch": 0.33, + "learning_rate": 1.555340593445618e-05, + "loss": 0.4927, + "step": 3908 + }, + { + "epoch": 0.33, + "learning_rate": 1.5551109115190408e-05, + "loss": 0.4821, + "step": 3909 + }, + { + "epoch": 0.33, + "learning_rate": 1.5548811872573883e-05, + "loss": 0.5074, + "step": 3910 + }, + { + "epoch": 0.33, + "learning_rate": 1.55465142067818e-05, + "loss": 0.4852, + "step": 3911 + }, + { + "epoch": 0.33, + "learning_rate": 1.554421611798939e-05, + "loss": 0.5034, + "step": 3912 + }, + { + "epoch": 0.33, + "learning_rate": 1.5541917606371904e-05, + "loss": 0.4716, + "step": 3913 + }, + { + "epoch": 0.33, + "learning_rate": 1.553961867210465e-05, + "loss": 0.4802, + "step": 3914 + }, + { + "epoch": 0.33, + "learning_rate": 1.553731931536295e-05, + "loss": 0.4795, + "step": 3915 + }, + { + "epoch": 0.33, + "learning_rate": 1.5535019536322158e-05, + "loss": 0.4816, + "step": 3916 + }, + { + "epoch": 0.33, + "learning_rate": 1.5532719335157673e-05, + "loss": 0.48, + "step": 3917 + }, + { + "epoch": 0.33, + "learning_rate": 1.5530418712044907e-05, + "loss": 0.488, + "step": 3918 + }, + { + "epoch": 0.33, + "learning_rate": 1.5528117667159325e-05, + "loss": 0.5021, + "step": 3919 + }, + { + "epoch": 0.33, + "learning_rate": 1.552581620067641e-05, + "loss": 0.4874, + "step": 3920 + }, + { + "epoch": 0.33, + "learning_rate": 1.5523514312771683e-05, + "loss": 0.4934, + "step": 3921 + }, + { + "epoch": 0.33, + "learning_rate": 1.5521212003620692e-05, + "loss": 0.4656, + "step": 3922 + }, + { + "epoch": 0.33, + "learning_rate": 1.5518909273399026e-05, + "loss": 0.4723, + "step": 3923 + }, + { + "epoch": 0.33, + "learning_rate": 1.5516606122282297e-05, + "loss": 0.5162, + "step": 3924 + }, + { + "epoch": 0.33, + "learning_rate": 1.5514302550446153e-05, + "loss": 0.4873, + "step": 3925 + }, + { + "epoch": 0.33, + "learning_rate": 1.5511998558066276e-05, + "loss": 0.4723, + "step": 3926 + }, + { + "epoch": 0.33, + "learning_rate": 1.5509694145318374e-05, + "loss": 0.4825, + "step": 3927 + }, + { + "epoch": 0.33, + "learning_rate": 1.55073893123782e-05, + "loss": 0.4861, + "step": 3928 + }, + { + "epoch": 0.34, + "learning_rate": 1.5505084059421517e-05, + "loss": 0.5117, + "step": 3929 + }, + { + "epoch": 0.34, + "learning_rate": 1.5502778386624147e-05, + "loss": 0.4805, + "step": 3930 + }, + { + "epoch": 0.34, + "learning_rate": 1.550047229416192e-05, + "loss": 0.5117, + "step": 3931 + }, + { + "epoch": 0.34, + "learning_rate": 1.5498165782210713e-05, + "loss": 0.4862, + "step": 3932 + }, + { + "epoch": 0.34, + "learning_rate": 1.5495858850946433e-05, + "loss": 0.5021, + "step": 3933 + }, + { + "epoch": 0.34, + "learning_rate": 1.549355150054501e-05, + "loss": 0.4936, + "step": 3934 + }, + { + "epoch": 0.34, + "learning_rate": 1.5491243731182414e-05, + "loss": 0.4881, + "step": 3935 + }, + { + "epoch": 0.34, + "learning_rate": 1.5488935543034644e-05, + "loss": 0.4771, + "step": 3936 + }, + { + "epoch": 0.34, + "learning_rate": 1.5486626936277737e-05, + "loss": 0.4806, + "step": 3937 + }, + { + "epoch": 0.34, + "learning_rate": 1.548431791108775e-05, + "loss": 0.4821, + "step": 3938 + }, + { + "epoch": 0.34, + "learning_rate": 1.548200846764079e-05, + "loss": 0.4909, + "step": 3939 + }, + { + "epoch": 0.34, + "learning_rate": 1.547969860611297e-05, + "loss": 0.5036, + "step": 3940 + }, + { + "epoch": 0.34, + "learning_rate": 1.547738832668046e-05, + "loss": 0.4715, + "step": 3941 + }, + { + "epoch": 0.34, + "learning_rate": 1.547507762951945e-05, + "loss": 0.492, + "step": 3942 + }, + { + "epoch": 0.34, + "learning_rate": 1.547276651480616e-05, + "loss": 0.4916, + "step": 3943 + }, + { + "epoch": 0.34, + "learning_rate": 1.5470454982716852e-05, + "loss": 0.4736, + "step": 3944 + }, + { + "epoch": 0.34, + "learning_rate": 1.5468143033427802e-05, + "loss": 0.5132, + "step": 3945 + }, + { + "epoch": 0.34, + "learning_rate": 1.546583066711534e-05, + "loss": 0.4813, + "step": 3946 + }, + { + "epoch": 0.34, + "learning_rate": 1.5463517883955813e-05, + "loss": 0.5018, + "step": 3947 + }, + { + "epoch": 0.34, + "learning_rate": 1.5461204684125595e-05, + "loss": 0.5026, + "step": 3948 + }, + { + "epoch": 0.34, + "learning_rate": 1.545889106780112e-05, + "loss": 0.5087, + "step": 3949 + }, + { + "epoch": 0.34, + "learning_rate": 1.5456577035158814e-05, + "loss": 0.4782, + "step": 3950 + }, + { + "epoch": 0.34, + "learning_rate": 1.5454262586375164e-05, + "loss": 0.4932, + "step": 3951 + }, + { + "epoch": 0.34, + "learning_rate": 1.5451947721626676e-05, + "loss": 0.4987, + "step": 3952 + }, + { + "epoch": 0.34, + "learning_rate": 1.5449632441089896e-05, + "loss": 0.4609, + "step": 3953 + }, + { + "epoch": 0.34, + "learning_rate": 1.54473167449414e-05, + "loss": 0.4951, + "step": 3954 + }, + { + "epoch": 0.34, + "learning_rate": 1.544500063335778e-05, + "loss": 0.4669, + "step": 3955 + }, + { + "epoch": 0.34, + "learning_rate": 1.544268410651568e-05, + "loss": 0.4875, + "step": 3956 + }, + { + "epoch": 0.34, + "learning_rate": 1.5440367164591768e-05, + "loss": 0.4614, + "step": 3957 + }, + { + "epoch": 0.34, + "learning_rate": 1.5438049807762746e-05, + "loss": 0.5078, + "step": 3958 + }, + { + "epoch": 0.34, + "learning_rate": 1.543573203620534e-05, + "loss": 0.4848, + "step": 3959 + }, + { + "epoch": 0.34, + "learning_rate": 1.5433413850096316e-05, + "loss": 0.5104, + "step": 3960 + }, + { + "epoch": 0.34, + "learning_rate": 1.5431095249612466e-05, + "loss": 0.4905, + "step": 3961 + }, + { + "epoch": 0.34, + "learning_rate": 1.542877623493062e-05, + "loss": 0.4738, + "step": 3962 + }, + { + "epoch": 0.34, + "learning_rate": 1.5426456806227635e-05, + "loss": 0.5096, + "step": 3963 + }, + { + "epoch": 0.34, + "learning_rate": 1.5424136963680398e-05, + "loss": 0.4681, + "step": 3964 + }, + { + "epoch": 0.34, + "learning_rate": 1.542181670746583e-05, + "loss": 0.5045, + "step": 3965 + }, + { + "epoch": 0.34, + "learning_rate": 1.5419496037760887e-05, + "loss": 0.4785, + "step": 3966 + }, + { + "epoch": 0.34, + "learning_rate": 1.541717495474255e-05, + "loss": 0.4973, + "step": 3967 + }, + { + "epoch": 0.34, + "learning_rate": 1.5414853458587834e-05, + "loss": 0.5206, + "step": 3968 + }, + { + "epoch": 0.34, + "learning_rate": 1.5412531549473786e-05, + "loss": 0.4829, + "step": 3969 + }, + { + "epoch": 0.34, + "learning_rate": 1.5410209227577487e-05, + "loss": 0.482, + "step": 3970 + }, + { + "epoch": 0.34, + "learning_rate": 1.5407886493076043e-05, + "loss": 0.4707, + "step": 3971 + }, + { + "epoch": 0.34, + "learning_rate": 1.5405563346146603e-05, + "loss": 0.4983, + "step": 3972 + }, + { + "epoch": 0.34, + "learning_rate": 1.540323978696633e-05, + "loss": 0.4918, + "step": 3973 + }, + { + "epoch": 0.34, + "learning_rate": 1.540091581571243e-05, + "loss": 0.4851, + "step": 3974 + }, + { + "epoch": 0.34, + "learning_rate": 1.539859143256215e-05, + "loss": 0.4815, + "step": 3975 + }, + { + "epoch": 0.34, + "learning_rate": 1.5396266637692746e-05, + "loss": 0.4675, + "step": 3976 + }, + { + "epoch": 0.34, + "learning_rate": 1.5393941431281513e-05, + "loss": 0.4791, + "step": 3977 + }, + { + "epoch": 0.34, + "learning_rate": 1.5391615813505792e-05, + "loss": 0.4986, + "step": 3978 + }, + { + "epoch": 0.34, + "learning_rate": 1.5389289784542944e-05, + "loss": 0.5028, + "step": 3979 + }, + { + "epoch": 0.34, + "learning_rate": 1.5386963344570352e-05, + "loss": 0.4713, + "step": 3980 + }, + { + "epoch": 0.34, + "learning_rate": 1.538463649376545e-05, + "loss": 0.4817, + "step": 3981 + }, + { + "epoch": 0.34, + "learning_rate": 1.5382309232305685e-05, + "loss": 0.531, + "step": 3982 + }, + { + "epoch": 0.34, + "learning_rate": 1.5379981560368548e-05, + "loss": 0.4811, + "step": 3983 + }, + { + "epoch": 0.34, + "learning_rate": 1.5377653478131557e-05, + "loss": 0.5003, + "step": 3984 + }, + { + "epoch": 0.34, + "learning_rate": 1.5375324985772262e-05, + "loss": 0.5037, + "step": 3985 + }, + { + "epoch": 0.34, + "learning_rate": 1.5372996083468242e-05, + "loss": 0.4701, + "step": 3986 + }, + { + "epoch": 0.34, + "learning_rate": 1.5370666771397105e-05, + "loss": 0.4726, + "step": 3987 + }, + { + "epoch": 0.34, + "learning_rate": 1.5368337049736505e-05, + "loss": 0.4815, + "step": 3988 + }, + { + "epoch": 0.34, + "learning_rate": 1.53660069186641e-05, + "loss": 0.4823, + "step": 3989 + }, + { + "epoch": 0.34, + "learning_rate": 1.5363676378357614e-05, + "loss": 0.4717, + "step": 3990 + }, + { + "epoch": 0.34, + "learning_rate": 1.5361345428994772e-05, + "loss": 0.4821, + "step": 3991 + }, + { + "epoch": 0.34, + "learning_rate": 1.5359014070753345e-05, + "loss": 0.4893, + "step": 3992 + }, + { + "epoch": 0.34, + "learning_rate": 1.535668230381113e-05, + "loss": 0.4779, + "step": 3993 + }, + { + "epoch": 0.34, + "learning_rate": 1.535435012834596e-05, + "loss": 0.4829, + "step": 3994 + }, + { + "epoch": 0.34, + "learning_rate": 1.5352017544535694e-05, + "loss": 0.4882, + "step": 3995 + }, + { + "epoch": 0.34, + "learning_rate": 1.5349684552558226e-05, + "loss": 0.4848, + "step": 3996 + }, + { + "epoch": 0.34, + "learning_rate": 1.5347351152591485e-05, + "loss": 0.5034, + "step": 3997 + }, + { + "epoch": 0.34, + "learning_rate": 1.5345017344813414e-05, + "loss": 0.4822, + "step": 3998 + }, + { + "epoch": 0.34, + "learning_rate": 1.534268312940201e-05, + "loss": 0.4887, + "step": 3999 + }, + { + "epoch": 0.34, + "learning_rate": 1.534034850653528e-05, + "loss": 0.4759, + "step": 4000 + }, + { + "epoch": 0.34, + "learning_rate": 1.5338013476391282e-05, + "loss": 0.4983, + "step": 4001 + }, + { + "epoch": 0.34, + "learning_rate": 1.5335678039148094e-05, + "loss": 0.4882, + "step": 4002 + }, + { + "epoch": 0.34, + "learning_rate": 1.533334219498382e-05, + "loss": 0.4814, + "step": 4003 + }, + { + "epoch": 0.34, + "learning_rate": 1.53310059440766e-05, + "loss": 0.5108, + "step": 4004 + }, + { + "epoch": 0.34, + "learning_rate": 1.5328669286604612e-05, + "loss": 0.4952, + "step": 4005 + }, + { + "epoch": 0.34, + "learning_rate": 1.532633222274606e-05, + "loss": 0.4661, + "step": 4006 + }, + { + "epoch": 0.34, + "learning_rate": 1.5323994752679174e-05, + "loss": 0.4965, + "step": 4007 + }, + { + "epoch": 0.34, + "learning_rate": 1.5321656876582226e-05, + "loss": 0.4918, + "step": 4008 + }, + { + "epoch": 0.34, + "learning_rate": 1.53193185946335e-05, + "loss": 0.4796, + "step": 4009 + }, + { + "epoch": 0.34, + "learning_rate": 1.5316979907011335e-05, + "loss": 0.4806, + "step": 4010 + }, + { + "epoch": 0.34, + "learning_rate": 1.5314640813894088e-05, + "loss": 0.4856, + "step": 4011 + }, + { + "epoch": 0.34, + "learning_rate": 1.531230131546014e-05, + "loss": 0.4891, + "step": 4012 + }, + { + "epoch": 0.34, + "learning_rate": 1.5309961411887915e-05, + "loss": 0.469, + "step": 4013 + }, + { + "epoch": 0.34, + "learning_rate": 1.5307621103355865e-05, + "loss": 0.499, + "step": 4014 + }, + { + "epoch": 0.34, + "learning_rate": 1.530528039004247e-05, + "loss": 0.5021, + "step": 4015 + }, + { + "epoch": 0.34, + "learning_rate": 1.5302939272126243e-05, + "loss": 0.4842, + "step": 4016 + }, + { + "epoch": 0.34, + "learning_rate": 1.530059774978573e-05, + "loss": 0.4744, + "step": 4017 + }, + { + "epoch": 0.34, + "learning_rate": 1.5298255823199503e-05, + "loss": 0.4916, + "step": 4018 + }, + { + "epoch": 0.34, + "learning_rate": 1.5295913492546168e-05, + "loss": 0.4613, + "step": 4019 + }, + { + "epoch": 0.34, + "learning_rate": 1.529357075800436e-05, + "loss": 0.5065, + "step": 4020 + }, + { + "epoch": 0.34, + "learning_rate": 1.5291227619752748e-05, + "loss": 0.4898, + "step": 4021 + }, + { + "epoch": 0.34, + "learning_rate": 1.5288884077970025e-05, + "loss": 0.4796, + "step": 4022 + }, + { + "epoch": 0.34, + "learning_rate": 1.528654013283492e-05, + "loss": 0.4845, + "step": 4023 + }, + { + "epoch": 0.34, + "learning_rate": 1.5284195784526196e-05, + "loss": 0.4808, + "step": 4024 + }, + { + "epoch": 0.34, + "learning_rate": 1.528185103322264e-05, + "loss": 0.4871, + "step": 4025 + }, + { + "epoch": 0.34, + "learning_rate": 1.5279505879103074e-05, + "loss": 0.4665, + "step": 4026 + }, + { + "epoch": 0.34, + "learning_rate": 1.527716032234635e-05, + "loss": 0.482, + "step": 4027 + }, + { + "epoch": 0.34, + "learning_rate": 1.5274814363131346e-05, + "loss": 0.4837, + "step": 4028 + }, + { + "epoch": 0.34, + "learning_rate": 1.5272468001636975e-05, + "loss": 0.4891, + "step": 4029 + }, + { + "epoch": 0.34, + "learning_rate": 1.5270121238042186e-05, + "loss": 0.5038, + "step": 4030 + }, + { + "epoch": 0.34, + "learning_rate": 1.5267774072525948e-05, + "loss": 0.4996, + "step": 4031 + }, + { + "epoch": 0.34, + "learning_rate": 1.5265426505267265e-05, + "loss": 0.4757, + "step": 4032 + }, + { + "epoch": 0.34, + "learning_rate": 1.5263078536445176e-05, + "loss": 0.5009, + "step": 4033 + }, + { + "epoch": 0.34, + "learning_rate": 1.5260730166238747e-05, + "loss": 0.4806, + "step": 4034 + }, + { + "epoch": 0.34, + "learning_rate": 1.525838139482707e-05, + "loss": 0.4717, + "step": 4035 + }, + { + "epoch": 0.34, + "learning_rate": 1.5256032222389276e-05, + "loss": 0.4881, + "step": 4036 + }, + { + "epoch": 0.34, + "learning_rate": 1.5253682649104519e-05, + "loss": 0.4827, + "step": 4037 + }, + { + "epoch": 0.34, + "learning_rate": 1.5251332675151993e-05, + "loss": 0.4975, + "step": 4038 + }, + { + "epoch": 0.34, + "learning_rate": 1.5248982300710913e-05, + "loss": 0.4933, + "step": 4039 + }, + { + "epoch": 0.34, + "learning_rate": 1.5246631525960527e-05, + "loss": 0.4836, + "step": 4040 + }, + { + "epoch": 0.34, + "learning_rate": 1.5244280351080121e-05, + "loss": 0.4989, + "step": 4041 + }, + { + "epoch": 0.34, + "learning_rate": 1.5241928776248993e-05, + "loss": 0.4815, + "step": 4042 + }, + { + "epoch": 0.34, + "learning_rate": 1.5239576801646501e-05, + "loss": 0.4577, + "step": 4043 + }, + { + "epoch": 0.34, + "learning_rate": 1.5237224427452002e-05, + "loss": 0.5196, + "step": 4044 + }, + { + "epoch": 0.34, + "learning_rate": 1.5234871653844904e-05, + "loss": 0.4694, + "step": 4045 + }, + { + "epoch": 0.34, + "learning_rate": 1.5232518481004642e-05, + "loss": 0.4869, + "step": 4046 + }, + { + "epoch": 0.35, + "learning_rate": 1.5230164909110674e-05, + "loss": 0.4875, + "step": 4047 + }, + { + "epoch": 0.35, + "learning_rate": 1.5227810938342493e-05, + "loss": 0.4796, + "step": 4048 + }, + { + "epoch": 0.35, + "learning_rate": 1.5225456568879624e-05, + "loss": 0.4726, + "step": 4049 + }, + { + "epoch": 0.35, + "learning_rate": 1.5223101800901625e-05, + "loss": 0.4954, + "step": 4050 + }, + { + "epoch": 0.35, + "learning_rate": 1.5220746634588076e-05, + "loss": 0.4922, + "step": 4051 + }, + { + "epoch": 0.35, + "learning_rate": 1.521839107011859e-05, + "loss": 0.4758, + "step": 4052 + }, + { + "epoch": 0.35, + "learning_rate": 1.5216035107672818e-05, + "loss": 0.4871, + "step": 4053 + }, + { + "epoch": 0.35, + "learning_rate": 1.5213678747430429e-05, + "loss": 0.4562, + "step": 4054 + }, + { + "epoch": 0.35, + "learning_rate": 1.5211321989571134e-05, + "loss": 0.4698, + "step": 4055 + }, + { + "epoch": 0.35, + "learning_rate": 1.5208964834274669e-05, + "loss": 0.4872, + "step": 4056 + }, + { + "epoch": 0.35, + "learning_rate": 1.5206607281720797e-05, + "loss": 0.5011, + "step": 4057 + }, + { + "epoch": 0.35, + "learning_rate": 1.5204249332089318e-05, + "loss": 0.4675, + "step": 4058 + }, + { + "epoch": 0.35, + "learning_rate": 1.5201890985560056e-05, + "loss": 0.4875, + "step": 4059 + }, + { + "epoch": 0.35, + "learning_rate": 1.5199532242312872e-05, + "loss": 0.4996, + "step": 4060 + }, + { + "epoch": 0.35, + "learning_rate": 1.5197173102527652e-05, + "loss": 0.4916, + "step": 4061 + }, + { + "epoch": 0.35, + "learning_rate": 1.5194813566384312e-05, + "loss": 0.4956, + "step": 4062 + }, + { + "epoch": 0.35, + "learning_rate": 1.51924536340628e-05, + "loss": 0.5038, + "step": 4063 + }, + { + "epoch": 0.35, + "learning_rate": 1.5190093305743103e-05, + "loss": 0.4761, + "step": 4064 + }, + { + "epoch": 0.35, + "learning_rate": 1.5187732581605217e-05, + "loss": 0.4839, + "step": 4065 + }, + { + "epoch": 0.35, + "learning_rate": 1.5185371461829186e-05, + "loss": 0.5018, + "step": 4066 + }, + { + "epoch": 0.35, + "learning_rate": 1.518300994659508e-05, + "loss": 0.5062, + "step": 4067 + }, + { + "epoch": 0.35, + "learning_rate": 1.5180648036082998e-05, + "loss": 0.4834, + "step": 4068 + }, + { + "epoch": 0.35, + "learning_rate": 1.5178285730473068e-05, + "loss": 0.5115, + "step": 4069 + }, + { + "epoch": 0.35, + "learning_rate": 1.5175923029945447e-05, + "loss": 0.491, + "step": 4070 + }, + { + "epoch": 0.35, + "learning_rate": 1.5173559934680331e-05, + "loss": 0.4844, + "step": 4071 + }, + { + "epoch": 0.35, + "learning_rate": 1.5171196444857933e-05, + "loss": 0.4752, + "step": 4072 + }, + { + "epoch": 0.35, + "learning_rate": 1.5168832560658506e-05, + "loss": 0.4653, + "step": 4073 + }, + { + "epoch": 0.35, + "learning_rate": 1.5166468282262327e-05, + "loss": 0.4915, + "step": 4074 + }, + { + "epoch": 0.35, + "learning_rate": 1.516410360984971e-05, + "loss": 0.4833, + "step": 4075 + }, + { + "epoch": 0.35, + "learning_rate": 1.516173854360099e-05, + "loss": 0.5093, + "step": 4076 + }, + { + "epoch": 0.35, + "learning_rate": 1.515937308369654e-05, + "loss": 0.4616, + "step": 4077 + }, + { + "epoch": 0.35, + "learning_rate": 1.5157007230316757e-05, + "loss": 0.5034, + "step": 4078 + }, + { + "epoch": 0.35, + "learning_rate": 1.5154640983642077e-05, + "loss": 0.4805, + "step": 4079 + }, + { + "epoch": 0.35, + "learning_rate": 1.5152274343852953e-05, + "loss": 0.4952, + "step": 4080 + }, + { + "epoch": 0.35, + "learning_rate": 1.5149907311129877e-05, + "loss": 0.4856, + "step": 4081 + }, + { + "epoch": 0.35, + "learning_rate": 1.514753988565337e-05, + "loss": 0.5014, + "step": 4082 + }, + { + "epoch": 0.35, + "learning_rate": 1.514517206760398e-05, + "loss": 0.4795, + "step": 4083 + }, + { + "epoch": 0.35, + "learning_rate": 1.5142803857162289e-05, + "loss": 0.4585, + "step": 4084 + }, + { + "epoch": 0.35, + "learning_rate": 1.5140435254508905e-05, + "loss": 0.4824, + "step": 4085 + }, + { + "epoch": 0.35, + "learning_rate": 1.5138066259824468e-05, + "loss": 0.4976, + "step": 4086 + }, + { + "epoch": 0.35, + "learning_rate": 1.5135696873289648e-05, + "loss": 0.4955, + "step": 4087 + }, + { + "epoch": 0.35, + "learning_rate": 1.5133327095085139e-05, + "loss": 0.5017, + "step": 4088 + }, + { + "epoch": 0.35, + "learning_rate": 1.5130956925391678e-05, + "loss": 0.4766, + "step": 4089 + }, + { + "epoch": 0.35, + "learning_rate": 1.5128586364390021e-05, + "loss": 0.4983, + "step": 4090 + }, + { + "epoch": 0.35, + "learning_rate": 1.5126215412260958e-05, + "loss": 0.4774, + "step": 4091 + }, + { + "epoch": 0.35, + "learning_rate": 1.5123844069185305e-05, + "loss": 0.4874, + "step": 4092 + }, + { + "epoch": 0.35, + "learning_rate": 1.5121472335343912e-05, + "loss": 0.474, + "step": 4093 + }, + { + "epoch": 0.35, + "learning_rate": 1.5119100210917657e-05, + "loss": 0.4971, + "step": 4094 + }, + { + "epoch": 0.35, + "learning_rate": 1.5116727696087447e-05, + "loss": 0.4915, + "step": 4095 + }, + { + "epoch": 0.35, + "learning_rate": 1.5114354791034225e-05, + "loss": 0.526, + "step": 4096 + }, + { + "epoch": 0.35, + "learning_rate": 1.511198149593895e-05, + "loss": 0.4803, + "step": 4097 + }, + { + "epoch": 0.35, + "learning_rate": 1.5109607810982628e-05, + "loss": 0.4991, + "step": 4098 + }, + { + "epoch": 0.35, + "learning_rate": 1.5107233736346278e-05, + "loss": 0.4992, + "step": 4099 + }, + { + "epoch": 0.35, + "learning_rate": 1.5104859272210966e-05, + "loss": 0.4661, + "step": 4100 + }, + { + "epoch": 0.35, + "learning_rate": 1.5102484418757772e-05, + "loss": 0.4967, + "step": 4101 + }, + { + "epoch": 0.35, + "learning_rate": 1.5100109176167814e-05, + "loss": 0.4959, + "step": 4102 + }, + { + "epoch": 0.35, + "learning_rate": 1.5097733544622239e-05, + "loss": 0.4841, + "step": 4103 + }, + { + "epoch": 0.35, + "learning_rate": 1.5095357524302219e-05, + "loss": 0.5046, + "step": 4104 + }, + { + "epoch": 0.35, + "learning_rate": 1.5092981115388963e-05, + "loss": 0.4772, + "step": 4105 + }, + { + "epoch": 0.35, + "learning_rate": 1.5090604318063704e-05, + "loss": 0.5079, + "step": 4106 + }, + { + "epoch": 0.35, + "learning_rate": 1.508822713250771e-05, + "loss": 0.4735, + "step": 4107 + }, + { + "epoch": 0.35, + "learning_rate": 1.5085849558902265e-05, + "loss": 0.4879, + "step": 4108 + }, + { + "epoch": 0.35, + "learning_rate": 1.5083471597428707e-05, + "loss": 0.4677, + "step": 4109 + }, + { + "epoch": 0.35, + "learning_rate": 1.5081093248268382e-05, + "loss": 0.4747, + "step": 4110 + }, + { + "epoch": 0.35, + "learning_rate": 1.5078714511602667e-05, + "loss": 0.4941, + "step": 4111 + }, + { + "epoch": 0.35, + "learning_rate": 1.5076335387612987e-05, + "loss": 0.4886, + "step": 4112 + }, + { + "epoch": 0.35, + "learning_rate": 1.5073955876480775e-05, + "loss": 0.4601, + "step": 4113 + }, + { + "epoch": 0.35, + "learning_rate": 1.5071575978387505e-05, + "loss": 0.4864, + "step": 4114 + }, + { + "epoch": 0.35, + "learning_rate": 1.5069195693514672e-05, + "loss": 0.4899, + "step": 4115 + }, + { + "epoch": 0.35, + "learning_rate": 1.506681502204382e-05, + "loss": 0.4747, + "step": 4116 + }, + { + "epoch": 0.35, + "learning_rate": 1.5064433964156497e-05, + "loss": 0.4746, + "step": 4117 + }, + { + "epoch": 0.35, + "learning_rate": 1.5062052520034299e-05, + "loss": 0.4935, + "step": 4118 + }, + { + "epoch": 0.35, + "learning_rate": 1.505967068985884e-05, + "loss": 0.508, + "step": 4119 + }, + { + "epoch": 0.35, + "learning_rate": 1.5057288473811773e-05, + "loss": 0.4801, + "step": 4120 + }, + { + "epoch": 0.35, + "learning_rate": 1.5054905872074772e-05, + "loss": 0.4712, + "step": 4121 + }, + { + "epoch": 0.35, + "learning_rate": 1.5052522884829543e-05, + "loss": 0.4951, + "step": 4122 + }, + { + "epoch": 0.35, + "learning_rate": 1.505013951225783e-05, + "loss": 0.4559, + "step": 4123 + }, + { + "epoch": 0.35, + "learning_rate": 1.5047755754541392e-05, + "loss": 0.5025, + "step": 4124 + }, + { + "epoch": 0.35, + "learning_rate": 1.5045371611862026e-05, + "loss": 0.4884, + "step": 4125 + }, + { + "epoch": 0.35, + "learning_rate": 1.5042987084401559e-05, + "loss": 0.4792, + "step": 4126 + }, + { + "epoch": 0.35, + "learning_rate": 1.504060217234184e-05, + "loss": 0.4933, + "step": 4127 + }, + { + "epoch": 0.35, + "learning_rate": 1.5038216875864758e-05, + "loss": 0.4999, + "step": 4128 + }, + { + "epoch": 0.35, + "learning_rate": 1.5035831195152221e-05, + "loss": 0.481, + "step": 4129 + }, + { + "epoch": 0.35, + "learning_rate": 1.5033445130386176e-05, + "loss": 0.5122, + "step": 4130 + }, + { + "epoch": 0.35, + "learning_rate": 1.5031058681748587e-05, + "loss": 0.4855, + "step": 4131 + }, + { + "epoch": 0.35, + "learning_rate": 1.5028671849421463e-05, + "loss": 0.4933, + "step": 4132 + }, + { + "epoch": 0.35, + "learning_rate": 1.5026284633586828e-05, + "loss": 0.4882, + "step": 4133 + }, + { + "epoch": 0.35, + "learning_rate": 1.5023897034426741e-05, + "loss": 0.5095, + "step": 4134 + }, + { + "epoch": 0.35, + "learning_rate": 1.5021509052123295e-05, + "loss": 0.4832, + "step": 4135 + }, + { + "epoch": 0.35, + "learning_rate": 1.5019120686858603e-05, + "loss": 0.4846, + "step": 4136 + }, + { + "epoch": 0.35, + "learning_rate": 1.5016731938814815e-05, + "loss": 0.4845, + "step": 4137 + }, + { + "epoch": 0.35, + "learning_rate": 1.5014342808174102e-05, + "loss": 0.4873, + "step": 4138 + }, + { + "epoch": 0.35, + "learning_rate": 1.5011953295118677e-05, + "loss": 0.4757, + "step": 4139 + }, + { + "epoch": 0.35, + "learning_rate": 1.5009563399830764e-05, + "loss": 0.5001, + "step": 4140 + }, + { + "epoch": 0.35, + "learning_rate": 1.5007173122492635e-05, + "loss": 0.4925, + "step": 4141 + }, + { + "epoch": 0.35, + "learning_rate": 1.500478246328658e-05, + "loss": 0.4902, + "step": 4142 + }, + { + "epoch": 0.35, + "learning_rate": 1.5002391422394915e-05, + "loss": 0.4812, + "step": 4143 + }, + { + "epoch": 0.35, + "learning_rate": 1.5000000000000002e-05, + "loss": 0.4955, + "step": 4144 + }, + { + "epoch": 0.35, + "learning_rate": 1.4997608196284212e-05, + "loss": 0.4899, + "step": 4145 + }, + { + "epoch": 0.35, + "learning_rate": 1.4995216011429956e-05, + "loss": 0.4917, + "step": 4146 + }, + { + "epoch": 0.35, + "learning_rate": 1.4992823445619672e-05, + "loss": 0.4926, + "step": 4147 + }, + { + "epoch": 0.35, + "learning_rate": 1.499043049903583e-05, + "loss": 0.4861, + "step": 4148 + }, + { + "epoch": 0.35, + "learning_rate": 1.498803717186092e-05, + "loss": 0.4845, + "step": 4149 + }, + { + "epoch": 0.35, + "learning_rate": 1.4985643464277475e-05, + "loss": 0.5006, + "step": 4150 + }, + { + "epoch": 0.35, + "learning_rate": 1.4983249376468045e-05, + "loss": 0.4962, + "step": 4151 + }, + { + "epoch": 0.35, + "learning_rate": 1.498085490861521e-05, + "loss": 0.4761, + "step": 4152 + }, + { + "epoch": 0.35, + "learning_rate": 1.4978460060901587e-05, + "loss": 0.4983, + "step": 4153 + }, + { + "epoch": 0.35, + "learning_rate": 1.4976064833509816e-05, + "loss": 0.513, + "step": 4154 + }, + { + "epoch": 0.35, + "learning_rate": 1.4973669226622564e-05, + "loss": 0.4689, + "step": 4155 + }, + { + "epoch": 0.35, + "learning_rate": 1.4971273240422534e-05, + "loss": 0.5088, + "step": 4156 + }, + { + "epoch": 0.35, + "learning_rate": 1.4968876875092453e-05, + "loss": 0.4796, + "step": 4157 + }, + { + "epoch": 0.35, + "learning_rate": 1.4966480130815076e-05, + "loss": 0.4866, + "step": 4158 + }, + { + "epoch": 0.35, + "learning_rate": 1.4964083007773189e-05, + "loss": 0.4754, + "step": 4159 + }, + { + "epoch": 0.35, + "learning_rate": 1.4961685506149608e-05, + "loss": 0.4874, + "step": 4160 + }, + { + "epoch": 0.35, + "learning_rate": 1.4959287626127175e-05, + "loss": 0.4878, + "step": 4161 + }, + { + "epoch": 0.35, + "learning_rate": 1.4956889367888765e-05, + "loss": 0.4681, + "step": 4162 + }, + { + "epoch": 0.35, + "learning_rate": 1.4954490731617278e-05, + "loss": 0.5002, + "step": 4163 + }, + { + "epoch": 0.36, + "learning_rate": 1.495209171749564e-05, + "loss": 0.4852, + "step": 4164 + }, + { + "epoch": 0.36, + "learning_rate": 1.4949692325706818e-05, + "loss": 0.4698, + "step": 4165 + }, + { + "epoch": 0.36, + "learning_rate": 1.494729255643379e-05, + "loss": 0.4824, + "step": 4166 + }, + { + "epoch": 0.36, + "learning_rate": 1.4944892409859581e-05, + "loss": 0.4883, + "step": 4167 + }, + { + "epoch": 0.36, + "learning_rate": 1.494249188616723e-05, + "loss": 0.4721, + "step": 4168 + }, + { + "epoch": 0.36, + "learning_rate": 1.4940090985539818e-05, + "loss": 0.4776, + "step": 4169 + }, + { + "epoch": 0.36, + "learning_rate": 1.4937689708160434e-05, + "loss": 0.502, + "step": 4170 + }, + { + "epoch": 0.36, + "learning_rate": 1.4935288054212228e-05, + "loss": 0.4907, + "step": 4171 + }, + { + "epoch": 0.36, + "learning_rate": 1.4932886023878346e-05, + "loss": 0.4949, + "step": 4172 + }, + { + "epoch": 0.36, + "learning_rate": 1.4930483617341982e-05, + "loss": 0.4996, + "step": 4173 + }, + { + "epoch": 0.36, + "learning_rate": 1.4928080834786356e-05, + "loss": 0.4723, + "step": 4174 + }, + { + "epoch": 0.36, + "learning_rate": 1.492567767639471e-05, + "loss": 0.4853, + "step": 4175 + }, + { + "epoch": 0.36, + "learning_rate": 1.492327414235032e-05, + "loss": 0.491, + "step": 4176 + }, + { + "epoch": 0.36, + "learning_rate": 1.4920870232836487e-05, + "loss": 0.5252, + "step": 4177 + }, + { + "epoch": 0.36, + "learning_rate": 1.491846594803655e-05, + "loss": 0.4961, + "step": 4178 + }, + { + "epoch": 0.36, + "learning_rate": 1.4916061288133862e-05, + "loss": 0.5273, + "step": 4179 + }, + { + "epoch": 0.36, + "learning_rate": 1.491365625331182e-05, + "loss": 0.4707, + "step": 4180 + }, + { + "epoch": 0.36, + "learning_rate": 1.4911250843753838e-05, + "loss": 0.4858, + "step": 4181 + }, + { + "epoch": 0.36, + "learning_rate": 1.490884505964336e-05, + "loss": 0.482, + "step": 4182 + }, + { + "epoch": 0.36, + "learning_rate": 1.490643890116387e-05, + "loss": 0.4765, + "step": 4183 + }, + { + "epoch": 0.36, + "learning_rate": 1.4904032368498857e-05, + "loss": 0.4932, + "step": 4184 + }, + { + "epoch": 0.36, + "learning_rate": 1.4901625461831868e-05, + "loss": 0.4823, + "step": 4185 + }, + { + "epoch": 0.36, + "learning_rate": 1.4899218181346453e-05, + "loss": 0.5056, + "step": 4186 + }, + { + "epoch": 0.36, + "learning_rate": 1.489681052722621e-05, + "loss": 0.4649, + "step": 4187 + }, + { + "epoch": 0.36, + "learning_rate": 1.489440249965475e-05, + "loss": 0.4853, + "step": 4188 + }, + { + "epoch": 0.36, + "learning_rate": 1.4891994098815725e-05, + "loss": 0.5137, + "step": 4189 + }, + { + "epoch": 0.36, + "learning_rate": 1.4889585324892803e-05, + "loss": 0.4911, + "step": 4190 + }, + { + "epoch": 0.36, + "learning_rate": 1.4887176178069693e-05, + "loss": 0.4914, + "step": 4191 + }, + { + "epoch": 0.36, + "learning_rate": 1.4884766658530126e-05, + "loss": 0.4816, + "step": 4192 + }, + { + "epoch": 0.36, + "learning_rate": 1.4882356766457857e-05, + "loss": 0.5093, + "step": 4193 + }, + { + "epoch": 0.36, + "learning_rate": 1.4879946502036677e-05, + "loss": 0.4758, + "step": 4194 + }, + { + "epoch": 0.36, + "learning_rate": 1.4877535865450405e-05, + "loss": 0.4775, + "step": 4195 + }, + { + "epoch": 0.36, + "learning_rate": 1.4875124856882885e-05, + "loss": 0.4707, + "step": 4196 + }, + { + "epoch": 0.36, + "learning_rate": 1.4872713476517993e-05, + "loss": 0.4757, + "step": 4197 + }, + { + "epoch": 0.36, + "learning_rate": 1.4870301724539627e-05, + "loss": 0.4965, + "step": 4198 + }, + { + "epoch": 0.36, + "learning_rate": 1.4867889601131716e-05, + "loss": 0.4694, + "step": 4199 + }, + { + "epoch": 0.36, + "learning_rate": 1.486547710647822e-05, + "loss": 0.4905, + "step": 4200 + }, + { + "epoch": 0.36, + "learning_rate": 1.4863064240763132e-05, + "loss": 0.4755, + "step": 4201 + }, + { + "epoch": 0.36, + "learning_rate": 1.486065100417046e-05, + "loss": 0.4777, + "step": 4202 + }, + { + "epoch": 0.36, + "learning_rate": 1.4858237396884249e-05, + "loss": 0.4904, + "step": 4203 + }, + { + "epoch": 0.36, + "learning_rate": 1.4855823419088576e-05, + "loss": 0.4618, + "step": 4204 + }, + { + "epoch": 0.36, + "learning_rate": 1.4853409070967528e-05, + "loss": 0.4889, + "step": 4205 + }, + { + "epoch": 0.36, + "learning_rate": 1.485099435270525e-05, + "loss": 0.5078, + "step": 4206 + }, + { + "epoch": 0.36, + "learning_rate": 1.4848579264485887e-05, + "loss": 0.5029, + "step": 4207 + }, + { + "epoch": 0.36, + "learning_rate": 1.4846163806493628e-05, + "loss": 0.4675, + "step": 4208 + }, + { + "epoch": 0.36, + "learning_rate": 1.4843747978912682e-05, + "loss": 0.5082, + "step": 4209 + }, + { + "epoch": 0.36, + "learning_rate": 1.4841331781927297e-05, + "loss": 0.4802, + "step": 4210 + }, + { + "epoch": 0.36, + "learning_rate": 1.4838915215721735e-05, + "loss": 0.5168, + "step": 4211 + }, + { + "epoch": 0.36, + "learning_rate": 1.48364982804803e-05, + "loss": 0.5006, + "step": 4212 + }, + { + "epoch": 0.36, + "learning_rate": 1.4834080976387316e-05, + "loss": 0.4968, + "step": 4213 + }, + { + "epoch": 0.36, + "learning_rate": 1.4831663303627128e-05, + "loss": 0.484, + "step": 4214 + }, + { + "epoch": 0.36, + "learning_rate": 1.482924526238413e-05, + "loss": 0.4848, + "step": 4215 + }, + { + "epoch": 0.36, + "learning_rate": 1.4826826852842725e-05, + "loss": 0.5118, + "step": 4216 + }, + { + "epoch": 0.36, + "learning_rate": 1.4824408075187352e-05, + "loss": 0.4698, + "step": 4217 + }, + { + "epoch": 0.36, + "learning_rate": 1.482198892960248e-05, + "loss": 0.4723, + "step": 4218 + }, + { + "epoch": 0.36, + "learning_rate": 1.4819569416272604e-05, + "loss": 0.4894, + "step": 4219 + }, + { + "epoch": 0.36, + "learning_rate": 1.4817149535382238e-05, + "loss": 0.4799, + "step": 4220 + }, + { + "epoch": 0.36, + "learning_rate": 1.481472928711594e-05, + "loss": 0.4946, + "step": 4221 + }, + { + "epoch": 0.36, + "learning_rate": 1.4812308671658285e-05, + "loss": 0.5066, + "step": 4222 + }, + { + "epoch": 0.36, + "learning_rate": 1.4809887689193878e-05, + "loss": 0.5022, + "step": 4223 + }, + { + "epoch": 0.36, + "learning_rate": 1.4807466339907358e-05, + "loss": 0.4772, + "step": 4224 + }, + { + "epoch": 0.36, + "learning_rate": 1.4805044623983382e-05, + "loss": 0.4973, + "step": 4225 + }, + { + "epoch": 0.36, + "learning_rate": 1.4802622541606644e-05, + "loss": 0.4783, + "step": 4226 + }, + { + "epoch": 0.36, + "learning_rate": 1.4800200092961859e-05, + "loss": 0.462, + "step": 4227 + }, + { + "epoch": 0.36, + "learning_rate": 1.4797777278233779e-05, + "loss": 0.4666, + "step": 4228 + }, + { + "epoch": 0.36, + "learning_rate": 1.4795354097607169e-05, + "loss": 0.4928, + "step": 4229 + }, + { + "epoch": 0.36, + "learning_rate": 1.4792930551266836e-05, + "loss": 0.4896, + "step": 4230 + }, + { + "epoch": 0.36, + "learning_rate": 1.4790506639397613e-05, + "loss": 0.4793, + "step": 4231 + }, + { + "epoch": 0.36, + "learning_rate": 1.4788082362184348e-05, + "loss": 0.5037, + "step": 4232 + }, + { + "epoch": 0.36, + "learning_rate": 1.4785657719811938e-05, + "loss": 0.4662, + "step": 4233 + }, + { + "epoch": 0.36, + "learning_rate": 1.4783232712465287e-05, + "loss": 0.4948, + "step": 4234 + }, + { + "epoch": 0.36, + "learning_rate": 1.4780807340329342e-05, + "loss": 0.4933, + "step": 4235 + }, + { + "epoch": 0.36, + "learning_rate": 1.477838160358907e-05, + "loss": 0.4839, + "step": 4236 + }, + { + "epoch": 0.36, + "learning_rate": 1.4775955502429467e-05, + "loss": 0.501, + "step": 4237 + }, + { + "epoch": 0.36, + "learning_rate": 1.477352903703556e-05, + "loss": 0.4713, + "step": 4238 + }, + { + "epoch": 0.36, + "learning_rate": 1.4771102207592395e-05, + "loss": 0.504, + "step": 4239 + }, + { + "epoch": 0.36, + "learning_rate": 1.4768675014285063e-05, + "loss": 0.4804, + "step": 4240 + }, + { + "epoch": 0.36, + "learning_rate": 1.4766247457298661e-05, + "loss": 0.516, + "step": 4241 + }, + { + "epoch": 0.36, + "learning_rate": 1.4763819536818331e-05, + "loss": 0.4655, + "step": 4242 + }, + { + "epoch": 0.36, + "learning_rate": 1.4761391253029236e-05, + "loss": 0.4868, + "step": 4243 + }, + { + "epoch": 0.36, + "learning_rate": 1.4758962606116565e-05, + "loss": 0.4729, + "step": 4244 + }, + { + "epoch": 0.36, + "learning_rate": 1.4756533596265538e-05, + "loss": 0.472, + "step": 4245 + }, + { + "epoch": 0.36, + "learning_rate": 1.47541042236614e-05, + "loss": 0.4785, + "step": 4246 + }, + { + "epoch": 0.36, + "learning_rate": 1.4751674488489427e-05, + "loss": 0.4747, + "step": 4247 + }, + { + "epoch": 0.36, + "learning_rate": 1.474924439093492e-05, + "loss": 0.4826, + "step": 4248 + }, + { + "epoch": 0.36, + "learning_rate": 1.4746813931183209e-05, + "loss": 0.4778, + "step": 4249 + }, + { + "epoch": 0.36, + "learning_rate": 1.4744383109419646e-05, + "loss": 0.5044, + "step": 4250 + }, + { + "epoch": 0.36, + "learning_rate": 1.4741951925829625e-05, + "loss": 0.4916, + "step": 4251 + }, + { + "epoch": 0.36, + "learning_rate": 1.473952038059855e-05, + "loss": 0.498, + "step": 4252 + }, + { + "epoch": 0.36, + "learning_rate": 1.4737088473911865e-05, + "loss": 0.4942, + "step": 4253 + }, + { + "epoch": 0.36, + "learning_rate": 1.4734656205955037e-05, + "loss": 0.4792, + "step": 4254 + }, + { + "epoch": 0.36, + "learning_rate": 1.473222357691356e-05, + "loss": 0.465, + "step": 4255 + }, + { + "epoch": 0.36, + "learning_rate": 1.4729790586972957e-05, + "loss": 0.4865, + "step": 4256 + }, + { + "epoch": 0.36, + "learning_rate": 1.4727357236318773e-05, + "loss": 0.4745, + "step": 4257 + }, + { + "epoch": 0.36, + "learning_rate": 1.4724923525136597e-05, + "loss": 0.4913, + "step": 4258 + }, + { + "epoch": 0.36, + "learning_rate": 1.4722489453612023e-05, + "loss": 0.4653, + "step": 4259 + }, + { + "epoch": 0.36, + "learning_rate": 1.4720055021930686e-05, + "loss": 0.4964, + "step": 4260 + }, + { + "epoch": 0.36, + "learning_rate": 1.4717620230278249e-05, + "loss": 0.4765, + "step": 4261 + }, + { + "epoch": 0.36, + "learning_rate": 1.4715185078840399e-05, + "loss": 0.514, + "step": 4262 + }, + { + "epoch": 0.36, + "learning_rate": 1.4712749567802849e-05, + "loss": 0.4778, + "step": 4263 + }, + { + "epoch": 0.36, + "learning_rate": 1.4710313697351342e-05, + "loss": 0.4844, + "step": 4264 + }, + { + "epoch": 0.36, + "learning_rate": 1.4707877467671648e-05, + "loss": 0.503, + "step": 4265 + }, + { + "epoch": 0.36, + "learning_rate": 1.470544087894956e-05, + "loss": 0.5028, + "step": 4266 + }, + { + "epoch": 0.36, + "learning_rate": 1.470300393137091e-05, + "loss": 0.5071, + "step": 4267 + }, + { + "epoch": 0.36, + "learning_rate": 1.4700566625121543e-05, + "loss": 0.4909, + "step": 4268 + }, + { + "epoch": 0.36, + "learning_rate": 1.469812896038734e-05, + "loss": 0.481, + "step": 4269 + }, + { + "epoch": 0.36, + "learning_rate": 1.4695690937354212e-05, + "loss": 0.5, + "step": 4270 + }, + { + "epoch": 0.36, + "learning_rate": 1.4693252556208089e-05, + "loss": 0.5149, + "step": 4271 + }, + { + "epoch": 0.36, + "learning_rate": 1.469081381713493e-05, + "loss": 0.4844, + "step": 4272 + }, + { + "epoch": 0.36, + "learning_rate": 1.4688374720320729e-05, + "loss": 0.4787, + "step": 4273 + }, + { + "epoch": 0.36, + "learning_rate": 1.4685935265951495e-05, + "loss": 0.4711, + "step": 4274 + }, + { + "epoch": 0.36, + "learning_rate": 1.4683495454213277e-05, + "loss": 0.4897, + "step": 4275 + }, + { + "epoch": 0.36, + "learning_rate": 1.4681055285292138e-05, + "loss": 0.5089, + "step": 4276 + }, + { + "epoch": 0.36, + "learning_rate": 1.4678614759374186e-05, + "loss": 0.4781, + "step": 4277 + }, + { + "epoch": 0.36, + "learning_rate": 1.4676173876645537e-05, + "loss": 0.5099, + "step": 4278 + }, + { + "epoch": 0.36, + "learning_rate": 1.4673732637292344e-05, + "loss": 0.4755, + "step": 4279 + }, + { + "epoch": 0.36, + "learning_rate": 1.4671291041500791e-05, + "loss": 0.4824, + "step": 4280 + }, + { + "epoch": 0.37, + "learning_rate": 1.466884908945708e-05, + "loss": 0.4791, + "step": 4281 + }, + { + "epoch": 0.37, + "learning_rate": 1.4666406781347443e-05, + "loss": 0.4878, + "step": 4282 + }, + { + "epoch": 0.37, + "learning_rate": 1.4663964117358147e-05, + "loss": 0.5064, + "step": 4283 + }, + { + "epoch": 0.37, + "learning_rate": 1.4661521097675478e-05, + "loss": 0.4797, + "step": 4284 + }, + { + "epoch": 0.37, + "learning_rate": 1.4659077722485741e-05, + "loss": 0.4636, + "step": 4285 + }, + { + "epoch": 0.37, + "learning_rate": 1.4656633991975294e-05, + "loss": 0.4779, + "step": 4286 + }, + { + "epoch": 0.37, + "learning_rate": 1.4654189906330491e-05, + "loss": 0.5072, + "step": 4287 + }, + { + "epoch": 0.37, + "learning_rate": 1.465174546573774e-05, + "loss": 0.4794, + "step": 4288 + }, + { + "epoch": 0.37, + "learning_rate": 1.4649300670383456e-05, + "loss": 0.4956, + "step": 4289 + }, + { + "epoch": 0.37, + "learning_rate": 1.4646855520454096e-05, + "loss": 0.4882, + "step": 4290 + }, + { + "epoch": 0.37, + "learning_rate": 1.4644410016136132e-05, + "loss": 0.4944, + "step": 4291 + }, + { + "epoch": 0.37, + "learning_rate": 1.4641964157616068e-05, + "loss": 0.47, + "step": 4292 + }, + { + "epoch": 0.37, + "learning_rate": 1.4639517945080444e-05, + "loss": 0.4619, + "step": 4293 + }, + { + "epoch": 0.37, + "learning_rate": 1.4637071378715807e-05, + "loss": 0.5072, + "step": 4294 + }, + { + "epoch": 0.37, + "learning_rate": 1.4634624458708749e-05, + "loss": 0.4646, + "step": 4295 + }, + { + "epoch": 0.37, + "learning_rate": 1.463217718524588e-05, + "loss": 0.4926, + "step": 4296 + }, + { + "epoch": 0.37, + "learning_rate": 1.4629729558513841e-05, + "loss": 0.4767, + "step": 4297 + }, + { + "epoch": 0.37, + "learning_rate": 1.4627281578699297e-05, + "loss": 0.4875, + "step": 4298 + }, + { + "epoch": 0.37, + "learning_rate": 1.462483324598894e-05, + "loss": 0.5112, + "step": 4299 + }, + { + "epoch": 0.37, + "learning_rate": 1.4622384560569493e-05, + "loss": 0.4949, + "step": 4300 + }, + { + "epoch": 0.37, + "learning_rate": 1.4619935522627702e-05, + "loss": 0.5029, + "step": 4301 + }, + { + "epoch": 0.37, + "learning_rate": 1.4617486132350343e-05, + "loss": 0.488, + "step": 4302 + }, + { + "epoch": 0.37, + "learning_rate": 1.4615036389924209e-05, + "loss": 0.475, + "step": 4303 + }, + { + "epoch": 0.37, + "learning_rate": 1.4612586295536136e-05, + "loss": 0.4874, + "step": 4304 + }, + { + "epoch": 0.37, + "learning_rate": 1.4610135849372972e-05, + "loss": 0.4854, + "step": 4305 + }, + { + "epoch": 0.37, + "learning_rate": 1.4607685051621603e-05, + "loss": 0.4774, + "step": 4306 + }, + { + "epoch": 0.37, + "learning_rate": 1.4605233902468939e-05, + "loss": 0.4818, + "step": 4307 + }, + { + "epoch": 0.37, + "learning_rate": 1.4602782402101908e-05, + "loss": 0.4863, + "step": 4308 + }, + { + "epoch": 0.37, + "learning_rate": 1.4600330550707473e-05, + "loss": 0.4921, + "step": 4309 + }, + { + "epoch": 0.37, + "learning_rate": 1.4597878348472625e-05, + "loss": 0.5017, + "step": 4310 + }, + { + "epoch": 0.37, + "learning_rate": 1.4595425795584384e-05, + "loss": 0.4833, + "step": 4311 + }, + { + "epoch": 0.37, + "learning_rate": 1.4592972892229779e-05, + "loss": 0.517, + "step": 4312 + }, + { + "epoch": 0.37, + "learning_rate": 1.4590519638595892e-05, + "loss": 0.5049, + "step": 4313 + }, + { + "epoch": 0.37, + "learning_rate": 1.458806603486981e-05, + "loss": 0.482, + "step": 4314 + }, + { + "epoch": 0.37, + "learning_rate": 1.4585612081238656e-05, + "loss": 0.4842, + "step": 4315 + }, + { + "epoch": 0.37, + "learning_rate": 1.4583157777889585e-05, + "loss": 0.4801, + "step": 4316 + }, + { + "epoch": 0.37, + "learning_rate": 1.4580703125009765e-05, + "loss": 0.4681, + "step": 4317 + }, + { + "epoch": 0.37, + "learning_rate": 1.4578248122786401e-05, + "loss": 0.5027, + "step": 4318 + }, + { + "epoch": 0.37, + "learning_rate": 1.4575792771406719e-05, + "loss": 0.4861, + "step": 4319 + }, + { + "epoch": 0.37, + "learning_rate": 1.457333707105798e-05, + "loss": 0.4941, + "step": 4320 + }, + { + "epoch": 0.37, + "learning_rate": 1.4570881021927461e-05, + "loss": 0.4864, + "step": 4321 + }, + { + "epoch": 0.37, + "learning_rate": 1.4568424624202475e-05, + "loss": 0.4937, + "step": 4322 + }, + { + "epoch": 0.37, + "learning_rate": 1.4565967878070351e-05, + "loss": 0.4825, + "step": 4323 + }, + { + "epoch": 0.37, + "learning_rate": 1.4563510783718457e-05, + "loss": 0.4843, + "step": 4324 + }, + { + "epoch": 0.37, + "learning_rate": 1.456105334133418e-05, + "loss": 0.476, + "step": 4325 + }, + { + "epoch": 0.37, + "learning_rate": 1.455859555110493e-05, + "loss": 0.4944, + "step": 4326 + }, + { + "epoch": 0.37, + "learning_rate": 1.4556137413218153e-05, + "loss": 0.4901, + "step": 4327 + }, + { + "epoch": 0.37, + "learning_rate": 1.4553678927861314e-05, + "loss": 0.4698, + "step": 4328 + }, + { + "epoch": 0.37, + "learning_rate": 1.4551220095221911e-05, + "loss": 0.4963, + "step": 4329 + }, + { + "epoch": 0.37, + "learning_rate": 1.4548760915487463e-05, + "loss": 0.4614, + "step": 4330 + }, + { + "epoch": 0.37, + "learning_rate": 1.4546301388845515e-05, + "loss": 0.4796, + "step": 4331 + }, + { + "epoch": 0.37, + "learning_rate": 1.4543841515483645e-05, + "loss": 0.4999, + "step": 4332 + }, + { + "epoch": 0.37, + "learning_rate": 1.454138129558945e-05, + "loss": 0.5036, + "step": 4333 + }, + { + "epoch": 0.37, + "learning_rate": 1.4538920729350559e-05, + "loss": 0.4533, + "step": 4334 + }, + { + "epoch": 0.37, + "learning_rate": 1.4536459816954623e-05, + "loss": 0.4986, + "step": 4335 + }, + { + "epoch": 0.37, + "learning_rate": 1.4533998558589319e-05, + "loss": 0.4806, + "step": 4336 + }, + { + "epoch": 0.37, + "learning_rate": 1.4531536954442363e-05, + "loss": 0.4931, + "step": 4337 + }, + { + "epoch": 0.37, + "learning_rate": 1.4529075004701474e-05, + "loss": 0.496, + "step": 4338 + }, + { + "epoch": 0.37, + "learning_rate": 1.452661270955442e-05, + "loss": 0.4814, + "step": 4339 + }, + { + "epoch": 0.37, + "learning_rate": 1.452415006918898e-05, + "loss": 0.4898, + "step": 4340 + }, + { + "epoch": 0.37, + "learning_rate": 1.452168708379297e-05, + "loss": 0.488, + "step": 4341 + }, + { + "epoch": 0.37, + "learning_rate": 1.4519223753554223e-05, + "loss": 0.5023, + "step": 4342 + }, + { + "epoch": 0.37, + "learning_rate": 1.451676007866061e-05, + "loss": 0.4861, + "step": 4343 + }, + { + "epoch": 0.37, + "learning_rate": 1.4514296059300014e-05, + "loss": 0.4874, + "step": 4344 + }, + { + "epoch": 0.37, + "learning_rate": 1.4511831695660354e-05, + "loss": 0.49, + "step": 4345 + }, + { + "epoch": 0.37, + "learning_rate": 1.4509366987929574e-05, + "loss": 0.4737, + "step": 4346 + }, + { + "epoch": 0.37, + "learning_rate": 1.4506901936295638e-05, + "loss": 0.4792, + "step": 4347 + }, + { + "epoch": 0.37, + "learning_rate": 1.4504436540946548e-05, + "loss": 0.4914, + "step": 4348 + }, + { + "epoch": 0.37, + "learning_rate": 1.450197080207032e-05, + "loss": 0.507, + "step": 4349 + }, + { + "epoch": 0.37, + "learning_rate": 1.4499504719855002e-05, + "loss": 0.4753, + "step": 4350 + }, + { + "epoch": 0.37, + "learning_rate": 1.449703829448867e-05, + "loss": 0.4912, + "step": 4351 + }, + { + "epoch": 0.37, + "learning_rate": 1.4494571526159427e-05, + "loss": 0.4964, + "step": 4352 + }, + { + "epoch": 0.37, + "learning_rate": 1.4492104415055393e-05, + "loss": 0.4775, + "step": 4353 + }, + { + "epoch": 0.37, + "learning_rate": 1.4489636961364719e-05, + "loss": 0.4802, + "step": 4354 + }, + { + "epoch": 0.37, + "learning_rate": 1.4487169165275592e-05, + "loss": 0.4754, + "step": 4355 + }, + { + "epoch": 0.37, + "learning_rate": 1.4484701026976207e-05, + "loss": 0.4595, + "step": 4356 + }, + { + "epoch": 0.37, + "learning_rate": 1.4482232546654799e-05, + "loss": 0.4892, + "step": 4357 + }, + { + "epoch": 0.37, + "learning_rate": 1.4479763724499627e-05, + "loss": 0.4908, + "step": 4358 + }, + { + "epoch": 0.37, + "learning_rate": 1.4477294560698968e-05, + "loss": 0.4801, + "step": 4359 + }, + { + "epoch": 0.37, + "learning_rate": 1.4474825055441135e-05, + "loss": 0.4719, + "step": 4360 + }, + { + "epoch": 0.37, + "learning_rate": 1.4472355208914462e-05, + "loss": 0.4755, + "step": 4361 + }, + { + "epoch": 0.37, + "learning_rate": 1.4469885021307308e-05, + "loss": 0.4928, + "step": 4362 + }, + { + "epoch": 0.37, + "learning_rate": 1.4467414492808061e-05, + "loss": 0.496, + "step": 4363 + }, + { + "epoch": 0.37, + "learning_rate": 1.4464943623605136e-05, + "loss": 0.4923, + "step": 4364 + }, + { + "epoch": 0.37, + "learning_rate": 1.4462472413886965e-05, + "loss": 0.4818, + "step": 4365 + }, + { + "epoch": 0.37, + "learning_rate": 1.4460000863842023e-05, + "loss": 0.4822, + "step": 4366 + }, + { + "epoch": 0.37, + "learning_rate": 1.4457528973658793e-05, + "loss": 0.4815, + "step": 4367 + }, + { + "epoch": 0.37, + "learning_rate": 1.4455056743525793e-05, + "loss": 0.492, + "step": 4368 + }, + { + "epoch": 0.37, + "learning_rate": 1.445258417363157e-05, + "loss": 0.4611, + "step": 4369 + }, + { + "epoch": 0.37, + "learning_rate": 1.4450111264164683e-05, + "loss": 0.4825, + "step": 4370 + }, + { + "epoch": 0.37, + "learning_rate": 1.4447638015313737e-05, + "loss": 0.4967, + "step": 4371 + }, + { + "epoch": 0.37, + "learning_rate": 1.4445164427267344e-05, + "loss": 0.528, + "step": 4372 + }, + { + "epoch": 0.37, + "learning_rate": 1.4442690500214158e-05, + "loss": 0.4656, + "step": 4373 + }, + { + "epoch": 0.37, + "learning_rate": 1.444021623434284e-05, + "loss": 0.4944, + "step": 4374 + }, + { + "epoch": 0.37, + "learning_rate": 1.4437741629842103e-05, + "loss": 0.4999, + "step": 4375 + }, + { + "epoch": 0.37, + "learning_rate": 1.443526668690066e-05, + "loss": 0.4789, + "step": 4376 + }, + { + "epoch": 0.37, + "learning_rate": 1.4432791405707257e-05, + "loss": 0.5054, + "step": 4377 + }, + { + "epoch": 0.37, + "learning_rate": 1.4430315786450683e-05, + "loss": 0.4885, + "step": 4378 + }, + { + "epoch": 0.37, + "learning_rate": 1.4427839829319728e-05, + "loss": 0.4687, + "step": 4379 + }, + { + "epoch": 0.37, + "learning_rate": 1.442536353450322e-05, + "loss": 0.5444, + "step": 4380 + }, + { + "epoch": 0.37, + "learning_rate": 1.4422886902190014e-05, + "loss": 0.494, + "step": 4381 + }, + { + "epoch": 0.37, + "learning_rate": 1.442040993256899e-05, + "loss": 0.4696, + "step": 4382 + }, + { + "epoch": 0.37, + "learning_rate": 1.4417932625829045e-05, + "loss": 0.5168, + "step": 4383 + }, + { + "epoch": 0.37, + "learning_rate": 1.4415454982159121e-05, + "loss": 0.5032, + "step": 4384 + }, + { + "epoch": 0.37, + "learning_rate": 1.4412977001748164e-05, + "loss": 0.4778, + "step": 4385 + }, + { + "epoch": 0.37, + "learning_rate": 1.4410498684785153e-05, + "loss": 0.4758, + "step": 4386 + }, + { + "epoch": 0.37, + "learning_rate": 1.4408020031459103e-05, + "loss": 0.4985, + "step": 4387 + }, + { + "epoch": 0.37, + "learning_rate": 1.440554104195904e-05, + "loss": 0.4866, + "step": 4388 + }, + { + "epoch": 0.37, + "learning_rate": 1.4403061716474026e-05, + "loss": 0.4645, + "step": 4389 + }, + { + "epoch": 0.37, + "learning_rate": 1.4400582055193143e-05, + "loss": 0.5033, + "step": 4390 + }, + { + "epoch": 0.37, + "learning_rate": 1.43981020583055e-05, + "loss": 0.503, + "step": 4391 + }, + { + "epoch": 0.37, + "learning_rate": 1.4395621726000232e-05, + "loss": 0.4919, + "step": 4392 + }, + { + "epoch": 0.37, + "learning_rate": 1.4393141058466502e-05, + "loss": 0.506, + "step": 4393 + }, + { + "epoch": 0.37, + "learning_rate": 1.4390660055893495e-05, + "loss": 0.4981, + "step": 4394 + }, + { + "epoch": 0.37, + "learning_rate": 1.4388178718470416e-05, + "loss": 0.4832, + "step": 4395 + }, + { + "epoch": 0.37, + "learning_rate": 1.4385697046386513e-05, + "loss": 0.4907, + "step": 4396 + }, + { + "epoch": 0.37, + "learning_rate": 1.4383215039831042e-05, + "loss": 0.5112, + "step": 4397 + }, + { + "epoch": 0.38, + "learning_rate": 1.4380732698993291e-05, + "loss": 0.4798, + "step": 4398 + }, + { + "epoch": 0.38, + "learning_rate": 1.4378250024062577e-05, + "loss": 0.4705, + "step": 4399 + }, + { + "epoch": 0.38, + "learning_rate": 1.437576701522824e-05, + "loss": 0.4889, + "step": 4400 + }, + { + "epoch": 0.38, + "learning_rate": 1.4373283672679638e-05, + "loss": 0.4848, + "step": 4401 + }, + { + "epoch": 0.38, + "learning_rate": 1.4370799996606169e-05, + "loss": 0.4846, + "step": 4402 + }, + { + "epoch": 0.38, + "learning_rate": 1.4368315987197244e-05, + "loss": 0.4869, + "step": 4403 + }, + { + "epoch": 0.38, + "learning_rate": 1.43658316446423e-05, + "loss": 0.4805, + "step": 4404 + }, + { + "epoch": 0.38, + "learning_rate": 1.4363346969130813e-05, + "loss": 0.4686, + "step": 4405 + }, + { + "epoch": 0.38, + "learning_rate": 1.4360861960852268e-05, + "loss": 0.4772, + "step": 4406 + }, + { + "epoch": 0.38, + "learning_rate": 1.4358376619996182e-05, + "loss": 0.4993, + "step": 4407 + }, + { + "epoch": 0.38, + "learning_rate": 1.4355890946752102e-05, + "loss": 0.4808, + "step": 4408 + }, + { + "epoch": 0.38, + "learning_rate": 1.4353404941309594e-05, + "loss": 0.4596, + "step": 4409 + }, + { + "epoch": 0.38, + "learning_rate": 1.4350918603858248e-05, + "loss": 0.4806, + "step": 4410 + }, + { + "epoch": 0.38, + "learning_rate": 1.4348431934587685e-05, + "loss": 0.4868, + "step": 4411 + }, + { + "epoch": 0.38, + "learning_rate": 1.4345944933687548e-05, + "loss": 0.4746, + "step": 4412 + }, + { + "epoch": 0.38, + "learning_rate": 1.4343457601347505e-05, + "loss": 0.4809, + "step": 4413 + }, + { + "epoch": 0.38, + "learning_rate": 1.4340969937757256e-05, + "loss": 0.499, + "step": 4414 + }, + { + "epoch": 0.38, + "learning_rate": 1.4338481943106516e-05, + "loss": 0.4808, + "step": 4415 + }, + { + "epoch": 0.38, + "learning_rate": 1.433599361758503e-05, + "loss": 0.4947, + "step": 4416 + }, + { + "epoch": 0.38, + "learning_rate": 1.4333504961382566e-05, + "loss": 0.4946, + "step": 4417 + }, + { + "epoch": 0.38, + "learning_rate": 1.4331015974688925e-05, + "loss": 0.4783, + "step": 4418 + }, + { + "epoch": 0.38, + "learning_rate": 1.4328526657693922e-05, + "loss": 0.4901, + "step": 4419 + }, + { + "epoch": 0.38, + "learning_rate": 1.4326037010587406e-05, + "loss": 0.4751, + "step": 4420 + }, + { + "epoch": 0.38, + "learning_rate": 1.4323547033559247e-05, + "loss": 0.4691, + "step": 4421 + }, + { + "epoch": 0.38, + "learning_rate": 1.4321056726799338e-05, + "loss": 0.4792, + "step": 4422 + }, + { + "epoch": 0.38, + "learning_rate": 1.4318566090497607e-05, + "loss": 0.4918, + "step": 4423 + }, + { + "epoch": 0.38, + "learning_rate": 1.4316075124843996e-05, + "loss": 0.4694, + "step": 4424 + }, + { + "epoch": 0.38, + "learning_rate": 1.4313583830028476e-05, + "loss": 0.4928, + "step": 4425 + }, + { + "epoch": 0.38, + "learning_rate": 1.4311092206241046e-05, + "loss": 0.506, + "step": 4426 + }, + { + "epoch": 0.38, + "learning_rate": 1.4308600253671725e-05, + "loss": 0.4898, + "step": 4427 + }, + { + "epoch": 0.38, + "learning_rate": 1.4306107972510559e-05, + "loss": 0.4629, + "step": 4428 + }, + { + "epoch": 0.38, + "learning_rate": 1.4303615362947623e-05, + "loss": 0.4889, + "step": 4429 + }, + { + "epoch": 0.38, + "learning_rate": 1.4301122425173014e-05, + "loss": 0.49, + "step": 4430 + }, + { + "epoch": 0.38, + "learning_rate": 1.4298629159376852e-05, + "loss": 0.4914, + "step": 4431 + }, + { + "epoch": 0.38, + "learning_rate": 1.429613556574928e-05, + "loss": 0.5174, + "step": 4432 + }, + { + "epoch": 0.38, + "learning_rate": 1.4293641644480478e-05, + "loss": 0.4693, + "step": 4433 + }, + { + "epoch": 0.38, + "learning_rate": 1.4291147395760637e-05, + "loss": 0.4629, + "step": 4434 + }, + { + "epoch": 0.38, + "learning_rate": 1.4288652819779982e-05, + "loss": 0.4888, + "step": 4435 + }, + { + "epoch": 0.38, + "learning_rate": 1.4286157916728756e-05, + "loss": 0.4962, + "step": 4436 + }, + { + "epoch": 0.38, + "learning_rate": 1.4283662686797236e-05, + "loss": 0.4732, + "step": 4437 + }, + { + "epoch": 0.38, + "learning_rate": 1.4281167130175712e-05, + "loss": 0.4731, + "step": 4438 + }, + { + "epoch": 0.38, + "learning_rate": 1.4278671247054511e-05, + "loss": 0.4913, + "step": 4439 + }, + { + "epoch": 0.38, + "learning_rate": 1.4276175037623981e-05, + "loss": 0.4853, + "step": 4440 + }, + { + "epoch": 0.38, + "learning_rate": 1.4273678502074487e-05, + "loss": 0.5042, + "step": 4441 + }, + { + "epoch": 0.38, + "learning_rate": 1.4271181640596428e-05, + "loss": 0.4729, + "step": 4442 + }, + { + "epoch": 0.38, + "learning_rate": 1.4268684453380227e-05, + "loss": 0.4701, + "step": 4443 + }, + { + "epoch": 0.38, + "learning_rate": 1.426618694061633e-05, + "loss": 0.4708, + "step": 4444 + }, + { + "epoch": 0.38, + "learning_rate": 1.42636891024952e-05, + "loss": 0.4743, + "step": 4445 + }, + { + "epoch": 0.38, + "learning_rate": 1.4261190939207343e-05, + "loss": 0.4837, + "step": 4446 + }, + { + "epoch": 0.38, + "learning_rate": 1.4258692450943276e-05, + "loss": 0.4758, + "step": 4447 + }, + { + "epoch": 0.38, + "learning_rate": 1.425619363789354e-05, + "loss": 0.5049, + "step": 4448 + }, + { + "epoch": 0.38, + "learning_rate": 1.4253694500248711e-05, + "loss": 0.4891, + "step": 4449 + }, + { + "epoch": 0.38, + "learning_rate": 1.425119503819938e-05, + "loss": 0.4915, + "step": 4450 + }, + { + "epoch": 0.38, + "learning_rate": 1.4248695251936167e-05, + "loss": 0.4923, + "step": 4451 + }, + { + "epoch": 0.38, + "learning_rate": 1.4246195141649715e-05, + "loss": 0.5001, + "step": 4452 + }, + { + "epoch": 0.38, + "learning_rate": 1.4243694707530696e-05, + "loss": 0.4767, + "step": 4453 + }, + { + "epoch": 0.38, + "learning_rate": 1.42411939497698e-05, + "loss": 0.478, + "step": 4454 + }, + { + "epoch": 0.38, + "learning_rate": 1.4238692868557748e-05, + "loss": 0.506, + "step": 4455 + }, + { + "epoch": 0.38, + "learning_rate": 1.4236191464085286e-05, + "loss": 0.4902, + "step": 4456 + }, + { + "epoch": 0.38, + "learning_rate": 1.4233689736543168e-05, + "loss": 0.4871, + "step": 4457 + }, + { + "epoch": 0.38, + "learning_rate": 1.4231187686122203e-05, + "loss": 0.4949, + "step": 4458 + }, + { + "epoch": 0.38, + "learning_rate": 1.4228685313013198e-05, + "loss": 0.4835, + "step": 4459 + }, + { + "epoch": 0.38, + "learning_rate": 1.4226182617406996e-05, + "loss": 0.4832, + "step": 4460 + }, + { + "epoch": 0.38, + "learning_rate": 1.4223679599494465e-05, + "loss": 0.4844, + "step": 4461 + }, + { + "epoch": 0.38, + "learning_rate": 1.4221176259466493e-05, + "loss": 0.4952, + "step": 4462 + }, + { + "epoch": 0.38, + "learning_rate": 1.4218672597513999e-05, + "loss": 0.473, + "step": 4463 + }, + { + "epoch": 0.38, + "learning_rate": 1.4216168613827918e-05, + "loss": 0.488, + "step": 4464 + }, + { + "epoch": 0.38, + "learning_rate": 1.421366430859922e-05, + "loss": 0.5054, + "step": 4465 + }, + { + "epoch": 0.38, + "learning_rate": 1.4211159682018884e-05, + "loss": 0.5021, + "step": 4466 + }, + { + "epoch": 0.38, + "learning_rate": 1.4208654734277936e-05, + "loss": 0.4831, + "step": 4467 + }, + { + "epoch": 0.38, + "learning_rate": 1.4206149465567402e-05, + "loss": 0.5069, + "step": 4468 + }, + { + "epoch": 0.38, + "learning_rate": 1.4203643876078354e-05, + "loss": 0.4841, + "step": 4469 + }, + { + "epoch": 0.38, + "learning_rate": 1.4201137966001874e-05, + "loss": 0.4932, + "step": 4470 + }, + { + "epoch": 0.38, + "learning_rate": 1.419863173552907e-05, + "loss": 0.4994, + "step": 4471 + }, + { + "epoch": 0.38, + "learning_rate": 1.4196125184851085e-05, + "loss": 0.4824, + "step": 4472 + }, + { + "epoch": 0.38, + "learning_rate": 1.4193618314159072e-05, + "loss": 0.4724, + "step": 4473 + }, + { + "epoch": 0.38, + "learning_rate": 1.419111112364422e-05, + "loss": 0.4785, + "step": 4474 + }, + { + "epoch": 0.38, + "learning_rate": 1.4188603613497735e-05, + "loss": 0.5023, + "step": 4475 + }, + { + "epoch": 0.38, + "learning_rate": 1.4186095783910854e-05, + "loss": 0.4858, + "step": 4476 + }, + { + "epoch": 0.38, + "learning_rate": 1.4183587635074831e-05, + "loss": 0.48, + "step": 4477 + }, + { + "epoch": 0.38, + "learning_rate": 1.4181079167180949e-05, + "loss": 0.5025, + "step": 4478 + }, + { + "epoch": 0.38, + "learning_rate": 1.4178570380420516e-05, + "loss": 0.4913, + "step": 4479 + }, + { + "epoch": 0.38, + "learning_rate": 1.4176061274984858e-05, + "loss": 0.4978, + "step": 4480 + }, + { + "epoch": 0.38, + "learning_rate": 1.4173551851065333e-05, + "loss": 0.4865, + "step": 4481 + }, + { + "epoch": 0.38, + "learning_rate": 1.4171042108853319e-05, + "loss": 0.4989, + "step": 4482 + }, + { + "epoch": 0.38, + "learning_rate": 1.4168532048540225e-05, + "loss": 0.5019, + "step": 4483 + }, + { + "epoch": 0.38, + "learning_rate": 1.4166021670317465e-05, + "loss": 0.5025, + "step": 4484 + }, + { + "epoch": 0.38, + "learning_rate": 1.4163510974376507e-05, + "loss": 0.4831, + "step": 4485 + }, + { + "epoch": 0.38, + "learning_rate": 1.4160999960908818e-05, + "loss": 0.4716, + "step": 4486 + }, + { + "epoch": 0.38, + "learning_rate": 1.4158488630105899e-05, + "loss": 0.5052, + "step": 4487 + }, + { + "epoch": 0.38, + "learning_rate": 1.415597698215928e-05, + "loss": 0.4896, + "step": 4488 + }, + { + "epoch": 0.38, + "learning_rate": 1.4153465017260504e-05, + "loss": 0.4702, + "step": 4489 + }, + { + "epoch": 0.38, + "learning_rate": 1.4150952735601143e-05, + "loss": 0.4665, + "step": 4490 + }, + { + "epoch": 0.38, + "learning_rate": 1.4148440137372799e-05, + "loss": 0.4865, + "step": 4491 + }, + { + "epoch": 0.38, + "learning_rate": 1.414592722276709e-05, + "loss": 0.494, + "step": 4492 + }, + { + "epoch": 0.38, + "learning_rate": 1.4143413991975663e-05, + "loss": 0.4633, + "step": 4493 + }, + { + "epoch": 0.38, + "learning_rate": 1.4140900445190187e-05, + "loss": 0.521, + "step": 4494 + }, + { + "epoch": 0.38, + "learning_rate": 1.4138386582602353e-05, + "loss": 0.4813, + "step": 4495 + }, + { + "epoch": 0.38, + "learning_rate": 1.4135872404403881e-05, + "loss": 0.4809, + "step": 4496 + }, + { + "epoch": 0.38, + "learning_rate": 1.4133357910786517e-05, + "loss": 0.4827, + "step": 4497 + }, + { + "epoch": 0.38, + "learning_rate": 1.4130843101942017e-05, + "loss": 0.4997, + "step": 4498 + }, + { + "epoch": 0.38, + "learning_rate": 1.412832797806218e-05, + "loss": 0.4967, + "step": 4499 + }, + { + "epoch": 0.38, + "learning_rate": 1.4125812539338814e-05, + "loss": 0.4881, + "step": 4500 + }, + { + "epoch": 0.38, + "learning_rate": 1.412329678596376e-05, + "loss": 0.4886, + "step": 4501 + }, + { + "epoch": 0.38, + "learning_rate": 1.4120780718128879e-05, + "loss": 0.4564, + "step": 4502 + }, + { + "epoch": 0.38, + "learning_rate": 1.4118264336026057e-05, + "loss": 0.4866, + "step": 4503 + }, + { + "epoch": 0.38, + "learning_rate": 1.4115747639847204e-05, + "loss": 0.4756, + "step": 4504 + }, + { + "epoch": 0.38, + "learning_rate": 1.411323062978425e-05, + "loss": 0.4915, + "step": 4505 + }, + { + "epoch": 0.38, + "learning_rate": 1.4110713306029161e-05, + "loss": 0.4586, + "step": 4506 + }, + { + "epoch": 0.38, + "learning_rate": 1.410819566877391e-05, + "loss": 0.4815, + "step": 4507 + }, + { + "epoch": 0.38, + "learning_rate": 1.4105677718210506e-05, + "loss": 0.4905, + "step": 4508 + }, + { + "epoch": 0.38, + "learning_rate": 1.4103159454530982e-05, + "loss": 0.4889, + "step": 4509 + }, + { + "epoch": 0.38, + "learning_rate": 1.4100640877927383e-05, + "loss": 0.4974, + "step": 4510 + }, + { + "epoch": 0.38, + "learning_rate": 1.4098121988591796e-05, + "loss": 0.4797, + "step": 4511 + }, + { + "epoch": 0.38, + "learning_rate": 1.4095602786716312e-05, + "loss": 0.482, + "step": 4512 + }, + { + "epoch": 0.38, + "learning_rate": 1.4093083272493061e-05, + "loss": 0.494, + "step": 4513 + }, + { + "epoch": 0.38, + "learning_rate": 1.4090563446114195e-05, + "loss": 0.5172, + "step": 4514 + }, + { + "epoch": 0.38, + "learning_rate": 1.4088043307771883e-05, + "loss": 0.486, + "step": 4515 + }, + { + "epoch": 0.39, + "learning_rate": 1.4085522857658321e-05, + "loss": 0.471, + "step": 4516 + }, + { + "epoch": 0.39, + "learning_rate": 1.4083002095965727e-05, + "loss": 0.4894, + "step": 4517 + }, + { + "epoch": 0.39, + "learning_rate": 1.4080481022886349e-05, + "loss": 0.491, + "step": 4518 + }, + { + "epoch": 0.39, + "learning_rate": 1.4077959638612451e-05, + "loss": 0.472, + "step": 4519 + }, + { + "epoch": 0.39, + "learning_rate": 1.4075437943336328e-05, + "loss": 0.4687, + "step": 4520 + }, + { + "epoch": 0.39, + "learning_rate": 1.4072915937250294e-05, + "loss": 0.5033, + "step": 4521 + }, + { + "epoch": 0.39, + "learning_rate": 1.4070393620546684e-05, + "loss": 0.4654, + "step": 4522 + }, + { + "epoch": 0.39, + "learning_rate": 1.4067870993417863e-05, + "loss": 0.5024, + "step": 4523 + }, + { + "epoch": 0.39, + "learning_rate": 1.4065348056056219e-05, + "loss": 0.4825, + "step": 4524 + }, + { + "epoch": 0.39, + "learning_rate": 1.4062824808654158e-05, + "loss": 0.4901, + "step": 4525 + }, + { + "epoch": 0.39, + "learning_rate": 1.4060301251404116e-05, + "loss": 0.4977, + "step": 4526 + }, + { + "epoch": 0.39, + "learning_rate": 1.4057777384498551e-05, + "loss": 0.4783, + "step": 4527 + }, + { + "epoch": 0.39, + "learning_rate": 1.405525320812994e-05, + "loss": 0.4708, + "step": 4528 + }, + { + "epoch": 0.39, + "learning_rate": 1.405272872249079e-05, + "loss": 0.4786, + "step": 4529 + }, + { + "epoch": 0.39, + "learning_rate": 1.4050203927773627e-05, + "loss": 0.4817, + "step": 4530 + }, + { + "epoch": 0.39, + "learning_rate": 1.4047678824171005e-05, + "loss": 0.4951, + "step": 4531 + }, + { + "epoch": 0.39, + "learning_rate": 1.4045153411875497e-05, + "loss": 0.4807, + "step": 4532 + }, + { + "epoch": 0.39, + "learning_rate": 1.4042627691079701e-05, + "loss": 0.4849, + "step": 4533 + }, + { + "epoch": 0.39, + "learning_rate": 1.4040101661976239e-05, + "loss": 0.5022, + "step": 4534 + }, + { + "epoch": 0.39, + "learning_rate": 1.4037575324757759e-05, + "loss": 0.4907, + "step": 4535 + }, + { + "epoch": 0.39, + "learning_rate": 1.403504867961693e-05, + "loss": 0.4671, + "step": 4536 + }, + { + "epoch": 0.39, + "learning_rate": 1.4032521726746438e-05, + "loss": 0.4994, + "step": 4537 + }, + { + "epoch": 0.39, + "learning_rate": 1.4029994466339007e-05, + "loss": 0.4623, + "step": 4538 + }, + { + "epoch": 0.39, + "learning_rate": 1.4027466898587375e-05, + "loss": 0.464, + "step": 4539 + }, + { + "epoch": 0.39, + "learning_rate": 1.4024939023684298e-05, + "loss": 0.5021, + "step": 4540 + }, + { + "epoch": 0.39, + "learning_rate": 1.4022410841822574e-05, + "loss": 0.4946, + "step": 4541 + }, + { + "epoch": 0.39, + "learning_rate": 1.4019882353195002e-05, + "loss": 0.4858, + "step": 4542 + }, + { + "epoch": 0.39, + "learning_rate": 1.401735355799442e-05, + "loss": 0.4913, + "step": 4543 + }, + { + "epoch": 0.39, + "learning_rate": 1.401482445641368e-05, + "loss": 0.4836, + "step": 4544 + }, + { + "epoch": 0.39, + "learning_rate": 1.4012295048645672e-05, + "loss": 0.4983, + "step": 4545 + }, + { + "epoch": 0.39, + "learning_rate": 1.4009765334883287e-05, + "loss": 0.4779, + "step": 4546 + }, + { + "epoch": 0.39, + "learning_rate": 1.4007235315319463e-05, + "loss": 0.4883, + "step": 4547 + }, + { + "epoch": 0.39, + "learning_rate": 1.4004704990147142e-05, + "loss": 0.4861, + "step": 4548 + }, + { + "epoch": 0.39, + "learning_rate": 1.4002174359559298e-05, + "loss": 0.4824, + "step": 4549 + }, + { + "epoch": 0.39, + "learning_rate": 1.399964342374893e-05, + "loss": 0.5008, + "step": 4550 + }, + { + "epoch": 0.39, + "learning_rate": 1.3997112182909053e-05, + "loss": 0.503, + "step": 4551 + }, + { + "epoch": 0.39, + "learning_rate": 1.3994580637232717e-05, + "loss": 0.5086, + "step": 4552 + }, + { + "epoch": 0.39, + "learning_rate": 1.3992048786912984e-05, + "loss": 0.4877, + "step": 4553 + }, + { + "epoch": 0.39, + "learning_rate": 1.3989516632142946e-05, + "loss": 0.4833, + "step": 4554 + }, + { + "epoch": 0.39, + "learning_rate": 1.3986984173115709e-05, + "loss": 0.4638, + "step": 4555 + }, + { + "epoch": 0.39, + "learning_rate": 1.398445141002442e-05, + "loss": 0.4678, + "step": 4556 + }, + { + "epoch": 0.39, + "learning_rate": 1.398191834306223e-05, + "loss": 0.4829, + "step": 4557 + }, + { + "epoch": 0.39, + "learning_rate": 1.397938497242232e-05, + "loss": 0.4961, + "step": 4558 + }, + { + "epoch": 0.39, + "learning_rate": 1.3976851298297902e-05, + "loss": 0.4826, + "step": 4559 + }, + { + "epoch": 0.39, + "learning_rate": 1.39743173208822e-05, + "loss": 0.4939, + "step": 4560 + }, + { + "epoch": 0.39, + "learning_rate": 1.3971783040368465e-05, + "loss": 0.4796, + "step": 4561 + }, + { + "epoch": 0.39, + "learning_rate": 1.3969248456949975e-05, + "loss": 0.4819, + "step": 4562 + }, + { + "epoch": 0.39, + "learning_rate": 1.3966713570820028e-05, + "loss": 0.4951, + "step": 4563 + }, + { + "epoch": 0.39, + "learning_rate": 1.3964178382171942e-05, + "loss": 0.4883, + "step": 4564 + }, + { + "epoch": 0.39, + "learning_rate": 1.3961642891199063e-05, + "loss": 0.4988, + "step": 4565 + }, + { + "epoch": 0.39, + "learning_rate": 1.3959107098094758e-05, + "loss": 0.4742, + "step": 4566 + }, + { + "epoch": 0.39, + "learning_rate": 1.3956571003052416e-05, + "loss": 0.474, + "step": 4567 + }, + { + "epoch": 0.39, + "learning_rate": 1.3954034606265452e-05, + "loss": 0.4725, + "step": 4568 + }, + { + "epoch": 0.39, + "learning_rate": 1.39514979079273e-05, + "loss": 0.488, + "step": 4569 + }, + { + "epoch": 0.39, + "learning_rate": 1.3948960908231422e-05, + "loss": 0.493, + "step": 4570 + }, + { + "epoch": 0.39, + "learning_rate": 1.3946423607371298e-05, + "loss": 0.4928, + "step": 4571 + }, + { + "epoch": 0.39, + "learning_rate": 1.3943886005540436e-05, + "loss": 0.4888, + "step": 4572 + }, + { + "epoch": 0.39, + "learning_rate": 1.394134810293236e-05, + "loss": 0.4999, + "step": 4573 + }, + { + "epoch": 0.39, + "learning_rate": 1.3938809899740622e-05, + "loss": 0.4565, + "step": 4574 + }, + { + "epoch": 0.39, + "learning_rate": 1.3936271396158798e-05, + "loss": 0.4858, + "step": 4575 + }, + { + "epoch": 0.39, + "learning_rate": 1.3933732592380485e-05, + "loss": 0.4879, + "step": 4576 + }, + { + "epoch": 0.39, + "learning_rate": 1.3931193488599301e-05, + "loss": 0.4873, + "step": 4577 + }, + { + "epoch": 0.39, + "learning_rate": 1.3928654085008887e-05, + "loss": 0.4896, + "step": 4578 + }, + { + "epoch": 0.39, + "learning_rate": 1.3926114381802915e-05, + "loss": 0.5055, + "step": 4579 + }, + { + "epoch": 0.39, + "learning_rate": 1.3923574379175068e-05, + "loss": 0.4847, + "step": 4580 + }, + { + "epoch": 0.39, + "learning_rate": 1.3921034077319057e-05, + "loss": 0.4963, + "step": 4581 + }, + { + "epoch": 0.39, + "learning_rate": 1.3918493476428618e-05, + "loss": 0.485, + "step": 4582 + }, + { + "epoch": 0.39, + "learning_rate": 1.3915952576697507e-05, + "loss": 0.4743, + "step": 4583 + }, + { + "epoch": 0.39, + "learning_rate": 1.3913411378319503e-05, + "loss": 0.4865, + "step": 4584 + }, + { + "epoch": 0.39, + "learning_rate": 1.391086988148841e-05, + "loss": 0.4739, + "step": 4585 + }, + { + "epoch": 0.39, + "learning_rate": 1.3908328086398055e-05, + "loss": 0.4952, + "step": 4586 + }, + { + "epoch": 0.39, + "learning_rate": 1.3905785993242283e-05, + "loss": 0.4671, + "step": 4587 + }, + { + "epoch": 0.39, + "learning_rate": 1.390324360221496e-05, + "loss": 0.4878, + "step": 4588 + }, + { + "epoch": 0.39, + "learning_rate": 1.3900700913509991e-05, + "loss": 0.4679, + "step": 4589 + }, + { + "epoch": 0.39, + "learning_rate": 1.3898157927321278e-05, + "loss": 0.4738, + "step": 4590 + }, + { + "epoch": 0.39, + "learning_rate": 1.3895614643842773e-05, + "loss": 0.5035, + "step": 4591 + }, + { + "epoch": 0.39, + "learning_rate": 1.3893071063268431e-05, + "loss": 0.4829, + "step": 4592 + }, + { + "epoch": 0.39, + "learning_rate": 1.3890527185792233e-05, + "loss": 0.4692, + "step": 4593 + }, + { + "epoch": 0.39, + "learning_rate": 1.3887983011608192e-05, + "loss": 0.4741, + "step": 4594 + }, + { + "epoch": 0.39, + "learning_rate": 1.3885438540910336e-05, + "loss": 0.4941, + "step": 4595 + }, + { + "epoch": 0.39, + "learning_rate": 1.3882893773892714e-05, + "loss": 0.4859, + "step": 4596 + }, + { + "epoch": 0.39, + "learning_rate": 1.3880348710749401e-05, + "loss": 0.4976, + "step": 4597 + }, + { + "epoch": 0.39, + "learning_rate": 1.3877803351674498e-05, + "loss": 0.4843, + "step": 4598 + }, + { + "epoch": 0.39, + "learning_rate": 1.3875257696862118e-05, + "loss": 0.4949, + "step": 4599 + }, + { + "epoch": 0.39, + "learning_rate": 1.3872711746506413e-05, + "loss": 0.4927, + "step": 4600 + }, + { + "epoch": 0.39, + "learning_rate": 1.3870165500801538e-05, + "loss": 0.4798, + "step": 4601 + }, + { + "epoch": 0.39, + "learning_rate": 1.3867618959941684e-05, + "loss": 0.4744, + "step": 4602 + }, + { + "epoch": 0.39, + "learning_rate": 1.3865072124121066e-05, + "loss": 0.4687, + "step": 4603 + }, + { + "epoch": 0.39, + "learning_rate": 1.3862524993533908e-05, + "loss": 0.5137, + "step": 4604 + }, + { + "epoch": 0.39, + "learning_rate": 1.3859977568374468e-05, + "loss": 0.4756, + "step": 4605 + }, + { + "epoch": 0.39, + "learning_rate": 1.3857429848837022e-05, + "loss": 0.4753, + "step": 4606 + }, + { + "epoch": 0.39, + "learning_rate": 1.3854881835115878e-05, + "loss": 0.4987, + "step": 4607 + }, + { + "epoch": 0.39, + "learning_rate": 1.3852333527405346e-05, + "loss": 0.4734, + "step": 4608 + }, + { + "epoch": 0.39, + "learning_rate": 1.3849784925899779e-05, + "loss": 0.4808, + "step": 4609 + }, + { + "epoch": 0.39, + "learning_rate": 1.3847236030793538e-05, + "loss": 0.4817, + "step": 4610 + }, + { + "epoch": 0.39, + "learning_rate": 1.384468684228102e-05, + "loss": 0.474, + "step": 4611 + }, + { + "epoch": 0.39, + "learning_rate": 1.3842137360556629e-05, + "loss": 0.5033, + "step": 4612 + }, + { + "epoch": 0.39, + "learning_rate": 1.3839587585814801e-05, + "loss": 0.4827, + "step": 4613 + }, + { + "epoch": 0.39, + "learning_rate": 1.3837037518249998e-05, + "loss": 0.4837, + "step": 4614 + }, + { + "epoch": 0.39, + "learning_rate": 1.3834487158056692e-05, + "loss": 0.5046, + "step": 4615 + }, + { + "epoch": 0.39, + "learning_rate": 1.383193650542939e-05, + "loss": 0.4856, + "step": 4616 + }, + { + "epoch": 0.39, + "learning_rate": 1.3829385560562607e-05, + "loss": 0.4951, + "step": 4617 + }, + { + "epoch": 0.39, + "learning_rate": 1.3826834323650899e-05, + "loss": 0.4891, + "step": 4618 + }, + { + "epoch": 0.39, + "learning_rate": 1.3824282794888828e-05, + "loss": 0.4747, + "step": 4619 + }, + { + "epoch": 0.39, + "learning_rate": 1.3821730974470981e-05, + "loss": 0.4878, + "step": 4620 + }, + { + "epoch": 0.39, + "learning_rate": 1.3819178862591982e-05, + "loss": 0.4925, + "step": 4621 + }, + { + "epoch": 0.39, + "learning_rate": 1.3816626459446451e-05, + "loss": 0.4945, + "step": 4622 + }, + { + "epoch": 0.39, + "learning_rate": 1.3814073765229056e-05, + "loss": 0.5084, + "step": 4623 + }, + { + "epoch": 0.39, + "learning_rate": 1.3811520780134471e-05, + "loss": 0.4922, + "step": 4624 + }, + { + "epoch": 0.39, + "learning_rate": 1.3808967504357402e-05, + "loss": 0.4896, + "step": 4625 + }, + { + "epoch": 0.39, + "learning_rate": 1.3806413938092566e-05, + "loss": 0.4777, + "step": 4626 + }, + { + "epoch": 0.39, + "learning_rate": 1.380386008153471e-05, + "loss": 0.4813, + "step": 4627 + }, + { + "epoch": 0.39, + "learning_rate": 1.3801305934878609e-05, + "loss": 0.4933, + "step": 4628 + }, + { + "epoch": 0.39, + "learning_rate": 1.379875149831904e-05, + "loss": 0.46, + "step": 4629 + }, + { + "epoch": 0.39, + "learning_rate": 1.3796196772050829e-05, + "loss": 0.4775, + "step": 4630 + }, + { + "epoch": 0.39, + "learning_rate": 1.3793641756268801e-05, + "loss": 0.4932, + "step": 4631 + }, + { + "epoch": 0.39, + "learning_rate": 1.3791086451167814e-05, + "loss": 0.4951, + "step": 4632 + }, + { + "epoch": 0.4, + "learning_rate": 1.3788530856942747e-05, + "loss": 0.4785, + "step": 4633 + }, + { + "epoch": 0.4, + "learning_rate": 1.3785974973788506e-05, + "loss": 0.4758, + "step": 4634 + }, + { + "epoch": 0.4, + "learning_rate": 1.3783418801900001e-05, + "loss": 0.5045, + "step": 4635 + }, + { + "epoch": 0.4, + "learning_rate": 1.3780862341472183e-05, + "loss": 0.4925, + "step": 4636 + }, + { + "epoch": 0.4, + "learning_rate": 1.3778305592700023e-05, + "loss": 0.4801, + "step": 4637 + }, + { + "epoch": 0.4, + "learning_rate": 1.3775748555778497e-05, + "loss": 0.4856, + "step": 4638 + }, + { + "epoch": 0.4, + "learning_rate": 1.3773191230902629e-05, + "loss": 0.4821, + "step": 4639 + }, + { + "epoch": 0.4, + "learning_rate": 1.3770633618267444e-05, + "loss": 0.4846, + "step": 4640 + }, + { + "epoch": 0.4, + "learning_rate": 1.3768075718067994e-05, + "loss": 0.4872, + "step": 4641 + }, + { + "epoch": 0.4, + "learning_rate": 1.3765517530499364e-05, + "loss": 0.4729, + "step": 4642 + }, + { + "epoch": 0.4, + "learning_rate": 1.3762959055756643e-05, + "loss": 0.4919, + "step": 4643 + }, + { + "epoch": 0.4, + "learning_rate": 1.3760400294034955e-05, + "loss": 0.4789, + "step": 4644 + }, + { + "epoch": 0.4, + "learning_rate": 1.3757841245529442e-05, + "loss": 0.4812, + "step": 4645 + }, + { + "epoch": 0.4, + "learning_rate": 1.3755281910435267e-05, + "loss": 0.4775, + "step": 4646 + }, + { + "epoch": 0.4, + "learning_rate": 1.3752722288947614e-05, + "loss": 0.4804, + "step": 4647 + }, + { + "epoch": 0.4, + "learning_rate": 1.3750162381261693e-05, + "loss": 0.4776, + "step": 4648 + }, + { + "epoch": 0.4, + "learning_rate": 1.3747602187572733e-05, + "loss": 0.4899, + "step": 4649 + }, + { + "epoch": 0.4, + "learning_rate": 1.3745041708075983e-05, + "loss": 0.5036, + "step": 4650 + }, + { + "epoch": 0.4, + "learning_rate": 1.3742480942966721e-05, + "loss": 0.4822, + "step": 4651 + }, + { + "epoch": 0.4, + "learning_rate": 1.3739919892440234e-05, + "loss": 0.4994, + "step": 4652 + }, + { + "epoch": 0.4, + "learning_rate": 1.3737358556691844e-05, + "loss": 0.4821, + "step": 4653 + }, + { + "epoch": 0.4, + "learning_rate": 1.3734796935916888e-05, + "loss": 0.4936, + "step": 4654 + }, + { + "epoch": 0.4, + "learning_rate": 1.3732235030310723e-05, + "loss": 0.4762, + "step": 4655 + }, + { + "epoch": 0.4, + "learning_rate": 1.3729672840068732e-05, + "loss": 0.4906, + "step": 4656 + }, + { + "epoch": 0.4, + "learning_rate": 1.3727110365386325e-05, + "loss": 0.4862, + "step": 4657 + }, + { + "epoch": 0.4, + "learning_rate": 1.3724547606458918e-05, + "loss": 0.4998, + "step": 4658 + }, + { + "epoch": 0.4, + "learning_rate": 1.3721984563481961e-05, + "loss": 0.5129, + "step": 4659 + }, + { + "epoch": 0.4, + "learning_rate": 1.3719421236650923e-05, + "loss": 0.4934, + "step": 4660 + }, + { + "epoch": 0.4, + "learning_rate": 1.3716857626161293e-05, + "loss": 0.4804, + "step": 4661 + }, + { + "epoch": 0.4, + "learning_rate": 1.3714293732208583e-05, + "loss": 0.4829, + "step": 4662 + }, + { + "epoch": 0.4, + "learning_rate": 1.3711729554988324e-05, + "loss": 0.4839, + "step": 4663 + }, + { + "epoch": 0.4, + "learning_rate": 1.3709165094696074e-05, + "loss": 0.4825, + "step": 4664 + }, + { + "epoch": 0.4, + "learning_rate": 1.3706600351527413e-05, + "loss": 0.4808, + "step": 4665 + }, + { + "epoch": 0.4, + "learning_rate": 1.3704035325677931e-05, + "loss": 0.4916, + "step": 4666 + }, + { + "epoch": 0.4, + "learning_rate": 1.370147001734325e-05, + "loss": 0.4924, + "step": 4667 + }, + { + "epoch": 0.4, + "learning_rate": 1.3698904426719015e-05, + "loss": 0.4743, + "step": 4668 + }, + { + "epoch": 0.4, + "learning_rate": 1.3696338554000885e-05, + "loss": 0.4799, + "step": 4669 + }, + { + "epoch": 0.4, + "learning_rate": 1.3693772399384547e-05, + "loss": 0.4681, + "step": 4670 + }, + { + "epoch": 0.4, + "learning_rate": 1.3691205963065701e-05, + "loss": 0.4699, + "step": 4671 + }, + { + "epoch": 0.4, + "learning_rate": 1.3688639245240078e-05, + "loss": 0.4747, + "step": 4672 + }, + { + "epoch": 0.4, + "learning_rate": 1.368607224610343e-05, + "loss": 0.5214, + "step": 4673 + }, + { + "epoch": 0.4, + "learning_rate": 1.3683504965851522e-05, + "loss": 0.4757, + "step": 4674 + }, + { + "epoch": 0.4, + "learning_rate": 1.3680937404680147e-05, + "loss": 0.4878, + "step": 4675 + }, + { + "epoch": 0.4, + "learning_rate": 1.3678369562785119e-05, + "loss": 0.4967, + "step": 4676 + }, + { + "epoch": 0.4, + "learning_rate": 1.3675801440362268e-05, + "loss": 0.4559, + "step": 4677 + }, + { + "epoch": 0.4, + "learning_rate": 1.3673233037607458e-05, + "loss": 0.4987, + "step": 4678 + }, + { + "epoch": 0.4, + "learning_rate": 1.3670664354716555e-05, + "loss": 0.4713, + "step": 4679 + }, + { + "epoch": 0.4, + "learning_rate": 1.3668095391885472e-05, + "loss": 0.5082, + "step": 4680 + }, + { + "epoch": 0.4, + "learning_rate": 1.3665526149310115e-05, + "loss": 0.4795, + "step": 4681 + }, + { + "epoch": 0.4, + "learning_rate": 1.3662956627186433e-05, + "loss": 0.4983, + "step": 4682 + }, + { + "epoch": 0.4, + "learning_rate": 1.3660386825710386e-05, + "loss": 0.4861, + "step": 4683 + }, + { + "epoch": 0.4, + "learning_rate": 1.3657816745077957e-05, + "loss": 0.4826, + "step": 4684 + }, + { + "epoch": 0.4, + "learning_rate": 1.365524638548515e-05, + "loss": 0.5044, + "step": 4685 + }, + { + "epoch": 0.4, + "learning_rate": 1.3652675747127995e-05, + "loss": 0.4642, + "step": 4686 + }, + { + "epoch": 0.4, + "learning_rate": 1.3650104830202542e-05, + "loss": 0.4712, + "step": 4687 + }, + { + "epoch": 0.4, + "learning_rate": 1.364753363490485e-05, + "loss": 0.4839, + "step": 4688 + }, + { + "epoch": 0.4, + "learning_rate": 1.3644962161431019e-05, + "loss": 0.4715, + "step": 4689 + }, + { + "epoch": 0.4, + "learning_rate": 1.3642390409977156e-05, + "loss": 0.4653, + "step": 4690 + }, + { + "epoch": 0.4, + "learning_rate": 1.363981838073939e-05, + "loss": 0.5033, + "step": 4691 + }, + { + "epoch": 0.4, + "learning_rate": 1.3637246073913884e-05, + "loss": 0.47, + "step": 4692 + }, + { + "epoch": 0.4, + "learning_rate": 1.3634673489696804e-05, + "loss": 0.4855, + "step": 4693 + }, + { + "epoch": 0.4, + "learning_rate": 1.363210062828435e-05, + "loss": 0.4846, + "step": 4694 + }, + { + "epoch": 0.4, + "learning_rate": 1.3629527489872738e-05, + "loss": 0.4924, + "step": 4695 + }, + { + "epoch": 0.4, + "learning_rate": 1.362695407465821e-05, + "loss": 0.4836, + "step": 4696 + }, + { + "epoch": 0.4, + "learning_rate": 1.3624380382837017e-05, + "loss": 0.4953, + "step": 4697 + }, + { + "epoch": 0.4, + "learning_rate": 1.3621806414605447e-05, + "loss": 0.4961, + "step": 4698 + }, + { + "epoch": 0.4, + "learning_rate": 1.3619232170159803e-05, + "loss": 0.496, + "step": 4699 + }, + { + "epoch": 0.4, + "learning_rate": 1.3616657649696397e-05, + "loss": 0.4832, + "step": 4700 + }, + { + "epoch": 0.4, + "learning_rate": 1.3614082853411583e-05, + "loss": 0.4704, + "step": 4701 + }, + { + "epoch": 0.4, + "learning_rate": 1.3611507781501722e-05, + "loss": 0.5002, + "step": 4702 + }, + { + "epoch": 0.4, + "learning_rate": 1.36089324341632e-05, + "loss": 0.485, + "step": 4703 + }, + { + "epoch": 0.4, + "learning_rate": 1.3606356811592427e-05, + "loss": 0.5011, + "step": 4704 + }, + { + "epoch": 0.4, + "learning_rate": 1.3603780913985825e-05, + "loss": 0.4817, + "step": 4705 + }, + { + "epoch": 0.4, + "learning_rate": 1.3601204741539843e-05, + "loss": 0.487, + "step": 4706 + }, + { + "epoch": 0.4, + "learning_rate": 1.3598628294450954e-05, + "loss": 0.4934, + "step": 4707 + }, + { + "epoch": 0.4, + "learning_rate": 1.359605157291565e-05, + "loss": 0.5068, + "step": 4708 + }, + { + "epoch": 0.4, + "learning_rate": 1.3593474577130434e-05, + "loss": 0.4801, + "step": 4709 + }, + { + "epoch": 0.4, + "learning_rate": 1.359089730729185e-05, + "loss": 0.485, + "step": 4710 + }, + { + "epoch": 0.4, + "learning_rate": 1.3588319763596443e-05, + "loss": 0.4812, + "step": 4711 + }, + { + "epoch": 0.4, + "learning_rate": 1.3585741946240792e-05, + "loss": 0.5057, + "step": 4712 + }, + { + "epoch": 0.4, + "learning_rate": 1.358316385542149e-05, + "loss": 0.4811, + "step": 4713 + }, + { + "epoch": 0.4, + "learning_rate": 1.3580585491335151e-05, + "loss": 0.5072, + "step": 4714 + }, + { + "epoch": 0.4, + "learning_rate": 1.3578006854178416e-05, + "loss": 0.4764, + "step": 4715 + }, + { + "epoch": 0.4, + "learning_rate": 1.3575427944147939e-05, + "loss": 0.4638, + "step": 4716 + }, + { + "epoch": 0.4, + "learning_rate": 1.3572848761440403e-05, + "loss": 0.5027, + "step": 4717 + }, + { + "epoch": 0.4, + "learning_rate": 1.3570269306252499e-05, + "loss": 0.4849, + "step": 4718 + }, + { + "epoch": 0.4, + "learning_rate": 1.3567689578780957e-05, + "loss": 0.4879, + "step": 4719 + }, + { + "epoch": 0.4, + "learning_rate": 1.3565109579222511e-05, + "loss": 0.4813, + "step": 4720 + }, + { + "epoch": 0.4, + "learning_rate": 1.3562529307773926e-05, + "loss": 0.4957, + "step": 4721 + }, + { + "epoch": 0.4, + "learning_rate": 1.3559948764631983e-05, + "loss": 0.5002, + "step": 4722 + }, + { + "epoch": 0.4, + "learning_rate": 1.3557367949993483e-05, + "loss": 0.5072, + "step": 4723 + }, + { + "epoch": 0.4, + "learning_rate": 1.3554786864055251e-05, + "loss": 0.501, + "step": 4724 + }, + { + "epoch": 0.4, + "learning_rate": 1.3552205507014133e-05, + "loss": 0.4712, + "step": 4725 + }, + { + "epoch": 0.4, + "learning_rate": 1.3549623879066996e-05, + "loss": 0.4742, + "step": 4726 + }, + { + "epoch": 0.4, + "learning_rate": 1.3547041980410717e-05, + "loss": 0.4639, + "step": 4727 + }, + { + "epoch": 0.4, + "learning_rate": 1.3544459811242212e-05, + "loss": 0.4974, + "step": 4728 + }, + { + "epoch": 0.4, + "learning_rate": 1.3541877371758405e-05, + "loss": 0.4975, + "step": 4729 + }, + { + "epoch": 0.4, + "learning_rate": 1.3539294662156239e-05, + "loss": 0.4945, + "step": 4730 + }, + { + "epoch": 0.4, + "learning_rate": 1.353671168263269e-05, + "loss": 0.4956, + "step": 4731 + }, + { + "epoch": 0.4, + "learning_rate": 1.3534128433384741e-05, + "loss": 0.4797, + "step": 4732 + }, + { + "epoch": 0.4, + "learning_rate": 1.3531544914609403e-05, + "loss": 0.4743, + "step": 4733 + }, + { + "epoch": 0.4, + "learning_rate": 1.3528961126503704e-05, + "loss": 0.4866, + "step": 4734 + }, + { + "epoch": 0.4, + "learning_rate": 1.35263770692647e-05, + "loss": 0.5015, + "step": 4735 + }, + { + "epoch": 0.4, + "learning_rate": 1.3523792743089457e-05, + "loss": 0.4637, + "step": 4736 + }, + { + "epoch": 0.4, + "learning_rate": 1.3521208148175067e-05, + "loss": 0.4894, + "step": 4737 + }, + { + "epoch": 0.4, + "learning_rate": 1.3518623284718644e-05, + "loss": 0.4783, + "step": 4738 + }, + { + "epoch": 0.4, + "learning_rate": 1.3516038152917319e-05, + "loss": 0.4791, + "step": 4739 + }, + { + "epoch": 0.4, + "learning_rate": 1.3513452752968248e-05, + "loss": 0.501, + "step": 4740 + }, + { + "epoch": 0.4, + "learning_rate": 1.3510867085068599e-05, + "loss": 0.4936, + "step": 4741 + }, + { + "epoch": 0.4, + "learning_rate": 1.350828114941557e-05, + "loss": 0.4751, + "step": 4742 + }, + { + "epoch": 0.4, + "learning_rate": 1.3505694946206374e-05, + "loss": 0.4832, + "step": 4743 + }, + { + "epoch": 0.4, + "learning_rate": 1.3503108475638244e-05, + "loss": 0.4969, + "step": 4744 + }, + { + "epoch": 0.4, + "learning_rate": 1.3500521737908439e-05, + "loss": 0.4877, + "step": 4745 + }, + { + "epoch": 0.4, + "learning_rate": 1.3497934733214231e-05, + "loss": 0.48, + "step": 4746 + }, + { + "epoch": 0.4, + "learning_rate": 1.3495347461752914e-05, + "loss": 0.4983, + "step": 4747 + }, + { + "epoch": 0.4, + "learning_rate": 1.349275992372181e-05, + "loss": 0.4647, + "step": 4748 + }, + { + "epoch": 0.4, + "learning_rate": 1.3490172119318252e-05, + "loss": 0.4772, + "step": 4749 + }, + { + "epoch": 0.41, + "learning_rate": 1.3487584048739598e-05, + "loss": 0.4758, + "step": 4750 + }, + { + "epoch": 0.41, + "learning_rate": 1.3484995712183222e-05, + "loss": 0.4814, + "step": 4751 + }, + { + "epoch": 0.41, + "learning_rate": 1.3482407109846527e-05, + "loss": 0.4819, + "step": 4752 + }, + { + "epoch": 0.41, + "learning_rate": 1.3479818241926921e-05, + "loss": 0.4744, + "step": 4753 + }, + { + "epoch": 0.41, + "learning_rate": 1.3477229108621855e-05, + "loss": 0.481, + "step": 4754 + }, + { + "epoch": 0.41, + "learning_rate": 1.3474639710128777e-05, + "loss": 0.4604, + "step": 4755 + }, + { + "epoch": 0.41, + "learning_rate": 1.3472050046645167e-05, + "loss": 0.4951, + "step": 4756 + }, + { + "epoch": 0.41, + "learning_rate": 1.3469460118368527e-05, + "loss": 0.4792, + "step": 4757 + }, + { + "epoch": 0.41, + "learning_rate": 1.3466869925496374e-05, + "loss": 0.5027, + "step": 4758 + }, + { + "epoch": 0.41, + "learning_rate": 1.3464279468226247e-05, + "loss": 0.4719, + "step": 4759 + }, + { + "epoch": 0.41, + "learning_rate": 1.3461688746755704e-05, + "loss": 0.4932, + "step": 4760 + }, + { + "epoch": 0.41, + "learning_rate": 1.3459097761282325e-05, + "loss": 0.4762, + "step": 4761 + }, + { + "epoch": 0.41, + "learning_rate": 1.3456506512003707e-05, + "loss": 0.4754, + "step": 4762 + }, + { + "epoch": 0.41, + "learning_rate": 1.3453914999117477e-05, + "loss": 0.4916, + "step": 4763 + }, + { + "epoch": 0.41, + "learning_rate": 1.3451323222821267e-05, + "loss": 0.4873, + "step": 4764 + }, + { + "epoch": 0.41, + "learning_rate": 1.3448731183312738e-05, + "loss": 0.4843, + "step": 4765 + }, + { + "epoch": 0.41, + "learning_rate": 1.3446138880789572e-05, + "loss": 0.4732, + "step": 4766 + }, + { + "epoch": 0.41, + "learning_rate": 1.344354631544947e-05, + "loss": 0.5267, + "step": 4767 + }, + { + "epoch": 0.41, + "learning_rate": 1.3440953487490145e-05, + "loss": 0.4614, + "step": 4768 + }, + { + "epoch": 0.41, + "learning_rate": 1.3438360397109345e-05, + "loss": 0.4992, + "step": 4769 + }, + { + "epoch": 0.41, + "learning_rate": 1.3435767044504826e-05, + "loss": 0.5083, + "step": 4770 + }, + { + "epoch": 0.41, + "learning_rate": 1.3433173429874367e-05, + "loss": 0.4868, + "step": 4771 + }, + { + "epoch": 0.41, + "learning_rate": 1.343057955341577e-05, + "loss": 0.4884, + "step": 4772 + }, + { + "epoch": 0.41, + "learning_rate": 1.3427985415326854e-05, + "loss": 0.4867, + "step": 4773 + }, + { + "epoch": 0.41, + "learning_rate": 1.3425391015805458e-05, + "loss": 0.4877, + "step": 4774 + }, + { + "epoch": 0.41, + "learning_rate": 1.3422796355049444e-05, + "loss": 0.4865, + "step": 4775 + }, + { + "epoch": 0.41, + "learning_rate": 1.342020143325669e-05, + "loss": 0.4749, + "step": 4776 + }, + { + "epoch": 0.41, + "learning_rate": 1.3417606250625096e-05, + "loss": 0.4847, + "step": 4777 + }, + { + "epoch": 0.41, + "learning_rate": 1.3415010807352578e-05, + "loss": 0.4661, + "step": 4778 + }, + { + "epoch": 0.41, + "learning_rate": 1.3412415103637081e-05, + "loss": 0.4953, + "step": 4779 + }, + { + "epoch": 0.41, + "learning_rate": 1.3409819139676562e-05, + "loss": 0.4864, + "step": 4780 + }, + { + "epoch": 0.41, + "learning_rate": 1.3407222915669e-05, + "loss": 0.4721, + "step": 4781 + }, + { + "epoch": 0.41, + "learning_rate": 1.3404626431812394e-05, + "loss": 0.4793, + "step": 4782 + }, + { + "epoch": 0.41, + "learning_rate": 1.340202968830476e-05, + "loss": 0.5013, + "step": 4783 + }, + { + "epoch": 0.41, + "learning_rate": 1.3399432685344143e-05, + "loss": 0.4808, + "step": 4784 + }, + { + "epoch": 0.41, + "learning_rate": 1.3396835423128596e-05, + "loss": 0.4715, + "step": 4785 + }, + { + "epoch": 0.41, + "learning_rate": 1.3394237901856195e-05, + "loss": 0.5003, + "step": 4786 + }, + { + "epoch": 0.41, + "learning_rate": 1.3391640121725043e-05, + "loss": 0.4803, + "step": 4787 + }, + { + "epoch": 0.41, + "learning_rate": 1.3389042082933257e-05, + "loss": 0.479, + "step": 4788 + }, + { + "epoch": 0.41, + "learning_rate": 1.3386443785678972e-05, + "loss": 0.4696, + "step": 4789 + }, + { + "epoch": 0.41, + "learning_rate": 1.3383845230160346e-05, + "loss": 0.4692, + "step": 4790 + }, + { + "epoch": 0.41, + "learning_rate": 1.3381246416575558e-05, + "loss": 0.4735, + "step": 4791 + }, + { + "epoch": 0.41, + "learning_rate": 1.3378647345122795e-05, + "loss": 0.4842, + "step": 4792 + }, + { + "epoch": 0.41, + "learning_rate": 1.3376048016000286e-05, + "loss": 0.4915, + "step": 4793 + }, + { + "epoch": 0.41, + "learning_rate": 1.3373448429406259e-05, + "loss": 0.4672, + "step": 4794 + }, + { + "epoch": 0.41, + "learning_rate": 1.337084858553897e-05, + "loss": 0.4895, + "step": 4795 + }, + { + "epoch": 0.41, + "learning_rate": 1.3368248484596697e-05, + "loss": 0.4942, + "step": 4796 + }, + { + "epoch": 0.41, + "learning_rate": 1.3365648126777733e-05, + "loss": 0.4899, + "step": 4797 + }, + { + "epoch": 0.41, + "learning_rate": 1.3363047512280391e-05, + "loss": 0.4797, + "step": 4798 + }, + { + "epoch": 0.41, + "learning_rate": 1.3360446641303004e-05, + "loss": 0.4788, + "step": 4799 + }, + { + "epoch": 0.41, + "learning_rate": 1.3357845514043927e-05, + "loss": 0.5046, + "step": 4800 + }, + { + "epoch": 0.41, + "learning_rate": 1.3355244130701532e-05, + "loss": 0.4787, + "step": 4801 + }, + { + "epoch": 0.41, + "learning_rate": 1.3352642491474215e-05, + "loss": 0.4841, + "step": 4802 + }, + { + "epoch": 0.41, + "learning_rate": 1.3350040596560382e-05, + "loss": 0.4767, + "step": 4803 + }, + { + "epoch": 0.41, + "learning_rate": 1.3347438446158467e-05, + "loss": 0.4893, + "step": 4804 + }, + { + "epoch": 0.41, + "learning_rate": 1.3344836040466923e-05, + "loss": 0.4539, + "step": 4805 + }, + { + "epoch": 0.41, + "learning_rate": 1.3342233379684217e-05, + "loss": 0.4858, + "step": 4806 + }, + { + "epoch": 0.41, + "learning_rate": 1.3339630464008838e-05, + "loss": 0.4907, + "step": 4807 + }, + { + "epoch": 0.41, + "learning_rate": 1.3337027293639303e-05, + "loss": 0.4691, + "step": 4808 + }, + { + "epoch": 0.41, + "learning_rate": 1.3334423868774128e-05, + "loss": 0.4868, + "step": 4809 + }, + { + "epoch": 0.41, + "learning_rate": 1.3331820189611872e-05, + "loss": 0.471, + "step": 4810 + }, + { + "epoch": 0.41, + "learning_rate": 1.33292162563511e-05, + "loss": 0.4988, + "step": 4811 + }, + { + "epoch": 0.41, + "learning_rate": 1.3326612069190394e-05, + "loss": 0.4863, + "step": 4812 + }, + { + "epoch": 0.41, + "learning_rate": 1.3324007628328363e-05, + "loss": 0.4908, + "step": 4813 + }, + { + "epoch": 0.41, + "learning_rate": 1.3321402933963637e-05, + "loss": 0.4609, + "step": 4814 + }, + { + "epoch": 0.41, + "learning_rate": 1.3318797986294854e-05, + "loss": 0.4997, + "step": 4815 + }, + { + "epoch": 0.41, + "learning_rate": 1.331619278552068e-05, + "loss": 0.4648, + "step": 4816 + }, + { + "epoch": 0.41, + "learning_rate": 1.33135873318398e-05, + "loss": 0.4772, + "step": 4817 + }, + { + "epoch": 0.41, + "learning_rate": 1.3310981625450915e-05, + "loss": 0.4835, + "step": 4818 + }, + { + "epoch": 0.41, + "learning_rate": 1.3308375666552752e-05, + "loss": 0.4796, + "step": 4819 + }, + { + "epoch": 0.41, + "learning_rate": 1.3305769455344049e-05, + "loss": 0.4776, + "step": 4820 + }, + { + "epoch": 0.41, + "learning_rate": 1.3303162992023562e-05, + "loss": 0.4811, + "step": 4821 + }, + { + "epoch": 0.41, + "learning_rate": 1.3300556276790078e-05, + "loss": 0.4979, + "step": 4822 + }, + { + "epoch": 0.41, + "learning_rate": 1.3297949309842393e-05, + "loss": 0.4752, + "step": 4823 + }, + { + "epoch": 0.41, + "learning_rate": 1.3295342091379322e-05, + "loss": 0.5128, + "step": 4824 + }, + { + "epoch": 0.41, + "learning_rate": 1.3292734621599708e-05, + "loss": 0.4985, + "step": 4825 + }, + { + "epoch": 0.41, + "learning_rate": 1.3290126900702403e-05, + "loss": 0.481, + "step": 4826 + }, + { + "epoch": 0.41, + "learning_rate": 1.3287518928886285e-05, + "loss": 0.4811, + "step": 4827 + }, + { + "epoch": 0.41, + "learning_rate": 1.3284910706350249e-05, + "loss": 0.4663, + "step": 4828 + }, + { + "epoch": 0.41, + "learning_rate": 1.3282302233293211e-05, + "loss": 0.4984, + "step": 4829 + }, + { + "epoch": 0.41, + "learning_rate": 1.32796935099141e-05, + "loss": 0.4642, + "step": 4830 + }, + { + "epoch": 0.41, + "learning_rate": 1.3277084536411869e-05, + "loss": 0.4886, + "step": 4831 + }, + { + "epoch": 0.41, + "learning_rate": 1.327447531298549e-05, + "loss": 0.491, + "step": 4832 + }, + { + "epoch": 0.41, + "learning_rate": 1.327186583983395e-05, + "loss": 0.4665, + "step": 4833 + }, + { + "epoch": 0.41, + "learning_rate": 1.326925611715627e-05, + "loss": 0.4761, + "step": 4834 + }, + { + "epoch": 0.41, + "learning_rate": 1.326664614515146e-05, + "loss": 0.4953, + "step": 4835 + }, + { + "epoch": 0.41, + "learning_rate": 1.3264035924018584e-05, + "loss": 0.4741, + "step": 4836 + }, + { + "epoch": 0.41, + "learning_rate": 1.3261425453956698e-05, + "loss": 0.4762, + "step": 4837 + }, + { + "epoch": 0.41, + "learning_rate": 1.3258814735164892e-05, + "loss": 0.481, + "step": 4838 + }, + { + "epoch": 0.41, + "learning_rate": 1.3256203767842268e-05, + "loss": 0.4811, + "step": 4839 + }, + { + "epoch": 0.41, + "learning_rate": 1.325359255218795e-05, + "loss": 0.4767, + "step": 4840 + }, + { + "epoch": 0.41, + "learning_rate": 1.3250981088401085e-05, + "loss": 0.493, + "step": 4841 + }, + { + "epoch": 0.41, + "learning_rate": 1.3248369376680824e-05, + "loss": 0.4946, + "step": 4842 + }, + { + "epoch": 0.41, + "learning_rate": 1.3245757417226356e-05, + "loss": 0.4695, + "step": 4843 + }, + { + "epoch": 0.41, + "learning_rate": 1.3243145210236876e-05, + "loss": 0.4697, + "step": 4844 + }, + { + "epoch": 0.41, + "learning_rate": 1.3240532755911603e-05, + "loss": 0.4853, + "step": 4845 + }, + { + "epoch": 0.41, + "learning_rate": 1.3237920054449775e-05, + "loss": 0.4571, + "step": 4846 + }, + { + "epoch": 0.41, + "learning_rate": 1.3235307106050644e-05, + "loss": 0.479, + "step": 4847 + }, + { + "epoch": 0.41, + "learning_rate": 1.3232693910913486e-05, + "loss": 0.487, + "step": 4848 + }, + { + "epoch": 0.41, + "learning_rate": 1.3230080469237592e-05, + "loss": 0.4722, + "step": 4849 + }, + { + "epoch": 0.41, + "learning_rate": 1.322746678122228e-05, + "loss": 0.5033, + "step": 4850 + }, + { + "epoch": 0.41, + "learning_rate": 1.322485284706687e-05, + "loss": 0.4904, + "step": 4851 + }, + { + "epoch": 0.41, + "learning_rate": 1.3222238666970728e-05, + "loss": 0.4878, + "step": 4852 + }, + { + "epoch": 0.41, + "learning_rate": 1.3219624241133211e-05, + "loss": 0.4579, + "step": 4853 + }, + { + "epoch": 0.41, + "learning_rate": 1.3217009569753702e-05, + "loss": 0.4701, + "step": 4854 + }, + { + "epoch": 0.41, + "learning_rate": 1.3214394653031616e-05, + "loss": 0.4777, + "step": 4855 + }, + { + "epoch": 0.41, + "learning_rate": 1.3211779491166375e-05, + "loss": 0.4997, + "step": 4856 + }, + { + "epoch": 0.41, + "learning_rate": 1.3209164084357423e-05, + "loss": 0.4786, + "step": 4857 + }, + { + "epoch": 0.41, + "learning_rate": 1.3206548432804213e-05, + "loss": 0.4865, + "step": 4858 + }, + { + "epoch": 0.41, + "learning_rate": 1.320393253670624e-05, + "loss": 0.4752, + "step": 4859 + }, + { + "epoch": 0.41, + "learning_rate": 1.3201316396262991e-05, + "loss": 0.4765, + "step": 4860 + }, + { + "epoch": 0.41, + "learning_rate": 1.319870001167399e-05, + "loss": 0.4651, + "step": 4861 + }, + { + "epoch": 0.41, + "learning_rate": 1.3196083383138776e-05, + "loss": 0.4694, + "step": 4862 + }, + { + "epoch": 0.41, + "learning_rate": 1.3193466510856894e-05, + "loss": 0.4818, + "step": 4863 + }, + { + "epoch": 0.41, + "learning_rate": 1.3190849395027926e-05, + "loss": 0.4908, + "step": 4864 + }, + { + "epoch": 0.41, + "learning_rate": 1.3188232035851463e-05, + "loss": 0.4895, + "step": 4865 + }, + { + "epoch": 0.41, + "learning_rate": 1.318561443352711e-05, + "loss": 0.4991, + "step": 4866 + }, + { + "epoch": 0.41, + "learning_rate": 1.3182996588254503e-05, + "loss": 0.4607, + "step": 4867 + }, + { + "epoch": 0.42, + "learning_rate": 1.3180378500233291e-05, + "loss": 0.4809, + "step": 4868 + }, + { + "epoch": 0.42, + "learning_rate": 1.3177760169663134e-05, + "loss": 0.4611, + "step": 4869 + }, + { + "epoch": 0.42, + "learning_rate": 1.317514159674372e-05, + "loss": 0.4697, + "step": 4870 + }, + { + "epoch": 0.42, + "learning_rate": 1.3172522781674753e-05, + "loss": 0.4867, + "step": 4871 + }, + { + "epoch": 0.42, + "learning_rate": 1.316990372465595e-05, + "loss": 0.4681, + "step": 4872 + }, + { + "epoch": 0.42, + "learning_rate": 1.316728442588706e-05, + "loss": 0.4846, + "step": 4873 + }, + { + "epoch": 0.42, + "learning_rate": 1.3164664885567833e-05, + "loss": 0.4927, + "step": 4874 + }, + { + "epoch": 0.42, + "learning_rate": 1.316204510389805e-05, + "loss": 0.4684, + "step": 4875 + }, + { + "epoch": 0.42, + "learning_rate": 1.315942508107751e-05, + "loss": 0.4723, + "step": 4876 + }, + { + "epoch": 0.42, + "learning_rate": 1.315680481730602e-05, + "loss": 0.4635, + "step": 4877 + }, + { + "epoch": 0.42, + "learning_rate": 1.3154184312783416e-05, + "loss": 0.4926, + "step": 4878 + }, + { + "epoch": 0.42, + "learning_rate": 1.3151563567709547e-05, + "loss": 0.4972, + "step": 4879 + }, + { + "epoch": 0.42, + "learning_rate": 1.3148942582284286e-05, + "loss": 0.4849, + "step": 4880 + }, + { + "epoch": 0.42, + "learning_rate": 1.3146321356707513e-05, + "loss": 0.4864, + "step": 4881 + }, + { + "epoch": 0.42, + "learning_rate": 1.314369989117914e-05, + "loss": 0.4864, + "step": 4882 + }, + { + "epoch": 0.42, + "learning_rate": 1.3141078185899088e-05, + "loss": 0.4954, + "step": 4883 + }, + { + "epoch": 0.42, + "learning_rate": 1.31384562410673e-05, + "loss": 0.4973, + "step": 4884 + }, + { + "epoch": 0.42, + "learning_rate": 1.3135834056883738e-05, + "loss": 0.4817, + "step": 4885 + }, + { + "epoch": 0.42, + "learning_rate": 1.313321163354838e-05, + "loss": 0.4864, + "step": 4886 + }, + { + "epoch": 0.42, + "learning_rate": 1.3130588971261218e-05, + "loss": 0.4729, + "step": 4887 + }, + { + "epoch": 0.42, + "learning_rate": 1.3127966070222273e-05, + "loss": 0.4721, + "step": 4888 + }, + { + "epoch": 0.42, + "learning_rate": 1.3125342930631577e-05, + "loss": 0.4717, + "step": 4889 + }, + { + "epoch": 0.42, + "learning_rate": 1.312271955268918e-05, + "loss": 0.4792, + "step": 4890 + }, + { + "epoch": 0.42, + "learning_rate": 1.3120095936595156e-05, + "loss": 0.4973, + "step": 4891 + }, + { + "epoch": 0.42, + "learning_rate": 1.3117472082549588e-05, + "loss": 0.4762, + "step": 4892 + }, + { + "epoch": 0.42, + "learning_rate": 1.3114847990752582e-05, + "loss": 0.4758, + "step": 4893 + }, + { + "epoch": 0.42, + "learning_rate": 1.3112223661404268e-05, + "loss": 0.4851, + "step": 4894 + }, + { + "epoch": 0.42, + "learning_rate": 1.3109599094704782e-05, + "loss": 0.4716, + "step": 4895 + }, + { + "epoch": 0.42, + "learning_rate": 1.3106974290854286e-05, + "loss": 0.4776, + "step": 4896 + }, + { + "epoch": 0.42, + "learning_rate": 1.310434925005296e-05, + "loss": 0.4895, + "step": 4897 + }, + { + "epoch": 0.42, + "learning_rate": 1.3101723972501002e-05, + "loss": 0.4703, + "step": 4898 + }, + { + "epoch": 0.42, + "learning_rate": 1.3099098458398623e-05, + "loss": 0.4688, + "step": 4899 + }, + { + "epoch": 0.42, + "learning_rate": 1.3096472707946057e-05, + "loss": 0.4883, + "step": 4900 + }, + { + "epoch": 0.42, + "learning_rate": 1.3093846721343555e-05, + "loss": 0.4801, + "step": 4901 + }, + { + "epoch": 0.42, + "learning_rate": 1.3091220498791386e-05, + "loss": 0.4714, + "step": 4902 + }, + { + "epoch": 0.42, + "learning_rate": 1.3088594040489837e-05, + "loss": 0.4879, + "step": 4903 + }, + { + "epoch": 0.42, + "learning_rate": 1.3085967346639212e-05, + "loss": 0.4714, + "step": 4904 + }, + { + "epoch": 0.42, + "learning_rate": 1.3083340417439832e-05, + "loss": 0.4709, + "step": 4905 + }, + { + "epoch": 0.42, + "learning_rate": 1.3080713253092039e-05, + "loss": 0.4761, + "step": 4906 + }, + { + "epoch": 0.42, + "learning_rate": 1.3078085853796192e-05, + "loss": 0.5103, + "step": 4907 + }, + { + "epoch": 0.42, + "learning_rate": 1.307545821975267e-05, + "loss": 0.4692, + "step": 4908 + }, + { + "epoch": 0.42, + "learning_rate": 1.3072830351161862e-05, + "loss": 0.4891, + "step": 4909 + }, + { + "epoch": 0.42, + "learning_rate": 1.3070202248224182e-05, + "loss": 0.504, + "step": 4910 + }, + { + "epoch": 0.42, + "learning_rate": 1.3067573911140061e-05, + "loss": 0.4726, + "step": 4911 + }, + { + "epoch": 0.42, + "learning_rate": 1.306494534010995e-05, + "loss": 0.5209, + "step": 4912 + }, + { + "epoch": 0.42, + "learning_rate": 1.306231653533431e-05, + "loss": 0.5102, + "step": 4913 + }, + { + "epoch": 0.42, + "learning_rate": 1.3059687497013625e-05, + "loss": 0.4857, + "step": 4914 + }, + { + "epoch": 0.42, + "learning_rate": 1.30570582253484e-05, + "loss": 0.4876, + "step": 4915 + }, + { + "epoch": 0.42, + "learning_rate": 1.3054428720539147e-05, + "loss": 0.4991, + "step": 4916 + }, + { + "epoch": 0.42, + "learning_rate": 1.3051798982786412e-05, + "loss": 0.4876, + "step": 4917 + }, + { + "epoch": 0.42, + "learning_rate": 1.3049169012290745e-05, + "loss": 0.4756, + "step": 4918 + }, + { + "epoch": 0.42, + "learning_rate": 1.3046538809252718e-05, + "loss": 0.4729, + "step": 4919 + }, + { + "epoch": 0.42, + "learning_rate": 1.3043908373872922e-05, + "loss": 0.484, + "step": 4920 + }, + { + "epoch": 0.42, + "learning_rate": 1.304127770635197e-05, + "loss": 0.4874, + "step": 4921 + }, + { + "epoch": 0.42, + "learning_rate": 1.3038646806890479e-05, + "loss": 0.4755, + "step": 4922 + }, + { + "epoch": 0.42, + "learning_rate": 1.3036015675689098e-05, + "loss": 0.5001, + "step": 4923 + }, + { + "epoch": 0.42, + "learning_rate": 1.3033384312948487e-05, + "loss": 0.472, + "step": 4924 + }, + { + "epoch": 0.42, + "learning_rate": 1.3030752718869321e-05, + "loss": 0.4872, + "step": 4925 + }, + { + "epoch": 0.42, + "learning_rate": 1.3028120893652305e-05, + "loss": 0.5004, + "step": 4926 + }, + { + "epoch": 0.42, + "learning_rate": 1.3025488837498144e-05, + "loss": 0.458, + "step": 4927 + }, + { + "epoch": 0.42, + "learning_rate": 1.3022856550607572e-05, + "loss": 0.47, + "step": 4928 + }, + { + "epoch": 0.42, + "learning_rate": 1.3020224033181342e-05, + "loss": 0.4942, + "step": 4929 + }, + { + "epoch": 0.42, + "learning_rate": 1.3017591285420219e-05, + "loss": 0.4969, + "step": 4930 + }, + { + "epoch": 0.42, + "learning_rate": 1.3014958307524985e-05, + "loss": 0.4778, + "step": 4931 + }, + { + "epoch": 0.42, + "learning_rate": 1.3012325099696443e-05, + "loss": 0.4782, + "step": 4932 + }, + { + "epoch": 0.42, + "learning_rate": 1.3009691662135415e-05, + "loss": 0.4787, + "step": 4933 + }, + { + "epoch": 0.42, + "learning_rate": 1.300705799504273e-05, + "loss": 0.476, + "step": 4934 + }, + { + "epoch": 0.42, + "learning_rate": 1.3004424098619254e-05, + "loss": 0.4792, + "step": 4935 + }, + { + "epoch": 0.42, + "learning_rate": 1.3001789973065852e-05, + "loss": 0.4992, + "step": 4936 + }, + { + "epoch": 0.42, + "learning_rate": 1.2999155618583414e-05, + "loss": 0.4897, + "step": 4937 + }, + { + "epoch": 0.42, + "learning_rate": 1.2996521035372847e-05, + "loss": 0.4771, + "step": 4938 + }, + { + "epoch": 0.42, + "learning_rate": 1.2993886223635076e-05, + "loss": 0.5054, + "step": 4939 + }, + { + "epoch": 0.42, + "learning_rate": 1.2991251183571043e-05, + "loss": 0.4941, + "step": 4940 + }, + { + "epoch": 0.42, + "learning_rate": 1.2988615915381707e-05, + "loss": 0.4895, + "step": 4941 + }, + { + "epoch": 0.42, + "learning_rate": 1.2985980419268045e-05, + "loss": 0.4878, + "step": 4942 + }, + { + "epoch": 0.42, + "learning_rate": 1.2983344695431046e-05, + "loss": 0.4724, + "step": 4943 + }, + { + "epoch": 0.42, + "learning_rate": 1.298070874407173e-05, + "loss": 0.4868, + "step": 4944 + }, + { + "epoch": 0.42, + "learning_rate": 1.2978072565391118e-05, + "loss": 0.4822, + "step": 4945 + }, + { + "epoch": 0.42, + "learning_rate": 1.297543615959026e-05, + "loss": 0.4788, + "step": 4946 + }, + { + "epoch": 0.42, + "learning_rate": 1.2972799526870219e-05, + "loss": 0.4807, + "step": 4947 + }, + { + "epoch": 0.42, + "learning_rate": 1.2970162667432075e-05, + "loss": 0.4807, + "step": 4948 + }, + { + "epoch": 0.42, + "learning_rate": 1.2967525581476925e-05, + "loss": 0.5076, + "step": 4949 + }, + { + "epoch": 0.42, + "learning_rate": 1.2964888269205886e-05, + "loss": 0.4714, + "step": 4950 + }, + { + "epoch": 0.42, + "learning_rate": 1.2962250730820092e-05, + "loss": 0.4841, + "step": 4951 + }, + { + "epoch": 0.42, + "learning_rate": 1.2959612966520683e-05, + "loss": 0.4883, + "step": 4952 + }, + { + "epoch": 0.42, + "learning_rate": 1.295697497650884e-05, + "loss": 0.4657, + "step": 4953 + }, + { + "epoch": 0.42, + "learning_rate": 1.2954336760985737e-05, + "loss": 0.483, + "step": 4954 + }, + { + "epoch": 0.42, + "learning_rate": 1.2951698320152578e-05, + "loss": 0.4747, + "step": 4955 + }, + { + "epoch": 0.42, + "learning_rate": 1.2949059654210587e-05, + "loss": 0.4767, + "step": 4956 + }, + { + "epoch": 0.42, + "learning_rate": 1.294642076336099e-05, + "loss": 0.4611, + "step": 4957 + }, + { + "epoch": 0.42, + "learning_rate": 1.2943781647805048e-05, + "loss": 0.4999, + "step": 4958 + }, + { + "epoch": 0.42, + "learning_rate": 1.2941142307744023e-05, + "loss": 0.5002, + "step": 4959 + }, + { + "epoch": 0.42, + "learning_rate": 1.2938502743379212e-05, + "loss": 0.4671, + "step": 4960 + }, + { + "epoch": 0.42, + "learning_rate": 1.2935862954911909e-05, + "loss": 0.4805, + "step": 4961 + }, + { + "epoch": 0.42, + "learning_rate": 1.2933222942543444e-05, + "loss": 0.482, + "step": 4962 + }, + { + "epoch": 0.42, + "learning_rate": 1.293058270647515e-05, + "loss": 0.4813, + "step": 4963 + }, + { + "epoch": 0.42, + "learning_rate": 1.2927942246908383e-05, + "loss": 0.4731, + "step": 4964 + }, + { + "epoch": 0.42, + "learning_rate": 1.2925301564044519e-05, + "loss": 0.4979, + "step": 4965 + }, + { + "epoch": 0.42, + "learning_rate": 1.2922660658084945e-05, + "loss": 0.4735, + "step": 4966 + }, + { + "epoch": 0.42, + "learning_rate": 1.2920019529231065e-05, + "loss": 0.4798, + "step": 4967 + }, + { + "epoch": 0.42, + "learning_rate": 1.2917378177684303e-05, + "loss": 0.4751, + "step": 4968 + }, + { + "epoch": 0.42, + "learning_rate": 1.2914736603646108e-05, + "loss": 0.4862, + "step": 4969 + }, + { + "epoch": 0.42, + "learning_rate": 1.2912094807317927e-05, + "loss": 0.4927, + "step": 4970 + }, + { + "epoch": 0.42, + "learning_rate": 1.2909452788901238e-05, + "loss": 0.4666, + "step": 4971 + }, + { + "epoch": 0.42, + "learning_rate": 1.2906810548597533e-05, + "loss": 0.4822, + "step": 4972 + }, + { + "epoch": 0.42, + "learning_rate": 1.290416808660832e-05, + "loss": 0.4719, + "step": 4973 + }, + { + "epoch": 0.42, + "learning_rate": 1.2901525403135126e-05, + "loss": 0.4987, + "step": 4974 + }, + { + "epoch": 0.42, + "learning_rate": 1.289888249837949e-05, + "loss": 0.4875, + "step": 4975 + }, + { + "epoch": 0.42, + "learning_rate": 1.2896239372542971e-05, + "loss": 0.4737, + "step": 4976 + }, + { + "epoch": 0.42, + "learning_rate": 1.2893596025827146e-05, + "loss": 0.4934, + "step": 4977 + }, + { + "epoch": 0.42, + "learning_rate": 1.289095245843361e-05, + "loss": 0.4864, + "step": 4978 + }, + { + "epoch": 0.42, + "learning_rate": 1.288830867056397e-05, + "loss": 0.4866, + "step": 4979 + }, + { + "epoch": 0.42, + "learning_rate": 1.288566466241985e-05, + "loss": 0.4631, + "step": 4980 + }, + { + "epoch": 0.42, + "learning_rate": 1.2883020434202897e-05, + "loss": 0.4846, + "step": 4981 + }, + { + "epoch": 0.42, + "learning_rate": 1.288037598611477e-05, + "loss": 0.4993, + "step": 4982 + }, + { + "epoch": 0.42, + "learning_rate": 1.2877731318357145e-05, + "loss": 0.498, + "step": 4983 + }, + { + "epoch": 0.42, + "learning_rate": 1.2875086431131716e-05, + "loss": 0.4905, + "step": 4984 + }, + { + "epoch": 0.43, + "learning_rate": 1.2872441324640191e-05, + "loss": 0.4845, + "step": 4985 + }, + { + "epoch": 0.43, + "learning_rate": 1.28697959990843e-05, + "loss": 0.476, + "step": 4986 + }, + { + "epoch": 0.43, + "learning_rate": 1.2867150454665783e-05, + "loss": 0.4825, + "step": 4987 + }, + { + "epoch": 0.43, + "learning_rate": 1.2864504691586404e-05, + "loss": 0.4991, + "step": 4988 + }, + { + "epoch": 0.43, + "learning_rate": 1.2861858710047938e-05, + "loss": 0.4624, + "step": 4989 + }, + { + "epoch": 0.43, + "learning_rate": 1.2859212510252176e-05, + "loss": 0.5, + "step": 4990 + }, + { + "epoch": 0.43, + "learning_rate": 1.2856566092400936e-05, + "loss": 0.4703, + "step": 4991 + }, + { + "epoch": 0.43, + "learning_rate": 1.2853919456696038e-05, + "loss": 0.4835, + "step": 4992 + }, + { + "epoch": 0.43, + "learning_rate": 1.2851272603339329e-05, + "loss": 0.4954, + "step": 4993 + }, + { + "epoch": 0.43, + "learning_rate": 1.2848625532532664e-05, + "loss": 0.4753, + "step": 4994 + }, + { + "epoch": 0.43, + "learning_rate": 1.2845978244477925e-05, + "loss": 0.4834, + "step": 4995 + }, + { + "epoch": 0.43, + "learning_rate": 1.2843330739377003e-05, + "loss": 0.4747, + "step": 4996 + }, + { + "epoch": 0.43, + "learning_rate": 1.284068301743181e-05, + "loss": 0.4894, + "step": 4997 + }, + { + "epoch": 0.43, + "learning_rate": 1.2838035078844268e-05, + "loss": 0.4821, + "step": 4998 + }, + { + "epoch": 0.43, + "learning_rate": 1.2835386923816324e-05, + "loss": 0.4585, + "step": 4999 + }, + { + "epoch": 0.43, + "learning_rate": 1.2832738552549935e-05, + "loss": 0.4873, + "step": 5000 + }, + { + "epoch": 0.43, + "learning_rate": 1.283008996524708e-05, + "loss": 0.4931, + "step": 5001 + }, + { + "epoch": 0.43, + "learning_rate": 1.2827441162109749e-05, + "loss": 0.455, + "step": 5002 + }, + { + "epoch": 0.43, + "learning_rate": 1.2824792143339948e-05, + "loss": 0.4789, + "step": 5003 + }, + { + "epoch": 0.43, + "learning_rate": 1.2822142909139707e-05, + "loss": 0.4613, + "step": 5004 + }, + { + "epoch": 0.43, + "learning_rate": 1.2819493459711061e-05, + "loss": 0.4629, + "step": 5005 + }, + { + "epoch": 0.43, + "learning_rate": 1.281684379525608e-05, + "loss": 0.4955, + "step": 5006 + }, + { + "epoch": 0.43, + "learning_rate": 1.2814193915976827e-05, + "loss": 0.4746, + "step": 5007 + }, + { + "epoch": 0.43, + "learning_rate": 1.2811543822075396e-05, + "loss": 0.4804, + "step": 5008 + }, + { + "epoch": 0.43, + "learning_rate": 1.28088935137539e-05, + "loss": 0.4897, + "step": 5009 + }, + { + "epoch": 0.43, + "learning_rate": 1.2806242991214454e-05, + "loss": 0.4676, + "step": 5010 + }, + { + "epoch": 0.43, + "learning_rate": 1.2803592254659202e-05, + "loss": 0.4783, + "step": 5011 + }, + { + "epoch": 0.43, + "learning_rate": 1.28009413042903e-05, + "loss": 0.4777, + "step": 5012 + }, + { + "epoch": 0.43, + "learning_rate": 1.2798290140309924e-05, + "loss": 0.4843, + "step": 5013 + }, + { + "epoch": 0.43, + "learning_rate": 1.2795638762920254e-05, + "loss": 0.5035, + "step": 5014 + }, + { + "epoch": 0.43, + "learning_rate": 1.2792987172323504e-05, + "loss": 0.4743, + "step": 5015 + }, + { + "epoch": 0.43, + "learning_rate": 1.2790335368721891e-05, + "loss": 0.5164, + "step": 5016 + }, + { + "epoch": 0.43, + "learning_rate": 1.2787683352317652e-05, + "loss": 0.5026, + "step": 5017 + }, + { + "epoch": 0.43, + "learning_rate": 1.2785031123313046e-05, + "loss": 0.4653, + "step": 5018 + }, + { + "epoch": 0.43, + "learning_rate": 1.2782378681910337e-05, + "loss": 0.4758, + "step": 5019 + }, + { + "epoch": 0.43, + "learning_rate": 1.2779726028311812e-05, + "loss": 0.5016, + "step": 5020 + }, + { + "epoch": 0.43, + "learning_rate": 1.2777073162719777e-05, + "loss": 0.468, + "step": 5021 + }, + { + "epoch": 0.43, + "learning_rate": 1.2774420085336549e-05, + "loss": 0.48, + "step": 5022 + }, + { + "epoch": 0.43, + "learning_rate": 1.2771766796364462e-05, + "loss": 0.4923, + "step": 5023 + }, + { + "epoch": 0.43, + "learning_rate": 1.2769113296005868e-05, + "loss": 0.4771, + "step": 5024 + }, + { + "epoch": 0.43, + "learning_rate": 1.2766459584463133e-05, + "loss": 0.4555, + "step": 5025 + }, + { + "epoch": 0.43, + "learning_rate": 1.276380566193864e-05, + "loss": 0.4728, + "step": 5026 + }, + { + "epoch": 0.43, + "learning_rate": 1.276115152863479e-05, + "loss": 0.5026, + "step": 5027 + }, + { + "epoch": 0.43, + "learning_rate": 1.2758497184753995e-05, + "loss": 0.4744, + "step": 5028 + }, + { + "epoch": 0.43, + "learning_rate": 1.2755842630498689e-05, + "loss": 0.4939, + "step": 5029 + }, + { + "epoch": 0.43, + "learning_rate": 1.2753187866071317e-05, + "loss": 0.4805, + "step": 5030 + }, + { + "epoch": 0.43, + "learning_rate": 1.2750532891674347e-05, + "loss": 0.4661, + "step": 5031 + }, + { + "epoch": 0.43, + "learning_rate": 1.2747877707510252e-05, + "loss": 0.475, + "step": 5032 + }, + { + "epoch": 0.43, + "learning_rate": 1.2745222313781536e-05, + "loss": 0.483, + "step": 5033 + }, + { + "epoch": 0.43, + "learning_rate": 1.2742566710690703e-05, + "loss": 0.4985, + "step": 5034 + }, + { + "epoch": 0.43, + "learning_rate": 1.2739910898440282e-05, + "loss": 0.479, + "step": 5035 + }, + { + "epoch": 0.43, + "learning_rate": 1.273725487723282e-05, + "loss": 0.4809, + "step": 5036 + }, + { + "epoch": 0.43, + "learning_rate": 1.273459864727087e-05, + "loss": 0.4705, + "step": 5037 + }, + { + "epoch": 0.43, + "learning_rate": 1.2731942208757012e-05, + "loss": 0.4948, + "step": 5038 + }, + { + "epoch": 0.43, + "learning_rate": 1.2729285561893833e-05, + "loss": 0.4835, + "step": 5039 + }, + { + "epoch": 0.43, + "learning_rate": 1.2726628706883947e-05, + "loss": 0.4517, + "step": 5040 + }, + { + "epoch": 0.43, + "learning_rate": 1.272397164392997e-05, + "loss": 0.4764, + "step": 5041 + }, + { + "epoch": 0.43, + "learning_rate": 1.2721314373234543e-05, + "loss": 0.4914, + "step": 5042 + }, + { + "epoch": 0.43, + "learning_rate": 1.271865689500032e-05, + "loss": 0.488, + "step": 5043 + }, + { + "epoch": 0.43, + "learning_rate": 1.2715999209429974e-05, + "loss": 0.4859, + "step": 5044 + }, + { + "epoch": 0.43, + "learning_rate": 1.2713341316726191e-05, + "loss": 0.4709, + "step": 5045 + }, + { + "epoch": 0.43, + "learning_rate": 1.2710683217091668e-05, + "loss": 0.4775, + "step": 5046 + }, + { + "epoch": 0.43, + "learning_rate": 1.2708024910729127e-05, + "loss": 0.4729, + "step": 5047 + }, + { + "epoch": 0.43, + "learning_rate": 1.2705366397841303e-05, + "loss": 0.5038, + "step": 5048 + }, + { + "epoch": 0.43, + "learning_rate": 1.2702707678630941e-05, + "loss": 0.4812, + "step": 5049 + }, + { + "epoch": 0.43, + "learning_rate": 1.2700048753300806e-05, + "loss": 0.4778, + "step": 5050 + }, + { + "epoch": 0.43, + "learning_rate": 1.2697389622053681e-05, + "loss": 0.4938, + "step": 5051 + }, + { + "epoch": 0.43, + "learning_rate": 1.2694730285092365e-05, + "loss": 0.4999, + "step": 5052 + }, + { + "epoch": 0.43, + "learning_rate": 1.2692070742619665e-05, + "loss": 0.4765, + "step": 5053 + }, + { + "epoch": 0.43, + "learning_rate": 1.2689410994838414e-05, + "loss": 0.4783, + "step": 5054 + }, + { + "epoch": 0.43, + "learning_rate": 1.2686751041951451e-05, + "loss": 0.4968, + "step": 5055 + }, + { + "epoch": 0.43, + "learning_rate": 1.2684090884161636e-05, + "loss": 0.4853, + "step": 5056 + }, + { + "epoch": 0.43, + "learning_rate": 1.2681430521671845e-05, + "loss": 0.4768, + "step": 5057 + }, + { + "epoch": 0.43, + "learning_rate": 1.2678769954684966e-05, + "loss": 0.4856, + "step": 5058 + }, + { + "epoch": 0.43, + "learning_rate": 1.2676109183403909e-05, + "loss": 0.4908, + "step": 5059 + }, + { + "epoch": 0.43, + "learning_rate": 1.2673448208031591e-05, + "loss": 0.4537, + "step": 5060 + }, + { + "epoch": 0.43, + "learning_rate": 1.2670787028770955e-05, + "loss": 0.4938, + "step": 5061 + }, + { + "epoch": 0.43, + "learning_rate": 1.2668125645824945e-05, + "loss": 0.4616, + "step": 5062 + }, + { + "epoch": 0.43, + "learning_rate": 1.266546405939654e-05, + "loss": 0.4728, + "step": 5063 + }, + { + "epoch": 0.43, + "learning_rate": 1.2662802269688715e-05, + "loss": 0.495, + "step": 5064 + }, + { + "epoch": 0.43, + "learning_rate": 1.2660140276904471e-05, + "loss": 0.4883, + "step": 5065 + }, + { + "epoch": 0.43, + "learning_rate": 1.2657478081246826e-05, + "loss": 0.4818, + "step": 5066 + }, + { + "epoch": 0.43, + "learning_rate": 1.2654815682918801e-05, + "loss": 0.4791, + "step": 5067 + }, + { + "epoch": 0.43, + "learning_rate": 1.2652153082123458e-05, + "loss": 0.4919, + "step": 5068 + }, + { + "epoch": 0.43, + "learning_rate": 1.2649490279063845e-05, + "loss": 0.4705, + "step": 5069 + }, + { + "epoch": 0.43, + "learning_rate": 1.2646827273943042e-05, + "loss": 0.4606, + "step": 5070 + }, + { + "epoch": 0.43, + "learning_rate": 1.2644164066964138e-05, + "loss": 0.4741, + "step": 5071 + }, + { + "epoch": 0.43, + "learning_rate": 1.2641500658330248e-05, + "loss": 0.4829, + "step": 5072 + }, + { + "epoch": 0.43, + "learning_rate": 1.2638837048244486e-05, + "loss": 0.4855, + "step": 5073 + }, + { + "epoch": 0.43, + "learning_rate": 1.2636173236909995e-05, + "loss": 0.4725, + "step": 5074 + }, + { + "epoch": 0.43, + "learning_rate": 1.263350922452993e-05, + "loss": 0.4829, + "step": 5075 + }, + { + "epoch": 0.43, + "learning_rate": 1.263084501130745e-05, + "loss": 0.4754, + "step": 5076 + }, + { + "epoch": 0.43, + "learning_rate": 1.2628180597445754e-05, + "loss": 0.4734, + "step": 5077 + }, + { + "epoch": 0.43, + "learning_rate": 1.2625515983148029e-05, + "loss": 0.4783, + "step": 5078 + }, + { + "epoch": 0.43, + "learning_rate": 1.2622851168617495e-05, + "loss": 0.4809, + "step": 5079 + }, + { + "epoch": 0.43, + "learning_rate": 1.2620186154057383e-05, + "loss": 0.4835, + "step": 5080 + }, + { + "epoch": 0.43, + "learning_rate": 1.2617520939670934e-05, + "loss": 0.4844, + "step": 5081 + }, + { + "epoch": 0.43, + "learning_rate": 1.2614855525661409e-05, + "loss": 0.5053, + "step": 5082 + }, + { + "epoch": 0.43, + "learning_rate": 1.2612189912232084e-05, + "loss": 0.4822, + "step": 5083 + }, + { + "epoch": 0.43, + "learning_rate": 1.2609524099586254e-05, + "loss": 0.4987, + "step": 5084 + }, + { + "epoch": 0.43, + "learning_rate": 1.2606858087927219e-05, + "loss": 0.4917, + "step": 5085 + }, + { + "epoch": 0.43, + "learning_rate": 1.2604191877458307e-05, + "loss": 0.4614, + "step": 5086 + }, + { + "epoch": 0.43, + "learning_rate": 1.2601525468382846e-05, + "loss": 0.4816, + "step": 5087 + }, + { + "epoch": 0.43, + "learning_rate": 1.2598858860904193e-05, + "loss": 0.4781, + "step": 5088 + }, + { + "epoch": 0.43, + "learning_rate": 1.2596192055225716e-05, + "loss": 0.4494, + "step": 5089 + }, + { + "epoch": 0.43, + "learning_rate": 1.259352505155079e-05, + "loss": 0.5084, + "step": 5090 + }, + { + "epoch": 0.43, + "learning_rate": 1.2590857850082819e-05, + "loss": 0.5017, + "step": 5091 + }, + { + "epoch": 0.43, + "learning_rate": 1.2588190451025209e-05, + "loss": 0.4863, + "step": 5092 + }, + { + "epoch": 0.43, + "learning_rate": 1.2585522854581393e-05, + "loss": 0.4782, + "step": 5093 + }, + { + "epoch": 0.43, + "learning_rate": 1.2582855060954806e-05, + "loss": 0.4817, + "step": 5094 + }, + { + "epoch": 0.43, + "learning_rate": 1.2580187070348913e-05, + "loss": 0.4796, + "step": 5095 + }, + { + "epoch": 0.43, + "learning_rate": 1.2577518882967182e-05, + "loss": 0.4734, + "step": 5096 + }, + { + "epoch": 0.43, + "learning_rate": 1.2574850499013093e-05, + "loss": 0.4798, + "step": 5097 + }, + { + "epoch": 0.43, + "learning_rate": 1.2572181918690162e-05, + "loss": 0.4942, + "step": 5098 + }, + { + "epoch": 0.43, + "learning_rate": 1.25695131422019e-05, + "loss": 0.4909, + "step": 5099 + }, + { + "epoch": 0.43, + "learning_rate": 1.2566844169751835e-05, + "loss": 0.4866, + "step": 5100 + }, + { + "epoch": 0.43, + "learning_rate": 1.2564175001543517e-05, + "loss": 0.4913, + "step": 5101 + }, + { + "epoch": 0.44, + "learning_rate": 1.2561505637780514e-05, + "loss": 0.4631, + "step": 5102 + }, + { + "epoch": 0.44, + "learning_rate": 1.2558836078666392e-05, + "loss": 0.4858, + "step": 5103 + }, + { + "epoch": 0.44, + "learning_rate": 1.2556166324404747e-05, + "loss": 0.4787, + "step": 5104 + }, + { + "epoch": 0.44, + "learning_rate": 1.255349637519919e-05, + "loss": 0.4943, + "step": 5105 + }, + { + "epoch": 0.44, + "learning_rate": 1.2550826231253335e-05, + "loss": 0.4899, + "step": 5106 + }, + { + "epoch": 0.44, + "learning_rate": 1.2548155892770825e-05, + "loss": 0.4757, + "step": 5107 + }, + { + "epoch": 0.44, + "learning_rate": 1.2545485359955309e-05, + "loss": 0.4945, + "step": 5108 + }, + { + "epoch": 0.44, + "learning_rate": 1.2542814633010452e-05, + "loss": 0.472, + "step": 5109 + }, + { + "epoch": 0.44, + "learning_rate": 1.2540143712139935e-05, + "loss": 0.4792, + "step": 5110 + }, + { + "epoch": 0.44, + "learning_rate": 1.2537472597547453e-05, + "loss": 0.48, + "step": 5111 + }, + { + "epoch": 0.44, + "learning_rate": 1.2534801289436715e-05, + "loss": 0.4794, + "step": 5112 + }, + { + "epoch": 0.44, + "learning_rate": 1.2532129788011452e-05, + "loss": 0.472, + "step": 5113 + }, + { + "epoch": 0.44, + "learning_rate": 1.25294580934754e-05, + "loss": 0.4812, + "step": 5114 + }, + { + "epoch": 0.44, + "learning_rate": 1.252678620603231e-05, + "loss": 0.4898, + "step": 5115 + }, + { + "epoch": 0.44, + "learning_rate": 1.2524114125885958e-05, + "loss": 0.5117, + "step": 5116 + }, + { + "epoch": 0.44, + "learning_rate": 1.2521441853240124e-05, + "loss": 0.4995, + "step": 5117 + }, + { + "epoch": 0.44, + "learning_rate": 1.2518769388298607e-05, + "loss": 0.4802, + "step": 5118 + }, + { + "epoch": 0.44, + "learning_rate": 1.2516096731265222e-05, + "loss": 0.479, + "step": 5119 + }, + { + "epoch": 0.44, + "learning_rate": 1.2513423882343797e-05, + "loss": 0.4817, + "step": 5120 + }, + { + "epoch": 0.44, + "learning_rate": 1.2510750841738168e-05, + "loss": 0.4853, + "step": 5121 + }, + { + "epoch": 0.44, + "learning_rate": 1.2508077609652203e-05, + "loss": 0.4534, + "step": 5122 + }, + { + "epoch": 0.44, + "learning_rate": 1.2505404186289765e-05, + "loss": 0.4729, + "step": 5123 + }, + { + "epoch": 0.44, + "learning_rate": 1.2502730571854747e-05, + "loss": 0.4949, + "step": 5124 + }, + { + "epoch": 0.44, + "learning_rate": 1.2500056766551047e-05, + "loss": 0.4736, + "step": 5125 + }, + { + "epoch": 0.44, + "learning_rate": 1.249738277058258e-05, + "loss": 0.4919, + "step": 5126 + }, + { + "epoch": 0.44, + "learning_rate": 1.2494708584153275e-05, + "loss": 0.4858, + "step": 5127 + }, + { + "epoch": 0.44, + "learning_rate": 1.2492034207467081e-05, + "loss": 0.4643, + "step": 5128 + }, + { + "epoch": 0.44, + "learning_rate": 1.2489359640727953e-05, + "loss": 0.4738, + "step": 5129 + }, + { + "epoch": 0.44, + "learning_rate": 1.2486684884139866e-05, + "loss": 0.4771, + "step": 5130 + }, + { + "epoch": 0.44, + "learning_rate": 1.2484009937906807e-05, + "loss": 0.4749, + "step": 5131 + }, + { + "epoch": 0.44, + "learning_rate": 1.248133480223278e-05, + "loss": 0.4969, + "step": 5132 + }, + { + "epoch": 0.44, + "learning_rate": 1.2478659477321801e-05, + "loss": 0.4861, + "step": 5133 + }, + { + "epoch": 0.44, + "learning_rate": 1.2475983963377907e-05, + "loss": 0.4833, + "step": 5134 + }, + { + "epoch": 0.44, + "learning_rate": 1.2473308260605134e-05, + "loss": 0.4801, + "step": 5135 + }, + { + "epoch": 0.44, + "learning_rate": 1.247063236920755e-05, + "loss": 0.4901, + "step": 5136 + }, + { + "epoch": 0.44, + "learning_rate": 1.2467956289389228e-05, + "loss": 0.4832, + "step": 5137 + }, + { + "epoch": 0.44, + "learning_rate": 1.2465280021354254e-05, + "loss": 0.4644, + "step": 5138 + }, + { + "epoch": 0.44, + "learning_rate": 1.2462603565306733e-05, + "loss": 0.4808, + "step": 5139 + }, + { + "epoch": 0.44, + "learning_rate": 1.245992692145078e-05, + "loss": 0.4836, + "step": 5140 + }, + { + "epoch": 0.44, + "learning_rate": 1.2457250089990534e-05, + "loss": 0.4697, + "step": 5141 + }, + { + "epoch": 0.44, + "learning_rate": 1.2454573071130138e-05, + "loss": 0.4976, + "step": 5142 + }, + { + "epoch": 0.44, + "learning_rate": 1.2451895865073751e-05, + "loss": 0.4706, + "step": 5143 + }, + { + "epoch": 0.44, + "learning_rate": 1.2449218472025548e-05, + "loss": 0.4734, + "step": 5144 + }, + { + "epoch": 0.44, + "learning_rate": 1.244654089218972e-05, + "loss": 0.4955, + "step": 5145 + }, + { + "epoch": 0.44, + "learning_rate": 1.2443863125770473e-05, + "loss": 0.4672, + "step": 5146 + }, + { + "epoch": 0.44, + "learning_rate": 1.2441185172972015e-05, + "loss": 0.5048, + "step": 5147 + }, + { + "epoch": 0.44, + "learning_rate": 1.2438507033998588e-05, + "loss": 0.4911, + "step": 5148 + }, + { + "epoch": 0.44, + "learning_rate": 1.2435828709054431e-05, + "loss": 0.4969, + "step": 5149 + }, + { + "epoch": 0.44, + "learning_rate": 1.2433150198343808e-05, + "loss": 0.4702, + "step": 5150 + }, + { + "epoch": 0.44, + "learning_rate": 1.2430471502070998e-05, + "loss": 0.4711, + "step": 5151 + }, + { + "epoch": 0.44, + "learning_rate": 1.242779262044028e-05, + "loss": 0.4722, + "step": 5152 + }, + { + "epoch": 0.44, + "learning_rate": 1.242511355365596e-05, + "loss": 0.5053, + "step": 5153 + }, + { + "epoch": 0.44, + "learning_rate": 1.2422434301922358e-05, + "loss": 0.4903, + "step": 5154 + }, + { + "epoch": 0.44, + "learning_rate": 1.2419754865443803e-05, + "loss": 0.4821, + "step": 5155 + }, + { + "epoch": 0.44, + "learning_rate": 1.2417075244424637e-05, + "loss": 0.4828, + "step": 5156 + }, + { + "epoch": 0.44, + "learning_rate": 1.2414395439069224e-05, + "loss": 0.4878, + "step": 5157 + }, + { + "epoch": 0.44, + "learning_rate": 1.2411715449581938e-05, + "loss": 0.4862, + "step": 5158 + }, + { + "epoch": 0.44, + "learning_rate": 1.2409035276167156e-05, + "loss": 0.4774, + "step": 5159 + }, + { + "epoch": 0.44, + "learning_rate": 1.2406354919029294e-05, + "loss": 0.4815, + "step": 5160 + }, + { + "epoch": 0.44, + "learning_rate": 1.2403674378372755e-05, + "loss": 0.4884, + "step": 5161 + }, + { + "epoch": 0.44, + "learning_rate": 1.2400993654401974e-05, + "loss": 0.4852, + "step": 5162 + }, + { + "epoch": 0.44, + "learning_rate": 1.239831274732139e-05, + "loss": 0.4771, + "step": 5163 + }, + { + "epoch": 0.44, + "learning_rate": 1.239563165733547e-05, + "loss": 0.4822, + "step": 5164 + }, + { + "epoch": 0.44, + "learning_rate": 1.2392950384648674e-05, + "loss": 0.4907, + "step": 5165 + }, + { + "epoch": 0.44, + "learning_rate": 1.2390268929465492e-05, + "loss": 0.4839, + "step": 5166 + }, + { + "epoch": 0.44, + "learning_rate": 1.2387587291990423e-05, + "loss": 0.4758, + "step": 5167 + }, + { + "epoch": 0.44, + "learning_rate": 1.2384905472427975e-05, + "loss": 0.4928, + "step": 5168 + }, + { + "epoch": 0.44, + "learning_rate": 1.2382223470982687e-05, + "loss": 0.5195, + "step": 5169 + }, + { + "epoch": 0.44, + "learning_rate": 1.2379541287859085e-05, + "loss": 0.4746, + "step": 5170 + }, + { + "epoch": 0.44, + "learning_rate": 1.2376858923261732e-05, + "loss": 0.4847, + "step": 5171 + }, + { + "epoch": 0.44, + "learning_rate": 1.2374176377395194e-05, + "loss": 0.5012, + "step": 5172 + }, + { + "epoch": 0.44, + "learning_rate": 1.2371493650464057e-05, + "loss": 0.4813, + "step": 5173 + }, + { + "epoch": 0.44, + "learning_rate": 1.236881074267291e-05, + "loss": 0.4832, + "step": 5174 + }, + { + "epoch": 0.44, + "learning_rate": 1.2366127654226365e-05, + "loss": 0.5043, + "step": 5175 + }, + { + "epoch": 0.44, + "learning_rate": 1.2363444385329052e-05, + "loss": 0.5132, + "step": 5176 + }, + { + "epoch": 0.44, + "learning_rate": 1.2360760936185599e-05, + "loss": 0.4537, + "step": 5177 + }, + { + "epoch": 0.44, + "learning_rate": 1.2358077307000663e-05, + "loss": 0.4834, + "step": 5178 + }, + { + "epoch": 0.44, + "learning_rate": 1.2355393497978904e-05, + "loss": 0.4782, + "step": 5179 + }, + { + "epoch": 0.44, + "learning_rate": 1.2352709509325005e-05, + "loss": 0.4679, + "step": 5180 + }, + { + "epoch": 0.44, + "learning_rate": 1.2350025341243659e-05, + "loss": 0.4611, + "step": 5181 + }, + { + "epoch": 0.44, + "learning_rate": 1.2347340993939567e-05, + "loss": 0.4859, + "step": 5182 + }, + { + "epoch": 0.44, + "learning_rate": 1.2344656467617451e-05, + "loss": 0.4629, + "step": 5183 + }, + { + "epoch": 0.44, + "learning_rate": 1.2341971762482043e-05, + "loss": 0.4946, + "step": 5184 + }, + { + "epoch": 0.44, + "learning_rate": 1.2339286878738094e-05, + "loss": 0.4836, + "step": 5185 + }, + { + "epoch": 0.44, + "learning_rate": 1.2336601816590359e-05, + "loss": 0.4887, + "step": 5186 + }, + { + "epoch": 0.44, + "learning_rate": 1.2333916576243617e-05, + "loss": 0.466, + "step": 5187 + }, + { + "epoch": 0.44, + "learning_rate": 1.233123115790265e-05, + "loss": 0.4798, + "step": 5188 + }, + { + "epoch": 0.44, + "learning_rate": 1.2328545561772263e-05, + "loss": 0.4669, + "step": 5189 + }, + { + "epoch": 0.44, + "learning_rate": 1.2325859788057273e-05, + "loss": 0.4695, + "step": 5190 + }, + { + "epoch": 0.44, + "learning_rate": 1.2323173836962502e-05, + "loss": 0.4829, + "step": 5191 + }, + { + "epoch": 0.44, + "learning_rate": 1.2320487708692797e-05, + "loss": 0.4831, + "step": 5192 + }, + { + "epoch": 0.44, + "learning_rate": 1.231780140345301e-05, + "loss": 0.4601, + "step": 5193 + }, + { + "epoch": 0.44, + "learning_rate": 1.2315114921448012e-05, + "loss": 0.4752, + "step": 5194 + }, + { + "epoch": 0.44, + "learning_rate": 1.2312428262882685e-05, + "loss": 0.5056, + "step": 5195 + }, + { + "epoch": 0.44, + "learning_rate": 1.2309741427961925e-05, + "loss": 0.4836, + "step": 5196 + }, + { + "epoch": 0.44, + "learning_rate": 1.230705441689064e-05, + "loss": 0.5092, + "step": 5197 + }, + { + "epoch": 0.44, + "learning_rate": 1.2304367229873754e-05, + "loss": 0.5142, + "step": 5198 + }, + { + "epoch": 0.44, + "learning_rate": 1.2301679867116206e-05, + "loss": 0.5103, + "step": 5199 + }, + { + "epoch": 0.44, + "learning_rate": 1.2298992328822937e-05, + "loss": 0.4613, + "step": 5200 + }, + { + "epoch": 0.44, + "learning_rate": 1.2296304615198915e-05, + "loss": 0.4854, + "step": 5201 + }, + { + "epoch": 0.44, + "learning_rate": 1.2293616726449117e-05, + "loss": 0.503, + "step": 5202 + }, + { + "epoch": 0.44, + "learning_rate": 1.2290928662778535e-05, + "loss": 0.4697, + "step": 5203 + }, + { + "epoch": 0.44, + "learning_rate": 1.2288240424392168e-05, + "loss": 0.4844, + "step": 5204 + }, + { + "epoch": 0.44, + "learning_rate": 1.228555201149503e-05, + "loss": 0.4622, + "step": 5205 + }, + { + "epoch": 0.44, + "learning_rate": 1.2282863424292155e-05, + "loss": 0.4678, + "step": 5206 + }, + { + "epoch": 0.44, + "learning_rate": 1.2280174662988587e-05, + "loss": 0.4795, + "step": 5207 + }, + { + "epoch": 0.44, + "learning_rate": 1.2277485727789378e-05, + "loss": 0.4671, + "step": 5208 + }, + { + "epoch": 0.44, + "learning_rate": 1.2274796618899599e-05, + "loss": 0.4825, + "step": 5209 + }, + { + "epoch": 0.44, + "learning_rate": 1.2272107336524333e-05, + "loss": 0.4869, + "step": 5210 + }, + { + "epoch": 0.44, + "learning_rate": 1.2269417880868674e-05, + "loss": 0.5037, + "step": 5211 + }, + { + "epoch": 0.44, + "learning_rate": 1.2266728252137735e-05, + "loss": 0.4696, + "step": 5212 + }, + { + "epoch": 0.44, + "learning_rate": 1.2264038450536637e-05, + "loss": 0.4804, + "step": 5213 + }, + { + "epoch": 0.44, + "learning_rate": 1.2261348476270514e-05, + "loss": 0.4933, + "step": 5214 + }, + { + "epoch": 0.44, + "learning_rate": 1.2258658329544513e-05, + "loss": 0.4851, + "step": 5215 + }, + { + "epoch": 0.44, + "learning_rate": 1.2255968010563799e-05, + "loss": 0.4731, + "step": 5216 + }, + { + "epoch": 0.44, + "learning_rate": 1.2253277519533549e-05, + "loss": 0.4949, + "step": 5217 + }, + { + "epoch": 0.44, + "learning_rate": 1.2250586856658946e-05, + "loss": 0.4768, + "step": 5218 + }, + { + "epoch": 0.45, + "learning_rate": 1.2247896022145194e-05, + "loss": 0.4697, + "step": 5219 + }, + { + "epoch": 0.45, + "learning_rate": 1.2245205016197507e-05, + "loss": 0.4778, + "step": 5220 + }, + { + "epoch": 0.45, + "learning_rate": 1.2242513839021109e-05, + "loss": 0.4798, + "step": 5221 + }, + { + "epoch": 0.45, + "learning_rate": 1.2239822490821247e-05, + "loss": 0.4923, + "step": 5222 + }, + { + "epoch": 0.45, + "learning_rate": 1.2237130971803171e-05, + "loss": 0.4716, + "step": 5223 + }, + { + "epoch": 0.45, + "learning_rate": 1.2234439282172144e-05, + "loss": 0.4978, + "step": 5224 + }, + { + "epoch": 0.45, + "learning_rate": 1.223174742213345e-05, + "loss": 0.4867, + "step": 5225 + }, + { + "epoch": 0.45, + "learning_rate": 1.2229055391892383e-05, + "loss": 0.4742, + "step": 5226 + }, + { + "epoch": 0.45, + "learning_rate": 1.2226363191654244e-05, + "loss": 0.4893, + "step": 5227 + }, + { + "epoch": 0.45, + "learning_rate": 1.2223670821624353e-05, + "loss": 0.4972, + "step": 5228 + }, + { + "epoch": 0.45, + "learning_rate": 1.2220978282008044e-05, + "loss": 0.4669, + "step": 5229 + }, + { + "epoch": 0.45, + "learning_rate": 1.2218285573010654e-05, + "loss": 0.4943, + "step": 5230 + }, + { + "epoch": 0.45, + "learning_rate": 1.221559269483755e-05, + "loss": 0.5037, + "step": 5231 + }, + { + "epoch": 0.45, + "learning_rate": 1.2212899647694094e-05, + "loss": 0.4796, + "step": 5232 + }, + { + "epoch": 0.45, + "learning_rate": 1.2210206431785674e-05, + "loss": 0.4678, + "step": 5233 + }, + { + "epoch": 0.45, + "learning_rate": 1.2207513047317683e-05, + "loss": 0.4901, + "step": 5234 + }, + { + "epoch": 0.45, + "learning_rate": 1.2204819494495531e-05, + "loss": 0.4742, + "step": 5235 + }, + { + "epoch": 0.45, + "learning_rate": 1.220212577352464e-05, + "loss": 0.4719, + "step": 5236 + }, + { + "epoch": 0.45, + "learning_rate": 1.2199431884610444e-05, + "loss": 0.4598, + "step": 5237 + }, + { + "epoch": 0.45, + "learning_rate": 1.2196737827958391e-05, + "loss": 0.4764, + "step": 5238 + }, + { + "epoch": 0.45, + "learning_rate": 1.2194043603773938e-05, + "loss": 0.485, + "step": 5239 + }, + { + "epoch": 0.45, + "learning_rate": 1.2191349212262562e-05, + "loss": 0.4743, + "step": 5240 + }, + { + "epoch": 0.45, + "learning_rate": 1.2188654653629745e-05, + "loss": 0.4614, + "step": 5241 + }, + { + "epoch": 0.45, + "learning_rate": 1.2185959928080988e-05, + "loss": 0.4958, + "step": 5242 + }, + { + "epoch": 0.45, + "learning_rate": 1.21832650358218e-05, + "loss": 0.4733, + "step": 5243 + }, + { + "epoch": 0.45, + "learning_rate": 1.2180569977057706e-05, + "loss": 0.4697, + "step": 5244 + }, + { + "epoch": 0.45, + "learning_rate": 1.217787475199424e-05, + "loss": 0.4722, + "step": 5245 + }, + { + "epoch": 0.45, + "learning_rate": 1.2175179360836955e-05, + "loss": 0.4834, + "step": 5246 + }, + { + "epoch": 0.45, + "learning_rate": 1.2172483803791413e-05, + "loss": 0.4832, + "step": 5247 + }, + { + "epoch": 0.45, + "learning_rate": 1.2169788081063181e-05, + "loss": 0.4899, + "step": 5248 + }, + { + "epoch": 0.45, + "learning_rate": 1.2167092192857854e-05, + "loss": 0.4883, + "step": 5249 + }, + { + "epoch": 0.45, + "learning_rate": 1.2164396139381029e-05, + "loss": 0.4794, + "step": 5250 + }, + { + "epoch": 0.45, + "learning_rate": 1.216169992083832e-05, + "loss": 0.4803, + "step": 5251 + }, + { + "epoch": 0.45, + "learning_rate": 1.2159003537435349e-05, + "loss": 0.4633, + "step": 5252 + }, + { + "epoch": 0.45, + "learning_rate": 1.2156306989377753e-05, + "loss": 0.4767, + "step": 5253 + }, + { + "epoch": 0.45, + "learning_rate": 1.2153610276871187e-05, + "loss": 0.4911, + "step": 5254 + }, + { + "epoch": 0.45, + "learning_rate": 1.2150913400121306e-05, + "loss": 0.4744, + "step": 5255 + }, + { + "epoch": 0.45, + "learning_rate": 1.2148216359333793e-05, + "loss": 0.4626, + "step": 5256 + }, + { + "epoch": 0.45, + "learning_rate": 1.214551915471433e-05, + "loss": 0.4809, + "step": 5257 + }, + { + "epoch": 0.45, + "learning_rate": 1.2142821786468619e-05, + "loss": 0.4779, + "step": 5258 + }, + { + "epoch": 0.45, + "learning_rate": 1.2140124254802374e-05, + "loss": 0.4864, + "step": 5259 + }, + { + "epoch": 0.45, + "learning_rate": 1.2137426559921317e-05, + "loss": 0.485, + "step": 5260 + }, + { + "epoch": 0.45, + "learning_rate": 1.2134728702031189e-05, + "loss": 0.4554, + "step": 5261 + }, + { + "epoch": 0.45, + "learning_rate": 1.2132030681337736e-05, + "loss": 0.4971, + "step": 5262 + }, + { + "epoch": 0.45, + "learning_rate": 1.2129332498046721e-05, + "loss": 0.489, + "step": 5263 + }, + { + "epoch": 0.45, + "learning_rate": 1.2126634152363924e-05, + "loss": 0.4771, + "step": 5264 + }, + { + "epoch": 0.45, + "learning_rate": 1.2123935644495127e-05, + "loss": 0.4823, + "step": 5265 + }, + { + "epoch": 0.45, + "learning_rate": 1.2121236974646127e-05, + "loss": 0.4765, + "step": 5266 + }, + { + "epoch": 0.45, + "learning_rate": 1.2118538143022743e-05, + "loss": 0.4677, + "step": 5267 + }, + { + "epoch": 0.45, + "learning_rate": 1.2115839149830798e-05, + "loss": 0.4582, + "step": 5268 + }, + { + "epoch": 0.45, + "learning_rate": 1.2113139995276118e-05, + "loss": 0.468, + "step": 5269 + }, + { + "epoch": 0.45, + "learning_rate": 1.2110440679564565e-05, + "loss": 0.4975, + "step": 5270 + }, + { + "epoch": 0.45, + "learning_rate": 1.2107741202901996e-05, + "loss": 0.4775, + "step": 5271 + }, + { + "epoch": 0.45, + "learning_rate": 1.210504156549428e-05, + "loss": 0.4867, + "step": 5272 + }, + { + "epoch": 0.45, + "learning_rate": 1.2102341767547308e-05, + "loss": 0.4667, + "step": 5273 + }, + { + "epoch": 0.45, + "learning_rate": 1.2099641809266978e-05, + "loss": 0.4791, + "step": 5274 + }, + { + "epoch": 0.45, + "learning_rate": 1.2096941690859194e-05, + "loss": 0.5093, + "step": 5275 + }, + { + "epoch": 0.45, + "learning_rate": 1.2094241412529883e-05, + "loss": 0.5009, + "step": 5276 + }, + { + "epoch": 0.45, + "learning_rate": 1.2091540974484979e-05, + "loss": 0.4899, + "step": 5277 + }, + { + "epoch": 0.45, + "learning_rate": 1.2088840376930429e-05, + "loss": 0.4956, + "step": 5278 + }, + { + "epoch": 0.45, + "learning_rate": 1.208613962007219e-05, + "loss": 0.4841, + "step": 5279 + }, + { + "epoch": 0.45, + "learning_rate": 1.2083438704116235e-05, + "loss": 0.5001, + "step": 5280 + }, + { + "epoch": 0.45, + "learning_rate": 1.2080737629268546e-05, + "loss": 0.4606, + "step": 5281 + }, + { + "epoch": 0.45, + "learning_rate": 1.2078036395735118e-05, + "loss": 0.4901, + "step": 5282 + }, + { + "epoch": 0.45, + "learning_rate": 1.2075335003721961e-05, + "loss": 0.4861, + "step": 5283 + }, + { + "epoch": 0.45, + "learning_rate": 1.2072633453435092e-05, + "loss": 0.4714, + "step": 5284 + }, + { + "epoch": 0.45, + "learning_rate": 1.206993174508054e-05, + "loss": 0.4869, + "step": 5285 + }, + { + "epoch": 0.45, + "learning_rate": 1.2067229878864355e-05, + "loss": 0.4907, + "step": 5286 + }, + { + "epoch": 0.45, + "learning_rate": 1.2064527854992587e-05, + "loss": 0.4733, + "step": 5287 + }, + { + "epoch": 0.45, + "learning_rate": 1.2061825673671307e-05, + "loss": 0.4775, + "step": 5288 + }, + { + "epoch": 0.45, + "learning_rate": 1.2059123335106592e-05, + "loss": 0.4748, + "step": 5289 + }, + { + "epoch": 0.45, + "learning_rate": 1.2056420839504535e-05, + "loss": 0.4836, + "step": 5290 + }, + { + "epoch": 0.45, + "learning_rate": 1.2053718187071242e-05, + "loss": 0.504, + "step": 5291 + }, + { + "epoch": 0.45, + "learning_rate": 1.2051015378012823e-05, + "loss": 0.4839, + "step": 5292 + }, + { + "epoch": 0.45, + "learning_rate": 1.2048312412535407e-05, + "loss": 0.5011, + "step": 5293 + }, + { + "epoch": 0.45, + "learning_rate": 1.2045609290845137e-05, + "loss": 0.4677, + "step": 5294 + }, + { + "epoch": 0.45, + "learning_rate": 1.2042906013148163e-05, + "loss": 0.4703, + "step": 5295 + }, + { + "epoch": 0.45, + "learning_rate": 1.2040202579650649e-05, + "loss": 0.4902, + "step": 5296 + }, + { + "epoch": 0.45, + "learning_rate": 1.2037498990558768e-05, + "loss": 0.4648, + "step": 5297 + }, + { + "epoch": 0.45, + "learning_rate": 1.2034795246078706e-05, + "loss": 0.5073, + "step": 5298 + }, + { + "epoch": 0.45, + "learning_rate": 1.2032091346416663e-05, + "loss": 0.4633, + "step": 5299 + }, + { + "epoch": 0.45, + "learning_rate": 1.2029387291778854e-05, + "loss": 0.4697, + "step": 5300 + }, + { + "epoch": 0.45, + "learning_rate": 1.202668308237149e-05, + "loss": 0.5039, + "step": 5301 + }, + { + "epoch": 0.45, + "learning_rate": 1.202397871840082e-05, + "loss": 0.4918, + "step": 5302 + }, + { + "epoch": 0.45, + "learning_rate": 1.202127420007308e-05, + "loss": 0.4794, + "step": 5303 + }, + { + "epoch": 0.45, + "learning_rate": 1.2018569527594533e-05, + "loss": 0.4577, + "step": 5304 + }, + { + "epoch": 0.45, + "learning_rate": 1.2015864701171444e-05, + "loss": 0.4847, + "step": 5305 + }, + { + "epoch": 0.45, + "learning_rate": 1.2013159721010101e-05, + "loss": 0.4638, + "step": 5306 + }, + { + "epoch": 0.45, + "learning_rate": 1.201045458731679e-05, + "loss": 0.4853, + "step": 5307 + }, + { + "epoch": 0.45, + "learning_rate": 1.2007749300297818e-05, + "loss": 0.4819, + "step": 5308 + }, + { + "epoch": 0.45, + "learning_rate": 1.2005043860159504e-05, + "loss": 0.4754, + "step": 5309 + }, + { + "epoch": 0.45, + "learning_rate": 1.2002338267108171e-05, + "loss": 0.4678, + "step": 5310 + }, + { + "epoch": 0.45, + "learning_rate": 1.1999632521350168e-05, + "loss": 0.4812, + "step": 5311 + }, + { + "epoch": 0.45, + "learning_rate": 1.1996926623091839e-05, + "loss": 0.4576, + "step": 5312 + }, + { + "epoch": 0.45, + "learning_rate": 1.1994220572539545e-05, + "loss": 0.4559, + "step": 5313 + }, + { + "epoch": 0.45, + "learning_rate": 1.1991514369899668e-05, + "loss": 0.4869, + "step": 5314 + }, + { + "epoch": 0.45, + "learning_rate": 1.1988808015378591e-05, + "loss": 0.4785, + "step": 5315 + }, + { + "epoch": 0.45, + "learning_rate": 1.198610150918271e-05, + "loss": 0.4779, + "step": 5316 + }, + { + "epoch": 0.45, + "learning_rate": 1.1983394851518435e-05, + "loss": 0.4831, + "step": 5317 + }, + { + "epoch": 0.45, + "learning_rate": 1.1980688042592192e-05, + "loss": 0.4924, + "step": 5318 + }, + { + "epoch": 0.45, + "learning_rate": 1.1977981082610406e-05, + "loss": 0.4654, + "step": 5319 + }, + { + "epoch": 0.45, + "learning_rate": 1.1975273971779528e-05, + "loss": 0.4428, + "step": 5320 + }, + { + "epoch": 0.45, + "learning_rate": 1.1972566710306009e-05, + "loss": 0.4799, + "step": 5321 + }, + { + "epoch": 0.45, + "learning_rate": 1.1969859298396317e-05, + "loss": 0.4704, + "step": 5322 + }, + { + "epoch": 0.45, + "learning_rate": 1.1967151736256932e-05, + "loss": 0.4747, + "step": 5323 + }, + { + "epoch": 0.45, + "learning_rate": 1.1964444024094344e-05, + "loss": 0.5067, + "step": 5324 + }, + { + "epoch": 0.45, + "learning_rate": 1.196173616211505e-05, + "loss": 0.5017, + "step": 5325 + }, + { + "epoch": 0.45, + "learning_rate": 1.195902815052557e-05, + "loss": 0.4818, + "step": 5326 + }, + { + "epoch": 0.45, + "learning_rate": 1.1956319989532422e-05, + "loss": 0.4796, + "step": 5327 + }, + { + "epoch": 0.45, + "learning_rate": 1.1953611679342144e-05, + "loss": 0.4995, + "step": 5328 + }, + { + "epoch": 0.45, + "learning_rate": 1.1950903220161286e-05, + "loss": 0.4829, + "step": 5329 + }, + { + "epoch": 0.45, + "learning_rate": 1.1948194612196402e-05, + "loss": 0.5035, + "step": 5330 + }, + { + "epoch": 0.45, + "learning_rate": 1.194548585565406e-05, + "loss": 0.4865, + "step": 5331 + }, + { + "epoch": 0.45, + "learning_rate": 1.1942776950740849e-05, + "loss": 0.4846, + "step": 5332 + }, + { + "epoch": 0.45, + "learning_rate": 1.1940067897663355e-05, + "loss": 0.4734, + "step": 5333 + }, + { + "epoch": 0.45, + "learning_rate": 1.1937358696628185e-05, + "loss": 0.4831, + "step": 5334 + }, + { + "epoch": 0.45, + "learning_rate": 1.193464934784195e-05, + "loss": 0.4863, + "step": 5335 + }, + { + "epoch": 0.45, + "learning_rate": 1.1931939851511283e-05, + "loss": 0.5031, + "step": 5336 + }, + { + "epoch": 0.46, + "learning_rate": 1.1929230207842815e-05, + "loss": 0.488, + "step": 5337 + }, + { + "epoch": 0.46, + "learning_rate": 1.1926520417043195e-05, + "loss": 0.4849, + "step": 5338 + }, + { + "epoch": 0.46, + "learning_rate": 1.1923810479319089e-05, + "loss": 0.476, + "step": 5339 + }, + { + "epoch": 0.46, + "learning_rate": 1.1921100394877158e-05, + "loss": 0.471, + "step": 5340 + }, + { + "epoch": 0.46, + "learning_rate": 1.1918390163924098e-05, + "loss": 0.4909, + "step": 5341 + }, + { + "epoch": 0.46, + "learning_rate": 1.1915679786666592e-05, + "loss": 0.4677, + "step": 5342 + }, + { + "epoch": 0.46, + "learning_rate": 1.1912969263311345e-05, + "loss": 0.4979, + "step": 5343 + }, + { + "epoch": 0.46, + "learning_rate": 1.1910258594065079e-05, + "loss": 0.464, + "step": 5344 + }, + { + "epoch": 0.46, + "learning_rate": 1.1907547779134518e-05, + "loss": 0.486, + "step": 5345 + }, + { + "epoch": 0.46, + "learning_rate": 1.1904836818726397e-05, + "loss": 0.4877, + "step": 5346 + }, + { + "epoch": 0.46, + "learning_rate": 1.1902125713047467e-05, + "loss": 0.4732, + "step": 5347 + }, + { + "epoch": 0.46, + "learning_rate": 1.1899414462304496e-05, + "loss": 0.469, + "step": 5348 + }, + { + "epoch": 0.46, + "learning_rate": 1.1896703066704238e-05, + "loss": 0.4561, + "step": 5349 + }, + { + "epoch": 0.46, + "learning_rate": 1.1893991526453493e-05, + "loss": 0.4831, + "step": 5350 + }, + { + "epoch": 0.46, + "learning_rate": 1.1891279841759044e-05, + "loss": 0.4953, + "step": 5351 + }, + { + "epoch": 0.46, + "learning_rate": 1.18885680128277e-05, + "loss": 0.4627, + "step": 5352 + }, + { + "epoch": 0.46, + "learning_rate": 1.1885856039866275e-05, + "loss": 0.498, + "step": 5353 + }, + { + "epoch": 0.46, + "learning_rate": 1.1883143923081592e-05, + "loss": 0.4707, + "step": 5354 + }, + { + "epoch": 0.46, + "learning_rate": 1.1880431662680494e-05, + "loss": 0.4781, + "step": 5355 + }, + { + "epoch": 0.46, + "learning_rate": 1.1877719258869827e-05, + "loss": 0.4689, + "step": 5356 + }, + { + "epoch": 0.46, + "learning_rate": 1.1875006711856452e-05, + "loss": 0.4966, + "step": 5357 + }, + { + "epoch": 0.46, + "learning_rate": 1.1872294021847231e-05, + "loss": 0.4923, + "step": 5358 + }, + { + "epoch": 0.46, + "learning_rate": 1.1869581189049057e-05, + "loss": 0.4654, + "step": 5359 + }, + { + "epoch": 0.46, + "learning_rate": 1.1866868213668813e-05, + "loss": 0.4936, + "step": 5360 + }, + { + "epoch": 0.46, + "learning_rate": 1.1864155095913407e-05, + "loss": 0.502, + "step": 5361 + }, + { + "epoch": 0.46, + "learning_rate": 1.1861441835989754e-05, + "loss": 0.4798, + "step": 5362 + }, + { + "epoch": 0.46, + "learning_rate": 1.1858728434104769e-05, + "loss": 0.467, + "step": 5363 + }, + { + "epoch": 0.46, + "learning_rate": 1.1856014890465396e-05, + "loss": 0.4784, + "step": 5364 + }, + { + "epoch": 0.46, + "learning_rate": 1.1853301205278579e-05, + "loss": 0.4778, + "step": 5365 + }, + { + "epoch": 0.46, + "learning_rate": 1.1850587378751274e-05, + "loss": 0.4733, + "step": 5366 + }, + { + "epoch": 0.46, + "learning_rate": 1.184787341109045e-05, + "loss": 0.5015, + "step": 5367 + }, + { + "epoch": 0.46, + "learning_rate": 1.1845159302503086e-05, + "loss": 0.4649, + "step": 5368 + }, + { + "epoch": 0.46, + "learning_rate": 1.184244505319617e-05, + "loss": 0.4803, + "step": 5369 + }, + { + "epoch": 0.46, + "learning_rate": 1.18397306633767e-05, + "loss": 0.4946, + "step": 5370 + }, + { + "epoch": 0.46, + "learning_rate": 1.1837016133251695e-05, + "loss": 0.4693, + "step": 5371 + }, + { + "epoch": 0.46, + "learning_rate": 1.1834301463028166e-05, + "loss": 0.4811, + "step": 5372 + }, + { + "epoch": 0.46, + "learning_rate": 1.1831586652913147e-05, + "loss": 0.4797, + "step": 5373 + }, + { + "epoch": 0.46, + "learning_rate": 1.1828871703113686e-05, + "loss": 0.4794, + "step": 5374 + }, + { + "epoch": 0.46, + "learning_rate": 1.1826156613836835e-05, + "loss": 0.4615, + "step": 5375 + }, + { + "epoch": 0.46, + "learning_rate": 1.1823441385289656e-05, + "loss": 0.4812, + "step": 5376 + }, + { + "epoch": 0.46, + "learning_rate": 1.1820726017679222e-05, + "loss": 0.4821, + "step": 5377 + }, + { + "epoch": 0.46, + "learning_rate": 1.1818010511212624e-05, + "loss": 0.4888, + "step": 5378 + }, + { + "epoch": 0.46, + "learning_rate": 1.181529486609695e-05, + "loss": 0.4973, + "step": 5379 + }, + { + "epoch": 0.46, + "learning_rate": 1.1812579082539317e-05, + "loss": 0.468, + "step": 5380 + }, + { + "epoch": 0.46, + "learning_rate": 1.180986316074683e-05, + "loss": 0.4945, + "step": 5381 + }, + { + "epoch": 0.46, + "learning_rate": 1.1807147100926626e-05, + "loss": 0.4886, + "step": 5382 + }, + { + "epoch": 0.46, + "learning_rate": 1.1804430903285837e-05, + "loss": 0.4783, + "step": 5383 + }, + { + "epoch": 0.46, + "learning_rate": 1.1801714568031615e-05, + "loss": 0.4909, + "step": 5384 + }, + { + "epoch": 0.46, + "learning_rate": 1.1798998095371119e-05, + "loss": 0.473, + "step": 5385 + }, + { + "epoch": 0.46, + "learning_rate": 1.1796281485511519e-05, + "loss": 0.4936, + "step": 5386 + }, + { + "epoch": 0.46, + "learning_rate": 1.1793564738659988e-05, + "loss": 0.4731, + "step": 5387 + }, + { + "epoch": 0.46, + "learning_rate": 1.1790847855023727e-05, + "loss": 0.4825, + "step": 5388 + }, + { + "epoch": 0.46, + "learning_rate": 1.1788130834809932e-05, + "loss": 0.4743, + "step": 5389 + }, + { + "epoch": 0.46, + "learning_rate": 1.178541367822581e-05, + "loss": 0.4848, + "step": 5390 + }, + { + "epoch": 0.46, + "learning_rate": 1.1782696385478593e-05, + "loss": 0.4619, + "step": 5391 + }, + { + "epoch": 0.46, + "learning_rate": 1.1779978956775507e-05, + "loss": 0.4866, + "step": 5392 + }, + { + "epoch": 0.46, + "learning_rate": 1.1777261392323789e-05, + "loss": 0.4843, + "step": 5393 + }, + { + "epoch": 0.46, + "learning_rate": 1.17745436923307e-05, + "loss": 0.4741, + "step": 5394 + }, + { + "epoch": 0.46, + "learning_rate": 1.17718258570035e-05, + "loss": 0.4986, + "step": 5395 + }, + { + "epoch": 0.46, + "learning_rate": 1.1769107886549465e-05, + "loss": 0.4614, + "step": 5396 + }, + { + "epoch": 0.46, + "learning_rate": 1.1766389781175876e-05, + "loss": 0.4716, + "step": 5397 + }, + { + "epoch": 0.46, + "learning_rate": 1.1763671541090027e-05, + "loss": 0.4846, + "step": 5398 + }, + { + "epoch": 0.46, + "learning_rate": 1.1760953166499221e-05, + "loss": 0.4808, + "step": 5399 + }, + { + "epoch": 0.46, + "learning_rate": 1.1758234657610778e-05, + "loss": 0.4841, + "step": 5400 + }, + { + "epoch": 0.46, + "learning_rate": 1.1755516014632023e-05, + "loss": 0.5047, + "step": 5401 + }, + { + "epoch": 0.46, + "learning_rate": 1.1752797237770279e-05, + "loss": 0.4813, + "step": 5402 + }, + { + "epoch": 0.46, + "learning_rate": 1.1750078327232908e-05, + "loss": 0.4736, + "step": 5403 + }, + { + "epoch": 0.46, + "learning_rate": 1.1747359283227251e-05, + "loss": 0.4669, + "step": 5404 + }, + { + "epoch": 0.46, + "learning_rate": 1.1744640105960683e-05, + "loss": 0.4718, + "step": 5405 + }, + { + "epoch": 0.46, + "learning_rate": 1.1741920795640578e-05, + "loss": 0.4925, + "step": 5406 + }, + { + "epoch": 0.46, + "learning_rate": 1.1739201352474322e-05, + "loss": 0.4518, + "step": 5407 + }, + { + "epoch": 0.46, + "learning_rate": 1.1736481776669307e-05, + "loss": 0.4872, + "step": 5408 + }, + { + "epoch": 0.46, + "learning_rate": 1.173376206843294e-05, + "loss": 0.5035, + "step": 5409 + }, + { + "epoch": 0.46, + "learning_rate": 1.1731042227972645e-05, + "loss": 0.473, + "step": 5410 + }, + { + "epoch": 0.46, + "learning_rate": 1.1728322255495836e-05, + "loss": 0.4834, + "step": 5411 + }, + { + "epoch": 0.46, + "learning_rate": 1.1725602151209962e-05, + "loss": 0.4818, + "step": 5412 + }, + { + "epoch": 0.46, + "learning_rate": 1.1722881915322462e-05, + "loss": 0.5011, + "step": 5413 + }, + { + "epoch": 0.46, + "learning_rate": 1.1720161548040793e-05, + "loss": 0.4643, + "step": 5414 + }, + { + "epoch": 0.46, + "learning_rate": 1.1717441049572427e-05, + "loss": 0.4882, + "step": 5415 + }, + { + "epoch": 0.46, + "learning_rate": 1.1714720420124833e-05, + "loss": 0.4793, + "step": 5416 + }, + { + "epoch": 0.46, + "learning_rate": 1.17119996599055e-05, + "loss": 0.4704, + "step": 5417 + }, + { + "epoch": 0.46, + "learning_rate": 1.1709278769121928e-05, + "loss": 0.4833, + "step": 5418 + }, + { + "epoch": 0.46, + "learning_rate": 1.1706557747981622e-05, + "loss": 0.4757, + "step": 5419 + }, + { + "epoch": 0.46, + "learning_rate": 1.1703836596692094e-05, + "loss": 0.4915, + "step": 5420 + }, + { + "epoch": 0.46, + "learning_rate": 1.1701115315460875e-05, + "loss": 0.4924, + "step": 5421 + }, + { + "epoch": 0.46, + "learning_rate": 1.16983939044955e-05, + "loss": 0.4657, + "step": 5422 + }, + { + "epoch": 0.46, + "learning_rate": 1.1695672364003516e-05, + "loss": 0.4985, + "step": 5423 + }, + { + "epoch": 0.46, + "learning_rate": 1.169295069419248e-05, + "loss": 0.4988, + "step": 5424 + }, + { + "epoch": 0.46, + "learning_rate": 1.1690228895269953e-05, + "loss": 0.5054, + "step": 5425 + }, + { + "epoch": 0.46, + "learning_rate": 1.1687506967443516e-05, + "loss": 0.4675, + "step": 5426 + }, + { + "epoch": 0.46, + "learning_rate": 1.168478491092075e-05, + "loss": 0.471, + "step": 5427 + }, + { + "epoch": 0.46, + "learning_rate": 1.1682062725909257e-05, + "loss": 0.5117, + "step": 5428 + }, + { + "epoch": 0.46, + "learning_rate": 1.1679340412616633e-05, + "loss": 0.4814, + "step": 5429 + }, + { + "epoch": 0.46, + "learning_rate": 1.1676617971250504e-05, + "loss": 0.4549, + "step": 5430 + }, + { + "epoch": 0.46, + "learning_rate": 1.1673895402018484e-05, + "loss": 0.4818, + "step": 5431 + }, + { + "epoch": 0.46, + "learning_rate": 1.1671172705128216e-05, + "loss": 0.4868, + "step": 5432 + }, + { + "epoch": 0.46, + "learning_rate": 1.1668449880787338e-05, + "loss": 0.4668, + "step": 5433 + }, + { + "epoch": 0.46, + "learning_rate": 1.1665726929203509e-05, + "loss": 0.4625, + "step": 5434 + }, + { + "epoch": 0.46, + "learning_rate": 1.1663003850584387e-05, + "loss": 0.4778, + "step": 5435 + }, + { + "epoch": 0.46, + "learning_rate": 1.166028064513765e-05, + "loss": 0.4708, + "step": 5436 + }, + { + "epoch": 0.46, + "learning_rate": 1.165755731307098e-05, + "loss": 0.4788, + "step": 5437 + }, + { + "epoch": 0.46, + "learning_rate": 1.1654833854592067e-05, + "loss": 0.484, + "step": 5438 + }, + { + "epoch": 0.46, + "learning_rate": 1.1652110269908618e-05, + "loss": 0.4788, + "step": 5439 + }, + { + "epoch": 0.46, + "learning_rate": 1.1649386559228342e-05, + "loss": 0.4546, + "step": 5440 + }, + { + "epoch": 0.46, + "learning_rate": 1.1646662722758961e-05, + "loss": 0.4895, + "step": 5441 + }, + { + "epoch": 0.46, + "learning_rate": 1.1643938760708207e-05, + "loss": 0.4755, + "step": 5442 + }, + { + "epoch": 0.46, + "learning_rate": 1.1641214673283818e-05, + "loss": 0.4876, + "step": 5443 + }, + { + "epoch": 0.46, + "learning_rate": 1.1638490460693546e-05, + "loss": 0.4713, + "step": 5444 + }, + { + "epoch": 0.46, + "learning_rate": 1.1635766123145151e-05, + "loss": 0.4917, + "step": 5445 + }, + { + "epoch": 0.46, + "learning_rate": 1.1633041660846405e-05, + "loss": 0.4667, + "step": 5446 + }, + { + "epoch": 0.46, + "learning_rate": 1.1630317074005082e-05, + "loss": 0.4812, + "step": 5447 + }, + { + "epoch": 0.46, + "learning_rate": 1.1627592362828972e-05, + "loss": 0.4897, + "step": 5448 + }, + { + "epoch": 0.46, + "learning_rate": 1.1624867527525876e-05, + "loss": 0.448, + "step": 5449 + }, + { + "epoch": 0.46, + "learning_rate": 1.1622142568303596e-05, + "loss": 0.5137, + "step": 5450 + }, + { + "epoch": 0.46, + "learning_rate": 1.1619417485369954e-05, + "loss": 0.4571, + "step": 5451 + }, + { + "epoch": 0.46, + "learning_rate": 1.1616692278932772e-05, + "loss": 0.4825, + "step": 5452 + }, + { + "epoch": 0.46, + "learning_rate": 1.1613966949199886e-05, + "loss": 0.4535, + "step": 5453 + }, + { + "epoch": 0.47, + "learning_rate": 1.1611241496379144e-05, + "loss": 0.4777, + "step": 5454 + }, + { + "epoch": 0.47, + "learning_rate": 1.1608515920678398e-05, + "loss": 0.4902, + "step": 5455 + }, + { + "epoch": 0.47, + "learning_rate": 1.1605790222305516e-05, + "loss": 0.4963, + "step": 5456 + }, + { + "epoch": 0.47, + "learning_rate": 1.1603064401468364e-05, + "loss": 0.5008, + "step": 5457 + }, + { + "epoch": 0.47, + "learning_rate": 1.1600338458374829e-05, + "loss": 0.5062, + "step": 5458 + }, + { + "epoch": 0.47, + "learning_rate": 1.1597612393232803e-05, + "loss": 0.508, + "step": 5459 + }, + { + "epoch": 0.47, + "learning_rate": 1.1594886206250186e-05, + "loss": 0.4816, + "step": 5460 + }, + { + "epoch": 0.47, + "learning_rate": 1.1592159897634887e-05, + "loss": 0.4905, + "step": 5461 + }, + { + "epoch": 0.47, + "learning_rate": 1.1589433467594826e-05, + "loss": 0.4678, + "step": 5462 + }, + { + "epoch": 0.47, + "learning_rate": 1.1586706916337937e-05, + "loss": 0.4969, + "step": 5463 + }, + { + "epoch": 0.47, + "learning_rate": 1.158398024407215e-05, + "loss": 0.4937, + "step": 5464 + }, + { + "epoch": 0.47, + "learning_rate": 1.158125345100542e-05, + "loss": 0.487, + "step": 5465 + }, + { + "epoch": 0.47, + "learning_rate": 1.1578526537345698e-05, + "loss": 0.4695, + "step": 5466 + }, + { + "epoch": 0.47, + "learning_rate": 1.1575799503300952e-05, + "loss": 0.4796, + "step": 5467 + }, + { + "epoch": 0.47, + "learning_rate": 1.157307234907916e-05, + "loss": 0.4897, + "step": 5468 + }, + { + "epoch": 0.47, + "learning_rate": 1.1570345074888304e-05, + "loss": 0.4688, + "step": 5469 + }, + { + "epoch": 0.47, + "learning_rate": 1.1567617680936372e-05, + "loss": 0.4739, + "step": 5470 + }, + { + "epoch": 0.47, + "learning_rate": 1.1564890167431372e-05, + "loss": 0.475, + "step": 5471 + }, + { + "epoch": 0.47, + "learning_rate": 1.1562162534581318e-05, + "loss": 0.4597, + "step": 5472 + }, + { + "epoch": 0.47, + "learning_rate": 1.1559434782594224e-05, + "loss": 0.4983, + "step": 5473 + }, + { + "epoch": 0.47, + "learning_rate": 1.1556706911678124e-05, + "loss": 0.4844, + "step": 5474 + }, + { + "epoch": 0.47, + "learning_rate": 1.1553978922041055e-05, + "loss": 0.4916, + "step": 5475 + }, + { + "epoch": 0.47, + "learning_rate": 1.1551250813891066e-05, + "loss": 0.4642, + "step": 5476 + }, + { + "epoch": 0.47, + "learning_rate": 1.1548522587436216e-05, + "loss": 0.4888, + "step": 5477 + }, + { + "epoch": 0.47, + "learning_rate": 1.1545794242884567e-05, + "loss": 0.4671, + "step": 5478 + }, + { + "epoch": 0.47, + "learning_rate": 1.1543065780444196e-05, + "loss": 0.4828, + "step": 5479 + }, + { + "epoch": 0.47, + "learning_rate": 1.1540337200323187e-05, + "loss": 0.4696, + "step": 5480 + }, + { + "epoch": 0.47, + "learning_rate": 1.153760850272963e-05, + "loss": 0.498, + "step": 5481 + }, + { + "epoch": 0.47, + "learning_rate": 1.1534879687871629e-05, + "loss": 0.4759, + "step": 5482 + }, + { + "epoch": 0.47, + "learning_rate": 1.15321507559573e-05, + "loss": 0.4896, + "step": 5483 + }, + { + "epoch": 0.47, + "learning_rate": 1.1529421707194753e-05, + "loss": 0.481, + "step": 5484 + }, + { + "epoch": 0.47, + "learning_rate": 1.1526692541792122e-05, + "loss": 0.4757, + "step": 5485 + }, + { + "epoch": 0.47, + "learning_rate": 1.1523963259957546e-05, + "loss": 0.4954, + "step": 5486 + }, + { + "epoch": 0.47, + "learning_rate": 1.1521233861899168e-05, + "loss": 0.4989, + "step": 5487 + }, + { + "epoch": 0.47, + "learning_rate": 1.1518504347825146e-05, + "loss": 0.4551, + "step": 5488 + }, + { + "epoch": 0.47, + "learning_rate": 1.1515774717943642e-05, + "loss": 0.479, + "step": 5489 + }, + { + "epoch": 0.47, + "learning_rate": 1.151304497246283e-05, + "loss": 0.4766, + "step": 5490 + }, + { + "epoch": 0.47, + "learning_rate": 1.151031511159089e-05, + "loss": 0.5058, + "step": 5491 + }, + { + "epoch": 0.47, + "learning_rate": 1.1507585135536017e-05, + "loss": 0.4571, + "step": 5492 + }, + { + "epoch": 0.47, + "learning_rate": 1.1504855044506407e-05, + "loss": 0.4647, + "step": 5493 + }, + { + "epoch": 0.47, + "learning_rate": 1.1502124838710268e-05, + "loss": 0.4953, + "step": 5494 + }, + { + "epoch": 0.47, + "learning_rate": 1.1499394518355818e-05, + "loss": 0.4736, + "step": 5495 + }, + { + "epoch": 0.47, + "learning_rate": 1.1496664083651281e-05, + "loss": 0.4839, + "step": 5496 + }, + { + "epoch": 0.47, + "learning_rate": 1.1493933534804892e-05, + "loss": 0.478, + "step": 5497 + }, + { + "epoch": 0.47, + "learning_rate": 1.1491202872024896e-05, + "loss": 0.4718, + "step": 5498 + }, + { + "epoch": 0.47, + "learning_rate": 1.1488472095519545e-05, + "loss": 0.4842, + "step": 5499 + }, + { + "epoch": 0.47, + "learning_rate": 1.1485741205497094e-05, + "loss": 0.4874, + "step": 5500 + }, + { + "epoch": 0.47, + "learning_rate": 1.1483010202165821e-05, + "loss": 0.4706, + "step": 5501 + }, + { + "epoch": 0.47, + "learning_rate": 1.1480279085733997e-05, + "loss": 0.4773, + "step": 5502 + }, + { + "epoch": 0.47, + "learning_rate": 1.1477547856409905e-05, + "loss": 0.4887, + "step": 5503 + }, + { + "epoch": 0.47, + "learning_rate": 1.1474816514401851e-05, + "loss": 0.4735, + "step": 5504 + }, + { + "epoch": 0.47, + "learning_rate": 1.147208505991813e-05, + "loss": 0.4806, + "step": 5505 + }, + { + "epoch": 0.47, + "learning_rate": 1.1469353493167056e-05, + "loss": 0.4702, + "step": 5506 + }, + { + "epoch": 0.47, + "learning_rate": 1.1466621814356951e-05, + "loss": 0.4772, + "step": 5507 + }, + { + "epoch": 0.47, + "learning_rate": 1.1463890023696145e-05, + "loss": 0.4817, + "step": 5508 + }, + { + "epoch": 0.47, + "learning_rate": 1.1461158121392972e-05, + "loss": 0.4944, + "step": 5509 + }, + { + "epoch": 0.47, + "learning_rate": 1.145842610765578e-05, + "loss": 0.4888, + "step": 5510 + }, + { + "epoch": 0.47, + "learning_rate": 1.1455693982692926e-05, + "loss": 0.4935, + "step": 5511 + }, + { + "epoch": 0.47, + "learning_rate": 1.1452961746712769e-05, + "loss": 0.4941, + "step": 5512 + }, + { + "epoch": 0.47, + "learning_rate": 1.1450229399923687e-05, + "loss": 0.4742, + "step": 5513 + }, + { + "epoch": 0.47, + "learning_rate": 1.1447496942534056e-05, + "loss": 0.4823, + "step": 5514 + }, + { + "epoch": 0.47, + "learning_rate": 1.1444764374752262e-05, + "loss": 0.4801, + "step": 5515 + }, + { + "epoch": 0.47, + "learning_rate": 1.1442031696786707e-05, + "loss": 0.4736, + "step": 5516 + }, + { + "epoch": 0.47, + "learning_rate": 1.1439298908845795e-05, + "loss": 0.4635, + "step": 5517 + }, + { + "epoch": 0.47, + "learning_rate": 1.143656601113794e-05, + "loss": 0.5015, + "step": 5518 + }, + { + "epoch": 0.47, + "learning_rate": 1.143383300387156e-05, + "loss": 0.4908, + "step": 5519 + }, + { + "epoch": 0.47, + "learning_rate": 1.143109988725509e-05, + "loss": 0.4615, + "step": 5520 + }, + { + "epoch": 0.47, + "learning_rate": 1.1428366661496971e-05, + "loss": 0.4867, + "step": 5521 + }, + { + "epoch": 0.47, + "learning_rate": 1.1425633326805645e-05, + "loss": 0.5, + "step": 5522 + }, + { + "epoch": 0.47, + "learning_rate": 1.1422899883389569e-05, + "loss": 0.5025, + "step": 5523 + }, + { + "epoch": 0.47, + "learning_rate": 1.1420166331457208e-05, + "loss": 0.4537, + "step": 5524 + }, + { + "epoch": 0.47, + "learning_rate": 1.1417432671217037e-05, + "loss": 0.49, + "step": 5525 + }, + { + "epoch": 0.47, + "learning_rate": 1.1414698902877528e-05, + "loss": 0.4957, + "step": 5526 + }, + { + "epoch": 0.47, + "learning_rate": 1.1411965026647177e-05, + "loss": 0.457, + "step": 5527 + }, + { + "epoch": 0.47, + "learning_rate": 1.1409231042734476e-05, + "loss": 0.4848, + "step": 5528 + }, + { + "epoch": 0.47, + "learning_rate": 1.1406496951347934e-05, + "loss": 0.4853, + "step": 5529 + }, + { + "epoch": 0.47, + "learning_rate": 1.140376275269606e-05, + "loss": 0.4578, + "step": 5530 + }, + { + "epoch": 0.47, + "learning_rate": 1.1401028446987384e-05, + "loss": 0.4907, + "step": 5531 + }, + { + "epoch": 0.47, + "learning_rate": 1.1398294034430423e-05, + "loss": 0.4982, + "step": 5532 + }, + { + "epoch": 0.47, + "learning_rate": 1.1395559515233726e-05, + "loss": 0.4857, + "step": 5533 + }, + { + "epoch": 0.47, + "learning_rate": 1.1392824889605834e-05, + "loss": 0.4717, + "step": 5534 + }, + { + "epoch": 0.47, + "learning_rate": 1.1390090157755298e-05, + "loss": 0.4959, + "step": 5535 + }, + { + "epoch": 0.47, + "learning_rate": 1.1387355319890685e-05, + "loss": 0.4895, + "step": 5536 + }, + { + "epoch": 0.47, + "learning_rate": 1.138462037622056e-05, + "loss": 0.4563, + "step": 5537 + }, + { + "epoch": 0.47, + "learning_rate": 1.1381885326953507e-05, + "loss": 0.4824, + "step": 5538 + }, + { + "epoch": 0.47, + "learning_rate": 1.137915017229811e-05, + "loss": 0.4826, + "step": 5539 + }, + { + "epoch": 0.47, + "learning_rate": 1.1376414912462964e-05, + "loss": 0.4932, + "step": 5540 + }, + { + "epoch": 0.47, + "learning_rate": 1.1373679547656669e-05, + "loss": 0.4733, + "step": 5541 + }, + { + "epoch": 0.47, + "learning_rate": 1.1370944078087837e-05, + "loss": 0.4793, + "step": 5542 + }, + { + "epoch": 0.47, + "learning_rate": 1.1368208503965087e-05, + "loss": 0.4749, + "step": 5543 + }, + { + "epoch": 0.47, + "learning_rate": 1.1365472825497041e-05, + "loss": 0.4744, + "step": 5544 + }, + { + "epoch": 0.47, + "learning_rate": 1.1362737042892342e-05, + "loss": 0.4788, + "step": 5545 + }, + { + "epoch": 0.47, + "learning_rate": 1.1360001156359623e-05, + "loss": 0.4729, + "step": 5546 + }, + { + "epoch": 0.47, + "learning_rate": 1.1357265166107538e-05, + "loss": 0.4772, + "step": 5547 + }, + { + "epoch": 0.47, + "learning_rate": 1.1354529072344749e-05, + "loss": 0.4866, + "step": 5548 + }, + { + "epoch": 0.47, + "learning_rate": 1.1351792875279914e-05, + "loss": 0.489, + "step": 5549 + }, + { + "epoch": 0.47, + "learning_rate": 1.1349056575121713e-05, + "loss": 0.4761, + "step": 5550 + }, + { + "epoch": 0.47, + "learning_rate": 1.1346320172078822e-05, + "loss": 0.4759, + "step": 5551 + }, + { + "epoch": 0.47, + "learning_rate": 1.1343583666359938e-05, + "loss": 0.4973, + "step": 5552 + }, + { + "epoch": 0.47, + "learning_rate": 1.1340847058173752e-05, + "loss": 0.4775, + "step": 5553 + }, + { + "epoch": 0.47, + "learning_rate": 1.1338110347728973e-05, + "loss": 0.491, + "step": 5554 + }, + { + "epoch": 0.47, + "learning_rate": 1.1335373535234312e-05, + "loss": 0.4867, + "step": 5555 + }, + { + "epoch": 0.47, + "learning_rate": 1.1332636620898487e-05, + "loss": 0.4774, + "step": 5556 + }, + { + "epoch": 0.47, + "learning_rate": 1.1329899604930235e-05, + "loss": 0.477, + "step": 5557 + }, + { + "epoch": 0.47, + "learning_rate": 1.1327162487538283e-05, + "loss": 0.4967, + "step": 5558 + }, + { + "epoch": 0.47, + "learning_rate": 1.132442526893138e-05, + "loss": 0.4683, + "step": 5559 + }, + { + "epoch": 0.47, + "learning_rate": 1.1321687949318276e-05, + "loss": 0.4716, + "step": 5560 + }, + { + "epoch": 0.47, + "learning_rate": 1.1318950528907734e-05, + "loss": 0.4754, + "step": 5561 + }, + { + "epoch": 0.47, + "learning_rate": 1.1316213007908514e-05, + "loss": 0.4879, + "step": 5562 + }, + { + "epoch": 0.47, + "learning_rate": 1.13134753865294e-05, + "loss": 0.4488, + "step": 5563 + }, + { + "epoch": 0.47, + "learning_rate": 1.1310737664979168e-05, + "loss": 0.4789, + "step": 5564 + }, + { + "epoch": 0.47, + "learning_rate": 1.1307999843466605e-05, + "loss": 0.4988, + "step": 5565 + }, + { + "epoch": 0.47, + "learning_rate": 1.130526192220052e-05, + "loss": 0.4812, + "step": 5566 + }, + { + "epoch": 0.47, + "learning_rate": 1.1302523901389706e-05, + "loss": 0.4726, + "step": 5567 + }, + { + "epoch": 0.47, + "learning_rate": 1.1299785781242982e-05, + "loss": 0.4716, + "step": 5568 + }, + { + "epoch": 0.47, + "learning_rate": 1.129704756196917e-05, + "loss": 0.4723, + "step": 5569 + }, + { + "epoch": 0.47, + "learning_rate": 1.1294309243777094e-05, + "loss": 0.4644, + "step": 5570 + }, + { + "epoch": 0.48, + "learning_rate": 1.1291570826875593e-05, + "loss": 0.4906, + "step": 5571 + }, + { + "epoch": 0.48, + "learning_rate": 1.1288832311473507e-05, + "loss": 0.4864, + "step": 5572 + }, + { + "epoch": 0.48, + "learning_rate": 1.1286093697779692e-05, + "loss": 0.4807, + "step": 5573 + }, + { + "epoch": 0.48, + "learning_rate": 1.1283354986002997e-05, + "loss": 0.4735, + "step": 5574 + }, + { + "epoch": 0.48, + "learning_rate": 1.1280616176352299e-05, + "loss": 0.472, + "step": 5575 + }, + { + "epoch": 0.48, + "learning_rate": 1.1277877269036461e-05, + "loss": 0.478, + "step": 5576 + }, + { + "epoch": 0.48, + "learning_rate": 1.1275138264264366e-05, + "loss": 0.4696, + "step": 5577 + }, + { + "epoch": 0.48, + "learning_rate": 1.1272399162244907e-05, + "loss": 0.4794, + "step": 5578 + }, + { + "epoch": 0.48, + "learning_rate": 1.1269659963186976e-05, + "loss": 0.4623, + "step": 5579 + }, + { + "epoch": 0.48, + "learning_rate": 1.1266920667299473e-05, + "loss": 0.4715, + "step": 5580 + }, + { + "epoch": 0.48, + "learning_rate": 1.1264181274791311e-05, + "loss": 0.4637, + "step": 5581 + }, + { + "epoch": 0.48, + "learning_rate": 1.126144178587141e-05, + "loss": 0.481, + "step": 5582 + }, + { + "epoch": 0.48, + "learning_rate": 1.1258702200748685e-05, + "loss": 0.4759, + "step": 5583 + }, + { + "epoch": 0.48, + "learning_rate": 1.1255962519632082e-05, + "loss": 0.4553, + "step": 5584 + }, + { + "epoch": 0.48, + "learning_rate": 1.1253222742730531e-05, + "loss": 0.4819, + "step": 5585 + }, + { + "epoch": 0.48, + "learning_rate": 1.1250482870252984e-05, + "loss": 0.4721, + "step": 5586 + }, + { + "epoch": 0.48, + "learning_rate": 1.1247742902408391e-05, + "loss": 0.4786, + "step": 5587 + }, + { + "epoch": 0.48, + "learning_rate": 1.1245002839405714e-05, + "loss": 0.4762, + "step": 5588 + }, + { + "epoch": 0.48, + "learning_rate": 1.1242262681453924e-05, + "loss": 0.4697, + "step": 5589 + }, + { + "epoch": 0.48, + "learning_rate": 1.1239522428761996e-05, + "loss": 0.4809, + "step": 5590 + }, + { + "epoch": 0.48, + "learning_rate": 1.1236782081538915e-05, + "loss": 0.476, + "step": 5591 + }, + { + "epoch": 0.48, + "learning_rate": 1.1234041639993663e-05, + "loss": 0.4662, + "step": 5592 + }, + { + "epoch": 0.48, + "learning_rate": 1.1231301104335248e-05, + "loss": 0.474, + "step": 5593 + }, + { + "epoch": 0.48, + "learning_rate": 1.122856047477267e-05, + "loss": 0.4922, + "step": 5594 + }, + { + "epoch": 0.48, + "learning_rate": 1.122581975151494e-05, + "loss": 0.4724, + "step": 5595 + }, + { + "epoch": 0.48, + "learning_rate": 1.1223078934771079e-05, + "loss": 0.495, + "step": 5596 + }, + { + "epoch": 0.48, + "learning_rate": 1.122033802475011e-05, + "loss": 0.5025, + "step": 5597 + }, + { + "epoch": 0.48, + "learning_rate": 1.1217597021661071e-05, + "loss": 0.4784, + "step": 5598 + }, + { + "epoch": 0.48, + "learning_rate": 1.1214855925712998e-05, + "loss": 0.4935, + "step": 5599 + }, + { + "epoch": 0.48, + "learning_rate": 1.1212114737114941e-05, + "loss": 0.4979, + "step": 5600 + }, + { + "epoch": 0.48, + "learning_rate": 1.1209373456075952e-05, + "loss": 0.478, + "step": 5601 + }, + { + "epoch": 0.48, + "learning_rate": 1.1206632082805099e-05, + "loss": 0.4863, + "step": 5602 + }, + { + "epoch": 0.48, + "learning_rate": 1.120389061751144e-05, + "loss": 0.4843, + "step": 5603 + }, + { + "epoch": 0.48, + "learning_rate": 1.120114906040406e-05, + "loss": 0.4644, + "step": 5604 + }, + { + "epoch": 0.48, + "learning_rate": 1.1198407411692041e-05, + "loss": 0.4508, + "step": 5605 + }, + { + "epoch": 0.48, + "learning_rate": 1.1195665671584463e-05, + "loss": 0.4908, + "step": 5606 + }, + { + "epoch": 0.48, + "learning_rate": 1.1192923840290433e-05, + "loss": 0.4698, + "step": 5607 + }, + { + "epoch": 0.48, + "learning_rate": 1.119018191801905e-05, + "loss": 0.4807, + "step": 5608 + }, + { + "epoch": 0.48, + "learning_rate": 1.1187439904979422e-05, + "loss": 0.4769, + "step": 5609 + }, + { + "epoch": 0.48, + "learning_rate": 1.1184697801380673e-05, + "loss": 0.4794, + "step": 5610 + }, + { + "epoch": 0.48, + "learning_rate": 1.1181955607431925e-05, + "loss": 0.4794, + "step": 5611 + }, + { + "epoch": 0.48, + "learning_rate": 1.1179213323342304e-05, + "loss": 0.4687, + "step": 5612 + }, + { + "epoch": 0.48, + "learning_rate": 1.1176470949320954e-05, + "loss": 0.4855, + "step": 5613 + }, + { + "epoch": 0.48, + "learning_rate": 1.117372848557702e-05, + "loss": 0.4826, + "step": 5614 + }, + { + "epoch": 0.48, + "learning_rate": 1.1170985932319647e-05, + "loss": 0.4861, + "step": 5615 + }, + { + "epoch": 0.48, + "learning_rate": 1.1168243289758001e-05, + "loss": 0.4895, + "step": 5616 + }, + { + "epoch": 0.48, + "learning_rate": 1.116550055810124e-05, + "loss": 0.4692, + "step": 5617 + }, + { + "epoch": 0.48, + "learning_rate": 1.1162757737558545e-05, + "loss": 0.4783, + "step": 5618 + }, + { + "epoch": 0.48, + "learning_rate": 1.1160014828339093e-05, + "loss": 0.4747, + "step": 5619 + }, + { + "epoch": 0.48, + "learning_rate": 1.1157271830652063e-05, + "loss": 0.4651, + "step": 5620 + }, + { + "epoch": 0.48, + "learning_rate": 1.1154528744706652e-05, + "loss": 0.4805, + "step": 5621 + }, + { + "epoch": 0.48, + "learning_rate": 1.115178557071206e-05, + "loss": 0.4824, + "step": 5622 + }, + { + "epoch": 0.48, + "learning_rate": 1.114904230887749e-05, + "loss": 0.4809, + "step": 5623 + }, + { + "epoch": 0.48, + "learning_rate": 1.1146298959412159e-05, + "loss": 0.4863, + "step": 5624 + }, + { + "epoch": 0.48, + "learning_rate": 1.1143555522525282e-05, + "loss": 0.4881, + "step": 5625 + }, + { + "epoch": 0.48, + "learning_rate": 1.1140811998426089e-05, + "loss": 0.4672, + "step": 5626 + }, + { + "epoch": 0.48, + "learning_rate": 1.1138068387323806e-05, + "loss": 0.4926, + "step": 5627 + }, + { + "epoch": 0.48, + "learning_rate": 1.113532468942768e-05, + "loss": 0.4646, + "step": 5628 + }, + { + "epoch": 0.48, + "learning_rate": 1.1132580904946952e-05, + "loss": 0.4726, + "step": 5629 + }, + { + "epoch": 0.48, + "learning_rate": 1.1129837034090876e-05, + "loss": 0.4764, + "step": 5630 + }, + { + "epoch": 0.48, + "learning_rate": 1.1127093077068712e-05, + "loss": 0.4672, + "step": 5631 + }, + { + "epoch": 0.48, + "learning_rate": 1.1124349034089724e-05, + "loss": 0.4821, + "step": 5632 + }, + { + "epoch": 0.48, + "learning_rate": 1.1121604905363181e-05, + "loss": 0.4693, + "step": 5633 + }, + { + "epoch": 0.48, + "learning_rate": 1.111886069109837e-05, + "loss": 0.4833, + "step": 5634 + }, + { + "epoch": 0.48, + "learning_rate": 1.1116116391504572e-05, + "loss": 0.4731, + "step": 5635 + }, + { + "epoch": 0.48, + "learning_rate": 1.1113372006791074e-05, + "loss": 0.4844, + "step": 5636 + }, + { + "epoch": 0.48, + "learning_rate": 1.1110627537167183e-05, + "loss": 0.4683, + "step": 5637 + }, + { + "epoch": 0.48, + "learning_rate": 1.1107882982842195e-05, + "loss": 0.4909, + "step": 5638 + }, + { + "epoch": 0.48, + "learning_rate": 1.1105138344025429e-05, + "loss": 0.4678, + "step": 5639 + }, + { + "epoch": 0.48, + "learning_rate": 1.1102393620926196e-05, + "loss": 0.4978, + "step": 5640 + }, + { + "epoch": 0.48, + "learning_rate": 1.1099648813753827e-05, + "loss": 0.4747, + "step": 5641 + }, + { + "epoch": 0.48, + "learning_rate": 1.1096903922717645e-05, + "loss": 0.4866, + "step": 5642 + }, + { + "epoch": 0.48, + "learning_rate": 1.1094158948026993e-05, + "loss": 0.4753, + "step": 5643 + }, + { + "epoch": 0.48, + "learning_rate": 1.1091413889891211e-05, + "loss": 0.4812, + "step": 5644 + }, + { + "epoch": 0.48, + "learning_rate": 1.1088668748519646e-05, + "loss": 0.4777, + "step": 5645 + }, + { + "epoch": 0.48, + "learning_rate": 1.1085923524121663e-05, + "loss": 0.4732, + "step": 5646 + }, + { + "epoch": 0.48, + "learning_rate": 1.1083178216906614e-05, + "loss": 0.4791, + "step": 5647 + }, + { + "epoch": 0.48, + "learning_rate": 1.1080432827083874e-05, + "loss": 0.4836, + "step": 5648 + }, + { + "epoch": 0.48, + "learning_rate": 1.1077687354862814e-05, + "loss": 0.4839, + "step": 5649 + }, + { + "epoch": 0.48, + "learning_rate": 1.1074941800452818e-05, + "loss": 0.4692, + "step": 5650 + }, + { + "epoch": 0.48, + "learning_rate": 1.1072196164063273e-05, + "loss": 0.5022, + "step": 5651 + }, + { + "epoch": 0.48, + "learning_rate": 1.1069450445903573e-05, + "loss": 0.4921, + "step": 5652 + }, + { + "epoch": 0.48, + "learning_rate": 1.1066704646183117e-05, + "loss": 0.4737, + "step": 5653 + }, + { + "epoch": 0.48, + "learning_rate": 1.1063958765111308e-05, + "loss": 0.4767, + "step": 5654 + }, + { + "epoch": 0.48, + "learning_rate": 1.1061212802897567e-05, + "loss": 0.4734, + "step": 5655 + }, + { + "epoch": 0.48, + "learning_rate": 1.1058466759751302e-05, + "loss": 0.4701, + "step": 5656 + }, + { + "epoch": 0.48, + "learning_rate": 1.1055720635881948e-05, + "loss": 0.4647, + "step": 5657 + }, + { + "epoch": 0.48, + "learning_rate": 1.1052974431498929e-05, + "loss": 0.4783, + "step": 5658 + }, + { + "epoch": 0.48, + "learning_rate": 1.1050228146811684e-05, + "loss": 0.4979, + "step": 5659 + }, + { + "epoch": 0.48, + "learning_rate": 1.1047481782029654e-05, + "loss": 0.4653, + "step": 5660 + }, + { + "epoch": 0.48, + "learning_rate": 1.1044735337362291e-05, + "loss": 0.4897, + "step": 5661 + }, + { + "epoch": 0.48, + "learning_rate": 1.1041988813019051e-05, + "loss": 0.4723, + "step": 5662 + }, + { + "epoch": 0.48, + "learning_rate": 1.103924220920939e-05, + "loss": 0.4611, + "step": 5663 + }, + { + "epoch": 0.48, + "learning_rate": 1.1036495526142784e-05, + "loss": 0.4732, + "step": 5664 + }, + { + "epoch": 0.48, + "learning_rate": 1.10337487640287e-05, + "loss": 0.477, + "step": 5665 + }, + { + "epoch": 0.48, + "learning_rate": 1.1031001923076619e-05, + "loss": 0.4958, + "step": 5666 + }, + { + "epoch": 0.48, + "learning_rate": 1.102825500349603e-05, + "loss": 0.4698, + "step": 5667 + }, + { + "epoch": 0.48, + "learning_rate": 1.1025508005496417e-05, + "loss": 0.4903, + "step": 5668 + }, + { + "epoch": 0.48, + "learning_rate": 1.1022760929287286e-05, + "loss": 0.4853, + "step": 5669 + }, + { + "epoch": 0.48, + "learning_rate": 1.1020013775078134e-05, + "loss": 0.4838, + "step": 5670 + }, + { + "epoch": 0.48, + "learning_rate": 1.1017266543078475e-05, + "loss": 0.4765, + "step": 5671 + }, + { + "epoch": 0.48, + "learning_rate": 1.101451923349782e-05, + "loss": 0.489, + "step": 5672 + }, + { + "epoch": 0.48, + "learning_rate": 1.1011771846545696e-05, + "loss": 0.4735, + "step": 5673 + }, + { + "epoch": 0.48, + "learning_rate": 1.1009024382431623e-05, + "loss": 0.4739, + "step": 5674 + }, + { + "epoch": 0.48, + "learning_rate": 1.1006276841365142e-05, + "loss": 0.4831, + "step": 5675 + }, + { + "epoch": 0.48, + "learning_rate": 1.1003529223555786e-05, + "loss": 0.4899, + "step": 5676 + }, + { + "epoch": 0.48, + "learning_rate": 1.1000781529213103e-05, + "loss": 0.4948, + "step": 5677 + }, + { + "epoch": 0.48, + "learning_rate": 1.099803375854664e-05, + "loss": 0.4833, + "step": 5678 + }, + { + "epoch": 0.48, + "learning_rate": 1.0995285911765958e-05, + "loss": 0.4806, + "step": 5679 + }, + { + "epoch": 0.48, + "learning_rate": 1.0992537989080618e-05, + "loss": 0.4624, + "step": 5680 + }, + { + "epoch": 0.48, + "learning_rate": 1.0989789990700187e-05, + "loss": 0.4773, + "step": 5681 + }, + { + "epoch": 0.48, + "learning_rate": 1.0987041916834236e-05, + "loss": 0.497, + "step": 5682 + }, + { + "epoch": 0.48, + "learning_rate": 1.0984293767692349e-05, + "loss": 0.4747, + "step": 5683 + }, + { + "epoch": 0.48, + "learning_rate": 1.0981545543484111e-05, + "loss": 0.457, + "step": 5684 + }, + { + "epoch": 0.48, + "learning_rate": 1.0978797244419113e-05, + "loss": 0.4927, + "step": 5685 + }, + { + "epoch": 0.48, + "learning_rate": 1.097604887070695e-05, + "loss": 0.4805, + "step": 5686 + }, + { + "epoch": 0.48, + "learning_rate": 1.0973300422557223e-05, + "loss": 0.4919, + "step": 5687 + }, + { + "epoch": 0.48, + "learning_rate": 1.0970551900179544e-05, + "loss": 0.4894, + "step": 5688 + }, + { + "epoch": 0.49, + "learning_rate": 1.0967803303783523e-05, + "loss": 0.4744, + "step": 5689 + }, + { + "epoch": 0.49, + "learning_rate": 1.0965054633578786e-05, + "loss": 0.4657, + "step": 5690 + }, + { + "epoch": 0.49, + "learning_rate": 1.0962305889774952e-05, + "loss": 0.4825, + "step": 5691 + }, + { + "epoch": 0.49, + "learning_rate": 1.0959557072581652e-05, + "loss": 0.489, + "step": 5692 + }, + { + "epoch": 0.49, + "learning_rate": 1.0956808182208525e-05, + "loss": 0.4609, + "step": 5693 + }, + { + "epoch": 0.49, + "learning_rate": 1.0954059218865211e-05, + "loss": 0.4786, + "step": 5694 + }, + { + "epoch": 0.49, + "learning_rate": 1.0951310182761358e-05, + "loss": 0.5028, + "step": 5695 + }, + { + "epoch": 0.49, + "learning_rate": 1.0948561074106618e-05, + "loss": 0.4925, + "step": 5696 + }, + { + "epoch": 0.49, + "learning_rate": 1.0945811893110653e-05, + "loss": 0.4811, + "step": 5697 + }, + { + "epoch": 0.49, + "learning_rate": 1.0943062639983119e-05, + "loss": 0.5011, + "step": 5698 + }, + { + "epoch": 0.49, + "learning_rate": 1.0940313314933697e-05, + "loss": 0.4558, + "step": 5699 + }, + { + "epoch": 0.49, + "learning_rate": 1.0937563918172052e-05, + "loss": 0.4797, + "step": 5700 + }, + { + "epoch": 0.49, + "learning_rate": 1.093481444990787e-05, + "loss": 0.4813, + "step": 5701 + }, + { + "epoch": 0.49, + "learning_rate": 1.0932064910350835e-05, + "loss": 0.4756, + "step": 5702 + }, + { + "epoch": 0.49, + "learning_rate": 1.092931529971064e-05, + "loss": 0.4821, + "step": 5703 + }, + { + "epoch": 0.49, + "learning_rate": 1.0926565618196978e-05, + "loss": 0.4959, + "step": 5704 + }, + { + "epoch": 0.49, + "learning_rate": 1.0923815866019553e-05, + "loss": 0.4749, + "step": 5705 + }, + { + "epoch": 0.49, + "learning_rate": 1.0921066043388078e-05, + "loss": 0.4654, + "step": 5706 + }, + { + "epoch": 0.49, + "learning_rate": 1.0918316150512256e-05, + "loss": 0.4731, + "step": 5707 + }, + { + "epoch": 0.49, + "learning_rate": 1.0915566187601814e-05, + "loss": 0.4834, + "step": 5708 + }, + { + "epoch": 0.49, + "learning_rate": 1.091281615486647e-05, + "loss": 0.4542, + "step": 5709 + }, + { + "epoch": 0.49, + "learning_rate": 1.0910066052515956e-05, + "loss": 0.4831, + "step": 5710 + }, + { + "epoch": 0.49, + "learning_rate": 1.0907315880760003e-05, + "loss": 0.4815, + "step": 5711 + }, + { + "epoch": 0.49, + "learning_rate": 1.0904565639808358e-05, + "loss": 0.4831, + "step": 5712 + }, + { + "epoch": 0.49, + "learning_rate": 1.0901815329870758e-05, + "loss": 0.4686, + "step": 5713 + }, + { + "epoch": 0.49, + "learning_rate": 1.0899064951156956e-05, + "loss": 0.484, + "step": 5714 + }, + { + "epoch": 0.49, + "learning_rate": 1.0896314503876708e-05, + "loss": 0.4713, + "step": 5715 + }, + { + "epoch": 0.49, + "learning_rate": 1.0893563988239773e-05, + "loss": 0.4793, + "step": 5716 + }, + { + "epoch": 0.49, + "learning_rate": 1.089081340445592e-05, + "loss": 0.4635, + "step": 5717 + }, + { + "epoch": 0.49, + "learning_rate": 1.0888062752734913e-05, + "loss": 0.4732, + "step": 5718 + }, + { + "epoch": 0.49, + "learning_rate": 1.0885312033286537e-05, + "loss": 0.4812, + "step": 5719 + }, + { + "epoch": 0.49, + "learning_rate": 1.088256124632057e-05, + "loss": 0.4738, + "step": 5720 + }, + { + "epoch": 0.49, + "learning_rate": 1.0879810392046795e-05, + "loss": 0.4799, + "step": 5721 + }, + { + "epoch": 0.49, + "learning_rate": 1.0877059470675007e-05, + "loss": 0.4749, + "step": 5722 + }, + { + "epoch": 0.49, + "learning_rate": 1.0874308482415002e-05, + "loss": 0.484, + "step": 5723 + }, + { + "epoch": 0.49, + "learning_rate": 1.0871557427476585e-05, + "loss": 0.4905, + "step": 5724 + }, + { + "epoch": 0.49, + "learning_rate": 1.0868806306069555e-05, + "loss": 0.4773, + "step": 5725 + }, + { + "epoch": 0.49, + "learning_rate": 1.0866055118403733e-05, + "loss": 0.5007, + "step": 5726 + }, + { + "epoch": 0.49, + "learning_rate": 1.086330386468893e-05, + "loss": 0.4807, + "step": 5727 + }, + { + "epoch": 0.49, + "learning_rate": 1.086055254513497e-05, + "loss": 0.4568, + "step": 5728 + }, + { + "epoch": 0.49, + "learning_rate": 1.0857801159951681e-05, + "loss": 0.4773, + "step": 5729 + }, + { + "epoch": 0.49, + "learning_rate": 1.0855049709348895e-05, + "loss": 0.486, + "step": 5730 + }, + { + "epoch": 0.49, + "learning_rate": 1.0852298193536446e-05, + "loss": 0.4701, + "step": 5731 + }, + { + "epoch": 0.49, + "learning_rate": 1.084954661272418e-05, + "loss": 0.4913, + "step": 5732 + }, + { + "epoch": 0.49, + "learning_rate": 1.0846794967121942e-05, + "loss": 0.4871, + "step": 5733 + }, + { + "epoch": 0.49, + "learning_rate": 1.0844043256939585e-05, + "loss": 0.473, + "step": 5734 + }, + { + "epoch": 0.49, + "learning_rate": 1.0841291482386967e-05, + "loss": 0.4978, + "step": 5735 + }, + { + "epoch": 0.49, + "learning_rate": 1.0838539643673948e-05, + "loss": 0.4952, + "step": 5736 + }, + { + "epoch": 0.49, + "learning_rate": 1.083578774101039e-05, + "loss": 0.4975, + "step": 5737 + }, + { + "epoch": 0.49, + "learning_rate": 1.0833035774606176e-05, + "loss": 0.4743, + "step": 5738 + }, + { + "epoch": 0.49, + "learning_rate": 1.0830283744671173e-05, + "loss": 0.4795, + "step": 5739 + }, + { + "epoch": 0.49, + "learning_rate": 1.0827531651415266e-05, + "loss": 0.5006, + "step": 5740 + }, + { + "epoch": 0.49, + "learning_rate": 1.082477949504834e-05, + "loss": 0.4663, + "step": 5741 + }, + { + "epoch": 0.49, + "learning_rate": 1.0822027275780287e-05, + "loss": 0.4914, + "step": 5742 + }, + { + "epoch": 0.49, + "learning_rate": 1.0819274993820998e-05, + "loss": 0.478, + "step": 5743 + }, + { + "epoch": 0.49, + "learning_rate": 1.0816522649380383e-05, + "loss": 0.4834, + "step": 5744 + }, + { + "epoch": 0.49, + "learning_rate": 1.081377024266834e-05, + "loss": 0.4558, + "step": 5745 + }, + { + "epoch": 0.49, + "learning_rate": 1.0811017773894781e-05, + "loss": 0.4946, + "step": 5746 + }, + { + "epoch": 0.49, + "learning_rate": 1.0808265243269623e-05, + "loss": 0.4661, + "step": 5747 + }, + { + "epoch": 0.49, + "learning_rate": 1.0805512651002779e-05, + "loss": 0.4491, + "step": 5748 + }, + { + "epoch": 0.49, + "learning_rate": 1.080275999730418e-05, + "loss": 0.4669, + "step": 5749 + }, + { + "epoch": 0.49, + "learning_rate": 1.0800007282383748e-05, + "loss": 0.4682, + "step": 5750 + }, + { + "epoch": 0.49, + "learning_rate": 1.0797254506451426e-05, + "loss": 0.4452, + "step": 5751 + }, + { + "epoch": 0.49, + "learning_rate": 1.0794501669717146e-05, + "loss": 0.4768, + "step": 5752 + }, + { + "epoch": 0.49, + "learning_rate": 1.0791748772390849e-05, + "loss": 0.4768, + "step": 5753 + }, + { + "epoch": 0.49, + "learning_rate": 1.0788995814682486e-05, + "loss": 0.4597, + "step": 5754 + }, + { + "epoch": 0.49, + "learning_rate": 1.078624279680201e-05, + "loss": 0.5029, + "step": 5755 + }, + { + "epoch": 0.49, + "learning_rate": 1.0783489718959376e-05, + "loss": 0.4747, + "step": 5756 + }, + { + "epoch": 0.49, + "learning_rate": 1.0780736581364543e-05, + "loss": 0.4768, + "step": 5757 + }, + { + "epoch": 0.49, + "learning_rate": 1.077798338422748e-05, + "loss": 0.4671, + "step": 5758 + }, + { + "epoch": 0.49, + "learning_rate": 1.0775230127758156e-05, + "loss": 0.4884, + "step": 5759 + }, + { + "epoch": 0.49, + "learning_rate": 1.0772476812166545e-05, + "loss": 0.4874, + "step": 5760 + }, + { + "epoch": 0.49, + "learning_rate": 1.076972343766263e-05, + "loss": 0.4696, + "step": 5761 + }, + { + "epoch": 0.49, + "learning_rate": 1.076697000445639e-05, + "loss": 0.468, + "step": 5762 + }, + { + "epoch": 0.49, + "learning_rate": 1.0764216512757815e-05, + "loss": 0.4809, + "step": 5763 + }, + { + "epoch": 0.49, + "learning_rate": 1.0761462962776896e-05, + "loss": 0.4819, + "step": 5764 + }, + { + "epoch": 0.49, + "learning_rate": 1.0758709354723638e-05, + "loss": 0.4698, + "step": 5765 + }, + { + "epoch": 0.49, + "learning_rate": 1.0755955688808035e-05, + "loss": 0.4655, + "step": 5766 + }, + { + "epoch": 0.49, + "learning_rate": 1.0753201965240095e-05, + "loss": 0.4545, + "step": 5767 + }, + { + "epoch": 0.49, + "learning_rate": 1.075044818422983e-05, + "loss": 0.4986, + "step": 5768 + }, + { + "epoch": 0.49, + "learning_rate": 1.0747694345987249e-05, + "loss": 0.4659, + "step": 5769 + }, + { + "epoch": 0.49, + "learning_rate": 1.0744940450722378e-05, + "loss": 0.4747, + "step": 5770 + }, + { + "epoch": 0.49, + "learning_rate": 1.074218649864524e-05, + "loss": 0.4648, + "step": 5771 + }, + { + "epoch": 0.49, + "learning_rate": 1.0739432489965858e-05, + "loss": 0.4835, + "step": 5772 + }, + { + "epoch": 0.49, + "learning_rate": 1.0736678424894269e-05, + "loss": 0.4749, + "step": 5773 + }, + { + "epoch": 0.49, + "learning_rate": 1.0733924303640508e-05, + "loss": 0.4702, + "step": 5774 + }, + { + "epoch": 0.49, + "learning_rate": 1.0731170126414617e-05, + "loss": 0.4724, + "step": 5775 + }, + { + "epoch": 0.49, + "learning_rate": 1.0728415893426636e-05, + "loss": 0.4789, + "step": 5776 + }, + { + "epoch": 0.49, + "learning_rate": 1.0725661604886622e-05, + "loss": 0.4774, + "step": 5777 + }, + { + "epoch": 0.49, + "learning_rate": 1.0722907261004618e-05, + "loss": 0.4819, + "step": 5778 + }, + { + "epoch": 0.49, + "learning_rate": 1.0720152861990693e-05, + "loss": 0.485, + "step": 5779 + }, + { + "epoch": 0.49, + "learning_rate": 1.0717398408054905e-05, + "loss": 0.4727, + "step": 5780 + }, + { + "epoch": 0.49, + "learning_rate": 1.0714643899407317e-05, + "loss": 0.4657, + "step": 5781 + }, + { + "epoch": 0.49, + "learning_rate": 1.0711889336258004e-05, + "loss": 0.477, + "step": 5782 + }, + { + "epoch": 0.49, + "learning_rate": 1.0709134718817038e-05, + "loss": 0.4857, + "step": 5783 + }, + { + "epoch": 0.49, + "learning_rate": 1.0706380047294496e-05, + "loss": 0.4833, + "step": 5784 + }, + { + "epoch": 0.49, + "learning_rate": 1.0703625321900462e-05, + "loss": 0.4604, + "step": 5785 + }, + { + "epoch": 0.49, + "learning_rate": 1.0700870542845026e-05, + "loss": 0.4889, + "step": 5786 + }, + { + "epoch": 0.49, + "learning_rate": 1.0698115710338273e-05, + "loss": 0.4878, + "step": 5787 + }, + { + "epoch": 0.49, + "learning_rate": 1.0695360824590304e-05, + "loss": 0.471, + "step": 5788 + }, + { + "epoch": 0.49, + "learning_rate": 1.0692605885811215e-05, + "loss": 0.4878, + "step": 5789 + }, + { + "epoch": 0.49, + "learning_rate": 1.068985089421111e-05, + "loss": 0.475, + "step": 5790 + }, + { + "epoch": 0.49, + "learning_rate": 1.0687095850000096e-05, + "loss": 0.4713, + "step": 5791 + }, + { + "epoch": 0.49, + "learning_rate": 1.0684340753388283e-05, + "loss": 0.4824, + "step": 5792 + }, + { + "epoch": 0.49, + "learning_rate": 1.0681585604585787e-05, + "loss": 0.4724, + "step": 5793 + }, + { + "epoch": 0.49, + "learning_rate": 1.0678830403802728e-05, + "loss": 0.49, + "step": 5794 + }, + { + "epoch": 0.49, + "learning_rate": 1.0676075151249228e-05, + "loss": 0.4836, + "step": 5795 + }, + { + "epoch": 0.49, + "learning_rate": 1.067331984713541e-05, + "loss": 0.4878, + "step": 5796 + }, + { + "epoch": 0.49, + "learning_rate": 1.0670564491671415e-05, + "loss": 0.4933, + "step": 5797 + }, + { + "epoch": 0.49, + "learning_rate": 1.0667809085067376e-05, + "loss": 0.4795, + "step": 5798 + }, + { + "epoch": 0.49, + "learning_rate": 1.066505362753342e-05, + "loss": 0.4966, + "step": 5799 + }, + { + "epoch": 0.49, + "learning_rate": 1.0662298119279702e-05, + "loss": 0.4772, + "step": 5800 + }, + { + "epoch": 0.49, + "learning_rate": 1.0659542560516364e-05, + "loss": 0.4927, + "step": 5801 + }, + { + "epoch": 0.49, + "learning_rate": 1.0656786951453556e-05, + "loss": 0.4727, + "step": 5802 + }, + { + "epoch": 0.49, + "learning_rate": 1.0654031292301432e-05, + "loss": 0.4756, + "step": 5803 + }, + { + "epoch": 0.49, + "learning_rate": 1.0651275583270153e-05, + "loss": 0.4787, + "step": 5804 + }, + { + "epoch": 0.49, + "learning_rate": 1.0648519824569876e-05, + "loss": 0.4832, + "step": 5805 + }, + { + "epoch": 0.5, + "learning_rate": 1.0645764016410776e-05, + "loss": 0.4551, + "step": 5806 + }, + { + "epoch": 0.5, + "learning_rate": 1.0643008159003012e-05, + "loss": 0.4906, + "step": 5807 + }, + { + "epoch": 0.5, + "learning_rate": 1.064025225255676e-05, + "loss": 0.4823, + "step": 5808 + }, + { + "epoch": 0.5, + "learning_rate": 1.0637496297282202e-05, + "loss": 0.4695, + "step": 5809 + }, + { + "epoch": 0.5, + "learning_rate": 1.0634740293389512e-05, + "loss": 0.4756, + "step": 5810 + }, + { + "epoch": 0.5, + "learning_rate": 1.0631984241088877e-05, + "loss": 0.477, + "step": 5811 + }, + { + "epoch": 0.5, + "learning_rate": 1.0629228140590486e-05, + "loss": 0.4646, + "step": 5812 + }, + { + "epoch": 0.5, + "learning_rate": 1.0626471992104532e-05, + "loss": 0.513, + "step": 5813 + }, + { + "epoch": 0.5, + "learning_rate": 1.0623715795841207e-05, + "loss": 0.4776, + "step": 5814 + }, + { + "epoch": 0.5, + "learning_rate": 1.062095955201071e-05, + "loss": 0.4818, + "step": 5815 + }, + { + "epoch": 0.5, + "learning_rate": 1.061820326082325e-05, + "loss": 0.4654, + "step": 5816 + }, + { + "epoch": 0.5, + "learning_rate": 1.0615446922489022e-05, + "loss": 0.4989, + "step": 5817 + }, + { + "epoch": 0.5, + "learning_rate": 1.0612690537218246e-05, + "loss": 0.4974, + "step": 5818 + }, + { + "epoch": 0.5, + "learning_rate": 1.0609934105221131e-05, + "loss": 0.4642, + "step": 5819 + }, + { + "epoch": 0.5, + "learning_rate": 1.0607177626707895e-05, + "loss": 0.4591, + "step": 5820 + }, + { + "epoch": 0.5, + "learning_rate": 1.0604421101888755e-05, + "loss": 0.4812, + "step": 5821 + }, + { + "epoch": 0.5, + "learning_rate": 1.0601664530973945e-05, + "loss": 0.4719, + "step": 5822 + }, + { + "epoch": 0.5, + "learning_rate": 1.0598907914173682e-05, + "loss": 0.4648, + "step": 5823 + }, + { + "epoch": 0.5, + "learning_rate": 1.05961512516982e-05, + "loss": 0.4978, + "step": 5824 + }, + { + "epoch": 0.5, + "learning_rate": 1.0593394543757738e-05, + "loss": 0.465, + "step": 5825 + }, + { + "epoch": 0.5, + "learning_rate": 1.0590637790562526e-05, + "loss": 0.474, + "step": 5826 + }, + { + "epoch": 0.5, + "learning_rate": 1.0587880992322814e-05, + "loss": 0.4761, + "step": 5827 + }, + { + "epoch": 0.5, + "learning_rate": 1.0585124149248842e-05, + "loss": 0.4705, + "step": 5828 + }, + { + "epoch": 0.5, + "learning_rate": 1.058236726155086e-05, + "loss": 0.4713, + "step": 5829 + }, + { + "epoch": 0.5, + "learning_rate": 1.0579610329439121e-05, + "loss": 0.4607, + "step": 5830 + }, + { + "epoch": 0.5, + "learning_rate": 1.0576853353123877e-05, + "loss": 0.5079, + "step": 5831 + }, + { + "epoch": 0.5, + "learning_rate": 1.0574096332815386e-05, + "loss": 0.4633, + "step": 5832 + }, + { + "epoch": 0.5, + "learning_rate": 1.0571339268723915e-05, + "loss": 0.4875, + "step": 5833 + }, + { + "epoch": 0.5, + "learning_rate": 1.0568582161059723e-05, + "loss": 0.492, + "step": 5834 + }, + { + "epoch": 0.5, + "learning_rate": 1.0565825010033085e-05, + "loss": 0.4629, + "step": 5835 + }, + { + "epoch": 0.5, + "learning_rate": 1.0563067815854266e-05, + "loss": 0.4791, + "step": 5836 + }, + { + "epoch": 0.5, + "learning_rate": 1.0560310578733549e-05, + "loss": 0.4766, + "step": 5837 + }, + { + "epoch": 0.5, + "learning_rate": 1.0557553298881202e-05, + "loss": 0.4906, + "step": 5838 + }, + { + "epoch": 0.5, + "learning_rate": 1.055479597650752e-05, + "loss": 0.4698, + "step": 5839 + }, + { + "epoch": 0.5, + "learning_rate": 1.0552038611822774e-05, + "loss": 0.5196, + "step": 5840 + }, + { + "epoch": 0.5, + "learning_rate": 1.0549281205037263e-05, + "loss": 0.469, + "step": 5841 + }, + { + "epoch": 0.5, + "learning_rate": 1.0546523756361271e-05, + "loss": 0.456, + "step": 5842 + }, + { + "epoch": 0.5, + "learning_rate": 1.0543766266005097e-05, + "loss": 0.4858, + "step": 5843 + }, + { + "epoch": 0.5, + "learning_rate": 1.0541008734179039e-05, + "loss": 0.4624, + "step": 5844 + }, + { + "epoch": 0.5, + "learning_rate": 1.0538251161093396e-05, + "loss": 0.4654, + "step": 5845 + }, + { + "epoch": 0.5, + "learning_rate": 1.0535493546958471e-05, + "loss": 0.4854, + "step": 5846 + }, + { + "epoch": 0.5, + "learning_rate": 1.0532735891984571e-05, + "loss": 0.484, + "step": 5847 + }, + { + "epoch": 0.5, + "learning_rate": 1.0529978196382011e-05, + "loss": 0.4737, + "step": 5848 + }, + { + "epoch": 0.5, + "learning_rate": 1.05272204603611e-05, + "loss": 0.4796, + "step": 5849 + }, + { + "epoch": 0.5, + "learning_rate": 1.0524462684132155e-05, + "loss": 0.4934, + "step": 5850 + }, + { + "epoch": 0.5, + "learning_rate": 1.0521704867905496e-05, + "loss": 0.4691, + "step": 5851 + }, + { + "epoch": 0.5, + "learning_rate": 1.0518947011891447e-05, + "loss": 0.4573, + "step": 5852 + }, + { + "epoch": 0.5, + "learning_rate": 1.0516189116300333e-05, + "loss": 0.4789, + "step": 5853 + }, + { + "epoch": 0.5, + "learning_rate": 1.051343118134248e-05, + "loss": 0.4811, + "step": 5854 + }, + { + "epoch": 0.5, + "learning_rate": 1.0510673207228222e-05, + "loss": 0.4703, + "step": 5855 + }, + { + "epoch": 0.5, + "learning_rate": 1.0507915194167893e-05, + "loss": 0.4957, + "step": 5856 + }, + { + "epoch": 0.5, + "learning_rate": 1.0505157142371832e-05, + "loss": 0.4904, + "step": 5857 + }, + { + "epoch": 0.5, + "learning_rate": 1.0502399052050378e-05, + "loss": 0.4705, + "step": 5858 + }, + { + "epoch": 0.5, + "learning_rate": 1.0499640923413874e-05, + "loss": 0.4955, + "step": 5859 + }, + { + "epoch": 0.5, + "learning_rate": 1.0496882756672667e-05, + "loss": 0.4891, + "step": 5860 + }, + { + "epoch": 0.5, + "learning_rate": 1.0494124552037105e-05, + "loss": 0.4745, + "step": 5861 + }, + { + "epoch": 0.5, + "learning_rate": 1.0491366309717548e-05, + "loss": 0.4567, + "step": 5862 + }, + { + "epoch": 0.5, + "learning_rate": 1.048860802992434e-05, + "loss": 0.4801, + "step": 5863 + }, + { + "epoch": 0.5, + "learning_rate": 1.0485849712867844e-05, + "loss": 0.4674, + "step": 5864 + }, + { + "epoch": 0.5, + "learning_rate": 1.048309135875842e-05, + "loss": 0.4784, + "step": 5865 + }, + { + "epoch": 0.5, + "learning_rate": 1.0480332967806435e-05, + "loss": 0.4672, + "step": 5866 + }, + { + "epoch": 0.5, + "learning_rate": 1.0477574540222249e-05, + "loss": 0.4818, + "step": 5867 + }, + { + "epoch": 0.5, + "learning_rate": 1.0474816076216237e-05, + "loss": 0.4754, + "step": 5868 + }, + { + "epoch": 0.5, + "learning_rate": 1.047205757599877e-05, + "loss": 0.4672, + "step": 5869 + }, + { + "epoch": 0.5, + "learning_rate": 1.0469299039780217e-05, + "loss": 0.4816, + "step": 5870 + }, + { + "epoch": 0.5, + "learning_rate": 1.0466540467770965e-05, + "loss": 0.4541, + "step": 5871 + }, + { + "epoch": 0.5, + "learning_rate": 1.0463781860181385e-05, + "loss": 0.4928, + "step": 5872 + }, + { + "epoch": 0.5, + "learning_rate": 1.0461023217221867e-05, + "loss": 0.4783, + "step": 5873 + }, + { + "epoch": 0.5, + "learning_rate": 1.0458264539102792e-05, + "loss": 0.4704, + "step": 5874 + }, + { + "epoch": 0.5, + "learning_rate": 1.045550582603455e-05, + "loss": 0.4591, + "step": 5875 + }, + { + "epoch": 0.5, + "learning_rate": 1.0452747078227534e-05, + "loss": 0.4808, + "step": 5876 + }, + { + "epoch": 0.5, + "learning_rate": 1.0449988295892134e-05, + "loss": 0.4666, + "step": 5877 + }, + { + "epoch": 0.5, + "learning_rate": 1.044722947923875e-05, + "loss": 0.4848, + "step": 5878 + }, + { + "epoch": 0.5, + "learning_rate": 1.0444470628477773e-05, + "loss": 0.4988, + "step": 5879 + }, + { + "epoch": 0.5, + "learning_rate": 1.0441711743819618e-05, + "loss": 0.4792, + "step": 5880 + }, + { + "epoch": 0.5, + "learning_rate": 1.0438952825474678e-05, + "loss": 0.4694, + "step": 5881 + }, + { + "epoch": 0.5, + "learning_rate": 1.0436193873653362e-05, + "loss": 0.4798, + "step": 5882 + }, + { + "epoch": 0.5, + "learning_rate": 1.0433434888566078e-05, + "loss": 0.4736, + "step": 5883 + }, + { + "epoch": 0.5, + "learning_rate": 1.0430675870423245e-05, + "loss": 0.4651, + "step": 5884 + }, + { + "epoch": 0.5, + "learning_rate": 1.0427916819435271e-05, + "loss": 0.4658, + "step": 5885 + }, + { + "epoch": 0.5, + "learning_rate": 1.0425157735812572e-05, + "loss": 0.4877, + "step": 5886 + }, + { + "epoch": 0.5, + "learning_rate": 1.0422398619765571e-05, + "loss": 0.4709, + "step": 5887 + }, + { + "epoch": 0.5, + "learning_rate": 1.0419639471504684e-05, + "loss": 0.4852, + "step": 5888 + }, + { + "epoch": 0.5, + "learning_rate": 1.0416880291240343e-05, + "loss": 0.4819, + "step": 5889 + }, + { + "epoch": 0.5, + "learning_rate": 1.0414121079182969e-05, + "loss": 0.4669, + "step": 5890 + }, + { + "epoch": 0.5, + "learning_rate": 1.0411361835542991e-05, + "loss": 0.4866, + "step": 5891 + }, + { + "epoch": 0.5, + "learning_rate": 1.0408602560530845e-05, + "loss": 0.4624, + "step": 5892 + }, + { + "epoch": 0.5, + "learning_rate": 1.0405843254356959e-05, + "loss": 0.4784, + "step": 5893 + }, + { + "epoch": 0.5, + "learning_rate": 1.0403083917231776e-05, + "loss": 0.4542, + "step": 5894 + }, + { + "epoch": 0.5, + "learning_rate": 1.0400324549365725e-05, + "loss": 0.4875, + "step": 5895 + }, + { + "epoch": 0.5, + "learning_rate": 1.039756515096926e-05, + "loss": 0.4798, + "step": 5896 + }, + { + "epoch": 0.5, + "learning_rate": 1.039480572225281e-05, + "loss": 0.4479, + "step": 5897 + }, + { + "epoch": 0.5, + "learning_rate": 1.0392046263426832e-05, + "loss": 0.4658, + "step": 5898 + }, + { + "epoch": 0.5, + "learning_rate": 1.0389286774701765e-05, + "loss": 0.4631, + "step": 5899 + }, + { + "epoch": 0.5, + "learning_rate": 1.0386527256288065e-05, + "loss": 0.4726, + "step": 5900 + }, + { + "epoch": 0.5, + "learning_rate": 1.0383767708396187e-05, + "loss": 0.4926, + "step": 5901 + }, + { + "epoch": 0.5, + "learning_rate": 1.0381008131236576e-05, + "loss": 0.4847, + "step": 5902 + }, + { + "epoch": 0.5, + "learning_rate": 1.0378248525019694e-05, + "loss": 0.4902, + "step": 5903 + }, + { + "epoch": 0.5, + "learning_rate": 1.0375488889956003e-05, + "loss": 0.4743, + "step": 5904 + }, + { + "epoch": 0.5, + "learning_rate": 1.0372729226255962e-05, + "loss": 0.4862, + "step": 5905 + }, + { + "epoch": 0.5, + "learning_rate": 1.0369969534130031e-05, + "loss": 0.4797, + "step": 5906 + }, + { + "epoch": 0.5, + "learning_rate": 1.036720981378868e-05, + "loss": 0.4779, + "step": 5907 + }, + { + "epoch": 0.5, + "learning_rate": 1.0364450065442377e-05, + "loss": 0.4875, + "step": 5908 + }, + { + "epoch": 0.5, + "learning_rate": 1.036169028930159e-05, + "loss": 0.483, + "step": 5909 + }, + { + "epoch": 0.5, + "learning_rate": 1.0358930485576793e-05, + "loss": 0.4764, + "step": 5910 + }, + { + "epoch": 0.5, + "learning_rate": 1.0356170654478457e-05, + "loss": 0.4863, + "step": 5911 + }, + { + "epoch": 0.5, + "learning_rate": 1.0353410796217058e-05, + "loss": 0.4921, + "step": 5912 + }, + { + "epoch": 0.5, + "learning_rate": 1.035065091100308e-05, + "loss": 0.4662, + "step": 5913 + }, + { + "epoch": 0.5, + "learning_rate": 1.0347890999046998e-05, + "loss": 0.4694, + "step": 5914 + }, + { + "epoch": 0.5, + "learning_rate": 1.0345131060559295e-05, + "loss": 0.4751, + "step": 5915 + }, + { + "epoch": 0.5, + "learning_rate": 1.0342371095750456e-05, + "loss": 0.4776, + "step": 5916 + }, + { + "epoch": 0.5, + "learning_rate": 1.033961110483097e-05, + "loss": 0.4798, + "step": 5917 + }, + { + "epoch": 0.5, + "learning_rate": 1.0336851088011321e-05, + "loss": 0.4751, + "step": 5918 + }, + { + "epoch": 0.5, + "learning_rate": 1.0334091045502005e-05, + "loss": 0.494, + "step": 5919 + }, + { + "epoch": 0.5, + "learning_rate": 1.033133097751351e-05, + "loss": 0.4639, + "step": 5920 + }, + { + "epoch": 0.5, + "learning_rate": 1.0328570884256328e-05, + "loss": 0.48, + "step": 5921 + }, + { + "epoch": 0.5, + "learning_rate": 1.0325810765940962e-05, + "loss": 0.4577, + "step": 5922 + }, + { + "epoch": 0.51, + "learning_rate": 1.0323050622777906e-05, + "loss": 0.4769, + "step": 5923 + }, + { + "epoch": 0.51, + "learning_rate": 1.0320290454977662e-05, + "loss": 0.4783, + "step": 5924 + }, + { + "epoch": 0.51, + "learning_rate": 1.0317530262750728e-05, + "loss": 0.4908, + "step": 5925 + }, + { + "epoch": 0.51, + "learning_rate": 1.0314770046307611e-05, + "loss": 0.4864, + "step": 5926 + }, + { + "epoch": 0.51, + "learning_rate": 1.0312009805858818e-05, + "loss": 0.4742, + "step": 5927 + }, + { + "epoch": 0.51, + "learning_rate": 1.0309249541614854e-05, + "loss": 0.4942, + "step": 5928 + }, + { + "epoch": 0.51, + "learning_rate": 1.030648925378623e-05, + "loss": 0.4652, + "step": 5929 + }, + { + "epoch": 0.51, + "learning_rate": 1.0303728942583454e-05, + "loss": 0.4767, + "step": 5930 + }, + { + "epoch": 0.51, + "learning_rate": 1.0300968608217042e-05, + "loss": 0.4827, + "step": 5931 + }, + { + "epoch": 0.51, + "learning_rate": 1.0298208250897504e-05, + "loss": 0.4854, + "step": 5932 + }, + { + "epoch": 0.51, + "learning_rate": 1.0295447870835364e-05, + "loss": 0.454, + "step": 5933 + }, + { + "epoch": 0.51, + "learning_rate": 1.0292687468241136e-05, + "loss": 0.4881, + "step": 5934 + }, + { + "epoch": 0.51, + "learning_rate": 1.0289927043325336e-05, + "loss": 0.4831, + "step": 5935 + }, + { + "epoch": 0.51, + "learning_rate": 1.0287166596298492e-05, + "loss": 0.452, + "step": 5936 + }, + { + "epoch": 0.51, + "learning_rate": 1.0284406127371125e-05, + "loss": 0.4944, + "step": 5937 + }, + { + "epoch": 0.51, + "learning_rate": 1.0281645636753758e-05, + "loss": 0.4721, + "step": 5938 + }, + { + "epoch": 0.51, + "learning_rate": 1.0278885124656919e-05, + "loss": 0.447, + "step": 5939 + }, + { + "epoch": 0.51, + "learning_rate": 1.027612459129114e-05, + "loss": 0.4795, + "step": 5940 + }, + { + "epoch": 0.51, + "learning_rate": 1.027336403686694e-05, + "loss": 0.4877, + "step": 5941 + }, + { + "epoch": 0.51, + "learning_rate": 1.0270603461594861e-05, + "loss": 0.4646, + "step": 5942 + }, + { + "epoch": 0.51, + "learning_rate": 1.0267842865685431e-05, + "loss": 0.484, + "step": 5943 + }, + { + "epoch": 0.51, + "learning_rate": 1.0265082249349188e-05, + "loss": 0.4707, + "step": 5944 + }, + { + "epoch": 0.51, + "learning_rate": 1.0262321612796662e-05, + "loss": 0.4819, + "step": 5945 + }, + { + "epoch": 0.51, + "learning_rate": 1.02595609562384e-05, + "loss": 0.4744, + "step": 5946 + }, + { + "epoch": 0.51, + "learning_rate": 1.0256800279884934e-05, + "loss": 0.4858, + "step": 5947 + }, + { + "epoch": 0.51, + "learning_rate": 1.0254039583946805e-05, + "loss": 0.49, + "step": 5948 + }, + { + "epoch": 0.51, + "learning_rate": 1.0251278868634557e-05, + "loss": 0.4667, + "step": 5949 + }, + { + "epoch": 0.51, + "learning_rate": 1.024851813415873e-05, + "loss": 0.4678, + "step": 5950 + }, + { + "epoch": 0.51, + "learning_rate": 1.024575738072988e-05, + "loss": 0.4741, + "step": 5951 + }, + { + "epoch": 0.51, + "learning_rate": 1.0242996608558542e-05, + "loss": 0.4744, + "step": 5952 + }, + { + "epoch": 0.51, + "learning_rate": 1.0240235817855269e-05, + "loss": 0.4753, + "step": 5953 + }, + { + "epoch": 0.51, + "learning_rate": 1.0237475008830608e-05, + "loss": 0.4863, + "step": 5954 + }, + { + "epoch": 0.51, + "learning_rate": 1.0234714181695115e-05, + "loss": 0.4726, + "step": 5955 + }, + { + "epoch": 0.51, + "learning_rate": 1.0231953336659334e-05, + "loss": 0.4596, + "step": 5956 + }, + { + "epoch": 0.51, + "learning_rate": 1.0229192473933826e-05, + "loss": 0.4995, + "step": 5957 + }, + { + "epoch": 0.51, + "learning_rate": 1.0226431593729144e-05, + "loss": 0.4677, + "step": 5958 + }, + { + "epoch": 0.51, + "learning_rate": 1.022367069625584e-05, + "loss": 0.4619, + "step": 5959 + }, + { + "epoch": 0.51, + "learning_rate": 1.0220909781724478e-05, + "loss": 0.48, + "step": 5960 + }, + { + "epoch": 0.51, + "learning_rate": 1.0218148850345613e-05, + "loss": 0.4743, + "step": 5961 + }, + { + "epoch": 0.51, + "learning_rate": 1.0215387902329806e-05, + "loss": 0.4804, + "step": 5962 + }, + { + "epoch": 0.51, + "learning_rate": 1.0212626937887618e-05, + "loss": 0.5004, + "step": 5963 + }, + { + "epoch": 0.51, + "learning_rate": 1.0209865957229612e-05, + "loss": 0.4797, + "step": 5964 + }, + { + "epoch": 0.51, + "learning_rate": 1.020710496056635e-05, + "loss": 0.4465, + "step": 5965 + }, + { + "epoch": 0.51, + "learning_rate": 1.0204343948108402e-05, + "loss": 0.4503, + "step": 5966 + }, + { + "epoch": 0.51, + "learning_rate": 1.020158292006633e-05, + "loss": 0.4827, + "step": 5967 + }, + { + "epoch": 0.51, + "learning_rate": 1.0198821876650702e-05, + "loss": 0.4637, + "step": 5968 + }, + { + "epoch": 0.51, + "learning_rate": 1.019606081807209e-05, + "loss": 0.4763, + "step": 5969 + }, + { + "epoch": 0.51, + "learning_rate": 1.0193299744541063e-05, + "loss": 0.4657, + "step": 5970 + }, + { + "epoch": 0.51, + "learning_rate": 1.0190538656268186e-05, + "loss": 0.4821, + "step": 5971 + }, + { + "epoch": 0.51, + "learning_rate": 1.0187777553464038e-05, + "loss": 0.4611, + "step": 5972 + }, + { + "epoch": 0.51, + "learning_rate": 1.0185016436339187e-05, + "loss": 0.4889, + "step": 5973 + }, + { + "epoch": 0.51, + "learning_rate": 1.0182255305104215e-05, + "loss": 0.4882, + "step": 5974 + }, + { + "epoch": 0.51, + "learning_rate": 1.0179494159969687e-05, + "loss": 0.4727, + "step": 5975 + }, + { + "epoch": 0.51, + "learning_rate": 1.017673300114619e-05, + "loss": 0.493, + "step": 5976 + }, + { + "epoch": 0.51, + "learning_rate": 1.017397182884429e-05, + "loss": 0.4503, + "step": 5977 + }, + { + "epoch": 0.51, + "learning_rate": 1.017121064327458e-05, + "loss": 0.4565, + "step": 5978 + }, + { + "epoch": 0.51, + "learning_rate": 1.016844944464763e-05, + "loss": 0.4727, + "step": 5979 + }, + { + "epoch": 0.51, + "learning_rate": 1.0165688233174019e-05, + "loss": 0.4753, + "step": 5980 + }, + { + "epoch": 0.51, + "learning_rate": 1.0162927009064331e-05, + "loss": 0.4681, + "step": 5981 + }, + { + "epoch": 0.51, + "learning_rate": 1.0160165772529151e-05, + "loss": 0.47, + "step": 5982 + }, + { + "epoch": 0.51, + "learning_rate": 1.015740452377906e-05, + "loss": 0.4869, + "step": 5983 + }, + { + "epoch": 0.51, + "learning_rate": 1.0154643263024644e-05, + "loss": 0.4813, + "step": 5984 + }, + { + "epoch": 0.51, + "learning_rate": 1.0151881990476486e-05, + "loss": 0.4657, + "step": 5985 + }, + { + "epoch": 0.51, + "learning_rate": 1.0149120706345175e-05, + "loss": 0.4751, + "step": 5986 + }, + { + "epoch": 0.51, + "learning_rate": 1.0146359410841292e-05, + "loss": 0.4792, + "step": 5987 + }, + { + "epoch": 0.51, + "learning_rate": 1.0143598104175434e-05, + "loss": 0.4794, + "step": 5988 + }, + { + "epoch": 0.51, + "learning_rate": 1.0140836786558184e-05, + "loss": 0.475, + "step": 5989 + }, + { + "epoch": 0.51, + "learning_rate": 1.0138075458200132e-05, + "loss": 0.4674, + "step": 5990 + }, + { + "epoch": 0.51, + "learning_rate": 1.013531411931187e-05, + "loss": 0.4528, + "step": 5991 + }, + { + "epoch": 0.51, + "learning_rate": 1.0132552770103987e-05, + "loss": 0.4912, + "step": 5992 + }, + { + "epoch": 0.51, + "learning_rate": 1.0129791410787076e-05, + "loss": 0.4553, + "step": 5993 + }, + { + "epoch": 0.51, + "learning_rate": 1.0127030041571733e-05, + "loss": 0.471, + "step": 5994 + }, + { + "epoch": 0.51, + "learning_rate": 1.0124268662668547e-05, + "loss": 0.466, + "step": 5995 + }, + { + "epoch": 0.51, + "learning_rate": 1.0121507274288112e-05, + "loss": 0.5047, + "step": 5996 + }, + { + "epoch": 0.51, + "learning_rate": 1.0118745876641025e-05, + "loss": 0.478, + "step": 5997 + }, + { + "epoch": 0.51, + "learning_rate": 1.0115984469937883e-05, + "loss": 0.4828, + "step": 5998 + }, + { + "epoch": 0.51, + "learning_rate": 1.0113223054389284e-05, + "loss": 0.4653, + "step": 5999 + }, + { + "epoch": 0.51, + "learning_rate": 1.0110461630205819e-05, + "loss": 0.4635, + "step": 6000 + }, + { + "epoch": 0.51, + "learning_rate": 1.0107700197598089e-05, + "loss": 0.4854, + "step": 6001 + }, + { + "epoch": 0.51, + "learning_rate": 1.0104938756776694e-05, + "loss": 0.466, + "step": 6002 + }, + { + "epoch": 0.51, + "learning_rate": 1.010217730795223e-05, + "loss": 0.473, + "step": 6003 + }, + { + "epoch": 0.51, + "learning_rate": 1.00994158513353e-05, + "loss": 0.4842, + "step": 6004 + }, + { + "epoch": 0.51, + "learning_rate": 1.0096654387136497e-05, + "loss": 0.4973, + "step": 6005 + }, + { + "epoch": 0.51, + "learning_rate": 1.009389291556643e-05, + "loss": 0.4845, + "step": 6006 + }, + { + "epoch": 0.51, + "learning_rate": 1.0091131436835698e-05, + "loss": 0.479, + "step": 6007 + }, + { + "epoch": 0.51, + "learning_rate": 1.0088369951154904e-05, + "loss": 0.5021, + "step": 6008 + }, + { + "epoch": 0.51, + "learning_rate": 1.0085608458734644e-05, + "loss": 0.4843, + "step": 6009 + }, + { + "epoch": 0.51, + "learning_rate": 1.0082846959785528e-05, + "loss": 0.4672, + "step": 6010 + }, + { + "epoch": 0.51, + "learning_rate": 1.0080085454518158e-05, + "loss": 0.4962, + "step": 6011 + }, + { + "epoch": 0.51, + "learning_rate": 1.0077323943143134e-05, + "loss": 0.4777, + "step": 6012 + }, + { + "epoch": 0.51, + "learning_rate": 1.0074562425871065e-05, + "loss": 0.515, + "step": 6013 + }, + { + "epoch": 0.51, + "learning_rate": 1.0071800902912553e-05, + "loss": 0.4822, + "step": 6014 + }, + { + "epoch": 0.51, + "learning_rate": 1.0069039374478207e-05, + "loss": 0.4878, + "step": 6015 + }, + { + "epoch": 0.51, + "learning_rate": 1.0066277840778626e-05, + "loss": 0.4842, + "step": 6016 + }, + { + "epoch": 0.51, + "learning_rate": 1.0063516302024425e-05, + "loss": 0.4827, + "step": 6017 + }, + { + "epoch": 0.51, + "learning_rate": 1.0060754758426204e-05, + "loss": 0.4626, + "step": 6018 + }, + { + "epoch": 0.51, + "learning_rate": 1.005799321019457e-05, + "loss": 0.4717, + "step": 6019 + }, + { + "epoch": 0.51, + "learning_rate": 1.0055231657540132e-05, + "loss": 0.4908, + "step": 6020 + }, + { + "epoch": 0.51, + "learning_rate": 1.0052470100673495e-05, + "loss": 0.4868, + "step": 6021 + }, + { + "epoch": 0.51, + "learning_rate": 1.0049708539805274e-05, + "loss": 0.4825, + "step": 6022 + }, + { + "epoch": 0.51, + "learning_rate": 1.004694697514607e-05, + "loss": 0.4784, + "step": 6023 + }, + { + "epoch": 0.51, + "learning_rate": 1.0044185406906493e-05, + "loss": 0.4917, + "step": 6024 + }, + { + "epoch": 0.51, + "learning_rate": 1.0041423835297155e-05, + "loss": 0.4768, + "step": 6025 + }, + { + "epoch": 0.51, + "learning_rate": 1.003866226052866e-05, + "loss": 0.4705, + "step": 6026 + }, + { + "epoch": 0.51, + "learning_rate": 1.0035900682811619e-05, + "loss": 0.4645, + "step": 6027 + }, + { + "epoch": 0.51, + "learning_rate": 1.0033139102356641e-05, + "loss": 0.4896, + "step": 6028 + }, + { + "epoch": 0.51, + "learning_rate": 1.0030377519374342e-05, + "loss": 0.4921, + "step": 6029 + }, + { + "epoch": 0.51, + "learning_rate": 1.0027615934075321e-05, + "loss": 0.4532, + "step": 6030 + }, + { + "epoch": 0.51, + "learning_rate": 1.0024854346670196e-05, + "loss": 0.4717, + "step": 6031 + }, + { + "epoch": 0.51, + "learning_rate": 1.0022092757369575e-05, + "loss": 0.4716, + "step": 6032 + }, + { + "epoch": 0.51, + "learning_rate": 1.0019331166384068e-05, + "loss": 0.465, + "step": 6033 + }, + { + "epoch": 0.51, + "learning_rate": 1.0016569573924287e-05, + "loss": 0.4817, + "step": 6034 + }, + { + "epoch": 0.51, + "learning_rate": 1.0013807980200838e-05, + "loss": 0.4805, + "step": 6035 + }, + { + "epoch": 0.51, + "learning_rate": 1.0011046385424335e-05, + "loss": 0.4853, + "step": 6036 + }, + { + "epoch": 0.51, + "learning_rate": 1.0008284789805389e-05, + "loss": 0.4745, + "step": 6037 + }, + { + "epoch": 0.51, + "learning_rate": 1.0005523193554613e-05, + "loss": 0.4858, + "step": 6038 + }, + { + "epoch": 0.51, + "learning_rate": 1.000276159688261e-05, + "loss": 0.4591, + "step": 6039 + }, + { + "epoch": 0.52, + "learning_rate": 1e-05, + "loss": 0.4665, + "step": 6040 + }, + { + "epoch": 0.52, + "learning_rate": 9.997238403117391e-06, + "loss": 0.4828, + "step": 6041 + }, + { + "epoch": 0.52, + "learning_rate": 9.994476806445392e-06, + "loss": 0.4682, + "step": 6042 + }, + { + "epoch": 0.52, + "learning_rate": 9.991715210194611e-06, + "loss": 0.476, + "step": 6043 + }, + { + "epoch": 0.52, + "learning_rate": 9.988953614575668e-06, + "loss": 0.492, + "step": 6044 + }, + { + "epoch": 0.52, + "learning_rate": 9.986192019799166e-06, + "loss": 0.4844, + "step": 6045 + }, + { + "epoch": 0.52, + "learning_rate": 9.98343042607572e-06, + "loss": 0.4737, + "step": 6046 + }, + { + "epoch": 0.52, + "learning_rate": 9.980668833615933e-06, + "loss": 0.4963, + "step": 6047 + }, + { + "epoch": 0.52, + "learning_rate": 9.977907242630425e-06, + "loss": 0.4672, + "step": 6048 + }, + { + "epoch": 0.52, + "learning_rate": 9.975145653329806e-06, + "loss": 0.4932, + "step": 6049 + }, + { + "epoch": 0.52, + "learning_rate": 9.972384065924684e-06, + "loss": 0.4732, + "step": 6050 + }, + { + "epoch": 0.52, + "learning_rate": 9.969622480625663e-06, + "loss": 0.4859, + "step": 6051 + }, + { + "epoch": 0.52, + "learning_rate": 9.966860897643359e-06, + "loss": 0.4964, + "step": 6052 + }, + { + "epoch": 0.52, + "learning_rate": 9.964099317188384e-06, + "loss": 0.4597, + "step": 6053 + }, + { + "epoch": 0.52, + "learning_rate": 9.961337739471344e-06, + "loss": 0.4657, + "step": 6054 + }, + { + "epoch": 0.52, + "learning_rate": 9.95857616470285e-06, + "loss": 0.4773, + "step": 6055 + }, + { + "epoch": 0.52, + "learning_rate": 9.95581459309351e-06, + "loss": 0.4645, + "step": 6056 + }, + { + "epoch": 0.52, + "learning_rate": 9.953053024853932e-06, + "loss": 0.5327, + "step": 6057 + }, + { + "epoch": 0.52, + "learning_rate": 9.950291460194729e-06, + "loss": 0.4825, + "step": 6058 + }, + { + "epoch": 0.52, + "learning_rate": 9.947529899326507e-06, + "loss": 0.47, + "step": 6059 + }, + { + "epoch": 0.52, + "learning_rate": 9.944768342459872e-06, + "loss": 0.4708, + "step": 6060 + }, + { + "epoch": 0.52, + "learning_rate": 9.942006789805432e-06, + "loss": 0.4622, + "step": 6061 + }, + { + "epoch": 0.52, + "learning_rate": 9.939245241573801e-06, + "loss": 0.4668, + "step": 6062 + }, + { + "epoch": 0.52, + "learning_rate": 9.936483697975578e-06, + "loss": 0.473, + "step": 6063 + }, + { + "epoch": 0.52, + "learning_rate": 9.933722159221375e-06, + "loss": 0.4742, + "step": 6064 + }, + { + "epoch": 0.52, + "learning_rate": 9.930960625521798e-06, + "loss": 0.4883, + "step": 6065 + }, + { + "epoch": 0.52, + "learning_rate": 9.928199097087447e-06, + "loss": 0.4683, + "step": 6066 + }, + { + "epoch": 0.52, + "learning_rate": 9.925437574128938e-06, + "loss": 0.4759, + "step": 6067 + }, + { + "epoch": 0.52, + "learning_rate": 9.92267605685687e-06, + "loss": 0.4885, + "step": 6068 + }, + { + "epoch": 0.52, + "learning_rate": 9.919914545481847e-06, + "loss": 0.4505, + "step": 6069 + }, + { + "epoch": 0.52, + "learning_rate": 9.917153040214473e-06, + "loss": 0.4669, + "step": 6070 + }, + { + "epoch": 0.52, + "learning_rate": 9.914391541265358e-06, + "loss": 0.4798, + "step": 6071 + }, + { + "epoch": 0.52, + "learning_rate": 9.9116300488451e-06, + "loss": 0.4624, + "step": 6072 + }, + { + "epoch": 0.52, + "learning_rate": 9.908868563164305e-06, + "loss": 0.4882, + "step": 6073 + }, + { + "epoch": 0.52, + "learning_rate": 9.906107084433573e-06, + "loss": 0.4799, + "step": 6074 + }, + { + "epoch": 0.52, + "learning_rate": 9.903345612863503e-06, + "loss": 0.4726, + "step": 6075 + }, + { + "epoch": 0.52, + "learning_rate": 9.900584148664705e-06, + "loss": 0.4645, + "step": 6076 + }, + { + "epoch": 0.52, + "learning_rate": 9.897822692047772e-06, + "loss": 0.4893, + "step": 6077 + }, + { + "epoch": 0.52, + "learning_rate": 9.895061243223311e-06, + "loss": 0.4651, + "step": 6078 + }, + { + "epoch": 0.52, + "learning_rate": 9.892299802401911e-06, + "loss": 0.4799, + "step": 6079 + }, + { + "epoch": 0.52, + "learning_rate": 9.889538369794185e-06, + "loss": 0.4726, + "step": 6080 + }, + { + "epoch": 0.52, + "learning_rate": 9.886776945610719e-06, + "loss": 0.4953, + "step": 6081 + }, + { + "epoch": 0.52, + "learning_rate": 9.884015530062119e-06, + "loss": 0.4747, + "step": 6082 + }, + { + "epoch": 0.52, + "learning_rate": 9.881254123358977e-06, + "loss": 0.4832, + "step": 6083 + }, + { + "epoch": 0.52, + "learning_rate": 9.87849272571189e-06, + "loss": 0.489, + "step": 6084 + }, + { + "epoch": 0.52, + "learning_rate": 9.875731337331458e-06, + "loss": 0.4612, + "step": 6085 + }, + { + "epoch": 0.52, + "learning_rate": 9.87296995842827e-06, + "loss": 0.4905, + "step": 6086 + }, + { + "epoch": 0.52, + "learning_rate": 9.870208589212928e-06, + "loss": 0.4682, + "step": 6087 + }, + { + "epoch": 0.52, + "learning_rate": 9.86744722989602e-06, + "loss": 0.4695, + "step": 6088 + }, + { + "epoch": 0.52, + "learning_rate": 9.864685880688134e-06, + "loss": 0.4961, + "step": 6089 + }, + { + "epoch": 0.52, + "learning_rate": 9.86192454179987e-06, + "loss": 0.4824, + "step": 6090 + }, + { + "epoch": 0.52, + "learning_rate": 9.85916321344182e-06, + "loss": 0.4904, + "step": 6091 + }, + { + "epoch": 0.52, + "learning_rate": 9.85640189582457e-06, + "loss": 0.4632, + "step": 6092 + }, + { + "epoch": 0.52, + "learning_rate": 9.853640589158706e-06, + "loss": 0.4639, + "step": 6093 + }, + { + "epoch": 0.52, + "learning_rate": 9.850879293654829e-06, + "loss": 0.4844, + "step": 6094 + }, + { + "epoch": 0.52, + "learning_rate": 9.848118009523516e-06, + "loss": 0.4678, + "step": 6095 + }, + { + "epoch": 0.52, + "learning_rate": 9.84535673697536e-06, + "loss": 0.4898, + "step": 6096 + }, + { + "epoch": 0.52, + "learning_rate": 9.842595476220945e-06, + "loss": 0.4592, + "step": 6097 + }, + { + "epoch": 0.52, + "learning_rate": 9.839834227470852e-06, + "loss": 0.4646, + "step": 6098 + }, + { + "epoch": 0.52, + "learning_rate": 9.83707299093567e-06, + "loss": 0.4695, + "step": 6099 + }, + { + "epoch": 0.52, + "learning_rate": 9.834311766825986e-06, + "loss": 0.4802, + "step": 6100 + }, + { + "epoch": 0.52, + "learning_rate": 9.831550555352375e-06, + "loss": 0.4689, + "step": 6101 + }, + { + "epoch": 0.52, + "learning_rate": 9.828789356725422e-06, + "loss": 0.4615, + "step": 6102 + }, + { + "epoch": 0.52, + "learning_rate": 9.82602817115571e-06, + "loss": 0.4817, + "step": 6103 + }, + { + "epoch": 0.52, + "learning_rate": 9.823266998853813e-06, + "loss": 0.4849, + "step": 6104 + }, + { + "epoch": 0.52, + "learning_rate": 9.820505840030315e-06, + "loss": 0.4638, + "step": 6105 + }, + { + "epoch": 0.52, + "learning_rate": 9.817744694895792e-06, + "loss": 0.4677, + "step": 6106 + }, + { + "epoch": 0.52, + "learning_rate": 9.814983563660814e-06, + "loss": 0.4951, + "step": 6107 + }, + { + "epoch": 0.52, + "learning_rate": 9.812222446535965e-06, + "loss": 0.4591, + "step": 6108 + }, + { + "epoch": 0.52, + "learning_rate": 9.80946134373182e-06, + "loss": 0.4686, + "step": 6109 + }, + { + "epoch": 0.52, + "learning_rate": 9.806700255458942e-06, + "loss": 0.4719, + "step": 6110 + }, + { + "epoch": 0.52, + "learning_rate": 9.803939181927914e-06, + "loss": 0.462, + "step": 6111 + }, + { + "epoch": 0.52, + "learning_rate": 9.801178123349298e-06, + "loss": 0.489, + "step": 6112 + }, + { + "epoch": 0.52, + "learning_rate": 9.798417079933672e-06, + "loss": 0.4787, + "step": 6113 + }, + { + "epoch": 0.52, + "learning_rate": 9.795656051891603e-06, + "loss": 0.4843, + "step": 6114 + }, + { + "epoch": 0.52, + "learning_rate": 9.792895039433655e-06, + "loss": 0.4689, + "step": 6115 + }, + { + "epoch": 0.52, + "learning_rate": 9.790134042770391e-06, + "loss": 0.4866, + "step": 6116 + }, + { + "epoch": 0.52, + "learning_rate": 9.787373062112386e-06, + "loss": 0.4888, + "step": 6117 + }, + { + "epoch": 0.52, + "learning_rate": 9.7846120976702e-06, + "loss": 0.466, + "step": 6118 + }, + { + "epoch": 0.52, + "learning_rate": 9.78185114965439e-06, + "loss": 0.4824, + "step": 6119 + }, + { + "epoch": 0.52, + "learning_rate": 9.779090218275527e-06, + "loss": 0.4744, + "step": 6120 + }, + { + "epoch": 0.52, + "learning_rate": 9.77632930374416e-06, + "loss": 0.482, + "step": 6121 + }, + { + "epoch": 0.52, + "learning_rate": 9.773568406270857e-06, + "loss": 0.471, + "step": 6122 + }, + { + "epoch": 0.52, + "learning_rate": 9.770807526066175e-06, + "loss": 0.4827, + "step": 6123 + }, + { + "epoch": 0.52, + "learning_rate": 9.76804666334067e-06, + "loss": 0.4614, + "step": 6124 + }, + { + "epoch": 0.52, + "learning_rate": 9.765285818304888e-06, + "loss": 0.4601, + "step": 6125 + }, + { + "epoch": 0.52, + "learning_rate": 9.762524991169392e-06, + "loss": 0.4441, + "step": 6126 + }, + { + "epoch": 0.52, + "learning_rate": 9.759764182144734e-06, + "loss": 0.47, + "step": 6127 + }, + { + "epoch": 0.52, + "learning_rate": 9.75700339144146e-06, + "loss": 0.4982, + "step": 6128 + }, + { + "epoch": 0.52, + "learning_rate": 9.754242619270125e-06, + "loss": 0.4736, + "step": 6129 + }, + { + "epoch": 0.52, + "learning_rate": 9.75148186584127e-06, + "loss": 0.4609, + "step": 6130 + }, + { + "epoch": 0.52, + "learning_rate": 9.748721131365445e-06, + "loss": 0.4577, + "step": 6131 + }, + { + "epoch": 0.52, + "learning_rate": 9.7459604160532e-06, + "loss": 0.4844, + "step": 6132 + }, + { + "epoch": 0.52, + "learning_rate": 9.743199720115071e-06, + "loss": 0.4672, + "step": 6133 + }, + { + "epoch": 0.52, + "learning_rate": 9.740439043761604e-06, + "loss": 0.4493, + "step": 6134 + }, + { + "epoch": 0.52, + "learning_rate": 9.737678387203337e-06, + "loss": 0.466, + "step": 6135 + }, + { + "epoch": 0.52, + "learning_rate": 9.734917750650817e-06, + "loss": 0.4834, + "step": 6136 + }, + { + "epoch": 0.52, + "learning_rate": 9.732157134314572e-06, + "loss": 0.4748, + "step": 6137 + }, + { + "epoch": 0.52, + "learning_rate": 9.729396538405144e-06, + "loss": 0.4591, + "step": 6138 + }, + { + "epoch": 0.52, + "learning_rate": 9.726635963133062e-06, + "loss": 0.4752, + "step": 6139 + }, + { + "epoch": 0.52, + "learning_rate": 9.723875408708866e-06, + "loss": 0.4606, + "step": 6140 + }, + { + "epoch": 0.52, + "learning_rate": 9.721114875343085e-06, + "loss": 0.48, + "step": 6141 + }, + { + "epoch": 0.52, + "learning_rate": 9.718354363246243e-06, + "loss": 0.4794, + "step": 6142 + }, + { + "epoch": 0.52, + "learning_rate": 9.71559387262888e-06, + "loss": 0.4598, + "step": 6143 + }, + { + "epoch": 0.52, + "learning_rate": 9.71283340370151e-06, + "loss": 0.4812, + "step": 6144 + }, + { + "epoch": 0.52, + "learning_rate": 9.710072956674666e-06, + "loss": 0.4644, + "step": 6145 + }, + { + "epoch": 0.52, + "learning_rate": 9.707312531758869e-06, + "loss": 0.4799, + "step": 6146 + }, + { + "epoch": 0.52, + "learning_rate": 9.704552129164641e-06, + "loss": 0.4598, + "step": 6147 + }, + { + "epoch": 0.52, + "learning_rate": 9.701791749102496e-06, + "loss": 0.4861, + "step": 6148 + }, + { + "epoch": 0.52, + "learning_rate": 9.69903139178296e-06, + "loss": 0.4861, + "step": 6149 + }, + { + "epoch": 0.52, + "learning_rate": 9.69627105741655e-06, + "loss": 0.4682, + "step": 6150 + }, + { + "epoch": 0.52, + "learning_rate": 9.693510746213774e-06, + "loss": 0.4756, + "step": 6151 + }, + { + "epoch": 0.52, + "learning_rate": 9.69075045838515e-06, + "loss": 0.4817, + "step": 6152 + }, + { + "epoch": 0.52, + "learning_rate": 9.687990194141183e-06, + "loss": 0.4685, + "step": 6153 + }, + { + "epoch": 0.52, + "learning_rate": 9.68522995369239e-06, + "loss": 0.4729, + "step": 6154 + }, + { + "epoch": 0.52, + "learning_rate": 9.682469737249274e-06, + "loss": 0.4664, + "step": 6155 + }, + { + "epoch": 0.52, + "learning_rate": 9.679709545022343e-06, + "loss": 0.4597, + "step": 6156 + }, + { + "epoch": 0.52, + "learning_rate": 9.676949377222096e-06, + "loss": 0.4712, + "step": 6157 + }, + { + "epoch": 0.53, + "learning_rate": 9.67418923405904e-06, + "loss": 0.4865, + "step": 6158 + }, + { + "epoch": 0.53, + "learning_rate": 9.671429115743674e-06, + "loss": 0.472, + "step": 6159 + }, + { + "epoch": 0.53, + "learning_rate": 9.668669022486495e-06, + "loss": 0.4792, + "step": 6160 + }, + { + "epoch": 0.53, + "learning_rate": 9.665908954498e-06, + "loss": 0.4724, + "step": 6161 + }, + { + "epoch": 0.53, + "learning_rate": 9.663148911988679e-06, + "loss": 0.486, + "step": 6162 + }, + { + "epoch": 0.53, + "learning_rate": 9.660388895169034e-06, + "loss": 0.4625, + "step": 6163 + }, + { + "epoch": 0.53, + "learning_rate": 9.657628904249546e-06, + "loss": 0.477, + "step": 6164 + }, + { + "epoch": 0.53, + "learning_rate": 9.65486893944071e-06, + "loss": 0.48, + "step": 6165 + }, + { + "epoch": 0.53, + "learning_rate": 9.652109000953007e-06, + "loss": 0.481, + "step": 6166 + }, + { + "epoch": 0.53, + "learning_rate": 9.649349088996922e-06, + "loss": 0.474, + "step": 6167 + }, + { + "epoch": 0.53, + "learning_rate": 9.646589203782944e-06, + "loss": 0.474, + "step": 6168 + }, + { + "epoch": 0.53, + "learning_rate": 9.643829345521546e-06, + "loss": 0.4812, + "step": 6169 + }, + { + "epoch": 0.53, + "learning_rate": 9.641069514423212e-06, + "loss": 0.4662, + "step": 6170 + }, + { + "epoch": 0.53, + "learning_rate": 9.63830971069841e-06, + "loss": 0.4751, + "step": 6171 + }, + { + "epoch": 0.53, + "learning_rate": 9.635549934557626e-06, + "loss": 0.4816, + "step": 6172 + }, + { + "epoch": 0.53, + "learning_rate": 9.632790186211321e-06, + "loss": 0.4732, + "step": 6173 + }, + { + "epoch": 0.53, + "learning_rate": 9.630030465869972e-06, + "loss": 0.4578, + "step": 6174 + }, + { + "epoch": 0.53, + "learning_rate": 9.627270773744043e-06, + "loss": 0.4806, + "step": 6175 + }, + { + "epoch": 0.53, + "learning_rate": 9.624511110043999e-06, + "loss": 0.4771, + "step": 6176 + }, + { + "epoch": 0.53, + "learning_rate": 9.621751474980308e-06, + "loss": 0.4751, + "step": 6177 + }, + { + "epoch": 0.53, + "learning_rate": 9.618991868763428e-06, + "loss": 0.4853, + "step": 6178 + }, + { + "epoch": 0.53, + "learning_rate": 9.61623229160382e-06, + "loss": 0.4701, + "step": 6179 + }, + { + "epoch": 0.53, + "learning_rate": 9.613472743711937e-06, + "loss": 0.4875, + "step": 6180 + }, + { + "epoch": 0.53, + "learning_rate": 9.610713225298238e-06, + "loss": 0.4865, + "step": 6181 + }, + { + "epoch": 0.53, + "learning_rate": 9.607953736573173e-06, + "loss": 0.4569, + "step": 6182 + }, + { + "epoch": 0.53, + "learning_rate": 9.605194277747193e-06, + "loss": 0.5042, + "step": 6183 + }, + { + "epoch": 0.53, + "learning_rate": 9.602434849030747e-06, + "loss": 0.4588, + "step": 6184 + }, + { + "epoch": 0.53, + "learning_rate": 9.599675450634273e-06, + "loss": 0.4904, + "step": 6185 + }, + { + "epoch": 0.53, + "learning_rate": 9.596916082768228e-06, + "loss": 0.4826, + "step": 6186 + }, + { + "epoch": 0.53, + "learning_rate": 9.594156745643043e-06, + "loss": 0.4766, + "step": 6187 + }, + { + "epoch": 0.53, + "learning_rate": 9.59139743946916e-06, + "loss": 0.4757, + "step": 6188 + }, + { + "epoch": 0.53, + "learning_rate": 9.58863816445701e-06, + "loss": 0.4814, + "step": 6189 + }, + { + "epoch": 0.53, + "learning_rate": 9.585878920817032e-06, + "loss": 0.4845, + "step": 6190 + }, + { + "epoch": 0.53, + "learning_rate": 9.58311970875966e-06, + "loss": 0.4909, + "step": 6191 + }, + { + "epoch": 0.53, + "learning_rate": 9.58036052849532e-06, + "loss": 0.4775, + "step": 6192 + }, + { + "epoch": 0.53, + "learning_rate": 9.577601380234434e-06, + "loss": 0.4571, + "step": 6193 + }, + { + "epoch": 0.53, + "learning_rate": 9.57484226418743e-06, + "loss": 0.4768, + "step": 6194 + }, + { + "epoch": 0.53, + "learning_rate": 9.572083180564734e-06, + "loss": 0.4771, + "step": 6195 + }, + { + "epoch": 0.53, + "learning_rate": 9.569324129576756e-06, + "loss": 0.4692, + "step": 6196 + }, + { + "epoch": 0.53, + "learning_rate": 9.566565111433923e-06, + "loss": 0.4704, + "step": 6197 + }, + { + "epoch": 0.53, + "learning_rate": 9.563806126346643e-06, + "loss": 0.4816, + "step": 6198 + }, + { + "epoch": 0.53, + "learning_rate": 9.561047174525324e-06, + "loss": 0.4768, + "step": 6199 + }, + { + "epoch": 0.53, + "learning_rate": 9.558288256180385e-06, + "loss": 0.466, + "step": 6200 + }, + { + "epoch": 0.53, + "learning_rate": 9.555529371522228e-06, + "loss": 0.4843, + "step": 6201 + }, + { + "epoch": 0.53, + "learning_rate": 9.552770520761256e-06, + "loss": 0.4738, + "step": 6202 + }, + { + "epoch": 0.53, + "learning_rate": 9.550011704107867e-06, + "loss": 0.4789, + "step": 6203 + }, + { + "epoch": 0.53, + "learning_rate": 9.54725292177247e-06, + "loss": 0.4887, + "step": 6204 + }, + { + "epoch": 0.53, + "learning_rate": 9.544494173965451e-06, + "loss": 0.4714, + "step": 6205 + }, + { + "epoch": 0.53, + "learning_rate": 9.541735460897211e-06, + "loss": 0.4918, + "step": 6206 + }, + { + "epoch": 0.53, + "learning_rate": 9.538976782778136e-06, + "loss": 0.4777, + "step": 6207 + }, + { + "epoch": 0.53, + "learning_rate": 9.536218139818615e-06, + "loss": 0.4894, + "step": 6208 + }, + { + "epoch": 0.53, + "learning_rate": 9.53345953222904e-06, + "loss": 0.4892, + "step": 6209 + }, + { + "epoch": 0.53, + "learning_rate": 9.530700960219787e-06, + "loss": 0.4747, + "step": 6210 + }, + { + "epoch": 0.53, + "learning_rate": 9.527942424001235e-06, + "loss": 0.449, + "step": 6211 + }, + { + "epoch": 0.53, + "learning_rate": 9.525183923783768e-06, + "loss": 0.4876, + "step": 6212 + }, + { + "epoch": 0.53, + "learning_rate": 9.522425459777753e-06, + "loss": 0.468, + "step": 6213 + }, + { + "epoch": 0.53, + "learning_rate": 9.519667032193569e-06, + "loss": 0.4926, + "step": 6214 + }, + { + "epoch": 0.53, + "learning_rate": 9.516908641241584e-06, + "loss": 0.4882, + "step": 6215 + }, + { + "epoch": 0.53, + "learning_rate": 9.51415028713216e-06, + "loss": 0.4694, + "step": 6216 + }, + { + "epoch": 0.53, + "learning_rate": 9.511391970075662e-06, + "loss": 0.4771, + "step": 6217 + }, + { + "epoch": 0.53, + "learning_rate": 9.508633690282456e-06, + "loss": 0.4454, + "step": 6218 + }, + { + "epoch": 0.53, + "learning_rate": 9.505875447962896e-06, + "loss": 0.4853, + "step": 6219 + }, + { + "epoch": 0.53, + "learning_rate": 9.503117243327336e-06, + "loss": 0.4843, + "step": 6220 + }, + { + "epoch": 0.53, + "learning_rate": 9.500359076586131e-06, + "loss": 0.4748, + "step": 6221 + }, + { + "epoch": 0.53, + "learning_rate": 9.497600947949625e-06, + "loss": 0.4751, + "step": 6222 + }, + { + "epoch": 0.53, + "learning_rate": 9.49484285762817e-06, + "loss": 0.467, + "step": 6223 + }, + { + "epoch": 0.53, + "learning_rate": 9.49208480583211e-06, + "loss": 0.4712, + "step": 6224 + }, + { + "epoch": 0.53, + "learning_rate": 9.489326792771781e-06, + "loss": 0.4563, + "step": 6225 + }, + { + "epoch": 0.53, + "learning_rate": 9.48656881865752e-06, + "loss": 0.4878, + "step": 6226 + }, + { + "epoch": 0.53, + "learning_rate": 9.48381088369967e-06, + "loss": 0.476, + "step": 6227 + }, + { + "epoch": 0.53, + "learning_rate": 9.481052988108556e-06, + "loss": 0.4657, + "step": 6228 + }, + { + "epoch": 0.53, + "learning_rate": 9.478295132094505e-06, + "loss": 0.4677, + "step": 6229 + }, + { + "epoch": 0.53, + "learning_rate": 9.47553731586785e-06, + "loss": 0.4587, + "step": 6230 + }, + { + "epoch": 0.53, + "learning_rate": 9.472779539638901e-06, + "loss": 0.4511, + "step": 6231 + }, + { + "epoch": 0.53, + "learning_rate": 9.47002180361799e-06, + "loss": 0.469, + "step": 6232 + }, + { + "epoch": 0.53, + "learning_rate": 9.46726410801543e-06, + "loss": 0.4849, + "step": 6233 + }, + { + "epoch": 0.53, + "learning_rate": 9.464506453041532e-06, + "loss": 0.4751, + "step": 6234 + }, + { + "epoch": 0.53, + "learning_rate": 9.461748838906606e-06, + "loss": 0.4923, + "step": 6235 + }, + { + "epoch": 0.53, + "learning_rate": 9.458991265820962e-06, + "loss": 0.4905, + "step": 6236 + }, + { + "epoch": 0.53, + "learning_rate": 9.456233733994906e-06, + "loss": 0.4865, + "step": 6237 + }, + { + "epoch": 0.53, + "learning_rate": 9.45347624363873e-06, + "loss": 0.4761, + "step": 6238 + }, + { + "epoch": 0.53, + "learning_rate": 9.450718794962742e-06, + "loss": 0.4512, + "step": 6239 + }, + { + "epoch": 0.53, + "learning_rate": 9.447961388177227e-06, + "loss": 0.4898, + "step": 6240 + }, + { + "epoch": 0.53, + "learning_rate": 9.445204023492484e-06, + "loss": 0.4407, + "step": 6241 + }, + { + "epoch": 0.53, + "learning_rate": 9.4424467011188e-06, + "loss": 0.4823, + "step": 6242 + }, + { + "epoch": 0.53, + "learning_rate": 9.439689421266456e-06, + "loss": 0.478, + "step": 6243 + }, + { + "epoch": 0.53, + "learning_rate": 9.436932184145737e-06, + "loss": 0.4615, + "step": 6244 + }, + { + "epoch": 0.53, + "learning_rate": 9.434174989966917e-06, + "loss": 0.4897, + "step": 6245 + }, + { + "epoch": 0.53, + "learning_rate": 9.43141783894028e-06, + "loss": 0.4927, + "step": 6246 + }, + { + "epoch": 0.53, + "learning_rate": 9.428660731276089e-06, + "loss": 0.4566, + "step": 6247 + }, + { + "epoch": 0.53, + "learning_rate": 9.425903667184619e-06, + "loss": 0.4581, + "step": 6248 + }, + { + "epoch": 0.53, + "learning_rate": 9.423146646876126e-06, + "loss": 0.4764, + "step": 6249 + }, + { + "epoch": 0.53, + "learning_rate": 9.42038967056088e-06, + "loss": 0.4642, + "step": 6250 + }, + { + "epoch": 0.53, + "learning_rate": 9.417632738449143e-06, + "loss": 0.4942, + "step": 6251 + }, + { + "epoch": 0.53, + "learning_rate": 9.41487585075116e-06, + "loss": 0.4767, + "step": 6252 + }, + { + "epoch": 0.53, + "learning_rate": 9.41211900767719e-06, + "loss": 0.4783, + "step": 6253 + }, + { + "epoch": 0.53, + "learning_rate": 9.409362209437474e-06, + "loss": 0.479, + "step": 6254 + }, + { + "epoch": 0.53, + "learning_rate": 9.406605456242265e-06, + "loss": 0.4639, + "step": 6255 + }, + { + "epoch": 0.53, + "learning_rate": 9.403848748301802e-06, + "loss": 0.4875, + "step": 6256 + }, + { + "epoch": 0.53, + "learning_rate": 9.401092085826325e-06, + "loss": 0.4694, + "step": 6257 + }, + { + "epoch": 0.53, + "learning_rate": 9.398335469026058e-06, + "loss": 0.4753, + "step": 6258 + }, + { + "epoch": 0.53, + "learning_rate": 9.395578898111243e-06, + "loss": 0.4751, + "step": 6259 + }, + { + "epoch": 0.53, + "learning_rate": 9.392822373292108e-06, + "loss": 0.4717, + "step": 6260 + }, + { + "epoch": 0.53, + "learning_rate": 9.390065894778872e-06, + "loss": 0.4929, + "step": 6261 + }, + { + "epoch": 0.53, + "learning_rate": 9.387309462781759e-06, + "loss": 0.475, + "step": 6262 + }, + { + "epoch": 0.53, + "learning_rate": 9.38455307751098e-06, + "loss": 0.4837, + "step": 6263 + }, + { + "epoch": 0.53, + "learning_rate": 9.381796739176754e-06, + "loss": 0.4673, + "step": 6264 + }, + { + "epoch": 0.53, + "learning_rate": 9.379040447989292e-06, + "loss": 0.4791, + "step": 6265 + }, + { + "epoch": 0.53, + "learning_rate": 9.3762842041588e-06, + "loss": 0.486, + "step": 6266 + }, + { + "epoch": 0.53, + "learning_rate": 9.373528007895473e-06, + "loss": 0.453, + "step": 6267 + }, + { + "epoch": 0.53, + "learning_rate": 9.370771859409514e-06, + "loss": 0.4836, + "step": 6268 + }, + { + "epoch": 0.53, + "learning_rate": 9.368015758911126e-06, + "loss": 0.4682, + "step": 6269 + }, + { + "epoch": 0.53, + "learning_rate": 9.365259706610491e-06, + "loss": 0.4841, + "step": 6270 + }, + { + "epoch": 0.53, + "learning_rate": 9.362503702717803e-06, + "loss": 0.4676, + "step": 6271 + }, + { + "epoch": 0.53, + "learning_rate": 9.359747747443241e-06, + "loss": 0.4645, + "step": 6272 + }, + { + "epoch": 0.53, + "learning_rate": 9.356991840996991e-06, + "loss": 0.4624, + "step": 6273 + }, + { + "epoch": 0.53, + "learning_rate": 9.354235983589229e-06, + "loss": 0.4834, + "step": 6274 + }, + { + "epoch": 0.54, + "learning_rate": 9.351480175430126e-06, + "loss": 0.4747, + "step": 6275 + }, + { + "epoch": 0.54, + "learning_rate": 9.348724416729852e-06, + "loss": 0.4625, + "step": 6276 + }, + { + "epoch": 0.54, + "learning_rate": 9.34596870769857e-06, + "loss": 0.4691, + "step": 6277 + }, + { + "epoch": 0.54, + "learning_rate": 9.34321304854645e-06, + "loss": 0.4711, + "step": 6278 + }, + { + "epoch": 0.54, + "learning_rate": 9.34045743948364e-06, + "loss": 0.4869, + "step": 6279 + }, + { + "epoch": 0.54, + "learning_rate": 9.337701880720303e-06, + "loss": 0.4757, + "step": 6280 + }, + { + "epoch": 0.54, + "learning_rate": 9.334946372466582e-06, + "loss": 0.5034, + "step": 6281 + }, + { + "epoch": 0.54, + "learning_rate": 9.332190914932629e-06, + "loss": 0.4926, + "step": 6282 + }, + { + "epoch": 0.54, + "learning_rate": 9.329435508328587e-06, + "loss": 0.4664, + "step": 6283 + }, + { + "epoch": 0.54, + "learning_rate": 9.326680152864592e-06, + "loss": 0.4675, + "step": 6284 + }, + { + "epoch": 0.54, + "learning_rate": 9.323924848750777e-06, + "loss": 0.4657, + "step": 6285 + }, + { + "epoch": 0.54, + "learning_rate": 9.321169596197274e-06, + "loss": 0.473, + "step": 6286 + }, + { + "epoch": 0.54, + "learning_rate": 9.318414395414216e-06, + "loss": 0.4819, + "step": 6287 + }, + { + "epoch": 0.54, + "learning_rate": 9.31565924661172e-06, + "loss": 0.464, + "step": 6288 + }, + { + "epoch": 0.54, + "learning_rate": 9.312904149999909e-06, + "loss": 0.4602, + "step": 6289 + }, + { + "epoch": 0.54, + "learning_rate": 9.310149105788892e-06, + "loss": 0.4684, + "step": 6290 + }, + { + "epoch": 0.54, + "learning_rate": 9.307394114188786e-06, + "loss": 0.4621, + "step": 6291 + }, + { + "epoch": 0.54, + "learning_rate": 9.304639175409699e-06, + "loss": 0.4903, + "step": 6292 + }, + { + "epoch": 0.54, + "learning_rate": 9.30188428966173e-06, + "loss": 0.4553, + "step": 6293 + }, + { + "epoch": 0.54, + "learning_rate": 9.299129457154979e-06, + "loss": 0.4692, + "step": 6294 + }, + { + "epoch": 0.54, + "learning_rate": 9.29637467809954e-06, + "loss": 0.4889, + "step": 6295 + }, + { + "epoch": 0.54, + "learning_rate": 9.293619952705509e-06, + "loss": 0.467, + "step": 6296 + }, + { + "epoch": 0.54, + "learning_rate": 9.290865281182965e-06, + "loss": 0.4887, + "step": 6297 + }, + { + "epoch": 0.54, + "learning_rate": 9.288110663742001e-06, + "loss": 0.4659, + "step": 6298 + }, + { + "epoch": 0.54, + "learning_rate": 9.285356100592685e-06, + "loss": 0.4666, + "step": 6299 + }, + { + "epoch": 0.54, + "learning_rate": 9.282601591945097e-06, + "loss": 0.4914, + "step": 6300 + }, + { + "epoch": 0.54, + "learning_rate": 9.279847138009308e-06, + "loss": 0.4639, + "step": 6301 + }, + { + "epoch": 0.54, + "learning_rate": 9.277092738995385e-06, + "loss": 0.4626, + "step": 6302 + }, + { + "epoch": 0.54, + "learning_rate": 9.274338395113383e-06, + "loss": 0.4678, + "step": 6303 + }, + { + "epoch": 0.54, + "learning_rate": 9.271584106573364e-06, + "loss": 0.4659, + "step": 6304 + }, + { + "epoch": 0.54, + "learning_rate": 9.268829873585388e-06, + "loss": 0.4773, + "step": 6305 + }, + { + "epoch": 0.54, + "learning_rate": 9.266075696359495e-06, + "loss": 0.4681, + "step": 6306 + }, + { + "epoch": 0.54, + "learning_rate": 9.263321575105734e-06, + "loss": 0.5068, + "step": 6307 + }, + { + "epoch": 0.54, + "learning_rate": 9.260567510034146e-06, + "loss": 0.4725, + "step": 6308 + }, + { + "epoch": 0.54, + "learning_rate": 9.257813501354761e-06, + "loss": 0.4658, + "step": 6309 + }, + { + "epoch": 0.54, + "learning_rate": 9.255059549277624e-06, + "loss": 0.4885, + "step": 6310 + }, + { + "epoch": 0.54, + "learning_rate": 9.252305654012753e-06, + "loss": 0.4594, + "step": 6311 + }, + { + "epoch": 0.54, + "learning_rate": 9.249551815770177e-06, + "loss": 0.4734, + "step": 6312 + }, + { + "epoch": 0.54, + "learning_rate": 9.246798034759907e-06, + "loss": 0.4914, + "step": 6313 + }, + { + "epoch": 0.54, + "learning_rate": 9.244044311191968e-06, + "loss": 0.4739, + "step": 6314 + }, + { + "epoch": 0.54, + "learning_rate": 9.241290645276364e-06, + "loss": 0.4776, + "step": 6315 + }, + { + "epoch": 0.54, + "learning_rate": 9.238537037223106e-06, + "loss": 0.4892, + "step": 6316 + }, + { + "epoch": 0.54, + "learning_rate": 9.235783487242188e-06, + "loss": 0.4576, + "step": 6317 + }, + { + "epoch": 0.54, + "learning_rate": 9.233029995543612e-06, + "loss": 0.4942, + "step": 6318 + }, + { + "epoch": 0.54, + "learning_rate": 9.230276562337374e-06, + "loss": 0.4477, + "step": 6319 + }, + { + "epoch": 0.54, + "learning_rate": 9.227523187833456e-06, + "loss": 0.4603, + "step": 6320 + }, + { + "epoch": 0.54, + "learning_rate": 9.224769872241848e-06, + "loss": 0.4894, + "step": 6321 + }, + { + "epoch": 0.54, + "learning_rate": 9.222016615772525e-06, + "loss": 0.4503, + "step": 6322 + }, + { + "epoch": 0.54, + "learning_rate": 9.21926341863546e-06, + "loss": 0.4716, + "step": 6323 + }, + { + "epoch": 0.54, + "learning_rate": 9.216510281040627e-06, + "loss": 0.4863, + "step": 6324 + }, + { + "epoch": 0.54, + "learning_rate": 9.213757203197994e-06, + "loss": 0.4874, + "step": 6325 + }, + { + "epoch": 0.54, + "learning_rate": 9.211004185317515e-06, + "loss": 0.4689, + "step": 6326 + }, + { + "epoch": 0.54, + "learning_rate": 9.208251227609151e-06, + "loss": 0.4886, + "step": 6327 + }, + { + "epoch": 0.54, + "learning_rate": 9.205498330282857e-06, + "loss": 0.4841, + "step": 6328 + }, + { + "epoch": 0.54, + "learning_rate": 9.202745493548576e-06, + "loss": 0.4793, + "step": 6329 + }, + { + "epoch": 0.54, + "learning_rate": 9.199992717616253e-06, + "loss": 0.4929, + "step": 6330 + }, + { + "epoch": 0.54, + "learning_rate": 9.197240002695826e-06, + "loss": 0.4762, + "step": 6331 + }, + { + "epoch": 0.54, + "learning_rate": 9.194487348997223e-06, + "loss": 0.4547, + "step": 6332 + }, + { + "epoch": 0.54, + "learning_rate": 9.19173475673038e-06, + "loss": 0.4797, + "step": 6333 + }, + { + "epoch": 0.54, + "learning_rate": 9.188982226105222e-06, + "loss": 0.4793, + "step": 6334 + }, + { + "epoch": 0.54, + "learning_rate": 9.186229757331663e-06, + "loss": 0.4631, + "step": 6335 + }, + { + "epoch": 0.54, + "learning_rate": 9.183477350619617e-06, + "loss": 0.4591, + "step": 6336 + }, + { + "epoch": 0.54, + "learning_rate": 9.180725006179002e-06, + "loss": 0.4615, + "step": 6337 + }, + { + "epoch": 0.54, + "learning_rate": 9.177972724219715e-06, + "loss": 0.4645, + "step": 6338 + }, + { + "epoch": 0.54, + "learning_rate": 9.175220504951664e-06, + "loss": 0.4772, + "step": 6339 + }, + { + "epoch": 0.54, + "learning_rate": 9.17246834858474e-06, + "loss": 0.4822, + "step": 6340 + }, + { + "epoch": 0.54, + "learning_rate": 9.16971625532883e-06, + "loss": 0.4534, + "step": 6341 + }, + { + "epoch": 0.54, + "learning_rate": 9.166964225393826e-06, + "loss": 0.4966, + "step": 6342 + }, + { + "epoch": 0.54, + "learning_rate": 9.164212258989611e-06, + "loss": 0.4871, + "step": 6343 + }, + { + "epoch": 0.54, + "learning_rate": 9.161460356326057e-06, + "loss": 0.4715, + "step": 6344 + }, + { + "epoch": 0.54, + "learning_rate": 9.158708517613038e-06, + "loss": 0.4875, + "step": 6345 + }, + { + "epoch": 0.54, + "learning_rate": 9.155956743060417e-06, + "loss": 0.4508, + "step": 6346 + }, + { + "epoch": 0.54, + "learning_rate": 9.15320503287806e-06, + "loss": 0.4629, + "step": 6347 + }, + { + "epoch": 0.54, + "learning_rate": 9.150453387275823e-06, + "loss": 0.4889, + "step": 6348 + }, + { + "epoch": 0.54, + "learning_rate": 9.147701806463559e-06, + "loss": 0.4862, + "step": 6349 + }, + { + "epoch": 0.54, + "learning_rate": 9.144950290651109e-06, + "loss": 0.502, + "step": 6350 + }, + { + "epoch": 0.54, + "learning_rate": 9.14219884004832e-06, + "loss": 0.4505, + "step": 6351 + }, + { + "epoch": 0.54, + "learning_rate": 9.139447454865034e-06, + "loss": 0.4658, + "step": 6352 + }, + { + "epoch": 0.54, + "learning_rate": 9.136696135311075e-06, + "loss": 0.4701, + "step": 6353 + }, + { + "epoch": 0.54, + "learning_rate": 9.133944881596273e-06, + "loss": 0.4701, + "step": 6354 + }, + { + "epoch": 0.54, + "learning_rate": 9.131193693930447e-06, + "loss": 0.4937, + "step": 6355 + }, + { + "epoch": 0.54, + "learning_rate": 9.128442572523418e-06, + "loss": 0.4526, + "step": 6356 + }, + { + "epoch": 0.54, + "learning_rate": 9.125691517585e-06, + "loss": 0.4731, + "step": 6357 + }, + { + "epoch": 0.54, + "learning_rate": 9.122940529324997e-06, + "loss": 0.4538, + "step": 6358 + }, + { + "epoch": 0.54, + "learning_rate": 9.120189607953206e-06, + "loss": 0.4788, + "step": 6359 + }, + { + "epoch": 0.54, + "learning_rate": 9.117438753679433e-06, + "loss": 0.4669, + "step": 6360 + }, + { + "epoch": 0.54, + "learning_rate": 9.114687966713465e-06, + "loss": 0.4699, + "step": 6361 + }, + { + "epoch": 0.54, + "learning_rate": 9.111937247265088e-06, + "loss": 0.4706, + "step": 6362 + }, + { + "epoch": 0.54, + "learning_rate": 9.109186595544085e-06, + "loss": 0.4566, + "step": 6363 + }, + { + "epoch": 0.54, + "learning_rate": 9.106436011760229e-06, + "loss": 0.4623, + "step": 6364 + }, + { + "epoch": 0.54, + "learning_rate": 9.103685496123294e-06, + "loss": 0.4611, + "step": 6365 + }, + { + "epoch": 0.54, + "learning_rate": 9.100935048843047e-06, + "loss": 0.4778, + "step": 6366 + }, + { + "epoch": 0.54, + "learning_rate": 9.098184670129244e-06, + "loss": 0.4588, + "step": 6367 + }, + { + "epoch": 0.54, + "learning_rate": 9.095434360191642e-06, + "loss": 0.467, + "step": 6368 + }, + { + "epoch": 0.54, + "learning_rate": 9.092684119239996e-06, + "loss": 0.4931, + "step": 6369 + }, + { + "epoch": 0.54, + "learning_rate": 9.089933947484048e-06, + "loss": 0.4698, + "step": 6370 + }, + { + "epoch": 0.54, + "learning_rate": 9.087183845133532e-06, + "loss": 0.4695, + "step": 6371 + }, + { + "epoch": 0.54, + "learning_rate": 9.084433812398191e-06, + "loss": 0.4704, + "step": 6372 + }, + { + "epoch": 0.54, + "learning_rate": 9.081683849487745e-06, + "loss": 0.4875, + "step": 6373 + }, + { + "epoch": 0.54, + "learning_rate": 9.078933956611925e-06, + "loss": 0.4816, + "step": 6374 + }, + { + "epoch": 0.54, + "learning_rate": 9.076184133980449e-06, + "loss": 0.4694, + "step": 6375 + }, + { + "epoch": 0.54, + "learning_rate": 9.073434381803025e-06, + "loss": 0.4893, + "step": 6376 + }, + { + "epoch": 0.54, + "learning_rate": 9.070684700289365e-06, + "loss": 0.4753, + "step": 6377 + }, + { + "epoch": 0.54, + "learning_rate": 9.067935089649167e-06, + "loss": 0.4821, + "step": 6378 + }, + { + "epoch": 0.54, + "learning_rate": 9.065185550092134e-06, + "loss": 0.4813, + "step": 6379 + }, + { + "epoch": 0.54, + "learning_rate": 9.06243608182795e-06, + "loss": 0.4646, + "step": 6380 + }, + { + "epoch": 0.54, + "learning_rate": 9.059686685066308e-06, + "loss": 0.4855, + "step": 6381 + }, + { + "epoch": 0.54, + "learning_rate": 9.056937360016881e-06, + "loss": 0.4576, + "step": 6382 + }, + { + "epoch": 0.54, + "learning_rate": 9.05418810688935e-06, + "loss": 0.4715, + "step": 6383 + }, + { + "epoch": 0.54, + "learning_rate": 9.051438925893385e-06, + "loss": 0.4708, + "step": 6384 + }, + { + "epoch": 0.54, + "learning_rate": 9.048689817238645e-06, + "loss": 0.4851, + "step": 6385 + }, + { + "epoch": 0.54, + "learning_rate": 9.045940781134794e-06, + "loss": 0.475, + "step": 6386 + }, + { + "epoch": 0.54, + "learning_rate": 9.043191817791476e-06, + "loss": 0.4602, + "step": 6387 + }, + { + "epoch": 0.54, + "learning_rate": 9.04044292741835e-06, + "loss": 0.4751, + "step": 6388 + }, + { + "epoch": 0.54, + "learning_rate": 9.03769411022505e-06, + "loss": 0.4812, + "step": 6389 + }, + { + "epoch": 0.54, + "learning_rate": 9.034945366421219e-06, + "loss": 0.4719, + "step": 6390 + }, + { + "epoch": 0.54, + "learning_rate": 9.032196696216477e-06, + "loss": 0.4703, + "step": 6391 + }, + { + "epoch": 0.55, + "learning_rate": 9.029448099820458e-06, + "loss": 0.4979, + "step": 6392 + }, + { + "epoch": 0.55, + "learning_rate": 9.026699577442779e-06, + "loss": 0.4843, + "step": 6393 + }, + { + "epoch": 0.55, + "learning_rate": 9.023951129293053e-06, + "loss": 0.482, + "step": 6394 + }, + { + "epoch": 0.55, + "learning_rate": 9.021202755580892e-06, + "loss": 0.492, + "step": 6395 + }, + { + "epoch": 0.55, + "learning_rate": 9.018454456515889e-06, + "loss": 0.4814, + "step": 6396 + }, + { + "epoch": 0.55, + "learning_rate": 9.015706232307653e-06, + "loss": 0.4877, + "step": 6397 + }, + { + "epoch": 0.55, + "learning_rate": 9.012958083165766e-06, + "loss": 0.4727, + "step": 6398 + }, + { + "epoch": 0.55, + "learning_rate": 9.010210009299818e-06, + "loss": 0.4699, + "step": 6399 + }, + { + "epoch": 0.55, + "learning_rate": 9.007462010919387e-06, + "loss": 0.4559, + "step": 6400 + }, + { + "epoch": 0.55, + "learning_rate": 9.004714088234042e-06, + "loss": 0.47, + "step": 6401 + }, + { + "epoch": 0.55, + "learning_rate": 9.001966241453362e-06, + "loss": 0.4718, + "step": 6402 + }, + { + "epoch": 0.55, + "learning_rate": 8.9992184707869e-06, + "loss": 0.4788, + "step": 6403 + }, + { + "epoch": 0.55, + "learning_rate": 8.996470776444217e-06, + "loss": 0.4702, + "step": 6404 + }, + { + "epoch": 0.55, + "learning_rate": 8.993723158634859e-06, + "loss": 0.4804, + "step": 6405 + }, + { + "epoch": 0.55, + "learning_rate": 8.990975617568379e-06, + "loss": 0.4839, + "step": 6406 + }, + { + "epoch": 0.55, + "learning_rate": 8.988228153454308e-06, + "loss": 0.4778, + "step": 6407 + }, + { + "epoch": 0.55, + "learning_rate": 8.985480766502183e-06, + "loss": 0.4814, + "step": 6408 + }, + { + "epoch": 0.55, + "learning_rate": 8.98273345692153e-06, + "loss": 0.4572, + "step": 6409 + }, + { + "epoch": 0.55, + "learning_rate": 8.979986224921868e-06, + "loss": 0.4853, + "step": 6410 + }, + { + "epoch": 0.55, + "learning_rate": 8.977239070712717e-06, + "loss": 0.4634, + "step": 6411 + }, + { + "epoch": 0.55, + "learning_rate": 8.974491994503585e-06, + "loss": 0.4664, + "step": 6412 + }, + { + "epoch": 0.55, + "learning_rate": 8.971744996503975e-06, + "loss": 0.4695, + "step": 6413 + }, + { + "epoch": 0.55, + "learning_rate": 8.968998076923381e-06, + "loss": 0.4595, + "step": 6414 + }, + { + "epoch": 0.55, + "learning_rate": 8.966251235971302e-06, + "loss": 0.4492, + "step": 6415 + }, + { + "epoch": 0.55, + "learning_rate": 8.963504473857218e-06, + "loss": 0.4637, + "step": 6416 + }, + { + "epoch": 0.55, + "learning_rate": 8.960757790790613e-06, + "loss": 0.4776, + "step": 6417 + }, + { + "epoch": 0.55, + "learning_rate": 8.958011186980954e-06, + "loss": 0.471, + "step": 6418 + }, + { + "epoch": 0.55, + "learning_rate": 8.95526466263771e-06, + "loss": 0.4739, + "step": 6419 + }, + { + "epoch": 0.55, + "learning_rate": 8.95251821797035e-06, + "loss": 0.5049, + "step": 6420 + }, + { + "epoch": 0.55, + "learning_rate": 8.94977185318832e-06, + "loss": 0.4594, + "step": 6421 + }, + { + "epoch": 0.55, + "learning_rate": 8.947025568501075e-06, + "loss": 0.464, + "step": 6422 + }, + { + "epoch": 0.55, + "learning_rate": 8.944279364118059e-06, + "loss": 0.4919, + "step": 6423 + }, + { + "epoch": 0.55, + "learning_rate": 8.9415332402487e-06, + "loss": 0.4861, + "step": 6424 + }, + { + "epoch": 0.55, + "learning_rate": 8.938787197102437e-06, + "loss": 0.4652, + "step": 6425 + }, + { + "epoch": 0.55, + "learning_rate": 8.936041234888693e-06, + "loss": 0.4617, + "step": 6426 + }, + { + "epoch": 0.55, + "learning_rate": 8.933295353816888e-06, + "loss": 0.4679, + "step": 6427 + }, + { + "epoch": 0.55, + "learning_rate": 8.930549554096429e-06, + "loss": 0.4842, + "step": 6428 + }, + { + "epoch": 0.55, + "learning_rate": 8.927803835936729e-06, + "loss": 0.4601, + "step": 6429 + }, + { + "epoch": 0.55, + "learning_rate": 8.925058199547183e-06, + "loss": 0.4781, + "step": 6430 + }, + { + "epoch": 0.55, + "learning_rate": 8.92231264513719e-06, + "loss": 0.5146, + "step": 6431 + }, + { + "epoch": 0.55, + "learning_rate": 8.91956717291613e-06, + "loss": 0.4532, + "step": 6432 + }, + { + "epoch": 0.55, + "learning_rate": 8.916821783093386e-06, + "loss": 0.4784, + "step": 6433 + }, + { + "epoch": 0.55, + "learning_rate": 8.914076475878342e-06, + "loss": 0.4695, + "step": 6434 + }, + { + "epoch": 0.55, + "learning_rate": 8.911331251480357e-06, + "loss": 0.466, + "step": 6435 + }, + { + "epoch": 0.55, + "learning_rate": 8.908586110108794e-06, + "loss": 0.488, + "step": 6436 + }, + { + "epoch": 0.55, + "learning_rate": 8.905841051973009e-06, + "loss": 0.4777, + "step": 6437 + }, + { + "epoch": 0.55, + "learning_rate": 8.903096077282356e-06, + "loss": 0.4698, + "step": 6438 + }, + { + "epoch": 0.55, + "learning_rate": 8.900351186246177e-06, + "loss": 0.4595, + "step": 6439 + }, + { + "epoch": 0.55, + "learning_rate": 8.897606379073806e-06, + "loss": 0.4815, + "step": 6440 + }, + { + "epoch": 0.55, + "learning_rate": 8.894861655974575e-06, + "loss": 0.4935, + "step": 6441 + }, + { + "epoch": 0.55, + "learning_rate": 8.892117017157805e-06, + "loss": 0.467, + "step": 6442 + }, + { + "epoch": 0.55, + "learning_rate": 8.88937246283282e-06, + "loss": 0.4759, + "step": 6443 + }, + { + "epoch": 0.55, + "learning_rate": 8.886627993208929e-06, + "loss": 0.4697, + "step": 6444 + }, + { + "epoch": 0.55, + "learning_rate": 8.883883608495433e-06, + "loss": 0.4691, + "step": 6445 + }, + { + "epoch": 0.55, + "learning_rate": 8.88113930890163e-06, + "loss": 0.4682, + "step": 6446 + }, + { + "epoch": 0.55, + "learning_rate": 8.87839509463682e-06, + "loss": 0.4867, + "step": 6447 + }, + { + "epoch": 0.55, + "learning_rate": 8.87565096591028e-06, + "loss": 0.457, + "step": 6448 + }, + { + "epoch": 0.55, + "learning_rate": 8.872906922931293e-06, + "loss": 0.492, + "step": 6449 + }, + { + "epoch": 0.55, + "learning_rate": 8.870162965909127e-06, + "loss": 0.4872, + "step": 6450 + }, + { + "epoch": 0.55, + "learning_rate": 8.867419095053047e-06, + "loss": 0.4781, + "step": 6451 + }, + { + "epoch": 0.55, + "learning_rate": 8.864675310572323e-06, + "loss": 0.4737, + "step": 6452 + }, + { + "epoch": 0.55, + "learning_rate": 8.861931612676197e-06, + "loss": 0.4543, + "step": 6453 + }, + { + "epoch": 0.55, + "learning_rate": 8.859188001573916e-06, + "loss": 0.4781, + "step": 6454 + }, + { + "epoch": 0.55, + "learning_rate": 8.856444477474723e-06, + "loss": 0.474, + "step": 6455 + }, + { + "epoch": 0.55, + "learning_rate": 8.853701040587843e-06, + "loss": 0.4575, + "step": 6456 + }, + { + "epoch": 0.55, + "learning_rate": 8.850957691122511e-06, + "loss": 0.4876, + "step": 6457 + }, + { + "epoch": 0.55, + "learning_rate": 8.848214429287945e-06, + "loss": 0.482, + "step": 6458 + }, + { + "epoch": 0.55, + "learning_rate": 8.845471255293351e-06, + "loss": 0.4941, + "step": 6459 + }, + { + "epoch": 0.55, + "learning_rate": 8.842728169347938e-06, + "loss": 0.4964, + "step": 6460 + }, + { + "epoch": 0.55, + "learning_rate": 8.83998517166091e-06, + "loss": 0.4641, + "step": 6461 + }, + { + "epoch": 0.55, + "learning_rate": 8.837242262441457e-06, + "loss": 0.4856, + "step": 6462 + }, + { + "epoch": 0.55, + "learning_rate": 8.834499441898761e-06, + "loss": 0.4629, + "step": 6463 + }, + { + "epoch": 0.55, + "learning_rate": 8.831756710242006e-06, + "loss": 0.4586, + "step": 6464 + }, + { + "epoch": 0.55, + "learning_rate": 8.829014067680355e-06, + "loss": 0.4664, + "step": 6465 + }, + { + "epoch": 0.55, + "learning_rate": 8.826271514422983e-06, + "loss": 0.4758, + "step": 6466 + }, + { + "epoch": 0.55, + "learning_rate": 8.823529050679049e-06, + "loss": 0.4693, + "step": 6467 + }, + { + "epoch": 0.55, + "learning_rate": 8.820786676657698e-06, + "loss": 0.4845, + "step": 6468 + }, + { + "epoch": 0.55, + "learning_rate": 8.818044392568076e-06, + "loss": 0.4707, + "step": 6469 + }, + { + "epoch": 0.55, + "learning_rate": 8.815302198619328e-06, + "loss": 0.4919, + "step": 6470 + }, + { + "epoch": 0.55, + "learning_rate": 8.81256009502058e-06, + "loss": 0.475, + "step": 6471 + }, + { + "epoch": 0.55, + "learning_rate": 8.809818081980954e-06, + "loss": 0.4698, + "step": 6472 + }, + { + "epoch": 0.55, + "learning_rate": 8.807076159709572e-06, + "loss": 0.4548, + "step": 6473 + }, + { + "epoch": 0.55, + "learning_rate": 8.804334328415539e-06, + "loss": 0.4612, + "step": 6474 + }, + { + "epoch": 0.55, + "learning_rate": 8.801592588307964e-06, + "loss": 0.4819, + "step": 6475 + }, + { + "epoch": 0.55, + "learning_rate": 8.798850939595942e-06, + "loss": 0.4632, + "step": 6476 + }, + { + "epoch": 0.55, + "learning_rate": 8.796109382488561e-06, + "loss": 0.4807, + "step": 6477 + }, + { + "epoch": 0.55, + "learning_rate": 8.793367917194906e-06, + "loss": 0.4627, + "step": 6478 + }, + { + "epoch": 0.55, + "learning_rate": 8.790626543924048e-06, + "loss": 0.4812, + "step": 6479 + }, + { + "epoch": 0.55, + "learning_rate": 8.787885262885062e-06, + "loss": 0.4797, + "step": 6480 + }, + { + "epoch": 0.55, + "learning_rate": 8.785144074287006e-06, + "loss": 0.4535, + "step": 6481 + }, + { + "epoch": 0.55, + "learning_rate": 8.782402978338936e-06, + "loss": 0.4688, + "step": 6482 + }, + { + "epoch": 0.55, + "learning_rate": 8.779661975249893e-06, + "loss": 0.4502, + "step": 6483 + }, + { + "epoch": 0.55, + "learning_rate": 8.776921065228924e-06, + "loss": 0.4625, + "step": 6484 + }, + { + "epoch": 0.55, + "learning_rate": 8.774180248485065e-06, + "loss": 0.4842, + "step": 6485 + }, + { + "epoch": 0.55, + "learning_rate": 8.771439525227335e-06, + "loss": 0.4588, + "step": 6486 + }, + { + "epoch": 0.55, + "learning_rate": 8.768698895664757e-06, + "loss": 0.459, + "step": 6487 + }, + { + "epoch": 0.55, + "learning_rate": 8.765958360006339e-06, + "loss": 0.4659, + "step": 6488 + }, + { + "epoch": 0.55, + "learning_rate": 8.763217918461089e-06, + "loss": 0.4895, + "step": 6489 + }, + { + "epoch": 0.55, + "learning_rate": 8.760477571238006e-06, + "loss": 0.4673, + "step": 6490 + }, + { + "epoch": 0.55, + "learning_rate": 8.75773731854608e-06, + "loss": 0.46, + "step": 6491 + }, + { + "epoch": 0.55, + "learning_rate": 8.754997160594288e-06, + "loss": 0.4705, + "step": 6492 + }, + { + "epoch": 0.55, + "learning_rate": 8.75225709759161e-06, + "loss": 0.5027, + "step": 6493 + }, + { + "epoch": 0.55, + "learning_rate": 8.74951712974702e-06, + "loss": 0.4413, + "step": 6494 + }, + { + "epoch": 0.55, + "learning_rate": 8.74677725726947e-06, + "loss": 0.4759, + "step": 6495 + }, + { + "epoch": 0.55, + "learning_rate": 8.744037480367922e-06, + "loss": 0.4763, + "step": 6496 + }, + { + "epoch": 0.55, + "learning_rate": 8.741297799251314e-06, + "loss": 0.4715, + "step": 6497 + }, + { + "epoch": 0.55, + "learning_rate": 8.738558214128594e-06, + "loss": 0.4616, + "step": 6498 + }, + { + "epoch": 0.55, + "learning_rate": 8.735818725208692e-06, + "loss": 0.4713, + "step": 6499 + }, + { + "epoch": 0.55, + "learning_rate": 8.733079332700532e-06, + "loss": 0.466, + "step": 6500 + }, + { + "epoch": 0.55, + "learning_rate": 8.73034003681303e-06, + "loss": 0.455, + "step": 6501 + }, + { + "epoch": 0.55, + "learning_rate": 8.727600837755095e-06, + "loss": 0.4792, + "step": 6502 + }, + { + "epoch": 0.55, + "learning_rate": 8.724861735735635e-06, + "loss": 0.4589, + "step": 6503 + }, + { + "epoch": 0.55, + "learning_rate": 8.722122730963542e-06, + "loss": 0.4549, + "step": 6504 + }, + { + "epoch": 0.55, + "learning_rate": 8.719383823647708e-06, + "loss": 0.4839, + "step": 6505 + }, + { + "epoch": 0.55, + "learning_rate": 8.716645013997003e-06, + "loss": 0.4589, + "step": 6506 + }, + { + "epoch": 0.55, + "learning_rate": 8.71390630222031e-06, + "loss": 0.4554, + "step": 6507 + }, + { + "epoch": 0.55, + "learning_rate": 8.711167688526495e-06, + "loss": 0.4523, + "step": 6508 + }, + { + "epoch": 0.55, + "learning_rate": 8.70842917312441e-06, + "loss": 0.4894, + "step": 6509 + }, + { + "epoch": 0.56, + "learning_rate": 8.705690756222909e-06, + "loss": 0.4456, + "step": 6510 + }, + { + "epoch": 0.56, + "learning_rate": 8.702952438030832e-06, + "loss": 0.4682, + "step": 6511 + }, + { + "epoch": 0.56, + "learning_rate": 8.700214218757021e-06, + "loss": 0.4607, + "step": 6512 + }, + { + "epoch": 0.56, + "learning_rate": 8.697476098610299e-06, + "loss": 0.4763, + "step": 6513 + }, + { + "epoch": 0.56, + "learning_rate": 8.694738077799487e-06, + "loss": 0.4783, + "step": 6514 + }, + { + "epoch": 0.56, + "learning_rate": 8.692000156533395e-06, + "loss": 0.4731, + "step": 6515 + }, + { + "epoch": 0.56, + "learning_rate": 8.689262335020836e-06, + "loss": 0.4767, + "step": 6516 + }, + { + "epoch": 0.56, + "learning_rate": 8.686524613470603e-06, + "loss": 0.4897, + "step": 6517 + }, + { + "epoch": 0.56, + "learning_rate": 8.683786992091488e-06, + "loss": 0.4802, + "step": 6518 + }, + { + "epoch": 0.56, + "learning_rate": 8.68104947109227e-06, + "loss": 0.4711, + "step": 6519 + }, + { + "epoch": 0.56, + "learning_rate": 8.678312050681724e-06, + "loss": 0.4675, + "step": 6520 + }, + { + "epoch": 0.56, + "learning_rate": 8.675574731068622e-06, + "loss": 0.467, + "step": 6521 + }, + { + "epoch": 0.56, + "learning_rate": 8.672837512461718e-06, + "loss": 0.4695, + "step": 6522 + }, + { + "epoch": 0.56, + "learning_rate": 8.67010039506977e-06, + "loss": 0.4702, + "step": 6523 + }, + { + "epoch": 0.56, + "learning_rate": 8.667363379101513e-06, + "loss": 0.4734, + "step": 6524 + }, + { + "epoch": 0.56, + "learning_rate": 8.66462646476569e-06, + "loss": 0.471, + "step": 6525 + }, + { + "epoch": 0.56, + "learning_rate": 8.66188965227103e-06, + "loss": 0.4577, + "step": 6526 + }, + { + "epoch": 0.56, + "learning_rate": 8.659152941826251e-06, + "loss": 0.4765, + "step": 6527 + }, + { + "epoch": 0.56, + "learning_rate": 8.656416333640067e-06, + "loss": 0.481, + "step": 6528 + }, + { + "epoch": 0.56, + "learning_rate": 8.653679827921178e-06, + "loss": 0.4779, + "step": 6529 + }, + { + "epoch": 0.56, + "learning_rate": 8.65094342487829e-06, + "loss": 0.4838, + "step": 6530 + }, + { + "epoch": 0.56, + "learning_rate": 8.648207124720088e-06, + "loss": 0.4801, + "step": 6531 + }, + { + "epoch": 0.56, + "learning_rate": 8.645470927655254e-06, + "loss": 0.4762, + "step": 6532 + }, + { + "epoch": 0.56, + "learning_rate": 8.642734833892463e-06, + "loss": 0.4342, + "step": 6533 + }, + { + "epoch": 0.56, + "learning_rate": 8.639998843640377e-06, + "loss": 0.4836, + "step": 6534 + }, + { + "epoch": 0.56, + "learning_rate": 8.637262957107661e-06, + "loss": 0.4752, + "step": 6535 + }, + { + "epoch": 0.56, + "learning_rate": 8.63452717450296e-06, + "loss": 0.4701, + "step": 6536 + }, + { + "epoch": 0.56, + "learning_rate": 8.631791496034916e-06, + "loss": 0.5, + "step": 6537 + }, + { + "epoch": 0.56, + "learning_rate": 8.629055921912164e-06, + "loss": 0.4719, + "step": 6538 + }, + { + "epoch": 0.56, + "learning_rate": 8.626320452343333e-06, + "loss": 0.485, + "step": 6539 + }, + { + "epoch": 0.56, + "learning_rate": 8.623585087537039e-06, + "loss": 0.474, + "step": 6540 + }, + { + "epoch": 0.56, + "learning_rate": 8.620849827701893e-06, + "loss": 0.5026, + "step": 6541 + }, + { + "epoch": 0.56, + "learning_rate": 8.618114673046494e-06, + "loss": 0.4622, + "step": 6542 + }, + { + "epoch": 0.56, + "learning_rate": 8.61537962377944e-06, + "loss": 0.4581, + "step": 6543 + }, + { + "epoch": 0.56, + "learning_rate": 8.61264468010932e-06, + "loss": 0.4798, + "step": 6544 + }, + { + "epoch": 0.56, + "learning_rate": 8.609909842244706e-06, + "loss": 0.4415, + "step": 6545 + }, + { + "epoch": 0.56, + "learning_rate": 8.607175110394171e-06, + "loss": 0.4686, + "step": 6546 + }, + { + "epoch": 0.56, + "learning_rate": 8.604440484766276e-06, + "loss": 0.4793, + "step": 6547 + }, + { + "epoch": 0.56, + "learning_rate": 8.601705965569579e-06, + "loss": 0.4844, + "step": 6548 + }, + { + "epoch": 0.56, + "learning_rate": 8.59897155301262e-06, + "loss": 0.4452, + "step": 6549 + }, + { + "epoch": 0.56, + "learning_rate": 8.596237247303941e-06, + "loss": 0.484, + "step": 6550 + }, + { + "epoch": 0.56, + "learning_rate": 8.59350304865207e-06, + "loss": 0.453, + "step": 6551 + }, + { + "epoch": 0.56, + "learning_rate": 8.590768957265525e-06, + "loss": 0.477, + "step": 6552 + }, + { + "epoch": 0.56, + "learning_rate": 8.588034973352827e-06, + "loss": 0.4824, + "step": 6553 + }, + { + "epoch": 0.56, + "learning_rate": 8.585301097122473e-06, + "loss": 0.4757, + "step": 6554 + }, + { + "epoch": 0.56, + "learning_rate": 8.58256732878297e-06, + "loss": 0.4603, + "step": 6555 + }, + { + "epoch": 0.56, + "learning_rate": 8.579833668542796e-06, + "loss": 0.4603, + "step": 6556 + }, + { + "epoch": 0.56, + "learning_rate": 8.577100116610433e-06, + "loss": 0.4858, + "step": 6557 + }, + { + "epoch": 0.56, + "learning_rate": 8.574366673194357e-06, + "loss": 0.4603, + "step": 6558 + }, + { + "epoch": 0.56, + "learning_rate": 8.571633338503034e-06, + "loss": 0.4658, + "step": 6559 + }, + { + "epoch": 0.56, + "learning_rate": 8.568900112744912e-06, + "loss": 0.4644, + "step": 6560 + }, + { + "epoch": 0.56, + "learning_rate": 8.56616699612844e-06, + "loss": 0.4797, + "step": 6561 + }, + { + "epoch": 0.56, + "learning_rate": 8.563433988862064e-06, + "loss": 0.4716, + "step": 6562 + }, + { + "epoch": 0.56, + "learning_rate": 8.560701091154208e-06, + "loss": 0.4762, + "step": 6563 + }, + { + "epoch": 0.56, + "learning_rate": 8.557968303213296e-06, + "loss": 0.4816, + "step": 6564 + }, + { + "epoch": 0.56, + "learning_rate": 8.555235625247743e-06, + "loss": 0.4797, + "step": 6565 + }, + { + "epoch": 0.56, + "learning_rate": 8.552503057465949e-06, + "loss": 0.4658, + "step": 6566 + }, + { + "epoch": 0.56, + "learning_rate": 8.549770600076314e-06, + "loss": 0.4652, + "step": 6567 + }, + { + "epoch": 0.56, + "learning_rate": 8.547038253287233e-06, + "loss": 0.4546, + "step": 6568 + }, + { + "epoch": 0.56, + "learning_rate": 8.544306017307077e-06, + "loss": 0.504, + "step": 6569 + }, + { + "epoch": 0.56, + "learning_rate": 8.54157389234422e-06, + "loss": 0.4872, + "step": 6570 + }, + { + "epoch": 0.56, + "learning_rate": 8.538841878607031e-06, + "loss": 0.4786, + "step": 6571 + }, + { + "epoch": 0.56, + "learning_rate": 8.536109976303859e-06, + "loss": 0.462, + "step": 6572 + }, + { + "epoch": 0.56, + "learning_rate": 8.533378185643052e-06, + "loss": 0.4752, + "step": 6573 + }, + { + "epoch": 0.56, + "learning_rate": 8.530646506832949e-06, + "loss": 0.4819, + "step": 6574 + }, + { + "epoch": 0.56, + "learning_rate": 8.527914940081873e-06, + "loss": 0.4623, + "step": 6575 + }, + { + "epoch": 0.56, + "learning_rate": 8.525183485598152e-06, + "loss": 0.4537, + "step": 6576 + }, + { + "epoch": 0.56, + "learning_rate": 8.522452143590096e-06, + "loss": 0.4649, + "step": 6577 + }, + { + "epoch": 0.56, + "learning_rate": 8.519720914266008e-06, + "loss": 0.4619, + "step": 6578 + }, + { + "epoch": 0.56, + "learning_rate": 8.51698979783418e-06, + "loss": 0.4587, + "step": 6579 + }, + { + "epoch": 0.56, + "learning_rate": 8.514258794502906e-06, + "loss": 0.4833, + "step": 6580 + }, + { + "epoch": 0.56, + "learning_rate": 8.511527904480457e-06, + "loss": 0.4489, + "step": 6581 + }, + { + "epoch": 0.56, + "learning_rate": 8.508797127975105e-06, + "loss": 0.4903, + "step": 6582 + }, + { + "epoch": 0.56, + "learning_rate": 8.506066465195113e-06, + "loss": 0.494, + "step": 6583 + }, + { + "epoch": 0.56, + "learning_rate": 8.503335916348722e-06, + "loss": 0.4848, + "step": 6584 + }, + { + "epoch": 0.56, + "learning_rate": 8.500605481644186e-06, + "loss": 0.4764, + "step": 6585 + }, + { + "epoch": 0.56, + "learning_rate": 8.497875161289737e-06, + "loss": 0.4725, + "step": 6586 + }, + { + "epoch": 0.56, + "learning_rate": 8.495144955493596e-06, + "loss": 0.4746, + "step": 6587 + }, + { + "epoch": 0.56, + "learning_rate": 8.492414864463988e-06, + "loss": 0.4752, + "step": 6588 + }, + { + "epoch": 0.56, + "learning_rate": 8.489684888409111e-06, + "loss": 0.4868, + "step": 6589 + }, + { + "epoch": 0.56, + "learning_rate": 8.486955027537172e-06, + "loss": 0.4674, + "step": 6590 + }, + { + "epoch": 0.56, + "learning_rate": 8.484225282056362e-06, + "loss": 0.4617, + "step": 6591 + }, + { + "epoch": 0.56, + "learning_rate": 8.481495652174859e-06, + "loss": 0.4826, + "step": 6592 + }, + { + "epoch": 0.56, + "learning_rate": 8.478766138100834e-06, + "loss": 0.477, + "step": 6593 + }, + { + "epoch": 0.56, + "learning_rate": 8.476036740042456e-06, + "loss": 0.4541, + "step": 6594 + }, + { + "epoch": 0.56, + "learning_rate": 8.47330745820788e-06, + "loss": 0.4799, + "step": 6595 + }, + { + "epoch": 0.56, + "learning_rate": 8.470578292805249e-06, + "loss": 0.4762, + "step": 6596 + }, + { + "epoch": 0.56, + "learning_rate": 8.467849244042706e-06, + "loss": 0.4511, + "step": 6597 + }, + { + "epoch": 0.56, + "learning_rate": 8.465120312128371e-06, + "loss": 0.4655, + "step": 6598 + }, + { + "epoch": 0.56, + "learning_rate": 8.46239149727037e-06, + "loss": 0.4695, + "step": 6599 + }, + { + "epoch": 0.56, + "learning_rate": 8.459662799676818e-06, + "loss": 0.4795, + "step": 6600 + }, + { + "epoch": 0.56, + "learning_rate": 8.456934219555809e-06, + "loss": 0.4736, + "step": 6601 + }, + { + "epoch": 0.56, + "learning_rate": 8.454205757115434e-06, + "loss": 0.461, + "step": 6602 + }, + { + "epoch": 0.56, + "learning_rate": 8.451477412563786e-06, + "loss": 0.4846, + "step": 6603 + }, + { + "epoch": 0.56, + "learning_rate": 8.448749186108936e-06, + "loss": 0.4655, + "step": 6604 + }, + { + "epoch": 0.56, + "learning_rate": 8.446021077958947e-06, + "loss": 0.4818, + "step": 6605 + }, + { + "epoch": 0.56, + "learning_rate": 8.44329308832188e-06, + "loss": 0.4734, + "step": 6606 + }, + { + "epoch": 0.56, + "learning_rate": 8.440565217405778e-06, + "loss": 0.4472, + "step": 6607 + }, + { + "epoch": 0.56, + "learning_rate": 8.437837465418684e-06, + "loss": 0.4825, + "step": 6608 + }, + { + "epoch": 0.56, + "learning_rate": 8.43510983256863e-06, + "loss": 0.4765, + "step": 6609 + }, + { + "epoch": 0.56, + "learning_rate": 8.43238231906363e-06, + "loss": 0.4571, + "step": 6610 + }, + { + "epoch": 0.56, + "learning_rate": 8.429654925111701e-06, + "loss": 0.4623, + "step": 6611 + }, + { + "epoch": 0.56, + "learning_rate": 8.426927650920842e-06, + "loss": 0.4825, + "step": 6612 + }, + { + "epoch": 0.56, + "learning_rate": 8.42420049669905e-06, + "loss": 0.4713, + "step": 6613 + }, + { + "epoch": 0.56, + "learning_rate": 8.421473462654304e-06, + "loss": 0.482, + "step": 6614 + }, + { + "epoch": 0.56, + "learning_rate": 8.418746548994585e-06, + "loss": 0.4756, + "step": 6615 + }, + { + "epoch": 0.56, + "learning_rate": 8.416019755927851e-06, + "loss": 0.4738, + "step": 6616 + }, + { + "epoch": 0.56, + "learning_rate": 8.413293083662065e-06, + "loss": 0.4676, + "step": 6617 + }, + { + "epoch": 0.56, + "learning_rate": 8.410566532405175e-06, + "loss": 0.4694, + "step": 6618 + }, + { + "epoch": 0.56, + "learning_rate": 8.407840102365116e-06, + "loss": 0.4742, + "step": 6619 + }, + { + "epoch": 0.56, + "learning_rate": 8.405113793749819e-06, + "loss": 0.4408, + "step": 6620 + }, + { + "epoch": 0.56, + "learning_rate": 8.402387606767199e-06, + "loss": 0.4845, + "step": 6621 + }, + { + "epoch": 0.56, + "learning_rate": 8.399661541625174e-06, + "loss": 0.4823, + "step": 6622 + }, + { + "epoch": 0.56, + "learning_rate": 8.396935598531637e-06, + "loss": 0.455, + "step": 6623 + }, + { + "epoch": 0.56, + "learning_rate": 8.39420977769449e-06, + "loss": 0.4928, + "step": 6624 + }, + { + "epoch": 0.56, + "learning_rate": 8.391484079321602e-06, + "loss": 0.4736, + "step": 6625 + }, + { + "epoch": 0.56, + "learning_rate": 8.388758503620856e-06, + "loss": 0.4567, + "step": 6626 + }, + { + "epoch": 0.57, + "learning_rate": 8.386033050800116e-06, + "loss": 0.4586, + "step": 6627 + }, + { + "epoch": 0.57, + "learning_rate": 8.383307721067231e-06, + "loss": 0.4745, + "step": 6628 + }, + { + "epoch": 0.57, + "learning_rate": 8.38058251463005e-06, + "loss": 0.4847, + "step": 6629 + }, + { + "epoch": 0.57, + "learning_rate": 8.377857431696405e-06, + "loss": 0.464, + "step": 6630 + }, + { + "epoch": 0.57, + "learning_rate": 8.375132472474127e-06, + "loss": 0.4792, + "step": 6631 + }, + { + "epoch": 0.57, + "learning_rate": 8.37240763717103e-06, + "loss": 0.4637, + "step": 6632 + }, + { + "epoch": 0.57, + "learning_rate": 8.369682925994922e-06, + "loss": 0.4667, + "step": 6633 + }, + { + "epoch": 0.57, + "learning_rate": 8.3669583391536e-06, + "loss": 0.4725, + "step": 6634 + }, + { + "epoch": 0.57, + "learning_rate": 8.364233876854848e-06, + "loss": 0.4778, + "step": 6635 + }, + { + "epoch": 0.57, + "learning_rate": 8.361509539306456e-06, + "loss": 0.4553, + "step": 6636 + }, + { + "epoch": 0.57, + "learning_rate": 8.358785326716184e-06, + "loss": 0.4799, + "step": 6637 + }, + { + "epoch": 0.57, + "learning_rate": 8.356061239291798e-06, + "loss": 0.4733, + "step": 6638 + }, + { + "epoch": 0.57, + "learning_rate": 8.35333727724104e-06, + "loss": 0.4771, + "step": 6639 + }, + { + "epoch": 0.57, + "learning_rate": 8.350613440771661e-06, + "loss": 0.4629, + "step": 6640 + }, + { + "epoch": 0.57, + "learning_rate": 8.347889730091384e-06, + "loss": 0.4828, + "step": 6641 + }, + { + "epoch": 0.57, + "learning_rate": 8.345166145407935e-06, + "loss": 0.4619, + "step": 6642 + }, + { + "epoch": 0.57, + "learning_rate": 8.342442686929024e-06, + "loss": 0.4621, + "step": 6643 + }, + { + "epoch": 0.57, + "learning_rate": 8.33971935486235e-06, + "loss": 0.4995, + "step": 6644 + }, + { + "epoch": 0.57, + "learning_rate": 8.336996149415616e-06, + "loss": 0.4787, + "step": 6645 + }, + { + "epoch": 0.57, + "learning_rate": 8.334273070796495e-06, + "loss": 0.4826, + "step": 6646 + }, + { + "epoch": 0.57, + "learning_rate": 8.331550119212665e-06, + "loss": 0.4721, + "step": 6647 + }, + { + "epoch": 0.57, + "learning_rate": 8.328827294871786e-06, + "loss": 0.455, + "step": 6648 + }, + { + "epoch": 0.57, + "learning_rate": 8.326104597981517e-06, + "loss": 0.4669, + "step": 6649 + }, + { + "epoch": 0.57, + "learning_rate": 8.323382028749499e-06, + "loss": 0.4655, + "step": 6650 + }, + { + "epoch": 0.57, + "learning_rate": 8.320659587383369e-06, + "loss": 0.4754, + "step": 6651 + }, + { + "epoch": 0.57, + "learning_rate": 8.317937274090748e-06, + "loss": 0.4737, + "step": 6652 + }, + { + "epoch": 0.57, + "learning_rate": 8.315215089079249e-06, + "loss": 0.4652, + "step": 6653 + }, + { + "epoch": 0.57, + "learning_rate": 8.312493032556489e-06, + "loss": 0.4893, + "step": 6654 + }, + { + "epoch": 0.57, + "learning_rate": 8.309771104730049e-06, + "loss": 0.4733, + "step": 6655 + }, + { + "epoch": 0.57, + "learning_rate": 8.307049305807525e-06, + "loss": 0.4832, + "step": 6656 + }, + { + "epoch": 0.57, + "learning_rate": 8.304327635996486e-06, + "loss": 0.4499, + "step": 6657 + }, + { + "epoch": 0.57, + "learning_rate": 8.301606095504501e-06, + "loss": 0.4876, + "step": 6658 + }, + { + "epoch": 0.57, + "learning_rate": 8.298884684539128e-06, + "loss": 0.4798, + "step": 6659 + }, + { + "epoch": 0.57, + "learning_rate": 8.296163403307912e-06, + "loss": 0.4653, + "step": 6660 + }, + { + "epoch": 0.57, + "learning_rate": 8.293442252018384e-06, + "loss": 0.4752, + "step": 6661 + }, + { + "epoch": 0.57, + "learning_rate": 8.290721230878074e-06, + "loss": 0.4627, + "step": 6662 + }, + { + "epoch": 0.57, + "learning_rate": 8.288000340094502e-06, + "loss": 0.4844, + "step": 6663 + }, + { + "epoch": 0.57, + "learning_rate": 8.28527957987517e-06, + "loss": 0.4664, + "step": 6664 + }, + { + "epoch": 0.57, + "learning_rate": 8.282558950427578e-06, + "loss": 0.484, + "step": 6665 + }, + { + "epoch": 0.57, + "learning_rate": 8.279838451959209e-06, + "loss": 0.4703, + "step": 6666 + }, + { + "epoch": 0.57, + "learning_rate": 8.277118084677538e-06, + "loss": 0.4982, + "step": 6667 + }, + { + "epoch": 0.57, + "learning_rate": 8.274397848790041e-06, + "loss": 0.4725, + "step": 6668 + }, + { + "epoch": 0.57, + "learning_rate": 8.271677744504166e-06, + "loss": 0.4418, + "step": 6669 + }, + { + "epoch": 0.57, + "learning_rate": 8.26895777202736e-06, + "loss": 0.4962, + "step": 6670 + }, + { + "epoch": 0.57, + "learning_rate": 8.26623793156706e-06, + "loss": 0.4764, + "step": 6671 + }, + { + "epoch": 0.57, + "learning_rate": 8.263518223330698e-06, + "loss": 0.465, + "step": 6672 + }, + { + "epoch": 0.57, + "learning_rate": 8.260798647525684e-06, + "loss": 0.4863, + "step": 6673 + }, + { + "epoch": 0.57, + "learning_rate": 8.258079204359427e-06, + "loss": 0.4664, + "step": 6674 + }, + { + "epoch": 0.57, + "learning_rate": 8.255359894039319e-06, + "loss": 0.4655, + "step": 6675 + }, + { + "epoch": 0.57, + "learning_rate": 8.252640716772748e-06, + "loss": 0.4635, + "step": 6676 + }, + { + "epoch": 0.57, + "learning_rate": 8.249921672767095e-06, + "loss": 0.4817, + "step": 6677 + }, + { + "epoch": 0.57, + "learning_rate": 8.247202762229723e-06, + "loss": 0.4589, + "step": 6678 + }, + { + "epoch": 0.57, + "learning_rate": 8.244483985367984e-06, + "loss": 0.4587, + "step": 6679 + }, + { + "epoch": 0.57, + "learning_rate": 8.241765342389222e-06, + "loss": 0.4611, + "step": 6680 + }, + { + "epoch": 0.57, + "learning_rate": 8.239046833500779e-06, + "loss": 0.4848, + "step": 6681 + }, + { + "epoch": 0.57, + "learning_rate": 8.236328458909975e-06, + "loss": 0.468, + "step": 6682 + }, + { + "epoch": 0.57, + "learning_rate": 8.233610218824129e-06, + "loss": 0.4642, + "step": 6683 + }, + { + "epoch": 0.57, + "learning_rate": 8.23089211345054e-06, + "loss": 0.4677, + "step": 6684 + }, + { + "epoch": 0.57, + "learning_rate": 8.2281741429965e-06, + "loss": 0.4519, + "step": 6685 + }, + { + "epoch": 0.57, + "learning_rate": 8.225456307669301e-06, + "loss": 0.4625, + "step": 6686 + }, + { + "epoch": 0.57, + "learning_rate": 8.222738607676214e-06, + "loss": 0.459, + "step": 6687 + }, + { + "epoch": 0.57, + "learning_rate": 8.2200210432245e-06, + "loss": 0.4463, + "step": 6688 + }, + { + "epoch": 0.57, + "learning_rate": 8.217303614521412e-06, + "loss": 0.4575, + "step": 6689 + }, + { + "epoch": 0.57, + "learning_rate": 8.214586321774189e-06, + "loss": 0.4783, + "step": 6690 + }, + { + "epoch": 0.57, + "learning_rate": 8.21186916519007e-06, + "loss": 0.5001, + "step": 6691 + }, + { + "epoch": 0.57, + "learning_rate": 8.209152144976275e-06, + "loss": 0.4659, + "step": 6692 + }, + { + "epoch": 0.57, + "learning_rate": 8.206435261340014e-06, + "loss": 0.4801, + "step": 6693 + }, + { + "epoch": 0.57, + "learning_rate": 8.203718514488483e-06, + "loss": 0.4836, + "step": 6694 + }, + { + "epoch": 0.57, + "learning_rate": 8.201001904628883e-06, + "loss": 0.4593, + "step": 6695 + }, + { + "epoch": 0.57, + "learning_rate": 8.198285431968388e-06, + "loss": 0.4809, + "step": 6696 + }, + { + "epoch": 0.57, + "learning_rate": 8.195569096714166e-06, + "loss": 0.4888, + "step": 6697 + }, + { + "epoch": 0.57, + "learning_rate": 8.19285289907338e-06, + "loss": 0.4812, + "step": 6698 + }, + { + "epoch": 0.57, + "learning_rate": 8.190136839253171e-06, + "loss": 0.4726, + "step": 6699 + }, + { + "epoch": 0.57, + "learning_rate": 8.187420917460686e-06, + "loss": 0.4823, + "step": 6700 + }, + { + "epoch": 0.57, + "learning_rate": 8.184705133903053e-06, + "loss": 0.4685, + "step": 6701 + }, + { + "epoch": 0.57, + "learning_rate": 8.181989488787381e-06, + "loss": 0.4827, + "step": 6702 + }, + { + "epoch": 0.57, + "learning_rate": 8.179273982320778e-06, + "loss": 0.4712, + "step": 6703 + }, + { + "epoch": 0.57, + "learning_rate": 8.176558614710347e-06, + "loss": 0.4858, + "step": 6704 + }, + { + "epoch": 0.57, + "learning_rate": 8.17384338616317e-06, + "loss": 0.4487, + "step": 6705 + }, + { + "epoch": 0.57, + "learning_rate": 8.171128296886316e-06, + "loss": 0.4683, + "step": 6706 + }, + { + "epoch": 0.57, + "learning_rate": 8.168413347086856e-06, + "loss": 0.4842, + "step": 6707 + }, + { + "epoch": 0.57, + "learning_rate": 8.165698536971838e-06, + "loss": 0.4556, + "step": 6708 + }, + { + "epoch": 0.57, + "learning_rate": 8.162983866748308e-06, + "loss": 0.475, + "step": 6709 + }, + { + "epoch": 0.57, + "learning_rate": 8.160269336623301e-06, + "loss": 0.4587, + "step": 6710 + }, + { + "epoch": 0.57, + "learning_rate": 8.157554946803832e-06, + "loss": 0.4697, + "step": 6711 + }, + { + "epoch": 0.57, + "learning_rate": 8.154840697496917e-06, + "loss": 0.4658, + "step": 6712 + }, + { + "epoch": 0.57, + "learning_rate": 8.15212658890955e-06, + "loss": 0.4598, + "step": 6713 + }, + { + "epoch": 0.57, + "learning_rate": 8.149412621248729e-06, + "loss": 0.4801, + "step": 6714 + }, + { + "epoch": 0.57, + "learning_rate": 8.146698794721423e-06, + "loss": 0.4554, + "step": 6715 + }, + { + "epoch": 0.57, + "learning_rate": 8.143985109534609e-06, + "loss": 0.4661, + "step": 6716 + }, + { + "epoch": 0.57, + "learning_rate": 8.141271565895233e-06, + "loss": 0.4831, + "step": 6717 + }, + { + "epoch": 0.57, + "learning_rate": 8.138558164010251e-06, + "loss": 0.4628, + "step": 6718 + }, + { + "epoch": 0.57, + "learning_rate": 8.135844904086596e-06, + "loss": 0.4667, + "step": 6719 + }, + { + "epoch": 0.57, + "learning_rate": 8.133131786331188e-06, + "loss": 0.4647, + "step": 6720 + }, + { + "epoch": 0.57, + "learning_rate": 8.130418810950948e-06, + "loss": 0.4694, + "step": 6721 + }, + { + "epoch": 0.57, + "learning_rate": 8.127705978152769e-06, + "loss": 0.4775, + "step": 6722 + }, + { + "epoch": 0.57, + "learning_rate": 8.124993288143553e-06, + "loss": 0.4702, + "step": 6723 + }, + { + "epoch": 0.57, + "learning_rate": 8.122280741130177e-06, + "loss": 0.4506, + "step": 6724 + }, + { + "epoch": 0.57, + "learning_rate": 8.11956833731951e-06, + "loss": 0.4709, + "step": 6725 + }, + { + "epoch": 0.57, + "learning_rate": 8.11685607691841e-06, + "loss": 0.4546, + "step": 6726 + }, + { + "epoch": 0.57, + "learning_rate": 8.114143960133728e-06, + "loss": 0.4746, + "step": 6727 + }, + { + "epoch": 0.57, + "learning_rate": 8.111431987172303e-06, + "loss": 0.4603, + "step": 6728 + }, + { + "epoch": 0.57, + "learning_rate": 8.10872015824096e-06, + "loss": 0.4722, + "step": 6729 + }, + { + "epoch": 0.57, + "learning_rate": 8.106008473546512e-06, + "loss": 0.4658, + "step": 6730 + }, + { + "epoch": 0.57, + "learning_rate": 8.103296933295762e-06, + "loss": 0.4835, + "step": 6731 + }, + { + "epoch": 0.57, + "learning_rate": 8.10058553769551e-06, + "loss": 0.4863, + "step": 6732 + }, + { + "epoch": 0.57, + "learning_rate": 8.097874286952534e-06, + "loss": 0.4719, + "step": 6733 + }, + { + "epoch": 0.57, + "learning_rate": 8.095163181273608e-06, + "loss": 0.4696, + "step": 6734 + }, + { + "epoch": 0.57, + "learning_rate": 8.092452220865485e-06, + "loss": 0.474, + "step": 6735 + }, + { + "epoch": 0.57, + "learning_rate": 8.089741405934923e-06, + "loss": 0.4813, + "step": 6736 + }, + { + "epoch": 0.57, + "learning_rate": 8.087030736688657e-06, + "loss": 0.4816, + "step": 6737 + }, + { + "epoch": 0.57, + "learning_rate": 8.084320213333413e-06, + "loss": 0.484, + "step": 6738 + }, + { + "epoch": 0.57, + "learning_rate": 8.081609836075907e-06, + "loss": 0.4835, + "step": 6739 + }, + { + "epoch": 0.57, + "learning_rate": 8.07889960512284e-06, + "loss": 0.4424, + "step": 6740 + }, + { + "epoch": 0.57, + "learning_rate": 8.076189520680914e-06, + "loss": 0.4822, + "step": 6741 + }, + { + "epoch": 0.57, + "learning_rate": 8.073479582956806e-06, + "loss": 0.4743, + "step": 6742 + }, + { + "epoch": 0.57, + "learning_rate": 8.070769792157192e-06, + "loss": 0.4684, + "step": 6743 + }, + { + "epoch": 0.58, + "learning_rate": 8.068060148488722e-06, + "loss": 0.4763, + "step": 6744 + }, + { + "epoch": 0.58, + "learning_rate": 8.065350652158051e-06, + "loss": 0.4825, + "step": 6745 + }, + { + "epoch": 0.58, + "learning_rate": 8.062641303371818e-06, + "loss": 0.4745, + "step": 6746 + }, + { + "epoch": 0.58, + "learning_rate": 8.059932102336647e-06, + "loss": 0.4657, + "step": 6747 + }, + { + "epoch": 0.58, + "learning_rate": 8.057223049259155e-06, + "loss": 0.4838, + "step": 6748 + }, + { + "epoch": 0.58, + "learning_rate": 8.054514144345941e-06, + "loss": 0.4686, + "step": 6749 + }, + { + "epoch": 0.58, + "learning_rate": 8.051805387803601e-06, + "loss": 0.4882, + "step": 6750 + }, + { + "epoch": 0.58, + "learning_rate": 8.04909677983872e-06, + "loss": 0.469, + "step": 6751 + }, + { + "epoch": 0.58, + "learning_rate": 8.046388320657861e-06, + "loss": 0.4728, + "step": 6752 + }, + { + "epoch": 0.58, + "learning_rate": 8.043680010467583e-06, + "loss": 0.451, + "step": 6753 + }, + { + "epoch": 0.58, + "learning_rate": 8.040971849474432e-06, + "loss": 0.4723, + "step": 6754 + }, + { + "epoch": 0.58, + "learning_rate": 8.038263837884952e-06, + "loss": 0.4777, + "step": 6755 + }, + { + "epoch": 0.58, + "learning_rate": 8.03555597590566e-06, + "loss": 0.4435, + "step": 6756 + }, + { + "epoch": 0.58, + "learning_rate": 8.032848263743071e-06, + "loss": 0.4769, + "step": 6757 + }, + { + "epoch": 0.58, + "learning_rate": 8.030140701603684e-06, + "loss": 0.4685, + "step": 6758 + }, + { + "epoch": 0.58, + "learning_rate": 8.027433289693991e-06, + "loss": 0.4958, + "step": 6759 + }, + { + "epoch": 0.58, + "learning_rate": 8.024726028220474e-06, + "loss": 0.4782, + "step": 6760 + }, + { + "epoch": 0.58, + "learning_rate": 8.022018917389597e-06, + "loss": 0.4655, + "step": 6761 + }, + { + "epoch": 0.58, + "learning_rate": 8.019311957407811e-06, + "loss": 0.4731, + "step": 6762 + }, + { + "epoch": 0.58, + "learning_rate": 8.016605148481565e-06, + "loss": 0.4586, + "step": 6763 + }, + { + "epoch": 0.58, + "learning_rate": 8.013898490817293e-06, + "loss": 0.4829, + "step": 6764 + }, + { + "epoch": 0.58, + "learning_rate": 8.011191984621412e-06, + "loss": 0.4623, + "step": 6765 + }, + { + "epoch": 0.58, + "learning_rate": 8.008485630100336e-06, + "loss": 0.4632, + "step": 6766 + }, + { + "epoch": 0.58, + "learning_rate": 8.005779427460457e-06, + "loss": 0.4899, + "step": 6767 + }, + { + "epoch": 0.58, + "learning_rate": 8.003073376908163e-06, + "loss": 0.4757, + "step": 6768 + }, + { + "epoch": 0.58, + "learning_rate": 8.000367478649835e-06, + "loss": 0.4571, + "step": 6769 + }, + { + "epoch": 0.58, + "learning_rate": 7.99766173289183e-06, + "loss": 0.4623, + "step": 6770 + }, + { + "epoch": 0.58, + "learning_rate": 7.9949561398405e-06, + "loss": 0.4867, + "step": 6771 + }, + { + "epoch": 0.58, + "learning_rate": 7.992250699702182e-06, + "loss": 0.4527, + "step": 6772 + }, + { + "epoch": 0.58, + "learning_rate": 7.989545412683214e-06, + "loss": 0.4685, + "step": 6773 + }, + { + "epoch": 0.58, + "learning_rate": 7.986840278989902e-06, + "loss": 0.4848, + "step": 6774 + }, + { + "epoch": 0.58, + "learning_rate": 7.98413529882856e-06, + "loss": 0.4639, + "step": 6775 + }, + { + "epoch": 0.58, + "learning_rate": 7.98143047240547e-06, + "loss": 0.4662, + "step": 6776 + }, + { + "epoch": 0.58, + "learning_rate": 7.97872579992692e-06, + "loss": 0.458, + "step": 6777 + }, + { + "epoch": 0.58, + "learning_rate": 7.976021281599182e-06, + "loss": 0.4792, + "step": 6778 + }, + { + "epoch": 0.58, + "learning_rate": 7.973316917628513e-06, + "loss": 0.4432, + "step": 6779 + }, + { + "epoch": 0.58, + "learning_rate": 7.970612708221153e-06, + "loss": 0.4887, + "step": 6780 + }, + { + "epoch": 0.58, + "learning_rate": 7.967908653583338e-06, + "loss": 0.4733, + "step": 6781 + }, + { + "epoch": 0.58, + "learning_rate": 7.9652047539213e-06, + "loss": 0.4818, + "step": 6782 + }, + { + "epoch": 0.58, + "learning_rate": 7.962501009441236e-06, + "loss": 0.4753, + "step": 6783 + }, + { + "epoch": 0.58, + "learning_rate": 7.959797420349356e-06, + "loss": 0.447, + "step": 6784 + }, + { + "epoch": 0.58, + "learning_rate": 7.957093986851839e-06, + "loss": 0.469, + "step": 6785 + }, + { + "epoch": 0.58, + "learning_rate": 7.954390709154863e-06, + "loss": 0.4612, + "step": 6786 + }, + { + "epoch": 0.58, + "learning_rate": 7.951687587464595e-06, + "loss": 0.4786, + "step": 6787 + }, + { + "epoch": 0.58, + "learning_rate": 7.94898462198718e-06, + "loss": 0.4595, + "step": 6788 + }, + { + "epoch": 0.58, + "learning_rate": 7.946281812928763e-06, + "loss": 0.4718, + "step": 6789 + }, + { + "epoch": 0.58, + "learning_rate": 7.943579160495466e-06, + "loss": 0.4945, + "step": 6790 + }, + { + "epoch": 0.58, + "learning_rate": 7.940876664893411e-06, + "loss": 0.4822, + "step": 6791 + }, + { + "epoch": 0.58, + "learning_rate": 7.938174326328696e-06, + "loss": 0.4711, + "step": 6792 + }, + { + "epoch": 0.58, + "learning_rate": 7.935472145007416e-06, + "loss": 0.4786, + "step": 6793 + }, + { + "epoch": 0.58, + "learning_rate": 7.932770121135648e-06, + "loss": 0.4609, + "step": 6794 + }, + { + "epoch": 0.58, + "learning_rate": 7.93006825491946e-06, + "loss": 0.4843, + "step": 6795 + }, + { + "epoch": 0.58, + "learning_rate": 7.927366546564911e-06, + "loss": 0.481, + "step": 6796 + }, + { + "epoch": 0.58, + "learning_rate": 7.92466499627804e-06, + "loss": 0.4788, + "step": 6797 + }, + { + "epoch": 0.58, + "learning_rate": 7.921963604264884e-06, + "loss": 0.4863, + "step": 6798 + }, + { + "epoch": 0.58, + "learning_rate": 7.919262370731459e-06, + "loss": 0.4495, + "step": 6799 + }, + { + "epoch": 0.58, + "learning_rate": 7.916561295883767e-06, + "loss": 0.4726, + "step": 6800 + }, + { + "epoch": 0.58, + "learning_rate": 7.913860379927812e-06, + "loss": 0.4844, + "step": 6801 + }, + { + "epoch": 0.58, + "learning_rate": 7.911159623069575e-06, + "loss": 0.4869, + "step": 6802 + }, + { + "epoch": 0.58, + "learning_rate": 7.908459025515024e-06, + "loss": 0.479, + "step": 6803 + }, + { + "epoch": 0.58, + "learning_rate": 7.905758587470119e-06, + "loss": 0.461, + "step": 6804 + }, + { + "epoch": 0.58, + "learning_rate": 7.903058309140809e-06, + "loss": 0.4597, + "step": 6805 + }, + { + "epoch": 0.58, + "learning_rate": 7.900358190733026e-06, + "loss": 0.4672, + "step": 6806 + }, + { + "epoch": 0.58, + "learning_rate": 7.897658232452696e-06, + "loss": 0.4806, + "step": 6807 + }, + { + "epoch": 0.58, + "learning_rate": 7.894958434505725e-06, + "loss": 0.4619, + "step": 6808 + }, + { + "epoch": 0.58, + "learning_rate": 7.892258797098008e-06, + "loss": 0.4651, + "step": 6809 + }, + { + "epoch": 0.58, + "learning_rate": 7.889559320435436e-06, + "loss": 0.4695, + "step": 6810 + }, + { + "epoch": 0.58, + "learning_rate": 7.886860004723885e-06, + "loss": 0.4835, + "step": 6811 + }, + { + "epoch": 0.58, + "learning_rate": 7.884160850169209e-06, + "loss": 0.4721, + "step": 6812 + }, + { + "epoch": 0.58, + "learning_rate": 7.881461856977259e-06, + "loss": 0.4731, + "step": 6813 + }, + { + "epoch": 0.58, + "learning_rate": 7.878763025353875e-06, + "loss": 0.495, + "step": 6814 + }, + { + "epoch": 0.58, + "learning_rate": 7.876064355504877e-06, + "loss": 0.4709, + "step": 6815 + }, + { + "epoch": 0.58, + "learning_rate": 7.873365847636081e-06, + "loss": 0.46, + "step": 6816 + }, + { + "epoch": 0.58, + "learning_rate": 7.870667501953284e-06, + "loss": 0.4856, + "step": 6817 + }, + { + "epoch": 0.58, + "learning_rate": 7.867969318662267e-06, + "loss": 0.4658, + "step": 6818 + }, + { + "epoch": 0.58, + "learning_rate": 7.865271297968815e-06, + "loss": 0.4894, + "step": 6819 + }, + { + "epoch": 0.58, + "learning_rate": 7.862573440078686e-06, + "loss": 0.4766, + "step": 6820 + }, + { + "epoch": 0.58, + "learning_rate": 7.85987574519763e-06, + "loss": 0.472, + "step": 6821 + }, + { + "epoch": 0.58, + "learning_rate": 7.857178213531385e-06, + "loss": 0.4764, + "step": 6822 + }, + { + "epoch": 0.58, + "learning_rate": 7.854480845285672e-06, + "loss": 0.4838, + "step": 6823 + }, + { + "epoch": 0.58, + "learning_rate": 7.851783640666209e-06, + "loss": 0.4739, + "step": 6824 + }, + { + "epoch": 0.58, + "learning_rate": 7.849086599878697e-06, + "loss": 0.4549, + "step": 6825 + }, + { + "epoch": 0.58, + "learning_rate": 7.846389723128819e-06, + "loss": 0.4616, + "step": 6826 + }, + { + "epoch": 0.58, + "learning_rate": 7.843693010622249e-06, + "loss": 0.4571, + "step": 6827 + }, + { + "epoch": 0.58, + "learning_rate": 7.840996462564654e-06, + "loss": 0.4682, + "step": 6828 + }, + { + "epoch": 0.58, + "learning_rate": 7.838300079161684e-06, + "loss": 0.4791, + "step": 6829 + }, + { + "epoch": 0.58, + "learning_rate": 7.835603860618973e-06, + "loss": 0.4546, + "step": 6830 + }, + { + "epoch": 0.58, + "learning_rate": 7.832907807142149e-06, + "loss": 0.4762, + "step": 6831 + }, + { + "epoch": 0.58, + "learning_rate": 7.83021191893682e-06, + "loss": 0.4588, + "step": 6832 + }, + { + "epoch": 0.58, + "learning_rate": 7.82751619620859e-06, + "loss": 0.4616, + "step": 6833 + }, + { + "epoch": 0.58, + "learning_rate": 7.824820639163047e-06, + "loss": 0.466, + "step": 6834 + }, + { + "epoch": 0.58, + "learning_rate": 7.822125248005764e-06, + "loss": 0.4598, + "step": 6835 + }, + { + "epoch": 0.58, + "learning_rate": 7.819430022942298e-06, + "loss": 0.4742, + "step": 6836 + }, + { + "epoch": 0.58, + "learning_rate": 7.816734964178202e-06, + "loss": 0.4715, + "step": 6837 + }, + { + "epoch": 0.58, + "learning_rate": 7.814040071919016e-06, + "loss": 0.4704, + "step": 6838 + }, + { + "epoch": 0.58, + "learning_rate": 7.811345346370257e-06, + "loss": 0.4686, + "step": 6839 + }, + { + "epoch": 0.58, + "learning_rate": 7.808650787737443e-06, + "loss": 0.4908, + "step": 6840 + }, + { + "epoch": 0.58, + "learning_rate": 7.805956396226064e-06, + "loss": 0.4551, + "step": 6841 + }, + { + "epoch": 0.58, + "learning_rate": 7.80326217204161e-06, + "loss": 0.4837, + "step": 6842 + }, + { + "epoch": 0.58, + "learning_rate": 7.800568115389559e-06, + "loss": 0.475, + "step": 6843 + }, + { + "epoch": 0.58, + "learning_rate": 7.797874226475362e-06, + "loss": 0.4791, + "step": 6844 + }, + { + "epoch": 0.58, + "learning_rate": 7.795180505504472e-06, + "loss": 0.4853, + "step": 6845 + }, + { + "epoch": 0.58, + "learning_rate": 7.792486952682319e-06, + "loss": 0.4614, + "step": 6846 + }, + { + "epoch": 0.58, + "learning_rate": 7.78979356821433e-06, + "loss": 0.4718, + "step": 6847 + }, + { + "epoch": 0.58, + "learning_rate": 7.78710035230591e-06, + "loss": 0.4769, + "step": 6848 + }, + { + "epoch": 0.58, + "learning_rate": 7.784407305162456e-06, + "loss": 0.4812, + "step": 6849 + }, + { + "epoch": 0.58, + "learning_rate": 7.781714426989346e-06, + "loss": 0.471, + "step": 6850 + }, + { + "epoch": 0.58, + "learning_rate": 7.779021717991959e-06, + "loss": 0.4658, + "step": 6851 + }, + { + "epoch": 0.58, + "learning_rate": 7.77632917837565e-06, + "loss": 0.462, + "step": 6852 + }, + { + "epoch": 0.58, + "learning_rate": 7.773636808345757e-06, + "loss": 0.4679, + "step": 6853 + }, + { + "epoch": 0.58, + "learning_rate": 7.770944608107622e-06, + "loss": 0.4648, + "step": 6854 + }, + { + "epoch": 0.58, + "learning_rate": 7.76825257786655e-06, + "loss": 0.4595, + "step": 6855 + }, + { + "epoch": 0.58, + "learning_rate": 7.765560717827857e-06, + "loss": 0.4763, + "step": 6856 + }, + { + "epoch": 0.58, + "learning_rate": 7.762869028196832e-06, + "loss": 0.4627, + "step": 6857 + }, + { + "epoch": 0.58, + "learning_rate": 7.760177509178756e-06, + "loss": 0.4843, + "step": 6858 + }, + { + "epoch": 0.58, + "learning_rate": 7.757486160978891e-06, + "loss": 0.4733, + "step": 6859 + }, + { + "epoch": 0.58, + "learning_rate": 7.754794983802494e-06, + "loss": 0.4763, + "step": 6860 + }, + { + "epoch": 0.59, + "learning_rate": 7.752103977854809e-06, + "loss": 0.4751, + "step": 6861 + }, + { + "epoch": 0.59, + "learning_rate": 7.749413143341056e-06, + "loss": 0.488, + "step": 6862 + }, + { + "epoch": 0.59, + "learning_rate": 7.746722480466456e-06, + "loss": 0.4751, + "step": 6863 + }, + { + "epoch": 0.59, + "learning_rate": 7.7440319894362e-06, + "loss": 0.4829, + "step": 6864 + }, + { + "epoch": 0.59, + "learning_rate": 7.741341670455489e-06, + "loss": 0.4892, + "step": 6865 + }, + { + "epoch": 0.59, + "learning_rate": 7.73865152372949e-06, + "loss": 0.4674, + "step": 6866 + }, + { + "epoch": 0.59, + "learning_rate": 7.735961549463368e-06, + "loss": 0.4575, + "step": 6867 + }, + { + "epoch": 0.59, + "learning_rate": 7.733271747862265e-06, + "loss": 0.4668, + "step": 6868 + }, + { + "epoch": 0.59, + "learning_rate": 7.730582119131328e-06, + "loss": 0.4634, + "step": 6869 + }, + { + "epoch": 0.59, + "learning_rate": 7.727892663475672e-06, + "loss": 0.4493, + "step": 6870 + }, + { + "epoch": 0.59, + "learning_rate": 7.725203381100403e-06, + "loss": 0.4587, + "step": 6871 + }, + { + "epoch": 0.59, + "learning_rate": 7.722514272210627e-06, + "loss": 0.4765, + "step": 6872 + }, + { + "epoch": 0.59, + "learning_rate": 7.719825337011415e-06, + "loss": 0.453, + "step": 6873 + }, + { + "epoch": 0.59, + "learning_rate": 7.717136575707846e-06, + "loss": 0.4642, + "step": 6874 + }, + { + "epoch": 0.59, + "learning_rate": 7.714447988504972e-06, + "loss": 0.4499, + "step": 6875 + }, + { + "epoch": 0.59, + "learning_rate": 7.711759575607838e-06, + "loss": 0.4527, + "step": 6876 + }, + { + "epoch": 0.59, + "learning_rate": 7.709071337221468e-06, + "loss": 0.4996, + "step": 6877 + }, + { + "epoch": 0.59, + "learning_rate": 7.706383273550883e-06, + "loss": 0.444, + "step": 6878 + }, + { + "epoch": 0.59, + "learning_rate": 7.703695384801086e-06, + "loss": 0.4797, + "step": 6879 + }, + { + "epoch": 0.59, + "learning_rate": 7.701007671177066e-06, + "loss": 0.4592, + "step": 6880 + }, + { + "epoch": 0.59, + "learning_rate": 7.698320132883801e-06, + "loss": 0.4791, + "step": 6881 + }, + { + "epoch": 0.59, + "learning_rate": 7.695632770126247e-06, + "loss": 0.4682, + "step": 6882 + }, + { + "epoch": 0.59, + "learning_rate": 7.692945583109362e-06, + "loss": 0.4499, + "step": 6883 + }, + { + "epoch": 0.59, + "learning_rate": 7.690258572038077e-06, + "loss": 0.5006, + "step": 6884 + }, + { + "epoch": 0.59, + "learning_rate": 7.687571737117318e-06, + "loss": 0.4488, + "step": 6885 + }, + { + "epoch": 0.59, + "learning_rate": 7.684885078551991e-06, + "loss": 0.4645, + "step": 6886 + }, + { + "epoch": 0.59, + "learning_rate": 7.682198596546992e-06, + "loss": 0.4467, + "step": 6887 + }, + { + "epoch": 0.59, + "learning_rate": 7.679512291307207e-06, + "loss": 0.4741, + "step": 6888 + }, + { + "epoch": 0.59, + "learning_rate": 7.6768261630375e-06, + "loss": 0.4323, + "step": 6889 + }, + { + "epoch": 0.59, + "learning_rate": 7.674140211942732e-06, + "loss": 0.4686, + "step": 6890 + }, + { + "epoch": 0.59, + "learning_rate": 7.671454438227739e-06, + "loss": 0.491, + "step": 6891 + }, + { + "epoch": 0.59, + "learning_rate": 7.668768842097353e-06, + "loss": 0.4935, + "step": 6892 + }, + { + "epoch": 0.59, + "learning_rate": 7.666083423756387e-06, + "loss": 0.4906, + "step": 6893 + }, + { + "epoch": 0.59, + "learning_rate": 7.663398183409645e-06, + "loss": 0.4721, + "step": 6894 + }, + { + "epoch": 0.59, + "learning_rate": 7.660713121261911e-06, + "loss": 0.4881, + "step": 6895 + }, + { + "epoch": 0.59, + "learning_rate": 7.658028237517957e-06, + "loss": 0.4548, + "step": 6896 + }, + { + "epoch": 0.59, + "learning_rate": 7.655343532382552e-06, + "loss": 0.4706, + "step": 6897 + }, + { + "epoch": 0.59, + "learning_rate": 7.652659006060436e-06, + "loss": 0.4598, + "step": 6898 + }, + { + "epoch": 0.59, + "learning_rate": 7.649974658756346e-06, + "loss": 0.4549, + "step": 6899 + }, + { + "epoch": 0.59, + "learning_rate": 7.647290490674997e-06, + "loss": 0.4681, + "step": 6900 + }, + { + "epoch": 0.59, + "learning_rate": 7.644606502021096e-06, + "loss": 0.4945, + "step": 6901 + }, + { + "epoch": 0.59, + "learning_rate": 7.64192269299934e-06, + "loss": 0.4756, + "step": 6902 + }, + { + "epoch": 0.59, + "learning_rate": 7.639239063814405e-06, + "loss": 0.4737, + "step": 6903 + }, + { + "epoch": 0.59, + "learning_rate": 7.636555614670953e-06, + "loss": 0.4772, + "step": 6904 + }, + { + "epoch": 0.59, + "learning_rate": 7.633872345773635e-06, + "loss": 0.4605, + "step": 6905 + }, + { + "epoch": 0.59, + "learning_rate": 7.631189257327092e-06, + "loss": 0.4439, + "step": 6906 + }, + { + "epoch": 0.59, + "learning_rate": 7.6285063495359465e-06, + "loss": 0.4784, + "step": 6907 + }, + { + "epoch": 0.59, + "learning_rate": 7.625823622604809e-06, + "loss": 0.4489, + "step": 6908 + }, + { + "epoch": 0.59, + "learning_rate": 7.623141076738271e-06, + "loss": 0.479, + "step": 6909 + }, + { + "epoch": 0.59, + "learning_rate": 7.620458712140916e-06, + "loss": 0.4775, + "step": 6910 + }, + { + "epoch": 0.59, + "learning_rate": 7.617776529017318e-06, + "loss": 0.4953, + "step": 6911 + }, + { + "epoch": 0.59, + "learning_rate": 7.615094527572027e-06, + "loss": 0.4493, + "step": 6912 + }, + { + "epoch": 0.59, + "learning_rate": 7.612412708009583e-06, + "loss": 0.4893, + "step": 6913 + }, + { + "epoch": 0.59, + "learning_rate": 7.6097310705345096e-06, + "loss": 0.4949, + "step": 6914 + }, + { + "epoch": 0.59, + "learning_rate": 7.607049615351329e-06, + "loss": 0.4539, + "step": 6915 + }, + { + "epoch": 0.59, + "learning_rate": 7.604368342664533e-06, + "loss": 0.475, + "step": 6916 + }, + { + "epoch": 0.59, + "learning_rate": 7.601687252678611e-06, + "loss": 0.469, + "step": 6917 + }, + { + "epoch": 0.59, + "learning_rate": 7.59900634559803e-06, + "loss": 0.4852, + "step": 6918 + }, + { + "epoch": 0.59, + "learning_rate": 7.596325621627247e-06, + "loss": 0.457, + "step": 6919 + }, + { + "epoch": 0.59, + "learning_rate": 7.5936450809707096e-06, + "loss": 0.5128, + "step": 6920 + }, + { + "epoch": 0.59, + "learning_rate": 7.590964723832846e-06, + "loss": 0.4803, + "step": 6921 + }, + { + "epoch": 0.59, + "learning_rate": 7.588284550418068e-06, + "loss": 0.4532, + "step": 6922 + }, + { + "epoch": 0.59, + "learning_rate": 7.58560456093078e-06, + "loss": 0.4716, + "step": 6923 + }, + { + "epoch": 0.59, + "learning_rate": 7.582924755575365e-06, + "loss": 0.4659, + "step": 6924 + }, + { + "epoch": 0.59, + "learning_rate": 7.5802451345562e-06, + "loss": 0.4564, + "step": 6925 + }, + { + "epoch": 0.59, + "learning_rate": 7.577565698077646e-06, + "loss": 0.473, + "step": 6926 + }, + { + "epoch": 0.59, + "learning_rate": 7.574886446344043e-06, + "loss": 0.4762, + "step": 6927 + }, + { + "epoch": 0.59, + "learning_rate": 7.572207379559722e-06, + "loss": 0.4768, + "step": 6928 + }, + { + "epoch": 0.59, + "learning_rate": 7.569528497929005e-06, + "loss": 0.498, + "step": 6929 + }, + { + "epoch": 0.59, + "learning_rate": 7.566849801656193e-06, + "loss": 0.4768, + "step": 6930 + }, + { + "epoch": 0.59, + "learning_rate": 7.564171290945571e-06, + "loss": 0.4731, + "step": 6931 + }, + { + "epoch": 0.59, + "learning_rate": 7.561492966001418e-06, + "loss": 0.4771, + "step": 6932 + }, + { + "epoch": 0.59, + "learning_rate": 7.558814827027987e-06, + "loss": 0.492, + "step": 6933 + }, + { + "epoch": 0.59, + "learning_rate": 7.556136874229532e-06, + "loss": 0.459, + "step": 6934 + }, + { + "epoch": 0.59, + "learning_rate": 7.5534591078102825e-06, + "loss": 0.4651, + "step": 6935 + }, + { + "epoch": 0.59, + "learning_rate": 7.550781527974455e-06, + "loss": 0.4632, + "step": 6936 + }, + { + "epoch": 0.59, + "learning_rate": 7.54810413492625e-06, + "loss": 0.4959, + "step": 6937 + }, + { + "epoch": 0.59, + "learning_rate": 7.545426928869863e-06, + "loss": 0.4589, + "step": 6938 + }, + { + "epoch": 0.59, + "learning_rate": 7.542749910009468e-06, + "loss": 0.4891, + "step": 6939 + }, + { + "epoch": 0.59, + "learning_rate": 7.540073078549221e-06, + "loss": 0.4659, + "step": 6940 + }, + { + "epoch": 0.59, + "learning_rate": 7.537396434693274e-06, + "loss": 0.458, + "step": 6941 + }, + { + "epoch": 0.59, + "learning_rate": 7.53471997864575e-06, + "loss": 0.4593, + "step": 6942 + }, + { + "epoch": 0.59, + "learning_rate": 7.5320437106107756e-06, + "loss": 0.4572, + "step": 6943 + }, + { + "epoch": 0.59, + "learning_rate": 7.5293676307924535e-06, + "loss": 0.4709, + "step": 6944 + }, + { + "epoch": 0.59, + "learning_rate": 7.526691739394868e-06, + "loss": 0.4619, + "step": 6945 + }, + { + "epoch": 0.59, + "learning_rate": 7.524016036622094e-06, + "loss": 0.4662, + "step": 6946 + }, + { + "epoch": 0.59, + "learning_rate": 7.521340522678199e-06, + "loss": 0.46, + "step": 6947 + }, + { + "epoch": 0.59, + "learning_rate": 7.518665197767223e-06, + "loss": 0.4735, + "step": 6948 + }, + { + "epoch": 0.59, + "learning_rate": 7.515990062093196e-06, + "loss": 0.4659, + "step": 6949 + }, + { + "epoch": 0.59, + "learning_rate": 7.51331511586014e-06, + "loss": 0.4698, + "step": 6950 + }, + { + "epoch": 0.59, + "learning_rate": 7.51064035927205e-06, + "loss": 0.4604, + "step": 6951 + }, + { + "epoch": 0.59, + "learning_rate": 7.507965792532922e-06, + "loss": 0.477, + "step": 6952 + }, + { + "epoch": 0.59, + "learning_rate": 7.505291415846728e-06, + "loss": 0.4657, + "step": 6953 + }, + { + "epoch": 0.59, + "learning_rate": 7.5026172294174234e-06, + "loss": 0.4592, + "step": 6954 + }, + { + "epoch": 0.59, + "learning_rate": 7.499943233448958e-06, + "loss": 0.4723, + "step": 6955 + }, + { + "epoch": 0.59, + "learning_rate": 7.497269428145255e-06, + "loss": 0.4477, + "step": 6956 + }, + { + "epoch": 0.59, + "learning_rate": 7.494595813710237e-06, + "loss": 0.473, + "step": 6957 + }, + { + "epoch": 0.59, + "learning_rate": 7.491922390347801e-06, + "loss": 0.4571, + "step": 6958 + }, + { + "epoch": 0.59, + "learning_rate": 7.489249158261836e-06, + "loss": 0.4726, + "step": 6959 + }, + { + "epoch": 0.59, + "learning_rate": 7.4865761176562075e-06, + "loss": 0.5043, + "step": 6960 + }, + { + "epoch": 0.59, + "learning_rate": 7.48390326873478e-06, + "loss": 0.4801, + "step": 6961 + }, + { + "epoch": 0.59, + "learning_rate": 7.4812306117013965e-06, + "loss": 0.4768, + "step": 6962 + }, + { + "epoch": 0.59, + "learning_rate": 7.47855814675988e-06, + "loss": 0.4697, + "step": 6963 + }, + { + "epoch": 0.59, + "learning_rate": 7.475885874114047e-06, + "loss": 0.4624, + "step": 6964 + }, + { + "epoch": 0.59, + "learning_rate": 7.473213793967692e-06, + "loss": 0.4642, + "step": 6965 + }, + { + "epoch": 0.59, + "learning_rate": 7.470541906524603e-06, + "loss": 0.4858, + "step": 6966 + }, + { + "epoch": 0.59, + "learning_rate": 7.467870211988551e-06, + "loss": 0.4619, + "step": 6967 + }, + { + "epoch": 0.59, + "learning_rate": 7.465198710563289e-06, + "loss": 0.4783, + "step": 6968 + }, + { + "epoch": 0.59, + "learning_rate": 7.4625274024525504e-06, + "loss": 0.4686, + "step": 6969 + }, + { + "epoch": 0.59, + "learning_rate": 7.459856287860068e-06, + "loss": 0.4775, + "step": 6970 + }, + { + "epoch": 0.59, + "learning_rate": 7.457185366989552e-06, + "loss": 0.462, + "step": 6971 + }, + { + "epoch": 0.59, + "learning_rate": 7.454514640044693e-06, + "loss": 0.4654, + "step": 6972 + }, + { + "epoch": 0.59, + "learning_rate": 7.451844107229178e-06, + "loss": 0.4869, + "step": 6973 + }, + { + "epoch": 0.59, + "learning_rate": 7.449173768746665e-06, + "loss": 0.4671, + "step": 6974 + }, + { + "epoch": 0.59, + "learning_rate": 7.446503624800811e-06, + "loss": 0.4952, + "step": 6975 + }, + { + "epoch": 0.59, + "learning_rate": 7.443833675595254e-06, + "loss": 0.475, + "step": 6976 + }, + { + "epoch": 0.59, + "learning_rate": 7.441163921333614e-06, + "loss": 0.46, + "step": 6977 + }, + { + "epoch": 0.59, + "learning_rate": 7.438494362219491e-06, + "loss": 0.4635, + "step": 6978 + }, + { + "epoch": 0.6, + "learning_rate": 7.4358249984564824e-06, + "loss": 0.4804, + "step": 6979 + }, + { + "epoch": 0.6, + "learning_rate": 7.4331558302481674e-06, + "loss": 0.4635, + "step": 6980 + }, + { + "epoch": 0.6, + "learning_rate": 7.430486857798104e-06, + "loss": 0.4668, + "step": 6981 + }, + { + "epoch": 0.6, + "learning_rate": 7.427818081309841e-06, + "loss": 0.5148, + "step": 6982 + }, + { + "epoch": 0.6, + "learning_rate": 7.425149500986906e-06, + "loss": 0.4784, + "step": 6983 + }, + { + "epoch": 0.6, + "learning_rate": 7.422481117032822e-06, + "loss": 0.4549, + "step": 6984 + }, + { + "epoch": 0.6, + "learning_rate": 7.419812929651091e-06, + "loss": 0.4743, + "step": 6985 + }, + { + "epoch": 0.6, + "learning_rate": 7.417144939045198e-06, + "loss": 0.4695, + "step": 6986 + }, + { + "epoch": 0.6, + "learning_rate": 7.4144771454186125e-06, + "loss": 0.4543, + "step": 6987 + }, + { + "epoch": 0.6, + "learning_rate": 7.411809548974792e-06, + "loss": 0.4601, + "step": 6988 + }, + { + "epoch": 0.6, + "learning_rate": 7.409142149917185e-06, + "loss": 0.468, + "step": 6989 + }, + { + "epoch": 0.6, + "learning_rate": 7.406474948449212e-06, + "loss": 0.4552, + "step": 6990 + }, + { + "epoch": 0.6, + "learning_rate": 7.403807944774291e-06, + "loss": 0.4726, + "step": 6991 + }, + { + "epoch": 0.6, + "learning_rate": 7.401141139095809e-06, + "loss": 0.4744, + "step": 6992 + }, + { + "epoch": 0.6, + "learning_rate": 7.398474531617155e-06, + "loss": 0.4529, + "step": 6993 + }, + { + "epoch": 0.6, + "learning_rate": 7.395808122541697e-06, + "loss": 0.5021, + "step": 6994 + }, + { + "epoch": 0.6, + "learning_rate": 7.393141912072783e-06, + "loss": 0.4773, + "step": 6995 + }, + { + "epoch": 0.6, + "learning_rate": 7.390475900413749e-06, + "loss": 0.4613, + "step": 6996 + }, + { + "epoch": 0.6, + "learning_rate": 7.387810087767916e-06, + "loss": 0.4757, + "step": 6997 + }, + { + "epoch": 0.6, + "learning_rate": 7.385144474338595e-06, + "loss": 0.4684, + "step": 6998 + }, + { + "epoch": 0.6, + "learning_rate": 7.38247906032907e-06, + "loss": 0.4837, + "step": 6999 + }, + { + "epoch": 0.6, + "learning_rate": 7.3798138459426225e-06, + "loss": 0.5051, + "step": 7000 + }, + { + "epoch": 0.6, + "learning_rate": 7.3771488313825055e-06, + "loss": 0.5016, + "step": 7001 + }, + { + "epoch": 0.6, + "learning_rate": 7.37448401685197e-06, + "loss": 0.472, + "step": 7002 + }, + { + "epoch": 0.6, + "learning_rate": 7.371819402554248e-06, + "loss": 0.4673, + "step": 7003 + }, + { + "epoch": 0.6, + "learning_rate": 7.3691549886925505e-06, + "loss": 0.4543, + "step": 7004 + }, + { + "epoch": 0.6, + "learning_rate": 7.366490775470074e-06, + "loss": 0.4724, + "step": 7005 + }, + { + "epoch": 0.6, + "learning_rate": 7.363826763090005e-06, + "loss": 0.464, + "step": 7006 + }, + { + "epoch": 0.6, + "learning_rate": 7.361162951755516e-06, + "loss": 0.4667, + "step": 7007 + }, + { + "epoch": 0.6, + "learning_rate": 7.358499341669756e-06, + "loss": 0.4725, + "step": 7008 + }, + { + "epoch": 0.6, + "learning_rate": 7.355835933035864e-06, + "loss": 0.4735, + "step": 7009 + }, + { + "epoch": 0.6, + "learning_rate": 7.353172726056963e-06, + "loss": 0.4715, + "step": 7010 + }, + { + "epoch": 0.6, + "learning_rate": 7.350509720936157e-06, + "loss": 0.4585, + "step": 7011 + }, + { + "epoch": 0.6, + "learning_rate": 7.3478469178765444e-06, + "loss": 0.4734, + "step": 7012 + }, + { + "epoch": 0.6, + "learning_rate": 7.3451843170812e-06, + "loss": 0.4667, + "step": 7013 + }, + { + "epoch": 0.6, + "learning_rate": 7.3425219187531805e-06, + "loss": 0.4747, + "step": 7014 + }, + { + "epoch": 0.6, + "learning_rate": 7.33985972309553e-06, + "loss": 0.4721, + "step": 7015 + }, + { + "epoch": 0.6, + "learning_rate": 7.3371977303112895e-06, + "loss": 0.4603, + "step": 7016 + }, + { + "epoch": 0.6, + "learning_rate": 7.3345359406034646e-06, + "loss": 0.4722, + "step": 7017 + }, + { + "epoch": 0.6, + "learning_rate": 7.331874354175057e-06, + "loss": 0.4826, + "step": 7018 + }, + { + "epoch": 0.6, + "learning_rate": 7.329212971229049e-06, + "loss": 0.4771, + "step": 7019 + }, + { + "epoch": 0.6, + "learning_rate": 7.326551791968408e-06, + "loss": 0.4637, + "step": 7020 + }, + { + "epoch": 0.6, + "learning_rate": 7.323890816596094e-06, + "loss": 0.467, + "step": 7021 + }, + { + "epoch": 0.6, + "learning_rate": 7.321230045315035e-06, + "loss": 0.4785, + "step": 7022 + }, + { + "epoch": 0.6, + "learning_rate": 7.31856947832816e-06, + "loss": 0.4739, + "step": 7023 + }, + { + "epoch": 0.6, + "learning_rate": 7.315909115838367e-06, + "loss": 0.4669, + "step": 7024 + }, + { + "epoch": 0.6, + "learning_rate": 7.313248958048553e-06, + "loss": 0.4623, + "step": 7025 + }, + { + "epoch": 0.6, + "learning_rate": 7.310589005161589e-06, + "loss": 0.4692, + "step": 7026 + }, + { + "epoch": 0.6, + "learning_rate": 7.307929257380337e-06, + "loss": 0.4864, + "step": 7027 + }, + { + "epoch": 0.6, + "learning_rate": 7.305269714907639e-06, + "loss": 0.4838, + "step": 7028 + }, + { + "epoch": 0.6, + "learning_rate": 7.302610377946319e-06, + "loss": 0.4516, + "step": 7029 + }, + { + "epoch": 0.6, + "learning_rate": 7.299951246699198e-06, + "loss": 0.4778, + "step": 7030 + }, + { + "epoch": 0.6, + "learning_rate": 7.297292321369062e-06, + "loss": 0.485, + "step": 7031 + }, + { + "epoch": 0.6, + "learning_rate": 7.294633602158703e-06, + "loss": 0.4598, + "step": 7032 + }, + { + "epoch": 0.6, + "learning_rate": 7.291975089270877e-06, + "loss": 0.4772, + "step": 7033 + }, + { + "epoch": 0.6, + "learning_rate": 7.289316782908334e-06, + "loss": 0.4718, + "step": 7034 + }, + { + "epoch": 0.6, + "learning_rate": 7.286658683273813e-06, + "loss": 0.4615, + "step": 7035 + }, + { + "epoch": 0.6, + "learning_rate": 7.284000790570029e-06, + "loss": 0.4815, + "step": 7036 + }, + { + "epoch": 0.6, + "learning_rate": 7.2813431049996816e-06, + "loss": 0.458, + "step": 7037 + }, + { + "epoch": 0.6, + "learning_rate": 7.278685626765458e-06, + "loss": 0.4624, + "step": 7038 + }, + { + "epoch": 0.6, + "learning_rate": 7.276028356070033e-06, + "loss": 0.4697, + "step": 7039 + }, + { + "epoch": 0.6, + "learning_rate": 7.273371293116056e-06, + "loss": 0.4718, + "step": 7040 + }, + { + "epoch": 0.6, + "learning_rate": 7.2707144381061686e-06, + "loss": 0.482, + "step": 7041 + }, + { + "epoch": 0.6, + "learning_rate": 7.268057791242994e-06, + "loss": 0.4633, + "step": 7042 + }, + { + "epoch": 0.6, + "learning_rate": 7.265401352729133e-06, + "loss": 0.463, + "step": 7043 + }, + { + "epoch": 0.6, + "learning_rate": 7.262745122767183e-06, + "loss": 0.482, + "step": 7044 + }, + { + "epoch": 0.6, + "learning_rate": 7.2600891015597206e-06, + "loss": 0.4727, + "step": 7045 + }, + { + "epoch": 0.6, + "learning_rate": 7.2574332893093e-06, + "loss": 0.4587, + "step": 7046 + }, + { + "epoch": 0.6, + "learning_rate": 7.2547776862184635e-06, + "loss": 0.4865, + "step": 7047 + }, + { + "epoch": 0.6, + "learning_rate": 7.252122292489747e-06, + "loss": 0.4537, + "step": 7048 + }, + { + "epoch": 0.6, + "learning_rate": 7.249467108325654e-06, + "loss": 0.4619, + "step": 7049 + }, + { + "epoch": 0.6, + "learning_rate": 7.246812133928685e-06, + "loss": 0.4715, + "step": 7050 + }, + { + "epoch": 0.6, + "learning_rate": 7.244157369501317e-06, + "loss": 0.4706, + "step": 7051 + }, + { + "epoch": 0.6, + "learning_rate": 7.241502815246009e-06, + "loss": 0.4447, + "step": 7052 + }, + { + "epoch": 0.6, + "learning_rate": 7.238848471365214e-06, + "loss": 0.4701, + "step": 7053 + }, + { + "epoch": 0.6, + "learning_rate": 7.236194338061364e-06, + "loss": 0.4722, + "step": 7054 + }, + { + "epoch": 0.6, + "learning_rate": 7.233540415536871e-06, + "loss": 0.459, + "step": 7055 + }, + { + "epoch": 0.6, + "learning_rate": 7.2308867039941366e-06, + "loss": 0.4838, + "step": 7056 + }, + { + "epoch": 0.6, + "learning_rate": 7.22823320363554e-06, + "loss": 0.4665, + "step": 7057 + }, + { + "epoch": 0.6, + "learning_rate": 7.225579914663452e-06, + "loss": 0.4713, + "step": 7058 + }, + { + "epoch": 0.6, + "learning_rate": 7.222926837280225e-06, + "loss": 0.4752, + "step": 7059 + }, + { + "epoch": 0.6, + "learning_rate": 7.220273971688192e-06, + "loss": 0.4613, + "step": 7060 + }, + { + "epoch": 0.6, + "learning_rate": 7.217621318089666e-06, + "loss": 0.4592, + "step": 7061 + }, + { + "epoch": 0.6, + "learning_rate": 7.214968876686956e-06, + "loss": 0.4633, + "step": 7062 + }, + { + "epoch": 0.6, + "learning_rate": 7.212316647682351e-06, + "loss": 0.4895, + "step": 7063 + }, + { + "epoch": 0.6, + "learning_rate": 7.209664631278113e-06, + "loss": 0.4762, + "step": 7064 + }, + { + "epoch": 0.6, + "learning_rate": 7.2070128276765005e-06, + "loss": 0.4768, + "step": 7065 + }, + { + "epoch": 0.6, + "learning_rate": 7.204361237079746e-06, + "loss": 0.4805, + "step": 7066 + }, + { + "epoch": 0.6, + "learning_rate": 7.201709859690081e-06, + "loss": 0.4902, + "step": 7067 + }, + { + "epoch": 0.6, + "learning_rate": 7.199058695709702e-06, + "loss": 0.4729, + "step": 7068 + }, + { + "epoch": 0.6, + "learning_rate": 7.1964077453408036e-06, + "loss": 0.4816, + "step": 7069 + }, + { + "epoch": 0.6, + "learning_rate": 7.193757008785549e-06, + "loss": 0.4656, + "step": 7070 + }, + { + "epoch": 0.6, + "learning_rate": 7.191106486246103e-06, + "loss": 0.4756, + "step": 7071 + }, + { + "epoch": 0.6, + "learning_rate": 7.1884561779246055e-06, + "loss": 0.4519, + "step": 7072 + }, + { + "epoch": 0.6, + "learning_rate": 7.185806084023177e-06, + "loss": 0.468, + "step": 7073 + }, + { + "epoch": 0.6, + "learning_rate": 7.183156204743926e-06, + "loss": 0.4603, + "step": 7074 + }, + { + "epoch": 0.6, + "learning_rate": 7.180506540288939e-06, + "loss": 0.4686, + "step": 7075 + }, + { + "epoch": 0.6, + "learning_rate": 7.177857090860296e-06, + "loss": 0.4932, + "step": 7076 + }, + { + "epoch": 0.6, + "learning_rate": 7.1752078566600556e-06, + "loss": 0.4775, + "step": 7077 + }, + { + "epoch": 0.6, + "learning_rate": 7.172558837890256e-06, + "loss": 0.4488, + "step": 7078 + }, + { + "epoch": 0.6, + "learning_rate": 7.16991003475292e-06, + "loss": 0.4812, + "step": 7079 + }, + { + "epoch": 0.6, + "learning_rate": 7.167261447450065e-06, + "loss": 0.4619, + "step": 7080 + }, + { + "epoch": 0.6, + "learning_rate": 7.164613076183678e-06, + "loss": 0.4535, + "step": 7081 + }, + { + "epoch": 0.6, + "learning_rate": 7.161964921155733e-06, + "loss": 0.462, + "step": 7082 + }, + { + "epoch": 0.6, + "learning_rate": 7.159316982568194e-06, + "loss": 0.4651, + "step": 7083 + }, + { + "epoch": 0.6, + "learning_rate": 7.156669260622997e-06, + "loss": 0.4614, + "step": 7084 + }, + { + "epoch": 0.6, + "learning_rate": 7.154021755522076e-06, + "loss": 0.4506, + "step": 7085 + }, + { + "epoch": 0.6, + "learning_rate": 7.151374467467338e-06, + "loss": 0.4623, + "step": 7086 + }, + { + "epoch": 0.6, + "learning_rate": 7.148727396660675e-06, + "loss": 0.4752, + "step": 7087 + }, + { + "epoch": 0.6, + "learning_rate": 7.146080543303966e-06, + "loss": 0.4874, + "step": 7088 + }, + { + "epoch": 0.6, + "learning_rate": 7.143433907599064e-06, + "loss": 0.4771, + "step": 7089 + }, + { + "epoch": 0.6, + "learning_rate": 7.140787489747824e-06, + "loss": 0.4533, + "step": 7090 + }, + { + "epoch": 0.6, + "learning_rate": 7.1381412899520655e-06, + "loss": 0.467, + "step": 7091 + }, + { + "epoch": 0.6, + "learning_rate": 7.1354953084136e-06, + "loss": 0.4473, + "step": 7092 + }, + { + "epoch": 0.6, + "learning_rate": 7.132849545334218e-06, + "loss": 0.4646, + "step": 7093 + }, + { + "epoch": 0.6, + "learning_rate": 7.130204000915701e-06, + "loss": 0.4741, + "step": 7094 + }, + { + "epoch": 0.6, + "learning_rate": 7.127558675359811e-06, + "loss": 0.4924, + "step": 7095 + }, + { + "epoch": 0.61, + "learning_rate": 7.124913568868288e-06, + "loss": 0.4614, + "step": 7096 + }, + { + "epoch": 0.61, + "learning_rate": 7.122268681642859e-06, + "loss": 0.4535, + "step": 7097 + }, + { + "epoch": 0.61, + "learning_rate": 7.119624013885231e-06, + "loss": 0.4723, + "step": 7098 + }, + { + "epoch": 0.61, + "learning_rate": 7.116979565797104e-06, + "loss": 0.4675, + "step": 7099 + }, + { + "epoch": 0.61, + "learning_rate": 7.114335337580152e-06, + "loss": 0.4548, + "step": 7100 + }, + { + "epoch": 0.61, + "learning_rate": 7.111691329436034e-06, + "loss": 0.4653, + "step": 7101 + }, + { + "epoch": 0.61, + "learning_rate": 7.109047541566392e-06, + "loss": 0.4659, + "step": 7102 + }, + { + "epoch": 0.61, + "learning_rate": 7.106403974172853e-06, + "loss": 0.4727, + "step": 7103 + }, + { + "epoch": 0.61, + "learning_rate": 7.10376062745703e-06, + "loss": 0.4844, + "step": 7104 + }, + { + "epoch": 0.61, + "learning_rate": 7.101117501620514e-06, + "loss": 0.4759, + "step": 7105 + }, + { + "epoch": 0.61, + "learning_rate": 7.098474596864878e-06, + "loss": 0.4783, + "step": 7106 + }, + { + "epoch": 0.61, + "learning_rate": 7.09583191339168e-06, + "loss": 0.4677, + "step": 7107 + }, + { + "epoch": 0.61, + "learning_rate": 7.0931894514024695e-06, + "loss": 0.4743, + "step": 7108 + }, + { + "epoch": 0.61, + "learning_rate": 7.090547211098765e-06, + "loss": 0.4795, + "step": 7109 + }, + { + "epoch": 0.61, + "learning_rate": 7.087905192682079e-06, + "loss": 0.4587, + "step": 7110 + }, + { + "epoch": 0.61, + "learning_rate": 7.085263396353897e-06, + "loss": 0.4788, + "step": 7111 + }, + { + "epoch": 0.61, + "learning_rate": 7.082621822315696e-06, + "loss": 0.4742, + "step": 7112 + }, + { + "epoch": 0.61, + "learning_rate": 7.079980470768939e-06, + "loss": 0.4988, + "step": 7113 + }, + { + "epoch": 0.61, + "learning_rate": 7.077339341915059e-06, + "loss": 0.4789, + "step": 7114 + }, + { + "epoch": 0.61, + "learning_rate": 7.074698435955485e-06, + "loss": 0.4631, + "step": 7115 + }, + { + "epoch": 0.61, + "learning_rate": 7.072057753091617e-06, + "loss": 0.4568, + "step": 7116 + }, + { + "epoch": 0.61, + "learning_rate": 7.069417293524854e-06, + "loss": 0.4637, + "step": 7117 + }, + { + "epoch": 0.61, + "learning_rate": 7.06677705745656e-06, + "loss": 0.4798, + "step": 7118 + }, + { + "epoch": 0.61, + "learning_rate": 7.064137045088094e-06, + "loss": 0.4595, + "step": 7119 + }, + { + "epoch": 0.61, + "learning_rate": 7.061497256620793e-06, + "loss": 0.4758, + "step": 7120 + }, + { + "epoch": 0.61, + "learning_rate": 7.058857692255977e-06, + "loss": 0.4923, + "step": 7121 + }, + { + "epoch": 0.61, + "learning_rate": 7.0562183521949565e-06, + "loss": 0.4658, + "step": 7122 + }, + { + "epoch": 0.61, + "learning_rate": 7.053579236639012e-06, + "loss": 0.4598, + "step": 7123 + }, + { + "epoch": 0.61, + "learning_rate": 7.0509403457894184e-06, + "loss": 0.4951, + "step": 7124 + }, + { + "epoch": 0.61, + "learning_rate": 7.0483016798474215e-06, + "loss": 0.4683, + "step": 7125 + }, + { + "epoch": 0.61, + "learning_rate": 7.045663239014265e-06, + "loss": 0.449, + "step": 7126 + }, + { + "epoch": 0.61, + "learning_rate": 7.043025023491163e-06, + "loss": 0.4779, + "step": 7127 + }, + { + "epoch": 0.61, + "learning_rate": 7.040387033479319e-06, + "loss": 0.5029, + "step": 7128 + }, + { + "epoch": 0.61, + "learning_rate": 7.037749269179914e-06, + "loss": 0.4777, + "step": 7129 + }, + { + "epoch": 0.61, + "learning_rate": 7.035111730794115e-06, + "loss": 0.471, + "step": 7130 + }, + { + "epoch": 0.61, + "learning_rate": 7.032474418523076e-06, + "loss": 0.4631, + "step": 7131 + }, + { + "epoch": 0.61, + "learning_rate": 7.029837332567928e-06, + "loss": 0.4786, + "step": 7132 + }, + { + "epoch": 0.61, + "learning_rate": 7.027200473129785e-06, + "loss": 0.4613, + "step": 7133 + }, + { + "epoch": 0.61, + "learning_rate": 7.024563840409745e-06, + "loss": 0.4675, + "step": 7134 + }, + { + "epoch": 0.61, + "learning_rate": 7.0219274346088835e-06, + "loss": 0.452, + "step": 7135 + }, + { + "epoch": 0.61, + "learning_rate": 7.019291255928274e-06, + "loss": 0.4652, + "step": 7136 + }, + { + "epoch": 0.61, + "learning_rate": 7.016655304568957e-06, + "loss": 0.4783, + "step": 7137 + }, + { + "epoch": 0.61, + "learning_rate": 7.01401958073196e-06, + "loss": 0.4883, + "step": 7138 + }, + { + "epoch": 0.61, + "learning_rate": 7.011384084618293e-06, + "loss": 0.4851, + "step": 7139 + }, + { + "epoch": 0.61, + "learning_rate": 7.008748816428958e-06, + "loss": 0.4709, + "step": 7140 + }, + { + "epoch": 0.61, + "learning_rate": 7.006113776364924e-06, + "loss": 0.4606, + "step": 7141 + }, + { + "epoch": 0.61, + "learning_rate": 7.003478964627156e-06, + "loss": 0.475, + "step": 7142 + }, + { + "epoch": 0.61, + "learning_rate": 7.000844381416589e-06, + "loss": 0.4691, + "step": 7143 + }, + { + "epoch": 0.61, + "learning_rate": 6.998210026934148e-06, + "loss": 0.4655, + "step": 7144 + }, + { + "epoch": 0.61, + "learning_rate": 6.9955759013807465e-06, + "loss": 0.4707, + "step": 7145 + }, + { + "epoch": 0.61, + "learning_rate": 6.992942004957271e-06, + "loss": 0.4756, + "step": 7146 + }, + { + "epoch": 0.61, + "learning_rate": 6.99030833786459e-06, + "loss": 0.451, + "step": 7147 + }, + { + "epoch": 0.61, + "learning_rate": 6.987674900303558e-06, + "loss": 0.474, + "step": 7148 + }, + { + "epoch": 0.61, + "learning_rate": 6.985041692475018e-06, + "loss": 0.461, + "step": 7149 + }, + { + "epoch": 0.61, + "learning_rate": 6.9824087145797825e-06, + "loss": 0.4798, + "step": 7150 + }, + { + "epoch": 0.61, + "learning_rate": 6.979775966818661e-06, + "loss": 0.4735, + "step": 7151 + }, + { + "epoch": 0.61, + "learning_rate": 6.9771434493924296e-06, + "loss": 0.441, + "step": 7152 + }, + { + "epoch": 0.61, + "learning_rate": 6.974511162501857e-06, + "loss": 0.4854, + "step": 7153 + }, + { + "epoch": 0.61, + "learning_rate": 6.971879106347699e-06, + "loss": 0.4784, + "step": 7154 + }, + { + "epoch": 0.61, + "learning_rate": 6.969247281130681e-06, + "loss": 0.4662, + "step": 7155 + }, + { + "epoch": 0.61, + "learning_rate": 6.966615687051517e-06, + "loss": 0.4777, + "step": 7156 + }, + { + "epoch": 0.61, + "learning_rate": 6.963984324310903e-06, + "loss": 0.4617, + "step": 7157 + }, + { + "epoch": 0.61, + "learning_rate": 6.961353193109524e-06, + "loss": 0.4737, + "step": 7158 + }, + { + "epoch": 0.61, + "learning_rate": 6.958722293648032e-06, + "loss": 0.4734, + "step": 7159 + }, + { + "epoch": 0.61, + "learning_rate": 6.95609162612708e-06, + "loss": 0.4703, + "step": 7160 + }, + { + "epoch": 0.61, + "learning_rate": 6.953461190747283e-06, + "loss": 0.4659, + "step": 7161 + }, + { + "epoch": 0.61, + "learning_rate": 6.9508309877092566e-06, + "loss": 0.4591, + "step": 7162 + }, + { + "epoch": 0.61, + "learning_rate": 6.948201017213589e-06, + "loss": 0.4782, + "step": 7163 + }, + { + "epoch": 0.61, + "learning_rate": 6.945571279460857e-06, + "loss": 0.474, + "step": 7164 + }, + { + "epoch": 0.61, + "learning_rate": 6.942941774651606e-06, + "loss": 0.4568, + "step": 7165 + }, + { + "epoch": 0.61, + "learning_rate": 6.94031250298638e-06, + "loss": 0.489, + "step": 7166 + }, + { + "epoch": 0.61, + "learning_rate": 6.937683464665694e-06, + "loss": 0.4452, + "step": 7167 + }, + { + "epoch": 0.61, + "learning_rate": 6.935054659890053e-06, + "loss": 0.4686, + "step": 7168 + }, + { + "epoch": 0.61, + "learning_rate": 6.9324260888599405e-06, + "loss": 0.4878, + "step": 7169 + }, + { + "epoch": 0.61, + "learning_rate": 6.92979775177582e-06, + "loss": 0.4582, + "step": 7170 + }, + { + "epoch": 0.61, + "learning_rate": 6.927169648838139e-06, + "loss": 0.4564, + "step": 7171 + }, + { + "epoch": 0.61, + "learning_rate": 6.9245417802473335e-06, + "loss": 0.4756, + "step": 7172 + }, + { + "epoch": 0.61, + "learning_rate": 6.92191414620381e-06, + "loss": 0.4696, + "step": 7173 + }, + { + "epoch": 0.61, + "learning_rate": 6.9192867469079625e-06, + "loss": 0.4593, + "step": 7174 + }, + { + "epoch": 0.61, + "learning_rate": 6.916659582560172e-06, + "loss": 0.4608, + "step": 7175 + }, + { + "epoch": 0.61, + "learning_rate": 6.914032653360792e-06, + "loss": 0.4474, + "step": 7176 + }, + { + "epoch": 0.61, + "learning_rate": 6.911405959510164e-06, + "loss": 0.4753, + "step": 7177 + }, + { + "epoch": 0.61, + "learning_rate": 6.9087795012086165e-06, + "loss": 0.4564, + "step": 7178 + }, + { + "epoch": 0.61, + "learning_rate": 6.9061532786564465e-06, + "loss": 0.4691, + "step": 7179 + }, + { + "epoch": 0.61, + "learning_rate": 6.903527292053942e-06, + "loss": 0.4677, + "step": 7180 + }, + { + "epoch": 0.61, + "learning_rate": 6.900901541601379e-06, + "loss": 0.472, + "step": 7181 + }, + { + "epoch": 0.61, + "learning_rate": 6.898276027499002e-06, + "loss": 0.4776, + "step": 7182 + }, + { + "epoch": 0.61, + "learning_rate": 6.895650749947041e-06, + "loss": 0.472, + "step": 7183 + }, + { + "epoch": 0.61, + "learning_rate": 6.8930257091457175e-06, + "loss": 0.4735, + "step": 7184 + }, + { + "epoch": 0.61, + "learning_rate": 6.89040090529522e-06, + "loss": 0.4534, + "step": 7185 + }, + { + "epoch": 0.61, + "learning_rate": 6.887776338595735e-06, + "loss": 0.4609, + "step": 7186 + }, + { + "epoch": 0.61, + "learning_rate": 6.88515200924742e-06, + "loss": 0.4705, + "step": 7187 + }, + { + "epoch": 0.61, + "learning_rate": 6.882527917450416e-06, + "loss": 0.4499, + "step": 7188 + }, + { + "epoch": 0.61, + "learning_rate": 6.8799040634048496e-06, + "loss": 0.4785, + "step": 7189 + }, + { + "epoch": 0.61, + "learning_rate": 6.877280447310821e-06, + "loss": 0.4729, + "step": 7190 + }, + { + "epoch": 0.61, + "learning_rate": 6.874657069368427e-06, + "loss": 0.4637, + "step": 7191 + }, + { + "epoch": 0.61, + "learning_rate": 6.872033929777731e-06, + "loss": 0.4524, + "step": 7192 + }, + { + "epoch": 0.61, + "learning_rate": 6.869411028738787e-06, + "loss": 0.4669, + "step": 7193 + }, + { + "epoch": 0.61, + "learning_rate": 6.866788366451624e-06, + "loss": 0.4662, + "step": 7194 + }, + { + "epoch": 0.61, + "learning_rate": 6.864165943116265e-06, + "loss": 0.4542, + "step": 7195 + }, + { + "epoch": 0.61, + "learning_rate": 6.861543758932703e-06, + "loss": 0.4613, + "step": 7196 + }, + { + "epoch": 0.61, + "learning_rate": 6.858921814100914e-06, + "loss": 0.4537, + "step": 7197 + }, + { + "epoch": 0.61, + "learning_rate": 6.856300108820865e-06, + "loss": 0.4646, + "step": 7198 + }, + { + "epoch": 0.61, + "learning_rate": 6.85367864329249e-06, + "loss": 0.4552, + "step": 7199 + }, + { + "epoch": 0.61, + "learning_rate": 6.851057417715719e-06, + "loss": 0.4608, + "step": 7200 + }, + { + "epoch": 0.61, + "learning_rate": 6.8484364322904565e-06, + "loss": 0.4525, + "step": 7201 + }, + { + "epoch": 0.61, + "learning_rate": 6.84581568721659e-06, + "loss": 0.4719, + "step": 7202 + }, + { + "epoch": 0.61, + "learning_rate": 6.843195182693982e-06, + "loss": 0.4724, + "step": 7203 + }, + { + "epoch": 0.61, + "learning_rate": 6.8405749189224935e-06, + "loss": 0.4686, + "step": 7204 + }, + { + "epoch": 0.61, + "learning_rate": 6.8379548961019526e-06, + "loss": 0.4788, + "step": 7205 + }, + { + "epoch": 0.61, + "learning_rate": 6.835335114432169e-06, + "loss": 0.4712, + "step": 7206 + }, + { + "epoch": 0.61, + "learning_rate": 6.832715574112946e-06, + "loss": 0.4788, + "step": 7207 + }, + { + "epoch": 0.61, + "learning_rate": 6.8300962753440514e-06, + "loss": 0.45, + "step": 7208 + }, + { + "epoch": 0.61, + "learning_rate": 6.82747721832525e-06, + "loss": 0.4753, + "step": 7209 + }, + { + "epoch": 0.61, + "learning_rate": 6.824858403256284e-06, + "loss": 0.4911, + "step": 7210 + }, + { + "epoch": 0.61, + "learning_rate": 6.8222398303368705e-06, + "loss": 0.4539, + "step": 7211 + }, + { + "epoch": 0.61, + "learning_rate": 6.819621499766713e-06, + "loss": 0.4847, + "step": 7212 + }, + { + "epoch": 0.62, + "learning_rate": 6.8170034117454965e-06, + "loss": 0.4658, + "step": 7213 + }, + { + "epoch": 0.62, + "learning_rate": 6.814385566472892e-06, + "loss": 0.4863, + "step": 7214 + }, + { + "epoch": 0.62, + "learning_rate": 6.811767964148542e-06, + "loss": 0.4729, + "step": 7215 + }, + { + "epoch": 0.62, + "learning_rate": 6.809150604972079e-06, + "loss": 0.47, + "step": 7216 + }, + { + "epoch": 0.62, + "learning_rate": 6.806533489143108e-06, + "loss": 0.4747, + "step": 7217 + }, + { + "epoch": 0.62, + "learning_rate": 6.803916616861228e-06, + "loss": 0.4496, + "step": 7218 + }, + { + "epoch": 0.62, + "learning_rate": 6.801299988326011e-06, + "loss": 0.4874, + "step": 7219 + }, + { + "epoch": 0.62, + "learning_rate": 6.798683603737013e-06, + "loss": 0.465, + "step": 7220 + }, + { + "epoch": 0.62, + "learning_rate": 6.796067463293765e-06, + "loss": 0.4711, + "step": 7221 + }, + { + "epoch": 0.62, + "learning_rate": 6.793451567195785e-06, + "loss": 0.4636, + "step": 7222 + }, + { + "epoch": 0.62, + "learning_rate": 6.7908359156425814e-06, + "loss": 0.4771, + "step": 7223 + }, + { + "epoch": 0.62, + "learning_rate": 6.788220508833627e-06, + "loss": 0.452, + "step": 7224 + }, + { + "epoch": 0.62, + "learning_rate": 6.785605346968387e-06, + "loss": 0.4823, + "step": 7225 + }, + { + "epoch": 0.62, + "learning_rate": 6.782990430246299e-06, + "loss": 0.4773, + "step": 7226 + }, + { + "epoch": 0.62, + "learning_rate": 6.780375758866793e-06, + "loss": 0.4534, + "step": 7227 + }, + { + "epoch": 0.62, + "learning_rate": 6.777761333029274e-06, + "loss": 0.4682, + "step": 7228 + }, + { + "epoch": 0.62, + "learning_rate": 6.77514715293313e-06, + "loss": 0.4712, + "step": 7229 + }, + { + "epoch": 0.62, + "learning_rate": 6.7725332187777244e-06, + "loss": 0.4672, + "step": 7230 + }, + { + "epoch": 0.62, + "learning_rate": 6.769919530762409e-06, + "loss": 0.4559, + "step": 7231 + }, + { + "epoch": 0.62, + "learning_rate": 6.7673060890865184e-06, + "loss": 0.4661, + "step": 7232 + }, + { + "epoch": 0.62, + "learning_rate": 6.764692893949361e-06, + "loss": 0.4826, + "step": 7233 + }, + { + "epoch": 0.62, + "learning_rate": 6.7620799455502305e-06, + "loss": 0.4486, + "step": 7234 + }, + { + "epoch": 0.62, + "learning_rate": 6.759467244088398e-06, + "loss": 0.4908, + "step": 7235 + }, + { + "epoch": 0.62, + "learning_rate": 6.756854789763123e-06, + "loss": 0.4563, + "step": 7236 + }, + { + "epoch": 0.62, + "learning_rate": 6.754242582773646e-06, + "loss": 0.4646, + "step": 7237 + }, + { + "epoch": 0.62, + "learning_rate": 6.751630623319179e-06, + "loss": 0.472, + "step": 7238 + }, + { + "epoch": 0.62, + "learning_rate": 6.74901891159892e-06, + "loss": 0.4628, + "step": 7239 + }, + { + "epoch": 0.62, + "learning_rate": 6.746407447812049e-06, + "loss": 0.4657, + "step": 7240 + }, + { + "epoch": 0.62, + "learning_rate": 6.743796232157734e-06, + "loss": 0.4669, + "step": 7241 + }, + { + "epoch": 0.62, + "learning_rate": 6.741185264835111e-06, + "loss": 0.4693, + "step": 7242 + }, + { + "epoch": 0.62, + "learning_rate": 6.738574546043306e-06, + "loss": 0.4596, + "step": 7243 + }, + { + "epoch": 0.62, + "learning_rate": 6.7359640759814204e-06, + "loss": 0.4815, + "step": 7244 + }, + { + "epoch": 0.62, + "learning_rate": 6.733353854848539e-06, + "loss": 0.4638, + "step": 7245 + }, + { + "epoch": 0.62, + "learning_rate": 6.730743882843736e-06, + "loss": 0.464, + "step": 7246 + }, + { + "epoch": 0.62, + "learning_rate": 6.728134160166051e-06, + "loss": 0.4748, + "step": 7247 + }, + { + "epoch": 0.62, + "learning_rate": 6.7255246870145144e-06, + "loss": 0.4637, + "step": 7248 + }, + { + "epoch": 0.62, + "learning_rate": 6.7229154635881334e-06, + "loss": 0.5037, + "step": 7249 + }, + { + "epoch": 0.62, + "learning_rate": 6.720306490085904e-06, + "loss": 0.4606, + "step": 7250 + }, + { + "epoch": 0.62, + "learning_rate": 6.717697766706792e-06, + "loss": 0.4594, + "step": 7251 + }, + { + "epoch": 0.62, + "learning_rate": 6.7150892936497525e-06, + "loss": 0.476, + "step": 7252 + }, + { + "epoch": 0.62, + "learning_rate": 6.712481071113717e-06, + "loss": 0.466, + "step": 7253 + }, + { + "epoch": 0.62, + "learning_rate": 6.709873099297597e-06, + "loss": 0.4744, + "step": 7254 + }, + { + "epoch": 0.62, + "learning_rate": 6.7072653784002965e-06, + "loss": 0.4767, + "step": 7255 + }, + { + "epoch": 0.62, + "learning_rate": 6.70465790862068e-06, + "loss": 0.4605, + "step": 7256 + }, + { + "epoch": 0.62, + "learning_rate": 6.702050690157614e-06, + "loss": 0.4643, + "step": 7257 + }, + { + "epoch": 0.62, + "learning_rate": 6.6994437232099245e-06, + "loss": 0.4666, + "step": 7258 + }, + { + "epoch": 0.62, + "learning_rate": 6.696837007976441e-06, + "loss": 0.4503, + "step": 7259 + }, + { + "epoch": 0.62, + "learning_rate": 6.694230544655955e-06, + "loss": 0.465, + "step": 7260 + }, + { + "epoch": 0.62, + "learning_rate": 6.691624333447252e-06, + "loss": 0.4635, + "step": 7261 + }, + { + "epoch": 0.62, + "learning_rate": 6.689018374549086e-06, + "loss": 0.474, + "step": 7262 + }, + { + "epoch": 0.62, + "learning_rate": 6.6864126681602e-06, + "loss": 0.4805, + "step": 7263 + }, + { + "epoch": 0.62, + "learning_rate": 6.683807214479323e-06, + "loss": 0.4749, + "step": 7264 + }, + { + "epoch": 0.62, + "learning_rate": 6.68120201370515e-06, + "loss": 0.4895, + "step": 7265 + }, + { + "epoch": 0.62, + "learning_rate": 6.678597066036368e-06, + "loss": 0.4519, + "step": 7266 + }, + { + "epoch": 0.62, + "learning_rate": 6.675992371671641e-06, + "loss": 0.4648, + "step": 7267 + }, + { + "epoch": 0.62, + "learning_rate": 6.67338793080961e-06, + "loss": 0.4745, + "step": 7268 + }, + { + "epoch": 0.62, + "learning_rate": 6.670783743648903e-06, + "loss": 0.4635, + "step": 7269 + }, + { + "epoch": 0.62, + "learning_rate": 6.668179810388131e-06, + "loss": 0.4641, + "step": 7270 + }, + { + "epoch": 0.62, + "learning_rate": 6.665576131225874e-06, + "loss": 0.4721, + "step": 7271 + }, + { + "epoch": 0.62, + "learning_rate": 6.6629727063607e-06, + "loss": 0.4617, + "step": 7272 + }, + { + "epoch": 0.62, + "learning_rate": 6.660369535991162e-06, + "loss": 0.4745, + "step": 7273 + }, + { + "epoch": 0.62, + "learning_rate": 6.6577666203157845e-06, + "loss": 0.4615, + "step": 7274 + }, + { + "epoch": 0.62, + "learning_rate": 6.655163959533081e-06, + "loss": 0.4699, + "step": 7275 + }, + { + "epoch": 0.62, + "learning_rate": 6.652561553841537e-06, + "loss": 0.4743, + "step": 7276 + }, + { + "epoch": 0.62, + "learning_rate": 6.649959403439621e-06, + "loss": 0.4768, + "step": 7277 + }, + { + "epoch": 0.62, + "learning_rate": 6.647357508525787e-06, + "loss": 0.4641, + "step": 7278 + }, + { + "epoch": 0.62, + "learning_rate": 6.64475586929847e-06, + "loss": 0.48, + "step": 7279 + }, + { + "epoch": 0.62, + "learning_rate": 6.642154485956076e-06, + "loss": 0.4646, + "step": 7280 + }, + { + "epoch": 0.62, + "learning_rate": 6.6395533586969975e-06, + "loss": 0.4739, + "step": 7281 + }, + { + "epoch": 0.62, + "learning_rate": 6.636952487719612e-06, + "loss": 0.4534, + "step": 7282 + }, + { + "epoch": 0.62, + "learning_rate": 6.634351873222269e-06, + "loss": 0.4682, + "step": 7283 + }, + { + "epoch": 0.62, + "learning_rate": 6.6317515154033064e-06, + "loss": 0.4725, + "step": 7284 + }, + { + "epoch": 0.62, + "learning_rate": 6.629151414461033e-06, + "loss": 0.4577, + "step": 7285 + }, + { + "epoch": 0.62, + "learning_rate": 6.6265515705937435e-06, + "loss": 0.4756, + "step": 7286 + }, + { + "epoch": 0.62, + "learning_rate": 6.623951983999717e-06, + "loss": 0.4639, + "step": 7287 + }, + { + "epoch": 0.62, + "learning_rate": 6.621352654877207e-06, + "loss": 0.4744, + "step": 7288 + }, + { + "epoch": 0.62, + "learning_rate": 6.618753583424449e-06, + "loss": 0.4638, + "step": 7289 + }, + { + "epoch": 0.62, + "learning_rate": 6.616154769839655e-06, + "loss": 0.4679, + "step": 7290 + }, + { + "epoch": 0.62, + "learning_rate": 6.613556214321031e-06, + "loss": 0.4565, + "step": 7291 + }, + { + "epoch": 0.62, + "learning_rate": 6.610957917066745e-06, + "loss": 0.485, + "step": 7292 + }, + { + "epoch": 0.62, + "learning_rate": 6.608359878274959e-06, + "loss": 0.482, + "step": 7293 + }, + { + "epoch": 0.62, + "learning_rate": 6.60576209814381e-06, + "loss": 0.468, + "step": 7294 + }, + { + "epoch": 0.62, + "learning_rate": 6.603164576871408e-06, + "loss": 0.4511, + "step": 7295 + }, + { + "epoch": 0.62, + "learning_rate": 6.600567314655859e-06, + "loss": 0.4872, + "step": 7296 + }, + { + "epoch": 0.62, + "learning_rate": 6.597970311695242e-06, + "loss": 0.4707, + "step": 7297 + }, + { + "epoch": 0.62, + "learning_rate": 6.5953735681876096e-06, + "loss": 0.4535, + "step": 7298 + }, + { + "epoch": 0.62, + "learning_rate": 6.5927770843310045e-06, + "loss": 0.4808, + "step": 7299 + }, + { + "epoch": 0.62, + "learning_rate": 6.59018086032344e-06, + "loss": 0.4957, + "step": 7300 + }, + { + "epoch": 0.62, + "learning_rate": 6.587584896362919e-06, + "loss": 0.448, + "step": 7301 + }, + { + "epoch": 0.62, + "learning_rate": 6.584989192647424e-06, + "loss": 0.471, + "step": 7302 + }, + { + "epoch": 0.62, + "learning_rate": 6.582393749374911e-06, + "loss": 0.46, + "step": 7303 + }, + { + "epoch": 0.62, + "learning_rate": 6.579798566743314e-06, + "loss": 0.4669, + "step": 7304 + }, + { + "epoch": 0.62, + "learning_rate": 6.5772036449505586e-06, + "loss": 0.4612, + "step": 7305 + }, + { + "epoch": 0.62, + "learning_rate": 6.574608984194546e-06, + "loss": 0.4498, + "step": 7306 + }, + { + "epoch": 0.62, + "learning_rate": 6.57201458467315e-06, + "loss": 0.4703, + "step": 7307 + }, + { + "epoch": 0.62, + "learning_rate": 6.569420446584235e-06, + "loss": 0.4439, + "step": 7308 + }, + { + "epoch": 0.62, + "learning_rate": 6.566826570125635e-06, + "loss": 0.48, + "step": 7309 + }, + { + "epoch": 0.62, + "learning_rate": 6.5642329554951754e-06, + "loss": 0.4747, + "step": 7310 + }, + { + "epoch": 0.62, + "learning_rate": 6.561639602890658e-06, + "loss": 0.4604, + "step": 7311 + }, + { + "epoch": 0.62, + "learning_rate": 6.559046512509859e-06, + "loss": 0.476, + "step": 7312 + }, + { + "epoch": 0.62, + "learning_rate": 6.556453684550534e-06, + "loss": 0.4784, + "step": 7313 + }, + { + "epoch": 0.62, + "learning_rate": 6.553861119210429e-06, + "loss": 0.4501, + "step": 7314 + }, + { + "epoch": 0.62, + "learning_rate": 6.551268816687265e-06, + "loss": 0.4541, + "step": 7315 + }, + { + "epoch": 0.62, + "learning_rate": 6.548676777178737e-06, + "loss": 0.4522, + "step": 7316 + }, + { + "epoch": 0.62, + "learning_rate": 6.546085000882528e-06, + "loss": 0.4658, + "step": 7317 + }, + { + "epoch": 0.62, + "learning_rate": 6.543493487996293e-06, + "loss": 0.464, + "step": 7318 + }, + { + "epoch": 0.62, + "learning_rate": 6.540902238717677e-06, + "loss": 0.4794, + "step": 7319 + }, + { + "epoch": 0.62, + "learning_rate": 6.5383112532443e-06, + "loss": 0.4678, + "step": 7320 + }, + { + "epoch": 0.62, + "learning_rate": 6.535720531773757e-06, + "loss": 0.4558, + "step": 7321 + }, + { + "epoch": 0.62, + "learning_rate": 6.533130074503631e-06, + "loss": 0.4602, + "step": 7322 + }, + { + "epoch": 0.62, + "learning_rate": 6.530539881631475e-06, + "loss": 0.4866, + "step": 7323 + }, + { + "epoch": 0.62, + "learning_rate": 6.527949953354835e-06, + "loss": 0.4976, + "step": 7324 + }, + { + "epoch": 0.62, + "learning_rate": 6.525360289871227e-06, + "loss": 0.4822, + "step": 7325 + }, + { + "epoch": 0.62, + "learning_rate": 6.522770891378151e-06, + "loss": 0.4624, + "step": 7326 + }, + { + "epoch": 0.62, + "learning_rate": 6.5201817580730786e-06, + "loss": 0.4796, + "step": 7327 + }, + { + "epoch": 0.62, + "learning_rate": 6.517592890153477e-06, + "loss": 0.4564, + "step": 7328 + }, + { + "epoch": 0.62, + "learning_rate": 6.515004287816781e-06, + "loss": 0.4655, + "step": 7329 + }, + { + "epoch": 0.62, + "learning_rate": 6.5124159512604055e-06, + "loss": 0.4818, + "step": 7330 + }, + { + "epoch": 0.63, + "learning_rate": 6.509827880681752e-06, + "loss": 0.4512, + "step": 7331 + }, + { + "epoch": 0.63, + "learning_rate": 6.507240076278192e-06, + "loss": 0.4831, + "step": 7332 + }, + { + "epoch": 0.63, + "learning_rate": 6.504652538247088e-06, + "loss": 0.4669, + "step": 7333 + }, + { + "epoch": 0.63, + "learning_rate": 6.502065266785773e-06, + "loss": 0.4661, + "step": 7334 + }, + { + "epoch": 0.63, + "learning_rate": 6.499478262091566e-06, + "loss": 0.454, + "step": 7335 + }, + { + "epoch": 0.63, + "learning_rate": 6.496891524361757e-06, + "loss": 0.4668, + "step": 7336 + }, + { + "epoch": 0.63, + "learning_rate": 6.494305053793628e-06, + "loss": 0.4545, + "step": 7337 + }, + { + "epoch": 0.63, + "learning_rate": 6.491718850584433e-06, + "loss": 0.4543, + "step": 7338 + }, + { + "epoch": 0.63, + "learning_rate": 6.489132914931403e-06, + "loss": 0.4686, + "step": 7339 + }, + { + "epoch": 0.63, + "learning_rate": 6.486547247031756e-06, + "loss": 0.4543, + "step": 7340 + }, + { + "epoch": 0.63, + "learning_rate": 6.48396184708268e-06, + "loss": 0.4571, + "step": 7341 + }, + { + "epoch": 0.63, + "learning_rate": 6.481376715281358e-06, + "loss": 0.4633, + "step": 7342 + }, + { + "epoch": 0.63, + "learning_rate": 6.478791851824935e-06, + "loss": 0.4608, + "step": 7343 + }, + { + "epoch": 0.63, + "learning_rate": 6.476207256910547e-06, + "loss": 0.4546, + "step": 7344 + }, + { + "epoch": 0.63, + "learning_rate": 6.4736229307353035e-06, + "loss": 0.4859, + "step": 7345 + }, + { + "epoch": 0.63, + "learning_rate": 6.4710388734962955e-06, + "loss": 0.4675, + "step": 7346 + }, + { + "epoch": 0.63, + "learning_rate": 6.468455085390601e-06, + "loss": 0.4662, + "step": 7347 + }, + { + "epoch": 0.63, + "learning_rate": 6.4658715666152625e-06, + "loss": 0.4873, + "step": 7348 + }, + { + "epoch": 0.63, + "learning_rate": 6.4632883173673145e-06, + "loss": 0.4568, + "step": 7349 + }, + { + "epoch": 0.63, + "learning_rate": 6.460705337843761e-06, + "loss": 0.481, + "step": 7350 + }, + { + "epoch": 0.63, + "learning_rate": 6.458122628241599e-06, + "loss": 0.4832, + "step": 7351 + }, + { + "epoch": 0.63, + "learning_rate": 6.4555401887577895e-06, + "loss": 0.4839, + "step": 7352 + }, + { + "epoch": 0.63, + "learning_rate": 6.452958019589286e-06, + "loss": 0.4547, + "step": 7353 + }, + { + "epoch": 0.63, + "learning_rate": 6.450376120933008e-06, + "loss": 0.4694, + "step": 7354 + }, + { + "epoch": 0.63, + "learning_rate": 6.447794492985867e-06, + "loss": 0.4642, + "step": 7355 + }, + { + "epoch": 0.63, + "learning_rate": 6.445213135944751e-06, + "loss": 0.4541, + "step": 7356 + }, + { + "epoch": 0.63, + "learning_rate": 6.4426320500065196e-06, + "loss": 0.4753, + "step": 7357 + }, + { + "epoch": 0.63, + "learning_rate": 6.440051235368022e-06, + "loss": 0.4713, + "step": 7358 + }, + { + "epoch": 0.63, + "learning_rate": 6.437470692226075e-06, + "loss": 0.4655, + "step": 7359 + }, + { + "epoch": 0.63, + "learning_rate": 6.434890420777491e-06, + "loss": 0.4501, + "step": 7360 + }, + { + "epoch": 0.63, + "learning_rate": 6.432310421219046e-06, + "loss": 0.4634, + "step": 7361 + }, + { + "epoch": 0.63, + "learning_rate": 6.429730693747503e-06, + "loss": 0.4731, + "step": 7362 + }, + { + "epoch": 0.63, + "learning_rate": 6.427151238559602e-06, + "loss": 0.4732, + "step": 7363 + }, + { + "epoch": 0.63, + "learning_rate": 6.424572055852062e-06, + "loss": 0.4837, + "step": 7364 + }, + { + "epoch": 0.63, + "learning_rate": 6.421993145821588e-06, + "loss": 0.4723, + "step": 7365 + }, + { + "epoch": 0.63, + "learning_rate": 6.419414508664851e-06, + "loss": 0.4705, + "step": 7366 + }, + { + "epoch": 0.63, + "learning_rate": 6.416836144578516e-06, + "loss": 0.4588, + "step": 7367 + }, + { + "epoch": 0.63, + "learning_rate": 6.41425805375921e-06, + "loss": 0.4721, + "step": 7368 + }, + { + "epoch": 0.63, + "learning_rate": 6.411680236403559e-06, + "loss": 0.4644, + "step": 7369 + }, + { + "epoch": 0.63, + "learning_rate": 6.409102692708154e-06, + "loss": 0.4564, + "step": 7370 + }, + { + "epoch": 0.63, + "learning_rate": 6.40652542286957e-06, + "loss": 0.4738, + "step": 7371 + }, + { + "epoch": 0.63, + "learning_rate": 6.403948427084356e-06, + "loss": 0.4707, + "step": 7372 + }, + { + "epoch": 0.63, + "learning_rate": 6.401371705549046e-06, + "loss": 0.4666, + "step": 7373 + }, + { + "epoch": 0.63, + "learning_rate": 6.39879525846016e-06, + "loss": 0.4768, + "step": 7374 + }, + { + "epoch": 0.63, + "learning_rate": 6.396219086014179e-06, + "loss": 0.4653, + "step": 7375 + }, + { + "epoch": 0.63, + "learning_rate": 6.393643188407579e-06, + "loss": 0.4499, + "step": 7376 + }, + { + "epoch": 0.63, + "learning_rate": 6.391067565836801e-06, + "loss": 0.47, + "step": 7377 + }, + { + "epoch": 0.63, + "learning_rate": 6.388492218498277e-06, + "loss": 0.4638, + "step": 7378 + }, + { + "epoch": 0.63, + "learning_rate": 6.385917146588419e-06, + "loss": 0.4686, + "step": 7379 + }, + { + "epoch": 0.63, + "learning_rate": 6.3833423503036054e-06, + "loss": 0.4671, + "step": 7380 + }, + { + "epoch": 0.63, + "learning_rate": 6.380767829840202e-06, + "loss": 0.4584, + "step": 7381 + }, + { + "epoch": 0.63, + "learning_rate": 6.378193585394552e-06, + "loss": 0.4632, + "step": 7382 + }, + { + "epoch": 0.63, + "learning_rate": 6.375619617162985e-06, + "loss": 0.4653, + "step": 7383 + }, + { + "epoch": 0.63, + "learning_rate": 6.373045925341794e-06, + "loss": 0.4634, + "step": 7384 + }, + { + "epoch": 0.63, + "learning_rate": 6.370472510127265e-06, + "loss": 0.4686, + "step": 7385 + }, + { + "epoch": 0.63, + "learning_rate": 6.367899371715653e-06, + "loss": 0.4537, + "step": 7386 + }, + { + "epoch": 0.63, + "learning_rate": 6.365326510303196e-06, + "loss": 0.4831, + "step": 7387 + }, + { + "epoch": 0.63, + "learning_rate": 6.362753926086118e-06, + "loss": 0.4752, + "step": 7388 + }, + { + "epoch": 0.63, + "learning_rate": 6.360181619260613e-06, + "loss": 0.4587, + "step": 7389 + }, + { + "epoch": 0.63, + "learning_rate": 6.357609590022849e-06, + "loss": 0.4686, + "step": 7390 + }, + { + "epoch": 0.63, + "learning_rate": 6.355037838568981e-06, + "loss": 0.4697, + "step": 7391 + }, + { + "epoch": 0.63, + "learning_rate": 6.352466365095151e-06, + "loss": 0.4603, + "step": 7392 + }, + { + "epoch": 0.63, + "learning_rate": 6.349895169797462e-06, + "loss": 0.4622, + "step": 7393 + }, + { + "epoch": 0.63, + "learning_rate": 6.3473242528720065e-06, + "loss": 0.4645, + "step": 7394 + }, + { + "epoch": 0.63, + "learning_rate": 6.3447536145148515e-06, + "loss": 0.4425, + "step": 7395 + }, + { + "epoch": 0.63, + "learning_rate": 6.342183254922045e-06, + "loss": 0.4701, + "step": 7396 + }, + { + "epoch": 0.63, + "learning_rate": 6.339613174289618e-06, + "loss": 0.4669, + "step": 7397 + }, + { + "epoch": 0.63, + "learning_rate": 6.337043372813572e-06, + "loss": 0.4684, + "step": 7398 + }, + { + "epoch": 0.63, + "learning_rate": 6.334473850689889e-06, + "loss": 0.4575, + "step": 7399 + }, + { + "epoch": 0.63, + "learning_rate": 6.331904608114534e-06, + "loss": 0.4699, + "step": 7400 + }, + { + "epoch": 0.63, + "learning_rate": 6.3293356452834445e-06, + "loss": 0.4708, + "step": 7401 + }, + { + "epoch": 0.63, + "learning_rate": 6.326766962392544e-06, + "loss": 0.4535, + "step": 7402 + }, + { + "epoch": 0.63, + "learning_rate": 6.324198559637733e-06, + "loss": 0.4785, + "step": 7403 + }, + { + "epoch": 0.63, + "learning_rate": 6.321630437214885e-06, + "loss": 0.4701, + "step": 7404 + }, + { + "epoch": 0.63, + "learning_rate": 6.319062595319853e-06, + "loss": 0.455, + "step": 7405 + }, + { + "epoch": 0.63, + "learning_rate": 6.31649503414848e-06, + "loss": 0.4513, + "step": 7406 + }, + { + "epoch": 0.63, + "learning_rate": 6.313927753896573e-06, + "loss": 0.4535, + "step": 7407 + }, + { + "epoch": 0.63, + "learning_rate": 6.311360754759923e-06, + "loss": 0.455, + "step": 7408 + }, + { + "epoch": 0.63, + "learning_rate": 6.308794036934304e-06, + "loss": 0.4531, + "step": 7409 + }, + { + "epoch": 0.63, + "learning_rate": 6.3062276006154576e-06, + "loss": 0.473, + "step": 7410 + }, + { + "epoch": 0.63, + "learning_rate": 6.303661445999116e-06, + "loss": 0.4723, + "step": 7411 + }, + { + "epoch": 0.63, + "learning_rate": 6.301095573280988e-06, + "loss": 0.4502, + "step": 7412 + }, + { + "epoch": 0.63, + "learning_rate": 6.298529982656752e-06, + "loss": 0.464, + "step": 7413 + }, + { + "epoch": 0.63, + "learning_rate": 6.295964674322069e-06, + "loss": 0.4805, + "step": 7414 + }, + { + "epoch": 0.63, + "learning_rate": 6.293399648472589e-06, + "loss": 0.4546, + "step": 7415 + }, + { + "epoch": 0.63, + "learning_rate": 6.290834905303926e-06, + "loss": 0.4502, + "step": 7416 + }, + { + "epoch": 0.63, + "learning_rate": 6.288270445011677e-06, + "loss": 0.4768, + "step": 7417 + }, + { + "epoch": 0.63, + "learning_rate": 6.2857062677914225e-06, + "loss": 0.4602, + "step": 7418 + }, + { + "epoch": 0.63, + "learning_rate": 6.2831423738387095e-06, + "loss": 0.4889, + "step": 7419 + }, + { + "epoch": 0.63, + "learning_rate": 6.280578763349079e-06, + "loss": 0.4852, + "step": 7420 + }, + { + "epoch": 0.63, + "learning_rate": 6.278015436518042e-06, + "loss": 0.451, + "step": 7421 + }, + { + "epoch": 0.63, + "learning_rate": 6.2754523935410845e-06, + "loss": 0.4817, + "step": 7422 + }, + { + "epoch": 0.63, + "learning_rate": 6.272889634613679e-06, + "loss": 0.4558, + "step": 7423 + }, + { + "epoch": 0.63, + "learning_rate": 6.270327159931267e-06, + "loss": 0.469, + "step": 7424 + }, + { + "epoch": 0.63, + "learning_rate": 6.26776496968928e-06, + "loss": 0.442, + "step": 7425 + }, + { + "epoch": 0.63, + "learning_rate": 6.265203064083117e-06, + "loss": 0.4801, + "step": 7426 + }, + { + "epoch": 0.63, + "learning_rate": 6.26264144330816e-06, + "loss": 0.4671, + "step": 7427 + }, + { + "epoch": 0.63, + "learning_rate": 6.260080107559767e-06, + "loss": 0.4644, + "step": 7428 + }, + { + "epoch": 0.63, + "learning_rate": 6.257519057033281e-06, + "loss": 0.4647, + "step": 7429 + }, + { + "epoch": 0.63, + "learning_rate": 6.254958291924018e-06, + "loss": 0.4747, + "step": 7430 + }, + { + "epoch": 0.63, + "learning_rate": 6.2523978124272686e-06, + "loss": 0.464, + "step": 7431 + }, + { + "epoch": 0.63, + "learning_rate": 6.24983761873831e-06, + "loss": 0.4348, + "step": 7432 + }, + { + "epoch": 0.63, + "learning_rate": 6.247277711052388e-06, + "loss": 0.4774, + "step": 7433 + }, + { + "epoch": 0.63, + "learning_rate": 6.244718089564735e-06, + "loss": 0.467, + "step": 7434 + }, + { + "epoch": 0.63, + "learning_rate": 6.242158754470562e-06, + "loss": 0.4658, + "step": 7435 + }, + { + "epoch": 0.63, + "learning_rate": 6.23959970596505e-06, + "loss": 0.4639, + "step": 7436 + }, + { + "epoch": 0.63, + "learning_rate": 6.23704094424336e-06, + "loss": 0.4804, + "step": 7437 + }, + { + "epoch": 0.63, + "learning_rate": 6.234482469500639e-06, + "loss": 0.4471, + "step": 7438 + }, + { + "epoch": 0.63, + "learning_rate": 6.231924281932007e-06, + "loss": 0.4842, + "step": 7439 + }, + { + "epoch": 0.63, + "learning_rate": 6.22936638173256e-06, + "loss": 0.4543, + "step": 7440 + }, + { + "epoch": 0.63, + "learning_rate": 6.226808769097376e-06, + "loss": 0.4732, + "step": 7441 + }, + { + "epoch": 0.63, + "learning_rate": 6.224251444221503e-06, + "loss": 0.4845, + "step": 7442 + }, + { + "epoch": 0.63, + "learning_rate": 6.221694407299981e-06, + "loss": 0.4512, + "step": 7443 + }, + { + "epoch": 0.63, + "learning_rate": 6.219137658527819e-06, + "loss": 0.4602, + "step": 7444 + }, + { + "epoch": 0.63, + "learning_rate": 6.216581198100005e-06, + "loss": 0.4607, + "step": 7445 + }, + { + "epoch": 0.63, + "learning_rate": 6.214025026211499e-06, + "loss": 0.4755, + "step": 7446 + }, + { + "epoch": 0.63, + "learning_rate": 6.211469143057252e-06, + "loss": 0.4757, + "step": 7447 + }, + { + "epoch": 0.64, + "learning_rate": 6.208913548832187e-06, + "loss": 0.4545, + "step": 7448 + }, + { + "epoch": 0.64, + "learning_rate": 6.206358243731201e-06, + "loss": 0.4562, + "step": 7449 + }, + { + "epoch": 0.64, + "learning_rate": 6.203803227949175e-06, + "loss": 0.4692, + "step": 7450 + }, + { + "epoch": 0.64, + "learning_rate": 6.201248501680959e-06, + "loss": 0.4364, + "step": 7451 + }, + { + "epoch": 0.64, + "learning_rate": 6.198694065121393e-06, + "loss": 0.4517, + "step": 7452 + }, + { + "epoch": 0.64, + "learning_rate": 6.196139918465291e-06, + "loss": 0.4785, + "step": 7453 + }, + { + "epoch": 0.64, + "learning_rate": 6.1935860619074396e-06, + "loss": 0.4574, + "step": 7454 + }, + { + "epoch": 0.64, + "learning_rate": 6.191032495642604e-06, + "loss": 0.4535, + "step": 7455 + }, + { + "epoch": 0.64, + "learning_rate": 6.188479219865529e-06, + "loss": 0.4751, + "step": 7456 + }, + { + "epoch": 0.64, + "learning_rate": 6.185926234770947e-06, + "loss": 0.4671, + "step": 7457 + }, + { + "epoch": 0.64, + "learning_rate": 6.18337354055355e-06, + "loss": 0.4668, + "step": 7458 + }, + { + "epoch": 0.64, + "learning_rate": 6.180821137408024e-06, + "loss": 0.4668, + "step": 7459 + }, + { + "epoch": 0.64, + "learning_rate": 6.178269025529018e-06, + "loss": 0.4711, + "step": 7460 + }, + { + "epoch": 0.64, + "learning_rate": 6.1757172051111736e-06, + "loss": 0.4716, + "step": 7461 + }, + { + "epoch": 0.64, + "learning_rate": 6.173165676349103e-06, + "loss": 0.4695, + "step": 7462 + }, + { + "epoch": 0.64, + "learning_rate": 6.1706144394373945e-06, + "loss": 0.467, + "step": 7463 + }, + { + "epoch": 0.64, + "learning_rate": 6.168063494570615e-06, + "loss": 0.4654, + "step": 7464 + }, + { + "epoch": 0.64, + "learning_rate": 6.165512841943308e-06, + "loss": 0.4691, + "step": 7465 + }, + { + "epoch": 0.64, + "learning_rate": 6.162962481750004e-06, + "loss": 0.4638, + "step": 7466 + }, + { + "epoch": 0.64, + "learning_rate": 6.160412414185199e-06, + "loss": 0.4521, + "step": 7467 + }, + { + "epoch": 0.64, + "learning_rate": 6.157862639443375e-06, + "loss": 0.4685, + "step": 7468 + }, + { + "epoch": 0.64, + "learning_rate": 6.155313157718983e-06, + "loss": 0.4675, + "step": 7469 + }, + { + "epoch": 0.64, + "learning_rate": 6.152763969206461e-06, + "loss": 0.4766, + "step": 7470 + }, + { + "epoch": 0.64, + "learning_rate": 6.1502150741002254e-06, + "loss": 0.4759, + "step": 7471 + }, + { + "epoch": 0.64, + "learning_rate": 6.147666472594658e-06, + "loss": 0.4727, + "step": 7472 + }, + { + "epoch": 0.64, + "learning_rate": 6.145118164884127e-06, + "loss": 0.4432, + "step": 7473 + }, + { + "epoch": 0.64, + "learning_rate": 6.142570151162977e-06, + "loss": 0.4741, + "step": 7474 + }, + { + "epoch": 0.64, + "learning_rate": 6.140022431625535e-06, + "loss": 0.473, + "step": 7475 + }, + { + "epoch": 0.64, + "learning_rate": 6.137475006466096e-06, + "loss": 0.4603, + "step": 7476 + }, + { + "epoch": 0.64, + "learning_rate": 6.13492787587894e-06, + "loss": 0.4723, + "step": 7477 + }, + { + "epoch": 0.64, + "learning_rate": 6.132381040058317e-06, + "loss": 0.4531, + "step": 7478 + }, + { + "epoch": 0.64, + "learning_rate": 6.129834499198464e-06, + "loss": 0.4802, + "step": 7479 + }, + { + "epoch": 0.64, + "learning_rate": 6.127288253493591e-06, + "loss": 0.4505, + "step": 7480 + }, + { + "epoch": 0.64, + "learning_rate": 6.124742303137885e-06, + "loss": 0.4772, + "step": 7481 + }, + { + "epoch": 0.64, + "learning_rate": 6.122196648325507e-06, + "loss": 0.473, + "step": 7482 + }, + { + "epoch": 0.64, + "learning_rate": 6.119651289250599e-06, + "loss": 0.4582, + "step": 7483 + }, + { + "epoch": 0.64, + "learning_rate": 6.11710622610729e-06, + "loss": 0.4759, + "step": 7484 + }, + { + "epoch": 0.64, + "learning_rate": 6.114561459089668e-06, + "loss": 0.4852, + "step": 7485 + }, + { + "epoch": 0.64, + "learning_rate": 6.1120169883918115e-06, + "loss": 0.4447, + "step": 7486 + }, + { + "epoch": 0.64, + "learning_rate": 6.109472814207768e-06, + "loss": 0.4776, + "step": 7487 + }, + { + "epoch": 0.64, + "learning_rate": 6.106928936731571e-06, + "loss": 0.4647, + "step": 7488 + }, + { + "epoch": 0.64, + "learning_rate": 6.10438535615723e-06, + "loss": 0.4573, + "step": 7489 + }, + { + "epoch": 0.64, + "learning_rate": 6.101842072678724e-06, + "loss": 0.4683, + "step": 7490 + }, + { + "epoch": 0.64, + "learning_rate": 6.099299086490015e-06, + "loss": 0.4427, + "step": 7491 + }, + { + "epoch": 0.64, + "learning_rate": 6.096756397785039e-06, + "loss": 0.4793, + "step": 7492 + }, + { + "epoch": 0.64, + "learning_rate": 6.094214006757721e-06, + "loss": 0.4602, + "step": 7493 + }, + { + "epoch": 0.64, + "learning_rate": 6.091671913601948e-06, + "loss": 0.4571, + "step": 7494 + }, + { + "epoch": 0.64, + "learning_rate": 6.089130118511593e-06, + "loss": 0.4543, + "step": 7495 + }, + { + "epoch": 0.64, + "learning_rate": 6.086588621680498e-06, + "loss": 0.4419, + "step": 7496 + }, + { + "epoch": 0.64, + "learning_rate": 6.0840474233024935e-06, + "loss": 0.4825, + "step": 7497 + }, + { + "epoch": 0.64, + "learning_rate": 6.081506523571384e-06, + "loss": 0.4746, + "step": 7498 + }, + { + "epoch": 0.64, + "learning_rate": 6.078965922680945e-06, + "loss": 0.4536, + "step": 7499 + }, + { + "epoch": 0.64, + "learning_rate": 6.0764256208249365e-06, + "loss": 0.4684, + "step": 7500 + }, + { + "epoch": 0.64, + "learning_rate": 6.0738856181970865e-06, + "loss": 0.4576, + "step": 7501 + }, + { + "epoch": 0.64, + "learning_rate": 6.071345914991113e-06, + "loss": 0.446, + "step": 7502 + }, + { + "epoch": 0.64, + "learning_rate": 6.0688065114007015e-06, + "loss": 0.453, + "step": 7503 + }, + { + "epoch": 0.64, + "learning_rate": 6.06626740761952e-06, + "loss": 0.4674, + "step": 7504 + }, + { + "epoch": 0.64, + "learning_rate": 6.063728603841203e-06, + "loss": 0.484, + "step": 7505 + }, + { + "epoch": 0.64, + "learning_rate": 6.061190100259377e-06, + "loss": 0.4723, + "step": 7506 + }, + { + "epoch": 0.64, + "learning_rate": 6.058651897067642e-06, + "loss": 0.4507, + "step": 7507 + }, + { + "epoch": 0.64, + "learning_rate": 6.056113994459567e-06, + "loss": 0.4738, + "step": 7508 + }, + { + "epoch": 0.64, + "learning_rate": 6.053576392628704e-06, + "loss": 0.4579, + "step": 7509 + }, + { + "epoch": 0.64, + "learning_rate": 6.051039091768582e-06, + "loss": 0.4689, + "step": 7510 + }, + { + "epoch": 0.64, + "learning_rate": 6.048502092072701e-06, + "loss": 0.4934, + "step": 7511 + }, + { + "epoch": 0.64, + "learning_rate": 6.04596539373455e-06, + "loss": 0.4406, + "step": 7512 + }, + { + "epoch": 0.64, + "learning_rate": 6.043428996947587e-06, + "loss": 0.4801, + "step": 7513 + }, + { + "epoch": 0.64, + "learning_rate": 6.040892901905247e-06, + "loss": 0.4859, + "step": 7514 + }, + { + "epoch": 0.64, + "learning_rate": 6.038357108800939e-06, + "loss": 0.4647, + "step": 7515 + }, + { + "epoch": 0.64, + "learning_rate": 6.03582161782806e-06, + "loss": 0.4816, + "step": 7516 + }, + { + "epoch": 0.64, + "learning_rate": 6.033286429179974e-06, + "loss": 0.4569, + "step": 7517 + }, + { + "epoch": 0.64, + "learning_rate": 6.030751543050028e-06, + "loss": 0.473, + "step": 7518 + }, + { + "epoch": 0.64, + "learning_rate": 6.02821695963154e-06, + "loss": 0.4612, + "step": 7519 + }, + { + "epoch": 0.64, + "learning_rate": 6.025682679117804e-06, + "loss": 0.4593, + "step": 7520 + }, + { + "epoch": 0.64, + "learning_rate": 6.023148701702102e-06, + "loss": 0.4592, + "step": 7521 + }, + { + "epoch": 0.64, + "learning_rate": 6.020615027577683e-06, + "loss": 0.4509, + "step": 7522 + }, + { + "epoch": 0.64, + "learning_rate": 6.018081656937775e-06, + "loss": 0.486, + "step": 7523 + }, + { + "epoch": 0.64, + "learning_rate": 6.0155485899755814e-06, + "loss": 0.4659, + "step": 7524 + }, + { + "epoch": 0.64, + "learning_rate": 6.013015826884291e-06, + "loss": 0.4626, + "step": 7525 + }, + { + "epoch": 0.64, + "learning_rate": 6.0104833678570565e-06, + "loss": 0.4608, + "step": 7526 + }, + { + "epoch": 0.64, + "learning_rate": 6.007951213087018e-06, + "loss": 0.4559, + "step": 7527 + }, + { + "epoch": 0.64, + "learning_rate": 6.005419362767286e-06, + "loss": 0.4569, + "step": 7528 + }, + { + "epoch": 0.64, + "learning_rate": 6.0028878170909475e-06, + "loss": 0.4784, + "step": 7529 + }, + { + "epoch": 0.64, + "learning_rate": 6.000356576251074e-06, + "loss": 0.4782, + "step": 7530 + }, + { + "epoch": 0.64, + "learning_rate": 5.997825640440706e-06, + "loss": 0.4829, + "step": 7531 + }, + { + "epoch": 0.64, + "learning_rate": 5.995295009852861e-06, + "loss": 0.4564, + "step": 7532 + }, + { + "epoch": 0.64, + "learning_rate": 5.992764684680542e-06, + "loss": 0.477, + "step": 7533 + }, + { + "epoch": 0.64, + "learning_rate": 5.990234665116713e-06, + "loss": 0.4829, + "step": 7534 + }, + { + "epoch": 0.64, + "learning_rate": 5.987704951354329e-06, + "loss": 0.4533, + "step": 7535 + }, + { + "epoch": 0.64, + "learning_rate": 5.985175543586321e-06, + "loss": 0.4549, + "step": 7536 + }, + { + "epoch": 0.64, + "learning_rate": 5.982646442005586e-06, + "loss": 0.4512, + "step": 7537 + }, + { + "epoch": 0.64, + "learning_rate": 5.980117646805002e-06, + "loss": 0.4744, + "step": 7538 + }, + { + "epoch": 0.64, + "learning_rate": 5.9775891581774305e-06, + "loss": 0.4759, + "step": 7539 + }, + { + "epoch": 0.64, + "learning_rate": 5.975060976315703e-06, + "loss": 0.4496, + "step": 7540 + }, + { + "epoch": 0.64, + "learning_rate": 5.97253310141263e-06, + "loss": 0.4676, + "step": 7541 + }, + { + "epoch": 0.64, + "learning_rate": 5.970005533660997e-06, + "loss": 0.4772, + "step": 7542 + }, + { + "epoch": 0.64, + "learning_rate": 5.967478273253562e-06, + "loss": 0.4969, + "step": 7543 + }, + { + "epoch": 0.64, + "learning_rate": 5.9649513203830724e-06, + "loss": 0.4735, + "step": 7544 + }, + { + "epoch": 0.64, + "learning_rate": 5.9624246752422435e-06, + "loss": 0.4823, + "step": 7545 + }, + { + "epoch": 0.64, + "learning_rate": 5.959898338023764e-06, + "loss": 0.4669, + "step": 7546 + }, + { + "epoch": 0.64, + "learning_rate": 5.957372308920302e-06, + "loss": 0.4563, + "step": 7547 + }, + { + "epoch": 0.64, + "learning_rate": 5.9548465881245055e-06, + "loss": 0.4763, + "step": 7548 + }, + { + "epoch": 0.64, + "learning_rate": 5.952321175828998e-06, + "loss": 0.4788, + "step": 7549 + }, + { + "epoch": 0.64, + "learning_rate": 5.949796072226375e-06, + "loss": 0.4563, + "step": 7550 + }, + { + "epoch": 0.64, + "learning_rate": 5.947271277509215e-06, + "loss": 0.4518, + "step": 7551 + }, + { + "epoch": 0.64, + "learning_rate": 5.944746791870062e-06, + "loss": 0.4617, + "step": 7552 + }, + { + "epoch": 0.64, + "learning_rate": 5.94222261550145e-06, + "loss": 0.4563, + "step": 7553 + }, + { + "epoch": 0.64, + "learning_rate": 5.939698748595885e-06, + "loss": 0.4703, + "step": 7554 + }, + { + "epoch": 0.64, + "learning_rate": 5.937175191345844e-06, + "loss": 0.4714, + "step": 7555 + }, + { + "epoch": 0.64, + "learning_rate": 5.934651943943785e-06, + "loss": 0.4601, + "step": 7556 + }, + { + "epoch": 0.64, + "learning_rate": 5.932129006582139e-06, + "loss": 0.4655, + "step": 7557 + }, + { + "epoch": 0.64, + "learning_rate": 5.92960637945332e-06, + "loss": 0.4535, + "step": 7558 + }, + { + "epoch": 0.64, + "learning_rate": 5.927084062749711e-06, + "loss": 0.4561, + "step": 7559 + }, + { + "epoch": 0.64, + "learning_rate": 5.924562056663676e-06, + "loss": 0.465, + "step": 7560 + }, + { + "epoch": 0.64, + "learning_rate": 5.92204036138755e-06, + "loss": 0.4693, + "step": 7561 + }, + { + "epoch": 0.64, + "learning_rate": 5.919518977113652e-06, + "loss": 0.4809, + "step": 7562 + }, + { + "epoch": 0.64, + "learning_rate": 5.916997904034276e-06, + "loss": 0.4661, + "step": 7563 + }, + { + "epoch": 0.64, + "learning_rate": 5.914477142341682e-06, + "loss": 0.4645, + "step": 7564 + }, + { + "epoch": 0.65, + "learning_rate": 5.91195669222812e-06, + "loss": 0.4744, + "step": 7565 + }, + { + "epoch": 0.65, + "learning_rate": 5.9094365538858055e-06, + "loss": 0.4678, + "step": 7566 + }, + { + "epoch": 0.65, + "learning_rate": 5.906916727506939e-06, + "loss": 0.4718, + "step": 7567 + }, + { + "epoch": 0.65, + "learning_rate": 5.9043972132836905e-06, + "loss": 0.4687, + "step": 7568 + }, + { + "epoch": 0.65, + "learning_rate": 5.901878011408211e-06, + "loss": 0.4823, + "step": 7569 + }, + { + "epoch": 0.65, + "learning_rate": 5.899359122072617e-06, + "loss": 0.4903, + "step": 7570 + }, + { + "epoch": 0.65, + "learning_rate": 5.89684054546902e-06, + "loss": 0.4538, + "step": 7571 + }, + { + "epoch": 0.65, + "learning_rate": 5.894322281789495e-06, + "loss": 0.4502, + "step": 7572 + }, + { + "epoch": 0.65, + "learning_rate": 5.891804331226092e-06, + "loss": 0.4794, + "step": 7573 + }, + { + "epoch": 0.65, + "learning_rate": 5.889286693970843e-06, + "loss": 0.4645, + "step": 7574 + }, + { + "epoch": 0.65, + "learning_rate": 5.88676937021575e-06, + "loss": 0.4587, + "step": 7575 + }, + { + "epoch": 0.65, + "learning_rate": 5.8842523601528e-06, + "loss": 0.457, + "step": 7576 + }, + { + "epoch": 0.65, + "learning_rate": 5.881735663973945e-06, + "loss": 0.4776, + "step": 7577 + }, + { + "epoch": 0.65, + "learning_rate": 5.879219281871125e-06, + "loss": 0.4755, + "step": 7578 + }, + { + "epoch": 0.65, + "learning_rate": 5.876703214036241e-06, + "loss": 0.4635, + "step": 7579 + }, + { + "epoch": 0.65, + "learning_rate": 5.874187460661187e-06, + "loss": 0.4642, + "step": 7580 + }, + { + "epoch": 0.65, + "learning_rate": 5.871672021937823e-06, + "loss": 0.4392, + "step": 7581 + }, + { + "epoch": 0.65, + "learning_rate": 5.869156898057983e-06, + "loss": 0.4767, + "step": 7582 + }, + { + "epoch": 0.65, + "learning_rate": 5.866642089213488e-06, + "loss": 0.4808, + "step": 7583 + }, + { + "epoch": 0.65, + "learning_rate": 5.864127595596119e-06, + "loss": 0.4655, + "step": 7584 + }, + { + "epoch": 0.65, + "learning_rate": 5.86161341739765e-06, + "loss": 0.4722, + "step": 7585 + }, + { + "epoch": 0.65, + "learning_rate": 5.859099554809817e-06, + "loss": 0.4795, + "step": 7586 + }, + { + "epoch": 0.65, + "learning_rate": 5.856586008024342e-06, + "loss": 0.4606, + "step": 7587 + }, + { + "epoch": 0.65, + "learning_rate": 5.854072777232914e-06, + "loss": 0.4616, + "step": 7588 + }, + { + "epoch": 0.65, + "learning_rate": 5.851559862627203e-06, + "loss": 0.4677, + "step": 7589 + }, + { + "epoch": 0.65, + "learning_rate": 5.849047264398859e-06, + "loss": 0.4836, + "step": 7590 + }, + { + "epoch": 0.65, + "learning_rate": 5.8465349827395e-06, + "loss": 0.4712, + "step": 7591 + }, + { + "epoch": 0.65, + "learning_rate": 5.8440230178407245e-06, + "loss": 0.4789, + "step": 7592 + }, + { + "epoch": 0.65, + "learning_rate": 5.841511369894099e-06, + "loss": 0.4617, + "step": 7593 + }, + { + "epoch": 0.65, + "learning_rate": 5.839000039091185e-06, + "loss": 0.4774, + "step": 7594 + }, + { + "epoch": 0.65, + "learning_rate": 5.836489025623495e-06, + "loss": 0.4586, + "step": 7595 + }, + { + "epoch": 0.65, + "learning_rate": 5.833978329682535e-06, + "loss": 0.501, + "step": 7596 + }, + { + "epoch": 0.65, + "learning_rate": 5.831467951459784e-06, + "loss": 0.4706, + "step": 7597 + }, + { + "epoch": 0.65, + "learning_rate": 5.828957891146682e-06, + "loss": 0.4598, + "step": 7598 + }, + { + "epoch": 0.65, + "learning_rate": 5.826448148934669e-06, + "loss": 0.4577, + "step": 7599 + }, + { + "epoch": 0.65, + "learning_rate": 5.823938725015148e-06, + "loss": 0.4667, + "step": 7600 + }, + { + "epoch": 0.65, + "learning_rate": 5.821429619579491e-06, + "loss": 0.4935, + "step": 7601 + }, + { + "epoch": 0.65, + "learning_rate": 5.818920832819051e-06, + "loss": 0.4675, + "step": 7602 + }, + { + "epoch": 0.65, + "learning_rate": 5.816412364925173e-06, + "loss": 0.4528, + "step": 7603 + }, + { + "epoch": 0.65, + "learning_rate": 5.813904216089148e-06, + "loss": 0.4495, + "step": 7604 + }, + { + "epoch": 0.65, + "learning_rate": 5.811396386502266e-06, + "loss": 0.4663, + "step": 7605 + }, + { + "epoch": 0.65, + "learning_rate": 5.808888876355785e-06, + "loss": 0.4606, + "step": 7606 + }, + { + "epoch": 0.65, + "learning_rate": 5.80638168584093e-06, + "loss": 0.4602, + "step": 7607 + }, + { + "epoch": 0.65, + "learning_rate": 5.803874815148916e-06, + "loss": 0.4841, + "step": 7608 + }, + { + "epoch": 0.65, + "learning_rate": 5.8013682644709335e-06, + "loss": 0.4419, + "step": 7609 + }, + { + "epoch": 0.65, + "learning_rate": 5.798862033998131e-06, + "loss": 0.4591, + "step": 7610 + }, + { + "epoch": 0.65, + "learning_rate": 5.796356123921649e-06, + "loss": 0.4564, + "step": 7611 + }, + { + "epoch": 0.65, + "learning_rate": 5.793850534432599e-06, + "loss": 0.4734, + "step": 7612 + }, + { + "epoch": 0.65, + "learning_rate": 5.791345265722068e-06, + "loss": 0.4679, + "step": 7613 + }, + { + "epoch": 0.65, + "learning_rate": 5.788840317981117e-06, + "loss": 0.4777, + "step": 7614 + }, + { + "epoch": 0.65, + "learning_rate": 5.786335691400789e-06, + "loss": 0.4747, + "step": 7615 + }, + { + "epoch": 0.65, + "learning_rate": 5.783831386172083e-06, + "loss": 0.4871, + "step": 7616 + }, + { + "epoch": 0.65, + "learning_rate": 5.781327402486002e-06, + "loss": 0.4711, + "step": 7617 + }, + { + "epoch": 0.65, + "learning_rate": 5.77882374053351e-06, + "loss": 0.4699, + "step": 7618 + }, + { + "epoch": 0.65, + "learning_rate": 5.776320400505539e-06, + "loss": 0.466, + "step": 7619 + }, + { + "epoch": 0.65, + "learning_rate": 5.773817382593008e-06, + "loss": 0.4612, + "step": 7620 + }, + { + "epoch": 0.65, + "learning_rate": 5.771314686986806e-06, + "loss": 0.4656, + "step": 7621 + }, + { + "epoch": 0.65, + "learning_rate": 5.7688123138778e-06, + "loss": 0.4497, + "step": 7622 + }, + { + "epoch": 0.65, + "learning_rate": 5.766310263456833e-06, + "loss": 0.4656, + "step": 7623 + }, + { + "epoch": 0.65, + "learning_rate": 5.7638085359147235e-06, + "loss": 0.4887, + "step": 7624 + }, + { + "epoch": 0.65, + "learning_rate": 5.761307131442253e-06, + "loss": 0.4927, + "step": 7625 + }, + { + "epoch": 0.65, + "learning_rate": 5.758806050230199e-06, + "loss": 0.4288, + "step": 7626 + }, + { + "epoch": 0.65, + "learning_rate": 5.756305292469308e-06, + "loss": 0.4697, + "step": 7627 + }, + { + "epoch": 0.65, + "learning_rate": 5.753804858350288e-06, + "loss": 0.4702, + "step": 7628 + }, + { + "epoch": 0.65, + "learning_rate": 5.751304748063838e-06, + "loss": 0.4366, + "step": 7629 + }, + { + "epoch": 0.65, + "learning_rate": 5.748804961800623e-06, + "loss": 0.504, + "step": 7630 + }, + { + "epoch": 0.65, + "learning_rate": 5.746305499751291e-06, + "loss": 0.4896, + "step": 7631 + }, + { + "epoch": 0.65, + "learning_rate": 5.743806362106461e-06, + "loss": 0.4486, + "step": 7632 + }, + { + "epoch": 0.65, + "learning_rate": 5.74130754905673e-06, + "loss": 0.4632, + "step": 7633 + }, + { + "epoch": 0.65, + "learning_rate": 5.7388090607926605e-06, + "loss": 0.4581, + "step": 7634 + }, + { + "epoch": 0.65, + "learning_rate": 5.736310897504799e-06, + "loss": 0.4628, + "step": 7635 + }, + { + "epoch": 0.65, + "learning_rate": 5.733813059383676e-06, + "loss": 0.4483, + "step": 7636 + }, + { + "epoch": 0.65, + "learning_rate": 5.7313155466197765e-06, + "loss": 0.4818, + "step": 7637 + }, + { + "epoch": 0.65, + "learning_rate": 5.728818359403574e-06, + "loss": 0.4653, + "step": 7638 + }, + { + "epoch": 0.65, + "learning_rate": 5.726321497925516e-06, + "loss": 0.4599, + "step": 7639 + }, + { + "epoch": 0.65, + "learning_rate": 5.7238249623760215e-06, + "loss": 0.461, + "step": 7640 + }, + { + "epoch": 0.65, + "learning_rate": 5.7213287529454885e-06, + "loss": 0.4727, + "step": 7641 + }, + { + "epoch": 0.65, + "learning_rate": 5.718832869824291e-06, + "loss": 0.4577, + "step": 7642 + }, + { + "epoch": 0.65, + "learning_rate": 5.71633731320277e-06, + "loss": 0.4788, + "step": 7643 + }, + { + "epoch": 0.65, + "learning_rate": 5.713842083271244e-06, + "loss": 0.4716, + "step": 7644 + }, + { + "epoch": 0.65, + "learning_rate": 5.711347180220023e-06, + "loss": 0.4453, + "step": 7645 + }, + { + "epoch": 0.65, + "learning_rate": 5.7088526042393665e-06, + "loss": 0.4669, + "step": 7646 + }, + { + "epoch": 0.65, + "learning_rate": 5.706358355519526e-06, + "loss": 0.4682, + "step": 7647 + }, + { + "epoch": 0.65, + "learning_rate": 5.703864434250721e-06, + "loss": 0.4513, + "step": 7648 + }, + { + "epoch": 0.65, + "learning_rate": 5.701370840623153e-06, + "loss": 0.4878, + "step": 7649 + }, + { + "epoch": 0.65, + "learning_rate": 5.698877574826989e-06, + "loss": 0.4843, + "step": 7650 + }, + { + "epoch": 0.65, + "learning_rate": 5.696384637052381e-06, + "loss": 0.4615, + "step": 7651 + }, + { + "epoch": 0.65, + "learning_rate": 5.693892027489445e-06, + "loss": 0.4413, + "step": 7652 + }, + { + "epoch": 0.65, + "learning_rate": 5.691399746328277e-06, + "loss": 0.4455, + "step": 7653 + }, + { + "epoch": 0.65, + "learning_rate": 5.688907793758959e-06, + "loss": 0.4689, + "step": 7654 + }, + { + "epoch": 0.65, + "learning_rate": 5.686416169971527e-06, + "loss": 0.4645, + "step": 7655 + }, + { + "epoch": 0.65, + "learning_rate": 5.683924875156006e-06, + "loss": 0.4688, + "step": 7656 + }, + { + "epoch": 0.65, + "learning_rate": 5.681433909502394e-06, + "loss": 0.4638, + "step": 7657 + }, + { + "epoch": 0.65, + "learning_rate": 5.678943273200661e-06, + "loss": 0.4515, + "step": 7658 + }, + { + "epoch": 0.65, + "learning_rate": 5.676452966440755e-06, + "loss": 0.4604, + "step": 7659 + }, + { + "epoch": 0.65, + "learning_rate": 5.673962989412599e-06, + "loss": 0.4829, + "step": 7660 + }, + { + "epoch": 0.65, + "learning_rate": 5.671473342306082e-06, + "loss": 0.4605, + "step": 7661 + }, + { + "epoch": 0.65, + "learning_rate": 5.6689840253110765e-06, + "loss": 0.4809, + "step": 7662 + }, + { + "epoch": 0.65, + "learning_rate": 5.666495038617437e-06, + "loss": 0.495, + "step": 7663 + }, + { + "epoch": 0.65, + "learning_rate": 5.664006382414975e-06, + "loss": 0.4793, + "step": 7664 + }, + { + "epoch": 0.65, + "learning_rate": 5.661518056893487e-06, + "loss": 0.4773, + "step": 7665 + }, + { + "epoch": 0.65, + "learning_rate": 5.659030062242746e-06, + "loss": 0.4622, + "step": 7666 + }, + { + "epoch": 0.65, + "learning_rate": 5.656542398652494e-06, + "loss": 0.4749, + "step": 7667 + }, + { + "epoch": 0.65, + "learning_rate": 5.6540550663124536e-06, + "loss": 0.4631, + "step": 7668 + }, + { + "epoch": 0.65, + "learning_rate": 5.65156806541232e-06, + "loss": 0.4786, + "step": 7669 + }, + { + "epoch": 0.65, + "learning_rate": 5.649081396141758e-06, + "loss": 0.4691, + "step": 7670 + }, + { + "epoch": 0.65, + "learning_rate": 5.646595058690407e-06, + "loss": 0.4736, + "step": 7671 + }, + { + "epoch": 0.65, + "learning_rate": 5.6441090532479016e-06, + "loss": 0.493, + "step": 7672 + }, + { + "epoch": 0.65, + "learning_rate": 5.64162338000382e-06, + "loss": 0.4682, + "step": 7673 + }, + { + "epoch": 0.65, + "learning_rate": 5.639138039147736e-06, + "loss": 0.446, + "step": 7674 + }, + { + "epoch": 0.65, + "learning_rate": 5.63665303086919e-06, + "loss": 0.4624, + "step": 7675 + }, + { + "epoch": 0.65, + "learning_rate": 5.634168355357701e-06, + "loss": 0.4831, + "step": 7676 + }, + { + "epoch": 0.65, + "learning_rate": 5.631684012802759e-06, + "loss": 0.4599, + "step": 7677 + }, + { + "epoch": 0.65, + "learning_rate": 5.629200003393838e-06, + "loss": 0.4499, + "step": 7678 + }, + { + "epoch": 0.65, + "learning_rate": 5.626716327320365e-06, + "loss": 0.4622, + "step": 7679 + }, + { + "epoch": 0.65, + "learning_rate": 5.62423298477176e-06, + "loss": 0.4684, + "step": 7680 + }, + { + "epoch": 0.65, + "learning_rate": 5.621749975937425e-06, + "loss": 0.4751, + "step": 7681 + }, + { + "epoch": 0.66, + "learning_rate": 5.61926730100671e-06, + "loss": 0.446, + "step": 7682 + }, + { + "epoch": 0.66, + "learning_rate": 5.616784960168962e-06, + "loss": 0.4736, + "step": 7683 + }, + { + "epoch": 0.66, + "learning_rate": 5.61430295361349e-06, + "loss": 0.4477, + "step": 7684 + }, + { + "epoch": 0.66, + "learning_rate": 5.611821281529585e-06, + "loss": 0.481, + "step": 7685 + }, + { + "epoch": 0.66, + "learning_rate": 5.609339944106509e-06, + "loss": 0.4722, + "step": 7686 + }, + { + "epoch": 0.66, + "learning_rate": 5.606858941533504e-06, + "loss": 0.4516, + "step": 7687 + }, + { + "epoch": 0.66, + "learning_rate": 5.604378273999772e-06, + "loss": 0.4712, + "step": 7688 + }, + { + "epoch": 0.66, + "learning_rate": 5.601897941694505e-06, + "loss": 0.4704, + "step": 7689 + }, + { + "epoch": 0.66, + "learning_rate": 5.5994179448068616e-06, + "loss": 0.4928, + "step": 7690 + }, + { + "epoch": 0.66, + "learning_rate": 5.596938283525978e-06, + "loss": 0.4583, + "step": 7691 + }, + { + "epoch": 0.66, + "learning_rate": 5.5944589580409625e-06, + "loss": 0.4855, + "step": 7692 + }, + { + "epoch": 0.66, + "learning_rate": 5.591979968540902e-06, + "loss": 0.4659, + "step": 7693 + }, + { + "epoch": 0.66, + "learning_rate": 5.589501315214849e-06, + "loss": 0.471, + "step": 7694 + }, + { + "epoch": 0.66, + "learning_rate": 5.58702299825184e-06, + "loss": 0.4608, + "step": 7695 + }, + { + "epoch": 0.66, + "learning_rate": 5.584545017840886e-06, + "loss": 0.4812, + "step": 7696 + }, + { + "epoch": 0.66, + "learning_rate": 5.5820673741709566e-06, + "loss": 0.4728, + "step": 7697 + }, + { + "epoch": 0.66, + "learning_rate": 5.579590067431016e-06, + "loss": 0.4619, + "step": 7698 + }, + { + "epoch": 0.66, + "learning_rate": 5.5771130978099896e-06, + "loss": 0.455, + "step": 7699 + }, + { + "epoch": 0.66, + "learning_rate": 5.5746364654967835e-06, + "loss": 0.4626, + "step": 7700 + }, + { + "epoch": 0.66, + "learning_rate": 5.572160170680277e-06, + "loss": 0.4842, + "step": 7701 + }, + { + "epoch": 0.66, + "learning_rate": 5.56968421354932e-06, + "loss": 0.4832, + "step": 7702 + }, + { + "epoch": 0.66, + "learning_rate": 5.5672085942927425e-06, + "loss": 0.4647, + "step": 7703 + }, + { + "epoch": 0.66, + "learning_rate": 5.564733313099343e-06, + "loss": 0.4511, + "step": 7704 + }, + { + "epoch": 0.66, + "learning_rate": 5.5622583701578984e-06, + "loss": 0.4716, + "step": 7705 + }, + { + "epoch": 0.66, + "learning_rate": 5.55978376565716e-06, + "loss": 0.481, + "step": 7706 + }, + { + "epoch": 0.66, + "learning_rate": 5.557309499785847e-06, + "loss": 0.4683, + "step": 7707 + }, + { + "epoch": 0.66, + "learning_rate": 5.554835572732658e-06, + "loss": 0.4779, + "step": 7708 + }, + { + "epoch": 0.66, + "learning_rate": 5.552361984686267e-06, + "loss": 0.4778, + "step": 7709 + }, + { + "epoch": 0.66, + "learning_rate": 5.549888735835318e-06, + "loss": 0.4589, + "step": 7710 + }, + { + "epoch": 0.66, + "learning_rate": 5.547415826368434e-06, + "loss": 0.4915, + "step": 7711 + }, + { + "epoch": 0.66, + "learning_rate": 5.5449432564742074e-06, + "loss": 0.4554, + "step": 7712 + }, + { + "epoch": 0.66, + "learning_rate": 5.542471026341207e-06, + "loss": 0.4667, + "step": 7713 + }, + { + "epoch": 0.66, + "learning_rate": 5.539999136157977e-06, + "loss": 0.4499, + "step": 7714 + }, + { + "epoch": 0.66, + "learning_rate": 5.537527586113036e-06, + "loss": 0.483, + "step": 7715 + }, + { + "epoch": 0.66, + "learning_rate": 5.535056376394868e-06, + "loss": 0.4548, + "step": 7716 + }, + { + "epoch": 0.66, + "learning_rate": 5.532585507191941e-06, + "loss": 0.4678, + "step": 7717 + }, + { + "epoch": 0.66, + "learning_rate": 5.530114978692695e-06, + "loss": 0.4557, + "step": 7718 + }, + { + "epoch": 0.66, + "learning_rate": 5.52764479108554e-06, + "loss": 0.4579, + "step": 7719 + }, + { + "epoch": 0.66, + "learning_rate": 5.525174944558866e-06, + "loss": 0.449, + "step": 7720 + }, + { + "epoch": 0.66, + "learning_rate": 5.522705439301037e-06, + "loss": 0.4502, + "step": 7721 + }, + { + "epoch": 0.66, + "learning_rate": 5.520236275500375e-06, + "loss": 0.4635, + "step": 7722 + }, + { + "epoch": 0.66, + "learning_rate": 5.517767453345199e-06, + "loss": 0.4588, + "step": 7723 + }, + { + "epoch": 0.66, + "learning_rate": 5.515298973023797e-06, + "loss": 0.4523, + "step": 7724 + }, + { + "epoch": 0.66, + "learning_rate": 5.512830834724413e-06, + "loss": 0.4661, + "step": 7725 + }, + { + "epoch": 0.66, + "learning_rate": 5.510363038635282e-06, + "loss": 0.4673, + "step": 7726 + }, + { + "epoch": 0.66, + "learning_rate": 5.5078955849446115e-06, + "loss": 0.4881, + "step": 7727 + }, + { + "epoch": 0.66, + "learning_rate": 5.505428473840576e-06, + "loss": 0.4662, + "step": 7728 + }, + { + "epoch": 0.66, + "learning_rate": 5.502961705511329e-06, + "loss": 0.475, + "step": 7729 + }, + { + "epoch": 0.66, + "learning_rate": 5.500495280145002e-06, + "loss": 0.4621, + "step": 7730 + }, + { + "epoch": 0.66, + "learning_rate": 5.498029197929682e-06, + "loss": 0.4706, + "step": 7731 + }, + { + "epoch": 0.66, + "learning_rate": 5.495563459053455e-06, + "loss": 0.4595, + "step": 7732 + }, + { + "epoch": 0.66, + "learning_rate": 5.493098063704367e-06, + "loss": 0.4655, + "step": 7733 + }, + { + "epoch": 0.66, + "learning_rate": 5.490633012070432e-06, + "loss": 0.4745, + "step": 7734 + }, + { + "epoch": 0.66, + "learning_rate": 5.48816830433965e-06, + "loss": 0.4519, + "step": 7735 + }, + { + "epoch": 0.66, + "learning_rate": 5.485703940699989e-06, + "loss": 0.4663, + "step": 7736 + }, + { + "epoch": 0.66, + "learning_rate": 5.483239921339393e-06, + "loss": 0.4785, + "step": 7737 + }, + { + "epoch": 0.66, + "learning_rate": 5.480776246445776e-06, + "loss": 0.4691, + "step": 7738 + }, + { + "epoch": 0.66, + "learning_rate": 5.478312916207036e-06, + "loss": 0.4627, + "step": 7739 + }, + { + "epoch": 0.66, + "learning_rate": 5.475849930811021e-06, + "loss": 0.481, + "step": 7740 + }, + { + "epoch": 0.66, + "learning_rate": 5.473387290445582e-06, + "loss": 0.4757, + "step": 7741 + }, + { + "epoch": 0.66, + "learning_rate": 5.47092499529853e-06, + "loss": 0.4474, + "step": 7742 + }, + { + "epoch": 0.66, + "learning_rate": 5.468463045557644e-06, + "loss": 0.4866, + "step": 7743 + }, + { + "epoch": 0.66, + "learning_rate": 5.4660014414106825e-06, + "loss": 0.4598, + "step": 7744 + }, + { + "epoch": 0.66, + "learning_rate": 5.4635401830453815e-06, + "loss": 0.4752, + "step": 7745 + }, + { + "epoch": 0.66, + "learning_rate": 5.461079270649444e-06, + "loss": 0.4592, + "step": 7746 + }, + { + "epoch": 0.66, + "learning_rate": 5.4586187044105524e-06, + "loss": 0.4732, + "step": 7747 + }, + { + "epoch": 0.66, + "learning_rate": 5.456158484516361e-06, + "loss": 0.4615, + "step": 7748 + }, + { + "epoch": 0.66, + "learning_rate": 5.453698611154485e-06, + "loss": 0.4495, + "step": 7749 + }, + { + "epoch": 0.66, + "learning_rate": 5.451239084512537e-06, + "loss": 0.4783, + "step": 7750 + }, + { + "epoch": 0.66, + "learning_rate": 5.448779904778092e-06, + "loss": 0.4756, + "step": 7751 + }, + { + "epoch": 0.66, + "learning_rate": 5.446321072138688e-06, + "loss": 0.4534, + "step": 7752 + }, + { + "epoch": 0.66, + "learning_rate": 5.44386258678185e-06, + "loss": 0.4677, + "step": 7753 + }, + { + "epoch": 0.66, + "learning_rate": 5.441404448895073e-06, + "loss": 0.4726, + "step": 7754 + }, + { + "epoch": 0.66, + "learning_rate": 5.438946658665823e-06, + "loss": 0.4431, + "step": 7755 + }, + { + "epoch": 0.66, + "learning_rate": 5.436489216281544e-06, + "loss": 0.4502, + "step": 7756 + }, + { + "epoch": 0.66, + "learning_rate": 5.434032121929653e-06, + "loss": 0.5031, + "step": 7757 + }, + { + "epoch": 0.66, + "learning_rate": 5.431575375797526e-06, + "loss": 0.4671, + "step": 7758 + }, + { + "epoch": 0.66, + "learning_rate": 5.4291189780725385e-06, + "loss": 0.4689, + "step": 7759 + }, + { + "epoch": 0.66, + "learning_rate": 5.426662928942024e-06, + "loss": 0.485, + "step": 7760 + }, + { + "epoch": 0.66, + "learning_rate": 5.424207228593283e-06, + "loss": 0.4834, + "step": 7761 + }, + { + "epoch": 0.66, + "learning_rate": 5.421751877213603e-06, + "loss": 0.4521, + "step": 7762 + }, + { + "epoch": 0.66, + "learning_rate": 5.4192968749902385e-06, + "loss": 0.4702, + "step": 7763 + }, + { + "epoch": 0.66, + "learning_rate": 5.416842222110419e-06, + "loss": 0.4633, + "step": 7764 + }, + { + "epoch": 0.66, + "learning_rate": 5.4143879187613435e-06, + "loss": 0.4602, + "step": 7765 + }, + { + "epoch": 0.66, + "learning_rate": 5.411933965130196e-06, + "loss": 0.4851, + "step": 7766 + }, + { + "epoch": 0.66, + "learning_rate": 5.409480361404113e-06, + "loss": 0.4616, + "step": 7767 + }, + { + "epoch": 0.66, + "learning_rate": 5.40702710777022e-06, + "loss": 0.4504, + "step": 7768 + }, + { + "epoch": 0.66, + "learning_rate": 5.404574204415622e-06, + "loss": 0.4815, + "step": 7769 + }, + { + "epoch": 0.66, + "learning_rate": 5.4021216515273765e-06, + "loss": 0.4535, + "step": 7770 + }, + { + "epoch": 0.66, + "learning_rate": 5.399669449292529e-06, + "loss": 0.4587, + "step": 7771 + }, + { + "epoch": 0.66, + "learning_rate": 5.397217597898097e-06, + "loss": 0.448, + "step": 7772 + }, + { + "epoch": 0.66, + "learning_rate": 5.394766097531066e-06, + "loss": 0.4758, + "step": 7773 + }, + { + "epoch": 0.66, + "learning_rate": 5.392314948378396e-06, + "loss": 0.4548, + "step": 7774 + }, + { + "epoch": 0.66, + "learning_rate": 5.389864150627032e-06, + "loss": 0.4632, + "step": 7775 + }, + { + "epoch": 0.66, + "learning_rate": 5.38741370446387e-06, + "loss": 0.4706, + "step": 7776 + }, + { + "epoch": 0.66, + "learning_rate": 5.384963610075791e-06, + "loss": 0.475, + "step": 7777 + }, + { + "epoch": 0.66, + "learning_rate": 5.382513867649663e-06, + "loss": 0.4755, + "step": 7778 + }, + { + "epoch": 0.66, + "learning_rate": 5.3800644773723e-06, + "loss": 0.453, + "step": 7779 + }, + { + "epoch": 0.66, + "learning_rate": 5.377615439430508e-06, + "loss": 0.4752, + "step": 7780 + }, + { + "epoch": 0.66, + "learning_rate": 5.375166754011061e-06, + "loss": 0.4444, + "step": 7781 + }, + { + "epoch": 0.66, + "learning_rate": 5.372718421300704e-06, + "loss": 0.4744, + "step": 7782 + }, + { + "epoch": 0.66, + "learning_rate": 5.37027044148616e-06, + "loss": 0.4599, + "step": 7783 + }, + { + "epoch": 0.66, + "learning_rate": 5.367822814754124e-06, + "loss": 0.4867, + "step": 7784 + }, + { + "epoch": 0.66, + "learning_rate": 5.365375541291255e-06, + "loss": 0.4551, + "step": 7785 + }, + { + "epoch": 0.66, + "learning_rate": 5.362928621284193e-06, + "loss": 0.4646, + "step": 7786 + }, + { + "epoch": 0.66, + "learning_rate": 5.360482054919561e-06, + "loss": 0.489, + "step": 7787 + }, + { + "epoch": 0.66, + "learning_rate": 5.358035842383933e-06, + "loss": 0.4433, + "step": 7788 + }, + { + "epoch": 0.66, + "learning_rate": 5.355589983863872e-06, + "loss": 0.4609, + "step": 7789 + }, + { + "epoch": 0.66, + "learning_rate": 5.3531444795459065e-06, + "loss": 0.4557, + "step": 7790 + }, + { + "epoch": 0.66, + "learning_rate": 5.350699329616544e-06, + "loss": 0.4574, + "step": 7791 + }, + { + "epoch": 0.66, + "learning_rate": 5.348254534262262e-06, + "loss": 0.4693, + "step": 7792 + }, + { + "epoch": 0.66, + "learning_rate": 5.345810093669512e-06, + "loss": 0.4643, + "step": 7793 + }, + { + "epoch": 0.66, + "learning_rate": 5.343366008024713e-06, + "loss": 0.4648, + "step": 7794 + }, + { + "epoch": 0.66, + "learning_rate": 5.340922277514258e-06, + "loss": 0.4442, + "step": 7795 + }, + { + "epoch": 0.66, + "learning_rate": 5.3384789023245285e-06, + "loss": 0.4526, + "step": 7796 + }, + { + "epoch": 0.66, + "learning_rate": 5.336035882641854e-06, + "loss": 0.4848, + "step": 7797 + }, + { + "epoch": 0.66, + "learning_rate": 5.333593218652557e-06, + "loss": 0.4442, + "step": 7798 + }, + { + "epoch": 0.66, + "learning_rate": 5.331150910542926e-06, + "loss": 0.4563, + "step": 7799 + }, + { + "epoch": 0.67, + "learning_rate": 5.3287089584992116e-06, + "loss": 0.4639, + "step": 7800 + }, + { + "epoch": 0.67, + "learning_rate": 5.3262673627076555e-06, + "loss": 0.4732, + "step": 7801 + }, + { + "epoch": 0.67, + "learning_rate": 5.323826123354469e-06, + "loss": 0.4686, + "step": 7802 + }, + { + "epoch": 0.67, + "learning_rate": 5.3213852406258195e-06, + "loss": 0.4654, + "step": 7803 + }, + { + "epoch": 0.67, + "learning_rate": 5.318944714707861e-06, + "loss": 0.4474, + "step": 7804 + }, + { + "epoch": 0.67, + "learning_rate": 5.316504545786728e-06, + "loss": 0.4678, + "step": 7805 + }, + { + "epoch": 0.67, + "learning_rate": 5.3140647340485086e-06, + "loss": 0.4512, + "step": 7806 + }, + { + "epoch": 0.67, + "learning_rate": 5.3116252796792755e-06, + "loss": 0.4694, + "step": 7807 + }, + { + "epoch": 0.67, + "learning_rate": 5.309186182865076e-06, + "loss": 0.4564, + "step": 7808 + }, + { + "epoch": 0.67, + "learning_rate": 5.306747443791913e-06, + "loss": 0.4624, + "step": 7809 + }, + { + "epoch": 0.67, + "learning_rate": 5.304309062645788e-06, + "loss": 0.4728, + "step": 7810 + }, + { + "epoch": 0.67, + "learning_rate": 5.301871039612663e-06, + "loss": 0.455, + "step": 7811 + }, + { + "epoch": 0.67, + "learning_rate": 5.299433374878461e-06, + "loss": 0.4702, + "step": 7812 + }, + { + "epoch": 0.67, + "learning_rate": 5.29699606862909e-06, + "loss": 0.4471, + "step": 7813 + }, + { + "epoch": 0.67, + "learning_rate": 5.294559121050442e-06, + "loss": 0.4643, + "step": 7814 + }, + { + "epoch": 0.67, + "learning_rate": 5.292122532328356e-06, + "loss": 0.4589, + "step": 7815 + }, + { + "epoch": 0.67, + "learning_rate": 5.289686302648661e-06, + "loss": 0.4743, + "step": 7816 + }, + { + "epoch": 0.67, + "learning_rate": 5.287250432197157e-06, + "loss": 0.471, + "step": 7817 + }, + { + "epoch": 0.67, + "learning_rate": 5.284814921159602e-06, + "loss": 0.4438, + "step": 7818 + }, + { + "epoch": 0.67, + "learning_rate": 5.28237976972175e-06, + "loss": 0.4683, + "step": 7819 + }, + { + "epoch": 0.67, + "learning_rate": 5.279944978069318e-06, + "loss": 0.4287, + "step": 7820 + }, + { + "epoch": 0.67, + "learning_rate": 5.277510546387982e-06, + "loss": 0.4834, + "step": 7821 + }, + { + "epoch": 0.67, + "learning_rate": 5.275076474863408e-06, + "loss": 0.4643, + "step": 7822 + }, + { + "epoch": 0.67, + "learning_rate": 5.272642763681228e-06, + "loss": 0.4664, + "step": 7823 + }, + { + "epoch": 0.67, + "learning_rate": 5.2702094130270476e-06, + "loss": 0.4532, + "step": 7824 + }, + { + "epoch": 0.67, + "learning_rate": 5.2677764230864434e-06, + "loss": 0.4671, + "step": 7825 + }, + { + "epoch": 0.67, + "learning_rate": 5.265343794044964e-06, + "loss": 0.4579, + "step": 7826 + }, + { + "epoch": 0.67, + "learning_rate": 5.262911526088136e-06, + "loss": 0.4437, + "step": 7827 + }, + { + "epoch": 0.67, + "learning_rate": 5.260479619401451e-06, + "loss": 0.4635, + "step": 7828 + }, + { + "epoch": 0.67, + "learning_rate": 5.258048074170379e-06, + "loss": 0.4748, + "step": 7829 + }, + { + "epoch": 0.67, + "learning_rate": 5.255616890580356e-06, + "loss": 0.4578, + "step": 7830 + }, + { + "epoch": 0.67, + "learning_rate": 5.253186068816795e-06, + "loss": 0.4496, + "step": 7831 + }, + { + "epoch": 0.67, + "learning_rate": 5.2507556090650835e-06, + "loss": 0.4578, + "step": 7832 + }, + { + "epoch": 0.67, + "learning_rate": 5.248325511510575e-06, + "loss": 0.4441, + "step": 7833 + }, + { + "epoch": 0.67, + "learning_rate": 5.2458957763386005e-06, + "loss": 0.479, + "step": 7834 + }, + { + "epoch": 0.67, + "learning_rate": 5.243466403734464e-06, + "loss": 0.4855, + "step": 7835 + }, + { + "epoch": 0.67, + "learning_rate": 5.241037393883436e-06, + "loss": 0.4729, + "step": 7836 + }, + { + "epoch": 0.67, + "learning_rate": 5.2386087469707644e-06, + "loss": 0.4586, + "step": 7837 + }, + { + "epoch": 0.67, + "learning_rate": 5.236180463181672e-06, + "loss": 0.4643, + "step": 7838 + }, + { + "epoch": 0.67, + "learning_rate": 5.233752542701342e-06, + "loss": 0.4643, + "step": 7839 + }, + { + "epoch": 0.67, + "learning_rate": 5.231324985714942e-06, + "loss": 0.4518, + "step": 7840 + }, + { + "epoch": 0.67, + "learning_rate": 5.228897792407607e-06, + "loss": 0.4925, + "step": 7841 + }, + { + "epoch": 0.67, + "learning_rate": 5.226470962964445e-06, + "loss": 0.4744, + "step": 7842 + }, + { + "epoch": 0.67, + "learning_rate": 5.224044497570535e-06, + "loss": 0.4445, + "step": 7843 + }, + { + "epoch": 0.67, + "learning_rate": 5.2216183964109325e-06, + "loss": 0.4934, + "step": 7844 + }, + { + "epoch": 0.67, + "learning_rate": 5.219192659670663e-06, + "loss": 0.466, + "step": 7845 + }, + { + "epoch": 0.67, + "learning_rate": 5.2167672875347135e-06, + "loss": 0.4567, + "step": 7846 + }, + { + "epoch": 0.67, + "learning_rate": 5.214342280188067e-06, + "loss": 0.4599, + "step": 7847 + }, + { + "epoch": 0.67, + "learning_rate": 5.211917637815654e-06, + "loss": 0.4662, + "step": 7848 + }, + { + "epoch": 0.67, + "learning_rate": 5.209493360602392e-06, + "loss": 0.4446, + "step": 7849 + }, + { + "epoch": 0.67, + "learning_rate": 5.207069448733166e-06, + "loss": 0.468, + "step": 7850 + }, + { + "epoch": 0.67, + "learning_rate": 5.204645902392834e-06, + "loss": 0.4688, + "step": 7851 + }, + { + "epoch": 0.67, + "learning_rate": 5.202222721766226e-06, + "loss": 0.4651, + "step": 7852 + }, + { + "epoch": 0.67, + "learning_rate": 5.199799907038141e-06, + "loss": 0.4859, + "step": 7853 + }, + { + "epoch": 0.67, + "learning_rate": 5.197377458393363e-06, + "loss": 0.4543, + "step": 7854 + }, + { + "epoch": 0.67, + "learning_rate": 5.19495537601662e-06, + "loss": 0.467, + "step": 7855 + }, + { + "epoch": 0.67, + "learning_rate": 5.192533660092647e-06, + "loss": 0.4517, + "step": 7856 + }, + { + "epoch": 0.67, + "learning_rate": 5.190112310806126e-06, + "loss": 0.449, + "step": 7857 + }, + { + "epoch": 0.67, + "learning_rate": 5.1876913283417196e-06, + "loss": 0.4859, + "step": 7858 + }, + { + "epoch": 0.67, + "learning_rate": 5.185270712884064e-06, + "loss": 0.4444, + "step": 7859 + }, + { + "epoch": 0.67, + "learning_rate": 5.1828504646177655e-06, + "loss": 0.4716, + "step": 7860 + }, + { + "epoch": 0.67, + "learning_rate": 5.180430583727401e-06, + "loss": 0.4688, + "step": 7861 + }, + { + "epoch": 0.67, + "learning_rate": 5.178011070397519e-06, + "loss": 0.4832, + "step": 7862 + }, + { + "epoch": 0.67, + "learning_rate": 5.175591924812651e-06, + "loss": 0.5115, + "step": 7863 + }, + { + "epoch": 0.67, + "learning_rate": 5.173173147157275e-06, + "loss": 0.4487, + "step": 7864 + }, + { + "epoch": 0.67, + "learning_rate": 5.170754737615874e-06, + "loss": 0.4689, + "step": 7865 + }, + { + "epoch": 0.67, + "learning_rate": 5.168336696372875e-06, + "loss": 0.4569, + "step": 7866 + }, + { + "epoch": 0.67, + "learning_rate": 5.165919023612691e-06, + "loss": 0.4613, + "step": 7867 + }, + { + "epoch": 0.67, + "learning_rate": 5.163501719519704e-06, + "loss": 0.463, + "step": 7868 + }, + { + "epoch": 0.67, + "learning_rate": 5.161084784278265e-06, + "loss": 0.4631, + "step": 7869 + }, + { + "epoch": 0.67, + "learning_rate": 5.158668218072706e-06, + "loss": 0.4755, + "step": 7870 + }, + { + "epoch": 0.67, + "learning_rate": 5.156252021087318e-06, + "loss": 0.4642, + "step": 7871 + }, + { + "epoch": 0.67, + "learning_rate": 5.153836193506378e-06, + "loss": 0.4928, + "step": 7872 + }, + { + "epoch": 0.67, + "learning_rate": 5.151420735514114e-06, + "loss": 0.4566, + "step": 7873 + }, + { + "epoch": 0.67, + "learning_rate": 5.149005647294755e-06, + "loss": 0.4818, + "step": 7874 + }, + { + "epoch": 0.67, + "learning_rate": 5.146590929032473e-06, + "loss": 0.4617, + "step": 7875 + }, + { + "epoch": 0.67, + "learning_rate": 5.144176580911431e-06, + "loss": 0.4803, + "step": 7876 + }, + { + "epoch": 0.67, + "learning_rate": 5.1417626031157534e-06, + "loss": 0.4733, + "step": 7877 + }, + { + "epoch": 0.67, + "learning_rate": 5.139348995829543e-06, + "loss": 0.4579, + "step": 7878 + }, + { + "epoch": 0.67, + "learning_rate": 5.13693575923687e-06, + "loss": 0.4465, + "step": 7879 + }, + { + "epoch": 0.67, + "learning_rate": 5.1345228935217796e-06, + "loss": 0.4485, + "step": 7880 + }, + { + "epoch": 0.67, + "learning_rate": 5.1321103988682894e-06, + "loss": 0.4834, + "step": 7881 + }, + { + "epoch": 0.67, + "learning_rate": 5.129698275460375e-06, + "loss": 0.449, + "step": 7882 + }, + { + "epoch": 0.67, + "learning_rate": 5.127286523482008e-06, + "loss": 0.4653, + "step": 7883 + }, + { + "epoch": 0.67, + "learning_rate": 5.124875143117116e-06, + "loss": 0.4598, + "step": 7884 + }, + { + "epoch": 0.67, + "learning_rate": 5.122464134549596e-06, + "loss": 0.4523, + "step": 7885 + }, + { + "epoch": 0.67, + "learning_rate": 5.120053497963324e-06, + "loss": 0.4924, + "step": 7886 + }, + { + "epoch": 0.67, + "learning_rate": 5.117643233542146e-06, + "loss": 0.4749, + "step": 7887 + }, + { + "epoch": 0.67, + "learning_rate": 5.1152333414698774e-06, + "loss": 0.4696, + "step": 7888 + }, + { + "epoch": 0.67, + "learning_rate": 5.1128238219303085e-06, + "loss": 0.4612, + "step": 7889 + }, + { + "epoch": 0.67, + "learning_rate": 5.110414675107201e-06, + "loss": 0.462, + "step": 7890 + }, + { + "epoch": 0.67, + "learning_rate": 5.1080059011842764e-06, + "loss": 0.4591, + "step": 7891 + }, + { + "epoch": 0.67, + "learning_rate": 5.105597500345249e-06, + "loss": 0.4662, + "step": 7892 + }, + { + "epoch": 0.67, + "learning_rate": 5.103189472773793e-06, + "loss": 0.4537, + "step": 7893 + }, + { + "epoch": 0.67, + "learning_rate": 5.100781818653549e-06, + "loss": 0.4519, + "step": 7894 + }, + { + "epoch": 0.67, + "learning_rate": 5.098374538168136e-06, + "loss": 0.4929, + "step": 7895 + }, + { + "epoch": 0.67, + "learning_rate": 5.0959676315011445e-06, + "loss": 0.4484, + "step": 7896 + }, + { + "epoch": 0.67, + "learning_rate": 5.093561098836135e-06, + "loss": 0.4603, + "step": 7897 + }, + { + "epoch": 0.67, + "learning_rate": 5.09115494035664e-06, + "loss": 0.4536, + "step": 7898 + }, + { + "epoch": 0.67, + "learning_rate": 5.0887491562461665e-06, + "loss": 0.4755, + "step": 7899 + }, + { + "epoch": 0.67, + "learning_rate": 5.086343746688184e-06, + "loss": 0.4463, + "step": 7900 + }, + { + "epoch": 0.67, + "learning_rate": 5.083938711866136e-06, + "loss": 0.4466, + "step": 7901 + }, + { + "epoch": 0.67, + "learning_rate": 5.081534051963455e-06, + "loss": 0.4882, + "step": 7902 + }, + { + "epoch": 0.67, + "learning_rate": 5.079129767163516e-06, + "loss": 0.48, + "step": 7903 + }, + { + "epoch": 0.67, + "learning_rate": 5.0767258576496846e-06, + "loss": 0.4664, + "step": 7904 + }, + { + "epoch": 0.67, + "learning_rate": 5.0743223236052944e-06, + "loss": 0.4402, + "step": 7905 + }, + { + "epoch": 0.67, + "learning_rate": 5.071919165213647e-06, + "loss": 0.4605, + "step": 7906 + }, + { + "epoch": 0.67, + "learning_rate": 5.069516382658017e-06, + "loss": 0.4594, + "step": 7907 + }, + { + "epoch": 0.67, + "learning_rate": 5.0671139761216585e-06, + "loss": 0.4767, + "step": 7908 + }, + { + "epoch": 0.67, + "learning_rate": 5.064711945787777e-06, + "loss": 0.4601, + "step": 7909 + }, + { + "epoch": 0.67, + "learning_rate": 5.062310291839563e-06, + "loss": 0.4781, + "step": 7910 + }, + { + "epoch": 0.67, + "learning_rate": 5.059909014460188e-06, + "loss": 0.4658, + "step": 7911 + }, + { + "epoch": 0.67, + "learning_rate": 5.057508113832772e-06, + "loss": 0.4704, + "step": 7912 + }, + { + "epoch": 0.67, + "learning_rate": 5.055107590140423e-06, + "loss": 0.4569, + "step": 7913 + }, + { + "epoch": 0.67, + "learning_rate": 5.052707443566212e-06, + "loss": 0.4485, + "step": 7914 + }, + { + "epoch": 0.67, + "learning_rate": 5.050307674293185e-06, + "loss": 0.4729, + "step": 7915 + }, + { + "epoch": 0.67, + "learning_rate": 5.0479082825043604e-06, + "loss": 0.465, + "step": 7916 + }, + { + "epoch": 0.68, + "learning_rate": 5.045509268382728e-06, + "loss": 0.48, + "step": 7917 + }, + { + "epoch": 0.68, + "learning_rate": 5.043110632111239e-06, + "loss": 0.4565, + "step": 7918 + }, + { + "epoch": 0.68, + "learning_rate": 5.040712373872824e-06, + "loss": 0.455, + "step": 7919 + }, + { + "epoch": 0.68, + "learning_rate": 5.038314493850396e-06, + "loss": 0.466, + "step": 7920 + }, + { + "epoch": 0.68, + "learning_rate": 5.035916992226814e-06, + "loss": 0.4452, + "step": 7921 + }, + { + "epoch": 0.68, + "learning_rate": 5.033519869184928e-06, + "loss": 0.4614, + "step": 7922 + }, + { + "epoch": 0.68, + "learning_rate": 5.031123124907553e-06, + "loss": 0.4527, + "step": 7923 + }, + { + "epoch": 0.68, + "learning_rate": 5.028726759577467e-06, + "loss": 0.4646, + "step": 7924 + }, + { + "epoch": 0.68, + "learning_rate": 5.026330773377437e-06, + "loss": 0.4446, + "step": 7925 + }, + { + "epoch": 0.68, + "learning_rate": 5.023935166490189e-06, + "loss": 0.4651, + "step": 7926 + }, + { + "epoch": 0.68, + "learning_rate": 5.021539939098416e-06, + "loss": 0.454, + "step": 7927 + }, + { + "epoch": 0.68, + "learning_rate": 5.019145091384789e-06, + "loss": 0.4625, + "step": 7928 + }, + { + "epoch": 0.68, + "learning_rate": 5.016750623531959e-06, + "loss": 0.4604, + "step": 7929 + }, + { + "epoch": 0.68, + "learning_rate": 5.014356535722527e-06, + "loss": 0.451, + "step": 7930 + }, + { + "epoch": 0.68, + "learning_rate": 5.01196282813908e-06, + "loss": 0.46, + "step": 7931 + }, + { + "epoch": 0.68, + "learning_rate": 5.009569500964175e-06, + "loss": 0.4807, + "step": 7932 + }, + { + "epoch": 0.68, + "learning_rate": 5.007176554380328e-06, + "loss": 0.4608, + "step": 7933 + }, + { + "epoch": 0.68, + "learning_rate": 5.004783988570045e-06, + "loss": 0.4509, + "step": 7934 + }, + { + "epoch": 0.68, + "learning_rate": 5.0023918037157926e-06, + "loss": 0.4399, + "step": 7935 + }, + { + "epoch": 0.68, + "learning_rate": 5.000000000000003e-06, + "loss": 0.471, + "step": 7936 + }, + { + "epoch": 0.68, + "learning_rate": 4.997608577605082e-06, + "loss": 0.4576, + "step": 7937 + }, + { + "epoch": 0.68, + "learning_rate": 4.995217536713425e-06, + "loss": 0.4666, + "step": 7938 + }, + { + "epoch": 0.68, + "learning_rate": 4.9928268775073675e-06, + "loss": 0.4601, + "step": 7939 + }, + { + "epoch": 0.68, + "learning_rate": 4.9904366001692375e-06, + "loss": 0.4568, + "step": 7940 + }, + { + "epoch": 0.68, + "learning_rate": 4.9880467048813305e-06, + "loss": 0.4607, + "step": 7941 + }, + { + "epoch": 0.68, + "learning_rate": 4.9856571918258976e-06, + "loss": 0.4529, + "step": 7942 + }, + { + "epoch": 0.68, + "learning_rate": 4.983268061185185e-06, + "loss": 0.4896, + "step": 7943 + }, + { + "epoch": 0.68, + "learning_rate": 4.9808793131414e-06, + "loss": 0.4501, + "step": 7944 + }, + { + "epoch": 0.68, + "learning_rate": 4.978490947876709e-06, + "loss": 0.4842, + "step": 7945 + }, + { + "epoch": 0.68, + "learning_rate": 4.976102965573258e-06, + "loss": 0.4715, + "step": 7946 + }, + { + "epoch": 0.68, + "learning_rate": 4.9737153664131754e-06, + "loss": 0.4911, + "step": 7947 + }, + { + "epoch": 0.68, + "learning_rate": 4.9713281505785404e-06, + "loss": 0.4748, + "step": 7948 + }, + { + "epoch": 0.68, + "learning_rate": 4.968941318251415e-06, + "loss": 0.4678, + "step": 7949 + }, + { + "epoch": 0.68, + "learning_rate": 4.966554869613831e-06, + "loss": 0.463, + "step": 7950 + }, + { + "epoch": 0.68, + "learning_rate": 4.96416880484778e-06, + "loss": 0.4803, + "step": 7951 + }, + { + "epoch": 0.68, + "learning_rate": 4.961783124135244e-06, + "loss": 0.4842, + "step": 7952 + }, + { + "epoch": 0.68, + "learning_rate": 4.959397827658164e-06, + "loss": 0.4624, + "step": 7953 + }, + { + "epoch": 0.68, + "learning_rate": 4.957012915598446e-06, + "loss": 0.4784, + "step": 7954 + }, + { + "epoch": 0.68, + "learning_rate": 4.9546283881379775e-06, + "loss": 0.4577, + "step": 7955 + }, + { + "epoch": 0.68, + "learning_rate": 4.952244245458612e-06, + "loss": 0.4523, + "step": 7956 + }, + { + "epoch": 0.68, + "learning_rate": 4.949860487742173e-06, + "loss": 0.4439, + "step": 7957 + }, + { + "epoch": 0.68, + "learning_rate": 4.947477115170457e-06, + "loss": 0.4627, + "step": 7958 + }, + { + "epoch": 0.68, + "learning_rate": 4.945094127925234e-06, + "loss": 0.4641, + "step": 7959 + }, + { + "epoch": 0.68, + "learning_rate": 4.94271152618823e-06, + "loss": 0.4555, + "step": 7960 + }, + { + "epoch": 0.68, + "learning_rate": 4.940329310141161e-06, + "loss": 0.4718, + "step": 7961 + }, + { + "epoch": 0.68, + "learning_rate": 4.937947479965705e-06, + "loss": 0.4685, + "step": 7962 + }, + { + "epoch": 0.68, + "learning_rate": 4.935566035843506e-06, + "loss": 0.4668, + "step": 7963 + }, + { + "epoch": 0.68, + "learning_rate": 4.933184977956184e-06, + "loss": 0.4751, + "step": 7964 + }, + { + "epoch": 0.68, + "learning_rate": 4.930804306485328e-06, + "loss": 0.4541, + "step": 7965 + }, + { + "epoch": 0.68, + "learning_rate": 4.928424021612499e-06, + "loss": 0.4778, + "step": 7966 + }, + { + "epoch": 0.68, + "learning_rate": 4.926044123519228e-06, + "loss": 0.4512, + "step": 7967 + }, + { + "epoch": 0.68, + "learning_rate": 4.9236646123870194e-06, + "loss": 0.4528, + "step": 7968 + }, + { + "epoch": 0.68, + "learning_rate": 4.921285488397332e-06, + "loss": 0.4455, + "step": 7969 + }, + { + "epoch": 0.68, + "learning_rate": 4.9189067517316205e-06, + "loss": 0.4561, + "step": 7970 + }, + { + "epoch": 0.68, + "learning_rate": 4.916528402571296e-06, + "loss": 0.4555, + "step": 7971 + }, + { + "epoch": 0.68, + "learning_rate": 4.914150441097736e-06, + "loss": 0.447, + "step": 7972 + }, + { + "epoch": 0.68, + "learning_rate": 4.911772867492295e-06, + "loss": 0.4443, + "step": 7973 + }, + { + "epoch": 0.68, + "learning_rate": 4.909395681936297e-06, + "loss": 0.4561, + "step": 7974 + }, + { + "epoch": 0.68, + "learning_rate": 4.907018884611039e-06, + "loss": 0.478, + "step": 7975 + }, + { + "epoch": 0.68, + "learning_rate": 4.904642475697783e-06, + "loss": 0.4489, + "step": 7976 + }, + { + "epoch": 0.68, + "learning_rate": 4.902266455377768e-06, + "loss": 0.4656, + "step": 7977 + }, + { + "epoch": 0.68, + "learning_rate": 4.899890823832191e-06, + "loss": 0.4582, + "step": 7978 + }, + { + "epoch": 0.68, + "learning_rate": 4.897515581242228e-06, + "loss": 0.4674, + "step": 7979 + }, + { + "epoch": 0.68, + "learning_rate": 4.895140727789037e-06, + "loss": 0.4538, + "step": 7980 + }, + { + "epoch": 0.68, + "learning_rate": 4.892766263653723e-06, + "loss": 0.473, + "step": 7981 + }, + { + "epoch": 0.68, + "learning_rate": 4.890392189017375e-06, + "loss": 0.4527, + "step": 7982 + }, + { + "epoch": 0.68, + "learning_rate": 4.888018504061051e-06, + "loss": 0.4441, + "step": 7983 + }, + { + "epoch": 0.68, + "learning_rate": 4.885645208965779e-06, + "loss": 0.4802, + "step": 7984 + }, + { + "epoch": 0.68, + "learning_rate": 4.883272303912554e-06, + "loss": 0.4553, + "step": 7985 + }, + { + "epoch": 0.68, + "learning_rate": 4.880899789082349e-06, + "loss": 0.4558, + "step": 7986 + }, + { + "epoch": 0.68, + "learning_rate": 4.8785276646560935e-06, + "loss": 0.4849, + "step": 7987 + }, + { + "epoch": 0.68, + "learning_rate": 4.876155930814696e-06, + "loss": 0.4425, + "step": 7988 + }, + { + "epoch": 0.68, + "learning_rate": 4.8737845877390455e-06, + "loss": 0.483, + "step": 7989 + }, + { + "epoch": 0.68, + "learning_rate": 4.871413635609981e-06, + "loss": 0.4682, + "step": 7990 + }, + { + "epoch": 0.68, + "learning_rate": 4.869043074608324e-06, + "loss": 0.462, + "step": 7991 + }, + { + "epoch": 0.68, + "learning_rate": 4.866672904914862e-06, + "loss": 0.4638, + "step": 7992 + }, + { + "epoch": 0.68, + "learning_rate": 4.8643031267103556e-06, + "loss": 0.4922, + "step": 7993 + }, + { + "epoch": 0.68, + "learning_rate": 4.861933740175534e-06, + "loss": 0.4696, + "step": 7994 + }, + { + "epoch": 0.68, + "learning_rate": 4.8595647454911e-06, + "loss": 0.4568, + "step": 7995 + }, + { + "epoch": 0.68, + "learning_rate": 4.857196142837716e-06, + "loss": 0.4821, + "step": 7996 + }, + { + "epoch": 0.68, + "learning_rate": 4.85482793239602e-06, + "loss": 0.4903, + "step": 7997 + }, + { + "epoch": 0.68, + "learning_rate": 4.852460114346634e-06, + "loss": 0.4738, + "step": 7998 + }, + { + "epoch": 0.68, + "learning_rate": 4.850092688870126e-06, + "loss": 0.4525, + "step": 7999 + }, + { + "epoch": 0.68, + "learning_rate": 4.847725656147051e-06, + "loss": 0.4585, + "step": 8000 + }, + { + "epoch": 0.68, + "learning_rate": 4.845359016357927e-06, + "loss": 0.4608, + "step": 8001 + }, + { + "epoch": 0.68, + "learning_rate": 4.8429927696832434e-06, + "loss": 0.4611, + "step": 8002 + }, + { + "epoch": 0.68, + "learning_rate": 4.840626916303461e-06, + "loss": 0.4714, + "step": 8003 + }, + { + "epoch": 0.68, + "learning_rate": 4.838261456399012e-06, + "loss": 0.4627, + "step": 8004 + }, + { + "epoch": 0.68, + "learning_rate": 4.835896390150295e-06, + "loss": 0.4661, + "step": 8005 + }, + { + "epoch": 0.68, + "learning_rate": 4.833531717737673e-06, + "loss": 0.4535, + "step": 8006 + }, + { + "epoch": 0.68, + "learning_rate": 4.831167439341499e-06, + "loss": 0.4654, + "step": 8007 + }, + { + "epoch": 0.68, + "learning_rate": 4.82880355514207e-06, + "loss": 0.4677, + "step": 8008 + }, + { + "epoch": 0.68, + "learning_rate": 4.826440065319672e-06, + "loss": 0.4673, + "step": 8009 + }, + { + "epoch": 0.68, + "learning_rate": 4.824076970054554e-06, + "loss": 0.4539, + "step": 8010 + }, + { + "epoch": 0.68, + "learning_rate": 4.821714269526935e-06, + "loss": 0.449, + "step": 8011 + }, + { + "epoch": 0.68, + "learning_rate": 4.819351963917004e-06, + "loss": 0.465, + "step": 8012 + }, + { + "epoch": 0.68, + "learning_rate": 4.816990053404921e-06, + "loss": 0.4646, + "step": 8013 + }, + { + "epoch": 0.68, + "learning_rate": 4.814628538170818e-06, + "loss": 0.4696, + "step": 8014 + }, + { + "epoch": 0.68, + "learning_rate": 4.812267418394784e-06, + "loss": 0.4641, + "step": 8015 + }, + { + "epoch": 0.68, + "learning_rate": 4.809906694256903e-06, + "loss": 0.4757, + "step": 8016 + }, + { + "epoch": 0.68, + "learning_rate": 4.807546365937201e-06, + "loss": 0.4756, + "step": 8017 + }, + { + "epoch": 0.68, + "learning_rate": 4.805186433615691e-06, + "loss": 0.4433, + "step": 8018 + }, + { + "epoch": 0.68, + "learning_rate": 4.802826897472351e-06, + "loss": 0.485, + "step": 8019 + }, + { + "epoch": 0.68, + "learning_rate": 4.800467757687131e-06, + "loss": 0.4495, + "step": 8020 + }, + { + "epoch": 0.68, + "learning_rate": 4.798109014439944e-06, + "loss": 0.4486, + "step": 8021 + }, + { + "epoch": 0.68, + "learning_rate": 4.795750667910684e-06, + "loss": 0.4622, + "step": 8022 + }, + { + "epoch": 0.68, + "learning_rate": 4.793392718279207e-06, + "loss": 0.4738, + "step": 8023 + }, + { + "epoch": 0.68, + "learning_rate": 4.791035165725332e-06, + "loss": 0.4648, + "step": 8024 + }, + { + "epoch": 0.68, + "learning_rate": 4.788678010428869e-06, + "loss": 0.4665, + "step": 8025 + }, + { + "epoch": 0.68, + "learning_rate": 4.786321252569574e-06, + "loss": 0.476, + "step": 8026 + }, + { + "epoch": 0.68, + "learning_rate": 4.7839648923271855e-06, + "loss": 0.4611, + "step": 8027 + }, + { + "epoch": 0.68, + "learning_rate": 4.781608929881412e-06, + "loss": 0.4643, + "step": 8028 + }, + { + "epoch": 0.68, + "learning_rate": 4.779253365411927e-06, + "loss": 0.4718, + "step": 8029 + }, + { + "epoch": 0.68, + "learning_rate": 4.776898199098377e-06, + "loss": 0.4773, + "step": 8030 + }, + { + "epoch": 0.68, + "learning_rate": 4.7745434311203755e-06, + "loss": 0.4748, + "step": 8031 + }, + { + "epoch": 0.68, + "learning_rate": 4.772189061657511e-06, + "loss": 0.4726, + "step": 8032 + }, + { + "epoch": 0.68, + "learning_rate": 4.769835090889331e-06, + "loss": 0.4732, + "step": 8033 + }, + { + "epoch": 0.69, + "learning_rate": 4.767481518995362e-06, + "loss": 0.4638, + "step": 8034 + }, + { + "epoch": 0.69, + "learning_rate": 4.765128346155098e-06, + "loss": 0.4623, + "step": 8035 + }, + { + "epoch": 0.69, + "learning_rate": 4.762775572547999e-06, + "loss": 0.489, + "step": 8036 + }, + { + "epoch": 0.69, + "learning_rate": 4.760423198353502e-06, + "loss": 0.4693, + "step": 8037 + }, + { + "epoch": 0.69, + "learning_rate": 4.758071223751006e-06, + "loss": 0.4573, + "step": 8038 + }, + { + "epoch": 0.69, + "learning_rate": 4.755719648919883e-06, + "loss": 0.4667, + "step": 8039 + }, + { + "epoch": 0.69, + "learning_rate": 4.753368474039473e-06, + "loss": 0.4563, + "step": 8040 + }, + { + "epoch": 0.69, + "learning_rate": 4.751017699289092e-06, + "loss": 0.4495, + "step": 8041 + }, + { + "epoch": 0.69, + "learning_rate": 4.748667324848011e-06, + "loss": 0.4822, + "step": 8042 + }, + { + "epoch": 0.69, + "learning_rate": 4.746317350895483e-06, + "loss": 0.464, + "step": 8043 + }, + { + "epoch": 0.69, + "learning_rate": 4.743967777610727e-06, + "loss": 0.4543, + "step": 8044 + }, + { + "epoch": 0.69, + "learning_rate": 4.741618605172933e-06, + "loss": 0.4586, + "step": 8045 + }, + { + "epoch": 0.69, + "learning_rate": 4.739269833761256e-06, + "loss": 0.4951, + "step": 8046 + }, + { + "epoch": 0.69, + "learning_rate": 4.736921463554824e-06, + "loss": 0.4435, + "step": 8047 + }, + { + "epoch": 0.69, + "learning_rate": 4.7345734947327345e-06, + "loss": 0.4808, + "step": 8048 + }, + { + "epoch": 0.69, + "learning_rate": 4.732225927474054e-06, + "loss": 0.4599, + "step": 8049 + }, + { + "epoch": 0.69, + "learning_rate": 4.729878761957819e-06, + "loss": 0.4483, + "step": 8050 + }, + { + "epoch": 0.69, + "learning_rate": 4.727531998363028e-06, + "loss": 0.4623, + "step": 8051 + }, + { + "epoch": 0.69, + "learning_rate": 4.725185636868659e-06, + "loss": 0.4533, + "step": 8052 + }, + { + "epoch": 0.69, + "learning_rate": 4.722839677653654e-06, + "loss": 0.4678, + "step": 8053 + }, + { + "epoch": 0.69, + "learning_rate": 4.720494120896928e-06, + "loss": 0.4704, + "step": 8054 + }, + { + "epoch": 0.69, + "learning_rate": 4.718148966777362e-06, + "loss": 0.4582, + "step": 8055 + }, + { + "epoch": 0.69, + "learning_rate": 4.7158042154738094e-06, + "loss": 0.4787, + "step": 8056 + }, + { + "epoch": 0.69, + "learning_rate": 4.713459867165081e-06, + "loss": 0.4461, + "step": 8057 + }, + { + "epoch": 0.69, + "learning_rate": 4.711115922029977e-06, + "loss": 0.4675, + "step": 8058 + }, + { + "epoch": 0.69, + "learning_rate": 4.708772380247257e-06, + "loss": 0.4611, + "step": 8059 + }, + { + "epoch": 0.69, + "learning_rate": 4.706429241995642e-06, + "loss": 0.4645, + "step": 8060 + }, + { + "epoch": 0.69, + "learning_rate": 4.70408650745383e-06, + "loss": 0.459, + "step": 8061 + }, + { + "epoch": 0.69, + "learning_rate": 4.701744176800498e-06, + "loss": 0.4799, + "step": 8062 + }, + { + "epoch": 0.69, + "learning_rate": 4.699402250214271e-06, + "loss": 0.4632, + "step": 8063 + }, + { + "epoch": 0.69, + "learning_rate": 4.697060727873757e-06, + "loss": 0.4618, + "step": 8064 + }, + { + "epoch": 0.69, + "learning_rate": 4.694719609957536e-06, + "loss": 0.4826, + "step": 8065 + }, + { + "epoch": 0.69, + "learning_rate": 4.692378896644137e-06, + "loss": 0.463, + "step": 8066 + }, + { + "epoch": 0.69, + "learning_rate": 4.690038588112087e-06, + "loss": 0.4741, + "step": 8067 + }, + { + "epoch": 0.69, + "learning_rate": 4.6876986845398665e-06, + "loss": 0.4609, + "step": 8068 + }, + { + "epoch": 0.69, + "learning_rate": 4.685359186105918e-06, + "loss": 0.4747, + "step": 8069 + }, + { + "epoch": 0.69, + "learning_rate": 4.683020092988662e-06, + "loss": 0.4398, + "step": 8070 + }, + { + "epoch": 0.69, + "learning_rate": 4.6806814053665e-06, + "loss": 0.4613, + "step": 8071 + }, + { + "epoch": 0.69, + "learning_rate": 4.678343123417778e-06, + "loss": 0.4769, + "step": 8072 + }, + { + "epoch": 0.69, + "learning_rate": 4.676005247320826e-06, + "loss": 0.4712, + "step": 8073 + }, + { + "epoch": 0.69, + "learning_rate": 4.673667777253944e-06, + "loss": 0.4532, + "step": 8074 + }, + { + "epoch": 0.69, + "learning_rate": 4.671330713395388e-06, + "loss": 0.4652, + "step": 8075 + }, + { + "epoch": 0.69, + "learning_rate": 4.6689940559234e-06, + "loss": 0.4776, + "step": 8076 + }, + { + "epoch": 0.69, + "learning_rate": 4.666657805016187e-06, + "loss": 0.4715, + "step": 8077 + }, + { + "epoch": 0.69, + "learning_rate": 4.664321960851912e-06, + "loss": 0.4542, + "step": 8078 + }, + { + "epoch": 0.69, + "learning_rate": 4.661986523608716e-06, + "loss": 0.4666, + "step": 8079 + }, + { + "epoch": 0.69, + "learning_rate": 4.659651493464721e-06, + "loss": 0.4417, + "step": 8080 + }, + { + "epoch": 0.69, + "learning_rate": 4.657316870597993e-06, + "loss": 0.4604, + "step": 8081 + }, + { + "epoch": 0.69, + "learning_rate": 4.6549826551865876e-06, + "loss": 0.4721, + "step": 8082 + }, + { + "epoch": 0.69, + "learning_rate": 4.652648847408523e-06, + "loss": 0.4648, + "step": 8083 + }, + { + "epoch": 0.69, + "learning_rate": 4.650315447441773e-06, + "loss": 0.477, + "step": 8084 + }, + { + "epoch": 0.69, + "learning_rate": 4.647982455464306e-06, + "loss": 0.4824, + "step": 8085 + }, + { + "epoch": 0.69, + "learning_rate": 4.645649871654045e-06, + "loss": 0.4671, + "step": 8086 + }, + { + "epoch": 0.69, + "learning_rate": 4.643317696188875e-06, + "loss": 0.4731, + "step": 8087 + }, + { + "epoch": 0.69, + "learning_rate": 4.64098592924666e-06, + "loss": 0.4705, + "step": 8088 + }, + { + "epoch": 0.69, + "learning_rate": 4.638654571005231e-06, + "loss": 0.4482, + "step": 8089 + }, + { + "epoch": 0.69, + "learning_rate": 4.636323621642389e-06, + "loss": 0.4656, + "step": 8090 + }, + { + "epoch": 0.69, + "learning_rate": 4.633993081335899e-06, + "loss": 0.4659, + "step": 8091 + }, + { + "epoch": 0.69, + "learning_rate": 4.631662950263502e-06, + "loss": 0.4631, + "step": 8092 + }, + { + "epoch": 0.69, + "learning_rate": 4.629333228602895e-06, + "loss": 0.4533, + "step": 8093 + }, + { + "epoch": 0.69, + "learning_rate": 4.627003916531761e-06, + "loss": 0.4518, + "step": 8094 + }, + { + "epoch": 0.69, + "learning_rate": 4.624675014227743e-06, + "loss": 0.4659, + "step": 8095 + }, + { + "epoch": 0.69, + "learning_rate": 4.622346521868446e-06, + "loss": 0.4559, + "step": 8096 + }, + { + "epoch": 0.69, + "learning_rate": 4.620018439631455e-06, + "loss": 0.4732, + "step": 8097 + }, + { + "epoch": 0.69, + "learning_rate": 4.617690767694319e-06, + "loss": 0.4735, + "step": 8098 + }, + { + "epoch": 0.69, + "learning_rate": 4.615363506234554e-06, + "loss": 0.4637, + "step": 8099 + }, + { + "epoch": 0.69, + "learning_rate": 4.613036655429649e-06, + "loss": 0.4685, + "step": 8100 + }, + { + "epoch": 0.69, + "learning_rate": 4.610710215457062e-06, + "loss": 0.4611, + "step": 8101 + }, + { + "epoch": 0.69, + "learning_rate": 4.608384186494205e-06, + "loss": 0.4721, + "step": 8102 + }, + { + "epoch": 0.69, + "learning_rate": 4.606058568718486e-06, + "loss": 0.4518, + "step": 8103 + }, + { + "epoch": 0.69, + "learning_rate": 4.603733362307261e-06, + "loss": 0.474, + "step": 8104 + }, + { + "epoch": 0.69, + "learning_rate": 4.601408567437855e-06, + "loss": 0.4691, + "step": 8105 + }, + { + "epoch": 0.69, + "learning_rate": 4.599084184287571e-06, + "loss": 0.4451, + "step": 8106 + }, + { + "epoch": 0.69, + "learning_rate": 4.596760213033674e-06, + "loss": 0.4609, + "step": 8107 + }, + { + "epoch": 0.69, + "learning_rate": 4.594436653853402e-06, + "loss": 0.4592, + "step": 8108 + }, + { + "epoch": 0.69, + "learning_rate": 4.592113506923959e-06, + "loss": 0.441, + "step": 8109 + }, + { + "epoch": 0.69, + "learning_rate": 4.589790772422519e-06, + "loss": 0.4817, + "step": 8110 + }, + { + "epoch": 0.69, + "learning_rate": 4.587468450526219e-06, + "loss": 0.4687, + "step": 8111 + }, + { + "epoch": 0.69, + "learning_rate": 4.585146541412168e-06, + "loss": 0.4516, + "step": 8112 + }, + { + "epoch": 0.69, + "learning_rate": 4.582825045257455e-06, + "loss": 0.4727, + "step": 8113 + }, + { + "epoch": 0.69, + "learning_rate": 4.580503962239117e-06, + "loss": 0.4703, + "step": 8114 + }, + { + "epoch": 0.69, + "learning_rate": 4.578183292534172e-06, + "loss": 0.4578, + "step": 8115 + }, + { + "epoch": 0.69, + "learning_rate": 4.575863036319604e-06, + "loss": 0.455, + "step": 8116 + }, + { + "epoch": 0.69, + "learning_rate": 4.573543193772368e-06, + "loss": 0.4772, + "step": 8117 + }, + { + "epoch": 0.69, + "learning_rate": 4.5712237650693806e-06, + "loss": 0.4722, + "step": 8118 + }, + { + "epoch": 0.69, + "learning_rate": 4.568904750387538e-06, + "loss": 0.4494, + "step": 8119 + }, + { + "epoch": 0.69, + "learning_rate": 4.566586149903689e-06, + "loss": 0.4573, + "step": 8120 + }, + { + "epoch": 0.69, + "learning_rate": 4.5642679637946605e-06, + "loss": 0.4571, + "step": 8121 + }, + { + "epoch": 0.69, + "learning_rate": 4.561950192237259e-06, + "loss": 0.453, + "step": 8122 + }, + { + "epoch": 0.69, + "learning_rate": 4.5596328354082344e-06, + "loss": 0.4636, + "step": 8123 + }, + { + "epoch": 0.69, + "learning_rate": 4.557315893484323e-06, + "loss": 0.4576, + "step": 8124 + }, + { + "epoch": 0.69, + "learning_rate": 4.554999366642225e-06, + "loss": 0.446, + "step": 8125 + }, + { + "epoch": 0.69, + "learning_rate": 4.552683255058605e-06, + "loss": 0.4691, + "step": 8126 + }, + { + "epoch": 0.69, + "learning_rate": 4.550367558910104e-06, + "loss": 0.4655, + "step": 8127 + }, + { + "epoch": 0.69, + "learning_rate": 4.548052278373327e-06, + "loss": 0.4687, + "step": 8128 + }, + { + "epoch": 0.69, + "learning_rate": 4.545737413624841e-06, + "loss": 0.4779, + "step": 8129 + }, + { + "epoch": 0.69, + "learning_rate": 4.543422964841188e-06, + "loss": 0.4832, + "step": 8130 + }, + { + "epoch": 0.69, + "learning_rate": 4.541108932198887e-06, + "loss": 0.454, + "step": 8131 + }, + { + "epoch": 0.69, + "learning_rate": 4.5387953158744045e-06, + "loss": 0.4472, + "step": 8132 + }, + { + "epoch": 0.69, + "learning_rate": 4.536482116044192e-06, + "loss": 0.4706, + "step": 8133 + }, + { + "epoch": 0.69, + "learning_rate": 4.534169332884662e-06, + "loss": 0.4714, + "step": 8134 + }, + { + "epoch": 0.69, + "learning_rate": 4.531856966572198e-06, + "loss": 0.4567, + "step": 8135 + }, + { + "epoch": 0.69, + "learning_rate": 4.529545017283151e-06, + "loss": 0.4601, + "step": 8136 + }, + { + "epoch": 0.69, + "learning_rate": 4.527233485193843e-06, + "loss": 0.4518, + "step": 8137 + }, + { + "epoch": 0.69, + "learning_rate": 4.524922370480554e-06, + "loss": 0.4582, + "step": 8138 + }, + { + "epoch": 0.69, + "learning_rate": 4.522611673319539e-06, + "loss": 0.4592, + "step": 8139 + }, + { + "epoch": 0.69, + "learning_rate": 4.520301393887032e-06, + "loss": 0.4805, + "step": 8140 + }, + { + "epoch": 0.69, + "learning_rate": 4.517991532359215e-06, + "loss": 0.4704, + "step": 8141 + }, + { + "epoch": 0.69, + "learning_rate": 4.51568208891225e-06, + "loss": 0.4505, + "step": 8142 + }, + { + "epoch": 0.69, + "learning_rate": 4.513373063722266e-06, + "loss": 0.4906, + "step": 8143 + }, + { + "epoch": 0.69, + "learning_rate": 4.511064456965357e-06, + "loss": 0.4612, + "step": 8144 + }, + { + "epoch": 0.69, + "learning_rate": 4.508756268817589e-06, + "loss": 0.439, + "step": 8145 + }, + { + "epoch": 0.69, + "learning_rate": 4.506448499454996e-06, + "loss": 0.4505, + "step": 8146 + }, + { + "epoch": 0.69, + "learning_rate": 4.504141149053572e-06, + "loss": 0.466, + "step": 8147 + }, + { + "epoch": 0.69, + "learning_rate": 4.5018342177892845e-06, + "loss": 0.4682, + "step": 8148 + }, + { + "epoch": 0.69, + "learning_rate": 4.499527705838081e-06, + "loss": 0.4636, + "step": 8149 + }, + { + "epoch": 0.69, + "learning_rate": 4.497221613375856e-06, + "loss": 0.4799, + "step": 8150 + }, + { + "epoch": 0.7, + "learning_rate": 4.4949159405784834e-06, + "loss": 0.4316, + "step": 8151 + }, + { + "epoch": 0.7, + "learning_rate": 4.492610687621805e-06, + "loss": 0.463, + "step": 8152 + }, + { + "epoch": 0.7, + "learning_rate": 4.490305854681627e-06, + "loss": 0.451, + "step": 8153 + }, + { + "epoch": 0.7, + "learning_rate": 4.488001441933727e-06, + "loss": 0.4684, + "step": 8154 + }, + { + "epoch": 0.7, + "learning_rate": 4.485697449553853e-06, + "loss": 0.4602, + "step": 8155 + }, + { + "epoch": 0.7, + "learning_rate": 4.483393877717709e-06, + "loss": 0.4833, + "step": 8156 + }, + { + "epoch": 0.7, + "learning_rate": 4.481090726600975e-06, + "loss": 0.4757, + "step": 8157 + }, + { + "epoch": 0.7, + "learning_rate": 4.478787996379311e-06, + "loss": 0.4567, + "step": 8158 + }, + { + "epoch": 0.7, + "learning_rate": 4.476485687228322e-06, + "loss": 0.4678, + "step": 8159 + }, + { + "epoch": 0.7, + "learning_rate": 4.4741837993235925e-06, + "loss": 0.4584, + "step": 8160 + }, + { + "epoch": 0.7, + "learning_rate": 4.471882332840677e-06, + "loss": 0.4429, + "step": 8161 + }, + { + "epoch": 0.7, + "learning_rate": 4.469581287955094e-06, + "loss": 0.4683, + "step": 8162 + }, + { + "epoch": 0.7, + "learning_rate": 4.467280664842331e-06, + "loss": 0.4654, + "step": 8163 + }, + { + "epoch": 0.7, + "learning_rate": 4.464980463677846e-06, + "loss": 0.4669, + "step": 8164 + }, + { + "epoch": 0.7, + "learning_rate": 4.4626806846370555e-06, + "loss": 0.468, + "step": 8165 + }, + { + "epoch": 0.7, + "learning_rate": 4.460381327895353e-06, + "loss": 0.4869, + "step": 8166 + }, + { + "epoch": 0.7, + "learning_rate": 4.458082393628098e-06, + "loss": 0.4581, + "step": 8167 + }, + { + "epoch": 0.7, + "learning_rate": 4.455783882010617e-06, + "loss": 0.483, + "step": 8168 + }, + { + "epoch": 0.7, + "learning_rate": 4.453485793218203e-06, + "loss": 0.4515, + "step": 8169 + }, + { + "epoch": 0.7, + "learning_rate": 4.451188127426119e-06, + "loss": 0.4773, + "step": 8170 + }, + { + "epoch": 0.7, + "learning_rate": 4.4488908848095935e-06, + "loss": 0.471, + "step": 8171 + }, + { + "epoch": 0.7, + "learning_rate": 4.446594065543825e-06, + "loss": 0.4517, + "step": 8172 + }, + { + "epoch": 0.7, + "learning_rate": 4.444297669803981e-06, + "loss": 0.4744, + "step": 8173 + }, + { + "epoch": 0.7, + "learning_rate": 4.442001697765187e-06, + "loss": 0.4399, + "step": 8174 + }, + { + "epoch": 0.7, + "learning_rate": 4.439706149602547e-06, + "loss": 0.4696, + "step": 8175 + }, + { + "epoch": 0.7, + "learning_rate": 4.437411025491131e-06, + "loss": 0.4586, + "step": 8176 + }, + { + "epoch": 0.7, + "learning_rate": 4.435116325605972e-06, + "loss": 0.4484, + "step": 8177 + }, + { + "epoch": 0.7, + "learning_rate": 4.432822050122076e-06, + "loss": 0.4558, + "step": 8178 + }, + { + "epoch": 0.7, + "learning_rate": 4.4305281992144125e-06, + "loss": 0.4654, + "step": 8179 + }, + { + "epoch": 0.7, + "learning_rate": 4.42823477305792e-06, + "loss": 0.4518, + "step": 8180 + }, + { + "epoch": 0.7, + "learning_rate": 4.425941771827506e-06, + "loss": 0.4594, + "step": 8181 + }, + { + "epoch": 0.7, + "learning_rate": 4.423649195698042e-06, + "loss": 0.463, + "step": 8182 + }, + { + "epoch": 0.7, + "learning_rate": 4.421357044844374e-06, + "loss": 0.4682, + "step": 8183 + }, + { + "epoch": 0.7, + "learning_rate": 4.419065319441306e-06, + "loss": 0.4551, + "step": 8184 + }, + { + "epoch": 0.7, + "learning_rate": 4.416774019663615e-06, + "loss": 0.4449, + "step": 8185 + }, + { + "epoch": 0.7, + "learning_rate": 4.414483145686048e-06, + "loss": 0.4786, + "step": 8186 + }, + { + "epoch": 0.7, + "learning_rate": 4.412192697683315e-06, + "loss": 0.462, + "step": 8187 + }, + { + "epoch": 0.7, + "learning_rate": 4.409902675830094e-06, + "loss": 0.4521, + "step": 8188 + }, + { + "epoch": 0.7, + "learning_rate": 4.407613080301037e-06, + "loss": 0.482, + "step": 8189 + }, + { + "epoch": 0.7, + "learning_rate": 4.405323911270748e-06, + "loss": 0.4624, + "step": 8190 + }, + { + "epoch": 0.7, + "learning_rate": 4.403035168913817e-06, + "loss": 0.4737, + "step": 8191 + }, + { + "epoch": 0.7, + "learning_rate": 4.400746853404795e-06, + "loss": 0.4733, + "step": 8192 + }, + { + "epoch": 0.7, + "learning_rate": 4.39845896491819e-06, + "loss": 0.4659, + "step": 8193 + }, + { + "epoch": 0.7, + "learning_rate": 4.39617150362849e-06, + "loss": 0.4415, + "step": 8194 + }, + { + "epoch": 0.7, + "learning_rate": 4.393884469710147e-06, + "loss": 0.4432, + "step": 8195 + }, + { + "epoch": 0.7, + "learning_rate": 4.391597863337579e-06, + "loss": 0.4787, + "step": 8196 + }, + { + "epoch": 0.7, + "learning_rate": 4.389311684685171e-06, + "loss": 0.4631, + "step": 8197 + }, + { + "epoch": 0.7, + "learning_rate": 4.387025933927282e-06, + "loss": 0.4618, + "step": 8198 + }, + { + "epoch": 0.7, + "learning_rate": 4.384740611238223e-06, + "loss": 0.4697, + "step": 8199 + }, + { + "epoch": 0.7, + "learning_rate": 4.382455716792291e-06, + "loss": 0.4635, + "step": 8200 + }, + { + "epoch": 0.7, + "learning_rate": 4.380171250763741e-06, + "loss": 0.4357, + "step": 8201 + }, + { + "epoch": 0.7, + "learning_rate": 4.377887213326791e-06, + "loss": 0.477, + "step": 8202 + }, + { + "epoch": 0.7, + "learning_rate": 4.375603604655634e-06, + "loss": 0.4729, + "step": 8203 + }, + { + "epoch": 0.7, + "learning_rate": 4.373320424924427e-06, + "loss": 0.4476, + "step": 8204 + }, + { + "epoch": 0.7, + "learning_rate": 4.371037674307294e-06, + "loss": 0.4701, + "step": 8205 + }, + { + "epoch": 0.7, + "learning_rate": 4.368755352978329e-06, + "loss": 0.4515, + "step": 8206 + }, + { + "epoch": 0.7, + "learning_rate": 4.366473461111593e-06, + "loss": 0.4954, + "step": 8207 + }, + { + "epoch": 0.7, + "learning_rate": 4.3641919988811045e-06, + "loss": 0.4725, + "step": 8208 + }, + { + "epoch": 0.7, + "learning_rate": 4.361910966460866e-06, + "loss": 0.4487, + "step": 8209 + }, + { + "epoch": 0.7, + "learning_rate": 4.3596303640248394e-06, + "loss": 0.4529, + "step": 8210 + }, + { + "epoch": 0.7, + "learning_rate": 4.357350191746945e-06, + "loss": 0.467, + "step": 8211 + }, + { + "epoch": 0.7, + "learning_rate": 4.355070449801083e-06, + "loss": 0.482, + "step": 8212 + }, + { + "epoch": 0.7, + "learning_rate": 4.352791138361115e-06, + "loss": 0.4477, + "step": 8213 + }, + { + "epoch": 0.7, + "learning_rate": 4.350512257600871e-06, + "loss": 0.4588, + "step": 8214 + }, + { + "epoch": 0.7, + "learning_rate": 4.348233807694147e-06, + "loss": 0.4447, + "step": 8215 + }, + { + "epoch": 0.7, + "learning_rate": 4.345955788814714e-06, + "loss": 0.4786, + "step": 8216 + }, + { + "epoch": 0.7, + "learning_rate": 4.343678201136289e-06, + "loss": 0.4425, + "step": 8217 + }, + { + "epoch": 0.7, + "learning_rate": 4.341401044832583e-06, + "loss": 0.4561, + "step": 8218 + }, + { + "epoch": 0.7, + "learning_rate": 4.33912432007726e-06, + "loss": 0.4446, + "step": 8219 + }, + { + "epoch": 0.7, + "learning_rate": 4.336848027043947e-06, + "loss": 0.4807, + "step": 8220 + }, + { + "epoch": 0.7, + "learning_rate": 4.334572165906247e-06, + "loss": 0.4801, + "step": 8221 + }, + { + "epoch": 0.7, + "learning_rate": 4.332296736837724e-06, + "loss": 0.4309, + "step": 8222 + }, + { + "epoch": 0.7, + "learning_rate": 4.330021740011916e-06, + "loss": 0.4704, + "step": 8223 + }, + { + "epoch": 0.7, + "learning_rate": 4.327747175602321e-06, + "loss": 0.4432, + "step": 8224 + }, + { + "epoch": 0.7, + "learning_rate": 4.32547304378241e-06, + "loss": 0.4727, + "step": 8225 + }, + { + "epoch": 0.7, + "learning_rate": 4.32319934472561e-06, + "loss": 0.4573, + "step": 8226 + }, + { + "epoch": 0.7, + "learning_rate": 4.320926078605328e-06, + "loss": 0.4591, + "step": 8227 + }, + { + "epoch": 0.7, + "learning_rate": 4.318653245594939e-06, + "loss": 0.469, + "step": 8228 + }, + { + "epoch": 0.7, + "learning_rate": 4.316380845867768e-06, + "loss": 0.443, + "step": 8229 + }, + { + "epoch": 0.7, + "learning_rate": 4.314108879597122e-06, + "loss": 0.4671, + "step": 8230 + }, + { + "epoch": 0.7, + "learning_rate": 4.311837346956271e-06, + "loss": 0.4544, + "step": 8231 + }, + { + "epoch": 0.7, + "learning_rate": 4.3095662481184505e-06, + "loss": 0.479, + "step": 8232 + }, + { + "epoch": 0.7, + "learning_rate": 4.307295583256866e-06, + "loss": 0.484, + "step": 8233 + }, + { + "epoch": 0.7, + "learning_rate": 4.3050253525446895e-06, + "loss": 0.4601, + "step": 8234 + }, + { + "epoch": 0.7, + "learning_rate": 4.302755556155048e-06, + "loss": 0.4684, + "step": 8235 + }, + { + "epoch": 0.7, + "learning_rate": 4.3004861942610575e-06, + "loss": 0.4523, + "step": 8236 + }, + { + "epoch": 0.7, + "learning_rate": 4.298217267035788e-06, + "loss": 0.4768, + "step": 8237 + }, + { + "epoch": 0.7, + "learning_rate": 4.2959487746522695e-06, + "loss": 0.4723, + "step": 8238 + }, + { + "epoch": 0.7, + "learning_rate": 4.293680717283512e-06, + "loss": 0.4606, + "step": 8239 + }, + { + "epoch": 0.7, + "learning_rate": 4.291413095102487e-06, + "loss": 0.4485, + "step": 8240 + }, + { + "epoch": 0.7, + "learning_rate": 4.289145908282131e-06, + "loss": 0.47, + "step": 8241 + }, + { + "epoch": 0.7, + "learning_rate": 4.286879156995349e-06, + "loss": 0.4482, + "step": 8242 + }, + { + "epoch": 0.7, + "learning_rate": 4.284612841415019e-06, + "loss": 0.4619, + "step": 8243 + }, + { + "epoch": 0.7, + "learning_rate": 4.282346961713971e-06, + "loss": 0.4641, + "step": 8244 + }, + { + "epoch": 0.7, + "learning_rate": 4.28008151806501e-06, + "loss": 0.4584, + "step": 8245 + }, + { + "epoch": 0.7, + "learning_rate": 4.27781651064092e-06, + "loss": 0.4759, + "step": 8246 + }, + { + "epoch": 0.7, + "learning_rate": 4.275551939614429e-06, + "loss": 0.4589, + "step": 8247 + }, + { + "epoch": 0.7, + "learning_rate": 4.273287805158245e-06, + "loss": 0.4548, + "step": 8248 + }, + { + "epoch": 0.7, + "learning_rate": 4.271024107445042e-06, + "loss": 0.4627, + "step": 8249 + }, + { + "epoch": 0.7, + "learning_rate": 4.268760846647459e-06, + "loss": 0.4656, + "step": 8250 + }, + { + "epoch": 0.7, + "learning_rate": 4.2664980229381e-06, + "loss": 0.4675, + "step": 8251 + }, + { + "epoch": 0.7, + "learning_rate": 4.264235636489542e-06, + "loss": 0.4619, + "step": 8252 + }, + { + "epoch": 0.7, + "learning_rate": 4.261973687474316e-06, + "loss": 0.462, + "step": 8253 + }, + { + "epoch": 0.7, + "learning_rate": 4.25971217606493e-06, + "loss": 0.4604, + "step": 8254 + }, + { + "epoch": 0.7, + "learning_rate": 4.257451102433866e-06, + "loss": 0.452, + "step": 8255 + }, + { + "epoch": 0.7, + "learning_rate": 4.255190466753551e-06, + "loss": 0.4715, + "step": 8256 + }, + { + "epoch": 0.7, + "learning_rate": 4.252930269196395e-06, + "loss": 0.4508, + "step": 8257 + }, + { + "epoch": 0.7, + "learning_rate": 4.25067050993477e-06, + "loss": 0.4451, + "step": 8258 + }, + { + "epoch": 0.7, + "learning_rate": 4.248411189141014e-06, + "loss": 0.4613, + "step": 8259 + }, + { + "epoch": 0.7, + "learning_rate": 4.246152306987434e-06, + "loss": 0.4637, + "step": 8260 + }, + { + "epoch": 0.7, + "learning_rate": 4.2438938636463035e-06, + "loss": 0.4555, + "step": 8261 + }, + { + "epoch": 0.7, + "learning_rate": 4.241635859289855e-06, + "loss": 0.4774, + "step": 8262 + }, + { + "epoch": 0.7, + "learning_rate": 4.239378294090292e-06, + "loss": 0.4609, + "step": 8263 + }, + { + "epoch": 0.7, + "learning_rate": 4.237121168219798e-06, + "loss": 0.4683, + "step": 8264 + }, + { + "epoch": 0.7, + "learning_rate": 4.234864481850499e-06, + "loss": 0.4613, + "step": 8265 + }, + { + "epoch": 0.7, + "learning_rate": 4.2326082351545025e-06, + "loss": 0.4716, + "step": 8266 + }, + { + "epoch": 0.7, + "learning_rate": 4.230352428303886e-06, + "loss": 0.4519, + "step": 8267 + }, + { + "epoch": 0.7, + "learning_rate": 4.228097061470672e-06, + "loss": 0.4408, + "step": 8268 + }, + { + "epoch": 0.71, + "learning_rate": 4.225842134826876e-06, + "loss": 0.4757, + "step": 8269 + }, + { + "epoch": 0.71, + "learning_rate": 4.223587648544471e-06, + "loss": 0.4578, + "step": 8270 + }, + { + "epoch": 0.71, + "learning_rate": 4.221333602795382e-06, + "loss": 0.4442, + "step": 8271 + }, + { + "epoch": 0.71, + "learning_rate": 4.219079997751515e-06, + "loss": 0.4486, + "step": 8272 + }, + { + "epoch": 0.71, + "learning_rate": 4.216826833584749e-06, + "loss": 0.4764, + "step": 8273 + }, + { + "epoch": 0.71, + "learning_rate": 4.214574110466909e-06, + "loss": 0.4755, + "step": 8274 + }, + { + "epoch": 0.71, + "learning_rate": 4.212321828569801e-06, + "loss": 0.4643, + "step": 8275 + }, + { + "epoch": 0.71, + "learning_rate": 4.210069988065197e-06, + "loss": 0.4737, + "step": 8276 + }, + { + "epoch": 0.71, + "learning_rate": 4.207818589124821e-06, + "loss": 0.4458, + "step": 8277 + }, + { + "epoch": 0.71, + "learning_rate": 4.2055676319203835e-06, + "loss": 0.4476, + "step": 8278 + }, + { + "epoch": 0.71, + "learning_rate": 4.203317116623553e-06, + "loss": 0.4696, + "step": 8279 + }, + { + "epoch": 0.71, + "learning_rate": 4.201067043405956e-06, + "loss": 0.4757, + "step": 8280 + }, + { + "epoch": 0.71, + "learning_rate": 4.198817412439194e-06, + "loss": 0.4597, + "step": 8281 + }, + { + "epoch": 0.71, + "learning_rate": 4.196568223894841e-06, + "loss": 0.4493, + "step": 8282 + }, + { + "epoch": 0.71, + "learning_rate": 4.1943194779444215e-06, + "loss": 0.471, + "step": 8283 + }, + { + "epoch": 0.71, + "learning_rate": 4.192071174759435e-06, + "loss": 0.4721, + "step": 8284 + }, + { + "epoch": 0.71, + "learning_rate": 4.1898233145113535e-06, + "loss": 0.4967, + "step": 8285 + }, + { + "epoch": 0.71, + "learning_rate": 4.1875758973715955e-06, + "loss": 0.4438, + "step": 8286 + }, + { + "epoch": 0.71, + "learning_rate": 4.185328923511568e-06, + "loss": 0.4577, + "step": 8287 + }, + { + "epoch": 0.71, + "learning_rate": 4.1830823931026365e-06, + "loss": 0.4686, + "step": 8288 + }, + { + "epoch": 0.71, + "learning_rate": 4.180836306316123e-06, + "loss": 0.4635, + "step": 8289 + }, + { + "epoch": 0.71, + "learning_rate": 4.178590663323323e-06, + "loss": 0.4602, + "step": 8290 + }, + { + "epoch": 0.71, + "learning_rate": 4.17634546429551e-06, + "loss": 0.4607, + "step": 8291 + }, + { + "epoch": 0.71, + "learning_rate": 4.174100709403902e-06, + "loss": 0.4646, + "step": 8292 + }, + { + "epoch": 0.71, + "learning_rate": 4.171856398819696e-06, + "loss": 0.4559, + "step": 8293 + }, + { + "epoch": 0.71, + "learning_rate": 4.169612532714052e-06, + "loss": 0.461, + "step": 8294 + }, + { + "epoch": 0.71, + "learning_rate": 4.167369111258098e-06, + "loss": 0.4686, + "step": 8295 + }, + { + "epoch": 0.71, + "learning_rate": 4.165126134622927e-06, + "loss": 0.468, + "step": 8296 + }, + { + "epoch": 0.71, + "learning_rate": 4.1628836029795995e-06, + "loss": 0.4625, + "step": 8297 + }, + { + "epoch": 0.71, + "learning_rate": 4.160641516499134e-06, + "loss": 0.4572, + "step": 8298 + }, + { + "epoch": 0.71, + "learning_rate": 4.158399875352525e-06, + "loss": 0.4628, + "step": 8299 + }, + { + "epoch": 0.71, + "learning_rate": 4.15615867971073e-06, + "loss": 0.4464, + "step": 8300 + }, + { + "epoch": 0.71, + "learning_rate": 4.153917929744671e-06, + "loss": 0.4625, + "step": 8301 + }, + { + "epoch": 0.71, + "learning_rate": 4.151677625625237e-06, + "loss": 0.4759, + "step": 8302 + }, + { + "epoch": 0.71, + "learning_rate": 4.149437767523284e-06, + "loss": 0.4625, + "step": 8303 + }, + { + "epoch": 0.71, + "learning_rate": 4.1471983556096316e-06, + "loss": 0.4569, + "step": 8304 + }, + { + "epoch": 0.71, + "learning_rate": 4.1449593900550686e-06, + "loss": 0.4452, + "step": 8305 + }, + { + "epoch": 0.71, + "learning_rate": 4.142720871030349e-06, + "loss": 0.4733, + "step": 8306 + }, + { + "epoch": 0.71, + "learning_rate": 4.140482798706186e-06, + "loss": 0.4471, + "step": 8307 + }, + { + "epoch": 0.71, + "learning_rate": 4.138245173253267e-06, + "loss": 0.4656, + "step": 8308 + }, + { + "epoch": 0.71, + "learning_rate": 4.136007994842244e-06, + "loss": 0.459, + "step": 8309 + }, + { + "epoch": 0.71, + "learning_rate": 4.133771263643732e-06, + "loss": 0.4702, + "step": 8310 + }, + { + "epoch": 0.71, + "learning_rate": 4.1315349798283145e-06, + "loss": 0.468, + "step": 8311 + }, + { + "epoch": 0.71, + "learning_rate": 4.129299143566538e-06, + "loss": 0.4627, + "step": 8312 + }, + { + "epoch": 0.71, + "learning_rate": 4.127063755028921e-06, + "loss": 0.456, + "step": 8313 + }, + { + "epoch": 0.71, + "learning_rate": 4.124828814385939e-06, + "loss": 0.4722, + "step": 8314 + }, + { + "epoch": 0.71, + "learning_rate": 4.122594321808044e-06, + "loss": 0.4567, + "step": 8315 + }, + { + "epoch": 0.71, + "learning_rate": 4.1203602774656405e-06, + "loss": 0.4587, + "step": 8316 + }, + { + "epoch": 0.71, + "learning_rate": 4.118126681529108e-06, + "loss": 0.4616, + "step": 8317 + }, + { + "epoch": 0.71, + "learning_rate": 4.115893534168791e-06, + "loss": 0.4709, + "step": 8318 + }, + { + "epoch": 0.71, + "learning_rate": 4.113660835554998e-06, + "loss": 0.4676, + "step": 8319 + }, + { + "epoch": 0.71, + "learning_rate": 4.111428585858005e-06, + "loss": 0.4577, + "step": 8320 + }, + { + "epoch": 0.71, + "learning_rate": 4.109196785248052e-06, + "loss": 0.4632, + "step": 8321 + }, + { + "epoch": 0.71, + "learning_rate": 4.106965433895349e-06, + "loss": 0.4804, + "step": 8322 + }, + { + "epoch": 0.71, + "learning_rate": 4.104734531970058e-06, + "loss": 0.4549, + "step": 8323 + }, + { + "epoch": 0.71, + "learning_rate": 4.10250407964233e-06, + "loss": 0.4712, + "step": 8324 + }, + { + "epoch": 0.71, + "learning_rate": 4.100274077082259e-06, + "loss": 0.4649, + "step": 8325 + }, + { + "epoch": 0.71, + "learning_rate": 4.0980445244599174e-06, + "loss": 0.4892, + "step": 8326 + }, + { + "epoch": 0.71, + "learning_rate": 4.09581542194534e-06, + "loss": 0.4664, + "step": 8327 + }, + { + "epoch": 0.71, + "learning_rate": 4.0935867697085285e-06, + "loss": 0.4757, + "step": 8328 + }, + { + "epoch": 0.71, + "learning_rate": 4.091358567919449e-06, + "loss": 0.4825, + "step": 8329 + }, + { + "epoch": 0.71, + "learning_rate": 4.089130816748031e-06, + "loss": 0.4659, + "step": 8330 + }, + { + "epoch": 0.71, + "learning_rate": 4.086903516364179e-06, + "loss": 0.4628, + "step": 8331 + }, + { + "epoch": 0.71, + "learning_rate": 4.084676666937745e-06, + "loss": 0.4713, + "step": 8332 + }, + { + "epoch": 0.71, + "learning_rate": 4.0824502686385696e-06, + "loss": 0.4427, + "step": 8333 + }, + { + "epoch": 0.71, + "learning_rate": 4.080224321636438e-06, + "loss": 0.4829, + "step": 8334 + }, + { + "epoch": 0.71, + "learning_rate": 4.077998826101115e-06, + "loss": 0.4551, + "step": 8335 + }, + { + "epoch": 0.71, + "learning_rate": 4.075773782202325e-06, + "loss": 0.4902, + "step": 8336 + }, + { + "epoch": 0.71, + "learning_rate": 4.073549190109759e-06, + "loss": 0.4636, + "step": 8337 + }, + { + "epoch": 0.71, + "learning_rate": 4.071325049993073e-06, + "loss": 0.457, + "step": 8338 + }, + { + "epoch": 0.71, + "learning_rate": 4.069101362021893e-06, + "loss": 0.4552, + "step": 8339 + }, + { + "epoch": 0.71, + "learning_rate": 4.066878126365804e-06, + "loss": 0.4619, + "step": 8340 + }, + { + "epoch": 0.71, + "learning_rate": 4.064655343194354e-06, + "loss": 0.4779, + "step": 8341 + }, + { + "epoch": 0.71, + "learning_rate": 4.062433012677074e-06, + "loss": 0.4646, + "step": 8342 + }, + { + "epoch": 0.71, + "learning_rate": 4.060211134983437e-06, + "loss": 0.4816, + "step": 8343 + }, + { + "epoch": 0.71, + "learning_rate": 4.057989710282897e-06, + "loss": 0.4757, + "step": 8344 + }, + { + "epoch": 0.71, + "learning_rate": 4.055768738744868e-06, + "loss": 0.4668, + "step": 8345 + }, + { + "epoch": 0.71, + "learning_rate": 4.053548220538732e-06, + "loss": 0.4774, + "step": 8346 + }, + { + "epoch": 0.71, + "learning_rate": 4.051328155833835e-06, + "loss": 0.4591, + "step": 8347 + }, + { + "epoch": 0.71, + "learning_rate": 4.049108544799487e-06, + "loss": 0.4415, + "step": 8348 + }, + { + "epoch": 0.71, + "learning_rate": 4.046889387604969e-06, + "loss": 0.4706, + "step": 8349 + }, + { + "epoch": 0.71, + "learning_rate": 4.044670684419513e-06, + "loss": 0.4648, + "step": 8350 + }, + { + "epoch": 0.71, + "learning_rate": 4.0424524354123375e-06, + "loss": 0.4628, + "step": 8351 + }, + { + "epoch": 0.71, + "learning_rate": 4.0402346407526135e-06, + "loss": 0.4473, + "step": 8352 + }, + { + "epoch": 0.71, + "learning_rate": 4.038017300609475e-06, + "loss": 0.4594, + "step": 8353 + }, + { + "epoch": 0.71, + "learning_rate": 4.035800415152027e-06, + "loss": 0.4624, + "step": 8354 + }, + { + "epoch": 0.71, + "learning_rate": 4.033583984549338e-06, + "loss": 0.445, + "step": 8355 + }, + { + "epoch": 0.71, + "learning_rate": 4.031368008970446e-06, + "loss": 0.4601, + "step": 8356 + }, + { + "epoch": 0.71, + "learning_rate": 4.029152488584346e-06, + "loss": 0.4663, + "step": 8357 + }, + { + "epoch": 0.71, + "learning_rate": 4.026937423560008e-06, + "loss": 0.4652, + "step": 8358 + }, + { + "epoch": 0.71, + "learning_rate": 4.024722814066353e-06, + "loss": 0.4519, + "step": 8359 + }, + { + "epoch": 0.71, + "learning_rate": 4.022508660272285e-06, + "loss": 0.4469, + "step": 8360 + }, + { + "epoch": 0.71, + "learning_rate": 4.020294962346666e-06, + "loss": 0.4816, + "step": 8361 + }, + { + "epoch": 0.71, + "learning_rate": 4.018081720458314e-06, + "loss": 0.4473, + "step": 8362 + }, + { + "epoch": 0.71, + "learning_rate": 4.015868934776023e-06, + "loss": 0.4895, + "step": 8363 + }, + { + "epoch": 0.71, + "learning_rate": 4.013656605468551e-06, + "loss": 0.467, + "step": 8364 + }, + { + "epoch": 0.71, + "learning_rate": 4.011444732704618e-06, + "loss": 0.4525, + "step": 8365 + }, + { + "epoch": 0.71, + "learning_rate": 4.009233316652911e-06, + "loss": 0.4818, + "step": 8366 + }, + { + "epoch": 0.71, + "learning_rate": 4.007022357482086e-06, + "loss": 0.4642, + "step": 8367 + }, + { + "epoch": 0.71, + "learning_rate": 4.0048118553607485e-06, + "loss": 0.4413, + "step": 8368 + }, + { + "epoch": 0.71, + "learning_rate": 4.002601810457492e-06, + "loss": 0.4669, + "step": 8369 + }, + { + "epoch": 0.71, + "learning_rate": 4.000392222940863e-06, + "loss": 0.4704, + "step": 8370 + }, + { + "epoch": 0.71, + "learning_rate": 3.998183092979368e-06, + "loss": 0.4707, + "step": 8371 + }, + { + "epoch": 0.71, + "learning_rate": 3.995974420741485e-06, + "loss": 0.4503, + "step": 8372 + }, + { + "epoch": 0.71, + "learning_rate": 3.99376620639566e-06, + "loss": 0.4791, + "step": 8373 + }, + { + "epoch": 0.71, + "learning_rate": 3.9915584501103e-06, + "loss": 0.4555, + "step": 8374 + }, + { + "epoch": 0.71, + "learning_rate": 3.9893511520537766e-06, + "loss": 0.4623, + "step": 8375 + }, + { + "epoch": 0.71, + "learning_rate": 3.987144312394432e-06, + "loss": 0.4503, + "step": 8376 + }, + { + "epoch": 0.71, + "learning_rate": 3.9849379313005605e-06, + "loss": 0.4463, + "step": 8377 + }, + { + "epoch": 0.71, + "learning_rate": 3.982732008940432e-06, + "loss": 0.466, + "step": 8378 + }, + { + "epoch": 0.71, + "learning_rate": 3.980526545482288e-06, + "loss": 0.4701, + "step": 8379 + }, + { + "epoch": 0.71, + "learning_rate": 3.978321541094318e-06, + "loss": 0.4727, + "step": 8380 + }, + { + "epoch": 0.71, + "learning_rate": 3.9761169959446855e-06, + "loss": 0.458, + "step": 8381 + }, + { + "epoch": 0.71, + "learning_rate": 3.973912910201521e-06, + "loss": 0.447, + "step": 8382 + }, + { + "epoch": 0.71, + "learning_rate": 3.9717092840329155e-06, + "loss": 0.4711, + "step": 8383 + }, + { + "epoch": 0.71, + "learning_rate": 3.969506117606927e-06, + "loss": 0.4494, + "step": 8384 + }, + { + "epoch": 0.71, + "learning_rate": 3.967303411091582e-06, + "loss": 0.4513, + "step": 8385 + }, + { + "epoch": 0.72, + "learning_rate": 3.965101164654862e-06, + "loss": 0.4885, + "step": 8386 + }, + { + "epoch": 0.72, + "learning_rate": 3.9628993784647186e-06, + "loss": 0.4463, + "step": 8387 + }, + { + "epoch": 0.72, + "learning_rate": 3.960698052689079e-06, + "loss": 0.4665, + "step": 8388 + }, + { + "epoch": 0.72, + "learning_rate": 3.958497187495815e-06, + "loss": 0.4819, + "step": 8389 + }, + { + "epoch": 0.72, + "learning_rate": 3.95629678305278e-06, + "loss": 0.4493, + "step": 8390 + }, + { + "epoch": 0.72, + "learning_rate": 3.954096839527784e-06, + "loss": 0.4862, + "step": 8391 + }, + { + "epoch": 0.72, + "learning_rate": 3.951897357088602e-06, + "loss": 0.4705, + "step": 8392 + }, + { + "epoch": 0.72, + "learning_rate": 3.9496983359029795e-06, + "loss": 0.4689, + "step": 8393 + }, + { + "epoch": 0.72, + "learning_rate": 3.947499776138624e-06, + "loss": 0.4579, + "step": 8394 + }, + { + "epoch": 0.72, + "learning_rate": 3.9453016779631995e-06, + "loss": 0.4646, + "step": 8395 + }, + { + "epoch": 0.72, + "learning_rate": 3.943104041544344e-06, + "loss": 0.4612, + "step": 8396 + }, + { + "epoch": 0.72, + "learning_rate": 3.940906867049668e-06, + "loss": 0.4738, + "step": 8397 + }, + { + "epoch": 0.72, + "learning_rate": 3.938710154646727e-06, + "loss": 0.4753, + "step": 8398 + }, + { + "epoch": 0.72, + "learning_rate": 3.9365139045030545e-06, + "loss": 0.4556, + "step": 8399 + }, + { + "epoch": 0.72, + "learning_rate": 3.934318116786149e-06, + "loss": 0.4746, + "step": 8400 + }, + { + "epoch": 0.72, + "learning_rate": 3.932122791663461e-06, + "loss": 0.4565, + "step": 8401 + }, + { + "epoch": 0.72, + "learning_rate": 3.929927929302425e-06, + "loss": 0.4575, + "step": 8402 + }, + { + "epoch": 0.72, + "learning_rate": 3.92773352987043e-06, + "loss": 0.4751, + "step": 8403 + }, + { + "epoch": 0.72, + "learning_rate": 3.925539593534824e-06, + "loss": 0.4472, + "step": 8404 + }, + { + "epoch": 0.72, + "learning_rate": 3.923346120462925e-06, + "loss": 0.4448, + "step": 8405 + }, + { + "epoch": 0.72, + "learning_rate": 3.921153110822027e-06, + "loss": 0.4315, + "step": 8406 + }, + { + "epoch": 0.72, + "learning_rate": 3.918960564779368e-06, + "loss": 0.4484, + "step": 8407 + }, + { + "epoch": 0.72, + "learning_rate": 3.916768482502164e-06, + "loss": 0.4536, + "step": 8408 + }, + { + "epoch": 0.72, + "learning_rate": 3.914576864157594e-06, + "loss": 0.4606, + "step": 8409 + }, + { + "epoch": 0.72, + "learning_rate": 3.912385709912794e-06, + "loss": 0.4524, + "step": 8410 + }, + { + "epoch": 0.72, + "learning_rate": 3.910195019934876e-06, + "loss": 0.4387, + "step": 8411 + }, + { + "epoch": 0.72, + "learning_rate": 3.908004794390915e-06, + "loss": 0.4759, + "step": 8412 + }, + { + "epoch": 0.72, + "learning_rate": 3.905815033447937e-06, + "loss": 0.4725, + "step": 8413 + }, + { + "epoch": 0.72, + "learning_rate": 3.903625737272944e-06, + "loss": 0.4551, + "step": 8414 + }, + { + "epoch": 0.72, + "learning_rate": 3.901436906032912e-06, + "loss": 0.4651, + "step": 8415 + }, + { + "epoch": 0.72, + "learning_rate": 3.899248539894756e-06, + "loss": 0.4667, + "step": 8416 + }, + { + "epoch": 0.72, + "learning_rate": 3.897060639025378e-06, + "loss": 0.4415, + "step": 8417 + }, + { + "epoch": 0.72, + "learning_rate": 3.894873203591639e-06, + "loss": 0.4789, + "step": 8418 + }, + { + "epoch": 0.72, + "learning_rate": 3.89268623376035e-06, + "loss": 0.4933, + "step": 8419 + }, + { + "epoch": 0.72, + "learning_rate": 3.89049972969831e-06, + "loss": 0.4612, + "step": 8420 + }, + { + "epoch": 0.72, + "learning_rate": 3.8883136915722685e-06, + "loss": 0.4432, + "step": 8421 + }, + { + "epoch": 0.72, + "learning_rate": 3.886128119548938e-06, + "loss": 0.4762, + "step": 8422 + }, + { + "epoch": 0.72, + "learning_rate": 3.883943013795e-06, + "loss": 0.4733, + "step": 8423 + }, + { + "epoch": 0.72, + "learning_rate": 3.8817583744771055e-06, + "loss": 0.4481, + "step": 8424 + }, + { + "epoch": 0.72, + "learning_rate": 3.879574201761859e-06, + "loss": 0.4835, + "step": 8425 + }, + { + "epoch": 0.72, + "learning_rate": 3.8773904958158345e-06, + "loss": 0.4849, + "step": 8426 + }, + { + "epoch": 0.72, + "learning_rate": 3.8752072568055764e-06, + "loss": 0.4541, + "step": 8427 + }, + { + "epoch": 0.72, + "learning_rate": 3.8730244848975766e-06, + "loss": 0.4439, + "step": 8428 + }, + { + "epoch": 0.72, + "learning_rate": 3.8708421802583116e-06, + "loss": 0.4501, + "step": 8429 + }, + { + "epoch": 0.72, + "learning_rate": 3.868660343054213e-06, + "loss": 0.4497, + "step": 8430 + }, + { + "epoch": 0.72, + "learning_rate": 3.866478973451673e-06, + "loss": 0.4718, + "step": 8431 + }, + { + "epoch": 0.72, + "learning_rate": 3.864298071617051e-06, + "loss": 0.4799, + "step": 8432 + }, + { + "epoch": 0.72, + "learning_rate": 3.862117637716675e-06, + "loss": 0.448, + "step": 8433 + }, + { + "epoch": 0.72, + "learning_rate": 3.859937671916833e-06, + "loss": 0.4655, + "step": 8434 + }, + { + "epoch": 0.72, + "learning_rate": 3.857758174383777e-06, + "loss": 0.4832, + "step": 8435 + }, + { + "epoch": 0.72, + "learning_rate": 3.85557914528373e-06, + "loss": 0.476, + "step": 8436 + }, + { + "epoch": 0.72, + "learning_rate": 3.853400584782862e-06, + "loss": 0.4486, + "step": 8437 + }, + { + "epoch": 0.72, + "learning_rate": 3.851222493047331e-06, + "loss": 0.4583, + "step": 8438 + }, + { + "epoch": 0.72, + "learning_rate": 3.849044870243246e-06, + "loss": 0.4501, + "step": 8439 + }, + { + "epoch": 0.72, + "learning_rate": 3.846867716536676e-06, + "loss": 0.4596, + "step": 8440 + }, + { + "epoch": 0.72, + "learning_rate": 3.844691032093662e-06, + "loss": 0.45, + "step": 8441 + }, + { + "epoch": 0.72, + "learning_rate": 3.842514817080206e-06, + "loss": 0.4652, + "step": 8442 + }, + { + "epoch": 0.72, + "learning_rate": 3.840339071662279e-06, + "loss": 0.4446, + "step": 8443 + }, + { + "epoch": 0.72, + "learning_rate": 3.838163796005809e-06, + "loss": 0.4673, + "step": 8444 + }, + { + "epoch": 0.72, + "learning_rate": 3.835988990276696e-06, + "loss": 0.4593, + "step": 8445 + }, + { + "epoch": 0.72, + "learning_rate": 3.83381465464079e-06, + "loss": 0.4701, + "step": 8446 + }, + { + "epoch": 0.72, + "learning_rate": 3.8316407892639265e-06, + "loss": 0.4671, + "step": 8447 + }, + { + "epoch": 0.72, + "learning_rate": 3.82946739431189e-06, + "loss": 0.4653, + "step": 8448 + }, + { + "epoch": 0.72, + "learning_rate": 3.8272944699504285e-06, + "loss": 0.4563, + "step": 8449 + }, + { + "epoch": 0.72, + "learning_rate": 3.825122016345261e-06, + "loss": 0.4512, + "step": 8450 + }, + { + "epoch": 0.72, + "learning_rate": 3.822950033662068e-06, + "loss": 0.4632, + "step": 8451 + }, + { + "epoch": 0.72, + "learning_rate": 3.8207785220664935e-06, + "loss": 0.4486, + "step": 8452 + }, + { + "epoch": 0.72, + "learning_rate": 3.818607481724147e-06, + "loss": 0.4607, + "step": 8453 + }, + { + "epoch": 0.72, + "learning_rate": 3.816436912800603e-06, + "loss": 0.4636, + "step": 8454 + }, + { + "epoch": 0.72, + "learning_rate": 3.8142668154613925e-06, + "loss": 0.4596, + "step": 8455 + }, + { + "epoch": 0.72, + "learning_rate": 3.812097189872016e-06, + "loss": 0.4554, + "step": 8456 + }, + { + "epoch": 0.72, + "learning_rate": 3.8099280361979484e-06, + "loss": 0.4619, + "step": 8457 + }, + { + "epoch": 0.72, + "learning_rate": 3.8077593546046087e-06, + "loss": 0.4573, + "step": 8458 + }, + { + "epoch": 0.72, + "learning_rate": 3.8055911452573913e-06, + "loss": 0.4287, + "step": 8459 + }, + { + "epoch": 0.72, + "learning_rate": 3.803423408321655e-06, + "loss": 0.4613, + "step": 8460 + }, + { + "epoch": 0.72, + "learning_rate": 3.801256143962719e-06, + "loss": 0.4817, + "step": 8461 + }, + { + "epoch": 0.72, + "learning_rate": 3.7990893523458682e-06, + "loss": 0.4501, + "step": 8462 + }, + { + "epoch": 0.72, + "learning_rate": 3.796923033636356e-06, + "loss": 0.4502, + "step": 8463 + }, + { + "epoch": 0.72, + "learning_rate": 3.794757187999386e-06, + "loss": 0.4691, + "step": 8464 + }, + { + "epoch": 0.72, + "learning_rate": 3.792591815600135e-06, + "loss": 0.4806, + "step": 8465 + }, + { + "epoch": 0.72, + "learning_rate": 3.7904269166037553e-06, + "loss": 0.4361, + "step": 8466 + }, + { + "epoch": 0.72, + "learning_rate": 3.7882624911753386e-06, + "loss": 0.4667, + "step": 8467 + }, + { + "epoch": 0.72, + "learning_rate": 3.786098539479959e-06, + "loss": 0.4574, + "step": 8468 + }, + { + "epoch": 0.72, + "learning_rate": 3.7839350616826454e-06, + "loss": 0.4634, + "step": 8469 + }, + { + "epoch": 0.72, + "learning_rate": 3.7817720579483962e-06, + "loss": 0.4614, + "step": 8470 + }, + { + "epoch": 0.72, + "learning_rate": 3.77960952844217e-06, + "loss": 0.4749, + "step": 8471 + }, + { + "epoch": 0.72, + "learning_rate": 3.7774474733288904e-06, + "loss": 0.4883, + "step": 8472 + }, + { + "epoch": 0.72, + "learning_rate": 3.7752858927734492e-06, + "loss": 0.4655, + "step": 8473 + }, + { + "epoch": 0.72, + "learning_rate": 3.773124786940685e-06, + "loss": 0.474, + "step": 8474 + }, + { + "epoch": 0.72, + "learning_rate": 3.770964155995428e-06, + "loss": 0.4605, + "step": 8475 + }, + { + "epoch": 0.72, + "learning_rate": 3.7688040001024473e-06, + "loss": 0.4522, + "step": 8476 + }, + { + "epoch": 0.72, + "learning_rate": 3.766644319426488e-06, + "loss": 0.445, + "step": 8477 + }, + { + "epoch": 0.72, + "learning_rate": 3.764485114132256e-06, + "loss": 0.4799, + "step": 8478 + }, + { + "epoch": 0.72, + "learning_rate": 3.7623263843844216e-06, + "loss": 0.461, + "step": 8479 + }, + { + "epoch": 0.72, + "learning_rate": 3.760168130347619e-06, + "loss": 0.4788, + "step": 8480 + }, + { + "epoch": 0.72, + "learning_rate": 3.7580103521864444e-06, + "loss": 0.4642, + "step": 8481 + }, + { + "epoch": 0.72, + "learning_rate": 3.7558530500654643e-06, + "loss": 0.4548, + "step": 8482 + }, + { + "epoch": 0.72, + "learning_rate": 3.7536962241491913e-06, + "loss": 0.4469, + "step": 8483 + }, + { + "epoch": 0.72, + "learning_rate": 3.751539874602129e-06, + "loss": 0.4592, + "step": 8484 + }, + { + "epoch": 0.72, + "learning_rate": 3.7493840015887196e-06, + "loss": 0.4599, + "step": 8485 + }, + { + "epoch": 0.72, + "learning_rate": 3.747228605273381e-06, + "loss": 0.452, + "step": 8486 + }, + { + "epoch": 0.72, + "learning_rate": 3.745073685820494e-06, + "loss": 0.478, + "step": 8487 + }, + { + "epoch": 0.72, + "learning_rate": 3.7429192433944016e-06, + "loss": 0.4648, + "step": 8488 + }, + { + "epoch": 0.72, + "learning_rate": 3.7407652781594094e-06, + "loss": 0.4532, + "step": 8489 + }, + { + "epoch": 0.72, + "learning_rate": 3.7386117902797892e-06, + "loss": 0.4692, + "step": 8490 + }, + { + "epoch": 0.72, + "learning_rate": 3.736458779919777e-06, + "loss": 0.4503, + "step": 8491 + }, + { + "epoch": 0.72, + "learning_rate": 3.734306247243562e-06, + "loss": 0.4537, + "step": 8492 + }, + { + "epoch": 0.72, + "learning_rate": 3.732154192415317e-06, + "loss": 0.4524, + "step": 8493 + }, + { + "epoch": 0.72, + "learning_rate": 3.7300026155991574e-06, + "loss": 0.4773, + "step": 8494 + }, + { + "epoch": 0.72, + "learning_rate": 3.7278515169591757e-06, + "loss": 0.4469, + "step": 8495 + }, + { + "epoch": 0.72, + "learning_rate": 3.725700896659422e-06, + "loss": 0.4772, + "step": 8496 + }, + { + "epoch": 0.72, + "learning_rate": 3.7235507548639127e-06, + "loss": 0.4719, + "step": 8497 + }, + { + "epoch": 0.72, + "learning_rate": 3.721401091736626e-06, + "loss": 0.4762, + "step": 8498 + }, + { + "epoch": 0.72, + "learning_rate": 3.7192519074415035e-06, + "loss": 0.4598, + "step": 8499 + }, + { + "epoch": 0.72, + "learning_rate": 3.717103202142457e-06, + "loss": 0.45, + "step": 8500 + }, + { + "epoch": 0.72, + "learning_rate": 3.714954976003342e-06, + "loss": 0.456, + "step": 8501 + }, + { + "epoch": 0.72, + "learning_rate": 3.712807229188008e-06, + "loss": 0.4442, + "step": 8502 + }, + { + "epoch": 0.73, + "learning_rate": 3.710659961860239e-06, + "loss": 0.466, + "step": 8503 + }, + { + "epoch": 0.73, + "learning_rate": 3.708513174183799e-06, + "loss": 0.4452, + "step": 8504 + }, + { + "epoch": 0.73, + "learning_rate": 3.7063668663224096e-06, + "loss": 0.4398, + "step": 8505 + }, + { + "epoch": 0.73, + "learning_rate": 3.704221038439759e-06, + "loss": 0.4685, + "step": 8506 + }, + { + "epoch": 0.73, + "learning_rate": 3.702075690699496e-06, + "loss": 0.4496, + "step": 8507 + }, + { + "epoch": 0.73, + "learning_rate": 3.699930823265233e-06, + "loss": 0.4598, + "step": 8508 + }, + { + "epoch": 0.73, + "learning_rate": 3.697786436300552e-06, + "loss": 0.4676, + "step": 8509 + }, + { + "epoch": 0.73, + "learning_rate": 3.6956425299689848e-06, + "loss": 0.4992, + "step": 8510 + }, + { + "epoch": 0.73, + "learning_rate": 3.6934991044340375e-06, + "loss": 0.4589, + "step": 8511 + }, + { + "epoch": 0.73, + "learning_rate": 3.6913561598591775e-06, + "loss": 0.4742, + "step": 8512 + }, + { + "epoch": 0.73, + "learning_rate": 3.689213696407834e-06, + "loss": 0.4788, + "step": 8513 + }, + { + "epoch": 0.73, + "learning_rate": 3.687071714243402e-06, + "loss": 0.4493, + "step": 8514 + }, + { + "epoch": 0.73, + "learning_rate": 3.6849302135292354e-06, + "loss": 0.4863, + "step": 8515 + }, + { + "epoch": 0.73, + "learning_rate": 3.6827891944286564e-06, + "loss": 0.4543, + "step": 8516 + }, + { + "epoch": 0.73, + "learning_rate": 3.680648657104946e-06, + "loss": 0.4791, + "step": 8517 + }, + { + "epoch": 0.73, + "learning_rate": 3.6785086017213555e-06, + "loss": 0.4495, + "step": 8518 + }, + { + "epoch": 0.73, + "learning_rate": 3.676369028441088e-06, + "loss": 0.4689, + "step": 8519 + }, + { + "epoch": 0.73, + "learning_rate": 3.674229937427317e-06, + "loss": 0.4696, + "step": 8520 + }, + { + "epoch": 0.73, + "learning_rate": 3.6720913288431813e-06, + "loss": 0.4558, + "step": 8521 + }, + { + "epoch": 0.73, + "learning_rate": 3.669953202851779e-06, + "loss": 0.4612, + "step": 8522 + }, + { + "epoch": 0.73, + "learning_rate": 3.6678155596161725e-06, + "loss": 0.469, + "step": 8523 + }, + { + "epoch": 0.73, + "learning_rate": 3.6656783992993885e-06, + "loss": 0.4486, + "step": 8524 + }, + { + "epoch": 0.73, + "learning_rate": 3.663541722064413e-06, + "loss": 0.4529, + "step": 8525 + }, + { + "epoch": 0.73, + "learning_rate": 3.6614055280742013e-06, + "loss": 0.467, + "step": 8526 + }, + { + "epoch": 0.73, + "learning_rate": 3.6592698174916687e-06, + "loss": 0.4655, + "step": 8527 + }, + { + "epoch": 0.73, + "learning_rate": 3.6571345904796896e-06, + "loss": 0.4464, + "step": 8528 + }, + { + "epoch": 0.73, + "learning_rate": 3.6549998472011027e-06, + "loss": 0.462, + "step": 8529 + }, + { + "epoch": 0.73, + "learning_rate": 3.6528655878187247e-06, + "loss": 0.4643, + "step": 8530 + }, + { + "epoch": 0.73, + "learning_rate": 3.6507318124953117e-06, + "loss": 0.4445, + "step": 8531 + }, + { + "epoch": 0.73, + "learning_rate": 3.648598521393598e-06, + "loss": 0.4493, + "step": 8532 + }, + { + "epoch": 0.73, + "learning_rate": 3.6464657146762805e-06, + "loss": 0.4809, + "step": 8533 + }, + { + "epoch": 0.73, + "learning_rate": 3.6443333925060065e-06, + "loss": 0.4414, + "step": 8534 + }, + { + "epoch": 0.73, + "learning_rate": 3.6422015550454046e-06, + "loss": 0.4437, + "step": 8535 + }, + { + "epoch": 0.73, + "learning_rate": 3.64007020245706e-06, + "loss": 0.473, + "step": 8536 + }, + { + "epoch": 0.73, + "learning_rate": 3.63793933490351e-06, + "loss": 0.4452, + "step": 8537 + }, + { + "epoch": 0.73, + "learning_rate": 3.6358089525472628e-06, + "loss": 0.4611, + "step": 8538 + }, + { + "epoch": 0.73, + "learning_rate": 3.6336790555508018e-06, + "loss": 0.4569, + "step": 8539 + }, + { + "epoch": 0.73, + "learning_rate": 3.631549644076552e-06, + "loss": 0.4523, + "step": 8540 + }, + { + "epoch": 0.73, + "learning_rate": 3.6294207182869124e-06, + "loss": 0.4494, + "step": 8541 + }, + { + "epoch": 0.73, + "learning_rate": 3.62729227834425e-06, + "loss": 0.4539, + "step": 8542 + }, + { + "epoch": 0.73, + "learning_rate": 3.625164324410876e-06, + "loss": 0.4922, + "step": 8543 + }, + { + "epoch": 0.73, + "learning_rate": 3.6230368566490883e-06, + "loss": 0.4539, + "step": 8544 + }, + { + "epoch": 0.73, + "learning_rate": 3.6209098752211356e-06, + "loss": 0.4739, + "step": 8545 + }, + { + "epoch": 0.73, + "learning_rate": 3.618783380289226e-06, + "loss": 0.4642, + "step": 8546 + }, + { + "epoch": 0.73, + "learning_rate": 3.6166573720155316e-06, + "loss": 0.4785, + "step": 8547 + }, + { + "epoch": 0.73, + "learning_rate": 3.614531850562203e-06, + "loss": 0.4535, + "step": 8548 + }, + { + "epoch": 0.73, + "learning_rate": 3.6124068160913306e-06, + "loss": 0.4585, + "step": 8549 + }, + { + "epoch": 0.73, + "learning_rate": 3.610282268764983e-06, + "loss": 0.4533, + "step": 8550 + }, + { + "epoch": 0.73, + "learning_rate": 3.608158208745187e-06, + "loss": 0.4622, + "step": 8551 + }, + { + "epoch": 0.73, + "learning_rate": 3.606034636193926e-06, + "loss": 0.4734, + "step": 8552 + }, + { + "epoch": 0.73, + "learning_rate": 3.6039115512731605e-06, + "loss": 0.4515, + "step": 8553 + }, + { + "epoch": 0.73, + "learning_rate": 3.601788954144807e-06, + "loss": 0.4747, + "step": 8554 + }, + { + "epoch": 0.73, + "learning_rate": 3.599666844970735e-06, + "loss": 0.4588, + "step": 8555 + }, + { + "epoch": 0.73, + "learning_rate": 3.5975452239127916e-06, + "loss": 0.4736, + "step": 8556 + }, + { + "epoch": 0.73, + "learning_rate": 3.5954240911327777e-06, + "loss": 0.4649, + "step": 8557 + }, + { + "epoch": 0.73, + "learning_rate": 3.593303446792461e-06, + "loss": 0.4619, + "step": 8558 + }, + { + "epoch": 0.73, + "learning_rate": 3.5911832910535703e-06, + "loss": 0.4636, + "step": 8559 + }, + { + "epoch": 0.73, + "learning_rate": 3.589063624077802e-06, + "loss": 0.458, + "step": 8560 + }, + { + "epoch": 0.73, + "learning_rate": 3.5869444460268e-06, + "loss": 0.467, + "step": 8561 + }, + { + "epoch": 0.73, + "learning_rate": 3.58482575706219e-06, + "loss": 0.4456, + "step": 8562 + }, + { + "epoch": 0.73, + "learning_rate": 3.582707557345555e-06, + "loss": 0.45, + "step": 8563 + }, + { + "epoch": 0.73, + "learning_rate": 3.5805898470384305e-06, + "loss": 0.4602, + "step": 8564 + }, + { + "epoch": 0.73, + "learning_rate": 3.5784726263023227e-06, + "loss": 0.4676, + "step": 8565 + }, + { + "epoch": 0.73, + "learning_rate": 3.576355895298702e-06, + "loss": 0.47, + "step": 8566 + }, + { + "epoch": 0.73, + "learning_rate": 3.574239654188999e-06, + "loss": 0.4396, + "step": 8567 + }, + { + "epoch": 0.73, + "learning_rate": 3.5721239031346067e-06, + "loss": 0.4783, + "step": 8568 + }, + { + "epoch": 0.73, + "learning_rate": 3.570008642296885e-06, + "loss": 0.4587, + "step": 8569 + }, + { + "epoch": 0.73, + "learning_rate": 3.5678938718371414e-06, + "loss": 0.4672, + "step": 8570 + }, + { + "epoch": 0.73, + "learning_rate": 3.565779591916667e-06, + "loss": 0.4694, + "step": 8571 + }, + { + "epoch": 0.73, + "learning_rate": 3.5636658026967076e-06, + "loss": 0.4774, + "step": 8572 + }, + { + "epoch": 0.73, + "learning_rate": 3.5615525043384604e-06, + "loss": 0.4727, + "step": 8573 + }, + { + "epoch": 0.73, + "learning_rate": 3.5594396970031e-06, + "loss": 0.4395, + "step": 8574 + }, + { + "epoch": 0.73, + "learning_rate": 3.557327380851756e-06, + "loss": 0.4731, + "step": 8575 + }, + { + "epoch": 0.73, + "learning_rate": 3.5552155560455237e-06, + "loss": 0.4467, + "step": 8576 + }, + { + "epoch": 0.73, + "learning_rate": 3.5531042227454595e-06, + "loss": 0.4318, + "step": 8577 + }, + { + "epoch": 0.73, + "learning_rate": 3.550993381112585e-06, + "loss": 0.4654, + "step": 8578 + }, + { + "epoch": 0.73, + "learning_rate": 3.5488830313078727e-06, + "loss": 0.4255, + "step": 8579 + }, + { + "epoch": 0.73, + "learning_rate": 3.546773173492276e-06, + "loss": 0.4689, + "step": 8580 + }, + { + "epoch": 0.73, + "learning_rate": 3.5446638078267027e-06, + "loss": 0.4469, + "step": 8581 + }, + { + "epoch": 0.73, + "learning_rate": 3.5425549344720133e-06, + "loss": 0.4615, + "step": 8582 + }, + { + "epoch": 0.73, + "learning_rate": 3.5404465535890443e-06, + "loss": 0.4724, + "step": 8583 + }, + { + "epoch": 0.73, + "learning_rate": 3.5383386653385888e-06, + "loss": 0.4693, + "step": 8584 + }, + { + "epoch": 0.73, + "learning_rate": 3.536231269881404e-06, + "loss": 0.4533, + "step": 8585 + }, + { + "epoch": 0.73, + "learning_rate": 3.5341243673782067e-06, + "loss": 0.4582, + "step": 8586 + }, + { + "epoch": 0.73, + "learning_rate": 3.532017957989684e-06, + "loss": 0.4555, + "step": 8587 + }, + { + "epoch": 0.73, + "learning_rate": 3.5299120418764697e-06, + "loss": 0.4652, + "step": 8588 + }, + { + "epoch": 0.73, + "learning_rate": 3.5278066191991733e-06, + "loss": 0.4637, + "step": 8589 + }, + { + "epoch": 0.73, + "learning_rate": 3.5257016901183707e-06, + "loss": 0.4498, + "step": 8590 + }, + { + "epoch": 0.73, + "learning_rate": 3.523597254794583e-06, + "loss": 0.4794, + "step": 8591 + }, + { + "epoch": 0.73, + "learning_rate": 3.521493313388307e-06, + "loss": 0.456, + "step": 8592 + }, + { + "epoch": 0.73, + "learning_rate": 3.519389866059998e-06, + "loss": 0.4701, + "step": 8593 + }, + { + "epoch": 0.73, + "learning_rate": 3.517286912970074e-06, + "loss": 0.4551, + "step": 8594 + }, + { + "epoch": 0.73, + "learning_rate": 3.515184454278914e-06, + "loss": 0.457, + "step": 8595 + }, + { + "epoch": 0.73, + "learning_rate": 3.513082490146864e-06, + "loss": 0.4645, + "step": 8596 + }, + { + "epoch": 0.73, + "learning_rate": 3.5109810207342222e-06, + "loss": 0.4607, + "step": 8597 + }, + { + "epoch": 0.73, + "learning_rate": 3.5088800462012553e-06, + "loss": 0.4743, + "step": 8598 + }, + { + "epoch": 0.73, + "learning_rate": 3.506779566708203e-06, + "loss": 0.4422, + "step": 8599 + }, + { + "epoch": 0.73, + "learning_rate": 3.5046795824152447e-06, + "loss": 0.4682, + "step": 8600 + }, + { + "epoch": 0.73, + "learning_rate": 3.5025800934825392e-06, + "loss": 0.4562, + "step": 8601 + }, + { + "epoch": 0.73, + "learning_rate": 3.500481100070201e-06, + "loss": 0.4467, + "step": 8602 + }, + { + "epoch": 0.73, + "learning_rate": 3.4983826023383105e-06, + "loss": 0.4707, + "step": 8603 + }, + { + "epoch": 0.73, + "learning_rate": 3.4962846004469042e-06, + "loss": 0.4611, + "step": 8604 + }, + { + "epoch": 0.73, + "learning_rate": 3.4941870945559906e-06, + "loss": 0.4725, + "step": 8605 + }, + { + "epoch": 0.73, + "learning_rate": 3.492090084825528e-06, + "loss": 0.4626, + "step": 8606 + }, + { + "epoch": 0.73, + "learning_rate": 3.489993571415441e-06, + "loss": 0.472, + "step": 8607 + }, + { + "epoch": 0.73, + "learning_rate": 3.4878975544856285e-06, + "loss": 0.4556, + "step": 8608 + }, + { + "epoch": 0.73, + "learning_rate": 3.4858020341959332e-06, + "loss": 0.4676, + "step": 8609 + }, + { + "epoch": 0.73, + "learning_rate": 3.483707010706171e-06, + "loss": 0.4583, + "step": 8610 + }, + { + "epoch": 0.73, + "learning_rate": 3.4816124841761157e-06, + "loss": 0.4556, + "step": 8611 + }, + { + "epoch": 0.73, + "learning_rate": 3.479518454765507e-06, + "loss": 0.4728, + "step": 8612 + }, + { + "epoch": 0.73, + "learning_rate": 3.477424922634043e-06, + "loss": 0.4607, + "step": 8613 + }, + { + "epoch": 0.73, + "learning_rate": 3.475331887941388e-06, + "loss": 0.4462, + "step": 8614 + }, + { + "epoch": 0.73, + "learning_rate": 3.4732393508471607e-06, + "loss": 0.4464, + "step": 8615 + }, + { + "epoch": 0.73, + "learning_rate": 3.471147311510944e-06, + "loss": 0.4772, + "step": 8616 + }, + { + "epoch": 0.73, + "learning_rate": 3.4690557700922976e-06, + "loss": 0.4812, + "step": 8617 + }, + { + "epoch": 0.73, + "learning_rate": 3.466964726750722e-06, + "loss": 0.4604, + "step": 8618 + }, + { + "epoch": 0.73, + "learning_rate": 3.4648741816456897e-06, + "loss": 0.4692, + "step": 8619 + }, + { + "epoch": 0.73, + "learning_rate": 3.4627841349366363e-06, + "loss": 0.4674, + "step": 8620 + }, + { + "epoch": 0.74, + "learning_rate": 3.460694586782957e-06, + "loss": 0.4474, + "step": 8621 + }, + { + "epoch": 0.74, + "learning_rate": 3.4586055373440075e-06, + "loss": 0.4779, + "step": 8622 + }, + { + "epoch": 0.74, + "learning_rate": 3.4565169867791147e-06, + "loss": 0.4697, + "step": 8623 + }, + { + "epoch": 0.74, + "learning_rate": 3.45442893524755e-06, + "loss": 0.4628, + "step": 8624 + }, + { + "epoch": 0.74, + "learning_rate": 3.4523413829085597e-06, + "loss": 0.4592, + "step": 8625 + }, + { + "epoch": 0.74, + "learning_rate": 3.4502543299213563e-06, + "loss": 0.4698, + "step": 8626 + }, + { + "epoch": 0.74, + "learning_rate": 3.448167776445099e-06, + "loss": 0.4655, + "step": 8627 + }, + { + "epoch": 0.74, + "learning_rate": 3.446081722638921e-06, + "loss": 0.4704, + "step": 8628 + }, + { + "epoch": 0.74, + "learning_rate": 3.443996168661912e-06, + "loss": 0.4605, + "step": 8629 + }, + { + "epoch": 0.74, + "learning_rate": 3.4419111146731255e-06, + "loss": 0.4582, + "step": 8630 + }, + { + "epoch": 0.74, + "learning_rate": 3.4398265608315774e-06, + "loss": 0.4345, + "step": 8631 + }, + { + "epoch": 0.74, + "learning_rate": 3.4377425072962467e-06, + "loss": 0.476, + "step": 8632 + }, + { + "epoch": 0.74, + "learning_rate": 3.4356589542260654e-06, + "loss": 0.4587, + "step": 8633 + }, + { + "epoch": 0.74, + "learning_rate": 3.4335759017799375e-06, + "loss": 0.4637, + "step": 8634 + }, + { + "epoch": 0.74, + "learning_rate": 3.4314933501167257e-06, + "loss": 0.4758, + "step": 8635 + }, + { + "epoch": 0.74, + "learning_rate": 3.4294112993952533e-06, + "loss": 0.4605, + "step": 8636 + }, + { + "epoch": 0.74, + "learning_rate": 3.4273297497743063e-06, + "loss": 0.4637, + "step": 8637 + }, + { + "epoch": 0.74, + "learning_rate": 3.4252487014126336e-06, + "loss": 0.4625, + "step": 8638 + }, + { + "epoch": 0.74, + "learning_rate": 3.4231681544689433e-06, + "loss": 0.4625, + "step": 8639 + }, + { + "epoch": 0.74, + "learning_rate": 3.4210881091019067e-06, + "loss": 0.4382, + "step": 8640 + }, + { + "epoch": 0.74, + "learning_rate": 3.419008565470161e-06, + "loss": 0.4758, + "step": 8641 + }, + { + "epoch": 0.74, + "learning_rate": 3.416929523732293e-06, + "loss": 0.4802, + "step": 8642 + }, + { + "epoch": 0.74, + "learning_rate": 3.4148509840468636e-06, + "loss": 0.4567, + "step": 8643 + }, + { + "epoch": 0.74, + "learning_rate": 3.412772946572389e-06, + "loss": 0.4313, + "step": 8644 + }, + { + "epoch": 0.74, + "learning_rate": 3.410695411467352e-06, + "loss": 0.4543, + "step": 8645 + }, + { + "epoch": 0.74, + "learning_rate": 3.4086183788901916e-06, + "loss": 0.4687, + "step": 8646 + }, + { + "epoch": 0.74, + "learning_rate": 3.4065418489993118e-06, + "loss": 0.4509, + "step": 8647 + }, + { + "epoch": 0.74, + "learning_rate": 3.404465821953078e-06, + "loss": 0.4513, + "step": 8648 + }, + { + "epoch": 0.74, + "learning_rate": 3.4023902979098155e-06, + "loss": 0.4507, + "step": 8649 + }, + { + "epoch": 0.74, + "learning_rate": 3.4003152770278124e-06, + "loss": 0.4653, + "step": 8650 + }, + { + "epoch": 0.74, + "learning_rate": 3.3982407594653244e-06, + "loss": 0.4582, + "step": 8651 + }, + { + "epoch": 0.74, + "learning_rate": 3.3961667453805526e-06, + "loss": 0.4521, + "step": 8652 + }, + { + "epoch": 0.74, + "learning_rate": 3.3940932349316757e-06, + "loss": 0.4456, + "step": 8653 + }, + { + "epoch": 0.74, + "learning_rate": 3.3920202282768277e-06, + "loss": 0.4505, + "step": 8654 + }, + { + "epoch": 0.74, + "learning_rate": 3.3899477255741043e-06, + "loss": 0.4809, + "step": 8655 + }, + { + "epoch": 0.74, + "learning_rate": 3.387875726981563e-06, + "loss": 0.4654, + "step": 8656 + }, + { + "epoch": 0.74, + "learning_rate": 3.385804232657224e-06, + "loss": 0.4645, + "step": 8657 + }, + { + "epoch": 0.74, + "learning_rate": 3.3837332427590673e-06, + "loss": 0.476, + "step": 8658 + }, + { + "epoch": 0.74, + "learning_rate": 3.3816627574450367e-06, + "loss": 0.4838, + "step": 8659 + }, + { + "epoch": 0.74, + "learning_rate": 3.3795927768730376e-06, + "loss": 0.4407, + "step": 8660 + }, + { + "epoch": 0.74, + "learning_rate": 3.377523301200929e-06, + "loss": 0.478, + "step": 8661 + }, + { + "epoch": 0.74, + "learning_rate": 3.3754543305865418e-06, + "loss": 0.4693, + "step": 8662 + }, + { + "epoch": 0.74, + "learning_rate": 3.373385865187664e-06, + "loss": 0.4397, + "step": 8663 + }, + { + "epoch": 0.74, + "learning_rate": 3.3713179051620457e-06, + "loss": 0.4343, + "step": 8664 + }, + { + "epoch": 0.74, + "learning_rate": 3.3692504506673973e-06, + "loss": 0.4699, + "step": 8665 + }, + { + "epoch": 0.74, + "learning_rate": 3.367183501861395e-06, + "loss": 0.454, + "step": 8666 + }, + { + "epoch": 0.74, + "learning_rate": 3.3651170589016645e-06, + "loss": 0.4531, + "step": 8667 + }, + { + "epoch": 0.74, + "learning_rate": 3.3630511219458093e-06, + "loss": 0.4706, + "step": 8668 + }, + { + "epoch": 0.74, + "learning_rate": 3.3609856911513885e-06, + "loss": 0.4758, + "step": 8669 + }, + { + "epoch": 0.74, + "learning_rate": 3.3589207666759114e-06, + "loss": 0.4533, + "step": 8670 + }, + { + "epoch": 0.74, + "learning_rate": 3.3568563486768636e-06, + "loss": 0.4733, + "step": 8671 + }, + { + "epoch": 0.74, + "learning_rate": 3.3547924373116836e-06, + "loss": 0.4577, + "step": 8672 + }, + { + "epoch": 0.74, + "learning_rate": 3.352729032737776e-06, + "loss": 0.4549, + "step": 8673 + }, + { + "epoch": 0.74, + "learning_rate": 3.350666135112504e-06, + "loss": 0.4629, + "step": 8674 + }, + { + "epoch": 0.74, + "learning_rate": 3.348603744593195e-06, + "loss": 0.4638, + "step": 8675 + }, + { + "epoch": 0.74, + "learning_rate": 3.346541861337127e-06, + "loss": 0.4643, + "step": 8676 + }, + { + "epoch": 0.74, + "learning_rate": 3.3444804855015576e-06, + "loss": 0.448, + "step": 8677 + }, + { + "epoch": 0.74, + "learning_rate": 3.342419617243695e-06, + "loss": 0.45, + "step": 8678 + }, + { + "epoch": 0.74, + "learning_rate": 3.3403592567207046e-06, + "loss": 0.4458, + "step": 8679 + }, + { + "epoch": 0.74, + "learning_rate": 3.3382994040897197e-06, + "loss": 0.4858, + "step": 8680 + }, + { + "epoch": 0.74, + "learning_rate": 3.336240059507835e-06, + "loss": 0.4802, + "step": 8681 + }, + { + "epoch": 0.74, + "learning_rate": 3.3341812231321024e-06, + "loss": 0.451, + "step": 8682 + }, + { + "epoch": 0.74, + "learning_rate": 3.3321228951195396e-06, + "loss": 0.4524, + "step": 8683 + }, + { + "epoch": 0.74, + "learning_rate": 3.330065075627126e-06, + "loss": 0.4542, + "step": 8684 + }, + { + "epoch": 0.74, + "learning_rate": 3.3280077648117883e-06, + "loss": 0.4669, + "step": 8685 + }, + { + "epoch": 0.74, + "learning_rate": 3.3259509628304364e-06, + "loss": 0.4493, + "step": 8686 + }, + { + "epoch": 0.74, + "learning_rate": 3.323894669839932e-06, + "loss": 0.4553, + "step": 8687 + }, + { + "epoch": 0.74, + "learning_rate": 3.3218388859970874e-06, + "loss": 0.4668, + "step": 8688 + }, + { + "epoch": 0.74, + "learning_rate": 3.3197836114586903e-06, + "loss": 0.4471, + "step": 8689 + }, + { + "epoch": 0.74, + "learning_rate": 3.317728846381484e-06, + "loss": 0.4548, + "step": 8690 + }, + { + "epoch": 0.74, + "learning_rate": 3.315674590922173e-06, + "loss": 0.4689, + "step": 8691 + }, + { + "epoch": 0.74, + "learning_rate": 3.313620845237425e-06, + "loss": 0.4556, + "step": 8692 + }, + { + "epoch": 0.74, + "learning_rate": 3.3115676094838687e-06, + "loss": 0.474, + "step": 8693 + }, + { + "epoch": 0.74, + "learning_rate": 3.3095148838180836e-06, + "loss": 0.4936, + "step": 8694 + }, + { + "epoch": 0.74, + "learning_rate": 3.307462668396628e-06, + "loss": 0.4576, + "step": 8695 + }, + { + "epoch": 0.74, + "learning_rate": 3.3054109633760147e-06, + "loss": 0.4727, + "step": 8696 + }, + { + "epoch": 0.74, + "learning_rate": 3.303359768912706e-06, + "loss": 0.4701, + "step": 8697 + }, + { + "epoch": 0.74, + "learning_rate": 3.3013090851631393e-06, + "loss": 0.4511, + "step": 8698 + }, + { + "epoch": 0.74, + "learning_rate": 3.2992589122837073e-06, + "loss": 0.4581, + "step": 8699 + }, + { + "epoch": 0.74, + "learning_rate": 3.297209250430766e-06, + "loss": 0.448, + "step": 8700 + }, + { + "epoch": 0.74, + "learning_rate": 3.2951600997606305e-06, + "loss": 0.4493, + "step": 8701 + }, + { + "epoch": 0.74, + "learning_rate": 3.29311146042958e-06, + "loss": 0.457, + "step": 8702 + }, + { + "epoch": 0.74, + "learning_rate": 3.2910633325938447e-06, + "loss": 0.4781, + "step": 8703 + }, + { + "epoch": 0.74, + "learning_rate": 3.2890157164096315e-06, + "loss": 0.4644, + "step": 8704 + }, + { + "epoch": 0.74, + "learning_rate": 3.2869686120331e-06, + "loss": 0.4547, + "step": 8705 + }, + { + "epoch": 0.74, + "learning_rate": 3.2849220196203657e-06, + "loss": 0.4526, + "step": 8706 + }, + { + "epoch": 0.74, + "learning_rate": 3.282875939327512e-06, + "loss": 0.4655, + "step": 8707 + }, + { + "epoch": 0.74, + "learning_rate": 3.2808303713105826e-06, + "loss": 0.4654, + "step": 8708 + }, + { + "epoch": 0.74, + "learning_rate": 3.278785315725581e-06, + "loss": 0.4413, + "step": 8709 + }, + { + "epoch": 0.74, + "learning_rate": 3.2767407727284716e-06, + "loss": 0.4655, + "step": 8710 + }, + { + "epoch": 0.74, + "learning_rate": 3.274696742475183e-06, + "loss": 0.4466, + "step": 8711 + }, + { + "epoch": 0.74, + "learning_rate": 3.2726532251215917e-06, + "loss": 0.4466, + "step": 8712 + }, + { + "epoch": 0.74, + "learning_rate": 3.2706102208235535e-06, + "loss": 0.4408, + "step": 8713 + }, + { + "epoch": 0.74, + "learning_rate": 3.268567729736879e-06, + "loss": 0.4482, + "step": 8714 + }, + { + "epoch": 0.74, + "learning_rate": 3.2665257520173276e-06, + "loss": 0.4648, + "step": 8715 + }, + { + "epoch": 0.74, + "learning_rate": 3.264484287820634e-06, + "loss": 0.464, + "step": 8716 + }, + { + "epoch": 0.74, + "learning_rate": 3.262443337302489e-06, + "loss": 0.4683, + "step": 8717 + }, + { + "epoch": 0.74, + "learning_rate": 3.2604029006185434e-06, + "loss": 0.4626, + "step": 8718 + }, + { + "epoch": 0.74, + "learning_rate": 3.2583629779244097e-06, + "loss": 0.4498, + "step": 8719 + }, + { + "epoch": 0.74, + "learning_rate": 3.2563235693756645e-06, + "loss": 0.4623, + "step": 8720 + }, + { + "epoch": 0.74, + "learning_rate": 3.2542846751278333e-06, + "loss": 0.4634, + "step": 8721 + }, + { + "epoch": 0.74, + "learning_rate": 3.252246295336413e-06, + "loss": 0.4632, + "step": 8722 + }, + { + "epoch": 0.74, + "learning_rate": 3.250208430156868e-06, + "loss": 0.4434, + "step": 8723 + }, + { + "epoch": 0.74, + "learning_rate": 3.248171079744604e-06, + "loss": 0.4682, + "step": 8724 + }, + { + "epoch": 0.74, + "learning_rate": 3.2461342442550017e-06, + "loss": 0.4583, + "step": 8725 + }, + { + "epoch": 0.74, + "learning_rate": 3.2440979238433977e-06, + "loss": 0.4545, + "step": 8726 + }, + { + "epoch": 0.74, + "learning_rate": 3.2420621186650927e-06, + "loss": 0.4596, + "step": 8727 + }, + { + "epoch": 0.74, + "learning_rate": 3.2400268288753423e-06, + "loss": 0.4418, + "step": 8728 + }, + { + "epoch": 0.74, + "learning_rate": 3.237992054629372e-06, + "loss": 0.4456, + "step": 8729 + }, + { + "epoch": 0.74, + "learning_rate": 3.235957796082355e-06, + "loss": 0.4698, + "step": 8730 + }, + { + "epoch": 0.74, + "learning_rate": 3.2339240533894323e-06, + "loss": 0.4736, + "step": 8731 + }, + { + "epoch": 0.74, + "learning_rate": 3.2318908267057147e-06, + "loss": 0.463, + "step": 8732 + }, + { + "epoch": 0.74, + "learning_rate": 3.2298581161862565e-06, + "loss": 0.4572, + "step": 8733 + }, + { + "epoch": 0.74, + "learning_rate": 3.227825921986082e-06, + "loss": 0.4789, + "step": 8734 + }, + { + "epoch": 0.74, + "learning_rate": 3.2257942442601755e-06, + "loss": 0.4718, + "step": 8735 + }, + { + "epoch": 0.74, + "learning_rate": 3.2237630831634816e-06, + "loss": 0.4571, + "step": 8736 + }, + { + "epoch": 0.74, + "learning_rate": 3.2217324388509053e-06, + "loss": 0.4508, + "step": 8737 + }, + { + "epoch": 0.75, + "learning_rate": 3.219702311477314e-06, + "loss": 0.4352, + "step": 8738 + }, + { + "epoch": 0.75, + "learning_rate": 3.2176727011975286e-06, + "loss": 0.4551, + "step": 8739 + }, + { + "epoch": 0.75, + "learning_rate": 3.2156436081663356e-06, + "loss": 0.4688, + "step": 8740 + }, + { + "epoch": 0.75, + "learning_rate": 3.2136150325384905e-06, + "loss": 0.4432, + "step": 8741 + }, + { + "epoch": 0.75, + "learning_rate": 3.2115869744686932e-06, + "loss": 0.4406, + "step": 8742 + }, + { + "epoch": 0.75, + "learning_rate": 3.2095594341116133e-06, + "loss": 0.4435, + "step": 8743 + }, + { + "epoch": 0.75, + "learning_rate": 3.2075324116218833e-06, + "loss": 0.434, + "step": 8744 + }, + { + "epoch": 0.75, + "learning_rate": 3.205505907154083e-06, + "loss": 0.4684, + "step": 8745 + }, + { + "epoch": 0.75, + "learning_rate": 3.203479920862772e-06, + "loss": 0.4459, + "step": 8746 + }, + { + "epoch": 0.75, + "learning_rate": 3.2014544529024595e-06, + "loss": 0.4621, + "step": 8747 + }, + { + "epoch": 0.75, + "learning_rate": 3.19942950342761e-06, + "loss": 0.4433, + "step": 8748 + }, + { + "epoch": 0.75, + "learning_rate": 3.1974050725926552e-06, + "loss": 0.4504, + "step": 8749 + }, + { + "epoch": 0.75, + "learning_rate": 3.1953811605519967e-06, + "loss": 0.4758, + "step": 8750 + }, + { + "epoch": 0.75, + "learning_rate": 3.193357767459975e-06, + "loss": 0.4469, + "step": 8751 + }, + { + "epoch": 0.75, + "learning_rate": 3.1913348934709076e-06, + "loss": 0.4507, + "step": 8752 + }, + { + "epoch": 0.75, + "learning_rate": 3.18931253873907e-06, + "loss": 0.4575, + "step": 8753 + }, + { + "epoch": 0.75, + "learning_rate": 3.1872907034186852e-06, + "loss": 0.4534, + "step": 8754 + }, + { + "epoch": 0.75, + "learning_rate": 3.1852693876639563e-06, + "loss": 0.4756, + "step": 8755 + }, + { + "epoch": 0.75, + "learning_rate": 3.183248591629038e-06, + "loss": 0.4652, + "step": 8756 + }, + { + "epoch": 0.75, + "learning_rate": 3.181228315468038e-06, + "loss": 0.4575, + "step": 8757 + }, + { + "epoch": 0.75, + "learning_rate": 3.179208559335031e-06, + "loss": 0.4567, + "step": 8758 + }, + { + "epoch": 0.75, + "learning_rate": 3.177189323384061e-06, + "loss": 0.4535, + "step": 8759 + }, + { + "epoch": 0.75, + "learning_rate": 3.175170607769116e-06, + "loss": 0.4488, + "step": 8760 + }, + { + "epoch": 0.75, + "learning_rate": 3.1731524126441513e-06, + "loss": 0.4496, + "step": 8761 + }, + { + "epoch": 0.75, + "learning_rate": 3.17113473816309e-06, + "loss": 0.4642, + "step": 8762 + }, + { + "epoch": 0.75, + "learning_rate": 3.169117584479795e-06, + "loss": 0.4516, + "step": 8763 + }, + { + "epoch": 0.75, + "learning_rate": 3.1671009517481155e-06, + "loss": 0.4451, + "step": 8764 + }, + { + "epoch": 0.75, + "learning_rate": 3.165084840121847e-06, + "loss": 0.4763, + "step": 8765 + }, + { + "epoch": 0.75, + "learning_rate": 3.16306924975474e-06, + "loss": 0.4518, + "step": 8766 + }, + { + "epoch": 0.75, + "learning_rate": 3.161054180800516e-06, + "loss": 0.431, + "step": 8767 + }, + { + "epoch": 0.75, + "learning_rate": 3.1590396334128505e-06, + "loss": 0.4677, + "step": 8768 + }, + { + "epoch": 0.75, + "learning_rate": 3.1570256077453833e-06, + "loss": 0.4677, + "step": 8769 + }, + { + "epoch": 0.75, + "learning_rate": 3.1550121039517125e-06, + "loss": 0.4652, + "step": 8770 + }, + { + "epoch": 0.75, + "learning_rate": 3.152999122185395e-06, + "loss": 0.4302, + "step": 8771 + }, + { + "epoch": 0.75, + "learning_rate": 3.1509866625999497e-06, + "loss": 0.4601, + "step": 8772 + }, + { + "epoch": 0.75, + "learning_rate": 3.1489747253488555e-06, + "loss": 0.4653, + "step": 8773 + }, + { + "epoch": 0.75, + "learning_rate": 3.1469633105855545e-06, + "loss": 0.4313, + "step": 8774 + }, + { + "epoch": 0.75, + "learning_rate": 3.1449524184634383e-06, + "loss": 0.4773, + "step": 8775 + }, + { + "epoch": 0.75, + "learning_rate": 3.1429420491358696e-06, + "loss": 0.4698, + "step": 8776 + }, + { + "epoch": 0.75, + "learning_rate": 3.1409322027561683e-06, + "loss": 0.4666, + "step": 8777 + }, + { + "epoch": 0.75, + "learning_rate": 3.138922879477613e-06, + "loss": 0.4545, + "step": 8778 + }, + { + "epoch": 0.75, + "learning_rate": 3.1369140794534412e-06, + "loss": 0.4613, + "step": 8779 + }, + { + "epoch": 0.75, + "learning_rate": 3.134905802836856e-06, + "loss": 0.4438, + "step": 8780 + }, + { + "epoch": 0.75, + "learning_rate": 3.1328980497810145e-06, + "loss": 0.4522, + "step": 8781 + }, + { + "epoch": 0.75, + "learning_rate": 3.1308908204390376e-06, + "loss": 0.4644, + "step": 8782 + }, + { + "epoch": 0.75, + "learning_rate": 3.128884114964007e-06, + "loss": 0.447, + "step": 8783 + }, + { + "epoch": 0.75, + "learning_rate": 3.126877933508957e-06, + "loss": 0.4593, + "step": 8784 + }, + { + "epoch": 0.75, + "learning_rate": 3.1248722762268902e-06, + "loss": 0.4514, + "step": 8785 + }, + { + "epoch": 0.75, + "learning_rate": 3.1228671432707656e-06, + "loss": 0.4645, + "step": 8786 + }, + { + "epoch": 0.75, + "learning_rate": 3.120862534793505e-06, + "loss": 0.4617, + "step": 8787 + }, + { + "epoch": 0.75, + "learning_rate": 3.1188584509479867e-06, + "loss": 0.4645, + "step": 8788 + }, + { + "epoch": 0.75, + "learning_rate": 3.11685489188705e-06, + "loss": 0.4819, + "step": 8789 + }, + { + "epoch": 0.75, + "learning_rate": 3.1148518577634966e-06, + "loss": 0.4467, + "step": 8790 + }, + { + "epoch": 0.75, + "learning_rate": 3.1128493487300847e-06, + "loss": 0.4641, + "step": 8791 + }, + { + "epoch": 0.75, + "learning_rate": 3.1108473649395376e-06, + "loss": 0.4544, + "step": 8792 + }, + { + "epoch": 0.75, + "learning_rate": 3.1088459065445288e-06, + "loss": 0.4611, + "step": 8793 + }, + { + "epoch": 0.75, + "learning_rate": 3.1068449736977015e-06, + "loss": 0.4543, + "step": 8794 + }, + { + "epoch": 0.75, + "learning_rate": 3.1048445665516535e-06, + "loss": 0.4512, + "step": 8795 + }, + { + "epoch": 0.75, + "learning_rate": 3.1028446852589456e-06, + "loss": 0.4532, + "step": 8796 + }, + { + "epoch": 0.75, + "learning_rate": 3.1008453299720965e-06, + "loss": 0.4544, + "step": 8797 + }, + { + "epoch": 0.75, + "learning_rate": 3.098846500843585e-06, + "loss": 0.4557, + "step": 8798 + }, + { + "epoch": 0.75, + "learning_rate": 3.096848198025856e-06, + "loss": 0.4627, + "step": 8799 + }, + { + "epoch": 0.75, + "learning_rate": 3.094850421671295e-06, + "loss": 0.4692, + "step": 8800 + }, + { + "epoch": 0.75, + "learning_rate": 3.0928531719322764e-06, + "loss": 0.4711, + "step": 8801 + }, + { + "epoch": 0.75, + "learning_rate": 3.0908564489611083e-06, + "loss": 0.4635, + "step": 8802 + }, + { + "epoch": 0.75, + "learning_rate": 3.088860252910071e-06, + "loss": 0.4437, + "step": 8803 + }, + { + "epoch": 0.75, + "learning_rate": 3.086864583931405e-06, + "loss": 0.4479, + "step": 8804 + }, + { + "epoch": 0.75, + "learning_rate": 3.0848694421773075e-06, + "loss": 0.4615, + "step": 8805 + }, + { + "epoch": 0.75, + "learning_rate": 3.0828748277999354e-06, + "loss": 0.4528, + "step": 8806 + }, + { + "epoch": 0.75, + "learning_rate": 3.0808807409514073e-06, + "loss": 0.5022, + "step": 8807 + }, + { + "epoch": 0.75, + "learning_rate": 3.078887181783803e-06, + "loss": 0.4642, + "step": 8808 + }, + { + "epoch": 0.75, + "learning_rate": 3.0768941504491514e-06, + "loss": 0.4613, + "step": 8809 + }, + { + "epoch": 0.75, + "learning_rate": 3.074901647099461e-06, + "loss": 0.466, + "step": 8810 + }, + { + "epoch": 0.75, + "learning_rate": 3.072909671886679e-06, + "loss": 0.4746, + "step": 8811 + }, + { + "epoch": 0.75, + "learning_rate": 3.0709182249627255e-06, + "loss": 0.4731, + "step": 8812 + }, + { + "epoch": 0.75, + "learning_rate": 3.0689273064794767e-06, + "loss": 0.437, + "step": 8813 + }, + { + "epoch": 0.75, + "learning_rate": 3.0669369165887674e-06, + "loss": 0.4854, + "step": 8814 + }, + { + "epoch": 0.75, + "learning_rate": 3.0649470554423932e-06, + "loss": 0.4686, + "step": 8815 + }, + { + "epoch": 0.75, + "learning_rate": 3.0629577231921102e-06, + "loss": 0.4559, + "step": 8816 + }, + { + "epoch": 0.75, + "learning_rate": 3.060968919989635e-06, + "loss": 0.4454, + "step": 8817 + }, + { + "epoch": 0.75, + "learning_rate": 3.0589806459866336e-06, + "loss": 0.4618, + "step": 8818 + }, + { + "epoch": 0.75, + "learning_rate": 3.056992901334752e-06, + "loss": 0.4544, + "step": 8819 + }, + { + "epoch": 0.75, + "learning_rate": 3.055005686185576e-06, + "loss": 0.4727, + "step": 8820 + }, + { + "epoch": 0.75, + "learning_rate": 3.053019000690659e-06, + "loss": 0.4515, + "step": 8821 + }, + { + "epoch": 0.75, + "learning_rate": 3.051032845001517e-06, + "loss": 0.4545, + "step": 8822 + }, + { + "epoch": 0.75, + "learning_rate": 3.0490472192696206e-06, + "loss": 0.4819, + "step": 8823 + }, + { + "epoch": 0.75, + "learning_rate": 3.047062123646404e-06, + "loss": 0.4496, + "step": 8824 + }, + { + "epoch": 0.75, + "learning_rate": 3.045077558283256e-06, + "loss": 0.4673, + "step": 8825 + }, + { + "epoch": 0.75, + "learning_rate": 3.043093523331533e-06, + "loss": 0.4584, + "step": 8826 + }, + { + "epoch": 0.75, + "learning_rate": 3.0411100189425356e-06, + "loss": 0.4612, + "step": 8827 + }, + { + "epoch": 0.75, + "learning_rate": 3.039127045267544e-06, + "loss": 0.4618, + "step": 8828 + }, + { + "epoch": 0.75, + "learning_rate": 3.0371446024577878e-06, + "loss": 0.4475, + "step": 8829 + }, + { + "epoch": 0.75, + "learning_rate": 3.0351626906644505e-06, + "loss": 0.4664, + "step": 8830 + }, + { + "epoch": 0.75, + "learning_rate": 3.033181310038683e-06, + "loss": 0.4719, + "step": 8831 + }, + { + "epoch": 0.75, + "learning_rate": 3.031200460731595e-06, + "loss": 0.4578, + "step": 8832 + }, + { + "epoch": 0.75, + "learning_rate": 3.0292201428942535e-06, + "loss": 0.4622, + "step": 8833 + }, + { + "epoch": 0.75, + "learning_rate": 3.0272403566776855e-06, + "loss": 0.4749, + "step": 8834 + }, + { + "epoch": 0.75, + "learning_rate": 3.0252611022328826e-06, + "loss": 0.4491, + "step": 8835 + }, + { + "epoch": 0.75, + "learning_rate": 3.0232823797107793e-06, + "loss": 0.4801, + "step": 8836 + }, + { + "epoch": 0.75, + "learning_rate": 3.021304189262293e-06, + "loss": 0.4469, + "step": 8837 + }, + { + "epoch": 0.75, + "learning_rate": 3.019326531038287e-06, + "loss": 0.4658, + "step": 8838 + }, + { + "epoch": 0.75, + "learning_rate": 3.017349405189579e-06, + "loss": 0.4408, + "step": 8839 + }, + { + "epoch": 0.75, + "learning_rate": 3.015372811866958e-06, + "loss": 0.4483, + "step": 8840 + }, + { + "epoch": 0.75, + "learning_rate": 3.013396751221166e-06, + "loss": 0.4716, + "step": 8841 + }, + { + "epoch": 0.75, + "learning_rate": 3.011421223402906e-06, + "loss": 0.4558, + "step": 8842 + }, + { + "epoch": 0.75, + "learning_rate": 3.00944622856284e-06, + "loss": 0.4927, + "step": 8843 + }, + { + "epoch": 0.75, + "learning_rate": 3.007471766851593e-06, + "loss": 0.4425, + "step": 8844 + }, + { + "epoch": 0.75, + "learning_rate": 3.0054978384197386e-06, + "loss": 0.4588, + "step": 8845 + }, + { + "epoch": 0.75, + "learning_rate": 3.0035244434178168e-06, + "loss": 0.459, + "step": 8846 + }, + { + "epoch": 0.75, + "learning_rate": 3.001551581996337e-06, + "loss": 0.4497, + "step": 8847 + }, + { + "epoch": 0.75, + "learning_rate": 2.999579254305748e-06, + "loss": 0.4583, + "step": 8848 + }, + { + "epoch": 0.75, + "learning_rate": 2.99760746049647e-06, + "loss": 0.4458, + "step": 8849 + }, + { + "epoch": 0.75, + "learning_rate": 2.995636200718882e-06, + "loss": 0.4516, + "step": 8850 + }, + { + "epoch": 0.75, + "learning_rate": 2.9936654751233196e-06, + "loss": 0.467, + "step": 8851 + }, + { + "epoch": 0.75, + "learning_rate": 2.991695283860079e-06, + "loss": 0.453, + "step": 8852 + }, + { + "epoch": 0.75, + "learning_rate": 2.9897256270794172e-06, + "loss": 0.4605, + "step": 8853 + }, + { + "epoch": 0.75, + "learning_rate": 2.9877565049315425e-06, + "loss": 0.4381, + "step": 8854 + }, + { + "epoch": 0.76, + "learning_rate": 2.9857879175666303e-06, + "loss": 0.453, + "step": 8855 + }, + { + "epoch": 0.76, + "learning_rate": 2.9838198651348206e-06, + "loss": 0.4523, + "step": 8856 + }, + { + "epoch": 0.76, + "learning_rate": 2.981852347786196e-06, + "loss": 0.4511, + "step": 8857 + }, + { + "epoch": 0.76, + "learning_rate": 2.9798853656708126e-06, + "loss": 0.4559, + "step": 8858 + }, + { + "epoch": 0.76, + "learning_rate": 2.9779189189386782e-06, + "loss": 0.4633, + "step": 8859 + }, + { + "epoch": 0.76, + "learning_rate": 2.9759530077397637e-06, + "loss": 0.4805, + "step": 8860 + }, + { + "epoch": 0.76, + "learning_rate": 2.973987632223997e-06, + "loss": 0.4393, + "step": 8861 + }, + { + "epoch": 0.76, + "learning_rate": 2.972022792541269e-06, + "loss": 0.4577, + "step": 8862 + }, + { + "epoch": 0.76, + "learning_rate": 2.9700584888414217e-06, + "loss": 0.4543, + "step": 8863 + }, + { + "epoch": 0.76, + "learning_rate": 2.9680947212742593e-06, + "loss": 0.4556, + "step": 8864 + }, + { + "epoch": 0.76, + "learning_rate": 2.9661314899895577e-06, + "loss": 0.4388, + "step": 8865 + }, + { + "epoch": 0.76, + "learning_rate": 2.96416879513703e-06, + "loss": 0.4711, + "step": 8866 + }, + { + "epoch": 0.76, + "learning_rate": 2.962206636866365e-06, + "loss": 0.4608, + "step": 8867 + }, + { + "epoch": 0.76, + "learning_rate": 2.9602450153272033e-06, + "loss": 0.4492, + "step": 8868 + }, + { + "epoch": 0.76, + "learning_rate": 2.9582839306691468e-06, + "loss": 0.4528, + "step": 8869 + }, + { + "epoch": 0.76, + "learning_rate": 2.956323383041756e-06, + "loss": 0.4653, + "step": 8870 + }, + { + "epoch": 0.76, + "learning_rate": 2.954363372594553e-06, + "loss": 0.4732, + "step": 8871 + }, + { + "epoch": 0.76, + "learning_rate": 2.952403899477011e-06, + "loss": 0.4398, + "step": 8872 + }, + { + "epoch": 0.76, + "learning_rate": 2.950444963838568e-06, + "loss": 0.4614, + "step": 8873 + }, + { + "epoch": 0.76, + "learning_rate": 2.9484865658286287e-06, + "loss": 0.4444, + "step": 8874 + }, + { + "epoch": 0.76, + "learning_rate": 2.94652870559654e-06, + "loss": 0.4676, + "step": 8875 + }, + { + "epoch": 0.76, + "learning_rate": 2.94457138329162e-06, + "loss": 0.4633, + "step": 8876 + }, + { + "epoch": 0.76, + "learning_rate": 2.942614599063144e-06, + "loss": 0.4569, + "step": 8877 + }, + { + "epoch": 0.76, + "learning_rate": 2.940658353060337e-06, + "loss": 0.4273, + "step": 8878 + }, + { + "epoch": 0.76, + "learning_rate": 2.9387026454323986e-06, + "loss": 0.45, + "step": 8879 + }, + { + "epoch": 0.76, + "learning_rate": 2.93674747632848e-06, + "loss": 0.4745, + "step": 8880 + }, + { + "epoch": 0.76, + "learning_rate": 2.934792845897684e-06, + "loss": 0.4388, + "step": 8881 + }, + { + "epoch": 0.76, + "learning_rate": 2.932838754289078e-06, + "loss": 0.4694, + "step": 8882 + }, + { + "epoch": 0.76, + "learning_rate": 2.9308852016516997e-06, + "loss": 0.4551, + "step": 8883 + }, + { + "epoch": 0.76, + "learning_rate": 2.9289321881345257e-06, + "loss": 0.434, + "step": 8884 + }, + { + "epoch": 0.76, + "learning_rate": 2.9269797138865044e-06, + "loss": 0.4501, + "step": 8885 + }, + { + "epoch": 0.76, + "learning_rate": 2.9250277790565407e-06, + "loss": 0.4532, + "step": 8886 + }, + { + "epoch": 0.76, + "learning_rate": 2.9230763837934907e-06, + "loss": 0.4596, + "step": 8887 + }, + { + "epoch": 0.76, + "learning_rate": 2.9211255282461835e-06, + "loss": 0.4621, + "step": 8888 + }, + { + "epoch": 0.76, + "learning_rate": 2.9191752125634e-06, + "loss": 0.4648, + "step": 8889 + }, + { + "epoch": 0.76, + "learning_rate": 2.9172254368938736e-06, + "loss": 0.4607, + "step": 8890 + }, + { + "epoch": 0.76, + "learning_rate": 2.9152762013863023e-06, + "loss": 0.4383, + "step": 8891 + }, + { + "epoch": 0.76, + "learning_rate": 2.9133275061893506e-06, + "loss": 0.4906, + "step": 8892 + }, + { + "epoch": 0.76, + "learning_rate": 2.9113793514516277e-06, + "loss": 0.4854, + "step": 8893 + }, + { + "epoch": 0.76, + "learning_rate": 2.9094317373217085e-06, + "loss": 0.4556, + "step": 8894 + }, + { + "epoch": 0.76, + "learning_rate": 2.90748466394813e-06, + "loss": 0.4595, + "step": 8895 + }, + { + "epoch": 0.76, + "learning_rate": 2.905538131479376e-06, + "loss": 0.4871, + "step": 8896 + }, + { + "epoch": 0.76, + "learning_rate": 2.9035921400639056e-06, + "loss": 0.4605, + "step": 8897 + }, + { + "epoch": 0.76, + "learning_rate": 2.901646689850128e-06, + "loss": 0.4805, + "step": 8898 + }, + { + "epoch": 0.76, + "learning_rate": 2.8997017809864068e-06, + "loss": 0.4772, + "step": 8899 + }, + { + "epoch": 0.76, + "learning_rate": 2.8977574136210696e-06, + "loss": 0.4258, + "step": 8900 + }, + { + "epoch": 0.76, + "learning_rate": 2.8958135879024028e-06, + "loss": 0.4555, + "step": 8901 + }, + { + "epoch": 0.76, + "learning_rate": 2.8938703039786507e-06, + "loss": 0.4563, + "step": 8902 + }, + { + "epoch": 0.76, + "learning_rate": 2.891927561998017e-06, + "loss": 0.4576, + "step": 8903 + }, + { + "epoch": 0.76, + "learning_rate": 2.889985362108666e-06, + "loss": 0.4509, + "step": 8904 + }, + { + "epoch": 0.76, + "learning_rate": 2.888043704458707e-06, + "loss": 0.45, + "step": 8905 + }, + { + "epoch": 0.76, + "learning_rate": 2.8861025891962314e-06, + "loss": 0.4526, + "step": 8906 + }, + { + "epoch": 0.76, + "learning_rate": 2.884162016469274e-06, + "loss": 0.4385, + "step": 8907 + }, + { + "epoch": 0.76, + "learning_rate": 2.8822219864258272e-06, + "loss": 0.495, + "step": 8908 + }, + { + "epoch": 0.76, + "learning_rate": 2.880282499213847e-06, + "loss": 0.4617, + "step": 8909 + }, + { + "epoch": 0.76, + "learning_rate": 2.8783435549812464e-06, + "loss": 0.4481, + "step": 8910 + }, + { + "epoch": 0.76, + "learning_rate": 2.8764051538758986e-06, + "loss": 0.4488, + "step": 8911 + }, + { + "epoch": 0.76, + "learning_rate": 2.8744672960456345e-06, + "loss": 0.4607, + "step": 8912 + }, + { + "epoch": 0.76, + "learning_rate": 2.8725299816382455e-06, + "loss": 0.4533, + "step": 8913 + }, + { + "epoch": 0.76, + "learning_rate": 2.87059321080147e-06, + "loss": 0.4615, + "step": 8914 + }, + { + "epoch": 0.76, + "learning_rate": 2.8686569836830246e-06, + "loss": 0.4671, + "step": 8915 + }, + { + "epoch": 0.76, + "learning_rate": 2.8667213004305716e-06, + "loss": 0.4389, + "step": 8916 + }, + { + "epoch": 0.76, + "learning_rate": 2.8647861611917303e-06, + "loss": 0.4446, + "step": 8917 + }, + { + "epoch": 0.76, + "learning_rate": 2.8628515661140856e-06, + "loss": 0.4605, + "step": 8918 + }, + { + "epoch": 0.76, + "learning_rate": 2.8609175153451775e-06, + "loss": 0.4721, + "step": 8919 + }, + { + "epoch": 0.76, + "learning_rate": 2.8589840090325028e-06, + "loss": 0.4704, + "step": 8920 + }, + { + "epoch": 0.76, + "learning_rate": 2.8570510473235214e-06, + "loss": 0.4442, + "step": 8921 + }, + { + "epoch": 0.76, + "learning_rate": 2.855118630365652e-06, + "loss": 0.4541, + "step": 8922 + }, + { + "epoch": 0.76, + "learning_rate": 2.8531867583062567e-06, + "loss": 0.4571, + "step": 8923 + }, + { + "epoch": 0.76, + "learning_rate": 2.851255431292681e-06, + "loss": 0.4655, + "step": 8924 + }, + { + "epoch": 0.76, + "learning_rate": 2.8493246494722136e-06, + "loss": 0.4777, + "step": 8925 + }, + { + "epoch": 0.76, + "learning_rate": 2.8473944129920985e-06, + "loss": 0.4571, + "step": 8926 + }, + { + "epoch": 0.76, + "learning_rate": 2.8454647219995467e-06, + "loss": 0.4512, + "step": 8927 + }, + { + "epoch": 0.76, + "learning_rate": 2.843535576641725e-06, + "loss": 0.4628, + "step": 8928 + }, + { + "epoch": 0.76, + "learning_rate": 2.841606977065757e-06, + "loss": 0.4564, + "step": 8929 + }, + { + "epoch": 0.76, + "learning_rate": 2.839678923418726e-06, + "loss": 0.4542, + "step": 8930 + }, + { + "epoch": 0.76, + "learning_rate": 2.837751415847678e-06, + "loss": 0.4552, + "step": 8931 + }, + { + "epoch": 0.76, + "learning_rate": 2.8358244544996038e-06, + "loss": 0.4351, + "step": 8932 + }, + { + "epoch": 0.76, + "learning_rate": 2.8338980395214643e-06, + "loss": 0.4699, + "step": 8933 + }, + { + "epoch": 0.76, + "learning_rate": 2.8319721710601843e-06, + "loss": 0.4771, + "step": 8934 + }, + { + "epoch": 0.76, + "learning_rate": 2.830046849262629e-06, + "loss": 0.459, + "step": 8935 + }, + { + "epoch": 0.76, + "learning_rate": 2.8281220742756333e-06, + "loss": 0.4416, + "step": 8936 + }, + { + "epoch": 0.76, + "learning_rate": 2.8261978462459917e-06, + "loss": 0.4561, + "step": 8937 + }, + { + "epoch": 0.76, + "learning_rate": 2.8242741653204508e-06, + "loss": 0.463, + "step": 8938 + }, + { + "epoch": 0.76, + "learning_rate": 2.8223510316457205e-06, + "loss": 0.4519, + "step": 8939 + }, + { + "epoch": 0.76, + "learning_rate": 2.820428445368468e-06, + "loss": 0.4593, + "step": 8940 + }, + { + "epoch": 0.76, + "learning_rate": 2.8185064066353153e-06, + "loss": 0.4539, + "step": 8941 + }, + { + "epoch": 0.76, + "learning_rate": 2.8165849155928416e-06, + "loss": 0.4595, + "step": 8942 + }, + { + "epoch": 0.76, + "learning_rate": 2.8146639723875977e-06, + "loss": 0.4684, + "step": 8943 + }, + { + "epoch": 0.76, + "learning_rate": 2.812743577166075e-06, + "loss": 0.4538, + "step": 8944 + }, + { + "epoch": 0.76, + "learning_rate": 2.810823730074732e-06, + "loss": 0.4637, + "step": 8945 + }, + { + "epoch": 0.76, + "learning_rate": 2.8089044312599857e-06, + "loss": 0.4672, + "step": 8946 + }, + { + "epoch": 0.76, + "learning_rate": 2.8069856808682093e-06, + "loss": 0.4651, + "step": 8947 + }, + { + "epoch": 0.76, + "learning_rate": 2.8050674790457355e-06, + "loss": 0.4473, + "step": 8948 + }, + { + "epoch": 0.76, + "learning_rate": 2.8031498259388535e-06, + "loss": 0.4549, + "step": 8949 + }, + { + "epoch": 0.76, + "learning_rate": 2.801232721693814e-06, + "loss": 0.4458, + "step": 8950 + }, + { + "epoch": 0.76, + "learning_rate": 2.799316166456816e-06, + "loss": 0.4386, + "step": 8951 + }, + { + "epoch": 0.76, + "learning_rate": 2.7974001603740343e-06, + "loss": 0.444, + "step": 8952 + }, + { + "epoch": 0.76, + "learning_rate": 2.7954847035915846e-06, + "loss": 0.4546, + "step": 8953 + }, + { + "epoch": 0.76, + "learning_rate": 2.7935697962555477e-06, + "loss": 0.5009, + "step": 8954 + }, + { + "epoch": 0.76, + "learning_rate": 2.7916554385119643e-06, + "loss": 0.4411, + "step": 8955 + }, + { + "epoch": 0.76, + "learning_rate": 2.7897416305068325e-06, + "loss": 0.4776, + "step": 8956 + }, + { + "epoch": 0.76, + "learning_rate": 2.7878283723861045e-06, + "loss": 0.4678, + "step": 8957 + }, + { + "epoch": 0.76, + "learning_rate": 2.7859156642956953e-06, + "loss": 0.4586, + "step": 8958 + }, + { + "epoch": 0.76, + "learning_rate": 2.7840035063814784e-06, + "loss": 0.4839, + "step": 8959 + }, + { + "epoch": 0.76, + "learning_rate": 2.7820918987892742e-06, + "loss": 0.4871, + "step": 8960 + }, + { + "epoch": 0.76, + "learning_rate": 2.7801808416648814e-06, + "loss": 0.4871, + "step": 8961 + }, + { + "epoch": 0.76, + "learning_rate": 2.778270335154036e-06, + "loss": 0.4467, + "step": 8962 + }, + { + "epoch": 0.76, + "learning_rate": 2.776360379402445e-06, + "loss": 0.4396, + "step": 8963 + }, + { + "epoch": 0.76, + "learning_rate": 2.774450974555769e-06, + "loss": 0.4697, + "step": 8964 + }, + { + "epoch": 0.76, + "learning_rate": 2.772542120759628e-06, + "loss": 0.4501, + "step": 8965 + }, + { + "epoch": 0.76, + "learning_rate": 2.7706338181595982e-06, + "loss": 0.4591, + "step": 8966 + }, + { + "epoch": 0.76, + "learning_rate": 2.768726066901216e-06, + "loss": 0.4576, + "step": 8967 + }, + { + "epoch": 0.76, + "learning_rate": 2.766818867129976e-06, + "loss": 0.4586, + "step": 8968 + }, + { + "epoch": 0.76, + "learning_rate": 2.7649122189913204e-06, + "loss": 0.4535, + "step": 8969 + }, + { + "epoch": 0.76, + "learning_rate": 2.7630061226306715e-06, + "loss": 0.4658, + "step": 8970 + }, + { + "epoch": 0.76, + "learning_rate": 2.761100578193385e-06, + "loss": 0.445, + "step": 8971 + }, + { + "epoch": 0.77, + "learning_rate": 2.759195585824791e-06, + "loss": 0.4533, + "step": 8972 + }, + { + "epoch": 0.77, + "learning_rate": 2.75729114567017e-06, + "loss": 0.4721, + "step": 8973 + }, + { + "epoch": 0.77, + "learning_rate": 2.755387257874764e-06, + "loss": 0.4496, + "step": 8974 + }, + { + "epoch": 0.77, + "learning_rate": 2.7534839225837716e-06, + "loss": 0.4489, + "step": 8975 + }, + { + "epoch": 0.77, + "learning_rate": 2.7515811399423486e-06, + "loss": 0.4745, + "step": 8976 + }, + { + "epoch": 0.77, + "learning_rate": 2.749678910095611e-06, + "loss": 0.4742, + "step": 8977 + }, + { + "epoch": 0.77, + "learning_rate": 2.7477772331886275e-06, + "loss": 0.4294, + "step": 8978 + }, + { + "epoch": 0.77, + "learning_rate": 2.745876109366429e-06, + "loss": 0.4613, + "step": 8979 + }, + { + "epoch": 0.77, + "learning_rate": 2.743975538774002e-06, + "loss": 0.4642, + "step": 8980 + }, + { + "epoch": 0.77, + "learning_rate": 2.7420755215562944e-06, + "loss": 0.4671, + "step": 8981 + }, + { + "epoch": 0.77, + "learning_rate": 2.740176057858208e-06, + "loss": 0.4622, + "step": 8982 + }, + { + "epoch": 0.77, + "learning_rate": 2.738277147824605e-06, + "loss": 0.4522, + "step": 8983 + }, + { + "epoch": 0.77, + "learning_rate": 2.7363787916003037e-06, + "loss": 0.4631, + "step": 8984 + }, + { + "epoch": 0.77, + "learning_rate": 2.7344809893300796e-06, + "loss": 0.4465, + "step": 8985 + }, + { + "epoch": 0.77, + "learning_rate": 2.732583741158671e-06, + "loss": 0.4843, + "step": 8986 + }, + { + "epoch": 0.77, + "learning_rate": 2.7306870472307645e-06, + "loss": 0.4494, + "step": 8987 + }, + { + "epoch": 0.77, + "learning_rate": 2.7287909076910114e-06, + "loss": 0.4534, + "step": 8988 + }, + { + "epoch": 0.77, + "learning_rate": 2.7268953226840213e-06, + "loss": 0.4683, + "step": 8989 + }, + { + "epoch": 0.77, + "learning_rate": 2.7250002923543575e-06, + "loss": 0.4573, + "step": 8990 + }, + { + "epoch": 0.77, + "learning_rate": 2.723105816846543e-06, + "loss": 0.4466, + "step": 8991 + }, + { + "epoch": 0.77, + "learning_rate": 2.721211896305059e-06, + "loss": 0.462, + "step": 8992 + }, + { + "epoch": 0.77, + "learning_rate": 2.7193185308743443e-06, + "loss": 0.4757, + "step": 8993 + }, + { + "epoch": 0.77, + "learning_rate": 2.7174257206987943e-06, + "loss": 0.4519, + "step": 8994 + }, + { + "epoch": 0.77, + "learning_rate": 2.715533465922766e-06, + "loss": 0.4613, + "step": 8995 + }, + { + "epoch": 0.77, + "learning_rate": 2.7136417666905646e-06, + "loss": 0.4566, + "step": 8996 + }, + { + "epoch": 0.77, + "learning_rate": 2.7117506231464606e-06, + "loss": 0.4771, + "step": 8997 + }, + { + "epoch": 0.77, + "learning_rate": 2.7098600354346826e-06, + "loss": 0.4494, + "step": 8998 + }, + { + "epoch": 0.77, + "learning_rate": 2.7079700036994128e-06, + "loss": 0.4638, + "step": 8999 + }, + { + "epoch": 0.77, + "learning_rate": 2.7060805280847947e-06, + "loss": 0.4599, + "step": 9000 + }, + { + "epoch": 0.77, + "learning_rate": 2.7041916087349264e-06, + "loss": 0.4475, + "step": 9001 + }, + { + "epoch": 0.77, + "learning_rate": 2.702303245793865e-06, + "loss": 0.4612, + "step": 9002 + }, + { + "epoch": 0.77, + "learning_rate": 2.700415439405625e-06, + "loss": 0.4478, + "step": 9003 + }, + { + "epoch": 0.77, + "learning_rate": 2.6985281897141815e-06, + "loss": 0.4417, + "step": 9004 + }, + { + "epoch": 0.77, + "learning_rate": 2.696641496863458e-06, + "loss": 0.453, + "step": 9005 + }, + { + "epoch": 0.77, + "learning_rate": 2.694755360997342e-06, + "loss": 0.4634, + "step": 9006 + }, + { + "epoch": 0.77, + "learning_rate": 2.6928697822596863e-06, + "loss": 0.4541, + "step": 9007 + }, + { + "epoch": 0.77, + "learning_rate": 2.690984760794284e-06, + "loss": 0.4571, + "step": 9008 + }, + { + "epoch": 0.77, + "learning_rate": 2.6891002967448986e-06, + "loss": 0.4585, + "step": 9009 + }, + { + "epoch": 0.77, + "learning_rate": 2.6872163902552494e-06, + "loss": 0.4494, + "step": 9010 + }, + { + "epoch": 0.77, + "learning_rate": 2.6853330414690016e-06, + "loss": 0.4605, + "step": 9011 + }, + { + "epoch": 0.77, + "learning_rate": 2.6834502505297975e-06, + "loss": 0.4566, + "step": 9012 + }, + { + "epoch": 0.77, + "learning_rate": 2.6815680175812266e-06, + "loss": 0.455, + "step": 9013 + }, + { + "epoch": 0.77, + "learning_rate": 2.6796863427668284e-06, + "loss": 0.4698, + "step": 9014 + }, + { + "epoch": 0.77, + "learning_rate": 2.677805226230108e-06, + "loss": 0.4569, + "step": 9015 + }, + { + "epoch": 0.77, + "learning_rate": 2.675924668114537e-06, + "loss": 0.4801, + "step": 9016 + }, + { + "epoch": 0.77, + "learning_rate": 2.6740446685635246e-06, + "loss": 0.4339, + "step": 9017 + }, + { + "epoch": 0.77, + "learning_rate": 2.67216522772045e-06, + "loss": 0.4612, + "step": 9018 + }, + { + "epoch": 0.77, + "learning_rate": 2.670286345728652e-06, + "loss": 0.4509, + "step": 9019 + }, + { + "epoch": 0.77, + "learning_rate": 2.6684080227314115e-06, + "loss": 0.4715, + "step": 9020 + }, + { + "epoch": 0.77, + "learning_rate": 2.6665302588719866e-06, + "loss": 0.4634, + "step": 9021 + }, + { + "epoch": 0.77, + "learning_rate": 2.664653054293583e-06, + "loss": 0.4485, + "step": 9022 + }, + { + "epoch": 0.77, + "learning_rate": 2.6627764091393594e-06, + "loss": 0.4647, + "step": 9023 + }, + { + "epoch": 0.77, + "learning_rate": 2.6609003235524355e-06, + "loss": 0.4643, + "step": 9024 + }, + { + "epoch": 0.77, + "learning_rate": 2.6590247976758988e-06, + "loss": 0.4521, + "step": 9025 + }, + { + "epoch": 0.77, + "learning_rate": 2.6571498316527756e-06, + "loss": 0.4538, + "step": 9026 + }, + { + "epoch": 0.77, + "learning_rate": 2.6552754256260614e-06, + "loss": 0.4474, + "step": 9027 + }, + { + "epoch": 0.77, + "learning_rate": 2.6534015797387103e-06, + "loss": 0.4624, + "step": 9028 + }, + { + "epoch": 0.77, + "learning_rate": 2.6515282941336197e-06, + "loss": 0.4697, + "step": 9029 + }, + { + "epoch": 0.77, + "learning_rate": 2.649655568953663e-06, + "loss": 0.4471, + "step": 9030 + }, + { + "epoch": 0.77, + "learning_rate": 2.647783404341663e-06, + "loss": 0.4595, + "step": 9031 + }, + { + "epoch": 0.77, + "learning_rate": 2.6459118004403915e-06, + "loss": 0.4501, + "step": 9032 + }, + { + "epoch": 0.77, + "learning_rate": 2.6440407573925887e-06, + "loss": 0.462, + "step": 9033 + }, + { + "epoch": 0.77, + "learning_rate": 2.6421702753409474e-06, + "loss": 0.4597, + "step": 9034 + }, + { + "epoch": 0.77, + "learning_rate": 2.640300354428119e-06, + "loss": 0.459, + "step": 9035 + }, + { + "epoch": 0.77, + "learning_rate": 2.6384309947967124e-06, + "loss": 0.4755, + "step": 9036 + }, + { + "epoch": 0.77, + "learning_rate": 2.636562196589294e-06, + "loss": 0.4556, + "step": 9037 + }, + { + "epoch": 0.77, + "learning_rate": 2.6346939599483776e-06, + "loss": 0.455, + "step": 9038 + }, + { + "epoch": 0.77, + "learning_rate": 2.632826285016453e-06, + "loss": 0.4748, + "step": 9039 + }, + { + "epoch": 0.77, + "learning_rate": 2.6309591719359563e-06, + "loss": 0.4471, + "step": 9040 + }, + { + "epoch": 0.77, + "learning_rate": 2.629092620849274e-06, + "loss": 0.4725, + "step": 9041 + }, + { + "epoch": 0.77, + "learning_rate": 2.6272266318987606e-06, + "loss": 0.4695, + "step": 9042 + }, + { + "epoch": 0.77, + "learning_rate": 2.6253612052267254e-06, + "loss": 0.4611, + "step": 9043 + }, + { + "epoch": 0.77, + "learning_rate": 2.623496340975433e-06, + "loss": 0.4645, + "step": 9044 + }, + { + "epoch": 0.77, + "learning_rate": 2.6216320392871055e-06, + "loss": 0.4606, + "step": 9045 + }, + { + "epoch": 0.77, + "learning_rate": 2.6197683003039253e-06, + "loss": 0.461, + "step": 9046 + }, + { + "epoch": 0.77, + "learning_rate": 2.61790512416802e-06, + "loss": 0.4812, + "step": 9047 + }, + { + "epoch": 0.77, + "learning_rate": 2.6160425110214915e-06, + "loss": 0.4764, + "step": 9048 + }, + { + "epoch": 0.77, + "learning_rate": 2.6141804610063926e-06, + "loss": 0.4786, + "step": 9049 + }, + { + "epoch": 0.77, + "learning_rate": 2.6123189742647227e-06, + "loss": 0.4533, + "step": 9050 + }, + { + "epoch": 0.77, + "learning_rate": 2.6104580509384514e-06, + "loss": 0.4555, + "step": 9051 + }, + { + "epoch": 0.77, + "learning_rate": 2.6085976911694986e-06, + "loss": 0.4497, + "step": 9052 + }, + { + "epoch": 0.77, + "learning_rate": 2.606737895099745e-06, + "loss": 0.4724, + "step": 9053 + }, + { + "epoch": 0.77, + "learning_rate": 2.6048786628710244e-06, + "loss": 0.4503, + "step": 9054 + }, + { + "epoch": 0.77, + "learning_rate": 2.6030199946251334e-06, + "loss": 0.4475, + "step": 9055 + }, + { + "epoch": 0.77, + "learning_rate": 2.601161890503817e-06, + "loss": 0.4588, + "step": 9056 + }, + { + "epoch": 0.77, + "learning_rate": 2.5993043506487812e-06, + "loss": 0.4777, + "step": 9057 + }, + { + "epoch": 0.77, + "learning_rate": 2.5974473752016984e-06, + "loss": 0.4613, + "step": 9058 + }, + { + "epoch": 0.77, + "learning_rate": 2.5955909643041797e-06, + "loss": 0.4543, + "step": 9059 + }, + { + "epoch": 0.77, + "learning_rate": 2.5937351180978077e-06, + "loss": 0.4765, + "step": 9060 + }, + { + "epoch": 0.77, + "learning_rate": 2.5918798367241147e-06, + "loss": 0.456, + "step": 9061 + }, + { + "epoch": 0.77, + "learning_rate": 2.590025120324594e-06, + "loss": 0.4559, + "step": 9062 + }, + { + "epoch": 0.77, + "learning_rate": 2.5881709690406933e-06, + "loss": 0.4647, + "step": 9063 + }, + { + "epoch": 0.77, + "learning_rate": 2.5863173830138212e-06, + "loss": 0.4664, + "step": 9064 + }, + { + "epoch": 0.77, + "learning_rate": 2.5844643623853327e-06, + "loss": 0.4693, + "step": 9065 + }, + { + "epoch": 0.77, + "learning_rate": 2.5826119072965494e-06, + "loss": 0.4408, + "step": 9066 + }, + { + "epoch": 0.77, + "learning_rate": 2.5807600178887536e-06, + "loss": 0.4609, + "step": 9067 + }, + { + "epoch": 0.77, + "learning_rate": 2.5789086943031704e-06, + "loss": 0.4532, + "step": 9068 + }, + { + "epoch": 0.77, + "learning_rate": 2.577057936680992e-06, + "loss": 0.4605, + "step": 9069 + }, + { + "epoch": 0.77, + "learning_rate": 2.575207745163366e-06, + "loss": 0.4667, + "step": 9070 + }, + { + "epoch": 0.77, + "learning_rate": 2.573358119891395e-06, + "loss": 0.4588, + "step": 9071 + }, + { + "epoch": 0.77, + "learning_rate": 2.5715090610061376e-06, + "loss": 0.4537, + "step": 9072 + }, + { + "epoch": 0.77, + "learning_rate": 2.5696605686486166e-06, + "loss": 0.4698, + "step": 9073 + }, + { + "epoch": 0.77, + "learning_rate": 2.567812642959798e-06, + "loss": 0.4588, + "step": 9074 + }, + { + "epoch": 0.77, + "learning_rate": 2.5659652840806125e-06, + "loss": 0.4423, + "step": 9075 + }, + { + "epoch": 0.77, + "learning_rate": 2.5641184921519568e-06, + "loss": 0.4588, + "step": 9076 + }, + { + "epoch": 0.77, + "learning_rate": 2.562272267314666e-06, + "loss": 0.4372, + "step": 9077 + }, + { + "epoch": 0.77, + "learning_rate": 2.5604266097095433e-06, + "loss": 0.4388, + "step": 9078 + }, + { + "epoch": 0.77, + "learning_rate": 2.5585815194773466e-06, + "loss": 0.4445, + "step": 9079 + }, + { + "epoch": 0.77, + "learning_rate": 2.5567369967587907e-06, + "loss": 0.461, + "step": 9080 + }, + { + "epoch": 0.77, + "learning_rate": 2.554893041694545e-06, + "loss": 0.4781, + "step": 9081 + }, + { + "epoch": 0.77, + "learning_rate": 2.5530496544252426e-06, + "loss": 0.4641, + "step": 9082 + }, + { + "epoch": 0.77, + "learning_rate": 2.55120683509146e-06, + "loss": 0.4695, + "step": 9083 + }, + { + "epoch": 0.77, + "learning_rate": 2.549364583833739e-06, + "loss": 0.4606, + "step": 9084 + }, + { + "epoch": 0.77, + "learning_rate": 2.5475229007925863e-06, + "loss": 0.4571, + "step": 9085 + }, + { + "epoch": 0.77, + "learning_rate": 2.545681786108447e-06, + "loss": 0.4563, + "step": 9086 + }, + { + "epoch": 0.77, + "learning_rate": 2.543841239921736e-06, + "loss": 0.463, + "step": 9087 + }, + { + "epoch": 0.77, + "learning_rate": 2.542001262372821e-06, + "loss": 0.4336, + "step": 9088 + }, + { + "epoch": 0.77, + "learning_rate": 2.5401618536020255e-06, + "loss": 0.4704, + "step": 9089 + }, + { + "epoch": 0.78, + "learning_rate": 2.5383230137496308e-06, + "loss": 0.4631, + "step": 9090 + }, + { + "epoch": 0.78, + "learning_rate": 2.536484742955878e-06, + "loss": 0.4746, + "step": 9091 + }, + { + "epoch": 0.78, + "learning_rate": 2.5346470413609547e-06, + "loss": 0.4745, + "step": 9092 + }, + { + "epoch": 0.78, + "learning_rate": 2.5328099091050117e-06, + "loss": 0.4609, + "step": 9093 + }, + { + "epoch": 0.78, + "learning_rate": 2.530973346328166e-06, + "loss": 0.4477, + "step": 9094 + }, + { + "epoch": 0.78, + "learning_rate": 2.5291373531704712e-06, + "loss": 0.4402, + "step": 9095 + }, + { + "epoch": 0.78, + "learning_rate": 2.5273019297719524e-06, + "loss": 0.4691, + "step": 9096 + }, + { + "epoch": 0.78, + "learning_rate": 2.5254670762725864e-06, + "loss": 0.4649, + "step": 9097 + }, + { + "epoch": 0.78, + "learning_rate": 2.523632792812306e-06, + "loss": 0.4491, + "step": 9098 + }, + { + "epoch": 0.78, + "learning_rate": 2.5217990795310023e-06, + "loss": 0.4578, + "step": 9099 + }, + { + "epoch": 0.78, + "learning_rate": 2.5199659365685235e-06, + "loss": 0.4518, + "step": 9100 + }, + { + "epoch": 0.78, + "learning_rate": 2.5181333640646676e-06, + "loss": 0.4506, + "step": 9101 + }, + { + "epoch": 0.78, + "learning_rate": 2.5163013621591948e-06, + "loss": 0.446, + "step": 9102 + }, + { + "epoch": 0.78, + "learning_rate": 2.5144699309918296e-06, + "loss": 0.4484, + "step": 9103 + }, + { + "epoch": 0.78, + "learning_rate": 2.512639070702235e-06, + "loss": 0.4688, + "step": 9104 + }, + { + "epoch": 0.78, + "learning_rate": 2.510808781430045e-06, + "loss": 0.4621, + "step": 9105 + }, + { + "epoch": 0.78, + "learning_rate": 2.5089790633148426e-06, + "loss": 0.4676, + "step": 9106 + }, + { + "epoch": 0.78, + "learning_rate": 2.507149916496171e-06, + "loss": 0.4747, + "step": 9107 + }, + { + "epoch": 0.78, + "learning_rate": 2.5053213411135293e-06, + "loss": 0.4594, + "step": 9108 + }, + { + "epoch": 0.78, + "learning_rate": 2.503493337306373e-06, + "loss": 0.4575, + "step": 9109 + }, + { + "epoch": 0.78, + "learning_rate": 2.50166590521411e-06, + "loss": 0.4553, + "step": 9110 + }, + { + "epoch": 0.78, + "learning_rate": 2.499839044976109e-06, + "loss": 0.4473, + "step": 9111 + }, + { + "epoch": 0.78, + "learning_rate": 2.4980127567316948e-06, + "loss": 0.4593, + "step": 9112 + }, + { + "epoch": 0.78, + "learning_rate": 2.4961870406201483e-06, + "loss": 0.4584, + "step": 9113 + }, + { + "epoch": 0.78, + "learning_rate": 2.494361896780705e-06, + "loss": 0.4459, + "step": 9114 + }, + { + "epoch": 0.78, + "learning_rate": 2.4925373253525584e-06, + "loss": 0.4743, + "step": 9115 + }, + { + "epoch": 0.78, + "learning_rate": 2.4907133264748585e-06, + "loss": 0.4455, + "step": 9116 + }, + { + "epoch": 0.78, + "learning_rate": 2.4888899002867094e-06, + "loss": 0.4507, + "step": 9117 + }, + { + "epoch": 0.78, + "learning_rate": 2.4870670469271783e-06, + "loss": 0.4421, + "step": 9118 + }, + { + "epoch": 0.78, + "learning_rate": 2.4852447665352773e-06, + "loss": 0.463, + "step": 9119 + }, + { + "epoch": 0.78, + "learning_rate": 2.4834230592499833e-06, + "loss": 0.4665, + "step": 9120 + }, + { + "epoch": 0.78, + "learning_rate": 2.4816019252102274e-06, + "loss": 0.4377, + "step": 9121 + }, + { + "epoch": 0.78, + "learning_rate": 2.4797813645548973e-06, + "loss": 0.454, + "step": 9122 + }, + { + "epoch": 0.78, + "learning_rate": 2.477961377422836e-06, + "loss": 0.4519, + "step": 9123 + }, + { + "epoch": 0.78, + "learning_rate": 2.476141963952844e-06, + "loss": 0.4658, + "step": 9124 + }, + { + "epoch": 0.78, + "learning_rate": 2.474323124283676e-06, + "loss": 0.4431, + "step": 9125 + }, + { + "epoch": 0.78, + "learning_rate": 2.4725048585540456e-06, + "loss": 0.4563, + "step": 9126 + }, + { + "epoch": 0.78, + "learning_rate": 2.470687166902622e-06, + "loss": 0.4411, + "step": 9127 + }, + { + "epoch": 0.78, + "learning_rate": 2.4688700494680317e-06, + "loss": 0.4721, + "step": 9128 + }, + { + "epoch": 0.78, + "learning_rate": 2.467053506388849e-06, + "loss": 0.4377, + "step": 9129 + }, + { + "epoch": 0.78, + "learning_rate": 2.4652375378036164e-06, + "loss": 0.44, + "step": 9130 + }, + { + "epoch": 0.78, + "learning_rate": 2.4634221438508242e-06, + "loss": 0.4547, + "step": 9131 + }, + { + "epoch": 0.78, + "learning_rate": 2.4616073246689254e-06, + "loss": 0.4403, + "step": 9132 + }, + { + "epoch": 0.78, + "learning_rate": 2.459793080396322e-06, + "loss": 0.4812, + "step": 9133 + }, + { + "epoch": 0.78, + "learning_rate": 2.4579794111713793e-06, + "loss": 0.4428, + "step": 9134 + }, + { + "epoch": 0.78, + "learning_rate": 2.4561663171324137e-06, + "loss": 0.4761, + "step": 9135 + }, + { + "epoch": 0.78, + "learning_rate": 2.454353798417698e-06, + "loss": 0.4536, + "step": 9136 + }, + { + "epoch": 0.78, + "learning_rate": 2.452541855165468e-06, + "loss": 0.4362, + "step": 9137 + }, + { + "epoch": 0.78, + "learning_rate": 2.4507304875139015e-06, + "loss": 0.4571, + "step": 9138 + }, + { + "epoch": 0.78, + "learning_rate": 2.4489196956011464e-06, + "loss": 0.4393, + "step": 9139 + }, + { + "epoch": 0.78, + "learning_rate": 2.4471094795652992e-06, + "loss": 0.479, + "step": 9140 + }, + { + "epoch": 0.78, + "learning_rate": 2.445299839544416e-06, + "loss": 0.4635, + "step": 9141 + }, + { + "epoch": 0.78, + "learning_rate": 2.443490775676507e-06, + "loss": 0.4633, + "step": 9142 + }, + { + "epoch": 0.78, + "learning_rate": 2.4416822880995416e-06, + "loss": 0.4642, + "step": 9143 + }, + { + "epoch": 0.78, + "learning_rate": 2.4398743769514344e-06, + "loss": 0.4611, + "step": 9144 + }, + { + "epoch": 0.78, + "learning_rate": 2.4380670423700726e-06, + "loss": 0.462, + "step": 9145 + }, + { + "epoch": 0.78, + "learning_rate": 2.4362602844932915e-06, + "loss": 0.4382, + "step": 9146 + }, + { + "epoch": 0.78, + "learning_rate": 2.4344541034588752e-06, + "loss": 0.4654, + "step": 9147 + }, + { + "epoch": 0.78, + "learning_rate": 2.432648499404575e-06, + "loss": 0.4695, + "step": 9148 + }, + { + "epoch": 0.78, + "learning_rate": 2.430843472468093e-06, + "loss": 0.4536, + "step": 9149 + }, + { + "epoch": 0.78, + "learning_rate": 2.4290390227870874e-06, + "loss": 0.4345, + "step": 9150 + }, + { + "epoch": 0.78, + "learning_rate": 2.4272351504991744e-06, + "loss": 0.4555, + "step": 9151 + }, + { + "epoch": 0.78, + "learning_rate": 2.4254318557419256e-06, + "loss": 0.4411, + "step": 9152 + }, + { + "epoch": 0.78, + "learning_rate": 2.423629138652862e-06, + "loss": 0.4462, + "step": 9153 + }, + { + "epoch": 0.78, + "learning_rate": 2.4218269993694733e-06, + "loss": 0.4592, + "step": 9154 + }, + { + "epoch": 0.78, + "learning_rate": 2.4200254380291975e-06, + "loss": 0.4657, + "step": 9155 + }, + { + "epoch": 0.78, + "learning_rate": 2.4182244547694256e-06, + "loss": 0.481, + "step": 9156 + }, + { + "epoch": 0.78, + "learning_rate": 2.416424049727509e-06, + "loss": 0.4479, + "step": 9157 + }, + { + "epoch": 0.78, + "learning_rate": 2.414624223040756e-06, + "loss": 0.4606, + "step": 9158 + }, + { + "epoch": 0.78, + "learning_rate": 2.4128249748464262e-06, + "loss": 0.4667, + "step": 9159 + }, + { + "epoch": 0.78, + "learning_rate": 2.4110263052817396e-06, + "loss": 0.4296, + "step": 9160 + }, + { + "epoch": 0.78, + "learning_rate": 2.409228214483873e-06, + "loss": 0.4583, + "step": 9161 + }, + { + "epoch": 0.78, + "learning_rate": 2.407430702589948e-06, + "loss": 0.4571, + "step": 9162 + }, + { + "epoch": 0.78, + "learning_rate": 2.405633769737059e-06, + "loss": 0.4581, + "step": 9163 + }, + { + "epoch": 0.78, + "learning_rate": 2.403837416062246e-06, + "loss": 0.4407, + "step": 9164 + }, + { + "epoch": 0.78, + "learning_rate": 2.402041641702502e-06, + "loss": 0.4563, + "step": 9165 + }, + { + "epoch": 0.78, + "learning_rate": 2.400246446794783e-06, + "loss": 0.4367, + "step": 9166 + }, + { + "epoch": 0.78, + "learning_rate": 2.3984518314759985e-06, + "loss": 0.462, + "step": 9167 + }, + { + "epoch": 0.78, + "learning_rate": 2.396657795883013e-06, + "loss": 0.4821, + "step": 9168 + }, + { + "epoch": 0.78, + "learning_rate": 2.3948643401526463e-06, + "loss": 0.4512, + "step": 9169 + }, + { + "epoch": 0.78, + "learning_rate": 2.393071464421678e-06, + "loss": 0.4596, + "step": 9170 + }, + { + "epoch": 0.78, + "learning_rate": 2.391279168826832e-06, + "loss": 0.4375, + "step": 9171 + }, + { + "epoch": 0.78, + "learning_rate": 2.389487453504806e-06, + "loss": 0.4629, + "step": 9172 + }, + { + "epoch": 0.78, + "learning_rate": 2.387696318592242e-06, + "loss": 0.4479, + "step": 9173 + }, + { + "epoch": 0.78, + "learning_rate": 2.3859057642257343e-06, + "loss": 0.4644, + "step": 9174 + }, + { + "epoch": 0.78, + "learning_rate": 2.384115790541841e-06, + "loss": 0.4608, + "step": 9175 + }, + { + "epoch": 0.78, + "learning_rate": 2.382326397677073e-06, + "loss": 0.4596, + "step": 9176 + }, + { + "epoch": 0.78, + "learning_rate": 2.380537585767897e-06, + "loss": 0.4831, + "step": 9177 + }, + { + "epoch": 0.78, + "learning_rate": 2.3787493549507346e-06, + "loss": 0.449, + "step": 9178 + }, + { + "epoch": 0.78, + "learning_rate": 2.3769617053619666e-06, + "loss": 0.4465, + "step": 9179 + }, + { + "epoch": 0.78, + "learning_rate": 2.3751746371379193e-06, + "loss": 0.4491, + "step": 9180 + }, + { + "epoch": 0.78, + "learning_rate": 2.373388150414889e-06, + "loss": 0.454, + "step": 9181 + }, + { + "epoch": 0.78, + "learning_rate": 2.371602245329121e-06, + "loss": 0.4425, + "step": 9182 + }, + { + "epoch": 0.78, + "learning_rate": 2.369816922016811e-06, + "loss": 0.4686, + "step": 9183 + }, + { + "epoch": 0.78, + "learning_rate": 2.3680321806141182e-06, + "loss": 0.4553, + "step": 9184 + }, + { + "epoch": 0.78, + "learning_rate": 2.3662480212571536e-06, + "loss": 0.4384, + "step": 9185 + }, + { + "epoch": 0.78, + "learning_rate": 2.364464444081984e-06, + "loss": 0.4366, + "step": 9186 + }, + { + "epoch": 0.78, + "learning_rate": 2.362681449224634e-06, + "loss": 0.452, + "step": 9187 + }, + { + "epoch": 0.78, + "learning_rate": 2.360899036821085e-06, + "loss": 0.4527, + "step": 9188 + }, + { + "epoch": 0.78, + "learning_rate": 2.3591172070072644e-06, + "loss": 0.4528, + "step": 9189 + }, + { + "epoch": 0.78, + "learning_rate": 2.3573359599190616e-06, + "loss": 0.4554, + "step": 9190 + }, + { + "epoch": 0.78, + "learning_rate": 2.355555295692332e-06, + "loss": 0.4667, + "step": 9191 + }, + { + "epoch": 0.78, + "learning_rate": 2.353775214462868e-06, + "loss": 0.4434, + "step": 9192 + }, + { + "epoch": 0.78, + "learning_rate": 2.3519957163664263e-06, + "loss": 0.4528, + "step": 9193 + }, + { + "epoch": 0.78, + "learning_rate": 2.350216801538723e-06, + "loss": 0.4495, + "step": 9194 + }, + { + "epoch": 0.78, + "learning_rate": 2.3484384701154216e-06, + "loss": 0.4591, + "step": 9195 + }, + { + "epoch": 0.78, + "learning_rate": 2.346660722232148e-06, + "loss": 0.4646, + "step": 9196 + }, + { + "epoch": 0.78, + "learning_rate": 2.344883558024481e-06, + "loss": 0.479, + "step": 9197 + }, + { + "epoch": 0.78, + "learning_rate": 2.3431069776279515e-06, + "loss": 0.4619, + "step": 9198 + }, + { + "epoch": 0.78, + "learning_rate": 2.341330981178046e-06, + "loss": 0.462, + "step": 9199 + }, + { + "epoch": 0.78, + "learning_rate": 2.339555568810221e-06, + "loss": 0.4798, + "step": 9200 + }, + { + "epoch": 0.78, + "learning_rate": 2.337780740659866e-06, + "loss": 0.4656, + "step": 9201 + }, + { + "epoch": 0.78, + "learning_rate": 2.336006496862342e-06, + "loss": 0.4697, + "step": 9202 + }, + { + "epoch": 0.78, + "learning_rate": 2.3342328375529567e-06, + "loss": 0.4662, + "step": 9203 + }, + { + "epoch": 0.78, + "learning_rate": 2.3324597628669798e-06, + "loss": 0.4717, + "step": 9204 + }, + { + "epoch": 0.78, + "learning_rate": 2.3306872729396323e-06, + "loss": 0.4693, + "step": 9205 + }, + { + "epoch": 0.78, + "learning_rate": 2.328915367906095e-06, + "loss": 0.4569, + "step": 9206 + }, + { + "epoch": 0.79, + "learning_rate": 2.327144047901495e-06, + "loss": 0.4818, + "step": 9207 + }, + { + "epoch": 0.79, + "learning_rate": 2.325373313060919e-06, + "loss": 0.4532, + "step": 9208 + }, + { + "epoch": 0.79, + "learning_rate": 2.323603163519421e-06, + "loss": 0.456, + "step": 9209 + }, + { + "epoch": 0.79, + "learning_rate": 2.3218335994119913e-06, + "loss": 0.4388, + "step": 9210 + }, + { + "epoch": 0.79, + "learning_rate": 2.3200646208735866e-06, + "loss": 0.4643, + "step": 9211 + }, + { + "epoch": 0.79, + "learning_rate": 2.318296228039116e-06, + "loss": 0.4592, + "step": 9212 + }, + { + "epoch": 0.79, + "learning_rate": 2.316528421043446e-06, + "loss": 0.4627, + "step": 9213 + }, + { + "epoch": 0.79, + "learning_rate": 2.3147612000213958e-06, + "loss": 0.4787, + "step": 9214 + }, + { + "epoch": 0.79, + "learning_rate": 2.3129945651077445e-06, + "loss": 0.4542, + "step": 9215 + }, + { + "epoch": 0.79, + "learning_rate": 2.3112285164372173e-06, + "loss": 0.4647, + "step": 9216 + }, + { + "epoch": 0.79, + "learning_rate": 2.3094630541444997e-06, + "loss": 0.4494, + "step": 9217 + }, + { + "epoch": 0.79, + "learning_rate": 2.3076981783642427e-06, + "loss": 0.4457, + "step": 9218 + }, + { + "epoch": 0.79, + "learning_rate": 2.3059338892310336e-06, + "loss": 0.4519, + "step": 9219 + }, + { + "epoch": 0.79, + "learning_rate": 2.3041701868794285e-06, + "loss": 0.4476, + "step": 9220 + }, + { + "epoch": 0.79, + "learning_rate": 2.302407071443936e-06, + "loss": 0.4583, + "step": 9221 + }, + { + "epoch": 0.79, + "learning_rate": 2.300644543059012e-06, + "loss": 0.4488, + "step": 9222 + }, + { + "epoch": 0.79, + "learning_rate": 2.2988826018590816e-06, + "loss": 0.4565, + "step": 9223 + }, + { + "epoch": 0.79, + "learning_rate": 2.2971212479785175e-06, + "loss": 0.4814, + "step": 9224 + }, + { + "epoch": 0.79, + "learning_rate": 2.2953604815516427e-06, + "loss": 0.4508, + "step": 9225 + }, + { + "epoch": 0.79, + "learning_rate": 2.2936003027127418e-06, + "loss": 0.447, + "step": 9226 + }, + { + "epoch": 0.79, + "learning_rate": 2.2918407115960594e-06, + "loss": 0.4666, + "step": 9227 + }, + { + "epoch": 0.79, + "learning_rate": 2.290081708335783e-06, + "loss": 0.4517, + "step": 9228 + }, + { + "epoch": 0.79, + "learning_rate": 2.2883232930660638e-06, + "loss": 0.4652, + "step": 9229 + }, + { + "epoch": 0.79, + "learning_rate": 2.2865654659210067e-06, + "loss": 0.4949, + "step": 9230 + }, + { + "epoch": 0.79, + "learning_rate": 2.284808227034666e-06, + "loss": 0.4434, + "step": 9231 + }, + { + "epoch": 0.79, + "learning_rate": 2.283051576541062e-06, + "loss": 0.4818, + "step": 9232 + }, + { + "epoch": 0.79, + "learning_rate": 2.2812955145741644e-06, + "loss": 0.4469, + "step": 9233 + }, + { + "epoch": 0.79, + "learning_rate": 2.2795400412678926e-06, + "loss": 0.441, + "step": 9234 + }, + { + "epoch": 0.79, + "learning_rate": 2.2777851567561272e-06, + "loss": 0.4437, + "step": 9235 + }, + { + "epoch": 0.79, + "learning_rate": 2.27603086117271e-06, + "loss": 0.4501, + "step": 9236 + }, + { + "epoch": 0.79, + "learning_rate": 2.274277154651424e-06, + "loss": 0.4637, + "step": 9237 + }, + { + "epoch": 0.79, + "learning_rate": 2.272524037326015e-06, + "loss": 0.4561, + "step": 9238 + }, + { + "epoch": 0.79, + "learning_rate": 2.2707715093301872e-06, + "loss": 0.4598, + "step": 9239 + }, + { + "epoch": 0.79, + "learning_rate": 2.269019570797588e-06, + "loss": 0.4426, + "step": 9240 + }, + { + "epoch": 0.79, + "learning_rate": 2.2672682218618337e-06, + "loss": 0.4496, + "step": 9241 + }, + { + "epoch": 0.79, + "learning_rate": 2.2655174626564914e-06, + "loss": 0.4335, + "step": 9242 + }, + { + "epoch": 0.79, + "learning_rate": 2.2637672933150756e-06, + "loss": 0.4738, + "step": 9243 + }, + { + "epoch": 0.79, + "learning_rate": 2.262017713971063e-06, + "loss": 0.4493, + "step": 9244 + }, + { + "epoch": 0.79, + "learning_rate": 2.2602687247578847e-06, + "loss": 0.4366, + "step": 9245 + }, + { + "epoch": 0.79, + "learning_rate": 2.258520325808926e-06, + "loss": 0.4611, + "step": 9246 + }, + { + "epoch": 0.79, + "learning_rate": 2.256772517257527e-06, + "loss": 0.4519, + "step": 9247 + }, + { + "epoch": 0.79, + "learning_rate": 2.2550252992369837e-06, + "loss": 0.4659, + "step": 9248 + }, + { + "epoch": 0.79, + "learning_rate": 2.2532786718805444e-06, + "loss": 0.4404, + "step": 9249 + }, + { + "epoch": 0.79, + "learning_rate": 2.251532635321415e-06, + "loss": 0.4711, + "step": 9250 + }, + { + "epoch": 0.79, + "learning_rate": 2.249787189692759e-06, + "loss": 0.4506, + "step": 9251 + }, + { + "epoch": 0.79, + "learning_rate": 2.248042335127685e-06, + "loss": 0.4539, + "step": 9252 + }, + { + "epoch": 0.79, + "learning_rate": 2.2462980717592662e-06, + "loss": 0.4761, + "step": 9253 + }, + { + "epoch": 0.79, + "learning_rate": 2.2445543997205277e-06, + "loss": 0.4632, + "step": 9254 + }, + { + "epoch": 0.79, + "learning_rate": 2.242811319144448e-06, + "loss": 0.4781, + "step": 9255 + }, + { + "epoch": 0.79, + "learning_rate": 2.2410688301639617e-06, + "loss": 0.4437, + "step": 9256 + }, + { + "epoch": 0.79, + "learning_rate": 2.2393269329119603e-06, + "loss": 0.4647, + "step": 9257 + }, + { + "epoch": 0.79, + "learning_rate": 2.237585627521286e-06, + "loss": 0.4539, + "step": 9258 + }, + { + "epoch": 0.79, + "learning_rate": 2.2358449141247395e-06, + "loss": 0.464, + "step": 9259 + }, + { + "epoch": 0.79, + "learning_rate": 2.2341047928550763e-06, + "loss": 0.4798, + "step": 9260 + }, + { + "epoch": 0.79, + "learning_rate": 2.2323652638450012e-06, + "loss": 0.4634, + "step": 9261 + }, + { + "epoch": 0.79, + "learning_rate": 2.2306263272271787e-06, + "loss": 0.4559, + "step": 9262 + }, + { + "epoch": 0.79, + "learning_rate": 2.2288879831342302e-06, + "loss": 0.457, + "step": 9263 + }, + { + "epoch": 0.79, + "learning_rate": 2.227150231698727e-06, + "loss": 0.4688, + "step": 9264 + }, + { + "epoch": 0.79, + "learning_rate": 2.2254130730531977e-06, + "loss": 0.4599, + "step": 9265 + }, + { + "epoch": 0.79, + "learning_rate": 2.2236765073301247e-06, + "loss": 0.4638, + "step": 9266 + }, + { + "epoch": 0.79, + "learning_rate": 2.2219405346619505e-06, + "loss": 0.4407, + "step": 9267 + }, + { + "epoch": 0.79, + "learning_rate": 2.2202051551810568e-06, + "loss": 0.4461, + "step": 9268 + }, + { + "epoch": 0.79, + "learning_rate": 2.218470369019804e-06, + "loss": 0.4681, + "step": 9269 + }, + { + "epoch": 0.79, + "learning_rate": 2.2167361763104844e-06, + "loss": 0.4531, + "step": 9270 + }, + { + "epoch": 0.79, + "learning_rate": 2.215002577185359e-06, + "loss": 0.4658, + "step": 9271 + }, + { + "epoch": 0.79, + "learning_rate": 2.213269571776637e-06, + "loss": 0.4593, + "step": 9272 + }, + { + "epoch": 0.79, + "learning_rate": 2.211537160216487e-06, + "loss": 0.4674, + "step": 9273 + }, + { + "epoch": 0.79, + "learning_rate": 2.209805342637029e-06, + "loss": 0.4637, + "step": 9274 + }, + { + "epoch": 0.79, + "learning_rate": 2.208074119170339e-06, + "loss": 0.4644, + "step": 9275 + }, + { + "epoch": 0.79, + "learning_rate": 2.206343489948449e-06, + "loss": 0.4714, + "step": 9276 + }, + { + "epoch": 0.79, + "learning_rate": 2.204613455103337e-06, + "loss": 0.4525, + "step": 9277 + }, + { + "epoch": 0.79, + "learning_rate": 2.2028840147669527e-06, + "loss": 0.4515, + "step": 9278 + }, + { + "epoch": 0.79, + "learning_rate": 2.201155169071184e-06, + "loss": 0.4359, + "step": 9279 + }, + { + "epoch": 0.79, + "learning_rate": 2.19942691814788e-06, + "loss": 0.4573, + "step": 9280 + }, + { + "epoch": 0.79, + "learning_rate": 2.1976992621288462e-06, + "loss": 0.4435, + "step": 9281 + }, + { + "epoch": 0.79, + "learning_rate": 2.1959722011458397e-06, + "loss": 0.4567, + "step": 9282 + }, + { + "epoch": 0.79, + "learning_rate": 2.1942457353305746e-06, + "loss": 0.4406, + "step": 9283 + }, + { + "epoch": 0.79, + "learning_rate": 2.192519864814717e-06, + "loss": 0.4613, + "step": 9284 + }, + { + "epoch": 0.79, + "learning_rate": 2.1907945897298934e-06, + "loss": 0.455, + "step": 9285 + }, + { + "epoch": 0.79, + "learning_rate": 2.1890699102076707e-06, + "loss": 0.4547, + "step": 9286 + }, + { + "epoch": 0.79, + "learning_rate": 2.187345826379592e-06, + "loss": 0.4761, + "step": 9287 + }, + { + "epoch": 0.79, + "learning_rate": 2.185622338377135e-06, + "loss": 0.4687, + "step": 9288 + }, + { + "epoch": 0.79, + "learning_rate": 2.183899446331742e-06, + "loss": 0.4569, + "step": 9289 + }, + { + "epoch": 0.79, + "learning_rate": 2.182177150374809e-06, + "loss": 0.4385, + "step": 9290 + }, + { + "epoch": 0.79, + "learning_rate": 2.180455450637684e-06, + "loss": 0.4512, + "step": 9291 + }, + { + "epoch": 0.79, + "learning_rate": 2.178734347251673e-06, + "loss": 0.4599, + "step": 9292 + }, + { + "epoch": 0.79, + "learning_rate": 2.1770138403480334e-06, + "loss": 0.4338, + "step": 9293 + }, + { + "epoch": 0.79, + "learning_rate": 2.17529393005798e-06, + "loss": 0.4587, + "step": 9294 + }, + { + "epoch": 0.79, + "learning_rate": 2.173574616512675e-06, + "loss": 0.4437, + "step": 9295 + }, + { + "epoch": 0.79, + "learning_rate": 2.171855899843248e-06, + "loss": 0.447, + "step": 9296 + }, + { + "epoch": 0.79, + "learning_rate": 2.1701377801807687e-06, + "loss": 0.4574, + "step": 9297 + }, + { + "epoch": 0.79, + "learning_rate": 2.1684202576562718e-06, + "loss": 0.489, + "step": 9298 + }, + { + "epoch": 0.79, + "learning_rate": 2.166703332400741e-06, + "loss": 0.4626, + "step": 9299 + }, + { + "epoch": 0.79, + "learning_rate": 2.164987004545118e-06, + "loss": 0.4477, + "step": 9300 + }, + { + "epoch": 0.79, + "learning_rate": 2.1632712742202966e-06, + "loss": 0.4506, + "step": 9301 + }, + { + "epoch": 0.79, + "learning_rate": 2.161556141557125e-06, + "loss": 0.4438, + "step": 9302 + }, + { + "epoch": 0.79, + "learning_rate": 2.1598416066864092e-06, + "loss": 0.4469, + "step": 9303 + }, + { + "epoch": 0.79, + "learning_rate": 2.1581276697388974e-06, + "loss": 0.4753, + "step": 9304 + }, + { + "epoch": 0.79, + "learning_rate": 2.156414330845312e-06, + "loss": 0.4514, + "step": 9305 + }, + { + "epoch": 0.79, + "learning_rate": 2.154701590136319e-06, + "loss": 0.4592, + "step": 9306 + }, + { + "epoch": 0.79, + "learning_rate": 2.1529894477425327e-06, + "loss": 0.4607, + "step": 9307 + }, + { + "epoch": 0.79, + "learning_rate": 2.1512779037945318e-06, + "loss": 0.4517, + "step": 9308 + }, + { + "epoch": 0.79, + "learning_rate": 2.149566958422845e-06, + "loss": 0.4652, + "step": 9309 + }, + { + "epoch": 0.79, + "learning_rate": 2.147856611757957e-06, + "loss": 0.461, + "step": 9310 + }, + { + "epoch": 0.79, + "learning_rate": 2.146146863930304e-06, + "loss": 0.4541, + "step": 9311 + }, + { + "epoch": 0.79, + "learning_rate": 2.1444377150702845e-06, + "loss": 0.457, + "step": 9312 + }, + { + "epoch": 0.79, + "learning_rate": 2.1427291653082337e-06, + "loss": 0.4875, + "step": 9313 + }, + { + "epoch": 0.79, + "learning_rate": 2.1410212147744634e-06, + "loss": 0.4579, + "step": 9314 + }, + { + "epoch": 0.79, + "learning_rate": 2.1393138635992296e-06, + "loss": 0.4781, + "step": 9315 + }, + { + "epoch": 0.79, + "learning_rate": 2.137607111912734e-06, + "loss": 0.4369, + "step": 9316 + }, + { + "epoch": 0.79, + "learning_rate": 2.135900959845144e-06, + "loss": 0.4767, + "step": 9317 + }, + { + "epoch": 0.79, + "learning_rate": 2.134195407526579e-06, + "loss": 0.4816, + "step": 9318 + }, + { + "epoch": 0.79, + "learning_rate": 2.1324904550871107e-06, + "loss": 0.4508, + "step": 9319 + }, + { + "epoch": 0.79, + "learning_rate": 2.1307861026567667e-06, + "loss": 0.4547, + "step": 9320 + }, + { + "epoch": 0.79, + "learning_rate": 2.12908235036553e-06, + "loss": 0.4423, + "step": 9321 + }, + { + "epoch": 0.79, + "learning_rate": 2.12737919834333e-06, + "loss": 0.4688, + "step": 9322 + }, + { + "epoch": 0.79, + "learning_rate": 2.1256766467200572e-06, + "loss": 0.4788, + "step": 9323 + }, + { + "epoch": 0.8, + "learning_rate": 2.1239746956255636e-06, + "loss": 0.4802, + "step": 9324 + }, + { + "epoch": 0.8, + "learning_rate": 2.122273345189638e-06, + "loss": 0.447, + "step": 9325 + }, + { + "epoch": 0.8, + "learning_rate": 2.1205725955420353e-06, + "loss": 0.4463, + "step": 9326 + }, + { + "epoch": 0.8, + "learning_rate": 2.1188724468124634e-06, + "loss": 0.4519, + "step": 9327 + }, + { + "epoch": 0.8, + "learning_rate": 2.1171728991305797e-06, + "loss": 0.425, + "step": 9328 + }, + { + "epoch": 0.8, + "learning_rate": 2.1154739526260017e-06, + "loss": 0.4693, + "step": 9329 + }, + { + "epoch": 0.8, + "learning_rate": 2.113775607428299e-06, + "loss": 0.4472, + "step": 9330 + }, + { + "epoch": 0.8, + "learning_rate": 2.1120778636669905e-06, + "loss": 0.4614, + "step": 9331 + }, + { + "epoch": 0.8, + "learning_rate": 2.110380721471551e-06, + "loss": 0.4521, + "step": 9332 + }, + { + "epoch": 0.8, + "learning_rate": 2.108684180971423e-06, + "loss": 0.452, + "step": 9333 + }, + { + "epoch": 0.8, + "learning_rate": 2.106988242295981e-06, + "loss": 0.4637, + "step": 9334 + }, + { + "epoch": 0.8, + "learning_rate": 2.1052929055745687e-06, + "loss": 0.4535, + "step": 9335 + }, + { + "epoch": 0.8, + "learning_rate": 2.1035981709364784e-06, + "loss": 0.4494, + "step": 9336 + }, + { + "epoch": 0.8, + "learning_rate": 2.101904038510958e-06, + "loss": 0.4616, + "step": 9337 + }, + { + "epoch": 0.8, + "learning_rate": 2.1002105084272085e-06, + "loss": 0.4648, + "step": 9338 + }, + { + "epoch": 0.8, + "learning_rate": 2.0985175808143897e-06, + "loss": 0.4693, + "step": 9339 + }, + { + "epoch": 0.8, + "learning_rate": 2.0968252558016055e-06, + "loss": 0.4628, + "step": 9340 + }, + { + "epoch": 0.8, + "learning_rate": 2.095133533517919e-06, + "loss": 0.4482, + "step": 9341 + }, + { + "epoch": 0.8, + "learning_rate": 2.093442414092356e-06, + "loss": 0.459, + "step": 9342 + }, + { + "epoch": 0.8, + "learning_rate": 2.091751897653881e-06, + "loss": 0.4564, + "step": 9343 + }, + { + "epoch": 0.8, + "learning_rate": 2.090061984331423e-06, + "loss": 0.4641, + "step": 9344 + }, + { + "epoch": 0.8, + "learning_rate": 2.0883726742538625e-06, + "loss": 0.4462, + "step": 9345 + }, + { + "epoch": 0.8, + "learning_rate": 2.086683967550027e-06, + "loss": 0.4473, + "step": 9346 + }, + { + "epoch": 0.8, + "learning_rate": 2.0849958643487122e-06, + "loss": 0.4616, + "step": 9347 + }, + { + "epoch": 0.8, + "learning_rate": 2.08330836477866e-06, + "loss": 0.448, + "step": 9348 + }, + { + "epoch": 0.8, + "learning_rate": 2.0816214689685598e-06, + "loss": 0.4605, + "step": 9349 + }, + { + "epoch": 0.8, + "learning_rate": 2.079935177047061e-06, + "loss": 0.4576, + "step": 9350 + }, + { + "epoch": 0.8, + "learning_rate": 2.0782494891427773e-06, + "loss": 0.4576, + "step": 9351 + }, + { + "epoch": 0.8, + "learning_rate": 2.0765644053842583e-06, + "loss": 0.4629, + "step": 9352 + }, + { + "epoch": 0.8, + "learning_rate": 2.074879925900015e-06, + "loss": 0.448, + "step": 9353 + }, + { + "epoch": 0.8, + "learning_rate": 2.073196050818519e-06, + "loss": 0.4535, + "step": 9354 + }, + { + "epoch": 0.8, + "learning_rate": 2.07151278026818e-06, + "loss": 0.4597, + "step": 9355 + }, + { + "epoch": 0.8, + "learning_rate": 2.0698301143773793e-06, + "loss": 0.4399, + "step": 9356 + }, + { + "epoch": 0.8, + "learning_rate": 2.0681480532744436e-06, + "loss": 0.4579, + "step": 9357 + }, + { + "epoch": 0.8, + "learning_rate": 2.0664665970876496e-06, + "loss": 0.4672, + "step": 9358 + }, + { + "epoch": 0.8, + "learning_rate": 2.0647857459452324e-06, + "loss": 0.4553, + "step": 9359 + }, + { + "epoch": 0.8, + "learning_rate": 2.0631054999753876e-06, + "loss": 0.4492, + "step": 9360 + }, + { + "epoch": 0.8, + "learning_rate": 2.0614258593062496e-06, + "loss": 0.4681, + "step": 9361 + }, + { + "epoch": 0.8, + "learning_rate": 2.059746824065919e-06, + "loss": 0.471, + "step": 9362 + }, + { + "epoch": 0.8, + "learning_rate": 2.0580683943824474e-06, + "loss": 0.4671, + "step": 9363 + }, + { + "epoch": 0.8, + "learning_rate": 2.0563905703838315e-06, + "loss": 0.4592, + "step": 9364 + }, + { + "epoch": 0.8, + "learning_rate": 2.054713352198037e-06, + "loss": 0.4687, + "step": 9365 + }, + { + "epoch": 0.8, + "learning_rate": 2.053036739952976e-06, + "loss": 0.4611, + "step": 9366 + }, + { + "epoch": 0.8, + "learning_rate": 2.0513607337765074e-06, + "loss": 0.4511, + "step": 9367 + }, + { + "epoch": 0.8, + "learning_rate": 2.0496853337964508e-06, + "loss": 0.4661, + "step": 9368 + }, + { + "epoch": 0.8, + "learning_rate": 2.0480105401405882e-06, + "loss": 0.4596, + "step": 9369 + }, + { + "epoch": 0.8, + "learning_rate": 2.0463363529366375e-06, + "loss": 0.4696, + "step": 9370 + }, + { + "epoch": 0.8, + "learning_rate": 2.0446627723122826e-06, + "loss": 0.4424, + "step": 9371 + }, + { + "epoch": 0.8, + "learning_rate": 2.0429897983951585e-06, + "loss": 0.4759, + "step": 9372 + }, + { + "epoch": 0.8, + "learning_rate": 2.0413174313128483e-06, + "loss": 0.4473, + "step": 9373 + }, + { + "epoch": 0.8, + "learning_rate": 2.039645671192898e-06, + "loss": 0.4675, + "step": 9374 + }, + { + "epoch": 0.8, + "learning_rate": 2.0379745181628064e-06, + "loss": 0.4592, + "step": 9375 + }, + { + "epoch": 0.8, + "learning_rate": 2.0363039723500155e-06, + "loss": 0.4586, + "step": 9376 + }, + { + "epoch": 0.8, + "learning_rate": 2.0346340338819316e-06, + "loss": 0.4529, + "step": 9377 + }, + { + "epoch": 0.8, + "learning_rate": 2.03296470288591e-06, + "loss": 0.4553, + "step": 9378 + }, + { + "epoch": 0.8, + "learning_rate": 2.0312959794892618e-06, + "loss": 0.4675, + "step": 9379 + }, + { + "epoch": 0.8, + "learning_rate": 2.0296278638192502e-06, + "loss": 0.4522, + "step": 9380 + }, + { + "epoch": 0.8, + "learning_rate": 2.027960356003096e-06, + "loss": 0.4567, + "step": 9381 + }, + { + "epoch": 0.8, + "learning_rate": 2.0262934561679615e-06, + "loss": 0.4598, + "step": 9382 + }, + { + "epoch": 0.8, + "learning_rate": 2.0246271644409797e-06, + "loss": 0.4842, + "step": 9383 + }, + { + "epoch": 0.8, + "learning_rate": 2.0229614809492304e-06, + "loss": 0.4418, + "step": 9384 + }, + { + "epoch": 0.8, + "learning_rate": 2.021296405819738e-06, + "loss": 0.4419, + "step": 9385 + }, + { + "epoch": 0.8, + "learning_rate": 2.0196319391794927e-06, + "loss": 0.4529, + "step": 9386 + }, + { + "epoch": 0.8, + "learning_rate": 2.0179680811554324e-06, + "loss": 0.4563, + "step": 9387 + }, + { + "epoch": 0.8, + "learning_rate": 2.016304831874449e-06, + "loss": 0.459, + "step": 9388 + }, + { + "epoch": 0.8, + "learning_rate": 2.014642191463392e-06, + "loss": 0.4517, + "step": 9389 + }, + { + "epoch": 0.8, + "learning_rate": 2.0129801600490606e-06, + "loss": 0.4634, + "step": 9390 + }, + { + "epoch": 0.8, + "learning_rate": 2.0113187377582023e-06, + "loss": 0.4708, + "step": 9391 + }, + { + "epoch": 0.8, + "learning_rate": 2.009657924717532e-06, + "loss": 0.4502, + "step": 9392 + }, + { + "epoch": 0.8, + "learning_rate": 2.0079977210537084e-06, + "loss": 0.4507, + "step": 9393 + }, + { + "epoch": 0.8, + "learning_rate": 2.0063381268933426e-06, + "loss": 0.4631, + "step": 9394 + }, + { + "epoch": 0.8, + "learning_rate": 2.004679142363003e-06, + "loss": 0.459, + "step": 9395 + }, + { + "epoch": 0.8, + "learning_rate": 2.003020767589212e-06, + "loss": 0.441, + "step": 9396 + }, + { + "epoch": 0.8, + "learning_rate": 2.0013630026984433e-06, + "loss": 0.4492, + "step": 9397 + }, + { + "epoch": 0.8, + "learning_rate": 1.999705847817126e-06, + "loss": 0.4739, + "step": 9398 + }, + { + "epoch": 0.8, + "learning_rate": 1.998049303071643e-06, + "loss": 0.4593, + "step": 9399 + }, + { + "epoch": 0.8, + "learning_rate": 1.996393368588325e-06, + "loss": 0.4443, + "step": 9400 + }, + { + "epoch": 0.8, + "learning_rate": 1.9947380444934595e-06, + "loss": 0.4505, + "step": 9401 + }, + { + "epoch": 0.8, + "learning_rate": 1.993083330913298e-06, + "loss": 0.4556, + "step": 9402 + }, + { + "epoch": 0.8, + "learning_rate": 1.9914292279740256e-06, + "loss": 0.455, + "step": 9403 + }, + { + "epoch": 0.8, + "learning_rate": 1.9897757358017956e-06, + "loss": 0.473, + "step": 9404 + }, + { + "epoch": 0.8, + "learning_rate": 1.9881228545227106e-06, + "loss": 0.4558, + "step": 9405 + }, + { + "epoch": 0.8, + "learning_rate": 1.986470584262824e-06, + "loss": 0.4535, + "step": 9406 + }, + { + "epoch": 0.8, + "learning_rate": 1.9848189251481465e-06, + "loss": 0.4525, + "step": 9407 + }, + { + "epoch": 0.8, + "learning_rate": 1.9831678773046424e-06, + "loss": 0.4699, + "step": 9408 + }, + { + "epoch": 0.8, + "learning_rate": 1.9815174408582237e-06, + "loss": 0.4786, + "step": 9409 + }, + { + "epoch": 0.8, + "learning_rate": 1.9798676159347574e-06, + "loss": 0.4519, + "step": 9410 + }, + { + "epoch": 0.8, + "learning_rate": 1.978218402660076e-06, + "loss": 0.4524, + "step": 9411 + }, + { + "epoch": 0.8, + "learning_rate": 1.9765698011599464e-06, + "loss": 0.4746, + "step": 9412 + }, + { + "epoch": 0.8, + "learning_rate": 1.9749218115601e-06, + "loss": 0.4575, + "step": 9413 + }, + { + "epoch": 0.8, + "learning_rate": 1.9732744339862197e-06, + "loss": 0.4603, + "step": 9414 + }, + { + "epoch": 0.8, + "learning_rate": 1.9716276685639426e-06, + "loss": 0.4594, + "step": 9415 + }, + { + "epoch": 0.8, + "learning_rate": 1.9699815154188563e-06, + "loss": 0.4591, + "step": 9416 + }, + { + "epoch": 0.8, + "learning_rate": 1.9683359746765063e-06, + "loss": 0.4641, + "step": 9417 + }, + { + "epoch": 0.8, + "learning_rate": 1.9666910464623844e-06, + "loss": 0.4524, + "step": 9418 + }, + { + "epoch": 0.8, + "learning_rate": 1.965046730901938e-06, + "loss": 0.4469, + "step": 9419 + }, + { + "epoch": 0.8, + "learning_rate": 1.9634030281205786e-06, + "loss": 0.4652, + "step": 9420 + }, + { + "epoch": 0.8, + "learning_rate": 1.9617599382436526e-06, + "loss": 0.4726, + "step": 9421 + }, + { + "epoch": 0.8, + "learning_rate": 1.960117461396472e-06, + "loss": 0.4701, + "step": 9422 + }, + { + "epoch": 0.8, + "learning_rate": 1.9584755977043014e-06, + "loss": 0.4558, + "step": 9423 + }, + { + "epoch": 0.8, + "learning_rate": 1.9568343472923524e-06, + "loss": 0.4593, + "step": 9424 + }, + { + "epoch": 0.8, + "learning_rate": 1.9551937102857955e-06, + "loss": 0.4488, + "step": 9425 + }, + { + "epoch": 0.8, + "learning_rate": 1.9535536868097526e-06, + "loss": 0.4398, + "step": 9426 + }, + { + "epoch": 0.8, + "learning_rate": 1.9519142769893006e-06, + "loss": 0.4689, + "step": 9427 + }, + { + "epoch": 0.8, + "learning_rate": 1.9502754809494606e-06, + "loss": 0.4578, + "step": 9428 + }, + { + "epoch": 0.8, + "learning_rate": 1.9486372988152246e-06, + "loss": 0.46, + "step": 9429 + }, + { + "epoch": 0.8, + "learning_rate": 1.9469997307115185e-06, + "loss": 0.4663, + "step": 9430 + }, + { + "epoch": 0.8, + "learning_rate": 1.9453627767632344e-06, + "loss": 0.4568, + "step": 9431 + }, + { + "epoch": 0.8, + "learning_rate": 1.94372643709521e-06, + "loss": 0.4572, + "step": 9432 + }, + { + "epoch": 0.8, + "learning_rate": 1.9420907118322428e-06, + "loss": 0.4527, + "step": 9433 + }, + { + "epoch": 0.8, + "learning_rate": 1.9404556010990792e-06, + "loss": 0.4484, + "step": 9434 + }, + { + "epoch": 0.8, + "learning_rate": 1.9388211050204175e-06, + "loss": 0.4733, + "step": 9435 + }, + { + "epoch": 0.8, + "learning_rate": 1.9371872237209167e-06, + "loss": 0.4445, + "step": 9436 + }, + { + "epoch": 0.8, + "learning_rate": 1.9355539573251737e-06, + "loss": 0.4551, + "step": 9437 + }, + { + "epoch": 0.8, + "learning_rate": 1.9339213059577587e-06, + "loss": 0.4505, + "step": 9438 + }, + { + "epoch": 0.8, + "learning_rate": 1.9322892697431783e-06, + "loss": 0.4513, + "step": 9439 + }, + { + "epoch": 0.8, + "learning_rate": 1.9306578488058993e-06, + "loss": 0.4682, + "step": 9440 + }, + { + "epoch": 0.8, + "learning_rate": 1.9290270432703408e-06, + "loss": 0.439, + "step": 9441 + }, + { + "epoch": 0.81, + "learning_rate": 1.9273968532608754e-06, + "loss": 0.4409, + "step": 9442 + }, + { + "epoch": 0.81, + "learning_rate": 1.925767278901828e-06, + "loss": 0.4516, + "step": 9443 + }, + { + "epoch": 0.81, + "learning_rate": 1.924138320317477e-06, + "loss": 0.4567, + "step": 9444 + }, + { + "epoch": 0.81, + "learning_rate": 1.9225099776320567e-06, + "loss": 0.4832, + "step": 9445 + }, + { + "epoch": 0.81, + "learning_rate": 1.920882250969742e-06, + "loss": 0.4588, + "step": 9446 + }, + { + "epoch": 0.81, + "learning_rate": 1.9192551404546812e-06, + "loss": 0.4671, + "step": 9447 + }, + { + "epoch": 0.81, + "learning_rate": 1.9176286462109574e-06, + "loss": 0.4322, + "step": 9448 + }, + { + "epoch": 0.81, + "learning_rate": 1.916002768362616e-06, + "loss": 0.4507, + "step": 9449 + }, + { + "epoch": 0.81, + "learning_rate": 1.9143775070336523e-06, + "loss": 0.474, + "step": 9450 + }, + { + "epoch": 0.81, + "learning_rate": 1.9127528623480175e-06, + "loss": 0.4534, + "step": 9451 + }, + { + "epoch": 0.81, + "learning_rate": 1.911128834429612e-06, + "loss": 0.4558, + "step": 9452 + }, + { + "epoch": 0.81, + "learning_rate": 1.9095054234022915e-06, + "loss": 0.4647, + "step": 9453 + }, + { + "epoch": 0.81, + "learning_rate": 1.9078826293898676e-06, + "loss": 0.4459, + "step": 9454 + }, + { + "epoch": 0.81, + "learning_rate": 1.9062604525160944e-06, + "loss": 0.4395, + "step": 9455 + }, + { + "epoch": 0.81, + "learning_rate": 1.90463889290469e-06, + "loss": 0.4563, + "step": 9456 + }, + { + "epoch": 0.81, + "learning_rate": 1.9030179506793201e-06, + "loss": 0.4521, + "step": 9457 + }, + { + "epoch": 0.81, + "learning_rate": 1.9013976259636057e-06, + "loss": 0.4436, + "step": 9458 + }, + { + "epoch": 0.81, + "learning_rate": 1.8997779188811194e-06, + "loss": 0.4585, + "step": 9459 + }, + { + "epoch": 0.81, + "learning_rate": 1.8981588295553855e-06, + "loss": 0.4432, + "step": 9460 + }, + { + "epoch": 0.81, + "learning_rate": 1.896540358109884e-06, + "loss": 0.4378, + "step": 9461 + }, + { + "epoch": 0.81, + "learning_rate": 1.8949225046680464e-06, + "loss": 0.4632, + "step": 9462 + }, + { + "epoch": 0.81, + "learning_rate": 1.893305269353257e-06, + "loss": 0.4764, + "step": 9463 + }, + { + "epoch": 0.81, + "learning_rate": 1.891688652288851e-06, + "loss": 0.463, + "step": 9464 + }, + { + "epoch": 0.81, + "learning_rate": 1.8900726535981195e-06, + "loss": 0.4429, + "step": 9465 + }, + { + "epoch": 0.81, + "learning_rate": 1.888457273404305e-06, + "loss": 0.477, + "step": 9466 + }, + { + "epoch": 0.81, + "learning_rate": 1.8868425118306033e-06, + "loss": 0.45, + "step": 9467 + }, + { + "epoch": 0.81, + "learning_rate": 1.8852283690001638e-06, + "loss": 0.4408, + "step": 9468 + }, + { + "epoch": 0.81, + "learning_rate": 1.883614845036087e-06, + "loss": 0.4774, + "step": 9469 + }, + { + "epoch": 0.81, + "learning_rate": 1.8820019400614264e-06, + "loss": 0.4479, + "step": 9470 + }, + { + "epoch": 0.81, + "learning_rate": 1.8803896541991895e-06, + "loss": 0.4524, + "step": 9471 + }, + { + "epoch": 0.81, + "learning_rate": 1.8787779875723389e-06, + "loss": 0.4599, + "step": 9472 + }, + { + "epoch": 0.81, + "learning_rate": 1.8771669403037807e-06, + "loss": 0.4606, + "step": 9473 + }, + { + "epoch": 0.81, + "learning_rate": 1.8755565125163844e-06, + "loss": 0.4372, + "step": 9474 + }, + { + "epoch": 0.81, + "learning_rate": 1.8739467043329663e-06, + "loss": 0.4452, + "step": 9475 + }, + { + "epoch": 0.81, + "learning_rate": 1.872337515876298e-06, + "loss": 0.4518, + "step": 9476 + }, + { + "epoch": 0.81, + "learning_rate": 1.8707289472691037e-06, + "loss": 0.474, + "step": 9477 + }, + { + "epoch": 0.81, + "learning_rate": 1.8691209986340598e-06, + "loss": 0.4501, + "step": 9478 + }, + { + "epoch": 0.81, + "learning_rate": 1.867513670093789e-06, + "loss": 0.4342, + "step": 9479 + }, + { + "epoch": 0.81, + "learning_rate": 1.8659069617708802e-06, + "loss": 0.4387, + "step": 9480 + }, + { + "epoch": 0.81, + "learning_rate": 1.8643008737878687e-06, + "loss": 0.4608, + "step": 9481 + }, + { + "epoch": 0.81, + "learning_rate": 1.8626954062672353e-06, + "loss": 0.4563, + "step": 9482 + }, + { + "epoch": 0.81, + "learning_rate": 1.8610905593314199e-06, + "loss": 0.4568, + "step": 9483 + }, + { + "epoch": 0.81, + "learning_rate": 1.8594863331028224e-06, + "loss": 0.4482, + "step": 9484 + }, + { + "epoch": 0.81, + "learning_rate": 1.8578827277037804e-06, + "loss": 0.4616, + "step": 9485 + }, + { + "epoch": 0.81, + "learning_rate": 1.8562797432565926e-06, + "loss": 0.4512, + "step": 9486 + }, + { + "epoch": 0.81, + "learning_rate": 1.8546773798835149e-06, + "loss": 0.4589, + "step": 9487 + }, + { + "epoch": 0.81, + "learning_rate": 1.8530756377067394e-06, + "loss": 0.4634, + "step": 9488 + }, + { + "epoch": 0.81, + "learning_rate": 1.8514745168484317e-06, + "loss": 0.4626, + "step": 9489 + }, + { + "epoch": 0.81, + "learning_rate": 1.8498740174306984e-06, + "loss": 0.4613, + "step": 9490 + }, + { + "epoch": 0.81, + "learning_rate": 1.8482741395755966e-06, + "loss": 0.4436, + "step": 9491 + }, + { + "epoch": 0.81, + "learning_rate": 1.8466748834051374e-06, + "loss": 0.4573, + "step": 9492 + }, + { + "epoch": 0.81, + "learning_rate": 1.8450762490412965e-06, + "loss": 0.4509, + "step": 9493 + }, + { + "epoch": 0.81, + "learning_rate": 1.8434782366059844e-06, + "loss": 0.451, + "step": 9494 + }, + { + "epoch": 0.81, + "learning_rate": 1.8418808462210746e-06, + "loss": 0.4434, + "step": 9495 + }, + { + "epoch": 0.81, + "learning_rate": 1.840284078008393e-06, + "loss": 0.4573, + "step": 9496 + }, + { + "epoch": 0.81, + "learning_rate": 1.8386879320897077e-06, + "loss": 0.4449, + "step": 9497 + }, + { + "epoch": 0.81, + "learning_rate": 1.8370924085867558e-06, + "loss": 0.4872, + "step": 9498 + }, + { + "epoch": 0.81, + "learning_rate": 1.8354975076212188e-06, + "loss": 0.4647, + "step": 9499 + }, + { + "epoch": 0.81, + "learning_rate": 1.8339032293147251e-06, + "loss": 0.4524, + "step": 9500 + }, + { + "epoch": 0.81, + "learning_rate": 1.8323095737888607e-06, + "loss": 0.4869, + "step": 9501 + }, + { + "epoch": 0.81, + "learning_rate": 1.8307165411651728e-06, + "loss": 0.4623, + "step": 9502 + }, + { + "epoch": 0.81, + "learning_rate": 1.8291241315651442e-06, + "loss": 0.4764, + "step": 9503 + }, + { + "epoch": 0.81, + "learning_rate": 1.8275323451102223e-06, + "loss": 0.4428, + "step": 9504 + }, + { + "epoch": 0.81, + "learning_rate": 1.8259411819218054e-06, + "loss": 0.4456, + "step": 9505 + }, + { + "epoch": 0.81, + "learning_rate": 1.8243506421212332e-06, + "loss": 0.46, + "step": 9506 + }, + { + "epoch": 0.81, + "learning_rate": 1.8227607258298175e-06, + "loss": 0.4379, + "step": 9507 + }, + { + "epoch": 0.81, + "learning_rate": 1.821171433168809e-06, + "loss": 0.4608, + "step": 9508 + }, + { + "epoch": 0.81, + "learning_rate": 1.819582764259411e-06, + "loss": 0.4485, + "step": 9509 + }, + { + "epoch": 0.81, + "learning_rate": 1.8179947192227832e-06, + "loss": 0.4567, + "step": 9510 + }, + { + "epoch": 0.81, + "learning_rate": 1.8164072981800374e-06, + "loss": 0.4567, + "step": 9511 + }, + { + "epoch": 0.81, + "learning_rate": 1.8148205012522357e-06, + "loss": 0.4681, + "step": 9512 + }, + { + "epoch": 0.81, + "learning_rate": 1.813234328560396e-06, + "loss": 0.4414, + "step": 9513 + }, + { + "epoch": 0.81, + "learning_rate": 1.8116487802254868e-06, + "loss": 0.4585, + "step": 9514 + }, + { + "epoch": 0.81, + "learning_rate": 1.8100638563684214e-06, + "loss": 0.4818, + "step": 9515 + }, + { + "epoch": 0.81, + "learning_rate": 1.808479557110081e-06, + "loss": 0.4604, + "step": 9516 + }, + { + "epoch": 0.81, + "learning_rate": 1.8068958825712912e-06, + "loss": 0.4641, + "step": 9517 + }, + { + "epoch": 0.81, + "learning_rate": 1.8053128328728243e-06, + "loss": 0.4766, + "step": 9518 + }, + { + "epoch": 0.81, + "learning_rate": 1.8037304081354124e-06, + "loss": 0.4568, + "step": 9519 + }, + { + "epoch": 0.81, + "learning_rate": 1.8021486084797368e-06, + "loss": 0.4428, + "step": 9520 + }, + { + "epoch": 0.81, + "learning_rate": 1.8005674340264346e-06, + "loss": 0.4558, + "step": 9521 + }, + { + "epoch": 0.81, + "learning_rate": 1.798986884896091e-06, + "loss": 0.4778, + "step": 9522 + }, + { + "epoch": 0.81, + "learning_rate": 1.7974069612092481e-06, + "loss": 0.442, + "step": 9523 + }, + { + "epoch": 0.81, + "learning_rate": 1.7958276630863903e-06, + "loss": 0.461, + "step": 9524 + }, + { + "epoch": 0.81, + "learning_rate": 1.7942489906479687e-06, + "loss": 0.451, + "step": 9525 + }, + { + "epoch": 0.81, + "learning_rate": 1.7926709440143797e-06, + "loss": 0.4485, + "step": 9526 + }, + { + "epoch": 0.81, + "learning_rate": 1.7910935233059667e-06, + "loss": 0.4493, + "step": 9527 + }, + { + "epoch": 0.81, + "learning_rate": 1.7895167286430326e-06, + "loss": 0.455, + "step": 9528 + }, + { + "epoch": 0.81, + "learning_rate": 1.7879405601458311e-06, + "loss": 0.4614, + "step": 9529 + }, + { + "epoch": 0.81, + "learning_rate": 1.786365017934566e-06, + "loss": 0.4534, + "step": 9530 + }, + { + "epoch": 0.81, + "learning_rate": 1.7847901021293956e-06, + "loss": 0.4658, + "step": 9531 + }, + { + "epoch": 0.81, + "learning_rate": 1.7832158128504328e-06, + "loss": 0.4644, + "step": 9532 + }, + { + "epoch": 0.81, + "learning_rate": 1.7816421502177328e-06, + "loss": 0.4563, + "step": 9533 + }, + { + "epoch": 0.81, + "learning_rate": 1.7800691143513104e-06, + "loss": 0.4533, + "step": 9534 + }, + { + "epoch": 0.81, + "learning_rate": 1.77849670537114e-06, + "loss": 0.4626, + "step": 9535 + }, + { + "epoch": 0.81, + "learning_rate": 1.776924923397132e-06, + "loss": 0.4632, + "step": 9536 + }, + { + "epoch": 0.81, + "learning_rate": 1.7753537685491596e-06, + "loss": 0.4541, + "step": 9537 + }, + { + "epoch": 0.81, + "learning_rate": 1.7737832409470458e-06, + "loss": 0.4541, + "step": 9538 + }, + { + "epoch": 0.81, + "learning_rate": 1.7722133407105656e-06, + "loss": 0.4439, + "step": 9539 + }, + { + "epoch": 0.81, + "learning_rate": 1.7706440679594462e-06, + "loss": 0.4606, + "step": 9540 + }, + { + "epoch": 0.81, + "learning_rate": 1.7690754228133688e-06, + "loss": 0.444, + "step": 9541 + }, + { + "epoch": 0.81, + "learning_rate": 1.7675074053919606e-06, + "loss": 0.4657, + "step": 9542 + }, + { + "epoch": 0.81, + "learning_rate": 1.7659400158148043e-06, + "loss": 0.4828, + "step": 9543 + }, + { + "epoch": 0.81, + "learning_rate": 1.7643732542014437e-06, + "loss": 0.4599, + "step": 9544 + }, + { + "epoch": 0.81, + "learning_rate": 1.7628071206713582e-06, + "loss": 0.4915, + "step": 9545 + }, + { + "epoch": 0.81, + "learning_rate": 1.7612416153439916e-06, + "loss": 0.438, + "step": 9546 + }, + { + "epoch": 0.81, + "learning_rate": 1.7596767383387359e-06, + "loss": 0.4686, + "step": 9547 + }, + { + "epoch": 0.81, + "learning_rate": 1.7581124897749335e-06, + "loss": 0.4649, + "step": 9548 + }, + { + "epoch": 0.81, + "learning_rate": 1.7565488697718814e-06, + "loss": 0.4428, + "step": 9549 + }, + { + "epoch": 0.81, + "learning_rate": 1.7549858784488317e-06, + "loss": 0.4537, + "step": 9550 + }, + { + "epoch": 0.81, + "learning_rate": 1.7534235159249768e-06, + "loss": 0.4468, + "step": 9551 + }, + { + "epoch": 0.81, + "learning_rate": 1.7518617823194705e-06, + "loss": 0.4437, + "step": 9552 + }, + { + "epoch": 0.81, + "learning_rate": 1.7503006777514254e-06, + "loss": 0.456, + "step": 9553 + }, + { + "epoch": 0.81, + "learning_rate": 1.7487402023398891e-06, + "loss": 0.4803, + "step": 9554 + }, + { + "epoch": 0.81, + "learning_rate": 1.7471803562038737e-06, + "loss": 0.453, + "step": 9555 + }, + { + "epoch": 0.81, + "learning_rate": 1.7456211394623379e-06, + "loss": 0.463, + "step": 9556 + }, + { + "epoch": 0.81, + "learning_rate": 1.7440625522341958e-06, + "loss": 0.4525, + "step": 9557 + }, + { + "epoch": 0.81, + "learning_rate": 1.74250459463831e-06, + "loss": 0.4537, + "step": 9558 + }, + { + "epoch": 0.82, + "learning_rate": 1.7409472667935012e-06, + "loss": 0.4485, + "step": 9559 + }, + { + "epoch": 0.82, + "learning_rate": 1.7393905688185319e-06, + "loss": 0.4626, + "step": 9560 + }, + { + "epoch": 0.82, + "learning_rate": 1.737834500832122e-06, + "loss": 0.4505, + "step": 9561 + }, + { + "epoch": 0.82, + "learning_rate": 1.7362790629529513e-06, + "loss": 0.4346, + "step": 9562 + }, + { + "epoch": 0.82, + "learning_rate": 1.734724255299637e-06, + "loss": 0.4916, + "step": 9563 + }, + { + "epoch": 0.82, + "learning_rate": 1.7331700779907579e-06, + "loss": 0.4376, + "step": 9564 + }, + { + "epoch": 0.82, + "learning_rate": 1.7316165311448407e-06, + "loss": 0.4482, + "step": 9565 + }, + { + "epoch": 0.82, + "learning_rate": 1.7300636148803674e-06, + "loss": 0.4717, + "step": 9566 + }, + { + "epoch": 0.82, + "learning_rate": 1.7285113293157673e-06, + "loss": 0.4583, + "step": 9567 + }, + { + "epoch": 0.82, + "learning_rate": 1.7269596745694295e-06, + "loss": 0.4456, + "step": 9568 + }, + { + "epoch": 0.82, + "learning_rate": 1.7254086507596834e-06, + "loss": 0.45, + "step": 9569 + }, + { + "epoch": 0.82, + "learning_rate": 1.7238582580048157e-06, + "loss": 0.4685, + "step": 9570 + }, + { + "epoch": 0.82, + "learning_rate": 1.722308496423074e-06, + "loss": 0.44, + "step": 9571 + }, + { + "epoch": 0.82, + "learning_rate": 1.7207593661326427e-06, + "loss": 0.4647, + "step": 9572 + }, + { + "epoch": 0.82, + "learning_rate": 1.7192108672516672e-06, + "loss": 0.4576, + "step": 9573 + }, + { + "epoch": 0.82, + "learning_rate": 1.7176629998982408e-06, + "loss": 0.4736, + "step": 9574 + }, + { + "epoch": 0.82, + "learning_rate": 1.7161157641904136e-06, + "loss": 0.4352, + "step": 9575 + }, + { + "epoch": 0.82, + "learning_rate": 1.7145691602461812e-06, + "loss": 0.4801, + "step": 9576 + }, + { + "epoch": 0.82, + "learning_rate": 1.713023188183498e-06, + "loss": 0.4572, + "step": 9577 + }, + { + "epoch": 0.82, + "learning_rate": 1.711477848120261e-06, + "loss": 0.4373, + "step": 9578 + }, + { + "epoch": 0.82, + "learning_rate": 1.7099331401743247e-06, + "loss": 0.4499, + "step": 9579 + }, + { + "epoch": 0.82, + "learning_rate": 1.7083890644635015e-06, + "loss": 0.4549, + "step": 9580 + }, + { + "epoch": 0.82, + "learning_rate": 1.706845621105543e-06, + "loss": 0.4578, + "step": 9581 + }, + { + "epoch": 0.82, + "learning_rate": 1.7053028102181601e-06, + "loss": 0.4566, + "step": 9582 + }, + { + "epoch": 0.82, + "learning_rate": 1.7037606319190137e-06, + "loss": 0.4669, + "step": 9583 + }, + { + "epoch": 0.82, + "learning_rate": 1.7022190863257182e-06, + "loss": 0.4483, + "step": 9584 + }, + { + "epoch": 0.82, + "learning_rate": 1.7006781735558364e-06, + "loss": 0.4351, + "step": 9585 + }, + { + "epoch": 0.82, + "learning_rate": 1.6991378937268888e-06, + "loss": 0.4479, + "step": 9586 + }, + { + "epoch": 0.82, + "learning_rate": 1.6975982469563369e-06, + "loss": 0.464, + "step": 9587 + }, + { + "epoch": 0.82, + "learning_rate": 1.6960592333616055e-06, + "loss": 0.4645, + "step": 9588 + }, + { + "epoch": 0.82, + "learning_rate": 1.6945208530600644e-06, + "loss": 0.4612, + "step": 9589 + }, + { + "epoch": 0.82, + "learning_rate": 1.6929831061690371e-06, + "loss": 0.4685, + "step": 9590 + }, + { + "epoch": 0.82, + "learning_rate": 1.6914459928057992e-06, + "loss": 0.4668, + "step": 9591 + }, + { + "epoch": 0.82, + "learning_rate": 1.6899095130875775e-06, + "loss": 0.4383, + "step": 9592 + }, + { + "epoch": 0.82, + "learning_rate": 1.6883736671315488e-06, + "loss": 0.4579, + "step": 9593 + }, + { + "epoch": 0.82, + "learning_rate": 1.6868384550548455e-06, + "loss": 0.4433, + "step": 9594 + }, + { + "epoch": 0.82, + "learning_rate": 1.6853038769745466e-06, + "loss": 0.4463, + "step": 9595 + }, + { + "epoch": 0.82, + "learning_rate": 1.6837699330076906e-06, + "loss": 0.4805, + "step": 9596 + }, + { + "epoch": 0.82, + "learning_rate": 1.682236623271256e-06, + "loss": 0.4571, + "step": 9597 + }, + { + "epoch": 0.82, + "learning_rate": 1.680703947882182e-06, + "loss": 0.4282, + "step": 9598 + }, + { + "epoch": 0.82, + "learning_rate": 1.6791719069573563e-06, + "loss": 0.4545, + "step": 9599 + }, + { + "epoch": 0.82, + "learning_rate": 1.6776405006136199e-06, + "loss": 0.4698, + "step": 9600 + }, + { + "epoch": 0.82, + "learning_rate": 1.6761097289677642e-06, + "loss": 0.4505, + "step": 9601 + }, + { + "epoch": 0.82, + "learning_rate": 1.6745795921365314e-06, + "loss": 0.4576, + "step": 9602 + }, + { + "epoch": 0.82, + "learning_rate": 1.6730500902366165e-06, + "loss": 0.4697, + "step": 9603 + }, + { + "epoch": 0.82, + "learning_rate": 1.6715212233846656e-06, + "loss": 0.4658, + "step": 9604 + }, + { + "epoch": 0.82, + "learning_rate": 1.669992991697279e-06, + "loss": 0.4696, + "step": 9605 + }, + { + "epoch": 0.82, + "learning_rate": 1.6684653952910013e-06, + "loss": 0.4627, + "step": 9606 + }, + { + "epoch": 0.82, + "learning_rate": 1.6669384342823347e-06, + "loss": 0.4384, + "step": 9607 + }, + { + "epoch": 0.82, + "learning_rate": 1.665412108787734e-06, + "loss": 0.4495, + "step": 9608 + }, + { + "epoch": 0.82, + "learning_rate": 1.6638864189236015e-06, + "loss": 0.4551, + "step": 9609 + }, + { + "epoch": 0.82, + "learning_rate": 1.662361364806292e-06, + "loss": 0.4489, + "step": 9610 + }, + { + "epoch": 0.82, + "learning_rate": 1.6608369465521169e-06, + "loss": 0.4356, + "step": 9611 + }, + { + "epoch": 0.82, + "learning_rate": 1.6593131642773252e-06, + "loss": 0.483, + "step": 9612 + }, + { + "epoch": 0.82, + "learning_rate": 1.6577900180981366e-06, + "loss": 0.464, + "step": 9613 + }, + { + "epoch": 0.82, + "learning_rate": 1.6562675081307101e-06, + "loss": 0.4644, + "step": 9614 + }, + { + "epoch": 0.82, + "learning_rate": 1.654745634491156e-06, + "loss": 0.4681, + "step": 9615 + }, + { + "epoch": 0.82, + "learning_rate": 1.6532243972955397e-06, + "loss": 0.459, + "step": 9616 + }, + { + "epoch": 0.82, + "learning_rate": 1.651703796659878e-06, + "loss": 0.4344, + "step": 9617 + }, + { + "epoch": 0.82, + "learning_rate": 1.6501838327001374e-06, + "loss": 0.478, + "step": 9618 + }, + { + "epoch": 0.82, + "learning_rate": 1.6486645055322381e-06, + "loss": 0.4612, + "step": 9619 + }, + { + "epoch": 0.82, + "learning_rate": 1.647145815272051e-06, + "loss": 0.4539, + "step": 9620 + }, + { + "epoch": 0.82, + "learning_rate": 1.645627762035391e-06, + "loss": 0.4436, + "step": 9621 + }, + { + "epoch": 0.82, + "learning_rate": 1.6441103459380392e-06, + "loss": 0.4543, + "step": 9622 + }, + { + "epoch": 0.82, + "learning_rate": 1.6425935670957194e-06, + "loss": 0.4554, + "step": 9623 + }, + { + "epoch": 0.82, + "learning_rate": 1.6410774256241036e-06, + "loss": 0.4553, + "step": 9624 + }, + { + "epoch": 0.82, + "learning_rate": 1.6395619216388204e-06, + "loss": 0.4561, + "step": 9625 + }, + { + "epoch": 0.82, + "learning_rate": 1.6380470552554483e-06, + "loss": 0.4668, + "step": 9626 + }, + { + "epoch": 0.82, + "learning_rate": 1.6365328265895186e-06, + "loss": 0.4517, + "step": 9627 + }, + { + "epoch": 0.82, + "learning_rate": 1.635019235756511e-06, + "loss": 0.4706, + "step": 9628 + }, + { + "epoch": 0.82, + "learning_rate": 1.633506282871863e-06, + "loss": 0.4543, + "step": 9629 + }, + { + "epoch": 0.82, + "learning_rate": 1.631993968050949e-06, + "loss": 0.4463, + "step": 9630 + }, + { + "epoch": 0.82, + "learning_rate": 1.6304822914091134e-06, + "loss": 0.4422, + "step": 9631 + }, + { + "epoch": 0.82, + "learning_rate": 1.628971253061642e-06, + "loss": 0.4495, + "step": 9632 + }, + { + "epoch": 0.82, + "learning_rate": 1.6274608531237679e-06, + "loss": 0.447, + "step": 9633 + }, + { + "epoch": 0.82, + "learning_rate": 1.6259510917106847e-06, + "loss": 0.4475, + "step": 9634 + }, + { + "epoch": 0.82, + "learning_rate": 1.6244419689375313e-06, + "loss": 0.4478, + "step": 9635 + }, + { + "epoch": 0.82, + "learning_rate": 1.6229334849194001e-06, + "loss": 0.4653, + "step": 9636 + }, + { + "epoch": 0.82, + "learning_rate": 1.6214256397713347e-06, + "loss": 0.4377, + "step": 9637 + }, + { + "epoch": 0.82, + "learning_rate": 1.6199184336083319e-06, + "loss": 0.462, + "step": 9638 + }, + { + "epoch": 0.82, + "learning_rate": 1.6184118665453296e-06, + "loss": 0.4546, + "step": 9639 + }, + { + "epoch": 0.82, + "learning_rate": 1.6169059386972342e-06, + "loss": 0.4544, + "step": 9640 + }, + { + "epoch": 0.82, + "learning_rate": 1.615400650178891e-06, + "loss": 0.4543, + "step": 9641 + }, + { + "epoch": 0.82, + "learning_rate": 1.6138960011050974e-06, + "loss": 0.4622, + "step": 9642 + }, + { + "epoch": 0.82, + "learning_rate": 1.612391991590606e-06, + "loss": 0.4656, + "step": 9643 + }, + { + "epoch": 0.82, + "learning_rate": 1.6108886217501184e-06, + "loss": 0.4641, + "step": 9644 + }, + { + "epoch": 0.82, + "learning_rate": 1.6093858916982884e-06, + "loss": 0.4585, + "step": 9645 + }, + { + "epoch": 0.82, + "learning_rate": 1.607883801549719e-06, + "loss": 0.434, + "step": 9646 + }, + { + "epoch": 0.82, + "learning_rate": 1.6063823514189703e-06, + "loss": 0.4595, + "step": 9647 + }, + { + "epoch": 0.82, + "learning_rate": 1.60488154142054e-06, + "loss": 0.4683, + "step": 9648 + }, + { + "epoch": 0.82, + "learning_rate": 1.603381371668895e-06, + "loss": 0.4717, + "step": 9649 + }, + { + "epoch": 0.82, + "learning_rate": 1.6018818422784433e-06, + "loss": 0.4232, + "step": 9650 + }, + { + "epoch": 0.82, + "learning_rate": 1.6003829533635417e-06, + "loss": 0.4502, + "step": 9651 + }, + { + "epoch": 0.82, + "learning_rate": 1.5988847050385037e-06, + "loss": 0.4503, + "step": 9652 + }, + { + "epoch": 0.82, + "learning_rate": 1.5973870974175909e-06, + "loss": 0.4496, + "step": 9653 + }, + { + "epoch": 0.82, + "learning_rate": 1.5958901306150177e-06, + "loss": 0.4682, + "step": 9654 + }, + { + "epoch": 0.82, + "learning_rate": 1.5943938047449493e-06, + "loss": 0.4697, + "step": 9655 + }, + { + "epoch": 0.82, + "learning_rate": 1.5928981199215044e-06, + "loss": 0.4554, + "step": 9656 + }, + { + "epoch": 0.82, + "learning_rate": 1.591403076258743e-06, + "loss": 0.4722, + "step": 9657 + }, + { + "epoch": 0.82, + "learning_rate": 1.5899086738706904e-06, + "loss": 0.4635, + "step": 9658 + }, + { + "epoch": 0.82, + "learning_rate": 1.5884149128713155e-06, + "loss": 0.4414, + "step": 9659 + }, + { + "epoch": 0.82, + "learning_rate": 1.586921793374534e-06, + "loss": 0.4438, + "step": 9660 + }, + { + "epoch": 0.82, + "learning_rate": 1.5854293154942203e-06, + "loss": 0.4594, + "step": 9661 + }, + { + "epoch": 0.82, + "learning_rate": 1.5839374793441964e-06, + "loss": 0.4457, + "step": 9662 + }, + { + "epoch": 0.82, + "learning_rate": 1.582446285038236e-06, + "loss": 0.4524, + "step": 9663 + }, + { + "epoch": 0.82, + "learning_rate": 1.580955732690065e-06, + "loss": 0.465, + "step": 9664 + }, + { + "epoch": 0.82, + "learning_rate": 1.5794658224133607e-06, + "loss": 0.4533, + "step": 9665 + }, + { + "epoch": 0.82, + "learning_rate": 1.577976554321745e-06, + "loss": 0.4443, + "step": 9666 + }, + { + "epoch": 0.82, + "learning_rate": 1.576487928528795e-06, + "loss": 0.4406, + "step": 9667 + }, + { + "epoch": 0.82, + "learning_rate": 1.574999945148048e-06, + "loss": 0.4724, + "step": 9668 + }, + { + "epoch": 0.82, + "learning_rate": 1.573512604292976e-06, + "loss": 0.4383, + "step": 9669 + }, + { + "epoch": 0.82, + "learning_rate": 1.5720259060770128e-06, + "loss": 0.4423, + "step": 9670 + }, + { + "epoch": 0.82, + "learning_rate": 1.5705398506135394e-06, + "loss": 0.4575, + "step": 9671 + }, + { + "epoch": 0.82, + "learning_rate": 1.569054438015889e-06, + "loss": 0.4356, + "step": 9672 + }, + { + "epoch": 0.82, + "learning_rate": 1.5675696683973452e-06, + "loss": 0.4755, + "step": 9673 + }, + { + "epoch": 0.82, + "learning_rate": 1.566085541871145e-06, + "loss": 0.4545, + "step": 9674 + }, + { + "epoch": 0.82, + "learning_rate": 1.5646020585504696e-06, + "loss": 0.4302, + "step": 9675 + }, + { + "epoch": 0.83, + "learning_rate": 1.5631192185484557e-06, + "loss": 0.4658, + "step": 9676 + }, + { + "epoch": 0.83, + "learning_rate": 1.5616370219781985e-06, + "loss": 0.4363, + "step": 9677 + }, + { + "epoch": 0.83, + "learning_rate": 1.5601554689527276e-06, + "loss": 0.4754, + "step": 9678 + }, + { + "epoch": 0.83, + "learning_rate": 1.558674559585036e-06, + "loss": 0.4362, + "step": 9679 + }, + { + "epoch": 0.83, + "learning_rate": 1.5571942939880646e-06, + "loss": 0.4706, + "step": 9680 + }, + { + "epoch": 0.83, + "learning_rate": 1.555714672274704e-06, + "loss": 0.4622, + "step": 9681 + }, + { + "epoch": 0.83, + "learning_rate": 1.5542356945577964e-06, + "loss": 0.4325, + "step": 9682 + }, + { + "epoch": 0.83, + "learning_rate": 1.5527573609501367e-06, + "loss": 0.4527, + "step": 9683 + }, + { + "epoch": 0.83, + "learning_rate": 1.551279671564464e-06, + "loss": 0.471, + "step": 9684 + }, + { + "epoch": 0.83, + "learning_rate": 1.5498026265134747e-06, + "loss": 0.4452, + "step": 9685 + }, + { + "epoch": 0.83, + "learning_rate": 1.5483262259098197e-06, + "loss": 0.4601, + "step": 9686 + }, + { + "epoch": 0.83, + "learning_rate": 1.546850469866089e-06, + "loss": 0.4403, + "step": 9687 + }, + { + "epoch": 0.83, + "learning_rate": 1.5453753584948329e-06, + "loss": 0.4305, + "step": 9688 + }, + { + "epoch": 0.83, + "learning_rate": 1.5439008919085507e-06, + "loss": 0.4624, + "step": 9689 + }, + { + "epoch": 0.83, + "learning_rate": 1.5424270702196841e-06, + "loss": 0.4576, + "step": 9690 + }, + { + "epoch": 0.83, + "learning_rate": 1.5409538935406422e-06, + "loss": 0.4678, + "step": 9691 + }, + { + "epoch": 0.83, + "learning_rate": 1.5394813619837734e-06, + "loss": 0.4725, + "step": 9692 + }, + { + "epoch": 0.83, + "learning_rate": 1.5380094756613761e-06, + "loss": 0.4353, + "step": 9693 + }, + { + "epoch": 0.83, + "learning_rate": 1.5365382346857005e-06, + "loss": 0.4687, + "step": 9694 + }, + { + "epoch": 0.83, + "learning_rate": 1.5350676391689578e-06, + "loss": 0.4656, + "step": 9695 + }, + { + "epoch": 0.83, + "learning_rate": 1.533597689223295e-06, + "loss": 0.4593, + "step": 9696 + }, + { + "epoch": 0.83, + "learning_rate": 1.5321283849608193e-06, + "loss": 0.4553, + "step": 9697 + }, + { + "epoch": 0.83, + "learning_rate": 1.5306597264935863e-06, + "loss": 0.4521, + "step": 9698 + }, + { + "epoch": 0.83, + "learning_rate": 1.5291917139335976e-06, + "loss": 0.4567, + "step": 9699 + }, + { + "epoch": 0.83, + "learning_rate": 1.527724347392815e-06, + "loss": 0.4507, + "step": 9700 + }, + { + "epoch": 0.83, + "learning_rate": 1.5262576269831464e-06, + "loss": 0.456, + "step": 9701 + }, + { + "epoch": 0.83, + "learning_rate": 1.5247915528164458e-06, + "loss": 0.4387, + "step": 9702 + }, + { + "epoch": 0.83, + "learning_rate": 1.5233261250045218e-06, + "loss": 0.4665, + "step": 9703 + }, + { + "epoch": 0.83, + "learning_rate": 1.5218613436591422e-06, + "loss": 0.462, + "step": 9704 + }, + { + "epoch": 0.83, + "learning_rate": 1.5203972088920082e-06, + "loss": 0.4564, + "step": 9705 + }, + { + "epoch": 0.83, + "learning_rate": 1.5189337208147848e-06, + "loss": 0.45, + "step": 9706 + }, + { + "epoch": 0.83, + "learning_rate": 1.5174708795390859e-06, + "loss": 0.4655, + "step": 9707 + }, + { + "epoch": 0.83, + "learning_rate": 1.5160086851764666e-06, + "loss": 0.4597, + "step": 9708 + }, + { + "epoch": 0.83, + "learning_rate": 1.5145471378384458e-06, + "loss": 0.4595, + "step": 9709 + }, + { + "epoch": 0.83, + "learning_rate": 1.5130862376364897e-06, + "loss": 0.4612, + "step": 9710 + }, + { + "epoch": 0.83, + "learning_rate": 1.5116259846820058e-06, + "loss": 0.4397, + "step": 9711 + }, + { + "epoch": 0.83, + "learning_rate": 1.5101663790863597e-06, + "loss": 0.4726, + "step": 9712 + }, + { + "epoch": 0.83, + "learning_rate": 1.5087074209608743e-06, + "loss": 0.4474, + "step": 9713 + }, + { + "epoch": 0.83, + "learning_rate": 1.5072491104168097e-06, + "loss": 0.4566, + "step": 9714 + }, + { + "epoch": 0.83, + "learning_rate": 1.5057914475653835e-06, + "loss": 0.4525, + "step": 9715 + }, + { + "epoch": 0.83, + "learning_rate": 1.5043344325177634e-06, + "loss": 0.4625, + "step": 9716 + }, + { + "epoch": 0.83, + "learning_rate": 1.502878065385067e-06, + "loss": 0.4653, + "step": 9717 + }, + { + "epoch": 0.83, + "learning_rate": 1.501422346278365e-06, + "loss": 0.4508, + "step": 9718 + }, + { + "epoch": 0.83, + "learning_rate": 1.499967275308678e-06, + "loss": 0.4811, + "step": 9719 + }, + { + "epoch": 0.83, + "learning_rate": 1.4985128525869697e-06, + "loss": 0.4527, + "step": 9720 + }, + { + "epoch": 0.83, + "learning_rate": 1.4970590782241645e-06, + "loss": 0.4539, + "step": 9721 + }, + { + "epoch": 0.83, + "learning_rate": 1.4956059523311328e-06, + "loss": 0.4766, + "step": 9722 + }, + { + "epoch": 0.83, + "learning_rate": 1.4941534750186958e-06, + "loss": 0.4401, + "step": 9723 + }, + { + "epoch": 0.83, + "learning_rate": 1.4927016463976262e-06, + "loss": 0.4386, + "step": 9724 + }, + { + "epoch": 0.83, + "learning_rate": 1.4912504665786454e-06, + "loss": 0.4572, + "step": 9725 + }, + { + "epoch": 0.83, + "learning_rate": 1.4897999356724268e-06, + "loss": 0.4579, + "step": 9726 + }, + { + "epoch": 0.83, + "learning_rate": 1.4883500537895946e-06, + "loss": 0.4428, + "step": 9727 + }, + { + "epoch": 0.83, + "learning_rate": 1.4869008210407243e-06, + "loss": 0.4686, + "step": 9728 + }, + { + "epoch": 0.83, + "learning_rate": 1.4854522375363367e-06, + "loss": 0.4554, + "step": 9729 + }, + { + "epoch": 0.83, + "learning_rate": 1.4840043033869079e-06, + "loss": 0.4484, + "step": 9730 + }, + { + "epoch": 0.83, + "learning_rate": 1.482557018702865e-06, + "loss": 0.4545, + "step": 9731 + }, + { + "epoch": 0.83, + "learning_rate": 1.4811103835945817e-06, + "loss": 0.4457, + "step": 9732 + }, + { + "epoch": 0.83, + "learning_rate": 1.479664398172387e-06, + "loss": 0.4756, + "step": 9733 + }, + { + "epoch": 0.83, + "learning_rate": 1.4782190625465565e-06, + "loss": 0.4317, + "step": 9734 + }, + { + "epoch": 0.83, + "learning_rate": 1.476774376827318e-06, + "loss": 0.4631, + "step": 9735 + }, + { + "epoch": 0.83, + "learning_rate": 1.4753303411248477e-06, + "loss": 0.4627, + "step": 9736 + }, + { + "epoch": 0.83, + "learning_rate": 1.4738869555492786e-06, + "loss": 0.4683, + "step": 9737 + }, + { + "epoch": 0.83, + "learning_rate": 1.4724442202106825e-06, + "loss": 0.4562, + "step": 9738 + }, + { + "epoch": 0.83, + "learning_rate": 1.4710021352190918e-06, + "loss": 0.4531, + "step": 9739 + }, + { + "epoch": 0.83, + "learning_rate": 1.4695607006844859e-06, + "loss": 0.4587, + "step": 9740 + }, + { + "epoch": 0.83, + "learning_rate": 1.4681199167167949e-06, + "loss": 0.4521, + "step": 9741 + }, + { + "epoch": 0.83, + "learning_rate": 1.4666797834258984e-06, + "loss": 0.4537, + "step": 9742 + }, + { + "epoch": 0.83, + "learning_rate": 1.4652403009216265e-06, + "loss": 0.4508, + "step": 9743 + }, + { + "epoch": 0.83, + "learning_rate": 1.4638014693137637e-06, + "loss": 0.4578, + "step": 9744 + }, + { + "epoch": 0.83, + "learning_rate": 1.4623632887120343e-06, + "loss": 0.4563, + "step": 9745 + }, + { + "epoch": 0.83, + "learning_rate": 1.4609257592261273e-06, + "loss": 0.4485, + "step": 9746 + }, + { + "epoch": 0.83, + "learning_rate": 1.4594888809656704e-06, + "loss": 0.4651, + "step": 9747 + }, + { + "epoch": 0.83, + "learning_rate": 1.4580526540402462e-06, + "loss": 0.4671, + "step": 9748 + }, + { + "epoch": 0.83, + "learning_rate": 1.456617078559389e-06, + "loss": 0.4713, + "step": 9749 + }, + { + "epoch": 0.83, + "learning_rate": 1.4551821546325806e-06, + "loss": 0.4405, + "step": 9750 + }, + { + "epoch": 0.83, + "learning_rate": 1.453747882369254e-06, + "loss": 0.4694, + "step": 9751 + }, + { + "epoch": 0.83, + "learning_rate": 1.4523142618787944e-06, + "loss": 0.4404, + "step": 9752 + }, + { + "epoch": 0.83, + "learning_rate": 1.4508812932705364e-06, + "loss": 0.4447, + "step": 9753 + }, + { + "epoch": 0.83, + "learning_rate": 1.4494489766537579e-06, + "loss": 0.4639, + "step": 9754 + }, + { + "epoch": 0.83, + "learning_rate": 1.4480173121377028e-06, + "loss": 0.4516, + "step": 9755 + }, + { + "epoch": 0.83, + "learning_rate": 1.4465862998315483e-06, + "loss": 0.4698, + "step": 9756 + }, + { + "epoch": 0.83, + "learning_rate": 1.4451559398444314e-06, + "loss": 0.4463, + "step": 9757 + }, + { + "epoch": 0.83, + "learning_rate": 1.4437262322854394e-06, + "loss": 0.4647, + "step": 9758 + }, + { + "epoch": 0.83, + "learning_rate": 1.442297177263605e-06, + "loss": 0.4467, + "step": 9759 + }, + { + "epoch": 0.83, + "learning_rate": 1.4408687748879157e-06, + "loss": 0.4589, + "step": 9760 + }, + { + "epoch": 0.83, + "learning_rate": 1.4394410252673075e-06, + "loss": 0.4596, + "step": 9761 + }, + { + "epoch": 0.83, + "learning_rate": 1.4380139285106676e-06, + "loss": 0.4483, + "step": 9762 + }, + { + "epoch": 0.83, + "learning_rate": 1.4365874847268257e-06, + "loss": 0.462, + "step": 9763 + }, + { + "epoch": 0.83, + "learning_rate": 1.4351616940245794e-06, + "loss": 0.4606, + "step": 9764 + }, + { + "epoch": 0.83, + "learning_rate": 1.433736556512656e-06, + "loss": 0.4535, + "step": 9765 + }, + { + "epoch": 0.83, + "learning_rate": 1.4323120722997463e-06, + "loss": 0.4621, + "step": 9766 + }, + { + "epoch": 0.83, + "learning_rate": 1.430888241494487e-06, + "loss": 0.4561, + "step": 9767 + }, + { + "epoch": 0.83, + "learning_rate": 1.4294650642054654e-06, + "loss": 0.4334, + "step": 9768 + }, + { + "epoch": 0.83, + "learning_rate": 1.428042540541218e-06, + "loss": 0.4649, + "step": 9769 + }, + { + "epoch": 0.83, + "learning_rate": 1.4266206706102337e-06, + "loss": 0.4577, + "step": 9770 + }, + { + "epoch": 0.83, + "learning_rate": 1.4251994545209524e-06, + "loss": 0.4642, + "step": 9771 + }, + { + "epoch": 0.83, + "learning_rate": 1.4237788923817553e-06, + "loss": 0.4707, + "step": 9772 + }, + { + "epoch": 0.83, + "learning_rate": 1.4223589843009866e-06, + "loss": 0.4413, + "step": 9773 + }, + { + "epoch": 0.83, + "learning_rate": 1.4209397303869343e-06, + "loss": 0.4575, + "step": 9774 + }, + { + "epoch": 0.83, + "learning_rate": 1.419521130747833e-06, + "loss": 0.4626, + "step": 9775 + }, + { + "epoch": 0.83, + "learning_rate": 1.4181031854918714e-06, + "loss": 0.4589, + "step": 9776 + }, + { + "epoch": 0.83, + "learning_rate": 1.41668589472719e-06, + "loss": 0.4456, + "step": 9777 + }, + { + "epoch": 0.83, + "learning_rate": 1.4152692585618767e-06, + "loss": 0.4548, + "step": 9778 + }, + { + "epoch": 0.83, + "learning_rate": 1.4138532771039703e-06, + "loss": 0.4304, + "step": 9779 + }, + { + "epoch": 0.83, + "learning_rate": 1.4124379504614604e-06, + "loss": 0.4421, + "step": 9780 + }, + { + "epoch": 0.83, + "learning_rate": 1.4110232787422807e-06, + "loss": 0.454, + "step": 9781 + }, + { + "epoch": 0.83, + "learning_rate": 1.4096092620543257e-06, + "loss": 0.46, + "step": 9782 + }, + { + "epoch": 0.83, + "learning_rate": 1.4081959005054335e-06, + "loss": 0.449, + "step": 9783 + }, + { + "epoch": 0.83, + "learning_rate": 1.4067831942033904e-06, + "loss": 0.4658, + "step": 9784 + }, + { + "epoch": 0.83, + "learning_rate": 1.4053711432559358e-06, + "loss": 0.4554, + "step": 9785 + }, + { + "epoch": 0.83, + "learning_rate": 1.40395974777076e-06, + "loss": 0.4737, + "step": 9786 + }, + { + "epoch": 0.83, + "learning_rate": 1.4025490078555015e-06, + "loss": 0.4556, + "step": 9787 + }, + { + "epoch": 0.83, + "learning_rate": 1.4011389236177476e-06, + "loss": 0.4773, + "step": 9788 + }, + { + "epoch": 0.83, + "learning_rate": 1.399729495165042e-06, + "loss": 0.4548, + "step": 9789 + }, + { + "epoch": 0.83, + "learning_rate": 1.3983207226048656e-06, + "loss": 0.4765, + "step": 9790 + }, + { + "epoch": 0.83, + "learning_rate": 1.3969126060446635e-06, + "loss": 0.4478, + "step": 9791 + }, + { + "epoch": 0.83, + "learning_rate": 1.3955051455918257e-06, + "loss": 0.444, + "step": 9792 + }, + { + "epoch": 0.84, + "learning_rate": 1.3940983413536847e-06, + "loss": 0.4817, + "step": 9793 + }, + { + "epoch": 0.84, + "learning_rate": 1.3926921934375338e-06, + "loss": 0.4511, + "step": 9794 + }, + { + "epoch": 0.84, + "learning_rate": 1.3912867019506105e-06, + "loss": 0.4459, + "step": 9795 + }, + { + "epoch": 0.84, + "learning_rate": 1.3898818670001035e-06, + "loss": 0.4512, + "step": 9796 + }, + { + "epoch": 0.84, + "learning_rate": 1.3884776886931517e-06, + "loss": 0.4541, + "step": 9797 + }, + { + "epoch": 0.84, + "learning_rate": 1.387074167136846e-06, + "loss": 0.455, + "step": 9798 + }, + { + "epoch": 0.84, + "learning_rate": 1.3856713024382195e-06, + "loss": 0.4504, + "step": 9799 + }, + { + "epoch": 0.84, + "learning_rate": 1.3842690947042604e-06, + "loss": 0.4715, + "step": 9800 + }, + { + "epoch": 0.84, + "learning_rate": 1.3828675440419147e-06, + "loss": 0.4287, + "step": 9801 + }, + { + "epoch": 0.84, + "learning_rate": 1.3814666505580632e-06, + "loss": 0.4433, + "step": 9802 + }, + { + "epoch": 0.84, + "learning_rate": 1.3800664143595465e-06, + "loss": 0.4546, + "step": 9803 + }, + { + "epoch": 0.84, + "learning_rate": 1.3786668355531518e-06, + "loss": 0.4411, + "step": 9804 + }, + { + "epoch": 0.84, + "learning_rate": 1.377267914245618e-06, + "loss": 0.4309, + "step": 9805 + }, + { + "epoch": 0.84, + "learning_rate": 1.3758696505436309e-06, + "loss": 0.4418, + "step": 9806 + }, + { + "epoch": 0.84, + "learning_rate": 1.3744720445538318e-06, + "loss": 0.4776, + "step": 9807 + }, + { + "epoch": 0.84, + "learning_rate": 1.3730750963828033e-06, + "loss": 0.4453, + "step": 9808 + }, + { + "epoch": 0.84, + "learning_rate": 1.3716788061370812e-06, + "loss": 0.4634, + "step": 9809 + }, + { + "epoch": 0.84, + "learning_rate": 1.3702831739231593e-06, + "loss": 0.464, + "step": 9810 + }, + { + "epoch": 0.84, + "learning_rate": 1.36888819984747e-06, + "loss": 0.4555, + "step": 9811 + }, + { + "epoch": 0.84, + "learning_rate": 1.3674938840163986e-06, + "loss": 0.4573, + "step": 9812 + }, + { + "epoch": 0.84, + "learning_rate": 1.3661002265362844e-06, + "loss": 0.4604, + "step": 9813 + }, + { + "epoch": 0.84, + "learning_rate": 1.3647072275134122e-06, + "loss": 0.467, + "step": 9814 + }, + { + "epoch": 0.84, + "learning_rate": 1.363314887054018e-06, + "loss": 0.4472, + "step": 9815 + }, + { + "epoch": 0.84, + "learning_rate": 1.3619232052642906e-06, + "loss": 0.4559, + "step": 9816 + }, + { + "epoch": 0.84, + "learning_rate": 1.3605321822503592e-06, + "loss": 0.4658, + "step": 9817 + }, + { + "epoch": 0.84, + "learning_rate": 1.3591418181183103e-06, + "loss": 0.4318, + "step": 9818 + }, + { + "epoch": 0.84, + "learning_rate": 1.3577521129741856e-06, + "loss": 0.4605, + "step": 9819 + }, + { + "epoch": 0.84, + "learning_rate": 1.3563630669239625e-06, + "loss": 0.4532, + "step": 9820 + }, + { + "epoch": 0.84, + "learning_rate": 1.3549746800735775e-06, + "loss": 0.4402, + "step": 9821 + }, + { + "epoch": 0.84, + "learning_rate": 1.353586952528918e-06, + "loss": 0.4527, + "step": 9822 + }, + { + "epoch": 0.84, + "learning_rate": 1.3521998843958117e-06, + "loss": 0.4683, + "step": 9823 + }, + { + "epoch": 0.84, + "learning_rate": 1.350813475780046e-06, + "loss": 0.4483, + "step": 9824 + }, + { + "epoch": 0.84, + "learning_rate": 1.349427726787358e-06, + "loss": 0.446, + "step": 9825 + }, + { + "epoch": 0.84, + "learning_rate": 1.3480426375234234e-06, + "loss": 0.4566, + "step": 9826 + }, + { + "epoch": 0.84, + "learning_rate": 1.3466582080938762e-06, + "loss": 0.4583, + "step": 9827 + }, + { + "epoch": 0.84, + "learning_rate": 1.345274438604305e-06, + "loss": 0.4518, + "step": 9828 + }, + { + "epoch": 0.84, + "learning_rate": 1.343891329160235e-06, + "loss": 0.4517, + "step": 9829 + }, + { + "epoch": 0.84, + "learning_rate": 1.3425088798671504e-06, + "loss": 0.4533, + "step": 9830 + }, + { + "epoch": 0.84, + "learning_rate": 1.3411270908304853e-06, + "loss": 0.4613, + "step": 9831 + }, + { + "epoch": 0.84, + "learning_rate": 1.339745962155613e-06, + "loss": 0.4678, + "step": 9832 + }, + { + "epoch": 0.84, + "learning_rate": 1.3383654939478718e-06, + "loss": 0.4508, + "step": 9833 + }, + { + "epoch": 0.84, + "learning_rate": 1.3369856863125418e-06, + "loss": 0.4559, + "step": 9834 + }, + { + "epoch": 0.84, + "learning_rate": 1.3356065393548467e-06, + "loss": 0.451, + "step": 9835 + }, + { + "epoch": 0.84, + "learning_rate": 1.334228053179969e-06, + "loss": 0.4573, + "step": 9836 + }, + { + "epoch": 0.84, + "learning_rate": 1.3328502278930422e-06, + "loss": 0.4644, + "step": 9837 + }, + { + "epoch": 0.84, + "learning_rate": 1.3314730635991391e-06, + "loss": 0.4305, + "step": 9838 + }, + { + "epoch": 0.84, + "learning_rate": 1.33009656040329e-06, + "loss": 0.4859, + "step": 9839 + }, + { + "epoch": 0.84, + "learning_rate": 1.3287207184104756e-06, + "loss": 0.4379, + "step": 9840 + }, + { + "epoch": 0.84, + "learning_rate": 1.3273455377256162e-06, + "loss": 0.4641, + "step": 9841 + }, + { + "epoch": 0.84, + "learning_rate": 1.3259710184535957e-06, + "loss": 0.4508, + "step": 9842 + }, + { + "epoch": 0.84, + "learning_rate": 1.3245971606992404e-06, + "loss": 0.4511, + "step": 9843 + }, + { + "epoch": 0.84, + "learning_rate": 1.3232239645673217e-06, + "loss": 0.444, + "step": 9844 + }, + { + "epoch": 0.84, + "learning_rate": 1.3218514301625662e-06, + "loss": 0.4654, + "step": 9845 + }, + { + "epoch": 0.84, + "learning_rate": 1.3204795575896545e-06, + "loss": 0.4728, + "step": 9846 + }, + { + "epoch": 0.84, + "learning_rate": 1.3191083469532062e-06, + "loss": 0.456, + "step": 9847 + }, + { + "epoch": 0.84, + "learning_rate": 1.3177377983577967e-06, + "loss": 0.4435, + "step": 9848 + }, + { + "epoch": 0.84, + "learning_rate": 1.316367911907952e-06, + "loss": 0.449, + "step": 9849 + }, + { + "epoch": 0.84, + "learning_rate": 1.31499868770814e-06, + "loss": 0.4654, + "step": 9850 + }, + { + "epoch": 0.84, + "learning_rate": 1.313630125862788e-06, + "loss": 0.4753, + "step": 9851 + }, + { + "epoch": 0.84, + "learning_rate": 1.3122622264762696e-06, + "loss": 0.4437, + "step": 9852 + }, + { + "epoch": 0.84, + "learning_rate": 1.3108949896529023e-06, + "loss": 0.4409, + "step": 9853 + }, + { + "epoch": 0.84, + "learning_rate": 1.3095284154969578e-06, + "loss": 0.4483, + "step": 9854 + }, + { + "epoch": 0.84, + "learning_rate": 1.308162504112659e-06, + "loss": 0.4571, + "step": 9855 + }, + { + "epoch": 0.84, + "learning_rate": 1.3067972556041753e-06, + "loss": 0.4534, + "step": 9856 + }, + { + "epoch": 0.84, + "learning_rate": 1.3054326700756248e-06, + "loss": 0.4332, + "step": 9857 + }, + { + "epoch": 0.84, + "learning_rate": 1.304068747631081e-06, + "loss": 0.4686, + "step": 9858 + }, + { + "epoch": 0.84, + "learning_rate": 1.3027054883745538e-06, + "loss": 0.4653, + "step": 9859 + }, + { + "epoch": 0.84, + "learning_rate": 1.301342892410018e-06, + "loss": 0.4306, + "step": 9860 + }, + { + "epoch": 0.84, + "learning_rate": 1.2999809598413927e-06, + "loss": 0.4545, + "step": 9861 + }, + { + "epoch": 0.84, + "learning_rate": 1.2986196907725368e-06, + "loss": 0.4501, + "step": 9862 + }, + { + "epoch": 0.84, + "learning_rate": 1.297259085307272e-06, + "loss": 0.454, + "step": 9863 + }, + { + "epoch": 0.84, + "learning_rate": 1.2958991435493618e-06, + "loss": 0.4417, + "step": 9864 + }, + { + "epoch": 0.84, + "learning_rate": 1.294539865602521e-06, + "loss": 0.4627, + "step": 9865 + }, + { + "epoch": 0.84, + "learning_rate": 1.2931812515704145e-06, + "loss": 0.4847, + "step": 9866 + }, + { + "epoch": 0.84, + "learning_rate": 1.2918233015566573e-06, + "loss": 0.4454, + "step": 9867 + }, + { + "epoch": 0.84, + "learning_rate": 1.2904660156648074e-06, + "loss": 0.4592, + "step": 9868 + }, + { + "epoch": 0.84, + "learning_rate": 1.2891093939983812e-06, + "loss": 0.4679, + "step": 9869 + }, + { + "epoch": 0.84, + "learning_rate": 1.2877534366608424e-06, + "loss": 0.4361, + "step": 9870 + }, + { + "epoch": 0.84, + "learning_rate": 1.2863981437555972e-06, + "loss": 0.4711, + "step": 9871 + }, + { + "epoch": 0.84, + "learning_rate": 1.2850435153860075e-06, + "loss": 0.4463, + "step": 9872 + }, + { + "epoch": 0.84, + "learning_rate": 1.2836895516553826e-06, + "loss": 0.4622, + "step": 9873 + }, + { + "epoch": 0.84, + "learning_rate": 1.2823362526669825e-06, + "loss": 0.4475, + "step": 9874 + }, + { + "epoch": 0.84, + "learning_rate": 1.2809836185240154e-06, + "loss": 0.4717, + "step": 9875 + }, + { + "epoch": 0.84, + "learning_rate": 1.2796316493296402e-06, + "loss": 0.464, + "step": 9876 + }, + { + "epoch": 0.84, + "learning_rate": 1.2782803451869597e-06, + "loss": 0.4456, + "step": 9877 + }, + { + "epoch": 0.84, + "learning_rate": 1.2769297061990294e-06, + "loss": 0.4655, + "step": 9878 + }, + { + "epoch": 0.84, + "learning_rate": 1.2755797324688622e-06, + "loss": 0.4649, + "step": 9879 + }, + { + "epoch": 0.84, + "learning_rate": 1.2742304240994053e-06, + "loss": 0.458, + "step": 9880 + }, + { + "epoch": 0.84, + "learning_rate": 1.2728817811935657e-06, + "loss": 0.4767, + "step": 9881 + }, + { + "epoch": 0.84, + "learning_rate": 1.2715338038541969e-06, + "loss": 0.4871, + "step": 9882 + }, + { + "epoch": 0.84, + "learning_rate": 1.2701864921840989e-06, + "loss": 0.4445, + "step": 9883 + }, + { + "epoch": 0.84, + "learning_rate": 1.2688398462860262e-06, + "loss": 0.4678, + "step": 9884 + }, + { + "epoch": 0.84, + "learning_rate": 1.26749386626268e-06, + "loss": 0.4655, + "step": 9885 + }, + { + "epoch": 0.84, + "learning_rate": 1.2661485522167062e-06, + "loss": 0.4521, + "step": 9886 + }, + { + "epoch": 0.84, + "learning_rate": 1.2648039042507043e-06, + "loss": 0.4751, + "step": 9887 + }, + { + "epoch": 0.84, + "learning_rate": 1.2634599224672295e-06, + "loss": 0.4386, + "step": 9888 + }, + { + "epoch": 0.84, + "learning_rate": 1.262116606968773e-06, + "loss": 0.4527, + "step": 9889 + }, + { + "epoch": 0.84, + "learning_rate": 1.2607739578577838e-06, + "loss": 0.4406, + "step": 9890 + }, + { + "epoch": 0.84, + "learning_rate": 1.2594319752366578e-06, + "loss": 0.4579, + "step": 9891 + }, + { + "epoch": 0.84, + "learning_rate": 1.2580906592077403e-06, + "loss": 0.4778, + "step": 9892 + }, + { + "epoch": 0.84, + "learning_rate": 1.2567500098733242e-06, + "loss": 0.4538, + "step": 9893 + }, + { + "epoch": 0.84, + "learning_rate": 1.2554100273356552e-06, + "loss": 0.4551, + "step": 9894 + }, + { + "epoch": 0.84, + "learning_rate": 1.2540707116969274e-06, + "loss": 0.4576, + "step": 9895 + }, + { + "epoch": 0.84, + "learning_rate": 1.2527320630592765e-06, + "loss": 0.4668, + "step": 9896 + }, + { + "epoch": 0.84, + "learning_rate": 1.2513940815248005e-06, + "loss": 0.457, + "step": 9897 + }, + { + "epoch": 0.84, + "learning_rate": 1.2500567671955345e-06, + "loss": 0.4352, + "step": 9898 + }, + { + "epoch": 0.84, + "learning_rate": 1.2487201201734689e-06, + "loss": 0.4651, + "step": 9899 + }, + { + "epoch": 0.84, + "learning_rate": 1.2473841405605424e-06, + "loss": 0.4441, + "step": 9900 + }, + { + "epoch": 0.84, + "learning_rate": 1.2460488284586437e-06, + "loss": 0.4704, + "step": 9901 + }, + { + "epoch": 0.84, + "learning_rate": 1.2447141839696065e-06, + "loss": 0.461, + "step": 9902 + }, + { + "epoch": 0.84, + "learning_rate": 1.2433802071952183e-06, + "loss": 0.4555, + "step": 9903 + }, + { + "epoch": 0.84, + "learning_rate": 1.2420468982372158e-06, + "loss": 0.4506, + "step": 9904 + }, + { + "epoch": 0.84, + "learning_rate": 1.2407142571972752e-06, + "loss": 0.4502, + "step": 9905 + }, + { + "epoch": 0.84, + "learning_rate": 1.2393822841770397e-06, + "loss": 0.4612, + "step": 9906 + }, + { + "epoch": 0.84, + "learning_rate": 1.2380509792780826e-06, + "loss": 0.4703, + "step": 9907 + }, + { + "epoch": 0.84, + "learning_rate": 1.236720342601938e-06, + "loss": 0.461, + "step": 9908 + }, + { + "epoch": 0.84, + "learning_rate": 1.2353903742500861e-06, + "loss": 0.4482, + "step": 9909 + }, + { + "epoch": 0.84, + "learning_rate": 1.2340610743239545e-06, + "loss": 0.4521, + "step": 9910 + }, + { + "epoch": 0.85, + "learning_rate": 1.2327324429249232e-06, + "loss": 0.4463, + "step": 9911 + }, + { + "epoch": 0.85, + "learning_rate": 1.2314044801543168e-06, + "loss": 0.454, + "step": 9912 + }, + { + "epoch": 0.85, + "learning_rate": 1.2300771861134153e-06, + "loss": 0.4607, + "step": 9913 + }, + { + "epoch": 0.85, + "learning_rate": 1.2287505609034367e-06, + "loss": 0.4397, + "step": 9914 + }, + { + "epoch": 0.85, + "learning_rate": 1.2274246046255633e-06, + "loss": 0.4569, + "step": 9915 + }, + { + "epoch": 0.85, + "learning_rate": 1.2260993173809122e-06, + "loss": 0.4646, + "step": 9916 + }, + { + "epoch": 0.85, + "learning_rate": 1.2247746992705566e-06, + "loss": 0.4804, + "step": 9917 + }, + { + "epoch": 0.85, + "learning_rate": 1.2234507503955185e-06, + "loss": 0.4593, + "step": 9918 + }, + { + "epoch": 0.85, + "learning_rate": 1.2221274708567664e-06, + "loss": 0.4363, + "step": 9919 + }, + { + "epoch": 0.85, + "learning_rate": 1.2208048607552214e-06, + "loss": 0.4444, + "step": 9920 + }, + { + "epoch": 0.85, + "learning_rate": 1.219482920191748e-06, + "loss": 0.4587, + "step": 9921 + }, + { + "epoch": 0.85, + "learning_rate": 1.2181616492671677e-06, + "loss": 0.4397, + "step": 9922 + }, + { + "epoch": 0.85, + "learning_rate": 1.216841048082239e-06, + "loss": 0.4531, + "step": 9923 + }, + { + "epoch": 0.85, + "learning_rate": 1.2155211167376835e-06, + "loss": 0.4686, + "step": 9924 + }, + { + "epoch": 0.85, + "learning_rate": 1.2142018553341607e-06, + "loss": 0.442, + "step": 9925 + }, + { + "epoch": 0.85, + "learning_rate": 1.2128832639722844e-06, + "loss": 0.4613, + "step": 9926 + }, + { + "epoch": 0.85, + "learning_rate": 1.2115653427526142e-06, + "loss": 0.4493, + "step": 9927 + }, + { + "epoch": 0.85, + "learning_rate": 1.2102480917756632e-06, + "loss": 0.4808, + "step": 9928 + }, + { + "epoch": 0.85, + "learning_rate": 1.2089315111418876e-06, + "loss": 0.4564, + "step": 9929 + }, + { + "epoch": 0.85, + "learning_rate": 1.2076156009516971e-06, + "loss": 0.4545, + "step": 9930 + }, + { + "epoch": 0.85, + "learning_rate": 1.2063003613054491e-06, + "loss": 0.4444, + "step": 9931 + }, + { + "epoch": 0.85, + "learning_rate": 1.2049857923034468e-06, + "loss": 0.4418, + "step": 9932 + }, + { + "epoch": 0.85, + "learning_rate": 1.2036718940459468e-06, + "loss": 0.4663, + "step": 9933 + }, + { + "epoch": 0.85, + "learning_rate": 1.202358666633151e-06, + "loss": 0.4584, + "step": 9934 + }, + { + "epoch": 0.85, + "learning_rate": 1.2010461101652127e-06, + "loss": 0.4271, + "step": 9935 + }, + { + "epoch": 0.85, + "learning_rate": 1.1997342247422317e-06, + "loss": 0.4541, + "step": 9936 + }, + { + "epoch": 0.85, + "learning_rate": 1.198423010464259e-06, + "loss": 0.4567, + "step": 9937 + }, + { + "epoch": 0.85, + "learning_rate": 1.1971124674312939e-06, + "loss": 0.4396, + "step": 9938 + }, + { + "epoch": 0.85, + "learning_rate": 1.1958025957432816e-06, + "loss": 0.4678, + "step": 9939 + }, + { + "epoch": 0.85, + "learning_rate": 1.1944933955001226e-06, + "loss": 0.4447, + "step": 9940 + }, + { + "epoch": 0.85, + "learning_rate": 1.1931848668016576e-06, + "loss": 0.4352, + "step": 9941 + }, + { + "epoch": 0.85, + "learning_rate": 1.1918770097476818e-06, + "loss": 0.4645, + "step": 9942 + }, + { + "epoch": 0.85, + "learning_rate": 1.190569824437937e-06, + "loss": 0.4762, + "step": 9943 + }, + { + "epoch": 0.85, + "learning_rate": 1.1892633109721163e-06, + "loss": 0.4612, + "step": 9944 + }, + { + "epoch": 0.85, + "learning_rate": 1.1879574694498597e-06, + "loss": 0.4469, + "step": 9945 + }, + { + "epoch": 0.85, + "learning_rate": 1.1866522999707553e-06, + "loss": 0.4616, + "step": 9946 + }, + { + "epoch": 0.85, + "learning_rate": 1.18534780263434e-06, + "loss": 0.4556, + "step": 9947 + }, + { + "epoch": 0.85, + "learning_rate": 1.1840439775401025e-06, + "loss": 0.4508, + "step": 9948 + }, + { + "epoch": 0.85, + "learning_rate": 1.1827408247874795e-06, + "loss": 0.4642, + "step": 9949 + }, + { + "epoch": 0.85, + "learning_rate": 1.1814383444758493e-06, + "loss": 0.4319, + "step": 9950 + }, + { + "epoch": 0.85, + "learning_rate": 1.1801365367045448e-06, + "loss": 0.4683, + "step": 9951 + }, + { + "epoch": 0.85, + "learning_rate": 1.1788354015728543e-06, + "loss": 0.4406, + "step": 9952 + }, + { + "epoch": 0.85, + "learning_rate": 1.1775349391800017e-06, + "loss": 0.4673, + "step": 9953 + }, + { + "epoch": 0.85, + "learning_rate": 1.1762351496251666e-06, + "loss": 0.4466, + "step": 9954 + }, + { + "epoch": 0.85, + "learning_rate": 1.1749360330074799e-06, + "loss": 0.4727, + "step": 9955 + }, + { + "epoch": 0.85, + "learning_rate": 1.173637589426011e-06, + "loss": 0.4624, + "step": 9956 + }, + { + "epoch": 0.85, + "learning_rate": 1.1723398189797897e-06, + "loss": 0.4744, + "step": 9957 + }, + { + "epoch": 0.85, + "learning_rate": 1.171042721767791e-06, + "loss": 0.4442, + "step": 9958 + }, + { + "epoch": 0.85, + "learning_rate": 1.1697462978889307e-06, + "loss": 0.4704, + "step": 9959 + }, + { + "epoch": 0.85, + "learning_rate": 1.1684505474420826e-06, + "loss": 0.4662, + "step": 9960 + }, + { + "epoch": 0.85, + "learning_rate": 1.167155470526069e-06, + "loss": 0.4331, + "step": 9961 + }, + { + "epoch": 0.85, + "learning_rate": 1.1658610672396543e-06, + "loss": 0.4693, + "step": 9962 + }, + { + "epoch": 0.85, + "learning_rate": 1.1645673376815558e-06, + "loss": 0.4713, + "step": 9963 + }, + { + "epoch": 0.85, + "learning_rate": 1.1632742819504406e-06, + "loss": 0.4438, + "step": 9964 + }, + { + "epoch": 0.85, + "learning_rate": 1.1619819001449162e-06, + "loss": 0.4595, + "step": 9965 + }, + { + "epoch": 0.85, + "learning_rate": 1.1606901923635526e-06, + "loss": 0.4424, + "step": 9966 + }, + { + "epoch": 0.85, + "learning_rate": 1.1593991587048604e-06, + "loss": 0.4604, + "step": 9967 + }, + { + "epoch": 0.85, + "learning_rate": 1.1581087992672936e-06, + "loss": 0.4678, + "step": 9968 + }, + { + "epoch": 0.85, + "learning_rate": 1.1568191141492624e-06, + "loss": 0.4613, + "step": 9969 + }, + { + "epoch": 0.85, + "learning_rate": 1.1555301034491284e-06, + "loss": 0.4602, + "step": 9970 + }, + { + "epoch": 0.85, + "learning_rate": 1.1542417672651917e-06, + "loss": 0.4431, + "step": 9971 + }, + { + "epoch": 0.85, + "learning_rate": 1.1529541056957072e-06, + "loss": 0.4528, + "step": 9972 + }, + { + "epoch": 0.85, + "learning_rate": 1.1516671188388805e-06, + "loss": 0.4677, + "step": 9973 + }, + { + "epoch": 0.85, + "learning_rate": 1.1503808067928557e-06, + "loss": 0.4563, + "step": 9974 + }, + { + "epoch": 0.85, + "learning_rate": 1.1490951696557385e-06, + "loss": 0.4433, + "step": 9975 + }, + { + "epoch": 0.85, + "learning_rate": 1.147810207525577e-06, + "loss": 0.4282, + "step": 9976 + }, + { + "epoch": 0.85, + "learning_rate": 1.146525920500363e-06, + "loss": 0.4705, + "step": 9977 + }, + { + "epoch": 0.85, + "learning_rate": 1.1452423086780463e-06, + "loss": 0.4594, + "step": 9978 + }, + { + "epoch": 0.85, + "learning_rate": 1.143959372156518e-06, + "loss": 0.4722, + "step": 9979 + }, + { + "epoch": 0.85, + "learning_rate": 1.14267711103362e-06, + "loss": 0.4484, + "step": 9980 + }, + { + "epoch": 0.85, + "learning_rate": 1.1413955254071441e-06, + "loss": 0.4551, + "step": 9981 + }, + { + "epoch": 0.85, + "learning_rate": 1.140114615374831e-06, + "loss": 0.4644, + "step": 9982 + }, + { + "epoch": 0.85, + "learning_rate": 1.1388343810343627e-06, + "loss": 0.4479, + "step": 9983 + }, + { + "epoch": 0.85, + "learning_rate": 1.137554822483381e-06, + "loss": 0.444, + "step": 9984 + }, + { + "epoch": 0.85, + "learning_rate": 1.136275939819469e-06, + "loss": 0.4556, + "step": 9985 + }, + { + "epoch": 0.85, + "learning_rate": 1.1349977331401573e-06, + "loss": 0.4528, + "step": 9986 + }, + { + "epoch": 0.85, + "learning_rate": 1.1337202025429295e-06, + "loss": 0.452, + "step": 9987 + }, + { + "epoch": 0.85, + "learning_rate": 1.132443348125214e-06, + "loss": 0.4551, + "step": 9988 + }, + { + "epoch": 0.85, + "learning_rate": 1.1311671699843896e-06, + "loss": 0.453, + "step": 9989 + }, + { + "epoch": 0.85, + "learning_rate": 1.129891668217783e-06, + "loss": 0.4525, + "step": 9990 + }, + { + "epoch": 0.85, + "learning_rate": 1.128616842922672e-06, + "loss": 0.4557, + "step": 9991 + }, + { + "epoch": 0.85, + "learning_rate": 1.1273426941962728e-06, + "loss": 0.4703, + "step": 9992 + }, + { + "epoch": 0.85, + "learning_rate": 1.1260692221357638e-06, + "loss": 0.4475, + "step": 9993 + }, + { + "epoch": 0.85, + "learning_rate": 1.1247964268382661e-06, + "loss": 0.4385, + "step": 9994 + }, + { + "epoch": 0.85, + "learning_rate": 1.123524308400844e-06, + "loss": 0.466, + "step": 9995 + }, + { + "epoch": 0.85, + "learning_rate": 1.1222528669205158e-06, + "loss": 0.4458, + "step": 9996 + }, + { + "epoch": 0.85, + "learning_rate": 1.120982102494247e-06, + "loss": 0.4526, + "step": 9997 + }, + { + "epoch": 0.85, + "learning_rate": 1.1197120152189522e-06, + "loss": 0.4408, + "step": 9998 + }, + { + "epoch": 0.85, + "learning_rate": 1.1184426051914932e-06, + "loss": 0.4658, + "step": 9999 + }, + { + "epoch": 0.85, + "learning_rate": 1.1171738725086833e-06, + "loss": 0.4664, + "step": 10000 + }, + { + "epoch": 0.85, + "learning_rate": 1.1159058172672732e-06, + "loss": 0.4579, + "step": 10001 + }, + { + "epoch": 0.85, + "learning_rate": 1.1146384395639786e-06, + "loss": 0.4572, + "step": 10002 + }, + { + "epoch": 0.85, + "learning_rate": 1.1133717394954536e-06, + "loss": 0.4424, + "step": 10003 + }, + { + "epoch": 0.85, + "learning_rate": 1.1121057171582984e-06, + "loss": 0.4572, + "step": 10004 + }, + { + "epoch": 0.85, + "learning_rate": 1.1108403726490669e-06, + "loss": 0.4548, + "step": 10005 + }, + { + "epoch": 0.85, + "learning_rate": 1.1095757060642588e-06, + "loss": 0.4449, + "step": 10006 + }, + { + "epoch": 0.85, + "learning_rate": 1.1083117175003245e-06, + "loss": 0.4556, + "step": 10007 + }, + { + "epoch": 0.85, + "learning_rate": 1.1070484070536613e-06, + "loss": 0.4641, + "step": 10008 + }, + { + "epoch": 0.85, + "learning_rate": 1.1057857748206148e-06, + "loss": 0.474, + "step": 10009 + }, + { + "epoch": 0.85, + "learning_rate": 1.104523820897474e-06, + "loss": 0.4553, + "step": 10010 + }, + { + "epoch": 0.85, + "learning_rate": 1.1032625453804835e-06, + "loss": 0.4554, + "step": 10011 + }, + { + "epoch": 0.85, + "learning_rate": 1.1020019483658385e-06, + "loss": 0.4509, + "step": 10012 + }, + { + "epoch": 0.85, + "learning_rate": 1.1007420299496696e-06, + "loss": 0.4401, + "step": 10013 + }, + { + "epoch": 0.85, + "learning_rate": 1.0994827902280681e-06, + "loss": 0.4813, + "step": 10014 + }, + { + "epoch": 0.85, + "learning_rate": 1.0982242292970668e-06, + "loss": 0.4585, + "step": 10015 + }, + { + "epoch": 0.85, + "learning_rate": 1.0969663472526492e-06, + "loss": 0.4447, + "step": 10016 + }, + { + "epoch": 0.85, + "learning_rate": 1.0957091441907475e-06, + "loss": 0.4292, + "step": 10017 + }, + { + "epoch": 0.85, + "learning_rate": 1.0944526202072424e-06, + "loss": 0.484, + "step": 10018 + }, + { + "epoch": 0.85, + "learning_rate": 1.093196775397959e-06, + "loss": 0.4516, + "step": 10019 + }, + { + "epoch": 0.85, + "learning_rate": 1.0919416098586711e-06, + "loss": 0.451, + "step": 10020 + }, + { + "epoch": 0.85, + "learning_rate": 1.0906871236851114e-06, + "loss": 0.4504, + "step": 10021 + }, + { + "epoch": 0.85, + "learning_rate": 1.0894333169729432e-06, + "loss": 0.4458, + "step": 10022 + }, + { + "epoch": 0.85, + "learning_rate": 1.0881801898177924e-06, + "loss": 0.455, + "step": 10023 + }, + { + "epoch": 0.85, + "learning_rate": 1.0869277423152248e-06, + "loss": 0.4511, + "step": 10024 + }, + { + "epoch": 0.85, + "learning_rate": 1.0856759745607592e-06, + "loss": 0.4793, + "step": 10025 + }, + { + "epoch": 0.85, + "learning_rate": 1.0844248866498598e-06, + "loss": 0.4239, + "step": 10026 + }, + { + "epoch": 0.85, + "learning_rate": 1.083174478677942e-06, + "loss": 0.4493, + "step": 10027 + }, + { + "epoch": 0.86, + "learning_rate": 1.0819247507403629e-06, + "loss": 0.4518, + "step": 10028 + }, + { + "epoch": 0.86, + "learning_rate": 1.0806757029324321e-06, + "loss": 0.457, + "step": 10029 + }, + { + "epoch": 0.86, + "learning_rate": 1.0794273353494144e-06, + "loss": 0.4613, + "step": 10030 + }, + { + "epoch": 0.86, + "learning_rate": 1.078179648086507e-06, + "loss": 0.4527, + "step": 10031 + }, + { + "epoch": 0.86, + "learning_rate": 1.076932641238868e-06, + "loss": 0.4446, + "step": 10032 + }, + { + "epoch": 0.86, + "learning_rate": 1.0756863149015972e-06, + "loss": 0.4473, + "step": 10033 + }, + { + "epoch": 0.86, + "learning_rate": 1.0744406691697474e-06, + "loss": 0.4778, + "step": 10034 + }, + { + "epoch": 0.86, + "learning_rate": 1.0731957041383146e-06, + "loss": 0.4777, + "step": 10035 + }, + { + "epoch": 0.86, + "learning_rate": 1.0719514199022473e-06, + "loss": 0.4481, + "step": 10036 + }, + { + "epoch": 0.86, + "learning_rate": 1.0707078165564366e-06, + "loss": 0.4598, + "step": 10037 + }, + { + "epoch": 0.86, + "learning_rate": 1.0694648941957241e-06, + "loss": 0.4915, + "step": 10038 + }, + { + "epoch": 0.86, + "learning_rate": 1.0682226529149076e-06, + "loss": 0.4472, + "step": 10039 + }, + { + "epoch": 0.86, + "learning_rate": 1.0669810928087176e-06, + "loss": 0.4595, + "step": 10040 + }, + { + "epoch": 0.86, + "learning_rate": 1.0657402139718442e-06, + "loss": 0.4385, + "step": 10041 + }, + { + "epoch": 0.86, + "learning_rate": 1.0645000164989217e-06, + "loss": 0.4318, + "step": 10042 + }, + { + "epoch": 0.86, + "learning_rate": 1.063260500484532e-06, + "loss": 0.4712, + "step": 10043 + }, + { + "epoch": 0.86, + "learning_rate": 1.0620216660232074e-06, + "loss": 0.4646, + "step": 10044 + }, + { + "epoch": 0.86, + "learning_rate": 1.0607835132094258e-06, + "loss": 0.4607, + "step": 10045 + }, + { + "epoch": 0.86, + "learning_rate": 1.0595460421376125e-06, + "loss": 0.4341, + "step": 10046 + }, + { + "epoch": 0.86, + "learning_rate": 1.0583092529021411e-06, + "loss": 0.4243, + "step": 10047 + }, + { + "epoch": 0.86, + "learning_rate": 1.0570731455973415e-06, + "loss": 0.4519, + "step": 10048 + }, + { + "epoch": 0.86, + "learning_rate": 1.0558377203174764e-06, + "loss": 0.4485, + "step": 10049 + }, + { + "epoch": 0.86, + "learning_rate": 1.054602977156768e-06, + "loss": 0.461, + "step": 10050 + }, + { + "epoch": 0.86, + "learning_rate": 1.053368916209382e-06, + "loss": 0.4834, + "step": 10051 + }, + { + "epoch": 0.86, + "learning_rate": 1.052135537569433e-06, + "loss": 0.4525, + "step": 10052 + }, + { + "epoch": 0.86, + "learning_rate": 1.0509028413309851e-06, + "loss": 0.4573, + "step": 10053 + }, + { + "epoch": 0.86, + "learning_rate": 1.0496708275880497e-06, + "loss": 0.4669, + "step": 10054 + }, + { + "epoch": 0.86, + "learning_rate": 1.0484394964345812e-06, + "loss": 0.4563, + "step": 10055 + }, + { + "epoch": 0.86, + "learning_rate": 1.0472088479644882e-06, + "loss": 0.447, + "step": 10056 + }, + { + "epoch": 0.86, + "learning_rate": 1.0459788822716255e-06, + "loss": 0.4527, + "step": 10057 + }, + { + "epoch": 0.86, + "learning_rate": 1.0447495994497958e-06, + "loss": 0.4441, + "step": 10058 + }, + { + "epoch": 0.86, + "learning_rate": 1.0435209995927476e-06, + "loss": 0.4777, + "step": 10059 + }, + { + "epoch": 0.86, + "learning_rate": 1.0422930827941803e-06, + "loss": 0.4445, + "step": 10060 + }, + { + "epoch": 0.86, + "learning_rate": 1.041065849147741e-06, + "loss": 0.4542, + "step": 10061 + }, + { + "epoch": 0.86, + "learning_rate": 1.0398392987470208e-06, + "loss": 0.479, + "step": 10062 + }, + { + "epoch": 0.86, + "learning_rate": 1.0386134316855667e-06, + "loss": 0.4476, + "step": 10063 + }, + { + "epoch": 0.86, + "learning_rate": 1.037388248056862e-06, + "loss": 0.4483, + "step": 10064 + }, + { + "epoch": 0.86, + "learning_rate": 1.0361637479543474e-06, + "loss": 0.4409, + "step": 10065 + }, + { + "epoch": 0.86, + "learning_rate": 1.034939931471408e-06, + "loss": 0.4653, + "step": 10066 + }, + { + "epoch": 0.86, + "learning_rate": 1.0337167987013785e-06, + "loss": 0.4398, + "step": 10067 + }, + { + "epoch": 0.86, + "learning_rate": 1.0324943497375383e-06, + "loss": 0.452, + "step": 10068 + }, + { + "epoch": 0.86, + "learning_rate": 1.0312725846731174e-06, + "loss": 0.4388, + "step": 10069 + }, + { + "epoch": 0.86, + "learning_rate": 1.0300515036012926e-06, + "loss": 0.4548, + "step": 10070 + }, + { + "epoch": 0.86, + "learning_rate": 1.028831106615188e-06, + "loss": 0.4606, + "step": 10071 + }, + { + "epoch": 0.86, + "learning_rate": 1.0276113938078768e-06, + "loss": 0.4446, + "step": 10072 + }, + { + "epoch": 0.86, + "learning_rate": 1.0263923652723816e-06, + "loss": 0.4434, + "step": 10073 + }, + { + "epoch": 0.86, + "learning_rate": 1.0251740211016658e-06, + "loss": 0.4432, + "step": 10074 + }, + { + "epoch": 0.86, + "learning_rate": 1.0239563613886495e-06, + "loss": 0.4612, + "step": 10075 + }, + { + "epoch": 0.86, + "learning_rate": 1.0227393862261937e-06, + "loss": 0.4573, + "step": 10076 + }, + { + "epoch": 0.86, + "learning_rate": 1.0215230957071108e-06, + "loss": 0.4421, + "step": 10077 + }, + { + "epoch": 0.86, + "learning_rate": 1.0203074899241616e-06, + "loss": 0.4483, + "step": 10078 + }, + { + "epoch": 0.86, + "learning_rate": 1.0190925689700514e-06, + "loss": 0.4615, + "step": 10079 + }, + { + "epoch": 0.86, + "learning_rate": 1.0178783329374363e-06, + "loss": 0.4921, + "step": 10080 + }, + { + "epoch": 0.86, + "learning_rate": 1.0166647819189202e-06, + "loss": 0.4654, + "step": 10081 + }, + { + "epoch": 0.86, + "learning_rate": 1.0154519160070519e-06, + "loss": 0.4454, + "step": 10082 + }, + { + "epoch": 0.86, + "learning_rate": 1.014239735294329e-06, + "loss": 0.4602, + "step": 10083 + }, + { + "epoch": 0.86, + "learning_rate": 1.0130282398731984e-06, + "loss": 0.4664, + "step": 10084 + }, + { + "epoch": 0.86, + "learning_rate": 1.011817429836054e-06, + "loss": 0.4709, + "step": 10085 + }, + { + "epoch": 0.86, + "learning_rate": 1.0106073052752364e-06, + "loss": 0.4568, + "step": 10086 + }, + { + "epoch": 0.86, + "learning_rate": 1.0093978662830351e-06, + "loss": 0.4502, + "step": 10087 + }, + { + "epoch": 0.86, + "learning_rate": 1.0081891129516896e-06, + "loss": 0.456, + "step": 10088 + }, + { + "epoch": 0.86, + "learning_rate": 1.0069810453733774e-06, + "loss": 0.4526, + "step": 10089 + }, + { + "epoch": 0.86, + "learning_rate": 1.0057736636402382e-06, + "loss": 0.4623, + "step": 10090 + }, + { + "epoch": 0.86, + "learning_rate": 1.0045669678443504e-06, + "loss": 0.4509, + "step": 10091 + }, + { + "epoch": 0.86, + "learning_rate": 1.0033609580777392e-06, + "loss": 0.4564, + "step": 10092 + }, + { + "epoch": 0.86, + "learning_rate": 1.0021556344323812e-06, + "loss": 0.4641, + "step": 10093 + }, + { + "epoch": 0.86, + "learning_rate": 1.0009509970001985e-06, + "loss": 0.4524, + "step": 10094 + }, + { + "epoch": 0.86, + "learning_rate": 9.99747045873063e-07, + "loss": 0.4484, + "step": 10095 + }, + { + "epoch": 0.86, + "learning_rate": 9.985437811427934e-07, + "loss": 0.4612, + "step": 10096 + }, + { + "epoch": 0.86, + "learning_rate": 9.973412029011564e-07, + "loss": 0.4455, + "step": 10097 + }, + { + "epoch": 0.86, + "learning_rate": 9.961393112398599e-07, + "loss": 0.4557, + "step": 10098 + }, + { + "epoch": 0.86, + "learning_rate": 9.949381062505726e-07, + "loss": 0.433, + "step": 10099 + }, + { + "epoch": 0.86, + "learning_rate": 9.937375880249012e-07, + "loss": 0.4749, + "step": 10100 + }, + { + "epoch": 0.86, + "learning_rate": 9.925377566544003e-07, + "loss": 0.4745, + "step": 10101 + }, + { + "epoch": 0.86, + "learning_rate": 9.913386122305747e-07, + "loss": 0.4432, + "step": 10102 + }, + { + "epoch": 0.86, + "learning_rate": 9.901401548448764e-07, + "loss": 0.466, + "step": 10103 + }, + { + "epoch": 0.86, + "learning_rate": 9.889423845887048e-07, + "loss": 0.4176, + "step": 10104 + }, + { + "epoch": 0.86, + "learning_rate": 9.877453015534066e-07, + "loss": 0.4752, + "step": 10105 + }, + { + "epoch": 0.86, + "learning_rate": 9.865489058302791e-07, + "loss": 0.4692, + "step": 10106 + }, + { + "epoch": 0.86, + "learning_rate": 9.85353197510559e-07, + "loss": 0.4506, + "step": 10107 + }, + { + "epoch": 0.86, + "learning_rate": 9.841581766854402e-07, + "loss": 0.4561, + "step": 10108 + }, + { + "epoch": 0.86, + "learning_rate": 9.829638434460609e-07, + "loss": 0.453, + "step": 10109 + }, + { + "epoch": 0.86, + "learning_rate": 9.817701978835026e-07, + "loss": 0.4542, + "step": 10110 + }, + { + "epoch": 0.86, + "learning_rate": 9.80577240088798e-07, + "loss": 0.4442, + "step": 10111 + }, + { + "epoch": 0.86, + "learning_rate": 9.79384970152928e-07, + "loss": 0.4604, + "step": 10112 + }, + { + "epoch": 0.86, + "learning_rate": 9.781933881668203e-07, + "loss": 0.4398, + "step": 10113 + }, + { + "epoch": 0.86, + "learning_rate": 9.770024942213507e-07, + "loss": 0.4777, + "step": 10114 + }, + { + "epoch": 0.86, + "learning_rate": 9.758122884073417e-07, + "loss": 0.4495, + "step": 10115 + }, + { + "epoch": 0.86, + "learning_rate": 9.746227708155586e-07, + "loss": 0.4469, + "step": 10116 + }, + { + "epoch": 0.86, + "learning_rate": 9.734339415367254e-07, + "loss": 0.4524, + "step": 10117 + }, + { + "epoch": 0.86, + "learning_rate": 9.722458006615066e-07, + "loss": 0.4559, + "step": 10118 + }, + { + "epoch": 0.86, + "learning_rate": 9.710583482805102e-07, + "loss": 0.4655, + "step": 10119 + }, + { + "epoch": 0.86, + "learning_rate": 9.698715844842988e-07, + "loss": 0.4364, + "step": 10120 + }, + { + "epoch": 0.86, + "learning_rate": 9.686855093633807e-07, + "loss": 0.455, + "step": 10121 + }, + { + "epoch": 0.86, + "learning_rate": 9.675001230082092e-07, + "loss": 0.4518, + "step": 10122 + }, + { + "epoch": 0.86, + "learning_rate": 9.663154255091889e-07, + "loss": 0.4498, + "step": 10123 + }, + { + "epoch": 0.86, + "learning_rate": 9.651314169566694e-07, + "loss": 0.4634, + "step": 10124 + }, + { + "epoch": 0.86, + "learning_rate": 9.639480974409453e-07, + "loss": 0.4433, + "step": 10125 + }, + { + "epoch": 0.86, + "learning_rate": 9.627654670522646e-07, + "loss": 0.4675, + "step": 10126 + }, + { + "epoch": 0.86, + "learning_rate": 9.615835258808203e-07, + "loss": 0.4464, + "step": 10127 + }, + { + "epoch": 0.86, + "learning_rate": 9.604022740167496e-07, + "loss": 0.4775, + "step": 10128 + }, + { + "epoch": 0.86, + "learning_rate": 9.5922171155014e-07, + "loss": 0.448, + "step": 10129 + }, + { + "epoch": 0.86, + "learning_rate": 9.580418385710278e-07, + "loss": 0.4555, + "step": 10130 + }, + { + "epoch": 0.86, + "learning_rate": 9.568626551693927e-07, + "loss": 0.4499, + "step": 10131 + }, + { + "epoch": 0.86, + "learning_rate": 9.556841614351664e-07, + "loss": 0.4456, + "step": 10132 + }, + { + "epoch": 0.86, + "learning_rate": 9.545063574582258e-07, + "loss": 0.4528, + "step": 10133 + }, + { + "epoch": 0.86, + "learning_rate": 9.533292433283914e-07, + "loss": 0.4586, + "step": 10134 + }, + { + "epoch": 0.86, + "learning_rate": 9.52152819135439e-07, + "loss": 0.4541, + "step": 10135 + }, + { + "epoch": 0.86, + "learning_rate": 9.50977084969088e-07, + "loss": 0.4389, + "step": 10136 + }, + { + "epoch": 0.86, + "learning_rate": 9.498020409190012e-07, + "loss": 0.4731, + "step": 10137 + }, + { + "epoch": 0.86, + "learning_rate": 9.486276870747946e-07, + "loss": 0.4401, + "step": 10138 + }, + { + "epoch": 0.86, + "learning_rate": 9.474540235260288e-07, + "loss": 0.446, + "step": 10139 + }, + { + "epoch": 0.86, + "learning_rate": 9.462810503622122e-07, + "loss": 0.4586, + "step": 10140 + }, + { + "epoch": 0.86, + "learning_rate": 9.45108767672801e-07, + "loss": 0.4445, + "step": 10141 + }, + { + "epoch": 0.86, + "learning_rate": 9.439371755472005e-07, + "loss": 0.4614, + "step": 10142 + }, + { + "epoch": 0.86, + "learning_rate": 9.427662740747567e-07, + "loss": 0.4439, + "step": 10143 + }, + { + "epoch": 0.86, + "learning_rate": 9.415960633447674e-07, + "loss": 0.4707, + "step": 10144 + }, + { + "epoch": 0.87, + "learning_rate": 9.404265434464844e-07, + "loss": 0.4491, + "step": 10145 + }, + { + "epoch": 0.87, + "learning_rate": 9.392577144690929e-07, + "loss": 0.4493, + "step": 10146 + }, + { + "epoch": 0.87, + "learning_rate": 9.380895765017361e-07, + "loss": 0.4598, + "step": 10147 + }, + { + "epoch": 0.87, + "learning_rate": 9.369221296335007e-07, + "loss": 0.4479, + "step": 10148 + }, + { + "epoch": 0.87, + "learning_rate": 9.357553739534208e-07, + "loss": 0.4593, + "step": 10149 + }, + { + "epoch": 0.87, + "learning_rate": 9.345893095504777e-07, + "loss": 0.4472, + "step": 10150 + }, + { + "epoch": 0.87, + "learning_rate": 9.334239365136033e-07, + "loss": 0.4895, + "step": 10151 + }, + { + "epoch": 0.87, + "learning_rate": 9.3225925493167e-07, + "loss": 0.4482, + "step": 10152 + }, + { + "epoch": 0.87, + "learning_rate": 9.310952648935001e-07, + "loss": 0.4599, + "step": 10153 + }, + { + "epoch": 0.87, + "learning_rate": 9.299319664878703e-07, + "loss": 0.4647, + "step": 10154 + }, + { + "epoch": 0.87, + "learning_rate": 9.28769359803493e-07, + "loss": 0.4689, + "step": 10155 + }, + { + "epoch": 0.87, + "learning_rate": 9.276074449290362e-07, + "loss": 0.4643, + "step": 10156 + }, + { + "epoch": 0.87, + "learning_rate": 9.264462219531112e-07, + "loss": 0.4412, + "step": 10157 + }, + { + "epoch": 0.87, + "learning_rate": 9.252856909642794e-07, + "loss": 0.4676, + "step": 10158 + }, + { + "epoch": 0.87, + "learning_rate": 9.241258520510454e-07, + "loss": 0.4388, + "step": 10159 + }, + { + "epoch": 0.87, + "learning_rate": 9.229667053018665e-07, + "loss": 0.4494, + "step": 10160 + }, + { + "epoch": 0.87, + "learning_rate": 9.218082508051407e-07, + "loss": 0.4549, + "step": 10161 + }, + { + "epoch": 0.87, + "learning_rate": 9.206504886492162e-07, + "loss": 0.455, + "step": 10162 + }, + { + "epoch": 0.87, + "learning_rate": 9.194934189223947e-07, + "loss": 0.4369, + "step": 10163 + }, + { + "epoch": 0.87, + "learning_rate": 9.183370417129122e-07, + "loss": 0.4478, + "step": 10164 + }, + { + "epoch": 0.87, + "learning_rate": 9.171813571089628e-07, + "loss": 0.4521, + "step": 10165 + }, + { + "epoch": 0.87, + "learning_rate": 9.160263651986834e-07, + "loss": 0.4531, + "step": 10166 + }, + { + "epoch": 0.87, + "learning_rate": 9.148720660701549e-07, + "loss": 0.4419, + "step": 10167 + }, + { + "epoch": 0.87, + "learning_rate": 9.137184598114135e-07, + "loss": 0.423, + "step": 10168 + }, + { + "epoch": 0.87, + "learning_rate": 9.125655465104388e-07, + "loss": 0.4534, + "step": 10169 + }, + { + "epoch": 0.87, + "learning_rate": 9.114133262551517e-07, + "loss": 0.4679, + "step": 10170 + }, + { + "epoch": 0.87, + "learning_rate": 9.102617991334273e-07, + "loss": 0.4643, + "step": 10171 + }, + { + "epoch": 0.87, + "learning_rate": 9.091109652330887e-07, + "loss": 0.4434, + "step": 10172 + }, + { + "epoch": 0.87, + "learning_rate": 9.079608246419003e-07, + "loss": 0.4431, + "step": 10173 + }, + { + "epoch": 0.87, + "learning_rate": 9.068113774475784e-07, + "loss": 0.463, + "step": 10174 + }, + { + "epoch": 0.87, + "learning_rate": 9.056626237377841e-07, + "loss": 0.4306, + "step": 10175 + }, + { + "epoch": 0.87, + "learning_rate": 9.045145636001229e-07, + "loss": 0.4532, + "step": 10176 + }, + { + "epoch": 0.87, + "learning_rate": 9.033671971221558e-07, + "loss": 0.4661, + "step": 10177 + }, + { + "epoch": 0.87, + "learning_rate": 9.022205243913851e-07, + "loss": 0.464, + "step": 10178 + }, + { + "epoch": 0.87, + "learning_rate": 9.010745454952563e-07, + "loss": 0.4397, + "step": 10179 + }, + { + "epoch": 0.87, + "learning_rate": 8.999292605211695e-07, + "loss": 0.4377, + "step": 10180 + }, + { + "epoch": 0.87, + "learning_rate": 8.987846695564717e-07, + "loss": 0.4348, + "step": 10181 + }, + { + "epoch": 0.87, + "learning_rate": 8.976407726884495e-07, + "loss": 0.4456, + "step": 10182 + }, + { + "epoch": 0.87, + "learning_rate": 8.964975700043433e-07, + "loss": 0.4446, + "step": 10183 + }, + { + "epoch": 0.87, + "learning_rate": 8.953550615913398e-07, + "loss": 0.4477, + "step": 10184 + }, + { + "epoch": 0.87, + "learning_rate": 8.942132475365672e-07, + "loss": 0.446, + "step": 10185 + }, + { + "epoch": 0.87, + "learning_rate": 8.930721279271093e-07, + "loss": 0.4606, + "step": 10186 + }, + { + "epoch": 0.87, + "learning_rate": 8.91931702849993e-07, + "loss": 0.4689, + "step": 10187 + }, + { + "epoch": 0.87, + "learning_rate": 8.907919723921888e-07, + "loss": 0.4585, + "step": 10188 + }, + { + "epoch": 0.87, + "learning_rate": 8.896529366406181e-07, + "loss": 0.4418, + "step": 10189 + }, + { + "epoch": 0.87, + "learning_rate": 8.885145956821495e-07, + "loss": 0.482, + "step": 10190 + }, + { + "epoch": 0.87, + "learning_rate": 8.873769496035966e-07, + "loss": 0.447, + "step": 10191 + }, + { + "epoch": 0.87, + "learning_rate": 8.862399984917214e-07, + "loss": 0.4593, + "step": 10192 + }, + { + "epoch": 0.87, + "learning_rate": 8.851037424332331e-07, + "loss": 0.4708, + "step": 10193 + }, + { + "epoch": 0.87, + "learning_rate": 8.839681815147871e-07, + "loss": 0.4309, + "step": 10194 + }, + { + "epoch": 0.87, + "learning_rate": 8.828333158229851e-07, + "loss": 0.4706, + "step": 10195 + }, + { + "epoch": 0.87, + "learning_rate": 8.816991454443802e-07, + "loss": 0.4564, + "step": 10196 + }, + { + "epoch": 0.87, + "learning_rate": 8.805656704654642e-07, + "loss": 0.4718, + "step": 10197 + }, + { + "epoch": 0.87, + "learning_rate": 8.794328909726823e-07, + "loss": 0.4562, + "step": 10198 + }, + { + "epoch": 0.87, + "learning_rate": 8.783008070524257e-07, + "loss": 0.4506, + "step": 10199 + }, + { + "epoch": 0.87, + "learning_rate": 8.771694187910307e-07, + "loss": 0.4562, + "step": 10200 + }, + { + "epoch": 0.87, + "learning_rate": 8.760387262747838e-07, + "loss": 0.4582, + "step": 10201 + }, + { + "epoch": 0.87, + "learning_rate": 8.749087295899139e-07, + "loss": 0.4717, + "step": 10202 + }, + { + "epoch": 0.87, + "learning_rate": 8.737794288226009e-07, + "loss": 0.4605, + "step": 10203 + }, + { + "epoch": 0.87, + "learning_rate": 8.726508240589693e-07, + "loss": 0.4481, + "step": 10204 + }, + { + "epoch": 0.87, + "learning_rate": 8.715229153850935e-07, + "loss": 0.492, + "step": 10205 + }, + { + "epoch": 0.87, + "learning_rate": 8.703957028869881e-07, + "loss": 0.4561, + "step": 10206 + }, + { + "epoch": 0.87, + "learning_rate": 8.69269186650622e-07, + "loss": 0.4396, + "step": 10207 + }, + { + "epoch": 0.87, + "learning_rate": 8.681433667619065e-07, + "loss": 0.4584, + "step": 10208 + }, + { + "epoch": 0.87, + "learning_rate": 8.670182433067031e-07, + "loss": 0.4572, + "step": 10209 + }, + { + "epoch": 0.87, + "learning_rate": 8.658938163708175e-07, + "loss": 0.4656, + "step": 10210 + }, + { + "epoch": 0.87, + "learning_rate": 8.647700860400032e-07, + "loss": 0.4721, + "step": 10211 + }, + { + "epoch": 0.87, + "learning_rate": 8.636470523999596e-07, + "loss": 0.4512, + "step": 10212 + }, + { + "epoch": 0.87, + "learning_rate": 8.625247155363358e-07, + "loss": 0.4604, + "step": 10213 + }, + { + "epoch": 0.87, + "learning_rate": 8.614030755347269e-07, + "loss": 0.4521, + "step": 10214 + }, + { + "epoch": 0.87, + "learning_rate": 8.602821324806698e-07, + "loss": 0.46, + "step": 10215 + }, + { + "epoch": 0.87, + "learning_rate": 8.591618864596541e-07, + "loss": 0.4613, + "step": 10216 + }, + { + "epoch": 0.87, + "learning_rate": 8.580423375571156e-07, + "loss": 0.4664, + "step": 10217 + }, + { + "epoch": 0.87, + "learning_rate": 8.569234858584341e-07, + "loss": 0.461, + "step": 10218 + }, + { + "epoch": 0.87, + "learning_rate": 8.5580533144894e-07, + "loss": 0.4491, + "step": 10219 + }, + { + "epoch": 0.87, + "learning_rate": 8.546878744139065e-07, + "loss": 0.4538, + "step": 10220 + }, + { + "epoch": 0.87, + "learning_rate": 8.535711148385572e-07, + "loss": 0.4588, + "step": 10221 + }, + { + "epoch": 0.87, + "learning_rate": 8.524550528080578e-07, + "loss": 0.4614, + "step": 10222 + }, + { + "epoch": 0.87, + "learning_rate": 8.513396884075287e-07, + "loss": 0.4553, + "step": 10223 + }, + { + "epoch": 0.87, + "learning_rate": 8.502250217220276e-07, + "loss": 0.4569, + "step": 10224 + }, + { + "epoch": 0.87, + "learning_rate": 8.491110528365653e-07, + "loss": 0.4723, + "step": 10225 + }, + { + "epoch": 0.87, + "learning_rate": 8.479977818360985e-07, + "loss": 0.4491, + "step": 10226 + }, + { + "epoch": 0.87, + "learning_rate": 8.468852088055291e-07, + "loss": 0.4433, + "step": 10227 + }, + { + "epoch": 0.87, + "learning_rate": 8.457733338297069e-07, + "loss": 0.4471, + "step": 10228 + }, + { + "epoch": 0.87, + "learning_rate": 8.446621569934276e-07, + "loss": 0.464, + "step": 10229 + }, + { + "epoch": 0.87, + "learning_rate": 8.435516783814368e-07, + "loss": 0.4409, + "step": 10230 + }, + { + "epoch": 0.87, + "learning_rate": 8.424418980784177e-07, + "loss": 0.4673, + "step": 10231 + }, + { + "epoch": 0.87, + "learning_rate": 8.413328161690159e-07, + "loss": 0.4807, + "step": 10232 + }, + { + "epoch": 0.87, + "learning_rate": 8.402244327378073e-07, + "loss": 0.4523, + "step": 10233 + }, + { + "epoch": 0.87, + "learning_rate": 8.391167478693241e-07, + "loss": 0.4505, + "step": 10234 + }, + { + "epoch": 0.87, + "learning_rate": 8.380097616480443e-07, + "loss": 0.451, + "step": 10235 + }, + { + "epoch": 0.87, + "learning_rate": 8.369034741583892e-07, + "loss": 0.4687, + "step": 10236 + }, + { + "epoch": 0.87, + "learning_rate": 8.357978854847304e-07, + "loss": 0.4402, + "step": 10237 + }, + { + "epoch": 0.87, + "learning_rate": 8.346929957113848e-07, + "loss": 0.4528, + "step": 10238 + }, + { + "epoch": 0.87, + "learning_rate": 8.335888049226159e-07, + "loss": 0.4608, + "step": 10239 + }, + { + "epoch": 0.87, + "learning_rate": 8.3248531320263e-07, + "loss": 0.4454, + "step": 10240 + }, + { + "epoch": 0.87, + "learning_rate": 8.313825206355919e-07, + "loss": 0.4538, + "step": 10241 + }, + { + "epoch": 0.87, + "learning_rate": 8.302804273055976e-07, + "loss": 0.446, + "step": 10242 + }, + { + "epoch": 0.87, + "learning_rate": 8.291790332967009e-07, + "loss": 0.452, + "step": 10243 + }, + { + "epoch": 0.87, + "learning_rate": 8.280783386928981e-07, + "loss": 0.4447, + "step": 10244 + }, + { + "epoch": 0.87, + "learning_rate": 8.269783435781331e-07, + "loss": 0.4816, + "step": 10245 + }, + { + "epoch": 0.87, + "learning_rate": 8.258790480362955e-07, + "loss": 0.4558, + "step": 10246 + }, + { + "epoch": 0.87, + "learning_rate": 8.247804521512237e-07, + "loss": 0.4583, + "step": 10247 + }, + { + "epoch": 0.87, + "learning_rate": 8.236825560066997e-07, + "loss": 0.4601, + "step": 10248 + }, + { + "epoch": 0.87, + "learning_rate": 8.225853596864519e-07, + "loss": 0.4598, + "step": 10249 + }, + { + "epoch": 0.87, + "learning_rate": 8.214888632741603e-07, + "loss": 0.4572, + "step": 10250 + }, + { + "epoch": 0.87, + "learning_rate": 8.203930668534488e-07, + "loss": 0.4711, + "step": 10251 + }, + { + "epoch": 0.87, + "learning_rate": 8.192979705078852e-07, + "loss": 0.4674, + "step": 10252 + }, + { + "epoch": 0.87, + "learning_rate": 8.182035743209848e-07, + "loss": 0.4322, + "step": 10253 + }, + { + "epoch": 0.87, + "learning_rate": 8.171098783762132e-07, + "loss": 0.4635, + "step": 10254 + }, + { + "epoch": 0.87, + "learning_rate": 8.160168827569804e-07, + "loss": 0.462, + "step": 10255 + }, + { + "epoch": 0.87, + "learning_rate": 8.149245875466416e-07, + "loss": 0.4446, + "step": 10256 + }, + { + "epoch": 0.87, + "learning_rate": 8.138329928285027e-07, + "loss": 0.4544, + "step": 10257 + }, + { + "epoch": 0.87, + "learning_rate": 8.12742098685807e-07, + "loss": 0.4608, + "step": 10258 + }, + { + "epoch": 0.87, + "learning_rate": 8.116519052017558e-07, + "loss": 0.4715, + "step": 10259 + }, + { + "epoch": 0.87, + "learning_rate": 8.105624124594924e-07, + "loss": 0.4478, + "step": 10260 + }, + { + "epoch": 0.87, + "learning_rate": 8.094736205421027e-07, + "loss": 0.4566, + "step": 10261 + }, + { + "epoch": 0.88, + "learning_rate": 8.083855295326237e-07, + "loss": 0.4485, + "step": 10262 + }, + { + "epoch": 0.88, + "learning_rate": 8.072981395140378e-07, + "loss": 0.4654, + "step": 10263 + }, + { + "epoch": 0.88, + "learning_rate": 8.062114505692742e-07, + "loss": 0.4516, + "step": 10264 + }, + { + "epoch": 0.88, + "learning_rate": 8.051254627812088e-07, + "loss": 0.4475, + "step": 10265 + }, + { + "epoch": 0.88, + "learning_rate": 8.040401762326655e-07, + "loss": 0.4618, + "step": 10266 + }, + { + "epoch": 0.88, + "learning_rate": 8.029555910064069e-07, + "loss": 0.4352, + "step": 10267 + }, + { + "epoch": 0.88, + "learning_rate": 8.018717071851512e-07, + "loss": 0.4856, + "step": 10268 + }, + { + "epoch": 0.88, + "learning_rate": 8.007885248515624e-07, + "loss": 0.4282, + "step": 10269 + }, + { + "epoch": 0.88, + "learning_rate": 7.997060440882453e-07, + "loss": 0.4323, + "step": 10270 + }, + { + "epoch": 0.88, + "learning_rate": 7.986242649777553e-07, + "loss": 0.4573, + "step": 10271 + }, + { + "epoch": 0.88, + "learning_rate": 7.97543187602593e-07, + "loss": 0.473, + "step": 10272 + }, + { + "epoch": 0.88, + "learning_rate": 7.964628120452067e-07, + "loss": 0.458, + "step": 10273 + }, + { + "epoch": 0.88, + "learning_rate": 7.953831383879895e-07, + "loss": 0.4484, + "step": 10274 + }, + { + "epoch": 0.88, + "learning_rate": 7.943041667132845e-07, + "loss": 0.4618, + "step": 10275 + }, + { + "epoch": 0.88, + "learning_rate": 7.932258971033746e-07, + "loss": 0.4482, + "step": 10276 + }, + { + "epoch": 0.88, + "learning_rate": 7.92148329640493e-07, + "loss": 0.4556, + "step": 10277 + }, + { + "epoch": 0.88, + "learning_rate": 7.910714644068251e-07, + "loss": 0.4721, + "step": 10278 + }, + { + "epoch": 0.88, + "learning_rate": 7.899953014844919e-07, + "loss": 0.4489, + "step": 10279 + }, + { + "epoch": 0.88, + "learning_rate": 7.889198409555665e-07, + "loss": 0.4547, + "step": 10280 + }, + { + "epoch": 0.88, + "learning_rate": 7.8784508290207e-07, + "loss": 0.45, + "step": 10281 + }, + { + "epoch": 0.88, + "learning_rate": 7.86771027405967e-07, + "loss": 0.448, + "step": 10282 + }, + { + "epoch": 0.88, + "learning_rate": 7.856976745491696e-07, + "loss": 0.4686, + "step": 10283 + }, + { + "epoch": 0.88, + "learning_rate": 7.846250244135378e-07, + "loss": 0.4561, + "step": 10284 + }, + { + "epoch": 0.88, + "learning_rate": 7.835530770808731e-07, + "loss": 0.4367, + "step": 10285 + }, + { + "epoch": 0.88, + "learning_rate": 7.824818326329264e-07, + "loss": 0.4654, + "step": 10286 + }, + { + "epoch": 0.88, + "learning_rate": 7.814112911514005e-07, + "loss": 0.4697, + "step": 10287 + }, + { + "epoch": 0.88, + "learning_rate": 7.803414527179343e-07, + "loss": 0.4761, + "step": 10288 + }, + { + "epoch": 0.88, + "learning_rate": 7.792723174141192e-07, + "loss": 0.4497, + "step": 10289 + }, + { + "epoch": 0.88, + "learning_rate": 7.782038853214935e-07, + "loss": 0.4412, + "step": 10290 + }, + { + "epoch": 0.88, + "learning_rate": 7.771361565215385e-07, + "loss": 0.4613, + "step": 10291 + }, + { + "epoch": 0.88, + "learning_rate": 7.760691310956847e-07, + "loss": 0.444, + "step": 10292 + }, + { + "epoch": 0.88, + "learning_rate": 7.750028091253104e-07, + "loss": 0.4478, + "step": 10293 + }, + { + "epoch": 0.88, + "learning_rate": 7.739371906917326e-07, + "loss": 0.4683, + "step": 10294 + }, + { + "epoch": 0.88, + "learning_rate": 7.728722758762208e-07, + "loss": 0.4348, + "step": 10295 + }, + { + "epoch": 0.88, + "learning_rate": 7.718080647599946e-07, + "loss": 0.4714, + "step": 10296 + }, + { + "epoch": 0.88, + "learning_rate": 7.7074455742421e-07, + "loss": 0.4445, + "step": 10297 + }, + { + "epoch": 0.88, + "learning_rate": 7.696817539499768e-07, + "loss": 0.449, + "step": 10298 + }, + { + "epoch": 0.88, + "learning_rate": 7.6861965441835e-07, + "loss": 0.4765, + "step": 10299 + }, + { + "epoch": 0.88, + "learning_rate": 7.675582589103248e-07, + "loss": 0.4489, + "step": 10300 + }, + { + "epoch": 0.88, + "learning_rate": 7.664975675068531e-07, + "loss": 0.4371, + "step": 10301 + }, + { + "epoch": 0.88, + "learning_rate": 7.65437580288827e-07, + "loss": 0.4474, + "step": 10302 + }, + { + "epoch": 0.88, + "learning_rate": 7.643782973370817e-07, + "loss": 0.4731, + "step": 10303 + }, + { + "epoch": 0.88, + "learning_rate": 7.633197187324048e-07, + "loss": 0.454, + "step": 10304 + }, + { + "epoch": 0.88, + "learning_rate": 7.622618445555308e-07, + "loss": 0.4405, + "step": 10305 + }, + { + "epoch": 0.88, + "learning_rate": 7.612046748871327e-07, + "loss": 0.4489, + "step": 10306 + }, + { + "epoch": 0.88, + "learning_rate": 7.601482098078372e-07, + "loss": 0.4645, + "step": 10307 + }, + { + "epoch": 0.88, + "learning_rate": 7.590924493982165e-07, + "loss": 0.4477, + "step": 10308 + }, + { + "epoch": 0.88, + "learning_rate": 7.580373937387819e-07, + "loss": 0.4528, + "step": 10309 + }, + { + "epoch": 0.88, + "learning_rate": 7.569830429100012e-07, + "loss": 0.4631, + "step": 10310 + }, + { + "epoch": 0.88, + "learning_rate": 7.559293969922843e-07, + "loss": 0.4534, + "step": 10311 + }, + { + "epoch": 0.88, + "learning_rate": 7.548764560659815e-07, + "loss": 0.4622, + "step": 10312 + }, + { + "epoch": 0.88, + "learning_rate": 7.538242202113965e-07, + "loss": 0.4412, + "step": 10313 + }, + { + "epoch": 0.88, + "learning_rate": 7.527726895087817e-07, + "loss": 0.447, + "step": 10314 + }, + { + "epoch": 0.88, + "learning_rate": 7.517218640383262e-07, + "loss": 0.4291, + "step": 10315 + }, + { + "epoch": 0.88, + "learning_rate": 7.506717438801703e-07, + "loss": 0.472, + "step": 10316 + }, + { + "epoch": 0.88, + "learning_rate": 7.496223291144045e-07, + "loss": 0.46, + "step": 10317 + }, + { + "epoch": 0.88, + "learning_rate": 7.485736198210559e-07, + "loss": 0.4336, + "step": 10318 + }, + { + "epoch": 0.88, + "learning_rate": 7.475256160801081e-07, + "loss": 0.4553, + "step": 10319 + }, + { + "epoch": 0.88, + "learning_rate": 7.464783179714863e-07, + "loss": 0.4685, + "step": 10320 + }, + { + "epoch": 0.88, + "learning_rate": 7.454317255750587e-07, + "loss": 0.4337, + "step": 10321 + }, + { + "epoch": 0.88, + "learning_rate": 7.443858389706449e-07, + "loss": 0.4493, + "step": 10322 + }, + { + "epoch": 0.88, + "learning_rate": 7.433406582380076e-07, + "loss": 0.4327, + "step": 10323 + }, + { + "epoch": 0.88, + "learning_rate": 7.422961834568565e-07, + "loss": 0.4466, + "step": 10324 + }, + { + "epoch": 0.88, + "learning_rate": 7.41252414706849e-07, + "loss": 0.461, + "step": 10325 + }, + { + "epoch": 0.88, + "learning_rate": 7.402093520675879e-07, + "loss": 0.456, + "step": 10326 + }, + { + "epoch": 0.88, + "learning_rate": 7.391669956186165e-07, + "loss": 0.4352, + "step": 10327 + }, + { + "epoch": 0.88, + "learning_rate": 7.381253454394343e-07, + "loss": 0.4514, + "step": 10328 + }, + { + "epoch": 0.88, + "learning_rate": 7.370844016094836e-07, + "loss": 0.4613, + "step": 10329 + }, + { + "epoch": 0.88, + "learning_rate": 7.36044164208145e-07, + "loss": 0.4518, + "step": 10330 + }, + { + "epoch": 0.88, + "learning_rate": 7.350046333147543e-07, + "loss": 0.439, + "step": 10331 + }, + { + "epoch": 0.88, + "learning_rate": 7.339658090085899e-07, + "loss": 0.4764, + "step": 10332 + }, + { + "epoch": 0.88, + "learning_rate": 7.329276913688788e-07, + "loss": 0.4693, + "step": 10333 + }, + { + "epoch": 0.88, + "learning_rate": 7.318902804747896e-07, + "loss": 0.4467, + "step": 10334 + }, + { + "epoch": 0.88, + "learning_rate": 7.308535764054437e-07, + "loss": 0.4763, + "step": 10335 + }, + { + "epoch": 0.88, + "learning_rate": 7.298175792398976e-07, + "loss": 0.4355, + "step": 10336 + }, + { + "epoch": 0.88, + "learning_rate": 7.287822890571661e-07, + "loss": 0.4473, + "step": 10337 + }, + { + "epoch": 0.88, + "learning_rate": 7.277477059362059e-07, + "loss": 0.4565, + "step": 10338 + }, + { + "epoch": 0.88, + "learning_rate": 7.267138299559129e-07, + "loss": 0.4501, + "step": 10339 + }, + { + "epoch": 0.88, + "learning_rate": 7.256806611951395e-07, + "loss": 0.4693, + "step": 10340 + }, + { + "epoch": 0.88, + "learning_rate": 7.246481997326782e-07, + "loss": 0.4588, + "step": 10341 + }, + { + "epoch": 0.88, + "learning_rate": 7.236164456472672e-07, + "loss": 0.4738, + "step": 10342 + }, + { + "epoch": 0.88, + "learning_rate": 7.225853990175946e-07, + "loss": 0.4685, + "step": 10343 + }, + { + "epoch": 0.88, + "learning_rate": 7.215550599222931e-07, + "loss": 0.4572, + "step": 10344 + }, + { + "epoch": 0.88, + "learning_rate": 7.205254284399366e-07, + "loss": 0.4299, + "step": 10345 + }, + { + "epoch": 0.88, + "learning_rate": 7.194965046490521e-07, + "loss": 0.4613, + "step": 10346 + }, + { + "epoch": 0.88, + "learning_rate": 7.184682886281114e-07, + "loss": 0.44, + "step": 10347 + }, + { + "epoch": 0.88, + "learning_rate": 7.174407804555261e-07, + "loss": 0.4391, + "step": 10348 + }, + { + "epoch": 0.88, + "learning_rate": 7.164139802096604e-07, + "loss": 0.4524, + "step": 10349 + }, + { + "epoch": 0.88, + "learning_rate": 7.153878879688225e-07, + "loss": 0.44, + "step": 10350 + }, + { + "epoch": 0.88, + "learning_rate": 7.143625038112667e-07, + "loss": 0.4359, + "step": 10351 + }, + { + "epoch": 0.88, + "learning_rate": 7.133378278151926e-07, + "loss": 0.4407, + "step": 10352 + }, + { + "epoch": 0.88, + "learning_rate": 7.123138600587476e-07, + "loss": 0.4496, + "step": 10353 + }, + { + "epoch": 0.88, + "learning_rate": 7.112906006200215e-07, + "loss": 0.4552, + "step": 10354 + }, + { + "epoch": 0.88, + "learning_rate": 7.102680495770509e-07, + "loss": 0.4759, + "step": 10355 + }, + { + "epoch": 0.88, + "learning_rate": 7.092462070078265e-07, + "loss": 0.4537, + "step": 10356 + }, + { + "epoch": 0.88, + "learning_rate": 7.082250729902718e-07, + "loss": 0.4146, + "step": 10357 + }, + { + "epoch": 0.88, + "learning_rate": 7.072046476022654e-07, + "loss": 0.4612, + "step": 10358 + }, + { + "epoch": 0.88, + "learning_rate": 7.061849309216285e-07, + "loss": 0.4493, + "step": 10359 + }, + { + "epoch": 0.88, + "learning_rate": 7.051659230261299e-07, + "loss": 0.4512, + "step": 10360 + }, + { + "epoch": 0.88, + "learning_rate": 7.041476239934819e-07, + "loss": 0.4521, + "step": 10361 + }, + { + "epoch": 0.88, + "learning_rate": 7.031300339013481e-07, + "loss": 0.4624, + "step": 10362 + }, + { + "epoch": 0.88, + "learning_rate": 7.021131528273284e-07, + "loss": 0.4513, + "step": 10363 + }, + { + "epoch": 0.88, + "learning_rate": 7.010969808489754e-07, + "loss": 0.4352, + "step": 10364 + }, + { + "epoch": 0.88, + "learning_rate": 7.000815180437925e-07, + "loss": 0.4605, + "step": 10365 + }, + { + "epoch": 0.88, + "learning_rate": 6.990667644892168e-07, + "loss": 0.4449, + "step": 10366 + }, + { + "epoch": 0.88, + "learning_rate": 6.980527202626397e-07, + "loss": 0.4461, + "step": 10367 + }, + { + "epoch": 0.88, + "learning_rate": 6.97039385441397e-07, + "loss": 0.4502, + "step": 10368 + }, + { + "epoch": 0.88, + "learning_rate": 6.960267601027693e-07, + "loss": 0.4718, + "step": 10369 + }, + { + "epoch": 0.88, + "learning_rate": 6.950148443239846e-07, + "loss": 0.4352, + "step": 10370 + }, + { + "epoch": 0.88, + "learning_rate": 6.940036381822135e-07, + "loss": 0.4505, + "step": 10371 + }, + { + "epoch": 0.88, + "learning_rate": 6.929931417545787e-07, + "loss": 0.4626, + "step": 10372 + }, + { + "epoch": 0.88, + "learning_rate": 6.919833551181399e-07, + "loss": 0.442, + "step": 10373 + }, + { + "epoch": 0.88, + "learning_rate": 6.909742783499129e-07, + "loss": 0.4644, + "step": 10374 + }, + { + "epoch": 0.88, + "learning_rate": 6.899659115268498e-07, + "loss": 0.4635, + "step": 10375 + }, + { + "epoch": 0.88, + "learning_rate": 6.889582547258545e-07, + "loss": 0.4532, + "step": 10376 + }, + { + "epoch": 0.88, + "learning_rate": 6.879513080237754e-07, + "loss": 0.4746, + "step": 10377 + }, + { + "epoch": 0.88, + "learning_rate": 6.869450714974058e-07, + "loss": 0.4474, + "step": 10378 + }, + { + "epoch": 0.88, + "learning_rate": 6.859395452234863e-07, + "loss": 0.4501, + "step": 10379 + }, + { + "epoch": 0.89, + "learning_rate": 6.849347292787012e-07, + "loss": 0.4744, + "step": 10380 + }, + { + "epoch": 0.89, + "learning_rate": 6.839306237396859e-07, + "loss": 0.4645, + "step": 10381 + }, + { + "epoch": 0.89, + "learning_rate": 6.829272286830102e-07, + "loss": 0.4603, + "step": 10382 + }, + { + "epoch": 0.89, + "learning_rate": 6.819245441852051e-07, + "loss": 0.4461, + "step": 10383 + }, + { + "epoch": 0.89, + "learning_rate": 6.809225703227352e-07, + "loss": 0.4318, + "step": 10384 + }, + { + "epoch": 0.89, + "learning_rate": 6.799213071720156e-07, + "loss": 0.447, + "step": 10385 + }, + { + "epoch": 0.89, + "learning_rate": 6.789207548094068e-07, + "loss": 0.4407, + "step": 10386 + }, + { + "epoch": 0.89, + "learning_rate": 6.779209133112164e-07, + "loss": 0.4659, + "step": 10387 + }, + { + "epoch": 0.89, + "learning_rate": 6.769217827536956e-07, + "loss": 0.4589, + "step": 10388 + }, + { + "epoch": 0.89, + "learning_rate": 6.759233632130413e-07, + "loss": 0.4557, + "step": 10389 + }, + { + "epoch": 0.89, + "learning_rate": 6.749256547654004e-07, + "loss": 0.4446, + "step": 10390 + }, + { + "epoch": 0.89, + "learning_rate": 6.739286574868575e-07, + "loss": 0.464, + "step": 10391 + }, + { + "epoch": 0.89, + "learning_rate": 6.72932371453453e-07, + "loss": 0.4395, + "step": 10392 + }, + { + "epoch": 0.89, + "learning_rate": 6.719367967411638e-07, + "loss": 0.4454, + "step": 10393 + }, + { + "epoch": 0.89, + "learning_rate": 6.70941933425917e-07, + "loss": 0.4568, + "step": 10394 + }, + { + "epoch": 0.89, + "learning_rate": 6.699477815835875e-07, + "loss": 0.4543, + "step": 10395 + }, + { + "epoch": 0.89, + "learning_rate": 6.689543412899913e-07, + "loss": 0.4547, + "step": 10396 + }, + { + "epoch": 0.89, + "learning_rate": 6.679616126208921e-07, + "loss": 0.4629, + "step": 10397 + }, + { + "epoch": 0.89, + "learning_rate": 6.669695956520017e-07, + "loss": 0.4627, + "step": 10398 + }, + { + "epoch": 0.89, + "learning_rate": 6.659782904589752e-07, + "loss": 0.4567, + "step": 10399 + }, + { + "epoch": 0.89, + "learning_rate": 6.649876971174118e-07, + "loss": 0.4556, + "step": 10400 + }, + { + "epoch": 0.89, + "learning_rate": 6.639978157028581e-07, + "loss": 0.4783, + "step": 10401 + }, + { + "epoch": 0.89, + "learning_rate": 6.630086462908081e-07, + "loss": 0.4499, + "step": 10402 + }, + { + "epoch": 0.89, + "learning_rate": 6.620201889566991e-07, + "loss": 0.4424, + "step": 10403 + }, + { + "epoch": 0.89, + "learning_rate": 6.610324437759153e-07, + "loss": 0.4446, + "step": 10404 + }, + { + "epoch": 0.89, + "learning_rate": 6.600454108237875e-07, + "loss": 0.4431, + "step": 10405 + }, + { + "epoch": 0.89, + "learning_rate": 6.590590901755889e-07, + "loss": 0.4559, + "step": 10406 + }, + { + "epoch": 0.89, + "learning_rate": 6.580734819065415e-07, + "loss": 0.4516, + "step": 10407 + }, + { + "epoch": 0.89, + "learning_rate": 6.57088586091813e-07, + "loss": 0.4536, + "step": 10408 + }, + { + "epoch": 0.89, + "learning_rate": 6.561044028065134e-07, + "loss": 0.4696, + "step": 10409 + }, + { + "epoch": 0.89, + "learning_rate": 6.551209321257013e-07, + "loss": 0.4421, + "step": 10410 + }, + { + "epoch": 0.89, + "learning_rate": 6.541381741243802e-07, + "loss": 0.4728, + "step": 10411 + }, + { + "epoch": 0.89, + "learning_rate": 6.531561288775001e-07, + "loss": 0.4338, + "step": 10412 + }, + { + "epoch": 0.89, + "learning_rate": 6.521747964599556e-07, + "loss": 0.4656, + "step": 10413 + }, + { + "epoch": 0.89, + "learning_rate": 6.51194176946588e-07, + "loss": 0.4815, + "step": 10414 + }, + { + "epoch": 0.89, + "learning_rate": 6.502142704121816e-07, + "loss": 0.4442, + "step": 10415 + }, + { + "epoch": 0.89, + "learning_rate": 6.492350769314693e-07, + "loss": 0.4304, + "step": 10416 + }, + { + "epoch": 0.89, + "learning_rate": 6.482565965791299e-07, + "loss": 0.4654, + "step": 10417 + }, + { + "epoch": 0.89, + "learning_rate": 6.472788294297827e-07, + "loss": 0.4649, + "step": 10418 + }, + { + "epoch": 0.89, + "learning_rate": 6.463017755579992e-07, + "loss": 0.4442, + "step": 10419 + }, + { + "epoch": 0.89, + "learning_rate": 6.453254350382921e-07, + "loss": 0.4444, + "step": 10420 + }, + { + "epoch": 0.89, + "learning_rate": 6.443498079451215e-07, + "loss": 0.4391, + "step": 10421 + }, + { + "epoch": 0.89, + "learning_rate": 6.43374894352895e-07, + "loss": 0.4546, + "step": 10422 + }, + { + "epoch": 0.89, + "learning_rate": 6.424006943359606e-07, + "loss": 0.4642, + "step": 10423 + }, + { + "epoch": 0.89, + "learning_rate": 6.414272079686157e-07, + "loss": 0.441, + "step": 10424 + }, + { + "epoch": 0.89, + "learning_rate": 6.404544353251041e-07, + "loss": 0.4428, + "step": 10425 + }, + { + "epoch": 0.89, + "learning_rate": 6.394823764796121e-07, + "loss": 0.4459, + "step": 10426 + }, + { + "epoch": 0.89, + "learning_rate": 6.385110315062725e-07, + "loss": 0.4438, + "step": 10427 + }, + { + "epoch": 0.89, + "learning_rate": 6.37540400479163e-07, + "loss": 0.4472, + "step": 10428 + }, + { + "epoch": 0.89, + "learning_rate": 6.36570483472313e-07, + "loss": 0.4709, + "step": 10429 + }, + { + "epoch": 0.89, + "learning_rate": 6.356012805596867e-07, + "loss": 0.459, + "step": 10430 + }, + { + "epoch": 0.89, + "learning_rate": 6.346327918152029e-07, + "loss": 0.453, + "step": 10431 + }, + { + "epoch": 0.89, + "learning_rate": 6.336650173127224e-07, + "loss": 0.4512, + "step": 10432 + }, + { + "epoch": 0.89, + "learning_rate": 6.326979571260483e-07, + "loss": 0.4729, + "step": 10433 + }, + { + "epoch": 0.89, + "learning_rate": 6.317316113289373e-07, + "loss": 0.4487, + "step": 10434 + }, + { + "epoch": 0.89, + "learning_rate": 6.30765979995086e-07, + "loss": 0.4295, + "step": 10435 + }, + { + "epoch": 0.89, + "learning_rate": 6.298010631981344e-07, + "loss": 0.4817, + "step": 10436 + }, + { + "epoch": 0.89, + "learning_rate": 6.288368610116724e-07, + "loss": 0.4512, + "step": 10437 + }, + { + "epoch": 0.89, + "learning_rate": 6.278733735092379e-07, + "loss": 0.4655, + "step": 10438 + }, + { + "epoch": 0.89, + "learning_rate": 6.269106007643056e-07, + "loss": 0.4545, + "step": 10439 + }, + { + "epoch": 0.89, + "learning_rate": 6.259485428503021e-07, + "loss": 0.4409, + "step": 10440 + }, + { + "epoch": 0.89, + "learning_rate": 6.249871998405998e-07, + "loss": 0.4529, + "step": 10441 + }, + { + "epoch": 0.89, + "learning_rate": 6.240265718085103e-07, + "loss": 0.4389, + "step": 10442 + }, + { + "epoch": 0.89, + "learning_rate": 6.230666588272993e-07, + "loss": 0.4616, + "step": 10443 + }, + { + "epoch": 0.89, + "learning_rate": 6.221074609701739e-07, + "loss": 0.4284, + "step": 10444 + }, + { + "epoch": 0.89, + "learning_rate": 6.211489783102831e-07, + "loss": 0.4473, + "step": 10445 + }, + { + "epoch": 0.89, + "learning_rate": 6.201912109207264e-07, + "loss": 0.4545, + "step": 10446 + }, + { + "epoch": 0.89, + "learning_rate": 6.192341588745498e-07, + "loss": 0.4512, + "step": 10447 + }, + { + "epoch": 0.89, + "learning_rate": 6.182778222447383e-07, + "loss": 0.4591, + "step": 10448 + }, + { + "epoch": 0.89, + "learning_rate": 6.173222011042279e-07, + "loss": 0.439, + "step": 10449 + }, + { + "epoch": 0.89, + "learning_rate": 6.163672955258982e-07, + "loss": 0.4696, + "step": 10450 + }, + { + "epoch": 0.89, + "learning_rate": 6.154131055825729e-07, + "loss": 0.4419, + "step": 10451 + }, + { + "epoch": 0.89, + "learning_rate": 6.144596313470241e-07, + "loss": 0.4718, + "step": 10452 + }, + { + "epoch": 0.89, + "learning_rate": 6.135068728919691e-07, + "loss": 0.4579, + "step": 10453 + }, + { + "epoch": 0.89, + "learning_rate": 6.125548302900653e-07, + "loss": 0.4768, + "step": 10454 + }, + { + "epoch": 0.89, + "learning_rate": 6.116035036139223e-07, + "loss": 0.4537, + "step": 10455 + }, + { + "epoch": 0.89, + "learning_rate": 6.106528929360911e-07, + "loss": 0.4519, + "step": 10456 + }, + { + "epoch": 0.89, + "learning_rate": 6.097029983290692e-07, + "loss": 0.4568, + "step": 10457 + }, + { + "epoch": 0.89, + "learning_rate": 6.087538198653009e-07, + "loss": 0.4504, + "step": 10458 + }, + { + "epoch": 0.89, + "learning_rate": 6.078053576171738e-07, + "loss": 0.4474, + "step": 10459 + }, + { + "epoch": 0.89, + "learning_rate": 6.06857611657019e-07, + "loss": 0.4472, + "step": 10460 + }, + { + "epoch": 0.89, + "learning_rate": 6.059105820571198e-07, + "loss": 0.4566, + "step": 10461 + }, + { + "epoch": 0.89, + "learning_rate": 6.049642688897007e-07, + "loss": 0.4761, + "step": 10462 + }, + { + "epoch": 0.89, + "learning_rate": 6.04018672226927e-07, + "loss": 0.456, + "step": 10463 + }, + { + "epoch": 0.89, + "learning_rate": 6.030737921409169e-07, + "loss": 0.4552, + "step": 10464 + }, + { + "epoch": 0.89, + "learning_rate": 6.021296287037304e-07, + "loss": 0.466, + "step": 10465 + }, + { + "epoch": 0.89, + "learning_rate": 6.011861819873732e-07, + "loss": 0.4564, + "step": 10466 + }, + { + "epoch": 0.89, + "learning_rate": 6.002434520637968e-07, + "loss": 0.4571, + "step": 10467 + }, + { + "epoch": 0.89, + "learning_rate": 5.99301439004899e-07, + "loss": 0.4487, + "step": 10468 + }, + { + "epoch": 0.89, + "learning_rate": 5.98360142882517e-07, + "loss": 0.4603, + "step": 10469 + }, + { + "epoch": 0.89, + "learning_rate": 5.974195637684422e-07, + "loss": 0.4677, + "step": 10470 + }, + { + "epoch": 0.89, + "learning_rate": 5.964797017344081e-07, + "loss": 0.4658, + "step": 10471 + }, + { + "epoch": 0.89, + "learning_rate": 5.955405568520889e-07, + "loss": 0.4387, + "step": 10472 + }, + { + "epoch": 0.89, + "learning_rate": 5.946021291931092e-07, + "loss": 0.4626, + "step": 10473 + }, + { + "epoch": 0.89, + "learning_rate": 5.936644188290386e-07, + "loss": 0.4465, + "step": 10474 + }, + { + "epoch": 0.89, + "learning_rate": 5.927274258313887e-07, + "loss": 0.4414, + "step": 10475 + }, + { + "epoch": 0.89, + "learning_rate": 5.91791150271619e-07, + "loss": 0.4511, + "step": 10476 + }, + { + "epoch": 0.89, + "learning_rate": 5.908555922211368e-07, + "loss": 0.4489, + "step": 10477 + }, + { + "epoch": 0.89, + "learning_rate": 5.899207517512873e-07, + "loss": 0.4597, + "step": 10478 + }, + { + "epoch": 0.89, + "learning_rate": 5.889866289333645e-07, + "loss": 0.4619, + "step": 10479 + }, + { + "epoch": 0.89, + "learning_rate": 5.880532238386161e-07, + "loss": 0.4463, + "step": 10480 + }, + { + "epoch": 0.89, + "learning_rate": 5.871205365382194e-07, + "loss": 0.4548, + "step": 10481 + }, + { + "epoch": 0.89, + "learning_rate": 5.861885671033097e-07, + "loss": 0.4476, + "step": 10482 + }, + { + "epoch": 0.89, + "learning_rate": 5.852573156049601e-07, + "loss": 0.4371, + "step": 10483 + }, + { + "epoch": 0.89, + "learning_rate": 5.84326782114194e-07, + "loss": 0.4544, + "step": 10484 + }, + { + "epoch": 0.89, + "learning_rate": 5.833969667019757e-07, + "loss": 0.4552, + "step": 10485 + }, + { + "epoch": 0.89, + "learning_rate": 5.824678694392194e-07, + "loss": 0.435, + "step": 10486 + }, + { + "epoch": 0.89, + "learning_rate": 5.815394903967797e-07, + "loss": 0.4524, + "step": 10487 + }, + { + "epoch": 0.89, + "learning_rate": 5.806118296454577e-07, + "loss": 0.4517, + "step": 10488 + }, + { + "epoch": 0.89, + "learning_rate": 5.796848872560045e-07, + "loss": 0.4508, + "step": 10489 + }, + { + "epoch": 0.89, + "learning_rate": 5.787586632991105e-07, + "loss": 0.4388, + "step": 10490 + }, + { + "epoch": 0.89, + "learning_rate": 5.778331578454121e-07, + "loss": 0.4773, + "step": 10491 + }, + { + "epoch": 0.89, + "learning_rate": 5.769083709654933e-07, + "loss": 0.4475, + "step": 10492 + }, + { + "epoch": 0.89, + "learning_rate": 5.759843027298828e-07, + "loss": 0.4611, + "step": 10493 + }, + { + "epoch": 0.89, + "learning_rate": 5.750609532090534e-07, + "loss": 0.4577, + "step": 10494 + }, + { + "epoch": 0.89, + "learning_rate": 5.741383224734254e-07, + "loss": 0.4496, + "step": 10495 + }, + { + "epoch": 0.89, + "learning_rate": 5.732164105933591e-07, + "loss": 0.4445, + "step": 10496 + }, + { + "epoch": 0.9, + "learning_rate": 5.722952176391639e-07, + "loss": 0.4429, + "step": 10497 + }, + { + "epoch": 0.9, + "learning_rate": 5.713747436810968e-07, + "loss": 0.4609, + "step": 10498 + }, + { + "epoch": 0.9, + "learning_rate": 5.70454988789354e-07, + "loss": 0.4463, + "step": 10499 + }, + { + "epoch": 0.9, + "learning_rate": 5.695359530340816e-07, + "loss": 0.4858, + "step": 10500 + }, + { + "epoch": 0.9, + "learning_rate": 5.68617636485368e-07, + "loss": 0.468, + "step": 10501 + }, + { + "epoch": 0.9, + "learning_rate": 5.677000392132481e-07, + "loss": 0.4637, + "step": 10502 + }, + { + "epoch": 0.9, + "learning_rate": 5.667831612877018e-07, + "loss": 0.4538, + "step": 10503 + }, + { + "epoch": 0.9, + "learning_rate": 5.658670027786561e-07, + "loss": 0.4407, + "step": 10504 + }, + { + "epoch": 0.9, + "learning_rate": 5.649515637559766e-07, + "loss": 0.467, + "step": 10505 + }, + { + "epoch": 0.9, + "learning_rate": 5.640368442894806e-07, + "loss": 0.4507, + "step": 10506 + }, + { + "epoch": 0.9, + "learning_rate": 5.631228444489312e-07, + "loss": 0.4645, + "step": 10507 + }, + { + "epoch": 0.9, + "learning_rate": 5.622095643040304e-07, + "loss": 0.4494, + "step": 10508 + }, + { + "epoch": 0.9, + "learning_rate": 5.612970039244292e-07, + "loss": 0.4516, + "step": 10509 + }, + { + "epoch": 0.9, + "learning_rate": 5.603851633797242e-07, + "loss": 0.4709, + "step": 10510 + }, + { + "epoch": 0.9, + "learning_rate": 5.594740427394562e-07, + "loss": 0.4396, + "step": 10511 + }, + { + "epoch": 0.9, + "learning_rate": 5.5856364207311e-07, + "loss": 0.4814, + "step": 10512 + }, + { + "epoch": 0.9, + "learning_rate": 5.576539614501197e-07, + "loss": 0.4567, + "step": 10513 + }, + { + "epoch": 0.9, + "learning_rate": 5.567450009398567e-07, + "loss": 0.4524, + "step": 10514 + }, + { + "epoch": 0.9, + "learning_rate": 5.558367606116433e-07, + "loss": 0.4323, + "step": 10515 + }, + { + "epoch": 0.9, + "learning_rate": 5.549292405347495e-07, + "loss": 0.4515, + "step": 10516 + }, + { + "epoch": 0.9, + "learning_rate": 5.540224407783823e-07, + "loss": 0.4616, + "step": 10517 + }, + { + "epoch": 0.9, + "learning_rate": 5.531163614116986e-07, + "loss": 0.4447, + "step": 10518 + }, + { + "epoch": 0.9, + "learning_rate": 5.522110025038019e-07, + "loss": 0.4713, + "step": 10519 + }, + { + "epoch": 0.9, + "learning_rate": 5.51306364123737e-07, + "loss": 0.4669, + "step": 10520 + }, + { + "epoch": 0.9, + "learning_rate": 5.504024463404967e-07, + "loss": 0.4422, + "step": 10521 + }, + { + "epoch": 0.9, + "learning_rate": 5.494992492230167e-07, + "loss": 0.4644, + "step": 10522 + }, + { + "epoch": 0.9, + "learning_rate": 5.485967728401786e-07, + "loss": 0.4608, + "step": 10523 + }, + { + "epoch": 0.9, + "learning_rate": 5.476950172608064e-07, + "loss": 0.4437, + "step": 10524 + }, + { + "epoch": 0.9, + "learning_rate": 5.467939825536783e-07, + "loss": 0.4377, + "step": 10525 + }, + { + "epoch": 0.9, + "learning_rate": 5.458936687875049e-07, + "loss": 0.4637, + "step": 10526 + }, + { + "epoch": 0.9, + "learning_rate": 5.449940760309502e-07, + "loss": 0.4928, + "step": 10527 + }, + { + "epoch": 0.9, + "learning_rate": 5.440952043526215e-07, + "loss": 0.4462, + "step": 10528 + }, + { + "epoch": 0.9, + "learning_rate": 5.431970538210685e-07, + "loss": 0.4474, + "step": 10529 + }, + { + "epoch": 0.9, + "learning_rate": 5.422996245047896e-07, + "loss": 0.4696, + "step": 10530 + }, + { + "epoch": 0.9, + "learning_rate": 5.414029164722279e-07, + "loss": 0.4761, + "step": 10531 + }, + { + "epoch": 0.9, + "learning_rate": 5.405069297917665e-07, + "loss": 0.4319, + "step": 10532 + }, + { + "epoch": 0.9, + "learning_rate": 5.396116645317384e-07, + "loss": 0.4523, + "step": 10533 + }, + { + "epoch": 0.9, + "learning_rate": 5.387171207604214e-07, + "loss": 0.4515, + "step": 10534 + }, + { + "epoch": 0.9, + "learning_rate": 5.378232985460363e-07, + "loss": 0.4462, + "step": 10535 + }, + { + "epoch": 0.9, + "learning_rate": 5.369301979567498e-07, + "loss": 0.4707, + "step": 10536 + }, + { + "epoch": 0.9, + "learning_rate": 5.36037819060673e-07, + "loss": 0.4835, + "step": 10537 + }, + { + "epoch": 0.9, + "learning_rate": 5.351461619258636e-07, + "loss": 0.4314, + "step": 10538 + }, + { + "epoch": 0.9, + "learning_rate": 5.342552266203227e-07, + "loss": 0.4716, + "step": 10539 + }, + { + "epoch": 0.9, + "learning_rate": 5.333650132119972e-07, + "loss": 0.4538, + "step": 10540 + }, + { + "epoch": 0.9, + "learning_rate": 5.32475521768776e-07, + "loss": 0.4565, + "step": 10541 + }, + { + "epoch": 0.9, + "learning_rate": 5.315867523584984e-07, + "loss": 0.4698, + "step": 10542 + }, + { + "epoch": 0.9, + "learning_rate": 5.306987050489442e-07, + "loss": 0.4589, + "step": 10543 + }, + { + "epoch": 0.9, + "learning_rate": 5.298113799078397e-07, + "loss": 0.4593, + "step": 10544 + }, + { + "epoch": 0.9, + "learning_rate": 5.28924777002856e-07, + "loss": 0.446, + "step": 10545 + }, + { + "epoch": 0.9, + "learning_rate": 5.280388964016093e-07, + "loss": 0.462, + "step": 10546 + }, + { + "epoch": 0.9, + "learning_rate": 5.271537381716607e-07, + "loss": 0.4715, + "step": 10547 + }, + { + "epoch": 0.9, + "learning_rate": 5.262693023805165e-07, + "loss": 0.4589, + "step": 10548 + }, + { + "epoch": 0.9, + "learning_rate": 5.253855890956272e-07, + "loss": 0.4726, + "step": 10549 + }, + { + "epoch": 0.9, + "learning_rate": 5.245025983843888e-07, + "loss": 0.4489, + "step": 10550 + }, + { + "epoch": 0.9, + "learning_rate": 5.236203303141396e-07, + "loss": 0.4665, + "step": 10551 + }, + { + "epoch": 0.9, + "learning_rate": 5.22738784952167e-07, + "loss": 0.4429, + "step": 10552 + }, + { + "epoch": 0.9, + "learning_rate": 5.218579623657016e-07, + "loss": 0.4751, + "step": 10553 + }, + { + "epoch": 0.9, + "learning_rate": 5.209778626219176e-07, + "loss": 0.4545, + "step": 10554 + }, + { + "epoch": 0.9, + "learning_rate": 5.200984857879355e-07, + "loss": 0.4494, + "step": 10555 + }, + { + "epoch": 0.9, + "learning_rate": 5.192198319308206e-07, + "loss": 0.4377, + "step": 10556 + }, + { + "epoch": 0.9, + "learning_rate": 5.183419011175817e-07, + "loss": 0.4402, + "step": 10557 + }, + { + "epoch": 0.9, + "learning_rate": 5.174646934151751e-07, + "loss": 0.4455, + "step": 10558 + }, + { + "epoch": 0.9, + "learning_rate": 5.165882088905005e-07, + "loss": 0.4509, + "step": 10559 + }, + { + "epoch": 0.9, + "learning_rate": 5.157124476103992e-07, + "loss": 0.4483, + "step": 10560 + }, + { + "epoch": 0.9, + "learning_rate": 5.14837409641663e-07, + "loss": 0.4432, + "step": 10561 + }, + { + "epoch": 0.9, + "learning_rate": 5.139630950510243e-07, + "loss": 0.453, + "step": 10562 + }, + { + "epoch": 0.9, + "learning_rate": 5.130895039051642e-07, + "loss": 0.4524, + "step": 10563 + }, + { + "epoch": 0.9, + "learning_rate": 5.122166362707048e-07, + "loss": 0.4533, + "step": 10564 + }, + { + "epoch": 0.9, + "learning_rate": 5.113444922142163e-07, + "loss": 0.4558, + "step": 10565 + }, + { + "epoch": 0.9, + "learning_rate": 5.104730718022077e-07, + "loss": 0.4676, + "step": 10566 + }, + { + "epoch": 0.9, + "learning_rate": 5.096023751011414e-07, + "loss": 0.4567, + "step": 10567 + }, + { + "epoch": 0.9, + "learning_rate": 5.087324021774209e-07, + "loss": 0.4788, + "step": 10568 + }, + { + "epoch": 0.9, + "learning_rate": 5.078631530973921e-07, + "loss": 0.4502, + "step": 10569 + }, + { + "epoch": 0.9, + "learning_rate": 5.069946279273464e-07, + "loss": 0.4363, + "step": 10570 + }, + { + "epoch": 0.9, + "learning_rate": 5.061268267335228e-07, + "loss": 0.4472, + "step": 10571 + }, + { + "epoch": 0.9, + "learning_rate": 5.052597495821032e-07, + "loss": 0.463, + "step": 10572 + }, + { + "epoch": 0.9, + "learning_rate": 5.043933965392134e-07, + "loss": 0.4596, + "step": 10573 + }, + { + "epoch": 0.9, + "learning_rate": 5.035277676709294e-07, + "loss": 0.4552, + "step": 10574 + }, + { + "epoch": 0.9, + "learning_rate": 5.026628630432607e-07, + "loss": 0.4732, + "step": 10575 + }, + { + "epoch": 0.9, + "learning_rate": 5.017986827221733e-07, + "loss": 0.493, + "step": 10576 + }, + { + "epoch": 0.9, + "learning_rate": 5.009352267735734e-07, + "loss": 0.4377, + "step": 10577 + }, + { + "epoch": 0.9, + "learning_rate": 5.000724952633096e-07, + "loss": 0.4587, + "step": 10578 + }, + { + "epoch": 0.9, + "learning_rate": 4.99210488257178e-07, + "loss": 0.4616, + "step": 10579 + }, + { + "epoch": 0.9, + "learning_rate": 4.983492058209194e-07, + "loss": 0.4479, + "step": 10580 + }, + { + "epoch": 0.9, + "learning_rate": 4.97488648020219e-07, + "loss": 0.4772, + "step": 10581 + }, + { + "epoch": 0.9, + "learning_rate": 4.966288149207055e-07, + "loss": 0.4649, + "step": 10582 + }, + { + "epoch": 0.9, + "learning_rate": 4.957697065879563e-07, + "loss": 0.4436, + "step": 10583 + }, + { + "epoch": 0.9, + "learning_rate": 4.949113230874846e-07, + "loss": 0.4639, + "step": 10584 + }, + { + "epoch": 0.9, + "learning_rate": 4.940536644847593e-07, + "loss": 0.4348, + "step": 10585 + }, + { + "epoch": 0.9, + "learning_rate": 4.931967308451891e-07, + "loss": 0.4544, + "step": 10586 + }, + { + "epoch": 0.9, + "learning_rate": 4.923405222341248e-07, + "loss": 0.4567, + "step": 10587 + }, + { + "epoch": 0.9, + "learning_rate": 4.914850387168657e-07, + "loss": 0.4472, + "step": 10588 + }, + { + "epoch": 0.9, + "learning_rate": 4.906302803586538e-07, + "loss": 0.4429, + "step": 10589 + }, + { + "epoch": 0.9, + "learning_rate": 4.897762472246781e-07, + "loss": 0.4335, + "step": 10590 + }, + { + "epoch": 0.9, + "learning_rate": 4.889229393800687e-07, + "loss": 0.4474, + "step": 10591 + }, + { + "epoch": 0.9, + "learning_rate": 4.880703568899047e-07, + "loss": 0.473, + "step": 10592 + }, + { + "epoch": 0.9, + "learning_rate": 4.872184998192053e-07, + "loss": 0.4456, + "step": 10593 + }, + { + "epoch": 0.9, + "learning_rate": 4.863673682329373e-07, + "loss": 0.4505, + "step": 10594 + }, + { + "epoch": 0.9, + "learning_rate": 4.855169621960143e-07, + "loss": 0.4486, + "step": 10595 + }, + { + "epoch": 0.9, + "learning_rate": 4.846672817732889e-07, + "loss": 0.4655, + "step": 10596 + }, + { + "epoch": 0.9, + "learning_rate": 4.838183270295604e-07, + "loss": 0.4487, + "step": 10597 + }, + { + "epoch": 0.9, + "learning_rate": 4.82970098029576e-07, + "loss": 0.4375, + "step": 10598 + }, + { + "epoch": 0.9, + "learning_rate": 4.821225948380237e-07, + "loss": 0.4485, + "step": 10599 + }, + { + "epoch": 0.9, + "learning_rate": 4.812758175195397e-07, + "loss": 0.4247, + "step": 10600 + }, + { + "epoch": 0.9, + "learning_rate": 4.804297661387014e-07, + "loss": 0.4539, + "step": 10601 + }, + { + "epoch": 0.9, + "learning_rate": 4.795844407600292e-07, + "loss": 0.4486, + "step": 10602 + }, + { + "epoch": 0.9, + "learning_rate": 4.78739841447996e-07, + "loss": 0.4438, + "step": 10603 + }, + { + "epoch": 0.9, + "learning_rate": 4.778959682670147e-07, + "loss": 0.4709, + "step": 10604 + }, + { + "epoch": 0.9, + "learning_rate": 4.770528212814385e-07, + "loss": 0.4342, + "step": 10605 + }, + { + "epoch": 0.9, + "learning_rate": 4.762104005555701e-07, + "loss": 0.4571, + "step": 10606 + }, + { + "epoch": 0.9, + "learning_rate": 4.7536870615365825e-07, + "loss": 0.4553, + "step": 10607 + }, + { + "epoch": 0.9, + "learning_rate": 4.7452773813989385e-07, + "loss": 0.4431, + "step": 10608 + }, + { + "epoch": 0.9, + "learning_rate": 4.7368749657840997e-07, + "loss": 0.4532, + "step": 10609 + }, + { + "epoch": 0.9, + "learning_rate": 4.728479815332909e-07, + "loss": 0.431, + "step": 10610 + }, + { + "epoch": 0.9, + "learning_rate": 4.7200919306855883e-07, + "loss": 0.4619, + "step": 10611 + }, + { + "epoch": 0.9, + "learning_rate": 4.711711312481815e-07, + "loss": 0.4673, + "step": 10612 + }, + { + "epoch": 0.9, + "learning_rate": 4.7033379613607876e-07, + "loss": 0.4507, + "step": 10613 + }, + { + "epoch": 0.91, + "learning_rate": 4.694971877961041e-07, + "loss": 0.4574, + "step": 10614 + }, + { + "epoch": 0.91, + "learning_rate": 4.68661306292062e-07, + "loss": 0.4703, + "step": 10615 + }, + { + "epoch": 0.91, + "learning_rate": 4.678261516877014e-07, + "loss": 0.4597, + "step": 10616 + }, + { + "epoch": 0.91, + "learning_rate": 4.669917240467148e-07, + "loss": 0.4583, + "step": 10617 + }, + { + "epoch": 0.91, + "learning_rate": 4.6615802343273787e-07, + "loss": 0.4646, + "step": 10618 + }, + { + "epoch": 0.91, + "learning_rate": 4.6532504990935423e-07, + "loss": 0.4227, + "step": 10619 + }, + { + "epoch": 0.91, + "learning_rate": 4.644928035400864e-07, + "loss": 0.4671, + "step": 10620 + }, + { + "epoch": 0.91, + "learning_rate": 4.6366128438840586e-07, + "loss": 0.4649, + "step": 10621 + }, + { + "epoch": 0.91, + "learning_rate": 4.628304925177318e-07, + "loss": 0.4622, + "step": 10622 + }, + { + "epoch": 0.91, + "learning_rate": 4.620004279914192e-07, + "loss": 0.423, + "step": 10623 + }, + { + "epoch": 0.91, + "learning_rate": 4.61171090872774e-07, + "loss": 0.4753, + "step": 10624 + }, + { + "epoch": 0.91, + "learning_rate": 4.6034248122504454e-07, + "loss": 0.4429, + "step": 10625 + }, + { + "epoch": 0.91, + "learning_rate": 4.595145991114247e-07, + "loss": 0.44, + "step": 10626 + }, + { + "epoch": 0.91, + "learning_rate": 4.5868744459505174e-07, + "loss": 0.4565, + "step": 10627 + }, + { + "epoch": 0.91, + "learning_rate": 4.578610177390086e-07, + "loss": 0.4567, + "step": 10628 + }, + { + "epoch": 0.91, + "learning_rate": 4.5703531860632146e-07, + "loss": 0.4397, + "step": 10629 + }, + { + "epoch": 0.91, + "learning_rate": 4.5621034725995994e-07, + "loss": 0.4619, + "step": 10630 + }, + { + "epoch": 0.91, + "learning_rate": 4.5538610376284375e-07, + "loss": 0.4436, + "step": 10631 + }, + { + "epoch": 0.91, + "learning_rate": 4.5456258817782925e-07, + "loss": 0.4591, + "step": 10632 + }, + { + "epoch": 0.91, + "learning_rate": 4.5373980056772405e-07, + "loss": 0.4296, + "step": 10633 + }, + { + "epoch": 0.91, + "learning_rate": 4.5291774099527453e-07, + "loss": 0.4542, + "step": 10634 + }, + { + "epoch": 0.91, + "learning_rate": 4.5209640952317723e-07, + "loss": 0.4529, + "step": 10635 + }, + { + "epoch": 0.91, + "learning_rate": 4.5127580621406877e-07, + "loss": 0.442, + "step": 10636 + }, + { + "epoch": 0.91, + "learning_rate": 4.504559311305323e-07, + "loss": 0.4564, + "step": 10637 + }, + { + "epoch": 0.91, + "learning_rate": 4.4963678433509463e-07, + "loss": 0.4336, + "step": 10638 + }, + { + "epoch": 0.91, + "learning_rate": 4.4881836589022566e-07, + "loss": 0.4216, + "step": 10639 + }, + { + "epoch": 0.91, + "learning_rate": 4.480006758583455e-07, + "loss": 0.451, + "step": 10640 + }, + { + "epoch": 0.91, + "learning_rate": 4.4718371430181095e-07, + "loss": 0.4667, + "step": 10641 + }, + { + "epoch": 0.91, + "learning_rate": 4.463674812829277e-07, + "loss": 0.4268, + "step": 10642 + }, + { + "epoch": 0.91, + "learning_rate": 4.455519768639471e-07, + "loss": 0.4817, + "step": 10643 + }, + { + "epoch": 0.91, + "learning_rate": 4.447372011070594e-07, + "loss": 0.4537, + "step": 10644 + }, + { + "epoch": 0.91, + "learning_rate": 4.43923154074406e-07, + "loss": 0.446, + "step": 10645 + }, + { + "epoch": 0.91, + "learning_rate": 4.4310983582806945e-07, + "loss": 0.4564, + "step": 10646 + }, + { + "epoch": 0.91, + "learning_rate": 4.4229724643007346e-07, + "loss": 0.4677, + "step": 10647 + }, + { + "epoch": 0.91, + "learning_rate": 4.4148538594239176e-07, + "loss": 0.4446, + "step": 10648 + }, + { + "epoch": 0.91, + "learning_rate": 4.4067425442694157e-07, + "loss": 0.4459, + "step": 10649 + }, + { + "epoch": 0.91, + "learning_rate": 4.398638519455811e-07, + "loss": 0.4697, + "step": 10650 + }, + { + "epoch": 0.91, + "learning_rate": 4.3905417856011543e-07, + "loss": 0.4594, + "step": 10651 + }, + { + "epoch": 0.91, + "learning_rate": 4.382452343322952e-07, + "loss": 0.4446, + "step": 10652 + }, + { + "epoch": 0.91, + "learning_rate": 4.3743701932380975e-07, + "loss": 0.4451, + "step": 10653 + }, + { + "epoch": 0.91, + "learning_rate": 4.366295335963011e-07, + "loss": 0.4482, + "step": 10654 + }, + { + "epoch": 0.91, + "learning_rate": 4.3582277721135104e-07, + "loss": 0.434, + "step": 10655 + }, + { + "epoch": 0.91, + "learning_rate": 4.350167502304847e-07, + "loss": 0.4512, + "step": 10656 + }, + { + "epoch": 0.91, + "learning_rate": 4.3421145271517193e-07, + "loss": 0.4759, + "step": 10657 + }, + { + "epoch": 0.91, + "learning_rate": 4.3340688472683245e-07, + "loss": 0.4336, + "step": 10658 + }, + { + "epoch": 0.91, + "learning_rate": 4.326030463268216e-07, + "loss": 0.4342, + "step": 10659 + }, + { + "epoch": 0.91, + "learning_rate": 4.317999375764459e-07, + "loss": 0.4388, + "step": 10660 + }, + { + "epoch": 0.91, + "learning_rate": 4.30997558536953e-07, + "loss": 0.444, + "step": 10661 + }, + { + "epoch": 0.91, + "learning_rate": 4.3019590926953405e-07, + "loss": 0.4589, + "step": 10662 + }, + { + "epoch": 0.91, + "learning_rate": 4.293949898353289e-07, + "loss": 0.4506, + "step": 10663 + }, + { + "epoch": 0.91, + "learning_rate": 4.285948002954199e-07, + "loss": 0.4598, + "step": 10664 + }, + { + "epoch": 0.91, + "learning_rate": 4.277953407108282e-07, + "loss": 0.4541, + "step": 10665 + }, + { + "epoch": 0.91, + "learning_rate": 4.269966111425272e-07, + "loss": 0.4549, + "step": 10666 + }, + { + "epoch": 0.91, + "learning_rate": 4.261986116514305e-07, + "loss": 0.4685, + "step": 10667 + }, + { + "epoch": 0.91, + "learning_rate": 4.2540134229839714e-07, + "loss": 0.4522, + "step": 10668 + }, + { + "epoch": 0.91, + "learning_rate": 4.246048031442307e-07, + "loss": 0.4596, + "step": 10669 + }, + { + "epoch": 0.91, + "learning_rate": 4.2380899424967814e-07, + "loss": 0.4591, + "step": 10670 + }, + { + "epoch": 0.91, + "learning_rate": 4.2301391567542983e-07, + "loss": 0.4545, + "step": 10671 + }, + { + "epoch": 0.91, + "learning_rate": 4.222195674821239e-07, + "loss": 0.4729, + "step": 10672 + }, + { + "epoch": 0.91, + "learning_rate": 4.2142594973034077e-07, + "loss": 0.4594, + "step": 10673 + }, + { + "epoch": 0.91, + "learning_rate": 4.2063306248060323e-07, + "loss": 0.4515, + "step": 10674 + }, + { + "epoch": 0.91, + "learning_rate": 4.1984090579338054e-07, + "loss": 0.4648, + "step": 10675 + }, + { + "epoch": 0.91, + "learning_rate": 4.1904947972908673e-07, + "loss": 0.4531, + "step": 10676 + }, + { + "epoch": 0.91, + "learning_rate": 4.18258784348079e-07, + "loss": 0.4437, + "step": 10677 + }, + { + "epoch": 0.91, + "learning_rate": 4.17468819710658e-07, + "loss": 0.449, + "step": 10678 + }, + { + "epoch": 0.91, + "learning_rate": 4.1667958587707226e-07, + "loss": 0.451, + "step": 10679 + }, + { + "epoch": 0.91, + "learning_rate": 4.1589108290750915e-07, + "loss": 0.4599, + "step": 10680 + }, + { + "epoch": 0.91, + "learning_rate": 4.15103310862105e-07, + "loss": 0.4504, + "step": 10681 + }, + { + "epoch": 0.91, + "learning_rate": 4.143162698009384e-07, + "loss": 0.4485, + "step": 10682 + }, + { + "epoch": 0.91, + "learning_rate": 4.135299597840325e-07, + "loss": 0.4672, + "step": 10683 + }, + { + "epoch": 0.91, + "learning_rate": 4.1274438087135273e-07, + "loss": 0.4541, + "step": 10684 + }, + { + "epoch": 0.91, + "learning_rate": 4.119595331228132e-07, + "loss": 0.444, + "step": 10685 + }, + { + "epoch": 0.91, + "learning_rate": 4.111754165982673e-07, + "loss": 0.4833, + "step": 10686 + }, + { + "epoch": 0.91, + "learning_rate": 4.1039203135751717e-07, + "loss": 0.445, + "step": 10687 + }, + { + "epoch": 0.91, + "learning_rate": 4.0960937746030607e-07, + "loss": 0.4548, + "step": 10688 + }, + { + "epoch": 0.91, + "learning_rate": 4.0882745496632406e-07, + "loss": 0.4462, + "step": 10689 + }, + { + "epoch": 0.91, + "learning_rate": 4.0804626393519897e-07, + "loss": 0.4486, + "step": 10690 + }, + { + "epoch": 0.91, + "learning_rate": 4.0726580442651433e-07, + "loss": 0.4505, + "step": 10691 + }, + { + "epoch": 0.91, + "learning_rate": 4.064860764997858e-07, + "loss": 0.4446, + "step": 10692 + }, + { + "epoch": 0.91, + "learning_rate": 4.0570708021448134e-07, + "loss": 0.4678, + "step": 10693 + }, + { + "epoch": 0.91, + "learning_rate": 4.049288156300102e-07, + "loss": 0.4449, + "step": 10694 + }, + { + "epoch": 0.91, + "learning_rate": 4.041512828057248e-07, + "loss": 0.4731, + "step": 10695 + }, + { + "epoch": 0.91, + "learning_rate": 4.0337448180092444e-07, + "loss": 0.4717, + "step": 10696 + }, + { + "epoch": 0.91, + "learning_rate": 4.0259841267485167e-07, + "loss": 0.4508, + "step": 10697 + }, + { + "epoch": 0.91, + "learning_rate": 4.0182307548669255e-07, + "loss": 0.4442, + "step": 10698 + }, + { + "epoch": 0.91, + "learning_rate": 4.010484702955741e-07, + "loss": 0.4498, + "step": 10699 + }, + { + "epoch": 0.91, + "learning_rate": 4.002745971605759e-07, + "loss": 0.4309, + "step": 10700 + }, + { + "epoch": 0.91, + "learning_rate": 3.99501456140714e-07, + "loss": 0.4489, + "step": 10701 + }, + { + "epoch": 0.91, + "learning_rate": 3.9872904729495123e-07, + "loss": 0.4606, + "step": 10702 + }, + { + "epoch": 0.91, + "learning_rate": 3.97957370682196e-07, + "loss": 0.4386, + "step": 10703 + }, + { + "epoch": 0.91, + "learning_rate": 3.97186426361299e-07, + "loss": 0.4226, + "step": 10704 + }, + { + "epoch": 0.91, + "learning_rate": 3.964162143910555e-07, + "loss": 0.4383, + "step": 10705 + }, + { + "epoch": 0.91, + "learning_rate": 3.956467348302062e-07, + "loss": 0.4636, + "step": 10706 + }, + { + "epoch": 0.91, + "learning_rate": 3.9487798773743425e-07, + "loss": 0.4384, + "step": 10707 + }, + { + "epoch": 0.91, + "learning_rate": 3.941099731713638e-07, + "loss": 0.4584, + "step": 10708 + }, + { + "epoch": 0.91, + "learning_rate": 3.9334269119057354e-07, + "loss": 0.4685, + "step": 10709 + }, + { + "epoch": 0.91, + "learning_rate": 3.925761418535756e-07, + "loss": 0.4457, + "step": 10710 + }, + { + "epoch": 0.91, + "learning_rate": 3.918103252188299e-07, + "loss": 0.4445, + "step": 10711 + }, + { + "epoch": 0.91, + "learning_rate": 3.9104524134474187e-07, + "loss": 0.4621, + "step": 10712 + }, + { + "epoch": 0.91, + "learning_rate": 3.902808902896604e-07, + "loss": 0.4157, + "step": 10713 + }, + { + "epoch": 0.91, + "learning_rate": 3.895172721118778e-07, + "loss": 0.4593, + "step": 10714 + }, + { + "epoch": 0.91, + "learning_rate": 3.8875438686962973e-07, + "loss": 0.4646, + "step": 10715 + }, + { + "epoch": 0.91, + "learning_rate": 3.879922346210996e-07, + "loss": 0.4533, + "step": 10716 + }, + { + "epoch": 0.91, + "learning_rate": 3.8723081542440866e-07, + "loss": 0.4384, + "step": 10717 + }, + { + "epoch": 0.91, + "learning_rate": 3.864701293376294e-07, + "loss": 0.4425, + "step": 10718 + }, + { + "epoch": 0.91, + "learning_rate": 3.8571017641877206e-07, + "loss": 0.438, + "step": 10719 + }, + { + "epoch": 0.91, + "learning_rate": 3.8495095672579584e-07, + "loss": 0.4424, + "step": 10720 + }, + { + "epoch": 0.91, + "learning_rate": 3.8419247031660113e-07, + "loss": 0.4705, + "step": 10721 + }, + { + "epoch": 0.91, + "learning_rate": 3.834347172490327e-07, + "loss": 0.4399, + "step": 10722 + }, + { + "epoch": 0.91, + "learning_rate": 3.826776975808821e-07, + "loss": 0.4824, + "step": 10723 + }, + { + "epoch": 0.91, + "learning_rate": 3.819214113698799e-07, + "loss": 0.4573, + "step": 10724 + }, + { + "epoch": 0.91, + "learning_rate": 3.811658586737077e-07, + "loss": 0.4359, + "step": 10725 + }, + { + "epoch": 0.91, + "learning_rate": 3.8041103954998046e-07, + "loss": 0.4514, + "step": 10726 + }, + { + "epoch": 0.91, + "learning_rate": 3.7965695405627e-07, + "loss": 0.4585, + "step": 10727 + }, + { + "epoch": 0.91, + "learning_rate": 3.789036022500858e-07, + "loss": 0.479, + "step": 10728 + }, + { + "epoch": 0.91, + "learning_rate": 3.781509841888775e-07, + "loss": 0.4538, + "step": 10729 + }, + { + "epoch": 0.91, + "learning_rate": 3.773990999300459e-07, + "loss": 0.4418, + "step": 10730 + }, + { + "epoch": 0.91, + "learning_rate": 3.7664794953093163e-07, + "loss": 0.4539, + "step": 10731 + }, + { + "epoch": 0.92, + "learning_rate": 3.7589753304882125e-07, + "loss": 0.4536, + "step": 10732 + }, + { + "epoch": 0.92, + "learning_rate": 3.7514785054094447e-07, + "loss": 0.4367, + "step": 10733 + }, + { + "epoch": 0.92, + "learning_rate": 3.7439890206447674e-07, + "loss": 0.4456, + "step": 10734 + }, + { + "epoch": 0.92, + "learning_rate": 3.736506876765311e-07, + "loss": 0.4632, + "step": 10735 + }, + { + "epoch": 0.92, + "learning_rate": 3.729032074341743e-07, + "loss": 0.4355, + "step": 10736 + }, + { + "epoch": 0.92, + "learning_rate": 3.7215646139441284e-07, + "loss": 0.4501, + "step": 10737 + }, + { + "epoch": 0.92, + "learning_rate": 3.714104496141924e-07, + "loss": 0.4501, + "step": 10738 + }, + { + "epoch": 0.92, + "learning_rate": 3.706651721504095e-07, + "loss": 0.4545, + "step": 10739 + }, + { + "epoch": 0.92, + "learning_rate": 3.6992062905990225e-07, + "loss": 0.4302, + "step": 10740 + }, + { + "epoch": 0.92, + "learning_rate": 3.6917682039945167e-07, + "loss": 0.4448, + "step": 10741 + }, + { + "epoch": 0.92, + "learning_rate": 3.6843374622578474e-07, + "loss": 0.4381, + "step": 10742 + }, + { + "epoch": 0.92, + "learning_rate": 3.676914065955717e-07, + "loss": 0.4291, + "step": 10743 + }, + { + "epoch": 0.92, + "learning_rate": 3.6694980156542494e-07, + "loss": 0.4577, + "step": 10744 + }, + { + "epoch": 0.92, + "learning_rate": 3.662089311919015e-07, + "loss": 0.4566, + "step": 10745 + }, + { + "epoch": 0.92, + "learning_rate": 3.6546879553150727e-07, + "loss": 0.4365, + "step": 10746 + }, + { + "epoch": 0.92, + "learning_rate": 3.647293946406849e-07, + "loss": 0.4389, + "step": 10747 + }, + { + "epoch": 0.92, + "learning_rate": 3.6399072857582487e-07, + "loss": 0.4798, + "step": 10748 + }, + { + "epoch": 0.92, + "learning_rate": 3.6325279739325983e-07, + "loss": 0.4492, + "step": 10749 + }, + { + "epoch": 0.92, + "learning_rate": 3.625156011492703e-07, + "loss": 0.456, + "step": 10750 + }, + { + "epoch": 0.92, + "learning_rate": 3.6177913990007473e-07, + "loss": 0.4598, + "step": 10751 + }, + { + "epoch": 0.92, + "learning_rate": 3.610434137018426e-07, + "loss": 0.437, + "step": 10752 + }, + { + "epoch": 0.92, + "learning_rate": 3.603084226106801e-07, + "loss": 0.4735, + "step": 10753 + }, + { + "epoch": 0.92, + "learning_rate": 3.595741666826402e-07, + "loss": 0.46, + "step": 10754 + }, + { + "epoch": 0.92, + "learning_rate": 3.588406459737237e-07, + "loss": 0.4639, + "step": 10755 + }, + { + "epoch": 0.92, + "learning_rate": 3.5810786053987025e-07, + "loss": 0.4394, + "step": 10756 + }, + { + "epoch": 0.92, + "learning_rate": 3.57375810436964e-07, + "loss": 0.4323, + "step": 10757 + }, + { + "epoch": 0.92, + "learning_rate": 3.5664449572083594e-07, + "loss": 0.4605, + "step": 10758 + }, + { + "epoch": 0.92, + "learning_rate": 3.5591391644725805e-07, + "loss": 0.4382, + "step": 10759 + }, + { + "epoch": 0.92, + "learning_rate": 3.55184072671948e-07, + "loss": 0.4762, + "step": 10760 + }, + { + "epoch": 0.92, + "learning_rate": 3.544549644505668e-07, + "loss": 0.4541, + "step": 10761 + }, + { + "epoch": 0.92, + "learning_rate": 3.5372659183871895e-07, + "loss": 0.4383, + "step": 10762 + }, + { + "epoch": 0.92, + "learning_rate": 3.52998954891951e-07, + "loss": 0.4489, + "step": 10763 + }, + { + "epoch": 0.92, + "learning_rate": 3.522720536657609e-07, + "loss": 0.4537, + "step": 10764 + }, + { + "epoch": 0.92, + "learning_rate": 3.515458882155798e-07, + "loss": 0.4424, + "step": 10765 + }, + { + "epoch": 0.92, + "learning_rate": 3.508204585967911e-07, + "loss": 0.4475, + "step": 10766 + }, + { + "epoch": 0.92, + "learning_rate": 3.500957648647196e-07, + "loss": 0.4645, + "step": 10767 + }, + { + "epoch": 0.92, + "learning_rate": 3.493718070746299e-07, + "loss": 0.4574, + "step": 10768 + }, + { + "epoch": 0.92, + "learning_rate": 3.486485852817378e-07, + "loss": 0.4375, + "step": 10769 + }, + { + "epoch": 0.92, + "learning_rate": 3.4792609954119815e-07, + "loss": 0.4703, + "step": 10770 + }, + { + "epoch": 0.92, + "learning_rate": 3.4720434990810904e-07, + "loss": 0.4444, + "step": 10771 + }, + { + "epoch": 0.92, + "learning_rate": 3.4648333643751533e-07, + "loss": 0.4494, + "step": 10772 + }, + { + "epoch": 0.92, + "learning_rate": 3.4576305918440635e-07, + "loss": 0.4395, + "step": 10773 + }, + { + "epoch": 0.92, + "learning_rate": 3.450435182037104e-07, + "loss": 0.4739, + "step": 10774 + }, + { + "epoch": 0.92, + "learning_rate": 3.443247135503036e-07, + "loss": 0.4394, + "step": 10775 + }, + { + "epoch": 0.92, + "learning_rate": 3.4360664527900767e-07, + "loss": 0.4625, + "step": 10776 + }, + { + "epoch": 0.92, + "learning_rate": 3.4288931344457987e-07, + "loss": 0.4538, + "step": 10777 + }, + { + "epoch": 0.92, + "learning_rate": 3.42172718101732e-07, + "loss": 0.4354, + "step": 10778 + }, + { + "epoch": 0.92, + "learning_rate": 3.4145685930511374e-07, + "loss": 0.4474, + "step": 10779 + }, + { + "epoch": 0.92, + "learning_rate": 3.4074173710931804e-07, + "loss": 0.448, + "step": 10780 + }, + { + "epoch": 0.92, + "learning_rate": 3.4002735156888234e-07, + "loss": 0.4528, + "step": 10781 + }, + { + "epoch": 0.92, + "learning_rate": 3.393137027382909e-07, + "loss": 0.4629, + "step": 10782 + }, + { + "epoch": 0.92, + "learning_rate": 3.3860079067196906e-07, + "loss": 0.4499, + "step": 10783 + }, + { + "epoch": 0.92, + "learning_rate": 3.3788861542428555e-07, + "loss": 0.4509, + "step": 10784 + }, + { + "epoch": 0.92, + "learning_rate": 3.3717717704955575e-07, + "loss": 0.4515, + "step": 10785 + }, + { + "epoch": 0.92, + "learning_rate": 3.3646647560203303e-07, + "loss": 0.4613, + "step": 10786 + }, + { + "epoch": 0.92, + "learning_rate": 3.3575651113592177e-07, + "loss": 0.4781, + "step": 10787 + }, + { + "epoch": 0.92, + "learning_rate": 3.3504728370536755e-07, + "loss": 0.4362, + "step": 10788 + }, + { + "epoch": 0.92, + "learning_rate": 3.3433879336445597e-07, + "loss": 0.4405, + "step": 10789 + }, + { + "epoch": 0.92, + "learning_rate": 3.3363104016721936e-07, + "loss": 0.4474, + "step": 10790 + }, + { + "epoch": 0.92, + "learning_rate": 3.329240241676379e-07, + "loss": 0.424, + "step": 10791 + }, + { + "epoch": 0.92, + "learning_rate": 3.322177454196285e-07, + "loss": 0.4486, + "step": 10792 + }, + { + "epoch": 0.92, + "learning_rate": 3.3151220397705577e-07, + "loss": 0.4524, + "step": 10793 + }, + { + "epoch": 0.92, + "learning_rate": 3.308073998937278e-07, + "loss": 0.45, + "step": 10794 + }, + { + "epoch": 0.92, + "learning_rate": 3.301033332233938e-07, + "loss": 0.4637, + "step": 10795 + }, + { + "epoch": 0.92, + "learning_rate": 3.2940000401975094e-07, + "loss": 0.4619, + "step": 10796 + }, + { + "epoch": 0.92, + "learning_rate": 3.2869741233643726e-07, + "loss": 0.47, + "step": 10797 + }, + { + "epoch": 0.92, + "learning_rate": 3.2799555822703554e-07, + "loss": 0.446, + "step": 10798 + }, + { + "epoch": 0.92, + "learning_rate": 3.2729444174507186e-07, + "loss": 0.4464, + "step": 10799 + }, + { + "epoch": 0.92, + "learning_rate": 3.2659406294401566e-07, + "loss": 0.4605, + "step": 10800 + }, + { + "epoch": 0.92, + "learning_rate": 3.2589442187728193e-07, + "loss": 0.4487, + "step": 10801 + }, + { + "epoch": 0.92, + "learning_rate": 3.2519551859822805e-07, + "loss": 0.4311, + "step": 10802 + }, + { + "epoch": 0.92, + "learning_rate": 3.2449735316015583e-07, + "loss": 0.4653, + "step": 10803 + }, + { + "epoch": 0.92, + "learning_rate": 3.237999256163071e-07, + "loss": 0.4293, + "step": 10804 + }, + { + "epoch": 0.92, + "learning_rate": 3.231032360198749e-07, + "loss": 0.4505, + "step": 10805 + }, + { + "epoch": 0.92, + "learning_rate": 3.2240728442399005e-07, + "loss": 0.4623, + "step": 10806 + }, + { + "epoch": 0.92, + "learning_rate": 3.2171207088172676e-07, + "loss": 0.4564, + "step": 10807 + }, + { + "epoch": 0.92, + "learning_rate": 3.210175954461081e-07, + "loss": 0.4688, + "step": 10808 + }, + { + "epoch": 0.92, + "learning_rate": 3.2032385817009514e-07, + "loss": 0.4513, + "step": 10809 + }, + { + "epoch": 0.92, + "learning_rate": 3.196308591065966e-07, + "loss": 0.47, + "step": 10810 + }, + { + "epoch": 0.92, + "learning_rate": 3.189385983084625e-07, + "loss": 0.4418, + "step": 10811 + }, + { + "epoch": 0.92, + "learning_rate": 3.1824707582848945e-07, + "loss": 0.4576, + "step": 10812 + }, + { + "epoch": 0.92, + "learning_rate": 3.1755629171941196e-07, + "loss": 0.4422, + "step": 10813 + }, + { + "epoch": 0.92, + "learning_rate": 3.168662460339167e-07, + "loss": 0.4553, + "step": 10814 + }, + { + "epoch": 0.92, + "learning_rate": 3.161769388246283e-07, + "loss": 0.4629, + "step": 10815 + }, + { + "epoch": 0.92, + "learning_rate": 3.154883701441136e-07, + "loss": 0.4626, + "step": 10816 + }, + { + "epoch": 0.92, + "learning_rate": 3.1480054004488723e-07, + "loss": 0.453, + "step": 10817 + }, + { + "epoch": 0.92, + "learning_rate": 3.141134485794073e-07, + "loss": 0.4488, + "step": 10818 + }, + { + "epoch": 0.92, + "learning_rate": 3.134270958000718e-07, + "loss": 0.4527, + "step": 10819 + }, + { + "epoch": 0.92, + "learning_rate": 3.127414817592278e-07, + "loss": 0.4499, + "step": 10820 + }, + { + "epoch": 0.92, + "learning_rate": 3.1205660650916127e-07, + "loss": 0.4657, + "step": 10821 + }, + { + "epoch": 0.92, + "learning_rate": 3.113724701021026e-07, + "loss": 0.453, + "step": 10822 + }, + { + "epoch": 0.92, + "learning_rate": 3.1068907259022786e-07, + "loss": 0.4477, + "step": 10823 + }, + { + "epoch": 0.92, + "learning_rate": 3.1000641402565866e-07, + "loss": 0.44, + "step": 10824 + }, + { + "epoch": 0.92, + "learning_rate": 3.093244944604523e-07, + "loss": 0.457, + "step": 10825 + }, + { + "epoch": 0.92, + "learning_rate": 3.086433139466183e-07, + "loss": 0.4296, + "step": 10826 + }, + { + "epoch": 0.92, + "learning_rate": 3.079628725361061e-07, + "loss": 0.4454, + "step": 10827 + }, + { + "epoch": 0.92, + "learning_rate": 3.0728317028080656e-07, + "loss": 0.4539, + "step": 10828 + }, + { + "epoch": 0.92, + "learning_rate": 3.066042072325592e-07, + "loss": 0.4594, + "step": 10829 + }, + { + "epoch": 0.92, + "learning_rate": 3.0592598344314495e-07, + "loss": 0.4462, + "step": 10830 + }, + { + "epoch": 0.92, + "learning_rate": 3.0524849896428567e-07, + "loss": 0.455, + "step": 10831 + }, + { + "epoch": 0.92, + "learning_rate": 3.0457175384764894e-07, + "loss": 0.4527, + "step": 10832 + }, + { + "epoch": 0.92, + "learning_rate": 3.0389574814485015e-07, + "loss": 0.4485, + "step": 10833 + }, + { + "epoch": 0.92, + "learning_rate": 3.0322048190744025e-07, + "loss": 0.4629, + "step": 10834 + }, + { + "epoch": 0.92, + "learning_rate": 3.025459551869192e-07, + "loss": 0.4724, + "step": 10835 + }, + { + "epoch": 0.92, + "learning_rate": 3.0187216803472805e-07, + "loss": 0.4465, + "step": 10836 + }, + { + "epoch": 0.92, + "learning_rate": 3.0119912050225576e-07, + "loss": 0.4374, + "step": 10837 + }, + { + "epoch": 0.92, + "learning_rate": 3.0052681264082895e-07, + "loss": 0.4513, + "step": 10838 + }, + { + "epoch": 0.92, + "learning_rate": 2.998552445017222e-07, + "loss": 0.4478, + "step": 10839 + }, + { + "epoch": 0.92, + "learning_rate": 2.991844161361512e-07, + "loss": 0.4462, + "step": 10840 + }, + { + "epoch": 0.92, + "learning_rate": 2.9851432759527397e-07, + "loss": 0.4585, + "step": 10841 + }, + { + "epoch": 0.92, + "learning_rate": 2.978449789301996e-07, + "loss": 0.4467, + "step": 10842 + }, + { + "epoch": 0.92, + "learning_rate": 2.9717637019197163e-07, + "loss": 0.4527, + "step": 10843 + }, + { + "epoch": 0.92, + "learning_rate": 2.965085014315816e-07, + "loss": 0.463, + "step": 10844 + }, + { + "epoch": 0.92, + "learning_rate": 2.958413726999632e-07, + "loss": 0.4577, + "step": 10845 + }, + { + "epoch": 0.92, + "learning_rate": 2.9517498404799674e-07, + "loss": 0.4464, + "step": 10846 + }, + { + "epoch": 0.92, + "learning_rate": 2.9450933552650163e-07, + "loss": 0.4518, + "step": 10847 + }, + { + "epoch": 0.92, + "learning_rate": 2.9384442718624397e-07, + "loss": 0.4506, + "step": 10848 + }, + { + "epoch": 0.93, + "learning_rate": 2.9318025907793314e-07, + "loss": 0.4628, + "step": 10849 + }, + { + "epoch": 0.93, + "learning_rate": 2.9251683125221864e-07, + "loss": 0.4484, + "step": 10850 + }, + { + "epoch": 0.93, + "learning_rate": 2.918541437597e-07, + "loss": 0.4432, + "step": 10851 + }, + { + "epoch": 0.93, + "learning_rate": 2.9119219665091345e-07, + "loss": 0.4581, + "step": 10852 + }, + { + "epoch": 0.93, + "learning_rate": 2.905309899763431e-07, + "loss": 0.4439, + "step": 10853 + }, + { + "epoch": 0.93, + "learning_rate": 2.898705237864152e-07, + "loss": 0.4493, + "step": 10854 + }, + { + "epoch": 0.93, + "learning_rate": 2.8921079813150066e-07, + "loss": 0.4408, + "step": 10855 + }, + { + "epoch": 0.93, + "learning_rate": 2.8855181306191137e-07, + "loss": 0.4507, + "step": 10856 + }, + { + "epoch": 0.93, + "learning_rate": 2.87893568627905e-07, + "loss": 0.4679, + "step": 10857 + }, + { + "epoch": 0.93, + "learning_rate": 2.8723606487968235e-07, + "loss": 0.4614, + "step": 10858 + }, + { + "epoch": 0.93, + "learning_rate": 2.865793018673857e-07, + "loss": 0.4448, + "step": 10859 + }, + { + "epoch": 0.93, + "learning_rate": 2.859232796411049e-07, + "loss": 0.4648, + "step": 10860 + }, + { + "epoch": 0.93, + "learning_rate": 2.8526799825086993e-07, + "loss": 0.4605, + "step": 10861 + }, + { + "epoch": 0.93, + "learning_rate": 2.8461345774665414e-07, + "loss": 0.4526, + "step": 10862 + }, + { + "epoch": 0.93, + "learning_rate": 2.8395965817837766e-07, + "loss": 0.453, + "step": 10863 + }, + { + "epoch": 0.93, + "learning_rate": 2.8330659959589944e-07, + "loss": 0.461, + "step": 10864 + }, + { + "epoch": 0.93, + "learning_rate": 2.8265428204902746e-07, + "loss": 0.4615, + "step": 10865 + }, + { + "epoch": 0.93, + "learning_rate": 2.8200270558750743e-07, + "loss": 0.4408, + "step": 10866 + }, + { + "epoch": 0.93, + "learning_rate": 2.8135187026103403e-07, + "loss": 0.4709, + "step": 10867 + }, + { + "epoch": 0.93, + "learning_rate": 2.807017761192399e-07, + "loss": 0.4721, + "step": 10868 + }, + { + "epoch": 0.93, + "learning_rate": 2.8005242321170633e-07, + "loss": 0.4391, + "step": 10869 + }, + { + "epoch": 0.93, + "learning_rate": 2.794038115879538e-07, + "loss": 0.4762, + "step": 10870 + }, + { + "epoch": 0.93, + "learning_rate": 2.787559412974483e-07, + "loss": 0.4436, + "step": 10871 + }, + { + "epoch": 0.93, + "learning_rate": 2.781088123896003e-07, + "loss": 0.4365, + "step": 10872 + }, + { + "epoch": 0.93, + "learning_rate": 2.774624249137614e-07, + "loss": 0.4727, + "step": 10873 + }, + { + "epoch": 0.93, + "learning_rate": 2.7681677891922887e-07, + "loss": 0.4587, + "step": 10874 + }, + { + "epoch": 0.93, + "learning_rate": 2.761718744552422e-07, + "loss": 0.4572, + "step": 10875 + }, + { + "epoch": 0.93, + "learning_rate": 2.755277115709842e-07, + "loss": 0.4392, + "step": 10876 + }, + { + "epoch": 0.93, + "learning_rate": 2.7488429031558016e-07, + "loss": 0.4541, + "step": 10877 + }, + { + "epoch": 0.93, + "learning_rate": 2.7424161073810183e-07, + "loss": 0.4473, + "step": 10878 + }, + { + "epoch": 0.93, + "learning_rate": 2.735996728875623e-07, + "loss": 0.4477, + "step": 10879 + }, + { + "epoch": 0.93, + "learning_rate": 2.7295847681291897e-07, + "loss": 0.4554, + "step": 10880 + }, + { + "epoch": 0.93, + "learning_rate": 2.723180225630695e-07, + "loss": 0.4646, + "step": 10881 + }, + { + "epoch": 0.93, + "learning_rate": 2.716783101868614e-07, + "loss": 0.4902, + "step": 10882 + }, + { + "epoch": 0.93, + "learning_rate": 2.7103933973307796e-07, + "loss": 0.4533, + "step": 10883 + }, + { + "epoch": 0.93, + "learning_rate": 2.7040111125045345e-07, + "loss": 0.4447, + "step": 10884 + }, + { + "epoch": 0.93, + "learning_rate": 2.6976362478766003e-07, + "loss": 0.4466, + "step": 10885 + }, + { + "epoch": 0.93, + "learning_rate": 2.691268803933145e-07, + "loss": 0.4382, + "step": 10886 + }, + { + "epoch": 0.93, + "learning_rate": 2.6849087811597787e-07, + "loss": 0.4655, + "step": 10887 + }, + { + "epoch": 0.93, + "learning_rate": 2.678556180041547e-07, + "loss": 0.4502, + "step": 10888 + }, + { + "epoch": 0.93, + "learning_rate": 2.67221100106293e-07, + "loss": 0.4517, + "step": 10889 + }, + { + "epoch": 0.93, + "learning_rate": 2.6658732447078286e-07, + "loss": 0.44, + "step": 10890 + }, + { + "epoch": 0.93, + "learning_rate": 2.6595429114595894e-07, + "loss": 0.4694, + "step": 10891 + }, + { + "epoch": 0.93, + "learning_rate": 2.653220001801005e-07, + "loss": 0.4388, + "step": 10892 + }, + { + "epoch": 0.93, + "learning_rate": 2.646904516214266e-07, + "loss": 0.4509, + "step": 10893 + }, + { + "epoch": 0.93, + "learning_rate": 2.6405964551810325e-07, + "loss": 0.4457, + "step": 10894 + }, + { + "epoch": 0.93, + "learning_rate": 2.6342958191823643e-07, + "loss": 0.4393, + "step": 10895 + }, + { + "epoch": 0.93, + "learning_rate": 2.6280026086987985e-07, + "loss": 0.4579, + "step": 10896 + }, + { + "epoch": 0.93, + "learning_rate": 2.621716824210263e-07, + "loss": 0.4432, + "step": 10897 + }, + { + "epoch": 0.93, + "learning_rate": 2.6154384661961405e-07, + "loss": 0.4409, + "step": 10898 + }, + { + "epoch": 0.93, + "learning_rate": 2.6091675351352485e-07, + "loss": 0.4484, + "step": 10899 + }, + { + "epoch": 0.93, + "learning_rate": 2.6029040315058487e-07, + "loss": 0.4707, + "step": 10900 + }, + { + "epoch": 0.93, + "learning_rate": 2.5966479557855914e-07, + "loss": 0.4309, + "step": 10901 + }, + { + "epoch": 0.93, + "learning_rate": 2.5903993084516077e-07, + "loss": 0.4475, + "step": 10902 + }, + { + "epoch": 0.93, + "learning_rate": 2.5841580899804706e-07, + "loss": 0.4383, + "step": 10903 + }, + { + "epoch": 0.93, + "learning_rate": 2.5779243008481114e-07, + "loss": 0.4722, + "step": 10904 + }, + { + "epoch": 0.93, + "learning_rate": 2.5716979415299714e-07, + "loss": 0.4388, + "step": 10905 + }, + { + "epoch": 0.93, + "learning_rate": 2.565479012500915e-07, + "loss": 0.4364, + "step": 10906 + }, + { + "epoch": 0.93, + "learning_rate": 2.5592675142351865e-07, + "loss": 0.4683, + "step": 10907 + }, + { + "epoch": 0.93, + "learning_rate": 2.553063447206527e-07, + "loss": 0.4362, + "step": 10908 + }, + { + "epoch": 0.93, + "learning_rate": 2.5468668118880935e-07, + "loss": 0.4706, + "step": 10909 + }, + { + "epoch": 0.93, + "learning_rate": 2.540677608752429e-07, + "loss": 0.4553, + "step": 10910 + }, + { + "epoch": 0.93, + "learning_rate": 2.534495838271578e-07, + "loss": 0.4531, + "step": 10911 + }, + { + "epoch": 0.93, + "learning_rate": 2.528321500916986e-07, + "loss": 0.4502, + "step": 10912 + }, + { + "epoch": 0.93, + "learning_rate": 2.5221545971595207e-07, + "loss": 0.4777, + "step": 10913 + }, + { + "epoch": 0.93, + "learning_rate": 2.5159951274694947e-07, + "loss": 0.445, + "step": 10914 + }, + { + "epoch": 0.93, + "learning_rate": 2.509843092316688e-07, + "loss": 0.4549, + "step": 10915 + }, + { + "epoch": 0.93, + "learning_rate": 2.503698492170237e-07, + "loss": 0.4535, + "step": 10916 + }, + { + "epoch": 0.93, + "learning_rate": 2.497561327498788e-07, + "loss": 0.4606, + "step": 10917 + }, + { + "epoch": 0.93, + "learning_rate": 2.4914315987703664e-07, + "loss": 0.4436, + "step": 10918 + }, + { + "epoch": 0.93, + "learning_rate": 2.4853093064524434e-07, + "loss": 0.452, + "step": 10919 + }, + { + "epoch": 0.93, + "learning_rate": 2.479194451011957e-07, + "loss": 0.4697, + "step": 10920 + }, + { + "epoch": 0.93, + "learning_rate": 2.4730870329152557e-07, + "loss": 0.4624, + "step": 10921 + }, + { + "epoch": 0.93, + "learning_rate": 2.466987052628078e-07, + "loss": 0.4499, + "step": 10922 + }, + { + "epoch": 0.93, + "learning_rate": 2.4608945106156524e-07, + "loss": 0.4677, + "step": 10923 + }, + { + "epoch": 0.93, + "learning_rate": 2.45480940734264e-07, + "loss": 0.4209, + "step": 10924 + }, + { + "epoch": 0.93, + "learning_rate": 2.4487317432730917e-07, + "loss": 0.4617, + "step": 10925 + }, + { + "epoch": 0.93, + "learning_rate": 2.442661518870526e-07, + "loss": 0.4745, + "step": 10926 + }, + { + "epoch": 0.93, + "learning_rate": 2.4365987345978946e-07, + "loss": 0.4456, + "step": 10927 + }, + { + "epoch": 0.93, + "learning_rate": 2.430543390917539e-07, + "loss": 0.4683, + "step": 10928 + }, + { + "epoch": 0.93, + "learning_rate": 2.4244954882912895e-07, + "loss": 0.4511, + "step": 10929 + }, + { + "epoch": 0.93, + "learning_rate": 2.418455027180389e-07, + "loss": 0.4572, + "step": 10930 + }, + { + "epoch": 0.93, + "learning_rate": 2.4124220080455006e-07, + "loss": 0.4276, + "step": 10931 + }, + { + "epoch": 0.93, + "learning_rate": 2.4063964313467135e-07, + "loss": 0.4566, + "step": 10932 + }, + { + "epoch": 0.93, + "learning_rate": 2.400378297543582e-07, + "loss": 0.4477, + "step": 10933 + }, + { + "epoch": 0.93, + "learning_rate": 2.3943676070950606e-07, + "loss": 0.4399, + "step": 10934 + }, + { + "epoch": 0.93, + "learning_rate": 2.3883643604595607e-07, + "loss": 0.4562, + "step": 10935 + }, + { + "epoch": 0.93, + "learning_rate": 2.3823685580949273e-07, + "loss": 0.4639, + "step": 10936 + }, + { + "epoch": 0.93, + "learning_rate": 2.3763802004583835e-07, + "loss": 0.4601, + "step": 10937 + }, + { + "epoch": 0.93, + "learning_rate": 2.370399288006664e-07, + "loss": 0.4415, + "step": 10938 + }, + { + "epoch": 0.93, + "learning_rate": 2.3644258211958926e-07, + "loss": 0.4355, + "step": 10939 + }, + { + "epoch": 0.93, + "learning_rate": 2.3584598004816162e-07, + "loss": 0.447, + "step": 10940 + }, + { + "epoch": 0.93, + "learning_rate": 2.3525012263188373e-07, + "loss": 0.4539, + "step": 10941 + }, + { + "epoch": 0.93, + "learning_rate": 2.3465500991619815e-07, + "loss": 0.4374, + "step": 10942 + }, + { + "epoch": 0.93, + "learning_rate": 2.340606419464897e-07, + "loss": 0.4357, + "step": 10943 + }, + { + "epoch": 0.93, + "learning_rate": 2.3346701876808987e-07, + "loss": 0.4678, + "step": 10944 + }, + { + "epoch": 0.93, + "learning_rate": 2.328741404262691e-07, + "loss": 0.4749, + "step": 10945 + }, + { + "epoch": 0.93, + "learning_rate": 2.3228200696624125e-07, + "loss": 0.4584, + "step": 10946 + }, + { + "epoch": 0.93, + "learning_rate": 2.3169061843316688e-07, + "loss": 0.4437, + "step": 10947 + }, + { + "epoch": 0.93, + "learning_rate": 2.3109997487214987e-07, + "loss": 0.4559, + "step": 10948 + }, + { + "epoch": 0.93, + "learning_rate": 2.3051007632823085e-07, + "loss": 0.4641, + "step": 10949 + }, + { + "epoch": 0.93, + "learning_rate": 2.2992092284639944e-07, + "loss": 0.4333, + "step": 10950 + }, + { + "epoch": 0.93, + "learning_rate": 2.2933251447158744e-07, + "loss": 0.4453, + "step": 10951 + }, + { + "epoch": 0.93, + "learning_rate": 2.2874485124867007e-07, + "loss": 0.4492, + "step": 10952 + }, + { + "epoch": 0.93, + "learning_rate": 2.281579332224626e-07, + "loss": 0.4592, + "step": 10953 + }, + { + "epoch": 0.93, + "learning_rate": 2.275717604377292e-07, + "loss": 0.4332, + "step": 10954 + }, + { + "epoch": 0.93, + "learning_rate": 2.2698633293917193e-07, + "loss": 0.4594, + "step": 10955 + }, + { + "epoch": 0.93, + "learning_rate": 2.2640165077143618e-07, + "loss": 0.4852, + "step": 10956 + }, + { + "epoch": 0.93, + "learning_rate": 2.2581771397911512e-07, + "loss": 0.4415, + "step": 10957 + }, + { + "epoch": 0.93, + "learning_rate": 2.2523452260674207e-07, + "loss": 0.4633, + "step": 10958 + }, + { + "epoch": 0.93, + "learning_rate": 2.246520766987914e-07, + "loss": 0.4636, + "step": 10959 + }, + { + "epoch": 0.93, + "learning_rate": 2.2407037629968431e-07, + "loss": 0.4401, + "step": 10960 + }, + { + "epoch": 0.93, + "learning_rate": 2.2348942145378415e-07, + "loss": 0.4451, + "step": 10961 + }, + { + "epoch": 0.93, + "learning_rate": 2.2290921220539662e-07, + "loss": 0.4524, + "step": 10962 + }, + { + "epoch": 0.93, + "learning_rate": 2.2232974859877076e-07, + "loss": 0.4527, + "step": 10963 + }, + { + "epoch": 0.93, + "learning_rate": 2.2175103067809788e-07, + "loss": 0.4699, + "step": 10964 + }, + { + "epoch": 0.93, + "learning_rate": 2.211730584875138e-07, + "loss": 0.4765, + "step": 10965 + }, + { + "epoch": 0.94, + "learning_rate": 2.2059583207109992e-07, + "loss": 0.4437, + "step": 10966 + }, + { + "epoch": 0.94, + "learning_rate": 2.2001935147287434e-07, + "loss": 0.4708, + "step": 10967 + }, + { + "epoch": 0.94, + "learning_rate": 2.1944361673680304e-07, + "loss": 0.4577, + "step": 10968 + }, + { + "epoch": 0.94, + "learning_rate": 2.188686279067942e-07, + "loss": 0.4519, + "step": 10969 + }, + { + "epoch": 0.94, + "learning_rate": 2.182943850266994e-07, + "loss": 0.4476, + "step": 10970 + }, + { + "epoch": 0.94, + "learning_rate": 2.1772088814031144e-07, + "loss": 0.451, + "step": 10971 + }, + { + "epoch": 0.94, + "learning_rate": 2.1714813729136975e-07, + "loss": 0.4642, + "step": 10972 + }, + { + "epoch": 0.94, + "learning_rate": 2.165761325235527e-07, + "loss": 0.4584, + "step": 10973 + }, + { + "epoch": 0.94, + "learning_rate": 2.160048738804821e-07, + "loss": 0.4681, + "step": 10974 + }, + { + "epoch": 0.94, + "learning_rate": 2.1543436140572972e-07, + "loss": 0.4437, + "step": 10975 + }, + { + "epoch": 0.94, + "learning_rate": 2.1486459514280078e-07, + "loss": 0.444, + "step": 10976 + }, + { + "epoch": 0.94, + "learning_rate": 2.1429557513514942e-07, + "loss": 0.479, + "step": 10977 + }, + { + "epoch": 0.94, + "learning_rate": 2.1372730142617205e-07, + "loss": 0.4597, + "step": 10978 + }, + { + "epoch": 0.94, + "learning_rate": 2.131597740592073e-07, + "loss": 0.4416, + "step": 10979 + }, + { + "epoch": 0.94, + "learning_rate": 2.1259299307753721e-07, + "loss": 0.4525, + "step": 10980 + }, + { + "epoch": 0.94, + "learning_rate": 2.1202695852438725e-07, + "loss": 0.4464, + "step": 10981 + }, + { + "epoch": 0.94, + "learning_rate": 2.11461670442924e-07, + "loss": 0.4404, + "step": 10982 + }, + { + "epoch": 0.94, + "learning_rate": 2.1089712887625847e-07, + "loss": 0.4468, + "step": 10983 + }, + { + "epoch": 0.94, + "learning_rate": 2.1033333386744848e-07, + "loss": 0.4434, + "step": 10984 + }, + { + "epoch": 0.94, + "learning_rate": 2.097702854594874e-07, + "loss": 0.4478, + "step": 10985 + }, + { + "epoch": 0.94, + "learning_rate": 2.092079836953176e-07, + "loss": 0.4562, + "step": 10986 + }, + { + "epoch": 0.94, + "learning_rate": 2.0864642861782246e-07, + "loss": 0.4505, + "step": 10987 + }, + { + "epoch": 0.94, + "learning_rate": 2.0808562026982894e-07, + "loss": 0.4579, + "step": 10988 + }, + { + "epoch": 0.94, + "learning_rate": 2.0752555869410495e-07, + "loss": 0.4424, + "step": 10989 + }, + { + "epoch": 0.94, + "learning_rate": 2.069662439333664e-07, + "loss": 0.4755, + "step": 10990 + }, + { + "epoch": 0.94, + "learning_rate": 2.064076760302647e-07, + "loss": 0.4535, + "step": 10991 + }, + { + "epoch": 0.94, + "learning_rate": 2.0584985502740018e-07, + "loss": 0.4339, + "step": 10992 + }, + { + "epoch": 0.94, + "learning_rate": 2.0529278096731664e-07, + "loss": 0.4365, + "step": 10993 + }, + { + "epoch": 0.94, + "learning_rate": 2.0473645389249674e-07, + "loss": 0.4527, + "step": 10994 + }, + { + "epoch": 0.94, + "learning_rate": 2.0418087384536878e-07, + "loss": 0.4547, + "step": 10995 + }, + { + "epoch": 0.94, + "learning_rate": 2.0362604086830328e-07, + "loss": 0.442, + "step": 10996 + }, + { + "epoch": 0.94, + "learning_rate": 2.0307195500361532e-07, + "loss": 0.4553, + "step": 10997 + }, + { + "epoch": 0.94, + "learning_rate": 2.0251861629356108e-07, + "loss": 0.4639, + "step": 10998 + }, + { + "epoch": 0.94, + "learning_rate": 2.0196602478034012e-07, + "loss": 0.4334, + "step": 10999 + }, + { + "epoch": 0.94, + "learning_rate": 2.014141805060954e-07, + "loss": 0.4603, + "step": 11000 + }, + { + "epoch": 0.94, + "learning_rate": 2.0086308351291328e-07, + "loss": 0.4658, + "step": 11001 + }, + { + "epoch": 0.94, + "learning_rate": 2.0031273384282347e-07, + "loss": 0.4344, + "step": 11002 + }, + { + "epoch": 0.94, + "learning_rate": 1.9976313153779568e-07, + "loss": 0.4628, + "step": 11003 + }, + { + "epoch": 0.94, + "learning_rate": 1.9921427663974646e-07, + "loss": 0.4693, + "step": 11004 + }, + { + "epoch": 0.94, + "learning_rate": 1.986661691905345e-07, + "loss": 0.4587, + "step": 11005 + }, + { + "epoch": 0.94, + "learning_rate": 1.981188092319586e-07, + "loss": 0.4865, + "step": 11006 + }, + { + "epoch": 0.94, + "learning_rate": 1.9757219680576422e-07, + "loss": 0.4623, + "step": 11007 + }, + { + "epoch": 0.94, + "learning_rate": 1.9702633195363918e-07, + "loss": 0.4291, + "step": 11008 + }, + { + "epoch": 0.94, + "learning_rate": 1.9648121471721126e-07, + "loss": 0.46, + "step": 11009 + }, + { + "epoch": 0.94, + "learning_rate": 1.95936845138055e-07, + "loss": 0.4559, + "step": 11010 + }, + { + "epoch": 0.94, + "learning_rate": 1.9539322325768494e-07, + "loss": 0.4591, + "step": 11011 + }, + { + "epoch": 0.94, + "learning_rate": 1.9485034911756018e-07, + "loss": 0.4236, + "step": 11012 + }, + { + "epoch": 0.94, + "learning_rate": 1.9430822275908423e-07, + "loss": 0.4554, + "step": 11013 + }, + { + "epoch": 0.94, + "learning_rate": 1.937668442235996e-07, + "loss": 0.441, + "step": 11014 + }, + { + "epoch": 0.94, + "learning_rate": 1.9322621355239658e-07, + "loss": 0.4628, + "step": 11015 + }, + { + "epoch": 0.94, + "learning_rate": 1.9268633078670328e-07, + "loss": 0.4591, + "step": 11016 + }, + { + "epoch": 0.94, + "learning_rate": 1.921471959676957e-07, + "loss": 0.462, + "step": 11017 + }, + { + "epoch": 0.94, + "learning_rate": 1.9160880913648983e-07, + "loss": 0.4692, + "step": 11018 + }, + { + "epoch": 0.94, + "learning_rate": 1.910711703341439e-07, + "loss": 0.4639, + "step": 11019 + }, + { + "epoch": 0.94, + "learning_rate": 1.9053427960166183e-07, + "loss": 0.4549, + "step": 11020 + }, + { + "epoch": 0.94, + "learning_rate": 1.8999813697998858e-07, + "loss": 0.435, + "step": 11021 + }, + { + "epoch": 0.94, + "learning_rate": 1.8946274251001373e-07, + "loss": 0.4579, + "step": 11022 + }, + { + "epoch": 0.94, + "learning_rate": 1.889280962325668e-07, + "loss": 0.4396, + "step": 11023 + }, + { + "epoch": 0.94, + "learning_rate": 1.8839419818842408e-07, + "loss": 0.4506, + "step": 11024 + }, + { + "epoch": 0.94, + "learning_rate": 1.8786104841830188e-07, + "loss": 0.4461, + "step": 11025 + }, + { + "epoch": 0.94, + "learning_rate": 1.87328646962861e-07, + "loss": 0.463, + "step": 11026 + }, + { + "epoch": 0.94, + "learning_rate": 1.8679699386270457e-07, + "loss": 0.4612, + "step": 11027 + }, + { + "epoch": 0.94, + "learning_rate": 1.8626608915837675e-07, + "loss": 0.4457, + "step": 11028 + }, + { + "epoch": 0.94, + "learning_rate": 1.857359328903685e-07, + "loss": 0.4449, + "step": 11029 + }, + { + "epoch": 0.94, + "learning_rate": 1.8520652509911196e-07, + "loss": 0.4326, + "step": 11030 + }, + { + "epoch": 0.94, + "learning_rate": 1.8467786582498147e-07, + "loss": 0.4674, + "step": 11031 + }, + { + "epoch": 0.94, + "learning_rate": 1.841499551082937e-07, + "loss": 0.4605, + "step": 11032 + }, + { + "epoch": 0.94, + "learning_rate": 1.8362279298931197e-07, + "loss": 0.4382, + "step": 11033 + }, + { + "epoch": 0.94, + "learning_rate": 1.8309637950823632e-07, + "loss": 0.4566, + "step": 11034 + }, + { + "epoch": 0.94, + "learning_rate": 1.825707147052147e-07, + "loss": 0.459, + "step": 11035 + }, + { + "epoch": 0.94, + "learning_rate": 1.8204579862033945e-07, + "loss": 0.4591, + "step": 11036 + }, + { + "epoch": 0.94, + "learning_rate": 1.8152163129363854e-07, + "loss": 0.4548, + "step": 11037 + }, + { + "epoch": 0.94, + "learning_rate": 1.8099821276508888e-07, + "loss": 0.4586, + "step": 11038 + }, + { + "epoch": 0.94, + "learning_rate": 1.8047554307460967e-07, + "loss": 0.4338, + "step": 11039 + }, + { + "epoch": 0.94, + "learning_rate": 1.7995362226206014e-07, + "loss": 0.4548, + "step": 11040 + }, + { + "epoch": 0.94, + "learning_rate": 1.7943245036724512e-07, + "loss": 0.4346, + "step": 11041 + }, + { + "epoch": 0.94, + "learning_rate": 1.7891202742991165e-07, + "loss": 0.4554, + "step": 11042 + }, + { + "epoch": 0.94, + "learning_rate": 1.7839235348974692e-07, + "loss": 0.4458, + "step": 11043 + }, + { + "epoch": 0.94, + "learning_rate": 1.7787342858638589e-07, + "loss": 0.4568, + "step": 11044 + }, + { + "epoch": 0.94, + "learning_rate": 1.773552527594047e-07, + "loss": 0.4612, + "step": 11045 + }, + { + "epoch": 0.94, + "learning_rate": 1.7683782604831946e-07, + "loss": 0.4704, + "step": 11046 + }, + { + "epoch": 0.94, + "learning_rate": 1.7632114849259197e-07, + "loss": 0.4416, + "step": 11047 + }, + { + "epoch": 0.94, + "learning_rate": 1.7580522013162626e-07, + "loss": 0.4583, + "step": 11048 + }, + { + "epoch": 0.94, + "learning_rate": 1.7529004100476866e-07, + "loss": 0.4331, + "step": 11049 + }, + { + "epoch": 0.94, + "learning_rate": 1.747756111513099e-07, + "loss": 0.4574, + "step": 11050 + }, + { + "epoch": 0.94, + "learning_rate": 1.7426193061048313e-07, + "loss": 0.4417, + "step": 11051 + }, + { + "epoch": 0.94, + "learning_rate": 1.7374899942146139e-07, + "loss": 0.466, + "step": 11052 + }, + { + "epoch": 0.94, + "learning_rate": 1.7323681762336453e-07, + "loss": 0.4488, + "step": 11053 + }, + { + "epoch": 0.94, + "learning_rate": 1.7272538525525462e-07, + "loss": 0.4597, + "step": 11054 + }, + { + "epoch": 0.94, + "learning_rate": 1.722147023561338e-07, + "loss": 0.4388, + "step": 11055 + }, + { + "epoch": 0.94, + "learning_rate": 1.717047689649487e-07, + "loss": 0.4611, + "step": 11056 + }, + { + "epoch": 0.94, + "learning_rate": 1.7119558512059044e-07, + "loss": 0.4352, + "step": 11057 + }, + { + "epoch": 0.94, + "learning_rate": 1.7068715086189124e-07, + "loss": 0.4608, + "step": 11058 + }, + { + "epoch": 0.94, + "learning_rate": 1.701794662276257e-07, + "loss": 0.454, + "step": 11059 + }, + { + "epoch": 0.94, + "learning_rate": 1.6967253125651284e-07, + "loss": 0.4486, + "step": 11060 + }, + { + "epoch": 0.94, + "learning_rate": 1.6916634598721283e-07, + "loss": 0.4516, + "step": 11061 + }, + { + "epoch": 0.94, + "learning_rate": 1.6866091045832923e-07, + "loss": 0.4441, + "step": 11062 + }, + { + "epoch": 0.94, + "learning_rate": 1.6815622470841008e-07, + "loss": 0.4722, + "step": 11063 + }, + { + "epoch": 0.94, + "learning_rate": 1.6765228877594352e-07, + "loss": 0.4273, + "step": 11064 + }, + { + "epoch": 0.94, + "learning_rate": 1.6714910269936213e-07, + "loss": 0.4615, + "step": 11065 + }, + { + "epoch": 0.94, + "learning_rate": 1.6664666651704075e-07, + "loss": 0.4544, + "step": 11066 + }, + { + "epoch": 0.94, + "learning_rate": 1.6614498026729876e-07, + "loss": 0.4181, + "step": 11067 + }, + { + "epoch": 0.94, + "learning_rate": 1.656440439883944e-07, + "loss": 0.4683, + "step": 11068 + }, + { + "epoch": 0.94, + "learning_rate": 1.651438577185338e-07, + "loss": 0.457, + "step": 11069 + }, + { + "epoch": 0.94, + "learning_rate": 1.646444214958598e-07, + "loss": 0.4588, + "step": 11070 + }, + { + "epoch": 0.94, + "learning_rate": 1.6414573535846523e-07, + "loss": 0.4582, + "step": 11071 + }, + { + "epoch": 0.94, + "learning_rate": 1.636477993443808e-07, + "loss": 0.4614, + "step": 11072 + }, + { + "epoch": 0.94, + "learning_rate": 1.6315061349157946e-07, + "loss": 0.4429, + "step": 11073 + }, + { + "epoch": 0.94, + "learning_rate": 1.6265417783798087e-07, + "loss": 0.434, + "step": 11074 + }, + { + "epoch": 0.94, + "learning_rate": 1.6215849242144365e-07, + "loss": 0.4679, + "step": 11075 + }, + { + "epoch": 0.94, + "learning_rate": 1.61663557279772e-07, + "loss": 0.4637, + "step": 11076 + }, + { + "epoch": 0.94, + "learning_rate": 1.6116937245071018e-07, + "loss": 0.4559, + "step": 11077 + }, + { + "epoch": 0.94, + "learning_rate": 1.6067593797195025e-07, + "loss": 0.475, + "step": 11078 + }, + { + "epoch": 0.94, + "learning_rate": 1.6018325388111876e-07, + "loss": 0.4626, + "step": 11079 + }, + { + "epoch": 0.94, + "learning_rate": 1.5969132021579347e-07, + "loss": 0.4456, + "step": 11080 + }, + { + "epoch": 0.94, + "learning_rate": 1.5920013701349103e-07, + "loss": 0.4441, + "step": 11081 + }, + { + "epoch": 0.94, + "learning_rate": 1.587097043116681e-07, + "loss": 0.4634, + "step": 11082 + }, + { + "epoch": 0.95, + "learning_rate": 1.5822002214773035e-07, + "loss": 0.437, + "step": 11083 + }, + { + "epoch": 0.95, + "learning_rate": 1.5773109055902235e-07, + "loss": 0.4629, + "step": 11084 + }, + { + "epoch": 0.95, + "learning_rate": 1.5724290958283094e-07, + "loss": 0.4376, + "step": 11085 + }, + { + "epoch": 0.95, + "learning_rate": 1.5675547925638856e-07, + "loss": 0.4558, + "step": 11086 + }, + { + "epoch": 0.95, + "learning_rate": 1.562687996168677e-07, + "loss": 0.4587, + "step": 11087 + }, + { + "epoch": 0.95, + "learning_rate": 1.5578287070138308e-07, + "loss": 0.4498, + "step": 11088 + }, + { + "epoch": 0.95, + "learning_rate": 1.5529769254699512e-07, + "loss": 0.4503, + "step": 11089 + }, + { + "epoch": 0.95, + "learning_rate": 1.5481326519070638e-07, + "loss": 0.4405, + "step": 11090 + }, + { + "epoch": 0.95, + "learning_rate": 1.543295886694607e-07, + "loss": 0.4704, + "step": 11091 + }, + { + "epoch": 0.95, + "learning_rate": 1.5384666302014407e-07, + "loss": 0.4414, + "step": 11092 + }, + { + "epoch": 0.95, + "learning_rate": 1.5336448827958815e-07, + "loss": 0.4426, + "step": 11093 + }, + { + "epoch": 0.95, + "learning_rate": 1.5288306448456468e-07, + "loss": 0.4727, + "step": 11094 + }, + { + "epoch": 0.95, + "learning_rate": 1.5240239167178872e-07, + "loss": 0.48, + "step": 11095 + }, + { + "epoch": 0.95, + "learning_rate": 1.519224698779198e-07, + "loss": 0.4368, + "step": 11096 + }, + { + "epoch": 0.95, + "learning_rate": 1.5144329913955759e-07, + "loss": 0.463, + "step": 11097 + }, + { + "epoch": 0.95, + "learning_rate": 1.50964879493245e-07, + "loss": 0.4582, + "step": 11098 + }, + { + "epoch": 0.95, + "learning_rate": 1.504872109754696e-07, + "loss": 0.4312, + "step": 11099 + }, + { + "epoch": 0.95, + "learning_rate": 1.5001029362265996e-07, + "loss": 0.4585, + "step": 11100 + }, + { + "epoch": 0.95, + "learning_rate": 1.4953412747118813e-07, + "loss": 0.4355, + "step": 11101 + }, + { + "epoch": 0.95, + "learning_rate": 1.4905871255736838e-07, + "loss": 0.4648, + "step": 11102 + }, + { + "epoch": 0.95, + "learning_rate": 1.4858404891745616e-07, + "loss": 0.4411, + "step": 11103 + }, + { + "epoch": 0.95, + "learning_rate": 1.4811013658765471e-07, + "loss": 0.4465, + "step": 11104 + }, + { + "epoch": 0.95, + "learning_rate": 1.4763697560410406e-07, + "loss": 0.4731, + "step": 11105 + }, + { + "epoch": 0.95, + "learning_rate": 1.4716456600288975e-07, + "loss": 0.4523, + "step": 11106 + }, + { + "epoch": 0.95, + "learning_rate": 1.4669290782003963e-07, + "loss": 0.4483, + "step": 11107 + }, + { + "epoch": 0.95, + "learning_rate": 1.4622200109152495e-07, + "loss": 0.4605, + "step": 11108 + }, + { + "epoch": 0.95, + "learning_rate": 1.4575184585325918e-07, + "loss": 0.4506, + "step": 11109 + }, + { + "epoch": 0.95, + "learning_rate": 1.452824421410981e-07, + "loss": 0.4615, + "step": 11110 + }, + { + "epoch": 0.95, + "learning_rate": 1.4481378999083973e-07, + "loss": 0.4493, + "step": 11111 + }, + { + "epoch": 0.95, + "learning_rate": 1.4434588943822547e-07, + "loss": 0.4284, + "step": 11112 + }, + { + "epoch": 0.95, + "learning_rate": 1.4387874051894013e-07, + "loss": 0.4511, + "step": 11113 + }, + { + "epoch": 0.95, + "learning_rate": 1.4341234326861076e-07, + "loss": 0.4698, + "step": 11114 + }, + { + "epoch": 0.95, + "learning_rate": 1.4294669772280556e-07, + "loss": 0.4439, + "step": 11115 + }, + { + "epoch": 0.95, + "learning_rate": 1.4248180391703614e-07, + "loss": 0.4508, + "step": 11116 + }, + { + "epoch": 0.95, + "learning_rate": 1.420176618867597e-07, + "loss": 0.4403, + "step": 11117 + }, + { + "epoch": 0.95, + "learning_rate": 1.4155427166737123e-07, + "loss": 0.479, + "step": 11118 + }, + { + "epoch": 0.95, + "learning_rate": 1.410916332942125e-07, + "loss": 0.443, + "step": 11119 + }, + { + "epoch": 0.95, + "learning_rate": 1.4062974680256635e-07, + "loss": 0.46, + "step": 11120 + }, + { + "epoch": 0.95, + "learning_rate": 1.4016861222765576e-07, + "loss": 0.4518, + "step": 11121 + }, + { + "epoch": 0.95, + "learning_rate": 1.3970822960465035e-07, + "loss": 0.4201, + "step": 11122 + }, + { + "epoch": 0.95, + "learning_rate": 1.3924859896866206e-07, + "loss": 0.4475, + "step": 11123 + }, + { + "epoch": 0.95, + "learning_rate": 1.387897203547417e-07, + "loss": 0.4447, + "step": 11124 + }, + { + "epoch": 0.95, + "learning_rate": 1.3833159379788686e-07, + "loss": 0.4459, + "step": 11125 + }, + { + "epoch": 0.95, + "learning_rate": 1.3787421933303735e-07, + "loss": 0.4391, + "step": 11126 + }, + { + "epoch": 0.95, + "learning_rate": 1.3741759699507084e-07, + "loss": 0.4734, + "step": 11127 + }, + { + "epoch": 0.95, + "learning_rate": 1.3696172681881504e-07, + "loss": 0.435, + "step": 11128 + }, + { + "epoch": 0.95, + "learning_rate": 1.3650660883903545e-07, + "loss": 0.4521, + "step": 11129 + }, + { + "epoch": 0.95, + "learning_rate": 1.3605224309043873e-07, + "loss": 0.4717, + "step": 11130 + }, + { + "epoch": 0.95, + "learning_rate": 1.3559862960767944e-07, + "loss": 0.4448, + "step": 11131 + }, + { + "epoch": 0.95, + "learning_rate": 1.351457684253521e-07, + "loss": 0.4376, + "step": 11132 + }, + { + "epoch": 0.95, + "learning_rate": 1.346936595779924e-07, + "loss": 0.4508, + "step": 11133 + }, + { + "epoch": 0.95, + "learning_rate": 1.3424230310007946e-07, + "loss": 0.4451, + "step": 11134 + }, + { + "epoch": 0.95, + "learning_rate": 1.3379169902603796e-07, + "loss": 0.4569, + "step": 11135 + }, + { + "epoch": 0.95, + "learning_rate": 1.3334184739023147e-07, + "loss": 0.4518, + "step": 11136 + }, + { + "epoch": 0.95, + "learning_rate": 1.3289274822696818e-07, + "loss": 0.4577, + "step": 11137 + }, + { + "epoch": 0.95, + "learning_rate": 1.3244440157049733e-07, + "loss": 0.4355, + "step": 11138 + }, + { + "epoch": 0.95, + "learning_rate": 1.3199680745501265e-07, + "loss": 0.4519, + "step": 11139 + }, + { + "epoch": 0.95, + "learning_rate": 1.315499659146491e-07, + "loss": 0.4451, + "step": 11140 + }, + { + "epoch": 0.95, + "learning_rate": 1.3110387698348493e-07, + "loss": 0.4382, + "step": 11141 + }, + { + "epoch": 0.95, + "learning_rate": 1.3065854069553963e-07, + "loss": 0.4723, + "step": 11142 + }, + { + "epoch": 0.95, + "learning_rate": 1.3021395708477824e-07, + "loss": 0.4612, + "step": 11143 + }, + { + "epoch": 0.95, + "learning_rate": 1.2977012618510477e-07, + "loss": 0.4486, + "step": 11144 + }, + { + "epoch": 0.95, + "learning_rate": 1.2932704803036877e-07, + "loss": 0.4362, + "step": 11145 + }, + { + "epoch": 0.95, + "learning_rate": 1.2888472265436104e-07, + "loss": 0.4738, + "step": 11146 + }, + { + "epoch": 0.95, + "learning_rate": 1.2844315009081453e-07, + "loss": 0.459, + "step": 11147 + }, + { + "epoch": 0.95, + "learning_rate": 1.280023303734057e-07, + "loss": 0.46, + "step": 11148 + }, + { + "epoch": 0.95, + "learning_rate": 1.2756226353575428e-07, + "loss": 0.4405, + "step": 11149 + }, + { + "epoch": 0.95, + "learning_rate": 1.2712294961142125e-07, + "loss": 0.4577, + "step": 11150 + }, + { + "epoch": 0.95, + "learning_rate": 1.2668438863390975e-07, + "loss": 0.4326, + "step": 11151 + }, + { + "epoch": 0.95, + "learning_rate": 1.262465806366664e-07, + "loss": 0.4452, + "step": 11152 + }, + { + "epoch": 0.95, + "learning_rate": 1.2580952565308002e-07, + "loss": 0.4548, + "step": 11153 + }, + { + "epoch": 0.95, + "learning_rate": 1.2537322371648286e-07, + "loss": 0.4275, + "step": 11154 + }, + { + "epoch": 0.95, + "learning_rate": 1.249376748601494e-07, + "loss": 0.4595, + "step": 11155 + }, + { + "epoch": 0.95, + "learning_rate": 1.245028791172964e-07, + "loss": 0.4445, + "step": 11156 + }, + { + "epoch": 0.95, + "learning_rate": 1.2406883652108182e-07, + "loss": 0.4728, + "step": 11157 + }, + { + "epoch": 0.95, + "learning_rate": 1.2363554710460913e-07, + "loss": 0.4463, + "step": 11158 + }, + { + "epoch": 0.95, + "learning_rate": 1.2320301090092301e-07, + "loss": 0.45, + "step": 11159 + }, + { + "epoch": 0.95, + "learning_rate": 1.2277122794300822e-07, + "loss": 0.4638, + "step": 11160 + }, + { + "epoch": 0.95, + "learning_rate": 1.2234019826379618e-07, + "loss": 0.4349, + "step": 11161 + }, + { + "epoch": 0.95, + "learning_rate": 1.2190992189615836e-07, + "loss": 0.4557, + "step": 11162 + }, + { + "epoch": 0.95, + "learning_rate": 1.2148039887290963e-07, + "loss": 0.4634, + "step": 11163 + }, + { + "epoch": 0.95, + "learning_rate": 1.2105162922680823e-07, + "loss": 0.4286, + "step": 11164 + }, + { + "epoch": 0.95, + "learning_rate": 1.2062361299055247e-07, + "loss": 0.4577, + "step": 11165 + }, + { + "epoch": 0.95, + "learning_rate": 1.201963501967851e-07, + "loss": 0.4493, + "step": 11166 + }, + { + "epoch": 0.95, + "learning_rate": 1.1976984087809007e-07, + "loss": 0.4532, + "step": 11167 + }, + { + "epoch": 0.95, + "learning_rate": 1.19344085066998e-07, + "loss": 0.4614, + "step": 11168 + }, + { + "epoch": 0.95, + "learning_rate": 1.1891908279597519e-07, + "loss": 0.4585, + "step": 11169 + }, + { + "epoch": 0.95, + "learning_rate": 1.1849483409743457e-07, + "loss": 0.4547, + "step": 11170 + }, + { + "epoch": 0.95, + "learning_rate": 1.1807133900373246e-07, + "loss": 0.4472, + "step": 11171 + }, + { + "epoch": 0.95, + "learning_rate": 1.176485975471664e-07, + "loss": 0.4495, + "step": 11172 + }, + { + "epoch": 0.95, + "learning_rate": 1.1722660975997501e-07, + "loss": 0.4726, + "step": 11173 + }, + { + "epoch": 0.95, + "learning_rate": 1.1680537567434259e-07, + "loss": 0.4655, + "step": 11174 + }, + { + "epoch": 0.95, + "learning_rate": 1.1638489532239339e-07, + "loss": 0.4449, + "step": 11175 + }, + { + "epoch": 0.95, + "learning_rate": 1.1596516873619401e-07, + "loss": 0.456, + "step": 11176 + }, + { + "epoch": 0.95, + "learning_rate": 1.1554619594775663e-07, + "loss": 0.4299, + "step": 11177 + }, + { + "epoch": 0.95, + "learning_rate": 1.1512797698903122e-07, + "loss": 0.4617, + "step": 11178 + }, + { + "epoch": 0.95, + "learning_rate": 1.1471051189191562e-07, + "loss": 0.4518, + "step": 11179 + }, + { + "epoch": 0.95, + "learning_rate": 1.1429380068824547e-07, + "loss": 0.4374, + "step": 11180 + }, + { + "epoch": 0.95, + "learning_rate": 1.1387784340980201e-07, + "loss": 0.4468, + "step": 11181 + }, + { + "epoch": 0.95, + "learning_rate": 1.1346264008830765e-07, + "loss": 0.4498, + "step": 11182 + }, + { + "epoch": 0.95, + "learning_rate": 1.1304819075542706e-07, + "loss": 0.4418, + "step": 11183 + }, + { + "epoch": 0.95, + "learning_rate": 1.1263449544276938e-07, + "loss": 0.428, + "step": 11184 + }, + { + "epoch": 0.95, + "learning_rate": 1.1222155418188163e-07, + "loss": 0.4761, + "step": 11185 + }, + { + "epoch": 0.95, + "learning_rate": 1.118093670042597e-07, + "loss": 0.4554, + "step": 11186 + }, + { + "epoch": 0.95, + "learning_rate": 1.1139793394133736e-07, + "loss": 0.4336, + "step": 11187 + }, + { + "epoch": 0.95, + "learning_rate": 1.109872550244917e-07, + "loss": 0.4504, + "step": 11188 + }, + { + "epoch": 0.95, + "learning_rate": 1.1057733028504325e-07, + "loss": 0.457, + "step": 11189 + }, + { + "epoch": 0.95, + "learning_rate": 1.1016815975425587e-07, + "loss": 0.447, + "step": 11190 + }, + { + "epoch": 0.95, + "learning_rate": 1.097597434633324e-07, + "loss": 0.4383, + "step": 11191 + }, + { + "epoch": 0.95, + "learning_rate": 1.0935208144342125e-07, + "loss": 0.4527, + "step": 11192 + }, + { + "epoch": 0.95, + "learning_rate": 1.089451737256142e-07, + "loss": 0.4472, + "step": 11193 + }, + { + "epoch": 0.95, + "learning_rate": 1.0853902034093977e-07, + "loss": 0.4591, + "step": 11194 + }, + { + "epoch": 0.95, + "learning_rate": 1.0813362132037652e-07, + "loss": 0.4611, + "step": 11195 + }, + { + "epoch": 0.95, + "learning_rate": 1.0772897669484084e-07, + "loss": 0.4541, + "step": 11196 + }, + { + "epoch": 0.95, + "learning_rate": 1.0732508649519247e-07, + "loss": 0.4464, + "step": 11197 + }, + { + "epoch": 0.95, + "learning_rate": 1.0692195075223233e-07, + "loss": 0.463, + "step": 11198 + }, + { + "epoch": 0.95, + "learning_rate": 1.0651956949670805e-07, + "loss": 0.4446, + "step": 11199 + }, + { + "epoch": 0.95, + "learning_rate": 1.0611794275930398e-07, + "loss": 0.4544, + "step": 11200 + }, + { + "epoch": 0.96, + "learning_rate": 1.0571707057065229e-07, + "loss": 0.4527, + "step": 11201 + }, + { + "epoch": 0.96, + "learning_rate": 1.0531695296132515e-07, + "loss": 0.4584, + "step": 11202 + }, + { + "epoch": 0.96, + "learning_rate": 1.0491758996183487e-07, + "loss": 0.442, + "step": 11203 + }, + { + "epoch": 0.96, + "learning_rate": 1.045189816026393e-07, + "loss": 0.4488, + "step": 11204 + }, + { + "epoch": 0.96, + "learning_rate": 1.0412112791414075e-07, + "loss": 0.4419, + "step": 11205 + }, + { + "epoch": 0.96, + "learning_rate": 1.0372402892667721e-07, + "loss": 0.4535, + "step": 11206 + }, + { + "epoch": 0.96, + "learning_rate": 1.0332768467053556e-07, + "loss": 0.4299, + "step": 11207 + }, + { + "epoch": 0.96, + "learning_rate": 1.029320951759416e-07, + "loss": 0.4473, + "step": 11208 + }, + { + "epoch": 0.96, + "learning_rate": 1.0253726047306567e-07, + "loss": 0.4606, + "step": 11209 + }, + { + "epoch": 0.96, + "learning_rate": 1.0214318059201922e-07, + "loss": 0.453, + "step": 11210 + }, + { + "epoch": 0.96, + "learning_rate": 1.01749855562856e-07, + "loss": 0.4488, + "step": 11211 + }, + { + "epoch": 0.96, + "learning_rate": 1.0135728541557199e-07, + "loss": 0.448, + "step": 11212 + }, + { + "epoch": 0.96, + "learning_rate": 1.009654701801066e-07, + "loss": 0.4661, + "step": 11213 + }, + { + "epoch": 0.96, + "learning_rate": 1.005744098863437e-07, + "loss": 0.4439, + "step": 11214 + }, + { + "epoch": 0.96, + "learning_rate": 1.0018410456410388e-07, + "loss": 0.4469, + "step": 11215 + }, + { + "epoch": 0.96, + "learning_rate": 9.979455424315442e-08, + "loss": 0.4398, + "step": 11216 + }, + { + "epoch": 0.96, + "learning_rate": 9.940575895320492e-08, + "loss": 0.4658, + "step": 11217 + }, + { + "epoch": 0.96, + "learning_rate": 9.901771872390497e-08, + "loss": 0.4472, + "step": 11218 + }, + { + "epoch": 0.96, + "learning_rate": 9.863043358485092e-08, + "loss": 0.4364, + "step": 11219 + }, + { + "epoch": 0.96, + "learning_rate": 9.824390356557578e-08, + "loss": 0.4682, + "step": 11220 + }, + { + "epoch": 0.96, + "learning_rate": 9.785812869555933e-08, + "loss": 0.4421, + "step": 11221 + }, + { + "epoch": 0.96, + "learning_rate": 9.747310900422136e-08, + "loss": 0.4712, + "step": 11222 + }, + { + "epoch": 0.96, + "learning_rate": 9.708884452092837e-08, + "loss": 0.4265, + "step": 11223 + }, + { + "epoch": 0.96, + "learning_rate": 9.670533527498139e-08, + "loss": 0.4718, + "step": 11224 + }, + { + "epoch": 0.96, + "learning_rate": 9.632258129563144e-08, + "loss": 0.4537, + "step": 11225 + }, + { + "epoch": 0.96, + "learning_rate": 9.59405826120674e-08, + "loss": 0.4379, + "step": 11226 + }, + { + "epoch": 0.96, + "learning_rate": 9.555933925342265e-08, + "loss": 0.4574, + "step": 11227 + }, + { + "epoch": 0.96, + "learning_rate": 9.517885124877279e-08, + "loss": 0.465, + "step": 11228 + }, + { + "epoch": 0.96, + "learning_rate": 9.479911862713576e-08, + "loss": 0.4393, + "step": 11229 + }, + { + "epoch": 0.96, + "learning_rate": 9.442014141747058e-08, + "loss": 0.4452, + "step": 11230 + }, + { + "epoch": 0.96, + "learning_rate": 9.40419196486786e-08, + "loss": 0.4504, + "step": 11231 + }, + { + "epoch": 0.96, + "learning_rate": 9.366445334960783e-08, + "loss": 0.4456, + "step": 11232 + }, + { + "epoch": 0.96, + "learning_rate": 9.328774254904305e-08, + "loss": 0.4754, + "step": 11233 + }, + { + "epoch": 0.96, + "learning_rate": 9.29117872757146e-08, + "loss": 0.4671, + "step": 11234 + }, + { + "epoch": 0.96, + "learning_rate": 9.253658755829286e-08, + "loss": 0.4556, + "step": 11235 + }, + { + "epoch": 0.96, + "learning_rate": 9.216214342539387e-08, + "loss": 0.4667, + "step": 11236 + }, + { + "epoch": 0.96, + "learning_rate": 9.178845490557475e-08, + "loss": 0.4531, + "step": 11237 + }, + { + "epoch": 0.96, + "learning_rate": 9.141552202733272e-08, + "loss": 0.4503, + "step": 11238 + }, + { + "epoch": 0.96, + "learning_rate": 9.104334481911059e-08, + "loss": 0.4469, + "step": 11239 + }, + { + "epoch": 0.96, + "learning_rate": 9.067192330929009e-08, + "loss": 0.4632, + "step": 11240 + }, + { + "epoch": 0.96, + "learning_rate": 9.030125752620078e-08, + "loss": 0.4466, + "step": 11241 + }, + { + "epoch": 0.96, + "learning_rate": 8.993134749810895e-08, + "loss": 0.44, + "step": 11242 + }, + { + "epoch": 0.96, + "learning_rate": 8.956219325322535e-08, + "loss": 0.4614, + "step": 11243 + }, + { + "epoch": 0.96, + "learning_rate": 8.919379481970414e-08, + "loss": 0.4487, + "step": 11244 + }, + { + "epoch": 0.96, + "learning_rate": 8.88261522256395e-08, + "loss": 0.4312, + "step": 11245 + }, + { + "epoch": 0.96, + "learning_rate": 8.845926549907125e-08, + "loss": 0.4475, + "step": 11246 + }, + { + "epoch": 0.96, + "learning_rate": 8.809313466798031e-08, + "loss": 0.4507, + "step": 11247 + }, + { + "epoch": 0.96, + "learning_rate": 8.772775976028547e-08, + "loss": 0.4456, + "step": 11248 + }, + { + "epoch": 0.96, + "learning_rate": 8.736314080385444e-08, + "loss": 0.4361, + "step": 11249 + }, + { + "epoch": 0.96, + "learning_rate": 8.699927782649609e-08, + "loss": 0.4718, + "step": 11250 + }, + { + "epoch": 0.96, + "learning_rate": 8.66361708559571e-08, + "loss": 0.4512, + "step": 11251 + }, + { + "epoch": 0.96, + "learning_rate": 8.627381991993089e-08, + "loss": 0.4457, + "step": 11252 + }, + { + "epoch": 0.96, + "learning_rate": 8.591222504605201e-08, + "loss": 0.447, + "step": 11253 + }, + { + "epoch": 0.96, + "learning_rate": 8.555138626189619e-08, + "loss": 0.4401, + "step": 11254 + }, + { + "epoch": 0.96, + "learning_rate": 8.519130359498362e-08, + "loss": 0.4421, + "step": 11255 + }, + { + "epoch": 0.96, + "learning_rate": 8.483197707277568e-08, + "loss": 0.4638, + "step": 11256 + }, + { + "epoch": 0.96, + "learning_rate": 8.44734067226749e-08, + "loss": 0.4506, + "step": 11257 + }, + { + "epoch": 0.96, + "learning_rate": 8.411559257202828e-08, + "loss": 0.4484, + "step": 11258 + }, + { + "epoch": 0.96, + "learning_rate": 8.37585346481251e-08, + "loss": 0.4468, + "step": 11259 + }, + { + "epoch": 0.96, + "learning_rate": 8.340223297819472e-08, + "loss": 0.446, + "step": 11260 + }, + { + "epoch": 0.96, + "learning_rate": 8.304668758941093e-08, + "loss": 0.4385, + "step": 11261 + }, + { + "epoch": 0.96, + "learning_rate": 8.26918985088887e-08, + "loss": 0.4606, + "step": 11262 + }, + { + "epoch": 0.96, + "learning_rate": 8.233786576368418e-08, + "loss": 0.4508, + "step": 11263 + }, + { + "epoch": 0.96, + "learning_rate": 8.198458938080023e-08, + "loss": 0.4615, + "step": 11264 + }, + { + "epoch": 0.96, + "learning_rate": 8.16320693871786e-08, + "loss": 0.4301, + "step": 11265 + }, + { + "epoch": 0.96, + "learning_rate": 8.128030580970336e-08, + "loss": 0.4524, + "step": 11266 + }, + { + "epoch": 0.96, + "learning_rate": 8.092929867519972e-08, + "loss": 0.4583, + "step": 11267 + }, + { + "epoch": 0.96, + "learning_rate": 8.05790480104407e-08, + "loss": 0.4411, + "step": 11268 + }, + { + "epoch": 0.96, + "learning_rate": 8.022955384213493e-08, + "loss": 0.4482, + "step": 11269 + }, + { + "epoch": 0.96, + "learning_rate": 7.988081619693666e-08, + "loss": 0.4485, + "step": 11270 + }, + { + "epoch": 0.96, + "learning_rate": 7.95328351014435e-08, + "loss": 0.4305, + "step": 11271 + }, + { + "epoch": 0.96, + "learning_rate": 7.918561058219198e-08, + "loss": 0.45, + "step": 11272 + }, + { + "epoch": 0.96, + "learning_rate": 7.883914266566427e-08, + "loss": 0.4578, + "step": 11273 + }, + { + "epoch": 0.96, + "learning_rate": 7.849343137828369e-08, + "loss": 0.4372, + "step": 11274 + }, + { + "epoch": 0.96, + "learning_rate": 7.814847674641468e-08, + "loss": 0.4456, + "step": 11275 + }, + { + "epoch": 0.96, + "learning_rate": 7.78042787963662e-08, + "loss": 0.463, + "step": 11276 + }, + { + "epoch": 0.96, + "learning_rate": 7.746083755438616e-08, + "loss": 0.4815, + "step": 11277 + }, + { + "epoch": 0.96, + "learning_rate": 7.711815304666804e-08, + "loss": 0.418, + "step": 11278 + }, + { + "epoch": 0.96, + "learning_rate": 7.677622529934648e-08, + "loss": 0.4534, + "step": 11279 + }, + { + "epoch": 0.96, + "learning_rate": 7.643505433849952e-08, + "loss": 0.4446, + "step": 11280 + }, + { + "epoch": 0.96, + "learning_rate": 7.609464019014301e-08, + "loss": 0.4393, + "step": 11281 + }, + { + "epoch": 0.96, + "learning_rate": 7.575498288024174e-08, + "loss": 0.4612, + "step": 11282 + }, + { + "epoch": 0.96, + "learning_rate": 7.541608243469723e-08, + "loss": 0.4473, + "step": 11283 + }, + { + "epoch": 0.96, + "learning_rate": 7.507793887935655e-08, + "loss": 0.4308, + "step": 11284 + }, + { + "epoch": 0.96, + "learning_rate": 7.474055224000688e-08, + "loss": 0.4453, + "step": 11285 + }, + { + "epoch": 0.96, + "learning_rate": 7.440392254237983e-08, + "loss": 0.4487, + "step": 11286 + }, + { + "epoch": 0.96, + "learning_rate": 7.406804981214822e-08, + "loss": 0.4492, + "step": 11287 + }, + { + "epoch": 0.96, + "learning_rate": 7.373293407492598e-08, + "loss": 0.4785, + "step": 11288 + }, + { + "epoch": 0.96, + "learning_rate": 7.33985753562716e-08, + "loss": 0.4528, + "step": 11289 + }, + { + "epoch": 0.96, + "learning_rate": 7.306497368168352e-08, + "loss": 0.4499, + "step": 11290 + }, + { + "epoch": 0.96, + "learning_rate": 7.273212907660476e-08, + "loss": 0.4408, + "step": 11291 + }, + { + "epoch": 0.96, + "learning_rate": 7.240004156641944e-08, + "loss": 0.4683, + "step": 11292 + }, + { + "epoch": 0.96, + "learning_rate": 7.206871117645286e-08, + "loss": 0.451, + "step": 11293 + }, + { + "epoch": 0.96, + "learning_rate": 7.17381379319737e-08, + "loss": 0.4402, + "step": 11294 + }, + { + "epoch": 0.96, + "learning_rate": 7.140832185819402e-08, + "loss": 0.4633, + "step": 11295 + }, + { + "epoch": 0.96, + "learning_rate": 7.10792629802659e-08, + "loss": 0.4634, + "step": 11296 + }, + { + "epoch": 0.96, + "learning_rate": 7.075096132328597e-08, + "loss": 0.4277, + "step": 11297 + }, + { + "epoch": 0.96, + "learning_rate": 7.042341691229082e-08, + "loss": 0.4409, + "step": 11298 + }, + { + "epoch": 0.96, + "learning_rate": 7.00966297722605e-08, + "loss": 0.4445, + "step": 11299 + }, + { + "epoch": 0.96, + "learning_rate": 6.977059992811619e-08, + "loss": 0.4304, + "step": 11300 + }, + { + "epoch": 0.96, + "learning_rate": 6.944532740472464e-08, + "loss": 0.4406, + "step": 11301 + }, + { + "epoch": 0.96, + "learning_rate": 6.91208122268916e-08, + "loss": 0.461, + "step": 11302 + }, + { + "epoch": 0.96, + "learning_rate": 6.879705441936502e-08, + "loss": 0.4427, + "step": 11303 + }, + { + "epoch": 0.96, + "learning_rate": 6.847405400683626e-08, + "loss": 0.4481, + "step": 11304 + }, + { + "epoch": 0.96, + "learning_rate": 6.815181101393898e-08, + "loss": 0.4703, + "step": 11305 + }, + { + "epoch": 0.96, + "learning_rate": 6.783032546524904e-08, + "loss": 0.4439, + "step": 11306 + }, + { + "epoch": 0.96, + "learning_rate": 6.750959738528462e-08, + "loss": 0.4347, + "step": 11307 + }, + { + "epoch": 0.96, + "learning_rate": 6.718962679850504e-08, + "loss": 0.4556, + "step": 11308 + }, + { + "epoch": 0.96, + "learning_rate": 6.687041372931192e-08, + "loss": 0.4536, + "step": 11309 + }, + { + "epoch": 0.96, + "learning_rate": 6.65519582020513e-08, + "loss": 0.4418, + "step": 11310 + }, + { + "epoch": 0.96, + "learning_rate": 6.623426024100931e-08, + "loss": 0.5019, + "step": 11311 + }, + { + "epoch": 0.96, + "learning_rate": 6.591731987041439e-08, + "loss": 0.4575, + "step": 11312 + }, + { + "epoch": 0.96, + "learning_rate": 6.560113711443938e-08, + "loss": 0.4517, + "step": 11313 + }, + { + "epoch": 0.96, + "learning_rate": 6.528571199719502e-08, + "loss": 0.4495, + "step": 11314 + }, + { + "epoch": 0.96, + "learning_rate": 6.497104454273872e-08, + "loss": 0.4403, + "step": 11315 + }, + { + "epoch": 0.96, + "learning_rate": 6.465713477506907e-08, + "loss": 0.4417, + "step": 11316 + }, + { + "epoch": 0.96, + "learning_rate": 6.43439827181247e-08, + "loss": 0.4425, + "step": 11317 + }, + { + "epoch": 0.97, + "learning_rate": 6.403158839578761e-08, + "loss": 0.4616, + "step": 11318 + }, + { + "epoch": 0.97, + "learning_rate": 6.371995183188429e-08, + "loss": 0.4299, + "step": 11319 + }, + { + "epoch": 0.97, + "learning_rate": 6.340907305017907e-08, + "loss": 0.4372, + "step": 11320 + }, + { + "epoch": 0.97, + "learning_rate": 6.309895207438188e-08, + "loss": 0.4676, + "step": 11321 + }, + { + "epoch": 0.97, + "learning_rate": 6.27895889281438e-08, + "loss": 0.4622, + "step": 11322 + }, + { + "epoch": 0.97, + "learning_rate": 6.248098363505928e-08, + "loss": 0.4506, + "step": 11323 + }, + { + "epoch": 0.97, + "learning_rate": 6.217313621866283e-08, + "loss": 0.4437, + "step": 11324 + }, + { + "epoch": 0.97, + "learning_rate": 6.186604670243124e-08, + "loss": 0.4586, + "step": 11325 + }, + { + "epoch": 0.97, + "learning_rate": 6.155971510978576e-08, + "loss": 0.4371, + "step": 11326 + }, + { + "epoch": 0.97, + "learning_rate": 6.12541414640877e-08, + "loss": 0.4586, + "step": 11327 + }, + { + "epoch": 0.97, + "learning_rate": 6.094932578864288e-08, + "loss": 0.4687, + "step": 11328 + }, + { + "epoch": 0.97, + "learning_rate": 6.064526810669602e-08, + "loss": 0.4497, + "step": 11329 + }, + { + "epoch": 0.97, + "learning_rate": 6.034196844143747e-08, + "loss": 0.4482, + "step": 11330 + }, + { + "epoch": 0.97, + "learning_rate": 6.00394268159965e-08, + "loss": 0.4623, + "step": 11331 + }, + { + "epoch": 0.97, + "learning_rate": 5.973764325344689e-08, + "loss": 0.4709, + "step": 11332 + }, + { + "epoch": 0.97, + "learning_rate": 5.943661777680354e-08, + "loss": 0.4272, + "step": 11333 + }, + { + "epoch": 0.97, + "learning_rate": 5.9136350409024766e-08, + "loss": 0.4487, + "step": 11334 + }, + { + "epoch": 0.97, + "learning_rate": 5.8836841173011136e-08, + "loss": 0.4666, + "step": 11335 + }, + { + "epoch": 0.97, + "learning_rate": 5.8538090091601055e-08, + "loss": 0.444, + "step": 11336 + }, + { + "epoch": 0.97, + "learning_rate": 5.824009718758184e-08, + "loss": 0.4706, + "step": 11337 + }, + { + "epoch": 0.97, + "learning_rate": 5.794286248367753e-08, + "loss": 0.4514, + "step": 11338 + }, + { + "epoch": 0.97, + "learning_rate": 5.7646386002557784e-08, + "loss": 0.4505, + "step": 11339 + }, + { + "epoch": 0.97, + "learning_rate": 5.735066776683229e-08, + "loss": 0.4496, + "step": 11340 + }, + { + "epoch": 0.97, + "learning_rate": 5.705570779905523e-08, + "loss": 0.4572, + "step": 11341 + }, + { + "epoch": 0.97, + "learning_rate": 5.676150612171971e-08, + "loss": 0.487, + "step": 11342 + }, + { + "epoch": 0.97, + "learning_rate": 5.6468062757263356e-08, + "loss": 0.4567, + "step": 11343 + }, + { + "epoch": 0.97, + "learning_rate": 5.617537772806603e-08, + "loss": 0.4512, + "step": 11344 + }, + { + "epoch": 0.97, + "learning_rate": 5.588345105644766e-08, + "loss": 0.4546, + "step": 11345 + }, + { + "epoch": 0.97, + "learning_rate": 5.5592282764673766e-08, + "loss": 0.4449, + "step": 11346 + }, + { + "epoch": 0.97, + "learning_rate": 5.530187287494882e-08, + "loss": 0.4558, + "step": 11347 + }, + { + "epoch": 0.97, + "learning_rate": 5.501222140942064e-08, + "loss": 0.4627, + "step": 11348 + }, + { + "epoch": 0.97, + "learning_rate": 5.472332839017935e-08, + "loss": 0.4498, + "step": 11349 + }, + { + "epoch": 0.97, + "learning_rate": 5.443519383925844e-08, + "loss": 0.4537, + "step": 11350 + }, + { + "epoch": 0.97, + "learning_rate": 5.414781777863032e-08, + "loss": 0.4606, + "step": 11351 + }, + { + "epoch": 0.97, + "learning_rate": 5.386120023021191e-08, + "loss": 0.4359, + "step": 11352 + }, + { + "epoch": 0.97, + "learning_rate": 5.3575341215863496e-08, + "loss": 0.4658, + "step": 11353 + }, + { + "epoch": 0.97, + "learning_rate": 5.3290240757383205e-08, + "loss": 0.4535, + "step": 11354 + }, + { + "epoch": 0.97, + "learning_rate": 5.300589887651586e-08, + "loss": 0.4505, + "step": 11355 + }, + { + "epoch": 0.97, + "learning_rate": 5.272231559494634e-08, + "loss": 0.4474, + "step": 11356 + }, + { + "epoch": 0.97, + "learning_rate": 5.243949093430179e-08, + "loss": 0.4632, + "step": 11357 + }, + { + "epoch": 0.97, + "learning_rate": 5.215742491615161e-08, + "loss": 0.4455, + "step": 11358 + }, + { + "epoch": 0.97, + "learning_rate": 5.187611756200639e-08, + "loss": 0.4412, + "step": 11359 + }, + { + "epoch": 0.97, + "learning_rate": 5.159556889332118e-08, + "loss": 0.4553, + "step": 11360 + }, + { + "epoch": 0.97, + "learning_rate": 5.131577893149109e-08, + "loss": 0.4621, + "step": 11361 + }, + { + "epoch": 0.97, + "learning_rate": 5.103674769785461e-08, + "loss": 0.4581, + "step": 11362 + }, + { + "epoch": 0.97, + "learning_rate": 5.075847521369137e-08, + "loss": 0.4511, + "step": 11363 + }, + { + "epoch": 0.97, + "learning_rate": 5.0480961500223306e-08, + "loss": 0.441, + "step": 11364 + }, + { + "epoch": 0.97, + "learning_rate": 5.020420657861569e-08, + "loss": 0.4531, + "step": 11365 + }, + { + "epoch": 0.97, + "learning_rate": 4.992821046997387e-08, + "loss": 0.488, + "step": 11366 + }, + { + "epoch": 0.97, + "learning_rate": 4.9652973195346566e-08, + "loss": 0.4575, + "step": 11367 + }, + { + "epoch": 0.97, + "learning_rate": 4.937849477572587e-08, + "loss": 0.4494, + "step": 11368 + }, + { + "epoch": 0.97, + "learning_rate": 4.910477523204282e-08, + "loss": 0.4377, + "step": 11369 + }, + { + "epoch": 0.97, + "learning_rate": 4.883181458517405e-08, + "loss": 0.4389, + "step": 11370 + }, + { + "epoch": 0.97, + "learning_rate": 4.8559612855936244e-08, + "loss": 0.4448, + "step": 11371 + }, + { + "epoch": 0.97, + "learning_rate": 4.8288170065088344e-08, + "loss": 0.4432, + "step": 11372 + }, + { + "epoch": 0.97, + "learning_rate": 4.801748623333047e-08, + "loss": 0.4414, + "step": 11373 + }, + { + "epoch": 0.97, + "learning_rate": 4.774756138130831e-08, + "loss": 0.4683, + "step": 11374 + }, + { + "epoch": 0.97, + "learning_rate": 4.7478395529606537e-08, + "loss": 0.4321, + "step": 11375 + }, + { + "epoch": 0.97, + "learning_rate": 4.720998869875315e-08, + "loss": 0.4525, + "step": 11376 + }, + { + "epoch": 0.97, + "learning_rate": 4.694234090921734e-08, + "loss": 0.4621, + "step": 11377 + }, + { + "epoch": 0.97, + "learning_rate": 4.6675452181410566e-08, + "loss": 0.4497, + "step": 11378 + }, + { + "epoch": 0.97, + "learning_rate": 4.640932253568875e-08, + "loss": 0.4468, + "step": 11379 + }, + { + "epoch": 0.97, + "learning_rate": 4.6143951992346783e-08, + "loss": 0.4702, + "step": 11380 + }, + { + "epoch": 0.97, + "learning_rate": 4.587934057162402e-08, + "loss": 0.4394, + "step": 11381 + }, + { + "epoch": 0.97, + "learning_rate": 4.561548829369766e-08, + "loss": 0.4459, + "step": 11382 + }, + { + "epoch": 0.97, + "learning_rate": 4.535239517869494e-08, + "loss": 0.4444, + "step": 11383 + }, + { + "epoch": 0.97, + "learning_rate": 4.5090061246676474e-08, + "loss": 0.468, + "step": 11384 + }, + { + "epoch": 0.97, + "learning_rate": 4.4828486517650705e-08, + "loss": 0.4568, + "step": 11385 + }, + { + "epoch": 0.97, + "learning_rate": 4.4567671011567224e-08, + "loss": 0.4554, + "step": 11386 + }, + { + "epoch": 0.97, + "learning_rate": 4.4307614748313466e-08, + "loss": 0.4414, + "step": 11387 + }, + { + "epoch": 0.97, + "learning_rate": 4.404831774772689e-08, + "loss": 0.4517, + "step": 11388 + }, + { + "epoch": 0.97, + "learning_rate": 4.3789780029579456e-08, + "loss": 0.458, + "step": 11389 + }, + { + "epoch": 0.97, + "learning_rate": 4.353200161358984e-08, + "loss": 0.4534, + "step": 11390 + }, + { + "epoch": 0.97, + "learning_rate": 4.327498251941564e-08, + "loss": 0.4464, + "step": 11391 + }, + { + "epoch": 0.97, + "learning_rate": 4.3018722766661194e-08, + "loss": 0.467, + "step": 11392 + }, + { + "epoch": 0.97, + "learning_rate": 4.276322237486752e-08, + "loss": 0.449, + "step": 11393 + }, + { + "epoch": 0.97, + "learning_rate": 4.250848136352015e-08, + "loss": 0.4514, + "step": 11394 + }, + { + "epoch": 0.97, + "learning_rate": 4.225449975204798e-08, + "loss": 0.4452, + "step": 11395 + }, + { + "epoch": 0.97, + "learning_rate": 4.2001277559818864e-08, + "loss": 0.4699, + "step": 11396 + }, + { + "epoch": 0.97, + "learning_rate": 4.174881480614623e-08, + "loss": 0.4764, + "step": 11397 + }, + { + "epoch": 0.97, + "learning_rate": 4.1497111510283574e-08, + "loss": 0.4519, + "step": 11398 + }, + { + "epoch": 0.97, + "learning_rate": 4.124616769142664e-08, + "loss": 0.4725, + "step": 11399 + }, + { + "epoch": 0.97, + "learning_rate": 4.0995983368713465e-08, + "loss": 0.4514, + "step": 11400 + }, + { + "epoch": 0.97, + "learning_rate": 4.0746558561224336e-08, + "loss": 0.4356, + "step": 11401 + }, + { + "epoch": 0.97, + "learning_rate": 4.0497893287980706e-08, + "loss": 0.4488, + "step": 11402 + }, + { + "epoch": 0.97, + "learning_rate": 4.0249987567948514e-08, + "loss": 0.4629, + "step": 11403 + }, + { + "epoch": 0.97, + "learning_rate": 4.000284142003264e-08, + "loss": 0.4369, + "step": 11404 + }, + { + "epoch": 0.97, + "learning_rate": 3.975645486308133e-08, + "loss": 0.4763, + "step": 11405 + }, + { + "epoch": 0.97, + "learning_rate": 3.951082791588512e-08, + "loss": 0.4791, + "step": 11406 + }, + { + "epoch": 0.97, + "learning_rate": 3.926596059717791e-08, + "loss": 0.4393, + "step": 11407 + }, + { + "epoch": 0.97, + "learning_rate": 3.902185292563365e-08, + "loss": 0.4591, + "step": 11408 + }, + { + "epoch": 0.97, + "learning_rate": 3.877850491986746e-08, + "loss": 0.4368, + "step": 11409 + }, + { + "epoch": 0.97, + "learning_rate": 3.853591659844003e-08, + "loss": 0.4642, + "step": 11410 + }, + { + "epoch": 0.97, + "learning_rate": 3.8294087979852124e-08, + "loss": 0.4469, + "step": 11411 + }, + { + "epoch": 0.97, + "learning_rate": 3.805301908254455e-08, + "loss": 0.4641, + "step": 11412 + }, + { + "epoch": 0.97, + "learning_rate": 3.781270992490482e-08, + "loss": 0.4522, + "step": 11413 + }, + { + "epoch": 0.97, + "learning_rate": 3.757316052525828e-08, + "loss": 0.4226, + "step": 11414 + }, + { + "epoch": 0.97, + "learning_rate": 3.733437090187364e-08, + "loss": 0.4431, + "step": 11415 + }, + { + "epoch": 0.97, + "learning_rate": 3.7096341072964116e-08, + "loss": 0.4488, + "step": 11416 + }, + { + "epoch": 0.97, + "learning_rate": 3.685907105668074e-08, + "loss": 0.4381, + "step": 11417 + }, + { + "epoch": 0.97, + "learning_rate": 3.662256087111904e-08, + "loss": 0.4556, + "step": 11418 + }, + { + "epoch": 0.97, + "learning_rate": 3.638681053431792e-08, + "loss": 0.4551, + "step": 11419 + }, + { + "epoch": 0.97, + "learning_rate": 3.615182006425411e-08, + "loss": 0.4431, + "step": 11420 + }, + { + "epoch": 0.97, + "learning_rate": 3.591758947885105e-08, + "loss": 0.4543, + "step": 11421 + }, + { + "epoch": 0.97, + "learning_rate": 3.568411879597111e-08, + "loss": 0.4599, + "step": 11422 + }, + { + "epoch": 0.97, + "learning_rate": 3.5451408033420064e-08, + "loss": 0.4489, + "step": 11423 + }, + { + "epoch": 0.97, + "learning_rate": 3.521945720894593e-08, + "loss": 0.4438, + "step": 11424 + }, + { + "epoch": 0.97, + "learning_rate": 3.498826634023789e-08, + "loss": 0.4479, + "step": 11425 + }, + { + "epoch": 0.97, + "learning_rate": 3.475783544492628e-08, + "loss": 0.4671, + "step": 11426 + }, + { + "epoch": 0.97, + "learning_rate": 3.452816454058594e-08, + "loss": 0.4335, + "step": 11427 + }, + { + "epoch": 0.97, + "learning_rate": 3.429925364473285e-08, + "loss": 0.4873, + "step": 11428 + }, + { + "epoch": 0.97, + "learning_rate": 3.407110277482417e-08, + "loss": 0.4519, + "step": 11429 + }, + { + "epoch": 0.97, + "learning_rate": 3.3843711948259306e-08, + "loss": 0.4255, + "step": 11430 + }, + { + "epoch": 0.97, + "learning_rate": 3.361708118238105e-08, + "loss": 0.4789, + "step": 11431 + }, + { + "epoch": 0.97, + "learning_rate": 3.339121049447225e-08, + "loss": 0.4506, + "step": 11432 + }, + { + "epoch": 0.97, + "learning_rate": 3.316609990175912e-08, + "loss": 0.4532, + "step": 11433 + }, + { + "epoch": 0.97, + "learning_rate": 3.294174942140904e-08, + "loss": 0.448, + "step": 11434 + }, + { + "epoch": 0.98, + "learning_rate": 3.2718159070532774e-08, + "loss": 0.4515, + "step": 11435 + }, + { + "epoch": 0.98, + "learning_rate": 3.249532886618223e-08, + "loss": 0.4485, + "step": 11436 + }, + { + "epoch": 0.98, + "learning_rate": 3.227325882535048e-08, + "loss": 0.452, + "step": 11437 + }, + { + "epoch": 0.98, + "learning_rate": 3.205194896497399e-08, + "loss": 0.441, + "step": 11438 + }, + { + "epoch": 0.98, + "learning_rate": 3.1831399301931466e-08, + "loss": 0.4686, + "step": 11439 + }, + { + "epoch": 0.98, + "learning_rate": 3.161160985304168e-08, + "loss": 0.4663, + "step": 11440 + }, + { + "epoch": 0.98, + "learning_rate": 3.1392580635067896e-08, + "loss": 0.4492, + "step": 11441 + }, + { + "epoch": 0.98, + "learning_rate": 3.1174311664712297e-08, + "loss": 0.4634, + "step": 11442 + }, + { + "epoch": 0.98, + "learning_rate": 3.09568029586238e-08, + "loss": 0.4366, + "step": 11443 + }, + { + "epoch": 0.98, + "learning_rate": 3.074005453338802e-08, + "loss": 0.4534, + "step": 11444 + }, + { + "epoch": 0.98, + "learning_rate": 3.052406640553618e-08, + "loss": 0.4614, + "step": 11445 + }, + { + "epoch": 0.98, + "learning_rate": 3.030883859154066e-08, + "loss": 0.4393, + "step": 11446 + }, + { + "epoch": 0.98, + "learning_rate": 3.009437110781499e-08, + "loss": 0.4571, + "step": 11447 + }, + { + "epoch": 0.98, + "learning_rate": 2.988066397071609e-08, + "loss": 0.4846, + "step": 11448 + }, + { + "epoch": 0.98, + "learning_rate": 2.9667717196542045e-08, + "loss": 0.4759, + "step": 11449 + }, + { + "epoch": 0.98, + "learning_rate": 2.9455530801532073e-08, + "loss": 0.4343, + "step": 11450 + }, + { + "epoch": 0.98, + "learning_rate": 2.924410480186879e-08, + "loss": 0.4581, + "step": 11451 + }, + { + "epoch": 0.98, + "learning_rate": 2.903343921367707e-08, + "loss": 0.4656, + "step": 11452 + }, + { + "epoch": 0.98, + "learning_rate": 2.882353405302296e-08, + "loss": 0.4307, + "step": 11453 + }, + { + "epoch": 0.98, + "learning_rate": 2.861438933591476e-08, + "loss": 0.4506, + "step": 11454 + }, + { + "epoch": 0.98, + "learning_rate": 2.8406005078301934e-08, + "loss": 0.44, + "step": 11455 + }, + { + "epoch": 0.98, + "learning_rate": 2.8198381296078436e-08, + "loss": 0.4332, + "step": 11456 + }, + { + "epoch": 0.98, + "learning_rate": 2.7991518005076045e-08, + "loss": 0.443, + "step": 11457 + }, + { + "epoch": 0.98, + "learning_rate": 2.7785415221073254e-08, + "loss": 0.4388, + "step": 11458 + }, + { + "epoch": 0.98, + "learning_rate": 2.7580072959787484e-08, + "loss": 0.4453, + "step": 11459 + }, + { + "epoch": 0.98, + "learning_rate": 2.7375491236878438e-08, + "loss": 0.4398, + "step": 11460 + }, + { + "epoch": 0.98, + "learning_rate": 2.7171670067949186e-08, + "loss": 0.4432, + "step": 11461 + }, + { + "epoch": 0.98, + "learning_rate": 2.696860946854396e-08, + "loss": 0.4499, + "step": 11462 + }, + { + "epoch": 0.98, + "learning_rate": 2.6766309454148155e-08, + "loss": 0.4526, + "step": 11463 + }, + { + "epoch": 0.98, + "learning_rate": 2.6564770040190535e-08, + "loss": 0.4434, + "step": 11464 + }, + { + "epoch": 0.98, + "learning_rate": 2.636399124204214e-08, + "loss": 0.4684, + "step": 11465 + }, + { + "epoch": 0.98, + "learning_rate": 2.616397307501295e-08, + "loss": 0.4388, + "step": 11466 + }, + { + "epoch": 0.98, + "learning_rate": 2.5964715554360753e-08, + "loss": 0.4385, + "step": 11467 + }, + { + "epoch": 0.98, + "learning_rate": 2.5766218695277843e-08, + "loss": 0.4614, + "step": 11468 + }, + { + "epoch": 0.98, + "learning_rate": 2.5568482512905445e-08, + "loss": 0.4535, + "step": 11469 + }, + { + "epoch": 0.98, + "learning_rate": 2.5371507022322606e-08, + "loss": 0.4548, + "step": 11470 + }, + { + "epoch": 0.98, + "learning_rate": 2.5175292238550643e-08, + "loss": 0.4366, + "step": 11471 + }, + { + "epoch": 0.98, + "learning_rate": 2.497983817655536e-08, + "loss": 0.46, + "step": 11472 + }, + { + "epoch": 0.98, + "learning_rate": 2.4785144851241506e-08, + "loss": 0.4415, + "step": 11473 + }, + { + "epoch": 0.98, + "learning_rate": 2.45912122774572e-08, + "loss": 0.4594, + "step": 11474 + }, + { + "epoch": 0.98, + "learning_rate": 2.4398040469993943e-08, + "loss": 0.4707, + "step": 11475 + }, + { + "epoch": 0.98, + "learning_rate": 2.420562944358329e-08, + "loss": 0.4245, + "step": 11476 + }, + { + "epoch": 0.98, + "learning_rate": 2.4013979212899054e-08, + "loss": 0.4685, + "step": 11477 + }, + { + "epoch": 0.98, + "learning_rate": 2.3823089792556208e-08, + "loss": 0.4465, + "step": 11478 + }, + { + "epoch": 0.98, + "learning_rate": 2.3632961197115335e-08, + "loss": 0.4637, + "step": 11479 + }, + { + "epoch": 0.98, + "learning_rate": 2.344359344107372e-08, + "loss": 0.4351, + "step": 11480 + }, + { + "epoch": 0.98, + "learning_rate": 2.325498653887426e-08, + "loss": 0.4798, + "step": 11481 + }, + { + "epoch": 0.98, + "learning_rate": 2.3067140504902108e-08, + "loss": 0.4461, + "step": 11482 + }, + { + "epoch": 0.98, + "learning_rate": 2.2880055353482477e-08, + "loss": 0.4584, + "step": 11483 + }, + { + "epoch": 0.98, + "learning_rate": 2.269373109888173e-08, + "loss": 0.4725, + "step": 11484 + }, + { + "epoch": 0.98, + "learning_rate": 2.250816775531295e-08, + "loss": 0.4325, + "step": 11485 + }, + { + "epoch": 0.98, + "learning_rate": 2.2323365336924806e-08, + "loss": 0.4578, + "step": 11486 + }, + { + "epoch": 0.98, + "learning_rate": 2.21393238578127e-08, + "loss": 0.4339, + "step": 11487 + }, + { + "epoch": 0.98, + "learning_rate": 2.1956043332010957e-08, + "loss": 0.4603, + "step": 11488 + }, + { + "epoch": 0.98, + "learning_rate": 2.1773523773499506e-08, + "loss": 0.4561, + "step": 11489 + }, + { + "epoch": 0.98, + "learning_rate": 2.1591765196197213e-08, + "loss": 0.464, + "step": 11490 + }, + { + "epoch": 0.98, + "learning_rate": 2.1410767613965212e-08, + "loss": 0.446, + "step": 11491 + }, + { + "epoch": 0.98, + "learning_rate": 2.1230531040606904e-08, + "loss": 0.4361, + "step": 11492 + }, + { + "epoch": 0.98, + "learning_rate": 2.1051055489869076e-08, + "loss": 0.4447, + "step": 11493 + }, + { + "epoch": 0.98, + "learning_rate": 2.0872340975438555e-08, + "loss": 0.4606, + "step": 11494 + }, + { + "epoch": 0.98, + "learning_rate": 2.0694387510944436e-08, + "loss": 0.4579, + "step": 11495 + }, + { + "epoch": 0.98, + "learning_rate": 2.0517195109959197e-08, + "loss": 0.4596, + "step": 11496 + }, + { + "epoch": 0.98, + "learning_rate": 2.0340763785995366e-08, + "loss": 0.4613, + "step": 11497 + }, + { + "epoch": 0.98, + "learning_rate": 2.016509355250884e-08, + "loss": 0.4544, + "step": 11498 + }, + { + "epoch": 0.98, + "learning_rate": 1.9990184422897797e-08, + "loss": 0.4425, + "step": 11499 + }, + { + "epoch": 0.98, + "learning_rate": 1.981603641049934e-08, + "loss": 0.4645, + "step": 11500 + }, + { + "epoch": 0.98, + "learning_rate": 1.964264952859618e-08, + "loss": 0.4567, + "step": 11501 + }, + { + "epoch": 0.98, + "learning_rate": 1.9470023790411073e-08, + "loss": 0.4512, + "step": 11502 + }, + { + "epoch": 0.98, + "learning_rate": 1.9298159209110157e-08, + "loss": 0.4379, + "step": 11503 + }, + { + "epoch": 0.98, + "learning_rate": 1.9127055797799608e-08, + "loss": 0.4652, + "step": 11504 + }, + { + "epoch": 0.98, + "learning_rate": 1.8956713569527884e-08, + "loss": 0.4532, + "step": 11505 + }, + { + "epoch": 0.98, + "learning_rate": 1.878713253728792e-08, + "loss": 0.47, + "step": 11506 + }, + { + "epoch": 0.98, + "learning_rate": 1.8618312714010488e-08, + "loss": 0.4697, + "step": 11507 + }, + { + "epoch": 0.98, + "learning_rate": 1.8450254112571954e-08, + "loss": 0.4473, + "step": 11508 + }, + { + "epoch": 0.98, + "learning_rate": 1.8282956745789837e-08, + "loss": 0.4569, + "step": 11509 + }, + { + "epoch": 0.98, + "learning_rate": 1.8116420626420605e-08, + "loss": 0.4434, + "step": 11510 + }, + { + "epoch": 0.98, + "learning_rate": 1.795064576716632e-08, + "loss": 0.4273, + "step": 11511 + }, + { + "epoch": 0.98, + "learning_rate": 1.77856321806702e-08, + "loss": 0.4583, + "step": 11512 + }, + { + "epoch": 0.98, + "learning_rate": 1.762137987951551e-08, + "loss": 0.4556, + "step": 11513 + }, + { + "epoch": 0.98, + "learning_rate": 1.745788887623001e-08, + "loss": 0.4628, + "step": 11514 + }, + { + "epoch": 0.98, + "learning_rate": 1.7295159183281507e-08, + "loss": 0.4279, + "step": 11515 + }, + { + "epoch": 0.98, + "learning_rate": 1.713319081308118e-08, + "loss": 0.4825, + "step": 11516 + }, + { + "epoch": 0.98, + "learning_rate": 1.697198377798026e-08, + "loss": 0.455, + "step": 11517 + }, + { + "epoch": 0.98, + "learning_rate": 1.6811538090274472e-08, + "loss": 0.4757, + "step": 11518 + }, + { + "epoch": 0.98, + "learning_rate": 1.6651853762198467e-08, + "loss": 0.4298, + "step": 11519 + }, + { + "epoch": 0.98, + "learning_rate": 1.6492930805932505e-08, + "loss": 0.4409, + "step": 11520 + }, + { + "epoch": 0.98, + "learning_rate": 1.6334769233594673e-08, + "loss": 0.4511, + "step": 11521 + }, + { + "epoch": 0.98, + "learning_rate": 1.6177369057247537e-08, + "loss": 0.4518, + "step": 11522 + }, + { + "epoch": 0.98, + "learning_rate": 1.6020730288897056e-08, + "loss": 0.4378, + "step": 11523 + }, + { + "epoch": 0.98, + "learning_rate": 1.5864852940485896e-08, + "loss": 0.4359, + "step": 11524 + }, + { + "epoch": 0.98, + "learning_rate": 1.570973702390455e-08, + "loss": 0.4657, + "step": 11525 + }, + { + "epoch": 0.98, + "learning_rate": 1.5555382550981325e-08, + "loss": 0.4496, + "step": 11526 + }, + { + "epoch": 0.98, + "learning_rate": 1.540178953348792e-08, + "loss": 0.4538, + "step": 11527 + }, + { + "epoch": 0.98, + "learning_rate": 1.5248957983139412e-08, + "loss": 0.4363, + "step": 11528 + }, + { + "epoch": 0.98, + "learning_rate": 1.5096887911589808e-08, + "loss": 0.4537, + "step": 11529 + }, + { + "epoch": 0.98, + "learning_rate": 1.494557933043761e-08, + "loss": 0.4481, + "step": 11530 + }, + { + "epoch": 0.98, + "learning_rate": 1.4795032251222474e-08, + "loss": 0.4501, + "step": 11531 + }, + { + "epoch": 0.98, + "learning_rate": 1.4645246685424109e-08, + "loss": 0.4691, + "step": 11532 + }, + { + "epoch": 0.98, + "learning_rate": 1.4496222644467816e-08, + "loss": 0.4464, + "step": 11533 + }, + { + "epoch": 0.98, + "learning_rate": 1.4347960139716732e-08, + "loss": 0.4428, + "step": 11534 + }, + { + "epoch": 0.98, + "learning_rate": 1.4200459182479587e-08, + "loss": 0.4629, + "step": 11535 + }, + { + "epoch": 0.98, + "learning_rate": 1.405371978400516e-08, + "loss": 0.4537, + "step": 11536 + }, + { + "epoch": 0.98, + "learning_rate": 1.390774195548339e-08, + "loss": 0.4565, + "step": 11537 + }, + { + "epoch": 0.98, + "learning_rate": 1.3762525708048702e-08, + "loss": 0.4652, + "step": 11538 + }, + { + "epoch": 0.98, + "learning_rate": 1.3618071052774462e-08, + "loss": 0.4787, + "step": 11539 + }, + { + "epoch": 0.98, + "learning_rate": 1.3474378000678523e-08, + "loss": 0.4417, + "step": 11540 + }, + { + "epoch": 0.98, + "learning_rate": 1.3331446562718787e-08, + "loss": 0.4548, + "step": 11541 + }, + { + "epoch": 0.98, + "learning_rate": 1.3189276749795421e-08, + "loss": 0.4518, + "step": 11542 + }, + { + "epoch": 0.98, + "learning_rate": 1.3047868572751976e-08, + "loss": 0.4695, + "step": 11543 + }, + { + "epoch": 0.98, + "learning_rate": 1.2907222042373158e-08, + "loss": 0.4452, + "step": 11544 + }, + { + "epoch": 0.98, + "learning_rate": 1.276733716938372e-08, + "loss": 0.4442, + "step": 11545 + }, + { + "epoch": 0.98, + "learning_rate": 1.2628213964452907e-08, + "loss": 0.4648, + "step": 11546 + }, + { + "epoch": 0.98, + "learning_rate": 1.2489852438190008e-08, + "loss": 0.4426, + "step": 11547 + }, + { + "epoch": 0.98, + "learning_rate": 1.2352252601147696e-08, + "loss": 0.4638, + "step": 11548 + }, + { + "epoch": 0.98, + "learning_rate": 1.2215414463819797e-08, + "loss": 0.4325, + "step": 11549 + }, + { + "epoch": 0.98, + "learning_rate": 1.2079338036642407e-08, + "loss": 0.4557, + "step": 11550 + }, + { + "epoch": 0.98, + "learning_rate": 1.1944023329992782e-08, + "loss": 0.4608, + "step": 11551 + }, + { + "epoch": 0.98, + "learning_rate": 1.1809470354190444e-08, + "loss": 0.464, + "step": 11552 + }, + { + "epoch": 0.99, + "learning_rate": 1.1675679119498295e-08, + "loss": 0.4542, + "step": 11553 + }, + { + "epoch": 0.99, + "learning_rate": 1.1542649636118175e-08, + "loss": 0.4611, + "step": 11554 + }, + { + "epoch": 0.99, + "learning_rate": 1.1410381914196411e-08, + "loss": 0.4467, + "step": 11555 + }, + { + "epoch": 0.99, + "learning_rate": 1.127887596381938e-08, + "loss": 0.493, + "step": 11556 + }, + { + "epoch": 0.99, + "learning_rate": 1.1148131795017946e-08, + "loss": 0.4415, + "step": 11557 + }, + { + "epoch": 0.99, + "learning_rate": 1.1018149417761915e-08, + "loss": 0.4367, + "step": 11558 + }, + { + "epoch": 0.99, + "learning_rate": 1.0888928841963353e-08, + "loss": 0.4371, + "step": 11559 + }, + { + "epoch": 0.99, + "learning_rate": 1.0760470077479934e-08, + "loss": 0.4454, + "step": 11560 + }, + { + "epoch": 0.99, + "learning_rate": 1.0632773134106045e-08, + "loss": 0.462, + "step": 11561 + }, + { + "epoch": 0.99, + "learning_rate": 1.0505838021581671e-08, + "loss": 0.4712, + "step": 11562 + }, + { + "epoch": 0.99, + "learning_rate": 1.0379664749586849e-08, + "loss": 0.454, + "step": 11563 + }, + { + "epoch": 0.99, + "learning_rate": 1.025425332774388e-08, + "loss": 0.4302, + "step": 11564 + }, + { + "epoch": 0.99, + "learning_rate": 1.0129603765617334e-08, + "loss": 0.4546, + "step": 11565 + }, + { + "epoch": 0.99, + "learning_rate": 1.0005716072714055e-08, + "loss": 0.4564, + "step": 11566 + }, + { + "epoch": 0.99, + "learning_rate": 9.882590258482038e-09, + "loss": 0.4533, + "step": 11567 + }, + { + "epoch": 0.99, + "learning_rate": 9.760226332311551e-09, + "loss": 0.4576, + "step": 11568 + }, + { + "epoch": 0.99, + "learning_rate": 9.638624303532907e-09, + "loss": 0.4559, + "step": 11569 + }, + { + "epoch": 0.99, + "learning_rate": 9.517784181422018e-09, + "loss": 0.4399, + "step": 11570 + }, + { + "epoch": 0.99, + "learning_rate": 9.397705975193738e-09, + "loss": 0.4356, + "step": 11571 + }, + { + "epoch": 0.99, + "learning_rate": 9.278389694006296e-09, + "loss": 0.4514, + "step": 11572 + }, + { + "epoch": 0.99, + "learning_rate": 9.15983534695908e-09, + "loss": 0.4741, + "step": 11573 + }, + { + "epoch": 0.99, + "learning_rate": 9.042042943092632e-09, + "loss": 0.4435, + "step": 11574 + }, + { + "epoch": 0.99, + "learning_rate": 8.925012491390882e-09, + "loss": 0.44, + "step": 11575 + }, + { + "epoch": 0.99, + "learning_rate": 8.808744000780022e-09, + "loss": 0.4388, + "step": 11576 + }, + { + "epoch": 0.99, + "learning_rate": 8.693237480126293e-09, + "loss": 0.4401, + "step": 11577 + }, + { + "epoch": 0.99, + "learning_rate": 8.578492938238203e-09, + "loss": 0.4739, + "step": 11578 + }, + { + "epoch": 0.99, + "learning_rate": 8.464510383866531e-09, + "loss": 0.4705, + "step": 11579 + }, + { + "epoch": 0.99, + "learning_rate": 8.351289825705433e-09, + "loss": 0.4578, + "step": 11580 + }, + { + "epoch": 0.99, + "learning_rate": 8.238831272389114e-09, + "loss": 0.4639, + "step": 11581 + }, + { + "epoch": 0.99, + "learning_rate": 8.127134732494047e-09, + "loss": 0.4579, + "step": 11582 + }, + { + "epoch": 0.99, + "learning_rate": 8.016200214537861e-09, + "loss": 0.4433, + "step": 11583 + }, + { + "epoch": 0.99, + "learning_rate": 7.906027726981568e-09, + "loss": 0.4538, + "step": 11584 + }, + { + "epoch": 0.99, + "learning_rate": 7.796617278227336e-09, + "loss": 0.4653, + "step": 11585 + }, + { + "epoch": 0.99, + "learning_rate": 7.6879688766196e-09, + "loss": 0.4401, + "step": 11586 + }, + { + "epoch": 0.99, + "learning_rate": 7.580082530443955e-09, + "loss": 0.4625, + "step": 11587 + }, + { + "epoch": 0.99, + "learning_rate": 7.472958247928264e-09, + "loss": 0.4264, + "step": 11588 + }, + { + "epoch": 0.99, + "learning_rate": 7.3665960372415465e-09, + "loss": 0.4482, + "step": 11589 + }, + { + "epoch": 0.99, + "learning_rate": 7.260995906497314e-09, + "loss": 0.4698, + "step": 11590 + }, + { + "epoch": 0.99, + "learning_rate": 7.156157863746904e-09, + "loss": 0.4539, + "step": 11591 + }, + { + "epoch": 0.99, + "learning_rate": 7.052081916988362e-09, + "loss": 0.4491, + "step": 11592 + }, + { + "epoch": 0.99, + "learning_rate": 6.9487680741553435e-09, + "loss": 0.4394, + "step": 11593 + }, + { + "epoch": 0.99, + "learning_rate": 6.84621634313043e-09, + "loss": 0.4726, + "step": 11594 + }, + { + "epoch": 0.99, + "learning_rate": 6.7444267317329225e-09, + "loss": 0.4347, + "step": 11595 + }, + { + "epoch": 0.99, + "learning_rate": 6.643399247725502e-09, + "loss": 0.4399, + "step": 11596 + }, + { + "epoch": 0.99, + "learning_rate": 6.543133898814225e-09, + "loss": 0.4466, + "step": 11597 + }, + { + "epoch": 0.99, + "learning_rate": 6.4436306926451974e-09, + "loss": 0.451, + "step": 11598 + }, + { + "epoch": 0.99, + "learning_rate": 6.3448896368056845e-09, + "loss": 0.4532, + "step": 11599 + }, + { + "epoch": 0.99, + "learning_rate": 6.246910738827439e-09, + "loss": 0.4451, + "step": 11600 + }, + { + "epoch": 0.99, + "learning_rate": 6.149694006183371e-09, + "loss": 0.4546, + "step": 11601 + }, + { + "epoch": 0.99, + "learning_rate": 6.05323944628533e-09, + "loss": 0.4414, + "step": 11602 + }, + { + "epoch": 0.99, + "learning_rate": 5.957547066491875e-09, + "loss": 0.4581, + "step": 11603 + }, + { + "epoch": 0.99, + "learning_rate": 5.862616874099391e-09, + "loss": 0.4359, + "step": 11604 + }, + { + "epoch": 0.99, + "learning_rate": 5.768448876347643e-09, + "loss": 0.45, + "step": 11605 + }, + { + "epoch": 0.99, + "learning_rate": 5.675043080418663e-09, + "loss": 0.4553, + "step": 11606 + }, + { + "epoch": 0.99, + "learning_rate": 5.582399493436752e-09, + "loss": 0.4635, + "step": 11607 + }, + { + "epoch": 0.99, + "learning_rate": 5.49051812246515e-09, + "loss": 0.4439, + "step": 11608 + }, + { + "epoch": 0.99, + "learning_rate": 5.399398974513803e-09, + "loss": 0.4433, + "step": 11609 + }, + { + "epoch": 0.99, + "learning_rate": 5.309042056529379e-09, + "loss": 0.4442, + "step": 11610 + }, + { + "epoch": 0.99, + "learning_rate": 5.219447375405251e-09, + "loss": 0.4826, + "step": 11611 + }, + { + "epoch": 0.99, + "learning_rate": 5.130614937971512e-09, + "loss": 0.4446, + "step": 11612 + }, + { + "epoch": 0.99, + "learning_rate": 5.042544751006073e-09, + "loss": 0.4689, + "step": 11613 + }, + { + "epoch": 0.99, + "learning_rate": 4.955236821222453e-09, + "loss": 0.4461, + "step": 11614 + }, + { + "epoch": 0.99, + "learning_rate": 4.86869115528088e-09, + "loss": 0.476, + "step": 11615 + }, + { + "epoch": 0.99, + "learning_rate": 4.78290775978163e-09, + "loss": 0.4392, + "step": 11616 + }, + { + "epoch": 0.99, + "learning_rate": 4.697886641266136e-09, + "loss": 0.4493, + "step": 11617 + }, + { + "epoch": 0.99, + "learning_rate": 4.613627806220322e-09, + "loss": 0.4398, + "step": 11618 + }, + { + "epoch": 0.99, + "learning_rate": 4.530131261066828e-09, + "loss": 0.4755, + "step": 11619 + }, + { + "epoch": 0.99, + "learning_rate": 4.447397012177224e-09, + "loss": 0.477, + "step": 11620 + }, + { + "epoch": 0.99, + "learning_rate": 4.3654250658575755e-09, + "loss": 0.4464, + "step": 11621 + }, + { + "epoch": 0.99, + "learning_rate": 4.284215428361771e-09, + "loss": 0.4343, + "step": 11622 + }, + { + "epoch": 0.99, + "learning_rate": 4.203768105882633e-09, + "loss": 0.4555, + "step": 11623 + }, + { + "epoch": 0.99, + "learning_rate": 4.124083104555254e-09, + "loss": 0.4582, + "step": 11624 + }, + { + "epoch": 0.99, + "learning_rate": 4.045160430456996e-09, + "loss": 0.4418, + "step": 11625 + }, + { + "epoch": 0.99, + "learning_rate": 3.9670000896074865e-09, + "loss": 0.4666, + "step": 11626 + }, + { + "epoch": 0.99, + "learning_rate": 3.889602087965294e-09, + "loss": 0.4556, + "step": 11627 + }, + { + "epoch": 0.99, + "learning_rate": 3.812966431435694e-09, + "loss": 0.4434, + "step": 11628 + }, + { + "epoch": 0.99, + "learning_rate": 3.73709312586068e-09, + "loss": 0.4644, + "step": 11629 + }, + { + "epoch": 0.99, + "learning_rate": 3.6619821770289554e-09, + "loss": 0.4443, + "step": 11630 + }, + { + "epoch": 0.99, + "learning_rate": 3.58763359066816e-09, + "loss": 0.4694, + "step": 11631 + }, + { + "epoch": 0.99, + "learning_rate": 3.514047372448204e-09, + "loss": 0.4286, + "step": 11632 + }, + { + "epoch": 0.99, + "learning_rate": 3.441223527980153e-09, + "loss": 0.4465, + "step": 11633 + }, + { + "epoch": 0.99, + "learning_rate": 3.3691620628195643e-09, + "loss": 0.4393, + "step": 11634 + }, + { + "epoch": 0.99, + "learning_rate": 3.297862982460931e-09, + "loss": 0.4381, + "step": 11635 + }, + { + "epoch": 0.99, + "learning_rate": 3.2273262923432357e-09, + "loss": 0.4644, + "step": 11636 + }, + { + "epoch": 0.99, + "learning_rate": 3.157551997844399e-09, + "loss": 0.4604, + "step": 11637 + }, + { + "epoch": 0.99, + "learning_rate": 3.0885401042857197e-09, + "loss": 0.4753, + "step": 11638 + }, + { + "epoch": 0.99, + "learning_rate": 3.0202906169307654e-09, + "loss": 0.4458, + "step": 11639 + }, + { + "epoch": 0.99, + "learning_rate": 2.9528035409853715e-09, + "loss": 0.4519, + "step": 11640 + }, + { + "epoch": 0.99, + "learning_rate": 2.886078881595422e-09, + "loss": 0.4505, + "step": 11641 + }, + { + "epoch": 0.99, + "learning_rate": 2.820116643849069e-09, + "loss": 0.4583, + "step": 11642 + }, + { + "epoch": 0.99, + "learning_rate": 2.754916832777843e-09, + "loss": 0.4366, + "step": 11643 + }, + { + "epoch": 0.99, + "learning_rate": 2.690479453354433e-09, + "loss": 0.4553, + "step": 11644 + }, + { + "epoch": 0.99, + "learning_rate": 2.6268045104926867e-09, + "loss": 0.4566, + "step": 11645 + }, + { + "epoch": 0.99, + "learning_rate": 2.5638920090476082e-09, + "loss": 0.4567, + "step": 11646 + }, + { + "epoch": 0.99, + "learning_rate": 2.501741953818693e-09, + "loss": 0.44, + "step": 11647 + }, + { + "epoch": 0.99, + "learning_rate": 2.440354349545482e-09, + "loss": 0.4438, + "step": 11648 + }, + { + "epoch": 0.99, + "learning_rate": 2.379729200908676e-09, + "loss": 0.4527, + "step": 11649 + }, + { + "epoch": 0.99, + "learning_rate": 2.319866512533464e-09, + "loss": 0.4653, + "step": 11650 + }, + { + "epoch": 0.99, + "learning_rate": 2.2607662889839733e-09, + "loss": 0.4687, + "step": 11651 + }, + { + "epoch": 0.99, + "learning_rate": 2.2024285347677087e-09, + "loss": 0.4547, + "step": 11652 + }, + { + "epoch": 0.99, + "learning_rate": 2.1448532543333344e-09, + "loss": 0.4516, + "step": 11653 + }, + { + "epoch": 0.99, + "learning_rate": 2.0880404520728926e-09, + "loss": 0.438, + "step": 11654 + }, + { + "epoch": 0.99, + "learning_rate": 2.031990132318473e-09, + "loss": 0.4563, + "step": 11655 + }, + { + "epoch": 0.99, + "learning_rate": 1.9767022993444353e-09, + "loss": 0.4392, + "step": 11656 + }, + { + "epoch": 0.99, + "learning_rate": 1.9221769573674052e-09, + "loss": 0.4443, + "step": 11657 + }, + { + "epoch": 0.99, + "learning_rate": 1.8684141105462792e-09, + "loss": 0.4505, + "step": 11658 + }, + { + "epoch": 0.99, + "learning_rate": 1.8154137629811108e-09, + "loss": 0.4485, + "step": 11659 + }, + { + "epoch": 0.99, + "learning_rate": 1.7631759187131114e-09, + "loss": 0.4457, + "step": 11660 + }, + { + "epoch": 0.99, + "learning_rate": 1.7117005817268718e-09, + "loss": 0.4553, + "step": 11661 + }, + { + "epoch": 0.99, + "learning_rate": 1.6609877559481402e-09, + "loss": 0.4558, + "step": 11662 + }, + { + "epoch": 0.99, + "learning_rate": 1.6110374452438238e-09, + "loss": 0.4636, + "step": 11663 + }, + { + "epoch": 0.99, + "learning_rate": 1.5618496534242079e-09, + "loss": 0.4553, + "step": 11664 + }, + { + "epoch": 0.99, + "learning_rate": 1.5134243842396257e-09, + "loss": 0.4525, + "step": 11665 + }, + { + "epoch": 0.99, + "learning_rate": 1.4657616413837894e-09, + "loss": 0.4532, + "step": 11666 + }, + { + "epoch": 0.99, + "learning_rate": 1.4188614284926794e-09, + "loss": 0.4655, + "step": 11667 + }, + { + "epoch": 0.99, + "learning_rate": 1.3727237491412138e-09, + "loss": 0.4546, + "step": 11668 + }, + { + "epoch": 0.99, + "learning_rate": 1.3273486068487996e-09, + "loss": 0.4393, + "step": 11669 + }, + { + "epoch": 1.0, + "learning_rate": 1.282736005076002e-09, + "loss": 0.4357, + "step": 11670 + }, + { + "epoch": 1.0, + "learning_rate": 1.2388859472256542e-09, + "loss": 0.4524, + "step": 11671 + }, + { + "epoch": 1.0, + "learning_rate": 1.1957984366406384e-09, + "loss": 0.4656, + "step": 11672 + }, + { + "epoch": 1.0, + "learning_rate": 1.1534734766083245e-09, + "loss": 0.4608, + "step": 11673 + }, + { + "epoch": 1.0, + "learning_rate": 1.111911070356131e-09, + "loss": 0.4582, + "step": 11674 + }, + { + "epoch": 1.0, + "learning_rate": 1.0711112210526342e-09, + "loss": 0.4546, + "step": 11675 + }, + { + "epoch": 1.0, + "learning_rate": 1.03107393181201e-09, + "loss": 0.4452, + "step": 11676 + }, + { + "epoch": 1.0, + "learning_rate": 9.917992056851511e-10, + "loss": 0.4634, + "step": 11677 + }, + { + "epoch": 1.0, + "learning_rate": 9.532870456685494e-10, + "loss": 0.4379, + "step": 11678 + }, + { + "epoch": 1.0, + "learning_rate": 9.15537454698745e-10, + "loss": 0.4631, + "step": 11679 + }, + { + "epoch": 1.0, + "learning_rate": 8.785504356556562e-10, + "loss": 0.4501, + "step": 11680 + }, + { + "epoch": 1.0, + "learning_rate": 8.423259913592496e-10, + "loss": 0.4584, + "step": 11681 + }, + { + "epoch": 1.0, + "learning_rate": 8.068641245717601e-10, + "loss": 0.4568, + "step": 11682 + }, + { + "epoch": 1.0, + "learning_rate": 7.721648379988011e-10, + "loss": 0.4362, + "step": 11683 + }, + { + "epoch": 1.0, + "learning_rate": 7.38228134284924e-10, + "loss": 0.4551, + "step": 11684 + }, + { + "epoch": 1.0, + "learning_rate": 7.050540160202791e-10, + "loss": 0.4358, + "step": 11685 + }, + { + "epoch": 1.0, + "learning_rate": 6.726424857339542e-10, + "loss": 0.4388, + "step": 11686 + }, + { + "epoch": 1.0, + "learning_rate": 6.409935458984162e-10, + "loss": 0.4521, + "step": 11687 + }, + { + "epoch": 1.0, + "learning_rate": 6.101071989261798e-10, + "loss": 0.4582, + "step": 11688 + }, + { + "epoch": 1.0, + "learning_rate": 5.79983447173138e-10, + "loss": 0.4294, + "step": 11689 + }, + { + "epoch": 1.0, + "learning_rate": 5.506222929374527e-10, + "loss": 0.4372, + "step": 11690 + }, + { + "epoch": 1.0, + "learning_rate": 5.220237384573334e-10, + "loss": 0.4632, + "step": 11691 + }, + { + "epoch": 1.0, + "learning_rate": 4.941877859143684e-10, + "loss": 0.4312, + "step": 11692 + }, + { + "epoch": 1.0, + "learning_rate": 4.671144374313041e-10, + "loss": 0.4253, + "step": 11693 + }, + { + "epoch": 1.0, + "learning_rate": 4.408036950731553e-10, + "loss": 0.455, + "step": 11694 + }, + { + "epoch": 1.0, + "learning_rate": 4.1525556084609507e-10, + "loss": 0.4803, + "step": 11695 + }, + { + "epoch": 1.0, + "learning_rate": 3.9047003669856477e-10, + "loss": 0.434, + "step": 11696 + }, + { + "epoch": 1.0, + "learning_rate": 3.6644712452127416e-10, + "loss": 0.4729, + "step": 11697 + }, + { + "epoch": 1.0, + "learning_rate": 3.4318682614498113e-10, + "loss": 0.4624, + "step": 11698 + }, + { + "epoch": 1.0, + "learning_rate": 3.206891433449322e-10, + "loss": 0.4577, + "step": 11699 + }, + { + "epoch": 1.0, + "learning_rate": 2.9895407783753214e-10, + "loss": 0.4491, + "step": 11700 + }, + { + "epoch": 1.0, + "learning_rate": 2.7798163127812363e-10, + "loss": 0.4496, + "step": 11701 + }, + { + "epoch": 1.0, + "learning_rate": 2.577718052676481e-10, + "loss": 0.4709, + "step": 11702 + }, + { + "epoch": 1.0, + "learning_rate": 2.383246013482055e-10, + "loss": 0.4615, + "step": 11703 + }, + { + "epoch": 1.0, + "learning_rate": 2.1964002100083314e-10, + "loss": 0.4575, + "step": 11704 + }, + { + "epoch": 1.0, + "learning_rate": 2.0171806565216777e-10, + "loss": 0.4535, + "step": 11705 + }, + { + "epoch": 1.0, + "learning_rate": 1.8455873666778368e-10, + "loss": 0.4559, + "step": 11706 + }, + { + "epoch": 1.0, + "learning_rate": 1.6816203535663379e-10, + "loss": 0.4666, + "step": 11707 + }, + { + "epoch": 1.0, + "learning_rate": 1.5252796296993944e-10, + "loss": 0.4451, + "step": 11708 + }, + { + "epoch": 1.0, + "learning_rate": 1.3765652070008018e-10, + "loss": 0.4496, + "step": 11709 + }, + { + "epoch": 1.0, + "learning_rate": 1.235477096805937e-10, + "loss": 0.4415, + "step": 11710 + }, + { + "epoch": 1.0, + "learning_rate": 1.1020153098728615e-10, + "loss": 0.4597, + "step": 11711 + }, + { + "epoch": 1.0, + "learning_rate": 9.7617985638232e-11, + "loss": 0.4478, + "step": 11712 + }, + { + "epoch": 1.0, + "learning_rate": 8.579707459266396e-11, + "loss": 0.4584, + "step": 11713 + }, + { + "epoch": 1.0, + "learning_rate": 7.473879875319335e-11, + "loss": 0.4665, + "step": 11714 + }, + { + "epoch": 1.0, + "learning_rate": 6.444315896358966e-11, + "loss": 0.4562, + "step": 11715 + }, + { + "epoch": 1.0, + "learning_rate": 5.491015600656013e-11, + "loss": 0.4494, + "step": 11716 + }, + { + "epoch": 1.0, + "learning_rate": 4.6139790610411073e-11, + "loss": 0.4701, + "step": 11717 + }, + { + "epoch": 1.0, + "learning_rate": 3.8132063445717184e-11, + "loss": 0.4639, + "step": 11718 + }, + { + "epoch": 1.0, + "learning_rate": 3.088697512088068e-11, + "loss": 0.4618, + "step": 11719 + }, + { + "epoch": 1.0, + "learning_rate": 2.4404526188792633e-11, + "loss": 0.4717, + "step": 11720 + }, + { + "epoch": 1.0, + "learning_rate": 1.8684717144612506e-11, + "loss": 0.454, + "step": 11721 + }, + { + "epoch": 1.0, + "learning_rate": 1.3727548423547732e-11, + "loss": 0.4375, + "step": 11722 + }, + { + "epoch": 1.0, + "learning_rate": 9.53302040529458e-12, + "loss": 0.4485, + "step": 11723 + }, + { + "epoch": 1.0, + "learning_rate": 6.101133408487059e-12, + "loss": 0.4612, + "step": 11724 + }, + { + "epoch": 1.0, + "learning_rate": 3.4318876951378034e-12, + "loss": 0.4539, + "step": 11725 + }, + { + "epoch": 1.0, + "learning_rate": 1.5252834684176266e-12, + "loss": 0.4449, + "step": 11726 + }, + { + "epoch": 1.0, + "learning_rate": 3.8132087487596783e-13, + "loss": 0.4445, + "step": 11727 + }, + { + "epoch": 1.0, + "learning_rate": 0.0, + "loss": 0.4591, + "step": 11728 + }, + { + "epoch": 1.0, + "step": 11728, + "total_flos": 0.0, + "train_loss": 0.00880163661769679, + "train_runtime": 1404.9182, + "train_samples_per_second": 2137.167, + "train_steps_per_second": 8.348 + } + ], + "logging_steps": 1.0, + "max_steps": 11728, + "num_input_tokens_seen": 0, + "num_train_epochs": 1, + "save_steps": 100, + "total_flos": 0.0, + "train_batch_size": 16, + "trial_name": null, + "trial_params": null +} diff --git a/vision_tower/config.json b/vision_tower/config.json new file mode 100644 index 0000000000000000000000000000000000000000..958bd161f2f869fd2944c35a512be844a35d9488 --- /dev/null +++ b/vision_tower/config.json @@ -0,0 +1,19 @@ +{ + "_name_or_path": "/lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask_fast/vision_tower", + "architectures": [ + "SiglipVisionModel" + ], + "attention_dropout": 0.0, + "hidden_act": "gelu_pytorch_tanh", + "hidden_size": 1152, + "image_size": 384, + "intermediate_size": 4304, + "layer_norm_eps": 1e-06, + "model_type": "siglip_vision_model", + "num_attention_heads": 16, + "num_channels": 3, + "num_hidden_layers": 27, + "patch_size": 14, + "torch_dtype": "bfloat16", + "transformers_version": "4.36.2" +} diff --git a/vision_tower/model.safetensors b/vision_tower/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ed3e953f9e149213d5914d49cee50586aa81e856 --- /dev/null +++ b/vision_tower/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38649b10f84ddb2d4e4d797396f8028f2a50dac0e384070e3d3953226416fd04 +size 856506120 diff --git a/vision_tower/preprocessor_config.json b/vision_tower/preprocessor_config.json new file mode 100644 index 0000000000000000000000000000000000000000..0f13134ed29056f82f3ab7e0246f0ab973e7ecf3 --- /dev/null +++ b/vision_tower/preprocessor_config.json @@ -0,0 +1,24 @@ +{ + "do_convert_rgb": true, + "do_normalize": true, + "do_rescale": true, + "do_resize": true, + "image_mean": [ + 0.5, + 0.5, + 0.5 + ], + "image_processor_type": "SiglipImageProcessor", + "image_std": [ + 0.5, + 0.5, + 0.5 + ], + "processor_class": "SiglipProcessor", + "resample": 3, + "rescale_factor": 0.00392156862745098, + "size": { + "height": 384, + "width": 384 + } +}