diff --git a/checkpoint-11900/config.json b/checkpoint-11900/config.json new file mode 100644 index 0000000000000000000000000000000000000000..44297312cc29516aa24d174765d6093fc1fdeeb7 --- /dev/null +++ b/checkpoint-11900/config.json @@ -0,0 +1,253 @@ +{ + "_name_or_path": "/lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-11900", + "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/tmp-checkpoint-11900/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/tmp-checkpoint-11900/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/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/tmp-checkpoint-11900/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-11900/global_step11900/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/checkpoint-11900/global_step11900/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..425e01cb99551b4b9242bbfffe5042e4dab9f090 --- /dev/null +++ b/checkpoint-11900/global_step11900/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:e16feb908e83de7948f133af315081b18bc8661dd5680b1e830476d0132938bf +size 4722230103 diff --git a/checkpoint-11900/global_step11900/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/checkpoint-11900/global_step11900/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..4c8f0ff2164ad980580ffe252e3cefbcd1bf0dfa --- /dev/null +++ b/checkpoint-11900/global_step11900/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47f14a70e8c8f21d0ead644dc2d1cb465a729b710c8ca139a61e11289085130c +size 4722230103 diff --git a/checkpoint-11900/global_step11900/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt b/checkpoint-11900/global_step11900/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..17e7dcfcda311fe98e1e51b3435d6f03eb547922 --- /dev/null +++ b/checkpoint-11900/global_step11900/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:b282117719e06098acdff5535759074c2b41b2a077fb455987c6ed61fc9aad75 +size 4722230103 diff --git a/checkpoint-11900/global_step11900/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt b/checkpoint-11900/global_step11900/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..36eb27147341acf850188f3d9d1efbf6e525d251 --- /dev/null +++ b/checkpoint-11900/global_step11900/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:b488f8196b3ca11647334633206edd0918a60f48dcdb0adf8d958244e42d9764 +size 4722230103 diff --git a/checkpoint-11900/global_step11900/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt b/checkpoint-11900/global_step11900/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1e9b02b88519cfa1a619da0d3cb55064b5904778 --- /dev/null +++ b/checkpoint-11900/global_step11900/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e3c7119bbcb3e948f801d52390d1d2a67b67cc0f2841a9d86e096754e834c53 +size 4722230103 diff --git a/checkpoint-11900/global_step11900/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt b/checkpoint-11900/global_step11900/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..e1ff23a8c76e111a75c3204f5ec2b5119a620cb0 --- /dev/null +++ b/checkpoint-11900/global_step11900/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:545bdd1c243aa362e78a2a61f5de3dcc530fdff06c1118dbe4fbd10186885b60 +size 4722230103 diff --git a/checkpoint-11900/global_step11900/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt b/checkpoint-11900/global_step11900/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ff9a4fbced98368c5a676a0cf373217ba9ef387e --- /dev/null +++ b/checkpoint-11900/global_step11900/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d341406942df99af515cfebd48e33ef83aebdac5a39934d1b01790b5ea2dc5b +size 4722230103 diff --git a/checkpoint-11900/global_step11900/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt b/checkpoint-11900/global_step11900/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..b90437d89555912d0871c8d91895f71434098634 --- /dev/null +++ b/checkpoint-11900/global_step11900/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:e808100a2bf9ffd60a778770bb2832bf1f3c67829a45f22b8416d2bf11c24462 +size 4722230103 diff --git a/checkpoint-11900/global_step11900/zero_pp_rank_0_mp_rank_00_model_states.pt b/checkpoint-11900/global_step11900/zero_pp_rank_0_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d23a9c0faee750ecbd1e5f96f3b820a4ee8bd736 --- /dev/null +++ b/checkpoint-11900/global_step11900/zero_pp_rank_0_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91d2be6c9218d48dac0fec2185b29da65a9348cdbe10390090c15b3b1249dcbe +size 413988 diff --git a/checkpoint-11900/global_step11900/zero_pp_rank_1_mp_rank_00_model_states.pt b/checkpoint-11900/global_step11900/zero_pp_rank_1_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..1b7db38e4a4b68e4779b0e8171cdf7903415d8ca --- /dev/null +++ b/checkpoint-11900/global_step11900/zero_pp_rank_1_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cddafad2e5d10a8340d15d2011546e4f9072eeba09f5ae4bd5ed3a8220d5e260 +size 413988 diff --git a/checkpoint-11900/global_step11900/zero_pp_rank_2_mp_rank_00_model_states.pt b/checkpoint-11900/global_step11900/zero_pp_rank_2_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..f7d4e0eadea258624503866f4b074903142ca910 --- /dev/null +++ b/checkpoint-11900/global_step11900/zero_pp_rank_2_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:610cc1d7f0a0c8bf0ad12cc381bc428be3d85fe7313a39d0f55a105c8ff7a71a +size 413988 diff --git a/checkpoint-11900/global_step11900/zero_pp_rank_3_mp_rank_00_model_states.pt b/checkpoint-11900/global_step11900/zero_pp_rank_3_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..ae21867ce7504b937df3d823ca286c0057e84c33 --- /dev/null +++ b/checkpoint-11900/global_step11900/zero_pp_rank_3_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d67159e213a62e2864f2ba8086ef0d2b52489712a50b57526c5f76a4c039d30a +size 413988 diff --git a/checkpoint-11900/global_step11900/zero_pp_rank_4_mp_rank_00_model_states.pt b/checkpoint-11900/global_step11900/zero_pp_rank_4_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d5fe514e495855c1a1fef2ef108ae61138774bab --- /dev/null +++ b/checkpoint-11900/global_step11900/zero_pp_rank_4_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f9524f78cfd7a20009ec30e55152d38cbc93cf6630b88c4ca5342d57d0802f3 +size 413988 diff --git a/checkpoint-11900/global_step11900/zero_pp_rank_5_mp_rank_00_model_states.pt b/checkpoint-11900/global_step11900/zero_pp_rank_5_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..d695fa9e152d67f0e5f28c7db288e8fd4cbae8ae --- /dev/null +++ b/checkpoint-11900/global_step11900/zero_pp_rank_5_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64c19b85f0bdb37f7a9ed93ea10bce8392a3964700d7a1b5f8dd3dc2dfece17c +size 413988 diff --git a/checkpoint-11900/global_step11900/zero_pp_rank_6_mp_rank_00_model_states.pt b/checkpoint-11900/global_step11900/zero_pp_rank_6_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2c46463b9b78d38324103b1db824cd43e0688355 --- /dev/null +++ b/checkpoint-11900/global_step11900/zero_pp_rank_6_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5fc2fca47cff61908821663d681977d83f5ccf6242b8741665efe0baff6979f +size 413988 diff --git a/checkpoint-11900/global_step11900/zero_pp_rank_7_mp_rank_00_model_states.pt b/checkpoint-11900/global_step11900/zero_pp_rank_7_mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..85ac1d8b2a84c4f6285bd758521e283a2e96ec0e --- /dev/null +++ b/checkpoint-11900/global_step11900/zero_pp_rank_7_mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:789e3ee152ac13aa2e8902b45d36a27aa774930a78ca0a9eadf6aad458d160fb +size 413988 diff --git a/checkpoint-11900/latest b/checkpoint-11900/latest new file mode 100644 index 0000000000000000000000000000000000000000..04f241ff9e03d5551095c3acbf6a446bf647c694 --- /dev/null +++ b/checkpoint-11900/latest @@ -0,0 +1 @@ +global_step11900 \ No newline at end of file diff --git a/checkpoint-11900/llm/config.json b/checkpoint-11900/llm/config.json new file mode 100644 index 0000000000000000000000000000000000000000..cc0aa92bd96efcdcc640e1ffca5fafc2d352c9b7 --- /dev/null +++ b/checkpoint-11900/llm/config.json @@ -0,0 +1,32 @@ +{ + "_name_or_path": "/lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-11900/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-11900/llm/generation_config.json b/checkpoint-11900/llm/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..bf84ec1a28ba89feb07162d95b06633a40b4975f --- /dev/null +++ b/checkpoint-11900/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-11900/llm/model-00001-of-00002.safetensors b/checkpoint-11900/llm/model-00001-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bf97f1d77bde1530d166322e24d17e294e368697 --- /dev/null +++ b/checkpoint-11900/llm/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:160cdacee1c8bd833184e358926133805fc11c976741a25f7b8809c433852af2 +size 4974521464 diff --git a/checkpoint-11900/llm/model-00002-of-00002.safetensors b/checkpoint-11900/llm/model-00002-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9c241ca2b12e0aeb2ee2b926551e0b2e30ced259 --- /dev/null +++ b/checkpoint-11900/llm/model-00002-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5174749cbe7d2efb6ba225ccb6cc6f419cb674a7b94db949a828fb5bb9a3c13 +size 428632856 diff --git a/checkpoint-11900/llm/model.safetensors.index.json b/checkpoint-11900/llm/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..8b173c9ac8194749df58c92051618c0ff74c4c20 --- /dev/null +++ b/checkpoint-11900/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-11900/llm/special_tokens_map.json b/checkpoint-11900/llm/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..14761dcf1466dc232bd41de9c21d4c617b15755e --- /dev/null +++ b/checkpoint-11900/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-11900/llm/tokenizer.model b/checkpoint-11900/llm/tokenizer.model new file mode 100644 index 0000000000000000000000000000000000000000..3b7eab905db502ae7629c8a3c1f8412a3178c4c2 --- /dev/null +++ b/checkpoint-11900/llm/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7aedb3582ecda9fa99ee9242c17a9658f6744db083ee6ebdc8fb14857f84d220 +size 499723 diff --git a/checkpoint-11900/llm/tokenizer_config.json b/checkpoint-11900/llm/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..47ab96cd62cc374653a0ea0fb77f9457e0f53481 --- /dev/null +++ b/checkpoint-11900/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-11900/mm_projector/config.json b/checkpoint-11900/mm_projector/config.json new file mode 100644 index 0000000000000000000000000000000000000000..42234ef77e0036c1e92d4914bd9fdbd8d693af72 --- /dev/null +++ b/checkpoint-11900/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/tmp-checkpoint-11900/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-11900/mm_projector/model.safetensors b/checkpoint-11900/mm_projector/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..25b51569f448053ddac96daae2aa1eae0aa9086d --- /dev/null +++ b/checkpoint-11900/mm_projector/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea87319d485227b1679d459a29bf423078274ed9cc4c6a6d68efe6ccdae02892 +size 36729360 diff --git a/checkpoint-11900/rng_state_0.pth b/checkpoint-11900/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..fc929e783118d90d60e8ed23a46ed17d58f070a7 --- /dev/null +++ b/checkpoint-11900/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfee7792e373bc4f2e2c6a05b8fd239a8934a9e750f2bcb4d6a752c83a95e675 +size 21687 diff --git a/checkpoint-11900/rng_state_1.pth b/checkpoint-11900/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..2455787246d278a41af027b4821a0a9980a8b12b --- /dev/null +++ b/checkpoint-11900/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b124f629d2d70a74af545b007dc89569ebceccf6661ebfc4f9567210ac6c701f +size 21687 diff --git a/checkpoint-11900/rng_state_2.pth b/checkpoint-11900/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..81a8b247a877cc71fda42daafa5efbd12e3b93c9 --- /dev/null +++ b/checkpoint-11900/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a668a0848f7bbb499d74db45fa777942e8f6c92c1e0f6c5c5a5aa5079964201 +size 21687 diff --git a/checkpoint-11900/rng_state_3.pth b/checkpoint-11900/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..97c06b34543e1fc12f6627d498b838df13f99dfb --- /dev/null +++ b/checkpoint-11900/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2b8f85cc2d9b5264be911136a09181bdc6a1e9d691e4fc913ff930cea6c86e5 +size 21687 diff --git a/checkpoint-11900/rng_state_4.pth b/checkpoint-11900/rng_state_4.pth new file mode 100644 index 0000000000000000000000000000000000000000..eccc1ec3663f5ee2897e99ac8ecc03c5a773f134 --- /dev/null +++ b/checkpoint-11900/rng_state_4.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aee5ccac64db6c38edc9d752999c3cf6df4f1b7442b1689bb111a672cf858653 +size 21687 diff --git a/checkpoint-11900/rng_state_5.pth b/checkpoint-11900/rng_state_5.pth new file mode 100644 index 0000000000000000000000000000000000000000..427917369058a4a6217b643e2abe65f1a7c8f6ff --- /dev/null +++ b/checkpoint-11900/rng_state_5.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d160edeace5cc4d3b8b0e1fea79e623657eb5bd2ec0977ae41a7f1ec8dc3c10 +size 21687 diff --git a/checkpoint-11900/rng_state_6.pth b/checkpoint-11900/rng_state_6.pth new file mode 100644 index 0000000000000000000000000000000000000000..e33f2aa30eb2375dbeed5d967b3bf87415e54967 --- /dev/null +++ b/checkpoint-11900/rng_state_6.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:244880196327bb05a163dd9bf21e2a97f6a437c92938bd5bc03b14460357eeee +size 21687 diff --git a/checkpoint-11900/rng_state_7.pth b/checkpoint-11900/rng_state_7.pth new file mode 100644 index 0000000000000000000000000000000000000000..51da94e98244271d7616e419f761c11794738a28 --- /dev/null +++ b/checkpoint-11900/rng_state_7.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d666b54fef8eb195b33afa8e4bd98bbc865a31733c80760a0946ed7cf5b3e35b +size 21687 diff --git a/checkpoint-11900/scheduler.pt b/checkpoint-11900/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..e2bcb05422911e6f087890cdf68f750fb8b0cda7 --- /dev/null +++ b/checkpoint-11900/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d47fb793bad63d37c1e3d1579743f720fa29687663792556cf7fc9d78ac3de8 +size 627 diff --git a/checkpoint-11900/trainer_state.json b/checkpoint-11900/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..ce33bb3ec6919b3750b12e122457f47e4335be30 --- /dev/null +++ b/checkpoint-11900/trainer_state.json @@ -0,0 +1,71421 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 0.9956076134699854, + "eval_steps": 500, + "global_step": 11900, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0, + "learning_rate": 5.571030640668524e-08, + "loss": 0.8031, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 1.1142061281337048e-07, + "loss": 0.8071, + "step": 2 + }, + { + "epoch": 0.0, + "learning_rate": 1.6713091922005573e-07, + "loss": 0.7913, + "step": 3 + }, + { + "epoch": 0.0, + "learning_rate": 2.2284122562674096e-07, + "loss": 0.8033, + "step": 4 + }, + { + "epoch": 0.0, + "learning_rate": 2.785515320334262e-07, + "loss": 0.805, + "step": 5 + }, + { + "epoch": 0.0, + "learning_rate": 3.3426183844011146e-07, + "loss": 0.8159, + "step": 6 + }, + { + "epoch": 0.0, + "learning_rate": 3.899721448467967e-07, + "loss": 0.8095, + "step": 7 + }, + { + "epoch": 0.0, + "learning_rate": 4.456824512534819e-07, + "loss": 0.7973, + "step": 8 + }, + { + "epoch": 0.0, + "learning_rate": 5.013927576601672e-07, + "loss": 0.7913, + "step": 9 + }, + { + "epoch": 0.0, + "learning_rate": 5.571030640668524e-07, + "loss": 0.8118, + "step": 10 + }, + { + "epoch": 0.0, + "learning_rate": 6.128133704735377e-07, + "loss": 0.7926, + "step": 11 + }, + { + "epoch": 0.0, + "learning_rate": 6.685236768802229e-07, + "loss": 0.7805, + "step": 12 + }, + { + "epoch": 0.0, + "learning_rate": 7.242339832869082e-07, + "loss": 0.7913, + "step": 13 + }, + { + "epoch": 0.0, + "learning_rate": 7.799442896935934e-07, + "loss": 0.7994, + "step": 14 + }, + { + "epoch": 0.0, + "learning_rate": 8.356545961002786e-07, + "loss": 0.7979, + "step": 15 + }, + { + "epoch": 0.0, + "learning_rate": 8.913649025069638e-07, + "loss": 0.7736, + "step": 16 + }, + { + "epoch": 0.0, + "learning_rate": 9.470752089136491e-07, + "loss": 0.7817, + "step": 17 + }, + { + "epoch": 0.0, + "learning_rate": 1.0027855153203343e-06, + "loss": 0.7678, + "step": 18 + }, + { + "epoch": 0.0, + "learning_rate": 1.0584958217270195e-06, + "loss": 0.7265, + "step": 19 + }, + { + "epoch": 0.0, + "learning_rate": 1.1142061281337048e-06, + "loss": 0.7331, + "step": 20 + }, + { + "epoch": 0.0, + "learning_rate": 1.16991643454039e-06, + "loss": 0.7349, + "step": 21 + }, + { + "epoch": 0.0, + "learning_rate": 1.2256267409470754e-06, + "loss": 0.7219, + "step": 22 + }, + { + "epoch": 0.0, + "learning_rate": 1.2813370473537607e-06, + "loss": 0.7335, + "step": 23 + }, + { + "epoch": 0.0, + "learning_rate": 1.3370473537604459e-06, + "loss": 0.7127, + "step": 24 + }, + { + "epoch": 0.0, + "learning_rate": 1.392757660167131e-06, + "loss": 0.7235, + "step": 25 + }, + { + "epoch": 0.0, + "learning_rate": 1.4484679665738164e-06, + "loss": 0.6903, + "step": 26 + }, + { + "epoch": 0.0, + "learning_rate": 1.5041782729805015e-06, + "loss": 0.6748, + "step": 27 + }, + { + "epoch": 0.0, + "learning_rate": 1.5598885793871869e-06, + "loss": 0.6899, + "step": 28 + }, + { + "epoch": 0.0, + "learning_rate": 1.615598885793872e-06, + "loss": 0.6611, + "step": 29 + }, + { + "epoch": 0.0, + "learning_rate": 1.6713091922005572e-06, + "loss": 0.6656, + "step": 30 + }, + { + "epoch": 0.0, + "learning_rate": 1.7270194986072425e-06, + "loss": 0.6954, + "step": 31 + }, + { + "epoch": 0.0, + "learning_rate": 1.7827298050139277e-06, + "loss": 0.683, + "step": 32 + }, + { + "epoch": 0.0, + "learning_rate": 1.838440111420613e-06, + "loss": 0.6812, + "step": 33 + }, + { + "epoch": 0.0, + "learning_rate": 1.8941504178272982e-06, + "loss": 0.6796, + "step": 34 + }, + { + "epoch": 0.0, + "learning_rate": 1.9498607242339835e-06, + "loss": 0.6593, + "step": 35 + }, + { + "epoch": 0.0, + "learning_rate": 2.0055710306406687e-06, + "loss": 0.6622, + "step": 36 + }, + { + "epoch": 0.0, + "learning_rate": 2.061281337047354e-06, + "loss": 0.6774, + "step": 37 + }, + { + "epoch": 0.0, + "learning_rate": 2.116991643454039e-06, + "loss": 0.6606, + "step": 38 + }, + { + "epoch": 0.0, + "learning_rate": 2.1727019498607245e-06, + "loss": 0.658, + "step": 39 + }, + { + "epoch": 0.0, + "learning_rate": 2.2284122562674097e-06, + "loss": 0.6551, + "step": 40 + }, + { + "epoch": 0.0, + "learning_rate": 2.284122562674095e-06, + "loss": 0.621, + "step": 41 + }, + { + "epoch": 0.0, + "learning_rate": 2.33983286908078e-06, + "loss": 0.6396, + "step": 42 + }, + { + "epoch": 0.0, + "learning_rate": 2.395543175487465e-06, + "loss": 0.6604, + "step": 43 + }, + { + "epoch": 0.0, + "learning_rate": 2.4512534818941507e-06, + "loss": 0.6269, + "step": 44 + }, + { + "epoch": 0.0, + "learning_rate": 2.506963788300836e-06, + "loss": 0.6314, + "step": 45 + }, + { + "epoch": 0.0, + "learning_rate": 2.5626740947075214e-06, + "loss": 0.623, + "step": 46 + }, + { + "epoch": 0.0, + "learning_rate": 2.618384401114206e-06, + "loss": 0.6306, + "step": 47 + }, + { + "epoch": 0.0, + "learning_rate": 2.6740947075208917e-06, + "loss": 0.6014, + "step": 48 + }, + { + "epoch": 0.0, + "learning_rate": 2.729805013927577e-06, + "loss": 0.6312, + "step": 49 + }, + { + "epoch": 0.0, + "learning_rate": 2.785515320334262e-06, + "loss": 0.617, + "step": 50 + }, + { + "epoch": 0.0, + "learning_rate": 2.841225626740947e-06, + "loss": 0.6195, + "step": 51 + }, + { + "epoch": 0.0, + "learning_rate": 2.8969359331476327e-06, + "loss": 0.6213, + "step": 52 + }, + { + "epoch": 0.0, + "learning_rate": 2.9526462395543174e-06, + "loss": 0.6236, + "step": 53 + }, + { + "epoch": 0.0, + "learning_rate": 3.008356545961003e-06, + "loss": 0.6158, + "step": 54 + }, + { + "epoch": 0.0, + "learning_rate": 3.064066852367688e-06, + "loss": 0.5968, + "step": 55 + }, + { + "epoch": 0.0, + "learning_rate": 3.1197771587743737e-06, + "loss": 0.6257, + "step": 56 + }, + { + "epoch": 0.0, + "learning_rate": 3.1754874651810585e-06, + "loss": 0.6096, + "step": 57 + }, + { + "epoch": 0.0, + "learning_rate": 3.231197771587744e-06, + "loss": 0.6253, + "step": 58 + }, + { + "epoch": 0.0, + "learning_rate": 3.286908077994429e-06, + "loss": 0.6213, + "step": 59 + }, + { + "epoch": 0.01, + "learning_rate": 3.3426183844011143e-06, + "loss": 0.6041, + "step": 60 + }, + { + "epoch": 0.01, + "learning_rate": 3.3983286908077995e-06, + "loss": 0.6098, + "step": 61 + }, + { + "epoch": 0.01, + "learning_rate": 3.454038997214485e-06, + "loss": 0.614, + "step": 62 + }, + { + "epoch": 0.01, + "learning_rate": 3.5097493036211698e-06, + "loss": 0.6163, + "step": 63 + }, + { + "epoch": 0.01, + "learning_rate": 3.5654596100278553e-06, + "loss": 0.6006, + "step": 64 + }, + { + "epoch": 0.01, + "learning_rate": 3.6211699164345405e-06, + "loss": 0.5992, + "step": 65 + }, + { + "epoch": 0.01, + "learning_rate": 3.676880222841226e-06, + "loss": 0.6079, + "step": 66 + }, + { + "epoch": 0.01, + "learning_rate": 3.7325905292479116e-06, + "loss": 0.607, + "step": 67 + }, + { + "epoch": 0.01, + "learning_rate": 3.7883008356545963e-06, + "loss": 0.6128, + "step": 68 + }, + { + "epoch": 0.01, + "learning_rate": 3.844011142061282e-06, + "loss": 0.6046, + "step": 69 + }, + { + "epoch": 0.01, + "learning_rate": 3.899721448467967e-06, + "loss": 0.5908, + "step": 70 + }, + { + "epoch": 0.01, + "learning_rate": 3.955431754874652e-06, + "loss": 0.6016, + "step": 71 + }, + { + "epoch": 0.01, + "learning_rate": 4.011142061281337e-06, + "loss": 0.615, + "step": 72 + }, + { + "epoch": 0.01, + "learning_rate": 4.0668523676880225e-06, + "loss": 0.6117, + "step": 73 + }, + { + "epoch": 0.01, + "learning_rate": 4.122562674094708e-06, + "loss": 0.5916, + "step": 74 + }, + { + "epoch": 0.01, + "learning_rate": 4.178272980501394e-06, + "loss": 0.6005, + "step": 75 + }, + { + "epoch": 0.01, + "learning_rate": 4.233983286908078e-06, + "loss": 0.5826, + "step": 76 + }, + { + "epoch": 0.01, + "learning_rate": 4.289693593314764e-06, + "loss": 0.6087, + "step": 77 + }, + { + "epoch": 0.01, + "learning_rate": 4.345403899721449e-06, + "loss": 0.5953, + "step": 78 + }, + { + "epoch": 0.01, + "learning_rate": 4.401114206128134e-06, + "loss": 0.581, + "step": 79 + }, + { + "epoch": 0.01, + "learning_rate": 4.456824512534819e-06, + "loss": 0.5961, + "step": 80 + }, + { + "epoch": 0.01, + "learning_rate": 4.5125348189415045e-06, + "loss": 0.5837, + "step": 81 + }, + { + "epoch": 0.01, + "learning_rate": 4.56824512534819e-06, + "loss": 0.5881, + "step": 82 + }, + { + "epoch": 0.01, + "learning_rate": 4.623955431754875e-06, + "loss": 0.6076, + "step": 83 + }, + { + "epoch": 0.01, + "learning_rate": 4.67966573816156e-06, + "loss": 0.5977, + "step": 84 + }, + { + "epoch": 0.01, + "learning_rate": 4.735376044568246e-06, + "loss": 0.6113, + "step": 85 + }, + { + "epoch": 0.01, + "learning_rate": 4.79108635097493e-06, + "loss": 0.5748, + "step": 86 + }, + { + "epoch": 0.01, + "learning_rate": 4.846796657381616e-06, + "loss": 0.6021, + "step": 87 + }, + { + "epoch": 0.01, + "learning_rate": 4.902506963788301e-06, + "loss": 0.5738, + "step": 88 + }, + { + "epoch": 0.01, + "learning_rate": 4.9582172701949865e-06, + "loss": 0.5804, + "step": 89 + }, + { + "epoch": 0.01, + "learning_rate": 5.013927576601672e-06, + "loss": 0.5796, + "step": 90 + }, + { + "epoch": 0.01, + "learning_rate": 5.069637883008357e-06, + "loss": 0.591, + "step": 91 + }, + { + "epoch": 0.01, + "learning_rate": 5.125348189415043e-06, + "loss": 0.5811, + "step": 92 + }, + { + "epoch": 0.01, + "learning_rate": 5.181058495821727e-06, + "loss": 0.5667, + "step": 93 + }, + { + "epoch": 0.01, + "learning_rate": 5.236768802228412e-06, + "loss": 0.6095, + "step": 94 + }, + { + "epoch": 0.01, + "learning_rate": 5.292479108635098e-06, + "loss": 0.5935, + "step": 95 + }, + { + "epoch": 0.01, + "learning_rate": 5.3481894150417834e-06, + "loss": 0.57, + "step": 96 + }, + { + "epoch": 0.01, + "learning_rate": 5.403899721448468e-06, + "loss": 0.5865, + "step": 97 + }, + { + "epoch": 0.01, + "learning_rate": 5.459610027855154e-06, + "loss": 0.6119, + "step": 98 + }, + { + "epoch": 0.01, + "learning_rate": 5.515320334261839e-06, + "loss": 0.6189, + "step": 99 + }, + { + "epoch": 0.01, + "learning_rate": 5.571030640668524e-06, + "loss": 0.6001, + "step": 100 + }, + { + "epoch": 0.01, + "learning_rate": 5.62674094707521e-06, + "loss": 0.5787, + "step": 101 + }, + { + "epoch": 0.01, + "learning_rate": 5.682451253481894e-06, + "loss": 0.5809, + "step": 102 + }, + { + "epoch": 0.01, + "learning_rate": 5.7381615598885795e-06, + "loss": 0.5708, + "step": 103 + }, + { + "epoch": 0.01, + "learning_rate": 5.7938718662952654e-06, + "loss": 0.6033, + "step": 104 + }, + { + "epoch": 0.01, + "learning_rate": 5.849582172701951e-06, + "loss": 0.5802, + "step": 105 + }, + { + "epoch": 0.01, + "learning_rate": 5.905292479108635e-06, + "loss": 0.587, + "step": 106 + }, + { + "epoch": 0.01, + "learning_rate": 5.961002785515321e-06, + "loss": 0.5665, + "step": 107 + }, + { + "epoch": 0.01, + "learning_rate": 6.016713091922006e-06, + "loss": 0.5883, + "step": 108 + }, + { + "epoch": 0.01, + "learning_rate": 6.072423398328692e-06, + "loss": 0.5707, + "step": 109 + }, + { + "epoch": 0.01, + "learning_rate": 6.128133704735376e-06, + "loss": 0.5862, + "step": 110 + }, + { + "epoch": 0.01, + "learning_rate": 6.1838440111420615e-06, + "loss": 0.5918, + "step": 111 + }, + { + "epoch": 0.01, + "learning_rate": 6.2395543175487475e-06, + "loss": 0.564, + "step": 112 + }, + { + "epoch": 0.01, + "learning_rate": 6.295264623955433e-06, + "loss": 0.571, + "step": 113 + }, + { + "epoch": 0.01, + "learning_rate": 6.350974930362117e-06, + "loss": 0.5589, + "step": 114 + }, + { + "epoch": 0.01, + "learning_rate": 6.406685236768803e-06, + "loss": 0.5875, + "step": 115 + }, + { + "epoch": 0.01, + "learning_rate": 6.462395543175488e-06, + "loss": 0.5771, + "step": 116 + }, + { + "epoch": 0.01, + "learning_rate": 6.518105849582173e-06, + "loss": 0.5563, + "step": 117 + }, + { + "epoch": 0.01, + "learning_rate": 6.573816155988858e-06, + "loss": 0.5947, + "step": 118 + }, + { + "epoch": 0.01, + "learning_rate": 6.6295264623955435e-06, + "loss": 0.5625, + "step": 119 + }, + { + "epoch": 0.01, + "learning_rate": 6.685236768802229e-06, + "loss": 0.5658, + "step": 120 + }, + { + "epoch": 0.01, + "learning_rate": 6.740947075208915e-06, + "loss": 0.5672, + "step": 121 + }, + { + "epoch": 0.01, + "learning_rate": 6.796657381615599e-06, + "loss": 0.5932, + "step": 122 + }, + { + "epoch": 0.01, + "learning_rate": 6.852367688022284e-06, + "loss": 0.5779, + "step": 123 + }, + { + "epoch": 0.01, + "learning_rate": 6.90807799442897e-06, + "loss": 0.5683, + "step": 124 + }, + { + "epoch": 0.01, + "learning_rate": 6.963788300835655e-06, + "loss": 0.565, + "step": 125 + }, + { + "epoch": 0.01, + "learning_rate": 7.0194986072423395e-06, + "loss": 0.5455, + "step": 126 + }, + { + "epoch": 0.01, + "learning_rate": 7.0752089136490255e-06, + "loss": 0.5816, + "step": 127 + }, + { + "epoch": 0.01, + "learning_rate": 7.130919220055711e-06, + "loss": 0.5675, + "step": 128 + }, + { + "epoch": 0.01, + "learning_rate": 7.186629526462397e-06, + "loss": 0.575, + "step": 129 + }, + { + "epoch": 0.01, + "learning_rate": 7.242339832869081e-06, + "loss": 0.5656, + "step": 130 + }, + { + "epoch": 0.01, + "learning_rate": 7.298050139275766e-06, + "loss": 0.5686, + "step": 131 + }, + { + "epoch": 0.01, + "learning_rate": 7.353760445682452e-06, + "loss": 0.5917, + "step": 132 + }, + { + "epoch": 0.01, + "learning_rate": 7.409470752089137e-06, + "loss": 0.5935, + "step": 133 + }, + { + "epoch": 0.01, + "learning_rate": 7.465181058495823e-06, + "loss": 0.5816, + "step": 134 + }, + { + "epoch": 0.01, + "learning_rate": 7.5208913649025075e-06, + "loss": 0.5658, + "step": 135 + }, + { + "epoch": 0.01, + "learning_rate": 7.576601671309193e-06, + "loss": 0.5707, + "step": 136 + }, + { + "epoch": 0.01, + "learning_rate": 7.632311977715879e-06, + "loss": 0.5605, + "step": 137 + }, + { + "epoch": 0.01, + "learning_rate": 7.688022284122564e-06, + "loss": 0.5882, + "step": 138 + }, + { + "epoch": 0.01, + "learning_rate": 7.743732590529249e-06, + "loss": 0.5645, + "step": 139 + }, + { + "epoch": 0.01, + "learning_rate": 7.799442896935934e-06, + "loss": 0.5875, + "step": 140 + }, + { + "epoch": 0.01, + "learning_rate": 7.85515320334262e-06, + "loss": 0.5554, + "step": 141 + }, + { + "epoch": 0.01, + "learning_rate": 7.910863509749304e-06, + "loss": 0.5579, + "step": 142 + }, + { + "epoch": 0.01, + "learning_rate": 7.96657381615599e-06, + "loss": 0.5873, + "step": 143 + }, + { + "epoch": 0.01, + "learning_rate": 8.022284122562675e-06, + "loss": 0.5785, + "step": 144 + }, + { + "epoch": 0.01, + "learning_rate": 8.07799442896936e-06, + "loss": 0.5596, + "step": 145 + }, + { + "epoch": 0.01, + "learning_rate": 8.133704735376045e-06, + "loss": 0.5765, + "step": 146 + }, + { + "epoch": 0.01, + "learning_rate": 8.18941504178273e-06, + "loss": 0.5682, + "step": 147 + }, + { + "epoch": 0.01, + "learning_rate": 8.245125348189415e-06, + "loss": 0.5593, + "step": 148 + }, + { + "epoch": 0.01, + "learning_rate": 8.3008356545961e-06, + "loss": 0.5568, + "step": 149 + }, + { + "epoch": 0.01, + "learning_rate": 8.356545961002787e-06, + "loss": 0.5685, + "step": 150 + }, + { + "epoch": 0.01, + "learning_rate": 8.41225626740947e-06, + "loss": 0.5681, + "step": 151 + }, + { + "epoch": 0.01, + "learning_rate": 8.467966573816156e-06, + "loss": 0.5858, + "step": 152 + }, + { + "epoch": 0.01, + "learning_rate": 8.523676880222843e-06, + "loss": 0.5611, + "step": 153 + }, + { + "epoch": 0.01, + "learning_rate": 8.579387186629528e-06, + "loss": 0.5584, + "step": 154 + }, + { + "epoch": 0.01, + "learning_rate": 8.635097493036211e-06, + "loss": 0.5517, + "step": 155 + }, + { + "epoch": 0.01, + "learning_rate": 8.690807799442898e-06, + "loss": 0.56, + "step": 156 + }, + { + "epoch": 0.01, + "learning_rate": 8.746518105849583e-06, + "loss": 0.5673, + "step": 157 + }, + { + "epoch": 0.01, + "learning_rate": 8.802228412256268e-06, + "loss": 0.5571, + "step": 158 + }, + { + "epoch": 0.01, + "learning_rate": 8.857938718662954e-06, + "loss": 0.5716, + "step": 159 + }, + { + "epoch": 0.01, + "learning_rate": 8.913649025069639e-06, + "loss": 0.5634, + "step": 160 + }, + { + "epoch": 0.01, + "learning_rate": 8.969359331476324e-06, + "loss": 0.5602, + "step": 161 + }, + { + "epoch": 0.01, + "learning_rate": 9.025069637883009e-06, + "loss": 0.5444, + "step": 162 + }, + { + "epoch": 0.01, + "learning_rate": 9.080779944289694e-06, + "loss": 0.5793, + "step": 163 + }, + { + "epoch": 0.01, + "learning_rate": 9.13649025069638e-06, + "loss": 0.5443, + "step": 164 + }, + { + "epoch": 0.01, + "learning_rate": 9.192200557103064e-06, + "loss": 0.5449, + "step": 165 + }, + { + "epoch": 0.01, + "learning_rate": 9.24791086350975e-06, + "loss": 0.5599, + "step": 166 + }, + { + "epoch": 0.01, + "learning_rate": 9.303621169916436e-06, + "loss": 0.5362, + "step": 167 + }, + { + "epoch": 0.01, + "learning_rate": 9.35933147632312e-06, + "loss": 0.5649, + "step": 168 + }, + { + "epoch": 0.01, + "learning_rate": 9.415041782729805e-06, + "loss": 0.5734, + "step": 169 + }, + { + "epoch": 0.01, + "learning_rate": 9.470752089136492e-06, + "loss": 0.5595, + "step": 170 + }, + { + "epoch": 0.01, + "learning_rate": 9.526462395543177e-06, + "loss": 0.5483, + "step": 171 + }, + { + "epoch": 0.01, + "learning_rate": 9.58217270194986e-06, + "loss": 0.5569, + "step": 172 + }, + { + "epoch": 0.01, + "learning_rate": 9.637883008356547e-06, + "loss": 0.5591, + "step": 173 + }, + { + "epoch": 0.01, + "learning_rate": 9.693593314763233e-06, + "loss": 0.5639, + "step": 174 + }, + { + "epoch": 0.01, + "learning_rate": 9.749303621169918e-06, + "loss": 0.5504, + "step": 175 + }, + { + "epoch": 0.01, + "learning_rate": 9.805013927576603e-06, + "loss": 0.5627, + "step": 176 + }, + { + "epoch": 0.01, + "learning_rate": 9.860724233983288e-06, + "loss": 0.5587, + "step": 177 + }, + { + "epoch": 0.01, + "learning_rate": 9.916434540389973e-06, + "loss": 0.5603, + "step": 178 + }, + { + "epoch": 0.01, + "learning_rate": 9.972144846796658e-06, + "loss": 0.5558, + "step": 179 + }, + { + "epoch": 0.02, + "learning_rate": 1.0027855153203343e-05, + "loss": 0.5519, + "step": 180 + }, + { + "epoch": 0.02, + "learning_rate": 1.008356545961003e-05, + "loss": 0.5488, + "step": 181 + }, + { + "epoch": 0.02, + "learning_rate": 1.0139275766016714e-05, + "loss": 0.5417, + "step": 182 + }, + { + "epoch": 0.02, + "learning_rate": 1.0194986072423399e-05, + "loss": 0.5537, + "step": 183 + }, + { + "epoch": 0.02, + "learning_rate": 1.0250696378830086e-05, + "loss": 0.5349, + "step": 184 + }, + { + "epoch": 0.02, + "learning_rate": 1.0306406685236769e-05, + "loss": 0.5355, + "step": 185 + }, + { + "epoch": 0.02, + "learning_rate": 1.0362116991643454e-05, + "loss": 0.5492, + "step": 186 + }, + { + "epoch": 0.02, + "learning_rate": 1.0417827298050141e-05, + "loss": 0.5627, + "step": 187 + }, + { + "epoch": 0.02, + "learning_rate": 1.0473537604456825e-05, + "loss": 0.5576, + "step": 188 + }, + { + "epoch": 0.02, + "learning_rate": 1.0529247910863511e-05, + "loss": 0.5411, + "step": 189 + }, + { + "epoch": 0.02, + "learning_rate": 1.0584958217270197e-05, + "loss": 0.5494, + "step": 190 + }, + { + "epoch": 0.02, + "learning_rate": 1.064066852367688e-05, + "loss": 0.5574, + "step": 191 + }, + { + "epoch": 0.02, + "learning_rate": 1.0696378830083567e-05, + "loss": 0.5522, + "step": 192 + }, + { + "epoch": 0.02, + "learning_rate": 1.0752089136490252e-05, + "loss": 0.546, + "step": 193 + }, + { + "epoch": 0.02, + "learning_rate": 1.0807799442896935e-05, + "loss": 0.5454, + "step": 194 + }, + { + "epoch": 0.02, + "learning_rate": 1.0863509749303622e-05, + "loss": 0.5463, + "step": 195 + }, + { + "epoch": 0.02, + "learning_rate": 1.0919220055710307e-05, + "loss": 0.5607, + "step": 196 + }, + { + "epoch": 0.02, + "learning_rate": 1.0974930362116993e-05, + "loss": 0.5493, + "step": 197 + }, + { + "epoch": 0.02, + "learning_rate": 1.1030640668523678e-05, + "loss": 0.5301, + "step": 198 + }, + { + "epoch": 0.02, + "learning_rate": 1.1086350974930363e-05, + "loss": 0.5335, + "step": 199 + }, + { + "epoch": 0.02, + "learning_rate": 1.1142061281337048e-05, + "loss": 0.5532, + "step": 200 + }, + { + "epoch": 0.02, + "learning_rate": 1.1197771587743733e-05, + "loss": 0.5332, + "step": 201 + }, + { + "epoch": 0.02, + "learning_rate": 1.125348189415042e-05, + "loss": 0.5719, + "step": 202 + }, + { + "epoch": 0.02, + "learning_rate": 1.1309192200557103e-05, + "loss": 0.5222, + "step": 203 + }, + { + "epoch": 0.02, + "learning_rate": 1.1364902506963789e-05, + "loss": 0.5481, + "step": 204 + }, + { + "epoch": 0.02, + "learning_rate": 1.1420612813370475e-05, + "loss": 0.5465, + "step": 205 + }, + { + "epoch": 0.02, + "learning_rate": 1.1476323119777159e-05, + "loss": 0.552, + "step": 206 + }, + { + "epoch": 0.02, + "learning_rate": 1.1532033426183844e-05, + "loss": 0.5473, + "step": 207 + }, + { + "epoch": 0.02, + "learning_rate": 1.1587743732590531e-05, + "loss": 0.5439, + "step": 208 + }, + { + "epoch": 0.02, + "learning_rate": 1.1643454038997214e-05, + "loss": 0.5462, + "step": 209 + }, + { + "epoch": 0.02, + "learning_rate": 1.1699164345403901e-05, + "loss": 0.5401, + "step": 210 + }, + { + "epoch": 0.02, + "learning_rate": 1.1754874651810586e-05, + "loss": 0.5498, + "step": 211 + }, + { + "epoch": 0.02, + "learning_rate": 1.181058495821727e-05, + "loss": 0.5567, + "step": 212 + }, + { + "epoch": 0.02, + "learning_rate": 1.1866295264623957e-05, + "loss": 0.5436, + "step": 213 + }, + { + "epoch": 0.02, + "learning_rate": 1.1922005571030642e-05, + "loss": 0.5484, + "step": 214 + }, + { + "epoch": 0.02, + "learning_rate": 1.1977715877437325e-05, + "loss": 0.5411, + "step": 215 + }, + { + "epoch": 0.02, + "learning_rate": 1.2033426183844012e-05, + "loss": 0.5581, + "step": 216 + }, + { + "epoch": 0.02, + "learning_rate": 1.2089136490250697e-05, + "loss": 0.5441, + "step": 217 + }, + { + "epoch": 0.02, + "learning_rate": 1.2144846796657384e-05, + "loss": 0.5574, + "step": 218 + }, + { + "epoch": 0.02, + "learning_rate": 1.2200557103064068e-05, + "loss": 0.5588, + "step": 219 + }, + { + "epoch": 0.02, + "learning_rate": 1.2256267409470753e-05, + "loss": 0.5554, + "step": 220 + }, + { + "epoch": 0.02, + "learning_rate": 1.231197771587744e-05, + "loss": 0.5342, + "step": 221 + }, + { + "epoch": 0.02, + "learning_rate": 1.2367688022284123e-05, + "loss": 0.568, + "step": 222 + }, + { + "epoch": 0.02, + "learning_rate": 1.2423398328690808e-05, + "loss": 0.5387, + "step": 223 + }, + { + "epoch": 0.02, + "learning_rate": 1.2479108635097495e-05, + "loss": 0.5469, + "step": 224 + }, + { + "epoch": 0.02, + "learning_rate": 1.2534818941504178e-05, + "loss": 0.5312, + "step": 225 + }, + { + "epoch": 0.02, + "learning_rate": 1.2590529247910865e-05, + "loss": 0.5462, + "step": 226 + }, + { + "epoch": 0.02, + "learning_rate": 1.264623955431755e-05, + "loss": 0.5595, + "step": 227 + }, + { + "epoch": 0.02, + "learning_rate": 1.2701949860724234e-05, + "loss": 0.5355, + "step": 228 + }, + { + "epoch": 0.02, + "learning_rate": 1.275766016713092e-05, + "loss": 0.548, + "step": 229 + }, + { + "epoch": 0.02, + "learning_rate": 1.2813370473537606e-05, + "loss": 0.547, + "step": 230 + }, + { + "epoch": 0.02, + "learning_rate": 1.2869080779944293e-05, + "loss": 0.5309, + "step": 231 + }, + { + "epoch": 0.02, + "learning_rate": 1.2924791086350976e-05, + "loss": 0.557, + "step": 232 + }, + { + "epoch": 0.02, + "learning_rate": 1.2980501392757661e-05, + "loss": 0.5592, + "step": 233 + }, + { + "epoch": 0.02, + "learning_rate": 1.3036211699164346e-05, + "loss": 0.5326, + "step": 234 + }, + { + "epoch": 0.02, + "learning_rate": 1.3091922005571032e-05, + "loss": 0.5262, + "step": 235 + }, + { + "epoch": 0.02, + "learning_rate": 1.3147632311977717e-05, + "loss": 0.5443, + "step": 236 + }, + { + "epoch": 0.02, + "learning_rate": 1.3203342618384402e-05, + "loss": 0.541, + "step": 237 + }, + { + "epoch": 0.02, + "learning_rate": 1.3259052924791087e-05, + "loss": 0.5411, + "step": 238 + }, + { + "epoch": 0.02, + "learning_rate": 1.3314763231197774e-05, + "loss": 0.5406, + "step": 239 + }, + { + "epoch": 0.02, + "learning_rate": 1.3370473537604457e-05, + "loss": 0.5488, + "step": 240 + }, + { + "epoch": 0.02, + "learning_rate": 1.3426183844011142e-05, + "loss": 0.5626, + "step": 241 + }, + { + "epoch": 0.02, + "learning_rate": 1.348189415041783e-05, + "loss": 0.5479, + "step": 242 + }, + { + "epoch": 0.02, + "learning_rate": 1.3537604456824513e-05, + "loss": 0.5583, + "step": 243 + }, + { + "epoch": 0.02, + "learning_rate": 1.3593314763231198e-05, + "loss": 0.5572, + "step": 244 + }, + { + "epoch": 0.02, + "learning_rate": 1.3649025069637885e-05, + "loss": 0.5438, + "step": 245 + }, + { + "epoch": 0.02, + "learning_rate": 1.3704735376044568e-05, + "loss": 0.5382, + "step": 246 + }, + { + "epoch": 0.02, + "learning_rate": 1.3760445682451255e-05, + "loss": 0.5321, + "step": 247 + }, + { + "epoch": 0.02, + "learning_rate": 1.381615598885794e-05, + "loss": 0.5513, + "step": 248 + }, + { + "epoch": 0.02, + "learning_rate": 1.3871866295264624e-05, + "loss": 0.546, + "step": 249 + }, + { + "epoch": 0.02, + "learning_rate": 1.392757660167131e-05, + "loss": 0.5539, + "step": 250 + }, + { + "epoch": 0.02, + "learning_rate": 1.3983286908077996e-05, + "loss": 0.5551, + "step": 251 + }, + { + "epoch": 0.02, + "learning_rate": 1.4038997214484679e-05, + "loss": 0.5484, + "step": 252 + }, + { + "epoch": 0.02, + "learning_rate": 1.4094707520891366e-05, + "loss": 0.5445, + "step": 253 + }, + { + "epoch": 0.02, + "learning_rate": 1.4150417827298051e-05, + "loss": 0.5497, + "step": 254 + }, + { + "epoch": 0.02, + "learning_rate": 1.4206128133704738e-05, + "loss": 0.5279, + "step": 255 + }, + { + "epoch": 0.02, + "learning_rate": 1.4261838440111421e-05, + "loss": 0.5312, + "step": 256 + }, + { + "epoch": 0.02, + "learning_rate": 1.4317548746518106e-05, + "loss": 0.5578, + "step": 257 + }, + { + "epoch": 0.02, + "learning_rate": 1.4373259052924793e-05, + "loss": 0.549, + "step": 258 + }, + { + "epoch": 0.02, + "learning_rate": 1.4428969359331477e-05, + "loss": 0.5359, + "step": 259 + }, + { + "epoch": 0.02, + "learning_rate": 1.4484679665738162e-05, + "loss": 0.5571, + "step": 260 + }, + { + "epoch": 0.02, + "learning_rate": 1.4540389972144849e-05, + "loss": 0.5211, + "step": 261 + }, + { + "epoch": 0.02, + "learning_rate": 1.4596100278551532e-05, + "loss": 0.5446, + "step": 262 + }, + { + "epoch": 0.02, + "learning_rate": 1.4651810584958219e-05, + "loss": 0.533, + "step": 263 + }, + { + "epoch": 0.02, + "learning_rate": 1.4707520891364904e-05, + "loss": 0.548, + "step": 264 + }, + { + "epoch": 0.02, + "learning_rate": 1.4763231197771588e-05, + "loss": 0.546, + "step": 265 + }, + { + "epoch": 0.02, + "learning_rate": 1.4818941504178274e-05, + "loss": 0.5171, + "step": 266 + }, + { + "epoch": 0.02, + "learning_rate": 1.487465181058496e-05, + "loss": 0.5478, + "step": 267 + }, + { + "epoch": 0.02, + "learning_rate": 1.4930362116991646e-05, + "loss": 0.5389, + "step": 268 + }, + { + "epoch": 0.02, + "learning_rate": 1.498607242339833e-05, + "loss": 0.5388, + "step": 269 + }, + { + "epoch": 0.02, + "learning_rate": 1.5041782729805015e-05, + "loss": 0.5412, + "step": 270 + }, + { + "epoch": 0.02, + "learning_rate": 1.5097493036211702e-05, + "loss": 0.5354, + "step": 271 + }, + { + "epoch": 0.02, + "learning_rate": 1.5153203342618385e-05, + "loss": 0.5453, + "step": 272 + }, + { + "epoch": 0.02, + "learning_rate": 1.520891364902507e-05, + "loss": 0.5322, + "step": 273 + }, + { + "epoch": 0.02, + "learning_rate": 1.5264623955431757e-05, + "loss": 0.5533, + "step": 274 + }, + { + "epoch": 0.02, + "learning_rate": 1.5320334261838443e-05, + "loss": 0.5358, + "step": 275 + }, + { + "epoch": 0.02, + "learning_rate": 1.5376044568245128e-05, + "loss": 0.5376, + "step": 276 + }, + { + "epoch": 0.02, + "learning_rate": 1.5431754874651813e-05, + "loss": 0.5359, + "step": 277 + }, + { + "epoch": 0.02, + "learning_rate": 1.5487465181058498e-05, + "loss": 0.5518, + "step": 278 + }, + { + "epoch": 0.02, + "learning_rate": 1.5543175487465183e-05, + "loss": 0.5365, + "step": 279 + }, + { + "epoch": 0.02, + "learning_rate": 1.5598885793871868e-05, + "loss": 0.5345, + "step": 280 + }, + { + "epoch": 0.02, + "learning_rate": 1.5654596100278553e-05, + "loss": 0.5424, + "step": 281 + }, + { + "epoch": 0.02, + "learning_rate": 1.571030640668524e-05, + "loss": 0.5337, + "step": 282 + }, + { + "epoch": 0.02, + "learning_rate": 1.5766016713091924e-05, + "loss": 0.5202, + "step": 283 + }, + { + "epoch": 0.02, + "learning_rate": 1.582172701949861e-05, + "loss": 0.5293, + "step": 284 + }, + { + "epoch": 0.02, + "learning_rate": 1.5877437325905294e-05, + "loss": 0.549, + "step": 285 + }, + { + "epoch": 0.02, + "learning_rate": 1.593314763231198e-05, + "loss": 0.5346, + "step": 286 + }, + { + "epoch": 0.02, + "learning_rate": 1.5988857938718664e-05, + "loss": 0.5482, + "step": 287 + }, + { + "epoch": 0.02, + "learning_rate": 1.604456824512535e-05, + "loss": 0.5549, + "step": 288 + }, + { + "epoch": 0.02, + "learning_rate": 1.6100278551532035e-05, + "loss": 0.5293, + "step": 289 + }, + { + "epoch": 0.02, + "learning_rate": 1.615598885793872e-05, + "loss": 0.5656, + "step": 290 + }, + { + "epoch": 0.02, + "learning_rate": 1.6211699164345405e-05, + "loss": 0.5305, + "step": 291 + }, + { + "epoch": 0.02, + "learning_rate": 1.626740947075209e-05, + "loss": 0.5557, + "step": 292 + }, + { + "epoch": 0.02, + "learning_rate": 1.6323119777158775e-05, + "loss": 0.5374, + "step": 293 + }, + { + "epoch": 0.02, + "learning_rate": 1.637883008356546e-05, + "loss": 0.5183, + "step": 294 + }, + { + "epoch": 0.02, + "learning_rate": 1.6434540389972145e-05, + "loss": 0.5629, + "step": 295 + }, + { + "epoch": 0.02, + "learning_rate": 1.649025069637883e-05, + "loss": 0.5362, + "step": 296 + }, + { + "epoch": 0.02, + "learning_rate": 1.654596100278552e-05, + "loss": 0.532, + "step": 297 + }, + { + "epoch": 0.02, + "learning_rate": 1.66016713091922e-05, + "loss": 0.5322, + "step": 298 + }, + { + "epoch": 0.03, + "learning_rate": 1.6657381615598886e-05, + "loss": 0.528, + "step": 299 + }, + { + "epoch": 0.03, + "learning_rate": 1.6713091922005575e-05, + "loss": 0.5609, + "step": 300 + }, + { + "epoch": 0.03, + "learning_rate": 1.6768802228412256e-05, + "loss": 0.5438, + "step": 301 + }, + { + "epoch": 0.03, + "learning_rate": 1.682451253481894e-05, + "loss": 0.5241, + "step": 302 + }, + { + "epoch": 0.03, + "learning_rate": 1.688022284122563e-05, + "loss": 0.5318, + "step": 303 + }, + { + "epoch": 0.03, + "learning_rate": 1.6935933147632312e-05, + "loss": 0.539, + "step": 304 + }, + { + "epoch": 0.03, + "learning_rate": 1.6991643454039e-05, + "loss": 0.5516, + "step": 305 + }, + { + "epoch": 0.03, + "learning_rate": 1.7047353760445685e-05, + "loss": 0.5418, + "step": 306 + }, + { + "epoch": 0.03, + "learning_rate": 1.7103064066852367e-05, + "loss": 0.5453, + "step": 307 + }, + { + "epoch": 0.03, + "learning_rate": 1.7158774373259056e-05, + "loss": 0.5144, + "step": 308 + }, + { + "epoch": 0.03, + "learning_rate": 1.721448467966574e-05, + "loss": 0.5553, + "step": 309 + }, + { + "epoch": 0.03, + "learning_rate": 1.7270194986072423e-05, + "loss": 0.5618, + "step": 310 + }, + { + "epoch": 0.03, + "learning_rate": 1.732590529247911e-05, + "loss": 0.525, + "step": 311 + }, + { + "epoch": 0.03, + "learning_rate": 1.7381615598885796e-05, + "loss": 0.5315, + "step": 312 + }, + { + "epoch": 0.03, + "learning_rate": 1.743732590529248e-05, + "loss": 0.5413, + "step": 313 + }, + { + "epoch": 0.03, + "learning_rate": 1.7493036211699167e-05, + "loss": 0.549, + "step": 314 + }, + { + "epoch": 0.03, + "learning_rate": 1.7548746518105852e-05, + "loss": 0.5299, + "step": 315 + }, + { + "epoch": 0.03, + "learning_rate": 1.7604456824512537e-05, + "loss": 0.5693, + "step": 316 + }, + { + "epoch": 0.03, + "learning_rate": 1.7660167130919222e-05, + "loss": 0.5535, + "step": 317 + }, + { + "epoch": 0.03, + "learning_rate": 1.7715877437325907e-05, + "loss": 0.5383, + "step": 318 + }, + { + "epoch": 0.03, + "learning_rate": 1.7771587743732592e-05, + "loss": 0.5564, + "step": 319 + }, + { + "epoch": 0.03, + "learning_rate": 1.7827298050139278e-05, + "loss": 0.5521, + "step": 320 + }, + { + "epoch": 0.03, + "learning_rate": 1.7883008356545963e-05, + "loss": 0.5272, + "step": 321 + }, + { + "epoch": 0.03, + "learning_rate": 1.7938718662952648e-05, + "loss": 0.5204, + "step": 322 + }, + { + "epoch": 0.03, + "learning_rate": 1.7994428969359333e-05, + "loss": 0.5537, + "step": 323 + }, + { + "epoch": 0.03, + "learning_rate": 1.8050139275766018e-05, + "loss": 0.5412, + "step": 324 + }, + { + "epoch": 0.03, + "learning_rate": 1.8105849582172703e-05, + "loss": 0.5343, + "step": 325 + }, + { + "epoch": 0.03, + "learning_rate": 1.816155988857939e-05, + "loss": 0.5388, + "step": 326 + }, + { + "epoch": 0.03, + "learning_rate": 1.8217270194986074e-05, + "loss": 0.5325, + "step": 327 + }, + { + "epoch": 0.03, + "learning_rate": 1.827298050139276e-05, + "loss": 0.525, + "step": 328 + }, + { + "epoch": 0.03, + "learning_rate": 1.8328690807799444e-05, + "loss": 0.5467, + "step": 329 + }, + { + "epoch": 0.03, + "learning_rate": 1.838440111420613e-05, + "loss": 0.5329, + "step": 330 + }, + { + "epoch": 0.03, + "learning_rate": 1.8440111420612814e-05, + "loss": 0.5338, + "step": 331 + }, + { + "epoch": 0.03, + "learning_rate": 1.84958217270195e-05, + "loss": 0.5236, + "step": 332 + }, + { + "epoch": 0.03, + "learning_rate": 1.8551532033426184e-05, + "loss": 0.5235, + "step": 333 + }, + { + "epoch": 0.03, + "learning_rate": 1.8607242339832873e-05, + "loss": 0.5295, + "step": 334 + }, + { + "epoch": 0.03, + "learning_rate": 1.8662952646239555e-05, + "loss": 0.5306, + "step": 335 + }, + { + "epoch": 0.03, + "learning_rate": 1.871866295264624e-05, + "loss": 0.5102, + "step": 336 + }, + { + "epoch": 0.03, + "learning_rate": 1.877437325905293e-05, + "loss": 0.5463, + "step": 337 + }, + { + "epoch": 0.03, + "learning_rate": 1.883008356545961e-05, + "loss": 0.5163, + "step": 338 + }, + { + "epoch": 0.03, + "learning_rate": 1.8885793871866295e-05, + "loss": 0.5452, + "step": 339 + }, + { + "epoch": 0.03, + "learning_rate": 1.8941504178272984e-05, + "loss": 0.547, + "step": 340 + }, + { + "epoch": 0.03, + "learning_rate": 1.8997214484679666e-05, + "loss": 0.5442, + "step": 341 + }, + { + "epoch": 0.03, + "learning_rate": 1.9052924791086354e-05, + "loss": 0.5389, + "step": 342 + }, + { + "epoch": 0.03, + "learning_rate": 1.910863509749304e-05, + "loss": 0.5253, + "step": 343 + }, + { + "epoch": 0.03, + "learning_rate": 1.916434540389972e-05, + "loss": 0.5252, + "step": 344 + }, + { + "epoch": 0.03, + "learning_rate": 1.922005571030641e-05, + "loss": 0.5388, + "step": 345 + }, + { + "epoch": 0.03, + "learning_rate": 1.9275766016713095e-05, + "loss": 0.5336, + "step": 346 + }, + { + "epoch": 0.03, + "learning_rate": 1.9331476323119776e-05, + "loss": 0.5342, + "step": 347 + }, + { + "epoch": 0.03, + "learning_rate": 1.9387186629526465e-05, + "loss": 0.5227, + "step": 348 + }, + { + "epoch": 0.03, + "learning_rate": 1.944289693593315e-05, + "loss": 0.5062, + "step": 349 + }, + { + "epoch": 0.03, + "learning_rate": 1.9498607242339835e-05, + "loss": 0.5286, + "step": 350 + }, + { + "epoch": 0.03, + "learning_rate": 1.955431754874652e-05, + "loss": 0.5326, + "step": 351 + }, + { + "epoch": 0.03, + "learning_rate": 1.9610027855153206e-05, + "loss": 0.5219, + "step": 352 + }, + { + "epoch": 0.03, + "learning_rate": 1.966573816155989e-05, + "loss": 0.5258, + "step": 353 + }, + { + "epoch": 0.03, + "learning_rate": 1.9721448467966576e-05, + "loss": 0.5307, + "step": 354 + }, + { + "epoch": 0.03, + "learning_rate": 1.977715877437326e-05, + "loss": 0.5314, + "step": 355 + }, + { + "epoch": 0.03, + "learning_rate": 1.9832869080779946e-05, + "loss": 0.5438, + "step": 356 + }, + { + "epoch": 0.03, + "learning_rate": 1.988857938718663e-05, + "loss": 0.5321, + "step": 357 + }, + { + "epoch": 0.03, + "learning_rate": 1.9944289693593316e-05, + "loss": 0.5139, + "step": 358 + }, + { + "epoch": 0.03, + "learning_rate": 2e-05, + "loss": 0.5207, + "step": 359 + }, + { + "epoch": 0.03, + "learning_rate": 1.99999996328208e-05, + "loss": 0.5364, + "step": 360 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999998531283215e-05, + "loss": 0.54, + "step": 361 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999996695387335e-05, + "loss": 0.5216, + "step": 362 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999994125133287e-05, + "loss": 0.5454, + "step": 363 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999990820521264e-05, + "loss": 0.5464, + "step": 364 + }, + { + "epoch": 0.03, + "learning_rate": 1.999998678155151e-05, + "loss": 0.5201, + "step": 365 + }, + { + "epoch": 0.03, + "learning_rate": 1.999998200822432e-05, + "loss": 0.541, + "step": 366 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999976500540042e-05, + "loss": 0.5372, + "step": 367 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999970258499083e-05, + "loss": 0.5408, + "step": 368 + }, + { + "epoch": 0.03, + "learning_rate": 1.99999632821019e-05, + "loss": 0.5416, + "step": 369 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999955571349014e-05, + "loss": 0.5459, + "step": 370 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999947126240977e-05, + "loss": 0.5258, + "step": 371 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999937946778418e-05, + "loss": 0.5256, + "step": 372 + }, + { + "epoch": 0.03, + "learning_rate": 1.999992803296201e-05, + "loss": 0.5362, + "step": 373 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999917384792477e-05, + "loss": 0.5381, + "step": 374 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999906002270605e-05, + "loss": 0.536, + "step": 375 + }, + { + "epoch": 0.03, + "learning_rate": 1.999989388539723e-05, + "loss": 0.5304, + "step": 376 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999881034173242e-05, + "loss": 0.5351, + "step": 377 + }, + { + "epoch": 0.03, + "learning_rate": 1.999986744859958e-05, + "loss": 0.5387, + "step": 378 + }, + { + "epoch": 0.03, + "learning_rate": 1.999985312867725e-05, + "loss": 0.5333, + "step": 379 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999838074407296e-05, + "loss": 0.5152, + "step": 380 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999822285790825e-05, + "loss": 0.516, + "step": 381 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999805762829e-05, + "loss": 0.539, + "step": 382 + }, + { + "epoch": 0.03, + "learning_rate": 1.999978850552303e-05, + "loss": 0.5299, + "step": 383 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999770513874187e-05, + "loss": 0.5556, + "step": 384 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999751787883787e-05, + "loss": 0.5509, + "step": 385 + }, + { + "epoch": 0.03, + "learning_rate": 1.999973232755321e-05, + "loss": 0.5262, + "step": 386 + }, + { + "epoch": 0.03, + "learning_rate": 1.999971213288388e-05, + "loss": 0.5146, + "step": 387 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999691203877286e-05, + "loss": 0.5112, + "step": 388 + }, + { + "epoch": 0.03, + "learning_rate": 1.999966954053496e-05, + "loss": 0.544, + "step": 389 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999647142858496e-05, + "loss": 0.519, + "step": 390 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999624010849536e-05, + "loss": 0.5349, + "step": 391 + }, + { + "epoch": 0.03, + "learning_rate": 1.999960014450978e-05, + "loss": 0.5184, + "step": 392 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999575543840982e-05, + "loss": 0.5374, + "step": 393 + }, + { + "epoch": 0.03, + "learning_rate": 1.999955020884495e-05, + "loss": 0.5205, + "step": 394 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999524139523538e-05, + "loss": 0.5536, + "step": 395 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999497335878666e-05, + "loss": 0.5277, + "step": 396 + }, + { + "epoch": 0.03, + "learning_rate": 1.99994697979123e-05, + "loss": 0.5181, + "step": 397 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999441525626464e-05, + "loss": 0.5173, + "step": 398 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999412519023233e-05, + "loss": 0.5443, + "step": 399 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999382778104734e-05, + "loss": 0.5279, + "step": 400 + }, + { + "epoch": 0.03, + "learning_rate": 1.999935230287316e-05, + "loss": 0.5472, + "step": 401 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999321093330736e-05, + "loss": 0.5348, + "step": 402 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999289149479767e-05, + "loss": 0.5534, + "step": 403 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999256471322593e-05, + "loss": 0.5447, + "step": 404 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999223058861613e-05, + "loss": 0.5312, + "step": 405 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999188912099278e-05, + "loss": 0.5267, + "step": 406 + }, + { + "epoch": 0.03, + "learning_rate": 1.99991540310381e-05, + "loss": 0.5221, + "step": 407 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999118415680642e-05, + "loss": 0.5456, + "step": 408 + }, + { + "epoch": 0.03, + "learning_rate": 1.999908206602952e-05, + "loss": 0.5202, + "step": 409 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999044982087394e-05, + "loss": 0.5202, + "step": 410 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999007163856998e-05, + "loss": 0.5302, + "step": 411 + }, + { + "epoch": 0.03, + "learning_rate": 1.9998968611341102e-05, + "loss": 0.5081, + "step": 412 + }, + { + "epoch": 0.03, + "learning_rate": 1.9998929324542543e-05, + "loss": 0.5599, + "step": 413 + }, + { + "epoch": 0.03, + "learning_rate": 1.99988893034642e-05, + "loss": 0.5327, + "step": 414 + }, + { + "epoch": 0.03, + "learning_rate": 1.9998848548109017e-05, + "loss": 0.5236, + "step": 415 + }, + { + "epoch": 0.03, + "learning_rate": 1.9998807058479986e-05, + "loss": 0.5366, + "step": 416 + }, + { + "epoch": 0.03, + "learning_rate": 1.9998764834580147e-05, + "loss": 0.5525, + "step": 417 + }, + { + "epoch": 0.03, + "learning_rate": 1.9998721876412613e-05, + "loss": 0.5199, + "step": 418 + }, + { + "epoch": 0.04, + "learning_rate": 1.9998678183980532e-05, + "loss": 0.518, + "step": 419 + }, + { + "epoch": 0.04, + "learning_rate": 1.999863375728711e-05, + "loss": 0.5472, + "step": 420 + }, + { + "epoch": 0.04, + "learning_rate": 1.9998588596335612e-05, + "loss": 0.5363, + "step": 421 + }, + { + "epoch": 0.04, + "learning_rate": 1.9998542701129357e-05, + "loss": 0.5383, + "step": 422 + }, + { + "epoch": 0.04, + "learning_rate": 1.999849607167171e-05, + "loss": 0.5367, + "step": 423 + }, + { + "epoch": 0.04, + "learning_rate": 1.99984487079661e-05, + "loss": 0.5358, + "step": 424 + }, + { + "epoch": 0.04, + "learning_rate": 1.9998400610016003e-05, + "loss": 0.5414, + "step": 425 + }, + { + "epoch": 0.04, + "learning_rate": 1.9998351777824956e-05, + "loss": 0.5361, + "step": 426 + }, + { + "epoch": 0.04, + "learning_rate": 1.9998302211396537e-05, + "loss": 0.5266, + "step": 427 + }, + { + "epoch": 0.04, + "learning_rate": 1.999825191073439e-05, + "loss": 0.5149, + "step": 428 + }, + { + "epoch": 0.04, + "learning_rate": 1.9998200875842206e-05, + "loss": 0.5253, + "step": 429 + }, + { + "epoch": 0.04, + "learning_rate": 1.9998149106723737e-05, + "loss": 0.5362, + "step": 430 + }, + { + "epoch": 0.04, + "learning_rate": 1.9998096603382785e-05, + "loss": 0.5377, + "step": 431 + }, + { + "epoch": 0.04, + "learning_rate": 1.9998043365823205e-05, + "loss": 0.5397, + "step": 432 + }, + { + "epoch": 0.04, + "learning_rate": 1.99979893940489e-05, + "loss": 0.5267, + "step": 433 + }, + { + "epoch": 0.04, + "learning_rate": 1.999793468806384e-05, + "loss": 0.5379, + "step": 434 + }, + { + "epoch": 0.04, + "learning_rate": 1.9997879247872042e-05, + "loss": 0.5283, + "step": 435 + }, + { + "epoch": 0.04, + "learning_rate": 1.9997823073477577e-05, + "loss": 0.5098, + "step": 436 + }, + { + "epoch": 0.04, + "learning_rate": 1.9997766164884572e-05, + "loss": 0.5102, + "step": 437 + }, + { + "epoch": 0.04, + "learning_rate": 1.9997708522097202e-05, + "loss": 0.5374, + "step": 438 + }, + { + "epoch": 0.04, + "learning_rate": 1.9997650145119702e-05, + "loss": 0.5158, + "step": 439 + }, + { + "epoch": 0.04, + "learning_rate": 1.9997591033956353e-05, + "loss": 0.5019, + "step": 440 + }, + { + "epoch": 0.04, + "learning_rate": 1.9997531188611507e-05, + "loss": 0.5368, + "step": 441 + }, + { + "epoch": 0.04, + "learning_rate": 1.999747060908955e-05, + "loss": 0.5247, + "step": 442 + }, + { + "epoch": 0.04, + "learning_rate": 1.9997409295394938e-05, + "loss": 0.5346, + "step": 443 + }, + { + "epoch": 0.04, + "learning_rate": 1.999734724753217e-05, + "loss": 0.5386, + "step": 444 + }, + { + "epoch": 0.04, + "learning_rate": 1.99972844655058e-05, + "loss": 0.5305, + "step": 445 + }, + { + "epoch": 0.04, + "learning_rate": 1.999722094932044e-05, + "loss": 0.5347, + "step": 446 + }, + { + "epoch": 0.04, + "learning_rate": 1.9997156698980755e-05, + "loss": 0.5309, + "step": 447 + }, + { + "epoch": 0.04, + "learning_rate": 1.9997091714491465e-05, + "loss": 0.5383, + "step": 448 + }, + { + "epoch": 0.04, + "learning_rate": 1.999702599585734e-05, + "loss": 0.524, + "step": 449 + }, + { + "epoch": 0.04, + "learning_rate": 1.9996959543083207e-05, + "loss": 0.5387, + "step": 450 + }, + { + "epoch": 0.04, + "learning_rate": 1.9996892356173946e-05, + "loss": 0.5336, + "step": 451 + }, + { + "epoch": 0.04, + "learning_rate": 1.9996824435134486e-05, + "loss": 0.5338, + "step": 452 + }, + { + "epoch": 0.04, + "learning_rate": 1.9996755779969827e-05, + "loss": 0.5231, + "step": 453 + }, + { + "epoch": 0.04, + "learning_rate": 1.9996686390685e-05, + "loss": 0.5371, + "step": 454 + }, + { + "epoch": 0.04, + "learning_rate": 1.9996616267285104e-05, + "loss": 0.5467, + "step": 455 + }, + { + "epoch": 0.04, + "learning_rate": 1.9996545409775286e-05, + "loss": 0.5239, + "step": 456 + }, + { + "epoch": 0.04, + "learning_rate": 1.9996473818160752e-05, + "loss": 0.5296, + "step": 457 + }, + { + "epoch": 0.04, + "learning_rate": 1.999640149244676e-05, + "loss": 0.5514, + "step": 458 + }, + { + "epoch": 0.04, + "learning_rate": 1.9996328432638622e-05, + "loss": 0.5196, + "step": 459 + }, + { + "epoch": 0.04, + "learning_rate": 1.9996254638741702e-05, + "loss": 0.5297, + "step": 460 + }, + { + "epoch": 0.04, + "learning_rate": 1.999618011076142e-05, + "loss": 0.5309, + "step": 461 + }, + { + "epoch": 0.04, + "learning_rate": 1.9996104848703243e-05, + "loss": 0.5313, + "step": 462 + }, + { + "epoch": 0.04, + "learning_rate": 1.9996028852572705e-05, + "loss": 0.5292, + "step": 463 + }, + { + "epoch": 0.04, + "learning_rate": 1.9995952122375385e-05, + "loss": 0.5368, + "step": 464 + }, + { + "epoch": 0.04, + "learning_rate": 1.9995874658116917e-05, + "loss": 0.5373, + "step": 465 + }, + { + "epoch": 0.04, + "learning_rate": 1.999579645980299e-05, + "loss": 0.5392, + "step": 466 + }, + { + "epoch": 0.04, + "learning_rate": 1.9995717527439348e-05, + "loss": 0.5315, + "step": 467 + }, + { + "epoch": 0.04, + "learning_rate": 1.9995637861031786e-05, + "loss": 0.5325, + "step": 468 + }, + { + "epoch": 0.04, + "learning_rate": 1.9995557460586153e-05, + "loss": 0.5468, + "step": 469 + }, + { + "epoch": 0.04, + "learning_rate": 1.9995476326108355e-05, + "loss": 0.5525, + "step": 470 + }, + { + "epoch": 0.04, + "learning_rate": 1.9995394457604354e-05, + "loss": 0.5133, + "step": 471 + }, + { + "epoch": 0.04, + "learning_rate": 1.9995311855080155e-05, + "loss": 0.5228, + "step": 472 + }, + { + "epoch": 0.04, + "learning_rate": 1.9995228518541828e-05, + "loss": 0.5394, + "step": 473 + }, + { + "epoch": 0.04, + "learning_rate": 1.999514444799549e-05, + "loss": 0.5449, + "step": 474 + }, + { + "epoch": 0.04, + "learning_rate": 1.9995059643447313e-05, + "loss": 0.5181, + "step": 475 + }, + { + "epoch": 0.04, + "learning_rate": 1.9994974104903536e-05, + "loss": 0.533, + "step": 476 + }, + { + "epoch": 0.04, + "learning_rate": 1.999488783237043e-05, + "loss": 0.5344, + "step": 477 + }, + { + "epoch": 0.04, + "learning_rate": 1.999480082585433e-05, + "loss": 0.5248, + "step": 478 + }, + { + "epoch": 0.04, + "learning_rate": 1.999471308536163e-05, + "loss": 0.5394, + "step": 479 + }, + { + "epoch": 0.04, + "learning_rate": 1.9994624610898778e-05, + "loss": 0.5263, + "step": 480 + }, + { + "epoch": 0.04, + "learning_rate": 1.999453540247226e-05, + "loss": 0.5065, + "step": 481 + }, + { + "epoch": 0.04, + "learning_rate": 1.9994445460088635e-05, + "loss": 0.5423, + "step": 482 + }, + { + "epoch": 0.04, + "learning_rate": 1.9994354783754504e-05, + "loss": 0.5219, + "step": 483 + }, + { + "epoch": 0.04, + "learning_rate": 1.9994263373476526e-05, + "loss": 0.5298, + "step": 484 + }, + { + "epoch": 0.04, + "learning_rate": 1.9994171229261417e-05, + "loss": 0.5212, + "step": 485 + }, + { + "epoch": 0.04, + "learning_rate": 1.999407835111594e-05, + "loss": 0.5283, + "step": 486 + }, + { + "epoch": 0.04, + "learning_rate": 1.999398473904692e-05, + "loss": 0.5377, + "step": 487 + }, + { + "epoch": 0.04, + "learning_rate": 1.999389039306123e-05, + "loss": 0.536, + "step": 488 + }, + { + "epoch": 0.04, + "learning_rate": 1.9993795313165795e-05, + "loss": 0.5229, + "step": 489 + }, + { + "epoch": 0.04, + "learning_rate": 1.99936994993676e-05, + "loss": 0.5259, + "step": 490 + }, + { + "epoch": 0.04, + "learning_rate": 1.999360295167368e-05, + "loss": 0.5236, + "step": 491 + }, + { + "epoch": 0.04, + "learning_rate": 1.9993505670091123e-05, + "loss": 0.5245, + "step": 492 + }, + { + "epoch": 0.04, + "learning_rate": 1.999340765462708e-05, + "loss": 0.5348, + "step": 493 + }, + { + "epoch": 0.04, + "learning_rate": 1.9993308905288745e-05, + "loss": 0.5415, + "step": 494 + }, + { + "epoch": 0.04, + "learning_rate": 1.9993209422083367e-05, + "loss": 0.5391, + "step": 495 + }, + { + "epoch": 0.04, + "learning_rate": 1.999310920501825e-05, + "loss": 0.5202, + "step": 496 + }, + { + "epoch": 0.04, + "learning_rate": 1.9993008254100765e-05, + "loss": 0.5172, + "step": 497 + }, + { + "epoch": 0.04, + "learning_rate": 1.9992906569338314e-05, + "loss": 0.534, + "step": 498 + }, + { + "epoch": 0.04, + "learning_rate": 1.999280415073837e-05, + "loss": 0.5294, + "step": 499 + }, + { + "epoch": 0.04, + "learning_rate": 1.9992700998308453e-05, + "loss": 0.5486, + "step": 500 + }, + { + "epoch": 0.04, + "learning_rate": 1.9992597112056134e-05, + "loss": 0.5134, + "step": 501 + }, + { + "epoch": 0.04, + "learning_rate": 1.9992492491989045e-05, + "loss": 0.5241, + "step": 502 + }, + { + "epoch": 0.04, + "learning_rate": 1.999238713811487e-05, + "loss": 0.528, + "step": 503 + }, + { + "epoch": 0.04, + "learning_rate": 1.999228105044135e-05, + "loss": 0.5463, + "step": 504 + }, + { + "epoch": 0.04, + "learning_rate": 1.9992174228976265e-05, + "loss": 0.5119, + "step": 505 + }, + { + "epoch": 0.04, + "learning_rate": 1.999206667372747e-05, + "loss": 0.5352, + "step": 506 + }, + { + "epoch": 0.04, + "learning_rate": 1.9991958384702855e-05, + "loss": 0.5365, + "step": 507 + }, + { + "epoch": 0.04, + "learning_rate": 1.999184936191038e-05, + "loss": 0.5205, + "step": 508 + }, + { + "epoch": 0.04, + "learning_rate": 1.9991739605358042e-05, + "loss": 0.5034, + "step": 509 + }, + { + "epoch": 0.04, + "learning_rate": 1.9991629115053908e-05, + "loss": 0.5319, + "step": 510 + }, + { + "epoch": 0.04, + "learning_rate": 1.999151789100609e-05, + "loss": 0.5195, + "step": 511 + }, + { + "epoch": 0.04, + "learning_rate": 1.9991405933222758e-05, + "loss": 0.5319, + "step": 512 + }, + { + "epoch": 0.04, + "learning_rate": 1.9991293241712128e-05, + "loss": 0.5359, + "step": 513 + }, + { + "epoch": 0.04, + "learning_rate": 1.999117981648248e-05, + "loss": 0.5251, + "step": 514 + }, + { + "epoch": 0.04, + "learning_rate": 1.9991065657542146e-05, + "loss": 0.5134, + "step": 515 + }, + { + "epoch": 0.04, + "learning_rate": 1.9990950764899502e-05, + "loss": 0.5365, + "step": 516 + }, + { + "epoch": 0.04, + "learning_rate": 1.999083513856299e-05, + "loss": 0.5388, + "step": 517 + }, + { + "epoch": 0.04, + "learning_rate": 1.99907187785411e-05, + "loss": 0.5144, + "step": 518 + }, + { + "epoch": 0.04, + "learning_rate": 1.9990601684842385e-05, + "loss": 0.5203, + "step": 519 + }, + { + "epoch": 0.04, + "learning_rate": 1.9990483857475428e-05, + "loss": 0.5384, + "step": 520 + }, + { + "epoch": 0.04, + "learning_rate": 1.9990365296448892e-05, + "loss": 0.5309, + "step": 521 + }, + { + "epoch": 0.04, + "learning_rate": 1.999024600177148e-05, + "loss": 0.5405, + "step": 522 + }, + { + "epoch": 0.04, + "learning_rate": 1.9990125973451956e-05, + "loss": 0.5271, + "step": 523 + }, + { + "epoch": 0.04, + "learning_rate": 1.9990005211499137e-05, + "loss": 0.5266, + "step": 524 + }, + { + "epoch": 0.04, + "learning_rate": 1.998988371592188e-05, + "loss": 0.521, + "step": 525 + }, + { + "epoch": 0.04, + "learning_rate": 1.998976148672912e-05, + "loss": 0.5432, + "step": 526 + }, + { + "epoch": 0.04, + "learning_rate": 1.998963852392982e-05, + "loss": 0.5378, + "step": 527 + }, + { + "epoch": 0.04, + "learning_rate": 1.998951482753302e-05, + "loss": 0.5218, + "step": 528 + }, + { + "epoch": 0.04, + "learning_rate": 1.99893903975478e-05, + "loss": 0.5309, + "step": 529 + }, + { + "epoch": 0.04, + "learning_rate": 1.99892652339833e-05, + "loss": 0.5238, + "step": 530 + }, + { + "epoch": 0.04, + "learning_rate": 1.9989139336848708e-05, + "loss": 0.5364, + "step": 531 + }, + { + "epoch": 0.04, + "learning_rate": 1.9989012706153273e-05, + "loss": 0.5396, + "step": 532 + }, + { + "epoch": 0.04, + "learning_rate": 1.9988885341906292e-05, + "loss": 0.5236, + "step": 533 + }, + { + "epoch": 0.04, + "learning_rate": 1.9988757244117118e-05, + "loss": 0.5107, + "step": 534 + }, + { + "epoch": 0.04, + "learning_rate": 1.9988628412795158e-05, + "loss": 0.5068, + "step": 535 + }, + { + "epoch": 0.04, + "learning_rate": 1.9988498847949872e-05, + "loss": 0.5272, + "step": 536 + }, + { + "epoch": 0.04, + "learning_rate": 1.9988368549590778e-05, + "loss": 0.5193, + "step": 537 + }, + { + "epoch": 0.05, + "learning_rate": 1.998823751772744e-05, + "loss": 0.5314, + "step": 538 + }, + { + "epoch": 0.05, + "learning_rate": 1.9988105752369487e-05, + "loss": 0.524, + "step": 539 + }, + { + "epoch": 0.05, + "learning_rate": 1.998797325352659e-05, + "loss": 0.51, + "step": 540 + }, + { + "epoch": 0.05, + "learning_rate": 1.9987840021208477e-05, + "loss": 0.5412, + "step": 541 + }, + { + "epoch": 0.05, + "learning_rate": 1.9987706055424935e-05, + "loss": 0.5195, + "step": 542 + }, + { + "epoch": 0.05, + "learning_rate": 1.9987571356185807e-05, + "loss": 0.5251, + "step": 543 + }, + { + "epoch": 0.05, + "learning_rate": 1.9987435923500978e-05, + "loss": 0.5078, + "step": 544 + }, + { + "epoch": 0.05, + "learning_rate": 1.9987299757380393e-05, + "loss": 0.5461, + "step": 545 + }, + { + "epoch": 0.05, + "learning_rate": 1.998716285783406e-05, + "loss": 0.5278, + "step": 546 + }, + { + "epoch": 0.05, + "learning_rate": 1.998702522487202e-05, + "loss": 0.5154, + "step": 547 + }, + { + "epoch": 0.05, + "learning_rate": 1.998688685850439e-05, + "loss": 0.5246, + "step": 548 + }, + { + "epoch": 0.05, + "learning_rate": 1.998674775874133e-05, + "loss": 0.5102, + "step": 549 + }, + { + "epoch": 0.05, + "learning_rate": 1.9986607925593046e-05, + "loss": 0.5195, + "step": 550 + }, + { + "epoch": 0.05, + "learning_rate": 1.998646735906982e-05, + "loss": 0.5231, + "step": 551 + }, + { + "epoch": 0.05, + "learning_rate": 1.9986326059181965e-05, + "loss": 0.5364, + "step": 552 + }, + { + "epoch": 0.05, + "learning_rate": 1.998618402593986e-05, + "loss": 0.5223, + "step": 553 + }, + { + "epoch": 0.05, + "learning_rate": 1.9986041259353937e-05, + "loss": 0.5358, + "step": 554 + }, + { + "epoch": 0.05, + "learning_rate": 1.9985897759434677e-05, + "loss": 0.5318, + "step": 555 + }, + { + "epoch": 0.05, + "learning_rate": 1.998575352619262e-05, + "loss": 0.5339, + "step": 556 + }, + { + "epoch": 0.05, + "learning_rate": 1.9985608559638364e-05, + "loss": 0.5275, + "step": 557 + }, + { + "epoch": 0.05, + "learning_rate": 1.9985462859782544e-05, + "loss": 0.5343, + "step": 558 + }, + { + "epoch": 0.05, + "learning_rate": 1.9985316426635863e-05, + "loss": 0.5217, + "step": 559 + }, + { + "epoch": 0.05, + "learning_rate": 1.9985169260209075e-05, + "loss": 0.5284, + "step": 560 + }, + { + "epoch": 0.05, + "learning_rate": 1.998502136051299e-05, + "loss": 0.5254, + "step": 561 + }, + { + "epoch": 0.05, + "learning_rate": 1.9984872727558468e-05, + "loss": 0.5316, + "step": 562 + }, + { + "epoch": 0.05, + "learning_rate": 1.998472336135642e-05, + "loss": 0.525, + "step": 563 + }, + { + "epoch": 0.05, + "learning_rate": 1.9984573261917825e-05, + "loss": 0.5241, + "step": 564 + }, + { + "epoch": 0.05, + "learning_rate": 1.998442242925369e-05, + "loss": 0.5233, + "step": 565 + }, + { + "epoch": 0.05, + "learning_rate": 1.9984270863375105e-05, + "loss": 0.5282, + "step": 566 + }, + { + "epoch": 0.05, + "learning_rate": 1.9984118564293197e-05, + "loss": 0.5263, + "step": 567 + }, + { + "epoch": 0.05, + "learning_rate": 1.9983965532019142e-05, + "loss": 0.5201, + "step": 568 + }, + { + "epoch": 0.05, + "learning_rate": 1.998381176656419e-05, + "loss": 0.5317, + "step": 569 + }, + { + "epoch": 0.05, + "learning_rate": 1.9983657267939627e-05, + "loss": 0.5263, + "step": 570 + }, + { + "epoch": 0.05, + "learning_rate": 1.99835020361568e-05, + "loss": 0.5158, + "step": 571 + }, + { + "epoch": 0.05, + "learning_rate": 1.9983346071227107e-05, + "loss": 0.5344, + "step": 572 + }, + { + "epoch": 0.05, + "learning_rate": 1.9983189373162003e-05, + "loss": 0.5306, + "step": 573 + }, + { + "epoch": 0.05, + "learning_rate": 1.9983031941972994e-05, + "loss": 0.5402, + "step": 574 + }, + { + "epoch": 0.05, + "learning_rate": 1.998287377767164e-05, + "loss": 0.5339, + "step": 575 + }, + { + "epoch": 0.05, + "learning_rate": 1.9982714880269557e-05, + "loss": 0.5216, + "step": 576 + }, + { + "epoch": 0.05, + "learning_rate": 1.998255524977842e-05, + "loss": 0.5053, + "step": 577 + }, + { + "epoch": 0.05, + "learning_rate": 1.9982394886209943e-05, + "loss": 0.5199, + "step": 578 + }, + { + "epoch": 0.05, + "learning_rate": 1.9982233789575904e-05, + "loss": 0.5293, + "step": 579 + }, + { + "epoch": 0.05, + "learning_rate": 1.9982071959888138e-05, + "loss": 0.5093, + "step": 580 + }, + { + "epoch": 0.05, + "learning_rate": 1.998190939715852e-05, + "loss": 0.5355, + "step": 581 + }, + { + "epoch": 0.05, + "learning_rate": 1.9981746101399e-05, + "loss": 0.5191, + "step": 582 + }, + { + "epoch": 0.05, + "learning_rate": 1.998158207262156e-05, + "loss": 0.5267, + "step": 583 + }, + { + "epoch": 0.05, + "learning_rate": 1.998141731083825e-05, + "loss": 0.5117, + "step": 584 + }, + { + "epoch": 0.05, + "learning_rate": 1.9981251816061168e-05, + "loss": 0.5119, + "step": 585 + }, + { + "epoch": 0.05, + "learning_rate": 1.9981085588302468e-05, + "loss": 0.518, + "step": 586 + }, + { + "epoch": 0.05, + "learning_rate": 1.998091862757436e-05, + "loss": 0.5203, + "step": 587 + }, + { + "epoch": 0.05, + "learning_rate": 1.9980750933889098e-05, + "loss": 0.5326, + "step": 588 + }, + { + "epoch": 0.05, + "learning_rate": 1.9980582507259e-05, + "loss": 0.5318, + "step": 589 + }, + { + "epoch": 0.05, + "learning_rate": 1.998041334769644e-05, + "loss": 0.5275, + "step": 590 + }, + { + "epoch": 0.05, + "learning_rate": 1.998024345521383e-05, + "loss": 0.5346, + "step": 591 + }, + { + "epoch": 0.05, + "learning_rate": 1.9980072829823656e-05, + "loss": 0.5313, + "step": 592 + }, + { + "epoch": 0.05, + "learning_rate": 1.9979901471538442e-05, + "loss": 0.5433, + "step": 593 + }, + { + "epoch": 0.05, + "learning_rate": 1.997972938037077e-05, + "loss": 0.5223, + "step": 594 + }, + { + "epoch": 0.05, + "learning_rate": 1.9979556556333283e-05, + "loss": 0.5244, + "step": 595 + }, + { + "epoch": 0.05, + "learning_rate": 1.9979382999438672e-05, + "loss": 0.5391, + "step": 596 + }, + { + "epoch": 0.05, + "learning_rate": 1.997920870969968e-05, + "loss": 0.5366, + "step": 597 + }, + { + "epoch": 0.05, + "learning_rate": 1.997903368712911e-05, + "loss": 0.518, + "step": 598 + }, + { + "epoch": 0.05, + "learning_rate": 1.9978857931739805e-05, + "loss": 0.5125, + "step": 599 + }, + { + "epoch": 0.05, + "learning_rate": 1.9978681443544687e-05, + "loss": 0.5062, + "step": 600 + }, + { + "epoch": 0.05, + "learning_rate": 1.9978504222556704e-05, + "loss": 0.51, + "step": 601 + }, + { + "epoch": 0.05, + "learning_rate": 1.9978326268788873e-05, + "loss": 0.5224, + "step": 602 + }, + { + "epoch": 0.05, + "learning_rate": 1.9978147582254266e-05, + "loss": 0.5183, + "step": 603 + }, + { + "epoch": 0.05, + "learning_rate": 1.9977968162966e-05, + "loss": 0.529, + "step": 604 + }, + { + "epoch": 0.05, + "learning_rate": 1.997778801093726e-05, + "loss": 0.5163, + "step": 605 + }, + { + "epoch": 0.05, + "learning_rate": 1.9977607126181264e-05, + "loss": 0.508, + "step": 606 + }, + { + "epoch": 0.05, + "learning_rate": 1.9977425508711303e-05, + "loss": 0.5383, + "step": 607 + }, + { + "epoch": 0.05, + "learning_rate": 1.997724315854071e-05, + "loss": 0.5161, + "step": 608 + }, + { + "epoch": 0.05, + "learning_rate": 1.9977060075682878e-05, + "loss": 0.5294, + "step": 609 + }, + { + "epoch": 0.05, + "learning_rate": 1.997687626015125e-05, + "loss": 0.5113, + "step": 610 + }, + { + "epoch": 0.05, + "learning_rate": 1.997669171195933e-05, + "loss": 0.525, + "step": 611 + }, + { + "epoch": 0.05, + "learning_rate": 1.9976506431120665e-05, + "loss": 0.5313, + "step": 612 + }, + { + "epoch": 0.05, + "learning_rate": 1.9976320417648868e-05, + "loss": 0.5248, + "step": 613 + }, + { + "epoch": 0.05, + "learning_rate": 1.9976133671557587e-05, + "loss": 0.537, + "step": 614 + }, + { + "epoch": 0.05, + "learning_rate": 1.9975946192860544e-05, + "loss": 0.5232, + "step": 615 + }, + { + "epoch": 0.05, + "learning_rate": 1.9975757981571512e-05, + "loss": 0.5132, + "step": 616 + }, + { + "epoch": 0.05, + "learning_rate": 1.99755690377043e-05, + "loss": 0.531, + "step": 617 + }, + { + "epoch": 0.05, + "learning_rate": 1.997537936127279e-05, + "loss": 0.532, + "step": 618 + }, + { + "epoch": 0.05, + "learning_rate": 1.9975188952290915e-05, + "loss": 0.5399, + "step": 619 + }, + { + "epoch": 0.05, + "learning_rate": 1.997499781077265e-05, + "loss": 0.5195, + "step": 620 + }, + { + "epoch": 0.05, + "learning_rate": 1.997480593673203e-05, + "loss": 0.5213, + "step": 621 + }, + { + "epoch": 0.05, + "learning_rate": 1.9974613330183156e-05, + "loss": 0.5198, + "step": 622 + }, + { + "epoch": 0.05, + "learning_rate": 1.997441999114017e-05, + "loss": 0.5242, + "step": 623 + }, + { + "epoch": 0.05, + "learning_rate": 1.9974225919617258e-05, + "loss": 0.5376, + "step": 624 + }, + { + "epoch": 0.05, + "learning_rate": 1.9974031115628688e-05, + "loss": 0.521, + "step": 625 + }, + { + "epoch": 0.05, + "learning_rate": 1.9973835579188753e-05, + "loss": 0.5179, + "step": 626 + }, + { + "epoch": 0.05, + "learning_rate": 1.997363931031182e-05, + "loss": 0.5341, + "step": 627 + }, + { + "epoch": 0.05, + "learning_rate": 1.9973442309012296e-05, + "loss": 0.4995, + "step": 628 + }, + { + "epoch": 0.05, + "learning_rate": 1.9973244575304657e-05, + "loss": 0.5421, + "step": 629 + }, + { + "epoch": 0.05, + "learning_rate": 1.9973046109203414e-05, + "loss": 0.5164, + "step": 630 + }, + { + "epoch": 0.05, + "learning_rate": 1.9972846910723146e-05, + "loss": 0.5236, + "step": 631 + }, + { + "epoch": 0.05, + "learning_rate": 1.9972646979878483e-05, + "loss": 0.5341, + "step": 632 + }, + { + "epoch": 0.05, + "learning_rate": 1.9972446316684106e-05, + "loss": 0.5337, + "step": 633 + }, + { + "epoch": 0.05, + "learning_rate": 1.9972244921154746e-05, + "loss": 0.5226, + "step": 634 + }, + { + "epoch": 0.05, + "learning_rate": 1.9972042793305196e-05, + "loss": 0.5177, + "step": 635 + }, + { + "epoch": 0.05, + "learning_rate": 1.9971839933150307e-05, + "loss": 0.5229, + "step": 636 + }, + { + "epoch": 0.05, + "learning_rate": 1.997163634070496e-05, + "loss": 0.513, + "step": 637 + }, + { + "epoch": 0.05, + "learning_rate": 1.9971432015984126e-05, + "loss": 0.5055, + "step": 638 + }, + { + "epoch": 0.05, + "learning_rate": 1.9971226959002796e-05, + "loss": 0.4982, + "step": 639 + }, + { + "epoch": 0.05, + "learning_rate": 1.9971021169776024e-05, + "loss": 0.5206, + "step": 640 + }, + { + "epoch": 0.05, + "learning_rate": 1.9970814648318937e-05, + "loss": 0.4946, + "step": 641 + }, + { + "epoch": 0.05, + "learning_rate": 1.997060739464669e-05, + "loss": 0.5367, + "step": 642 + }, + { + "epoch": 0.05, + "learning_rate": 1.997039940877451e-05, + "loss": 0.5368, + "step": 643 + }, + { + "epoch": 0.05, + "learning_rate": 1.997019069071767e-05, + "loss": 0.5131, + "step": 644 + }, + { + "epoch": 0.05, + "learning_rate": 1.996998124049149e-05, + "loss": 0.5253, + "step": 645 + }, + { + "epoch": 0.05, + "learning_rate": 1.9969771058111357e-05, + "loss": 0.5273, + "step": 646 + }, + { + "epoch": 0.05, + "learning_rate": 1.9969560143592705e-05, + "loss": 0.5247, + "step": 647 + }, + { + "epoch": 0.05, + "learning_rate": 1.996934849695102e-05, + "loss": 0.5292, + "step": 648 + }, + { + "epoch": 0.05, + "learning_rate": 1.9969136118201852e-05, + "loss": 0.5262, + "step": 649 + }, + { + "epoch": 0.05, + "learning_rate": 1.9968923007360788e-05, + "loss": 0.5031, + "step": 650 + }, + { + "epoch": 0.05, + "learning_rate": 1.9968709164443483e-05, + "loss": 0.523, + "step": 651 + }, + { + "epoch": 0.05, + "learning_rate": 1.9968494589465645e-05, + "loss": 0.5326, + "step": 652 + }, + { + "epoch": 0.05, + "learning_rate": 1.996827928244302e-05, + "loss": 0.4976, + "step": 653 + }, + { + "epoch": 0.05, + "learning_rate": 1.996806324339143e-05, + "loss": 0.5387, + "step": 654 + }, + { + "epoch": 0.05, + "learning_rate": 1.996784647232673e-05, + "loss": 0.5141, + "step": 655 + }, + { + "epoch": 0.05, + "learning_rate": 1.996762896926485e-05, + "loss": 0.5372, + "step": 656 + }, + { + "epoch": 0.05, + "learning_rate": 1.9967410734221757e-05, + "loss": 0.5209, + "step": 657 + }, + { + "epoch": 0.06, + "learning_rate": 1.9967191767213475e-05, + "loss": 0.5474, + "step": 658 + }, + { + "epoch": 0.06, + "learning_rate": 1.9966972068256087e-05, + "loss": 0.5331, + "step": 659 + }, + { + "epoch": 0.06, + "learning_rate": 1.9966751637365726e-05, + "loss": 0.513, + "step": 660 + }, + { + "epoch": 0.06, + "learning_rate": 1.996653047455858e-05, + "loss": 0.5238, + "step": 661 + }, + { + "epoch": 0.06, + "learning_rate": 1.996630857985089e-05, + "loss": 0.5155, + "step": 662 + }, + { + "epoch": 0.06, + "learning_rate": 1.996608595325895e-05, + "loss": 0.5119, + "step": 663 + }, + { + "epoch": 0.06, + "learning_rate": 1.996586259479911e-05, + "loss": 0.5187, + "step": 664 + }, + { + "epoch": 0.06, + "learning_rate": 1.9965638504487773e-05, + "loss": 0.5293, + "step": 665 + }, + { + "epoch": 0.06, + "learning_rate": 1.9965413682341393e-05, + "loss": 0.5285, + "step": 666 + }, + { + "epoch": 0.06, + "learning_rate": 1.996518812837648e-05, + "loss": 0.5239, + "step": 667 + }, + { + "epoch": 0.06, + "learning_rate": 1.9964961842609602e-05, + "loss": 0.524, + "step": 668 + }, + { + "epoch": 0.06, + "learning_rate": 1.9964734825057374e-05, + "loss": 0.5324, + "step": 669 + }, + { + "epoch": 0.06, + "learning_rate": 1.9964507075736463e-05, + "loss": 0.5108, + "step": 670 + }, + { + "epoch": 0.06, + "learning_rate": 1.99642785946636e-05, + "loss": 0.5108, + "step": 671 + }, + { + "epoch": 0.06, + "learning_rate": 1.9964049381855566e-05, + "loss": 0.5037, + "step": 672 + }, + { + "epoch": 0.06, + "learning_rate": 1.9963819437329184e-05, + "loss": 0.5381, + "step": 673 + }, + { + "epoch": 0.06, + "learning_rate": 1.9963588761101347e-05, + "loss": 0.5213, + "step": 674 + }, + { + "epoch": 0.06, + "learning_rate": 1.9963357353188993e-05, + "loss": 0.5213, + "step": 675 + }, + { + "epoch": 0.06, + "learning_rate": 1.9963125213609113e-05, + "loss": 0.5493, + "step": 676 + }, + { + "epoch": 0.06, + "learning_rate": 1.996289234237876e-05, + "loss": 0.5336, + "step": 677 + }, + { + "epoch": 0.06, + "learning_rate": 1.996265873951503e-05, + "loss": 0.5166, + "step": 678 + }, + { + "epoch": 0.06, + "learning_rate": 1.996242440503508e-05, + "loss": 0.5261, + "step": 679 + }, + { + "epoch": 0.06, + "learning_rate": 1.9962189338956124e-05, + "loss": 0.516, + "step": 680 + }, + { + "epoch": 0.06, + "learning_rate": 1.9961953541295413e-05, + "loss": 0.5128, + "step": 681 + }, + { + "epoch": 0.06, + "learning_rate": 1.9961717012070273e-05, + "loss": 0.5057, + "step": 682 + }, + { + "epoch": 0.06, + "learning_rate": 1.9961479751298066e-05, + "loss": 0.514, + "step": 683 + }, + { + "epoch": 0.06, + "learning_rate": 1.996124175899622e-05, + "loss": 0.5306, + "step": 684 + }, + { + "epoch": 0.06, + "learning_rate": 1.996100303518221e-05, + "loss": 0.5231, + "step": 685 + }, + { + "epoch": 0.06, + "learning_rate": 1.9960763579873568e-05, + "loss": 0.5202, + "step": 686 + }, + { + "epoch": 0.06, + "learning_rate": 1.996052339308788e-05, + "loss": 0.5057, + "step": 687 + }, + { + "epoch": 0.06, + "learning_rate": 1.9960282474842784e-05, + "loss": 0.5059, + "step": 688 + }, + { + "epoch": 0.06, + "learning_rate": 1.9960040825155968e-05, + "loss": 0.5282, + "step": 689 + }, + { + "epoch": 0.06, + "learning_rate": 1.9959798444045184e-05, + "loss": 0.5417, + "step": 690 + }, + { + "epoch": 0.06, + "learning_rate": 1.9959555331528226e-05, + "loss": 0.5122, + "step": 691 + }, + { + "epoch": 0.06, + "learning_rate": 1.995931148762295e-05, + "loss": 0.5125, + "step": 692 + }, + { + "epoch": 0.06, + "learning_rate": 1.9959066912347262e-05, + "loss": 0.5131, + "step": 693 + }, + { + "epoch": 0.06, + "learning_rate": 1.9958821605719122e-05, + "loss": 0.5258, + "step": 694 + }, + { + "epoch": 0.06, + "learning_rate": 1.9958575567756546e-05, + "loss": 0.5234, + "step": 695 + }, + { + "epoch": 0.06, + "learning_rate": 1.9958328798477602e-05, + "loss": 0.5072, + "step": 696 + }, + { + "epoch": 0.06, + "learning_rate": 1.9958081297900413e-05, + "loss": 0.5149, + "step": 697 + }, + { + "epoch": 0.06, + "learning_rate": 1.995783306604315e-05, + "loss": 0.5273, + "step": 698 + }, + { + "epoch": 0.06, + "learning_rate": 1.995758410292404e-05, + "loss": 0.5115, + "step": 699 + }, + { + "epoch": 0.06, + "learning_rate": 1.9957334408561374e-05, + "loss": 0.5219, + "step": 700 + }, + { + "epoch": 0.06, + "learning_rate": 1.9957083982973488e-05, + "loss": 0.5097, + "step": 701 + }, + { + "epoch": 0.06, + "learning_rate": 1.9956832826178765e-05, + "loss": 0.5104, + "step": 702 + }, + { + "epoch": 0.06, + "learning_rate": 1.9956580938195654e-05, + "loss": 0.5237, + "step": 703 + }, + { + "epoch": 0.06, + "learning_rate": 1.9956328319042648e-05, + "loss": 0.519, + "step": 704 + }, + { + "epoch": 0.06, + "learning_rate": 1.9956074968738306e-05, + "loss": 0.5404, + "step": 705 + }, + { + "epoch": 0.06, + "learning_rate": 1.9955820887301227e-05, + "loss": 0.5104, + "step": 706 + }, + { + "epoch": 0.06, + "learning_rate": 1.995556607475007e-05, + "loss": 0.5055, + "step": 707 + }, + { + "epoch": 0.06, + "learning_rate": 1.9955310531103552e-05, + "loss": 0.5312, + "step": 708 + }, + { + "epoch": 0.06, + "learning_rate": 1.9955054256380436e-05, + "loss": 0.5138, + "step": 709 + }, + { + "epoch": 0.06, + "learning_rate": 1.995479725059954e-05, + "loss": 0.5236, + "step": 710 + }, + { + "epoch": 0.06, + "learning_rate": 1.9954539513779737e-05, + "loss": 0.5212, + "step": 711 + }, + { + "epoch": 0.06, + "learning_rate": 1.9954281045939958e-05, + "loss": 0.5143, + "step": 712 + }, + { + "epoch": 0.06, + "learning_rate": 1.995402184709918e-05, + "loss": 0.5225, + "step": 713 + }, + { + "epoch": 0.06, + "learning_rate": 1.9953761917276443e-05, + "loss": 0.5255, + "step": 714 + }, + { + "epoch": 0.06, + "learning_rate": 1.995350125649083e-05, + "loss": 0.5169, + "step": 715 + }, + { + "epoch": 0.06, + "learning_rate": 1.9953239864761486e-05, + "loss": 0.5122, + "step": 716 + }, + { + "epoch": 0.06, + "learning_rate": 1.9952977742107606e-05, + "loss": 0.5222, + "step": 717 + }, + { + "epoch": 0.06, + "learning_rate": 1.9952714888548432e-05, + "loss": 0.5347, + "step": 718 + }, + { + "epoch": 0.06, + "learning_rate": 1.9952451304103278e-05, + "loss": 0.5194, + "step": 719 + }, + { + "epoch": 0.06, + "learning_rate": 1.9952186988791494e-05, + "loss": 0.5115, + "step": 720 + }, + { + "epoch": 0.06, + "learning_rate": 1.9951921942632493e-05, + "loss": 0.521, + "step": 721 + }, + { + "epoch": 0.06, + "learning_rate": 1.9951656165645736e-05, + "loss": 0.5169, + "step": 722 + }, + { + "epoch": 0.06, + "learning_rate": 1.9951389657850744e-05, + "loss": 0.5083, + "step": 723 + }, + { + "epoch": 0.06, + "learning_rate": 1.9951122419267085e-05, + "loss": 0.5222, + "step": 724 + }, + { + "epoch": 0.06, + "learning_rate": 1.9950854449914384e-05, + "loss": 0.5328, + "step": 725 + }, + { + "epoch": 0.06, + "learning_rate": 1.9950585749812326e-05, + "loss": 0.502, + "step": 726 + }, + { + "epoch": 0.06, + "learning_rate": 1.9950316318980632e-05, + "loss": 0.5185, + "step": 727 + }, + { + "epoch": 0.06, + "learning_rate": 1.99500461574391e-05, + "loss": 0.528, + "step": 728 + }, + { + "epoch": 0.06, + "learning_rate": 1.994977526520756e-05, + "loss": 0.5134, + "step": 729 + }, + { + "epoch": 0.06, + "learning_rate": 1.9949503642305908e-05, + "loss": 0.5163, + "step": 730 + }, + { + "epoch": 0.06, + "learning_rate": 1.9949231288754094e-05, + "loss": 0.5277, + "step": 731 + }, + { + "epoch": 0.06, + "learning_rate": 1.9948958204572114e-05, + "loss": 0.5142, + "step": 732 + }, + { + "epoch": 0.06, + "learning_rate": 1.9948684389780026e-05, + "loss": 0.5133, + "step": 733 + }, + { + "epoch": 0.06, + "learning_rate": 1.9948409844397934e-05, + "loss": 0.5184, + "step": 734 + }, + { + "epoch": 0.06, + "learning_rate": 1.9948134568446006e-05, + "loss": 0.4933, + "step": 735 + }, + { + "epoch": 0.06, + "learning_rate": 1.994785856194445e-05, + "loss": 0.5337, + "step": 736 + }, + { + "epoch": 0.06, + "learning_rate": 1.9947581824913536e-05, + "loss": 0.5312, + "step": 737 + }, + { + "epoch": 0.06, + "learning_rate": 1.994730435737359e-05, + "loss": 0.5064, + "step": 738 + }, + { + "epoch": 0.06, + "learning_rate": 1.9947026159344985e-05, + "loss": 0.5289, + "step": 739 + }, + { + "epoch": 0.06, + "learning_rate": 1.9946747230848152e-05, + "loss": 0.5196, + "step": 740 + }, + { + "epoch": 0.06, + "learning_rate": 1.994646757190357e-05, + "loss": 0.5098, + "step": 741 + }, + { + "epoch": 0.06, + "learning_rate": 1.9946187182531785e-05, + "loss": 0.5362, + "step": 742 + }, + { + "epoch": 0.06, + "learning_rate": 1.9945906062753383e-05, + "loss": 0.5438, + "step": 743 + }, + { + "epoch": 0.06, + "learning_rate": 1.9945624212589007e-05, + "loss": 0.5376, + "step": 744 + }, + { + "epoch": 0.06, + "learning_rate": 1.9945341632059356e-05, + "loss": 0.508, + "step": 745 + }, + { + "epoch": 0.06, + "learning_rate": 1.9945058321185175e-05, + "loss": 0.5277, + "step": 746 + }, + { + "epoch": 0.06, + "learning_rate": 1.994477427998728e-05, + "loss": 0.528, + "step": 747 + }, + { + "epoch": 0.06, + "learning_rate": 1.9944489508486528e-05, + "loss": 0.515, + "step": 748 + }, + { + "epoch": 0.06, + "learning_rate": 1.9944204006703828e-05, + "loss": 0.5223, + "step": 749 + }, + { + "epoch": 0.06, + "learning_rate": 1.9943917774660145e-05, + "loss": 0.5251, + "step": 750 + }, + { + "epoch": 0.06, + "learning_rate": 1.99436308123765e-05, + "loss": 0.51, + "step": 751 + }, + { + "epoch": 0.06, + "learning_rate": 1.9943343119873966e-05, + "loss": 0.5188, + "step": 752 + }, + { + "epoch": 0.06, + "learning_rate": 1.9943054697173676e-05, + "loss": 0.5078, + "step": 753 + }, + { + "epoch": 0.06, + "learning_rate": 1.99427655442968e-05, + "loss": 0.505, + "step": 754 + }, + { + "epoch": 0.06, + "learning_rate": 1.994247566126458e-05, + "loss": 0.5079, + "step": 755 + }, + { + "epoch": 0.06, + "learning_rate": 1.99421850480983e-05, + "loss": 0.521, + "step": 756 + }, + { + "epoch": 0.06, + "learning_rate": 1.9941893704819307e-05, + "loss": 0.5151, + "step": 757 + }, + { + "epoch": 0.06, + "learning_rate": 1.9941601631448986e-05, + "loss": 0.5118, + "step": 758 + }, + { + "epoch": 0.06, + "learning_rate": 1.9941308828008794e-05, + "loss": 0.5173, + "step": 759 + }, + { + "epoch": 0.06, + "learning_rate": 1.994101529452023e-05, + "loss": 0.5219, + "step": 760 + }, + { + "epoch": 0.06, + "learning_rate": 1.9940721031004853e-05, + "loss": 0.5182, + "step": 761 + }, + { + "epoch": 0.06, + "learning_rate": 1.9940426037484268e-05, + "loss": 0.5159, + "step": 762 + }, + { + "epoch": 0.06, + "learning_rate": 1.994013031398014e-05, + "loss": 0.5232, + "step": 763 + }, + { + "epoch": 0.06, + "learning_rate": 1.9939833860514187e-05, + "loss": 0.5113, + "step": 764 + }, + { + "epoch": 0.06, + "learning_rate": 1.9939536677108176e-05, + "loss": 0.5284, + "step": 765 + }, + { + "epoch": 0.06, + "learning_rate": 1.993923876378393e-05, + "loss": 0.5181, + "step": 766 + }, + { + "epoch": 0.06, + "learning_rate": 1.993894012056334e-05, + "loss": 0.5263, + "step": 767 + }, + { + "epoch": 0.06, + "learning_rate": 1.993864074746832e-05, + "loss": 0.508, + "step": 768 + }, + { + "epoch": 0.06, + "learning_rate": 1.993834064452086e-05, + "loss": 0.5173, + "step": 769 + }, + { + "epoch": 0.06, + "learning_rate": 1.9938039811743e-05, + "loss": 0.5273, + "step": 770 + }, + { + "epoch": 0.06, + "learning_rate": 1.9937738249156836e-05, + "loss": 0.5169, + "step": 771 + }, + { + "epoch": 0.06, + "learning_rate": 1.9937435956784506e-05, + "loss": 0.5033, + "step": 772 + }, + { + "epoch": 0.06, + "learning_rate": 1.9937132934648213e-05, + "loss": 0.4927, + "step": 773 + }, + { + "epoch": 0.06, + "learning_rate": 1.993682918277021e-05, + "loss": 0.5177, + "step": 774 + }, + { + "epoch": 0.06, + "learning_rate": 1.99365247011728e-05, + "loss": 0.51, + "step": 775 + }, + { + "epoch": 0.06, + "learning_rate": 1.9936219489878343e-05, + "loss": 0.5046, + "step": 776 + }, + { + "epoch": 0.07, + "learning_rate": 1.9935913548909258e-05, + "loss": 0.5577, + "step": 777 + }, + { + "epoch": 0.07, + "learning_rate": 1.9935606878288008e-05, + "loss": 0.5247, + "step": 778 + }, + { + "epoch": 0.07, + "learning_rate": 1.9935299478037114e-05, + "loss": 0.5033, + "step": 779 + }, + { + "epoch": 0.07, + "learning_rate": 1.993499134817915e-05, + "loss": 0.5286, + "step": 780 + }, + { + "epoch": 0.07, + "learning_rate": 1.9934682488736745e-05, + "loss": 0.5342, + "step": 781 + }, + { + "epoch": 0.07, + "learning_rate": 1.993437289973258e-05, + "loss": 0.5145, + "step": 782 + }, + { + "epoch": 0.07, + "learning_rate": 1.993406258118939e-05, + "loss": 0.5139, + "step": 783 + }, + { + "epoch": 0.07, + "learning_rate": 1.993375153312996e-05, + "loss": 0.5159, + "step": 784 + }, + { + "epoch": 0.07, + "learning_rate": 1.9933439755577134e-05, + "loss": 0.506, + "step": 785 + }, + { + "epoch": 0.07, + "learning_rate": 1.9933127248553813e-05, + "loss": 0.5219, + "step": 786 + }, + { + "epoch": 0.07, + "learning_rate": 1.993281401208294e-05, + "loss": 0.5383, + "step": 787 + }, + { + "epoch": 0.07, + "learning_rate": 1.993250004618752e-05, + "loss": 0.5096, + "step": 788 + }, + { + "epoch": 0.07, + "learning_rate": 1.9932185350890606e-05, + "loss": 0.5199, + "step": 789 + }, + { + "epoch": 0.07, + "learning_rate": 1.9931869926215315e-05, + "loss": 0.5117, + "step": 790 + }, + { + "epoch": 0.07, + "learning_rate": 1.9931553772184805e-05, + "loss": 0.5312, + "step": 791 + }, + { + "epoch": 0.07, + "learning_rate": 1.9931236888822295e-05, + "loss": 0.5135, + "step": 792 + }, + { + "epoch": 0.07, + "learning_rate": 1.993091927615105e-05, + "loss": 0.5282, + "step": 793 + }, + { + "epoch": 0.07, + "learning_rate": 1.9930600934194405e-05, + "loss": 0.5438, + "step": 794 + }, + { + "epoch": 0.07, + "learning_rate": 1.993028186297573e-05, + "loss": 0.5087, + "step": 795 + }, + { + "epoch": 0.07, + "learning_rate": 1.9929962062518458e-05, + "loss": 0.5244, + "step": 796 + }, + { + "epoch": 0.07, + "learning_rate": 1.9929641532846074e-05, + "loss": 0.5054, + "step": 797 + }, + { + "epoch": 0.07, + "learning_rate": 1.992932027398212e-05, + "loss": 0.5353, + "step": 798 + }, + { + "epoch": 0.07, + "learning_rate": 1.992899828595018e-05, + "loss": 0.5065, + "step": 799 + }, + { + "epoch": 0.07, + "learning_rate": 1.9928675568773906e-05, + "loss": 0.5293, + "step": 800 + }, + { + "epoch": 0.07, + "learning_rate": 1.992835212247699e-05, + "loss": 0.5097, + "step": 801 + }, + { + "epoch": 0.07, + "learning_rate": 1.9928027947083195e-05, + "loss": 0.5242, + "step": 802 + }, + { + "epoch": 0.07, + "learning_rate": 1.992770304261632e-05, + "loss": 0.5199, + "step": 803 + }, + { + "epoch": 0.07, + "learning_rate": 1.9927377409100222e-05, + "loss": 0.5333, + "step": 804 + }, + { + "epoch": 0.07, + "learning_rate": 1.992705104655882e-05, + "loss": 0.5338, + "step": 805 + }, + { + "epoch": 0.07, + "learning_rate": 1.992672395501608e-05, + "loss": 0.5206, + "step": 806 + }, + { + "epoch": 0.07, + "learning_rate": 1.992639613449602e-05, + "loss": 0.5262, + "step": 807 + }, + { + "epoch": 0.07, + "learning_rate": 1.9926067585022718e-05, + "loss": 0.5317, + "step": 808 + }, + { + "epoch": 0.07, + "learning_rate": 1.9925738306620294e-05, + "loss": 0.5414, + "step": 809 + }, + { + "epoch": 0.07, + "learning_rate": 1.9925408299312935e-05, + "loss": 0.5112, + "step": 810 + }, + { + "epoch": 0.07, + "learning_rate": 1.992507756312487e-05, + "loss": 0.5168, + "step": 811 + }, + { + "epoch": 0.07, + "learning_rate": 1.99247460980804e-05, + "loss": 0.5242, + "step": 812 + }, + { + "epoch": 0.07, + "learning_rate": 1.9924413904203847e-05, + "loss": 0.51, + "step": 813 + }, + { + "epoch": 0.07, + "learning_rate": 1.992408098151962e-05, + "loss": 0.5168, + "step": 814 + }, + { + "epoch": 0.07, + "learning_rate": 1.992374733005216e-05, + "loss": 0.5223, + "step": 815 + }, + { + "epoch": 0.07, + "learning_rate": 1.9923412949825975e-05, + "loss": 0.5066, + "step": 816 + }, + { + "epoch": 0.07, + "learning_rate": 1.9923077840865615e-05, + "loss": 0.5063, + "step": 817 + }, + { + "epoch": 0.07, + "learning_rate": 1.9922742003195696e-05, + "loss": 0.5171, + "step": 818 + }, + { + "epoch": 0.07, + "learning_rate": 1.9922405436840872e-05, + "loss": 0.5278, + "step": 819 + }, + { + "epoch": 0.07, + "learning_rate": 1.9922068141825864e-05, + "loss": 0.5183, + "step": 820 + }, + { + "epoch": 0.07, + "learning_rate": 1.9921730118175443e-05, + "loss": 0.5055, + "step": 821 + }, + { + "epoch": 0.07, + "learning_rate": 1.9921391365914426e-05, + "loss": 0.5416, + "step": 822 + }, + { + "epoch": 0.07, + "learning_rate": 1.9921051885067695e-05, + "loss": 0.5098, + "step": 823 + }, + { + "epoch": 0.07, + "learning_rate": 1.9920711675660178e-05, + "loss": 0.543, + "step": 824 + }, + { + "epoch": 0.07, + "learning_rate": 1.992037073771686e-05, + "loss": 0.5269, + "step": 825 + }, + { + "epoch": 0.07, + "learning_rate": 1.9920029071262778e-05, + "loss": 0.4967, + "step": 826 + }, + { + "epoch": 0.07, + "learning_rate": 1.9919686676323015e-05, + "loss": 0.5036, + "step": 827 + }, + { + "epoch": 0.07, + "learning_rate": 1.9919343552922727e-05, + "loss": 0.518, + "step": 828 + }, + { + "epoch": 0.07, + "learning_rate": 1.9918999701087104e-05, + "loss": 0.5273, + "step": 829 + }, + { + "epoch": 0.07, + "learning_rate": 1.9918655120841403e-05, + "loss": 0.5271, + "step": 830 + }, + { + "epoch": 0.07, + "learning_rate": 1.991830981221092e-05, + "loss": 0.5263, + "step": 831 + }, + { + "epoch": 0.07, + "learning_rate": 1.991796377522102e-05, + "loss": 0.5187, + "step": 832 + }, + { + "epoch": 0.07, + "learning_rate": 1.9917617009897113e-05, + "loss": 0.5042, + "step": 833 + }, + { + "epoch": 0.07, + "learning_rate": 1.9917269516264662e-05, + "loss": 0.5248, + "step": 834 + }, + { + "epoch": 0.07, + "learning_rate": 1.9916921294349187e-05, + "loss": 0.4992, + "step": 835 + }, + { + "epoch": 0.07, + "learning_rate": 1.9916572344176258e-05, + "loss": 0.5347, + "step": 836 + }, + { + "epoch": 0.07, + "learning_rate": 1.9916222665771506e-05, + "loss": 0.5343, + "step": 837 + }, + { + "epoch": 0.07, + "learning_rate": 1.9915872259160603e-05, + "loss": 0.511, + "step": 838 + }, + { + "epoch": 0.07, + "learning_rate": 1.991552112436929e-05, + "loss": 0.5374, + "step": 839 + }, + { + "epoch": 0.07, + "learning_rate": 1.991516926142334e-05, + "loss": 0.5074, + "step": 840 + }, + { + "epoch": 0.07, + "learning_rate": 1.99148166703486e-05, + "loss": 0.5287, + "step": 841 + }, + { + "epoch": 0.07, + "learning_rate": 1.991446335117097e-05, + "loss": 0.5089, + "step": 842 + }, + { + "epoch": 0.07, + "learning_rate": 1.991410930391638e-05, + "loss": 0.5148, + "step": 843 + }, + { + "epoch": 0.07, + "learning_rate": 1.9913754528610846e-05, + "loss": 0.5282, + "step": 844 + }, + { + "epoch": 0.07, + "learning_rate": 1.991339902528041e-05, + "loss": 0.5093, + "step": 845 + }, + { + "epoch": 0.07, + "learning_rate": 1.9913042793951184e-05, + "loss": 0.5292, + "step": 846 + }, + { + "epoch": 0.07, + "learning_rate": 1.9912685834649324e-05, + "loss": 0.5164, + "step": 847 + }, + { + "epoch": 0.07, + "learning_rate": 1.991232814740105e-05, + "loss": 0.5011, + "step": 848 + }, + { + "epoch": 0.07, + "learning_rate": 1.991196973223262e-05, + "loss": 0.5238, + "step": 849 + }, + { + "epoch": 0.07, + "learning_rate": 1.9911610589170363e-05, + "loss": 0.5173, + "step": 850 + }, + { + "epoch": 0.07, + "learning_rate": 1.9911250718240653e-05, + "loss": 0.5082, + "step": 851 + }, + { + "epoch": 0.07, + "learning_rate": 1.991089011946991e-05, + "loss": 0.5063, + "step": 852 + }, + { + "epoch": 0.07, + "learning_rate": 1.991052879288462e-05, + "loss": 0.5203, + "step": 853 + }, + { + "epoch": 0.07, + "learning_rate": 1.9910166738511315e-05, + "loss": 0.5008, + "step": 854 + }, + { + "epoch": 0.07, + "learning_rate": 1.9909803956376588e-05, + "loss": 0.5135, + "step": 855 + }, + { + "epoch": 0.07, + "learning_rate": 1.9909440446507074e-05, + "loss": 0.5087, + "step": 856 + }, + { + "epoch": 0.07, + "learning_rate": 1.990907620892947e-05, + "loss": 0.5175, + "step": 857 + }, + { + "epoch": 0.07, + "learning_rate": 1.9908711243670526e-05, + "loss": 0.5173, + "step": 858 + }, + { + "epoch": 0.07, + "learning_rate": 1.990834555075704e-05, + "loss": 0.5081, + "step": 859 + }, + { + "epoch": 0.07, + "learning_rate": 1.9907979130215868e-05, + "loss": 0.517, + "step": 860 + }, + { + "epoch": 0.07, + "learning_rate": 1.990761198207392e-05, + "loss": 0.5276, + "step": 861 + }, + { + "epoch": 0.07, + "learning_rate": 1.9907244106358158e-05, + "loss": 0.5121, + "step": 862 + }, + { + "epoch": 0.07, + "learning_rate": 1.9906875503095594e-05, + "loss": 0.5236, + "step": 863 + }, + { + "epoch": 0.07, + "learning_rate": 1.99065061723133e-05, + "loss": 0.524, + "step": 864 + }, + { + "epoch": 0.07, + "learning_rate": 1.9906136114038398e-05, + "loss": 0.5112, + "step": 865 + }, + { + "epoch": 0.07, + "learning_rate": 1.990576532829806e-05, + "loss": 0.5318, + "step": 866 + }, + { + "epoch": 0.07, + "learning_rate": 1.990539381511952e-05, + "loss": 0.5188, + "step": 867 + }, + { + "epoch": 0.07, + "learning_rate": 1.9905021574530055e-05, + "loss": 0.5064, + "step": 868 + }, + { + "epoch": 0.07, + "learning_rate": 1.9904648606557007e-05, + "loss": 0.528, + "step": 869 + }, + { + "epoch": 0.07, + "learning_rate": 1.9904274911227762e-05, + "loss": 0.5179, + "step": 870 + }, + { + "epoch": 0.07, + "learning_rate": 1.990390048856976e-05, + "loss": 0.5177, + "step": 871 + }, + { + "epoch": 0.07, + "learning_rate": 1.99035253386105e-05, + "loss": 0.516, + "step": 872 + }, + { + "epoch": 0.07, + "learning_rate": 1.9903149461377532e-05, + "loss": 0.525, + "step": 873 + }, + { + "epoch": 0.07, + "learning_rate": 1.9902772856898457e-05, + "loss": 0.5407, + "step": 874 + }, + { + "epoch": 0.07, + "learning_rate": 1.9902395525200933e-05, + "loss": 0.5232, + "step": 875 + }, + { + "epoch": 0.07, + "learning_rate": 1.9902017466312668e-05, + "loss": 0.5302, + "step": 876 + }, + { + "epoch": 0.07, + "learning_rate": 1.9901638680261426e-05, + "loss": 0.5218, + "step": 877 + }, + { + "epoch": 0.07, + "learning_rate": 1.9901259167075023e-05, + "loss": 0.5213, + "step": 878 + }, + { + "epoch": 0.07, + "learning_rate": 1.9900878926781327e-05, + "loss": 0.5346, + "step": 879 + }, + { + "epoch": 0.07, + "learning_rate": 1.990049795940827e-05, + "loss": 0.5155, + "step": 880 + }, + { + "epoch": 0.07, + "learning_rate": 1.9900116264983815e-05, + "loss": 0.523, + "step": 881 + }, + { + "epoch": 0.07, + "learning_rate": 1.9899733843536e-05, + "loss": 0.5037, + "step": 882 + }, + { + "epoch": 0.07, + "learning_rate": 1.9899350695092914e-05, + "loss": 0.516, + "step": 883 + }, + { + "epoch": 0.07, + "learning_rate": 1.989896681968268e-05, + "loss": 0.5274, + "step": 884 + }, + { + "epoch": 0.07, + "learning_rate": 1.98985822173335e-05, + "loss": 0.5063, + "step": 885 + }, + { + "epoch": 0.07, + "learning_rate": 1.9898196888073612e-05, + "loss": 0.507, + "step": 886 + }, + { + "epoch": 0.07, + "learning_rate": 1.9897810831931314e-05, + "loss": 0.5332, + "step": 887 + }, + { + "epoch": 0.07, + "learning_rate": 1.989742404893496e-05, + "loss": 0.5391, + "step": 888 + }, + { + "epoch": 0.07, + "learning_rate": 1.9897036539112945e-05, + "loss": 0.5041, + "step": 889 + }, + { + "epoch": 0.07, + "learning_rate": 1.9896648302493734e-05, + "loss": 0.5138, + "step": 890 + }, + { + "epoch": 0.07, + "learning_rate": 1.9896259339105835e-05, + "loss": 0.5398, + "step": 891 + }, + { + "epoch": 0.07, + "learning_rate": 1.9895869648977812e-05, + "loss": 0.516, + "step": 892 + }, + { + "epoch": 0.07, + "learning_rate": 1.9895479232138282e-05, + "loss": 0.5177, + "step": 893 + }, + { + "epoch": 0.07, + "learning_rate": 1.9895088088615915e-05, + "loss": 0.4917, + "step": 894 + }, + { + "epoch": 0.07, + "learning_rate": 1.9894696218439436e-05, + "loss": 0.526, + "step": 895 + }, + { + "epoch": 0.07, + "learning_rate": 1.989430362163762e-05, + "loss": 0.5205, + "step": 896 + }, + { + "epoch": 0.08, + "learning_rate": 1.98939102982393e-05, + "loss": 0.5188, + "step": 897 + }, + { + "epoch": 0.08, + "learning_rate": 1.9893516248273362e-05, + "loss": 0.5392, + "step": 898 + }, + { + "epoch": 0.08, + "learning_rate": 1.989312147176874e-05, + "loss": 0.5131, + "step": 899 + }, + { + "epoch": 0.08, + "learning_rate": 1.9892725968754426e-05, + "loss": 0.5156, + "step": 900 + }, + { + "epoch": 0.08, + "learning_rate": 1.9892329739259462e-05, + "loss": 0.4967, + "step": 901 + }, + { + "epoch": 0.08, + "learning_rate": 1.9891932783312948e-05, + "loss": 0.5241, + "step": 902 + }, + { + "epoch": 0.08, + "learning_rate": 1.9891535100944033e-05, + "loss": 0.5174, + "step": 903 + }, + { + "epoch": 0.08, + "learning_rate": 1.9891136692181926e-05, + "loss": 0.5355, + "step": 904 + }, + { + "epoch": 0.08, + "learning_rate": 1.989073755705588e-05, + "loss": 0.5073, + "step": 905 + }, + { + "epoch": 0.08, + "learning_rate": 1.9890337695595202e-05, + "loss": 0.518, + "step": 906 + }, + { + "epoch": 0.08, + "learning_rate": 1.988993710782926e-05, + "loss": 0.5088, + "step": 907 + }, + { + "epoch": 0.08, + "learning_rate": 1.988953579378748e-05, + "loss": 0.5005, + "step": 908 + }, + { + "epoch": 0.08, + "learning_rate": 1.988913375349932e-05, + "loss": 0.5177, + "step": 909 + }, + { + "epoch": 0.08, + "learning_rate": 1.988873098699431e-05, + "loss": 0.5096, + "step": 910 + }, + { + "epoch": 0.08, + "learning_rate": 1.9888327494302025e-05, + "loss": 0.5153, + "step": 911 + }, + { + "epoch": 0.08, + "learning_rate": 1.98879232754521e-05, + "loss": 0.5335, + "step": 912 + }, + { + "epoch": 0.08, + "learning_rate": 1.9887518330474216e-05, + "loss": 0.5308, + "step": 913 + }, + { + "epoch": 0.08, + "learning_rate": 1.9887112659398108e-05, + "loss": 0.5303, + "step": 914 + }, + { + "epoch": 0.08, + "learning_rate": 1.9886706262253574e-05, + "loss": 0.5258, + "step": 915 + }, + { + "epoch": 0.08, + "learning_rate": 1.988629913907045e-05, + "loss": 0.5278, + "step": 916 + }, + { + "epoch": 0.08, + "learning_rate": 1.988589128987864e-05, + "loss": 0.5097, + "step": 917 + }, + { + "epoch": 0.08, + "learning_rate": 1.9885482714708093e-05, + "loss": 0.5024, + "step": 918 + }, + { + "epoch": 0.08, + "learning_rate": 1.988507341358881e-05, + "loss": 0.5346, + "step": 919 + }, + { + "epoch": 0.08, + "learning_rate": 1.9884663386550853e-05, + "loss": 0.5104, + "step": 920 + }, + { + "epoch": 0.08, + "learning_rate": 1.988425263362433e-05, + "loss": 0.5202, + "step": 921 + }, + { + "epoch": 0.08, + "learning_rate": 1.98838411548394e-05, + "loss": 0.5188, + "step": 922 + }, + { + "epoch": 0.08, + "learning_rate": 1.9883428950226294e-05, + "loss": 0.5121, + "step": 923 + }, + { + "epoch": 0.08, + "learning_rate": 1.9883016019815268e-05, + "loss": 0.5089, + "step": 924 + }, + { + "epoch": 0.08, + "learning_rate": 1.9882602363636656e-05, + "loss": 0.5172, + "step": 925 + }, + { + "epoch": 0.08, + "learning_rate": 1.9882187981720827e-05, + "loss": 0.52, + "step": 926 + }, + { + "epoch": 0.08, + "learning_rate": 1.9881772874098218e-05, + "loss": 0.5118, + "step": 927 + }, + { + "epoch": 0.08, + "learning_rate": 1.9881357040799312e-05, + "loss": 0.531, + "step": 928 + }, + { + "epoch": 0.08, + "learning_rate": 1.9880940481854646e-05, + "loss": 0.5273, + "step": 929 + }, + { + "epoch": 0.08, + "learning_rate": 1.9880523197294804e-05, + "loss": 0.5082, + "step": 930 + }, + { + "epoch": 0.08, + "learning_rate": 1.9880105187150435e-05, + "loss": 0.5142, + "step": 931 + }, + { + "epoch": 0.08, + "learning_rate": 1.987968645145224e-05, + "loss": 0.5217, + "step": 932 + }, + { + "epoch": 0.08, + "learning_rate": 1.987926699023096e-05, + "loss": 0.504, + "step": 933 + }, + { + "epoch": 0.08, + "learning_rate": 1.9878846803517408e-05, + "loss": 0.5272, + "step": 934 + }, + { + "epoch": 0.08, + "learning_rate": 1.987842589134243e-05, + "loss": 0.5336, + "step": 935 + }, + { + "epoch": 0.08, + "learning_rate": 1.9878004253736945e-05, + "loss": 0.5198, + "step": 936 + }, + { + "epoch": 0.08, + "learning_rate": 1.9877581890731915e-05, + "loss": 0.5233, + "step": 937 + }, + { + "epoch": 0.08, + "learning_rate": 1.987715880235835e-05, + "loss": 0.5315, + "step": 938 + }, + { + "epoch": 0.08, + "learning_rate": 1.9876734988647334e-05, + "loss": 0.5072, + "step": 939 + }, + { + "epoch": 0.08, + "learning_rate": 1.9876310449629973e-05, + "loss": 0.5278, + "step": 940 + }, + { + "epoch": 0.08, + "learning_rate": 1.9875885185337453e-05, + "loss": 0.5219, + "step": 941 + }, + { + "epoch": 0.08, + "learning_rate": 1.9875459195801e-05, + "loss": 0.5161, + "step": 942 + }, + { + "epoch": 0.08, + "learning_rate": 1.98750324810519e-05, + "loss": 0.5227, + "step": 943 + }, + { + "epoch": 0.08, + "learning_rate": 1.987460504112149e-05, + "loss": 0.5114, + "step": 944 + }, + { + "epoch": 0.08, + "learning_rate": 1.9874176876041157e-05, + "loss": 0.5262, + "step": 945 + }, + { + "epoch": 0.08, + "learning_rate": 1.9873747985842343e-05, + "loss": 0.508, + "step": 946 + }, + { + "epoch": 0.08, + "learning_rate": 1.9873318370556546e-05, + "loss": 0.5422, + "step": 947 + }, + { + "epoch": 0.08, + "learning_rate": 1.9872888030215313e-05, + "loss": 0.5087, + "step": 948 + }, + { + "epoch": 0.08, + "learning_rate": 1.9872456964850246e-05, + "loss": 0.5138, + "step": 949 + }, + { + "epoch": 0.08, + "learning_rate": 1.9872025174493003e-05, + "loss": 0.5138, + "step": 950 + }, + { + "epoch": 0.08, + "learning_rate": 1.9871592659175296e-05, + "loss": 0.5301, + "step": 951 + }, + { + "epoch": 0.08, + "learning_rate": 1.987115941892888e-05, + "loss": 0.4924, + "step": 952 + }, + { + "epoch": 0.08, + "learning_rate": 1.987072545378557e-05, + "loss": 0.5321, + "step": 953 + }, + { + "epoch": 0.08, + "learning_rate": 1.9870290763777243e-05, + "loss": 0.5333, + "step": 954 + }, + { + "epoch": 0.08, + "learning_rate": 1.9869855348935817e-05, + "loss": 0.5032, + "step": 955 + }, + { + "epoch": 0.08, + "learning_rate": 1.986941920929326e-05, + "loss": 0.5294, + "step": 956 + }, + { + "epoch": 0.08, + "learning_rate": 1.986898234488161e-05, + "loss": 0.5085, + "step": 957 + }, + { + "epoch": 0.08, + "learning_rate": 1.9868544755732948e-05, + "loss": 0.4924, + "step": 958 + }, + { + "epoch": 0.08, + "learning_rate": 1.9868106441879403e-05, + "loss": 0.496, + "step": 959 + }, + { + "epoch": 0.08, + "learning_rate": 1.9867667403353162e-05, + "loss": 0.5076, + "step": 960 + }, + { + "epoch": 0.08, + "learning_rate": 1.9867227640186474e-05, + "loss": 0.5201, + "step": 961 + }, + { + "epoch": 0.08, + "learning_rate": 1.9866787152411624e-05, + "loss": 0.5204, + "step": 962 + }, + { + "epoch": 0.08, + "learning_rate": 1.986634594006097e-05, + "loss": 0.5269, + "step": 963 + }, + { + "epoch": 0.08, + "learning_rate": 1.9865904003166904e-05, + "loss": 0.5226, + "step": 964 + }, + { + "epoch": 0.08, + "learning_rate": 1.9865461341761885e-05, + "loss": 0.5212, + "step": 965 + }, + { + "epoch": 0.08, + "learning_rate": 1.986501795587842e-05, + "loss": 0.5216, + "step": 966 + }, + { + "epoch": 0.08, + "learning_rate": 1.9864573845549063e-05, + "loss": 0.5174, + "step": 967 + }, + { + "epoch": 0.08, + "learning_rate": 1.9864129010806437e-05, + "loss": 0.5356, + "step": 968 + }, + { + "epoch": 0.08, + "learning_rate": 1.9863683451683204e-05, + "loss": 0.4997, + "step": 969 + }, + { + "epoch": 0.08, + "learning_rate": 1.9863237168212084e-05, + "loss": 0.5137, + "step": 970 + }, + { + "epoch": 0.08, + "learning_rate": 1.986279016042585e-05, + "loss": 0.5368, + "step": 971 + }, + { + "epoch": 0.08, + "learning_rate": 1.9862342428357327e-05, + "loss": 0.5209, + "step": 972 + }, + { + "epoch": 0.08, + "learning_rate": 1.9861893972039402e-05, + "loss": 0.5135, + "step": 973 + }, + { + "epoch": 0.08, + "learning_rate": 1.9861444791504997e-05, + "loss": 0.517, + "step": 974 + }, + { + "epoch": 0.08, + "learning_rate": 1.9860994886787106e-05, + "loss": 0.5308, + "step": 975 + }, + { + "epoch": 0.08, + "learning_rate": 1.9860544257918765e-05, + "loss": 0.5223, + "step": 976 + }, + { + "epoch": 0.08, + "learning_rate": 1.9860092904933065e-05, + "loss": 0.5231, + "step": 977 + }, + { + "epoch": 0.08, + "learning_rate": 1.9859640827863157e-05, + "loss": 0.5187, + "step": 978 + }, + { + "epoch": 0.08, + "learning_rate": 1.9859188026742235e-05, + "loss": 0.524, + "step": 979 + }, + { + "epoch": 0.08, + "learning_rate": 1.9858734501603553e-05, + "loss": 0.5258, + "step": 980 + }, + { + "epoch": 0.08, + "learning_rate": 1.985828025248041e-05, + "loss": 0.5138, + "step": 981 + }, + { + "epoch": 0.08, + "learning_rate": 1.985782527940617e-05, + "loss": 0.5222, + "step": 982 + }, + { + "epoch": 0.08, + "learning_rate": 1.9857369582414246e-05, + "loss": 0.5048, + "step": 983 + }, + { + "epoch": 0.08, + "learning_rate": 1.98569131615381e-05, + "loss": 0.498, + "step": 984 + }, + { + "epoch": 0.08, + "learning_rate": 1.985645601681125e-05, + "loss": 0.5268, + "step": 985 + }, + { + "epoch": 0.08, + "learning_rate": 1.9855998148267265e-05, + "loss": 0.5111, + "step": 986 + }, + { + "epoch": 0.08, + "learning_rate": 1.9855539555939768e-05, + "loss": 0.5131, + "step": 987 + }, + { + "epoch": 0.08, + "learning_rate": 1.985508023986244e-05, + "loss": 0.5085, + "step": 988 + }, + { + "epoch": 0.08, + "learning_rate": 1.985462020006901e-05, + "loss": 0.4973, + "step": 989 + }, + { + "epoch": 0.08, + "learning_rate": 1.9854159436593258e-05, + "loss": 0.5084, + "step": 990 + }, + { + "epoch": 0.08, + "learning_rate": 1.9853697949469027e-05, + "loss": 0.499, + "step": 991 + }, + { + "epoch": 0.08, + "learning_rate": 1.98532357387302e-05, + "loss": 0.5203, + "step": 992 + }, + { + "epoch": 0.08, + "learning_rate": 1.9852772804410728e-05, + "loss": 0.4915, + "step": 993 + }, + { + "epoch": 0.08, + "learning_rate": 1.98523091465446e-05, + "loss": 0.5183, + "step": 994 + }, + { + "epoch": 0.08, + "learning_rate": 1.9851844765165863e-05, + "loss": 0.505, + "step": 995 + }, + { + "epoch": 0.08, + "learning_rate": 1.9851379660308624e-05, + "loss": 0.5046, + "step": 996 + }, + { + "epoch": 0.08, + "learning_rate": 1.9850913832007042e-05, + "loss": 0.515, + "step": 997 + }, + { + "epoch": 0.08, + "learning_rate": 1.985044728029532e-05, + "loss": 0.503, + "step": 998 + }, + { + "epoch": 0.08, + "learning_rate": 1.984998000520772e-05, + "loss": 0.5179, + "step": 999 + }, + { + "epoch": 0.08, + "learning_rate": 1.9849512006778557e-05, + "loss": 0.5145, + "step": 1000 + }, + { + "epoch": 0.08, + "learning_rate": 1.9849043285042203e-05, + "loss": 0.5222, + "step": 1001 + }, + { + "epoch": 0.08, + "learning_rate": 1.9848573840033068e-05, + "loss": 0.4923, + "step": 1002 + }, + { + "epoch": 0.08, + "learning_rate": 1.984810367178564e-05, + "loss": 0.5156, + "step": 1003 + }, + { + "epoch": 0.08, + "learning_rate": 1.984763278033444e-05, + "loss": 0.5181, + "step": 1004 + }, + { + "epoch": 0.08, + "learning_rate": 1.9847161165714043e-05, + "loss": 0.5291, + "step": 1005 + }, + { + "epoch": 0.08, + "learning_rate": 1.984668882795909e-05, + "loss": 0.5196, + "step": 1006 + }, + { + "epoch": 0.08, + "learning_rate": 1.9846215767104266e-05, + "loss": 0.5165, + "step": 1007 + }, + { + "epoch": 0.08, + "learning_rate": 1.984574198318431e-05, + "loss": 0.5066, + "step": 1008 + }, + { + "epoch": 0.08, + "learning_rate": 1.9845267476234013e-05, + "loss": 0.5345, + "step": 1009 + }, + { + "epoch": 0.08, + "learning_rate": 1.984479224628822e-05, + "loss": 0.5275, + "step": 1010 + }, + { + "epoch": 0.08, + "learning_rate": 1.9844316293381834e-05, + "loss": 0.5111, + "step": 1011 + }, + { + "epoch": 0.08, + "learning_rate": 1.9843839617549805e-05, + "loss": 0.4976, + "step": 1012 + }, + { + "epoch": 0.08, + "learning_rate": 1.984336221882714e-05, + "loss": 0.5251, + "step": 1013 + }, + { + "epoch": 0.08, + "learning_rate": 1.9842884097248892e-05, + "loss": 0.5083, + "step": 1014 + }, + { + "epoch": 0.08, + "learning_rate": 1.9842405252850175e-05, + "loss": 0.5086, + "step": 1015 + }, + { + "epoch": 0.09, + "learning_rate": 1.984192568566616e-05, + "loss": 0.535, + "step": 1016 + }, + { + "epoch": 0.09, + "learning_rate": 1.9841445395732054e-05, + "loss": 0.5005, + "step": 1017 + }, + { + "epoch": 0.09, + "learning_rate": 1.984096438308313e-05, + "loss": 0.5042, + "step": 1018 + }, + { + "epoch": 0.09, + "learning_rate": 1.9840482647754716e-05, + "loss": 0.5152, + "step": 1019 + }, + { + "epoch": 0.09, + "learning_rate": 1.9840000189782184e-05, + "loss": 0.5217, + "step": 1020 + }, + { + "epoch": 0.09, + "learning_rate": 1.983951700920097e-05, + "loss": 0.5063, + "step": 1021 + }, + { + "epoch": 0.09, + "learning_rate": 1.9839033106046548e-05, + "loss": 0.5153, + "step": 1022 + }, + { + "epoch": 0.09, + "learning_rate": 1.983854848035446e-05, + "loss": 0.5272, + "step": 1023 + }, + { + "epoch": 0.09, + "learning_rate": 1.9838063132160292e-05, + "loss": 0.5123, + "step": 1024 + }, + { + "epoch": 0.09, + "learning_rate": 1.983757706149969e-05, + "loss": 0.5136, + "step": 1025 + }, + { + "epoch": 0.09, + "learning_rate": 1.9837090268408342e-05, + "loss": 0.5199, + "step": 1026 + }, + { + "epoch": 0.09, + "learning_rate": 1.9836602752922004e-05, + "loss": 0.5092, + "step": 1027 + }, + { + "epoch": 0.09, + "learning_rate": 1.9836114515076473e-05, + "loss": 0.5272, + "step": 1028 + }, + { + "epoch": 0.09, + "learning_rate": 1.98356255549076e-05, + "loss": 0.5041, + "step": 1029 + }, + { + "epoch": 0.09, + "learning_rate": 1.98351358724513e-05, + "loss": 0.529, + "step": 1030 + }, + { + "epoch": 0.09, + "learning_rate": 1.9834645467743524e-05, + "loss": 0.5032, + "step": 1031 + }, + { + "epoch": 0.09, + "learning_rate": 1.9834154340820296e-05, + "loss": 0.5256, + "step": 1032 + }, + { + "epoch": 0.09, + "learning_rate": 1.983366249171767e-05, + "loss": 0.5248, + "step": 1033 + }, + { + "epoch": 0.09, + "learning_rate": 1.9833169920471778e-05, + "loss": 0.5205, + "step": 1034 + }, + { + "epoch": 0.09, + "learning_rate": 1.9832676627118784e-05, + "loss": 0.5149, + "step": 1035 + }, + { + "epoch": 0.09, + "learning_rate": 1.9832182611694916e-05, + "loss": 0.5022, + "step": 1036 + }, + { + "epoch": 0.09, + "learning_rate": 1.983168787423645e-05, + "loss": 0.5143, + "step": 1037 + }, + { + "epoch": 0.09, + "learning_rate": 1.9831192414779724e-05, + "loss": 0.5363, + "step": 1038 + }, + { + "epoch": 0.09, + "learning_rate": 1.9830696233361113e-05, + "loss": 0.4941, + "step": 1039 + }, + { + "epoch": 0.09, + "learning_rate": 1.9830199330017063e-05, + "loss": 0.5166, + "step": 1040 + }, + { + "epoch": 0.09, + "learning_rate": 1.982970170478406e-05, + "loss": 0.5323, + "step": 1041 + }, + { + "epoch": 0.09, + "learning_rate": 1.9829203357698647e-05, + "loss": 0.5265, + "step": 1042 + }, + { + "epoch": 0.09, + "learning_rate": 1.9828704288797425e-05, + "loss": 0.5111, + "step": 1043 + }, + { + "epoch": 0.09, + "learning_rate": 1.982820449811704e-05, + "loss": 0.5161, + "step": 1044 + }, + { + "epoch": 0.09, + "learning_rate": 1.9827703985694194e-05, + "loss": 0.5233, + "step": 1045 + }, + { + "epoch": 0.09, + "learning_rate": 1.9827202751565644e-05, + "loss": 0.5273, + "step": 1046 + }, + { + "epoch": 0.09, + "learning_rate": 1.9826700795768197e-05, + "loss": 0.5168, + "step": 1047 + }, + { + "epoch": 0.09, + "learning_rate": 1.982619811833872e-05, + "loss": 0.504, + "step": 1048 + }, + { + "epoch": 0.09, + "learning_rate": 1.982569471931412e-05, + "loss": 0.5216, + "step": 1049 + }, + { + "epoch": 0.09, + "learning_rate": 1.982519059873137e-05, + "loss": 0.5331, + "step": 1050 + }, + { + "epoch": 0.09, + "learning_rate": 1.9824685756627487e-05, + "loss": 0.5473, + "step": 1051 + }, + { + "epoch": 0.09, + "learning_rate": 1.9824180193039545e-05, + "loss": 0.5213, + "step": 1052 + }, + { + "epoch": 0.09, + "learning_rate": 1.9823673908004673e-05, + "loss": 0.5104, + "step": 1053 + }, + { + "epoch": 0.09, + "learning_rate": 1.982316690156005e-05, + "loss": 0.5322, + "step": 1054 + }, + { + "epoch": 0.09, + "learning_rate": 1.9822659173742904e-05, + "loss": 0.52, + "step": 1055 + }, + { + "epoch": 0.09, + "learning_rate": 1.9822150724590528e-05, + "loss": 0.5226, + "step": 1056 + }, + { + "epoch": 0.09, + "learning_rate": 1.9821641554140252e-05, + "loss": 0.4941, + "step": 1057 + }, + { + "epoch": 0.09, + "learning_rate": 1.9821131662429476e-05, + "loss": 0.5173, + "step": 1058 + }, + { + "epoch": 0.09, + "learning_rate": 1.9820621049495637e-05, + "loss": 0.5042, + "step": 1059 + }, + { + "epoch": 0.09, + "learning_rate": 1.9820109715376236e-05, + "loss": 0.5264, + "step": 1060 + }, + { + "epoch": 0.09, + "learning_rate": 1.9819597660108823e-05, + "loss": 0.5155, + "step": 1061 + }, + { + "epoch": 0.09, + "learning_rate": 1.9819084883731e-05, + "loss": 0.5059, + "step": 1062 + }, + { + "epoch": 0.09, + "learning_rate": 1.9818571386280422e-05, + "loss": 0.5237, + "step": 1063 + }, + { + "epoch": 0.09, + "learning_rate": 1.9818057167794803e-05, + "loss": 0.5203, + "step": 1064 + }, + { + "epoch": 0.09, + "learning_rate": 1.98175422283119e-05, + "loss": 0.5128, + "step": 1065 + }, + { + "epoch": 0.09, + "learning_rate": 1.9817026567869527e-05, + "loss": 0.5125, + "step": 1066 + }, + { + "epoch": 0.09, + "learning_rate": 1.9816510186505562e-05, + "loss": 0.5056, + "step": 1067 + }, + { + "epoch": 0.09, + "learning_rate": 1.9815993084257913e-05, + "loss": 0.5249, + "step": 1068 + }, + { + "epoch": 0.09, + "learning_rate": 1.9815475261164563e-05, + "loss": 0.5111, + "step": 1069 + }, + { + "epoch": 0.09, + "learning_rate": 1.9814956717263534e-05, + "loss": 0.5204, + "step": 1070 + }, + { + "epoch": 0.09, + "learning_rate": 1.9814437452592908e-05, + "loss": 0.5045, + "step": 1071 + }, + { + "epoch": 0.09, + "learning_rate": 1.9813917467190817e-05, + "loss": 0.4943, + "step": 1072 + }, + { + "epoch": 0.09, + "learning_rate": 1.9813396761095446e-05, + "loss": 0.5294, + "step": 1073 + }, + { + "epoch": 0.09, + "learning_rate": 1.9812875334345032e-05, + "loss": 0.5243, + "step": 1074 + }, + { + "epoch": 0.09, + "learning_rate": 1.981235318697787e-05, + "loss": 0.508, + "step": 1075 + }, + { + "epoch": 0.09, + "learning_rate": 1.98118303190323e-05, + "loss": 0.5013, + "step": 1076 + }, + { + "epoch": 0.09, + "learning_rate": 1.9811306730546728e-05, + "loss": 0.494, + "step": 1077 + }, + { + "epoch": 0.09, + "learning_rate": 1.9810782421559595e-05, + "loss": 0.5325, + "step": 1078 + }, + { + "epoch": 0.09, + "learning_rate": 1.9810257392109405e-05, + "loss": 0.5255, + "step": 1079 + }, + { + "epoch": 0.09, + "learning_rate": 1.9809731642234715e-05, + "loss": 0.5053, + "step": 1080 + }, + { + "epoch": 0.09, + "learning_rate": 1.9809205171974136e-05, + "loss": 0.5062, + "step": 1081 + }, + { + "epoch": 0.09, + "learning_rate": 1.9808677981366334e-05, + "loss": 0.5201, + "step": 1082 + }, + { + "epoch": 0.09, + "learning_rate": 1.9808150070450015e-05, + "loss": 0.4957, + "step": 1083 + }, + { + "epoch": 0.09, + "learning_rate": 1.980762143926395e-05, + "loss": 0.5247, + "step": 1084 + }, + { + "epoch": 0.09, + "learning_rate": 1.9807092087846956e-05, + "loss": 0.5265, + "step": 1085 + }, + { + "epoch": 0.09, + "learning_rate": 1.9806562016237913e-05, + "loss": 0.528, + "step": 1086 + }, + { + "epoch": 0.09, + "learning_rate": 1.9806031224475743e-05, + "loss": 0.5301, + "step": 1087 + }, + { + "epoch": 0.09, + "learning_rate": 1.9805499712599426e-05, + "loss": 0.5281, + "step": 1088 + }, + { + "epoch": 0.09, + "learning_rate": 1.9804967480647996e-05, + "loss": 0.5024, + "step": 1089 + }, + { + "epoch": 0.09, + "learning_rate": 1.9804434528660536e-05, + "loss": 0.5087, + "step": 1090 + }, + { + "epoch": 0.09, + "learning_rate": 1.9803900856676182e-05, + "loss": 0.5004, + "step": 1091 + }, + { + "epoch": 0.09, + "learning_rate": 1.980336646473413e-05, + "loss": 0.5165, + "step": 1092 + }, + { + "epoch": 0.09, + "learning_rate": 1.980283135287362e-05, + "loss": 0.4901, + "step": 1093 + }, + { + "epoch": 0.09, + "learning_rate": 1.9802295521133942e-05, + "loss": 0.5026, + "step": 1094 + }, + { + "epoch": 0.09, + "learning_rate": 1.980175896955446e-05, + "loss": 0.5191, + "step": 1095 + }, + { + "epoch": 0.09, + "learning_rate": 1.9801221698174564e-05, + "loss": 0.5122, + "step": 1096 + }, + { + "epoch": 0.09, + "learning_rate": 1.980068370703371e-05, + "loss": 0.5061, + "step": 1097 + }, + { + "epoch": 0.09, + "learning_rate": 1.9800144996171415e-05, + "loss": 0.5216, + "step": 1098 + }, + { + "epoch": 0.09, + "learning_rate": 1.979960556562723e-05, + "loss": 0.5257, + "step": 1099 + }, + { + "epoch": 0.09, + "learning_rate": 1.979906541544077e-05, + "loss": 0.5028, + "step": 1100 + }, + { + "epoch": 0.09, + "learning_rate": 1.9798524545651705e-05, + "loss": 0.5225, + "step": 1101 + }, + { + "epoch": 0.09, + "learning_rate": 1.9797982956299754e-05, + "loss": 0.5049, + "step": 1102 + }, + { + "epoch": 0.09, + "learning_rate": 1.9797440647424687e-05, + "loss": 0.5348, + "step": 1103 + }, + { + "epoch": 0.09, + "learning_rate": 1.9796897619066327e-05, + "loss": 0.5152, + "step": 1104 + }, + { + "epoch": 0.09, + "learning_rate": 1.9796353871264555e-05, + "loss": 0.5002, + "step": 1105 + }, + { + "epoch": 0.09, + "learning_rate": 1.97958094040593e-05, + "loss": 0.5106, + "step": 1106 + }, + { + "epoch": 0.09, + "learning_rate": 1.9795264217490547e-05, + "loss": 0.5306, + "step": 1107 + }, + { + "epoch": 0.09, + "learning_rate": 1.9794718311598337e-05, + "loss": 0.5149, + "step": 1108 + }, + { + "epoch": 0.09, + "learning_rate": 1.9794171686422746e-05, + "loss": 0.4985, + "step": 1109 + }, + { + "epoch": 0.09, + "learning_rate": 1.9793624342003927e-05, + "loss": 0.526, + "step": 1110 + }, + { + "epoch": 0.09, + "learning_rate": 1.979307627838207e-05, + "loss": 0.5112, + "step": 1111 + }, + { + "epoch": 0.09, + "learning_rate": 1.9792527495597423e-05, + "loss": 0.5188, + "step": 1112 + }, + { + "epoch": 0.09, + "learning_rate": 1.9791977993690292e-05, + "loss": 0.5096, + "step": 1113 + }, + { + "epoch": 0.09, + "learning_rate": 1.9791427772701017e-05, + "loss": 0.5175, + "step": 1114 + }, + { + "epoch": 0.09, + "learning_rate": 1.9790876832670018e-05, + "loss": 0.5098, + "step": 1115 + }, + { + "epoch": 0.09, + "learning_rate": 1.9790325173637744e-05, + "loss": 0.5037, + "step": 1116 + }, + { + "epoch": 0.09, + "learning_rate": 1.9789772795644714e-05, + "loss": 0.5231, + "step": 1117 + }, + { + "epoch": 0.09, + "learning_rate": 1.9789219698731484e-05, + "loss": 0.5139, + "step": 1118 + }, + { + "epoch": 0.09, + "learning_rate": 1.9788665882938677e-05, + "loss": 0.5106, + "step": 1119 + }, + { + "epoch": 0.09, + "learning_rate": 1.9788111348306963e-05, + "loss": 0.522, + "step": 1120 + }, + { + "epoch": 0.09, + "learning_rate": 1.978755609487706e-05, + "loss": 0.4982, + "step": 1121 + }, + { + "epoch": 0.09, + "learning_rate": 1.9787000122689753e-05, + "loss": 0.5091, + "step": 1122 + }, + { + "epoch": 0.09, + "learning_rate": 1.978644343178586e-05, + "loss": 0.5313, + "step": 1123 + }, + { + "epoch": 0.09, + "learning_rate": 1.978588602220627e-05, + "loss": 0.5007, + "step": 1124 + }, + { + "epoch": 0.09, + "learning_rate": 1.978532789399191e-05, + "loss": 0.5144, + "step": 1125 + }, + { + "epoch": 0.09, + "learning_rate": 1.978476904718377e-05, + "loss": 0.5293, + "step": 1126 + }, + { + "epoch": 0.09, + "learning_rate": 1.9784209481822892e-05, + "loss": 0.5137, + "step": 1127 + }, + { + "epoch": 0.09, + "learning_rate": 1.9783649197950362e-05, + "loss": 0.4985, + "step": 1128 + }, + { + "epoch": 0.09, + "learning_rate": 1.978308819560733e-05, + "loss": 0.5455, + "step": 1129 + }, + { + "epoch": 0.09, + "learning_rate": 1.9782526474834988e-05, + "loss": 0.4913, + "step": 1130 + }, + { + "epoch": 0.09, + "learning_rate": 1.978196403567459e-05, + "loss": 0.5198, + "step": 1131 + }, + { + "epoch": 0.09, + "learning_rate": 1.9781400878167446e-05, + "loss": 0.5024, + "step": 1132 + }, + { + "epoch": 0.09, + "learning_rate": 1.97808370023549e-05, + "loss": 0.5142, + "step": 1133 + }, + { + "epoch": 0.09, + "learning_rate": 1.978027240827837e-05, + "loss": 0.5143, + "step": 1134 + }, + { + "epoch": 0.09, + "learning_rate": 1.977970709597931e-05, + "loss": 0.5094, + "step": 1135 + }, + { + "epoch": 0.1, + "learning_rate": 1.977914106549924e-05, + "loss": 0.5372, + "step": 1136 + }, + { + "epoch": 0.1, + "learning_rate": 1.9778574316879724e-05, + "loss": 0.5168, + "step": 1137 + }, + { + "epoch": 0.1, + "learning_rate": 1.9778006850162384e-05, + "loss": 0.4953, + "step": 1138 + }, + { + "epoch": 0.1, + "learning_rate": 1.9777438665388885e-05, + "loss": 0.5212, + "step": 1139 + }, + { + "epoch": 0.1, + "learning_rate": 1.9776869762600963e-05, + "loss": 0.5067, + "step": 1140 + }, + { + "epoch": 0.1, + "learning_rate": 1.977630014184039e-05, + "loss": 0.5148, + "step": 1141 + }, + { + "epoch": 0.1, + "learning_rate": 1.9775729803148994e-05, + "loss": 0.5136, + "step": 1142 + }, + { + "epoch": 0.1, + "learning_rate": 1.9775158746568665e-05, + "loss": 0.508, + "step": 1143 + }, + { + "epoch": 0.1, + "learning_rate": 1.9774586972141337e-05, + "loss": 0.5262, + "step": 1144 + }, + { + "epoch": 0.1, + "learning_rate": 1.9774014479908996e-05, + "loss": 0.5161, + "step": 1145 + }, + { + "epoch": 0.1, + "learning_rate": 1.977344126991368e-05, + "loss": 0.5174, + "step": 1146 + }, + { + "epoch": 0.1, + "learning_rate": 1.9772867342197494e-05, + "loss": 0.5228, + "step": 1147 + }, + { + "epoch": 0.1, + "learning_rate": 1.977229269680258e-05, + "loss": 0.5263, + "step": 1148 + }, + { + "epoch": 0.1, + "learning_rate": 1.9771717333771133e-05, + "loss": 0.4995, + "step": 1149 + }, + { + "epoch": 0.1, + "learning_rate": 1.9771141253145405e-05, + "loss": 0.5082, + "step": 1150 + }, + { + "epoch": 0.1, + "learning_rate": 1.977056445496771e-05, + "loss": 0.5178, + "step": 1151 + }, + { + "epoch": 0.1, + "learning_rate": 1.97699869392804e-05, + "loss": 0.5053, + "step": 1152 + }, + { + "epoch": 0.1, + "learning_rate": 1.9769408706125882e-05, + "loss": 0.5052, + "step": 1153 + }, + { + "epoch": 0.1, + "learning_rate": 1.9768829755546625e-05, + "loss": 0.5217, + "step": 1154 + }, + { + "epoch": 0.1, + "learning_rate": 1.9768250087585143e-05, + "loss": 0.5274, + "step": 1155 + }, + { + "epoch": 0.1, + "learning_rate": 1.9767669702284e-05, + "loss": 0.5186, + "step": 1156 + }, + { + "epoch": 0.1, + "learning_rate": 1.9767088599685828e-05, + "loss": 0.5069, + "step": 1157 + }, + { + "epoch": 0.1, + "learning_rate": 1.9766506779833288e-05, + "loss": 0.523, + "step": 1158 + }, + { + "epoch": 0.1, + "learning_rate": 1.976592424276911e-05, + "loss": 0.4902, + "step": 1159 + }, + { + "epoch": 0.1, + "learning_rate": 1.976534098853608e-05, + "loss": 0.5006, + "step": 1160 + }, + { + "epoch": 0.1, + "learning_rate": 1.9764757017177025e-05, + "loss": 0.5004, + "step": 1161 + }, + { + "epoch": 0.1, + "learning_rate": 1.9764172328734828e-05, + "loss": 0.5145, + "step": 1162 + }, + { + "epoch": 0.1, + "learning_rate": 1.9763586923252428e-05, + "loss": 0.493, + "step": 1163 + }, + { + "epoch": 0.1, + "learning_rate": 1.9763000800772812e-05, + "loss": 0.5021, + "step": 1164 + }, + { + "epoch": 0.1, + "learning_rate": 1.9762413961339025e-05, + "loss": 0.5073, + "step": 1165 + }, + { + "epoch": 0.1, + "learning_rate": 1.9761826404994166e-05, + "loss": 0.5356, + "step": 1166 + }, + { + "epoch": 0.1, + "learning_rate": 1.9761238131781373e-05, + "loss": 0.523, + "step": 1167 + }, + { + "epoch": 0.1, + "learning_rate": 1.9760649141743855e-05, + "loss": 0.513, + "step": 1168 + }, + { + "epoch": 0.1, + "learning_rate": 1.9760059434924857e-05, + "loss": 0.5363, + "step": 1169 + }, + { + "epoch": 0.1, + "learning_rate": 1.9759469011367695e-05, + "loss": 0.5097, + "step": 1170 + }, + { + "epoch": 0.1, + "learning_rate": 1.975887787111572e-05, + "loss": 0.5259, + "step": 1171 + }, + { + "epoch": 0.1, + "learning_rate": 1.975828601421234e-05, + "loss": 0.5167, + "step": 1172 + }, + { + "epoch": 0.1, + "learning_rate": 1.975769344070103e-05, + "loss": 0.4906, + "step": 1173 + }, + { + "epoch": 0.1, + "learning_rate": 1.9757100150625295e-05, + "loss": 0.525, + "step": 1174 + }, + { + "epoch": 0.1, + "learning_rate": 1.975650614402871e-05, + "loss": 0.5207, + "step": 1175 + }, + { + "epoch": 0.1, + "learning_rate": 1.975591142095489e-05, + "loss": 0.5033, + "step": 1176 + }, + { + "epoch": 0.1, + "learning_rate": 1.9755315981447513e-05, + "loss": 0.5178, + "step": 1177 + }, + { + "epoch": 0.1, + "learning_rate": 1.975471982555031e-05, + "loss": 0.4966, + "step": 1178 + }, + { + "epoch": 0.1, + "learning_rate": 1.9754122953307052e-05, + "loss": 0.524, + "step": 1179 + }, + { + "epoch": 0.1, + "learning_rate": 1.9753525364761577e-05, + "loss": 0.5143, + "step": 1180 + }, + { + "epoch": 0.1, + "learning_rate": 1.975292705995777e-05, + "loss": 0.5026, + "step": 1181 + }, + { + "epoch": 0.1, + "learning_rate": 1.9752328038939562e-05, + "loss": 0.5305, + "step": 1182 + }, + { + "epoch": 0.1, + "learning_rate": 1.9751728301750943e-05, + "loss": 0.5092, + "step": 1183 + }, + { + "epoch": 0.1, + "learning_rate": 1.975112784843596e-05, + "loss": 0.5055, + "step": 1184 + }, + { + "epoch": 0.1, + "learning_rate": 1.975052667903871e-05, + "loss": 0.5055, + "step": 1185 + }, + { + "epoch": 0.1, + "learning_rate": 1.9749924793603333e-05, + "loss": 0.5254, + "step": 1186 + }, + { + "epoch": 0.1, + "learning_rate": 1.974932219217403e-05, + "loss": 0.4859, + "step": 1187 + }, + { + "epoch": 0.1, + "learning_rate": 1.9748718874795057e-05, + "loss": 0.524, + "step": 1188 + }, + { + "epoch": 0.1, + "learning_rate": 1.9748114841510723e-05, + "loss": 0.5059, + "step": 1189 + }, + { + "epoch": 0.1, + "learning_rate": 1.9747510092365373e-05, + "loss": 0.4723, + "step": 1190 + }, + { + "epoch": 0.1, + "learning_rate": 1.974690462740343e-05, + "loss": 0.4963, + "step": 1191 + }, + { + "epoch": 0.1, + "learning_rate": 1.974629844666935e-05, + "loss": 0.522, + "step": 1192 + }, + { + "epoch": 0.1, + "learning_rate": 1.9745691550207647e-05, + "loss": 0.5129, + "step": 1193 + }, + { + "epoch": 0.1, + "learning_rate": 1.9745083938062896e-05, + "loss": 0.5143, + "step": 1194 + }, + { + "epoch": 0.1, + "learning_rate": 1.974447561027971e-05, + "loss": 0.51, + "step": 1195 + }, + { + "epoch": 0.1, + "learning_rate": 1.9743866566902766e-05, + "loss": 0.4938, + "step": 1196 + }, + { + "epoch": 0.1, + "learning_rate": 1.974325680797679e-05, + "loss": 0.5115, + "step": 1197 + }, + { + "epoch": 0.1, + "learning_rate": 1.9742646333546564e-05, + "loss": 0.5036, + "step": 1198 + }, + { + "epoch": 0.1, + "learning_rate": 1.9742035143656907e-05, + "loss": 0.5087, + "step": 1199 + }, + { + "epoch": 0.1, + "learning_rate": 1.9741423238352713e-05, + "loss": 0.5302, + "step": 1200 + }, + { + "epoch": 0.1, + "learning_rate": 1.9740810617678912e-05, + "loss": 0.5194, + "step": 1201 + }, + { + "epoch": 0.1, + "learning_rate": 1.9740197281680495e-05, + "loss": 0.5209, + "step": 1202 + }, + { + "epoch": 0.1, + "learning_rate": 1.9739583230402503e-05, + "loss": 0.5251, + "step": 1203 + }, + { + "epoch": 0.1, + "learning_rate": 1.9738968463890026e-05, + "loss": 0.4995, + "step": 1204 + }, + { + "epoch": 0.1, + "learning_rate": 1.9738352982188217e-05, + "loss": 0.5176, + "step": 1205 + }, + { + "epoch": 0.1, + "learning_rate": 1.9737736785342265e-05, + "loss": 0.4993, + "step": 1206 + }, + { + "epoch": 0.1, + "learning_rate": 1.9737119873397427e-05, + "loss": 0.5252, + "step": 1207 + }, + { + "epoch": 0.1, + "learning_rate": 1.9736502246399006e-05, + "loss": 0.5087, + "step": 1208 + }, + { + "epoch": 0.1, + "learning_rate": 1.973588390439236e-05, + "loss": 0.5036, + "step": 1209 + }, + { + "epoch": 0.1, + "learning_rate": 1.9735264847422893e-05, + "loss": 0.5247, + "step": 1210 + }, + { + "epoch": 0.1, + "learning_rate": 1.9734645075536063e-05, + "loss": 0.5141, + "step": 1211 + }, + { + "epoch": 0.1, + "learning_rate": 1.9734024588777393e-05, + "loss": 0.5, + "step": 1212 + }, + { + "epoch": 0.1, + "learning_rate": 1.9733403387192443e-05, + "loss": 0.5339, + "step": 1213 + }, + { + "epoch": 0.1, + "learning_rate": 1.973278147082683e-05, + "loss": 0.5397, + "step": 1214 + }, + { + "epoch": 0.1, + "learning_rate": 1.9732158839726233e-05, + "loss": 0.5121, + "step": 1215 + }, + { + "epoch": 0.1, + "learning_rate": 1.9731535493936365e-05, + "loss": 0.5215, + "step": 1216 + }, + { + "epoch": 0.1, + "learning_rate": 1.9730911433503007e-05, + "loss": 0.5149, + "step": 1217 + }, + { + "epoch": 0.1, + "learning_rate": 1.973028665847199e-05, + "loss": 0.4978, + "step": 1218 + }, + { + "epoch": 0.1, + "learning_rate": 1.9729661168889193e-05, + "loss": 0.5068, + "step": 1219 + }, + { + "epoch": 0.1, + "learning_rate": 1.9729034964800546e-05, + "loss": 0.5087, + "step": 1220 + }, + { + "epoch": 0.1, + "learning_rate": 1.9728408046252035e-05, + "loss": 0.5171, + "step": 1221 + }, + { + "epoch": 0.1, + "learning_rate": 1.9727780413289706e-05, + "loss": 0.4988, + "step": 1222 + }, + { + "epoch": 0.1, + "learning_rate": 1.972715206595964e-05, + "loss": 0.5109, + "step": 1223 + }, + { + "epoch": 0.1, + "learning_rate": 1.9726523004307987e-05, + "loss": 0.5163, + "step": 1224 + }, + { + "epoch": 0.1, + "learning_rate": 1.9725893228380938e-05, + "loss": 0.5143, + "step": 1225 + }, + { + "epoch": 0.1, + "learning_rate": 1.9725262738224743e-05, + "loss": 0.4988, + "step": 1226 + }, + { + "epoch": 0.1, + "learning_rate": 1.9724631533885706e-05, + "loss": 0.5187, + "step": 1227 + }, + { + "epoch": 0.1, + "learning_rate": 1.9723999615410175e-05, + "loss": 0.4917, + "step": 1228 + }, + { + "epoch": 0.1, + "learning_rate": 1.9723366982844555e-05, + "loss": 0.5087, + "step": 1229 + }, + { + "epoch": 0.1, + "learning_rate": 1.972273363623531e-05, + "loss": 0.5089, + "step": 1230 + }, + { + "epoch": 0.1, + "learning_rate": 1.9722099575628947e-05, + "loss": 0.5231, + "step": 1231 + }, + { + "epoch": 0.1, + "learning_rate": 1.9721464801072027e-05, + "loss": 0.526, + "step": 1232 + }, + { + "epoch": 0.1, + "learning_rate": 1.972082931261117e-05, + "loss": 0.5141, + "step": 1233 + }, + { + "epoch": 0.1, + "learning_rate": 1.9720193110293033e-05, + "loss": 0.5202, + "step": 1234 + }, + { + "epoch": 0.1, + "learning_rate": 1.971955619416435e-05, + "loss": 0.5147, + "step": 1235 + }, + { + "epoch": 0.1, + "learning_rate": 1.9718918564271883e-05, + "loss": 0.5051, + "step": 1236 + }, + { + "epoch": 0.1, + "learning_rate": 1.9718280220662463e-05, + "loss": 0.5223, + "step": 1237 + }, + { + "epoch": 0.1, + "learning_rate": 1.9717641163382963e-05, + "loss": 0.4992, + "step": 1238 + }, + { + "epoch": 0.1, + "learning_rate": 1.9717001392480316e-05, + "loss": 0.5245, + "step": 1239 + }, + { + "epoch": 0.1, + "learning_rate": 1.9716360908001498e-05, + "loss": 0.5031, + "step": 1240 + }, + { + "epoch": 0.1, + "learning_rate": 1.9715719709993557e-05, + "loss": 0.525, + "step": 1241 + }, + { + "epoch": 0.1, + "learning_rate": 1.9715077798503564e-05, + "loss": 0.5027, + "step": 1242 + }, + { + "epoch": 0.1, + "learning_rate": 1.971443517357867e-05, + "loss": 0.5122, + "step": 1243 + }, + { + "epoch": 0.1, + "learning_rate": 1.971379183526606e-05, + "loss": 0.5119, + "step": 1244 + }, + { + "epoch": 0.1, + "learning_rate": 1.971314778361298e-05, + "loss": 0.5363, + "step": 1245 + }, + { + "epoch": 0.1, + "learning_rate": 1.9712503018666725e-05, + "loss": 0.508, + "step": 1246 + }, + { + "epoch": 0.1, + "learning_rate": 1.9711857540474653e-05, + "loss": 0.5225, + "step": 1247 + }, + { + "epoch": 0.1, + "learning_rate": 1.971121134908415e-05, + "loss": 0.4993, + "step": 1248 + }, + { + "epoch": 0.1, + "learning_rate": 1.9710564444542683e-05, + "loss": 0.5271, + "step": 1249 + }, + { + "epoch": 0.1, + "learning_rate": 1.9709916826897747e-05, + "loss": 0.502, + "step": 1250 + }, + { + "epoch": 0.1, + "learning_rate": 1.9709268496196912e-05, + "loss": 0.519, + "step": 1251 + }, + { + "epoch": 0.1, + "learning_rate": 1.9708619452487777e-05, + "loss": 0.5257, + "step": 1252 + }, + { + "epoch": 0.1, + "learning_rate": 1.9707969695818013e-05, + "loss": 0.5047, + "step": 1253 + }, + { + "epoch": 0.1, + "learning_rate": 1.9707319226235337e-05, + "loss": 0.5178, + "step": 1254 + }, + { + "epoch": 0.1, + "learning_rate": 1.9706668043787505e-05, + "loss": 0.5169, + "step": 1255 + }, + { + "epoch": 0.11, + "learning_rate": 1.970601614852235e-05, + "loss": 0.5234, + "step": 1256 + }, + { + "epoch": 0.11, + "learning_rate": 1.9705363540487737e-05, + "loss": 0.5084, + "step": 1257 + }, + { + "epoch": 0.11, + "learning_rate": 1.9704710219731594e-05, + "loss": 0.5308, + "step": 1258 + }, + { + "epoch": 0.11, + "learning_rate": 1.9704056186301898e-05, + "loss": 0.4999, + "step": 1259 + }, + { + "epoch": 0.11, + "learning_rate": 1.970340144024668e-05, + "loss": 0.5197, + "step": 1260 + }, + { + "epoch": 0.11, + "learning_rate": 1.9702745981614018e-05, + "loss": 0.5139, + "step": 1261 + }, + { + "epoch": 0.11, + "learning_rate": 1.9702089810452046e-05, + "loss": 0.513, + "step": 1262 + }, + { + "epoch": 0.11, + "learning_rate": 1.9701432926808955e-05, + "loss": 0.5229, + "step": 1263 + }, + { + "epoch": 0.11, + "learning_rate": 1.9700775330732977e-05, + "loss": 0.5081, + "step": 1264 + }, + { + "epoch": 0.11, + "learning_rate": 1.970011702227241e-05, + "loss": 0.5058, + "step": 1265 + }, + { + "epoch": 0.11, + "learning_rate": 1.9699458001475594e-05, + "loss": 0.5179, + "step": 1266 + }, + { + "epoch": 0.11, + "learning_rate": 1.9698798268390927e-05, + "loss": 0.521, + "step": 1267 + }, + { + "epoch": 0.11, + "learning_rate": 1.9698137823066856e-05, + "loss": 0.5244, + "step": 1268 + }, + { + "epoch": 0.11, + "learning_rate": 1.969747666555188e-05, + "loss": 0.5232, + "step": 1269 + }, + { + "epoch": 0.11, + "learning_rate": 1.969681479589455e-05, + "loss": 0.4983, + "step": 1270 + }, + { + "epoch": 0.11, + "learning_rate": 1.9696152214143476e-05, + "loss": 0.4996, + "step": 1271 + }, + { + "epoch": 0.11, + "learning_rate": 1.9695488920347313e-05, + "loss": 0.5006, + "step": 1272 + }, + { + "epoch": 0.11, + "learning_rate": 1.969482491455477e-05, + "loss": 0.5173, + "step": 1273 + }, + { + "epoch": 0.11, + "learning_rate": 1.969416019681461e-05, + "loss": 0.5322, + "step": 1274 + }, + { + "epoch": 0.11, + "learning_rate": 1.9693494767175644e-05, + "loss": 0.5, + "step": 1275 + }, + { + "epoch": 0.11, + "learning_rate": 1.969282862568674e-05, + "loss": 0.5144, + "step": 1276 + }, + { + "epoch": 0.11, + "learning_rate": 1.969216177239682e-05, + "loss": 0.5095, + "step": 1277 + }, + { + "epoch": 0.11, + "learning_rate": 1.969149420735485e-05, + "loss": 0.4908, + "step": 1278 + }, + { + "epoch": 0.11, + "learning_rate": 1.9690825930609857e-05, + "loss": 0.5235, + "step": 1279 + }, + { + "epoch": 0.11, + "learning_rate": 1.9690156942210912e-05, + "loss": 0.5159, + "step": 1280 + }, + { + "epoch": 0.11, + "learning_rate": 1.968948724220715e-05, + "loss": 0.5012, + "step": 1281 + }, + { + "epoch": 0.11, + "learning_rate": 1.9688816830647743e-05, + "loss": 0.5233, + "step": 1282 + }, + { + "epoch": 0.11, + "learning_rate": 1.9688145707581927e-05, + "loss": 0.5285, + "step": 1283 + }, + { + "epoch": 0.11, + "learning_rate": 1.9687473873058987e-05, + "loss": 0.4938, + "step": 1284 + }, + { + "epoch": 0.11, + "learning_rate": 1.9686801327128256e-05, + "loss": 0.5234, + "step": 1285 + }, + { + "epoch": 0.11, + "learning_rate": 1.968612806983913e-05, + "loss": 0.5155, + "step": 1286 + }, + { + "epoch": 0.11, + "learning_rate": 1.9685454101241048e-05, + "loss": 0.5218, + "step": 1287 + }, + { + "epoch": 0.11, + "learning_rate": 1.9684779421383496e-05, + "loss": 0.5122, + "step": 1288 + }, + { + "epoch": 0.11, + "learning_rate": 1.968410403031603e-05, + "loss": 0.5191, + "step": 1289 + }, + { + "epoch": 0.11, + "learning_rate": 1.9683427928088243e-05, + "loss": 0.5145, + "step": 1290 + }, + { + "epoch": 0.11, + "learning_rate": 1.9682751114749783e-05, + "loss": 0.4944, + "step": 1291 + }, + { + "epoch": 0.11, + "learning_rate": 1.968207359035036e-05, + "loss": 0.5042, + "step": 1292 + }, + { + "epoch": 0.11, + "learning_rate": 1.9681395354939714e-05, + "loss": 0.5227, + "step": 1293 + }, + { + "epoch": 0.11, + "learning_rate": 1.9680716408567667e-05, + "loss": 0.4942, + "step": 1294 + }, + { + "epoch": 0.11, + "learning_rate": 1.968003675128407e-05, + "loss": 0.5026, + "step": 1295 + }, + { + "epoch": 0.11, + "learning_rate": 1.967935638313884e-05, + "loss": 0.5096, + "step": 1296 + }, + { + "epoch": 0.11, + "learning_rate": 1.9678675304181932e-05, + "loss": 0.5114, + "step": 1297 + }, + { + "epoch": 0.11, + "learning_rate": 1.9677993514463368e-05, + "loss": 0.5041, + "step": 1298 + }, + { + "epoch": 0.11, + "learning_rate": 1.9677311014033217e-05, + "loss": 0.5283, + "step": 1299 + }, + { + "epoch": 0.11, + "learning_rate": 1.967662780294159e-05, + "loss": 0.524, + "step": 1300 + }, + { + "epoch": 0.11, + "learning_rate": 1.9675943881238672e-05, + "loss": 0.5259, + "step": 1301 + }, + { + "epoch": 0.11, + "learning_rate": 1.9675259248974675e-05, + "loss": 0.5022, + "step": 1302 + }, + { + "epoch": 0.11, + "learning_rate": 1.967457390619988e-05, + "loss": 0.5028, + "step": 1303 + }, + { + "epoch": 0.11, + "learning_rate": 1.9673887852964623e-05, + "loss": 0.5134, + "step": 1304 + }, + { + "epoch": 0.11, + "learning_rate": 1.9673201089319275e-05, + "loss": 0.5189, + "step": 1305 + }, + { + "epoch": 0.11, + "learning_rate": 1.9672513615314278e-05, + "loss": 0.507, + "step": 1306 + }, + { + "epoch": 0.11, + "learning_rate": 1.9671825431000107e-05, + "loss": 0.5226, + "step": 1307 + }, + { + "epoch": 0.11, + "learning_rate": 1.9671136536427308e-05, + "loss": 0.5185, + "step": 1308 + }, + { + "epoch": 0.11, + "learning_rate": 1.9670446931646463e-05, + "loss": 0.5154, + "step": 1309 + }, + { + "epoch": 0.11, + "learning_rate": 1.966975661670822e-05, + "loss": 0.5179, + "step": 1310 + }, + { + "epoch": 0.11, + "learning_rate": 1.966906559166327e-05, + "loss": 0.541, + "step": 1311 + }, + { + "epoch": 0.11, + "learning_rate": 1.966837385656236e-05, + "loss": 0.5082, + "step": 1312 + }, + { + "epoch": 0.11, + "learning_rate": 1.9667681411456286e-05, + "loss": 0.4997, + "step": 1313 + }, + { + "epoch": 0.11, + "learning_rate": 1.96669882563959e-05, + "loss": 0.5202, + "step": 1314 + }, + { + "epoch": 0.11, + "learning_rate": 1.9666294391432108e-05, + "loss": 0.5297, + "step": 1315 + }, + { + "epoch": 0.11, + "learning_rate": 1.966559981661586e-05, + "loss": 0.5074, + "step": 1316 + }, + { + "epoch": 0.11, + "learning_rate": 1.9664904531998165e-05, + "loss": 0.4969, + "step": 1317 + }, + { + "epoch": 0.11, + "learning_rate": 1.9664208537630073e-05, + "loss": 0.5015, + "step": 1318 + }, + { + "epoch": 0.11, + "learning_rate": 1.966351183356271e-05, + "loss": 0.5037, + "step": 1319 + }, + { + "epoch": 0.11, + "learning_rate": 1.9662814419847228e-05, + "loss": 0.4986, + "step": 1320 + }, + { + "epoch": 0.11, + "learning_rate": 1.966211629653485e-05, + "loss": 0.5048, + "step": 1321 + }, + { + "epoch": 0.11, + "learning_rate": 1.9661417463676834e-05, + "loss": 0.5106, + "step": 1322 + }, + { + "epoch": 0.11, + "learning_rate": 1.966071792132451e-05, + "loss": 0.5144, + "step": 1323 + }, + { + "epoch": 0.11, + "learning_rate": 1.9660017669529236e-05, + "loss": 0.5227, + "step": 1324 + }, + { + "epoch": 0.11, + "learning_rate": 1.965931670834245e-05, + "loss": 0.5105, + "step": 1325 + }, + { + "epoch": 0.11, + "learning_rate": 1.965861503781562e-05, + "loss": 0.4987, + "step": 1326 + }, + { + "epoch": 0.11, + "learning_rate": 1.9657912658000272e-05, + "loss": 0.5063, + "step": 1327 + }, + { + "epoch": 0.11, + "learning_rate": 1.965720956894799e-05, + "loss": 0.5112, + "step": 1328 + }, + { + "epoch": 0.11, + "learning_rate": 1.9656505770710404e-05, + "loss": 0.5036, + "step": 1329 + }, + { + "epoch": 0.11, + "learning_rate": 1.9655801263339198e-05, + "loss": 0.4904, + "step": 1330 + }, + { + "epoch": 0.11, + "learning_rate": 1.965509604688611e-05, + "loss": 0.5203, + "step": 1331 + }, + { + "epoch": 0.11, + "learning_rate": 1.9654390121402927e-05, + "loss": 0.5097, + "step": 1332 + }, + { + "epoch": 0.11, + "learning_rate": 1.965368348694149e-05, + "loss": 0.5146, + "step": 1333 + }, + { + "epoch": 0.11, + "learning_rate": 1.965297614355369e-05, + "loss": 0.4991, + "step": 1334 + }, + { + "epoch": 0.11, + "learning_rate": 1.965226809129147e-05, + "loss": 0.5255, + "step": 1335 + }, + { + "epoch": 0.11, + "learning_rate": 1.9651559330206827e-05, + "loss": 0.5182, + "step": 1336 + }, + { + "epoch": 0.11, + "learning_rate": 1.9650849860351818e-05, + "loss": 0.5092, + "step": 1337 + }, + { + "epoch": 0.11, + "learning_rate": 1.9650139681778527e-05, + "loss": 0.537, + "step": 1338 + }, + { + "epoch": 0.11, + "learning_rate": 1.9649428794539122e-05, + "loss": 0.5066, + "step": 1339 + }, + { + "epoch": 0.11, + "learning_rate": 1.9648717198685798e-05, + "loss": 0.5199, + "step": 1340 + }, + { + "epoch": 0.11, + "learning_rate": 1.9648004894270816e-05, + "loss": 0.4998, + "step": 1341 + }, + { + "epoch": 0.11, + "learning_rate": 1.9647291881346485e-05, + "loss": 0.5155, + "step": 1342 + }, + { + "epoch": 0.11, + "learning_rate": 1.9646578159965163e-05, + "loss": 0.5068, + "step": 1343 + }, + { + "epoch": 0.11, + "learning_rate": 1.9645863730179263e-05, + "loss": 0.4993, + "step": 1344 + }, + { + "epoch": 0.11, + "learning_rate": 1.964514859204125e-05, + "loss": 0.5225, + "step": 1345 + }, + { + "epoch": 0.11, + "learning_rate": 1.9644432745603644e-05, + "loss": 0.5065, + "step": 1346 + }, + { + "epoch": 0.11, + "learning_rate": 1.9643716190919014e-05, + "loss": 0.5013, + "step": 1347 + }, + { + "epoch": 0.11, + "learning_rate": 1.9642998928039976e-05, + "loss": 0.499, + "step": 1348 + }, + { + "epoch": 0.11, + "learning_rate": 1.96422809570192e-05, + "loss": 0.515, + "step": 1349 + }, + { + "epoch": 0.11, + "learning_rate": 1.9641562277909424e-05, + "loss": 0.5082, + "step": 1350 + }, + { + "epoch": 0.11, + "learning_rate": 1.9640842890763413e-05, + "loss": 0.5162, + "step": 1351 + }, + { + "epoch": 0.11, + "learning_rate": 1.9640122795633997e-05, + "loss": 0.4928, + "step": 1352 + }, + { + "epoch": 0.11, + "learning_rate": 1.9639401992574065e-05, + "loss": 0.4976, + "step": 1353 + }, + { + "epoch": 0.11, + "learning_rate": 1.9638680481636535e-05, + "loss": 0.5015, + "step": 1354 + }, + { + "epoch": 0.11, + "learning_rate": 1.9637958262874404e-05, + "loss": 0.4962, + "step": 1355 + }, + { + "epoch": 0.11, + "learning_rate": 1.963723533634071e-05, + "loss": 0.5228, + "step": 1356 + }, + { + "epoch": 0.11, + "learning_rate": 1.9636511702088535e-05, + "loss": 0.5255, + "step": 1357 + }, + { + "epoch": 0.11, + "learning_rate": 1.963578736017102e-05, + "loss": 0.5213, + "step": 1358 + }, + { + "epoch": 0.11, + "learning_rate": 1.963506231064136e-05, + "loss": 0.5361, + "step": 1359 + }, + { + "epoch": 0.11, + "learning_rate": 1.9634336553552803e-05, + "loss": 0.5014, + "step": 1360 + }, + { + "epoch": 0.11, + "learning_rate": 1.9633610088958638e-05, + "loss": 0.5107, + "step": 1361 + }, + { + "epoch": 0.11, + "learning_rate": 1.9632882916912217e-05, + "loss": 0.501, + "step": 1362 + }, + { + "epoch": 0.11, + "learning_rate": 1.9632155037466942e-05, + "loss": 0.513, + "step": 1363 + }, + { + "epoch": 0.11, + "learning_rate": 1.9631426450676264e-05, + "loss": 0.4982, + "step": 1364 + }, + { + "epoch": 0.11, + "learning_rate": 1.9630697156593688e-05, + "loss": 0.5127, + "step": 1365 + }, + { + "epoch": 0.11, + "learning_rate": 1.962996715527277e-05, + "loss": 0.488, + "step": 1366 + }, + { + "epoch": 0.11, + "learning_rate": 1.9629236446767118e-05, + "loss": 0.5273, + "step": 1367 + }, + { + "epoch": 0.11, + "learning_rate": 1.962850503113039e-05, + "loss": 0.506, + "step": 1368 + }, + { + "epoch": 0.11, + "learning_rate": 1.9627772908416302e-05, + "loss": 0.4915, + "step": 1369 + }, + { + "epoch": 0.11, + "learning_rate": 1.9627040078678617e-05, + "loss": 0.506, + "step": 1370 + }, + { + "epoch": 0.11, + "learning_rate": 1.9626306541971153e-05, + "loss": 0.5139, + "step": 1371 + }, + { + "epoch": 0.11, + "learning_rate": 1.962557229834777e-05, + "loss": 0.4852, + "step": 1372 + }, + { + "epoch": 0.11, + "learning_rate": 1.9624837347862398e-05, + "loss": 0.532, + "step": 1373 + }, + { + "epoch": 0.11, + "learning_rate": 1.9624101690569e-05, + "loss": 0.5052, + "step": 1374 + }, + { + "epoch": 0.12, + "learning_rate": 1.9623365326521603e-05, + "loss": 0.5007, + "step": 1375 + }, + { + "epoch": 0.12, + "learning_rate": 1.9622628255774288e-05, + "loss": 0.4933, + "step": 1376 + }, + { + "epoch": 0.12, + "learning_rate": 1.9621890478381175e-05, + "loss": 0.5235, + "step": 1377 + }, + { + "epoch": 0.12, + "learning_rate": 1.9621151994396443e-05, + "loss": 0.5125, + "step": 1378 + }, + { + "epoch": 0.12, + "learning_rate": 1.962041280387433e-05, + "loss": 0.5039, + "step": 1379 + }, + { + "epoch": 0.12, + "learning_rate": 1.9619672906869114e-05, + "loss": 0.5263, + "step": 1380 + }, + { + "epoch": 0.12, + "learning_rate": 1.961893230343513e-05, + "loss": 0.5178, + "step": 1381 + }, + { + "epoch": 0.12, + "learning_rate": 1.9618190993626768e-05, + "loss": 0.5091, + "step": 1382 + }, + { + "epoch": 0.12, + "learning_rate": 1.961744897749846e-05, + "loss": 0.5201, + "step": 1383 + }, + { + "epoch": 0.12, + "learning_rate": 1.9616706255104705e-05, + "loss": 0.5166, + "step": 1384 + }, + { + "epoch": 0.12, + "learning_rate": 1.9615962826500038e-05, + "loss": 0.5028, + "step": 1385 + }, + { + "epoch": 0.12, + "learning_rate": 1.961521869173906e-05, + "loss": 0.5015, + "step": 1386 + }, + { + "epoch": 0.12, + "learning_rate": 1.9614473850876413e-05, + "loss": 0.507, + "step": 1387 + }, + { + "epoch": 0.12, + "learning_rate": 1.9613728303966794e-05, + "loss": 0.513, + "step": 1388 + }, + { + "epoch": 0.12, + "learning_rate": 1.961298205106496e-05, + "loss": 0.5002, + "step": 1389 + }, + { + "epoch": 0.12, + "learning_rate": 1.9612235092225704e-05, + "loss": 0.5226, + "step": 1390 + }, + { + "epoch": 0.12, + "learning_rate": 1.9611487427503883e-05, + "loss": 0.4932, + "step": 1391 + }, + { + "epoch": 0.12, + "learning_rate": 1.9610739056954406e-05, + "loss": 0.5077, + "step": 1392 + }, + { + "epoch": 0.12, + "learning_rate": 1.9609989980632222e-05, + "loss": 0.5023, + "step": 1393 + }, + { + "epoch": 0.12, + "learning_rate": 1.9609240198592344e-05, + "loss": 0.52, + "step": 1394 + }, + { + "epoch": 0.12, + "learning_rate": 1.9608489710889837e-05, + "loss": 0.488, + "step": 1395 + }, + { + "epoch": 0.12, + "learning_rate": 1.9607738517579807e-05, + "loss": 0.4979, + "step": 1396 + }, + { + "epoch": 0.12, + "learning_rate": 1.9606986618717428e-05, + "loss": 0.5187, + "step": 1397 + }, + { + "epoch": 0.12, + "learning_rate": 1.9606234014357905e-05, + "loss": 0.5141, + "step": 1398 + }, + { + "epoch": 0.12, + "learning_rate": 1.9605480704556516e-05, + "loss": 0.5124, + "step": 1399 + }, + { + "epoch": 0.12, + "learning_rate": 1.960472668936857e-05, + "loss": 0.4959, + "step": 1400 + }, + { + "epoch": 0.12, + "learning_rate": 1.960397196884945e-05, + "loss": 0.495, + "step": 1401 + }, + { + "epoch": 0.12, + "learning_rate": 1.960321654305457e-05, + "loss": 0.514, + "step": 1402 + }, + { + "epoch": 0.12, + "learning_rate": 1.9602460412039416e-05, + "loss": 0.5115, + "step": 1403 + }, + { + "epoch": 0.12, + "learning_rate": 1.9601703575859504e-05, + "loss": 0.527, + "step": 1404 + }, + { + "epoch": 0.12, + "learning_rate": 1.960094603457042e-05, + "loss": 0.5074, + "step": 1405 + }, + { + "epoch": 0.12, + "learning_rate": 1.960018778822779e-05, + "loss": 0.51, + "step": 1406 + }, + { + "epoch": 0.12, + "learning_rate": 1.9599428836887302e-05, + "loss": 0.5231, + "step": 1407 + }, + { + "epoch": 0.12, + "learning_rate": 1.9598669180604685e-05, + "loss": 0.5108, + "step": 1408 + }, + { + "epoch": 0.12, + "learning_rate": 1.959790881943573e-05, + "loss": 0.5175, + "step": 1409 + }, + { + "epoch": 0.12, + "learning_rate": 1.959714775343627e-05, + "loss": 0.4948, + "step": 1410 + }, + { + "epoch": 0.12, + "learning_rate": 1.9596385982662197e-05, + "loss": 0.5196, + "step": 1411 + }, + { + "epoch": 0.12, + "learning_rate": 1.959562350716945e-05, + "loss": 0.4951, + "step": 1412 + }, + { + "epoch": 0.12, + "learning_rate": 1.959486032701403e-05, + "loss": 0.5001, + "step": 1413 + }, + { + "epoch": 0.12, + "learning_rate": 1.959409644225197e-05, + "loss": 0.5112, + "step": 1414 + }, + { + "epoch": 0.12, + "learning_rate": 1.959333185293937e-05, + "loss": 0.5144, + "step": 1415 + }, + { + "epoch": 0.12, + "learning_rate": 1.9592566559132384e-05, + "loss": 0.5077, + "step": 1416 + }, + { + "epoch": 0.12, + "learning_rate": 1.9591800560887207e-05, + "loss": 0.5186, + "step": 1417 + }, + { + "epoch": 0.12, + "learning_rate": 1.9591033858260094e-05, + "loss": 0.5239, + "step": 1418 + }, + { + "epoch": 0.12, + "learning_rate": 1.9590266451307348e-05, + "loss": 0.5225, + "step": 1419 + }, + { + "epoch": 0.12, + "learning_rate": 1.958949834008532e-05, + "loss": 0.5016, + "step": 1420 + }, + { + "epoch": 0.12, + "learning_rate": 1.958872952465042e-05, + "loss": 0.4952, + "step": 1421 + }, + { + "epoch": 0.12, + "learning_rate": 1.9587960005059104e-05, + "loss": 0.4957, + "step": 1422 + }, + { + "epoch": 0.12, + "learning_rate": 1.9587189781367888e-05, + "loss": 0.5117, + "step": 1423 + }, + { + "epoch": 0.12, + "learning_rate": 1.958641885363333e-05, + "loss": 0.5254, + "step": 1424 + }, + { + "epoch": 0.12, + "learning_rate": 1.9585647221912044e-05, + "loss": 0.5041, + "step": 1425 + }, + { + "epoch": 0.12, + "learning_rate": 1.9584874886260695e-05, + "loss": 0.4954, + "step": 1426 + }, + { + "epoch": 0.12, + "learning_rate": 1.9584101846736002e-05, + "loss": 0.5099, + "step": 1427 + }, + { + "epoch": 0.12, + "learning_rate": 1.9583328103394733e-05, + "loss": 0.5261, + "step": 1428 + }, + { + "epoch": 0.12, + "learning_rate": 1.9582553656293707e-05, + "loss": 0.4948, + "step": 1429 + }, + { + "epoch": 0.12, + "learning_rate": 1.9581778505489797e-05, + "loss": 0.5298, + "step": 1430 + }, + { + "epoch": 0.12, + "learning_rate": 1.9581002651039928e-05, + "loss": 0.5066, + "step": 1431 + }, + { + "epoch": 0.12, + "learning_rate": 1.9580226093001077e-05, + "loss": 0.5078, + "step": 1432 + }, + { + "epoch": 0.12, + "learning_rate": 1.9579448831430264e-05, + "loss": 0.5214, + "step": 1433 + }, + { + "epoch": 0.12, + "learning_rate": 1.9578670866384574e-05, + "loss": 0.5257, + "step": 1434 + }, + { + "epoch": 0.12, + "learning_rate": 1.9577892197921136e-05, + "loss": 0.5086, + "step": 1435 + }, + { + "epoch": 0.12, + "learning_rate": 1.9577112826097134e-05, + "loss": 0.5219, + "step": 1436 + }, + { + "epoch": 0.12, + "learning_rate": 1.95763327509698e-05, + "loss": 0.509, + "step": 1437 + }, + { + "epoch": 0.12, + "learning_rate": 1.9575551972596422e-05, + "loss": 0.5082, + "step": 1438 + }, + { + "epoch": 0.12, + "learning_rate": 1.9574770491034333e-05, + "loss": 0.5165, + "step": 1439 + }, + { + "epoch": 0.12, + "learning_rate": 1.9573988306340924e-05, + "loss": 0.5104, + "step": 1440 + }, + { + "epoch": 0.12, + "learning_rate": 1.9573205418573634e-05, + "loss": 0.5131, + "step": 1441 + }, + { + "epoch": 0.12, + "learning_rate": 1.9572421827789954e-05, + "loss": 0.5001, + "step": 1442 + }, + { + "epoch": 0.12, + "learning_rate": 1.957163753404743e-05, + "loss": 0.5068, + "step": 1443 + }, + { + "epoch": 0.12, + "learning_rate": 1.957085253740366e-05, + "loss": 0.5094, + "step": 1444 + }, + { + "epoch": 0.12, + "learning_rate": 1.9570066837916285e-05, + "loss": 0.504, + "step": 1445 + }, + { + "epoch": 0.12, + "learning_rate": 1.956928043564301e-05, + "loss": 0.5258, + "step": 1446 + }, + { + "epoch": 0.12, + "learning_rate": 1.956849333064158e-05, + "loss": 0.5101, + "step": 1447 + }, + { + "epoch": 0.12, + "learning_rate": 1.9567705522969796e-05, + "loss": 0.5094, + "step": 1448 + }, + { + "epoch": 0.12, + "learning_rate": 1.9566917012685515e-05, + "loss": 0.5293, + "step": 1449 + }, + { + "epoch": 0.12, + "learning_rate": 1.9566127799846642e-05, + "loss": 0.515, + "step": 1450 + }, + { + "epoch": 0.12, + "learning_rate": 1.9565337884511128e-05, + "loss": 0.4926, + "step": 1451 + }, + { + "epoch": 0.12, + "learning_rate": 1.956454726673699e-05, + "loss": 0.5152, + "step": 1452 + }, + { + "epoch": 0.12, + "learning_rate": 1.9563755946582277e-05, + "loss": 0.5183, + "step": 1453 + }, + { + "epoch": 0.12, + "learning_rate": 1.956296392410511e-05, + "loss": 0.5313, + "step": 1454 + }, + { + "epoch": 0.12, + "learning_rate": 1.9562171199363646e-05, + "loss": 0.4952, + "step": 1455 + }, + { + "epoch": 0.12, + "learning_rate": 1.9561377772416103e-05, + "loss": 0.5244, + "step": 1456 + }, + { + "epoch": 0.12, + "learning_rate": 1.9560583643320745e-05, + "loss": 0.5044, + "step": 1457 + }, + { + "epoch": 0.12, + "learning_rate": 1.955978881213589e-05, + "loss": 0.5245, + "step": 1458 + }, + { + "epoch": 0.12, + "learning_rate": 1.9558993278919904e-05, + "loss": 0.5117, + "step": 1459 + }, + { + "epoch": 0.12, + "learning_rate": 1.9558197043731214e-05, + "loss": 0.4932, + "step": 1460 + }, + { + "epoch": 0.12, + "learning_rate": 1.9557400106628285e-05, + "loss": 0.4863, + "step": 1461 + }, + { + "epoch": 0.12, + "learning_rate": 1.9556602467669645e-05, + "loss": 0.5167, + "step": 1462 + }, + { + "epoch": 0.12, + "learning_rate": 1.9555804126913868e-05, + "loss": 0.5063, + "step": 1463 + }, + { + "epoch": 0.12, + "learning_rate": 1.9555005084419585e-05, + "loss": 0.5097, + "step": 1464 + }, + { + "epoch": 0.12, + "learning_rate": 1.9554205340245468e-05, + "loss": 0.5213, + "step": 1465 + }, + { + "epoch": 0.12, + "learning_rate": 1.955340489445025e-05, + "loss": 0.4985, + "step": 1466 + }, + { + "epoch": 0.12, + "learning_rate": 1.9552603747092714e-05, + "loss": 0.5026, + "step": 1467 + }, + { + "epoch": 0.12, + "learning_rate": 1.9551801898231692e-05, + "loss": 0.506, + "step": 1468 + }, + { + "epoch": 0.12, + "learning_rate": 1.9550999347926064e-05, + "loss": 0.5001, + "step": 1469 + }, + { + "epoch": 0.12, + "learning_rate": 1.955019609623477e-05, + "loss": 0.5154, + "step": 1470 + }, + { + "epoch": 0.12, + "learning_rate": 1.95493921432168e-05, + "loss": 0.5028, + "step": 1471 + }, + { + "epoch": 0.12, + "learning_rate": 1.9548587488931187e-05, + "loss": 0.5032, + "step": 1472 + }, + { + "epoch": 0.12, + "learning_rate": 1.9547782133437024e-05, + "loss": 0.508, + "step": 1473 + }, + { + "epoch": 0.12, + "learning_rate": 1.9546976076793456e-05, + "loss": 0.5321, + "step": 1474 + }, + { + "epoch": 0.12, + "learning_rate": 1.954616931905967e-05, + "loss": 0.4916, + "step": 1475 + }, + { + "epoch": 0.12, + "learning_rate": 1.954536186029492e-05, + "loss": 0.4889, + "step": 1476 + }, + { + "epoch": 0.12, + "learning_rate": 1.954455370055849e-05, + "loss": 0.5233, + "step": 1477 + }, + { + "epoch": 0.12, + "learning_rate": 1.9543744839909743e-05, + "loss": 0.4962, + "step": 1478 + }, + { + "epoch": 0.12, + "learning_rate": 1.9542935278408066e-05, + "loss": 0.4988, + "step": 1479 + }, + { + "epoch": 0.12, + "learning_rate": 1.9542125016112913e-05, + "loss": 0.5181, + "step": 1480 + }, + { + "epoch": 0.12, + "learning_rate": 1.954131405308379e-05, + "loss": 0.5045, + "step": 1481 + }, + { + "epoch": 0.12, + "learning_rate": 1.9540502389380245e-05, + "loss": 0.5008, + "step": 1482 + }, + { + "epoch": 0.12, + "learning_rate": 1.953969002506189e-05, + "loss": 0.522, + "step": 1483 + }, + { + "epoch": 0.12, + "learning_rate": 1.9538876960188378e-05, + "loss": 0.5198, + "step": 1484 + }, + { + "epoch": 0.12, + "learning_rate": 1.9538063194819418e-05, + "loss": 0.5029, + "step": 1485 + }, + { + "epoch": 0.12, + "learning_rate": 1.9537248729014767e-05, + "loss": 0.5282, + "step": 1486 + }, + { + "epoch": 0.12, + "learning_rate": 1.9536433562834235e-05, + "loss": 0.5243, + "step": 1487 + }, + { + "epoch": 0.12, + "learning_rate": 1.953561769633769e-05, + "loss": 0.5025, + "step": 1488 + }, + { + "epoch": 0.12, + "learning_rate": 1.9534801129585044e-05, + "loss": 0.5192, + "step": 1489 + }, + { + "epoch": 0.12, + "learning_rate": 1.953398386263626e-05, + "loss": 0.4863, + "step": 1490 + }, + { + "epoch": 0.12, + "learning_rate": 1.9533165895551356e-05, + "loss": 0.5097, + "step": 1491 + }, + { + "epoch": 0.12, + "learning_rate": 1.95323472283904e-05, + "loss": 0.5092, + "step": 1492 + }, + { + "epoch": 0.12, + "learning_rate": 1.9531527861213514e-05, + "loss": 0.5021, + "step": 1493 + }, + { + "epoch": 0.12, + "learning_rate": 1.9530707794080864e-05, + "loss": 0.5236, + "step": 1494 + }, + { + "epoch": 0.13, + "learning_rate": 1.9529887027052676e-05, + "loss": 0.5116, + "step": 1495 + }, + { + "epoch": 0.13, + "learning_rate": 1.952906556018922e-05, + "loss": 0.5081, + "step": 1496 + }, + { + "epoch": 0.13, + "learning_rate": 1.9528243393550825e-05, + "loss": 0.4812, + "step": 1497 + }, + { + "epoch": 0.13, + "learning_rate": 1.9527420527197867e-05, + "loss": 0.5272, + "step": 1498 + }, + { + "epoch": 0.13, + "learning_rate": 1.9526596961190772e-05, + "loss": 0.4959, + "step": 1499 + }, + { + "epoch": 0.13, + "learning_rate": 1.952577269559002e-05, + "loss": 0.5129, + "step": 1500 + }, + { + "epoch": 0.13, + "learning_rate": 1.952494773045614e-05, + "loss": 0.5061, + "step": 1501 + }, + { + "epoch": 0.13, + "learning_rate": 1.9524122065849722e-05, + "loss": 0.5036, + "step": 1502 + }, + { + "epoch": 0.13, + "learning_rate": 1.9523295701831388e-05, + "loss": 0.5044, + "step": 1503 + }, + { + "epoch": 0.13, + "learning_rate": 1.952246863846183e-05, + "loss": 0.516, + "step": 1504 + }, + { + "epoch": 0.13, + "learning_rate": 1.9521640875801783e-05, + "loss": 0.5064, + "step": 1505 + }, + { + "epoch": 0.13, + "learning_rate": 1.9520812413912032e-05, + "loss": 0.5003, + "step": 1506 + }, + { + "epoch": 0.13, + "learning_rate": 1.9519983252853415e-05, + "loss": 0.5019, + "step": 1507 + }, + { + "epoch": 0.13, + "learning_rate": 1.9519153392686828e-05, + "loss": 0.5233, + "step": 1508 + }, + { + "epoch": 0.13, + "learning_rate": 1.951832283347321e-05, + "loss": 0.516, + "step": 1509 + }, + { + "epoch": 0.13, + "learning_rate": 1.9517491575273552e-05, + "loss": 0.5068, + "step": 1510 + }, + { + "epoch": 0.13, + "learning_rate": 1.9516659618148897e-05, + "loss": 0.5093, + "step": 1511 + }, + { + "epoch": 0.13, + "learning_rate": 1.9515826962160342e-05, + "loss": 0.5433, + "step": 1512 + }, + { + "epoch": 0.13, + "learning_rate": 1.9514993607369037e-05, + "loss": 0.4968, + "step": 1513 + }, + { + "epoch": 0.13, + "learning_rate": 1.9514159553836177e-05, + "loss": 0.5295, + "step": 1514 + }, + { + "epoch": 0.13, + "learning_rate": 1.951332480162301e-05, + "loss": 0.5024, + "step": 1515 + }, + { + "epoch": 0.13, + "learning_rate": 1.9512489350790838e-05, + "loss": 0.4909, + "step": 1516 + }, + { + "epoch": 0.13, + "learning_rate": 1.9511653201401012e-05, + "loss": 0.5222, + "step": 1517 + }, + { + "epoch": 0.13, + "learning_rate": 1.951081635351494e-05, + "loss": 0.538, + "step": 1518 + }, + { + "epoch": 0.13, + "learning_rate": 1.9509978807194075e-05, + "loss": 0.5152, + "step": 1519 + }, + { + "epoch": 0.13, + "learning_rate": 1.950914056249992e-05, + "loss": 0.5195, + "step": 1520 + }, + { + "epoch": 0.13, + "learning_rate": 1.9508301619494033e-05, + "loss": 0.496, + "step": 1521 + }, + { + "epoch": 0.13, + "learning_rate": 1.950746197823802e-05, + "loss": 0.5049, + "step": 1522 + }, + { + "epoch": 0.13, + "learning_rate": 1.9506621638793548e-05, + "loss": 0.4945, + "step": 1523 + }, + { + "epoch": 0.13, + "learning_rate": 1.9505780601222323e-05, + "loss": 0.5202, + "step": 1524 + }, + { + "epoch": 0.13, + "learning_rate": 1.9504938865586107e-05, + "loss": 0.523, + "step": 1525 + }, + { + "epoch": 0.13, + "learning_rate": 1.9504096431946716e-05, + "loss": 0.522, + "step": 1526 + }, + { + "epoch": 0.13, + "learning_rate": 1.9503253300366013e-05, + "loss": 0.49, + "step": 1527 + }, + { + "epoch": 0.13, + "learning_rate": 1.9502409470905913e-05, + "loss": 0.5066, + "step": 1528 + }, + { + "epoch": 0.13, + "learning_rate": 1.950156494362839e-05, + "loss": 0.4991, + "step": 1529 + }, + { + "epoch": 0.13, + "learning_rate": 1.9500719718595454e-05, + "loss": 0.4954, + "step": 1530 + }, + { + "epoch": 0.13, + "learning_rate": 1.9499873795869178e-05, + "loss": 0.5012, + "step": 1531 + }, + { + "epoch": 0.13, + "learning_rate": 1.9499027175511682e-05, + "loss": 0.4998, + "step": 1532 + }, + { + "epoch": 0.13, + "learning_rate": 1.9498179857585143e-05, + "loss": 0.5168, + "step": 1533 + }, + { + "epoch": 0.13, + "learning_rate": 1.949733184215178e-05, + "loss": 0.5179, + "step": 1534 + }, + { + "epoch": 0.13, + "learning_rate": 1.9496483129273866e-05, + "loss": 0.5061, + "step": 1535 + }, + { + "epoch": 0.13, + "learning_rate": 1.9495633719013733e-05, + "loss": 0.527, + "step": 1536 + }, + { + "epoch": 0.13, + "learning_rate": 1.9494783611433754e-05, + "loss": 0.506, + "step": 1537 + }, + { + "epoch": 0.13, + "learning_rate": 1.9493932806596357e-05, + "loss": 0.5057, + "step": 1538 + }, + { + "epoch": 0.13, + "learning_rate": 1.9493081304564025e-05, + "loss": 0.5144, + "step": 1539 + }, + { + "epoch": 0.13, + "learning_rate": 1.9492229105399287e-05, + "loss": 0.518, + "step": 1540 + }, + { + "epoch": 0.13, + "learning_rate": 1.9491376209164726e-05, + "loss": 0.526, + "step": 1541 + }, + { + "epoch": 0.13, + "learning_rate": 1.949052261592297e-05, + "loss": 0.5012, + "step": 1542 + }, + { + "epoch": 0.13, + "learning_rate": 1.948966832573671e-05, + "loss": 0.5005, + "step": 1543 + }, + { + "epoch": 0.13, + "learning_rate": 1.9488813338668676e-05, + "loss": 0.5124, + "step": 1544 + }, + { + "epoch": 0.13, + "learning_rate": 1.948795765478166e-05, + "loss": 0.5017, + "step": 1545 + }, + { + "epoch": 0.13, + "learning_rate": 1.9487101274138494e-05, + "loss": 0.5069, + "step": 1546 + }, + { + "epoch": 0.13, + "learning_rate": 1.9486244196802075e-05, + "loss": 0.4965, + "step": 1547 + }, + { + "epoch": 0.13, + "learning_rate": 1.9485386422835334e-05, + "loss": 0.5156, + "step": 1548 + }, + { + "epoch": 0.13, + "learning_rate": 1.948452795230127e-05, + "loss": 0.5098, + "step": 1549 + }, + { + "epoch": 0.13, + "learning_rate": 1.948366878526292e-05, + "loss": 0.5146, + "step": 1550 + }, + { + "epoch": 0.13, + "learning_rate": 1.948280892178338e-05, + "loss": 0.4822, + "step": 1551 + }, + { + "epoch": 0.13, + "learning_rate": 1.9481948361925796e-05, + "loss": 0.52, + "step": 1552 + }, + { + "epoch": 0.13, + "learning_rate": 1.9481087105753364e-05, + "loss": 0.5043, + "step": 1553 + }, + { + "epoch": 0.13, + "learning_rate": 1.948022515332933e-05, + "loss": 0.4827, + "step": 1554 + }, + { + "epoch": 0.13, + "learning_rate": 1.9479362504716987e-05, + "loss": 0.5335, + "step": 1555 + }, + { + "epoch": 0.13, + "learning_rate": 1.9478499159979693e-05, + "loss": 0.5135, + "step": 1556 + }, + { + "epoch": 0.13, + "learning_rate": 1.9477635119180843e-05, + "loss": 0.5032, + "step": 1557 + }, + { + "epoch": 0.13, + "learning_rate": 1.947677038238389e-05, + "loss": 0.5122, + "step": 1558 + }, + { + "epoch": 0.13, + "learning_rate": 1.947590494965234e-05, + "loss": 0.5083, + "step": 1559 + }, + { + "epoch": 0.13, + "learning_rate": 1.9475038821049744e-05, + "loss": 0.5332, + "step": 1560 + }, + { + "epoch": 0.13, + "learning_rate": 1.9474171996639702e-05, + "loss": 0.4818, + "step": 1561 + }, + { + "epoch": 0.13, + "learning_rate": 1.947330447648588e-05, + "loss": 0.5206, + "step": 1562 + }, + { + "epoch": 0.13, + "learning_rate": 1.9472436260651976e-05, + "loss": 0.5059, + "step": 1563 + }, + { + "epoch": 0.13, + "learning_rate": 1.947156734920175e-05, + "loss": 0.5188, + "step": 1564 + }, + { + "epoch": 0.13, + "learning_rate": 1.9470697742199018e-05, + "loss": 0.5141, + "step": 1565 + }, + { + "epoch": 0.13, + "learning_rate": 1.9469827439707632e-05, + "loss": 0.505, + "step": 1566 + }, + { + "epoch": 0.13, + "learning_rate": 1.946895644179151e-05, + "loss": 0.5005, + "step": 1567 + }, + { + "epoch": 0.13, + "learning_rate": 1.946808474851461e-05, + "loss": 0.5152, + "step": 1568 + }, + { + "epoch": 0.13, + "learning_rate": 1.9467212359940944e-05, + "loss": 0.5156, + "step": 1569 + }, + { + "epoch": 0.13, + "learning_rate": 1.9466339276134584e-05, + "loss": 0.5007, + "step": 1570 + }, + { + "epoch": 0.13, + "learning_rate": 1.946546549715964e-05, + "loss": 0.514, + "step": 1571 + }, + { + "epoch": 0.13, + "learning_rate": 1.9464591023080274e-05, + "loss": 0.5101, + "step": 1572 + }, + { + "epoch": 0.13, + "learning_rate": 1.9463715853960714e-05, + "loss": 0.5019, + "step": 1573 + }, + { + "epoch": 0.13, + "learning_rate": 1.9462839989865226e-05, + "loss": 0.5165, + "step": 1574 + }, + { + "epoch": 0.13, + "learning_rate": 1.9461963430858125e-05, + "loss": 0.5078, + "step": 1575 + }, + { + "epoch": 0.13, + "learning_rate": 1.9461086177003788e-05, + "loss": 0.5235, + "step": 1576 + }, + { + "epoch": 0.13, + "learning_rate": 1.946020822836663e-05, + "loss": 0.4954, + "step": 1577 + }, + { + "epoch": 0.13, + "learning_rate": 1.945932958501113e-05, + "loss": 0.5357, + "step": 1578 + }, + { + "epoch": 0.13, + "learning_rate": 1.945845024700181e-05, + "loss": 0.4957, + "step": 1579 + }, + { + "epoch": 0.13, + "learning_rate": 1.9457570214403242e-05, + "loss": 0.5249, + "step": 1580 + }, + { + "epoch": 0.13, + "learning_rate": 1.9456689487280056e-05, + "loss": 0.5397, + "step": 1581 + }, + { + "epoch": 0.13, + "learning_rate": 1.9455808065696925e-05, + "loss": 0.5026, + "step": 1582 + }, + { + "epoch": 0.13, + "learning_rate": 1.9454925949718583e-05, + "loss": 0.4986, + "step": 1583 + }, + { + "epoch": 0.13, + "learning_rate": 1.9454043139409803e-05, + "loss": 0.5172, + "step": 1584 + }, + { + "epoch": 0.13, + "learning_rate": 1.945315963483542e-05, + "loss": 0.5243, + "step": 1585 + }, + { + "epoch": 0.13, + "learning_rate": 1.945227543606031e-05, + "loss": 0.4918, + "step": 1586 + }, + { + "epoch": 0.13, + "learning_rate": 1.945139054314941e-05, + "loss": 0.5084, + "step": 1587 + }, + { + "epoch": 0.13, + "learning_rate": 1.945050495616769e-05, + "loss": 0.5445, + "step": 1588 + }, + { + "epoch": 0.13, + "learning_rate": 1.9449618675180205e-05, + "loss": 0.5013, + "step": 1589 + }, + { + "epoch": 0.13, + "learning_rate": 1.9448731700252025e-05, + "loss": 0.5026, + "step": 1590 + }, + { + "epoch": 0.13, + "learning_rate": 1.9447844031448288e-05, + "loss": 0.5368, + "step": 1591 + }, + { + "epoch": 0.13, + "learning_rate": 1.944695566883418e-05, + "loss": 0.5089, + "step": 1592 + }, + { + "epoch": 0.13, + "learning_rate": 1.9446066612474942e-05, + "loss": 0.4996, + "step": 1593 + }, + { + "epoch": 0.13, + "learning_rate": 1.9445176862435864e-05, + "loss": 0.5315, + "step": 1594 + }, + { + "epoch": 0.13, + "learning_rate": 1.944428641878228e-05, + "loss": 0.4945, + "step": 1595 + }, + { + "epoch": 0.13, + "learning_rate": 1.9443395281579583e-05, + "loss": 0.5109, + "step": 1596 + }, + { + "epoch": 0.13, + "learning_rate": 1.9442503450893216e-05, + "loss": 0.4996, + "step": 1597 + }, + { + "epoch": 0.13, + "learning_rate": 1.944161092678867e-05, + "loss": 0.4923, + "step": 1598 + }, + { + "epoch": 0.13, + "learning_rate": 1.9440717709331484e-05, + "loss": 0.5056, + "step": 1599 + }, + { + "epoch": 0.13, + "learning_rate": 1.943982379858726e-05, + "loss": 0.5007, + "step": 1600 + }, + { + "epoch": 0.13, + "learning_rate": 1.943892919462164e-05, + "loss": 0.498, + "step": 1601 + }, + { + "epoch": 0.13, + "learning_rate": 1.943803389750032e-05, + "loss": 0.5099, + "step": 1602 + }, + { + "epoch": 0.13, + "learning_rate": 1.943713790728904e-05, + "loss": 0.5205, + "step": 1603 + }, + { + "epoch": 0.13, + "learning_rate": 1.943624122405361e-05, + "loss": 0.5158, + "step": 1604 + }, + { + "epoch": 0.13, + "learning_rate": 1.9435343847859873e-05, + "loss": 0.5149, + "step": 1605 + }, + { + "epoch": 0.13, + "learning_rate": 1.9434445778773724e-05, + "loss": 0.5091, + "step": 1606 + }, + { + "epoch": 0.13, + "learning_rate": 1.9433547016861124e-05, + "loss": 0.5026, + "step": 1607 + }, + { + "epoch": 0.13, + "learning_rate": 1.9432647562188062e-05, + "loss": 0.502, + "step": 1608 + }, + { + "epoch": 0.13, + "learning_rate": 1.9431747414820597e-05, + "loss": 0.4999, + "step": 1609 + }, + { + "epoch": 0.13, + "learning_rate": 1.9430846574824835e-05, + "loss": 0.5014, + "step": 1610 + }, + { + "epoch": 0.13, + "learning_rate": 1.9429945042266925e-05, + "loss": 0.4999, + "step": 1611 + }, + { + "epoch": 0.13, + "learning_rate": 1.9429042817213072e-05, + "loss": 0.5387, + "step": 1612 + }, + { + "epoch": 0.13, + "learning_rate": 1.9428139899729538e-05, + "loss": 0.5215, + "step": 1613 + }, + { + "epoch": 0.14, + "learning_rate": 1.9427236289882618e-05, + "loss": 0.49, + "step": 1614 + }, + { + "epoch": 0.14, + "learning_rate": 1.9426331987738678e-05, + "loss": 0.5053, + "step": 1615 + }, + { + "epoch": 0.14, + "learning_rate": 1.9425426993364126e-05, + "loss": 0.5108, + "step": 1616 + }, + { + "epoch": 0.14, + "learning_rate": 1.9424521306825414e-05, + "loss": 0.5044, + "step": 1617 + }, + { + "epoch": 0.14, + "learning_rate": 1.942361492818906e-05, + "loss": 0.5024, + "step": 1618 + }, + { + "epoch": 0.14, + "learning_rate": 1.942270785752162e-05, + "loss": 0.5122, + "step": 1619 + }, + { + "epoch": 0.14, + "learning_rate": 1.942180009488971e-05, + "loss": 0.4883, + "step": 1620 + }, + { + "epoch": 0.14, + "learning_rate": 1.9420891640359986e-05, + "loss": 0.5229, + "step": 1621 + }, + { + "epoch": 0.14, + "learning_rate": 1.9419982493999164e-05, + "loss": 0.5099, + "step": 1622 + }, + { + "epoch": 0.14, + "learning_rate": 1.941907265587401e-05, + "loss": 0.506, + "step": 1623 + }, + { + "epoch": 0.14, + "learning_rate": 1.941816212605134e-05, + "loss": 0.5054, + "step": 1624 + }, + { + "epoch": 0.14, + "learning_rate": 1.9417250904598012e-05, + "loss": 0.5049, + "step": 1625 + }, + { + "epoch": 0.14, + "learning_rate": 1.941633899158095e-05, + "loss": 0.4866, + "step": 1626 + }, + { + "epoch": 0.14, + "learning_rate": 1.9415426387067113e-05, + "loss": 0.5025, + "step": 1627 + }, + { + "epoch": 0.14, + "learning_rate": 1.9414513091123527e-05, + "loss": 0.4994, + "step": 1628 + }, + { + "epoch": 0.14, + "learning_rate": 1.941359910381726e-05, + "loss": 0.4944, + "step": 1629 + }, + { + "epoch": 0.14, + "learning_rate": 1.9412684425215426e-05, + "loss": 0.4999, + "step": 1630 + }, + { + "epoch": 0.14, + "learning_rate": 1.94117690553852e-05, + "loss": 0.5114, + "step": 1631 + }, + { + "epoch": 0.14, + "learning_rate": 1.94108529943938e-05, + "loss": 0.5099, + "step": 1632 + }, + { + "epoch": 0.14, + "learning_rate": 1.9409936242308496e-05, + "loss": 0.4935, + "step": 1633 + }, + { + "epoch": 0.14, + "learning_rate": 1.9409018799196615e-05, + "loss": 0.5183, + "step": 1634 + }, + { + "epoch": 0.14, + "learning_rate": 1.940810066512553e-05, + "loss": 0.5118, + "step": 1635 + }, + { + "epoch": 0.14, + "learning_rate": 1.9407181840162664e-05, + "loss": 0.4947, + "step": 1636 + }, + { + "epoch": 0.14, + "learning_rate": 1.940626232437549e-05, + "loss": 0.4854, + "step": 1637 + }, + { + "epoch": 0.14, + "learning_rate": 1.9405342117831533e-05, + "loss": 0.5058, + "step": 1638 + }, + { + "epoch": 0.14, + "learning_rate": 1.940442122059837e-05, + "loss": 0.5044, + "step": 1639 + }, + { + "epoch": 0.14, + "learning_rate": 1.940349963274363e-05, + "loss": 0.5109, + "step": 1640 + }, + { + "epoch": 0.14, + "learning_rate": 1.940257735433499e-05, + "loss": 0.5157, + "step": 1641 + }, + { + "epoch": 0.14, + "learning_rate": 1.9401654385440176e-05, + "loss": 0.5039, + "step": 1642 + }, + { + "epoch": 0.14, + "learning_rate": 1.9400730726126967e-05, + "loss": 0.5233, + "step": 1643 + }, + { + "epoch": 0.14, + "learning_rate": 1.9399806376463197e-05, + "loss": 0.5069, + "step": 1644 + }, + { + "epoch": 0.14, + "learning_rate": 1.9398881336516743e-05, + "loss": 0.4975, + "step": 1645 + }, + { + "epoch": 0.14, + "learning_rate": 1.9397955606355535e-05, + "loss": 0.4895, + "step": 1646 + }, + { + "epoch": 0.14, + "learning_rate": 1.939702918604756e-05, + "loss": 0.5138, + "step": 1647 + }, + { + "epoch": 0.14, + "learning_rate": 1.939610207566084e-05, + "loss": 0.5043, + "step": 1648 + }, + { + "epoch": 0.14, + "learning_rate": 1.9395174275263474e-05, + "loss": 0.5129, + "step": 1649 + }, + { + "epoch": 0.14, + "learning_rate": 1.939424578492358e-05, + "loss": 0.5204, + "step": 1650 + }, + { + "epoch": 0.14, + "learning_rate": 1.939331660470935e-05, + "loss": 0.5179, + "step": 1651 + }, + { + "epoch": 0.14, + "learning_rate": 1.939238673468902e-05, + "loss": 0.4908, + "step": 1652 + }, + { + "epoch": 0.14, + "learning_rate": 1.9391456174930872e-05, + "loss": 0.5208, + "step": 1653 + }, + { + "epoch": 0.14, + "learning_rate": 1.9390524925503244e-05, + "loss": 0.5036, + "step": 1654 + }, + { + "epoch": 0.14, + "learning_rate": 1.938959298647453e-05, + "loss": 0.5021, + "step": 1655 + }, + { + "epoch": 0.14, + "learning_rate": 1.9388660357913155e-05, + "loss": 0.4836, + "step": 1656 + }, + { + "epoch": 0.14, + "learning_rate": 1.9387727039887613e-05, + "loss": 0.5131, + "step": 1657 + }, + { + "epoch": 0.14, + "learning_rate": 1.9386793032466447e-05, + "loss": 0.4923, + "step": 1658 + }, + { + "epoch": 0.14, + "learning_rate": 1.938585833571824e-05, + "loss": 0.4989, + "step": 1659 + }, + { + "epoch": 0.14, + "learning_rate": 1.938492294971164e-05, + "loss": 0.4997, + "step": 1660 + }, + { + "epoch": 0.14, + "learning_rate": 1.938398687451533e-05, + "loss": 0.5122, + "step": 1661 + }, + { + "epoch": 0.14, + "learning_rate": 1.938305011019806e-05, + "loss": 0.5224, + "step": 1662 + }, + { + "epoch": 0.14, + "learning_rate": 1.938211265682861e-05, + "loss": 0.5035, + "step": 1663 + }, + { + "epoch": 0.14, + "learning_rate": 1.938117451447583e-05, + "loss": 0.4923, + "step": 1664 + }, + { + "epoch": 0.14, + "learning_rate": 1.938023568320862e-05, + "loss": 0.4831, + "step": 1665 + }, + { + "epoch": 0.14, + "learning_rate": 1.937929616309591e-05, + "loss": 0.5233, + "step": 1666 + }, + { + "epoch": 0.14, + "learning_rate": 1.9378355954206706e-05, + "loss": 0.4931, + "step": 1667 + }, + { + "epoch": 0.14, + "learning_rate": 1.9377415056610044e-05, + "loss": 0.5169, + "step": 1668 + }, + { + "epoch": 0.14, + "learning_rate": 1.9376473470375027e-05, + "loss": 0.5293, + "step": 1669 + }, + { + "epoch": 0.14, + "learning_rate": 1.9375531195570793e-05, + "loss": 0.4901, + "step": 1670 + }, + { + "epoch": 0.14, + "learning_rate": 1.937458823226655e-05, + "loss": 0.494, + "step": 1671 + }, + { + "epoch": 0.14, + "learning_rate": 1.9373644580531538e-05, + "loss": 0.4901, + "step": 1672 + }, + { + "epoch": 0.14, + "learning_rate": 1.9372700240435054e-05, + "loss": 0.4935, + "step": 1673 + }, + { + "epoch": 0.14, + "learning_rate": 1.9371755212046448e-05, + "loss": 0.5092, + "step": 1674 + }, + { + "epoch": 0.14, + "learning_rate": 1.937080949543512e-05, + "loss": 0.5221, + "step": 1675 + }, + { + "epoch": 0.14, + "learning_rate": 1.9369863090670518e-05, + "loss": 0.5167, + "step": 1676 + }, + { + "epoch": 0.14, + "learning_rate": 1.9368915997822143e-05, + "loss": 0.4965, + "step": 1677 + }, + { + "epoch": 0.14, + "learning_rate": 1.936796821695955e-05, + "loss": 0.5117, + "step": 1678 + }, + { + "epoch": 0.14, + "learning_rate": 1.9367019748152328e-05, + "loss": 0.4949, + "step": 1679 + }, + { + "epoch": 0.14, + "learning_rate": 1.936607059147014e-05, + "loss": 0.4979, + "step": 1680 + }, + { + "epoch": 0.14, + "learning_rate": 1.9365120746982683e-05, + "loss": 0.5053, + "step": 1681 + }, + { + "epoch": 0.14, + "learning_rate": 1.936417021475971e-05, + "loss": 0.5028, + "step": 1682 + }, + { + "epoch": 0.14, + "learning_rate": 1.9363218994871026e-05, + "loss": 0.4857, + "step": 1683 + }, + { + "epoch": 0.14, + "learning_rate": 1.9362267087386487e-05, + "loss": 0.5216, + "step": 1684 + }, + { + "epoch": 0.14, + "learning_rate": 1.936131449237599e-05, + "loss": 0.5015, + "step": 1685 + }, + { + "epoch": 0.14, + "learning_rate": 1.9360361209909494e-05, + "loss": 0.513, + "step": 1686 + }, + { + "epoch": 0.14, + "learning_rate": 1.9359407240057003e-05, + "loss": 0.4847, + "step": 1687 + }, + { + "epoch": 0.14, + "learning_rate": 1.9358452582888575e-05, + "loss": 0.5185, + "step": 1688 + }, + { + "epoch": 0.14, + "learning_rate": 1.935749723847431e-05, + "loss": 0.4861, + "step": 1689 + }, + { + "epoch": 0.14, + "learning_rate": 1.935654120688437e-05, + "loss": 0.5161, + "step": 1690 + }, + { + "epoch": 0.14, + "learning_rate": 1.9355584488188965e-05, + "loss": 0.4871, + "step": 1691 + }, + { + "epoch": 0.14, + "learning_rate": 1.9354627082458342e-05, + "loss": 0.525, + "step": 1692 + }, + { + "epoch": 0.14, + "learning_rate": 1.9353668989762817e-05, + "loss": 0.504, + "step": 1693 + }, + { + "epoch": 0.14, + "learning_rate": 1.935271021017275e-05, + "loss": 0.4978, + "step": 1694 + }, + { + "epoch": 0.14, + "learning_rate": 1.9351750743758543e-05, + "loss": 0.5007, + "step": 1695 + }, + { + "epoch": 0.14, + "learning_rate": 1.9350790590590657e-05, + "loss": 0.5096, + "step": 1696 + }, + { + "epoch": 0.14, + "learning_rate": 1.93498297507396e-05, + "loss": 0.5025, + "step": 1697 + }, + { + "epoch": 0.14, + "learning_rate": 1.9348868224275943e-05, + "loss": 0.5048, + "step": 1698 + }, + { + "epoch": 0.14, + "learning_rate": 1.9347906011270283e-05, + "loss": 0.5047, + "step": 1699 + }, + { + "epoch": 0.14, + "learning_rate": 1.9346943111793286e-05, + "loss": 0.512, + "step": 1700 + }, + { + "epoch": 0.14, + "learning_rate": 1.934597952591567e-05, + "loss": 0.5133, + "step": 1701 + }, + { + "epoch": 0.14, + "learning_rate": 1.934501525370818e-05, + "loss": 0.4905, + "step": 1702 + }, + { + "epoch": 0.14, + "learning_rate": 1.9344050295241648e-05, + "loss": 0.4937, + "step": 1703 + }, + { + "epoch": 0.14, + "learning_rate": 1.9343084650586922e-05, + "loss": 0.5147, + "step": 1704 + }, + { + "epoch": 0.14, + "learning_rate": 1.9342118319814923e-05, + "loss": 0.4967, + "step": 1705 + }, + { + "epoch": 0.14, + "learning_rate": 1.934115130299661e-05, + "loss": 0.5341, + "step": 1706 + }, + { + "epoch": 0.14, + "learning_rate": 1.9340183600202998e-05, + "loss": 0.4955, + "step": 1707 + }, + { + "epoch": 0.14, + "learning_rate": 1.933921521150515e-05, + "loss": 0.4864, + "step": 1708 + }, + { + "epoch": 0.14, + "learning_rate": 1.9338246136974182e-05, + "loss": 0.5248, + "step": 1709 + }, + { + "epoch": 0.14, + "learning_rate": 1.9337276376681264e-05, + "loss": 0.5103, + "step": 1710 + }, + { + "epoch": 0.14, + "learning_rate": 1.93363059306976e-05, + "loss": 0.5182, + "step": 1711 + }, + { + "epoch": 0.14, + "learning_rate": 1.933533479909446e-05, + "loss": 0.5186, + "step": 1712 + }, + { + "epoch": 0.14, + "learning_rate": 1.9334362981943163e-05, + "loss": 0.5112, + "step": 1713 + }, + { + "epoch": 0.14, + "learning_rate": 1.9333390479315074e-05, + "loss": 0.4874, + "step": 1714 + }, + { + "epoch": 0.14, + "learning_rate": 1.9332417291281608e-05, + "loss": 0.4948, + "step": 1715 + }, + { + "epoch": 0.14, + "learning_rate": 1.9331443417914232e-05, + "loss": 0.5153, + "step": 1716 + }, + { + "epoch": 0.14, + "learning_rate": 1.9330468859284462e-05, + "loss": 0.5004, + "step": 1717 + }, + { + "epoch": 0.14, + "learning_rate": 1.932949361546387e-05, + "loss": 0.4919, + "step": 1718 + }, + { + "epoch": 0.14, + "learning_rate": 1.9328517686524073e-05, + "loss": 0.5057, + "step": 1719 + }, + { + "epoch": 0.14, + "learning_rate": 1.9327541072536733e-05, + "loss": 0.5056, + "step": 1720 + }, + { + "epoch": 0.14, + "learning_rate": 1.9326563773573576e-05, + "loss": 0.4943, + "step": 1721 + }, + { + "epoch": 0.14, + "learning_rate": 1.9325585789706366e-05, + "loss": 0.5114, + "step": 1722 + }, + { + "epoch": 0.14, + "learning_rate": 1.932460712100692e-05, + "loss": 0.4955, + "step": 1723 + }, + { + "epoch": 0.14, + "learning_rate": 1.9323627767547118e-05, + "loss": 0.4962, + "step": 1724 + }, + { + "epoch": 0.14, + "learning_rate": 1.932264772939887e-05, + "loss": 0.5037, + "step": 1725 + }, + { + "epoch": 0.14, + "learning_rate": 1.9321667006634146e-05, + "loss": 0.5101, + "step": 1726 + }, + { + "epoch": 0.14, + "learning_rate": 1.932068559932497e-05, + "loss": 0.5041, + "step": 1727 + }, + { + "epoch": 0.14, + "learning_rate": 1.9319703507543415e-05, + "loss": 0.4974, + "step": 1728 + }, + { + "epoch": 0.14, + "learning_rate": 1.9318720731361593e-05, + "loss": 0.5173, + "step": 1729 + }, + { + "epoch": 0.14, + "learning_rate": 1.931773727085168e-05, + "loss": 0.5043, + "step": 1730 + }, + { + "epoch": 0.14, + "learning_rate": 1.9316753126085902e-05, + "loss": 0.5068, + "step": 1731 + }, + { + "epoch": 0.14, + "learning_rate": 1.9315768297136523e-05, + "loss": 0.5033, + "step": 1732 + }, + { + "epoch": 0.14, + "learning_rate": 1.9314782784075866e-05, + "loss": 0.5153, + "step": 1733 + }, + { + "epoch": 0.15, + "learning_rate": 1.9313796586976306e-05, + "loss": 0.5235, + "step": 1734 + }, + { + "epoch": 0.15, + "learning_rate": 1.9312809705910266e-05, + "loss": 0.4886, + "step": 1735 + }, + { + "epoch": 0.15, + "learning_rate": 1.9311822140950213e-05, + "loss": 0.493, + "step": 1736 + }, + { + "epoch": 0.15, + "learning_rate": 1.931083389216867e-05, + "loss": 0.5066, + "step": 1737 + }, + { + "epoch": 0.15, + "learning_rate": 1.930984495963822e-05, + "loss": 0.4965, + "step": 1738 + }, + { + "epoch": 0.15, + "learning_rate": 1.930885534343147e-05, + "loss": 0.497, + "step": 1739 + }, + { + "epoch": 0.15, + "learning_rate": 1.930786504362111e-05, + "loss": 0.4967, + "step": 1740 + }, + { + "epoch": 0.15, + "learning_rate": 1.930687406027985e-05, + "loss": 0.4892, + "step": 1741 + }, + { + "epoch": 0.15, + "learning_rate": 1.930588239348047e-05, + "loss": 0.5099, + "step": 1742 + }, + { + "epoch": 0.15, + "learning_rate": 1.9304890043295796e-05, + "loss": 0.5118, + "step": 1743 + }, + { + "epoch": 0.15, + "learning_rate": 1.93038970097987e-05, + "loss": 0.504, + "step": 1744 + }, + { + "epoch": 0.15, + "learning_rate": 1.93029032930621e-05, + "loss": 0.5056, + "step": 1745 + }, + { + "epoch": 0.15, + "learning_rate": 1.930190889315898e-05, + "loss": 0.499, + "step": 1746 + }, + { + "epoch": 0.15, + "learning_rate": 1.930091381016236e-05, + "loss": 0.5259, + "step": 1747 + }, + { + "epoch": 0.15, + "learning_rate": 1.9299918044145315e-05, + "loss": 0.5033, + "step": 1748 + }, + { + "epoch": 0.15, + "learning_rate": 1.9298921595180968e-05, + "loss": 0.5005, + "step": 1749 + }, + { + "epoch": 0.15, + "learning_rate": 1.9297924463342495e-05, + "loss": 0.518, + "step": 1750 + }, + { + "epoch": 0.15, + "learning_rate": 1.929692664870313e-05, + "loss": 0.5143, + "step": 1751 + }, + { + "epoch": 0.15, + "learning_rate": 1.9295928151336134e-05, + "loss": 0.5061, + "step": 1752 + }, + { + "epoch": 0.15, + "learning_rate": 1.9294928971314843e-05, + "loss": 0.5013, + "step": 1753 + }, + { + "epoch": 0.15, + "learning_rate": 1.9293929108712624e-05, + "loss": 0.5112, + "step": 1754 + }, + { + "epoch": 0.15, + "learning_rate": 1.9292928563602912e-05, + "loss": 0.4963, + "step": 1755 + }, + { + "epoch": 0.15, + "learning_rate": 1.9291927336059175e-05, + "loss": 0.5058, + "step": 1756 + }, + { + "epoch": 0.15, + "learning_rate": 1.9290925426154948e-05, + "loss": 0.4977, + "step": 1757 + }, + { + "epoch": 0.15, + "learning_rate": 1.9289922833963798e-05, + "loss": 0.5122, + "step": 1758 + }, + { + "epoch": 0.15, + "learning_rate": 1.9288919559559353e-05, + "loss": 0.5096, + "step": 1759 + }, + { + "epoch": 0.15, + "learning_rate": 1.928791560301529e-05, + "loss": 0.5032, + "step": 1760 + }, + { + "epoch": 0.15, + "learning_rate": 1.9286910964405345e-05, + "loss": 0.4987, + "step": 1761 + }, + { + "epoch": 0.15, + "learning_rate": 1.9285905643803277e-05, + "loss": 0.5022, + "step": 1762 + }, + { + "epoch": 0.15, + "learning_rate": 1.9284899641282925e-05, + "loss": 0.4889, + "step": 1763 + }, + { + "epoch": 0.15, + "learning_rate": 1.928389295691816e-05, + "loss": 0.5117, + "step": 1764 + }, + { + "epoch": 0.15, + "learning_rate": 1.9282885590782916e-05, + "loss": 0.5068, + "step": 1765 + }, + { + "epoch": 0.15, + "learning_rate": 1.928187754295116e-05, + "loss": 0.5271, + "step": 1766 + }, + { + "epoch": 0.15, + "learning_rate": 1.9280868813496927e-05, + "loss": 0.497, + "step": 1767 + }, + { + "epoch": 0.15, + "learning_rate": 1.9279859402494288e-05, + "loss": 0.5223, + "step": 1768 + }, + { + "epoch": 0.15, + "learning_rate": 1.9278849310017372e-05, + "loss": 0.5151, + "step": 1769 + }, + { + "epoch": 0.15, + "learning_rate": 1.9277838536140357e-05, + "loss": 0.5233, + "step": 1770 + }, + { + "epoch": 0.15, + "learning_rate": 1.927682708093747e-05, + "loss": 0.4949, + "step": 1771 + }, + { + "epoch": 0.15, + "learning_rate": 1.9275814944482988e-05, + "loss": 0.5211, + "step": 1772 + }, + { + "epoch": 0.15, + "learning_rate": 1.9274802126851237e-05, + "loss": 0.4977, + "step": 1773 + }, + { + "epoch": 0.15, + "learning_rate": 1.9273788628116593e-05, + "loss": 0.5169, + "step": 1774 + }, + { + "epoch": 0.15, + "learning_rate": 1.9272774448353484e-05, + "loss": 0.5062, + "step": 1775 + }, + { + "epoch": 0.15, + "learning_rate": 1.927175958763639e-05, + "loss": 0.4999, + "step": 1776 + }, + { + "epoch": 0.15, + "learning_rate": 1.9270744046039834e-05, + "loss": 0.5578, + "step": 1777 + }, + { + "epoch": 0.15, + "learning_rate": 1.92697278236384e-05, + "loss": 0.5188, + "step": 1778 + }, + { + "epoch": 0.15, + "learning_rate": 1.9268710920506707e-05, + "loss": 0.5076, + "step": 1779 + }, + { + "epoch": 0.15, + "learning_rate": 1.926769333671943e-05, + "loss": 0.4947, + "step": 1780 + }, + { + "epoch": 0.15, + "learning_rate": 1.926667507235131e-05, + "loss": 0.5049, + "step": 1781 + }, + { + "epoch": 0.15, + "learning_rate": 1.9265656127477114e-05, + "loss": 0.5118, + "step": 1782 + }, + { + "epoch": 0.15, + "learning_rate": 1.926463650217167e-05, + "loss": 0.489, + "step": 1783 + }, + { + "epoch": 0.15, + "learning_rate": 1.9263616196509855e-05, + "loss": 0.5062, + "step": 1784 + }, + { + "epoch": 0.15, + "learning_rate": 1.9262595210566598e-05, + "loss": 0.5238, + "step": 1785 + }, + { + "epoch": 0.15, + "learning_rate": 1.9261573544416872e-05, + "loss": 0.4939, + "step": 1786 + }, + { + "epoch": 0.15, + "learning_rate": 1.926055119813571e-05, + "loss": 0.491, + "step": 1787 + }, + { + "epoch": 0.15, + "learning_rate": 1.9259528171798184e-05, + "loss": 0.4932, + "step": 1788 + }, + { + "epoch": 0.15, + "learning_rate": 1.925850446547942e-05, + "loss": 0.5256, + "step": 1789 + }, + { + "epoch": 0.15, + "learning_rate": 1.92574800792546e-05, + "loss": 0.5049, + "step": 1790 + }, + { + "epoch": 0.15, + "learning_rate": 1.925645501319895e-05, + "loss": 0.4982, + "step": 1791 + }, + { + "epoch": 0.15, + "learning_rate": 1.925542926738774e-05, + "loss": 0.5154, + "step": 1792 + }, + { + "epoch": 0.15, + "learning_rate": 1.92544028418963e-05, + "loss": 0.5136, + "step": 1793 + }, + { + "epoch": 0.15, + "learning_rate": 1.9253375736800014e-05, + "loss": 0.4918, + "step": 1794 + }, + { + "epoch": 0.15, + "learning_rate": 1.9252347952174294e-05, + "loss": 0.5009, + "step": 1795 + }, + { + "epoch": 0.15, + "learning_rate": 1.925131948809463e-05, + "loss": 0.5235, + "step": 1796 + }, + { + "epoch": 0.15, + "learning_rate": 1.9250290344636537e-05, + "loss": 0.5012, + "step": 1797 + }, + { + "epoch": 0.15, + "learning_rate": 1.92492605218756e-05, + "loss": 0.4942, + "step": 1798 + }, + { + "epoch": 0.15, + "learning_rate": 1.9248230019887438e-05, + "loss": 0.5102, + "step": 1799 + }, + { + "epoch": 0.15, + "learning_rate": 1.924719883874773e-05, + "loss": 0.4946, + "step": 1800 + }, + { + "epoch": 0.15, + "learning_rate": 1.9246166978532203e-05, + "loss": 0.5077, + "step": 1801 + }, + { + "epoch": 0.15, + "learning_rate": 1.924513443931663e-05, + "loss": 0.5084, + "step": 1802 + }, + { + "epoch": 0.15, + "learning_rate": 1.9244101221176834e-05, + "loss": 0.4944, + "step": 1803 + }, + { + "epoch": 0.15, + "learning_rate": 1.9243067324188696e-05, + "loss": 0.5069, + "step": 1804 + }, + { + "epoch": 0.15, + "learning_rate": 1.9242032748428138e-05, + "loss": 0.4945, + "step": 1805 + }, + { + "epoch": 0.15, + "learning_rate": 1.924099749397114e-05, + "loss": 0.507, + "step": 1806 + }, + { + "epoch": 0.15, + "learning_rate": 1.9239961560893717e-05, + "loss": 0.5152, + "step": 1807 + }, + { + "epoch": 0.15, + "learning_rate": 1.923892494927195e-05, + "loss": 0.4897, + "step": 1808 + }, + { + "epoch": 0.15, + "learning_rate": 1.9237887659181963e-05, + "loss": 0.4968, + "step": 1809 + }, + { + "epoch": 0.15, + "learning_rate": 1.9236849690699924e-05, + "loss": 0.5118, + "step": 1810 + }, + { + "epoch": 0.15, + "learning_rate": 1.923581104390207e-05, + "loss": 0.5128, + "step": 1811 + }, + { + "epoch": 0.15, + "learning_rate": 1.9234771718864667e-05, + "loss": 0.4928, + "step": 1812 + }, + { + "epoch": 0.15, + "learning_rate": 1.9233731715664036e-05, + "loss": 0.5075, + "step": 1813 + }, + { + "epoch": 0.15, + "learning_rate": 1.9232691034376556e-05, + "loss": 0.5109, + "step": 1814 + }, + { + "epoch": 0.15, + "learning_rate": 1.9231649675078647e-05, + "loss": 0.4918, + "step": 1815 + }, + { + "epoch": 0.15, + "learning_rate": 1.9230607637846785e-05, + "loss": 0.5056, + "step": 1816 + }, + { + "epoch": 0.15, + "learning_rate": 1.9229564922757487e-05, + "loss": 0.4999, + "step": 1817 + }, + { + "epoch": 0.15, + "learning_rate": 1.9228521529887333e-05, + "loss": 0.5066, + "step": 1818 + }, + { + "epoch": 0.15, + "learning_rate": 1.9227477459312942e-05, + "loss": 0.4944, + "step": 1819 + }, + { + "epoch": 0.15, + "learning_rate": 1.9226432711110983e-05, + "loss": 0.5145, + "step": 1820 + }, + { + "epoch": 0.15, + "learning_rate": 1.922538728535819e-05, + "loss": 0.5033, + "step": 1821 + }, + { + "epoch": 0.15, + "learning_rate": 1.922434118213132e-05, + "loss": 0.5292, + "step": 1822 + }, + { + "epoch": 0.15, + "learning_rate": 1.9223294401507196e-05, + "loss": 0.5067, + "step": 1823 + }, + { + "epoch": 0.15, + "learning_rate": 1.9222246943562702e-05, + "loss": 0.5016, + "step": 1824 + }, + { + "epoch": 0.15, + "learning_rate": 1.9221198808374746e-05, + "loss": 0.4928, + "step": 1825 + }, + { + "epoch": 0.15, + "learning_rate": 1.9220149996020306e-05, + "loss": 0.5077, + "step": 1826 + }, + { + "epoch": 0.15, + "learning_rate": 1.9219100506576396e-05, + "loss": 0.4962, + "step": 1827 + }, + { + "epoch": 0.15, + "learning_rate": 1.9218050340120095e-05, + "loss": 0.5081, + "step": 1828 + }, + { + "epoch": 0.15, + "learning_rate": 1.9216999496728513e-05, + "loss": 0.5203, + "step": 1829 + }, + { + "epoch": 0.15, + "learning_rate": 1.9215947976478825e-05, + "loss": 0.511, + "step": 1830 + }, + { + "epoch": 0.15, + "learning_rate": 1.9214895779448254e-05, + "loss": 0.5018, + "step": 1831 + }, + { + "epoch": 0.15, + "learning_rate": 1.921384290571406e-05, + "loss": 0.4929, + "step": 1832 + }, + { + "epoch": 0.15, + "learning_rate": 1.9212789355353567e-05, + "loss": 0.4992, + "step": 1833 + }, + { + "epoch": 0.15, + "learning_rate": 1.921173512844414e-05, + "loss": 0.5106, + "step": 1834 + }, + { + "epoch": 0.15, + "learning_rate": 1.9210680225063204e-05, + "loss": 0.4934, + "step": 1835 + }, + { + "epoch": 0.15, + "learning_rate": 1.9209624645288224e-05, + "loss": 0.5013, + "step": 1836 + }, + { + "epoch": 0.15, + "learning_rate": 1.9208568389196715e-05, + "loss": 0.4948, + "step": 1837 + }, + { + "epoch": 0.15, + "learning_rate": 1.920751145686624e-05, + "loss": 0.4963, + "step": 1838 + }, + { + "epoch": 0.15, + "learning_rate": 1.9206453848374425e-05, + "loss": 0.499, + "step": 1839 + }, + { + "epoch": 0.15, + "learning_rate": 1.920539556379893e-05, + "loss": 0.4947, + "step": 1840 + }, + { + "epoch": 0.15, + "learning_rate": 1.920433660321747e-05, + "loss": 0.5145, + "step": 1841 + }, + { + "epoch": 0.15, + "learning_rate": 1.920327696670782e-05, + "loss": 0.4967, + "step": 1842 + }, + { + "epoch": 0.15, + "learning_rate": 1.9202216654347786e-05, + "loss": 0.52, + "step": 1843 + }, + { + "epoch": 0.15, + "learning_rate": 1.9201155666215237e-05, + "loss": 0.5103, + "step": 1844 + }, + { + "epoch": 0.15, + "learning_rate": 1.9200094002388084e-05, + "loss": 0.5124, + "step": 1845 + }, + { + "epoch": 0.15, + "learning_rate": 1.9199031662944294e-05, + "loss": 0.5054, + "step": 1846 + }, + { + "epoch": 0.15, + "learning_rate": 1.919796864796188e-05, + "loss": 0.4923, + "step": 1847 + }, + { + "epoch": 0.15, + "learning_rate": 1.919690495751891e-05, + "loss": 0.5264, + "step": 1848 + }, + { + "epoch": 0.15, + "learning_rate": 1.9195840591693486e-05, + "loss": 0.4979, + "step": 1849 + }, + { + "epoch": 0.15, + "learning_rate": 1.919477555056378e-05, + "loss": 0.5072, + "step": 1850 + }, + { + "epoch": 0.15, + "learning_rate": 1.9193709834208005e-05, + "loss": 0.5136, + "step": 1851 + }, + { + "epoch": 0.15, + "learning_rate": 1.9192643442704413e-05, + "loss": 0.5028, + "step": 1852 + }, + { + "epoch": 0.16, + "learning_rate": 1.9191576376131328e-05, + "loss": 0.52, + "step": 1853 + }, + { + "epoch": 0.16, + "learning_rate": 1.91905086345671e-05, + "loss": 0.5033, + "step": 1854 + }, + { + "epoch": 0.16, + "learning_rate": 1.9189440218090146e-05, + "loss": 0.5088, + "step": 1855 + }, + { + "epoch": 0.16, + "learning_rate": 1.9188371126778923e-05, + "loss": 0.5009, + "step": 1856 + }, + { + "epoch": 0.16, + "learning_rate": 1.9187301360711943e-05, + "loss": 0.5068, + "step": 1857 + }, + { + "epoch": 0.16, + "learning_rate": 1.9186230919967764e-05, + "loss": 0.4997, + "step": 1858 + }, + { + "epoch": 0.16, + "learning_rate": 1.9185159804624994e-05, + "loss": 0.5098, + "step": 1859 + }, + { + "epoch": 0.16, + "learning_rate": 1.9184088014762292e-05, + "loss": 0.4964, + "step": 1860 + }, + { + "epoch": 0.16, + "learning_rate": 1.9183015550458367e-05, + "loss": 0.5084, + "step": 1861 + }, + { + "epoch": 0.16, + "learning_rate": 1.918194241179197e-05, + "loss": 0.5049, + "step": 1862 + }, + { + "epoch": 0.16, + "learning_rate": 1.9180868598841916e-05, + "loss": 0.4998, + "step": 1863 + }, + { + "epoch": 0.16, + "learning_rate": 1.9179794111687063e-05, + "loss": 0.5073, + "step": 1864 + }, + { + "epoch": 0.16, + "learning_rate": 1.9178718950406304e-05, + "loss": 0.5088, + "step": 1865 + }, + { + "epoch": 0.16, + "learning_rate": 1.917764311507861e-05, + "loss": 0.4973, + "step": 1866 + }, + { + "epoch": 0.16, + "learning_rate": 1.9176566605782974e-05, + "loss": 0.5177, + "step": 1867 + }, + { + "epoch": 0.16, + "learning_rate": 1.9175489422598455e-05, + "loss": 0.5072, + "step": 1868 + }, + { + "epoch": 0.16, + "learning_rate": 1.9174411565604157e-05, + "loss": 0.5095, + "step": 1869 + }, + { + "epoch": 0.16, + "learning_rate": 1.917333303487923e-05, + "loss": 0.4966, + "step": 1870 + }, + { + "epoch": 0.16, + "learning_rate": 1.9172253830502883e-05, + "loss": 0.5067, + "step": 1871 + }, + { + "epoch": 0.16, + "learning_rate": 1.9171173952554367e-05, + "loss": 0.5058, + "step": 1872 + }, + { + "epoch": 0.16, + "learning_rate": 1.917009340111298e-05, + "loss": 0.5126, + "step": 1873 + }, + { + "epoch": 0.16, + "learning_rate": 1.916901217625807e-05, + "loss": 0.5041, + "step": 1874 + }, + { + "epoch": 0.16, + "learning_rate": 1.916793027806905e-05, + "loss": 0.4989, + "step": 1875 + }, + { + "epoch": 0.16, + "learning_rate": 1.9166847706625357e-05, + "loss": 0.5211, + "step": 1876 + }, + { + "epoch": 0.16, + "learning_rate": 1.91657644620065e-05, + "loss": 0.499, + "step": 1877 + }, + { + "epoch": 0.16, + "learning_rate": 1.9164680544292023e-05, + "loss": 0.4914, + "step": 1878 + }, + { + "epoch": 0.16, + "learning_rate": 1.9163595953561523e-05, + "loss": 0.5074, + "step": 1879 + }, + { + "epoch": 0.16, + "learning_rate": 1.9162510689894653e-05, + "loss": 0.534, + "step": 1880 + }, + { + "epoch": 0.16, + "learning_rate": 1.916142475337111e-05, + "loss": 0.5084, + "step": 1881 + }, + { + "epoch": 0.16, + "learning_rate": 1.9160338144070635e-05, + "loss": 0.5069, + "step": 1882 + }, + { + "epoch": 0.16, + "learning_rate": 1.9159250862073028e-05, + "loss": 0.5611, + "step": 1883 + }, + { + "epoch": 0.16, + "learning_rate": 1.9158162907458135e-05, + "loss": 0.4864, + "step": 1884 + }, + { + "epoch": 0.16, + "learning_rate": 1.9157074280305847e-05, + "loss": 0.5034, + "step": 1885 + }, + { + "epoch": 0.16, + "learning_rate": 1.9155984980696112e-05, + "loss": 0.5303, + "step": 1886 + }, + { + "epoch": 0.16, + "learning_rate": 1.9154895008708923e-05, + "loss": 0.4934, + "step": 1887 + }, + { + "epoch": 0.16, + "learning_rate": 1.9153804364424325e-05, + "loss": 0.4889, + "step": 1888 + }, + { + "epoch": 0.16, + "learning_rate": 1.9152713047922406e-05, + "loss": 0.5199, + "step": 1889 + }, + { + "epoch": 0.16, + "learning_rate": 1.9151621059283306e-05, + "loss": 0.5035, + "step": 1890 + }, + { + "epoch": 0.16, + "learning_rate": 1.9150528398587226e-05, + "loss": 0.5213, + "step": 1891 + }, + { + "epoch": 0.16, + "learning_rate": 1.9149435065914395e-05, + "loss": 0.4933, + "step": 1892 + }, + { + "epoch": 0.16, + "learning_rate": 1.9148341061345114e-05, + "loss": 0.4935, + "step": 1893 + }, + { + "epoch": 0.16, + "learning_rate": 1.9147246384959715e-05, + "loss": 0.5199, + "step": 1894 + }, + { + "epoch": 0.16, + "learning_rate": 1.9146151036838583e-05, + "loss": 0.5242, + "step": 1895 + }, + { + "epoch": 0.16, + "learning_rate": 1.9145055017062165e-05, + "loss": 0.4793, + "step": 1896 + }, + { + "epoch": 0.16, + "learning_rate": 1.914395832571094e-05, + "loss": 0.5142, + "step": 1897 + }, + { + "epoch": 0.16, + "learning_rate": 1.914286096286545e-05, + "loss": 0.4923, + "step": 1898 + }, + { + "epoch": 0.16, + "learning_rate": 1.9141762928606282e-05, + "loss": 0.4866, + "step": 1899 + }, + { + "epoch": 0.16, + "learning_rate": 1.9140664223014064e-05, + "loss": 0.4988, + "step": 1900 + }, + { + "epoch": 0.16, + "learning_rate": 1.9139564846169486e-05, + "loss": 0.4838, + "step": 1901 + }, + { + "epoch": 0.16, + "learning_rate": 1.913846479815328e-05, + "loss": 0.5151, + "step": 1902 + }, + { + "epoch": 0.16, + "learning_rate": 1.913736407904623e-05, + "loss": 0.493, + "step": 1903 + }, + { + "epoch": 0.16, + "learning_rate": 1.9136262688929167e-05, + "loss": 0.4959, + "step": 1904 + }, + { + "epoch": 0.16, + "learning_rate": 1.913516062788297e-05, + "loss": 0.5162, + "step": 1905 + }, + { + "epoch": 0.16, + "learning_rate": 1.9134057895988574e-05, + "loss": 0.4908, + "step": 1906 + }, + { + "epoch": 0.16, + "learning_rate": 1.913295449332696e-05, + "loss": 0.5083, + "step": 1907 + }, + { + "epoch": 0.16, + "learning_rate": 1.913185041997915e-05, + "loss": 0.5152, + "step": 1908 + }, + { + "epoch": 0.16, + "learning_rate": 1.913074567602623e-05, + "loss": 0.5059, + "step": 1909 + }, + { + "epoch": 0.16, + "learning_rate": 1.9129640261549324e-05, + "loss": 0.509, + "step": 1910 + }, + { + "epoch": 0.16, + "learning_rate": 1.9128534176629613e-05, + "loss": 0.5031, + "step": 1911 + }, + { + "epoch": 0.16, + "learning_rate": 1.9127427421348316e-05, + "loss": 0.5084, + "step": 1912 + }, + { + "epoch": 0.16, + "learning_rate": 1.9126319995786717e-05, + "loss": 0.5322, + "step": 1913 + }, + { + "epoch": 0.16, + "learning_rate": 1.912521190002614e-05, + "loss": 0.5027, + "step": 1914 + }, + { + "epoch": 0.16, + "learning_rate": 1.9124103134147945e-05, + "loss": 0.505, + "step": 1915 + }, + { + "epoch": 0.16, + "learning_rate": 1.9122993698233576e-05, + "loss": 0.5083, + "step": 1916 + }, + { + "epoch": 0.16, + "learning_rate": 1.9121883592364486e-05, + "loss": 0.5209, + "step": 1917 + }, + { + "epoch": 0.16, + "learning_rate": 1.9120772816622213e-05, + "loss": 0.509, + "step": 1918 + }, + { + "epoch": 0.16, + "learning_rate": 1.9119661371088318e-05, + "loss": 0.5019, + "step": 1919 + }, + { + "epoch": 0.16, + "learning_rate": 1.9118549255844425e-05, + "loss": 0.4998, + "step": 1920 + }, + { + "epoch": 0.16, + "learning_rate": 1.91174364709722e-05, + "loss": 0.4973, + "step": 1921 + }, + { + "epoch": 0.16, + "learning_rate": 1.9116323016553363e-05, + "loss": 0.5233, + "step": 1922 + }, + { + "epoch": 0.16, + "learning_rate": 1.911520889266968e-05, + "loss": 0.492, + "step": 1923 + }, + { + "epoch": 0.16, + "learning_rate": 1.911409409940297e-05, + "loss": 0.5242, + "step": 1924 + }, + { + "epoch": 0.16, + "learning_rate": 1.91129786368351e-05, + "loss": 0.5041, + "step": 1925 + }, + { + "epoch": 0.16, + "learning_rate": 1.911186250504798e-05, + "loss": 0.5142, + "step": 1926 + }, + { + "epoch": 0.16, + "learning_rate": 1.9110745704123577e-05, + "loss": 0.5063, + "step": 1927 + }, + { + "epoch": 0.16, + "learning_rate": 1.9109628234143905e-05, + "loss": 0.497, + "step": 1928 + }, + { + "epoch": 0.16, + "learning_rate": 1.9108510095191025e-05, + "loss": 0.4973, + "step": 1929 + }, + { + "epoch": 0.16, + "learning_rate": 1.910739128734705e-05, + "loss": 0.4926, + "step": 1930 + }, + { + "epoch": 0.16, + "learning_rate": 1.9106271810694137e-05, + "loss": 0.5205, + "step": 1931 + }, + { + "epoch": 0.16, + "learning_rate": 1.9105151665314497e-05, + "loss": 0.4997, + "step": 1932 + }, + { + "epoch": 0.16, + "learning_rate": 1.9104030851290393e-05, + "loss": 0.5069, + "step": 1933 + }, + { + "epoch": 0.16, + "learning_rate": 1.910290936870413e-05, + "loss": 0.5012, + "step": 1934 + }, + { + "epoch": 0.16, + "learning_rate": 1.910178721763806e-05, + "loss": 0.5198, + "step": 1935 + }, + { + "epoch": 0.16, + "learning_rate": 1.91006643981746e-05, + "loss": 0.5206, + "step": 1936 + }, + { + "epoch": 0.16, + "learning_rate": 1.9099540910396194e-05, + "loss": 0.4984, + "step": 1937 + }, + { + "epoch": 0.16, + "learning_rate": 1.9098416754385355e-05, + "loss": 0.5317, + "step": 1938 + }, + { + "epoch": 0.16, + "learning_rate": 1.909729193022463e-05, + "loss": 0.4949, + "step": 1939 + }, + { + "epoch": 0.16, + "learning_rate": 1.9096166437996626e-05, + "loss": 0.4801, + "step": 1940 + }, + { + "epoch": 0.16, + "learning_rate": 1.9095040277783993e-05, + "loss": 0.5191, + "step": 1941 + }, + { + "epoch": 0.16, + "learning_rate": 1.909391344966943e-05, + "loss": 0.5103, + "step": 1942 + }, + { + "epoch": 0.16, + "learning_rate": 1.909278595373569e-05, + "loss": 0.4988, + "step": 1943 + }, + { + "epoch": 0.16, + "learning_rate": 1.9091657790065565e-05, + "loss": 0.49, + "step": 1944 + }, + { + "epoch": 0.16, + "learning_rate": 1.909052895874191e-05, + "loss": 0.528, + "step": 1945 + }, + { + "epoch": 0.16, + "learning_rate": 1.9089399459847615e-05, + "loss": 0.4989, + "step": 1946 + }, + { + "epoch": 0.16, + "learning_rate": 1.9088269293465634e-05, + "loss": 0.4941, + "step": 1947 + }, + { + "epoch": 0.16, + "learning_rate": 1.9087138459678956e-05, + "loss": 0.5119, + "step": 1948 + }, + { + "epoch": 0.16, + "learning_rate": 1.908600695857062e-05, + "loss": 0.5093, + "step": 1949 + }, + { + "epoch": 0.16, + "learning_rate": 1.9084874790223735e-05, + "loss": 0.5122, + "step": 1950 + }, + { + "epoch": 0.16, + "learning_rate": 1.9083741954721423e-05, + "loss": 0.4985, + "step": 1951 + }, + { + "epoch": 0.16, + "learning_rate": 1.908260845214689e-05, + "loss": 0.5291, + "step": 1952 + }, + { + "epoch": 0.16, + "learning_rate": 1.9081474282583367e-05, + "loss": 0.5037, + "step": 1953 + }, + { + "epoch": 0.16, + "learning_rate": 1.9080339446114148e-05, + "loss": 0.4901, + "step": 1954 + }, + { + "epoch": 0.16, + "learning_rate": 1.907920394282256e-05, + "loss": 0.4888, + "step": 1955 + }, + { + "epoch": 0.16, + "learning_rate": 1.9078067772792006e-05, + "loss": 0.4985, + "step": 1956 + }, + { + "epoch": 0.16, + "learning_rate": 1.907693093610591e-05, + "loss": 0.5106, + "step": 1957 + }, + { + "epoch": 0.16, + "learning_rate": 1.9075793432847763e-05, + "loss": 0.5031, + "step": 1958 + }, + { + "epoch": 0.16, + "learning_rate": 1.907465526310109e-05, + "loss": 0.5117, + "step": 1959 + }, + { + "epoch": 0.16, + "learning_rate": 1.9073516426949485e-05, + "loss": 0.5219, + "step": 1960 + }, + { + "epoch": 0.16, + "learning_rate": 1.9072376924476568e-05, + "loss": 0.5064, + "step": 1961 + }, + { + "epoch": 0.16, + "learning_rate": 1.9071236755766028e-05, + "loss": 0.5332, + "step": 1962 + }, + { + "epoch": 0.16, + "learning_rate": 1.9070095920901588e-05, + "loss": 0.5191, + "step": 1963 + }, + { + "epoch": 0.16, + "learning_rate": 1.906895441996703e-05, + "loss": 0.5143, + "step": 1964 + }, + { + "epoch": 0.16, + "learning_rate": 1.906781225304618e-05, + "loss": 0.491, + "step": 1965 + }, + { + "epoch": 0.16, + "learning_rate": 1.9066669420222915e-05, + "loss": 0.5089, + "step": 1966 + }, + { + "epoch": 0.16, + "learning_rate": 1.9065525921581158e-05, + "loss": 0.5046, + "step": 1967 + }, + { + "epoch": 0.16, + "learning_rate": 1.9064381757204884e-05, + "loss": 0.501, + "step": 1968 + }, + { + "epoch": 0.16, + "learning_rate": 1.9063236927178116e-05, + "loss": 0.5061, + "step": 1969 + }, + { + "epoch": 0.16, + "learning_rate": 1.9062091431584924e-05, + "loss": 0.5049, + "step": 1970 + }, + { + "epoch": 0.16, + "learning_rate": 1.9060945270509427e-05, + "loss": 0.4905, + "step": 1971 + }, + { + "epoch": 0.16, + "learning_rate": 1.90597984440358e-05, + "loss": 0.4926, + "step": 1972 + }, + { + "epoch": 0.17, + "learning_rate": 1.9058650952248257e-05, + "loss": 0.4932, + "step": 1973 + }, + { + "epoch": 0.17, + "learning_rate": 1.9057502795231066e-05, + "loss": 0.5016, + "step": 1974 + }, + { + "epoch": 0.17, + "learning_rate": 1.9056353973068544e-05, + "loss": 0.4863, + "step": 1975 + }, + { + "epoch": 0.17, + "learning_rate": 1.905520448584505e-05, + "loss": 0.5144, + "step": 1976 + }, + { + "epoch": 0.17, + "learning_rate": 1.9054054333645006e-05, + "loss": 0.4898, + "step": 1977 + }, + { + "epoch": 0.17, + "learning_rate": 1.905290351655287e-05, + "loss": 0.4975, + "step": 1978 + }, + { + "epoch": 0.17, + "learning_rate": 1.9051752034653153e-05, + "loss": 0.526, + "step": 1979 + }, + { + "epoch": 0.17, + "learning_rate": 1.9050599888030413e-05, + "loss": 0.5172, + "step": 1980 + }, + { + "epoch": 0.17, + "learning_rate": 1.9049447076769265e-05, + "loss": 0.4884, + "step": 1981 + }, + { + "epoch": 0.17, + "learning_rate": 1.904829360095436e-05, + "loss": 0.5012, + "step": 1982 + }, + { + "epoch": 0.17, + "learning_rate": 1.904713946067041e-05, + "loss": 0.5017, + "step": 1983 + }, + { + "epoch": 0.17, + "learning_rate": 1.904598465600217e-05, + "loss": 0.5158, + "step": 1984 + }, + { + "epoch": 0.17, + "learning_rate": 1.904482918703444e-05, + "loss": 0.5017, + "step": 1985 + }, + { + "epoch": 0.17, + "learning_rate": 1.9043673053852073e-05, + "loss": 0.496, + "step": 1986 + }, + { + "epoch": 0.17, + "learning_rate": 1.9042516256539974e-05, + "loss": 0.5146, + "step": 1987 + }, + { + "epoch": 0.17, + "learning_rate": 1.904135879518309e-05, + "loss": 0.497, + "step": 1988 + }, + { + "epoch": 0.17, + "learning_rate": 1.9040200669866426e-05, + "loss": 0.5092, + "step": 1989 + }, + { + "epoch": 0.17, + "learning_rate": 1.903904188067502e-05, + "loss": 0.4902, + "step": 1990 + }, + { + "epoch": 0.17, + "learning_rate": 1.903788242769398e-05, + "loss": 0.5079, + "step": 1991 + }, + { + "epoch": 0.17, + "learning_rate": 1.9036722311008442e-05, + "loss": 0.5132, + "step": 1992 + }, + { + "epoch": 0.17, + "learning_rate": 1.9035561530703605e-05, + "loss": 0.5149, + "step": 1993 + }, + { + "epoch": 0.17, + "learning_rate": 1.903440008686471e-05, + "loss": 0.4911, + "step": 1994 + }, + { + "epoch": 0.17, + "learning_rate": 1.9033237979577053e-05, + "loss": 0.5114, + "step": 1995 + }, + { + "epoch": 0.17, + "learning_rate": 1.9032075208925967e-05, + "loss": 0.5084, + "step": 1996 + }, + { + "epoch": 0.17, + "learning_rate": 1.903091177499685e-05, + "loss": 0.4958, + "step": 1997 + }, + { + "epoch": 0.17, + "learning_rate": 1.9029747677875132e-05, + "loss": 0.5, + "step": 1998 + }, + { + "epoch": 0.17, + "learning_rate": 1.90285829176463e-05, + "loss": 0.5156, + "step": 1999 + }, + { + "epoch": 0.17, + "learning_rate": 1.9027417494395896e-05, + "loss": 0.501, + "step": 2000 + }, + { + "epoch": 0.17, + "learning_rate": 1.9026251408209494e-05, + "loss": 0.4945, + "step": 2001 + }, + { + "epoch": 0.17, + "learning_rate": 1.9025084659172733e-05, + "loss": 0.4951, + "step": 2002 + }, + { + "epoch": 0.17, + "learning_rate": 1.9023917247371292e-05, + "loss": 0.4994, + "step": 2003 + }, + { + "epoch": 0.17, + "learning_rate": 1.9022749172890904e-05, + "loss": 0.5328, + "step": 2004 + }, + { + "epoch": 0.17, + "learning_rate": 1.9021580435817343e-05, + "loss": 0.5034, + "step": 2005 + }, + { + "epoch": 0.17, + "learning_rate": 1.902041103623644e-05, + "loss": 0.5178, + "step": 2006 + }, + { + "epoch": 0.17, + "learning_rate": 1.901924097423407e-05, + "loss": 0.4987, + "step": 2007 + }, + { + "epoch": 0.17, + "learning_rate": 1.901807024989615e-05, + "loss": 0.4948, + "step": 2008 + }, + { + "epoch": 0.17, + "learning_rate": 1.9016898863308667e-05, + "loss": 0.4785, + "step": 2009 + }, + { + "epoch": 0.17, + "learning_rate": 1.9015726814557632e-05, + "loss": 0.496, + "step": 2010 + }, + { + "epoch": 0.17, + "learning_rate": 1.9014554103729125e-05, + "loss": 0.5314, + "step": 2011 + }, + { + "epoch": 0.17, + "learning_rate": 1.9013380730909255e-05, + "loss": 0.503, + "step": 2012 + }, + { + "epoch": 0.17, + "learning_rate": 1.901220669618419e-05, + "loss": 0.5094, + "step": 2013 + }, + { + "epoch": 0.17, + "learning_rate": 1.9011031999640152e-05, + "loss": 0.5112, + "step": 2014 + }, + { + "epoch": 0.17, + "learning_rate": 1.9009856641363406e-05, + "loss": 0.5092, + "step": 2015 + }, + { + "epoch": 0.17, + "learning_rate": 1.9008680621440262e-05, + "loss": 0.5008, + "step": 2016 + }, + { + "epoch": 0.17, + "learning_rate": 1.9007503939957085e-05, + "loss": 0.503, + "step": 2017 + }, + { + "epoch": 0.17, + "learning_rate": 1.900632659700028e-05, + "loss": 0.5023, + "step": 2018 + }, + { + "epoch": 0.17, + "learning_rate": 1.9005148592656312e-05, + "loss": 0.4859, + "step": 2019 + }, + { + "epoch": 0.17, + "learning_rate": 1.9003969927011683e-05, + "loss": 0.4745, + "step": 2020 + }, + { + "epoch": 0.17, + "learning_rate": 1.900279060015296e-05, + "loss": 0.5014, + "step": 2021 + }, + { + "epoch": 0.17, + "learning_rate": 1.9001610612166735e-05, + "loss": 0.4822, + "step": 2022 + }, + { + "epoch": 0.17, + "learning_rate": 1.9000429963139668e-05, + "loss": 0.4995, + "step": 2023 + }, + { + "epoch": 0.17, + "learning_rate": 1.8999248653158463e-05, + "loss": 0.5026, + "step": 2024 + }, + { + "epoch": 0.17, + "learning_rate": 1.8998066682309864e-05, + "loss": 0.5068, + "step": 2025 + }, + { + "epoch": 0.17, + "learning_rate": 1.8996884050680675e-05, + "loss": 0.5157, + "step": 2026 + }, + { + "epoch": 0.17, + "learning_rate": 1.8995700758357744e-05, + "loss": 0.4847, + "step": 2027 + }, + { + "epoch": 0.17, + "learning_rate": 1.899451680542796e-05, + "loss": 0.4887, + "step": 2028 + }, + { + "epoch": 0.17, + "learning_rate": 1.8993332191978277e-05, + "loss": 0.5107, + "step": 2029 + }, + { + "epoch": 0.17, + "learning_rate": 1.8992146918095684e-05, + "loss": 0.5014, + "step": 2030 + }, + { + "epoch": 0.17, + "learning_rate": 1.8990960983867222e-05, + "loss": 0.5074, + "step": 2031 + }, + { + "epoch": 0.17, + "learning_rate": 1.898977438937998e-05, + "loss": 0.5281, + "step": 2032 + }, + { + "epoch": 0.17, + "learning_rate": 1.8988587134721103e-05, + "loss": 0.4978, + "step": 2033 + }, + { + "epoch": 0.17, + "learning_rate": 1.8987399219977768e-05, + "loss": 0.5055, + "step": 2034 + }, + { + "epoch": 0.17, + "learning_rate": 1.8986210645237216e-05, + "loss": 0.5146, + "step": 2035 + }, + { + "epoch": 0.17, + "learning_rate": 1.8985021410586732e-05, + "loss": 0.5041, + "step": 2036 + }, + { + "epoch": 0.17, + "learning_rate": 1.8983831516113645e-05, + "loss": 0.5209, + "step": 2037 + }, + { + "epoch": 0.17, + "learning_rate": 1.898264096190534e-05, + "loss": 0.4876, + "step": 2038 + }, + { + "epoch": 0.17, + "learning_rate": 1.8981449748049248e-05, + "loss": 0.5127, + "step": 2039 + }, + { + "epoch": 0.17, + "learning_rate": 1.8980257874632836e-05, + "loss": 0.5006, + "step": 2040 + }, + { + "epoch": 0.17, + "learning_rate": 1.8979065341743642e-05, + "loss": 0.4796, + "step": 2041 + }, + { + "epoch": 0.17, + "learning_rate": 1.8977872149469236e-05, + "loss": 0.4946, + "step": 2042 + }, + { + "epoch": 0.17, + "learning_rate": 1.897667829789724e-05, + "loss": 0.5015, + "step": 2043 + }, + { + "epoch": 0.17, + "learning_rate": 1.8975483787115326e-05, + "loss": 0.4806, + "step": 2044 + }, + { + "epoch": 0.17, + "learning_rate": 1.8974288617211217e-05, + "loss": 0.5259, + "step": 2045 + }, + { + "epoch": 0.17, + "learning_rate": 1.8973092788272677e-05, + "loss": 0.5037, + "step": 2046 + }, + { + "epoch": 0.17, + "learning_rate": 1.8971896300387525e-05, + "loss": 0.506, + "step": 2047 + }, + { + "epoch": 0.17, + "learning_rate": 1.8970699153643623e-05, + "loss": 0.5138, + "step": 2048 + }, + { + "epoch": 0.17, + "learning_rate": 1.896950134812889e-05, + "loss": 0.5103, + "step": 2049 + }, + { + "epoch": 0.17, + "learning_rate": 1.8968302883931283e-05, + "loss": 0.4973, + "step": 2050 + }, + { + "epoch": 0.17, + "learning_rate": 1.8967103761138817e-05, + "loss": 0.524, + "step": 2051 + }, + { + "epoch": 0.17, + "learning_rate": 1.8965903979839547e-05, + "loss": 0.5037, + "step": 2052 + }, + { + "epoch": 0.17, + "learning_rate": 1.8964703540121577e-05, + "loss": 0.4964, + "step": 2053 + }, + { + "epoch": 0.17, + "learning_rate": 1.8963502442073073e-05, + "loss": 0.499, + "step": 2054 + }, + { + "epoch": 0.17, + "learning_rate": 1.8962300685782224e-05, + "loss": 0.507, + "step": 2055 + }, + { + "epoch": 0.17, + "learning_rate": 1.8961098271337296e-05, + "loss": 0.5196, + "step": 2056 + }, + { + "epoch": 0.17, + "learning_rate": 1.8959895198826582e-05, + "loss": 0.489, + "step": 2057 + }, + { + "epoch": 0.17, + "learning_rate": 1.895869146833843e-05, + "loss": 0.5034, + "step": 2058 + }, + { + "epoch": 0.17, + "learning_rate": 1.8957487079961235e-05, + "loss": 0.5135, + "step": 2059 + }, + { + "epoch": 0.17, + "learning_rate": 1.895628203378345e-05, + "loss": 0.4917, + "step": 2060 + }, + { + "epoch": 0.17, + "learning_rate": 1.8955076329893565e-05, + "loss": 0.503, + "step": 2061 + }, + { + "epoch": 0.17, + "learning_rate": 1.8953869968380117e-05, + "loss": 0.53, + "step": 2062 + }, + { + "epoch": 0.17, + "learning_rate": 1.8952662949331707e-05, + "loss": 0.4998, + "step": 2063 + }, + { + "epoch": 0.17, + "learning_rate": 1.8951455272836963e-05, + "loss": 0.4908, + "step": 2064 + }, + { + "epoch": 0.17, + "learning_rate": 1.8950246938984573e-05, + "loss": 0.5131, + "step": 2065 + }, + { + "epoch": 0.17, + "learning_rate": 1.894903794786328e-05, + "loss": 0.5325, + "step": 2066 + }, + { + "epoch": 0.17, + "learning_rate": 1.894782829956186e-05, + "loss": 0.5071, + "step": 2067 + }, + { + "epoch": 0.17, + "learning_rate": 1.8946617994169146e-05, + "loss": 0.5157, + "step": 2068 + }, + { + "epoch": 0.17, + "learning_rate": 1.8945407031774018e-05, + "loss": 0.4963, + "step": 2069 + }, + { + "epoch": 0.17, + "learning_rate": 1.8944195412465404e-05, + "loss": 0.5301, + "step": 2070 + }, + { + "epoch": 0.17, + "learning_rate": 1.8942983136332282e-05, + "loss": 0.5193, + "step": 2071 + }, + { + "epoch": 0.17, + "learning_rate": 1.8941770203463674e-05, + "loss": 0.4954, + "step": 2072 + }, + { + "epoch": 0.17, + "learning_rate": 1.8940556613948656e-05, + "loss": 0.5124, + "step": 2073 + }, + { + "epoch": 0.17, + "learning_rate": 1.8939342367876345e-05, + "loss": 0.51, + "step": 2074 + }, + { + "epoch": 0.17, + "learning_rate": 1.893812746533591e-05, + "loss": 0.4831, + "step": 2075 + }, + { + "epoch": 0.17, + "learning_rate": 1.8936911906416572e-05, + "loss": 0.4994, + "step": 2076 + }, + { + "epoch": 0.17, + "learning_rate": 1.8935695691207598e-05, + "loss": 0.5263, + "step": 2077 + }, + { + "epoch": 0.17, + "learning_rate": 1.8934478819798296e-05, + "loss": 0.4893, + "step": 2078 + }, + { + "epoch": 0.17, + "learning_rate": 1.8933261292278033e-05, + "loss": 0.5132, + "step": 2079 + }, + { + "epoch": 0.17, + "learning_rate": 1.8932043108736217e-05, + "loss": 0.5076, + "step": 2080 + }, + { + "epoch": 0.17, + "learning_rate": 1.89308242692623e-05, + "loss": 0.527, + "step": 2081 + }, + { + "epoch": 0.17, + "learning_rate": 1.89296047739458e-05, + "loss": 0.5058, + "step": 2082 + }, + { + "epoch": 0.17, + "learning_rate": 1.892838462287627e-05, + "loss": 0.5095, + "step": 2083 + }, + { + "epoch": 0.17, + "learning_rate": 1.8927163816143302e-05, + "loss": 0.4916, + "step": 2084 + }, + { + "epoch": 0.17, + "learning_rate": 1.8925942353836558e-05, + "loss": 0.4806, + "step": 2085 + }, + { + "epoch": 0.17, + "learning_rate": 1.892472023604573e-05, + "loss": 0.5076, + "step": 2086 + }, + { + "epoch": 0.17, + "learning_rate": 1.8923497462860572e-05, + "loss": 0.5209, + "step": 2087 + }, + { + "epoch": 0.17, + "learning_rate": 1.8922274034370875e-05, + "loss": 0.4888, + "step": 2088 + }, + { + "epoch": 0.17, + "learning_rate": 1.8921049950666484e-05, + "loss": 0.5002, + "step": 2089 + }, + { + "epoch": 0.17, + "learning_rate": 1.891982521183729e-05, + "loss": 0.5068, + "step": 2090 + }, + { + "epoch": 0.17, + "learning_rate": 1.891859981797323e-05, + "loss": 0.4904, + "step": 2091 + }, + { + "epoch": 0.18, + "learning_rate": 1.89173737691643e-05, + "loss": 0.5147, + "step": 2092 + }, + { + "epoch": 0.18, + "learning_rate": 1.8916147065500524e-05, + "loss": 0.489, + "step": 2093 + }, + { + "epoch": 0.18, + "learning_rate": 1.8914919707071997e-05, + "loss": 0.5265, + "step": 2094 + }, + { + "epoch": 0.18, + "learning_rate": 1.8913691693968846e-05, + "loss": 0.4928, + "step": 2095 + }, + { + "epoch": 0.18, + "learning_rate": 1.891246302628125e-05, + "loss": 0.5037, + "step": 2096 + }, + { + "epoch": 0.18, + "learning_rate": 1.891123370409944e-05, + "loss": 0.5027, + "step": 2097 + }, + { + "epoch": 0.18, + "learning_rate": 1.8910003727513697e-05, + "loss": 0.496, + "step": 2098 + }, + { + "epoch": 0.18, + "learning_rate": 1.8908773096614333e-05, + "loss": 0.4993, + "step": 2099 + }, + { + "epoch": 0.18, + "learning_rate": 1.8907541811491726e-05, + "loss": 0.4809, + "step": 2100 + }, + { + "epoch": 0.18, + "learning_rate": 1.89063098722363e-05, + "loss": 0.4981, + "step": 2101 + }, + { + "epoch": 0.18, + "learning_rate": 1.8905077278938524e-05, + "loss": 0.5007, + "step": 2102 + }, + { + "epoch": 0.18, + "learning_rate": 1.890384403168891e-05, + "loss": 0.5164, + "step": 2103 + }, + { + "epoch": 0.18, + "learning_rate": 1.890261013057802e-05, + "loss": 0.5046, + "step": 2104 + }, + { + "epoch": 0.18, + "learning_rate": 1.8901375575696476e-05, + "loss": 0.5137, + "step": 2105 + }, + { + "epoch": 0.18, + "learning_rate": 1.890014036713493e-05, + "loss": 0.5103, + "step": 2106 + }, + { + "epoch": 0.18, + "learning_rate": 1.8898904504984096e-05, + "loss": 0.5071, + "step": 2107 + }, + { + "epoch": 0.18, + "learning_rate": 1.8897667989334726e-05, + "loss": 0.5271, + "step": 2108 + }, + { + "epoch": 0.18, + "learning_rate": 1.889643082027763e-05, + "loss": 0.5044, + "step": 2109 + }, + { + "epoch": 0.18, + "learning_rate": 1.8895192997903657e-05, + "loss": 0.4989, + "step": 2110 + }, + { + "epoch": 0.18, + "learning_rate": 1.8893954522303707e-05, + "loss": 0.5072, + "step": 2111 + }, + { + "epoch": 0.18, + "learning_rate": 1.889271539356873e-05, + "loss": 0.4782, + "step": 2112 + }, + { + "epoch": 0.18, + "learning_rate": 1.889147561178972e-05, + "loss": 0.4853, + "step": 2113 + }, + { + "epoch": 0.18, + "learning_rate": 1.889023517705773e-05, + "loss": 0.5108, + "step": 2114 + }, + { + "epoch": 0.18, + "learning_rate": 1.888899408946384e-05, + "loss": 0.5195, + "step": 2115 + }, + { + "epoch": 0.18, + "learning_rate": 1.88877523490992e-05, + "loss": 0.4972, + "step": 2116 + }, + { + "epoch": 0.18, + "learning_rate": 1.888650995605499e-05, + "loss": 0.4881, + "step": 2117 + }, + { + "epoch": 0.18, + "learning_rate": 1.8885266910422454e-05, + "loss": 0.4766, + "step": 2118 + }, + { + "epoch": 0.18, + "learning_rate": 1.888402321229287e-05, + "loss": 0.4896, + "step": 2119 + }, + { + "epoch": 0.18, + "learning_rate": 1.8882778861757573e-05, + "loss": 0.5269, + "step": 2120 + }, + { + "epoch": 0.18, + "learning_rate": 1.8881533858907945e-05, + "loss": 0.5108, + "step": 2121 + }, + { + "epoch": 0.18, + "learning_rate": 1.888028820383541e-05, + "loss": 0.5037, + "step": 2122 + }, + { + "epoch": 0.18, + "learning_rate": 1.8879041896631448e-05, + "loss": 0.4973, + "step": 2123 + }, + { + "epoch": 0.18, + "learning_rate": 1.8877794937387576e-05, + "loss": 0.5348, + "step": 2124 + }, + { + "epoch": 0.18, + "learning_rate": 1.8876547326195373e-05, + "loss": 0.5247, + "step": 2125 + }, + { + "epoch": 0.18, + "learning_rate": 1.887529906314645e-05, + "loss": 0.5148, + "step": 2126 + }, + { + "epoch": 0.18, + "learning_rate": 1.8874050148332484e-05, + "loss": 0.5, + "step": 2127 + }, + { + "epoch": 0.18, + "learning_rate": 1.887280058184518e-05, + "loss": 0.4996, + "step": 2128 + }, + { + "epoch": 0.18, + "learning_rate": 1.8871550363776308e-05, + "loss": 0.5084, + "step": 2129 + }, + { + "epoch": 0.18, + "learning_rate": 1.8870299494217675e-05, + "loss": 0.5191, + "step": 2130 + }, + { + "epoch": 0.18, + "learning_rate": 1.8869047973261148e-05, + "loss": 0.5196, + "step": 2131 + }, + { + "epoch": 0.18, + "learning_rate": 1.8867795800998623e-05, + "loss": 0.5111, + "step": 2132 + }, + { + "epoch": 0.18, + "learning_rate": 1.8866542977522057e-05, + "loss": 0.4926, + "step": 2133 + }, + { + "epoch": 0.18, + "learning_rate": 1.8865289502923455e-05, + "loss": 0.5095, + "step": 2134 + }, + { + "epoch": 0.18, + "learning_rate": 1.8864035377294865e-05, + "loss": 0.5105, + "step": 2135 + }, + { + "epoch": 0.18, + "learning_rate": 1.8862780600728384e-05, + "loss": 0.507, + "step": 2136 + }, + { + "epoch": 0.18, + "learning_rate": 1.886152517331616e-05, + "loss": 0.486, + "step": 2137 + }, + { + "epoch": 0.18, + "learning_rate": 1.8860269095150387e-05, + "loss": 0.5058, + "step": 2138 + }, + { + "epoch": 0.18, + "learning_rate": 1.88590123663233e-05, + "loss": 0.4886, + "step": 2139 + }, + { + "epoch": 0.18, + "learning_rate": 1.8857754986927196e-05, + "loss": 0.5001, + "step": 2140 + }, + { + "epoch": 0.18, + "learning_rate": 1.8856496957054406e-05, + "loss": 0.5071, + "step": 2141 + }, + { + "epoch": 0.18, + "learning_rate": 1.8855238276797315e-05, + "loss": 0.5145, + "step": 2142 + }, + { + "epoch": 0.18, + "learning_rate": 1.885397894624836e-05, + "loss": 0.5025, + "step": 2143 + }, + { + "epoch": 0.18, + "learning_rate": 1.8852718965500018e-05, + "loss": 0.4977, + "step": 2144 + }, + { + "epoch": 0.18, + "learning_rate": 1.8851458334644814e-05, + "loss": 0.4879, + "step": 2145 + }, + { + "epoch": 0.18, + "learning_rate": 1.8850197053775326e-05, + "loss": 0.499, + "step": 2146 + }, + { + "epoch": 0.18, + "learning_rate": 1.8848935122984177e-05, + "loss": 0.4959, + "step": 2147 + }, + { + "epoch": 0.18, + "learning_rate": 1.884767254236404e-05, + "loss": 0.4981, + "step": 2148 + }, + { + "epoch": 0.18, + "learning_rate": 1.884640931200763e-05, + "loss": 0.5005, + "step": 2149 + }, + { + "epoch": 0.18, + "learning_rate": 1.8845145432007715e-05, + "loss": 0.4988, + "step": 2150 + }, + { + "epoch": 0.18, + "learning_rate": 1.884388090245711e-05, + "loss": 0.4929, + "step": 2151 + }, + { + "epoch": 0.18, + "learning_rate": 1.8842615723448678e-05, + "loss": 0.5127, + "step": 2152 + }, + { + "epoch": 0.18, + "learning_rate": 1.884134989507532e-05, + "loss": 0.5139, + "step": 2153 + }, + { + "epoch": 0.18, + "learning_rate": 1.8840083417430003e-05, + "loss": 0.4953, + "step": 2154 + }, + { + "epoch": 0.18, + "learning_rate": 1.8838816290605732e-05, + "loss": 0.5164, + "step": 2155 + }, + { + "epoch": 0.18, + "learning_rate": 1.883754851469555e-05, + "loss": 0.5008, + "step": 2156 + }, + { + "epoch": 0.18, + "learning_rate": 1.883628008979257e-05, + "loss": 0.4822, + "step": 2157 + }, + { + "epoch": 0.18, + "learning_rate": 1.8835011015989927e-05, + "loss": 0.5138, + "step": 2158 + }, + { + "epoch": 0.18, + "learning_rate": 1.8833741293380826e-05, + "loss": 0.5049, + "step": 2159 + }, + { + "epoch": 0.18, + "learning_rate": 1.883247092205851e-05, + "loss": 0.5085, + "step": 2160 + }, + { + "epoch": 0.18, + "learning_rate": 1.883119990211626e-05, + "loss": 0.4884, + "step": 2161 + }, + { + "epoch": 0.18, + "learning_rate": 1.8829928233647422e-05, + "loss": 0.5028, + "step": 2162 + }, + { + "epoch": 0.18, + "learning_rate": 1.8828655916745383e-05, + "loss": 0.5221, + "step": 2163 + }, + { + "epoch": 0.18, + "learning_rate": 1.8827382951503575e-05, + "loss": 0.5228, + "step": 2164 + }, + { + "epoch": 0.18, + "learning_rate": 1.8826109338015478e-05, + "loss": 0.5035, + "step": 2165 + }, + { + "epoch": 0.18, + "learning_rate": 1.8824835076374622e-05, + "loss": 0.4917, + "step": 2166 + }, + { + "epoch": 0.18, + "learning_rate": 1.882356016667458e-05, + "loss": 0.5087, + "step": 2167 + }, + { + "epoch": 0.18, + "learning_rate": 1.8822284609008985e-05, + "loss": 0.4921, + "step": 2168 + }, + { + "epoch": 0.18, + "learning_rate": 1.8821008403471497e-05, + "loss": 0.5027, + "step": 2169 + }, + { + "epoch": 0.18, + "learning_rate": 1.8819731550155845e-05, + "loss": 0.5117, + "step": 2170 + }, + { + "epoch": 0.18, + "learning_rate": 1.8818454049155792e-05, + "loss": 0.4992, + "step": 2171 + }, + { + "epoch": 0.18, + "learning_rate": 1.881717590056515e-05, + "loss": 0.4923, + "step": 2172 + }, + { + "epoch": 0.18, + "learning_rate": 1.8815897104477786e-05, + "loss": 0.4898, + "step": 2173 + }, + { + "epoch": 0.18, + "learning_rate": 1.8814617660987603e-05, + "loss": 0.523, + "step": 2174 + }, + { + "epoch": 0.18, + "learning_rate": 1.881333757018857e-05, + "loss": 0.5144, + "step": 2175 + }, + { + "epoch": 0.18, + "learning_rate": 1.8812056832174673e-05, + "loss": 0.4931, + "step": 2176 + }, + { + "epoch": 0.18, + "learning_rate": 1.881077544703998e-05, + "loss": 0.4996, + "step": 2177 + }, + { + "epoch": 0.18, + "learning_rate": 1.8809493414878585e-05, + "loss": 0.4943, + "step": 2178 + }, + { + "epoch": 0.18, + "learning_rate": 1.880821073578463e-05, + "loss": 0.4915, + "step": 2179 + }, + { + "epoch": 0.18, + "learning_rate": 1.8806927409852323e-05, + "loss": 0.5129, + "step": 2180 + }, + { + "epoch": 0.18, + "learning_rate": 1.8805643437175892e-05, + "loss": 0.4973, + "step": 2181 + }, + { + "epoch": 0.18, + "learning_rate": 1.8804358817849634e-05, + "loss": 0.4808, + "step": 2182 + }, + { + "epoch": 0.18, + "learning_rate": 1.8803073551967884e-05, + "loss": 0.5014, + "step": 2183 + }, + { + "epoch": 0.18, + "learning_rate": 1.8801787639625025e-05, + "loss": 0.5324, + "step": 2184 + }, + { + "epoch": 0.18, + "learning_rate": 1.8800501080915496e-05, + "loss": 0.4964, + "step": 2185 + }, + { + "epoch": 0.18, + "learning_rate": 1.879921387593377e-05, + "loss": 0.5127, + "step": 2186 + }, + { + "epoch": 0.18, + "learning_rate": 1.8797926024774375e-05, + "loss": 0.5176, + "step": 2187 + }, + { + "epoch": 0.18, + "learning_rate": 1.8796637527531883e-05, + "loss": 0.5158, + "step": 2188 + }, + { + "epoch": 0.18, + "learning_rate": 1.8795348384300922e-05, + "loss": 0.5075, + "step": 2189 + }, + { + "epoch": 0.18, + "learning_rate": 1.879405859517616e-05, + "loss": 0.4952, + "step": 2190 + }, + { + "epoch": 0.18, + "learning_rate": 1.8792768160252308e-05, + "loss": 0.5071, + "step": 2191 + }, + { + "epoch": 0.18, + "learning_rate": 1.8791477079624138e-05, + "loss": 0.5143, + "step": 2192 + }, + { + "epoch": 0.18, + "learning_rate": 1.8790185353386453e-05, + "loss": 0.4903, + "step": 2193 + }, + { + "epoch": 0.18, + "learning_rate": 1.878889298163412e-05, + "loss": 0.5099, + "step": 2194 + }, + { + "epoch": 0.18, + "learning_rate": 1.8787599964462044e-05, + "loss": 0.5002, + "step": 2195 + }, + { + "epoch": 0.18, + "learning_rate": 1.8786306301965175e-05, + "loss": 0.4997, + "step": 2196 + }, + { + "epoch": 0.18, + "learning_rate": 1.8785011994238516e-05, + "loss": 0.5037, + "step": 2197 + }, + { + "epoch": 0.18, + "learning_rate": 1.8783717041377113e-05, + "loss": 0.5111, + "step": 2198 + }, + { + "epoch": 0.18, + "learning_rate": 1.8782421443476072e-05, + "loss": 0.4795, + "step": 2199 + }, + { + "epoch": 0.18, + "learning_rate": 1.878112520063052e-05, + "loss": 0.4958, + "step": 2200 + }, + { + "epoch": 0.18, + "learning_rate": 1.8779828312935664e-05, + "loss": 0.5096, + "step": 2201 + }, + { + "epoch": 0.18, + "learning_rate": 1.877853078048673e-05, + "loss": 0.5011, + "step": 2202 + }, + { + "epoch": 0.18, + "learning_rate": 1.8777232603379012e-05, + "loss": 0.5011, + "step": 2203 + }, + { + "epoch": 0.18, + "learning_rate": 1.8775933781707836e-05, + "loss": 0.4967, + "step": 2204 + }, + { + "epoch": 0.18, + "learning_rate": 1.8774634315568583e-05, + "loss": 0.5074, + "step": 2205 + }, + { + "epoch": 0.18, + "learning_rate": 1.8773334205056687e-05, + "loss": 0.4919, + "step": 2206 + }, + { + "epoch": 0.18, + "learning_rate": 1.8772033450267617e-05, + "loss": 0.5044, + "step": 2207 + }, + { + "epoch": 0.18, + "learning_rate": 1.8770732051296895e-05, + "loss": 0.5007, + "step": 2208 + }, + { + "epoch": 0.18, + "learning_rate": 1.876943000824009e-05, + "loss": 0.5067, + "step": 2209 + }, + { + "epoch": 0.18, + "learning_rate": 1.8768127321192825e-05, + "loss": 0.4923, + "step": 2210 + }, + { + "epoch": 0.18, + "learning_rate": 1.8766823990250756e-05, + "loss": 0.4937, + "step": 2211 + }, + { + "epoch": 0.19, + "learning_rate": 1.8765520015509597e-05, + "loss": 0.5473, + "step": 2212 + }, + { + "epoch": 0.19, + "learning_rate": 1.8764215397065105e-05, + "loss": 0.5043, + "step": 2213 + }, + { + "epoch": 0.19, + "learning_rate": 1.8762910135013088e-05, + "loss": 0.4941, + "step": 2214 + }, + { + "epoch": 0.19, + "learning_rate": 1.8761604229449402e-05, + "loss": 0.5032, + "step": 2215 + }, + { + "epoch": 0.19, + "learning_rate": 1.8760297680469938e-05, + "loss": 0.4992, + "step": 2216 + }, + { + "epoch": 0.19, + "learning_rate": 1.875899048817065e-05, + "loss": 0.4925, + "step": 2217 + }, + { + "epoch": 0.19, + "learning_rate": 1.8757682652647538e-05, + "loss": 0.5178, + "step": 2218 + }, + { + "epoch": 0.19, + "learning_rate": 1.875637417399663e-05, + "loss": 0.5141, + "step": 2219 + }, + { + "epoch": 0.19, + "learning_rate": 1.875506505231403e-05, + "loss": 0.4848, + "step": 2220 + }, + { + "epoch": 0.19, + "learning_rate": 1.8753755287695866e-05, + "loss": 0.4989, + "step": 2221 + }, + { + "epoch": 0.19, + "learning_rate": 1.875244488023832e-05, + "loss": 0.4951, + "step": 2222 + }, + { + "epoch": 0.19, + "learning_rate": 1.875113383003763e-05, + "loss": 0.4867, + "step": 2223 + }, + { + "epoch": 0.19, + "learning_rate": 1.8749822137190065e-05, + "loss": 0.4955, + "step": 2224 + }, + { + "epoch": 0.19, + "learning_rate": 1.8748509801791962e-05, + "loss": 0.514, + "step": 2225 + }, + { + "epoch": 0.19, + "learning_rate": 1.874719682393968e-05, + "loss": 0.4934, + "step": 2226 + }, + { + "epoch": 0.19, + "learning_rate": 1.8745883203729648e-05, + "loss": 0.504, + "step": 2227 + }, + { + "epoch": 0.19, + "learning_rate": 1.8744568941258335e-05, + "loss": 0.5041, + "step": 2228 + }, + { + "epoch": 0.19, + "learning_rate": 1.8743254036622243e-05, + "loss": 0.4908, + "step": 2229 + }, + { + "epoch": 0.19, + "learning_rate": 1.874193848991795e-05, + "loss": 0.5062, + "step": 2230 + }, + { + "epoch": 0.19, + "learning_rate": 1.8740622301242045e-05, + "loss": 0.5084, + "step": 2231 + }, + { + "epoch": 0.19, + "learning_rate": 1.8739305470691197e-05, + "loss": 0.4935, + "step": 2232 + }, + { + "epoch": 0.19, + "learning_rate": 1.8737987998362106e-05, + "loss": 0.4952, + "step": 2233 + }, + { + "epoch": 0.19, + "learning_rate": 1.8736669884351523e-05, + "loss": 0.5139, + "step": 2234 + }, + { + "epoch": 0.19, + "learning_rate": 1.8735351128756238e-05, + "loss": 0.4954, + "step": 2235 + }, + { + "epoch": 0.19, + "learning_rate": 1.8734031731673096e-05, + "loss": 0.5215, + "step": 2236 + }, + { + "epoch": 0.19, + "learning_rate": 1.8732711693199e-05, + "loss": 0.5039, + "step": 2237 + }, + { + "epoch": 0.19, + "learning_rate": 1.873139101343087e-05, + "loss": 0.5171, + "step": 2238 + }, + { + "epoch": 0.19, + "learning_rate": 1.8730069692465708e-05, + "loss": 0.4796, + "step": 2239 + }, + { + "epoch": 0.19, + "learning_rate": 1.8728747730400533e-05, + "loss": 0.5093, + "step": 2240 + }, + { + "epoch": 0.19, + "learning_rate": 1.872742512733243e-05, + "loss": 0.5096, + "step": 2241 + }, + { + "epoch": 0.19, + "learning_rate": 1.8726101883358534e-05, + "loss": 0.4824, + "step": 2242 + }, + { + "epoch": 0.19, + "learning_rate": 1.8724777998576006e-05, + "loss": 0.5057, + "step": 2243 + }, + { + "epoch": 0.19, + "learning_rate": 1.872345347308207e-05, + "loss": 0.5089, + "step": 2244 + }, + { + "epoch": 0.19, + "learning_rate": 1.872212830697399e-05, + "loss": 0.501, + "step": 2245 + }, + { + "epoch": 0.19, + "learning_rate": 1.8720802500349095e-05, + "loss": 0.5236, + "step": 2246 + }, + { + "epoch": 0.19, + "learning_rate": 1.871947605330473e-05, + "loss": 0.5291, + "step": 2247 + }, + { + "epoch": 0.19, + "learning_rate": 1.8718148965938312e-05, + "loss": 0.5228, + "step": 2248 + }, + { + "epoch": 0.19, + "learning_rate": 1.8716821238347296e-05, + "loss": 0.4989, + "step": 2249 + }, + { + "epoch": 0.19, + "learning_rate": 1.8715492870629183e-05, + "loss": 0.4978, + "step": 2250 + }, + { + "epoch": 0.19, + "learning_rate": 1.8714163862881527e-05, + "loss": 0.4955, + "step": 2251 + }, + { + "epoch": 0.19, + "learning_rate": 1.8712834215201918e-05, + "loss": 0.5113, + "step": 2252 + }, + { + "epoch": 0.19, + "learning_rate": 1.8711503927688007e-05, + "loss": 0.5227, + "step": 2253 + }, + { + "epoch": 0.19, + "learning_rate": 1.871017300043748e-05, + "loss": 0.5006, + "step": 2254 + }, + { + "epoch": 0.19, + "learning_rate": 1.8708841433548076e-05, + "loss": 0.5215, + "step": 2255 + }, + { + "epoch": 0.19, + "learning_rate": 1.8707509227117578e-05, + "loss": 0.5261, + "step": 2256 + }, + { + "epoch": 0.19, + "learning_rate": 1.8706176381243822e-05, + "loss": 0.5057, + "step": 2257 + }, + { + "epoch": 0.19, + "learning_rate": 1.8704842896024685e-05, + "loss": 0.4915, + "step": 2258 + }, + { + "epoch": 0.19, + "learning_rate": 1.8703508771558093e-05, + "loss": 0.4977, + "step": 2259 + }, + { + "epoch": 0.19, + "learning_rate": 1.8702174007942012e-05, + "loss": 0.4921, + "step": 2260 + }, + { + "epoch": 0.19, + "learning_rate": 1.870083860527447e-05, + "loss": 0.4881, + "step": 2261 + }, + { + "epoch": 0.19, + "learning_rate": 1.869950256365353e-05, + "loss": 0.5051, + "step": 2262 + }, + { + "epoch": 0.19, + "learning_rate": 1.8698165883177308e-05, + "loss": 0.5007, + "step": 2263 + }, + { + "epoch": 0.19, + "learning_rate": 1.8696828563943962e-05, + "loss": 0.5076, + "step": 2264 + }, + { + "epoch": 0.19, + "learning_rate": 1.8695490606051694e-05, + "loss": 0.4853, + "step": 2265 + }, + { + "epoch": 0.19, + "learning_rate": 1.8694152009598767e-05, + "loss": 0.5068, + "step": 2266 + }, + { + "epoch": 0.19, + "learning_rate": 1.8692812774683477e-05, + "loss": 0.4871, + "step": 2267 + }, + { + "epoch": 0.19, + "learning_rate": 1.8691472901404174e-05, + "loss": 0.4977, + "step": 2268 + }, + { + "epoch": 0.19, + "learning_rate": 1.8690132389859254e-05, + "loss": 0.4994, + "step": 2269 + }, + { + "epoch": 0.19, + "learning_rate": 1.868879124014715e-05, + "loss": 0.4928, + "step": 2270 + }, + { + "epoch": 0.19, + "learning_rate": 1.8687449452366362e-05, + "loss": 0.5154, + "step": 2271 + }, + { + "epoch": 0.19, + "learning_rate": 1.8686107026615418e-05, + "loss": 0.5094, + "step": 2272 + }, + { + "epoch": 0.19, + "learning_rate": 1.8684763962992903e-05, + "loss": 0.4799, + "step": 2273 + }, + { + "epoch": 0.19, + "learning_rate": 1.8683420261597445e-05, + "loss": 0.5091, + "step": 2274 + }, + { + "epoch": 0.19, + "learning_rate": 1.8682075922527717e-05, + "loss": 0.5067, + "step": 2275 + }, + { + "epoch": 0.19, + "learning_rate": 1.868073094588245e-05, + "loss": 0.5016, + "step": 2276 + }, + { + "epoch": 0.19, + "learning_rate": 1.8679385331760405e-05, + "loss": 0.5159, + "step": 2277 + }, + { + "epoch": 0.19, + "learning_rate": 1.8678039080260403e-05, + "loss": 0.5221, + "step": 2278 + }, + { + "epoch": 0.19, + "learning_rate": 1.8676692191481303e-05, + "loss": 0.4992, + "step": 2279 + }, + { + "epoch": 0.19, + "learning_rate": 1.867534466552202e-05, + "loss": 0.5096, + "step": 2280 + }, + { + "epoch": 0.19, + "learning_rate": 1.8673996502481507e-05, + "loss": 0.5064, + "step": 2281 + }, + { + "epoch": 0.19, + "learning_rate": 1.867264770245877e-05, + "loss": 0.4879, + "step": 2282 + }, + { + "epoch": 0.19, + "learning_rate": 1.8671298265552855e-05, + "loss": 0.5101, + "step": 2283 + }, + { + "epoch": 0.19, + "learning_rate": 1.8669948191862866e-05, + "loss": 0.5155, + "step": 2284 + }, + { + "epoch": 0.19, + "learning_rate": 1.866859748148794e-05, + "loss": 0.5111, + "step": 2285 + }, + { + "epoch": 0.19, + "learning_rate": 1.866724613452727e-05, + "loss": 0.4805, + "step": 2286 + }, + { + "epoch": 0.19, + "learning_rate": 1.8665894151080097e-05, + "loss": 0.5088, + "step": 2287 + }, + { + "epoch": 0.19, + "learning_rate": 1.8664541531245698e-05, + "loss": 0.5163, + "step": 2288 + }, + { + "epoch": 0.19, + "learning_rate": 1.866318827512341e-05, + "loss": 0.5177, + "step": 2289 + }, + { + "epoch": 0.19, + "learning_rate": 1.8661834382812608e-05, + "loss": 0.4867, + "step": 2290 + }, + { + "epoch": 0.19, + "learning_rate": 1.8660479854412713e-05, + "loss": 0.5183, + "step": 2291 + }, + { + "epoch": 0.19, + "learning_rate": 1.8659124690023205e-05, + "loss": 0.4917, + "step": 2292 + }, + { + "epoch": 0.19, + "learning_rate": 1.865776888974359e-05, + "loss": 0.5098, + "step": 2293 + }, + { + "epoch": 0.19, + "learning_rate": 1.865641245367344e-05, + "loss": 0.4977, + "step": 2294 + }, + { + "epoch": 0.19, + "learning_rate": 1.8655055381912367e-05, + "loss": 0.5151, + "step": 2295 + }, + { + "epoch": 0.19, + "learning_rate": 1.8653697674560023e-05, + "loss": 0.524, + "step": 2296 + }, + { + "epoch": 0.19, + "learning_rate": 1.8652339331716114e-05, + "loss": 0.4991, + "step": 2297 + }, + { + "epoch": 0.19, + "learning_rate": 1.8650980353480395e-05, + "loss": 0.5015, + "step": 2298 + }, + { + "epoch": 0.19, + "learning_rate": 1.8649620739952658e-05, + "loss": 0.5034, + "step": 2299 + }, + { + "epoch": 0.19, + "learning_rate": 1.8648260491232753e-05, + "loss": 0.4985, + "step": 2300 + }, + { + "epoch": 0.19, + "learning_rate": 1.8646899607420567e-05, + "loss": 0.4961, + "step": 2301 + }, + { + "epoch": 0.19, + "learning_rate": 1.8645538088616038e-05, + "loss": 0.5044, + "step": 2302 + }, + { + "epoch": 0.19, + "learning_rate": 1.8644175934919156e-05, + "loss": 0.5092, + "step": 2303 + }, + { + "epoch": 0.19, + "learning_rate": 1.8642813146429943e-05, + "loss": 0.5069, + "step": 2304 + }, + { + "epoch": 0.19, + "learning_rate": 1.8641449723248482e-05, + "loss": 0.5064, + "step": 2305 + }, + { + "epoch": 0.19, + "learning_rate": 1.8640085665474898e-05, + "loss": 0.5085, + "step": 2306 + }, + { + "epoch": 0.19, + "learning_rate": 1.8638720973209353e-05, + "loss": 0.5056, + "step": 2307 + }, + { + "epoch": 0.19, + "learning_rate": 1.863735564655208e-05, + "loss": 0.4973, + "step": 2308 + }, + { + "epoch": 0.19, + "learning_rate": 1.8635989685603327e-05, + "loss": 0.5089, + "step": 2309 + }, + { + "epoch": 0.19, + "learning_rate": 1.8634623090463413e-05, + "loss": 0.4941, + "step": 2310 + }, + { + "epoch": 0.19, + "learning_rate": 1.8633255861232692e-05, + "loss": 0.4903, + "step": 2311 + }, + { + "epoch": 0.19, + "learning_rate": 1.863188799801157e-05, + "loss": 0.5029, + "step": 2312 + }, + { + "epoch": 0.19, + "learning_rate": 1.8630519500900495e-05, + "loss": 0.4915, + "step": 2313 + }, + { + "epoch": 0.19, + "learning_rate": 1.8629150369999967e-05, + "loss": 0.4913, + "step": 2314 + }, + { + "epoch": 0.19, + "learning_rate": 1.8627780605410528e-05, + "loss": 0.5075, + "step": 2315 + }, + { + "epoch": 0.19, + "learning_rate": 1.8626410207232762e-05, + "loss": 0.4993, + "step": 2316 + }, + { + "epoch": 0.19, + "learning_rate": 1.8625039175567316e-05, + "loss": 0.5164, + "step": 2317 + }, + { + "epoch": 0.19, + "learning_rate": 1.8623667510514867e-05, + "loss": 0.4919, + "step": 2318 + }, + { + "epoch": 0.19, + "learning_rate": 1.8622295212176142e-05, + "loss": 0.5125, + "step": 2319 + }, + { + "epoch": 0.19, + "learning_rate": 1.862092228065192e-05, + "loss": 0.5005, + "step": 2320 + }, + { + "epoch": 0.19, + "learning_rate": 1.861954871604302e-05, + "loss": 0.4824, + "step": 2321 + }, + { + "epoch": 0.19, + "learning_rate": 1.8618174518450317e-05, + "loss": 0.4943, + "step": 2322 + }, + { + "epoch": 0.19, + "learning_rate": 1.8616799687974724e-05, + "loss": 0.5029, + "step": 2323 + }, + { + "epoch": 0.19, + "learning_rate": 1.86154242247172e-05, + "loss": 0.4923, + "step": 2324 + }, + { + "epoch": 0.19, + "learning_rate": 1.8614048128778755e-05, + "loss": 0.5028, + "step": 2325 + }, + { + "epoch": 0.19, + "learning_rate": 1.8612671400260445e-05, + "loss": 0.4956, + "step": 2326 + }, + { + "epoch": 0.19, + "learning_rate": 1.861129403926337e-05, + "loss": 0.5067, + "step": 2327 + }, + { + "epoch": 0.19, + "learning_rate": 1.8609916045888677e-05, + "loss": 0.4775, + "step": 2328 + }, + { + "epoch": 0.19, + "learning_rate": 1.860853742023756e-05, + "loss": 0.4859, + "step": 2329 + }, + { + "epoch": 0.19, + "learning_rate": 1.860715816241126e-05, + "loss": 0.5, + "step": 2330 + }, + { + "epoch": 0.2, + "learning_rate": 1.860577827251107e-05, + "loss": 0.5103, + "step": 2331 + }, + { + "epoch": 0.2, + "learning_rate": 1.8604397750638314e-05, + "loss": 0.5085, + "step": 2332 + }, + { + "epoch": 0.2, + "learning_rate": 1.8603016596894375e-05, + "loss": 0.4992, + "step": 2333 + }, + { + "epoch": 0.2, + "learning_rate": 1.860163481138068e-05, + "loss": 0.5093, + "step": 2334 + }, + { + "epoch": 0.2, + "learning_rate": 1.8600252394198702e-05, + "loss": 0.5172, + "step": 2335 + }, + { + "epoch": 0.2, + "learning_rate": 1.8598869345449957e-05, + "loss": 0.4971, + "step": 2336 + }, + { + "epoch": 0.2, + "learning_rate": 1.8597485665236016e-05, + "loss": 0.5007, + "step": 2337 + }, + { + "epoch": 0.2, + "learning_rate": 1.8596101353658488e-05, + "loss": 0.4957, + "step": 2338 + }, + { + "epoch": 0.2, + "learning_rate": 1.8594716410819027e-05, + "loss": 0.4941, + "step": 2339 + }, + { + "epoch": 0.2, + "learning_rate": 1.8593330836819342e-05, + "loss": 0.4833, + "step": 2340 + }, + { + "epoch": 0.2, + "learning_rate": 1.8591944631761185e-05, + "loss": 0.4959, + "step": 2341 + }, + { + "epoch": 0.2, + "learning_rate": 1.859055779574635e-05, + "loss": 0.5065, + "step": 2342 + }, + { + "epoch": 0.2, + "learning_rate": 1.858917032887668e-05, + "loss": 0.5085, + "step": 2343 + }, + { + "epoch": 0.2, + "learning_rate": 1.8587782231254065e-05, + "loss": 0.5195, + "step": 2344 + }, + { + "epoch": 0.2, + "learning_rate": 1.8586393502980442e-05, + "loss": 0.5003, + "step": 2345 + }, + { + "epoch": 0.2, + "learning_rate": 1.8585004144157798e-05, + "loss": 0.4933, + "step": 2346 + }, + { + "epoch": 0.2, + "learning_rate": 1.8583614154888154e-05, + "loss": 0.5186, + "step": 2347 + }, + { + "epoch": 0.2, + "learning_rate": 1.8582223535273587e-05, + "loss": 0.4988, + "step": 2348 + }, + { + "epoch": 0.2, + "learning_rate": 1.8580832285416223e-05, + "loss": 0.5032, + "step": 2349 + }, + { + "epoch": 0.2, + "learning_rate": 1.8579440405418222e-05, + "loss": 0.5109, + "step": 2350 + }, + { + "epoch": 0.2, + "learning_rate": 1.857804789538181e-05, + "loss": 0.503, + "step": 2351 + }, + { + "epoch": 0.2, + "learning_rate": 1.8576654755409233e-05, + "loss": 0.5101, + "step": 2352 + }, + { + "epoch": 0.2, + "learning_rate": 1.8575260985602806e-05, + "loss": 0.5242, + "step": 2353 + }, + { + "epoch": 0.2, + "learning_rate": 1.8573866586064877e-05, + "loss": 0.5165, + "step": 2354 + }, + { + "epoch": 0.2, + "learning_rate": 1.857247155689785e-05, + "loss": 0.5158, + "step": 2355 + }, + { + "epoch": 0.2, + "learning_rate": 1.8571075898204167e-05, + "loss": 0.4967, + "step": 2356 + }, + { + "epoch": 0.2, + "learning_rate": 1.856967961008632e-05, + "loss": 0.5094, + "step": 2357 + }, + { + "epoch": 0.2, + "learning_rate": 1.8568282692646844e-05, + "loss": 0.4908, + "step": 2358 + }, + { + "epoch": 0.2, + "learning_rate": 1.8566885145988326e-05, + "loss": 0.48, + "step": 2359 + }, + { + "epoch": 0.2, + "learning_rate": 1.8565486970213397e-05, + "loss": 0.5177, + "step": 2360 + }, + { + "epoch": 0.2, + "learning_rate": 1.8564088165424733e-05, + "loss": 0.496, + "step": 2361 + }, + { + "epoch": 0.2, + "learning_rate": 1.8562688731725053e-05, + "loss": 0.5195, + "step": 2362 + }, + { + "epoch": 0.2, + "learning_rate": 1.8561288669217125e-05, + "loss": 0.4852, + "step": 2363 + }, + { + "epoch": 0.2, + "learning_rate": 1.8559887978003766e-05, + "loss": 0.4954, + "step": 2364 + }, + { + "epoch": 0.2, + "learning_rate": 1.8558486658187843e-05, + "loss": 0.5074, + "step": 2365 + }, + { + "epoch": 0.2, + "learning_rate": 1.8557084709872253e-05, + "loss": 0.4885, + "step": 2366 + }, + { + "epoch": 0.2, + "learning_rate": 1.8555682133159952e-05, + "loss": 0.4868, + "step": 2367 + }, + { + "epoch": 0.2, + "learning_rate": 1.8554278928153942e-05, + "loss": 0.5194, + "step": 2368 + }, + { + "epoch": 0.2, + "learning_rate": 1.855287509495727e-05, + "loss": 0.4986, + "step": 2369 + }, + { + "epoch": 0.2, + "learning_rate": 1.8551470633673023e-05, + "loss": 0.5032, + "step": 2370 + }, + { + "epoch": 0.2, + "learning_rate": 1.855006554440434e-05, + "loss": 0.5006, + "step": 2371 + }, + { + "epoch": 0.2, + "learning_rate": 1.8548659827254408e-05, + "loss": 0.5124, + "step": 2372 + }, + { + "epoch": 0.2, + "learning_rate": 1.8547253482326458e-05, + "loss": 0.4894, + "step": 2373 + }, + { + "epoch": 0.2, + "learning_rate": 1.8545846509723757e-05, + "loss": 0.5089, + "step": 2374 + }, + { + "epoch": 0.2, + "learning_rate": 1.8544438909549636e-05, + "loss": 0.4991, + "step": 2375 + }, + { + "epoch": 0.2, + "learning_rate": 1.854303068190746e-05, + "loss": 0.5044, + "step": 2376 + }, + { + "epoch": 0.2, + "learning_rate": 1.854162182690064e-05, + "loss": 0.5011, + "step": 2377 + }, + { + "epoch": 0.2, + "learning_rate": 1.8540212344632646e-05, + "loss": 0.4879, + "step": 2378 + }, + { + "epoch": 0.2, + "learning_rate": 1.8538802235206977e-05, + "loss": 0.5249, + "step": 2379 + }, + { + "epoch": 0.2, + "learning_rate": 1.8537391498727187e-05, + "loss": 0.489, + "step": 2380 + }, + { + "epoch": 0.2, + "learning_rate": 1.8535980135296876e-05, + "loss": 0.5214, + "step": 2381 + }, + { + "epoch": 0.2, + "learning_rate": 1.8534568145019687e-05, + "loss": 0.5325, + "step": 2382 + }, + { + "epoch": 0.2, + "learning_rate": 1.853315552799931e-05, + "loss": 0.5143, + "step": 2383 + }, + { + "epoch": 0.2, + "learning_rate": 1.8531742284339486e-05, + "loss": 0.5069, + "step": 2384 + }, + { + "epoch": 0.2, + "learning_rate": 1.853032841414399e-05, + "loss": 0.4942, + "step": 2385 + }, + { + "epoch": 0.2, + "learning_rate": 1.852891391751666e-05, + "loss": 0.4831, + "step": 2386 + }, + { + "epoch": 0.2, + "learning_rate": 1.8527498794561367e-05, + "loss": 0.4999, + "step": 2387 + }, + { + "epoch": 0.2, + "learning_rate": 1.8526083045382025e-05, + "loss": 0.4998, + "step": 2388 + }, + { + "epoch": 0.2, + "learning_rate": 1.852466667008261e-05, + "loss": 0.5075, + "step": 2389 + }, + { + "epoch": 0.2, + "learning_rate": 1.8523249668767135e-05, + "loss": 0.5047, + "step": 2390 + }, + { + "epoch": 0.2, + "learning_rate": 1.852183204153965e-05, + "loss": 0.5177, + "step": 2391 + }, + { + "epoch": 0.2, + "learning_rate": 1.852041378850427e-05, + "loss": 0.486, + "step": 2392 + }, + { + "epoch": 0.2, + "learning_rate": 1.851899490976514e-05, + "loss": 0.4809, + "step": 2393 + }, + { + "epoch": 0.2, + "learning_rate": 1.851757540542645e-05, + "loss": 0.5098, + "step": 2394 + }, + { + "epoch": 0.2, + "learning_rate": 1.8516155275592457e-05, + "loss": 0.4916, + "step": 2395 + }, + { + "epoch": 0.2, + "learning_rate": 1.8514734520367438e-05, + "loss": 0.5143, + "step": 2396 + }, + { + "epoch": 0.2, + "learning_rate": 1.8513313139855734e-05, + "loss": 0.4984, + "step": 2397 + }, + { + "epoch": 0.2, + "learning_rate": 1.8511891134161718e-05, + "loss": 0.4834, + "step": 2398 + }, + { + "epoch": 0.2, + "learning_rate": 1.8510468503389825e-05, + "loss": 0.4972, + "step": 2399 + }, + { + "epoch": 0.2, + "learning_rate": 1.8509045247644524e-05, + "loss": 0.4988, + "step": 2400 + }, + { + "epoch": 0.2, + "learning_rate": 1.8507621367030326e-05, + "loss": 0.5079, + "step": 2401 + }, + { + "epoch": 0.2, + "learning_rate": 1.8506196861651802e-05, + "loss": 0.514, + "step": 2402 + }, + { + "epoch": 0.2, + "learning_rate": 1.8504771731613568e-05, + "loss": 0.4905, + "step": 2403 + }, + { + "epoch": 0.2, + "learning_rate": 1.8503345977020262e-05, + "loss": 0.5006, + "step": 2404 + }, + { + "epoch": 0.2, + "learning_rate": 1.8501919597976602e-05, + "loss": 0.4949, + "step": 2405 + }, + { + "epoch": 0.2, + "learning_rate": 1.850049259458733e-05, + "loss": 0.5129, + "step": 2406 + }, + { + "epoch": 0.2, + "learning_rate": 1.8499064966957233e-05, + "loss": 0.498, + "step": 2407 + }, + { + "epoch": 0.2, + "learning_rate": 1.8497636715191153e-05, + "loss": 0.499, + "step": 2408 + }, + { + "epoch": 0.2, + "learning_rate": 1.8496207839393984e-05, + "loss": 0.4932, + "step": 2409 + }, + { + "epoch": 0.2, + "learning_rate": 1.849477833967065e-05, + "loss": 0.5081, + "step": 2410 + }, + { + "epoch": 0.2, + "learning_rate": 1.849334821612612e-05, + "loss": 0.497, + "step": 2411 + }, + { + "epoch": 0.2, + "learning_rate": 1.8491917468865426e-05, + "loss": 0.5113, + "step": 2412 + }, + { + "epoch": 0.2, + "learning_rate": 1.8490486097993635e-05, + "loss": 0.5037, + "step": 2413 + }, + { + "epoch": 0.2, + "learning_rate": 1.848905410361586e-05, + "loss": 0.4858, + "step": 2414 + }, + { + "epoch": 0.2, + "learning_rate": 1.848762148583726e-05, + "loss": 0.4957, + "step": 2415 + }, + { + "epoch": 0.2, + "learning_rate": 1.8486188244763038e-05, + "loss": 0.5217, + "step": 2416 + }, + { + "epoch": 0.2, + "learning_rate": 1.8484754380498452e-05, + "loss": 0.496, + "step": 2417 + }, + { + "epoch": 0.2, + "learning_rate": 1.8483319893148794e-05, + "loss": 0.4957, + "step": 2418 + }, + { + "epoch": 0.2, + "learning_rate": 1.848188478281941e-05, + "loss": 0.4935, + "step": 2419 + }, + { + "epoch": 0.2, + "learning_rate": 1.8480449049615684e-05, + "loss": 0.4964, + "step": 2420 + }, + { + "epoch": 0.2, + "learning_rate": 1.847901269364305e-05, + "loss": 0.4948, + "step": 2421 + }, + { + "epoch": 0.2, + "learning_rate": 1.847757571500699e-05, + "loss": 0.4968, + "step": 2422 + }, + { + "epoch": 0.2, + "learning_rate": 1.8476138113813037e-05, + "loss": 0.5153, + "step": 2423 + }, + { + "epoch": 0.2, + "learning_rate": 1.8474699890166753e-05, + "loss": 0.513, + "step": 2424 + }, + { + "epoch": 0.2, + "learning_rate": 1.8473261044173756e-05, + "loss": 0.5264, + "step": 2425 + }, + { + "epoch": 0.2, + "learning_rate": 1.8471821575939713e-05, + "loss": 0.4933, + "step": 2426 + }, + { + "epoch": 0.2, + "learning_rate": 1.8470381485570327e-05, + "loss": 0.5192, + "step": 2427 + }, + { + "epoch": 0.2, + "learning_rate": 1.8468940773171357e-05, + "loss": 0.4959, + "step": 2428 + }, + { + "epoch": 0.2, + "learning_rate": 1.8467499438848606e-05, + "loss": 0.5083, + "step": 2429 + }, + { + "epoch": 0.2, + "learning_rate": 1.846605748270791e-05, + "loss": 0.5058, + "step": 2430 + }, + { + "epoch": 0.2, + "learning_rate": 1.8464614904855168e-05, + "loss": 0.5126, + "step": 2431 + }, + { + "epoch": 0.2, + "learning_rate": 1.8463171705396313e-05, + "loss": 0.5123, + "step": 2432 + }, + { + "epoch": 0.2, + "learning_rate": 1.846172788443733e-05, + "loss": 0.4949, + "step": 2433 + }, + { + "epoch": 0.2, + "learning_rate": 1.8460283442084246e-05, + "loss": 0.497, + "step": 2434 + }, + { + "epoch": 0.2, + "learning_rate": 1.8458838378443134e-05, + "loss": 0.5059, + "step": 2435 + }, + { + "epoch": 0.2, + "learning_rate": 1.8457392693620114e-05, + "loss": 0.5048, + "step": 2436 + }, + { + "epoch": 0.2, + "learning_rate": 1.8455946387721356e-05, + "loss": 0.518, + "step": 2437 + }, + { + "epoch": 0.2, + "learning_rate": 1.845449946085306e-05, + "loss": 0.5013, + "step": 2438 + }, + { + "epoch": 0.2, + "learning_rate": 1.8453051913121494e-05, + "loss": 0.4975, + "step": 2439 + }, + { + "epoch": 0.2, + "learning_rate": 1.8451603744632952e-05, + "loss": 0.504, + "step": 2440 + }, + { + "epoch": 0.2, + "learning_rate": 1.845015495549378e-05, + "loss": 0.5083, + "step": 2441 + }, + { + "epoch": 0.2, + "learning_rate": 1.844870554581038e-05, + "loss": 0.5114, + "step": 2442 + }, + { + "epoch": 0.2, + "learning_rate": 1.8447255515689185e-05, + "loss": 0.4908, + "step": 2443 + }, + { + "epoch": 0.2, + "learning_rate": 1.844580486523668e-05, + "loss": 0.4994, + "step": 2444 + }, + { + "epoch": 0.2, + "learning_rate": 1.8444353594559392e-05, + "loss": 0.5013, + "step": 2445 + }, + { + "epoch": 0.2, + "learning_rate": 1.84429017037639e-05, + "loss": 0.5016, + "step": 2446 + }, + { + "epoch": 0.2, + "learning_rate": 1.8441449192956823e-05, + "loss": 0.5037, + "step": 2447 + }, + { + "epoch": 0.2, + "learning_rate": 1.8439996062244828e-05, + "loss": 0.4919, + "step": 2448 + }, + { + "epoch": 0.2, + "learning_rate": 1.843854231173463e-05, + "loss": 0.4875, + "step": 2449 + }, + { + "epoch": 0.2, + "learning_rate": 1.8437087941532982e-05, + "loss": 0.4861, + "step": 2450 + }, + { + "epoch": 0.21, + "learning_rate": 1.8435632951746685e-05, + "loss": 0.5123, + "step": 2451 + }, + { + "epoch": 0.21, + "learning_rate": 1.8434177342482594e-05, + "loss": 0.4923, + "step": 2452 + }, + { + "epoch": 0.21, + "learning_rate": 1.8432721113847596e-05, + "loss": 0.5275, + "step": 2453 + }, + { + "epoch": 0.21, + "learning_rate": 1.8431264265948636e-05, + "loss": 0.529, + "step": 2454 + }, + { + "epoch": 0.21, + "learning_rate": 1.8429806798892694e-05, + "loss": 0.5048, + "step": 2455 + }, + { + "epoch": 0.21, + "learning_rate": 1.8428348712786803e-05, + "loss": 0.485, + "step": 2456 + }, + { + "epoch": 0.21, + "learning_rate": 1.842689000773804e-05, + "loss": 0.5057, + "step": 2457 + }, + { + "epoch": 0.21, + "learning_rate": 1.8425430683853527e-05, + "loss": 0.5013, + "step": 2458 + }, + { + "epoch": 0.21, + "learning_rate": 1.8423970741240426e-05, + "loss": 0.4978, + "step": 2459 + }, + { + "epoch": 0.21, + "learning_rate": 1.842251018000595e-05, + "loss": 0.4971, + "step": 2460 + }, + { + "epoch": 0.21, + "learning_rate": 1.8421049000257362e-05, + "loss": 0.5246, + "step": 2461 + }, + { + "epoch": 0.21, + "learning_rate": 1.841958720210196e-05, + "loss": 0.4989, + "step": 2462 + }, + { + "epoch": 0.21, + "learning_rate": 1.8418124785647092e-05, + "loss": 0.5098, + "step": 2463 + }, + { + "epoch": 0.21, + "learning_rate": 1.8416661751000156e-05, + "loss": 0.5075, + "step": 2464 + }, + { + "epoch": 0.21, + "learning_rate": 1.841519809826859e-05, + "loss": 0.4991, + "step": 2465 + }, + { + "epoch": 0.21, + "learning_rate": 1.8413733827559873e-05, + "loss": 0.4971, + "step": 2466 + }, + { + "epoch": 0.21, + "learning_rate": 1.841226893898154e-05, + "loss": 0.5031, + "step": 2467 + }, + { + "epoch": 0.21, + "learning_rate": 1.8410803432641165e-05, + "loss": 0.4909, + "step": 2468 + }, + { + "epoch": 0.21, + "learning_rate": 1.840933730864637e-05, + "loss": 0.5077, + "step": 2469 + }, + { + "epoch": 0.21, + "learning_rate": 1.840787056710482e-05, + "loss": 0.5273, + "step": 2470 + }, + { + "epoch": 0.21, + "learning_rate": 1.8406403208124227e-05, + "loss": 0.5063, + "step": 2471 + }, + { + "epoch": 0.21, + "learning_rate": 1.8404935231812348e-05, + "loss": 0.5041, + "step": 2472 + }, + { + "epoch": 0.21, + "learning_rate": 1.8403466638276983e-05, + "loss": 0.493, + "step": 2473 + }, + { + "epoch": 0.21, + "learning_rate": 1.840199742762598e-05, + "loss": 0.4928, + "step": 2474 + }, + { + "epoch": 0.21, + "learning_rate": 1.840052759996723e-05, + "loss": 0.506, + "step": 2475 + }, + { + "epoch": 0.21, + "learning_rate": 1.839905715540868e-05, + "loss": 0.503, + "step": 2476 + }, + { + "epoch": 0.21, + "learning_rate": 1.8397586094058303e-05, + "loss": 0.4865, + "step": 2477 + }, + { + "epoch": 0.21, + "learning_rate": 1.839611441602413e-05, + "loss": 0.4936, + "step": 2478 + }, + { + "epoch": 0.21, + "learning_rate": 1.8394642121414238e-05, + "loss": 0.501, + "step": 2479 + }, + { + "epoch": 0.21, + "learning_rate": 1.8393169210336747e-05, + "loss": 0.4826, + "step": 2480 + }, + { + "epoch": 0.21, + "learning_rate": 1.8391695682899814e-05, + "loss": 0.5122, + "step": 2481 + }, + { + "epoch": 0.21, + "learning_rate": 1.839022153921166e-05, + "loss": 0.5038, + "step": 2482 + }, + { + "epoch": 0.21, + "learning_rate": 1.8388746779380532e-05, + "loss": 0.4954, + "step": 2483 + }, + { + "epoch": 0.21, + "learning_rate": 1.838727140351473e-05, + "loss": 0.5098, + "step": 2484 + }, + { + "epoch": 0.21, + "learning_rate": 1.83857954117226e-05, + "loss": 0.4984, + "step": 2485 + }, + { + "epoch": 0.21, + "learning_rate": 1.8384318804112533e-05, + "loss": 0.5117, + "step": 2486 + }, + { + "epoch": 0.21, + "learning_rate": 1.838284158079297e-05, + "loss": 0.4905, + "step": 2487 + }, + { + "epoch": 0.21, + "learning_rate": 1.8381363741872386e-05, + "loss": 0.4969, + "step": 2488 + }, + { + "epoch": 0.21, + "learning_rate": 1.8379885287459315e-05, + "loss": 0.5055, + "step": 2489 + }, + { + "epoch": 0.21, + "learning_rate": 1.8378406217662314e-05, + "loss": 0.4903, + "step": 2490 + }, + { + "epoch": 0.21, + "learning_rate": 1.8376926532590012e-05, + "loss": 0.4854, + "step": 2491 + }, + { + "epoch": 0.21, + "learning_rate": 1.837544623235107e-05, + "loss": 0.5033, + "step": 2492 + }, + { + "epoch": 0.21, + "learning_rate": 1.8373965317054195e-05, + "loss": 0.5127, + "step": 2493 + }, + { + "epoch": 0.21, + "learning_rate": 1.8372483786808133e-05, + "loss": 0.488, + "step": 2494 + }, + { + "epoch": 0.21, + "learning_rate": 1.8371001641721685e-05, + "loss": 0.4882, + "step": 2495 + }, + { + "epoch": 0.21, + "learning_rate": 1.8369518881903698e-05, + "loss": 0.5022, + "step": 2496 + }, + { + "epoch": 0.21, + "learning_rate": 1.8368035507463053e-05, + "loss": 0.4967, + "step": 2497 + }, + { + "epoch": 0.21, + "learning_rate": 1.8366551518508685e-05, + "loss": 0.4857, + "step": 2498 + }, + { + "epoch": 0.21, + "learning_rate": 1.8365066915149573e-05, + "loss": 0.4862, + "step": 2499 + }, + { + "epoch": 0.21, + "learning_rate": 1.8363581697494738e-05, + "loss": 0.4842, + "step": 2500 + }, + { + "epoch": 0.21, + "learning_rate": 1.8362095865653257e-05, + "loss": 0.4985, + "step": 2501 + }, + { + "epoch": 0.21, + "learning_rate": 1.8360609419734227e-05, + "loss": 0.5008, + "step": 2502 + }, + { + "epoch": 0.21, + "learning_rate": 1.835912235984682e-05, + "loss": 0.5087, + "step": 2503 + }, + { + "epoch": 0.21, + "learning_rate": 1.8357634686100236e-05, + "loss": 0.4947, + "step": 2504 + }, + { + "epoch": 0.21, + "learning_rate": 1.835614639860372e-05, + "loss": 0.4921, + "step": 2505 + }, + { + "epoch": 0.21, + "learning_rate": 1.835465749746657e-05, + "loss": 0.4997, + "step": 2506 + }, + { + "epoch": 0.21, + "learning_rate": 1.8353167982798124e-05, + "loss": 0.5113, + "step": 2507 + }, + { + "epoch": 0.21, + "learning_rate": 1.8351677854707763e-05, + "loss": 0.4809, + "step": 2508 + }, + { + "epoch": 0.21, + "learning_rate": 1.8350187113304918e-05, + "loss": 0.5035, + "step": 2509 + }, + { + "epoch": 0.21, + "learning_rate": 1.8348695758699065e-05, + "loss": 0.5228, + "step": 2510 + }, + { + "epoch": 0.21, + "learning_rate": 1.8347203790999716e-05, + "loss": 0.5196, + "step": 2511 + }, + { + "epoch": 0.21, + "learning_rate": 1.834571121031644e-05, + "loss": 0.4999, + "step": 2512 + }, + { + "epoch": 0.21, + "learning_rate": 1.8344218016758847e-05, + "loss": 0.5013, + "step": 2513 + }, + { + "epoch": 0.21, + "learning_rate": 1.834272421043659e-05, + "loss": 0.5062, + "step": 2514 + }, + { + "epoch": 0.21, + "learning_rate": 1.8341229791459365e-05, + "loss": 0.5037, + "step": 2515 + }, + { + "epoch": 0.21, + "learning_rate": 1.833973475993692e-05, + "loss": 0.5002, + "step": 2516 + }, + { + "epoch": 0.21, + "learning_rate": 1.8338239115979038e-05, + "loss": 0.501, + "step": 2517 + }, + { + "epoch": 0.21, + "learning_rate": 1.833674285969556e-05, + "loss": 0.4984, + "step": 2518 + }, + { + "epoch": 0.21, + "learning_rate": 1.833524599119636e-05, + "loss": 0.4887, + "step": 2519 + }, + { + "epoch": 0.21, + "learning_rate": 1.8333748510591364e-05, + "loss": 0.5059, + "step": 2520 + }, + { + "epoch": 0.21, + "learning_rate": 1.833225041799054e-05, + "loss": 0.5056, + "step": 2521 + }, + { + "epoch": 0.21, + "learning_rate": 1.8330751713503902e-05, + "loss": 0.494, + "step": 2522 + }, + { + "epoch": 0.21, + "learning_rate": 1.8329252397241504e-05, + "loss": 0.497, + "step": 2523 + }, + { + "epoch": 0.21, + "learning_rate": 1.832775246931346e-05, + "loss": 0.5149, + "step": 2524 + }, + { + "epoch": 0.21, + "learning_rate": 1.832625192982991e-05, + "loss": 0.4997, + "step": 2525 + }, + { + "epoch": 0.21, + "learning_rate": 1.8324750778901047e-05, + "loss": 0.5015, + "step": 2526 + }, + { + "epoch": 0.21, + "learning_rate": 1.8323249016637118e-05, + "loss": 0.5, + "step": 2527 + }, + { + "epoch": 0.21, + "learning_rate": 1.8321746643148394e-05, + "loss": 0.5136, + "step": 2528 + }, + { + "epoch": 0.21, + "learning_rate": 1.8320243658545215e-05, + "loss": 0.5003, + "step": 2529 + }, + { + "epoch": 0.21, + "learning_rate": 1.8318740062937944e-05, + "loss": 0.482, + "step": 2530 + }, + { + "epoch": 0.21, + "learning_rate": 1.8317235856437006e-05, + "loss": 0.476, + "step": 2531 + }, + { + "epoch": 0.21, + "learning_rate": 1.831573103915286e-05, + "loss": 0.4906, + "step": 2532 + }, + { + "epoch": 0.21, + "learning_rate": 1.8314225611196013e-05, + "loss": 0.5128, + "step": 2533 + }, + { + "epoch": 0.21, + "learning_rate": 1.8312719572677018e-05, + "loss": 0.5126, + "step": 2534 + }, + { + "epoch": 0.21, + "learning_rate": 1.8311212923706473e-05, + "loss": 0.5084, + "step": 2535 + }, + { + "epoch": 0.21, + "learning_rate": 1.8309705664395024e-05, + "loss": 0.5062, + "step": 2536 + }, + { + "epoch": 0.21, + "learning_rate": 1.830819779485335e-05, + "loss": 0.4906, + "step": 2537 + }, + { + "epoch": 0.21, + "learning_rate": 1.8306689315192187e-05, + "loss": 0.5119, + "step": 2538 + }, + { + "epoch": 0.21, + "learning_rate": 1.8305180225522306e-05, + "loss": 0.4949, + "step": 2539 + }, + { + "epoch": 0.21, + "learning_rate": 1.830367052595454e-05, + "loss": 0.4931, + "step": 2540 + }, + { + "epoch": 0.21, + "learning_rate": 1.8302160216599745e-05, + "loss": 0.5127, + "step": 2541 + }, + { + "epoch": 0.21, + "learning_rate": 1.8300649297568837e-05, + "loss": 0.488, + "step": 2542 + }, + { + "epoch": 0.21, + "learning_rate": 1.8299137768972766e-05, + "loss": 0.5083, + "step": 2543 + }, + { + "epoch": 0.21, + "learning_rate": 1.829762563092254e-05, + "loss": 0.4948, + "step": 2544 + }, + { + "epoch": 0.21, + "learning_rate": 1.8296112883529197e-05, + "loss": 0.5074, + "step": 2545 + }, + { + "epoch": 0.21, + "learning_rate": 1.829459952690383e-05, + "loss": 0.5196, + "step": 2546 + }, + { + "epoch": 0.21, + "learning_rate": 1.8293085561157578e-05, + "loss": 0.4939, + "step": 2547 + }, + { + "epoch": 0.21, + "learning_rate": 1.829157098640161e-05, + "loss": 0.4937, + "step": 2548 + }, + { + "epoch": 0.21, + "learning_rate": 1.829005580274716e-05, + "loss": 0.4949, + "step": 2549 + }, + { + "epoch": 0.21, + "learning_rate": 1.828854001030549e-05, + "loss": 0.4918, + "step": 2550 + }, + { + "epoch": 0.21, + "learning_rate": 1.828702360918792e-05, + "loss": 0.5065, + "step": 2551 + }, + { + "epoch": 0.21, + "learning_rate": 1.8285506599505803e-05, + "loss": 0.4884, + "step": 2552 + }, + { + "epoch": 0.21, + "learning_rate": 1.8283988981370543e-05, + "loss": 0.5058, + "step": 2553 + }, + { + "epoch": 0.21, + "learning_rate": 1.8282470754893585e-05, + "loss": 0.5247, + "step": 2554 + }, + { + "epoch": 0.21, + "learning_rate": 1.828095192018643e-05, + "loss": 0.5005, + "step": 2555 + }, + { + "epoch": 0.21, + "learning_rate": 1.82794324773606e-05, + "loss": 0.4886, + "step": 2556 + }, + { + "epoch": 0.21, + "learning_rate": 1.8277912426527696e-05, + "loss": 0.5016, + "step": 2557 + }, + { + "epoch": 0.21, + "learning_rate": 1.8276391767799326e-05, + "loss": 0.4991, + "step": 2558 + }, + { + "epoch": 0.21, + "learning_rate": 1.8274870501287174e-05, + "loss": 0.5007, + "step": 2559 + }, + { + "epoch": 0.21, + "learning_rate": 1.8273348627102948e-05, + "loss": 0.4941, + "step": 2560 + }, + { + "epoch": 0.21, + "learning_rate": 1.827182614535841e-05, + "loss": 0.4995, + "step": 2561 + }, + { + "epoch": 0.21, + "learning_rate": 1.8270303056165364e-05, + "loss": 0.4974, + "step": 2562 + }, + { + "epoch": 0.21, + "learning_rate": 1.826877935963566e-05, + "loss": 0.5034, + "step": 2563 + }, + { + "epoch": 0.21, + "learning_rate": 1.8267255055881197e-05, + "loss": 0.4848, + "step": 2564 + }, + { + "epoch": 0.21, + "learning_rate": 1.8265730145013903e-05, + "loss": 0.5114, + "step": 2565 + }, + { + "epoch": 0.21, + "learning_rate": 1.826420462714577e-05, + "loss": 0.5084, + "step": 2566 + }, + { + "epoch": 0.21, + "learning_rate": 1.8262678502388824e-05, + "loss": 0.5176, + "step": 2567 + }, + { + "epoch": 0.21, + "learning_rate": 1.8261151770855134e-05, + "loss": 0.4974, + "step": 2568 + }, + { + "epoch": 0.21, + "learning_rate": 1.8259624432656816e-05, + "loss": 0.5196, + "step": 2569 + }, + { + "epoch": 0.22, + "learning_rate": 1.825809648790604e-05, + "loss": 0.4914, + "step": 2570 + }, + { + "epoch": 0.22, + "learning_rate": 1.8256567936715e-05, + "loss": 0.4887, + "step": 2571 + }, + { + "epoch": 0.22, + "learning_rate": 1.8255038779195957e-05, + "loss": 0.513, + "step": 2572 + }, + { + "epoch": 0.22, + "learning_rate": 1.82535090154612e-05, + "loss": 0.4801, + "step": 2573 + }, + { + "epoch": 0.22, + "learning_rate": 1.825197864562307e-05, + "loss": 0.4912, + "step": 2574 + }, + { + "epoch": 0.22, + "learning_rate": 1.825044766979395e-05, + "loss": 0.5092, + "step": 2575 + }, + { + "epoch": 0.22, + "learning_rate": 1.8248916088086268e-05, + "loss": 0.5197, + "step": 2576 + }, + { + "epoch": 0.22, + "learning_rate": 1.82473839006125e-05, + "loss": 0.4776, + "step": 2577 + }, + { + "epoch": 0.22, + "learning_rate": 1.824585110748516e-05, + "loss": 0.4789, + "step": 2578 + }, + { + "epoch": 0.22, + "learning_rate": 1.8244317708816815e-05, + "loss": 0.5079, + "step": 2579 + }, + { + "epoch": 0.22, + "learning_rate": 1.8242783704720066e-05, + "loss": 0.5039, + "step": 2580 + }, + { + "epoch": 0.22, + "learning_rate": 1.8241249095307566e-05, + "loss": 0.4892, + "step": 2581 + }, + { + "epoch": 0.22, + "learning_rate": 1.823971388069201e-05, + "loss": 0.4991, + "step": 2582 + }, + { + "epoch": 0.22, + "learning_rate": 1.823817806098614e-05, + "loss": 0.4969, + "step": 2583 + }, + { + "epoch": 0.22, + "learning_rate": 1.8236641636302737e-05, + "loss": 0.4987, + "step": 2584 + }, + { + "epoch": 0.22, + "learning_rate": 1.823510460675463e-05, + "loss": 0.49, + "step": 2585 + }, + { + "epoch": 0.22, + "learning_rate": 1.8233566972454696e-05, + "loss": 0.4967, + "step": 2586 + }, + { + "epoch": 0.22, + "learning_rate": 1.823202873351585e-05, + "loss": 0.4846, + "step": 2587 + }, + { + "epoch": 0.22, + "learning_rate": 1.8230489890051048e-05, + "loss": 0.5066, + "step": 2588 + }, + { + "epoch": 0.22, + "learning_rate": 1.8228950442173304e-05, + "loss": 0.513, + "step": 2589 + }, + { + "epoch": 0.22, + "learning_rate": 1.8227410389995668e-05, + "loss": 0.4966, + "step": 2590 + }, + { + "epoch": 0.22, + "learning_rate": 1.8225869733631234e-05, + "loss": 0.5062, + "step": 2591 + }, + { + "epoch": 0.22, + "learning_rate": 1.8224328473193137e-05, + "loss": 0.488, + "step": 2592 + }, + { + "epoch": 0.22, + "learning_rate": 1.822278660879457e-05, + "loss": 0.4971, + "step": 2593 + }, + { + "epoch": 0.22, + "learning_rate": 1.822124414054875e-05, + "loss": 0.5029, + "step": 2594 + }, + { + "epoch": 0.22, + "learning_rate": 1.8219701068568957e-05, + "loss": 0.4926, + "step": 2595 + }, + { + "epoch": 0.22, + "learning_rate": 1.8218157392968505e-05, + "loss": 0.4797, + "step": 2596 + }, + { + "epoch": 0.22, + "learning_rate": 1.821661311386076e-05, + "loss": 0.5108, + "step": 2597 + }, + { + "epoch": 0.22, + "learning_rate": 1.8215068231359118e-05, + "loss": 0.5117, + "step": 2598 + }, + { + "epoch": 0.22, + "learning_rate": 1.821352274557704e-05, + "loss": 0.4963, + "step": 2599 + }, + { + "epoch": 0.22, + "learning_rate": 1.8211976656628007e-05, + "loss": 0.5159, + "step": 2600 + }, + { + "epoch": 0.22, + "learning_rate": 1.821042996462557e-05, + "loss": 0.4822, + "step": 2601 + }, + { + "epoch": 0.22, + "learning_rate": 1.8208882669683305e-05, + "loss": 0.4933, + "step": 2602 + }, + { + "epoch": 0.22, + "learning_rate": 1.820733477191484e-05, + "loss": 0.4897, + "step": 2603 + }, + { + "epoch": 0.22, + "learning_rate": 1.8205786271433845e-05, + "loss": 0.4959, + "step": 2604 + }, + { + "epoch": 0.22, + "learning_rate": 1.8204237168354038e-05, + "loss": 0.5009, + "step": 2605 + }, + { + "epoch": 0.22, + "learning_rate": 1.8202687462789175e-05, + "loss": 0.4853, + "step": 2606 + }, + { + "epoch": 0.22, + "learning_rate": 1.8201137154853065e-05, + "loss": 0.523, + "step": 2607 + }, + { + "epoch": 0.22, + "learning_rate": 1.8199586244659554e-05, + "loss": 0.512, + "step": 2608 + }, + { + "epoch": 0.22, + "learning_rate": 1.8198034732322532e-05, + "loss": 0.4876, + "step": 2609 + }, + { + "epoch": 0.22, + "learning_rate": 1.8196482617955938e-05, + "loss": 0.5184, + "step": 2610 + }, + { + "epoch": 0.22, + "learning_rate": 1.8194929901673752e-05, + "loss": 0.536, + "step": 2611 + }, + { + "epoch": 0.22, + "learning_rate": 1.819337658359e-05, + "loss": 0.4823, + "step": 2612 + }, + { + "epoch": 0.22, + "learning_rate": 1.819182266381875e-05, + "loss": 0.504, + "step": 2613 + }, + { + "epoch": 0.22, + "learning_rate": 1.8190268142474113e-05, + "loss": 0.5123, + "step": 2614 + }, + { + "epoch": 0.22, + "learning_rate": 1.8188713019670253e-05, + "loss": 0.4874, + "step": 2615 + }, + { + "epoch": 0.22, + "learning_rate": 1.8187157295521366e-05, + "loss": 0.4956, + "step": 2616 + }, + { + "epoch": 0.22, + "learning_rate": 1.8185600970141703e-05, + "loss": 0.5148, + "step": 2617 + }, + { + "epoch": 0.22, + "learning_rate": 1.818404404364555e-05, + "loss": 0.4907, + "step": 2618 + }, + { + "epoch": 0.22, + "learning_rate": 1.818248651614724e-05, + "loss": 0.4943, + "step": 2619 + }, + { + "epoch": 0.22, + "learning_rate": 1.8180928387761157e-05, + "loss": 0.5055, + "step": 2620 + }, + { + "epoch": 0.22, + "learning_rate": 1.817936965860172e-05, + "loss": 0.4992, + "step": 2621 + }, + { + "epoch": 0.22, + "learning_rate": 1.8177810328783395e-05, + "loss": 0.5033, + "step": 2622 + }, + { + "epoch": 0.22, + "learning_rate": 1.8176250398420694e-05, + "loss": 0.4799, + "step": 2623 + }, + { + "epoch": 0.22, + "learning_rate": 1.817468986762817e-05, + "loss": 0.4893, + "step": 2624 + }, + { + "epoch": 0.22, + "learning_rate": 1.8173128736520427e-05, + "loss": 0.5092, + "step": 2625 + }, + { + "epoch": 0.22, + "learning_rate": 1.81715670052121e-05, + "loss": 0.4862, + "step": 2626 + }, + { + "epoch": 0.22, + "learning_rate": 1.8170004673817882e-05, + "loss": 0.5004, + "step": 2627 + }, + { + "epoch": 0.22, + "learning_rate": 1.8168441742452502e-05, + "loss": 0.4948, + "step": 2628 + }, + { + "epoch": 0.22, + "learning_rate": 1.8166878211230736e-05, + "loss": 0.5071, + "step": 2629 + }, + { + "epoch": 0.22, + "learning_rate": 1.8165314080267406e-05, + "loss": 0.5127, + "step": 2630 + }, + { + "epoch": 0.22, + "learning_rate": 1.8163749349677363e-05, + "loss": 0.5117, + "step": 2631 + }, + { + "epoch": 0.22, + "learning_rate": 1.8162184019575534e-05, + "loss": 0.5178, + "step": 2632 + }, + { + "epoch": 0.22, + "learning_rate": 1.816061809007685e-05, + "loss": 0.5083, + "step": 2633 + }, + { + "epoch": 0.22, + "learning_rate": 1.8159051561296323e-05, + "loss": 0.5078, + "step": 2634 + }, + { + "epoch": 0.22, + "learning_rate": 1.815748443334898e-05, + "loss": 0.5072, + "step": 2635 + }, + { + "epoch": 0.22, + "learning_rate": 1.8155916706349913e-05, + "loss": 0.4987, + "step": 2636 + }, + { + "epoch": 0.22, + "learning_rate": 1.8154348380414245e-05, + "loss": 0.5096, + "step": 2637 + }, + { + "epoch": 0.22, + "learning_rate": 1.815277945565715e-05, + "loss": 0.5288, + "step": 2638 + }, + { + "epoch": 0.22, + "learning_rate": 1.8151209932193844e-05, + "loss": 0.4849, + "step": 2639 + }, + { + "epoch": 0.22, + "learning_rate": 1.814963981013958e-05, + "loss": 0.4918, + "step": 2640 + }, + { + "epoch": 0.22, + "learning_rate": 1.8148069089609667e-05, + "loss": 0.4967, + "step": 2641 + }, + { + "epoch": 0.22, + "learning_rate": 1.8146497770719448e-05, + "loss": 0.5129, + "step": 2642 + }, + { + "epoch": 0.22, + "learning_rate": 1.8144925853584315e-05, + "loss": 0.4814, + "step": 2643 + }, + { + "epoch": 0.22, + "learning_rate": 1.8143353338319712e-05, + "loss": 0.5177, + "step": 2644 + }, + { + "epoch": 0.22, + "learning_rate": 1.8141780225041104e-05, + "loss": 0.5168, + "step": 2645 + }, + { + "epoch": 0.22, + "learning_rate": 1.8140206513864026e-05, + "loss": 0.5167, + "step": 2646 + }, + { + "epoch": 0.22, + "learning_rate": 1.8138632204904033e-05, + "loss": 0.4849, + "step": 2647 + }, + { + "epoch": 0.22, + "learning_rate": 1.8137057298276745e-05, + "loss": 0.4971, + "step": 2648 + }, + { + "epoch": 0.22, + "learning_rate": 1.8135481794097814e-05, + "loss": 0.5189, + "step": 2649 + }, + { + "epoch": 0.22, + "learning_rate": 1.813390569248294e-05, + "loss": 0.4916, + "step": 2650 + }, + { + "epoch": 0.22, + "learning_rate": 1.813232899354786e-05, + "loss": 0.5015, + "step": 2651 + }, + { + "epoch": 0.22, + "learning_rate": 1.8130751697408364e-05, + "loss": 0.499, + "step": 2652 + }, + { + "epoch": 0.22, + "learning_rate": 1.8129173804180285e-05, + "loss": 0.4776, + "step": 2653 + }, + { + "epoch": 0.22, + "learning_rate": 1.812759531397949e-05, + "loss": 0.4923, + "step": 2654 + }, + { + "epoch": 0.22, + "learning_rate": 1.8126016226921898e-05, + "loss": 0.5178, + "step": 2655 + }, + { + "epoch": 0.22, + "learning_rate": 1.812443654312348e-05, + "loss": 0.4954, + "step": 2656 + }, + { + "epoch": 0.22, + "learning_rate": 1.8122856262700227e-05, + "loss": 0.5286, + "step": 2657 + }, + { + "epoch": 0.22, + "learning_rate": 1.81212753857682e-05, + "loss": 0.5092, + "step": 2658 + }, + { + "epoch": 0.22, + "learning_rate": 1.8119693912443487e-05, + "loss": 0.5141, + "step": 2659 + }, + { + "epoch": 0.22, + "learning_rate": 1.8118111842842227e-05, + "loss": 0.5079, + "step": 2660 + }, + { + "epoch": 0.22, + "learning_rate": 1.8116529177080594e-05, + "loss": 0.4833, + "step": 2661 + }, + { + "epoch": 0.22, + "learning_rate": 1.8114945915274826e-05, + "loss": 0.5262, + "step": 2662 + }, + { + "epoch": 0.22, + "learning_rate": 1.8113362057541175e-05, + "loss": 0.5065, + "step": 2663 + }, + { + "epoch": 0.22, + "learning_rate": 1.811177760399596e-05, + "loss": 0.492, + "step": 2664 + }, + { + "epoch": 0.22, + "learning_rate": 1.811019255475554e-05, + "loss": 0.4939, + "step": 2665 + }, + { + "epoch": 0.22, + "learning_rate": 1.8108606909936312e-05, + "loss": 0.4864, + "step": 2666 + }, + { + "epoch": 0.22, + "learning_rate": 1.810702066965472e-05, + "loss": 0.4914, + "step": 2667 + }, + { + "epoch": 0.22, + "learning_rate": 1.810543383402725e-05, + "loss": 0.5023, + "step": 2668 + }, + { + "epoch": 0.22, + "learning_rate": 1.8103846403170427e-05, + "loss": 0.4967, + "step": 2669 + }, + { + "epoch": 0.22, + "learning_rate": 1.8102258377200837e-05, + "loss": 0.4998, + "step": 2670 + }, + { + "epoch": 0.22, + "learning_rate": 1.8100669756235087e-05, + "loss": 0.5019, + "step": 2671 + }, + { + "epoch": 0.22, + "learning_rate": 1.8099080540389845e-05, + "loss": 0.5198, + "step": 2672 + }, + { + "epoch": 0.22, + "learning_rate": 1.8097490729781815e-05, + "loss": 0.5041, + "step": 2673 + }, + { + "epoch": 0.22, + "learning_rate": 1.8095900324527745e-05, + "loss": 0.4983, + "step": 2674 + }, + { + "epoch": 0.22, + "learning_rate": 1.8094309324744428e-05, + "loss": 0.4895, + "step": 2675 + }, + { + "epoch": 0.22, + "learning_rate": 1.8092717730548702e-05, + "loss": 0.5035, + "step": 2676 + }, + { + "epoch": 0.22, + "learning_rate": 1.8091125542057442e-05, + "loss": 0.51, + "step": 2677 + }, + { + "epoch": 0.22, + "learning_rate": 1.8089532759387586e-05, + "loss": 0.4928, + "step": 2678 + }, + { + "epoch": 0.22, + "learning_rate": 1.8087939382656082e-05, + "loss": 0.4932, + "step": 2679 + }, + { + "epoch": 0.22, + "learning_rate": 1.8086345411979952e-05, + "loss": 0.5225, + "step": 2680 + }, + { + "epoch": 0.22, + "learning_rate": 1.808475084747625e-05, + "loss": 0.4933, + "step": 2681 + }, + { + "epoch": 0.22, + "learning_rate": 1.808315568926207e-05, + "loss": 0.5014, + "step": 2682 + }, + { + "epoch": 0.22, + "learning_rate": 1.808155993745456e-05, + "loss": 0.4988, + "step": 2683 + }, + { + "epoch": 0.22, + "learning_rate": 1.8079963592170903e-05, + "loss": 0.4932, + "step": 2684 + }, + { + "epoch": 0.22, + "learning_rate": 1.807836665352832e-05, + "loss": 0.4945, + "step": 2685 + }, + { + "epoch": 0.22, + "learning_rate": 1.8076769121644097e-05, + "loss": 0.4966, + "step": 2686 + }, + { + "epoch": 0.22, + "learning_rate": 1.8075170996635538e-05, + "loss": 0.516, + "step": 2687 + }, + { + "epoch": 0.22, + "learning_rate": 1.8073572278620015e-05, + "loss": 0.5308, + "step": 2688 + }, + { + "epoch": 0.22, + "learning_rate": 1.8071972967714918e-05, + "loss": 0.4975, + "step": 2689 + }, + { + "epoch": 0.23, + "learning_rate": 1.8070373064037702e-05, + "loss": 0.5108, + "step": 2690 + }, + { + "epoch": 0.23, + "learning_rate": 1.8068772567705858e-05, + "loss": 0.4995, + "step": 2691 + }, + { + "epoch": 0.23, + "learning_rate": 1.8067171478836916e-05, + "loss": 0.4989, + "step": 2692 + }, + { + "epoch": 0.23, + "learning_rate": 1.8065569797548453e-05, + "loss": 0.4833, + "step": 2693 + }, + { + "epoch": 0.23, + "learning_rate": 1.8063967523958093e-05, + "loss": 0.4976, + "step": 2694 + }, + { + "epoch": 0.23, + "learning_rate": 1.80623646581835e-05, + "loss": 0.5101, + "step": 2695 + }, + { + "epoch": 0.23, + "learning_rate": 1.8060761200342376e-05, + "loss": 0.5045, + "step": 2696 + }, + { + "epoch": 0.23, + "learning_rate": 1.8059157150552477e-05, + "loss": 0.4985, + "step": 2697 + }, + { + "epoch": 0.23, + "learning_rate": 1.80575525089316e-05, + "loss": 0.4916, + "step": 2698 + }, + { + "epoch": 0.23, + "learning_rate": 1.805594727559758e-05, + "loss": 0.4951, + "step": 2699 + }, + { + "epoch": 0.23, + "learning_rate": 1.80543414506683e-05, + "loss": 0.5025, + "step": 2700 + }, + { + "epoch": 0.23, + "learning_rate": 1.8052735034261683e-05, + "loss": 0.5244, + "step": 2701 + }, + { + "epoch": 0.23, + "learning_rate": 1.8051128026495703e-05, + "loss": 0.4934, + "step": 2702 + }, + { + "epoch": 0.23, + "learning_rate": 1.8049520427488362e-05, + "loss": 0.5106, + "step": 2703 + }, + { + "epoch": 0.23, + "learning_rate": 1.8047912237357724e-05, + "loss": 0.5032, + "step": 2704 + }, + { + "epoch": 0.23, + "learning_rate": 1.8046303456221885e-05, + "loss": 0.4925, + "step": 2705 + }, + { + "epoch": 0.23, + "learning_rate": 1.8044694084198985e-05, + "loss": 0.4961, + "step": 2706 + }, + { + "epoch": 0.23, + "learning_rate": 1.8043084121407214e-05, + "loss": 0.4993, + "step": 2707 + }, + { + "epoch": 0.23, + "learning_rate": 1.80414735679648e-05, + "loss": 0.5052, + "step": 2708 + }, + { + "epoch": 0.23, + "learning_rate": 1.8039862423990012e-05, + "loss": 0.5097, + "step": 2709 + }, + { + "epoch": 0.23, + "learning_rate": 1.803825068960117e-05, + "loss": 0.5066, + "step": 2710 + }, + { + "epoch": 0.23, + "learning_rate": 1.803663836491663e-05, + "loss": 0.5189, + "step": 2711 + }, + { + "epoch": 0.23, + "learning_rate": 1.8035025450054796e-05, + "loss": 0.4867, + "step": 2712 + }, + { + "epoch": 0.23, + "learning_rate": 1.803341194513411e-05, + "loss": 0.4937, + "step": 2713 + }, + { + "epoch": 0.23, + "learning_rate": 1.803179785027307e-05, + "loss": 0.512, + "step": 2714 + }, + { + "epoch": 0.23, + "learning_rate": 1.8030183165590197e-05, + "loss": 0.4938, + "step": 2715 + }, + { + "epoch": 0.23, + "learning_rate": 1.8028567891204074e-05, + "loss": 0.4957, + "step": 2716 + }, + { + "epoch": 0.23, + "learning_rate": 1.802695202723332e-05, + "loss": 0.4973, + "step": 2717 + }, + { + "epoch": 0.23, + "learning_rate": 1.8025335573796596e-05, + "loss": 0.5068, + "step": 2718 + }, + { + "epoch": 0.23, + "learning_rate": 1.8023718531012602e-05, + "loss": 0.4977, + "step": 2719 + }, + { + "epoch": 0.23, + "learning_rate": 1.80221008990001e-05, + "loss": 0.4864, + "step": 2720 + }, + { + "epoch": 0.23, + "learning_rate": 1.8020482677877868e-05, + "loss": 0.5293, + "step": 2721 + }, + { + "epoch": 0.23, + "learning_rate": 1.801886386776475e-05, + "loss": 0.4882, + "step": 2722 + }, + { + "epoch": 0.23, + "learning_rate": 1.8017244468779625e-05, + "loss": 0.4978, + "step": 2723 + }, + { + "epoch": 0.23, + "learning_rate": 1.8015624481041408e-05, + "loss": 0.4887, + "step": 2724 + }, + { + "epoch": 0.23, + "learning_rate": 1.8014003904669073e-05, + "loss": 0.4994, + "step": 2725 + }, + { + "epoch": 0.23, + "learning_rate": 1.8012382739781623e-05, + "loss": 0.498, + "step": 2726 + }, + { + "epoch": 0.23, + "learning_rate": 1.801076098649811e-05, + "loss": 0.5084, + "step": 2727 + }, + { + "epoch": 0.23, + "learning_rate": 1.8009138644937626e-05, + "loss": 0.5097, + "step": 2728 + }, + { + "epoch": 0.23, + "learning_rate": 1.8007515715219317e-05, + "loss": 0.5071, + "step": 2729 + }, + { + "epoch": 0.23, + "learning_rate": 1.8005892197462355e-05, + "loss": 0.5053, + "step": 2730 + }, + { + "epoch": 0.23, + "learning_rate": 1.8004268091785973e-05, + "loss": 0.4957, + "step": 2731 + }, + { + "epoch": 0.23, + "learning_rate": 1.8002643398309434e-05, + "loss": 0.4895, + "step": 2732 + }, + { + "epoch": 0.23, + "learning_rate": 1.800101811715205e-05, + "loss": 0.4991, + "step": 2733 + }, + { + "epoch": 0.23, + "learning_rate": 1.799939224843317e-05, + "loss": 0.4882, + "step": 2734 + }, + { + "epoch": 0.23, + "learning_rate": 1.7997765792272203e-05, + "loss": 0.4993, + "step": 2735 + }, + { + "epoch": 0.23, + "learning_rate": 1.7996138748788573e-05, + "loss": 0.4852, + "step": 2736 + }, + { + "epoch": 0.23, + "learning_rate": 1.799451111810178e-05, + "loss": 0.5067, + "step": 2737 + }, + { + "epoch": 0.23, + "learning_rate": 1.7992882900331336e-05, + "loss": 0.5039, + "step": 2738 + }, + { + "epoch": 0.23, + "learning_rate": 1.799125409559682e-05, + "loss": 0.4889, + "step": 2739 + }, + { + "epoch": 0.23, + "learning_rate": 1.7989624704017838e-05, + "loss": 0.4925, + "step": 2740 + }, + { + "epoch": 0.23, + "learning_rate": 1.798799472571405e-05, + "loss": 0.4827, + "step": 2741 + }, + { + "epoch": 0.23, + "learning_rate": 1.7986364160805156e-05, + "loss": 0.4894, + "step": 2742 + }, + { + "epoch": 0.23, + "learning_rate": 1.7984733009410896e-05, + "loss": 0.5013, + "step": 2743 + }, + { + "epoch": 0.23, + "learning_rate": 1.7983101271651052e-05, + "loss": 0.4842, + "step": 2744 + }, + { + "epoch": 0.23, + "learning_rate": 1.798146894764546e-05, + "loss": 0.5058, + "step": 2745 + }, + { + "epoch": 0.23, + "learning_rate": 1.7979836037513977e-05, + "loss": 0.5045, + "step": 2746 + }, + { + "epoch": 0.23, + "learning_rate": 1.7978202541376533e-05, + "loss": 0.4997, + "step": 2747 + }, + { + "epoch": 0.23, + "learning_rate": 1.7976568459353078e-05, + "loss": 0.5177, + "step": 2748 + }, + { + "epoch": 0.23, + "learning_rate": 1.797493379156361e-05, + "loss": 0.4966, + "step": 2749 + }, + { + "epoch": 0.23, + "learning_rate": 1.7973298538128174e-05, + "loss": 0.4932, + "step": 2750 + }, + { + "epoch": 0.23, + "learning_rate": 1.797166269916686e-05, + "loss": 0.4896, + "step": 2751 + }, + { + "epoch": 0.23, + "learning_rate": 1.797002627479979e-05, + "loss": 0.4984, + "step": 2752 + }, + { + "epoch": 0.23, + "learning_rate": 1.7968389265147142e-05, + "loss": 0.5047, + "step": 2753 + }, + { + "epoch": 0.23, + "learning_rate": 1.796675167032913e-05, + "loss": 0.4992, + "step": 2754 + }, + { + "epoch": 0.23, + "learning_rate": 1.7965113490466013e-05, + "loss": 0.4927, + "step": 2755 + }, + { + "epoch": 0.23, + "learning_rate": 1.796347472567809e-05, + "loss": 0.4969, + "step": 2756 + }, + { + "epoch": 0.23, + "learning_rate": 1.7961835376085702e-05, + "loss": 0.497, + "step": 2757 + }, + { + "epoch": 0.23, + "learning_rate": 1.7960195441809242e-05, + "loss": 0.4832, + "step": 2758 + }, + { + "epoch": 0.23, + "learning_rate": 1.795855492296914e-05, + "loss": 0.5121, + "step": 2759 + }, + { + "epoch": 0.23, + "learning_rate": 1.7956913819685865e-05, + "loss": 0.5147, + "step": 2760 + }, + { + "epoch": 0.23, + "learning_rate": 1.7955272132079935e-05, + "loss": 0.4937, + "step": 2761 + }, + { + "epoch": 0.23, + "learning_rate": 1.7953629860271906e-05, + "loss": 0.5006, + "step": 2762 + }, + { + "epoch": 0.23, + "learning_rate": 1.7951987004382384e-05, + "loss": 0.4956, + "step": 2763 + }, + { + "epoch": 0.23, + "learning_rate": 1.795034356453201e-05, + "loss": 0.5006, + "step": 2764 + }, + { + "epoch": 0.23, + "learning_rate": 1.794869954084147e-05, + "loss": 0.51, + "step": 2765 + }, + { + "epoch": 0.23, + "learning_rate": 1.79470549334315e-05, + "loss": 0.4736, + "step": 2766 + }, + { + "epoch": 0.23, + "learning_rate": 1.794540974242287e-05, + "loss": 0.5055, + "step": 2767 + }, + { + "epoch": 0.23, + "learning_rate": 1.7943763967936395e-05, + "loss": 0.5209, + "step": 2768 + }, + { + "epoch": 0.23, + "learning_rate": 1.7942117610092938e-05, + "loss": 0.493, + "step": 2769 + }, + { + "epoch": 0.23, + "learning_rate": 1.794047066901339e-05, + "loss": 0.4909, + "step": 2770 + }, + { + "epoch": 0.23, + "learning_rate": 1.7938823144818712e-05, + "loss": 0.5175, + "step": 2771 + }, + { + "epoch": 0.23, + "learning_rate": 1.7937175037629876e-05, + "loss": 0.4814, + "step": 2772 + }, + { + "epoch": 0.23, + "learning_rate": 1.793552634756792e-05, + "loss": 0.5145, + "step": 2773 + }, + { + "epoch": 0.23, + "learning_rate": 1.793387707475392e-05, + "loss": 0.5087, + "step": 2774 + }, + { + "epoch": 0.23, + "learning_rate": 1.793222721930898e-05, + "loss": 0.504, + "step": 2775 + }, + { + "epoch": 0.23, + "learning_rate": 1.793057678135427e-05, + "loss": 0.4912, + "step": 2776 + }, + { + "epoch": 0.23, + "learning_rate": 1.7928925761010984e-05, + "loss": 0.5088, + "step": 2777 + }, + { + "epoch": 0.23, + "learning_rate": 1.792727415840037e-05, + "loss": 0.484, + "step": 2778 + }, + { + "epoch": 0.23, + "learning_rate": 1.7925621973643713e-05, + "loss": 0.5029, + "step": 2779 + }, + { + "epoch": 0.23, + "learning_rate": 1.7923969206862347e-05, + "loss": 0.5131, + "step": 2780 + }, + { + "epoch": 0.23, + "learning_rate": 1.7922315858177638e-05, + "loss": 0.4955, + "step": 2781 + }, + { + "epoch": 0.23, + "learning_rate": 1.7920661927711002e-05, + "loss": 0.5075, + "step": 2782 + }, + { + "epoch": 0.23, + "learning_rate": 1.7919007415583903e-05, + "loss": 0.469, + "step": 2783 + }, + { + "epoch": 0.23, + "learning_rate": 1.7917352321917834e-05, + "loss": 0.5087, + "step": 2784 + }, + { + "epoch": 0.23, + "learning_rate": 1.7915696646834343e-05, + "loss": 0.4729, + "step": 2785 + }, + { + "epoch": 0.23, + "learning_rate": 1.7914040390455014e-05, + "loss": 0.4914, + "step": 2786 + }, + { + "epoch": 0.23, + "learning_rate": 1.7912383552901473e-05, + "loss": 0.5058, + "step": 2787 + }, + { + "epoch": 0.23, + "learning_rate": 1.7910726134295396e-05, + "loss": 0.4916, + "step": 2788 + }, + { + "epoch": 0.23, + "learning_rate": 1.7909068134758497e-05, + "loss": 0.5064, + "step": 2789 + }, + { + "epoch": 0.23, + "learning_rate": 1.7907409554412526e-05, + "loss": 0.501, + "step": 2790 + }, + { + "epoch": 0.23, + "learning_rate": 1.790575039337929e-05, + "loss": 0.5054, + "step": 2791 + }, + { + "epoch": 0.23, + "learning_rate": 1.7904090651780624e-05, + "loss": 0.4934, + "step": 2792 + }, + { + "epoch": 0.23, + "learning_rate": 1.790243032973842e-05, + "loss": 0.5042, + "step": 2793 + }, + { + "epoch": 0.23, + "learning_rate": 1.79007694273746e-05, + "loss": 0.4681, + "step": 2794 + }, + { + "epoch": 0.23, + "learning_rate": 1.7899107944811133e-05, + "loss": 0.5011, + "step": 2795 + }, + { + "epoch": 0.23, + "learning_rate": 1.7897445882170038e-05, + "loss": 0.5067, + "step": 2796 + }, + { + "epoch": 0.23, + "learning_rate": 1.789578323957336e-05, + "loss": 0.5044, + "step": 2797 + }, + { + "epoch": 0.23, + "learning_rate": 1.7894120017143205e-05, + "loss": 0.5046, + "step": 2798 + }, + { + "epoch": 0.23, + "learning_rate": 1.789245621500171e-05, + "loss": 0.4989, + "step": 2799 + }, + { + "epoch": 0.23, + "learning_rate": 1.7890791833271058e-05, + "loss": 0.4721, + "step": 2800 + }, + { + "epoch": 0.23, + "learning_rate": 1.7889126872073473e-05, + "loss": 0.5095, + "step": 2801 + }, + { + "epoch": 0.23, + "learning_rate": 1.7887461331531224e-05, + "loss": 0.496, + "step": 2802 + }, + { + "epoch": 0.23, + "learning_rate": 1.788579521176662e-05, + "loss": 0.4881, + "step": 2803 + }, + { + "epoch": 0.23, + "learning_rate": 1.7884128512902018e-05, + "loss": 0.5057, + "step": 2804 + }, + { + "epoch": 0.23, + "learning_rate": 1.788246123505981e-05, + "loss": 0.5034, + "step": 2805 + }, + { + "epoch": 0.23, + "learning_rate": 1.7880793378362432e-05, + "loss": 0.4997, + "step": 2806 + }, + { + "epoch": 0.23, + "learning_rate": 1.787912494293237e-05, + "loss": 0.4959, + "step": 2807 + }, + { + "epoch": 0.23, + "learning_rate": 1.787745592889214e-05, + "loss": 0.4812, + "step": 2808 + }, + { + "epoch": 0.24, + "learning_rate": 1.7875786336364316e-05, + "loss": 0.5047, + "step": 2809 + }, + { + "epoch": 0.24, + "learning_rate": 1.78741161654715e-05, + "loss": 0.4924, + "step": 2810 + }, + { + "epoch": 0.24, + "learning_rate": 1.7872445416336343e-05, + "loss": 0.5078, + "step": 2811 + }, + { + "epoch": 0.24, + "learning_rate": 1.7870774089081537e-05, + "loss": 0.4883, + "step": 2812 + }, + { + "epoch": 0.24, + "learning_rate": 1.786910218382982e-05, + "loss": 0.5038, + "step": 2813 + }, + { + "epoch": 0.24, + "learning_rate": 1.7867429700703967e-05, + "loss": 0.5137, + "step": 2814 + }, + { + "epoch": 0.24, + "learning_rate": 1.7865756639826805e-05, + "loss": 0.5147, + "step": 2815 + }, + { + "epoch": 0.24, + "learning_rate": 1.786408300132119e-05, + "loss": 0.4802, + "step": 2816 + }, + { + "epoch": 0.24, + "learning_rate": 1.7862408785310025e-05, + "loss": 0.5072, + "step": 2817 + }, + { + "epoch": 0.24, + "learning_rate": 1.7860733991916263e-05, + "loss": 0.5101, + "step": 2818 + }, + { + "epoch": 0.24, + "learning_rate": 1.7859058621262893e-05, + "loss": 0.4928, + "step": 2819 + }, + { + "epoch": 0.24, + "learning_rate": 1.7857382673472946e-05, + "loss": 0.499, + "step": 2820 + }, + { + "epoch": 0.24, + "learning_rate": 1.7855706148669494e-05, + "loss": 0.5024, + "step": 2821 + }, + { + "epoch": 0.24, + "learning_rate": 1.785402904697566e-05, + "loss": 0.4932, + "step": 2822 + }, + { + "epoch": 0.24, + "learning_rate": 1.7852351368514597e-05, + "loss": 0.5075, + "step": 2823 + }, + { + "epoch": 0.24, + "learning_rate": 1.7850673113409514e-05, + "loss": 0.499, + "step": 2824 + }, + { + "epoch": 0.24, + "learning_rate": 1.7848994281783648e-05, + "loss": 0.5007, + "step": 2825 + }, + { + "epoch": 0.24, + "learning_rate": 1.784731487376029e-05, + "loss": 0.5201, + "step": 2826 + }, + { + "epoch": 0.24, + "learning_rate": 1.7845634889462763e-05, + "loss": 0.4836, + "step": 2827 + }, + { + "epoch": 0.24, + "learning_rate": 1.784395432901445e-05, + "loss": 0.5021, + "step": 2828 + }, + { + "epoch": 0.24, + "learning_rate": 1.784227319253875e-05, + "loss": 0.5008, + "step": 2829 + }, + { + "epoch": 0.24, + "learning_rate": 1.7840591480159127e-05, + "loss": 0.5007, + "step": 2830 + }, + { + "epoch": 0.24, + "learning_rate": 1.7838909191999077e-05, + "loss": 0.4969, + "step": 2831 + }, + { + "epoch": 0.24, + "learning_rate": 1.783722632818214e-05, + "loss": 0.4959, + "step": 2832 + }, + { + "epoch": 0.24, + "learning_rate": 1.78355428888319e-05, + "loss": 0.5112, + "step": 2833 + }, + { + "epoch": 0.24, + "learning_rate": 1.783385887407198e-05, + "loss": 0.5032, + "step": 2834 + }, + { + "epoch": 0.24, + "learning_rate": 1.783217428402605e-05, + "loss": 0.5036, + "step": 2835 + }, + { + "epoch": 0.24, + "learning_rate": 1.7830489118817812e-05, + "loss": 0.5104, + "step": 2836 + }, + { + "epoch": 0.24, + "learning_rate": 1.7828803378571028e-05, + "loss": 0.4815, + "step": 2837 + }, + { + "epoch": 0.24, + "learning_rate": 1.7827117063409483e-05, + "loss": 0.4726, + "step": 2838 + }, + { + "epoch": 0.24, + "learning_rate": 1.782543017345702e-05, + "loss": 0.4989, + "step": 2839 + }, + { + "epoch": 0.24, + "learning_rate": 1.782374270883751e-05, + "loss": 0.4892, + "step": 2840 + }, + { + "epoch": 0.24, + "learning_rate": 1.7822054669674878e-05, + "loss": 0.4928, + "step": 2841 + }, + { + "epoch": 0.24, + "learning_rate": 1.7820366056093083e-05, + "loss": 0.4805, + "step": 2842 + }, + { + "epoch": 0.24, + "learning_rate": 1.7818676868216137e-05, + "loss": 0.4995, + "step": 2843 + }, + { + "epoch": 0.24, + "learning_rate": 1.781698710616808e-05, + "loss": 0.4744, + "step": 2844 + }, + { + "epoch": 0.24, + "learning_rate": 1.7815296770073002e-05, + "loss": 0.4918, + "step": 2845 + }, + { + "epoch": 0.24, + "learning_rate": 1.7813605860055034e-05, + "loss": 0.5363, + "step": 2846 + }, + { + "epoch": 0.24, + "learning_rate": 1.7811914376238354e-05, + "loss": 0.4904, + "step": 2847 + }, + { + "epoch": 0.24, + "learning_rate": 1.7810222318747173e-05, + "loss": 0.4744, + "step": 2848 + }, + { + "epoch": 0.24, + "learning_rate": 1.780852968770575e-05, + "loss": 0.4957, + "step": 2849 + }, + { + "epoch": 0.24, + "learning_rate": 1.7806836483238387e-05, + "loss": 0.521, + "step": 2850 + }, + { + "epoch": 0.24, + "learning_rate": 1.780514270546942e-05, + "loss": 0.4905, + "step": 2851 + }, + { + "epoch": 0.24, + "learning_rate": 1.780344835452324e-05, + "loss": 0.494, + "step": 2852 + }, + { + "epoch": 0.24, + "learning_rate": 1.780175343052427e-05, + "loss": 0.4928, + "step": 2853 + }, + { + "epoch": 0.24, + "learning_rate": 1.7800057933596975e-05, + "loss": 0.4872, + "step": 2854 + }, + { + "epoch": 0.24, + "learning_rate": 1.779836186386587e-05, + "loss": 0.4856, + "step": 2855 + }, + { + "epoch": 0.24, + "learning_rate": 1.7796665221455503e-05, + "loss": 0.5121, + "step": 2856 + }, + { + "epoch": 0.24, + "learning_rate": 1.7794968006490475e-05, + "loss": 0.4866, + "step": 2857 + }, + { + "epoch": 0.24, + "learning_rate": 1.7793270219095418e-05, + "loss": 0.498, + "step": 2858 + }, + { + "epoch": 0.24, + "learning_rate": 1.779157185939501e-05, + "loss": 0.4983, + "step": 2859 + }, + { + "epoch": 0.24, + "learning_rate": 1.778987292751397e-05, + "loss": 0.501, + "step": 2860 + }, + { + "epoch": 0.24, + "learning_rate": 1.7788173423577063e-05, + "loss": 0.5019, + "step": 2861 + }, + { + "epoch": 0.24, + "learning_rate": 1.7786473347709094e-05, + "loss": 0.5126, + "step": 2862 + }, + { + "epoch": 0.24, + "learning_rate": 1.778477270003491e-05, + "loss": 0.5096, + "step": 2863 + }, + { + "epoch": 0.24, + "learning_rate": 1.7783071480679397e-05, + "loss": 0.506, + "step": 2864 + }, + { + "epoch": 0.24, + "learning_rate": 1.7781369689767488e-05, + "loss": 0.4847, + "step": 2865 + }, + { + "epoch": 0.24, + "learning_rate": 1.7779667327424152e-05, + "loss": 0.5061, + "step": 2866 + }, + { + "epoch": 0.24, + "learning_rate": 1.777796439377441e-05, + "loss": 0.5108, + "step": 2867 + }, + { + "epoch": 0.24, + "learning_rate": 1.777626088894331e-05, + "loss": 0.486, + "step": 2868 + }, + { + "epoch": 0.24, + "learning_rate": 1.7774556813055956e-05, + "loss": 0.4891, + "step": 2869 + }, + { + "epoch": 0.24, + "learning_rate": 1.7772852166237483e-05, + "loss": 0.5196, + "step": 2870 + }, + { + "epoch": 0.24, + "learning_rate": 1.7771146948613078e-05, + "loss": 0.507, + "step": 2871 + }, + { + "epoch": 0.24, + "learning_rate": 1.7769441160307967e-05, + "loss": 0.5085, + "step": 2872 + }, + { + "epoch": 0.24, + "learning_rate": 1.776773480144741e-05, + "loss": 0.4863, + "step": 2873 + }, + { + "epoch": 0.24, + "learning_rate": 1.776602787215672e-05, + "loss": 0.4874, + "step": 2874 + }, + { + "epoch": 0.24, + "learning_rate": 1.7764320372561238e-05, + "loss": 0.5047, + "step": 2875 + }, + { + "epoch": 0.24, + "learning_rate": 1.7762612302786372e-05, + "loss": 0.495, + "step": 2876 + }, + { + "epoch": 0.24, + "learning_rate": 1.776090366295754e-05, + "loss": 0.5146, + "step": 2877 + }, + { + "epoch": 0.24, + "learning_rate": 1.775919445320022e-05, + "loss": 0.4959, + "step": 2878 + }, + { + "epoch": 0.24, + "learning_rate": 1.7757484673639936e-05, + "loss": 0.4918, + "step": 2879 + }, + { + "epoch": 0.24, + "learning_rate": 1.7755774324402244e-05, + "loss": 0.4994, + "step": 2880 + }, + { + "epoch": 0.24, + "learning_rate": 1.7754063405612744e-05, + "loss": 0.4843, + "step": 2881 + }, + { + "epoch": 0.24, + "learning_rate": 1.7752351917397078e-05, + "loss": 0.5114, + "step": 2882 + }, + { + "epoch": 0.24, + "learning_rate": 1.775063985988093e-05, + "loss": 0.4892, + "step": 2883 + }, + { + "epoch": 0.24, + "learning_rate": 1.774892723319003e-05, + "loss": 0.5053, + "step": 2884 + }, + { + "epoch": 0.24, + "learning_rate": 1.7747214037450146e-05, + "loss": 0.4994, + "step": 2885 + }, + { + "epoch": 0.24, + "learning_rate": 1.7745500272787084e-05, + "loss": 0.4916, + "step": 2886 + }, + { + "epoch": 0.24, + "learning_rate": 1.7743785939326697e-05, + "loss": 0.5066, + "step": 2887 + }, + { + "epoch": 0.24, + "learning_rate": 1.7742071037194882e-05, + "loss": 0.484, + "step": 2888 + }, + { + "epoch": 0.24, + "learning_rate": 1.7740355566517567e-05, + "loss": 0.5008, + "step": 2889 + }, + { + "epoch": 0.24, + "learning_rate": 1.7738639527420738e-05, + "loss": 0.4982, + "step": 2890 + }, + { + "epoch": 0.24, + "learning_rate": 1.773692292003041e-05, + "loss": 0.4913, + "step": 2891 + }, + { + "epoch": 0.24, + "learning_rate": 1.7735205744472642e-05, + "loss": 0.5338, + "step": 2892 + }, + { + "epoch": 0.24, + "learning_rate": 1.7733488000873538e-05, + "loss": 0.5042, + "step": 2893 + }, + { + "epoch": 0.24, + "learning_rate": 1.773176968935924e-05, + "loss": 0.4934, + "step": 2894 + }, + { + "epoch": 0.24, + "learning_rate": 1.7730050810055935e-05, + "loss": 0.499, + "step": 2895 + }, + { + "epoch": 0.24, + "learning_rate": 1.772833136308985e-05, + "loss": 0.5032, + "step": 2896 + }, + { + "epoch": 0.24, + "learning_rate": 1.7726611348587255e-05, + "loss": 0.5151, + "step": 2897 + }, + { + "epoch": 0.24, + "learning_rate": 1.7724890766674457e-05, + "loss": 0.4901, + "step": 2898 + }, + { + "epoch": 0.24, + "learning_rate": 1.7723169617477815e-05, + "loss": 0.5074, + "step": 2899 + }, + { + "epoch": 0.24, + "learning_rate": 1.772144790112372e-05, + "loss": 0.4803, + "step": 2900 + }, + { + "epoch": 0.24, + "learning_rate": 1.7719725617738605e-05, + "loss": 0.4699, + "step": 2901 + }, + { + "epoch": 0.24, + "learning_rate": 1.771800276744895e-05, + "loss": 0.5076, + "step": 2902 + }, + { + "epoch": 0.24, + "learning_rate": 1.771627935038127e-05, + "loss": 0.4943, + "step": 2903 + }, + { + "epoch": 0.24, + "learning_rate": 1.7714555366662133e-05, + "loss": 0.4933, + "step": 2904 + }, + { + "epoch": 0.24, + "learning_rate": 1.7712830816418137e-05, + "loss": 0.5069, + "step": 2905 + }, + { + "epoch": 0.24, + "learning_rate": 1.7711105699775925e-05, + "loss": 0.4909, + "step": 2906 + }, + { + "epoch": 0.24, + "learning_rate": 1.7709380016862182e-05, + "loss": 0.4913, + "step": 2907 + }, + { + "epoch": 0.24, + "learning_rate": 1.7707653767803638e-05, + "loss": 0.4997, + "step": 2908 + }, + { + "epoch": 0.24, + "learning_rate": 1.770592695272706e-05, + "loss": 0.4943, + "step": 2909 + }, + { + "epoch": 0.24, + "learning_rate": 1.7704199571759257e-05, + "loss": 0.5002, + "step": 2910 + }, + { + "epoch": 0.24, + "learning_rate": 1.770247162502708e-05, + "loss": 0.4869, + "step": 2911 + }, + { + "epoch": 0.24, + "learning_rate": 1.7700743112657427e-05, + "loss": 0.504, + "step": 2912 + }, + { + "epoch": 0.24, + "learning_rate": 1.7699014034777227e-05, + "loss": 0.4923, + "step": 2913 + }, + { + "epoch": 0.24, + "learning_rate": 1.7697284391513462e-05, + "loss": 0.5013, + "step": 2914 + }, + { + "epoch": 0.24, + "learning_rate": 1.7695554182993145e-05, + "loss": 0.5073, + "step": 2915 + }, + { + "epoch": 0.24, + "learning_rate": 1.7693823409343335e-05, + "loss": 0.4885, + "step": 2916 + }, + { + "epoch": 0.24, + "learning_rate": 1.769209207069114e-05, + "loss": 0.5021, + "step": 2917 + }, + { + "epoch": 0.24, + "learning_rate": 1.7690360167163693e-05, + "loss": 0.4975, + "step": 2918 + }, + { + "epoch": 0.24, + "learning_rate": 1.768862769888818e-05, + "loss": 0.5013, + "step": 2919 + }, + { + "epoch": 0.24, + "learning_rate": 1.7686894665991837e-05, + "loss": 0.5013, + "step": 2920 + }, + { + "epoch": 0.24, + "learning_rate": 1.7685161068601915e-05, + "loss": 0.4903, + "step": 2921 + }, + { + "epoch": 0.24, + "learning_rate": 1.768342690684573e-05, + "loss": 0.4874, + "step": 2922 + }, + { + "epoch": 0.24, + "learning_rate": 1.768169218085063e-05, + "loss": 0.5023, + "step": 2923 + }, + { + "epoch": 0.24, + "learning_rate": 1.7679956890744008e-05, + "loss": 0.4943, + "step": 2924 + }, + { + "epoch": 0.24, + "learning_rate": 1.7678221036653295e-05, + "loss": 0.505, + "step": 2925 + }, + { + "epoch": 0.24, + "learning_rate": 1.7676484618705966e-05, + "loss": 0.4858, + "step": 2926 + }, + { + "epoch": 0.24, + "learning_rate": 1.7674747637029533e-05, + "loss": 0.4885, + "step": 2927 + }, + { + "epoch": 0.24, + "learning_rate": 1.7673010091751557e-05, + "loss": 0.4894, + "step": 2928 + }, + { + "epoch": 0.25, + "learning_rate": 1.7671271982999637e-05, + "loss": 0.4983, + "step": 2929 + }, + { + "epoch": 0.25, + "learning_rate": 1.7669533310901405e-05, + "loss": 0.4914, + "step": 2930 + }, + { + "epoch": 0.25, + "learning_rate": 1.766779407558455e-05, + "loss": 0.5021, + "step": 2931 + }, + { + "epoch": 0.25, + "learning_rate": 1.7666054277176788e-05, + "loss": 0.4882, + "step": 2932 + }, + { + "epoch": 0.25, + "learning_rate": 1.7664313915805885e-05, + "loss": 0.4862, + "step": 2933 + }, + { + "epoch": 0.25, + "learning_rate": 1.7662572991599648e-05, + "loss": 0.5032, + "step": 2934 + }, + { + "epoch": 0.25, + "learning_rate": 1.7660831504685923e-05, + "loss": 0.4968, + "step": 2935 + }, + { + "epoch": 0.25, + "learning_rate": 1.7659089455192594e-05, + "loss": 0.4915, + "step": 2936 + }, + { + "epoch": 0.25, + "learning_rate": 1.7657346843247595e-05, + "loss": 0.5019, + "step": 2937 + }, + { + "epoch": 0.25, + "learning_rate": 1.765560366897889e-05, + "loss": 0.4972, + "step": 2938 + }, + { + "epoch": 0.25, + "learning_rate": 1.7653859932514494e-05, + "loss": 0.4978, + "step": 2939 + }, + { + "epoch": 0.25, + "learning_rate": 1.765211563398246e-05, + "loss": 0.5023, + "step": 2940 + }, + { + "epoch": 0.25, + "learning_rate": 1.7650370773510885e-05, + "loss": 0.5064, + "step": 2941 + }, + { + "epoch": 0.25, + "learning_rate": 1.7648625351227894e-05, + "loss": 0.481, + "step": 2942 + }, + { + "epoch": 0.25, + "learning_rate": 1.7646879367261673e-05, + "loss": 0.4964, + "step": 2943 + }, + { + "epoch": 0.25, + "learning_rate": 1.7645132821740437e-05, + "loss": 0.4971, + "step": 2944 + }, + { + "epoch": 0.25, + "learning_rate": 1.7643385714792446e-05, + "loss": 0.4873, + "step": 2945 + }, + { + "epoch": 0.25, + "learning_rate": 1.7641638046546e-05, + "loss": 0.4941, + "step": 2946 + }, + { + "epoch": 0.25, + "learning_rate": 1.7639889817129435e-05, + "loss": 0.4745, + "step": 2947 + }, + { + "epoch": 0.25, + "learning_rate": 1.763814102667114e-05, + "loss": 0.4895, + "step": 2948 + }, + { + "epoch": 0.25, + "learning_rate": 1.7636391675299546e-05, + "loss": 0.5155, + "step": 2949 + }, + { + "epoch": 0.25, + "learning_rate": 1.76346417631431e-05, + "loss": 0.4832, + "step": 2950 + }, + { + "epoch": 0.25, + "learning_rate": 1.763289129033032e-05, + "loss": 0.4912, + "step": 2951 + }, + { + "epoch": 0.25, + "learning_rate": 1.7631140256989753e-05, + "loss": 0.5079, + "step": 2952 + }, + { + "epoch": 0.25, + "learning_rate": 1.762938866324998e-05, + "loss": 0.4972, + "step": 2953 + }, + { + "epoch": 0.25, + "learning_rate": 1.7627636509239646e-05, + "loss": 0.4955, + "step": 2954 + }, + { + "epoch": 0.25, + "learning_rate": 1.7625883795087405e-05, + "loss": 0.4958, + "step": 2955 + }, + { + "epoch": 0.25, + "learning_rate": 1.762413052092198e-05, + "loss": 0.4923, + "step": 2956 + }, + { + "epoch": 0.25, + "learning_rate": 1.7622376686872122e-05, + "loss": 0.4913, + "step": 2957 + }, + { + "epoch": 0.25, + "learning_rate": 1.762062229306662e-05, + "loss": 0.51, + "step": 2958 + }, + { + "epoch": 0.25, + "learning_rate": 1.7618867339634314e-05, + "loss": 0.4916, + "step": 2959 + }, + { + "epoch": 0.25, + "learning_rate": 1.7617111826704083e-05, + "loss": 0.5067, + "step": 2960 + }, + { + "epoch": 0.25, + "learning_rate": 1.761535575440484e-05, + "loss": 0.517, + "step": 2961 + }, + { + "epoch": 0.25, + "learning_rate": 1.7613599122865545e-05, + "loss": 0.4977, + "step": 2962 + }, + { + "epoch": 0.25, + "learning_rate": 1.76118419322152e-05, + "loss": 0.5007, + "step": 2963 + }, + { + "epoch": 0.25, + "learning_rate": 1.761008418258284e-05, + "loss": 0.4947, + "step": 2964 + }, + { + "epoch": 0.25, + "learning_rate": 1.7608325874097548e-05, + "loss": 0.5109, + "step": 2965 + }, + { + "epoch": 0.25, + "learning_rate": 1.7606567006888453e-05, + "loss": 0.4925, + "step": 2966 + }, + { + "epoch": 0.25, + "learning_rate": 1.7604807581084714e-05, + "loss": 0.4935, + "step": 2967 + }, + { + "epoch": 0.25, + "learning_rate": 1.7603047596815538e-05, + "loss": 0.4883, + "step": 2968 + }, + { + "epoch": 0.25, + "learning_rate": 1.760128705421017e-05, + "loss": 0.5063, + "step": 2969 + }, + { + "epoch": 0.25, + "learning_rate": 1.7599525953397898e-05, + "loss": 0.4865, + "step": 2970 + }, + { + "epoch": 0.25, + "learning_rate": 1.7597764294508048e-05, + "loss": 0.5095, + "step": 2971 + }, + { + "epoch": 0.25, + "learning_rate": 1.7596002077669988e-05, + "loss": 0.4756, + "step": 2972 + }, + { + "epoch": 0.25, + "learning_rate": 1.759423930301313e-05, + "loss": 0.4943, + "step": 2973 + }, + { + "epoch": 0.25, + "learning_rate": 1.7592475970666926e-05, + "loss": 0.5059, + "step": 2974 + }, + { + "epoch": 0.25, + "learning_rate": 1.7590712080760865e-05, + "loss": 0.493, + "step": 2975 + }, + { + "epoch": 0.25, + "learning_rate": 1.7588947633424478e-05, + "loss": 0.4919, + "step": 2976 + }, + { + "epoch": 0.25, + "learning_rate": 1.7587182628787343e-05, + "loss": 0.492, + "step": 2977 + }, + { + "epoch": 0.25, + "learning_rate": 1.758541706697908e-05, + "loss": 0.5072, + "step": 2978 + }, + { + "epoch": 0.25, + "learning_rate": 1.758365094812933e-05, + "loss": 0.4911, + "step": 2979 + }, + { + "epoch": 0.25, + "learning_rate": 1.75818842723678e-05, + "loss": 0.4993, + "step": 2980 + }, + { + "epoch": 0.25, + "learning_rate": 1.7580117039824224e-05, + "loss": 0.5072, + "step": 2981 + }, + { + "epoch": 0.25, + "learning_rate": 1.757834925062838e-05, + "loss": 0.4968, + "step": 2982 + }, + { + "epoch": 0.25, + "learning_rate": 1.7576580904910088e-05, + "loss": 0.4873, + "step": 2983 + }, + { + "epoch": 0.25, + "learning_rate": 1.757481200279921e-05, + "loss": 0.5004, + "step": 2984 + }, + { + "epoch": 0.25, + "learning_rate": 1.7573042544425644e-05, + "loss": 0.5078, + "step": 2985 + }, + { + "epoch": 0.25, + "learning_rate": 1.757127252991933e-05, + "loss": 0.486, + "step": 2986 + }, + { + "epoch": 0.25, + "learning_rate": 1.7569501959410253e-05, + "loss": 0.5065, + "step": 2987 + }, + { + "epoch": 0.25, + "learning_rate": 1.7567730833028436e-05, + "loss": 0.5147, + "step": 2988 + }, + { + "epoch": 0.25, + "learning_rate": 1.7565959150903943e-05, + "loss": 0.4804, + "step": 2989 + }, + { + "epoch": 0.25, + "learning_rate": 1.756418691316688e-05, + "loss": 0.4937, + "step": 2990 + }, + { + "epoch": 0.25, + "learning_rate": 1.7562414119947392e-05, + "loss": 0.4972, + "step": 2991 + }, + { + "epoch": 0.25, + "learning_rate": 1.7560640771375668e-05, + "loss": 0.4794, + "step": 2992 + }, + { + "epoch": 0.25, + "learning_rate": 1.755886686758193e-05, + "loss": 0.5034, + "step": 2993 + }, + { + "epoch": 0.25, + "learning_rate": 1.7557092408696446e-05, + "loss": 0.5085, + "step": 2994 + }, + { + "epoch": 0.25, + "learning_rate": 1.7555317394849532e-05, + "loss": 0.4924, + "step": 2995 + }, + { + "epoch": 0.25, + "learning_rate": 1.7553541826171535e-05, + "loss": 0.5068, + "step": 2996 + }, + { + "epoch": 0.25, + "learning_rate": 1.755176570279284e-05, + "loss": 0.4977, + "step": 2997 + }, + { + "epoch": 0.25, + "learning_rate": 1.7549989024843883e-05, + "loss": 0.4948, + "step": 2998 + }, + { + "epoch": 0.25, + "learning_rate": 1.7548211792455134e-05, + "loss": 0.5113, + "step": 2999 + }, + { + "epoch": 0.25, + "learning_rate": 1.754643400575711e-05, + "loss": 0.4921, + "step": 3000 + }, + { + "epoch": 0.25, + "learning_rate": 1.7544655664880357e-05, + "loss": 0.4879, + "step": 3001 + }, + { + "epoch": 0.25, + "learning_rate": 1.7542876769955475e-05, + "loss": 0.5032, + "step": 3002 + }, + { + "epoch": 0.25, + "learning_rate": 1.7541097321113093e-05, + "loss": 0.4926, + "step": 3003 + }, + { + "epoch": 0.25, + "learning_rate": 1.7539317318483893e-05, + "loss": 0.4976, + "step": 3004 + }, + { + "epoch": 0.25, + "learning_rate": 1.7537536762198584e-05, + "loss": 0.4868, + "step": 3005 + }, + { + "epoch": 0.25, + "learning_rate": 1.753575565238793e-05, + "loss": 0.5015, + "step": 3006 + }, + { + "epoch": 0.25, + "learning_rate": 1.753397398918272e-05, + "loss": 0.4932, + "step": 3007 + }, + { + "epoch": 0.25, + "learning_rate": 1.75321917727138e-05, + "loss": 0.5025, + "step": 3008 + }, + { + "epoch": 0.25, + "learning_rate": 1.7530409003112042e-05, + "loss": 0.5077, + "step": 3009 + }, + { + "epoch": 0.25, + "learning_rate": 1.7528625680508372e-05, + "loss": 0.5092, + "step": 3010 + }, + { + "epoch": 0.25, + "learning_rate": 1.7526841805033742e-05, + "loss": 0.483, + "step": 3011 + }, + { + "epoch": 0.25, + "learning_rate": 1.752505737681916e-05, + "loss": 0.4801, + "step": 3012 + }, + { + "epoch": 0.25, + "learning_rate": 1.7523272395995657e-05, + "loss": 0.5236, + "step": 3013 + }, + { + "epoch": 0.25, + "learning_rate": 1.752148686269433e-05, + "loss": 0.4854, + "step": 3014 + }, + { + "epoch": 0.25, + "learning_rate": 1.7519700777046285e-05, + "loss": 0.4899, + "step": 3015 + }, + { + "epoch": 0.25, + "learning_rate": 1.7517914139182694e-05, + "loss": 0.4946, + "step": 3016 + }, + { + "epoch": 0.25, + "learning_rate": 1.751612694923476e-05, + "loss": 0.4829, + "step": 3017 + }, + { + "epoch": 0.25, + "learning_rate": 1.751433920733372e-05, + "loss": 0.4841, + "step": 3018 + }, + { + "epoch": 0.25, + "learning_rate": 1.7512550913610867e-05, + "loss": 0.5057, + "step": 3019 + }, + { + "epoch": 0.25, + "learning_rate": 1.751076206819752e-05, + "loss": 0.4959, + "step": 3020 + }, + { + "epoch": 0.25, + "learning_rate": 1.750897267122505e-05, + "loss": 0.5034, + "step": 3021 + }, + { + "epoch": 0.25, + "learning_rate": 1.7507182722824854e-05, + "loss": 0.4933, + "step": 3022 + }, + { + "epoch": 0.25, + "learning_rate": 1.7505392223128385e-05, + "loss": 0.5029, + "step": 3023 + }, + { + "epoch": 0.25, + "learning_rate": 1.750360117226713e-05, + "loss": 0.5082, + "step": 3024 + }, + { + "epoch": 0.25, + "learning_rate": 1.7501809570372614e-05, + "loss": 0.4933, + "step": 3025 + }, + { + "epoch": 0.25, + "learning_rate": 1.7500017417576406e-05, + "loss": 0.4984, + "step": 3026 + }, + { + "epoch": 0.25, + "learning_rate": 1.7498224714010113e-05, + "loss": 0.5161, + "step": 3027 + }, + { + "epoch": 0.25, + "learning_rate": 1.7496431459805387e-05, + "loss": 0.5026, + "step": 3028 + }, + { + "epoch": 0.25, + "learning_rate": 1.749463765509391e-05, + "loss": 0.5023, + "step": 3029 + }, + { + "epoch": 0.25, + "learning_rate": 1.749284330000742e-05, + "loss": 0.5051, + "step": 3030 + }, + { + "epoch": 0.25, + "learning_rate": 1.7491048394677682e-05, + "loss": 0.503, + "step": 3031 + }, + { + "epoch": 0.25, + "learning_rate": 1.7489252939236506e-05, + "loss": 0.5008, + "step": 3032 + }, + { + "epoch": 0.25, + "learning_rate": 1.7487456933815746e-05, + "loss": 0.507, + "step": 3033 + }, + { + "epoch": 0.25, + "learning_rate": 1.7485660378547293e-05, + "loss": 0.5189, + "step": 3034 + }, + { + "epoch": 0.25, + "learning_rate": 1.7483863273563072e-05, + "loss": 0.4798, + "step": 3035 + }, + { + "epoch": 0.25, + "learning_rate": 1.7482065618995063e-05, + "loss": 0.4859, + "step": 3036 + }, + { + "epoch": 0.25, + "learning_rate": 1.7480267414975274e-05, + "loss": 0.5047, + "step": 3037 + }, + { + "epoch": 0.25, + "learning_rate": 1.7478468661635763e-05, + "loss": 0.4966, + "step": 3038 + }, + { + "epoch": 0.25, + "learning_rate": 1.7476669359108614e-05, + "loss": 0.4787, + "step": 3039 + }, + { + "epoch": 0.25, + "learning_rate": 1.7474869507525967e-05, + "loss": 0.4912, + "step": 3040 + }, + { + "epoch": 0.25, + "learning_rate": 1.7473069107019993e-05, + "loss": 0.4911, + "step": 3041 + }, + { + "epoch": 0.25, + "learning_rate": 1.7471268157722907e-05, + "loss": 0.4955, + "step": 3042 + }, + { + "epoch": 0.25, + "learning_rate": 1.7469466659766963e-05, + "loss": 0.4862, + "step": 3043 + }, + { + "epoch": 0.25, + "learning_rate": 1.7467664613284455e-05, + "loss": 0.5016, + "step": 3044 + }, + { + "epoch": 0.25, + "learning_rate": 1.7465862018407718e-05, + "loss": 0.5008, + "step": 3045 + }, + { + "epoch": 0.25, + "learning_rate": 1.746405887526913e-05, + "loss": 0.5055, + "step": 3046 + }, + { + "epoch": 0.25, + "learning_rate": 1.74622551840011e-05, + "loss": 0.4982, + "step": 3047 + }, + { + "epoch": 0.26, + "learning_rate": 1.7460450944736087e-05, + "loss": 0.5026, + "step": 3048 + }, + { + "epoch": 0.26, + "learning_rate": 1.7458646157606585e-05, + "loss": 0.4959, + "step": 3049 + }, + { + "epoch": 0.26, + "learning_rate": 1.745684082274514e-05, + "loss": 0.4894, + "step": 3050 + }, + { + "epoch": 0.26, + "learning_rate": 1.7455034940284313e-05, + "loss": 0.4976, + "step": 3051 + }, + { + "epoch": 0.26, + "learning_rate": 1.745322851035673e-05, + "loss": 0.4959, + "step": 3052 + }, + { + "epoch": 0.26, + "learning_rate": 1.7451421533095047e-05, + "loss": 0.4848, + "step": 3053 + }, + { + "epoch": 0.26, + "learning_rate": 1.744961400863196e-05, + "loss": 0.5046, + "step": 3054 + }, + { + "epoch": 0.26, + "learning_rate": 1.7447805937100203e-05, + "loss": 0.4826, + "step": 3055 + }, + { + "epoch": 0.26, + "learning_rate": 1.7445997318632555e-05, + "loss": 0.4998, + "step": 3056 + }, + { + "epoch": 0.26, + "learning_rate": 1.7444188153361836e-05, + "loss": 0.4941, + "step": 3057 + }, + { + "epoch": 0.26, + "learning_rate": 1.74423784414209e-05, + "loss": 0.4904, + "step": 3058 + }, + { + "epoch": 0.26, + "learning_rate": 1.744056818294265e-05, + "loss": 0.4982, + "step": 3059 + }, + { + "epoch": 0.26, + "learning_rate": 1.743875737806002e-05, + "loss": 0.4896, + "step": 3060 + }, + { + "epoch": 0.26, + "learning_rate": 1.7436946026905986e-05, + "loss": 0.5043, + "step": 3061 + }, + { + "epoch": 0.26, + "learning_rate": 1.743513412961357e-05, + "loss": 0.4901, + "step": 3062 + }, + { + "epoch": 0.26, + "learning_rate": 1.7433321686315824e-05, + "loss": 0.4888, + "step": 3063 + }, + { + "epoch": 0.26, + "learning_rate": 1.7431508697145855e-05, + "loss": 0.498, + "step": 3064 + }, + { + "epoch": 0.26, + "learning_rate": 1.7429695162236798e-05, + "loss": 0.5043, + "step": 3065 + }, + { + "epoch": 0.26, + "learning_rate": 1.7427881081721828e-05, + "loss": 0.4807, + "step": 3066 + }, + { + "epoch": 0.26, + "learning_rate": 1.7426066455734167e-05, + "loss": 0.483, + "step": 3067 + }, + { + "epoch": 0.26, + "learning_rate": 1.7424251284407075e-05, + "loss": 0.5025, + "step": 3068 + }, + { + "epoch": 0.26, + "learning_rate": 1.7422435567873846e-05, + "loss": 0.5057, + "step": 3069 + }, + { + "epoch": 0.26, + "learning_rate": 1.742061930626782e-05, + "loss": 0.4982, + "step": 3070 + }, + { + "epoch": 0.26, + "learning_rate": 1.7418802499722377e-05, + "loss": 0.5053, + "step": 3071 + }, + { + "epoch": 0.26, + "learning_rate": 1.7416985148370938e-05, + "loss": 0.5214, + "step": 3072 + }, + { + "epoch": 0.26, + "learning_rate": 1.741516725234696e-05, + "loss": 0.4795, + "step": 3073 + }, + { + "epoch": 0.26, + "learning_rate": 1.7413348811783938e-05, + "loss": 0.4918, + "step": 3074 + }, + { + "epoch": 0.26, + "learning_rate": 1.7411529826815416e-05, + "loss": 0.4958, + "step": 3075 + }, + { + "epoch": 0.26, + "learning_rate": 1.740971029757497e-05, + "loss": 0.502, + "step": 3076 + }, + { + "epoch": 0.26, + "learning_rate": 1.7407890224196217e-05, + "loss": 0.4911, + "step": 3077 + }, + { + "epoch": 0.26, + "learning_rate": 1.7406069606812822e-05, + "loss": 0.503, + "step": 3078 + }, + { + "epoch": 0.26, + "learning_rate": 1.7404248445558476e-05, + "loss": 0.4926, + "step": 3079 + }, + { + "epoch": 0.26, + "learning_rate": 1.7402426740566922e-05, + "loss": 0.4967, + "step": 3080 + }, + { + "epoch": 0.26, + "learning_rate": 1.7400604491971937e-05, + "loss": 0.4957, + "step": 3081 + }, + { + "epoch": 0.26, + "learning_rate": 1.7398781699907337e-05, + "loss": 0.4982, + "step": 3082 + }, + { + "epoch": 0.26, + "learning_rate": 1.7396958364506983e-05, + "loss": 0.4722, + "step": 3083 + }, + { + "epoch": 0.26, + "learning_rate": 1.7395134485904775e-05, + "loss": 0.4908, + "step": 3084 + }, + { + "epoch": 0.26, + "learning_rate": 1.739331006423465e-05, + "loss": 0.5098, + "step": 3085 + }, + { + "epoch": 0.26, + "learning_rate": 1.7391485099630584e-05, + "loss": 0.4836, + "step": 3086 + }, + { + "epoch": 0.26, + "learning_rate": 1.7389659592226597e-05, + "loss": 0.5039, + "step": 3087 + }, + { + "epoch": 0.26, + "learning_rate": 1.7387833542156743e-05, + "loss": 0.4989, + "step": 3088 + }, + { + "epoch": 0.26, + "learning_rate": 1.7386006949555124e-05, + "loss": 0.4883, + "step": 3089 + }, + { + "epoch": 0.26, + "learning_rate": 1.7384179814555872e-05, + "loss": 0.4955, + "step": 3090 + }, + { + "epoch": 0.26, + "learning_rate": 1.7382352137293172e-05, + "loss": 0.5069, + "step": 3091 + }, + { + "epoch": 0.26, + "learning_rate": 1.7380523917901233e-05, + "loss": 0.4878, + "step": 3092 + }, + { + "epoch": 0.26, + "learning_rate": 1.7378695156514318e-05, + "loss": 0.4928, + "step": 3093 + }, + { + "epoch": 0.26, + "learning_rate": 1.7376865853266717e-05, + "loss": 0.5107, + "step": 3094 + }, + { + "epoch": 0.26, + "learning_rate": 1.7375036008292775e-05, + "loss": 0.4845, + "step": 3095 + }, + { + "epoch": 0.26, + "learning_rate": 1.7373205621726864e-05, + "loss": 0.5126, + "step": 3096 + }, + { + "epoch": 0.26, + "learning_rate": 1.7371374693703395e-05, + "loss": 0.4847, + "step": 3097 + }, + { + "epoch": 0.26, + "learning_rate": 1.736954322435683e-05, + "loss": 0.5076, + "step": 3098 + }, + { + "epoch": 0.26, + "learning_rate": 1.7367711213821663e-05, + "loss": 0.4967, + "step": 3099 + }, + { + "epoch": 0.26, + "learning_rate": 1.736587866223243e-05, + "loss": 0.508, + "step": 3100 + }, + { + "epoch": 0.26, + "learning_rate": 1.7364045569723706e-05, + "loss": 0.4877, + "step": 3101 + }, + { + "epoch": 0.26, + "learning_rate": 1.7362211936430103e-05, + "loss": 0.4913, + "step": 3102 + }, + { + "epoch": 0.26, + "learning_rate": 1.7360377762486277e-05, + "loss": 0.5046, + "step": 3103 + }, + { + "epoch": 0.26, + "learning_rate": 1.7358543048026925e-05, + "loss": 0.5047, + "step": 3104 + }, + { + "epoch": 0.26, + "learning_rate": 1.7356707793186777e-05, + "loss": 0.4684, + "step": 3105 + }, + { + "epoch": 0.26, + "learning_rate": 1.7354871998100605e-05, + "loss": 0.5183, + "step": 3106 + }, + { + "epoch": 0.26, + "learning_rate": 1.7353035662903225e-05, + "loss": 0.4857, + "step": 3107 + }, + { + "epoch": 0.26, + "learning_rate": 1.735119878772949e-05, + "loss": 0.4787, + "step": 3108 + }, + { + "epoch": 0.26, + "learning_rate": 1.7349361372714294e-05, + "loss": 0.4873, + "step": 3109 + }, + { + "epoch": 0.26, + "learning_rate": 1.7347523417992564e-05, + "loss": 0.4822, + "step": 3110 + }, + { + "epoch": 0.26, + "learning_rate": 1.7345684923699277e-05, + "loss": 0.4815, + "step": 3111 + }, + { + "epoch": 0.26, + "learning_rate": 1.734384588996944e-05, + "loss": 0.5008, + "step": 3112 + }, + { + "epoch": 0.26, + "learning_rate": 1.734200631693811e-05, + "loss": 0.5086, + "step": 3113 + }, + { + "epoch": 0.26, + "learning_rate": 1.7340166204740373e-05, + "loss": 0.4907, + "step": 3114 + }, + { + "epoch": 0.26, + "learning_rate": 1.7338325553511357e-05, + "loss": 0.4919, + "step": 3115 + }, + { + "epoch": 0.26, + "learning_rate": 1.7336484363386237e-05, + "loss": 0.5166, + "step": 3116 + }, + { + "epoch": 0.26, + "learning_rate": 1.7334642634500217e-05, + "loss": 0.4958, + "step": 3117 + }, + { + "epoch": 0.26, + "learning_rate": 1.7332800366988552e-05, + "loss": 0.4995, + "step": 3118 + }, + { + "epoch": 0.26, + "learning_rate": 1.733095756098653e-05, + "loss": 0.5063, + "step": 3119 + }, + { + "epoch": 0.26, + "learning_rate": 1.732911421662947e-05, + "loss": 0.4965, + "step": 3120 + }, + { + "epoch": 0.26, + "learning_rate": 1.732727033405275e-05, + "loss": 0.5028, + "step": 3121 + }, + { + "epoch": 0.26, + "learning_rate": 1.7325425913391772e-05, + "loss": 0.484, + "step": 3122 + }, + { + "epoch": 0.26, + "learning_rate": 1.7323580954781986e-05, + "loss": 0.516, + "step": 3123 + }, + { + "epoch": 0.26, + "learning_rate": 1.7321735458358872e-05, + "loss": 0.4818, + "step": 3124 + }, + { + "epoch": 0.26, + "learning_rate": 1.731988942425796e-05, + "loss": 0.4944, + "step": 3125 + }, + { + "epoch": 0.26, + "learning_rate": 1.7318042852614817e-05, + "loss": 0.5021, + "step": 3126 + }, + { + "epoch": 0.26, + "learning_rate": 1.7316195743565045e-05, + "loss": 0.5114, + "step": 3127 + }, + { + "epoch": 0.26, + "learning_rate": 1.7314348097244288e-05, + "loss": 0.5076, + "step": 3128 + }, + { + "epoch": 0.26, + "learning_rate": 1.7312499913788225e-05, + "loss": 0.503, + "step": 3129 + }, + { + "epoch": 0.26, + "learning_rate": 1.7310651193332586e-05, + "loss": 0.4836, + "step": 3130 + }, + { + "epoch": 0.26, + "learning_rate": 1.730880193601313e-05, + "loss": 0.4987, + "step": 3131 + }, + { + "epoch": 0.26, + "learning_rate": 1.7306952141965664e-05, + "loss": 0.4865, + "step": 3132 + }, + { + "epoch": 0.26, + "learning_rate": 1.7305101811326017e-05, + "loss": 0.4911, + "step": 3133 + }, + { + "epoch": 0.26, + "learning_rate": 1.7303250944230084e-05, + "loss": 0.5219, + "step": 3134 + }, + { + "epoch": 0.26, + "learning_rate": 1.7301399540813773e-05, + "loss": 0.4941, + "step": 3135 + }, + { + "epoch": 0.26, + "learning_rate": 1.729954760121305e-05, + "loss": 0.4856, + "step": 3136 + }, + { + "epoch": 0.26, + "learning_rate": 1.7297695125563915e-05, + "loss": 0.496, + "step": 3137 + }, + { + "epoch": 0.26, + "learning_rate": 1.72958421140024e-05, + "loss": 0.4944, + "step": 3138 + }, + { + "epoch": 0.26, + "learning_rate": 1.7293988566664586e-05, + "loss": 0.4983, + "step": 3139 + }, + { + "epoch": 0.26, + "learning_rate": 1.7292134483686594e-05, + "loss": 0.4886, + "step": 3140 + }, + { + "epoch": 0.26, + "learning_rate": 1.7290279865204567e-05, + "loss": 0.498, + "step": 3141 + }, + { + "epoch": 0.26, + "learning_rate": 1.728842471135472e-05, + "loss": 0.4731, + "step": 3142 + }, + { + "epoch": 0.26, + "learning_rate": 1.728656902227327e-05, + "loss": 0.5268, + "step": 3143 + }, + { + "epoch": 0.26, + "learning_rate": 1.72847127980965e-05, + "loss": 0.5159, + "step": 3144 + }, + { + "epoch": 0.26, + "learning_rate": 1.7282856038960724e-05, + "loss": 0.5017, + "step": 3145 + }, + { + "epoch": 0.26, + "learning_rate": 1.7280998745002286e-05, + "loss": 0.4799, + "step": 3146 + }, + { + "epoch": 0.26, + "learning_rate": 1.7279140916357588e-05, + "loss": 0.4828, + "step": 3147 + }, + { + "epoch": 0.26, + "learning_rate": 1.727728255316306e-05, + "loss": 0.5081, + "step": 3148 + }, + { + "epoch": 0.26, + "learning_rate": 1.7275423655555163e-05, + "loss": 0.4772, + "step": 3149 + }, + { + "epoch": 0.26, + "learning_rate": 1.7273564223670422e-05, + "loss": 0.5074, + "step": 3150 + }, + { + "epoch": 0.26, + "learning_rate": 1.727170425764537e-05, + "loss": 0.4899, + "step": 3151 + }, + { + "epoch": 0.26, + "learning_rate": 1.7269843757616605e-05, + "loss": 0.4881, + "step": 3152 + }, + { + "epoch": 0.26, + "learning_rate": 1.7267982723720755e-05, + "loss": 0.4807, + "step": 3153 + }, + { + "epoch": 0.26, + "learning_rate": 1.726612115609448e-05, + "loss": 0.5115, + "step": 3154 + }, + { + "epoch": 0.26, + "learning_rate": 1.7264259054874492e-05, + "loss": 0.5049, + "step": 3155 + }, + { + "epoch": 0.26, + "learning_rate": 1.726239642019753e-05, + "loss": 0.496, + "step": 3156 + }, + { + "epoch": 0.26, + "learning_rate": 1.7260533252200383e-05, + "loss": 0.4848, + "step": 3157 + }, + { + "epoch": 0.26, + "learning_rate": 1.7258669551019872e-05, + "loss": 0.5023, + "step": 3158 + }, + { + "epoch": 0.26, + "learning_rate": 1.725680531679286e-05, + "loss": 0.5088, + "step": 3159 + }, + { + "epoch": 0.26, + "learning_rate": 1.725494054965625e-05, + "loss": 0.5108, + "step": 3160 + }, + { + "epoch": 0.26, + "learning_rate": 1.7253075249746984e-05, + "loss": 0.4842, + "step": 3161 + }, + { + "epoch": 0.26, + "learning_rate": 1.7251209417202036e-05, + "loss": 0.4926, + "step": 3162 + }, + { + "epoch": 0.26, + "learning_rate": 1.724934305215843e-05, + "loss": 0.5006, + "step": 3163 + }, + { + "epoch": 0.26, + "learning_rate": 1.7247476154753222e-05, + "loss": 0.4902, + "step": 3164 + }, + { + "epoch": 0.26, + "learning_rate": 1.724560872512351e-05, + "loss": 0.5061, + "step": 3165 + }, + { + "epoch": 0.26, + "learning_rate": 1.724374076340643e-05, + "loss": 0.4807, + "step": 3166 + }, + { + "epoch": 0.26, + "learning_rate": 1.724187226973916e-05, + "loss": 0.4988, + "step": 3167 + }, + { + "epoch": 0.27, + "learning_rate": 1.7240003244258904e-05, + "loss": 0.4889, + "step": 3168 + }, + { + "epoch": 0.27, + "learning_rate": 1.723813368710293e-05, + "loss": 0.488, + "step": 3169 + }, + { + "epoch": 0.27, + "learning_rate": 1.723626359840852e-05, + "loss": 0.5014, + "step": 3170 + }, + { + "epoch": 0.27, + "learning_rate": 1.7234392978313012e-05, + "loss": 0.4979, + "step": 3171 + }, + { + "epoch": 0.27, + "learning_rate": 1.7232521826953773e-05, + "loss": 0.4916, + "step": 3172 + }, + { + "epoch": 0.27, + "learning_rate": 1.7230650144468212e-05, + "loss": 0.5112, + "step": 3173 + }, + { + "epoch": 0.27, + "learning_rate": 1.7228777930993784e-05, + "loss": 0.477, + "step": 3174 + }, + { + "epoch": 0.27, + "learning_rate": 1.7226905186667965e-05, + "loss": 0.5136, + "step": 3175 + }, + { + "epoch": 0.27, + "learning_rate": 1.722503191162829e-05, + "loss": 0.5031, + "step": 3176 + }, + { + "epoch": 0.27, + "learning_rate": 1.7223158106012326e-05, + "loss": 0.4908, + "step": 3177 + }, + { + "epoch": 0.27, + "learning_rate": 1.722128376995767e-05, + "loss": 0.4848, + "step": 3178 + }, + { + "epoch": 0.27, + "learning_rate": 1.721940890360197e-05, + "loss": 0.4897, + "step": 3179 + }, + { + "epoch": 0.27, + "learning_rate": 1.7217533507082907e-05, + "loss": 0.489, + "step": 3180 + }, + { + "epoch": 0.27, + "learning_rate": 1.721565758053821e-05, + "loss": 0.5087, + "step": 3181 + }, + { + "epoch": 0.27, + "learning_rate": 1.7213781124105623e-05, + "loss": 0.5086, + "step": 3182 + }, + { + "epoch": 0.27, + "learning_rate": 1.7211904137922962e-05, + "loss": 0.4942, + "step": 3183 + }, + { + "epoch": 0.27, + "learning_rate": 1.721002662212805e-05, + "loss": 0.4779, + "step": 3184 + }, + { + "epoch": 0.27, + "learning_rate": 1.720814857685878e-05, + "loss": 0.4938, + "step": 3185 + }, + { + "epoch": 0.27, + "learning_rate": 1.7206270002253056e-05, + "loss": 0.4867, + "step": 3186 + }, + { + "epoch": 0.27, + "learning_rate": 1.7204390898448837e-05, + "loss": 0.4784, + "step": 3187 + }, + { + "epoch": 0.27, + "learning_rate": 1.720251126558411e-05, + "loss": 0.4861, + "step": 3188 + }, + { + "epoch": 0.27, + "learning_rate": 1.720063110379692e-05, + "loss": 0.5038, + "step": 3189 + }, + { + "epoch": 0.27, + "learning_rate": 1.7198750413225327e-05, + "loss": 0.5021, + "step": 3190 + }, + { + "epoch": 0.27, + "learning_rate": 1.7196869194007448e-05, + "loss": 0.4814, + "step": 3191 + }, + { + "epoch": 0.27, + "learning_rate": 1.719498744628143e-05, + "loss": 0.4862, + "step": 3192 + }, + { + "epoch": 0.27, + "learning_rate": 1.719310517018546e-05, + "loss": 0.5017, + "step": 3193 + }, + { + "epoch": 0.27, + "learning_rate": 1.7191222365857764e-05, + "loss": 0.4901, + "step": 3194 + }, + { + "epoch": 0.27, + "learning_rate": 1.7189339033436607e-05, + "loss": 0.4953, + "step": 3195 + }, + { + "epoch": 0.27, + "learning_rate": 1.7187455173060294e-05, + "loss": 0.5086, + "step": 3196 + }, + { + "epoch": 0.27, + "learning_rate": 1.7185570784867168e-05, + "loss": 0.4942, + "step": 3197 + }, + { + "epoch": 0.27, + "learning_rate": 1.7183685868995616e-05, + "loss": 0.5027, + "step": 3198 + }, + { + "epoch": 0.27, + "learning_rate": 1.718180042558405e-05, + "loss": 0.4924, + "step": 3199 + }, + { + "epoch": 0.27, + "learning_rate": 1.717991445477093e-05, + "loss": 0.517, + "step": 3200 + }, + { + "epoch": 0.27, + "learning_rate": 1.7178027956694753e-05, + "loss": 0.4834, + "step": 3201 + }, + { + "epoch": 0.27, + "learning_rate": 1.7176140931494064e-05, + "loss": 0.4947, + "step": 3202 + }, + { + "epoch": 0.27, + "learning_rate": 1.717425337930743e-05, + "loss": 0.5267, + "step": 3203 + }, + { + "epoch": 0.27, + "learning_rate": 1.7172365300273467e-05, + "loss": 0.5019, + "step": 3204 + }, + { + "epoch": 0.27, + "learning_rate": 1.7170476694530834e-05, + "loss": 0.4692, + "step": 3205 + }, + { + "epoch": 0.27, + "learning_rate": 1.716858756221821e-05, + "loss": 0.4858, + "step": 3206 + }, + { + "epoch": 0.27, + "learning_rate": 1.7166697903474335e-05, + "loss": 0.5162, + "step": 3207 + }, + { + "epoch": 0.27, + "learning_rate": 1.716480771843798e-05, + "loss": 0.493, + "step": 3208 + }, + { + "epoch": 0.27, + "learning_rate": 1.7162917007247937e-05, + "loss": 0.4835, + "step": 3209 + }, + { + "epoch": 0.27, + "learning_rate": 1.7161025770043065e-05, + "loss": 0.5061, + "step": 3210 + }, + { + "epoch": 0.27, + "learning_rate": 1.7159134006962248e-05, + "loss": 0.4877, + "step": 3211 + }, + { + "epoch": 0.27, + "learning_rate": 1.7157241718144404e-05, + "loss": 0.4893, + "step": 3212 + }, + { + "epoch": 0.27, + "learning_rate": 1.7155348903728497e-05, + "loss": 0.4832, + "step": 3213 + }, + { + "epoch": 0.27, + "learning_rate": 1.715345556385353e-05, + "loss": 0.4912, + "step": 3214 + }, + { + "epoch": 0.27, + "learning_rate": 1.715156169865854e-05, + "loss": 0.4865, + "step": 3215 + }, + { + "epoch": 0.27, + "learning_rate": 1.7149667308282604e-05, + "loss": 0.4766, + "step": 3216 + }, + { + "epoch": 0.27, + "learning_rate": 1.714777239286484e-05, + "loss": 0.5137, + "step": 3217 + }, + { + "epoch": 0.27, + "learning_rate": 1.7145876952544395e-05, + "loss": 0.4717, + "step": 3218 + }, + { + "epoch": 0.27, + "learning_rate": 1.7143980987460475e-05, + "loss": 0.5099, + "step": 3219 + }, + { + "epoch": 0.27, + "learning_rate": 1.7142084497752304e-05, + "loss": 0.5271, + "step": 3220 + }, + { + "epoch": 0.27, + "learning_rate": 1.714018748355915e-05, + "loss": 0.4995, + "step": 3221 + }, + { + "epoch": 0.27, + "learning_rate": 1.713828994502033e-05, + "loss": 0.522, + "step": 3222 + }, + { + "epoch": 0.27, + "learning_rate": 1.7136391882275186e-05, + "loss": 0.4746, + "step": 3223 + }, + { + "epoch": 0.27, + "learning_rate": 1.7134493295463104e-05, + "loss": 0.4952, + "step": 3224 + }, + { + "epoch": 0.27, + "learning_rate": 1.713259418472351e-05, + "loss": 0.4802, + "step": 3225 + }, + { + "epoch": 0.27, + "learning_rate": 1.713069455019586e-05, + "loss": 0.4934, + "step": 3226 + }, + { + "epoch": 0.27, + "learning_rate": 1.712879439201967e-05, + "loss": 0.5037, + "step": 3227 + }, + { + "epoch": 0.27, + "learning_rate": 1.7126893710334465e-05, + "loss": 0.497, + "step": 3228 + }, + { + "epoch": 0.27, + "learning_rate": 1.7124992505279833e-05, + "loss": 0.4945, + "step": 3229 + }, + { + "epoch": 0.27, + "learning_rate": 1.712309077699538e-05, + "loss": 0.4899, + "step": 3230 + }, + { + "epoch": 0.27, + "learning_rate": 1.712118852562077e-05, + "loss": 0.5034, + "step": 3231 + }, + { + "epoch": 0.27, + "learning_rate": 1.71192857512957e-05, + "loss": 0.4879, + "step": 3232 + }, + { + "epoch": 0.27, + "learning_rate": 1.7117382454159887e-05, + "loss": 0.4883, + "step": 3233 + }, + { + "epoch": 0.27, + "learning_rate": 1.7115478634353117e-05, + "loss": 0.4988, + "step": 3234 + }, + { + "epoch": 0.27, + "learning_rate": 1.7113574292015185e-05, + "loss": 0.4861, + "step": 3235 + }, + { + "epoch": 0.27, + "learning_rate": 1.711166942728595e-05, + "loss": 0.5031, + "step": 3236 + }, + { + "epoch": 0.27, + "learning_rate": 1.710976404030529e-05, + "loss": 0.4695, + "step": 3237 + }, + { + "epoch": 0.27, + "learning_rate": 1.710785813121313e-05, + "loss": 0.4973, + "step": 3238 + }, + { + "epoch": 0.27, + "learning_rate": 1.7105951700149433e-05, + "loss": 0.5143, + "step": 3239 + }, + { + "epoch": 0.27, + "learning_rate": 1.7104044747254202e-05, + "loss": 0.4813, + "step": 3240 + }, + { + "epoch": 0.27, + "learning_rate": 1.7102137272667466e-05, + "loss": 0.513, + "step": 3241 + }, + { + "epoch": 0.27, + "learning_rate": 1.7100229276529314e-05, + "loss": 0.4643, + "step": 3242 + }, + { + "epoch": 0.27, + "learning_rate": 1.7098320758979854e-05, + "loss": 0.492, + "step": 3243 + }, + { + "epoch": 0.27, + "learning_rate": 1.7096411720159244e-05, + "loss": 0.4903, + "step": 3244 + }, + { + "epoch": 0.27, + "learning_rate": 1.7094502160207672e-05, + "loss": 0.5142, + "step": 3245 + }, + { + "epoch": 0.27, + "learning_rate": 1.7092592079265368e-05, + "loss": 0.4952, + "step": 3246 + }, + { + "epoch": 0.27, + "learning_rate": 1.7090681477472605e-05, + "loss": 0.491, + "step": 3247 + }, + { + "epoch": 0.27, + "learning_rate": 1.7088770354969685e-05, + "loss": 0.5151, + "step": 3248 + }, + { + "epoch": 0.27, + "learning_rate": 1.708685871189695e-05, + "loss": 0.503, + "step": 3249 + }, + { + "epoch": 0.27, + "learning_rate": 1.7084946548394797e-05, + "loss": 0.5048, + "step": 3250 + }, + { + "epoch": 0.27, + "learning_rate": 1.7083033864603632e-05, + "loss": 0.4966, + "step": 3251 + }, + { + "epoch": 0.27, + "learning_rate": 1.7081120660663923e-05, + "loss": 0.5089, + "step": 3252 + }, + { + "epoch": 0.27, + "learning_rate": 1.7079206936716163e-05, + "loss": 0.4987, + "step": 3253 + }, + { + "epoch": 0.27, + "learning_rate": 1.707729269290089e-05, + "loss": 0.4891, + "step": 3254 + }, + { + "epoch": 0.27, + "learning_rate": 1.707537792935868e-05, + "loss": 0.4912, + "step": 3255 + }, + { + "epoch": 0.27, + "learning_rate": 1.7073462646230144e-05, + "loss": 0.4958, + "step": 3256 + }, + { + "epoch": 0.27, + "learning_rate": 1.7071546843655932e-05, + "loss": 0.4796, + "step": 3257 + }, + { + "epoch": 0.27, + "learning_rate": 1.706963052177673e-05, + "loss": 0.494, + "step": 3258 + }, + { + "epoch": 0.27, + "learning_rate": 1.706771368073327e-05, + "loss": 0.5072, + "step": 3259 + }, + { + "epoch": 0.27, + "learning_rate": 1.7065796320666312e-05, + "loss": 0.5034, + "step": 3260 + }, + { + "epoch": 0.27, + "learning_rate": 1.7063878441716665e-05, + "loss": 0.5014, + "step": 3261 + }, + { + "epoch": 0.27, + "learning_rate": 1.7061960044025162e-05, + "loss": 0.509, + "step": 3262 + }, + { + "epoch": 0.27, + "learning_rate": 1.706004112773269e-05, + "loss": 0.504, + "step": 3263 + }, + { + "epoch": 0.27, + "learning_rate": 1.7058121692980157e-05, + "loss": 0.494, + "step": 3264 + }, + { + "epoch": 0.27, + "learning_rate": 1.7056201739908528e-05, + "loss": 0.494, + "step": 3265 + }, + { + "epoch": 0.27, + "learning_rate": 1.705428126865879e-05, + "loss": 0.4973, + "step": 3266 + }, + { + "epoch": 0.27, + "learning_rate": 1.7052360279371978e-05, + "loss": 0.4877, + "step": 3267 + }, + { + "epoch": 0.27, + "learning_rate": 1.705043877218916e-05, + "loss": 0.4844, + "step": 3268 + }, + { + "epoch": 0.27, + "learning_rate": 1.7048516747251444e-05, + "loss": 0.5011, + "step": 3269 + }, + { + "epoch": 0.27, + "learning_rate": 1.704659420469997e-05, + "loss": 0.4979, + "step": 3270 + }, + { + "epoch": 0.27, + "learning_rate": 1.7044671144675935e-05, + "loss": 0.4596, + "step": 3271 + }, + { + "epoch": 0.27, + "learning_rate": 1.7042747567320548e-05, + "loss": 0.5083, + "step": 3272 + }, + { + "epoch": 0.27, + "learning_rate": 1.704082347277507e-05, + "loss": 0.4956, + "step": 3273 + }, + { + "epoch": 0.27, + "learning_rate": 1.7038898861180805e-05, + "loss": 0.481, + "step": 3274 + }, + { + "epoch": 0.27, + "learning_rate": 1.7036973732679084e-05, + "loss": 0.507, + "step": 3275 + }, + { + "epoch": 0.27, + "learning_rate": 1.7035048087411283e-05, + "loss": 0.4831, + "step": 3276 + }, + { + "epoch": 0.27, + "learning_rate": 1.703312192551881e-05, + "loss": 0.4758, + "step": 3277 + }, + { + "epoch": 0.27, + "learning_rate": 1.703119524714311e-05, + "loss": 0.503, + "step": 3278 + }, + { + "epoch": 0.27, + "learning_rate": 1.702926805242568e-05, + "loss": 0.508, + "step": 3279 + }, + { + "epoch": 0.27, + "learning_rate": 1.7027340341508043e-05, + "loss": 0.5148, + "step": 3280 + }, + { + "epoch": 0.27, + "learning_rate": 1.702541211453176e-05, + "loss": 0.469, + "step": 3281 + }, + { + "epoch": 0.27, + "learning_rate": 1.702348337163843e-05, + "loss": 0.4877, + "step": 3282 + }, + { + "epoch": 0.27, + "learning_rate": 1.7021554112969696e-05, + "loss": 0.5001, + "step": 3283 + }, + { + "epoch": 0.27, + "learning_rate": 1.701962433866723e-05, + "loss": 0.4817, + "step": 3284 + }, + { + "epoch": 0.27, + "learning_rate": 1.7017694048872756e-05, + "loss": 0.5152, + "step": 3285 + }, + { + "epoch": 0.27, + "learning_rate": 1.7015763243728014e-05, + "loss": 0.5012, + "step": 3286 + }, + { + "epoch": 0.28, + "learning_rate": 1.70138319233748e-05, + "loss": 0.4863, + "step": 3287 + }, + { + "epoch": 0.28, + "learning_rate": 1.7011900087954945e-05, + "loss": 0.4832, + "step": 3288 + }, + { + "epoch": 0.28, + "learning_rate": 1.7009967737610312e-05, + "loss": 0.5042, + "step": 3289 + }, + { + "epoch": 0.28, + "learning_rate": 1.70080348724828e-05, + "loss": 0.5057, + "step": 3290 + }, + { + "epoch": 0.28, + "learning_rate": 1.7006101492714362e-05, + "loss": 0.5154, + "step": 3291 + }, + { + "epoch": 0.28, + "learning_rate": 1.7004167598446967e-05, + "loss": 0.4931, + "step": 3292 + }, + { + "epoch": 0.28, + "learning_rate": 1.700223318982264e-05, + "loss": 0.5065, + "step": 3293 + }, + { + "epoch": 0.28, + "learning_rate": 1.7000298266983428e-05, + "loss": 0.4968, + "step": 3294 + }, + { + "epoch": 0.28, + "learning_rate": 1.699836283007143e-05, + "loss": 0.4878, + "step": 3295 + }, + { + "epoch": 0.28, + "learning_rate": 1.6996426879228775e-05, + "loss": 0.4811, + "step": 3296 + }, + { + "epoch": 0.28, + "learning_rate": 1.6994490414597627e-05, + "loss": 0.5043, + "step": 3297 + }, + { + "epoch": 0.28, + "learning_rate": 1.6992553436320195e-05, + "loss": 0.4804, + "step": 3298 + }, + { + "epoch": 0.28, + "learning_rate": 1.6990615944538725e-05, + "loss": 0.481, + "step": 3299 + }, + { + "epoch": 0.28, + "learning_rate": 1.6988677939395496e-05, + "loss": 0.4824, + "step": 3300 + }, + { + "epoch": 0.28, + "learning_rate": 1.698673942103283e-05, + "loss": 0.4943, + "step": 3301 + }, + { + "epoch": 0.28, + "learning_rate": 1.6984800389593076e-05, + "loss": 0.4982, + "step": 3302 + }, + { + "epoch": 0.28, + "learning_rate": 1.6982860845218637e-05, + "loss": 0.4838, + "step": 3303 + }, + { + "epoch": 0.28, + "learning_rate": 1.698092078805194e-05, + "loss": 0.5223, + "step": 3304 + }, + { + "epoch": 0.28, + "learning_rate": 1.6978980218235454e-05, + "loss": 0.4791, + "step": 3305 + }, + { + "epoch": 0.28, + "learning_rate": 1.697703913591169e-05, + "loss": 0.4881, + "step": 3306 + }, + { + "epoch": 0.28, + "learning_rate": 1.6975097541223195e-05, + "loss": 0.4824, + "step": 3307 + }, + { + "epoch": 0.28, + "learning_rate": 1.6973155434312544e-05, + "loss": 0.4667, + "step": 3308 + }, + { + "epoch": 0.28, + "learning_rate": 1.6971212815322365e-05, + "loss": 0.509, + "step": 3309 + }, + { + "epoch": 0.28, + "learning_rate": 1.696926968439531e-05, + "loss": 0.5058, + "step": 3310 + }, + { + "epoch": 0.28, + "learning_rate": 1.6967326041674076e-05, + "loss": 0.5017, + "step": 3311 + }, + { + "epoch": 0.28, + "learning_rate": 1.69653818873014e-05, + "loss": 0.4986, + "step": 3312 + }, + { + "epoch": 0.28, + "learning_rate": 1.6963437221420046e-05, + "loss": 0.5003, + "step": 3313 + }, + { + "epoch": 0.28, + "learning_rate": 1.6961492044172824e-05, + "loss": 0.4991, + "step": 3314 + }, + { + "epoch": 0.28, + "learning_rate": 1.6959546355702584e-05, + "loss": 0.495, + "step": 3315 + }, + { + "epoch": 0.28, + "learning_rate": 1.6957600156152206e-05, + "loss": 0.4848, + "step": 3316 + }, + { + "epoch": 0.28, + "learning_rate": 1.6955653445664612e-05, + "loss": 0.4958, + "step": 3317 + }, + { + "epoch": 0.28, + "learning_rate": 1.695370622438276e-05, + "loss": 0.4899, + "step": 3318 + }, + { + "epoch": 0.28, + "learning_rate": 1.6951758492449646e-05, + "loss": 0.4963, + "step": 3319 + }, + { + "epoch": 0.28, + "learning_rate": 1.6949810250008302e-05, + "loss": 0.4902, + "step": 3320 + }, + { + "epoch": 0.28, + "learning_rate": 1.69478614972018e-05, + "loss": 0.4889, + "step": 3321 + }, + { + "epoch": 0.28, + "learning_rate": 1.694591223417325e-05, + "loss": 0.4899, + "step": 3322 + }, + { + "epoch": 0.28, + "learning_rate": 1.694396246106579e-05, + "loss": 0.4928, + "step": 3323 + }, + { + "epoch": 0.28, + "learning_rate": 1.6942012178022613e-05, + "loss": 0.5079, + "step": 3324 + }, + { + "epoch": 0.28, + "learning_rate": 1.6940061385186936e-05, + "loss": 0.48, + "step": 3325 + }, + { + "epoch": 0.28, + "learning_rate": 1.6938110082702014e-05, + "loss": 0.4855, + "step": 3326 + }, + { + "epoch": 0.28, + "learning_rate": 1.6936158270711148e-05, + "loss": 0.4925, + "step": 3327 + }, + { + "epoch": 0.28, + "learning_rate": 1.6934205949357666e-05, + "loss": 0.4942, + "step": 3328 + }, + { + "epoch": 0.28, + "learning_rate": 1.693225311878494e-05, + "loss": 0.507, + "step": 3329 + }, + { + "epoch": 0.28, + "learning_rate": 1.6930299779136382e-05, + "loss": 0.4764, + "step": 3330 + }, + { + "epoch": 0.28, + "learning_rate": 1.6928345930555432e-05, + "loss": 0.49, + "step": 3331 + }, + { + "epoch": 0.28, + "learning_rate": 1.6926391573185576e-05, + "loss": 0.4877, + "step": 3332 + }, + { + "epoch": 0.28, + "learning_rate": 1.692443670717033e-05, + "loss": 0.491, + "step": 3333 + }, + { + "epoch": 0.28, + "learning_rate": 1.6922481332653248e-05, + "loss": 0.4942, + "step": 3334 + }, + { + "epoch": 0.28, + "learning_rate": 1.6920525449777937e-05, + "loss": 0.4978, + "step": 3335 + }, + { + "epoch": 0.28, + "learning_rate": 1.691856905868802e-05, + "loss": 0.4789, + "step": 3336 + }, + { + "epoch": 0.28, + "learning_rate": 1.6916612159527166e-05, + "loss": 0.4907, + "step": 3337 + }, + { + "epoch": 0.28, + "learning_rate": 1.6914654752439083e-05, + "loss": 0.5074, + "step": 3338 + }, + { + "epoch": 0.28, + "learning_rate": 1.691269683756752e-05, + "loss": 0.4883, + "step": 3339 + }, + { + "epoch": 0.28, + "learning_rate": 1.6910738415056245e-05, + "loss": 0.4935, + "step": 3340 + }, + { + "epoch": 0.28, + "learning_rate": 1.6908779485049093e-05, + "loss": 0.5326, + "step": 3341 + }, + { + "epoch": 0.28, + "learning_rate": 1.6906820047689907e-05, + "loss": 0.5007, + "step": 3342 + }, + { + "epoch": 0.28, + "learning_rate": 1.6904860103122587e-05, + "loss": 0.473, + "step": 3343 + }, + { + "epoch": 0.28, + "learning_rate": 1.6902899651491056e-05, + "loss": 0.4961, + "step": 3344 + }, + { + "epoch": 0.28, + "learning_rate": 1.690093869293929e-05, + "loss": 0.4919, + "step": 3345 + }, + { + "epoch": 0.28, + "learning_rate": 1.6898977227611288e-05, + "loss": 0.5026, + "step": 3346 + }, + { + "epoch": 0.28, + "learning_rate": 1.6897015255651093e-05, + "loss": 0.5022, + "step": 3347 + }, + { + "epoch": 0.28, + "learning_rate": 1.6895052777202784e-05, + "loss": 0.4966, + "step": 3348 + }, + { + "epoch": 0.28, + "learning_rate": 1.689308979241048e-05, + "loss": 0.511, + "step": 3349 + }, + { + "epoch": 0.28, + "learning_rate": 1.6891126301418334e-05, + "loss": 0.4936, + "step": 3350 + }, + { + "epoch": 0.28, + "learning_rate": 1.688916230437053e-05, + "loss": 0.4949, + "step": 3351 + }, + { + "epoch": 0.28, + "learning_rate": 1.68871978014113e-05, + "loss": 0.504, + "step": 3352 + }, + { + "epoch": 0.28, + "learning_rate": 1.6885232792684914e-05, + "loss": 0.4937, + "step": 3353 + }, + { + "epoch": 0.28, + "learning_rate": 1.6883267278335668e-05, + "loss": 0.5026, + "step": 3354 + }, + { + "epoch": 0.28, + "learning_rate": 1.68813012585079e-05, + "loss": 0.4734, + "step": 3355 + }, + { + "epoch": 0.28, + "learning_rate": 1.687933473334599e-05, + "loss": 0.4808, + "step": 3356 + }, + { + "epoch": 0.28, + "learning_rate": 1.6877367702994353e-05, + "loss": 0.4932, + "step": 3357 + }, + { + "epoch": 0.28, + "learning_rate": 1.6875400167597433e-05, + "loss": 0.5041, + "step": 3358 + }, + { + "epoch": 0.28, + "learning_rate": 1.6873432127299725e-05, + "loss": 0.4932, + "step": 3359 + }, + { + "epoch": 0.28, + "learning_rate": 1.6871463582245753e-05, + "loss": 0.4834, + "step": 3360 + }, + { + "epoch": 0.28, + "learning_rate": 1.6869494532580072e-05, + "loss": 0.499, + "step": 3361 + }, + { + "epoch": 0.28, + "learning_rate": 1.6867524978447286e-05, + "loss": 0.4741, + "step": 3362 + }, + { + "epoch": 0.28, + "learning_rate": 1.6865554919992026e-05, + "loss": 0.5121, + "step": 3363 + }, + { + "epoch": 0.28, + "learning_rate": 1.6863584357358974e-05, + "loss": 0.5057, + "step": 3364 + }, + { + "epoch": 0.28, + "learning_rate": 1.686161329069283e-05, + "loss": 0.4854, + "step": 3365 + }, + { + "epoch": 0.28, + "learning_rate": 1.685964172013835e-05, + "loss": 0.4994, + "step": 3366 + }, + { + "epoch": 0.28, + "learning_rate": 1.685766964584031e-05, + "loss": 0.4862, + "step": 3367 + }, + { + "epoch": 0.28, + "learning_rate": 1.685569706794354e-05, + "loss": 0.4974, + "step": 3368 + }, + { + "epoch": 0.28, + "learning_rate": 1.6853723986592885e-05, + "loss": 0.5175, + "step": 3369 + }, + { + "epoch": 0.28, + "learning_rate": 1.685175040193325e-05, + "loss": 0.5038, + "step": 3370 + }, + { + "epoch": 0.28, + "learning_rate": 1.6849776314109568e-05, + "loss": 0.5083, + "step": 3371 + }, + { + "epoch": 0.28, + "learning_rate": 1.6847801723266798e-05, + "loss": 0.5001, + "step": 3372 + }, + { + "epoch": 0.28, + "learning_rate": 1.6845826629549952e-05, + "loss": 0.5107, + "step": 3373 + }, + { + "epoch": 0.28, + "learning_rate": 1.6843851033104076e-05, + "loss": 0.5127, + "step": 3374 + }, + { + "epoch": 0.28, + "learning_rate": 1.6841874934074244e-05, + "loss": 0.491, + "step": 3375 + }, + { + "epoch": 0.28, + "learning_rate": 1.6839898332605575e-05, + "loss": 0.495, + "step": 3376 + }, + { + "epoch": 0.28, + "learning_rate": 1.683792122884322e-05, + "loss": 0.4971, + "step": 3377 + }, + { + "epoch": 0.28, + "learning_rate": 1.6835943622932377e-05, + "loss": 0.5114, + "step": 3378 + }, + { + "epoch": 0.28, + "learning_rate": 1.6833965515018257e-05, + "loss": 0.4907, + "step": 3379 + }, + { + "epoch": 0.28, + "learning_rate": 1.683198690524614e-05, + "loss": 0.519, + "step": 3380 + }, + { + "epoch": 0.28, + "learning_rate": 1.6830007793761323e-05, + "loss": 0.4936, + "step": 3381 + }, + { + "epoch": 0.28, + "learning_rate": 1.682802818070914e-05, + "loss": 0.4878, + "step": 3382 + }, + { + "epoch": 0.28, + "learning_rate": 1.6826048066234967e-05, + "loss": 0.4965, + "step": 3383 + }, + { + "epoch": 0.28, + "learning_rate": 1.6824067450484214e-05, + "loss": 0.5071, + "step": 3384 + }, + { + "epoch": 0.28, + "learning_rate": 1.682208633360233e-05, + "loss": 0.4647, + "step": 3385 + }, + { + "epoch": 0.28, + "learning_rate": 1.6820104715734803e-05, + "loss": 0.484, + "step": 3386 + }, + { + "epoch": 0.28, + "learning_rate": 1.6818122597027152e-05, + "loss": 0.4863, + "step": 3387 + }, + { + "epoch": 0.28, + "learning_rate": 1.681613997762494e-05, + "loss": 0.4965, + "step": 3388 + }, + { + "epoch": 0.28, + "learning_rate": 1.6814156857673753e-05, + "loss": 0.4948, + "step": 3389 + }, + { + "epoch": 0.28, + "learning_rate": 1.6812173237319232e-05, + "loss": 0.4834, + "step": 3390 + }, + { + "epoch": 0.28, + "learning_rate": 1.6810189116707042e-05, + "loss": 0.5055, + "step": 3391 + }, + { + "epoch": 0.28, + "learning_rate": 1.6808204495982887e-05, + "loss": 0.5029, + "step": 3392 + }, + { + "epoch": 0.28, + "learning_rate": 1.6806219375292513e-05, + "loss": 0.495, + "step": 3393 + }, + { + "epoch": 0.28, + "learning_rate": 1.68042337547817e-05, + "loss": 0.4815, + "step": 3394 + }, + { + "epoch": 0.28, + "learning_rate": 1.6802247634596256e-05, + "loss": 0.4937, + "step": 3395 + }, + { + "epoch": 0.28, + "learning_rate": 1.680026101488204e-05, + "loss": 0.5125, + "step": 3396 + }, + { + "epoch": 0.28, + "learning_rate": 1.679827389578494e-05, + "loss": 0.4883, + "step": 3397 + }, + { + "epoch": 0.28, + "learning_rate": 1.6796286277450882e-05, + "loss": 0.503, + "step": 3398 + }, + { + "epoch": 0.28, + "learning_rate": 1.6794298160025822e-05, + "loss": 0.4779, + "step": 3399 + }, + { + "epoch": 0.28, + "learning_rate": 1.6792309543655774e-05, + "loss": 0.4657, + "step": 3400 + }, + { + "epoch": 0.28, + "learning_rate": 1.6790320428486757e-05, + "loss": 0.5017, + "step": 3401 + }, + { + "epoch": 0.28, + "learning_rate": 1.6788330814664856e-05, + "loss": 0.4918, + "step": 3402 + }, + { + "epoch": 0.28, + "learning_rate": 1.678634070233617e-05, + "loss": 0.4799, + "step": 3403 + }, + { + "epoch": 0.28, + "learning_rate": 1.6784350091646852e-05, + "loss": 0.4953, + "step": 3404 + }, + { + "epoch": 0.28, + "learning_rate": 1.6782358982743084e-05, + "loss": 0.5107, + "step": 3405 + }, + { + "epoch": 0.28, + "learning_rate": 1.6780367375771075e-05, + "loss": 0.4833, + "step": 3406 + }, + { + "epoch": 0.29, + "learning_rate": 1.6778375270877095e-05, + "loss": 0.493, + "step": 3407 + }, + { + "epoch": 0.29, + "learning_rate": 1.6776382668207424e-05, + "loss": 0.4983, + "step": 3408 + }, + { + "epoch": 0.29, + "learning_rate": 1.6774389567908394e-05, + "loss": 0.482, + "step": 3409 + }, + { + "epoch": 0.29, + "learning_rate": 1.677239597012638e-05, + "loss": 0.502, + "step": 3410 + }, + { + "epoch": 0.29, + "learning_rate": 1.6770401875007766e-05, + "loss": 0.5169, + "step": 3411 + }, + { + "epoch": 0.29, + "learning_rate": 1.6768407282699e-05, + "loss": 0.4878, + "step": 3412 + }, + { + "epoch": 0.29, + "learning_rate": 1.6766412193346555e-05, + "loss": 0.5064, + "step": 3413 + }, + { + "epoch": 0.29, + "learning_rate": 1.6764416607096942e-05, + "loss": 0.5101, + "step": 3414 + }, + { + "epoch": 0.29, + "learning_rate": 1.6762420524096712e-05, + "loss": 0.5111, + "step": 3415 + }, + { + "epoch": 0.29, + "learning_rate": 1.6760423944492442e-05, + "loss": 0.4933, + "step": 3416 + }, + { + "epoch": 0.29, + "learning_rate": 1.6758426868430758e-05, + "loss": 0.4991, + "step": 3417 + }, + { + "epoch": 0.29, + "learning_rate": 1.6756429296058314e-05, + "loss": 0.5079, + "step": 3418 + }, + { + "epoch": 0.29, + "learning_rate": 1.6754431227521806e-05, + "loss": 0.4799, + "step": 3419 + }, + { + "epoch": 0.29, + "learning_rate": 1.6752432662967958e-05, + "loss": 0.4992, + "step": 3420 + }, + { + "epoch": 0.29, + "learning_rate": 1.6750433602543546e-05, + "loss": 0.5113, + "step": 3421 + }, + { + "epoch": 0.29, + "learning_rate": 1.674843404639537e-05, + "loss": 0.4779, + "step": 3422 + }, + { + "epoch": 0.29, + "learning_rate": 1.6746433994670258e-05, + "loss": 0.509, + "step": 3423 + }, + { + "epoch": 0.29, + "learning_rate": 1.6744433447515098e-05, + "loss": 0.4972, + "step": 3424 + }, + { + "epoch": 0.29, + "learning_rate": 1.67424324050768e-05, + "loss": 0.4903, + "step": 3425 + }, + { + "epoch": 0.29, + "learning_rate": 1.6740430867502307e-05, + "loss": 0.4894, + "step": 3426 + }, + { + "epoch": 0.29, + "learning_rate": 1.6738428834938606e-05, + "loss": 0.4954, + "step": 3427 + }, + { + "epoch": 0.29, + "learning_rate": 1.6736426307532722e-05, + "loss": 0.4985, + "step": 3428 + }, + { + "epoch": 0.29, + "learning_rate": 1.6734423285431705e-05, + "loss": 0.4952, + "step": 3429 + }, + { + "epoch": 0.29, + "learning_rate": 1.6732419768782656e-05, + "loss": 0.5189, + "step": 3430 + }, + { + "epoch": 0.29, + "learning_rate": 1.6730415757732702e-05, + "loss": 0.4859, + "step": 3431 + }, + { + "epoch": 0.29, + "learning_rate": 1.6728411252429006e-05, + "loss": 0.5037, + "step": 3432 + }, + { + "epoch": 0.29, + "learning_rate": 1.672640625301877e-05, + "loss": 0.4977, + "step": 3433 + }, + { + "epoch": 0.29, + "learning_rate": 1.6724400759649243e-05, + "loss": 0.4831, + "step": 3434 + }, + { + "epoch": 0.29, + "learning_rate": 1.672239477246769e-05, + "loss": 0.4928, + "step": 3435 + }, + { + "epoch": 0.29, + "learning_rate": 1.6720388291621423e-05, + "loss": 0.4899, + "step": 3436 + }, + { + "epoch": 0.29, + "learning_rate": 1.6718381317257793e-05, + "loss": 0.4841, + "step": 3437 + }, + { + "epoch": 0.29, + "learning_rate": 1.6716373849524187e-05, + "loss": 0.5012, + "step": 3438 + }, + { + "epoch": 0.29, + "learning_rate": 1.671436588856802e-05, + "loss": 0.5064, + "step": 3439 + }, + { + "epoch": 0.29, + "learning_rate": 1.6712357434536747e-05, + "loss": 0.4881, + "step": 3440 + }, + { + "epoch": 0.29, + "learning_rate": 1.6710348487577863e-05, + "loss": 0.4914, + "step": 3441 + }, + { + "epoch": 0.29, + "learning_rate": 1.6708339047838897e-05, + "loss": 0.4985, + "step": 3442 + }, + { + "epoch": 0.29, + "learning_rate": 1.6706329115467412e-05, + "loss": 0.4928, + "step": 3443 + }, + { + "epoch": 0.29, + "learning_rate": 1.670431869061101e-05, + "loss": 0.4741, + "step": 3444 + }, + { + "epoch": 0.29, + "learning_rate": 1.6702307773417334e-05, + "loss": 0.4799, + "step": 3445 + }, + { + "epoch": 0.29, + "learning_rate": 1.6700296364034048e-05, + "loss": 0.5049, + "step": 3446 + }, + { + "epoch": 0.29, + "learning_rate": 1.6698284462608866e-05, + "loss": 0.5034, + "step": 3447 + }, + { + "epoch": 0.29, + "learning_rate": 1.6696272069289533e-05, + "loss": 0.4924, + "step": 3448 + }, + { + "epoch": 0.29, + "learning_rate": 1.6694259184223833e-05, + "loss": 0.5037, + "step": 3449 + }, + { + "epoch": 0.29, + "learning_rate": 1.6692245807559578e-05, + "loss": 0.4939, + "step": 3450 + }, + { + "epoch": 0.29, + "learning_rate": 1.669023193944463e-05, + "loss": 0.4952, + "step": 3451 + }, + { + "epoch": 0.29, + "learning_rate": 1.668821758002688e-05, + "loss": 0.4887, + "step": 3452 + }, + { + "epoch": 0.29, + "learning_rate": 1.668620272945424e-05, + "loss": 0.5063, + "step": 3453 + }, + { + "epoch": 0.29, + "learning_rate": 1.6684187387874686e-05, + "loss": 0.4739, + "step": 3454 + }, + { + "epoch": 0.29, + "learning_rate": 1.668217155543621e-05, + "loss": 0.5013, + "step": 3455 + }, + { + "epoch": 0.29, + "learning_rate": 1.668015523228685e-05, + "loss": 0.4862, + "step": 3456 + }, + { + "epoch": 0.29, + "learning_rate": 1.6678138418574673e-05, + "loss": 0.4973, + "step": 3457 + }, + { + "epoch": 0.29, + "learning_rate": 1.6676121114447784e-05, + "loss": 0.4797, + "step": 3458 + }, + { + "epoch": 0.29, + "learning_rate": 1.6674103320054335e-05, + "loss": 0.5063, + "step": 3459 + }, + { + "epoch": 0.29, + "learning_rate": 1.6672085035542497e-05, + "loss": 0.4745, + "step": 3460 + }, + { + "epoch": 0.29, + "learning_rate": 1.667006626106048e-05, + "loss": 0.4841, + "step": 3461 + }, + { + "epoch": 0.29, + "learning_rate": 1.6668046996756544e-05, + "loss": 0.4975, + "step": 3462 + }, + { + "epoch": 0.29, + "learning_rate": 1.6666027242778972e-05, + "loss": 0.5235, + "step": 3463 + }, + { + "epoch": 0.29, + "learning_rate": 1.666400699927608e-05, + "loss": 0.4883, + "step": 3464 + }, + { + "epoch": 0.29, + "learning_rate": 1.6661986266396235e-05, + "loss": 0.5063, + "step": 3465 + }, + { + "epoch": 0.29, + "learning_rate": 1.6659965044287826e-05, + "loss": 0.4858, + "step": 3466 + }, + { + "epoch": 0.29, + "learning_rate": 1.6657943333099287e-05, + "loss": 0.4754, + "step": 3467 + }, + { + "epoch": 0.29, + "learning_rate": 1.6655921132979082e-05, + "loss": 0.4743, + "step": 3468 + }, + { + "epoch": 0.29, + "learning_rate": 1.6653898444075713e-05, + "loss": 0.4887, + "step": 3469 + }, + { + "epoch": 0.29, + "learning_rate": 1.6651875266537718e-05, + "loss": 0.4948, + "step": 3470 + }, + { + "epoch": 0.29, + "learning_rate": 1.664985160051367e-05, + "loss": 0.4873, + "step": 3471 + }, + { + "epoch": 0.29, + "learning_rate": 1.6647827446152183e-05, + "loss": 0.486, + "step": 3472 + }, + { + "epoch": 0.29, + "learning_rate": 1.6645802803601893e-05, + "loss": 0.4984, + "step": 3473 + }, + { + "epoch": 0.29, + "learning_rate": 1.664377767301149e-05, + "loss": 0.5056, + "step": 3474 + }, + { + "epoch": 0.29, + "learning_rate": 1.664175205452969e-05, + "loss": 0.4926, + "step": 3475 + }, + { + "epoch": 0.29, + "learning_rate": 1.663972594830524e-05, + "loss": 0.5159, + "step": 3476 + }, + { + "epoch": 0.29, + "learning_rate": 1.6637699354486936e-05, + "loss": 0.5252, + "step": 3477 + }, + { + "epoch": 0.29, + "learning_rate": 1.6635672273223597e-05, + "loss": 0.4872, + "step": 3478 + }, + { + "epoch": 0.29, + "learning_rate": 1.663364470466409e-05, + "loss": 0.4877, + "step": 3479 + }, + { + "epoch": 0.29, + "learning_rate": 1.6631616648957303e-05, + "loss": 0.4879, + "step": 3480 + }, + { + "epoch": 0.29, + "learning_rate": 1.6629588106252173e-05, + "loss": 0.4756, + "step": 3481 + }, + { + "epoch": 0.29, + "learning_rate": 1.6627559076697672e-05, + "loss": 0.5409, + "step": 3482 + }, + { + "epoch": 0.29, + "learning_rate": 1.6625529560442793e-05, + "loss": 0.5017, + "step": 3483 + }, + { + "epoch": 0.29, + "learning_rate": 1.6623499557636584e-05, + "loss": 0.4925, + "step": 3484 + }, + { + "epoch": 0.29, + "learning_rate": 1.6621469068428114e-05, + "loss": 0.4936, + "step": 3485 + }, + { + "epoch": 0.29, + "learning_rate": 1.66194380929665e-05, + "loss": 0.5126, + "step": 3486 + }, + { + "epoch": 0.29, + "learning_rate": 1.6617406631400884e-05, + "loss": 0.4967, + "step": 3487 + }, + { + "epoch": 0.29, + "learning_rate": 1.6615374683880445e-05, + "loss": 0.4864, + "step": 3488 + }, + { + "epoch": 0.29, + "learning_rate": 1.6613342250554406e-05, + "loss": 0.4922, + "step": 3489 + }, + { + "epoch": 0.29, + "learning_rate": 1.6611309331572022e-05, + "loss": 0.4962, + "step": 3490 + }, + { + "epoch": 0.29, + "learning_rate": 1.6609275927082577e-05, + "loss": 0.4899, + "step": 3491 + }, + { + "epoch": 0.29, + "learning_rate": 1.66072420372354e-05, + "loss": 0.4947, + "step": 3492 + }, + { + "epoch": 0.29, + "learning_rate": 1.660520766217985e-05, + "loss": 0.5001, + "step": 3493 + }, + { + "epoch": 0.29, + "learning_rate": 1.6603172802065317e-05, + "loss": 0.5018, + "step": 3494 + }, + { + "epoch": 0.29, + "learning_rate": 1.6601137457041242e-05, + "loss": 0.5025, + "step": 3495 + }, + { + "epoch": 0.29, + "learning_rate": 1.6599101627257087e-05, + "loss": 0.4887, + "step": 3496 + }, + { + "epoch": 0.29, + "learning_rate": 1.6597065312862358e-05, + "loss": 0.4875, + "step": 3497 + }, + { + "epoch": 0.29, + "learning_rate": 1.659502851400659e-05, + "loss": 0.5023, + "step": 3498 + }, + { + "epoch": 0.29, + "learning_rate": 1.6592991230839355e-05, + "loss": 0.4966, + "step": 3499 + }, + { + "epoch": 0.29, + "learning_rate": 1.659095346351027e-05, + "loss": 0.5032, + "step": 3500 + }, + { + "epoch": 0.29, + "learning_rate": 1.6588915212168977e-05, + "loss": 0.4823, + "step": 3501 + }, + { + "epoch": 0.29, + "learning_rate": 1.658687647696516e-05, + "loss": 0.5014, + "step": 3502 + }, + { + "epoch": 0.29, + "learning_rate": 1.658483725804853e-05, + "loss": 0.4557, + "step": 3503 + }, + { + "epoch": 0.29, + "learning_rate": 1.6582797555568834e-05, + "loss": 0.5108, + "step": 3504 + }, + { + "epoch": 0.29, + "learning_rate": 1.658075736967587e-05, + "loss": 0.5026, + "step": 3505 + }, + { + "epoch": 0.29, + "learning_rate": 1.6578716700519454e-05, + "loss": 0.5017, + "step": 3506 + }, + { + "epoch": 0.29, + "learning_rate": 1.657667554824945e-05, + "loss": 0.4901, + "step": 3507 + }, + { + "epoch": 0.29, + "learning_rate": 1.6574633913015742e-05, + "loss": 0.4907, + "step": 3508 + }, + { + "epoch": 0.29, + "learning_rate": 1.657259179496827e-05, + "loss": 0.4864, + "step": 3509 + }, + { + "epoch": 0.29, + "learning_rate": 1.6570549194256995e-05, + "loss": 0.495, + "step": 3510 + }, + { + "epoch": 0.29, + "learning_rate": 1.6568506111031913e-05, + "loss": 0.5021, + "step": 3511 + }, + { + "epoch": 0.29, + "learning_rate": 1.6566462545443066e-05, + "loss": 0.5074, + "step": 3512 + }, + { + "epoch": 0.29, + "learning_rate": 1.656441849764052e-05, + "loss": 0.4989, + "step": 3513 + }, + { + "epoch": 0.29, + "learning_rate": 1.6562373967774382e-05, + "loss": 0.509, + "step": 3514 + }, + { + "epoch": 0.29, + "learning_rate": 1.6560328955994796e-05, + "loss": 0.5201, + "step": 3515 + }, + { + "epoch": 0.29, + "learning_rate": 1.655828346245194e-05, + "loss": 0.5027, + "step": 3516 + }, + { + "epoch": 0.29, + "learning_rate": 1.655623748729602e-05, + "loss": 0.4831, + "step": 3517 + }, + { + "epoch": 0.29, + "learning_rate": 1.655419103067729e-05, + "loss": 0.5112, + "step": 3518 + }, + { + "epoch": 0.29, + "learning_rate": 1.6552144092746032e-05, + "loss": 0.4874, + "step": 3519 + }, + { + "epoch": 0.29, + "learning_rate": 1.6550096673652565e-05, + "loss": 0.4991, + "step": 3520 + }, + { + "epoch": 0.29, + "learning_rate": 1.654804877354724e-05, + "loss": 0.4899, + "step": 3521 + }, + { + "epoch": 0.29, + "learning_rate": 1.654600039258045e-05, + "loss": 0.5151, + "step": 3522 + }, + { + "epoch": 0.29, + "learning_rate": 1.6543951530902618e-05, + "loss": 0.5163, + "step": 3523 + }, + { + "epoch": 0.29, + "learning_rate": 1.6541902188664206e-05, + "loss": 0.4763, + "step": 3524 + }, + { + "epoch": 0.29, + "learning_rate": 1.6539852366015702e-05, + "loss": 0.5012, + "step": 3525 + }, + { + "epoch": 0.3, + "learning_rate": 1.6537802063107646e-05, + "loss": 0.4732, + "step": 3526 + }, + { + "epoch": 0.3, + "learning_rate": 1.6535751280090598e-05, + "loss": 0.51, + "step": 3527 + }, + { + "epoch": 0.3, + "learning_rate": 1.6533700017115162e-05, + "loss": 0.5077, + "step": 3528 + }, + { + "epoch": 0.3, + "learning_rate": 1.653164827433197e-05, + "loss": 0.5029, + "step": 3529 + }, + { + "epoch": 0.3, + "learning_rate": 1.6529596051891696e-05, + "loss": 0.4791, + "step": 3530 + }, + { + "epoch": 0.3, + "learning_rate": 1.6527543349945047e-05, + "loss": 0.5035, + "step": 3531 + }, + { + "epoch": 0.3, + "learning_rate": 1.6525490168642765e-05, + "loss": 0.4892, + "step": 3532 + }, + { + "epoch": 0.3, + "learning_rate": 1.6523436508135624e-05, + "loss": 0.4915, + "step": 3533 + }, + { + "epoch": 0.3, + "learning_rate": 1.6521382368574442e-05, + "loss": 0.4816, + "step": 3534 + }, + { + "epoch": 0.3, + "learning_rate": 1.651932775011006e-05, + "loss": 0.481, + "step": 3535 + }, + { + "epoch": 0.3, + "learning_rate": 1.6517272652893367e-05, + "loss": 0.4885, + "step": 3536 + }, + { + "epoch": 0.3, + "learning_rate": 1.6515217077075276e-05, + "loss": 0.506, + "step": 3537 + }, + { + "epoch": 0.3, + "learning_rate": 1.651316102280674e-05, + "loss": 0.4849, + "step": 3538 + }, + { + "epoch": 0.3, + "learning_rate": 1.6511104490238753e-05, + "loss": 0.5038, + "step": 3539 + }, + { + "epoch": 0.3, + "learning_rate": 1.6509047479522332e-05, + "loss": 0.5172, + "step": 3540 + }, + { + "epoch": 0.3, + "learning_rate": 1.650698999080854e-05, + "loss": 0.4906, + "step": 3541 + }, + { + "epoch": 0.3, + "learning_rate": 1.6504932024248462e-05, + "loss": 0.4895, + "step": 3542 + }, + { + "epoch": 0.3, + "learning_rate": 1.6502873579993238e-05, + "loss": 0.4769, + "step": 3543 + }, + { + "epoch": 0.3, + "learning_rate": 1.6500814658194024e-05, + "loss": 0.5035, + "step": 3544 + }, + { + "epoch": 0.3, + "learning_rate": 1.649875525900202e-05, + "loss": 0.5003, + "step": 3545 + }, + { + "epoch": 0.3, + "learning_rate": 1.649669538256846e-05, + "loss": 0.4854, + "step": 3546 + }, + { + "epoch": 0.3, + "learning_rate": 1.6494635029044613e-05, + "loss": 0.4941, + "step": 3547 + }, + { + "epoch": 0.3, + "learning_rate": 1.649257419858178e-05, + "loss": 0.4851, + "step": 3548 + }, + { + "epoch": 0.3, + "learning_rate": 1.6490512891331304e-05, + "loss": 0.4964, + "step": 3549 + }, + { + "epoch": 0.3, + "learning_rate": 1.6488451107444556e-05, + "loss": 0.5009, + "step": 3550 + }, + { + "epoch": 0.3, + "learning_rate": 1.648638884707295e-05, + "loss": 0.496, + "step": 3551 + }, + { + "epoch": 0.3, + "learning_rate": 1.6484326110367924e-05, + "loss": 0.5007, + "step": 3552 + }, + { + "epoch": 0.3, + "learning_rate": 1.648226289748096e-05, + "loss": 0.5075, + "step": 3553 + }, + { + "epoch": 0.3, + "learning_rate": 1.648019920856357e-05, + "loss": 0.4816, + "step": 3554 + }, + { + "epoch": 0.3, + "learning_rate": 1.6478135043767303e-05, + "loss": 0.5059, + "step": 3555 + }, + { + "epoch": 0.3, + "learning_rate": 1.647607040324374e-05, + "loss": 0.4913, + "step": 3556 + }, + { + "epoch": 0.3, + "learning_rate": 1.6474005287144507e-05, + "loss": 0.4945, + "step": 3557 + }, + { + "epoch": 0.3, + "learning_rate": 1.647193969562125e-05, + "loss": 0.4799, + "step": 3558 + }, + { + "epoch": 0.3, + "learning_rate": 1.6469873628825665e-05, + "loss": 0.5039, + "step": 3559 + }, + { + "epoch": 0.3, + "learning_rate": 1.6467807086909468e-05, + "loss": 0.4956, + "step": 3560 + }, + { + "epoch": 0.3, + "learning_rate": 1.646574007002442e-05, + "loss": 0.5098, + "step": 3561 + }, + { + "epoch": 0.3, + "learning_rate": 1.6463672578322315e-05, + "loss": 0.4929, + "step": 3562 + }, + { + "epoch": 0.3, + "learning_rate": 1.646160461195498e-05, + "loss": 0.4958, + "step": 3563 + }, + { + "epoch": 0.3, + "learning_rate": 1.6459536171074278e-05, + "loss": 0.4969, + "step": 3564 + }, + { + "epoch": 0.3, + "learning_rate": 1.6457467255832108e-05, + "loss": 0.5093, + "step": 3565 + }, + { + "epoch": 0.3, + "learning_rate": 1.64553978663804e-05, + "loss": 0.4717, + "step": 3566 + }, + { + "epoch": 0.3, + "learning_rate": 1.645332800287112e-05, + "loss": 0.498, + "step": 3567 + }, + { + "epoch": 0.3, + "learning_rate": 1.645125766545628e-05, + "loss": 0.5006, + "step": 3568 + }, + { + "epoch": 0.3, + "learning_rate": 1.6449186854287903e-05, + "loss": 0.5093, + "step": 3569 + }, + { + "epoch": 0.3, + "learning_rate": 1.644711556951807e-05, + "loss": 0.5111, + "step": 3570 + }, + { + "epoch": 0.3, + "learning_rate": 1.6445043811298887e-05, + "loss": 0.5057, + "step": 3571 + }, + { + "epoch": 0.3, + "learning_rate": 1.644297157978249e-05, + "loss": 0.4916, + "step": 3572 + }, + { + "epoch": 0.3, + "learning_rate": 1.644089887512106e-05, + "loss": 0.4835, + "step": 3573 + }, + { + "epoch": 0.3, + "learning_rate": 1.6438825697466808e-05, + "loss": 0.4892, + "step": 3574 + }, + { + "epoch": 0.3, + "learning_rate": 1.6436752046971975e-05, + "loss": 0.4817, + "step": 3575 + }, + { + "epoch": 0.3, + "learning_rate": 1.6434677923788848e-05, + "loss": 0.483, + "step": 3576 + }, + { + "epoch": 0.3, + "learning_rate": 1.6432603328069732e-05, + "loss": 0.5143, + "step": 3577 + }, + { + "epoch": 0.3, + "learning_rate": 1.643052825996699e-05, + "loss": 0.507, + "step": 3578 + }, + { + "epoch": 0.3, + "learning_rate": 1.6428452719632994e-05, + "loss": 0.4962, + "step": 3579 + }, + { + "epoch": 0.3, + "learning_rate": 1.642637670722017e-05, + "loss": 0.5072, + "step": 3580 + }, + { + "epoch": 0.3, + "learning_rate": 1.642430022288097e-05, + "loss": 0.4931, + "step": 3581 + }, + { + "epoch": 0.3, + "learning_rate": 1.6422223266767883e-05, + "loss": 0.4838, + "step": 3582 + }, + { + "epoch": 0.3, + "learning_rate": 1.642014583903343e-05, + "loss": 0.5034, + "step": 3583 + }, + { + "epoch": 0.3, + "learning_rate": 1.641806793983017e-05, + "loss": 0.5004, + "step": 3584 + }, + { + "epoch": 0.3, + "learning_rate": 1.6415989569310698e-05, + "loss": 0.4913, + "step": 3585 + }, + { + "epoch": 0.3, + "learning_rate": 1.6413910727627637e-05, + "loss": 0.4919, + "step": 3586 + }, + { + "epoch": 0.3, + "learning_rate": 1.6411831414933647e-05, + "loss": 0.5063, + "step": 3587 + }, + { + "epoch": 0.3, + "learning_rate": 1.6409751631381428e-05, + "loss": 0.481, + "step": 3588 + }, + { + "epoch": 0.3, + "learning_rate": 1.640767137712371e-05, + "loss": 0.5164, + "step": 3589 + }, + { + "epoch": 0.3, + "learning_rate": 1.6405590652313256e-05, + "loss": 0.4764, + "step": 3590 + }, + { + "epoch": 0.3, + "learning_rate": 1.640350945710287e-05, + "loss": 0.4895, + "step": 3591 + }, + { + "epoch": 0.3, + "learning_rate": 1.640142779164538e-05, + "loss": 0.5138, + "step": 3592 + }, + { + "epoch": 0.3, + "learning_rate": 1.6399345656093663e-05, + "loss": 0.476, + "step": 3593 + }, + { + "epoch": 0.3, + "learning_rate": 1.6397263050600615e-05, + "loss": 0.4773, + "step": 3594 + }, + { + "epoch": 0.3, + "learning_rate": 1.6395179975319178e-05, + "loss": 0.5097, + "step": 3595 + }, + { + "epoch": 0.3, + "learning_rate": 1.6393096430402323e-05, + "loss": 0.5019, + "step": 3596 + }, + { + "epoch": 0.3, + "learning_rate": 1.6391012416003053e-05, + "loss": 0.4923, + "step": 3597 + }, + { + "epoch": 0.3, + "learning_rate": 1.638892793227442e-05, + "loss": 0.4851, + "step": 3598 + }, + { + "epoch": 0.3, + "learning_rate": 1.6386842979369487e-05, + "loss": 0.4981, + "step": 3599 + }, + { + "epoch": 0.3, + "learning_rate": 1.6384757557441373e-05, + "loss": 0.5019, + "step": 3600 + }, + { + "epoch": 0.3, + "learning_rate": 1.6382671666643223e-05, + "loss": 0.492, + "step": 3601 + }, + { + "epoch": 0.3, + "learning_rate": 1.638058530712821e-05, + "loss": 0.4817, + "step": 3602 + }, + { + "epoch": 0.3, + "learning_rate": 1.6378498479049553e-05, + "loss": 0.5039, + "step": 3603 + }, + { + "epoch": 0.3, + "learning_rate": 1.6376411182560498e-05, + "loss": 0.5044, + "step": 3604 + }, + { + "epoch": 0.3, + "learning_rate": 1.6374323417814325e-05, + "loss": 0.5089, + "step": 3605 + }, + { + "epoch": 0.3, + "learning_rate": 1.6372235184964357e-05, + "loss": 0.4915, + "step": 3606 + }, + { + "epoch": 0.3, + "learning_rate": 1.6370146484163935e-05, + "loss": 0.4752, + "step": 3607 + }, + { + "epoch": 0.3, + "learning_rate": 1.6368057315566454e-05, + "loss": 0.5043, + "step": 3608 + }, + { + "epoch": 0.3, + "learning_rate": 1.636596767932533e-05, + "loss": 0.5013, + "step": 3609 + }, + { + "epoch": 0.3, + "learning_rate": 1.636387757559402e-05, + "loss": 0.482, + "step": 3610 + }, + { + "epoch": 0.3, + "learning_rate": 1.6361787004526006e-05, + "loss": 0.524, + "step": 3611 + }, + { + "epoch": 0.3, + "learning_rate": 1.635969596627482e-05, + "loss": 0.5078, + "step": 3612 + }, + { + "epoch": 0.3, + "learning_rate": 1.635760446099401e-05, + "loss": 0.4964, + "step": 3613 + }, + { + "epoch": 0.3, + "learning_rate": 1.6355512488837173e-05, + "loss": 0.4827, + "step": 3614 + }, + { + "epoch": 0.3, + "learning_rate": 1.6353420049957932e-05, + "loss": 0.4924, + "step": 3615 + }, + { + "epoch": 0.3, + "learning_rate": 1.6351327144509954e-05, + "loss": 0.5235, + "step": 3616 + }, + { + "epoch": 0.3, + "learning_rate": 1.6349233772646923e-05, + "loss": 0.4919, + "step": 3617 + }, + { + "epoch": 0.3, + "learning_rate": 1.6347139934522572e-05, + "loss": 0.5046, + "step": 3618 + }, + { + "epoch": 0.3, + "learning_rate": 1.6345045630290664e-05, + "loss": 0.5007, + "step": 3619 + }, + { + "epoch": 0.3, + "learning_rate": 1.6342950860105e-05, + "loss": 0.4592, + "step": 3620 + }, + { + "epoch": 0.3, + "learning_rate": 1.63408556241194e-05, + "loss": 0.4886, + "step": 3621 + }, + { + "epoch": 0.3, + "learning_rate": 1.633875992248774e-05, + "loss": 0.4956, + "step": 3622 + }, + { + "epoch": 0.3, + "learning_rate": 1.633666375536392e-05, + "loss": 0.4919, + "step": 3623 + }, + { + "epoch": 0.3, + "learning_rate": 1.6334567122901862e-05, + "loss": 0.5073, + "step": 3624 + }, + { + "epoch": 0.3, + "learning_rate": 1.633247002525555e-05, + "loss": 0.5198, + "step": 3625 + }, + { + "epoch": 0.3, + "learning_rate": 1.6330372462578972e-05, + "loss": 0.481, + "step": 3626 + }, + { + "epoch": 0.3, + "learning_rate": 1.6328274435026174e-05, + "loss": 0.4838, + "step": 3627 + }, + { + "epoch": 0.3, + "learning_rate": 1.6326175942751222e-05, + "loss": 0.4937, + "step": 3628 + }, + { + "epoch": 0.3, + "learning_rate": 1.632407698590822e-05, + "loss": 0.4734, + "step": 3629 + }, + { + "epoch": 0.3, + "learning_rate": 1.6321977564651313e-05, + "loss": 0.4866, + "step": 3630 + }, + { + "epoch": 0.3, + "learning_rate": 1.6319877679134662e-05, + "loss": 0.5065, + "step": 3631 + }, + { + "epoch": 0.3, + "learning_rate": 1.6317777329512485e-05, + "loss": 0.4771, + "step": 3632 + }, + { + "epoch": 0.3, + "learning_rate": 1.6315676515939015e-05, + "loss": 0.4991, + "step": 3633 + }, + { + "epoch": 0.3, + "learning_rate": 1.6313575238568535e-05, + "loss": 0.494, + "step": 3634 + }, + { + "epoch": 0.3, + "learning_rate": 1.6311473497555343e-05, + "loss": 0.4731, + "step": 3635 + }, + { + "epoch": 0.3, + "learning_rate": 1.6309371293053793e-05, + "loss": 0.5089, + "step": 3636 + }, + { + "epoch": 0.3, + "learning_rate": 1.630726862521826e-05, + "loss": 0.4857, + "step": 3637 + }, + { + "epoch": 0.3, + "learning_rate": 1.6305165494203147e-05, + "loss": 0.4843, + "step": 3638 + }, + { + "epoch": 0.3, + "learning_rate": 1.6303061900162912e-05, + "loss": 0.5002, + "step": 3639 + }, + { + "epoch": 0.3, + "learning_rate": 1.6300957843252027e-05, + "loss": 0.4996, + "step": 3640 + }, + { + "epoch": 0.3, + "learning_rate": 1.6298853323625003e-05, + "loss": 0.4843, + "step": 3641 + }, + { + "epoch": 0.3, + "learning_rate": 1.6296748341436386e-05, + "loss": 0.491, + "step": 3642 + }, + { + "epoch": 0.3, + "learning_rate": 1.6294642896840768e-05, + "loss": 0.4923, + "step": 3643 + }, + { + "epoch": 0.3, + "learning_rate": 1.6292536989992754e-05, + "loss": 0.4955, + "step": 3644 + }, + { + "epoch": 0.3, + "learning_rate": 1.6290430621046994e-05, + "loss": 0.4928, + "step": 3645 + }, + { + "epoch": 0.31, + "learning_rate": 1.6288323790158175e-05, + "loss": 0.4971, + "step": 3646 + }, + { + "epoch": 0.31, + "learning_rate": 1.6286216497481014e-05, + "loss": 0.488, + "step": 3647 + }, + { + "epoch": 0.31, + "learning_rate": 1.6284108743170256e-05, + "loss": 0.493, + "step": 3648 + }, + { + "epoch": 0.31, + "learning_rate": 1.628200052738069e-05, + "loss": 0.4973, + "step": 3649 + }, + { + "epoch": 0.31, + "learning_rate": 1.6279891850267134e-05, + "loss": 0.4951, + "step": 3650 + }, + { + "epoch": 0.31, + "learning_rate": 1.6277782711984446e-05, + "loss": 0.4991, + "step": 3651 + }, + { + "epoch": 0.31, + "learning_rate": 1.62756731126875e-05, + "loss": 0.4884, + "step": 3652 + }, + { + "epoch": 0.31, + "learning_rate": 1.6273563052531227e-05, + "loss": 0.4774, + "step": 3653 + }, + { + "epoch": 0.31, + "learning_rate": 1.6271452531670577e-05, + "loss": 0.4959, + "step": 3654 + }, + { + "epoch": 0.31, + "learning_rate": 1.6269341550260537e-05, + "loss": 0.4922, + "step": 3655 + }, + { + "epoch": 0.31, + "learning_rate": 1.6267230108456126e-05, + "loss": 0.5079, + "step": 3656 + }, + { + "epoch": 0.31, + "learning_rate": 1.6265118206412412e-05, + "loss": 0.482, + "step": 3657 + }, + { + "epoch": 0.31, + "learning_rate": 1.6263005844284468e-05, + "loss": 0.4812, + "step": 3658 + }, + { + "epoch": 0.31, + "learning_rate": 1.6260893022227425e-05, + "loss": 0.521, + "step": 3659 + }, + { + "epoch": 0.31, + "learning_rate": 1.6258779740396443e-05, + "loss": 0.4847, + "step": 3660 + }, + { + "epoch": 0.31, + "learning_rate": 1.6256665998946708e-05, + "loss": 0.499, + "step": 3661 + }, + { + "epoch": 0.31, + "learning_rate": 1.6254551798033444e-05, + "loss": 0.4978, + "step": 3662 + }, + { + "epoch": 0.31, + "learning_rate": 1.6252437137811913e-05, + "loss": 0.4887, + "step": 3663 + }, + { + "epoch": 0.31, + "learning_rate": 1.62503220184374e-05, + "loss": 0.4927, + "step": 3664 + }, + { + "epoch": 0.31, + "learning_rate": 1.624820644006524e-05, + "loss": 0.4999, + "step": 3665 + }, + { + "epoch": 0.31, + "learning_rate": 1.6246090402850783e-05, + "loss": 0.5203, + "step": 3666 + }, + { + "epoch": 0.31, + "learning_rate": 1.6243973906949434e-05, + "loss": 0.4929, + "step": 3667 + }, + { + "epoch": 0.31, + "learning_rate": 1.6241856952516604e-05, + "loss": 0.4796, + "step": 3668 + }, + { + "epoch": 0.31, + "learning_rate": 1.623973953970776e-05, + "loss": 0.4937, + "step": 3669 + }, + { + "epoch": 0.31, + "learning_rate": 1.6237621668678406e-05, + "loss": 0.4927, + "step": 3670 + }, + { + "epoch": 0.31, + "learning_rate": 1.6235503339584052e-05, + "loss": 0.4964, + "step": 3671 + }, + { + "epoch": 0.31, + "learning_rate": 1.6233384552580272e-05, + "loss": 0.4833, + "step": 3672 + }, + { + "epoch": 0.31, + "learning_rate": 1.6231265307822658e-05, + "loss": 0.4704, + "step": 3673 + }, + { + "epoch": 0.31, + "learning_rate": 1.622914560546684e-05, + "loss": 0.5002, + "step": 3674 + }, + { + "epoch": 0.31, + "learning_rate": 1.6227025445668473e-05, + "loss": 0.4905, + "step": 3675 + }, + { + "epoch": 0.31, + "learning_rate": 1.622490482858326e-05, + "loss": 0.4894, + "step": 3676 + }, + { + "epoch": 0.31, + "learning_rate": 1.6222783754366926e-05, + "loss": 0.4877, + "step": 3677 + }, + { + "epoch": 0.31, + "learning_rate": 1.6220662223175233e-05, + "loss": 0.4793, + "step": 3678 + }, + { + "epoch": 0.31, + "learning_rate": 1.6218540235163983e-05, + "loss": 0.4839, + "step": 3679 + }, + { + "epoch": 0.31, + "learning_rate": 1.6216417790489005e-05, + "loss": 0.4906, + "step": 3680 + }, + { + "epoch": 0.31, + "learning_rate": 1.6214294889306158e-05, + "loss": 0.4857, + "step": 3681 + }, + { + "epoch": 0.31, + "learning_rate": 1.621217153177134e-05, + "loss": 0.4932, + "step": 3682 + }, + { + "epoch": 0.31, + "learning_rate": 1.621004771804049e-05, + "loss": 0.4943, + "step": 3683 + }, + { + "epoch": 0.31, + "learning_rate": 1.620792344826956e-05, + "loss": 0.517, + "step": 3684 + }, + { + "epoch": 0.31, + "learning_rate": 1.6205798722614552e-05, + "loss": 0.4828, + "step": 3685 + }, + { + "epoch": 0.31, + "learning_rate": 1.6203673541231497e-05, + "loss": 0.473, + "step": 3686 + }, + { + "epoch": 0.31, + "learning_rate": 1.6201547904276463e-05, + "loss": 0.4931, + "step": 3687 + }, + { + "epoch": 0.31, + "learning_rate": 1.6199421811905542e-05, + "loss": 0.508, + "step": 3688 + }, + { + "epoch": 0.31, + "learning_rate": 1.619729526427487e-05, + "loss": 0.4883, + "step": 3689 + }, + { + "epoch": 0.31, + "learning_rate": 1.6195168261540612e-05, + "loss": 0.4819, + "step": 3690 + }, + { + "epoch": 0.31, + "learning_rate": 1.6193040803858965e-05, + "loss": 0.5097, + "step": 3691 + }, + { + "epoch": 0.31, + "learning_rate": 1.6190912891386154e-05, + "loss": 0.5071, + "step": 3692 + }, + { + "epoch": 0.31, + "learning_rate": 1.6188784524278455e-05, + "loss": 0.4829, + "step": 3693 + }, + { + "epoch": 0.31, + "learning_rate": 1.6186655702692162e-05, + "loss": 0.4916, + "step": 3694 + }, + { + "epoch": 0.31, + "learning_rate": 1.6184526426783607e-05, + "loss": 0.5002, + "step": 3695 + }, + { + "epoch": 0.31, + "learning_rate": 1.618239669670915e-05, + "loss": 0.4863, + "step": 3696 + }, + { + "epoch": 0.31, + "learning_rate": 1.61802665126252e-05, + "loss": 0.5061, + "step": 3697 + }, + { + "epoch": 0.31, + "learning_rate": 1.6178135874688183e-05, + "loss": 0.4785, + "step": 3698 + }, + { + "epoch": 0.31, + "learning_rate": 1.6176004783054556e-05, + "loss": 0.5046, + "step": 3699 + }, + { + "epoch": 0.31, + "learning_rate": 1.6173873237880832e-05, + "loss": 0.5005, + "step": 3700 + }, + { + "epoch": 0.31, + "learning_rate": 1.6171741239323537e-05, + "loss": 0.4856, + "step": 3701 + }, + { + "epoch": 0.31, + "learning_rate": 1.6169608787539234e-05, + "loss": 0.5233, + "step": 3702 + }, + { + "epoch": 0.31, + "learning_rate": 1.6167475882684522e-05, + "loss": 0.4767, + "step": 3703 + }, + { + "epoch": 0.31, + "learning_rate": 1.6165342524916035e-05, + "loss": 0.5088, + "step": 3704 + }, + { + "epoch": 0.31, + "learning_rate": 1.6163208714390437e-05, + "loss": 0.5114, + "step": 3705 + }, + { + "epoch": 0.31, + "learning_rate": 1.6161074451264425e-05, + "loss": 0.503, + "step": 3706 + }, + { + "epoch": 0.31, + "learning_rate": 1.615893973569473e-05, + "loss": 0.4942, + "step": 3707 + }, + { + "epoch": 0.31, + "learning_rate": 1.615680456783812e-05, + "loss": 0.4998, + "step": 3708 + }, + { + "epoch": 0.31, + "learning_rate": 1.615466894785139e-05, + "loss": 0.5169, + "step": 3709 + }, + { + "epoch": 0.31, + "learning_rate": 1.6152532875891372e-05, + "loss": 0.4753, + "step": 3710 + }, + { + "epoch": 0.31, + "learning_rate": 1.6150396352114926e-05, + "loss": 0.481, + "step": 3711 + }, + { + "epoch": 0.31, + "learning_rate": 1.6148259376678957e-05, + "loss": 0.4966, + "step": 3712 + }, + { + "epoch": 0.31, + "learning_rate": 1.6146121949740393e-05, + "loss": 0.5167, + "step": 3713 + }, + { + "epoch": 0.31, + "learning_rate": 1.6143984071456197e-05, + "loss": 0.4961, + "step": 3714 + }, + { + "epoch": 0.31, + "learning_rate": 1.614184574198336e-05, + "loss": 0.5012, + "step": 3715 + }, + { + "epoch": 0.31, + "learning_rate": 1.613970696147892e-05, + "loss": 0.4894, + "step": 3716 + }, + { + "epoch": 0.31, + "learning_rate": 1.613756773009994e-05, + "loss": 0.4937, + "step": 3717 + }, + { + "epoch": 0.31, + "learning_rate": 1.6135428048003513e-05, + "loss": 0.4853, + "step": 3718 + }, + { + "epoch": 0.31, + "learning_rate": 1.6133287915346772e-05, + "loss": 0.5156, + "step": 3719 + }, + { + "epoch": 0.31, + "learning_rate": 1.6131147332286872e-05, + "loss": 0.4906, + "step": 3720 + }, + { + "epoch": 0.31, + "learning_rate": 1.6129006298981015e-05, + "loss": 0.4942, + "step": 3721 + }, + { + "epoch": 0.31, + "learning_rate": 1.6126864815586427e-05, + "loss": 0.5072, + "step": 3722 + }, + { + "epoch": 0.31, + "learning_rate": 1.6124722882260372e-05, + "loss": 0.5006, + "step": 3723 + }, + { + "epoch": 0.31, + "learning_rate": 1.6122580499160144e-05, + "loss": 0.4895, + "step": 3724 + }, + { + "epoch": 0.31, + "learning_rate": 1.6120437666443067e-05, + "loss": 0.5041, + "step": 3725 + }, + { + "epoch": 0.31, + "learning_rate": 1.6118294384266506e-05, + "loss": 0.4864, + "step": 3726 + }, + { + "epoch": 0.31, + "learning_rate": 1.6116150652787852e-05, + "loss": 0.4983, + "step": 3727 + }, + { + "epoch": 0.31, + "learning_rate": 1.6114006472164535e-05, + "loss": 0.5044, + "step": 3728 + }, + { + "epoch": 0.31, + "learning_rate": 1.6111861842554014e-05, + "loss": 0.4779, + "step": 3729 + }, + { + "epoch": 0.31, + "learning_rate": 1.6109716764113778e-05, + "loss": 0.4895, + "step": 3730 + }, + { + "epoch": 0.31, + "learning_rate": 1.6107571237001356e-05, + "loss": 0.4795, + "step": 3731 + }, + { + "epoch": 0.31, + "learning_rate": 1.6105425261374305e-05, + "loss": 0.4991, + "step": 3732 + }, + { + "epoch": 0.31, + "learning_rate": 1.6103278837390218e-05, + "loss": 0.4792, + "step": 3733 + }, + { + "epoch": 0.31, + "learning_rate": 1.6101131965206714e-05, + "loss": 0.4891, + "step": 3734 + }, + { + "epoch": 0.31, + "learning_rate": 1.6098984644981463e-05, + "loss": 0.5137, + "step": 3735 + }, + { + "epoch": 0.31, + "learning_rate": 1.6096836876872143e-05, + "loss": 0.5098, + "step": 3736 + }, + { + "epoch": 0.31, + "learning_rate": 1.6094688661036483e-05, + "loss": 0.5053, + "step": 3737 + }, + { + "epoch": 0.31, + "learning_rate": 1.6092539997632236e-05, + "loss": 0.4915, + "step": 3738 + }, + { + "epoch": 0.31, + "learning_rate": 1.609039088681719e-05, + "loss": 0.4916, + "step": 3739 + }, + { + "epoch": 0.31, + "learning_rate": 1.6088241328749172e-05, + "loss": 0.484, + "step": 3740 + }, + { + "epoch": 0.31, + "learning_rate": 1.6086091323586034e-05, + "loss": 0.5012, + "step": 3741 + }, + { + "epoch": 0.31, + "learning_rate": 1.6083940871485663e-05, + "loss": 0.4669, + "step": 3742 + }, + { + "epoch": 0.31, + "learning_rate": 1.608178997260598e-05, + "loss": 0.4923, + "step": 3743 + }, + { + "epoch": 0.31, + "learning_rate": 1.6079638627104937e-05, + "loss": 0.4927, + "step": 3744 + }, + { + "epoch": 0.31, + "learning_rate": 1.6077486835140518e-05, + "loss": 0.4755, + "step": 3745 + }, + { + "epoch": 0.31, + "learning_rate": 1.6075334596870746e-05, + "loss": 0.4855, + "step": 3746 + }, + { + "epoch": 0.31, + "learning_rate": 1.607318191245367e-05, + "loss": 0.4979, + "step": 3747 + }, + { + "epoch": 0.31, + "learning_rate": 1.607102878204738e-05, + "loss": 0.4754, + "step": 3748 + }, + { + "epoch": 0.31, + "learning_rate": 1.6068875205809978e-05, + "loss": 0.5086, + "step": 3749 + }, + { + "epoch": 0.31, + "learning_rate": 1.606672118389963e-05, + "loss": 0.5113, + "step": 3750 + }, + { + "epoch": 0.31, + "learning_rate": 1.6064566716474506e-05, + "loss": 0.5014, + "step": 3751 + }, + { + "epoch": 0.31, + "learning_rate": 1.606241180369283e-05, + "loss": 0.4899, + "step": 3752 + }, + { + "epoch": 0.31, + "learning_rate": 1.606025644571285e-05, + "loss": 0.5102, + "step": 3753 + }, + { + "epoch": 0.31, + "learning_rate": 1.6058100642692837e-05, + "loss": 0.4875, + "step": 3754 + }, + { + "epoch": 0.31, + "learning_rate": 1.6055944394791113e-05, + "loss": 0.5025, + "step": 3755 + }, + { + "epoch": 0.31, + "learning_rate": 1.605378770216602e-05, + "loss": 0.4748, + "step": 3756 + }, + { + "epoch": 0.31, + "learning_rate": 1.605163056497594e-05, + "loss": 0.4893, + "step": 3757 + }, + { + "epoch": 0.31, + "learning_rate": 1.6049472983379285e-05, + "loss": 0.4999, + "step": 3758 + }, + { + "epoch": 0.31, + "learning_rate": 1.6047314957534487e-05, + "loss": 0.5149, + "step": 3759 + }, + { + "epoch": 0.31, + "learning_rate": 1.604515648760004e-05, + "loss": 0.4722, + "step": 3760 + }, + { + "epoch": 0.31, + "learning_rate": 1.6042997573734437e-05, + "loss": 0.5037, + "step": 3761 + }, + { + "epoch": 0.31, + "learning_rate": 1.6040838216096233e-05, + "loss": 0.4684, + "step": 3762 + }, + { + "epoch": 0.31, + "learning_rate": 1.6038678414843994e-05, + "loss": 0.5232, + "step": 3763 + }, + { + "epoch": 0.31, + "learning_rate": 1.6036518170136326e-05, + "loss": 0.4807, + "step": 3764 + }, + { + "epoch": 0.31, + "learning_rate": 1.603435748213187e-05, + "loss": 0.4972, + "step": 3765 + }, + { + "epoch": 0.32, + "learning_rate": 1.6032196350989306e-05, + "loss": 0.4843, + "step": 3766 + }, + { + "epoch": 0.32, + "learning_rate": 1.603003477686733e-05, + "loss": 0.4668, + "step": 3767 + }, + { + "epoch": 0.32, + "learning_rate": 1.6027872759924678e-05, + "loss": 0.4949, + "step": 3768 + }, + { + "epoch": 0.32, + "learning_rate": 1.6025710300320124e-05, + "loss": 0.4948, + "step": 3769 + }, + { + "epoch": 0.32, + "learning_rate": 1.6023547398212467e-05, + "loss": 0.4746, + "step": 3770 + }, + { + "epoch": 0.32, + "learning_rate": 1.6021384053760546e-05, + "loss": 0.476, + "step": 3771 + }, + { + "epoch": 0.32, + "learning_rate": 1.6019220267123223e-05, + "loss": 0.4951, + "step": 3772 + }, + { + "epoch": 0.32, + "learning_rate": 1.60170560384594e-05, + "loss": 0.4662, + "step": 3773 + }, + { + "epoch": 0.32, + "learning_rate": 1.601489136792801e-05, + "loss": 0.4972, + "step": 3774 + }, + { + "epoch": 0.32, + "learning_rate": 1.6012726255688013e-05, + "loss": 0.4956, + "step": 3775 + }, + { + "epoch": 0.32, + "learning_rate": 1.6010560701898405e-05, + "loss": 0.4779, + "step": 3776 + }, + { + "epoch": 0.32, + "learning_rate": 1.6008394706718224e-05, + "loss": 0.5058, + "step": 3777 + }, + { + "epoch": 0.32, + "learning_rate": 1.6006228270306526e-05, + "loss": 0.5015, + "step": 3778 + }, + { + "epoch": 0.32, + "learning_rate": 1.6004061392822407e-05, + "loss": 0.4791, + "step": 3779 + }, + { + "epoch": 0.32, + "learning_rate": 1.6001894074424987e-05, + "loss": 0.4736, + "step": 3780 + }, + { + "epoch": 0.32, + "learning_rate": 1.5999726315273435e-05, + "loss": 0.4803, + "step": 3781 + }, + { + "epoch": 0.32, + "learning_rate": 1.599755811552693e-05, + "loss": 0.5038, + "step": 3782 + }, + { + "epoch": 0.32, + "learning_rate": 1.5995389475344715e-05, + "loss": 0.4888, + "step": 3783 + }, + { + "epoch": 0.32, + "learning_rate": 1.5993220394886024e-05, + "loss": 0.4943, + "step": 3784 + }, + { + "epoch": 0.32, + "learning_rate": 1.5991050874310156e-05, + "loss": 0.5088, + "step": 3785 + }, + { + "epoch": 0.32, + "learning_rate": 1.5988880913776434e-05, + "loss": 0.4833, + "step": 3786 + }, + { + "epoch": 0.32, + "learning_rate": 1.5986710513444205e-05, + "loss": 0.499, + "step": 3787 + }, + { + "epoch": 0.32, + "learning_rate": 1.5984539673472856e-05, + "loss": 0.4909, + "step": 3788 + }, + { + "epoch": 0.32, + "learning_rate": 1.5982368394021804e-05, + "loss": 0.4929, + "step": 3789 + }, + { + "epoch": 0.32, + "learning_rate": 1.5980196675250504e-05, + "loss": 0.4894, + "step": 3790 + }, + { + "epoch": 0.32, + "learning_rate": 1.5978024517318428e-05, + "loss": 0.4776, + "step": 3791 + }, + { + "epoch": 0.32, + "learning_rate": 1.5975851920385103e-05, + "loss": 0.4832, + "step": 3792 + }, + { + "epoch": 0.32, + "learning_rate": 1.5973678884610062e-05, + "loss": 0.4832, + "step": 3793 + }, + { + "epoch": 0.32, + "learning_rate": 1.597150541015289e-05, + "loss": 0.4827, + "step": 3794 + }, + { + "epoch": 0.32, + "learning_rate": 1.5969331497173203e-05, + "loss": 0.4805, + "step": 3795 + }, + { + "epoch": 0.32, + "learning_rate": 1.5967157145830638e-05, + "loss": 0.4961, + "step": 3796 + }, + { + "epoch": 0.32, + "learning_rate": 1.596498235628487e-05, + "loss": 0.5165, + "step": 3797 + }, + { + "epoch": 0.32, + "learning_rate": 1.5962807128695606e-05, + "loss": 0.4927, + "step": 3798 + }, + { + "epoch": 0.32, + "learning_rate": 1.5960631463222592e-05, + "loss": 0.5033, + "step": 3799 + }, + { + "epoch": 0.32, + "learning_rate": 1.595845536002559e-05, + "loss": 0.4744, + "step": 3800 + }, + { + "epoch": 0.32, + "learning_rate": 1.5956278819264417e-05, + "loss": 0.4675, + "step": 3801 + }, + { + "epoch": 0.32, + "learning_rate": 1.5954101841098895e-05, + "loss": 0.4773, + "step": 3802 + }, + { + "epoch": 0.32, + "learning_rate": 1.59519244256889e-05, + "loss": 0.4848, + "step": 3803 + }, + { + "epoch": 0.32, + "learning_rate": 1.5949746573194334e-05, + "loss": 0.4883, + "step": 3804 + }, + { + "epoch": 0.32, + "learning_rate": 1.5947568283775125e-05, + "loss": 0.4869, + "step": 3805 + }, + { + "epoch": 0.32, + "learning_rate": 1.5945389557591237e-05, + "loss": 0.4972, + "step": 3806 + }, + { + "epoch": 0.32, + "learning_rate": 1.594321039480267e-05, + "loss": 0.4711, + "step": 3807 + }, + { + "epoch": 0.32, + "learning_rate": 1.5941030795569452e-05, + "loss": 0.4634, + "step": 3808 + }, + { + "epoch": 0.32, + "learning_rate": 1.5938850760051643e-05, + "loss": 0.4964, + "step": 3809 + }, + { + "epoch": 0.32, + "learning_rate": 1.5936670288409335e-05, + "loss": 0.4977, + "step": 3810 + }, + { + "epoch": 0.32, + "learning_rate": 1.5934489380802653e-05, + "loss": 0.5042, + "step": 3811 + }, + { + "epoch": 0.32, + "learning_rate": 1.5932308037391756e-05, + "loss": 0.493, + "step": 3812 + }, + { + "epoch": 0.32, + "learning_rate": 1.593012625833683e-05, + "loss": 0.4989, + "step": 3813 + }, + { + "epoch": 0.32, + "learning_rate": 1.59279440437981e-05, + "loss": 0.4855, + "step": 3814 + }, + { + "epoch": 0.32, + "learning_rate": 1.592576139393581e-05, + "loss": 0.483, + "step": 3815 + }, + { + "epoch": 0.32, + "learning_rate": 1.5923578308910254e-05, + "loss": 0.4849, + "step": 3816 + }, + { + "epoch": 0.32, + "learning_rate": 1.592139478888174e-05, + "loss": 0.483, + "step": 3817 + }, + { + "epoch": 0.32, + "learning_rate": 1.5919210834010628e-05, + "loss": 0.511, + "step": 3818 + }, + { + "epoch": 0.32, + "learning_rate": 1.5917026444457288e-05, + "loss": 0.4953, + "step": 3819 + }, + { + "epoch": 0.32, + "learning_rate": 1.591484162038214e-05, + "loss": 0.4849, + "step": 3820 + }, + { + "epoch": 0.32, + "learning_rate": 1.5912656361945626e-05, + "loss": 0.4783, + "step": 3821 + }, + { + "epoch": 0.32, + "learning_rate": 1.5910470669308217e-05, + "loss": 0.4872, + "step": 3822 + }, + { + "epoch": 0.32, + "learning_rate": 1.5908284542630425e-05, + "loss": 0.5001, + "step": 3823 + }, + { + "epoch": 0.32, + "learning_rate": 1.5906097982072793e-05, + "loss": 0.4711, + "step": 3824 + }, + { + "epoch": 0.32, + "learning_rate": 1.590391098779589e-05, + "loss": 0.468, + "step": 3825 + }, + { + "epoch": 0.32, + "learning_rate": 1.5901723559960322e-05, + "loss": 0.5036, + "step": 3826 + }, + { + "epoch": 0.32, + "learning_rate": 1.5899535698726723e-05, + "loss": 0.483, + "step": 3827 + }, + { + "epoch": 0.32, + "learning_rate": 1.5897347404255757e-05, + "loss": 0.4843, + "step": 3828 + }, + { + "epoch": 0.32, + "learning_rate": 1.589515867670813e-05, + "loss": 0.4897, + "step": 3829 + }, + { + "epoch": 0.32, + "learning_rate": 1.589296951624457e-05, + "loss": 0.4886, + "step": 3830 + }, + { + "epoch": 0.32, + "learning_rate": 1.5890779923025832e-05, + "loss": 0.4777, + "step": 3831 + }, + { + "epoch": 0.32, + "learning_rate": 1.5888589897212726e-05, + "loss": 0.495, + "step": 3832 + }, + { + "epoch": 0.32, + "learning_rate": 1.5886399438966068e-05, + "loss": 0.4896, + "step": 3833 + }, + { + "epoch": 0.32, + "learning_rate": 1.5884208548446716e-05, + "loss": 0.4846, + "step": 3834 + }, + { + "epoch": 0.32, + "learning_rate": 1.5882017225815566e-05, + "loss": 0.4673, + "step": 3835 + }, + { + "epoch": 0.32, + "learning_rate": 1.5879825471233538e-05, + "loss": 0.4854, + "step": 3836 + }, + { + "epoch": 0.32, + "learning_rate": 1.5877633284861577e-05, + "loss": 0.4916, + "step": 3837 + }, + { + "epoch": 0.32, + "learning_rate": 1.587544066686068e-05, + "loss": 0.4774, + "step": 3838 + }, + { + "epoch": 0.32, + "learning_rate": 1.5873247617391854e-05, + "loss": 0.4825, + "step": 3839 + }, + { + "epoch": 0.32, + "learning_rate": 1.5871054136616154e-05, + "loss": 0.4933, + "step": 3840 + }, + { + "epoch": 0.32, + "learning_rate": 1.5868860224694656e-05, + "loss": 0.5059, + "step": 3841 + }, + { + "epoch": 0.32, + "learning_rate": 1.586666588178848e-05, + "loss": 0.4819, + "step": 3842 + }, + { + "epoch": 0.32, + "learning_rate": 1.5864471108058755e-05, + "loss": 0.4753, + "step": 3843 + }, + { + "epoch": 0.32, + "learning_rate": 1.586227590366667e-05, + "loss": 0.5028, + "step": 3844 + }, + { + "epoch": 0.32, + "learning_rate": 1.586008026877342e-05, + "loss": 0.5122, + "step": 3845 + }, + { + "epoch": 0.32, + "learning_rate": 1.585788420354025e-05, + "loss": 0.5066, + "step": 3846 + }, + { + "epoch": 0.32, + "learning_rate": 1.5855687708128433e-05, + "loss": 0.4991, + "step": 3847 + }, + { + "epoch": 0.32, + "learning_rate": 1.5853490782699266e-05, + "loss": 0.4953, + "step": 3848 + }, + { + "epoch": 0.32, + "learning_rate": 1.5851293427414075e-05, + "loss": 0.4834, + "step": 3849 + }, + { + "epoch": 0.32, + "learning_rate": 1.584909564243424e-05, + "loss": 0.49, + "step": 3850 + }, + { + "epoch": 0.32, + "learning_rate": 1.5846897427921147e-05, + "loss": 0.4989, + "step": 3851 + }, + { + "epoch": 0.32, + "learning_rate": 1.584469878403623e-05, + "loss": 0.481, + "step": 3852 + }, + { + "epoch": 0.32, + "learning_rate": 1.5842499710940936e-05, + "loss": 0.5093, + "step": 3853 + }, + { + "epoch": 0.32, + "learning_rate": 1.5840300208796767e-05, + "loss": 0.4943, + "step": 3854 + }, + { + "epoch": 0.32, + "learning_rate": 1.5838100277765244e-05, + "loss": 0.4794, + "step": 3855 + }, + { + "epoch": 0.32, + "learning_rate": 1.5835899918007917e-05, + "loss": 0.4951, + "step": 3856 + }, + { + "epoch": 0.32, + "learning_rate": 1.5833699129686376e-05, + "loss": 0.4958, + "step": 3857 + }, + { + "epoch": 0.32, + "learning_rate": 1.5831497912962235e-05, + "loss": 0.5049, + "step": 3858 + }, + { + "epoch": 0.32, + "learning_rate": 1.5829296267997142e-05, + "loss": 0.4801, + "step": 3859 + }, + { + "epoch": 0.32, + "learning_rate": 1.582709419495277e-05, + "loss": 0.4781, + "step": 3860 + }, + { + "epoch": 0.32, + "learning_rate": 1.5824891693990845e-05, + "loss": 0.5053, + "step": 3861 + }, + { + "epoch": 0.32, + "learning_rate": 1.58226887652731e-05, + "loss": 0.5095, + "step": 3862 + }, + { + "epoch": 0.32, + "learning_rate": 1.582048540896131e-05, + "loss": 0.5, + "step": 3863 + }, + { + "epoch": 0.32, + "learning_rate": 1.581828162521728e-05, + "loss": 0.4818, + "step": 3864 + }, + { + "epoch": 0.32, + "learning_rate": 1.5816077414202848e-05, + "loss": 0.4957, + "step": 3865 + }, + { + "epoch": 0.32, + "learning_rate": 1.5813872776079882e-05, + "loss": 0.477, + "step": 3866 + }, + { + "epoch": 0.32, + "learning_rate": 1.581166771101028e-05, + "loss": 0.4875, + "step": 3867 + }, + { + "epoch": 0.32, + "learning_rate": 1.5809462219155976e-05, + "loss": 0.4905, + "step": 3868 + }, + { + "epoch": 0.32, + "learning_rate": 1.580725630067893e-05, + "loss": 0.4993, + "step": 3869 + }, + { + "epoch": 0.32, + "learning_rate": 1.5805049955741135e-05, + "loss": 0.486, + "step": 3870 + }, + { + "epoch": 0.32, + "learning_rate": 1.5802843184504614e-05, + "loss": 0.4895, + "step": 3871 + }, + { + "epoch": 0.32, + "learning_rate": 1.5800635987131426e-05, + "loss": 0.5033, + "step": 3872 + }, + { + "epoch": 0.32, + "learning_rate": 1.579842836378366e-05, + "loss": 0.4842, + "step": 3873 + }, + { + "epoch": 0.32, + "learning_rate": 1.579622031462343e-05, + "loss": 0.479, + "step": 3874 + }, + { + "epoch": 0.32, + "learning_rate": 1.5794011839812888e-05, + "loss": 0.5077, + "step": 3875 + }, + { + "epoch": 0.32, + "learning_rate": 1.579180293951422e-05, + "loss": 0.4942, + "step": 3876 + }, + { + "epoch": 0.32, + "learning_rate": 1.5789593613889632e-05, + "loss": 0.4722, + "step": 3877 + }, + { + "epoch": 0.32, + "learning_rate": 1.5787383863101366e-05, + "loss": 0.48, + "step": 3878 + }, + { + "epoch": 0.32, + "learning_rate": 1.5785173687311704e-05, + "loss": 0.4909, + "step": 3879 + }, + { + "epoch": 0.32, + "learning_rate": 1.5782963086682946e-05, + "loss": 0.4962, + "step": 3880 + }, + { + "epoch": 0.32, + "learning_rate": 1.5780752061377436e-05, + "loss": 0.502, + "step": 3881 + }, + { + "epoch": 0.32, + "learning_rate": 1.5778540611557538e-05, + "loss": 0.4961, + "step": 3882 + }, + { + "epoch": 0.32, + "learning_rate": 1.577632873738565e-05, + "loss": 0.506, + "step": 3883 + }, + { + "epoch": 0.32, + "learning_rate": 1.5774116439024206e-05, + "loss": 0.4868, + "step": 3884 + }, + { + "epoch": 0.33, + "learning_rate": 1.5771903716635666e-05, + "loss": 0.4888, + "step": 3885 + }, + { + "epoch": 0.33, + "learning_rate": 1.576969057038253e-05, + "loss": 0.5003, + "step": 3886 + }, + { + "epoch": 0.33, + "learning_rate": 1.5767477000427306e-05, + "loss": 0.4854, + "step": 3887 + }, + { + "epoch": 0.33, + "learning_rate": 1.576526300693257e-05, + "loss": 0.4996, + "step": 3888 + }, + { + "epoch": 0.33, + "learning_rate": 1.5763048590060894e-05, + "loss": 0.4976, + "step": 3889 + }, + { + "epoch": 0.33, + "learning_rate": 1.5760833749974898e-05, + "loss": 0.4881, + "step": 3890 + }, + { + "epoch": 0.33, + "learning_rate": 1.5758618486837232e-05, + "loss": 0.494, + "step": 3891 + }, + { + "epoch": 0.33, + "learning_rate": 1.5756402800810582e-05, + "loss": 0.4804, + "step": 3892 + }, + { + "epoch": 0.33, + "learning_rate": 1.575418669205765e-05, + "loss": 0.4861, + "step": 3893 + }, + { + "epoch": 0.33, + "learning_rate": 1.575197016074118e-05, + "loss": 0.4914, + "step": 3894 + }, + { + "epoch": 0.33, + "learning_rate": 1.5749753207023944e-05, + "loss": 0.4872, + "step": 3895 + }, + { + "epoch": 0.33, + "learning_rate": 1.574753583106875e-05, + "loss": 0.489, + "step": 3896 + }, + { + "epoch": 0.33, + "learning_rate": 1.574531803303843e-05, + "loss": 0.4924, + "step": 3897 + }, + { + "epoch": 0.33, + "learning_rate": 1.574309981309585e-05, + "loss": 0.4816, + "step": 3898 + }, + { + "epoch": 0.33, + "learning_rate": 1.574088117140391e-05, + "loss": 0.4639, + "step": 3899 + }, + { + "epoch": 0.33, + "learning_rate": 1.573866210812553e-05, + "loss": 0.4816, + "step": 3900 + }, + { + "epoch": 0.33, + "learning_rate": 1.5736442623423675e-05, + "loss": 0.4962, + "step": 3901 + }, + { + "epoch": 0.33, + "learning_rate": 1.5734222717461338e-05, + "loss": 0.4772, + "step": 3902 + }, + { + "epoch": 0.33, + "learning_rate": 1.5732002390401527e-05, + "loss": 0.5055, + "step": 3903 + }, + { + "epoch": 0.33, + "learning_rate": 1.5729781642407305e-05, + "loss": 0.5134, + "step": 3904 + }, + { + "epoch": 0.33, + "learning_rate": 1.5727560473641755e-05, + "loss": 0.4845, + "step": 3905 + }, + { + "epoch": 0.33, + "learning_rate": 1.572533888426798e-05, + "loss": 0.4959, + "step": 3906 + }, + { + "epoch": 0.33, + "learning_rate": 1.5723116874449136e-05, + "loss": 0.5198, + "step": 3907 + }, + { + "epoch": 0.33, + "learning_rate": 1.5720894444348393e-05, + "loss": 0.4905, + "step": 3908 + }, + { + "epoch": 0.33, + "learning_rate": 1.5718671594128957e-05, + "loss": 0.4815, + "step": 3909 + }, + { + "epoch": 0.33, + "learning_rate": 1.571644832395406e-05, + "loss": 0.5216, + "step": 3910 + }, + { + "epoch": 0.33, + "learning_rate": 1.5714224633986978e-05, + "loss": 0.4948, + "step": 3911 + }, + { + "epoch": 0.33, + "learning_rate": 1.5712000524391004e-05, + "loss": 0.4868, + "step": 3912 + }, + { + "epoch": 0.33, + "learning_rate": 1.5709775995329475e-05, + "loss": 0.488, + "step": 3913 + }, + { + "epoch": 0.33, + "learning_rate": 1.570755104696574e-05, + "loss": 0.4918, + "step": 3914 + }, + { + "epoch": 0.33, + "learning_rate": 1.5705325679463198e-05, + "loss": 0.4765, + "step": 3915 + }, + { + "epoch": 0.33, + "learning_rate": 1.5703099892985267e-05, + "loss": 0.501, + "step": 3916 + }, + { + "epoch": 0.33, + "learning_rate": 1.5700873687695405e-05, + "loss": 0.4919, + "step": 3917 + }, + { + "epoch": 0.33, + "learning_rate": 1.5698647063757086e-05, + "loss": 0.4837, + "step": 3918 + }, + { + "epoch": 0.33, + "learning_rate": 1.5696420021333828e-05, + "loss": 0.4798, + "step": 3919 + }, + { + "epoch": 0.33, + "learning_rate": 1.5694192560589184e-05, + "loss": 0.4893, + "step": 3920 + }, + { + "epoch": 0.33, + "learning_rate": 1.5691964681686715e-05, + "loss": 0.4969, + "step": 3921 + }, + { + "epoch": 0.33, + "learning_rate": 1.5689736384790038e-05, + "loss": 0.4692, + "step": 3922 + }, + { + "epoch": 0.33, + "learning_rate": 1.5687507670062788e-05, + "loss": 0.4862, + "step": 3923 + }, + { + "epoch": 0.33, + "learning_rate": 1.5685278537668627e-05, + "loss": 0.4888, + "step": 3924 + }, + { + "epoch": 0.33, + "learning_rate": 1.568304898777126e-05, + "loss": 0.518, + "step": 3925 + }, + { + "epoch": 0.33, + "learning_rate": 1.568081902053441e-05, + "loss": 0.4963, + "step": 3926 + }, + { + "epoch": 0.33, + "learning_rate": 1.567858863612184e-05, + "loss": 0.4802, + "step": 3927 + }, + { + "epoch": 0.33, + "learning_rate": 1.5676357834697342e-05, + "loss": 0.5066, + "step": 3928 + }, + { + "epoch": 0.33, + "learning_rate": 1.5674126616424735e-05, + "loss": 0.495, + "step": 3929 + }, + { + "epoch": 0.33, + "learning_rate": 1.5671894981467866e-05, + "loss": 0.4616, + "step": 3930 + }, + { + "epoch": 0.33, + "learning_rate": 1.5669662929990622e-05, + "loss": 0.4896, + "step": 3931 + }, + { + "epoch": 0.33, + "learning_rate": 1.5667430462156918e-05, + "loss": 0.4981, + "step": 3932 + }, + { + "epoch": 0.33, + "learning_rate": 1.566519757813069e-05, + "loss": 0.4783, + "step": 3933 + }, + { + "epoch": 0.33, + "learning_rate": 1.5662964278075913e-05, + "loss": 0.5017, + "step": 3934 + }, + { + "epoch": 0.33, + "learning_rate": 1.5660730562156596e-05, + "loss": 0.4876, + "step": 3935 + }, + { + "epoch": 0.33, + "learning_rate": 1.5658496430536772e-05, + "loss": 0.4888, + "step": 3936 + }, + { + "epoch": 0.33, + "learning_rate": 1.5656261883380504e-05, + "loss": 0.484, + "step": 3937 + }, + { + "epoch": 0.33, + "learning_rate": 1.565402692085189e-05, + "loss": 0.5082, + "step": 3938 + }, + { + "epoch": 0.33, + "learning_rate": 1.5651791543115056e-05, + "loss": 0.4958, + "step": 3939 + }, + { + "epoch": 0.33, + "learning_rate": 1.564955575033416e-05, + "loss": 0.4958, + "step": 3940 + }, + { + "epoch": 0.33, + "learning_rate": 1.5647319542673386e-05, + "loss": 0.5015, + "step": 3941 + }, + { + "epoch": 0.33, + "learning_rate": 1.564508292029695e-05, + "loss": 0.4872, + "step": 3942 + }, + { + "epoch": 0.33, + "learning_rate": 1.5642845883369114e-05, + "loss": 0.471, + "step": 3943 + }, + { + "epoch": 0.33, + "learning_rate": 1.564060843205414e-05, + "loss": 0.484, + "step": 3944 + }, + { + "epoch": 0.33, + "learning_rate": 1.5638370566516344e-05, + "loss": 0.4949, + "step": 3945 + }, + { + "epoch": 0.33, + "learning_rate": 1.5636132286920066e-05, + "loss": 0.4749, + "step": 3946 + }, + { + "epoch": 0.33, + "learning_rate": 1.5633893593429677e-05, + "loss": 0.4953, + "step": 3947 + }, + { + "epoch": 0.33, + "learning_rate": 1.5631654486209572e-05, + "loss": 0.513, + "step": 3948 + }, + { + "epoch": 0.33, + "learning_rate": 1.5629414965424187e-05, + "loss": 0.4946, + "step": 3949 + }, + { + "epoch": 0.33, + "learning_rate": 1.5627175031237986e-05, + "loss": 0.4743, + "step": 3950 + }, + { + "epoch": 0.33, + "learning_rate": 1.562493468381545e-05, + "loss": 0.4942, + "step": 3951 + }, + { + "epoch": 0.33, + "learning_rate": 1.5622693923321105e-05, + "loss": 0.5027, + "step": 3952 + }, + { + "epoch": 0.33, + "learning_rate": 1.562045274991951e-05, + "loss": 0.5063, + "step": 3953 + }, + { + "epoch": 0.33, + "learning_rate": 1.5618211163775242e-05, + "loss": 0.5087, + "step": 3954 + }, + { + "epoch": 0.33, + "learning_rate": 1.561596916505291e-05, + "loss": 0.4906, + "step": 3955 + }, + { + "epoch": 0.33, + "learning_rate": 1.5613726753917166e-05, + "loss": 0.4729, + "step": 3956 + }, + { + "epoch": 0.33, + "learning_rate": 1.5611483930532677e-05, + "loss": 0.4925, + "step": 3957 + }, + { + "epoch": 0.33, + "learning_rate": 1.5609240695064146e-05, + "loss": 0.4867, + "step": 3958 + }, + { + "epoch": 0.33, + "learning_rate": 1.560699704767631e-05, + "loss": 0.4978, + "step": 3959 + }, + { + "epoch": 0.33, + "learning_rate": 1.5604752988533933e-05, + "loss": 0.4827, + "step": 3960 + }, + { + "epoch": 0.33, + "learning_rate": 1.560250851780181e-05, + "loss": 0.4758, + "step": 3961 + }, + { + "epoch": 0.33, + "learning_rate": 1.560026363564476e-05, + "loss": 0.5156, + "step": 3962 + }, + { + "epoch": 0.33, + "learning_rate": 1.5598018342227645e-05, + "loss": 0.4874, + "step": 3963 + }, + { + "epoch": 0.33, + "learning_rate": 1.5595772637715345e-05, + "loss": 0.4942, + "step": 3964 + }, + { + "epoch": 0.33, + "learning_rate": 1.5593526522272774e-05, + "loss": 0.4825, + "step": 3965 + }, + { + "epoch": 0.33, + "learning_rate": 1.5591279996064884e-05, + "loss": 0.4938, + "step": 3966 + }, + { + "epoch": 0.33, + "learning_rate": 1.558903305925665e-05, + "loss": 0.5092, + "step": 3967 + }, + { + "epoch": 0.33, + "learning_rate": 1.5586785712013073e-05, + "loss": 0.4806, + "step": 3968 + }, + { + "epoch": 0.33, + "learning_rate": 1.5584537954499186e-05, + "loss": 0.5001, + "step": 3969 + }, + { + "epoch": 0.33, + "learning_rate": 1.5582289786880064e-05, + "loss": 0.4897, + "step": 3970 + }, + { + "epoch": 0.33, + "learning_rate": 1.5580041209320797e-05, + "loss": 0.4813, + "step": 3971 + }, + { + "epoch": 0.33, + "learning_rate": 1.5577792221986512e-05, + "loss": 0.4873, + "step": 3972 + }, + { + "epoch": 0.33, + "learning_rate": 1.5575542825042368e-05, + "loss": 0.4936, + "step": 3973 + }, + { + "epoch": 0.33, + "learning_rate": 1.557329301865355e-05, + "loss": 0.4823, + "step": 3974 + }, + { + "epoch": 0.33, + "learning_rate": 1.557104280298527e-05, + "loss": 0.4738, + "step": 3975 + }, + { + "epoch": 0.33, + "learning_rate": 1.556879217820278e-05, + "loss": 0.4857, + "step": 3976 + }, + { + "epoch": 0.33, + "learning_rate": 1.5566541144471355e-05, + "loss": 0.4782, + "step": 3977 + }, + { + "epoch": 0.33, + "learning_rate": 1.55642897019563e-05, + "loss": 0.5053, + "step": 3978 + }, + { + "epoch": 0.33, + "learning_rate": 1.5562037850822954e-05, + "loss": 0.4842, + "step": 3979 + }, + { + "epoch": 0.33, + "learning_rate": 1.5559785591236683e-05, + "loss": 0.4971, + "step": 3980 + }, + { + "epoch": 0.33, + "learning_rate": 1.5557532923362883e-05, + "loss": 0.4861, + "step": 3981 + }, + { + "epoch": 0.33, + "learning_rate": 1.555527984736698e-05, + "loss": 0.4977, + "step": 3982 + }, + { + "epoch": 0.33, + "learning_rate": 1.555302636341443e-05, + "loss": 0.5032, + "step": 3983 + }, + { + "epoch": 0.33, + "learning_rate": 1.5550772471670724e-05, + "loss": 0.4829, + "step": 3984 + }, + { + "epoch": 0.33, + "learning_rate": 1.5548518172301373e-05, + "loss": 0.5062, + "step": 3985 + }, + { + "epoch": 0.33, + "learning_rate": 1.5546263465471926e-05, + "loss": 0.4957, + "step": 3986 + }, + { + "epoch": 0.33, + "learning_rate": 1.554400835134796e-05, + "loss": 0.4942, + "step": 3987 + }, + { + "epoch": 0.33, + "learning_rate": 1.554175283009508e-05, + "loss": 0.4794, + "step": 3988 + }, + { + "epoch": 0.33, + "learning_rate": 1.5539496901878915e-05, + "loss": 0.4872, + "step": 3989 + }, + { + "epoch": 0.33, + "learning_rate": 1.5537240566865145e-05, + "loss": 0.4901, + "step": 3990 + }, + { + "epoch": 0.33, + "learning_rate": 1.553498382521946e-05, + "loss": 0.4855, + "step": 3991 + }, + { + "epoch": 0.33, + "learning_rate": 1.5532726677107583e-05, + "loss": 0.4874, + "step": 3992 + }, + { + "epoch": 0.33, + "learning_rate": 1.553046912269527e-05, + "loss": 0.4815, + "step": 3993 + }, + { + "epoch": 0.33, + "learning_rate": 1.5528211162148305e-05, + "loss": 0.5012, + "step": 3994 + }, + { + "epoch": 0.33, + "learning_rate": 1.552595279563251e-05, + "loss": 0.4831, + "step": 3995 + }, + { + "epoch": 0.33, + "learning_rate": 1.5523694023313723e-05, + "loss": 0.487, + "step": 3996 + }, + { + "epoch": 0.33, + "learning_rate": 1.5521434845357824e-05, + "loss": 0.4729, + "step": 3997 + }, + { + "epoch": 0.33, + "learning_rate": 1.5519175261930716e-05, + "loss": 0.4859, + "step": 3998 + }, + { + "epoch": 0.33, + "learning_rate": 1.551691527319833e-05, + "loss": 0.4979, + "step": 3999 + }, + { + "epoch": 0.33, + "learning_rate": 1.551465487932663e-05, + "loss": 0.4947, + "step": 4000 + }, + { + "epoch": 0.33, + "learning_rate": 1.551239408048162e-05, + "loss": 0.48, + "step": 4001 + }, + { + "epoch": 0.33, + "learning_rate": 1.5510132876829313e-05, + "loss": 0.4818, + "step": 4002 + }, + { + "epoch": 0.33, + "learning_rate": 1.5507871268535765e-05, + "loss": 0.4845, + "step": 4003 + }, + { + "epoch": 0.33, + "learning_rate": 1.550560925576706e-05, + "loss": 0.5188, + "step": 4004 + }, + { + "epoch": 0.34, + "learning_rate": 1.5503346838689314e-05, + "loss": 0.479, + "step": 4005 + }, + { + "epoch": 0.34, + "learning_rate": 1.5501084017468665e-05, + "loss": 0.5038, + "step": 4006 + }, + { + "epoch": 0.34, + "learning_rate": 1.5498820792271284e-05, + "loss": 0.5002, + "step": 4007 + }, + { + "epoch": 0.34, + "learning_rate": 1.549655716326338e-05, + "loss": 0.5109, + "step": 4008 + }, + { + "epoch": 0.34, + "learning_rate": 1.5494293130611175e-05, + "loss": 0.4899, + "step": 4009 + }, + { + "epoch": 0.34, + "learning_rate": 1.5492028694480938e-05, + "loss": 0.4973, + "step": 4010 + }, + { + "epoch": 0.34, + "learning_rate": 1.5489763855038954e-05, + "loss": 0.4873, + "step": 4011 + }, + { + "epoch": 0.34, + "learning_rate": 1.548749861245155e-05, + "loss": 0.4707, + "step": 4012 + }, + { + "epoch": 0.34, + "learning_rate": 1.548523296688507e-05, + "loss": 0.48, + "step": 4013 + }, + { + "epoch": 0.34, + "learning_rate": 1.5482966918505897e-05, + "loss": 0.4909, + "step": 4014 + }, + { + "epoch": 0.34, + "learning_rate": 1.5480700467480437e-05, + "loss": 0.496, + "step": 4015 + }, + { + "epoch": 0.34, + "learning_rate": 1.547843361397513e-05, + "loss": 0.4784, + "step": 4016 + }, + { + "epoch": 0.34, + "learning_rate": 1.5476166358156446e-05, + "loss": 0.49, + "step": 4017 + }, + { + "epoch": 0.34, + "learning_rate": 1.5473898700190884e-05, + "loss": 0.5039, + "step": 4018 + }, + { + "epoch": 0.34, + "learning_rate": 1.5471630640244966e-05, + "loss": 0.4724, + "step": 4019 + }, + { + "epoch": 0.34, + "learning_rate": 1.5469362178485252e-05, + "loss": 0.481, + "step": 4020 + }, + { + "epoch": 0.34, + "learning_rate": 1.546709331507833e-05, + "loss": 0.5026, + "step": 4021 + }, + { + "epoch": 0.34, + "learning_rate": 1.5464824050190816e-05, + "loss": 0.4854, + "step": 4022 + }, + { + "epoch": 0.34, + "learning_rate": 1.5462554383989347e-05, + "loss": 0.5195, + "step": 4023 + }, + { + "epoch": 0.34, + "learning_rate": 1.546028431664061e-05, + "loss": 0.4913, + "step": 4024 + }, + { + "epoch": 0.34, + "learning_rate": 1.5458013848311305e-05, + "loss": 0.4944, + "step": 4025 + }, + { + "epoch": 0.34, + "learning_rate": 1.545574297916816e-05, + "loss": 0.4911, + "step": 4026 + }, + { + "epoch": 0.34, + "learning_rate": 1.5453471709377945e-05, + "loss": 0.4948, + "step": 4027 + }, + { + "epoch": 0.34, + "learning_rate": 1.545120003910745e-05, + "loss": 0.4996, + "step": 4028 + }, + { + "epoch": 0.34, + "learning_rate": 1.54489279685235e-05, + "loss": 0.4778, + "step": 4029 + }, + { + "epoch": 0.34, + "learning_rate": 1.544665549779294e-05, + "loss": 0.4836, + "step": 4030 + }, + { + "epoch": 0.34, + "learning_rate": 1.5444382627082657e-05, + "loss": 0.4674, + "step": 4031 + }, + { + "epoch": 0.34, + "learning_rate": 1.5442109356559556e-05, + "loss": 0.4828, + "step": 4032 + }, + { + "epoch": 0.34, + "learning_rate": 1.543983568639058e-05, + "loss": 0.4952, + "step": 4033 + }, + { + "epoch": 0.34, + "learning_rate": 1.5437561616742703e-05, + "loss": 0.4733, + "step": 4034 + }, + { + "epoch": 0.34, + "learning_rate": 1.543528714778291e-05, + "loss": 0.4976, + "step": 4035 + }, + { + "epoch": 0.34, + "learning_rate": 1.543301227967824e-05, + "loss": 0.4952, + "step": 4036 + }, + { + "epoch": 0.34, + "learning_rate": 1.543073701259574e-05, + "loss": 0.496, + "step": 4037 + }, + { + "epoch": 0.34, + "learning_rate": 1.542846134670251e-05, + "loss": 0.4901, + "step": 4038 + }, + { + "epoch": 0.34, + "learning_rate": 1.5426185282165652e-05, + "loss": 0.5044, + "step": 4039 + }, + { + "epoch": 0.34, + "learning_rate": 1.5423908819152317e-05, + "loss": 0.4779, + "step": 4040 + }, + { + "epoch": 0.34, + "learning_rate": 1.542163195782968e-05, + "loss": 0.5076, + "step": 4041 + }, + { + "epoch": 0.34, + "learning_rate": 1.5419354698364944e-05, + "loss": 0.4836, + "step": 4042 + }, + { + "epoch": 0.34, + "learning_rate": 1.5417077040925334e-05, + "loss": 0.4994, + "step": 4043 + }, + { + "epoch": 0.34, + "learning_rate": 1.541479898567812e-05, + "loss": 0.5221, + "step": 4044 + }, + { + "epoch": 0.34, + "learning_rate": 1.541252053279059e-05, + "loss": 0.4938, + "step": 4045 + }, + { + "epoch": 0.34, + "learning_rate": 1.541024168243007e-05, + "loss": 0.4794, + "step": 4046 + }, + { + "epoch": 0.34, + "learning_rate": 1.5407962434763897e-05, + "loss": 0.4798, + "step": 4047 + }, + { + "epoch": 0.34, + "learning_rate": 1.5405682789959455e-05, + "loss": 0.4878, + "step": 4048 + }, + { + "epoch": 0.34, + "learning_rate": 1.5403402748184156e-05, + "loss": 0.5025, + "step": 4049 + }, + { + "epoch": 0.34, + "learning_rate": 1.5401122309605437e-05, + "loss": 0.4778, + "step": 4050 + }, + { + "epoch": 0.34, + "learning_rate": 1.5398841474390754e-05, + "loss": 0.4801, + "step": 4051 + }, + { + "epoch": 0.34, + "learning_rate": 1.5396560242707613e-05, + "loss": 0.4845, + "step": 4052 + }, + { + "epoch": 0.34, + "learning_rate": 1.5394278614723535e-05, + "loss": 0.4736, + "step": 4053 + }, + { + "epoch": 0.34, + "learning_rate": 1.5391996590606066e-05, + "loss": 0.5036, + "step": 4054 + }, + { + "epoch": 0.34, + "learning_rate": 1.53897141705228e-05, + "loss": 0.5004, + "step": 4055 + }, + { + "epoch": 0.34, + "learning_rate": 1.538743135464134e-05, + "loss": 0.4898, + "step": 4056 + }, + { + "epoch": 0.34, + "learning_rate": 1.5385148143129328e-05, + "loss": 0.4723, + "step": 4057 + }, + { + "epoch": 0.34, + "learning_rate": 1.5382864536154437e-05, + "loss": 0.5157, + "step": 4058 + }, + { + "epoch": 0.34, + "learning_rate": 1.5380580533884364e-05, + "loss": 0.4803, + "step": 4059 + }, + { + "epoch": 0.34, + "learning_rate": 1.5378296136486837e-05, + "loss": 0.5016, + "step": 4060 + }, + { + "epoch": 0.34, + "learning_rate": 1.5376011344129608e-05, + "loss": 0.5045, + "step": 4061 + }, + { + "epoch": 0.34, + "learning_rate": 1.537372615698047e-05, + "loss": 0.4805, + "step": 4062 + }, + { + "epoch": 0.34, + "learning_rate": 1.5371440575207233e-05, + "loss": 0.5004, + "step": 4063 + }, + { + "epoch": 0.34, + "learning_rate": 1.536915459897774e-05, + "loss": 0.4941, + "step": 4064 + }, + { + "epoch": 0.34, + "learning_rate": 1.5366868228459866e-05, + "loss": 0.4623, + "step": 4065 + }, + { + "epoch": 0.34, + "learning_rate": 1.536458146382151e-05, + "loss": 0.4911, + "step": 4066 + }, + { + "epoch": 0.34, + "learning_rate": 1.536229430523061e-05, + "loss": 0.4749, + "step": 4067 + }, + { + "epoch": 0.34, + "learning_rate": 1.5360006752855113e-05, + "loss": 0.4797, + "step": 4068 + }, + { + "epoch": 0.34, + "learning_rate": 1.535771880686302e-05, + "loss": 0.4853, + "step": 4069 + }, + { + "epoch": 0.34, + "learning_rate": 1.5355430467422343e-05, + "loss": 0.4968, + "step": 4070 + }, + { + "epoch": 0.34, + "learning_rate": 1.535314173470112e-05, + "loss": 0.4907, + "step": 4071 + }, + { + "epoch": 0.34, + "learning_rate": 1.5350852608867436e-05, + "loss": 0.4847, + "step": 4072 + }, + { + "epoch": 0.34, + "learning_rate": 1.5348563090089394e-05, + "loss": 0.5151, + "step": 4073 + }, + { + "epoch": 0.34, + "learning_rate": 1.5346273178535126e-05, + "loss": 0.4775, + "step": 4074 + }, + { + "epoch": 0.34, + "learning_rate": 1.534398287437279e-05, + "loss": 0.4907, + "step": 4075 + }, + { + "epoch": 0.34, + "learning_rate": 1.5341692177770583e-05, + "loss": 0.466, + "step": 4076 + }, + { + "epoch": 0.34, + "learning_rate": 1.5339401088896715e-05, + "loss": 0.5019, + "step": 4077 + }, + { + "epoch": 0.34, + "learning_rate": 1.533710960791944e-05, + "loss": 0.4801, + "step": 4078 + }, + { + "epoch": 0.34, + "learning_rate": 1.5334817735007037e-05, + "loss": 0.4967, + "step": 4079 + }, + { + "epoch": 0.34, + "learning_rate": 1.533252547032781e-05, + "loss": 0.4966, + "step": 4080 + }, + { + "epoch": 0.34, + "learning_rate": 1.533023281405009e-05, + "loss": 0.5023, + "step": 4081 + }, + { + "epoch": 0.34, + "learning_rate": 1.5327939766342237e-05, + "loss": 0.5038, + "step": 4082 + }, + { + "epoch": 0.34, + "learning_rate": 1.5325646327372658e-05, + "loss": 0.4999, + "step": 4083 + }, + { + "epoch": 0.34, + "learning_rate": 1.532335249730976e-05, + "loss": 0.4819, + "step": 4084 + }, + { + "epoch": 0.34, + "learning_rate": 1.5321058276321988e-05, + "loss": 0.4924, + "step": 4085 + }, + { + "epoch": 0.34, + "learning_rate": 1.5318763664577838e-05, + "loss": 0.4895, + "step": 4086 + }, + { + "epoch": 0.34, + "learning_rate": 1.5316468662245805e-05, + "loss": 0.4882, + "step": 4087 + }, + { + "epoch": 0.34, + "learning_rate": 1.531417326949442e-05, + "loss": 0.4849, + "step": 4088 + }, + { + "epoch": 0.34, + "learning_rate": 1.5311877486492264e-05, + "loss": 0.4824, + "step": 4089 + }, + { + "epoch": 0.34, + "learning_rate": 1.5309581313407914e-05, + "loss": 0.483, + "step": 4090 + }, + { + "epoch": 0.34, + "learning_rate": 1.5307284750409993e-05, + "loss": 0.4939, + "step": 4091 + }, + { + "epoch": 0.34, + "learning_rate": 1.530498779766716e-05, + "loss": 0.5149, + "step": 4092 + }, + { + "epoch": 0.34, + "learning_rate": 1.5302690455348085e-05, + "loss": 0.4828, + "step": 4093 + }, + { + "epoch": 0.34, + "learning_rate": 1.530039272362148e-05, + "loss": 0.4805, + "step": 4094 + }, + { + "epoch": 0.34, + "learning_rate": 1.5298094602656077e-05, + "loss": 0.4946, + "step": 4095 + }, + { + "epoch": 0.34, + "learning_rate": 1.5295796092620646e-05, + "loss": 0.4826, + "step": 4096 + }, + { + "epoch": 0.34, + "learning_rate": 1.5293497193683974e-05, + "loss": 0.5091, + "step": 4097 + }, + { + "epoch": 0.34, + "learning_rate": 1.5291197906014886e-05, + "loss": 0.4893, + "step": 4098 + }, + { + "epoch": 0.34, + "learning_rate": 1.5288898229782234e-05, + "loss": 0.4873, + "step": 4099 + }, + { + "epoch": 0.34, + "learning_rate": 1.5286598165154892e-05, + "loss": 0.4815, + "step": 4100 + }, + { + "epoch": 0.34, + "learning_rate": 1.5284297712301773e-05, + "loss": 0.4878, + "step": 4101 + }, + { + "epoch": 0.34, + "learning_rate": 1.5281996871391805e-05, + "loss": 0.4834, + "step": 4102 + }, + { + "epoch": 0.34, + "learning_rate": 1.5279695642593958e-05, + "loss": 0.4621, + "step": 4103 + }, + { + "epoch": 0.34, + "learning_rate": 1.527739402607722e-05, + "loss": 0.4742, + "step": 4104 + }, + { + "epoch": 0.34, + "learning_rate": 1.527509202201062e-05, + "loss": 0.4787, + "step": 4105 + }, + { + "epoch": 0.34, + "learning_rate": 1.5272789630563202e-05, + "loss": 0.495, + "step": 4106 + }, + { + "epoch": 0.34, + "learning_rate": 1.527048685190404e-05, + "loss": 0.495, + "step": 4107 + }, + { + "epoch": 0.34, + "learning_rate": 1.5268183686202245e-05, + "loss": 0.51, + "step": 4108 + }, + { + "epoch": 0.34, + "learning_rate": 1.5265880133626956e-05, + "loss": 0.4721, + "step": 4109 + }, + { + "epoch": 0.34, + "learning_rate": 1.5263576194347334e-05, + "loss": 0.498, + "step": 4110 + }, + { + "epoch": 0.34, + "learning_rate": 1.5261271868532568e-05, + "loss": 0.5005, + "step": 4111 + }, + { + "epoch": 0.34, + "learning_rate": 1.5258967156351878e-05, + "loss": 0.4735, + "step": 4112 + }, + { + "epoch": 0.34, + "learning_rate": 1.525666205797451e-05, + "loss": 0.4863, + "step": 4113 + }, + { + "epoch": 0.34, + "learning_rate": 1.5254356573569748e-05, + "loss": 0.4886, + "step": 4114 + }, + { + "epoch": 0.34, + "learning_rate": 1.5252050703306895e-05, + "loss": 0.4866, + "step": 4115 + }, + { + "epoch": 0.34, + "learning_rate": 1.5249744447355282e-05, + "loss": 0.5044, + "step": 4116 + }, + { + "epoch": 0.34, + "learning_rate": 1.5247437805884273e-05, + "loss": 0.4863, + "step": 4117 + }, + { + "epoch": 0.34, + "learning_rate": 1.5245130779063255e-05, + "loss": 0.5085, + "step": 4118 + }, + { + "epoch": 0.34, + "learning_rate": 1.524282336706165e-05, + "loss": 0.4725, + "step": 4119 + }, + { + "epoch": 0.34, + "learning_rate": 1.5240515570048903e-05, + "loss": 0.4866, + "step": 4120 + }, + { + "epoch": 0.34, + "learning_rate": 1.5238207388194493e-05, + "loss": 0.485, + "step": 4121 + }, + { + "epoch": 0.34, + "learning_rate": 1.5235898821667916e-05, + "loss": 0.5004, + "step": 4122 + }, + { + "epoch": 0.34, + "learning_rate": 1.5233589870638708e-05, + "loss": 0.4852, + "step": 4123 + }, + { + "epoch": 0.35, + "learning_rate": 1.5231280535276426e-05, + "loss": 0.4778, + "step": 4124 + }, + { + "epoch": 0.35, + "learning_rate": 1.5228970815750666e-05, + "loss": 0.4932, + "step": 4125 + }, + { + "epoch": 0.35, + "learning_rate": 1.5226660712231032e-05, + "loss": 0.4973, + "step": 4126 + }, + { + "epoch": 0.35, + "learning_rate": 1.5224350224887179e-05, + "loss": 0.4899, + "step": 4127 + }, + { + "epoch": 0.35, + "learning_rate": 1.5222039353888774e-05, + "loss": 0.4763, + "step": 4128 + }, + { + "epoch": 0.35, + "learning_rate": 1.5219728099405516e-05, + "loss": 0.4994, + "step": 4129 + }, + { + "epoch": 0.35, + "learning_rate": 1.521741646160714e-05, + "loss": 0.4798, + "step": 4130 + }, + { + "epoch": 0.35, + "learning_rate": 1.5215104440663399e-05, + "loss": 0.4698, + "step": 4131 + }, + { + "epoch": 0.35, + "learning_rate": 1.521279203674408e-05, + "loss": 0.472, + "step": 4132 + }, + { + "epoch": 0.35, + "learning_rate": 1.5210479250018995e-05, + "loss": 0.4933, + "step": 4133 + }, + { + "epoch": 0.35, + "learning_rate": 1.5208166080657982e-05, + "loss": 0.4828, + "step": 4134 + }, + { + "epoch": 0.35, + "learning_rate": 1.520585252883092e-05, + "loss": 0.497, + "step": 4135 + }, + { + "epoch": 0.35, + "learning_rate": 1.5203538594707699e-05, + "loss": 0.4824, + "step": 4136 + }, + { + "epoch": 0.35, + "learning_rate": 1.520122427845825e-05, + "loss": 0.4743, + "step": 4137 + }, + { + "epoch": 0.35, + "learning_rate": 1.5198909580252517e-05, + "loss": 0.5035, + "step": 4138 + }, + { + "epoch": 0.35, + "learning_rate": 1.519659450026049e-05, + "loss": 0.5019, + "step": 4139 + }, + { + "epoch": 0.35, + "learning_rate": 1.519427903865218e-05, + "loss": 0.5058, + "step": 4140 + }, + { + "epoch": 0.35, + "learning_rate": 1.519196319559762e-05, + "loss": 0.4959, + "step": 4141 + }, + { + "epoch": 0.35, + "learning_rate": 1.518964697126688e-05, + "loss": 0.4922, + "step": 4142 + }, + { + "epoch": 0.35, + "learning_rate": 1.518733036583005e-05, + "loss": 0.5021, + "step": 4143 + }, + { + "epoch": 0.35, + "learning_rate": 1.5185013379457254e-05, + "loss": 0.4927, + "step": 4144 + }, + { + "epoch": 0.35, + "learning_rate": 1.5182696012318641e-05, + "loss": 0.5034, + "step": 4145 + }, + { + "epoch": 0.35, + "learning_rate": 1.518037826458439e-05, + "loss": 0.498, + "step": 4146 + }, + { + "epoch": 0.35, + "learning_rate": 1.5178060136424706e-05, + "loss": 0.5033, + "step": 4147 + }, + { + "epoch": 0.35, + "learning_rate": 1.5175741628009824e-05, + "loss": 0.4818, + "step": 4148 + }, + { + "epoch": 0.35, + "learning_rate": 1.5173422739510003e-05, + "loss": 0.5017, + "step": 4149 + }, + { + "epoch": 0.35, + "learning_rate": 1.5171103471095533e-05, + "loss": 0.4716, + "step": 4150 + }, + { + "epoch": 0.35, + "learning_rate": 1.5168783822936735e-05, + "loss": 0.4648, + "step": 4151 + }, + { + "epoch": 0.35, + "learning_rate": 1.516646379520395e-05, + "loss": 0.4952, + "step": 4152 + }, + { + "epoch": 0.35, + "learning_rate": 1.5164143388067554e-05, + "loss": 0.4907, + "step": 4153 + }, + { + "epoch": 0.35, + "learning_rate": 1.5161822601697945e-05, + "loss": 0.4882, + "step": 4154 + }, + { + "epoch": 0.35, + "learning_rate": 1.5159501436265553e-05, + "loss": 0.4774, + "step": 4155 + }, + { + "epoch": 0.35, + "learning_rate": 1.5157179891940837e-05, + "loss": 0.4901, + "step": 4156 + }, + { + "epoch": 0.35, + "learning_rate": 1.5154857968894278e-05, + "loss": 0.4773, + "step": 4157 + }, + { + "epoch": 0.35, + "learning_rate": 1.5152535667296395e-05, + "loss": 0.4894, + "step": 4158 + }, + { + "epoch": 0.35, + "learning_rate": 1.5150212987317721e-05, + "loss": 0.4976, + "step": 4159 + }, + { + "epoch": 0.35, + "learning_rate": 1.5147889929128825e-05, + "loss": 0.4964, + "step": 4160 + }, + { + "epoch": 0.35, + "learning_rate": 1.5145566492900305e-05, + "loss": 0.4747, + "step": 4161 + }, + { + "epoch": 0.35, + "learning_rate": 1.5143242678802787e-05, + "loss": 0.4627, + "step": 4162 + }, + { + "epoch": 0.35, + "learning_rate": 1.5140918487006918e-05, + "loss": 0.483, + "step": 4163 + }, + { + "epoch": 0.35, + "learning_rate": 1.5138593917683374e-05, + "loss": 0.4939, + "step": 4164 + }, + { + "epoch": 0.35, + "learning_rate": 1.513626897100287e-05, + "loss": 0.4938, + "step": 4165 + }, + { + "epoch": 0.35, + "learning_rate": 1.5133943647136131e-05, + "loss": 0.4925, + "step": 4166 + }, + { + "epoch": 0.35, + "learning_rate": 1.5131617946253928e-05, + "loss": 0.4871, + "step": 4167 + }, + { + "epoch": 0.35, + "learning_rate": 1.5129291868527052e-05, + "loss": 0.4939, + "step": 4168 + }, + { + "epoch": 0.35, + "learning_rate": 1.5126965414126309e-05, + "loss": 0.4752, + "step": 4169 + }, + { + "epoch": 0.35, + "learning_rate": 1.512463858322255e-05, + "loss": 0.4781, + "step": 4170 + }, + { + "epoch": 0.35, + "learning_rate": 1.5122311375986649e-05, + "loss": 0.4782, + "step": 4171 + }, + { + "epoch": 0.35, + "learning_rate": 1.511998379258951e-05, + "loss": 0.4739, + "step": 4172 + }, + { + "epoch": 0.35, + "learning_rate": 1.5117655833202052e-05, + "loss": 0.5065, + "step": 4173 + }, + { + "epoch": 0.35, + "learning_rate": 1.5115327497995238e-05, + "loss": 0.5288, + "step": 4174 + }, + { + "epoch": 0.35, + "learning_rate": 1.511299878714005e-05, + "loss": 0.4939, + "step": 4175 + }, + { + "epoch": 0.35, + "learning_rate": 1.5110669700807496e-05, + "loss": 0.5027, + "step": 4176 + }, + { + "epoch": 0.35, + "learning_rate": 1.5108340239168614e-05, + "loss": 0.5097, + "step": 4177 + }, + { + "epoch": 0.35, + "learning_rate": 1.5106010402394477e-05, + "loss": 0.4741, + "step": 4178 + }, + { + "epoch": 0.35, + "learning_rate": 1.5103680190656169e-05, + "loss": 0.4856, + "step": 4179 + }, + { + "epoch": 0.35, + "learning_rate": 1.5101349604124816e-05, + "loss": 0.5238, + "step": 4180 + }, + { + "epoch": 0.35, + "learning_rate": 1.5099018642971568e-05, + "loss": 0.4797, + "step": 4181 + }, + { + "epoch": 0.35, + "learning_rate": 1.5096687307367601e-05, + "loss": 0.5027, + "step": 4182 + }, + { + "epoch": 0.35, + "learning_rate": 1.5094355597484111e-05, + "loss": 0.481, + "step": 4183 + }, + { + "epoch": 0.35, + "learning_rate": 1.509202351349234e-05, + "loss": 0.5015, + "step": 4184 + }, + { + "epoch": 0.35, + "learning_rate": 1.508969105556354e-05, + "loss": 0.4847, + "step": 4185 + }, + { + "epoch": 0.35, + "learning_rate": 1.5087358223869e-05, + "loss": 0.4803, + "step": 4186 + }, + { + "epoch": 0.35, + "learning_rate": 1.5085025018580029e-05, + "loss": 0.4904, + "step": 4187 + }, + { + "epoch": 0.35, + "learning_rate": 1.5082691439867973e-05, + "loss": 0.4654, + "step": 4188 + }, + { + "epoch": 0.35, + "learning_rate": 1.5080357487904198e-05, + "loss": 0.4828, + "step": 4189 + }, + { + "epoch": 0.35, + "learning_rate": 1.5078023162860099e-05, + "loss": 0.5049, + "step": 4190 + }, + { + "epoch": 0.35, + "learning_rate": 1.5075688464907099e-05, + "loss": 0.4923, + "step": 4191 + }, + { + "epoch": 0.35, + "learning_rate": 1.5073353394216652e-05, + "loss": 0.4693, + "step": 4192 + }, + { + "epoch": 0.35, + "learning_rate": 1.5071017950960234e-05, + "loss": 0.4917, + "step": 4193 + }, + { + "epoch": 0.35, + "learning_rate": 1.5068682135309347e-05, + "loss": 0.495, + "step": 4194 + }, + { + "epoch": 0.35, + "learning_rate": 1.5066345947435525e-05, + "loss": 0.4869, + "step": 4195 + }, + { + "epoch": 0.35, + "learning_rate": 1.5064009387510333e-05, + "loss": 0.4836, + "step": 4196 + }, + { + "epoch": 0.35, + "learning_rate": 1.5061672455705352e-05, + "loss": 0.4999, + "step": 4197 + }, + { + "epoch": 0.35, + "learning_rate": 1.50593351521922e-05, + "loss": 0.5058, + "step": 4198 + }, + { + "epoch": 0.35, + "learning_rate": 1.505699747714252e-05, + "loss": 0.4897, + "step": 4199 + }, + { + "epoch": 0.35, + "learning_rate": 1.5054659430727974e-05, + "loss": 0.4752, + "step": 4200 + }, + { + "epoch": 0.35, + "learning_rate": 1.5052321013120263e-05, + "loss": 0.4942, + "step": 4201 + }, + { + "epoch": 0.35, + "learning_rate": 1.5049982224491115e-05, + "loss": 0.4665, + "step": 4202 + }, + { + "epoch": 0.35, + "learning_rate": 1.5047643065012276e-05, + "loss": 0.497, + "step": 4203 + }, + { + "epoch": 0.35, + "learning_rate": 1.5045303534855524e-05, + "loss": 0.5008, + "step": 4204 + }, + { + "epoch": 0.35, + "learning_rate": 1.5042963634192667e-05, + "loss": 0.4908, + "step": 4205 + }, + { + "epoch": 0.35, + "learning_rate": 1.5040623363195535e-05, + "loss": 0.498, + "step": 4206 + }, + { + "epoch": 0.35, + "learning_rate": 1.5038282722035986e-05, + "loss": 0.4864, + "step": 4207 + }, + { + "epoch": 0.35, + "learning_rate": 1.5035941710885915e-05, + "loss": 0.5004, + "step": 4208 + }, + { + "epoch": 0.35, + "learning_rate": 1.5033600329917227e-05, + "loss": 0.5207, + "step": 4209 + }, + { + "epoch": 0.35, + "learning_rate": 1.5031258579301868e-05, + "loss": 0.4731, + "step": 4210 + }, + { + "epoch": 0.35, + "learning_rate": 1.5028916459211804e-05, + "loss": 0.4995, + "step": 4211 + }, + { + "epoch": 0.35, + "learning_rate": 1.5026573969819035e-05, + "loss": 0.4928, + "step": 4212 + }, + { + "epoch": 0.35, + "learning_rate": 1.502423111129558e-05, + "loss": 0.4968, + "step": 4213 + }, + { + "epoch": 0.35, + "learning_rate": 1.5021887883813488e-05, + "loss": 0.4896, + "step": 4214 + }, + { + "epoch": 0.35, + "learning_rate": 1.501954428754484e-05, + "loss": 0.4845, + "step": 4215 + }, + { + "epoch": 0.35, + "learning_rate": 1.5017200322661735e-05, + "loss": 0.4936, + "step": 4216 + }, + { + "epoch": 0.35, + "learning_rate": 1.5014855989336308e-05, + "loss": 0.4902, + "step": 4217 + }, + { + "epoch": 0.35, + "learning_rate": 1.5012511287740715e-05, + "loss": 0.4821, + "step": 4218 + }, + { + "epoch": 0.35, + "learning_rate": 1.5010166218047139e-05, + "loss": 0.4979, + "step": 4219 + }, + { + "epoch": 0.35, + "learning_rate": 1.50078207804278e-05, + "loss": 0.4948, + "step": 4220 + }, + { + "epoch": 0.35, + "learning_rate": 1.5005474975054928e-05, + "loss": 0.4824, + "step": 4221 + }, + { + "epoch": 0.35, + "learning_rate": 1.5003128802100792e-05, + "loss": 0.4921, + "step": 4222 + }, + { + "epoch": 0.35, + "learning_rate": 1.500078226173769e-05, + "loss": 0.4964, + "step": 4223 + }, + { + "epoch": 0.35, + "learning_rate": 1.4998435354137937e-05, + "loss": 0.4867, + "step": 4224 + }, + { + "epoch": 0.35, + "learning_rate": 1.4996088079473884e-05, + "loss": 0.4999, + "step": 4225 + }, + { + "epoch": 0.35, + "learning_rate": 1.4993740437917898e-05, + "loss": 0.5114, + "step": 4226 + }, + { + "epoch": 0.35, + "learning_rate": 1.4991392429642389e-05, + "loss": 0.4886, + "step": 4227 + }, + { + "epoch": 0.35, + "learning_rate": 1.498904405481978e-05, + "loss": 0.4818, + "step": 4228 + }, + { + "epoch": 0.35, + "learning_rate": 1.4986695313622525e-05, + "loss": 0.5041, + "step": 4229 + }, + { + "epoch": 0.35, + "learning_rate": 1.4984346206223108e-05, + "loss": 0.4954, + "step": 4230 + }, + { + "epoch": 0.35, + "learning_rate": 1.4981996732794038e-05, + "loss": 0.494, + "step": 4231 + }, + { + "epoch": 0.35, + "learning_rate": 1.4979646893507847e-05, + "loss": 0.4941, + "step": 4232 + }, + { + "epoch": 0.35, + "learning_rate": 1.4977296688537101e-05, + "loss": 0.4994, + "step": 4233 + }, + { + "epoch": 0.35, + "learning_rate": 1.4974946118054392e-05, + "loss": 0.4972, + "step": 4234 + }, + { + "epoch": 0.35, + "learning_rate": 1.4972595182232328e-05, + "loss": 0.4681, + "step": 4235 + }, + { + "epoch": 0.35, + "learning_rate": 1.4970243881243558e-05, + "loss": 0.4936, + "step": 4236 + }, + { + "epoch": 0.35, + "learning_rate": 1.4967892215260751e-05, + "loss": 0.4879, + "step": 4237 + }, + { + "epoch": 0.35, + "learning_rate": 1.49655401844566e-05, + "loss": 0.4786, + "step": 4238 + }, + { + "epoch": 0.35, + "learning_rate": 1.4963187789003835e-05, + "loss": 0.4921, + "step": 4239 + }, + { + "epoch": 0.35, + "learning_rate": 1.49608350290752e-05, + "loss": 0.4926, + "step": 4240 + }, + { + "epoch": 0.35, + "learning_rate": 1.4958481904843473e-05, + "loss": 0.4689, + "step": 4241 + }, + { + "epoch": 0.35, + "learning_rate": 1.4956128416481459e-05, + "loss": 0.478, + "step": 4242 + }, + { + "epoch": 0.35, + "learning_rate": 1.4953774564161991e-05, + "loss": 0.4967, + "step": 4243 + }, + { + "epoch": 0.36, + "learning_rate": 1.495142034805792e-05, + "loss": 0.4759, + "step": 4244 + }, + { + "epoch": 0.36, + "learning_rate": 1.4949065768342136e-05, + "loss": 0.4725, + "step": 4245 + }, + { + "epoch": 0.36, + "learning_rate": 1.4946710825187545e-05, + "loss": 0.4913, + "step": 4246 + }, + { + "epoch": 0.36, + "learning_rate": 1.4944355518767086e-05, + "loss": 0.4778, + "step": 4247 + }, + { + "epoch": 0.36, + "learning_rate": 1.4941999849253723e-05, + "loss": 0.4754, + "step": 4248 + }, + { + "epoch": 0.36, + "learning_rate": 1.4939643816820449e-05, + "loss": 0.4989, + "step": 4249 + }, + { + "epoch": 0.36, + "learning_rate": 1.4937287421640277e-05, + "loss": 0.4903, + "step": 4250 + }, + { + "epoch": 0.36, + "learning_rate": 1.493493066388625e-05, + "loss": 0.4936, + "step": 4251 + }, + { + "epoch": 0.36, + "learning_rate": 1.4932573543731441e-05, + "loss": 0.4945, + "step": 4252 + }, + { + "epoch": 0.36, + "learning_rate": 1.493021606134895e-05, + "loss": 0.5001, + "step": 4253 + }, + { + "epoch": 0.36, + "learning_rate": 1.4927858216911897e-05, + "loss": 0.4595, + "step": 4254 + }, + { + "epoch": 0.36, + "learning_rate": 1.492550001059343e-05, + "loss": 0.4922, + "step": 4255 + }, + { + "epoch": 0.36, + "learning_rate": 1.4923141442566732e-05, + "loss": 0.4985, + "step": 4256 + }, + { + "epoch": 0.36, + "learning_rate": 1.4920782513005003e-05, + "loss": 0.5076, + "step": 4257 + }, + { + "epoch": 0.36, + "learning_rate": 1.4918423222081473e-05, + "loss": 0.5075, + "step": 4258 + }, + { + "epoch": 0.36, + "learning_rate": 1.4916063569969398e-05, + "loss": 0.5165, + "step": 4259 + }, + { + "epoch": 0.36, + "learning_rate": 1.4913703556842066e-05, + "loss": 0.4758, + "step": 4260 + }, + { + "epoch": 0.36, + "learning_rate": 1.491134318287278e-05, + "loss": 0.4828, + "step": 4261 + }, + { + "epoch": 0.36, + "learning_rate": 1.4908982448234875e-05, + "loss": 0.4891, + "step": 4262 + }, + { + "epoch": 0.36, + "learning_rate": 1.490662135310172e-05, + "loss": 0.4657, + "step": 4263 + }, + { + "epoch": 0.36, + "learning_rate": 1.49042598976467e-05, + "loss": 0.5058, + "step": 4264 + }, + { + "epoch": 0.36, + "learning_rate": 1.4901898082043232e-05, + "loss": 0.4888, + "step": 4265 + }, + { + "epoch": 0.36, + "learning_rate": 1.4899535906464757e-05, + "loss": 0.4943, + "step": 4266 + }, + { + "epoch": 0.36, + "learning_rate": 1.4897173371084743e-05, + "loss": 0.4916, + "step": 4267 + }, + { + "epoch": 0.36, + "learning_rate": 1.4894810476076688e-05, + "loss": 0.4967, + "step": 4268 + }, + { + "epoch": 0.36, + "learning_rate": 1.489244722161411e-05, + "loss": 0.5103, + "step": 4269 + }, + { + "epoch": 0.36, + "learning_rate": 1.4890083607870559e-05, + "loss": 0.4885, + "step": 4270 + }, + { + "epoch": 0.36, + "learning_rate": 1.4887719635019605e-05, + "loss": 0.5045, + "step": 4271 + }, + { + "epoch": 0.36, + "learning_rate": 1.488535530323485e-05, + "loss": 0.4692, + "step": 4272 + }, + { + "epoch": 0.36, + "learning_rate": 1.4882990612689918e-05, + "loss": 0.5159, + "step": 4273 + }, + { + "epoch": 0.36, + "learning_rate": 1.488062556355847e-05, + "loss": 0.4899, + "step": 4274 + }, + { + "epoch": 0.36, + "learning_rate": 1.4878260156014182e-05, + "loss": 0.4831, + "step": 4275 + }, + { + "epoch": 0.36, + "learning_rate": 1.4875894390230757e-05, + "loss": 0.4664, + "step": 4276 + }, + { + "epoch": 0.36, + "learning_rate": 1.4873528266381927e-05, + "loss": 0.4861, + "step": 4277 + }, + { + "epoch": 0.36, + "learning_rate": 1.487116178464145e-05, + "loss": 0.4937, + "step": 4278 + }, + { + "epoch": 0.36, + "learning_rate": 1.4868794945183113e-05, + "loss": 0.4788, + "step": 4279 + }, + { + "epoch": 0.36, + "learning_rate": 1.4866427748180729e-05, + "loss": 0.4746, + "step": 4280 + }, + { + "epoch": 0.36, + "learning_rate": 1.4864060193808133e-05, + "loss": 0.5078, + "step": 4281 + }, + { + "epoch": 0.36, + "learning_rate": 1.4861692282239181e-05, + "loss": 0.4726, + "step": 4282 + }, + { + "epoch": 0.36, + "learning_rate": 1.4859324013647773e-05, + "loss": 0.4855, + "step": 4283 + }, + { + "epoch": 0.36, + "learning_rate": 1.4856955388207821e-05, + "loss": 0.4965, + "step": 4284 + }, + { + "epoch": 0.36, + "learning_rate": 1.485458640609327e-05, + "loss": 0.4585, + "step": 4285 + }, + { + "epoch": 0.36, + "learning_rate": 1.4852217067478082e-05, + "loss": 0.4939, + "step": 4286 + }, + { + "epoch": 0.36, + "learning_rate": 1.4849847372536252e-05, + "loss": 0.4907, + "step": 4287 + }, + { + "epoch": 0.36, + "learning_rate": 1.4847477321441806e-05, + "loss": 0.4992, + "step": 4288 + }, + { + "epoch": 0.36, + "learning_rate": 1.4845106914368786e-05, + "loss": 0.4741, + "step": 4289 + }, + { + "epoch": 0.36, + "learning_rate": 1.4842736151491268e-05, + "loss": 0.5102, + "step": 4290 + }, + { + "epoch": 0.36, + "learning_rate": 1.484036503298335e-05, + "loss": 0.4947, + "step": 4291 + }, + { + "epoch": 0.36, + "learning_rate": 1.4837993559019157e-05, + "loss": 0.5033, + "step": 4292 + }, + { + "epoch": 0.36, + "learning_rate": 1.4835621729772838e-05, + "loss": 0.4976, + "step": 4293 + }, + { + "epoch": 0.36, + "learning_rate": 1.4833249545418572e-05, + "loss": 0.4881, + "step": 4294 + }, + { + "epoch": 0.36, + "learning_rate": 1.4830877006130561e-05, + "loss": 0.4842, + "step": 4295 + }, + { + "epoch": 0.36, + "learning_rate": 1.4828504112083038e-05, + "loss": 0.5006, + "step": 4296 + }, + { + "epoch": 0.36, + "learning_rate": 1.4826130863450257e-05, + "loss": 0.4883, + "step": 4297 + }, + { + "epoch": 0.36, + "learning_rate": 1.4823757260406498e-05, + "loss": 0.4763, + "step": 4298 + }, + { + "epoch": 0.36, + "learning_rate": 1.4821383303126067e-05, + "loss": 0.4734, + "step": 4299 + }, + { + "epoch": 0.36, + "learning_rate": 1.48190089917833e-05, + "loss": 0.5042, + "step": 4300 + }, + { + "epoch": 0.36, + "learning_rate": 1.4816634326552561e-05, + "loss": 0.4874, + "step": 4301 + }, + { + "epoch": 0.36, + "learning_rate": 1.481425930760823e-05, + "loss": 0.4944, + "step": 4302 + }, + { + "epoch": 0.36, + "learning_rate": 1.4811883935124716e-05, + "loss": 0.512, + "step": 4303 + }, + { + "epoch": 0.36, + "learning_rate": 1.480950820927646e-05, + "loss": 0.5002, + "step": 4304 + }, + { + "epoch": 0.36, + "learning_rate": 1.480713213023793e-05, + "loss": 0.4948, + "step": 4305 + }, + { + "epoch": 0.36, + "learning_rate": 1.4804755698183606e-05, + "loss": 0.4853, + "step": 4306 + }, + { + "epoch": 0.36, + "learning_rate": 1.4802378913288009e-05, + "loss": 0.4656, + "step": 4307 + }, + { + "epoch": 0.36, + "learning_rate": 1.4800001775725684e-05, + "loss": 0.4808, + "step": 4308 + }, + { + "epoch": 0.36, + "learning_rate": 1.4797624285671187e-05, + "loss": 0.4804, + "step": 4309 + }, + { + "epoch": 0.36, + "learning_rate": 1.4795246443299119e-05, + "loss": 0.4866, + "step": 4310 + }, + { + "epoch": 0.36, + "learning_rate": 1.4792868248784098e-05, + "loss": 0.5026, + "step": 4311 + }, + { + "epoch": 0.36, + "learning_rate": 1.4790489702300768e-05, + "loss": 0.4892, + "step": 4312 + }, + { + "epoch": 0.36, + "learning_rate": 1.4788110804023798e-05, + "loss": 0.4854, + "step": 4313 + }, + { + "epoch": 0.36, + "learning_rate": 1.4785731554127885e-05, + "loss": 0.4904, + "step": 4314 + }, + { + "epoch": 0.36, + "learning_rate": 1.4783351952787754e-05, + "loss": 0.4885, + "step": 4315 + }, + { + "epoch": 0.36, + "learning_rate": 1.4780972000178151e-05, + "loss": 0.4908, + "step": 4316 + }, + { + "epoch": 0.36, + "learning_rate": 1.477859169647385e-05, + "loss": 0.4939, + "step": 4317 + }, + { + "epoch": 0.36, + "learning_rate": 1.4776211041849651e-05, + "loss": 0.4988, + "step": 4318 + }, + { + "epoch": 0.36, + "learning_rate": 1.4773830036480377e-05, + "loss": 0.4819, + "step": 4319 + }, + { + "epoch": 0.36, + "learning_rate": 1.4771448680540881e-05, + "loss": 0.4991, + "step": 4320 + }, + { + "epoch": 0.36, + "learning_rate": 1.4769066974206041e-05, + "loss": 0.4881, + "step": 4321 + }, + { + "epoch": 0.36, + "learning_rate": 1.476668491765076e-05, + "loss": 0.511, + "step": 4322 + }, + { + "epoch": 0.36, + "learning_rate": 1.4764302511049962e-05, + "loss": 0.4744, + "step": 4323 + }, + { + "epoch": 0.36, + "learning_rate": 1.4761919754578603e-05, + "loss": 0.4949, + "step": 4324 + }, + { + "epoch": 0.36, + "learning_rate": 1.4759536648411668e-05, + "loss": 0.4802, + "step": 4325 + }, + { + "epoch": 0.36, + "learning_rate": 1.4757153192724154e-05, + "loss": 0.4845, + "step": 4326 + }, + { + "epoch": 0.36, + "learning_rate": 1.4754769387691096e-05, + "loss": 0.4661, + "step": 4327 + }, + { + "epoch": 0.36, + "learning_rate": 1.4752385233487554e-05, + "loss": 0.4855, + "step": 4328 + }, + { + "epoch": 0.36, + "learning_rate": 1.4750000730288605e-05, + "loss": 0.465, + "step": 4329 + }, + { + "epoch": 0.36, + "learning_rate": 1.4747615878269358e-05, + "loss": 0.4894, + "step": 4330 + }, + { + "epoch": 0.36, + "learning_rate": 1.474523067760495e-05, + "loss": 0.5, + "step": 4331 + }, + { + "epoch": 0.36, + "learning_rate": 1.4742845128470538e-05, + "loss": 0.5042, + "step": 4332 + }, + { + "epoch": 0.36, + "learning_rate": 1.4740459231041306e-05, + "loss": 0.4949, + "step": 4333 + }, + { + "epoch": 0.36, + "learning_rate": 1.4738072985492462e-05, + "loss": 0.505, + "step": 4334 + }, + { + "epoch": 0.36, + "learning_rate": 1.4735686391999249e-05, + "loss": 0.4786, + "step": 4335 + }, + { + "epoch": 0.36, + "learning_rate": 1.4733299450736925e-05, + "loss": 0.482, + "step": 4336 + }, + { + "epoch": 0.36, + "learning_rate": 1.4730912161880772e-05, + "loss": 0.4861, + "step": 4337 + }, + { + "epoch": 0.36, + "learning_rate": 1.4728524525606111e-05, + "loss": 0.4779, + "step": 4338 + }, + { + "epoch": 0.36, + "learning_rate": 1.4726136542088277e-05, + "loss": 0.4865, + "step": 4339 + }, + { + "epoch": 0.36, + "learning_rate": 1.4723748211502628e-05, + "loss": 0.4938, + "step": 4340 + }, + { + "epoch": 0.36, + "learning_rate": 1.4721359534024562e-05, + "loss": 0.4721, + "step": 4341 + }, + { + "epoch": 0.36, + "learning_rate": 1.4718970509829489e-05, + "loss": 0.4929, + "step": 4342 + }, + { + "epoch": 0.36, + "learning_rate": 1.4716581139092851e-05, + "loss": 0.5027, + "step": 4343 + }, + { + "epoch": 0.36, + "learning_rate": 1.471419142199011e-05, + "loss": 0.4993, + "step": 4344 + }, + { + "epoch": 0.36, + "learning_rate": 1.4711801358696755e-05, + "loss": 0.4877, + "step": 4345 + }, + { + "epoch": 0.36, + "learning_rate": 1.4709410949388311e-05, + "loss": 0.491, + "step": 4346 + }, + { + "epoch": 0.36, + "learning_rate": 1.4707020194240313e-05, + "loss": 0.5074, + "step": 4347 + }, + { + "epoch": 0.36, + "learning_rate": 1.4704629093428331e-05, + "loss": 0.5038, + "step": 4348 + }, + { + "epoch": 0.36, + "learning_rate": 1.4702237647127957e-05, + "loss": 0.4815, + "step": 4349 + }, + { + "epoch": 0.36, + "learning_rate": 1.4699845855514807e-05, + "loss": 0.5135, + "step": 4350 + }, + { + "epoch": 0.36, + "learning_rate": 1.4697453718764525e-05, + "loss": 0.4867, + "step": 4351 + }, + { + "epoch": 0.36, + "learning_rate": 1.4695061237052781e-05, + "loss": 0.5028, + "step": 4352 + }, + { + "epoch": 0.36, + "learning_rate": 1.4692668410555269e-05, + "loss": 0.5103, + "step": 4353 + }, + { + "epoch": 0.36, + "learning_rate": 1.4690275239447704e-05, + "loss": 0.486, + "step": 4354 + }, + { + "epoch": 0.36, + "learning_rate": 1.4687881723905834e-05, + "loss": 0.4773, + "step": 4355 + }, + { + "epoch": 0.36, + "learning_rate": 1.4685487864105431e-05, + "loss": 0.486, + "step": 4356 + }, + { + "epoch": 0.36, + "learning_rate": 1.4683093660222288e-05, + "loss": 0.502, + "step": 4357 + }, + { + "epoch": 0.36, + "learning_rate": 1.4680699112432223e-05, + "loss": 0.5118, + "step": 4358 + }, + { + "epoch": 0.36, + "learning_rate": 1.4678304220911086e-05, + "loss": 0.475, + "step": 4359 + }, + { + "epoch": 0.36, + "learning_rate": 1.4675908985834744e-05, + "loss": 0.4904, + "step": 4360 + }, + { + "epoch": 0.36, + "learning_rate": 1.4673513407379095e-05, + "loss": 0.494, + "step": 4361 + }, + { + "epoch": 0.36, + "learning_rate": 1.4671117485720058e-05, + "loss": 0.4699, + "step": 4362 + }, + { + "epoch": 0.37, + "learning_rate": 1.4668721221033586e-05, + "loss": 0.4813, + "step": 4363 + }, + { + "epoch": 0.37, + "learning_rate": 1.4666324613495641e-05, + "loss": 0.5052, + "step": 4364 + }, + { + "epoch": 0.37, + "learning_rate": 1.4663927663282228e-05, + "loss": 0.5067, + "step": 4365 + }, + { + "epoch": 0.37, + "learning_rate": 1.4661530370569366e-05, + "loss": 0.4903, + "step": 4366 + }, + { + "epoch": 0.37, + "learning_rate": 1.4659132735533104e-05, + "loss": 0.4757, + "step": 4367 + }, + { + "epoch": 0.37, + "learning_rate": 1.4656734758349509e-05, + "loss": 0.4849, + "step": 4368 + }, + { + "epoch": 0.37, + "learning_rate": 1.4654336439194686e-05, + "loss": 0.5033, + "step": 4369 + }, + { + "epoch": 0.37, + "learning_rate": 1.4651937778244748e-05, + "loss": 0.4794, + "step": 4370 + }, + { + "epoch": 0.37, + "learning_rate": 1.464953877567585e-05, + "loss": 0.4982, + "step": 4371 + }, + { + "epoch": 0.37, + "learning_rate": 1.4647139431664167e-05, + "loss": 0.4785, + "step": 4372 + }, + { + "epoch": 0.37, + "learning_rate": 1.4644739746385894e-05, + "loss": 0.4746, + "step": 4373 + }, + { + "epoch": 0.37, + "learning_rate": 1.4642339720017249e-05, + "loss": 0.4791, + "step": 4374 + }, + { + "epoch": 0.37, + "learning_rate": 1.4639939352734484e-05, + "loss": 0.482, + "step": 4375 + }, + { + "epoch": 0.37, + "learning_rate": 1.4637538644713873e-05, + "loss": 0.4858, + "step": 4376 + }, + { + "epoch": 0.37, + "learning_rate": 1.4635137596131715e-05, + "loss": 0.4855, + "step": 4377 + }, + { + "epoch": 0.37, + "learning_rate": 1.4632736207164326e-05, + "loss": 0.4978, + "step": 4378 + }, + { + "epoch": 0.37, + "learning_rate": 1.4630334477988064e-05, + "loss": 0.4673, + "step": 4379 + }, + { + "epoch": 0.37, + "learning_rate": 1.4627932408779295e-05, + "loss": 0.4958, + "step": 4380 + }, + { + "epoch": 0.37, + "learning_rate": 1.4625529999714416e-05, + "loss": 0.5042, + "step": 4381 + }, + { + "epoch": 0.37, + "learning_rate": 1.4623127250969858e-05, + "loss": 0.4891, + "step": 4382 + }, + { + "epoch": 0.37, + "learning_rate": 1.4620724162722062e-05, + "loss": 0.5032, + "step": 4383 + }, + { + "epoch": 0.37, + "learning_rate": 1.4618320735147501e-05, + "loss": 0.4884, + "step": 4384 + }, + { + "epoch": 0.37, + "learning_rate": 1.4615916968422674e-05, + "loss": 0.4967, + "step": 4385 + }, + { + "epoch": 0.37, + "learning_rate": 1.4613512862724103e-05, + "loss": 0.4824, + "step": 4386 + }, + { + "epoch": 0.37, + "learning_rate": 1.4611108418228342e-05, + "loss": 0.4766, + "step": 4387 + }, + { + "epoch": 0.37, + "learning_rate": 1.460870363511195e-05, + "loss": 0.4905, + "step": 4388 + }, + { + "epoch": 0.37, + "learning_rate": 1.460629851355154e-05, + "loss": 0.4821, + "step": 4389 + }, + { + "epoch": 0.37, + "learning_rate": 1.460389305372372e-05, + "loss": 0.4958, + "step": 4390 + }, + { + "epoch": 0.37, + "learning_rate": 1.4601487255805146e-05, + "loss": 0.4676, + "step": 4391 + }, + { + "epoch": 0.37, + "learning_rate": 1.4599081119972486e-05, + "loss": 0.501, + "step": 4392 + }, + { + "epoch": 0.37, + "learning_rate": 1.459667464640244e-05, + "loss": 0.4787, + "step": 4393 + }, + { + "epoch": 0.37, + "learning_rate": 1.4594267835271725e-05, + "loss": 0.5029, + "step": 4394 + }, + { + "epoch": 0.37, + "learning_rate": 1.4591860686757089e-05, + "loss": 0.5047, + "step": 4395 + }, + { + "epoch": 0.37, + "learning_rate": 1.4589453201035302e-05, + "loss": 0.5009, + "step": 4396 + }, + { + "epoch": 0.37, + "learning_rate": 1.4587045378283162e-05, + "loss": 0.4818, + "step": 4397 + }, + { + "epoch": 0.37, + "learning_rate": 1.4584637218677488e-05, + "loss": 0.4601, + "step": 4398 + }, + { + "epoch": 0.37, + "learning_rate": 1.4582228722395128e-05, + "loss": 0.504, + "step": 4399 + }, + { + "epoch": 0.37, + "learning_rate": 1.4579819889612949e-05, + "loss": 0.4719, + "step": 4400 + }, + { + "epoch": 0.37, + "learning_rate": 1.4577410720507842e-05, + "loss": 0.5031, + "step": 4401 + }, + { + "epoch": 0.37, + "learning_rate": 1.4575001215256735e-05, + "loss": 0.4812, + "step": 4402 + }, + { + "epoch": 0.37, + "learning_rate": 1.4572591374036567e-05, + "loss": 0.4906, + "step": 4403 + }, + { + "epoch": 0.37, + "learning_rate": 1.4570181197024307e-05, + "loss": 0.4945, + "step": 4404 + }, + { + "epoch": 0.37, + "learning_rate": 1.4567770684396947e-05, + "loss": 0.4849, + "step": 4405 + }, + { + "epoch": 0.37, + "learning_rate": 1.456535983633151e-05, + "loss": 0.4788, + "step": 4406 + }, + { + "epoch": 0.37, + "learning_rate": 1.4562948653005032e-05, + "loss": 0.4917, + "step": 4407 + }, + { + "epoch": 0.37, + "learning_rate": 1.4560537134594586e-05, + "loss": 0.4728, + "step": 4408 + }, + { + "epoch": 0.37, + "learning_rate": 1.455812528127726e-05, + "loss": 0.4997, + "step": 4409 + }, + { + "epoch": 0.37, + "learning_rate": 1.4555713093230173e-05, + "loss": 0.493, + "step": 4410 + }, + { + "epoch": 0.37, + "learning_rate": 1.4553300570630464e-05, + "loss": 0.4758, + "step": 4411 + }, + { + "epoch": 0.37, + "learning_rate": 1.4550887713655297e-05, + "loss": 0.4887, + "step": 4412 + }, + { + "epoch": 0.37, + "learning_rate": 1.454847452248187e-05, + "loss": 0.4892, + "step": 4413 + }, + { + "epoch": 0.37, + "learning_rate": 1.4546060997287392e-05, + "loss": 0.4678, + "step": 4414 + }, + { + "epoch": 0.37, + "learning_rate": 1.45436471382491e-05, + "loss": 0.5012, + "step": 4415 + }, + { + "epoch": 0.37, + "learning_rate": 1.4541232945544263e-05, + "loss": 0.5001, + "step": 4416 + }, + { + "epoch": 0.37, + "learning_rate": 1.4538818419350164e-05, + "loss": 0.4674, + "step": 4417 + }, + { + "epoch": 0.37, + "learning_rate": 1.4536403559844123e-05, + "loss": 0.5016, + "step": 4418 + }, + { + "epoch": 0.37, + "learning_rate": 1.453398836720347e-05, + "loss": 0.4768, + "step": 4419 + }, + { + "epoch": 0.37, + "learning_rate": 1.453157284160557e-05, + "loss": 0.4941, + "step": 4420 + }, + { + "epoch": 0.37, + "learning_rate": 1.452915698322781e-05, + "loss": 0.4916, + "step": 4421 + }, + { + "epoch": 0.37, + "learning_rate": 1.4526740792247597e-05, + "loss": 0.4901, + "step": 4422 + }, + { + "epoch": 0.37, + "learning_rate": 1.4524324268842369e-05, + "loss": 0.4863, + "step": 4423 + }, + { + "epoch": 0.37, + "learning_rate": 1.4521907413189587e-05, + "loss": 0.4917, + "step": 4424 + }, + { + "epoch": 0.37, + "learning_rate": 1.4519490225466733e-05, + "loss": 0.4962, + "step": 4425 + }, + { + "epoch": 0.37, + "learning_rate": 1.4517072705851312e-05, + "loss": 0.485, + "step": 4426 + }, + { + "epoch": 0.37, + "learning_rate": 1.451465485452086e-05, + "loss": 0.4956, + "step": 4427 + }, + { + "epoch": 0.37, + "learning_rate": 1.4512236671652932e-05, + "loss": 0.4826, + "step": 4428 + }, + { + "epoch": 0.37, + "learning_rate": 1.4509818157425112e-05, + "loss": 0.4832, + "step": 4429 + }, + { + "epoch": 0.37, + "learning_rate": 1.4507399312015005e-05, + "loss": 0.4936, + "step": 4430 + }, + { + "epoch": 0.37, + "learning_rate": 1.4504980135600242e-05, + "loss": 0.4902, + "step": 4431 + }, + { + "epoch": 0.37, + "learning_rate": 1.4502560628358473e-05, + "loss": 0.4943, + "step": 4432 + }, + { + "epoch": 0.37, + "learning_rate": 1.4500140790467377e-05, + "loss": 0.4822, + "step": 4433 + }, + { + "epoch": 0.37, + "learning_rate": 1.449772062210466e-05, + "loss": 0.4996, + "step": 4434 + }, + { + "epoch": 0.37, + "learning_rate": 1.449530012344805e-05, + "loss": 0.5047, + "step": 4435 + }, + { + "epoch": 0.37, + "learning_rate": 1.4492879294675297e-05, + "loss": 0.4677, + "step": 4436 + }, + { + "epoch": 0.37, + "learning_rate": 1.4490458135964173e-05, + "loss": 0.4872, + "step": 4437 + }, + { + "epoch": 0.37, + "learning_rate": 1.4488036647492482e-05, + "loss": 0.4731, + "step": 4438 + }, + { + "epoch": 0.37, + "learning_rate": 1.4485614829438046e-05, + "loss": 0.4759, + "step": 4439 + }, + { + "epoch": 0.37, + "learning_rate": 1.4483192681978715e-05, + "loss": 0.4946, + "step": 4440 + }, + { + "epoch": 0.37, + "learning_rate": 1.4480770205292363e-05, + "loss": 0.4783, + "step": 4441 + }, + { + "epoch": 0.37, + "learning_rate": 1.4478347399556878e-05, + "loss": 0.4796, + "step": 4442 + }, + { + "epoch": 0.37, + "learning_rate": 1.447592426495019e-05, + "loss": 0.495, + "step": 4443 + }, + { + "epoch": 0.37, + "learning_rate": 1.4473500801650243e-05, + "loss": 0.4885, + "step": 4444 + }, + { + "epoch": 0.37, + "learning_rate": 1.4471077009835001e-05, + "loss": 0.4771, + "step": 4445 + }, + { + "epoch": 0.37, + "learning_rate": 1.446865288968246e-05, + "loss": 0.4934, + "step": 4446 + }, + { + "epoch": 0.37, + "learning_rate": 1.4466228441370638e-05, + "loss": 0.5003, + "step": 4447 + }, + { + "epoch": 0.37, + "learning_rate": 1.4463803665077573e-05, + "loss": 0.4921, + "step": 4448 + }, + { + "epoch": 0.37, + "learning_rate": 1.4461378560981335e-05, + "loss": 0.4844, + "step": 4449 + }, + { + "epoch": 0.37, + "learning_rate": 1.4458953129260014e-05, + "loss": 0.484, + "step": 4450 + }, + { + "epoch": 0.37, + "learning_rate": 1.4456527370091722e-05, + "loss": 0.477, + "step": 4451 + }, + { + "epoch": 0.37, + "learning_rate": 1.4454101283654594e-05, + "loss": 0.4759, + "step": 4452 + }, + { + "epoch": 0.37, + "learning_rate": 1.445167487012679e-05, + "loss": 0.4673, + "step": 4453 + }, + { + "epoch": 0.37, + "learning_rate": 1.4449248129686504e-05, + "loss": 0.4975, + "step": 4454 + }, + { + "epoch": 0.37, + "learning_rate": 1.4446821062511942e-05, + "loss": 0.5007, + "step": 4455 + }, + { + "epoch": 0.37, + "learning_rate": 1.4444393668781334e-05, + "loss": 0.5061, + "step": 4456 + }, + { + "epoch": 0.37, + "learning_rate": 1.4441965948672943e-05, + "loss": 0.4783, + "step": 4457 + }, + { + "epoch": 0.37, + "learning_rate": 1.4439537902365047e-05, + "loss": 0.5025, + "step": 4458 + }, + { + "epoch": 0.37, + "learning_rate": 1.4437109530035951e-05, + "loss": 0.4762, + "step": 4459 + }, + { + "epoch": 0.37, + "learning_rate": 1.443468083186399e-05, + "loss": 0.503, + "step": 4460 + }, + { + "epoch": 0.37, + "learning_rate": 1.443225180802751e-05, + "loss": 0.4933, + "step": 4461 + }, + { + "epoch": 0.37, + "learning_rate": 1.4429822458704896e-05, + "loss": 0.4887, + "step": 4462 + }, + { + "epoch": 0.37, + "learning_rate": 1.4427392784074545e-05, + "loss": 0.4973, + "step": 4463 + }, + { + "epoch": 0.37, + "learning_rate": 1.442496278431488e-05, + "loss": 0.5274, + "step": 4464 + }, + { + "epoch": 0.37, + "learning_rate": 1.4422532459604357e-05, + "loss": 0.4956, + "step": 4465 + }, + { + "epoch": 0.37, + "learning_rate": 1.442010181012144e-05, + "loss": 0.4856, + "step": 4466 + }, + { + "epoch": 0.37, + "learning_rate": 1.4417670836044635e-05, + "loss": 0.5036, + "step": 4467 + }, + { + "epoch": 0.37, + "learning_rate": 1.4415239537552457e-05, + "loss": 0.5218, + "step": 4468 + }, + { + "epoch": 0.37, + "learning_rate": 1.4412807914823452e-05, + "loss": 0.4733, + "step": 4469 + }, + { + "epoch": 0.37, + "learning_rate": 1.4410375968036185e-05, + "loss": 0.4742, + "step": 4470 + }, + { + "epoch": 0.37, + "learning_rate": 1.4407943697369255e-05, + "loss": 0.4971, + "step": 4471 + }, + { + "epoch": 0.37, + "learning_rate": 1.4405511103001274e-05, + "loss": 0.4941, + "step": 4472 + }, + { + "epoch": 0.37, + "learning_rate": 1.440307818511088e-05, + "loss": 0.4734, + "step": 4473 + }, + { + "epoch": 0.37, + "learning_rate": 1.4400644943876736e-05, + "loss": 0.494, + "step": 4474 + }, + { + "epoch": 0.37, + "learning_rate": 1.4398211379477534e-05, + "loss": 0.5102, + "step": 4475 + }, + { + "epoch": 0.37, + "learning_rate": 1.439577749209198e-05, + "loss": 0.4926, + "step": 4476 + }, + { + "epoch": 0.37, + "learning_rate": 1.439334328189881e-05, + "loss": 0.4995, + "step": 4477 + }, + { + "epoch": 0.37, + "learning_rate": 1.4390908749076787e-05, + "loss": 0.5003, + "step": 4478 + }, + { + "epoch": 0.37, + "learning_rate": 1.4388473893804683e-05, + "loss": 0.5023, + "step": 4479 + }, + { + "epoch": 0.37, + "learning_rate": 1.438603871626131e-05, + "loss": 0.4786, + "step": 4480 + }, + { + "epoch": 0.37, + "learning_rate": 1.4383603216625499e-05, + "loss": 0.4957, + "step": 4481 + }, + { + "epoch": 0.37, + "learning_rate": 1.4381167395076101e-05, + "loss": 0.5121, + "step": 4482 + }, + { + "epoch": 0.38, + "learning_rate": 1.4378731251791989e-05, + "loss": 0.4638, + "step": 4483 + }, + { + "epoch": 0.38, + "learning_rate": 1.4376294786952067e-05, + "loss": 0.4954, + "step": 4484 + }, + { + "epoch": 0.38, + "learning_rate": 1.4373858000735262e-05, + "loss": 0.4954, + "step": 4485 + }, + { + "epoch": 0.38, + "learning_rate": 1.4371420893320515e-05, + "loss": 0.4881, + "step": 4486 + }, + { + "epoch": 0.38, + "learning_rate": 1.4368983464886799e-05, + "loss": 0.5036, + "step": 4487 + }, + { + "epoch": 0.38, + "learning_rate": 1.4366545715613112e-05, + "loss": 0.4723, + "step": 4488 + }, + { + "epoch": 0.38, + "learning_rate": 1.4364107645678465e-05, + "loss": 0.4846, + "step": 4489 + }, + { + "epoch": 0.38, + "learning_rate": 1.4361669255261905e-05, + "loss": 0.4819, + "step": 4490 + }, + { + "epoch": 0.38, + "learning_rate": 1.43592305445425e-05, + "loss": 0.4875, + "step": 4491 + }, + { + "epoch": 0.38, + "learning_rate": 1.4356791513699334e-05, + "loss": 0.4895, + "step": 4492 + }, + { + "epoch": 0.38, + "learning_rate": 1.4354352162911522e-05, + "loss": 0.4762, + "step": 4493 + }, + { + "epoch": 0.38, + "learning_rate": 1.4351912492358196e-05, + "loss": 0.4905, + "step": 4494 + }, + { + "epoch": 0.38, + "learning_rate": 1.4349472502218515e-05, + "loss": 0.4592, + "step": 4495 + }, + { + "epoch": 0.38, + "learning_rate": 1.4347032192671668e-05, + "loss": 0.4966, + "step": 4496 + }, + { + "epoch": 0.38, + "learning_rate": 1.4344591563896857e-05, + "loss": 0.4847, + "step": 4497 + }, + { + "epoch": 0.38, + "learning_rate": 1.4342150616073312e-05, + "loss": 0.4795, + "step": 4498 + }, + { + "epoch": 0.38, + "learning_rate": 1.4339709349380285e-05, + "loss": 0.5128, + "step": 4499 + }, + { + "epoch": 0.38, + "learning_rate": 1.4337267763997054e-05, + "loss": 0.4757, + "step": 4500 + }, + { + "epoch": 0.38, + "learning_rate": 1.4334825860102917e-05, + "loss": 0.4912, + "step": 4501 + }, + { + "epoch": 0.38, + "learning_rate": 1.4332383637877203e-05, + "loss": 0.4773, + "step": 4502 + }, + { + "epoch": 0.38, + "learning_rate": 1.432994109749925e-05, + "loss": 0.4955, + "step": 4503 + }, + { + "epoch": 0.38, + "learning_rate": 1.4327498239148434e-05, + "loss": 0.4786, + "step": 4504 + }, + { + "epoch": 0.38, + "learning_rate": 1.4325055063004145e-05, + "loss": 0.4953, + "step": 4505 + }, + { + "epoch": 0.38, + "learning_rate": 1.4322611569245806e-05, + "loss": 0.4892, + "step": 4506 + }, + { + "epoch": 0.38, + "learning_rate": 1.4320167758052848e-05, + "loss": 0.4917, + "step": 4507 + }, + { + "epoch": 0.38, + "learning_rate": 1.4317723629604743e-05, + "loss": 0.4832, + "step": 4508 + }, + { + "epoch": 0.38, + "learning_rate": 1.431527918408097e-05, + "loss": 0.4878, + "step": 4509 + }, + { + "epoch": 0.38, + "learning_rate": 1.4312834421661044e-05, + "loss": 0.4948, + "step": 4510 + }, + { + "epoch": 0.38, + "learning_rate": 1.4310389342524494e-05, + "loss": 0.4869, + "step": 4511 + }, + { + "epoch": 0.38, + "learning_rate": 1.4307943946850883e-05, + "loss": 0.491, + "step": 4512 + }, + { + "epoch": 0.38, + "learning_rate": 1.4305498234819783e-05, + "loss": 0.4886, + "step": 4513 + }, + { + "epoch": 0.38, + "learning_rate": 1.4303052206610801e-05, + "loss": 0.4815, + "step": 4514 + }, + { + "epoch": 0.38, + "learning_rate": 1.4300605862403563e-05, + "loss": 0.4738, + "step": 4515 + }, + { + "epoch": 0.38, + "learning_rate": 1.4298159202377719e-05, + "loss": 0.5164, + "step": 4516 + }, + { + "epoch": 0.38, + "learning_rate": 1.4295712226712941e-05, + "loss": 0.4937, + "step": 4517 + }, + { + "epoch": 0.38, + "learning_rate": 1.4293264935588921e-05, + "loss": 0.4743, + "step": 4518 + }, + { + "epoch": 0.38, + "learning_rate": 1.4290817329185388e-05, + "loss": 0.4843, + "step": 4519 + }, + { + "epoch": 0.38, + "learning_rate": 1.428836940768207e-05, + "loss": 0.4989, + "step": 4520 + }, + { + "epoch": 0.38, + "learning_rate": 1.4285921171258741e-05, + "loss": 0.4858, + "step": 4521 + }, + { + "epoch": 0.38, + "learning_rate": 1.4283472620095192e-05, + "loss": 0.477, + "step": 4522 + }, + { + "epoch": 0.38, + "learning_rate": 1.4281023754371226e-05, + "loss": 0.4741, + "step": 4523 + }, + { + "epoch": 0.38, + "learning_rate": 1.4278574574266681e-05, + "loss": 0.4952, + "step": 4524 + }, + { + "epoch": 0.38, + "learning_rate": 1.4276125079961417e-05, + "loss": 0.4953, + "step": 4525 + }, + { + "epoch": 0.38, + "learning_rate": 1.4273675271635313e-05, + "loss": 0.5021, + "step": 4526 + }, + { + "epoch": 0.38, + "learning_rate": 1.4271225149468272e-05, + "loss": 0.4825, + "step": 4527 + }, + { + "epoch": 0.38, + "learning_rate": 1.426877471364022e-05, + "loss": 0.4693, + "step": 4528 + }, + { + "epoch": 0.38, + "learning_rate": 1.4266323964331112e-05, + "loss": 0.4788, + "step": 4529 + }, + { + "epoch": 0.38, + "learning_rate": 1.4263872901720914e-05, + "loss": 0.469, + "step": 4530 + }, + { + "epoch": 0.38, + "learning_rate": 1.4261421525989625e-05, + "loss": 0.4949, + "step": 4531 + }, + { + "epoch": 0.38, + "learning_rate": 1.4258969837317265e-05, + "loss": 0.4905, + "step": 4532 + }, + { + "epoch": 0.38, + "learning_rate": 1.4256517835883874e-05, + "loss": 0.488, + "step": 4533 + }, + { + "epoch": 0.38, + "learning_rate": 1.4254065521869519e-05, + "loss": 0.5049, + "step": 4534 + }, + { + "epoch": 0.38, + "learning_rate": 1.4251612895454282e-05, + "loss": 0.5057, + "step": 4535 + }, + { + "epoch": 0.38, + "learning_rate": 1.4249159956818279e-05, + "loss": 0.4912, + "step": 4536 + }, + { + "epoch": 0.38, + "learning_rate": 1.4246706706141646e-05, + "loss": 0.5032, + "step": 4537 + }, + { + "epoch": 0.38, + "learning_rate": 1.4244253143604531e-05, + "loss": 0.4765, + "step": 4538 + }, + { + "epoch": 0.38, + "learning_rate": 1.4241799269387122e-05, + "loss": 0.4854, + "step": 4539 + }, + { + "epoch": 0.38, + "learning_rate": 1.4239345083669615e-05, + "loss": 0.4815, + "step": 4540 + }, + { + "epoch": 0.38, + "learning_rate": 1.423689058663224e-05, + "loss": 0.5124, + "step": 4541 + }, + { + "epoch": 0.38, + "learning_rate": 1.4234435778455242e-05, + "loss": 0.4851, + "step": 4542 + }, + { + "epoch": 0.38, + "learning_rate": 1.4231980659318891e-05, + "loss": 0.5049, + "step": 4543 + }, + { + "epoch": 0.38, + "learning_rate": 1.4229525229403486e-05, + "loss": 0.4756, + "step": 4544 + }, + { + "epoch": 0.38, + "learning_rate": 1.4227069488889338e-05, + "loss": 0.4865, + "step": 4545 + }, + { + "epoch": 0.38, + "learning_rate": 1.422461343795679e-05, + "loss": 0.4887, + "step": 4546 + }, + { + "epoch": 0.38, + "learning_rate": 1.4222157076786201e-05, + "loss": 0.4804, + "step": 4547 + }, + { + "epoch": 0.38, + "learning_rate": 1.4219700405557958e-05, + "loss": 0.4999, + "step": 4548 + }, + { + "epoch": 0.38, + "learning_rate": 1.4217243424452466e-05, + "loss": 0.4974, + "step": 4549 + }, + { + "epoch": 0.38, + "learning_rate": 1.4214786133650162e-05, + "loss": 0.5029, + "step": 4550 + }, + { + "epoch": 0.38, + "learning_rate": 1.4212328533331493e-05, + "loss": 0.4983, + "step": 4551 + }, + { + "epoch": 0.38, + "learning_rate": 1.4209870623676934e-05, + "loss": 0.5079, + "step": 4552 + }, + { + "epoch": 0.38, + "learning_rate": 1.4207412404866992e-05, + "loss": 0.5062, + "step": 4553 + }, + { + "epoch": 0.38, + "learning_rate": 1.420495387708218e-05, + "loss": 0.496, + "step": 4554 + }, + { + "epoch": 0.38, + "learning_rate": 1.4202495040503043e-05, + "loss": 0.5021, + "step": 4555 + }, + { + "epoch": 0.38, + "learning_rate": 1.4200035895310151e-05, + "loss": 0.492, + "step": 4556 + }, + { + "epoch": 0.38, + "learning_rate": 1.4197576441684096e-05, + "loss": 0.4871, + "step": 4557 + }, + { + "epoch": 0.38, + "learning_rate": 1.4195116679805483e-05, + "loss": 0.4845, + "step": 4558 + }, + { + "epoch": 0.38, + "learning_rate": 1.4192656609854949e-05, + "loss": 0.4746, + "step": 4559 + }, + { + "epoch": 0.38, + "learning_rate": 1.4190196232013154e-05, + "loss": 0.486, + "step": 4560 + }, + { + "epoch": 0.38, + "learning_rate": 1.4187735546460775e-05, + "loss": 0.4918, + "step": 4561 + }, + { + "epoch": 0.38, + "learning_rate": 1.4185274553378513e-05, + "loss": 0.5124, + "step": 4562 + }, + { + "epoch": 0.38, + "learning_rate": 1.41828132529471e-05, + "loss": 0.4785, + "step": 4563 + }, + { + "epoch": 0.38, + "learning_rate": 1.4180351645347279e-05, + "loss": 0.4927, + "step": 4564 + }, + { + "epoch": 0.38, + "learning_rate": 1.417788973075982e-05, + "loss": 0.5018, + "step": 4565 + }, + { + "epoch": 0.38, + "learning_rate": 1.4175427509365516e-05, + "loss": 0.4941, + "step": 4566 + }, + { + "epoch": 0.38, + "learning_rate": 1.417296498134518e-05, + "loss": 0.4783, + "step": 4567 + }, + { + "epoch": 0.38, + "learning_rate": 1.4170502146879656e-05, + "loss": 0.5057, + "step": 4568 + }, + { + "epoch": 0.38, + "learning_rate": 1.4168039006149799e-05, + "loss": 0.5271, + "step": 4569 + }, + { + "epoch": 0.38, + "learning_rate": 1.4165575559336496e-05, + "loss": 0.4779, + "step": 4570 + }, + { + "epoch": 0.38, + "learning_rate": 1.4163111806620646e-05, + "loss": 0.4642, + "step": 4571 + }, + { + "epoch": 0.38, + "learning_rate": 1.416064774818318e-05, + "loss": 0.5108, + "step": 4572 + }, + { + "epoch": 0.38, + "learning_rate": 1.4158183384205052e-05, + "loss": 0.4914, + "step": 4573 + }, + { + "epoch": 0.38, + "learning_rate": 1.4155718714867232e-05, + "loss": 0.4902, + "step": 4574 + }, + { + "epoch": 0.38, + "learning_rate": 1.4153253740350717e-05, + "loss": 0.4846, + "step": 4575 + }, + { + "epoch": 0.38, + "learning_rate": 1.4150788460836516e-05, + "loss": 0.4685, + "step": 4576 + }, + { + "epoch": 0.38, + "learning_rate": 1.4148322876505675e-05, + "loss": 0.4808, + "step": 4577 + }, + { + "epoch": 0.38, + "learning_rate": 1.4145856987539261e-05, + "loss": 0.4915, + "step": 4578 + }, + { + "epoch": 0.38, + "learning_rate": 1.414339079411835e-05, + "loss": 0.4938, + "step": 4579 + }, + { + "epoch": 0.38, + "learning_rate": 1.4140924296424055e-05, + "loss": 0.4984, + "step": 4580 + }, + { + "epoch": 0.38, + "learning_rate": 1.4138457494637501e-05, + "loss": 0.4884, + "step": 4581 + }, + { + "epoch": 0.38, + "learning_rate": 1.4135990388939839e-05, + "loss": 0.4833, + "step": 4582 + }, + { + "epoch": 0.38, + "learning_rate": 1.4133522979512252e-05, + "loss": 0.4856, + "step": 4583 + }, + { + "epoch": 0.38, + "learning_rate": 1.4131055266535926e-05, + "loss": 0.4952, + "step": 4584 + }, + { + "epoch": 0.38, + "learning_rate": 1.4128587250192087e-05, + "loss": 0.5056, + "step": 4585 + }, + { + "epoch": 0.38, + "learning_rate": 1.412611893066197e-05, + "loss": 0.4818, + "step": 4586 + }, + { + "epoch": 0.38, + "learning_rate": 1.4123650308126839e-05, + "loss": 0.4854, + "step": 4587 + }, + { + "epoch": 0.38, + "learning_rate": 1.4121181382767986e-05, + "loss": 0.4762, + "step": 4588 + }, + { + "epoch": 0.38, + "learning_rate": 1.4118712154766708e-05, + "loss": 0.4713, + "step": 4589 + }, + { + "epoch": 0.38, + "learning_rate": 1.4116242624304343e-05, + "loss": 0.4836, + "step": 4590 + }, + { + "epoch": 0.38, + "learning_rate": 1.411377279156224e-05, + "loss": 0.4767, + "step": 4591 + }, + { + "epoch": 0.38, + "learning_rate": 1.4111302656721775e-05, + "loss": 0.4845, + "step": 4592 + }, + { + "epoch": 0.38, + "learning_rate": 1.410883221996434e-05, + "loss": 0.4769, + "step": 4593 + }, + { + "epoch": 0.38, + "learning_rate": 1.410636148147136e-05, + "loss": 0.4906, + "step": 4594 + }, + { + "epoch": 0.38, + "learning_rate": 1.4103890441424271e-05, + "loss": 0.4971, + "step": 4595 + }, + { + "epoch": 0.38, + "learning_rate": 1.4101419100004537e-05, + "loss": 0.481, + "step": 4596 + }, + { + "epoch": 0.38, + "learning_rate": 1.4098947457393641e-05, + "loss": 0.4774, + "step": 4597 + }, + { + "epoch": 0.38, + "learning_rate": 1.4096475513773097e-05, + "loss": 0.4893, + "step": 4598 + }, + { + "epoch": 0.38, + "learning_rate": 1.4094003269324428e-05, + "loss": 0.4874, + "step": 4599 + }, + { + "epoch": 0.38, + "learning_rate": 1.4091530724229188e-05, + "loss": 0.5024, + "step": 4600 + }, + { + "epoch": 0.38, + "learning_rate": 1.408905787866895e-05, + "loss": 0.5141, + "step": 4601 + }, + { + "epoch": 0.39, + "learning_rate": 1.4086584732825306e-05, + "loss": 0.4768, + "step": 4602 + }, + { + "epoch": 0.39, + "learning_rate": 1.4084111286879878e-05, + "loss": 0.5029, + "step": 4603 + }, + { + "epoch": 0.39, + "learning_rate": 1.4081637541014306e-05, + "loss": 0.4939, + "step": 4604 + }, + { + "epoch": 0.39, + "learning_rate": 1.4079163495410248e-05, + "loss": 0.4798, + "step": 4605 + }, + { + "epoch": 0.39, + "learning_rate": 1.407668915024939e-05, + "loss": 0.4618, + "step": 4606 + }, + { + "epoch": 0.39, + "learning_rate": 1.4074214505713437e-05, + "loss": 0.4803, + "step": 4607 + }, + { + "epoch": 0.39, + "learning_rate": 1.4071739561984115e-05, + "loss": 0.4847, + "step": 4608 + }, + { + "epoch": 0.39, + "learning_rate": 1.4069264319243178e-05, + "loss": 0.4754, + "step": 4609 + }, + { + "epoch": 0.39, + "learning_rate": 1.4066788777672393e-05, + "loss": 0.5171, + "step": 4610 + }, + { + "epoch": 0.39, + "learning_rate": 1.4064312937453556e-05, + "loss": 0.4757, + "step": 4611 + }, + { + "epoch": 0.39, + "learning_rate": 1.406183679876848e-05, + "loss": 0.5263, + "step": 4612 + }, + { + "epoch": 0.39, + "learning_rate": 1.4059360361799004e-05, + "loss": 0.4928, + "step": 4613 + }, + { + "epoch": 0.39, + "learning_rate": 1.4056883626726989e-05, + "loss": 0.4916, + "step": 4614 + }, + { + "epoch": 0.39, + "learning_rate": 1.4054406593734316e-05, + "loss": 0.482, + "step": 4615 + }, + { + "epoch": 0.39, + "learning_rate": 1.4051929263002884e-05, + "loss": 0.4772, + "step": 4616 + }, + { + "epoch": 0.39, + "learning_rate": 1.404945163471462e-05, + "loss": 0.4909, + "step": 4617 + }, + { + "epoch": 0.39, + "learning_rate": 1.4046973709051467e-05, + "loss": 0.4879, + "step": 4618 + }, + { + "epoch": 0.39, + "learning_rate": 1.4044495486195404e-05, + "loss": 0.492, + "step": 4619 + }, + { + "epoch": 0.39, + "learning_rate": 1.4042016966328411e-05, + "loss": 0.4755, + "step": 4620 + }, + { + "epoch": 0.39, + "learning_rate": 1.4039538149632508e-05, + "loss": 0.526, + "step": 4621 + }, + { + "epoch": 0.39, + "learning_rate": 1.4037059036289722e-05, + "loss": 0.4765, + "step": 4622 + }, + { + "epoch": 0.39, + "learning_rate": 1.4034579626482112e-05, + "loss": 0.4763, + "step": 4623 + }, + { + "epoch": 0.39, + "learning_rate": 1.4032099920391753e-05, + "loss": 0.4879, + "step": 4624 + }, + { + "epoch": 0.39, + "learning_rate": 1.402961991820075e-05, + "loss": 0.4795, + "step": 4625 + }, + { + "epoch": 0.39, + "learning_rate": 1.4027139620091221e-05, + "loss": 0.4731, + "step": 4626 + }, + { + "epoch": 0.39, + "learning_rate": 1.4024659026245307e-05, + "loss": 0.4775, + "step": 4627 + }, + { + "epoch": 0.39, + "learning_rate": 1.4022178136845173e-05, + "loss": 0.5075, + "step": 4628 + }, + { + "epoch": 0.39, + "learning_rate": 1.4019696952073008e-05, + "loss": 0.4915, + "step": 4629 + }, + { + "epoch": 0.39, + "learning_rate": 1.4017215472111016e-05, + "loss": 0.4835, + "step": 4630 + }, + { + "epoch": 0.39, + "learning_rate": 1.401473369714143e-05, + "loss": 0.4964, + "step": 4631 + }, + { + "epoch": 0.39, + "learning_rate": 1.40122516273465e-05, + "loss": 0.4938, + "step": 4632 + }, + { + "epoch": 0.39, + "learning_rate": 1.4009769262908498e-05, + "loss": 0.4688, + "step": 4633 + }, + { + "epoch": 0.39, + "learning_rate": 1.4007286604009717e-05, + "loss": 0.4844, + "step": 4634 + }, + { + "epoch": 0.39, + "learning_rate": 1.400480365083248e-05, + "loss": 0.5028, + "step": 4635 + }, + { + "epoch": 0.39, + "learning_rate": 1.400232040355912e-05, + "loss": 0.4694, + "step": 4636 + }, + { + "epoch": 0.39, + "learning_rate": 1.3999836862371992e-05, + "loss": 0.5068, + "step": 4637 + }, + { + "epoch": 0.39, + "learning_rate": 1.3997353027453484e-05, + "loss": 0.526, + "step": 4638 + }, + { + "epoch": 0.39, + "learning_rate": 1.3994868898985996e-05, + "loss": 0.5087, + "step": 4639 + }, + { + "epoch": 0.39, + "learning_rate": 1.399238447715195e-05, + "loss": 0.4647, + "step": 4640 + }, + { + "epoch": 0.39, + "learning_rate": 1.3989899762133797e-05, + "loss": 0.5089, + "step": 4641 + }, + { + "epoch": 0.39, + "learning_rate": 1.3987414754114e-05, + "loss": 0.477, + "step": 4642 + }, + { + "epoch": 0.39, + "learning_rate": 1.3984929453275045e-05, + "loss": 0.4633, + "step": 4643 + }, + { + "epoch": 0.39, + "learning_rate": 1.3982443859799446e-05, + "loss": 0.4792, + "step": 4644 + }, + { + "epoch": 0.39, + "learning_rate": 1.3979957973869738e-05, + "loss": 0.508, + "step": 4645 + }, + { + "epoch": 0.39, + "learning_rate": 1.397747179566847e-05, + "loss": 0.4722, + "step": 4646 + }, + { + "epoch": 0.39, + "learning_rate": 1.3974985325378215e-05, + "loss": 0.4924, + "step": 4647 + }, + { + "epoch": 0.39, + "learning_rate": 1.397249856318157e-05, + "loss": 0.4871, + "step": 4648 + }, + { + "epoch": 0.39, + "learning_rate": 1.3970011509261155e-05, + "loss": 0.4978, + "step": 4649 + }, + { + "epoch": 0.39, + "learning_rate": 1.3967524163799606e-05, + "loss": 0.4922, + "step": 4650 + }, + { + "epoch": 0.39, + "learning_rate": 1.3965036526979586e-05, + "loss": 0.4957, + "step": 4651 + }, + { + "epoch": 0.39, + "learning_rate": 1.3962548598983774e-05, + "loss": 0.4908, + "step": 4652 + }, + { + "epoch": 0.39, + "learning_rate": 1.3960060379994875e-05, + "loss": 0.489, + "step": 4653 + }, + { + "epoch": 0.39, + "learning_rate": 1.395757187019561e-05, + "loss": 0.4736, + "step": 4654 + }, + { + "epoch": 0.39, + "learning_rate": 1.3955083069768733e-05, + "loss": 0.4822, + "step": 4655 + }, + { + "epoch": 0.39, + "learning_rate": 1.3952593978897002e-05, + "loss": 0.4798, + "step": 4656 + }, + { + "epoch": 0.39, + "learning_rate": 1.3950104597763212e-05, + "loss": 0.4925, + "step": 4657 + }, + { + "epoch": 0.39, + "learning_rate": 1.3947614926550168e-05, + "loss": 0.4817, + "step": 4658 + }, + { + "epoch": 0.39, + "learning_rate": 1.3945124965440701e-05, + "loss": 0.4935, + "step": 4659 + }, + { + "epoch": 0.39, + "learning_rate": 1.3942634714617671e-05, + "loss": 0.5021, + "step": 4660 + }, + { + "epoch": 0.39, + "learning_rate": 1.3940144174263943e-05, + "loss": 0.492, + "step": 4661 + }, + { + "epoch": 0.39, + "learning_rate": 1.3937653344562417e-05, + "loss": 0.4698, + "step": 4662 + }, + { + "epoch": 0.39, + "learning_rate": 1.3935162225696006e-05, + "loss": 0.4974, + "step": 4663 + }, + { + "epoch": 0.39, + "learning_rate": 1.3932670817847647e-05, + "loss": 0.4825, + "step": 4664 + }, + { + "epoch": 0.39, + "learning_rate": 1.3930179121200303e-05, + "loss": 0.4825, + "step": 4665 + }, + { + "epoch": 0.39, + "learning_rate": 1.392768713593695e-05, + "loss": 0.4866, + "step": 4666 + }, + { + "epoch": 0.39, + "learning_rate": 1.3925194862240589e-05, + "loss": 0.498, + "step": 4667 + }, + { + "epoch": 0.39, + "learning_rate": 1.3922702300294246e-05, + "loss": 0.4945, + "step": 4668 + }, + { + "epoch": 0.39, + "learning_rate": 1.3920209450280959e-05, + "loss": 0.4962, + "step": 4669 + }, + { + "epoch": 0.39, + "learning_rate": 1.3917716312383797e-05, + "loss": 0.4794, + "step": 4670 + }, + { + "epoch": 0.39, + "learning_rate": 1.3915222886785844e-05, + "loss": 0.4718, + "step": 4671 + }, + { + "epoch": 0.39, + "learning_rate": 1.3912729173670207e-05, + "loss": 0.485, + "step": 4672 + }, + { + "epoch": 0.39, + "learning_rate": 1.3910235173220015e-05, + "loss": 0.4924, + "step": 4673 + }, + { + "epoch": 0.39, + "learning_rate": 1.3907740885618415e-05, + "loss": 0.4844, + "step": 4674 + }, + { + "epoch": 0.39, + "learning_rate": 1.3905246311048575e-05, + "loss": 0.4807, + "step": 4675 + }, + { + "epoch": 0.39, + "learning_rate": 1.3902751449693693e-05, + "loss": 0.4933, + "step": 4676 + }, + { + "epoch": 0.39, + "learning_rate": 1.3900256301736976e-05, + "loss": 0.4699, + "step": 4677 + }, + { + "epoch": 0.39, + "learning_rate": 1.3897760867361657e-05, + "loss": 0.4775, + "step": 4678 + }, + { + "epoch": 0.39, + "learning_rate": 1.3895265146750994e-05, + "loss": 0.4956, + "step": 4679 + }, + { + "epoch": 0.39, + "learning_rate": 1.3892769140088259e-05, + "loss": 0.4707, + "step": 4680 + }, + { + "epoch": 0.39, + "learning_rate": 1.3890272847556747e-05, + "loss": 0.4774, + "step": 4681 + }, + { + "epoch": 0.39, + "learning_rate": 1.3887776269339783e-05, + "loss": 0.4832, + "step": 4682 + }, + { + "epoch": 0.39, + "learning_rate": 1.38852794056207e-05, + "loss": 0.4933, + "step": 4683 + }, + { + "epoch": 0.39, + "learning_rate": 1.3882782256582852e-05, + "loss": 0.4934, + "step": 4684 + }, + { + "epoch": 0.39, + "learning_rate": 1.388028482240963e-05, + "loss": 0.4822, + "step": 4685 + }, + { + "epoch": 0.39, + "learning_rate": 1.3877787103284428e-05, + "loss": 0.4891, + "step": 4686 + }, + { + "epoch": 0.39, + "learning_rate": 1.3875289099390672e-05, + "loss": 0.4905, + "step": 4687 + }, + { + "epoch": 0.39, + "learning_rate": 1.38727908109118e-05, + "loss": 0.5032, + "step": 4688 + }, + { + "epoch": 0.39, + "learning_rate": 1.3870292238031283e-05, + "loss": 0.4791, + "step": 4689 + }, + { + "epoch": 0.39, + "learning_rate": 1.3867793380932597e-05, + "loss": 0.4809, + "step": 4690 + }, + { + "epoch": 0.39, + "learning_rate": 1.3865294239799254e-05, + "loss": 0.4697, + "step": 4691 + }, + { + "epoch": 0.39, + "learning_rate": 1.386279481481478e-05, + "loss": 0.5101, + "step": 4692 + }, + { + "epoch": 0.39, + "learning_rate": 1.3860295106162722e-05, + "loss": 0.477, + "step": 4693 + }, + { + "epoch": 0.39, + "learning_rate": 1.3857795114026648e-05, + "loss": 0.4973, + "step": 4694 + }, + { + "epoch": 0.39, + "learning_rate": 1.3855294838590143e-05, + "loss": 0.4843, + "step": 4695 + }, + { + "epoch": 0.39, + "learning_rate": 1.3852794280036823e-05, + "loss": 0.4937, + "step": 4696 + }, + { + "epoch": 0.39, + "learning_rate": 1.3850293438550317e-05, + "loss": 0.481, + "step": 4697 + }, + { + "epoch": 0.39, + "learning_rate": 1.3847792314314272e-05, + "loss": 0.4813, + "step": 4698 + }, + { + "epoch": 0.39, + "learning_rate": 1.3845290907512367e-05, + "loss": 0.4771, + "step": 4699 + }, + { + "epoch": 0.39, + "learning_rate": 1.3842789218328289e-05, + "loss": 0.5068, + "step": 4700 + }, + { + "epoch": 0.39, + "learning_rate": 1.3840287246945759e-05, + "loss": 0.4914, + "step": 4701 + }, + { + "epoch": 0.39, + "learning_rate": 1.38377849935485e-05, + "loss": 0.4749, + "step": 4702 + }, + { + "epoch": 0.39, + "learning_rate": 1.3835282458320278e-05, + "loss": 0.4946, + "step": 4703 + }, + { + "epoch": 0.39, + "learning_rate": 1.3832779641444864e-05, + "loss": 0.4967, + "step": 4704 + }, + { + "epoch": 0.39, + "learning_rate": 1.3830276543106053e-05, + "loss": 0.4846, + "step": 4705 + }, + { + "epoch": 0.39, + "learning_rate": 1.3827773163487663e-05, + "loss": 0.4776, + "step": 4706 + }, + { + "epoch": 0.39, + "learning_rate": 1.3825269502773538e-05, + "loss": 0.505, + "step": 4707 + }, + { + "epoch": 0.39, + "learning_rate": 1.3822765561147529e-05, + "loss": 0.465, + "step": 4708 + }, + { + "epoch": 0.39, + "learning_rate": 1.3820261338793515e-05, + "loss": 0.4896, + "step": 4709 + }, + { + "epoch": 0.39, + "learning_rate": 1.3817756835895399e-05, + "loss": 0.5086, + "step": 4710 + }, + { + "epoch": 0.39, + "learning_rate": 1.38152520526371e-05, + "loss": 0.5081, + "step": 4711 + }, + { + "epoch": 0.39, + "learning_rate": 1.3812746989202559e-05, + "loss": 0.4698, + "step": 4712 + }, + { + "epoch": 0.39, + "learning_rate": 1.3810241645775738e-05, + "loss": 0.497, + "step": 4713 + }, + { + "epoch": 0.39, + "learning_rate": 1.380773602254062e-05, + "loss": 0.4849, + "step": 4714 + }, + { + "epoch": 0.39, + "learning_rate": 1.3805230119681203e-05, + "loss": 0.4766, + "step": 4715 + }, + { + "epoch": 0.39, + "learning_rate": 1.3802723937381512e-05, + "loss": 0.4944, + "step": 4716 + }, + { + "epoch": 0.39, + "learning_rate": 1.3800217475825597e-05, + "loss": 0.489, + "step": 4717 + }, + { + "epoch": 0.39, + "learning_rate": 1.3797710735197516e-05, + "loss": 0.4637, + "step": 4718 + }, + { + "epoch": 0.39, + "learning_rate": 1.379520371568135e-05, + "loss": 0.482, + "step": 4719 + }, + { + "epoch": 0.39, + "learning_rate": 1.3792696417461213e-05, + "loss": 0.5144, + "step": 4720 + }, + { + "epoch": 0.39, + "learning_rate": 1.3790188840721223e-05, + "loss": 0.4927, + "step": 4721 + }, + { + "epoch": 0.4, + "learning_rate": 1.378768098564553e-05, + "loss": 0.4736, + "step": 4722 + }, + { + "epoch": 0.4, + "learning_rate": 1.3785172852418303e-05, + "loss": 0.4891, + "step": 4723 + }, + { + "epoch": 0.4, + "learning_rate": 1.3782664441223724e-05, + "loss": 0.495, + "step": 4724 + }, + { + "epoch": 0.4, + "learning_rate": 1.3780155752246e-05, + "loss": 0.4943, + "step": 4725 + }, + { + "epoch": 0.4, + "learning_rate": 1.3777646785669357e-05, + "loss": 0.4907, + "step": 4726 + }, + { + "epoch": 0.4, + "learning_rate": 1.3775137541678052e-05, + "loss": 0.4822, + "step": 4727 + }, + { + "epoch": 0.4, + "learning_rate": 1.3772628020456346e-05, + "loss": 0.4896, + "step": 4728 + }, + { + "epoch": 0.4, + "learning_rate": 1.3770118222188529e-05, + "loss": 0.4812, + "step": 4729 + }, + { + "epoch": 0.4, + "learning_rate": 1.3767608147058913e-05, + "loss": 0.4859, + "step": 4730 + }, + { + "epoch": 0.4, + "learning_rate": 1.3765097795251822e-05, + "loss": 0.4721, + "step": 4731 + }, + { + "epoch": 0.4, + "learning_rate": 1.376258716695161e-05, + "loss": 0.4959, + "step": 4732 + }, + { + "epoch": 0.4, + "learning_rate": 1.376007626234265e-05, + "loss": 0.4818, + "step": 4733 + }, + { + "epoch": 0.4, + "learning_rate": 1.3757565081609327e-05, + "loss": 0.4732, + "step": 4734 + }, + { + "epoch": 0.4, + "learning_rate": 1.3755053624936055e-05, + "loss": 0.4902, + "step": 4735 + }, + { + "epoch": 0.4, + "learning_rate": 1.375254189250726e-05, + "loss": 0.4942, + "step": 4736 + }, + { + "epoch": 0.4, + "learning_rate": 1.3750029884507394e-05, + "loss": 0.4723, + "step": 4737 + }, + { + "epoch": 0.4, + "learning_rate": 1.3747517601120934e-05, + "loss": 0.5007, + "step": 4738 + }, + { + "epoch": 0.4, + "learning_rate": 1.3745005042532369e-05, + "loss": 0.5025, + "step": 4739 + }, + { + "epoch": 0.4, + "learning_rate": 1.374249220892621e-05, + "loss": 0.4768, + "step": 4740 + }, + { + "epoch": 0.4, + "learning_rate": 1.3739979100486986e-05, + "loss": 0.494, + "step": 4741 + }, + { + "epoch": 0.4, + "learning_rate": 1.3737465717399259e-05, + "loss": 0.5006, + "step": 4742 + }, + { + "epoch": 0.4, + "learning_rate": 1.3734952059847589e-05, + "loss": 0.4787, + "step": 4743 + }, + { + "epoch": 0.4, + "learning_rate": 1.3732438128016578e-05, + "loss": 0.486, + "step": 4744 + }, + { + "epoch": 0.4, + "learning_rate": 1.3729923922090836e-05, + "loss": 0.5041, + "step": 4745 + }, + { + "epoch": 0.4, + "learning_rate": 1.3727409442254994e-05, + "loss": 0.4867, + "step": 4746 + }, + { + "epoch": 0.4, + "learning_rate": 1.3724894688693704e-05, + "loss": 0.5076, + "step": 4747 + }, + { + "epoch": 0.4, + "learning_rate": 1.3722379661591643e-05, + "loss": 0.5011, + "step": 4748 + }, + { + "epoch": 0.4, + "learning_rate": 1.3719864361133502e-05, + "loss": 0.4931, + "step": 4749 + }, + { + "epoch": 0.4, + "learning_rate": 1.3717348787503993e-05, + "loss": 0.4803, + "step": 4750 + }, + { + "epoch": 0.4, + "learning_rate": 1.3714832940887854e-05, + "loss": 0.4869, + "step": 4751 + }, + { + "epoch": 0.4, + "learning_rate": 1.3712316821469831e-05, + "loss": 0.4963, + "step": 4752 + }, + { + "epoch": 0.4, + "learning_rate": 1.3709800429434702e-05, + "loss": 0.4769, + "step": 4753 + }, + { + "epoch": 0.4, + "learning_rate": 1.370728376496726e-05, + "loss": 0.477, + "step": 4754 + }, + { + "epoch": 0.4, + "learning_rate": 1.3704766828252321e-05, + "loss": 0.5086, + "step": 4755 + }, + { + "epoch": 0.4, + "learning_rate": 1.3702249619474712e-05, + "loss": 0.4896, + "step": 4756 + }, + { + "epoch": 0.4, + "learning_rate": 1.369973213881929e-05, + "loss": 0.4693, + "step": 4757 + }, + { + "epoch": 0.4, + "learning_rate": 1.3697214386470932e-05, + "loss": 0.4847, + "step": 4758 + }, + { + "epoch": 0.4, + "learning_rate": 1.3694696362614524e-05, + "loss": 0.4807, + "step": 4759 + }, + { + "epoch": 0.4, + "learning_rate": 1.3692178067434982e-05, + "loss": 0.4717, + "step": 4760 + }, + { + "epoch": 0.4, + "learning_rate": 1.3689659501117243e-05, + "loss": 0.4815, + "step": 4761 + }, + { + "epoch": 0.4, + "learning_rate": 1.3687140663846252e-05, + "loss": 0.4829, + "step": 4762 + }, + { + "epoch": 0.4, + "learning_rate": 1.3684621555806988e-05, + "loss": 0.4869, + "step": 4763 + }, + { + "epoch": 0.4, + "learning_rate": 1.3682102177184444e-05, + "loss": 0.4915, + "step": 4764 + }, + { + "epoch": 0.4, + "learning_rate": 1.3679582528163633e-05, + "loss": 0.4821, + "step": 4765 + }, + { + "epoch": 0.4, + "learning_rate": 1.3677062608929583e-05, + "loss": 0.4984, + "step": 4766 + }, + { + "epoch": 0.4, + "learning_rate": 1.3674542419667347e-05, + "loss": 0.4911, + "step": 4767 + }, + { + "epoch": 0.4, + "learning_rate": 1.3672021960562001e-05, + "loss": 0.4761, + "step": 4768 + }, + { + "epoch": 0.4, + "learning_rate": 1.3669501231798638e-05, + "loss": 0.4801, + "step": 4769 + }, + { + "epoch": 0.4, + "learning_rate": 1.3666980233562364e-05, + "loss": 0.5164, + "step": 4770 + }, + { + "epoch": 0.4, + "learning_rate": 1.3664458966038314e-05, + "loss": 0.4852, + "step": 4771 + }, + { + "epoch": 0.4, + "learning_rate": 1.366193742941164e-05, + "loss": 0.4944, + "step": 4772 + }, + { + "epoch": 0.4, + "learning_rate": 1.365941562386751e-05, + "loss": 0.4886, + "step": 4773 + }, + { + "epoch": 0.4, + "learning_rate": 1.3656893549591121e-05, + "loss": 0.4837, + "step": 4774 + }, + { + "epoch": 0.4, + "learning_rate": 1.3654371206767678e-05, + "loss": 0.4903, + "step": 4775 + }, + { + "epoch": 0.4, + "learning_rate": 1.3651848595582416e-05, + "loss": 0.4611, + "step": 4776 + }, + { + "epoch": 0.4, + "learning_rate": 1.3649325716220579e-05, + "loss": 0.4914, + "step": 4777 + }, + { + "epoch": 0.4, + "learning_rate": 1.364680256886744e-05, + "loss": 0.4672, + "step": 4778 + }, + { + "epoch": 0.4, + "learning_rate": 1.364427915370829e-05, + "loss": 0.4768, + "step": 4779 + }, + { + "epoch": 0.4, + "learning_rate": 1.3641755470928435e-05, + "loss": 0.4871, + "step": 4780 + }, + { + "epoch": 0.4, + "learning_rate": 1.3639231520713207e-05, + "loss": 0.4953, + "step": 4781 + }, + { + "epoch": 0.4, + "learning_rate": 1.3636707303247953e-05, + "loss": 0.4642, + "step": 4782 + }, + { + "epoch": 0.4, + "learning_rate": 1.363418281871804e-05, + "loss": 0.5042, + "step": 4783 + }, + { + "epoch": 0.4, + "learning_rate": 1.3631658067308857e-05, + "loss": 0.485, + "step": 4784 + }, + { + "epoch": 0.4, + "learning_rate": 1.362913304920581e-05, + "loss": 0.4988, + "step": 4785 + }, + { + "epoch": 0.4, + "learning_rate": 1.3626607764594329e-05, + "loss": 0.4921, + "step": 4786 + }, + { + "epoch": 0.4, + "learning_rate": 1.3624082213659854e-05, + "loss": 0.5012, + "step": 4787 + }, + { + "epoch": 0.4, + "learning_rate": 1.3621556396587856e-05, + "loss": 0.4926, + "step": 4788 + }, + { + "epoch": 0.4, + "learning_rate": 1.3619030313563821e-05, + "loss": 0.4879, + "step": 4789 + }, + { + "epoch": 0.4, + "learning_rate": 1.3616503964773252e-05, + "loss": 0.4911, + "step": 4790 + }, + { + "epoch": 0.4, + "learning_rate": 1.3613977350401675e-05, + "loss": 0.4665, + "step": 4791 + }, + { + "epoch": 0.4, + "learning_rate": 1.3611450470634631e-05, + "loss": 0.4938, + "step": 4792 + }, + { + "epoch": 0.4, + "learning_rate": 1.3608923325657686e-05, + "loss": 0.4847, + "step": 4793 + }, + { + "epoch": 0.4, + "learning_rate": 1.3606395915656423e-05, + "loss": 0.5109, + "step": 4794 + }, + { + "epoch": 0.4, + "learning_rate": 1.3603868240816445e-05, + "loss": 0.4765, + "step": 4795 + }, + { + "epoch": 0.4, + "learning_rate": 1.3601340301323371e-05, + "loss": 0.4859, + "step": 4796 + }, + { + "epoch": 0.4, + "learning_rate": 1.3598812097362846e-05, + "loss": 0.505, + "step": 4797 + }, + { + "epoch": 0.4, + "learning_rate": 1.3596283629120527e-05, + "loss": 0.5041, + "step": 4798 + }, + { + "epoch": 0.4, + "learning_rate": 1.3593754896782099e-05, + "loss": 0.4924, + "step": 4799 + }, + { + "epoch": 0.4, + "learning_rate": 1.359122590053326e-05, + "loss": 0.467, + "step": 4800 + }, + { + "epoch": 0.4, + "learning_rate": 1.3588696640559725e-05, + "loss": 0.5029, + "step": 4801 + }, + { + "epoch": 0.4, + "learning_rate": 1.3586167117047238e-05, + "loss": 0.4932, + "step": 4802 + }, + { + "epoch": 0.4, + "learning_rate": 1.358363733018155e-05, + "loss": 0.4759, + "step": 4803 + }, + { + "epoch": 0.4, + "learning_rate": 1.3581107280148443e-05, + "loss": 0.5209, + "step": 4804 + }, + { + "epoch": 0.4, + "learning_rate": 1.3578576967133712e-05, + "loss": 0.4676, + "step": 4805 + }, + { + "epoch": 0.4, + "learning_rate": 1.3576046391323176e-05, + "loss": 0.4666, + "step": 4806 + }, + { + "epoch": 0.4, + "learning_rate": 1.3573515552902663e-05, + "loss": 0.4912, + "step": 4807 + }, + { + "epoch": 0.4, + "learning_rate": 1.3570984452058035e-05, + "loss": 0.4882, + "step": 4808 + }, + { + "epoch": 0.4, + "learning_rate": 1.356845308897516e-05, + "loss": 0.475, + "step": 4809 + }, + { + "epoch": 0.4, + "learning_rate": 1.3565921463839934e-05, + "loss": 0.4938, + "step": 4810 + }, + { + "epoch": 0.4, + "learning_rate": 1.3563389576838264e-05, + "loss": 0.4858, + "step": 4811 + }, + { + "epoch": 0.4, + "learning_rate": 1.3560857428156086e-05, + "loss": 0.4817, + "step": 4812 + }, + { + "epoch": 0.4, + "learning_rate": 1.355832501797935e-05, + "loss": 0.5182, + "step": 4813 + }, + { + "epoch": 0.4, + "learning_rate": 1.3555792346494023e-05, + "loss": 0.5071, + "step": 4814 + }, + { + "epoch": 0.4, + "learning_rate": 1.35532594138861e-05, + "loss": 0.486, + "step": 4815 + }, + { + "epoch": 0.4, + "learning_rate": 1.355072622034158e-05, + "loss": 0.4677, + "step": 4816 + }, + { + "epoch": 0.4, + "learning_rate": 1.3548192766046499e-05, + "loss": 0.4871, + "step": 4817 + }, + { + "epoch": 0.4, + "learning_rate": 1.3545659051186897e-05, + "loss": 0.505, + "step": 4818 + }, + { + "epoch": 0.4, + "learning_rate": 1.3543125075948842e-05, + "loss": 0.4679, + "step": 4819 + }, + { + "epoch": 0.4, + "learning_rate": 1.354059084051842e-05, + "loss": 0.518, + "step": 4820 + }, + { + "epoch": 0.4, + "learning_rate": 1.3538056345081729e-05, + "loss": 0.4902, + "step": 4821 + }, + { + "epoch": 0.4, + "learning_rate": 1.35355215898249e-05, + "loss": 0.4813, + "step": 4822 + }, + { + "epoch": 0.4, + "learning_rate": 1.3532986574934071e-05, + "loss": 0.4975, + "step": 4823 + }, + { + "epoch": 0.4, + "learning_rate": 1.35304513005954e-05, + "loss": 0.4795, + "step": 4824 + }, + { + "epoch": 0.4, + "learning_rate": 1.352791576699507e-05, + "loss": 0.4782, + "step": 4825 + }, + { + "epoch": 0.4, + "learning_rate": 1.3525379974319282e-05, + "loss": 0.491, + "step": 4826 + }, + { + "epoch": 0.4, + "learning_rate": 1.352284392275425e-05, + "loss": 0.4788, + "step": 4827 + }, + { + "epoch": 0.4, + "learning_rate": 1.3520307612486211e-05, + "loss": 0.4711, + "step": 4828 + }, + { + "epoch": 0.4, + "learning_rate": 1.3517771043701427e-05, + "loss": 0.4901, + "step": 4829 + }, + { + "epoch": 0.4, + "learning_rate": 1.3515234216586169e-05, + "loss": 0.4877, + "step": 4830 + }, + { + "epoch": 0.4, + "learning_rate": 1.3512697131326726e-05, + "loss": 0.4863, + "step": 4831 + }, + { + "epoch": 0.4, + "learning_rate": 1.351015978810942e-05, + "loss": 0.4971, + "step": 4832 + }, + { + "epoch": 0.4, + "learning_rate": 1.3507622187120582e-05, + "loss": 0.4835, + "step": 4833 + }, + { + "epoch": 0.4, + "learning_rate": 1.3505084328546554e-05, + "loss": 0.4859, + "step": 4834 + }, + { + "epoch": 0.4, + "learning_rate": 1.3502546212573715e-05, + "loss": 0.4858, + "step": 4835 + }, + { + "epoch": 0.4, + "learning_rate": 1.350000783938845e-05, + "loss": 0.4833, + "step": 4836 + }, + { + "epoch": 0.4, + "learning_rate": 1.3497469209177166e-05, + "loss": 0.4879, + "step": 4837 + }, + { + "epoch": 0.4, + "learning_rate": 1.349493032212629e-05, + "loss": 0.4848, + "step": 4838 + }, + { + "epoch": 0.4, + "learning_rate": 1.3492391178422271e-05, + "loss": 0.4863, + "step": 4839 + }, + { + "epoch": 0.4, + "learning_rate": 1.3489851778251563e-05, + "loss": 0.48, + "step": 4840 + }, + { + "epoch": 0.41, + "learning_rate": 1.3487312121800661e-05, + "loss": 0.4777, + "step": 4841 + }, + { + "epoch": 0.41, + "learning_rate": 1.3484772209256061e-05, + "loss": 0.4783, + "step": 4842 + }, + { + "epoch": 0.41, + "learning_rate": 1.3482232040804286e-05, + "loss": 0.5042, + "step": 4843 + }, + { + "epoch": 0.41, + "learning_rate": 1.3479691616631869e-05, + "loss": 0.4642, + "step": 4844 + }, + { + "epoch": 0.41, + "learning_rate": 1.3477150936925374e-05, + "loss": 0.4839, + "step": 4845 + }, + { + "epoch": 0.41, + "learning_rate": 1.3474610001871379e-05, + "loss": 0.4922, + "step": 4846 + }, + { + "epoch": 0.41, + "learning_rate": 1.3472068811656477e-05, + "loss": 0.4956, + "step": 4847 + }, + { + "epoch": 0.41, + "learning_rate": 1.3469527366467281e-05, + "loss": 0.479, + "step": 4848 + }, + { + "epoch": 0.41, + "learning_rate": 1.3466985666490428e-05, + "loss": 0.502, + "step": 4849 + }, + { + "epoch": 0.41, + "learning_rate": 1.3464443711912566e-05, + "loss": 0.4734, + "step": 4850 + }, + { + "epoch": 0.41, + "learning_rate": 1.3461901502920371e-05, + "loss": 0.4976, + "step": 4851 + }, + { + "epoch": 0.41, + "learning_rate": 1.3459359039700525e-05, + "loss": 0.4828, + "step": 4852 + }, + { + "epoch": 0.41, + "learning_rate": 1.3456816322439742e-05, + "loss": 0.488, + "step": 4853 + }, + { + "epoch": 0.41, + "learning_rate": 1.3454273351324747e-05, + "loss": 0.4822, + "step": 4854 + }, + { + "epoch": 0.41, + "learning_rate": 1.345173012654228e-05, + "loss": 0.4855, + "step": 4855 + }, + { + "epoch": 0.41, + "learning_rate": 1.3449186648279114e-05, + "loss": 0.4978, + "step": 4856 + }, + { + "epoch": 0.41, + "learning_rate": 1.3446642916722027e-05, + "loss": 0.4827, + "step": 4857 + }, + { + "epoch": 0.41, + "learning_rate": 1.3444098932057818e-05, + "loss": 0.5126, + "step": 4858 + }, + { + "epoch": 0.41, + "learning_rate": 1.3441554694473307e-05, + "loss": 0.4707, + "step": 4859 + }, + { + "epoch": 0.41, + "learning_rate": 1.3439010204155334e-05, + "loss": 0.5114, + "step": 4860 + }, + { + "epoch": 0.41, + "learning_rate": 1.3436465461290757e-05, + "loss": 0.5015, + "step": 4861 + }, + { + "epoch": 0.41, + "learning_rate": 1.343392046606645e-05, + "loss": 0.4831, + "step": 4862 + }, + { + "epoch": 0.41, + "learning_rate": 1.3431375218669307e-05, + "loss": 0.4898, + "step": 4863 + }, + { + "epoch": 0.41, + "learning_rate": 1.342882971928624e-05, + "loss": 0.4893, + "step": 4864 + }, + { + "epoch": 0.41, + "learning_rate": 1.3426283968104178e-05, + "loss": 0.4799, + "step": 4865 + }, + { + "epoch": 0.41, + "learning_rate": 1.3423737965310073e-05, + "loss": 0.4845, + "step": 4866 + }, + { + "epoch": 0.41, + "learning_rate": 1.3421191711090895e-05, + "loss": 0.4986, + "step": 4867 + }, + { + "epoch": 0.41, + "learning_rate": 1.3418645205633625e-05, + "loss": 0.4814, + "step": 4868 + }, + { + "epoch": 0.41, + "learning_rate": 1.341609844912527e-05, + "loss": 0.4772, + "step": 4869 + }, + { + "epoch": 0.41, + "learning_rate": 1.3413551441752855e-05, + "loss": 0.4904, + "step": 4870 + }, + { + "epoch": 0.41, + "learning_rate": 1.341100418370342e-05, + "loss": 0.4926, + "step": 4871 + }, + { + "epoch": 0.41, + "learning_rate": 1.3408456675164023e-05, + "loss": 0.4714, + "step": 4872 + }, + { + "epoch": 0.41, + "learning_rate": 1.3405908916321748e-05, + "loss": 0.471, + "step": 4873 + }, + { + "epoch": 0.41, + "learning_rate": 1.3403360907363687e-05, + "loss": 0.5065, + "step": 4874 + }, + { + "epoch": 0.41, + "learning_rate": 1.3400812648476956e-05, + "loss": 0.4832, + "step": 4875 + }, + { + "epoch": 0.41, + "learning_rate": 1.3398264139848687e-05, + "loss": 0.4877, + "step": 4876 + }, + { + "epoch": 0.41, + "learning_rate": 1.3395715381666038e-05, + "loss": 0.4762, + "step": 4877 + }, + { + "epoch": 0.41, + "learning_rate": 1.3393166374116175e-05, + "loss": 0.4868, + "step": 4878 + }, + { + "epoch": 0.41, + "learning_rate": 1.3390617117386285e-05, + "loss": 0.4823, + "step": 4879 + }, + { + "epoch": 0.41, + "learning_rate": 1.3388067611663578e-05, + "loss": 0.4737, + "step": 4880 + }, + { + "epoch": 0.41, + "learning_rate": 1.3385517857135274e-05, + "loss": 0.4901, + "step": 4881 + }, + { + "epoch": 0.41, + "learning_rate": 1.3382967853988623e-05, + "loss": 0.4653, + "step": 4882 + }, + { + "epoch": 0.41, + "learning_rate": 1.3380417602410884e-05, + "loss": 0.4864, + "step": 4883 + }, + { + "epoch": 0.41, + "learning_rate": 1.3377867102589336e-05, + "loss": 0.4931, + "step": 4884 + }, + { + "epoch": 0.41, + "learning_rate": 1.3375316354711277e-05, + "loss": 0.4761, + "step": 4885 + }, + { + "epoch": 0.41, + "learning_rate": 1.3372765358964024e-05, + "loss": 0.489, + "step": 4886 + }, + { + "epoch": 0.41, + "learning_rate": 1.3370214115534912e-05, + "loss": 0.4897, + "step": 4887 + }, + { + "epoch": 0.41, + "learning_rate": 1.3367662624611293e-05, + "loss": 0.4856, + "step": 4888 + }, + { + "epoch": 0.41, + "learning_rate": 1.3365110886380537e-05, + "loss": 0.5125, + "step": 4889 + }, + { + "epoch": 0.41, + "learning_rate": 1.3362558901030035e-05, + "loss": 0.4959, + "step": 4890 + }, + { + "epoch": 0.41, + "learning_rate": 1.3360006668747195e-05, + "loss": 0.4597, + "step": 4891 + }, + { + "epoch": 0.41, + "learning_rate": 1.3357454189719437e-05, + "loss": 0.5056, + "step": 4892 + }, + { + "epoch": 0.41, + "learning_rate": 1.3354901464134208e-05, + "loss": 0.4856, + "step": 4893 + }, + { + "epoch": 0.41, + "learning_rate": 1.3352348492178972e-05, + "loss": 0.4788, + "step": 4894 + }, + { + "epoch": 0.41, + "learning_rate": 1.3349795274041208e-05, + "loss": 0.4858, + "step": 4895 + }, + { + "epoch": 0.41, + "learning_rate": 1.3347241809908408e-05, + "loss": 0.4982, + "step": 4896 + }, + { + "epoch": 0.41, + "learning_rate": 1.3344688099968092e-05, + "loss": 0.4558, + "step": 4897 + }, + { + "epoch": 0.41, + "learning_rate": 1.3342134144407796e-05, + "loss": 0.482, + "step": 4898 + }, + { + "epoch": 0.41, + "learning_rate": 1.3339579943415069e-05, + "loss": 0.5045, + "step": 4899 + }, + { + "epoch": 0.41, + "learning_rate": 1.333702549717748e-05, + "loss": 0.4684, + "step": 4900 + }, + { + "epoch": 0.41, + "learning_rate": 1.3334470805882615e-05, + "loss": 0.4804, + "step": 4901 + }, + { + "epoch": 0.41, + "learning_rate": 1.3331915869718088e-05, + "loss": 0.4914, + "step": 4902 + }, + { + "epoch": 0.41, + "learning_rate": 1.3329360688871518e-05, + "loss": 0.4885, + "step": 4903 + }, + { + "epoch": 0.41, + "learning_rate": 1.3326805263530545e-05, + "loss": 0.4959, + "step": 4904 + }, + { + "epoch": 0.41, + "learning_rate": 1.3324249593882832e-05, + "loss": 0.4996, + "step": 4905 + }, + { + "epoch": 0.41, + "learning_rate": 1.3321693680116054e-05, + "loss": 0.4728, + "step": 4906 + }, + { + "epoch": 0.41, + "learning_rate": 1.3319137522417908e-05, + "loss": 0.4861, + "step": 4907 + }, + { + "epoch": 0.41, + "learning_rate": 1.3316581120976109e-05, + "loss": 0.4854, + "step": 4908 + }, + { + "epoch": 0.41, + "learning_rate": 1.3314024475978388e-05, + "loss": 0.4933, + "step": 4909 + }, + { + "epoch": 0.41, + "learning_rate": 1.331146758761249e-05, + "loss": 0.4676, + "step": 4910 + }, + { + "epoch": 0.41, + "learning_rate": 1.3308910456066191e-05, + "loss": 0.4983, + "step": 4911 + }, + { + "epoch": 0.41, + "learning_rate": 1.3306353081527265e-05, + "loss": 0.5059, + "step": 4912 + }, + { + "epoch": 0.41, + "learning_rate": 1.3303795464183522e-05, + "loss": 0.4859, + "step": 4913 + }, + { + "epoch": 0.41, + "learning_rate": 1.3301237604222786e-05, + "loss": 0.5003, + "step": 4914 + }, + { + "epoch": 0.41, + "learning_rate": 1.329867950183289e-05, + "loss": 0.4709, + "step": 4915 + }, + { + "epoch": 0.41, + "learning_rate": 1.3296121157201689e-05, + "loss": 0.5096, + "step": 4916 + }, + { + "epoch": 0.41, + "learning_rate": 1.329356257051706e-05, + "loss": 0.4888, + "step": 4917 + }, + { + "epoch": 0.41, + "learning_rate": 1.3291003741966898e-05, + "loss": 0.4876, + "step": 4918 + }, + { + "epoch": 0.41, + "learning_rate": 1.3288444671739106e-05, + "loss": 0.4887, + "step": 4919 + }, + { + "epoch": 0.41, + "learning_rate": 1.3285885360021615e-05, + "loss": 0.4732, + "step": 4920 + }, + { + "epoch": 0.41, + "learning_rate": 1.3283325807002374e-05, + "loss": 0.4874, + "step": 4921 + }, + { + "epoch": 0.41, + "learning_rate": 1.3280766012869338e-05, + "loss": 0.4845, + "step": 4922 + }, + { + "epoch": 0.41, + "learning_rate": 1.3278205977810492e-05, + "loss": 0.4866, + "step": 4923 + }, + { + "epoch": 0.41, + "learning_rate": 1.3275645702013836e-05, + "loss": 0.4692, + "step": 4924 + }, + { + "epoch": 0.41, + "learning_rate": 1.3273085185667385e-05, + "loss": 0.4743, + "step": 4925 + }, + { + "epoch": 0.41, + "learning_rate": 1.327052442895917e-05, + "loss": 0.4811, + "step": 4926 + }, + { + "epoch": 0.41, + "learning_rate": 1.3267963432077242e-05, + "loss": 0.4902, + "step": 4927 + }, + { + "epoch": 0.41, + "learning_rate": 1.3265402195209675e-05, + "loss": 0.475, + "step": 4928 + }, + { + "epoch": 0.41, + "learning_rate": 1.3262840718544552e-05, + "loss": 0.4967, + "step": 4929 + }, + { + "epoch": 0.41, + "learning_rate": 1.3260279002269977e-05, + "loss": 0.4948, + "step": 4930 + }, + { + "epoch": 0.41, + "learning_rate": 1.3257717046574074e-05, + "loss": 0.467, + "step": 4931 + }, + { + "epoch": 0.41, + "learning_rate": 1.325515485164498e-05, + "loss": 0.4723, + "step": 4932 + }, + { + "epoch": 0.41, + "learning_rate": 1.3252592417670856e-05, + "loss": 0.4997, + "step": 4933 + }, + { + "epoch": 0.41, + "learning_rate": 1.3250029744839867e-05, + "loss": 0.4764, + "step": 4934 + }, + { + "epoch": 0.41, + "learning_rate": 1.3247466833340216e-05, + "loss": 0.492, + "step": 4935 + }, + { + "epoch": 0.41, + "learning_rate": 1.324490368336011e-05, + "loss": 0.4627, + "step": 4936 + }, + { + "epoch": 0.41, + "learning_rate": 1.324234029508777e-05, + "loss": 0.484, + "step": 4937 + }, + { + "epoch": 0.41, + "learning_rate": 1.3239776668711444e-05, + "loss": 0.4789, + "step": 4938 + }, + { + "epoch": 0.41, + "learning_rate": 1.3237212804419398e-05, + "loss": 0.4715, + "step": 4939 + }, + { + "epoch": 0.41, + "learning_rate": 1.3234648702399903e-05, + "loss": 0.4995, + "step": 4940 + }, + { + "epoch": 0.41, + "learning_rate": 1.3232084362841267e-05, + "loss": 0.4747, + "step": 4941 + }, + { + "epoch": 0.41, + "learning_rate": 1.3229519785931795e-05, + "loss": 0.4898, + "step": 4942 + }, + { + "epoch": 0.41, + "learning_rate": 1.3226954971859827e-05, + "loss": 0.5059, + "step": 4943 + }, + { + "epoch": 0.41, + "learning_rate": 1.3224389920813703e-05, + "loss": 0.4816, + "step": 4944 + }, + { + "epoch": 0.41, + "learning_rate": 1.3221824632981797e-05, + "loss": 0.474, + "step": 4945 + }, + { + "epoch": 0.41, + "learning_rate": 1.3219259108552488e-05, + "loss": 0.4707, + "step": 4946 + }, + { + "epoch": 0.41, + "learning_rate": 1.3216693347714183e-05, + "loss": 0.4751, + "step": 4947 + }, + { + "epoch": 0.41, + "learning_rate": 1.3214127350655294e-05, + "loss": 0.4763, + "step": 4948 + }, + { + "epoch": 0.41, + "learning_rate": 1.3211561117564267e-05, + "loss": 0.517, + "step": 4949 + }, + { + "epoch": 0.41, + "learning_rate": 1.3208994648629546e-05, + "loss": 0.4788, + "step": 4950 + }, + { + "epoch": 0.41, + "learning_rate": 1.3206427944039604e-05, + "loss": 0.4886, + "step": 4951 + }, + { + "epoch": 0.41, + "learning_rate": 1.3203861003982933e-05, + "loss": 0.4797, + "step": 4952 + }, + { + "epoch": 0.41, + "learning_rate": 1.3201293828648032e-05, + "loss": 0.4796, + "step": 4953 + }, + { + "epoch": 0.41, + "learning_rate": 1.3198726418223428e-05, + "loss": 0.4591, + "step": 4954 + }, + { + "epoch": 0.41, + "learning_rate": 1.3196158772897663e-05, + "loss": 0.4763, + "step": 4955 + }, + { + "epoch": 0.41, + "learning_rate": 1.3193590892859291e-05, + "loss": 0.4906, + "step": 4956 + }, + { + "epoch": 0.41, + "learning_rate": 1.3191022778296887e-05, + "loss": 0.492, + "step": 4957 + }, + { + "epoch": 0.41, + "learning_rate": 1.318845442939904e-05, + "loss": 0.4808, + "step": 4958 + }, + { + "epoch": 0.41, + "learning_rate": 1.3185885846354365e-05, + "loss": 0.495, + "step": 4959 + }, + { + "epoch": 0.41, + "learning_rate": 1.3183317029351483e-05, + "loss": 0.4769, + "step": 4960 + }, + { + "epoch": 0.42, + "learning_rate": 1.3180747978579039e-05, + "loss": 0.4781, + "step": 4961 + }, + { + "epoch": 0.42, + "learning_rate": 1.3178178694225695e-05, + "loss": 0.4663, + "step": 4962 + }, + { + "epoch": 0.42, + "learning_rate": 1.3175609176480122e-05, + "loss": 0.4681, + "step": 4963 + }, + { + "epoch": 0.42, + "learning_rate": 1.317303942553102e-05, + "loss": 0.4945, + "step": 4964 + }, + { + "epoch": 0.42, + "learning_rate": 1.3170469441567104e-05, + "loss": 0.47, + "step": 4965 + }, + { + "epoch": 0.42, + "learning_rate": 1.3167899224777098e-05, + "loss": 0.4708, + "step": 4966 + }, + { + "epoch": 0.42, + "learning_rate": 1.316532877534975e-05, + "loss": 0.5071, + "step": 4967 + }, + { + "epoch": 0.42, + "learning_rate": 1.316275809347382e-05, + "loss": 0.4788, + "step": 4968 + }, + { + "epoch": 0.42, + "learning_rate": 1.316018717933809e-05, + "loss": 0.4694, + "step": 4969 + }, + { + "epoch": 0.42, + "learning_rate": 1.3157616033131361e-05, + "loss": 0.4749, + "step": 4970 + }, + { + "epoch": 0.42, + "learning_rate": 1.315504465504244e-05, + "loss": 0.4792, + "step": 4971 + }, + { + "epoch": 0.42, + "learning_rate": 1.3152473045260168e-05, + "loss": 0.4936, + "step": 4972 + }, + { + "epoch": 0.42, + "learning_rate": 1.3149901203973383e-05, + "loss": 0.5079, + "step": 4973 + }, + { + "epoch": 0.42, + "learning_rate": 1.3147329131370956e-05, + "loss": 0.4884, + "step": 4974 + }, + { + "epoch": 0.42, + "learning_rate": 1.3144756827641769e-05, + "loss": 0.4967, + "step": 4975 + }, + { + "epoch": 0.42, + "learning_rate": 1.3142184292974723e-05, + "loss": 0.48, + "step": 4976 + }, + { + "epoch": 0.42, + "learning_rate": 1.3139611527558729e-05, + "loss": 0.502, + "step": 4977 + }, + { + "epoch": 0.42, + "learning_rate": 1.3137038531582721e-05, + "loss": 0.4875, + "step": 4978 + }, + { + "epoch": 0.42, + "learning_rate": 1.3134465305235653e-05, + "loss": 0.4827, + "step": 4979 + }, + { + "epoch": 0.42, + "learning_rate": 1.3131891848706492e-05, + "loss": 0.479, + "step": 4980 + }, + { + "epoch": 0.42, + "learning_rate": 1.3129318162184216e-05, + "loss": 0.4702, + "step": 4981 + }, + { + "epoch": 0.42, + "learning_rate": 1.3126744245857835e-05, + "loss": 0.4727, + "step": 4982 + }, + { + "epoch": 0.42, + "learning_rate": 1.312417009991636e-05, + "loss": 0.4882, + "step": 4983 + }, + { + "epoch": 0.42, + "learning_rate": 1.3121595724548825e-05, + "loss": 0.4865, + "step": 4984 + }, + { + "epoch": 0.42, + "learning_rate": 1.3119021119944287e-05, + "loss": 0.4924, + "step": 4985 + }, + { + "epoch": 0.42, + "learning_rate": 1.3116446286291811e-05, + "loss": 0.499, + "step": 4986 + }, + { + "epoch": 0.42, + "learning_rate": 1.3113871223780481e-05, + "loss": 0.4787, + "step": 4987 + }, + { + "epoch": 0.42, + "learning_rate": 1.3111295932599396e-05, + "loss": 0.478, + "step": 4988 + }, + { + "epoch": 0.42, + "learning_rate": 1.3108720412937681e-05, + "loss": 0.4822, + "step": 4989 + }, + { + "epoch": 0.42, + "learning_rate": 1.3106144664984473e-05, + "loss": 0.4804, + "step": 4990 + }, + { + "epoch": 0.42, + "learning_rate": 1.3103568688928917e-05, + "loss": 0.4707, + "step": 4991 + }, + { + "epoch": 0.42, + "learning_rate": 1.3100992484960185e-05, + "loss": 0.4968, + "step": 4992 + }, + { + "epoch": 0.42, + "learning_rate": 1.3098416053267463e-05, + "loss": 0.4693, + "step": 4993 + }, + { + "epoch": 0.42, + "learning_rate": 1.3095839394039953e-05, + "loss": 0.4758, + "step": 4994 + }, + { + "epoch": 0.42, + "learning_rate": 1.3093262507466873e-05, + "loss": 0.5018, + "step": 4995 + }, + { + "epoch": 0.42, + "learning_rate": 1.3090685393737464e-05, + "loss": 0.4784, + "step": 4996 + }, + { + "epoch": 0.42, + "learning_rate": 1.3088108053040974e-05, + "loss": 0.4755, + "step": 4997 + }, + { + "epoch": 0.42, + "learning_rate": 1.308553048556667e-05, + "loss": 0.4867, + "step": 4998 + }, + { + "epoch": 0.42, + "learning_rate": 1.3082952691503843e-05, + "loss": 0.4803, + "step": 4999 + }, + { + "epoch": 0.42, + "learning_rate": 1.3080374671041793e-05, + "loss": 0.4798, + "step": 5000 + }, + { + "epoch": 0.42, + "learning_rate": 1.3077796424369842e-05, + "loss": 0.4852, + "step": 5001 + }, + { + "epoch": 0.42, + "learning_rate": 1.307521795167732e-05, + "loss": 0.4841, + "step": 5002 + }, + { + "epoch": 0.42, + "learning_rate": 1.3072639253153583e-05, + "loss": 0.5082, + "step": 5003 + }, + { + "epoch": 0.42, + "learning_rate": 1.3070060328988e-05, + "loss": 0.4823, + "step": 5004 + }, + { + "epoch": 0.42, + "learning_rate": 1.3067481179369951e-05, + "loss": 0.4915, + "step": 5005 + }, + { + "epoch": 0.42, + "learning_rate": 1.306490180448885e-05, + "loss": 0.5137, + "step": 5006 + }, + { + "epoch": 0.42, + "learning_rate": 1.3062322204534105e-05, + "loss": 0.509, + "step": 5007 + }, + { + "epoch": 0.42, + "learning_rate": 1.3059742379695158e-05, + "loss": 0.4846, + "step": 5008 + }, + { + "epoch": 0.42, + "learning_rate": 1.3057162330161453e-05, + "loss": 0.4945, + "step": 5009 + }, + { + "epoch": 0.42, + "learning_rate": 1.305458205612246e-05, + "loss": 0.4883, + "step": 5010 + }, + { + "epoch": 0.42, + "learning_rate": 1.3052001557767671e-05, + "loss": 0.4953, + "step": 5011 + }, + { + "epoch": 0.42, + "learning_rate": 1.304942083528658e-05, + "loss": 0.5003, + "step": 5012 + }, + { + "epoch": 0.42, + "learning_rate": 1.3046839888868706e-05, + "loss": 0.4656, + "step": 5013 + }, + { + "epoch": 0.42, + "learning_rate": 1.3044258718703581e-05, + "loss": 0.492, + "step": 5014 + }, + { + "epoch": 0.42, + "learning_rate": 1.304167732498076e-05, + "loss": 0.4865, + "step": 5015 + }, + { + "epoch": 0.42, + "learning_rate": 1.3039095707889808e-05, + "loss": 0.486, + "step": 5016 + }, + { + "epoch": 0.42, + "learning_rate": 1.3036513867620309e-05, + "loss": 0.4977, + "step": 5017 + }, + { + "epoch": 0.42, + "learning_rate": 1.303393180436186e-05, + "loss": 0.4894, + "step": 5018 + }, + { + "epoch": 0.42, + "learning_rate": 1.3031349518304078e-05, + "loss": 0.4717, + "step": 5019 + }, + { + "epoch": 0.42, + "learning_rate": 1.3028767009636593e-05, + "loss": 0.5052, + "step": 5020 + }, + { + "epoch": 0.42, + "learning_rate": 1.3026184278549062e-05, + "loss": 0.4768, + "step": 5021 + }, + { + "epoch": 0.42, + "learning_rate": 1.302360132523114e-05, + "loss": 0.4759, + "step": 5022 + }, + { + "epoch": 0.42, + "learning_rate": 1.3021018149872516e-05, + "loss": 0.4861, + "step": 5023 + }, + { + "epoch": 0.42, + "learning_rate": 1.3018434752662882e-05, + "loss": 0.5004, + "step": 5024 + }, + { + "epoch": 0.42, + "learning_rate": 1.3015851133791955e-05, + "loss": 0.4867, + "step": 5025 + }, + { + "epoch": 0.42, + "learning_rate": 1.3013267293449463e-05, + "loss": 0.4708, + "step": 5026 + }, + { + "epoch": 0.42, + "learning_rate": 1.3010683231825158e-05, + "loss": 0.4981, + "step": 5027 + }, + { + "epoch": 0.42, + "learning_rate": 1.30080989491088e-05, + "loss": 0.4881, + "step": 5028 + }, + { + "epoch": 0.42, + "learning_rate": 1.300551444549016e-05, + "loss": 0.4787, + "step": 5029 + }, + { + "epoch": 0.42, + "learning_rate": 1.3002929721159043e-05, + "loss": 0.504, + "step": 5030 + }, + { + "epoch": 0.42, + "learning_rate": 1.3000344776305258e-05, + "loss": 0.511, + "step": 5031 + }, + { + "epoch": 0.42, + "learning_rate": 1.2997759611118634e-05, + "loss": 0.4751, + "step": 5032 + }, + { + "epoch": 0.42, + "learning_rate": 1.2995174225789008e-05, + "loss": 0.5148, + "step": 5033 + }, + { + "epoch": 0.42, + "learning_rate": 1.2992588620506251e-05, + "loss": 0.5013, + "step": 5034 + }, + { + "epoch": 0.42, + "learning_rate": 1.2990002795460228e-05, + "loss": 0.4959, + "step": 5035 + }, + { + "epoch": 0.42, + "learning_rate": 1.2987416750840836e-05, + "loss": 0.4788, + "step": 5036 + }, + { + "epoch": 0.42, + "learning_rate": 1.2984830486837985e-05, + "loss": 0.4932, + "step": 5037 + }, + { + "epoch": 0.42, + "learning_rate": 1.2982244003641599e-05, + "loss": 0.487, + "step": 5038 + }, + { + "epoch": 0.42, + "learning_rate": 1.2979657301441615e-05, + "loss": 0.4873, + "step": 5039 + }, + { + "epoch": 0.42, + "learning_rate": 1.2977070380427993e-05, + "loss": 0.4762, + "step": 5040 + }, + { + "epoch": 0.42, + "learning_rate": 1.2974483240790705e-05, + "loss": 0.4804, + "step": 5041 + }, + { + "epoch": 0.42, + "learning_rate": 1.2971895882719741e-05, + "loss": 0.4935, + "step": 5042 + }, + { + "epoch": 0.42, + "learning_rate": 1.2969308306405102e-05, + "loss": 0.4742, + "step": 5043 + }, + { + "epoch": 0.42, + "learning_rate": 1.2966720512036813e-05, + "loss": 0.5088, + "step": 5044 + }, + { + "epoch": 0.42, + "learning_rate": 1.2964132499804907e-05, + "loss": 0.4828, + "step": 5045 + }, + { + "epoch": 0.42, + "learning_rate": 1.296154426989944e-05, + "loss": 0.4859, + "step": 5046 + }, + { + "epoch": 0.42, + "learning_rate": 1.2958955822510482e-05, + "loss": 0.4948, + "step": 5047 + }, + { + "epoch": 0.42, + "learning_rate": 1.2956367157828113e-05, + "loss": 0.4609, + "step": 5048 + }, + { + "epoch": 0.42, + "learning_rate": 1.295377827604244e-05, + "loss": 0.5, + "step": 5049 + }, + { + "epoch": 0.42, + "learning_rate": 1.295118917734357e-05, + "loss": 0.4859, + "step": 5050 + }, + { + "epoch": 0.42, + "learning_rate": 1.2948599861921644e-05, + "loss": 0.4748, + "step": 5051 + }, + { + "epoch": 0.42, + "learning_rate": 1.2946010329966811e-05, + "loss": 0.4679, + "step": 5052 + }, + { + "epoch": 0.42, + "learning_rate": 1.2943420581669231e-05, + "loss": 0.4995, + "step": 5053 + }, + { + "epoch": 0.42, + "learning_rate": 1.2940830617219087e-05, + "loss": 0.5, + "step": 5054 + }, + { + "epoch": 0.42, + "learning_rate": 1.2938240436806575e-05, + "loss": 0.4732, + "step": 5055 + }, + { + "epoch": 0.42, + "learning_rate": 1.2935650040621901e-05, + "loss": 0.4839, + "step": 5056 + }, + { + "epoch": 0.42, + "learning_rate": 1.2933059428855303e-05, + "loss": 0.4713, + "step": 5057 + }, + { + "epoch": 0.42, + "learning_rate": 1.2930468601697022e-05, + "loss": 0.4795, + "step": 5058 + }, + { + "epoch": 0.42, + "learning_rate": 1.2927877559337311e-05, + "loss": 0.4778, + "step": 5059 + }, + { + "epoch": 0.42, + "learning_rate": 1.2925286301966451e-05, + "loss": 0.4813, + "step": 5060 + }, + { + "epoch": 0.42, + "learning_rate": 1.2922694829774733e-05, + "loss": 0.5003, + "step": 5061 + }, + { + "epoch": 0.42, + "learning_rate": 1.2920103142952465e-05, + "loss": 0.4835, + "step": 5062 + }, + { + "epoch": 0.42, + "learning_rate": 1.2917511241689963e-05, + "loss": 0.4714, + "step": 5063 + }, + { + "epoch": 0.42, + "learning_rate": 1.2914919126177576e-05, + "loss": 0.5055, + "step": 5064 + }, + { + "epoch": 0.42, + "learning_rate": 1.291232679660565e-05, + "loss": 0.4942, + "step": 5065 + }, + { + "epoch": 0.42, + "learning_rate": 1.2909734253164557e-05, + "loss": 0.4614, + "step": 5066 + }, + { + "epoch": 0.42, + "learning_rate": 1.2907141496044679e-05, + "loss": 0.4689, + "step": 5067 + }, + { + "epoch": 0.42, + "learning_rate": 1.2904548525436429e-05, + "loss": 0.4843, + "step": 5068 + }, + { + "epoch": 0.42, + "learning_rate": 1.2901955341530213e-05, + "loss": 0.472, + "step": 5069 + }, + { + "epoch": 0.42, + "learning_rate": 1.2899361944516464e-05, + "loss": 0.489, + "step": 5070 + }, + { + "epoch": 0.42, + "learning_rate": 1.2896768334585635e-05, + "loss": 0.5033, + "step": 5071 + }, + { + "epoch": 0.42, + "learning_rate": 1.2894174511928189e-05, + "loss": 0.4797, + "step": 5072 + }, + { + "epoch": 0.42, + "learning_rate": 1.2891580476734602e-05, + "loss": 0.4992, + "step": 5073 + }, + { + "epoch": 0.42, + "learning_rate": 1.2888986229195375e-05, + "loss": 0.4896, + "step": 5074 + }, + { + "epoch": 0.42, + "learning_rate": 1.2886391769501016e-05, + "loss": 0.4872, + "step": 5075 + }, + { + "epoch": 0.42, + "learning_rate": 1.2883797097842048e-05, + "loss": 0.4663, + "step": 5076 + }, + { + "epoch": 0.42, + "learning_rate": 1.2881202214409016e-05, + "loss": 0.4954, + "step": 5077 + }, + { + "epoch": 0.42, + "learning_rate": 1.2878607119392479e-05, + "loss": 0.5041, + "step": 5078 + }, + { + "epoch": 0.42, + "learning_rate": 1.2876011812983009e-05, + "loss": 0.4777, + "step": 5079 + }, + { + "epoch": 0.43, + "learning_rate": 1.287341629537119e-05, + "loss": 0.5026, + "step": 5080 + }, + { + "epoch": 0.43, + "learning_rate": 1.2870820566747633e-05, + "loss": 0.471, + "step": 5081 + }, + { + "epoch": 0.43, + "learning_rate": 1.2868224627302952e-05, + "loss": 0.4873, + "step": 5082 + }, + { + "epoch": 0.43, + "learning_rate": 1.2865628477227787e-05, + "loss": 0.488, + "step": 5083 + }, + { + "epoch": 0.43, + "learning_rate": 1.2863032116712781e-05, + "loss": 0.4907, + "step": 5084 + }, + { + "epoch": 0.43, + "learning_rate": 1.2860435545948609e-05, + "loss": 0.4816, + "step": 5085 + }, + { + "epoch": 0.43, + "learning_rate": 1.2857838765125945e-05, + "loss": 0.4917, + "step": 5086 + }, + { + "epoch": 0.43, + "learning_rate": 1.285524177443549e-05, + "loss": 0.4916, + "step": 5087 + }, + { + "epoch": 0.43, + "learning_rate": 1.2852644574067955e-05, + "loss": 0.4771, + "step": 5088 + }, + { + "epoch": 0.43, + "learning_rate": 1.285004716421407e-05, + "loss": 0.4911, + "step": 5089 + }, + { + "epoch": 0.43, + "learning_rate": 1.2847449545064572e-05, + "loss": 0.4913, + "step": 5090 + }, + { + "epoch": 0.43, + "learning_rate": 1.2844851716810225e-05, + "loss": 0.4803, + "step": 5091 + }, + { + "epoch": 0.43, + "learning_rate": 1.2842253679641799e-05, + "loss": 0.4891, + "step": 5092 + }, + { + "epoch": 0.43, + "learning_rate": 1.2839655433750084e-05, + "loss": 0.4777, + "step": 5093 + }, + { + "epoch": 0.43, + "learning_rate": 1.2837056979325886e-05, + "loss": 0.4791, + "step": 5094 + }, + { + "epoch": 0.43, + "learning_rate": 1.2834458316560023e-05, + "loss": 0.4653, + "step": 5095 + }, + { + "epoch": 0.43, + "learning_rate": 1.2831859445643333e-05, + "loss": 0.4935, + "step": 5096 + }, + { + "epoch": 0.43, + "learning_rate": 1.282926036676666e-05, + "loss": 0.5006, + "step": 5097 + }, + { + "epoch": 0.43, + "learning_rate": 1.2826661080120877e-05, + "loss": 0.463, + "step": 5098 + }, + { + "epoch": 0.43, + "learning_rate": 1.282406158589686e-05, + "loss": 0.4902, + "step": 5099 + }, + { + "epoch": 0.43, + "learning_rate": 1.2821461884285506e-05, + "loss": 0.4759, + "step": 5100 + }, + { + "epoch": 0.43, + "learning_rate": 1.2818861975477728e-05, + "loss": 0.4796, + "step": 5101 + }, + { + "epoch": 0.43, + "learning_rate": 1.2816261859664448e-05, + "loss": 0.4833, + "step": 5102 + }, + { + "epoch": 0.43, + "learning_rate": 1.2813661537036613e-05, + "loss": 0.4863, + "step": 5103 + }, + { + "epoch": 0.43, + "learning_rate": 1.2811061007785175e-05, + "loss": 0.4719, + "step": 5104 + }, + { + "epoch": 0.43, + "learning_rate": 1.2808460272101113e-05, + "loss": 0.4843, + "step": 5105 + }, + { + "epoch": 0.43, + "learning_rate": 1.280585933017541e-05, + "loss": 0.4763, + "step": 5106 + }, + { + "epoch": 0.43, + "learning_rate": 1.2803258182199064e-05, + "loss": 0.4812, + "step": 5107 + }, + { + "epoch": 0.43, + "learning_rate": 1.2800656828363098e-05, + "loss": 0.4878, + "step": 5108 + }, + { + "epoch": 0.43, + "learning_rate": 1.2798055268858544e-05, + "loss": 0.4949, + "step": 5109 + }, + { + "epoch": 0.43, + "learning_rate": 1.2795453503876449e-05, + "loss": 0.5089, + "step": 5110 + }, + { + "epoch": 0.43, + "learning_rate": 1.2792851533607875e-05, + "loss": 0.482, + "step": 5111 + }, + { + "epoch": 0.43, + "learning_rate": 1.2790249358243902e-05, + "loss": 0.5057, + "step": 5112 + }, + { + "epoch": 0.43, + "learning_rate": 1.2787646977975623e-05, + "loss": 0.5177, + "step": 5113 + }, + { + "epoch": 0.43, + "learning_rate": 1.2785044392994142e-05, + "loss": 0.461, + "step": 5114 + }, + { + "epoch": 0.43, + "learning_rate": 1.2782441603490585e-05, + "loss": 0.479, + "step": 5115 + }, + { + "epoch": 0.43, + "learning_rate": 1.277983860965609e-05, + "loss": 0.5029, + "step": 5116 + }, + { + "epoch": 0.43, + "learning_rate": 1.277723541168181e-05, + "loss": 0.475, + "step": 5117 + }, + { + "epoch": 0.43, + "learning_rate": 1.2774632009758911e-05, + "loss": 0.4754, + "step": 5118 + }, + { + "epoch": 0.43, + "learning_rate": 1.2772028404078581e-05, + "loss": 0.483, + "step": 5119 + }, + { + "epoch": 0.43, + "learning_rate": 1.2769424594832014e-05, + "loss": 0.4806, + "step": 5120 + }, + { + "epoch": 0.43, + "learning_rate": 1.2766820582210421e-05, + "loss": 0.4651, + "step": 5121 + }, + { + "epoch": 0.43, + "learning_rate": 1.2764216366405036e-05, + "loss": 0.4875, + "step": 5122 + }, + { + "epoch": 0.43, + "learning_rate": 1.2761611947607095e-05, + "loss": 0.4948, + "step": 5123 + }, + { + "epoch": 0.43, + "learning_rate": 1.2759007326007862e-05, + "loss": 0.4835, + "step": 5124 + }, + { + "epoch": 0.43, + "learning_rate": 1.2756402501798606e-05, + "loss": 0.4828, + "step": 5125 + }, + { + "epoch": 0.43, + "learning_rate": 1.2753797475170613e-05, + "loss": 0.4781, + "step": 5126 + }, + { + "epoch": 0.43, + "learning_rate": 1.275119224631519e-05, + "loss": 0.4875, + "step": 5127 + }, + { + "epoch": 0.43, + "learning_rate": 1.2748586815423646e-05, + "loss": 0.4688, + "step": 5128 + }, + { + "epoch": 0.43, + "learning_rate": 1.2745981182687323e-05, + "loss": 0.479, + "step": 5129 + }, + { + "epoch": 0.43, + "learning_rate": 1.2743375348297567e-05, + "loss": 0.4941, + "step": 5130 + }, + { + "epoch": 0.43, + "learning_rate": 1.274076931244573e-05, + "loss": 0.5048, + "step": 5131 + }, + { + "epoch": 0.43, + "learning_rate": 1.2738163075323198e-05, + "loss": 0.4627, + "step": 5132 + }, + { + "epoch": 0.43, + "learning_rate": 1.2735556637121356e-05, + "loss": 0.4784, + "step": 5133 + }, + { + "epoch": 0.43, + "learning_rate": 1.2732949998031612e-05, + "loss": 0.4883, + "step": 5134 + }, + { + "epoch": 0.43, + "learning_rate": 1.2730343158245389e-05, + "loss": 0.4992, + "step": 5135 + }, + { + "epoch": 0.43, + "learning_rate": 1.2727736117954122e-05, + "loss": 0.4715, + "step": 5136 + }, + { + "epoch": 0.43, + "learning_rate": 1.272512887734926e-05, + "loss": 0.4769, + "step": 5137 + }, + { + "epoch": 0.43, + "learning_rate": 1.2722521436622263e-05, + "loss": 0.5004, + "step": 5138 + }, + { + "epoch": 0.43, + "learning_rate": 1.2719913795964618e-05, + "loss": 0.4909, + "step": 5139 + }, + { + "epoch": 0.43, + "learning_rate": 1.271730595556782e-05, + "loss": 0.4747, + "step": 5140 + }, + { + "epoch": 0.43, + "learning_rate": 1.2714697915623374e-05, + "loss": 0.4969, + "step": 5141 + }, + { + "epoch": 0.43, + "learning_rate": 1.2712089676322803e-05, + "loss": 0.479, + "step": 5142 + }, + { + "epoch": 0.43, + "learning_rate": 1.2709481237857643e-05, + "loss": 0.4771, + "step": 5143 + }, + { + "epoch": 0.43, + "learning_rate": 1.2706872600419456e-05, + "loss": 0.5098, + "step": 5144 + }, + { + "epoch": 0.43, + "learning_rate": 1.2704263764199803e-05, + "loss": 0.4819, + "step": 5145 + }, + { + "epoch": 0.43, + "learning_rate": 1.2701654729390264e-05, + "loss": 0.4838, + "step": 5146 + }, + { + "epoch": 0.43, + "learning_rate": 1.2699045496182442e-05, + "loss": 0.4829, + "step": 5147 + }, + { + "epoch": 0.43, + "learning_rate": 1.2696436064767943e-05, + "loss": 0.4952, + "step": 5148 + }, + { + "epoch": 0.43, + "learning_rate": 1.2693826435338394e-05, + "loss": 0.4854, + "step": 5149 + }, + { + "epoch": 0.43, + "learning_rate": 1.269121660808544e-05, + "loss": 0.483, + "step": 5150 + }, + { + "epoch": 0.43, + "learning_rate": 1.2688606583200728e-05, + "loss": 0.4843, + "step": 5151 + }, + { + "epoch": 0.43, + "learning_rate": 1.2685996360875933e-05, + "loss": 0.4863, + "step": 5152 + }, + { + "epoch": 0.43, + "learning_rate": 1.2683385941302737e-05, + "loss": 0.4922, + "step": 5153 + }, + { + "epoch": 0.43, + "learning_rate": 1.2680775324672839e-05, + "loss": 0.4687, + "step": 5154 + }, + { + "epoch": 0.43, + "learning_rate": 1.2678164511177948e-05, + "loss": 0.494, + "step": 5155 + }, + { + "epoch": 0.43, + "learning_rate": 1.26755535010098e-05, + "loss": 0.4872, + "step": 5156 + }, + { + "epoch": 0.43, + "learning_rate": 1.267294229436013e-05, + "loss": 0.4892, + "step": 5157 + }, + { + "epoch": 0.43, + "learning_rate": 1.2670330891420694e-05, + "loss": 0.4867, + "step": 5158 + }, + { + "epoch": 0.43, + "learning_rate": 1.266771929238326e-05, + "loss": 0.4676, + "step": 5159 + }, + { + "epoch": 0.43, + "learning_rate": 1.2665107497439623e-05, + "loss": 0.4976, + "step": 5160 + }, + { + "epoch": 0.43, + "learning_rate": 1.2662495506781575e-05, + "loss": 0.4855, + "step": 5161 + }, + { + "epoch": 0.43, + "learning_rate": 1.265988332060093e-05, + "loss": 0.4878, + "step": 5162 + }, + { + "epoch": 0.43, + "learning_rate": 1.265727093908952e-05, + "loss": 0.4841, + "step": 5163 + }, + { + "epoch": 0.43, + "learning_rate": 1.265465836243918e-05, + "loss": 0.4876, + "step": 5164 + }, + { + "epoch": 0.43, + "learning_rate": 1.2652045590841774e-05, + "loss": 0.4905, + "step": 5165 + }, + { + "epoch": 0.43, + "learning_rate": 1.2649432624489171e-05, + "loss": 0.4761, + "step": 5166 + }, + { + "epoch": 0.43, + "learning_rate": 1.2646819463573257e-05, + "loss": 0.4716, + "step": 5167 + }, + { + "epoch": 0.43, + "learning_rate": 1.264420610828593e-05, + "loss": 0.4791, + "step": 5168 + }, + { + "epoch": 0.43, + "learning_rate": 1.2641592558819102e-05, + "loss": 0.4844, + "step": 5169 + }, + { + "epoch": 0.43, + "learning_rate": 1.2638978815364705e-05, + "loss": 0.4864, + "step": 5170 + }, + { + "epoch": 0.43, + "learning_rate": 1.2636364878114682e-05, + "loss": 0.4723, + "step": 5171 + }, + { + "epoch": 0.43, + "learning_rate": 1.2633750747260985e-05, + "loss": 0.4821, + "step": 5172 + }, + { + "epoch": 0.43, + "learning_rate": 1.263113642299559e-05, + "loss": 0.4819, + "step": 5173 + }, + { + "epoch": 0.43, + "learning_rate": 1.2628521905510476e-05, + "loss": 0.4784, + "step": 5174 + }, + { + "epoch": 0.43, + "learning_rate": 1.2625907194997652e-05, + "loss": 0.4812, + "step": 5175 + }, + { + "epoch": 0.43, + "learning_rate": 1.2623292291649119e-05, + "loss": 0.4735, + "step": 5176 + }, + { + "epoch": 0.43, + "learning_rate": 1.2620677195656916e-05, + "loss": 0.4846, + "step": 5177 + }, + { + "epoch": 0.43, + "learning_rate": 1.261806190721308e-05, + "loss": 0.5012, + "step": 5178 + }, + { + "epoch": 0.43, + "learning_rate": 1.2615446426509663e-05, + "loss": 0.5073, + "step": 5179 + }, + { + "epoch": 0.43, + "learning_rate": 1.261283075373874e-05, + "loss": 0.4963, + "step": 5180 + }, + { + "epoch": 0.43, + "learning_rate": 1.2610214889092399e-05, + "loss": 0.4903, + "step": 5181 + }, + { + "epoch": 0.43, + "learning_rate": 1.2607598832762728e-05, + "loss": 0.485, + "step": 5182 + }, + { + "epoch": 0.43, + "learning_rate": 1.2604982584941846e-05, + "loss": 0.4773, + "step": 5183 + }, + { + "epoch": 0.43, + "learning_rate": 1.2602366145821879e-05, + "loss": 0.4819, + "step": 5184 + }, + { + "epoch": 0.43, + "learning_rate": 1.2599749515594964e-05, + "loss": 0.4781, + "step": 5185 + }, + { + "epoch": 0.43, + "learning_rate": 1.2597132694453258e-05, + "loss": 0.4648, + "step": 5186 + }, + { + "epoch": 0.43, + "learning_rate": 1.259451568258893e-05, + "loss": 0.4819, + "step": 5187 + }, + { + "epoch": 0.43, + "learning_rate": 1.2591898480194165e-05, + "loss": 0.5044, + "step": 5188 + }, + { + "epoch": 0.43, + "learning_rate": 1.2589281087461152e-05, + "loss": 0.4943, + "step": 5189 + }, + { + "epoch": 0.43, + "learning_rate": 1.2586663504582104e-05, + "loss": 0.4827, + "step": 5190 + }, + { + "epoch": 0.43, + "learning_rate": 1.258404573174925e-05, + "loss": 0.4828, + "step": 5191 + }, + { + "epoch": 0.43, + "learning_rate": 1.2581427769154826e-05, + "loss": 0.4685, + "step": 5192 + }, + { + "epoch": 0.43, + "learning_rate": 1.2578809616991081e-05, + "loss": 0.4819, + "step": 5193 + }, + { + "epoch": 0.43, + "learning_rate": 1.2576191275450287e-05, + "loss": 0.4996, + "step": 5194 + }, + { + "epoch": 0.43, + "learning_rate": 1.2573572744724718e-05, + "loss": 0.4831, + "step": 5195 + }, + { + "epoch": 0.43, + "learning_rate": 1.2570954025006672e-05, + "loss": 0.499, + "step": 5196 + }, + { + "epoch": 0.43, + "learning_rate": 1.2568335116488457e-05, + "loss": 0.4894, + "step": 5197 + }, + { + "epoch": 0.43, + "learning_rate": 1.2565716019362393e-05, + "loss": 0.4802, + "step": 5198 + }, + { + "epoch": 0.43, + "learning_rate": 1.2563096733820816e-05, + "loss": 0.479, + "step": 5199 + }, + { + "epoch": 0.44, + "learning_rate": 1.2560477260056072e-05, + "loss": 0.4739, + "step": 5200 + }, + { + "epoch": 0.44, + "learning_rate": 1.2557857598260532e-05, + "loss": 0.4864, + "step": 5201 + }, + { + "epoch": 0.44, + "learning_rate": 1.255523774862657e-05, + "loss": 0.4791, + "step": 5202 + }, + { + "epoch": 0.44, + "learning_rate": 1.2552617711346572e-05, + "loss": 0.4939, + "step": 5203 + }, + { + "epoch": 0.44, + "learning_rate": 1.254999748661295e-05, + "loss": 0.4796, + "step": 5204 + }, + { + "epoch": 0.44, + "learning_rate": 1.2547377074618114e-05, + "loss": 0.4678, + "step": 5205 + }, + { + "epoch": 0.44, + "learning_rate": 1.2544756475554505e-05, + "loss": 0.4995, + "step": 5206 + }, + { + "epoch": 0.44, + "learning_rate": 1.2542135689614565e-05, + "loss": 0.483, + "step": 5207 + }, + { + "epoch": 0.44, + "learning_rate": 1.2539514716990753e-05, + "loss": 0.4679, + "step": 5208 + }, + { + "epoch": 0.44, + "learning_rate": 1.2536893557875543e-05, + "loss": 0.4865, + "step": 5209 + }, + { + "epoch": 0.44, + "learning_rate": 1.253427221246142e-05, + "loss": 0.4795, + "step": 5210 + }, + { + "epoch": 0.44, + "learning_rate": 1.2531650680940888e-05, + "loss": 0.4777, + "step": 5211 + }, + { + "epoch": 0.44, + "learning_rate": 1.252902896350646e-05, + "loss": 0.4953, + "step": 5212 + }, + { + "epoch": 0.44, + "learning_rate": 1.252640706035066e-05, + "loss": 0.5058, + "step": 5213 + }, + { + "epoch": 0.44, + "learning_rate": 1.2523784971666039e-05, + "loss": 0.4991, + "step": 5214 + }, + { + "epoch": 0.44, + "learning_rate": 1.2521162697645144e-05, + "loss": 0.4984, + "step": 5215 + }, + { + "epoch": 0.44, + "learning_rate": 1.251854023848055e-05, + "loss": 0.4979, + "step": 5216 + }, + { + "epoch": 0.44, + "learning_rate": 1.251591759436483e-05, + "loss": 0.4866, + "step": 5217 + }, + { + "epoch": 0.44, + "learning_rate": 1.2513294765490593e-05, + "loss": 0.4815, + "step": 5218 + }, + { + "epoch": 0.44, + "learning_rate": 1.2510671752050441e-05, + "loss": 0.4922, + "step": 5219 + }, + { + "epoch": 0.44, + "learning_rate": 1.2508048554236996e-05, + "loss": 0.4619, + "step": 5220 + }, + { + "epoch": 0.44, + "learning_rate": 1.2505425172242895e-05, + "loss": 0.4701, + "step": 5221 + }, + { + "epoch": 0.44, + "learning_rate": 1.2502801606260792e-05, + "loss": 0.4784, + "step": 5222 + }, + { + "epoch": 0.44, + "learning_rate": 1.2500177856483351e-05, + "loss": 0.4772, + "step": 5223 + }, + { + "epoch": 0.44, + "learning_rate": 1.2497553923103247e-05, + "loss": 0.4912, + "step": 5224 + }, + { + "epoch": 0.44, + "learning_rate": 1.249492980631317e-05, + "loss": 0.4981, + "step": 5225 + }, + { + "epoch": 0.44, + "learning_rate": 1.2492305506305824e-05, + "loss": 0.4649, + "step": 5226 + }, + { + "epoch": 0.44, + "learning_rate": 1.2489681023273927e-05, + "loss": 0.4915, + "step": 5227 + }, + { + "epoch": 0.44, + "learning_rate": 1.2487056357410215e-05, + "loss": 0.4691, + "step": 5228 + }, + { + "epoch": 0.44, + "learning_rate": 1.2484431508907429e-05, + "loss": 0.4756, + "step": 5229 + }, + { + "epoch": 0.44, + "learning_rate": 1.2481806477958323e-05, + "loss": 0.4938, + "step": 5230 + }, + { + "epoch": 0.44, + "learning_rate": 1.247918126475567e-05, + "loss": 0.4832, + "step": 5231 + }, + { + "epoch": 0.44, + "learning_rate": 1.2476555869492262e-05, + "loss": 0.4856, + "step": 5232 + }, + { + "epoch": 0.44, + "learning_rate": 1.2473930292360889e-05, + "loss": 0.4804, + "step": 5233 + }, + { + "epoch": 0.44, + "learning_rate": 1.2471304533554364e-05, + "loss": 0.5037, + "step": 5234 + }, + { + "epoch": 0.44, + "learning_rate": 1.2468678593265518e-05, + "loss": 0.4744, + "step": 5235 + }, + { + "epoch": 0.44, + "learning_rate": 1.2466052471687178e-05, + "loss": 0.4723, + "step": 5236 + }, + { + "epoch": 0.44, + "learning_rate": 1.2463426169012204e-05, + "loss": 0.4755, + "step": 5237 + }, + { + "epoch": 0.44, + "learning_rate": 1.2460799685433457e-05, + "loss": 0.4816, + "step": 5238 + }, + { + "epoch": 0.44, + "learning_rate": 1.245817302114382e-05, + "loss": 0.4794, + "step": 5239 + }, + { + "epoch": 0.44, + "learning_rate": 1.2455546176336177e-05, + "loss": 0.4817, + "step": 5240 + }, + { + "epoch": 0.44, + "learning_rate": 1.2452919151203439e-05, + "loss": 0.5024, + "step": 5241 + }, + { + "epoch": 0.44, + "learning_rate": 1.245029194593852e-05, + "loss": 0.4645, + "step": 5242 + }, + { + "epoch": 0.44, + "learning_rate": 1.2447664560734352e-05, + "loss": 0.4934, + "step": 5243 + }, + { + "epoch": 0.44, + "learning_rate": 1.2445036995783876e-05, + "loss": 0.4699, + "step": 5244 + }, + { + "epoch": 0.44, + "learning_rate": 1.2442409251280058e-05, + "loss": 0.4868, + "step": 5245 + }, + { + "epoch": 0.44, + "learning_rate": 1.2439781327415858e-05, + "loss": 0.4947, + "step": 5246 + }, + { + "epoch": 0.44, + "learning_rate": 1.2437153224384269e-05, + "loss": 0.4851, + "step": 5247 + }, + { + "epoch": 0.44, + "learning_rate": 1.2434524942378283e-05, + "loss": 0.5058, + "step": 5248 + }, + { + "epoch": 0.44, + "learning_rate": 1.2431896481590912e-05, + "loss": 0.4728, + "step": 5249 + }, + { + "epoch": 0.44, + "learning_rate": 1.2429267842215181e-05, + "loss": 0.4873, + "step": 5250 + }, + { + "epoch": 0.44, + "learning_rate": 1.2426639024444118e-05, + "loss": 0.4701, + "step": 5251 + }, + { + "epoch": 0.44, + "learning_rate": 1.2424010028470779e-05, + "loss": 0.4963, + "step": 5252 + }, + { + "epoch": 0.44, + "learning_rate": 1.242138085448823e-05, + "loss": 0.501, + "step": 5253 + }, + { + "epoch": 0.44, + "learning_rate": 1.2418751502689537e-05, + "loss": 0.4718, + "step": 5254 + }, + { + "epoch": 0.44, + "learning_rate": 1.24161219732678e-05, + "loss": 0.5091, + "step": 5255 + }, + { + "epoch": 0.44, + "learning_rate": 1.241349226641611e-05, + "loss": 0.493, + "step": 5256 + }, + { + "epoch": 0.44, + "learning_rate": 1.2410862382327587e-05, + "loss": 0.4905, + "step": 5257 + }, + { + "epoch": 0.44, + "learning_rate": 1.240823232119536e-05, + "loss": 0.4691, + "step": 5258 + }, + { + "epoch": 0.44, + "learning_rate": 1.2405602083212567e-05, + "loss": 0.4941, + "step": 5259 + }, + { + "epoch": 0.44, + "learning_rate": 1.2402971668572364e-05, + "loss": 0.4871, + "step": 5260 + }, + { + "epoch": 0.44, + "learning_rate": 1.2400341077467912e-05, + "loss": 0.4755, + "step": 5261 + }, + { + "epoch": 0.44, + "learning_rate": 1.2397710310092396e-05, + "loss": 0.4886, + "step": 5262 + }, + { + "epoch": 0.44, + "learning_rate": 1.2395079366639011e-05, + "loss": 0.5008, + "step": 5263 + }, + { + "epoch": 0.44, + "learning_rate": 1.2392448247300959e-05, + "loss": 0.4723, + "step": 5264 + }, + { + "epoch": 0.44, + "learning_rate": 1.2389816952271456e-05, + "loss": 0.4819, + "step": 5265 + }, + { + "epoch": 0.44, + "learning_rate": 1.238718548174374e-05, + "loss": 0.4801, + "step": 5266 + }, + { + "epoch": 0.44, + "learning_rate": 1.2384553835911049e-05, + "loss": 0.5106, + "step": 5267 + }, + { + "epoch": 0.44, + "learning_rate": 1.2381922014966641e-05, + "loss": 0.5061, + "step": 5268 + }, + { + "epoch": 0.44, + "learning_rate": 1.237929001910379e-05, + "loss": 0.4961, + "step": 5269 + }, + { + "epoch": 0.44, + "learning_rate": 1.2376657848515774e-05, + "loss": 0.4996, + "step": 5270 + }, + { + "epoch": 0.44, + "learning_rate": 1.237402550339589e-05, + "loss": 0.4873, + "step": 5271 + }, + { + "epoch": 0.44, + "learning_rate": 1.2371392983937449e-05, + "loss": 0.4964, + "step": 5272 + }, + { + "epoch": 0.44, + "learning_rate": 1.2368760290333771e-05, + "loss": 0.493, + "step": 5273 + }, + { + "epoch": 0.44, + "learning_rate": 1.2366127422778192e-05, + "loss": 0.4932, + "step": 5274 + }, + { + "epoch": 0.44, + "learning_rate": 1.2363494381464052e-05, + "loss": 0.4952, + "step": 5275 + }, + { + "epoch": 0.44, + "learning_rate": 1.2360861166584717e-05, + "loss": 0.4878, + "step": 5276 + }, + { + "epoch": 0.44, + "learning_rate": 1.2358227778333556e-05, + "loss": 0.4842, + "step": 5277 + }, + { + "epoch": 0.44, + "learning_rate": 1.2355594216903956e-05, + "loss": 0.4739, + "step": 5278 + }, + { + "epoch": 0.44, + "learning_rate": 1.2352960482489317e-05, + "loss": 0.4898, + "step": 5279 + }, + { + "epoch": 0.44, + "learning_rate": 1.2350326575283047e-05, + "loss": 0.45, + "step": 5280 + }, + { + "epoch": 0.44, + "learning_rate": 1.2347692495478565e-05, + "loss": 0.4845, + "step": 5281 + }, + { + "epoch": 0.44, + "learning_rate": 1.2345058243269314e-05, + "loss": 0.4905, + "step": 5282 + }, + { + "epoch": 0.44, + "learning_rate": 1.234242381884874e-05, + "loss": 0.4936, + "step": 5283 + }, + { + "epoch": 0.44, + "learning_rate": 1.2339789222410301e-05, + "loss": 0.4803, + "step": 5284 + }, + { + "epoch": 0.44, + "learning_rate": 1.2337154454147476e-05, + "loss": 0.4985, + "step": 5285 + }, + { + "epoch": 0.44, + "learning_rate": 1.2334519514253747e-05, + "loss": 0.4824, + "step": 5286 + }, + { + "epoch": 0.44, + "learning_rate": 1.2331884402922613e-05, + "loss": 0.4794, + "step": 5287 + }, + { + "epoch": 0.44, + "learning_rate": 1.2329249120347591e-05, + "loss": 0.4644, + "step": 5288 + }, + { + "epoch": 0.44, + "learning_rate": 1.23266136667222e-05, + "loss": 0.4718, + "step": 5289 + }, + { + "epoch": 0.44, + "learning_rate": 1.2323978042239982e-05, + "loss": 0.4865, + "step": 5290 + }, + { + "epoch": 0.44, + "learning_rate": 1.232134224709448e-05, + "loss": 0.4865, + "step": 5291 + }, + { + "epoch": 0.44, + "learning_rate": 1.2318706281479256e-05, + "loss": 0.4886, + "step": 5292 + }, + { + "epoch": 0.44, + "learning_rate": 1.2316070145587888e-05, + "loss": 0.4689, + "step": 5293 + }, + { + "epoch": 0.44, + "learning_rate": 1.2313433839613964e-05, + "loss": 0.4984, + "step": 5294 + }, + { + "epoch": 0.44, + "learning_rate": 1.2310797363751078e-05, + "loss": 0.497, + "step": 5295 + }, + { + "epoch": 0.44, + "learning_rate": 1.230816071819285e-05, + "loss": 0.4869, + "step": 5296 + }, + { + "epoch": 0.44, + "learning_rate": 1.2305523903132897e-05, + "loss": 0.5057, + "step": 5297 + }, + { + "epoch": 0.44, + "learning_rate": 1.2302886918764856e-05, + "loss": 0.4959, + "step": 5298 + }, + { + "epoch": 0.44, + "learning_rate": 1.230024976528238e-05, + "loss": 0.4867, + "step": 5299 + }, + { + "epoch": 0.44, + "learning_rate": 1.2297612442879129e-05, + "loss": 0.4817, + "step": 5300 + }, + { + "epoch": 0.44, + "learning_rate": 1.2294974951748775e-05, + "loss": 0.4834, + "step": 5301 + }, + { + "epoch": 0.44, + "learning_rate": 1.2292337292085006e-05, + "loss": 0.4934, + "step": 5302 + }, + { + "epoch": 0.44, + "learning_rate": 1.2289699464081521e-05, + "loss": 0.4969, + "step": 5303 + }, + { + "epoch": 0.44, + "learning_rate": 1.2287061467932033e-05, + "loss": 0.4713, + "step": 5304 + }, + { + "epoch": 0.44, + "learning_rate": 1.228442330383026e-05, + "loss": 0.4615, + "step": 5305 + }, + { + "epoch": 0.44, + "learning_rate": 1.2281784971969944e-05, + "loss": 0.4634, + "step": 5306 + }, + { + "epoch": 0.44, + "learning_rate": 1.227914647254483e-05, + "loss": 0.4882, + "step": 5307 + }, + { + "epoch": 0.44, + "learning_rate": 1.2276507805748676e-05, + "loss": 0.4769, + "step": 5308 + }, + { + "epoch": 0.44, + "learning_rate": 1.227386897177526e-05, + "loss": 0.4874, + "step": 5309 + }, + { + "epoch": 0.44, + "learning_rate": 1.2271229970818366e-05, + "loss": 0.504, + "step": 5310 + }, + { + "epoch": 0.44, + "learning_rate": 1.2268590803071787e-05, + "loss": 0.4827, + "step": 5311 + }, + { + "epoch": 0.44, + "learning_rate": 1.2265951468729336e-05, + "loss": 0.4654, + "step": 5312 + }, + { + "epoch": 0.44, + "learning_rate": 1.2263311967984834e-05, + "loss": 0.5182, + "step": 5313 + }, + { + "epoch": 0.44, + "learning_rate": 1.2260672301032116e-05, + "loss": 0.4757, + "step": 5314 + }, + { + "epoch": 0.44, + "learning_rate": 1.2258032468065024e-05, + "loss": 0.4899, + "step": 5315 + }, + { + "epoch": 0.44, + "learning_rate": 1.2255392469277421e-05, + "loss": 0.4886, + "step": 5316 + }, + { + "epoch": 0.44, + "learning_rate": 1.2252752304863178e-05, + "loss": 0.4833, + "step": 5317 + }, + { + "epoch": 0.44, + "learning_rate": 1.2250111975016173e-05, + "loss": 0.4766, + "step": 5318 + }, + { + "epoch": 0.45, + "learning_rate": 1.2247471479930303e-05, + "loss": 0.4942, + "step": 5319 + }, + { + "epoch": 0.45, + "learning_rate": 1.2244830819799478e-05, + "loss": 0.4695, + "step": 5320 + }, + { + "epoch": 0.45, + "learning_rate": 1.2242189994817614e-05, + "loss": 0.4811, + "step": 5321 + }, + { + "epoch": 0.45, + "learning_rate": 1.2239549005178642e-05, + "loss": 0.4927, + "step": 5322 + }, + { + "epoch": 0.45, + "learning_rate": 1.2236907851076505e-05, + "loss": 0.4838, + "step": 5323 + }, + { + "epoch": 0.45, + "learning_rate": 1.2234266532705161e-05, + "loss": 0.4872, + "step": 5324 + }, + { + "epoch": 0.45, + "learning_rate": 1.2231625050258576e-05, + "loss": 0.492, + "step": 5325 + }, + { + "epoch": 0.45, + "learning_rate": 1.2228983403930727e-05, + "loss": 0.4847, + "step": 5326 + }, + { + "epoch": 0.45, + "learning_rate": 1.2226341593915612e-05, + "loss": 0.4641, + "step": 5327 + }, + { + "epoch": 0.45, + "learning_rate": 1.2223699620407227e-05, + "loss": 0.5174, + "step": 5328 + }, + { + "epoch": 0.45, + "learning_rate": 1.222105748359959e-05, + "loss": 0.4728, + "step": 5329 + }, + { + "epoch": 0.45, + "learning_rate": 1.2218415183686732e-05, + "loss": 0.4889, + "step": 5330 + }, + { + "epoch": 0.45, + "learning_rate": 1.2215772720862691e-05, + "loss": 0.5182, + "step": 5331 + }, + { + "epoch": 0.45, + "learning_rate": 1.2213130095321517e-05, + "loss": 0.4757, + "step": 5332 + }, + { + "epoch": 0.45, + "learning_rate": 1.221048730725727e-05, + "loss": 0.4729, + "step": 5333 + }, + { + "epoch": 0.45, + "learning_rate": 1.2207844356864031e-05, + "loss": 0.4839, + "step": 5334 + }, + { + "epoch": 0.45, + "learning_rate": 1.2205201244335889e-05, + "loss": 0.4946, + "step": 5335 + }, + { + "epoch": 0.45, + "learning_rate": 1.2202557969866934e-05, + "loss": 0.4686, + "step": 5336 + }, + { + "epoch": 0.45, + "learning_rate": 1.2199914533651289e-05, + "loss": 0.4722, + "step": 5337 + }, + { + "epoch": 0.45, + "learning_rate": 1.2197270935883068e-05, + "loss": 0.4708, + "step": 5338 + }, + { + "epoch": 0.45, + "learning_rate": 1.2194627176756408e-05, + "loss": 0.5, + "step": 5339 + }, + { + "epoch": 0.45, + "learning_rate": 1.2191983256465455e-05, + "loss": 0.463, + "step": 5340 + }, + { + "epoch": 0.45, + "learning_rate": 1.2189339175204373e-05, + "loss": 0.4606, + "step": 5341 + }, + { + "epoch": 0.45, + "learning_rate": 1.2186694933167326e-05, + "loss": 0.5079, + "step": 5342 + }, + { + "epoch": 0.45, + "learning_rate": 1.2184050530548496e-05, + "loss": 0.4716, + "step": 5343 + }, + { + "epoch": 0.45, + "learning_rate": 1.2181405967542082e-05, + "loss": 0.4788, + "step": 5344 + }, + { + "epoch": 0.45, + "learning_rate": 1.2178761244342286e-05, + "loss": 0.488, + "step": 5345 + }, + { + "epoch": 0.45, + "learning_rate": 1.2176116361143326e-05, + "loss": 0.4836, + "step": 5346 + }, + { + "epoch": 0.45, + "learning_rate": 1.2173471318139431e-05, + "loss": 0.4844, + "step": 5347 + }, + { + "epoch": 0.45, + "learning_rate": 1.2170826115524845e-05, + "loss": 0.4895, + "step": 5348 + }, + { + "epoch": 0.45, + "learning_rate": 1.2168180753493817e-05, + "loss": 0.4887, + "step": 5349 + }, + { + "epoch": 0.45, + "learning_rate": 1.2165535232240611e-05, + "loss": 0.4839, + "step": 5350 + }, + { + "epoch": 0.45, + "learning_rate": 1.2162889551959506e-05, + "loss": 0.4759, + "step": 5351 + }, + { + "epoch": 0.45, + "learning_rate": 1.216024371284479e-05, + "loss": 0.4753, + "step": 5352 + }, + { + "epoch": 0.45, + "learning_rate": 1.215759771509076e-05, + "loss": 0.4875, + "step": 5353 + }, + { + "epoch": 0.45, + "learning_rate": 1.2154951558891728e-05, + "loss": 0.4858, + "step": 5354 + }, + { + "epoch": 0.45, + "learning_rate": 1.2152305244442014e-05, + "loss": 0.4829, + "step": 5355 + }, + { + "epoch": 0.45, + "learning_rate": 1.2149658771935955e-05, + "loss": 0.4784, + "step": 5356 + }, + { + "epoch": 0.45, + "learning_rate": 1.21470121415679e-05, + "loss": 0.4715, + "step": 5357 + }, + { + "epoch": 0.45, + "learning_rate": 1.2144365353532204e-05, + "loss": 0.4761, + "step": 5358 + }, + { + "epoch": 0.45, + "learning_rate": 1.2141718408023233e-05, + "loss": 0.4941, + "step": 5359 + }, + { + "epoch": 0.45, + "learning_rate": 1.2139071305235368e-05, + "loss": 0.4754, + "step": 5360 + }, + { + "epoch": 0.45, + "learning_rate": 1.2136424045363007e-05, + "loss": 0.4846, + "step": 5361 + }, + { + "epoch": 0.45, + "learning_rate": 1.2133776628600552e-05, + "loss": 0.4779, + "step": 5362 + }, + { + "epoch": 0.45, + "learning_rate": 1.2131129055142411e-05, + "loss": 0.481, + "step": 5363 + }, + { + "epoch": 0.45, + "learning_rate": 1.2128481325183022e-05, + "loss": 0.4914, + "step": 5364 + }, + { + "epoch": 0.45, + "learning_rate": 1.2125833438916812e-05, + "loss": 0.4922, + "step": 5365 + }, + { + "epoch": 0.45, + "learning_rate": 1.2123185396538242e-05, + "loss": 0.4835, + "step": 5366 + }, + { + "epoch": 0.45, + "learning_rate": 1.2120537198241763e-05, + "loss": 0.4769, + "step": 5367 + }, + { + "epoch": 0.45, + "learning_rate": 1.2117888844221852e-05, + "loss": 0.4646, + "step": 5368 + }, + { + "epoch": 0.45, + "learning_rate": 1.2115240334672997e-05, + "loss": 0.4822, + "step": 5369 + }, + { + "epoch": 0.45, + "learning_rate": 1.2112591669789685e-05, + "loss": 0.4844, + "step": 5370 + }, + { + "epoch": 0.45, + "learning_rate": 1.2109942849766432e-05, + "loss": 0.4739, + "step": 5371 + }, + { + "epoch": 0.45, + "learning_rate": 1.210729387479775e-05, + "loss": 0.4888, + "step": 5372 + }, + { + "epoch": 0.45, + "learning_rate": 1.210464474507817e-05, + "loss": 0.496, + "step": 5373 + }, + { + "epoch": 0.45, + "learning_rate": 1.2101995460802235e-05, + "loss": 0.4643, + "step": 5374 + }, + { + "epoch": 0.45, + "learning_rate": 1.2099346022164496e-05, + "loss": 0.4959, + "step": 5375 + }, + { + "epoch": 0.45, + "learning_rate": 1.2096696429359518e-05, + "loss": 0.4997, + "step": 5376 + }, + { + "epoch": 0.45, + "learning_rate": 1.2094046682581872e-05, + "loss": 0.5001, + "step": 5377 + }, + { + "epoch": 0.45, + "learning_rate": 1.209139678202615e-05, + "loss": 0.4878, + "step": 5378 + }, + { + "epoch": 0.45, + "learning_rate": 1.2088746727886949e-05, + "loss": 0.4932, + "step": 5379 + }, + { + "epoch": 0.45, + "learning_rate": 1.2086096520358872e-05, + "loss": 0.4941, + "step": 5380 + }, + { + "epoch": 0.45, + "learning_rate": 1.2083446159636543e-05, + "loss": 0.4906, + "step": 5381 + }, + { + "epoch": 0.45, + "learning_rate": 1.2080795645914595e-05, + "loss": 0.4808, + "step": 5382 + }, + { + "epoch": 0.45, + "learning_rate": 1.2078144979387674e-05, + "loss": 0.5055, + "step": 5383 + }, + { + "epoch": 0.45, + "learning_rate": 1.2075494160250423e-05, + "loss": 0.4768, + "step": 5384 + }, + { + "epoch": 0.45, + "learning_rate": 1.2072843188697516e-05, + "loss": 0.4818, + "step": 5385 + }, + { + "epoch": 0.45, + "learning_rate": 1.2070192064923627e-05, + "loss": 0.4919, + "step": 5386 + }, + { + "epoch": 0.45, + "learning_rate": 1.2067540789123441e-05, + "loss": 0.4866, + "step": 5387 + }, + { + "epoch": 0.45, + "learning_rate": 1.2064889361491663e-05, + "loss": 0.4826, + "step": 5388 + }, + { + "epoch": 0.45, + "learning_rate": 1.2062237782222996e-05, + "loss": 0.4683, + "step": 5389 + }, + { + "epoch": 0.45, + "learning_rate": 1.2059586051512164e-05, + "loss": 0.4713, + "step": 5390 + }, + { + "epoch": 0.45, + "learning_rate": 1.20569341695539e-05, + "loss": 0.4872, + "step": 5391 + }, + { + "epoch": 0.45, + "learning_rate": 1.2054282136542946e-05, + "loss": 0.5091, + "step": 5392 + }, + { + "epoch": 0.45, + "learning_rate": 1.2051629952674055e-05, + "loss": 0.4817, + "step": 5393 + }, + { + "epoch": 0.45, + "learning_rate": 1.2048977618141995e-05, + "loss": 0.5097, + "step": 5394 + }, + { + "epoch": 0.45, + "learning_rate": 1.2046325133141542e-05, + "loss": 0.4779, + "step": 5395 + }, + { + "epoch": 0.45, + "learning_rate": 1.2043672497867479e-05, + "loss": 0.4591, + "step": 5396 + }, + { + "epoch": 0.45, + "learning_rate": 1.2041019712514607e-05, + "loss": 0.4957, + "step": 5397 + }, + { + "epoch": 0.45, + "learning_rate": 1.2038366777277743e-05, + "loss": 0.475, + "step": 5398 + }, + { + "epoch": 0.45, + "learning_rate": 1.2035713692351698e-05, + "loss": 0.483, + "step": 5399 + }, + { + "epoch": 0.45, + "learning_rate": 1.2033060457931308e-05, + "loss": 0.4841, + "step": 5400 + }, + { + "epoch": 0.45, + "learning_rate": 1.203040707421141e-05, + "loss": 0.4775, + "step": 5401 + }, + { + "epoch": 0.45, + "learning_rate": 1.2027753541386865e-05, + "loss": 0.466, + "step": 5402 + }, + { + "epoch": 0.45, + "learning_rate": 1.2025099859652532e-05, + "loss": 0.4859, + "step": 5403 + }, + { + "epoch": 0.45, + "learning_rate": 1.202244602920329e-05, + "loss": 0.4848, + "step": 5404 + }, + { + "epoch": 0.45, + "learning_rate": 1.2019792050234022e-05, + "loss": 0.4779, + "step": 5405 + }, + { + "epoch": 0.45, + "learning_rate": 1.2017137922939629e-05, + "loss": 0.4719, + "step": 5406 + }, + { + "epoch": 0.45, + "learning_rate": 1.2014483647515014e-05, + "loss": 0.4811, + "step": 5407 + }, + { + "epoch": 0.45, + "learning_rate": 1.2011829224155101e-05, + "loss": 0.4836, + "step": 5408 + }, + { + "epoch": 0.45, + "learning_rate": 1.2009174653054815e-05, + "loss": 0.4754, + "step": 5409 + }, + { + "epoch": 0.45, + "learning_rate": 1.2006519934409105e-05, + "loss": 0.4843, + "step": 5410 + }, + { + "epoch": 0.45, + "learning_rate": 1.200386506841291e-05, + "loss": 0.4793, + "step": 5411 + }, + { + "epoch": 0.45, + "learning_rate": 1.20012100552612e-05, + "loss": 0.4602, + "step": 5412 + }, + { + "epoch": 0.45, + "learning_rate": 1.1998554895148953e-05, + "loss": 0.4766, + "step": 5413 + }, + { + "epoch": 0.45, + "learning_rate": 1.199589958827114e-05, + "loss": 0.4675, + "step": 5414 + }, + { + "epoch": 0.45, + "learning_rate": 1.1993244134822767e-05, + "loss": 0.4753, + "step": 5415 + }, + { + "epoch": 0.45, + "learning_rate": 1.1990588534998834e-05, + "loss": 0.4726, + "step": 5416 + }, + { + "epoch": 0.45, + "learning_rate": 1.1987932788994362e-05, + "loss": 0.4837, + "step": 5417 + }, + { + "epoch": 0.45, + "learning_rate": 1.1985276897004367e-05, + "loss": 0.475, + "step": 5418 + }, + { + "epoch": 0.45, + "learning_rate": 1.1982620859223902e-05, + "loss": 0.4957, + "step": 5419 + }, + { + "epoch": 0.45, + "learning_rate": 1.1979964675848004e-05, + "loss": 0.5041, + "step": 5420 + }, + { + "epoch": 0.45, + "learning_rate": 1.1977308347071735e-05, + "loss": 0.4591, + "step": 5421 + }, + { + "epoch": 0.45, + "learning_rate": 1.1974651873090163e-05, + "loss": 0.4675, + "step": 5422 + }, + { + "epoch": 0.45, + "learning_rate": 1.1971995254098374e-05, + "loss": 0.4879, + "step": 5423 + }, + { + "epoch": 0.45, + "learning_rate": 1.1969338490291455e-05, + "loss": 0.464, + "step": 5424 + }, + { + "epoch": 0.45, + "learning_rate": 1.1966681581864507e-05, + "loss": 0.4879, + "step": 5425 + }, + { + "epoch": 0.45, + "learning_rate": 1.1964024529012648e-05, + "loss": 0.5053, + "step": 5426 + }, + { + "epoch": 0.45, + "learning_rate": 1.196136733193099e-05, + "loss": 0.5042, + "step": 5427 + }, + { + "epoch": 0.45, + "learning_rate": 1.1958709990814677e-05, + "loss": 0.4944, + "step": 5428 + }, + { + "epoch": 0.45, + "learning_rate": 1.1956052505858851e-05, + "loss": 0.4783, + "step": 5429 + }, + { + "epoch": 0.45, + "learning_rate": 1.1953394877258662e-05, + "loss": 0.5042, + "step": 5430 + }, + { + "epoch": 0.45, + "learning_rate": 1.1950737105209278e-05, + "loss": 0.4801, + "step": 5431 + }, + { + "epoch": 0.45, + "learning_rate": 1.1948079189905872e-05, + "loss": 0.502, + "step": 5432 + }, + { + "epoch": 0.45, + "learning_rate": 1.1945421131543639e-05, + "loss": 0.4985, + "step": 5433 + }, + { + "epoch": 0.45, + "learning_rate": 1.1942762930317768e-05, + "loss": 0.4746, + "step": 5434 + }, + { + "epoch": 0.45, + "learning_rate": 1.1940104586423465e-05, + "loss": 0.4948, + "step": 5435 + }, + { + "epoch": 0.45, + "learning_rate": 1.1937446100055954e-05, + "loss": 0.4836, + "step": 5436 + }, + { + "epoch": 0.45, + "learning_rate": 1.1934787471410457e-05, + "loss": 0.4663, + "step": 5437 + }, + { + "epoch": 0.45, + "learning_rate": 1.1932128700682216e-05, + "loss": 0.5137, + "step": 5438 + }, + { + "epoch": 0.46, + "learning_rate": 1.1929469788066481e-05, + "loss": 0.4803, + "step": 5439 + }, + { + "epoch": 0.46, + "learning_rate": 1.1926810733758511e-05, + "loss": 0.4849, + "step": 5440 + }, + { + "epoch": 0.46, + "learning_rate": 1.1924151537953574e-05, + "loss": 0.4916, + "step": 5441 + }, + { + "epoch": 0.46, + "learning_rate": 1.1921492200846949e-05, + "loss": 0.4784, + "step": 5442 + }, + { + "epoch": 0.46, + "learning_rate": 1.191883272263393e-05, + "loss": 0.4805, + "step": 5443 + }, + { + "epoch": 0.46, + "learning_rate": 1.1916173103509819e-05, + "loss": 0.4756, + "step": 5444 + }, + { + "epoch": 0.46, + "learning_rate": 1.191351334366992e-05, + "loss": 0.5125, + "step": 5445 + }, + { + "epoch": 0.46, + "learning_rate": 1.1910853443309566e-05, + "loss": 0.4804, + "step": 5446 + }, + { + "epoch": 0.46, + "learning_rate": 1.190819340262408e-05, + "loss": 0.4834, + "step": 5447 + }, + { + "epoch": 0.46, + "learning_rate": 1.1905533221808805e-05, + "loss": 0.4813, + "step": 5448 + }, + { + "epoch": 0.46, + "learning_rate": 1.1902872901059102e-05, + "loss": 0.501, + "step": 5449 + }, + { + "epoch": 0.46, + "learning_rate": 1.1900212440570324e-05, + "loss": 0.4523, + "step": 5450 + }, + { + "epoch": 0.46, + "learning_rate": 1.1897551840537848e-05, + "loss": 0.4583, + "step": 5451 + }, + { + "epoch": 0.46, + "learning_rate": 1.1894891101157058e-05, + "loss": 0.4717, + "step": 5452 + }, + { + "epoch": 0.46, + "learning_rate": 1.1892230222623345e-05, + "loss": 0.4813, + "step": 5453 + }, + { + "epoch": 0.46, + "learning_rate": 1.1889569205132119e-05, + "loss": 0.495, + "step": 5454 + }, + { + "epoch": 0.46, + "learning_rate": 1.1886908048878785e-05, + "loss": 0.4842, + "step": 5455 + }, + { + "epoch": 0.46, + "learning_rate": 1.1884246754058775e-05, + "loss": 0.4882, + "step": 5456 + }, + { + "epoch": 0.46, + "learning_rate": 1.1881585320867521e-05, + "loss": 0.4802, + "step": 5457 + }, + { + "epoch": 0.46, + "learning_rate": 1.1878923749500466e-05, + "loss": 0.4653, + "step": 5458 + }, + { + "epoch": 0.46, + "learning_rate": 1.1876262040153064e-05, + "loss": 0.4861, + "step": 5459 + }, + { + "epoch": 0.46, + "learning_rate": 1.1873600193020786e-05, + "loss": 0.4977, + "step": 5460 + }, + { + "epoch": 0.46, + "learning_rate": 1.18709382082991e-05, + "loss": 0.4697, + "step": 5461 + }, + { + "epoch": 0.46, + "learning_rate": 1.1868276086183494e-05, + "loss": 0.4973, + "step": 5462 + }, + { + "epoch": 0.46, + "learning_rate": 1.1865613826869463e-05, + "loss": 0.5125, + "step": 5463 + }, + { + "epoch": 0.46, + "learning_rate": 1.1862951430552514e-05, + "loss": 0.4998, + "step": 5464 + }, + { + "epoch": 0.46, + "learning_rate": 1.1860288897428158e-05, + "loss": 0.4609, + "step": 5465 + }, + { + "epoch": 0.46, + "learning_rate": 1.1857626227691924e-05, + "loss": 0.47, + "step": 5466 + }, + { + "epoch": 0.46, + "learning_rate": 1.1854963421539348e-05, + "loss": 0.4728, + "step": 5467 + }, + { + "epoch": 0.46, + "learning_rate": 1.185230047916597e-05, + "loss": 0.4885, + "step": 5468 + }, + { + "epoch": 0.46, + "learning_rate": 1.1849637400767351e-05, + "loss": 0.49, + "step": 5469 + }, + { + "epoch": 0.46, + "learning_rate": 1.1846974186539055e-05, + "loss": 0.5007, + "step": 5470 + }, + { + "epoch": 0.46, + "learning_rate": 1.1844310836676658e-05, + "loss": 0.4694, + "step": 5471 + }, + { + "epoch": 0.46, + "learning_rate": 1.184164735137574e-05, + "loss": 0.4736, + "step": 5472 + }, + { + "epoch": 0.46, + "learning_rate": 1.1838983730831904e-05, + "loss": 0.5052, + "step": 5473 + }, + { + "epoch": 0.46, + "learning_rate": 1.1836319975240751e-05, + "loss": 0.4826, + "step": 5474 + }, + { + "epoch": 0.46, + "learning_rate": 1.1833656084797898e-05, + "loss": 0.4675, + "step": 5475 + }, + { + "epoch": 0.46, + "learning_rate": 1.1830992059698967e-05, + "loss": 0.4842, + "step": 5476 + }, + { + "epoch": 0.46, + "learning_rate": 1.1828327900139596e-05, + "loss": 0.4937, + "step": 5477 + }, + { + "epoch": 0.46, + "learning_rate": 1.1825663606315425e-05, + "loss": 0.4691, + "step": 5478 + }, + { + "epoch": 0.46, + "learning_rate": 1.1822999178422114e-05, + "loss": 0.4715, + "step": 5479 + }, + { + "epoch": 0.46, + "learning_rate": 1.182033461665533e-05, + "loss": 0.4987, + "step": 5480 + }, + { + "epoch": 0.46, + "learning_rate": 1.181766992121074e-05, + "loss": 0.4855, + "step": 5481 + }, + { + "epoch": 0.46, + "learning_rate": 1.1815005092284033e-05, + "loss": 0.4915, + "step": 5482 + }, + { + "epoch": 0.46, + "learning_rate": 1.18123401300709e-05, + "loss": 0.469, + "step": 5483 + }, + { + "epoch": 0.46, + "learning_rate": 1.1809675034767043e-05, + "loss": 0.4964, + "step": 5484 + }, + { + "epoch": 0.46, + "learning_rate": 1.1807009806568181e-05, + "loss": 0.4829, + "step": 5485 + }, + { + "epoch": 0.46, + "learning_rate": 1.1804344445670034e-05, + "loss": 0.4707, + "step": 5486 + }, + { + "epoch": 0.46, + "learning_rate": 1.1801678952268338e-05, + "loss": 0.4788, + "step": 5487 + }, + { + "epoch": 0.46, + "learning_rate": 1.179901332655883e-05, + "loss": 0.4759, + "step": 5488 + }, + { + "epoch": 0.46, + "learning_rate": 1.1796347568737268e-05, + "loss": 0.4847, + "step": 5489 + }, + { + "epoch": 0.46, + "learning_rate": 1.1793681678999412e-05, + "loss": 0.4786, + "step": 5490 + }, + { + "epoch": 0.46, + "learning_rate": 1.1791015657541037e-05, + "loss": 0.4953, + "step": 5491 + }, + { + "epoch": 0.46, + "learning_rate": 1.1788349504557917e-05, + "loss": 0.4832, + "step": 5492 + }, + { + "epoch": 0.46, + "learning_rate": 1.1785683220245849e-05, + "loss": 0.4776, + "step": 5493 + }, + { + "epoch": 0.46, + "learning_rate": 1.1783016804800631e-05, + "loss": 0.4789, + "step": 5494 + }, + { + "epoch": 0.46, + "learning_rate": 1.1780350258418078e-05, + "loss": 0.4819, + "step": 5495 + }, + { + "epoch": 0.46, + "learning_rate": 1.1777683581294003e-05, + "loss": 0.4795, + "step": 5496 + }, + { + "epoch": 0.46, + "learning_rate": 1.1775016773624246e-05, + "loss": 0.4736, + "step": 5497 + }, + { + "epoch": 0.46, + "learning_rate": 1.1772349835604638e-05, + "loss": 0.5113, + "step": 5498 + }, + { + "epoch": 0.46, + "learning_rate": 1.1769682767431026e-05, + "loss": 0.4702, + "step": 5499 + }, + { + "epoch": 0.46, + "learning_rate": 1.1767015569299274e-05, + "loss": 0.4802, + "step": 5500 + }, + { + "epoch": 0.46, + "learning_rate": 1.1764348241405249e-05, + "loss": 0.4804, + "step": 5501 + }, + { + "epoch": 0.46, + "learning_rate": 1.1761680783944829e-05, + "loss": 0.4852, + "step": 5502 + }, + { + "epoch": 0.46, + "learning_rate": 1.1759013197113895e-05, + "loss": 0.4836, + "step": 5503 + }, + { + "epoch": 0.46, + "learning_rate": 1.175634548110835e-05, + "loss": 0.4939, + "step": 5504 + }, + { + "epoch": 0.46, + "learning_rate": 1.1753677636124101e-05, + "loss": 0.5088, + "step": 5505 + }, + { + "epoch": 0.46, + "learning_rate": 1.1751009662357059e-05, + "loss": 0.471, + "step": 5506 + }, + { + "epoch": 0.46, + "learning_rate": 1.1748341560003149e-05, + "loss": 0.489, + "step": 5507 + }, + { + "epoch": 0.46, + "learning_rate": 1.174567332925831e-05, + "loss": 0.4822, + "step": 5508 + }, + { + "epoch": 0.46, + "learning_rate": 1.174300497031848e-05, + "loss": 0.4794, + "step": 5509 + }, + { + "epoch": 0.46, + "learning_rate": 1.1740336483379613e-05, + "loss": 0.4821, + "step": 5510 + }, + { + "epoch": 0.46, + "learning_rate": 1.1737667868637674e-05, + "loss": 0.4755, + "step": 5511 + }, + { + "epoch": 0.46, + "learning_rate": 1.1734999126288637e-05, + "loss": 0.4849, + "step": 5512 + }, + { + "epoch": 0.46, + "learning_rate": 1.1732330256528477e-05, + "loss": 0.4922, + "step": 5513 + }, + { + "epoch": 0.46, + "learning_rate": 1.1729661259553193e-05, + "loss": 0.4849, + "step": 5514 + }, + { + "epoch": 0.46, + "learning_rate": 1.1726992135558776e-05, + "loss": 0.4955, + "step": 5515 + }, + { + "epoch": 0.46, + "learning_rate": 1.1724322884741242e-05, + "loss": 0.4834, + "step": 5516 + }, + { + "epoch": 0.46, + "learning_rate": 1.1721653507296604e-05, + "loss": 0.5012, + "step": 5517 + }, + { + "epoch": 0.46, + "learning_rate": 1.1718984003420899e-05, + "loss": 0.4802, + "step": 5518 + }, + { + "epoch": 0.46, + "learning_rate": 1.1716314373310154e-05, + "loss": 0.4789, + "step": 5519 + }, + { + "epoch": 0.46, + "learning_rate": 1.171364461716042e-05, + "loss": 0.4883, + "step": 5520 + }, + { + "epoch": 0.46, + "learning_rate": 1.1710974735167755e-05, + "loss": 0.4702, + "step": 5521 + }, + { + "epoch": 0.46, + "learning_rate": 1.1708304727528223e-05, + "loss": 0.4768, + "step": 5522 + }, + { + "epoch": 0.46, + "learning_rate": 1.1705634594437893e-05, + "loss": 0.4884, + "step": 5523 + }, + { + "epoch": 0.46, + "learning_rate": 1.1702964336092857e-05, + "loss": 0.4935, + "step": 5524 + }, + { + "epoch": 0.46, + "learning_rate": 1.17002939526892e-05, + "loss": 0.4804, + "step": 5525 + }, + { + "epoch": 0.46, + "learning_rate": 1.169762344442303e-05, + "loss": 0.4896, + "step": 5526 + }, + { + "epoch": 0.46, + "learning_rate": 1.1694952811490451e-05, + "loss": 0.4846, + "step": 5527 + }, + { + "epoch": 0.46, + "learning_rate": 1.1692282054087594e-05, + "loss": 0.4812, + "step": 5528 + }, + { + "epoch": 0.46, + "learning_rate": 1.1689611172410577e-05, + "loss": 0.5226, + "step": 5529 + }, + { + "epoch": 0.46, + "learning_rate": 1.1686940166655543e-05, + "loss": 0.4731, + "step": 5530 + }, + { + "epoch": 0.46, + "learning_rate": 1.1684269037018641e-05, + "loss": 0.475, + "step": 5531 + }, + { + "epoch": 0.46, + "learning_rate": 1.1681597783696027e-05, + "loss": 0.5193, + "step": 5532 + }, + { + "epoch": 0.46, + "learning_rate": 1.1678926406883866e-05, + "loss": 0.4724, + "step": 5533 + }, + { + "epoch": 0.46, + "learning_rate": 1.1676254906778331e-05, + "loss": 0.4698, + "step": 5534 + }, + { + "epoch": 0.46, + "learning_rate": 1.1673583283575607e-05, + "loss": 0.4757, + "step": 5535 + }, + { + "epoch": 0.46, + "learning_rate": 1.1670911537471889e-05, + "loss": 0.48, + "step": 5536 + }, + { + "epoch": 0.46, + "learning_rate": 1.1668239668663377e-05, + "loss": 0.4737, + "step": 5537 + }, + { + "epoch": 0.46, + "learning_rate": 1.1665567677346285e-05, + "loss": 0.4547, + "step": 5538 + }, + { + "epoch": 0.46, + "learning_rate": 1.166289556371683e-05, + "loss": 0.4934, + "step": 5539 + }, + { + "epoch": 0.46, + "learning_rate": 1.1660223327971239e-05, + "loss": 0.4754, + "step": 5540 + }, + { + "epoch": 0.46, + "learning_rate": 1.1657550970305752e-05, + "loss": 0.473, + "step": 5541 + }, + { + "epoch": 0.46, + "learning_rate": 1.1654878490916617e-05, + "loss": 0.4748, + "step": 5542 + }, + { + "epoch": 0.46, + "learning_rate": 1.165220589000009e-05, + "loss": 0.486, + "step": 5543 + }, + { + "epoch": 0.46, + "learning_rate": 1.1649533167752434e-05, + "loss": 0.4595, + "step": 5544 + }, + { + "epoch": 0.46, + "learning_rate": 1.164686032436992e-05, + "loss": 0.4842, + "step": 5545 + }, + { + "epoch": 0.46, + "learning_rate": 1.1644187360048838e-05, + "loss": 0.4897, + "step": 5546 + }, + { + "epoch": 0.46, + "learning_rate": 1.164151427498547e-05, + "loss": 0.4752, + "step": 5547 + }, + { + "epoch": 0.46, + "learning_rate": 1.1638841069376125e-05, + "loss": 0.4937, + "step": 5548 + }, + { + "epoch": 0.46, + "learning_rate": 1.1636167743417111e-05, + "loss": 0.4841, + "step": 5549 + }, + { + "epoch": 0.46, + "learning_rate": 1.1633494297304738e-05, + "loss": 0.4826, + "step": 5550 + }, + { + "epoch": 0.46, + "learning_rate": 1.163082073123534e-05, + "loss": 0.4777, + "step": 5551 + }, + { + "epoch": 0.46, + "learning_rate": 1.1628147045405248e-05, + "loss": 0.4806, + "step": 5552 + }, + { + "epoch": 0.46, + "learning_rate": 1.1625473240010814e-05, + "loss": 0.4643, + "step": 5553 + }, + { + "epoch": 0.46, + "learning_rate": 1.1622799315248382e-05, + "loss": 0.5037, + "step": 5554 + }, + { + "epoch": 0.46, + "learning_rate": 1.1620125271314322e-05, + "loss": 0.4654, + "step": 5555 + }, + { + "epoch": 0.46, + "learning_rate": 1.1617451108404996e-05, + "loss": 0.4785, + "step": 5556 + }, + { + "epoch": 0.46, + "learning_rate": 1.1614776826716791e-05, + "loss": 0.4712, + "step": 5557 + }, + { + "epoch": 0.47, + "learning_rate": 1.161210242644609e-05, + "loss": 0.4797, + "step": 5558 + }, + { + "epoch": 0.47, + "learning_rate": 1.1609427907789294e-05, + "loss": 0.4672, + "step": 5559 + }, + { + "epoch": 0.47, + "learning_rate": 1.160675327094281e-05, + "loss": 0.5135, + "step": 5560 + }, + { + "epoch": 0.47, + "learning_rate": 1.160407851610304e-05, + "loss": 0.5052, + "step": 5561 + }, + { + "epoch": 0.47, + "learning_rate": 1.1601403643466422e-05, + "loss": 0.4833, + "step": 5562 + }, + { + "epoch": 0.47, + "learning_rate": 1.159872865322938e-05, + "loss": 0.5247, + "step": 5563 + }, + { + "epoch": 0.47, + "learning_rate": 1.1596053545588355e-05, + "loss": 0.5032, + "step": 5564 + }, + { + "epoch": 0.47, + "learning_rate": 1.1593378320739796e-05, + "loss": 0.4918, + "step": 5565 + }, + { + "epoch": 0.47, + "learning_rate": 1.1590702978880159e-05, + "loss": 0.4745, + "step": 5566 + }, + { + "epoch": 0.47, + "learning_rate": 1.1588027520205915e-05, + "loss": 0.4933, + "step": 5567 + }, + { + "epoch": 0.47, + "learning_rate": 1.1585351944913532e-05, + "loss": 0.4832, + "step": 5568 + }, + { + "epoch": 0.47, + "learning_rate": 1.1582676253199498e-05, + "loss": 0.4923, + "step": 5569 + }, + { + "epoch": 0.47, + "learning_rate": 1.1580000445260305e-05, + "loss": 0.4878, + "step": 5570 + }, + { + "epoch": 0.47, + "learning_rate": 1.1577324521292445e-05, + "loss": 0.4873, + "step": 5571 + }, + { + "epoch": 0.47, + "learning_rate": 1.1574648481492434e-05, + "loss": 0.4808, + "step": 5572 + }, + { + "epoch": 0.47, + "learning_rate": 1.1571972326056794e-05, + "loss": 0.4868, + "step": 5573 + }, + { + "epoch": 0.47, + "learning_rate": 1.156929605518204e-05, + "loss": 0.49, + "step": 5574 + }, + { + "epoch": 0.47, + "learning_rate": 1.1566619669064709e-05, + "loss": 0.468, + "step": 5575 + }, + { + "epoch": 0.47, + "learning_rate": 1.1563943167901348e-05, + "loss": 0.4702, + "step": 5576 + }, + { + "epoch": 0.47, + "learning_rate": 1.1561266551888505e-05, + "loss": 0.4777, + "step": 5577 + }, + { + "epoch": 0.47, + "learning_rate": 1.1558589821222742e-05, + "loss": 0.4819, + "step": 5578 + }, + { + "epoch": 0.47, + "learning_rate": 1.1555912976100623e-05, + "loss": 0.4927, + "step": 5579 + }, + { + "epoch": 0.47, + "learning_rate": 1.155323601671873e-05, + "loss": 0.4894, + "step": 5580 + }, + { + "epoch": 0.47, + "learning_rate": 1.155055894327364e-05, + "loss": 0.4895, + "step": 5581 + }, + { + "epoch": 0.47, + "learning_rate": 1.1547881755961952e-05, + "loss": 0.4753, + "step": 5582 + }, + { + "epoch": 0.47, + "learning_rate": 1.1545204454980268e-05, + "loss": 0.483, + "step": 5583 + }, + { + "epoch": 0.47, + "learning_rate": 1.1542527040525192e-05, + "loss": 0.4889, + "step": 5584 + }, + { + "epoch": 0.47, + "learning_rate": 1.1539849512793348e-05, + "loss": 0.4702, + "step": 5585 + }, + { + "epoch": 0.47, + "learning_rate": 1.1537171871981363e-05, + "loss": 0.4892, + "step": 5586 + }, + { + "epoch": 0.47, + "learning_rate": 1.1534494118285865e-05, + "loss": 0.4854, + "step": 5587 + }, + { + "epoch": 0.47, + "learning_rate": 1.1531816251903503e-05, + "loss": 0.4915, + "step": 5588 + }, + { + "epoch": 0.47, + "learning_rate": 1.1529138273030927e-05, + "loss": 0.4627, + "step": 5589 + }, + { + "epoch": 0.47, + "learning_rate": 1.1526460181864799e-05, + "loss": 0.4904, + "step": 5590 + }, + { + "epoch": 0.47, + "learning_rate": 1.152378197860178e-05, + "loss": 0.5022, + "step": 5591 + }, + { + "epoch": 0.47, + "learning_rate": 1.1521103663438551e-05, + "loss": 0.4974, + "step": 5592 + }, + { + "epoch": 0.47, + "learning_rate": 1.1518425236571797e-05, + "loss": 0.48, + "step": 5593 + }, + { + "epoch": 0.47, + "learning_rate": 1.1515746698198211e-05, + "loss": 0.4676, + "step": 5594 + }, + { + "epoch": 0.47, + "learning_rate": 1.1513068048514489e-05, + "loss": 0.4756, + "step": 5595 + }, + { + "epoch": 0.47, + "learning_rate": 1.1510389287717345e-05, + "loss": 0.4957, + "step": 5596 + }, + { + "epoch": 0.47, + "learning_rate": 1.150771041600349e-05, + "loss": 0.4611, + "step": 5597 + }, + { + "epoch": 0.47, + "learning_rate": 1.1505031433569658e-05, + "loss": 0.4657, + "step": 5598 + }, + { + "epoch": 0.47, + "learning_rate": 1.1502352340612576e-05, + "loss": 0.4936, + "step": 5599 + }, + { + "epoch": 0.47, + "learning_rate": 1.1499673137328986e-05, + "loss": 0.4698, + "step": 5600 + }, + { + "epoch": 0.47, + "learning_rate": 1.1496993823915639e-05, + "loss": 0.4816, + "step": 5601 + }, + { + "epoch": 0.47, + "learning_rate": 1.1494314400569288e-05, + "loss": 0.4927, + "step": 5602 + }, + { + "epoch": 0.47, + "learning_rate": 1.1491634867486707e-05, + "loss": 0.4541, + "step": 5603 + }, + { + "epoch": 0.47, + "learning_rate": 1.1488955224864667e-05, + "loss": 0.48, + "step": 5604 + }, + { + "epoch": 0.47, + "learning_rate": 1.1486275472899943e-05, + "loss": 0.4936, + "step": 5605 + }, + { + "epoch": 0.47, + "learning_rate": 1.1483595611789336e-05, + "loss": 0.4853, + "step": 5606 + }, + { + "epoch": 0.47, + "learning_rate": 1.1480915641729633e-05, + "loss": 0.4817, + "step": 5607 + }, + { + "epoch": 0.47, + "learning_rate": 1.147823556291765e-05, + "loss": 0.4931, + "step": 5608 + }, + { + "epoch": 0.47, + "learning_rate": 1.1475555375550191e-05, + "loss": 0.4849, + "step": 5609 + }, + { + "epoch": 0.47, + "learning_rate": 1.1472875079824087e-05, + "loss": 0.4649, + "step": 5610 + }, + { + "epoch": 0.47, + "learning_rate": 1.1470194675936159e-05, + "loss": 0.4762, + "step": 5611 + }, + { + "epoch": 0.47, + "learning_rate": 1.1467514164083252e-05, + "loss": 0.4908, + "step": 5612 + }, + { + "epoch": 0.47, + "learning_rate": 1.1464833544462203e-05, + "loss": 0.4826, + "step": 5613 + }, + { + "epoch": 0.47, + "learning_rate": 1.1462152817269879e-05, + "loss": 0.4964, + "step": 5614 + }, + { + "epoch": 0.47, + "learning_rate": 1.145947198270313e-05, + "loss": 0.4881, + "step": 5615 + }, + { + "epoch": 0.47, + "learning_rate": 1.1456791040958828e-05, + "loss": 0.4719, + "step": 5616 + }, + { + "epoch": 0.47, + "learning_rate": 1.1454109992233851e-05, + "loss": 0.4977, + "step": 5617 + }, + { + "epoch": 0.47, + "learning_rate": 1.1451428836725087e-05, + "loss": 0.4921, + "step": 5618 + }, + { + "epoch": 0.47, + "learning_rate": 1.1448747574629424e-05, + "loss": 0.476, + "step": 5619 + }, + { + "epoch": 0.47, + "learning_rate": 1.1446066206143766e-05, + "loss": 0.4831, + "step": 5620 + }, + { + "epoch": 0.47, + "learning_rate": 1.1443384731465021e-05, + "loss": 0.4824, + "step": 5621 + }, + { + "epoch": 0.47, + "learning_rate": 1.1440703150790102e-05, + "loss": 0.4794, + "step": 5622 + }, + { + "epoch": 0.47, + "learning_rate": 1.1438021464315939e-05, + "loss": 0.4919, + "step": 5623 + }, + { + "epoch": 0.47, + "learning_rate": 1.143533967223946e-05, + "loss": 0.4893, + "step": 5624 + }, + { + "epoch": 0.47, + "learning_rate": 1.1432657774757607e-05, + "loss": 0.4674, + "step": 5625 + }, + { + "epoch": 0.47, + "learning_rate": 1.1429975772067322e-05, + "loss": 0.4806, + "step": 5626 + }, + { + "epoch": 0.47, + "learning_rate": 1.1427293664365568e-05, + "loss": 0.5062, + "step": 5627 + }, + { + "epoch": 0.47, + "learning_rate": 1.1424611451849301e-05, + "loss": 0.4882, + "step": 5628 + }, + { + "epoch": 0.47, + "learning_rate": 1.1421929134715492e-05, + "loss": 0.4883, + "step": 5629 + }, + { + "epoch": 0.47, + "learning_rate": 1.1419246713161128e-05, + "loss": 0.4493, + "step": 5630 + }, + { + "epoch": 0.47, + "learning_rate": 1.1416564187383185e-05, + "loss": 0.4925, + "step": 5631 + }, + { + "epoch": 0.47, + "learning_rate": 1.1413881557578662e-05, + "loss": 0.4814, + "step": 5632 + }, + { + "epoch": 0.47, + "learning_rate": 1.1411198823944553e-05, + "loss": 0.4868, + "step": 5633 + }, + { + "epoch": 0.47, + "learning_rate": 1.1408515986677877e-05, + "loss": 0.4744, + "step": 5634 + }, + { + "epoch": 0.47, + "learning_rate": 1.1405833045975644e-05, + "loss": 0.4786, + "step": 5635 + }, + { + "epoch": 0.47, + "learning_rate": 1.140315000203488e-05, + "loss": 0.4724, + "step": 5636 + }, + { + "epoch": 0.47, + "learning_rate": 1.1400466855052617e-05, + "loss": 0.4885, + "step": 5637 + }, + { + "epoch": 0.47, + "learning_rate": 1.139778360522589e-05, + "loss": 0.4876, + "step": 5638 + }, + { + "epoch": 0.47, + "learning_rate": 1.139510025275175e-05, + "loss": 0.4921, + "step": 5639 + }, + { + "epoch": 0.47, + "learning_rate": 1.139241679782725e-05, + "loss": 0.5004, + "step": 5640 + }, + { + "epoch": 0.47, + "learning_rate": 1.1389733240649454e-05, + "loss": 0.4859, + "step": 5641 + }, + { + "epoch": 0.47, + "learning_rate": 1.1387049581415428e-05, + "loss": 0.4938, + "step": 5642 + }, + { + "epoch": 0.47, + "learning_rate": 1.138436582032225e-05, + "loss": 0.4681, + "step": 5643 + }, + { + "epoch": 0.47, + "learning_rate": 1.1381681957567e-05, + "loss": 0.4845, + "step": 5644 + }, + { + "epoch": 0.47, + "learning_rate": 1.1378997993346782e-05, + "loss": 0.4733, + "step": 5645 + }, + { + "epoch": 0.47, + "learning_rate": 1.137631392785868e-05, + "loss": 0.4937, + "step": 5646 + }, + { + "epoch": 0.47, + "learning_rate": 1.1373629761299811e-05, + "loss": 0.4775, + "step": 5647 + }, + { + "epoch": 0.47, + "learning_rate": 1.1370945493867284e-05, + "loss": 0.471, + "step": 5648 + }, + { + "epoch": 0.47, + "learning_rate": 1.1368261125758224e-05, + "loss": 0.4901, + "step": 5649 + }, + { + "epoch": 0.47, + "learning_rate": 1.1365576657169754e-05, + "loss": 0.4707, + "step": 5650 + }, + { + "epoch": 0.47, + "learning_rate": 1.136289208829902e-05, + "loss": 0.4803, + "step": 5651 + }, + { + "epoch": 0.47, + "learning_rate": 1.1360207419343157e-05, + "loss": 0.4749, + "step": 5652 + }, + { + "epoch": 0.47, + "learning_rate": 1.1357522650499317e-05, + "loss": 0.4835, + "step": 5653 + }, + { + "epoch": 0.47, + "learning_rate": 1.135483778196466e-05, + "loss": 0.4921, + "step": 5654 + }, + { + "epoch": 0.47, + "learning_rate": 1.1352152813936354e-05, + "loss": 0.4825, + "step": 5655 + }, + { + "epoch": 0.47, + "learning_rate": 1.1349467746611569e-05, + "loss": 0.4778, + "step": 5656 + }, + { + "epoch": 0.47, + "learning_rate": 1.1346782580187486e-05, + "loss": 0.4877, + "step": 5657 + }, + { + "epoch": 0.47, + "learning_rate": 1.1344097314861292e-05, + "loss": 0.5045, + "step": 5658 + }, + { + "epoch": 0.47, + "learning_rate": 1.1341411950830179e-05, + "loss": 0.4885, + "step": 5659 + }, + { + "epoch": 0.47, + "learning_rate": 1.1338726488291351e-05, + "loss": 0.4939, + "step": 5660 + }, + { + "epoch": 0.47, + "learning_rate": 1.1336040927442023e-05, + "loss": 0.4826, + "step": 5661 + }, + { + "epoch": 0.47, + "learning_rate": 1.1333355268479403e-05, + "loss": 0.4694, + "step": 5662 + }, + { + "epoch": 0.47, + "learning_rate": 1.1330669511600716e-05, + "loss": 0.467, + "step": 5663 + }, + { + "epoch": 0.47, + "learning_rate": 1.1327983657003197e-05, + "loss": 0.5067, + "step": 5664 + }, + { + "epoch": 0.47, + "learning_rate": 1.1325297704884081e-05, + "loss": 0.4779, + "step": 5665 + }, + { + "epoch": 0.47, + "learning_rate": 1.132261165544062e-05, + "loss": 0.4802, + "step": 5666 + }, + { + "epoch": 0.47, + "learning_rate": 1.131992550887005e-05, + "loss": 0.4811, + "step": 5667 + }, + { + "epoch": 0.47, + "learning_rate": 1.1317239265369648e-05, + "loss": 0.5074, + "step": 5668 + }, + { + "epoch": 0.47, + "learning_rate": 1.131455292513667e-05, + "loss": 0.4494, + "step": 5669 + }, + { + "epoch": 0.47, + "learning_rate": 1.1311866488368392e-05, + "loss": 0.4755, + "step": 5670 + }, + { + "epoch": 0.47, + "learning_rate": 1.1309179955262097e-05, + "loss": 0.5055, + "step": 5671 + }, + { + "epoch": 0.47, + "learning_rate": 1.1306493326015074e-05, + "loss": 0.4714, + "step": 5672 + }, + { + "epoch": 0.47, + "learning_rate": 1.1303806600824613e-05, + "loss": 0.4855, + "step": 5673 + }, + { + "epoch": 0.47, + "learning_rate": 1.1301119779888015e-05, + "loss": 0.4815, + "step": 5674 + }, + { + "epoch": 0.47, + "learning_rate": 1.1298432863402595e-05, + "loss": 0.4807, + "step": 5675 + }, + { + "epoch": 0.47, + "learning_rate": 1.1295745851565667e-05, + "loss": 0.4727, + "step": 5676 + }, + { + "epoch": 0.47, + "learning_rate": 1.1293058744574552e-05, + "loss": 0.4793, + "step": 5677 + }, + { + "epoch": 0.48, + "learning_rate": 1.129037154262658e-05, + "loss": 0.4741, + "step": 5678 + }, + { + "epoch": 0.48, + "learning_rate": 1.128768424591909e-05, + "loss": 0.4584, + "step": 5679 + }, + { + "epoch": 0.48, + "learning_rate": 1.1284996854649424e-05, + "loss": 0.4911, + "step": 5680 + }, + { + "epoch": 0.48, + "learning_rate": 1.1282309369014937e-05, + "loss": 0.4811, + "step": 5681 + }, + { + "epoch": 0.48, + "learning_rate": 1.127962178921298e-05, + "loss": 0.4769, + "step": 5682 + }, + { + "epoch": 0.48, + "learning_rate": 1.1276934115440924e-05, + "loss": 0.4743, + "step": 5683 + }, + { + "epoch": 0.48, + "learning_rate": 1.1274246347896136e-05, + "loss": 0.48, + "step": 5684 + }, + { + "epoch": 0.48, + "learning_rate": 1.1271558486775995e-05, + "loss": 0.4874, + "step": 5685 + }, + { + "epoch": 0.48, + "learning_rate": 1.1268870532277889e-05, + "loss": 0.463, + "step": 5686 + }, + { + "epoch": 0.48, + "learning_rate": 1.1266182484599209e-05, + "loss": 0.4752, + "step": 5687 + }, + { + "epoch": 0.48, + "learning_rate": 1.1263494343937354e-05, + "loss": 0.4682, + "step": 5688 + }, + { + "epoch": 0.48, + "learning_rate": 1.1260806110489726e-05, + "loss": 0.4947, + "step": 5689 + }, + { + "epoch": 0.48, + "learning_rate": 1.1258117784453746e-05, + "loss": 0.4735, + "step": 5690 + }, + { + "epoch": 0.48, + "learning_rate": 1.1255429366026826e-05, + "loss": 0.4578, + "step": 5691 + }, + { + "epoch": 0.48, + "learning_rate": 1.1252740855406397e-05, + "loss": 0.4827, + "step": 5692 + }, + { + "epoch": 0.48, + "learning_rate": 1.1250052252789891e-05, + "loss": 0.4848, + "step": 5693 + }, + { + "epoch": 0.48, + "learning_rate": 1.1247363558374745e-05, + "loss": 0.4687, + "step": 5694 + }, + { + "epoch": 0.48, + "learning_rate": 1.1244674772358406e-05, + "loss": 0.473, + "step": 5695 + }, + { + "epoch": 0.48, + "learning_rate": 1.124198589493833e-05, + "loss": 0.4834, + "step": 5696 + }, + { + "epoch": 0.48, + "learning_rate": 1.1239296926311975e-05, + "loss": 0.4675, + "step": 5697 + }, + { + "epoch": 0.48, + "learning_rate": 1.123660786667681e-05, + "loss": 0.4829, + "step": 5698 + }, + { + "epoch": 0.48, + "learning_rate": 1.1233918716230308e-05, + "loss": 0.4824, + "step": 5699 + }, + { + "epoch": 0.48, + "learning_rate": 1.1231229475169945e-05, + "loss": 0.4713, + "step": 5700 + }, + { + "epoch": 0.48, + "learning_rate": 1.1228540143693209e-05, + "loss": 0.4831, + "step": 5701 + }, + { + "epoch": 0.48, + "learning_rate": 1.12258507219976e-05, + "loss": 0.4796, + "step": 5702 + }, + { + "epoch": 0.48, + "learning_rate": 1.122316121028061e-05, + "loss": 0.4962, + "step": 5703 + }, + { + "epoch": 0.48, + "learning_rate": 1.1220471608739748e-05, + "loss": 0.4918, + "step": 5704 + }, + { + "epoch": 0.48, + "learning_rate": 1.1217781917572524e-05, + "loss": 0.4789, + "step": 5705 + }, + { + "epoch": 0.48, + "learning_rate": 1.1215092136976466e-05, + "loss": 0.5123, + "step": 5706 + }, + { + "epoch": 0.48, + "learning_rate": 1.1212402267149094e-05, + "loss": 0.478, + "step": 5707 + }, + { + "epoch": 0.48, + "learning_rate": 1.1209712308287941e-05, + "loss": 0.4826, + "step": 5708 + }, + { + "epoch": 0.48, + "learning_rate": 1.120702226059055e-05, + "loss": 0.4965, + "step": 5709 + }, + { + "epoch": 0.48, + "learning_rate": 1.1204332124254463e-05, + "loss": 0.469, + "step": 5710 + }, + { + "epoch": 0.48, + "learning_rate": 1.1201641899477231e-05, + "loss": 0.4617, + "step": 5711 + }, + { + "epoch": 0.48, + "learning_rate": 1.119895158645642e-05, + "loss": 0.4843, + "step": 5712 + }, + { + "epoch": 0.48, + "learning_rate": 1.1196261185389593e-05, + "loss": 0.4833, + "step": 5713 + }, + { + "epoch": 0.48, + "learning_rate": 1.1193570696474317e-05, + "loss": 0.4829, + "step": 5714 + }, + { + "epoch": 0.48, + "learning_rate": 1.1190880119908175e-05, + "loss": 0.4845, + "step": 5715 + }, + { + "epoch": 0.48, + "learning_rate": 1.1188189455888747e-05, + "loss": 0.4692, + "step": 5716 + }, + { + "epoch": 0.48, + "learning_rate": 1.1185498704613632e-05, + "loss": 0.4786, + "step": 5717 + }, + { + "epoch": 0.48, + "learning_rate": 1.1182807866280419e-05, + "loss": 0.4714, + "step": 5718 + }, + { + "epoch": 0.48, + "learning_rate": 1.1180116941086719e-05, + "loss": 0.4922, + "step": 5719 + }, + { + "epoch": 0.48, + "learning_rate": 1.1177425929230137e-05, + "loss": 0.4893, + "step": 5720 + }, + { + "epoch": 0.48, + "learning_rate": 1.117473483090829e-05, + "loss": 0.476, + "step": 5721 + }, + { + "epoch": 0.48, + "learning_rate": 1.1172043646318809e-05, + "loss": 0.4827, + "step": 5722 + }, + { + "epoch": 0.48, + "learning_rate": 1.1169352375659314e-05, + "loss": 0.4936, + "step": 5723 + }, + { + "epoch": 0.48, + "learning_rate": 1.1166661019127447e-05, + "loss": 0.4858, + "step": 5724 + }, + { + "epoch": 0.48, + "learning_rate": 1.1163969576920846e-05, + "loss": 0.4639, + "step": 5725 + }, + { + "epoch": 0.48, + "learning_rate": 1.1161278049237157e-05, + "loss": 0.5047, + "step": 5726 + }, + { + "epoch": 0.48, + "learning_rate": 1.1158586436274042e-05, + "loss": 0.4743, + "step": 5727 + }, + { + "epoch": 0.48, + "learning_rate": 1.1155894738229156e-05, + "loss": 0.485, + "step": 5728 + }, + { + "epoch": 0.48, + "learning_rate": 1.115320295530017e-05, + "loss": 0.4729, + "step": 5729 + }, + { + "epoch": 0.48, + "learning_rate": 1.1150511087684757e-05, + "loss": 0.4761, + "step": 5730 + }, + { + "epoch": 0.48, + "learning_rate": 1.1147819135580588e-05, + "loss": 0.4886, + "step": 5731 + }, + { + "epoch": 0.48, + "learning_rate": 1.1145127099185363e-05, + "loss": 0.4789, + "step": 5732 + }, + { + "epoch": 0.48, + "learning_rate": 1.1142434978696763e-05, + "loss": 0.495, + "step": 5733 + }, + { + "epoch": 0.48, + "learning_rate": 1.1139742774312495e-05, + "loss": 0.4717, + "step": 5734 + }, + { + "epoch": 0.48, + "learning_rate": 1.1137050486230251e-05, + "loss": 0.495, + "step": 5735 + }, + { + "epoch": 0.48, + "learning_rate": 1.1134358114647752e-05, + "loss": 0.4825, + "step": 5736 + }, + { + "epoch": 0.48, + "learning_rate": 1.1131665659762712e-05, + "loss": 0.476, + "step": 5737 + }, + { + "epoch": 0.48, + "learning_rate": 1.112897312177285e-05, + "loss": 0.4794, + "step": 5738 + }, + { + "epoch": 0.48, + "learning_rate": 1.11262805008759e-05, + "loss": 0.4632, + "step": 5739 + }, + { + "epoch": 0.48, + "learning_rate": 1.1123587797269596e-05, + "loss": 0.5031, + "step": 5740 + }, + { + "epoch": 0.48, + "learning_rate": 1.1120895011151675e-05, + "loss": 0.4687, + "step": 5741 + }, + { + "epoch": 0.48, + "learning_rate": 1.1118202142719887e-05, + "loss": 0.5017, + "step": 5742 + }, + { + "epoch": 0.48, + "learning_rate": 1.1115509192171988e-05, + "loss": 0.4941, + "step": 5743 + }, + { + "epoch": 0.48, + "learning_rate": 1.111281615970573e-05, + "loss": 0.4736, + "step": 5744 + }, + { + "epoch": 0.48, + "learning_rate": 1.1110123045518882e-05, + "loss": 0.4698, + "step": 5745 + }, + { + "epoch": 0.48, + "learning_rate": 1.1107429849809215e-05, + "loss": 0.491, + "step": 5746 + }, + { + "epoch": 0.48, + "learning_rate": 1.1104736572774506e-05, + "loss": 0.4839, + "step": 5747 + }, + { + "epoch": 0.48, + "learning_rate": 1.1102043214612539e-05, + "loss": 0.4779, + "step": 5748 + }, + { + "epoch": 0.48, + "learning_rate": 1.1099349775521103e-05, + "loss": 0.4833, + "step": 5749 + }, + { + "epoch": 0.48, + "learning_rate": 1.1096656255697991e-05, + "loss": 0.4852, + "step": 5750 + }, + { + "epoch": 0.48, + "learning_rate": 1.1093962655341002e-05, + "loss": 0.4684, + "step": 5751 + }, + { + "epoch": 0.48, + "learning_rate": 1.1091268974647947e-05, + "loss": 0.4879, + "step": 5752 + }, + { + "epoch": 0.48, + "learning_rate": 1.108857521381664e-05, + "loss": 0.4902, + "step": 5753 + }, + { + "epoch": 0.48, + "learning_rate": 1.1085881373044895e-05, + "loss": 0.4738, + "step": 5754 + }, + { + "epoch": 0.48, + "learning_rate": 1.1083187452530539e-05, + "loss": 0.4899, + "step": 5755 + }, + { + "epoch": 0.48, + "learning_rate": 1.1080493452471403e-05, + "loss": 0.4831, + "step": 5756 + }, + { + "epoch": 0.48, + "learning_rate": 1.1077799373065321e-05, + "loss": 0.4738, + "step": 5757 + }, + { + "epoch": 0.48, + "learning_rate": 1.1075105214510135e-05, + "loss": 0.4864, + "step": 5758 + }, + { + "epoch": 0.48, + "learning_rate": 1.1072410977003693e-05, + "loss": 0.4776, + "step": 5759 + }, + { + "epoch": 0.48, + "learning_rate": 1.1069716660743852e-05, + "loss": 0.4847, + "step": 5760 + }, + { + "epoch": 0.48, + "learning_rate": 1.1067022265928472e-05, + "loss": 0.482, + "step": 5761 + }, + { + "epoch": 0.48, + "learning_rate": 1.1064327792755405e-05, + "loss": 0.4857, + "step": 5762 + }, + { + "epoch": 0.48, + "learning_rate": 1.1061633241422538e-05, + "loss": 0.4833, + "step": 5763 + }, + { + "epoch": 0.48, + "learning_rate": 1.1058938612127744e-05, + "loss": 0.4706, + "step": 5764 + }, + { + "epoch": 0.48, + "learning_rate": 1.1056243905068899e-05, + "loss": 0.481, + "step": 5765 + }, + { + "epoch": 0.48, + "learning_rate": 1.1053549120443893e-05, + "loss": 0.4646, + "step": 5766 + }, + { + "epoch": 0.48, + "learning_rate": 1.1050854258450623e-05, + "loss": 0.4928, + "step": 5767 + }, + { + "epoch": 0.48, + "learning_rate": 1.104815931928699e-05, + "loss": 0.4864, + "step": 5768 + }, + { + "epoch": 0.48, + "learning_rate": 1.1045464303150892e-05, + "loss": 0.4873, + "step": 5769 + }, + { + "epoch": 0.48, + "learning_rate": 1.1042769210240248e-05, + "loss": 0.4881, + "step": 5770 + }, + { + "epoch": 0.48, + "learning_rate": 1.1040074040752971e-05, + "loss": 0.4759, + "step": 5771 + }, + { + "epoch": 0.48, + "learning_rate": 1.1037378794886977e-05, + "loss": 0.4723, + "step": 5772 + }, + { + "epoch": 0.48, + "learning_rate": 1.1034683472840201e-05, + "loss": 0.468, + "step": 5773 + }, + { + "epoch": 0.48, + "learning_rate": 1.1031988074810578e-05, + "loss": 0.4803, + "step": 5774 + }, + { + "epoch": 0.48, + "learning_rate": 1.1029292600996042e-05, + "loss": 0.5059, + "step": 5775 + }, + { + "epoch": 0.48, + "learning_rate": 1.1026597051594534e-05, + "loss": 0.4792, + "step": 5776 + }, + { + "epoch": 0.48, + "learning_rate": 1.102390142680401e-05, + "loss": 0.4762, + "step": 5777 + }, + { + "epoch": 0.48, + "learning_rate": 1.1021205726822429e-05, + "loss": 0.4988, + "step": 5778 + }, + { + "epoch": 0.48, + "learning_rate": 1.1018509951847743e-05, + "loss": 0.4742, + "step": 5779 + }, + { + "epoch": 0.48, + "learning_rate": 1.1015814102077921e-05, + "loss": 0.4762, + "step": 5780 + }, + { + "epoch": 0.48, + "learning_rate": 1.1013118177710942e-05, + "loss": 0.4947, + "step": 5781 + }, + { + "epoch": 0.48, + "learning_rate": 1.1010422178944772e-05, + "loss": 0.4727, + "step": 5782 + }, + { + "epoch": 0.48, + "learning_rate": 1.10077261059774e-05, + "loss": 0.4662, + "step": 5783 + }, + { + "epoch": 0.48, + "learning_rate": 1.1005029959006818e-05, + "loss": 0.4927, + "step": 5784 + }, + { + "epoch": 0.48, + "learning_rate": 1.1002333738231016e-05, + "loss": 0.4872, + "step": 5785 + }, + { + "epoch": 0.48, + "learning_rate": 1.099963744384799e-05, + "loss": 0.4899, + "step": 5786 + }, + { + "epoch": 0.48, + "learning_rate": 1.0996941076055751e-05, + "loss": 0.4824, + "step": 5787 + }, + { + "epoch": 0.48, + "learning_rate": 1.0994244635052304e-05, + "loss": 0.4645, + "step": 5788 + }, + { + "epoch": 0.48, + "learning_rate": 1.0991548121035664e-05, + "loss": 0.4843, + "step": 5789 + }, + { + "epoch": 0.48, + "learning_rate": 1.098885153420386e-05, + "loss": 0.4767, + "step": 5790 + }, + { + "epoch": 0.48, + "learning_rate": 1.098615487475491e-05, + "loss": 0.4897, + "step": 5791 + }, + { + "epoch": 0.48, + "learning_rate": 1.0983458142886848e-05, + "loss": 0.4754, + "step": 5792 + }, + { + "epoch": 0.48, + "learning_rate": 1.0980761338797707e-05, + "loss": 0.4671, + "step": 5793 + }, + { + "epoch": 0.48, + "learning_rate": 1.0978064462685536e-05, + "loss": 0.4932, + "step": 5794 + }, + { + "epoch": 0.48, + "learning_rate": 1.0975367514748378e-05, + "loss": 0.4822, + "step": 5795 + }, + { + "epoch": 0.48, + "learning_rate": 1.0972670495184286e-05, + "loss": 0.5096, + "step": 5796 + }, + { + "epoch": 0.49, + "learning_rate": 1.0969973404191322e-05, + "loss": 0.5035, + "step": 5797 + }, + { + "epoch": 0.49, + "learning_rate": 1.096727624196754e-05, + "loss": 0.4778, + "step": 5798 + }, + { + "epoch": 0.49, + "learning_rate": 1.0964579008711018e-05, + "loss": 0.4801, + "step": 5799 + }, + { + "epoch": 0.49, + "learning_rate": 1.0961881704619823e-05, + "loss": 0.4845, + "step": 5800 + }, + { + "epoch": 0.49, + "learning_rate": 1.095918432989204e-05, + "loss": 0.4793, + "step": 5801 + }, + { + "epoch": 0.49, + "learning_rate": 1.0956486884725748e-05, + "loss": 0.4717, + "step": 5802 + }, + { + "epoch": 0.49, + "learning_rate": 1.0953789369319031e-05, + "loss": 0.4756, + "step": 5803 + }, + { + "epoch": 0.49, + "learning_rate": 1.0951091783869998e-05, + "loss": 0.485, + "step": 5804 + }, + { + "epoch": 0.49, + "learning_rate": 1.0948394128576739e-05, + "loss": 0.496, + "step": 5805 + }, + { + "epoch": 0.49, + "learning_rate": 1.094569640363736e-05, + "loss": 0.4963, + "step": 5806 + }, + { + "epoch": 0.49, + "learning_rate": 1.0942998609249968e-05, + "loss": 0.4884, + "step": 5807 + }, + { + "epoch": 0.49, + "learning_rate": 1.0940300745612679e-05, + "loss": 0.4687, + "step": 5808 + }, + { + "epoch": 0.49, + "learning_rate": 1.0937602812923617e-05, + "loss": 0.4779, + "step": 5809 + }, + { + "epoch": 0.49, + "learning_rate": 1.0934904811380904e-05, + "loss": 0.4892, + "step": 5810 + }, + { + "epoch": 0.49, + "learning_rate": 1.0932206741182672e-05, + "loss": 0.4831, + "step": 5811 + }, + { + "epoch": 0.49, + "learning_rate": 1.0929508602527052e-05, + "loss": 0.4711, + "step": 5812 + }, + { + "epoch": 0.49, + "learning_rate": 1.0926810395612187e-05, + "loss": 0.4934, + "step": 5813 + }, + { + "epoch": 0.49, + "learning_rate": 1.0924112120636222e-05, + "loss": 0.48, + "step": 5814 + }, + { + "epoch": 0.49, + "learning_rate": 1.0921413777797305e-05, + "loss": 0.4744, + "step": 5815 + }, + { + "epoch": 0.49, + "learning_rate": 1.0918715367293595e-05, + "loss": 0.4796, + "step": 5816 + }, + { + "epoch": 0.49, + "learning_rate": 1.0916016889323246e-05, + "loss": 0.4669, + "step": 5817 + }, + { + "epoch": 0.49, + "learning_rate": 1.0913318344084428e-05, + "loss": 0.4656, + "step": 5818 + }, + { + "epoch": 0.49, + "learning_rate": 1.0910619731775311e-05, + "loss": 0.4658, + "step": 5819 + }, + { + "epoch": 0.49, + "learning_rate": 1.0907921052594066e-05, + "loss": 0.4817, + "step": 5820 + }, + { + "epoch": 0.49, + "learning_rate": 1.0905222306738879e-05, + "loss": 0.4862, + "step": 5821 + }, + { + "epoch": 0.49, + "learning_rate": 1.0902523494407928e-05, + "loss": 0.4828, + "step": 5822 + }, + { + "epoch": 0.49, + "learning_rate": 1.0899824615799406e-05, + "loss": 0.4725, + "step": 5823 + }, + { + "epoch": 0.49, + "learning_rate": 1.0897125671111507e-05, + "loss": 0.4827, + "step": 5824 + }, + { + "epoch": 0.49, + "learning_rate": 1.089442666054243e-05, + "loss": 0.4902, + "step": 5825 + }, + { + "epoch": 0.49, + "learning_rate": 1.0891727584290381e-05, + "loss": 0.465, + "step": 5826 + }, + { + "epoch": 0.49, + "learning_rate": 1.0889028442553565e-05, + "loss": 0.4795, + "step": 5827 + }, + { + "epoch": 0.49, + "learning_rate": 1.08863292355302e-05, + "loss": 0.4693, + "step": 5828 + }, + { + "epoch": 0.49, + "learning_rate": 1.0883629963418501e-05, + "loss": 0.4781, + "step": 5829 + }, + { + "epoch": 0.49, + "learning_rate": 1.088093062641669e-05, + "loss": 0.5004, + "step": 5830 + }, + { + "epoch": 0.49, + "learning_rate": 1.0878231224723001e-05, + "loss": 0.4815, + "step": 5831 + }, + { + "epoch": 0.49, + "learning_rate": 1.0875531758535668e-05, + "loss": 0.4879, + "step": 5832 + }, + { + "epoch": 0.49, + "learning_rate": 1.0872832228052919e-05, + "loss": 0.4919, + "step": 5833 + }, + { + "epoch": 0.49, + "learning_rate": 1.0870132633472999e-05, + "loss": 0.5049, + "step": 5834 + }, + { + "epoch": 0.49, + "learning_rate": 1.0867432974994162e-05, + "loss": 0.4874, + "step": 5835 + }, + { + "epoch": 0.49, + "learning_rate": 1.0864733252814654e-05, + "loss": 0.4906, + "step": 5836 + }, + { + "epoch": 0.49, + "learning_rate": 1.0862033467132732e-05, + "loss": 0.4875, + "step": 5837 + }, + { + "epoch": 0.49, + "learning_rate": 1.0859333618146659e-05, + "loss": 0.4617, + "step": 5838 + }, + { + "epoch": 0.49, + "learning_rate": 1.0856633706054698e-05, + "loss": 0.4761, + "step": 5839 + }, + { + "epoch": 0.49, + "learning_rate": 1.0853933731055122e-05, + "loss": 0.4735, + "step": 5840 + }, + { + "epoch": 0.49, + "learning_rate": 1.0851233693346204e-05, + "loss": 0.4843, + "step": 5841 + }, + { + "epoch": 0.49, + "learning_rate": 1.0848533593126225e-05, + "loss": 0.4845, + "step": 5842 + }, + { + "epoch": 0.49, + "learning_rate": 1.0845833430593467e-05, + "loss": 0.4731, + "step": 5843 + }, + { + "epoch": 0.49, + "learning_rate": 1.0843133205946218e-05, + "loss": 0.4897, + "step": 5844 + }, + { + "epoch": 0.49, + "learning_rate": 1.0840432919382774e-05, + "loss": 0.501, + "step": 5845 + }, + { + "epoch": 0.49, + "learning_rate": 1.0837732571101437e-05, + "loss": 0.4934, + "step": 5846 + }, + { + "epoch": 0.49, + "learning_rate": 1.0835032161300499e-05, + "loss": 0.4878, + "step": 5847 + }, + { + "epoch": 0.49, + "learning_rate": 1.0832331690178274e-05, + "loss": 0.4885, + "step": 5848 + }, + { + "epoch": 0.49, + "learning_rate": 1.0829631157933071e-05, + "loss": 0.4741, + "step": 5849 + }, + { + "epoch": 0.49, + "learning_rate": 1.0826930564763207e-05, + "loss": 0.5027, + "step": 5850 + }, + { + "epoch": 0.49, + "learning_rate": 1.0824229910867002e-05, + "loss": 0.4769, + "step": 5851 + }, + { + "epoch": 0.49, + "learning_rate": 1.0821529196442782e-05, + "loss": 0.4863, + "step": 5852 + }, + { + "epoch": 0.49, + "learning_rate": 1.0818828421688873e-05, + "loss": 0.4707, + "step": 5853 + }, + { + "epoch": 0.49, + "learning_rate": 1.081612758680361e-05, + "loss": 0.4718, + "step": 5854 + }, + { + "epoch": 0.49, + "learning_rate": 1.0813426691985331e-05, + "loss": 0.469, + "step": 5855 + }, + { + "epoch": 0.49, + "learning_rate": 1.0810725737432381e-05, + "loss": 0.4993, + "step": 5856 + }, + { + "epoch": 0.49, + "learning_rate": 1.0808024723343104e-05, + "loss": 0.4695, + "step": 5857 + }, + { + "epoch": 0.49, + "learning_rate": 1.0805323649915854e-05, + "loss": 0.4555, + "step": 5858 + }, + { + "epoch": 0.49, + "learning_rate": 1.0802622517348982e-05, + "loss": 0.4673, + "step": 5859 + }, + { + "epoch": 0.49, + "learning_rate": 1.0799921325840851e-05, + "loss": 0.4788, + "step": 5860 + }, + { + "epoch": 0.49, + "learning_rate": 1.0797220075589825e-05, + "loss": 0.4518, + "step": 5861 + }, + { + "epoch": 0.49, + "learning_rate": 1.0794518766794272e-05, + "loss": 0.4822, + "step": 5862 + }, + { + "epoch": 0.49, + "learning_rate": 1.079181739965257e-05, + "loss": 0.4787, + "step": 5863 + }, + { + "epoch": 0.49, + "learning_rate": 1.0789115974363086e-05, + "loss": 0.4897, + "step": 5864 + }, + { + "epoch": 0.49, + "learning_rate": 1.0786414491124208e-05, + "loss": 0.4997, + "step": 5865 + }, + { + "epoch": 0.49, + "learning_rate": 1.0783712950134324e-05, + "loss": 0.4807, + "step": 5866 + }, + { + "epoch": 0.49, + "learning_rate": 1.0781011351591819e-05, + "loss": 0.4609, + "step": 5867 + }, + { + "epoch": 0.49, + "learning_rate": 1.0778309695695088e-05, + "loss": 0.4857, + "step": 5868 + }, + { + "epoch": 0.49, + "learning_rate": 1.077560798264253e-05, + "loss": 0.4819, + "step": 5869 + }, + { + "epoch": 0.49, + "learning_rate": 1.0772906212632547e-05, + "loss": 0.4784, + "step": 5870 + }, + { + "epoch": 0.49, + "learning_rate": 1.0770204385863547e-05, + "loss": 0.4976, + "step": 5871 + }, + { + "epoch": 0.49, + "learning_rate": 1.0767502502533945e-05, + "loss": 0.473, + "step": 5872 + }, + { + "epoch": 0.49, + "learning_rate": 1.0764800562842149e-05, + "loss": 0.4696, + "step": 5873 + }, + { + "epoch": 0.49, + "learning_rate": 1.0762098566986578e-05, + "loss": 0.4932, + "step": 5874 + }, + { + "epoch": 0.49, + "learning_rate": 1.0759396515165657e-05, + "loss": 0.4942, + "step": 5875 + }, + { + "epoch": 0.49, + "learning_rate": 1.075669440757782e-05, + "loss": 0.4632, + "step": 5876 + }, + { + "epoch": 0.49, + "learning_rate": 1.075399224442149e-05, + "loss": 0.477, + "step": 5877 + }, + { + "epoch": 0.49, + "learning_rate": 1.0751290025895104e-05, + "loss": 0.49, + "step": 5878 + }, + { + "epoch": 0.49, + "learning_rate": 1.0748587752197106e-05, + "loss": 0.4698, + "step": 5879 + }, + { + "epoch": 0.49, + "learning_rate": 1.0745885423525934e-05, + "loss": 0.4739, + "step": 5880 + }, + { + "epoch": 0.49, + "learning_rate": 1.0743183040080043e-05, + "loss": 0.4757, + "step": 5881 + }, + { + "epoch": 0.49, + "learning_rate": 1.0740480602057877e-05, + "loss": 0.4677, + "step": 5882 + }, + { + "epoch": 0.49, + "learning_rate": 1.0737778109657899e-05, + "loss": 0.4867, + "step": 5883 + }, + { + "epoch": 0.49, + "learning_rate": 1.0735075563078565e-05, + "loss": 0.4678, + "step": 5884 + }, + { + "epoch": 0.49, + "learning_rate": 1.0732372962518337e-05, + "loss": 0.4661, + "step": 5885 + }, + { + "epoch": 0.49, + "learning_rate": 1.0729670308175683e-05, + "loss": 0.4743, + "step": 5886 + }, + { + "epoch": 0.49, + "learning_rate": 1.072696760024908e-05, + "loss": 0.4877, + "step": 5887 + }, + { + "epoch": 0.49, + "learning_rate": 1.0724264838936998e-05, + "loss": 0.4869, + "step": 5888 + }, + { + "epoch": 0.49, + "learning_rate": 1.0721562024437919e-05, + "loss": 0.4722, + "step": 5889 + }, + { + "epoch": 0.49, + "learning_rate": 1.0718859156950329e-05, + "loss": 0.4959, + "step": 5890 + }, + { + "epoch": 0.49, + "learning_rate": 1.071615623667271e-05, + "loss": 0.4653, + "step": 5891 + }, + { + "epoch": 0.49, + "learning_rate": 1.0713453263803553e-05, + "loss": 0.4606, + "step": 5892 + }, + { + "epoch": 0.49, + "learning_rate": 1.071075023854136e-05, + "loss": 0.49, + "step": 5893 + }, + { + "epoch": 0.49, + "learning_rate": 1.0708047161084626e-05, + "loss": 0.4895, + "step": 5894 + }, + { + "epoch": 0.49, + "learning_rate": 1.070534403163185e-05, + "loss": 0.4806, + "step": 5895 + }, + { + "epoch": 0.49, + "learning_rate": 1.0702640850381542e-05, + "loss": 0.4713, + "step": 5896 + }, + { + "epoch": 0.49, + "learning_rate": 1.0699937617532216e-05, + "loss": 0.4832, + "step": 5897 + }, + { + "epoch": 0.49, + "learning_rate": 1.0697234333282382e-05, + "loss": 0.4784, + "step": 5898 + }, + { + "epoch": 0.49, + "learning_rate": 1.0694530997830556e-05, + "loss": 0.4696, + "step": 5899 + }, + { + "epoch": 0.49, + "learning_rate": 1.0691827611375268e-05, + "loss": 0.5059, + "step": 5900 + }, + { + "epoch": 0.49, + "learning_rate": 1.068912417411503e-05, + "loss": 0.4705, + "step": 5901 + }, + { + "epoch": 0.49, + "learning_rate": 1.0686420686248382e-05, + "loss": 0.4696, + "step": 5902 + }, + { + "epoch": 0.49, + "learning_rate": 1.0683717147973856e-05, + "loss": 0.4935, + "step": 5903 + }, + { + "epoch": 0.49, + "learning_rate": 1.0681013559489985e-05, + "loss": 0.4837, + "step": 5904 + }, + { + "epoch": 0.49, + "learning_rate": 1.067830992099531e-05, + "loss": 0.4748, + "step": 5905 + }, + { + "epoch": 0.49, + "learning_rate": 1.0675606232688377e-05, + "loss": 0.4827, + "step": 5906 + }, + { + "epoch": 0.49, + "learning_rate": 1.0672902494767731e-05, + "loss": 0.5115, + "step": 5907 + }, + { + "epoch": 0.49, + "learning_rate": 1.0670198707431927e-05, + "loss": 0.4813, + "step": 5908 + }, + { + "epoch": 0.49, + "learning_rate": 1.0667494870879513e-05, + "loss": 0.4771, + "step": 5909 + }, + { + "epoch": 0.49, + "learning_rate": 1.0664790985309058e-05, + "loss": 0.5049, + "step": 5910 + }, + { + "epoch": 0.49, + "learning_rate": 1.0662087050919111e-05, + "loss": 0.4861, + "step": 5911 + }, + { + "epoch": 0.49, + "learning_rate": 1.065938306790825e-05, + "loss": 0.4752, + "step": 5912 + }, + { + "epoch": 0.49, + "learning_rate": 1.0656679036475038e-05, + "loss": 0.4789, + "step": 5913 + }, + { + "epoch": 0.49, + "learning_rate": 1.065397495681805e-05, + "loss": 0.4715, + "step": 5914 + }, + { + "epoch": 0.49, + "learning_rate": 1.065127082913586e-05, + "loss": 0.4669, + "step": 5915 + }, + { + "epoch": 0.49, + "learning_rate": 1.0648566653627048e-05, + "loss": 0.4878, + "step": 5916 + }, + { + "epoch": 0.5, + "learning_rate": 1.06458624304902e-05, + "loss": 0.4657, + "step": 5917 + }, + { + "epoch": 0.5, + "learning_rate": 1.0643158159923902e-05, + "loss": 0.4867, + "step": 5918 + }, + { + "epoch": 0.5, + "learning_rate": 1.0640453842126742e-05, + "loss": 0.4842, + "step": 5919 + }, + { + "epoch": 0.5, + "learning_rate": 1.0637749477297317e-05, + "loss": 0.4846, + "step": 5920 + }, + { + "epoch": 0.5, + "learning_rate": 1.063504506563422e-05, + "loss": 0.4753, + "step": 5921 + }, + { + "epoch": 0.5, + "learning_rate": 1.0632340607336056e-05, + "loss": 0.4803, + "step": 5922 + }, + { + "epoch": 0.5, + "learning_rate": 1.062963610260143e-05, + "loss": 0.4649, + "step": 5923 + }, + { + "epoch": 0.5, + "learning_rate": 1.0626931551628948e-05, + "loss": 0.5102, + "step": 5924 + }, + { + "epoch": 0.5, + "learning_rate": 1.0624226954617221e-05, + "loss": 0.4758, + "step": 5925 + }, + { + "epoch": 0.5, + "learning_rate": 1.0621522311764857e-05, + "loss": 0.4701, + "step": 5926 + }, + { + "epoch": 0.5, + "learning_rate": 1.0618817623270484e-05, + "loss": 0.4919, + "step": 5927 + }, + { + "epoch": 0.5, + "learning_rate": 1.061611288933272e-05, + "loss": 0.5002, + "step": 5928 + }, + { + "epoch": 0.5, + "learning_rate": 1.0613408110150185e-05, + "loss": 0.4994, + "step": 5929 + }, + { + "epoch": 0.5, + "learning_rate": 1.061070328592151e-05, + "loss": 0.4734, + "step": 5930 + }, + { + "epoch": 0.5, + "learning_rate": 1.0607998416845329e-05, + "loss": 0.4737, + "step": 5931 + }, + { + "epoch": 0.5, + "learning_rate": 1.0605293503120268e-05, + "loss": 0.4695, + "step": 5932 + }, + { + "epoch": 0.5, + "learning_rate": 1.0602588544944972e-05, + "loss": 0.4705, + "step": 5933 + }, + { + "epoch": 0.5, + "learning_rate": 1.059988354251808e-05, + "loss": 0.4683, + "step": 5934 + }, + { + "epoch": 0.5, + "learning_rate": 1.059717849603824e-05, + "loss": 0.4895, + "step": 5935 + }, + { + "epoch": 0.5, + "learning_rate": 1.0594473405704088e-05, + "loss": 0.4732, + "step": 5936 + }, + { + "epoch": 0.5, + "learning_rate": 1.0591768271714285e-05, + "loss": 0.4844, + "step": 5937 + }, + { + "epoch": 0.5, + "learning_rate": 1.058906309426748e-05, + "loss": 0.4746, + "step": 5938 + }, + { + "epoch": 0.5, + "learning_rate": 1.0586357873562332e-05, + "loss": 0.4765, + "step": 5939 + }, + { + "epoch": 0.5, + "learning_rate": 1.0583652609797501e-05, + "loss": 0.4753, + "step": 5940 + }, + { + "epoch": 0.5, + "learning_rate": 1.0580947303171651e-05, + "loss": 0.4755, + "step": 5941 + }, + { + "epoch": 0.5, + "learning_rate": 1.0578241953883445e-05, + "loss": 0.4855, + "step": 5942 + }, + { + "epoch": 0.5, + "learning_rate": 1.0575536562131556e-05, + "loss": 0.4863, + "step": 5943 + }, + { + "epoch": 0.5, + "learning_rate": 1.0572831128114658e-05, + "loss": 0.4672, + "step": 5944 + }, + { + "epoch": 0.5, + "learning_rate": 1.0570125652031425e-05, + "loss": 0.4928, + "step": 5945 + }, + { + "epoch": 0.5, + "learning_rate": 1.0567420134080531e-05, + "loss": 0.4896, + "step": 5946 + }, + { + "epoch": 0.5, + "learning_rate": 1.0564714574460664e-05, + "loss": 0.4839, + "step": 5947 + }, + { + "epoch": 0.5, + "learning_rate": 1.0562008973370508e-05, + "loss": 0.4808, + "step": 5948 + }, + { + "epoch": 0.5, + "learning_rate": 1.0559303331008752e-05, + "loss": 0.4783, + "step": 5949 + }, + { + "epoch": 0.5, + "learning_rate": 1.0556597647574083e-05, + "loss": 0.4887, + "step": 5950 + }, + { + "epoch": 0.5, + "learning_rate": 1.05538919232652e-05, + "loss": 0.4867, + "step": 5951 + }, + { + "epoch": 0.5, + "learning_rate": 1.0551186158280795e-05, + "loss": 0.5122, + "step": 5952 + }, + { + "epoch": 0.5, + "learning_rate": 1.0548480352819573e-05, + "loss": 0.4623, + "step": 5953 + }, + { + "epoch": 0.5, + "learning_rate": 1.0545774507080237e-05, + "loss": 0.4677, + "step": 5954 + }, + { + "epoch": 0.5, + "learning_rate": 1.054306862126149e-05, + "loss": 0.4772, + "step": 5955 + }, + { + "epoch": 0.5, + "learning_rate": 1.0540362695562043e-05, + "loss": 0.4747, + "step": 5956 + }, + { + "epoch": 0.5, + "learning_rate": 1.0537656730180606e-05, + "loss": 0.4751, + "step": 5957 + }, + { + "epoch": 0.5, + "learning_rate": 1.0534950725315893e-05, + "loss": 0.4904, + "step": 5958 + }, + { + "epoch": 0.5, + "learning_rate": 1.0532244681166628e-05, + "loss": 0.4845, + "step": 5959 + }, + { + "epoch": 0.5, + "learning_rate": 1.0529538597931524e-05, + "loss": 0.4788, + "step": 5960 + }, + { + "epoch": 0.5, + "learning_rate": 1.052683247580931e-05, + "loss": 0.4771, + "step": 5961 + }, + { + "epoch": 0.5, + "learning_rate": 1.0524126314998711e-05, + "loss": 0.4895, + "step": 5962 + }, + { + "epoch": 0.5, + "learning_rate": 1.0521420115698448e-05, + "loss": 0.4743, + "step": 5963 + }, + { + "epoch": 0.5, + "learning_rate": 1.0518713878107268e-05, + "loss": 0.4543, + "step": 5964 + }, + { + "epoch": 0.5, + "learning_rate": 1.0516007602423896e-05, + "loss": 0.4893, + "step": 5965 + }, + { + "epoch": 0.5, + "learning_rate": 1.0513301288847076e-05, + "loss": 0.4831, + "step": 5966 + }, + { + "epoch": 0.5, + "learning_rate": 1.0510594937575537e-05, + "loss": 0.4739, + "step": 5967 + }, + { + "epoch": 0.5, + "learning_rate": 1.0507888548808034e-05, + "loss": 0.4901, + "step": 5968 + }, + { + "epoch": 0.5, + "learning_rate": 1.0505182122743309e-05, + "loss": 0.4903, + "step": 5969 + }, + { + "epoch": 0.5, + "learning_rate": 1.0502475659580107e-05, + "loss": 0.4827, + "step": 5970 + }, + { + "epoch": 0.5, + "learning_rate": 1.0499769159517186e-05, + "loss": 0.4875, + "step": 5971 + }, + { + "epoch": 0.5, + "learning_rate": 1.0497062622753296e-05, + "loss": 0.4978, + "step": 5972 + }, + { + "epoch": 0.5, + "learning_rate": 1.049435604948719e-05, + "loss": 0.4832, + "step": 5973 + }, + { + "epoch": 0.5, + "learning_rate": 1.0491649439917636e-05, + "loss": 0.4586, + "step": 5974 + }, + { + "epoch": 0.5, + "learning_rate": 1.0488942794243393e-05, + "loss": 0.4639, + "step": 5975 + }, + { + "epoch": 0.5, + "learning_rate": 1.0486236112663224e-05, + "loss": 0.4936, + "step": 5976 + }, + { + "epoch": 0.5, + "learning_rate": 1.0483529395375896e-05, + "loss": 0.4603, + "step": 5977 + }, + { + "epoch": 0.5, + "learning_rate": 1.0480822642580178e-05, + "loss": 0.4836, + "step": 5978 + }, + { + "epoch": 0.5, + "learning_rate": 1.0478115854474848e-05, + "loss": 0.5113, + "step": 5979 + }, + { + "epoch": 0.5, + "learning_rate": 1.0475409031258678e-05, + "loss": 0.4747, + "step": 5980 + }, + { + "epoch": 0.5, + "learning_rate": 1.0472702173130447e-05, + "loss": 0.4841, + "step": 5981 + }, + { + "epoch": 0.5, + "learning_rate": 1.0469995280288936e-05, + "loss": 0.4726, + "step": 5982 + }, + { + "epoch": 0.5, + "learning_rate": 1.0467288352932923e-05, + "loss": 0.47, + "step": 5983 + }, + { + "epoch": 0.5, + "learning_rate": 1.0464581391261198e-05, + "loss": 0.4819, + "step": 5984 + }, + { + "epoch": 0.5, + "learning_rate": 1.0461874395472549e-05, + "loss": 0.4767, + "step": 5985 + }, + { + "epoch": 0.5, + "learning_rate": 1.0459167365765765e-05, + "loss": 0.4681, + "step": 5986 + }, + { + "epoch": 0.5, + "learning_rate": 1.0456460302339636e-05, + "loss": 0.4776, + "step": 5987 + }, + { + "epoch": 0.5, + "learning_rate": 1.0453753205392967e-05, + "loss": 0.4719, + "step": 5988 + }, + { + "epoch": 0.5, + "learning_rate": 1.0451046075124544e-05, + "loss": 0.4728, + "step": 5989 + }, + { + "epoch": 0.5, + "learning_rate": 1.0448338911733178e-05, + "loss": 0.4883, + "step": 5990 + }, + { + "epoch": 0.5, + "learning_rate": 1.0445631715417666e-05, + "loss": 0.5035, + "step": 5991 + }, + { + "epoch": 0.5, + "learning_rate": 1.0442924486376813e-05, + "loss": 0.4744, + "step": 5992 + }, + { + "epoch": 0.5, + "learning_rate": 1.0440217224809427e-05, + "loss": 0.498, + "step": 5993 + }, + { + "epoch": 0.5, + "learning_rate": 1.043750993091432e-05, + "loss": 0.4707, + "step": 5994 + }, + { + "epoch": 0.5, + "learning_rate": 1.0434802604890306e-05, + "loss": 0.4854, + "step": 5995 + }, + { + "epoch": 0.5, + "learning_rate": 1.0432095246936195e-05, + "loss": 0.4768, + "step": 5996 + }, + { + "epoch": 0.5, + "learning_rate": 1.0429387857250806e-05, + "loss": 0.4729, + "step": 5997 + }, + { + "epoch": 0.5, + "learning_rate": 1.042668043603296e-05, + "loss": 0.483, + "step": 5998 + }, + { + "epoch": 0.5, + "learning_rate": 1.0423972983481477e-05, + "loss": 0.4757, + "step": 5999 + }, + { + "epoch": 0.5, + "learning_rate": 1.0421265499795181e-05, + "loss": 0.4865, + "step": 6000 + }, + { + "epoch": 0.5, + "learning_rate": 1.0418557985172899e-05, + "loss": 0.4946, + "step": 6001 + }, + { + "epoch": 0.5, + "learning_rate": 1.0415850439813462e-05, + "loss": 0.4533, + "step": 6002 + }, + { + "epoch": 0.5, + "learning_rate": 1.0413142863915695e-05, + "loss": 0.4847, + "step": 6003 + }, + { + "epoch": 0.5, + "learning_rate": 1.0410435257678433e-05, + "loss": 0.4828, + "step": 6004 + }, + { + "epoch": 0.5, + "learning_rate": 1.0407727621300516e-05, + "loss": 0.4671, + "step": 6005 + }, + { + "epoch": 0.5, + "learning_rate": 1.0405019954980779e-05, + "loss": 0.4716, + "step": 6006 + }, + { + "epoch": 0.5, + "learning_rate": 1.0402312258918061e-05, + "loss": 0.4786, + "step": 6007 + }, + { + "epoch": 0.5, + "learning_rate": 1.03996045333112e-05, + "loss": 0.4873, + "step": 6008 + }, + { + "epoch": 0.5, + "learning_rate": 1.0396896778359047e-05, + "loss": 0.479, + "step": 6009 + }, + { + "epoch": 0.5, + "learning_rate": 1.0394188994260445e-05, + "loss": 0.463, + "step": 6010 + }, + { + "epoch": 0.5, + "learning_rate": 1.0391481181214244e-05, + "loss": 0.4551, + "step": 6011 + }, + { + "epoch": 0.5, + "learning_rate": 1.0388773339419294e-05, + "loss": 0.4634, + "step": 6012 + }, + { + "epoch": 0.5, + "learning_rate": 1.0386065469074447e-05, + "loss": 0.4834, + "step": 6013 + }, + { + "epoch": 0.5, + "learning_rate": 1.0383357570378553e-05, + "loss": 0.4901, + "step": 6014 + }, + { + "epoch": 0.5, + "learning_rate": 1.0380649643530476e-05, + "loss": 0.4779, + "step": 6015 + }, + { + "epoch": 0.5, + "learning_rate": 1.0377941688729074e-05, + "loss": 0.4925, + "step": 6016 + }, + { + "epoch": 0.5, + "learning_rate": 1.0375233706173207e-05, + "loss": 0.4912, + "step": 6017 + }, + { + "epoch": 0.5, + "learning_rate": 1.0372525696061735e-05, + "loss": 0.4781, + "step": 6018 + }, + { + "epoch": 0.5, + "learning_rate": 1.0369817658593524e-05, + "loss": 0.4854, + "step": 6019 + }, + { + "epoch": 0.5, + "learning_rate": 1.0367109593967445e-05, + "loss": 0.4858, + "step": 6020 + }, + { + "epoch": 0.5, + "learning_rate": 1.0364401502382364e-05, + "loss": 0.4811, + "step": 6021 + }, + { + "epoch": 0.5, + "learning_rate": 1.0361693384037154e-05, + "loss": 0.4865, + "step": 6022 + }, + { + "epoch": 0.5, + "learning_rate": 1.0358985239130685e-05, + "loss": 0.4867, + "step": 6023 + }, + { + "epoch": 0.5, + "learning_rate": 1.035627706786183e-05, + "loss": 0.4796, + "step": 6024 + }, + { + "epoch": 0.5, + "learning_rate": 1.035356887042947e-05, + "loss": 0.486, + "step": 6025 + }, + { + "epoch": 0.5, + "learning_rate": 1.0350860647032488e-05, + "loss": 0.4733, + "step": 6026 + }, + { + "epoch": 0.5, + "learning_rate": 1.0348152397869757e-05, + "loss": 0.4706, + "step": 6027 + }, + { + "epoch": 0.5, + "learning_rate": 1.0345444123140159e-05, + "loss": 0.4709, + "step": 6028 + }, + { + "epoch": 0.5, + "learning_rate": 1.0342735823042585e-05, + "loss": 0.4718, + "step": 6029 + }, + { + "epoch": 0.5, + "learning_rate": 1.0340027497775915e-05, + "loss": 0.476, + "step": 6030 + }, + { + "epoch": 0.5, + "learning_rate": 1.0337319147539042e-05, + "loss": 0.4838, + "step": 6031 + }, + { + "epoch": 0.5, + "learning_rate": 1.0334610772530851e-05, + "loss": 0.4914, + "step": 6032 + }, + { + "epoch": 0.5, + "learning_rate": 1.033190237295024e-05, + "loss": 0.4516, + "step": 6033 + }, + { + "epoch": 0.5, + "learning_rate": 1.0329193948996097e-05, + "loss": 0.4834, + "step": 6034 + }, + { + "epoch": 0.5, + "learning_rate": 1.0326485500867316e-05, + "loss": 0.4735, + "step": 6035 + }, + { + "epoch": 0.5, + "learning_rate": 1.0323777028762804e-05, + "loss": 0.4786, + "step": 6036 + }, + { + "epoch": 0.51, + "learning_rate": 1.0321068532881454e-05, + "loss": 0.4708, + "step": 6037 + }, + { + "epoch": 0.51, + "learning_rate": 1.0318360013422162e-05, + "loss": 0.5103, + "step": 6038 + }, + { + "epoch": 0.51, + "learning_rate": 1.0315651470583836e-05, + "loss": 0.5011, + "step": 6039 + }, + { + "epoch": 0.51, + "learning_rate": 1.0312942904565379e-05, + "loss": 0.4685, + "step": 6040 + }, + { + "epoch": 0.51, + "learning_rate": 1.0310234315565699e-05, + "loss": 0.4897, + "step": 6041 + }, + { + "epoch": 0.51, + "learning_rate": 1.0307525703783698e-05, + "loss": 0.489, + "step": 6042 + }, + { + "epoch": 0.51, + "learning_rate": 1.0304817069418292e-05, + "loss": 0.4754, + "step": 6043 + }, + { + "epoch": 0.51, + "learning_rate": 1.0302108412668387e-05, + "loss": 0.4889, + "step": 6044 + }, + { + "epoch": 0.51, + "learning_rate": 1.0299399733732893e-05, + "loss": 0.4967, + "step": 6045 + }, + { + "epoch": 0.51, + "learning_rate": 1.029669103281073e-05, + "loss": 0.4701, + "step": 6046 + }, + { + "epoch": 0.51, + "learning_rate": 1.0293982310100814e-05, + "loss": 0.4751, + "step": 6047 + }, + { + "epoch": 0.51, + "learning_rate": 1.0291273565802058e-05, + "loss": 0.4912, + "step": 6048 + }, + { + "epoch": 0.51, + "learning_rate": 1.0288564800113383e-05, + "loss": 0.4817, + "step": 6049 + }, + { + "epoch": 0.51, + "learning_rate": 1.0285856013233708e-05, + "loss": 0.4599, + "step": 6050 + }, + { + "epoch": 0.51, + "learning_rate": 1.0283147205361959e-05, + "loss": 0.4964, + "step": 6051 + }, + { + "epoch": 0.51, + "learning_rate": 1.0280438376697056e-05, + "loss": 0.4632, + "step": 6052 + }, + { + "epoch": 0.51, + "learning_rate": 1.0277729527437924e-05, + "loss": 0.463, + "step": 6053 + }, + { + "epoch": 0.51, + "learning_rate": 1.0275020657783492e-05, + "loss": 0.493, + "step": 6054 + }, + { + "epoch": 0.51, + "learning_rate": 1.0272311767932686e-05, + "loss": 0.4833, + "step": 6055 + }, + { + "epoch": 0.51, + "learning_rate": 1.0269602858084435e-05, + "loss": 0.4912, + "step": 6056 + }, + { + "epoch": 0.51, + "learning_rate": 1.0266893928437673e-05, + "loss": 0.481, + "step": 6057 + }, + { + "epoch": 0.51, + "learning_rate": 1.0264184979191331e-05, + "loss": 0.4745, + "step": 6058 + }, + { + "epoch": 0.51, + "learning_rate": 1.0261476010544345e-05, + "loss": 0.4958, + "step": 6059 + }, + { + "epoch": 0.51, + "learning_rate": 1.0258767022695645e-05, + "loss": 0.491, + "step": 6060 + }, + { + "epoch": 0.51, + "learning_rate": 1.0256058015844173e-05, + "loss": 0.4881, + "step": 6061 + }, + { + "epoch": 0.51, + "learning_rate": 1.0253348990188863e-05, + "loss": 0.4736, + "step": 6062 + }, + { + "epoch": 0.51, + "learning_rate": 1.025063994592866e-05, + "loss": 0.4744, + "step": 6063 + }, + { + "epoch": 0.51, + "learning_rate": 1.02479308832625e-05, + "loss": 0.4759, + "step": 6064 + }, + { + "epoch": 0.51, + "learning_rate": 1.0245221802389328e-05, + "loss": 0.4655, + "step": 6065 + }, + { + "epoch": 0.51, + "learning_rate": 1.0242512703508085e-05, + "loss": 0.4912, + "step": 6066 + }, + { + "epoch": 0.51, + "learning_rate": 1.023980358681772e-05, + "loss": 0.4852, + "step": 6067 + }, + { + "epoch": 0.51, + "learning_rate": 1.0237094452517178e-05, + "loss": 0.4838, + "step": 6068 + }, + { + "epoch": 0.51, + "learning_rate": 1.0234385300805403e-05, + "loss": 0.4851, + "step": 6069 + }, + { + "epoch": 0.51, + "learning_rate": 1.0231676131881348e-05, + "loss": 0.4732, + "step": 6070 + }, + { + "epoch": 0.51, + "learning_rate": 1.022896694594396e-05, + "loss": 0.4902, + "step": 6071 + }, + { + "epoch": 0.51, + "learning_rate": 1.022625774319219e-05, + "loss": 0.4603, + "step": 6072 + }, + { + "epoch": 0.51, + "learning_rate": 1.0223548523824996e-05, + "loss": 0.4785, + "step": 6073 + }, + { + "epoch": 0.51, + "learning_rate": 1.0220839288041328e-05, + "loss": 0.4651, + "step": 6074 + }, + { + "epoch": 0.51, + "learning_rate": 1.021813003604014e-05, + "loss": 0.4707, + "step": 6075 + }, + { + "epoch": 0.51, + "learning_rate": 1.0215420768020388e-05, + "loss": 0.5073, + "step": 6076 + }, + { + "epoch": 0.51, + "learning_rate": 1.0212711484181034e-05, + "loss": 0.4872, + "step": 6077 + }, + { + "epoch": 0.51, + "learning_rate": 1.0210002184721033e-05, + "loss": 0.4836, + "step": 6078 + }, + { + "epoch": 0.51, + "learning_rate": 1.0207292869839343e-05, + "loss": 0.46, + "step": 6079 + }, + { + "epoch": 0.51, + "learning_rate": 1.020458353973493e-05, + "loss": 0.4641, + "step": 6080 + }, + { + "epoch": 0.51, + "learning_rate": 1.0201874194606748e-05, + "loss": 0.4703, + "step": 6081 + }, + { + "epoch": 0.51, + "learning_rate": 1.019916483465377e-05, + "loss": 0.4775, + "step": 6082 + }, + { + "epoch": 0.51, + "learning_rate": 1.019645546007495e-05, + "loss": 0.4857, + "step": 6083 + }, + { + "epoch": 0.51, + "learning_rate": 1.0193746071069262e-05, + "loss": 0.4703, + "step": 6084 + }, + { + "epoch": 0.51, + "learning_rate": 1.0191036667835668e-05, + "loss": 0.4713, + "step": 6085 + }, + { + "epoch": 0.51, + "learning_rate": 1.0188327250573133e-05, + "loss": 0.4823, + "step": 6086 + }, + { + "epoch": 0.51, + "learning_rate": 1.0185617819480628e-05, + "loss": 0.4943, + "step": 6087 + }, + { + "epoch": 0.51, + "learning_rate": 1.0182908374757126e-05, + "loss": 0.4849, + "step": 6088 + }, + { + "epoch": 0.51, + "learning_rate": 1.0180198916601592e-05, + "loss": 0.4815, + "step": 6089 + }, + { + "epoch": 0.51, + "learning_rate": 1.0177489445212998e-05, + "loss": 0.486, + "step": 6090 + }, + { + "epoch": 0.51, + "learning_rate": 1.0174779960790318e-05, + "loss": 0.4575, + "step": 6091 + }, + { + "epoch": 0.51, + "learning_rate": 1.0172070463532524e-05, + "loss": 0.4709, + "step": 6092 + }, + { + "epoch": 0.51, + "learning_rate": 1.016936095363859e-05, + "loss": 0.4649, + "step": 6093 + }, + { + "epoch": 0.51, + "learning_rate": 1.0166651431307494e-05, + "loss": 0.4872, + "step": 6094 + }, + { + "epoch": 0.51, + "learning_rate": 1.0163941896738213e-05, + "loss": 0.4819, + "step": 6095 + }, + { + "epoch": 0.51, + "learning_rate": 1.0161232350129715e-05, + "loss": 0.4658, + "step": 6096 + }, + { + "epoch": 0.51, + "learning_rate": 1.0158522791680985e-05, + "loss": 0.4744, + "step": 6097 + }, + { + "epoch": 0.51, + "learning_rate": 1.0155813221591004e-05, + "loss": 0.4849, + "step": 6098 + }, + { + "epoch": 0.51, + "learning_rate": 1.0153103640058745e-05, + "loss": 0.4775, + "step": 6099 + }, + { + "epoch": 0.51, + "learning_rate": 1.0150394047283192e-05, + "loss": 0.4644, + "step": 6100 + }, + { + "epoch": 0.51, + "learning_rate": 1.0147684443463328e-05, + "loss": 0.4933, + "step": 6101 + }, + { + "epoch": 0.51, + "learning_rate": 1.0144974828798131e-05, + "loss": 0.4612, + "step": 6102 + }, + { + "epoch": 0.51, + "learning_rate": 1.0142265203486583e-05, + "loss": 0.4857, + "step": 6103 + }, + { + "epoch": 0.51, + "learning_rate": 1.0139555567727674e-05, + "loss": 0.4879, + "step": 6104 + }, + { + "epoch": 0.51, + "learning_rate": 1.0136845921720385e-05, + "loss": 0.4769, + "step": 6105 + }, + { + "epoch": 0.51, + "learning_rate": 1.0134136265663698e-05, + "loss": 0.4763, + "step": 6106 + }, + { + "epoch": 0.51, + "learning_rate": 1.01314265997566e-05, + "loss": 0.4778, + "step": 6107 + }, + { + "epoch": 0.51, + "learning_rate": 1.0128716924198083e-05, + "loss": 0.4715, + "step": 6108 + }, + { + "epoch": 0.51, + "learning_rate": 1.012600723918713e-05, + "loss": 0.468, + "step": 6109 + }, + { + "epoch": 0.51, + "learning_rate": 1.0123297544922728e-05, + "loss": 0.5026, + "step": 6110 + }, + { + "epoch": 0.51, + "learning_rate": 1.0120587841603868e-05, + "loss": 0.4965, + "step": 6111 + }, + { + "epoch": 0.51, + "learning_rate": 1.011787812942954e-05, + "loss": 0.4759, + "step": 6112 + }, + { + "epoch": 0.51, + "learning_rate": 1.0115168408598728e-05, + "loss": 0.4755, + "step": 6113 + }, + { + "epoch": 0.51, + "learning_rate": 1.011245867931043e-05, + "loss": 0.4671, + "step": 6114 + }, + { + "epoch": 0.51, + "learning_rate": 1.0109748941763635e-05, + "loss": 0.4646, + "step": 6115 + }, + { + "epoch": 0.51, + "learning_rate": 1.0107039196157335e-05, + "loss": 0.4868, + "step": 6116 + }, + { + "epoch": 0.51, + "learning_rate": 1.010432944269052e-05, + "loss": 0.4626, + "step": 6117 + }, + { + "epoch": 0.51, + "learning_rate": 1.0101619681562183e-05, + "loss": 0.4982, + "step": 6118 + }, + { + "epoch": 0.51, + "learning_rate": 1.0098909912971322e-05, + "loss": 0.4729, + "step": 6119 + }, + { + "epoch": 0.51, + "learning_rate": 1.0096200137116924e-05, + "loss": 0.4953, + "step": 6120 + }, + { + "epoch": 0.51, + "learning_rate": 1.0093490354197994e-05, + "loss": 0.4823, + "step": 6121 + }, + { + "epoch": 0.51, + "learning_rate": 1.0090780564413518e-05, + "loss": 0.4974, + "step": 6122 + }, + { + "epoch": 0.51, + "learning_rate": 1.0088070767962497e-05, + "loss": 0.4955, + "step": 6123 + }, + { + "epoch": 0.51, + "learning_rate": 1.0085360965043923e-05, + "loss": 0.4789, + "step": 6124 + }, + { + "epoch": 0.51, + "learning_rate": 1.0082651155856795e-05, + "loss": 0.4786, + "step": 6125 + }, + { + "epoch": 0.51, + "learning_rate": 1.007994134060011e-05, + "loss": 0.4877, + "step": 6126 + }, + { + "epoch": 0.51, + "learning_rate": 1.0077231519472866e-05, + "loss": 0.4656, + "step": 6127 + }, + { + "epoch": 0.51, + "learning_rate": 1.007452169267406e-05, + "loss": 0.4981, + "step": 6128 + }, + { + "epoch": 0.51, + "learning_rate": 1.0071811860402692e-05, + "loss": 0.5001, + "step": 6129 + }, + { + "epoch": 0.51, + "learning_rate": 1.0069102022857757e-05, + "loss": 0.4817, + "step": 6130 + }, + { + "epoch": 0.51, + "learning_rate": 1.0066392180238258e-05, + "loss": 0.4879, + "step": 6131 + }, + { + "epoch": 0.51, + "learning_rate": 1.0063682332743196e-05, + "loss": 0.4897, + "step": 6132 + }, + { + "epoch": 0.51, + "learning_rate": 1.0060972480571565e-05, + "loss": 0.4781, + "step": 6133 + }, + { + "epoch": 0.51, + "learning_rate": 1.0058262623922368e-05, + "loss": 0.4542, + "step": 6134 + }, + { + "epoch": 0.51, + "learning_rate": 1.005555276299461e-05, + "loss": 0.4887, + "step": 6135 + }, + { + "epoch": 0.51, + "learning_rate": 1.0052842897987288e-05, + "loss": 0.4949, + "step": 6136 + }, + { + "epoch": 0.51, + "learning_rate": 1.0050133029099401e-05, + "loss": 0.4703, + "step": 6137 + }, + { + "epoch": 0.51, + "learning_rate": 1.0047423156529952e-05, + "loss": 0.4776, + "step": 6138 + }, + { + "epoch": 0.51, + "learning_rate": 1.0044713280477946e-05, + "loss": 0.4973, + "step": 6139 + }, + { + "epoch": 0.51, + "learning_rate": 1.0042003401142383e-05, + "loss": 0.4845, + "step": 6140 + }, + { + "epoch": 0.51, + "learning_rate": 1.0039293518722262e-05, + "loss": 0.4794, + "step": 6141 + }, + { + "epoch": 0.51, + "learning_rate": 1.0036583633416593e-05, + "loss": 0.4974, + "step": 6142 + }, + { + "epoch": 0.51, + "learning_rate": 1.0033873745424369e-05, + "loss": 0.4832, + "step": 6143 + }, + { + "epoch": 0.51, + "learning_rate": 1.00311638549446e-05, + "loss": 0.4864, + "step": 6144 + }, + { + "epoch": 0.51, + "learning_rate": 1.0028453962176287e-05, + "loss": 0.4641, + "step": 6145 + }, + { + "epoch": 0.51, + "learning_rate": 1.0025744067318435e-05, + "loss": 0.4801, + "step": 6146 + }, + { + "epoch": 0.51, + "learning_rate": 1.0023034170570044e-05, + "loss": 0.4759, + "step": 6147 + }, + { + "epoch": 0.51, + "learning_rate": 1.0020324272130117e-05, + "loss": 0.4816, + "step": 6148 + }, + { + "epoch": 0.51, + "learning_rate": 1.0017614372197667e-05, + "loss": 0.4867, + "step": 6149 + }, + { + "epoch": 0.51, + "learning_rate": 1.0014904470971686e-05, + "loss": 0.4779, + "step": 6150 + }, + { + "epoch": 0.51, + "learning_rate": 1.0012194568651184e-05, + "loss": 0.4897, + "step": 6151 + }, + { + "epoch": 0.51, + "learning_rate": 1.0009484665435163e-05, + "loss": 0.4805, + "step": 6152 + }, + { + "epoch": 0.51, + "learning_rate": 1.0006774761522626e-05, + "loss": 0.4745, + "step": 6153 + }, + { + "epoch": 0.51, + "learning_rate": 1.000406485711258e-05, + "loss": 0.4776, + "step": 6154 + }, + { + "epoch": 0.51, + "learning_rate": 1.0001354952404027e-05, + "loss": 0.4708, + "step": 6155 + }, + { + "epoch": 0.52, + "learning_rate": 9.998645047595975e-06, + "loss": 0.4719, + "step": 6156 + }, + { + "epoch": 0.52, + "learning_rate": 9.995935142887424e-06, + "loss": 0.4778, + "step": 6157 + }, + { + "epoch": 0.52, + "learning_rate": 9.993225238477377e-06, + "loss": 0.479, + "step": 6158 + }, + { + "epoch": 0.52, + "learning_rate": 9.99051533456484e-06, + "loss": 0.4616, + "step": 6159 + }, + { + "epoch": 0.52, + "learning_rate": 9.987805431348818e-06, + "loss": 0.4924, + "step": 6160 + }, + { + "epoch": 0.52, + "learning_rate": 9.985095529028317e-06, + "loss": 0.4886, + "step": 6161 + }, + { + "epoch": 0.52, + "learning_rate": 9.982385627802338e-06, + "loss": 0.473, + "step": 6162 + }, + { + "epoch": 0.52, + "learning_rate": 9.979675727869884e-06, + "loss": 0.5046, + "step": 6163 + }, + { + "epoch": 0.52, + "learning_rate": 9.976965829429958e-06, + "loss": 0.4845, + "step": 6164 + }, + { + "epoch": 0.52, + "learning_rate": 9.97425593268157e-06, + "loss": 0.4805, + "step": 6165 + }, + { + "epoch": 0.52, + "learning_rate": 9.971546037823713e-06, + "loss": 0.4887, + "step": 6166 + }, + { + "epoch": 0.52, + "learning_rate": 9.968836145055402e-06, + "loss": 0.4882, + "step": 6167 + }, + { + "epoch": 0.52, + "learning_rate": 9.966126254575634e-06, + "loss": 0.4744, + "step": 6168 + }, + { + "epoch": 0.52, + "learning_rate": 9.963416366583412e-06, + "loss": 0.4752, + "step": 6169 + }, + { + "epoch": 0.52, + "learning_rate": 9.960706481277742e-06, + "loss": 0.4858, + "step": 6170 + }, + { + "epoch": 0.52, + "learning_rate": 9.957996598857622e-06, + "loss": 0.4589, + "step": 6171 + }, + { + "epoch": 0.52, + "learning_rate": 9.955286719522059e-06, + "loss": 0.4713, + "step": 6172 + }, + { + "epoch": 0.52, + "learning_rate": 9.952576843470048e-06, + "loss": 0.5407, + "step": 6173 + }, + { + "epoch": 0.52, + "learning_rate": 9.949866970900602e-06, + "loss": 0.4929, + "step": 6174 + }, + { + "epoch": 0.52, + "learning_rate": 9.947157102012716e-06, + "loss": 0.4734, + "step": 6175 + }, + { + "epoch": 0.52, + "learning_rate": 9.944447237005392e-06, + "loss": 0.4758, + "step": 6176 + }, + { + "epoch": 0.52, + "learning_rate": 9.941737376077634e-06, + "loss": 0.4628, + "step": 6177 + }, + { + "epoch": 0.52, + "learning_rate": 9.93902751942844e-06, + "loss": 0.4739, + "step": 6178 + }, + { + "epoch": 0.52, + "learning_rate": 9.93631766725681e-06, + "loss": 0.4739, + "step": 6179 + }, + { + "epoch": 0.52, + "learning_rate": 9.93360781976174e-06, + "loss": 0.488, + "step": 6180 + }, + { + "epoch": 0.52, + "learning_rate": 9.930897977142245e-06, + "loss": 0.484, + "step": 6181 + }, + { + "epoch": 0.52, + "learning_rate": 9.928188139597313e-06, + "loss": 0.4858, + "step": 6182 + }, + { + "epoch": 0.52, + "learning_rate": 9.925478307325944e-06, + "loss": 0.4791, + "step": 6183 + }, + { + "epoch": 0.52, + "learning_rate": 9.922768480527138e-06, + "loss": 0.4836, + "step": 6184 + }, + { + "epoch": 0.52, + "learning_rate": 9.920058659399895e-06, + "loss": 0.471, + "step": 6185 + }, + { + "epoch": 0.52, + "learning_rate": 9.91734884414321e-06, + "loss": 0.4773, + "step": 6186 + }, + { + "epoch": 0.52, + "learning_rate": 9.914639034956079e-06, + "loss": 0.4778, + "step": 6187 + }, + { + "epoch": 0.52, + "learning_rate": 9.911929232037507e-06, + "loss": 0.4983, + "step": 6188 + }, + { + "epoch": 0.52, + "learning_rate": 9.909219435586485e-06, + "loss": 0.4768, + "step": 6189 + }, + { + "epoch": 0.52, + "learning_rate": 9.906509645802009e-06, + "loss": 0.4848, + "step": 6190 + }, + { + "epoch": 0.52, + "learning_rate": 9.903799862883077e-06, + "loss": 0.4802, + "step": 6191 + }, + { + "epoch": 0.52, + "learning_rate": 9.901090087028685e-06, + "loss": 0.4775, + "step": 6192 + }, + { + "epoch": 0.52, + "learning_rate": 9.898380318437822e-06, + "loss": 0.4846, + "step": 6193 + }, + { + "epoch": 0.52, + "learning_rate": 9.895670557309484e-06, + "loss": 0.4832, + "step": 6194 + }, + { + "epoch": 0.52, + "learning_rate": 9.892960803842668e-06, + "loss": 0.4866, + "step": 6195 + }, + { + "epoch": 0.52, + "learning_rate": 9.890251058236368e-06, + "loss": 0.4776, + "step": 6196 + }, + { + "epoch": 0.52, + "learning_rate": 9.887541320689573e-06, + "loss": 0.4772, + "step": 6197 + }, + { + "epoch": 0.52, + "learning_rate": 9.884831591401276e-06, + "loss": 0.5, + "step": 6198 + }, + { + "epoch": 0.52, + "learning_rate": 9.882121870570465e-06, + "loss": 0.4832, + "step": 6199 + }, + { + "epoch": 0.52, + "learning_rate": 9.879412158396134e-06, + "loss": 0.4802, + "step": 6200 + }, + { + "epoch": 0.52, + "learning_rate": 9.876702455077272e-06, + "loss": 0.4718, + "step": 6201 + }, + { + "epoch": 0.52, + "learning_rate": 9.873992760812871e-06, + "loss": 0.4742, + "step": 6202 + }, + { + "epoch": 0.52, + "learning_rate": 9.87128307580192e-06, + "loss": 0.4717, + "step": 6203 + }, + { + "epoch": 0.52, + "learning_rate": 9.868573400243402e-06, + "loss": 0.4813, + "step": 6204 + }, + { + "epoch": 0.52, + "learning_rate": 9.865863734336305e-06, + "loss": 0.4895, + "step": 6205 + }, + { + "epoch": 0.52, + "learning_rate": 9.86315407827962e-06, + "loss": 0.4889, + "step": 6206 + }, + { + "epoch": 0.52, + "learning_rate": 9.860444432272328e-06, + "loss": 0.4873, + "step": 6207 + }, + { + "epoch": 0.52, + "learning_rate": 9.857734796513417e-06, + "loss": 0.4915, + "step": 6208 + }, + { + "epoch": 0.52, + "learning_rate": 9.855025171201874e-06, + "loss": 0.4696, + "step": 6209 + }, + { + "epoch": 0.52, + "learning_rate": 9.852315556536674e-06, + "loss": 0.4605, + "step": 6210 + }, + { + "epoch": 0.52, + "learning_rate": 9.84960595271681e-06, + "loss": 0.4808, + "step": 6211 + }, + { + "epoch": 0.52, + "learning_rate": 9.846896359941258e-06, + "loss": 0.4867, + "step": 6212 + }, + { + "epoch": 0.52, + "learning_rate": 9.844186778409002e-06, + "loss": 0.4805, + "step": 6213 + }, + { + "epoch": 0.52, + "learning_rate": 9.841477208319015e-06, + "loss": 0.4754, + "step": 6214 + }, + { + "epoch": 0.52, + "learning_rate": 9.838767649870287e-06, + "loss": 0.4691, + "step": 6215 + }, + { + "epoch": 0.52, + "learning_rate": 9.83605810326179e-06, + "loss": 0.4701, + "step": 6216 + }, + { + "epoch": 0.52, + "learning_rate": 9.833348568692507e-06, + "loss": 0.4799, + "step": 6217 + }, + { + "epoch": 0.52, + "learning_rate": 9.830639046361412e-06, + "loss": 0.4803, + "step": 6218 + }, + { + "epoch": 0.52, + "learning_rate": 9.82792953646748e-06, + "loss": 0.4602, + "step": 6219 + }, + { + "epoch": 0.52, + "learning_rate": 9.825220039209687e-06, + "loss": 0.4757, + "step": 6220 + }, + { + "epoch": 0.52, + "learning_rate": 9.822510554787004e-06, + "loss": 0.4817, + "step": 6221 + }, + { + "epoch": 0.52, + "learning_rate": 9.819801083398411e-06, + "loss": 0.4772, + "step": 6222 + }, + { + "epoch": 0.52, + "learning_rate": 9.817091625242879e-06, + "loss": 0.4876, + "step": 6223 + }, + { + "epoch": 0.52, + "learning_rate": 9.814382180519375e-06, + "loss": 0.4803, + "step": 6224 + }, + { + "epoch": 0.52, + "learning_rate": 9.81167274942687e-06, + "loss": 0.4761, + "step": 6225 + }, + { + "epoch": 0.52, + "learning_rate": 9.808963332164337e-06, + "loss": 0.4727, + "step": 6226 + }, + { + "epoch": 0.52, + "learning_rate": 9.806253928930743e-06, + "loss": 0.468, + "step": 6227 + }, + { + "epoch": 0.52, + "learning_rate": 9.80354453992505e-06, + "loss": 0.4583, + "step": 6228 + }, + { + "epoch": 0.52, + "learning_rate": 9.800835165346234e-06, + "loss": 0.4972, + "step": 6229 + }, + { + "epoch": 0.52, + "learning_rate": 9.798125805393255e-06, + "loss": 0.4874, + "step": 6230 + }, + { + "epoch": 0.52, + "learning_rate": 9.795416460265074e-06, + "loss": 0.4627, + "step": 6231 + }, + { + "epoch": 0.52, + "learning_rate": 9.79270713016066e-06, + "loss": 0.5072, + "step": 6232 + }, + { + "epoch": 0.52, + "learning_rate": 9.789997815278973e-06, + "loss": 0.4845, + "step": 6233 + }, + { + "epoch": 0.52, + "learning_rate": 9.787288515818968e-06, + "loss": 0.4799, + "step": 6234 + }, + { + "epoch": 0.52, + "learning_rate": 9.784579231979612e-06, + "loss": 0.47, + "step": 6235 + }, + { + "epoch": 0.52, + "learning_rate": 9.781869963959861e-06, + "loss": 0.4865, + "step": 6236 + }, + { + "epoch": 0.52, + "learning_rate": 9.779160711958673e-06, + "loss": 0.4727, + "step": 6237 + }, + { + "epoch": 0.52, + "learning_rate": 9.776451476175006e-06, + "loss": 0.4904, + "step": 6238 + }, + { + "epoch": 0.52, + "learning_rate": 9.773742256807812e-06, + "loss": 0.4865, + "step": 6239 + }, + { + "epoch": 0.52, + "learning_rate": 9.771033054056044e-06, + "loss": 0.4669, + "step": 6240 + }, + { + "epoch": 0.52, + "learning_rate": 9.768323868118656e-06, + "loss": 0.4877, + "step": 6241 + }, + { + "epoch": 0.52, + "learning_rate": 9.765614699194598e-06, + "loss": 0.469, + "step": 6242 + }, + { + "epoch": 0.52, + "learning_rate": 9.762905547482825e-06, + "loss": 0.473, + "step": 6243 + }, + { + "epoch": 0.52, + "learning_rate": 9.760196413182283e-06, + "loss": 0.4738, + "step": 6244 + }, + { + "epoch": 0.52, + "learning_rate": 9.757487296491918e-06, + "loss": 0.4813, + "step": 6245 + }, + { + "epoch": 0.52, + "learning_rate": 9.754778197610674e-06, + "loss": 0.4992, + "step": 6246 + }, + { + "epoch": 0.52, + "learning_rate": 9.752069116737504e-06, + "loss": 0.4679, + "step": 6247 + }, + { + "epoch": 0.52, + "learning_rate": 9.74936005407134e-06, + "loss": 0.456, + "step": 6248 + }, + { + "epoch": 0.52, + "learning_rate": 9.746651009811137e-06, + "loss": 0.4749, + "step": 6249 + }, + { + "epoch": 0.52, + "learning_rate": 9.74394198415583e-06, + "loss": 0.4758, + "step": 6250 + }, + { + "epoch": 0.52, + "learning_rate": 9.741232977304356e-06, + "loss": 0.4719, + "step": 6251 + }, + { + "epoch": 0.52, + "learning_rate": 9.738523989455659e-06, + "loss": 0.4639, + "step": 6252 + }, + { + "epoch": 0.52, + "learning_rate": 9.735815020808672e-06, + "loss": 0.4738, + "step": 6253 + }, + { + "epoch": 0.52, + "learning_rate": 9.733106071562332e-06, + "loss": 0.4639, + "step": 6254 + }, + { + "epoch": 0.52, + "learning_rate": 9.730397141915567e-06, + "loss": 0.4905, + "step": 6255 + }, + { + "epoch": 0.52, + "learning_rate": 9.727688232067318e-06, + "loss": 0.4697, + "step": 6256 + }, + { + "epoch": 0.52, + "learning_rate": 9.72497934221651e-06, + "loss": 0.4867, + "step": 6257 + }, + { + "epoch": 0.52, + "learning_rate": 9.722270472562078e-06, + "loss": 0.4721, + "step": 6258 + }, + { + "epoch": 0.52, + "learning_rate": 9.71956162330295e-06, + "loss": 0.4716, + "step": 6259 + }, + { + "epoch": 0.52, + "learning_rate": 9.716852794638046e-06, + "loss": 0.4712, + "step": 6260 + }, + { + "epoch": 0.52, + "learning_rate": 9.714143986766294e-06, + "loss": 0.4798, + "step": 6261 + }, + { + "epoch": 0.52, + "learning_rate": 9.711435199886618e-06, + "loss": 0.4679, + "step": 6262 + }, + { + "epoch": 0.52, + "learning_rate": 9.708726434197944e-06, + "loss": 0.4605, + "step": 6263 + }, + { + "epoch": 0.52, + "learning_rate": 9.706017689899189e-06, + "loss": 0.4812, + "step": 6264 + }, + { + "epoch": 0.52, + "learning_rate": 9.703308967189273e-06, + "loss": 0.4768, + "step": 6265 + }, + { + "epoch": 0.52, + "learning_rate": 9.700600266267109e-06, + "loss": 0.4735, + "step": 6266 + }, + { + "epoch": 0.52, + "learning_rate": 9.697891587331618e-06, + "loss": 0.4862, + "step": 6267 + }, + { + "epoch": 0.52, + "learning_rate": 9.695182930581715e-06, + "loss": 0.4751, + "step": 6268 + }, + { + "epoch": 0.52, + "learning_rate": 9.692474296216303e-06, + "loss": 0.4512, + "step": 6269 + }, + { + "epoch": 0.52, + "learning_rate": 9.689765684434305e-06, + "loss": 0.4947, + "step": 6270 + }, + { + "epoch": 0.52, + "learning_rate": 9.687057095434624e-06, + "loss": 0.4816, + "step": 6271 + }, + { + "epoch": 0.52, + "learning_rate": 9.684348529416166e-06, + "loss": 0.4744, + "step": 6272 + }, + { + "epoch": 0.52, + "learning_rate": 9.681639986577841e-06, + "loss": 0.4612, + "step": 6273 + }, + { + "epoch": 0.52, + "learning_rate": 9.678931467118553e-06, + "loss": 0.4734, + "step": 6274 + }, + { + "epoch": 0.52, + "learning_rate": 9.676222971237197e-06, + "loss": 0.4665, + "step": 6275 + }, + { + "epoch": 0.53, + "learning_rate": 9.673514499132683e-06, + "loss": 0.4761, + "step": 6276 + }, + { + "epoch": 0.53, + "learning_rate": 9.670806051003906e-06, + "loss": 0.4849, + "step": 6277 + }, + { + "epoch": 0.53, + "learning_rate": 9.668097627049765e-06, + "loss": 0.479, + "step": 6278 + }, + { + "epoch": 0.53, + "learning_rate": 9.665389227469152e-06, + "loss": 0.471, + "step": 6279 + }, + { + "epoch": 0.53, + "learning_rate": 9.662680852460963e-06, + "loss": 0.4824, + "step": 6280 + }, + { + "epoch": 0.53, + "learning_rate": 9.659972502224089e-06, + "loss": 0.4746, + "step": 6281 + }, + { + "epoch": 0.53, + "learning_rate": 9.657264176957419e-06, + "loss": 0.4834, + "step": 6282 + }, + { + "epoch": 0.53, + "learning_rate": 9.654555876859841e-06, + "loss": 0.4928, + "step": 6283 + }, + { + "epoch": 0.53, + "learning_rate": 9.651847602130247e-06, + "loss": 0.4866, + "step": 6284 + }, + { + "epoch": 0.53, + "learning_rate": 9.649139352967515e-06, + "loss": 0.4769, + "step": 6285 + }, + { + "epoch": 0.53, + "learning_rate": 9.646431129570531e-06, + "loss": 0.4794, + "step": 6286 + }, + { + "epoch": 0.53, + "learning_rate": 9.643722932138172e-06, + "loss": 0.4776, + "step": 6287 + }, + { + "epoch": 0.53, + "learning_rate": 9.64101476086932e-06, + "loss": 0.4743, + "step": 6288 + }, + { + "epoch": 0.53, + "learning_rate": 9.638306615962847e-06, + "loss": 0.4793, + "step": 6289 + }, + { + "epoch": 0.53, + "learning_rate": 9.635598497617636e-06, + "loss": 0.4823, + "step": 6290 + }, + { + "epoch": 0.53, + "learning_rate": 9.632890406032556e-06, + "loss": 0.467, + "step": 6291 + }, + { + "epoch": 0.53, + "learning_rate": 9.630182341406477e-06, + "loss": 0.4598, + "step": 6292 + }, + { + "epoch": 0.53, + "learning_rate": 9.627474303938267e-06, + "loss": 0.4697, + "step": 6293 + }, + { + "epoch": 0.53, + "learning_rate": 9.624766293826798e-06, + "loss": 0.4777, + "step": 6294 + }, + { + "epoch": 0.53, + "learning_rate": 9.62205831127093e-06, + "loss": 0.4762, + "step": 6295 + }, + { + "epoch": 0.53, + "learning_rate": 9.619350356469524e-06, + "loss": 0.4949, + "step": 6296 + }, + { + "epoch": 0.53, + "learning_rate": 9.616642429621449e-06, + "loss": 0.4867, + "step": 6297 + }, + { + "epoch": 0.53, + "learning_rate": 9.613934530925556e-06, + "loss": 0.4907, + "step": 6298 + }, + { + "epoch": 0.53, + "learning_rate": 9.611226660580709e-06, + "loss": 0.4929, + "step": 6299 + }, + { + "epoch": 0.53, + "learning_rate": 9.60851881878576e-06, + "loss": 0.4616, + "step": 6300 + }, + { + "epoch": 0.53, + "learning_rate": 9.605811005739558e-06, + "loss": 0.4869, + "step": 6301 + }, + { + "epoch": 0.53, + "learning_rate": 9.603103221640956e-06, + "loss": 0.4846, + "step": 6302 + }, + { + "epoch": 0.53, + "learning_rate": 9.600395466688801e-06, + "loss": 0.4695, + "step": 6303 + }, + { + "epoch": 0.53, + "learning_rate": 9.597687741081942e-06, + "loss": 0.4904, + "step": 6304 + }, + { + "epoch": 0.53, + "learning_rate": 9.594980045019224e-06, + "loss": 0.4837, + "step": 6305 + }, + { + "epoch": 0.53, + "learning_rate": 9.592272378699486e-06, + "loss": 0.4682, + "step": 6306 + }, + { + "epoch": 0.53, + "learning_rate": 9.589564742321569e-06, + "loss": 0.4882, + "step": 6307 + }, + { + "epoch": 0.53, + "learning_rate": 9.586857136084309e-06, + "loss": 0.483, + "step": 6308 + }, + { + "epoch": 0.53, + "learning_rate": 9.58414956018654e-06, + "loss": 0.4886, + "step": 6309 + }, + { + "epoch": 0.53, + "learning_rate": 9.581442014827101e-06, + "loss": 0.491, + "step": 6310 + }, + { + "epoch": 0.53, + "learning_rate": 9.57873450020482e-06, + "loss": 0.4758, + "step": 6311 + }, + { + "epoch": 0.53, + "learning_rate": 9.576027016518527e-06, + "loss": 0.4617, + "step": 6312 + }, + { + "epoch": 0.53, + "learning_rate": 9.573319563967043e-06, + "loss": 0.4783, + "step": 6313 + }, + { + "epoch": 0.53, + "learning_rate": 9.570612142749196e-06, + "loss": 0.4769, + "step": 6314 + }, + { + "epoch": 0.53, + "learning_rate": 9.56790475306381e-06, + "loss": 0.4733, + "step": 6315 + }, + { + "epoch": 0.53, + "learning_rate": 9.565197395109694e-06, + "loss": 0.4816, + "step": 6316 + }, + { + "epoch": 0.53, + "learning_rate": 9.56249006908568e-06, + "loss": 0.4784, + "step": 6317 + }, + { + "epoch": 0.53, + "learning_rate": 9.559782775190574e-06, + "loss": 0.4769, + "step": 6318 + }, + { + "epoch": 0.53, + "learning_rate": 9.55707551362319e-06, + "loss": 0.4679, + "step": 6319 + }, + { + "epoch": 0.53, + "learning_rate": 9.554368284582339e-06, + "loss": 0.4917, + "step": 6320 + }, + { + "epoch": 0.53, + "learning_rate": 9.551661088266825e-06, + "loss": 0.4883, + "step": 6321 + }, + { + "epoch": 0.53, + "learning_rate": 9.548953924875459e-06, + "loss": 0.4608, + "step": 6322 + }, + { + "epoch": 0.53, + "learning_rate": 9.546246794607037e-06, + "loss": 0.4799, + "step": 6323 + }, + { + "epoch": 0.53, + "learning_rate": 9.543539697660363e-06, + "loss": 0.4842, + "step": 6324 + }, + { + "epoch": 0.53, + "learning_rate": 9.540832634234238e-06, + "loss": 0.4864, + "step": 6325 + }, + { + "epoch": 0.53, + "learning_rate": 9.538125604527455e-06, + "loss": 0.4847, + "step": 6326 + }, + { + "epoch": 0.53, + "learning_rate": 9.535418608738808e-06, + "loss": 0.5013, + "step": 6327 + }, + { + "epoch": 0.53, + "learning_rate": 9.53271164706708e-06, + "loss": 0.4738, + "step": 6328 + }, + { + "epoch": 0.53, + "learning_rate": 9.53000471971107e-06, + "loss": 0.4796, + "step": 6329 + }, + { + "epoch": 0.53, + "learning_rate": 9.527297826869553e-06, + "loss": 0.4594, + "step": 6330 + }, + { + "epoch": 0.53, + "learning_rate": 9.524590968741324e-06, + "loss": 0.4737, + "step": 6331 + }, + { + "epoch": 0.53, + "learning_rate": 9.521884145525153e-06, + "loss": 0.4757, + "step": 6332 + }, + { + "epoch": 0.53, + "learning_rate": 9.519177357419824e-06, + "loss": 0.5014, + "step": 6333 + }, + { + "epoch": 0.53, + "learning_rate": 9.516470604624109e-06, + "loss": 0.4906, + "step": 6334 + }, + { + "epoch": 0.53, + "learning_rate": 9.513763887336781e-06, + "loss": 0.4728, + "step": 6335 + }, + { + "epoch": 0.53, + "learning_rate": 9.511057205756614e-06, + "loss": 0.4792, + "step": 6336 + }, + { + "epoch": 0.53, + "learning_rate": 9.508350560082364e-06, + "loss": 0.4579, + "step": 6337 + }, + { + "epoch": 0.53, + "learning_rate": 9.505643950512811e-06, + "loss": 0.4688, + "step": 6338 + }, + { + "epoch": 0.53, + "learning_rate": 9.502937377246707e-06, + "loss": 0.489, + "step": 6339 + }, + { + "epoch": 0.53, + "learning_rate": 9.500230840482817e-06, + "loss": 0.4965, + "step": 6340 + }, + { + "epoch": 0.53, + "learning_rate": 9.497524340419896e-06, + "loss": 0.4631, + "step": 6341 + }, + { + "epoch": 0.53, + "learning_rate": 9.494817877256696e-06, + "loss": 0.4601, + "step": 6342 + }, + { + "epoch": 0.53, + "learning_rate": 9.49211145119197e-06, + "loss": 0.4815, + "step": 6343 + }, + { + "epoch": 0.53, + "learning_rate": 9.489405062424464e-06, + "loss": 0.4815, + "step": 6344 + }, + { + "epoch": 0.53, + "learning_rate": 9.486698711152928e-06, + "loss": 0.489, + "step": 6345 + }, + { + "epoch": 0.53, + "learning_rate": 9.483992397576106e-06, + "loss": 0.4806, + "step": 6346 + }, + { + "epoch": 0.53, + "learning_rate": 9.481286121892734e-06, + "loss": 0.4701, + "step": 6347 + }, + { + "epoch": 0.53, + "learning_rate": 9.478579884301554e-06, + "loss": 0.4687, + "step": 6348 + }, + { + "epoch": 0.53, + "learning_rate": 9.475873685001295e-06, + "loss": 0.4647, + "step": 6349 + }, + { + "epoch": 0.53, + "learning_rate": 9.473167524190692e-06, + "loss": 0.4665, + "step": 6350 + }, + { + "epoch": 0.53, + "learning_rate": 9.470461402068478e-06, + "loss": 0.4681, + "step": 6351 + }, + { + "epoch": 0.53, + "learning_rate": 9.467755318833376e-06, + "loss": 0.482, + "step": 6352 + }, + { + "epoch": 0.53, + "learning_rate": 9.46504927468411e-06, + "loss": 0.4852, + "step": 6353 + }, + { + "epoch": 0.53, + "learning_rate": 9.462343269819398e-06, + "loss": 0.4887, + "step": 6354 + }, + { + "epoch": 0.53, + "learning_rate": 9.459637304437962e-06, + "loss": 0.4993, + "step": 6355 + }, + { + "epoch": 0.53, + "learning_rate": 9.456931378738515e-06, + "loss": 0.4926, + "step": 6356 + }, + { + "epoch": 0.53, + "learning_rate": 9.454225492919765e-06, + "loss": 0.4916, + "step": 6357 + }, + { + "epoch": 0.53, + "learning_rate": 9.451519647180427e-06, + "loss": 0.4718, + "step": 6358 + }, + { + "epoch": 0.53, + "learning_rate": 9.448813841719207e-06, + "loss": 0.4794, + "step": 6359 + }, + { + "epoch": 0.53, + "learning_rate": 9.446108076734803e-06, + "loss": 0.461, + "step": 6360 + }, + { + "epoch": 0.53, + "learning_rate": 9.44340235242592e-06, + "loss": 0.486, + "step": 6361 + }, + { + "epoch": 0.53, + "learning_rate": 9.440696668991253e-06, + "loss": 0.467, + "step": 6362 + }, + { + "epoch": 0.53, + "learning_rate": 9.437991026629497e-06, + "loss": 0.4657, + "step": 6363 + }, + { + "epoch": 0.53, + "learning_rate": 9.435285425539337e-06, + "loss": 0.4854, + "step": 6364 + }, + { + "epoch": 0.53, + "learning_rate": 9.43257986591947e-06, + "loss": 0.4839, + "step": 6365 + }, + { + "epoch": 0.53, + "learning_rate": 9.42987434796858e-06, + "loss": 0.4686, + "step": 6366 + }, + { + "epoch": 0.53, + "learning_rate": 9.427168871885345e-06, + "loss": 0.4639, + "step": 6367 + }, + { + "epoch": 0.53, + "learning_rate": 9.424463437868445e-06, + "loss": 0.4912, + "step": 6368 + }, + { + "epoch": 0.53, + "learning_rate": 9.421758046116557e-06, + "loss": 0.4673, + "step": 6369 + }, + { + "epoch": 0.53, + "learning_rate": 9.419052696828352e-06, + "loss": 0.4861, + "step": 6370 + }, + { + "epoch": 0.53, + "learning_rate": 9.416347390202499e-06, + "loss": 0.4816, + "step": 6371 + }, + { + "epoch": 0.53, + "learning_rate": 9.41364212643767e-06, + "loss": 0.4647, + "step": 6372 + }, + { + "epoch": 0.53, + "learning_rate": 9.410936905732522e-06, + "loss": 0.4781, + "step": 6373 + }, + { + "epoch": 0.53, + "learning_rate": 9.40823172828572e-06, + "loss": 0.4912, + "step": 6374 + }, + { + "epoch": 0.53, + "learning_rate": 9.405526594295915e-06, + "loss": 0.4641, + "step": 6375 + }, + { + "epoch": 0.53, + "learning_rate": 9.402821503961766e-06, + "loss": 0.4802, + "step": 6376 + }, + { + "epoch": 0.53, + "learning_rate": 9.400116457481924e-06, + "loss": 0.4938, + "step": 6377 + }, + { + "epoch": 0.53, + "learning_rate": 9.397411455055028e-06, + "loss": 0.4878, + "step": 6378 + }, + { + "epoch": 0.53, + "learning_rate": 9.394706496879733e-06, + "loss": 0.4762, + "step": 6379 + }, + { + "epoch": 0.53, + "learning_rate": 9.392001583154675e-06, + "loss": 0.4799, + "step": 6380 + }, + { + "epoch": 0.53, + "learning_rate": 9.389296714078493e-06, + "loss": 0.4966, + "step": 6381 + }, + { + "epoch": 0.53, + "learning_rate": 9.386591889849819e-06, + "loss": 0.4841, + "step": 6382 + }, + { + "epoch": 0.53, + "learning_rate": 9.383887110667285e-06, + "loss": 0.5037, + "step": 6383 + }, + { + "epoch": 0.53, + "learning_rate": 9.381182376729516e-06, + "loss": 0.4769, + "step": 6384 + }, + { + "epoch": 0.53, + "learning_rate": 9.378477688235144e-06, + "loss": 0.4716, + "step": 6385 + }, + { + "epoch": 0.53, + "learning_rate": 9.375773045382782e-06, + "loss": 0.4908, + "step": 6386 + }, + { + "epoch": 0.53, + "learning_rate": 9.373068448371054e-06, + "loss": 0.4506, + "step": 6387 + }, + { + "epoch": 0.53, + "learning_rate": 9.370363897398573e-06, + "loss": 0.4837, + "step": 6388 + }, + { + "epoch": 0.53, + "learning_rate": 9.367659392663947e-06, + "loss": 0.4797, + "step": 6389 + }, + { + "epoch": 0.53, + "learning_rate": 9.364954934365783e-06, + "loss": 0.4906, + "step": 6390 + }, + { + "epoch": 0.53, + "learning_rate": 9.362250522702685e-06, + "loss": 0.4653, + "step": 6391 + }, + { + "epoch": 0.53, + "learning_rate": 9.35954615787326e-06, + "loss": 0.4811, + "step": 6392 + }, + { + "epoch": 0.53, + "learning_rate": 9.356841840076102e-06, + "loss": 0.4746, + "step": 6393 + }, + { + "epoch": 0.53, + "learning_rate": 9.354137569509804e-06, + "loss": 0.4864, + "step": 6394 + }, + { + "epoch": 0.54, + "learning_rate": 9.351433346372955e-06, + "loss": 0.4882, + "step": 6395 + }, + { + "epoch": 0.54, + "learning_rate": 9.348729170864145e-06, + "loss": 0.4855, + "step": 6396 + }, + { + "epoch": 0.54, + "learning_rate": 9.346025043181955e-06, + "loss": 0.4606, + "step": 6397 + }, + { + "epoch": 0.54, + "learning_rate": 9.343320963524964e-06, + "loss": 0.482, + "step": 6398 + }, + { + "epoch": 0.54, + "learning_rate": 9.340616932091752e-06, + "loss": 0.4876, + "step": 6399 + }, + { + "epoch": 0.54, + "learning_rate": 9.33791294908089e-06, + "loss": 0.4936, + "step": 6400 + }, + { + "epoch": 0.54, + "learning_rate": 9.335209014690946e-06, + "loss": 0.495, + "step": 6401 + }, + { + "epoch": 0.54, + "learning_rate": 9.332505129120489e-06, + "loss": 0.4882, + "step": 6402 + }, + { + "epoch": 0.54, + "learning_rate": 9.32980129256808e-06, + "loss": 0.4871, + "step": 6403 + }, + { + "epoch": 0.54, + "learning_rate": 9.327097505232274e-06, + "loss": 0.4526, + "step": 6404 + }, + { + "epoch": 0.54, + "learning_rate": 9.324393767311625e-06, + "loss": 0.4816, + "step": 6405 + }, + { + "epoch": 0.54, + "learning_rate": 9.321690079004691e-06, + "loss": 0.4765, + "step": 6406 + }, + { + "epoch": 0.54, + "learning_rate": 9.318986440510018e-06, + "loss": 0.4737, + "step": 6407 + }, + { + "epoch": 0.54, + "learning_rate": 9.316282852026147e-06, + "loss": 0.4784, + "step": 6408 + }, + { + "epoch": 0.54, + "learning_rate": 9.313579313751621e-06, + "loss": 0.4744, + "step": 6409 + }, + { + "epoch": 0.54, + "learning_rate": 9.310875825884972e-06, + "loss": 0.4675, + "step": 6410 + }, + { + "epoch": 0.54, + "learning_rate": 9.308172388624739e-06, + "loss": 0.465, + "step": 6411 + }, + { + "epoch": 0.54, + "learning_rate": 9.305469002169442e-06, + "loss": 0.477, + "step": 6412 + }, + { + "epoch": 0.54, + "learning_rate": 9.30276566671762e-06, + "loss": 0.4649, + "step": 6413 + }, + { + "epoch": 0.54, + "learning_rate": 9.300062382467785e-06, + "loss": 0.4649, + "step": 6414 + }, + { + "epoch": 0.54, + "learning_rate": 9.29735914961846e-06, + "loss": 0.468, + "step": 6415 + }, + { + "epoch": 0.54, + "learning_rate": 9.294655968368153e-06, + "loss": 0.4863, + "step": 6416 + }, + { + "epoch": 0.54, + "learning_rate": 9.291952838915379e-06, + "loss": 0.4815, + "step": 6417 + }, + { + "epoch": 0.54, + "learning_rate": 9.289249761458643e-06, + "loss": 0.4916, + "step": 6418 + }, + { + "epoch": 0.54, + "learning_rate": 9.286546736196447e-06, + "loss": 0.4722, + "step": 6419 + }, + { + "epoch": 0.54, + "learning_rate": 9.283843763327293e-06, + "loss": 0.5097, + "step": 6420 + }, + { + "epoch": 0.54, + "learning_rate": 9.281140843049674e-06, + "loss": 0.4785, + "step": 6421 + }, + { + "epoch": 0.54, + "learning_rate": 9.278437975562083e-06, + "loss": 0.4712, + "step": 6422 + }, + { + "epoch": 0.54, + "learning_rate": 9.275735161063006e-06, + "loss": 0.4693, + "step": 6423 + }, + { + "epoch": 0.54, + "learning_rate": 9.273032399750925e-06, + "loss": 0.4631, + "step": 6424 + }, + { + "epoch": 0.54, + "learning_rate": 9.270329691824318e-06, + "loss": 0.4736, + "step": 6425 + }, + { + "epoch": 0.54, + "learning_rate": 9.267627037481667e-06, + "loss": 0.4763, + "step": 6426 + }, + { + "epoch": 0.54, + "learning_rate": 9.264924436921438e-06, + "loss": 0.475, + "step": 6427 + }, + { + "epoch": 0.54, + "learning_rate": 9.262221890342104e-06, + "loss": 0.5036, + "step": 6428 + }, + { + "epoch": 0.54, + "learning_rate": 9.259519397942125e-06, + "loss": 0.4682, + "step": 6429 + }, + { + "epoch": 0.54, + "learning_rate": 9.256816959919962e-06, + "loss": 0.4808, + "step": 6430 + }, + { + "epoch": 0.54, + "learning_rate": 9.254114576474068e-06, + "loss": 0.4676, + "step": 6431 + }, + { + "epoch": 0.54, + "learning_rate": 9.251412247802896e-06, + "loss": 0.4549, + "step": 6432 + }, + { + "epoch": 0.54, + "learning_rate": 9.248709974104897e-06, + "loss": 0.4904, + "step": 6433 + }, + { + "epoch": 0.54, + "learning_rate": 9.246007755578514e-06, + "loss": 0.4909, + "step": 6434 + }, + { + "epoch": 0.54, + "learning_rate": 9.243305592422184e-06, + "loss": 0.479, + "step": 6435 + }, + { + "epoch": 0.54, + "learning_rate": 9.240603484834347e-06, + "loss": 0.4879, + "step": 6436 + }, + { + "epoch": 0.54, + "learning_rate": 9.237901433013427e-06, + "loss": 0.4899, + "step": 6437 + }, + { + "epoch": 0.54, + "learning_rate": 9.235199437157858e-06, + "loss": 0.4525, + "step": 6438 + }, + { + "epoch": 0.54, + "learning_rate": 9.232497497466057e-06, + "loss": 0.4823, + "step": 6439 + }, + { + "epoch": 0.54, + "learning_rate": 9.229795614136452e-06, + "loss": 0.4723, + "step": 6440 + }, + { + "epoch": 0.54, + "learning_rate": 9.227093787367454e-06, + "loss": 0.4649, + "step": 6441 + }, + { + "epoch": 0.54, + "learning_rate": 9.224392017357471e-06, + "loss": 0.4885, + "step": 6442 + }, + { + "epoch": 0.54, + "learning_rate": 9.221690304304915e-06, + "loss": 0.4626, + "step": 6443 + }, + { + "epoch": 0.54, + "learning_rate": 9.218988648408187e-06, + "loss": 0.4568, + "step": 6444 + }, + { + "epoch": 0.54, + "learning_rate": 9.216287049865681e-06, + "loss": 0.4942, + "step": 6445 + }, + { + "epoch": 0.54, + "learning_rate": 9.213585508875792e-06, + "loss": 0.5012, + "step": 6446 + }, + { + "epoch": 0.54, + "learning_rate": 9.210884025636916e-06, + "loss": 0.4838, + "step": 6447 + }, + { + "epoch": 0.54, + "learning_rate": 9.208182600347432e-06, + "loss": 0.4744, + "step": 6448 + }, + { + "epoch": 0.54, + "learning_rate": 9.20548123320573e-06, + "loss": 0.4823, + "step": 6449 + }, + { + "epoch": 0.54, + "learning_rate": 9.20277992441018e-06, + "loss": 0.4897, + "step": 6450 + }, + { + "epoch": 0.54, + "learning_rate": 9.200078674159154e-06, + "loss": 0.4671, + "step": 6451 + }, + { + "epoch": 0.54, + "learning_rate": 9.197377482651023e-06, + "loss": 0.4986, + "step": 6452 + }, + { + "epoch": 0.54, + "learning_rate": 9.194676350084148e-06, + "loss": 0.4702, + "step": 6453 + }, + { + "epoch": 0.54, + "learning_rate": 9.191975276656898e-06, + "loss": 0.4758, + "step": 6454 + }, + { + "epoch": 0.54, + "learning_rate": 9.189274262567622e-06, + "loss": 0.4712, + "step": 6455 + }, + { + "epoch": 0.54, + "learning_rate": 9.186573308014672e-06, + "loss": 0.4757, + "step": 6456 + }, + { + "epoch": 0.54, + "learning_rate": 9.183872413196392e-06, + "loss": 0.4419, + "step": 6457 + }, + { + "epoch": 0.54, + "learning_rate": 9.181171578311132e-06, + "loss": 0.483, + "step": 6458 + }, + { + "epoch": 0.54, + "learning_rate": 9.17847080355722e-06, + "loss": 0.4725, + "step": 6459 + }, + { + "epoch": 0.54, + "learning_rate": 9.175770089133e-06, + "loss": 0.4854, + "step": 6460 + }, + { + "epoch": 0.54, + "learning_rate": 9.173069435236796e-06, + "loss": 0.5029, + "step": 6461 + }, + { + "epoch": 0.54, + "learning_rate": 9.170368842066932e-06, + "loss": 0.4741, + "step": 6462 + }, + { + "epoch": 0.54, + "learning_rate": 9.167668309821729e-06, + "loss": 0.4736, + "step": 6463 + }, + { + "epoch": 0.54, + "learning_rate": 9.164967838699504e-06, + "loss": 0.5017, + "step": 6464 + }, + { + "epoch": 0.54, + "learning_rate": 9.162267428898568e-06, + "loss": 0.4903, + "step": 6465 + }, + { + "epoch": 0.54, + "learning_rate": 9.159567080617226e-06, + "loss": 0.4764, + "step": 6466 + }, + { + "epoch": 0.54, + "learning_rate": 9.156866794053783e-06, + "loss": 0.4889, + "step": 6467 + }, + { + "epoch": 0.54, + "learning_rate": 9.154166569406537e-06, + "loss": 0.4664, + "step": 6468 + }, + { + "epoch": 0.54, + "learning_rate": 9.15146640687378e-06, + "loss": 0.494, + "step": 6469 + }, + { + "epoch": 0.54, + "learning_rate": 9.148766306653801e-06, + "loss": 0.4731, + "step": 6470 + }, + { + "epoch": 0.54, + "learning_rate": 9.146066268944883e-06, + "loss": 0.4908, + "step": 6471 + }, + { + "epoch": 0.54, + "learning_rate": 9.143366293945305e-06, + "loss": 0.4881, + "step": 6472 + }, + { + "epoch": 0.54, + "learning_rate": 9.140666381853343e-06, + "loss": 0.4623, + "step": 6473 + }, + { + "epoch": 0.54, + "learning_rate": 9.137966532867268e-06, + "loss": 0.4839, + "step": 6474 + }, + { + "epoch": 0.54, + "learning_rate": 9.135266747185348e-06, + "loss": 0.484, + "step": 6475 + }, + { + "epoch": 0.54, + "learning_rate": 9.132567025005842e-06, + "loss": 0.4819, + "step": 6476 + }, + { + "epoch": 0.54, + "learning_rate": 9.129867366527004e-06, + "loss": 0.4728, + "step": 6477 + }, + { + "epoch": 0.54, + "learning_rate": 9.127167771947086e-06, + "loss": 0.4608, + "step": 6478 + }, + { + "epoch": 0.54, + "learning_rate": 9.12446824146434e-06, + "loss": 0.4677, + "step": 6479 + }, + { + "epoch": 0.54, + "learning_rate": 9.121768775276997e-06, + "loss": 0.4838, + "step": 6480 + }, + { + "epoch": 0.54, + "learning_rate": 9.11906937358331e-06, + "loss": 0.4658, + "step": 6481 + }, + { + "epoch": 0.54, + "learning_rate": 9.116370036581504e-06, + "loss": 0.4829, + "step": 6482 + }, + { + "epoch": 0.54, + "learning_rate": 9.113670764469803e-06, + "loss": 0.4701, + "step": 6483 + }, + { + "epoch": 0.54, + "learning_rate": 9.110971557446437e-06, + "loss": 0.4751, + "step": 6484 + }, + { + "epoch": 0.54, + "learning_rate": 9.108272415709624e-06, + "loss": 0.4502, + "step": 6485 + }, + { + "epoch": 0.54, + "learning_rate": 9.105573339457574e-06, + "loss": 0.4784, + "step": 6486 + }, + { + "epoch": 0.54, + "learning_rate": 9.102874328888493e-06, + "loss": 0.4574, + "step": 6487 + }, + { + "epoch": 0.54, + "learning_rate": 9.100175384200595e-06, + "loss": 0.4764, + "step": 6488 + }, + { + "epoch": 0.54, + "learning_rate": 9.097476505592074e-06, + "loss": 0.4746, + "step": 6489 + }, + { + "epoch": 0.54, + "learning_rate": 9.094777693261124e-06, + "loss": 0.4867, + "step": 6490 + }, + { + "epoch": 0.54, + "learning_rate": 9.092078947405937e-06, + "loss": 0.4723, + "step": 6491 + }, + { + "epoch": 0.54, + "learning_rate": 9.089380268224694e-06, + "loss": 0.4829, + "step": 6492 + }, + { + "epoch": 0.54, + "learning_rate": 9.086681655915574e-06, + "loss": 0.4703, + "step": 6493 + }, + { + "epoch": 0.54, + "learning_rate": 9.083983110676755e-06, + "loss": 0.4804, + "step": 6494 + }, + { + "epoch": 0.54, + "learning_rate": 9.081284632706408e-06, + "loss": 0.4808, + "step": 6495 + }, + { + "epoch": 0.54, + "learning_rate": 9.078586222202698e-06, + "loss": 0.4923, + "step": 6496 + }, + { + "epoch": 0.54, + "learning_rate": 9.075887879363783e-06, + "loss": 0.4779, + "step": 6497 + }, + { + "epoch": 0.54, + "learning_rate": 9.073189604387815e-06, + "loss": 0.4824, + "step": 6498 + }, + { + "epoch": 0.54, + "learning_rate": 9.07049139747295e-06, + "loss": 0.4912, + "step": 6499 + }, + { + "epoch": 0.54, + "learning_rate": 9.06779325881733e-06, + "loss": 0.477, + "step": 6500 + }, + { + "epoch": 0.54, + "learning_rate": 9.065095188619096e-06, + "loss": 0.4758, + "step": 6501 + }, + { + "epoch": 0.54, + "learning_rate": 9.062397187076384e-06, + "loss": 0.467, + "step": 6502 + }, + { + "epoch": 0.54, + "learning_rate": 9.059699254387323e-06, + "loss": 0.4954, + "step": 6503 + }, + { + "epoch": 0.54, + "learning_rate": 9.057001390750035e-06, + "loss": 0.4689, + "step": 6504 + }, + { + "epoch": 0.54, + "learning_rate": 9.054303596362646e-06, + "loss": 0.4764, + "step": 6505 + }, + { + "epoch": 0.54, + "learning_rate": 9.051605871423266e-06, + "loss": 0.4866, + "step": 6506 + }, + { + "epoch": 0.54, + "learning_rate": 9.048908216130002e-06, + "loss": 0.4834, + "step": 6507 + }, + { + "epoch": 0.54, + "learning_rate": 9.046210630680968e-06, + "loss": 0.4618, + "step": 6508 + }, + { + "epoch": 0.54, + "learning_rate": 9.043513115274257e-06, + "loss": 0.4803, + "step": 6509 + }, + { + "epoch": 0.54, + "learning_rate": 9.040815670107964e-06, + "loss": 0.4672, + "step": 6510 + }, + { + "epoch": 0.54, + "learning_rate": 9.038118295380179e-06, + "loss": 0.4937, + "step": 6511 + }, + { + "epoch": 0.54, + "learning_rate": 9.035420991288987e-06, + "loss": 0.4753, + "step": 6512 + }, + { + "epoch": 0.54, + "learning_rate": 9.032723758032462e-06, + "loss": 0.4871, + "step": 6513 + }, + { + "epoch": 0.54, + "learning_rate": 9.030026595808682e-06, + "loss": 0.4761, + "step": 6514 + }, + { + "epoch": 0.55, + "learning_rate": 9.027329504815714e-06, + "loss": 0.509, + "step": 6515 + }, + { + "epoch": 0.55, + "learning_rate": 9.024632485251624e-06, + "loss": 0.4935, + "step": 6516 + }, + { + "epoch": 0.55, + "learning_rate": 9.021935537314467e-06, + "loss": 0.4866, + "step": 6517 + }, + { + "epoch": 0.55, + "learning_rate": 9.019238661202296e-06, + "loss": 0.4957, + "step": 6518 + }, + { + "epoch": 0.55, + "learning_rate": 9.016541857113157e-06, + "loss": 0.4776, + "step": 6519 + }, + { + "epoch": 0.55, + "learning_rate": 9.013845125245095e-06, + "loss": 0.4852, + "step": 6520 + }, + { + "epoch": 0.55, + "learning_rate": 9.01114846579614e-06, + "loss": 0.4643, + "step": 6521 + }, + { + "epoch": 0.55, + "learning_rate": 9.008451878964336e-06, + "loss": 0.4801, + "step": 6522 + }, + { + "epoch": 0.55, + "learning_rate": 9.005755364947699e-06, + "loss": 0.4683, + "step": 6523 + }, + { + "epoch": 0.55, + "learning_rate": 9.00305892394425e-06, + "loss": 0.4803, + "step": 6524 + }, + { + "epoch": 0.55, + "learning_rate": 9.000362556152013e-06, + "loss": 0.4789, + "step": 6525 + }, + { + "epoch": 0.55, + "learning_rate": 8.997666261768989e-06, + "loss": 0.4686, + "step": 6526 + }, + { + "epoch": 0.55, + "learning_rate": 8.994970040993187e-06, + "loss": 0.5007, + "step": 6527 + }, + { + "epoch": 0.55, + "learning_rate": 8.9922738940226e-06, + "loss": 0.4736, + "step": 6528 + }, + { + "epoch": 0.55, + "learning_rate": 8.989577821055231e-06, + "loss": 0.4812, + "step": 6529 + }, + { + "epoch": 0.55, + "learning_rate": 8.986881822289062e-06, + "loss": 0.49, + "step": 6530 + }, + { + "epoch": 0.55, + "learning_rate": 8.98418589792208e-06, + "loss": 0.4833, + "step": 6531 + }, + { + "epoch": 0.55, + "learning_rate": 8.98149004815226e-06, + "loss": 0.4741, + "step": 6532 + }, + { + "epoch": 0.55, + "learning_rate": 8.978794273177576e-06, + "loss": 0.4823, + "step": 6533 + }, + { + "epoch": 0.55, + "learning_rate": 8.97609857319599e-06, + "loss": 0.4539, + "step": 6534 + }, + { + "epoch": 0.55, + "learning_rate": 8.973402948405466e-06, + "loss": 0.4686, + "step": 6535 + }, + { + "epoch": 0.55, + "learning_rate": 8.970707399003961e-06, + "loss": 0.4727, + "step": 6536 + }, + { + "epoch": 0.55, + "learning_rate": 8.968011925189426e-06, + "loss": 0.4807, + "step": 6537 + }, + { + "epoch": 0.55, + "learning_rate": 8.9653165271598e-06, + "loss": 0.4661, + "step": 6538 + }, + { + "epoch": 0.55, + "learning_rate": 8.962621205113025e-06, + "loss": 0.4563, + "step": 6539 + }, + { + "epoch": 0.55, + "learning_rate": 8.959925959247036e-06, + "loss": 0.4915, + "step": 6540 + }, + { + "epoch": 0.55, + "learning_rate": 8.957230789759752e-06, + "loss": 0.4776, + "step": 6541 + }, + { + "epoch": 0.55, + "learning_rate": 8.954535696849108e-06, + "loss": 0.4824, + "step": 6542 + }, + { + "epoch": 0.55, + "learning_rate": 8.951840680713013e-06, + "loss": 0.4858, + "step": 6543 + }, + { + "epoch": 0.55, + "learning_rate": 8.949145741549378e-06, + "loss": 0.4641, + "step": 6544 + }, + { + "epoch": 0.55, + "learning_rate": 8.946450879556108e-06, + "loss": 0.4672, + "step": 6545 + }, + { + "epoch": 0.55, + "learning_rate": 8.943756094931106e-06, + "loss": 0.4964, + "step": 6546 + }, + { + "epoch": 0.55, + "learning_rate": 8.941061387872263e-06, + "loss": 0.4896, + "step": 6547 + }, + { + "epoch": 0.55, + "learning_rate": 8.938366758577462e-06, + "loss": 0.4759, + "step": 6548 + }, + { + "epoch": 0.55, + "learning_rate": 8.935672207244596e-06, + "loss": 0.4772, + "step": 6549 + }, + { + "epoch": 0.55, + "learning_rate": 8.932977734071533e-06, + "loss": 0.4732, + "step": 6550 + }, + { + "epoch": 0.55, + "learning_rate": 8.93028333925615e-06, + "loss": 0.4791, + "step": 6551 + }, + { + "epoch": 0.55, + "learning_rate": 8.927589022996308e-06, + "loss": 0.4696, + "step": 6552 + }, + { + "epoch": 0.55, + "learning_rate": 8.92489478548987e-06, + "loss": 0.4734, + "step": 6553 + }, + { + "epoch": 0.55, + "learning_rate": 8.922200626934682e-06, + "loss": 0.4917, + "step": 6554 + }, + { + "epoch": 0.55, + "learning_rate": 8.919506547528599e-06, + "loss": 0.4855, + "step": 6555 + }, + { + "epoch": 0.55, + "learning_rate": 8.916812547469461e-06, + "loss": 0.4893, + "step": 6556 + }, + { + "epoch": 0.55, + "learning_rate": 8.914118626955106e-06, + "loss": 0.4473, + "step": 6557 + }, + { + "epoch": 0.55, + "learning_rate": 8.911424786183362e-06, + "loss": 0.4829, + "step": 6558 + }, + { + "epoch": 0.55, + "learning_rate": 8.908731025352055e-06, + "loss": 0.4882, + "step": 6559 + }, + { + "epoch": 0.55, + "learning_rate": 8.906037344659e-06, + "loss": 0.4827, + "step": 6560 + }, + { + "epoch": 0.55, + "learning_rate": 8.903343744302016e-06, + "loss": 0.469, + "step": 6561 + }, + { + "epoch": 0.55, + "learning_rate": 8.900650224478899e-06, + "loss": 0.4783, + "step": 6562 + }, + { + "epoch": 0.55, + "learning_rate": 8.897956785387463e-06, + "loss": 0.4845, + "step": 6563 + }, + { + "epoch": 0.55, + "learning_rate": 8.895263427225497e-06, + "loss": 0.4707, + "step": 6564 + }, + { + "epoch": 0.55, + "learning_rate": 8.89257015019079e-06, + "loss": 0.4974, + "step": 6565 + }, + { + "epoch": 0.55, + "learning_rate": 8.889876954481122e-06, + "loss": 0.4709, + "step": 6566 + }, + { + "epoch": 0.55, + "learning_rate": 8.887183840294274e-06, + "loss": 0.4527, + "step": 6567 + }, + { + "epoch": 0.55, + "learning_rate": 8.88449080782802e-06, + "loss": 0.4861, + "step": 6568 + }, + { + "epoch": 0.55, + "learning_rate": 8.881797857280113e-06, + "loss": 0.4684, + "step": 6569 + }, + { + "epoch": 0.55, + "learning_rate": 8.879104988848326e-06, + "loss": 0.4724, + "step": 6570 + }, + { + "epoch": 0.55, + "learning_rate": 8.876412202730405e-06, + "loss": 0.4827, + "step": 6571 + }, + { + "epoch": 0.55, + "learning_rate": 8.873719499124101e-06, + "loss": 0.4686, + "step": 6572 + }, + { + "epoch": 0.55, + "learning_rate": 8.871026878227151e-06, + "loss": 0.4915, + "step": 6573 + }, + { + "epoch": 0.55, + "learning_rate": 8.868334340237293e-06, + "loss": 0.4946, + "step": 6574 + }, + { + "epoch": 0.55, + "learning_rate": 8.86564188535225e-06, + "loss": 0.4845, + "step": 6575 + }, + { + "epoch": 0.55, + "learning_rate": 8.86294951376975e-06, + "loss": 0.4632, + "step": 6576 + }, + { + "epoch": 0.55, + "learning_rate": 8.86025722568751e-06, + "loss": 0.4733, + "step": 6577 + }, + { + "epoch": 0.55, + "learning_rate": 8.857565021303238e-06, + "loss": 0.4629, + "step": 6578 + }, + { + "epoch": 0.55, + "learning_rate": 8.85487290081464e-06, + "loss": 0.4984, + "step": 6579 + }, + { + "epoch": 0.55, + "learning_rate": 8.852180864419413e-06, + "loss": 0.4787, + "step": 6580 + }, + { + "epoch": 0.55, + "learning_rate": 8.84948891231525e-06, + "loss": 0.4913, + "step": 6581 + }, + { + "epoch": 0.55, + "learning_rate": 8.846797044699831e-06, + "loss": 0.4955, + "step": 6582 + }, + { + "epoch": 0.55, + "learning_rate": 8.844105261770844e-06, + "loss": 0.478, + "step": 6583 + }, + { + "epoch": 0.55, + "learning_rate": 8.84141356372596e-06, + "loss": 0.4816, + "step": 6584 + }, + { + "epoch": 0.55, + "learning_rate": 8.838721950762845e-06, + "loss": 0.4711, + "step": 6585 + }, + { + "epoch": 0.55, + "learning_rate": 8.836030423079157e-06, + "loss": 0.4757, + "step": 6586 + }, + { + "epoch": 0.55, + "learning_rate": 8.833338980872558e-06, + "loss": 0.4635, + "step": 6587 + }, + { + "epoch": 0.55, + "learning_rate": 8.830647624340689e-06, + "loss": 0.4623, + "step": 6588 + }, + { + "epoch": 0.55, + "learning_rate": 8.827956353681191e-06, + "loss": 0.4898, + "step": 6589 + }, + { + "epoch": 0.55, + "learning_rate": 8.82526516909171e-06, + "loss": 0.4753, + "step": 6590 + }, + { + "epoch": 0.55, + "learning_rate": 8.822574070769867e-06, + "loss": 0.4799, + "step": 6591 + }, + { + "epoch": 0.55, + "learning_rate": 8.819883058913285e-06, + "loss": 0.4814, + "step": 6592 + }, + { + "epoch": 0.55, + "learning_rate": 8.817192133719583e-06, + "loss": 0.5005, + "step": 6593 + }, + { + "epoch": 0.55, + "learning_rate": 8.814501295386373e-06, + "loss": 0.4939, + "step": 6594 + }, + { + "epoch": 0.55, + "learning_rate": 8.811810544111258e-06, + "loss": 0.4781, + "step": 6595 + }, + { + "epoch": 0.55, + "learning_rate": 8.809119880091829e-06, + "loss": 0.4704, + "step": 6596 + }, + { + "epoch": 0.55, + "learning_rate": 8.806429303525685e-06, + "loss": 0.4791, + "step": 6597 + }, + { + "epoch": 0.55, + "learning_rate": 8.803738814610409e-06, + "loss": 0.4631, + "step": 6598 + }, + { + "epoch": 0.55, + "learning_rate": 8.801048413543581e-06, + "loss": 0.4904, + "step": 6599 + }, + { + "epoch": 0.55, + "learning_rate": 8.79835810052277e-06, + "loss": 0.4783, + "step": 6600 + }, + { + "epoch": 0.55, + "learning_rate": 8.79566787574554e-06, + "loss": 0.4744, + "step": 6601 + }, + { + "epoch": 0.55, + "learning_rate": 8.792977739409455e-06, + "loss": 0.4782, + "step": 6602 + }, + { + "epoch": 0.55, + "learning_rate": 8.790287691712059e-06, + "loss": 0.478, + "step": 6603 + }, + { + "epoch": 0.55, + "learning_rate": 8.78759773285091e-06, + "loss": 0.4799, + "step": 6604 + }, + { + "epoch": 0.55, + "learning_rate": 8.784907863023537e-06, + "loss": 0.4553, + "step": 6605 + }, + { + "epoch": 0.55, + "learning_rate": 8.782218082427478e-06, + "loss": 0.4705, + "step": 6606 + }, + { + "epoch": 0.55, + "learning_rate": 8.779528391260257e-06, + "loss": 0.4689, + "step": 6607 + }, + { + "epoch": 0.55, + "learning_rate": 8.776838789719396e-06, + "loss": 0.4538, + "step": 6608 + }, + { + "epoch": 0.55, + "learning_rate": 8.774149278002402e-06, + "loss": 0.4857, + "step": 6609 + }, + { + "epoch": 0.55, + "learning_rate": 8.771459856306791e-06, + "loss": 0.4831, + "step": 6610 + }, + { + "epoch": 0.55, + "learning_rate": 8.768770524830058e-06, + "loss": 0.4744, + "step": 6611 + }, + { + "epoch": 0.55, + "learning_rate": 8.766081283769695e-06, + "loss": 0.4704, + "step": 6612 + }, + { + "epoch": 0.55, + "learning_rate": 8.763392133323192e-06, + "loss": 0.476, + "step": 6613 + }, + { + "epoch": 0.55, + "learning_rate": 8.760703073688027e-06, + "loss": 0.4742, + "step": 6614 + }, + { + "epoch": 0.55, + "learning_rate": 8.758014105061674e-06, + "loss": 0.469, + "step": 6615 + }, + { + "epoch": 0.55, + "learning_rate": 8.755325227641596e-06, + "loss": 0.4838, + "step": 6616 + }, + { + "epoch": 0.55, + "learning_rate": 8.752636441625259e-06, + "loss": 0.4951, + "step": 6617 + }, + { + "epoch": 0.55, + "learning_rate": 8.749947747210112e-06, + "loss": 0.4718, + "step": 6618 + }, + { + "epoch": 0.55, + "learning_rate": 8.747259144593604e-06, + "loss": 0.4653, + "step": 6619 + }, + { + "epoch": 0.55, + "learning_rate": 8.744570633973177e-06, + "loss": 0.472, + "step": 6620 + }, + { + "epoch": 0.55, + "learning_rate": 8.741882215546259e-06, + "loss": 0.4854, + "step": 6621 + }, + { + "epoch": 0.55, + "learning_rate": 8.739193889510276e-06, + "loss": 0.4681, + "step": 6622 + }, + { + "epoch": 0.55, + "learning_rate": 8.736505656062648e-06, + "loss": 0.4679, + "step": 6623 + }, + { + "epoch": 0.55, + "learning_rate": 8.733817515400793e-06, + "loss": 0.4907, + "step": 6624 + }, + { + "epoch": 0.55, + "learning_rate": 8.731129467722113e-06, + "loss": 0.4657, + "step": 6625 + }, + { + "epoch": 0.55, + "learning_rate": 8.728441513224008e-06, + "loss": 0.4657, + "step": 6626 + }, + { + "epoch": 0.55, + "learning_rate": 8.725753652103868e-06, + "loss": 0.4826, + "step": 6627 + }, + { + "epoch": 0.55, + "learning_rate": 8.72306588455908e-06, + "loss": 0.4653, + "step": 6628 + }, + { + "epoch": 0.55, + "learning_rate": 8.720378210787024e-06, + "loss": 0.4729, + "step": 6629 + }, + { + "epoch": 0.55, + "learning_rate": 8.717690630985065e-06, + "loss": 0.4685, + "step": 6630 + }, + { + "epoch": 0.55, + "learning_rate": 8.715003145350576e-06, + "loss": 0.4579, + "step": 6631 + }, + { + "epoch": 0.55, + "learning_rate": 8.712315754080913e-06, + "loss": 0.4743, + "step": 6632 + }, + { + "epoch": 0.55, + "learning_rate": 8.709628457373421e-06, + "loss": 0.4584, + "step": 6633 + }, + { + "epoch": 0.56, + "learning_rate": 8.706941255425452e-06, + "loss": 0.4803, + "step": 6634 + }, + { + "epoch": 0.56, + "learning_rate": 8.704254148434338e-06, + "loss": 0.4585, + "step": 6635 + }, + { + "epoch": 0.56, + "learning_rate": 8.70156713659741e-06, + "loss": 0.4726, + "step": 6636 + }, + { + "epoch": 0.56, + "learning_rate": 8.698880220111987e-06, + "loss": 0.4588, + "step": 6637 + }, + { + "epoch": 0.56, + "learning_rate": 8.69619339917539e-06, + "loss": 0.4938, + "step": 6638 + }, + { + "epoch": 0.56, + "learning_rate": 8.69350667398493e-06, + "loss": 0.4575, + "step": 6639 + }, + { + "epoch": 0.56, + "learning_rate": 8.690820044737905e-06, + "loss": 0.4914, + "step": 6640 + }, + { + "epoch": 0.56, + "learning_rate": 8.688133511631611e-06, + "loss": 0.4948, + "step": 6641 + }, + { + "epoch": 0.56, + "learning_rate": 8.685447074863333e-06, + "loss": 0.4842, + "step": 6642 + }, + { + "epoch": 0.56, + "learning_rate": 8.682760734630357e-06, + "loss": 0.4749, + "step": 6643 + }, + { + "epoch": 0.56, + "learning_rate": 8.68007449112995e-06, + "loss": 0.4753, + "step": 6644 + }, + { + "epoch": 0.56, + "learning_rate": 8.677388344559386e-06, + "loss": 0.4793, + "step": 6645 + }, + { + "epoch": 0.56, + "learning_rate": 8.67470229511592e-06, + "loss": 0.4646, + "step": 6646 + }, + { + "epoch": 0.56, + "learning_rate": 8.672016342996805e-06, + "loss": 0.4625, + "step": 6647 + }, + { + "epoch": 0.56, + "learning_rate": 8.669330488399286e-06, + "loss": 0.4775, + "step": 6648 + }, + { + "epoch": 0.56, + "learning_rate": 8.6666447315206e-06, + "loss": 0.4756, + "step": 6649 + }, + { + "epoch": 0.56, + "learning_rate": 8.663959072557979e-06, + "loss": 0.4676, + "step": 6650 + }, + { + "epoch": 0.56, + "learning_rate": 8.66127351170865e-06, + "loss": 0.4726, + "step": 6651 + }, + { + "epoch": 0.56, + "learning_rate": 8.658588049169825e-06, + "loss": 0.4714, + "step": 6652 + }, + { + "epoch": 0.56, + "learning_rate": 8.655902685138712e-06, + "loss": 0.4803, + "step": 6653 + }, + { + "epoch": 0.56, + "learning_rate": 8.653217419812517e-06, + "loss": 0.4892, + "step": 6654 + }, + { + "epoch": 0.56, + "learning_rate": 8.650532253388435e-06, + "loss": 0.4818, + "step": 6655 + }, + { + "epoch": 0.56, + "learning_rate": 8.64784718606365e-06, + "loss": 0.4835, + "step": 6656 + }, + { + "epoch": 0.56, + "learning_rate": 8.64516221803534e-06, + "loss": 0.4779, + "step": 6657 + }, + { + "epoch": 0.56, + "learning_rate": 8.642477349500686e-06, + "loss": 0.4493, + "step": 6658 + }, + { + "epoch": 0.56, + "learning_rate": 8.639792580656845e-06, + "loss": 0.486, + "step": 6659 + }, + { + "epoch": 0.56, + "learning_rate": 8.637107911700984e-06, + "loss": 0.4814, + "step": 6660 + }, + { + "epoch": 0.56, + "learning_rate": 8.634423342830247e-06, + "loss": 0.4684, + "step": 6661 + }, + { + "epoch": 0.56, + "learning_rate": 8.631738874241781e-06, + "loss": 0.4948, + "step": 6662 + }, + { + "epoch": 0.56, + "learning_rate": 8.629054506132719e-06, + "loss": 0.4751, + "step": 6663 + }, + { + "epoch": 0.56, + "learning_rate": 8.62637023870019e-06, + "loss": 0.4949, + "step": 6664 + }, + { + "epoch": 0.56, + "learning_rate": 8.623686072141322e-06, + "loss": 0.4846, + "step": 6665 + }, + { + "epoch": 0.56, + "learning_rate": 8.621002006653223e-06, + "loss": 0.5014, + "step": 6666 + }, + { + "epoch": 0.56, + "learning_rate": 8.618318042433001e-06, + "loss": 0.4761, + "step": 6667 + }, + { + "epoch": 0.56, + "learning_rate": 8.615634179677754e-06, + "loss": 0.455, + "step": 6668 + }, + { + "epoch": 0.56, + "learning_rate": 8.612950418584575e-06, + "loss": 0.4812, + "step": 6669 + }, + { + "epoch": 0.56, + "learning_rate": 8.610266759350551e-06, + "loss": 0.445, + "step": 6670 + }, + { + "epoch": 0.56, + "learning_rate": 8.60758320217275e-06, + "loss": 0.4593, + "step": 6671 + }, + { + "epoch": 0.56, + "learning_rate": 8.604899747248251e-06, + "loss": 0.48, + "step": 6672 + }, + { + "epoch": 0.56, + "learning_rate": 8.602216394774114e-06, + "loss": 0.485, + "step": 6673 + }, + { + "epoch": 0.56, + "learning_rate": 8.599533144947386e-06, + "loss": 0.4597, + "step": 6674 + }, + { + "epoch": 0.56, + "learning_rate": 8.596849997965122e-06, + "loss": 0.4916, + "step": 6675 + }, + { + "epoch": 0.56, + "learning_rate": 8.594166954024359e-06, + "loss": 0.4836, + "step": 6676 + }, + { + "epoch": 0.56, + "learning_rate": 8.591484013322128e-06, + "loss": 0.4712, + "step": 6677 + }, + { + "epoch": 0.56, + "learning_rate": 8.588801176055447e-06, + "loss": 0.4779, + "step": 6678 + }, + { + "epoch": 0.56, + "learning_rate": 8.586118442421341e-06, + "loss": 0.4899, + "step": 6679 + }, + { + "epoch": 0.56, + "learning_rate": 8.583435812616817e-06, + "loss": 0.4701, + "step": 6680 + }, + { + "epoch": 0.56, + "learning_rate": 8.580753286838875e-06, + "loss": 0.4788, + "step": 6681 + }, + { + "epoch": 0.56, + "learning_rate": 8.57807086528451e-06, + "loss": 0.4701, + "step": 6682 + }, + { + "epoch": 0.56, + "learning_rate": 8.575388548150702e-06, + "loss": 0.4718, + "step": 6683 + }, + { + "epoch": 0.56, + "learning_rate": 8.572706335634437e-06, + "loss": 0.4727, + "step": 6684 + }, + { + "epoch": 0.56, + "learning_rate": 8.570024227932678e-06, + "loss": 0.4729, + "step": 6685 + }, + { + "epoch": 0.56, + "learning_rate": 8.567342225242397e-06, + "loss": 0.4713, + "step": 6686 + }, + { + "epoch": 0.56, + "learning_rate": 8.564660327760543e-06, + "loss": 0.4734, + "step": 6687 + }, + { + "epoch": 0.56, + "learning_rate": 8.561978535684065e-06, + "loss": 0.4841, + "step": 6688 + }, + { + "epoch": 0.56, + "learning_rate": 8.5592968492099e-06, + "loss": 0.4794, + "step": 6689 + }, + { + "epoch": 0.56, + "learning_rate": 8.556615268534984e-06, + "loss": 0.4915, + "step": 6690 + }, + { + "epoch": 0.56, + "learning_rate": 8.553933793856234e-06, + "loss": 0.4734, + "step": 6691 + }, + { + "epoch": 0.56, + "learning_rate": 8.551252425370577e-06, + "loss": 0.4661, + "step": 6692 + }, + { + "epoch": 0.56, + "learning_rate": 8.548571163274915e-06, + "loss": 0.4723, + "step": 6693 + }, + { + "epoch": 0.56, + "learning_rate": 8.54589000776615e-06, + "loss": 0.4812, + "step": 6694 + }, + { + "epoch": 0.56, + "learning_rate": 8.543208959041174e-06, + "loss": 0.4868, + "step": 6695 + }, + { + "epoch": 0.56, + "learning_rate": 8.540528017296876e-06, + "loss": 0.4789, + "step": 6696 + }, + { + "epoch": 0.56, + "learning_rate": 8.537847182730126e-06, + "loss": 0.4894, + "step": 6697 + }, + { + "epoch": 0.56, + "learning_rate": 8.535166455537795e-06, + "loss": 0.4734, + "step": 6698 + }, + { + "epoch": 0.56, + "learning_rate": 8.532485835916754e-06, + "loss": 0.4674, + "step": 6699 + }, + { + "epoch": 0.56, + "learning_rate": 8.529805324063843e-06, + "loss": 0.4828, + "step": 6700 + }, + { + "epoch": 0.56, + "learning_rate": 8.527124920175918e-06, + "loss": 0.4801, + "step": 6701 + }, + { + "epoch": 0.56, + "learning_rate": 8.524444624449812e-06, + "loss": 0.4383, + "step": 6702 + }, + { + "epoch": 0.56, + "learning_rate": 8.521764437082355e-06, + "loss": 0.4693, + "step": 6703 + }, + { + "epoch": 0.56, + "learning_rate": 8.519084358270368e-06, + "loss": 0.4689, + "step": 6704 + }, + { + "epoch": 0.56, + "learning_rate": 8.516404388210668e-06, + "loss": 0.4543, + "step": 6705 + }, + { + "epoch": 0.56, + "learning_rate": 8.513724527100055e-06, + "loss": 0.4868, + "step": 6706 + }, + { + "epoch": 0.56, + "learning_rate": 8.511044775135336e-06, + "loss": 0.4848, + "step": 6707 + }, + { + "epoch": 0.56, + "learning_rate": 8.508365132513296e-06, + "loss": 0.4832, + "step": 6708 + }, + { + "epoch": 0.56, + "learning_rate": 8.505685599430715e-06, + "loss": 0.4872, + "step": 6709 + }, + { + "epoch": 0.56, + "learning_rate": 8.503006176084366e-06, + "loss": 0.4848, + "step": 6710 + }, + { + "epoch": 0.56, + "learning_rate": 8.50032686267102e-06, + "loss": 0.4751, + "step": 6711 + }, + { + "epoch": 0.56, + "learning_rate": 8.497647659387426e-06, + "loss": 0.4748, + "step": 6712 + }, + { + "epoch": 0.56, + "learning_rate": 8.494968566430346e-06, + "loss": 0.4774, + "step": 6713 + }, + { + "epoch": 0.56, + "learning_rate": 8.492289583996511e-06, + "loss": 0.4901, + "step": 6714 + }, + { + "epoch": 0.56, + "learning_rate": 8.489610712282658e-06, + "loss": 0.477, + "step": 6715 + }, + { + "epoch": 0.56, + "learning_rate": 8.486931951485515e-06, + "loss": 0.4673, + "step": 6716 + }, + { + "epoch": 0.56, + "learning_rate": 8.484253301801794e-06, + "loss": 0.4684, + "step": 6717 + }, + { + "epoch": 0.56, + "learning_rate": 8.481574763428208e-06, + "loss": 0.4901, + "step": 6718 + }, + { + "epoch": 0.56, + "learning_rate": 8.47889633656145e-06, + "loss": 0.4841, + "step": 6719 + }, + { + "epoch": 0.56, + "learning_rate": 8.476218021398224e-06, + "loss": 0.4742, + "step": 6720 + }, + { + "epoch": 0.56, + "learning_rate": 8.473539818135205e-06, + "loss": 0.473, + "step": 6721 + }, + { + "epoch": 0.56, + "learning_rate": 8.470861726969075e-06, + "loss": 0.4822, + "step": 6722 + }, + { + "epoch": 0.56, + "learning_rate": 8.4681837480965e-06, + "loss": 0.4779, + "step": 6723 + }, + { + "epoch": 0.56, + "learning_rate": 8.46550588171414e-06, + "loss": 0.4748, + "step": 6724 + }, + { + "epoch": 0.56, + "learning_rate": 8.462828128018642e-06, + "loss": 0.4784, + "step": 6725 + }, + { + "epoch": 0.56, + "learning_rate": 8.460150487206652e-06, + "loss": 0.4835, + "step": 6726 + }, + { + "epoch": 0.56, + "learning_rate": 8.45747295947481e-06, + "loss": 0.4796, + "step": 6727 + }, + { + "epoch": 0.56, + "learning_rate": 8.454795545019737e-06, + "loss": 0.4778, + "step": 6728 + }, + { + "epoch": 0.56, + "learning_rate": 8.452118244038052e-06, + "loss": 0.4831, + "step": 6729 + }, + { + "epoch": 0.56, + "learning_rate": 8.449441056726364e-06, + "loss": 0.4749, + "step": 6730 + }, + { + "epoch": 0.56, + "learning_rate": 8.446763983281276e-06, + "loss": 0.4853, + "step": 6731 + }, + { + "epoch": 0.56, + "learning_rate": 8.444087023899377e-06, + "loss": 0.491, + "step": 6732 + }, + { + "epoch": 0.56, + "learning_rate": 8.44141017877726e-06, + "loss": 0.4564, + "step": 6733 + }, + { + "epoch": 0.56, + "learning_rate": 8.438733448111496e-06, + "loss": 0.4818, + "step": 6734 + }, + { + "epoch": 0.56, + "learning_rate": 8.436056832098655e-06, + "loss": 0.4734, + "step": 6735 + }, + { + "epoch": 0.56, + "learning_rate": 8.433380330935293e-06, + "loss": 0.4585, + "step": 6736 + }, + { + "epoch": 0.56, + "learning_rate": 8.430703944817967e-06, + "loss": 0.4646, + "step": 6737 + }, + { + "epoch": 0.56, + "learning_rate": 8.428027673943213e-06, + "loss": 0.4824, + "step": 6738 + }, + { + "epoch": 0.56, + "learning_rate": 8.425351518507565e-06, + "loss": 0.4706, + "step": 6739 + }, + { + "epoch": 0.56, + "learning_rate": 8.422675478707556e-06, + "loss": 0.4733, + "step": 6740 + }, + { + "epoch": 0.56, + "learning_rate": 8.4199995547397e-06, + "loss": 0.5001, + "step": 6741 + }, + { + "epoch": 0.56, + "learning_rate": 8.417323746800504e-06, + "loss": 0.4803, + "step": 6742 + }, + { + "epoch": 0.56, + "learning_rate": 8.414648055086471e-06, + "loss": 0.4705, + "step": 6743 + }, + { + "epoch": 0.56, + "learning_rate": 8.41197247979409e-06, + "loss": 0.4768, + "step": 6744 + }, + { + "epoch": 0.56, + "learning_rate": 8.409297021119843e-06, + "loss": 0.4859, + "step": 6745 + }, + { + "epoch": 0.56, + "learning_rate": 8.406621679260206e-06, + "loss": 0.4715, + "step": 6746 + }, + { + "epoch": 0.56, + "learning_rate": 8.403946454411645e-06, + "loss": 0.462, + "step": 6747 + }, + { + "epoch": 0.56, + "learning_rate": 8.401271346770622e-06, + "loss": 0.4751, + "step": 6748 + }, + { + "epoch": 0.56, + "learning_rate": 8.398596356533581e-06, + "loss": 0.4768, + "step": 6749 + }, + { + "epoch": 0.56, + "learning_rate": 8.395921483896963e-06, + "loss": 0.471, + "step": 6750 + }, + { + "epoch": 0.56, + "learning_rate": 8.393246729057196e-06, + "loss": 0.5009, + "step": 6751 + }, + { + "epoch": 0.56, + "learning_rate": 8.39057209221071e-06, + "loss": 0.4724, + "step": 6752 + }, + { + "epoch": 0.56, + "learning_rate": 8.38789757355391e-06, + "loss": 0.471, + "step": 6753 + }, + { + "epoch": 0.57, + "learning_rate": 8.38522317328321e-06, + "loss": 0.4789, + "step": 6754 + }, + { + "epoch": 0.57, + "learning_rate": 8.382548891595006e-06, + "loss": 0.4581, + "step": 6755 + }, + { + "epoch": 0.57, + "learning_rate": 8.379874728685681e-06, + "loss": 0.4895, + "step": 6756 + }, + { + "epoch": 0.57, + "learning_rate": 8.37720068475162e-06, + "loss": 0.4833, + "step": 6757 + }, + { + "epoch": 0.57, + "learning_rate": 8.37452675998919e-06, + "loss": 0.4793, + "step": 6758 + }, + { + "epoch": 0.57, + "learning_rate": 8.371852954594755e-06, + "loss": 0.4747, + "step": 6759 + }, + { + "epoch": 0.57, + "learning_rate": 8.369179268764662e-06, + "loss": 0.4749, + "step": 6760 + }, + { + "epoch": 0.57, + "learning_rate": 8.366505702695264e-06, + "loss": 0.4625, + "step": 6761 + }, + { + "epoch": 0.57, + "learning_rate": 8.363832256582892e-06, + "loss": 0.4828, + "step": 6762 + }, + { + "epoch": 0.57, + "learning_rate": 8.361158930623877e-06, + "loss": 0.4782, + "step": 6763 + }, + { + "epoch": 0.57, + "learning_rate": 8.358485725014531e-06, + "loss": 0.4788, + "step": 6764 + }, + { + "epoch": 0.57, + "learning_rate": 8.355812639951168e-06, + "loss": 0.4712, + "step": 6765 + }, + { + "epoch": 0.57, + "learning_rate": 8.35313967563008e-06, + "loss": 0.4894, + "step": 6766 + }, + { + "epoch": 0.57, + "learning_rate": 8.350466832247568e-06, + "loss": 0.4702, + "step": 6767 + }, + { + "epoch": 0.57, + "learning_rate": 8.347794109999912e-06, + "loss": 0.4668, + "step": 6768 + }, + { + "epoch": 0.57, + "learning_rate": 8.345121509083384e-06, + "loss": 0.4578, + "step": 6769 + }, + { + "epoch": 0.57, + "learning_rate": 8.34244902969425e-06, + "loss": 0.4826, + "step": 6770 + }, + { + "epoch": 0.57, + "learning_rate": 8.339776672028765e-06, + "loss": 0.4897, + "step": 6771 + }, + { + "epoch": 0.57, + "learning_rate": 8.337104436283176e-06, + "loss": 0.4767, + "step": 6772 + }, + { + "epoch": 0.57, + "learning_rate": 8.334432322653717e-06, + "loss": 0.5019, + "step": 6773 + }, + { + "epoch": 0.57, + "learning_rate": 8.331760331336622e-06, + "loss": 0.4777, + "step": 6774 + }, + { + "epoch": 0.57, + "learning_rate": 8.329088462528113e-06, + "loss": 0.4643, + "step": 6775 + }, + { + "epoch": 0.57, + "learning_rate": 8.326416716424396e-06, + "loss": 0.4687, + "step": 6776 + }, + { + "epoch": 0.57, + "learning_rate": 8.323745093221672e-06, + "loss": 0.4902, + "step": 6777 + }, + { + "epoch": 0.57, + "learning_rate": 8.32107359311614e-06, + "loss": 0.4804, + "step": 6778 + }, + { + "epoch": 0.57, + "learning_rate": 8.318402216303978e-06, + "loss": 0.4833, + "step": 6779 + }, + { + "epoch": 0.57, + "learning_rate": 8.31573096298136e-06, + "loss": 0.4916, + "step": 6780 + }, + { + "epoch": 0.57, + "learning_rate": 8.313059833344459e-06, + "loss": 0.4769, + "step": 6781 + }, + { + "epoch": 0.57, + "learning_rate": 8.310388827589424e-06, + "loss": 0.4853, + "step": 6782 + }, + { + "epoch": 0.57, + "learning_rate": 8.30771794591241e-06, + "loss": 0.4967, + "step": 6783 + }, + { + "epoch": 0.57, + "learning_rate": 8.30504718850955e-06, + "loss": 0.4618, + "step": 6784 + }, + { + "epoch": 0.57, + "learning_rate": 8.302376555576974e-06, + "loss": 0.4827, + "step": 6785 + }, + { + "epoch": 0.57, + "learning_rate": 8.299706047310803e-06, + "loss": 0.458, + "step": 6786 + }, + { + "epoch": 0.57, + "learning_rate": 8.297035663907146e-06, + "loss": 0.4838, + "step": 6787 + }, + { + "epoch": 0.57, + "learning_rate": 8.294365405562107e-06, + "loss": 0.4725, + "step": 6788 + }, + { + "epoch": 0.57, + "learning_rate": 8.29169527247178e-06, + "loss": 0.4844, + "step": 6789 + }, + { + "epoch": 0.57, + "learning_rate": 8.289025264832247e-06, + "loss": 0.479, + "step": 6790 + }, + { + "epoch": 0.57, + "learning_rate": 8.286355382839584e-06, + "loss": 0.4811, + "step": 6791 + }, + { + "epoch": 0.57, + "learning_rate": 8.283685626689851e-06, + "loss": 0.4781, + "step": 6792 + }, + { + "epoch": 0.57, + "learning_rate": 8.281015996579106e-06, + "loss": 0.4775, + "step": 6793 + }, + { + "epoch": 0.57, + "learning_rate": 8.278346492703394e-06, + "loss": 0.4994, + "step": 6794 + }, + { + "epoch": 0.57, + "learning_rate": 8.275677115258761e-06, + "loss": 0.4812, + "step": 6795 + }, + { + "epoch": 0.57, + "learning_rate": 8.273007864441227e-06, + "loss": 0.4621, + "step": 6796 + }, + { + "epoch": 0.57, + "learning_rate": 8.27033874044681e-06, + "loss": 0.4713, + "step": 6797 + }, + { + "epoch": 0.57, + "learning_rate": 8.267669743471525e-06, + "loss": 0.4923, + "step": 6798 + }, + { + "epoch": 0.57, + "learning_rate": 8.265000873711368e-06, + "loss": 0.4829, + "step": 6799 + }, + { + "epoch": 0.57, + "learning_rate": 8.262332131362326e-06, + "loss": 0.4658, + "step": 6800 + }, + { + "epoch": 0.57, + "learning_rate": 8.259663516620389e-06, + "loss": 0.5034, + "step": 6801 + }, + { + "epoch": 0.57, + "learning_rate": 8.256995029681526e-06, + "loss": 0.4598, + "step": 6802 + }, + { + "epoch": 0.57, + "learning_rate": 8.254326670741694e-06, + "loss": 0.4704, + "step": 6803 + }, + { + "epoch": 0.57, + "learning_rate": 8.251658439996854e-06, + "loss": 0.4928, + "step": 6804 + }, + { + "epoch": 0.57, + "learning_rate": 8.248990337642946e-06, + "loss": 0.4666, + "step": 6805 + }, + { + "epoch": 0.57, + "learning_rate": 8.246322363875904e-06, + "loss": 0.4721, + "step": 6806 + }, + { + "epoch": 0.57, + "learning_rate": 8.24365451889165e-06, + "loss": 0.474, + "step": 6807 + }, + { + "epoch": 0.57, + "learning_rate": 8.240986802886105e-06, + "loss": 0.4743, + "step": 6808 + }, + { + "epoch": 0.57, + "learning_rate": 8.238319216055175e-06, + "loss": 0.4705, + "step": 6809 + }, + { + "epoch": 0.57, + "learning_rate": 8.235651758594753e-06, + "loss": 0.4877, + "step": 6810 + }, + { + "epoch": 0.57, + "learning_rate": 8.23298443070073e-06, + "loss": 0.4727, + "step": 6811 + }, + { + "epoch": 0.57, + "learning_rate": 8.230317232568977e-06, + "loss": 0.4659, + "step": 6812 + }, + { + "epoch": 0.57, + "learning_rate": 8.227650164395369e-06, + "loss": 0.4665, + "step": 6813 + }, + { + "epoch": 0.57, + "learning_rate": 8.224983226375756e-06, + "loss": 0.461, + "step": 6814 + }, + { + "epoch": 0.57, + "learning_rate": 8.222316418705995e-06, + "loss": 0.4809, + "step": 6815 + }, + { + "epoch": 0.57, + "learning_rate": 8.219649741581925e-06, + "loss": 0.4596, + "step": 6816 + }, + { + "epoch": 0.57, + "learning_rate": 8.216983195199372e-06, + "loss": 0.4577, + "step": 6817 + }, + { + "epoch": 0.57, + "learning_rate": 8.214316779754154e-06, + "loss": 0.4787, + "step": 6818 + }, + { + "epoch": 0.57, + "learning_rate": 8.211650495442088e-06, + "loss": 0.4803, + "step": 6819 + }, + { + "epoch": 0.57, + "learning_rate": 8.20898434245897e-06, + "loss": 0.4821, + "step": 6820 + }, + { + "epoch": 0.57, + "learning_rate": 8.206318321000588e-06, + "loss": 0.4678, + "step": 6821 + }, + { + "epoch": 0.57, + "learning_rate": 8.203652431262733e-06, + "loss": 0.501, + "step": 6822 + }, + { + "epoch": 0.57, + "learning_rate": 8.200986673441173e-06, + "loss": 0.4752, + "step": 6823 + }, + { + "epoch": 0.57, + "learning_rate": 8.198321047731665e-06, + "loss": 0.4762, + "step": 6824 + }, + { + "epoch": 0.57, + "learning_rate": 8.195655554329969e-06, + "loss": 0.4846, + "step": 6825 + }, + { + "epoch": 0.57, + "learning_rate": 8.192990193431824e-06, + "loss": 0.4847, + "step": 6826 + }, + { + "epoch": 0.57, + "learning_rate": 8.19032496523296e-06, + "loss": 0.4782, + "step": 6827 + }, + { + "epoch": 0.57, + "learning_rate": 8.187659869929104e-06, + "loss": 0.4777, + "step": 6828 + }, + { + "epoch": 0.57, + "learning_rate": 8.184994907715969e-06, + "loss": 0.4826, + "step": 6829 + }, + { + "epoch": 0.57, + "learning_rate": 8.182330078789262e-06, + "loss": 0.4972, + "step": 6830 + }, + { + "epoch": 0.57, + "learning_rate": 8.179665383344674e-06, + "loss": 0.4655, + "step": 6831 + }, + { + "epoch": 0.57, + "learning_rate": 8.177000821577888e-06, + "loss": 0.4884, + "step": 6832 + }, + { + "epoch": 0.57, + "learning_rate": 8.174336393684577e-06, + "loss": 0.4607, + "step": 6833 + }, + { + "epoch": 0.57, + "learning_rate": 8.17167209986041e-06, + "loss": 0.4567, + "step": 6834 + }, + { + "epoch": 0.57, + "learning_rate": 8.169007940301034e-06, + "loss": 0.4858, + "step": 6835 + }, + { + "epoch": 0.57, + "learning_rate": 8.166343915202106e-06, + "loss": 0.473, + "step": 6836 + }, + { + "epoch": 0.57, + "learning_rate": 8.163680024759252e-06, + "loss": 0.4651, + "step": 6837 + }, + { + "epoch": 0.57, + "learning_rate": 8.161016269168101e-06, + "loss": 0.4667, + "step": 6838 + }, + { + "epoch": 0.57, + "learning_rate": 8.158352648624263e-06, + "loss": 0.5024, + "step": 6839 + }, + { + "epoch": 0.57, + "learning_rate": 8.155689163323348e-06, + "loss": 0.478, + "step": 6840 + }, + { + "epoch": 0.57, + "learning_rate": 8.153025813460947e-06, + "loss": 0.4516, + "step": 6841 + }, + { + "epoch": 0.57, + "learning_rate": 8.15036259923265e-06, + "loss": 0.478, + "step": 6842 + }, + { + "epoch": 0.57, + "learning_rate": 8.147699520834033e-06, + "loss": 0.4709, + "step": 6843 + }, + { + "epoch": 0.57, + "learning_rate": 8.145036578460656e-06, + "loss": 0.4604, + "step": 6844 + }, + { + "epoch": 0.57, + "learning_rate": 8.142373772308078e-06, + "loss": 0.4652, + "step": 6845 + }, + { + "epoch": 0.57, + "learning_rate": 8.139711102571846e-06, + "loss": 0.4943, + "step": 6846 + }, + { + "epoch": 0.57, + "learning_rate": 8.137048569447492e-06, + "loss": 0.4631, + "step": 6847 + }, + { + "epoch": 0.57, + "learning_rate": 8.134386173130539e-06, + "loss": 0.4891, + "step": 6848 + }, + { + "epoch": 0.57, + "learning_rate": 8.131723913816508e-06, + "loss": 0.4725, + "step": 6849 + }, + { + "epoch": 0.57, + "learning_rate": 8.129061791700903e-06, + "loss": 0.4699, + "step": 6850 + }, + { + "epoch": 0.57, + "learning_rate": 8.126399806979217e-06, + "loss": 0.4892, + "step": 6851 + }, + { + "epoch": 0.57, + "learning_rate": 8.123737959846937e-06, + "loss": 0.4647, + "step": 6852 + }, + { + "epoch": 0.57, + "learning_rate": 8.121076250499539e-06, + "loss": 0.4725, + "step": 6853 + }, + { + "epoch": 0.57, + "learning_rate": 8.118414679132484e-06, + "loss": 0.4585, + "step": 6854 + }, + { + "epoch": 0.57, + "learning_rate": 8.115753245941225e-06, + "loss": 0.481, + "step": 6855 + }, + { + "epoch": 0.57, + "learning_rate": 8.113091951121215e-06, + "loss": 0.4593, + "step": 6856 + }, + { + "epoch": 0.57, + "learning_rate": 8.110430794867884e-06, + "loss": 0.4727, + "step": 6857 + }, + { + "epoch": 0.57, + "learning_rate": 8.107769777376657e-06, + "loss": 0.4692, + "step": 6858 + }, + { + "epoch": 0.57, + "learning_rate": 8.105108898842946e-06, + "loss": 0.4705, + "step": 6859 + }, + { + "epoch": 0.57, + "learning_rate": 8.102448159462155e-06, + "loss": 0.4907, + "step": 6860 + }, + { + "epoch": 0.57, + "learning_rate": 8.099787559429682e-06, + "loss": 0.4831, + "step": 6861 + }, + { + "epoch": 0.57, + "learning_rate": 8.0971270989409e-06, + "loss": 0.4815, + "step": 6862 + }, + { + "epoch": 0.57, + "learning_rate": 8.094466778191194e-06, + "loss": 0.4879, + "step": 6863 + }, + { + "epoch": 0.57, + "learning_rate": 8.091806597375925e-06, + "loss": 0.4851, + "step": 6864 + }, + { + "epoch": 0.57, + "learning_rate": 8.089146556690437e-06, + "loss": 0.4682, + "step": 6865 + }, + { + "epoch": 0.57, + "learning_rate": 8.086486656330082e-06, + "loss": 0.4849, + "step": 6866 + }, + { + "epoch": 0.57, + "learning_rate": 8.083826896490186e-06, + "loss": 0.4875, + "step": 6867 + }, + { + "epoch": 0.57, + "learning_rate": 8.081167277366076e-06, + "loss": 0.4755, + "step": 6868 + }, + { + "epoch": 0.57, + "learning_rate": 8.078507799153053e-06, + "loss": 0.4663, + "step": 6869 + }, + { + "epoch": 0.57, + "learning_rate": 8.07584846204643e-06, + "loss": 0.4806, + "step": 6870 + }, + { + "epoch": 0.57, + "learning_rate": 8.073189266241492e-06, + "loss": 0.4771, + "step": 6871 + }, + { + "epoch": 0.57, + "learning_rate": 8.070530211933522e-06, + "loss": 0.4727, + "step": 6872 + }, + { + "epoch": 0.58, + "learning_rate": 8.067871299317786e-06, + "loss": 0.4623, + "step": 6873 + }, + { + "epoch": 0.58, + "learning_rate": 8.065212528589545e-06, + "loss": 0.5038, + "step": 6874 + }, + { + "epoch": 0.58, + "learning_rate": 8.062553899944049e-06, + "loss": 0.4703, + "step": 6875 + }, + { + "epoch": 0.58, + "learning_rate": 8.059895413576535e-06, + "loss": 0.4934, + "step": 6876 + }, + { + "epoch": 0.58, + "learning_rate": 8.057237069682235e-06, + "loss": 0.4898, + "step": 6877 + }, + { + "epoch": 0.58, + "learning_rate": 8.054578868456364e-06, + "loss": 0.4677, + "step": 6878 + }, + { + "epoch": 0.58, + "learning_rate": 8.05192081009413e-06, + "loss": 0.5034, + "step": 6879 + }, + { + "epoch": 0.58, + "learning_rate": 8.049262894790725e-06, + "loss": 0.4796, + "step": 6880 + }, + { + "epoch": 0.58, + "learning_rate": 8.046605122741343e-06, + "loss": 0.4751, + "step": 6881 + }, + { + "epoch": 0.58, + "learning_rate": 8.04394749414115e-06, + "loss": 0.4621, + "step": 6882 + }, + { + "epoch": 0.58, + "learning_rate": 8.041290009185325e-06, + "loss": 0.4772, + "step": 6883 + }, + { + "epoch": 0.58, + "learning_rate": 8.038632668069011e-06, + "loss": 0.471, + "step": 6884 + }, + { + "epoch": 0.58, + "learning_rate": 8.035975470987357e-06, + "loss": 0.4558, + "step": 6885 + }, + { + "epoch": 0.58, + "learning_rate": 8.033318418135494e-06, + "loss": 0.4728, + "step": 6886 + }, + { + "epoch": 0.58, + "learning_rate": 8.03066150970855e-06, + "loss": 0.4667, + "step": 6887 + }, + { + "epoch": 0.58, + "learning_rate": 8.02800474590163e-06, + "loss": 0.4804, + "step": 6888 + }, + { + "epoch": 0.58, + "learning_rate": 8.025348126909837e-06, + "loss": 0.4809, + "step": 6889 + }, + { + "epoch": 0.58, + "learning_rate": 8.02269165292827e-06, + "loss": 0.4799, + "step": 6890 + }, + { + "epoch": 0.58, + "learning_rate": 8.020035324152e-06, + "loss": 0.456, + "step": 6891 + }, + { + "epoch": 0.58, + "learning_rate": 8.017379140776103e-06, + "loss": 0.4874, + "step": 6892 + }, + { + "epoch": 0.58, + "learning_rate": 8.014723102995635e-06, + "loss": 0.4772, + "step": 6893 + }, + { + "epoch": 0.58, + "learning_rate": 8.012067211005645e-06, + "loss": 0.4651, + "step": 6894 + }, + { + "epoch": 0.58, + "learning_rate": 8.00941146500117e-06, + "loss": 0.4828, + "step": 6895 + }, + { + "epoch": 0.58, + "learning_rate": 8.006755865177233e-06, + "loss": 0.4682, + "step": 6896 + }, + { + "epoch": 0.58, + "learning_rate": 8.00410041172886e-06, + "loss": 0.4852, + "step": 6897 + }, + { + "epoch": 0.58, + "learning_rate": 8.001445104851052e-06, + "loss": 0.4691, + "step": 6898 + }, + { + "epoch": 0.58, + "learning_rate": 7.998789944738801e-06, + "loss": 0.4742, + "step": 6899 + }, + { + "epoch": 0.58, + "learning_rate": 7.996134931587092e-06, + "loss": 0.4673, + "step": 6900 + }, + { + "epoch": 0.58, + "learning_rate": 7.993480065590902e-06, + "loss": 0.502, + "step": 6901 + }, + { + "epoch": 0.58, + "learning_rate": 7.990825346945188e-06, + "loss": 0.4744, + "step": 6902 + }, + { + "epoch": 0.58, + "learning_rate": 7.9881707758449e-06, + "loss": 0.4806, + "step": 6903 + }, + { + "epoch": 0.58, + "learning_rate": 7.985516352484987e-06, + "loss": 0.4837, + "step": 6904 + }, + { + "epoch": 0.58, + "learning_rate": 7.982862077060376e-06, + "loss": 0.4685, + "step": 6905 + }, + { + "epoch": 0.58, + "learning_rate": 7.98020794976598e-06, + "loss": 0.466, + "step": 6906 + }, + { + "epoch": 0.58, + "learning_rate": 7.977553970796713e-06, + "loss": 0.4756, + "step": 6907 + }, + { + "epoch": 0.58, + "learning_rate": 7.974900140347473e-06, + "loss": 0.472, + "step": 6908 + }, + { + "epoch": 0.58, + "learning_rate": 7.97224645861314e-06, + "loss": 0.4496, + "step": 6909 + }, + { + "epoch": 0.58, + "learning_rate": 7.969592925788592e-06, + "loss": 0.4872, + "step": 6910 + }, + { + "epoch": 0.58, + "learning_rate": 7.966939542068694e-06, + "loss": 0.4819, + "step": 6911 + }, + { + "epoch": 0.58, + "learning_rate": 7.964286307648305e-06, + "loss": 0.4716, + "step": 6912 + }, + { + "epoch": 0.58, + "learning_rate": 7.96163322272226e-06, + "loss": 0.4722, + "step": 6913 + }, + { + "epoch": 0.58, + "learning_rate": 7.958980287485394e-06, + "loss": 0.4683, + "step": 6914 + }, + { + "epoch": 0.58, + "learning_rate": 7.956327502132523e-06, + "loss": 0.4634, + "step": 6915 + }, + { + "epoch": 0.58, + "learning_rate": 7.953674866858462e-06, + "loss": 0.4692, + "step": 6916 + }, + { + "epoch": 0.58, + "learning_rate": 7.951022381858005e-06, + "loss": 0.4735, + "step": 6917 + }, + { + "epoch": 0.58, + "learning_rate": 7.948370047325946e-06, + "loss": 0.4642, + "step": 6918 + }, + { + "epoch": 0.58, + "learning_rate": 7.945717863457057e-06, + "loss": 0.4884, + "step": 6919 + }, + { + "epoch": 0.58, + "learning_rate": 7.943065830446104e-06, + "loss": 0.4975, + "step": 6920 + }, + { + "epoch": 0.58, + "learning_rate": 7.940413948487838e-06, + "loss": 0.5001, + "step": 6921 + }, + { + "epoch": 0.58, + "learning_rate": 7.937762217777007e-06, + "loss": 0.4835, + "step": 6922 + }, + { + "epoch": 0.58, + "learning_rate": 7.935110638508339e-06, + "loss": 0.4903, + "step": 6923 + }, + { + "epoch": 0.58, + "learning_rate": 7.93245921087656e-06, + "loss": 0.4688, + "step": 6924 + }, + { + "epoch": 0.58, + "learning_rate": 7.929807935076376e-06, + "loss": 0.4764, + "step": 6925 + }, + { + "epoch": 0.58, + "learning_rate": 7.927156811302486e-06, + "loss": 0.4792, + "step": 6926 + }, + { + "epoch": 0.58, + "learning_rate": 7.92450583974958e-06, + "loss": 0.4833, + "step": 6927 + }, + { + "epoch": 0.58, + "learning_rate": 7.921855020612333e-06, + "loss": 0.4812, + "step": 6928 + }, + { + "epoch": 0.58, + "learning_rate": 7.919204354085408e-06, + "loss": 0.4649, + "step": 6929 + }, + { + "epoch": 0.58, + "learning_rate": 7.916553840363458e-06, + "loss": 0.4554, + "step": 6930 + }, + { + "epoch": 0.58, + "learning_rate": 7.913903479641131e-06, + "loss": 0.4636, + "step": 6931 + }, + { + "epoch": 0.58, + "learning_rate": 7.911253272113056e-06, + "loss": 0.5109, + "step": 6932 + }, + { + "epoch": 0.58, + "learning_rate": 7.908603217973853e-06, + "loss": 0.4811, + "step": 6933 + }, + { + "epoch": 0.58, + "learning_rate": 7.905953317418131e-06, + "loss": 0.4753, + "step": 6934 + }, + { + "epoch": 0.58, + "learning_rate": 7.903303570640488e-06, + "loss": 0.4691, + "step": 6935 + }, + { + "epoch": 0.58, + "learning_rate": 7.900653977835507e-06, + "loss": 0.4661, + "step": 6936 + }, + { + "epoch": 0.58, + "learning_rate": 7.898004539197766e-06, + "loss": 0.4696, + "step": 6937 + }, + { + "epoch": 0.58, + "learning_rate": 7.89535525492183e-06, + "loss": 0.4606, + "step": 6938 + }, + { + "epoch": 0.58, + "learning_rate": 7.892706125202254e-06, + "loss": 0.4798, + "step": 6939 + }, + { + "epoch": 0.58, + "learning_rate": 7.890057150233572e-06, + "loss": 0.4586, + "step": 6940 + }, + { + "epoch": 0.58, + "learning_rate": 7.887408330210316e-06, + "loss": 0.4835, + "step": 6941 + }, + { + "epoch": 0.58, + "learning_rate": 7.884759665327008e-06, + "loss": 0.4821, + "step": 6942 + }, + { + "epoch": 0.58, + "learning_rate": 7.882111155778152e-06, + "loss": 0.4927, + "step": 6943 + }, + { + "epoch": 0.58, + "learning_rate": 7.879462801758239e-06, + "loss": 0.4873, + "step": 6944 + }, + { + "epoch": 0.58, + "learning_rate": 7.876814603461763e-06, + "loss": 0.4801, + "step": 6945 + }, + { + "epoch": 0.58, + "learning_rate": 7.87416656108319e-06, + "loss": 0.476, + "step": 6946 + }, + { + "epoch": 0.58, + "learning_rate": 7.871518674816982e-06, + "loss": 0.464, + "step": 6947 + }, + { + "epoch": 0.58, + "learning_rate": 7.86887094485759e-06, + "loss": 0.4831, + "step": 6948 + }, + { + "epoch": 0.58, + "learning_rate": 7.866223371399453e-06, + "loss": 0.4791, + "step": 6949 + }, + { + "epoch": 0.58, + "learning_rate": 7.863575954636993e-06, + "loss": 0.4936, + "step": 6950 + }, + { + "epoch": 0.58, + "learning_rate": 7.860928694764632e-06, + "loss": 0.4846, + "step": 6951 + }, + { + "epoch": 0.58, + "learning_rate": 7.858281591976768e-06, + "loss": 0.4687, + "step": 6952 + }, + { + "epoch": 0.58, + "learning_rate": 7.8556346464678e-06, + "loss": 0.4587, + "step": 6953 + }, + { + "epoch": 0.58, + "learning_rate": 7.852987858432104e-06, + "loss": 0.4825, + "step": 6954 + }, + { + "epoch": 0.58, + "learning_rate": 7.850341228064048e-06, + "loss": 0.4723, + "step": 6955 + }, + { + "epoch": 0.58, + "learning_rate": 7.84769475555799e-06, + "loss": 0.4522, + "step": 6956 + }, + { + "epoch": 0.58, + "learning_rate": 7.845048441108276e-06, + "loss": 0.484, + "step": 6957 + }, + { + "epoch": 0.58, + "learning_rate": 7.842402284909242e-06, + "loss": 0.4794, + "step": 6958 + }, + { + "epoch": 0.58, + "learning_rate": 7.839756287155213e-06, + "loss": 0.4794, + "step": 6959 + }, + { + "epoch": 0.58, + "learning_rate": 7.837110448040495e-06, + "loss": 0.4825, + "step": 6960 + }, + { + "epoch": 0.58, + "learning_rate": 7.834464767759392e-06, + "loss": 0.4612, + "step": 6961 + }, + { + "epoch": 0.58, + "learning_rate": 7.831819246506187e-06, + "loss": 0.4708, + "step": 6962 + }, + { + "epoch": 0.58, + "learning_rate": 7.829173884475158e-06, + "loss": 0.4607, + "step": 6963 + }, + { + "epoch": 0.58, + "learning_rate": 7.826528681860567e-06, + "loss": 0.4605, + "step": 6964 + }, + { + "epoch": 0.58, + "learning_rate": 7.823883638856675e-06, + "loss": 0.4779, + "step": 6965 + }, + { + "epoch": 0.58, + "learning_rate": 7.821238755657716e-06, + "loss": 0.4447, + "step": 6966 + }, + { + "epoch": 0.58, + "learning_rate": 7.818594032457922e-06, + "loss": 0.4876, + "step": 6967 + }, + { + "epoch": 0.58, + "learning_rate": 7.815949469451506e-06, + "loss": 0.4654, + "step": 6968 + }, + { + "epoch": 0.58, + "learning_rate": 7.813305066832679e-06, + "loss": 0.4654, + "step": 6969 + }, + { + "epoch": 0.58, + "learning_rate": 7.810660824795632e-06, + "loss": 0.4729, + "step": 6970 + }, + { + "epoch": 0.58, + "learning_rate": 7.808016743534546e-06, + "loss": 0.4886, + "step": 6971 + }, + { + "epoch": 0.58, + "learning_rate": 7.805372823243595e-06, + "loss": 0.4669, + "step": 6972 + }, + { + "epoch": 0.58, + "learning_rate": 7.802729064116933e-06, + "loss": 0.4781, + "step": 6973 + }, + { + "epoch": 0.58, + "learning_rate": 7.800085466348715e-06, + "loss": 0.485, + "step": 6974 + }, + { + "epoch": 0.58, + "learning_rate": 7.797442030133067e-06, + "loss": 0.4754, + "step": 6975 + }, + { + "epoch": 0.58, + "learning_rate": 7.794798755664116e-06, + "loss": 0.4706, + "step": 6976 + }, + { + "epoch": 0.58, + "learning_rate": 7.79215564313597e-06, + "loss": 0.476, + "step": 6977 + }, + { + "epoch": 0.58, + "learning_rate": 7.789512692742731e-06, + "loss": 0.4709, + "step": 6978 + }, + { + "epoch": 0.58, + "learning_rate": 7.786869904678486e-06, + "loss": 0.481, + "step": 6979 + }, + { + "epoch": 0.58, + "learning_rate": 7.784227279137314e-06, + "loss": 0.4754, + "step": 6980 + }, + { + "epoch": 0.58, + "learning_rate": 7.781584816313271e-06, + "loss": 0.4683, + "step": 6981 + }, + { + "epoch": 0.58, + "learning_rate": 7.778942516400413e-06, + "loss": 0.4823, + "step": 6982 + }, + { + "epoch": 0.58, + "learning_rate": 7.776300379592778e-06, + "loss": 0.4723, + "step": 6983 + }, + { + "epoch": 0.58, + "learning_rate": 7.773658406084395e-06, + "loss": 0.4722, + "step": 6984 + }, + { + "epoch": 0.58, + "learning_rate": 7.771016596069273e-06, + "loss": 0.478, + "step": 6985 + }, + { + "epoch": 0.58, + "learning_rate": 7.768374949741427e-06, + "loss": 0.474, + "step": 6986 + }, + { + "epoch": 0.58, + "learning_rate": 7.765733467294842e-06, + "loss": 0.4582, + "step": 6987 + }, + { + "epoch": 0.58, + "learning_rate": 7.763092148923496e-06, + "loss": 0.4778, + "step": 6988 + }, + { + "epoch": 0.58, + "learning_rate": 7.760450994821363e-06, + "loss": 0.4914, + "step": 6989 + }, + { + "epoch": 0.58, + "learning_rate": 7.757810005182391e-06, + "loss": 0.4729, + "step": 6990 + }, + { + "epoch": 0.58, + "learning_rate": 7.755169180200524e-06, + "loss": 0.4858, + "step": 6991 + }, + { + "epoch": 0.58, + "learning_rate": 7.752528520069697e-06, + "loss": 0.4731, + "step": 6992 + }, + { + "epoch": 0.59, + "learning_rate": 7.74988802498383e-06, + "loss": 0.4915, + "step": 6993 + }, + { + "epoch": 0.59, + "learning_rate": 7.747247695136825e-06, + "loss": 0.4868, + "step": 6994 + }, + { + "epoch": 0.59, + "learning_rate": 7.74460753072258e-06, + "loss": 0.484, + "step": 6995 + }, + { + "epoch": 0.59, + "learning_rate": 7.74196753193498e-06, + "loss": 0.4831, + "step": 6996 + }, + { + "epoch": 0.59, + "learning_rate": 7.739327698967891e-06, + "loss": 0.4833, + "step": 6997 + }, + { + "epoch": 0.59, + "learning_rate": 7.736688032015168e-06, + "loss": 0.4727, + "step": 6998 + }, + { + "epoch": 0.59, + "learning_rate": 7.734048531270664e-06, + "loss": 0.4703, + "step": 6999 + }, + { + "epoch": 0.59, + "learning_rate": 7.731409196928214e-06, + "loss": 0.438, + "step": 7000 + }, + { + "epoch": 0.59, + "learning_rate": 7.728770029181638e-06, + "loss": 0.4715, + "step": 7001 + }, + { + "epoch": 0.59, + "learning_rate": 7.726131028224742e-06, + "loss": 0.4702, + "step": 7002 + }, + { + "epoch": 0.59, + "learning_rate": 7.723492194251326e-06, + "loss": 0.4689, + "step": 7003 + }, + { + "epoch": 0.59, + "learning_rate": 7.720853527455174e-06, + "loss": 0.4701, + "step": 7004 + }, + { + "epoch": 0.59, + "learning_rate": 7.718215028030056e-06, + "loss": 0.475, + "step": 7005 + }, + { + "epoch": 0.59, + "learning_rate": 7.71557669616974e-06, + "loss": 0.4504, + "step": 7006 + }, + { + "epoch": 0.59, + "learning_rate": 7.71293853206797e-06, + "loss": 0.4582, + "step": 7007 + }, + { + "epoch": 0.59, + "learning_rate": 7.710300535918482e-06, + "loss": 0.4723, + "step": 7008 + }, + { + "epoch": 0.59, + "learning_rate": 7.707662707914997e-06, + "loss": 0.4739, + "step": 7009 + }, + { + "epoch": 0.59, + "learning_rate": 7.705025048251228e-06, + "loss": 0.4664, + "step": 7010 + }, + { + "epoch": 0.59, + "learning_rate": 7.702387557120876e-06, + "loss": 0.4789, + "step": 7011 + }, + { + "epoch": 0.59, + "learning_rate": 7.699750234717622e-06, + "loss": 0.4828, + "step": 7012 + }, + { + "epoch": 0.59, + "learning_rate": 7.697113081235147e-06, + "loss": 0.4587, + "step": 7013 + }, + { + "epoch": 0.59, + "learning_rate": 7.694476096867105e-06, + "loss": 0.4863, + "step": 7014 + }, + { + "epoch": 0.59, + "learning_rate": 7.691839281807153e-06, + "loss": 0.4657, + "step": 7015 + }, + { + "epoch": 0.59, + "learning_rate": 7.689202636248923e-06, + "loss": 0.4932, + "step": 7016 + }, + { + "epoch": 0.59, + "learning_rate": 7.68656616038604e-06, + "loss": 0.4581, + "step": 7017 + }, + { + "epoch": 0.59, + "learning_rate": 7.683929854412114e-06, + "loss": 0.4734, + "step": 7018 + }, + { + "epoch": 0.59, + "learning_rate": 7.681293718520746e-06, + "loss": 0.4629, + "step": 7019 + }, + { + "epoch": 0.59, + "learning_rate": 7.678657752905522e-06, + "loss": 0.4578, + "step": 7020 + }, + { + "epoch": 0.59, + "learning_rate": 7.676021957760023e-06, + "loss": 0.4507, + "step": 7021 + }, + { + "epoch": 0.59, + "learning_rate": 7.673386333277802e-06, + "loss": 0.4571, + "step": 7022 + }, + { + "epoch": 0.59, + "learning_rate": 7.670750879652414e-06, + "loss": 0.4914, + "step": 7023 + }, + { + "epoch": 0.59, + "learning_rate": 7.668115597077388e-06, + "loss": 0.4869, + "step": 7024 + }, + { + "epoch": 0.59, + "learning_rate": 7.665480485746255e-06, + "loss": 0.4831, + "step": 7025 + }, + { + "epoch": 0.59, + "learning_rate": 7.662845545852526e-06, + "loss": 0.4795, + "step": 7026 + }, + { + "epoch": 0.59, + "learning_rate": 7.6602107775897e-06, + "loss": 0.4938, + "step": 7027 + }, + { + "epoch": 0.59, + "learning_rate": 7.657576181151266e-06, + "loss": 0.4709, + "step": 7028 + }, + { + "epoch": 0.59, + "learning_rate": 7.654941756730687e-06, + "loss": 0.4714, + "step": 7029 + }, + { + "epoch": 0.59, + "learning_rate": 7.652307504521437e-06, + "loss": 0.4525, + "step": 7030 + }, + { + "epoch": 0.59, + "learning_rate": 7.649673424716958e-06, + "loss": 0.4659, + "step": 7031 + }, + { + "epoch": 0.59, + "learning_rate": 7.647039517510685e-06, + "loss": 0.4626, + "step": 7032 + }, + { + "epoch": 0.59, + "learning_rate": 7.644405783096044e-06, + "loss": 0.4977, + "step": 7033 + }, + { + "epoch": 0.59, + "learning_rate": 7.641772221666446e-06, + "loss": 0.4793, + "step": 7034 + }, + { + "epoch": 0.59, + "learning_rate": 7.639138833415285e-06, + "loss": 0.4711, + "step": 7035 + }, + { + "epoch": 0.59, + "learning_rate": 7.636505618535953e-06, + "loss": 0.4851, + "step": 7036 + }, + { + "epoch": 0.59, + "learning_rate": 7.633872577221815e-06, + "loss": 0.4648, + "step": 7037 + }, + { + "epoch": 0.59, + "learning_rate": 7.631239709666234e-06, + "loss": 0.4492, + "step": 7038 + }, + { + "epoch": 0.59, + "learning_rate": 7.628607016062553e-06, + "loss": 0.4862, + "step": 7039 + }, + { + "epoch": 0.59, + "learning_rate": 7.625974496604109e-06, + "loss": 0.4618, + "step": 7040 + }, + { + "epoch": 0.59, + "learning_rate": 7.623342151484229e-06, + "loss": 0.457, + "step": 7041 + }, + { + "epoch": 0.59, + "learning_rate": 7.620709980896215e-06, + "loss": 0.4916, + "step": 7042 + }, + { + "epoch": 0.59, + "learning_rate": 7.618077985033363e-06, + "loss": 0.5061, + "step": 7043 + }, + { + "epoch": 0.59, + "learning_rate": 7.6154461640889555e-06, + "loss": 0.4657, + "step": 7044 + }, + { + "epoch": 0.59, + "learning_rate": 7.612814518256265e-06, + "loss": 0.4678, + "step": 7045 + }, + { + "epoch": 0.59, + "learning_rate": 7.610183047728543e-06, + "loss": 0.4981, + "step": 7046 + }, + { + "epoch": 0.59, + "learning_rate": 7.607551752699043e-06, + "loss": 0.4745, + "step": 7047 + }, + { + "epoch": 0.59, + "learning_rate": 7.604920633360991e-06, + "loss": 0.4684, + "step": 7048 + }, + { + "epoch": 0.59, + "learning_rate": 7.6022896899076045e-06, + "loss": 0.4702, + "step": 7049 + }, + { + "epoch": 0.59, + "learning_rate": 7.59965892253209e-06, + "loss": 0.4809, + "step": 7050 + }, + { + "epoch": 0.59, + "learning_rate": 7.597028331427643e-06, + "loss": 0.4865, + "step": 7051 + }, + { + "epoch": 0.59, + "learning_rate": 7.594397916787439e-06, + "loss": 0.4956, + "step": 7052 + }, + { + "epoch": 0.59, + "learning_rate": 7.591767678804642e-06, + "loss": 0.4843, + "step": 7053 + }, + { + "epoch": 0.59, + "learning_rate": 7.589137617672415e-06, + "loss": 0.4779, + "step": 7054 + }, + { + "epoch": 0.59, + "learning_rate": 7.586507733583892e-06, + "loss": 0.4786, + "step": 7055 + }, + { + "epoch": 0.59, + "learning_rate": 7.583878026732204e-06, + "loss": 0.4609, + "step": 7056 + }, + { + "epoch": 0.59, + "learning_rate": 7.581248497310465e-06, + "loss": 0.4686, + "step": 7057 + }, + { + "epoch": 0.59, + "learning_rate": 7.5786191455117765e-06, + "loss": 0.479, + "step": 7058 + }, + { + "epoch": 0.59, + "learning_rate": 7.575989971529223e-06, + "loss": 0.4769, + "step": 7059 + }, + { + "epoch": 0.59, + "learning_rate": 7.573360975555885e-06, + "loss": 0.4699, + "step": 7060 + }, + { + "epoch": 0.59, + "learning_rate": 7.570732157784823e-06, + "loss": 0.5061, + "step": 7061 + }, + { + "epoch": 0.59, + "learning_rate": 7.56810351840909e-06, + "loss": 0.4889, + "step": 7062 + }, + { + "epoch": 0.59, + "learning_rate": 7.56547505762172e-06, + "loss": 0.4664, + "step": 7063 + }, + { + "epoch": 0.59, + "learning_rate": 7.562846775615734e-06, + "loss": 0.4808, + "step": 7064 + }, + { + "epoch": 0.59, + "learning_rate": 7.560218672584143e-06, + "loss": 0.487, + "step": 7065 + }, + { + "epoch": 0.59, + "learning_rate": 7.557590748719943e-06, + "loss": 0.4975, + "step": 7066 + }, + { + "epoch": 0.59, + "learning_rate": 7.5549630042161236e-06, + "loss": 0.4613, + "step": 7067 + }, + { + "epoch": 0.59, + "learning_rate": 7.552335439265652e-06, + "loss": 0.4905, + "step": 7068 + }, + { + "epoch": 0.59, + "learning_rate": 7.549708054061484e-06, + "loss": 0.4649, + "step": 7069 + }, + { + "epoch": 0.59, + "learning_rate": 7.547080848796564e-06, + "loss": 0.5153, + "step": 7070 + }, + { + "epoch": 0.59, + "learning_rate": 7.544453823663825e-06, + "loss": 0.4835, + "step": 7071 + }, + { + "epoch": 0.59, + "learning_rate": 7.541826978856185e-06, + "loss": 0.4816, + "step": 7072 + }, + { + "epoch": 0.59, + "learning_rate": 7.539200314566543e-06, + "loss": 0.465, + "step": 7073 + }, + { + "epoch": 0.59, + "learning_rate": 7.536573830987798e-06, + "loss": 0.4549, + "step": 7074 + }, + { + "epoch": 0.59, + "learning_rate": 7.533947528312825e-06, + "loss": 0.4682, + "step": 7075 + }, + { + "epoch": 0.59, + "learning_rate": 7.531321406734486e-06, + "loss": 0.456, + "step": 7076 + }, + { + "epoch": 0.59, + "learning_rate": 7.528695466445638e-06, + "loss": 0.4794, + "step": 7077 + }, + { + "epoch": 0.59, + "learning_rate": 7.526069707639115e-06, + "loss": 0.461, + "step": 7078 + }, + { + "epoch": 0.59, + "learning_rate": 7.523444130507743e-06, + "loss": 0.4683, + "step": 7079 + }, + { + "epoch": 0.59, + "learning_rate": 7.52081873524433e-06, + "loss": 0.471, + "step": 7080 + }, + { + "epoch": 0.59, + "learning_rate": 7.518193522041679e-06, + "loss": 0.4773, + "step": 7081 + }, + { + "epoch": 0.59, + "learning_rate": 7.5155684910925754e-06, + "loss": 0.472, + "step": 7082 + }, + { + "epoch": 0.59, + "learning_rate": 7.5129436425897876e-06, + "loss": 0.4755, + "step": 7083 + }, + { + "epoch": 0.59, + "learning_rate": 7.510318976726074e-06, + "loss": 0.4634, + "step": 7084 + }, + { + "epoch": 0.59, + "learning_rate": 7.507694493694179e-06, + "loss": 0.476, + "step": 7085 + }, + { + "epoch": 0.59, + "learning_rate": 7.505070193686835e-06, + "loss": 0.4749, + "step": 7086 + }, + { + "epoch": 0.59, + "learning_rate": 7.502446076896754e-06, + "loss": 0.4622, + "step": 7087 + }, + { + "epoch": 0.59, + "learning_rate": 7.4998221435166504e-06, + "loss": 0.4815, + "step": 7088 + }, + { + "epoch": 0.59, + "learning_rate": 7.497198393739209e-06, + "loss": 0.4569, + "step": 7089 + }, + { + "epoch": 0.59, + "learning_rate": 7.494574827757107e-06, + "loss": 0.4719, + "step": 7090 + }, + { + "epoch": 0.59, + "learning_rate": 7.4919514457630085e-06, + "loss": 0.4518, + "step": 7091 + }, + { + "epoch": 0.59, + "learning_rate": 7.489328247949565e-06, + "loss": 0.4851, + "step": 7092 + }, + { + "epoch": 0.59, + "learning_rate": 7.486705234509412e-06, + "loss": 0.4957, + "step": 7093 + }, + { + "epoch": 0.59, + "learning_rate": 7.484082405635169e-06, + "loss": 0.4889, + "step": 7094 + }, + { + "epoch": 0.59, + "learning_rate": 7.481459761519454e-06, + "loss": 0.4776, + "step": 7095 + }, + { + "epoch": 0.59, + "learning_rate": 7.478837302354859e-06, + "loss": 0.4728, + "step": 7096 + }, + { + "epoch": 0.59, + "learning_rate": 7.476215028333964e-06, + "loss": 0.4643, + "step": 7097 + }, + { + "epoch": 0.59, + "learning_rate": 7.473592939649341e-06, + "loss": 0.468, + "step": 7098 + }, + { + "epoch": 0.59, + "learning_rate": 7.470971036493546e-06, + "loss": 0.4845, + "step": 7099 + }, + { + "epoch": 0.59, + "learning_rate": 7.468349319059114e-06, + "loss": 0.4818, + "step": 7100 + }, + { + "epoch": 0.59, + "learning_rate": 7.465727787538584e-06, + "loss": 0.4749, + "step": 7101 + }, + { + "epoch": 0.59, + "learning_rate": 7.463106442124459e-06, + "loss": 0.477, + "step": 7102 + }, + { + "epoch": 0.59, + "learning_rate": 7.46048528300925e-06, + "loss": 0.4793, + "step": 7103 + }, + { + "epoch": 0.59, + "learning_rate": 7.457864310385439e-06, + "loss": 0.4767, + "step": 7104 + }, + { + "epoch": 0.59, + "learning_rate": 7.455243524445499e-06, + "loss": 0.474, + "step": 7105 + }, + { + "epoch": 0.59, + "learning_rate": 7.452622925381887e-06, + "loss": 0.4725, + "step": 7106 + }, + { + "epoch": 0.59, + "learning_rate": 7.450002513387053e-06, + "loss": 0.4833, + "step": 7107 + }, + { + "epoch": 0.59, + "learning_rate": 7.4473822886534285e-06, + "loss": 0.4849, + "step": 7108 + }, + { + "epoch": 0.59, + "learning_rate": 7.444762251373433e-06, + "loss": 0.498, + "step": 7109 + }, + { + "epoch": 0.59, + "learning_rate": 7.442142401739469e-06, + "loss": 0.4671, + "step": 7110 + }, + { + "epoch": 0.59, + "learning_rate": 7.439522739943929e-06, + "loss": 0.4719, + "step": 7111 + }, + { + "epoch": 0.6, + "learning_rate": 7.436903266179187e-06, + "loss": 0.4683, + "step": 7112 + }, + { + "epoch": 0.6, + "learning_rate": 7.434283980637611e-06, + "loss": 0.4745, + "step": 7113 + }, + { + "epoch": 0.6, + "learning_rate": 7.4316648835115445e-06, + "loss": 0.4699, + "step": 7114 + }, + { + "epoch": 0.6, + "learning_rate": 7.4290459749933296e-06, + "loss": 0.4847, + "step": 7115 + }, + { + "epoch": 0.6, + "learning_rate": 7.426427255275284e-06, + "loss": 0.5188, + "step": 7116 + }, + { + "epoch": 0.6, + "learning_rate": 7.423808724549715e-06, + "loss": 0.483, + "step": 7117 + }, + { + "epoch": 0.6, + "learning_rate": 7.421190383008921e-06, + "loss": 0.4699, + "step": 7118 + }, + { + "epoch": 0.6, + "learning_rate": 7.418572230845178e-06, + "loss": 0.4695, + "step": 7119 + }, + { + "epoch": 0.6, + "learning_rate": 7.4159542682507535e-06, + "loss": 0.4848, + "step": 7120 + }, + { + "epoch": 0.6, + "learning_rate": 7.413336495417896e-06, + "loss": 0.4621, + "step": 7121 + }, + { + "epoch": 0.6, + "learning_rate": 7.410718912538853e-06, + "loss": 0.464, + "step": 7122 + }, + { + "epoch": 0.6, + "learning_rate": 7.40810151980584e-06, + "loss": 0.4818, + "step": 7123 + }, + { + "epoch": 0.6, + "learning_rate": 7.405484317411071e-06, + "loss": 0.4593, + "step": 7124 + }, + { + "epoch": 0.6, + "learning_rate": 7.4028673055467456e-06, + "loss": 0.4669, + "step": 7125 + }, + { + "epoch": 0.6, + "learning_rate": 7.400250484405041e-06, + "loss": 0.4662, + "step": 7126 + }, + { + "epoch": 0.6, + "learning_rate": 7.397633854178125e-06, + "loss": 0.4847, + "step": 7127 + }, + { + "epoch": 0.6, + "learning_rate": 7.395017415058154e-06, + "loss": 0.4946, + "step": 7128 + }, + { + "epoch": 0.6, + "learning_rate": 7.3924011672372745e-06, + "loss": 0.4734, + "step": 7129 + }, + { + "epoch": 0.6, + "learning_rate": 7.3897851109076055e-06, + "loss": 0.4795, + "step": 7130 + }, + { + "epoch": 0.6, + "learning_rate": 7.387169246261262e-06, + "loss": 0.4637, + "step": 7131 + }, + { + "epoch": 0.6, + "learning_rate": 7.3845535734903385e-06, + "loss": 0.4562, + "step": 7132 + }, + { + "epoch": 0.6, + "learning_rate": 7.381938092786926e-06, + "loss": 0.4704, + "step": 7133 + }, + { + "epoch": 0.6, + "learning_rate": 7.37932280434309e-06, + "loss": 0.5288, + "step": 7134 + }, + { + "epoch": 0.6, + "learning_rate": 7.376707708350881e-06, + "loss": 0.4919, + "step": 7135 + }, + { + "epoch": 0.6, + "learning_rate": 7.374092805002353e-06, + "loss": 0.476, + "step": 7136 + }, + { + "epoch": 0.6, + "learning_rate": 7.371478094489526e-06, + "loss": 0.4844, + "step": 7137 + }, + { + "epoch": 0.6, + "learning_rate": 7.368863577004415e-06, + "loss": 0.4514, + "step": 7138 + }, + { + "epoch": 0.6, + "learning_rate": 7.3662492527390195e-06, + "loss": 0.4578, + "step": 7139 + }, + { + "epoch": 0.6, + "learning_rate": 7.363635121885324e-06, + "loss": 0.4904, + "step": 7140 + }, + { + "epoch": 0.6, + "learning_rate": 7.361021184635296e-06, + "loss": 0.4677, + "step": 7141 + }, + { + "epoch": 0.6, + "learning_rate": 7.358407441180901e-06, + "loss": 0.4727, + "step": 7142 + }, + { + "epoch": 0.6, + "learning_rate": 7.355793891714073e-06, + "loss": 0.4931, + "step": 7143 + }, + { + "epoch": 0.6, + "learning_rate": 7.353180536426746e-06, + "loss": 0.4635, + "step": 7144 + }, + { + "epoch": 0.6, + "learning_rate": 7.350567375510831e-06, + "loss": 0.4627, + "step": 7145 + }, + { + "epoch": 0.6, + "learning_rate": 7.347954409158229e-06, + "loss": 0.4851, + "step": 7146 + }, + { + "epoch": 0.6, + "learning_rate": 7.345341637560822e-06, + "loss": 0.4668, + "step": 7147 + }, + { + "epoch": 0.6, + "learning_rate": 7.3427290609104825e-06, + "loss": 0.4759, + "step": 7148 + }, + { + "epoch": 0.6, + "learning_rate": 7.34011667939907e-06, + "loss": 0.4839, + "step": 7149 + }, + { + "epoch": 0.6, + "learning_rate": 7.337504493218427e-06, + "loss": 0.4695, + "step": 7150 + }, + { + "epoch": 0.6, + "learning_rate": 7.33489250256038e-06, + "loss": 0.4707, + "step": 7151 + }, + { + "epoch": 0.6, + "learning_rate": 7.332280707616742e-06, + "loss": 0.4862, + "step": 7152 + }, + { + "epoch": 0.6, + "learning_rate": 7.329669108579312e-06, + "loss": 0.4982, + "step": 7153 + }, + { + "epoch": 0.6, + "learning_rate": 7.3270577056398765e-06, + "loss": 0.4853, + "step": 7154 + }, + { + "epoch": 0.6, + "learning_rate": 7.324446498990202e-06, + "loss": 0.46, + "step": 7155 + }, + { + "epoch": 0.6, + "learning_rate": 7.321835488822052e-06, + "loss": 0.489, + "step": 7156 + }, + { + "epoch": 0.6, + "learning_rate": 7.319224675327165e-06, + "loss": 0.4728, + "step": 7157 + }, + { + "epoch": 0.6, + "learning_rate": 7.316614058697264e-06, + "loss": 0.4661, + "step": 7158 + }, + { + "epoch": 0.6, + "learning_rate": 7.31400363912407e-06, + "loss": 0.4589, + "step": 7159 + }, + { + "epoch": 0.6, + "learning_rate": 7.311393416799275e-06, + "loss": 0.477, + "step": 7160 + }, + { + "epoch": 0.6, + "learning_rate": 7.308783391914566e-06, + "loss": 0.4748, + "step": 7161 + }, + { + "epoch": 0.6, + "learning_rate": 7.306173564661606e-06, + "loss": 0.4859, + "step": 7162 + }, + { + "epoch": 0.6, + "learning_rate": 7.303563935232059e-06, + "loss": 0.4681, + "step": 7163 + }, + { + "epoch": 0.6, + "learning_rate": 7.30095450381756e-06, + "loss": 0.4732, + "step": 7164 + }, + { + "epoch": 0.6, + "learning_rate": 7.298345270609738e-06, + "loss": 0.4953, + "step": 7165 + }, + { + "epoch": 0.6, + "learning_rate": 7.295736235800202e-06, + "loss": 0.4648, + "step": 7166 + }, + { + "epoch": 0.6, + "learning_rate": 7.293127399580548e-06, + "loss": 0.4667, + "step": 7167 + }, + { + "epoch": 0.6, + "learning_rate": 7.290518762142359e-06, + "loss": 0.4753, + "step": 7168 + }, + { + "epoch": 0.6, + "learning_rate": 7.287910323677199e-06, + "loss": 0.4855, + "step": 7169 + }, + { + "epoch": 0.6, + "learning_rate": 7.285302084376629e-06, + "loss": 0.4779, + "step": 7170 + }, + { + "epoch": 0.6, + "learning_rate": 7.282694044432182e-06, + "loss": 0.4729, + "step": 7171 + }, + { + "epoch": 0.6, + "learning_rate": 7.2800862040353834e-06, + "loss": 0.4795, + "step": 7172 + }, + { + "epoch": 0.6, + "learning_rate": 7.277478563377738e-06, + "loss": 0.4546, + "step": 7173 + }, + { + "epoch": 0.6, + "learning_rate": 7.274871122650746e-06, + "loss": 0.4783, + "step": 7174 + }, + { + "epoch": 0.6, + "learning_rate": 7.272263882045884e-06, + "loss": 0.484, + "step": 7175 + }, + { + "epoch": 0.6, + "learning_rate": 7.269656841754612e-06, + "loss": 0.4802, + "step": 7176 + }, + { + "epoch": 0.6, + "learning_rate": 7.2670500019683895e-06, + "loss": 0.4704, + "step": 7177 + }, + { + "epoch": 0.6, + "learning_rate": 7.264443362878648e-06, + "loss": 0.4744, + "step": 7178 + }, + { + "epoch": 0.6, + "learning_rate": 7.261836924676806e-06, + "loss": 0.4763, + "step": 7179 + }, + { + "epoch": 0.6, + "learning_rate": 7.259230687554273e-06, + "loss": 0.4847, + "step": 7180 + }, + { + "epoch": 0.6, + "learning_rate": 7.25662465170244e-06, + "loss": 0.4645, + "step": 7181 + }, + { + "epoch": 0.6, + "learning_rate": 7.254018817312676e-06, + "loss": 0.4808, + "step": 7182 + }, + { + "epoch": 0.6, + "learning_rate": 7.2514131845763535e-06, + "loss": 0.4698, + "step": 7183 + }, + { + "epoch": 0.6, + "learning_rate": 7.248807753684812e-06, + "loss": 0.4562, + "step": 7184 + }, + { + "epoch": 0.6, + "learning_rate": 7.246202524829389e-06, + "loss": 0.4745, + "step": 7185 + }, + { + "epoch": 0.6, + "learning_rate": 7.243597498201398e-06, + "loss": 0.474, + "step": 7186 + }, + { + "epoch": 0.6, + "learning_rate": 7.240992673992142e-06, + "loss": 0.4557, + "step": 7187 + }, + { + "epoch": 0.6, + "learning_rate": 7.238388052392906e-06, + "loss": 0.4624, + "step": 7188 + }, + { + "epoch": 0.6, + "learning_rate": 7.235783633594966e-06, + "loss": 0.4785, + "step": 7189 + }, + { + "epoch": 0.6, + "learning_rate": 7.2331794177895785e-06, + "loss": 0.4791, + "step": 7190 + }, + { + "epoch": 0.6, + "learning_rate": 7.230575405167989e-06, + "loss": 0.4867, + "step": 7191 + }, + { + "epoch": 0.6, + "learning_rate": 7.2279715959214216e-06, + "loss": 0.473, + "step": 7192 + }, + { + "epoch": 0.6, + "learning_rate": 7.2253679902410914e-06, + "loss": 0.4794, + "step": 7193 + }, + { + "epoch": 0.6, + "learning_rate": 7.2227645883181926e-06, + "loss": 0.4752, + "step": 7194 + }, + { + "epoch": 0.6, + "learning_rate": 7.220161390343914e-06, + "loss": 0.4562, + "step": 7195 + }, + { + "epoch": 0.6, + "learning_rate": 7.217558396509416e-06, + "loss": 0.4697, + "step": 7196 + }, + { + "epoch": 0.6, + "learning_rate": 7.214955607005861e-06, + "loss": 0.479, + "step": 7197 + }, + { + "epoch": 0.6, + "learning_rate": 7.212353022024381e-06, + "loss": 0.4691, + "step": 7198 + }, + { + "epoch": 0.6, + "learning_rate": 7.209750641756099e-06, + "loss": 0.5009, + "step": 7199 + }, + { + "epoch": 0.6, + "learning_rate": 7.2071484663921265e-06, + "loss": 0.4813, + "step": 7200 + }, + { + "epoch": 0.6, + "learning_rate": 7.2045464961235545e-06, + "loss": 0.4723, + "step": 7201 + }, + { + "epoch": 0.6, + "learning_rate": 7.2019447311414615e-06, + "loss": 0.4889, + "step": 7202 + }, + { + "epoch": 0.6, + "learning_rate": 7.199343171636903e-06, + "loss": 0.4896, + "step": 7203 + }, + { + "epoch": 0.6, + "learning_rate": 7.1967418178009396e-06, + "loss": 0.4664, + "step": 7204 + }, + { + "epoch": 0.6, + "learning_rate": 7.1941406698245945e-06, + "loss": 0.465, + "step": 7205 + }, + { + "epoch": 0.6, + "learning_rate": 7.1915397278988895e-06, + "loss": 0.4895, + "step": 7206 + }, + { + "epoch": 0.6, + "learning_rate": 7.188938992214827e-06, + "loss": 0.4543, + "step": 7207 + }, + { + "epoch": 0.6, + "learning_rate": 7.186338462963392e-06, + "loss": 0.4568, + "step": 7208 + }, + { + "epoch": 0.6, + "learning_rate": 7.183738140335556e-06, + "loss": 0.4777, + "step": 7209 + }, + { + "epoch": 0.6, + "learning_rate": 7.181138024522274e-06, + "loss": 0.4731, + "step": 7210 + }, + { + "epoch": 0.6, + "learning_rate": 7.1785381157144954e-06, + "loss": 0.4658, + "step": 7211 + }, + { + "epoch": 0.6, + "learning_rate": 7.175938414103143e-06, + "loss": 0.4924, + "step": 7212 + }, + { + "epoch": 0.6, + "learning_rate": 7.173338919879127e-06, + "loss": 0.4749, + "step": 7213 + }, + { + "epoch": 0.6, + "learning_rate": 7.170739633233341e-06, + "loss": 0.46, + "step": 7214 + }, + { + "epoch": 0.6, + "learning_rate": 7.168140554356671e-06, + "loss": 0.486, + "step": 7215 + }, + { + "epoch": 0.6, + "learning_rate": 7.165541683439976e-06, + "loss": 0.4737, + "step": 7216 + }, + { + "epoch": 0.6, + "learning_rate": 7.162943020674116e-06, + "loss": 0.4437, + "step": 7217 + }, + { + "epoch": 0.6, + "learning_rate": 7.160344566249918e-06, + "loss": 0.4727, + "step": 7218 + }, + { + "epoch": 0.6, + "learning_rate": 7.1577463203582056e-06, + "loss": 0.4749, + "step": 7219 + }, + { + "epoch": 0.6, + "learning_rate": 7.155148283189779e-06, + "loss": 0.4594, + "step": 7220 + }, + { + "epoch": 0.6, + "learning_rate": 7.152550454935432e-06, + "loss": 0.4536, + "step": 7221 + }, + { + "epoch": 0.6, + "learning_rate": 7.149952835785936e-06, + "loss": 0.4791, + "step": 7222 + }, + { + "epoch": 0.6, + "learning_rate": 7.147355425932045e-06, + "loss": 0.4786, + "step": 7223 + }, + { + "epoch": 0.6, + "learning_rate": 7.144758225564511e-06, + "loss": 0.4874, + "step": 7224 + }, + { + "epoch": 0.6, + "learning_rate": 7.1421612348740564e-06, + "loss": 0.4724, + "step": 7225 + }, + { + "epoch": 0.6, + "learning_rate": 7.139564454051393e-06, + "loss": 0.4492, + "step": 7226 + }, + { + "epoch": 0.6, + "learning_rate": 7.1369678832872205e-06, + "loss": 0.4765, + "step": 7227 + }, + { + "epoch": 0.6, + "learning_rate": 7.134371522772218e-06, + "loss": 0.4604, + "step": 7228 + }, + { + "epoch": 0.6, + "learning_rate": 7.131775372697051e-06, + "loss": 0.4776, + "step": 7229 + }, + { + "epoch": 0.6, + "learning_rate": 7.129179433252369e-06, + "loss": 0.4757, + "step": 7230 + }, + { + "epoch": 0.6, + "learning_rate": 7.126583704628811e-06, + "loss": 0.4783, + "step": 7231 + }, + { + "epoch": 0.61, + "learning_rate": 7.123988187016994e-06, + "loss": 0.4575, + "step": 7232 + }, + { + "epoch": 0.61, + "learning_rate": 7.121392880607524e-06, + "loss": 0.4542, + "step": 7233 + }, + { + "epoch": 0.61, + "learning_rate": 7.118797785590987e-06, + "loss": 0.4811, + "step": 7234 + }, + { + "epoch": 0.61, + "learning_rate": 7.116202902157955e-06, + "loss": 0.4668, + "step": 7235 + }, + { + "epoch": 0.61, + "learning_rate": 7.113608230498989e-06, + "loss": 0.4617, + "step": 7236 + }, + { + "epoch": 0.61, + "learning_rate": 7.1110137708046245e-06, + "loss": 0.4798, + "step": 7237 + }, + { + "epoch": 0.61, + "learning_rate": 7.108419523265398e-06, + "loss": 0.4776, + "step": 7238 + }, + { + "epoch": 0.61, + "learning_rate": 7.105825488071814e-06, + "loss": 0.4692, + "step": 7239 + }, + { + "epoch": 0.61, + "learning_rate": 7.1032316654143685e-06, + "loss": 0.5049, + "step": 7240 + }, + { + "epoch": 0.61, + "learning_rate": 7.100638055483539e-06, + "loss": 0.497, + "step": 7241 + }, + { + "epoch": 0.61, + "learning_rate": 7.098044658469794e-06, + "loss": 0.4646, + "step": 7242 + }, + { + "epoch": 0.61, + "learning_rate": 7.095451474563577e-06, + "loss": 0.4768, + "step": 7243 + }, + { + "epoch": 0.61, + "learning_rate": 7.0928585039553196e-06, + "loss": 0.4877, + "step": 7244 + }, + { + "epoch": 0.61, + "learning_rate": 7.090265746835448e-06, + "loss": 0.4736, + "step": 7245 + }, + { + "epoch": 0.61, + "learning_rate": 7.087673203394353e-06, + "loss": 0.4889, + "step": 7246 + }, + { + "epoch": 0.61, + "learning_rate": 7.085080873822427e-06, + "loss": 0.4775, + "step": 7247 + }, + { + "epoch": 0.61, + "learning_rate": 7.082488758310039e-06, + "loss": 0.4754, + "step": 7248 + }, + { + "epoch": 0.61, + "learning_rate": 7.079896857047541e-06, + "loss": 0.4945, + "step": 7249 + }, + { + "epoch": 0.61, + "learning_rate": 7.07730517022527e-06, + "loss": 0.4771, + "step": 7250 + }, + { + "epoch": 0.61, + "learning_rate": 7.074713698033551e-06, + "loss": 0.4622, + "step": 7251 + }, + { + "epoch": 0.61, + "learning_rate": 7.0721224406626895e-06, + "loss": 0.4601, + "step": 7252 + }, + { + "epoch": 0.61, + "learning_rate": 7.069531398302982e-06, + "loss": 0.4758, + "step": 7253 + }, + { + "epoch": 0.61, + "learning_rate": 7.0669405711447e-06, + "loss": 0.4787, + "step": 7254 + }, + { + "epoch": 0.61, + "learning_rate": 7.064349959378102e-06, + "loss": 0.4817, + "step": 7255 + }, + { + "epoch": 0.61, + "learning_rate": 7.061759563193431e-06, + "loss": 0.4727, + "step": 7256 + }, + { + "epoch": 0.61, + "learning_rate": 7.059169382780914e-06, + "loss": 0.4839, + "step": 7257 + }, + { + "epoch": 0.61, + "learning_rate": 7.05657941833077e-06, + "loss": 0.4819, + "step": 7258 + }, + { + "epoch": 0.61, + "learning_rate": 7.053989670033191e-06, + "loss": 0.4709, + "step": 7259 + }, + { + "epoch": 0.61, + "learning_rate": 7.051400138078357e-06, + "loss": 0.5036, + "step": 7260 + }, + { + "epoch": 0.61, + "learning_rate": 7.048810822656431e-06, + "loss": 0.4635, + "step": 7261 + }, + { + "epoch": 0.61, + "learning_rate": 7.046221723957566e-06, + "loss": 0.4943, + "step": 7262 + }, + { + "epoch": 0.61, + "learning_rate": 7.043632842171891e-06, + "loss": 0.466, + "step": 7263 + }, + { + "epoch": 0.61, + "learning_rate": 7.04104417748952e-06, + "loss": 0.487, + "step": 7264 + }, + { + "epoch": 0.61, + "learning_rate": 7.038455730100562e-06, + "loss": 0.5054, + "step": 7265 + }, + { + "epoch": 0.61, + "learning_rate": 7.035867500195095e-06, + "loss": 0.4723, + "step": 7266 + }, + { + "epoch": 0.61, + "learning_rate": 7.033279487963189e-06, + "loss": 0.4646, + "step": 7267 + }, + { + "epoch": 0.61, + "learning_rate": 7.030691693594901e-06, + "loss": 0.49, + "step": 7268 + }, + { + "epoch": 0.61, + "learning_rate": 7.028104117280265e-06, + "loss": 0.4855, + "step": 7269 + }, + { + "epoch": 0.61, + "learning_rate": 7.0255167592092995e-06, + "loss": 0.4694, + "step": 7270 + }, + { + "epoch": 0.61, + "learning_rate": 7.022929619572009e-06, + "loss": 0.4606, + "step": 7271 + }, + { + "epoch": 0.61, + "learning_rate": 7.020342698558387e-06, + "loss": 0.4617, + "step": 7272 + }, + { + "epoch": 0.61, + "learning_rate": 7.017755996358404e-06, + "loss": 0.4771, + "step": 7273 + }, + { + "epoch": 0.61, + "learning_rate": 7.015169513162018e-06, + "loss": 0.4914, + "step": 7274 + }, + { + "epoch": 0.61, + "learning_rate": 7.012583249159167e-06, + "loss": 0.4829, + "step": 7275 + }, + { + "epoch": 0.61, + "learning_rate": 7.009997204539775e-06, + "loss": 0.488, + "step": 7276 + }, + { + "epoch": 0.61, + "learning_rate": 7.007411379493755e-06, + "loss": 0.4732, + "step": 7277 + }, + { + "epoch": 0.61, + "learning_rate": 7.004825774210992e-06, + "loss": 0.4704, + "step": 7278 + }, + { + "epoch": 0.61, + "learning_rate": 7.002240388881369e-06, + "loss": 0.4658, + "step": 7279 + }, + { + "epoch": 0.61, + "learning_rate": 6.999655223694743e-06, + "loss": 0.4793, + "step": 7280 + }, + { + "epoch": 0.61, + "learning_rate": 6.997070278840961e-06, + "loss": 0.4676, + "step": 7281 + }, + { + "epoch": 0.61, + "learning_rate": 6.994485554509842e-06, + "loss": 0.4818, + "step": 7282 + }, + { + "epoch": 0.61, + "learning_rate": 6.9919010508912075e-06, + "loss": 0.4762, + "step": 7283 + }, + { + "epoch": 0.61, + "learning_rate": 6.989316768174848e-06, + "loss": 0.4686, + "step": 7284 + }, + { + "epoch": 0.61, + "learning_rate": 6.986732706550536e-06, + "loss": 0.4748, + "step": 7285 + }, + { + "epoch": 0.61, + "learning_rate": 6.984148866208047e-06, + "loss": 0.4721, + "step": 7286 + }, + { + "epoch": 0.61, + "learning_rate": 6.98156524733712e-06, + "loss": 0.48, + "step": 7287 + }, + { + "epoch": 0.61, + "learning_rate": 6.978981850127487e-06, + "loss": 0.4841, + "step": 7288 + }, + { + "epoch": 0.61, + "learning_rate": 6.976398674768863e-06, + "loss": 0.4418, + "step": 7289 + }, + { + "epoch": 0.61, + "learning_rate": 6.973815721450942e-06, + "loss": 0.4861, + "step": 7290 + }, + { + "epoch": 0.61, + "learning_rate": 6.971232990363406e-06, + "loss": 0.4719, + "step": 7291 + }, + { + "epoch": 0.61, + "learning_rate": 6.968650481695926e-06, + "loss": 0.4704, + "step": 7292 + }, + { + "epoch": 0.61, + "learning_rate": 6.966068195638143e-06, + "loss": 0.4914, + "step": 7293 + }, + { + "epoch": 0.61, + "learning_rate": 6.963486132379694e-06, + "loss": 0.4566, + "step": 7294 + }, + { + "epoch": 0.61, + "learning_rate": 6.960904292110194e-06, + "loss": 0.4767, + "step": 7295 + }, + { + "epoch": 0.61, + "learning_rate": 6.958322675019243e-06, + "loss": 0.4918, + "step": 7296 + }, + { + "epoch": 0.61, + "learning_rate": 6.955741281296421e-06, + "loss": 0.4656, + "step": 7297 + }, + { + "epoch": 0.61, + "learning_rate": 6.953160111131295e-06, + "loss": 0.4493, + "step": 7298 + }, + { + "epoch": 0.61, + "learning_rate": 6.950579164713422e-06, + "loss": 0.4678, + "step": 7299 + }, + { + "epoch": 0.61, + "learning_rate": 6.947998442232332e-06, + "loss": 0.4811, + "step": 7300 + }, + { + "epoch": 0.61, + "learning_rate": 6.945417943877541e-06, + "loss": 0.4744, + "step": 7301 + }, + { + "epoch": 0.61, + "learning_rate": 6.942837669838552e-06, + "loss": 0.4583, + "step": 7302 + }, + { + "epoch": 0.61, + "learning_rate": 6.9402576203048474e-06, + "loss": 0.498, + "step": 7303 + }, + { + "epoch": 0.61, + "learning_rate": 6.937677795465898e-06, + "loss": 0.4433, + "step": 7304 + }, + { + "epoch": 0.61, + "learning_rate": 6.935098195511151e-06, + "loss": 0.4787, + "step": 7305 + }, + { + "epoch": 0.61, + "learning_rate": 6.932518820630048e-06, + "loss": 0.4839, + "step": 7306 + }, + { + "epoch": 0.61, + "learning_rate": 6.929939671012005e-06, + "loss": 0.4922, + "step": 7307 + }, + { + "epoch": 0.61, + "learning_rate": 6.9273607468464185e-06, + "loss": 0.451, + "step": 7308 + }, + { + "epoch": 0.61, + "learning_rate": 6.924782048322683e-06, + "loss": 0.4665, + "step": 7309 + }, + { + "epoch": 0.61, + "learning_rate": 6.922203575630164e-06, + "loss": 0.4927, + "step": 7310 + }, + { + "epoch": 0.61, + "learning_rate": 6.9196253289582104e-06, + "loss": 0.4512, + "step": 7311 + }, + { + "epoch": 0.61, + "learning_rate": 6.917047308496159e-06, + "loss": 0.4649, + "step": 7312 + }, + { + "epoch": 0.61, + "learning_rate": 6.914469514433331e-06, + "loss": 0.4551, + "step": 7313 + }, + { + "epoch": 0.61, + "learning_rate": 6.9118919469590285e-06, + "loss": 0.4659, + "step": 7314 + }, + { + "epoch": 0.61, + "learning_rate": 6.9093146062625395e-06, + "loss": 0.4642, + "step": 7315 + }, + { + "epoch": 0.61, + "learning_rate": 6.906737492533129e-06, + "loss": 0.4668, + "step": 7316 + }, + { + "epoch": 0.61, + "learning_rate": 6.904160605960051e-06, + "loss": 0.4703, + "step": 7317 + }, + { + "epoch": 0.61, + "learning_rate": 6.901583946732542e-06, + "loss": 0.4792, + "step": 7318 + }, + { + "epoch": 0.61, + "learning_rate": 6.899007515039817e-06, + "loss": 0.4782, + "step": 7319 + }, + { + "epoch": 0.61, + "learning_rate": 6.896431311071086e-06, + "loss": 0.4555, + "step": 7320 + }, + { + "epoch": 0.61, + "learning_rate": 6.893855335015532e-06, + "loss": 0.4866, + "step": 7321 + }, + { + "epoch": 0.61, + "learning_rate": 6.891279587062321e-06, + "loss": 0.4725, + "step": 7322 + }, + { + "epoch": 0.61, + "learning_rate": 6.888704067400605e-06, + "loss": 0.4588, + "step": 7323 + }, + { + "epoch": 0.61, + "learning_rate": 6.886128776219525e-06, + "loss": 0.4671, + "step": 7324 + }, + { + "epoch": 0.61, + "learning_rate": 6.8835537137081955e-06, + "loss": 0.4611, + "step": 7325 + }, + { + "epoch": 0.61, + "learning_rate": 6.880978880055716e-06, + "loss": 0.4666, + "step": 7326 + }, + { + "epoch": 0.61, + "learning_rate": 6.878404275451176e-06, + "loss": 0.473, + "step": 7327 + }, + { + "epoch": 0.61, + "learning_rate": 6.875829900083642e-06, + "loss": 0.4906, + "step": 7328 + }, + { + "epoch": 0.61, + "learning_rate": 6.873255754142167e-06, + "loss": 0.4585, + "step": 7329 + }, + { + "epoch": 0.61, + "learning_rate": 6.870681837815784e-06, + "loss": 0.4581, + "step": 7330 + }, + { + "epoch": 0.61, + "learning_rate": 6.868108151293513e-06, + "loss": 0.4791, + "step": 7331 + }, + { + "epoch": 0.61, + "learning_rate": 6.865534694764348e-06, + "loss": 0.4673, + "step": 7332 + }, + { + "epoch": 0.61, + "learning_rate": 6.86296146841728e-06, + "loss": 0.4584, + "step": 7333 + }, + { + "epoch": 0.61, + "learning_rate": 6.860388472441274e-06, + "loss": 0.4574, + "step": 7334 + }, + { + "epoch": 0.61, + "learning_rate": 6.8578157070252815e-06, + "loss": 0.4765, + "step": 7335 + }, + { + "epoch": 0.61, + "learning_rate": 6.8552431723582335e-06, + "loss": 0.4709, + "step": 7336 + }, + { + "epoch": 0.61, + "learning_rate": 6.852670868629048e-06, + "loss": 0.4589, + "step": 7337 + }, + { + "epoch": 0.61, + "learning_rate": 6.85009879602662e-06, + "loss": 0.4735, + "step": 7338 + }, + { + "epoch": 0.61, + "learning_rate": 6.8475269547398335e-06, + "loss": 0.4506, + "step": 7339 + }, + { + "epoch": 0.61, + "learning_rate": 6.844955344957559e-06, + "loss": 0.488, + "step": 7340 + }, + { + "epoch": 0.61, + "learning_rate": 6.842383966868642e-06, + "loss": 0.4864, + "step": 7341 + }, + { + "epoch": 0.61, + "learning_rate": 6.839812820661912e-06, + "loss": 0.4675, + "step": 7342 + }, + { + "epoch": 0.61, + "learning_rate": 6.837241906526182e-06, + "loss": 0.4823, + "step": 7343 + }, + { + "epoch": 0.61, + "learning_rate": 6.834671224650254e-06, + "loss": 0.4612, + "step": 7344 + }, + { + "epoch": 0.61, + "learning_rate": 6.832100775222906e-06, + "loss": 0.478, + "step": 7345 + }, + { + "epoch": 0.61, + "learning_rate": 6.829530558432898e-06, + "loss": 0.4456, + "step": 7346 + }, + { + "epoch": 0.61, + "learning_rate": 6.8269605744689805e-06, + "loss": 0.4765, + "step": 7347 + }, + { + "epoch": 0.61, + "learning_rate": 6.824390823519882e-06, + "loss": 0.481, + "step": 7348 + }, + { + "epoch": 0.61, + "learning_rate": 6.82182130577431e-06, + "loss": 0.4775, + "step": 7349 + }, + { + "epoch": 0.61, + "learning_rate": 6.819252021420966e-06, + "loss": 0.4842, + "step": 7350 + }, + { + "epoch": 0.62, + "learning_rate": 6.816682970648522e-06, + "loss": 0.4671, + "step": 7351 + }, + { + "epoch": 0.62, + "learning_rate": 6.814114153645641e-06, + "loss": 0.4894, + "step": 7352 + }, + { + "epoch": 0.62, + "learning_rate": 6.811545570600961e-06, + "loss": 0.4694, + "step": 7353 + }, + { + "epoch": 0.62, + "learning_rate": 6.808977221703115e-06, + "loss": 0.4797, + "step": 7354 + }, + { + "epoch": 0.62, + "learning_rate": 6.8064091071407115e-06, + "loss": 0.4816, + "step": 7355 + }, + { + "epoch": 0.62, + "learning_rate": 6.803841227102339e-06, + "loss": 0.4575, + "step": 7356 + }, + { + "epoch": 0.62, + "learning_rate": 6.801273581776575e-06, + "loss": 0.4852, + "step": 7357 + }, + { + "epoch": 0.62, + "learning_rate": 6.798706171351971e-06, + "loss": 0.4799, + "step": 7358 + }, + { + "epoch": 0.62, + "learning_rate": 6.796138996017073e-06, + "loss": 0.4692, + "step": 7359 + }, + { + "epoch": 0.62, + "learning_rate": 6.793572055960398e-06, + "loss": 0.4631, + "step": 7360 + }, + { + "epoch": 0.62, + "learning_rate": 6.791005351370458e-06, + "loss": 0.47, + "step": 7361 + }, + { + "epoch": 0.62, + "learning_rate": 6.788438882435737e-06, + "loss": 0.4797, + "step": 7362 + }, + { + "epoch": 0.62, + "learning_rate": 6.7858726493447084e-06, + "loss": 0.4582, + "step": 7363 + }, + { + "epoch": 0.62, + "learning_rate": 6.78330665228582e-06, + "loss": 0.4842, + "step": 7364 + }, + { + "epoch": 0.62, + "learning_rate": 6.780740891447515e-06, + "loss": 0.4711, + "step": 7365 + }, + { + "epoch": 0.62, + "learning_rate": 6.778175367018205e-06, + "loss": 0.4705, + "step": 7366 + }, + { + "epoch": 0.62, + "learning_rate": 6.775610079186299e-06, + "loss": 0.4719, + "step": 7367 + }, + { + "epoch": 0.62, + "learning_rate": 6.773045028140177e-06, + "loss": 0.474, + "step": 7368 + }, + { + "epoch": 0.62, + "learning_rate": 6.770480214068207e-06, + "loss": 0.4711, + "step": 7369 + }, + { + "epoch": 0.62, + "learning_rate": 6.767915637158735e-06, + "loss": 0.4732, + "step": 7370 + }, + { + "epoch": 0.62, + "learning_rate": 6.765351297600098e-06, + "loss": 0.5037, + "step": 7371 + }, + { + "epoch": 0.62, + "learning_rate": 6.762787195580609e-06, + "loss": 0.4625, + "step": 7372 + }, + { + "epoch": 0.62, + "learning_rate": 6.760223331288558e-06, + "loss": 0.4838, + "step": 7373 + }, + { + "epoch": 0.62, + "learning_rate": 6.757659704912234e-06, + "loss": 0.4613, + "step": 7374 + }, + { + "epoch": 0.62, + "learning_rate": 6.755096316639894e-06, + "loss": 0.4719, + "step": 7375 + }, + { + "epoch": 0.62, + "learning_rate": 6.752533166659786e-06, + "loss": 0.4777, + "step": 7376 + }, + { + "epoch": 0.62, + "learning_rate": 6.749970255160134e-06, + "loss": 0.4718, + "step": 7377 + }, + { + "epoch": 0.62, + "learning_rate": 6.747407582329151e-06, + "loss": 0.4682, + "step": 7378 + }, + { + "epoch": 0.62, + "learning_rate": 6.744845148355023e-06, + "loss": 0.4711, + "step": 7379 + }, + { + "epoch": 0.62, + "learning_rate": 6.742282953425928e-06, + "loss": 0.4649, + "step": 7380 + }, + { + "epoch": 0.62, + "learning_rate": 6.739720997730024e-06, + "loss": 0.4666, + "step": 7381 + }, + { + "epoch": 0.62, + "learning_rate": 6.73715928145545e-06, + "loss": 0.4793, + "step": 7382 + }, + { + "epoch": 0.62, + "learning_rate": 6.734597804790328e-06, + "loss": 0.4825, + "step": 7383 + }, + { + "epoch": 0.62, + "learning_rate": 6.732036567922761e-06, + "loss": 0.4683, + "step": 7384 + }, + { + "epoch": 0.62, + "learning_rate": 6.729475571040835e-06, + "loss": 0.4744, + "step": 7385 + }, + { + "epoch": 0.62, + "learning_rate": 6.726914814332621e-06, + "loss": 0.4606, + "step": 7386 + }, + { + "epoch": 0.62, + "learning_rate": 6.724354297986164e-06, + "loss": 0.4713, + "step": 7387 + }, + { + "epoch": 0.62, + "learning_rate": 6.7217940221895095e-06, + "loss": 0.5145, + "step": 7388 + }, + { + "epoch": 0.62, + "learning_rate": 6.7192339871306655e-06, + "loss": 0.4723, + "step": 7389 + }, + { + "epoch": 0.62, + "learning_rate": 6.7166741929976295e-06, + "loss": 0.4768, + "step": 7390 + }, + { + "epoch": 0.62, + "learning_rate": 6.7141146399783875e-06, + "loss": 0.4662, + "step": 7391 + }, + { + "epoch": 0.62, + "learning_rate": 6.711555328260899e-06, + "loss": 0.4682, + "step": 7392 + }, + { + "epoch": 0.62, + "learning_rate": 6.708996258033109e-06, + "loss": 0.4747, + "step": 7393 + }, + { + "epoch": 0.62, + "learning_rate": 6.706437429482942e-06, + "loss": 0.4901, + "step": 7394 + }, + { + "epoch": 0.62, + "learning_rate": 6.703878842798315e-06, + "loss": 0.4792, + "step": 7395 + }, + { + "epoch": 0.62, + "learning_rate": 6.701320498167115e-06, + "loss": 0.4451, + "step": 7396 + }, + { + "epoch": 0.62, + "learning_rate": 6.6987623957772165e-06, + "loss": 0.4769, + "step": 7397 + }, + { + "epoch": 0.62, + "learning_rate": 6.696204535816479e-06, + "loss": 0.4691, + "step": 7398 + }, + { + "epoch": 0.62, + "learning_rate": 6.693646918472739e-06, + "loss": 0.4577, + "step": 7399 + }, + { + "epoch": 0.62, + "learning_rate": 6.691089543933815e-06, + "loss": 0.4784, + "step": 7400 + }, + { + "epoch": 0.62, + "learning_rate": 6.68853241238751e-06, + "loss": 0.4884, + "step": 7401 + }, + { + "epoch": 0.62, + "learning_rate": 6.685975524021615e-06, + "loss": 0.4705, + "step": 7402 + }, + { + "epoch": 0.62, + "learning_rate": 6.683418879023893e-06, + "loss": 0.4748, + "step": 7403 + }, + { + "epoch": 0.62, + "learning_rate": 6.6808624775820954e-06, + "loss": 0.49, + "step": 7404 + }, + { + "epoch": 0.62, + "learning_rate": 6.678306319883948e-06, + "loss": 0.456, + "step": 7405 + }, + { + "epoch": 0.62, + "learning_rate": 6.675750406117172e-06, + "loss": 0.447, + "step": 7406 + }, + { + "epoch": 0.62, + "learning_rate": 6.673194736469455e-06, + "loss": 0.4794, + "step": 7407 + }, + { + "epoch": 0.62, + "learning_rate": 6.670639311128484e-06, + "loss": 0.4712, + "step": 7408 + }, + { + "epoch": 0.62, + "learning_rate": 6.668084130281913e-06, + "loss": 0.4512, + "step": 7409 + }, + { + "epoch": 0.62, + "learning_rate": 6.665529194117386e-06, + "loss": 0.4734, + "step": 7410 + }, + { + "epoch": 0.62, + "learning_rate": 6.662974502822524e-06, + "loss": 0.4735, + "step": 7411 + }, + { + "epoch": 0.62, + "learning_rate": 6.660420056584935e-06, + "loss": 0.4767, + "step": 7412 + }, + { + "epoch": 0.62, + "learning_rate": 6.65786585559221e-06, + "loss": 0.4643, + "step": 7413 + }, + { + "epoch": 0.62, + "learning_rate": 6.655311900031909e-06, + "loss": 0.4899, + "step": 7414 + }, + { + "epoch": 0.62, + "learning_rate": 6.652758190091595e-06, + "loss": 0.4542, + "step": 7415 + }, + { + "epoch": 0.62, + "learning_rate": 6.650204725958795e-06, + "loss": 0.4742, + "step": 7416 + }, + { + "epoch": 0.62, + "learning_rate": 6.647651507821029e-06, + "loss": 0.4802, + "step": 7417 + }, + { + "epoch": 0.62, + "learning_rate": 6.645098535865793e-06, + "loss": 0.4728, + "step": 7418 + }, + { + "epoch": 0.62, + "learning_rate": 6.642545810280567e-06, + "loss": 0.4773, + "step": 7419 + }, + { + "epoch": 0.62, + "learning_rate": 6.63999333125281e-06, + "loss": 0.4743, + "step": 7420 + }, + { + "epoch": 0.62, + "learning_rate": 6.637441098969967e-06, + "loss": 0.4709, + "step": 7421 + }, + { + "epoch": 0.62, + "learning_rate": 6.634889113619463e-06, + "loss": 0.4619, + "step": 7422 + }, + { + "epoch": 0.62, + "learning_rate": 6.632337375388709e-06, + "loss": 0.4638, + "step": 7423 + }, + { + "epoch": 0.62, + "learning_rate": 6.629785884465091e-06, + "loss": 0.4739, + "step": 7424 + }, + { + "epoch": 0.62, + "learning_rate": 6.62723464103598e-06, + "loss": 0.4845, + "step": 7425 + }, + { + "epoch": 0.62, + "learning_rate": 6.624683645288726e-06, + "loss": 0.46, + "step": 7426 + }, + { + "epoch": 0.62, + "learning_rate": 6.622132897410668e-06, + "loss": 0.4822, + "step": 7427 + }, + { + "epoch": 0.62, + "learning_rate": 6.619582397589117e-06, + "loss": 0.4872, + "step": 7428 + }, + { + "epoch": 0.62, + "learning_rate": 6.617032146011377e-06, + "loss": 0.4577, + "step": 7429 + }, + { + "epoch": 0.62, + "learning_rate": 6.614482142864728e-06, + "loss": 0.4661, + "step": 7430 + }, + { + "epoch": 0.62, + "learning_rate": 6.611932388336425e-06, + "loss": 0.4734, + "step": 7431 + }, + { + "epoch": 0.62, + "learning_rate": 6.609382882613717e-06, + "loss": 0.5089, + "step": 7432 + }, + { + "epoch": 0.62, + "learning_rate": 6.606833625883829e-06, + "loss": 0.4623, + "step": 7433 + }, + { + "epoch": 0.62, + "learning_rate": 6.604284618333967e-06, + "loss": 0.4694, + "step": 7434 + }, + { + "epoch": 0.62, + "learning_rate": 6.601735860151313e-06, + "loss": 0.4794, + "step": 7435 + }, + { + "epoch": 0.62, + "learning_rate": 6.599187351523046e-06, + "loss": 0.4663, + "step": 7436 + }, + { + "epoch": 0.62, + "learning_rate": 6.596639092636315e-06, + "loss": 0.4743, + "step": 7437 + }, + { + "epoch": 0.62, + "learning_rate": 6.594091083678256e-06, + "loss": 0.4755, + "step": 7438 + }, + { + "epoch": 0.62, + "learning_rate": 6.5915433248359795e-06, + "loss": 0.4826, + "step": 7439 + }, + { + "epoch": 0.62, + "learning_rate": 6.588995816296585e-06, + "loss": 0.4959, + "step": 7440 + }, + { + "epoch": 0.62, + "learning_rate": 6.586448558247147e-06, + "loss": 0.4803, + "step": 7441 + }, + { + "epoch": 0.62, + "learning_rate": 6.58390155087473e-06, + "loss": 0.4815, + "step": 7442 + }, + { + "epoch": 0.62, + "learning_rate": 6.581354794366377e-06, + "loss": 0.4684, + "step": 7443 + }, + { + "epoch": 0.62, + "learning_rate": 6.578808288909109e-06, + "loss": 0.4681, + "step": 7444 + }, + { + "epoch": 0.62, + "learning_rate": 6.576262034689929e-06, + "loss": 0.4779, + "step": 7445 + }, + { + "epoch": 0.62, + "learning_rate": 6.573716031895825e-06, + "loss": 0.4647, + "step": 7446 + }, + { + "epoch": 0.62, + "learning_rate": 6.571170280713765e-06, + "loss": 0.4679, + "step": 7447 + }, + { + "epoch": 0.62, + "learning_rate": 6.568624781330694e-06, + "loss": 0.472, + "step": 7448 + }, + { + "epoch": 0.62, + "learning_rate": 6.566079533933551e-06, + "loss": 0.4853, + "step": 7449 + }, + { + "epoch": 0.62, + "learning_rate": 6.563534538709244e-06, + "loss": 0.4819, + "step": 7450 + }, + { + "epoch": 0.62, + "learning_rate": 6.560989795844668e-06, + "loss": 0.4661, + "step": 7451 + }, + { + "epoch": 0.62, + "learning_rate": 6.558445305526695e-06, + "loss": 0.4871, + "step": 7452 + }, + { + "epoch": 0.62, + "learning_rate": 6.555901067942188e-06, + "loss": 0.4697, + "step": 7453 + }, + { + "epoch": 0.62, + "learning_rate": 6.553357083277979e-06, + "loss": 0.4684, + "step": 7454 + }, + { + "epoch": 0.62, + "learning_rate": 6.550813351720888e-06, + "loss": 0.448, + "step": 7455 + }, + { + "epoch": 0.62, + "learning_rate": 6.54826987345772e-06, + "loss": 0.4641, + "step": 7456 + }, + { + "epoch": 0.62, + "learning_rate": 6.545726648675255e-06, + "loss": 0.4725, + "step": 7457 + }, + { + "epoch": 0.62, + "learning_rate": 6.54318367756026e-06, + "loss": 0.4737, + "step": 7458 + }, + { + "epoch": 0.62, + "learning_rate": 6.540640960299477e-06, + "loss": 0.4911, + "step": 7459 + }, + { + "epoch": 0.62, + "learning_rate": 6.538098497079634e-06, + "loss": 0.4779, + "step": 7460 + }, + { + "epoch": 0.62, + "learning_rate": 6.5355562880874345e-06, + "loss": 0.4593, + "step": 7461 + }, + { + "epoch": 0.62, + "learning_rate": 6.533014333509573e-06, + "loss": 0.4589, + "step": 7462 + }, + { + "epoch": 0.62, + "learning_rate": 6.530472633532718e-06, + "loss": 0.485, + "step": 7463 + }, + { + "epoch": 0.62, + "learning_rate": 6.527931188343525e-06, + "loss": 0.5078, + "step": 7464 + }, + { + "epoch": 0.62, + "learning_rate": 6.525389998128624e-06, + "loss": 0.4716, + "step": 7465 + }, + { + "epoch": 0.62, + "learning_rate": 6.522849063074628e-06, + "loss": 0.4613, + "step": 7466 + }, + { + "epoch": 0.62, + "learning_rate": 6.520308383368134e-06, + "loss": 0.4736, + "step": 7467 + }, + { + "epoch": 0.62, + "learning_rate": 6.51776795919572e-06, + "loss": 0.4775, + "step": 7468 + }, + { + "epoch": 0.62, + "learning_rate": 6.515227790743939e-06, + "loss": 0.4675, + "step": 7469 + }, + { + "epoch": 0.62, + "learning_rate": 6.51268787819934e-06, + "loss": 0.5053, + "step": 7470 + }, + { + "epoch": 0.63, + "learning_rate": 6.510148221748438e-06, + "loss": 0.4562, + "step": 7471 + }, + { + "epoch": 0.63, + "learning_rate": 6.507608821577733e-06, + "loss": 0.4942, + "step": 7472 + }, + { + "epoch": 0.63, + "learning_rate": 6.505069677873712e-06, + "loss": 0.4833, + "step": 7473 + }, + { + "epoch": 0.63, + "learning_rate": 6.502530790822838e-06, + "loss": 0.4595, + "step": 7474 + }, + { + "epoch": 0.63, + "learning_rate": 6.499992160611556e-06, + "loss": 0.4807, + "step": 7475 + }, + { + "epoch": 0.63, + "learning_rate": 6.4974537874262865e-06, + "loss": 0.4696, + "step": 7476 + }, + { + "epoch": 0.63, + "learning_rate": 6.494915671453448e-06, + "loss": 0.4573, + "step": 7477 + }, + { + "epoch": 0.63, + "learning_rate": 6.492377812879422e-06, + "loss": 0.4639, + "step": 7478 + }, + { + "epoch": 0.63, + "learning_rate": 6.489840211890581e-06, + "loss": 0.4548, + "step": 7479 + }, + { + "epoch": 0.63, + "learning_rate": 6.4873028686732755e-06, + "loss": 0.4844, + "step": 7480 + }, + { + "epoch": 0.63, + "learning_rate": 6.484765783413838e-06, + "loss": 0.4707, + "step": 7481 + }, + { + "epoch": 0.63, + "learning_rate": 6.482228956298575e-06, + "loss": 0.4791, + "step": 7482 + }, + { + "epoch": 0.63, + "learning_rate": 6.479692387513788e-06, + "loss": 0.4717, + "step": 7483 + }, + { + "epoch": 0.63, + "learning_rate": 6.477156077245752e-06, + "loss": 0.4769, + "step": 7484 + }, + { + "epoch": 0.63, + "learning_rate": 6.474620025680722e-06, + "loss": 0.487, + "step": 7485 + }, + { + "epoch": 0.63, + "learning_rate": 6.472084233004934e-06, + "loss": 0.4828, + "step": 7486 + }, + { + "epoch": 0.63, + "learning_rate": 6.469548699404603e-06, + "loss": 0.4782, + "step": 7487 + }, + { + "epoch": 0.63, + "learning_rate": 6.467013425065935e-06, + "loss": 0.4786, + "step": 7488 + }, + { + "epoch": 0.63, + "learning_rate": 6.464478410175101e-06, + "loss": 0.4812, + "step": 7489 + }, + { + "epoch": 0.63, + "learning_rate": 6.461943654918271e-06, + "loss": 0.4729, + "step": 7490 + }, + { + "epoch": 0.63, + "learning_rate": 6.459409159481584e-06, + "loss": 0.4727, + "step": 7491 + }, + { + "epoch": 0.63, + "learning_rate": 6.456874924051162e-06, + "loss": 0.4939, + "step": 7492 + }, + { + "epoch": 0.63, + "learning_rate": 6.454340948813105e-06, + "loss": 0.4628, + "step": 7493 + }, + { + "epoch": 0.63, + "learning_rate": 6.451807233953504e-06, + "loss": 0.4971, + "step": 7494 + }, + { + "epoch": 0.63, + "learning_rate": 6.4492737796584225e-06, + "loss": 0.4719, + "step": 7495 + }, + { + "epoch": 0.63, + "learning_rate": 6.446740586113902e-06, + "loss": 0.4494, + "step": 7496 + }, + { + "epoch": 0.63, + "learning_rate": 6.4442076535059774e-06, + "loss": 0.4809, + "step": 7497 + }, + { + "epoch": 0.63, + "learning_rate": 6.441674982020654e-06, + "loss": 0.4808, + "step": 7498 + }, + { + "epoch": 0.63, + "learning_rate": 6.439142571843915e-06, + "loss": 0.4673, + "step": 7499 + }, + { + "epoch": 0.63, + "learning_rate": 6.43661042316174e-06, + "loss": 0.4685, + "step": 7500 + }, + { + "epoch": 0.63, + "learning_rate": 6.434078536160072e-06, + "loss": 0.4587, + "step": 7501 + }, + { + "epoch": 0.63, + "learning_rate": 6.431546911024844e-06, + "loss": 0.4609, + "step": 7502 + }, + { + "epoch": 0.63, + "learning_rate": 6.429015547941968e-06, + "loss": 0.4694, + "step": 7503 + }, + { + "epoch": 0.63, + "learning_rate": 6.426484447097336e-06, + "loss": 0.4861, + "step": 7504 + }, + { + "epoch": 0.63, + "learning_rate": 6.423953608676827e-06, + "loss": 0.4696, + "step": 7505 + }, + { + "epoch": 0.63, + "learning_rate": 6.42142303286629e-06, + "loss": 0.483, + "step": 7506 + }, + { + "epoch": 0.63, + "learning_rate": 6.418892719851561e-06, + "loss": 0.4773, + "step": 7507 + }, + { + "epoch": 0.63, + "learning_rate": 6.416362669818454e-06, + "loss": 0.4661, + "step": 7508 + }, + { + "epoch": 0.63, + "learning_rate": 6.413832882952769e-06, + "loss": 0.4772, + "step": 7509 + }, + { + "epoch": 0.63, + "learning_rate": 6.411303359440277e-06, + "loss": 0.4728, + "step": 7510 + }, + { + "epoch": 0.63, + "learning_rate": 6.408774099466744e-06, + "loss": 0.4697, + "step": 7511 + }, + { + "epoch": 0.63, + "learning_rate": 6.406245103217903e-06, + "loss": 0.4669, + "step": 7512 + }, + { + "epoch": 0.63, + "learning_rate": 6.403716370879476e-06, + "loss": 0.4848, + "step": 7513 + }, + { + "epoch": 0.63, + "learning_rate": 6.401187902637157e-06, + "loss": 0.4847, + "step": 7514 + }, + { + "epoch": 0.63, + "learning_rate": 6.398659698676632e-06, + "loss": 0.4871, + "step": 7515 + }, + { + "epoch": 0.63, + "learning_rate": 6.396131759183557e-06, + "loss": 0.4799, + "step": 7516 + }, + { + "epoch": 0.63, + "learning_rate": 6.393604084343579e-06, + "loss": 0.4634, + "step": 7517 + }, + { + "epoch": 0.63, + "learning_rate": 6.391076674342316e-06, + "loss": 0.4661, + "step": 7518 + }, + { + "epoch": 0.63, + "learning_rate": 6.388549529365371e-06, + "loss": 0.4611, + "step": 7519 + }, + { + "epoch": 0.63, + "learning_rate": 6.3860226495983295e-06, + "loss": 0.4653, + "step": 7520 + }, + { + "epoch": 0.63, + "learning_rate": 6.383496035226752e-06, + "loss": 0.4802, + "step": 7521 + }, + { + "epoch": 0.63, + "learning_rate": 6.380969686436183e-06, + "loss": 0.4697, + "step": 7522 + }, + { + "epoch": 0.63, + "learning_rate": 6.378443603412145e-06, + "loss": 0.47, + "step": 7523 + }, + { + "epoch": 0.63, + "learning_rate": 6.375917786340149e-06, + "loss": 0.4656, + "step": 7524 + }, + { + "epoch": 0.63, + "learning_rate": 6.373392235405674e-06, + "loss": 0.4674, + "step": 7525 + }, + { + "epoch": 0.63, + "learning_rate": 6.3708669507941925e-06, + "loss": 0.454, + "step": 7526 + }, + { + "epoch": 0.63, + "learning_rate": 6.368341932691146e-06, + "loss": 0.4648, + "step": 7527 + }, + { + "epoch": 0.63, + "learning_rate": 6.365817181281965e-06, + "loss": 0.4764, + "step": 7528 + }, + { + "epoch": 0.63, + "learning_rate": 6.36329269675205e-06, + "loss": 0.4925, + "step": 7529 + }, + { + "epoch": 0.63, + "learning_rate": 6.360768479286793e-06, + "loss": 0.4803, + "step": 7530 + }, + { + "epoch": 0.63, + "learning_rate": 6.358244529071565e-06, + "loss": 0.4688, + "step": 7531 + }, + { + "epoch": 0.63, + "learning_rate": 6.355720846291713e-06, + "loss": 0.4638, + "step": 7532 + }, + { + "epoch": 0.63, + "learning_rate": 6.3531974311325625e-06, + "loss": 0.4732, + "step": 7533 + }, + { + "epoch": 0.63, + "learning_rate": 6.350674283779424e-06, + "loss": 0.4725, + "step": 7534 + }, + { + "epoch": 0.63, + "learning_rate": 6.348151404417589e-06, + "loss": 0.46, + "step": 7535 + }, + { + "epoch": 0.63, + "learning_rate": 6.3456287932323255e-06, + "loss": 0.4699, + "step": 7536 + }, + { + "epoch": 0.63, + "learning_rate": 6.34310645040888e-06, + "loss": 0.464, + "step": 7537 + }, + { + "epoch": 0.63, + "learning_rate": 6.34058437613249e-06, + "loss": 0.4604, + "step": 7538 + }, + { + "epoch": 0.63, + "learning_rate": 6.338062570588363e-06, + "loss": 0.4868, + "step": 7539 + }, + { + "epoch": 0.63, + "learning_rate": 6.335541033961687e-06, + "loss": 0.4638, + "step": 7540 + }, + { + "epoch": 0.63, + "learning_rate": 6.33301976643764e-06, + "loss": 0.4742, + "step": 7541 + }, + { + "epoch": 0.63, + "learning_rate": 6.330498768201367e-06, + "loss": 0.4737, + "step": 7542 + }, + { + "epoch": 0.63, + "learning_rate": 6.327978039438003e-06, + "loss": 0.476, + "step": 7543 + }, + { + "epoch": 0.63, + "learning_rate": 6.325457580332655e-06, + "loss": 0.4563, + "step": 7544 + }, + { + "epoch": 0.63, + "learning_rate": 6.3229373910704205e-06, + "loss": 0.4869, + "step": 7545 + }, + { + "epoch": 0.63, + "learning_rate": 6.3204174718363705e-06, + "loss": 0.4795, + "step": 7546 + }, + { + "epoch": 0.63, + "learning_rate": 6.317897822815559e-06, + "loss": 0.4641, + "step": 7547 + }, + { + "epoch": 0.63, + "learning_rate": 6.315378444193014e-06, + "loss": 0.4707, + "step": 7548 + }, + { + "epoch": 0.63, + "learning_rate": 6.31285933615375e-06, + "loss": 0.4488, + "step": 7549 + }, + { + "epoch": 0.63, + "learning_rate": 6.310340498882763e-06, + "loss": 0.4658, + "step": 7550 + }, + { + "epoch": 0.63, + "learning_rate": 6.30782193256502e-06, + "loss": 0.4589, + "step": 7551 + }, + { + "epoch": 0.63, + "learning_rate": 6.305303637385478e-06, + "loss": 0.4657, + "step": 7552 + }, + { + "epoch": 0.63, + "learning_rate": 6.302785613529072e-06, + "loss": 0.4786, + "step": 7553 + }, + { + "epoch": 0.63, + "learning_rate": 6.300267861180713e-06, + "loss": 0.4664, + "step": 7554 + }, + { + "epoch": 0.63, + "learning_rate": 6.297750380525289e-06, + "loss": 0.4712, + "step": 7555 + }, + { + "epoch": 0.63, + "learning_rate": 6.295233171747683e-06, + "loss": 0.4753, + "step": 7556 + }, + { + "epoch": 0.63, + "learning_rate": 6.292716235032738e-06, + "loss": 0.4655, + "step": 7557 + }, + { + "epoch": 0.63, + "learning_rate": 6.290199570565298e-06, + "loss": 0.4664, + "step": 7558 + }, + { + "epoch": 0.63, + "learning_rate": 6.287683178530172e-06, + "loss": 0.4774, + "step": 7559 + }, + { + "epoch": 0.63, + "learning_rate": 6.285167059112149e-06, + "loss": 0.482, + "step": 7560 + }, + { + "epoch": 0.63, + "learning_rate": 6.282651212496009e-06, + "loss": 0.4864, + "step": 7561 + }, + { + "epoch": 0.63, + "learning_rate": 6.280135638866502e-06, + "loss": 0.4768, + "step": 7562 + }, + { + "epoch": 0.63, + "learning_rate": 6.277620338408362e-06, + "loss": 0.4789, + "step": 7563 + }, + { + "epoch": 0.63, + "learning_rate": 6.275105311306298e-06, + "loss": 0.4865, + "step": 7564 + }, + { + "epoch": 0.63, + "learning_rate": 6.272590557745011e-06, + "loss": 0.4426, + "step": 7565 + }, + { + "epoch": 0.63, + "learning_rate": 6.270076077909166e-06, + "loss": 0.4658, + "step": 7566 + }, + { + "epoch": 0.63, + "learning_rate": 6.267561871983424e-06, + "loss": 0.4645, + "step": 7567 + }, + { + "epoch": 0.63, + "learning_rate": 6.265047940152413e-06, + "loss": 0.4599, + "step": 7568 + }, + { + "epoch": 0.63, + "learning_rate": 6.262534282600747e-06, + "loss": 0.4751, + "step": 7569 + }, + { + "epoch": 0.63, + "learning_rate": 6.2600208995130156e-06, + "loss": 0.4681, + "step": 7570 + }, + { + "epoch": 0.63, + "learning_rate": 6.257507791073792e-06, + "loss": 0.4576, + "step": 7571 + }, + { + "epoch": 0.63, + "learning_rate": 6.254994957467633e-06, + "loss": 0.4755, + "step": 7572 + }, + { + "epoch": 0.63, + "learning_rate": 6.252482398879068e-06, + "loss": 0.4781, + "step": 7573 + }, + { + "epoch": 0.63, + "learning_rate": 6.249970115492609e-06, + "loss": 0.4545, + "step": 7574 + }, + { + "epoch": 0.63, + "learning_rate": 6.247458107492745e-06, + "loss": 0.4745, + "step": 7575 + }, + { + "epoch": 0.63, + "learning_rate": 6.244946375063951e-06, + "loss": 0.4892, + "step": 7576 + }, + { + "epoch": 0.63, + "learning_rate": 6.242434918390678e-06, + "loss": 0.4818, + "step": 7577 + }, + { + "epoch": 0.63, + "learning_rate": 6.239923737657351e-06, + "loss": 0.4687, + "step": 7578 + }, + { + "epoch": 0.63, + "learning_rate": 6.237412833048389e-06, + "loss": 0.4732, + "step": 7579 + }, + { + "epoch": 0.63, + "learning_rate": 6.2349022047481784e-06, + "loss": 0.4699, + "step": 7580 + }, + { + "epoch": 0.63, + "learning_rate": 6.2323918529410895e-06, + "loss": 0.4839, + "step": 7581 + }, + { + "epoch": 0.63, + "learning_rate": 6.2298817778114725e-06, + "loss": 0.4702, + "step": 7582 + }, + { + "epoch": 0.63, + "learning_rate": 6.227371979543658e-06, + "loss": 0.4687, + "step": 7583 + }, + { + "epoch": 0.63, + "learning_rate": 6.224862458321954e-06, + "loss": 0.5033, + "step": 7584 + }, + { + "epoch": 0.63, + "learning_rate": 6.222353214330643e-06, + "loss": 0.4622, + "step": 7585 + }, + { + "epoch": 0.63, + "learning_rate": 6.2198442477540036e-06, + "loss": 0.4653, + "step": 7586 + }, + { + "epoch": 0.63, + "learning_rate": 6.2173355587762805e-06, + "loss": 0.4618, + "step": 7587 + }, + { + "epoch": 0.63, + "learning_rate": 6.214827147581701e-06, + "loss": 0.4721, + "step": 7588 + }, + { + "epoch": 0.63, + "learning_rate": 6.212319014354472e-06, + "loss": 0.4822, + "step": 7589 + }, + { + "epoch": 0.64, + "learning_rate": 6.209811159278778e-06, + "loss": 0.4573, + "step": 7590 + }, + { + "epoch": 0.64, + "learning_rate": 6.207303582538789e-06, + "loss": 0.4765, + "step": 7591 + }, + { + "epoch": 0.64, + "learning_rate": 6.2047962843186495e-06, + "loss": 0.4657, + "step": 7592 + }, + { + "epoch": 0.64, + "learning_rate": 6.202289264802488e-06, + "loss": 0.4607, + "step": 7593 + }, + { + "epoch": 0.64, + "learning_rate": 6.199782524174406e-06, + "loss": 0.4389, + "step": 7594 + }, + { + "epoch": 0.64, + "learning_rate": 6.197276062618489e-06, + "loss": 0.4819, + "step": 7595 + }, + { + "epoch": 0.64, + "learning_rate": 6.194769880318801e-06, + "loss": 0.4754, + "step": 7596 + }, + { + "epoch": 0.64, + "learning_rate": 6.192263977459385e-06, + "loss": 0.4634, + "step": 7597 + }, + { + "epoch": 0.64, + "learning_rate": 6.189758354224262e-06, + "loss": 0.4707, + "step": 7598 + }, + { + "epoch": 0.64, + "learning_rate": 6.187253010797443e-06, + "loss": 0.4694, + "step": 7599 + }, + { + "epoch": 0.64, + "learning_rate": 6.1847479473629035e-06, + "loss": 0.4673, + "step": 7600 + }, + { + "epoch": 0.64, + "learning_rate": 6.1822431641046045e-06, + "loss": 0.4739, + "step": 7601 + }, + { + "epoch": 0.64, + "learning_rate": 6.1797386612064895e-06, + "loss": 0.4772, + "step": 7602 + }, + { + "epoch": 0.64, + "learning_rate": 6.177234438852477e-06, + "loss": 0.4582, + "step": 7603 + }, + { + "epoch": 0.64, + "learning_rate": 6.174730497226467e-06, + "loss": 0.4811, + "step": 7604 + }, + { + "epoch": 0.64, + "learning_rate": 6.172226836512336e-06, + "loss": 0.4807, + "step": 7605 + }, + { + "epoch": 0.64, + "learning_rate": 6.16972345689395e-06, + "loss": 0.4766, + "step": 7606 + }, + { + "epoch": 0.64, + "learning_rate": 6.167220358555138e-06, + "loss": 0.4655, + "step": 7607 + }, + { + "epoch": 0.64, + "learning_rate": 6.164717541679724e-06, + "loss": 0.4603, + "step": 7608 + }, + { + "epoch": 0.64, + "learning_rate": 6.162215006451502e-06, + "loss": 0.4671, + "step": 7609 + }, + { + "epoch": 0.64, + "learning_rate": 6.159712753054248e-06, + "loss": 0.4648, + "step": 7610 + }, + { + "epoch": 0.64, + "learning_rate": 6.157210781671713e-06, + "loss": 0.4749, + "step": 7611 + }, + { + "epoch": 0.64, + "learning_rate": 6.154709092487633e-06, + "loss": 0.4573, + "step": 7612 + }, + { + "epoch": 0.64, + "learning_rate": 6.152207685685727e-06, + "loss": 0.4714, + "step": 7613 + }, + { + "epoch": 0.64, + "learning_rate": 6.1497065614496866e-06, + "loss": 0.4892, + "step": 7614 + }, + { + "epoch": 0.64, + "learning_rate": 6.147205719963181e-06, + "loss": 0.4641, + "step": 7615 + }, + { + "epoch": 0.64, + "learning_rate": 6.144705161409858e-06, + "loss": 0.4658, + "step": 7616 + }, + { + "epoch": 0.64, + "learning_rate": 6.142204885973358e-06, + "loss": 0.4738, + "step": 7617 + }, + { + "epoch": 0.64, + "learning_rate": 6.1397048938372825e-06, + "loss": 0.4532, + "step": 7618 + }, + { + "epoch": 0.64, + "learning_rate": 6.13720518518522e-06, + "loss": 0.481, + "step": 7619 + }, + { + "epoch": 0.64, + "learning_rate": 6.134705760200747e-06, + "loss": 0.4683, + "step": 7620 + }, + { + "epoch": 0.64, + "learning_rate": 6.132206619067407e-06, + "loss": 0.4594, + "step": 7621 + }, + { + "epoch": 0.64, + "learning_rate": 6.1297077619687216e-06, + "loss": 0.4808, + "step": 7622 + }, + { + "epoch": 0.64, + "learning_rate": 6.127209189088204e-06, + "loss": 0.4638, + "step": 7623 + }, + { + "epoch": 0.64, + "learning_rate": 6.1247109006093345e-06, + "loss": 0.4768, + "step": 7624 + }, + { + "epoch": 0.64, + "learning_rate": 6.122212896715577e-06, + "loss": 0.4717, + "step": 7625 + }, + { + "epoch": 0.64, + "learning_rate": 6.119715177590373e-06, + "loss": 0.4688, + "step": 7626 + }, + { + "epoch": 0.64, + "learning_rate": 6.1172177434171495e-06, + "loss": 0.4736, + "step": 7627 + }, + { + "epoch": 0.64, + "learning_rate": 6.114720594379304e-06, + "loss": 0.5022, + "step": 7628 + }, + { + "epoch": 0.64, + "learning_rate": 6.112223730660221e-06, + "loss": 0.4698, + "step": 7629 + }, + { + "epoch": 0.64, + "learning_rate": 6.109727152443254e-06, + "loss": 0.4825, + "step": 7630 + }, + { + "epoch": 0.64, + "learning_rate": 6.1072308599117445e-06, + "loss": 0.4657, + "step": 7631 + }, + { + "epoch": 0.64, + "learning_rate": 6.104734853249009e-06, + "loss": 0.4716, + "step": 7632 + }, + { + "epoch": 0.64, + "learning_rate": 6.102239132638343e-06, + "loss": 0.4828, + "step": 7633 + }, + { + "epoch": 0.64, + "learning_rate": 6.099743698263028e-06, + "loss": 0.4588, + "step": 7634 + }, + { + "epoch": 0.64, + "learning_rate": 6.097248550306311e-06, + "loss": 0.4679, + "step": 7635 + }, + { + "epoch": 0.64, + "learning_rate": 6.094753688951428e-06, + "loss": 0.4711, + "step": 7636 + }, + { + "epoch": 0.64, + "learning_rate": 6.092259114381589e-06, + "loss": 0.4754, + "step": 7637 + }, + { + "epoch": 0.64, + "learning_rate": 6.089764826779989e-06, + "loss": 0.4503, + "step": 7638 + }, + { + "epoch": 0.64, + "learning_rate": 6.087270826329793e-06, + "loss": 0.4527, + "step": 7639 + }, + { + "epoch": 0.64, + "learning_rate": 6.084777113214156e-06, + "loss": 0.4627, + "step": 7640 + }, + { + "epoch": 0.64, + "learning_rate": 6.082283687616204e-06, + "loss": 0.4812, + "step": 7641 + }, + { + "epoch": 0.64, + "learning_rate": 6.079790549719044e-06, + "loss": 0.4899, + "step": 7642 + }, + { + "epoch": 0.64, + "learning_rate": 6.077297699705758e-06, + "loss": 0.4577, + "step": 7643 + }, + { + "epoch": 0.64, + "learning_rate": 6.074805137759414e-06, + "loss": 0.4823, + "step": 7644 + }, + { + "epoch": 0.64, + "learning_rate": 6.072312864063054e-06, + "loss": 0.4605, + "step": 7645 + }, + { + "epoch": 0.64, + "learning_rate": 6.0698208787996995e-06, + "loss": 0.4674, + "step": 7646 + }, + { + "epoch": 0.64, + "learning_rate": 6.067329182152355e-06, + "loss": 0.4326, + "step": 7647 + }, + { + "epoch": 0.64, + "learning_rate": 6.064837774303997e-06, + "loss": 0.4767, + "step": 7648 + }, + { + "epoch": 0.64, + "learning_rate": 6.0623466554375864e-06, + "loss": 0.4843, + "step": 7649 + }, + { + "epoch": 0.64, + "learning_rate": 6.059855825736061e-06, + "loss": 0.4827, + "step": 7650 + }, + { + "epoch": 0.64, + "learning_rate": 6.057365285382333e-06, + "loss": 0.4549, + "step": 7651 + }, + { + "epoch": 0.64, + "learning_rate": 6.0548750345593e-06, + "loss": 0.4818, + "step": 7652 + }, + { + "epoch": 0.64, + "learning_rate": 6.052385073449833e-06, + "loss": 0.4602, + "step": 7653 + }, + { + "epoch": 0.64, + "learning_rate": 6.049895402236789e-06, + "loss": 0.4846, + "step": 7654 + }, + { + "epoch": 0.64, + "learning_rate": 6.047406021103e-06, + "loss": 0.4772, + "step": 7655 + }, + { + "epoch": 0.64, + "learning_rate": 6.04491693023127e-06, + "loss": 0.4602, + "step": 7656 + }, + { + "epoch": 0.64, + "learning_rate": 6.042428129804392e-06, + "loss": 0.4973, + "step": 7657 + }, + { + "epoch": 0.64, + "learning_rate": 6.0399396200051285e-06, + "loss": 0.4907, + "step": 7658 + }, + { + "epoch": 0.64, + "learning_rate": 6.0374514010162296e-06, + "loss": 0.4616, + "step": 7659 + }, + { + "epoch": 0.64, + "learning_rate": 6.034963473020417e-06, + "loss": 0.4955, + "step": 7660 + }, + { + "epoch": 0.64, + "learning_rate": 6.0324758362003956e-06, + "loss": 0.4642, + "step": 7661 + }, + { + "epoch": 0.64, + "learning_rate": 6.029988490738849e-06, + "loss": 0.4725, + "step": 7662 + }, + { + "epoch": 0.64, + "learning_rate": 6.027501436818433e-06, + "loss": 0.4769, + "step": 7663 + }, + { + "epoch": 0.64, + "learning_rate": 6.0250146746217895e-06, + "loss": 0.4685, + "step": 7664 + }, + { + "epoch": 0.64, + "learning_rate": 6.022528204331534e-06, + "loss": 0.4556, + "step": 7665 + }, + { + "epoch": 0.64, + "learning_rate": 6.020042026130262e-06, + "loss": 0.4587, + "step": 7666 + }, + { + "epoch": 0.64, + "learning_rate": 6.017556140200553e-06, + "loss": 0.4977, + "step": 7667 + }, + { + "epoch": 0.64, + "learning_rate": 6.015070546724957e-06, + "loss": 0.4682, + "step": 7668 + }, + { + "epoch": 0.64, + "learning_rate": 6.012585245886004e-06, + "loss": 0.4524, + "step": 7669 + }, + { + "epoch": 0.64, + "learning_rate": 6.0101002378662066e-06, + "loss": 0.4828, + "step": 7670 + }, + { + "epoch": 0.64, + "learning_rate": 6.007615522848053e-06, + "loss": 0.4578, + "step": 7671 + }, + { + "epoch": 0.64, + "learning_rate": 6.00513110101401e-06, + "loss": 0.4576, + "step": 7672 + }, + { + "epoch": 0.64, + "learning_rate": 6.002646972546517e-06, + "loss": 0.4703, + "step": 7673 + }, + { + "epoch": 0.64, + "learning_rate": 6.000163137628009e-06, + "loss": 0.4826, + "step": 7674 + }, + { + "epoch": 0.64, + "learning_rate": 5.997679596440884e-06, + "loss": 0.4883, + "step": 7675 + }, + { + "epoch": 0.64, + "learning_rate": 5.995196349167523e-06, + "loss": 0.4739, + "step": 7676 + }, + { + "epoch": 0.64, + "learning_rate": 5.992713395990285e-06, + "loss": 0.485, + "step": 7677 + }, + { + "epoch": 0.64, + "learning_rate": 5.990230737091505e-06, + "loss": 0.4745, + "step": 7678 + }, + { + "epoch": 0.64, + "learning_rate": 5.987748372653504e-06, + "loss": 0.4834, + "step": 7679 + }, + { + "epoch": 0.64, + "learning_rate": 5.9852663028585704e-06, + "loss": 0.466, + "step": 7680 + }, + { + "epoch": 0.64, + "learning_rate": 5.982784527888985e-06, + "loss": 0.4647, + "step": 7681 + }, + { + "epoch": 0.64, + "learning_rate": 5.980303047926996e-06, + "loss": 0.476, + "step": 7682 + }, + { + "epoch": 0.64, + "learning_rate": 5.977821863154832e-06, + "loss": 0.4727, + "step": 7683 + }, + { + "epoch": 0.64, + "learning_rate": 5.975340973754697e-06, + "loss": 0.463, + "step": 7684 + }, + { + "epoch": 0.64, + "learning_rate": 5.972860379908784e-06, + "loss": 0.474, + "step": 7685 + }, + { + "epoch": 0.64, + "learning_rate": 5.970380081799254e-06, + "loss": 0.4732, + "step": 7686 + }, + { + "epoch": 0.64, + "learning_rate": 5.967900079608247e-06, + "loss": 0.4832, + "step": 7687 + }, + { + "epoch": 0.64, + "learning_rate": 5.965420373517892e-06, + "loss": 0.4749, + "step": 7688 + }, + { + "epoch": 0.64, + "learning_rate": 5.96294096371028e-06, + "loss": 0.4943, + "step": 7689 + }, + { + "epoch": 0.64, + "learning_rate": 5.960461850367496e-06, + "loss": 0.4747, + "step": 7690 + }, + { + "epoch": 0.64, + "learning_rate": 5.9579830336715905e-06, + "loss": 0.4638, + "step": 7691 + }, + { + "epoch": 0.64, + "learning_rate": 5.9555045138046e-06, + "loss": 0.4821, + "step": 7692 + }, + { + "epoch": 0.64, + "learning_rate": 5.953026290948534e-06, + "loss": 0.4843, + "step": 7693 + }, + { + "epoch": 0.64, + "learning_rate": 5.950548365285383e-06, + "loss": 0.4715, + "step": 7694 + }, + { + "epoch": 0.64, + "learning_rate": 5.948070736997118e-06, + "loss": 0.4683, + "step": 7695 + }, + { + "epoch": 0.64, + "learning_rate": 5.9455934062656874e-06, + "loss": 0.4626, + "step": 7696 + }, + { + "epoch": 0.64, + "learning_rate": 5.943116373273012e-06, + "loss": 0.4571, + "step": 7697 + }, + { + "epoch": 0.64, + "learning_rate": 5.940639638200998e-06, + "loss": 0.48, + "step": 7698 + }, + { + "epoch": 0.64, + "learning_rate": 5.938163201231523e-06, + "loss": 0.4771, + "step": 7699 + }, + { + "epoch": 0.64, + "learning_rate": 5.935687062546449e-06, + "loss": 0.4547, + "step": 7700 + }, + { + "epoch": 0.64, + "learning_rate": 5.933211222327608e-06, + "loss": 0.4689, + "step": 7701 + }, + { + "epoch": 0.64, + "learning_rate": 5.930735680756825e-06, + "loss": 0.4698, + "step": 7702 + }, + { + "epoch": 0.64, + "learning_rate": 5.928260438015887e-06, + "loss": 0.4458, + "step": 7703 + }, + { + "epoch": 0.64, + "learning_rate": 5.925785494286566e-06, + "loss": 0.4599, + "step": 7704 + }, + { + "epoch": 0.64, + "learning_rate": 5.923310849750614e-06, + "loss": 0.4897, + "step": 7705 + }, + { + "epoch": 0.64, + "learning_rate": 5.920836504589756e-06, + "loss": 0.4731, + "step": 7706 + }, + { + "epoch": 0.64, + "learning_rate": 5.9183624589856956e-06, + "loss": 0.4675, + "step": 7707 + }, + { + "epoch": 0.64, + "learning_rate": 5.915888713120124e-06, + "loss": 0.4822, + "step": 7708 + }, + { + "epoch": 0.64, + "learning_rate": 5.913415267174696e-06, + "loss": 0.4777, + "step": 7709 + }, + { + "epoch": 0.65, + "learning_rate": 5.910942121331054e-06, + "loss": 0.4775, + "step": 7710 + }, + { + "epoch": 0.65, + "learning_rate": 5.908469275770815e-06, + "loss": 0.4773, + "step": 7711 + }, + { + "epoch": 0.65, + "learning_rate": 5.905996730675575e-06, + "loss": 0.4766, + "step": 7712 + }, + { + "epoch": 0.65, + "learning_rate": 5.903524486226907e-06, + "loss": 0.4699, + "step": 7713 + }, + { + "epoch": 0.65, + "learning_rate": 5.901052542606358e-06, + "loss": 0.4748, + "step": 7714 + }, + { + "epoch": 0.65, + "learning_rate": 5.898580899995463e-06, + "loss": 0.4859, + "step": 7715 + }, + { + "epoch": 0.65, + "learning_rate": 5.896109558575731e-06, + "loss": 0.4632, + "step": 7716 + }, + { + "epoch": 0.65, + "learning_rate": 5.893638518528643e-06, + "loss": 0.4726, + "step": 7717 + }, + { + "epoch": 0.65, + "learning_rate": 5.891167780035663e-06, + "loss": 0.4775, + "step": 7718 + }, + { + "epoch": 0.65, + "learning_rate": 5.888697343278229e-06, + "loss": 0.4747, + "step": 7719 + }, + { + "epoch": 0.65, + "learning_rate": 5.886227208437763e-06, + "loss": 0.4684, + "step": 7720 + }, + { + "epoch": 0.65, + "learning_rate": 5.8837573756956575e-06, + "loss": 0.4646, + "step": 7721 + }, + { + "epoch": 0.65, + "learning_rate": 5.881287845233292e-06, + "loss": 0.4675, + "step": 7722 + }, + { + "epoch": 0.65, + "learning_rate": 5.878818617232018e-06, + "loss": 0.4882, + "step": 7723 + }, + { + "epoch": 0.65, + "learning_rate": 5.876349691873162e-06, + "loss": 0.4614, + "step": 7724 + }, + { + "epoch": 0.65, + "learning_rate": 5.873881069338032e-06, + "loss": 0.4633, + "step": 7725 + }, + { + "epoch": 0.65, + "learning_rate": 5.871412749807917e-06, + "loss": 0.4684, + "step": 7726 + }, + { + "epoch": 0.65, + "learning_rate": 5.868944733464077e-06, + "loss": 0.4677, + "step": 7727 + }, + { + "epoch": 0.65, + "learning_rate": 5.866477020487748e-06, + "loss": 0.4895, + "step": 7728 + }, + { + "epoch": 0.65, + "learning_rate": 5.86400961106016e-06, + "loss": 0.4697, + "step": 7729 + }, + { + "epoch": 0.65, + "learning_rate": 5.8615425053625005e-06, + "loss": 0.4953, + "step": 7730 + }, + { + "epoch": 0.65, + "learning_rate": 5.859075703575949e-06, + "loss": 0.464, + "step": 7731 + }, + { + "epoch": 0.65, + "learning_rate": 5.856609205881654e-06, + "loss": 0.4749, + "step": 7732 + }, + { + "epoch": 0.65, + "learning_rate": 5.854143012460745e-06, + "loss": 0.4698, + "step": 7733 + }, + { + "epoch": 0.65, + "learning_rate": 5.851677123494326e-06, + "loss": 0.4582, + "step": 7734 + }, + { + "epoch": 0.65, + "learning_rate": 5.849211539163486e-06, + "loss": 0.4782, + "step": 7735 + }, + { + "epoch": 0.65, + "learning_rate": 5.846746259649288e-06, + "loss": 0.4867, + "step": 7736 + }, + { + "epoch": 0.65, + "learning_rate": 5.844281285132769e-06, + "loss": 0.4811, + "step": 7737 + }, + { + "epoch": 0.65, + "learning_rate": 5.841816615794948e-06, + "loss": 0.4702, + "step": 7738 + }, + { + "epoch": 0.65, + "learning_rate": 5.839352251816821e-06, + "loss": 0.4787, + "step": 7739 + }, + { + "epoch": 0.65, + "learning_rate": 5.836888193379359e-06, + "loss": 0.4668, + "step": 7740 + }, + { + "epoch": 0.65, + "learning_rate": 5.834424440663512e-06, + "loss": 0.4868, + "step": 7741 + }, + { + "epoch": 0.65, + "learning_rate": 5.831960993850203e-06, + "loss": 0.4854, + "step": 7742 + }, + { + "epoch": 0.65, + "learning_rate": 5.829497853120345e-06, + "loss": 0.4697, + "step": 7743 + }, + { + "epoch": 0.65, + "learning_rate": 5.827035018654821e-06, + "loss": 0.4569, + "step": 7744 + }, + { + "epoch": 0.65, + "learning_rate": 5.824572490634488e-06, + "loss": 0.464, + "step": 7745 + }, + { + "epoch": 0.65, + "learning_rate": 5.822110269240184e-06, + "loss": 0.5041, + "step": 7746 + }, + { + "epoch": 0.65, + "learning_rate": 5.819648354652725e-06, + "loss": 0.4528, + "step": 7747 + }, + { + "epoch": 0.65, + "learning_rate": 5.8171867470529e-06, + "loss": 0.4847, + "step": 7748 + }, + { + "epoch": 0.65, + "learning_rate": 5.8147254466214865e-06, + "loss": 0.4592, + "step": 7749 + }, + { + "epoch": 0.65, + "learning_rate": 5.812264453539228e-06, + "loss": 0.4716, + "step": 7750 + }, + { + "epoch": 0.65, + "learning_rate": 5.809803767986851e-06, + "loss": 0.473, + "step": 7751 + }, + { + "epoch": 0.65, + "learning_rate": 5.807343390145055e-06, + "loss": 0.4787, + "step": 7752 + }, + { + "epoch": 0.65, + "learning_rate": 5.80488332019452e-06, + "loss": 0.4637, + "step": 7753 + }, + { + "epoch": 0.65, + "learning_rate": 5.802423558315908e-06, + "loss": 0.4845, + "step": 7754 + }, + { + "epoch": 0.65, + "learning_rate": 5.799964104689847e-06, + "loss": 0.4641, + "step": 7755 + }, + { + "epoch": 0.65, + "learning_rate": 5.797504959496957e-06, + "loss": 0.4473, + "step": 7756 + }, + { + "epoch": 0.65, + "learning_rate": 5.795046122917823e-06, + "loss": 0.4654, + "step": 7757 + }, + { + "epoch": 0.65, + "learning_rate": 5.792587595133012e-06, + "loss": 0.4761, + "step": 7758 + }, + { + "epoch": 0.65, + "learning_rate": 5.790129376323068e-06, + "loss": 0.4757, + "step": 7759 + }, + { + "epoch": 0.65, + "learning_rate": 5.787671466668513e-06, + "loss": 0.4667, + "step": 7760 + }, + { + "epoch": 0.65, + "learning_rate": 5.785213866349844e-06, + "loss": 0.5057, + "step": 7761 + }, + { + "epoch": 0.65, + "learning_rate": 5.782756575547535e-06, + "loss": 0.4902, + "step": 7762 + }, + { + "epoch": 0.65, + "learning_rate": 5.780299594442047e-06, + "loss": 0.4814, + "step": 7763 + }, + { + "epoch": 0.65, + "learning_rate": 5.777842923213801e-06, + "loss": 0.4806, + "step": 7764 + }, + { + "epoch": 0.65, + "learning_rate": 5.775386562043212e-06, + "loss": 0.4772, + "step": 7765 + }, + { + "epoch": 0.65, + "learning_rate": 5.7729305111106645e-06, + "loss": 0.4515, + "step": 7766 + }, + { + "epoch": 0.65, + "learning_rate": 5.770474770596518e-06, + "loss": 0.4629, + "step": 7767 + }, + { + "epoch": 0.65, + "learning_rate": 5.768019340681113e-06, + "loss": 0.4687, + "step": 7768 + }, + { + "epoch": 0.65, + "learning_rate": 5.765564221544759e-06, + "loss": 0.458, + "step": 7769 + }, + { + "epoch": 0.65, + "learning_rate": 5.763109413367762e-06, + "loss": 0.4801, + "step": 7770 + }, + { + "epoch": 0.65, + "learning_rate": 5.760654916330388e-06, + "loss": 0.5006, + "step": 7771 + }, + { + "epoch": 0.65, + "learning_rate": 5.758200730612883e-06, + "loss": 0.4343, + "step": 7772 + }, + { + "epoch": 0.65, + "learning_rate": 5.75574685639547e-06, + "loss": 0.4685, + "step": 7773 + }, + { + "epoch": 0.65, + "learning_rate": 5.7532932938583575e-06, + "loss": 0.4836, + "step": 7774 + }, + { + "epoch": 0.65, + "learning_rate": 5.750840043181722e-06, + "loss": 0.4585, + "step": 7775 + }, + { + "epoch": 0.65, + "learning_rate": 5.7483871045457185e-06, + "loss": 0.4923, + "step": 7776 + }, + { + "epoch": 0.65, + "learning_rate": 5.745934478130484e-06, + "loss": 0.4916, + "step": 7777 + }, + { + "epoch": 0.65, + "learning_rate": 5.7434821641161285e-06, + "loss": 0.4803, + "step": 7778 + }, + { + "epoch": 0.65, + "learning_rate": 5.74103016268274e-06, + "loss": 0.4627, + "step": 7779 + }, + { + "epoch": 0.65, + "learning_rate": 5.738578474010379e-06, + "loss": 0.4538, + "step": 7780 + }, + { + "epoch": 0.65, + "learning_rate": 5.736127098279092e-06, + "loss": 0.4798, + "step": 7781 + }, + { + "epoch": 0.65, + "learning_rate": 5.733676035668891e-06, + "loss": 0.4515, + "step": 7782 + }, + { + "epoch": 0.65, + "learning_rate": 5.731225286359781e-06, + "loss": 0.4924, + "step": 7783 + }, + { + "epoch": 0.65, + "learning_rate": 5.728774850531733e-06, + "loss": 0.468, + "step": 7784 + }, + { + "epoch": 0.65, + "learning_rate": 5.726324728364688e-06, + "loss": 0.4704, + "step": 7785 + }, + { + "epoch": 0.65, + "learning_rate": 5.723874920038586e-06, + "loss": 0.4524, + "step": 7786 + }, + { + "epoch": 0.65, + "learning_rate": 5.721425425733322e-06, + "loss": 0.4711, + "step": 7787 + }, + { + "epoch": 0.65, + "learning_rate": 5.718976245628779e-06, + "loss": 0.4704, + "step": 7788 + }, + { + "epoch": 0.65, + "learning_rate": 5.7165273799048105e-06, + "loss": 0.475, + "step": 7789 + }, + { + "epoch": 0.65, + "learning_rate": 5.71407882874126e-06, + "loss": 0.4684, + "step": 7790 + }, + { + "epoch": 0.65, + "learning_rate": 5.711630592317933e-06, + "loss": 0.4576, + "step": 7791 + }, + { + "epoch": 0.65, + "learning_rate": 5.709182670814619e-06, + "loss": 0.4713, + "step": 7792 + }, + { + "epoch": 0.65, + "learning_rate": 5.706735064411082e-06, + "loss": 0.4866, + "step": 7793 + }, + { + "epoch": 0.65, + "learning_rate": 5.704287773287061e-06, + "loss": 0.4498, + "step": 7794 + }, + { + "epoch": 0.65, + "learning_rate": 5.701840797622284e-06, + "loss": 0.4883, + "step": 7795 + }, + { + "epoch": 0.65, + "learning_rate": 5.699394137596437e-06, + "loss": 0.4998, + "step": 7796 + }, + { + "epoch": 0.65, + "learning_rate": 5.6969477933892e-06, + "loss": 0.4451, + "step": 7797 + }, + { + "epoch": 0.65, + "learning_rate": 5.69450176518022e-06, + "loss": 0.4563, + "step": 7798 + }, + { + "epoch": 0.65, + "learning_rate": 5.692056053149122e-06, + "loss": 0.4794, + "step": 7799 + }, + { + "epoch": 0.65, + "learning_rate": 5.68961065747551e-06, + "loss": 0.4454, + "step": 7800 + }, + { + "epoch": 0.65, + "learning_rate": 5.687165578338962e-06, + "loss": 0.4627, + "step": 7801 + }, + { + "epoch": 0.65, + "learning_rate": 5.684720815919036e-06, + "loss": 0.4788, + "step": 7802 + }, + { + "epoch": 0.65, + "learning_rate": 5.682276370395261e-06, + "loss": 0.4744, + "step": 7803 + }, + { + "epoch": 0.65, + "learning_rate": 5.679832241947154e-06, + "loss": 0.4643, + "step": 7804 + }, + { + "epoch": 0.65, + "learning_rate": 5.677388430754196e-06, + "loss": 0.4488, + "step": 7805 + }, + { + "epoch": 0.65, + "learning_rate": 5.674944936995854e-06, + "loss": 0.4716, + "step": 7806 + }, + { + "epoch": 0.65, + "learning_rate": 5.672501760851568e-06, + "loss": 0.4773, + "step": 7807 + }, + { + "epoch": 0.65, + "learning_rate": 5.6700589025007535e-06, + "loss": 0.4811, + "step": 7808 + }, + { + "epoch": 0.65, + "learning_rate": 5.667616362122803e-06, + "loss": 0.491, + "step": 7809 + }, + { + "epoch": 0.65, + "learning_rate": 5.665174139897083e-06, + "loss": 0.4657, + "step": 7810 + }, + { + "epoch": 0.65, + "learning_rate": 5.662732236002949e-06, + "loss": 0.4906, + "step": 7811 + }, + { + "epoch": 0.65, + "learning_rate": 5.660290650619719e-06, + "loss": 0.481, + "step": 7812 + }, + { + "epoch": 0.65, + "learning_rate": 5.657849383926693e-06, + "loss": 0.4664, + "step": 7813 + }, + { + "epoch": 0.65, + "learning_rate": 5.655408436103149e-06, + "loss": 0.4844, + "step": 7814 + }, + { + "epoch": 0.65, + "learning_rate": 5.652967807328334e-06, + "loss": 0.4665, + "step": 7815 + }, + { + "epoch": 0.65, + "learning_rate": 5.6505274977814875e-06, + "loss": 0.4795, + "step": 7816 + }, + { + "epoch": 0.65, + "learning_rate": 5.648087507641806e-06, + "loss": 0.4739, + "step": 7817 + }, + { + "epoch": 0.65, + "learning_rate": 5.6456478370884815e-06, + "loss": 0.508, + "step": 7818 + }, + { + "epoch": 0.65, + "learning_rate": 5.643208486300669e-06, + "loss": 0.4686, + "step": 7819 + }, + { + "epoch": 0.65, + "learning_rate": 5.640769455457502e-06, + "loss": 0.4812, + "step": 7820 + }, + { + "epoch": 0.65, + "learning_rate": 5.6383307447380965e-06, + "loss": 0.4453, + "step": 7821 + }, + { + "epoch": 0.65, + "learning_rate": 5.635892354321539e-06, + "loss": 0.4728, + "step": 7822 + }, + { + "epoch": 0.65, + "learning_rate": 5.633454284386893e-06, + "loss": 0.4947, + "step": 7823 + }, + { + "epoch": 0.65, + "learning_rate": 5.631016535113204e-06, + "loss": 0.4628, + "step": 7824 + }, + { + "epoch": 0.65, + "learning_rate": 5.628579106679491e-06, + "loss": 0.4684, + "step": 7825 + }, + { + "epoch": 0.65, + "learning_rate": 5.62614199926474e-06, + "loss": 0.4589, + "step": 7826 + }, + { + "epoch": 0.65, + "learning_rate": 5.623705213047933e-06, + "loss": 0.483, + "step": 7827 + }, + { + "epoch": 0.65, + "learning_rate": 5.621268748208013e-06, + "loss": 0.4802, + "step": 7828 + }, + { + "epoch": 0.66, + "learning_rate": 5.618832604923904e-06, + "loss": 0.4595, + "step": 7829 + }, + { + "epoch": 0.66, + "learning_rate": 5.616396783374501e-06, + "loss": 0.4818, + "step": 7830 + }, + { + "epoch": 0.66, + "learning_rate": 5.613961283738692e-06, + "loss": 0.4592, + "step": 7831 + }, + { + "epoch": 0.66, + "learning_rate": 5.61152610619532e-06, + "loss": 0.4717, + "step": 7832 + }, + { + "epoch": 0.66, + "learning_rate": 5.60909125092322e-06, + "loss": 0.4754, + "step": 7833 + }, + { + "epoch": 0.66, + "learning_rate": 5.606656718101193e-06, + "loss": 0.4837, + "step": 7834 + }, + { + "epoch": 0.66, + "learning_rate": 5.604222507908021e-06, + "loss": 0.4693, + "step": 7835 + }, + { + "epoch": 0.66, + "learning_rate": 5.60178862052247e-06, + "loss": 0.4601, + "step": 7836 + }, + { + "epoch": 0.66, + "learning_rate": 5.599355056123263e-06, + "loss": 0.5122, + "step": 7837 + }, + { + "epoch": 0.66, + "learning_rate": 5.596921814889122e-06, + "loss": 0.4721, + "step": 7838 + }, + { + "epoch": 0.66, + "learning_rate": 5.594488896998729e-06, + "loss": 0.481, + "step": 7839 + }, + { + "epoch": 0.66, + "learning_rate": 5.592056302630748e-06, + "loss": 0.4778, + "step": 7840 + }, + { + "epoch": 0.66, + "learning_rate": 5.589624031963816e-06, + "loss": 0.4752, + "step": 7841 + }, + { + "epoch": 0.66, + "learning_rate": 5.5871920851765535e-06, + "loss": 0.4595, + "step": 7842 + }, + { + "epoch": 0.66, + "learning_rate": 5.584760462447548e-06, + "loss": 0.4692, + "step": 7843 + }, + { + "epoch": 0.66, + "learning_rate": 5.582329163955367e-06, + "loss": 0.47, + "step": 7844 + }, + { + "epoch": 0.66, + "learning_rate": 5.579898189878561e-06, + "loss": 0.4761, + "step": 7845 + }, + { + "epoch": 0.66, + "learning_rate": 5.577467540395645e-06, + "loss": 0.473, + "step": 7846 + }, + { + "epoch": 0.66, + "learning_rate": 5.575037215685119e-06, + "loss": 0.4554, + "step": 7847 + }, + { + "epoch": 0.66, + "learning_rate": 5.572607215925458e-06, + "loss": 0.4822, + "step": 7848 + }, + { + "epoch": 0.66, + "learning_rate": 5.570177541295107e-06, + "loss": 0.4727, + "step": 7849 + }, + { + "epoch": 0.66, + "learning_rate": 5.567748191972493e-06, + "loss": 0.4875, + "step": 7850 + }, + { + "epoch": 0.66, + "learning_rate": 5.565319168136012e-06, + "loss": 0.4617, + "step": 7851 + }, + { + "epoch": 0.66, + "learning_rate": 5.56289046996405e-06, + "loss": 0.4695, + "step": 7852 + }, + { + "epoch": 0.66, + "learning_rate": 5.5604620976349575e-06, + "loss": 0.4883, + "step": 7853 + }, + { + "epoch": 0.66, + "learning_rate": 5.558034051327061e-06, + "loss": 0.4778, + "step": 7854 + }, + { + "epoch": 0.66, + "learning_rate": 5.55560633121867e-06, + "loss": 0.4758, + "step": 7855 + }, + { + "epoch": 0.66, + "learning_rate": 5.553178937488061e-06, + "loss": 0.4683, + "step": 7856 + }, + { + "epoch": 0.66, + "learning_rate": 5.550751870313494e-06, + "loss": 0.4598, + "step": 7857 + }, + { + "epoch": 0.66, + "learning_rate": 5.548325129873209e-06, + "loss": 0.5035, + "step": 7858 + }, + { + "epoch": 0.66, + "learning_rate": 5.545898716345408e-06, + "loss": 0.4741, + "step": 7859 + }, + { + "epoch": 0.66, + "learning_rate": 5.543472629908282e-06, + "loss": 0.4689, + "step": 7860 + }, + { + "epoch": 0.66, + "learning_rate": 5.541046870739987e-06, + "loss": 0.4767, + "step": 7861 + }, + { + "epoch": 0.66, + "learning_rate": 5.538621439018666e-06, + "loss": 0.4579, + "step": 7862 + }, + { + "epoch": 0.66, + "learning_rate": 5.53619633492243e-06, + "loss": 0.4773, + "step": 7863 + }, + { + "epoch": 0.66, + "learning_rate": 5.533771558629365e-06, + "loss": 0.4711, + "step": 7864 + }, + { + "epoch": 0.66, + "learning_rate": 5.531347110317544e-06, + "loss": 0.482, + "step": 7865 + }, + { + "epoch": 0.66, + "learning_rate": 5.528922990165004e-06, + "loss": 0.443, + "step": 7866 + }, + { + "epoch": 0.66, + "learning_rate": 5.52649919834976e-06, + "loss": 0.4557, + "step": 7867 + }, + { + "epoch": 0.66, + "learning_rate": 5.524075735049812e-06, + "loss": 0.4646, + "step": 7868 + }, + { + "epoch": 0.66, + "learning_rate": 5.521652600443124e-06, + "loss": 0.4632, + "step": 7869 + }, + { + "epoch": 0.66, + "learning_rate": 5.519229794707643e-06, + "loss": 0.4557, + "step": 7870 + }, + { + "epoch": 0.66, + "learning_rate": 5.516807318021286e-06, + "loss": 0.475, + "step": 7871 + }, + { + "epoch": 0.66, + "learning_rate": 5.514385170561956e-06, + "loss": 0.4735, + "step": 7872 + }, + { + "epoch": 0.66, + "learning_rate": 5.511963352507521e-06, + "loss": 0.4566, + "step": 7873 + }, + { + "epoch": 0.66, + "learning_rate": 5.50954186403583e-06, + "loss": 0.4755, + "step": 7874 + }, + { + "epoch": 0.66, + "learning_rate": 5.507120705324709e-06, + "loss": 0.4943, + "step": 7875 + }, + { + "epoch": 0.66, + "learning_rate": 5.504699876551951e-06, + "loss": 0.4656, + "step": 7876 + }, + { + "epoch": 0.66, + "learning_rate": 5.502279377895341e-06, + "loss": 0.4863, + "step": 7877 + }, + { + "epoch": 0.66, + "learning_rate": 5.499859209532622e-06, + "loss": 0.4729, + "step": 7878 + }, + { + "epoch": 0.66, + "learning_rate": 5.497439371641528e-06, + "loss": 0.4802, + "step": 7879 + }, + { + "epoch": 0.66, + "learning_rate": 5.495019864399761e-06, + "loss": 0.4667, + "step": 7880 + }, + { + "epoch": 0.66, + "learning_rate": 5.492600687984997e-06, + "loss": 0.4724, + "step": 7881 + }, + { + "epoch": 0.66, + "learning_rate": 5.490181842574891e-06, + "loss": 0.4769, + "step": 7882 + }, + { + "epoch": 0.66, + "learning_rate": 5.487763328347071e-06, + "loss": 0.4641, + "step": 7883 + }, + { + "epoch": 0.66, + "learning_rate": 5.485345145479147e-06, + "loss": 0.485, + "step": 7884 + }, + { + "epoch": 0.66, + "learning_rate": 5.482927294148691e-06, + "loss": 0.4727, + "step": 7885 + }, + { + "epoch": 0.66, + "learning_rate": 5.480509774533271e-06, + "loss": 0.4835, + "step": 7886 + }, + { + "epoch": 0.66, + "learning_rate": 5.478092586810413e-06, + "loss": 0.4731, + "step": 7887 + }, + { + "epoch": 0.66, + "learning_rate": 5.47567573115763e-06, + "loss": 0.4807, + "step": 7888 + }, + { + "epoch": 0.66, + "learning_rate": 5.473259207752404e-06, + "loss": 0.4883, + "step": 7889 + }, + { + "epoch": 0.66, + "learning_rate": 5.470843016772194e-06, + "loss": 0.4636, + "step": 7890 + }, + { + "epoch": 0.66, + "learning_rate": 5.468427158394434e-06, + "loss": 0.4616, + "step": 7891 + }, + { + "epoch": 0.66, + "learning_rate": 5.466011632796531e-06, + "loss": 0.4808, + "step": 7892 + }, + { + "epoch": 0.66, + "learning_rate": 5.463596440155878e-06, + "loss": 0.4907, + "step": 7893 + }, + { + "epoch": 0.66, + "learning_rate": 5.461181580649837e-06, + "loss": 0.4812, + "step": 7894 + }, + { + "epoch": 0.66, + "learning_rate": 5.4587670544557404e-06, + "loss": 0.4711, + "step": 7895 + }, + { + "epoch": 0.66, + "learning_rate": 5.456352861750904e-06, + "loss": 0.4735, + "step": 7896 + }, + { + "epoch": 0.66, + "learning_rate": 5.453939002712611e-06, + "loss": 0.4667, + "step": 7897 + }, + { + "epoch": 0.66, + "learning_rate": 5.451525477518133e-06, + "loss": 0.4629, + "step": 7898 + }, + { + "epoch": 0.66, + "learning_rate": 5.4491122863447e-06, + "loss": 0.4739, + "step": 7899 + }, + { + "epoch": 0.66, + "learning_rate": 5.446699429369538e-06, + "loss": 0.4901, + "step": 7900 + }, + { + "epoch": 0.66, + "learning_rate": 5.444286906769831e-06, + "loss": 0.4603, + "step": 7901 + }, + { + "epoch": 0.66, + "learning_rate": 5.441874718722744e-06, + "loss": 0.474, + "step": 7902 + }, + { + "epoch": 0.66, + "learning_rate": 5.439462865405419e-06, + "loss": 0.4659, + "step": 7903 + }, + { + "epoch": 0.66, + "learning_rate": 5.437051346994973e-06, + "loss": 0.4519, + "step": 7904 + }, + { + "epoch": 0.66, + "learning_rate": 5.434640163668494e-06, + "loss": 0.4696, + "step": 7905 + }, + { + "epoch": 0.66, + "learning_rate": 5.432229315603054e-06, + "loss": 0.5035, + "step": 7906 + }, + { + "epoch": 0.66, + "learning_rate": 5.429818802975697e-06, + "loss": 0.4653, + "step": 7907 + }, + { + "epoch": 0.66, + "learning_rate": 5.427408625963434e-06, + "loss": 0.473, + "step": 7908 + }, + { + "epoch": 0.66, + "learning_rate": 5.424998784743266e-06, + "loss": 0.5055, + "step": 7909 + }, + { + "epoch": 0.66, + "learning_rate": 5.4225892794921585e-06, + "loss": 0.4932, + "step": 7910 + }, + { + "epoch": 0.66, + "learning_rate": 5.420180110387056e-06, + "loss": 0.4689, + "step": 7911 + }, + { + "epoch": 0.66, + "learning_rate": 5.417771277604873e-06, + "loss": 0.4671, + "step": 7912 + }, + { + "epoch": 0.66, + "learning_rate": 5.4153627813225114e-06, + "loss": 0.4679, + "step": 7913 + }, + { + "epoch": 0.66, + "learning_rate": 5.412954621716839e-06, + "loss": 0.4852, + "step": 7914 + }, + { + "epoch": 0.66, + "learning_rate": 5.410546798964701e-06, + "loss": 0.4746, + "step": 7915 + }, + { + "epoch": 0.66, + "learning_rate": 5.408139313242916e-06, + "loss": 0.4582, + "step": 7916 + }, + { + "epoch": 0.66, + "learning_rate": 5.405732164728276e-06, + "loss": 0.4603, + "step": 7917 + }, + { + "epoch": 0.66, + "learning_rate": 5.4033253535975635e-06, + "loss": 0.4852, + "step": 7918 + }, + { + "epoch": 0.66, + "learning_rate": 5.400918880027513e-06, + "loss": 0.4561, + "step": 7919 + }, + { + "epoch": 0.66, + "learning_rate": 5.398512744194854e-06, + "loss": 0.4665, + "step": 7920 + }, + { + "epoch": 0.66, + "learning_rate": 5.3961069462762804e-06, + "loss": 0.4571, + "step": 7921 + }, + { + "epoch": 0.66, + "learning_rate": 5.3937014864484635e-06, + "loss": 0.4624, + "step": 7922 + }, + { + "epoch": 0.66, + "learning_rate": 5.39129636488805e-06, + "loss": 0.4613, + "step": 7923 + }, + { + "epoch": 0.66, + "learning_rate": 5.388891581771664e-06, + "loss": 0.4828, + "step": 7924 + }, + { + "epoch": 0.66, + "learning_rate": 5.3864871372759e-06, + "loss": 0.4632, + "step": 7925 + }, + { + "epoch": 0.66, + "learning_rate": 5.384083031577327e-06, + "loss": 0.4565, + "step": 7926 + }, + { + "epoch": 0.66, + "learning_rate": 5.381679264852503e-06, + "loss": 0.4787, + "step": 7927 + }, + { + "epoch": 0.66, + "learning_rate": 5.379275837277944e-06, + "loss": 0.4624, + "step": 7928 + }, + { + "epoch": 0.66, + "learning_rate": 5.3768727490301445e-06, + "loss": 0.4692, + "step": 7929 + }, + { + "epoch": 0.66, + "learning_rate": 5.374470000285584e-06, + "loss": 0.454, + "step": 7930 + }, + { + "epoch": 0.66, + "learning_rate": 5.3720675912207085e-06, + "loss": 0.4773, + "step": 7931 + }, + { + "epoch": 0.66, + "learning_rate": 5.369665522011938e-06, + "loss": 0.4697, + "step": 7932 + }, + { + "epoch": 0.66, + "learning_rate": 5.367263792835673e-06, + "loss": 0.4758, + "step": 7933 + }, + { + "epoch": 0.66, + "learning_rate": 5.3648624038682886e-06, + "loss": 0.4822, + "step": 7934 + }, + { + "epoch": 0.66, + "learning_rate": 5.362461355286129e-06, + "loss": 0.4614, + "step": 7935 + }, + { + "epoch": 0.66, + "learning_rate": 5.360060647265519e-06, + "loss": 0.4877, + "step": 7936 + }, + { + "epoch": 0.66, + "learning_rate": 5.357660279982757e-06, + "loss": 0.4527, + "step": 7937 + }, + { + "epoch": 0.66, + "learning_rate": 5.35526025361411e-06, + "loss": 0.4733, + "step": 7938 + }, + { + "epoch": 0.66, + "learning_rate": 5.352860568335835e-06, + "loss": 0.4525, + "step": 7939 + }, + { + "epoch": 0.66, + "learning_rate": 5.3504612243241474e-06, + "loss": 0.4608, + "step": 7940 + }, + { + "epoch": 0.66, + "learning_rate": 5.3480622217552524e-06, + "loss": 0.4853, + "step": 7941 + }, + { + "epoch": 0.66, + "learning_rate": 5.3456635608053186e-06, + "loss": 0.4678, + "step": 7942 + }, + { + "epoch": 0.66, + "learning_rate": 5.343265241650495e-06, + "loss": 0.4678, + "step": 7943 + }, + { + "epoch": 0.66, + "learning_rate": 5.340867264466902e-06, + "loss": 0.471, + "step": 7944 + }, + { + "epoch": 0.66, + "learning_rate": 5.338469629430638e-06, + "loss": 0.4485, + "step": 7945 + }, + { + "epoch": 0.66, + "learning_rate": 5.336072336717773e-06, + "loss": 0.4902, + "step": 7946 + }, + { + "epoch": 0.66, + "learning_rate": 5.333675386504361e-06, + "loss": 0.47, + "step": 7947 + }, + { + "epoch": 0.66, + "learning_rate": 5.33127877896642e-06, + "loss": 0.4581, + "step": 7948 + }, + { + "epoch": 0.67, + "learning_rate": 5.328882514279942e-06, + "loss": 0.4655, + "step": 7949 + }, + { + "epoch": 0.67, + "learning_rate": 5.3264865926209076e-06, + "loss": 0.4873, + "step": 7950 + }, + { + "epoch": 0.67, + "learning_rate": 5.324091014165259e-06, + "loss": 0.4545, + "step": 7951 + }, + { + "epoch": 0.67, + "learning_rate": 5.3216957790889176e-06, + "loss": 0.4819, + "step": 7952 + }, + { + "epoch": 0.67, + "learning_rate": 5.319300887567777e-06, + "loss": 0.4598, + "step": 7953 + }, + { + "epoch": 0.67, + "learning_rate": 5.316906339777714e-06, + "loss": 0.4577, + "step": 7954 + }, + { + "epoch": 0.67, + "learning_rate": 5.31451213589457e-06, + "loss": 0.4706, + "step": 7955 + }, + { + "epoch": 0.67, + "learning_rate": 5.312118276094167e-06, + "loss": 0.4746, + "step": 7956 + }, + { + "epoch": 0.67, + "learning_rate": 5.3097247605522996e-06, + "loss": 0.4613, + "step": 7957 + }, + { + "epoch": 0.67, + "learning_rate": 5.307331589444737e-06, + "loss": 0.469, + "step": 7958 + }, + { + "epoch": 0.67, + "learning_rate": 5.304938762947221e-06, + "loss": 0.4634, + "step": 7959 + }, + { + "epoch": 0.67, + "learning_rate": 5.3025462812354744e-06, + "loss": 0.4984, + "step": 7960 + }, + { + "epoch": 0.67, + "learning_rate": 5.300154144485194e-06, + "loss": 0.4598, + "step": 7961 + }, + { + "epoch": 0.67, + "learning_rate": 5.297762352872044e-06, + "loss": 0.448, + "step": 7962 + }, + { + "epoch": 0.67, + "learning_rate": 5.2953709065716704e-06, + "loss": 0.4654, + "step": 7963 + }, + { + "epoch": 0.67, + "learning_rate": 5.292979805759689e-06, + "loss": 0.4789, + "step": 7964 + }, + { + "epoch": 0.67, + "learning_rate": 5.290589050611692e-06, + "loss": 0.4614, + "step": 7965 + }, + { + "epoch": 0.67, + "learning_rate": 5.288198641303248e-06, + "loss": 0.4794, + "step": 7966 + }, + { + "epoch": 0.67, + "learning_rate": 5.285808578009894e-06, + "loss": 0.454, + "step": 7967 + }, + { + "epoch": 0.67, + "learning_rate": 5.283418860907155e-06, + "loss": 0.4548, + "step": 7968 + }, + { + "epoch": 0.67, + "learning_rate": 5.281029490170515e-06, + "loss": 0.469, + "step": 7969 + }, + { + "epoch": 0.67, + "learning_rate": 5.2786404659754375e-06, + "loss": 0.4638, + "step": 7970 + }, + { + "epoch": 0.67, + "learning_rate": 5.276251788497373e-06, + "loss": 0.4919, + "step": 7971 + }, + { + "epoch": 0.67, + "learning_rate": 5.273863457911728e-06, + "loss": 0.4731, + "step": 7972 + }, + { + "epoch": 0.67, + "learning_rate": 5.271475474393889e-06, + "loss": 0.4618, + "step": 7973 + }, + { + "epoch": 0.67, + "learning_rate": 5.269087838119229e-06, + "loss": 0.4624, + "step": 7974 + }, + { + "epoch": 0.67, + "learning_rate": 5.266700549263079e-06, + "loss": 0.4752, + "step": 7975 + }, + { + "epoch": 0.67, + "learning_rate": 5.264313608000755e-06, + "loss": 0.4623, + "step": 7976 + }, + { + "epoch": 0.67, + "learning_rate": 5.261927014507542e-06, + "loss": 0.4629, + "step": 7977 + }, + { + "epoch": 0.67, + "learning_rate": 5.2595407689587006e-06, + "loss": 0.457, + "step": 7978 + }, + { + "epoch": 0.67, + "learning_rate": 5.2571548715294664e-06, + "loss": 0.4797, + "step": 7979 + }, + { + "epoch": 0.67, + "learning_rate": 5.254769322395053e-06, + "loss": 0.474, + "step": 7980 + }, + { + "epoch": 0.67, + "learning_rate": 5.2523841217306415e-06, + "loss": 0.456, + "step": 7981 + }, + { + "epoch": 0.67, + "learning_rate": 5.249999269711396e-06, + "loss": 0.454, + "step": 7982 + }, + { + "epoch": 0.67, + "learning_rate": 5.247614766512449e-06, + "loss": 0.4753, + "step": 7983 + }, + { + "epoch": 0.67, + "learning_rate": 5.245230612308906e-06, + "loss": 0.4781, + "step": 7984 + }, + { + "epoch": 0.67, + "learning_rate": 5.24284680727585e-06, + "loss": 0.4845, + "step": 7985 + }, + { + "epoch": 0.67, + "learning_rate": 5.240463351588339e-06, + "loss": 0.4856, + "step": 7986 + }, + { + "epoch": 0.67, + "learning_rate": 5.238080245421397e-06, + "loss": 0.4736, + "step": 7987 + }, + { + "epoch": 0.67, + "learning_rate": 5.235697488950041e-06, + "loss": 0.4765, + "step": 7988 + }, + { + "epoch": 0.67, + "learning_rate": 5.233315082349245e-06, + "loss": 0.4583, + "step": 7989 + }, + { + "epoch": 0.67, + "learning_rate": 5.2309330257939596e-06, + "loss": 0.467, + "step": 7990 + }, + { + "epoch": 0.67, + "learning_rate": 5.22855131945912e-06, + "loss": 0.4896, + "step": 7991 + }, + { + "epoch": 0.67, + "learning_rate": 5.226169963519625e-06, + "loss": 0.4487, + "step": 7992 + }, + { + "epoch": 0.67, + "learning_rate": 5.223788958150353e-06, + "loss": 0.4804, + "step": 7993 + }, + { + "epoch": 0.67, + "learning_rate": 5.221408303526151e-06, + "loss": 0.4854, + "step": 7994 + }, + { + "epoch": 0.67, + "learning_rate": 5.219027999821851e-06, + "loss": 0.4575, + "step": 7995 + }, + { + "epoch": 0.67, + "learning_rate": 5.2166480472122475e-06, + "loss": 0.4674, + "step": 7996 + }, + { + "epoch": 0.67, + "learning_rate": 5.214268445872117e-06, + "loss": 0.4684, + "step": 7997 + }, + { + "epoch": 0.67, + "learning_rate": 5.211889195976207e-06, + "loss": 0.4653, + "step": 7998 + }, + { + "epoch": 0.67, + "learning_rate": 5.209510297699239e-06, + "loss": 0.4578, + "step": 7999 + }, + { + "epoch": 0.67, + "learning_rate": 5.2071317512159055e-06, + "loss": 0.4672, + "step": 8000 + }, + { + "epoch": 0.67, + "learning_rate": 5.204753556700881e-06, + "loss": 0.4591, + "step": 8001 + }, + { + "epoch": 0.67, + "learning_rate": 5.202375714328814e-06, + "loss": 0.4749, + "step": 8002 + }, + { + "epoch": 0.67, + "learning_rate": 5.199998224274321e-06, + "loss": 0.483, + "step": 8003 + }, + { + "epoch": 0.67, + "learning_rate": 5.197621086711993e-06, + "loss": 0.4896, + "step": 8004 + }, + { + "epoch": 0.67, + "learning_rate": 5.195244301816398e-06, + "loss": 0.4701, + "step": 8005 + }, + { + "epoch": 0.67, + "learning_rate": 5.192867869762076e-06, + "loss": 0.4645, + "step": 8006 + }, + { + "epoch": 0.67, + "learning_rate": 5.1904917907235395e-06, + "loss": 0.4561, + "step": 8007 + }, + { + "epoch": 0.67, + "learning_rate": 5.188116064875286e-06, + "loss": 0.4791, + "step": 8008 + }, + { + "epoch": 0.67, + "learning_rate": 5.185740692391774e-06, + "loss": 0.4797, + "step": 8009 + }, + { + "epoch": 0.67, + "learning_rate": 5.183365673447442e-06, + "loss": 0.4743, + "step": 8010 + }, + { + "epoch": 0.67, + "learning_rate": 5.180991008216698e-06, + "loss": 0.4652, + "step": 8011 + }, + { + "epoch": 0.67, + "learning_rate": 5.178616696873935e-06, + "loss": 0.4932, + "step": 8012 + }, + { + "epoch": 0.67, + "learning_rate": 5.1762427395935065e-06, + "loss": 0.4888, + "step": 8013 + }, + { + "epoch": 0.67, + "learning_rate": 5.173869136549744e-06, + "loss": 0.48, + "step": 8014 + }, + { + "epoch": 0.67, + "learning_rate": 5.171495887916962e-06, + "loss": 0.465, + "step": 8015 + }, + { + "epoch": 0.67, + "learning_rate": 5.1691229938694396e-06, + "loss": 0.4495, + "step": 8016 + }, + { + "epoch": 0.67, + "learning_rate": 5.166750454581432e-06, + "loss": 0.4761, + "step": 8017 + }, + { + "epoch": 0.67, + "learning_rate": 5.164378270227167e-06, + "loss": 0.4633, + "step": 8018 + }, + { + "epoch": 0.67, + "learning_rate": 5.162006440980849e-06, + "loss": 0.4559, + "step": 8019 + }, + { + "epoch": 0.67, + "learning_rate": 5.159634967016653e-06, + "loss": 0.4589, + "step": 8020 + }, + { + "epoch": 0.67, + "learning_rate": 5.157263848508735e-06, + "loss": 0.4933, + "step": 8021 + }, + { + "epoch": 0.67, + "learning_rate": 5.154893085631213e-06, + "loss": 0.4685, + "step": 8022 + }, + { + "epoch": 0.67, + "learning_rate": 5.152522678558195e-06, + "loss": 0.4722, + "step": 8023 + }, + { + "epoch": 0.67, + "learning_rate": 5.150152627463749e-06, + "loss": 0.473, + "step": 8024 + }, + { + "epoch": 0.67, + "learning_rate": 5.1477829325219235e-06, + "loss": 0.4841, + "step": 8025 + }, + { + "epoch": 0.67, + "learning_rate": 5.1454135939067365e-06, + "loss": 0.4842, + "step": 8026 + }, + { + "epoch": 0.67, + "learning_rate": 5.143044611792183e-06, + "loss": 0.4715, + "step": 8027 + }, + { + "epoch": 0.67, + "learning_rate": 5.140675986352228e-06, + "loss": 0.4933, + "step": 8028 + }, + { + "epoch": 0.67, + "learning_rate": 5.13830771776082e-06, + "loss": 0.4563, + "step": 8029 + }, + { + "epoch": 0.67, + "learning_rate": 5.135939806191874e-06, + "loss": 0.4535, + "step": 8030 + }, + { + "epoch": 0.67, + "learning_rate": 5.133572251819272e-06, + "loss": 0.4683, + "step": 8031 + }, + { + "epoch": 0.67, + "learning_rate": 5.131205054816888e-06, + "loss": 0.4829, + "step": 8032 + }, + { + "epoch": 0.67, + "learning_rate": 5.128838215358553e-06, + "loss": 0.4593, + "step": 8033 + }, + { + "epoch": 0.67, + "learning_rate": 5.126471733618079e-06, + "loss": 0.4618, + "step": 8034 + }, + { + "epoch": 0.67, + "learning_rate": 5.124105609769246e-06, + "loss": 0.4798, + "step": 8035 + }, + { + "epoch": 0.67, + "learning_rate": 5.12173984398582e-06, + "loss": 0.4731, + "step": 8036 + }, + { + "epoch": 0.67, + "learning_rate": 5.119374436441531e-06, + "loss": 0.4838, + "step": 8037 + }, + { + "epoch": 0.67, + "learning_rate": 5.117009387310083e-06, + "loss": 0.4896, + "step": 8038 + }, + { + "epoch": 0.67, + "learning_rate": 5.114644696765157e-06, + "loss": 0.4656, + "step": 8039 + }, + { + "epoch": 0.67, + "learning_rate": 5.112280364980402e-06, + "loss": 0.4628, + "step": 8040 + }, + { + "epoch": 0.67, + "learning_rate": 5.109916392129446e-06, + "loss": 0.469, + "step": 8041 + }, + { + "epoch": 0.67, + "learning_rate": 5.1075527783858934e-06, + "loss": 0.4615, + "step": 8042 + }, + { + "epoch": 0.67, + "learning_rate": 5.105189523923312e-06, + "loss": 0.4725, + "step": 8043 + }, + { + "epoch": 0.67, + "learning_rate": 5.1028266289152565e-06, + "loss": 0.4601, + "step": 8044 + }, + { + "epoch": 0.67, + "learning_rate": 5.100464093535244e-06, + "loss": 0.4656, + "step": 8045 + }, + { + "epoch": 0.67, + "learning_rate": 5.098101917956771e-06, + "loss": 0.4931, + "step": 8046 + }, + { + "epoch": 0.67, + "learning_rate": 5.0957401023533036e-06, + "loss": 0.4619, + "step": 8047 + }, + { + "epoch": 0.67, + "learning_rate": 5.093378646898282e-06, + "loss": 0.4562, + "step": 8048 + }, + { + "epoch": 0.67, + "learning_rate": 5.091017551765127e-06, + "loss": 0.4753, + "step": 8049 + }, + { + "epoch": 0.67, + "learning_rate": 5.0886568171272265e-06, + "loss": 0.475, + "step": 8050 + }, + { + "epoch": 0.67, + "learning_rate": 5.08629644315794e-06, + "loss": 0.453, + "step": 8051 + }, + { + "epoch": 0.67, + "learning_rate": 5.0839364300306016e-06, + "loss": 0.4629, + "step": 8052 + }, + { + "epoch": 0.67, + "learning_rate": 5.081576777918529e-06, + "loss": 0.4749, + "step": 8053 + }, + { + "epoch": 0.67, + "learning_rate": 5.079217486994999e-06, + "loss": 0.4747, + "step": 8054 + }, + { + "epoch": 0.67, + "learning_rate": 5.0768585574332675e-06, + "loss": 0.4711, + "step": 8055 + }, + { + "epoch": 0.67, + "learning_rate": 5.074499989406569e-06, + "loss": 0.4655, + "step": 8056 + }, + { + "epoch": 0.67, + "learning_rate": 5.072141783088107e-06, + "loss": 0.4468, + "step": 8057 + }, + { + "epoch": 0.67, + "learning_rate": 5.069783938651054e-06, + "loss": 0.45, + "step": 8058 + }, + { + "epoch": 0.67, + "learning_rate": 5.067426456268563e-06, + "loss": 0.4939, + "step": 8059 + }, + { + "epoch": 0.67, + "learning_rate": 5.065069336113756e-06, + "loss": 0.4619, + "step": 8060 + }, + { + "epoch": 0.67, + "learning_rate": 5.062712578359728e-06, + "loss": 0.4636, + "step": 8061 + }, + { + "epoch": 0.67, + "learning_rate": 5.060356183179556e-06, + "loss": 0.4795, + "step": 8062 + }, + { + "epoch": 0.67, + "learning_rate": 5.058000150746276e-06, + "loss": 0.471, + "step": 8063 + }, + { + "epoch": 0.67, + "learning_rate": 5.055644481232914e-06, + "loss": 0.4677, + "step": 8064 + }, + { + "epoch": 0.67, + "learning_rate": 5.0532891748124565e-06, + "loss": 0.4624, + "step": 8065 + }, + { + "epoch": 0.67, + "learning_rate": 5.050934231657867e-06, + "loss": 0.4759, + "step": 8066 + }, + { + "epoch": 0.67, + "learning_rate": 5.048579651942083e-06, + "loss": 0.4778, + "step": 8067 + }, + { + "epoch": 0.68, + "learning_rate": 5.046225435838015e-06, + "loss": 0.4734, + "step": 8068 + }, + { + "epoch": 0.68, + "learning_rate": 5.043871583518542e-06, + "loss": 0.4746, + "step": 8069 + }, + { + "epoch": 0.68, + "learning_rate": 5.04151809515653e-06, + "loss": 0.4566, + "step": 8070 + }, + { + "epoch": 0.68, + "learning_rate": 5.039164970924805e-06, + "loss": 0.4637, + "step": 8071 + }, + { + "epoch": 0.68, + "learning_rate": 5.0368122109961716e-06, + "loss": 0.453, + "step": 8072 + }, + { + "epoch": 0.68, + "learning_rate": 5.034459815543401e-06, + "loss": 0.4528, + "step": 8073 + }, + { + "epoch": 0.68, + "learning_rate": 5.032107784739253e-06, + "loss": 0.4723, + "step": 8074 + }, + { + "epoch": 0.68, + "learning_rate": 5.029756118756446e-06, + "loss": 0.4791, + "step": 8075 + }, + { + "epoch": 0.68, + "learning_rate": 5.027404817767672e-06, + "loss": 0.4692, + "step": 8076 + }, + { + "epoch": 0.68, + "learning_rate": 5.025053881945612e-06, + "loss": 0.4452, + "step": 8077 + }, + { + "epoch": 0.68, + "learning_rate": 5.0227033114629e-06, + "loss": 0.4711, + "step": 8078 + }, + { + "epoch": 0.68, + "learning_rate": 5.020353106492156e-06, + "loss": 0.4609, + "step": 8079 + }, + { + "epoch": 0.68, + "learning_rate": 5.018003267205969e-06, + "loss": 0.4732, + "step": 8080 + }, + { + "epoch": 0.68, + "learning_rate": 5.015653793776898e-06, + "loss": 0.4574, + "step": 8081 + }, + { + "epoch": 0.68, + "learning_rate": 5.013304686377478e-06, + "loss": 0.4587, + "step": 8082 + }, + { + "epoch": 0.68, + "learning_rate": 5.010955945180225e-06, + "loss": 0.4708, + "step": 8083 + }, + { + "epoch": 0.68, + "learning_rate": 5.008607570357612e-06, + "loss": 0.4685, + "step": 8084 + }, + { + "epoch": 0.68, + "learning_rate": 5.006259562082102e-06, + "loss": 0.4661, + "step": 8085 + }, + { + "epoch": 0.68, + "learning_rate": 5.003911920526119e-06, + "loss": 0.4538, + "step": 8086 + }, + { + "epoch": 0.68, + "learning_rate": 5.0015646458620645e-06, + "loss": 0.4543, + "step": 8087 + }, + { + "epoch": 0.68, + "learning_rate": 4.999217738262313e-06, + "loss": 0.4777, + "step": 8088 + }, + { + "epoch": 0.68, + "learning_rate": 4.996871197899207e-06, + "loss": 0.4714, + "step": 8089 + }, + { + "epoch": 0.68, + "learning_rate": 4.994525024945075e-06, + "loss": 0.4666, + "step": 8090 + }, + { + "epoch": 0.68, + "learning_rate": 4.992179219572204e-06, + "loss": 0.4673, + "step": 8091 + }, + { + "epoch": 0.68, + "learning_rate": 4.989833781952864e-06, + "loss": 0.4602, + "step": 8092 + }, + { + "epoch": 0.68, + "learning_rate": 4.987488712259288e-06, + "loss": 0.4727, + "step": 8093 + }, + { + "epoch": 0.68, + "learning_rate": 4.985144010663695e-06, + "loss": 0.4598, + "step": 8094 + }, + { + "epoch": 0.68, + "learning_rate": 4.982799677338268e-06, + "loss": 0.4775, + "step": 8095 + }, + { + "epoch": 0.68, + "learning_rate": 4.980455712455161e-06, + "loss": 0.4617, + "step": 8096 + }, + { + "epoch": 0.68, + "learning_rate": 4.978112116186512e-06, + "loss": 0.4769, + "step": 8097 + }, + { + "epoch": 0.68, + "learning_rate": 4.975768888704422e-06, + "loss": 0.4757, + "step": 8098 + }, + { + "epoch": 0.68, + "learning_rate": 4.973426030180968e-06, + "loss": 0.4748, + "step": 8099 + }, + { + "epoch": 0.68, + "learning_rate": 4.971083540788199e-06, + "loss": 0.4697, + "step": 8100 + }, + { + "epoch": 0.68, + "learning_rate": 4.968741420698137e-06, + "loss": 0.4743, + "step": 8101 + }, + { + "epoch": 0.68, + "learning_rate": 4.966399670082779e-06, + "loss": 0.4653, + "step": 8102 + }, + { + "epoch": 0.68, + "learning_rate": 4.964058289114089e-06, + "loss": 0.4759, + "step": 8103 + }, + { + "epoch": 0.68, + "learning_rate": 4.961717277964012e-06, + "loss": 0.5013, + "step": 8104 + }, + { + "epoch": 0.68, + "learning_rate": 4.959376636804467e-06, + "loss": 0.4803, + "step": 8105 + }, + { + "epoch": 0.68, + "learning_rate": 4.9570363658073366e-06, + "loss": 0.4712, + "step": 8106 + }, + { + "epoch": 0.68, + "learning_rate": 4.954696465144479e-06, + "loss": 0.4678, + "step": 8107 + }, + { + "epoch": 0.68, + "learning_rate": 4.952356934987728e-06, + "loss": 0.4561, + "step": 8108 + }, + { + "epoch": 0.68, + "learning_rate": 4.95001777550889e-06, + "loss": 0.4624, + "step": 8109 + }, + { + "epoch": 0.68, + "learning_rate": 4.947678986879737e-06, + "loss": 0.4786, + "step": 8110 + }, + { + "epoch": 0.68, + "learning_rate": 4.945340569272029e-06, + "loss": 0.4465, + "step": 8111 + }, + { + "epoch": 0.68, + "learning_rate": 4.943002522857487e-06, + "loss": 0.477, + "step": 8112 + }, + { + "epoch": 0.68, + "learning_rate": 4.940664847807804e-06, + "loss": 0.4772, + "step": 8113 + }, + { + "epoch": 0.68, + "learning_rate": 4.9383275442946495e-06, + "loss": 0.4757, + "step": 8114 + }, + { + "epoch": 0.68, + "learning_rate": 4.935990612489671e-06, + "loss": 0.4488, + "step": 8115 + }, + { + "epoch": 0.68, + "learning_rate": 4.933654052564477e-06, + "loss": 0.4872, + "step": 8116 + }, + { + "epoch": 0.68, + "learning_rate": 4.931317864690655e-06, + "loss": 0.4675, + "step": 8117 + }, + { + "epoch": 0.68, + "learning_rate": 4.92898204903977e-06, + "loss": 0.4818, + "step": 8118 + }, + { + "epoch": 0.68, + "learning_rate": 4.92664660578335e-06, + "loss": 0.4752, + "step": 8119 + }, + { + "epoch": 0.68, + "learning_rate": 4.924311535092904e-06, + "loss": 0.4517, + "step": 8120 + }, + { + "epoch": 0.68, + "learning_rate": 4.9219768371399055e-06, + "loss": 0.4548, + "step": 8121 + }, + { + "epoch": 0.68, + "learning_rate": 4.919642512095808e-06, + "loss": 0.454, + "step": 8122 + }, + { + "epoch": 0.68, + "learning_rate": 4.917308560132029e-06, + "loss": 0.4802, + "step": 8123 + }, + { + "epoch": 0.68, + "learning_rate": 4.914974981419974e-06, + "loss": 0.4431, + "step": 8124 + }, + { + "epoch": 0.68, + "learning_rate": 4.9126417761310005e-06, + "loss": 0.4663, + "step": 8125 + }, + { + "epoch": 0.68, + "learning_rate": 4.9103089444364605e-06, + "loss": 0.4542, + "step": 8126 + }, + { + "epoch": 0.68, + "learning_rate": 4.9079764865076615e-06, + "loss": 0.4589, + "step": 8127 + }, + { + "epoch": 0.68, + "learning_rate": 4.90564440251589e-06, + "loss": 0.4767, + "step": 8128 + }, + { + "epoch": 0.68, + "learning_rate": 4.903312692632405e-06, + "loss": 0.463, + "step": 8129 + }, + { + "epoch": 0.68, + "learning_rate": 4.9009813570284326e-06, + "loss": 0.4729, + "step": 8130 + }, + { + "epoch": 0.68, + "learning_rate": 4.898650395875185e-06, + "loss": 0.4562, + "step": 8131 + }, + { + "epoch": 0.68, + "learning_rate": 4.896319809343834e-06, + "loss": 0.4701, + "step": 8132 + }, + { + "epoch": 0.68, + "learning_rate": 4.893989597605528e-06, + "loss": 0.4578, + "step": 8133 + }, + { + "epoch": 0.68, + "learning_rate": 4.8916597608313855e-06, + "loss": 0.4918, + "step": 8134 + }, + { + "epoch": 0.68, + "learning_rate": 4.8893302991925075e-06, + "loss": 0.4608, + "step": 8135 + }, + { + "epoch": 0.68, + "learning_rate": 4.887001212859954e-06, + "loss": 0.4662, + "step": 8136 + }, + { + "epoch": 0.68, + "learning_rate": 4.884672502004762e-06, + "loss": 0.4747, + "step": 8137 + }, + { + "epoch": 0.68, + "learning_rate": 4.8823441667979475e-06, + "loss": 0.4636, + "step": 8138 + }, + { + "epoch": 0.68, + "learning_rate": 4.880016207410493e-06, + "loss": 0.4709, + "step": 8139 + }, + { + "epoch": 0.68, + "learning_rate": 4.877688624013353e-06, + "loss": 0.4848, + "step": 8140 + }, + { + "epoch": 0.68, + "learning_rate": 4.875361416777453e-06, + "loss": 0.4728, + "step": 8141 + }, + { + "epoch": 0.68, + "learning_rate": 4.873034585873697e-06, + "loss": 0.494, + "step": 8142 + }, + { + "epoch": 0.68, + "learning_rate": 4.870708131472957e-06, + "loss": 0.4538, + "step": 8143 + }, + { + "epoch": 0.68, + "learning_rate": 4.868382053746072e-06, + "loss": 0.4667, + "step": 8144 + }, + { + "epoch": 0.68, + "learning_rate": 4.866056352863866e-06, + "loss": 0.4854, + "step": 8145 + }, + { + "epoch": 0.68, + "learning_rate": 4.8637310289971314e-06, + "loss": 0.4811, + "step": 8146 + }, + { + "epoch": 0.68, + "learning_rate": 4.861406082316626e-06, + "loss": 0.471, + "step": 8147 + }, + { + "epoch": 0.68, + "learning_rate": 4.8590815129930865e-06, + "loss": 0.4748, + "step": 8148 + }, + { + "epoch": 0.68, + "learning_rate": 4.8567573211972175e-06, + "loss": 0.4685, + "step": 8149 + }, + { + "epoch": 0.68, + "learning_rate": 4.854433507099698e-06, + "loss": 0.4846, + "step": 8150 + }, + { + "epoch": 0.68, + "learning_rate": 4.852110070871175e-06, + "loss": 0.4754, + "step": 8151 + }, + { + "epoch": 0.68, + "learning_rate": 4.849787012682282e-06, + "loss": 0.464, + "step": 8152 + }, + { + "epoch": 0.68, + "learning_rate": 4.8474643327036095e-06, + "loss": 0.4705, + "step": 8153 + }, + { + "epoch": 0.68, + "learning_rate": 4.845142031105724e-06, + "loss": 0.4814, + "step": 8154 + }, + { + "epoch": 0.68, + "learning_rate": 4.8428201080591645e-06, + "loss": 0.4669, + "step": 8155 + }, + { + "epoch": 0.68, + "learning_rate": 4.840498563734449e-06, + "loss": 0.4703, + "step": 8156 + }, + { + "epoch": 0.68, + "learning_rate": 4.838177398302056e-06, + "loss": 0.4661, + "step": 8157 + }, + { + "epoch": 0.68, + "learning_rate": 4.8358566119324494e-06, + "loss": 0.4684, + "step": 8158 + }, + { + "epoch": 0.68, + "learning_rate": 4.833536204796052e-06, + "loss": 0.4745, + "step": 8159 + }, + { + "epoch": 0.68, + "learning_rate": 4.831216177063268e-06, + "loss": 0.4634, + "step": 8160 + }, + { + "epoch": 0.68, + "learning_rate": 4.82889652890447e-06, + "loss": 0.4606, + "step": 8161 + }, + { + "epoch": 0.68, + "learning_rate": 4.8265772604900015e-06, + "loss": 0.4659, + "step": 8162 + }, + { + "epoch": 0.68, + "learning_rate": 4.824258371990181e-06, + "loss": 0.4668, + "step": 8163 + }, + { + "epoch": 0.68, + "learning_rate": 4.821939863575295e-06, + "loss": 0.4562, + "step": 8164 + }, + { + "epoch": 0.68, + "learning_rate": 4.819621735415613e-06, + "loss": 0.4466, + "step": 8165 + }, + { + "epoch": 0.68, + "learning_rate": 4.817303987681359e-06, + "loss": 0.4877, + "step": 8166 + }, + { + "epoch": 0.68, + "learning_rate": 4.814986620542747e-06, + "loss": 0.4766, + "step": 8167 + }, + { + "epoch": 0.68, + "learning_rate": 4.8126696341699515e-06, + "loss": 0.4601, + "step": 8168 + }, + { + "epoch": 0.68, + "learning_rate": 4.810353028733123e-06, + "loss": 0.4765, + "step": 8169 + }, + { + "epoch": 0.68, + "learning_rate": 4.808036804402383e-06, + "loss": 0.4913, + "step": 8170 + }, + { + "epoch": 0.68, + "learning_rate": 4.80572096134782e-06, + "loss": 0.4553, + "step": 8171 + }, + { + "epoch": 0.68, + "learning_rate": 4.803405499739511e-06, + "loss": 0.4824, + "step": 8172 + }, + { + "epoch": 0.68, + "learning_rate": 4.801090419747486e-06, + "loss": 0.466, + "step": 8173 + }, + { + "epoch": 0.68, + "learning_rate": 4.798775721541757e-06, + "loss": 0.4502, + "step": 8174 + }, + { + "epoch": 0.68, + "learning_rate": 4.796461405292302e-06, + "loss": 0.453, + "step": 8175 + }, + { + "epoch": 0.68, + "learning_rate": 4.794147471169082e-06, + "loss": 0.4768, + "step": 8176 + }, + { + "epoch": 0.68, + "learning_rate": 4.7918339193420195e-06, + "loss": 0.4754, + "step": 8177 + }, + { + "epoch": 0.68, + "learning_rate": 4.789520749981007e-06, + "loss": 0.4688, + "step": 8178 + }, + { + "epoch": 0.68, + "learning_rate": 4.787207963255922e-06, + "loss": 0.4925, + "step": 8179 + }, + { + "epoch": 0.68, + "learning_rate": 4.7848955593366035e-06, + "loss": 0.4751, + "step": 8180 + }, + { + "epoch": 0.68, + "learning_rate": 4.782583538392863e-06, + "loss": 0.4647, + "step": 8181 + }, + { + "epoch": 0.68, + "learning_rate": 4.7802719005944875e-06, + "loss": 0.4637, + "step": 8182 + }, + { + "epoch": 0.68, + "learning_rate": 4.777960646111233e-06, + "loss": 0.4859, + "step": 8183 + }, + { + "epoch": 0.68, + "learning_rate": 4.775649775112828e-06, + "loss": 0.4761, + "step": 8184 + }, + { + "epoch": 0.68, + "learning_rate": 4.77333928776897e-06, + "loss": 0.4867, + "step": 8185 + }, + { + "epoch": 0.68, + "learning_rate": 4.771029184249339e-06, + "loss": 0.4683, + "step": 8186 + }, + { + "epoch": 0.68, + "learning_rate": 4.768719464723572e-06, + "loss": 0.4825, + "step": 8187 + }, + { + "epoch": 0.69, + "learning_rate": 4.766410129361294e-06, + "loss": 0.4661, + "step": 8188 + }, + { + "epoch": 0.69, + "learning_rate": 4.7641011783320866e-06, + "loss": 0.4592, + "step": 8189 + }, + { + "epoch": 0.69, + "learning_rate": 4.7617926118055125e-06, + "loss": 0.4794, + "step": 8190 + }, + { + "epoch": 0.69, + "learning_rate": 4.7594844299511e-06, + "loss": 0.4742, + "step": 8191 + }, + { + "epoch": 0.69, + "learning_rate": 4.757176632938351e-06, + "loss": 0.4719, + "step": 8192 + }, + { + "epoch": 0.69, + "learning_rate": 4.754869220936748e-06, + "loss": 0.4626, + "step": 8193 + }, + { + "epoch": 0.69, + "learning_rate": 4.752562194115732e-06, + "loss": 0.4645, + "step": 8194 + }, + { + "epoch": 0.69, + "learning_rate": 4.750255552644722e-06, + "loss": 0.4626, + "step": 8195 + }, + { + "epoch": 0.69, + "learning_rate": 4.7479492966931076e-06, + "loss": 0.4671, + "step": 8196 + }, + { + "epoch": 0.69, + "learning_rate": 4.745643426430254e-06, + "loss": 0.4699, + "step": 8197 + }, + { + "epoch": 0.69, + "learning_rate": 4.743337942025489e-06, + "loss": 0.4682, + "step": 8198 + }, + { + "epoch": 0.69, + "learning_rate": 4.741032843648126e-06, + "loss": 0.4568, + "step": 8199 + }, + { + "epoch": 0.69, + "learning_rate": 4.738728131467436e-06, + "loss": 0.4775, + "step": 8200 + }, + { + "epoch": 0.69, + "learning_rate": 4.73642380565267e-06, + "loss": 0.4795, + "step": 8201 + }, + { + "epoch": 0.69, + "learning_rate": 4.734119866373046e-06, + "loss": 0.4591, + "step": 8202 + }, + { + "epoch": 0.69, + "learning_rate": 4.731816313797757e-06, + "loss": 0.4689, + "step": 8203 + }, + { + "epoch": 0.69, + "learning_rate": 4.7295131480959655e-06, + "loss": 0.4534, + "step": 8204 + }, + { + "epoch": 0.69, + "learning_rate": 4.727210369436803e-06, + "loss": 0.4792, + "step": 8205 + }, + { + "epoch": 0.69, + "learning_rate": 4.724907977989384e-06, + "loss": 0.4638, + "step": 8206 + }, + { + "epoch": 0.69, + "learning_rate": 4.7226059739227796e-06, + "loss": 0.4603, + "step": 8207 + }, + { + "epoch": 0.69, + "learning_rate": 4.720304357406044e-06, + "loss": 0.4847, + "step": 8208 + }, + { + "epoch": 0.69, + "learning_rate": 4.7180031286081975e-06, + "loss": 0.464, + "step": 8209 + }, + { + "epoch": 0.69, + "learning_rate": 4.715702287698232e-06, + "loss": 0.4724, + "step": 8210 + }, + { + "epoch": 0.69, + "learning_rate": 4.71340183484511e-06, + "loss": 0.4716, + "step": 8211 + }, + { + "epoch": 0.69, + "learning_rate": 4.711101770217766e-06, + "loss": 0.471, + "step": 8212 + }, + { + "epoch": 0.69, + "learning_rate": 4.708802093985113e-06, + "loss": 0.473, + "step": 8213 + }, + { + "epoch": 0.69, + "learning_rate": 4.706502806316028e-06, + "loss": 0.4778, + "step": 8214 + }, + { + "epoch": 0.69, + "learning_rate": 4.704203907379358e-06, + "loss": 0.4548, + "step": 8215 + }, + { + "epoch": 0.69, + "learning_rate": 4.7019053973439265e-06, + "loss": 0.484, + "step": 8216 + }, + { + "epoch": 0.69, + "learning_rate": 4.6996072763785225e-06, + "loss": 0.473, + "step": 8217 + }, + { + "epoch": 0.69, + "learning_rate": 4.697309544651918e-06, + "loss": 0.4642, + "step": 8218 + }, + { + "epoch": 0.69, + "learning_rate": 4.6950122023328415e-06, + "loss": 0.4716, + "step": 8219 + }, + { + "epoch": 0.69, + "learning_rate": 4.692715249590007e-06, + "loss": 0.4708, + "step": 8220 + }, + { + "epoch": 0.69, + "learning_rate": 4.69041868659209e-06, + "loss": 0.4752, + "step": 8221 + }, + { + "epoch": 0.69, + "learning_rate": 4.68812251350774e-06, + "loss": 0.4551, + "step": 8222 + }, + { + "epoch": 0.69, + "learning_rate": 4.685826730505581e-06, + "loss": 0.4794, + "step": 8223 + }, + { + "epoch": 0.69, + "learning_rate": 4.683531337754201e-06, + "loss": 0.4568, + "step": 8224 + }, + { + "epoch": 0.69, + "learning_rate": 4.6812363354221675e-06, + "loss": 0.4637, + "step": 8225 + }, + { + "epoch": 0.69, + "learning_rate": 4.678941723678012e-06, + "loss": 0.4712, + "step": 8226 + }, + { + "epoch": 0.69, + "learning_rate": 4.676647502690248e-06, + "loss": 0.4848, + "step": 8227 + }, + { + "epoch": 0.69, + "learning_rate": 4.674353672627345e-06, + "loss": 0.4672, + "step": 8228 + }, + { + "epoch": 0.69, + "learning_rate": 4.672060233657762e-06, + "loss": 0.4781, + "step": 8229 + }, + { + "epoch": 0.69, + "learning_rate": 4.669767185949915e-06, + "loss": 0.4555, + "step": 8230 + }, + { + "epoch": 0.69, + "learning_rate": 4.667474529672196e-06, + "loss": 0.4874, + "step": 8231 + }, + { + "epoch": 0.69, + "learning_rate": 4.665182264992966e-06, + "loss": 0.4607, + "step": 8232 + }, + { + "epoch": 0.69, + "learning_rate": 4.66289039208056e-06, + "loss": 0.4571, + "step": 8233 + }, + { + "epoch": 0.69, + "learning_rate": 4.660598911103288e-06, + "loss": 0.4561, + "step": 8234 + }, + { + "epoch": 0.69, + "learning_rate": 4.658307822229423e-06, + "loss": 0.4632, + "step": 8235 + }, + { + "epoch": 0.69, + "learning_rate": 4.656017125627214e-06, + "loss": 0.4754, + "step": 8236 + }, + { + "epoch": 0.69, + "learning_rate": 4.653726821464876e-06, + "loss": 0.483, + "step": 8237 + }, + { + "epoch": 0.69, + "learning_rate": 4.651436909910607e-06, + "loss": 0.4668, + "step": 8238 + }, + { + "epoch": 0.69, + "learning_rate": 4.649147391132562e-06, + "loss": 0.4958, + "step": 8239 + }, + { + "epoch": 0.69, + "learning_rate": 4.646858265298881e-06, + "loss": 0.4723, + "step": 8240 + }, + { + "epoch": 0.69, + "learning_rate": 4.644569532577662e-06, + "loss": 0.4746, + "step": 8241 + }, + { + "epoch": 0.69, + "learning_rate": 4.6422811931369825e-06, + "loss": 0.4718, + "step": 8242 + }, + { + "epoch": 0.69, + "learning_rate": 4.639993247144889e-06, + "loss": 0.4667, + "step": 8243 + }, + { + "epoch": 0.69, + "learning_rate": 4.637705694769396e-06, + "loss": 0.4615, + "step": 8244 + }, + { + "epoch": 0.69, + "learning_rate": 4.635418536178492e-06, + "loss": 0.4802, + "step": 8245 + }, + { + "epoch": 0.69, + "learning_rate": 4.633131771540136e-06, + "loss": 0.471, + "step": 8246 + }, + { + "epoch": 0.69, + "learning_rate": 4.630845401022264e-06, + "loss": 0.4659, + "step": 8247 + }, + { + "epoch": 0.69, + "learning_rate": 4.628559424792769e-06, + "loss": 0.48, + "step": 8248 + }, + { + "epoch": 0.69, + "learning_rate": 4.626273843019532e-06, + "loss": 0.4433, + "step": 8249 + }, + { + "epoch": 0.69, + "learning_rate": 4.623988655870394e-06, + "loss": 0.4805, + "step": 8250 + }, + { + "epoch": 0.69, + "learning_rate": 4.621703863513168e-06, + "loss": 0.4693, + "step": 8251 + }, + { + "epoch": 0.69, + "learning_rate": 4.61941946611564e-06, + "loss": 0.4697, + "step": 8252 + }, + { + "epoch": 0.69, + "learning_rate": 4.617135463845563e-06, + "loss": 0.4931, + "step": 8253 + }, + { + "epoch": 0.69, + "learning_rate": 4.614851856870673e-06, + "loss": 0.4724, + "step": 8254 + }, + { + "epoch": 0.69, + "learning_rate": 4.612568645358664e-06, + "loss": 0.4771, + "step": 8255 + }, + { + "epoch": 0.69, + "learning_rate": 4.6102858294772055e-06, + "loss": 0.4438, + "step": 8256 + }, + { + "epoch": 0.69, + "learning_rate": 4.608003409393939e-06, + "loss": 0.49, + "step": 8257 + }, + { + "epoch": 0.69, + "learning_rate": 4.60572138527647e-06, + "loss": 0.4572, + "step": 8258 + }, + { + "epoch": 0.69, + "learning_rate": 4.60343975729239e-06, + "loss": 0.4596, + "step": 8259 + }, + { + "epoch": 0.69, + "learning_rate": 4.601158525609245e-06, + "loss": 0.4777, + "step": 8260 + }, + { + "epoch": 0.69, + "learning_rate": 4.598877690394565e-06, + "loss": 0.4661, + "step": 8261 + }, + { + "epoch": 0.69, + "learning_rate": 4.596597251815844e-06, + "loss": 0.458, + "step": 8262 + }, + { + "epoch": 0.69, + "learning_rate": 4.5943172100405455e-06, + "loss": 0.4684, + "step": 8263 + }, + { + "epoch": 0.69, + "learning_rate": 4.592037565236108e-06, + "loss": 0.4587, + "step": 8264 + }, + { + "epoch": 0.69, + "learning_rate": 4.589758317569938e-06, + "loss": 0.4612, + "step": 8265 + }, + { + "epoch": 0.69, + "learning_rate": 4.5874794672094135e-06, + "loss": 0.475, + "step": 8266 + }, + { + "epoch": 0.69, + "learning_rate": 4.585201014321882e-06, + "loss": 0.4665, + "step": 8267 + }, + { + "epoch": 0.69, + "learning_rate": 4.582922959074668e-06, + "loss": 0.4585, + "step": 8268 + }, + { + "epoch": 0.69, + "learning_rate": 4.5806453016350584e-06, + "loss": 0.4705, + "step": 8269 + }, + { + "epoch": 0.69, + "learning_rate": 4.5783680421703205e-06, + "loss": 0.4901, + "step": 8270 + }, + { + "epoch": 0.69, + "learning_rate": 4.576091180847684e-06, + "loss": 0.4554, + "step": 8271 + }, + { + "epoch": 0.69, + "learning_rate": 4.57381471783435e-06, + "loss": 0.4782, + "step": 8272 + }, + { + "epoch": 0.69, + "learning_rate": 4.571538653297491e-06, + "loss": 0.4807, + "step": 8273 + }, + { + "epoch": 0.69, + "learning_rate": 4.5692629874042585e-06, + "loss": 0.4598, + "step": 8274 + }, + { + "epoch": 0.69, + "learning_rate": 4.566987720321764e-06, + "loss": 0.4618, + "step": 8275 + }, + { + "epoch": 0.69, + "learning_rate": 4.564712852217094e-06, + "loss": 0.47, + "step": 8276 + }, + { + "epoch": 0.69, + "learning_rate": 4.562438383257304e-06, + "loss": 0.4723, + "step": 8277 + }, + { + "epoch": 0.69, + "learning_rate": 4.5601643136094195e-06, + "loss": 0.4548, + "step": 8278 + }, + { + "epoch": 0.69, + "learning_rate": 4.557890643440445e-06, + "loss": 0.4667, + "step": 8279 + }, + { + "epoch": 0.69, + "learning_rate": 4.5556173729173434e-06, + "loss": 0.4726, + "step": 8280 + }, + { + "epoch": 0.69, + "learning_rate": 4.55334450220706e-06, + "loss": 0.4704, + "step": 8281 + }, + { + "epoch": 0.69, + "learning_rate": 4.551072031476504e-06, + "loss": 0.4842, + "step": 8282 + }, + { + "epoch": 0.69, + "learning_rate": 4.548799960892552e-06, + "loss": 0.4802, + "step": 8283 + }, + { + "epoch": 0.69, + "learning_rate": 4.546528290622058e-06, + "loss": 0.4843, + "step": 8284 + }, + { + "epoch": 0.69, + "learning_rate": 4.544257020831843e-06, + "loss": 0.4921, + "step": 8285 + }, + { + "epoch": 0.69, + "learning_rate": 4.541986151688702e-06, + "loss": 0.4769, + "step": 8286 + }, + { + "epoch": 0.69, + "learning_rate": 4.539715683359391e-06, + "loss": 0.45, + "step": 8287 + }, + { + "epoch": 0.69, + "learning_rate": 4.537445616010655e-06, + "loss": 0.4646, + "step": 8288 + }, + { + "epoch": 0.69, + "learning_rate": 4.535175949809188e-06, + "loss": 0.4756, + "step": 8289 + }, + { + "epoch": 0.69, + "learning_rate": 4.532906684921672e-06, + "loss": 0.4601, + "step": 8290 + }, + { + "epoch": 0.69, + "learning_rate": 4.53063782151475e-06, + "loss": 0.486, + "step": 8291 + }, + { + "epoch": 0.69, + "learning_rate": 4.5283693597550384e-06, + "loss": 0.4705, + "step": 8292 + }, + { + "epoch": 0.69, + "learning_rate": 4.526101299809122e-06, + "loss": 0.4619, + "step": 8293 + }, + { + "epoch": 0.69, + "learning_rate": 4.523833641843554e-06, + "loss": 0.4683, + "step": 8294 + }, + { + "epoch": 0.69, + "learning_rate": 4.521566386024871e-06, + "loss": 0.4627, + "step": 8295 + }, + { + "epoch": 0.69, + "learning_rate": 4.519299532519566e-06, + "loss": 0.483, + "step": 8296 + }, + { + "epoch": 0.69, + "learning_rate": 4.517033081494109e-06, + "loss": 0.4766, + "step": 8297 + }, + { + "epoch": 0.69, + "learning_rate": 4.514767033114935e-06, + "loss": 0.4708, + "step": 8298 + }, + { + "epoch": 0.69, + "learning_rate": 4.512501387548453e-06, + "loss": 0.4741, + "step": 8299 + }, + { + "epoch": 0.69, + "learning_rate": 4.510236144961047e-06, + "loss": 0.4742, + "step": 8300 + }, + { + "epoch": 0.69, + "learning_rate": 4.507971305519062e-06, + "loss": 0.4632, + "step": 8301 + }, + { + "epoch": 0.69, + "learning_rate": 4.505706869388825e-06, + "loss": 0.468, + "step": 8302 + }, + { + "epoch": 0.69, + "learning_rate": 4.503442836736624e-06, + "loss": 0.4569, + "step": 8303 + }, + { + "epoch": 0.69, + "learning_rate": 4.5011792077287175e-06, + "loss": 0.4734, + "step": 8304 + }, + { + "epoch": 0.69, + "learning_rate": 4.498915982531339e-06, + "loss": 0.4751, + "step": 8305 + }, + { + "epoch": 0.69, + "learning_rate": 4.49665316131069e-06, + "loss": 0.4773, + "step": 8306 + }, + { + "epoch": 0.7, + "learning_rate": 4.494390744232943e-06, + "loss": 0.4506, + "step": 8307 + }, + { + "epoch": 0.7, + "learning_rate": 4.492128731464237e-06, + "loss": 0.4594, + "step": 8308 + }, + { + "epoch": 0.7, + "learning_rate": 4.489867123170692e-06, + "loss": 0.4719, + "step": 8309 + }, + { + "epoch": 0.7, + "learning_rate": 4.487605919518382e-06, + "loss": 0.4808, + "step": 8310 + }, + { + "epoch": 0.7, + "learning_rate": 4.485345120673369e-06, + "loss": 0.4713, + "step": 8311 + }, + { + "epoch": 0.7, + "learning_rate": 4.4830847268016745e-06, + "loss": 0.4824, + "step": 8312 + }, + { + "epoch": 0.7, + "learning_rate": 4.480824738069291e-06, + "loss": 0.4813, + "step": 8313 + }, + { + "epoch": 0.7, + "learning_rate": 4.478565154642178e-06, + "loss": 0.477, + "step": 8314 + }, + { + "epoch": 0.7, + "learning_rate": 4.476305976686279e-06, + "loss": 0.4704, + "step": 8315 + }, + { + "epoch": 0.7, + "learning_rate": 4.474047204367494e-06, + "loss": 0.4748, + "step": 8316 + }, + { + "epoch": 0.7, + "learning_rate": 4.4717888378516986e-06, + "loss": 0.454, + "step": 8317 + }, + { + "epoch": 0.7, + "learning_rate": 4.469530877304737e-06, + "loss": 0.4577, + "step": 8318 + }, + { + "epoch": 0.7, + "learning_rate": 4.467273322892421e-06, + "loss": 0.4852, + "step": 8319 + }, + { + "epoch": 0.7, + "learning_rate": 4.465016174780544e-06, + "loss": 0.4551, + "step": 8320 + }, + { + "epoch": 0.7, + "learning_rate": 4.462759433134855e-06, + "loss": 0.4726, + "step": 8321 + }, + { + "epoch": 0.7, + "learning_rate": 4.4605030981210824e-06, + "loss": 0.5028, + "step": 8322 + }, + { + "epoch": 0.7, + "learning_rate": 4.4582471699049245e-06, + "loss": 0.4718, + "step": 8323 + }, + { + "epoch": 0.7, + "learning_rate": 4.455991648652044e-06, + "loss": 0.479, + "step": 8324 + }, + { + "epoch": 0.7, + "learning_rate": 4.453736534528077e-06, + "loss": 0.4514, + "step": 8325 + }, + { + "epoch": 0.7, + "learning_rate": 4.45148182769863e-06, + "loss": 0.467, + "step": 8326 + }, + { + "epoch": 0.7, + "learning_rate": 4.449227528329281e-06, + "loss": 0.489, + "step": 8327 + }, + { + "epoch": 0.7, + "learning_rate": 4.446973636585571e-06, + "loss": 0.4569, + "step": 8328 + }, + { + "epoch": 0.7, + "learning_rate": 4.444720152633023e-06, + "loss": 0.4732, + "step": 8329 + }, + { + "epoch": 0.7, + "learning_rate": 4.442467076637121e-06, + "loss": 0.4608, + "step": 8330 + }, + { + "epoch": 0.7, + "learning_rate": 4.440214408763318e-06, + "loss": 0.4619, + "step": 8331 + }, + { + "epoch": 0.7, + "learning_rate": 4.437962149177047e-06, + "loss": 0.469, + "step": 8332 + }, + { + "epoch": 0.7, + "learning_rate": 4.435710298043703e-06, + "loss": 0.4816, + "step": 8333 + }, + { + "epoch": 0.7, + "learning_rate": 4.43345885552865e-06, + "loss": 0.4489, + "step": 8334 + }, + { + "epoch": 0.7, + "learning_rate": 4.431207821797222e-06, + "loss": 0.4529, + "step": 8335 + }, + { + "epoch": 0.7, + "learning_rate": 4.428957197014732e-06, + "loss": 0.4827, + "step": 8336 + }, + { + "epoch": 0.7, + "learning_rate": 4.426706981346456e-06, + "loss": 0.4554, + "step": 8337 + }, + { + "epoch": 0.7, + "learning_rate": 4.424457174957637e-06, + "loss": 0.4698, + "step": 8338 + }, + { + "epoch": 0.7, + "learning_rate": 4.422207778013493e-06, + "loss": 0.4708, + "step": 8339 + }, + { + "epoch": 0.7, + "learning_rate": 4.419958790679205e-06, + "loss": 0.4747, + "step": 8340 + }, + { + "epoch": 0.7, + "learning_rate": 4.4177102131199405e-06, + "loss": 0.4694, + "step": 8341 + }, + { + "epoch": 0.7, + "learning_rate": 4.415462045500813e-06, + "loss": 0.4597, + "step": 8342 + }, + { + "epoch": 0.7, + "learning_rate": 4.41321428798693e-06, + "loss": 0.4661, + "step": 8343 + }, + { + "epoch": 0.7, + "learning_rate": 4.410966940743353e-06, + "loss": 0.4799, + "step": 8344 + }, + { + "epoch": 0.7, + "learning_rate": 4.408720003935116e-06, + "loss": 0.4642, + "step": 8345 + }, + { + "epoch": 0.7, + "learning_rate": 4.406473477727228e-06, + "loss": 0.4708, + "step": 8346 + }, + { + "epoch": 0.7, + "learning_rate": 4.404227362284661e-06, + "loss": 0.4911, + "step": 8347 + }, + { + "epoch": 0.7, + "learning_rate": 4.401981657772359e-06, + "loss": 0.4707, + "step": 8348 + }, + { + "epoch": 0.7, + "learning_rate": 4.399736364355243e-06, + "loss": 0.4633, + "step": 8349 + }, + { + "epoch": 0.7, + "learning_rate": 4.397491482198195e-06, + "loss": 0.4862, + "step": 8350 + }, + { + "epoch": 0.7, + "learning_rate": 4.395247011466067e-06, + "loss": 0.461, + "step": 8351 + }, + { + "epoch": 0.7, + "learning_rate": 4.393002952323691e-06, + "loss": 0.4619, + "step": 8352 + }, + { + "epoch": 0.7, + "learning_rate": 4.3907593049358555e-06, + "loss": 0.4857, + "step": 8353 + }, + { + "epoch": 0.7, + "learning_rate": 4.388516069467327e-06, + "loss": 0.482, + "step": 8354 + }, + { + "epoch": 0.7, + "learning_rate": 4.386273246082834e-06, + "loss": 0.4656, + "step": 8355 + }, + { + "epoch": 0.7, + "learning_rate": 4.384030834947088e-06, + "loss": 0.4777, + "step": 8356 + }, + { + "epoch": 0.7, + "learning_rate": 4.381788836224759e-06, + "loss": 0.4786, + "step": 8357 + }, + { + "epoch": 0.7, + "learning_rate": 4.379547250080491e-06, + "loss": 0.4525, + "step": 8358 + }, + { + "epoch": 0.7, + "learning_rate": 4.377306076678895e-06, + "loss": 0.4711, + "step": 8359 + }, + { + "epoch": 0.7, + "learning_rate": 4.375065316184556e-06, + "loss": 0.4986, + "step": 8360 + }, + { + "epoch": 0.7, + "learning_rate": 4.372824968762019e-06, + "loss": 0.4564, + "step": 8361 + }, + { + "epoch": 0.7, + "learning_rate": 4.37058503457581e-06, + "loss": 0.4666, + "step": 8362 + }, + { + "epoch": 0.7, + "learning_rate": 4.368345513790427e-06, + "loss": 0.4745, + "step": 8363 + }, + { + "epoch": 0.7, + "learning_rate": 4.366106406570325e-06, + "loss": 0.5115, + "step": 8364 + }, + { + "epoch": 0.7, + "learning_rate": 4.363867713079935e-06, + "loss": 0.4606, + "step": 8365 + }, + { + "epoch": 0.7, + "learning_rate": 4.361629433483659e-06, + "loss": 0.4698, + "step": 8366 + }, + { + "epoch": 0.7, + "learning_rate": 4.3593915679458645e-06, + "loss": 0.4697, + "step": 8367 + }, + { + "epoch": 0.7, + "learning_rate": 4.3571541166308926e-06, + "loss": 0.4661, + "step": 8368 + }, + { + "epoch": 0.7, + "learning_rate": 4.354917079703049e-06, + "loss": 0.4622, + "step": 8369 + }, + { + "epoch": 0.7, + "learning_rate": 4.352680457326617e-06, + "loss": 0.4748, + "step": 8370 + }, + { + "epoch": 0.7, + "learning_rate": 4.350444249665845e-06, + "loss": 0.4748, + "step": 8371 + }, + { + "epoch": 0.7, + "learning_rate": 4.348208456884945e-06, + "loss": 0.4493, + "step": 8372 + }, + { + "epoch": 0.7, + "learning_rate": 4.345973079148111e-06, + "loss": 0.486, + "step": 8373 + }, + { + "epoch": 0.7, + "learning_rate": 4.343738116619499e-06, + "loss": 0.4661, + "step": 8374 + }, + { + "epoch": 0.7, + "learning_rate": 4.3415035694632326e-06, + "loss": 0.4423, + "step": 8375 + }, + { + "epoch": 0.7, + "learning_rate": 4.339269437843405e-06, + "loss": 0.4572, + "step": 8376 + }, + { + "epoch": 0.7, + "learning_rate": 4.337035721924089e-06, + "loss": 0.4763, + "step": 8377 + }, + { + "epoch": 0.7, + "learning_rate": 4.334802421869316e-06, + "loss": 0.4874, + "step": 8378 + }, + { + "epoch": 0.7, + "learning_rate": 4.332569537843089e-06, + "loss": 0.4534, + "step": 8379 + }, + { + "epoch": 0.7, + "learning_rate": 4.330337070009382e-06, + "loss": 0.4533, + "step": 8380 + }, + { + "epoch": 0.7, + "learning_rate": 4.328105018532136e-06, + "loss": 0.461, + "step": 8381 + }, + { + "epoch": 0.7, + "learning_rate": 4.32587338357527e-06, + "loss": 0.4669, + "step": 8382 + }, + { + "epoch": 0.7, + "learning_rate": 4.323642165302658e-06, + "loss": 0.4619, + "step": 8383 + }, + { + "epoch": 0.7, + "learning_rate": 4.321411363878159e-06, + "loss": 0.4544, + "step": 8384 + }, + { + "epoch": 0.7, + "learning_rate": 4.319180979465592e-06, + "loss": 0.4866, + "step": 8385 + }, + { + "epoch": 0.7, + "learning_rate": 4.316951012228744e-06, + "loss": 0.4647, + "step": 8386 + }, + { + "epoch": 0.7, + "learning_rate": 4.314721462331376e-06, + "loss": 0.4605, + "step": 8387 + }, + { + "epoch": 0.7, + "learning_rate": 4.312492329937218e-06, + "loss": 0.4656, + "step": 8388 + }, + { + "epoch": 0.7, + "learning_rate": 4.310263615209963e-06, + "loss": 0.4996, + "step": 8389 + }, + { + "epoch": 0.7, + "learning_rate": 4.308035318313286e-06, + "loss": 0.4711, + "step": 8390 + }, + { + "epoch": 0.7, + "learning_rate": 4.305807439410822e-06, + "loss": 0.4672, + "step": 8391 + }, + { + "epoch": 0.7, + "learning_rate": 4.30357997866617e-06, + "loss": 0.4885, + "step": 8392 + }, + { + "epoch": 0.7, + "learning_rate": 4.301352936242916e-06, + "loss": 0.4748, + "step": 8393 + }, + { + "epoch": 0.7, + "learning_rate": 4.2991263123046005e-06, + "loss": 0.4615, + "step": 8394 + }, + { + "epoch": 0.7, + "learning_rate": 4.296900107014735e-06, + "loss": 0.4693, + "step": 8395 + }, + { + "epoch": 0.7, + "learning_rate": 4.294674320536803e-06, + "loss": 0.4776, + "step": 8396 + }, + { + "epoch": 0.7, + "learning_rate": 4.292448953034261e-06, + "loss": 0.4694, + "step": 8397 + }, + { + "epoch": 0.7, + "learning_rate": 4.290224004670529e-06, + "loss": 0.4633, + "step": 8398 + }, + { + "epoch": 0.7, + "learning_rate": 4.287999475608997e-06, + "loss": 0.4731, + "step": 8399 + }, + { + "epoch": 0.7, + "learning_rate": 4.285775366013026e-06, + "loss": 0.4514, + "step": 8400 + }, + { + "epoch": 0.7, + "learning_rate": 4.283551676045945e-06, + "loss": 0.4551, + "step": 8401 + }, + { + "epoch": 0.7, + "learning_rate": 4.281328405871048e-06, + "loss": 0.4775, + "step": 8402 + }, + { + "epoch": 0.7, + "learning_rate": 4.279105555651608e-06, + "loss": 0.4647, + "step": 8403 + }, + { + "epoch": 0.7, + "learning_rate": 4.276883125550864e-06, + "loss": 0.47, + "step": 8404 + }, + { + "epoch": 0.7, + "learning_rate": 4.27466111573202e-06, + "loss": 0.4737, + "step": 8405 + }, + { + "epoch": 0.7, + "learning_rate": 4.272439526358249e-06, + "loss": 0.4676, + "step": 8406 + }, + { + "epoch": 0.7, + "learning_rate": 4.270218357592696e-06, + "loss": 0.459, + "step": 8407 + }, + { + "epoch": 0.7, + "learning_rate": 4.267997609598477e-06, + "loss": 0.4788, + "step": 8408 + }, + { + "epoch": 0.7, + "learning_rate": 4.26577728253867e-06, + "loss": 0.4554, + "step": 8409 + }, + { + "epoch": 0.7, + "learning_rate": 4.263557376576326e-06, + "loss": 0.4793, + "step": 8410 + }, + { + "epoch": 0.7, + "learning_rate": 4.261337891874473e-06, + "loss": 0.4776, + "step": 8411 + }, + { + "epoch": 0.7, + "learning_rate": 4.259118828596096e-06, + "loss": 0.4613, + "step": 8412 + }, + { + "epoch": 0.7, + "learning_rate": 4.25690018690415e-06, + "loss": 0.4708, + "step": 8413 + }, + { + "epoch": 0.7, + "learning_rate": 4.254681966961571e-06, + "loss": 0.4675, + "step": 8414 + }, + { + "epoch": 0.7, + "learning_rate": 4.2524641689312526e-06, + "loss": 0.4669, + "step": 8415 + }, + { + "epoch": 0.7, + "learning_rate": 4.250246792976058e-06, + "loss": 0.4417, + "step": 8416 + }, + { + "epoch": 0.7, + "learning_rate": 4.248029839258821e-06, + "loss": 0.4719, + "step": 8417 + }, + { + "epoch": 0.7, + "learning_rate": 4.245813307942354e-06, + "loss": 0.4622, + "step": 8418 + }, + { + "epoch": 0.7, + "learning_rate": 4.243597199189422e-06, + "loss": 0.4852, + "step": 8419 + }, + { + "epoch": 0.7, + "learning_rate": 4.241381513162769e-06, + "loss": 0.4809, + "step": 8420 + }, + { + "epoch": 0.7, + "learning_rate": 4.239166250025106e-06, + "loss": 0.4711, + "step": 8421 + }, + { + "epoch": 0.7, + "learning_rate": 4.236951409939109e-06, + "loss": 0.4572, + "step": 8422 + }, + { + "epoch": 0.7, + "learning_rate": 4.234736993067434e-06, + "loss": 0.4833, + "step": 8423 + }, + { + "epoch": 0.7, + "learning_rate": 4.2325229995726915e-06, + "loss": 0.4804, + "step": 8424 + }, + { + "epoch": 0.7, + "learning_rate": 4.230309429617474e-06, + "loss": 0.456, + "step": 8425 + }, + { + "epoch": 0.7, + "learning_rate": 4.228096283364335e-06, + "loss": 0.4626, + "step": 8426 + }, + { + "epoch": 0.71, + "learning_rate": 4.2258835609757965e-06, + "loss": 0.4777, + "step": 8427 + }, + { + "epoch": 0.71, + "learning_rate": 4.223671262614354e-06, + "loss": 0.4482, + "step": 8428 + }, + { + "epoch": 0.71, + "learning_rate": 4.221459388442467e-06, + "loss": 0.4631, + "step": 8429 + }, + { + "epoch": 0.71, + "learning_rate": 4.219247938622566e-06, + "loss": 0.451, + "step": 8430 + }, + { + "epoch": 0.71, + "learning_rate": 4.217036913317054e-06, + "loss": 0.4781, + "step": 8431 + }, + { + "epoch": 0.71, + "learning_rate": 4.214826312688299e-06, + "loss": 0.4649, + "step": 8432 + }, + { + "epoch": 0.71, + "learning_rate": 4.212616136898634e-06, + "loss": 0.4937, + "step": 8433 + }, + { + "epoch": 0.71, + "learning_rate": 4.210406386110371e-06, + "loss": 0.4511, + "step": 8434 + }, + { + "epoch": 0.71, + "learning_rate": 4.208197060485783e-06, + "loss": 0.4606, + "step": 8435 + }, + { + "epoch": 0.71, + "learning_rate": 4.205988160187113e-06, + "loss": 0.4546, + "step": 8436 + }, + { + "epoch": 0.71, + "learning_rate": 4.20377968537657e-06, + "loss": 0.4751, + "step": 8437 + }, + { + "epoch": 0.71, + "learning_rate": 4.201571636216343e-06, + "loss": 0.4677, + "step": 8438 + }, + { + "epoch": 0.71, + "learning_rate": 4.199364012868575e-06, + "loss": 0.4771, + "step": 8439 + }, + { + "epoch": 0.71, + "learning_rate": 4.197156815495389e-06, + "loss": 0.4534, + "step": 8440 + }, + { + "epoch": 0.71, + "learning_rate": 4.194950044258871e-06, + "loss": 0.4552, + "step": 8441 + }, + { + "epoch": 0.71, + "learning_rate": 4.192743699321075e-06, + "loss": 0.4798, + "step": 8442 + }, + { + "epoch": 0.71, + "learning_rate": 4.190537780844026e-06, + "loss": 0.4611, + "step": 8443 + }, + { + "epoch": 0.71, + "learning_rate": 4.188332288989721e-06, + "loss": 0.4666, + "step": 8444 + }, + { + "epoch": 0.71, + "learning_rate": 4.186127223920118e-06, + "loss": 0.4572, + "step": 8445 + }, + { + "epoch": 0.71, + "learning_rate": 4.183922585797152e-06, + "loss": 0.4646, + "step": 8446 + }, + { + "epoch": 0.71, + "learning_rate": 4.181718374782722e-06, + "loss": 0.4711, + "step": 8447 + }, + { + "epoch": 0.71, + "learning_rate": 4.179514591038692e-06, + "loss": 0.4616, + "step": 8448 + }, + { + "epoch": 0.71, + "learning_rate": 4.177311234726904e-06, + "loss": 0.473, + "step": 8449 + }, + { + "epoch": 0.71, + "learning_rate": 4.175108306009159e-06, + "loss": 0.4671, + "step": 8450 + }, + { + "epoch": 0.71, + "learning_rate": 4.172905805047229e-06, + "loss": 0.4892, + "step": 8451 + }, + { + "epoch": 0.71, + "learning_rate": 4.170703732002864e-06, + "loss": 0.4654, + "step": 8452 + }, + { + "epoch": 0.71, + "learning_rate": 4.168502087037771e-06, + "loss": 0.4498, + "step": 8453 + }, + { + "epoch": 0.71, + "learning_rate": 4.166300870313625e-06, + "loss": 0.493, + "step": 8454 + }, + { + "epoch": 0.71, + "learning_rate": 4.164100081992084e-06, + "loss": 0.4726, + "step": 8455 + }, + { + "epoch": 0.71, + "learning_rate": 4.161899722234759e-06, + "loss": 0.4567, + "step": 8456 + }, + { + "epoch": 0.71, + "learning_rate": 4.159699791203237e-06, + "loss": 0.4695, + "step": 8457 + }, + { + "epoch": 0.71, + "learning_rate": 4.157500289059065e-06, + "loss": 0.4722, + "step": 8458 + }, + { + "epoch": 0.71, + "learning_rate": 4.155301215963776e-06, + "loss": 0.4779, + "step": 8459 + }, + { + "epoch": 0.71, + "learning_rate": 4.153102572078855e-06, + "loss": 0.4611, + "step": 8460 + }, + { + "epoch": 0.71, + "learning_rate": 4.150904357565763e-06, + "loss": 0.4846, + "step": 8461 + }, + { + "epoch": 0.71, + "learning_rate": 4.148706572585927e-06, + "loss": 0.4619, + "step": 8462 + }, + { + "epoch": 0.71, + "learning_rate": 4.146509217300738e-06, + "loss": 0.4694, + "step": 8463 + }, + { + "epoch": 0.71, + "learning_rate": 4.14431229187157e-06, + "loss": 0.4676, + "step": 8464 + }, + { + "epoch": 0.71, + "learning_rate": 4.142115796459748e-06, + "loss": 0.4772, + "step": 8465 + }, + { + "epoch": 0.71, + "learning_rate": 4.13991973122658e-06, + "loss": 0.4591, + "step": 8466 + }, + { + "epoch": 0.71, + "learning_rate": 4.137724096333334e-06, + "loss": 0.4703, + "step": 8467 + }, + { + "epoch": 0.71, + "learning_rate": 4.135528891941246e-06, + "loss": 0.4667, + "step": 8468 + }, + { + "epoch": 0.71, + "learning_rate": 4.133334118211526e-06, + "loss": 0.4814, + "step": 8469 + }, + { + "epoch": 0.71, + "learning_rate": 4.131139775305346e-06, + "loss": 0.463, + "step": 8470 + }, + { + "epoch": 0.71, + "learning_rate": 4.128945863383846e-06, + "loss": 0.4672, + "step": 8471 + }, + { + "epoch": 0.71, + "learning_rate": 4.126752382608147e-06, + "loss": 0.4525, + "step": 8472 + }, + { + "epoch": 0.71, + "learning_rate": 4.124559333139324e-06, + "loss": 0.4729, + "step": 8473 + }, + { + "epoch": 0.71, + "learning_rate": 4.122366715138426e-06, + "loss": 0.4727, + "step": 8474 + }, + { + "epoch": 0.71, + "learning_rate": 4.1201745287664664e-06, + "loss": 0.4635, + "step": 8475 + }, + { + "epoch": 0.71, + "learning_rate": 4.117982774184436e-06, + "loss": 0.4769, + "step": 8476 + }, + { + "epoch": 0.71, + "learning_rate": 4.115791451553286e-06, + "loss": 0.4583, + "step": 8477 + }, + { + "epoch": 0.71, + "learning_rate": 4.1136005610339335e-06, + "loss": 0.476, + "step": 8478 + }, + { + "epoch": 0.71, + "learning_rate": 4.111410102787276e-06, + "loss": 0.4648, + "step": 8479 + }, + { + "epoch": 0.71, + "learning_rate": 4.109220076974168e-06, + "loss": 0.4614, + "step": 8480 + }, + { + "epoch": 0.71, + "learning_rate": 4.107030483755436e-06, + "loss": 0.482, + "step": 8481 + }, + { + "epoch": 0.71, + "learning_rate": 4.104841323291876e-06, + "loss": 0.4816, + "step": 8482 + }, + { + "epoch": 0.71, + "learning_rate": 4.102652595744248e-06, + "loss": 0.4644, + "step": 8483 + }, + { + "epoch": 0.71, + "learning_rate": 4.100464301273282e-06, + "loss": 0.4676, + "step": 8484 + }, + { + "epoch": 0.71, + "learning_rate": 4.098276440039681e-06, + "loss": 0.4865, + "step": 8485 + }, + { + "epoch": 0.71, + "learning_rate": 4.0960890122041095e-06, + "loss": 0.472, + "step": 8486 + }, + { + "epoch": 0.71, + "learning_rate": 4.093902017927208e-06, + "loss": 0.4773, + "step": 8487 + }, + { + "epoch": 0.71, + "learning_rate": 4.091715457369577e-06, + "loss": 0.4894, + "step": 8488 + }, + { + "epoch": 0.71, + "learning_rate": 4.089529330691789e-06, + "loss": 0.4876, + "step": 8489 + }, + { + "epoch": 0.71, + "learning_rate": 4.087343638054382e-06, + "loss": 0.4657, + "step": 8490 + }, + { + "epoch": 0.71, + "learning_rate": 4.085158379617866e-06, + "loss": 0.4594, + "step": 8491 + }, + { + "epoch": 0.71, + "learning_rate": 4.082973555542713e-06, + "loss": 0.4669, + "step": 8492 + }, + { + "epoch": 0.71, + "learning_rate": 4.080789165989376e-06, + "loss": 0.484, + "step": 8493 + }, + { + "epoch": 0.71, + "learning_rate": 4.0786052111182625e-06, + "loss": 0.4446, + "step": 8494 + }, + { + "epoch": 0.71, + "learning_rate": 4.0764216910897496e-06, + "loss": 0.4834, + "step": 8495 + }, + { + "epoch": 0.71, + "learning_rate": 4.074238606064194e-06, + "loss": 0.4814, + "step": 8496 + }, + { + "epoch": 0.71, + "learning_rate": 4.072055956201907e-06, + "loss": 0.4433, + "step": 8497 + }, + { + "epoch": 0.71, + "learning_rate": 4.069873741663171e-06, + "loss": 0.466, + "step": 8498 + }, + { + "epoch": 0.71, + "learning_rate": 4.067691962608245e-06, + "loss": 0.4694, + "step": 8499 + }, + { + "epoch": 0.71, + "learning_rate": 4.0655106191973485e-06, + "loss": 0.4718, + "step": 8500 + }, + { + "epoch": 0.71, + "learning_rate": 4.063329711590668e-06, + "loss": 0.4776, + "step": 8501 + }, + { + "epoch": 0.71, + "learning_rate": 4.061149239948361e-06, + "loss": 0.4952, + "step": 8502 + }, + { + "epoch": 0.71, + "learning_rate": 4.058969204430553e-06, + "loss": 0.4696, + "step": 8503 + }, + { + "epoch": 0.71, + "learning_rate": 4.056789605197335e-06, + "loss": 0.4936, + "step": 8504 + }, + { + "epoch": 0.71, + "learning_rate": 4.054610442408765e-06, + "loss": 0.4689, + "step": 8505 + }, + { + "epoch": 0.71, + "learning_rate": 4.052431716224876e-06, + "loss": 0.4777, + "step": 8506 + }, + { + "epoch": 0.71, + "learning_rate": 4.050253426805668e-06, + "loss": 0.4714, + "step": 8507 + }, + { + "epoch": 0.71, + "learning_rate": 4.048075574311101e-06, + "loss": 0.4638, + "step": 8508 + }, + { + "epoch": 0.71, + "learning_rate": 4.045898158901108e-06, + "loss": 0.4809, + "step": 8509 + }, + { + "epoch": 0.71, + "learning_rate": 4.043721180735589e-06, + "loss": 0.4672, + "step": 8510 + }, + { + "epoch": 0.71, + "learning_rate": 4.041544639974413e-06, + "loss": 0.4507, + "step": 8511 + }, + { + "epoch": 0.71, + "learning_rate": 4.03936853677741e-06, + "loss": 0.4801, + "step": 8512 + }, + { + "epoch": 0.71, + "learning_rate": 4.037192871304396e-06, + "loss": 0.4604, + "step": 8513 + }, + { + "epoch": 0.71, + "learning_rate": 4.035017643715135e-06, + "loss": 0.462, + "step": 8514 + }, + { + "epoch": 0.71, + "learning_rate": 4.032842854169368e-06, + "loss": 0.465, + "step": 8515 + }, + { + "epoch": 0.71, + "learning_rate": 4.030668502826799e-06, + "loss": 0.4692, + "step": 8516 + }, + { + "epoch": 0.71, + "learning_rate": 4.028494589847109e-06, + "loss": 0.4676, + "step": 8517 + }, + { + "epoch": 0.71, + "learning_rate": 4.026321115389942e-06, + "loss": 0.475, + "step": 8518 + }, + { + "epoch": 0.71, + "learning_rate": 4.0241480796149e-06, + "loss": 0.4485, + "step": 8519 + }, + { + "epoch": 0.71, + "learning_rate": 4.021975482681571e-06, + "loss": 0.4837, + "step": 8520 + }, + { + "epoch": 0.71, + "learning_rate": 4.0198033247494995e-06, + "loss": 0.4756, + "step": 8521 + }, + { + "epoch": 0.71, + "learning_rate": 4.017631605978198e-06, + "loss": 0.4693, + "step": 8522 + }, + { + "epoch": 0.71, + "learning_rate": 4.015460326527149e-06, + "loss": 0.4934, + "step": 8523 + }, + { + "epoch": 0.71, + "learning_rate": 4.013289486555801e-06, + "loss": 0.4677, + "step": 8524 + }, + { + "epoch": 0.71, + "learning_rate": 4.01111908622357e-06, + "loss": 0.4588, + "step": 8525 + }, + { + "epoch": 0.71, + "learning_rate": 4.008949125689846e-06, + "loss": 0.4807, + "step": 8526 + }, + { + "epoch": 0.71, + "learning_rate": 4.0067796051139775e-06, + "loss": 0.4802, + "step": 8527 + }, + { + "epoch": 0.71, + "learning_rate": 4.0046105246552895e-06, + "loss": 0.4561, + "step": 8528 + }, + { + "epoch": 0.71, + "learning_rate": 4.002441884473069e-06, + "loss": 0.4578, + "step": 8529 + }, + { + "epoch": 0.71, + "learning_rate": 4.000273684726569e-06, + "loss": 0.469, + "step": 8530 + }, + { + "epoch": 0.71, + "learning_rate": 3.998105925575017e-06, + "loss": 0.4794, + "step": 8531 + }, + { + "epoch": 0.71, + "learning_rate": 3.995938607177599e-06, + "loss": 0.4589, + "step": 8532 + }, + { + "epoch": 0.71, + "learning_rate": 3.993771729693476e-06, + "loss": 0.4691, + "step": 8533 + }, + { + "epoch": 0.71, + "learning_rate": 3.991605293281779e-06, + "loss": 0.4729, + "step": 8534 + }, + { + "epoch": 0.71, + "learning_rate": 3.989439298101597e-06, + "loss": 0.477, + "step": 8535 + }, + { + "epoch": 0.71, + "learning_rate": 3.9872737443119914e-06, + "loss": 0.4653, + "step": 8536 + }, + { + "epoch": 0.71, + "learning_rate": 3.985108632071995e-06, + "loss": 0.4654, + "step": 8537 + }, + { + "epoch": 0.71, + "learning_rate": 3.982943961540604e-06, + "loss": 0.4591, + "step": 8538 + }, + { + "epoch": 0.71, + "learning_rate": 3.980779732876777e-06, + "loss": 0.4844, + "step": 8539 + }, + { + "epoch": 0.71, + "learning_rate": 3.978615946239456e-06, + "loss": 0.4753, + "step": 8540 + }, + { + "epoch": 0.71, + "learning_rate": 3.9764526017875326e-06, + "loss": 0.4698, + "step": 8541 + }, + { + "epoch": 0.71, + "learning_rate": 3.974289699679879e-06, + "loss": 0.4496, + "step": 8542 + }, + { + "epoch": 0.71, + "learning_rate": 3.972127240075325e-06, + "loss": 0.4753, + "step": 8543 + }, + { + "epoch": 0.71, + "learning_rate": 3.969965223132675e-06, + "loss": 0.4723, + "step": 8544 + }, + { + "epoch": 0.71, + "learning_rate": 3.967803649010698e-06, + "loss": 0.4615, + "step": 8545 + }, + { + "epoch": 0.71, + "learning_rate": 3.965642517868129e-06, + "loss": 0.4637, + "step": 8546 + }, + { + "epoch": 0.72, + "learning_rate": 3.963481829863673e-06, + "loss": 0.4717, + "step": 8547 + }, + { + "epoch": 0.72, + "learning_rate": 3.9613215851560094e-06, + "loss": 0.4675, + "step": 8548 + }, + { + "epoch": 0.72, + "learning_rate": 3.95916178390377e-06, + "loss": 0.4737, + "step": 8549 + }, + { + "epoch": 0.72, + "learning_rate": 3.957002426265564e-06, + "loss": 0.4573, + "step": 8550 + }, + { + "epoch": 0.72, + "learning_rate": 3.954843512399965e-06, + "loss": 0.477, + "step": 8551 + }, + { + "epoch": 0.72, + "learning_rate": 3.952685042465515e-06, + "loss": 0.4955, + "step": 8552 + }, + { + "epoch": 0.72, + "learning_rate": 3.950527016620719e-06, + "loss": 0.4608, + "step": 8553 + }, + { + "epoch": 0.72, + "learning_rate": 3.948369435024061e-06, + "loss": 0.4601, + "step": 8554 + }, + { + "epoch": 0.72, + "learning_rate": 3.9462122978339815e-06, + "loss": 0.4654, + "step": 8555 + }, + { + "epoch": 0.72, + "learning_rate": 3.944055605208891e-06, + "loss": 0.4643, + "step": 8556 + }, + { + "epoch": 0.72, + "learning_rate": 3.941899357307164e-06, + "loss": 0.4667, + "step": 8557 + }, + { + "epoch": 0.72, + "learning_rate": 3.939743554287154e-06, + "loss": 0.4756, + "step": 8558 + }, + { + "epoch": 0.72, + "learning_rate": 3.937588196307172e-06, + "loss": 0.4816, + "step": 8559 + }, + { + "epoch": 0.72, + "learning_rate": 3.9354332835254935e-06, + "loss": 0.4623, + "step": 8560 + }, + { + "epoch": 0.72, + "learning_rate": 3.933278816100373e-06, + "loss": 0.468, + "step": 8561 + }, + { + "epoch": 0.72, + "learning_rate": 3.9311247941900245e-06, + "loss": 0.4859, + "step": 8562 + }, + { + "epoch": 0.72, + "learning_rate": 3.9289712179526275e-06, + "loss": 0.4537, + "step": 8563 + }, + { + "epoch": 0.72, + "learning_rate": 3.926818087546333e-06, + "loss": 0.4717, + "step": 8564 + }, + { + "epoch": 0.72, + "learning_rate": 3.924665403129259e-06, + "loss": 0.4674, + "step": 8565 + }, + { + "epoch": 0.72, + "learning_rate": 3.9225131648594835e-06, + "loss": 0.4457, + "step": 8566 + }, + { + "epoch": 0.72, + "learning_rate": 3.920361372895067e-06, + "loss": 0.4414, + "step": 8567 + }, + { + "epoch": 0.72, + "learning_rate": 3.918210027394021e-06, + "loss": 0.4717, + "step": 8568 + }, + { + "epoch": 0.72, + "learning_rate": 3.9160591285143375e-06, + "loss": 0.462, + "step": 8569 + }, + { + "epoch": 0.72, + "learning_rate": 3.9139086764139675e-06, + "loss": 0.4642, + "step": 8570 + }, + { + "epoch": 0.72, + "learning_rate": 3.911758671250829e-06, + "loss": 0.4636, + "step": 8571 + }, + { + "epoch": 0.72, + "learning_rate": 3.909609113182812e-06, + "loss": 0.462, + "step": 8572 + }, + { + "epoch": 0.72, + "learning_rate": 3.907460002367766e-06, + "loss": 0.4626, + "step": 8573 + }, + { + "epoch": 0.72, + "learning_rate": 3.90531133896352e-06, + "loss": 0.4717, + "step": 8574 + }, + { + "epoch": 0.72, + "learning_rate": 3.90316312312786e-06, + "loss": 0.4724, + "step": 8575 + }, + { + "epoch": 0.72, + "learning_rate": 3.901015355018541e-06, + "loss": 0.4667, + "step": 8576 + }, + { + "epoch": 0.72, + "learning_rate": 3.8988680347932836e-06, + "loss": 0.4813, + "step": 8577 + }, + { + "epoch": 0.72, + "learning_rate": 3.896721162609785e-06, + "loss": 0.4612, + "step": 8578 + }, + { + "epoch": 0.72, + "learning_rate": 3.894574738625699e-06, + "loss": 0.4741, + "step": 8579 + }, + { + "epoch": 0.72, + "learning_rate": 3.892428762998644e-06, + "loss": 0.4814, + "step": 8580 + }, + { + "epoch": 0.72, + "learning_rate": 3.890283235886223e-06, + "loss": 0.4944, + "step": 8581 + }, + { + "epoch": 0.72, + "learning_rate": 3.888138157445989e-06, + "loss": 0.433, + "step": 8582 + }, + { + "epoch": 0.72, + "learning_rate": 3.885993527835466e-06, + "loss": 0.4921, + "step": 8583 + }, + { + "epoch": 0.72, + "learning_rate": 3.883849347212151e-06, + "loss": 0.4568, + "step": 8584 + }, + { + "epoch": 0.72, + "learning_rate": 3.8817056157334985e-06, + "loss": 0.4738, + "step": 8585 + }, + { + "epoch": 0.72, + "learning_rate": 3.879562333556939e-06, + "loss": 0.4914, + "step": 8586 + }, + { + "epoch": 0.72, + "learning_rate": 3.877419500839861e-06, + "loss": 0.4677, + "step": 8587 + }, + { + "epoch": 0.72, + "learning_rate": 3.875277117739632e-06, + "loss": 0.4613, + "step": 8588 + }, + { + "epoch": 0.72, + "learning_rate": 3.873135184413573e-06, + "loss": 0.4628, + "step": 8589 + }, + { + "epoch": 0.72, + "learning_rate": 3.870993701018988e-06, + "loss": 0.4649, + "step": 8590 + }, + { + "epoch": 0.72, + "learning_rate": 3.868852667713131e-06, + "loss": 0.4456, + "step": 8591 + }, + { + "epoch": 0.72, + "learning_rate": 3.8667120846532335e-06, + "loss": 0.4777, + "step": 8592 + }, + { + "epoch": 0.72, + "learning_rate": 3.864571951996491e-06, + "loss": 0.476, + "step": 8593 + }, + { + "epoch": 0.72, + "learning_rate": 3.862432269900062e-06, + "loss": 0.4743, + "step": 8594 + }, + { + "epoch": 0.72, + "learning_rate": 3.860293038521082e-06, + "loss": 0.4484, + "step": 8595 + }, + { + "epoch": 0.72, + "learning_rate": 3.858154258016643e-06, + "loss": 0.4882, + "step": 8596 + }, + { + "epoch": 0.72, + "learning_rate": 3.856015928543811e-06, + "loss": 0.4718, + "step": 8597 + }, + { + "epoch": 0.72, + "learning_rate": 3.85387805025961e-06, + "loss": 0.4623, + "step": 8598 + }, + { + "epoch": 0.72, + "learning_rate": 3.8517406233210445e-06, + "loss": 0.4816, + "step": 8599 + }, + { + "epoch": 0.72, + "learning_rate": 3.849603647885076e-06, + "loss": 0.47, + "step": 8600 + }, + { + "epoch": 0.72, + "learning_rate": 3.84746712410863e-06, + "loss": 0.4653, + "step": 8601 + }, + { + "epoch": 0.72, + "learning_rate": 3.845331052148612e-06, + "loss": 0.4681, + "step": 8602 + }, + { + "epoch": 0.72, + "learning_rate": 3.843195432161883e-06, + "loss": 0.4579, + "step": 8603 + }, + { + "epoch": 0.72, + "learning_rate": 3.841060264305272e-06, + "loss": 0.4616, + "step": 8604 + }, + { + "epoch": 0.72, + "learning_rate": 3.838925548735579e-06, + "loss": 0.4761, + "step": 8605 + }, + { + "epoch": 0.72, + "learning_rate": 3.836791285609568e-06, + "loss": 0.4677, + "step": 8606 + }, + { + "epoch": 0.72, + "learning_rate": 3.834657475083967e-06, + "loss": 0.4562, + "step": 8607 + }, + { + "epoch": 0.72, + "learning_rate": 3.83252411731548e-06, + "loss": 0.492, + "step": 8608 + }, + { + "epoch": 0.72, + "learning_rate": 3.830391212460767e-06, + "loss": 0.4816, + "step": 8609 + }, + { + "epoch": 0.72, + "learning_rate": 3.828258760676464e-06, + "loss": 0.4645, + "step": 8610 + }, + { + "epoch": 0.72, + "learning_rate": 3.826126762119169e-06, + "loss": 0.4629, + "step": 8611 + }, + { + "epoch": 0.72, + "learning_rate": 3.823995216945445e-06, + "loss": 0.4651, + "step": 8612 + }, + { + "epoch": 0.72, + "learning_rate": 3.821864125311824e-06, + "loss": 0.4499, + "step": 8613 + }, + { + "epoch": 0.72, + "learning_rate": 3.819733487374801e-06, + "loss": 0.4697, + "step": 8614 + }, + { + "epoch": 0.72, + "learning_rate": 3.81760330329085e-06, + "loss": 0.4748, + "step": 8615 + }, + { + "epoch": 0.72, + "learning_rate": 3.815473573216397e-06, + "loss": 0.4666, + "step": 8616 + }, + { + "epoch": 0.72, + "learning_rate": 3.8133442973078415e-06, + "loss": 0.4688, + "step": 8617 + }, + { + "epoch": 0.72, + "learning_rate": 3.811215475721548e-06, + "loss": 0.4636, + "step": 8618 + }, + { + "epoch": 0.72, + "learning_rate": 3.809087108613846e-06, + "loss": 0.452, + "step": 8619 + }, + { + "epoch": 0.72, + "learning_rate": 3.8069591961410402e-06, + "loss": 0.458, + "step": 8620 + }, + { + "epoch": 0.72, + "learning_rate": 3.804831738459388e-06, + "loss": 0.4557, + "step": 8621 + }, + { + "epoch": 0.72, + "learning_rate": 3.80270473572513e-06, + "loss": 0.483, + "step": 8622 + }, + { + "epoch": 0.72, + "learning_rate": 3.800578188094459e-06, + "loss": 0.4682, + "step": 8623 + }, + { + "epoch": 0.72, + "learning_rate": 3.7984520957235403e-06, + "loss": 0.4645, + "step": 8624 + }, + { + "epoch": 0.72, + "learning_rate": 3.7963264587685067e-06, + "loss": 0.4688, + "step": 8625 + }, + { + "epoch": 0.72, + "learning_rate": 3.7942012773854532e-06, + "loss": 0.4634, + "step": 8626 + }, + { + "epoch": 0.72, + "learning_rate": 3.792076551730447e-06, + "loss": 0.4708, + "step": 8627 + }, + { + "epoch": 0.72, + "learning_rate": 3.789952281959515e-06, + "loss": 0.4622, + "step": 8628 + }, + { + "epoch": 0.72, + "learning_rate": 3.7878284682286615e-06, + "loss": 0.4641, + "step": 8629 + }, + { + "epoch": 0.72, + "learning_rate": 3.7857051106938425e-06, + "loss": 0.4655, + "step": 8630 + }, + { + "epoch": 0.72, + "learning_rate": 3.7835822095109966e-06, + "loss": 0.4844, + "step": 8631 + }, + { + "epoch": 0.72, + "learning_rate": 3.7814597648360176e-06, + "loss": 0.4661, + "step": 8632 + }, + { + "epoch": 0.72, + "learning_rate": 3.7793377768247685e-06, + "loss": 0.4646, + "step": 8633 + }, + { + "epoch": 0.72, + "learning_rate": 3.7772162456330796e-06, + "loss": 0.49, + "step": 8634 + }, + { + "epoch": 0.72, + "learning_rate": 3.775095171416744e-06, + "loss": 0.4759, + "step": 8635 + }, + { + "epoch": 0.72, + "learning_rate": 3.77297455433153e-06, + "loss": 0.4735, + "step": 8636 + }, + { + "epoch": 0.72, + "learning_rate": 3.7708543945331654e-06, + "loss": 0.4817, + "step": 8637 + }, + { + "epoch": 0.72, + "learning_rate": 3.768734692177345e-06, + "loss": 0.449, + "step": 8638 + }, + { + "epoch": 0.72, + "learning_rate": 3.766615447419727e-06, + "loss": 0.4656, + "step": 8639 + }, + { + "epoch": 0.72, + "learning_rate": 3.764496660415948e-06, + "loss": 0.4704, + "step": 8640 + }, + { + "epoch": 0.72, + "learning_rate": 3.762378331321599e-06, + "loss": 0.4846, + "step": 8641 + }, + { + "epoch": 0.72, + "learning_rate": 3.7602604602922365e-06, + "loss": 0.4714, + "step": 8642 + }, + { + "epoch": 0.72, + "learning_rate": 3.758143047483398e-06, + "loss": 0.4686, + "step": 8643 + }, + { + "epoch": 0.72, + "learning_rate": 3.756026093050571e-06, + "loss": 0.4748, + "step": 8644 + }, + { + "epoch": 0.72, + "learning_rate": 3.7539095971492177e-06, + "loss": 0.4507, + "step": 8645 + }, + { + "epoch": 0.72, + "learning_rate": 3.7517935599347634e-06, + "loss": 0.4642, + "step": 8646 + }, + { + "epoch": 0.72, + "learning_rate": 3.7496779815626026e-06, + "loss": 0.4805, + "step": 8647 + }, + { + "epoch": 0.72, + "learning_rate": 3.74756286218809e-06, + "loss": 0.4671, + "step": 8648 + }, + { + "epoch": 0.72, + "learning_rate": 3.745448201966558e-06, + "loss": 0.4739, + "step": 8649 + }, + { + "epoch": 0.72, + "learning_rate": 3.7433340010532926e-06, + "loss": 0.4768, + "step": 8650 + }, + { + "epoch": 0.72, + "learning_rate": 3.7412202596035586e-06, + "loss": 0.4509, + "step": 8651 + }, + { + "epoch": 0.72, + "learning_rate": 3.739106977772575e-06, + "loss": 0.4845, + "step": 8652 + }, + { + "epoch": 0.72, + "learning_rate": 3.7369941557155354e-06, + "loss": 0.4621, + "step": 8653 + }, + { + "epoch": 0.72, + "learning_rate": 3.7348817935875947e-06, + "loss": 0.4534, + "step": 8654 + }, + { + "epoch": 0.72, + "learning_rate": 3.7327698915438725e-06, + "loss": 0.4751, + "step": 8655 + }, + { + "epoch": 0.72, + "learning_rate": 3.730658449739466e-06, + "loss": 0.4679, + "step": 8656 + }, + { + "epoch": 0.72, + "learning_rate": 3.7285474683294274e-06, + "loss": 0.4685, + "step": 8657 + }, + { + "epoch": 0.72, + "learning_rate": 3.7264369474687767e-06, + "loss": 0.4646, + "step": 8658 + }, + { + "epoch": 0.72, + "learning_rate": 3.7243268873125038e-06, + "loss": 0.4867, + "step": 8659 + }, + { + "epoch": 0.72, + "learning_rate": 3.7222172880155585e-06, + "loss": 0.473, + "step": 8660 + }, + { + "epoch": 0.72, + "learning_rate": 3.720108149732866e-06, + "loss": 0.4919, + "step": 8661 + }, + { + "epoch": 0.72, + "learning_rate": 3.717999472619309e-06, + "loss": 0.4689, + "step": 8662 + }, + { + "epoch": 0.72, + "learning_rate": 3.7158912568297458e-06, + "loss": 0.482, + "step": 8663 + }, + { + "epoch": 0.72, + "learning_rate": 3.7137835025189894e-06, + "loss": 0.4459, + "step": 8664 + }, + { + "epoch": 0.72, + "learning_rate": 3.711676209841828e-06, + "loss": 0.4706, + "step": 8665 + }, + { + "epoch": 0.73, + "learning_rate": 3.7095693789530096e-06, + "loss": 0.4603, + "step": 8666 + }, + { + "epoch": 0.73, + "learning_rate": 3.707463010007252e-06, + "loss": 0.4563, + "step": 8667 + }, + { + "epoch": 0.73, + "learning_rate": 3.7053571031592393e-06, + "loss": 0.4674, + "step": 8668 + }, + { + "epoch": 0.73, + "learning_rate": 3.703251658563615e-06, + "loss": 0.4673, + "step": 8669 + }, + { + "epoch": 0.73, + "learning_rate": 3.7011466763750026e-06, + "loss": 0.4479, + "step": 8670 + }, + { + "epoch": 0.73, + "learning_rate": 3.6990421567479764e-06, + "loss": 0.465, + "step": 8671 + }, + { + "epoch": 0.73, + "learning_rate": 3.6969380998370896e-06, + "loss": 0.4908, + "step": 8672 + }, + { + "epoch": 0.73, + "learning_rate": 3.6948345057968525e-06, + "loss": 0.4905, + "step": 8673 + }, + { + "epoch": 0.73, + "learning_rate": 3.692731374781744e-06, + "loss": 0.4654, + "step": 8674 + }, + { + "epoch": 0.73, + "learning_rate": 3.69062870694621e-06, + "loss": 0.4858, + "step": 8675 + }, + { + "epoch": 0.73, + "learning_rate": 3.688526502444657e-06, + "loss": 0.4783, + "step": 8676 + }, + { + "epoch": 0.73, + "learning_rate": 3.6864247614314696e-06, + "loss": 0.4673, + "step": 8677 + }, + { + "epoch": 0.73, + "learning_rate": 3.6843234840609877e-06, + "loss": 0.4805, + "step": 8678 + }, + { + "epoch": 0.73, + "learning_rate": 3.6822226704875208e-06, + "loss": 0.4687, + "step": 8679 + }, + { + "epoch": 0.73, + "learning_rate": 3.6801223208653392e-06, + "loss": 0.4843, + "step": 8680 + }, + { + "epoch": 0.73, + "learning_rate": 3.6780224353486916e-06, + "loss": 0.4707, + "step": 8681 + }, + { + "epoch": 0.73, + "learning_rate": 3.675923014091781e-06, + "loss": 0.4632, + "step": 8682 + }, + { + "epoch": 0.73, + "learning_rate": 3.673824057248778e-06, + "loss": 0.4782, + "step": 8683 + }, + { + "epoch": 0.73, + "learning_rate": 3.671725564973827e-06, + "loss": 0.4764, + "step": 8684 + }, + { + "epoch": 0.73, + "learning_rate": 3.669627537421029e-06, + "loss": 0.4581, + "step": 8685 + }, + { + "epoch": 0.73, + "learning_rate": 3.6675299747444536e-06, + "loss": 0.4726, + "step": 8686 + }, + { + "epoch": 0.73, + "learning_rate": 3.6654328770981396e-06, + "loss": 0.4647, + "step": 8687 + }, + { + "epoch": 0.73, + "learning_rate": 3.6633362446360865e-06, + "loss": 0.4703, + "step": 8688 + }, + { + "epoch": 0.73, + "learning_rate": 3.6612400775122603e-06, + "loss": 0.448, + "step": 8689 + }, + { + "epoch": 0.73, + "learning_rate": 3.659144375880602e-06, + "loss": 0.4705, + "step": 8690 + }, + { + "epoch": 0.73, + "learning_rate": 3.6570491398950038e-06, + "loss": 0.4516, + "step": 8691 + }, + { + "epoch": 0.73, + "learning_rate": 3.654954369709337e-06, + "loss": 0.449, + "step": 8692 + }, + { + "epoch": 0.73, + "learning_rate": 3.6528600654774306e-06, + "loss": 0.466, + "step": 8693 + }, + { + "epoch": 0.73, + "learning_rate": 3.650766227353081e-06, + "loss": 0.464, + "step": 8694 + }, + { + "epoch": 0.73, + "learning_rate": 3.648672855490052e-06, + "loss": 0.4556, + "step": 8695 + }, + { + "epoch": 0.73, + "learning_rate": 3.6465799500420673e-06, + "loss": 0.4629, + "step": 8696 + }, + { + "epoch": 0.73, + "learning_rate": 3.6444875111628287e-06, + "loss": 0.4737, + "step": 8697 + }, + { + "epoch": 0.73, + "learning_rate": 3.642395539005993e-06, + "loss": 0.4636, + "step": 8698 + }, + { + "epoch": 0.73, + "learning_rate": 3.640304033725185e-06, + "loss": 0.4655, + "step": 8699 + }, + { + "epoch": 0.73, + "learning_rate": 3.6382129954739975e-06, + "loss": 0.4755, + "step": 8700 + }, + { + "epoch": 0.73, + "learning_rate": 3.6361224244059823e-06, + "loss": 0.4662, + "step": 8701 + }, + { + "epoch": 0.73, + "learning_rate": 3.634032320674672e-06, + "loss": 0.4579, + "step": 8702 + }, + { + "epoch": 0.73, + "learning_rate": 3.631942684433546e-06, + "loss": 0.4519, + "step": 8703 + }, + { + "epoch": 0.73, + "learning_rate": 3.629853515836065e-06, + "loss": 0.4656, + "step": 8704 + }, + { + "epoch": 0.73, + "learning_rate": 3.627764815035647e-06, + "loss": 0.463, + "step": 8705 + }, + { + "epoch": 0.73, + "learning_rate": 3.6256765821856775e-06, + "loss": 0.4798, + "step": 8706 + }, + { + "epoch": 0.73, + "learning_rate": 3.6235888174395062e-06, + "loss": 0.4823, + "step": 8707 + }, + { + "epoch": 0.73, + "learning_rate": 3.621501520950451e-06, + "loss": 0.4671, + "step": 8708 + }, + { + "epoch": 0.73, + "learning_rate": 3.6194146928717942e-06, + "loss": 0.4839, + "step": 8709 + }, + { + "epoch": 0.73, + "learning_rate": 3.61732833335678e-06, + "loss": 0.4805, + "step": 8710 + }, + { + "epoch": 0.73, + "learning_rate": 3.6152424425586285e-06, + "loss": 0.4655, + "step": 8711 + }, + { + "epoch": 0.73, + "learning_rate": 3.613157020630512e-06, + "loss": 0.4648, + "step": 8712 + }, + { + "epoch": 0.73, + "learning_rate": 3.611072067725583e-06, + "loss": 0.4541, + "step": 8713 + }, + { + "epoch": 0.73, + "learning_rate": 3.608987583996948e-06, + "loss": 0.4756, + "step": 8714 + }, + { + "epoch": 0.73, + "learning_rate": 3.606903569597683e-06, + "loss": 0.4576, + "step": 8715 + }, + { + "epoch": 0.73, + "learning_rate": 3.6048200246808273e-06, + "loss": 0.4836, + "step": 8716 + }, + { + "epoch": 0.73, + "learning_rate": 3.602736949399388e-06, + "loss": 0.473, + "step": 8717 + }, + { + "epoch": 0.73, + "learning_rate": 3.600654343906341e-06, + "loss": 0.4894, + "step": 8718 + }, + { + "epoch": 0.73, + "learning_rate": 3.5985722083546228e-06, + "loss": 0.4522, + "step": 8719 + }, + { + "epoch": 0.73, + "learning_rate": 3.5964905428971354e-06, + "loss": 0.473, + "step": 8720 + }, + { + "epoch": 0.73, + "learning_rate": 3.594409347686746e-06, + "loss": 0.4861, + "step": 8721 + }, + { + "epoch": 0.73, + "learning_rate": 3.5923286228762934e-06, + "loss": 0.4682, + "step": 8722 + }, + { + "epoch": 0.73, + "learning_rate": 3.5902483686185764e-06, + "loss": 0.457, + "step": 8723 + }, + { + "epoch": 0.73, + "learning_rate": 3.588168585066355e-06, + "loss": 0.4876, + "step": 8724 + }, + { + "epoch": 0.73, + "learning_rate": 3.5860892723723674e-06, + "loss": 0.4721, + "step": 8725 + }, + { + "epoch": 0.73, + "learning_rate": 3.5840104306893055e-06, + "loss": 0.4603, + "step": 8726 + }, + { + "epoch": 0.73, + "learning_rate": 3.5819320601698324e-06, + "loss": 0.4653, + "step": 8727 + }, + { + "epoch": 0.73, + "learning_rate": 3.579854160966574e-06, + "loss": 0.4754, + "step": 8728 + }, + { + "epoch": 0.73, + "learning_rate": 3.5777767332321222e-06, + "loss": 0.4538, + "step": 8729 + }, + { + "epoch": 0.73, + "learning_rate": 3.5756997771190317e-06, + "loss": 0.4826, + "step": 8730 + }, + { + "epoch": 0.73, + "learning_rate": 3.573623292779832e-06, + "loss": 0.4565, + "step": 8731 + }, + { + "epoch": 0.73, + "learning_rate": 3.5715472803670092e-06, + "loss": 0.4866, + "step": 8732 + }, + { + "epoch": 0.73, + "learning_rate": 3.5694717400330125e-06, + "loss": 0.4571, + "step": 8733 + }, + { + "epoch": 0.73, + "learning_rate": 3.5673966719302677e-06, + "loss": 0.4778, + "step": 8734 + }, + { + "epoch": 0.73, + "learning_rate": 3.565322076211156e-06, + "loss": 0.4611, + "step": 8735 + }, + { + "epoch": 0.73, + "learning_rate": 3.5632479530280273e-06, + "loss": 0.4616, + "step": 8736 + }, + { + "epoch": 0.73, + "learning_rate": 3.5611743025331933e-06, + "loss": 0.4913, + "step": 8737 + }, + { + "epoch": 0.73, + "learning_rate": 3.559101124878941e-06, + "loss": 0.46, + "step": 8738 + }, + { + "epoch": 0.73, + "learning_rate": 3.557028420217512e-06, + "loss": 0.4664, + "step": 8739 + }, + { + "epoch": 0.73, + "learning_rate": 3.5549561887011186e-06, + "loss": 0.47, + "step": 8740 + }, + { + "epoch": 0.73, + "learning_rate": 3.552884430481934e-06, + "loss": 0.4343, + "step": 8741 + }, + { + "epoch": 0.73, + "learning_rate": 3.5508131457120986e-06, + "loss": 0.4623, + "step": 8742 + }, + { + "epoch": 0.73, + "learning_rate": 3.5487423345437253e-06, + "loss": 0.4712, + "step": 8743 + }, + { + "epoch": 0.73, + "learning_rate": 3.546671997128879e-06, + "loss": 0.4623, + "step": 8744 + }, + { + "epoch": 0.73, + "learning_rate": 3.5446021336196024e-06, + "loss": 0.4617, + "step": 8745 + }, + { + "epoch": 0.73, + "learning_rate": 3.5425327441678956e-06, + "loss": 0.4594, + "step": 8746 + }, + { + "epoch": 0.73, + "learning_rate": 3.5404638289257256e-06, + "loss": 0.4785, + "step": 8747 + }, + { + "epoch": 0.73, + "learning_rate": 3.538395388045024e-06, + "loss": 0.4682, + "step": 8748 + }, + { + "epoch": 0.73, + "learning_rate": 3.53632742167769e-06, + "loss": 0.4745, + "step": 8749 + }, + { + "epoch": 0.73, + "learning_rate": 3.5342599299755854e-06, + "loss": 0.4562, + "step": 8750 + }, + { + "epoch": 0.73, + "learning_rate": 3.532192913090534e-06, + "loss": 0.4783, + "step": 8751 + }, + { + "epoch": 0.73, + "learning_rate": 3.5301263711743384e-06, + "loss": 0.4638, + "step": 8752 + }, + { + "epoch": 0.73, + "learning_rate": 3.528060304378749e-06, + "loss": 0.4599, + "step": 8753 + }, + { + "epoch": 0.73, + "learning_rate": 3.525994712855494e-06, + "loss": 0.4589, + "step": 8754 + }, + { + "epoch": 0.73, + "learning_rate": 3.5239295967562603e-06, + "loss": 0.4726, + "step": 8755 + }, + { + "epoch": 0.73, + "learning_rate": 3.5218649562327e-06, + "loss": 0.492, + "step": 8756 + }, + { + "epoch": 0.73, + "learning_rate": 3.519800791436434e-06, + "loss": 0.45, + "step": 8757 + }, + { + "epoch": 0.73, + "learning_rate": 3.517737102519041e-06, + "loss": 0.4591, + "step": 8758 + }, + { + "epoch": 0.73, + "learning_rate": 3.5156738896320773e-06, + "loss": 0.4785, + "step": 8759 + }, + { + "epoch": 0.73, + "learning_rate": 3.513611152927052e-06, + "loss": 0.4613, + "step": 8760 + }, + { + "epoch": 0.73, + "learning_rate": 3.5115488925554453e-06, + "loss": 0.46, + "step": 8761 + }, + { + "epoch": 0.73, + "learning_rate": 3.5094871086686997e-06, + "loss": 0.46, + "step": 8762 + }, + { + "epoch": 0.73, + "learning_rate": 3.507425801418223e-06, + "loss": 0.4892, + "step": 8763 + }, + { + "epoch": 0.73, + "learning_rate": 3.5053649709553893e-06, + "loss": 0.4579, + "step": 8764 + }, + { + "epoch": 0.73, + "learning_rate": 3.5033046174315422e-06, + "loss": 0.4607, + "step": 8765 + }, + { + "epoch": 0.73, + "learning_rate": 3.5012447409979832e-06, + "loss": 0.4775, + "step": 8766 + }, + { + "epoch": 0.73, + "learning_rate": 3.4991853418059798e-06, + "loss": 0.4502, + "step": 8767 + }, + { + "epoch": 0.73, + "learning_rate": 3.4971264200067657e-06, + "loss": 0.4841, + "step": 8768 + }, + { + "epoch": 0.73, + "learning_rate": 3.4950679757515395e-06, + "loss": 0.4704, + "step": 8769 + }, + { + "epoch": 0.73, + "learning_rate": 3.4930100091914655e-06, + "loss": 0.4668, + "step": 8770 + }, + { + "epoch": 0.73, + "learning_rate": 3.4909525204776684e-06, + "loss": 0.4685, + "step": 8771 + }, + { + "epoch": 0.73, + "learning_rate": 3.4888955097612487e-06, + "loss": 0.4771, + "step": 8772 + }, + { + "epoch": 0.73, + "learning_rate": 3.4868389771932608e-06, + "loss": 0.4739, + "step": 8773 + }, + { + "epoch": 0.73, + "learning_rate": 3.4847829229247243e-06, + "loss": 0.4764, + "step": 8774 + }, + { + "epoch": 0.73, + "learning_rate": 3.482727347106636e-06, + "loss": 0.4639, + "step": 8775 + }, + { + "epoch": 0.73, + "learning_rate": 3.4806722498899424e-06, + "loss": 0.4862, + "step": 8776 + }, + { + "epoch": 0.73, + "learning_rate": 3.4786176314255626e-06, + "loss": 0.4599, + "step": 8777 + }, + { + "epoch": 0.73, + "learning_rate": 3.4765634918643778e-06, + "loss": 0.4675, + "step": 8778 + }, + { + "epoch": 0.73, + "learning_rate": 3.474509831357239e-06, + "loss": 0.4556, + "step": 8779 + }, + { + "epoch": 0.73, + "learning_rate": 3.472456650054957e-06, + "loss": 0.4535, + "step": 8780 + }, + { + "epoch": 0.73, + "learning_rate": 3.4704039481083086e-06, + "loss": 0.4802, + "step": 8781 + }, + { + "epoch": 0.73, + "learning_rate": 3.4683517256680365e-06, + "loss": 0.4857, + "step": 8782 + }, + { + "epoch": 0.73, + "learning_rate": 3.466299982884842e-06, + "loss": 0.4661, + "step": 8783 + }, + { + "epoch": 0.73, + "learning_rate": 3.4642487199094042e-06, + "loss": 0.4644, + "step": 8784 + }, + { + "epoch": 0.73, + "learning_rate": 3.462197936892354e-06, + "loss": 0.4719, + "step": 8785 + }, + { + "epoch": 0.74, + "learning_rate": 3.4601476339842976e-06, + "loss": 0.4574, + "step": 8786 + }, + { + "epoch": 0.74, + "learning_rate": 3.4580978113357967e-06, + "loss": 0.4828, + "step": 8787 + }, + { + "epoch": 0.74, + "learning_rate": 3.4560484690973838e-06, + "loss": 0.4778, + "step": 8788 + }, + { + "epoch": 0.74, + "learning_rate": 3.4539996074195526e-06, + "loss": 0.4658, + "step": 8789 + }, + { + "epoch": 0.74, + "learning_rate": 3.4519512264527633e-06, + "loss": 0.4703, + "step": 8790 + }, + { + "epoch": 0.74, + "learning_rate": 3.44990332634744e-06, + "loss": 0.4833, + "step": 8791 + }, + { + "epoch": 0.74, + "learning_rate": 3.447855907253971e-06, + "loss": 0.464, + "step": 8792 + }, + { + "epoch": 0.74, + "learning_rate": 3.4458089693227127e-06, + "loss": 0.4666, + "step": 8793 + }, + { + "epoch": 0.74, + "learning_rate": 3.443762512703981e-06, + "loss": 0.4895, + "step": 8794 + }, + { + "epoch": 0.74, + "learning_rate": 3.4417165375480644e-06, + "loss": 0.4448, + "step": 8795 + }, + { + "epoch": 0.74, + "learning_rate": 3.439671044005206e-06, + "loss": 0.4548, + "step": 8796 + }, + { + "epoch": 0.74, + "learning_rate": 3.4376260322256207e-06, + "loss": 0.4647, + "step": 8797 + }, + { + "epoch": 0.74, + "learning_rate": 3.435581502359484e-06, + "loss": 0.4641, + "step": 8798 + }, + { + "epoch": 0.74, + "learning_rate": 3.4335374545569355e-06, + "loss": 0.4555, + "step": 8799 + }, + { + "epoch": 0.74, + "learning_rate": 3.431493888968087e-06, + "loss": 0.4594, + "step": 8800 + }, + { + "epoch": 0.74, + "learning_rate": 3.4294508057430077e-06, + "loss": 0.4741, + "step": 8801 + }, + { + "epoch": 0.74, + "learning_rate": 3.4274082050317324e-06, + "loss": 0.4444, + "step": 8802 + }, + { + "epoch": 0.74, + "learning_rate": 3.425366086984261e-06, + "loss": 0.4935, + "step": 8803 + }, + { + "epoch": 0.74, + "learning_rate": 3.4233244517505535e-06, + "loss": 0.4806, + "step": 8804 + }, + { + "epoch": 0.74, + "learning_rate": 3.4212832994805445e-06, + "loss": 0.4512, + "step": 8805 + }, + { + "epoch": 0.74, + "learning_rate": 3.419242630324131e-06, + "loss": 0.4563, + "step": 8806 + }, + { + "epoch": 0.74, + "learning_rate": 3.417202444431167e-06, + "loss": 0.4666, + "step": 8807 + }, + { + "epoch": 0.74, + "learning_rate": 3.4151627419514753e-06, + "loss": 0.4755, + "step": 8808 + }, + { + "epoch": 0.74, + "learning_rate": 3.4131235230348434e-06, + "loss": 0.4383, + "step": 8809 + }, + { + "epoch": 0.74, + "learning_rate": 3.411084787831024e-06, + "loss": 0.4517, + "step": 8810 + }, + { + "epoch": 0.74, + "learning_rate": 3.4090465364897317e-06, + "loss": 0.4664, + "step": 8811 + }, + { + "epoch": 0.74, + "learning_rate": 3.4070087691606446e-06, + "loss": 0.4844, + "step": 8812 + }, + { + "epoch": 0.74, + "learning_rate": 3.4049714859934144e-06, + "loss": 0.4634, + "step": 8813 + }, + { + "epoch": 0.74, + "learning_rate": 3.4029346871376477e-06, + "loss": 0.4492, + "step": 8814 + }, + { + "epoch": 0.74, + "learning_rate": 3.4008983727429147e-06, + "loss": 0.4665, + "step": 8815 + }, + { + "epoch": 0.74, + "learning_rate": 3.398862542958761e-06, + "loss": 0.4744, + "step": 8816 + }, + { + "epoch": 0.74, + "learning_rate": 3.3968271979346857e-06, + "loss": 0.4571, + "step": 8817 + }, + { + "epoch": 0.74, + "learning_rate": 3.3947923378201576e-06, + "loss": 0.4543, + "step": 8818 + }, + { + "epoch": 0.74, + "learning_rate": 3.3927579627646024e-06, + "loss": 0.4386, + "step": 8819 + }, + { + "epoch": 0.74, + "learning_rate": 3.390724072917424e-06, + "loss": 0.4878, + "step": 8820 + }, + { + "epoch": 0.74, + "learning_rate": 3.3886906684279806e-06, + "loss": 0.4807, + "step": 8821 + }, + { + "epoch": 0.74, + "learning_rate": 3.3866577494455953e-06, + "loss": 0.485, + "step": 8822 + }, + { + "epoch": 0.74, + "learning_rate": 3.3846253161195584e-06, + "loss": 0.46, + "step": 8823 + }, + { + "epoch": 0.74, + "learning_rate": 3.3825933685991184e-06, + "loss": 0.4907, + "step": 8824 + }, + { + "epoch": 0.74, + "learning_rate": 3.3805619070335026e-06, + "loss": 0.4913, + "step": 8825 + }, + { + "epoch": 0.74, + "learning_rate": 3.378530931571884e-06, + "loss": 0.4608, + "step": 8826 + }, + { + "epoch": 0.74, + "learning_rate": 3.3765004423634164e-06, + "loss": 0.4769, + "step": 8827 + }, + { + "epoch": 0.74, + "learning_rate": 3.374470439557207e-06, + "loss": 0.4694, + "step": 8828 + }, + { + "epoch": 0.74, + "learning_rate": 3.37244092330233e-06, + "loss": 0.4434, + "step": 8829 + }, + { + "epoch": 0.74, + "learning_rate": 3.370411893747827e-06, + "loss": 0.4433, + "step": 8830 + }, + { + "epoch": 0.74, + "learning_rate": 3.368383351042699e-06, + "loss": 0.4656, + "step": 8831 + }, + { + "epoch": 0.74, + "learning_rate": 3.366355295335915e-06, + "loss": 0.4648, + "step": 8832 + }, + { + "epoch": 0.74, + "learning_rate": 3.364327726776403e-06, + "loss": 0.4587, + "step": 8833 + }, + { + "epoch": 0.74, + "learning_rate": 3.362300645513067e-06, + "loss": 0.4806, + "step": 8834 + }, + { + "epoch": 0.74, + "learning_rate": 3.3602740516947595e-06, + "loss": 0.4774, + "step": 8835 + }, + { + "epoch": 0.74, + "learning_rate": 3.358247945470313e-06, + "loss": 0.4611, + "step": 8836 + }, + { + "epoch": 0.74, + "learning_rate": 3.356222326988512e-06, + "loss": 0.4639, + "step": 8837 + }, + { + "epoch": 0.74, + "learning_rate": 3.354197196398109e-06, + "loss": 0.4685, + "step": 8838 + }, + { + "epoch": 0.74, + "learning_rate": 3.352172553847819e-06, + "loss": 0.4648, + "step": 8839 + }, + { + "epoch": 0.74, + "learning_rate": 3.3501483994863293e-06, + "loss": 0.4667, + "step": 8840 + }, + { + "epoch": 0.74, + "learning_rate": 3.3481247334622822e-06, + "loss": 0.4724, + "step": 8841 + }, + { + "epoch": 0.74, + "learning_rate": 3.346101555924288e-06, + "loss": 0.4687, + "step": 8842 + }, + { + "epoch": 0.74, + "learning_rate": 3.34407886702092e-06, + "loss": 0.4531, + "step": 8843 + }, + { + "epoch": 0.74, + "learning_rate": 3.342056666900716e-06, + "loss": 0.4567, + "step": 8844 + }, + { + "epoch": 0.74, + "learning_rate": 3.3400349557121748e-06, + "loss": 0.4598, + "step": 8845 + }, + { + "epoch": 0.74, + "learning_rate": 3.338013733603768e-06, + "loss": 0.489, + "step": 8846 + }, + { + "epoch": 0.74, + "learning_rate": 3.3359930007239204e-06, + "loss": 0.4647, + "step": 8847 + }, + { + "epoch": 0.74, + "learning_rate": 3.3339727572210323e-06, + "loss": 0.4698, + "step": 8848 + }, + { + "epoch": 0.74, + "learning_rate": 3.3319530032434588e-06, + "loss": 0.4671, + "step": 8849 + }, + { + "epoch": 0.74, + "learning_rate": 3.3299337389395225e-06, + "loss": 0.4578, + "step": 8850 + }, + { + "epoch": 0.74, + "learning_rate": 3.327914964457509e-06, + "loss": 0.4684, + "step": 8851 + }, + { + "epoch": 0.74, + "learning_rate": 3.3258966799456705e-06, + "loss": 0.4679, + "step": 8852 + }, + { + "epoch": 0.74, + "learning_rate": 3.3238788855522164e-06, + "loss": 0.4732, + "step": 8853 + }, + { + "epoch": 0.74, + "learning_rate": 3.3218615814253306e-06, + "loss": 0.471, + "step": 8854 + }, + { + "epoch": 0.74, + "learning_rate": 3.319844767713155e-06, + "loss": 0.4485, + "step": 8855 + }, + { + "epoch": 0.74, + "learning_rate": 3.317828444563792e-06, + "loss": 0.4604, + "step": 8856 + }, + { + "epoch": 0.74, + "learning_rate": 3.3158126121253178e-06, + "loss": 0.4795, + "step": 8857 + }, + { + "epoch": 0.74, + "learning_rate": 3.3137972705457632e-06, + "loss": 0.4728, + "step": 8858 + }, + { + "epoch": 0.74, + "learning_rate": 3.3117824199731274e-06, + "loss": 0.4833, + "step": 8859 + }, + { + "epoch": 0.74, + "learning_rate": 3.3097680605553697e-06, + "loss": 0.4926, + "step": 8860 + }, + { + "epoch": 0.74, + "learning_rate": 3.307754192440421e-06, + "loss": 0.4609, + "step": 8861 + }, + { + "epoch": 0.74, + "learning_rate": 3.3057408157761696e-06, + "loss": 0.4956, + "step": 8862 + }, + { + "epoch": 0.74, + "learning_rate": 3.3037279307104685e-06, + "loss": 0.4779, + "step": 8863 + }, + { + "epoch": 0.74, + "learning_rate": 3.3017155373911382e-06, + "loss": 0.4621, + "step": 8864 + }, + { + "epoch": 0.74, + "learning_rate": 3.299703635965953e-06, + "loss": 0.4677, + "step": 8865 + }, + { + "epoch": 0.74, + "learning_rate": 3.2976922265826695e-06, + "loss": 0.4607, + "step": 8866 + }, + { + "epoch": 0.74, + "learning_rate": 3.295681309388987e-06, + "loss": 0.4671, + "step": 8867 + }, + { + "epoch": 0.74, + "learning_rate": 3.2936708845325882e-06, + "loss": 0.4555, + "step": 8868 + }, + { + "epoch": 0.74, + "learning_rate": 3.2916609521611052e-06, + "loss": 0.4641, + "step": 8869 + }, + { + "epoch": 0.74, + "learning_rate": 3.2896515124221395e-06, + "loss": 0.4775, + "step": 8870 + }, + { + "epoch": 0.74, + "learning_rate": 3.287642565463257e-06, + "loss": 0.4471, + "step": 8871 + }, + { + "epoch": 0.74, + "learning_rate": 3.2856341114319856e-06, + "loss": 0.467, + "step": 8872 + }, + { + "epoch": 0.74, + "learning_rate": 3.283626150475818e-06, + "loss": 0.4799, + "step": 8873 + }, + { + "epoch": 0.74, + "learning_rate": 3.281618682742207e-06, + "loss": 0.4601, + "step": 8874 + }, + { + "epoch": 0.74, + "learning_rate": 3.2796117083785793e-06, + "loss": 0.4666, + "step": 8875 + }, + { + "epoch": 0.74, + "learning_rate": 3.2776052275323155e-06, + "loss": 0.461, + "step": 8876 + }, + { + "epoch": 0.74, + "learning_rate": 3.2755992403507595e-06, + "loss": 0.4508, + "step": 8877 + }, + { + "epoch": 0.74, + "learning_rate": 3.2735937469812308e-06, + "loss": 0.4643, + "step": 8878 + }, + { + "epoch": 0.74, + "learning_rate": 3.2715887475709994e-06, + "loss": 0.4558, + "step": 8879 + }, + { + "epoch": 0.74, + "learning_rate": 3.269584242267301e-06, + "loss": 0.4459, + "step": 8880 + }, + { + "epoch": 0.74, + "learning_rate": 3.2675802312173468e-06, + "loss": 0.4652, + "step": 8881 + }, + { + "epoch": 0.74, + "learning_rate": 3.265576714568296e-06, + "loss": 0.4812, + "step": 8882 + }, + { + "epoch": 0.74, + "learning_rate": 3.263573692467282e-06, + "loss": 0.4507, + "step": 8883 + }, + { + "epoch": 0.74, + "learning_rate": 3.2615711650613978e-06, + "loss": 0.4705, + "step": 8884 + }, + { + "epoch": 0.74, + "learning_rate": 3.2595691324976987e-06, + "loss": 0.4785, + "step": 8885 + }, + { + "epoch": 0.74, + "learning_rate": 3.2575675949232044e-06, + "loss": 0.4464, + "step": 8886 + }, + { + "epoch": 0.74, + "learning_rate": 3.2555665524849056e-06, + "loss": 0.4793, + "step": 8887 + }, + { + "epoch": 0.74, + "learning_rate": 3.2535660053297426e-06, + "loss": 0.467, + "step": 8888 + }, + { + "epoch": 0.74, + "learning_rate": 3.2515659536046362e-06, + "loss": 0.4741, + "step": 8889 + }, + { + "epoch": 0.74, + "learning_rate": 3.249566397456456e-06, + "loss": 0.456, + "step": 8890 + }, + { + "epoch": 0.74, + "learning_rate": 3.2475673370320437e-06, + "loss": 0.4789, + "step": 8891 + }, + { + "epoch": 0.74, + "learning_rate": 3.2455687724781993e-06, + "loss": 0.4689, + "step": 8892 + }, + { + "epoch": 0.74, + "learning_rate": 3.243570703941692e-06, + "loss": 0.4554, + "step": 8893 + }, + { + "epoch": 0.74, + "learning_rate": 3.2415731315692456e-06, + "loss": 0.4697, + "step": 8894 + }, + { + "epoch": 0.74, + "learning_rate": 3.2395760555075616e-06, + "loss": 0.4546, + "step": 8895 + }, + { + "epoch": 0.74, + "learning_rate": 3.237579475903294e-06, + "loss": 0.4439, + "step": 8896 + }, + { + "epoch": 0.74, + "learning_rate": 3.235583392903059e-06, + "loss": 0.4737, + "step": 8897 + }, + { + "epoch": 0.74, + "learning_rate": 3.2335878066534464e-06, + "loss": 0.4907, + "step": 8898 + }, + { + "epoch": 0.74, + "learning_rate": 3.231592717301003e-06, + "loss": 0.4479, + "step": 8899 + }, + { + "epoch": 0.74, + "learning_rate": 3.229598124992238e-06, + "loss": 0.4761, + "step": 8900 + }, + { + "epoch": 0.74, + "learning_rate": 3.2276040298736246e-06, + "loss": 0.4905, + "step": 8901 + }, + { + "epoch": 0.74, + "learning_rate": 3.225610432091604e-06, + "loss": 0.4728, + "step": 8902 + }, + { + "epoch": 0.74, + "learning_rate": 3.223617331792578e-06, + "loss": 0.4552, + "step": 8903 + }, + { + "epoch": 0.74, + "learning_rate": 3.2216247291229087e-06, + "loss": 0.4697, + "step": 8904 + }, + { + "epoch": 0.75, + "learning_rate": 3.2196326242289266e-06, + "loss": 0.4414, + "step": 8905 + }, + { + "epoch": 0.75, + "learning_rate": 3.217641017256923e-06, + "loss": 0.4574, + "step": 8906 + }, + { + "epoch": 0.75, + "learning_rate": 3.21564990835315e-06, + "loss": 0.4696, + "step": 8907 + }, + { + "epoch": 0.75, + "learning_rate": 3.2136592976638293e-06, + "loss": 0.4626, + "step": 8908 + }, + { + "epoch": 0.75, + "learning_rate": 3.2116691853351455e-06, + "loss": 0.448, + "step": 8909 + }, + { + "epoch": 0.75, + "learning_rate": 3.2096795715132436e-06, + "loss": 0.4561, + "step": 8910 + }, + { + "epoch": 0.75, + "learning_rate": 3.2076904563442303e-06, + "loss": 0.4295, + "step": 8911 + }, + { + "epoch": 0.75, + "learning_rate": 3.2057018399741777e-06, + "loss": 0.4665, + "step": 8912 + }, + { + "epoch": 0.75, + "learning_rate": 3.2037137225491233e-06, + "loss": 0.4557, + "step": 8913 + }, + { + "epoch": 0.75, + "learning_rate": 3.2017261042150625e-06, + "loss": 0.4629, + "step": 8914 + }, + { + "epoch": 0.75, + "learning_rate": 3.199738985117963e-06, + "loss": 0.455, + "step": 8915 + }, + { + "epoch": 0.75, + "learning_rate": 3.197752365403748e-06, + "loss": 0.4552, + "step": 8916 + }, + { + "epoch": 0.75, + "learning_rate": 3.195766245218307e-06, + "loss": 0.469, + "step": 8917 + }, + { + "epoch": 0.75, + "learning_rate": 3.1937806247074875e-06, + "loss": 0.4608, + "step": 8918 + }, + { + "epoch": 0.75, + "learning_rate": 3.1917955040171146e-06, + "loss": 0.4603, + "step": 8919 + }, + { + "epoch": 0.75, + "learning_rate": 3.189810883292961e-06, + "loss": 0.4671, + "step": 8920 + }, + { + "epoch": 0.75, + "learning_rate": 3.187826762680768e-06, + "loss": 0.4597, + "step": 8921 + }, + { + "epoch": 0.75, + "learning_rate": 3.185843142326247e-06, + "loss": 0.4783, + "step": 8922 + }, + { + "epoch": 0.75, + "learning_rate": 3.1838600223750625e-06, + "loss": 0.4879, + "step": 8923 + }, + { + "epoch": 0.75, + "learning_rate": 3.181877402972848e-06, + "loss": 0.452, + "step": 8924 + }, + { + "epoch": 0.75, + "learning_rate": 3.1798952842651985e-06, + "loss": 0.4763, + "step": 8925 + }, + { + "epoch": 0.75, + "learning_rate": 3.177913666397673e-06, + "loss": 0.4543, + "step": 8926 + }, + { + "epoch": 0.75, + "learning_rate": 3.175932549515789e-06, + "loss": 0.4596, + "step": 8927 + }, + { + "epoch": 0.75, + "learning_rate": 3.173951933765038e-06, + "loss": 0.4473, + "step": 8928 + }, + { + "epoch": 0.75, + "learning_rate": 3.171971819290862e-06, + "loss": 0.4753, + "step": 8929 + }, + { + "epoch": 0.75, + "learning_rate": 3.169992206238679e-06, + "loss": 0.4606, + "step": 8930 + }, + { + "epoch": 0.75, + "learning_rate": 3.16801309475386e-06, + "loss": 0.4574, + "step": 8931 + }, + { + "epoch": 0.75, + "learning_rate": 3.166034484981744e-06, + "loss": 0.4675, + "step": 8932 + }, + { + "epoch": 0.75, + "learning_rate": 3.1640563770676305e-06, + "loss": 0.473, + "step": 8933 + }, + { + "epoch": 0.75, + "learning_rate": 3.1620787711567823e-06, + "loss": 0.4408, + "step": 8934 + }, + { + "epoch": 0.75, + "learning_rate": 3.1601016673944262e-06, + "loss": 0.4406, + "step": 8935 + }, + { + "epoch": 0.75, + "learning_rate": 3.158125065925758e-06, + "loss": 0.4783, + "step": 8936 + }, + { + "epoch": 0.75, + "learning_rate": 3.1561489668959268e-06, + "loss": 0.4705, + "step": 8937 + }, + { + "epoch": 0.75, + "learning_rate": 3.1541733704500464e-06, + "loss": 0.4587, + "step": 8938 + }, + { + "epoch": 0.75, + "learning_rate": 3.1521982767332038e-06, + "loss": 0.4524, + "step": 8939 + }, + { + "epoch": 0.75, + "learning_rate": 3.150223685890437e-06, + "loss": 0.4647, + "step": 8940 + }, + { + "epoch": 0.75, + "learning_rate": 3.1482495980667516e-06, + "loss": 0.4681, + "step": 8941 + }, + { + "epoch": 0.75, + "learning_rate": 3.1462760134071145e-06, + "loss": 0.4533, + "step": 8942 + }, + { + "epoch": 0.75, + "learning_rate": 3.1443029320564642e-06, + "loss": 0.4697, + "step": 8943 + }, + { + "epoch": 0.75, + "learning_rate": 3.1423303541596904e-06, + "loss": 0.4745, + "step": 8944 + }, + { + "epoch": 0.75, + "learning_rate": 3.1403582798616527e-06, + "loss": 0.4818, + "step": 8945 + }, + { + "epoch": 0.75, + "learning_rate": 3.1383867093071717e-06, + "loss": 0.4557, + "step": 8946 + }, + { + "epoch": 0.75, + "learning_rate": 3.1364156426410307e-06, + "loss": 0.4594, + "step": 8947 + }, + { + "epoch": 0.75, + "learning_rate": 3.1344450800079753e-06, + "loss": 0.4624, + "step": 8948 + }, + { + "epoch": 0.75, + "learning_rate": 3.1324750215527157e-06, + "loss": 0.4538, + "step": 8949 + }, + { + "epoch": 0.75, + "learning_rate": 3.1305054674199297e-06, + "loss": 0.4745, + "step": 8950 + }, + { + "epoch": 0.75, + "learning_rate": 3.12853641775425e-06, + "loss": 0.4548, + "step": 8951 + }, + { + "epoch": 0.75, + "learning_rate": 3.1265678727002758e-06, + "loss": 0.4664, + "step": 8952 + }, + { + "epoch": 0.75, + "learning_rate": 3.124599832402567e-06, + "loss": 0.459, + "step": 8953 + }, + { + "epoch": 0.75, + "learning_rate": 3.122632297005651e-06, + "loss": 0.4514, + "step": 8954 + }, + { + "epoch": 0.75, + "learning_rate": 3.1206652666540107e-06, + "loss": 0.5009, + "step": 8955 + }, + { + "epoch": 0.75, + "learning_rate": 3.1186987414921023e-06, + "loss": 0.451, + "step": 8956 + }, + { + "epoch": 0.75, + "learning_rate": 3.1167327216643374e-06, + "loss": 0.4915, + "step": 8957 + }, + { + "epoch": 0.75, + "learning_rate": 3.1147672073150916e-06, + "loss": 0.4549, + "step": 8958 + }, + { + "epoch": 0.75, + "learning_rate": 3.1128021985887004e-06, + "loss": 0.4543, + "step": 8959 + }, + { + "epoch": 0.75, + "learning_rate": 3.110837695629473e-06, + "loss": 0.4726, + "step": 8960 + }, + { + "epoch": 0.75, + "learning_rate": 3.1088736985816716e-06, + "loss": 0.4673, + "step": 8961 + }, + { + "epoch": 0.75, + "learning_rate": 3.1069102075895207e-06, + "loss": 0.4575, + "step": 8962 + }, + { + "epoch": 0.75, + "learning_rate": 3.1049472227972157e-06, + "loss": 0.4507, + "step": 8963 + }, + { + "epoch": 0.75, + "learning_rate": 3.1029847443489093e-06, + "loss": 0.4733, + "step": 8964 + }, + { + "epoch": 0.75, + "learning_rate": 3.1010227723887153e-06, + "loss": 0.4522, + "step": 8965 + }, + { + "epoch": 0.75, + "learning_rate": 3.0990613070607145e-06, + "loss": 0.4629, + "step": 8966 + }, + { + "epoch": 0.75, + "learning_rate": 3.0971003485089477e-06, + "loss": 0.4818, + "step": 8967 + }, + { + "epoch": 0.75, + "learning_rate": 3.095139896877417e-06, + "loss": 0.4479, + "step": 8968 + }, + { + "epoch": 0.75, + "learning_rate": 3.093179952310096e-06, + "loss": 0.4705, + "step": 8969 + }, + { + "epoch": 0.75, + "learning_rate": 3.091220514950908e-06, + "loss": 0.4932, + "step": 8970 + }, + { + "epoch": 0.75, + "learning_rate": 3.0892615849437533e-06, + "loss": 0.4519, + "step": 8971 + }, + { + "epoch": 0.75, + "learning_rate": 3.0873031624324835e-06, + "loss": 0.4589, + "step": 8972 + }, + { + "epoch": 0.75, + "learning_rate": 3.085345247560918e-06, + "loss": 0.4546, + "step": 8973 + }, + { + "epoch": 0.75, + "learning_rate": 3.0833878404728366e-06, + "loss": 0.4622, + "step": 8974 + }, + { + "epoch": 0.75, + "learning_rate": 3.081430941311985e-06, + "loss": 0.4992, + "step": 8975 + }, + { + "epoch": 0.75, + "learning_rate": 3.0794745502220646e-06, + "loss": 0.4815, + "step": 8976 + }, + { + "epoch": 0.75, + "learning_rate": 3.077518667346752e-06, + "loss": 0.4669, + "step": 8977 + }, + { + "epoch": 0.75, + "learning_rate": 3.075563292829675e-06, + "loss": 0.4699, + "step": 8978 + }, + { + "epoch": 0.75, + "learning_rate": 3.0736084268144264e-06, + "loss": 0.4627, + "step": 8979 + }, + { + "epoch": 0.75, + "learning_rate": 3.0716540694445694e-06, + "loss": 0.4654, + "step": 8980 + }, + { + "epoch": 0.75, + "learning_rate": 3.0697002208636195e-06, + "loss": 0.4628, + "step": 8981 + }, + { + "epoch": 0.75, + "learning_rate": 3.0677468812150612e-06, + "loss": 0.4558, + "step": 8982 + }, + { + "epoch": 0.75, + "learning_rate": 3.0657940506423345e-06, + "loss": 0.4844, + "step": 8983 + }, + { + "epoch": 0.75, + "learning_rate": 3.0638417292888546e-06, + "loss": 0.4778, + "step": 8984 + }, + { + "epoch": 0.75, + "learning_rate": 3.0618899172979875e-06, + "loss": 0.4671, + "step": 8985 + }, + { + "epoch": 0.75, + "learning_rate": 3.0599386148130684e-06, + "loss": 0.4511, + "step": 8986 + }, + { + "epoch": 0.75, + "learning_rate": 3.0579878219773917e-06, + "loss": 0.4486, + "step": 8987 + }, + { + "epoch": 0.75, + "learning_rate": 3.0560375389342147e-06, + "loss": 0.4686, + "step": 8988 + }, + { + "epoch": 0.75, + "learning_rate": 3.0540877658267555e-06, + "loss": 0.4589, + "step": 8989 + }, + { + "epoch": 0.75, + "learning_rate": 3.0521385027982033e-06, + "loss": 0.4522, + "step": 8990 + }, + { + "epoch": 0.75, + "learning_rate": 3.050189749991699e-06, + "loss": 0.4682, + "step": 8991 + }, + { + "epoch": 0.75, + "learning_rate": 3.0482415075503556e-06, + "loss": 0.4816, + "step": 8992 + }, + { + "epoch": 0.75, + "learning_rate": 3.0462937756172417e-06, + "loss": 0.4533, + "step": 8993 + }, + { + "epoch": 0.75, + "learning_rate": 3.0443465543353902e-06, + "loss": 0.4747, + "step": 8994 + }, + { + "epoch": 0.75, + "learning_rate": 3.0423998438477964e-06, + "loss": 0.4747, + "step": 8995 + }, + { + "epoch": 0.75, + "learning_rate": 3.0404536442974165e-06, + "loss": 0.4568, + "step": 8996 + }, + { + "epoch": 0.75, + "learning_rate": 3.0385079558271768e-06, + "loss": 0.4665, + "step": 8997 + }, + { + "epoch": 0.75, + "learning_rate": 3.036562778579959e-06, + "loss": 0.4617, + "step": 8998 + }, + { + "epoch": 0.75, + "learning_rate": 3.0346181126986063e-06, + "loss": 0.4713, + "step": 8999 + }, + { + "epoch": 0.75, + "learning_rate": 3.0326739583259255e-06, + "loss": 0.4868, + "step": 9000 + }, + { + "epoch": 0.75, + "learning_rate": 3.030730315604693e-06, + "loss": 0.4813, + "step": 9001 + }, + { + "epoch": 0.75, + "learning_rate": 3.0287871846776397e-06, + "loss": 0.4769, + "step": 9002 + }, + { + "epoch": 0.75, + "learning_rate": 3.0268445656874555e-06, + "loss": 0.4529, + "step": 9003 + }, + { + "epoch": 0.75, + "learning_rate": 3.0249024587768074e-06, + "loss": 0.4653, + "step": 9004 + }, + { + "epoch": 0.75, + "learning_rate": 3.02296086408831e-06, + "loss": 0.4987, + "step": 9005 + }, + { + "epoch": 0.75, + "learning_rate": 3.0210197817645472e-06, + "loss": 0.445, + "step": 9006 + }, + { + "epoch": 0.75, + "learning_rate": 3.0190792119480638e-06, + "loss": 0.4692, + "step": 9007 + }, + { + "epoch": 0.75, + "learning_rate": 3.017139154781368e-06, + "loss": 0.4617, + "step": 9008 + }, + { + "epoch": 0.75, + "learning_rate": 3.015199610406925e-06, + "loss": 0.4727, + "step": 9009 + }, + { + "epoch": 0.75, + "learning_rate": 3.0132605789671744e-06, + "loss": 0.4471, + "step": 9010 + }, + { + "epoch": 0.75, + "learning_rate": 3.0113220606045035e-06, + "loss": 0.4654, + "step": 9011 + }, + { + "epoch": 0.75, + "learning_rate": 3.0093840554612753e-06, + "loss": 0.4895, + "step": 9012 + }, + { + "epoch": 0.75, + "learning_rate": 3.0074465636798056e-06, + "loss": 0.4657, + "step": 9013 + }, + { + "epoch": 0.75, + "learning_rate": 3.0055095854023764e-06, + "loss": 0.483, + "step": 9014 + }, + { + "epoch": 0.75, + "learning_rate": 3.0035731207712305e-06, + "loss": 0.4526, + "step": 9015 + }, + { + "epoch": 0.75, + "learning_rate": 3.001637169928575e-06, + "loss": 0.4655, + "step": 9016 + }, + { + "epoch": 0.75, + "learning_rate": 2.9997017330165736e-06, + "loss": 0.4689, + "step": 9017 + }, + { + "epoch": 0.75, + "learning_rate": 2.9977668101773636e-06, + "loss": 0.4669, + "step": 9018 + }, + { + "epoch": 0.75, + "learning_rate": 2.995832401553035e-06, + "loss": 0.4726, + "step": 9019 + }, + { + "epoch": 0.75, + "learning_rate": 2.993898507285643e-06, + "loss": 0.4629, + "step": 9020 + }, + { + "epoch": 0.75, + "learning_rate": 2.9919651275172e-06, + "loss": 0.4591, + "step": 9021 + }, + { + "epoch": 0.75, + "learning_rate": 2.990032262389693e-06, + "loss": 0.4758, + "step": 9022 + }, + { + "epoch": 0.75, + "learning_rate": 2.9880999120450595e-06, + "loss": 0.4545, + "step": 9023 + }, + { + "epoch": 0.75, + "learning_rate": 2.9861680766252e-06, + "loss": 0.4509, + "step": 9024 + }, + { + "epoch": 0.76, + "learning_rate": 2.9842367562719887e-06, + "loss": 0.4604, + "step": 9025 + }, + { + "epoch": 0.76, + "learning_rate": 2.982305951127249e-06, + "loss": 0.46, + "step": 9026 + }, + { + "epoch": 0.76, + "learning_rate": 2.9803756613327704e-06, + "loss": 0.4715, + "step": 9027 + }, + { + "epoch": 0.76, + "learning_rate": 2.978445887030308e-06, + "loss": 0.4413, + "step": 9028 + }, + { + "epoch": 0.76, + "learning_rate": 2.976516628361574e-06, + "loss": 0.4943, + "step": 9029 + }, + { + "epoch": 0.76, + "learning_rate": 2.974587885468243e-06, + "loss": 0.4575, + "step": 9030 + }, + { + "epoch": 0.76, + "learning_rate": 2.9726596584919596e-06, + "loss": 0.4496, + "step": 9031 + }, + { + "epoch": 0.76, + "learning_rate": 2.970731947574319e-06, + "loss": 0.4542, + "step": 9032 + }, + { + "epoch": 0.76, + "learning_rate": 2.968804752856891e-06, + "loss": 0.4855, + "step": 9033 + }, + { + "epoch": 0.76, + "learning_rate": 2.9668780744811967e-06, + "loss": 0.4437, + "step": 9034 + }, + { + "epoch": 0.76, + "learning_rate": 2.9649519125887227e-06, + "loss": 0.4699, + "step": 9035 + }, + { + "epoch": 0.76, + "learning_rate": 2.96302626732092e-06, + "loss": 0.4794, + "step": 9036 + }, + { + "epoch": 0.76, + "learning_rate": 2.9611011388191956e-06, + "loss": 0.4607, + "step": 9037 + }, + { + "epoch": 0.76, + "learning_rate": 2.9591765272249305e-06, + "loss": 0.472, + "step": 9038 + }, + { + "epoch": 0.76, + "learning_rate": 2.9572524326794562e-06, + "loss": 0.4636, + "step": 9039 + }, + { + "epoch": 0.76, + "learning_rate": 2.9553288553240698e-06, + "loss": 0.4749, + "step": 9040 + }, + { + "epoch": 0.76, + "learning_rate": 2.9534057953000283e-06, + "loss": 0.4753, + "step": 9041 + }, + { + "epoch": 0.76, + "learning_rate": 2.9514832527485593e-06, + "loss": 0.4424, + "step": 9042 + }, + { + "epoch": 0.76, + "learning_rate": 2.949561227810843e-06, + "loss": 0.4706, + "step": 9043 + }, + { + "epoch": 0.76, + "learning_rate": 2.947639720628023e-06, + "loss": 0.4448, + "step": 9044 + }, + { + "epoch": 0.76, + "learning_rate": 2.945718731341212e-06, + "loss": 0.4846, + "step": 9045 + }, + { + "epoch": 0.76, + "learning_rate": 2.943798260091475e-06, + "loss": 0.4563, + "step": 9046 + }, + { + "epoch": 0.76, + "learning_rate": 2.9418783070198455e-06, + "loss": 0.4693, + "step": 9047 + }, + { + "epoch": 0.76, + "learning_rate": 2.9399588722673165e-06, + "loss": 0.4424, + "step": 9048 + }, + { + "epoch": 0.76, + "learning_rate": 2.938039955974843e-06, + "loss": 0.4605, + "step": 9049 + }, + { + "epoch": 0.76, + "learning_rate": 2.9361215582833425e-06, + "loss": 0.474, + "step": 9050 + }, + { + "epoch": 0.76, + "learning_rate": 2.9342036793336904e-06, + "loss": 0.4644, + "step": 9051 + }, + { + "epoch": 0.76, + "learning_rate": 2.9322863192667306e-06, + "loss": 0.4739, + "step": 9052 + }, + { + "epoch": 0.76, + "learning_rate": 2.9303694782232706e-06, + "loss": 0.451, + "step": 9053 + }, + { + "epoch": 0.76, + "learning_rate": 2.928453156344071e-06, + "loss": 0.4632, + "step": 9054 + }, + { + "epoch": 0.76, + "learning_rate": 2.9265373537698595e-06, + "loss": 0.4599, + "step": 9055 + }, + { + "epoch": 0.76, + "learning_rate": 2.924622070641323e-06, + "loss": 0.4581, + "step": 9056 + }, + { + "epoch": 0.76, + "learning_rate": 2.922707307099113e-06, + "loss": 0.4745, + "step": 9057 + }, + { + "epoch": 0.76, + "learning_rate": 2.920793063283839e-06, + "loss": 0.4713, + "step": 9058 + }, + { + "epoch": 0.76, + "learning_rate": 2.9188793393360813e-06, + "loss": 0.4605, + "step": 9059 + }, + { + "epoch": 0.76, + "learning_rate": 2.916966135396372e-06, + "loss": 0.4687, + "step": 9060 + }, + { + "epoch": 0.76, + "learning_rate": 2.9150534516052085e-06, + "loss": 0.4748, + "step": 9061 + }, + { + "epoch": 0.76, + "learning_rate": 2.9131412881030487e-06, + "loss": 0.454, + "step": 9062 + }, + { + "epoch": 0.76, + "learning_rate": 2.911229645030319e-06, + "loss": 0.4901, + "step": 9063 + }, + { + "epoch": 0.76, + "learning_rate": 2.909318522527397e-06, + "loss": 0.4588, + "step": 9064 + }, + { + "epoch": 0.76, + "learning_rate": 2.9074079207346328e-06, + "loss": 0.4642, + "step": 9065 + }, + { + "epoch": 0.76, + "learning_rate": 2.9054978397923306e-06, + "loss": 0.4733, + "step": 9066 + }, + { + "epoch": 0.76, + "learning_rate": 2.903588279840759e-06, + "loss": 0.4799, + "step": 9067 + }, + { + "epoch": 0.76, + "learning_rate": 2.901679241020149e-06, + "loss": 0.472, + "step": 9068 + }, + { + "epoch": 0.76, + "learning_rate": 2.8997707234706894e-06, + "loss": 0.4813, + "step": 9069 + }, + { + "epoch": 0.76, + "learning_rate": 2.8978627273325378e-06, + "loss": 0.4612, + "step": 9070 + }, + { + "epoch": 0.76, + "learning_rate": 2.8959552527458025e-06, + "loss": 0.4695, + "step": 9071 + }, + { + "epoch": 0.76, + "learning_rate": 2.8940482998505703e-06, + "loss": 0.4619, + "step": 9072 + }, + { + "epoch": 0.76, + "learning_rate": 2.892141868786871e-06, + "loss": 0.452, + "step": 9073 + }, + { + "epoch": 0.76, + "learning_rate": 2.8902359596947127e-06, + "loss": 0.4722, + "step": 9074 + }, + { + "epoch": 0.76, + "learning_rate": 2.8883305727140533e-06, + "loss": 0.442, + "step": 9075 + }, + { + "epoch": 0.76, + "learning_rate": 2.8864257079848166e-06, + "loss": 0.4708, + "step": 9076 + }, + { + "epoch": 0.76, + "learning_rate": 2.8845213656468896e-06, + "loss": 0.4646, + "step": 9077 + }, + { + "epoch": 0.76, + "learning_rate": 2.882617545840114e-06, + "loss": 0.4648, + "step": 9078 + }, + { + "epoch": 0.76, + "learning_rate": 2.8807142487043047e-06, + "loss": 0.4804, + "step": 9079 + }, + { + "epoch": 0.76, + "learning_rate": 2.8788114743792317e-06, + "loss": 0.46, + "step": 9080 + }, + { + "epoch": 0.76, + "learning_rate": 2.8769092230046236e-06, + "loss": 0.455, + "step": 9081 + }, + { + "epoch": 0.76, + "learning_rate": 2.875007494720171e-06, + "loss": 0.4514, + "step": 9082 + }, + { + "epoch": 0.76, + "learning_rate": 2.8731062896655383e-06, + "loss": 0.4745, + "step": 9083 + }, + { + "epoch": 0.76, + "learning_rate": 2.871205607980335e-06, + "loss": 0.4647, + "step": 9084 + }, + { + "epoch": 0.76, + "learning_rate": 2.8693054498041383e-06, + "loss": 0.4675, + "step": 9085 + }, + { + "epoch": 0.76, + "learning_rate": 2.867405815276494e-06, + "loss": 0.4572, + "step": 9086 + }, + { + "epoch": 0.76, + "learning_rate": 2.865506704536899e-06, + "loss": 0.4301, + "step": 9087 + }, + { + "epoch": 0.76, + "learning_rate": 2.8636081177248176e-06, + "loss": 0.4656, + "step": 9088 + }, + { + "epoch": 0.76, + "learning_rate": 2.861710054979674e-06, + "loss": 0.4682, + "step": 9089 + }, + { + "epoch": 0.76, + "learning_rate": 2.859812516440853e-06, + "loss": 0.4671, + "step": 9090 + }, + { + "epoch": 0.76, + "learning_rate": 2.8579155022477024e-06, + "loss": 0.4713, + "step": 9091 + }, + { + "epoch": 0.76, + "learning_rate": 2.856019012539528e-06, + "loss": 0.4732, + "step": 9092 + }, + { + "epoch": 0.76, + "learning_rate": 2.8541230474556035e-06, + "loss": 0.4658, + "step": 9093 + }, + { + "epoch": 0.76, + "learning_rate": 2.852227607135164e-06, + "loss": 0.4677, + "step": 9094 + }, + { + "epoch": 0.76, + "learning_rate": 2.850332691717399e-06, + "loss": 0.4676, + "step": 9095 + }, + { + "epoch": 0.76, + "learning_rate": 2.8484383013414627e-06, + "loss": 0.4892, + "step": 9096 + }, + { + "epoch": 0.76, + "learning_rate": 2.846544436146473e-06, + "loss": 0.4541, + "step": 9097 + }, + { + "epoch": 0.76, + "learning_rate": 2.8446510962715055e-06, + "loss": 0.464, + "step": 9098 + }, + { + "epoch": 0.76, + "learning_rate": 2.8427582818555976e-06, + "loss": 0.4755, + "step": 9099 + }, + { + "epoch": 0.76, + "learning_rate": 2.8408659930377556e-06, + "loss": 0.4582, + "step": 9100 + }, + { + "epoch": 0.76, + "learning_rate": 2.838974229956938e-06, + "loss": 0.4648, + "step": 9101 + }, + { + "epoch": 0.76, + "learning_rate": 2.837082992752067e-06, + "loss": 0.4542, + "step": 9102 + }, + { + "epoch": 0.76, + "learning_rate": 2.835192281562027e-06, + "loss": 0.4401, + "step": 9103 + }, + { + "epoch": 0.76, + "learning_rate": 2.8333020965256666e-06, + "loss": 0.4844, + "step": 9104 + }, + { + "epoch": 0.76, + "learning_rate": 2.8314124377817888e-06, + "loss": 0.4815, + "step": 9105 + }, + { + "epoch": 0.76, + "learning_rate": 2.8295233054691685e-06, + "loss": 0.479, + "step": 9106 + }, + { + "epoch": 0.76, + "learning_rate": 2.8276346997265324e-06, + "loss": 0.4473, + "step": 9107 + }, + { + "epoch": 0.76, + "learning_rate": 2.8257466206925723e-06, + "loss": 0.4676, + "step": 9108 + }, + { + "epoch": 0.76, + "learning_rate": 2.82385906850594e-06, + "loss": 0.4612, + "step": 9109 + }, + { + "epoch": 0.76, + "learning_rate": 2.82197204330525e-06, + "loss": 0.4752, + "step": 9110 + }, + { + "epoch": 0.76, + "learning_rate": 2.820085545229078e-06, + "loss": 0.4496, + "step": 9111 + }, + { + "epoch": 0.76, + "learning_rate": 2.8181995744159553e-06, + "loss": 0.4537, + "step": 9112 + }, + { + "epoch": 0.76, + "learning_rate": 2.8163141310043886e-06, + "loss": 0.4666, + "step": 9113 + }, + { + "epoch": 0.76, + "learning_rate": 2.81442921513283e-06, + "loss": 0.4734, + "step": 9114 + }, + { + "epoch": 0.76, + "learning_rate": 2.812544826939706e-06, + "loss": 0.4739, + "step": 9115 + }, + { + "epoch": 0.76, + "learning_rate": 2.8106609665633943e-06, + "loss": 0.4542, + "step": 9116 + }, + { + "epoch": 0.76, + "learning_rate": 2.808777634142239e-06, + "loss": 0.4808, + "step": 9117 + }, + { + "epoch": 0.76, + "learning_rate": 2.8068948298145437e-06, + "loss": 0.4737, + "step": 9118 + }, + { + "epoch": 0.76, + "learning_rate": 2.80501255371857e-06, + "loss": 0.453, + "step": 9119 + }, + { + "epoch": 0.76, + "learning_rate": 2.803130805992552e-06, + "loss": 0.4852, + "step": 9120 + }, + { + "epoch": 0.76, + "learning_rate": 2.8012495867746735e-06, + "loss": 0.4509, + "step": 9121 + }, + { + "epoch": 0.76, + "learning_rate": 2.799368896203084e-06, + "loss": 0.447, + "step": 9122 + }, + { + "epoch": 0.76, + "learning_rate": 2.7974887344158897e-06, + "loss": 0.4753, + "step": 9123 + }, + { + "epoch": 0.76, + "learning_rate": 2.7956091015511676e-06, + "loss": 0.4621, + "step": 9124 + }, + { + "epoch": 0.76, + "learning_rate": 2.793729997746948e-06, + "loss": 0.4722, + "step": 9125 + }, + { + "epoch": 0.76, + "learning_rate": 2.791851423141222e-06, + "loss": 0.4903, + "step": 9126 + }, + { + "epoch": 0.76, + "learning_rate": 2.7899733778719483e-06, + "loss": 0.4797, + "step": 9127 + }, + { + "epoch": 0.76, + "learning_rate": 2.7880958620770415e-06, + "loss": 0.4619, + "step": 9128 + }, + { + "epoch": 0.76, + "learning_rate": 2.7862188758943788e-06, + "loss": 0.4626, + "step": 9129 + }, + { + "epoch": 0.76, + "learning_rate": 2.7843424194617964e-06, + "loss": 0.4839, + "step": 9130 + }, + { + "epoch": 0.76, + "learning_rate": 2.7824664929170953e-06, + "loss": 0.4832, + "step": 9131 + }, + { + "epoch": 0.76, + "learning_rate": 2.7805910963980343e-06, + "loss": 0.5038, + "step": 9132 + }, + { + "epoch": 0.76, + "learning_rate": 2.778716230042333e-06, + "loss": 0.4822, + "step": 9133 + }, + { + "epoch": 0.76, + "learning_rate": 2.7768418939876794e-06, + "loss": 0.4542, + "step": 9134 + }, + { + "epoch": 0.76, + "learning_rate": 2.7749680883717102e-06, + "loss": 0.4602, + "step": 9135 + }, + { + "epoch": 0.76, + "learning_rate": 2.773094813332037e-06, + "loss": 0.4747, + "step": 9136 + }, + { + "epoch": 0.76, + "learning_rate": 2.7712220690062208e-06, + "loss": 0.4595, + "step": 9137 + }, + { + "epoch": 0.76, + "learning_rate": 2.769349855531789e-06, + "loss": 0.4627, + "step": 9138 + }, + { + "epoch": 0.76, + "learning_rate": 2.7674781730462273e-06, + "loss": 0.4563, + "step": 9139 + }, + { + "epoch": 0.76, + "learning_rate": 2.765607021686989e-06, + "loss": 0.4852, + "step": 9140 + }, + { + "epoch": 0.76, + "learning_rate": 2.7637364015914803e-06, + "loss": 0.4463, + "step": 9141 + }, + { + "epoch": 0.76, + "learning_rate": 2.7618663128970722e-06, + "loss": 0.4673, + "step": 9142 + }, + { + "epoch": 0.76, + "learning_rate": 2.759996755741098e-06, + "loss": 0.446, + "step": 9143 + }, + { + "epoch": 0.77, + "learning_rate": 2.7581277302608446e-06, + "loss": 0.4693, + "step": 9144 + }, + { + "epoch": 0.77, + "learning_rate": 2.7562592365935724e-06, + "loss": 0.4751, + "step": 9145 + }, + { + "epoch": 0.77, + "learning_rate": 2.75439127487649e-06, + "loss": 0.4539, + "step": 9146 + }, + { + "epoch": 0.77, + "learning_rate": 2.7525238452467783e-06, + "loss": 0.4628, + "step": 9147 + }, + { + "epoch": 0.77, + "learning_rate": 2.7506569478415713e-06, + "loss": 0.4756, + "step": 9148 + }, + { + "epoch": 0.77, + "learning_rate": 2.7487905827979654e-06, + "loss": 0.4652, + "step": 9149 + }, + { + "epoch": 0.77, + "learning_rate": 2.7469247502530194e-06, + "loss": 0.4361, + "step": 9150 + }, + { + "epoch": 0.77, + "learning_rate": 2.745059450343752e-06, + "loss": 0.4724, + "step": 9151 + }, + { + "epoch": 0.77, + "learning_rate": 2.7431946832071433e-06, + "loss": 0.4707, + "step": 9152 + }, + { + "epoch": 0.77, + "learning_rate": 2.7413304489801296e-06, + "loss": 0.4704, + "step": 9153 + }, + { + "epoch": 0.77, + "learning_rate": 2.7394667477996207e-06, + "loss": 0.4542, + "step": 9154 + }, + { + "epoch": 0.77, + "learning_rate": 2.737603579802471e-06, + "loss": 0.4505, + "step": 9155 + }, + { + "epoch": 0.77, + "learning_rate": 2.7357409451255113e-06, + "loss": 0.458, + "step": 9156 + }, + { + "epoch": 0.77, + "learning_rate": 2.733878843905523e-06, + "loss": 0.4673, + "step": 9157 + }, + { + "epoch": 0.77, + "learning_rate": 2.7320172762792497e-06, + "loss": 0.4914, + "step": 9158 + }, + { + "epoch": 0.77, + "learning_rate": 2.7301562423833985e-06, + "loss": 0.4658, + "step": 9159 + }, + { + "epoch": 0.77, + "learning_rate": 2.728295742354631e-06, + "loss": 0.449, + "step": 9160 + }, + { + "epoch": 0.77, + "learning_rate": 2.7264357763295822e-06, + "loss": 0.4757, + "step": 9161 + }, + { + "epoch": 0.77, + "learning_rate": 2.7245763444448383e-06, + "loss": 0.4689, + "step": 9162 + }, + { + "epoch": 0.77, + "learning_rate": 2.7227174468369454e-06, + "loss": 0.4551, + "step": 9163 + }, + { + "epoch": 0.77, + "learning_rate": 2.720859083642415e-06, + "loss": 0.4712, + "step": 9164 + }, + { + "epoch": 0.77, + "learning_rate": 2.7190012549977153e-06, + "loss": 0.4821, + "step": 9165 + }, + { + "epoch": 0.77, + "learning_rate": 2.7171439610392815e-06, + "loss": 0.4558, + "step": 9166 + }, + { + "epoch": 0.77, + "learning_rate": 2.7152872019035005e-06, + "loss": 0.4696, + "step": 9167 + }, + { + "epoch": 0.77, + "learning_rate": 2.7134309777267307e-06, + "loss": 0.4633, + "step": 9168 + }, + { + "epoch": 0.77, + "learning_rate": 2.711575288645284e-06, + "loss": 0.4628, + "step": 9169 + }, + { + "epoch": 0.77, + "learning_rate": 2.7097201347954318e-06, + "loss": 0.466, + "step": 9170 + }, + { + "epoch": 0.77, + "learning_rate": 2.7078655163134117e-06, + "loss": 0.4747, + "step": 9171 + }, + { + "epoch": 0.77, + "learning_rate": 2.706011433335417e-06, + "loss": 0.4617, + "step": 9172 + }, + { + "epoch": 0.77, + "learning_rate": 2.704157885997605e-06, + "loss": 0.4672, + "step": 9173 + }, + { + "epoch": 0.77, + "learning_rate": 2.702304874436089e-06, + "loss": 0.453, + "step": 9174 + }, + { + "epoch": 0.77, + "learning_rate": 2.7004523987869526e-06, + "loss": 0.4688, + "step": 9175 + }, + { + "epoch": 0.77, + "learning_rate": 2.698600459186228e-06, + "loss": 0.4595, + "step": 9176 + }, + { + "epoch": 0.77, + "learning_rate": 2.6967490557699196e-06, + "loss": 0.4421, + "step": 9177 + }, + { + "epoch": 0.77, + "learning_rate": 2.6948981886739846e-06, + "loss": 0.4677, + "step": 9178 + }, + { + "epoch": 0.77, + "learning_rate": 2.693047858034342e-06, + "loss": 0.4797, + "step": 9179 + }, + { + "epoch": 0.77, + "learning_rate": 2.6911980639868696e-06, + "loss": 0.4518, + "step": 9180 + }, + { + "epoch": 0.77, + "learning_rate": 2.6893488066674154e-06, + "loss": 0.4681, + "step": 9181 + }, + { + "epoch": 0.77, + "learning_rate": 2.687500086211777e-06, + "loss": 0.4684, + "step": 9182 + }, + { + "epoch": 0.77, + "learning_rate": 2.685651902755717e-06, + "loss": 0.465, + "step": 9183 + }, + { + "epoch": 0.77, + "learning_rate": 2.6838042564349597e-06, + "loss": 0.4633, + "step": 9184 + }, + { + "epoch": 0.77, + "learning_rate": 2.6819571473851836e-06, + "loss": 0.4565, + "step": 9185 + }, + { + "epoch": 0.77, + "learning_rate": 2.6801105757420397e-06, + "loss": 0.4577, + "step": 9186 + }, + { + "epoch": 0.77, + "learning_rate": 2.6782645416411267e-06, + "loss": 0.4726, + "step": 9187 + }, + { + "epoch": 0.77, + "learning_rate": 2.676419045218016e-06, + "loss": 0.4555, + "step": 9188 + }, + { + "epoch": 0.77, + "learning_rate": 2.674574086608228e-06, + "loss": 0.4847, + "step": 9189 + }, + { + "epoch": 0.77, + "learning_rate": 2.672729665947251e-06, + "loss": 0.4464, + "step": 9190 + }, + { + "epoch": 0.77, + "learning_rate": 2.6708857833705315e-06, + "loss": 0.4601, + "step": 9191 + }, + { + "epoch": 0.77, + "learning_rate": 2.669042439013476e-06, + "loss": 0.4795, + "step": 9192 + }, + { + "epoch": 0.77, + "learning_rate": 2.6671996330114514e-06, + "loss": 0.4571, + "step": 9193 + }, + { + "epoch": 0.77, + "learning_rate": 2.6653573654997835e-06, + "loss": 0.4686, + "step": 9194 + }, + { + "epoch": 0.77, + "learning_rate": 2.6635156366137672e-06, + "loss": 0.4599, + "step": 9195 + }, + { + "epoch": 0.77, + "learning_rate": 2.6616744464886437e-06, + "loss": 0.4802, + "step": 9196 + }, + { + "epoch": 0.77, + "learning_rate": 2.65983379525963e-06, + "loss": 0.4669, + "step": 9197 + }, + { + "epoch": 0.77, + "learning_rate": 2.6579936830618926e-06, + "loss": 0.4458, + "step": 9198 + }, + { + "epoch": 0.77, + "learning_rate": 2.656154110030561e-06, + "loss": 0.466, + "step": 9199 + }, + { + "epoch": 0.77, + "learning_rate": 2.6543150763007265e-06, + "loss": 0.4608, + "step": 9200 + }, + { + "epoch": 0.77, + "learning_rate": 2.652476582007436e-06, + "loss": 0.4676, + "step": 9201 + }, + { + "epoch": 0.77, + "learning_rate": 2.6506386272857086e-06, + "loss": 0.4696, + "step": 9202 + }, + { + "epoch": 0.77, + "learning_rate": 2.648801212270512e-06, + "loss": 0.463, + "step": 9203 + }, + { + "epoch": 0.77, + "learning_rate": 2.646964337096778e-06, + "loss": 0.4484, + "step": 9204 + }, + { + "epoch": 0.77, + "learning_rate": 2.6451280018993996e-06, + "loss": 0.4569, + "step": 9205 + }, + { + "epoch": 0.77, + "learning_rate": 2.643292206813227e-06, + "loss": 0.4825, + "step": 9206 + }, + { + "epoch": 0.77, + "learning_rate": 2.6414569519730793e-06, + "loss": 0.4526, + "step": 9207 + }, + { + "epoch": 0.77, + "learning_rate": 2.6396222375137227e-06, + "loss": 0.4555, + "step": 9208 + }, + { + "epoch": 0.77, + "learning_rate": 2.6377880635698973e-06, + "loss": 0.4824, + "step": 9209 + }, + { + "epoch": 0.77, + "learning_rate": 2.635954430276296e-06, + "loss": 0.4683, + "step": 9210 + }, + { + "epoch": 0.77, + "learning_rate": 2.634121337767571e-06, + "loss": 0.4648, + "step": 9211 + }, + { + "epoch": 0.77, + "learning_rate": 2.6322887861783385e-06, + "loss": 0.4767, + "step": 9212 + }, + { + "epoch": 0.77, + "learning_rate": 2.630456775643173e-06, + "loss": 0.4557, + "step": 9213 + }, + { + "epoch": 0.77, + "learning_rate": 2.6286253062966096e-06, + "loss": 0.4721, + "step": 9214 + }, + { + "epoch": 0.77, + "learning_rate": 2.6267943782731407e-06, + "loss": 0.4695, + "step": 9215 + }, + { + "epoch": 0.77, + "learning_rate": 2.624963991707228e-06, + "loss": 0.4559, + "step": 9216 + }, + { + "epoch": 0.77, + "learning_rate": 2.6231341467332827e-06, + "loss": 0.477, + "step": 9217 + }, + { + "epoch": 0.77, + "learning_rate": 2.6213048434856846e-06, + "loss": 0.4626, + "step": 9218 + }, + { + "epoch": 0.77, + "learning_rate": 2.61947608209877e-06, + "loss": 0.4592, + "step": 9219 + }, + { + "epoch": 0.77, + "learning_rate": 2.6176478627068324e-06, + "loss": 0.5004, + "step": 9220 + }, + { + "epoch": 0.77, + "learning_rate": 2.615820185444128e-06, + "loss": 0.488, + "step": 9221 + }, + { + "epoch": 0.77, + "learning_rate": 2.6139930504448785e-06, + "loss": 0.4704, + "step": 9222 + }, + { + "epoch": 0.77, + "learning_rate": 2.6121664578432593e-06, + "loss": 0.4755, + "step": 9223 + }, + { + "epoch": 0.77, + "learning_rate": 2.6103404077734075e-06, + "loss": 0.4581, + "step": 9224 + }, + { + "epoch": 0.77, + "learning_rate": 2.60851490036942e-06, + "loss": 0.4553, + "step": 9225 + }, + { + "epoch": 0.77, + "learning_rate": 2.606689935765351e-06, + "loss": 0.4777, + "step": 9226 + }, + { + "epoch": 0.77, + "learning_rate": 2.604865514095225e-06, + "loss": 0.4676, + "step": 9227 + }, + { + "epoch": 0.77, + "learning_rate": 2.6030416354930154e-06, + "loss": 0.4463, + "step": 9228 + }, + { + "epoch": 0.77, + "learning_rate": 2.6012183000926638e-06, + "loss": 0.4546, + "step": 9229 + }, + { + "epoch": 0.77, + "learning_rate": 2.5993955080280663e-06, + "loss": 0.483, + "step": 9230 + }, + { + "epoch": 0.77, + "learning_rate": 2.5975732594330816e-06, + "loss": 0.4715, + "step": 9231 + }, + { + "epoch": 0.77, + "learning_rate": 2.595751554441527e-06, + "loss": 0.4556, + "step": 9232 + }, + { + "epoch": 0.77, + "learning_rate": 2.5939303931871827e-06, + "loss": 0.4788, + "step": 9233 + }, + { + "epoch": 0.77, + "learning_rate": 2.592109775803785e-06, + "loss": 0.4724, + "step": 9234 + }, + { + "epoch": 0.77, + "learning_rate": 2.590289702425032e-06, + "loss": 0.4611, + "step": 9235 + }, + { + "epoch": 0.77, + "learning_rate": 2.5884701731845862e-06, + "loss": 0.4714, + "step": 9236 + }, + { + "epoch": 0.77, + "learning_rate": 2.5866511882160604e-06, + "loss": 0.4642, + "step": 9237 + }, + { + "epoch": 0.77, + "learning_rate": 2.584832747653041e-06, + "loss": 0.4718, + "step": 9238 + }, + { + "epoch": 0.77, + "learning_rate": 2.583014851629062e-06, + "loss": 0.4696, + "step": 9239 + }, + { + "epoch": 0.77, + "learning_rate": 2.5811975002776233e-06, + "loss": 0.4488, + "step": 9240 + }, + { + "epoch": 0.77, + "learning_rate": 2.579380693732183e-06, + "loss": 0.4678, + "step": 9241 + }, + { + "epoch": 0.77, + "learning_rate": 2.577564432126156e-06, + "loss": 0.4598, + "step": 9242 + }, + { + "epoch": 0.77, + "learning_rate": 2.5757487155929285e-06, + "loss": 0.482, + "step": 9243 + }, + { + "epoch": 0.77, + "learning_rate": 2.573933544265835e-06, + "loss": 0.4572, + "step": 9244 + }, + { + "epoch": 0.77, + "learning_rate": 2.572118918278176e-06, + "loss": 0.4634, + "step": 9245 + }, + { + "epoch": 0.77, + "learning_rate": 2.570304837763208e-06, + "loss": 0.4784, + "step": 9246 + }, + { + "epoch": 0.77, + "learning_rate": 2.568491302854147e-06, + "loss": 0.458, + "step": 9247 + }, + { + "epoch": 0.77, + "learning_rate": 2.5666783136841777e-06, + "loss": 0.4777, + "step": 9248 + }, + { + "epoch": 0.77, + "learning_rate": 2.564865870386433e-06, + "loss": 0.4558, + "step": 9249 + }, + { + "epoch": 0.77, + "learning_rate": 2.5630539730940163e-06, + "loss": 0.4666, + "step": 9250 + }, + { + "epoch": 0.77, + "learning_rate": 2.5612426219399834e-06, + "loss": 0.4487, + "step": 9251 + }, + { + "epoch": 0.77, + "learning_rate": 2.5594318170573527e-06, + "loss": 0.4581, + "step": 9252 + }, + { + "epoch": 0.77, + "learning_rate": 2.5576215585791007e-06, + "loss": 0.4659, + "step": 9253 + }, + { + "epoch": 0.77, + "learning_rate": 2.5558118466381675e-06, + "loss": 0.4502, + "step": 9254 + }, + { + "epoch": 0.77, + "learning_rate": 2.5540026813674458e-06, + "loss": 0.4941, + "step": 9255 + }, + { + "epoch": 0.77, + "learning_rate": 2.5521940628998e-06, + "loss": 0.4728, + "step": 9256 + }, + { + "epoch": 0.77, + "learning_rate": 2.550385991368044e-06, + "loss": 0.4579, + "step": 9257 + }, + { + "epoch": 0.77, + "learning_rate": 2.548578466904953e-06, + "loss": 0.4819, + "step": 9258 + }, + { + "epoch": 0.77, + "learning_rate": 2.5467714896432704e-06, + "loss": 0.4623, + "step": 9259 + }, + { + "epoch": 0.77, + "learning_rate": 2.5449650597156884e-06, + "loss": 0.4512, + "step": 9260 + }, + { + "epoch": 0.77, + "learning_rate": 2.5431591772548647e-06, + "loss": 0.469, + "step": 9261 + }, + { + "epoch": 0.77, + "learning_rate": 2.5413538423934125e-06, + "loss": 0.4628, + "step": 9262 + }, + { + "epoch": 0.77, + "learning_rate": 2.5395490552639145e-06, + "loss": 0.4641, + "step": 9263 + }, + { + "epoch": 0.78, + "learning_rate": 2.5377448159989037e-06, + "loss": 0.458, + "step": 9264 + }, + { + "epoch": 0.78, + "learning_rate": 2.5359411247308753e-06, + "loss": 0.4823, + "step": 9265 + }, + { + "epoch": 0.78, + "learning_rate": 2.5341379815922853e-06, + "loss": 0.467, + "step": 9266 + }, + { + "epoch": 0.78, + "learning_rate": 2.5323353867155465e-06, + "loss": 0.4686, + "step": 9267 + }, + { + "epoch": 0.78, + "learning_rate": 2.53053334023304e-06, + "loss": 0.4559, + "step": 9268 + }, + { + "epoch": 0.78, + "learning_rate": 2.5287318422770934e-06, + "loss": 0.4608, + "step": 9269 + }, + { + "epoch": 0.78, + "learning_rate": 2.5269308929800084e-06, + "loss": 0.4619, + "step": 9270 + }, + { + "epoch": 0.78, + "learning_rate": 2.525130492474035e-06, + "loss": 0.4805, + "step": 9271 + }, + { + "epoch": 0.78, + "learning_rate": 2.523330640891388e-06, + "loss": 0.4584, + "step": 9272 + }, + { + "epoch": 0.78, + "learning_rate": 2.5215313383642414e-06, + "loss": 0.4771, + "step": 9273 + }, + { + "epoch": 0.78, + "learning_rate": 2.519732585024729e-06, + "loss": 0.4555, + "step": 9274 + }, + { + "epoch": 0.78, + "learning_rate": 2.5179343810049418e-06, + "loss": 0.466, + "step": 9275 + }, + { + "epoch": 0.78, + "learning_rate": 2.5161367264369296e-06, + "loss": 0.4694, + "step": 9276 + }, + { + "epoch": 0.78, + "learning_rate": 2.5143396214527127e-06, + "loss": 0.4603, + "step": 9277 + }, + { + "epoch": 0.78, + "learning_rate": 2.5125430661842587e-06, + "loss": 0.4644, + "step": 9278 + }, + { + "epoch": 0.78, + "learning_rate": 2.5107470607634956e-06, + "loss": 0.4647, + "step": 9279 + }, + { + "epoch": 0.78, + "learning_rate": 2.5089516053223216e-06, + "loss": 0.4704, + "step": 9280 + }, + { + "epoch": 0.78, + "learning_rate": 2.5071566999925833e-06, + "loss": 0.4869, + "step": 9281 + }, + { + "epoch": 0.78, + "learning_rate": 2.5053623449060927e-06, + "loss": 0.4826, + "step": 9282 + }, + { + "epoch": 0.78, + "learning_rate": 2.5035685401946163e-06, + "loss": 0.4694, + "step": 9283 + }, + { + "epoch": 0.78, + "learning_rate": 2.5017752859898892e-06, + "loss": 0.4598, + "step": 9284 + }, + { + "epoch": 0.78, + "learning_rate": 2.499982582423597e-06, + "loss": 0.4522, + "step": 9285 + }, + { + "epoch": 0.78, + "learning_rate": 2.4981904296273884e-06, + "loss": 0.4609, + "step": 9286 + }, + { + "epoch": 0.78, + "learning_rate": 2.4963988277328733e-06, + "loss": 0.4702, + "step": 9287 + }, + { + "epoch": 0.78, + "learning_rate": 2.494607776871616e-06, + "loss": 0.4667, + "step": 9288 + }, + { + "epoch": 0.78, + "learning_rate": 2.492817277175148e-06, + "loss": 0.4737, + "step": 9289 + }, + { + "epoch": 0.78, + "learning_rate": 2.491027328774952e-06, + "loss": 0.4664, + "step": 9290 + }, + { + "epoch": 0.78, + "learning_rate": 2.4892379318024806e-06, + "loss": 0.4345, + "step": 9291 + }, + { + "epoch": 0.78, + "learning_rate": 2.4874490863891355e-06, + "loss": 0.4877, + "step": 9292 + }, + { + "epoch": 0.78, + "learning_rate": 2.485660792666281e-06, + "loss": 0.4726, + "step": 9293 + }, + { + "epoch": 0.78, + "learning_rate": 2.4838730507652455e-06, + "loss": 0.4508, + "step": 9294 + }, + { + "epoch": 0.78, + "learning_rate": 2.482085860817309e-06, + "loss": 0.4623, + "step": 9295 + }, + { + "epoch": 0.78, + "learning_rate": 2.480299222953716e-06, + "loss": 0.4561, + "step": 9296 + }, + { + "epoch": 0.78, + "learning_rate": 2.478513137305675e-06, + "loss": 0.4565, + "step": 9297 + }, + { + "epoch": 0.78, + "learning_rate": 2.4767276040043433e-06, + "loss": 0.4553, + "step": 9298 + }, + { + "epoch": 0.78, + "learning_rate": 2.4749426231808427e-06, + "loss": 0.4781, + "step": 9299 + }, + { + "epoch": 0.78, + "learning_rate": 2.4731581949662597e-06, + "loss": 0.4629, + "step": 9300 + }, + { + "epoch": 0.78, + "learning_rate": 2.4713743194916318e-06, + "loss": 0.4546, + "step": 9301 + }, + { + "epoch": 0.78, + "learning_rate": 2.4695909968879607e-06, + "loss": 0.466, + "step": 9302 + }, + { + "epoch": 0.78, + "learning_rate": 2.4678082272862025e-06, + "loss": 0.4552, + "step": 9303 + }, + { + "epoch": 0.78, + "learning_rate": 2.4660260108172816e-06, + "loss": 0.4513, + "step": 9304 + }, + { + "epoch": 0.78, + "learning_rate": 2.4642443476120746e-06, + "loss": 0.4539, + "step": 9305 + }, + { + "epoch": 0.78, + "learning_rate": 2.462463237801419e-06, + "loss": 0.4682, + "step": 9306 + }, + { + "epoch": 0.78, + "learning_rate": 2.460682681516112e-06, + "loss": 0.453, + "step": 9307 + }, + { + "epoch": 0.78, + "learning_rate": 2.4589026788869117e-06, + "loss": 0.4768, + "step": 9308 + }, + { + "epoch": 0.78, + "learning_rate": 2.4571232300445293e-06, + "loss": 0.4839, + "step": 9309 + }, + { + "epoch": 0.78, + "learning_rate": 2.4553443351196426e-06, + "loss": 0.4596, + "step": 9310 + }, + { + "epoch": 0.78, + "learning_rate": 2.453565994242891e-06, + "loss": 0.4595, + "step": 9311 + }, + { + "epoch": 0.78, + "learning_rate": 2.4517882075448663e-06, + "loss": 0.4475, + "step": 9312 + }, + { + "epoch": 0.78, + "learning_rate": 2.4500109751561187e-06, + "loss": 0.4539, + "step": 9313 + }, + { + "epoch": 0.78, + "learning_rate": 2.4482342972071626e-06, + "loss": 0.4622, + "step": 9314 + }, + { + "epoch": 0.78, + "learning_rate": 2.44645817382847e-06, + "loss": 0.4861, + "step": 9315 + }, + { + "epoch": 0.78, + "learning_rate": 2.444682605150471e-06, + "loss": 0.4707, + "step": 9316 + }, + { + "epoch": 0.78, + "learning_rate": 2.442907591303554e-06, + "loss": 0.479, + "step": 9317 + }, + { + "epoch": 0.78, + "learning_rate": 2.441133132418073e-06, + "loss": 0.4697, + "step": 9318 + }, + { + "epoch": 0.78, + "learning_rate": 2.4393592286243363e-06, + "loss": 0.4657, + "step": 9319 + }, + { + "epoch": 0.78, + "learning_rate": 2.4375858800526077e-06, + "loss": 0.4666, + "step": 9320 + }, + { + "epoch": 0.78, + "learning_rate": 2.43581308683312e-06, + "loss": 0.4637, + "step": 9321 + }, + { + "epoch": 0.78, + "learning_rate": 2.4340408490960575e-06, + "loss": 0.4706, + "step": 9322 + }, + { + "epoch": 0.78, + "learning_rate": 2.432269166971567e-06, + "loss": 0.4753, + "step": 9323 + }, + { + "epoch": 0.78, + "learning_rate": 2.4304980405897483e-06, + "loss": 0.4751, + "step": 9324 + }, + { + "epoch": 0.78, + "learning_rate": 2.4287274700806727e-06, + "loss": 0.4541, + "step": 9325 + }, + { + "epoch": 0.78, + "learning_rate": 2.42695745557436e-06, + "loss": 0.4487, + "step": 9326 + }, + { + "epoch": 0.78, + "learning_rate": 2.4251879972007943e-06, + "loss": 0.4575, + "step": 9327 + }, + { + "epoch": 0.78, + "learning_rate": 2.423419095089915e-06, + "loss": 0.4677, + "step": 9328 + }, + { + "epoch": 0.78, + "learning_rate": 2.4216507493716213e-06, + "loss": 0.4627, + "step": 9329 + }, + { + "epoch": 0.78, + "learning_rate": 2.4198829601757787e-06, + "loss": 0.4684, + "step": 9330 + }, + { + "epoch": 0.78, + "learning_rate": 2.418115727632201e-06, + "loss": 0.4892, + "step": 9331 + }, + { + "epoch": 0.78, + "learning_rate": 2.4163490518706713e-06, + "loss": 0.4636, + "step": 9332 + }, + { + "epoch": 0.78, + "learning_rate": 2.414582933020924e-06, + "loss": 0.459, + "step": 9333 + }, + { + "epoch": 0.78, + "learning_rate": 2.412817371212657e-06, + "loss": 0.4632, + "step": 9334 + }, + { + "epoch": 0.78, + "learning_rate": 2.4110523665755236e-06, + "loss": 0.4559, + "step": 9335 + }, + { + "epoch": 0.78, + "learning_rate": 2.4092879192391406e-06, + "loss": 0.4697, + "step": 9336 + }, + { + "epoch": 0.78, + "learning_rate": 2.407524029333077e-06, + "loss": 0.4719, + "step": 9337 + }, + { + "epoch": 0.78, + "learning_rate": 2.405760696986873e-06, + "loss": 0.4609, + "step": 9338 + }, + { + "epoch": 0.78, + "learning_rate": 2.403997922330016e-06, + "loss": 0.4663, + "step": 9339 + }, + { + "epoch": 0.78, + "learning_rate": 2.4022357054919545e-06, + "loss": 0.4537, + "step": 9340 + }, + { + "epoch": 0.78, + "learning_rate": 2.4004740466021047e-06, + "loss": 0.4711, + "step": 9341 + }, + { + "epoch": 0.78, + "learning_rate": 2.398712945789832e-06, + "loss": 0.4591, + "step": 9342 + }, + { + "epoch": 0.78, + "learning_rate": 2.3969524031844638e-06, + "loss": 0.4759, + "step": 9343 + }, + { + "epoch": 0.78, + "learning_rate": 2.3951924189152854e-06, + "loss": 0.4557, + "step": 9344 + }, + { + "epoch": 0.78, + "learning_rate": 2.3934329931115474e-06, + "loss": 0.4759, + "step": 9345 + }, + { + "epoch": 0.78, + "learning_rate": 2.391674125902452e-06, + "loss": 0.4565, + "step": 9346 + }, + { + "epoch": 0.78, + "learning_rate": 2.3899158174171644e-06, + "loss": 0.4823, + "step": 9347 + }, + { + "epoch": 0.78, + "learning_rate": 2.388158067784806e-06, + "loss": 0.4724, + "step": 9348 + }, + { + "epoch": 0.78, + "learning_rate": 2.3864008771344595e-06, + "loss": 0.4682, + "step": 9349 + }, + { + "epoch": 0.78, + "learning_rate": 2.3846442455951612e-06, + "loss": 0.4776, + "step": 9350 + }, + { + "epoch": 0.78, + "learning_rate": 2.3828881732959163e-06, + "loss": 0.4587, + "step": 9351 + }, + { + "epoch": 0.78, + "learning_rate": 2.381132660365684e-06, + "loss": 0.4814, + "step": 9352 + }, + { + "epoch": 0.78, + "learning_rate": 2.37937770693338e-06, + "loss": 0.4737, + "step": 9353 + }, + { + "epoch": 0.78, + "learning_rate": 2.3776233131278805e-06, + "loss": 0.447, + "step": 9354 + }, + { + "epoch": 0.78, + "learning_rate": 2.3758694790780214e-06, + "loss": 0.4658, + "step": 9355 + }, + { + "epoch": 0.78, + "learning_rate": 2.3741162049125964e-06, + "loss": 0.4719, + "step": 9356 + }, + { + "epoch": 0.78, + "learning_rate": 2.372363490760359e-06, + "loss": 0.4448, + "step": 9357 + }, + { + "epoch": 0.78, + "learning_rate": 2.3706113367500183e-06, + "loss": 0.4582, + "step": 9358 + }, + { + "epoch": 0.78, + "learning_rate": 2.36885974301025e-06, + "loss": 0.4683, + "step": 9359 + }, + { + "epoch": 0.78, + "learning_rate": 2.367108709669683e-06, + "loss": 0.4571, + "step": 9360 + }, + { + "epoch": 0.78, + "learning_rate": 2.3653582368569017e-06, + "loss": 0.4503, + "step": 9361 + }, + { + "epoch": 0.78, + "learning_rate": 2.3636083247004592e-06, + "loss": 0.4537, + "step": 9362 + }, + { + "epoch": 0.78, + "learning_rate": 2.3618589733288588e-06, + "loss": 0.4668, + "step": 9363 + }, + { + "epoch": 0.78, + "learning_rate": 2.3601101828705664e-06, + "loss": 0.4526, + "step": 9364 + }, + { + "epoch": 0.78, + "learning_rate": 2.358361953454004e-06, + "loss": 0.478, + "step": 9365 + }, + { + "epoch": 0.78, + "learning_rate": 2.356614285207557e-06, + "loss": 0.4649, + "step": 9366 + }, + { + "epoch": 0.78, + "learning_rate": 2.3548671782595655e-06, + "loss": 0.4418, + "step": 9367 + }, + { + "epoch": 0.78, + "learning_rate": 2.3531206327383305e-06, + "loss": 0.4629, + "step": 9368 + }, + { + "epoch": 0.78, + "learning_rate": 2.35137464877211e-06, + "loss": 0.4576, + "step": 9369 + }, + { + "epoch": 0.78, + "learning_rate": 2.3496292264891194e-06, + "loss": 0.4573, + "step": 9370 + }, + { + "epoch": 0.78, + "learning_rate": 2.3478843660175423e-06, + "loss": 0.4696, + "step": 9371 + }, + { + "epoch": 0.78, + "learning_rate": 2.346140067485506e-06, + "loss": 0.4837, + "step": 9372 + }, + { + "epoch": 0.78, + "learning_rate": 2.3443963310211105e-06, + "loss": 0.476, + "step": 9373 + }, + { + "epoch": 0.78, + "learning_rate": 2.342653156752408e-06, + "loss": 0.4577, + "step": 9374 + }, + { + "epoch": 0.78, + "learning_rate": 2.3409105448074067e-06, + "loss": 0.4761, + "step": 9375 + }, + { + "epoch": 0.78, + "learning_rate": 2.339168495314079e-06, + "loss": 0.4755, + "step": 9376 + }, + { + "epoch": 0.78, + "learning_rate": 2.3374270084003535e-06, + "loss": 0.4652, + "step": 9377 + }, + { + "epoch": 0.78, + "learning_rate": 2.3356860841941152e-06, + "loss": 0.4781, + "step": 9378 + }, + { + "epoch": 0.78, + "learning_rate": 2.3339457228232142e-06, + "loss": 0.4703, + "step": 9379 + }, + { + "epoch": 0.78, + "learning_rate": 2.332205924415455e-06, + "loss": 0.4699, + "step": 9380 + }, + { + "epoch": 0.78, + "learning_rate": 2.330466689098596e-06, + "loss": 0.4769, + "step": 9381 + }, + { + "epoch": 0.78, + "learning_rate": 2.328728017000367e-06, + "loss": 0.47, + "step": 9382 + }, + { + "epoch": 0.79, + "learning_rate": 2.3269899082484447e-06, + "loss": 0.4821, + "step": 9383 + }, + { + "epoch": 0.79, + "learning_rate": 2.325252362970469e-06, + "loss": 0.4785, + "step": 9384 + }, + { + "epoch": 0.79, + "learning_rate": 2.3235153812940357e-06, + "loss": 0.4489, + "step": 9385 + }, + { + "epoch": 0.79, + "learning_rate": 2.321778963346707e-06, + "loss": 0.4619, + "step": 9386 + }, + { + "epoch": 0.79, + "learning_rate": 2.3200431092559948e-06, + "loss": 0.4659, + "step": 9387 + }, + { + "epoch": 0.79, + "learning_rate": 2.3183078191493734e-06, + "loss": 0.4701, + "step": 9388 + }, + { + "epoch": 0.79, + "learning_rate": 2.3165730931542753e-06, + "loss": 0.4658, + "step": 9389 + }, + { + "epoch": 0.79, + "learning_rate": 2.3148389313980912e-06, + "loss": 0.4866, + "step": 9390 + }, + { + "epoch": 0.79, + "learning_rate": 2.3131053340081675e-06, + "loss": 0.4773, + "step": 9391 + }, + { + "epoch": 0.79, + "learning_rate": 2.3113723011118196e-06, + "loss": 0.4558, + "step": 9392 + }, + { + "epoch": 0.79, + "learning_rate": 2.3096398328363078e-06, + "loss": 0.4641, + "step": 9393 + }, + { + "epoch": 0.79, + "learning_rate": 2.3079079293088623e-06, + "loss": 0.4733, + "step": 9394 + }, + { + "epoch": 0.79, + "learning_rate": 2.3061765906566644e-06, + "loss": 0.4505, + "step": 9395 + }, + { + "epoch": 0.79, + "learning_rate": 2.304445817006857e-06, + "loss": 0.4527, + "step": 9396 + }, + { + "epoch": 0.79, + "learning_rate": 2.302715608486541e-06, + "loss": 0.4698, + "step": 9397 + }, + { + "epoch": 0.79, + "learning_rate": 2.300985965222775e-06, + "loss": 0.4587, + "step": 9398 + }, + { + "epoch": 0.79, + "learning_rate": 2.2992568873425746e-06, + "loss": 0.4571, + "step": 9399 + }, + { + "epoch": 0.79, + "learning_rate": 2.2975283749729205e-06, + "loss": 0.4801, + "step": 9400 + }, + { + "epoch": 0.79, + "learning_rate": 2.2958004282407466e-06, + "loss": 0.464, + "step": 9401 + }, + { + "epoch": 0.79, + "learning_rate": 2.2940730472729423e-06, + "loss": 0.4576, + "step": 9402 + }, + { + "epoch": 0.79, + "learning_rate": 2.292346232196364e-06, + "loss": 0.468, + "step": 9403 + }, + { + "epoch": 0.79, + "learning_rate": 2.2906199831378194e-06, + "loss": 0.4632, + "step": 9404 + }, + { + "epoch": 0.79, + "learning_rate": 2.288894300224076e-06, + "loss": 0.4746, + "step": 9405 + }, + { + "epoch": 0.79, + "learning_rate": 2.2871691835818642e-06, + "loss": 0.4696, + "step": 9406 + }, + { + "epoch": 0.79, + "learning_rate": 2.285444633337869e-06, + "loss": 0.4789, + "step": 9407 + }, + { + "epoch": 0.79, + "learning_rate": 2.2837206496187314e-06, + "loss": 0.4654, + "step": 9408 + }, + { + "epoch": 0.79, + "learning_rate": 2.281997232551055e-06, + "loss": 0.4687, + "step": 9409 + }, + { + "epoch": 0.79, + "learning_rate": 2.2802743822614003e-06, + "loss": 0.4548, + "step": 9410 + }, + { + "epoch": 0.79, + "learning_rate": 2.2785520988762833e-06, + "loss": 0.4527, + "step": 9411 + }, + { + "epoch": 0.79, + "learning_rate": 2.276830382522187e-06, + "loss": 0.4528, + "step": 9412 + }, + { + "epoch": 0.79, + "learning_rate": 2.275109233325542e-06, + "loss": 0.4684, + "step": 9413 + }, + { + "epoch": 0.79, + "learning_rate": 2.2733886514127466e-06, + "loss": 0.4661, + "step": 9414 + }, + { + "epoch": 0.79, + "learning_rate": 2.2716686369101525e-06, + "loss": 0.4706, + "step": 9415 + }, + { + "epoch": 0.79, + "learning_rate": 2.2699491899440683e-06, + "loss": 0.4721, + "step": 9416 + }, + { + "epoch": 0.79, + "learning_rate": 2.2682303106407645e-06, + "loss": 0.4519, + "step": 9417 + }, + { + "epoch": 0.79, + "learning_rate": 2.2665119991264673e-06, + "loss": 0.4758, + "step": 9418 + }, + { + "epoch": 0.79, + "learning_rate": 2.2647942555273592e-06, + "loss": 0.4432, + "step": 9419 + }, + { + "epoch": 0.79, + "learning_rate": 2.2630770799695922e-06, + "loss": 0.4654, + "step": 9420 + }, + { + "epoch": 0.79, + "learning_rate": 2.2613604725792636e-06, + "loss": 0.4654, + "step": 9421 + }, + { + "epoch": 0.79, + "learning_rate": 2.259644433482434e-06, + "loss": 0.4582, + "step": 9422 + }, + { + "epoch": 0.79, + "learning_rate": 2.2579289628051203e-06, + "loss": 0.4455, + "step": 9423 + }, + { + "epoch": 0.79, + "learning_rate": 2.256214060673305e-06, + "loss": 0.4711, + "step": 9424 + }, + { + "epoch": 0.79, + "learning_rate": 2.2544997272129197e-06, + "loss": 0.4694, + "step": 9425 + }, + { + "epoch": 0.79, + "learning_rate": 2.252785962549856e-06, + "loss": 0.4452, + "step": 9426 + }, + { + "epoch": 0.79, + "learning_rate": 2.2510727668099706e-06, + "loss": 0.4767, + "step": 9427 + }, + { + "epoch": 0.79, + "learning_rate": 2.2493601401190723e-06, + "loss": 0.4607, + "step": 9428 + }, + { + "epoch": 0.79, + "learning_rate": 2.247648082602927e-06, + "loss": 0.4478, + "step": 9429 + }, + { + "epoch": 0.79, + "learning_rate": 2.2459365943872613e-06, + "loss": 0.4754, + "step": 9430 + }, + { + "epoch": 0.79, + "learning_rate": 2.244225675597761e-06, + "loss": 0.4856, + "step": 9431 + }, + { + "epoch": 0.79, + "learning_rate": 2.242515326360066e-06, + "loss": 0.4694, + "step": 9432 + }, + { + "epoch": 0.79, + "learning_rate": 2.2408055467997823e-06, + "loss": 0.4513, + "step": 9433 + }, + { + "epoch": 0.79, + "learning_rate": 2.2390963370424635e-06, + "loss": 0.4721, + "step": 9434 + }, + { + "epoch": 0.79, + "learning_rate": 2.237387697213632e-06, + "loss": 0.4726, + "step": 9435 + }, + { + "epoch": 0.79, + "learning_rate": 2.2356796274387617e-06, + "loss": 0.4632, + "step": 9436 + }, + { + "epoch": 0.79, + "learning_rate": 2.2339721278432847e-06, + "loss": 0.4877, + "step": 9437 + }, + { + "epoch": 0.79, + "learning_rate": 2.2322651985525932e-06, + "loss": 0.4796, + "step": 9438 + }, + { + "epoch": 0.79, + "learning_rate": 2.2305588396920375e-06, + "loss": 0.4482, + "step": 9439 + }, + { + "epoch": 0.79, + "learning_rate": 2.228853051386922e-06, + "loss": 0.4621, + "step": 9440 + }, + { + "epoch": 0.79, + "learning_rate": 2.22714783376252e-06, + "loss": 0.4697, + "step": 9441 + }, + { + "epoch": 0.79, + "learning_rate": 2.2254431869440496e-06, + "loss": 0.4766, + "step": 9442 + }, + { + "epoch": 0.79, + "learning_rate": 2.223739111056692e-06, + "loss": 0.4686, + "step": 9443 + }, + { + "epoch": 0.79, + "learning_rate": 2.222035606225593e-06, + "loss": 0.46, + "step": 9444 + }, + { + "epoch": 0.79, + "learning_rate": 2.220332672575849e-06, + "loss": 0.4642, + "step": 9445 + }, + { + "epoch": 0.79, + "learning_rate": 2.2186303102325125e-06, + "loss": 0.4591, + "step": 9446 + }, + { + "epoch": 0.79, + "learning_rate": 2.2169285193206038e-06, + "loss": 0.4726, + "step": 9447 + }, + { + "epoch": 0.79, + "learning_rate": 2.2152272999650916e-06, + "loss": 0.4684, + "step": 9448 + }, + { + "epoch": 0.79, + "learning_rate": 2.2135266522909073e-06, + "loss": 0.491, + "step": 9449 + }, + { + "epoch": 0.79, + "learning_rate": 2.2118265764229396e-06, + "loss": 0.4728, + "step": 9450 + }, + { + "epoch": 0.79, + "learning_rate": 2.2101270724860345e-06, + "loss": 0.4598, + "step": 9451 + }, + { + "epoch": 0.79, + "learning_rate": 2.2084281406049966e-06, + "loss": 0.4708, + "step": 9452 + }, + { + "epoch": 0.79, + "learning_rate": 2.2067297809045863e-06, + "loss": 0.4778, + "step": 9453 + }, + { + "epoch": 0.79, + "learning_rate": 2.2050319935095254e-06, + "loss": 0.4637, + "step": 9454 + }, + { + "epoch": 0.79, + "learning_rate": 2.203334778544497e-06, + "loss": 0.4553, + "step": 9455 + }, + { + "epoch": 0.79, + "learning_rate": 2.201638136134132e-06, + "loss": 0.4488, + "step": 9456 + }, + { + "epoch": 0.79, + "learning_rate": 2.199942066403028e-06, + "loss": 0.4643, + "step": 9457 + }, + { + "epoch": 0.79, + "learning_rate": 2.198246569475735e-06, + "loss": 0.4453, + "step": 9458 + }, + { + "epoch": 0.79, + "learning_rate": 2.1965516454767645e-06, + "loss": 0.4703, + "step": 9459 + }, + { + "epoch": 0.79, + "learning_rate": 2.1948572945305813e-06, + "loss": 0.4579, + "step": 9460 + }, + { + "epoch": 0.79, + "learning_rate": 2.193163516761617e-06, + "loss": 0.4486, + "step": 9461 + }, + { + "epoch": 0.79, + "learning_rate": 2.1914703122942525e-06, + "loss": 0.4719, + "step": 9462 + }, + { + "epoch": 0.79, + "learning_rate": 2.1897776812528317e-06, + "loss": 0.4651, + "step": 9463 + }, + { + "epoch": 0.79, + "learning_rate": 2.188085623761649e-06, + "loss": 0.4757, + "step": 9464 + }, + { + "epoch": 0.79, + "learning_rate": 2.1863941399449685e-06, + "loss": 0.4875, + "step": 9465 + }, + { + "epoch": 0.79, + "learning_rate": 2.1847032299270032e-06, + "loss": 0.4704, + "step": 9466 + }, + { + "epoch": 0.79, + "learning_rate": 2.1830128938319238e-06, + "loss": 0.455, + "step": 9467 + }, + { + "epoch": 0.79, + "learning_rate": 2.1813231317838667e-06, + "loss": 0.4656, + "step": 9468 + }, + { + "epoch": 0.79, + "learning_rate": 2.179633943906918e-06, + "loss": 0.454, + "step": 9469 + }, + { + "epoch": 0.79, + "learning_rate": 2.1779453303251262e-06, + "loss": 0.4647, + "step": 9470 + }, + { + "epoch": 0.79, + "learning_rate": 2.176257291162495e-06, + "loss": 0.4512, + "step": 9471 + }, + { + "epoch": 0.79, + "learning_rate": 2.174569826542986e-06, + "loss": 0.473, + "step": 9472 + }, + { + "epoch": 0.79, + "learning_rate": 2.172882936590518e-06, + "loss": 0.4463, + "step": 9473 + }, + { + "epoch": 0.79, + "learning_rate": 2.1711966214289747e-06, + "loss": 0.4627, + "step": 9474 + }, + { + "epoch": 0.79, + "learning_rate": 2.1695108811821863e-06, + "loss": 0.4592, + "step": 9475 + }, + { + "epoch": 0.79, + "learning_rate": 2.1678257159739524e-06, + "loss": 0.4872, + "step": 9476 + }, + { + "epoch": 0.79, + "learning_rate": 2.1661411259280206e-06, + "loss": 0.4719, + "step": 9477 + }, + { + "epoch": 0.79, + "learning_rate": 2.1644571111681023e-06, + "loss": 0.4569, + "step": 9478 + }, + { + "epoch": 0.79, + "learning_rate": 2.1627736718178626e-06, + "loss": 0.4524, + "step": 9479 + }, + { + "epoch": 0.79, + "learning_rate": 2.161090808000924e-06, + "loss": 0.4584, + "step": 9480 + }, + { + "epoch": 0.79, + "learning_rate": 2.1594085198408756e-06, + "loss": 0.4599, + "step": 9481 + }, + { + "epoch": 0.79, + "learning_rate": 2.1577268074612535e-06, + "loss": 0.4763, + "step": 9482 + }, + { + "epoch": 0.79, + "learning_rate": 2.156045670985556e-06, + "loss": 0.4584, + "step": 9483 + }, + { + "epoch": 0.79, + "learning_rate": 2.1543651105372352e-06, + "loss": 0.4735, + "step": 9484 + }, + { + "epoch": 0.79, + "learning_rate": 2.152685126239713e-06, + "loss": 0.4688, + "step": 9485 + }, + { + "epoch": 0.79, + "learning_rate": 2.1510057182163547e-06, + "loss": 0.4492, + "step": 9486 + }, + { + "epoch": 0.79, + "learning_rate": 2.1493268865904872e-06, + "loss": 0.4916, + "step": 9487 + }, + { + "epoch": 0.79, + "learning_rate": 2.1476486314854027e-06, + "loss": 0.4659, + "step": 9488 + }, + { + "epoch": 0.79, + "learning_rate": 2.1459709530243423e-06, + "loss": 0.4438, + "step": 9489 + }, + { + "epoch": 0.79, + "learning_rate": 2.144293851330508e-06, + "loss": 0.4826, + "step": 9490 + }, + { + "epoch": 0.79, + "learning_rate": 2.1426173265270578e-06, + "loss": 0.4829, + "step": 9491 + }, + { + "epoch": 0.79, + "learning_rate": 2.1409413787371114e-06, + "loss": 0.4722, + "step": 9492 + }, + { + "epoch": 0.79, + "learning_rate": 2.13926600808374e-06, + "loss": 0.4796, + "step": 9493 + }, + { + "epoch": 0.79, + "learning_rate": 2.1375912146899767e-06, + "loss": 0.4647, + "step": 9494 + }, + { + "epoch": 0.79, + "learning_rate": 2.135916998678812e-06, + "loss": 0.4497, + "step": 9495 + }, + { + "epoch": 0.79, + "learning_rate": 2.134243360173196e-06, + "loss": 0.4972, + "step": 9496 + }, + { + "epoch": 0.79, + "learning_rate": 2.1325702992960317e-06, + "loss": 0.4788, + "step": 9497 + }, + { + "epoch": 0.79, + "learning_rate": 2.130897816170181e-06, + "loss": 0.4516, + "step": 9498 + }, + { + "epoch": 0.79, + "learning_rate": 2.1292259109184654e-06, + "loss": 0.4556, + "step": 9499 + }, + { + "epoch": 0.79, + "learning_rate": 2.1275545836636625e-06, + "loss": 0.4519, + "step": 9500 + }, + { + "epoch": 0.79, + "learning_rate": 2.1258838345285027e-06, + "loss": 0.4905, + "step": 9501 + }, + { + "epoch": 0.79, + "learning_rate": 2.124213663635687e-06, + "loss": 0.4682, + "step": 9502 + }, + { + "epoch": 0.8, + "learning_rate": 2.1225440711078615e-06, + "loss": 0.4862, + "step": 9503 + }, + { + "epoch": 0.8, + "learning_rate": 2.120875057067635e-06, + "loss": 0.4761, + "step": 9504 + }, + { + "epoch": 0.8, + "learning_rate": 2.1192066216375695e-06, + "loss": 0.4625, + "step": 9505 + }, + { + "epoch": 0.8, + "learning_rate": 2.1175387649401935e-06, + "loss": 0.4456, + "step": 9506 + }, + { + "epoch": 0.8, + "learning_rate": 2.1158714870979856e-06, + "loss": 0.4596, + "step": 9507 + }, + { + "epoch": 0.8, + "learning_rate": 2.114204788233379e-06, + "loss": 0.4775, + "step": 9508 + }, + { + "epoch": 0.8, + "learning_rate": 2.1125386684687774e-06, + "loss": 0.4652, + "step": 9509 + }, + { + "epoch": 0.8, + "learning_rate": 2.110873127926529e-06, + "loss": 0.4516, + "step": 9510 + }, + { + "epoch": 0.8, + "learning_rate": 2.1092081667289454e-06, + "loss": 0.4667, + "step": 9511 + }, + { + "epoch": 0.8, + "learning_rate": 2.1075437849982937e-06, + "loss": 0.4646, + "step": 9512 + }, + { + "epoch": 0.8, + "learning_rate": 2.105879982856799e-06, + "loss": 0.473, + "step": 9513 + }, + { + "epoch": 0.8, + "learning_rate": 2.1042167604266415e-06, + "loss": 0.4532, + "step": 9514 + }, + { + "epoch": 0.8, + "learning_rate": 2.102554117829967e-06, + "loss": 0.4778, + "step": 9515 + }, + { + "epoch": 0.8, + "learning_rate": 2.100892055188867e-06, + "loss": 0.4789, + "step": 9516 + }, + { + "epoch": 0.8, + "learning_rate": 2.0992305726254026e-06, + "loss": 0.4668, + "step": 9517 + }, + { + "epoch": 0.8, + "learning_rate": 2.0975696702615823e-06, + "loss": 0.483, + "step": 9518 + }, + { + "epoch": 0.8, + "learning_rate": 2.0959093482193783e-06, + "loss": 0.4624, + "step": 9519 + }, + { + "epoch": 0.8, + "learning_rate": 2.094249606620715e-06, + "loss": 0.4581, + "step": 9520 + }, + { + "epoch": 0.8, + "learning_rate": 2.092590445587476e-06, + "loss": 0.4768, + "step": 9521 + }, + { + "epoch": 0.8, + "learning_rate": 2.0909318652415078e-06, + "loss": 0.4691, + "step": 9522 + }, + { + "epoch": 0.8, + "learning_rate": 2.0892738657046065e-06, + "loss": 0.4657, + "step": 9523 + }, + { + "epoch": 0.8, + "learning_rate": 2.0876164470985305e-06, + "loss": 0.4549, + "step": 9524 + }, + { + "epoch": 0.8, + "learning_rate": 2.0859596095449886e-06, + "loss": 0.4605, + "step": 9525 + }, + { + "epoch": 0.8, + "learning_rate": 2.0843033531656596e-06, + "loss": 0.4536, + "step": 9526 + }, + { + "epoch": 0.8, + "learning_rate": 2.0826476780821683e-06, + "loss": 0.4656, + "step": 9527 + }, + { + "epoch": 0.8, + "learning_rate": 2.080992584416097e-06, + "loss": 0.4637, + "step": 9528 + }, + { + "epoch": 0.8, + "learning_rate": 2.079338072288997e-06, + "loss": 0.4756, + "step": 9529 + }, + { + "epoch": 0.8, + "learning_rate": 2.0776841418223635e-06, + "loss": 0.4659, + "step": 9530 + }, + { + "epoch": 0.8, + "learning_rate": 2.0760307931376555e-06, + "loss": 0.4654, + "step": 9531 + }, + { + "epoch": 0.8, + "learning_rate": 2.0743780263562884e-06, + "loss": 0.4624, + "step": 9532 + }, + { + "epoch": 0.8, + "learning_rate": 2.0727258415996334e-06, + "loss": 0.4591, + "step": 9533 + }, + { + "epoch": 0.8, + "learning_rate": 2.0710742389890205e-06, + "loss": 0.4664, + "step": 9534 + }, + { + "epoch": 0.8, + "learning_rate": 2.069423218645734e-06, + "loss": 0.4513, + "step": 9535 + }, + { + "epoch": 0.8, + "learning_rate": 2.067772780691023e-06, + "loss": 0.4584, + "step": 9536 + }, + { + "epoch": 0.8, + "learning_rate": 2.0661229252460835e-06, + "loss": 0.4804, + "step": 9537 + }, + { + "epoch": 0.8, + "learning_rate": 2.064473652432081e-06, + "loss": 0.4685, + "step": 9538 + }, + { + "epoch": 0.8, + "learning_rate": 2.0628249623701255e-06, + "loss": 0.457, + "step": 9539 + }, + { + "epoch": 0.8, + "learning_rate": 2.061176855181293e-06, + "loss": 0.4696, + "step": 9540 + }, + { + "epoch": 0.8, + "learning_rate": 2.0595293309866107e-06, + "loss": 0.4725, + "step": 9541 + }, + { + "epoch": 0.8, + "learning_rate": 2.0578823899070653e-06, + "loss": 0.4579, + "step": 9542 + }, + { + "epoch": 0.8, + "learning_rate": 2.0562360320636064e-06, + "loss": 0.4803, + "step": 9543 + }, + { + "epoch": 0.8, + "learning_rate": 2.0545902575771326e-06, + "loss": 0.4821, + "step": 9544 + }, + { + "epoch": 0.8, + "learning_rate": 2.0529450665685023e-06, + "loss": 0.4638, + "step": 9545 + }, + { + "epoch": 0.8, + "learning_rate": 2.0513004591585305e-06, + "loss": 0.4593, + "step": 9546 + }, + { + "epoch": 0.8, + "learning_rate": 2.049656435467994e-06, + "loss": 0.473, + "step": 9547 + }, + { + "epoch": 0.8, + "learning_rate": 2.04801299561762e-06, + "loss": 0.4585, + "step": 9548 + }, + { + "epoch": 0.8, + "learning_rate": 2.0463701397280953e-06, + "loss": 0.4658, + "step": 9549 + }, + { + "epoch": 0.8, + "learning_rate": 2.0447278679200676e-06, + "loss": 0.4673, + "step": 9550 + }, + { + "epoch": 0.8, + "learning_rate": 2.0430861803141377e-06, + "loss": 0.4683, + "step": 9551 + }, + { + "epoch": 0.8, + "learning_rate": 2.0414450770308638e-06, + "loss": 0.4636, + "step": 9552 + }, + { + "epoch": 0.8, + "learning_rate": 2.03980455819076e-06, + "loss": 0.4777, + "step": 9553 + }, + { + "epoch": 0.8, + "learning_rate": 2.0381646239143017e-06, + "loss": 0.453, + "step": 9554 + }, + { + "epoch": 0.8, + "learning_rate": 2.0365252743219143e-06, + "loss": 0.4474, + "step": 9555 + }, + { + "epoch": 0.8, + "learning_rate": 2.034886509533991e-06, + "loss": 0.4671, + "step": 9556 + }, + { + "epoch": 0.8, + "learning_rate": 2.0332483296708693e-06, + "loss": 0.4719, + "step": 9557 + }, + { + "epoch": 0.8, + "learning_rate": 2.031610734852858e-06, + "loss": 0.4555, + "step": 9558 + }, + { + "epoch": 0.8, + "learning_rate": 2.029973725200212e-06, + "loss": 0.4698, + "step": 9559 + }, + { + "epoch": 0.8, + "learning_rate": 2.028337300833144e-06, + "loss": 0.4783, + "step": 9560 + }, + { + "epoch": 0.8, + "learning_rate": 2.0267014618718295e-06, + "loss": 0.4447, + "step": 9561 + }, + { + "epoch": 0.8, + "learning_rate": 2.0250662084363928e-06, + "loss": 0.4752, + "step": 9562 + }, + { + "epoch": 0.8, + "learning_rate": 2.023431540646926e-06, + "loss": 0.4757, + "step": 9563 + }, + { + "epoch": 0.8, + "learning_rate": 2.02179745862347e-06, + "loss": 0.4496, + "step": 9564 + }, + { + "epoch": 0.8, + "learning_rate": 2.0201639624860246e-06, + "loss": 0.4651, + "step": 9565 + }, + { + "epoch": 0.8, + "learning_rate": 2.0185310523545475e-06, + "loss": 0.4539, + "step": 9566 + }, + { + "epoch": 0.8, + "learning_rate": 2.0168987283489494e-06, + "loss": 0.4631, + "step": 9567 + }, + { + "epoch": 0.8, + "learning_rate": 2.0152669905891075e-06, + "loss": 0.4478, + "step": 9568 + }, + { + "epoch": 0.8, + "learning_rate": 2.013635839194844e-06, + "loss": 0.4758, + "step": 9569 + }, + { + "epoch": 0.8, + "learning_rate": 2.0120052742859497e-06, + "loss": 0.4786, + "step": 9570 + }, + { + "epoch": 0.8, + "learning_rate": 2.010375295982163e-06, + "loss": 0.4593, + "step": 9571 + }, + { + "epoch": 0.8, + "learning_rate": 2.0087459044031843e-06, + "loss": 0.466, + "step": 9572 + }, + { + "epoch": 0.8, + "learning_rate": 2.0071170996686674e-06, + "loss": 0.4639, + "step": 9573 + }, + { + "epoch": 0.8, + "learning_rate": 2.0054888818982254e-06, + "loss": 0.4788, + "step": 9574 + }, + { + "epoch": 0.8, + "learning_rate": 2.0038612512114285e-06, + "loss": 0.4549, + "step": 9575 + }, + { + "epoch": 0.8, + "learning_rate": 2.0022342077278014e-06, + "loss": 0.454, + "step": 9576 + }, + { + "epoch": 0.8, + "learning_rate": 2.00060775156683e-06, + "loss": 0.4759, + "step": 9577 + }, + { + "epoch": 0.8, + "learning_rate": 1.998981882847951e-06, + "loss": 0.4794, + "step": 9578 + }, + { + "epoch": 0.8, + "learning_rate": 1.9973566016905666e-06, + "loss": 0.4785, + "step": 9579 + }, + { + "epoch": 0.8, + "learning_rate": 1.995731908214028e-06, + "loss": 0.4464, + "step": 9580 + }, + { + "epoch": 0.8, + "learning_rate": 1.994107802537646e-06, + "loss": 0.4696, + "step": 9581 + }, + { + "epoch": 0.8, + "learning_rate": 1.9924842847806867e-06, + "loss": 0.4567, + "step": 9582 + }, + { + "epoch": 0.8, + "learning_rate": 1.9908613550623746e-06, + "loss": 0.4601, + "step": 9583 + }, + { + "epoch": 0.8, + "learning_rate": 1.9892390135018945e-06, + "loss": 0.4741, + "step": 9584 + }, + { + "epoch": 0.8, + "learning_rate": 1.987617260218382e-06, + "loss": 0.4543, + "step": 9585 + }, + { + "epoch": 0.8, + "learning_rate": 1.985996095330931e-06, + "loss": 0.4632, + "step": 9586 + }, + { + "epoch": 0.8, + "learning_rate": 1.984375518958592e-06, + "loss": 0.4491, + "step": 9587 + }, + { + "epoch": 0.8, + "learning_rate": 1.9827555312203785e-06, + "loss": 0.4767, + "step": 9588 + }, + { + "epoch": 0.8, + "learning_rate": 1.9811361322352517e-06, + "loss": 0.473, + "step": 9589 + }, + { + "epoch": 0.8, + "learning_rate": 1.9795173221221318e-06, + "loss": 0.4599, + "step": 9590 + }, + { + "epoch": 0.8, + "learning_rate": 1.9778991009999036e-06, + "loss": 0.482, + "step": 9591 + }, + { + "epoch": 0.8, + "learning_rate": 1.9762814689873987e-06, + "loss": 0.4809, + "step": 9592 + }, + { + "epoch": 0.8, + "learning_rate": 1.974664426203409e-06, + "loss": 0.4695, + "step": 9593 + }, + { + "epoch": 0.8, + "learning_rate": 1.973047972766684e-06, + "loss": 0.4676, + "step": 9594 + }, + { + "epoch": 0.8, + "learning_rate": 1.9714321087959296e-06, + "loss": 0.4593, + "step": 9595 + }, + { + "epoch": 0.8, + "learning_rate": 1.9698168344098056e-06, + "loss": 0.4615, + "step": 9596 + }, + { + "epoch": 0.8, + "learning_rate": 1.9682021497269357e-06, + "loss": 0.4768, + "step": 9597 + }, + { + "epoch": 0.8, + "learning_rate": 1.9665880548658888e-06, + "loss": 0.457, + "step": 9598 + }, + { + "epoch": 0.8, + "learning_rate": 1.9649745499452067e-06, + "loss": 0.4568, + "step": 9599 + }, + { + "epoch": 0.8, + "learning_rate": 1.9633616350833717e-06, + "loss": 0.4788, + "step": 9600 + }, + { + "epoch": 0.8, + "learning_rate": 1.961749310398833e-06, + "loss": 0.4911, + "step": 9601 + }, + { + "epoch": 0.8, + "learning_rate": 1.9601375760099895e-06, + "loss": 0.4736, + "step": 9602 + }, + { + "epoch": 0.8, + "learning_rate": 1.9585264320352003e-06, + "loss": 0.464, + "step": 9603 + }, + { + "epoch": 0.8, + "learning_rate": 1.9569158785927867e-06, + "loss": 0.4649, + "step": 9604 + }, + { + "epoch": 0.8, + "learning_rate": 1.955305915801016e-06, + "loss": 0.4484, + "step": 9605 + }, + { + "epoch": 0.8, + "learning_rate": 1.9536965437781186e-06, + "loss": 0.4635, + "step": 9606 + }, + { + "epoch": 0.8, + "learning_rate": 1.9520877626422794e-06, + "loss": 0.4572, + "step": 9607 + }, + { + "epoch": 0.8, + "learning_rate": 1.95047957251164e-06, + "loss": 0.4729, + "step": 9608 + }, + { + "epoch": 0.8, + "learning_rate": 1.9488719735043018e-06, + "loss": 0.4615, + "step": 9609 + }, + { + "epoch": 0.8, + "learning_rate": 1.9472649657383157e-06, + "loss": 0.4654, + "step": 9610 + }, + { + "epoch": 0.8, + "learning_rate": 1.9456585493317004e-06, + "loss": 0.4707, + "step": 9611 + }, + { + "epoch": 0.8, + "learning_rate": 1.94405272440242e-06, + "loss": 0.4773, + "step": 9612 + }, + { + "epoch": 0.8, + "learning_rate": 1.942447491068401e-06, + "loss": 0.4667, + "step": 9613 + }, + { + "epoch": 0.8, + "learning_rate": 1.940842849447524e-06, + "loss": 0.4603, + "step": 9614 + }, + { + "epoch": 0.8, + "learning_rate": 1.9392387996576277e-06, + "loss": 0.4447, + "step": 9615 + }, + { + "epoch": 0.8, + "learning_rate": 1.937635341816506e-06, + "loss": 0.4665, + "step": 9616 + }, + { + "epoch": 0.8, + "learning_rate": 1.9360324760419093e-06, + "loss": 0.4667, + "step": 9617 + }, + { + "epoch": 0.8, + "learning_rate": 1.934430202451549e-06, + "loss": 0.454, + "step": 9618 + }, + { + "epoch": 0.8, + "learning_rate": 1.9328285211630847e-06, + "loss": 0.4657, + "step": 9619 + }, + { + "epoch": 0.8, + "learning_rate": 1.9312274322941426e-06, + "loss": 0.4621, + "step": 9620 + }, + { + "epoch": 0.8, + "learning_rate": 1.9296269359622977e-06, + "loss": 0.457, + "step": 9621 + }, + { + "epoch": 0.81, + "learning_rate": 1.9280270322850836e-06, + "loss": 0.4572, + "step": 9622 + }, + { + "epoch": 0.81, + "learning_rate": 1.92642772137999e-06, + "loss": 0.4614, + "step": 9623 + }, + { + "epoch": 0.81, + "learning_rate": 1.9248290033644614e-06, + "loss": 0.4545, + "step": 9624 + }, + { + "epoch": 0.81, + "learning_rate": 1.9232308783559064e-06, + "loss": 0.4749, + "step": 9625 + }, + { + "epoch": 0.81, + "learning_rate": 1.9216333464716817e-06, + "loss": 0.4872, + "step": 9626 + }, + { + "epoch": 0.81, + "learning_rate": 1.9200364078291032e-06, + "loss": 0.4565, + "step": 9627 + }, + { + "epoch": 0.81, + "learning_rate": 1.9184400625454413e-06, + "loss": 0.4787, + "step": 9628 + }, + { + "epoch": 0.81, + "learning_rate": 1.916844310737931e-06, + "loss": 0.4553, + "step": 9629 + }, + { + "epoch": 0.81, + "learning_rate": 1.9152491525237504e-06, + "loss": 0.4542, + "step": 9630 + }, + { + "epoch": 0.81, + "learning_rate": 1.9136545880200484e-06, + "loss": 0.4756, + "step": 9631 + }, + { + "epoch": 0.81, + "learning_rate": 1.912060617343919e-06, + "loss": 0.4579, + "step": 9632 + }, + { + "epoch": 0.81, + "learning_rate": 1.910467240612419e-06, + "loss": 0.4656, + "step": 9633 + }, + { + "epoch": 0.81, + "learning_rate": 1.9088744579425567e-06, + "loss": 0.4556, + "step": 9634 + }, + { + "epoch": 0.81, + "learning_rate": 1.9072822694513016e-06, + "loss": 0.4717, + "step": 9635 + }, + { + "epoch": 0.81, + "learning_rate": 1.9056906752555759e-06, + "loss": 0.4633, + "step": 9636 + }, + { + "epoch": 0.81, + "learning_rate": 1.9040996754722574e-06, + "loss": 0.4566, + "step": 9637 + }, + { + "epoch": 0.81, + "learning_rate": 1.902509270218189e-06, + "loss": 0.4552, + "step": 9638 + }, + { + "epoch": 0.81, + "learning_rate": 1.9009194596101566e-06, + "loss": 0.4667, + "step": 9639 + }, + { + "epoch": 0.81, + "learning_rate": 1.8993302437649143e-06, + "loss": 0.4566, + "step": 9640 + }, + { + "epoch": 0.81, + "learning_rate": 1.8977416227991663e-06, + "loss": 0.4585, + "step": 9641 + }, + { + "epoch": 0.81, + "learning_rate": 1.896153596829574e-06, + "loss": 0.4518, + "step": 9642 + }, + { + "epoch": 0.81, + "learning_rate": 1.8945661659727555e-06, + "loss": 0.4677, + "step": 9643 + }, + { + "epoch": 0.81, + "learning_rate": 1.8929793303452814e-06, + "loss": 0.4731, + "step": 9644 + }, + { + "epoch": 0.81, + "learning_rate": 1.891393090063688e-06, + "loss": 0.4661, + "step": 9645 + }, + { + "epoch": 0.81, + "learning_rate": 1.8898074452444604e-06, + "loss": 0.4539, + "step": 9646 + }, + { + "epoch": 0.81, + "learning_rate": 1.8882223960040413e-06, + "loss": 0.4814, + "step": 9647 + }, + { + "epoch": 0.81, + "learning_rate": 1.8866379424588287e-06, + "loss": 0.4711, + "step": 9648 + }, + { + "epoch": 0.81, + "learning_rate": 1.8850540847251786e-06, + "loss": 0.4454, + "step": 9649 + }, + { + "epoch": 0.81, + "learning_rate": 1.8834708229194054e-06, + "loss": 0.4759, + "step": 9650 + }, + { + "epoch": 0.81, + "learning_rate": 1.8818881571577741e-06, + "loss": 0.4592, + "step": 9651 + }, + { + "epoch": 0.81, + "learning_rate": 1.8803060875565127e-06, + "loss": 0.4533, + "step": 9652 + }, + { + "epoch": 0.81, + "learning_rate": 1.8787246142318006e-06, + "loss": 0.484, + "step": 9653 + }, + { + "epoch": 0.81, + "learning_rate": 1.8771437372997736e-06, + "loss": 0.4713, + "step": 9654 + }, + { + "epoch": 0.81, + "learning_rate": 1.8755634568765246e-06, + "loss": 0.4474, + "step": 9655 + }, + { + "epoch": 0.81, + "learning_rate": 1.8739837730781029e-06, + "loss": 0.4372, + "step": 9656 + }, + { + "epoch": 0.81, + "learning_rate": 1.872404686020516e-06, + "loss": 0.4562, + "step": 9657 + }, + { + "epoch": 0.81, + "learning_rate": 1.8708261958197193e-06, + "loss": 0.4659, + "step": 9658 + }, + { + "epoch": 0.81, + "learning_rate": 1.8692483025916387e-06, + "loss": 0.4809, + "step": 9659 + }, + { + "epoch": 0.81, + "learning_rate": 1.8676710064521409e-06, + "loss": 0.4592, + "step": 9660 + }, + { + "epoch": 0.81, + "learning_rate": 1.8660943075170634e-06, + "loss": 0.4448, + "step": 9661 + }, + { + "epoch": 0.81, + "learning_rate": 1.864518205902187e-06, + "loss": 0.4631, + "step": 9662 + }, + { + "epoch": 0.81, + "learning_rate": 1.862942701723257e-06, + "loss": 0.4671, + "step": 9663 + }, + { + "epoch": 0.81, + "learning_rate": 1.8613677950959697e-06, + "loss": 0.4527, + "step": 9664 + }, + { + "epoch": 0.81, + "learning_rate": 1.8597934861359779e-06, + "loss": 0.4446, + "step": 9665 + }, + { + "epoch": 0.81, + "learning_rate": 1.858219774958897e-06, + "loss": 0.4743, + "step": 9666 + }, + { + "epoch": 0.81, + "learning_rate": 1.8566466616802914e-06, + "loss": 0.4744, + "step": 9667 + }, + { + "epoch": 0.81, + "learning_rate": 1.855074146415685e-06, + "loss": 0.4457, + "step": 9668 + }, + { + "epoch": 0.81, + "learning_rate": 1.8535022292805539e-06, + "loss": 0.4582, + "step": 9669 + }, + { + "epoch": 0.81, + "learning_rate": 1.851930910390337e-06, + "loss": 0.4666, + "step": 9670 + }, + { + "epoch": 0.81, + "learning_rate": 1.8503601898604207e-06, + "loss": 0.4709, + "step": 9671 + }, + { + "epoch": 0.81, + "learning_rate": 1.8487900678061588e-06, + "loss": 0.4568, + "step": 9672 + }, + { + "epoch": 0.81, + "learning_rate": 1.8472205443428504e-06, + "loss": 0.4638, + "step": 9673 + }, + { + "epoch": 0.81, + "learning_rate": 1.8456516195857543e-06, + "loss": 0.4657, + "step": 9674 + }, + { + "epoch": 0.81, + "learning_rate": 1.8440832936500875e-06, + "loss": 0.4578, + "step": 9675 + }, + { + "epoch": 0.81, + "learning_rate": 1.842515566651021e-06, + "loss": 0.4629, + "step": 9676 + }, + { + "epoch": 0.81, + "learning_rate": 1.8409484387036813e-06, + "loss": 0.4413, + "step": 9677 + }, + { + "epoch": 0.81, + "learning_rate": 1.8393819099231503e-06, + "loss": 0.4732, + "step": 9678 + }, + { + "epoch": 0.81, + "learning_rate": 1.837815980424471e-06, + "loss": 0.4708, + "step": 9679 + }, + { + "epoch": 0.81, + "learning_rate": 1.8362506503226374e-06, + "loss": 0.483, + "step": 9680 + }, + { + "epoch": 0.81, + "learning_rate": 1.8346859197325984e-06, + "loss": 0.4639, + "step": 9681 + }, + { + "epoch": 0.81, + "learning_rate": 1.8331217887692653e-06, + "loss": 0.4756, + "step": 9682 + }, + { + "epoch": 0.81, + "learning_rate": 1.8315582575475e-06, + "loss": 0.4638, + "step": 9683 + }, + { + "epoch": 0.81, + "learning_rate": 1.8299953261821202e-06, + "loss": 0.4641, + "step": 9684 + }, + { + "epoch": 0.81, + "learning_rate": 1.8284329947878999e-06, + "loss": 0.4882, + "step": 9685 + }, + { + "epoch": 0.81, + "learning_rate": 1.8268712634795749e-06, + "loss": 0.4464, + "step": 9686 + }, + { + "epoch": 0.81, + "learning_rate": 1.8253101323718303e-06, + "loss": 0.4501, + "step": 9687 + }, + { + "epoch": 0.81, + "learning_rate": 1.8237496015793077e-06, + "loss": 0.4642, + "step": 9688 + }, + { + "epoch": 0.81, + "learning_rate": 1.8221896712166075e-06, + "loss": 0.4618, + "step": 9689 + }, + { + "epoch": 0.81, + "learning_rate": 1.8206303413982806e-06, + "loss": 0.4548, + "step": 9690 + }, + { + "epoch": 0.81, + "learning_rate": 1.819071612238843e-06, + "loss": 0.4565, + "step": 9691 + }, + { + "epoch": 0.81, + "learning_rate": 1.8175134838527575e-06, + "loss": 0.4589, + "step": 9692 + }, + { + "epoch": 0.81, + "learning_rate": 1.8159559563544504e-06, + "loss": 0.4569, + "step": 9693 + }, + { + "epoch": 0.81, + "learning_rate": 1.814399029858298e-06, + "loss": 0.4753, + "step": 9694 + }, + { + "epoch": 0.81, + "learning_rate": 1.8128427044786345e-06, + "loss": 0.4571, + "step": 9695 + }, + { + "epoch": 0.81, + "learning_rate": 1.8112869803297494e-06, + "loss": 0.4539, + "step": 9696 + }, + { + "epoch": 0.81, + "learning_rate": 1.8097318575258894e-06, + "loss": 0.4814, + "step": 9697 + }, + { + "epoch": 0.81, + "learning_rate": 1.808177336181256e-06, + "loss": 0.4669, + "step": 9698 + }, + { + "epoch": 0.81, + "learning_rate": 1.8066234164100038e-06, + "loss": 0.4593, + "step": 9699 + }, + { + "epoch": 0.81, + "learning_rate": 1.8050700983262526e-06, + "loss": 0.4782, + "step": 9700 + }, + { + "epoch": 0.81, + "learning_rate": 1.8035173820440643e-06, + "loss": 0.4736, + "step": 9701 + }, + { + "epoch": 0.81, + "learning_rate": 1.8019652676774703e-06, + "loss": 0.4838, + "step": 9702 + }, + { + "epoch": 0.81, + "learning_rate": 1.8004137553404498e-06, + "loss": 0.4489, + "step": 9703 + }, + { + "epoch": 0.81, + "learning_rate": 1.798862845146938e-06, + "loss": 0.4896, + "step": 9704 + }, + { + "epoch": 0.81, + "learning_rate": 1.797312537210827e-06, + "loss": 0.4669, + "step": 9705 + }, + { + "epoch": 0.81, + "learning_rate": 1.795762831645964e-06, + "loss": 0.4614, + "step": 9706 + }, + { + "epoch": 0.81, + "learning_rate": 1.7942137285661576e-06, + "loss": 0.4606, + "step": 9707 + }, + { + "epoch": 0.81, + "learning_rate": 1.7926652280851642e-06, + "loss": 0.4639, + "step": 9708 + }, + { + "epoch": 0.81, + "learning_rate": 1.7911173303166985e-06, + "loss": 0.4593, + "step": 9709 + }, + { + "epoch": 0.81, + "learning_rate": 1.789570035374434e-06, + "loss": 0.4639, + "step": 9710 + }, + { + "epoch": 0.81, + "learning_rate": 1.7880233433719929e-06, + "loss": 0.4737, + "step": 9711 + }, + { + "epoch": 0.81, + "learning_rate": 1.7864772544229626e-06, + "loss": 0.4641, + "step": 9712 + }, + { + "epoch": 0.81, + "learning_rate": 1.7849317686408817e-06, + "loss": 0.4718, + "step": 9713 + }, + { + "epoch": 0.81, + "learning_rate": 1.7833868861392423e-06, + "loss": 0.4658, + "step": 9714 + }, + { + "epoch": 0.81, + "learning_rate": 1.7818426070314953e-06, + "loss": 0.4595, + "step": 9715 + }, + { + "epoch": 0.81, + "learning_rate": 1.7802989314310449e-06, + "loss": 0.4852, + "step": 9716 + }, + { + "epoch": 0.81, + "learning_rate": 1.7787558594512533e-06, + "loss": 0.4482, + "step": 9717 + }, + { + "epoch": 0.81, + "learning_rate": 1.7772133912054367e-06, + "loss": 0.4569, + "step": 9718 + }, + { + "epoch": 0.81, + "learning_rate": 1.7756715268068635e-06, + "loss": 0.4792, + "step": 9719 + }, + { + "epoch": 0.81, + "learning_rate": 1.7741302663687697e-06, + "loss": 0.4654, + "step": 9720 + }, + { + "epoch": 0.81, + "learning_rate": 1.7725896100043349e-06, + "loss": 0.4532, + "step": 9721 + }, + { + "epoch": 0.81, + "learning_rate": 1.7710495578266963e-06, + "loss": 0.4619, + "step": 9722 + }, + { + "epoch": 0.81, + "learning_rate": 1.7695101099489542e-06, + "loss": 0.4695, + "step": 9723 + }, + { + "epoch": 0.81, + "learning_rate": 1.7679712664841554e-06, + "loss": 0.465, + "step": 9724 + }, + { + "epoch": 0.81, + "learning_rate": 1.766433027545308e-06, + "loss": 0.4712, + "step": 9725 + }, + { + "epoch": 0.81, + "learning_rate": 1.7648953932453706e-06, + "loss": 0.4926, + "step": 9726 + }, + { + "epoch": 0.81, + "learning_rate": 1.763358363697265e-06, + "loss": 0.4681, + "step": 9727 + }, + { + "epoch": 0.81, + "learning_rate": 1.7618219390138635e-06, + "loss": 0.4721, + "step": 9728 + }, + { + "epoch": 0.81, + "learning_rate": 1.7602861193079922e-06, + "loss": 0.4555, + "step": 9729 + }, + { + "epoch": 0.81, + "learning_rate": 1.7587509046924378e-06, + "loss": 0.4666, + "step": 9730 + }, + { + "epoch": 0.81, + "learning_rate": 1.7572162952799366e-06, + "loss": 0.4645, + "step": 9731 + }, + { + "epoch": 0.81, + "learning_rate": 1.7556822911831882e-06, + "loss": 0.4613, + "step": 9732 + }, + { + "epoch": 0.81, + "learning_rate": 1.7541488925148397e-06, + "loss": 0.4739, + "step": 9733 + }, + { + "epoch": 0.81, + "learning_rate": 1.752616099387502e-06, + "loss": 0.455, + "step": 9734 + }, + { + "epoch": 0.81, + "learning_rate": 1.7510839119137347e-06, + "loss": 0.4624, + "step": 9735 + }, + { + "epoch": 0.81, + "learning_rate": 1.7495523302060546e-06, + "loss": 0.4691, + "step": 9736 + }, + { + "epoch": 0.81, + "learning_rate": 1.7480213543769343e-06, + "loss": 0.4729, + "step": 9737 + }, + { + "epoch": 0.81, + "learning_rate": 1.7464909845388045e-06, + "loss": 0.4682, + "step": 9738 + }, + { + "epoch": 0.81, + "learning_rate": 1.7449612208040479e-06, + "loss": 0.4588, + "step": 9739 + }, + { + "epoch": 0.81, + "learning_rate": 1.743432063285001e-06, + "loss": 0.464, + "step": 9740 + }, + { + "epoch": 0.81, + "learning_rate": 1.7419035120939642e-06, + "loss": 0.4633, + "step": 9741 + }, + { + "epoch": 0.82, + "learning_rate": 1.740375567343182e-06, + "loss": 0.4697, + "step": 9742 + }, + { + "epoch": 0.82, + "learning_rate": 1.7388482291448684e-06, + "loss": 0.4564, + "step": 9743 + }, + { + "epoch": 0.82, + "learning_rate": 1.7373214976111786e-06, + "loss": 0.4541, + "step": 9744 + }, + { + "epoch": 0.82, + "learning_rate": 1.735795372854231e-06, + "loss": 0.4673, + "step": 9745 + }, + { + "epoch": 0.82, + "learning_rate": 1.7342698549860958e-06, + "loss": 0.4842, + "step": 9746 + }, + { + "epoch": 0.82, + "learning_rate": 1.732744944118805e-06, + "loss": 0.459, + "step": 9747 + }, + { + "epoch": 0.82, + "learning_rate": 1.7312206403643395e-06, + "loss": 0.4632, + "step": 9748 + }, + { + "epoch": 0.82, + "learning_rate": 1.7296969438346378e-06, + "loss": 0.4745, + "step": 9749 + }, + { + "epoch": 0.82, + "learning_rate": 1.7281738546415938e-06, + "loss": 0.4645, + "step": 9750 + }, + { + "epoch": 0.82, + "learning_rate": 1.726651372897057e-06, + "loss": 0.4611, + "step": 9751 + }, + { + "epoch": 0.82, + "learning_rate": 1.7251294987128287e-06, + "loss": 0.4632, + "step": 9752 + }, + { + "epoch": 0.82, + "learning_rate": 1.723608232200673e-06, + "loss": 0.4493, + "step": 9753 + }, + { + "epoch": 0.82, + "learning_rate": 1.7220875734723063e-06, + "loss": 0.4455, + "step": 9754 + }, + { + "epoch": 0.82, + "learning_rate": 1.720567522639398e-06, + "loss": 0.4785, + "step": 9755 + }, + { + "epoch": 0.82, + "learning_rate": 1.7190480798135745e-06, + "loss": 0.4574, + "step": 9756 + }, + { + "epoch": 0.82, + "learning_rate": 1.7175292451064174e-06, + "loss": 0.4784, + "step": 9757 + }, + { + "epoch": 0.82, + "learning_rate": 1.716011018629462e-06, + "loss": 0.4608, + "step": 9758 + }, + { + "epoch": 0.82, + "learning_rate": 1.7144934004942027e-06, + "loss": 0.4531, + "step": 9759 + }, + { + "epoch": 0.82, + "learning_rate": 1.7129763908120823e-06, + "loss": 0.4734, + "step": 9760 + }, + { + "epoch": 0.82, + "learning_rate": 1.7114599896945105e-06, + "loss": 0.4574, + "step": 9761 + }, + { + "epoch": 0.82, + "learning_rate": 1.709944197252843e-06, + "loss": 0.4479, + "step": 9762 + }, + { + "epoch": 0.82, + "learning_rate": 1.7084290135983895e-06, + "loss": 0.4544, + "step": 9763 + }, + { + "epoch": 0.82, + "learning_rate": 1.7069144388424253e-06, + "loss": 0.4866, + "step": 9764 + }, + { + "epoch": 0.82, + "learning_rate": 1.7054004730961704e-06, + "loss": 0.4746, + "step": 9765 + }, + { + "epoch": 0.82, + "learning_rate": 1.7038871164708059e-06, + "loss": 0.4562, + "step": 9766 + }, + { + "epoch": 0.82, + "learning_rate": 1.7023743690774619e-06, + "loss": 0.4627, + "step": 9767 + }, + { + "epoch": 0.82, + "learning_rate": 1.7008622310272349e-06, + "loss": 0.4512, + "step": 9768 + }, + { + "epoch": 0.82, + "learning_rate": 1.6993507024311661e-06, + "loss": 0.4584, + "step": 9769 + }, + { + "epoch": 0.82, + "learning_rate": 1.697839783400258e-06, + "loss": 0.4578, + "step": 9770 + }, + { + "epoch": 0.82, + "learning_rate": 1.6963294740454638e-06, + "loss": 0.4818, + "step": 9771 + }, + { + "epoch": 0.82, + "learning_rate": 1.694819774477694e-06, + "loss": 0.4753, + "step": 9772 + }, + { + "epoch": 0.82, + "learning_rate": 1.6933106848078174e-06, + "loss": 0.4678, + "step": 9773 + }, + { + "epoch": 0.82, + "learning_rate": 1.691802205146652e-06, + "loss": 0.4589, + "step": 9774 + }, + { + "epoch": 0.82, + "learning_rate": 1.6902943356049796e-06, + "loss": 0.4672, + "step": 9775 + }, + { + "epoch": 0.82, + "learning_rate": 1.6887870762935276e-06, + "loss": 0.4603, + "step": 9776 + }, + { + "epoch": 0.82, + "learning_rate": 1.6872804273229838e-06, + "loss": 0.4586, + "step": 9777 + }, + { + "epoch": 0.82, + "learning_rate": 1.6857743888039902e-06, + "loss": 0.4551, + "step": 9778 + }, + { + "epoch": 0.82, + "learning_rate": 1.6842689608471451e-06, + "loss": 0.4649, + "step": 9779 + }, + { + "epoch": 0.82, + "learning_rate": 1.6827641435629983e-06, + "loss": 0.4798, + "step": 9780 + }, + { + "epoch": 0.82, + "learning_rate": 1.6812599370620574e-06, + "loss": 0.4601, + "step": 9781 + }, + { + "epoch": 0.82, + "learning_rate": 1.679756341454788e-06, + "loss": 0.4397, + "step": 9782 + }, + { + "epoch": 0.82, + "learning_rate": 1.6782533568516047e-06, + "loss": 0.4517, + "step": 9783 + }, + { + "epoch": 0.82, + "learning_rate": 1.6767509833628847e-06, + "loss": 0.4718, + "step": 9784 + }, + { + "epoch": 0.82, + "learning_rate": 1.6752492210989523e-06, + "loss": 0.4713, + "step": 9785 + }, + { + "epoch": 0.82, + "learning_rate": 1.6737480701700936e-06, + "loss": 0.4593, + "step": 9786 + }, + { + "epoch": 0.82, + "learning_rate": 1.6722475306865415e-06, + "loss": 0.4871, + "step": 9787 + }, + { + "epoch": 0.82, + "learning_rate": 1.6707476027584956e-06, + "loss": 0.4819, + "step": 9788 + }, + { + "epoch": 0.82, + "learning_rate": 1.6692482864961024e-06, + "loss": 0.4736, + "step": 9789 + }, + { + "epoch": 0.82, + "learning_rate": 1.6677495820094635e-06, + "loss": 0.4608, + "step": 9790 + }, + { + "epoch": 0.82, + "learning_rate": 1.6662514894086402e-06, + "loss": 0.4389, + "step": 9791 + }, + { + "epoch": 0.82, + "learning_rate": 1.664754008803644e-06, + "loss": 0.4748, + "step": 9792 + }, + { + "epoch": 0.82, + "learning_rate": 1.6632571403044429e-06, + "loss": 0.4592, + "step": 9793 + }, + { + "epoch": 0.82, + "learning_rate": 1.6617608840209642e-06, + "loss": 0.4609, + "step": 9794 + }, + { + "epoch": 0.82, + "learning_rate": 1.6602652400630825e-06, + "loss": 0.4567, + "step": 9795 + }, + { + "epoch": 0.82, + "learning_rate": 1.6587702085406366e-06, + "loss": 0.5012, + "step": 9796 + }, + { + "epoch": 0.82, + "learning_rate": 1.6572757895634117e-06, + "loss": 0.4571, + "step": 9797 + }, + { + "epoch": 0.82, + "learning_rate": 1.6557819832411537e-06, + "loss": 0.4843, + "step": 9798 + }, + { + "epoch": 0.82, + "learning_rate": 1.6542887896835614e-06, + "loss": 0.4747, + "step": 9799 + }, + { + "epoch": 0.82, + "learning_rate": 1.652796209000287e-06, + "loss": 0.4576, + "step": 9800 + }, + { + "epoch": 0.82, + "learning_rate": 1.6513042413009383e-06, + "loss": 0.4586, + "step": 9801 + }, + { + "epoch": 0.82, + "learning_rate": 1.6498128866950835e-06, + "loss": 0.4844, + "step": 9802 + }, + { + "epoch": 0.82, + "learning_rate": 1.6483221452922394e-06, + "loss": 0.4594, + "step": 9803 + }, + { + "epoch": 0.82, + "learning_rate": 1.646832017201877e-06, + "loss": 0.4692, + "step": 9804 + }, + { + "epoch": 0.82, + "learning_rate": 1.6453425025334302e-06, + "loss": 0.4718, + "step": 9805 + }, + { + "epoch": 0.82, + "learning_rate": 1.6438536013962814e-06, + "loss": 0.4611, + "step": 9806 + }, + { + "epoch": 0.82, + "learning_rate": 1.6423653138997675e-06, + "loss": 0.4661, + "step": 9807 + }, + { + "epoch": 0.82, + "learning_rate": 1.64087764015318e-06, + "loss": 0.4553, + "step": 9808 + }, + { + "epoch": 0.82, + "learning_rate": 1.639390580265774e-06, + "loss": 0.4626, + "step": 9809 + }, + { + "epoch": 0.82, + "learning_rate": 1.6379041343467484e-06, + "loss": 0.4576, + "step": 9810 + }, + { + "epoch": 0.82, + "learning_rate": 1.6364183025052626e-06, + "loss": 0.4766, + "step": 9811 + }, + { + "epoch": 0.82, + "learning_rate": 1.6349330848504308e-06, + "loss": 0.4571, + "step": 9812 + }, + { + "epoch": 0.82, + "learning_rate": 1.6334484814913165e-06, + "loss": 0.4734, + "step": 9813 + }, + { + "epoch": 0.82, + "learning_rate": 1.6319644925369504e-06, + "loss": 0.4534, + "step": 9814 + }, + { + "epoch": 0.82, + "learning_rate": 1.6304811180963032e-06, + "loss": 0.4627, + "step": 9815 + }, + { + "epoch": 0.82, + "learning_rate": 1.6289983582783142e-06, + "loss": 0.4361, + "step": 9816 + }, + { + "epoch": 0.82, + "learning_rate": 1.6275162131918688e-06, + "loss": 0.4706, + "step": 9817 + }, + { + "epoch": 0.82, + "learning_rate": 1.6260346829458084e-06, + "loss": 0.4615, + "step": 9818 + }, + { + "epoch": 0.82, + "learning_rate": 1.624553767648931e-06, + "loss": 0.4508, + "step": 9819 + }, + { + "epoch": 0.82, + "learning_rate": 1.623073467409988e-06, + "loss": 0.4657, + "step": 9820 + }, + { + "epoch": 0.82, + "learning_rate": 1.621593782337686e-06, + "loss": 0.4634, + "step": 9821 + }, + { + "epoch": 0.82, + "learning_rate": 1.62011471254069e-06, + "loss": 0.4603, + "step": 9822 + }, + { + "epoch": 0.82, + "learning_rate": 1.618636258127615e-06, + "loss": 0.4654, + "step": 9823 + }, + { + "epoch": 0.82, + "learning_rate": 1.6171584192070322e-06, + "loss": 0.46, + "step": 9824 + }, + { + "epoch": 0.82, + "learning_rate": 1.6156811958874664e-06, + "loss": 0.478, + "step": 9825 + }, + { + "epoch": 0.82, + "learning_rate": 1.6142045882774027e-06, + "loss": 0.4481, + "step": 9826 + }, + { + "epoch": 0.82, + "learning_rate": 1.6127285964852758e-06, + "loss": 0.4746, + "step": 9827 + }, + { + "epoch": 0.82, + "learning_rate": 1.6112532206194719e-06, + "loss": 0.4595, + "step": 9828 + }, + { + "epoch": 0.82, + "learning_rate": 1.6097784607883427e-06, + "loss": 0.4624, + "step": 9829 + }, + { + "epoch": 0.82, + "learning_rate": 1.6083043171001856e-06, + "loss": 0.4669, + "step": 9830 + }, + { + "epoch": 0.82, + "learning_rate": 1.6068307896632562e-06, + "loss": 0.456, + "step": 9831 + }, + { + "epoch": 0.82, + "learning_rate": 1.6053578785857637e-06, + "loss": 0.4572, + "step": 9832 + }, + { + "epoch": 0.82, + "learning_rate": 1.6038855839758727e-06, + "loss": 0.4696, + "step": 9833 + }, + { + "epoch": 0.82, + "learning_rate": 1.6024139059417e-06, + "loss": 0.4707, + "step": 9834 + }, + { + "epoch": 0.82, + "learning_rate": 1.6009428445913245e-06, + "loss": 0.4542, + "step": 9835 + }, + { + "epoch": 0.82, + "learning_rate": 1.5994724000327689e-06, + "loss": 0.4657, + "step": 9836 + }, + { + "epoch": 0.82, + "learning_rate": 1.5980025723740222e-06, + "loss": 0.4558, + "step": 9837 + }, + { + "epoch": 0.82, + "learning_rate": 1.5965333617230206e-06, + "loss": 0.4499, + "step": 9838 + }, + { + "epoch": 0.82, + "learning_rate": 1.5950647681876564e-06, + "loss": 0.4672, + "step": 9839 + }, + { + "epoch": 0.82, + "learning_rate": 1.5935967918757766e-06, + "loss": 0.4803, + "step": 9840 + }, + { + "epoch": 0.82, + "learning_rate": 1.5921294328951842e-06, + "loss": 0.4685, + "step": 9841 + }, + { + "epoch": 0.82, + "learning_rate": 1.5906626913536315e-06, + "loss": 0.4913, + "step": 9842 + }, + { + "epoch": 0.82, + "learning_rate": 1.5891965673588371e-06, + "loss": 0.4623, + "step": 9843 + }, + { + "epoch": 0.82, + "learning_rate": 1.5877310610184638e-06, + "loss": 0.467, + "step": 9844 + }, + { + "epoch": 0.82, + "learning_rate": 1.5862661724401296e-06, + "loss": 0.4534, + "step": 9845 + }, + { + "epoch": 0.82, + "learning_rate": 1.5848019017314143e-06, + "loss": 0.4589, + "step": 9846 + }, + { + "epoch": 0.82, + "learning_rate": 1.5833382489998461e-06, + "loss": 0.4532, + "step": 9847 + }, + { + "epoch": 0.82, + "learning_rate": 1.5818752143529092e-06, + "loss": 0.4563, + "step": 9848 + }, + { + "epoch": 0.82, + "learning_rate": 1.580412797898041e-06, + "loss": 0.4748, + "step": 9849 + }, + { + "epoch": 0.82, + "learning_rate": 1.578950999742639e-06, + "loss": 0.4534, + "step": 9850 + }, + { + "epoch": 0.82, + "learning_rate": 1.5774898199940503e-06, + "loss": 0.4749, + "step": 9851 + }, + { + "epoch": 0.82, + "learning_rate": 1.576029258759577e-06, + "loss": 0.4571, + "step": 9852 + }, + { + "epoch": 0.82, + "learning_rate": 1.574569316146477e-06, + "loss": 0.4619, + "step": 9853 + }, + { + "epoch": 0.82, + "learning_rate": 1.573109992261963e-06, + "loss": 0.4568, + "step": 9854 + }, + { + "epoch": 0.82, + "learning_rate": 1.5716512872131983e-06, + "loss": 0.46, + "step": 9855 + }, + { + "epoch": 0.82, + "learning_rate": 1.5701932011073072e-06, + "loss": 0.464, + "step": 9856 + }, + { + "epoch": 0.82, + "learning_rate": 1.5687357340513676e-06, + "loss": 0.4505, + "step": 9857 + }, + { + "epoch": 0.82, + "learning_rate": 1.567278886152407e-06, + "loss": 0.4821, + "step": 9858 + }, + { + "epoch": 0.82, + "learning_rate": 1.5658226575174107e-06, + "loss": 0.4536, + "step": 9859 + }, + { + "epoch": 0.82, + "learning_rate": 1.564367048253318e-06, + "loss": 0.4568, + "step": 9860 + }, + { + "epoch": 0.83, + "learning_rate": 1.5629120584670233e-06, + "loss": 0.4723, + "step": 9861 + }, + { + "epoch": 0.83, + "learning_rate": 1.561457688265372e-06, + "loss": 0.4438, + "step": 9862 + }, + { + "epoch": 0.83, + "learning_rate": 1.5600039377551713e-06, + "loss": 0.4778, + "step": 9863 + }, + { + "epoch": 0.83, + "learning_rate": 1.5585508070431777e-06, + "loss": 0.4595, + "step": 9864 + }, + { + "epoch": 0.83, + "learning_rate": 1.5570982962361014e-06, + "loss": 0.4779, + "step": 9865 + }, + { + "epoch": 0.83, + "learning_rate": 1.5556464054406084e-06, + "loss": 0.4676, + "step": 9866 + }, + { + "epoch": 0.83, + "learning_rate": 1.5541951347633222e-06, + "loss": 0.4708, + "step": 9867 + }, + { + "epoch": 0.83, + "learning_rate": 1.5527444843108164e-06, + "loss": 0.4505, + "step": 9868 + }, + { + "epoch": 0.83, + "learning_rate": 1.5512944541896192e-06, + "loss": 0.4521, + "step": 9869 + }, + { + "epoch": 0.83, + "learning_rate": 1.5498450445062185e-06, + "loss": 0.4528, + "step": 9870 + }, + { + "epoch": 0.83, + "learning_rate": 1.5483962553670507e-06, + "loss": 0.4653, + "step": 9871 + }, + { + "epoch": 0.83, + "learning_rate": 1.5469480868785092e-06, + "loss": 0.4514, + "step": 9872 + }, + { + "epoch": 0.83, + "learning_rate": 1.5455005391469414e-06, + "loss": 0.4529, + "step": 9873 + }, + { + "epoch": 0.83, + "learning_rate": 1.5440536122786487e-06, + "loss": 0.4503, + "step": 9874 + }, + { + "epoch": 0.83, + "learning_rate": 1.5426073063798853e-06, + "loss": 0.4638, + "step": 9875 + }, + { + "epoch": 0.83, + "learning_rate": 1.541161621556867e-06, + "loss": 0.4875, + "step": 9876 + }, + { + "epoch": 0.83, + "learning_rate": 1.5397165579157547e-06, + "loss": 0.4691, + "step": 9877 + }, + { + "epoch": 0.83, + "learning_rate": 1.5382721155626701e-06, + "loss": 0.4669, + "step": 9878 + }, + { + "epoch": 0.83, + "learning_rate": 1.5368282946036884e-06, + "loss": 0.4839, + "step": 9879 + }, + { + "epoch": 0.83, + "learning_rate": 1.5353850951448346e-06, + "loss": 0.45, + "step": 9880 + }, + { + "epoch": 0.83, + "learning_rate": 1.533942517292092e-06, + "loss": 0.4832, + "step": 9881 + }, + { + "epoch": 0.83, + "learning_rate": 1.5325005611513988e-06, + "loss": 0.4552, + "step": 9882 + }, + { + "epoch": 0.83, + "learning_rate": 1.5310592268286427e-06, + "loss": 0.4636, + "step": 9883 + }, + { + "epoch": 0.83, + "learning_rate": 1.5296185144296737e-06, + "loss": 0.4557, + "step": 9884 + }, + { + "epoch": 0.83, + "learning_rate": 1.5281784240602915e-06, + "loss": 0.4538, + "step": 9885 + }, + { + "epoch": 0.83, + "learning_rate": 1.5267389558262458e-06, + "loss": 0.4727, + "step": 9886 + }, + { + "epoch": 0.83, + "learning_rate": 1.525300109833251e-06, + "loss": 0.468, + "step": 9887 + }, + { + "epoch": 0.83, + "learning_rate": 1.5238618861869657e-06, + "loss": 0.4555, + "step": 9888 + }, + { + "epoch": 0.83, + "learning_rate": 1.5224242849930104e-06, + "loss": 0.4554, + "step": 9889 + }, + { + "epoch": 0.83, + "learning_rate": 1.5209873063569514e-06, + "loss": 0.461, + "step": 9890 + }, + { + "epoch": 0.83, + "learning_rate": 1.5195509503843198e-06, + "loss": 0.4678, + "step": 9891 + }, + { + "epoch": 0.83, + "learning_rate": 1.5181152171805946e-06, + "loss": 0.4675, + "step": 9892 + }, + { + "epoch": 0.83, + "learning_rate": 1.5166801068512083e-06, + "loss": 0.4785, + "step": 9893 + }, + { + "epoch": 0.83, + "learning_rate": 1.5152456195015508e-06, + "loss": 0.4646, + "step": 9894 + }, + { + "epoch": 0.83, + "learning_rate": 1.5138117552369636e-06, + "loss": 0.4579, + "step": 9895 + }, + { + "epoch": 0.83, + "learning_rate": 1.5123785141627422e-06, + "loss": 0.4778, + "step": 9896 + }, + { + "epoch": 0.83, + "learning_rate": 1.5109458963841405e-06, + "loss": 0.4539, + "step": 9897 + }, + { + "epoch": 0.83, + "learning_rate": 1.5095139020063654e-06, + "loss": 0.4777, + "step": 9898 + }, + { + "epoch": 0.83, + "learning_rate": 1.5080825311345748e-06, + "loss": 0.4639, + "step": 9899 + }, + { + "epoch": 0.83, + "learning_rate": 1.5066517838738826e-06, + "loss": 0.4715, + "step": 9900 + }, + { + "epoch": 0.83, + "learning_rate": 1.5052216603293567e-06, + "loss": 0.4642, + "step": 9901 + }, + { + "epoch": 0.83, + "learning_rate": 1.5037921606060201e-06, + "loss": 0.4706, + "step": 9902 + }, + { + "epoch": 0.83, + "learning_rate": 1.5023632848088466e-06, + "loss": 0.4704, + "step": 9903 + }, + { + "epoch": 0.83, + "learning_rate": 1.5009350330427707e-06, + "loss": 0.4681, + "step": 9904 + }, + { + "epoch": 0.83, + "learning_rate": 1.4995074054126758e-06, + "loss": 0.4892, + "step": 9905 + }, + { + "epoch": 0.83, + "learning_rate": 1.4980804020234018e-06, + "loss": 0.4726, + "step": 9906 + }, + { + "epoch": 0.83, + "learning_rate": 1.4966540229797377e-06, + "loss": 0.449, + "step": 9907 + }, + { + "epoch": 0.83, + "learning_rate": 1.495228268386436e-06, + "loss": 0.4921, + "step": 9908 + }, + { + "epoch": 0.83, + "learning_rate": 1.4938031383481976e-06, + "loss": 0.4561, + "step": 9909 + }, + { + "epoch": 0.83, + "learning_rate": 1.4923786329696732e-06, + "loss": 0.4515, + "step": 9910 + }, + { + "epoch": 0.83, + "learning_rate": 1.490954752355479e-06, + "loss": 0.4636, + "step": 9911 + }, + { + "epoch": 0.83, + "learning_rate": 1.4895314966101771e-06, + "loss": 0.4696, + "step": 9912 + }, + { + "epoch": 0.83, + "learning_rate": 1.4881088658382825e-06, + "loss": 0.46, + "step": 9913 + }, + { + "epoch": 0.83, + "learning_rate": 1.4866868601442708e-06, + "loss": 0.4571, + "step": 9914 + }, + { + "epoch": 0.83, + "learning_rate": 1.4852654796325649e-06, + "loss": 0.4791, + "step": 9915 + }, + { + "epoch": 0.83, + "learning_rate": 1.483844724407546e-06, + "loss": 0.4548, + "step": 9916 + }, + { + "epoch": 0.83, + "learning_rate": 1.4824245945735504e-06, + "loss": 0.4757, + "step": 9917 + }, + { + "epoch": 0.83, + "learning_rate": 1.4810050902348637e-06, + "loss": 0.4646, + "step": 9918 + }, + { + "epoch": 0.83, + "learning_rate": 1.4795862114957316e-06, + "loss": 0.4581, + "step": 9919 + }, + { + "epoch": 0.83, + "learning_rate": 1.4781679584603502e-06, + "loss": 0.4629, + "step": 9920 + }, + { + "epoch": 0.83, + "learning_rate": 1.476750331232868e-06, + "loss": 0.4577, + "step": 9921 + }, + { + "epoch": 0.83, + "learning_rate": 1.475333329917391e-06, + "loss": 0.4527, + "step": 9922 + }, + { + "epoch": 0.83, + "learning_rate": 1.4739169546179765e-06, + "loss": 0.4807, + "step": 9923 + }, + { + "epoch": 0.83, + "learning_rate": 1.4725012054386378e-06, + "loss": 0.4923, + "step": 9924 + }, + { + "epoch": 0.83, + "learning_rate": 1.471086082483343e-06, + "loss": 0.4598, + "step": 9925 + }, + { + "epoch": 0.83, + "learning_rate": 1.4696715858560117e-06, + "loss": 0.4665, + "step": 9926 + }, + { + "epoch": 0.83, + "learning_rate": 1.4682577156605172e-06, + "loss": 0.4629, + "step": 9927 + }, + { + "epoch": 0.83, + "learning_rate": 1.4668444720006925e-06, + "loss": 0.4601, + "step": 9928 + }, + { + "epoch": 0.83, + "learning_rate": 1.465431854980317e-06, + "loss": 0.4491, + "step": 9929 + }, + { + "epoch": 0.83, + "learning_rate": 1.464019864703128e-06, + "loss": 0.4712, + "step": 9930 + }, + { + "epoch": 0.83, + "learning_rate": 1.462608501272814e-06, + "loss": 0.4774, + "step": 9931 + }, + { + "epoch": 0.83, + "learning_rate": 1.4611977647930253e-06, + "loss": 0.4513, + "step": 9932 + }, + { + "epoch": 0.83, + "learning_rate": 1.4597876553673563e-06, + "loss": 0.4563, + "step": 9933 + }, + { + "epoch": 0.83, + "learning_rate": 1.4583781730993608e-06, + "loss": 0.499, + "step": 9934 + }, + { + "epoch": 0.83, + "learning_rate": 1.4569693180925448e-06, + "loss": 0.4526, + "step": 9935 + }, + { + "epoch": 0.83, + "learning_rate": 1.4555610904503693e-06, + "loss": 0.4584, + "step": 9936 + }, + { + "epoch": 0.83, + "learning_rate": 1.4541534902762454e-06, + "loss": 0.4796, + "step": 9937 + }, + { + "epoch": 0.83, + "learning_rate": 1.4527465176735468e-06, + "loss": 0.4667, + "step": 9938 + }, + { + "epoch": 0.83, + "learning_rate": 1.4513401727455912e-06, + "loss": 0.4605, + "step": 9939 + }, + { + "epoch": 0.83, + "learning_rate": 1.4499344555956596e-06, + "loss": 0.4599, + "step": 9940 + }, + { + "epoch": 0.83, + "learning_rate": 1.4485293663269784e-06, + "loss": 0.4705, + "step": 9941 + }, + { + "epoch": 0.83, + "learning_rate": 1.4471249050427327e-06, + "loss": 0.4587, + "step": 9942 + }, + { + "epoch": 0.83, + "learning_rate": 1.445721071846059e-06, + "loss": 0.4666, + "step": 9943 + }, + { + "epoch": 0.83, + "learning_rate": 1.4443178668400482e-06, + "loss": 0.4746, + "step": 9944 + }, + { + "epoch": 0.83, + "learning_rate": 1.44291529012775e-06, + "loss": 0.4541, + "step": 9945 + }, + { + "epoch": 0.83, + "learning_rate": 1.4415133418121607e-06, + "loss": 0.4601, + "step": 9946 + }, + { + "epoch": 0.83, + "learning_rate": 1.440112021996235e-06, + "loss": 0.4644, + "step": 9947 + }, + { + "epoch": 0.83, + "learning_rate": 1.438711330782877e-06, + "loss": 0.4746, + "step": 9948 + }, + { + "epoch": 0.83, + "learning_rate": 1.4373112682749513e-06, + "loss": 0.453, + "step": 9949 + }, + { + "epoch": 0.83, + "learning_rate": 1.435911834575271e-06, + "loss": 0.4469, + "step": 9950 + }, + { + "epoch": 0.83, + "learning_rate": 1.4345130297866028e-06, + "loss": 0.4831, + "step": 9951 + }, + { + "epoch": 0.83, + "learning_rate": 1.4331148540116736e-06, + "loss": 0.4721, + "step": 9952 + }, + { + "epoch": 0.83, + "learning_rate": 1.4317173073531577e-06, + "loss": 0.4719, + "step": 9953 + }, + { + "epoch": 0.83, + "learning_rate": 1.4303203899136841e-06, + "loss": 0.4573, + "step": 9954 + }, + { + "epoch": 0.83, + "learning_rate": 1.4289241017958366e-06, + "loss": 0.4556, + "step": 9955 + }, + { + "epoch": 0.83, + "learning_rate": 1.4275284431021541e-06, + "loss": 0.4715, + "step": 9956 + }, + { + "epoch": 0.83, + "learning_rate": 1.4261334139351269e-06, + "loss": 0.4622, + "step": 9957 + }, + { + "epoch": 0.83, + "learning_rate": 1.4247390143971972e-06, + "loss": 0.4679, + "step": 9958 + }, + { + "epoch": 0.83, + "learning_rate": 1.423345244590768e-06, + "loss": 0.4744, + "step": 9959 + }, + { + "epoch": 0.83, + "learning_rate": 1.4219521046181928e-06, + "loss": 0.4441, + "step": 9960 + }, + { + "epoch": 0.83, + "learning_rate": 1.4205595945817773e-06, + "loss": 0.4609, + "step": 9961 + }, + { + "epoch": 0.83, + "learning_rate": 1.41916771458378e-06, + "loss": 0.4812, + "step": 9962 + }, + { + "epoch": 0.83, + "learning_rate": 1.4177764647264148e-06, + "loss": 0.4526, + "step": 9963 + }, + { + "epoch": 0.83, + "learning_rate": 1.4163858451118506e-06, + "loss": 0.4531, + "step": 9964 + }, + { + "epoch": 0.83, + "learning_rate": 1.414995855842205e-06, + "loss": 0.4603, + "step": 9965 + }, + { + "epoch": 0.83, + "learning_rate": 1.4136064970195595e-06, + "loss": 0.447, + "step": 9966 + }, + { + "epoch": 0.83, + "learning_rate": 1.4122177687459382e-06, + "loss": 0.4504, + "step": 9967 + }, + { + "epoch": 0.83, + "learning_rate": 1.4108296711233249e-06, + "loss": 0.461, + "step": 9968 + }, + { + "epoch": 0.83, + "learning_rate": 1.4094422042536538e-06, + "loss": 0.458, + "step": 9969 + }, + { + "epoch": 0.83, + "learning_rate": 1.4080553682388188e-06, + "loss": 0.4563, + "step": 9970 + }, + { + "epoch": 0.83, + "learning_rate": 1.4066691631806574e-06, + "loss": 0.4701, + "step": 9971 + }, + { + "epoch": 0.83, + "learning_rate": 1.4052835891809735e-06, + "loss": 0.4579, + "step": 9972 + }, + { + "epoch": 0.83, + "learning_rate": 1.403898646341515e-06, + "loss": 0.4772, + "step": 9973 + }, + { + "epoch": 0.83, + "learning_rate": 1.4025143347639858e-06, + "loss": 0.467, + "step": 9974 + }, + { + "epoch": 0.83, + "learning_rate": 1.4011306545500435e-06, + "loss": 0.4744, + "step": 9975 + }, + { + "epoch": 0.83, + "learning_rate": 1.3997476058013016e-06, + "loss": 0.4634, + "step": 9976 + }, + { + "epoch": 0.83, + "learning_rate": 1.398365188619324e-06, + "loss": 0.4809, + "step": 9977 + }, + { + "epoch": 0.83, + "learning_rate": 1.3969834031056273e-06, + "loss": 0.4474, + "step": 9978 + }, + { + "epoch": 0.83, + "learning_rate": 1.3956022493616895e-06, + "loss": 0.4512, + "step": 9979 + }, + { + "epoch": 0.83, + "learning_rate": 1.3942217274889325e-06, + "loss": 0.4772, + "step": 9980 + }, + { + "epoch": 0.84, + "learning_rate": 1.3928418375887388e-06, + "loss": 0.4751, + "step": 9981 + }, + { + "epoch": 0.84, + "learning_rate": 1.3914625797624415e-06, + "loss": 0.4361, + "step": 9982 + }, + { + "epoch": 0.84, + "learning_rate": 1.3900839541113265e-06, + "loss": 0.4814, + "step": 9983 + }, + { + "epoch": 0.84, + "learning_rate": 1.3887059607366338e-06, + "loss": 0.4506, + "step": 9984 + }, + { + "epoch": 0.84, + "learning_rate": 1.3873285997395569e-06, + "loss": 0.4521, + "step": 9985 + }, + { + "epoch": 0.84, + "learning_rate": 1.3859518712212473e-06, + "loss": 0.4759, + "step": 9986 + }, + { + "epoch": 0.84, + "learning_rate": 1.3845757752828037e-06, + "loss": 0.4694, + "step": 9987 + }, + { + "epoch": 0.84, + "learning_rate": 1.3832003120252801e-06, + "loss": 0.4438, + "step": 9988 + }, + { + "epoch": 0.84, + "learning_rate": 1.3818254815496846e-06, + "loss": 0.4566, + "step": 9989 + }, + { + "epoch": 0.84, + "learning_rate": 1.3804512839569805e-06, + "loss": 0.4699, + "step": 9990 + }, + { + "epoch": 0.84, + "learning_rate": 1.3790777193480842e-06, + "loss": 0.4585, + "step": 9991 + }, + { + "epoch": 0.84, + "learning_rate": 1.3777047878238603e-06, + "loss": 0.4504, + "step": 9992 + }, + { + "epoch": 0.84, + "learning_rate": 1.3763324894851371e-06, + "loss": 0.4583, + "step": 9993 + }, + { + "epoch": 0.84, + "learning_rate": 1.3749608244326862e-06, + "loss": 0.461, + "step": 9994 + }, + { + "epoch": 0.84, + "learning_rate": 1.373589792767238e-06, + "loss": 0.4712, + "step": 9995 + }, + { + "epoch": 0.84, + "learning_rate": 1.372219394589477e-06, + "loss": 0.4688, + "step": 9996 + }, + { + "epoch": 0.84, + "learning_rate": 1.3708496300000363e-06, + "loss": 0.479, + "step": 9997 + }, + { + "epoch": 0.84, + "learning_rate": 1.369480499099508e-06, + "loss": 0.4624, + "step": 9998 + }, + { + "epoch": 0.84, + "learning_rate": 1.3681120019884331e-06, + "loss": 0.4708, + "step": 9999 + }, + { + "epoch": 0.84, + "learning_rate": 1.3667441387673098e-06, + "loss": 0.4821, + "step": 10000 + }, + { + "epoch": 0.84, + "learning_rate": 1.36537690953659e-06, + "loss": 0.4553, + "step": 10001 + }, + { + "epoch": 0.84, + "learning_rate": 1.3640103143966765e-06, + "loss": 0.4771, + "step": 10002 + }, + { + "epoch": 0.84, + "learning_rate": 1.3626443534479262e-06, + "loss": 0.4618, + "step": 10003 + }, + { + "epoch": 0.84, + "learning_rate": 1.3612790267906484e-06, + "loss": 0.4534, + "step": 10004 + }, + { + "epoch": 0.84, + "learning_rate": 1.3599143345251075e-06, + "loss": 0.4711, + "step": 10005 + }, + { + "epoch": 0.84, + "learning_rate": 1.35855027675152e-06, + "loss": 0.4506, + "step": 10006 + }, + { + "epoch": 0.84, + "learning_rate": 1.3571868535700595e-06, + "loss": 0.4574, + "step": 10007 + }, + { + "epoch": 0.84, + "learning_rate": 1.3558240650808473e-06, + "loss": 0.4485, + "step": 10008 + }, + { + "epoch": 0.84, + "learning_rate": 1.354461911383963e-06, + "loss": 0.4536, + "step": 10009 + }, + { + "epoch": 0.84, + "learning_rate": 1.353100392579434e-06, + "loss": 0.467, + "step": 10010 + }, + { + "epoch": 0.84, + "learning_rate": 1.351739508767249e-06, + "loss": 0.4719, + "step": 10011 + }, + { + "epoch": 0.84, + "learning_rate": 1.3503792600473408e-06, + "loss": 0.4611, + "step": 10012 + }, + { + "epoch": 0.84, + "learning_rate": 1.349019646519607e-06, + "loss": 0.4513, + "step": 10013 + }, + { + "epoch": 0.84, + "learning_rate": 1.3476606682838866e-06, + "loss": 0.4686, + "step": 10014 + }, + { + "epoch": 0.84, + "learning_rate": 1.3463023254399798e-06, + "loss": 0.4681, + "step": 10015 + }, + { + "epoch": 0.84, + "learning_rate": 1.3449446180876369e-06, + "loss": 0.4556, + "step": 10016 + }, + { + "epoch": 0.84, + "learning_rate": 1.3435875463265624e-06, + "loss": 0.4678, + "step": 10017 + }, + { + "epoch": 0.84, + "learning_rate": 1.3422311102564134e-06, + "loss": 0.4727, + "step": 10018 + }, + { + "epoch": 0.84, + "learning_rate": 1.340875309976799e-06, + "loss": 0.4818, + "step": 10019 + }, + { + "epoch": 0.84, + "learning_rate": 1.3395201455872886e-06, + "loss": 0.4737, + "step": 10020 + }, + { + "epoch": 0.84, + "learning_rate": 1.3381656171873936e-06, + "loss": 0.4683, + "step": 10021 + }, + { + "epoch": 0.84, + "learning_rate": 1.336811724876592e-06, + "loss": 0.4708, + "step": 10022 + }, + { + "epoch": 0.84, + "learning_rate": 1.3354584687543037e-06, + "loss": 0.4664, + "step": 10023 + }, + { + "epoch": 0.84, + "learning_rate": 1.3341058489199065e-06, + "loss": 0.4535, + "step": 10024 + }, + { + "epoch": 0.84, + "learning_rate": 1.3327538654727323e-06, + "loss": 0.4832, + "step": 10025 + }, + { + "epoch": 0.84, + "learning_rate": 1.3314025185120616e-06, + "loss": 0.4402, + "step": 10026 + }, + { + "epoch": 0.84, + "learning_rate": 1.3300518081371373e-06, + "loss": 0.4713, + "step": 10027 + }, + { + "epoch": 0.84, + "learning_rate": 1.3287017344471477e-06, + "loss": 0.4847, + "step": 10028 + }, + { + "epoch": 0.84, + "learning_rate": 1.3273522975412344e-06, + "loss": 0.485, + "step": 10029 + }, + { + "epoch": 0.84, + "learning_rate": 1.3260034975184955e-06, + "loss": 0.4526, + "step": 10030 + }, + { + "epoch": 0.84, + "learning_rate": 1.3246553344779834e-06, + "loss": 0.4636, + "step": 10031 + }, + { + "epoch": 0.84, + "learning_rate": 1.3233078085187002e-06, + "loss": 0.4618, + "step": 10032 + }, + { + "epoch": 0.84, + "learning_rate": 1.3219609197396e-06, + "loss": 0.4777, + "step": 10033 + }, + { + "epoch": 0.84, + "learning_rate": 1.3206146682395983e-06, + "loss": 0.4768, + "step": 10034 + }, + { + "epoch": 0.84, + "learning_rate": 1.3192690541175536e-06, + "loss": 0.469, + "step": 10035 + }, + { + "epoch": 0.84, + "learning_rate": 1.3179240774722845e-06, + "loss": 0.4677, + "step": 10036 + }, + { + "epoch": 0.84, + "learning_rate": 1.3165797384025602e-06, + "loss": 0.4521, + "step": 10037 + }, + { + "epoch": 0.84, + "learning_rate": 1.3152360370071016e-06, + "loss": 0.458, + "step": 10038 + }, + { + "epoch": 0.84, + "learning_rate": 1.3138929733845873e-06, + "loss": 0.4684, + "step": 10039 + }, + { + "epoch": 0.84, + "learning_rate": 1.3125505476336408e-06, + "loss": 0.4928, + "step": 10040 + }, + { + "epoch": 0.84, + "learning_rate": 1.31120875985285e-06, + "loss": 0.4457, + "step": 10041 + }, + { + "epoch": 0.84, + "learning_rate": 1.3098676101407493e-06, + "loss": 0.4711, + "step": 10042 + }, + { + "epoch": 0.84, + "learning_rate": 1.3085270985958276e-06, + "loss": 0.4534, + "step": 10043 + }, + { + "epoch": 0.84, + "learning_rate": 1.307187225316524e-06, + "loss": 0.4645, + "step": 10044 + }, + { + "epoch": 0.84, + "learning_rate": 1.3058479904012356e-06, + "loss": 0.4482, + "step": 10045 + }, + { + "epoch": 0.84, + "learning_rate": 1.3045093939483066e-06, + "loss": 0.4551, + "step": 10046 + }, + { + "epoch": 0.84, + "learning_rate": 1.303171436056042e-06, + "loss": 0.4767, + "step": 10047 + }, + { + "epoch": 0.84, + "learning_rate": 1.3018341168226944e-06, + "loss": 0.4526, + "step": 10048 + }, + { + "epoch": 0.84, + "learning_rate": 1.3004974363464717e-06, + "loss": 0.4568, + "step": 10049 + }, + { + "epoch": 0.84, + "learning_rate": 1.2991613947255321e-06, + "loss": 0.4566, + "step": 10050 + }, + { + "epoch": 0.84, + "learning_rate": 1.2978259920579895e-06, + "loss": 0.4475, + "step": 10051 + }, + { + "epoch": 0.84, + "learning_rate": 1.2964912284419119e-06, + "loss": 0.4601, + "step": 10052 + }, + { + "epoch": 0.84, + "learning_rate": 1.2951571039753163e-06, + "loss": 0.4661, + "step": 10053 + }, + { + "epoch": 0.84, + "learning_rate": 1.2938236187561782e-06, + "loss": 0.4581, + "step": 10054 + }, + { + "epoch": 0.84, + "learning_rate": 1.292490772882422e-06, + "loss": 0.4995, + "step": 10055 + }, + { + "epoch": 0.84, + "learning_rate": 1.2911585664519267e-06, + "loss": 0.4664, + "step": 10056 + }, + { + "epoch": 0.84, + "learning_rate": 1.2898269995625234e-06, + "loss": 0.4653, + "step": 10057 + }, + { + "epoch": 0.84, + "learning_rate": 1.2884960723119978e-06, + "loss": 0.4812, + "step": 10058 + }, + { + "epoch": 0.84, + "learning_rate": 1.2871657847980856e-06, + "loss": 0.4597, + "step": 10059 + }, + { + "epoch": 0.84, + "learning_rate": 1.285836137118477e-06, + "loss": 0.4648, + "step": 10060 + }, + { + "epoch": 0.84, + "learning_rate": 1.2845071293708188e-06, + "loss": 0.4471, + "step": 10061 + }, + { + "epoch": 0.84, + "learning_rate": 1.2831787616527058e-06, + "loss": 0.4796, + "step": 10062 + }, + { + "epoch": 0.84, + "learning_rate": 1.2818510340616896e-06, + "loss": 0.4558, + "step": 10063 + }, + { + "epoch": 0.84, + "learning_rate": 1.2805239466952723e-06, + "loss": 0.4706, + "step": 10064 + }, + { + "epoch": 0.84, + "learning_rate": 1.2791974996509094e-06, + "loss": 0.4646, + "step": 10065 + }, + { + "epoch": 0.84, + "learning_rate": 1.2778716930260105e-06, + "loss": 0.4734, + "step": 10066 + }, + { + "epoch": 0.84, + "learning_rate": 1.2765465269179334e-06, + "loss": 0.4534, + "step": 10067 + }, + { + "epoch": 0.84, + "learning_rate": 1.275222001423998e-06, + "loss": 0.4768, + "step": 10068 + }, + { + "epoch": 0.84, + "learning_rate": 1.2738981166414688e-06, + "loss": 0.467, + "step": 10069 + }, + { + "epoch": 0.84, + "learning_rate": 1.2725748726675691e-06, + "loss": 0.4768, + "step": 10070 + }, + { + "epoch": 0.84, + "learning_rate": 1.2712522695994666e-06, + "loss": 0.4946, + "step": 10071 + }, + { + "epoch": 0.84, + "learning_rate": 1.269930307534295e-06, + "loss": 0.4539, + "step": 10072 + }, + { + "epoch": 0.84, + "learning_rate": 1.268608986569131e-06, + "loss": 0.4647, + "step": 10073 + }, + { + "epoch": 0.84, + "learning_rate": 1.2672883068010033e-06, + "loss": 0.4726, + "step": 10074 + }, + { + "epoch": 0.84, + "learning_rate": 1.2659682683269036e-06, + "loss": 0.4771, + "step": 10075 + }, + { + "epoch": 0.84, + "learning_rate": 1.2646488712437654e-06, + "loss": 0.4556, + "step": 10076 + }, + { + "epoch": 0.84, + "learning_rate": 1.2633301156484822e-06, + "loss": 0.4647, + "step": 10077 + }, + { + "epoch": 0.84, + "learning_rate": 1.2620120016378956e-06, + "loss": 0.4549, + "step": 10078 + }, + { + "epoch": 0.84, + "learning_rate": 1.2606945293088047e-06, + "loss": 0.4467, + "step": 10079 + }, + { + "epoch": 0.84, + "learning_rate": 1.2593776987579576e-06, + "loss": 0.4639, + "step": 10080 + }, + { + "epoch": 0.84, + "learning_rate": 1.2580615100820548e-06, + "loss": 0.4664, + "step": 10081 + }, + { + "epoch": 0.84, + "learning_rate": 1.2567459633777567e-06, + "loss": 0.4634, + "step": 10082 + }, + { + "epoch": 0.84, + "learning_rate": 1.2554310587416674e-06, + "loss": 0.4713, + "step": 10083 + }, + { + "epoch": 0.84, + "learning_rate": 1.2541167962703515e-06, + "loss": 0.4783, + "step": 10084 + }, + { + "epoch": 0.84, + "learning_rate": 1.252803176060321e-06, + "loss": 0.4557, + "step": 10085 + }, + { + "epoch": 0.84, + "learning_rate": 1.251490198208043e-06, + "loss": 0.4748, + "step": 10086 + }, + { + "epoch": 0.84, + "learning_rate": 1.2501778628099349e-06, + "loss": 0.4805, + "step": 10087 + }, + { + "epoch": 0.84, + "learning_rate": 1.2488661699623739e-06, + "loss": 0.4657, + "step": 10088 + }, + { + "epoch": 0.84, + "learning_rate": 1.247555119761682e-06, + "loss": 0.4644, + "step": 10089 + }, + { + "epoch": 0.84, + "learning_rate": 1.2462447123041388e-06, + "loss": 0.464, + "step": 10090 + }, + { + "epoch": 0.84, + "learning_rate": 1.244934947685974e-06, + "loss": 0.4735, + "step": 10091 + }, + { + "epoch": 0.84, + "learning_rate": 1.2436258260033696e-06, + "loss": 0.4721, + "step": 10092 + }, + { + "epoch": 0.84, + "learning_rate": 1.2423173473524653e-06, + "loss": 0.4823, + "step": 10093 + }, + { + "epoch": 0.84, + "learning_rate": 1.2410095118293475e-06, + "loss": 0.4499, + "step": 10094 + }, + { + "epoch": 0.84, + "learning_rate": 1.2397023195300618e-06, + "loss": 0.4769, + "step": 10095 + }, + { + "epoch": 0.84, + "learning_rate": 1.238395770550601e-06, + "loss": 0.4584, + "step": 10096 + }, + { + "epoch": 0.84, + "learning_rate": 1.2370898649869122e-06, + "loss": 0.4785, + "step": 10097 + }, + { + "epoch": 0.84, + "learning_rate": 1.2357846029348975e-06, + "loss": 0.461, + "step": 10098 + }, + { + "epoch": 0.84, + "learning_rate": 1.2344799844904065e-06, + "loss": 0.4563, + "step": 10099 + }, + { + "epoch": 0.85, + "learning_rate": 1.2331760097492485e-06, + "loss": 0.4628, + "step": 10100 + }, + { + "epoch": 0.85, + "learning_rate": 1.2318726788071767e-06, + "loss": 0.4704, + "step": 10101 + }, + { + "epoch": 0.85, + "learning_rate": 1.230569991759909e-06, + "loss": 0.473, + "step": 10102 + }, + { + "epoch": 0.85, + "learning_rate": 1.2292679487031045e-06, + "loss": 0.4632, + "step": 10103 + }, + { + "epoch": 0.85, + "learning_rate": 1.2279665497323835e-06, + "loss": 0.4495, + "step": 10104 + }, + { + "epoch": 0.85, + "learning_rate": 1.2266657949433135e-06, + "loss": 0.4662, + "step": 10105 + }, + { + "epoch": 0.85, + "learning_rate": 1.2253656844314155e-06, + "loss": 0.4628, + "step": 10106 + }, + { + "epoch": 0.85, + "learning_rate": 1.224066218292167e-06, + "loss": 0.4859, + "step": 10107 + }, + { + "epoch": 0.85, + "learning_rate": 1.2227673966209896e-06, + "loss": 0.4671, + "step": 10108 + }, + { + "epoch": 0.85, + "learning_rate": 1.2214692195132705e-06, + "loss": 0.4454, + "step": 10109 + }, + { + "epoch": 0.85, + "learning_rate": 1.2201716870643388e-06, + "loss": 0.458, + "step": 10110 + }, + { + "epoch": 0.85, + "learning_rate": 1.2188747993694805e-06, + "loss": 0.452, + "step": 10111 + }, + { + "epoch": 0.85, + "learning_rate": 1.217578556523934e-06, + "loss": 0.4621, + "step": 10112 + }, + { + "epoch": 0.85, + "learning_rate": 1.2162829586228874e-06, + "loss": 0.4471, + "step": 10113 + }, + { + "epoch": 0.85, + "learning_rate": 1.214988005761487e-06, + "loss": 0.4653, + "step": 10114 + }, + { + "epoch": 0.85, + "learning_rate": 1.2136936980348267e-06, + "loss": 0.4649, + "step": 10115 + }, + { + "epoch": 0.85, + "learning_rate": 1.2124000355379583e-06, + "loss": 0.4577, + "step": 10116 + }, + { + "epoch": 0.85, + "learning_rate": 1.21110701836588e-06, + "loss": 0.4553, + "step": 10117 + }, + { + "epoch": 0.85, + "learning_rate": 1.2098146466135475e-06, + "loss": 0.4912, + "step": 10118 + }, + { + "epoch": 0.85, + "learning_rate": 1.2085229203758663e-06, + "loss": 0.4616, + "step": 10119 + }, + { + "epoch": 0.85, + "learning_rate": 1.2072318397476945e-06, + "loss": 0.4577, + "step": 10120 + }, + { + "epoch": 0.85, + "learning_rate": 1.2059414048238437e-06, + "loss": 0.4583, + "step": 10121 + }, + { + "epoch": 0.85, + "learning_rate": 1.2046516156990796e-06, + "loss": 0.4592, + "step": 10122 + }, + { + "epoch": 0.85, + "learning_rate": 1.2033624724681191e-06, + "loss": 0.468, + "step": 10123 + }, + { + "epoch": 0.85, + "learning_rate": 1.2020739752256282e-06, + "loss": 0.4817, + "step": 10124 + }, + { + "epoch": 0.85, + "learning_rate": 1.2007861240662334e-06, + "loss": 0.4542, + "step": 10125 + }, + { + "epoch": 0.85, + "learning_rate": 1.1994989190845075e-06, + "loss": 0.4465, + "step": 10126 + }, + { + "epoch": 0.85, + "learning_rate": 1.1982123603749762e-06, + "loss": 0.455, + "step": 10127 + }, + { + "epoch": 0.85, + "learning_rate": 1.1969264480321175e-06, + "loss": 0.465, + "step": 10128 + }, + { + "epoch": 0.85, + "learning_rate": 1.1956411821503688e-06, + "loss": 0.462, + "step": 10129 + }, + { + "epoch": 0.85, + "learning_rate": 1.1943565628241105e-06, + "loss": 0.4554, + "step": 10130 + }, + { + "epoch": 0.85, + "learning_rate": 1.1930725901476814e-06, + "loss": 0.4542, + "step": 10131 + }, + { + "epoch": 0.85, + "learning_rate": 1.1917892642153706e-06, + "loss": 0.469, + "step": 10132 + }, + { + "epoch": 0.85, + "learning_rate": 1.190506585121418e-06, + "loss": 0.4819, + "step": 10133 + }, + { + "epoch": 0.85, + "learning_rate": 1.1892245529600222e-06, + "loss": 0.4757, + "step": 10134 + }, + { + "epoch": 0.85, + "learning_rate": 1.1879431678253261e-06, + "loss": 0.4704, + "step": 10135 + }, + { + "epoch": 0.85, + "learning_rate": 1.1866624298114338e-06, + "loss": 0.459, + "step": 10136 + }, + { + "epoch": 0.85, + "learning_rate": 1.1853823390123964e-06, + "loss": 0.4646, + "step": 10137 + }, + { + "epoch": 0.85, + "learning_rate": 1.1841028955222155e-06, + "loss": 0.4662, + "step": 10138 + }, + { + "epoch": 0.85, + "learning_rate": 1.1828240994348517e-06, + "loss": 0.4671, + "step": 10139 + }, + { + "epoch": 0.85, + "learning_rate": 1.1815459508442118e-06, + "loss": 0.4511, + "step": 10140 + }, + { + "epoch": 0.85, + "learning_rate": 1.1802684498441585e-06, + "loss": 0.4797, + "step": 10141 + }, + { + "epoch": 0.85, + "learning_rate": 1.1789915965285037e-06, + "loss": 0.4553, + "step": 10142 + }, + { + "epoch": 0.85, + "learning_rate": 1.177715390991019e-06, + "loss": 0.4775, + "step": 10143 + }, + { + "epoch": 0.85, + "learning_rate": 1.1764398333254202e-06, + "loss": 0.4567, + "step": 10144 + }, + { + "epoch": 0.85, + "learning_rate": 1.1751649236253815e-06, + "loss": 0.4767, + "step": 10145 + }, + { + "epoch": 0.85, + "learning_rate": 1.1738906619845248e-06, + "loss": 0.4722, + "step": 10146 + }, + { + "epoch": 0.85, + "learning_rate": 1.1726170484964282e-06, + "loss": 0.4849, + "step": 10147 + }, + { + "epoch": 0.85, + "learning_rate": 1.1713440832546196e-06, + "loss": 0.4432, + "step": 10148 + }, + { + "epoch": 0.85, + "learning_rate": 1.1700717663525784e-06, + "loss": 0.4562, + "step": 10149 + }, + { + "epoch": 0.85, + "learning_rate": 1.1688000978837423e-06, + "loss": 0.478, + "step": 10150 + }, + { + "epoch": 0.85, + "learning_rate": 1.1675290779414949e-06, + "loss": 0.4653, + "step": 10151 + }, + { + "epoch": 0.85, + "learning_rate": 1.1662587066191755e-06, + "loss": 0.4584, + "step": 10152 + }, + { + "epoch": 0.85, + "learning_rate": 1.1649889840100737e-06, + "loss": 0.4666, + "step": 10153 + }, + { + "epoch": 0.85, + "learning_rate": 1.1637199102074326e-06, + "loss": 0.4629, + "step": 10154 + }, + { + "epoch": 0.85, + "learning_rate": 1.1624514853044488e-06, + "loss": 0.4594, + "step": 10155 + }, + { + "epoch": 0.85, + "learning_rate": 1.1611837093942691e-06, + "loss": 0.4912, + "step": 10156 + }, + { + "epoch": 0.85, + "learning_rate": 1.1599165825699955e-06, + "loss": 0.4794, + "step": 10157 + }, + { + "epoch": 0.85, + "learning_rate": 1.1586501049246801e-06, + "loss": 0.4589, + "step": 10158 + }, + { + "epoch": 0.85, + "learning_rate": 1.1573842765513266e-06, + "loss": 0.4812, + "step": 10159 + }, + { + "epoch": 0.85, + "learning_rate": 1.1561190975428926e-06, + "loss": 0.4629, + "step": 10160 + }, + { + "epoch": 0.85, + "learning_rate": 1.1548545679922885e-06, + "loss": 0.4512, + "step": 10161 + }, + { + "epoch": 0.85, + "learning_rate": 1.153590687992372e-06, + "loss": 0.4553, + "step": 10162 + }, + { + "epoch": 0.85, + "learning_rate": 1.1523274576359633e-06, + "loss": 0.4647, + "step": 10163 + }, + { + "epoch": 0.85, + "learning_rate": 1.151064877015825e-06, + "loss": 0.4667, + "step": 10164 + }, + { + "epoch": 0.85, + "learning_rate": 1.1498029462246752e-06, + "loss": 0.4664, + "step": 10165 + }, + { + "epoch": 0.85, + "learning_rate": 1.1485416653551884e-06, + "loss": 0.459, + "step": 10166 + }, + { + "epoch": 0.85, + "learning_rate": 1.1472810344999852e-06, + "loss": 0.4335, + "step": 10167 + }, + { + "epoch": 0.85, + "learning_rate": 1.1460210537516426e-06, + "loss": 0.4746, + "step": 10168 + }, + { + "epoch": 0.85, + "learning_rate": 1.1447617232026842e-06, + "loss": 0.4671, + "step": 10169 + }, + { + "epoch": 0.85, + "learning_rate": 1.1435030429455951e-06, + "loss": 0.4687, + "step": 10170 + }, + { + "epoch": 0.85, + "learning_rate": 1.1422450130728069e-06, + "loss": 0.4722, + "step": 10171 + }, + { + "epoch": 0.85, + "learning_rate": 1.1409876336767013e-06, + "loss": 0.4592, + "step": 10172 + }, + { + "epoch": 0.85, + "learning_rate": 1.1397309048496174e-06, + "loss": 0.4744, + "step": 10173 + }, + { + "epoch": 0.85, + "learning_rate": 1.1384748266838408e-06, + "loss": 0.4578, + "step": 10174 + }, + { + "epoch": 0.85, + "learning_rate": 1.1372193992716175e-06, + "loss": 0.467, + "step": 10175 + }, + { + "epoch": 0.85, + "learning_rate": 1.1359646227051357e-06, + "loss": 0.4537, + "step": 10176 + }, + { + "epoch": 0.85, + "learning_rate": 1.1347104970765466e-06, + "loss": 0.454, + "step": 10177 + }, + { + "epoch": 0.85, + "learning_rate": 1.133457022477945e-06, + "loss": 0.475, + "step": 10178 + }, + { + "epoch": 0.85, + "learning_rate": 1.1322041990013798e-06, + "loss": 0.4638, + "step": 10179 + }, + { + "epoch": 0.85, + "learning_rate": 1.130952026738855e-06, + "loss": 0.4609, + "step": 10180 + }, + { + "epoch": 0.85, + "learning_rate": 1.1297005057823251e-06, + "loss": 0.4676, + "step": 10181 + }, + { + "epoch": 0.85, + "learning_rate": 1.1284496362236952e-06, + "loss": 0.4789, + "step": 10182 + }, + { + "epoch": 0.85, + "learning_rate": 1.1271994181548217e-06, + "loss": 0.4718, + "step": 10183 + }, + { + "epoch": 0.85, + "learning_rate": 1.1259498516675204e-06, + "loss": 0.4717, + "step": 10184 + }, + { + "epoch": 0.85, + "learning_rate": 1.12470093685355e-06, + "loss": 0.4607, + "step": 10185 + }, + { + "epoch": 0.85, + "learning_rate": 1.1234526738046303e-06, + "loss": 0.4358, + "step": 10186 + }, + { + "epoch": 0.85, + "learning_rate": 1.122205062612426e-06, + "loss": 0.474, + "step": 10187 + }, + { + "epoch": 0.85, + "learning_rate": 1.1209581033685558e-06, + "loss": 0.4668, + "step": 10188 + }, + { + "epoch": 0.85, + "learning_rate": 1.1197117961645921e-06, + "loss": 0.4598, + "step": 10189 + }, + { + "epoch": 0.85, + "learning_rate": 1.118466141092055e-06, + "loss": 0.4466, + "step": 10190 + }, + { + "epoch": 0.85, + "learning_rate": 1.1172211382424269e-06, + "loss": 0.4796, + "step": 10191 + }, + { + "epoch": 0.85, + "learning_rate": 1.1159767877071314e-06, + "loss": 0.461, + "step": 10192 + }, + { + "epoch": 0.85, + "learning_rate": 1.1147330895775498e-06, + "loss": 0.472, + "step": 10193 + }, + { + "epoch": 0.85, + "learning_rate": 1.1134900439450124e-06, + "loss": 0.4753, + "step": 10194 + }, + { + "epoch": 0.85, + "learning_rate": 1.112247650900804e-06, + "loss": 0.449, + "step": 10195 + }, + { + "epoch": 0.85, + "learning_rate": 1.1110059105361616e-06, + "loss": 0.4559, + "step": 10196 + }, + { + "epoch": 0.85, + "learning_rate": 1.1097648229422719e-06, + "loss": 0.4649, + "step": 10197 + }, + { + "epoch": 0.85, + "learning_rate": 1.108524388210278e-06, + "loss": 0.4535, + "step": 10198 + }, + { + "epoch": 0.85, + "learning_rate": 1.1072846064312715e-06, + "loss": 0.4645, + "step": 10199 + }, + { + "epoch": 0.85, + "learning_rate": 1.1060454776962947e-06, + "loss": 0.4628, + "step": 10200 + }, + { + "epoch": 0.85, + "learning_rate": 1.1048070020963453e-06, + "loss": 0.4658, + "step": 10201 + }, + { + "epoch": 0.85, + "learning_rate": 1.1035691797223724e-06, + "loss": 0.4706, + "step": 10202 + }, + { + "epoch": 0.85, + "learning_rate": 1.1023320106652735e-06, + "loss": 0.4566, + "step": 10203 + }, + { + "epoch": 0.85, + "learning_rate": 1.1010954950159058e-06, + "loss": 0.4699, + "step": 10204 + }, + { + "epoch": 0.85, + "learning_rate": 1.0998596328650724e-06, + "loss": 0.4587, + "step": 10205 + }, + { + "epoch": 0.85, + "learning_rate": 1.098624424303526e-06, + "loss": 0.4722, + "step": 10206 + }, + { + "epoch": 0.85, + "learning_rate": 1.0973898694219809e-06, + "loss": 0.4548, + "step": 10207 + }, + { + "epoch": 0.85, + "learning_rate": 1.0961559683110946e-06, + "loss": 0.4523, + "step": 10208 + }, + { + "epoch": 0.85, + "learning_rate": 1.0949227210614798e-06, + "loss": 0.4467, + "step": 10209 + }, + { + "epoch": 0.85, + "learning_rate": 1.0936901277637002e-06, + "loss": 0.4952, + "step": 10210 + }, + { + "epoch": 0.85, + "learning_rate": 1.0924581885082753e-06, + "loss": 0.4745, + "step": 10211 + }, + { + "epoch": 0.85, + "learning_rate": 1.0912269033856716e-06, + "loss": 0.45, + "step": 10212 + }, + { + "epoch": 0.85, + "learning_rate": 1.089996272486309e-06, + "loss": 0.4564, + "step": 10213 + }, + { + "epoch": 0.85, + "learning_rate": 1.088766295900562e-06, + "loss": 0.4536, + "step": 10214 + }, + { + "epoch": 0.85, + "learning_rate": 1.0875369737187502e-06, + "loss": 0.4627, + "step": 10215 + }, + { + "epoch": 0.85, + "learning_rate": 1.0863083060311563e-06, + "loss": 0.4539, + "step": 10216 + }, + { + "epoch": 0.85, + "learning_rate": 1.0850802929280034e-06, + "loss": 0.474, + "step": 10217 + }, + { + "epoch": 0.85, + "learning_rate": 1.0838529344994763e-06, + "loss": 0.4448, + "step": 10218 + }, + { + "epoch": 0.85, + "learning_rate": 1.0826262308357038e-06, + "loss": 0.4548, + "step": 10219 + }, + { + "epoch": 0.86, + "learning_rate": 1.0814001820267717e-06, + "loss": 0.4531, + "step": 10220 + }, + { + "epoch": 0.86, + "learning_rate": 1.0801747881627134e-06, + "loss": 0.4624, + "step": 10221 + }, + { + "epoch": 0.86, + "learning_rate": 1.0789500493335191e-06, + "loss": 0.4819, + "step": 10222 + }, + { + "epoch": 0.86, + "learning_rate": 1.0777259656291284e-06, + "loss": 0.4558, + "step": 10223 + }, + { + "epoch": 0.86, + "learning_rate": 1.07650253713943e-06, + "loss": 0.4588, + "step": 10224 + }, + { + "epoch": 0.86, + "learning_rate": 1.0752797639542712e-06, + "loss": 0.4649, + "step": 10225 + }, + { + "epoch": 0.86, + "learning_rate": 1.0740576461634466e-06, + "loss": 0.4855, + "step": 10226 + }, + { + "epoch": 0.86, + "learning_rate": 1.0728361838567003e-06, + "loss": 0.4787, + "step": 10227 + }, + { + "epoch": 0.86, + "learning_rate": 1.0716153771237359e-06, + "loss": 0.4544, + "step": 10228 + }, + { + "epoch": 0.86, + "learning_rate": 1.0703952260542016e-06, + "loss": 0.4666, + "step": 10229 + }, + { + "epoch": 0.86, + "learning_rate": 1.0691757307377014e-06, + "loss": 0.4757, + "step": 10230 + }, + { + "epoch": 0.86, + "learning_rate": 1.0679568912637872e-06, + "loss": 0.4772, + "step": 10231 + }, + { + "epoch": 0.86, + "learning_rate": 1.0667387077219704e-06, + "loss": 0.4798, + "step": 10232 + }, + { + "epoch": 0.86, + "learning_rate": 1.0655211802017052e-06, + "loss": 0.4355, + "step": 10233 + }, + { + "epoch": 0.86, + "learning_rate": 1.0643043087924043e-06, + "loss": 0.4507, + "step": 10234 + }, + { + "epoch": 0.86, + "learning_rate": 1.0630880935834286e-06, + "loss": 0.4636, + "step": 10235 + }, + { + "epoch": 0.86, + "learning_rate": 1.0618725346640902e-06, + "loss": 0.4574, + "step": 10236 + }, + { + "epoch": 0.86, + "learning_rate": 1.0606576321236585e-06, + "loss": 0.473, + "step": 10237 + }, + { + "epoch": 0.86, + "learning_rate": 1.0594433860513452e-06, + "loss": 0.458, + "step": 10238 + }, + { + "epoch": 0.86, + "learning_rate": 1.0582297965363264e-06, + "loss": 0.4414, + "step": 10239 + }, + { + "epoch": 0.86, + "learning_rate": 1.0570168636677191e-06, + "loss": 0.4564, + "step": 10240 + }, + { + "epoch": 0.86, + "learning_rate": 1.055804587534598e-06, + "loss": 0.4609, + "step": 10241 + }, + { + "epoch": 0.86, + "learning_rate": 1.0545929682259847e-06, + "loss": 0.4552, + "step": 10242 + }, + { + "epoch": 0.86, + "learning_rate": 1.0533820058308576e-06, + "loss": 0.487, + "step": 10243 + }, + { + "epoch": 0.86, + "learning_rate": 1.0521717004381427e-06, + "loss": 0.4707, + "step": 10244 + }, + { + "epoch": 0.86, + "learning_rate": 1.0509620521367225e-06, + "loss": 0.4729, + "step": 10245 + }, + { + "epoch": 0.86, + "learning_rate": 1.0497530610154283e-06, + "loss": 0.4663, + "step": 10246 + }, + { + "epoch": 0.86, + "learning_rate": 1.04854472716304e-06, + "loss": 0.4829, + "step": 10247 + }, + { + "epoch": 0.86, + "learning_rate": 1.0473370506682968e-06, + "loss": 0.4565, + "step": 10248 + }, + { + "epoch": 0.86, + "learning_rate": 1.046130031619883e-06, + "loss": 0.4666, + "step": 10249 + }, + { + "epoch": 0.86, + "learning_rate": 1.044923670106439e-06, + "loss": 0.4489, + "step": 10250 + }, + { + "epoch": 0.86, + "learning_rate": 1.0437179662165508e-06, + "loss": 0.4793, + "step": 10251 + }, + { + "epoch": 0.86, + "learning_rate": 1.0425129200387662e-06, + "loss": 0.4564, + "step": 10252 + }, + { + "epoch": 0.86, + "learning_rate": 1.0413085316615745e-06, + "loss": 0.47, + "step": 10253 + }, + { + "epoch": 0.86, + "learning_rate": 1.0401048011734227e-06, + "loss": 0.4469, + "step": 10254 + }, + { + "epoch": 0.86, + "learning_rate": 1.0389017286627078e-06, + "loss": 0.4772, + "step": 10255 + }, + { + "epoch": 0.86, + "learning_rate": 1.0376993142177771e-06, + "loss": 0.475, + "step": 10256 + }, + { + "epoch": 0.86, + "learning_rate": 1.036497557926931e-06, + "loss": 0.4524, + "step": 10257 + }, + { + "epoch": 0.86, + "learning_rate": 1.035296459878421e-06, + "loss": 0.4645, + "step": 10258 + }, + { + "epoch": 0.86, + "learning_rate": 1.0340960201604544e-06, + "loss": 0.4579, + "step": 10259 + }, + { + "epoch": 0.86, + "learning_rate": 1.0328962388611841e-06, + "loss": 0.4659, + "step": 10260 + }, + { + "epoch": 0.86, + "learning_rate": 1.0316971160687172e-06, + "loss": 0.4552, + "step": 10261 + }, + { + "epoch": 0.86, + "learning_rate": 1.0304986518711124e-06, + "loss": 0.452, + "step": 10262 + }, + { + "epoch": 0.86, + "learning_rate": 1.029300846356379e-06, + "loss": 0.4648, + "step": 10263 + }, + { + "epoch": 0.86, + "learning_rate": 1.0281036996124793e-06, + "loss": 0.4696, + "step": 10264 + }, + { + "epoch": 0.86, + "learning_rate": 1.026907211727326e-06, + "loss": 0.4558, + "step": 10265 + }, + { + "epoch": 0.86, + "learning_rate": 1.0257113827887865e-06, + "loss": 0.4506, + "step": 10266 + }, + { + "epoch": 0.86, + "learning_rate": 1.0245162128846764e-06, + "loss": 0.4555, + "step": 10267 + }, + { + "epoch": 0.86, + "learning_rate": 1.023321702102762e-06, + "loss": 0.4706, + "step": 10268 + }, + { + "epoch": 0.86, + "learning_rate": 1.0221278505307665e-06, + "loss": 0.4593, + "step": 10269 + }, + { + "epoch": 0.86, + "learning_rate": 1.0209346582563596e-06, + "loss": 0.4606, + "step": 10270 + }, + { + "epoch": 0.86, + "learning_rate": 1.0197421253671646e-06, + "loss": 0.458, + "step": 10271 + }, + { + "epoch": 0.86, + "learning_rate": 1.018550251950755e-06, + "loss": 0.4643, + "step": 10272 + }, + { + "epoch": 0.86, + "learning_rate": 1.0173590380946596e-06, + "loss": 0.497, + "step": 10273 + }, + { + "epoch": 0.86, + "learning_rate": 1.016168483886356e-06, + "loss": 0.4946, + "step": 10274 + }, + { + "epoch": 0.86, + "learning_rate": 1.0149785894132714e-06, + "loss": 0.4545, + "step": 10275 + }, + { + "epoch": 0.86, + "learning_rate": 1.0137893547627875e-06, + "loss": 0.4669, + "step": 10276 + }, + { + "epoch": 0.86, + "learning_rate": 1.0126007800222347e-06, + "loss": 0.4839, + "step": 10277 + }, + { + "epoch": 0.86, + "learning_rate": 1.0114128652789023e-06, + "loss": 0.4633, + "step": 10278 + }, + { + "epoch": 0.86, + "learning_rate": 1.0102256106200203e-06, + "loss": 0.4627, + "step": 10279 + }, + { + "epoch": 0.86, + "learning_rate": 1.0090390161327801e-06, + "loss": 0.4656, + "step": 10280 + }, + { + "epoch": 0.86, + "learning_rate": 1.0078530819043174e-06, + "loss": 0.4692, + "step": 10281 + }, + { + "epoch": 0.86, + "learning_rate": 1.006667808021725e-06, + "loss": 0.4646, + "step": 10282 + }, + { + "epoch": 0.86, + "learning_rate": 1.0054831945720411e-06, + "loss": 0.4597, + "step": 10283 + }, + { + "epoch": 0.86, + "learning_rate": 1.0042992416422614e-06, + "loss": 0.4651, + "step": 10284 + }, + { + "epoch": 0.86, + "learning_rate": 1.0031159493193277e-06, + "loss": 0.4696, + "step": 10285 + }, + { + "epoch": 0.86, + "learning_rate": 1.001933317690139e-06, + "loss": 0.4727, + "step": 10286 + }, + { + "epoch": 0.86, + "learning_rate": 1.000751346841542e-06, + "loss": 0.4629, + "step": 10287 + }, + { + "epoch": 0.86, + "learning_rate": 9.995700368603333e-07, + "loss": 0.4629, + "step": 10288 + }, + { + "epoch": 0.86, + "learning_rate": 9.983893878332674e-07, + "loss": 0.4644, + "step": 10289 + }, + { + "epoch": 0.86, + "learning_rate": 9.972093998470444e-07, + "loss": 0.4686, + "step": 10290 + }, + { + "epoch": 0.86, + "learning_rate": 9.960300729883177e-07, + "loss": 0.4609, + "step": 10291 + }, + { + "epoch": 0.86, + "learning_rate": 9.9485140734369e-07, + "loss": 0.4454, + "step": 10292 + }, + { + "epoch": 0.86, + "learning_rate": 9.936734029997218e-07, + "loss": 0.4597, + "step": 10293 + }, + { + "epoch": 0.86, + "learning_rate": 9.92496060042919e-07, + "loss": 0.4802, + "step": 10294 + }, + { + "epoch": 0.86, + "learning_rate": 9.913193785597396e-07, + "loss": 0.4629, + "step": 10295 + }, + { + "epoch": 0.86, + "learning_rate": 9.90143358636596e-07, + "loss": 0.4501, + "step": 10296 + }, + { + "epoch": 0.86, + "learning_rate": 9.88968000359849e-07, + "loss": 0.4537, + "step": 10297 + }, + { + "epoch": 0.86, + "learning_rate": 9.877933038158105e-07, + "loss": 0.464, + "step": 10298 + }, + { + "epoch": 0.86, + "learning_rate": 9.866192690907472e-07, + "loss": 0.4678, + "step": 10299 + }, + { + "epoch": 0.86, + "learning_rate": 9.85445896270878e-07, + "loss": 0.4739, + "step": 10300 + }, + { + "epoch": 0.86, + "learning_rate": 9.84273185442367e-07, + "loss": 0.4806, + "step": 10301 + }, + { + "epoch": 0.86, + "learning_rate": 9.831011366913335e-07, + "loss": 0.4504, + "step": 10302 + }, + { + "epoch": 0.86, + "learning_rate": 9.819297501038494e-07, + "loss": 0.4628, + "step": 10303 + }, + { + "epoch": 0.86, + "learning_rate": 9.80759025765935e-07, + "loss": 0.4659, + "step": 10304 + }, + { + "epoch": 0.86, + "learning_rate": 9.795889637635636e-07, + "loss": 0.4496, + "step": 10305 + }, + { + "epoch": 0.86, + "learning_rate": 9.78419564182659e-07, + "loss": 0.4522, + "step": 10306 + }, + { + "epoch": 0.86, + "learning_rate": 9.772508271090997e-07, + "loss": 0.4757, + "step": 10307 + }, + { + "epoch": 0.86, + "learning_rate": 9.760827526287108e-07, + "loss": 0.4711, + "step": 10308 + }, + { + "epoch": 0.86, + "learning_rate": 9.749153408272693e-07, + "loss": 0.4507, + "step": 10309 + }, + { + "epoch": 0.86, + "learning_rate": 9.737485917905088e-07, + "loss": 0.4604, + "step": 10310 + }, + { + "epoch": 0.86, + "learning_rate": 9.725825056041094e-07, + "loss": 0.4598, + "step": 10311 + }, + { + "epoch": 0.86, + "learning_rate": 9.714170823537007e-07, + "loss": 0.471, + "step": 10312 + }, + { + "epoch": 0.86, + "learning_rate": 9.702523221248706e-07, + "loss": 0.4624, + "step": 10313 + }, + { + "epoch": 0.86, + "learning_rate": 9.69088225003152e-07, + "loss": 0.4548, + "step": 10314 + }, + { + "epoch": 0.86, + "learning_rate": 9.679247910740331e-07, + "loss": 0.4672, + "step": 10315 + }, + { + "epoch": 0.86, + "learning_rate": 9.667620204229488e-07, + "loss": 0.4596, + "step": 10316 + }, + { + "epoch": 0.86, + "learning_rate": 9.6559991313529e-07, + "loss": 0.447, + "step": 10317 + }, + { + "epoch": 0.86, + "learning_rate": 9.64438469296396e-07, + "loss": 0.4531, + "step": 10318 + }, + { + "epoch": 0.86, + "learning_rate": 9.632776889915595e-07, + "loss": 0.4692, + "step": 10319 + }, + { + "epoch": 0.86, + "learning_rate": 9.621175723060216e-07, + "loss": 0.4731, + "step": 10320 + }, + { + "epoch": 0.86, + "learning_rate": 9.609581193249794e-07, + "loss": 0.4477, + "step": 10321 + }, + { + "epoch": 0.86, + "learning_rate": 9.597993301335773e-07, + "loss": 0.48, + "step": 10322 + }, + { + "epoch": 0.86, + "learning_rate": 9.586412048169114e-07, + "loss": 0.4617, + "step": 10323 + }, + { + "epoch": 0.86, + "learning_rate": 9.574837434600293e-07, + "loss": 0.4565, + "step": 10324 + }, + { + "epoch": 0.86, + "learning_rate": 9.563269461479307e-07, + "loss": 0.4485, + "step": 10325 + }, + { + "epoch": 0.86, + "learning_rate": 9.551708129655635e-07, + "loss": 0.4653, + "step": 10326 + }, + { + "epoch": 0.86, + "learning_rate": 9.54015343997834e-07, + "loss": 0.46, + "step": 10327 + }, + { + "epoch": 0.86, + "learning_rate": 9.528605393295909e-07, + "loss": 0.4716, + "step": 10328 + }, + { + "epoch": 0.86, + "learning_rate": 9.517063990456399e-07, + "loss": 0.4637, + "step": 10329 + }, + { + "epoch": 0.86, + "learning_rate": 9.505529232307376e-07, + "loss": 0.4507, + "step": 10330 + }, + { + "epoch": 0.86, + "learning_rate": 9.494001119695884e-07, + "loss": 0.4772, + "step": 10331 + }, + { + "epoch": 0.86, + "learning_rate": 9.482479653468512e-07, + "loss": 0.4558, + "step": 10332 + }, + { + "epoch": 0.86, + "learning_rate": 9.47096483447133e-07, + "loss": 0.4491, + "step": 10333 + }, + { + "epoch": 0.86, + "learning_rate": 9.459456663549959e-07, + "loss": 0.4573, + "step": 10334 + }, + { + "epoch": 0.86, + "learning_rate": 9.447955141549514e-07, + "loss": 0.4429, + "step": 10335 + }, + { + "epoch": 0.86, + "learning_rate": 9.436460269314607e-07, + "loss": 0.4629, + "step": 10336 + }, + { + "epoch": 0.86, + "learning_rate": 9.424972047689374e-07, + "loss": 0.4625, + "step": 10337 + }, + { + "epoch": 0.86, + "learning_rate": 9.413490477517462e-07, + "loss": 0.4684, + "step": 10338 + }, + { + "epoch": 0.87, + "learning_rate": 9.402015559642019e-07, + "loss": 0.4807, + "step": 10339 + }, + { + "epoch": 0.87, + "learning_rate": 9.390547294905739e-07, + "loss": 0.4669, + "step": 10340 + }, + { + "epoch": 0.87, + "learning_rate": 9.379085684150779e-07, + "loss": 0.4493, + "step": 10341 + }, + { + "epoch": 0.87, + "learning_rate": 9.367630728218868e-07, + "loss": 0.4639, + "step": 10342 + }, + { + "epoch": 0.87, + "learning_rate": 9.356182427951188e-07, + "loss": 0.4678, + "step": 10343 + }, + { + "epoch": 0.87, + "learning_rate": 9.344740784188445e-07, + "loss": 0.4619, + "step": 10344 + }, + { + "epoch": 0.87, + "learning_rate": 9.333305797770887e-07, + "loss": 0.489, + "step": 10345 + }, + { + "epoch": 0.87, + "learning_rate": 9.321877469538232e-07, + "loss": 0.4565, + "step": 10346 + }, + { + "epoch": 0.87, + "learning_rate": 9.31045580032972e-07, + "loss": 0.4754, + "step": 10347 + }, + { + "epoch": 0.87, + "learning_rate": 9.299040790984137e-07, + "loss": 0.4564, + "step": 10348 + }, + { + "epoch": 0.87, + "learning_rate": 9.287632442339756e-07, + "loss": 0.472, + "step": 10349 + }, + { + "epoch": 0.87, + "learning_rate": 9.276230755234328e-07, + "loss": 0.4752, + "step": 10350 + }, + { + "epoch": 0.87, + "learning_rate": 9.264835730505184e-07, + "loss": 0.4529, + "step": 10351 + }, + { + "epoch": 0.87, + "learning_rate": 9.25344736898911e-07, + "loss": 0.4372, + "step": 10352 + }, + { + "epoch": 0.87, + "learning_rate": 9.242065671522393e-07, + "loss": 0.4867, + "step": 10353 + }, + { + "epoch": 0.87, + "learning_rate": 9.230690638940898e-07, + "loss": 0.4552, + "step": 10354 + }, + { + "epoch": 0.87, + "learning_rate": 9.219322272079955e-07, + "loss": 0.47, + "step": 10355 + }, + { + "epoch": 0.87, + "learning_rate": 9.207960571774388e-07, + "loss": 0.459, + "step": 10356 + }, + { + "epoch": 0.87, + "learning_rate": 9.196605538858571e-07, + "loss": 0.4625, + "step": 10357 + }, + { + "epoch": 0.87, + "learning_rate": 9.185257174166362e-07, + "loss": 0.4528, + "step": 10358 + }, + { + "epoch": 0.87, + "learning_rate": 9.173915478531148e-07, + "loss": 0.4446, + "step": 10359 + }, + { + "epoch": 0.87, + "learning_rate": 9.162580452785775e-07, + "loss": 0.477, + "step": 10360 + }, + { + "epoch": 0.87, + "learning_rate": 9.151252097762675e-07, + "loss": 0.4613, + "step": 10361 + }, + { + "epoch": 0.87, + "learning_rate": 9.139930414293774e-07, + "loss": 0.4511, + "step": 10362 + }, + { + "epoch": 0.87, + "learning_rate": 9.128615403210472e-07, + "loss": 0.4492, + "step": 10363 + }, + { + "epoch": 0.87, + "learning_rate": 9.117307065343683e-07, + "loss": 0.4666, + "step": 10364 + }, + { + "epoch": 0.87, + "learning_rate": 9.106005401523865e-07, + "loss": 0.4672, + "step": 10365 + }, + { + "epoch": 0.87, + "learning_rate": 9.094710412580942e-07, + "loss": 0.4787, + "step": 10366 + }, + { + "epoch": 0.87, + "learning_rate": 9.083422099344375e-07, + "loss": 0.4664, + "step": 10367 + }, + { + "epoch": 0.87, + "learning_rate": 9.072140462643154e-07, + "loss": 0.4515, + "step": 10368 + }, + { + "epoch": 0.87, + "learning_rate": 9.060865503305738e-07, + "loss": 0.4508, + "step": 10369 + }, + { + "epoch": 0.87, + "learning_rate": 9.049597222160111e-07, + "loss": 0.4644, + "step": 10370 + }, + { + "epoch": 0.87, + "learning_rate": 9.038335620033756e-07, + "loss": 0.4454, + "step": 10371 + }, + { + "epoch": 0.87, + "learning_rate": 9.02708069775372e-07, + "loss": 0.4649, + "step": 10372 + }, + { + "epoch": 0.87, + "learning_rate": 9.015832456146489e-07, + "loss": 0.4778, + "step": 10373 + }, + { + "epoch": 0.87, + "learning_rate": 9.004590896038068e-07, + "loss": 0.4462, + "step": 10374 + }, + { + "epoch": 0.87, + "learning_rate": 8.99335601825404e-07, + "loss": 0.4462, + "step": 10375 + }, + { + "epoch": 0.87, + "learning_rate": 8.982127823619413e-07, + "loss": 0.4594, + "step": 10376 + }, + { + "epoch": 0.87, + "learning_rate": 8.970906312958749e-07, + "loss": 0.4522, + "step": 10377 + }, + { + "epoch": 0.87, + "learning_rate": 8.959691487096111e-07, + "loss": 0.482, + "step": 10378 + }, + { + "epoch": 0.87, + "learning_rate": 8.948483346855064e-07, + "loss": 0.4502, + "step": 10379 + }, + { + "epoch": 0.87, + "learning_rate": 8.937281893058658e-07, + "loss": 0.4623, + "step": 10380 + }, + { + "epoch": 0.87, + "learning_rate": 8.926087126529548e-07, + "loss": 0.4559, + "step": 10381 + }, + { + "epoch": 0.87, + "learning_rate": 8.914899048089765e-07, + "loss": 0.4734, + "step": 10382 + }, + { + "epoch": 0.87, + "learning_rate": 8.903717658560961e-07, + "loss": 0.4638, + "step": 10383 + }, + { + "epoch": 0.87, + "learning_rate": 8.892542958764238e-07, + "loss": 0.4368, + "step": 10384 + }, + { + "epoch": 0.87, + "learning_rate": 8.881374949520216e-07, + "loss": 0.4844, + "step": 10385 + }, + { + "epoch": 0.87, + "learning_rate": 8.870213631649038e-07, + "loss": 0.4673, + "step": 10386 + }, + { + "epoch": 0.87, + "learning_rate": 8.859059005970305e-07, + "loss": 0.4555, + "step": 10387 + }, + { + "epoch": 0.87, + "learning_rate": 8.847911073303206e-07, + "loss": 0.4701, + "step": 10388 + }, + { + "epoch": 0.87, + "learning_rate": 8.836769834466397e-07, + "loss": 0.4677, + "step": 10389 + }, + { + "epoch": 0.87, + "learning_rate": 8.825635290278034e-07, + "loss": 0.4631, + "step": 10390 + }, + { + "epoch": 0.87, + "learning_rate": 8.814507441555775e-07, + "loss": 0.4691, + "step": 10391 + }, + { + "epoch": 0.87, + "learning_rate": 8.803386289116833e-07, + "loss": 0.4743, + "step": 10392 + }, + { + "epoch": 0.87, + "learning_rate": 8.792271833777888e-07, + "loss": 0.4724, + "step": 10393 + }, + { + "epoch": 0.87, + "learning_rate": 8.78116407635512e-07, + "loss": 0.4461, + "step": 10394 + }, + { + "epoch": 0.87, + "learning_rate": 8.770063017664276e-07, + "loss": 0.4705, + "step": 10395 + }, + { + "epoch": 0.87, + "learning_rate": 8.75896865852055e-07, + "loss": 0.4547, + "step": 10396 + }, + { + "epoch": 0.87, + "learning_rate": 8.747880999738667e-07, + "loss": 0.4837, + "step": 10397 + }, + { + "epoch": 0.87, + "learning_rate": 8.736800042132853e-07, + "loss": 0.4696, + "step": 10398 + }, + { + "epoch": 0.87, + "learning_rate": 8.725725786516858e-07, + "loss": 0.4605, + "step": 10399 + }, + { + "epoch": 0.87, + "learning_rate": 8.714658233703921e-07, + "loss": 0.4868, + "step": 10400 + }, + { + "epoch": 0.87, + "learning_rate": 8.703597384506779e-07, + "loss": 0.4542, + "step": 10401 + }, + { + "epoch": 0.87, + "learning_rate": 8.692543239737706e-07, + "loss": 0.4542, + "step": 10402 + }, + { + "epoch": 0.87, + "learning_rate": 8.681495800208517e-07, + "loss": 0.4587, + "step": 10403 + }, + { + "epoch": 0.87, + "learning_rate": 8.670455066730444e-07, + "loss": 0.4659, + "step": 10404 + }, + { + "epoch": 0.87, + "learning_rate": 8.65942104011428e-07, + "loss": 0.474, + "step": 10405 + }, + { + "epoch": 0.87, + "learning_rate": 8.648393721170323e-07, + "loss": 0.4734, + "step": 10406 + }, + { + "epoch": 0.87, + "learning_rate": 8.63737311070837e-07, + "loss": 0.4765, + "step": 10407 + }, + { + "epoch": 0.87, + "learning_rate": 8.626359209537716e-07, + "loss": 0.4577, + "step": 10408 + }, + { + "epoch": 0.87, + "learning_rate": 8.615352018467204e-07, + "loss": 0.4625, + "step": 10409 + }, + { + "epoch": 0.87, + "learning_rate": 8.604351538305156e-07, + "loss": 0.4697, + "step": 10410 + }, + { + "epoch": 0.87, + "learning_rate": 8.593357769859368e-07, + "loss": 0.4622, + "step": 10411 + }, + { + "epoch": 0.87, + "learning_rate": 8.582370713937193e-07, + "loss": 0.4769, + "step": 10412 + }, + { + "epoch": 0.87, + "learning_rate": 8.571390371345489e-07, + "loss": 0.4899, + "step": 10413 + }, + { + "epoch": 0.87, + "learning_rate": 8.560416742890599e-07, + "loss": 0.4746, + "step": 10414 + }, + { + "epoch": 0.87, + "learning_rate": 8.549449829378354e-07, + "loss": 0.4566, + "step": 10415 + }, + { + "epoch": 0.87, + "learning_rate": 8.538489631614167e-07, + "loss": 0.4804, + "step": 10416 + }, + { + "epoch": 0.87, + "learning_rate": 8.527536150402882e-07, + "loss": 0.4592, + "step": 10417 + }, + { + "epoch": 0.87, + "learning_rate": 8.516589386548879e-07, + "loss": 0.4471, + "step": 10418 + }, + { + "epoch": 0.87, + "learning_rate": 8.505649340856048e-07, + "loss": 0.4799, + "step": 10419 + }, + { + "epoch": 0.87, + "learning_rate": 8.494716014127768e-07, + "loss": 0.4877, + "step": 10420 + }, + { + "epoch": 0.87, + "learning_rate": 8.483789407166932e-07, + "loss": 0.4582, + "step": 10421 + }, + { + "epoch": 0.87, + "learning_rate": 8.472869520775972e-07, + "loss": 0.4554, + "step": 10422 + }, + { + "epoch": 0.87, + "learning_rate": 8.461956355756772e-07, + "loss": 0.4487, + "step": 10423 + }, + { + "epoch": 0.87, + "learning_rate": 8.451049912910769e-07, + "loss": 0.4454, + "step": 10424 + }, + { + "epoch": 0.87, + "learning_rate": 8.440150193038888e-07, + "loss": 0.4578, + "step": 10425 + }, + { + "epoch": 0.87, + "learning_rate": 8.429257196941554e-07, + "loss": 0.4786, + "step": 10426 + }, + { + "epoch": 0.87, + "learning_rate": 8.418370925418695e-07, + "loss": 0.4635, + "step": 10427 + }, + { + "epoch": 0.87, + "learning_rate": 8.407491379269739e-07, + "loss": 0.4748, + "step": 10428 + }, + { + "epoch": 0.87, + "learning_rate": 8.396618559293679e-07, + "loss": 0.4652, + "step": 10429 + }, + { + "epoch": 0.87, + "learning_rate": 8.385752466288933e-07, + "loss": 0.4624, + "step": 10430 + }, + { + "epoch": 0.87, + "learning_rate": 8.374893101053482e-07, + "loss": 0.4563, + "step": 10431 + }, + { + "epoch": 0.87, + "learning_rate": 8.364040464384771e-07, + "loss": 0.4677, + "step": 10432 + }, + { + "epoch": 0.87, + "learning_rate": 8.353194557079791e-07, + "loss": 0.4588, + "step": 10433 + }, + { + "epoch": 0.87, + "learning_rate": 8.34235537993503e-07, + "loss": 0.4498, + "step": 10434 + }, + { + "epoch": 0.87, + "learning_rate": 8.331522933746428e-07, + "loss": 0.4734, + "step": 10435 + }, + { + "epoch": 0.87, + "learning_rate": 8.320697219309526e-07, + "loss": 0.4523, + "step": 10436 + }, + { + "epoch": 0.87, + "learning_rate": 8.309878237419289e-07, + "loss": 0.4687, + "step": 10437 + }, + { + "epoch": 0.87, + "learning_rate": 8.299065988870236e-07, + "loss": 0.4675, + "step": 10438 + }, + { + "epoch": 0.87, + "learning_rate": 8.288260474456367e-07, + "loss": 0.4673, + "step": 10439 + }, + { + "epoch": 0.87, + "learning_rate": 8.277461694971178e-07, + "loss": 0.4436, + "step": 10440 + }, + { + "epoch": 0.87, + "learning_rate": 8.266669651207704e-07, + "loss": 0.4659, + "step": 10441 + }, + { + "epoch": 0.87, + "learning_rate": 8.255884343958453e-07, + "loss": 0.4867, + "step": 10442 + }, + { + "epoch": 0.87, + "learning_rate": 8.245105774015461e-07, + "loss": 0.4468, + "step": 10443 + }, + { + "epoch": 0.87, + "learning_rate": 8.234333942170281e-07, + "loss": 0.4678, + "step": 10444 + }, + { + "epoch": 0.87, + "learning_rate": 8.223568849213925e-07, + "loss": 0.4726, + "step": 10445 + }, + { + "epoch": 0.87, + "learning_rate": 8.212810495936952e-07, + "loss": 0.4651, + "step": 10446 + }, + { + "epoch": 0.87, + "learning_rate": 8.202058883129404e-07, + "loss": 0.474, + "step": 10447 + }, + { + "epoch": 0.87, + "learning_rate": 8.191314011580842e-07, + "loss": 0.4809, + "step": 10448 + }, + { + "epoch": 0.87, + "learning_rate": 8.180575882080288e-07, + "loss": 0.4541, + "step": 10449 + }, + { + "epoch": 0.87, + "learning_rate": 8.169844495416368e-07, + "loss": 0.4656, + "step": 10450 + }, + { + "epoch": 0.87, + "learning_rate": 8.159119852377106e-07, + "loss": 0.4456, + "step": 10451 + }, + { + "epoch": 0.87, + "learning_rate": 8.148401953750096e-07, + "loss": 0.4625, + "step": 10452 + }, + { + "epoch": 0.87, + "learning_rate": 8.137690800322384e-07, + "loss": 0.4638, + "step": 10453 + }, + { + "epoch": 0.87, + "learning_rate": 8.126986392880587e-07, + "loss": 0.4811, + "step": 10454 + }, + { + "epoch": 0.87, + "learning_rate": 8.116288732210787e-07, + "loss": 0.4776, + "step": 10455 + }, + { + "epoch": 0.87, + "learning_rate": 8.105597819098554e-07, + "loss": 0.4533, + "step": 10456 + }, + { + "epoch": 0.87, + "learning_rate": 8.094913654329018e-07, + "loss": 0.4689, + "step": 10457 + }, + { + "epoch": 0.87, + "learning_rate": 8.08423623868676e-07, + "loss": 0.4605, + "step": 10458 + }, + { + "epoch": 0.88, + "learning_rate": 8.073565572955877e-07, + "loss": 0.4652, + "step": 10459 + }, + { + "epoch": 0.88, + "learning_rate": 8.062901657919998e-07, + "loss": 0.4584, + "step": 10460 + }, + { + "epoch": 0.88, + "learning_rate": 8.052244494362227e-07, + "loss": 0.4699, + "step": 10461 + }, + { + "epoch": 0.88, + "learning_rate": 8.041594083065152e-07, + "loss": 0.4525, + "step": 10462 + }, + { + "epoch": 0.88, + "learning_rate": 8.030950424810946e-07, + "loss": 0.476, + "step": 10463 + }, + { + "epoch": 0.88, + "learning_rate": 8.020313520381206e-07, + "loss": 0.4795, + "step": 10464 + }, + { + "epoch": 0.88, + "learning_rate": 8.009683370557075e-07, + "loss": 0.4751, + "step": 10465 + }, + { + "epoch": 0.88, + "learning_rate": 7.999059976119183e-07, + "loss": 0.4427, + "step": 10466 + }, + { + "epoch": 0.88, + "learning_rate": 7.988443337847673e-07, + "loss": 0.4616, + "step": 10467 + }, + { + "epoch": 0.88, + "learning_rate": 7.977833456522166e-07, + "loss": 0.4687, + "step": 10468 + }, + { + "epoch": 0.88, + "learning_rate": 7.967230332921816e-07, + "loss": 0.4731, + "step": 10469 + }, + { + "epoch": 0.88, + "learning_rate": 7.956633967825289e-07, + "loss": 0.4715, + "step": 10470 + }, + { + "epoch": 0.88, + "learning_rate": 7.946044362010718e-07, + "loss": 0.4532, + "step": 10471 + }, + { + "epoch": 0.88, + "learning_rate": 7.935461516255782e-07, + "loss": 0.4768, + "step": 10472 + }, + { + "epoch": 0.88, + "learning_rate": 7.924885431337604e-07, + "loss": 0.4527, + "step": 10473 + }, + { + "epoch": 0.88, + "learning_rate": 7.914316108032882e-07, + "loss": 0.4693, + "step": 10474 + }, + { + "epoch": 0.88, + "learning_rate": 7.903753547117788e-07, + "loss": 0.4768, + "step": 10475 + }, + { + "epoch": 0.88, + "learning_rate": 7.893197749367943e-07, + "loss": 0.4678, + "step": 10476 + }, + { + "epoch": 0.88, + "learning_rate": 7.882648715558583e-07, + "loss": 0.4589, + "step": 10477 + }, + { + "epoch": 0.88, + "learning_rate": 7.872106446464345e-07, + "loss": 0.4649, + "step": 10478 + }, + { + "epoch": 0.88, + "learning_rate": 7.861570942859431e-07, + "loss": 0.4652, + "step": 10479 + }, + { + "epoch": 0.88, + "learning_rate": 7.851042205517512e-07, + "loss": 0.4853, + "step": 10480 + }, + { + "epoch": 0.88, + "learning_rate": 7.840520235211768e-07, + "loss": 0.4503, + "step": 10481 + }, + { + "epoch": 0.88, + "learning_rate": 7.830005032714905e-07, + "loss": 0.463, + "step": 10482 + }, + { + "epoch": 0.88, + "learning_rate": 7.819496598799093e-07, + "loss": 0.4523, + "step": 10483 + }, + { + "epoch": 0.88, + "learning_rate": 7.808994934236058e-07, + "loss": 0.4681, + "step": 10484 + }, + { + "epoch": 0.88, + "learning_rate": 7.798500039796974e-07, + "loss": 0.4989, + "step": 10485 + }, + { + "epoch": 0.88, + "learning_rate": 7.788011916252558e-07, + "loss": 0.4629, + "step": 10486 + }, + { + "epoch": 0.88, + "learning_rate": 7.777530564373015e-07, + "loss": 0.4475, + "step": 10487 + }, + { + "epoch": 0.88, + "learning_rate": 7.767055984928041e-07, + "loss": 0.4632, + "step": 10488 + }, + { + "epoch": 0.88, + "learning_rate": 7.756588178686853e-07, + "loss": 0.4704, + "step": 10489 + }, + { + "epoch": 0.88, + "learning_rate": 7.746127146418148e-07, + "loss": 0.4527, + "step": 10490 + }, + { + "epoch": 0.88, + "learning_rate": 7.735672888890155e-07, + "loss": 0.4651, + "step": 10491 + }, + { + "epoch": 0.88, + "learning_rate": 7.725225406870607e-07, + "loss": 0.4569, + "step": 10492 + }, + { + "epoch": 0.88, + "learning_rate": 7.714784701126687e-07, + "loss": 0.464, + "step": 10493 + }, + { + "epoch": 0.88, + "learning_rate": 7.704350772425129e-07, + "loss": 0.4621, + "step": 10494 + }, + { + "epoch": 0.88, + "learning_rate": 7.693923621532184e-07, + "loss": 0.4683, + "step": 10495 + }, + { + "epoch": 0.88, + "learning_rate": 7.683503249213554e-07, + "loss": 0.4905, + "step": 10496 + }, + { + "epoch": 0.88, + "learning_rate": 7.673089656234456e-07, + "loss": 0.4562, + "step": 10497 + }, + { + "epoch": 0.88, + "learning_rate": 7.662682843359648e-07, + "loss": 0.4489, + "step": 10498 + }, + { + "epoch": 0.88, + "learning_rate": 7.652282811353362e-07, + "loss": 0.4638, + "step": 10499 + }, + { + "epoch": 0.88, + "learning_rate": 7.641889560979321e-07, + "loss": 0.4682, + "step": 10500 + }, + { + "epoch": 0.88, + "learning_rate": 7.631503093000758e-07, + "loss": 0.4702, + "step": 10501 + }, + { + "epoch": 0.88, + "learning_rate": 7.621123408180419e-07, + "loss": 0.4686, + "step": 10502 + }, + { + "epoch": 0.88, + "learning_rate": 7.61075050728054e-07, + "loss": 0.452, + "step": 10503 + }, + { + "epoch": 0.88, + "learning_rate": 7.600384391062865e-07, + "loss": 0.4584, + "step": 10504 + }, + { + "epoch": 0.88, + "learning_rate": 7.590025060288642e-07, + "loss": 0.4783, + "step": 10505 + }, + { + "epoch": 0.88, + "learning_rate": 7.579672515718628e-07, + "loss": 0.4468, + "step": 10506 + }, + { + "epoch": 0.88, + "learning_rate": 7.569326758113049e-07, + "loss": 0.4802, + "step": 10507 + }, + { + "epoch": 0.88, + "learning_rate": 7.558987788231675e-07, + "loss": 0.4594, + "step": 10508 + }, + { + "epoch": 0.88, + "learning_rate": 7.548655606833755e-07, + "loss": 0.4826, + "step": 10509 + }, + { + "epoch": 0.88, + "learning_rate": 7.538330214678002e-07, + "loss": 0.4664, + "step": 10510 + }, + { + "epoch": 0.88, + "learning_rate": 7.528011612522723e-07, + "loss": 0.4502, + "step": 10511 + }, + { + "epoch": 0.88, + "learning_rate": 7.517699801125655e-07, + "loss": 0.45, + "step": 10512 + }, + { + "epoch": 0.88, + "learning_rate": 7.507394781244038e-07, + "loss": 0.4798, + "step": 10513 + }, + { + "epoch": 0.88, + "learning_rate": 7.497096553634653e-07, + "loss": 0.4694, + "step": 10514 + }, + { + "epoch": 0.88, + "learning_rate": 7.48680511905373e-07, + "loss": 0.4539, + "step": 10515 + }, + { + "epoch": 0.88, + "learning_rate": 7.476520478257065e-07, + "loss": 0.466, + "step": 10516 + }, + { + "epoch": 0.88, + "learning_rate": 7.466242631999887e-07, + "loss": 0.4647, + "step": 10517 + }, + { + "epoch": 0.88, + "learning_rate": 7.455971581036991e-07, + "loss": 0.4704, + "step": 10518 + }, + { + "epoch": 0.88, + "learning_rate": 7.44570732612262e-07, + "loss": 0.4576, + "step": 10519 + }, + { + "epoch": 0.88, + "learning_rate": 7.435449868010535e-07, + "loss": 0.4648, + "step": 10520 + }, + { + "epoch": 0.88, + "learning_rate": 7.425199207454014e-07, + "loss": 0.4485, + "step": 10521 + }, + { + "epoch": 0.88, + "learning_rate": 7.41495534520581e-07, + "loss": 0.4636, + "step": 10522 + }, + { + "epoch": 0.88, + "learning_rate": 7.404718282018197e-07, + "loss": 0.4768, + "step": 10523 + }, + { + "epoch": 0.88, + "learning_rate": 7.394488018642931e-07, + "loss": 0.4482, + "step": 10524 + }, + { + "epoch": 0.88, + "learning_rate": 7.3842645558313e-07, + "loss": 0.4373, + "step": 10525 + }, + { + "epoch": 0.88, + "learning_rate": 7.374047894334047e-07, + "loss": 0.4618, + "step": 10526 + }, + { + "epoch": 0.88, + "learning_rate": 7.363838034901471e-07, + "loss": 0.4681, + "step": 10527 + }, + { + "epoch": 0.88, + "learning_rate": 7.35363497828333e-07, + "loss": 0.4577, + "step": 10528 + }, + { + "epoch": 0.88, + "learning_rate": 7.343438725228891e-07, + "loss": 0.4653, + "step": 10529 + }, + { + "epoch": 0.88, + "learning_rate": 7.33324927648692e-07, + "loss": 0.4989, + "step": 10530 + }, + { + "epoch": 0.88, + "learning_rate": 7.323066632805676e-07, + "loss": 0.4368, + "step": 10531 + }, + { + "epoch": 0.88, + "learning_rate": 7.312890794932969e-07, + "loss": 0.4771, + "step": 10532 + }, + { + "epoch": 0.88, + "learning_rate": 7.302721763616039e-07, + "loss": 0.4751, + "step": 10533 + }, + { + "epoch": 0.88, + "learning_rate": 7.292559539601674e-07, + "loss": 0.4537, + "step": 10534 + }, + { + "epoch": 0.88, + "learning_rate": 7.28240412363611e-07, + "loss": 0.4543, + "step": 10535 + }, + { + "epoch": 0.88, + "learning_rate": 7.272255516465176e-07, + "loss": 0.4839, + "step": 10536 + }, + { + "epoch": 0.88, + "learning_rate": 7.262113718834086e-07, + "loss": 0.4525, + "step": 10537 + }, + { + "epoch": 0.88, + "learning_rate": 7.251978731487664e-07, + "loss": 0.4823, + "step": 10538 + }, + { + "epoch": 0.88, + "learning_rate": 7.241850555170149e-07, + "loss": 0.4638, + "step": 10539 + }, + { + "epoch": 0.88, + "learning_rate": 7.231729190625314e-07, + "loss": 0.4807, + "step": 10540 + }, + { + "epoch": 0.88, + "learning_rate": 7.221614638596441e-07, + "loss": 0.4729, + "step": 10541 + }, + { + "epoch": 0.88, + "learning_rate": 7.211506899826304e-07, + "loss": 0.4802, + "step": 10542 + }, + { + "epoch": 0.88, + "learning_rate": 7.201405975057152e-07, + "loss": 0.4365, + "step": 10543 + }, + { + "epoch": 0.88, + "learning_rate": 7.191311865030748e-07, + "loss": 0.4644, + "step": 10544 + }, + { + "epoch": 0.88, + "learning_rate": 7.18122457048841e-07, + "loss": 0.4555, + "step": 10545 + }, + { + "epoch": 0.88, + "learning_rate": 7.171144092170845e-07, + "loss": 0.4495, + "step": 10546 + }, + { + "epoch": 0.88, + "learning_rate": 7.161070430818385e-07, + "loss": 0.4348, + "step": 10547 + }, + { + "epoch": 0.88, + "learning_rate": 7.151003587170757e-07, + "loss": 0.4765, + "step": 10548 + }, + { + "epoch": 0.88, + "learning_rate": 7.14094356196724e-07, + "loss": 0.4557, + "step": 10549 + }, + { + "epoch": 0.88, + "learning_rate": 7.130890355946596e-07, + "loss": 0.4436, + "step": 10550 + }, + { + "epoch": 0.88, + "learning_rate": 7.12084396984708e-07, + "loss": 0.4619, + "step": 10551 + }, + { + "epoch": 0.88, + "learning_rate": 7.11080440440648e-07, + "loss": 0.4572, + "step": 10552 + }, + { + "epoch": 0.88, + "learning_rate": 7.100771660362061e-07, + "loss": 0.464, + "step": 10553 + }, + { + "epoch": 0.88, + "learning_rate": 7.090745738450566e-07, + "loss": 0.465, + "step": 10554 + }, + { + "epoch": 0.88, + "learning_rate": 7.080726639408264e-07, + "loss": 0.4505, + "step": 10555 + }, + { + "epoch": 0.88, + "learning_rate": 7.070714363970899e-07, + "loss": 0.458, + "step": 10556 + }, + { + "epoch": 0.88, + "learning_rate": 7.060708912873771e-07, + "loss": 0.4661, + "step": 10557 + }, + { + "epoch": 0.88, + "learning_rate": 7.050710286851603e-07, + "loss": 0.4561, + "step": 10558 + }, + { + "epoch": 0.88, + "learning_rate": 7.040718486638676e-07, + "loss": 0.4619, + "step": 10559 + }, + { + "epoch": 0.88, + "learning_rate": 7.030733512968735e-07, + "loss": 0.4623, + "step": 10560 + }, + { + "epoch": 0.88, + "learning_rate": 7.020755366575038e-07, + "loss": 0.4636, + "step": 10561 + }, + { + "epoch": 0.88, + "learning_rate": 7.010784048190344e-07, + "loss": 0.4576, + "step": 10562 + }, + { + "epoch": 0.88, + "learning_rate": 7.000819558546901e-07, + "loss": 0.4482, + "step": 10563 + }, + { + "epoch": 0.88, + "learning_rate": 6.990861898376444e-07, + "loss": 0.4662, + "step": 10564 + }, + { + "epoch": 0.88, + "learning_rate": 6.980911068410224e-07, + "loss": 0.4577, + "step": 10565 + }, + { + "epoch": 0.88, + "learning_rate": 6.97096706937902e-07, + "loss": 0.4521, + "step": 10566 + }, + { + "epoch": 0.88, + "learning_rate": 6.961029902013039e-07, + "loss": 0.452, + "step": 10567 + }, + { + "epoch": 0.88, + "learning_rate": 6.951099567042052e-07, + "loss": 0.4763, + "step": 10568 + }, + { + "epoch": 0.88, + "learning_rate": 6.941176065195299e-07, + "loss": 0.4561, + "step": 10569 + }, + { + "epoch": 0.88, + "learning_rate": 6.931259397201517e-07, + "loss": 0.4594, + "step": 10570 + }, + { + "epoch": 0.88, + "learning_rate": 6.921349563788949e-07, + "loss": 0.4663, + "step": 10571 + }, + { + "epoch": 0.88, + "learning_rate": 6.911446565685298e-07, + "loss": 0.4581, + "step": 10572 + }, + { + "epoch": 0.88, + "learning_rate": 6.901550403617852e-07, + "loss": 0.4803, + "step": 10573 + }, + { + "epoch": 0.88, + "learning_rate": 6.891661078313317e-07, + "loss": 0.4621, + "step": 10574 + }, + { + "epoch": 0.88, + "learning_rate": 6.881778590497923e-07, + "loss": 0.4698, + "step": 10575 + }, + { + "epoch": 0.88, + "learning_rate": 6.87190294089738e-07, + "loss": 0.4748, + "step": 10576 + }, + { + "epoch": 0.88, + "learning_rate": 6.86203413023696e-07, + "loss": 0.453, + "step": 10577 + }, + { + "epoch": 0.89, + "learning_rate": 6.852172159241343e-07, + "loss": 0.4714, + "step": 10578 + }, + { + "epoch": 0.89, + "learning_rate": 6.842317028634793e-07, + "loss": 0.4762, + "step": 10579 + }, + { + "epoch": 0.89, + "learning_rate": 6.832468739141007e-07, + "loss": 0.4559, + "step": 10580 + }, + { + "epoch": 0.89, + "learning_rate": 6.822627291483197e-07, + "loss": 0.4699, + "step": 10581 + }, + { + "epoch": 0.89, + "learning_rate": 6.812792686384095e-07, + "loss": 0.4521, + "step": 10582 + }, + { + "epoch": 0.89, + "learning_rate": 6.802964924565891e-07, + "loss": 0.4515, + "step": 10583 + }, + { + "epoch": 0.89, + "learning_rate": 6.793144006750318e-07, + "loss": 0.4689, + "step": 10584 + }, + { + "epoch": 0.89, + "learning_rate": 6.783329933658555e-07, + "loss": 0.4531, + "step": 10585 + }, + { + "epoch": 0.89, + "learning_rate": 6.773522706011337e-07, + "loss": 0.4877, + "step": 10586 + }, + { + "epoch": 0.89, + "learning_rate": 6.763722324528843e-07, + "loss": 0.4599, + "step": 10587 + }, + { + "epoch": 0.89, + "learning_rate": 6.753928789930797e-07, + "loss": 0.469, + "step": 10588 + }, + { + "epoch": 0.89, + "learning_rate": 6.74414210293638e-07, + "loss": 0.4548, + "step": 10589 + }, + { + "epoch": 0.89, + "learning_rate": 6.734362264264283e-07, + "loss": 0.4717, + "step": 10590 + }, + { + "epoch": 0.89, + "learning_rate": 6.724589274632698e-07, + "loss": 0.4463, + "step": 10591 + }, + { + "epoch": 0.89, + "learning_rate": 6.714823134759307e-07, + "loss": 0.4454, + "step": 10592 + }, + { + "epoch": 0.89, + "learning_rate": 6.705063845361315e-07, + "loss": 0.4723, + "step": 10593 + }, + { + "epoch": 0.89, + "learning_rate": 6.695311407155391e-07, + "loss": 0.4621, + "step": 10594 + }, + { + "epoch": 0.89, + "learning_rate": 6.68556582085772e-07, + "loss": 0.4683, + "step": 10595 + }, + { + "epoch": 0.89, + "learning_rate": 6.675827087183961e-07, + "loss": 0.4772, + "step": 10596 + }, + { + "epoch": 0.89, + "learning_rate": 6.666095206849288e-07, + "loss": 0.4646, + "step": 10597 + }, + { + "epoch": 0.89, + "learning_rate": 6.656370180568395e-07, + "loss": 0.4574, + "step": 10598 + }, + { + "epoch": 0.89, + "learning_rate": 6.646652009055409e-07, + "loss": 0.4854, + "step": 10599 + }, + { + "epoch": 0.89, + "learning_rate": 6.63694069302403e-07, + "loss": 0.4795, + "step": 10600 + }, + { + "epoch": 0.89, + "learning_rate": 6.627236233187407e-07, + "loss": 0.4678, + "step": 10601 + }, + { + "epoch": 0.89, + "learning_rate": 6.61753863025818e-07, + "loss": 0.4546, + "step": 10602 + }, + { + "epoch": 0.89, + "learning_rate": 6.607847884948515e-07, + "loss": 0.4514, + "step": 10603 + }, + { + "epoch": 0.89, + "learning_rate": 6.598163997970053e-07, + "loss": 0.4607, + "step": 10604 + }, + { + "epoch": 0.89, + "learning_rate": 6.588486970033936e-07, + "loss": 0.467, + "step": 10605 + }, + { + "epoch": 0.89, + "learning_rate": 6.578816801850796e-07, + "loss": 0.461, + "step": 10606 + }, + { + "epoch": 0.89, + "learning_rate": 6.569153494130798e-07, + "loss": 0.4654, + "step": 10607 + }, + { + "epoch": 0.89, + "learning_rate": 6.55949704758354e-07, + "loss": 0.485, + "step": 10608 + }, + { + "epoch": 0.89, + "learning_rate": 6.549847462918191e-07, + "loss": 0.4681, + "step": 10609 + }, + { + "epoch": 0.89, + "learning_rate": 6.540204740843348e-07, + "loss": 0.4647, + "step": 10610 + }, + { + "epoch": 0.89, + "learning_rate": 6.530568882067145e-07, + "loss": 0.4694, + "step": 10611 + }, + { + "epoch": 0.89, + "learning_rate": 6.520939887297184e-07, + "loss": 0.4592, + "step": 10612 + }, + { + "epoch": 0.89, + "learning_rate": 6.511317757240598e-07, + "loss": 0.4805, + "step": 10613 + }, + { + "epoch": 0.89, + "learning_rate": 6.50170249260399e-07, + "loss": 0.4699, + "step": 10614 + }, + { + "epoch": 0.89, + "learning_rate": 6.492094094093459e-07, + "loss": 0.4552, + "step": 10615 + }, + { + "epoch": 0.89, + "learning_rate": 6.482492562414621e-07, + "loss": 0.4495, + "step": 10616 + }, + { + "epoch": 0.89, + "learning_rate": 6.472897898272534e-07, + "loss": 0.4724, + "step": 10617 + }, + { + "epoch": 0.89, + "learning_rate": 6.463310102371834e-07, + "loss": 0.4603, + "step": 10618 + }, + { + "epoch": 0.89, + "learning_rate": 6.453729175416579e-07, + "loss": 0.4423, + "step": 10619 + }, + { + "epoch": 0.89, + "learning_rate": 6.444155118110373e-07, + "loss": 0.4421, + "step": 10620 + }, + { + "epoch": 0.89, + "learning_rate": 6.434587931156299e-07, + "loss": 0.4656, + "step": 10621 + }, + { + "epoch": 0.89, + "learning_rate": 6.425027615256907e-07, + "loss": 0.4639, + "step": 10622 + }, + { + "epoch": 0.89, + "learning_rate": 6.415474171114288e-07, + "loss": 0.4575, + "step": 10623 + }, + { + "epoch": 0.89, + "learning_rate": 6.405927599429995e-07, + "loss": 0.4592, + "step": 10624 + }, + { + "epoch": 0.89, + "learning_rate": 6.396387900905099e-07, + "loss": 0.4616, + "step": 10625 + }, + { + "epoch": 0.89, + "learning_rate": 6.386855076240117e-07, + "loss": 0.4553, + "step": 10626 + }, + { + "epoch": 0.89, + "learning_rate": 6.377329126135168e-07, + "loss": 0.4603, + "step": 10627 + }, + { + "epoch": 0.89, + "learning_rate": 6.367810051289746e-07, + "loss": 0.4622, + "step": 10628 + }, + { + "epoch": 0.89, + "learning_rate": 6.358297852402894e-07, + "loss": 0.4787, + "step": 10629 + }, + { + "epoch": 0.89, + "learning_rate": 6.348792530173187e-07, + "loss": 0.4648, + "step": 10630 + }, + { + "epoch": 0.89, + "learning_rate": 6.339294085298631e-07, + "loss": 0.4586, + "step": 10631 + }, + { + "epoch": 0.89, + "learning_rate": 6.329802518476746e-07, + "loss": 0.464, + "step": 10632 + }, + { + "epoch": 0.89, + "learning_rate": 6.320317830404554e-07, + "loss": 0.4964, + "step": 10633 + }, + { + "epoch": 0.89, + "learning_rate": 6.310840021778586e-07, + "loss": 0.4679, + "step": 10634 + }, + { + "epoch": 0.89, + "learning_rate": 6.30136909329484e-07, + "loss": 0.4348, + "step": 10635 + }, + { + "epoch": 0.89, + "learning_rate": 6.291905045648839e-07, + "loss": 0.4809, + "step": 10636 + }, + { + "epoch": 0.89, + "learning_rate": 6.282447879535558e-07, + "loss": 0.4575, + "step": 10637 + }, + { + "epoch": 0.89, + "learning_rate": 6.272997595649499e-07, + "loss": 0.4739, + "step": 10638 + }, + { + "epoch": 0.89, + "learning_rate": 6.263554194684662e-07, + "loss": 0.4522, + "step": 10639 + }, + { + "epoch": 0.89, + "learning_rate": 6.254117677334514e-07, + "loss": 0.4417, + "step": 10640 + }, + { + "epoch": 0.89, + "learning_rate": 6.244688044292058e-07, + "loss": 0.4564, + "step": 10641 + }, + { + "epoch": 0.89, + "learning_rate": 6.23526529624976e-07, + "loss": 0.4505, + "step": 10642 + }, + { + "epoch": 0.89, + "learning_rate": 6.225849433899578e-07, + "loss": 0.4596, + "step": 10643 + }, + { + "epoch": 0.89, + "learning_rate": 6.216440457932981e-07, + "loss": 0.4338, + "step": 10644 + }, + { + "epoch": 0.89, + "learning_rate": 6.207038369040918e-07, + "loss": 0.4676, + "step": 10645 + }, + { + "epoch": 0.89, + "learning_rate": 6.197643167913847e-07, + "loss": 0.4753, + "step": 10646 + }, + { + "epoch": 0.89, + "learning_rate": 6.188254855241693e-07, + "loss": 0.4584, + "step": 10647 + }, + { + "epoch": 0.89, + "learning_rate": 6.178873431713928e-07, + "loss": 0.4765, + "step": 10648 + }, + { + "epoch": 0.89, + "learning_rate": 6.169498898019443e-07, + "loss": 0.4592, + "step": 10649 + }, + { + "epoch": 0.89, + "learning_rate": 6.160131254846702e-07, + "loss": 0.4643, + "step": 10650 + }, + { + "epoch": 0.89, + "learning_rate": 6.150770502883618e-07, + "loss": 0.4684, + "step": 10651 + }, + { + "epoch": 0.89, + "learning_rate": 6.141416642817599e-07, + "loss": 0.4886, + "step": 10652 + }, + { + "epoch": 0.89, + "learning_rate": 6.13206967533555e-07, + "loss": 0.4641, + "step": 10653 + }, + { + "epoch": 0.89, + "learning_rate": 6.122729601123878e-07, + "loss": 0.4639, + "step": 10654 + }, + { + "epoch": 0.89, + "learning_rate": 6.113396420868489e-07, + "loss": 0.4511, + "step": 10655 + }, + { + "epoch": 0.89, + "learning_rate": 6.104070135254758e-07, + "loss": 0.4748, + "step": 10656 + }, + { + "epoch": 0.89, + "learning_rate": 6.09475074496757e-07, + "loss": 0.4607, + "step": 10657 + }, + { + "epoch": 0.89, + "learning_rate": 6.085438250691311e-07, + "loss": 0.4689, + "step": 10658 + }, + { + "epoch": 0.89, + "learning_rate": 6.076132653109834e-07, + "loss": 0.4497, + "step": 10659 + }, + { + "epoch": 0.89, + "learning_rate": 6.066833952906515e-07, + "loss": 0.4615, + "step": 10660 + }, + { + "epoch": 0.89, + "learning_rate": 6.057542150764218e-07, + "loss": 0.4654, + "step": 10661 + }, + { + "epoch": 0.89, + "learning_rate": 6.048257247365297e-07, + "loss": 0.4703, + "step": 10662 + }, + { + "epoch": 0.89, + "learning_rate": 6.038979243391597e-07, + "loss": 0.4581, + "step": 10663 + }, + { + "epoch": 0.89, + "learning_rate": 6.029708139524438e-07, + "loss": 0.4653, + "step": 10664 + }, + { + "epoch": 0.89, + "learning_rate": 6.020443936444664e-07, + "loss": 0.4835, + "step": 10665 + }, + { + "epoch": 0.89, + "learning_rate": 6.0111866348326e-07, + "loss": 0.4538, + "step": 10666 + }, + { + "epoch": 0.89, + "learning_rate": 6.001936235368044e-07, + "loss": 0.4771, + "step": 10667 + }, + { + "epoch": 0.89, + "learning_rate": 5.992692738730332e-07, + "loss": 0.4604, + "step": 10668 + }, + { + "epoch": 0.89, + "learning_rate": 5.983456145598266e-07, + "loss": 0.4592, + "step": 10669 + }, + { + "epoch": 0.89, + "learning_rate": 5.974226456650123e-07, + "loss": 0.4773, + "step": 10670 + }, + { + "epoch": 0.89, + "learning_rate": 5.965003672563719e-07, + "loss": 0.472, + "step": 10671 + }, + { + "epoch": 0.89, + "learning_rate": 5.955787794016321e-07, + "loss": 0.4521, + "step": 10672 + }, + { + "epoch": 0.89, + "learning_rate": 5.946578821684713e-07, + "loss": 0.4492, + "step": 10673 + }, + { + "epoch": 0.89, + "learning_rate": 5.937376756245139e-07, + "loss": 0.4726, + "step": 10674 + }, + { + "epoch": 0.89, + "learning_rate": 5.928181598373395e-07, + "loss": 0.4556, + "step": 10675 + }, + { + "epoch": 0.89, + "learning_rate": 5.918993348744728e-07, + "loss": 0.4523, + "step": 10676 + }, + { + "epoch": 0.89, + "learning_rate": 5.909812008033866e-07, + "loss": 0.461, + "step": 10677 + }, + { + "epoch": 0.89, + "learning_rate": 5.900637576915069e-07, + "loss": 0.4729, + "step": 10678 + }, + { + "epoch": 0.89, + "learning_rate": 5.891470056062043e-07, + "loss": 0.4656, + "step": 10679 + }, + { + "epoch": 0.89, + "learning_rate": 5.882309446148038e-07, + "loss": 0.4639, + "step": 10680 + }, + { + "epoch": 0.89, + "learning_rate": 5.87315574784576e-07, + "loss": 0.4651, + "step": 10681 + }, + { + "epoch": 0.89, + "learning_rate": 5.864008961827428e-07, + "loss": 0.4665, + "step": 10682 + }, + { + "epoch": 0.89, + "learning_rate": 5.854869088764737e-07, + "loss": 0.4629, + "step": 10683 + }, + { + "epoch": 0.89, + "learning_rate": 5.845736129328883e-07, + "loss": 0.4569, + "step": 10684 + }, + { + "epoch": 0.89, + "learning_rate": 5.836610084190541e-07, + "loss": 0.455, + "step": 10685 + }, + { + "epoch": 0.89, + "learning_rate": 5.82749095401991e-07, + "loss": 0.4809, + "step": 10686 + }, + { + "epoch": 0.89, + "learning_rate": 5.81837873948663e-07, + "loss": 0.4639, + "step": 10687 + }, + { + "epoch": 0.89, + "learning_rate": 5.809273441259899e-07, + "loss": 0.4451, + "step": 10688 + }, + { + "epoch": 0.89, + "learning_rate": 5.800175060008362e-07, + "loss": 0.4691, + "step": 10689 + }, + { + "epoch": 0.89, + "learning_rate": 5.791083596400148e-07, + "loss": 0.467, + "step": 10690 + }, + { + "epoch": 0.89, + "learning_rate": 5.781999051102927e-07, + "loss": 0.463, + "step": 10691 + }, + { + "epoch": 0.89, + "learning_rate": 5.772921424783806e-07, + "loss": 0.4638, + "step": 10692 + }, + { + "epoch": 0.89, + "learning_rate": 5.763850718109421e-07, + "loss": 0.475, + "step": 10693 + }, + { + "epoch": 0.89, + "learning_rate": 5.754786931745859e-07, + "loss": 0.4652, + "step": 10694 + }, + { + "epoch": 0.89, + "learning_rate": 5.745730066358779e-07, + "loss": 0.4622, + "step": 10695 + }, + { + "epoch": 0.89, + "learning_rate": 5.736680122613237e-07, + "loss": 0.4608, + "step": 10696 + }, + { + "epoch": 0.89, + "learning_rate": 5.727637101173844e-07, + "loss": 0.4586, + "step": 10697 + }, + { + "epoch": 0.9, + "learning_rate": 5.718601002704671e-07, + "loss": 0.442, + "step": 10698 + }, + { + "epoch": 0.9, + "learning_rate": 5.709571827869287e-07, + "loss": 0.4706, + "step": 10699 + }, + { + "epoch": 0.9, + "learning_rate": 5.70054957733076e-07, + "loss": 0.4871, + "step": 10700 + }, + { + "epoch": 0.9, + "learning_rate": 5.691534251751652e-07, + "loss": 0.4701, + "step": 10701 + }, + { + "epoch": 0.9, + "learning_rate": 5.682525851794019e-07, + "loss": 0.4756, + "step": 10702 + }, + { + "epoch": 0.9, + "learning_rate": 5.673524378119388e-07, + "loss": 0.4662, + "step": 10703 + }, + { + "epoch": 0.9, + "learning_rate": 5.664529831388799e-07, + "loss": 0.4683, + "step": 10704 + }, + { + "epoch": 0.9, + "learning_rate": 5.655542212262766e-07, + "loss": 0.4452, + "step": 10705 + }, + { + "epoch": 0.9, + "learning_rate": 5.646561521401317e-07, + "loss": 0.4809, + "step": 10706 + }, + { + "epoch": 0.9, + "learning_rate": 5.637587759463925e-07, + "loss": 0.4604, + "step": 10707 + }, + { + "epoch": 0.9, + "learning_rate": 5.628620927109607e-07, + "loss": 0.4794, + "step": 10708 + }, + { + "epoch": 0.9, + "learning_rate": 5.619661024996848e-07, + "loss": 0.4603, + "step": 10709 + }, + { + "epoch": 0.9, + "learning_rate": 5.610708053783642e-07, + "loss": 0.4669, + "step": 10710 + }, + { + "epoch": 0.9, + "learning_rate": 5.60176201412741e-07, + "loss": 0.471, + "step": 10711 + }, + { + "epoch": 0.9, + "learning_rate": 5.59282290668517e-07, + "loss": 0.4629, + "step": 10712 + }, + { + "epoch": 0.9, + "learning_rate": 5.58389073211335e-07, + "loss": 0.4513, + "step": 10713 + }, + { + "epoch": 0.9, + "learning_rate": 5.574965491067874e-07, + "loss": 0.5152, + "step": 10714 + }, + { + "epoch": 0.9, + "learning_rate": 5.566047184204182e-07, + "loss": 0.4614, + "step": 10715 + }, + { + "epoch": 0.9, + "learning_rate": 5.557135812177228e-07, + "loss": 0.4401, + "step": 10716 + }, + { + "epoch": 0.9, + "learning_rate": 5.548231375641389e-07, + "loss": 0.4655, + "step": 10717 + }, + { + "epoch": 0.9, + "learning_rate": 5.539333875250596e-07, + "loss": 0.4761, + "step": 10718 + }, + { + "epoch": 0.9, + "learning_rate": 5.530443311658218e-07, + "loss": 0.4628, + "step": 10719 + }, + { + "epoch": 0.9, + "learning_rate": 5.521559685517153e-07, + "loss": 0.4645, + "step": 10720 + }, + { + "epoch": 0.9, + "learning_rate": 5.51268299747978e-07, + "loss": 0.4947, + "step": 10721 + }, + { + "epoch": 0.9, + "learning_rate": 5.503813248197965e-07, + "loss": 0.4574, + "step": 10722 + }, + { + "epoch": 0.9, + "learning_rate": 5.494950438323077e-07, + "loss": 0.4685, + "step": 10723 + }, + { + "epoch": 0.9, + "learning_rate": 5.48609456850594e-07, + "loss": 0.4751, + "step": 10724 + }, + { + "epoch": 0.9, + "learning_rate": 5.477245639396922e-07, + "loss": 0.4682, + "step": 10725 + }, + { + "epoch": 0.9, + "learning_rate": 5.468403651645826e-07, + "loss": 0.4474, + "step": 10726 + }, + { + "epoch": 0.9, + "learning_rate": 5.459568605901977e-07, + "loss": 0.4704, + "step": 10727 + }, + { + "epoch": 0.9, + "learning_rate": 5.450740502814178e-07, + "loss": 0.4847, + "step": 10728 + }, + { + "epoch": 0.9, + "learning_rate": 5.441919343030744e-07, + "loss": 0.4695, + "step": 10729 + }, + { + "epoch": 0.9, + "learning_rate": 5.433105127199467e-07, + "loss": 0.4646, + "step": 10730 + }, + { + "epoch": 0.9, + "learning_rate": 5.424297855967597e-07, + "loss": 0.4771, + "step": 10731 + }, + { + "epoch": 0.9, + "learning_rate": 5.415497529981928e-07, + "loss": 0.4748, + "step": 10732 + }, + { + "epoch": 0.9, + "learning_rate": 5.40670414988872e-07, + "loss": 0.4688, + "step": 10733 + }, + { + "epoch": 0.9, + "learning_rate": 5.397917716333723e-07, + "loss": 0.4381, + "step": 10734 + }, + { + "epoch": 0.9, + "learning_rate": 5.389138229962155e-07, + "loss": 0.4684, + "step": 10735 + }, + { + "epoch": 0.9, + "learning_rate": 5.380365691418765e-07, + "loss": 0.4519, + "step": 10736 + }, + { + "epoch": 0.9, + "learning_rate": 5.371600101347763e-07, + "loss": 0.4714, + "step": 10737 + }, + { + "epoch": 0.9, + "learning_rate": 5.362841460392875e-07, + "loss": 0.4653, + "step": 10738 + }, + { + "epoch": 0.9, + "learning_rate": 5.354089769197268e-07, + "loss": 0.4803, + "step": 10739 + }, + { + "epoch": 0.9, + "learning_rate": 5.345345028403659e-07, + "loss": 0.4518, + "step": 10740 + }, + { + "epoch": 0.9, + "learning_rate": 5.33660723865419e-07, + "loss": 0.4649, + "step": 10741 + }, + { + "epoch": 0.9, + "learning_rate": 5.32787640059057e-07, + "loss": 0.461, + "step": 10742 + }, + { + "epoch": 0.9, + "learning_rate": 5.31915251485392e-07, + "loss": 0.4962, + "step": 10743 + }, + { + "epoch": 0.9, + "learning_rate": 5.310435582084917e-07, + "loss": 0.4649, + "step": 10744 + }, + { + "epoch": 0.9, + "learning_rate": 5.301725602923691e-07, + "loss": 0.4624, + "step": 10745 + }, + { + "epoch": 0.9, + "learning_rate": 5.293022578009843e-07, + "loss": 0.467, + "step": 10746 + }, + { + "epoch": 0.9, + "learning_rate": 5.284326507982507e-07, + "loss": 0.4678, + "step": 10747 + }, + { + "epoch": 0.9, + "learning_rate": 5.275637393480282e-07, + "loss": 0.4608, + "step": 10748 + }, + { + "epoch": 0.9, + "learning_rate": 5.266955235141235e-07, + "loss": 0.4783, + "step": 10749 + }, + { + "epoch": 0.9, + "learning_rate": 5.258280033602992e-07, + "loss": 0.4863, + "step": 10750 + }, + { + "epoch": 0.9, + "learning_rate": 5.249611789502607e-07, + "loss": 0.4491, + "step": 10751 + }, + { + "epoch": 0.9, + "learning_rate": 5.240950503476616e-07, + "loss": 0.4695, + "step": 10752 + }, + { + "epoch": 0.9, + "learning_rate": 5.232296176161101e-07, + "loss": 0.4812, + "step": 10753 + }, + { + "epoch": 0.9, + "learning_rate": 5.223648808191584e-07, + "loss": 0.4459, + "step": 10754 + }, + { + "epoch": 0.9, + "learning_rate": 5.215008400203103e-07, + "loss": 0.4771, + "step": 10755 + }, + { + "epoch": 0.9, + "learning_rate": 5.20637495283014e-07, + "loss": 0.4675, + "step": 10756 + }, + { + "epoch": 0.9, + "learning_rate": 5.197748466706742e-07, + "loss": 0.4509, + "step": 10757 + }, + { + "epoch": 0.9, + "learning_rate": 5.189128942466393e-07, + "loss": 0.4566, + "step": 10758 + }, + { + "epoch": 0.9, + "learning_rate": 5.180516380742051e-07, + "loss": 0.4632, + "step": 10759 + }, + { + "epoch": 0.9, + "learning_rate": 5.171910782166212e-07, + "loss": 0.4563, + "step": 10760 + }, + { + "epoch": 0.9, + "learning_rate": 5.163312147370824e-07, + "loss": 0.4507, + "step": 10761 + }, + { + "epoch": 0.9, + "learning_rate": 5.154720476987329e-07, + "loss": 0.4547, + "step": 10762 + }, + { + "epoch": 0.9, + "learning_rate": 5.146135771646655e-07, + "loss": 0.4596, + "step": 10763 + }, + { + "epoch": 0.9, + "learning_rate": 5.137558031979273e-07, + "loss": 0.4456, + "step": 10764 + }, + { + "epoch": 0.9, + "learning_rate": 5.128987258615059e-07, + "loss": 0.4591, + "step": 10765 + }, + { + "epoch": 0.9, + "learning_rate": 5.12042345218342e-07, + "loss": 0.4841, + "step": 10766 + }, + { + "epoch": 0.9, + "learning_rate": 5.111866613313255e-07, + "loss": 0.4637, + "step": 10767 + }, + { + "epoch": 0.9, + "learning_rate": 5.103316742632935e-07, + "loss": 0.4692, + "step": 10768 + }, + { + "epoch": 0.9, + "learning_rate": 5.094773840770306e-07, + "loss": 0.4977, + "step": 10769 + }, + { + "epoch": 0.9, + "learning_rate": 5.086237908352776e-07, + "loss": 0.4727, + "step": 10770 + }, + { + "epoch": 0.9, + "learning_rate": 5.077708946007143e-07, + "loss": 0.4818, + "step": 10771 + }, + { + "epoch": 0.9, + "learning_rate": 5.069186954359761e-07, + "loss": 0.4501, + "step": 10772 + }, + { + "epoch": 0.9, + "learning_rate": 5.060671934036421e-07, + "loss": 0.4501, + "step": 10773 + }, + { + "epoch": 0.9, + "learning_rate": 5.052163885662476e-07, + "loss": 0.4629, + "step": 10774 + }, + { + "epoch": 0.9, + "learning_rate": 5.043662809862692e-07, + "loss": 0.4542, + "step": 10775 + }, + { + "epoch": 0.9, + "learning_rate": 5.03516870726134e-07, + "loss": 0.4559, + "step": 10776 + }, + { + "epoch": 0.9, + "learning_rate": 5.026681578482229e-07, + "loss": 0.4821, + "step": 10777 + }, + { + "epoch": 0.9, + "learning_rate": 5.018201424148606e-07, + "loss": 0.4764, + "step": 10778 + }, + { + "epoch": 0.9, + "learning_rate": 5.009728244883205e-07, + "loss": 0.4775, + "step": 10779 + }, + { + "epoch": 0.9, + "learning_rate": 5.001262041308263e-07, + "loss": 0.4691, + "step": 10780 + }, + { + "epoch": 0.9, + "learning_rate": 4.992802814045505e-07, + "loss": 0.4439, + "step": 10781 + }, + { + "epoch": 0.9, + "learning_rate": 4.984350563716145e-07, + "loss": 0.4732, + "step": 10782 + }, + { + "epoch": 0.9, + "learning_rate": 4.975905290940874e-07, + "loss": 0.4788, + "step": 10783 + }, + { + "epoch": 0.9, + "learning_rate": 4.967466996339887e-07, + "loss": 0.471, + "step": 10784 + }, + { + "epoch": 0.9, + "learning_rate": 4.959035680532854e-07, + "loss": 0.4454, + "step": 10785 + }, + { + "epoch": 0.9, + "learning_rate": 4.950611344138945e-07, + "loss": 0.4511, + "step": 10786 + }, + { + "epoch": 0.9, + "learning_rate": 4.9421939877768e-07, + "loss": 0.4767, + "step": 10787 + }, + { + "epoch": 0.9, + "learning_rate": 4.933783612064546e-07, + "loss": 0.4464, + "step": 10788 + }, + { + "epoch": 0.9, + "learning_rate": 4.925380217619813e-07, + "loss": 0.4537, + "step": 10789 + }, + { + "epoch": 0.9, + "learning_rate": 4.916983805059705e-07, + "loss": 0.4717, + "step": 10790 + }, + { + "epoch": 0.9, + "learning_rate": 4.90859437500083e-07, + "loss": 0.4549, + "step": 10791 + }, + { + "epoch": 0.9, + "learning_rate": 4.900211928059284e-07, + "loss": 0.4547, + "step": 10792 + }, + { + "epoch": 0.9, + "learning_rate": 4.891836464850596e-07, + "loss": 0.4571, + "step": 10793 + }, + { + "epoch": 0.9, + "learning_rate": 4.883467985989876e-07, + "loss": 0.4762, + "step": 10794 + }, + { + "epoch": 0.9, + "learning_rate": 4.875106492091642e-07, + "loss": 0.4692, + "step": 10795 + }, + { + "epoch": 0.9, + "learning_rate": 4.866751983769935e-07, + "loss": 0.4702, + "step": 10796 + }, + { + "epoch": 0.9, + "learning_rate": 4.858404461638266e-07, + "loss": 0.4569, + "step": 10797 + }, + { + "epoch": 0.9, + "learning_rate": 4.850063926309657e-07, + "loss": 0.4488, + "step": 10798 + }, + { + "epoch": 0.9, + "learning_rate": 4.841730378396592e-07, + "loss": 0.4586, + "step": 10799 + }, + { + "epoch": 0.9, + "learning_rate": 4.833403818511062e-07, + "loss": 0.4559, + "step": 10800 + }, + { + "epoch": 0.9, + "learning_rate": 4.825084247264522e-07, + "loss": 0.4566, + "step": 10801 + }, + { + "epoch": 0.9, + "learning_rate": 4.816771665267939e-07, + "loss": 0.4449, + "step": 10802 + }, + { + "epoch": 0.9, + "learning_rate": 4.808466073131735e-07, + "loss": 0.4585, + "step": 10803 + }, + { + "epoch": 0.9, + "learning_rate": 4.800167471465844e-07, + "loss": 0.4537, + "step": 10804 + }, + { + "epoch": 0.9, + "learning_rate": 4.791875860879703e-07, + "loss": 0.4585, + "step": 10805 + }, + { + "epoch": 0.9, + "learning_rate": 4.783591241982199e-07, + "loss": 0.4525, + "step": 10806 + }, + { + "epoch": 0.9, + "learning_rate": 4.775313615381716e-07, + "loss": 0.4708, + "step": 10807 + }, + { + "epoch": 0.9, + "learning_rate": 4.767042981686143e-07, + "loss": 0.4424, + "step": 10808 + }, + { + "epoch": 0.9, + "learning_rate": 4.758779341502817e-07, + "loss": 0.47, + "step": 10809 + }, + { + "epoch": 0.9, + "learning_rate": 4.750522695438597e-07, + "loss": 0.453, + "step": 10810 + }, + { + "epoch": 0.9, + "learning_rate": 4.742273044099821e-07, + "loss": 0.4558, + "step": 10811 + }, + { + "epoch": 0.9, + "learning_rate": 4.7340303880923145e-07, + "loss": 0.4708, + "step": 10812 + }, + { + "epoch": 0.9, + "learning_rate": 4.7257947280213713e-07, + "loss": 0.4453, + "step": 10813 + }, + { + "epoch": 0.9, + "learning_rate": 4.7175660644917745e-07, + "loss": 0.4709, + "step": 10814 + }, + { + "epoch": 0.9, + "learning_rate": 4.709344398107829e-07, + "loss": 0.4792, + "step": 10815 + }, + { + "epoch": 0.9, + "learning_rate": 4.701129729473286e-07, + "loss": 0.4693, + "step": 10816 + }, + { + "epoch": 0.9, + "learning_rate": 4.6929220591913847e-07, + "loss": 0.4548, + "step": 10817 + }, + { + "epoch": 0.91, + "learning_rate": 4.6847213878648876e-07, + "loss": 0.4827, + "step": 10818 + }, + { + "epoch": 0.91, + "learning_rate": 4.6765277160960133e-07, + "loss": 0.4751, + "step": 10819 + }, + { + "epoch": 0.91, + "learning_rate": 4.6683410444864573e-07, + "loss": 0.4529, + "step": 10820 + }, + { + "epoch": 0.91, + "learning_rate": 4.6601613736374173e-07, + "loss": 0.4748, + "step": 10821 + }, + { + "epoch": 0.91, + "learning_rate": 4.6519887041495905e-07, + "loss": 0.4607, + "step": 10822 + }, + { + "epoch": 0.91, + "learning_rate": 4.6438230366231075e-07, + "loss": 0.4451, + "step": 10823 + }, + { + "epoch": 0.91, + "learning_rate": 4.6356643716576557e-07, + "loss": 0.4693, + "step": 10824 + }, + { + "epoch": 0.91, + "learning_rate": 4.627512709852355e-07, + "loss": 0.4662, + "step": 10825 + }, + { + "epoch": 0.91, + "learning_rate": 4.61936805180585e-07, + "loss": 0.4448, + "step": 10826 + }, + { + "epoch": 0.91, + "learning_rate": 4.611230398116229e-07, + "loss": 0.47, + "step": 10827 + }, + { + "epoch": 0.91, + "learning_rate": 4.6030997493811126e-07, + "loss": 0.4645, + "step": 10828 + }, + { + "epoch": 0.91, + "learning_rate": 4.594976106197546e-07, + "loss": 0.435, + "step": 10829 + }, + { + "epoch": 0.91, + "learning_rate": 4.5868594691621304e-07, + "loss": 0.4691, + "step": 10830 + }, + { + "epoch": 0.91, + "learning_rate": 4.5787498388708774e-07, + "loss": 0.4661, + "step": 10831 + }, + { + "epoch": 0.91, + "learning_rate": 4.570647215919366e-07, + "loss": 0.4651, + "step": 10832 + }, + { + "epoch": 0.91, + "learning_rate": 4.5625516009026095e-07, + "loss": 0.4573, + "step": 10833 + }, + { + "epoch": 0.91, + "learning_rate": 4.5544629944150876e-07, + "loss": 0.4668, + "step": 10834 + }, + { + "epoch": 0.91, + "learning_rate": 4.5463813970508364e-07, + "loss": 0.461, + "step": 10835 + }, + { + "epoch": 0.91, + "learning_rate": 4.5383068094033036e-07, + "loss": 0.4437, + "step": 10836 + }, + { + "epoch": 0.91, + "learning_rate": 4.53023923206547e-07, + "loss": 0.4601, + "step": 10837 + }, + { + "epoch": 0.91, + "learning_rate": 4.5221786656297727e-07, + "loss": 0.4662, + "step": 10838 + }, + { + "epoch": 0.91, + "learning_rate": 4.51412511068815e-07, + "loss": 0.4571, + "step": 10839 + }, + { + "epoch": 0.91, + "learning_rate": 4.5060785678320397e-07, + "loss": 0.4747, + "step": 10840 + }, + { + "epoch": 0.91, + "learning_rate": 4.498039037652313e-07, + "loss": 0.4635, + "step": 10841 + }, + { + "epoch": 0.91, + "learning_rate": 4.490006520739387e-07, + "loss": 0.4445, + "step": 10842 + }, + { + "epoch": 0.91, + "learning_rate": 4.4819810176831235e-07, + "loss": 0.4579, + "step": 10843 + }, + { + "epoch": 0.91, + "learning_rate": 4.473962529072873e-07, + "loss": 0.4499, + "step": 10844 + }, + { + "epoch": 0.91, + "learning_rate": 4.465951055497497e-07, + "loss": 0.4692, + "step": 10845 + }, + { + "epoch": 0.91, + "learning_rate": 4.4579465975453264e-07, + "loss": 0.4776, + "step": 10846 + }, + { + "epoch": 0.91, + "learning_rate": 4.4499491558041673e-07, + "loss": 0.4795, + "step": 10847 + }, + { + "epoch": 0.91, + "learning_rate": 4.4419587308613285e-07, + "loss": 0.4559, + "step": 10848 + }, + { + "epoch": 0.91, + "learning_rate": 4.433975323303574e-07, + "loss": 0.4781, + "step": 10849 + }, + { + "epoch": 0.91, + "learning_rate": 4.42599893371719e-07, + "loss": 0.4636, + "step": 10850 + }, + { + "epoch": 0.91, + "learning_rate": 4.418029562687898e-07, + "loss": 0.462, + "step": 10851 + }, + { + "epoch": 0.91, + "learning_rate": 4.4100672108009837e-07, + "loss": 0.4626, + "step": 10852 + }, + { + "epoch": 0.91, + "learning_rate": 4.4021118786411465e-07, + "loss": 0.4657, + "step": 10853 + }, + { + "epoch": 0.91, + "learning_rate": 4.3941635667925866e-07, + "loss": 0.4566, + "step": 10854 + }, + { + "epoch": 0.91, + "learning_rate": 4.3862222758389806e-07, + "loss": 0.4768, + "step": 10855 + }, + { + "epoch": 0.91, + "learning_rate": 4.3782880063635403e-07, + "loss": 0.4521, + "step": 10856 + }, + { + "epoch": 0.91, + "learning_rate": 4.3703607589489105e-07, + "loss": 0.471, + "step": 10857 + }, + { + "epoch": 0.91, + "learning_rate": 4.362440534177226e-07, + "loss": 0.4468, + "step": 10858 + }, + { + "epoch": 0.91, + "learning_rate": 4.3545273326301205e-07, + "loss": 0.4578, + "step": 10859 + }, + { + "epoch": 0.91, + "learning_rate": 4.3466211548887195e-07, + "loss": 0.4488, + "step": 10860 + }, + { + "epoch": 0.91, + "learning_rate": 4.338722001533602e-07, + "loss": 0.4784, + "step": 10861 + }, + { + "epoch": 0.91, + "learning_rate": 4.3308298731448596e-07, + "loss": 0.4639, + "step": 10862 + }, + { + "epoch": 0.91, + "learning_rate": 4.322944770302051e-07, + "loss": 0.4591, + "step": 10863 + }, + { + "epoch": 0.91, + "learning_rate": 4.3150666935842243e-07, + "loss": 0.4511, + "step": 10864 + }, + { + "epoch": 0.91, + "learning_rate": 4.307195643569917e-07, + "loss": 0.459, + "step": 10865 + }, + { + "epoch": 0.91, + "learning_rate": 4.299331620837133e-07, + "loss": 0.4785, + "step": 10866 + }, + { + "epoch": 0.91, + "learning_rate": 4.29147462596341e-07, + "loss": 0.4438, + "step": 10867 + }, + { + "epoch": 0.91, + "learning_rate": 4.283624659525698e-07, + "loss": 0.465, + "step": 10868 + }, + { + "epoch": 0.91, + "learning_rate": 4.2757817221004803e-07, + "loss": 0.4592, + "step": 10869 + }, + { + "epoch": 0.91, + "learning_rate": 4.267945814263708e-07, + "loss": 0.4657, + "step": 10870 + }, + { + "epoch": 0.91, + "learning_rate": 4.2601169365908077e-07, + "loss": 0.4765, + "step": 10871 + }, + { + "epoch": 0.91, + "learning_rate": 4.2522950896566994e-07, + "loss": 0.4664, + "step": 10872 + }, + { + "epoch": 0.91, + "learning_rate": 4.2444802740358114e-07, + "loss": 0.4634, + "step": 10873 + }, + { + "epoch": 0.91, + "learning_rate": 4.2366724903020076e-07, + "loss": 0.4695, + "step": 10874 + }, + { + "epoch": 0.91, + "learning_rate": 4.2288717390286614e-07, + "loss": 0.4691, + "step": 10875 + }, + { + "epoch": 0.91, + "learning_rate": 4.2210780207886383e-07, + "loss": 0.4936, + "step": 10876 + }, + { + "epoch": 0.91, + "learning_rate": 4.2132913361542683e-07, + "loss": 0.4619, + "step": 10877 + }, + { + "epoch": 0.91, + "learning_rate": 4.205511685697372e-07, + "loss": 0.4653, + "step": 10878 + }, + { + "epoch": 0.91, + "learning_rate": 4.1977390699892706e-07, + "loss": 0.4641, + "step": 10879 + }, + { + "epoch": 0.91, + "learning_rate": 4.1899734896007404e-07, + "loss": 0.4697, + "step": 10880 + }, + { + "epoch": 0.91, + "learning_rate": 4.1822149451020475e-07, + "loss": 0.4413, + "step": 10881 + }, + { + "epoch": 0.91, + "learning_rate": 4.1744634370629587e-07, + "loss": 0.4594, + "step": 10882 + }, + { + "epoch": 0.91, + "learning_rate": 4.166718966052696e-07, + "loss": 0.4503, + "step": 10883 + }, + { + "epoch": 0.91, + "learning_rate": 4.158981532640005e-07, + "loss": 0.4772, + "step": 10884 + }, + { + "epoch": 0.91, + "learning_rate": 4.1512511373930533e-07, + "loss": 0.4692, + "step": 10885 + }, + { + "epoch": 0.91, + "learning_rate": 4.143527780879575e-07, + "loss": 0.4666, + "step": 10886 + }, + { + "epoch": 0.91, + "learning_rate": 4.1358114636667056e-07, + "loss": 0.4712, + "step": 10887 + }, + { + "epoch": 0.91, + "learning_rate": 4.128102186321126e-07, + "loss": 0.4737, + "step": 10888 + }, + { + "epoch": 0.91, + "learning_rate": 4.1203999494089596e-07, + "loss": 0.45, + "step": 10889 + }, + { + "epoch": 0.91, + "learning_rate": 4.112704753495822e-07, + "loss": 0.4695, + "step": 10890 + }, + { + "epoch": 0.91, + "learning_rate": 4.1050165991468273e-07, + "loss": 0.4741, + "step": 10891 + }, + { + "epoch": 0.91, + "learning_rate": 4.097335486926546e-07, + "loss": 0.4438, + "step": 10892 + }, + { + "epoch": 0.91, + "learning_rate": 4.08966141739906e-07, + "loss": 0.4623, + "step": 10893 + }, + { + "epoch": 0.91, + "learning_rate": 4.08199439112793e-07, + "loss": 0.4615, + "step": 10894 + }, + { + "epoch": 0.91, + "learning_rate": 4.0743344086761725e-07, + "loss": 0.4557, + "step": 10895 + }, + { + "epoch": 0.91, + "learning_rate": 4.066681470606304e-07, + "loss": 0.482, + "step": 10896 + }, + { + "epoch": 0.91, + "learning_rate": 4.0590355774803416e-07, + "loss": 0.4708, + "step": 10897 + }, + { + "epoch": 0.91, + "learning_rate": 4.051396729859758e-07, + "loss": 0.4756, + "step": 10898 + }, + { + "epoch": 0.91, + "learning_rate": 4.043764928305505e-07, + "loss": 0.466, + "step": 10899 + }, + { + "epoch": 0.91, + "learning_rate": 4.036140173378045e-07, + "loss": 0.4491, + "step": 10900 + }, + { + "epoch": 0.91, + "learning_rate": 4.028522465637319e-07, + "loss": 0.4952, + "step": 10901 + }, + { + "epoch": 0.91, + "learning_rate": 4.0209118056427356e-07, + "loss": 0.4506, + "step": 10902 + }, + { + "epoch": 0.91, + "learning_rate": 4.013308193953169e-07, + "loss": 0.4513, + "step": 10903 + }, + { + "epoch": 0.91, + "learning_rate": 4.0057116311270073e-07, + "loss": 0.4536, + "step": 10904 + }, + { + "epoch": 0.91, + "learning_rate": 3.998122117722125e-07, + "loss": 0.4479, + "step": 10905 + }, + { + "epoch": 0.91, + "learning_rate": 3.990539654295833e-07, + "loss": 0.4539, + "step": 10906 + }, + { + "epoch": 0.91, + "learning_rate": 3.982964241404974e-07, + "loss": 0.4578, + "step": 10907 + }, + { + "epoch": 0.91, + "learning_rate": 3.975395879605881e-07, + "loss": 0.4572, + "step": 10908 + }, + { + "epoch": 0.91, + "learning_rate": 3.96783456945431e-07, + "loss": 0.4333, + "step": 10909 + }, + { + "epoch": 0.91, + "learning_rate": 3.960280311505538e-07, + "loss": 0.4491, + "step": 10910 + }, + { + "epoch": 0.91, + "learning_rate": 3.9527331063143215e-07, + "loss": 0.4693, + "step": 10911 + }, + { + "epoch": 0.91, + "learning_rate": 3.9451929544348956e-07, + "loss": 0.4599, + "step": 10912 + }, + { + "epoch": 0.91, + "learning_rate": 3.9376598564209614e-07, + "loss": 0.4722, + "step": 10913 + }, + { + "epoch": 0.91, + "learning_rate": 3.9301338128257536e-07, + "loss": 0.4704, + "step": 10914 + }, + { + "epoch": 0.91, + "learning_rate": 3.922614824201931e-07, + "loss": 0.4599, + "step": 10915 + }, + { + "epoch": 0.91, + "learning_rate": 3.915102891101652e-07, + "loss": 0.4563, + "step": 10916 + }, + { + "epoch": 0.91, + "learning_rate": 3.9075980140765637e-07, + "loss": 0.4605, + "step": 10917 + }, + { + "epoch": 0.91, + "learning_rate": 3.900100193677814e-07, + "loss": 0.4588, + "step": 10918 + }, + { + "epoch": 0.91, + "learning_rate": 3.892609430455985e-07, + "loss": 0.4697, + "step": 10919 + }, + { + "epoch": 0.91, + "learning_rate": 3.885125724961192e-07, + "loss": 0.4797, + "step": 10920 + }, + { + "epoch": 0.91, + "learning_rate": 3.877649077742984e-07, + "loss": 0.4523, + "step": 10921 + }, + { + "epoch": 0.91, + "learning_rate": 3.8701794893504343e-07, + "loss": 0.4725, + "step": 10922 + }, + { + "epoch": 0.91, + "learning_rate": 3.862716960332058e-07, + "loss": 0.4492, + "step": 10923 + }, + { + "epoch": 0.91, + "learning_rate": 3.8552614912358956e-07, + "loss": 0.435, + "step": 10924 + }, + { + "epoch": 0.91, + "learning_rate": 3.8478130826094307e-07, + "loss": 0.4606, + "step": 10925 + }, + { + "epoch": 0.91, + "learning_rate": 3.8403717349996263e-07, + "loss": 0.4684, + "step": 10926 + }, + { + "epoch": 0.91, + "learning_rate": 3.832937448952978e-07, + "loss": 0.4579, + "step": 10927 + }, + { + "epoch": 0.91, + "learning_rate": 3.8255102250154054e-07, + "loss": 0.4772, + "step": 10928 + }, + { + "epoch": 0.91, + "learning_rate": 3.81809006373236e-07, + "loss": 0.4719, + "step": 10929 + }, + { + "epoch": 0.91, + "learning_rate": 3.8106769656487184e-07, + "loss": 0.4419, + "step": 10930 + }, + { + "epoch": 0.91, + "learning_rate": 3.803270931308889e-07, + "loss": 0.4684, + "step": 10931 + }, + { + "epoch": 0.91, + "learning_rate": 3.795871961256725e-07, + "loss": 0.4569, + "step": 10932 + }, + { + "epoch": 0.91, + "learning_rate": 3.788480056035571e-07, + "loss": 0.4644, + "step": 10933 + }, + { + "epoch": 0.91, + "learning_rate": 3.78109521618828e-07, + "loss": 0.4834, + "step": 10934 + }, + { + "epoch": 0.91, + "learning_rate": 3.773717442257141e-07, + "loss": 0.4578, + "step": 10935 + }, + { + "epoch": 0.91, + "learning_rate": 3.7663467347839766e-07, + "loss": 0.4573, + "step": 10936 + }, + { + "epoch": 0.92, + "learning_rate": 3.7589830943100205e-07, + "loss": 0.4669, + "step": 10937 + }, + { + "epoch": 0.92, + "learning_rate": 3.7516265213760507e-07, + "loss": 0.4479, + "step": 10938 + }, + { + "epoch": 0.92, + "learning_rate": 3.7442770165223133e-07, + "loss": 0.4579, + "step": 10939 + }, + { + "epoch": 0.92, + "learning_rate": 3.7369345802885095e-07, + "loss": 0.4696, + "step": 10940 + }, + { + "epoch": 0.92, + "learning_rate": 3.7295992132138416e-07, + "loss": 0.4632, + "step": 10941 + }, + { + "epoch": 0.92, + "learning_rate": 3.7222709158369895e-07, + "loss": 0.4405, + "step": 10942 + }, + { + "epoch": 0.92, + "learning_rate": 3.714949688696123e-07, + "loss": 0.4644, + "step": 10943 + }, + { + "epoch": 0.92, + "learning_rate": 3.707635532328857e-07, + "loss": 0.4782, + "step": 10944 + }, + { + "epoch": 0.92, + "learning_rate": 3.700328447272339e-07, + "loss": 0.4324, + "step": 10945 + }, + { + "epoch": 0.92, + "learning_rate": 3.693028434063151e-07, + "loss": 0.4569, + "step": 10946 + }, + { + "epoch": 0.92, + "learning_rate": 3.6857354932373857e-07, + "loss": 0.454, + "step": 10947 + }, + { + "epoch": 0.92, + "learning_rate": 3.6784496253305937e-07, + "loss": 0.4474, + "step": 10948 + }, + { + "epoch": 0.92, + "learning_rate": 3.671170830877846e-07, + "loss": 0.4524, + "step": 10949 + }, + { + "epoch": 0.92, + "learning_rate": 3.663899110413638e-07, + "loss": 0.4726, + "step": 10950 + }, + { + "epoch": 0.92, + "learning_rate": 3.6566344644719974e-07, + "loss": 0.4711, + "step": 10951 + }, + { + "epoch": 0.92, + "learning_rate": 3.649376893586398e-07, + "loss": 0.441, + "step": 10952 + }, + { + "epoch": 0.92, + "learning_rate": 3.6421263982898023e-07, + "loss": 0.4742, + "step": 10953 + }, + { + "epoch": 0.92, + "learning_rate": 3.634882979114662e-07, + "loss": 0.4701, + "step": 10954 + }, + { + "epoch": 0.92, + "learning_rate": 3.627646636592919e-07, + "loss": 0.4461, + "step": 10955 + }, + { + "epoch": 0.92, + "learning_rate": 3.6204173712559464e-07, + "loss": 0.4677, + "step": 10956 + }, + { + "epoch": 0.92, + "learning_rate": 3.6131951836346544e-07, + "loss": 0.4643, + "step": 10957 + }, + { + "epoch": 0.92, + "learning_rate": 3.6059800742593963e-07, + "loss": 0.4507, + "step": 10958 + }, + { + "epoch": 0.92, + "learning_rate": 3.5987720436600483e-07, + "loss": 0.4745, + "step": 10959 + }, + { + "epoch": 0.92, + "learning_rate": 3.5915710923658974e-07, + "loss": 0.4839, + "step": 10960 + }, + { + "epoch": 0.92, + "learning_rate": 3.584377220905788e-07, + "loss": 0.458, + "step": 10961 + }, + { + "epoch": 0.92, + "learning_rate": 3.5771904298079864e-07, + "loss": 0.4535, + "step": 10962 + }, + { + "epoch": 0.92, + "learning_rate": 3.57001071960027e-07, + "loss": 0.443, + "step": 10963 + }, + { + "epoch": 0.92, + "learning_rate": 3.562838090809884e-07, + "loss": 0.4507, + "step": 10964 + }, + { + "epoch": 0.92, + "learning_rate": 3.555672543963562e-07, + "loss": 0.4554, + "step": 10965 + }, + { + "epoch": 0.92, + "learning_rate": 3.548514079587495e-07, + "loss": 0.4864, + "step": 10966 + }, + { + "epoch": 0.92, + "learning_rate": 3.541362698207373e-07, + "loss": 0.4705, + "step": 10967 + }, + { + "epoch": 0.92, + "learning_rate": 3.5342184003483884e-07, + "loss": 0.451, + "step": 10968 + }, + { + "epoch": 0.92, + "learning_rate": 3.527081186535164e-07, + "loss": 0.4559, + "step": 10969 + }, + { + "epoch": 0.92, + "learning_rate": 3.5199510572918484e-07, + "loss": 0.4681, + "step": 10970 + }, + { + "epoch": 0.92, + "learning_rate": 3.5128280131420333e-07, + "loss": 0.4597, + "step": 10971 + }, + { + "epoch": 0.92, + "learning_rate": 3.505712054608801e-07, + "loss": 0.4551, + "step": 10972 + }, + { + "epoch": 0.92, + "learning_rate": 3.4986031822147325e-07, + "loss": 0.4646, + "step": 10973 + }, + { + "epoch": 0.92, + "learning_rate": 3.4915013964818556e-07, + "loss": 0.4706, + "step": 10974 + }, + { + "epoch": 0.92, + "learning_rate": 3.4844066979317193e-07, + "loss": 0.4488, + "step": 10975 + }, + { + "epoch": 0.92, + "learning_rate": 3.477319087085318e-07, + "loss": 0.4767, + "step": 10976 + }, + { + "epoch": 0.92, + "learning_rate": 3.470238564463135e-07, + "loss": 0.4695, + "step": 10977 + }, + { + "epoch": 0.92, + "learning_rate": 3.4631651305851224e-07, + "loss": 0.4663, + "step": 10978 + }, + { + "epoch": 0.92, + "learning_rate": 3.4560987859707407e-07, + "loss": 0.455, + "step": 10979 + }, + { + "epoch": 0.92, + "learning_rate": 3.44903953113892e-07, + "loss": 0.4549, + "step": 10980 + }, + { + "epoch": 0.92, + "learning_rate": 3.4419873666080237e-07, + "loss": 0.4622, + "step": 10981 + }, + { + "epoch": 0.92, + "learning_rate": 3.434942292895982e-07, + "loss": 0.4688, + "step": 10982 + }, + { + "epoch": 0.92, + "learning_rate": 3.427904310520136e-07, + "loss": 0.4463, + "step": 10983 + }, + { + "epoch": 0.92, + "learning_rate": 3.420873419997317e-07, + "loss": 0.4726, + "step": 10984 + }, + { + "epoch": 0.92, + "learning_rate": 3.413849621843857e-07, + "loss": 0.4541, + "step": 10985 + }, + { + "epoch": 0.92, + "learning_rate": 3.406832916575542e-07, + "loss": 0.4545, + "step": 10986 + }, + { + "epoch": 0.92, + "learning_rate": 3.3998233047076613e-07, + "loss": 0.449, + "step": 10987 + }, + { + "epoch": 0.92, + "learning_rate": 3.3928207867549467e-07, + "loss": 0.4896, + "step": 10988 + }, + { + "epoch": 0.92, + "learning_rate": 3.385825363231665e-07, + "loss": 0.4583, + "step": 10989 + }, + { + "epoch": 0.92, + "learning_rate": 3.3788370346515274e-07, + "loss": 0.4388, + "step": 10990 + }, + { + "epoch": 0.92, + "learning_rate": 3.3718558015277237e-07, + "loss": 0.4818, + "step": 10991 + }, + { + "epoch": 0.92, + "learning_rate": 3.3648816643729207e-07, + "loss": 0.4601, + "step": 10992 + }, + { + "epoch": 0.92, + "learning_rate": 3.357914623699265e-07, + "loss": 0.4561, + "step": 10993 + }, + { + "epoch": 0.92, + "learning_rate": 3.3509546800183923e-07, + "loss": 0.4834, + "step": 10994 + }, + { + "epoch": 0.92, + "learning_rate": 3.344001833841426e-07, + "loss": 0.4675, + "step": 10995 + }, + { + "epoch": 0.92, + "learning_rate": 3.337056085678936e-07, + "loss": 0.4454, + "step": 10996 + }, + { + "epoch": 0.92, + "learning_rate": 3.3301174360410026e-07, + "loss": 0.4625, + "step": 10997 + }, + { + "epoch": 0.92, + "learning_rate": 3.3231858854371634e-07, + "loss": 0.462, + "step": 10998 + }, + { + "epoch": 0.92, + "learning_rate": 3.3162614343764334e-07, + "loss": 0.4516, + "step": 10999 + }, + { + "epoch": 0.92, + "learning_rate": 3.309344083367327e-07, + "loss": 0.4705, + "step": 11000 + }, + { + "epoch": 0.92, + "learning_rate": 3.3024338329178285e-07, + "loss": 0.4631, + "step": 11001 + }, + { + "epoch": 0.92, + "learning_rate": 3.2955306835353863e-07, + "loss": 0.4625, + "step": 11002 + }, + { + "epoch": 0.92, + "learning_rate": 3.2886346357269614e-07, + "loss": 0.4815, + "step": 11003 + }, + { + "epoch": 0.92, + "learning_rate": 3.28174568999895e-07, + "loss": 0.4582, + "step": 11004 + }, + { + "epoch": 0.92, + "learning_rate": 3.274863846857257e-07, + "loss": 0.4654, + "step": 11005 + }, + { + "epoch": 0.92, + "learning_rate": 3.2679891068072566e-07, + "loss": 0.4465, + "step": 11006 + }, + { + "epoch": 0.92, + "learning_rate": 3.26112147035379e-07, + "loss": 0.4808, + "step": 11007 + }, + { + "epoch": 0.92, + "learning_rate": 3.254260938001186e-07, + "loss": 0.4494, + "step": 11008 + }, + { + "epoch": 0.92, + "learning_rate": 3.2474075102532756e-07, + "loss": 0.4643, + "step": 11009 + }, + { + "epoch": 0.92, + "learning_rate": 3.240561187613323e-07, + "loss": 0.4687, + "step": 11010 + }, + { + "epoch": 0.92, + "learning_rate": 3.233721970584114e-07, + "loss": 0.4417, + "step": 11011 + }, + { + "epoch": 0.92, + "learning_rate": 3.226889859667881e-07, + "loss": 0.4668, + "step": 11012 + }, + { + "epoch": 0.92, + "learning_rate": 3.220064855366345e-07, + "loss": 0.4714, + "step": 11013 + }, + { + "epoch": 0.92, + "learning_rate": 3.2132469581807046e-07, + "loss": 0.4715, + "step": 11014 + }, + { + "epoch": 0.92, + "learning_rate": 3.2064361686116377e-07, + "loss": 0.4557, + "step": 11015 + }, + { + "epoch": 0.92, + "learning_rate": 3.199632487159321e-07, + "loss": 0.4709, + "step": 11016 + }, + { + "epoch": 0.92, + "learning_rate": 3.1928359143233556e-07, + "loss": 0.4687, + "step": 11017 + }, + { + "epoch": 0.92, + "learning_rate": 3.1860464506028865e-07, + "loss": 0.4549, + "step": 11018 + }, + { + "epoch": 0.92, + "learning_rate": 3.1792640964964593e-07, + "loss": 0.4747, + "step": 11019 + }, + { + "epoch": 0.92, + "learning_rate": 3.172488852502187e-07, + "loss": 0.4414, + "step": 11020 + }, + { + "epoch": 0.92, + "learning_rate": 3.1657207191176043e-07, + "loss": 0.4593, + "step": 11021 + }, + { + "epoch": 0.92, + "learning_rate": 3.1589596968397027e-07, + "loss": 0.4616, + "step": 11022 + }, + { + "epoch": 0.92, + "learning_rate": 3.15220578616503e-07, + "loss": 0.4688, + "step": 11023 + }, + { + "epoch": 0.92, + "learning_rate": 3.1454589875895445e-07, + "loss": 0.4583, + "step": 11024 + }, + { + "epoch": 0.92, + "learning_rate": 3.1387193016086945e-07, + "loss": 0.4662, + "step": 11025 + }, + { + "epoch": 0.92, + "learning_rate": 3.131986728717429e-07, + "loss": 0.4629, + "step": 11026 + }, + { + "epoch": 0.92, + "learning_rate": 3.1252612694101515e-07, + "loss": 0.4678, + "step": 11027 + }, + { + "epoch": 0.92, + "learning_rate": 3.1185429241807453e-07, + "loss": 0.4724, + "step": 11028 + }, + { + "epoch": 0.92, + "learning_rate": 3.1118316935226043e-07, + "loss": 0.4607, + "step": 11029 + }, + { + "epoch": 0.92, + "learning_rate": 3.105127577928546e-07, + "loss": 0.4534, + "step": 11030 + }, + { + "epoch": 0.92, + "learning_rate": 3.0984305778908875e-07, + "loss": 0.4537, + "step": 11031 + }, + { + "epoch": 0.92, + "learning_rate": 3.091740693901468e-07, + "loss": 0.4804, + "step": 11032 + }, + { + "epoch": 0.92, + "learning_rate": 3.085057926451529e-07, + "loss": 0.4322, + "step": 11033 + }, + { + "epoch": 0.92, + "learning_rate": 3.078382276031833e-07, + "loss": 0.4564, + "step": 11034 + }, + { + "epoch": 0.92, + "learning_rate": 3.071713743132609e-07, + "loss": 0.4704, + "step": 11035 + }, + { + "epoch": 0.92, + "learning_rate": 3.0650523282435896e-07, + "loss": 0.4677, + "step": 11036 + }, + { + "epoch": 0.92, + "learning_rate": 3.0583980318539377e-07, + "loss": 0.467, + "step": 11037 + }, + { + "epoch": 0.92, + "learning_rate": 3.051750854452329e-07, + "loss": 0.452, + "step": 11038 + }, + { + "epoch": 0.92, + "learning_rate": 3.0451107965268956e-07, + "loss": 0.4757, + "step": 11039 + }, + { + "epoch": 0.92, + "learning_rate": 3.0384778585652477e-07, + "loss": 0.4601, + "step": 11040 + }, + { + "epoch": 0.92, + "learning_rate": 3.031852041054506e-07, + "loss": 0.4614, + "step": 11041 + }, + { + "epoch": 0.92, + "learning_rate": 3.0252333444812263e-07, + "loss": 0.4768, + "step": 11042 + }, + { + "epoch": 0.92, + "learning_rate": 3.0186217693314643e-07, + "loss": 0.4619, + "step": 11043 + }, + { + "epoch": 0.92, + "learning_rate": 3.012017316090743e-07, + "loss": 0.4598, + "step": 11044 + }, + { + "epoch": 0.92, + "learning_rate": 3.0054199852440626e-07, + "loss": 0.4628, + "step": 11045 + }, + { + "epoch": 0.92, + "learning_rate": 2.9988297772759136e-07, + "loss": 0.4393, + "step": 11046 + }, + { + "epoch": 0.92, + "learning_rate": 2.992246692670242e-07, + "loss": 0.475, + "step": 11047 + }, + { + "epoch": 0.92, + "learning_rate": 2.985670731910495e-07, + "loss": 0.4703, + "step": 11048 + }, + { + "epoch": 0.92, + "learning_rate": 2.9791018954795636e-07, + "loss": 0.4442, + "step": 11049 + }, + { + "epoch": 0.92, + "learning_rate": 2.972540183859862e-07, + "loss": 0.4694, + "step": 11050 + }, + { + "epoch": 0.92, + "learning_rate": 2.9659855975332274e-07, + "loss": 0.4698, + "step": 11051 + }, + { + "epoch": 0.92, + "learning_rate": 2.959438136981019e-07, + "loss": 0.4357, + "step": 11052 + }, + { + "epoch": 0.92, + "learning_rate": 2.9528978026840625e-07, + "loss": 0.4585, + "step": 11053 + }, + { + "epoch": 0.92, + "learning_rate": 2.9463645951226415e-07, + "loss": 0.4864, + "step": 11054 + }, + { + "epoch": 0.92, + "learning_rate": 2.939838514776527e-07, + "loss": 0.4584, + "step": 11055 + }, + { + "epoch": 0.92, + "learning_rate": 2.933319562124959e-07, + "loss": 0.4561, + "step": 11056 + }, + { + "epoch": 0.93, + "learning_rate": 2.926807737646675e-07, + "loss": 0.4795, + "step": 11057 + }, + { + "epoch": 0.93, + "learning_rate": 2.920303041819872e-07, + "loss": 0.4472, + "step": 11058 + }, + { + "epoch": 0.93, + "learning_rate": 2.9138054751222447e-07, + "loss": 0.461, + "step": 11059 + }, + { + "epoch": 0.93, + "learning_rate": 2.907315038030911e-07, + "loss": 0.4699, + "step": 11060 + }, + { + "epoch": 0.93, + "learning_rate": 2.900831731022524e-07, + "loss": 0.4574, + "step": 11061 + }, + { + "epoch": 0.93, + "learning_rate": 2.894355554573203e-07, + "loss": 0.4534, + "step": 11062 + }, + { + "epoch": 0.93, + "learning_rate": 2.8878865091584993e-07, + "loss": 0.4645, + "step": 11063 + }, + { + "epoch": 0.93, + "learning_rate": 2.881424595253501e-07, + "loss": 0.4718, + "step": 11064 + }, + { + "epoch": 0.93, + "learning_rate": 2.8749698133327396e-07, + "loss": 0.4806, + "step": 11065 + }, + { + "epoch": 0.93, + "learning_rate": 2.868522163870213e-07, + "loss": 0.4608, + "step": 11066 + }, + { + "epoch": 0.93, + "learning_rate": 2.8620816473394206e-07, + "loss": 0.4613, + "step": 11067 + }, + { + "epoch": 0.93, + "learning_rate": 2.855648264213329e-07, + "loss": 0.4636, + "step": 11068 + }, + { + "epoch": 0.93, + "learning_rate": 2.84922201496437e-07, + "loss": 0.4611, + "step": 11069 + }, + { + "epoch": 0.93, + "learning_rate": 2.8428029000644676e-07, + "loss": 0.4624, + "step": 11070 + }, + { + "epoch": 0.93, + "learning_rate": 2.83639091998501e-07, + "loss": 0.4557, + "step": 11071 + }, + { + "epoch": 0.93, + "learning_rate": 2.8299860751968664e-07, + "loss": 0.4618, + "step": 11072 + }, + { + "epoch": 0.93, + "learning_rate": 2.823588366170393e-07, + "loss": 0.4716, + "step": 11073 + }, + { + "epoch": 0.93, + "learning_rate": 2.8171977933754036e-07, + "loss": 0.4572, + "step": 11074 + }, + { + "epoch": 0.93, + "learning_rate": 2.810814357281189e-07, + "loss": 0.4798, + "step": 11075 + }, + { + "epoch": 0.93, + "learning_rate": 2.804438058356529e-07, + "loss": 0.4614, + "step": 11076 + }, + { + "epoch": 0.93, + "learning_rate": 2.798068897069672e-07, + "loss": 0.4506, + "step": 11077 + }, + { + "epoch": 0.93, + "learning_rate": 2.791706873888345e-07, + "loss": 0.4792, + "step": 11078 + }, + { + "epoch": 0.93, + "learning_rate": 2.78535198927975e-07, + "loss": 0.463, + "step": 11079 + }, + { + "epoch": 0.93, + "learning_rate": 2.779004243710548e-07, + "loss": 0.4493, + "step": 11080 + }, + { + "epoch": 0.93, + "learning_rate": 2.7726636376468995e-07, + "loss": 0.4583, + "step": 11081 + }, + { + "epoch": 0.93, + "learning_rate": 2.766330171554443e-07, + "loss": 0.4744, + "step": 11082 + }, + { + "epoch": 0.93, + "learning_rate": 2.7600038458982626e-07, + "loss": 0.4577, + "step": 11083 + }, + { + "epoch": 0.93, + "learning_rate": 2.7536846611429524e-07, + "loss": 0.4498, + "step": 11084 + }, + { + "epoch": 0.93, + "learning_rate": 2.747372617752575e-07, + "loss": 0.466, + "step": 11085 + }, + { + "epoch": 0.93, + "learning_rate": 2.741067716190637e-07, + "loss": 0.4466, + "step": 11086 + }, + { + "epoch": 0.93, + "learning_rate": 2.734769956920169e-07, + "loss": 0.4521, + "step": 11087 + }, + { + "epoch": 0.93, + "learning_rate": 2.728479340403634e-07, + "loss": 0.4548, + "step": 11088 + }, + { + "epoch": 0.93, + "learning_rate": 2.7221958671029834e-07, + "loss": 0.464, + "step": 11089 + }, + { + "epoch": 0.93, + "learning_rate": 2.715919537479661e-07, + "loss": 0.463, + "step": 11090 + }, + { + "epoch": 0.93, + "learning_rate": 2.709650351994575e-07, + "loss": 0.4979, + "step": 11091 + }, + { + "epoch": 0.93, + "learning_rate": 2.7033883111081014e-07, + "loss": 0.46, + "step": 11092 + }, + { + "epoch": 0.93, + "learning_rate": 2.6971334152801063e-07, + "loss": 0.4618, + "step": 11093 + }, + { + "epoch": 0.93, + "learning_rate": 2.690885664969933e-07, + "loss": 0.4493, + "step": 11094 + }, + { + "epoch": 0.93, + "learning_rate": 2.6846450606363705e-07, + "loss": 0.4691, + "step": 11095 + }, + { + "epoch": 0.93, + "learning_rate": 2.678411602737707e-07, + "loss": 0.4505, + "step": 11096 + }, + { + "epoch": 0.93, + "learning_rate": 2.6721852917316995e-07, + "loss": 0.4586, + "step": 11097 + }, + { + "epoch": 0.93, + "learning_rate": 2.665966128075592e-07, + "loss": 0.4665, + "step": 11098 + }, + { + "epoch": 0.93, + "learning_rate": 2.659754112226087e-07, + "loss": 0.4521, + "step": 11099 + }, + { + "epoch": 0.93, + "learning_rate": 2.653549244639375e-07, + "loss": 0.4666, + "step": 11100 + }, + { + "epoch": 0.93, + "learning_rate": 2.6473515257711136e-07, + "loss": 0.456, + "step": 11101 + }, + { + "epoch": 0.93, + "learning_rate": 2.6411609560764273e-07, + "loss": 0.4674, + "step": 11102 + }, + { + "epoch": 0.93, + "learning_rate": 2.6349775360099306e-07, + "loss": 0.4626, + "step": 11103 + }, + { + "epoch": 0.93, + "learning_rate": 2.628801266025727e-07, + "loss": 0.4403, + "step": 11104 + }, + { + "epoch": 0.93, + "learning_rate": 2.622632146577364e-07, + "loss": 0.4732, + "step": 11105 + }, + { + "epoch": 0.93, + "learning_rate": 2.616470178117858e-07, + "loss": 0.4657, + "step": 11106 + }, + { + "epoch": 0.93, + "learning_rate": 2.6103153610997464e-07, + "loss": 0.4599, + "step": 11107 + }, + { + "epoch": 0.93, + "learning_rate": 2.604167695975002e-07, + "loss": 0.4552, + "step": 11108 + }, + { + "epoch": 0.93, + "learning_rate": 2.5980271831950734e-07, + "loss": 0.4677, + "step": 11109 + }, + { + "epoch": 0.93, + "learning_rate": 2.5918938232109004e-07, + "loss": 0.4628, + "step": 11110 + }, + { + "epoch": 0.93, + "learning_rate": 2.5857676164729006e-07, + "loss": 0.4507, + "step": 11111 + }, + { + "epoch": 0.93, + "learning_rate": 2.5796485634309477e-07, + "loss": 0.4524, + "step": 11112 + }, + { + "epoch": 0.93, + "learning_rate": 2.573536664534404e-07, + "loss": 0.4644, + "step": 11113 + }, + { + "epoch": 0.93, + "learning_rate": 2.5674319202320997e-07, + "loss": 0.4485, + "step": 11114 + }, + { + "epoch": 0.93, + "learning_rate": 2.5613343309723426e-07, + "loss": 0.4583, + "step": 11115 + }, + { + "epoch": 0.93, + "learning_rate": 2.555243897202919e-07, + "loss": 0.4837, + "step": 11116 + }, + { + "epoch": 0.93, + "learning_rate": 2.549160619371072e-07, + "loss": 0.4759, + "step": 11117 + }, + { + "epoch": 0.93, + "learning_rate": 2.5430844979235426e-07, + "loss": 0.4621, + "step": 11118 + }, + { + "epoch": 0.93, + "learning_rate": 2.5370155333065416e-07, + "loss": 0.4752, + "step": 11119 + }, + { + "epoch": 0.93, + "learning_rate": 2.5309537259657346e-07, + "loss": 0.4624, + "step": 11120 + }, + { + "epoch": 0.93, + "learning_rate": 2.524899076346288e-07, + "loss": 0.4575, + "step": 11121 + }, + { + "epoch": 0.93, + "learning_rate": 2.518851584892812e-07, + "loss": 0.4817, + "step": 11122 + }, + { + "epoch": 0.93, + "learning_rate": 2.5128112520494297e-07, + "loss": 0.4768, + "step": 11123 + }, + { + "epoch": 0.93, + "learning_rate": 2.5067780782596973e-07, + "loss": 0.4499, + "step": 11124 + }, + { + "epoch": 0.93, + "learning_rate": 2.500752063966694e-07, + "loss": 0.4508, + "step": 11125 + }, + { + "epoch": 0.93, + "learning_rate": 2.494733209612921e-07, + "loss": 0.4726, + "step": 11126 + }, + { + "epoch": 0.93, + "learning_rate": 2.488721515640391e-07, + "loss": 0.4577, + "step": 11127 + }, + { + "epoch": 0.93, + "learning_rate": 2.482716982490574e-07, + "loss": 0.449, + "step": 11128 + }, + { + "epoch": 0.93, + "learning_rate": 2.476719610604417e-07, + "loss": 0.4783, + "step": 11129 + }, + { + "epoch": 0.93, + "learning_rate": 2.4707294004223335e-07, + "loss": 0.483, + "step": 11130 + }, + { + "epoch": 0.93, + "learning_rate": 2.464746352384229e-07, + "loss": 0.4561, + "step": 11131 + }, + { + "epoch": 0.93, + "learning_rate": 2.4587704669294834e-07, + "loss": 0.4791, + "step": 11132 + }, + { + "epoch": 0.93, + "learning_rate": 2.452801744496913e-07, + "loss": 0.4602, + "step": 11133 + }, + { + "epoch": 0.93, + "learning_rate": 2.446840185524868e-07, + "loss": 0.4529, + "step": 11134 + }, + { + "epoch": 0.93, + "learning_rate": 2.4408857904511196e-07, + "loss": 0.4832, + "step": 11135 + }, + { + "epoch": 0.93, + "learning_rate": 2.4349385597129403e-07, + "loss": 0.4787, + "step": 11136 + }, + { + "epoch": 0.93, + "learning_rate": 2.428998493747081e-07, + "loss": 0.4726, + "step": 11137 + }, + { + "epoch": 0.93, + "learning_rate": 2.4230655929897263e-07, + "loss": 0.4646, + "step": 11138 + }, + { + "epoch": 0.93, + "learning_rate": 2.417139857876583e-07, + "loss": 0.4458, + "step": 11139 + }, + { + "epoch": 0.93, + "learning_rate": 2.4112212888428246e-07, + "loss": 0.4363, + "step": 11140 + }, + { + "epoch": 0.93, + "learning_rate": 2.4053098863230706e-07, + "loss": 0.4711, + "step": 11141 + }, + { + "epoch": 0.93, + "learning_rate": 2.3994056507514183e-07, + "loss": 0.4633, + "step": 11142 + }, + { + "epoch": 0.93, + "learning_rate": 2.3935085825614655e-07, + "loss": 0.4565, + "step": 11143 + }, + { + "epoch": 0.93, + "learning_rate": 2.387618682186277e-07, + "loss": 0.4608, + "step": 11144 + }, + { + "epoch": 0.93, + "learning_rate": 2.3817359500583615e-07, + "loss": 0.4632, + "step": 11145 + }, + { + "epoch": 0.93, + "learning_rate": 2.3758603866097406e-07, + "loss": 0.4617, + "step": 11146 + }, + { + "epoch": 0.93, + "learning_rate": 2.3699919922718805e-07, + "loss": 0.4715, + "step": 11147 + }, + { + "epoch": 0.93, + "learning_rate": 2.3641307674757362e-07, + "loss": 0.4526, + "step": 11148 + }, + { + "epoch": 0.93, + "learning_rate": 2.3582767126517302e-07, + "loss": 0.4631, + "step": 11149 + }, + { + "epoch": 0.93, + "learning_rate": 2.352429828229763e-07, + "loss": 0.4627, + "step": 11150 + }, + { + "epoch": 0.93, + "learning_rate": 2.3465901146391912e-07, + "loss": 0.4579, + "step": 11151 + }, + { + "epoch": 0.93, + "learning_rate": 2.3407575723088827e-07, + "loss": 0.4531, + "step": 11152 + }, + { + "epoch": 0.93, + "learning_rate": 2.3349322016671394e-07, + "loss": 0.4655, + "step": 11153 + }, + { + "epoch": 0.93, + "learning_rate": 2.3291140031417525e-07, + "loss": 0.4745, + "step": 11154 + }, + { + "epoch": 0.93, + "learning_rate": 2.3233029771599913e-07, + "loss": 0.4893, + "step": 11155 + }, + { + "epoch": 0.93, + "learning_rate": 2.3174991241485923e-07, + "loss": 0.4505, + "step": 11156 + }, + { + "epoch": 0.93, + "learning_rate": 2.31170244453377e-07, + "loss": 0.4682, + "step": 11157 + }, + { + "epoch": 0.93, + "learning_rate": 2.305912938741184e-07, + "loss": 0.4609, + "step": 11158 + }, + { + "epoch": 0.93, + "learning_rate": 2.3001306071960384e-07, + "loss": 0.4606, + "step": 11159 + }, + { + "epoch": 0.93, + "learning_rate": 2.294355450322916e-07, + "loss": 0.4565, + "step": 11160 + }, + { + "epoch": 0.93, + "learning_rate": 2.2885874685459553e-07, + "loss": 0.4542, + "step": 11161 + }, + { + "epoch": 0.93, + "learning_rate": 2.2828266622887173e-07, + "loss": 0.4691, + "step": 11162 + }, + { + "epoch": 0.93, + "learning_rate": 2.2770730319742528e-07, + "loss": 0.4622, + "step": 11163 + }, + { + "epoch": 0.93, + "learning_rate": 2.271326578025068e-07, + "loss": 0.4703, + "step": 11164 + }, + { + "epoch": 0.93, + "learning_rate": 2.2655873008631812e-07, + "loss": 0.4572, + "step": 11165 + }, + { + "epoch": 0.93, + "learning_rate": 2.259855200910066e-07, + "loss": 0.4871, + "step": 11166 + }, + { + "epoch": 0.93, + "learning_rate": 2.2541302785866525e-07, + "loss": 0.4661, + "step": 11167 + }, + { + "epoch": 0.93, + "learning_rate": 2.248412534313349e-07, + "loss": 0.4621, + "step": 11168 + }, + { + "epoch": 0.93, + "learning_rate": 2.2427019685100527e-07, + "loss": 0.4768, + "step": 11169 + }, + { + "epoch": 0.93, + "learning_rate": 2.236998581596128e-07, + "loss": 0.4552, + "step": 11170 + }, + { + "epoch": 0.93, + "learning_rate": 2.231302373990385e-07, + "loss": 0.4535, + "step": 11171 + }, + { + "epoch": 0.93, + "learning_rate": 2.225613346111155e-07, + "loss": 0.4639, + "step": 11172 + }, + { + "epoch": 0.93, + "learning_rate": 2.2199314983762043e-07, + "loss": 0.4708, + "step": 11173 + }, + { + "epoch": 0.93, + "learning_rate": 2.2142568312027879e-07, + "loss": 0.4768, + "step": 11174 + }, + { + "epoch": 0.93, + "learning_rate": 2.2085893450076167e-07, + "loss": 0.4697, + "step": 11175 + }, + { + "epoch": 0.94, + "learning_rate": 2.2029290402069137e-07, + "loss": 0.4648, + "step": 11176 + }, + { + "epoch": 0.94, + "learning_rate": 2.1972759172163239e-07, + "loss": 0.4732, + "step": 11177 + }, + { + "epoch": 0.94, + "learning_rate": 2.191629976451004e-07, + "loss": 0.4662, + "step": 11178 + }, + { + "epoch": 0.94, + "learning_rate": 2.185991218325556e-07, + "loss": 0.458, + "step": 11179 + }, + { + "epoch": 0.94, + "learning_rate": 2.1803596432540818e-07, + "loss": 0.4644, + "step": 11180 + }, + { + "epoch": 0.94, + "learning_rate": 2.1747352516501396e-07, + "loss": 0.4514, + "step": 11181 + }, + { + "epoch": 0.94, + "learning_rate": 2.1691180439267434e-07, + "loss": 0.477, + "step": 11182 + }, + { + "epoch": 0.94, + "learning_rate": 2.1635080204964187e-07, + "loss": 0.4799, + "step": 11183 + }, + { + "epoch": 0.94, + "learning_rate": 2.157905181771114e-07, + "loss": 0.4699, + "step": 11184 + }, + { + "epoch": 0.94, + "learning_rate": 2.1523095281623109e-07, + "loss": 0.4609, + "step": 11185 + }, + { + "epoch": 0.94, + "learning_rate": 2.146721060080914e-07, + "loss": 0.446, + "step": 11186 + }, + { + "epoch": 0.94, + "learning_rate": 2.141139777937318e-07, + "loss": 0.4774, + "step": 11187 + }, + { + "epoch": 0.94, + "learning_rate": 2.1355656821413938e-07, + "loss": 0.4701, + "step": 11188 + }, + { + "epoch": 0.94, + "learning_rate": 2.1299987731024818e-07, + "loss": 0.457, + "step": 11189 + }, + { + "epoch": 0.94, + "learning_rate": 2.1244390512293878e-07, + "loss": 0.4449, + "step": 11190 + }, + { + "epoch": 0.94, + "learning_rate": 2.1188865169303852e-07, + "loss": 0.4626, + "step": 11191 + }, + { + "epoch": 0.94, + "learning_rate": 2.1133411706132368e-07, + "loss": 0.4547, + "step": 11192 + }, + { + "epoch": 0.94, + "learning_rate": 2.1078030126851833e-07, + "loss": 0.4508, + "step": 11193 + }, + { + "epoch": 0.94, + "learning_rate": 2.1022720435529109e-07, + "loss": 0.4558, + "step": 11194 + }, + { + "epoch": 0.94, + "learning_rate": 2.0967482636225723e-07, + "loss": 0.4591, + "step": 11195 + }, + { + "epoch": 0.94, + "learning_rate": 2.0912316732998538e-07, + "loss": 0.4874, + "step": 11196 + }, + { + "epoch": 0.94, + "learning_rate": 2.0857222729898429e-07, + "loss": 0.4589, + "step": 11197 + }, + { + "epoch": 0.94, + "learning_rate": 2.0802200630971382e-07, + "loss": 0.4498, + "step": 11198 + }, + { + "epoch": 0.94, + "learning_rate": 2.0747250440257715e-07, + "loss": 0.4682, + "step": 11199 + }, + { + "epoch": 0.94, + "learning_rate": 2.0692372161793094e-07, + "loss": 0.4665, + "step": 11200 + }, + { + "epoch": 0.94, + "learning_rate": 2.0637565799607517e-07, + "loss": 0.4639, + "step": 11201 + }, + { + "epoch": 0.94, + "learning_rate": 2.0582831357725542e-07, + "loss": 0.4561, + "step": 11202 + }, + { + "epoch": 0.94, + "learning_rate": 2.052816884016673e-07, + "loss": 0.4466, + "step": 11203 + }, + { + "epoch": 0.94, + "learning_rate": 2.0473578250945315e-07, + "loss": 0.4515, + "step": 11204 + }, + { + "epoch": 0.94, + "learning_rate": 2.0419059594069977e-07, + "loss": 0.4653, + "step": 11205 + }, + { + "epoch": 0.94, + "learning_rate": 2.0364612873544632e-07, + "loss": 0.4583, + "step": 11206 + }, + { + "epoch": 0.94, + "learning_rate": 2.0310238093367517e-07, + "loss": 0.4565, + "step": 11207 + }, + { + "epoch": 0.94, + "learning_rate": 2.0255935257531668e-07, + "loss": 0.4796, + "step": 11208 + }, + { + "epoch": 0.94, + "learning_rate": 2.0201704370024889e-07, + "loss": 0.4641, + "step": 11209 + }, + { + "epoch": 0.94, + "learning_rate": 2.0147545434829664e-07, + "loss": 0.4512, + "step": 11210 + }, + { + "epoch": 0.94, + "learning_rate": 2.0093458455923253e-07, + "loss": 0.4543, + "step": 11211 + }, + { + "epoch": 0.94, + "learning_rate": 2.0039443437277483e-07, + "loss": 0.4575, + "step": 11212 + }, + { + "epoch": 0.94, + "learning_rate": 1.9985500382858846e-07, + "loss": 0.4808, + "step": 11213 + }, + { + "epoch": 0.94, + "learning_rate": 1.9931629296629062e-07, + "loss": 0.4879, + "step": 11214 + }, + { + "epoch": 0.94, + "learning_rate": 1.9877830182543966e-07, + "loss": 0.4643, + "step": 11215 + }, + { + "epoch": 0.94, + "learning_rate": 1.982410304455429e-07, + "loss": 0.4918, + "step": 11216 + }, + { + "epoch": 0.94, + "learning_rate": 1.977044788660576e-07, + "loss": 0.4732, + "step": 11217 + }, + { + "epoch": 0.94, + "learning_rate": 1.9716864712638452e-07, + "loss": 0.458, + "step": 11218 + }, + { + "epoch": 0.94, + "learning_rate": 1.9663353526587104e-07, + "loss": 0.4465, + "step": 11219 + }, + { + "epoch": 0.94, + "learning_rate": 1.9609914332381797e-07, + "loss": 0.467, + "step": 11220 + }, + { + "epoch": 0.94, + "learning_rate": 1.9556547133946503e-07, + "loss": 0.471, + "step": 11221 + }, + { + "epoch": 0.94, + "learning_rate": 1.9503251935200418e-07, + "loss": 0.4334, + "step": 11222 + }, + { + "epoch": 0.94, + "learning_rate": 1.9450028740057415e-07, + "loss": 0.4527, + "step": 11223 + }, + { + "epoch": 0.94, + "learning_rate": 1.9396877552425808e-07, + "loss": 0.4616, + "step": 11224 + }, + { + "epoch": 0.94, + "learning_rate": 1.9343798376208812e-07, + "loss": 0.4508, + "step": 11225 + }, + { + "epoch": 0.94, + "learning_rate": 1.9290791215304527e-07, + "loss": 0.4742, + "step": 11226 + }, + { + "epoch": 0.94, + "learning_rate": 1.92378560736054e-07, + "loss": 0.4621, + "step": 11227 + }, + { + "epoch": 0.94, + "learning_rate": 1.918499295499887e-07, + "loss": 0.4577, + "step": 11228 + }, + { + "epoch": 0.94, + "learning_rate": 1.913220186336684e-07, + "loss": 0.4754, + "step": 11229 + }, + { + "epoch": 0.94, + "learning_rate": 1.9079482802586314e-07, + "loss": 0.4778, + "step": 11230 + }, + { + "epoch": 0.94, + "learning_rate": 1.9026835776528529e-07, + "loss": 0.443, + "step": 11231 + }, + { + "epoch": 0.94, + "learning_rate": 1.897426078905984e-07, + "loss": 0.4614, + "step": 11232 + }, + { + "epoch": 0.94, + "learning_rate": 1.8921757844040821e-07, + "loss": 0.4567, + "step": 11233 + }, + { + "epoch": 0.94, + "learning_rate": 1.8869326945327505e-07, + "loss": 0.4597, + "step": 11234 + }, + { + "epoch": 0.94, + "learning_rate": 1.8816968096769917e-07, + "loss": 0.4536, + "step": 11235 + }, + { + "epoch": 0.94, + "learning_rate": 1.8764681302213096e-07, + "loss": 0.4508, + "step": 11236 + }, + { + "epoch": 0.94, + "learning_rate": 1.8712466565496966e-07, + "loss": 0.4729, + "step": 11237 + }, + { + "epoch": 0.94, + "learning_rate": 1.866032389045569e-07, + "loss": 0.4623, + "step": 11238 + }, + { + "epoch": 0.94, + "learning_rate": 1.860825328091853e-07, + "loss": 0.4619, + "step": 11239 + }, + { + "epoch": 0.94, + "learning_rate": 1.8556254740709322e-07, + "loss": 0.4518, + "step": 11240 + }, + { + "epoch": 0.94, + "learning_rate": 1.8504328273646676e-07, + "loss": 0.4522, + "step": 11241 + }, + { + "epoch": 0.94, + "learning_rate": 1.8452473883543876e-07, + "loss": 0.4689, + "step": 11242 + }, + { + "epoch": 0.94, + "learning_rate": 1.8400691574208763e-07, + "loss": 0.4826, + "step": 11243 + }, + { + "epoch": 0.94, + "learning_rate": 1.8348981349444073e-07, + "loss": 0.4514, + "step": 11244 + }, + { + "epoch": 0.94, + "learning_rate": 1.8297343213047215e-07, + "loss": 0.4614, + "step": 11245 + }, + { + "epoch": 0.94, + "learning_rate": 1.8245777168810264e-07, + "loss": 0.4789, + "step": 11246 + }, + { + "epoch": 0.94, + "learning_rate": 1.8194283220519972e-07, + "loss": 0.4497, + "step": 11247 + }, + { + "epoch": 0.94, + "learning_rate": 1.8142861371957866e-07, + "loss": 0.4716, + "step": 11248 + }, + { + "epoch": 0.94, + "learning_rate": 1.809151162690026e-07, + "loss": 0.4514, + "step": 11249 + }, + { + "epoch": 0.94, + "learning_rate": 1.8040233989117915e-07, + "loss": 0.4515, + "step": 11250 + }, + { + "epoch": 0.94, + "learning_rate": 1.79890284623766e-07, + "loss": 0.4727, + "step": 11251 + }, + { + "epoch": 0.94, + "learning_rate": 1.7937895050436528e-07, + "loss": 0.4491, + "step": 11252 + }, + { + "epoch": 0.94, + "learning_rate": 1.7886833757052692e-07, + "loss": 0.4514, + "step": 11253 + }, + { + "epoch": 0.94, + "learning_rate": 1.783584458597476e-07, + "loss": 0.4681, + "step": 11254 + }, + { + "epoch": 0.94, + "learning_rate": 1.7784927540947406e-07, + "loss": 0.4641, + "step": 11255 + }, + { + "epoch": 0.94, + "learning_rate": 1.7734082625709637e-07, + "loss": 0.4511, + "step": 11256 + }, + { + "epoch": 0.94, + "learning_rate": 1.7683309843995245e-07, + "loss": 0.4866, + "step": 11257 + }, + { + "epoch": 0.94, + "learning_rate": 1.76326091995328e-07, + "loss": 0.4605, + "step": 11258 + }, + { + "epoch": 0.94, + "learning_rate": 1.7581980696045665e-07, + "loss": 0.4512, + "step": 11259 + }, + { + "epoch": 0.94, + "learning_rate": 1.7531424337251523e-07, + "loss": 0.4494, + "step": 11260 + }, + { + "epoch": 0.94, + "learning_rate": 1.74809401268633e-07, + "loss": 0.4466, + "step": 11261 + }, + { + "epoch": 0.94, + "learning_rate": 1.7430528068588136e-07, + "loss": 0.4511, + "step": 11262 + }, + { + "epoch": 0.94, + "learning_rate": 1.73801881661283e-07, + "loss": 0.4694, + "step": 11263 + }, + { + "epoch": 0.94, + "learning_rate": 1.732992042318038e-07, + "loss": 0.4656, + "step": 11264 + }, + { + "epoch": 0.94, + "learning_rate": 1.7279724843435874e-07, + "loss": 0.4696, + "step": 11265 + }, + { + "epoch": 0.94, + "learning_rate": 1.7229601430580832e-07, + "loss": 0.4668, + "step": 11266 + }, + { + "epoch": 0.94, + "learning_rate": 1.7179550188296313e-07, + "loss": 0.4587, + "step": 11267 + }, + { + "epoch": 0.94, + "learning_rate": 1.7129571120257705e-07, + "loss": 0.4508, + "step": 11268 + }, + { + "epoch": 0.94, + "learning_rate": 1.7079664230135406e-07, + "loss": 0.4877, + "step": 11269 + }, + { + "epoch": 0.94, + "learning_rate": 1.7029829521594265e-07, + "loss": 0.4431, + "step": 11270 + }, + { + "epoch": 0.94, + "learning_rate": 1.698006699829402e-07, + "loss": 0.4604, + "step": 11271 + }, + { + "epoch": 0.94, + "learning_rate": 1.693037666388886e-07, + "loss": 0.4764, + "step": 11272 + }, + { + "epoch": 0.94, + "learning_rate": 1.6880758522028083e-07, + "loss": 0.449, + "step": 11273 + }, + { + "epoch": 0.94, + "learning_rate": 1.6831212576355116e-07, + "loss": 0.4654, + "step": 11274 + }, + { + "epoch": 0.94, + "learning_rate": 1.6781738830508708e-07, + "loss": 0.4697, + "step": 11275 + }, + { + "epoch": 0.94, + "learning_rate": 1.6732337288121848e-07, + "loss": 0.4456, + "step": 11276 + }, + { + "epoch": 0.94, + "learning_rate": 1.6683007952822405e-07, + "loss": 0.4683, + "step": 11277 + }, + { + "epoch": 0.94, + "learning_rate": 1.663375082823293e-07, + "loss": 0.4491, + "step": 11278 + }, + { + "epoch": 0.94, + "learning_rate": 1.658456591797075e-07, + "loss": 0.4488, + "step": 11279 + }, + { + "epoch": 0.94, + "learning_rate": 1.6535453225647645e-07, + "loss": 0.4635, + "step": 11280 + }, + { + "epoch": 0.94, + "learning_rate": 1.6486412754870286e-07, + "loss": 0.4656, + "step": 11281 + }, + { + "epoch": 0.94, + "learning_rate": 1.643744450924012e-07, + "loss": 0.489, + "step": 11282 + }, + { + "epoch": 0.94, + "learning_rate": 1.638854849235305e-07, + "loss": 0.4561, + "step": 11283 + }, + { + "epoch": 0.94, + "learning_rate": 1.6339724707799875e-07, + "loss": 0.458, + "step": 11284 + }, + { + "epoch": 0.94, + "learning_rate": 1.6290973159165945e-07, + "loss": 0.4563, + "step": 11285 + }, + { + "epoch": 0.94, + "learning_rate": 1.62422938500314e-07, + "loss": 0.4512, + "step": 11286 + }, + { + "epoch": 0.94, + "learning_rate": 1.619368678397093e-07, + "loss": 0.4662, + "step": 11287 + }, + { + "epoch": 0.94, + "learning_rate": 1.614515196455424e-07, + "loss": 0.4656, + "step": 11288 + }, + { + "epoch": 0.94, + "learning_rate": 1.6096689395345366e-07, + "loss": 0.4872, + "step": 11289 + }, + { + "epoch": 0.94, + "learning_rate": 1.604829907990335e-07, + "loss": 0.4777, + "step": 11290 + }, + { + "epoch": 0.94, + "learning_rate": 1.5999981021781685e-07, + "loss": 0.4589, + "step": 11291 + }, + { + "epoch": 0.94, + "learning_rate": 1.595173522452864e-07, + "loss": 0.4641, + "step": 11292 + }, + { + "epoch": 0.94, + "learning_rate": 1.5903561691687164e-07, + "loss": 0.4715, + "step": 11293 + }, + { + "epoch": 0.94, + "learning_rate": 1.5855460426794865e-07, + "loss": 0.446, + "step": 11294 + }, + { + "epoch": 0.94, + "learning_rate": 1.5807431433384368e-07, + "loss": 0.4725, + "step": 11295 + }, + { + "epoch": 0.95, + "learning_rate": 1.5759474714982405e-07, + "loss": 0.4727, + "step": 11296 + }, + { + "epoch": 0.95, + "learning_rate": 1.5711590275110933e-07, + "loss": 0.4476, + "step": 11297 + }, + { + "epoch": 0.95, + "learning_rate": 1.5663778117286254e-07, + "loss": 0.4618, + "step": 11298 + }, + { + "epoch": 0.95, + "learning_rate": 1.561603824501956e-07, + "loss": 0.4643, + "step": 11299 + }, + { + "epoch": 0.95, + "learning_rate": 1.5568370661816713e-07, + "loss": 0.4793, + "step": 11300 + }, + { + "epoch": 0.95, + "learning_rate": 1.552077537117802e-07, + "loss": 0.4569, + "step": 11301 + }, + { + "epoch": 0.95, + "learning_rate": 1.5473252376598913e-07, + "loss": 0.4629, + "step": 11302 + }, + { + "epoch": 0.95, + "learning_rate": 1.5425801681569263e-07, + "loss": 0.4617, + "step": 11303 + }, + { + "epoch": 0.95, + "learning_rate": 1.5378423289573508e-07, + "loss": 0.4613, + "step": 11304 + }, + { + "epoch": 0.95, + "learning_rate": 1.5331117204091085e-07, + "loss": 0.45, + "step": 11305 + }, + { + "epoch": 0.95, + "learning_rate": 1.528388342859577e-07, + "loss": 0.4758, + "step": 11306 + }, + { + "epoch": 0.95, + "learning_rate": 1.5236721966556456e-07, + "loss": 0.4927, + "step": 11307 + }, + { + "epoch": 0.95, + "learning_rate": 1.518963282143615e-07, + "loss": 0.4616, + "step": 11308 + }, + { + "epoch": 0.95, + "learning_rate": 1.5142615996693087e-07, + "loss": 0.4713, + "step": 11309 + }, + { + "epoch": 0.95, + "learning_rate": 1.5095671495780062e-07, + "loss": 0.4613, + "step": 11310 + }, + { + "epoch": 0.95, + "learning_rate": 1.5048799322144426e-07, + "loss": 0.4549, + "step": 11311 + }, + { + "epoch": 0.95, + "learning_rate": 1.5001999479228203e-07, + "loss": 0.459, + "step": 11312 + }, + { + "epoch": 0.95, + "learning_rate": 1.49552719704682e-07, + "loss": 0.4595, + "step": 11313 + }, + { + "epoch": 0.95, + "learning_rate": 1.4908616799296006e-07, + "loss": 0.4503, + "step": 11314 + }, + { + "epoch": 0.95, + "learning_rate": 1.4862033969137545e-07, + "loss": 0.4753, + "step": 11315 + }, + { + "epoch": 0.95, + "learning_rate": 1.4815523483413864e-07, + "loss": 0.4399, + "step": 11316 + }, + { + "epoch": 0.95, + "learning_rate": 1.4769085345540556e-07, + "loss": 0.4847, + "step": 11317 + }, + { + "epoch": 0.95, + "learning_rate": 1.472271955892768e-07, + "loss": 0.4602, + "step": 11318 + }, + { + "epoch": 0.95, + "learning_rate": 1.4676426126980058e-07, + "loss": 0.4709, + "step": 11319 + }, + { + "epoch": 0.95, + "learning_rate": 1.4630205053097645e-07, + "loss": 0.4564, + "step": 11320 + }, + { + "epoch": 0.95, + "learning_rate": 1.4584056340674392e-07, + "loss": 0.4561, + "step": 11321 + }, + { + "epoch": 0.95, + "learning_rate": 1.4537979993099361e-07, + "loss": 0.4634, + "step": 11322 + }, + { + "epoch": 0.95, + "learning_rate": 1.4491976013756292e-07, + "loss": 0.462, + "step": 11323 + }, + { + "epoch": 0.95, + "learning_rate": 1.4446044406023485e-07, + "loss": 0.4504, + "step": 11324 + }, + { + "epoch": 0.95, + "learning_rate": 1.4400185173274018e-07, + "loss": 0.4507, + "step": 11325 + }, + { + "epoch": 0.95, + "learning_rate": 1.4354398318875417e-07, + "loss": 0.4674, + "step": 11326 + }, + { + "epoch": 0.95, + "learning_rate": 1.430868384619022e-07, + "loss": 0.4756, + "step": 11327 + }, + { + "epoch": 0.95, + "learning_rate": 1.4263041758575402e-07, + "loss": 0.4396, + "step": 11328 + }, + { + "epoch": 0.95, + "learning_rate": 1.4217472059382952e-07, + "loss": 0.464, + "step": 11329 + }, + { + "epoch": 0.95, + "learning_rate": 1.4171974751959082e-07, + "loss": 0.4678, + "step": 11330 + }, + { + "epoch": 0.95, + "learning_rate": 1.4126549839645009e-07, + "loss": 0.4847, + "step": 11331 + }, + { + "epoch": 0.95, + "learning_rate": 1.408119732577662e-07, + "loss": 0.4553, + "step": 11332 + }, + { + "epoch": 0.95, + "learning_rate": 1.4035917213684358e-07, + "loss": 0.4686, + "step": 11333 + }, + { + "epoch": 0.95, + "learning_rate": 1.3990709506693457e-07, + "loss": 0.4596, + "step": 11334 + }, + { + "epoch": 0.95, + "learning_rate": 1.394557420812359e-07, + "loss": 0.443, + "step": 11335 + }, + { + "epoch": 0.95, + "learning_rate": 1.3900511321289557e-07, + "loss": 0.4613, + "step": 11336 + }, + { + "epoch": 0.95, + "learning_rate": 1.385552084950037e-07, + "loss": 0.4579, + "step": 11337 + }, + { + "epoch": 0.95, + "learning_rate": 1.381060279606017e-07, + "loss": 0.4549, + "step": 11338 + }, + { + "epoch": 0.95, + "learning_rate": 1.3765757164267313e-07, + "loss": 0.4551, + "step": 11339 + }, + { + "epoch": 0.95, + "learning_rate": 1.3720983957415278e-07, + "loss": 0.4749, + "step": 11340 + }, + { + "epoch": 0.95, + "learning_rate": 1.3676283178791882e-07, + "loss": 0.4428, + "step": 11341 + }, + { + "epoch": 0.95, + "learning_rate": 1.363165483167983e-07, + "loss": 0.4797, + "step": 11342 + }, + { + "epoch": 0.95, + "learning_rate": 1.35870989193565e-07, + "loss": 0.4681, + "step": 11343 + }, + { + "epoch": 0.95, + "learning_rate": 1.3542615445093722e-07, + "loss": 0.4495, + "step": 11344 + }, + { + "epoch": 0.95, + "learning_rate": 1.3498204412158434e-07, + "loss": 0.4612, + "step": 11345 + }, + { + "epoch": 0.95, + "learning_rate": 1.3453865823811696e-07, + "loss": 0.4608, + "step": 11346 + }, + { + "epoch": 0.95, + "learning_rate": 1.3409599683309793e-07, + "loss": 0.4477, + "step": 11347 + }, + { + "epoch": 0.95, + "learning_rate": 1.3365405993903347e-07, + "loss": 0.4679, + "step": 11348 + }, + { + "epoch": 0.95, + "learning_rate": 1.332128475883765e-07, + "loss": 0.4465, + "step": 11349 + }, + { + "epoch": 0.95, + "learning_rate": 1.3277235981352887e-07, + "loss": 0.4629, + "step": 11350 + }, + { + "epoch": 0.95, + "learning_rate": 1.3233259664683916e-07, + "loss": 0.4655, + "step": 11351 + }, + { + "epoch": 0.95, + "learning_rate": 1.3189355812060157e-07, + "loss": 0.4558, + "step": 11352 + }, + { + "epoch": 0.95, + "learning_rate": 1.314552442670558e-07, + "loss": 0.4475, + "step": 11353 + }, + { + "epoch": 0.95, + "learning_rate": 1.310176551183906e-07, + "loss": 0.4415, + "step": 11354 + }, + { + "epoch": 0.95, + "learning_rate": 1.3058079070674023e-07, + "loss": 0.4641, + "step": 11355 + }, + { + "epoch": 0.95, + "learning_rate": 1.3014465106418573e-07, + "loss": 0.4601, + "step": 11356 + }, + { + "epoch": 0.95, + "learning_rate": 1.297092362227581e-07, + "loss": 0.4457, + "step": 11357 + }, + { + "epoch": 0.95, + "learning_rate": 1.2927454621442959e-07, + "loss": 0.4609, + "step": 11358 + }, + { + "epoch": 0.95, + "learning_rate": 1.2884058107112353e-07, + "loss": 0.4725, + "step": 11359 + }, + { + "epoch": 0.95, + "learning_rate": 1.2840734082470662e-07, + "loss": 0.455, + "step": 11360 + }, + { + "epoch": 0.95, + "learning_rate": 1.279748255069968e-07, + "loss": 0.453, + "step": 11361 + }, + { + "epoch": 0.95, + "learning_rate": 1.275430351497542e-07, + "loss": 0.4684, + "step": 11362 + }, + { + "epoch": 0.95, + "learning_rate": 1.27111969784689e-07, + "loss": 0.4651, + "step": 11363 + }, + { + "epoch": 0.95, + "learning_rate": 1.2668162944345587e-07, + "loss": 0.4371, + "step": 11364 + }, + { + "epoch": 0.95, + "learning_rate": 1.262520141576584e-07, + "loss": 0.4689, + "step": 11365 + }, + { + "epoch": 0.95, + "learning_rate": 1.2582312395884476e-07, + "loss": 0.4626, + "step": 11366 + }, + { + "epoch": 0.95, + "learning_rate": 1.2539495887851083e-07, + "loss": 0.4517, + "step": 11367 + }, + { + "epoch": 0.95, + "learning_rate": 1.2496751894810032e-07, + "loss": 0.4605, + "step": 11368 + }, + { + "epoch": 0.95, + "learning_rate": 1.245408041990004e-07, + "loss": 0.4645, + "step": 11369 + }, + { + "epoch": 0.95, + "learning_rate": 1.2411481466254926e-07, + "loss": 0.4477, + "step": 11370 + }, + { + "epoch": 0.95, + "learning_rate": 1.2368955037002973e-07, + "loss": 0.4739, + "step": 11371 + }, + { + "epoch": 0.95, + "learning_rate": 1.232650113526701e-07, + "loss": 0.4712, + "step": 11372 + }, + { + "epoch": 0.95, + "learning_rate": 1.228411976416488e-07, + "loss": 0.4649, + "step": 11373 + }, + { + "epoch": 0.95, + "learning_rate": 1.2241810926808762e-07, + "loss": 0.4477, + "step": 11374 + }, + { + "epoch": 0.95, + "learning_rate": 1.219957462630561e-07, + "loss": 0.4506, + "step": 11375 + }, + { + "epoch": 0.95, + "learning_rate": 1.2157410865757057e-07, + "loss": 0.4762, + "step": 11376 + }, + { + "epoch": 0.95, + "learning_rate": 1.2115319648259516e-07, + "loss": 0.4677, + "step": 11377 + }, + { + "epoch": 0.95, + "learning_rate": 1.2073300976904067e-07, + "loss": 0.4585, + "step": 11378 + }, + { + "epoch": 0.95, + "learning_rate": 1.2031354854776356e-07, + "loss": 0.4589, + "step": 11379 + }, + { + "epoch": 0.95, + "learning_rate": 1.198948128495647e-07, + "loss": 0.4742, + "step": 11380 + }, + { + "epoch": 0.95, + "learning_rate": 1.1947680270519733e-07, + "loss": 0.4694, + "step": 11381 + }, + { + "epoch": 0.95, + "learning_rate": 1.19059518145358e-07, + "loss": 0.4748, + "step": 11382 + }, + { + "epoch": 0.95, + "learning_rate": 1.186429592006888e-07, + "loss": 0.4683, + "step": 11383 + }, + { + "epoch": 0.95, + "learning_rate": 1.1822712590178197e-07, + "loss": 0.4732, + "step": 11384 + }, + { + "epoch": 0.95, + "learning_rate": 1.178120182791731e-07, + "loss": 0.4454, + "step": 11385 + }, + { + "epoch": 0.95, + "learning_rate": 1.1739763636334667e-07, + "loss": 0.4684, + "step": 11386 + }, + { + "epoch": 0.95, + "learning_rate": 1.1698398018473278e-07, + "loss": 0.4555, + "step": 11387 + }, + { + "epoch": 0.95, + "learning_rate": 1.1657104977370937e-07, + "loss": 0.4729, + "step": 11388 + }, + { + "epoch": 0.95, + "learning_rate": 1.1615884516059883e-07, + "loss": 0.4459, + "step": 11389 + }, + { + "epoch": 0.95, + "learning_rate": 1.1574736637567252e-07, + "loss": 0.462, + "step": 11390 + }, + { + "epoch": 0.95, + "learning_rate": 1.1533661344914848e-07, + "loss": 0.4428, + "step": 11391 + }, + { + "epoch": 0.95, + "learning_rate": 1.1492658641119037e-07, + "loss": 0.4663, + "step": 11392 + }, + { + "epoch": 0.95, + "learning_rate": 1.1451728529190852e-07, + "loss": 0.4739, + "step": 11393 + }, + { + "epoch": 0.95, + "learning_rate": 1.1410871012136116e-07, + "loss": 0.4518, + "step": 11394 + }, + { + "epoch": 0.95, + "learning_rate": 1.137008609295509e-07, + "loss": 0.4517, + "step": 11395 + }, + { + "epoch": 0.95, + "learning_rate": 1.1329373774642938e-07, + "loss": 0.4603, + "step": 11396 + }, + { + "epoch": 0.95, + "learning_rate": 1.1288734060189267e-07, + "loss": 0.4487, + "step": 11397 + }, + { + "epoch": 0.95, + "learning_rate": 1.1248166952578799e-07, + "loss": 0.4477, + "step": 11398 + }, + { + "epoch": 0.95, + "learning_rate": 1.1207672454790264e-07, + "loss": 0.4674, + "step": 11399 + }, + { + "epoch": 0.95, + "learning_rate": 1.1167250569797728e-07, + "loss": 0.4888, + "step": 11400 + }, + { + "epoch": 0.95, + "learning_rate": 1.112690130056926e-07, + "loss": 0.4248, + "step": 11401 + }, + { + "epoch": 0.95, + "learning_rate": 1.1086624650068267e-07, + "loss": 0.4714, + "step": 11402 + }, + { + "epoch": 0.95, + "learning_rate": 1.1046420621252275e-07, + "loss": 0.4564, + "step": 11403 + }, + { + "epoch": 0.95, + "learning_rate": 1.1006289217073806e-07, + "loss": 0.4568, + "step": 11404 + }, + { + "epoch": 0.95, + "learning_rate": 1.0966230440479953e-07, + "loss": 0.4453, + "step": 11405 + }, + { + "epoch": 0.95, + "learning_rate": 1.0926244294412359e-07, + "loss": 0.4599, + "step": 11406 + }, + { + "epoch": 0.95, + "learning_rate": 1.0886330781807674e-07, + "loss": 0.4831, + "step": 11407 + }, + { + "epoch": 0.95, + "learning_rate": 1.0846489905596669e-07, + "loss": 0.459, + "step": 11408 + }, + { + "epoch": 0.95, + "learning_rate": 1.0806721668705333e-07, + "loss": 0.4722, + "step": 11409 + }, + { + "epoch": 0.95, + "learning_rate": 1.0767026074053888e-07, + "loss": 0.4564, + "step": 11410 + }, + { + "epoch": 0.95, + "learning_rate": 1.0727403124557667e-07, + "loss": 0.473, + "step": 11411 + }, + { + "epoch": 0.95, + "learning_rate": 1.0687852823126122e-07, + "loss": 0.4533, + "step": 11412 + }, + { + "epoch": 0.95, + "learning_rate": 1.0648375172663927e-07, + "loss": 0.466, + "step": 11413 + }, + { + "epoch": 0.95, + "learning_rate": 1.0608970176069987e-07, + "loss": 0.4882, + "step": 11414 + }, + { + "epoch": 0.96, + "learning_rate": 1.05696378362381e-07, + "loss": 0.4757, + "step": 11415 + }, + { + "epoch": 0.96, + "learning_rate": 1.053037815605662e-07, + "loss": 0.4573, + "step": 11416 + }, + { + "epoch": 0.96, + "learning_rate": 1.0491191138408685e-07, + "loss": 0.4652, + "step": 11417 + }, + { + "epoch": 0.96, + "learning_rate": 1.0452076786171994e-07, + "loss": 0.4586, + "step": 11418 + }, + { + "epoch": 0.96, + "learning_rate": 1.0413035102219027e-07, + "loss": 0.4461, + "step": 11419 + }, + { + "epoch": 0.96, + "learning_rate": 1.0374066089416602e-07, + "loss": 0.4575, + "step": 11420 + }, + { + "epoch": 0.96, + "learning_rate": 1.033516975062676e-07, + "loss": 0.4532, + "step": 11421 + }, + { + "epoch": 0.96, + "learning_rate": 1.0296346088705555e-07, + "loss": 0.4417, + "step": 11422 + }, + { + "epoch": 0.96, + "learning_rate": 1.025759510650437e-07, + "loss": 0.4606, + "step": 11423 + }, + { + "epoch": 0.96, + "learning_rate": 1.0218916806868594e-07, + "loss": 0.469, + "step": 11424 + }, + { + "epoch": 0.96, + "learning_rate": 1.0180311192638848e-07, + "loss": 0.4542, + "step": 11425 + }, + { + "epoch": 0.96, + "learning_rate": 1.0141778266650082e-07, + "loss": 0.4661, + "step": 11426 + }, + { + "epoch": 0.96, + "learning_rate": 1.0103318031732035e-07, + "loss": 0.4652, + "step": 11427 + }, + { + "epoch": 0.96, + "learning_rate": 1.006493049070889e-07, + "loss": 0.4853, + "step": 11428 + }, + { + "epoch": 0.96, + "learning_rate": 1.002661564639995e-07, + "loss": 0.4559, + "step": 11429 + }, + { + "epoch": 0.96, + "learning_rate": 9.988373501618631e-08, + "loss": 0.4535, + "step": 11430 + }, + { + "epoch": 0.96, + "learning_rate": 9.950204059173462e-08, + "loss": 0.4537, + "step": 11431 + }, + { + "epoch": 0.96, + "learning_rate": 9.912107321867315e-08, + "loss": 0.462, + "step": 11432 + }, + { + "epoch": 0.96, + "learning_rate": 9.87408329249795e-08, + "loss": 0.4469, + "step": 11433 + }, + { + "epoch": 0.96, + "learning_rate": 9.836131973857687e-08, + "loss": 0.4602, + "step": 11434 + }, + { + "epoch": 0.96, + "learning_rate": 9.798253368733523e-08, + "loss": 0.4734, + "step": 11435 + }, + { + "epoch": 0.96, + "learning_rate": 9.76044747990701e-08, + "loss": 0.4662, + "step": 11436 + }, + { + "epoch": 0.96, + "learning_rate": 9.722714310154591e-08, + "loss": 0.4702, + "step": 11437 + }, + { + "epoch": 0.96, + "learning_rate": 9.685053862247051e-08, + "loss": 0.4542, + "step": 11438 + }, + { + "epoch": 0.96, + "learning_rate": 9.647466138950178e-08, + "loss": 0.4661, + "step": 11439 + }, + { + "epoch": 0.96, + "learning_rate": 9.60995114302421e-08, + "loss": 0.4739, + "step": 11440 + }, + { + "epoch": 0.96, + "learning_rate": 9.572508877224163e-08, + "loss": 0.4406, + "step": 11441 + }, + { + "epoch": 0.96, + "learning_rate": 9.535139344299393e-08, + "loss": 0.4697, + "step": 11442 + }, + { + "epoch": 0.96, + "learning_rate": 9.497842546994485e-08, + "loss": 0.4764, + "step": 11443 + }, + { + "epoch": 0.96, + "learning_rate": 9.460618488048024e-08, + "loss": 0.4497, + "step": 11444 + }, + { + "epoch": 0.96, + "learning_rate": 9.423467170193933e-08, + "loss": 0.4531, + "step": 11445 + }, + { + "epoch": 0.96, + "learning_rate": 9.386388596160367e-08, + "loss": 0.4582, + "step": 11446 + }, + { + "epoch": 0.96, + "learning_rate": 9.349382768670034e-08, + "loss": 0.4613, + "step": 11447 + }, + { + "epoch": 0.96, + "learning_rate": 9.31244969044065e-08, + "loss": 0.4622, + "step": 11448 + }, + { + "epoch": 0.96, + "learning_rate": 9.275589364184379e-08, + "loss": 0.4951, + "step": 11449 + }, + { + "epoch": 0.96, + "learning_rate": 9.238801792608054e-08, + "loss": 0.4514, + "step": 11450 + }, + { + "epoch": 0.96, + "learning_rate": 9.202086978413294e-08, + "loss": 0.4673, + "step": 11451 + }, + { + "epoch": 0.96, + "learning_rate": 9.165444924296163e-08, + "loss": 0.4674, + "step": 11452 + }, + { + "epoch": 0.96, + "learning_rate": 9.12887563294751e-08, + "loss": 0.462, + "step": 11453 + }, + { + "epoch": 0.96, + "learning_rate": 9.092379107053074e-08, + "loss": 0.4548, + "step": 11454 + }, + { + "epoch": 0.96, + "learning_rate": 9.055955349292711e-08, + "loss": 0.4618, + "step": 11455 + }, + { + "epoch": 0.96, + "learning_rate": 9.019604362341394e-08, + "loss": 0.4822, + "step": 11456 + }, + { + "epoch": 0.96, + "learning_rate": 8.983326148868432e-08, + "loss": 0.4545, + "step": 11457 + }, + { + "epoch": 0.96, + "learning_rate": 8.947120711538138e-08, + "loss": 0.4525, + "step": 11458 + }, + { + "epoch": 0.96, + "learning_rate": 8.910988053009162e-08, + "loss": 0.462, + "step": 11459 + }, + { + "epoch": 0.96, + "learning_rate": 8.874928175934938e-08, + "loss": 0.4336, + "step": 11460 + }, + { + "epoch": 0.96, + "learning_rate": 8.838941082963681e-08, + "loss": 0.4565, + "step": 11461 + }, + { + "epoch": 0.96, + "learning_rate": 8.803026776738055e-08, + "loss": 0.4647, + "step": 11462 + }, + { + "epoch": 0.96, + "learning_rate": 8.767185259895284e-08, + "loss": 0.4468, + "step": 11463 + }, + { + "epoch": 0.96, + "learning_rate": 8.731416535067705e-08, + "loss": 0.4473, + "step": 11464 + }, + { + "epoch": 0.96, + "learning_rate": 8.695720604881886e-08, + "loss": 0.4576, + "step": 11465 + }, + { + "epoch": 0.96, + "learning_rate": 8.660097471959173e-08, + "loss": 0.4786, + "step": 11466 + }, + { + "epoch": 0.96, + "learning_rate": 8.624547138915696e-08, + "loss": 0.4623, + "step": 11467 + }, + { + "epoch": 0.96, + "learning_rate": 8.589069608361922e-08, + "loss": 0.4606, + "step": 11468 + }, + { + "epoch": 0.96, + "learning_rate": 8.553664882903323e-08, + "loss": 0.4581, + "step": 11469 + }, + { + "epoch": 0.96, + "learning_rate": 8.518332965139931e-08, + "loss": 0.4398, + "step": 11470 + }, + { + "epoch": 0.96, + "learning_rate": 8.483073857666224e-08, + "loss": 0.4641, + "step": 11471 + }, + { + "epoch": 0.96, + "learning_rate": 8.447887563071466e-08, + "loss": 0.4707, + "step": 11472 + }, + { + "epoch": 0.96, + "learning_rate": 8.4127740839397e-08, + "loss": 0.4626, + "step": 11473 + }, + { + "epoch": 0.96, + "learning_rate": 8.377733422849532e-08, + "loss": 0.4563, + "step": 11474 + }, + { + "epoch": 0.96, + "learning_rate": 8.342765582374124e-08, + "loss": 0.4642, + "step": 11475 + }, + { + "epoch": 0.96, + "learning_rate": 8.307870565081422e-08, + "loss": 0.4385, + "step": 11476 + }, + { + "epoch": 0.96, + "learning_rate": 8.273048373533932e-08, + "loss": 0.4736, + "step": 11477 + }, + { + "epoch": 0.96, + "learning_rate": 8.23829901028883e-08, + "loss": 0.45, + "step": 11478 + }, + { + "epoch": 0.96, + "learning_rate": 8.203622477898077e-08, + "loss": 0.4565, + "step": 11479 + }, + { + "epoch": 0.96, + "learning_rate": 8.169018778908078e-08, + "loss": 0.4609, + "step": 11480 + }, + { + "epoch": 0.96, + "learning_rate": 8.134487915860024e-08, + "loss": 0.4565, + "step": 11481 + }, + { + "epoch": 0.96, + "learning_rate": 8.100029891289662e-08, + "loss": 0.4625, + "step": 11482 + }, + { + "epoch": 0.96, + "learning_rate": 8.065644707727415e-08, + "loss": 0.4632, + "step": 11483 + }, + { + "epoch": 0.96, + "learning_rate": 8.031332367698486e-08, + "loss": 0.4644, + "step": 11484 + }, + { + "epoch": 0.96, + "learning_rate": 7.997092873722633e-08, + "loss": 0.4493, + "step": 11485 + }, + { + "epoch": 0.96, + "learning_rate": 7.962926228314293e-08, + "loss": 0.4484, + "step": 11486 + }, + { + "epoch": 0.96, + "learning_rate": 7.928832433982348e-08, + "loss": 0.4623, + "step": 11487 + }, + { + "epoch": 0.96, + "learning_rate": 7.89481149323068e-08, + "loss": 0.4518, + "step": 11488 + }, + { + "epoch": 0.96, + "learning_rate": 7.860863408557629e-08, + "loss": 0.4552, + "step": 11489 + }, + { + "epoch": 0.96, + "learning_rate": 7.826988182456086e-08, + "loss": 0.4685, + "step": 11490 + }, + { + "epoch": 0.96, + "learning_rate": 7.793185817413728e-08, + "loss": 0.4479, + "step": 11491 + }, + { + "epoch": 0.96, + "learning_rate": 7.759456315912905e-08, + "loss": 0.478, + "step": 11492 + }, + { + "epoch": 0.96, + "learning_rate": 7.725799680430634e-08, + "loss": 0.4773, + "step": 11493 + }, + { + "epoch": 0.96, + "learning_rate": 7.692215913438383e-08, + "loss": 0.4452, + "step": 11494 + }, + { + "epoch": 0.96, + "learning_rate": 7.658705017402623e-08, + "loss": 0.4524, + "step": 11495 + }, + { + "epoch": 0.96, + "learning_rate": 7.625266994784053e-08, + "loss": 0.4712, + "step": 11496 + }, + { + "epoch": 0.96, + "learning_rate": 7.591901848038263e-08, + "loss": 0.4557, + "step": 11497 + }, + { + "epoch": 0.96, + "learning_rate": 7.558609579615406e-08, + "loss": 0.4618, + "step": 11498 + }, + { + "epoch": 0.96, + "learning_rate": 7.525390191960413e-08, + "loss": 0.4687, + "step": 11499 + }, + { + "epoch": 0.96, + "learning_rate": 7.49224368751278e-08, + "loss": 0.4418, + "step": 11500 + }, + { + "epoch": 0.96, + "learning_rate": 7.459170068706555e-08, + "loss": 0.4609, + "step": 11501 + }, + { + "epoch": 0.96, + "learning_rate": 7.42616933797069e-08, + "loss": 0.4724, + "step": 11502 + }, + { + "epoch": 0.96, + "learning_rate": 7.393241497728465e-08, + "loss": 0.4743, + "step": 11503 + }, + { + "epoch": 0.96, + "learning_rate": 7.360386550398058e-08, + "loss": 0.4792, + "step": 11504 + }, + { + "epoch": 0.96, + "learning_rate": 7.327604498392094e-08, + "loss": 0.4734, + "step": 11505 + }, + { + "epoch": 0.96, + "learning_rate": 7.294895344118091e-08, + "loss": 0.4442, + "step": 11506 + }, + { + "epoch": 0.96, + "learning_rate": 7.262259089977907e-08, + "loss": 0.4476, + "step": 11507 + }, + { + "epoch": 0.96, + "learning_rate": 7.229695738368403e-08, + "loss": 0.493, + "step": 11508 + }, + { + "epoch": 0.96, + "learning_rate": 7.197205291680887e-08, + "loss": 0.4545, + "step": 11509 + }, + { + "epoch": 0.96, + "learning_rate": 7.164787752301117e-08, + "loss": 0.4578, + "step": 11510 + }, + { + "epoch": 0.96, + "learning_rate": 7.132443122609856e-08, + "loss": 0.4767, + "step": 11511 + }, + { + "epoch": 0.96, + "learning_rate": 7.100171404982315e-08, + "loss": 0.4626, + "step": 11512 + }, + { + "epoch": 0.96, + "learning_rate": 7.067972601788376e-08, + "loss": 0.4525, + "step": 11513 + }, + { + "epoch": 0.96, + "learning_rate": 7.035846715392591e-08, + "loss": 0.4466, + "step": 11514 + }, + { + "epoch": 0.96, + "learning_rate": 7.003793748154186e-08, + "loss": 0.4565, + "step": 11515 + }, + { + "epoch": 0.96, + "learning_rate": 6.971813702427055e-08, + "loss": 0.4513, + "step": 11516 + }, + { + "epoch": 0.96, + "learning_rate": 6.939906580559542e-08, + "loss": 0.4462, + "step": 11517 + }, + { + "epoch": 0.96, + "learning_rate": 6.908072384894881e-08, + "loss": 0.4708, + "step": 11518 + }, + { + "epoch": 0.96, + "learning_rate": 6.876311117770762e-08, + "loss": 0.4715, + "step": 11519 + }, + { + "epoch": 0.96, + "learning_rate": 6.844622781519649e-08, + "loss": 0.4652, + "step": 11520 + }, + { + "epoch": 0.96, + "learning_rate": 6.813007378468684e-08, + "loss": 0.4617, + "step": 11521 + }, + { + "epoch": 0.96, + "learning_rate": 6.78146491093945e-08, + "loss": 0.4697, + "step": 11522 + }, + { + "epoch": 0.96, + "learning_rate": 6.74999538124832e-08, + "loss": 0.4436, + "step": 11523 + }, + { + "epoch": 0.96, + "learning_rate": 6.718598791706221e-08, + "loss": 0.4746, + "step": 11524 + }, + { + "epoch": 0.96, + "learning_rate": 6.687275144618865e-08, + "loss": 0.4787, + "step": 11525 + }, + { + "epoch": 0.96, + "learning_rate": 6.656024442286524e-08, + "loss": 0.4546, + "step": 11526 + }, + { + "epoch": 0.96, + "learning_rate": 6.62484668700425e-08, + "loss": 0.4944, + "step": 11527 + }, + { + "epoch": 0.96, + "learning_rate": 6.593741881061321e-08, + "loss": 0.4772, + "step": 11528 + }, + { + "epoch": 0.96, + "learning_rate": 6.562710026742248e-08, + "loss": 0.4597, + "step": 11529 + }, + { + "epoch": 0.96, + "learning_rate": 6.531751126325647e-08, + "loss": 0.462, + "step": 11530 + }, + { + "epoch": 0.96, + "learning_rate": 6.500865182085148e-08, + "loss": 0.4656, + "step": 11531 + }, + { + "epoch": 0.96, + "learning_rate": 6.470052196288712e-08, + "loss": 0.4457, + "step": 11532 + }, + { + "epoch": 0.96, + "learning_rate": 6.439312171199308e-08, + "loss": 0.462, + "step": 11533 + }, + { + "epoch": 0.96, + "learning_rate": 6.408645109074352e-08, + "loss": 0.4589, + "step": 11534 + }, + { + "epoch": 0.97, + "learning_rate": 6.37805101216571e-08, + "loss": 0.4681, + "step": 11535 + }, + { + "epoch": 0.97, + "learning_rate": 6.34752988272036e-08, + "loss": 0.4498, + "step": 11536 + }, + { + "epoch": 0.97, + "learning_rate": 6.317081722979402e-08, + "loss": 0.4609, + "step": 11537 + }, + { + "epoch": 0.97, + "learning_rate": 6.286706535179044e-08, + "loss": 0.4832, + "step": 11538 + }, + { + "epoch": 0.97, + "learning_rate": 6.256404321549725e-08, + "loss": 0.4635, + "step": 11539 + }, + { + "epoch": 0.97, + "learning_rate": 6.226175084316666e-08, + "loss": 0.4608, + "step": 11540 + }, + { + "epoch": 0.97, + "learning_rate": 6.19601882570009e-08, + "loss": 0.4557, + "step": 11541 + }, + { + "epoch": 0.97, + "learning_rate": 6.165935547914225e-08, + "loss": 0.458, + "step": 11542 + }, + { + "epoch": 0.97, + "learning_rate": 6.135925253168417e-08, + "loss": 0.4766, + "step": 11543 + }, + { + "epoch": 0.97, + "learning_rate": 6.105987943666459e-08, + "loss": 0.455, + "step": 11544 + }, + { + "epoch": 0.97, + "learning_rate": 6.07612362160681e-08, + "loss": 0.4563, + "step": 11545 + }, + { + "epoch": 0.97, + "learning_rate": 6.046332289182722e-08, + "loss": 0.4636, + "step": 11546 + }, + { + "epoch": 0.97, + "learning_rate": 6.016613948581662e-08, + "loss": 0.4598, + "step": 11547 + }, + { + "epoch": 0.97, + "learning_rate": 5.98696860198622e-08, + "loss": 0.4772, + "step": 11548 + }, + { + "epoch": 0.97, + "learning_rate": 5.957396251573433e-08, + "loss": 0.4755, + "step": 11549 + }, + { + "epoch": 0.97, + "learning_rate": 5.9278968995150066e-08, + "loss": 0.4486, + "step": 11550 + }, + { + "epoch": 0.97, + "learning_rate": 5.898470547977098e-08, + "loss": 0.4531, + "step": 11551 + }, + { + "epoch": 0.97, + "learning_rate": 5.8691171991207554e-08, + "loss": 0.4647, + "step": 11552 + }, + { + "epoch": 0.97, + "learning_rate": 5.8398368551014774e-08, + "loss": 0.4795, + "step": 11553 + }, + { + "epoch": 0.97, + "learning_rate": 5.810629518069655e-08, + "loss": 0.4659, + "step": 11554 + }, + { + "epoch": 0.97, + "learning_rate": 5.781495190170017e-08, + "loss": 0.4633, + "step": 11555 + }, + { + "epoch": 0.97, + "learning_rate": 5.7524338735420734e-08, + "loss": 0.4726, + "step": 11556 + }, + { + "epoch": 0.97, + "learning_rate": 5.7234455703200073e-08, + "loss": 0.4533, + "step": 11557 + }, + { + "epoch": 0.97, + "learning_rate": 5.69453028263256e-08, + "loss": 0.4576, + "step": 11558 + }, + { + "epoch": 0.97, + "learning_rate": 5.6656880126032544e-08, + "loss": 0.5139, + "step": 11559 + }, + { + "epoch": 0.97, + "learning_rate": 5.636918762350063e-08, + "loss": 0.4825, + "step": 11560 + }, + { + "epoch": 0.97, + "learning_rate": 5.60822253398563e-08, + "loss": 0.4501, + "step": 11561 + }, + { + "epoch": 0.97, + "learning_rate": 5.57959932961738e-08, + "loss": 0.4619, + "step": 11562 + }, + { + "epoch": 0.97, + "learning_rate": 5.551049151347299e-08, + "loss": 0.4715, + "step": 11563 + }, + { + "epoch": 0.97, + "learning_rate": 5.522572001271931e-08, + "loss": 0.4353, + "step": 11564 + }, + { + "epoch": 0.97, + "learning_rate": 5.494167881482493e-08, + "loss": 0.4583, + "step": 11565 + }, + { + "epoch": 0.97, + "learning_rate": 5.4658367940648716e-08, + "loss": 0.4748, + "step": 11566 + }, + { + "epoch": 0.97, + "learning_rate": 5.437578741099625e-08, + "loss": 0.4489, + "step": 11567 + }, + { + "epoch": 0.97, + "learning_rate": 5.409393724661982e-08, + "loss": 0.4516, + "step": 11568 + }, + { + "epoch": 0.97, + "learning_rate": 5.381281746821621e-08, + "loss": 0.4539, + "step": 11569 + }, + { + "epoch": 0.97, + "learning_rate": 5.353242809643e-08, + "loss": 0.4893, + "step": 11570 + }, + { + "epoch": 0.97, + "learning_rate": 5.3252769151851404e-08, + "loss": 0.4578, + "step": 11571 + }, + { + "epoch": 0.97, + "learning_rate": 5.297384065501843e-08, + "loss": 0.4645, + "step": 11572 + }, + { + "epoch": 0.97, + "learning_rate": 5.269564262641358e-08, + "loss": 0.45, + "step": 11573 + }, + { + "epoch": 0.97, + "learning_rate": 5.241817508646607e-08, + "loss": 0.4595, + "step": 11574 + }, + { + "epoch": 0.97, + "learning_rate": 5.214143805555294e-08, + "loss": 0.4711, + "step": 11575 + }, + { + "epoch": 0.97, + "learning_rate": 5.1865431553996814e-08, + "loss": 0.4387, + "step": 11576 + }, + { + "epoch": 0.97, + "learning_rate": 5.159015560206593e-08, + "loss": 0.4737, + "step": 11577 + }, + { + "epoch": 0.97, + "learning_rate": 5.131561021997522e-08, + "loss": 0.4596, + "step": 11578 + }, + { + "epoch": 0.97, + "learning_rate": 5.104179542788634e-08, + "loss": 0.4678, + "step": 11579 + }, + { + "epoch": 0.97, + "learning_rate": 5.0768711245907654e-08, + "loss": 0.458, + "step": 11580 + }, + { + "epoch": 0.97, + "learning_rate": 5.049635769409311e-08, + "loss": 0.4588, + "step": 11581 + }, + { + "epoch": 0.97, + "learning_rate": 5.022473479244228e-08, + "loss": 0.4621, + "step": 11582 + }, + { + "epoch": 0.97, + "learning_rate": 4.995384256090252e-08, + "loss": 0.4776, + "step": 11583 + }, + { + "epoch": 0.97, + "learning_rate": 4.9683681019367935e-08, + "loss": 0.5035, + "step": 11584 + }, + { + "epoch": 0.97, + "learning_rate": 4.941425018767709e-08, + "loss": 0.4653, + "step": 11585 + }, + { + "epoch": 0.97, + "learning_rate": 4.914555008561528e-08, + "loss": 0.4472, + "step": 11586 + }, + { + "epoch": 0.97, + "learning_rate": 4.8877580732916706e-08, + "loss": 0.4582, + "step": 11587 + }, + { + "epoch": 0.97, + "learning_rate": 4.861034214925786e-08, + "loss": 0.4557, + "step": 11588 + }, + { + "epoch": 0.97, + "learning_rate": 4.834383435426526e-08, + "loss": 0.4401, + "step": 11589 + }, + { + "epoch": 0.97, + "learning_rate": 4.807805736750881e-08, + "loss": 0.4679, + "step": 11590 + }, + { + "epoch": 0.97, + "learning_rate": 4.7813011208507344e-08, + "loss": 0.4689, + "step": 11591 + }, + { + "epoch": 0.97, + "learning_rate": 4.754869589672306e-08, + "loss": 0.4587, + "step": 11592 + }, + { + "epoch": 0.97, + "learning_rate": 4.728511145156822e-08, + "loss": 0.4385, + "step": 11593 + }, + { + "epoch": 0.97, + "learning_rate": 4.702225789239734e-08, + "loss": 0.4664, + "step": 11594 + }, + { + "epoch": 0.97, + "learning_rate": 4.676013523851497e-08, + "loss": 0.4549, + "step": 11595 + }, + { + "epoch": 0.97, + "learning_rate": 4.6498743509170165e-08, + "loss": 0.4589, + "step": 11596 + }, + { + "epoch": 0.97, + "learning_rate": 4.6238082723557566e-08, + "loss": 0.479, + "step": 11597 + }, + { + "epoch": 0.97, + "learning_rate": 4.597815290081853e-08, + "loss": 0.4623, + "step": 11598 + }, + { + "epoch": 0.97, + "learning_rate": 4.571895406004334e-08, + "loss": 0.4538, + "step": 11599 + }, + { + "epoch": 0.97, + "learning_rate": 4.546048622026455e-08, + "loss": 0.4619, + "step": 11600 + }, + { + "epoch": 0.97, + "learning_rate": 4.520274940046254e-08, + "loss": 0.4445, + "step": 11601 + }, + { + "epoch": 0.97, + "learning_rate": 4.494574361956661e-08, + "loss": 0.4731, + "step": 11602 + }, + { + "epoch": 0.97, + "learning_rate": 4.4689468896449426e-08, + "loss": 0.4714, + "step": 11603 + }, + { + "epoch": 0.97, + "learning_rate": 4.44339252499304e-08, + "loss": 0.4801, + "step": 11604 + }, + { + "epoch": 0.97, + "learning_rate": 4.4179112698774505e-08, + "loss": 0.4417, + "step": 11605 + }, + { + "epoch": 0.97, + "learning_rate": 4.392503126169678e-08, + "loss": 0.4605, + "step": 11606 + }, + { + "epoch": 0.97, + "learning_rate": 4.3671680957352304e-08, + "loss": 0.4555, + "step": 11607 + }, + { + "epoch": 0.97, + "learning_rate": 4.341906180434952e-08, + "loss": 0.4503, + "step": 11608 + }, + { + "epoch": 0.97, + "learning_rate": 4.3167173821238026e-08, + "loss": 0.4642, + "step": 11609 + }, + { + "epoch": 0.97, + "learning_rate": 4.291601702651527e-08, + "loss": 0.4799, + "step": 11610 + }, + { + "epoch": 0.97, + "learning_rate": 4.2665591438626474e-08, + "loss": 0.4446, + "step": 11611 + }, + { + "epoch": 0.97, + "learning_rate": 4.241589707596028e-08, + "loss": 0.4713, + "step": 11612 + }, + { + "epoch": 0.97, + "learning_rate": 4.216693395685423e-08, + "loss": 0.4628, + "step": 11613 + }, + { + "epoch": 0.97, + "learning_rate": 4.191870209959037e-08, + "loss": 0.4603, + "step": 11614 + }, + { + "epoch": 0.97, + "learning_rate": 4.167120152239856e-08, + "loss": 0.4876, + "step": 11615 + }, + { + "epoch": 0.97, + "learning_rate": 4.142443224345427e-08, + "loss": 0.4624, + "step": 11616 + }, + { + "epoch": 0.97, + "learning_rate": 4.1178394280878554e-08, + "loss": 0.4711, + "step": 11617 + }, + { + "epoch": 0.97, + "learning_rate": 4.093308765273918e-08, + "loss": 0.4748, + "step": 11618 + }, + { + "epoch": 0.97, + "learning_rate": 4.068851237705174e-08, + "loss": 0.4544, + "step": 11619 + }, + { + "epoch": 0.97, + "learning_rate": 4.044466847177519e-08, + "loss": 0.4416, + "step": 11620 + }, + { + "epoch": 0.97, + "learning_rate": 4.0201555954818563e-08, + "loss": 0.4559, + "step": 11621 + }, + { + "epoch": 0.97, + "learning_rate": 3.9959174844032e-08, + "loss": 0.4686, + "step": 11622 + }, + { + "epoch": 0.97, + "learning_rate": 3.971752515721794e-08, + "loss": 0.4665, + "step": 11623 + }, + { + "epoch": 0.97, + "learning_rate": 3.9476606912121073e-08, + "loss": 0.4777, + "step": 11624 + }, + { + "epoch": 0.97, + "learning_rate": 3.9236420126432806e-08, + "loss": 0.469, + "step": 11625 + }, + { + "epoch": 0.97, + "learning_rate": 3.899696481779236e-08, + "loss": 0.4729, + "step": 11626 + }, + { + "epoch": 0.97, + "learning_rate": 3.8758241003782336e-08, + "loss": 0.4659, + "step": 11627 + }, + { + "epoch": 0.97, + "learning_rate": 3.852024870193649e-08, + "loss": 0.4463, + "step": 11628 + }, + { + "epoch": 0.97, + "learning_rate": 3.8282987929730844e-08, + "loss": 0.4729, + "step": 11629 + }, + { + "epoch": 0.97, + "learning_rate": 3.804645870458812e-08, + "loss": 0.4636, + "step": 11630 + }, + { + "epoch": 0.97, + "learning_rate": 3.781066104387887e-08, + "loss": 0.4568, + "step": 11631 + }, + { + "epoch": 0.97, + "learning_rate": 3.757559496491925e-08, + "loss": 0.457, + "step": 11632 + }, + { + "epoch": 0.97, + "learning_rate": 3.7341260484969885e-08, + "loss": 0.4333, + "step": 11633 + }, + { + "epoch": 0.97, + "learning_rate": 3.710765762124147e-08, + "loss": 0.4622, + "step": 11634 + }, + { + "epoch": 0.97, + "learning_rate": 3.687478639088804e-08, + "loss": 0.4611, + "step": 11635 + }, + { + "epoch": 0.97, + "learning_rate": 3.6642646811010375e-08, + "loss": 0.4524, + "step": 11636 + }, + { + "epoch": 0.97, + "learning_rate": 3.6411238898655943e-08, + "loss": 0.4486, + "step": 11637 + }, + { + "epoch": 0.97, + "learning_rate": 3.618056267081782e-08, + "loss": 0.4561, + "step": 11638 + }, + { + "epoch": 0.97, + "learning_rate": 3.59506181444369e-08, + "loss": 0.465, + "step": 11639 + }, + { + "epoch": 0.97, + "learning_rate": 3.5721405336398565e-08, + "loss": 0.4843, + "step": 11640 + }, + { + "epoch": 0.97, + "learning_rate": 3.5492924263537124e-08, + "loss": 0.458, + "step": 11641 + }, + { + "epoch": 0.97, + "learning_rate": 3.526517494262804e-08, + "loss": 0.4535, + "step": 11642 + }, + { + "epoch": 0.97, + "learning_rate": 3.5038157390399067e-08, + "loss": 0.4647, + "step": 11643 + }, + { + "epoch": 0.97, + "learning_rate": 3.481187162352018e-08, + "loss": 0.4704, + "step": 11644 + }, + { + "epoch": 0.97, + "learning_rate": 3.4586317658609205e-08, + "loss": 0.4537, + "step": 11645 + }, + { + "epoch": 0.97, + "learning_rate": 3.436149551223067e-08, + "loss": 0.4813, + "step": 11646 + }, + { + "epoch": 0.97, + "learning_rate": 3.413740520089248e-08, + "loss": 0.4698, + "step": 11647 + }, + { + "epoch": 0.97, + "learning_rate": 3.3914046741052585e-08, + "loss": 0.4612, + "step": 11648 + }, + { + "epoch": 0.97, + "learning_rate": 3.369142014911231e-08, + "loss": 0.4437, + "step": 11649 + }, + { + "epoch": 0.97, + "learning_rate": 3.34695254414219e-08, + "loss": 0.4877, + "step": 11650 + }, + { + "epoch": 0.97, + "learning_rate": 3.3248362634275e-08, + "loss": 0.4612, + "step": 11651 + }, + { + "epoch": 0.97, + "learning_rate": 3.302793174391417e-08, + "loss": 0.4605, + "step": 11652 + }, + { + "epoch": 0.97, + "learning_rate": 3.280823278652645e-08, + "loss": 0.466, + "step": 11653 + }, + { + "epoch": 0.98, + "learning_rate": 3.2589265778244505e-08, + "loss": 0.4523, + "step": 11654 + }, + { + "epoch": 0.98, + "learning_rate": 3.237103073514991e-08, + "loss": 0.4371, + "step": 11655 + }, + { + "epoch": 0.98, + "learning_rate": 3.215352767326873e-08, + "loss": 0.4783, + "step": 11656 + }, + { + "epoch": 0.98, + "learning_rate": 3.193675660857265e-08, + "loss": 0.4543, + "step": 11657 + }, + { + "epoch": 0.98, + "learning_rate": 3.172071755698114e-08, + "loss": 0.471, + "step": 11658 + }, + { + "epoch": 0.98, + "learning_rate": 3.150541053435818e-08, + "loss": 0.4686, + "step": 11659 + }, + { + "epoch": 0.98, + "learning_rate": 3.129083555651668e-08, + "loss": 0.4683, + "step": 11660 + }, + { + "epoch": 0.98, + "learning_rate": 3.1076992639211824e-08, + "loss": 0.452, + "step": 11661 + }, + { + "epoch": 0.98, + "learning_rate": 3.086388179814992e-08, + "loss": 0.4614, + "step": 11662 + }, + { + "epoch": 0.98, + "learning_rate": 3.065150304897957e-08, + "loss": 0.469, + "step": 11663 + }, + { + "epoch": 0.98, + "learning_rate": 3.043985640729718e-08, + "loss": 0.4555, + "step": 11664 + }, + { + "epoch": 0.98, + "learning_rate": 3.022894188864589e-08, + "loss": 0.4715, + "step": 11665 + }, + { + "epoch": 0.98, + "learning_rate": 3.0018759508513297e-08, + "loss": 0.4541, + "step": 11666 + }, + { + "epoch": 0.98, + "learning_rate": 2.980930928233372e-08, + "loss": 0.4638, + "step": 11667 + }, + { + "epoch": 0.98, + "learning_rate": 2.9600591225490415e-08, + "loss": 0.4959, + "step": 11668 + }, + { + "epoch": 0.98, + "learning_rate": 2.93926053533089e-08, + "loss": 0.4738, + "step": 11669 + }, + { + "epoch": 0.98, + "learning_rate": 2.918535168106473e-08, + "loss": 0.4592, + "step": 11670 + }, + { + "epoch": 0.98, + "learning_rate": 2.897883022397574e-08, + "loss": 0.468, + "step": 11671 + }, + { + "epoch": 0.98, + "learning_rate": 2.8773040997208678e-08, + "loss": 0.4645, + "step": 11672 + }, + { + "epoch": 0.98, + "learning_rate": 2.8567984015877014e-08, + "loss": 0.4617, + "step": 11673 + }, + { + "epoch": 0.98, + "learning_rate": 2.8363659295037592e-08, + "loss": 0.4605, + "step": 11674 + }, + { + "epoch": 0.98, + "learning_rate": 2.8160066849696187e-08, + "loss": 0.4509, + "step": 11675 + }, + { + "epoch": 0.98, + "learning_rate": 2.7957206694803064e-08, + "loss": 0.4641, + "step": 11676 + }, + { + "epoch": 0.98, + "learning_rate": 2.77550788452563e-08, + "loss": 0.4295, + "step": 11677 + }, + { + "epoch": 0.98, + "learning_rate": 2.755368331589847e-08, + "loss": 0.4568, + "step": 11678 + }, + { + "epoch": 0.98, + "learning_rate": 2.7353020121518857e-08, + "loss": 0.4661, + "step": 11679 + }, + { + "epoch": 0.98, + "learning_rate": 2.715308927685567e-08, + "loss": 0.4596, + "step": 11680 + }, + { + "epoch": 0.98, + "learning_rate": 2.6953890796588276e-08, + "loss": 0.4582, + "step": 11681 + }, + { + "epoch": 0.98, + "learning_rate": 2.67554246953472e-08, + "loss": 0.4804, + "step": 11682 + }, + { + "epoch": 0.98, + "learning_rate": 2.655769098770522e-08, + "loss": 0.439, + "step": 11683 + }, + { + "epoch": 0.98, + "learning_rate": 2.636068968818295e-08, + "loss": 0.4728, + "step": 11684 + }, + { + "epoch": 0.98, + "learning_rate": 2.6164420811249925e-08, + "loss": 0.465, + "step": 11685 + }, + { + "epoch": 0.98, + "learning_rate": 2.5968884371315728e-08, + "loss": 0.4494, + "step": 11686 + }, + { + "epoch": 0.98, + "learning_rate": 2.5774080382743317e-08, + "loss": 0.4401, + "step": 11687 + }, + { + "epoch": 0.98, + "learning_rate": 2.5580008859835692e-08, + "loss": 0.4924, + "step": 11688 + }, + { + "epoch": 0.98, + "learning_rate": 2.538666981684479e-08, + "loss": 0.4549, + "step": 11689 + }, + { + "epoch": 0.98, + "learning_rate": 2.5194063267970358e-08, + "loss": 0.4631, + "step": 11690 + }, + { + "epoch": 0.98, + "learning_rate": 2.5002189227354425e-08, + "loss": 0.4868, + "step": 11691 + }, + { + "epoch": 0.98, + "learning_rate": 2.481104770908904e-08, + "loss": 0.4634, + "step": 11692 + }, + { + "epoch": 0.98, + "learning_rate": 2.4620638727210766e-08, + "loss": 0.4397, + "step": 11693 + }, + { + "epoch": 0.98, + "learning_rate": 2.4430962295701743e-08, + "loss": 0.4728, + "step": 11694 + }, + { + "epoch": 0.98, + "learning_rate": 2.4242018428491944e-08, + "loss": 0.4633, + "step": 11695 + }, + { + "epoch": 0.98, + "learning_rate": 2.405380713945582e-08, + "loss": 0.4515, + "step": 11696 + }, + { + "epoch": 0.98, + "learning_rate": 2.3866328442414545e-08, + "loss": 0.4745, + "step": 11697 + }, + { + "epoch": 0.98, + "learning_rate": 2.3679582351137098e-08, + "loss": 0.4766, + "step": 11698 + }, + { + "epoch": 0.98, + "learning_rate": 2.349356887933585e-08, + "loss": 0.4631, + "step": 11699 + }, + { + "epoch": 0.98, + "learning_rate": 2.330828804067098e-08, + "loss": 0.4695, + "step": 11700 + }, + { + "epoch": 0.98, + "learning_rate": 2.3123739848749382e-08, + "loss": 0.4665, + "step": 11701 + }, + { + "epoch": 0.98, + "learning_rate": 2.2939924317124663e-08, + "loss": 0.46, + "step": 11702 + }, + { + "epoch": 0.98, + "learning_rate": 2.275684145929269e-08, + "loss": 0.4722, + "step": 11703 + }, + { + "epoch": 0.98, + "learning_rate": 2.2574491288700485e-08, + "loss": 0.4655, + "step": 11704 + }, + { + "epoch": 0.98, + "learning_rate": 2.2392873818738447e-08, + "loss": 0.4503, + "step": 11705 + }, + { + "epoch": 0.98, + "learning_rate": 2.2211989062743688e-08, + "loss": 0.4614, + "step": 11706 + }, + { + "epoch": 0.98, + "learning_rate": 2.2031837034000024e-08, + "loss": 0.4405, + "step": 11707 + }, + { + "epoch": 0.98, + "learning_rate": 2.1852417745735764e-08, + "loss": 0.4648, + "step": 11708 + }, + { + "epoch": 0.98, + "learning_rate": 2.1673731211129255e-08, + "loss": 0.4791, + "step": 11709 + }, + { + "epoch": 0.98, + "learning_rate": 2.1495777443300005e-08, + "loss": 0.467, + "step": 11710 + }, + { + "epoch": 0.98, + "learning_rate": 2.131855645531644e-08, + "loss": 0.4428, + "step": 11711 + }, + { + "epoch": 0.98, + "learning_rate": 2.1142068260194827e-08, + "loss": 0.4568, + "step": 11712 + }, + { + "epoch": 0.98, + "learning_rate": 2.0966312870893678e-08, + "loss": 0.4525, + "step": 11713 + }, + { + "epoch": 0.98, + "learning_rate": 2.0791290300321564e-08, + "loss": 0.4744, + "step": 11714 + }, + { + "epoch": 0.98, + "learning_rate": 2.0617000561329315e-08, + "loss": 0.4685, + "step": 11715 + }, + { + "epoch": 0.98, + "learning_rate": 2.04434436667178e-08, + "loss": 0.4811, + "step": 11716 + }, + { + "epoch": 0.98, + "learning_rate": 2.027061962923127e-08, + "loss": 0.4609, + "step": 11717 + }, + { + "epoch": 0.98, + "learning_rate": 2.0098528461562906e-08, + "loss": 0.4709, + "step": 11718 + }, + { + "epoch": 0.98, + "learning_rate": 1.9927170176348155e-08, + "loss": 0.4597, + "step": 11719 + }, + { + "epoch": 0.98, + "learning_rate": 1.9756544786171393e-08, + "loss": 0.4651, + "step": 11720 + }, + { + "epoch": 0.98, + "learning_rate": 1.9586652303562603e-08, + "loss": 0.4463, + "step": 11721 + }, + { + "epoch": 0.98, + "learning_rate": 1.941749274099958e-08, + "loss": 0.4751, + "step": 11722 + }, + { + "epoch": 0.98, + "learning_rate": 1.924906611090349e-08, + "loss": 0.4505, + "step": 11723 + }, + { + "epoch": 0.98, + "learning_rate": 1.9081372425642232e-08, + "loss": 0.4564, + "step": 11724 + }, + { + "epoch": 0.98, + "learning_rate": 1.8914411697531498e-08, + "loss": 0.4579, + "step": 11725 + }, + { + "epoch": 0.98, + "learning_rate": 1.8748183938832597e-08, + "loss": 0.4747, + "step": 11726 + }, + { + "epoch": 0.98, + "learning_rate": 1.8582689161751323e-08, + "loss": 0.4637, + "step": 11727 + }, + { + "epoch": 0.98, + "learning_rate": 1.841792737844128e-08, + "loss": 0.4701, + "step": 11728 + }, + { + "epoch": 0.98, + "learning_rate": 1.8253898601002794e-08, + "loss": 0.4685, + "step": 11729 + }, + { + "epoch": 0.98, + "learning_rate": 1.8090602841479566e-08, + "loss": 0.4487, + "step": 11730 + }, + { + "epoch": 0.98, + "learning_rate": 1.792804011186533e-08, + "loss": 0.4494, + "step": 11731 + }, + { + "epoch": 0.98, + "learning_rate": 1.7766210424097207e-08, + "loss": 0.4415, + "step": 11732 + }, + { + "epoch": 0.98, + "learning_rate": 1.7605113790059024e-08, + "loss": 0.4635, + "step": 11733 + }, + { + "epoch": 0.98, + "learning_rate": 1.744475022158243e-08, + "loss": 0.459, + "step": 11734 + }, + { + "epoch": 0.98, + "learning_rate": 1.7285119730442446e-08, + "loss": 0.4558, + "step": 11735 + }, + { + "epoch": 0.98, + "learning_rate": 1.712622232836192e-08, + "loss": 0.4716, + "step": 11736 + }, + { + "epoch": 0.98, + "learning_rate": 1.6968058027009292e-08, + "loss": 0.4586, + "step": 11737 + }, + { + "epoch": 0.98, + "learning_rate": 1.6810626837999722e-08, + "loss": 0.4835, + "step": 11738 + }, + { + "epoch": 0.98, + "learning_rate": 1.6653928772895067e-08, + "loss": 0.4461, + "step": 11739 + }, + { + "epoch": 0.98, + "learning_rate": 1.649796384320168e-08, + "loss": 0.4419, + "step": 11740 + }, + { + "epoch": 0.98, + "learning_rate": 1.6342732060373733e-08, + "loss": 0.4625, + "step": 11741 + }, + { + "epoch": 0.98, + "learning_rate": 1.6188233435809887e-08, + "loss": 0.4593, + "step": 11742 + }, + { + "epoch": 0.98, + "learning_rate": 1.6034467980857727e-08, + "loss": 0.4429, + "step": 11743 + }, + { + "epoch": 0.98, + "learning_rate": 1.5881435706806002e-08, + "loss": 0.4512, + "step": 11744 + }, + { + "epoch": 0.98, + "learning_rate": 1.5729136624895723e-08, + "loss": 0.4645, + "step": 11745 + }, + { + "epoch": 0.98, + "learning_rate": 1.5577570746309057e-08, + "loss": 0.4584, + "step": 11746 + }, + { + "epoch": 0.98, + "learning_rate": 1.5426738082178206e-08, + "loss": 0.4629, + "step": 11747 + }, + { + "epoch": 0.98, + "learning_rate": 1.5276638643578756e-08, + "loss": 0.4594, + "step": 11748 + }, + { + "epoch": 0.98, + "learning_rate": 1.5127272441533004e-08, + "loss": 0.4414, + "step": 11749 + }, + { + "epoch": 0.98, + "learning_rate": 1.497863948700995e-08, + "loss": 0.4754, + "step": 11750 + }, + { + "epoch": 0.98, + "learning_rate": 1.4830739790925308e-08, + "loss": 0.4389, + "step": 11751 + }, + { + "epoch": 0.98, + "learning_rate": 1.4683573364138171e-08, + "loss": 0.4845, + "step": 11752 + }, + { + "epoch": 0.98, + "learning_rate": 1.4537140217458778e-08, + "loss": 0.4612, + "step": 11753 + }, + { + "epoch": 0.98, + "learning_rate": 1.439144036163964e-08, + "loss": 0.4562, + "step": 11754 + }, + { + "epoch": 0.98, + "learning_rate": 1.4246473807378869e-08, + "loss": 0.4516, + "step": 11755 + }, + { + "epoch": 0.98, + "learning_rate": 1.41022405653235e-08, + "loss": 0.4753, + "step": 11756 + }, + { + "epoch": 0.98, + "learning_rate": 1.395874064606506e-08, + "loss": 0.4545, + "step": 11757 + }, + { + "epoch": 0.98, + "learning_rate": 1.381597406014179e-08, + "loss": 0.4614, + "step": 11758 + }, + { + "epoch": 0.98, + "learning_rate": 1.3673940818037523e-08, + "loss": 0.4941, + "step": 11759 + }, + { + "epoch": 0.98, + "learning_rate": 1.3532640930182806e-08, + "loss": 0.4754, + "step": 11760 + }, + { + "epoch": 0.98, + "learning_rate": 1.339207440695378e-08, + "loss": 0.4795, + "step": 11761 + }, + { + "epoch": 0.98, + "learning_rate": 1.3252241258673305e-08, + "loss": 0.4604, + "step": 11762 + }, + { + "epoch": 0.98, + "learning_rate": 1.3113141495610937e-08, + "loss": 0.4656, + "step": 11763 + }, + { + "epoch": 0.98, + "learning_rate": 1.2974775127980732e-08, + "loss": 0.4797, + "step": 11764 + }, + { + "epoch": 0.98, + "learning_rate": 1.283714216594345e-08, + "loss": 0.4449, + "step": 11765 + }, + { + "epoch": 0.98, + "learning_rate": 1.2700242619606562e-08, + "loss": 0.4625, + "step": 11766 + }, + { + "epoch": 0.98, + "learning_rate": 1.2564076499024247e-08, + "loss": 0.4635, + "step": 11767 + }, + { + "epoch": 0.98, + "learning_rate": 1.2428643814195174e-08, + "loss": 0.4668, + "step": 11768 + }, + { + "epoch": 0.98, + "learning_rate": 1.229394457506472e-08, + "loss": 0.4709, + "step": 11769 + }, + { + "epoch": 0.98, + "learning_rate": 1.2159978791524973e-08, + "loss": 0.4454, + "step": 11770 + }, + { + "epoch": 0.98, + "learning_rate": 1.202674647341362e-08, + "loss": 0.474, + "step": 11771 + }, + { + "epoch": 0.98, + "learning_rate": 1.1894247630516165e-08, + "loss": 0.4544, + "step": 11772 + }, + { + "epoch": 0.98, + "learning_rate": 1.1762482272560382e-08, + "loss": 0.4765, + "step": 11773 + }, + { + "epoch": 0.99, + "learning_rate": 1.1631450409224088e-08, + "loss": 0.4647, + "step": 11774 + }, + { + "epoch": 0.99, + "learning_rate": 1.1501152050128472e-08, + "loss": 0.4871, + "step": 11775 + }, + { + "epoch": 0.99, + "learning_rate": 1.1371587204843659e-08, + "loss": 0.4494, + "step": 11776 + }, + { + "epoch": 0.99, + "learning_rate": 1.124275588288426e-08, + "loss": 0.4947, + "step": 11777 + }, + { + "epoch": 0.99, + "learning_rate": 1.1114658093709373e-08, + "loss": 0.4682, + "step": 11778 + }, + { + "epoch": 0.99, + "learning_rate": 1.0987293846728141e-08, + "loss": 0.4486, + "step": 11779 + }, + { + "epoch": 0.99, + "learning_rate": 1.0860663151291973e-08, + "loss": 0.4312, + "step": 11780 + }, + { + "epoch": 0.99, + "learning_rate": 1.0734766016700093e-08, + "loss": 0.4613, + "step": 11781 + }, + { + "epoch": 0.99, + "learning_rate": 1.0609602452199553e-08, + "loss": 0.4764, + "step": 11782 + }, + { + "epoch": 0.99, + "learning_rate": 1.0485172466980776e-08, + "loss": 0.4795, + "step": 11783 + }, + { + "epoch": 0.99, + "learning_rate": 1.0361476070180899e-08, + "loss": 0.4585, + "step": 11784 + }, + { + "epoch": 0.99, + "learning_rate": 1.0238513270884876e-08, + "loss": 0.459, + "step": 11785 + }, + { + "epoch": 0.99, + "learning_rate": 1.0116284078121042e-08, + "loss": 0.4561, + "step": 11786 + }, + { + "epoch": 0.99, + "learning_rate": 9.994788500866659e-09, + "loss": 0.4608, + "step": 11787 + }, + { + "epoch": 0.99, + "learning_rate": 9.87402654804348e-09, + "loss": 0.4812, + "step": 11788 + }, + { + "epoch": 0.99, + "learning_rate": 9.753998228519967e-09, + "loss": 0.4629, + "step": 11789 + }, + { + "epoch": 0.99, + "learning_rate": 9.634703551110181e-09, + "loss": 0.4569, + "step": 11790 + }, + { + "epoch": 0.99, + "learning_rate": 9.516142524574889e-09, + "loss": 0.4736, + "step": 11791 + }, + { + "epoch": 0.99, + "learning_rate": 9.398315157619354e-09, + "loss": 0.4595, + "step": 11792 + }, + { + "epoch": 0.99, + "learning_rate": 9.281221458898871e-09, + "loss": 0.456, + "step": 11793 + }, + { + "epoch": 0.99, + "learning_rate": 9.164861437009897e-09, + "loss": 0.4692, + "step": 11794 + }, + { + "epoch": 0.99, + "learning_rate": 9.049235100500042e-09, + "loss": 0.4546, + "step": 11795 + }, + { + "epoch": 0.99, + "learning_rate": 8.93434245785696e-09, + "loss": 0.4422, + "step": 11796 + }, + { + "epoch": 0.99, + "learning_rate": 8.820183517521675e-09, + "loss": 0.4557, + "step": 11797 + }, + { + "epoch": 0.99, + "learning_rate": 8.706758287874151e-09, + "loss": 0.4557, + "step": 11798 + }, + { + "epoch": 0.99, + "learning_rate": 8.594066777246613e-09, + "loss": 0.4656, + "step": 11799 + }, + { + "epoch": 0.99, + "learning_rate": 8.482108993912441e-09, + "loss": 0.501, + "step": 11800 + }, + { + "epoch": 0.99, + "learning_rate": 8.370884946095059e-09, + "loss": 0.4627, + "step": 11801 + }, + { + "epoch": 0.99, + "learning_rate": 8.260394641961267e-09, + "loss": 0.4597, + "step": 11802 + }, + { + "epoch": 0.99, + "learning_rate": 8.150638089624574e-09, + "loss": 0.4844, + "step": 11803 + }, + { + "epoch": 0.99, + "learning_rate": 8.04161529714631e-09, + "loss": 0.4403, + "step": 11804 + }, + { + "epoch": 0.99, + "learning_rate": 7.933326272532294e-09, + "loss": 0.4704, + "step": 11805 + }, + { + "epoch": 0.99, + "learning_rate": 7.825771023735051e-09, + "loss": 0.4568, + "step": 11806 + }, + { + "epoch": 0.99, + "learning_rate": 7.7189495586516e-09, + "loss": 0.4704, + "step": 11807 + }, + { + "epoch": 0.99, + "learning_rate": 7.612861885128997e-09, + "loss": 0.4585, + "step": 11808 + }, + { + "epoch": 0.99, + "learning_rate": 7.507508010955455e-09, + "loss": 0.4507, + "step": 11809 + }, + { + "epoch": 0.99, + "learning_rate": 7.40288794386812e-09, + "loss": 0.4675, + "step": 11810 + }, + { + "epoch": 0.99, + "learning_rate": 7.299001691550844e-09, + "loss": 0.4525, + "step": 11811 + }, + { + "epoch": 0.99, + "learning_rate": 7.195849261631971e-09, + "loss": 0.4645, + "step": 11812 + }, + { + "epoch": 0.99, + "learning_rate": 7.093430661686551e-09, + "loss": 0.4757, + "step": 11813 + }, + { + "epoch": 0.99, + "learning_rate": 6.991745899236346e-09, + "loss": 0.4585, + "step": 11814 + }, + { + "epoch": 0.99, + "learning_rate": 6.890794981748717e-09, + "loss": 0.4569, + "step": 11815 + }, + { + "epoch": 0.99, + "learning_rate": 6.79057791663551e-09, + "loss": 0.4858, + "step": 11816 + }, + { + "epoch": 0.99, + "learning_rate": 6.691094711258617e-09, + "loss": 0.4416, + "step": 11817 + }, + { + "epoch": 0.99, + "learning_rate": 6.5923453729221935e-09, + "loss": 0.4474, + "step": 11818 + }, + { + "epoch": 0.99, + "learning_rate": 6.4943299088771065e-09, + "loss": 0.4492, + "step": 11819 + }, + { + "epoch": 0.99, + "learning_rate": 6.397048326323152e-09, + "loss": 0.4803, + "step": 11820 + }, + { + "epoch": 0.99, + "learning_rate": 6.300500632403505e-09, + "loss": 0.458, + "step": 11821 + }, + { + "epoch": 0.99, + "learning_rate": 6.204686834208051e-09, + "loss": 0.4613, + "step": 11822 + }, + { + "epoch": 0.99, + "learning_rate": 6.1096069387733825e-09, + "loss": 0.4649, + "step": 11823 + }, + { + "epoch": 0.99, + "learning_rate": 6.015260953080582e-09, + "loss": 0.4637, + "step": 11824 + }, + { + "epoch": 0.99, + "learning_rate": 5.921648884059661e-09, + "loss": 0.4679, + "step": 11825 + }, + { + "epoch": 0.99, + "learning_rate": 5.828770738584011e-09, + "loss": 0.4586, + "step": 11826 + }, + { + "epoch": 0.99, + "learning_rate": 5.736626523474842e-09, + "loss": 0.4494, + "step": 11827 + }, + { + "epoch": 0.99, + "learning_rate": 5.645216245497853e-09, + "loss": 0.446, + "step": 11828 + }, + { + "epoch": 0.99, + "learning_rate": 5.554539911367673e-09, + "loss": 0.4763, + "step": 11829 + }, + { + "epoch": 0.99, + "learning_rate": 5.4645975277412004e-09, + "loss": 0.4616, + "step": 11830 + }, + { + "epoch": 0.99, + "learning_rate": 5.37538910122426e-09, + "loss": 0.4542, + "step": 11831 + }, + { + "epoch": 0.99, + "learning_rate": 5.2869146383682794e-09, + "loss": 0.4753, + "step": 11832 + }, + { + "epoch": 0.99, + "learning_rate": 5.199174145670283e-09, + "loss": 0.488, + "step": 11833 + }, + { + "epoch": 0.99, + "learning_rate": 5.112167629572895e-09, + "loss": 0.4638, + "step": 11834 + }, + { + "epoch": 0.99, + "learning_rate": 5.02589509646656e-09, + "loss": 0.479, + "step": 11835 + }, + { + "epoch": 0.99, + "learning_rate": 4.94035655268621e-09, + "loss": 0.4608, + "step": 11836 + }, + { + "epoch": 0.99, + "learning_rate": 4.855552004513486e-09, + "loss": 0.4786, + "step": 11837 + }, + { + "epoch": 0.99, + "learning_rate": 4.7714814581756305e-09, + "loss": 0.4579, + "step": 11838 + }, + { + "epoch": 0.99, + "learning_rate": 4.6881449198477035e-09, + "loss": 0.4622, + "step": 11839 + }, + { + "epoch": 0.99, + "learning_rate": 4.605542395648144e-09, + "loss": 0.4534, + "step": 11840 + }, + { + "epoch": 0.99, + "learning_rate": 4.52367389164432e-09, + "loss": 0.469, + "step": 11841 + }, + { + "epoch": 0.99, + "learning_rate": 4.44253941384698e-09, + "loss": 0.4853, + "step": 11842 + }, + { + "epoch": 0.99, + "learning_rate": 4.362138968214691e-09, + "loss": 0.4447, + "step": 11843 + }, + { + "epoch": 0.99, + "learning_rate": 4.282472560651618e-09, + "loss": 0.4573, + "step": 11844 + }, + { + "epoch": 0.99, + "learning_rate": 4.203540197009748e-09, + "loss": 0.461, + "step": 11845 + }, + { + "epoch": 0.99, + "learning_rate": 4.125341883083334e-09, + "loss": 0.4492, + "step": 11846 + }, + { + "epoch": 0.99, + "learning_rate": 4.047877624615559e-09, + "loss": 0.4663, + "step": 11847 + }, + { + "epoch": 0.99, + "learning_rate": 3.971147427296318e-09, + "loss": 0.455, + "step": 11848 + }, + { + "epoch": 0.99, + "learning_rate": 3.895151296758881e-09, + "loss": 0.4424, + "step": 11849 + }, + { + "epoch": 0.99, + "learning_rate": 3.81988923858434e-09, + "loss": 0.4672, + "step": 11850 + }, + { + "epoch": 0.99, + "learning_rate": 3.745361258300495e-09, + "loss": 0.4656, + "step": 11851 + }, + { + "epoch": 0.99, + "learning_rate": 3.6715673613796353e-09, + "loss": 0.4624, + "step": 11852 + }, + { + "epoch": 0.99, + "learning_rate": 3.59850755324076e-09, + "loss": 0.4421, + "step": 11853 + }, + { + "epoch": 0.99, + "learning_rate": 3.5261818392484657e-09, + "loss": 0.4816, + "step": 11854 + }, + { + "epoch": 0.99, + "learning_rate": 3.454590224716281e-09, + "loss": 0.4464, + "step": 11855 + }, + { + "epoch": 0.99, + "learning_rate": 3.383732714900001e-09, + "loss": 0.45, + "step": 11856 + }, + { + "epoch": 0.99, + "learning_rate": 3.313609315003241e-09, + "loss": 0.4448, + "step": 11857 + }, + { + "epoch": 0.99, + "learning_rate": 3.244220030175216e-09, + "loss": 0.4695, + "step": 11858 + }, + { + "epoch": 0.99, + "learning_rate": 3.175564865512959e-09, + "loss": 0.4581, + "step": 11859 + }, + { + "epoch": 0.99, + "learning_rate": 3.107643826055773e-09, + "loss": 0.4873, + "step": 11860 + }, + { + "epoch": 0.99, + "learning_rate": 3.04045691679411e-09, + "loss": 0.4794, + "step": 11861 + }, + { + "epoch": 0.99, + "learning_rate": 2.9740041426606915e-09, + "loss": 0.4446, + "step": 11862 + }, + { + "epoch": 0.99, + "learning_rate": 2.908285508536057e-09, + "loss": 0.4744, + "step": 11863 + }, + { + "epoch": 0.99, + "learning_rate": 2.843301019245237e-09, + "loss": 0.442, + "step": 11864 + }, + { + "epoch": 0.99, + "learning_rate": 2.7790506795610793e-09, + "loss": 0.46, + "step": 11865 + }, + { + "epoch": 0.99, + "learning_rate": 2.7155344942020324e-09, + "loss": 0.4449, + "step": 11866 + }, + { + "epoch": 0.99, + "learning_rate": 2.6527524678321424e-09, + "loss": 0.4606, + "step": 11867 + }, + { + "epoch": 0.99, + "learning_rate": 2.5907046050632767e-09, + "loss": 0.4512, + "step": 11868 + }, + { + "epoch": 0.99, + "learning_rate": 2.5293909104495696e-09, + "loss": 0.467, + "step": 11869 + }, + { + "epoch": 0.99, + "learning_rate": 2.4688113884940855e-09, + "loss": 0.4508, + "step": 11870 + }, + { + "epoch": 0.99, + "learning_rate": 2.4089660436477093e-09, + "loss": 0.4537, + "step": 11871 + }, + { + "epoch": 0.99, + "learning_rate": 2.3498548803024825e-09, + "loss": 0.4676, + "step": 11872 + }, + { + "epoch": 0.99, + "learning_rate": 2.2914779028015976e-09, + "loss": 0.472, + "step": 11873 + }, + { + "epoch": 0.99, + "learning_rate": 2.233835115430516e-09, + "loss": 0.4748, + "step": 11874 + }, + { + "epoch": 0.99, + "learning_rate": 2.1769265224225176e-09, + "loss": 0.4612, + "step": 11875 + }, + { + "epoch": 0.99, + "learning_rate": 2.1207521279575925e-09, + "loss": 0.4694, + "step": 11876 + }, + { + "epoch": 0.99, + "learning_rate": 2.065311936160219e-09, + "loss": 0.4486, + "step": 11877 + }, + { + "epoch": 0.99, + "learning_rate": 2.0106059511015853e-09, + "loss": 0.4707, + "step": 11878 + }, + { + "epoch": 0.99, + "learning_rate": 1.9566341767984774e-09, + "loss": 0.4409, + "step": 11879 + }, + { + "epoch": 0.99, + "learning_rate": 1.903396617216613e-09, + "loss": 0.4728, + "step": 11880 + }, + { + "epoch": 0.99, + "learning_rate": 1.8508932762628662e-09, + "loss": 0.4348, + "step": 11881 + }, + { + "epoch": 0.99, + "learning_rate": 1.7991241577952624e-09, + "loss": 0.4634, + "step": 11882 + }, + { + "epoch": 0.99, + "learning_rate": 1.7480892656129845e-09, + "loss": 0.4532, + "step": 11883 + }, + { + "epoch": 0.99, + "learning_rate": 1.697788603466366e-09, + "loss": 0.4515, + "step": 11884 + }, + { + "epoch": 0.99, + "learning_rate": 1.6482221750468984e-09, + "loss": 0.4701, + "step": 11885 + }, + { + "epoch": 0.99, + "learning_rate": 1.5993899839972239e-09, + "loss": 0.4458, + "step": 11886 + }, + { + "epoch": 0.99, + "learning_rate": 1.5512920339011416e-09, + "loss": 0.4809, + "step": 11887 + }, + { + "epoch": 0.99, + "learning_rate": 1.503928328291382e-09, + "loss": 0.4552, + "step": 11888 + }, + { + "epoch": 0.99, + "learning_rate": 1.4572988706462732e-09, + "loss": 0.4768, + "step": 11889 + }, + { + "epoch": 0.99, + "learning_rate": 1.4114036643897434e-09, + "loss": 0.4614, + "step": 11890 + }, + { + "epoch": 0.99, + "learning_rate": 1.3662427128924294e-09, + "loss": 0.4842, + "step": 11891 + }, + { + "epoch": 0.99, + "learning_rate": 1.3218160194716778e-09, + "loss": 0.4597, + "step": 11892 + }, + { + "epoch": 1.0, + "learning_rate": 1.2781235873882136e-09, + "loss": 0.456, + "step": 11893 + }, + { + "epoch": 1.0, + "learning_rate": 1.2351654198528018e-09, + "loss": 0.4666, + "step": 11894 + }, + { + "epoch": 1.0, + "learning_rate": 1.1929415200173656e-09, + "loss": 0.4657, + "step": 11895 + }, + { + "epoch": 1.0, + "learning_rate": 1.151451890984978e-09, + "loss": 0.4713, + "step": 11896 + }, + { + "epoch": 1.0, + "learning_rate": 1.1106965358009814e-09, + "loss": 0.4443, + "step": 11897 + }, + { + "epoch": 1.0, + "learning_rate": 1.0706754574596468e-09, + "loss": 0.4491, + "step": 11898 + }, + { + "epoch": 1.0, + "learning_rate": 1.0313886588986244e-09, + "loss": 0.4913, + "step": 11899 + }, + { + "epoch": 1.0, + "learning_rate": 9.928361430044941e-10, + "loss": 0.4457, + "step": 11900 + } + ], + "logging_steps": 1.0, + "max_steps": 11952, + "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-11900/vision_tower/config.json b/checkpoint-11900/vision_tower/config.json new file mode 100644 index 0000000000000000000000000000000000000000..5515c0578f6ddf3e45d1ab677176774db6634110 --- /dev/null +++ b/checkpoint-11900/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/tmp-checkpoint-11900/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-11900/vision_tower/model.safetensors b/checkpoint-11900/vision_tower/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5003e60dc5514579789356bf50818e2121ae56f2 --- /dev/null +++ b/checkpoint-11900/vision_tower/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c602abf3ee39781f02b41100da0213fe0a5ffb7ec869b4dc0fed316e80a76cd0 +size 856506120 diff --git a/checkpoint-11900/vision_tower/preprocessor_config.json b/checkpoint-11900/vision_tower/preprocessor_config.json new file mode 100644 index 0000000000000000000000000000000000000000..0f13134ed29056f82f3ab7e0246f0ab973e7ecf3 --- /dev/null +++ b/checkpoint-11900/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-11900/zero_to_fp32.py b/checkpoint-11900/zero_to_fp32.py new file mode 100644 index 0000000000000000000000000000000000000000..c5246ff52274e1d6142001ccf085186d3545ce57 --- /dev/null +++ b/checkpoint-11900/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..9325453c3515dd581031b1b6ac79fba4653ed69f --- /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", + "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/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/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", + "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/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..d385ac57663b58ba80dee4a8e8d3456f55c26c42 --- /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/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..27ddd467f481d9b88710818436c2ca8991140415 --- /dev/null +++ b/llm/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d34abe1d76878de8223dc920a1aca528f03f5a076ab0edc3ef96c0c829471830 +size 4974521464 diff --git a/llm/model-00002-of-00002.safetensors b/llm/model-00002-of-00002.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3c4a05d6ad9eb29af550cee87fcca1544dcf9e6f --- /dev/null +++ b/llm/model-00002-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81eb8fea09f4c1d6e0939133165c20adbacc5197dc1976727ae0b3f885a676e6 +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..6e9f215d95de28f15f2da1944cc55b182b6a1245 --- /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/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..541e3a678ce410e1d69a7a15f9f3a3373593b476 --- /dev/null +++ b/mm_projector/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5fddbf1c11889bed72ebb19ba6ba0330a1394730b705dedb127118d77a84d2e +size 36729360 diff --git a/terminal.log b/terminal.log new file mode 100644 index 0000000000000000000000000000000000000000..5e993eec273768277b123c8c33b011dfea325289 --- /dev/null +++ b/terminal.log @@ -0,0 +1,16200 @@ +srun: job 8825117 queued and waiting for resources +srun: job 8825117 has been allocated resources +wandb: Currently logged in as: memmelma. Use `wandb login --relogin` to force relogin +MASTER_ADDR=batch-block1-0014 +JobID: 8825117 | Full list: batch-block1-0014 +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! +[2025-06-10 08:33:18,324] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-10 08:33:18,324] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-10 08:33:18,324] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-10 08:33:18,324] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-10 08:33:18,324] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-10 08:33:18,324] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-10 08:33:18,324] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-10 08:33:18,324] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-10 08:33:20,106] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-10 08:33:20,106] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-10 08:33:20,106] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-10 08:33:20,106] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-10 08:33:20,106] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-10 08:33:20,106] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-10 08:33:20,106] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-10 08:33:20,106] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-10 08:33:20,106] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-10 08:33:20,106] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-10 08:33:20,106] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-10 08:33:20,106] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-10 08:33:20,106] [INFO] [comm.py:625:init_distributed] Initializing TorchBackend in DeepSpeed with backend nccl +[2025-06-10 08:33:20,106] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-10 08:33:20,106] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-10 08:33:20,106] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-10 08:33:20,106] [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%|██▊ | 3422/11952 [1:54:32<14:04:32, 5.94s/it] {'loss': 0.4779, 'learning_rate': 1.674843404639537e-05, 'epoch': 0.29} + 29%|██▊ | 3422/11952 [1:54:32<14:04:32, 5.94s/it] 29%|██▊ | 3423/11952 [1:54:37<14:03:05, 5.93s/it] {'loss': 0.509, 'learning_rate': 1.6746433994670258e-05, 'epoch': 0.29} + 29%|██▊ | 3423/11952 [1:54:37<14:03:05, 5.93s/it] 29%|██▊ | 3424/11952 [1:54:43<13:45:36, 5.81s/it] {'loss': 0.4972, 'learning_rate': 1.6744433447515098e-05, 'epoch': 0.29} + 29%|██▊ | 3424/11952 [1:54:43<13:45:36, 5.81s/it] 29%|██▊ | 3425/11952 [1:54:49<13:43:38, 5.80s/it] {'loss': 0.4903, 'learning_rate': 1.67424324050768e-05, 'epoch': 0.29} + 29%|██▊ | 3425/11952 [1:54:49<13:43:38, 5.80s/it] 29%|██▊ | 3426/11952 [1:54:55<13:43:12, 5.79s/it] {'loss': 0.4894, 'learning_rate': 1.6740430867502307e-05, 'epoch': 0.29} + 29%|██▊ | 3426/11952 [1:54:55<13:43:12, 5.79s/it] 29%|██▊ | 3427/11952 [1:55:00<13:42:33, 5.79s/it] {'loss': 0.4954, 'learning_rate': 1.6738428834938606e-05, 'epoch': 0.29} + 29%|██▊ | 3427/11952 [1:55:00<13:42:33, 5.79s/it] 29%|██▊ | 3428/11952 [1:55:07<14:08:07, 5.97s/it] {'loss': 0.4985, 'learning_rate': 1.6736426307532722e-05, 'epoch': 0.29} + 29%|██▊ | 3428/11952 [1:55:07<14:08:07, 5.97s/it] 29%|██▊ | 3429/11952 [1:55:13<13:59:51, 5.91s/it] {'loss': 0.4952, 'learning_rate': 1.6734423285431705e-05, 'epoch': 0.29} + 29%|██▊ | 3429/11952 [1:55:13<13:59:51, 5.91s/it] 29%|██▊ | 3430/11952 [1:55:19<14:12:32, 6.00s/it] {'loss': 0.5189, 'learning_rate': 1.6732419768782656e-05, 'epoch': 0.29} + 29%|██▊ | 3430/11952 [1:55:19<14:12:32, 6.00s/it] 29%|██▊ | 3431/11952 [1:55:25<14:12:05, 6.00s/it] {'loss': 0.4859, 'learning_rate': 1.6730415757732702e-05, 'epoch': 0.29} + 29%|██▊ | 3431/11952 [1:55:25<14:12:05, 6.00s/it] 29%|██▊ | 3432/11952 [1:55:31<14:02:46, 5.94s/it] {'loss': 0.5037, 'learning_rate': 1.6728411252429006e-05, 'epoch': 0.29} + 29%|██▊ | 3432/11952 [1:55:31<14:02:46, 5.94s/it] 29%|██▊ | 3433/11952 [1:55:36<14:01:42, 5.93s/it] {'loss': 0.4977, 'learning_rate': 1.672640625301877e-05, 'epoch': 0.29} + 29%|██▊ | 3433/11952 [1:55:36<14:01:42, 5.93s/it] 29%|██▊ | 3434/11952 [1:55:42<13:57:13, 5.90s/it] {'loss': 0.4831, 'learning_rate': 1.6724400759649243e-05, 'epoch': 0.29} + 29%|██▊ | 3434/11952 [1:55:42<13:57:13, 5.90s/it] 29%|██▊ | 3435/11952 [1:55:48<13:49:43, 5.85s/it] {'loss': 0.4928, 'learning_rate': 1.672239477246769e-05, 'epoch': 0.29} + 29%|██▊ | 3435/11952 [1:55:48<13:49:43, 5.85s/it] 29%|██▊ | 3436/11952 [1:55:54<13:58:25, 5.91s/it] {'loss': 0.4899, 'learning_rate': 1.6720388291621423e-05, 'epoch': 0.29} + 29%|██▊ | 3436/11952 [1:55:54<13:58:25, 5.91s/it] 29%|██▉ | 3437/11952 [1:56:00<13:41:34, 5.79s/it] {'loss': 0.4841, 'learning_rate': 1.6718381317257793e-05, 'epoch': 0.29} + 29%|██▉ | 3437/11952 [1:56:00<13:41:34, 5.79s/it] 29%|██▉ | 3438/11952 [1:56:06<13:56:10, 5.89s/it] {'loss': 0.5012, 'learning_rate': 1.6716373849524187e-05, 'epoch': 0.29} + 29%|██▉ | 3438/11952 [1:56:06<13:56:10, 5.89s/it]/lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/VILA/llava/model/llava_arch.py:397: UserWarning: Inputs truncated! + warnings.warn("Inputs truncated!") + 29%|██▉ | 3439/11952 [1:56:12<14:06:54, 5.97s/it] {'loss': 0.5064, 'learning_rate': 1.671436588856802e-05, 'epoch': 0.29} + 29%|██▉ | 3439/11952 [1:56:12<14:06:54, 5.97s/it] 29%|██▉ | 3440/11952 [1:56:17<13:50:57, 5.86s/it] {'loss': 0.4881, 'learning_rate': 1.6712357434536747e-05, 'epoch': 0.29} + 29%|██▉ | 3440/11952 [1:56:17<13:50:57, 5.86s/it] 29%|██▉ | 3441/11952 [1:56:23<13:50:10, 5.85s/it] {'loss': 0.4914, 'learning_rate': 1.6710348487577863e-05, 'epoch': 0.29} + 29%|██▉ | 3441/11952 [1:56:23<13:50:10, 5.85s/it] 29%|██▉ | 3442/11952 [1:56:29<13:56:41, 5.90s/it] {'loss': 0.4985, 'learning_rate': 1.6708339047838897e-05, 'epoch': 0.29} + 29%|██▉ | 3442/11952 [1:56:29<13:56:41, 5.90s/it] 29%|██▉ | 3443/11952 [1:56:35<13:53:51, 5.88s/it] {'loss': 0.4928, 'learning_rate': 1.6706329115467412e-05, 'epoch': 0.29} + 29%|██▉ | 3443/11952 [1:56:35<13:53:51, 5.88s/it] 29%|██▉ | 3444/11952 [1:56:41<13:42:21, 5.80s/it] {'loss': 0.4741, 'learning_rate': 1.670431869061101e-05, 'epoch': 0.29} + 29%|██▉ | 3444/11952 [1:56:41<13:42:21, 5.80s/it] 29%|██▉ | 3445/11952 [1:56:47<13:43:53, 5.81s/it] {'loss': 0.4799, 'learning_rate': 1.6702307773417334e-05, 'epoch': 0.29} + 29%|██▉ | 3445/11952 [1:56:47<13:43:53, 5.81s/it] 29%|██▉ | 3446/11952 [1:56:52<13:42:35, 5.80s/it] {'loss': 0.5049, 'learning_rate': 1.6700296364034048e-05, 'epoch': 0.29} + 29%|██▉ | 3446/11952 [1:56:52<13:42:35, 5.80s/it] 29%|██▉ | 3447/11952 [1:56:58<13:43:08, 5.81s/it] {'loss': 0.5034, 'learning_rate': 1.6698284462608866e-05, 'epoch': 0.29} + 29%|██▉ | 3447/11952 [1:56:58<13:43:08, 5.81s/it] 29%|██▉ | 3448/11952 [1:57:04<13:46:08, 5.83s/it] {'loss': 0.4924, 'learning_rate': 1.6696272069289533e-05, 'epoch': 0.29} + 29%|██▉ | 3448/11952 [1:57:04<13:46:08, 5.83s/it] 29%|██▉ | 3449/11952 [1:57:10<13:50:25, 5.86s/it] {'loss': 0.5037, 'learning_rate': 1.6694259184223833e-05, 'epoch': 0.29} + 29%|██▉ | 3449/11952 [1:57:10<13:50:25, 5.86s/it]6 AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +5 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... + 29%|██▉ | 3450/11952 [1:57:16<13:51:08, 5.87s/it] {'loss': 0.4939, 'learning_rate': 1.6692245807559578e-05, 'epoch': 0.29} + 29%|██▉ | 3450/11952 [1:57:16<13:51:08, 5.87s/it] 29%|██▉ | 3451/11952 [1:57:22<14:00:52, 5.93s/it] {'loss': 0.4952, 'learning_rate': 1.669023193944463e-05, 'epoch': 0.29} + 29%|██▉ | 3451/11952 [1:57:22<14:00:52, 5.93s/it] 29%|██▉ | 3452/11952 [1:57:28<13:49:15, 5.85s/it] {'loss': 0.4887, 'learning_rate': 1.668821758002688e-05, 'epoch': 0.29} + 29%|██▉ | 3452/11952 [1:57:28<13:49:15, 5.85s/it] 29%|██▉ | 3453/11952 [1:57:33<13:51:11, 5.87s/it] {'loss': 0.5063, 'learning_rate': 1.668620272945424e-05, 'epoch': 0.29} + 29%|██▉ | 3453/11952 [1:57:33<13:51:11, 5.87s/it] 29%|██▉ | 3454/11952 [1:57:39<13:49:22, 5.86s/it] {'loss': 0.4739, 'learning_rate': 1.6684187387874686e-05, 'epoch': 0.29} + 29%|██▉ | 3454/11952 [1:57:39<13:49:22, 5.86s/it] 29%|██▉ | 3455/11952 [1:57:45<13:58:32, 5.92s/it] {'loss': 0.5013, 'learning_rate': 1.668217155543621e-05, 'epoch': 0.29} + 29%|██▉ | 3455/11952 [1:57:45<13:58:32, 5.92s/it] 29%|██▉ | 3456/11952 [1:57:51<13:51:03, 5.87s/it] {'loss': 0.4862, 'learning_rate': 1.668015523228685e-05, 'epoch': 0.29} + 29%|██▉ | 3456/11952 [1:57:51<13:51:03, 5.87s/it] 29%|██▉ | 3457/11952 [1:57:57<13:57:04, 5.91s/it] {'loss': 0.4973, 'learning_rate': 1.6678138418574673e-05, 'epoch': 0.29} + 29%|██▉ | 3457/11952 [1:57:57<13:57:04, 5.91s/it] 29%|██▉ | 3458/11952 [1:58:03<13:54:44, 5.90s/it] {'loss': 0.4797, 'learning_rate': 1.6676121114447784e-05, 'epoch': 0.29} + 29%|██▉ | 3458/11952 [1:58:03<13:54:44, 5.90s/it] 29%|██▉ | 3459/11952 [1:58:09<13:51:46, 5.88s/it] {'loss': 0.5063, 'learning_rate': 1.6674103320054335e-05, 'epoch': 0.29} + 29%|██▉ | 3459/11952 [1:58:09<13:51:46, 5.88s/it] 29%|██▉ | 3460/11952 [1:58:15<13:45:53, 5.84s/it] {'loss': 0.4745, 'learning_rate': 1.6672085035542497e-05, 'epoch': 0.29} + 29%|██▉ | 3460/11952 [1:58:15<13:45:53, 5.84s/it] 29%|██▉ | 3461/11952 [1:58:21<14:02:40, 5.95s/it] {'loss': 0.4841, 'learning_rate': 1.667006626106048e-05, 'epoch': 0.29} + 29%|██▉ | 3461/11952 [1:58:21<14:02:40, 5.95s/it] 29%|██▉ | 3462/11952 [1:58:27<14:03:57, 5.96s/it] {'loss': 0.4975, 'learning_rate': 1.6668046996756544e-05, 'epoch': 0.29} + 29%|██▉ | 3462/11952 [1:58:27<14:03:57, 5.96s/it] 29%|██▉ | 3463/11952 [1:58:33<13:54:17, 5.90s/it] {'loss': 0.5235, 'learning_rate': 1.6666027242778972e-05, 'epoch': 0.29} + 29%|██▉ | 3463/11952 [1:58:33<13:54:17, 5.90s/it] 29%|██▉ | 3464/11952 [1:58:38<13:42:27, 5.81s/it] {'loss': 0.4883, 'learning_rate': 1.666400699927608e-05, 'epoch': 0.29} + 29%|██▉ | 3464/11952 [1:58:38<13:42:27, 5.81s/it] 29%|██▉ | 3465/11952 [1:58:44<13:56:02, 5.91s/it] {'loss': 0.5063, 'learning_rate': 1.6661986266396235e-05, 'epoch': 0.29} + 29%|██▉ | 3465/11952 [1:58:44<13:56:02, 5.91s/it] 29%|██▉ | 3466/11952 [1:58:51<14:09:56, 6.01s/it] {'loss': 0.4858, 'learning_rate': 1.6659965044287826e-05, 'epoch': 0.29} + 29%|██▉ | 3466/11952 [1:58:51<14:09:56, 6.01s/it] 29%|██▉ | 3467/11952 [1:58:56<14:05:15, 5.98s/it] {'loss': 0.4754, 'learning_rate': 1.6657943333099287e-05, 'epoch': 0.29} + 29%|██▉ | 3467/11952 [1:58:56<14:05:15, 5.98s/it] 29%|██▉ | 3468/11952 [1:59:02<14:03:46, 5.97s/it] {'loss': 0.4743, 'learning_rate': 1.6655921132979082e-05, 'epoch': 0.29} + 29%|██▉ | 3468/11952 [1:59:02<14:03:46, 5.97s/it] 29%|██▉ | 3469/11952 [1:59:08<13:47:17, 5.85s/it] {'loss': 0.4887, 'learning_rate': 1.6653898444075713e-05, 'epoch': 0.29} + 29%|██▉ | 3469/11952 [1:59:08<13:47:17, 5.85s/it] 29%|██▉ | 3470/11952 [1:59:14<13:46:13, 5.84s/it] {'loss': 0.4948, 'learning_rate': 1.6651875266537718e-05, 'epoch': 0.29} + 29%|██▉ | 3470/11952 [1:59:14<13:46:13, 5.84s/it] 29%|██▉ | 3471/11952 [1:59:20<13:53:47, 5.90s/it] {'loss': 0.4873, 'learning_rate': 1.664985160051367e-05, 'epoch': 0.29} + 29%|██▉ | 3471/11952 [1:59:20<13:53:47, 5.90s/it] 29%|██▉ | 3472/11952 [1:59:26<13:52:55, 5.89s/it] {'loss': 0.486, 'learning_rate': 1.6647827446152183e-05, 'epoch': 0.29} + 29%|██▉ | 3472/11952 [1:59:26<13:52:55, 5.89s/it] 29%|██▉ | 3473/11952 [1:59:32<13:58:05, 5.93s/it] {'loss': 0.4984, 'learning_rate': 1.6645802803601893e-05, 'epoch': 0.29} + 29%|██▉ | 3473/11952 [1:59:32<13:58:05, 5.93s/it] 29%|██▉ | 3474/11952 [1:59:38<14:00:39, 5.95s/it] {'loss': 0.5056, 'learning_rate': 1.664377767301149e-05, 'epoch': 0.29} + 29%|██▉ | 3474/11952 [1:59:38<14:00:39, 5.95s/it] 29%|██▉ | 3475/11952 [1:59:43<13:51:12, 5.88s/it] {'loss': 0.4926, 'learning_rate': 1.664175205452969e-05, 'epoch': 0.29} + 29%|██▉ | 3475/11952 [1:59:43<13:51:12, 5.88s/it] 29%|██▉ | 3476/11952 [1:59:49<13:55:31, 5.91s/it] {'loss': 0.5159, 'learning_rate': 1.663972594830524e-05, 'epoch': 0.29} + 29%|██▉ | 3476/11952 [1:59:49<13:55:31, 5.91s/it] 29%|██▉ | 3477/11952 [1:59:55<13:59:51, 5.95s/it] {'loss': 0.5252, 'learning_rate': 1.6637699354486936e-05, 'epoch': 0.29} + 29%|██▉ | 3477/11952 [1:59:55<13:59:51, 5.95s/it] 29%|██▉ | 3478/11952 [2:00:01<13:54:10, 5.91s/it] {'loss': 0.4872, 'learning_rate': 1.6635672273223597e-05, 'epoch': 0.29} + 29%|██▉ | 3478/11952 [2:00:01<13:54:10, 5.91s/it] 29%|██▉ | 3479/11952 [2:00:07<13:49:25, 5.87s/it] {'loss': 0.4877, 'learning_rate': 1.663364470466409e-05, 'epoch': 0.29} + 29%|██▉ | 3479/11952 [2:00:07<13:49:25, 5.87s/it] 29%|██▉ | 3480/11952 [2:00:13<13:47:40, 5.86s/it] {'loss': 0.4879, 'learning_rate': 1.6631616648957303e-05, 'epoch': 0.29} + 29%|██▉ | 3480/11952 [2:00:13<13:47:40, 5.86s/it] 29%|██▉ | 3481/11952 [2:00:19<13:42:29, 5.83s/it] {'loss': 0.4756, 'learning_rate': 1.6629588106252173e-05, 'epoch': 0.29} + 29%|██▉ | 3481/11952 [2:00:19<13:42:29, 5.83s/it] 29%|██▉ | 3482/11952 [2:00:25<13:53:30, 5.90s/it] {'loss': 0.5409, 'learning_rate': 1.6627559076697672e-05, 'epoch': 0.29} + 29%|██▉ | 3482/11952 [2:00:25<13:53:30, 5.90s/it] 29%|██▉ | 3483/11952 [2:00:30<13:44:18, 5.84s/it] {'loss': 0.5017, 'learning_rate': 1.6625529560442793e-05, 'epoch': 0.29} + 29%|██▉ | 3483/11952 [2:00:30<13:44:18, 5.84s/it] 29%|██▉ | 3484/11952 [2:00:36<13:35:35, 5.78s/it] {'loss': 0.4925, 'learning_rate': 1.6623499557636584e-05, 'epoch': 0.29} + 29%|██▉ | 3484/11952 [2:00:36<13:35:35, 5.78s/it] 29%|██▉ | 3485/11952 [2:00:42<13:35:12, 5.78s/it] {'loss': 0.4936, 'learning_rate': 1.6621469068428114e-05, 'epoch': 0.29} + 29%|██▉ | 3485/11952 [2:00:42<13:35:12, 5.78s/it] 29%|██▉ | 3486/11952 [2:00:48<13:41:00, 5.82s/it] {'loss': 0.5126, 'learning_rate': 1.66194380929665e-05, 'epoch': 0.29} + 29%|██▉ | 3486/11952 [2:00:48<13:41:00, 5.82s/it] 29%|██▉ | 3487/11952 [2:00:53<13:32:43, 5.76s/it] {'loss': 0.4967, 'learning_rate': 1.6617406631400884e-05, 'epoch': 0.29} + 29%|██▉ | 3487/11952 [2:00:53<13:32:43, 5.76s/it] 29%|██▉ | 3488/11952 [2:00:59<13:45:25, 5.85s/it] {'loss': 0.4864, 'learning_rate': 1.6615374683880445e-05, 'epoch': 0.29} + 29%|██▉ | 3488/11952 [2:00:59<13:45:25, 5.85s/it] 29%|██▉ | 3489/11952 [2:01:05<13:39:12, 5.81s/it] {'loss': 0.4922, 'learning_rate': 1.6613342250554406e-05, 'epoch': 0.29} + 29%|██▉ | 3489/11952 [2:01:05<13:39:12, 5.81s/it] 29%|██▉ | 3490/11952 [2:01:11<13:44:31, 5.85s/it] {'loss': 0.4962, 'learning_rate': 1.6611309331572022e-05, 'epoch': 0.29} + 29%|██▉ | 3490/11952 [2:01:11<13:44:31, 5.85s/it] 29%|██▉ | 3491/11952 [2:01:17<13:43:47, 5.84s/it] {'loss': 0.4899, 'learning_rate': 1.6609275927082577e-05, 'epoch': 0.29} + 29%|██▉ | 3491/11952 [2:01:17<13:43:47, 5.84s/it] 29%|██▉ | 3492/11952 [2:01:23<13:35:24, 5.78s/it] {'loss': 0.4947, 'learning_rate': 1.66072420372354e-05, 'epoch': 0.29} + 29%|██▉ | 3492/11952 [2:01:23<13:35:24, 5.78s/it] 29%|██▉ | 3493/11952 [2:01:28<13:39:42, 5.81s/it] {'loss': 0.5001, 'learning_rate': 1.660520766217985e-05, 'epoch': 0.29} + 29%|██▉ | 3493/11952 [2:01:28<13:39:42, 5.81s/it] 29%|██▉ | 3494/11952 [2:01:35<13:52:27, 5.91s/it] {'loss': 0.5018, 'learning_rate': 1.6603172802065317e-05, 'epoch': 0.29} + 29%|██▉ | 3494/11952 [2:01:35<13:52:27, 5.91s/it] 29%|██▉ | 3495/11952 [2:01:40<13:48:56, 5.88s/it] {'loss': 0.5025, 'learning_rate': 1.6601137457041242e-05, 'epoch': 0.29} + 29%|██▉ | 3495/11952 [2:01:40<13:48:56, 5.88s/it] 29%|██▉ | 3496/11952 [2:01:46<13:49:40, 5.89s/it] {'loss': 0.4887, 'learning_rate': 1.6599101627257087e-05, 'epoch': 0.29} + 29%|██▉ | 3496/11952 [2:01:46<13:49:40, 5.89s/it] 29%|██▉ | 3497/11952 [2:01:52<13:41:28, 5.83s/it] {'loss': 0.4875, 'learning_rate': 1.6597065312862358e-05, 'epoch': 0.29} + 29%|██▉ | 3497/11952 [2:01:52<13:41:28, 5.83s/it] 29%|██▉ | 3498/11952 [2:01:58<13:33:00, 5.77s/it] {'loss': 0.5023, 'learning_rate': 1.659502851400659e-05, 'epoch': 0.29} + 29%|██▉ | 3498/11952 [2:01:58<13:33:00, 5.77s/it] 29%|██▉ | 3499/11952 [2:02:04<13:46:42, 5.87s/it] {'loss': 0.4966, 'learning_rate': 1.6592991230839355e-05, 'epoch': 0.29} + 29%|██▉ | 3499/11952 [2:02:04<13:46:42, 5.87s/it]10 AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend...4 + AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... + 29%|██▉ | 3500/11952 [2:02:10<14:03:09, 5.99s/it]7 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... + {'loss': 0.5032, 'learning_rate': 1.659095346351027e-05, 'epoch': 0.29} + 29%|██▉ | 3500/11952 [2:02:10<14:03:09, 5.99s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-3500/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-3500/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/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( + 29%|██▉ | 3501/11952 [2:02:42<32:33:47, 13.87s/it] {'loss': 0.4823, 'learning_rate': 1.6588915212168977e-05, 'epoch': 0.29} + 29%|██▉ | 3501/11952 [2:02:42<32:33:47, 13.87s/it] 29%|██▉ | 3502/11952 [2:02:48<26:54:01, 11.46s/it] {'loss': 0.5014, 'learning_rate': 1.658687647696516e-05, 'epoch': 0.29} + 29%|██▉ | 3502/11952 [2:02:48<26:54:01, 11.46s/it] 29%|██▉ | 3503/11952 [2:02:54<22:49:10, 9.72s/it] {'loss': 0.4557, 'learning_rate': 1.658483725804853e-05, 'epoch': 0.29} + 29%|██▉ | 3503/11952 [2:02:54<22:49:10, 9.72s/it] 29%|██▉ | 3504/11952 [2:02:59<19:58:10, 8.51s/it] {'loss': 0.5108, 'learning_rate': 1.6582797555568834e-05, 'epoch': 0.29} + 29%|██▉ | 3504/11952 [2:02:59<19:58:10, 8.51s/it] 29%|██▉ | 3505/11952 [2:03:05<18:13:53, 7.77s/it] {'loss': 0.5026, 'learning_rate': 1.658075736967587e-05, 'epoch': 0.29} + 29%|██▉ | 3505/11952 [2:03:05<18:13:53, 7.77s/it] 29%|██▉ | 3506/11952 [2:03:11<16:50:15, 7.18s/it] {'loss': 0.5017, 'learning_rate': 1.6578716700519454e-05, 'epoch': 0.29} + 29%|██▉ | 3506/11952 [2:03:11<16:50:15, 7.18s/it] 29%|██▉ | 3507/11952 [2:03:17<16:02:47, 6.84s/it] {'loss': 0.4901, 'learning_rate': 1.657667554824945e-05, 'epoch': 0.29} + 29%|██▉ | 3507/11952 [2:03:17<16:02:47, 6.84s/it] 29%|██▉ | 3508/11952 [2:03:23<15:13:10, 6.49s/it] {'loss': 0.4907, 'learning_rate': 1.6574633913015742e-05, 'epoch': 0.29} + 29%|██▉ | 3508/11952 [2:03:23<15:13:10, 6.49s/it] 29%|██▉ | 3509/11952 [2:03:29<14:42:56, 6.27s/it] {'loss': 0.4864, 'learning_rate': 1.657259179496827e-05, 'epoch': 0.29} + 29%|██▉ | 3509/11952 [2:03:29<14:42:56, 6.27s/it] 29%|██▉ | 3510/11952 [2:03:35<14:25:42, 6.15s/it] {'loss': 0.495, 'learning_rate': 1.6570549194256995e-05, 'epoch': 0.29} + 29%|██▉ | 3510/11952 [2:03:35<14:25:42, 6.15s/it] 29%|██▉ | 3511/11952 [2:03:40<14:12:04, 6.06s/it] {'loss': 0.5021, 'learning_rate': 1.6568506111031913e-05, 'epoch': 0.29} + 29%|██▉ | 3511/11952 [2:03:40<14:12:04, 6.06s/it] 29%|██▉ | 3512/11952 [2:03:46<14:02:35, 5.99s/it] {'loss': 0.5074, 'learning_rate': 1.6566462545443066e-05, 'epoch': 0.29} + 29%|██▉ | 3512/11952 [2:03:46<14:02:35, 5.99s/it] 29%|██▉ | 3513/11952 [2:03:52<14:04:17, 6.00s/it] {'loss': 0.4989, 'learning_rate': 1.656441849764052e-05, 'epoch': 0.29} + 29%|██▉ | 3513/11952 [2:03:52<14:04:17, 6.00s/it] 29%|██▉ | 3514/11952 [2:03:58<14:05:44, 6.01s/it] {'loss': 0.509, 'learning_rate': 1.6562373967774382e-05, 'epoch': 0.29} + 29%|██▉ | 3514/11952 [2:03:58<14:05:44, 6.01s/it] 29%|██▉ | 3515/11952 [2:04:04<13:58:38, 5.96s/it] {'loss': 0.5201, 'learning_rate': 1.6560328955994796e-05, 'epoch': 0.29} + 29%|██▉ | 3515/11952 [2:04:04<13:58:38, 5.96s/it] 29%|██▉ | 3516/11952 [2:04:10<14:05:50, 6.02s/it] {'loss': 0.5027, 'learning_rate': 1.655828346245194e-05, 'epoch': 0.29} + 29%|██▉ | 3516/11952 [2:04:10<14:05:50, 6.02s/it] 29%|██▉ | 3517/11952 [2:04:16<14:00:08, 5.98s/it] {'loss': 0.4831, 'learning_rate': 1.655623748729602e-05, 'epoch': 0.29} + 29%|██▉ | 3517/11952 [2:04:16<14:00:08, 5.98s/it] 29%|██▉ | 3518/11952 [2:04:22<14:03:38, 6.00s/it] {'loss': 0.5112, 'learning_rate': 1.655419103067729e-05, 'epoch': 0.29} + 29%|██▉ | 3518/11952 [2:04:22<14:03:38, 6.00s/it] 29%|██▉ | 3519/11952 [2:04:28<14:06:16, 6.02s/it] {'loss': 0.4874, 'learning_rate': 1.6552144092746032e-05, 'epoch': 0.29} + 29%|██▉ | 3519/11952 [2:04:28<14:06:16, 6.02s/it] 29%|██▉ | 3520/11952 [2:04:35<14:13:14, 6.07s/it] {'loss': 0.4991, 'learning_rate': 1.6550096673652565e-05, 'epoch': 0.29} + 29%|██▉ | 3520/11952 [2:04:35<14:13:14, 6.07s/it] 29%|██▉ | 3521/11952 [2:04:40<13:58:45, 5.97s/it] {'loss': 0.4899, 'learning_rate': 1.654804877354724e-05, 'epoch': 0.29} + 29%|██▉ | 3521/11952 [2:04:40<13:58:45, 5.97s/it] 29%|██▉ | 3522/11952 [2:04:46<14:04:09, 6.01s/it] {'loss': 0.5151, 'learning_rate': 1.654600039258045e-05, 'epoch': 0.29} + 29%|██▉ | 3522/11952 [2:04:46<14:04:09, 6.01s/it] 29%|██▉ | 3523/11952 [2:04:52<13:48:01, 5.89s/it] {'loss': 0.5163, 'learning_rate': 1.6543951530902618e-05, 'epoch': 0.29} + 29%|██▉ | 3523/11952 [2:04:52<13:48:01, 5.89s/it] 29%|██▉ | 3524/11952 [2:04:58<13:36:43, 5.81s/it] {'loss': 0.4763, 'learning_rate': 1.6541902188664206e-05, 'epoch': 0.29} + 29%|██▉ | 3524/11952 [2:04:58<13:36:43, 5.81s/it] 29%|██▉ | 3525/11952 [2:05:03<13:31:40, 5.78s/it] {'loss': 0.5012, 'learning_rate': 1.6539852366015702e-05, 'epoch': 0.29} + 29%|██▉ | 3525/11952 [2:05:03<13:31:40, 5.78s/it] 30%|██▉ | 3526/11952 [2:05:09<13:23:47, 5.72s/it] {'loss': 0.4732, 'learning_rate': 1.6537802063107646e-05, 'epoch': 0.3} + 30%|██▉ | 3526/11952 [2:05:09<13:23:47, 5.72s/it] 30%|██▉ | 3527/11952 [2:05:15<13:35:42, 5.81s/it] {'loss': 0.51, 'learning_rate': 1.6535751280090598e-05, 'epoch': 0.3} + 30%|██▉ | 3527/11952 [2:05:15<13:35:42, 5.81s/it] 30%|██▉ | 3528/11952 [2:05:21<13:33:53, 5.80s/it] {'loss': 0.5077, 'learning_rate': 1.6533700017115162e-05, 'epoch': 0.3} + 30%|██▉ | 3528/11952 [2:05:21<13:33:53, 5.80s/it] 30%|██▉ | 3529/11952 [2:05:26<13:31:53, 5.78s/it] {'loss': 0.5029, 'learning_rate': 1.653164827433197e-05, 'epoch': 0.3} + 30%|██▉ | 3529/11952 [2:05:26<13:31:53, 5.78s/it] 30%|██▉ | 3530/11952 [2:05:32<13:40:27, 5.85s/it] {'loss': 0.4791, 'learning_rate': 1.6529596051891696e-05, 'epoch': 0.3} + 30%|██▉ | 3530/11952 [2:05:32<13:40:27, 5.85s/it] 30%|██▉ | 3531/11952 [2:05:38<13:39:32, 5.84s/it] {'loss': 0.5035, 'learning_rate': 1.6527543349945047e-05, 'epoch': 0.3} + 30%|██▉ | 3531/11952 [2:05:38<13:39:32, 5.84s/it] 30%|██▉ | 3532/11952 [2:05:44<13:38:02, 5.83s/it] {'loss': 0.4892, 'learning_rate': 1.6525490168642765e-05, 'epoch': 0.3} + 30%|██▉ | 3532/11952 [2:05:44<13:38:02, 5.83s/it] 30%|██▉ | 3533/11952 [2:05:50<13:42:19, 5.86s/it] {'loss': 0.4915, 'learning_rate': 1.6523436508135624e-05, 'epoch': 0.3} + 30%|██▉ | 3533/11952 [2:05:50<13:42:19, 5.86s/it] 30%|██▉ | 3534/11952 [2:05:56<13:34:28, 5.81s/it] {'loss': 0.4816, 'learning_rate': 1.6521382368574442e-05, 'epoch': 0.3} + 30%|██▉ | 3534/11952 [2:05:56<13:34:28, 5.81s/it] 30%|██▉ | 3535/11952 [2:06:02<13:38:07, 5.83s/it] {'loss': 0.481, 'learning_rate': 1.651932775011006e-05, 'epoch': 0.3} + 30%|██▉ | 3535/11952 [2:06:02<13:38:07, 5.83s/it] 30%|██▉ | 3536/11952 [2:06:08<13:45:11, 5.88s/it] {'loss': 0.4885, 'learning_rate': 1.6517272652893367e-05, 'epoch': 0.3} + 30%|██▉ | 3536/11952 [2:06:08<13:45:11, 5.88s/it] 30%|██▉ | 3537/11952 [2:06:14<13:46:56, 5.90s/it] {'loss': 0.506, 'learning_rate': 1.6515217077075276e-05, 'epoch': 0.3} + 30%|██▉ | 3537/11952 [2:06:14<13:46:56, 5.90s/it] 30%|██▉ | 3538/11952 [2:06:19<13:49:14, 5.91s/it] {'loss': 0.4849, 'learning_rate': 1.651316102280674e-05, 'epoch': 0.3} + 30%|██▉ | 3538/11952 [2:06:19<13:49:14, 5.91s/it] 30%|██▉ | 3539/11952 [2:06:25<13:40:06, 5.85s/it] {'loss': 0.5038, 'learning_rate': 1.6511104490238753e-05, 'epoch': 0.3} + 30%|██▉ | 3539/11952 [2:06:25<13:40:06, 5.85s/it] 30%|██▉ | 3540/11952 [2:06:31<13:49:31, 5.92s/it] {'loss': 0.5172, 'learning_rate': 1.6509047479522332e-05, 'epoch': 0.3} + 30%|██▉ | 3540/11952 [2:06:31<13:49:31, 5.92s/it] 30%|██▉ | 3541/11952 [2:06:37<13:44:20, 5.88s/it] {'loss': 0.4906, 'learning_rate': 1.650698999080854e-05, 'epoch': 0.3} + 30%|██▉ | 3541/11952 [2:06:37<13:44:20, 5.88s/it] 30%|██▉ | 3542/11952 [2:06:43<13:51:45, 5.93s/it] {'loss': 0.4895, 'learning_rate': 1.6504932024248462e-05, 'epoch': 0.3} + 30%|██▉ | 3542/11952 [2:06:43<13:51:45, 5.93s/it] 30%|██▉ | 3543/11952 [2:06:49<13:54:12, 5.95s/it] {'loss': 0.4769, 'learning_rate': 1.6502873579993238e-05, 'epoch': 0.3} + 30%|██▉ | 3543/11952 [2:06:49<13:54:12, 5.95s/it] 30%|██▉ | 3544/11952 [2:06:55<13:48:31, 5.91s/it] {'loss': 0.5035, 'learning_rate': 1.6500814658194024e-05, 'epoch': 0.3} + 30%|██▉ | 3544/11952 [2:06:55<13:48:31, 5.91s/it] 30%|██▉ | 3545/11952 [2:07:01<13:50:56, 5.93s/it] {'loss': 0.5003, 'learning_rate': 1.649875525900202e-05, 'epoch': 0.3} + 30%|██▉ | 3545/11952 [2:07:01<13:50:56, 5.93s/it] 30%|██▉ | 3546/11952 [2:07:07<13:41:07, 5.86s/it] {'loss': 0.4854, 'learning_rate': 1.649669538256846e-05, 'epoch': 0.3} + 30%|██▉ | 3546/11952 [2:07:07<13:41:07, 5.86s/it] 30%|██▉ | 3547/11952 [2:07:12<13:38:55, 5.85s/it] {'loss': 0.4941, 'learning_rate': 1.6494635029044613e-05, 'epoch': 0.3} + 30%|██▉ | 3547/11952 [2:07:12<13:38:55, 5.85s/it] 30%|██▉ | 3548/11952 [2:07:18<13:35:59, 5.83s/it] {'loss': 0.4851, 'learning_rate': 1.649257419858178e-05, 'epoch': 0.3} + 30%|██▉ | 3548/11952 [2:07:18<13:35:59, 5.83s/it] 30%|██▉ | 3549/11952 [2:07:24<13:45:41, 5.90s/it] {'loss': 0.4964, 'learning_rate': 1.6490512891331304e-05, 'epoch': 0.3} + 30%|██▉ | 3549/11952 [2:07:24<13:45:41, 5.90s/it]3 AutoResumeHook: Checking whether to suspend... +7 15AutoResumeHook: Checking whether to suspend...20 4 + AutoResumeHook: Checking whether to suspend...6 AutoResumeHook: Checking whether to suspend...AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... + +AutoResumeHook: Checking whether to suspend... + + AutoResumeHook: Checking whether to suspend... + 30%|██▉ | 3550/11952 [2:07:30<13:41:50, 5.87s/it] {'loss': 0.5009, 'learning_rate': 1.6488451107444556e-05, 'epoch': 0.3} + 30%|██▉ | 3550/11952 [2:07:30<13:41:50, 5.87s/it] 30%|██▉ | 3551/11952 [2:07:36<13:42:14, 5.87s/it] {'loss': 0.496, 'learning_rate': 1.648638884707295e-05, 'epoch': 0.3} + 30%|██▉ | 3551/11952 [2:07:36<13:42:14, 5.87s/it] 30%|██▉ | 3552/11952 [2:07:42<13:36:04, 5.83s/it] {'loss': 0.5007, 'learning_rate': 1.6484326110367924e-05, 'epoch': 0.3} + 30%|██▉ | 3552/11952 [2:07:42<13:36:04, 5.83s/it] 30%|██▉ | 3553/11952 [2:07:47<13:34:24, 5.82s/it] {'loss': 0.5075, 'learning_rate': 1.648226289748096e-05, 'epoch': 0.3} + 30%|██▉ | 3553/11952 [2:07:47<13:34:24, 5.82s/it] 30%|██▉ | 3554/11952 [2:07:53<13:39:48, 5.86s/it] {'loss': 0.4816, 'learning_rate': 1.648019920856357e-05, 'epoch': 0.3} + 30%|██▉ | 3554/11952 [2:07:53<13:39:48, 5.86s/it] 30%|██▉ | 3555/11952 [2:07:59<13:37:12, 5.84s/it] {'loss': 0.5059, 'learning_rate': 1.6478135043767303e-05, 'epoch': 0.3} + 30%|██▉ | 3555/11952 [2:07:59<13:37:12, 5.84s/it] 30%|██▉ | 3556/11952 [2:08:05<13:33:51, 5.82s/it] {'loss': 0.4913, 'learning_rate': 1.647607040324374e-05, 'epoch': 0.3} + 30%|██▉ | 3556/11952 [2:08:05<13:33:51, 5.82s/it] 30%|██▉ | 3557/11952 [2:08:11<13:36:16, 5.83s/it] {'loss': 0.4945, 'learning_rate': 1.6474005287144507e-05, 'epoch': 0.3} + 30%|██▉ | 3557/11952 [2:08:11<13:36:16, 5.83s/it] 30%|██▉ | 3558/11952 [2:08:17<13:32:39, 5.81s/it] {'loss': 0.4799, 'learning_rate': 1.647193969562125e-05, 'epoch': 0.3} + 30%|██▉ | 3558/11952 [2:08:17<13:32:39, 5.81s/it] 30%|██▉ | 3559/11952 [2:08:22<13:31:39, 5.80s/it] {'loss': 0.5039, 'learning_rate': 1.6469873628825665e-05, 'epoch': 0.3} + 30%|██▉ | 3559/11952 [2:08:22<13:31:39, 5.80s/it] 30%|██▉ | 3560/11952 [2:08:28<13:26:11, 5.76s/it] {'loss': 0.4956, 'learning_rate': 1.6467807086909468e-05, 'epoch': 0.3} + 30%|██▉ | 3560/11952 [2:08:28<13:26:11, 5.76s/it] 30%|██▉ | 3561/11952 [2:08:34<13:46:27, 5.91s/it] {'loss': 0.5098, 'learning_rate': 1.646574007002442e-05, 'epoch': 0.3} + 30%|██▉ | 3561/11952 [2:08:34<13:46:27, 5.91s/it] 30%|██▉ | 3562/11952 [2:08:40<13:43:20, 5.89s/it] {'loss': 0.4929, 'learning_rate': 1.6463672578322315e-05, 'epoch': 0.3} + 30%|██▉ | 3562/11952 [2:08:40<13:43:20, 5.89s/it] 30%|██▉ | 3563/11952 [2:08:46<13:58:35, 6.00s/it] {'loss': 0.4958, 'learning_rate': 1.646160461195498e-05, 'epoch': 0.3} + 30%|██▉ | 3563/11952 [2:08:46<13:58:35, 6.00s/it] 30%|██▉ | 3564/11952 [2:08:52<13:56:05, 5.98s/it] {'loss': 0.4969, 'learning_rate': 1.6459536171074278e-05, 'epoch': 0.3} + 30%|██▉ | 3564/11952 [2:08:52<13:56:05, 5.98s/it] 30%|██▉ | 3565/11952 [2:08:58<13:36:00, 5.84s/it] {'loss': 0.5093, 'learning_rate': 1.6457467255832108e-05, 'epoch': 0.3} + 30%|██▉ | 3565/11952 [2:08:58<13:36:00, 5.84s/it] 30%|██▉ | 3566/11952 [2:09:04<13:35:41, 5.84s/it] {'loss': 0.4717, 'learning_rate': 1.64553978663804e-05, 'epoch': 0.3} + 30%|██▉ | 3566/11952 [2:09:04<13:35:41, 5.84s/it] 30%|██▉ | 3567/11952 [2:09:10<13:41:16, 5.88s/it] {'loss': 0.498, 'learning_rate': 1.645332800287112e-05, 'epoch': 0.3} + 30%|██▉ | 3567/11952 [2:09:10<13:41:16, 5.88s/it] 30%|██▉ | 3568/11952 [2:09:16<13:43:42, 5.89s/it] {'loss': 0.5006, 'learning_rate': 1.645125766545628e-05, 'epoch': 0.3} + 30%|██▉ | 3568/11952 [2:09:16<13:43:42, 5.89s/it] 30%|██▉ | 3569/11952 [2:09:21<13:34:21, 5.83s/it] {'loss': 0.5093, 'learning_rate': 1.6449186854287903e-05, 'epoch': 0.3} + 30%|██▉ | 3569/11952 [2:09:21<13:34:21, 5.83s/it] 30%|██▉ | 3570/11952 [2:09:27<13:36:26, 5.84s/it] {'loss': 0.5111, 'learning_rate': 1.644711556951807e-05, 'epoch': 0.3} + 30%|██▉ | 3570/11952 [2:09:27<13:36:26, 5.84s/it] 30%|██▉ | 3571/11952 [2:09:33<13:30:49, 5.80s/it] {'loss': 0.5057, 'learning_rate': 1.6445043811298887e-05, 'epoch': 0.3} + 30%|██▉ | 3571/11952 [2:09:33<13:30:49, 5.80s/it] 30%|██▉ | 3572/11952 [2:09:39<13:33:20, 5.82s/it] {'loss': 0.4916, 'learning_rate': 1.644297157978249e-05, 'epoch': 0.3} + 30%|██▉ | 3572/11952 [2:09:39<13:33:20, 5.82s/it] 30%|██▉ | 3573/11952 [2:09:45<13:37:22, 5.85s/it] {'loss': 0.4835, 'learning_rate': 1.644089887512106e-05, 'epoch': 0.3} + 30%|██▉ | 3573/11952 [2:09:45<13:37:22, 5.85s/it] 30%|██▉ | 3574/11952 [2:09:50<13:24:33, 5.76s/it] {'loss': 0.4892, 'learning_rate': 1.6438825697466808e-05, 'epoch': 0.3} + 30%|██▉ | 3574/11952 [2:09:50<13:24:33, 5.76s/it] 30%|██▉ | 3575/11952 [2:09:56<13:19:03, 5.72s/it] {'loss': 0.4817, 'learning_rate': 1.6436752046971975e-05, 'epoch': 0.3} + 30%|██▉ | 3575/11952 [2:09:56<13:19:03, 5.72s/it] 30%|██▉ | 3576/11952 [2:10:02<13:25:42, 5.77s/it] {'loss': 0.483, 'learning_rate': 1.6434677923788848e-05, 'epoch': 0.3} + 30%|██▉ | 3576/11952 [2:10:02<13:25:42, 5.77s/it] 30%|██▉ | 3577/11952 [2:10:07<13:23:34, 5.76s/it] {'loss': 0.5143, 'learning_rate': 1.6432603328069732e-05, 'epoch': 0.3} + 30%|██▉ | 3577/11952 [2:10:07<13:23:34, 5.76s/it] 30%|██▉ | 3578/11952 [2:10:14<13:39:13, 5.87s/it] {'loss': 0.507, 'learning_rate': 1.643052825996699e-05, 'epoch': 0.3} + 30%|██▉ | 3578/11952 [2:10:14<13:39:13, 5.87s/it] 30%|██▉ | 3579/11952 [2:10:20<13:43:38, 5.90s/it] {'loss': 0.4962, 'learning_rate': 1.6428452719632994e-05, 'epoch': 0.3} + 30%|██▉ | 3579/11952 [2:10:20<13:43:38, 5.90s/it] 30%|██▉ | 3580/11952 [2:10:25<13:43:03, 5.90s/it] {'loss': 0.5072, 'learning_rate': 1.642637670722017e-05, 'epoch': 0.3} + 30%|██▉ | 3580/11952 [2:10:25<13:43:03, 5.90s/it] 30%|██▉ | 3581/11952 [2:10:31<13:28:30, 5.80s/it] {'loss': 0.4931, 'learning_rate': 1.642430022288097e-05, 'epoch': 0.3} + 30%|██▉ | 3581/11952 [2:10:31<13:28:30, 5.80s/it] 30%|██▉ | 3582/11952 [2:10:37<13:21:41, 5.75s/it] {'loss': 0.4838, 'learning_rate': 1.6422223266767883e-05, 'epoch': 0.3} + 30%|██▉ | 3582/11952 [2:10:37<13:21:41, 5.75s/it] 30%|██▉ | 3583/11952 [2:10:43<13:30:40, 5.81s/it] {'loss': 0.5034, 'learning_rate': 1.642014583903343e-05, 'epoch': 0.3} + 30%|██▉ | 3583/11952 [2:10:43<13:30:40, 5.81s/it] 30%|██▉ | 3584/11952 [2:10:48<13:30:08, 5.81s/it] {'loss': 0.5004, 'learning_rate': 1.641806793983017e-05, 'epoch': 0.3} + 30%|██▉ | 3584/11952 [2:10:48<13:30:08, 5.81s/it] 30%|██▉ | 3585/11952 [2:10:54<13:20:57, 5.74s/it] {'loss': 0.4913, 'learning_rate': 1.6415989569310698e-05, 'epoch': 0.3} + 30%|██▉ | 3585/11952 [2:10:54<13:20:57, 5.74s/it] 30%|███ | 3586/11952 [2:11:00<13:32:13, 5.83s/it] {'loss': 0.4919, 'learning_rate': 1.6413910727627637e-05, 'epoch': 0.3} + 30%|███ | 3586/11952 [2:11:00<13:32:13, 5.83s/it] 30%|███ | 3587/11952 [2:11:06<13:28:29, 5.80s/it] {'loss': 0.5063, 'learning_rate': 1.6411831414933647e-05, 'epoch': 0.3} + 30%|███ | 3587/11952 [2:11:06<13:28:29, 5.80s/it] 30%|███ | 3588/11952 [2:11:12<13:29:56, 5.81s/it] {'loss': 0.481, 'learning_rate': 1.6409751631381428e-05, 'epoch': 0.3} + 30%|███ | 3588/11952 [2:11:12<13:29:56, 5.81s/it] 30%|███ | 3589/11952 [2:11:17<13:30:46, 5.82s/it] {'loss': 0.5164, 'learning_rate': 1.640767137712371e-05, 'epoch': 0.3} + 30%|███ | 3589/11952 [2:11:17<13:30:46, 5.82s/it] 30%|███ | 3590/11952 [2:11:23<13:27:24, 5.79s/it] {'loss': 0.4764, 'learning_rate': 1.6405590652313256e-05, 'epoch': 0.3} + 30%|███ | 3590/11952 [2:11:23<13:27:24, 5.79s/it] 30%|███ | 3591/11952 [2:11:29<13:17:01, 5.72s/it] {'loss': 0.4895, 'learning_rate': 1.640350945710287e-05, 'epoch': 0.3} + 30%|███ | 3591/11952 [2:11:29<13:17:01, 5.72s/it] 30%|███ | 3592/11952 [2:11:34<13:21:28, 5.75s/it] {'loss': 0.5138, 'learning_rate': 1.640142779164538e-05, 'epoch': 0.3} + 30%|███ | 3592/11952 [2:11:34<13:21:28, 5.75s/it] 30%|███ | 3593/11952 [2:11:40<13:14:28, 5.70s/it] {'loss': 0.476, 'learning_rate': 1.6399345656093663e-05, 'epoch': 0.3} + 30%|███ | 3593/11952 [2:11:40<13:14:28, 5.70s/it] 30%|███ | 3594/11952 [2:11:46<13:40:50, 5.89s/it] {'loss': 0.4773, 'learning_rate': 1.6397263050600615e-05, 'epoch': 0.3} + 30%|███ | 3594/11952 [2:11:46<13:40:50, 5.89s/it] 30%|███ | 3595/11952 [2:11:53<13:51:09, 5.97s/it] {'loss': 0.5097, 'learning_rate': 1.6395179975319178e-05, 'epoch': 0.3} + 30%|███ | 3595/11952 [2:11:53<13:51:09, 5.97s/it] 30%|███ | 3596/11952 [2:11:58<13:47:35, 5.94s/it] {'loss': 0.5019, 'learning_rate': 1.6393096430402323e-05, 'epoch': 0.3} + 30%|███ | 3596/11952 [2:11:58<13:47:35, 5.94s/it] 30%|███ | 3597/11952 [2:12:04<13:48:42, 5.95s/it] {'loss': 0.4923, 'learning_rate': 1.6391012416003053e-05, 'epoch': 0.3} + 30%|███ | 3597/11952 [2:12:04<13:48:42, 5.95s/it] 30%|███ | 3598/11952 [2:12:10<13:31:07, 5.83s/it] {'loss': 0.4851, 'learning_rate': 1.638892793227442e-05, 'epoch': 0.3} + 30%|███ | 3598/11952 [2:12:10<13:31:07, 5.83s/it] 30%|███ | 3599/11952 [2:12:16<13:34:55, 5.85s/it] {'loss': 0.4981, 'learning_rate': 1.6386842979369487e-05, 'epoch': 0.3} + 30%|███ | 3599/11952 [2:12:16<13:34:55, 5.85s/it]3 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +57 AutoResumeHook: Checking whether to suspend...AutoResumeHook: Checking whether to suspend... + +2 AutoResumeHook: Checking whether to suspend... +60 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... + 30%|███ | 3600/11952 [2:12:22<13:29:37, 5.82s/it] {'loss': 0.5019, 'learning_rate': 1.6384757557441373e-05, 'epoch': 0.3} + 30%|███ | 3600/11952 [2:12:22<13:29:37, 5.82s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-3600/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-3600/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/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( + 30%|███ | 3601/11952 [2:12:54<32:13:40, 13.89s/it] {'loss': 0.492, 'learning_rate': 1.6382671666643223e-05, 'epoch': 0.3} + 30%|███ | 3601/11952 [2:12:54<32:13:40, 13.89s/it] 30%|███ | 3602/11952 [2:13:00<26:27:29, 11.41s/it] {'loss': 0.4817, 'learning_rate': 1.638058530712821e-05, 'epoch': 0.3} + 30%|███ | 3602/11952 [2:13:00<26:27:29, 11.41s/it] 30%|███ | 3603/11952 [2:13:06<22:28:44, 9.69s/it] {'loss': 0.5039, 'learning_rate': 1.6378498479049553e-05, 'epoch': 0.3} + 30%|███ | 3603/11952 [2:13:06<22:28:44, 9.69s/it] 30%|███ | 3604/11952 [2:13:11<19:45:53, 8.52s/it] {'loss': 0.5044, 'learning_rate': 1.6376411182560498e-05, 'epoch': 0.3} + 30%|███ | 3604/11952 [2:13:11<19:45:53, 8.52s/it] 30%|███ | 3605/11952 [2:13:17<18:00:25, 7.77s/it] {'loss': 0.5089, 'learning_rate': 1.6374323417814325e-05, 'epoch': 0.3} + 30%|███ | 3605/11952 [2:13:17<18:00:25, 7.77s/it] 30%|███ | 3606/11952 [2:13:23<16:32:58, 7.14s/it] {'loss': 0.4915, 'learning_rate': 1.6372235184964357e-05, 'epoch': 0.3} + 30%|███ | 3606/11952 [2:13:23<16:32:58, 7.14s/it] 30%|███ | 3607/11952 [2:13:29<15:28:15, 6.67s/it] {'loss': 0.4752, 'learning_rate': 1.6370146484163935e-05, 'epoch': 0.3} + 30%|███ | 3607/11952 [2:13:29<15:28:15, 6.67s/it] 30%|███ | 3608/11952 [2:13:35<14:56:42, 6.45s/it] {'loss': 0.5043, 'learning_rate': 1.6368057315566454e-05, 'epoch': 0.3} + 30%|███ | 3608/11952 [2:13:35<14:56:42, 6.45s/it] 30%|███ | 3609/11952 [2:13:40<14:31:54, 6.27s/it] {'loss': 0.5013, 'learning_rate': 1.636596767932533e-05, 'epoch': 0.3} + 30%|███ | 3609/11952 [2:13:40<14:31:54, 6.27s/it] 30%|███ | 3610/11952 [2:13:46<14:10:28, 6.12s/it] {'loss': 0.482, 'learning_rate': 1.636387757559402e-05, 'epoch': 0.3} + 30%|███ | 3610/11952 [2:13:46<14:10:28, 6.12s/it] 30%|███ | 3611/11952 [2:13:52<14:01:05, 6.05s/it] {'loss': 0.524, 'learning_rate': 1.6361787004526006e-05, 'epoch': 0.3} + 30%|███ | 3611/11952 [2:13:52<14:01:05, 6.05s/it] 30%|███ | 3612/11952 [2:13:58<13:56:55, 6.02s/it] {'loss': 0.5078, 'learning_rate': 1.635969596627482e-05, 'epoch': 0.3} + 30%|███ | 3612/11952 [2:13:58<13:56:55, 6.02s/it] 30%|███ | 3613/11952 [2:14:04<13:44:40, 5.93s/it] {'loss': 0.4964, 'learning_rate': 1.635760446099401e-05, 'epoch': 0.3} + 30%|███ | 3613/11952 [2:14:04<13:44:40, 5.93s/it] 30%|███ | 3614/11952 [2:14:10<13:43:51, 5.93s/it] {'loss': 0.4827, 'learning_rate': 1.6355512488837173e-05, 'epoch': 0.3} + 30%|███ | 3614/11952 [2:14:10<13:43:51, 5.93s/it] 30%|███ | 3615/11952 [2:14:15<13:37:27, 5.88s/it] {'loss': 0.4924, 'learning_rate': 1.6353420049957932e-05, 'epoch': 0.3} + 30%|███ | 3615/11952 [2:14:15<13:37:27, 5.88s/it] 30%|███ | 3616/11952 [2:14:22<13:47:36, 5.96s/it] {'loss': 0.5235, 'learning_rate': 1.6351327144509954e-05, 'epoch': 0.3} + 30%|███ | 3616/11952 [2:14:22<13:47:36, 5.96s/it] 30%|███ | 3617/11952 [2:14:27<13:42:11, 5.92s/it] {'loss': 0.4919, 'learning_rate': 1.6349233772646923e-05, 'epoch': 0.3} + 30%|███ | 3617/11952 [2:14:27<13:42:11, 5.92s/it] 30%|███ | 3618/11952 [2:14:33<13:45:37, 5.94s/it] {'loss': 0.5046, 'learning_rate': 1.6347139934522572e-05, 'epoch': 0.3} + 30%|███ | 3618/11952 [2:14:33<13:45:37, 5.94s/it] 30%|███ | 3619/11952 [2:14:39<13:49:26, 5.97s/it] {'loss': 0.5007, 'learning_rate': 1.6345045630290664e-05, 'epoch': 0.3} + 30%|███ | 3619/11952 [2:14:39<13:49:26, 5.97s/it] 30%|███ | 3620/11952 [2:14:45<13:44:04, 5.93s/it] {'loss': 0.4592, 'learning_rate': 1.6342950860105e-05, 'epoch': 0.3} + 30%|███ | 3620/11952 [2:14:45<13:44:04, 5.93s/it] 30%|███ | 3621/11952 [2:14:51<13:34:20, 5.86s/it] {'loss': 0.4886, 'learning_rate': 1.63408556241194e-05, 'epoch': 0.3} + 30%|███ | 3621/11952 [2:14:51<13:34:20, 5.86s/it] 30%|███ | 3622/11952 [2:14:57<13:30:17, 5.84s/it] {'loss': 0.4956, 'learning_rate': 1.633875992248774e-05, 'epoch': 0.3} + 30%|███ | 3622/11952 [2:14:57<13:30:17, 5.84s/it] 30%|███ | 3623/11952 [2:15:03<13:40:28, 5.91s/it] {'loss': 0.4919, 'learning_rate': 1.633666375536392e-05, 'epoch': 0.3} + 30%|███ | 3623/11952 [2:15:03<13:40:28, 5.91s/it] 30%|███ | 3624/11952 [2:15:09<13:37:09, 5.89s/it] {'loss': 0.5073, 'learning_rate': 1.6334567122901862e-05, 'epoch': 0.3} + 30%|███ | 3624/11952 [2:15:09<13:37:09, 5.89s/it] 30%|███ | 3625/11952 [2:15:15<13:37:47, 5.89s/it] {'loss': 0.5198, 'learning_rate': 1.633247002525555e-05, 'epoch': 0.3} + 30%|███ | 3625/11952 [2:15:15<13:37:47, 5.89s/it] 30%|███ | 3626/11952 [2:15:20<13:31:53, 5.85s/it] {'loss': 0.481, 'learning_rate': 1.6330372462578972e-05, 'epoch': 0.3} + 30%|███ | 3626/11952 [2:15:20<13:31:53, 5.85s/it] 30%|███ | 3627/11952 [2:15:26<13:40:29, 5.91s/it] {'loss': 0.4838, 'learning_rate': 1.6328274435026174e-05, 'epoch': 0.3} + 30%|███ | 3627/11952 [2:15:26<13:40:29, 5.91s/it] 30%|███ | 3628/11952 [2:15:32<13:30:47, 5.84s/it] {'loss': 0.4937, 'learning_rate': 1.6326175942751222e-05, 'epoch': 0.3} + 30%|███ | 3628/11952 [2:15:32<13:30:47, 5.84s/it] 30%|███ | 3629/11952 [2:15:38<13:27:08, 5.82s/it] {'loss': 0.4734, 'learning_rate': 1.632407698590822e-05, 'epoch': 0.3} + 30%|███ | 3629/11952 [2:15:38<13:27:08, 5.82s/it] 30%|███ | 3630/11952 [2:15:44<13:22:56, 5.79s/it] {'loss': 0.4866, 'learning_rate': 1.6321977564651313e-05, 'epoch': 0.3} + 30%|███ | 3630/11952 [2:15:44<13:22:56, 5.79s/it] 30%|███ | 3631/11952 [2:15:50<13:32:01, 5.86s/it] {'loss': 0.5065, 'learning_rate': 1.6319877679134662e-05, 'epoch': 0.3} + 30%|███ | 3631/11952 [2:15:50<13:32:01, 5.86s/it] 30%|███ | 3632/11952 [2:15:56<13:36:09, 5.89s/it] {'loss': 0.4771, 'learning_rate': 1.6317777329512485e-05, 'epoch': 0.3} + 30%|███ | 3632/11952 [2:15:56<13:36:09, 5.89s/it] 30%|███ | 3633/11952 [2:16:01<13:33:44, 5.87s/it] {'loss': 0.4991, 'learning_rate': 1.6315676515939015e-05, 'epoch': 0.3} + 30%|███ | 3633/11952 [2:16:01<13:33:44, 5.87s/it] 30%|███ | 3634/11952 [2:16:07<13:39:55, 5.91s/it] {'loss': 0.494, 'learning_rate': 1.6313575238568535e-05, 'epoch': 0.3} + 30%|███ | 3634/11952 [2:16:07<13:39:55, 5.91s/it] 30%|███ | 3635/11952 [2:16:13<13:29:21, 5.84s/it] {'loss': 0.4731, 'learning_rate': 1.6311473497555343e-05, 'epoch': 0.3} + 30%|███ | 3635/11952 [2:16:13<13:29:21, 5.84s/it] 30%|███ | 3636/11952 [2:16:19<13:42:58, 5.94s/it] {'loss': 0.5089, 'learning_rate': 1.6309371293053793e-05, 'epoch': 0.3} + 30%|███ | 3636/11952 [2:16:19<13:42:58, 5.94s/it] 30%|███ | 3637/11952 [2:16:25<13:30:50, 5.85s/it] {'loss': 0.4857, 'learning_rate': 1.630726862521826e-05, 'epoch': 0.3} + 30%|███ | 3637/11952 [2:16:25<13:30:50, 5.85s/it] 30%|███ | 3638/11952 [2:16:31<13:24:11, 5.80s/it] {'loss': 0.4843, 'learning_rate': 1.6305165494203147e-05, 'epoch': 0.3} + 30%|███ | 3638/11952 [2:16:31<13:24:11, 5.80s/it] 30%|███ | 3639/11952 [2:16:37<13:37:54, 5.90s/it] {'loss': 0.5002, 'learning_rate': 1.6303061900162912e-05, 'epoch': 0.3} + 30%|███ | 3639/11952 [2:16:37<13:37:54, 5.90s/it] 30%|███ | 3640/11952 [2:16:42<13:27:13, 5.83s/it] {'loss': 0.4996, 'learning_rate': 1.6300957843252027e-05, 'epoch': 0.3} + 30%|███ | 3640/11952 [2:16:42<13:27:13, 5.83s/it] 30%|███ | 3641/11952 [2:16:48<13:32:20, 5.86s/it] {'loss': 0.4843, 'learning_rate': 1.6298853323625003e-05, 'epoch': 0.3} + 30%|███ | 3641/11952 [2:16:48<13:32:20, 5.86s/it] 30%|███ | 3642/11952 [2:16:54<13:24:47, 5.81s/it] {'loss': 0.491, 'learning_rate': 1.6296748341436386e-05, 'epoch': 0.3} + 30%|███ | 3642/11952 [2:16:54<13:24:47, 5.81s/it] 30%|███ | 3643/11952 [2:17:00<13:15:30, 5.74s/it] {'loss': 0.4923, 'learning_rate': 1.6294642896840768e-05, 'epoch': 0.3} + 30%|███ | 3643/11952 [2:17:00<13:15:30, 5.74s/it] 30%|███ | 3644/11952 [2:17:06<13:28:58, 5.84s/it] {'loss': 0.4955, 'learning_rate': 1.6292536989992754e-05, 'epoch': 0.3} + 30%|███ | 3644/11952 [2:17:06<13:28:58, 5.84s/it] 30%|███ | 3645/11952 [2:17:12<13:49:37, 5.99s/it] {'loss': 0.4928, 'learning_rate': 1.6290430621046994e-05, 'epoch': 0.3} + 30%|███ | 3645/11952 [2:17:12<13:49:37, 5.99s/it] 31%|███ | 3646/11952 [2:17:18<13:34:36, 5.88s/it] {'loss': 0.4971, 'learning_rate': 1.6288323790158175e-05, 'epoch': 0.31} + 31%|███ | 3646/11952 [2:17:18<13:34:36, 5.88s/it] 31%|███ | 3647/11952 [2:17:23<13:32:58, 5.87s/it] {'loss': 0.488, 'learning_rate': 1.6286216497481014e-05, 'epoch': 0.31} + 31%|███ | 3647/11952 [2:17:23<13:32:58, 5.87s/it] 31%|███ | 3648/11952 [2:17:30<13:47:27, 5.98s/it] {'loss': 0.493, 'learning_rate': 1.6284108743170256e-05, 'epoch': 0.31} + 31%|███ | 3648/11952 [2:17:30<13:47:27, 5.98s/it] 31%|███ | 3649/11952 [2:17:36<13:40:03, 5.93s/it] {'loss': 0.4973, 'learning_rate': 1.628200052738069e-05, 'epoch': 0.31} + 31%|███ | 3649/11952 [2:17:36<13:40:03, 5.93s/it]3 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... +06 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... + 31%|███ | 3650/11952 [2:17:41<13:32:06, 5.87s/it] {'loss': 0.4951, 'learning_rate': 1.6279891850267134e-05, 'epoch': 0.31} + 31%|███ | 3650/11952 [2:17:41<13:32:06, 5.87s/it] 31%|███ | 3651/11952 [2:17:47<13:35:28, 5.89s/it] {'loss': 0.4991, 'learning_rate': 1.6277782711984446e-05, 'epoch': 0.31} + 31%|███ | 3651/11952 [2:17:47<13:35:28, 5.89s/it] 31%|███ | 3652/11952 [2:17:53<13:23:46, 5.81s/it] {'loss': 0.4884, 'learning_rate': 1.62756731126875e-05, 'epoch': 0.31} + 31%|███ | 3652/11952 [2:17:53<13:23:46, 5.81s/it] 31%|███ | 3653/11952 [2:17:58<13:15:07, 5.75s/it] {'loss': 0.4774, 'learning_rate': 1.6273563052531227e-05, 'epoch': 0.31} + 31%|███ | 3653/11952 [2:17:58<13:15:07, 5.75s/it] 31%|███ | 3654/11952 [2:18:04<13:13:39, 5.74s/it] {'loss': 0.4959, 'learning_rate': 1.6271452531670577e-05, 'epoch': 0.31} + 31%|███ | 3654/11952 [2:18:04<13:13:39, 5.74s/it] 31%|███ | 3655/11952 [2:18:10<13:34:04, 5.89s/it] {'loss': 0.4922, 'learning_rate': 1.6269341550260537e-05, 'epoch': 0.31} + 31%|███ | 3655/11952 [2:18:10<13:34:04, 5.89s/it] 31%|███ | 3656/11952 [2:18:16<13:40:43, 5.94s/it] {'loss': 0.5079, 'learning_rate': 1.6267230108456126e-05, 'epoch': 0.31} + 31%|███ | 3656/11952 [2:18:16<13:40:43, 5.94s/it] 31%|███ | 3657/11952 [2:18:22<13:40:58, 5.94s/it] {'loss': 0.482, 'learning_rate': 1.6265118206412412e-05, 'epoch': 0.31} + 31%|███ | 3657/11952 [2:18:22<13:40:58, 5.94s/it] 31%|███ | 3658/11952 [2:18:28<13:31:23, 5.87s/it] {'loss': 0.4812, 'learning_rate': 1.6263005844284468e-05, 'epoch': 0.31} + 31%|███ | 3658/11952 [2:18:28<13:31:23, 5.87s/it] 31%|███ | 3659/11952 [2:18:34<13:23:12, 5.81s/it] {'loss': 0.521, 'learning_rate': 1.6260893022227425e-05, 'epoch': 0.31} + 31%|███ | 3659/11952 [2:18:34<13:23:12, 5.81s/it] 31%|███ | 3660/11952 [2:18:40<13:31:21, 5.87s/it] {'loss': 0.4847, 'learning_rate': 1.6258779740396443e-05, 'epoch': 0.31} + 31%|███ | 3660/11952 [2:18:40<13:31:21, 5.87s/it] 31%|███ | 3661/11952 [2:18:45<13:24:26, 5.82s/it] {'loss': 0.499, 'learning_rate': 1.6256665998946708e-05, 'epoch': 0.31} + 31%|███ | 3661/11952 [2:18:45<13:24:26, 5.82s/it] 31%|███ | 3662/11952 [2:18:51<13:32:28, 5.88s/it] {'loss': 0.4978, 'learning_rate': 1.6254551798033444e-05, 'epoch': 0.31} + 31%|███ | 3662/11952 [2:18:51<13:32:28, 5.88s/it] 31%|███ | 3663/11952 [2:18:57<13:30:41, 5.87s/it] {'loss': 0.4887, 'learning_rate': 1.6252437137811913e-05, 'epoch': 0.31} + 31%|███ | 3663/11952 [2:18:57<13:30:41, 5.87s/it] 31%|███ | 3664/11952 [2:19:03<13:33:46, 5.89s/it] {'loss': 0.4927, 'learning_rate': 1.62503220184374e-05, 'epoch': 0.31} + 31%|███ | 3664/11952 [2:19:03<13:33:46, 5.89s/it] 31%|███ | 3665/11952 [2:19:09<13:28:57, 5.86s/it] {'loss': 0.4999, 'learning_rate': 1.624820644006524e-05, 'epoch': 0.31} + 31%|███ | 3665/11952 [2:19:09<13:28:57, 5.86s/it] 31%|███ | 3666/11952 [2:19:15<13:31:43, 5.88s/it] {'loss': 0.5203, 'learning_rate': 1.6246090402850783e-05, 'epoch': 0.31} + 31%|███ | 3666/11952 [2:19:15<13:31:43, 5.88s/it] 31%|███ | 3667/11952 [2:19:21<13:38:27, 5.93s/it] {'loss': 0.4929, 'learning_rate': 1.6243973906949434e-05, 'epoch': 0.31} + 31%|███ | 3667/11952 [2:19:21<13:38:27, 5.93s/it] 31%|███ | 3668/11952 [2:19:27<13:28:38, 5.86s/it] {'loss': 0.4796, 'learning_rate': 1.6241856952516604e-05, 'epoch': 0.31} + 31%|███ | 3668/11952 [2:19:27<13:28:38, 5.86s/it] 31%|███ | 3669/11952 [2:19:33<13:28:04, 5.85s/it] {'loss': 0.4937, 'learning_rate': 1.623973953970776e-05, 'epoch': 0.31} + 31%|███ | 3669/11952 [2:19:33<13:28:04, 5.85s/it] 31%|███ | 3670/11952 [2:19:39<13:44:25, 5.97s/it] {'loss': 0.4927, 'learning_rate': 1.6237621668678406e-05, 'epoch': 0.31} + 31%|███ | 3670/11952 [2:19:39<13:44:25, 5.97s/it] 31%|███ | 3671/11952 [2:19:45<13:39:58, 5.94s/it] {'loss': 0.4964, 'learning_rate': 1.6235503339584052e-05, 'epoch': 0.31} + 31%|███ | 3671/11952 [2:19:45<13:39:58, 5.94s/it] 31%|███ | 3672/11952 [2:19:50<13:24:57, 5.83s/it] {'loss': 0.4833, 'learning_rate': 1.6233384552580272e-05, 'epoch': 0.31} + 31%|███ | 3672/11952 [2:19:50<13:24:57, 5.83s/it] 31%|███ | 3673/11952 [2:19:56<13:19:38, 5.80s/it] {'loss': 0.4704, 'learning_rate': 1.6231265307822658e-05, 'epoch': 0.31} + 31%|███ | 3673/11952 [2:19:56<13:19:38, 5.80s/it] 31%|███ | 3674/11952 [2:20:02<13:10:34, 5.73s/it] {'loss': 0.5002, 'learning_rate': 1.622914560546684e-05, 'epoch': 0.31} + 31%|███ | 3674/11952 [2:20:02<13:10:34, 5.73s/it] 31%|███ | 3675/11952 [2:20:08<13:29:24, 5.87s/it] {'loss': 0.4905, 'learning_rate': 1.6227025445668473e-05, 'epoch': 0.31} + 31%|███ | 3675/11952 [2:20:08<13:29:24, 5.87s/it] 31%|███ | 3676/11952 [2:20:14<13:25:21, 5.84s/it] {'loss': 0.4894, 'learning_rate': 1.622490482858326e-05, 'epoch': 0.31} + 31%|███ | 3676/11952 [2:20:14<13:25:21, 5.84s/it] 31%|███ | 3677/11952 [2:20:19<13:26:05, 5.84s/it] {'loss': 0.4877, 'learning_rate': 1.6222783754366926e-05, 'epoch': 0.31} + 31%|███ | 3677/11952 [2:20:19<13:26:05, 5.84s/it] 31%|███ | 3678/11952 [2:20:25<13:24:46, 5.84s/it] {'loss': 0.4793, 'learning_rate': 1.6220662223175233e-05, 'epoch': 0.31} + 31%|███ | 3678/11952 [2:20:25<13:24:46, 5.84s/it] 31%|███ | 3679/11952 [2:20:31<13:40:05, 5.95s/it] {'loss': 0.4839, 'learning_rate': 1.6218540235163983e-05, 'epoch': 0.31} + 31%|███ | 3679/11952 [2:20:31<13:40:05, 5.95s/it] 31%|███ | 3680/11952 [2:20:37<13:37:08, 5.93s/it] {'loss': 0.4906, 'learning_rate': 1.6216417790489005e-05, 'epoch': 0.31} + 31%|███ | 3680/11952 [2:20:37<13:37:08, 5.93s/it] 31%|███ | 3681/11952 [2:20:43<13:32:39, 5.90s/it] {'loss': 0.4857, 'learning_rate': 1.6214294889306158e-05, 'epoch': 0.31} + 31%|███ | 3681/11952 [2:20:43<13:32:39, 5.90s/it] 31%|███ | 3682/11952 [2:20:49<13:37:05, 5.93s/it] {'loss': 0.4932, 'learning_rate': 1.621217153177134e-05, 'epoch': 0.31} + 31%|███ | 3682/11952 [2:20:49<13:37:05, 5.93s/it] 31%|███ | 3683/11952 [2:20:55<13:36:27, 5.92s/it] {'loss': 0.4943, 'learning_rate': 1.621004771804049e-05, 'epoch': 0.31} + 31%|███ | 3683/11952 [2:20:55<13:36:27, 5.92s/it] 31%|███ | 3684/11952 [2:21:01<13:28:58, 5.87s/it] {'loss': 0.517, 'learning_rate': 1.620792344826956e-05, 'epoch': 0.31} + 31%|███ | 3684/11952 [2:21:01<13:28:58, 5.87s/it] 31%|███ | 3685/11952 [2:21:06<13:19:38, 5.80s/it] {'loss': 0.4828, 'learning_rate': 1.6205798722614552e-05, 'epoch': 0.31} + 31%|███ | 3685/11952 [2:21:06<13:19:38, 5.80s/it] 31%|███ | 3686/11952 [2:21:12<13:19:44, 5.81s/it] {'loss': 0.473, 'learning_rate': 1.6203673541231497e-05, 'epoch': 0.31} + 31%|███ | 3686/11952 [2:21:12<13:19:44, 5.81s/it] 31%|███ | 3687/11952 [2:21:18<13:15:38, 5.78s/it] {'loss': 0.4931, 'learning_rate': 1.6201547904276463e-05, 'epoch': 0.31} + 31%|███ | 3687/11952 [2:21:18<13:15:38, 5.78s/it] 31%|███ | 3688/11952 [2:21:24<13:17:54, 5.79s/it] {'loss': 0.508, 'learning_rate': 1.6199421811905542e-05, 'epoch': 0.31} + 31%|███ | 3688/11952 [2:21:24<13:17:54, 5.79s/it] 31%|███ | 3689/11952 [2:21:30<13:37:33, 5.94s/it] {'loss': 0.4883, 'learning_rate': 1.619729526427487e-05, 'epoch': 0.31} + 31%|███ | 3689/11952 [2:21:30<13:37:33, 5.94s/it] 31%|███ | 3690/11952 [2:21:36<13:28:54, 5.87s/it] {'loss': 0.4819, 'learning_rate': 1.6195168261540612e-05, 'epoch': 0.31} + 31%|███ | 3690/11952 [2:21:36<13:28:54, 5.87s/it] 31%|███ | 3691/11952 [2:21:41<13:23:28, 5.84s/it] {'loss': 0.5097, 'learning_rate': 1.6193040803858965e-05, 'epoch': 0.31} + 31%|███ | 3691/11952 [2:21:41<13:23:28, 5.84s/it] 31%|███ | 3692/11952 [2:21:47<13:14:30, 5.77s/it] {'loss': 0.5071, 'learning_rate': 1.6190912891386154e-05, 'epoch': 0.31} + 31%|███ | 3692/11952 [2:21:47<13:14:30, 5.77s/it] 31%|███ | 3693/11952 [2:21:53<13:06:05, 5.71s/it] {'loss': 0.4829, 'learning_rate': 1.6188784524278455e-05, 'epoch': 0.31} + 31%|███ | 3693/11952 [2:21:53<13:06:05, 5.71s/it] 31%|███ | 3694/11952 [2:21:59<13:23:34, 5.84s/it] {'loss': 0.4916, 'learning_rate': 1.6186655702692162e-05, 'epoch': 0.31} + 31%|███ | 3694/11952 [2:21:59<13:23:34, 5.84s/it] 31%|███ | 3695/11952 [2:22:05<13:24:19, 5.84s/it] {'loss': 0.5002, 'learning_rate': 1.6184526426783607e-05, 'epoch': 0.31} + 31%|███ | 3695/11952 [2:22:05<13:24:19, 5.84s/it] 31%|███ | 3696/11952 [2:22:10<13:22:55, 5.84s/it] {'loss': 0.4863, 'learning_rate': 1.618239669670915e-05, 'epoch': 0.31} + 31%|███ | 3696/11952 [2:22:10<13:22:55, 5.84s/it] 31%|███ | 3697/11952 [2:22:16<13:28:01, 5.87s/it] {'loss': 0.5061, 'learning_rate': 1.61802665126252e-05, 'epoch': 0.31} + 31%|███ | 3697/11952 [2:22:16<13:28:01, 5.87s/it] 31%|███ | 3698/11952 [2:22:22<13:28:12, 5.88s/it] {'loss': 0.4785, 'learning_rate': 1.6178135874688183e-05, 'epoch': 0.31} + 31%|███ | 3698/11952 [2:22:22<13:28:12, 5.88s/it] 31%|███ | 3699/11952 [2:22:28<13:30:02, 5.89s/it] {'loss': 0.5046, 'learning_rate': 1.6176004783054556e-05, 'epoch': 0.31} + 31%|███ | 3699/11952 [2:22:28<13:30:02, 5.89s/it]3 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend...7 + AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... +06 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... + 31%|███ | 3700/11952 [2:22:34<13:19:49, 5.82s/it] {'loss': 0.5005, 'learning_rate': 1.6173873237880832e-05, 'epoch': 0.31} + 31%|███ | 3700/11952 [2:22:34<13:19:49, 5.82s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-3700/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-3700/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/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( + 31%|███ | 3701/11952 [2:23:07<32:04:06, 13.99s/it] {'loss': 0.4856, 'learning_rate': 1.6171741239323537e-05, 'epoch': 0.31} + 31%|███ | 3701/11952 [2:23:07<32:04:06, 13.99s/it] 31%|███ | 3702/11952 [2:23:13<26:33:20, 11.59s/it] {'loss': 0.5233, 'learning_rate': 1.6169608787539234e-05, 'epoch': 0.31} + 31%|███ | 3702/11952 [2:23:13<26:33:20, 11.59s/it] 31%|███ | 3703/11952 [2:23:19<22:40:12, 9.89s/it] {'loss': 0.4767, 'learning_rate': 1.6167475882684522e-05, 'epoch': 0.31} + 31%|███ | 3703/11952 [2:23:19<22:40:12, 9.89s/it] 31%|███ | 3704/11952 [2:23:25<19:53:32, 8.68s/it] {'loss': 0.5088, 'learning_rate': 1.6165342524916035e-05, 'epoch': 0.31} + 31%|███ | 3704/11952 [2:23:25<19:53:32, 8.68s/it] 31%|███ | 3705/11952 [2:23:31<18:02:41, 7.88s/it] {'loss': 0.5114, 'learning_rate': 1.6163208714390437e-05, 'epoch': 0.31} + 31%|███ | 3705/11952 [2:23:31<18:02:41, 7.88s/it] 31%|███ | 3706/11952 [2:23:37<16:38:19, 7.26s/it] {'loss': 0.503, 'learning_rate': 1.6161074451264425e-05, 'epoch': 0.31} + 31%|███ | 3706/11952 [2:23:37<16:38:19, 7.26s/it] 31%|███ | 3707/11952 [2:23:43<15:44:00, 6.87s/it] {'loss': 0.4942, 'learning_rate': 1.615893973569473e-05, 'epoch': 0.31} + 31%|███ | 3707/11952 [2:23:43<15:44:00, 6.87s/it] 31%|███ | 3708/11952 [2:23:48<14:57:44, 6.53s/it] {'loss': 0.4998, 'learning_rate': 1.615680456783812e-05, 'epoch': 0.31} + 31%|███ | 3708/11952 [2:23:48<14:57:44, 6.53s/it] 31%|███ | 3709/11952 [2:23:54<14:21:18, 6.27s/it] {'loss': 0.5169, 'learning_rate': 1.615466894785139e-05, 'epoch': 0.31} + 31%|███ | 3709/11952 [2:23:54<14:21:18, 6.27s/it] 31%|███ | 3710/11952 [2:24:00<13:53:26, 6.07s/it] {'loss': 0.4753, 'learning_rate': 1.6152532875891372e-05, 'epoch': 0.31} + 31%|███ | 3710/11952 [2:24:00<13:53:26, 6.07s/it] 31%|███ | 3711/11952 [2:24:05<13:38:39, 5.96s/it] {'loss': 0.481, 'learning_rate': 1.6150396352114926e-05, 'epoch': 0.31} + 31%|███ | 3711/11952 [2:24:05<13:38:39, 5.96s/it] 31%|███ | 3712/11952 [2:24:11<13:25:37, 5.87s/it] {'loss': 0.4966, 'learning_rate': 1.6148259376678957e-05, 'epoch': 0.31} + 31%|███ | 3712/11952 [2:24:11<13:25:37, 5.87s/it] 31%|███ | 3713/11952 [2:24:17<13:27:08, 5.88s/it] {'loss': 0.5167, 'learning_rate': 1.6146121949740393e-05, 'epoch': 0.31} + 31%|███ | 3713/11952 [2:24:17<13:27:08, 5.88s/it] 31%|███ | 3714/11952 [2:24:23<13:37:45, 5.96s/it] {'loss': 0.4961, 'learning_rate': 1.6143984071456197e-05, 'epoch': 0.31} + 31%|███ | 3714/11952 [2:24:23<13:37:45, 5.96s/it] 31%|███ | 3715/11952 [2:24:29<13:43:37, 6.00s/it] {'loss': 0.5012, 'learning_rate': 1.614184574198336e-05, 'epoch': 0.31} + 31%|███ | 3715/11952 [2:24:29<13:43:37, 6.00s/it] 31%|███ | 3716/11952 [2:24:35<13:44:29, 6.01s/it] {'loss': 0.4894, 'learning_rate': 1.613970696147892e-05, 'epoch': 0.31} + 31%|███ | 3716/11952 [2:24:35<13:44:29, 6.01s/it] 31%|███ | 3717/11952 [2:24:41<13:41:49, 5.99s/it] {'loss': 0.4937, 'learning_rate': 1.613756773009994e-05, 'epoch': 0.31} + 31%|███ | 3717/11952 [2:24:41<13:41:49, 5.99s/it] 31%|███ | 3718/11952 [2:24:47<13:28:47, 5.89s/it] {'loss': 0.4853, 'learning_rate': 1.6135428048003513e-05, 'epoch': 0.31} + 31%|███ | 3718/11952 [2:24:47<13:28:47, 5.89s/it] 31%|███ | 3719/11952 [2:24:52<13:18:18, 5.82s/it] {'loss': 0.5156, 'learning_rate': 1.6133287915346772e-05, 'epoch': 0.31} + 31%|███ | 3719/11952 [2:24:52<13:18:18, 5.82s/it] 31%|███ | 3720/11952 [2:24:58<13:19:55, 5.83s/it] {'loss': 0.4906, 'learning_rate': 1.6131147332286872e-05, 'epoch': 0.31} + 31%|███ | 3720/11952 [2:24:58<13:19:55, 5.83s/it] 31%|███ | 3721/11952 [2:25:04<13:12:46, 5.78s/it] {'loss': 0.4942, 'learning_rate': 1.6129006298981015e-05, 'epoch': 0.31} + 31%|███ | 3721/11952 [2:25:04<13:12:46, 5.78s/it] 31%|███ | 3722/11952 [2:25:09<13:07:10, 5.74s/it] {'loss': 0.5072, 'learning_rate': 1.6126864815586427e-05, 'epoch': 0.31} + 31%|███ | 3722/11952 [2:25:09<13:07:10, 5.74s/it] 31%|███ | 3723/11952 [2:25:16<13:24:43, 5.87s/it] {'loss': 0.5006, 'learning_rate': 1.6124722882260372e-05, 'epoch': 0.31} + 31%|███ | 3723/11952 [2:25:16<13:24:43, 5.87s/it] 31%|███ | 3724/11952 [2:25:22<13:27:36, 5.89s/it] {'loss': 0.4895, 'learning_rate': 1.6122580499160144e-05, 'epoch': 0.31} + 31%|███ | 3724/11952 [2:25:22<13:27:36, 5.89s/it] 31%|███ | 3725/11952 [2:25:27<13:25:19, 5.87s/it] {'loss': 0.5041, 'learning_rate': 1.6120437666443067e-05, 'epoch': 0.31} + 31%|███ | 3725/11952 [2:25:27<13:25:19, 5.87s/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%|███ | 3726/11952 [2:25:33<13:18:55, 5.83s/it] {'loss': 0.4864, 'learning_rate': 1.6118294384266506e-05, 'epoch': 0.31} + 31%|███ | 3726/11952 [2:25:33<13:18:55, 5.83s/it] 31%|███ | 3727/11952 [2:25:39<13:18:27, 5.82s/it] {'loss': 0.4983, 'learning_rate': 1.6116150652787852e-05, 'epoch': 0.31} + 31%|███ | 3727/11952 [2:25:39<13:18:27, 5.82s/it] 31%|███ | 3728/11952 [2:25:45<13:18:38, 5.83s/it] {'loss': 0.5044, 'learning_rate': 1.6114006472164535e-05, 'epoch': 0.31} + 31%|███ | 3728/11952 [2:25:45<13:18:38, 5.83s/it] 31%|███ | 3729/11952 [2:25:51<13:22:26, 5.86s/it] {'loss': 0.4779, 'learning_rate': 1.6111861842554014e-05, 'epoch': 0.31} + 31%|███ | 3729/11952 [2:25:51<13:22:26, 5.86s/it] 31%|███ | 3730/11952 [2:25:57<13:21:10, 5.85s/it] {'loss': 0.4895, 'learning_rate': 1.6109716764113778e-05, 'epoch': 0.31} + 31%|███ | 3730/11952 [2:25:57<13:21:10, 5.85s/it] 31%|███ | 3731/11952 [2:26:02<13:17:08, 5.82s/it] {'loss': 0.4795, 'learning_rate': 1.6107571237001356e-05, 'epoch': 0.31} + 31%|███ | 3731/11952 [2:26:02<13:17:08, 5.82s/it] 31%|███ | 3732/11952 [2:26:08<13:16:36, 5.81s/it] {'loss': 0.4991, 'learning_rate': 1.6105425261374305e-05, 'epoch': 0.31} + 31%|███ | 3732/11952 [2:26:08<13:16:36, 5.81s/it] 31%|███ | 3733/11952 [2:26:14<13:07:52, 5.75s/it] {'loss': 0.4792, 'learning_rate': 1.6103278837390218e-05, 'epoch': 0.31} + 31%|███ | 3733/11952 [2:26:14<13:07:52, 5.75s/it] 31%|███ | 3734/11952 [2:26:20<13:18:08, 5.83s/it] {'loss': 0.4891, 'learning_rate': 1.6101131965206714e-05, 'epoch': 0.31} + 31%|███ | 3734/11952 [2:26:20<13:18:08, 5.83s/it] 31%|███▏ | 3735/11952 [2:26:26<13:31:31, 5.93s/it] {'loss': 0.5137, 'learning_rate': 1.6098984644981463e-05, 'epoch': 0.31} + 31%|███▏ | 3735/11952 [2:26:26<13:31:31, 5.93s/it] 31%|███▏ | 3736/11952 [2:26:32<13:40:33, 5.99s/it] {'loss': 0.5098, 'learning_rate': 1.6096836876872143e-05, 'epoch': 0.31} + 31%|███▏ | 3736/11952 [2:26:32<13:40:33, 5.99s/it] 31%|███▏ | 3737/11952 [2:26:38<13:30:23, 5.92s/it] {'loss': 0.5053, 'learning_rate': 1.6094688661036483e-05, 'epoch': 0.31} + 31%|███▏ | 3737/11952 [2:26:38<13:30:23, 5.92s/it] 31%|███▏ | 3738/11952 [2:26:43<13:19:02, 5.84s/it] {'loss': 0.4915, 'learning_rate': 1.6092539997632236e-05, 'epoch': 0.31} + 31%|███▏ | 3738/11952 [2:26:43<13:19:02, 5.84s/it] 31%|███▏ | 3739/11952 [2:26:49<13:17:26, 5.83s/it] {'loss': 0.4916, 'learning_rate': 1.609039088681719e-05, 'epoch': 0.31} + 31%|███▏ | 3739/11952 [2:26:49<13:17:26, 5.83s/it] 31%|███▏ | 3740/11952 [2:26:55<13:12:23, 5.79s/it] {'loss': 0.484, 'learning_rate': 1.6088241328749172e-05, 'epoch': 0.31} + 31%|███▏ | 3740/11952 [2:26:55<13:12:23, 5.79s/it] 31%|███▏ | 3741/11952 [2:27:00<13:02:53, 5.72s/it] {'loss': 0.5012, 'learning_rate': 1.6086091323586034e-05, 'epoch': 0.31} + 31%|███▏ | 3741/11952 [2:27:00<13:02:53, 5.72s/it] 31%|███▏ | 3742/11952 [2:27:06<12:58:37, 5.69s/it] {'loss': 0.4669, 'learning_rate': 1.6083940871485663e-05, 'epoch': 0.31} + 31%|███▏ | 3742/11952 [2:27:06<12:58:37, 5.69s/it] 31%|███▏ | 3743/11952 [2:27:13<13:28:52, 5.91s/it] {'loss': 0.4923, 'learning_rate': 1.608178997260598e-05, 'epoch': 0.31} + 31%|███▏ | 3743/11952 [2:27:13<13:28:52, 5.91s/it] 31%|███▏ | 3744/11952 [2:27:18<13:30:19, 5.92s/it] {'loss': 0.4927, 'learning_rate': 1.6079638627104937e-05, 'epoch': 0.31} + 31%|███▏ | 3744/11952 [2:27:18<13:30:19, 5.92s/it] 31%|███▏ | 3745/11952 [2:27:24<13:31:40, 5.93s/it] {'loss': 0.4755, 'learning_rate': 1.6077486835140518e-05, 'epoch': 0.31} + 31%|███▏ | 3745/11952 [2:27:24<13:31:40, 5.93s/it] 31%|███▏ | 3746/11952 [2:27:30<13:18:39, 5.84s/it] {'loss': 0.4855, 'learning_rate': 1.6075334596870746e-05, 'epoch': 0.31} + 31%|███▏ | 3746/11952 [2:27:30<13:18:39, 5.84s/it] 31%|███▏ | 3747/11952 [2:27:35<13:02:28, 5.72s/it] {'loss': 0.4979, 'learning_rate': 1.607318191245367e-05, 'epoch': 0.31} + 31%|███▏ | 3747/11952 [2:27:35<13:02:28, 5.72s/it] 31%|███▏ | 3748/11952 [2:27:41<13:05:53, 5.75s/it] {'loss': 0.4754, 'learning_rate': 1.607102878204738e-05, 'epoch': 0.31} + 31%|███▏ | 3748/11952 [2:27:41<13:05:53, 5.75s/it] 31%|███▏ | 3749/11952 [2:27:47<13:21:33, 5.86s/it] {'loss': 0.5086, 'learning_rate': 1.6068875205809978e-05, 'epoch': 0.31} + 31%|███▏ | 3749/11952 [2:27:47<13:21:33, 5.86s/it]3 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +7 5AutoResumeHook: Checking whether to suspend...2 + 6 AutoResumeHook: Checking whether to suspend...0 AutoResumeHook: Checking whether to suspend... +AutoResumeHook: Checking whether to suspend... + + AutoResumeHook: Checking whether to suspend... + 31%|███▏ | 3750/11952 [2:27:53<13:26:21, 5.90s/it] {'loss': 0.5113, 'learning_rate': 1.606672118389963e-05, 'epoch': 0.31} + 31%|███▏ | 3750/11952 [2:27:53<13:26:21, 5.90s/it] 31%|███▏ | 3751/11952 [2:27:59<13:30:15, 5.93s/it] {'loss': 0.5014, 'learning_rate': 1.6064566716474506e-05, 'epoch': 0.31} + 31%|███▏ | 3751/11952 [2:27:59<13:30:15, 5.93s/it] 31%|███▏ | 3752/11952 [2:28:05<13:31:20, 5.94s/it] {'loss': 0.4899, 'learning_rate': 1.606241180369283e-05, 'epoch': 0.31} + 31%|███▏ | 3752/11952 [2:28:05<13:31:20, 5.94s/it] 31%|███▏ | 3753/11952 [2:28:11<13:29:01, 5.92s/it] {'loss': 0.5102, 'learning_rate': 1.606025644571285e-05, 'epoch': 0.31} + 31%|███▏ | 3753/11952 [2:28:11<13:29:01, 5.92s/it] 31%|███▏ | 3754/11952 [2:28:17<13:31:02, 5.94s/it] {'loss': 0.4875, 'learning_rate': 1.6058100642692837e-05, 'epoch': 0.31} + 31%|███▏ | 3754/11952 [2:28:17<13:31:02, 5.94s/it] 31%|███▏ | 3755/11952 [2:28:23<13:39:57, 6.00s/it] {'loss': 0.5025, 'learning_rate': 1.6055944394791113e-05, 'epoch': 0.31} + 31%|███▏ | 3755/11952 [2:28:23<13:39:57, 6.00s/it] 31%|███▏ | 3756/11952 [2:28:29<13:34:19, 5.96s/it] {'loss': 0.4748, 'learning_rate': 1.605378770216602e-05, 'epoch': 0.31} + 31%|███▏ | 3756/11952 [2:28:29<13:34:19, 5.96s/it] 31%|███▏ | 3757/11952 [2:28:35<13:17:01, 5.84s/it] {'loss': 0.4893, 'learning_rate': 1.605163056497594e-05, 'epoch': 0.31} + 31%|███▏ | 3757/11952 [2:28:35<13:17:01, 5.84s/it] 31%|███▏ | 3758/11952 [2:28:41<13:29:15, 5.93s/it] {'loss': 0.4999, 'learning_rate': 1.6049472983379285e-05, 'epoch': 0.31} + 31%|███▏ | 3758/11952 [2:28:41<13:29:15, 5.93s/it] 31%|███▏ | 3759/11952 [2:28:47<13:26:29, 5.91s/it] {'loss': 0.5149, 'learning_rate': 1.6047314957534487e-05, 'epoch': 0.31} + 31%|███▏ | 3759/11952 [2:28:47<13:26:29, 5.91s/it] 31%|███▏ | 3760/11952 [2:28:52<13:17:05, 5.84s/it] {'loss': 0.4722, 'learning_rate': 1.604515648760004e-05, 'epoch': 0.31} + 31%|███▏ | 3760/11952 [2:28:52<13:17:05, 5.84s/it] 31%|███▏ | 3761/11952 [2:28:58<13:19:21, 5.86s/it] {'loss': 0.5037, 'learning_rate': 1.6042997573734437e-05, 'epoch': 0.31} + 31%|███▏ | 3761/11952 [2:28:58<13:19:21, 5.86s/it] 31%|███▏ | 3762/11952 [2:29:04<13:15:58, 5.83s/it] {'loss': 0.4684, 'learning_rate': 1.6040838216096233e-05, 'epoch': 0.31} + 31%|███▏ | 3762/11952 [2:29:04<13:15:58, 5.83s/it] 31%|███▏ | 3763/11952 [2:29:10<13:10:31, 5.79s/it] {'loss': 0.5232, 'learning_rate': 1.6038678414843994e-05, 'epoch': 0.31} + 31%|███▏ | 3763/11952 [2:29:10<13:10:31, 5.79s/it] 31%|███▏ | 3764/11952 [2:29:16<13:15:55, 5.83s/it] {'loss': 0.4807, 'learning_rate': 1.6036518170136326e-05, 'epoch': 0.31} + 31%|███▏ | 3764/11952 [2:29:16<13:15:55, 5.83s/it] 32%|███▏ | 3765/11952 [2:29:22<13:14:33, 5.82s/it] {'loss': 0.4972, 'learning_rate': 1.603435748213187e-05, 'epoch': 0.31} + 32%|███▏ | 3765/11952 [2:29:22<13:14:33, 5.82s/it] 32%|███▏ | 3766/11952 [2:29:27<13:07:41, 5.77s/it] {'loss': 0.4843, 'learning_rate': 1.6032196350989306e-05, 'epoch': 0.32} + 32%|███▏ | 3766/11952 [2:29:27<13:07:41, 5.77s/it] 32%|███▏ | 3767/11952 [2:29:33<13:19:58, 5.86s/it] {'loss': 0.4668, 'learning_rate': 1.603003477686733e-05, 'epoch': 0.32} + 32%|███▏ | 3767/11952 [2:29:33<13:19:58, 5.86s/it] 32%|███▏ | 3768/11952 [2:29:39<13:07:34, 5.77s/it] {'loss': 0.4949, 'learning_rate': 1.6027872759924678e-05, 'epoch': 0.32} + 32%|███▏ | 3768/11952 [2:29:39<13:07:34, 5.77s/it] 32%|███▏ | 3769/11952 [2:29:44<13:02:16, 5.74s/it] {'loss': 0.4948, 'learning_rate': 1.6025710300320124e-05, 'epoch': 0.32} + 32%|███▏ | 3769/11952 [2:29:45<13:02:16, 5.74s/it] 32%|███▏ | 3770/11952 [2:29:50<13:00:40, 5.72s/it] {'loss': 0.4746, 'learning_rate': 1.6023547398212467e-05, 'epoch': 0.32} + 32%|███▏ | 3770/11952 [2:29:50<13:00:40, 5.72s/it] 32%|███▏ | 3771/11952 [2:29:56<12:55:02, 5.68s/it] {'loss': 0.476, 'learning_rate': 1.6021384053760546e-05, 'epoch': 0.32} + 32%|███▏ | 3771/11952 [2:29:56<12:55:02, 5.68s/it] 32%|███▏ | 3772/11952 [2:30:02<13:00:42, 5.73s/it] {'loss': 0.4951, 'learning_rate': 1.6019220267123223e-05, 'epoch': 0.32} + 32%|███▏ | 3772/11952 [2:30:02<13:00:42, 5.73s/it] 32%|███▏ | 3773/11952 [2:30:07<13:00:17, 5.72s/it] {'loss': 0.4662, 'learning_rate': 1.60170560384594e-05, 'epoch': 0.32} + 32%|███▏ | 3773/11952 [2:30:07<13:00:17, 5.72s/it] 32%|███▏ | 3774/11952 [2:30:13<13:06:31, 5.77s/it] {'loss': 0.4972, 'learning_rate': 1.601489136792801e-05, 'epoch': 0.32} + 32%|███▏ | 3774/11952 [2:30:13<13:06:31, 5.77s/it] 32%|███▏ | 3775/11952 [2:30:19<13:03:35, 5.75s/it] {'loss': 0.4956, 'learning_rate': 1.6012726255688013e-05, 'epoch': 0.32} + 32%|███▏ | 3775/11952 [2:30:19<13:03:35, 5.75s/it] 32%|███▏ | 3776/11952 [2:30:25<13:11:30, 5.81s/it] {'loss': 0.4779, 'learning_rate': 1.6010560701898405e-05, 'epoch': 0.32} + 32%|███▏ | 3776/11952 [2:30:25<13:11:30, 5.81s/it] 32%|███▏ | 3777/11952 [2:30:31<13:22:41, 5.89s/it] {'loss': 0.5058, 'learning_rate': 1.6008394706718224e-05, 'epoch': 0.32} + 32%|███▏ | 3777/11952 [2:30:31<13:22:41, 5.89s/it] 32%|███▏ | 3778/11952 [2:30:37<13:26:14, 5.92s/it] {'loss': 0.5015, 'learning_rate': 1.6006228270306526e-05, 'epoch': 0.32} + 32%|███▏ | 3778/11952 [2:30:37<13:26:14, 5.92s/it] 32%|███▏ | 3779/11952 [2:30:43<13:12:51, 5.82s/it] {'loss': 0.4791, 'learning_rate': 1.6004061392822407e-05, 'epoch': 0.32} + 32%|███▏ | 3779/11952 [2:30:43<13:12:51, 5.82s/it] 32%|███▏ | 3780/11952 [2:30:48<13:14:45, 5.84s/it] {'loss': 0.4736, 'learning_rate': 1.6001894074424987e-05, 'epoch': 0.32} + 32%|███▏ | 3780/11952 [2:30:48<13:14:45, 5.84s/it] 32%|███▏ | 3781/11952 [2:30:54<13:14:39, 5.84s/it] {'loss': 0.4803, 'learning_rate': 1.5999726315273435e-05, 'epoch': 0.32} + 32%|███▏ | 3781/11952 [2:30:54<13:14:39, 5.84s/it] 32%|███▏ | 3782/11952 [2:31:00<13:22:00, 5.89s/it] {'loss': 0.5038, 'learning_rate': 1.599755811552693e-05, 'epoch': 0.32} + 32%|███▏ | 3782/11952 [2:31:00<13:22:00, 5.89s/it] 32%|███▏ | 3783/11952 [2:31:06<13:20:17, 5.88s/it] {'loss': 0.4888, 'learning_rate': 1.5995389475344715e-05, 'epoch': 0.32} + 32%|███▏ | 3783/11952 [2:31:06<13:20:17, 5.88s/it] 32%|███▏ | 3784/11952 [2:31:12<13:13:57, 5.83s/it] {'loss': 0.4943, 'learning_rate': 1.5993220394886024e-05, 'epoch': 0.32} + 32%|███▏ | 3784/11952 [2:31:12<13:13:57, 5.83s/it] 32%|███▏ | 3785/11952 [2:31:18<13:15:22, 5.84s/it] {'loss': 0.5088, 'learning_rate': 1.5991050874310156e-05, 'epoch': 0.32} + 32%|███▏ | 3785/11952 [2:31:18<13:15:22, 5.84s/it] 32%|███▏ | 3786/11952 [2:31:23<13:05:14, 5.77s/it] {'loss': 0.4833, 'learning_rate': 1.5988880913776434e-05, 'epoch': 0.32} + 32%|███▏ | 3786/11952 [2:31:23<13:05:14, 5.77s/it] 32%|███▏ | 3787/11952 [2:31:29<13:06:58, 5.78s/it] {'loss': 0.499, 'learning_rate': 1.5986710513444205e-05, 'epoch': 0.32} + 32%|███▏ | 3787/11952 [2:31:29<13:06:58, 5.78s/it] 32%|███▏ | 3788/11952 [2:31:35<13:16:39, 5.85s/it] {'loss': 0.4909, 'learning_rate': 1.5984539673472856e-05, 'epoch': 0.32} + 32%|███▏ | 3788/11952 [2:31:35<13:16:39, 5.85s/it] 32%|███▏ | 3789/11952 [2:31:41<13:16:50, 5.86s/it] {'loss': 0.4929, 'learning_rate': 1.5982368394021804e-05, 'epoch': 0.32} + 32%|███▏ | 3789/11952 [2:31:41<13:16:50, 5.86s/it] 32%|███▏ | 3790/11952 [2:31:47<13:22:07, 5.90s/it] {'loss': 0.4894, 'learning_rate': 1.5980196675250504e-05, 'epoch': 0.32} + 32%|███▏ | 3790/11952 [2:31:47<13:22:07, 5.90s/it] 32%|███▏ | 3791/11952 [2:31:53<13:25:45, 5.92s/it] {'loss': 0.4776, 'learning_rate': 1.5978024517318428e-05, 'epoch': 0.32} + 32%|███▏ | 3791/11952 [2:31:53<13:25:45, 5.92s/it] 32%|███▏ | 3792/11952 [2:31:59<13:23:20, 5.91s/it] {'loss': 0.4832, 'learning_rate': 1.5975851920385103e-05, 'epoch': 0.32} + 32%|███▏ | 3792/11952 [2:31:59<13:23:20, 5.91s/it] 32%|███▏ | 3793/11952 [2:32:05<13:19:29, 5.88s/it] {'loss': 0.4832, 'learning_rate': 1.5973678884610062e-05, 'epoch': 0.32} + 32%|███▏ | 3793/11952 [2:32:05<13:19:29, 5.88s/it] 32%|███▏ | 3794/11952 [2:32:11<13:21:02, 5.89s/it] {'loss': 0.4827, 'learning_rate': 1.597150541015289e-05, 'epoch': 0.32} + 32%|███▏ | 3794/11952 [2:32:11<13:21:02, 5.89s/it] 32%|███▏ | 3795/11952 [2:32:16<13:13:39, 5.84s/it] {'loss': 0.4805, 'learning_rate': 1.5969331497173203e-05, 'epoch': 0.32} + 32%|███▏ | 3795/11952 [2:32:16<13:13:39, 5.84s/it] 32%|███▏ | 3796/11952 [2:32:22<13:05:13, 5.78s/it] {'loss': 0.4961, 'learning_rate': 1.5967157145830638e-05, 'epoch': 0.32} + 32%|███▏ | 3796/11952 [2:32:22<13:05:13, 5.78s/it] 32%|███▏ | 3797/11952 [2:32:28<13:07:21, 5.79s/it] {'loss': 0.5165, 'learning_rate': 1.596498235628487e-05, 'epoch': 0.32} + 32%|███▏ | 3797/11952 [2:32:28<13:07:21, 5.79s/it] 32%|███▏ | 3798/11952 [2:32:34<13:06:26, 5.79s/it] {'loss': 0.4927, 'learning_rate': 1.5962807128695606e-05, 'epoch': 0.32} + 32%|███▏ | 3798/11952 [2:32:34<13:06:26, 5.79s/it] 32%|███▏ | 3799/11952 [2:32:39<13:13:34, 5.84s/it] {'loss': 0.5033, 'learning_rate': 1.5960631463222592e-05, 'epoch': 0.32} + 32%|███▏ | 3799/11952 [2:32:39<13:13:34, 5.84s/it]3 AutoResumeHook: Checking whether to suspend... +41 AutoResumeHook: Checking whether to suspend... +AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +02 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... + 32%|███▏ | 3800/11952 [2:32:45<13:08:20, 5.80s/it] {'loss': 0.4744, 'learning_rate': 1.595845536002559e-05, 'epoch': 0.32} + 32%|███▏ | 3800/11952 [2:32:45<13:08:20, 5.80s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-3800/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-3800/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/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%|███▏ | 3801/11952 [2:33:18<31:21:20, 13.85s/it] {'loss': 0.4675, 'learning_rate': 1.5956278819264417e-05, 'epoch': 0.32} + 32%|███▏ | 3801/11952 [2:33:18<31:21:20, 13.85s/it] 32%|███▏ | 3802/11952 [2:33:23<25:45:23, 11.38s/it] {'loss': 0.4773, 'learning_rate': 1.5954101841098895e-05, 'epoch': 0.32} + 32%|███▏ | 3802/11952 [2:33:23<25:45:23, 11.38s/it] 32%|███▏ | 3803/11952 [2:33:29<21:51:58, 9.66s/it] {'loss': 0.4848, 'learning_rate': 1.59519244256889e-05, 'epoch': 0.32} + 32%|███▏ | 3803/11952 [2:33:29<21:51:58, 9.66s/it] 32%|███▏ | 3804/11952 [2:33:35<19:29:17, 8.61s/it] {'loss': 0.4883, 'learning_rate': 1.5949746573194334e-05, 'epoch': 0.32} + 32%|███▏ | 3804/11952 [2:33:35<19:29:17, 8.61s/it] 32%|███▏ | 3805/11952 [2:33:41<17:43:51, 7.84s/it] {'loss': 0.4869, 'learning_rate': 1.5947568283775125e-05, 'epoch': 0.32} + 32%|███▏ | 3805/11952 [2:33:41<17:43:51, 7.84s/it] 32%|███▏ | 3806/11952 [2:33:47<16:10:41, 7.15s/it] {'loss': 0.4972, 'learning_rate': 1.5945389557591237e-05, 'epoch': 0.32} + 32%|███▏ | 3806/11952 [2:33:47<16:10:41, 7.15s/it] 32%|███▏ | 3807/11952 [2:33:52<15:08:50, 6.69s/it] {'loss': 0.4711, 'learning_rate': 1.594321039480267e-05, 'epoch': 0.32} + 32%|███▏ | 3807/11952 [2:33:52<15:08:50, 6.69s/it] 32%|███▏ | 3808/11952 [2:33:58<14:28:29, 6.40s/it] {'loss': 0.4634, 'learning_rate': 1.5941030795569452e-05, 'epoch': 0.32} + 32%|███▏ | 3808/11952 [2:33:58<14:28:29, 6.40s/it] 32%|███▏ | 3809/11952 [2:34:04<14:12:16, 6.28s/it] {'loss': 0.4964, 'learning_rate': 1.5938850760051643e-05, 'epoch': 0.32} + 32%|███▏ | 3809/11952 [2:34:04<14:12:16, 6.28s/it] 32%|███▏ | 3810/11952 [2:34:10<13:51:57, 6.13s/it] {'loss': 0.4977, 'learning_rate': 1.5936670288409335e-05, 'epoch': 0.32} + 32%|███▏ | 3810/11952 [2:34:10<13:51:57, 6.13s/it] 32%|███▏ | 3811/11952 [2:34:16<13:47:21, 6.10s/it] {'loss': 0.5042, 'learning_rate': 1.5934489380802653e-05, 'epoch': 0.32} + 32%|███▏ | 3811/11952 [2:34:16<13:47:21, 6.10s/it] 32%|███▏ | 3812/11952 [2:34:22<13:31:05, 5.98s/it] {'loss': 0.493, 'learning_rate': 1.5932308037391756e-05, 'epoch': 0.32} + 32%|███▏ | 3812/11952 [2:34:22<13:31:05, 5.98s/it] 32%|███▏ | 3813/11952 [2:34:27<13:22:59, 5.92s/it] {'loss': 0.4989, 'learning_rate': 1.593012625833683e-05, 'epoch': 0.32} + 32%|███▏ | 3813/11952 [2:34:27<13:22:59, 5.92s/it] 32%|███▏ | 3814/11952 [2:34:33<13:23:19, 5.92s/it] {'loss': 0.4855, 'learning_rate': 1.59279440437981e-05, 'epoch': 0.32} + 32%|███▏ | 3814/11952 [2:34:33<13:23:19, 5.92s/it] 32%|███▏ | 3815/11952 [2:34:39<13:18:59, 5.89s/it] {'loss': 0.483, 'learning_rate': 1.592576139393581e-05, 'epoch': 0.32} + 32%|███▏ | 3815/11952 [2:34:39<13:18:59, 5.89s/it] 32%|███▏ | 3816/11952 [2:34:45<13:07:51, 5.81s/it] {'loss': 0.4849, 'learning_rate': 1.5923578308910254e-05, 'epoch': 0.32} + 32%|███▏ | 3816/11952 [2:34:45<13:07:51, 5.81s/it] 32%|███▏ | 3817/11952 [2:34:50<13:00:05, 5.75s/it] {'loss': 0.483, 'learning_rate': 1.592139478888174e-05, 'epoch': 0.32} + 32%|███▏ | 3817/11952 [2:34:50<13:00:05, 5.75s/it] 32%|███▏ | 3818/11952 [2:34:56<13:01:11, 5.76s/it] {'loss': 0.511, 'learning_rate': 1.5919210834010628e-05, 'epoch': 0.32} + 32%|███▏ | 3818/11952 [2:34:56<13:01:11, 5.76s/it] 32%|███▏ | 3819/11952 [2:35:02<13:03:12, 5.78s/it] {'loss': 0.4953, 'learning_rate': 1.5917026444457288e-05, 'epoch': 0.32} + 32%|███▏ | 3819/11952 [2:35:02<13:03:12, 5.78s/it] 32%|███▏ | 3820/11952 [2:35:08<12:56:37, 5.73s/it] {'loss': 0.4849, 'learning_rate': 1.591484162038214e-05, 'epoch': 0.32} + 32%|███▏ | 3820/11952 [2:35:08<12:56:37, 5.73s/it] 32%|███▏ | 3821/11952 [2:35:13<12:53:43, 5.71s/it] {'loss': 0.4783, 'learning_rate': 1.5912656361945626e-05, 'epoch': 0.32} + 32%|███▏ | 3821/11952 [2:35:13<12:53:43, 5.71s/it] 32%|███▏ | 3822/11952 [2:35:19<12:52:00, 5.70s/it] {'loss': 0.4872, 'learning_rate': 1.5910470669308217e-05, 'epoch': 0.32} + 32%|███▏ | 3822/11952 [2:35:19<12:52:00, 5.70s/it] 32%|███▏ | 3823/11952 [2:35:25<13:02:16, 5.77s/it] {'loss': 0.5001, 'learning_rate': 1.5908284542630425e-05, 'epoch': 0.32} + 32%|███▏ | 3823/11952 [2:35:25<13:02:16, 5.77s/it] 32%|███▏ | 3824/11952 [2:35:30<12:52:52, 5.71s/it] {'loss': 0.4711, 'learning_rate': 1.5906097982072793e-05, 'epoch': 0.32} + 32%|███▏ | 3824/11952 [2:35:30<12:52:52, 5.71s/it] 32%|███▏ | 3825/11952 [2:35:36<12:52:10, 5.70s/it] {'loss': 0.468, 'learning_rate': 1.590391098779589e-05, 'epoch': 0.32} + 32%|███▏ | 3825/11952 [2:35:36<12:52:10, 5.70s/it] 32%|███▏ | 3826/11952 [2:35:42<13:07:22, 5.81s/it] {'loss': 0.5036, 'learning_rate': 1.5901723559960322e-05, 'epoch': 0.32} + 32%|███▏ | 3826/11952 [2:35:42<13:07:22, 5.81s/it] 32%|███▏ | 3827/11952 [2:35:48<13:03:29, 5.79s/it] {'loss': 0.483, 'learning_rate': 1.5899535698726723e-05, 'epoch': 0.32} + 32%|███▏ | 3827/11952 [2:35:48<13:03:29, 5.79s/it] 32%|███▏ | 3828/11952 [2:35:54<13:15:16, 5.87s/it] {'loss': 0.4843, 'learning_rate': 1.5897347404255757e-05, 'epoch': 0.32} + 32%|███▏ | 3828/11952 [2:35:54<13:15:16, 5.87s/it] 32%|███▏ | 3829/11952 [2:36:00<13:12:48, 5.86s/it] {'loss': 0.4897, 'learning_rate': 1.589515867670813e-05, 'epoch': 0.32} + 32%|███▏ | 3829/11952 [2:36:00<13:12:48, 5.86s/it] 32%|███▏ | 3830/11952 [2:36:05<12:58:59, 5.75s/it] {'loss': 0.4886, 'learning_rate': 1.589296951624457e-05, 'epoch': 0.32} + 32%|███▏ | 3830/11952 [2:36:05<12:58:59, 5.75s/it] 32%|███▏ | 3831/11952 [2:36:11<12:52:42, 5.71s/it] {'loss': 0.4777, 'learning_rate': 1.5890779923025832e-05, 'epoch': 0.32} + 32%|███▏ | 3831/11952 [2:36:11<12:52:42, 5.71s/it] 32%|███▏ | 3832/11952 [2:36:17<12:57:26, 5.74s/it] {'loss': 0.495, 'learning_rate': 1.5888589897212726e-05, 'epoch': 0.32} + 32%|███▏ | 3832/11952 [2:36:17<12:57:26, 5.74s/it] 32%|███▏ | 3833/11952 [2:36:23<12:56:25, 5.74s/it] {'loss': 0.4896, 'learning_rate': 1.5886399438966068e-05, 'epoch': 0.32} + 32%|███▏ | 3833/11952 [2:36:23<12:56:25, 5.74s/it] 32%|███▏ | 3834/11952 [2:36:28<12:56:26, 5.74s/it] {'loss': 0.4846, 'learning_rate': 1.5884208548446716e-05, 'epoch': 0.32} + 32%|███▏ | 3834/11952 [2:36:28<12:56:26, 5.74s/it] 32%|███▏ | 3835/11952 [2:36:34<12:58:28, 5.75s/it] {'loss': 0.4673, 'learning_rate': 1.5882017225815566e-05, 'epoch': 0.32} + 32%|███▏ | 3835/11952 [2:36:34<12:58:28, 5.75s/it] 32%|███▏ | 3836/11952 [2:36:40<13:08:22, 5.83s/it] {'loss': 0.4854, 'learning_rate': 1.5879825471233538e-05, 'epoch': 0.32} + 32%|███▏ | 3836/11952 [2:36:40<13:08:22, 5.83s/it] 32%|███▏ | 3837/11952 [2:36:46<13:01:34, 5.78s/it] {'loss': 0.4916, 'learning_rate': 1.5877633284861577e-05, 'epoch': 0.32} + 32%|███▏ | 3837/11952 [2:36:46<13:01:34, 5.78s/it] 32%|███▏ | 3838/11952 [2:36:52<13:13:13, 5.87s/it] {'loss': 0.4774, 'learning_rate': 1.587544066686068e-05, 'epoch': 0.32} + 32%|███▏ | 3838/11952 [2:36:52<13:13:13, 5.87s/it] 32%|███▏ | 3839/11952 [2:36:58<13:17:38, 5.90s/it] {'loss': 0.4825, 'learning_rate': 1.5873247617391854e-05, 'epoch': 0.32} + 32%|███▏ | 3839/11952 [2:36:58<13:17:38, 5.90s/it] 32%|███▏ | 3840/11952 [2:37:04<13:24:07, 5.95s/it] {'loss': 0.4933, 'learning_rate': 1.5871054136616154e-05, 'epoch': 0.32} + 32%|███▏ | 3840/11952 [2:37:04<13:24:07, 5.95s/it] 32%|███▏ | 3841/11952 [2:37:10<13:23:15, 5.94s/it] {'loss': 0.5059, 'learning_rate': 1.5868860224694656e-05, 'epoch': 0.32} + 32%|███▏ | 3841/11952 [2:37:10<13:23:15, 5.94s/it] 32%|███▏ | 3842/11952 [2:37:16<13:22:34, 5.94s/it] {'loss': 0.4819, 'learning_rate': 1.586666588178848e-05, 'epoch': 0.32} + 32%|███▏ | 3842/11952 [2:37:16<13:22:34, 5.94s/it] 32%|███▏ | 3843/11952 [2:37:21<13:13:35, 5.87s/it] {'loss': 0.4753, 'learning_rate': 1.5864471108058755e-05, 'epoch': 0.32} + 32%|███▏ | 3843/11952 [2:37:21<13:13:35, 5.87s/it] 32%|███▏ | 3844/11952 [2:37:27<13:16:12, 5.89s/it] {'loss': 0.5028, 'learning_rate': 1.586227590366667e-05, 'epoch': 0.32} + 32%|███▏ | 3844/11952 [2:37:27<13:16:12, 5.89s/it] 32%|███▏ | 3845/11952 [2:37:33<13:13:23, 5.87s/it] {'loss': 0.5122, 'learning_rate': 1.586008026877342e-05, 'epoch': 0.32} + 32%|███▏ | 3845/11952 [2:37:33<13:13:23, 5.87s/it] 32%|███▏ | 3846/11952 [2:37:40<13:37:44, 6.05s/it] {'loss': 0.5066, 'learning_rate': 1.585788420354025e-05, 'epoch': 0.32} + 32%|███▏ | 3846/11952 [2:37:40<13:37:44, 6.05s/it] 32%|███▏ | 3847/11952 [2:37:46<13:35:22, 6.04s/it] {'loss': 0.4991, 'learning_rate': 1.5855687708128433e-05, 'epoch': 0.32} + 32%|███▏ | 3847/11952 [2:37:46<13:35:22, 6.04s/it] 32%|███▏ | 3848/11952 [2:37:51<13:21:12, 5.93s/it] {'loss': 0.4953, 'learning_rate': 1.5853490782699266e-05, 'epoch': 0.32} + 32%|███▏ | 3848/11952 [2:37:51<13:21:12, 5.93s/it] 32%|███▏ | 3849/11952 [2:37:57<13:13:22, 5.87s/it] {'loss': 0.4834, 'learning_rate': 1.5851293427414075e-05, 'epoch': 0.32} + 32%|███▏ | 3849/11952 [2:37:57<13:13:22, 5.87s/it]6 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... +04 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... + 32%|███▏ | 3850/11952 [2:38:03<13:22:08, 5.94s/it] {'loss': 0.49, 'learning_rate': 1.584909564243424e-05, 'epoch': 0.32} + 32%|███▏ | 3850/11952 [2:38:03<13:22:08, 5.94s/it] 32%|███▏ | 3851/11952 [2:38:09<13:09:44, 5.85s/it] {'loss': 0.4989, 'learning_rate': 1.5846897427921147e-05, 'epoch': 0.32} + 32%|███▏ | 3851/11952 [2:38:09<13:09:44, 5.85s/it] 32%|███▏ | 3852/11952 [2:38:14<13:03:23, 5.80s/it] {'loss': 0.481, 'learning_rate': 1.584469878403623e-05, 'epoch': 0.32} + 32%|███▏ | 3852/11952 [2:38:14<13:03:23, 5.80s/it] 32%|███▏ | 3853/11952 [2:38:20<13:05:36, 5.82s/it] {'loss': 0.5093, 'learning_rate': 1.5842499710940936e-05, 'epoch': 0.32} + 32%|███▏ | 3853/11952 [2:38:20<13:05:36, 5.82s/it] 32%|███▏ | 3854/11952 [2:38:26<13:02:55, 5.80s/it] {'loss': 0.4943, 'learning_rate': 1.5840300208796767e-05, 'epoch': 0.32} + 32%|███▏ | 3854/11952 [2:38:26<13:02:55, 5.80s/it] 32%|███▏ | 3855/11952 [2:38:32<13:01:11, 5.79s/it] {'loss': 0.4794, 'learning_rate': 1.5838100277765244e-05, 'epoch': 0.32} + 32%|███▏ | 3855/11952 [2:38:32<13:01:11, 5.79s/it] 32%|███▏ | 3856/11952 [2:38:38<13:02:28, 5.80s/it] {'loss': 0.4951, 'learning_rate': 1.5835899918007917e-05, 'epoch': 0.32} + 32%|███▏ | 3856/11952 [2:38:38<13:02:28, 5.80s/it] 32%|███▏ | 3857/11952 [2:38:44<13:30:59, 6.01s/it] {'loss': 0.4958, 'learning_rate': 1.5833699129686376e-05, 'epoch': 0.32} + 32%|███▏ | 3857/11952 [2:38:44<13:30:59, 6.01s/it] 32%|███▏ | 3858/11952 [2:38:50<13:20:35, 5.93s/it] {'loss': 0.5049, 'learning_rate': 1.5831497912962235e-05, 'epoch': 0.32} + 32%|███▏ | 3858/11952 [2:38:50<13:20:35, 5.93s/it] 32%|███▏ | 3859/11952 [2:38:56<13:18:37, 5.92s/it] {'loss': 0.4801, 'learning_rate': 1.5829296267997142e-05, 'epoch': 0.32} + 32%|███▏ | 3859/11952 [2:38:56<13:18:37, 5.92s/it] 32%|███▏ | 3860/11952 [2:39:02<13:14:21, 5.89s/it] {'loss': 0.4781, 'learning_rate': 1.582709419495277e-05, 'epoch': 0.32} + 32%|███▏ | 3860/11952 [2:39:02<13:14:21, 5.89s/it] 32%|███▏ | 3861/11952 [2:39:08<13:20:41, 5.94s/it] {'loss': 0.5053, 'learning_rate': 1.5824891693990845e-05, 'epoch': 0.32} + 32%|███▏ | 3861/11952 [2:39:08<13:20:41, 5.94s/it] 32%|███▏ | 3862/11952 [2:39:13<13:14:10, 5.89s/it] {'loss': 0.5095, 'learning_rate': 1.58226887652731e-05, 'epoch': 0.32} + 32%|███▏ | 3862/11952 [2:39:13<13:14:10, 5.89s/it] 32%|███▏ | 3863/11952 [2:39:19<13:09:18, 5.85s/it] {'loss': 0.5, 'learning_rate': 1.582048540896131e-05, 'epoch': 0.32} + 32%|███▏ | 3863/11952 [2:39:19<13:09:18, 5.85s/it] 32%|███▏ | 3864/11952 [2:39:25<13:10:50, 5.87s/it] {'loss': 0.4818, 'learning_rate': 1.581828162521728e-05, 'epoch': 0.32} + 32%|███▏ | 3864/11952 [2:39:25<13:10:50, 5.87s/it] 32%|███▏ | 3865/11952 [2:39:31<13:09:23, 5.86s/it] {'loss': 0.4957, 'learning_rate': 1.5816077414202848e-05, 'epoch': 0.32} + 32%|███▏ | 3865/11952 [2:39:31<13:09:23, 5.86s/it] 32%|███▏ | 3866/11952 [2:39:37<12:59:58, 5.79s/it] {'loss': 0.477, 'learning_rate': 1.5813872776079882e-05, 'epoch': 0.32} + 32%|███▏ | 3866/11952 [2:39:37<12:59:58, 5.79s/it] 32%|███▏ | 3867/11952 [2:39:42<12:59:54, 5.79s/it] {'loss': 0.4875, 'learning_rate': 1.581166771101028e-05, 'epoch': 0.32} + 32%|███▏ | 3867/11952 [2:39:42<12:59:54, 5.79s/it] 32%|███▏ | 3868/11952 [2:39:48<13:02:36, 5.81s/it] {'loss': 0.4905, 'learning_rate': 1.5809462219155976e-05, 'epoch': 0.32} + 32%|███▏ | 3868/11952 [2:39:48<13:02:36, 5.81s/it] 32%|███▏ | 3869/11952 [2:39:54<13:06:15, 5.84s/it] {'loss': 0.4993, 'learning_rate': 1.580725630067893e-05, 'epoch': 0.32} + 32%|███▏ | 3869/11952 [2:39:54<13:06:15, 5.84s/it] 32%|███▏ | 3870/11952 [2:40:00<13:12:05, 5.88s/it] {'loss': 0.486, 'learning_rate': 1.5805049955741135e-05, 'epoch': 0.32} + 32%|███▏ | 3870/11952 [2:40:00<13:12:05, 5.88s/it] 32%|███▏ | 3871/11952 [2:40:06<13:09:40, 5.86s/it] {'loss': 0.4895, 'learning_rate': 1.5802843184504614e-05, 'epoch': 0.32} + 32%|███▏ | 3871/11952 [2:40:06<13:09:40, 5.86s/it] 32%|███▏ | 3872/11952 [2:40:12<13:18:08, 5.93s/it] {'loss': 0.5033, 'learning_rate': 1.5800635987131426e-05, 'epoch': 0.32} + 32%|███▏ | 3872/11952 [2:40:12<13:18:08, 5.93s/it] 32%|███▏ | 3873/11952 [2:40:18<13:15:53, 5.91s/it] {'loss': 0.4842, 'learning_rate': 1.579842836378366e-05, 'epoch': 0.32} + 32%|███▏ | 3873/11952 [2:40:18<13:15:53, 5.91s/it] 32%|███▏ | 3874/11952 [2:40:24<13:12:43, 5.89s/it] {'loss': 0.479, 'learning_rate': 1.579622031462343e-05, 'epoch': 0.32} + 32%|███▏ | 3874/11952 [2:40:24<13:12:43, 5.89s/it] 32%|███▏ | 3875/11952 [2:40:30<13:11:22, 5.88s/it] {'loss': 0.5077, 'learning_rate': 1.5794011839812888e-05, 'epoch': 0.32} + 32%|███▏ | 3875/11952 [2:40:30<13:11:22, 5.88s/it] 32%|███▏ | 3876/11952 [2:40:35<12:58:22, 5.78s/it] {'loss': 0.4942, 'learning_rate': 1.579180293951422e-05, 'epoch': 0.32} + 32%|███▏ | 3876/11952 [2:40:35<12:58:22, 5.78s/it] 32%|███▏ | 3877/11952 [2:40:41<12:54:42, 5.76s/it] {'loss': 0.4722, 'learning_rate': 1.5789593613889632e-05, 'epoch': 0.32} + 32%|███▏ | 3877/11952 [2:40:41<12:54:42, 5.76s/it] 32%|███▏ | 3878/11952 [2:40:46<12:48:59, 5.71s/it] {'loss': 0.48, 'learning_rate': 1.5787383863101366e-05, 'epoch': 0.32} + 32%|███▏ | 3878/11952 [2:40:46<12:48:59, 5.71s/it] 32%|███▏ | 3879/11952 [2:40:52<12:58:29, 5.79s/it] {'loss': 0.4909, 'learning_rate': 1.5785173687311704e-05, 'epoch': 0.32} + 32%|███▏ | 3879/11952 [2:40:52<12:58:29, 5.79s/it] 32%|███▏ | 3880/11952 [2:40:58<13:07:55, 5.86s/it] {'loss': 0.4962, 'learning_rate': 1.5782963086682946e-05, 'epoch': 0.32} + 32%|███▏ | 3880/11952 [2:40:58<13:07:55, 5.86s/it] 32%|███▏ | 3881/11952 [2:41:05<13:29:54, 6.02s/it] {'loss': 0.502, 'learning_rate': 1.5780752061377436e-05, 'epoch': 0.32} + 32%|███▏ | 3881/11952 [2:41:05<13:29:54, 6.02s/it] 32%|███▏ | 3882/11952 [2:41:11<13:27:36, 6.00s/it] {'loss': 0.4961, 'learning_rate': 1.5778540611557538e-05, 'epoch': 0.32} + 32%|███▏ | 3882/11952 [2:41:11<13:27:36, 6.00s/it] 32%|███▏ | 3883/11952 [2:41:17<13:28:37, 6.01s/it] {'loss': 0.506, 'learning_rate': 1.577632873738565e-05, 'epoch': 0.32} + 32%|███▏ | 3883/11952 [2:41:17<13:28:37, 6.01s/it] 32%|███▏ | 3884/11952 [2:41:23<13:18:23, 5.94s/it] {'loss': 0.4868, 'learning_rate': 1.5774116439024206e-05, 'epoch': 0.32} + 32%|███▏ | 3884/11952 [2:41:23<13:18:23, 5.94s/it] 33%|███▎ | 3885/11952 [2:41:28<13:13:40, 5.90s/it] {'loss': 0.4888, 'learning_rate': 1.5771903716635666e-05, 'epoch': 0.33} + 33%|███▎ | 3885/11952 [2:41:28<13:13:40, 5.90s/it] 33%|███▎ | 3886/11952 [2:41:34<13:16:38, 5.93s/it] {'loss': 0.5003, 'learning_rate': 1.576969057038253e-05, 'epoch': 0.33} + 33%|███▎ | 3886/11952 [2:41:34<13:16:38, 5.93s/it] 33%|███▎ | 3887/11952 [2:41:40<13:16:18, 5.92s/it] {'loss': 0.4854, 'learning_rate': 1.5767477000427306e-05, 'epoch': 0.33} + 33%|███▎ | 3887/11952 [2:41:40<13:16:18, 5.92s/it] 33%|███▎ | 3888/11952 [2:41:46<13:10:07, 5.88s/it] {'loss': 0.4996, 'learning_rate': 1.576526300693257e-05, 'epoch': 0.33} + 33%|███▎ | 3888/11952 [2:41:46<13:10:07, 5.88s/it] 33%|███▎ | 3889/11952 [2:41:52<13:18:21, 5.94s/it] {'loss': 0.4976, 'learning_rate': 1.5763048590060894e-05, 'epoch': 0.33} + 33%|███▎ | 3889/11952 [2:41:52<13:18:21, 5.94s/it] 33%|███▎ | 3890/11952 [2:41:58<13:06:00, 5.85s/it] {'loss': 0.4881, 'learning_rate': 1.5760833749974898e-05, 'epoch': 0.33} + 33%|███▎ | 3890/11952 [2:41:58<13:06:00, 5.85s/it] 33%|███▎ | 3891/11952 [2:42:04<13:11:13, 5.89s/it] {'loss': 0.494, 'learning_rate': 1.5758618486837232e-05, 'epoch': 0.33} + 33%|███▎ | 3891/11952 [2:42:04<13:11:13, 5.89s/it] 33%|███▎ | 3892/11952 [2:42:10<13:05:09, 5.84s/it] {'loss': 0.4804, 'learning_rate': 1.5756402800810582e-05, 'epoch': 0.33} + 33%|███▎ | 3892/11952 [2:42:10<13:05:09, 5.84s/it] 33%|███▎ | 3893/11952 [2:42:15<13:02:04, 5.82s/it] {'loss': 0.4861, 'learning_rate': 1.575418669205765e-05, 'epoch': 0.33} + 33%|███▎ | 3893/11952 [2:42:15<13:02:04, 5.82s/it] 33%|███▎ | 3894/11952 [2:42:21<13:10:07, 5.88s/it] {'loss': 0.4914, 'learning_rate': 1.575197016074118e-05, 'epoch': 0.33} + 33%|███▎ | 3894/11952 [2:42:21<13:10:07, 5.88s/it] 33%|███▎ | 3895/11952 [2:42:27<13:01:07, 5.82s/it] {'loss': 0.4872, 'learning_rate': 1.5749753207023944e-05, 'epoch': 0.33} + 33%|███▎ | 3895/11952 [2:42:27<13:01:07, 5.82s/it] 33%|███▎ | 3896/11952 [2:42:33<12:50:57, 5.74s/it] {'loss': 0.489, 'learning_rate': 1.574753583106875e-05, 'epoch': 0.33} + 33%|███▎ | 3896/11952 [2:42:33<12:50:57, 5.74s/it] 33%|███▎ | 3897/11952 [2:42:39<13:05:19, 5.85s/it] {'loss': 0.4924, 'learning_rate': 1.574531803303843e-05, 'epoch': 0.33} + 33%|███▎ | 3897/11952 [2:42:39<13:05:19, 5.85s/it] 33%|███▎ | 3898/11952 [2:42:44<12:58:22, 5.80s/it] {'loss': 0.4816, 'learning_rate': 1.574309981309585e-05, 'epoch': 0.33} + 33%|███▎ | 3898/11952 [2:42:44<12:58:22, 5.80s/it] 33%|███▎ | 3899/11952 [2:42:50<12:54:21, 5.77s/it] {'loss': 0.4639, 'learning_rate': 1.574088117140391e-05, 'epoch': 0.33} + 33%|███▎ | 3899/11952 [2:42:50<12:54:21, 5.77s/it]6 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... +07 AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... +AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... + 33%|███▎ | 3900/11952 [2:42:56<12:49:27, 5.73s/it] {'loss': 0.4816, 'learning_rate': 1.573866210812553e-05, 'epoch': 0.33} + 33%|███▎ | 3900/11952 [2:42:56<12:49:27, 5.73s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-3900/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-3900/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/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%|███▎ | 3901/11952 [2:43:28<30:29:39, 13.64s/it] {'loss': 0.4962, 'learning_rate': 1.5736442623423675e-05, 'epoch': 0.33} + 33%|███▎ | 3901/11952 [2:43:28<30:29:39, 13.64s/it] 33%|███▎ | 3902/11952 [2:43:34<25:12:18, 11.27s/it] {'loss': 0.4772, 'learning_rate': 1.5734222717461338e-05, 'epoch': 0.33} + 33%|███▎ | 3902/11952 [2:43:34<25:12:18, 11.27s/it] 33%|███▎ | 3903/11952 [2:43:40<21:44:41, 9.73s/it] {'loss': 0.5055, 'learning_rate': 1.5732002390401527e-05, 'epoch': 0.33} + 33%|███▎ | 3903/11952 [2:43:40<21:44:41, 9.73s/it] 33%|███▎ | 3904/11952 [2:43:45<19:03:58, 8.53s/it] {'loss': 0.5134, 'learning_rate': 1.5729781642407305e-05, 'epoch': 0.33} + 33%|███▎ | 3904/11952 [2:43:45<19:03:58, 8.53s/it] 33%|███▎ | 3905/11952 [2:43:52<17:40:24, 7.91s/it] {'loss': 0.4845, 'learning_rate': 1.5727560473641755e-05, 'epoch': 0.33} + 33%|███▎ | 3905/11952 [2:43:52<17:40:24, 7.91s/it] 33%|███▎ | 3906/11952 [2:43:58<16:12:06, 7.25s/it] {'loss': 0.4959, 'learning_rate': 1.572533888426798e-05, 'epoch': 0.33} + 33%|███▎ | 3906/11952 [2:43:58<16:12:06, 7.25s/it] 33%|███▎ | 3907/11952 [2:44:03<15:17:29, 6.84s/it] {'loss': 0.5198, 'learning_rate': 1.5723116874449136e-05, 'epoch': 0.33} + 33%|███▎ | 3907/11952 [2:44:03<15:17:29, 6.84s/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%|███▎ | 3908/11952 [2:44:09<14:38:13, 6.55s/it] {'loss': 0.4905, 'learning_rate': 1.5720894444348393e-05, 'epoch': 0.33} + 33%|███▎ | 3908/11952 [2:44:09<14:38:13, 6.55s/it] 33%|███▎ | 3909/11952 [2:44:15<14:04:33, 6.30s/it] {'loss': 0.4815, 'learning_rate': 1.5718671594128957e-05, 'epoch': 0.33} + 33%|███▎ | 3909/11952 [2:44:15<14:04:33, 6.30s/it] 33%|███▎ | 3910/11952 [2:44:21<13:51:25, 6.20s/it] {'loss': 0.5216, 'learning_rate': 1.571644832395406e-05, 'epoch': 0.33} + 33%|███▎ | 3910/11952 [2:44:21<13:51:25, 6.20s/it] 33%|███▎ | 3911/11952 [2:44:27<13:38:25, 6.11s/it] {'loss': 0.4948, 'learning_rate': 1.5714224633986978e-05, 'epoch': 0.33} + 33%|███▎ | 3911/11952 [2:44:27<13:38:25, 6.11s/it] 33%|███▎ | 3912/11952 [2:44:33<13:23:15, 5.99s/it] {'loss': 0.4868, 'learning_rate': 1.5712000524391004e-05, 'epoch': 0.33} + 33%|███▎ | 3912/11952 [2:44:33<13:23:15, 5.99s/it] 33%|███▎ | 3913/11952 [2:44:39<13:19:15, 5.97s/it] {'loss': 0.488, 'learning_rate': 1.5709775995329475e-05, 'epoch': 0.33} + 33%|███▎ | 3913/11952 [2:44:39<13:19:15, 5.97s/it] 33%|███▎ | 3914/11952 [2:44:44<13:17:49, 5.96s/it] {'loss': 0.4918, 'learning_rate': 1.570755104696574e-05, 'epoch': 0.33} + 33%|███▎ | 3914/11952 [2:44:44<13:17:49, 5.96s/it] 33%|███▎ | 3915/11952 [2:44:50<13:17:02, 5.95s/it] {'loss': 0.4765, 'learning_rate': 1.5705325679463198e-05, 'epoch': 0.33} + 33%|███▎ | 3915/11952 [2:44:50<13:17:02, 5.95s/it] 33%|███▎ | 3916/11952 [2:44:57<13:22:44, 5.99s/it] {'loss': 0.501, 'learning_rate': 1.5703099892985267e-05, 'epoch': 0.33} + 33%|███▎ | 3916/11952 [2:44:57<13:22:44, 5.99s/it] 33%|███▎ | 3917/11952 [2:45:02<13:05:42, 5.87s/it] {'loss': 0.4919, 'learning_rate': 1.5700873687695405e-05, 'epoch': 0.33} + 33%|███▎ | 3917/11952 [2:45:02<13:05:42, 5.87s/it] 33%|███▎ | 3918/11952 [2:45:08<13:13:22, 5.93s/it] {'loss': 0.4837, 'learning_rate': 1.5698647063757086e-05, 'epoch': 0.33} + 33%|███▎ | 3918/11952 [2:45:08<13:13:22, 5.93s/it] 33%|███▎ | 3919/11952 [2:45:14<13:05:48, 5.87s/it] {'loss': 0.4798, 'learning_rate': 1.5696420021333828e-05, 'epoch': 0.33} + 33%|███▎ | 3919/11952 [2:45:14<13:05:48, 5.87s/it] 33%|███▎ | 3920/11952 [2:45:19<12:53:30, 5.78s/it] {'loss': 0.4893, 'learning_rate': 1.5694192560589184e-05, 'epoch': 0.33} + 33%|███▎ | 3920/11952 [2:45:19<12:53:30, 5.78s/it] 33%|███▎ | 3921/11952 [2:45:25<12:48:43, 5.74s/it] {'loss': 0.4969, 'learning_rate': 1.5691964681686715e-05, 'epoch': 0.33} + 33%|███▎ | 3921/11952 [2:45:25<12:48:43, 5.74s/it] 33%|███▎ | 3922/11952 [2:45:31<12:49:19, 5.75s/it] {'loss': 0.4692, 'learning_rate': 1.5689736384790038e-05, 'epoch': 0.33} + 33%|███▎ | 3922/11952 [2:45:31<12:49:19, 5.75s/it] 33%|███▎ | 3923/11952 [2:45:37<12:58:15, 5.82s/it] {'loss': 0.4862, 'learning_rate': 1.5687507670062788e-05, 'epoch': 0.33} + 33%|███▎ | 3923/11952 [2:45:37<12:58:15, 5.82s/it] 33%|███▎ | 3924/11952 [2:45:42<12:51:51, 5.77s/it] {'loss': 0.4888, 'learning_rate': 1.5685278537668627e-05, 'epoch': 0.33} + 33%|███▎ | 3924/11952 [2:45:42<12:51:51, 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!") + 33%|███▎ | 3925/11952 [2:45:49<13:07:49, 5.89s/it] {'loss': 0.518, 'learning_rate': 1.568304898777126e-05, 'epoch': 0.33} + 33%|███▎ | 3925/11952 [2:45:49<13:07:49, 5.89s/it] 33%|███▎ | 3926/11952 [2:45:54<12:59:55, 5.83s/it] {'loss': 0.4963, 'learning_rate': 1.568081902053441e-05, 'epoch': 0.33} + 33%|███▎ | 3926/11952 [2:45:54<12:59:55, 5.83s/it] 33%|███▎ | 3927/11952 [2:46:00<12:47:14, 5.74s/it] {'loss': 0.4802, 'learning_rate': 1.567858863612184e-05, 'epoch': 0.33} + 33%|███▎ | 3927/11952 [2:46:00<12:47:14, 5.74s/it] 33%|███▎ | 3928/11952 [2:46:06<12:59:10, 5.83s/it] {'loss': 0.5066, 'learning_rate': 1.5676357834697342e-05, 'epoch': 0.33} + 33%|███▎ | 3928/11952 [2:46:06<12:59:10, 5.83s/it] 33%|███▎ | 3929/11952 [2:46:12<12:59:31, 5.83s/it] {'loss': 0.495, 'learning_rate': 1.5674126616424735e-05, 'epoch': 0.33} + 33%|███▎ | 3929/11952 [2:46:12<12:59:31, 5.83s/it] 33%|███▎ | 3930/11952 [2:46:17<12:52:59, 5.78s/it] {'loss': 0.4616, 'learning_rate': 1.5671894981467866e-05, 'epoch': 0.33} + 33%|███▎ | 3930/11952 [2:46:17<12:52:59, 5.78s/it] 33%|███▎ | 3931/11952 [2:46:23<12:46:12, 5.73s/it] {'loss': 0.4896, 'learning_rate': 1.5669662929990622e-05, 'epoch': 0.33} + 33%|███▎ | 3931/11952 [2:46:23<12:46:12, 5.73s/it] 33%|███▎ | 3932/11952 [2:46:29<12:41:11, 5.69s/it] {'loss': 0.4981, 'learning_rate': 1.5667430462156918e-05, 'epoch': 0.33} + 33%|███▎ | 3932/11952 [2:46:29<12:41:11, 5.69s/it] 33%|███▎ | 3933/11952 [2:46:35<12:57:28, 5.82s/it] {'loss': 0.4783, 'learning_rate': 1.566519757813069e-05, 'epoch': 0.33} + 33%|███▎ | 3933/11952 [2:46:35<12:57:28, 5.82s/it] 33%|███▎ | 3934/11952 [2:46:41<12:57:45, 5.82s/it] {'loss': 0.5017, 'learning_rate': 1.5662964278075913e-05, 'epoch': 0.33} + 33%|███▎ | 3934/11952 [2:46:41<12:57:45, 5.82s/it] 33%|███▎ | 3935/11952 [2:46:46<12:58:22, 5.83s/it] {'loss': 0.4876, 'learning_rate': 1.5660730562156596e-05, 'epoch': 0.33} + 33%|███▎ | 3935/11952 [2:46:46<12:58:22, 5.83s/it] 33%|███▎ | 3936/11952 [2:46:53<13:11:05, 5.92s/it] {'loss': 0.4888, 'learning_rate': 1.5658496430536772e-05, 'epoch': 0.33} + 33%|███▎ | 3936/11952 [2:46:53<13:11:05, 5.92s/it] 33%|███▎ | 3937/11952 [2:46:59<13:19:46, 5.99s/it] {'loss': 0.484, 'learning_rate': 1.5656261883380504e-05, 'epoch': 0.33} + 33%|███▎ | 3937/11952 [2:46:59<13:19:46, 5.99s/it] 33%|███▎ | 3938/11952 [2:47:04<13:09:33, 5.91s/it] {'loss': 0.5082, 'learning_rate': 1.565402692085189e-05, 'epoch': 0.33} + 33%|███▎ | 3938/11952 [2:47:04<13:09:33, 5.91s/it] 33%|███▎ | 3939/11952 [2:47:10<13:04:40, 5.88s/it] {'loss': 0.4958, 'learning_rate': 1.5651791543115056e-05, 'epoch': 0.33} + 33%|███▎ | 3939/11952 [2:47:10<13:04:40, 5.88s/it] 33%|███▎ | 3940/11952 [2:47:16<12:55:45, 5.81s/it] {'loss': 0.4958, 'learning_rate': 1.564955575033416e-05, 'epoch': 0.33} + 33%|███▎ | 3940/11952 [2:47:16<12:55:45, 5.81s/it] 33%|███▎ | 3941/11952 [2:47:22<12:54:53, 5.80s/it] {'loss': 0.5015, 'learning_rate': 1.5647319542673386e-05, 'epoch': 0.33} + 33%|███▎ | 3941/11952 [2:47:22<12:54:53, 5.80s/it] 33%|███▎ | 3942/11952 [2:47:27<12:55:15, 5.81s/it] {'loss': 0.4872, 'learning_rate': 1.564508292029695e-05, 'epoch': 0.33} + 33%|███▎ | 3942/11952 [2:47:27<12:55:15, 5.81s/it] 33%|███▎ | 3943/11952 [2:47:33<12:55:39, 5.81s/it] {'loss': 0.471, 'learning_rate': 1.5642845883369114e-05, 'epoch': 0.33} + 33%|███▎ | 3943/11952 [2:47:33<12:55:39, 5.81s/it] 33%|███▎ | 3944/11952 [2:47:39<12:47:46, 5.75s/it] {'loss': 0.484, 'learning_rate': 1.564060843205414e-05, 'epoch': 0.33} + 33%|███▎ | 3944/11952 [2:47:39<12:47:46, 5.75s/it] 33%|███▎ | 3945/11952 [2:47:45<12:55:46, 5.81s/it] {'loss': 0.4949, 'learning_rate': 1.5638370566516344e-05, 'epoch': 0.33} + 33%|███▎ | 3945/11952 [2:47:45<12:55:46, 5.81s/it] 33%|███▎ | 3946/11952 [2:47:50<12:47:14, 5.75s/it] {'loss': 0.4749, 'learning_rate': 1.5636132286920066e-05, 'epoch': 0.33} + 33%|███▎ | 3946/11952 [2:47:50<12:47:14, 5.75s/it] 33%|███▎ | 3947/11952 [2:47:56<12:50:19, 5.77s/it] {'loss': 0.4953, 'learning_rate': 1.5633893593429677e-05, 'epoch': 0.33} + 33%|███▎ | 3947/11952 [2:47:56<12:50:19, 5.77s/it] 33%|███▎ | 3948/11952 [2:48:02<13:06:32, 5.90s/it] {'loss': 0.513, 'learning_rate': 1.5631654486209572e-05, 'epoch': 0.33} + 33%|███▎ | 3948/11952 [2:48:02<13:06:32, 5.90s/it] 33%|███▎ | 3949/11952 [2:48:08<13:01:51, 5.86s/it] {'loss': 0.4946, 'learning_rate': 1.5629414965424187e-05, 'epoch': 0.33} + 33%|███▎ | 3949/11952 [2:48:08<13:01:51, 5.86s/it]6 AutoResumeHook: Checking whether to suspend... +21 AutoResumeHook: Checking whether to suspend... +AutoResumeHook: Checking whether to suspend... +3 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... + 33%|███▎ | 3950/11952 [2:48:14<12:56:11, 5.82s/it] {'loss': 0.4743, 'learning_rate': 1.5627175031237986e-05, 'epoch': 0.33} + 33%|███▎ | 3950/11952 [2:48:14<12:56:11, 5.82s/it] 33%|███▎ | 3951/11952 [2:48:20<12:52:18, 5.79s/it] {'loss': 0.4942, 'learning_rate': 1.562493468381545e-05, 'epoch': 0.33} + 33%|███▎ | 3951/11952 [2:48:20<12:52:18, 5.79s/it] 33%|███▎ | 3952/11952 [2:48:26<12:58:21, 5.84s/it] {'loss': 0.5027, 'learning_rate': 1.5622693923321105e-05, 'epoch': 0.33} + 33%|███▎ | 3952/11952 [2:48:26<12:58:21, 5.84s/it] 33%|███▎ | 3953/11952 [2:48:31<12:53:33, 5.80s/it] {'loss': 0.5063, 'learning_rate': 1.562045274991951e-05, 'epoch': 0.33} + 33%|███▎ | 3953/11952 [2:48:31<12:53:33, 5.80s/it] 33%|███▎ | 3954/11952 [2:48:37<12:58:50, 5.84s/it] {'loss': 0.5087, 'learning_rate': 1.5618211163775242e-05, 'epoch': 0.33} + 33%|███▎ | 3954/11952 [2:48:37<12:58:50, 5.84s/it] 33%|███▎ | 3955/11952 [2:48:43<12:49:08, 5.77s/it] {'loss': 0.4906, 'learning_rate': 1.561596916505291e-05, 'epoch': 0.33} + 33%|███▎ | 3955/11952 [2:48:43<12:49:08, 5.77s/it] 33%|███▎ | 3956/11952 [2:48:49<12:48:09, 5.76s/it] {'loss': 0.4729, 'learning_rate': 1.5613726753917166e-05, 'epoch': 0.33} + 33%|███▎ | 3956/11952 [2:48:49<12:48:09, 5.76s/it] 33%|███▎ | 3957/11952 [2:48:54<12:42:07, 5.72s/it] {'loss': 0.4925, 'learning_rate': 1.5611483930532677e-05, 'epoch': 0.33} + 33%|███▎ | 3957/11952 [2:48:54<12:42:07, 5.72s/it] 33%|███▎ | 3958/11952 [2:49:00<12:49:27, 5.78s/it] {'loss': 0.4867, 'learning_rate': 1.5609240695064146e-05, 'epoch': 0.33} + 33%|███▎ | 3958/11952 [2:49:00<12:49:27, 5.78s/it] 33%|███▎ | 3959/11952 [2:49:06<12:48:00, 5.77s/it] {'loss': 0.4978, 'learning_rate': 1.560699704767631e-05, 'epoch': 0.33} + 33%|███▎ | 3959/11952 [2:49:06<12:48:00, 5.77s/it] 33%|███▎ | 3960/11952 [2:49:12<12:48:07, 5.77s/it] {'loss': 0.4827, 'learning_rate': 1.5604752988533933e-05, 'epoch': 0.33} + 33%|███▎ | 3960/11952 [2:49:12<12:48:07, 5.77s/it] 33%|███▎ | 3961/11952 [2:49:18<12:54:29, 5.82s/it] {'loss': 0.4758, 'learning_rate': 1.560250851780181e-05, 'epoch': 0.33} + 33%|███▎ | 3961/11952 [2:49:18<12:54:29, 5.82s/it] 33%|███▎ | 3962/11952 [2:49:24<12:57:50, 5.84s/it] {'loss': 0.5156, 'learning_rate': 1.560026363564476e-05, 'epoch': 0.33} + 33%|███▎ | 3962/11952 [2:49:24<12:57:50, 5.84s/it] 33%|███▎ | 3963/11952 [2:49:29<12:58:57, 5.85s/it] {'loss': 0.4874, 'learning_rate': 1.5598018342227645e-05, 'epoch': 0.33} + 33%|███▎ | 3963/11952 [2:49:29<12:58:57, 5.85s/it] 33%|███▎ | 3964/11952 [2:49:35<13:03:24, 5.88s/it] {'loss': 0.4942, 'learning_rate': 1.5595772637715345e-05, 'epoch': 0.33} + 33%|███▎ | 3964/11952 [2:49:35<13:03:24, 5.88s/it] 33%|███▎ | 3965/11952 [2:49:41<13:03:46, 5.89s/it] {'loss': 0.4825, 'learning_rate': 1.5593526522272774e-05, 'epoch': 0.33} + 33%|███▎ | 3965/11952 [2:49:41<13:03:46, 5.89s/it] 33%|███▎ | 3966/11952 [2:49:47<12:57:26, 5.84s/it] {'loss': 0.4938, 'learning_rate': 1.5591279996064884e-05, 'epoch': 0.33} + 33%|███▎ | 3966/11952 [2:49:47<12:57:26, 5.84s/it] 33%|███▎ | 3967/11952 [2:49:53<12:56:29, 5.83s/it] {'loss': 0.5092, 'learning_rate': 1.558903305925665e-05, 'epoch': 0.33} + 33%|███▎ | 3967/11952 [2:49:53<12:56:29, 5.83s/it] 33%|███▎ | 3968/11952 [2:49:58<12:47:01, 5.76s/it] {'loss': 0.4806, 'learning_rate': 1.5586785712013073e-05, 'epoch': 0.33} + 33%|███▎ | 3968/11952 [2:49:58<12:47:01, 5.76s/it] 33%|███▎ | 3969/11952 [2:50:04<12:50:48, 5.79s/it] {'loss': 0.5001, 'learning_rate': 1.5584537954499186e-05, 'epoch': 0.33} + 33%|███▎ | 3969/11952 [2:50:04<12:50:48, 5.79s/it] 33%|███▎ | 3970/11952 [2:50:10<12:54:49, 5.82s/it] {'loss': 0.4897, 'learning_rate': 1.5582289786880064e-05, 'epoch': 0.33} + 33%|███▎ | 3970/11952 [2:50:10<12:54:49, 5.82s/it] 33%|███▎ | 3971/11952 [2:50:16<12:54:09, 5.82s/it] {'loss': 0.4813, 'learning_rate': 1.5580041209320797e-05, 'epoch': 0.33} + 33%|███▎ | 3971/11952 [2:50:16<12:54:09, 5.82s/it] 33%|███▎ | 3972/11952 [2:50:22<12:58:33, 5.85s/it] {'loss': 0.4873, 'learning_rate': 1.5577792221986512e-05, 'epoch': 0.33} + 33%|███▎ | 3972/11952 [2:50:22<12:58:33, 5.85s/it] 33%|███▎ | 3973/11952 [2:50:28<13:14:07, 5.97s/it] {'loss': 0.4936, 'learning_rate': 1.5575542825042368e-05, 'epoch': 0.33} + 33%|███▎ | 3973/11952 [2:50:28<13:14:07, 5.97s/it] 33%|███▎ | 3974/11952 [2:50:34<12:58:54, 5.86s/it] {'loss': 0.4823, 'learning_rate': 1.557329301865355e-05, 'epoch': 0.33} + 33%|███▎ | 3974/11952 [2:50:34<12:58:54, 5.86s/it] 33%|███▎ | 3975/11952 [2:50:40<13:06:20, 5.91s/it] {'loss': 0.4738, 'learning_rate': 1.557104280298527e-05, 'epoch': 0.33} + 33%|███▎ | 3975/11952 [2:50:40<13:06:20, 5.91s/it] 33%|███▎ | 3976/11952 [2:50:46<12:59:17, 5.86s/it] {'loss': 0.4857, 'learning_rate': 1.556879217820278e-05, 'epoch': 0.33} + 33%|███▎ | 3976/11952 [2:50:46<12:59:17, 5.86s/it] 33%|███▎ | 3977/11952 [2:50:51<12:56:18, 5.84s/it] {'loss': 0.4782, 'learning_rate': 1.5566541144471355e-05, 'epoch': 0.33} + 33%|███▎ | 3977/11952 [2:50:51<12:56:18, 5.84s/it] 33%|███▎ | 3978/11952 [2:50:57<12:53:36, 5.82s/it] {'loss': 0.5053, 'learning_rate': 1.55642897019563e-05, 'epoch': 0.33} + 33%|███▎ | 3978/11952 [2:50:57<12:53:36, 5.82s/it] 33%|███▎ | 3979/11952 [2:51:03<12:38:29, 5.71s/it] {'loss': 0.4842, 'learning_rate': 1.5562037850822954e-05, 'epoch': 0.33} + 33%|███▎ | 3979/11952 [2:51:03<12:38:29, 5.71s/it] 33%|███▎ | 3980/11952 [2:51:09<12:53:30, 5.82s/it] {'loss': 0.4971, 'learning_rate': 1.5559785591236683e-05, 'epoch': 0.33} + 33%|███▎ | 3980/11952 [2:51:09<12:53:30, 5.82s/it] 33%|███▎ | 3981/11952 [2:51:14<12:50:58, 5.80s/it] {'loss': 0.4861, 'learning_rate': 1.5557532923362883e-05, 'epoch': 0.33} + 33%|███▎ | 3981/11952 [2:51:14<12:50:58, 5.80s/it] 33%|███▎ | 3982/11952 [2:51:21<13:13:51, 5.98s/it] {'loss': 0.4977, 'learning_rate': 1.555527984736698e-05, 'epoch': 0.33} + 33%|███▎ | 3982/11952 [2:51:21<13:13:51, 5.98s/it] 33%|███▎ | 3983/11952 [2:51:27<13:10:46, 5.95s/it] {'loss': 0.5032, 'learning_rate': 1.555302636341443e-05, 'epoch': 0.33} + 33%|███▎ | 3983/11952 [2:51:27<13:10:46, 5.95s/it] 33%|███▎ | 3984/11952 [2:51:33<13:21:35, 6.04s/it] {'loss': 0.4829, 'learning_rate': 1.5550772471670724e-05, 'epoch': 0.33} + 33%|███▎ | 3984/11952 [2:51:33<13:21:35, 6.04s/it] 33%|███▎ | 3985/11952 [2:51:39<13:10:48, 5.96s/it] {'loss': 0.5062, 'learning_rate': 1.5548518172301373e-05, 'epoch': 0.33} + 33%|███▎ | 3985/11952 [2:51:39<13:10:48, 5.96s/it] 33%|███▎ | 3986/11952 [2:51:45<13:07:01, 5.93s/it] {'loss': 0.4957, 'learning_rate': 1.5546263465471926e-05, 'epoch': 0.33} + 33%|███▎ | 3986/11952 [2:51:45<13:07:01, 5.93s/it] 33%|███▎ | 3987/11952 [2:51:51<13:15:04, 5.99s/it] {'loss': 0.4942, 'learning_rate': 1.554400835134796e-05, 'epoch': 0.33} + 33%|███▎ | 3987/11952 [2:51:51<13:15:04, 5.99s/it] 33%|███▎ | 3988/11952 [2:51:56<13:06:47, 5.93s/it] {'loss': 0.4794, 'learning_rate': 1.554175283009508e-05, 'epoch': 0.33} + 33%|███▎ | 3988/11952 [2:51:56<13:06:47, 5.93s/it] 33%|███▎ | 3989/11952 [2:52:02<13:02:53, 5.90s/it] {'loss': 0.4872, 'learning_rate': 1.5539496901878915e-05, 'epoch': 0.33} + 33%|███▎ | 3989/11952 [2:52:02<13:02:53, 5.90s/it] 33%|███▎ | 3990/11952 [2:52:08<12:58:07, 5.86s/it] {'loss': 0.4901, 'learning_rate': 1.5537240566865145e-05, 'epoch': 0.33} + 33%|███▎ | 3990/11952 [2:52:08<12:58:07, 5.86s/it] 33%|███▎ | 3991/11952 [2:52:14<12:52:28, 5.82s/it] {'loss': 0.4855, 'learning_rate': 1.553498382521946e-05, 'epoch': 0.33} + 33%|███▎ | 3991/11952 [2:52:14<12:52:28, 5.82s/it] 33%|███▎ | 3992/11952 [2:52:20<12:50:48, 5.81s/it] {'loss': 0.4874, 'learning_rate': 1.5532726677107583e-05, 'epoch': 0.33} + 33%|███▎ | 3992/11952 [2:52:20<12:50:48, 5.81s/it] 33%|███▎ | 3993/11952 [2:52:25<12:42:50, 5.75s/it] {'loss': 0.4815, 'learning_rate': 1.553046912269527e-05, 'epoch': 0.33} + 33%|███▎ | 3993/11952 [2:52:25<12:42:50, 5.75s/it] 33%|███▎ | 3994/11952 [2:52:31<12:43:10, 5.75s/it] {'loss': 0.5012, 'learning_rate': 1.5528211162148305e-05, 'epoch': 0.33} + 33%|███▎ | 3994/11952 [2:52:31<12:43:10, 5.75s/it] 33%|███▎ | 3995/11952 [2:52:37<12:36:03, 5.70s/it] {'loss': 0.4831, 'learning_rate': 1.552595279563251e-05, 'epoch': 0.33} + 33%|███▎ | 3995/11952 [2:52:37<12:36:03, 5.70s/it] 33%|███▎ | 3996/11952 [2:52:42<12:43:33, 5.76s/it] {'loss': 0.487, 'learning_rate': 1.5523694023313723e-05, 'epoch': 0.33} + 33%|███▎ | 3996/11952 [2:52:42<12:43:33, 5.76s/it] 33%|███▎ | 3997/11952 [2:52:48<12:44:58, 5.77s/it] {'loss': 0.4729, 'learning_rate': 1.5521434845357824e-05, 'epoch': 0.33} + 33%|███▎ | 3997/11952 [2:52:48<12:44:58, 5.77s/it] 33%|███▎ | 3998/11952 [2:52:54<12:39:30, 5.73s/it] {'loss': 0.4859, 'learning_rate': 1.5519175261930716e-05, 'epoch': 0.33} + 33%|███▎ | 3998/11952 [2:52:54<12:39:30, 5.73s/it] 33%|███▎ | 3999/11952 [2:53:00<12:51:13, 5.82s/it] {'loss': 0.4979, 'learning_rate': 1.551691527319833e-05, 'epoch': 0.33} + 33%|███▎ | 3999/11952 [2:53:00<12:51:13, 5.82s/it]1 AutoResumeHook: Checking whether to suspend... +23 AutoResumeHook: Checking whether to suspend... +AutoResumeHook: Checking whether to suspend... +76 5 AutoResumeHook: Checking whether to suspend...AutoResumeHook: Checking whether to suspend... + +AutoResumeHook: Checking whether to suspend... +04 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... + 33%|███▎ | 4000/11952 [2:53:06<12:52:00, 5.83s/it] {'loss': 0.4947, 'learning_rate': 1.551465487932663e-05, 'epoch': 0.33} + 33%|███▎ | 4000/11952 [2:53:06<12:52:00, 5.83s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-4000/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-4000/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/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( + 33%|███▎ | 4001/11952 [2:53:38<30:30:35, 13.81s/it] {'loss': 0.48, 'learning_rate': 1.551239408048162e-05, 'epoch': 0.33} + 33%|███▎ | 4001/11952 [2:53:38<30:30:35, 13.81s/it] 33%|███▎ | 4002/11952 [2:53:44<25:04:51, 11.36s/it] {'loss': 0.4818, 'learning_rate': 1.5510132876829313e-05, 'epoch': 0.33} + 33%|███▎ | 4002/11952 [2:53:44<25:04:51, 11.36s/it] 33%|███▎ | 4003/11952 [2:53:49<21:14:46, 9.62s/it] {'loss': 0.4845, 'learning_rate': 1.5507871268535765e-05, 'epoch': 0.33} + 33%|███▎ | 4003/11952 [2:53:49<21:14:46, 9.62s/it] 34%|███▎ | 4004/11952 [2:53:55<18:43:11, 8.48s/it] {'loss': 0.5188, 'learning_rate': 1.550560925576706e-05, 'epoch': 0.33} + 34%|███▎ | 4004/11952 [2:53:55<18:43:11, 8.48s/it] 34%|███▎ | 4005/11952 [2:54:01<16:51:15, 7.64s/it] {'loss': 0.479, 'learning_rate': 1.5503346838689314e-05, 'epoch': 0.34} + 34%|███▎ | 4005/11952 [2:54:01<16:51:15, 7.64s/it] 34%|███▎ | 4006/11952 [2:54:07<15:37:18, 7.08s/it] {'loss': 0.5038, 'learning_rate': 1.5501084017468665e-05, 'epoch': 0.34} + 34%|███▎ | 4006/11952 [2:54:07<15:37:18, 7.08s/it] 34%|███▎ | 4007/11952 [2:54:13<14:53:33, 6.75s/it] {'loss': 0.5002, 'learning_rate': 1.5498820792271284e-05, 'epoch': 0.34} + 34%|███▎ | 4007/11952 [2:54:13<14:53:33, 6.75s/it] 34%|███▎ | 4008/11952 [2:54:19<14:26:18, 6.54s/it] {'loss': 0.5109, 'learning_rate': 1.549655716326338e-05, 'epoch': 0.34} + 34%|███▎ | 4008/11952 [2:54:19<14:26:18, 6.54s/it] 34%|███▎ | 4009/11952 [2:54:24<13:53:52, 6.30s/it] {'loss': 0.4899, 'learning_rate': 1.5494293130611175e-05, 'epoch': 0.34} + 34%|███▎ | 4009/11952 [2:54:24<13:53:52, 6.30s/it] 34%|███▎ | 4010/11952 [2:54:30<13:36:28, 6.17s/it] {'loss': 0.4973, 'learning_rate': 1.5492028694480938e-05, 'epoch': 0.34} + 34%|███▎ | 4010/11952 [2:54:30<13:36:28, 6.17s/it] 34%|███▎ | 4011/11952 [2:54:36<13:24:09, 6.08s/it] {'loss': 0.4873, 'learning_rate': 1.5489763855038954e-05, 'epoch': 0.34} + 34%|███▎ | 4011/11952 [2:54:36<13:24:09, 6.08s/it] 34%|███▎ | 4012/11952 [2:54:42<13:06:22, 5.94s/it] {'loss': 0.4707, 'learning_rate': 1.548749861245155e-05, 'epoch': 0.34} + 34%|███▎ | 4012/11952 [2:54:42<13:06:22, 5.94s/it] 34%|███▎ | 4013/11952 [2:54:48<13:09:17, 5.97s/it] {'loss': 0.48, 'learning_rate': 1.548523296688507e-05, 'epoch': 0.34} + 34%|███▎ | 4013/11952 [2:54:48<13:09:17, 5.97s/it] 34%|███▎ | 4014/11952 [2:54:53<12:58:53, 5.89s/it] {'loss': 0.4909, 'learning_rate': 1.5482966918505897e-05, 'epoch': 0.34} + 34%|███▎ | 4014/11952 [2:54:53<12:58:53, 5.89s/it] 34%|███▎ | 4015/11952 [2:55:00<13:08:00, 5.96s/it] {'loss': 0.496, 'learning_rate': 1.5480700467480437e-05, 'epoch': 0.34} + 34%|███▎ | 4015/11952 [2:55:00<13:08:00, 5.96s/it] 34%|███▎ | 4016/11952 [2:55:05<13:04:36, 5.93s/it] {'loss': 0.4784, 'learning_rate': 1.547843361397513e-05, 'epoch': 0.34} + 34%|███▎ | 4016/11952 [2:55:05<13:04:36, 5.93s/it] 34%|███▎ | 4017/11952 [2:55:11<13:03:49, 5.93s/it] {'loss': 0.49, 'learning_rate': 1.5476166358156446e-05, 'epoch': 0.34} + 34%|███▎ | 4017/11952 [2:55:11<13:03:49, 5.93s/it] 34%|███▎ | 4018/11952 [2:55:17<13:07:50, 5.96s/it] {'loss': 0.5039, 'learning_rate': 1.5473898700190884e-05, 'epoch': 0.34} + 34%|███▎ | 4018/11952 [2:55:17<13:07:50, 5.96s/it] 34%|███▎ | 4019/11952 [2:55:23<12:58:19, 5.89s/it] {'loss': 0.4724, 'learning_rate': 1.5471630640244966e-05, 'epoch': 0.34} + 34%|███▎ | 4019/11952 [2:55:23<12:58:19, 5.89s/it] 34%|███▎ | 4020/11952 [2:55:29<12:54:37, 5.86s/it] {'loss': 0.481, 'learning_rate': 1.5469362178485252e-05, 'epoch': 0.34} + 34%|███▎ | 4020/11952 [2:55:29<12:54:37, 5.86s/it] 34%|███▎ | 4021/11952 [2:55:35<12:54:20, 5.86s/it] {'loss': 0.5026, 'learning_rate': 1.546709331507833e-05, 'epoch': 0.34} + 34%|███▎ | 4021/11952 [2:55:35<12:54:20, 5.86s/it] 34%|███▎ | 4022/11952 [2:55:41<12:53:26, 5.85s/it] {'loss': 0.4854, 'learning_rate': 1.5464824050190816e-05, 'epoch': 0.34} + 34%|███▎ | 4022/11952 [2:55:41<12:53:26, 5.85s/it] 34%|███▎ | 4023/11952 [2:55:46<12:52:21, 5.84s/it] {'loss': 0.5195, 'learning_rate': 1.5462554383989347e-05, 'epoch': 0.34} + 34%|███▎ | 4023/11952 [2:55:46<12:52:21, 5.84s/it] 34%|███▎ | 4024/11952 [2:55:52<12:48:37, 5.82s/it] {'loss': 0.4913, 'learning_rate': 1.546028431664061e-05, 'epoch': 0.34} + 34%|███▎ | 4024/11952 [2:55:52<12:48:37, 5.82s/it] 34%|███▎ | 4025/11952 [2:55:58<12:48:18, 5.82s/it] {'loss': 0.4944, 'learning_rate': 1.5458013848311305e-05, 'epoch': 0.34} + 34%|███▎ | 4025/11952 [2:55:58<12:48:18, 5.82s/it] 34%|███▎ | 4026/11952 [2:56:04<12:41:01, 5.76s/it] {'loss': 0.4911, 'learning_rate': 1.545574297916816e-05, 'epoch': 0.34} + 34%|███▎ | 4026/11952 [2:56:04<12:41:01, 5.76s/it] 34%|███▎ | 4027/11952 [2:56:10<12:46:06, 5.80s/it] {'loss': 0.4948, 'learning_rate': 1.5453471709377945e-05, 'epoch': 0.34} + 34%|███▎ | 4027/11952 [2:56:10<12:46:06, 5.80s/it] 34%|███▎ | 4028/11952 [2:56:15<12:44:11, 5.79s/it] {'loss': 0.4996, 'learning_rate': 1.545120003910745e-05, 'epoch': 0.34} + 34%|███▎ | 4028/11952 [2:56:15<12:44:11, 5.79s/it] 34%|███▎ | 4029/11952 [2:56:21<12:41:26, 5.77s/it] {'loss': 0.4778, 'learning_rate': 1.54489279685235e-05, 'epoch': 0.34} + 34%|███▎ | 4029/11952 [2:56:21<12:41:26, 5.77s/it] 34%|███▎ | 4030/11952 [2:56:27<12:38:19, 5.74s/it] {'loss': 0.4836, 'learning_rate': 1.544665549779294e-05, 'epoch': 0.34} + 34%|███▎ | 4030/11952 [2:56:27<12:38:19, 5.74s/it] 34%|███▎ | 4031/11952 [2:56:33<12:51:40, 5.85s/it] {'loss': 0.4674, 'learning_rate': 1.5444382627082657e-05, 'epoch': 0.34} + 34%|███▎ | 4031/11952 [2:56:33<12:51:40, 5.85s/it] 34%|███▎ | 4032/11952 [2:56:39<12:48:01, 5.82s/it] {'loss': 0.4828, 'learning_rate': 1.5442109356559556e-05, 'epoch': 0.34} + 34%|███▎ | 4032/11952 [2:56:39<12:48:01, 5.82s/it] 34%|███▎ | 4033/11952 [2:56:44<12:39:05, 5.75s/it] {'loss': 0.4952, 'learning_rate': 1.543983568639058e-05, 'epoch': 0.34} + 34%|███▎ | 4033/11952 [2:56:44<12:39:05, 5.75s/it] 34%|███▍ | 4034/11952 [2:56:50<12:49:12, 5.83s/it] {'loss': 0.4733, 'learning_rate': 1.5437561616742703e-05, 'epoch': 0.34} + 34%|███▍ | 4034/11952 [2:56:50<12:49:12, 5.83s/it] 34%|███▍ | 4035/11952 [2:56:56<12:44:43, 5.80s/it] {'loss': 0.4976, 'learning_rate': 1.543528714778291e-05, 'epoch': 0.34} + 34%|███▍ | 4035/11952 [2:56:56<12:44:43, 5.80s/it] 34%|███▍ | 4036/11952 [2:57:02<12:44:06, 5.79s/it] {'loss': 0.4952, 'learning_rate': 1.543301227967824e-05, 'epoch': 0.34} + 34%|███▍ | 4036/11952 [2:57:02<12:44:06, 5.79s/it] 34%|███▍ | 4037/11952 [2:57:07<12:36:19, 5.73s/it] {'loss': 0.496, 'learning_rate': 1.543073701259574e-05, 'epoch': 0.34} + 34%|███▍ | 4037/11952 [2:57:07<12:36:19, 5.73s/it] 34%|███▍ | 4038/11952 [2:57:13<12:36:54, 5.74s/it] {'loss': 0.4901, 'learning_rate': 1.542846134670251e-05, 'epoch': 0.34} + 34%|███▍ | 4038/11952 [2:57:13<12:36:54, 5.74s/it] 34%|███▍ | 4039/11952 [2:57:19<12:53:02, 5.86s/it] {'loss': 0.5044, 'learning_rate': 1.5426185282165652e-05, 'epoch': 0.34} + 34%|███▍ | 4039/11952 [2:57:19<12:53:02, 5.86s/it] 34%|███▍ | 4040/11952 [2:57:25<12:47:54, 5.82s/it] {'loss': 0.4779, 'learning_rate': 1.5423908819152317e-05, 'epoch': 0.34} + 34%|███▍ | 4040/11952 [2:57:25<12:47:54, 5.82s/it] 34%|███▍ | 4041/11952 [2:57:31<12:56:43, 5.89s/it] {'loss': 0.5076, 'learning_rate': 1.542163195782968e-05, 'epoch': 0.34} + 34%|███▍ | 4041/11952 [2:57:31<12:56:43, 5.89s/it] 34%|███▍ | 4042/11952 [2:57:37<12:50:52, 5.85s/it] {'loss': 0.4836, 'learning_rate': 1.5419354698364944e-05, 'epoch': 0.34} + 34%|███▍ | 4042/11952 [2:57:37<12:50:52, 5.85s/it] 34%|███▍ | 4043/11952 [2:57:43<12:52:45, 5.86s/it] {'loss': 0.4994, 'learning_rate': 1.5417077040925334e-05, 'epoch': 0.34} + 34%|███▍ | 4043/11952 [2:57:43<12:52:45, 5.86s/it] 34%|███▍ | 4044/11952 [2:57:49<12:59:19, 5.91s/it] {'loss': 0.5221, 'learning_rate': 1.541479898567812e-05, 'epoch': 0.34} + 34%|███▍ | 4044/11952 [2:57:49<12:59:19, 5.91s/it] 34%|███▍ | 4045/11952 [2:57:54<12:56:15, 5.89s/it] {'loss': 0.4938, 'learning_rate': 1.541252053279059e-05, 'epoch': 0.34} + 34%|███▍ | 4045/11952 [2:57:54<12:56:15, 5.89s/it] 34%|███▍ | 4046/11952 [2:58:00<13:00:06, 5.92s/it] {'loss': 0.4794, 'learning_rate': 1.541024168243007e-05, 'epoch': 0.34} + 34%|███▍ | 4046/11952 [2:58:00<13:00:06, 5.92s/it] 34%|███▍ | 4047/11952 [2:58:06<12:49:16, 5.84s/it] {'loss': 0.4798, 'learning_rate': 1.5407962434763897e-05, 'epoch': 0.34} + 34%|███▍ | 4047/11952 [2:58:06<12:49:16, 5.84s/it] 34%|███▍ | 4048/11952 [2:58:12<12:42:07, 5.79s/it] {'loss': 0.4878, 'learning_rate': 1.5405682789959455e-05, 'epoch': 0.34} + 34%|███▍ | 4048/11952 [2:58:12<12:42:07, 5.79s/it] 34%|███▍ | 4049/11952 [2:58:17<12:39:16, 5.76s/it] {'loss': 0.5025, 'learning_rate': 1.5403402748184156e-05, 'epoch': 0.34} + 34%|███▍ | 4049/11952 [2:58:17<12:39:16, 5.76s/it]1 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... +0 AutoResumeHook: Checking whether to suspend... + 34%|███▍ | 4050/11952 [2:58:24<13:00:00, 5.92s/it]7 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4778, 'learning_rate': 1.5401122309605437e-05, 'epoch': 0.34} + 34%|███▍ | 4050/11952 [2:58:24<13:00:00, 5.92s/it] 34%|███▍ | 4051/11952 [2:58:29<12:43:33, 5.80s/it] {'loss': 0.4801, 'learning_rate': 1.5398841474390754e-05, 'epoch': 0.34} + 34%|███▍ | 4051/11952 [2:58:29<12:43:33, 5.80s/it] 34%|███▍ | 4052/11952 [2:58:35<12:36:23, 5.74s/it] {'loss': 0.4845, 'learning_rate': 1.5396560242707613e-05, 'epoch': 0.34} + 34%|███▍ | 4052/11952 [2:58:35<12:36:23, 5.74s/it] 34%|███▍ | 4053/11952 [2:58:41<12:37:37, 5.75s/it] {'loss': 0.4736, 'learning_rate': 1.5394278614723535e-05, 'epoch': 0.34} + 34%|███▍ | 4053/11952 [2:58:41<12:37:37, 5.75s/it] 34%|███▍ | 4054/11952 [2:58:47<12:44:59, 5.81s/it] {'loss': 0.5036, 'learning_rate': 1.5391996590606066e-05, 'epoch': 0.34} + 34%|███▍ | 4054/11952 [2:58:47<12:44:59, 5.81s/it] 34%|███▍ | 4055/11952 [2:58:52<12:45:41, 5.82s/it] {'loss': 0.5004, 'learning_rate': 1.53897141705228e-05, 'epoch': 0.34} + 34%|███▍ | 4055/11952 [2:58:52<12:45:41, 5.82s/it] 34%|███▍ | 4056/11952 [2:58:58<12:49:31, 5.85s/it] {'loss': 0.4898, 'learning_rate': 1.538743135464134e-05, 'epoch': 0.34} + 34%|███▍ | 4056/11952 [2:58:58<12:49:31, 5.85s/it] 34%|███▍ | 4057/11952 [2:59:04<12:42:08, 5.79s/it] {'loss': 0.4723, 'learning_rate': 1.5385148143129328e-05, 'epoch': 0.34} + 34%|███▍ | 4057/11952 [2:59:04<12:42:08, 5.79s/it] 34%|███▍ | 4058/11952 [2:59:10<12:44:44, 5.81s/it] {'loss': 0.5157, 'learning_rate': 1.5382864536154437e-05, 'epoch': 0.34} + 34%|███▍ | 4058/11952 [2:59:10<12:44:44, 5.81s/it] 34%|███▍ | 4059/11952 [2:59:16<12:41:24, 5.79s/it] {'loss': 0.4803, 'learning_rate': 1.5380580533884364e-05, 'epoch': 0.34} + 34%|███▍ | 4059/11952 [2:59:16<12:41:24, 5.79s/it] 34%|███▍ | 4060/11952 [2:59:22<12:46:02, 5.82s/it] {'loss': 0.5016, 'learning_rate': 1.5378296136486837e-05, 'epoch': 0.34} + 34%|███▍ | 4060/11952 [2:59:22<12:46:02, 5.82s/it] 34%|███▍ | 4061/11952 [2:59:27<12:34:29, 5.74s/it] {'loss': 0.5045, 'learning_rate': 1.5376011344129608e-05, 'epoch': 0.34} + 34%|███▍ | 4061/11952 [2:59:27<12:34:29, 5.74s/it] 34%|███▍ | 4062/11952 [2:59:33<12:33:40, 5.73s/it] {'loss': 0.4805, 'learning_rate': 1.537372615698047e-05, 'epoch': 0.34} + 34%|███▍ | 4062/11952 [2:59:33<12:33:40, 5.73s/it] 34%|███▍ | 4063/11952 [2:59:39<12:35:36, 5.75s/it] {'loss': 0.5004, 'learning_rate': 1.5371440575207233e-05, 'epoch': 0.34} + 34%|███▍ | 4063/11952 [2:59:39<12:35:36, 5.75s/it] 34%|███▍ | 4064/11952 [2:59:44<12:26:51, 5.68s/it] {'loss': 0.4941, 'learning_rate': 1.536915459897774e-05, 'epoch': 0.34} + 34%|███▍ | 4064/11952 [2:59:44<12:26:51, 5.68s/it] 34%|███▍ | 4065/11952 [2:59:50<12:30:51, 5.71s/it] {'loss': 0.4623, 'learning_rate': 1.5366868228459866e-05, 'epoch': 0.34} + 34%|███▍ | 4065/11952 [2:59:50<12:30:51, 5.71s/it] 34%|███▍ | 4066/11952 [2:59:55<12:26:56, 5.68s/it] {'loss': 0.4911, 'learning_rate': 1.536458146382151e-05, 'epoch': 0.34} + 34%|███▍ | 4066/11952 [2:59:55<12:26:56, 5.68s/it] 34%|███▍ | 4067/11952 [3:00:01<12:29:48, 5.71s/it] {'loss': 0.4749, 'learning_rate': 1.536229430523061e-05, 'epoch': 0.34} + 34%|███▍ | 4067/11952 [3:00:01<12:29:48, 5.71s/it] 34%|███▍ | 4068/11952 [3:00:07<12:30:58, 5.72s/it] {'loss': 0.4797, 'learning_rate': 1.5360006752855113e-05, 'epoch': 0.34} + 34%|███▍ | 4068/11952 [3:00:07<12:30:58, 5.72s/it] 34%|███▍ | 4069/11952 [3:00:13<12:32:11, 5.73s/it] {'loss': 0.4853, 'learning_rate': 1.535771880686302e-05, 'epoch': 0.34} + 34%|███▍ | 4069/11952 [3:00:13<12:32:11, 5.73s/it] 34%|███▍ | 4070/11952 [3:00:19<12:44:55, 5.82s/it] {'loss': 0.4968, 'learning_rate': 1.5355430467422343e-05, 'epoch': 0.34} + 34%|███▍ | 4070/11952 [3:00:19<12:44:55, 5.82s/it] 34%|███▍ | 4071/11952 [3:00:24<12:39:16, 5.78s/it] {'loss': 0.4907, 'learning_rate': 1.535314173470112e-05, 'epoch': 0.34} + 34%|███▍ | 4071/11952 [3:00:24<12:39:16, 5.78s/it] 34%|███▍ | 4072/11952 [3:00:30<12:36:42, 5.76s/it] {'loss': 0.4847, 'learning_rate': 1.5350852608867436e-05, 'epoch': 0.34} + 34%|███▍ | 4072/11952 [3:00:30<12:36:42, 5.76s/it] 34%|███▍ | 4073/11952 [3:00:36<12:36:47, 5.76s/it] {'loss': 0.5151, 'learning_rate': 1.5348563090089394e-05, 'epoch': 0.34} + 34%|███▍ | 4073/11952 [3:00:36<12:36:47, 5.76s/it] 34%|███▍ | 4074/11952 [3:00:42<12:43:00, 5.81s/it] {'loss': 0.4775, 'learning_rate': 1.5346273178535126e-05, 'epoch': 0.34} + 34%|███▍ | 4074/11952 [3:00:42<12:43:00, 5.81s/it] 34%|███▍ | 4075/11952 [3:00:48<12:44:45, 5.83s/it] {'loss': 0.4907, 'learning_rate': 1.534398287437279e-05, 'epoch': 0.34} + 34%|███▍ | 4075/11952 [3:00:48<12:44:45, 5.83s/it] 34%|███▍ | 4076/11952 [3:00:53<12:37:55, 5.77s/it] {'loss': 0.466, 'learning_rate': 1.5341692177770583e-05, 'epoch': 0.34} + 34%|███▍ | 4076/11952 [3:00:53<12:37:55, 5.77s/it] 34%|███▍ | 4077/11952 [3:00:59<12:23:38, 5.67s/it] {'loss': 0.5019, 'learning_rate': 1.5339401088896715e-05, 'epoch': 0.34} + 34%|███▍ | 4077/11952 [3:00:59<12:23:38, 5.67s/it] 34%|███▍ | 4078/11952 [3:01:05<12:30:36, 5.72s/it] {'loss': 0.4801, 'learning_rate': 1.533710960791944e-05, 'epoch': 0.34} + 34%|███▍ | 4078/11952 [3:01:05<12:30:36, 5.72s/it] 34%|███▍ | 4079/11952 [3:01:11<12:47:07, 5.85s/it] {'loss': 0.4967, 'learning_rate': 1.5334817735007037e-05, 'epoch': 0.34} + 34%|███▍ | 4079/11952 [3:01:11<12:47:07, 5.85s/it] 34%|███▍ | 4080/11952 [3:01:17<12:52:33, 5.89s/it] {'loss': 0.4966, 'learning_rate': 1.533252547032781e-05, 'epoch': 0.34} + 34%|███▍ | 4080/11952 [3:01:17<12:52:33, 5.89s/it] 34%|███▍ | 4081/11952 [3:01:23<12:55:20, 5.91s/it] {'loss': 0.5023, 'learning_rate': 1.533023281405009e-05, 'epoch': 0.34} + 34%|███▍ | 4081/11952 [3:01:23<12:55:20, 5.91s/it] 34%|███▍ | 4082/11952 [3:01:29<12:54:13, 5.90s/it] {'loss': 0.5038, 'learning_rate': 1.5327939766342237e-05, 'epoch': 0.34} + 34%|███▍ | 4082/11952 [3:01:29<12:54:13, 5.90s/it] 34%|███▍ | 4083/11952 [3:01:35<13:06:25, 6.00s/it] {'loss': 0.4999, 'learning_rate': 1.5325646327372658e-05, 'epoch': 0.34} + 34%|███▍ | 4083/11952 [3:01:35<13:06:25, 6.00s/it] 34%|███▍ | 4084/11952 [3:01:41<13:00:52, 5.95s/it] {'loss': 0.4819, 'learning_rate': 1.532335249730976e-05, 'epoch': 0.34} + 34%|███▍ | 4084/11952 [3:01:41<13:00:52, 5.95s/it] 34%|███▍ | 4085/11952 [3:01:47<12:58:27, 5.94s/it] {'loss': 0.4924, 'learning_rate': 1.5321058276321988e-05, 'epoch': 0.34} + 34%|███▍ | 4085/11952 [3:01:47<12:58:27, 5.94s/it] 34%|███▍ | 4086/11952 [3:01:52<12:52:24, 5.89s/it] {'loss': 0.4895, 'learning_rate': 1.5318763664577838e-05, 'epoch': 0.34} + 34%|███▍ | 4086/11952 [3:01:52<12:52:24, 5.89s/it] 34%|███▍ | 4087/11952 [3:01:58<12:45:28, 5.84s/it] {'loss': 0.4882, 'learning_rate': 1.5316468662245805e-05, 'epoch': 0.34} + 34%|███▍ | 4087/11952 [3:01:58<12:45:28, 5.84s/it] 34%|███▍ | 4088/11952 [3:02:04<12:47:11, 5.85s/it] {'loss': 0.4849, 'learning_rate': 1.531417326949442e-05, 'epoch': 0.34} + 34%|███▍ | 4088/11952 [3:02:04<12:47:11, 5.85s/it] 34%|███▍ | 4089/11952 [3:02:10<12:51:22, 5.89s/it] {'loss': 0.4824, 'learning_rate': 1.5311877486492264e-05, 'epoch': 0.34} + 34%|███▍ | 4089/11952 [3:02:10<12:51:22, 5.89s/it] 34%|███▍ | 4090/11952 [3:02:16<12:55:41, 5.92s/it] {'loss': 0.483, 'learning_rate': 1.5309581313407914e-05, 'epoch': 0.34} + 34%|███▍ | 4090/11952 [3:02:16<12:55:41, 5.92s/it] 34%|███▍ | 4091/11952 [3:02:22<12:51:07, 5.89s/it] {'loss': 0.4939, 'learning_rate': 1.5307284750409993e-05, 'epoch': 0.34} + 34%|███▍ | 4091/11952 [3:02:22<12:51:07, 5.89s/it] 34%|███▍ | 4092/11952 [3:02:28<12:49:43, 5.88s/it] {'loss': 0.5149, 'learning_rate': 1.530498779766716e-05, 'epoch': 0.34} + 34%|███▍ | 4092/11952 [3:02:28<12:49:43, 5.88s/it] 34%|███▍ | 4093/11952 [3:02:33<12:46:18, 5.85s/it] {'loss': 0.4828, 'learning_rate': 1.5302690455348085e-05, 'epoch': 0.34} + 34%|███▍ | 4093/11952 [3:02:33<12:46:18, 5.85s/it] 34%|███▍ | 4094/11952 [3:02:39<12:45:03, 5.84s/it] {'loss': 0.4805, 'learning_rate': 1.530039272362148e-05, 'epoch': 0.34} + 34%|███▍ | 4094/11952 [3:02:39<12:45:03, 5.84s/it] 34%|███▍ | 4095/11952 [3:02:45<12:41:34, 5.82s/it] {'loss': 0.4946, 'learning_rate': 1.5298094602656077e-05, 'epoch': 0.34} + 34%|███▍ | 4095/11952 [3:02:45<12:41:34, 5.82s/it] 34%|███▍ | 4096/11952 [3:02:50<12:26:18, 5.70s/it] {'loss': 0.4826, 'learning_rate': 1.5295796092620646e-05, 'epoch': 0.34} + 34%|███▍ | 4096/11952 [3:02:50<12:26:18, 5.70s/it] 34%|███▍ | 4097/11952 [3:02:56<12:38:37, 5.79s/it] {'loss': 0.5091, 'learning_rate': 1.5293497193683974e-05, 'epoch': 0.34} + 34%|███▍ | 4097/11952 [3:02:56<12:38:37, 5.79s/it] 34%|███▍ | 4098/11952 [3:03:02<12:31:32, 5.74s/it] {'loss': 0.4893, 'learning_rate': 1.5291197906014886e-05, 'epoch': 0.34} + 34%|███▍ | 4098/11952 [3:03:02<12:31:32, 5.74s/it] 34%|███▍ | 4099/11952 [3:03:08<12:28:49, 5.72s/it] {'loss': 0.4873, 'learning_rate': 1.5288898229782234e-05, 'epoch': 0.34} + 34%|███▍ | 4099/11952 [3:03:08<12:28:49, 5.72s/it]5 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... +07 AutoResumeHook: Checking whether to suspend... + 4 AutoResumeHook: Checking whether to suspend... +AutoResumeHook: Checking whether to suspend... + 34%|███▍ | 4100/11952 [3:03:14<12:45:41, 5.85s/it] {'loss': 0.4815, 'learning_rate': 1.5286598165154892e-05, 'epoch': 0.34} + 34%|███▍ | 4100/11952 [3:03:14<12:45:41, 5.85s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-4100/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-4100/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/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( + 34%|███▍ | 4101/11952 [3:03:46<30:07:28, 13.81s/it] {'loss': 0.4878, 'learning_rate': 1.5284297712301773e-05, 'epoch': 0.34} + 34%|███▍ | 4101/11952 [3:03:46<30:07:28, 13.81s/it] 34%|███▍ | 4102/11952 [3:03:52<24:52:19, 11.41s/it] {'loss': 0.4834, 'learning_rate': 1.5281996871391805e-05, 'epoch': 0.34} + 34%|███▍ | 4102/11952 [3:03:52<24:52:19, 11.41s/it] 34%|███▍ | 4103/11952 [3:04:01<23:02:09, 10.57s/it] {'loss': 0.4621, 'learning_rate': 1.5279695642593958e-05, 'epoch': 0.34} + 34%|███▍ | 4103/11952 [3:04:01<23:02:09, 10.57s/it] 34%|███▍ | 4104/11952 [3:04:06<19:56:20, 9.15s/it] {'loss': 0.4742, 'learning_rate': 1.527739402607722e-05, 'epoch': 0.34} + 34%|███▍ | 4104/11952 [3:04:06<19:56:20, 9.15s/it] 34%|███▍ | 4105/11952 [3:04:12<17:36:48, 8.08s/it] {'loss': 0.4787, 'learning_rate': 1.527509202201062e-05, 'epoch': 0.34} + 34%|███▍ | 4105/11952 [3:04:12<17:36:48, 8.08s/it] 34%|███▍ | 4106/11952 [3:04:18<16:05:03, 7.38s/it] {'loss': 0.495, 'learning_rate': 1.5272789630563202e-05, 'epoch': 0.34} + 34%|███▍ | 4106/11952 [3:04:18<16:05:03, 7.38s/it] 34%|███▍ | 4107/11952 [3:04:24<15:00:58, 6.89s/it] {'loss': 0.495, 'learning_rate': 1.527048685190404e-05, 'epoch': 0.34} + 34%|███▍ | 4107/11952 [3:04:24<15:00:58, 6.89s/it] 34%|███▍ | 4108/11952 [3:04:29<14:11:26, 6.51s/it] {'loss': 0.51, 'learning_rate': 1.5268183686202245e-05, 'epoch': 0.34} + 34%|███▍ | 4108/11952 [3:04:29<14:11:26, 6.51s/it] 34%|███▍ | 4109/11952 [3:04:35<13:44:51, 6.31s/it] {'loss': 0.4721, 'learning_rate': 1.5265880133626956e-05, 'epoch': 0.34} + 34%|███▍ | 4109/11952 [3:04:35<13:44:51, 6.31s/it] 34%|███▍ | 4110/11952 [3:04:41<13:33:32, 6.22s/it] {'loss': 0.498, 'learning_rate': 1.5263576194347334e-05, 'epoch': 0.34} + 34%|███▍ | 4110/11952 [3:04:41<13:33:32, 6.22s/it] 34%|███▍ | 4111/11952 [3:04:47<13:18:06, 6.11s/it] {'loss': 0.5005, 'learning_rate': 1.5261271868532568e-05, 'epoch': 0.34} + 34%|███▍ | 4111/11952 [3:04:47<13:18:06, 6.11s/it] 34%|███▍ | 4112/11952 [3:04:53<13:00:20, 5.97s/it] {'loss': 0.4735, 'learning_rate': 1.5258967156351878e-05, 'epoch': 0.34} + 34%|███▍ | 4112/11952 [3:04:53<13:00:20, 5.97s/it] 34%|███▍ | 4113/11952 [3:04:58<12:53:52, 5.92s/it] {'loss': 0.4863, 'learning_rate': 1.525666205797451e-05, 'epoch': 0.34} + 34%|███▍ | 4113/11952 [3:04:58<12:53:52, 5.92s/it] 34%|███▍ | 4114/11952 [3:05:05<13:07:18, 6.03s/it] {'loss': 0.4886, 'learning_rate': 1.5254356573569748e-05, 'epoch': 0.34} + 34%|███▍ | 4114/11952 [3:05:05<13:07:18, 6.03s/it] 34%|███▍ | 4115/11952 [3:05:10<12:55:22, 5.94s/it] {'loss': 0.4866, 'learning_rate': 1.5252050703306895e-05, 'epoch': 0.34} + 34%|███▍ | 4115/11952 [3:05:10<12:55:22, 5.94s/it] 34%|███▍ | 4116/11952 [3:05:16<12:46:24, 5.87s/it] {'loss': 0.5044, 'learning_rate': 1.5249744447355282e-05, 'epoch': 0.34} + 34%|███▍ | 4116/11952 [3:05:16<12:46:24, 5.87s/it] 34%|███▍ | 4117/11952 [3:05:22<12:43:41, 5.85s/it] {'loss': 0.4863, 'learning_rate': 1.5247437805884273e-05, 'epoch': 0.34} + 34%|███▍ | 4117/11952 [3:05:22<12:43:41, 5.85s/it] 34%|███▍ | 4118/11952 [3:05:28<12:54:26, 5.93s/it] {'loss': 0.5085, 'learning_rate': 1.5245130779063255e-05, 'epoch': 0.34} + 34%|███▍ | 4118/11952 [3:05:28<12:54:26, 5.93s/it] 34%|███▍ | 4119/11952 [3:05:34<12:40:03, 5.82s/it] {'loss': 0.4725, 'learning_rate': 1.524282336706165e-05, 'epoch': 0.34} + 34%|███▍ | 4119/11952 [3:05:34<12:40:03, 5.82s/it] 34%|███▍ | 4120/11952 [3:05:39<12:35:30, 5.79s/it] {'loss': 0.4866, 'learning_rate': 1.5240515570048903e-05, 'epoch': 0.34} + 34%|███▍ | 4120/11952 [3:05:39<12:35:30, 5.79s/it] 34%|███▍ | 4121/11952 [3:05:45<12:46:59, 5.88s/it] {'loss': 0.485, 'learning_rate': 1.5238207388194493e-05, 'epoch': 0.34} + 34%|███▍ | 4121/11952 [3:05:45<12:46:59, 5.88s/it] 34%|███▍ | 4122/11952 [3:05:51<12:46:14, 5.87s/it] {'loss': 0.5004, 'learning_rate': 1.5235898821667916e-05, 'epoch': 0.34} + 34%|███▍ | 4122/11952 [3:05:51<12:46:14, 5.87s/it] 34%|███▍ | 4123/11952 [3:05:57<12:34:01, 5.78s/it] {'loss': 0.4852, 'learning_rate': 1.5233589870638708e-05, 'epoch': 0.34} + 34%|███▍ | 4123/11952 [3:05:57<12:34:01, 5.78s/it] 35%|███▍ | 4124/11952 [3:06:03<12:33:07, 5.77s/it] {'loss': 0.4778, 'learning_rate': 1.5231280535276426e-05, 'epoch': 0.35} + 35%|███▍ | 4124/11952 [3:06:03<12:33:07, 5.77s/it] 35%|███▍ | 4125/11952 [3:06:08<12:24:24, 5.71s/it] {'loss': 0.4932, 'learning_rate': 1.5228970815750666e-05, 'epoch': 0.35} + 35%|███▍ | 4125/11952 [3:06:08<12:24:24, 5.71s/it] 35%|███▍ | 4126/11952 [3:06:14<12:25:41, 5.72s/it] {'loss': 0.4973, 'learning_rate': 1.5226660712231032e-05, 'epoch': 0.35} + 35%|███▍ | 4126/11952 [3:06:14<12:25:41, 5.72s/it] 35%|███▍ | 4127/11952 [3:06:19<12:23:33, 5.70s/it] {'loss': 0.4899, 'learning_rate': 1.5224350224887179e-05, 'epoch': 0.35} + 35%|███▍ | 4127/11952 [3:06:19<12:23:33, 5.70s/it] 35%|███▍ | 4128/11952 [3:06:25<12:18:42, 5.66s/it] {'loss': 0.4763, 'learning_rate': 1.5222039353888774e-05, 'epoch': 0.35} + 35%|███▍ | 4128/11952 [3:06:25<12:18:42, 5.66s/it] 35%|███▍ | 4129/11952 [3:06:31<12:20:27, 5.68s/it] {'loss': 0.4994, 'learning_rate': 1.5219728099405516e-05, 'epoch': 0.35} + 35%|███▍ | 4129/11952 [3:06:31<12:20:27, 5.68s/it] 35%|███▍ | 4130/11952 [3:06:37<12:26:36, 5.73s/it] {'loss': 0.4798, 'learning_rate': 1.521741646160714e-05, 'epoch': 0.35} + 35%|███▍ | 4130/11952 [3:06:37<12:26:36, 5.73s/it] 35%|███▍ | 4131/11952 [3:06:42<12:32:16, 5.77s/it] {'loss': 0.4698, 'learning_rate': 1.5215104440663399e-05, 'epoch': 0.35} + 35%|███▍ | 4131/11952 [3:06:42<12:32:16, 5.77s/it] 35%|███▍ | 4132/11952 [3:06:51<14:08:55, 6.51s/it] {'loss': 0.472, 'learning_rate': 1.521279203674408e-05, 'epoch': 0.35} + 35%|███▍ | 4132/11952 [3:06:51<14:08:55, 6.51s/it] 35%|███▍ | 4133/11952 [3:06:56<13:39:34, 6.29s/it] {'loss': 0.4933, 'learning_rate': 1.5210479250018995e-05, 'epoch': 0.35} + 35%|███▍ | 4133/11952 [3:06:56<13:39:34, 6.29s/it] 35%|███▍ | 4134/11952 [3:07:02<13:14:14, 6.10s/it] {'loss': 0.4828, 'learning_rate': 1.5208166080657982e-05, 'epoch': 0.35} + 35%|███▍ | 4134/11952 [3:07:02<13:14:14, 6.10s/it] 35%|███▍ | 4135/11952 [3:07:08<13:03:20, 6.01s/it] {'loss': 0.497, 'learning_rate': 1.520585252883092e-05, 'epoch': 0.35} + 35%|███▍ | 4135/11952 [3:07:08<13:03:20, 6.01s/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%|███▍ | 4136/11952 [3:07:14<12:48:52, 5.90s/it] {'loss': 0.4824, 'learning_rate': 1.5203538594707699e-05, 'epoch': 0.35} + 35%|███▍ | 4136/11952 [3:07:14<12:48:52, 5.90s/it] 35%|███▍ | 4137/11952 [3:07:19<12:42:11, 5.85s/it] {'loss': 0.4743, 'learning_rate': 1.520122427845825e-05, 'epoch': 0.35} + 35%|███▍ | 4137/11952 [3:07:19<12:42:11, 5.85s/it] 35%|███▍ | 4138/11952 [3:07:28<14:47:03, 6.81s/it] {'loss': 0.5035, 'learning_rate': 1.5198909580252517e-05, 'epoch': 0.35} + 35%|███▍ | 4138/11952 [3:07:28<14:47:03, 6.81s/it] 35%|███▍ | 4139/11952 [3:07:34<14:11:51, 6.54s/it] {'loss': 0.5019, 'learning_rate': 1.519659450026049e-05, 'epoch': 0.35} + 35%|███▍ | 4139/11952 [3:07:34<14:11:51, 6.54s/it] 35%|███▍ | 4140/11952 [3:07:40<13:39:37, 6.30s/it] {'loss': 0.5058, 'learning_rate': 1.519427903865218e-05, 'epoch': 0.35} + 35%|███▍ | 4140/11952 [3:07:40<13:39:37, 6.30s/it] 35%|███▍ | 4141/11952 [3:07:46<13:42:09, 6.32s/it] {'loss': 0.4959, 'learning_rate': 1.519196319559762e-05, 'epoch': 0.35} + 35%|███▍ | 4141/11952 [3:07:46<13:42:09, 6.32s/it] 35%|███▍ | 4142/11952 [3:07:55<14:53:53, 6.87s/it] {'loss': 0.4922, 'learning_rate': 1.518964697126688e-05, 'epoch': 0.35} + 35%|███▍ | 4142/11952 [3:07:55<14:53:53, 6.87s/it] 35%|███▍ | 4143/11952 [3:08:00<14:05:01, 6.49s/it] {'loss': 0.5021, 'learning_rate': 1.518733036583005e-05, 'epoch': 0.35} + 35%|███▍ | 4143/11952 [3:08:00<14:05:01, 6.49s/it] 35%|███▍ | 4144/11952 [3:08:06<13:52:56, 6.40s/it] {'loss': 0.4927, 'learning_rate': 1.5185013379457254e-05, 'epoch': 0.35} + 35%|███▍ | 4144/11952 [3:08:06<13:52:56, 6.40s/it] 35%|███▍ | 4145/11952 [3:08:15<15:38:18, 7.21s/it] {'loss': 0.5034, 'learning_rate': 1.5182696012318641e-05, 'epoch': 0.35} + 35%|███▍ | 4145/11952 [3:08:15<15:38:18, 7.21s/it] 35%|███▍ | 4146/11952 [3:08:21<14:36:41, 6.74s/it] {'loss': 0.498, 'learning_rate': 1.518037826458439e-05, 'epoch': 0.35} + 35%|███▍ | 4146/11952 [3:08:21<14:36:41, 6.74s/it] 35%|███▍ | 4147/11952 [3:08:30<16:17:35, 7.52s/it] {'loss': 0.5033, 'learning_rate': 1.5178060136424706e-05, 'epoch': 0.35} + 35%|███▍ | 4147/11952 [3:08:30<16:17:35, 7.52s/it] 35%|███▍ | 4148/11952 [3:08:36<15:09:46, 6.99s/it] {'loss': 0.4818, 'learning_rate': 1.5175741628009824e-05, 'epoch': 0.35} + 35%|███▍ | 4148/11952 [3:08:36<15:09:46, 6.99s/it] 35%|███▍ | 4149/11952 [3:08:42<14:20:38, 6.62s/it] {'loss': 0.5017, 'learning_rate': 1.5173422739510003e-05, 'epoch': 0.35} + 35%|███▍ | 4149/11952 [3:08:42<14:20:38, 6.62s/it]3 AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +06 AutoResumeHook: Checking whether to suspend... +74 AutoResumeHook: Checking whether to suspend...AutoResumeHook: Checking whether to suspend... + + AutoResumeHook: Checking whether to suspend... + 35%|███▍ | 4150/11952 [3:08:48<13:50:58, 6.39s/it] {'loss': 0.4716, 'learning_rate': 1.5171103471095533e-05, 'epoch': 0.35} + 35%|███▍ | 4150/11952 [3:08:48<13:50:58, 6.39s/it] 35%|███▍ | 4151/11952 [3:08:53<13:23:42, 6.18s/it] {'loss': 0.4648, 'learning_rate': 1.5168783822936735e-05, 'epoch': 0.35} + 35%|███▍ | 4151/11952 [3:08:53<13:23:42, 6.18s/it] 35%|███▍ | 4152/11952 [3:08:59<13:00:19, 6.00s/it] {'loss': 0.4952, 'learning_rate': 1.516646379520395e-05, 'epoch': 0.35} + 35%|███▍ | 4152/11952 [3:08:59<13:00:19, 6.00s/it] 35%|███▍ | 4153/11952 [3:09:05<12:51:29, 5.94s/it] {'loss': 0.4907, 'learning_rate': 1.5164143388067554e-05, 'epoch': 0.35} + 35%|███▍ | 4153/11952 [3:09:05<12:51:29, 5.94s/it] 35%|███▍ | 4154/11952 [3:09:11<12:53:47, 5.95s/it] {'loss': 0.4882, 'learning_rate': 1.5161822601697945e-05, 'epoch': 0.35} + 35%|███▍ | 4154/11952 [3:09:11<12:53:47, 5.95s/it] 35%|███▍ | 4155/11952 [3:09:17<12:47:57, 5.91s/it] {'loss': 0.4774, 'learning_rate': 1.5159501436265553e-05, 'epoch': 0.35} + 35%|███▍ | 4155/11952 [3:09:17<12:47:57, 5.91s/it] 35%|███▍ | 4156/11952 [3:09:22<12:45:09, 5.89s/it] {'loss': 0.4901, 'learning_rate': 1.5157179891940837e-05, 'epoch': 0.35} + 35%|███▍ | 4156/11952 [3:09:22<12:45:09, 5.89s/it] 35%|███▍ | 4157/11952 [3:09:28<12:33:27, 5.80s/it] {'loss': 0.4773, 'learning_rate': 1.5154857968894278e-05, 'epoch': 0.35} + 35%|███▍ | 4157/11952 [3:09:28<12:33:27, 5.80s/it] 35%|███▍ | 4158/11952 [3:09:34<12:37:20, 5.83s/it] {'loss': 0.4894, 'learning_rate': 1.5152535667296395e-05, 'epoch': 0.35} + 35%|███▍ | 4158/11952 [3:09:34<12:37:20, 5.83s/it] 35%|███▍ | 4159/11952 [3:09:40<12:34:07, 5.81s/it] {'loss': 0.4976, 'learning_rate': 1.5150212987317721e-05, 'epoch': 0.35} + 35%|███▍ | 4159/11952 [3:09:40<12:34:07, 5.81s/it] 35%|███▍ | 4160/11952 [3:09:45<12:29:30, 5.77s/it] {'loss': 0.4964, 'learning_rate': 1.5147889929128825e-05, 'epoch': 0.35} + 35%|███▍ | 4160/11952 [3:09:45<12:29:30, 5.77s/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%|███▍ | 4161/11952 [3:09:51<12:35:05, 5.82s/it] {'loss': 0.4747, 'learning_rate': 1.5145566492900305e-05, 'epoch': 0.35} + 35%|███▍ | 4161/11952 [3:09:51<12:35:05, 5.82s/it] 35%|███▍ | 4162/11952 [3:09:57<12:33:35, 5.80s/it] {'loss': 0.4627, 'learning_rate': 1.5143242678802787e-05, 'epoch': 0.35} + 35%|███▍ | 4162/11952 [3:09:57<12:33:35, 5.80s/it] 35%|███▍ | 4163/11952 [3:10:03<12:31:59, 5.79s/it] {'loss': 0.483, 'learning_rate': 1.5140918487006918e-05, 'epoch': 0.35} + 35%|███▍ | 4163/11952 [3:10:03<12:31:59, 5.79s/it] 35%|███▍ | 4164/11952 [3:10:08<12:24:36, 5.74s/it] {'loss': 0.4939, 'learning_rate': 1.5138593917683374e-05, 'epoch': 0.35} + 35%|███▍ | 4164/11952 [3:10:08<12:24:36, 5.74s/it] 35%|███▍ | 4165/11952 [3:10:15<12:39:17, 5.85s/it] {'loss': 0.4938, 'learning_rate': 1.513626897100287e-05, 'epoch': 0.35} + 35%|███▍ | 4165/11952 [3:10:15<12:39:17, 5.85s/it] 35%|███▍ | 4166/11952 [3:10:21<12:42:36, 5.88s/it] {'loss': 0.4925, 'learning_rate': 1.5133943647136131e-05, 'epoch': 0.35} + 35%|███▍ | 4166/11952 [3:10:21<12:42:36, 5.88s/it] 35%|███▍ | 4167/11952 [3:10:26<12:29:44, 5.78s/it] {'loss': 0.4871, 'learning_rate': 1.5131617946253928e-05, 'epoch': 0.35} + 35%|███▍ | 4167/11952 [3:10:26<12:29:44, 5.78s/it] 35%|███▍ | 4168/11952 [3:10:32<12:36:35, 5.83s/it] {'loss': 0.4939, 'learning_rate': 1.5129291868527052e-05, 'epoch': 0.35} + 35%|███▍ | 4168/11952 [3:10:32<12:36:35, 5.83s/it] 35%|███▍ | 4169/11952 [3:10:38<12:31:10, 5.79s/it] {'loss': 0.4752, 'learning_rate': 1.5126965414126309e-05, 'epoch': 0.35} + 35%|███▍ | 4169/11952 [3:10:38<12:31:10, 5.79s/it] 35%|███▍ | 4170/11952 [3:10:44<12:39:07, 5.85s/it] {'loss': 0.4781, 'learning_rate': 1.512463858322255e-05, 'epoch': 0.35} + 35%|███▍ | 4170/11952 [3:10:44<12:39:07, 5.85s/it] 35%|███▍ | 4171/11952 [3:10:50<12:53:23, 5.96s/it] {'loss': 0.4782, 'learning_rate': 1.5122311375986649e-05, 'epoch': 0.35} + 35%|███▍ | 4171/11952 [3:10:50<12:53:23, 5.96s/it] 35%|███▍ | 4172/11952 [3:10:56<12:51:32, 5.95s/it] {'loss': 0.4739, 'learning_rate': 1.511998379258951e-05, 'epoch': 0.35} + 35%|███▍ | 4172/11952 [3:10:56<12:51:32, 5.95s/it] 35%|███▍ | 4173/11952 [3:11:02<12:43:07, 5.89s/it] {'loss': 0.5065, 'learning_rate': 1.5117655833202052e-05, 'epoch': 0.35} + 35%|███▍ | 4173/11952 [3:11:02<12:43:07, 5.89s/it] 35%|███▍ | 4174/11952 [3:11:08<12:48:45, 5.93s/it] {'loss': 0.5288, 'learning_rate': 1.5115327497995238e-05, 'epoch': 0.35} + 35%|███▍ | 4174/11952 [3:11:08<12:48:45, 5.93s/it] 35%|███▍ | 4175/11952 [3:11:14<12:58:44, 6.01s/it] {'loss': 0.4939, 'learning_rate': 1.511299878714005e-05, 'epoch': 0.35} + 35%|███▍ | 4175/11952 [3:11:14<12:58:44, 6.01s/it] 35%|███▍ | 4176/11952 [3:11:20<12:48:00, 5.93s/it] {'loss': 0.5027, 'learning_rate': 1.5110669700807496e-05, 'epoch': 0.35} + 35%|███▍ | 4176/11952 [3:11:20<12:48:00, 5.93s/it] 35%|███▍ | 4177/11952 [3:11:26<12:49:57, 5.94s/it] {'loss': 0.5097, 'learning_rate': 1.5108340239168614e-05, 'epoch': 0.35} + 35%|███▍ | 4177/11952 [3:11:26<12:49:57, 5.94s/it] 35%|███▍ | 4178/11952 [3:11:32<12:56:17, 5.99s/it] {'loss': 0.4741, 'learning_rate': 1.5106010402394477e-05, 'epoch': 0.35} + 35%|███▍ | 4178/11952 [3:11:32<12:56:17, 5.99s/it] 35%|███▍ | 4179/11952 [3:11:37<12:42:00, 5.88s/it] {'loss': 0.4856, 'learning_rate': 1.5103680190656169e-05, 'epoch': 0.35} + 35%|███▍ | 4179/11952 [3:11:37<12:42:00, 5.88s/it] 35%|███▍ | 4180/11952 [3:11:43<12:34:47, 5.83s/it] {'loss': 0.5238, 'learning_rate': 1.5101349604124816e-05, 'epoch': 0.35} + 35%|███▍ | 4180/11952 [3:11:43<12:34:47, 5.83s/it] 35%|███▍ | 4181/11952 [3:11:49<12:23:01, 5.74s/it] {'loss': 0.4797, 'learning_rate': 1.5099018642971568e-05, 'epoch': 0.35} + 35%|███▍ | 4181/11952 [3:11:49<12:23:01, 5.74s/it] 35%|███▍ | 4182/11952 [3:11:54<12:31:41, 5.80s/it] {'loss': 0.5027, 'learning_rate': 1.5096687307367601e-05, 'epoch': 0.35} + 35%|███▍ | 4182/11952 [3:11:54<12:31:41, 5.80s/it] 35%|███▍ | 4183/11952 [3:12:00<12:31:17, 5.80s/it] {'loss': 0.481, 'learning_rate': 1.5094355597484111e-05, 'epoch': 0.35} + 35%|███▍ | 4183/11952 [3:12:00<12:31:17, 5.80s/it] 35%|███▌ | 4184/11952 [3:12:06<12:30:10, 5.79s/it] {'loss': 0.5015, 'learning_rate': 1.509202351349234e-05, 'epoch': 0.35} + 35%|███▌ | 4184/11952 [3:12:06<12:30:10, 5.79s/it] 35%|███▌ | 4185/11952 [3:12:12<12:25:30, 5.76s/it] {'loss': 0.4847, 'learning_rate': 1.508969105556354e-05, 'epoch': 0.35} + 35%|███▌ | 4185/11952 [3:12:12<12:25:30, 5.76s/it] 35%|███▌ | 4186/11952 [3:12:18<12:32:13, 5.81s/it] {'loss': 0.4803, 'learning_rate': 1.5087358223869e-05, 'epoch': 0.35} + 35%|███▌ | 4186/11952 [3:12:18<12:32:13, 5.81s/it] 35%|███▌ | 4187/11952 [3:12:24<12:33:54, 5.83s/it] {'loss': 0.4904, 'learning_rate': 1.5085025018580029e-05, 'epoch': 0.35} + 35%|███▌ | 4187/11952 [3:12:24<12:33:54, 5.83s/it] 35%|███▌ | 4188/11952 [3:12:29<12:37:28, 5.85s/it] {'loss': 0.4654, 'learning_rate': 1.5082691439867973e-05, 'epoch': 0.35} + 35%|███▌ | 4188/11952 [3:12:29<12:37:28, 5.85s/it] 35%|███▌ | 4189/11952 [3:12:35<12:42:16, 5.89s/it] {'loss': 0.4828, 'learning_rate': 1.5080357487904198e-05, 'epoch': 0.35} + 35%|███▌ | 4189/11952 [3:12:35<12:42:16, 5.89s/it] 35%|███▌ | 4190/11952 [3:12:42<13:01:16, 6.04s/it] {'loss': 0.5049, 'learning_rate': 1.5078023162860099e-05, 'epoch': 0.35} + 35%|███▌ | 4190/11952 [3:12:42<13:01:16, 6.04s/it] 35%|███▌ | 4191/11952 [3:12:48<12:49:31, 5.95s/it] {'loss': 0.4923, 'learning_rate': 1.5075688464907099e-05, 'epoch': 0.35} + 35%|███▌ | 4191/11952 [3:12:48<12:49:31, 5.95s/it] 35%|███▌ | 4192/11952 [3:12:53<12:47:32, 5.93s/it] {'loss': 0.4693, 'learning_rate': 1.5073353394216652e-05, 'epoch': 0.35} + 35%|███▌ | 4192/11952 [3:12:53<12:47:32, 5.93s/it] 35%|███▌ | 4193/11952 [3:12:59<12:44:15, 5.91s/it] {'loss': 0.4917, 'learning_rate': 1.5071017950960234e-05, 'epoch': 0.35} + 35%|███▌ | 4193/11952 [3:12:59<12:44:15, 5.91s/it] 35%|███▌ | 4194/11952 [3:13:05<12:47:48, 5.94s/it] {'loss': 0.495, 'learning_rate': 1.5068682135309347e-05, 'epoch': 0.35} + 35%|███▌ | 4194/11952 [3:13:05<12:47:48, 5.94s/it] 35%|███▌ | 4195/11952 [3:13:11<12:42:06, 5.89s/it] {'loss': 0.4869, 'learning_rate': 1.5066345947435525e-05, 'epoch': 0.35} + 35%|███▌ | 4195/11952 [3:13:11<12:42:06, 5.89s/it] 35%|███▌ | 4196/11952 [3:13:17<12:39:02, 5.87s/it] {'loss': 0.4836, 'learning_rate': 1.5064009387510333e-05, 'epoch': 0.35} + 35%|███▌ | 4196/11952 [3:13:17<12:39:02, 5.87s/it] 35%|███▌ | 4197/11952 [3:13:23<12:52:17, 5.98s/it] {'loss': 0.4999, 'learning_rate': 1.5061672455705352e-05, 'epoch': 0.35} + 35%|███▌ | 4197/11952 [3:13:23<12:52:17, 5.98s/it] 35%|███▌ | 4198/11952 [3:13:29<12:53:53, 5.99s/it] {'loss': 0.5058, 'learning_rate': 1.50593351521922e-05, 'epoch': 0.35} + 35%|███▌ | 4198/11952 [3:13:29<12:53:53, 5.99s/it] 35%|███▌ | 4199/11952 [3:13:35<12:55:17, 6.00s/it] {'loss': 0.4897, 'learning_rate': 1.505699747714252e-05, 'epoch': 0.35} + 35%|███▌ | 4199/11952 [3:13:35<12:55:17, 6.00s/it]2 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend...4 + AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... +0 AutoResumeHook: Checking whether to suspend... + 35%|███▌ | 4200/11952 [3:13:41<13:04:45, 6.07s/it] {'loss': 0.4752, 'learning_rate': 1.5054659430727974e-05, 'epoch': 0.35} + 35%|███▌ | 4200/11952 [3:13:41<13:04:45, 6.07s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-4200/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-4200/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/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( + 35%|███▌ | 4201/11952 [3:14:13<29:50:44, 13.86s/it] {'loss': 0.4942, 'learning_rate': 1.5052321013120263e-05, 'epoch': 0.35} + 35%|███▌ | 4201/11952 [3:14:13<29:50:44, 13.86s/it] 35%|███▌ | 4202/11952 [3:14:19<24:27:29, 11.36s/it] {'loss': 0.4665, 'learning_rate': 1.5049982224491115e-05, 'epoch': 0.35} + 35%|███▌ | 4202/11952 [3:14:19<24:27:29, 11.36s/it] 35%|███▌ | 4203/11952 [3:14:25<21:01:39, 9.77s/it] {'loss': 0.497, 'learning_rate': 1.5047643065012276e-05, 'epoch': 0.35} + 35%|███▌ | 4203/11952 [3:14:25<21:01:39, 9.77s/it] 35%|███▌ | 4204/11952 [3:14:31<18:28:07, 8.58s/it] {'loss': 0.5008, 'learning_rate': 1.5045303534855524e-05, 'epoch': 0.35} + 35%|███▌ | 4204/11952 [3:14:31<18:28:07, 8.58s/it] 35%|███▌ | 4205/11952 [3:14:37<16:48:47, 7.81s/it] {'loss': 0.4908, 'learning_rate': 1.5042963634192667e-05, 'epoch': 0.35} + 35%|███▌ | 4205/11952 [3:14:37<16:48:47, 7.81s/it] 35%|███▌ | 4206/11952 [3:14:43<15:33:32, 7.23s/it] {'loss': 0.498, 'learning_rate': 1.5040623363195535e-05, 'epoch': 0.35} + 35%|███▌ | 4206/11952 [3:14:43<15:33:32, 7.23s/it] 35%|███▌ | 4207/11952 [3:14:49<14:38:29, 6.81s/it] {'loss': 0.4864, 'learning_rate': 1.5038282722035986e-05, 'epoch': 0.35} + 35%|███▌ | 4207/11952 [3:14:49<14:38:29, 6.81s/it] 35%|███▌ | 4208/11952 [3:14:54<13:52:49, 6.45s/it] {'loss': 0.5004, 'learning_rate': 1.5035941710885915e-05, 'epoch': 0.35} + 35%|███▌ | 4208/11952 [3:14:54<13:52:49, 6.45s/it] 35%|███▌ | 4209/11952 [3:15:00<13:30:57, 6.28s/it] {'loss': 0.5207, 'learning_rate': 1.5033600329917227e-05, 'epoch': 0.35} + 35%|███▌ | 4209/11952 [3:15:00<13:30:57, 6.28s/it] 35%|███▌ | 4210/11952 [3:15:06<13:11:59, 6.14s/it] {'loss': 0.4731, 'learning_rate': 1.5031258579301868e-05, 'epoch': 0.35} + 35%|███▌ | 4210/11952 [3:15:06<13:11:59, 6.14s/it] 35%|███▌ | 4211/11952 [3:15:11<12:51:41, 5.98s/it] {'loss': 0.4995, 'learning_rate': 1.5028916459211804e-05, 'epoch': 0.35} + 35%|███▌ | 4211/11952 [3:15:11<12:51:41, 5.98s/it] 35%|███▌ | 4212/11952 [3:15:17<12:48:09, 5.95s/it] {'loss': 0.4928, 'learning_rate': 1.5026573969819035e-05, 'epoch': 0.35} + 35%|███▌ | 4212/11952 [3:15:17<12:48:09, 5.95s/it] 35%|███▌ | 4213/11952 [3:15:23<12:53:37, 6.00s/it] {'loss': 0.4968, 'learning_rate': 1.502423111129558e-05, 'epoch': 0.35} + 35%|███▌ | 4213/11952 [3:15:23<12:53:37, 6.00s/it] 35%|███▌ | 4214/11952 [3:15:29<12:42:15, 5.91s/it] {'loss': 0.4896, 'learning_rate': 1.5021887883813488e-05, 'epoch': 0.35} + 35%|███▌ | 4214/11952 [3:15:29<12:42:15, 5.91s/it] 35%|███▌ | 4215/11952 [3:15:35<12:43:33, 5.92s/it] {'loss': 0.4845, 'learning_rate': 1.501954428754484e-05, 'epoch': 0.35} + 35%|███▌ | 4215/11952 [3:15:35<12:43:33, 5.92s/it] 35%|███▌ | 4216/11952 [3:15:41<12:53:05, 6.00s/it] {'loss': 0.4936, 'learning_rate': 1.5017200322661735e-05, 'epoch': 0.35} + 35%|███▌ | 4216/11952 [3:15:41<12:53:05, 6.00s/it] 35%|███▌ | 4217/11952 [3:15:47<12:41:45, 5.91s/it] {'loss': 0.4902, 'learning_rate': 1.5014855989336308e-05, 'epoch': 0.35} + 35%|███▌ | 4217/11952 [3:15:47<12:41:45, 5.91s/it] 35%|███▌ | 4218/11952 [3:15:53<12:27:05, 5.80s/it] {'loss': 0.4821, 'learning_rate': 1.5012511287740715e-05, 'epoch': 0.35} + 35%|███▌ | 4218/11952 [3:15:53<12:27:05, 5.80s/it] 35%|███▌ | 4219/11952 [3:15:58<12:32:10, 5.84s/it] {'loss': 0.4979, 'learning_rate': 1.5010166218047139e-05, 'epoch': 0.35} + 35%|███▌ | 4219/11952 [3:15:58<12:32:10, 5.84s/it] 35%|███▌ | 4220/11952 [3:16:04<12:24:37, 5.78s/it] {'loss': 0.4948, 'learning_rate': 1.50078207804278e-05, 'epoch': 0.35} + 35%|███▌ | 4220/11952 [3:16:04<12:24:37, 5.78s/it] 35%|███▌ | 4221/11952 [3:16:10<12:20:41, 5.75s/it] {'loss': 0.4824, 'learning_rate': 1.5005474975054928e-05, 'epoch': 0.35} + 35%|███▌ | 4221/11952 [3:16:10<12:20:41, 5.75s/it] 35%|███▌ | 4222/11952 [3:16:16<12:21:35, 5.76s/it] {'loss': 0.4921, 'learning_rate': 1.5003128802100792e-05, 'epoch': 0.35} + 35%|███▌ | 4222/11952 [3:16:16<12:21:35, 5.76s/it] 35%|███▌ | 4223/11952 [3:16:21<12:25:12, 5.79s/it] {'loss': 0.4964, 'learning_rate': 1.500078226173769e-05, 'epoch': 0.35} + 35%|███▌ | 4223/11952 [3:16:21<12:25:12, 5.79s/it] 35%|███▌ | 4224/11952 [3:16:27<12:17:44, 5.73s/it] {'loss': 0.4867, 'learning_rate': 1.4998435354137937e-05, 'epoch': 0.35} + 35%|███▌ | 4224/11952 [3:16:27<12:17:44, 5.73s/it] 35%|███▌ | 4225/11952 [3:16:33<12:23:38, 5.77s/it] {'loss': 0.4999, 'learning_rate': 1.4996088079473884e-05, 'epoch': 0.35} + 35%|███▌ | 4225/11952 [3:16:33<12:23:38, 5.77s/it] 35%|███▌ | 4226/11952 [3:16:39<12:21:32, 5.76s/it] {'loss': 0.5114, 'learning_rate': 1.4993740437917898e-05, 'epoch': 0.35} + 35%|███▌ | 4226/11952 [3:16:39<12:21:32, 5.76s/it] 35%|███▌ | 4227/11952 [3:16:44<12:19:56, 5.75s/it] {'loss': 0.4886, 'learning_rate': 1.4991392429642389e-05, 'epoch': 0.35} + 35%|███▌ | 4227/11952 [3:16:44<12:19:56, 5.75s/it] 35%|███▌ | 4228/11952 [3:16:51<12:39:58, 5.90s/it] {'loss': 0.4818, 'learning_rate': 1.498904405481978e-05, 'epoch': 0.35} + 35%|███▌ | 4228/11952 [3:16:51<12:39:58, 5.90s/it] 35%|███▌ | 4229/11952 [3:16:57<12:44:41, 5.94s/it] {'loss': 0.5041, 'learning_rate': 1.4986695313622525e-05, 'epoch': 0.35} + 35%|███▌ | 4229/11952 [3:16:57<12:44:41, 5.94s/it] 35%|███▌ | 4230/11952 [3:17:02<12:38:09, 5.89s/it] {'loss': 0.4954, 'learning_rate': 1.4984346206223108e-05, 'epoch': 0.35} + 35%|███▌ | 4230/11952 [3:17:02<12:38:09, 5.89s/it] 35%|███▌ | 4231/11952 [3:17:09<12:58:24, 6.05s/it] {'loss': 0.494, 'learning_rate': 1.4981996732794038e-05, 'epoch': 0.35} + 35%|███▌ | 4231/11952 [3:17:09<12:58:24, 6.05s/it] 35%|███▌ | 4232/11952 [3:17:15<13:05:52, 6.11s/it] {'loss': 0.4941, 'learning_rate': 1.4979646893507847e-05, 'epoch': 0.35} + 35%|███▌ | 4232/11952 [3:17:15<13:05:52, 6.11s/it] 35%|███▌ | 4233/11952 [3:17:21<12:56:15, 6.03s/it] {'loss': 0.4994, 'learning_rate': 1.4977296688537101e-05, 'epoch': 0.35} + 35%|███▌ | 4233/11952 [3:17:21<12:56:15, 6.03s/it] 35%|███▌ | 4234/11952 [3:17:27<12:45:02, 5.95s/it] {'loss': 0.4972, 'learning_rate': 1.4974946118054392e-05, 'epoch': 0.35} + 35%|███▌ | 4234/11952 [3:17:27<12:45:02, 5.95s/it] 35%|███▌ | 4235/11952 [3:17:33<12:42:39, 5.93s/it] {'loss': 0.4681, 'learning_rate': 1.4972595182232328e-05, 'epoch': 0.35} + 35%|███▌ | 4235/11952 [3:17:33<12:42:39, 5.93s/it] 35%|███▌ | 4236/11952 [3:17:38<12:35:51, 5.88s/it] {'loss': 0.4936, 'learning_rate': 1.4970243881243558e-05, 'epoch': 0.35} + 35%|███▌ | 4236/11952 [3:17:38<12:35:51, 5.88s/it] 35%|███▌ | 4237/11952 [3:17:44<12:29:14, 5.83s/it] {'loss': 0.4879, 'learning_rate': 1.4967892215260751e-05, 'epoch': 0.35} + 35%|███▌ | 4237/11952 [3:17:44<12:29:14, 5.83s/it] 35%|███▌ | 4238/11952 [3:17:50<12:40:13, 5.91s/it] {'loss': 0.4786, 'learning_rate': 1.49655401844566e-05, 'epoch': 0.35} + 35%|███▌ | 4238/11952 [3:17:50<12:40:13, 5.91s/it] 35%|███▌ | 4239/11952 [3:17:56<12:30:36, 5.84s/it] {'loss': 0.4921, 'learning_rate': 1.4963187789003835e-05, 'epoch': 0.35} + 35%|███▌ | 4239/11952 [3:17:56<12:30:36, 5.84s/it] 35%|███▌ | 4240/11952 [3:18:02<12:37:10, 5.89s/it] {'loss': 0.4926, 'learning_rate': 1.49608350290752e-05, 'epoch': 0.35} + 35%|███▌ | 4240/11952 [3:18:02<12:37:10, 5.89s/it] 35%|███▌ | 4241/11952 [3:18:08<12:33:56, 5.87s/it] {'loss': 0.4689, 'learning_rate': 1.4958481904843473e-05, 'epoch': 0.35} + 35%|███▌ | 4241/11952 [3:18:08<12:33:56, 5.87s/it] 35%|███▌ | 4242/11952 [3:18:13<12:31:30, 5.85s/it] {'loss': 0.478, 'learning_rate': 1.4956128416481459e-05, 'epoch': 0.35} + 35%|███▌ | 4242/11952 [3:18:13<12:31:30, 5.85s/it] 36%|███▌ | 4243/11952 [3:18:19<12:24:37, 5.80s/it] {'loss': 0.4967, 'learning_rate': 1.4953774564161991e-05, 'epoch': 0.35} + 36%|███▌ | 4243/11952 [3:18:19<12:24:37, 5.80s/it] 36%|███▌ | 4244/11952 [3:18:25<12:31:01, 5.85s/it] {'loss': 0.4759, 'learning_rate': 1.495142034805792e-05, 'epoch': 0.36} + 36%|███▌ | 4244/11952 [3:18:25<12:31:01, 5.85s/it] 36%|███▌ | 4245/11952 [3:18:31<12:18:40, 5.75s/it] {'loss': 0.4725, 'learning_rate': 1.4949065768342136e-05, 'epoch': 0.36} + 36%|███▌ | 4245/11952 [3:18:31<12:18:40, 5.75s/it] 36%|███▌ | 4246/11952 [3:18:36<12:17:38, 5.74s/it] {'loss': 0.4913, 'learning_rate': 1.4946710825187545e-05, 'epoch': 0.36} + 36%|███▌ | 4246/11952 [3:18:36<12:17:38, 5.74s/it] 36%|███▌ | 4247/11952 [3:18:42<12:25:28, 5.81s/it] {'loss': 0.4778, 'learning_rate': 1.4944355518767086e-05, 'epoch': 0.36} + 36%|███▌ | 4247/11952 [3:18:42<12:25:28, 5.81s/it] 36%|███▌ | 4248/11952 [3:18:48<12:28:05, 5.83s/it] {'loss': 0.4754, 'learning_rate': 1.4941999849253723e-05, 'epoch': 0.36} + 36%|███▌ | 4248/11952 [3:18:48<12:28:05, 5.83s/it] 36%|███▌ | 4249/11952 [3:18:54<12:23:51, 5.79s/it] {'loss': 0.4989, 'learning_rate': 1.4939643816820449e-05, 'epoch': 0.36} + 36%|███▌ | 4249/11952 [3:18:54<12:23:51, 5.79s/it]3 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +0 AutoResumeHook: Checking whether to suspend... + 36%|███▌ | 4250/11952 [3:19:00<12:38:24, 5.91s/it] {'loss': 0.4903, 'learning_rate': 1.4937287421640277e-05, 'epoch': 0.36} + 36%|███▌ | 4250/11952 [3:19:00<12:38:24, 5.91s/it] 36%|███▌ | 4251/11952 [3:19:06<12:30:37, 5.85s/it] {'loss': 0.4936, 'learning_rate': 1.493493066388625e-05, 'epoch': 0.36} + 36%|███▌ | 4251/11952 [3:19:06<12:30:37, 5.85s/it] 36%|███▌ | 4252/11952 [3:19:12<12:38:53, 5.91s/it] {'loss': 0.4945, 'learning_rate': 1.4932573543731441e-05, 'epoch': 0.36} + 36%|███▌ | 4252/11952 [3:19:12<12:38:53, 5.91s/it] 36%|███▌ | 4253/11952 [3:19:18<12:35:51, 5.89s/it] {'loss': 0.5001, 'learning_rate': 1.493021606134895e-05, 'epoch': 0.36} + 36%|███▌ | 4253/11952 [3:19:18<12:35:51, 5.89s/it] 36%|███▌ | 4254/11952 [3:19:24<12:41:13, 5.93s/it] {'loss': 0.4595, 'learning_rate': 1.4927858216911897e-05, 'epoch': 0.36} + 36%|███▌ | 4254/11952 [3:19:24<12:41:13, 5.93s/it] 36%|███▌ | 4255/11952 [3:19:30<12:39:31, 5.92s/it] {'loss': 0.4922, 'learning_rate': 1.492550001059343e-05, 'epoch': 0.36} + 36%|███▌ | 4255/11952 [3:19:30<12:39:31, 5.92s/it] 36%|███▌ | 4256/11952 [3:19:36<12:47:05, 5.98s/it] {'loss': 0.4985, 'learning_rate': 1.4923141442566732e-05, 'epoch': 0.36} + 36%|███▌ | 4256/11952 [3:19:36<12:47:05, 5.98s/it] 36%|███▌ | 4257/11952 [3:19:42<12:41:38, 5.94s/it] {'loss': 0.5076, 'learning_rate': 1.4920782513005003e-05, 'epoch': 0.36} + 36%|███▌ | 4257/11952 [3:19:42<12:41:38, 5.94s/it] 36%|███▌ | 4258/11952 [3:19:48<12:49:47, 6.00s/it] {'loss': 0.5075, 'learning_rate': 1.4918423222081473e-05, 'epoch': 0.36} + 36%|███▌ | 4258/11952 [3:19:48<12:49:47, 6.00s/it] 36%|███▌ | 4259/11952 [3:19:53<12:38:19, 5.91s/it] {'loss': 0.5165, 'learning_rate': 1.4916063569969398e-05, 'epoch': 0.36} + 36%|███▌ | 4259/11952 [3:19:53<12:38:19, 5.91s/it] 36%|███▌ | 4260/11952 [3:19:59<12:26:00, 5.82s/it] {'loss': 0.4758, 'learning_rate': 1.4913703556842066e-05, 'epoch': 0.36} + 36%|███▌ | 4260/11952 [3:19:59<12:26:00, 5.82s/it] 36%|███▌ | 4261/11952 [3:20:05<12:31:18, 5.86s/it] {'loss': 0.4828, 'learning_rate': 1.491134318287278e-05, 'epoch': 0.36} + 36%|███▌ | 4261/11952 [3:20:05<12:31:18, 5.86s/it] 36%|███▌ | 4262/11952 [3:20:11<12:27:03, 5.83s/it] {'loss': 0.4891, 'learning_rate': 1.4908982448234875e-05, 'epoch': 0.36} + 36%|███▌ | 4262/11952 [3:20:11<12:27:03, 5.83s/it] 36%|███▌ | 4263/11952 [3:20:16<12:25:46, 5.82s/it] {'loss': 0.4657, 'learning_rate': 1.490662135310172e-05, 'epoch': 0.36} + 36%|███▌ | 4263/11952 [3:20:16<12:25:46, 5.82s/it] 36%|███▌ | 4264/11952 [3:20:23<12:33:18, 5.88s/it] {'loss': 0.5058, 'learning_rate': 1.49042598976467e-05, 'epoch': 0.36} + 36%|███▌ | 4264/11952 [3:20:23<12:33:18, 5.88s/it] 36%|███▌ | 4265/11952 [3:20:28<12:30:12, 5.86s/it] {'loss': 0.4888, 'learning_rate': 1.4901898082043232e-05, 'epoch': 0.36} + 36%|███▌ | 4265/11952 [3:20:28<12:30:12, 5.86s/it] 36%|███▌ | 4266/11952 [3:20:34<12:34:11, 5.89s/it] {'loss': 0.4943, 'learning_rate': 1.4899535906464757e-05, 'epoch': 0.36} + 36%|███▌ | 4266/11952 [3:20:34<12:34:11, 5.89s/it] 36%|███▌ | 4267/11952 [3:20:40<12:28:06, 5.84s/it] {'loss': 0.4916, 'learning_rate': 1.4897173371084743e-05, 'epoch': 0.36} + 36%|███▌ | 4267/11952 [3:20:40<12:28:06, 5.84s/it] 36%|███▌ | 4268/11952 [3:20:46<12:28:07, 5.84s/it] {'loss': 0.4967, 'learning_rate': 1.4894810476076688e-05, 'epoch': 0.36} + 36%|███▌ | 4268/11952 [3:20:46<12:28:07, 5.84s/it] 36%|███▌ | 4269/11952 [3:20:52<12:24:15, 5.81s/it] {'loss': 0.5103, 'learning_rate': 1.489244722161411e-05, 'epoch': 0.36} + 36%|███▌ | 4269/11952 [3:20:52<12:24:15, 5.81s/it] 36%|███▌ | 4270/11952 [3:20:57<12:17:35, 5.76s/it] {'loss': 0.4885, 'learning_rate': 1.4890083607870559e-05, 'epoch': 0.36} + 36%|███▌ | 4270/11952 [3:20:57<12:17:35, 5.76s/it] 36%|███▌ | 4271/11952 [3:21:03<12:31:58, 5.87s/it] {'loss': 0.5045, 'learning_rate': 1.4887719635019605e-05, 'epoch': 0.36} + 36%|███▌ | 4271/11952 [3:21:03<12:31:58, 5.87s/it] 36%|███▌ | 4272/11952 [3:21:09<12:28:28, 5.85s/it] {'loss': 0.4692, 'learning_rate': 1.488535530323485e-05, 'epoch': 0.36} + 36%|███▌ | 4272/11952 [3:21:09<12:28:28, 5.85s/it] 36%|███▌ | 4273/11952 [3:21:15<12:33:17, 5.89s/it] {'loss': 0.5159, 'learning_rate': 1.4882990612689918e-05, 'epoch': 0.36} + 36%|███▌ | 4273/11952 [3:21:15<12:33:17, 5.89s/it] 36%|███▌ | 4274/11952 [3:21:21<12:38:18, 5.93s/it] {'loss': 0.4899, 'learning_rate': 1.488062556355847e-05, 'epoch': 0.36} + 36%|███▌ | 4274/11952 [3:21:21<12:38:18, 5.93s/it] 36%|███▌ | 4275/11952 [3:21:27<12:37:45, 5.92s/it] {'loss': 0.4831, 'learning_rate': 1.4878260156014182e-05, 'epoch': 0.36} + 36%|███▌ | 4275/11952 [3:21:27<12:37:45, 5.92s/it] 36%|███▌ | 4276/11952 [3:21:33<12:30:27, 5.87s/it] {'loss': 0.4664, 'learning_rate': 1.4875894390230757e-05, 'epoch': 0.36} + 36%|███▌ | 4276/11952 [3:21:33<12:30:27, 5.87s/it] 36%|███▌ | 4277/11952 [3:21:38<12:17:18, 5.76s/it] {'loss': 0.4861, 'learning_rate': 1.4873528266381927e-05, 'epoch': 0.36} + 36%|███▌ | 4277/11952 [3:21:38<12:17:18, 5.76s/it] 36%|███▌ | 4278/11952 [3:21:44<12:10:10, 5.71s/it] {'loss': 0.4937, 'learning_rate': 1.487116178464145e-05, 'epoch': 0.36} + 36%|███▌ | 4278/11952 [3:21:44<12:10:10, 5.71s/it] 36%|███▌ | 4279/11952 [3:21:50<12:17:01, 5.76s/it] {'loss': 0.4788, 'learning_rate': 1.4868794945183113e-05, 'epoch': 0.36} + 36%|███▌ | 4279/11952 [3:21:50<12:17:01, 5.76s/it] 36%|███▌ | 4280/11952 [3:21:56<12:26:05, 5.83s/it] {'loss': 0.4746, 'learning_rate': 1.4866427748180729e-05, 'epoch': 0.36} + 36%|███▌ | 4280/11952 [3:21:56<12:26:05, 5.83s/it] 36%|███▌ | 4281/11952 [3:22:02<12:34:32, 5.90s/it] {'loss': 0.5078, 'learning_rate': 1.4864060193808133e-05, 'epoch': 0.36} + 36%|███▌ | 4281/11952 [3:22:02<12:34:32, 5.90s/it] 36%|███▌ | 4282/11952 [3:22:08<12:32:54, 5.89s/it] {'loss': 0.4726, 'learning_rate': 1.4861692282239181e-05, 'epoch': 0.36} + 36%|███▌ | 4282/11952 [3:22:08<12:32:54, 5.89s/it] 36%|███▌ | 4283/11952 [3:22:14<12:42:15, 5.96s/it] {'loss': 0.4855, 'learning_rate': 1.4859324013647773e-05, 'epoch': 0.36} + 36%|███▌ | 4283/11952 [3:22:14<12:42:15, 5.96s/it] 36%|███▌ | 4284/11952 [3:22:20<12:36:34, 5.92s/it] {'loss': 0.4965, 'learning_rate': 1.4856955388207821e-05, 'epoch': 0.36} + 36%|███▌ | 4284/11952 [3:22:20<12:36:34, 5.92s/it] 36%|███▌ | 4285/11952 [3:22:26<12:35:45, 5.91s/it] {'loss': 0.4585, 'learning_rate': 1.485458640609327e-05, 'epoch': 0.36} + 36%|███▌ | 4285/11952 [3:22:26<12:35:45, 5.91s/it] 36%|███▌ | 4286/11952 [3:22:31<12:31:08, 5.88s/it] {'loss': 0.4939, 'learning_rate': 1.4852217067478082e-05, 'epoch': 0.36} + 36%|███▌ | 4286/11952 [3:22:31<12:31:08, 5.88s/it] 36%|███▌ | 4287/11952 [3:22:38<12:42:55, 5.97s/it] {'loss': 0.4907, 'learning_rate': 1.4849847372536252e-05, 'epoch': 0.36} + 36%|███▌ | 4287/11952 [3:22:38<12:42:55, 5.97s/it] 36%|███▌ | 4288/11952 [3:22:43<12:35:00, 5.91s/it] {'loss': 0.4992, 'learning_rate': 1.4847477321441806e-05, 'epoch': 0.36} + 36%|███▌ | 4288/11952 [3:22:43<12:35:00, 5.91s/it] 36%|███▌ | 4289/11952 [3:22:49<12:24:14, 5.83s/it] {'loss': 0.4741, 'learning_rate': 1.4845106914368786e-05, 'epoch': 0.36} + 36%|███▌ | 4289/11952 [3:22:49<12:24:14, 5.83s/it] 36%|███▌ | 4290/11952 [3:22:55<12:21:46, 5.81s/it] {'loss': 0.5102, 'learning_rate': 1.4842736151491268e-05, 'epoch': 0.36} + 36%|███▌ | 4290/11952 [3:22:55<12:21:46, 5.81s/it] 36%|███▌ | 4291/11952 [3:23:01<12:23:09, 5.82s/it] {'loss': 0.4947, 'learning_rate': 1.484036503298335e-05, 'epoch': 0.36} + 36%|███▌ | 4291/11952 [3:23:01<12:23:09, 5.82s/it] 36%|███▌ | 4292/11952 [3:23:06<12:26:54, 5.85s/it] {'loss': 0.5033, 'learning_rate': 1.4837993559019157e-05, 'epoch': 0.36} + 36%|███▌ | 4292/11952 [3:23:06<12:26:54, 5.85s/it] 36%|███▌ | 4293/11952 [3:23:13<12:38:51, 5.94s/it] {'loss': 0.4976, 'learning_rate': 1.4835621729772838e-05, 'epoch': 0.36} + 36%|███▌ | 4293/11952 [3:23:13<12:38:51, 5.94s/it] 36%|███▌ | 4294/11952 [3:23:18<12:32:46, 5.90s/it] {'loss': 0.4881, 'learning_rate': 1.4833249545418572e-05, 'epoch': 0.36} + 36%|███▌ | 4294/11952 [3:23:18<12:32:46, 5.90s/it] 36%|███▌ | 4295/11952 [3:23:24<12:16:55, 5.77s/it] {'loss': 0.4842, 'learning_rate': 1.4830877006130561e-05, 'epoch': 0.36} + 36%|███▌ | 4295/11952 [3:23:24<12:16:55, 5.77s/it] 36%|███▌ | 4296/11952 [3:23:30<12:32:28, 5.90s/it] {'loss': 0.5006, 'learning_rate': 1.4828504112083038e-05, 'epoch': 0.36} + 36%|███▌ | 4296/11952 [3:23:30<12:32:28, 5.90s/it] 36%|███▌ | 4297/11952 [3:23:36<12:26:00, 5.85s/it] {'loss': 0.4883, 'learning_rate': 1.4826130863450257e-05, 'epoch': 0.36} + 36%|███▌ | 4297/11952 [3:23:36<12:26:00, 5.85s/it] 36%|███▌ | 4298/11952 [3:23:42<12:20:31, 5.80s/it] {'loss': 0.4763, 'learning_rate': 1.4823757260406498e-05, 'epoch': 0.36} + 36%|███▌ | 4298/11952 [3:23:42<12:20:31, 5.80s/it] 36%|███▌ | 4299/11952 [3:23:47<12:13:41, 5.75s/it] {'loss': 0.4734, 'learning_rate': 1.4821383303126067e-05, 'epoch': 0.36} + 36%|███▌ | 4299/11952 [3:23:47<12:13:41, 5.75s/it]3 AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... +0 AutoResumeHook: Checking whether to suspend... + 36%|███▌ | 4300/11952 [3:23:53<12:14:50, 5.76s/it] {'loss': 0.5042, 'learning_rate': 1.48190089917833e-05, 'epoch': 0.36} + 36%|███▌ | 4300/11952 [3:23:53<12:14:50, 5.76s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-4300/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-4300/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/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( + 36%|███▌ | 4301/11952 [3:24:25<28:52:37, 13.59s/it] {'loss': 0.4874, 'learning_rate': 1.4816634326552561e-05, 'epoch': 0.36} + 36%|███▌ | 4301/11952 [3:24:25<28:52:37, 13.59s/it] 36%|███▌ | 4302/11952 [3:24:31<24:04:28, 11.33s/it] {'loss': 0.4944, 'learning_rate': 1.481425930760823e-05, 'epoch': 0.36} + 36%|███▌ | 4302/11952 [3:24:31<24:04:28, 11.33s/it] 36%|███▌ | 4303/11952 [3:24:37<20:37:51, 9.71s/it] {'loss': 0.512, 'learning_rate': 1.4811883935124716e-05, 'epoch': 0.36} + 36%|███▌ | 4303/11952 [3:24:37<20:37:51, 9.71s/it] 36%|███▌ | 4304/11952 [3:24:43<18:20:10, 8.63s/it] {'loss': 0.5002, 'learning_rate': 1.480950820927646e-05, 'epoch': 0.36} + 36%|███▌ | 4304/11952 [3:24:43<18:20:10, 8.63s/it] 36%|███▌ | 4305/11952 [3:24:49<16:30:42, 7.77s/it] {'loss': 0.4948, 'learning_rate': 1.480713213023793e-05, 'epoch': 0.36} + 36%|███▌ | 4305/11952 [3:24:49<16:30:42, 7.77s/it] 36%|███▌ | 4306/11952 [3:24:55<15:20:26, 7.22s/it] {'loss': 0.4853, 'learning_rate': 1.4804755698183606e-05, 'epoch': 0.36} + 36%|███▌ | 4306/11952 [3:24:55<15:20:26, 7.22s/it] 36%|███▌ | 4307/11952 [3:25:00<14:21:45, 6.76s/it] {'loss': 0.4656, 'learning_rate': 1.4802378913288009e-05, 'epoch': 0.36} + 36%|███▌ | 4307/11952 [3:25:00<14:21:45, 6.76s/it] 36%|███▌ | 4308/11952 [3:25:06<13:37:14, 6.41s/it] {'loss': 0.4808, 'learning_rate': 1.4800001775725684e-05, 'epoch': 0.36} + 36%|███▌ | 4308/11952 [3:25:06<13:37:14, 6.41s/it] 36%|███▌ | 4309/11952 [3:25:12<13:10:04, 6.20s/it] {'loss': 0.4804, 'learning_rate': 1.4797624285671187e-05, 'epoch': 0.36} + 36%|███▌ | 4309/11952 [3:25:12<13:10:04, 6.20s/it] 36%|███▌ | 4310/11952 [3:25:17<12:51:27, 6.06s/it] {'loss': 0.4866, 'learning_rate': 1.4795246443299119e-05, 'epoch': 0.36} + 36%|███▌ | 4310/11952 [3:25:17<12:51:27, 6.06s/it] 36%|███▌ | 4311/11952 [3:25:23<12:37:29, 5.95s/it] {'loss': 0.5026, 'learning_rate': 1.4792868248784098e-05, 'epoch': 0.36} + 36%|███▌ | 4311/11952 [3:25:23<12:37:29, 5.95s/it] 36%|███▌ | 4312/11952 [3:25:29<12:31:38, 5.90s/it] {'loss': 0.4892, 'learning_rate': 1.4790489702300768e-05, 'epoch': 0.36} + 36%|███▌ | 4312/11952 [3:25:29<12:31:38, 5.90s/it] 36%|███▌ | 4313/11952 [3:25:35<12:33:23, 5.92s/it] {'loss': 0.4854, 'learning_rate': 1.4788110804023798e-05, 'epoch': 0.36} + 36%|███▌ | 4313/11952 [3:25:35<12:33:23, 5.92s/it] 36%|███▌ | 4314/11952 [3:25:41<12:33:48, 5.92s/it] {'loss': 0.4904, 'learning_rate': 1.4785731554127885e-05, 'epoch': 0.36} + 36%|███▌ | 4314/11952 [3:25:41<12:33:48, 5.92s/it] 36%|███▌ | 4315/11952 [3:25:46<12:22:13, 5.83s/it] {'loss': 0.4885, 'learning_rate': 1.4783351952787754e-05, 'epoch': 0.36} + 36%|███▌ | 4315/11952 [3:25:46<12:22:13, 5.83s/it] 36%|███▌ | 4316/11952 [3:25:52<12:29:32, 5.89s/it] {'loss': 0.4908, 'learning_rate': 1.4780972000178151e-05, 'epoch': 0.36} + 36%|███▌ | 4316/11952 [3:25:52<12:29:32, 5.89s/it] 36%|███▌ | 4317/11952 [3:25:58<12:30:12, 5.90s/it] {'loss': 0.4939, 'learning_rate': 1.477859169647385e-05, 'epoch': 0.36} + 36%|███▌ | 4317/11952 [3:25:58<12:30:12, 5.90s/it] 36%|███▌ | 4318/11952 [3:26:04<12:27:40, 5.88s/it] {'loss': 0.4988, 'learning_rate': 1.4776211041849651e-05, 'epoch': 0.36} + 36%|███▌ | 4318/11952 [3:26:04<12:27:40, 5.88s/it] 36%|███▌ | 4319/11952 [3:26:10<12:25:21, 5.86s/it] {'loss': 0.4819, 'learning_rate': 1.4773830036480377e-05, 'epoch': 0.36} + 36%|███▌ | 4319/11952 [3:26:10<12:25:21, 5.86s/it] 36%|███▌ | 4320/11952 [3:26:16<12:44:03, 6.01s/it] {'loss': 0.4991, 'learning_rate': 1.4771448680540881e-05, 'epoch': 0.36} + 36%|███▌ | 4320/11952 [3:26:16<12:44:03, 6.01s/it] 36%|███▌ | 4321/11952 [3:26:22<12:34:10, 5.93s/it] {'loss': 0.4881, 'learning_rate': 1.4769066974206041e-05, 'epoch': 0.36} + 36%|███▌ | 4321/11952 [3:26:22<12:34:10, 5.93s/it] 36%|███▌ | 4322/11952 [3:26:28<12:29:22, 5.89s/it] {'loss': 0.511, 'learning_rate': 1.476668491765076e-05, 'epoch': 0.36} + 36%|███▌ | 4322/11952 [3:26:28<12:29:22, 5.89s/it] 36%|███▌ | 4323/11952 [3:26:34<12:22:06, 5.84s/it] {'loss': 0.4744, 'learning_rate': 1.4764302511049962e-05, 'epoch': 0.36} + 36%|███▌ | 4323/11952 [3:26:34<12:22:06, 5.84s/it] 36%|███▌ | 4324/11952 [3:26:39<12:19:51, 5.82s/it] {'loss': 0.4949, 'learning_rate': 1.4761919754578603e-05, 'epoch': 0.36} + 36%|███▌ | 4324/11952 [3:26:39<12:19:51, 5.82s/it] 36%|███▌ | 4325/11952 [3:26:45<12:13:17, 5.77s/it] {'loss': 0.4802, 'learning_rate': 1.4759536648411668e-05, 'epoch': 0.36} + 36%|███▌ | 4325/11952 [3:26:45<12:13:17, 5.77s/it] 36%|███▌ | 4326/11952 [3:26:51<12:07:30, 5.72s/it] {'loss': 0.4845, 'learning_rate': 1.4757153192724154e-05, 'epoch': 0.36} + 36%|███▌ | 4326/11952 [3:26:51<12:07:30, 5.72s/it] 36%|███▌ | 4327/11952 [3:26:56<12:01:51, 5.68s/it] {'loss': 0.4661, 'learning_rate': 1.4754769387691096e-05, 'epoch': 0.36} + 36%|███▌ | 4327/11952 [3:26:56<12:01:51, 5.68s/it] 36%|███▌ | 4328/11952 [3:27:02<12:03:27, 5.69s/it] {'loss': 0.4855, 'learning_rate': 1.4752385233487554e-05, 'epoch': 0.36} + 36%|███▌ | 4328/11952 [3:27:02<12:03:27, 5.69s/it] 36%|███▌ | 4329/11952 [3:27:08<12:02:24, 5.69s/it] {'loss': 0.465, 'learning_rate': 1.4750000730288605e-05, 'epoch': 0.36} + 36%|███▌ | 4329/11952 [3:27:08<12:02:24, 5.69s/it] 36%|███▌ | 4330/11952 [3:27:13<12:04:30, 5.70s/it] {'loss': 0.4894, 'learning_rate': 1.4747615878269358e-05, 'epoch': 0.36} + 36%|███▌ | 4330/11952 [3:27:13<12:04:30, 5.70s/it] 36%|███▌ | 4331/11952 [3:27:19<12:18:40, 5.82s/it] {'loss': 0.5, 'learning_rate': 1.474523067760495e-05, 'epoch': 0.36} + 36%|███▌ | 4331/11952 [3:27:19<12:18:40, 5.82s/it] 36%|███▌ | 4332/11952 [3:27:26<12:32:21, 5.92s/it] {'loss': 0.5042, 'learning_rate': 1.4742845128470538e-05, 'epoch': 0.36} + 36%|███▌ | 4332/11952 [3:27:26<12:32:21, 5.92s/it] 36%|███▋ | 4333/11952 [3:27:32<12:38:17, 5.97s/it] {'loss': 0.4949, 'learning_rate': 1.4740459231041306e-05, 'epoch': 0.36} + 36%|███▋ | 4333/11952 [3:27:32<12:38:17, 5.97s/it] 36%|███▋ | 4334/11952 [3:27:38<12:34:13, 5.94s/it] {'loss': 0.505, 'learning_rate': 1.4738072985492462e-05, 'epoch': 0.36} + 36%|███▋ | 4334/11952 [3:27:38<12:34:13, 5.94s/it] 36%|███▋ | 4335/11952 [3:27:43<12:31:17, 5.92s/it] {'loss': 0.4786, 'learning_rate': 1.4735686391999249e-05, 'epoch': 0.36} + 36%|███▋ | 4335/11952 [3:27:43<12:31:17, 5.92s/it] 36%|███▋ | 4336/11952 [3:27:49<12:18:11, 5.82s/it] {'loss': 0.482, 'learning_rate': 1.4733299450736925e-05, 'epoch': 0.36} + 36%|███▋ | 4336/11952 [3:27:49<12:18:11, 5.82s/it] 36%|███▋ | 4337/11952 [3:27:55<12:24:35, 5.87s/it] {'loss': 0.4861, 'learning_rate': 1.4730912161880772e-05, 'epoch': 0.36} + 36%|███▋ | 4337/11952 [3:27:55<12:24:35, 5.87s/it] 36%|███▋ | 4338/11952 [3:28:01<12:32:33, 5.93s/it] {'loss': 0.4779, 'learning_rate': 1.4728524525606111e-05, 'epoch': 0.36} + 36%|███▋ | 4338/11952 [3:28:01<12:32:33, 5.93s/it] 36%|███▋ | 4339/11952 [3:28:07<12:33:09, 5.94s/it] {'loss': 0.4865, 'learning_rate': 1.4726136542088277e-05, 'epoch': 0.36} + 36%|███▋ | 4339/11952 [3:28:07<12:33:09, 5.94s/it] 36%|███▋ | 4340/11952 [3:28:13<12:29:49, 5.91s/it] {'loss': 0.4938, 'learning_rate': 1.4723748211502628e-05, 'epoch': 0.36} + 36%|███▋ | 4340/11952 [3:28:13<12:29:49, 5.91s/it] 36%|███▋ | 4341/11952 [3:28:19<12:32:05, 5.93s/it] {'loss': 0.4721, 'learning_rate': 1.4721359534024562e-05, 'epoch': 0.36} + 36%|███▋ | 4341/11952 [3:28:19<12:32:05, 5.93s/it] 36%|███▋ | 4342/11952 [3:28:25<12:44:58, 6.03s/it] {'loss': 0.4929, 'learning_rate': 1.4718970509829489e-05, 'epoch': 0.36} + 36%|███▋ | 4342/11952 [3:28:25<12:44:58, 6.03s/it] 36%|███▋ | 4343/11952 [3:28:31<12:34:20, 5.95s/it] {'loss': 0.5027, 'learning_rate': 1.4716581139092851e-05, 'epoch': 0.36} + 36%|███▋ | 4343/11952 [3:28:31<12:34:20, 5.95s/it] 36%|███▋ | 4344/11952 [3:28:37<12:40:18, 6.00s/it] {'loss': 0.4993, 'learning_rate': 1.471419142199011e-05, 'epoch': 0.36} + 36%|███▋ | 4344/11952 [3:28:37<12:40:18, 6.00s/it] 36%|███▋ | 4345/11952 [3:28:43<12:34:42, 5.95s/it] {'loss': 0.4877, 'learning_rate': 1.4711801358696755e-05, 'epoch': 0.36} + 36%|███▋ | 4345/11952 [3:28:43<12:34:42, 5.95s/it] 36%|███▋ | 4346/11952 [3:28:49<12:26:22, 5.89s/it] {'loss': 0.491, 'learning_rate': 1.4709410949388311e-05, 'epoch': 0.36} + 36%|███▋ | 4346/11952 [3:28:49<12:26:22, 5.89s/it] 36%|███▋ | 4347/11952 [3:28:54<12:21:58, 5.85s/it] {'loss': 0.5074, 'learning_rate': 1.4707020194240313e-05, 'epoch': 0.36} + 36%|███▋ | 4347/11952 [3:28:54<12:21:58, 5.85s/it] 36%|███▋ | 4348/11952 [3:29:00<12:24:33, 5.87s/it] {'loss': 0.5038, 'learning_rate': 1.4704629093428331e-05, 'epoch': 0.36} + 36%|███▋ | 4348/11952 [3:29:00<12:24:33, 5.87s/it] 36%|███▋ | 4349/11952 [3:29:06<12:34:34, 5.95s/it] {'loss': 0.4815, 'learning_rate': 1.4702237647127957e-05, 'epoch': 0.36} + 36%|███▋ | 4349/11952 [3:29:06<12:34:34, 5.95s/it]3 AutoResumeHook: Checking whether to suspend...2 + AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend...5 + AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +07 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... + 36%|███▋ | 4350/11952 [3:29:13<12:46:30, 6.05s/it] {'loss': 0.5135, 'learning_rate': 1.4699845855514807e-05, 'epoch': 0.36} + 36%|███▋ | 4350/11952 [3:29:13<12:46:30, 6.05s/it] 36%|███▋ | 4351/11952 [3:29:19<12:39:54, 6.00s/it] {'loss': 0.4867, 'learning_rate': 1.4697453718764525e-05, 'epoch': 0.36} + 36%|███▋ | 4351/11952 [3:29:19<12:39:54, 6.00s/it] 36%|███▋ | 4352/11952 [3:29:25<12:47:34, 6.06s/it] {'loss': 0.5028, 'learning_rate': 1.4695061237052781e-05, 'epoch': 0.36} + 36%|███▋ | 4352/11952 [3:29:25<12:47:34, 6.06s/it] 36%|███▋ | 4353/11952 [3:29:31<12:38:23, 5.99s/it] {'loss': 0.5103, 'learning_rate': 1.4692668410555269e-05, 'epoch': 0.36} + 36%|███▋ | 4353/11952 [3:29:31<12:38:23, 5.99s/it] 36%|███▋ | 4354/11952 [3:29:36<12:35:43, 5.97s/it] {'loss': 0.486, 'learning_rate': 1.4690275239447704e-05, 'epoch': 0.36} + 36%|███▋ | 4354/11952 [3:29:36<12:35:43, 5.97s/it] 36%|███▋ | 4355/11952 [3:29:42<12:19:40, 5.84s/it] {'loss': 0.4773, 'learning_rate': 1.4687881723905834e-05, 'epoch': 0.36} + 36%|███▋ | 4355/11952 [3:29:42<12:19:40, 5.84s/it] 36%|███▋ | 4356/11952 [3:29:48<12:15:31, 5.81s/it] {'loss': 0.486, 'learning_rate': 1.4685487864105431e-05, 'epoch': 0.36} + 36%|███▋ | 4356/11952 [3:29:48<12:15:31, 5.81s/it] 36%|███▋ | 4357/11952 [3:29:53<12:11:46, 5.78s/it] {'loss': 0.502, 'learning_rate': 1.4683093660222288e-05, 'epoch': 0.36} + 36%|███▋ | 4357/11952 [3:29:53<12:11:46, 5.78s/it] 36%|███▋ | 4358/11952 [3:30:00<12:30:57, 5.93s/it] {'loss': 0.5118, 'learning_rate': 1.4680699112432223e-05, 'epoch': 0.36} + 36%|███▋ | 4358/11952 [3:30:00<12:30:57, 5.93s/it] 36%|███▋ | 4359/11952 [3:30:06<12:34:17, 5.96s/it] {'loss': 0.475, 'learning_rate': 1.4678304220911086e-05, 'epoch': 0.36} + 36%|███▋ | 4359/11952 [3:30:06<12:34:17, 5.96s/it] 36%|███▋ | 4360/11952 [3:30:12<12:30:44, 5.93s/it] {'loss': 0.4904, 'learning_rate': 1.4675908985834744e-05, 'epoch': 0.36} + 36%|███▋ | 4360/11952 [3:30:12<12:30:44, 5.93s/it] 36%|███▋ | 4361/11952 [3:30:17<12:21:59, 5.86s/it] {'loss': 0.494, 'learning_rate': 1.4673513407379095e-05, 'epoch': 0.36} + 36%|███▋ | 4361/11952 [3:30:17<12:21:59, 5.86s/it] 36%|███▋ | 4362/11952 [3:30:23<12:32:55, 5.95s/it] {'loss': 0.4699, 'learning_rate': 1.4671117485720058e-05, 'epoch': 0.36} + 36%|███▋ | 4362/11952 [3:30:23<12:32:55, 5.95s/it] 37%|███▋ | 4363/11952 [3:30:29<12:28:18, 5.92s/it] {'loss': 0.4813, 'learning_rate': 1.4668721221033586e-05, 'epoch': 0.37} + 37%|███▋ | 4363/11952 [3:30:29<12:28:18, 5.92s/it] 37%|███▋ | 4364/11952 [3:30:35<12:20:24, 5.85s/it] {'loss': 0.5052, 'learning_rate': 1.4666324613495641e-05, 'epoch': 0.37} + 37%|███▋ | 4364/11952 [3:30:35<12:20:24, 5.85s/it] 37%|███▋ | 4365/11952 [3:30:41<12:21:30, 5.86s/it] {'loss': 0.5067, 'learning_rate': 1.4663927663282228e-05, 'epoch': 0.37} + 37%|███▋ | 4365/11952 [3:30:41<12:21:30, 5.86s/it] 37%|███▋ | 4366/11952 [3:30:47<12:18:23, 5.84s/it] {'loss': 0.4903, 'learning_rate': 1.4661530370569366e-05, 'epoch': 0.37} + 37%|███▋ | 4366/11952 [3:30:47<12:18:23, 5.84s/it] 37%|███▋ | 4367/11952 [3:30:52<12:10:49, 5.78s/it] {'loss': 0.4757, 'learning_rate': 1.4659132735533104e-05, 'epoch': 0.37} + 37%|███▋ | 4367/11952 [3:30:52<12:10:49, 5.78s/it] 37%|███▋ | 4368/11952 [3:30:58<12:06:07, 5.74s/it] {'loss': 0.4849, 'learning_rate': 1.4656734758349509e-05, 'epoch': 0.37} + 37%|███▋ | 4368/11952 [3:30:58<12:06:07, 5.74s/it] 37%|███▋ | 4369/11952 [3:31:04<12:01:05, 5.71s/it] {'loss': 0.5033, 'learning_rate': 1.4654336439194686e-05, 'epoch': 0.37} + 37%|███▋ | 4369/11952 [3:31:04<12:01:05, 5.71s/it] 37%|███▋ | 4370/11952 [3:31:10<12:16:18, 5.83s/it] {'loss': 0.4794, 'learning_rate': 1.4651937778244748e-05, 'epoch': 0.37} + 37%|███▋ | 4370/11952 [3:31:10<12:16:18, 5.83s/it] 37%|███▋ | 4371/11952 [3:31:16<12:18:13, 5.84s/it] {'loss': 0.4982, 'learning_rate': 1.464953877567585e-05, 'epoch': 0.37} + 37%|███▋ | 4371/11952 [3:31:16<12:18:13, 5.84s/it] 37%|███▋ | 4372/11952 [3:31:21<12:07:54, 5.76s/it] {'loss': 0.4785, 'learning_rate': 1.4647139431664167e-05, 'epoch': 0.37} + 37%|███▋ | 4372/11952 [3:31:21<12:07:54, 5.76s/it] 37%|███▋ | 4373/11952 [3:31:27<12:12:04, 5.80s/it] {'loss': 0.4746, 'learning_rate': 1.4644739746385894e-05, 'epoch': 0.37} + 37%|███▋ | 4373/11952 [3:31:27<12:12:04, 5.80s/it] 37%|███▋ | 4374/11952 [3:31:33<12:09:39, 5.78s/it] {'loss': 0.4791, 'learning_rate': 1.4642339720017249e-05, 'epoch': 0.37} + 37%|███▋ | 4374/11952 [3:31:33<12:09:39, 5.78s/it] 37%|███▋ | 4375/11952 [3:31:38<12:06:38, 5.75s/it] {'loss': 0.482, 'learning_rate': 1.4639939352734484e-05, 'epoch': 0.37} + 37%|███▋ | 4375/11952 [3:31:38<12:06:38, 5.75s/it] 37%|███▋ | 4376/11952 [3:31:44<12:06:03, 5.75s/it] {'loss': 0.4858, 'learning_rate': 1.4637538644713873e-05, 'epoch': 0.37} + 37%|███▋ | 4376/11952 [3:31:44<12:06:03, 5.75s/it] 37%|███▋ | 4377/11952 [3:31:50<12:16:38, 5.83s/it] {'loss': 0.4855, 'learning_rate': 1.4635137596131715e-05, 'epoch': 0.37} + 37%|███▋ | 4377/11952 [3:31:50<12:16:38, 5.83s/it] 37%|███▋ | 4378/11952 [3:31:56<12:18:58, 5.85s/it] {'loss': 0.4978, 'learning_rate': 1.4632736207164326e-05, 'epoch': 0.37} + 37%|███▋ | 4378/11952 [3:31:56<12:18:58, 5.85s/it] 37%|███▋ | 4379/11952 [3:32:02<12:10:56, 5.79s/it] {'loss': 0.4673, 'learning_rate': 1.4630334477988064e-05, 'epoch': 0.37} + 37%|███▋ | 4379/11952 [3:32:02<12:10:56, 5.79s/it] 37%|███▋ | 4380/11952 [3:32:08<12:25:16, 5.91s/it] {'loss': 0.4958, 'learning_rate': 1.4627932408779295e-05, 'epoch': 0.37} + 37%|███▋ | 4380/11952 [3:32:08<12:25:16, 5.91s/it] 37%|███▋ | 4381/11952 [3:32:14<12:13:25, 5.81s/it] {'loss': 0.5042, 'learning_rate': 1.4625529999714416e-05, 'epoch': 0.37} + 37%|███▋ | 4381/11952 [3:32:14<12:13:25, 5.81s/it] 37%|███▋ | 4382/11952 [3:32:19<12:16:29, 5.84s/it] {'loss': 0.4891, 'learning_rate': 1.4623127250969858e-05, 'epoch': 0.37} + 37%|███▋ | 4382/11952 [3:32:19<12:16:29, 5.84s/it] 37%|███▋ | 4383/11952 [3:32:25<12:16:29, 5.84s/it] {'loss': 0.5032, 'learning_rate': 1.4620724162722062e-05, 'epoch': 0.37} + 37%|███▋ | 4383/11952 [3:32:25<12:16:29, 5.84s/it] 37%|███▋ | 4384/11952 [3:32:31<12:15:24, 5.83s/it] {'loss': 0.4884, 'learning_rate': 1.4618320735147501e-05, 'epoch': 0.37} + 37%|███▋ | 4384/11952 [3:32:31<12:15:24, 5.83s/it] 37%|███▋ | 4385/11952 [3:32:37<12:05:28, 5.75s/it] {'loss': 0.4967, 'learning_rate': 1.4615916968422674e-05, 'epoch': 0.37} + 37%|███▋ | 4385/11952 [3:32:37<12:05:28, 5.75s/it] 37%|███▋ | 4386/11952 [3:32:42<12:01:50, 5.72s/it] {'loss': 0.4824, 'learning_rate': 1.4613512862724103e-05, 'epoch': 0.37} + 37%|███▋ | 4386/11952 [3:32:42<12:01:50, 5.72s/it] 37%|███▋ | 4387/11952 [3:32:48<12:05:19, 5.75s/it] {'loss': 0.4766, 'learning_rate': 1.4611108418228342e-05, 'epoch': 0.37} + 37%|███▋ | 4387/11952 [3:32:48<12:05:19, 5.75s/it] 37%|███▋ | 4388/11952 [3:32:54<11:59:00, 5.70s/it] {'loss': 0.4905, 'learning_rate': 1.460870363511195e-05, 'epoch': 0.37} + 37%|███▋ | 4388/11952 [3:32:54<11:59:00, 5.70s/it] 37%|███▋ | 4389/11952 [3:32:59<11:58:17, 5.70s/it] {'loss': 0.4821, 'learning_rate': 1.460629851355154e-05, 'epoch': 0.37} + 37%|███▋ | 4389/11952 [3:32:59<11:58:17, 5.70s/it] 37%|███▋ | 4390/11952 [3:33:05<11:58:22, 5.70s/it] {'loss': 0.4958, 'learning_rate': 1.460389305372372e-05, 'epoch': 0.37} + 37%|███▋ | 4390/11952 [3:33:05<11:58:22, 5.70s/it] 37%|███▋ | 4391/11952 [3:33:11<11:59:47, 5.71s/it] {'loss': 0.4676, 'learning_rate': 1.4601487255805146e-05, 'epoch': 0.37} + 37%|███▋ | 4391/11952 [3:33:11<11:59:47, 5.71s/it] 37%|███▋ | 4392/11952 [3:33:17<12:03:07, 5.74s/it] {'loss': 0.501, 'learning_rate': 1.4599081119972486e-05, 'epoch': 0.37} + 37%|███▋ | 4392/11952 [3:33:17<12:03:07, 5.74s/it] 37%|███▋ | 4393/11952 [3:33:22<12:01:42, 5.73s/it] {'loss': 0.4787, 'learning_rate': 1.459667464640244e-05, 'epoch': 0.37} + 37%|███▋ | 4393/11952 [3:33:22<12:01:42, 5.73s/it] 37%|███▋ | 4394/11952 [3:33:28<12:06:53, 5.77s/it] {'loss': 0.5029, 'learning_rate': 1.4594267835271725e-05, 'epoch': 0.37} + 37%|███▋ | 4394/11952 [3:33:28<12:06:53, 5.77s/it] 37%|███▋ | 4395/11952 [3:33:34<12:10:45, 5.80s/it] {'loss': 0.5047, 'learning_rate': 1.4591860686757089e-05, 'epoch': 0.37} + 37%|███▋ | 4395/11952 [3:33:34<12:10:45, 5.80s/it] 37%|███▋ | 4396/11952 [3:33:40<12:11:47, 5.81s/it] {'loss': 0.5009, 'learning_rate': 1.4589453201035302e-05, 'epoch': 0.37} + 37%|███▋ | 4396/11952 [3:33:40<12:11:47, 5.81s/it] 37%|███▋ | 4397/11952 [3:33:46<12:21:44, 5.89s/it] {'loss': 0.4818, 'learning_rate': 1.4587045378283162e-05, 'epoch': 0.37} + 37%|███▋ | 4397/11952 [3:33:46<12:21:44, 5.89s/it] 37%|███▋ | 4398/11952 [3:33:52<12:12:56, 5.82s/it] {'loss': 0.4601, 'learning_rate': 1.4584637218677488e-05, 'epoch': 0.37} + 37%|███▋ | 4398/11952 [3:33:52<12:12:56, 5.82s/it] 37%|███▋ | 4399/11952 [3:33:57<12:06:44, 5.77s/it] {'loss': 0.504, 'learning_rate': 1.4582228722395128e-05, 'epoch': 0.37} + 37%|███▋ | 4399/11952 [3:33:57<12:06:44, 5.77s/it]3 AutoResumeHook: Checking whether to suspend... +72 AutoResumeHook: Checking whether to suspend...AutoResumeHook: Checking whether to suspend... +5 + AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... +01 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... + 37%|███▋ | 4400/11952 [3:34:03<12:03:05, 5.74s/it]4 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4719, 'learning_rate': 1.4579819889612949e-05, 'epoch': 0.37} + 37%|███▋ | 4400/11952 [3:34:03<12:03:05, 5.74s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-4400/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-4400/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/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( + 37%|███▋ | 4401/11952 [3:34:38<30:20:53, 14.47s/it] {'loss': 0.5031, 'learning_rate': 1.4577410720507842e-05, 'epoch': 0.37} + 37%|███▋ | 4401/11952 [3:34:38<30:20:53, 14.47s/it] 37%|███▋ | 4402/11952 [3:34:43<24:41:03, 11.77s/it] {'loss': 0.4812, 'learning_rate': 1.4575001215256735e-05, 'epoch': 0.37} + 37%|███▋ | 4402/11952 [3:34:43<24:41:03, 11.77s/it] 37%|███▋ | 4403/11952 [3:34:49<20:59:20, 10.01s/it] {'loss': 0.4906, 'learning_rate': 1.4572591374036567e-05, 'epoch': 0.37} + 37%|███▋ | 4403/11952 [3:34:49<20:59:20, 10.01s/it] 37%|███▋ | 4404/11952 [3:34:56<18:38:23, 8.89s/it] {'loss': 0.4945, 'learning_rate': 1.4570181197024307e-05, 'epoch': 0.37} + 37%|███▋ | 4404/11952 [3:34:56<18:38:23, 8.89s/it] 37%|███▋ | 4405/11952 [3:35:01<16:34:50, 7.91s/it] {'loss': 0.4849, 'learning_rate': 1.4567770684396947e-05, 'epoch': 0.37} + 37%|███▋ | 4405/11952 [3:35:01<16:34:50, 7.91s/it] 37%|███▋ | 4406/11952 [3:35:07<15:11:15, 7.25s/it] {'loss': 0.4788, 'learning_rate': 1.456535983633151e-05, 'epoch': 0.37} + 37%|███▋ | 4406/11952 [3:35:07<15:11:15, 7.25s/it] 37%|███▋ | 4407/11952 [3:35:12<14:10:31, 6.76s/it] {'loss': 0.4917, 'learning_rate': 1.4562948653005032e-05, 'epoch': 0.37} + 37%|███▋ | 4407/11952 [3:35:12<14:10:31, 6.76s/it] 37%|███▋ | 4408/11952 [3:35:18<13:30:01, 6.44s/it] {'loss': 0.4728, 'learning_rate': 1.4560537134594586e-05, 'epoch': 0.37} + 37%|███▋ | 4408/11952 [3:35:18<13:30:01, 6.44s/it] 37%|███▋ | 4409/11952 [3:35:24<13:24:49, 6.40s/it] {'loss': 0.4997, 'learning_rate': 1.455812528127726e-05, 'epoch': 0.37} + 37%|███▋ | 4409/11952 [3:35:24<13:24:49, 6.40s/it] 37%|███▋ | 4410/11952 [3:35:30<13:00:49, 6.21s/it] {'loss': 0.493, 'learning_rate': 1.4555713093230173e-05, 'epoch': 0.37} + 37%|███▋ | 4410/11952 [3:35:30<13:00:49, 6.21s/it] 37%|███▋ | 4411/11952 [3:35:36<12:39:51, 6.05s/it] {'loss': 0.4758, 'learning_rate': 1.4553300570630464e-05, 'epoch': 0.37} + 37%|███▋ | 4411/11952 [3:35:36<12:39:51, 6.05s/it] 37%|███▋ | 4412/11952 [3:35:42<12:38:04, 6.03s/it] {'loss': 0.4887, 'learning_rate': 1.4550887713655297e-05, 'epoch': 0.37} + 37%|███▋ | 4412/11952 [3:35:42<12:38:04, 6.03s/it] 37%|███▋ | 4413/11952 [3:35:48<12:29:50, 5.97s/it] {'loss': 0.4892, 'learning_rate': 1.454847452248187e-05, 'epoch': 0.37} + 37%|███▋ | 4413/11952 [3:35:48<12:29:50, 5.97s/it] 37%|███▋ | 4414/11952 [3:35:53<12:21:33, 5.90s/it] {'loss': 0.4678, 'learning_rate': 1.4546060997287392e-05, 'epoch': 0.37} + 37%|███▋ | 4414/11952 [3:35:53<12:21:33, 5.90s/it] 37%|███▋ | 4415/11952 [3:35:59<12:25:48, 5.94s/it] {'loss': 0.5012, 'learning_rate': 1.45436471382491e-05, 'epoch': 0.37} + 37%|███▋ | 4415/11952 [3:35:59<12:25:48, 5.94s/it] 37%|███▋ | 4416/11952 [3:36:05<12:19:14, 5.89s/it] {'loss': 0.5001, 'learning_rate': 1.4541232945544263e-05, 'epoch': 0.37} + 37%|███▋ | 4416/11952 [3:36:05<12:19:14, 5.89s/it] 37%|███▋ | 4417/11952 [3:36:11<12:07:50, 5.80s/it] {'loss': 0.4674, 'learning_rate': 1.4538818419350164e-05, 'epoch': 0.37} + 37%|███▋ | 4417/11952 [3:36:11<12:07:50, 5.80s/it] 37%|███▋ | 4418/11952 [3:36:17<12:04:26, 5.77s/it] {'loss': 0.5016, 'learning_rate': 1.4536403559844123e-05, 'epoch': 0.37} + 37%|███▋ | 4418/11952 [3:36:17<12:04:26, 5.77s/it] 37%|███▋ | 4419/11952 [3:36:22<12:08:03, 5.80s/it] {'loss': 0.4768, 'learning_rate': 1.453398836720347e-05, 'epoch': 0.37} + 37%|███▋ | 4419/11952 [3:36:22<12:08:03, 5.80s/it] 37%|███▋ | 4420/11952 [3:36:29<12:22:40, 5.92s/it] {'loss': 0.4941, 'learning_rate': 1.453157284160557e-05, 'epoch': 0.37} + 37%|███▋ | 4420/11952 [3:36:29<12:22:40, 5.92s/it] 37%|███▋ | 4421/11952 [3:36:34<12:13:55, 5.85s/it] {'loss': 0.4916, 'learning_rate': 1.452915698322781e-05, 'epoch': 0.37} + 37%|███▋ | 4421/11952 [3:36:34<12:13:55, 5.85s/it] 37%|███▋ | 4422/11952 [3:36:40<12:18:24, 5.88s/it] {'loss': 0.4901, 'learning_rate': 1.4526740792247597e-05, 'epoch': 0.37} + 37%|███▋ | 4422/11952 [3:36:40<12:18:24, 5.88s/it] 37%|███▋ | 4423/11952 [3:36:46<12:26:34, 5.95s/it] {'loss': 0.4863, 'learning_rate': 1.4524324268842369e-05, 'epoch': 0.37} + 37%|███▋ | 4423/11952 [3:36:46<12:26:34, 5.95s/it] 37%|███▋ | 4424/11952 [3:36:52<12:22:12, 5.92s/it] {'loss': 0.4917, 'learning_rate': 1.4521907413189587e-05, 'epoch': 0.37} + 37%|███▋ | 4424/11952 [3:36:52<12:22:12, 5.92s/it] 37%|███▋ | 4425/11952 [3:36:58<12:20:02, 5.90s/it] {'loss': 0.4962, 'learning_rate': 1.4519490225466733e-05, 'epoch': 0.37} + 37%|███▋ | 4425/11952 [3:36:58<12:20:02, 5.90s/it] 37%|███▋ | 4426/11952 [3:37:04<12:12:41, 5.84s/it] {'loss': 0.485, 'learning_rate': 1.4517072705851312e-05, 'epoch': 0.37} + 37%|███▋ | 4426/11952 [3:37:04<12:12:41, 5.84s/it] 37%|███▋ | 4427/11952 [3:37:09<12:04:03, 5.77s/it] {'loss': 0.4956, 'learning_rate': 1.451465485452086e-05, 'epoch': 0.37} + 37%|███▋ | 4427/11952 [3:37:09<12:04:03, 5.77s/it] 37%|███▋ | 4428/11952 [3:37:15<11:57:37, 5.72s/it] {'loss': 0.4826, 'learning_rate': 1.4512236671652932e-05, 'epoch': 0.37} + 37%|███▋ | 4428/11952 [3:37:15<11:57:37, 5.72s/it] 37%|███▋ | 4429/11952 [3:37:21<12:10:22, 5.83s/it] {'loss': 0.4832, 'learning_rate': 1.4509818157425112e-05, 'epoch': 0.37} + 37%|███▋ | 4429/11952 [3:37:21<12:10:22, 5.83s/it] 37%|███▋ | 4430/11952 [3:37:27<12:02:47, 5.77s/it] {'loss': 0.4936, 'learning_rate': 1.4507399312015005e-05, 'epoch': 0.37} + 37%|███▋ | 4430/11952 [3:37:27<12:02:47, 5.77s/it] 37%|███▋ | 4431/11952 [3:37:33<12:14:15, 5.86s/it] {'loss': 0.4902, 'learning_rate': 1.4504980135600242e-05, 'epoch': 0.37} + 37%|███▋ | 4431/11952 [3:37:33<12:14:15, 5.86s/it] 37%|███▋ | 4432/11952 [3:37:39<12:10:49, 5.83s/it] {'loss': 0.4943, 'learning_rate': 1.4502560628358473e-05, 'epoch': 0.37} + 37%|███▋ | 4432/11952 [3:37:39<12:10:49, 5.83s/it] 37%|███▋ | 4433/11952 [3:37:44<12:06:22, 5.80s/it] {'loss': 0.4822, 'learning_rate': 1.4500140790467377e-05, 'epoch': 0.37} + 37%|███▋ | 4433/11952 [3:37:44<12:06:22, 5.80s/it] 37%|███▋ | 4434/11952 [3:37:50<11:56:34, 5.72s/it] {'loss': 0.4996, 'learning_rate': 1.449772062210466e-05, 'epoch': 0.37} + 37%|███▋ | 4434/11952 [3:37:50<11:56:34, 5.72s/it] 37%|███▋ | 4435/11952 [3:37:56<12:06:06, 5.80s/it] {'loss': 0.5047, 'learning_rate': 1.449530012344805e-05, 'epoch': 0.37} + 37%|███▋ | 4435/11952 [3:37:56<12:06:06, 5.80s/it] 37%|███▋ | 4436/11952 [3:38:02<12:06:50, 5.80s/it] {'loss': 0.4677, 'learning_rate': 1.4492879294675297e-05, 'epoch': 0.37} + 37%|███▋ | 4436/11952 [3:38:02<12:06:50, 5.80s/it] 37%|███▋ | 4437/11952 [3:38:07<12:04:15, 5.78s/it] {'loss': 0.4872, 'learning_rate': 1.4490458135964173e-05, 'epoch': 0.37} + 37%|███▋ | 4437/11952 [3:38:07<12:04:15, 5.78s/it] 37%|███▋ | 4438/11952 [3:38:13<12:05:33, 5.79s/it] {'loss': 0.4731, 'learning_rate': 1.4488036647492482e-05, 'epoch': 0.37} + 37%|███▋ | 4438/11952 [3:38:13<12:05:33, 5.79s/it] 37%|███▋ | 4439/11952 [3:38:19<12:03:05, 5.77s/it] {'loss': 0.4759, 'learning_rate': 1.4485614829438046e-05, 'epoch': 0.37} + 37%|███▋ | 4439/11952 [3:38:19<12:03:05, 5.77s/it] 37%|███▋ | 4440/11952 [3:38:25<12:02:46, 5.77s/it] {'loss': 0.4946, 'learning_rate': 1.4483192681978715e-05, 'epoch': 0.37} + 37%|███▋ | 4440/11952 [3:38:25<12:02:46, 5.77s/it] 37%|███▋ | 4441/11952 [3:38:30<12:06:20, 5.80s/it] {'loss': 0.4783, 'learning_rate': 1.4480770205292363e-05, 'epoch': 0.37} + 37%|███▋ | 4441/11952 [3:38:30<12:06:20, 5.80s/it] 37%|███▋ | 4442/11952 [3:38:37<12:21:15, 5.92s/it] {'loss': 0.4796, 'learning_rate': 1.4478347399556878e-05, 'epoch': 0.37} + 37%|███▋ | 4442/11952 [3:38:37<12:21:15, 5.92s/it] 37%|███▋ | 4443/11952 [3:38:42<12:11:06, 5.84s/it] {'loss': 0.495, 'learning_rate': 1.447592426495019e-05, 'epoch': 0.37} + 37%|███▋ | 4443/11952 [3:38:42<12:11:06, 5.84s/it] 37%|███▋ | 4444/11952 [3:38:48<12:07:08, 5.81s/it] {'loss': 0.4885, 'learning_rate': 1.4473500801650243e-05, 'epoch': 0.37} + 37%|███▋ | 4444/11952 [3:38:48<12:07:08, 5.81s/it] 37%|███▋ | 4445/11952 [3:38:54<12:05:20, 5.80s/it] {'loss': 0.4771, 'learning_rate': 1.4471077009835001e-05, 'epoch': 0.37} + 37%|███▋ | 4445/11952 [3:38:54<12:05:20, 5.80s/it] 37%|███▋ | 4446/11952 [3:38:59<11:59:06, 5.75s/it] {'loss': 0.4934, 'learning_rate': 1.446865288968246e-05, 'epoch': 0.37} + 37%|███▋ | 4446/11952 [3:38:59<11:59:06, 5.75s/it] 37%|███▋ | 4447/11952 [3:39:05<12:01:01, 5.76s/it] {'loss': 0.5003, 'learning_rate': 1.4466228441370638e-05, 'epoch': 0.37} + 37%|███▋ | 4447/11952 [3:39:05<12:01:01, 5.76s/it] 37%|███▋ | 4448/11952 [3:39:11<12:08:57, 5.83s/it] {'loss': 0.4921, 'learning_rate': 1.4463803665077573e-05, 'epoch': 0.37} + 37%|███▋ | 4448/11952 [3:39:11<12:08:57, 5.83s/it] 37%|███▋ | 4449/11952 [3:39:17<12:01:29, 5.77s/it] {'loss': 0.4844, 'learning_rate': 1.4461378560981335e-05, 'epoch': 0.37} + 37%|███▋ | 4449/11952 [3:39:17<12:01:29, 5.77s/it]36 AutoResumeHook: Checking whether to suspend...AutoResumeHook: Checking whether to suspend... + +1 AutoResumeHook: Checking whether to suspend... +75 AutoResumeHook: Checking whether to suspend... +AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... +04 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... + 37%|███▋ | 4450/11952 [3:39:23<11:56:00, 5.73s/it] {'loss': 0.484, 'learning_rate': 1.4458953129260014e-05, 'epoch': 0.37} + 37%|███▋ | 4450/11952 [3:39:23<11:56:00, 5.73s/it] 37%|███▋ | 4451/11952 [3:39:28<11:53:31, 5.71s/it] {'loss': 0.477, 'learning_rate': 1.4456527370091722e-05, 'epoch': 0.37} + 37%|███▋ | 4451/11952 [3:39:28<11:53:31, 5.71s/it] 37%|███▋ | 4452/11952 [3:39:34<12:01:55, 5.78s/it] {'loss': 0.4759, 'learning_rate': 1.4454101283654594e-05, 'epoch': 0.37} + 37%|███▋ | 4452/11952 [3:39:34<12:01:55, 5.78s/it] 37%|███▋ | 4453/11952 [3:39:40<11:57:52, 5.74s/it] {'loss': 0.4673, 'learning_rate': 1.445167487012679e-05, 'epoch': 0.37} + 37%|███▋ | 4453/11952 [3:39:40<11:57:52, 5.74s/it] 37%|███▋ | 4454/11952 [3:39:46<12:08:58, 5.83s/it] {'loss': 0.4975, 'learning_rate': 1.4449248129686504e-05, 'epoch': 0.37} + 37%|███▋ | 4454/11952 [3:39:46<12:08:58, 5.83s/it] 37%|███▋ | 4455/11952 [3:39:52<12:30:15, 6.00s/it] {'loss': 0.5007, 'learning_rate': 1.4446821062511942e-05, 'epoch': 0.37} + 37%|███▋ | 4455/11952 [3:39:52<12:30:15, 6.00s/it] 37%|███▋ | 4456/11952 [3:39:58<12:26:06, 5.97s/it] {'loss': 0.5061, 'learning_rate': 1.4444393668781334e-05, 'epoch': 0.37} + 37%|███▋ | 4456/11952 [3:39:58<12:26:06, 5.97s/it] 37%|███▋ | 4457/11952 [3:40:04<12:20:01, 5.92s/it] {'loss': 0.4783, 'learning_rate': 1.4441965948672943e-05, 'epoch': 0.37} + 37%|███▋ | 4457/11952 [3:40:04<12:20:01, 5.92s/it] 37%|███▋ | 4458/11952 [3:40:10<12:17:19, 5.90s/it] {'loss': 0.5025, 'learning_rate': 1.4439537902365047e-05, 'epoch': 0.37} + 37%|███▋ | 4458/11952 [3:40:10<12:17:19, 5.90s/it] 37%|███▋ | 4459/11952 [3:40:16<12:11:06, 5.85s/it] {'loss': 0.4762, 'learning_rate': 1.4437109530035951e-05, 'epoch': 0.37} + 37%|███▋ | 4459/11952 [3:40:16<12:11:06, 5.85s/it] 37%|███▋ | 4460/11952 [3:40:21<11:59:27, 5.76s/it] {'loss': 0.503, 'learning_rate': 1.443468083186399e-05, 'epoch': 0.37} + 37%|███▋ | 4460/11952 [3:40:21<11:59:27, 5.76s/it] 37%|███▋ | 4461/11952 [3:40:27<12:16:26, 5.90s/it] {'loss': 0.4933, 'learning_rate': 1.443225180802751e-05, 'epoch': 0.37} + 37%|███▋ | 4461/11952 [3:40:27<12:16:26, 5.90s/it] 37%|███▋ | 4462/11952 [3:40:33<12:07:54, 5.83s/it] {'loss': 0.4887, 'learning_rate': 1.4429822458704896e-05, 'epoch': 0.37} + 37%|███▋ | 4462/11952 [3:40:33<12:07:54, 5.83s/it] 37%|███▋ | 4463/11952 [3:40:39<12:04:37, 5.81s/it] {'loss': 0.4973, 'learning_rate': 1.4427392784074545e-05, 'epoch': 0.37} + 37%|███▋ | 4463/11952 [3:40:39<12:04:37, 5.81s/it] 37%|███▋ | 4464/11952 [3:40:45<12:21:57, 5.95s/it] {'loss': 0.5274, 'learning_rate': 1.442496278431488e-05, 'epoch': 0.37} + 37%|███▋ | 4464/11952 [3:40:45<12:21:57, 5.95s/it] 37%|███▋ | 4465/11952 [3:40:51<12:17:31, 5.91s/it] {'loss': 0.4956, 'learning_rate': 1.4422532459604357e-05, 'epoch': 0.37} + 37%|███▋ | 4465/11952 [3:40:51<12:17:31, 5.91s/it] 37%|███▋ | 4466/11952 [3:40:57<12:29:42, 6.01s/it] {'loss': 0.4856, 'learning_rate': 1.442010181012144e-05, 'epoch': 0.37} + 37%|███▋ | 4466/11952 [3:40:57<12:29:42, 6.01s/it] 37%|███▋ | 4467/11952 [3:41:03<12:34:02, 6.04s/it] {'loss': 0.5036, 'learning_rate': 1.4417670836044635e-05, 'epoch': 0.37} + 37%|███▋ | 4467/11952 [3:41:03<12:34:02, 6.04s/it] 37%|███▋ | 4468/11952 [3:41:09<12:26:32, 5.99s/it] {'loss': 0.5218, 'learning_rate': 1.4415239537552457e-05, 'epoch': 0.37} + 37%|███▋ | 4468/11952 [3:41:09<12:26:32, 5.99s/it] 37%|███▋ | 4469/11952 [3:41:15<12:17:59, 5.92s/it] {'loss': 0.4733, 'learning_rate': 1.4412807914823452e-05, 'epoch': 0.37} + 37%|███▋ | 4469/11952 [3:41:15<12:17:59, 5.92s/it] 37%|███▋ | 4470/11952 [3:41:21<12:12:29, 5.87s/it] {'loss': 0.4742, 'learning_rate': 1.4410375968036185e-05, 'epoch': 0.37} + 37%|███▋ | 4470/11952 [3:41:21<12:12:29, 5.87s/it] 37%|███▋ | 4471/11952 [3:41:26<12:02:54, 5.80s/it] {'loss': 0.4971, 'learning_rate': 1.4407943697369255e-05, 'epoch': 0.37} + 37%|███▋ | 4471/11952 [3:41:26<12:02:54, 5.80s/it] 37%|███▋ | 4472/11952 [3:41:32<12:11:19, 5.87s/it] {'loss': 0.4941, 'learning_rate': 1.4405511103001274e-05, 'epoch': 0.37} + 37%|███▋ | 4472/11952 [3:41:32<12:11:19, 5.87s/it] 37%|███▋ | 4473/11952 [3:41:38<12:04:54, 5.82s/it] {'loss': 0.4734, 'learning_rate': 1.440307818511088e-05, 'epoch': 0.37} + 37%|███▋ | 4473/11952 [3:41:38<12:04:54, 5.82s/it] 37%|███▋ | 4474/11952 [3:41:44<12:07:04, 5.83s/it] {'loss': 0.494, 'learning_rate': 1.4400644943876736e-05, 'epoch': 0.37} + 37%|███▋ | 4474/11952 [3:41:44<12:07:04, 5.83s/it] 37%|███▋ | 4475/11952 [3:41:49<12:02:04, 5.79s/it] {'loss': 0.5102, 'learning_rate': 1.4398211379477534e-05, 'epoch': 0.37} + 37%|███▋ | 4475/11952 [3:41:49<12:02:04, 5.79s/it] 37%|███▋ | 4476/11952 [3:41:56<12:17:00, 5.92s/it] {'loss': 0.4926, 'learning_rate': 1.439577749209198e-05, 'epoch': 0.37} + 37%|███▋ | 4476/11952 [3:41:56<12:17:00, 5.92s/it] 37%|███▋ | 4477/11952 [3:42:02<12:16:27, 5.91s/it] {'loss': 0.4995, 'learning_rate': 1.439334328189881e-05, 'epoch': 0.37} + 37%|███▋ | 4477/11952 [3:42:02<12:16:27, 5.91s/it] 37%|███▋ | 4478/11952 [3:42:07<12:03:42, 5.81s/it] {'loss': 0.5003, 'learning_rate': 1.4390908749076787e-05, 'epoch': 0.37} + 37%|███▋ | 4478/11952 [3:42:07<12:03:42, 5.81s/it] 37%|███▋ | 4479/11952 [3:42:13<12:08:56, 5.85s/it] {'loss': 0.5023, 'learning_rate': 1.4388473893804683e-05, 'epoch': 0.37} + 37%|███▋ | 4479/11952 [3:42:13<12:08:56, 5.85s/it] 37%|███▋ | 4480/11952 [3:42:19<12:14:36, 5.90s/it] {'loss': 0.4786, 'learning_rate': 1.438603871626131e-05, 'epoch': 0.37} + 37%|███▋ | 4480/11952 [3:42:19<12:14:36, 5.90s/it] 37%|███▋ | 4481/11952 [3:42:25<12:13:38, 5.89s/it] {'loss': 0.4957, 'learning_rate': 1.4383603216625499e-05, 'epoch': 0.37} + 37%|███▋ | 4481/11952 [3:42:25<12:13:38, 5.89s/it] 38%|███▊ | 4482/11952 [3:42:31<12:17:04, 5.92s/it] {'loss': 0.5121, 'learning_rate': 1.4381167395076101e-05, 'epoch': 0.37} + 38%|███▊ | 4482/11952 [3:42:31<12:17:04, 5.92s/it] 38%|███▊ | 4483/11952 [3:42:37<12:13:09, 5.89s/it] {'loss': 0.4638, 'learning_rate': 1.4378731251791989e-05, 'epoch': 0.38} + 38%|███▊ | 4483/11952 [3:42:37<12:13:09, 5.89s/it] 38%|███▊ | 4484/11952 [3:42:43<12:08:17, 5.85s/it] {'loss': 0.4954, 'learning_rate': 1.4376294786952067e-05, 'epoch': 0.38} + 38%|███▊ | 4484/11952 [3:42:43<12:08:17, 5.85s/it] 38%|███▊ | 4485/11952 [3:42:48<12:00:45, 5.79s/it] {'loss': 0.4954, 'learning_rate': 1.4373858000735262e-05, 'epoch': 0.38} + 38%|███▊ | 4485/11952 [3:42:48<12:00:45, 5.79s/it] 38%|███▊ | 4486/11952 [3:42:54<11:49:48, 5.70s/it] {'loss': 0.4881, 'learning_rate': 1.4371420893320515e-05, 'epoch': 0.38} + 38%|███▊ | 4486/11952 [3:42:54<11:49:48, 5.70s/it] 38%|███▊ | 4487/11952 [3:43:00<11:53:48, 5.74s/it] {'loss': 0.5036, 'learning_rate': 1.4368983464886799e-05, 'epoch': 0.38} + 38%|███▊ | 4487/11952 [3:43:00<11:53:48, 5.74s/it] 38%|███▊ | 4488/11952 [3:43:05<11:54:06, 5.74s/it] {'loss': 0.4723, 'learning_rate': 1.4366545715613112e-05, 'epoch': 0.38} + 38%|███▊ | 4488/11952 [3:43:05<11:54:06, 5.74s/it] 38%|███▊ | 4489/11952 [3:43:11<11:47:37, 5.69s/it] {'loss': 0.4846, 'learning_rate': 1.4364107645678465e-05, 'epoch': 0.38} + 38%|███▊ | 4489/11952 [3:43:11<11:47:37, 5.69s/it] 38%|███▊ | 4490/11952 [3:43:17<11:53:14, 5.73s/it] {'loss': 0.4819, 'learning_rate': 1.4361669255261905e-05, 'epoch': 0.38} + 38%|███▊ | 4490/11952 [3:43:17<11:53:14, 5.73s/it] 38%|███▊ | 4491/11952 [3:43:22<11:50:59, 5.72s/it] {'loss': 0.4875, 'learning_rate': 1.43592305445425e-05, 'epoch': 0.38} + 38%|███▊ | 4491/11952 [3:43:22<11:50:59, 5.72s/it] 38%|███▊ | 4492/11952 [3:43:28<11:47:02, 5.69s/it] {'loss': 0.4895, 'learning_rate': 1.4356791513699334e-05, 'epoch': 0.38} + 38%|███▊ | 4492/11952 [3:43:28<11:47:02, 5.69s/it] 38%|███▊ | 4493/11952 [3:43:34<11:41:51, 5.65s/it] {'loss': 0.4762, 'learning_rate': 1.4354352162911522e-05, 'epoch': 0.38} + 38%|███▊ | 4493/11952 [3:43:34<11:41:51, 5.65s/it] 38%|███▊ | 4494/11952 [3:43:39<11:44:05, 5.66s/it] {'loss': 0.4905, 'learning_rate': 1.4351912492358196e-05, 'epoch': 0.38} + 38%|███▊ | 4494/11952 [3:43:39<11:44:05, 5.66s/it] 38%|███▊ | 4495/11952 [3:43:45<12:02:54, 5.82s/it] {'loss': 0.4592, 'learning_rate': 1.4349472502218515e-05, 'epoch': 0.38} + 38%|███▊ | 4495/11952 [3:43:45<12:02:54, 5.82s/it] 38%|███▊ | 4496/11952 [3:43:52<12:13:04, 5.90s/it] {'loss': 0.4966, 'learning_rate': 1.4347032192671668e-05, 'epoch': 0.38} + 38%|███▊ | 4496/11952 [3:43:52<12:13:04, 5.90s/it] 38%|███▊ | 4497/11952 [3:43:57<12:00:09, 5.80s/it] {'loss': 0.4847, 'learning_rate': 1.4344591563896857e-05, 'epoch': 0.38} + 38%|███▊ | 4497/11952 [3:43:57<12:00:09, 5.80s/it] 38%|███▊ | 4498/11952 [3:44:03<11:58:12, 5.78s/it] {'loss': 0.4795, 'learning_rate': 1.4342150616073312e-05, 'epoch': 0.38} + 38%|███▊ | 4498/11952 [3:44:03<11:58:12, 5.78s/it] 38%|███▊ | 4499/11952 [3:44:09<12:04:41, 5.83s/it] {'loss': 0.5128, 'learning_rate': 1.4339709349380285e-05, 'epoch': 0.38} + 38%|███▊ | 4499/11952 [3:44:09<12:04:41, 5.83s/it]3 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... +04 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... + 38%|███▊ | 4500/11952 [3:44:14<11:56:13, 5.77s/it] {'loss': 0.4757, 'learning_rate': 1.4337267763997054e-05, 'epoch': 0.38} + 38%|███▊ | 4500/11952 [3:44:14<11:56:13, 5.77s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-4500/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-4500/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/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%|███▊ | 4501/11952 [3:44:48<29:14:33, 14.13s/it] {'loss': 0.4912, 'learning_rate': 1.4334825860102917e-05, 'epoch': 0.38} + 38%|███▊ | 4501/11952 [3:44:48<29:14:33, 14.13s/it] 38%|███▊ | 4502/11952 [3:44:54<24:05:02, 11.64s/it] {'loss': 0.4773, 'learning_rate': 1.4332383637877203e-05, 'epoch': 0.38} + 38%|███▊ | 4502/11952 [3:44:54<24:05:02, 11.64s/it] 38%|███▊ | 4503/11952 [3:44:59<20:20:47, 9.83s/it] {'loss': 0.4955, 'learning_rate': 1.432994109749925e-05, 'epoch': 0.38} + 38%|███▊ | 4503/11952 [3:44:59<20:20:47, 9.83s/it] 38%|███▊ | 4504/11952 [3:45:05<17:43:09, 8.56s/it] {'loss': 0.4786, 'learning_rate': 1.4327498239148434e-05, 'epoch': 0.38} + 38%|███▊ | 4504/11952 [3:45:05<17:43:09, 8.56s/it] 38%|███▊ | 4505/11952 [3:45:11<15:59:40, 7.73s/it] {'loss': 0.4953, 'learning_rate': 1.4325055063004145e-05, 'epoch': 0.38} + 38%|███▊ | 4505/11952 [3:45:11<15:59:40, 7.73s/it] 38%|███▊ | 4506/11952 [3:45:17<14:43:44, 7.12s/it] {'loss': 0.4892, 'learning_rate': 1.4322611569245806e-05, 'epoch': 0.38} + 38%|███▊ | 4506/11952 [3:45:17<14:43:44, 7.12s/it] 38%|███▊ | 4507/11952 [3:45:23<14:03:12, 6.80s/it] {'loss': 0.4917, 'learning_rate': 1.4320167758052848e-05, 'epoch': 0.38} + 38%|███▊ | 4507/11952 [3:45:23<14:03:12, 6.80s/it] 38%|███▊ | 4508/11952 [3:45:29<13:30:59, 6.54s/it] {'loss': 0.4832, 'learning_rate': 1.4317723629604743e-05, 'epoch': 0.38} + 38%|███▊ | 4508/11952 [3:45:29<13:30:59, 6.54s/it] 38%|███▊ | 4509/11952 [3:45:35<13:14:16, 6.40s/it] {'loss': 0.4878, 'learning_rate': 1.431527918408097e-05, 'epoch': 0.38} + 38%|███▊ | 4509/11952 [3:45:35<13:14:16, 6.40s/it] 38%|███▊ | 4510/11952 [3:45:40<12:51:10, 6.22s/it] {'loss': 0.4948, 'learning_rate': 1.4312834421661044e-05, 'epoch': 0.38} + 38%|███▊ | 4510/11952 [3:45:40<12:51:10, 6.22s/it] 38%|███▊ | 4511/11952 [3:45:46<12:32:17, 6.07s/it] {'loss': 0.4869, 'learning_rate': 1.4310389342524494e-05, 'epoch': 0.38} + 38%|███▊ | 4511/11952 [3:45:46<12:32:17, 6.07s/it] 38%|███▊ | 4512/11952 [3:45:52<12:19:17, 5.96s/it] {'loss': 0.491, 'learning_rate': 1.4307943946850883e-05, 'epoch': 0.38} + 38%|███▊ | 4512/11952 [3:45:52<12:19:17, 5.96s/it] 38%|███▊ | 4513/11952 [3:45:58<12:14:19, 5.92s/it] {'loss': 0.4886, 'learning_rate': 1.4305498234819783e-05, 'epoch': 0.38} + 38%|███▊ | 4513/11952 [3:45:58<12:14:19, 5.92s/it] 38%|███▊ | 4514/11952 [3:46:03<12:06:44, 5.86s/it] {'loss': 0.4815, 'learning_rate': 1.4303052206610801e-05, 'epoch': 0.38} + 38%|███▊ | 4514/11952 [3:46:03<12:06:44, 5.86s/it] 38%|███▊ | 4515/11952 [3:46:09<12:05:28, 5.85s/it] {'loss': 0.4738, 'learning_rate': 1.4300605862403563e-05, 'epoch': 0.38} + 38%|███▊ | 4515/11952 [3:46:09<12:05:28, 5.85s/it] 38%|███▊ | 4516/11952 [3:46:15<12:16:59, 5.95s/it] {'loss': 0.5164, 'learning_rate': 1.4298159202377719e-05, 'epoch': 0.38} + 38%|███▊ | 4516/11952 [3:46:15<12:16:59, 5.95s/it] 38%|███▊ | 4517/11952 [3:46:21<12:13:21, 5.92s/it] {'loss': 0.4937, 'learning_rate': 1.4295712226712941e-05, 'epoch': 0.38} + 38%|███▊ | 4517/11952 [3:46:21<12:13:21, 5.92s/it] 38%|███▊ | 4518/11952 [3:46:27<12:05:25, 5.85s/it] {'loss': 0.4743, 'learning_rate': 1.4293264935588921e-05, 'epoch': 0.38} + 38%|███▊ | 4518/11952 [3:46:27<12:05:25, 5.85s/it] 38%|███▊ | 4519/11952 [3:46:33<12:05:35, 5.86s/it] {'loss': 0.4843, 'learning_rate': 1.4290817329185388e-05, 'epoch': 0.38} + 38%|███▊ | 4519/11952 [3:46:33<12:05:35, 5.86s/it] 38%|███▊ | 4520/11952 [3:46:39<12:11:00, 5.90s/it] {'loss': 0.4989, 'learning_rate': 1.428836940768207e-05, 'epoch': 0.38} + 38%|███▊ | 4520/11952 [3:46:39<12:11:00, 5.90s/it] 38%|███▊ | 4521/11952 [3:46:45<12:15:01, 5.93s/it] {'loss': 0.4858, 'learning_rate': 1.4285921171258741e-05, 'epoch': 0.38} + 38%|███▊ | 4521/11952 [3:46:45<12:15:01, 5.93s/it] 38%|███▊ | 4522/11952 [3:46:50<12:04:36, 5.85s/it] {'loss': 0.477, 'learning_rate': 1.4283472620095192e-05, 'epoch': 0.38} + 38%|███▊ | 4522/11952 [3:46:50<12:04:36, 5.85s/it] 38%|███▊ | 4523/11952 [3:46:56<11:55:25, 5.78s/it] {'loss': 0.4741, 'learning_rate': 1.4281023754371226e-05, 'epoch': 0.38} + 38%|███▊ | 4523/11952 [3:46:56<11:55:25, 5.78s/it] 38%|███▊ | 4524/11952 [3:47:02<11:56:52, 5.79s/it] {'loss': 0.4952, 'learning_rate': 1.4278574574266681e-05, 'epoch': 0.38} + 38%|███▊ | 4524/11952 [3:47:02<11:56:52, 5.79s/it] 38%|███▊ | 4525/11952 [3:47:08<11:53:51, 5.77s/it] {'loss': 0.4953, 'learning_rate': 1.4276125079961417e-05, 'epoch': 0.38} + 38%|███▊ | 4525/11952 [3:47:08<11:53:51, 5.77s/it] 38%|███▊ | 4526/11952 [3:47:13<11:49:46, 5.73s/it] {'loss': 0.5021, 'learning_rate': 1.4273675271635313e-05, 'epoch': 0.38} + 38%|███▊ | 4526/11952 [3:47:13<11:49:46, 5.73s/it] 38%|███▊ | 4527/11952 [3:47:19<11:54:52, 5.78s/it] {'loss': 0.4825, 'learning_rate': 1.4271225149468272e-05, 'epoch': 0.38} + 38%|███▊ | 4527/11952 [3:47:19<11:54:52, 5.78s/it] 38%|███▊ | 4528/11952 [3:47:25<11:53:42, 5.77s/it] {'loss': 0.4693, 'learning_rate': 1.426877471364022e-05, 'epoch': 0.38} + 38%|███▊ | 4528/11952 [3:47:25<11:53:42, 5.77s/it] 38%|███▊ | 4529/11952 [3:47:31<12:12:13, 5.92s/it] {'loss': 0.4788, 'learning_rate': 1.4266323964331112e-05, 'epoch': 0.38} + 38%|███▊ | 4529/11952 [3:47:31<12:12:13, 5.92s/it] 38%|███▊ | 4530/11952 [3:47:37<12:11:43, 5.92s/it] {'loss': 0.469, 'learning_rate': 1.4263872901720914e-05, 'epoch': 0.38} + 38%|███▊ | 4530/11952 [3:47:37<12:11:43, 5.92s/it] 38%|███▊ | 4531/11952 [3:47:43<12:06:05, 5.87s/it] {'loss': 0.4949, 'learning_rate': 1.4261421525989625e-05, 'epoch': 0.38} + 38%|███▊ | 4531/11952 [3:47:43<12:06:05, 5.87s/it] 38%|███▊ | 4532/11952 [3:47:48<11:57:01, 5.80s/it] {'loss': 0.4905, 'learning_rate': 1.4258969837317265e-05, 'epoch': 0.38} + 38%|███▊ | 4532/11952 [3:47:48<11:57:01, 5.80s/it] 38%|███▊ | 4533/11952 [3:47:54<12:01:10, 5.83s/it] {'loss': 0.488, 'learning_rate': 1.4256517835883874e-05, 'epoch': 0.38} + 38%|███▊ | 4533/11952 [3:47:54<12:01:10, 5.83s/it] 38%|███▊ | 4534/11952 [3:48:00<12:01:20, 5.83s/it] {'loss': 0.5049, 'learning_rate': 1.4254065521869519e-05, 'epoch': 0.38} + 38%|███▊ | 4534/11952 [3:48:00<12:01:20, 5.83s/it] 38%|███▊ | 4535/11952 [3:48:06<12:14:02, 5.94s/it] {'loss': 0.5057, 'learning_rate': 1.4251612895454282e-05, 'epoch': 0.38} + 38%|███▊ | 4535/11952 [3:48:06<12:14:02, 5.94s/it] 38%|███▊ | 4536/11952 [3:48:12<12:13:09, 5.93s/it] {'loss': 0.4912, 'learning_rate': 1.4249159956818279e-05, 'epoch': 0.38} + 38%|███▊ | 4536/11952 [3:48:12<12:13:09, 5.93s/it] 38%|███▊ | 4537/11952 [3:48:18<12:07:22, 5.89s/it] {'loss': 0.5032, 'learning_rate': 1.4246706706141646e-05, 'epoch': 0.38} + 38%|███▊ | 4537/11952 [3:48:18<12:07:22, 5.89s/it] 38%|███▊ | 4538/11952 [3:48:24<12:09:51, 5.91s/it] {'loss': 0.4765, 'learning_rate': 1.4244253143604531e-05, 'epoch': 0.38} + 38%|███▊ | 4538/11952 [3:48:24<12:09:51, 5.91s/it] 38%|███▊ | 4539/11952 [3:48:30<12:16:59, 5.97s/it] {'loss': 0.4854, 'learning_rate': 1.4241799269387122e-05, 'epoch': 0.38} + 38%|███▊ | 4539/11952 [3:48:30<12:16:59, 5.97s/it] 38%|███▊ | 4540/11952 [3:48:36<12:04:25, 5.86s/it] {'loss': 0.4815, 'learning_rate': 1.4239345083669615e-05, 'epoch': 0.38} + 38%|███▊ | 4540/11952 [3:48:36<12:04:25, 5.86s/it] 38%|███▊ | 4541/11952 [3:48:42<12:08:12, 5.90s/it] {'loss': 0.5124, 'learning_rate': 1.423689058663224e-05, 'epoch': 0.38} + 38%|███▊ | 4541/11952 [3:48:42<12:08:12, 5.90s/it] 38%|███▊ | 4542/11952 [3:48:48<12:07:09, 5.89s/it] {'loss': 0.4851, 'learning_rate': 1.4234435778455242e-05, 'epoch': 0.38} + 38%|███▊ | 4542/11952 [3:48:48<12:07:09, 5.89s/it] 38%|███▊ | 4543/11952 [3:48:53<12:01:18, 5.84s/it] {'loss': 0.5049, 'learning_rate': 1.4231980659318891e-05, 'epoch': 0.38} + 38%|███▊ | 4543/11952 [3:48:53<12:01:18, 5.84s/it] 38%|███▊ | 4544/11952 [3:48:59<11:53:25, 5.78s/it] {'loss': 0.4756, 'learning_rate': 1.4229525229403486e-05, 'epoch': 0.38} + 38%|███▊ | 4544/11952 [3:48:59<11:53:25, 5.78s/it] 38%|███▊ | 4545/11952 [3:49:05<11:57:36, 5.81s/it] {'loss': 0.4865, 'learning_rate': 1.4227069488889338e-05, 'epoch': 0.38} + 38%|███▊ | 4545/11952 [3:49:05<11:57:36, 5.81s/it] 38%|███▊ | 4546/11952 [3:49:11<11:56:14, 5.80s/it] {'loss': 0.4887, 'learning_rate': 1.422461343795679e-05, 'epoch': 0.38} + 38%|███▊ | 4546/11952 [3:49:11<11:56:14, 5.80s/it] 38%|███▊ | 4547/11952 [3:49:17<12:03:09, 5.86s/it] {'loss': 0.4804, 'learning_rate': 1.4222157076786201e-05, 'epoch': 0.38} + 38%|███▊ | 4547/11952 [3:49:17<12:03:09, 5.86s/it] 38%|███▊ | 4548/11952 [3:49:22<11:53:23, 5.78s/it] {'loss': 0.4999, 'learning_rate': 1.4219700405557958e-05, 'epoch': 0.38} + 38%|███▊ | 4548/11952 [3:49:22<11:53:23, 5.78s/it] 38%|███▊ | 4549/11952 [3:49:28<11:57:06, 5.81s/it] {'loss': 0.4974, 'learning_rate': 1.4217243424452466e-05, 'epoch': 0.38} + 38%|███▊ | 4549/11952 [3:49:28<11:57:06, 5.81s/it]1 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... +0 AutoResumeHook: Checking whether to suspend... + 38%|███▊ | 4550/11952 [3:49:34<11:53:42, 5.79s/it] {'loss': 0.5029, 'learning_rate': 1.4214786133650162e-05, 'epoch': 0.38} + 38%|███▊ | 4550/11952 [3:49:34<11:53:42, 5.79s/it] 38%|███▊ | 4551/11952 [3:49:40<11:52:41, 5.78s/it] {'loss': 0.4983, 'learning_rate': 1.4212328533331493e-05, 'epoch': 0.38} + 38%|███▊ | 4551/11952 [3:49:40<11:52:41, 5.78s/it] 38%|███▊ | 4552/11952 [3:49:46<11:56:49, 5.81s/it] {'loss': 0.5079, 'learning_rate': 1.4209870623676934e-05, 'epoch': 0.38} + 38%|███▊ | 4552/11952 [3:49:46<11:56:49, 5.81s/it] 38%|███▊ | 4553/11952 [3:49:51<11:59:10, 5.83s/it] {'loss': 0.5062, 'learning_rate': 1.4207412404866992e-05, 'epoch': 0.38} + 38%|███▊ | 4553/11952 [3:49:51<11:59:10, 5.83s/it] 38%|███▊ | 4554/11952 [3:49:57<12:03:20, 5.87s/it] {'loss': 0.496, 'learning_rate': 1.420495387708218e-05, 'epoch': 0.38} + 38%|███▊ | 4554/11952 [3:49:57<12:03:20, 5.87s/it] 38%|███▊ | 4555/11952 [3:50:03<11:53:53, 5.79s/it] {'loss': 0.5021, 'learning_rate': 1.4202495040503043e-05, 'epoch': 0.38} + 38%|███▊ | 4555/11952 [3:50:03<11:53:53, 5.79s/it] 38%|███▊ | 4556/11952 [3:50:09<11:48:40, 5.75s/it] {'loss': 0.492, 'learning_rate': 1.4200035895310151e-05, 'epoch': 0.38} + 38%|███▊ | 4556/11952 [3:50:09<11:48:40, 5.75s/it] 38%|███▊ | 4557/11952 [3:50:14<11:45:44, 5.73s/it] {'loss': 0.4871, 'learning_rate': 1.4197576441684096e-05, 'epoch': 0.38} + 38%|███▊ | 4557/11952 [3:50:14<11:45:44, 5.73s/it] 38%|███▊ | 4558/11952 [3:50:20<11:50:18, 5.76s/it] {'loss': 0.4845, 'learning_rate': 1.4195116679805483e-05, 'epoch': 0.38} + 38%|███▊ | 4558/11952 [3:50:20<11:50:18, 5.76s/it] 38%|███▊ | 4559/11952 [3:50:26<11:54:14, 5.80s/it] {'loss': 0.4746, 'learning_rate': 1.4192656609854949e-05, 'epoch': 0.38} + 38%|███▊ | 4559/11952 [3:50:26<11:54:14, 5.80s/it] 38%|███▊ | 4560/11952 [3:50:32<11:49:36, 5.76s/it] {'loss': 0.486, 'learning_rate': 1.4190196232013154e-05, 'epoch': 0.38} + 38%|███▊ | 4560/11952 [3:50:32<11:49:36, 5.76s/it] 38%|███▊ | 4561/11952 [3:50:38<11:59:20, 5.84s/it] {'loss': 0.4918, 'learning_rate': 1.4187735546460775e-05, 'epoch': 0.38} + 38%|███▊ | 4561/11952 [3:50:38<11:59:20, 5.84s/it] 38%|███▊ | 4562/11952 [3:50:44<12:03:24, 5.87s/it] {'loss': 0.5124, 'learning_rate': 1.4185274553378513e-05, 'epoch': 0.38} + 38%|███▊ | 4562/11952 [3:50:44<12:03:24, 5.87s/it] 38%|███▊ | 4563/11952 [3:50:49<11:57:28, 5.83s/it] {'loss': 0.4785, 'learning_rate': 1.41828132529471e-05, 'epoch': 0.38} + 38%|███▊ | 4563/11952 [3:50:49<11:57:28, 5.83s/it] 38%|███▊ | 4564/11952 [3:50:55<11:55:27, 5.81s/it] {'loss': 0.4927, 'learning_rate': 1.4180351645347279e-05, 'epoch': 0.38} + 38%|███▊ | 4564/11952 [3:50:55<11:55:27, 5.81s/it] 38%|███▊ | 4565/11952 [3:51:01<12:10:15, 5.93s/it] {'loss': 0.5018, 'learning_rate': 1.417788973075982e-05, 'epoch': 0.38} + 38%|███▊ | 4565/11952 [3:51:01<12:10:15, 5.93s/it] 38%|███▊ | 4566/11952 [3:51:07<12:00:19, 5.85s/it] {'loss': 0.4941, 'learning_rate': 1.4175427509365516e-05, 'epoch': 0.38} + 38%|███▊ | 4566/11952 [3:51:07<12:00:19, 5.85s/it] 38%|███▊ | 4567/11952 [3:51:13<12:11:17, 5.94s/it] {'loss': 0.4783, 'learning_rate': 1.417296498134518e-05, 'epoch': 0.38} + 38%|███▊ | 4567/11952 [3:51:13<12:11:17, 5.94s/it] 38%|███▊ | 4568/11952 [3:51:19<12:15:33, 5.98s/it] {'loss': 0.5057, 'learning_rate': 1.4170502146879656e-05, 'epoch': 0.38} + 38%|███▊ | 4568/11952 [3:51:19<12:15:33, 5.98s/it] 38%|███▊ | 4569/11952 [3:51:25<12:15:52, 5.98s/it] {'loss': 0.5271, 'learning_rate': 1.4168039006149799e-05, 'epoch': 0.38} + 38%|███▊ | 4569/11952 [3:51:25<12:15:52, 5.98s/it] 38%|███▊ | 4570/11952 [3:51:31<12:01:30, 5.86s/it] {'loss': 0.4779, 'learning_rate': 1.4165575559336496e-05, 'epoch': 0.38} + 38%|███▊ | 4570/11952 [3:51:31<12:01:30, 5.86s/it] 38%|███▊ | 4571/11952 [3:51:37<12:01:47, 5.87s/it] {'loss': 0.4642, 'learning_rate': 1.4163111806620646e-05, 'epoch': 0.38} + 38%|███▊ | 4571/11952 [3:51:37<12:01:47, 5.87s/it] 38%|███▊ | 4572/11952 [3:51:43<12:06:16, 5.90s/it] {'loss': 0.5108, 'learning_rate': 1.416064774818318e-05, 'epoch': 0.38} + 38%|███▊ | 4572/11952 [3:51:43<12:06:16, 5.90s/it] 38%|███▊ | 4573/11952 [3:51:49<12:04:08, 5.89s/it] {'loss': 0.4914, 'learning_rate': 1.4158183384205052e-05, 'epoch': 0.38} + 38%|███▊ | 4573/11952 [3:51:49<12:04:08, 5.89s/it] 38%|███▊ | 4574/11952 [3:51:54<12:02:42, 5.88s/it] {'loss': 0.4902, 'learning_rate': 1.4155718714867232e-05, 'epoch': 0.38} + 38%|███▊ | 4574/11952 [3:51:54<12:02:42, 5.88s/it] 38%|███▊ | 4575/11952 [3:52:00<12:04:10, 5.89s/it] {'loss': 0.4846, 'learning_rate': 1.4153253740350717e-05, 'epoch': 0.38} + 38%|███▊ | 4575/11952 [3:52:00<12:04:10, 5.89s/it] 38%|███▊ | 4576/11952 [3:52:06<12:02:11, 5.87s/it] {'loss': 0.4685, 'learning_rate': 1.4150788460836516e-05, 'epoch': 0.38} + 38%|███▊ | 4576/11952 [3:52:06<12:02:11, 5.87s/it] 38%|███▊ | 4577/11952 [3:52:12<12:00:16, 5.86s/it] {'loss': 0.4808, 'learning_rate': 1.4148322876505675e-05, 'epoch': 0.38} + 38%|███▊ | 4577/11952 [3:52:12<12:00:16, 5.86s/it] 38%|███▊ | 4578/11952 [3:52:18<11:56:32, 5.83s/it] {'loss': 0.4915, 'learning_rate': 1.4145856987539261e-05, 'epoch': 0.38} + 38%|███▊ | 4578/11952 [3:52:18<11:56:32, 5.83s/it] 38%|███▊ | 4579/11952 [3:52:24<11:59:39, 5.86s/it] {'loss': 0.4938, 'learning_rate': 1.414339079411835e-05, 'epoch': 0.38} + 38%|███▊ | 4579/11952 [3:52:24<11:59:39, 5.86s/it] 38%|███▊ | 4580/11952 [3:52:30<12:07:23, 5.92s/it] {'loss': 0.4984, 'learning_rate': 1.4140924296424055e-05, 'epoch': 0.38} + 38%|███▊ | 4580/11952 [3:52:30<12:07:23, 5.92s/it] 38%|███▊ | 4581/11952 [3:52:36<12:03:15, 5.89s/it] {'loss': 0.4884, 'learning_rate': 1.4138457494637501e-05, 'epoch': 0.38} + 38%|███▊ | 4581/11952 [3:52:36<12:03:15, 5.89s/it] 38%|███▊ | 4582/11952 [3:52:41<11:59:49, 5.86s/it] {'loss': 0.4833, 'learning_rate': 1.4135990388939839e-05, 'epoch': 0.38} + 38%|███▊ | 4582/11952 [3:52:41<11:59:49, 5.86s/it] 38%|███▊ | 4583/11952 [3:52:47<11:52:23, 5.80s/it] {'loss': 0.4856, 'learning_rate': 1.4133522979512252e-05, 'epoch': 0.38} + 38%|███▊ | 4583/11952 [3:52:47<11:52:23, 5.80s/it] 38%|███▊ | 4584/11952 [3:52:53<12:07:36, 5.93s/it] {'loss': 0.4952, 'learning_rate': 1.4131055266535926e-05, 'epoch': 0.38} + 38%|███▊ | 4584/11952 [3:52:53<12:07:36, 5.93s/it] 38%|███▊ | 4585/11952 [3:52:59<12:14:59, 5.99s/it] {'loss': 0.5056, 'learning_rate': 1.4128587250192087e-05, 'epoch': 0.38} + 38%|███▊ | 4585/11952 [3:52:59<12:14:59, 5.99s/it] 38%|███▊ | 4586/11952 [3:53:05<12:07:48, 5.93s/it] {'loss': 0.4818, 'learning_rate': 1.412611893066197e-05, 'epoch': 0.38} + 38%|███▊ | 4586/11952 [3:53:05<12:07:48, 5.93s/it] 38%|███▊ | 4587/11952 [3:53:11<12:00:58, 5.87s/it] {'loss': 0.4854, 'learning_rate': 1.4123650308126839e-05, 'epoch': 0.38} + 38%|███▊ | 4587/11952 [3:53:11<12:00:58, 5.87s/it] 38%|███▊ | 4588/11952 [3:53:17<12:05:23, 5.91s/it] {'loss': 0.4762, 'learning_rate': 1.4121181382767986e-05, 'epoch': 0.38} + 38%|███▊ | 4588/11952 [3:53:17<12:05:23, 5.91s/it] 38%|███▊ | 4589/11952 [3:53:22<11:49:43, 5.78s/it] {'loss': 0.4713, 'learning_rate': 1.4118712154766708e-05, 'epoch': 0.38} + 38%|███▊ | 4589/11952 [3:53:22<11:49:43, 5.78s/it] 38%|███▊ | 4590/11952 [3:53:28<11:47:19, 5.76s/it] {'loss': 0.4836, 'learning_rate': 1.4116242624304343e-05, 'epoch': 0.38} + 38%|███▊ | 4590/11952 [3:53:28<11:47:19, 5.76s/it] 38%|███▊ | 4591/11952 [3:53:34<11:52:50, 5.81s/it] {'loss': 0.4767, 'learning_rate': 1.411377279156224e-05, 'epoch': 0.38} + 38%|███▊ | 4591/11952 [3:53:34<11:52:50, 5.81s/it] 38%|███▊ | 4592/11952 [3:53:40<11:45:01, 5.75s/it] {'loss': 0.4845, 'learning_rate': 1.4111302656721775e-05, 'epoch': 0.38} + 38%|███▊ | 4592/11952 [3:53:40<11:45:01, 5.75s/it] 38%|███▊ | 4593/11952 [3:53:45<11:46:43, 5.76s/it] {'loss': 0.4769, 'learning_rate': 1.410883221996434e-05, 'epoch': 0.38} + 38%|███▊ | 4593/11952 [3:53:45<11:46:43, 5.76s/it] 38%|███▊ | 4594/11952 [3:53:51<11:50:24, 5.79s/it] {'loss': 0.4906, 'learning_rate': 1.410636148147136e-05, 'epoch': 0.38} + 38%|███▊ | 4594/11952 [3:53:51<11:50:24, 5.79s/it] 38%|███▊ | 4595/11952 [3:53:57<11:45:25, 5.75s/it] {'loss': 0.4971, 'learning_rate': 1.4103890441424271e-05, 'epoch': 0.38} + 38%|███▊ | 4595/11952 [3:53:57<11:45:25, 5.75s/it] 38%|███▊ | 4596/11952 [3:54:03<11:41:52, 5.72s/it] {'loss': 0.481, 'learning_rate': 1.4101419100004537e-05, 'epoch': 0.38} + 38%|███▊ | 4596/11952 [3:54:03<11:41:52, 5.72s/it] 38%|███▊ | 4597/11952 [3:54:09<11:49:35, 5.79s/it] {'loss': 0.4774, 'learning_rate': 1.4098947457393641e-05, 'epoch': 0.38} + 38%|███▊ | 4597/11952 [3:54:09<11:49:35, 5.79s/it] 38%|███▊ | 4598/11952 [3:54:14<11:47:59, 5.78s/it] {'loss': 0.4893, 'learning_rate': 1.4096475513773097e-05, 'epoch': 0.38} + 38%|███▊ | 4598/11952 [3:54:14<11:47:59, 5.78s/it] 38%|███▊ | 4599/11952 [3:54:20<12:04:40, 5.91s/it] {'loss': 0.4874, 'learning_rate': 1.4094003269324428e-05, 'epoch': 0.38} + 38%|███▊ | 4599/11952 [3:54:20<12:04:40, 5.91s/it]51 AutoResumeHook: Checking whether to suspend...AutoResumeHook: Checking whether to suspend... + +3 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +0 AutoResumeHook: Checking whether to suspend... + 38%|███▊ | 4600/11952 [3:54:26<12:03:58, 5.91s/it] {'loss': 0.5024, 'learning_rate': 1.4091530724229188e-05, 'epoch': 0.38} + 38%|███▊ | 4600/11952 [3:54:26<12:03:58, 5.91s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-4600/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-4600/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/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( + 38%|███▊ | 4601/11952 [3:55:00<29:03:47, 14.23s/it] {'loss': 0.5141, 'learning_rate': 1.408905787866895e-05, 'epoch': 0.38} + 38%|███▊ | 4601/11952 [3:55:00<29:03:47, 14.23s/it] 39%|███▊ | 4602/11952 [3:55:06<23:44:47, 11.63s/it] {'loss': 0.4768, 'learning_rate': 1.4086584732825306e-05, 'epoch': 0.39} + 39%|███▊ | 4602/11952 [3:55:06<23:44:47, 11.63s/it] 39%|███▊ | 4603/11952 [3:55:11<20:03:08, 9.82s/it] {'loss': 0.5032, 'learning_rate': 1.4084111286879878e-05, 'epoch': 0.39} + 39%|███▊ | 4603/11952 [3:55:11<20:03:08, 9.82s/it] 39%|███▊ | 4604/11952 [3:55:17<17:37:49, 8.64s/it] {'loss': 0.4939, 'learning_rate': 1.4081637541014306e-05, 'epoch': 0.39} + 39%|███▊ | 4604/11952 [3:55:17<17:37:49, 8.64s/it] 39%|███▊ | 4605/11952 [3:55:23<16:01:59, 7.86s/it] {'loss': 0.4796, 'learning_rate': 1.4079163495410248e-05, 'epoch': 0.39} + 39%|███▊ | 4605/11952 [3:55:23<16:01:59, 7.86s/it] 39%|███▊ | 4606/11952 [3:55:29<14:41:26, 7.20s/it] {'loss': 0.4617, 'learning_rate': 1.407668915024939e-05, 'epoch': 0.39} + 39%|███▊ | 4606/11952 [3:55:29<14:41:26, 7.20s/it] 39%|███▊ | 4607/11952 [3:55:34<13:39:25, 6.69s/it] {'loss': 0.4805, 'learning_rate': 1.4074214505713437e-05, 'epoch': 0.39} + 39%|███▊ | 4607/11952 [3:55:34<13:39:25, 6.69s/it] 39%|███▊ | 4608/11952 [3:55:40<13:12:07, 6.47s/it] {'loss': 0.4849, 'learning_rate': 1.4071739561984115e-05, 'epoch': 0.39} + 39%|███▊ | 4608/11952 [3:55:40<13:12:07, 6.47s/it] 39%|███▊ | 4609/11952 [3:55:46<12:49:27, 6.29s/it] {'loss': 0.4756, 'learning_rate': 1.4069264319243178e-05, 'epoch': 0.39} + 39%|███▊ | 4609/11952 [3:55:46<12:49:27, 6.29s/it] 39%|███▊ | 4610/11952 [3:55:52<12:33:46, 6.16s/it] {'loss': 0.517, 'learning_rate': 1.4066788777672393e-05, 'epoch': 0.39} + 39%|███▊ | 4610/11952 [3:55:52<12:33:46, 6.16s/it] 39%|███▊ | 4611/11952 [3:55:58<12:15:08, 6.01s/it] {'loss': 0.476, 'learning_rate': 1.4064312937453556e-05, 'epoch': 0.39} + 39%|███▊ | 4611/11952 [3:55:58<12:15:08, 6.01s/it] 39%|███▊ | 4612/11952 [3:56:04<12:33:42, 6.16s/it] {'loss': 0.5265, 'learning_rate': 1.406183679876848e-05, 'epoch': 0.39} + 39%|███▊ | 4612/11952 [3:56:04<12:33:42, 6.16s/it] 39%|███▊ | 4613/11952 [3:56:10<12:27:04, 6.11s/it] {'loss': 0.4927, 'learning_rate': 1.4059360361799004e-05, 'epoch': 0.39} + 39%|███▊ | 4613/11952 [3:56:10<12:27:04, 6.11s/it] 39%|███▊ | 4614/11952 [3:56:16<12:14:35, 6.01s/it] {'loss': 0.4918, 'learning_rate': 1.4056883626726989e-05, 'epoch': 0.39} + 39%|███▊ | 4614/11952 [3:56:16<12:14:35, 6.01s/it] 39%|███▊ | 4615/11952 [3:56:22<12:12:19, 5.99s/it] {'loss': 0.4821, 'learning_rate': 1.4054406593734316e-05, 'epoch': 0.39} + 39%|███▊ | 4615/11952 [3:56:22<12:12:19, 5.99s/it] 39%|███▊ | 4616/11952 [3:56:28<12:10:32, 5.97s/it] {'loss': 0.4773, 'learning_rate': 1.4051929263002884e-05, 'epoch': 0.39} + 39%|███▊ | 4616/11952 [3:56:28<12:10:32, 5.97s/it] 39%|███▊ | 4617/11952 [3:56:33<11:59:44, 5.89s/it] {'loss': 0.491, 'learning_rate': 1.404945163471462e-05, 'epoch': 0.39} + 39%|███▊ | 4617/11952 [3:56:33<11:59:44, 5.89s/it] 39%|███▊ | 4618/11952 [3:56:40<12:11:46, 5.99s/it] {'loss': 0.4877, 'learning_rate': 1.4046973709051467e-05, 'epoch': 0.39} + 39%|███▊ | 4618/11952 [3:56:40<12:11:46, 5.99s/it] 39%|███▊ | 4619/11952 [3:56:46<12:15:38, 6.02s/it] {'loss': 0.4922, 'learning_rate': 1.4044495486195404e-05, 'epoch': 0.39} + 39%|███▊ | 4619/11952 [3:56:46<12:15:38, 6.02s/it] 39%|███▊ | 4620/11952 [3:56:51<12:03:26, 5.92s/it] {'loss': 0.4758, 'learning_rate': 1.4042016966328411e-05, 'epoch': 0.39} + 39%|███▊ | 4620/11952 [3:56:51<12:03:26, 5.92s/it] 39%|███▊ | 4621/11952 [3:56:57<12:05:46, 5.94s/it] {'loss': 0.526, 'learning_rate': 1.4039538149632508e-05, 'epoch': 0.39} + 39%|███▊ | 4621/11952 [3:56:57<12:05:46, 5.94s/it] 39%|███▊ | 4622/11952 [3:57:03<11:56:22, 5.86s/it] {'loss': 0.4764, 'learning_rate': 1.4037059036289722e-05, 'epoch': 0.39} + 39%|███▊ | 4622/11952 [3:57:03<11:56:22, 5.86s/it] 39%|███▊ | 4623/11952 [3:57:09<11:47:56, 5.80s/it] {'loss': 0.4764, 'learning_rate': 1.4034579626482112e-05, 'epoch': 0.39} + 39%|███▊ | 4623/11952 [3:57:09<11:47:56, 5.80s/it] 39%|███▊ | 4624/11952 [3:57:15<12:01:10, 5.90s/it] {'loss': 0.4878, 'learning_rate': 1.4032099920391753e-05, 'epoch': 0.39} + 39%|███▊ | 4624/11952 [3:57:15<12:01:10, 5.90s/it] 39%|███▊ | 4625/11952 [3:57:21<11:52:32, 5.83s/it] {'loss': 0.4794, 'learning_rate': 1.402961991820075e-05, 'epoch': 0.39} + 39%|███▊ | 4625/11952 [3:57:21<11:52:32, 5.83s/it] 39%|███▊ | 4626/11952 [3:57:26<11:49:50, 5.81s/it] {'loss': 0.4732, 'learning_rate': 1.4027139620091221e-05, 'epoch': 0.39} + 39%|███▊ | 4626/11952 [3:57:26<11:49:50, 5.81s/it] 39%|███▊ | 4627/11952 [3:57:32<11:52:08, 5.83s/it] {'loss': 0.4775, 'learning_rate': 1.4024659026245307e-05, 'epoch': 0.39} + 39%|███▊ | 4627/11952 [3:57:32<11:52:08, 5.83s/it] 39%|███▊ | 4628/11952 [3:57:38<11:55:55, 5.87s/it] {'loss': 0.5077, 'learning_rate': 1.4022178136845173e-05, 'epoch': 0.39} + 39%|███▊ | 4628/11952 [3:57:38<11:55:55, 5.87s/it] 39%|███▊ | 4629/11952 [3:57:44<11:59:39, 5.90s/it] {'loss': 0.4914, 'learning_rate': 1.4019696952073008e-05, 'epoch': 0.39} + 39%|███▊ | 4629/11952 [3:57:44<11:59:39, 5.90s/it] 39%|███▊ | 4630/11952 [3:57:50<11:47:42, 5.80s/it] {'loss': 0.4836, 'learning_rate': 1.4017215472111016e-05, 'epoch': 0.39} + 39%|███▊ | 4630/11952 [3:57:50<11:47:42, 5.80s/it] 39%|███▊ | 4631/11952 [3:57:55<11:42:34, 5.76s/it] {'loss': 0.4965, 'learning_rate': 1.401473369714143e-05, 'epoch': 0.39} + 39%|███▊ | 4631/11952 [3:57:55<11:42:34, 5.76s/it] 39%|███▉ | 4632/11952 [3:58:02<11:55:56, 5.87s/it] {'loss': 0.4938, 'learning_rate': 1.40122516273465e-05, 'epoch': 0.39} + 39%|███▉ | 4632/11952 [3:58:02<11:55:56, 5.87s/it] 39%|███▉ | 4633/11952 [3:58:07<11:49:38, 5.82s/it] {'loss': 0.4691, 'learning_rate': 1.4009769262908498e-05, 'epoch': 0.39} + 39%|███▉ | 4633/11952 [3:58:07<11:49:38, 5.82s/it]Jun 10 16:33:11.115388 2754440 slurmstepd 0x155550ab8700: error: *** STEP 8828654.0 ON batch-block1-0014 CANCELLED AT 2025-06-10T16:33:11 DUE TO TIME LIMIT *** +srun: Job step aborted: Waiting up to 122 seconds for job step to finish. + 39%|███▉ | 4634/11952 [3:58:13<11:53:56, 5.85s/it] {'loss': 0.4841, 'learning_rate': 1.4007286604009717e-05, 'epoch': 0.39} + 39%|███▉ | 4634/11952 [3:58:13<11:53:56, 5.85s/it]srun: error: batch-block1-0014: task 0: Terminated +srun: Terminating StepId=8828654.0 +srun: job 8833833 queued and waiting for resources +srun: job 8833833 has been allocated resources +wandb: Currently logged in as: memmelma. Use `wandb login --relogin` to force relogin +MASTER_ADDR=batch-block1-2091 +JobID: 8833833 | Full list: batch-block1-2091 +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! +[2025-06-10 16:39:53,981] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-10 16:39:53,981] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-10 16:39:53,981] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-10 16:39:53,981] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-10 16:39:53,981] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-10 16:39:53,981] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-10 16:39:53,981] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-10 16:39:53,982] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-10 16:39:55,326] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-10 16:39:55,326] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-10 16:39:55,326] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-10 16:39:55,326] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-10 16:39:55,326] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-10 16:39:55,326] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-10 16:39:55,326] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-10 16:39:55,326] [INFO] [comm.py:625:init_distributed] Initializing TorchBackend in DeepSpeed with backend nccl +[2025-06-10 16:39:55,326] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-10 16:39:55,326] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-10 16:39:55,326] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-10 16:39:55,326] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-10 16:39:55,326] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-10 16:39:55,326] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-10 16:39:55,326] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-10 16:39:55,326] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-10 16:39:55,326] [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')`. +[2025-06-10 16:40:03,685] [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%|████▌ | 5414/11952 [1:23:21<10:50:16, 5.97s/it] {'loss': 0.4675, 'learning_rate': 1.199589958827114e-05, 'epoch': 0.45} + 45%|████▌ | 5414/11952 [1:23:21<10:50:16, 5.97s/it] 45%|████▌ | 5415/11952 [1:23:27<10:44:40, 5.92s/it] {'loss': 0.4753, 'learning_rate': 1.1993244134822767e-05, 'epoch': 0.45} + 45%|████▌ | 5415/11952 [1:23:27<10:44:40, 5.92s/it] 45%|████▌ | 5416/11952 [1:23:32<10:40:13, 5.88s/it] {'loss': 0.4726, 'learning_rate': 1.1990588534998834e-05, 'epoch': 0.45} + 45%|████▌ | 5416/11952 [1:23:32<10:40:13, 5.88s/it] 45%|████▌ | 5417/11952 [1:23:38<10:37:09, 5.85s/it] {'loss': 0.4837, 'learning_rate': 1.1987932788994362e-05, 'epoch': 0.45} + 45%|████▌ | 5417/11952 [1:23:38<10:37:09, 5.85s/it] 45%|████▌ | 5418/11952 [1:23:44<10:33:16, 5.82s/it] {'loss': 0.475, 'learning_rate': 1.1985276897004367e-05, 'epoch': 0.45} + 45%|████▌ | 5418/11952 [1:23:44<10:33:16, 5.82s/it] 45%|████▌ | 5419/11952 [1:23:50<10:43:30, 5.91s/it] {'loss': 0.4957, 'learning_rate': 1.1982620859223902e-05, 'epoch': 0.45} + 45%|████▌ | 5419/11952 [1:23:50<10:43:30, 5.91s/it] 45%|████▌ | 5420/11952 [1:23:56<10:40:00, 5.88s/it] {'loss': 0.5041, 'learning_rate': 1.1979964675848004e-05, 'epoch': 0.45} + 45%|████▌ | 5420/11952 [1:23:56<10:40:00, 5.88s/it] 45%|████▌ | 5421/11952 [1:24:01<10:29:05, 5.78s/it] {'loss': 0.4591, 'learning_rate': 1.1977308347071735e-05, 'epoch': 0.45} + 45%|████▌ | 5421/11952 [1:24:01<10:29:05, 5.78s/it] 45%|████▌ | 5422/11952 [1:24:07<10:30:26, 5.79s/it] {'loss': 0.4675, 'learning_rate': 1.1974651873090163e-05, 'epoch': 0.45} + 45%|████▌ | 5422/11952 [1:24:07<10:30:26, 5.79s/it] 45%|████▌ | 5423/11952 [1:24:14<10:49:20, 5.97s/it] {'loss': 0.4879, 'learning_rate': 1.1971995254098374e-05, 'epoch': 0.45} + 45%|████▌ | 5423/11952 [1:24:14<10:49:20, 5.97s/it] 45%|████▌ | 5424/11952 [1:24:19<10:42:06, 5.90s/it] {'loss': 0.464, 'learning_rate': 1.1969338490291455e-05, 'epoch': 0.45} + 45%|████▌ | 5424/11952 [1:24:19<10:42:06, 5.90s/it] 45%|████▌ | 5425/11952 [1:24:25<10:32:32, 5.81s/it] {'loss': 0.4879, 'learning_rate': 1.1966681581864507e-05, 'epoch': 0.45} + 45%|████▌ | 5425/11952 [1:24:25<10:32:32, 5.81s/it] 45%|████▌ | 5426/11952 [1:24:31<10:39:59, 5.88s/it] {'loss': 0.5053, 'learning_rate': 1.1964024529012648e-05, 'epoch': 0.45} + 45%|████▌ | 5426/11952 [1:24:31<10:39:59, 5.88s/it] 45%|████▌ | 5427/11952 [1:24:37<10:30:46, 5.80s/it] {'loss': 0.5042, 'learning_rate': 1.196136733193099e-05, 'epoch': 0.45} + 45%|████▌ | 5427/11952 [1:24:37<10:30:46, 5.80s/it] 45%|████▌ | 5428/11952 [1:24:42<10:26:42, 5.76s/it] {'loss': 0.4944, 'learning_rate': 1.1958709990814677e-05, 'epoch': 0.45} + 45%|████▌ | 5428/11952 [1:24:42<10:26:42, 5.76s/it] 45%|████▌ | 5429/11952 [1:24:48<10:27:47, 5.77s/it] {'loss': 0.4783, 'learning_rate': 1.1956052505858851e-05, 'epoch': 0.45} + 45%|████▌ | 5429/11952 [1:24:48<10:27:47, 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!") + 45%|████▌ | 5430/11952 [1:24:55<10:47:35, 5.96s/it] {'loss': 0.5042, 'learning_rate': 1.1953394877258662e-05, 'epoch': 0.45} + 45%|████▌ | 5430/11952 [1:24:55<10:47:35, 5.96s/it] 45%|████▌ | 5431/11952 [1:25:00<10:39:46, 5.89s/it] {'loss': 0.4801, 'learning_rate': 1.1950737105209278e-05, 'epoch': 0.45} + 45%|████▌ | 5431/11952 [1:25:00<10:39:46, 5.89s/it] 45%|████▌ | 5432/11952 [1:25:06<10:34:59, 5.84s/it] {'loss': 0.502, 'learning_rate': 1.1948079189905872e-05, 'epoch': 0.45} + 45%|████▌ | 5432/11952 [1:25:06<10:34:59, 5.84s/it] 45%|████▌ | 5433/11952 [1:25:12<10:30:21, 5.80s/it] {'loss': 0.4985, 'learning_rate': 1.1945421131543639e-05, 'epoch': 0.45} + 45%|████▌ | 5433/11952 [1:25:12<10:30:21, 5.80s/it] 45%|████▌ | 5434/11952 [1:25:17<10:25:15, 5.76s/it] {'loss': 0.4746, 'learning_rate': 1.1942762930317768e-05, 'epoch': 0.45} + 45%|████▌ | 5434/11952 [1:25:17<10:25:15, 5.76s/it] 45%|████▌ | 5435/11952 [1:25:23<10:24:49, 5.75s/it] {'loss': 0.4948, 'learning_rate': 1.1940104586423465e-05, 'epoch': 0.45} + 45%|████▌ | 5435/11952 [1:25:23<10:24:49, 5.75s/it] 45%|████▌ | 5436/11952 [1:25:29<10:24:34, 5.75s/it] {'loss': 0.4836, 'learning_rate': 1.1937446100055954e-05, 'epoch': 0.45} + 45%|████▌ | 5436/11952 [1:25:29<10:24:34, 5.75s/it] 45%|████▌ | 5437/11952 [1:25:35<10:31:04, 5.81s/it] {'loss': 0.4663, 'learning_rate': 1.1934787471410457e-05, 'epoch': 0.45} + 45%|████▌ | 5437/11952 [1:25:35<10:31:04, 5.81s/it] 45%|████▌ | 5438/11952 [1:25:41<10:49:05, 5.98s/it] {'loss': 0.5137, 'learning_rate': 1.1932128700682216e-05, 'epoch': 0.45} + 45%|████▌ | 5438/11952 [1:25:41<10:49:05, 5.98s/it] 46%|████▌ | 5439/11952 [1:25:47<10:47:42, 5.97s/it] {'loss': 0.4803, 'learning_rate': 1.1929469788066481e-05, 'epoch': 0.46} + 46%|████▌ | 5439/11952 [1:25:47<10:47:42, 5.97s/it] 46%|████▌ | 5440/11952 [1:25:53<10:50:09, 5.99s/it] {'loss': 0.4849, 'learning_rate': 1.1926810733758511e-05, 'epoch': 0.46} + 46%|████▌ | 5440/11952 [1:25:53<10:50:09, 5.99s/it] 46%|████▌ | 5441/11952 [1:25:59<10:42:39, 5.92s/it] {'loss': 0.4916, 'learning_rate': 1.1924151537953574e-05, 'epoch': 0.46} + 46%|████▌ | 5441/11952 [1:25:59<10:42:39, 5.92s/it] 46%|████▌ | 5442/11952 [1:26:05<10:33:53, 5.84s/it] {'loss': 0.4784, 'learning_rate': 1.1921492200846949e-05, 'epoch': 0.46} + 46%|████▌ | 5442/11952 [1:26:05<10:33:53, 5.84s/it] 46%|████▌ | 5443/11952 [1:26:11<10:37:55, 5.88s/it] {'loss': 0.4805, 'learning_rate': 1.191883272263393e-05, 'epoch': 0.46} + 46%|████▌ | 5443/11952 [1:26:11<10:37:55, 5.88s/it] 46%|████▌ | 5444/11952 [1:26:16<10:33:50, 5.84s/it] {'loss': 0.4756, 'learning_rate': 1.1916173103509819e-05, 'epoch': 0.46} + 46%|████▌ | 5444/11952 [1:26:16<10:33:50, 5.84s/it] 46%|████▌ | 5445/11952 [1:26:22<10:40:13, 5.90s/it] {'loss': 0.5125, 'learning_rate': 1.191351334366992e-05, 'epoch': 0.46} + 46%|████▌ | 5445/11952 [1:26:22<10:40:13, 5.90s/it] 46%|████▌ | 5446/11952 [1:26:28<10:32:21, 5.83s/it] {'loss': 0.4804, 'learning_rate': 1.1910853443309566e-05, 'epoch': 0.46} + 46%|████▌ | 5446/11952 [1:26:28<10:32:21, 5.83s/it] 46%|████▌ | 5447/11952 [1:26:34<10:32:17, 5.83s/it] {'loss': 0.4834, 'learning_rate': 1.190819340262408e-05, 'epoch': 0.46} + 46%|████▌ | 5447/11952 [1:26:34<10:32:17, 5.83s/it] 46%|████▌ | 5448/11952 [1:26:40<10:30:53, 5.82s/it] {'loss': 0.4813, 'learning_rate': 1.1905533221808805e-05, 'epoch': 0.46} + 46%|████▌ | 5448/11952 [1:26:40<10:30:53, 5.82s/it] 46%|████▌ | 5449/11952 [1:26:45<10:31:45, 5.83s/it] {'loss': 0.501, 'learning_rate': 1.1902872901059102e-05, 'epoch': 0.46} + 46%|████▌ | 5449/11952 [1:26:45<10:31:45, 5.83s/it]0 76 AutoResumeHook: Checking whether to suspend... +AutoResumeHook: Checking whether to suspend...AutoResumeHook: Checking whether to suspend... + + 46%|████▌ | 5450/11952 [1:26:51<10:32:59, 5.84s/it]5 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +23 AutoResumeHook: Checking whether to suspend...AutoResumeHook: Checking whether to suspend... + +1 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4523, 'learning_rate': 1.1900212440570324e-05, 'epoch': 0.46} + 46%|████▌ | 5450/11952 [1:26:51<10:32:59, 5.84s/it] 46%|████▌ | 5451/11952 [1:26:57<10:26:43, 5.78s/it] {'loss': 0.4583, 'learning_rate': 1.1897551840537848e-05, 'epoch': 0.46} + 46%|████▌ | 5451/11952 [1:26:57<10:26:43, 5.78s/it] 46%|████▌ | 5452/11952 [1:27:03<10:25:31, 5.77s/it] {'loss': 0.4717, 'learning_rate': 1.1894891101157058e-05, 'epoch': 0.46} + 46%|████▌ | 5452/11952 [1:27:03<10:25:31, 5.77s/it] 46%|████▌ | 5453/11952 [1:27:09<10:29:17, 5.81s/it] {'loss': 0.4813, 'learning_rate': 1.1892230222623345e-05, 'epoch': 0.46} + 46%|████▌ | 5453/11952 [1:27:09<10:29:17, 5.81s/it] 46%|████▌ | 5454/11952 [1:27:14<10:27:29, 5.79s/it] {'loss': 0.495, 'learning_rate': 1.1889569205132119e-05, 'epoch': 0.46} + 46%|████▌ | 5454/11952 [1:27:14<10:27:29, 5.79s/it] 46%|████▌ | 5455/11952 [1:27:21<10:41:19, 5.92s/it] {'loss': 0.4842, 'learning_rate': 1.1886908048878785e-05, 'epoch': 0.46} + 46%|████▌ | 5455/11952 [1:27:21<10:41:19, 5.92s/it] 46%|████▌ | 5456/11952 [1:27:27<10:41:28, 5.92s/it] {'loss': 0.4882, 'learning_rate': 1.1884246754058775e-05, 'epoch': 0.46} + 46%|████▌ | 5456/11952 [1:27:27<10:41:28, 5.92s/it] 46%|████▌ | 5457/11952 [1:27:32<10:28:56, 5.81s/it] {'loss': 0.4802, 'learning_rate': 1.1881585320867521e-05, 'epoch': 0.46} + 46%|████▌ | 5457/11952 [1:27:32<10:28:56, 5.81s/it] 46%|████▌ | 5458/11952 [1:27:38<10:27:09, 5.79s/it] {'loss': 0.4653, 'learning_rate': 1.1878923749500466e-05, 'epoch': 0.46} + 46%|████▌ | 5458/11952 [1:27:38<10:27:09, 5.79s/it] 46%|████▌ | 5459/11952 [1:27:44<10:26:20, 5.79s/it] {'loss': 0.4861, 'learning_rate': 1.1876262040153064e-05, 'epoch': 0.46} + 46%|████▌ | 5459/11952 [1:27:44<10:26:20, 5.79s/it] 46%|████▌ | 5460/11952 [1:27:49<10:29:33, 5.82s/it] {'loss': 0.4977, 'learning_rate': 1.1873600193020786e-05, 'epoch': 0.46} + 46%|████▌ | 5460/11952 [1:27:49<10:29:33, 5.82s/it] 46%|████▌ | 5461/11952 [1:27:55<10:21:24, 5.74s/it] {'loss': 0.4697, 'learning_rate': 1.18709382082991e-05, 'epoch': 0.46} + 46%|████▌ | 5461/11952 [1:27:55<10:21:24, 5.74s/it] 46%|████▌ | 5462/11952 [1:28:01<10:34:38, 5.87s/it] {'loss': 0.4973, 'learning_rate': 1.1868276086183494e-05, 'epoch': 0.46} + 46%|████▌ | 5462/11952 [1:28:01<10:34:38, 5.87s/it] 46%|████▌ | 5463/11952 [1:28:07<10:42:41, 5.94s/it] {'loss': 0.5125, 'learning_rate': 1.1865613826869463e-05, 'epoch': 0.46} + 46%|████▌ | 5463/11952 [1:28:07<10:42:41, 5.94s/it] 46%|████▌ | 5464/11952 [1:28:13<10:40:29, 5.92s/it] {'loss': 0.4998, 'learning_rate': 1.1862951430552514e-05, 'epoch': 0.46} + 46%|████▌ | 5464/11952 [1:28:13<10:40:29, 5.92s/it] 46%|████▌ | 5465/11952 [1:28:19<10:38:40, 5.91s/it] {'loss': 0.4609, 'learning_rate': 1.1860288897428158e-05, 'epoch': 0.46} + 46%|████▌ | 5465/11952 [1:28:19<10:38:40, 5.91s/it] 46%|████▌ | 5466/11952 [1:28:25<10:47:44, 5.99s/it] {'loss': 0.47, 'learning_rate': 1.1857626227691924e-05, 'epoch': 0.46} + 46%|████▌ | 5466/11952 [1:28:25<10:47:44, 5.99s/it] 46%|████▌ | 5467/11952 [1:28:31<10:44:48, 5.97s/it] {'loss': 0.4728, 'learning_rate': 1.1854963421539348e-05, 'epoch': 0.46} + 46%|████▌ | 5467/11952 [1:28:31<10:44:48, 5.97s/it] 46%|████▌ | 5468/11952 [1:28:37<10:44:34, 5.96s/it] {'loss': 0.4885, 'learning_rate': 1.185230047916597e-05, 'epoch': 0.46} + 46%|████▌ | 5468/11952 [1:28:37<10:44:34, 5.96s/it] 46%|████▌ | 5469/11952 [1:28:43<10:37:30, 5.90s/it] {'loss': 0.49, 'learning_rate': 1.1849637400767351e-05, 'epoch': 0.46} + 46%|████▌ | 5469/11952 [1:28:43<10:37:30, 5.90s/it] 46%|████▌ | 5470/11952 [1:28:49<10:34:00, 5.87s/it] {'loss': 0.5007, 'learning_rate': 1.1846974186539055e-05, 'epoch': 0.46} + 46%|████▌ | 5470/11952 [1:28:49<10:34:00, 5.87s/it] 46%|████▌ | 5471/11952 [1:28:54<10:29:06, 5.82s/it] {'loss': 0.4694, 'learning_rate': 1.1844310836676658e-05, 'epoch': 0.46} + 46%|████▌ | 5471/11952 [1:28:54<10:29:06, 5.82s/it] 46%|████▌ | 5472/11952 [1:29:00<10:34:19, 5.87s/it] {'loss': 0.4736, 'learning_rate': 1.184164735137574e-05, 'epoch': 0.46} + 46%|████▌ | 5472/11952 [1:29:00<10:34:19, 5.87s/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%|████▌ | 5473/11952 [1:29:06<10:35:58, 5.89s/it] {'loss': 0.5052, 'learning_rate': 1.1838983730831904e-05, 'epoch': 0.46} + 46%|████▌ | 5473/11952 [1:29:06<10:35:58, 5.89s/it] 46%|████▌ | 5474/11952 [1:29:12<10:32:01, 5.85s/it] {'loss': 0.4826, 'learning_rate': 1.1836319975240751e-05, 'epoch': 0.46} + 46%|████▌ | 5474/11952 [1:29:12<10:32:01, 5.85s/it] 46%|████▌ | 5475/11952 [1:29:18<10:34:49, 5.88s/it] {'loss': 0.4675, 'learning_rate': 1.1833656084797898e-05, 'epoch': 0.46} + 46%|████▌ | 5475/11952 [1:29:18<10:34:49, 5.88s/it] 46%|████▌ | 5476/11952 [1:29:24<10:42:17, 5.95s/it] {'loss': 0.4842, 'learning_rate': 1.1830992059698967e-05, 'epoch': 0.46} + 46%|████▌ | 5476/11952 [1:29:24<10:42:17, 5.95s/it] 46%|████▌ | 5477/11952 [1:29:30<10:33:25, 5.87s/it] {'loss': 0.4937, 'learning_rate': 1.1828327900139596e-05, 'epoch': 0.46} + 46%|████▌ | 5477/11952 [1:29:30<10:33:25, 5.87s/it] 46%|████▌ | 5478/11952 [1:29:36<10:28:44, 5.83s/it] {'loss': 0.4691, 'learning_rate': 1.1825663606315425e-05, 'epoch': 0.46} + 46%|████▌ | 5478/11952 [1:29:36<10:28:44, 5.83s/it] 46%|████▌ | 5479/11952 [1:29:41<10:30:11, 5.84s/it] {'loss': 0.4715, 'learning_rate': 1.1822999178422114e-05, 'epoch': 0.46} + 46%|████▌ | 5479/11952 [1:29:41<10:30:11, 5.84s/it] 46%|████▌ | 5480/11952 [1:29:48<10:41:32, 5.95s/it] {'loss': 0.4987, 'learning_rate': 1.182033461665533e-05, 'epoch': 0.46} + 46%|████▌ | 5480/11952 [1:29:48<10:41:32, 5.95s/it] 46%|████▌ | 5481/11952 [1:29:54<10:49:01, 6.02s/it] {'loss': 0.4855, 'learning_rate': 1.181766992121074e-05, 'epoch': 0.46} + 46%|████▌ | 5481/11952 [1:29:54<10:49:01, 6.02s/it] 46%|████▌ | 5482/11952 [1:30:00<10:40:12, 5.94s/it] {'loss': 0.4915, 'learning_rate': 1.1815005092284033e-05, 'epoch': 0.46} + 46%|████▌ | 5482/11952 [1:30:00<10:40:12, 5.94s/it] 46%|████▌ | 5483/11952 [1:30:05<10:35:39, 5.90s/it] {'loss': 0.469, 'learning_rate': 1.18123401300709e-05, 'epoch': 0.46} + 46%|████▌ | 5483/11952 [1:30:05<10:35:39, 5.90s/it] 46%|████▌ | 5484/11952 [1:30:11<10:34:55, 5.89s/it] {'loss': 0.4964, 'learning_rate': 1.1809675034767043e-05, 'epoch': 0.46} + 46%|████▌ | 5484/11952 [1:30:11<10:34:55, 5.89s/it] 46%|████▌ | 5485/11952 [1:30:17<10:41:31, 5.95s/it] {'loss': 0.4829, 'learning_rate': 1.1807009806568181e-05, 'epoch': 0.46} + 46%|████▌ | 5485/11952 [1:30:17<10:41:31, 5.95s/it] 46%|████▌ | 5486/11952 [1:30:23<10:34:31, 5.89s/it] {'loss': 0.4707, 'learning_rate': 1.1804344445670034e-05, 'epoch': 0.46} + 46%|████▌ | 5486/11952 [1:30:23<10:34:31, 5.89s/it] 46%|████▌ | 5487/11952 [1:30:29<10:33:12, 5.88s/it] {'loss': 0.4788, 'learning_rate': 1.1801678952268338e-05, 'epoch': 0.46} + 46%|████▌ | 5487/11952 [1:30:29<10:33:12, 5.88s/it] 46%|████▌ | 5488/11952 [1:30:35<10:35:34, 5.90s/it] {'loss': 0.4759, 'learning_rate': 1.179901332655883e-05, 'epoch': 0.46} + 46%|████▌ | 5488/11952 [1:30:35<10:35:34, 5.90s/it] 46%|████▌ | 5489/11952 [1:30:41<10:39:18, 5.94s/it] {'loss': 0.4847, 'learning_rate': 1.1796347568737268e-05, 'epoch': 0.46} + 46%|████▌ | 5489/11952 [1:30:41<10:39:18, 5.94s/it] 46%|████▌ | 5490/11952 [1:30:47<10:31:06, 5.86s/it] {'loss': 0.4786, 'learning_rate': 1.1793681678999412e-05, 'epoch': 0.46} + 46%|████▌ | 5490/11952 [1:30:47<10:31:06, 5.86s/it] 46%|████▌ | 5491/11952 [1:30:52<10:32:04, 5.87s/it] {'loss': 0.4953, 'learning_rate': 1.1791015657541037e-05, 'epoch': 0.46} + 46%|████▌ | 5491/11952 [1:30:52<10:32:04, 5.87s/it] 46%|████▌ | 5492/11952 [1:30:58<10:31:44, 5.87s/it] {'loss': 0.4832, 'learning_rate': 1.1788349504557917e-05, 'epoch': 0.46} + 46%|████▌ | 5492/11952 [1:30:58<10:31:44, 5.87s/it] 46%|████▌ | 5493/11952 [1:31:04<10:34:26, 5.89s/it] {'loss': 0.4776, 'learning_rate': 1.1785683220245849e-05, 'epoch': 0.46} + 46%|████▌ | 5493/11952 [1:31:04<10:34:26, 5.89s/it] 46%|████▌ | 5494/11952 [1:31:10<10:35:35, 5.91s/it] {'loss': 0.4789, 'learning_rate': 1.1783016804800631e-05, 'epoch': 0.46} + 46%|████▌ | 5494/11952 [1:31:10<10:35:35, 5.91s/it] 46%|████▌ | 5495/11952 [1:31:16<10:31:09, 5.86s/it] {'loss': 0.4819, 'learning_rate': 1.1780350258418078e-05, 'epoch': 0.46} + 46%|████▌ | 5495/11952 [1:31:16<10:31:09, 5.86s/it] 46%|████▌ | 5496/11952 [1:31:22<10:28:37, 5.84s/it] {'loss': 0.4795, 'learning_rate': 1.1777683581294003e-05, 'epoch': 0.46} + 46%|████▌ | 5496/11952 [1:31:22<10:28:37, 5.84s/it] 46%|████▌ | 5497/11952 [1:31:28<10:37:01, 5.92s/it] {'loss': 0.4736, 'learning_rate': 1.1775016773624246e-05, 'epoch': 0.46} + 46%|████▌ | 5497/11952 [1:31:28<10:37:01, 5.92s/it] 46%|████▌ | 5498/11952 [1:31:34<10:35:51, 5.91s/it] {'loss': 0.5113, 'learning_rate': 1.1772349835604638e-05, 'epoch': 0.46} + 46%|████▌ | 5498/11952 [1:31:34<10:35:51, 5.91s/it] 46%|████▌ | 5499/11952 [1:31:40<10:30:44, 5.86s/it] {'loss': 0.4702, 'learning_rate': 1.1769682767431026e-05, 'epoch': 0.46} + 46%|████▌ | 5499/11952 [1:31:40<10:30:44, 5.86s/it]07 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... +16 AutoResumeHook: Checking whether to suspend...AutoResumeHook: Checking whether to suspend... + + 46%|████▌ | 5500/11952 [1:31:46<10:49:01, 6.04s/it]2 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4802, 'learning_rate': 1.1767015569299274e-05, 'epoch': 0.46} + 46%|████▌ | 5500/11952 [1:31:46<10:49:01, 6.04s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-5500/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-5500/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/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( + 46%|████▌ | 5501/11952 [1:32:15<22:57:20, 12.81s/it] {'loss': 0.4804, 'learning_rate': 1.1764348241405249e-05, 'epoch': 0.46} + 46%|████▌ | 5501/11952 [1:32:15<22:57:20, 12.81s/it] 46%|████▌ | 5502/11952 [1:32:20<19:06:24, 10.66s/it] {'loss': 0.4852, 'learning_rate': 1.1761680783944829e-05, 'epoch': 0.46} + 46%|████▌ | 5502/11952 [1:32:20<19:06:24, 10.66s/it] 46%|████▌ | 5503/11952 [1:32:26<16:38:06, 9.29s/it] {'loss': 0.4836, 'learning_rate': 1.1759013197113895e-05, 'epoch': 0.46} + 46%|████▌ | 5503/11952 [1:32:26<16:38:06, 9.29s/it] 46%|████▌ | 5504/11952 [1:32:32<14:42:18, 8.21s/it] {'loss': 0.4939, 'learning_rate': 1.175634548110835e-05, 'epoch': 0.46} + 46%|████▌ | 5504/11952 [1:32:32<14:42:18, 8.21s/it] 46%|████▌ | 5505/11952 [1:32:38<13:27:07, 7.51s/it] {'loss': 0.5088, 'learning_rate': 1.1753677636124101e-05, 'epoch': 0.46} + 46%|████▌ | 5505/11952 [1:32:38<13:27:07, 7.51s/it] 46%|████▌ | 5506/11952 [1:32:44<12:41:18, 7.09s/it] {'loss': 0.471, 'learning_rate': 1.1751009662357059e-05, 'epoch': 0.46} + 46%|████▌ | 5506/11952 [1:32:44<12:41:18, 7.09s/it] 46%|████▌ | 5507/11952 [1:32:50<12:15:35, 6.85s/it] {'loss': 0.489, 'learning_rate': 1.1748341560003149e-05, 'epoch': 0.46} + 46%|████▌ | 5507/11952 [1:32:50<12:15:35, 6.85s/it] 46%|████▌ | 5508/11952 [1:32:56<11:38:52, 6.51s/it] {'loss': 0.4822, 'learning_rate': 1.174567332925831e-05, 'epoch': 0.46} + 46%|████▌ | 5508/11952 [1:32:56<11:38:52, 6.51s/it] 46%|████▌ | 5509/11952 [1:33:02<11:10:33, 6.24s/it] {'loss': 0.4794, 'learning_rate': 1.174300497031848e-05, 'epoch': 0.46} + 46%|████▌ | 5509/11952 [1:33:02<11:10:33, 6.24s/it] 46%|████▌ | 5510/11952 [1:33:07<10:52:28, 6.08s/it] {'loss': 0.4821, 'learning_rate': 1.1740336483379613e-05, 'epoch': 0.46} + 46%|████▌ | 5510/11952 [1:33:07<10:52:28, 6.08s/it] 46%|████▌ | 5511/11952 [1:33:13<10:39:48, 5.96s/it] {'loss': 0.4755, 'learning_rate': 1.1737667868637674e-05, 'epoch': 0.46} + 46%|████▌ | 5511/11952 [1:33:13<10:39:48, 5.96s/it] 46%|████▌ | 5512/11952 [1:33:19<10:32:18, 5.89s/it] {'loss': 0.4849, 'learning_rate': 1.1734999126288637e-05, 'epoch': 0.46} + 46%|████▌ | 5512/11952 [1:33:19<10:32:18, 5.89s/it] 46%|████▌ | 5513/11952 [1:33:25<10:39:48, 5.96s/it] {'loss': 0.4922, 'learning_rate': 1.1732330256528477e-05, 'epoch': 0.46} + 46%|████▌ | 5513/11952 [1:33:25<10:39:48, 5.96s/it] 46%|████▌ | 5514/11952 [1:33:30<10:28:55, 5.86s/it] {'loss': 0.4849, 'learning_rate': 1.1729661259553193e-05, 'epoch': 0.46} + 46%|████▌ | 5514/11952 [1:33:30<10:28:55, 5.86s/it] 46%|████▌ | 5515/11952 [1:33:36<10:32:03, 5.89s/it] {'loss': 0.4955, 'learning_rate': 1.1726992135558776e-05, 'epoch': 0.46} + 46%|████▌ | 5515/11952 [1:33:36<10:32:03, 5.89s/it] 46%|████▌ | 5516/11952 [1:33:42<10:28:41, 5.86s/it] {'loss': 0.4834, 'learning_rate': 1.1724322884741242e-05, 'epoch': 0.46} + 46%|████▌ | 5516/11952 [1:33:42<10:28:41, 5.86s/it] 46%|████▌ | 5517/11952 [1:33:48<10:22:34, 5.80s/it] {'loss': 0.5012, 'learning_rate': 1.1721653507296604e-05, 'epoch': 0.46} + 46%|████▌ | 5517/11952 [1:33:48<10:22:34, 5.80s/it] 46%|████▌ | 5518/11952 [1:33:54<10:21:52, 5.80s/it] {'loss': 0.4802, 'learning_rate': 1.1718984003420899e-05, 'epoch': 0.46} + 46%|████▌ | 5518/11952 [1:33:54<10:21:52, 5.80s/it] 46%|████▌ | 5519/11952 [1:33:59<10:17:23, 5.76s/it] {'loss': 0.4789, 'learning_rate': 1.1716314373310154e-05, 'epoch': 0.46} + 46%|████▌ | 5519/11952 [1:33:59<10:17:23, 5.76s/it] 46%|████▌ | 5520/11952 [1:34:06<10:30:08, 5.88s/it] {'loss': 0.4883, 'learning_rate': 1.171364461716042e-05, 'epoch': 0.46} + 46%|████▌ | 5520/11952 [1:34:06<10:30:08, 5.88s/it] 46%|████▌ | 5521/11952 [1:34:11<10:31:17, 5.89s/it] {'loss': 0.4702, 'learning_rate': 1.1710974735167755e-05, 'epoch': 0.46} + 46%|████▌ | 5521/11952 [1:34:11<10:31:17, 5.89s/it] 46%|████▌ | 5522/11952 [1:34:17<10:21:01, 5.79s/it] {'loss': 0.4768, 'learning_rate': 1.1708304727528223e-05, 'epoch': 0.46} + 46%|████▌ | 5522/11952 [1:34:17<10:21:01, 5.79s/it] 46%|████▌ | 5523/11952 [1:34:23<10:20:01, 5.79s/it] {'loss': 0.4884, 'learning_rate': 1.1705634594437893e-05, 'epoch': 0.46} + 46%|████▌ | 5523/11952 [1:34:23<10:20:01, 5.79s/it] 46%|████▌ | 5524/11952 [1:34:28<10:17:06, 5.76s/it] {'loss': 0.4935, 'learning_rate': 1.1702964336092857e-05, 'epoch': 0.46} + 46%|████▌ | 5524/11952 [1:34:28<10:17:06, 5.76s/it] 46%|████▌ | 5525/11952 [1:34:35<10:29:50, 5.88s/it] {'loss': 0.4804, 'learning_rate': 1.17002939526892e-05, 'epoch': 0.46} + 46%|████▌ | 5525/11952 [1:34:35<10:29:50, 5.88s/it] 46%|████▌ | 5526/11952 [1:34:40<10:27:52, 5.86s/it] {'loss': 0.4896, 'learning_rate': 1.169762344442303e-05, 'epoch': 0.46} + 46%|████▌ | 5526/11952 [1:34:40<10:27:52, 5.86s/it] 46%|████▌ | 5527/11952 [1:34:46<10:26:49, 5.85s/it] {'loss': 0.4846, 'learning_rate': 1.1694952811490451e-05, 'epoch': 0.46} + 46%|████▌ | 5527/11952 [1:34:46<10:26:49, 5.85s/it] 46%|████▋ | 5528/11952 [1:34:52<10:24:57, 5.84s/it] {'loss': 0.4812, 'learning_rate': 1.1692282054087594e-05, 'epoch': 0.46} + 46%|████▋ | 5528/11952 [1:34:52<10:24:57, 5.84s/it] 46%|████▋ | 5529/11952 [1:34:58<10:26:51, 5.86s/it] {'loss': 0.5226, 'learning_rate': 1.1689611172410577e-05, 'epoch': 0.46} + 46%|████▋ | 5529/11952 [1:34:58<10:26:51, 5.86s/it] 46%|████▋ | 5530/11952 [1:35:04<10:18:04, 5.77s/it] {'loss': 0.4731, 'learning_rate': 1.1686940166655543e-05, 'epoch': 0.46} + 46%|████▋ | 5530/11952 [1:35:04<10:18:04, 5.77s/it] 46%|████▋ | 5531/11952 [1:35:09<10:23:05, 5.82s/it] {'loss': 0.475, 'learning_rate': 1.1684269037018641e-05, 'epoch': 0.46} + 46%|████▋ | 5531/11952 [1:35:09<10:23:05, 5.82s/it] 46%|████▋ | 5532/11952 [1:35:16<10:34:28, 5.93s/it] {'loss': 0.5193, 'learning_rate': 1.1681597783696027e-05, 'epoch': 0.46} + 46%|████▋ | 5532/11952 [1:35:16<10:34:28, 5.93s/it] 46%|████▋ | 5533/11952 [1:35:22<10:33:52, 5.92s/it] {'loss': 0.4724, 'learning_rate': 1.1678926406883866e-05, 'epoch': 0.46} + 46%|████▋ | 5533/11952 [1:35:22<10:33:52, 5.92s/it] 46%|████▋ | 5534/11952 [1:35:28<10:34:25, 5.93s/it] {'loss': 0.4698, 'learning_rate': 1.1676254906778331e-05, 'epoch': 0.46} + 46%|████▋ | 5534/11952 [1:35:28<10:34:25, 5.93s/it] 46%|████▋ | 5535/11952 [1:35:33<10:31:46, 5.91s/it] {'loss': 0.4757, 'learning_rate': 1.1673583283575607e-05, 'epoch': 0.46} + 46%|████▋ | 5535/11952 [1:35:33<10:31:46, 5.91s/it] 46%|████▋ | 5536/11952 [1:35:39<10:34:03, 5.93s/it] {'loss': 0.48, 'learning_rate': 1.1670911537471889e-05, 'epoch': 0.46} + 46%|████▋ | 5536/11952 [1:35:39<10:34:03, 5.93s/it] 46%|████▋ | 5537/11952 [1:35:45<10:32:04, 5.91s/it] {'loss': 0.4737, 'learning_rate': 1.1668239668663377e-05, 'epoch': 0.46} + 46%|████▋ | 5537/11952 [1:35:45<10:32:04, 5.91s/it] 46%|████▋ | 5538/11952 [1:35:51<10:23:48, 5.84s/it] {'loss': 0.4547, 'learning_rate': 1.1665567677346285e-05, 'epoch': 0.46} + 46%|████▋ | 5538/11952 [1:35:51<10:23:48, 5.84s/it] 46%|████▋ | 5539/11952 [1:35:57<10:29:17, 5.89s/it] {'loss': 0.4934, 'learning_rate': 1.166289556371683e-05, 'epoch': 0.46} + 46%|████▋ | 5539/11952 [1:35:57<10:29:17, 5.89s/it] 46%|████▋ | 5540/11952 [1:36:03<10:34:55, 5.94s/it] {'loss': 0.4754, 'learning_rate': 1.1660223327971239e-05, 'epoch': 0.46} + 46%|████▋ | 5540/11952 [1:36:03<10:34:55, 5.94s/it] 46%|████▋ | 5541/11952 [1:36:09<10:27:09, 5.87s/it] {'loss': 0.473, 'learning_rate': 1.1657550970305752e-05, 'epoch': 0.46} + 46%|████▋ | 5541/11952 [1:36:09<10:27:09, 5.87s/it] 46%|████▋ | 5542/11952 [1:36:14<10:22:58, 5.83s/it] {'loss': 0.4748, 'learning_rate': 1.1654878490916617e-05, 'epoch': 0.46} + 46%|████▋ | 5542/11952 [1:36:14<10:22:58, 5.83s/it] 46%|████▋ | 5543/11952 [1:36:20<10:24:02, 5.84s/it] {'loss': 0.486, 'learning_rate': 1.165220589000009e-05, 'epoch': 0.46} + 46%|████▋ | 5543/11952 [1:36:20<10:24:02, 5.84s/it] 46%|████▋ | 5544/11952 [1:36:26<10:17:21, 5.78s/it] {'loss': 0.4595, 'learning_rate': 1.1649533167752434e-05, 'epoch': 0.46} + 46%|████▋ | 5544/11952 [1:36:26<10:17:21, 5.78s/it] 46%|████▋ | 5545/11952 [1:36:32<10:21:39, 5.82s/it] {'loss': 0.4842, 'learning_rate': 1.164686032436992e-05, 'epoch': 0.46} + 46%|████▋ | 5545/11952 [1:36:32<10:21:39, 5.82s/it]Token indices sequence length is longer than the specified maximum sequence length for this model (4399 > 4096). Running this sequence through the model will result in indexing errors + 46%|████▋ | 5546/11952 [1:36:38<10:22:46, 5.83s/it] {'loss': 0.4897, 'learning_rate': 1.1644187360048838e-05, 'epoch': 0.46} + 46%|████▋ | 5546/11952 [1:36:38<10:22:46, 5.83s/it] 46%|████▋ | 5547/11952 [1:36:43<10:20:35, 5.81s/it] {'loss': 0.4752, 'learning_rate': 1.164151427498547e-05, 'epoch': 0.46} + 46%|████▋ | 5547/11952 [1:36:43<10:20:35, 5.81s/it] 46%|████▋ | 5548/11952 [1:36:49<10:13:50, 5.75s/it] {'loss': 0.4937, 'learning_rate': 1.1638841069376125e-05, 'epoch': 0.46} + 46%|████▋ | 5548/11952 [1:36:49<10:13:50, 5.75s/it] 46%|████▋ | 5549/11952 [1:36:55<10:15:49, 5.77s/it] {'loss': 0.4841, 'learning_rate': 1.1636167743417111e-05, 'epoch': 0.46} + 46%|████▋ | 5549/11952 [1:36:55<10:15:49, 5.77s/it]6 AutoResumeHook: Checking whether to suspend... +0 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... + 46%|████▋ | 5550/11952 [1:37:01<10:14:29, 5.76s/it]5 AutoResumeHook: Checking whether to suspend... +24 AutoResumeHook: Checking whether to suspend... +AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4826, 'learning_rate': 1.1633494297304738e-05, 'epoch': 0.46} + 46%|████▋ | 5550/11952 [1:37:01<10:14:29, 5.76s/it] 46%|████▋ | 5551/11952 [1:37:07<10:21:36, 5.83s/it] {'loss': 0.4777, 'learning_rate': 1.163082073123534e-05, 'epoch': 0.46} + 46%|████▋ | 5551/11952 [1:37:07<10:21:36, 5.83s/it] 46%|████▋ | 5552/11952 [1:37:13<10:33:42, 5.94s/it] {'loss': 0.4806, 'learning_rate': 1.1628147045405248e-05, 'epoch': 0.46} + 46%|████▋ | 5552/11952 [1:37:13<10:33:42, 5.94s/it] 46%|████▋ | 5553/11952 [1:37:19<10:37:26, 5.98s/it] {'loss': 0.4643, 'learning_rate': 1.1625473240010814e-05, 'epoch': 0.46} + 46%|████▋ | 5553/11952 [1:37:19<10:37:26, 5.98s/it] 46%|████▋ | 5554/11952 [1:37:25<10:34:45, 5.95s/it] {'loss': 0.5037, 'learning_rate': 1.1622799315248382e-05, 'epoch': 0.46} + 46%|████▋ | 5554/11952 [1:37:25<10:34:45, 5.95s/it] 46%|████▋ | 5555/11952 [1:37:30<10:26:56, 5.88s/it] {'loss': 0.4654, 'learning_rate': 1.1620125271314322e-05, 'epoch': 0.46} + 46%|████▋ | 5555/11952 [1:37:30<10:26:56, 5.88s/it] 46%|████▋ | 5556/11952 [1:37:36<10:16:16, 5.78s/it] {'loss': 0.4785, 'learning_rate': 1.1617451108404996e-05, 'epoch': 0.46} + 46%|████▋ | 5556/11952 [1:37:36<10:16:16, 5.78s/it] 46%|████▋ | 5557/11952 [1:37:42<10:27:55, 5.89s/it] {'loss': 0.4712, 'learning_rate': 1.1614776826716791e-05, 'epoch': 0.46} + 46%|████▋ | 5557/11952 [1:37:42<10:27:55, 5.89s/it] 47%|████▋ | 5558/11952 [1:37:48<10:23:26, 5.85s/it] {'loss': 0.4797, 'learning_rate': 1.161210242644609e-05, 'epoch': 0.47} + 47%|████▋ | 5558/11952 [1:37:48<10:23:26, 5.85s/it] 47%|████▋ | 5559/11952 [1:37:54<10:27:15, 5.89s/it] {'loss': 0.4672, 'learning_rate': 1.1609427907789294e-05, 'epoch': 0.47} + 47%|████▋ | 5559/11952 [1:37:54<10:27:15, 5.89s/it] 47%|████▋ | 5560/11952 [1:38:00<10:30:52, 5.92s/it] {'loss': 0.5135, 'learning_rate': 1.160675327094281e-05, 'epoch': 0.47} + 47%|████▋ | 5560/11952 [1:38:00<10:30:52, 5.92s/it] 47%|████▋ | 5561/11952 [1:38:06<10:33:17, 5.95s/it] {'loss': 0.5052, 'learning_rate': 1.160407851610304e-05, 'epoch': 0.47} + 47%|████▋ | 5561/11952 [1:38:06<10:33:17, 5.95s/it] 47%|████▋ | 5562/11952 [1:38:12<10:25:32, 5.87s/it] {'loss': 0.4833, 'learning_rate': 1.1601403643466422e-05, 'epoch': 0.47} + 47%|████▋ | 5562/11952 [1:38:12<10:25:32, 5.87s/it]/lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/VILA/llava/model/llava_arch.py:397: UserWarning: Inputs truncated! + warnings.warn("Inputs truncated!") + 47%|████▋ | 5563/11952 [1:38:18<10:33:41, 5.95s/it] {'loss': 0.5247, 'learning_rate': 1.159872865322938e-05, 'epoch': 0.47} + 47%|████▋ | 5563/11952 [1:38:18<10:33:41, 5.95s/it] 47%|████▋ | 5564/11952 [1:38:24<10:34:27, 5.96s/it] {'loss': 0.5032, 'learning_rate': 1.1596053545588355e-05, 'epoch': 0.47} + 47%|████▋ | 5564/11952 [1:38:24<10:34:27, 5.96s/it] 47%|████▋ | 5565/11952 [1:38:30<10:35:50, 5.97s/it] {'loss': 0.4918, 'learning_rate': 1.1593378320739796e-05, 'epoch': 0.47} + 47%|████▋ | 5565/11952 [1:38:30<10:35:50, 5.97s/it] 47%|████▋ | 5566/11952 [1:38:36<10:46:34, 6.07s/it] {'loss': 0.4745, 'learning_rate': 1.1590702978880159e-05, 'epoch': 0.47} + 47%|████▋ | 5566/11952 [1:38:36<10:46:34, 6.07s/it] 47%|████▋ | 5567/11952 [1:38:42<10:37:39, 5.99s/it] {'loss': 0.4933, 'learning_rate': 1.1588027520205915e-05, 'epoch': 0.47} + 47%|████▋ | 5567/11952 [1:38:42<10:37:39, 5.99s/it] 47%|████▋ | 5568/11952 [1:38:48<10:28:39, 5.91s/it] {'loss': 0.4832, 'learning_rate': 1.1585351944913532e-05, 'epoch': 0.47} + 47%|████▋ | 5568/11952 [1:38:48<10:28:39, 5.91s/it] 47%|████▋ | 5569/11952 [1:38:53<10:21:41, 5.84s/it] {'loss': 0.4923, 'learning_rate': 1.1582676253199498e-05, 'epoch': 0.47} + 47%|████▋ | 5569/11952 [1:38:53<10:21:41, 5.84s/it] 47%|████▋ | 5570/11952 [1:38:59<10:26:32, 5.89s/it] {'loss': 0.4878, 'learning_rate': 1.1580000445260305e-05, 'epoch': 0.47} + 47%|████▋ | 5570/11952 [1:38:59<10:26:32, 5.89s/it] 47%|████▋ | 5571/11952 [1:39:05<10:25:13, 5.88s/it] {'loss': 0.4873, 'learning_rate': 1.1577324521292445e-05, 'epoch': 0.47} + 47%|████▋ | 5571/11952 [1:39:05<10:25:13, 5.88s/it] 47%|████▋ | 5572/11952 [1:39:11<10:28:58, 5.92s/it] {'loss': 0.4808, 'learning_rate': 1.1574648481492434e-05, 'epoch': 0.47} + 47%|████▋ | 5572/11952 [1:39:11<10:28:58, 5.92s/it] 47%|████▋ | 5573/11952 [1:39:17<10:36:13, 5.98s/it] {'loss': 0.4868, 'learning_rate': 1.1571972326056794e-05, 'epoch': 0.47} + 47%|████▋ | 5573/11952 [1:39:17<10:36:13, 5.98s/it] 47%|████▋ | 5574/11952 [1:39:23<10:30:29, 5.93s/it] {'loss': 0.49, 'learning_rate': 1.156929605518204e-05, 'epoch': 0.47} + 47%|████▋ | 5574/11952 [1:39:23<10:30:29, 5.93s/it] 47%|████▋ | 5575/11952 [1:39:29<10:29:38, 5.92s/it] {'loss': 0.468, 'learning_rate': 1.1566619669064709e-05, 'epoch': 0.47} + 47%|████▋ | 5575/11952 [1:39:29<10:29:38, 5.92s/it] 47%|████▋ | 5576/11952 [1:39:35<10:20:32, 5.84s/it] {'loss': 0.4702, 'learning_rate': 1.1563943167901348e-05, 'epoch': 0.47} + 47%|████▋ | 5576/11952 [1:39:35<10:20:32, 5.84s/it] 47%|████▋ | 5577/11952 [1:39:41<10:23:04, 5.86s/it] {'loss': 0.4777, 'learning_rate': 1.1561266551888505e-05, 'epoch': 0.47} + 47%|████▋ | 5577/11952 [1:39:41<10:23:04, 5.86s/it] 47%|████▋ | 5578/11952 [1:39:47<10:27:10, 5.90s/it] {'loss': 0.4819, 'learning_rate': 1.1558589821222742e-05, 'epoch': 0.47} + 47%|████▋ | 5578/11952 [1:39:47<10:27:10, 5.90s/it] 47%|████▋ | 5579/11952 [1:39:53<10:43:41, 6.06s/it] {'loss': 0.4927, 'learning_rate': 1.1555912976100623e-05, 'epoch': 0.47} + 47%|████▋ | 5579/11952 [1:39:53<10:43:41, 6.06s/it] 47%|████▋ | 5580/11952 [1:39:59<10:49:41, 6.12s/it] {'loss': 0.4894, 'learning_rate': 1.155323601671873e-05, 'epoch': 0.47} + 47%|████▋ | 5580/11952 [1:39:59<10:49:41, 6.12s/it] 47%|████▋ | 5581/11952 [1:40:05<10:40:15, 6.03s/it] {'loss': 0.4895, 'learning_rate': 1.155055894327364e-05, 'epoch': 0.47} + 47%|████▋ | 5581/11952 [1:40:05<10:40:15, 6.03s/it] 47%|████▋ | 5582/11952 [1:40:11<10:29:32, 5.93s/it] {'loss': 0.4753, 'learning_rate': 1.1547881755961952e-05, 'epoch': 0.47} + 47%|████▋ | 5582/11952 [1:40:11<10:29:32, 5.93s/it] 47%|████▋ | 5583/11952 [1:40:17<10:31:16, 5.95s/it] {'loss': 0.483, 'learning_rate': 1.1545204454980268e-05, 'epoch': 0.47} + 47%|████▋ | 5583/11952 [1:40:17<10:31:16, 5.95s/it] 47%|████▋ | 5584/11952 [1:40:23<10:33:54, 5.97s/it] {'loss': 0.4889, 'learning_rate': 1.1542527040525192e-05, 'epoch': 0.47} + 47%|████▋ | 5584/11952 [1:40:23<10:33:54, 5.97s/it] 47%|████▋ | 5585/11952 [1:40:28<10:25:02, 5.89s/it] {'loss': 0.4702, 'learning_rate': 1.1539849512793348e-05, 'epoch': 0.47} + 47%|████▋ | 5585/11952 [1:40:28<10:25:02, 5.89s/it] 47%|████▋ | 5586/11952 [1:40:34<10:24:05, 5.88s/it] {'loss': 0.4892, 'learning_rate': 1.1537171871981363e-05, 'epoch': 0.47} + 47%|████▋ | 5586/11952 [1:40:34<10:24:05, 5.88s/it] 47%|████▋ | 5587/11952 [1:40:40<10:21:11, 5.86s/it] {'loss': 0.4854, 'learning_rate': 1.1534494118285865e-05, 'epoch': 0.47} + 47%|████▋ | 5587/11952 [1:40:40<10:21:11, 5.86s/it] 47%|████▋ | 5588/11952 [1:40:46<10:21:11, 5.86s/it] {'loss': 0.4915, 'learning_rate': 1.1531816251903503e-05, 'epoch': 0.47} + 47%|████▋ | 5588/11952 [1:40:46<10:21:11, 5.86s/it] 47%|████▋ | 5589/11952 [1:40:52<10:24:53, 5.89s/it] {'loss': 0.4627, 'learning_rate': 1.1529138273030927e-05, 'epoch': 0.47} + 47%|████▋ | 5589/11952 [1:40:52<10:24:53, 5.89s/it] 47%|████▋ | 5590/11952 [1:40:58<10:25:45, 5.90s/it] {'loss': 0.4904, 'learning_rate': 1.1526460181864799e-05, 'epoch': 0.47} + 47%|████▋ | 5590/11952 [1:40:58<10:25:45, 5.90s/it] 47%|████▋ | 5591/11952 [1:41:04<10:27:11, 5.92s/it] {'loss': 0.5022, 'learning_rate': 1.152378197860178e-05, 'epoch': 0.47} + 47%|████▋ | 5591/11952 [1:41:04<10:27:11, 5.92s/it] 47%|████▋ | 5592/11952 [1:41:10<10:52:14, 6.15s/it] {'loss': 0.4974, 'learning_rate': 1.1521103663438551e-05, 'epoch': 0.47} + 47%|████▋ | 5592/11952 [1:41:11<10:52:14, 6.15s/it] 47%|████▋ | 5593/11952 [1:41:16<10:44:00, 6.08s/it] {'loss': 0.48, 'learning_rate': 1.1518425236571797e-05, 'epoch': 0.47} + 47%|████▋ | 5593/11952 [1:41:16<10:44:00, 6.08s/it] 47%|████▋ | 5594/11952 [1:41:22<10:27:02, 5.92s/it] {'loss': 0.4676, 'learning_rate': 1.1515746698198211e-05, 'epoch': 0.47} + 47%|████▋ | 5594/11952 [1:41:22<10:27:02, 5.92s/it] 47%|████▋ | 5595/11952 [1:41:27<10:15:22, 5.81s/it] {'loss': 0.4756, 'learning_rate': 1.1513068048514489e-05, 'epoch': 0.47} + 47%|████▋ | 5595/11952 [1:41:27<10:15:22, 5.81s/it] 47%|████▋ | 5596/11952 [1:41:34<10:28:35, 5.93s/it] {'loss': 0.4957, 'learning_rate': 1.1510389287717345e-05, 'epoch': 0.47} + 47%|████▋ | 5596/11952 [1:41:34<10:28:35, 5.93s/it] 47%|████▋ | 5597/11952 [1:41:40<10:25:15, 5.90s/it] {'loss': 0.4611, 'learning_rate': 1.150771041600349e-05, 'epoch': 0.47} + 47%|████▋ | 5597/11952 [1:41:40<10:25:15, 5.90s/it] 47%|████▋ | 5598/11952 [1:41:45<10:17:54, 5.83s/it] {'loss': 0.4657, 'learning_rate': 1.1505031433569658e-05, 'epoch': 0.47} + 47%|████▋ | 5598/11952 [1:41:45<10:17:54, 5.83s/it] 47%|████▋ | 5599/11952 [1:41:51<10:16:00, 5.82s/it] {'loss': 0.4936, 'learning_rate': 1.1502352340612576e-05, 'epoch': 0.47} + 47%|████▋ | 5599/11952 [1:41:51<10:16:00, 5.82s/it]7 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... +05 AutoResumeHook: Checking whether to suspend... +AutoResumeHook: Checking whether to suspend... + 47%|████▋ | 5600/11952 [1:41:57<10:24:13, 5.90s/it]3 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4698, 'learning_rate': 1.1499673137328986e-05, 'epoch': 0.47} + 47%|████▋ | 5600/11952 [1:41:57<10:24:13, 5.90s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-5600/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-5600/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/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( + 47%|████▋ | 5601/11952 [1:42:24<21:26:20, 12.15s/it] {'loss': 0.4816, 'learning_rate': 1.1496993823915639e-05, 'epoch': 0.47} + 47%|████▋ | 5601/11952 [1:42:24<21:26:20, 12.15s/it] 47%|████▋ | 5602/11952 [1:42:29<17:59:25, 10.20s/it] {'loss': 0.4927, 'learning_rate': 1.1494314400569288e-05, 'epoch': 0.47} + 47%|████▋ | 5602/11952 [1:42:29<17:59:25, 10.20s/it] 47%|████▋ | 5603/11952 [1:42:35<15:37:14, 8.86s/it] {'loss': 0.4541, 'learning_rate': 1.1491634867486707e-05, 'epoch': 0.47} + 47%|████▋ | 5603/11952 [1:42:35<15:37:14, 8.86s/it] 47%|████▋ | 5604/11952 [1:42:41<14:10:30, 8.04s/it] {'loss': 0.48, 'learning_rate': 1.1488955224864667e-05, 'epoch': 0.47} + 47%|████▋ | 5604/11952 [1:42:41<14:10:30, 8.04s/it] 47%|████▋ | 5605/11952 [1:42:47<13:00:11, 7.38s/it] {'loss': 0.4936, 'learning_rate': 1.1486275472899943e-05, 'epoch': 0.47} + 47%|████▋ | 5605/11952 [1:42:47<13:00:11, 7.38s/it] 47%|████▋ | 5606/11952 [1:42:53<12:14:09, 6.94s/it] {'loss': 0.4853, 'learning_rate': 1.1483595611789336e-05, 'epoch': 0.47} + 47%|████▋ | 5606/11952 [1:42:53<12:14:09, 6.94s/it] 47%|████▋ | 5607/11952 [1:42:59<11:51:42, 6.73s/it] {'loss': 0.4817, 'learning_rate': 1.1480915641729633e-05, 'epoch': 0.47} + 47%|████▋ | 5607/11952 [1:42:59<11:51:42, 6.73s/it] 47%|████▋ | 5608/11952 [1:43:05<11:22:06, 6.45s/it] {'loss': 0.4931, 'learning_rate': 1.147823556291765e-05, 'epoch': 0.47} + 47%|████▋ | 5608/11952 [1:43:05<11:22:06, 6.45s/it] 47%|████▋ | 5609/11952 [1:43:11<10:57:13, 6.22s/it] {'loss': 0.4849, 'learning_rate': 1.1475555375550191e-05, 'epoch': 0.47} + 47%|████▋ | 5609/11952 [1:43:11<10:57:13, 6.22s/it] 47%|████▋ | 5610/11952 [1:43:17<10:42:57, 6.08s/it] {'loss': 0.4649, 'learning_rate': 1.1472875079824087e-05, 'epoch': 0.47} + 47%|████▋ | 5610/11952 [1:43:17<10:42:57, 6.08s/it] 47%|████▋ | 5611/11952 [1:43:22<10:30:37, 5.97s/it] {'loss': 0.4762, 'learning_rate': 1.1470194675936159e-05, 'epoch': 0.47} + 47%|████▋ | 5611/11952 [1:43:22<10:30:37, 5.97s/it] 47%|████▋ | 5612/11952 [1:43:28<10:17:07, 5.84s/it] {'loss': 0.4908, 'learning_rate': 1.1467514164083252e-05, 'epoch': 0.47} + 47%|████▋ | 5612/11952 [1:43:28<10:17:07, 5.84s/it] 47%|████▋ | 5613/11952 [1:43:34<10:19:31, 5.86s/it] {'loss': 0.4826, 'learning_rate': 1.1464833544462203e-05, 'epoch': 0.47} + 47%|████▋ | 5613/11952 [1:43:34<10:19:31, 5.86s/it] 47%|████▋ | 5614/11952 [1:43:40<10:17:26, 5.85s/it] {'loss': 0.4964, 'learning_rate': 1.1462152817269879e-05, 'epoch': 0.47} + 47%|████▋ | 5614/11952 [1:43:40<10:17:26, 5.85s/it] 47%|████▋ | 5615/11952 [1:43:45<10:10:28, 5.78s/it] {'loss': 0.4881, 'learning_rate': 1.145947198270313e-05, 'epoch': 0.47} + 47%|████▋ | 5615/11952 [1:43:45<10:10:28, 5.78s/it] 47%|████▋ | 5616/11952 [1:43:51<10:12:36, 5.80s/it] {'loss': 0.4719, 'learning_rate': 1.1456791040958828e-05, 'epoch': 0.47} + 47%|████▋ | 5616/11952 [1:43:51<10:12:36, 5.80s/it] 47%|████▋ | 5617/11952 [1:43:57<10:14:29, 5.82s/it] {'loss': 0.4977, 'learning_rate': 1.1454109992233851e-05, 'epoch': 0.47} + 47%|████▋ | 5617/11952 [1:43:57<10:14:29, 5.82s/it] 47%|████▋ | 5618/11952 [1:44:03<10:18:59, 5.86s/it] {'loss': 0.4921, 'learning_rate': 1.1451428836725087e-05, 'epoch': 0.47} + 47%|████▋ | 5618/11952 [1:44:03<10:18:59, 5.86s/it] 47%|████▋ | 5619/11952 [1:44:09<10:19:46, 5.87s/it] {'loss': 0.476, 'learning_rate': 1.1448747574629424e-05, 'epoch': 0.47} + 47%|████▋ | 5619/11952 [1:44:09<10:19:46, 5.87s/it] 47%|████▋ | 5620/11952 [1:44:14<10:15:23, 5.83s/it] {'loss': 0.4831, 'learning_rate': 1.1446066206143766e-05, 'epoch': 0.47} + 47%|████▋ | 5620/11952 [1:44:14<10:15:23, 5.83s/it] 47%|████▋ | 5621/11952 [1:44:21<10:26:27, 5.94s/it] {'loss': 0.4824, 'learning_rate': 1.1443384731465021e-05, 'epoch': 0.47} + 47%|████▋ | 5621/11952 [1:44:21<10:26:27, 5.94s/it] 47%|████▋ | 5622/11952 [1:44:26<10:15:45, 5.84s/it] {'loss': 0.4794, 'learning_rate': 1.1440703150790102e-05, 'epoch': 0.47} + 47%|████▋ | 5622/11952 [1:44:26<10:15:45, 5.84s/it] 47%|████▋ | 5623/11952 [1:44:32<10:15:29, 5.83s/it] {'loss': 0.4919, 'learning_rate': 1.1438021464315939e-05, 'epoch': 0.47} + 47%|████▋ | 5623/11952 [1:44:32<10:15:29, 5.83s/it] 47%|████▋ | 5624/11952 [1:44:38<10:12:16, 5.81s/it] {'loss': 0.4893, 'learning_rate': 1.143533967223946e-05, 'epoch': 0.47} + 47%|████▋ | 5624/11952 [1:44:38<10:12:16, 5.81s/it] 47%|████▋ | 5625/11952 [1:44:43<10:07:03, 5.76s/it] {'loss': 0.4674, 'learning_rate': 1.1432657774757607e-05, 'epoch': 0.47} + 47%|████▋ | 5625/11952 [1:44:43<10:07:03, 5.76s/it] 47%|████▋ | 5626/11952 [1:44:49<10:15:06, 5.83s/it] {'loss': 0.4806, 'learning_rate': 1.1429975772067322e-05, 'epoch': 0.47} + 47%|████▋ | 5626/11952 [1:44:49<10:15:06, 5.83s/it] 47%|████▋ | 5627/11952 [1:44:55<10:20:53, 5.89s/it] {'loss': 0.5062, 'learning_rate': 1.1427293664365568e-05, 'epoch': 0.47} + 47%|████▋ | 5627/11952 [1:44:56<10:20:53, 5.89s/it] 47%|████▋ | 5628/11952 [1:45:02<10:27:36, 5.95s/it] {'loss': 0.4882, 'learning_rate': 1.1424611451849301e-05, 'epoch': 0.47} + 47%|████▋ | 5628/11952 [1:45:02<10:27:36, 5.95s/it] 47%|████▋ | 5629/11952 [1:45:07<10:17:18, 5.86s/it] {'loss': 0.4883, 'learning_rate': 1.1421929134715492e-05, 'epoch': 0.47} + 47%|████▋ | 5629/11952 [1:45:07<10:17:18, 5.86s/it] 47%|████▋ | 5630/11952 [1:45:13<10:09:22, 5.78s/it] {'loss': 0.4493, 'learning_rate': 1.1419246713161128e-05, 'epoch': 0.47} + 47%|████▋ | 5630/11952 [1:45:13<10:09:22, 5.78s/it] 47%|████▋ | 5631/11952 [1:45:19<10:18:45, 5.87s/it] {'loss': 0.4925, 'learning_rate': 1.1416564187383185e-05, 'epoch': 0.47} + 47%|████▋ | 5631/11952 [1:45:19<10:18:45, 5.87s/it] 47%|████▋ | 5632/11952 [1:45:25<10:18:00, 5.87s/it] {'loss': 0.4814, 'learning_rate': 1.1413881557578662e-05, 'epoch': 0.47} + 47%|████▋ | 5632/11952 [1:45:25<10:18:00, 5.87s/it] 47%|████▋ | 5633/11952 [1:45:30<10:06:38, 5.76s/it] {'loss': 0.4868, 'learning_rate': 1.1411198823944553e-05, 'epoch': 0.47} + 47%|████▋ | 5633/11952 [1:45:30<10:06:38, 5.76s/it] 47%|████▋ | 5634/11952 [1:45:36<10:04:28, 5.74s/it] {'loss': 0.4744, 'learning_rate': 1.1408515986677877e-05, 'epoch': 0.47} + 47%|████▋ | 5634/11952 [1:45:36<10:04:28, 5.74s/it] 47%|████▋ | 5635/11952 [1:45:42<10:02:10, 5.72s/it] {'loss': 0.4786, 'learning_rate': 1.1405833045975644e-05, 'epoch': 0.47} + 47%|████▋ | 5635/11952 [1:45:42<10:02:10, 5.72s/it] 47%|████▋ | 5636/11952 [1:45:47<10:05:27, 5.75s/it] {'loss': 0.4724, 'learning_rate': 1.140315000203488e-05, 'epoch': 0.47} + 47%|████▋ | 5636/11952 [1:45:47<10:05:27, 5.75s/it] 47%|████▋ | 5637/11952 [1:45:53<10:09:41, 5.79s/it] {'loss': 0.4885, 'learning_rate': 1.1400466855052617e-05, 'epoch': 0.47} + 47%|████▋ | 5637/11952 [1:45:53<10:09:41, 5.79s/it] 47%|████▋ | 5638/11952 [1:45:59<10:12:26, 5.82s/it] {'loss': 0.4876, 'learning_rate': 1.139778360522589e-05, 'epoch': 0.47} + 47%|████▋ | 5638/11952 [1:45:59<10:12:26, 5.82s/it] 47%|████▋ | 5639/11952 [1:46:05<10:06:49, 5.77s/it] {'loss': 0.4921, 'learning_rate': 1.139510025275175e-05, 'epoch': 0.47} + 47%|████▋ | 5639/11952 [1:46:05<10:06:49, 5.77s/it] 47%|████▋ | 5640/11952 [1:46:11<10:07:57, 5.78s/it] {'loss': 0.5004, 'learning_rate': 1.139241679782725e-05, 'epoch': 0.47} + 47%|████▋ | 5640/11952 [1:46:11<10:07:57, 5.78s/it] 47%|████▋ | 5641/11952 [1:46:17<10:10:02, 5.80s/it] {'loss': 0.4859, 'learning_rate': 1.1389733240649454e-05, 'epoch': 0.47} + 47%|████▋ | 5641/11952 [1:46:17<10:10:02, 5.80s/it] 47%|████▋ | 5642/11952 [1:46:22<10:08:32, 5.79s/it] {'loss': 0.4938, 'learning_rate': 1.1387049581415428e-05, 'epoch': 0.47} + 47%|████▋ | 5642/11952 [1:46:22<10:08:32, 5.79s/it] 47%|████▋ | 5643/11952 [1:46:28<10:04:46, 5.75s/it] {'loss': 0.4681, 'learning_rate': 1.138436582032225e-05, 'epoch': 0.47} + 47%|████▋ | 5643/11952 [1:46:28<10:04:46, 5.75s/it] 47%|████▋ | 5644/11952 [1:46:34<10:08:14, 5.79s/it] {'loss': 0.4845, 'learning_rate': 1.1381681957567e-05, 'epoch': 0.47} + 47%|████▋ | 5644/11952 [1:46:34<10:08:14, 5.79s/it] 47%|████▋ | 5645/11952 [1:46:40<10:11:04, 5.81s/it] {'loss': 0.4733, 'learning_rate': 1.1378997993346782e-05, 'epoch': 0.47} + 47%|████▋ | 5645/11952 [1:46:40<10:11:04, 5.81s/it] 47%|████▋ | 5646/11952 [1:46:46<10:10:34, 5.81s/it] {'loss': 0.4937, 'learning_rate': 1.137631392785868e-05, 'epoch': 0.47} + 47%|████▋ | 5646/11952 [1:46:46<10:10:34, 5.81s/it] 47%|████▋ | 5647/11952 [1:46:51<10:04:00, 5.75s/it] {'loss': 0.4775, 'learning_rate': 1.1373629761299811e-05, 'epoch': 0.47} + 47%|████▋ | 5647/11952 [1:46:51<10:04:00, 5.75s/it] 47%|████▋ | 5648/11952 [1:46:57<10:01:14, 5.72s/it] {'loss': 0.471, 'learning_rate': 1.1370945493867284e-05, 'epoch': 0.47} + 47%|████▋ | 5648/11952 [1:46:57<10:01:14, 5.72s/it] 47%|████▋ | 5649/11952 [1:47:02<9:59:42, 5.71s/it] {'loss': 0.4901, 'learning_rate': 1.1368261125758224e-05, 'epoch': 0.47} + 47%|████▋ | 5649/11952 [1:47:02<9:59:42, 5.71s/it]2 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +0 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... + 47%|████▋ | 5650/11952 [1:47:08<9:52:48, 5.64s/it]3 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4707, 'learning_rate': 1.1365576657169754e-05, 'epoch': 0.47} + 47%|████▋ | 5650/11952 [1:47:08<9:52:48, 5.64s/it] 47%|████▋ | 5651/11952 [1:47:14<9:52:58, 5.65s/it] {'loss': 0.4803, 'learning_rate': 1.136289208829902e-05, 'epoch': 0.47} + 47%|████▋ | 5651/11952 [1:47:14<9:52:58, 5.65s/it] 47%|████▋ | 5652/11952 [1:47:20<10:05:44, 5.77s/it] {'loss': 0.4749, 'learning_rate': 1.1360207419343157e-05, 'epoch': 0.47} + 47%|████▋ | 5652/11952 [1:47:20<10:05:44, 5.77s/it] 47%|████▋ | 5653/11952 [1:47:25<10:06:27, 5.78s/it] {'loss': 0.4835, 'learning_rate': 1.1357522650499317e-05, 'epoch': 0.47} + 47%|████▋ | 5653/11952 [1:47:25<10:06:27, 5.78s/it] 47%|████▋ | 5654/11952 [1:47:31<10:14:04, 5.85s/it] {'loss': 0.4921, 'learning_rate': 1.135483778196466e-05, 'epoch': 0.47} + 47%|████▋ | 5654/11952 [1:47:31<10:14:04, 5.85s/it] 47%|████▋ | 5655/11952 [1:47:37<10:19:01, 5.90s/it] {'loss': 0.4825, 'learning_rate': 1.1352152813936354e-05, 'epoch': 0.47} + 47%|████▋ | 5655/11952 [1:47:37<10:19:01, 5.90s/it] 47%|████▋ | 5656/11952 [1:47:43<10:14:29, 5.86s/it] {'loss': 0.4778, 'learning_rate': 1.1349467746611569e-05, 'epoch': 0.47} + 47%|████▋ | 5656/11952 [1:47:43<10:14:29, 5.86s/it] 47%|████▋ | 5657/11952 [1:47:49<10:17:54, 5.89s/it] {'loss': 0.4877, 'learning_rate': 1.1346782580187486e-05, 'epoch': 0.47} + 47%|████▋ | 5657/11952 [1:47:49<10:17:54, 5.89s/it] 47%|████▋ | 5658/11952 [1:47:55<10:22:52, 5.94s/it] {'loss': 0.5045, 'learning_rate': 1.1344097314861292e-05, 'epoch': 0.47} + 47%|████▋ | 5658/11952 [1:47:55<10:22:52, 5.94s/it] 47%|████▋ | 5659/11952 [1:48:01<10:25:23, 5.96s/it] {'loss': 0.4885, 'learning_rate': 1.1341411950830179e-05, 'epoch': 0.47} + 47%|████▋ | 5659/11952 [1:48:01<10:25:23, 5.96s/it] 47%|████▋ | 5660/11952 [1:48:07<10:22:07, 5.93s/it] {'loss': 0.4939, 'learning_rate': 1.1338726488291351e-05, 'epoch': 0.47} + 47%|████▋ | 5660/11952 [1:48:07<10:22:07, 5.93s/it] 47%|████▋ | 5661/11952 [1:48:13<10:17:39, 5.89s/it] {'loss': 0.4826, 'learning_rate': 1.1336040927442023e-05, 'epoch': 0.47} + 47%|████▋ | 5661/11952 [1:48:13<10:17:39, 5.89s/it] 47%|████▋ | 5662/11952 [1:48:19<10:15:05, 5.87s/it] {'loss': 0.4694, 'learning_rate': 1.1333355268479403e-05, 'epoch': 0.47} + 47%|████▋ | 5662/11952 [1:48:19<10:15:05, 5.87s/it] 47%|████▋ | 5663/11952 [1:48:25<10:25:47, 5.97s/it] {'loss': 0.467, 'learning_rate': 1.1330669511600716e-05, 'epoch': 0.47} + 47%|████▋ | 5663/11952 [1:48:25<10:25:47, 5.97s/it] 47%|████▋ | 5664/11952 [1:48:31<10:29:18, 6.00s/it] {'loss': 0.5067, 'learning_rate': 1.1327983657003197e-05, 'epoch': 0.47} + 47%|████▋ | 5664/11952 [1:48:31<10:29:18, 6.00s/it] 47%|████▋ | 5665/11952 [1:48:37<10:30:42, 6.02s/it] {'loss': 0.4779, 'learning_rate': 1.1325297704884081e-05, 'epoch': 0.47} + 47%|████▋ | 5665/11952 [1:48:37<10:30:42, 6.02s/it] 47%|████▋ | 5666/11952 [1:48:43<10:29:27, 6.01s/it] {'loss': 0.4802, 'learning_rate': 1.132261165544062e-05, 'epoch': 0.47} + 47%|████▋ | 5666/11952 [1:48:43<10:29:27, 6.01s/it] 47%|████▋ | 5667/11952 [1:48:49<10:15:36, 5.88s/it] {'loss': 0.4811, 'learning_rate': 1.131992550887005e-05, 'epoch': 0.47} + 47%|████▋ | 5667/11952 [1:48:49<10:15:36, 5.88s/it] 47%|████▋ | 5668/11952 [1:48:55<10:14:53, 5.87s/it] {'loss': 0.5074, 'learning_rate': 1.1317239265369648e-05, 'epoch': 0.47} + 47%|████▋ | 5668/11952 [1:48:55<10:14:53, 5.87s/it] 47%|████▋ | 5669/11952 [1:49:01<10:27:31, 5.99s/it] {'loss': 0.4494, 'learning_rate': 1.131455292513667e-05, 'epoch': 0.47} + 47%|████▋ | 5669/11952 [1:49:01<10:27:31, 5.99s/it] 47%|████▋ | 5670/11952 [1:49:07<10:20:55, 5.93s/it] {'loss': 0.4755, 'learning_rate': 1.1311866488368392e-05, 'epoch': 0.47} + 47%|████▋ | 5670/11952 [1:49:07<10:20:55, 5.93s/it] 47%|████▋ | 5671/11952 [1:49:13<10:21:50, 5.94s/it] {'loss': 0.5055, 'learning_rate': 1.1309179955262097e-05, 'epoch': 0.47} + 47%|████▋ | 5671/11952 [1:49:13<10:21:50, 5.94s/it] 47%|████▋ | 5672/11952 [1:49:18<10:10:52, 5.84s/it] {'loss': 0.4714, 'learning_rate': 1.1306493326015074e-05, 'epoch': 0.47} + 47%|████▋ | 5672/11952 [1:49:18<10:10:52, 5.84s/it] 47%|████▋ | 5673/11952 [1:49:24<10:21:31, 5.94s/it] {'loss': 0.4855, 'learning_rate': 1.1303806600824613e-05, 'epoch': 0.47} + 47%|████▋ | 5673/11952 [1:49:24<10:21:31, 5.94s/it] 47%|████▋ | 5674/11952 [1:49:30<10:15:03, 5.88s/it] {'loss': 0.4815, 'learning_rate': 1.1301119779888015e-05, 'epoch': 0.47} + 47%|████▋ | 5674/11952 [1:49:30<10:15:03, 5.88s/it] 47%|████▋ | 5675/11952 [1:49:36<10:15:51, 5.89s/it] {'loss': 0.4807, 'learning_rate': 1.1298432863402595e-05, 'epoch': 0.47} + 47%|████▋ | 5675/11952 [1:49:36<10:15:51, 5.89s/it] 47%|████▋ | 5676/11952 [1:49:42<10:18:00, 5.91s/it] {'loss': 0.4727, 'learning_rate': 1.1295745851565667e-05, 'epoch': 0.47} + 47%|████▋ | 5676/11952 [1:49:42<10:18:00, 5.91s/it] 47%|████▋ | 5677/11952 [1:49:48<10:20:28, 5.93s/it] {'loss': 0.4793, 'learning_rate': 1.1293058744574552e-05, 'epoch': 0.47} + 47%|████▋ | 5677/11952 [1:49:48<10:20:28, 5.93s/it] 48%|████▊ | 5678/11952 [1:49:54<10:15:44, 5.89s/it] {'loss': 0.4741, 'learning_rate': 1.129037154262658e-05, 'epoch': 0.48} + 48%|████▊ | 5678/11952 [1:49:54<10:15:44, 5.89s/it] 48%|████▊ | 5679/11952 [1:50:00<10:17:10, 5.90s/it] {'loss': 0.4584, 'learning_rate': 1.128768424591909e-05, 'epoch': 0.48} + 48%|████▊ | 5679/11952 [1:50:00<10:17:10, 5.90s/it] 48%|████▊ | 5680/11952 [1:50:06<10:19:01, 5.92s/it] {'loss': 0.4911, 'learning_rate': 1.1284996854649424e-05, 'epoch': 0.48} + 48%|████▊ | 5680/11952 [1:50:06<10:19:01, 5.92s/it] 48%|████▊ | 5681/11952 [1:50:11<10:09:24, 5.83s/it] {'loss': 0.4811, 'learning_rate': 1.1282309369014937e-05, 'epoch': 0.48} + 48%|████▊ | 5681/11952 [1:50:11<10:09:24, 5.83s/it] 48%|████▊ | 5682/11952 [1:50:17<10:09:17, 5.83s/it] {'loss': 0.4769, 'learning_rate': 1.127962178921298e-05, 'epoch': 0.48} + 48%|████▊ | 5682/11952 [1:50:17<10:09:17, 5.83s/it] 48%|████▊ | 5683/11952 [1:50:23<10:14:58, 5.89s/it] {'loss': 0.4743, 'learning_rate': 1.1276934115440924e-05, 'epoch': 0.48} + 48%|████▊ | 5683/11952 [1:50:23<10:14:58, 5.89s/it] 48%|████▊ | 5684/11952 [1:50:29<10:14:08, 5.88s/it] {'loss': 0.48, 'learning_rate': 1.1274246347896136e-05, 'epoch': 0.48} + 48%|████▊ | 5684/11952 [1:50:29<10:14:08, 5.88s/it] 48%|████▊ | 5685/11952 [1:50:35<10:11:07, 5.85s/it] {'loss': 0.4874, 'learning_rate': 1.1271558486775995e-05, 'epoch': 0.48} + 48%|████▊ | 5685/11952 [1:50:35<10:11:07, 5.85s/it] 48%|████▊ | 5686/11952 [1:50:40<10:05:45, 5.80s/it] {'loss': 0.463, 'learning_rate': 1.1268870532277889e-05, 'epoch': 0.48} + 48%|████▊ | 5686/11952 [1:50:40<10:05:45, 5.80s/it] 48%|████▊ | 5687/11952 [1:50:46<9:58:55, 5.74s/it] {'loss': 0.4752, 'learning_rate': 1.1266182484599209e-05, 'epoch': 0.48} + 48%|████▊ | 5687/11952 [1:50:46<9:58:55, 5.74s/it] 48%|████▊ | 5688/11952 [1:50:52<9:54:44, 5.70s/it] {'loss': 0.4682, 'learning_rate': 1.1263494343937354e-05, 'epoch': 0.48} + 48%|████▊ | 5688/11952 [1:50:52<9:54:44, 5.70s/it] 48%|████▊ | 5689/11952 [1:50:57<9:58:39, 5.74s/it] {'loss': 0.4947, 'learning_rate': 1.1260806110489726e-05, 'epoch': 0.48} + 48%|████▊ | 5689/11952 [1:50:57<9:58:39, 5.74s/it] 48%|████▊ | 5690/11952 [1:51:04<10:12:42, 5.87s/it] {'loss': 0.4735, 'learning_rate': 1.1258117784453746e-05, 'epoch': 0.48} + 48%|████▊ | 5690/11952 [1:51:04<10:12:42, 5.87s/it] 48%|████▊ | 5691/11952 [1:51:10<10:15:39, 5.90s/it] {'loss': 0.4578, 'learning_rate': 1.1255429366026826e-05, 'epoch': 0.48} + 48%|████▊ | 5691/11952 [1:51:10<10:15:39, 5.90s/it] 48%|████▊ | 5692/11952 [1:51:15<10:08:34, 5.83s/it] {'loss': 0.4827, 'learning_rate': 1.1252740855406397e-05, 'epoch': 0.48} + 48%|████▊ | 5692/11952 [1:51:15<10:08:34, 5.83s/it] 48%|████▊ | 5693/11952 [1:51:21<10:02:49, 5.78s/it] {'loss': 0.4848, 'learning_rate': 1.1250052252789891e-05, 'epoch': 0.48} + 48%|████▊ | 5693/11952 [1:51:21<10:02:49, 5.78s/it] 48%|████▊ | 5694/11952 [1:51:27<10:24:34, 5.99s/it] {'loss': 0.4687, 'learning_rate': 1.1247363558374745e-05, 'epoch': 0.48} + 48%|████▊ | 5694/11952 [1:51:27<10:24:34, 5.99s/it] 48%|████▊ | 5695/11952 [1:51:33<10:13:02, 5.88s/it] {'loss': 0.473, 'learning_rate': 1.1244674772358406e-05, 'epoch': 0.48} + 48%|████▊ | 5695/11952 [1:51:33<10:13:02, 5.88s/it] 48%|████▊ | 5696/11952 [1:51:39<10:16:21, 5.91s/it] {'loss': 0.4834, 'learning_rate': 1.124198589493833e-05, 'epoch': 0.48} + 48%|████▊ | 5696/11952 [1:51:39<10:16:21, 5.91s/it] 48%|████▊ | 5697/11952 [1:51:45<10:09:00, 5.84s/it] {'loss': 0.4675, 'learning_rate': 1.1239296926311975e-05, 'epoch': 0.48} + 48%|████▊ | 5697/11952 [1:51:45<10:09:00, 5.84s/it] 48%|████▊ | 5698/11952 [1:51:51<10:11:46, 5.87s/it] {'loss': 0.4829, 'learning_rate': 1.123660786667681e-05, 'epoch': 0.48} + 48%|████▊ | 5698/11952 [1:51:51<10:11:46, 5.87s/it] 48%|████▊ | 5699/11952 [1:51:56<10:07:36, 5.83s/it] {'loss': 0.4824, 'learning_rate': 1.1233918716230308e-05, 'epoch': 0.48} + 48%|████▊ | 5699/11952 [1:51:56<10:07:36, 5.83s/it]2 AutoResumeHook: Checking whether to suspend... +07 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... + 48%|████▊ | 5700/11952 [1:52:02<10:11:58, 5.87s/it]6 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... +34 AutoResumeHook: Checking whether to suspend...AutoResumeHook: Checking whether to suspend... + +1 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4713, 'learning_rate': 1.1231229475169945e-05, 'epoch': 0.48} + 48%|████▊ | 5700/11952 [1:52:02<10:11:58, 5.87s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-5700/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-5700/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/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( + 48%|████▊ | 5701/11952 [1:52:32<22:28:23, 12.94s/it] {'loss': 0.4831, 'learning_rate': 1.1228540143693209e-05, 'epoch': 0.48} + 48%|████▊ | 5701/11952 [1:52:32<22:28:23, 12.94s/it] 48%|████▊ | 5702/11952 [1:52:38<18:48:37, 10.83s/it] {'loss': 0.4796, 'learning_rate': 1.12258507219976e-05, 'epoch': 0.48} + 48%|████▊ | 5702/11952 [1:52:38<18:48:37, 10.83s/it] 48%|████▊ | 5703/11952 [1:52:43<16:07:36, 9.29s/it] {'loss': 0.4962, 'learning_rate': 1.122316121028061e-05, 'epoch': 0.48} + 48%|████▊ | 5703/11952 [1:52:43<16:07:36, 9.29s/it] 48%|████▊ | 5704/11952 [1:52:49<14:22:37, 8.28s/it] {'loss': 0.4918, 'learning_rate': 1.1220471608739748e-05, 'epoch': 0.48} + 48%|████▊ | 5704/11952 [1:52:49<14:22:37, 8.28s/it] 48%|████▊ | 5705/11952 [1:52:55<13:05:06, 7.54s/it] {'loss': 0.4789, 'learning_rate': 1.1217781917572524e-05, 'epoch': 0.48} + 48%|████▊ | 5705/11952 [1:52:55<13:05:06, 7.54s/it] 48%|████▊ | 5706/11952 [1:53:01<12:12:45, 7.04s/it] {'loss': 0.5123, 'learning_rate': 1.1215092136976466e-05, 'epoch': 0.48} + 48%|████▊ | 5706/11952 [1:53:01<12:12:45, 7.04s/it] 48%|████▊ | 5707/11952 [1:53:07<11:32:29, 6.65s/it] {'loss': 0.478, 'learning_rate': 1.1212402267149094e-05, 'epoch': 0.48} + 48%|████▊ | 5707/11952 [1:53:07<11:32:29, 6.65s/it] 48%|████▊ | 5708/11952 [1:53:13<11:08:22, 6.42s/it] {'loss': 0.4826, 'learning_rate': 1.1209712308287941e-05, 'epoch': 0.48} + 48%|████▊ | 5708/11952 [1:53:13<11:08:22, 6.42s/it] 48%|████▊ | 5709/11952 [1:53:18<10:51:44, 6.26s/it] {'loss': 0.4965, 'learning_rate': 1.120702226059055e-05, 'epoch': 0.48} + 48%|████▊ | 5709/11952 [1:53:18<10:51:44, 6.26s/it] 48%|████▊ | 5710/11952 [1:53:25<10:45:13, 6.20s/it] {'loss': 0.469, 'learning_rate': 1.1204332124254463e-05, 'epoch': 0.48} + 48%|████▊ | 5710/11952 [1:53:25<10:45:13, 6.20s/it] 48%|████▊ | 5711/11952 [1:53:30<10:30:48, 6.06s/it] {'loss': 0.4617, 'learning_rate': 1.1201641899477231e-05, 'epoch': 0.48} + 48%|████▊ | 5711/11952 [1:53:30<10:30:48, 6.06s/it] 48%|████▊ | 5712/11952 [1:53:36<10:17:55, 5.94s/it] {'loss': 0.4843, 'learning_rate': 1.119895158645642e-05, 'epoch': 0.48} + 48%|████▊ | 5712/11952 [1:53:36<10:17:55, 5.94s/it] 48%|████▊ | 5713/11952 [1:53:42<10:15:28, 5.92s/it] {'loss': 0.4833, 'learning_rate': 1.1196261185389593e-05, 'epoch': 0.48} + 48%|████▊ | 5713/11952 [1:53:42<10:15:28, 5.92s/it] 48%|████▊ | 5714/11952 [1:53:48<10:11:27, 5.88s/it] {'loss': 0.4829, 'learning_rate': 1.1193570696474317e-05, 'epoch': 0.48} + 48%|████▊ | 5714/11952 [1:53:48<10:11:27, 5.88s/it] 48%|████▊ | 5715/11952 [1:53:54<10:16:31, 5.93s/it] {'loss': 0.4845, 'learning_rate': 1.1190880119908175e-05, 'epoch': 0.48} + 48%|████▊ | 5715/11952 [1:53:54<10:16:31, 5.93s/it] 48%|████▊ | 5716/11952 [1:54:00<10:20:57, 5.97s/it] {'loss': 0.4692, 'learning_rate': 1.1188189455888747e-05, 'epoch': 0.48} + 48%|████▊ | 5716/11952 [1:54:00<10:20:57, 5.97s/it] 48%|████▊ | 5717/11952 [1:54:06<10:28:48, 6.05s/it] {'loss': 0.4786, 'learning_rate': 1.1185498704613632e-05, 'epoch': 0.48} + 48%|████▊ | 5717/11952 [1:54:06<10:28:48, 6.05s/it] 48%|████▊ | 5718/11952 [1:54:12<10:17:52, 5.95s/it] {'loss': 0.4714, 'learning_rate': 1.1182807866280419e-05, 'epoch': 0.48} + 48%|████▊ | 5718/11952 [1:54:12<10:17:52, 5.95s/it] 48%|████▊ | 5719/11952 [1:54:17<10:08:45, 5.86s/it] {'loss': 0.4922, 'learning_rate': 1.1180116941086719e-05, 'epoch': 0.48} + 48%|████▊ | 5719/11952 [1:54:17<10:08:45, 5.86s/it] 48%|████▊ | 5720/11952 [1:54:23<10:10:47, 5.88s/it] {'loss': 0.4893, 'learning_rate': 1.1177425929230137e-05, 'epoch': 0.48} + 48%|████▊ | 5720/11952 [1:54:23<10:10:47, 5.88s/it] 48%|████▊ | 5721/11952 [1:54:29<10:05:40, 5.83s/it] {'loss': 0.476, 'learning_rate': 1.117473483090829e-05, 'epoch': 0.48} + 48%|████▊ | 5721/11952 [1:54:29<10:05:40, 5.83s/it] 48%|████▊ | 5722/11952 [1:54:35<10:20:14, 5.97s/it] {'loss': 0.4827, 'learning_rate': 1.1172043646318809e-05, 'epoch': 0.48} + 48%|████▊ | 5722/11952 [1:54:35<10:20:14, 5.97s/it]Token indices sequence length is longer than the specified maximum sequence length for this model (4338 > 4096). Running this sequence through the model will result in indexing errors + 48%|████▊ | 5723/11952 [1:54:41<10:13:59, 5.91s/it] {'loss': 0.4936, 'learning_rate': 1.1169352375659314e-05, 'epoch': 0.48} + 48%|████▊ | 5723/11952 [1:54:41<10:13:59, 5.91s/it] 48%|████▊ | 5724/11952 [1:54:47<10:03:36, 5.82s/it] {'loss': 0.4858, 'learning_rate': 1.1166661019127447e-05, 'epoch': 0.48} + 48%|████▊ | 5724/11952 [1:54:47<10:03:36, 5.82s/it] 48%|████▊ | 5725/11952 [1:54:52<9:59:45, 5.78s/it] {'loss': 0.4639, 'learning_rate': 1.1163969576920846e-05, 'epoch': 0.48} + 48%|████▊ | 5725/11952 [1:54:52<9:59:45, 5.78s/it] 48%|████▊ | 5726/11952 [1:54:58<10:04:38, 5.83s/it] {'loss': 0.5047, 'learning_rate': 1.1161278049237157e-05, 'epoch': 0.48} + 48%|████▊ | 5726/11952 [1:54:58<10:04:38, 5.83s/it] 48%|████▊ | 5727/11952 [1:55:04<9:53:09, 5.72s/it] {'loss': 0.4743, 'learning_rate': 1.1158586436274042e-05, 'epoch': 0.48} + 48%|████▊ | 5727/11952 [1:55:04<9:53:09, 5.72s/it] 48%|████▊ | 5728/11952 [1:55:10<10:00:08, 5.79s/it] {'loss': 0.485, 'learning_rate': 1.1155894738229156e-05, 'epoch': 0.48} + 48%|████▊ | 5728/11952 [1:55:10<10:00:08, 5.79s/it] 48%|████▊ | 5729/11952 [1:55:15<9:55:50, 5.74s/it] {'loss': 0.4729, 'learning_rate': 1.115320295530017e-05, 'epoch': 0.48} + 48%|████▊ | 5729/11952 [1:55:15<9:55:50, 5.74s/it] 48%|████▊ | 5730/11952 [1:55:21<9:52:20, 5.71s/it] {'loss': 0.4761, 'learning_rate': 1.1150511087684757e-05, 'epoch': 0.48} + 48%|████▊ | 5730/11952 [1:55:21<9:52:20, 5.71s/it] 48%|████▊ | 5731/11952 [1:55:27<9:54:48, 5.74s/it] {'loss': 0.4886, 'learning_rate': 1.1147819135580588e-05, 'epoch': 0.48} + 48%|████▊ | 5731/11952 [1:55:27<9:54:48, 5.74s/it] 48%|████▊ | 5732/11952 [1:55:33<10:04:33, 5.83s/it] {'loss': 0.4789, 'learning_rate': 1.1145127099185363e-05, 'epoch': 0.48} + 48%|████▊ | 5732/11952 [1:55:33<10:04:33, 5.83s/it] 48%|████▊ | 5733/11952 [1:55:39<10:08:34, 5.87s/it] {'loss': 0.495, 'learning_rate': 1.1142434978696763e-05, 'epoch': 0.48} + 48%|████▊ | 5733/11952 [1:55:39<10:08:34, 5.87s/it] 48%|████▊ | 5734/11952 [1:55:45<10:10:08, 5.89s/it] {'loss': 0.4717, 'learning_rate': 1.1139742774312495e-05, 'epoch': 0.48} + 48%|████▊ | 5734/11952 [1:55:45<10:10:08, 5.89s/it] 48%|████▊ | 5735/11952 [1:55:51<10:13:49, 5.92s/it] {'loss': 0.495, 'learning_rate': 1.1137050486230251e-05, 'epoch': 0.48} + 48%|████▊ | 5735/11952 [1:55:51<10:13:49, 5.92s/it] 48%|████▊ | 5736/11952 [1:55:56<10:06:20, 5.85s/it] {'loss': 0.4825, 'learning_rate': 1.1134358114647752e-05, 'epoch': 0.48} + 48%|████▊ | 5736/11952 [1:55:56<10:06:20, 5.85s/it] 48%|████▊ | 5737/11952 [1:56:02<10:04:46, 5.84s/it] {'loss': 0.476, 'learning_rate': 1.1131665659762712e-05, 'epoch': 0.48} + 48%|████▊ | 5737/11952 [1:56:02<10:04:46, 5.84s/it] 48%|████▊ | 5738/11952 [1:56:08<10:13:23, 5.92s/it] {'loss': 0.4794, 'learning_rate': 1.112897312177285e-05, 'epoch': 0.48} + 48%|████▊ | 5738/11952 [1:56:08<10:13:23, 5.92s/it] 48%|████▊ | 5739/11952 [1:56:14<10:15:40, 5.95s/it] {'loss': 0.4632, 'learning_rate': 1.11262805008759e-05, 'epoch': 0.48} + 48%|████▊ | 5739/11952 [1:56:14<10:15:40, 5.95s/it]/lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/VILA/llava/model/llava_arch.py:397: UserWarning: Inputs truncated! + warnings.warn("Inputs truncated!") + 48%|████▊ | 5740/11952 [1:56:20<10:20:05, 5.99s/it] {'loss': 0.5031, 'learning_rate': 1.1123587797269596e-05, 'epoch': 0.48} + 48%|████▊ | 5740/11952 [1:56:20<10:20:05, 5.99s/it] 48%|████▊ | 5741/11952 [1:56:26<10:12:26, 5.92s/it] {'loss': 0.4687, 'learning_rate': 1.1120895011151675e-05, 'epoch': 0.48} + 48%|████▊ | 5741/11952 [1:56:26<10:12:26, 5.92s/it] 48%|████▊ | 5742/11952 [1:56:32<10:03:07, 5.83s/it] {'loss': 0.5017, 'learning_rate': 1.1118202142719887e-05, 'epoch': 0.48} + 48%|████▊ | 5742/11952 [1:56:32<10:03:07, 5.83s/it] 48%|████▊ | 5743/11952 [1:56:38<10:02:39, 5.82s/it] {'loss': 0.4941, 'learning_rate': 1.1115509192171988e-05, 'epoch': 0.48} + 48%|████▊ | 5743/11952 [1:56:38<10:02:39, 5.82s/it] 48%|████▊ | 5744/11952 [1:56:44<10:06:08, 5.86s/it] {'loss': 0.4736, 'learning_rate': 1.111281615970573e-05, 'epoch': 0.48} + 48%|████▊ | 5744/11952 [1:56:44<10:06:08, 5.86s/it] 48%|████▊ | 5745/11952 [1:56:49<9:58:04, 5.78s/it] {'loss': 0.4698, 'learning_rate': 1.1110123045518882e-05, 'epoch': 0.48} + 48%|████▊ | 5745/11952 [1:56:49<9:58:04, 5.78s/it] 48%|████▊ | 5746/11952 [1:56:55<10:03:36, 5.84s/it] {'loss': 0.491, 'learning_rate': 1.1107429849809215e-05, 'epoch': 0.48} + 48%|████▊ | 5746/11952 [1:56:55<10:03:36, 5.84s/it] 48%|████▊ | 5747/11952 [1:57:01<10:08:50, 5.89s/it] {'loss': 0.4839, 'learning_rate': 1.1104736572774506e-05, 'epoch': 0.48} + 48%|████▊ | 5747/11952 [1:57:01<10:08:50, 5.89s/it] 48%|████▊ | 5748/11952 [1:57:07<10:12:51, 5.93s/it] {'loss': 0.4779, 'learning_rate': 1.1102043214612539e-05, 'epoch': 0.48} + 48%|████▊ | 5748/11952 [1:57:07<10:12:51, 5.93s/it] 48%|████▊ | 5749/11952 [1:57:13<10:18:47, 5.99s/it] {'loss': 0.4833, 'learning_rate': 1.1099349775521103e-05, 'epoch': 0.48} + 48%|████▊ | 5749/11952 [1:57:13<10:18:47, 5.99s/it]2 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... +10 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend...7 + AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... + 48%|████▊ | 5750/11952 [1:57:19<10:18:09, 5.98s/it]5 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4852, 'learning_rate': 1.1096656255697991e-05, 'epoch': 0.48} + 48%|████▊ | 5750/11952 [1:57:19<10:18:09, 5.98s/it] 48%|████▊ | 5751/11952 [1:57:25<10:05:23, 5.86s/it] {'loss': 0.4684, 'learning_rate': 1.1093962655341002e-05, 'epoch': 0.48} + 48%|████▊ | 5751/11952 [1:57:25<10:05:23, 5.86s/it] 48%|████▊ | 5752/11952 [1:57:31<10:08:04, 5.88s/it] {'loss': 0.4879, 'learning_rate': 1.1091268974647947e-05, 'epoch': 0.48} + 48%|████▊ | 5752/11952 [1:57:31<10:08:04, 5.88s/it] 48%|████▊ | 5753/11952 [1:57:37<10:23:13, 6.03s/it] {'loss': 0.4902, 'learning_rate': 1.108857521381664e-05, 'epoch': 0.48} + 48%|████▊ | 5753/11952 [1:57:37<10:23:13, 6.03s/it] 48%|████▊ | 5754/11952 [1:57:43<10:12:45, 5.93s/it] {'loss': 0.4738, 'learning_rate': 1.1085881373044895e-05, 'epoch': 0.48} + 48%|████▊ | 5754/11952 [1:57:43<10:12:45, 5.93s/it] 48%|████▊ | 5755/11952 [1:57:49<10:09:23, 5.90s/it] {'loss': 0.4899, 'learning_rate': 1.1083187452530539e-05, 'epoch': 0.48} + 48%|████▊ | 5755/11952 [1:57:49<10:09:23, 5.90s/it] 48%|████▊ | 5756/11952 [1:57:55<10:09:39, 5.90s/it] {'loss': 0.4831, 'learning_rate': 1.1080493452471403e-05, 'epoch': 0.48} + 48%|████▊ | 5756/11952 [1:57:55<10:09:39, 5.90s/it] 48%|████▊ | 5757/11952 [1:58:00<10:05:32, 5.86s/it] {'loss': 0.4738, 'learning_rate': 1.1077799373065321e-05, 'epoch': 0.48} + 48%|████▊ | 5757/11952 [1:58:00<10:05:32, 5.86s/it] 48%|████▊ | 5758/11952 [1:58:06<10:07:47, 5.89s/it] {'loss': 0.4864, 'learning_rate': 1.1075105214510135e-05, 'epoch': 0.48} + 48%|████▊ | 5758/11952 [1:58:06<10:07:47, 5.89s/it] 48%|████▊ | 5759/11952 [1:58:12<10:03:55, 5.85s/it] {'loss': 0.4776, 'learning_rate': 1.1072410977003693e-05, 'epoch': 0.48} + 48%|████▊ | 5759/11952 [1:58:12<10:03:55, 5.85s/it] 48%|████▊ | 5760/11952 [1:58:18<10:13:04, 5.94s/it] {'loss': 0.4847, 'learning_rate': 1.1069716660743852e-05, 'epoch': 0.48} + 48%|████▊ | 5760/11952 [1:58:18<10:13:04, 5.94s/it] 48%|████▊ | 5761/11952 [1:58:24<10:05:18, 5.87s/it] {'loss': 0.482, 'learning_rate': 1.1067022265928472e-05, 'epoch': 0.48} + 48%|████▊ | 5761/11952 [1:58:24<10:05:18, 5.87s/it] 48%|████▊ | 5762/11952 [1:58:30<10:18:15, 5.99s/it] {'loss': 0.4857, 'learning_rate': 1.1064327792755405e-05, 'epoch': 0.48} + 48%|████▊ | 5762/11952 [1:58:30<10:18:15, 5.99s/it] 48%|████▊ | 5763/11952 [1:58:36<10:13:20, 5.95s/it] {'loss': 0.4833, 'learning_rate': 1.1061633241422538e-05, 'epoch': 0.48} + 48%|████▊ | 5763/11952 [1:58:36<10:13:20, 5.95s/it] 48%|████▊ | 5764/11952 [1:58:42<10:05:53, 5.87s/it] {'loss': 0.4706, 'learning_rate': 1.1058938612127744e-05, 'epoch': 0.48} + 48%|████▊ | 5764/11952 [1:58:42<10:05:53, 5.87s/it] 48%|████▊ | 5765/11952 [1:58:47<10:02:42, 5.84s/it] {'loss': 0.481, 'learning_rate': 1.1056243905068899e-05, 'epoch': 0.48} + 48%|████▊ | 5765/11952 [1:58:47<10:02:42, 5.84s/it] 48%|████▊ | 5766/11952 [1:58:53<10:01:16, 5.83s/it] {'loss': 0.4646, 'learning_rate': 1.1053549120443893e-05, 'epoch': 0.48} + 48%|████▊ | 5766/11952 [1:58:53<10:01:16, 5.83s/it] 48%|████▊ | 5767/11952 [1:58:59<10:08:01, 5.90s/it] {'loss': 0.4928, 'learning_rate': 1.1050854258450623e-05, 'epoch': 0.48} + 48%|████▊ | 5767/11952 [1:58:59<10:08:01, 5.90s/it] 48%|████▊ | 5768/11952 [1:59:05<10:02:16, 5.84s/it] {'loss': 0.4864, 'learning_rate': 1.104815931928699e-05, 'epoch': 0.48} + 48%|████▊ | 5768/11952 [1:59:05<10:02:16, 5.84s/it] 48%|████▊ | 5769/11952 [1:59:11<10:06:04, 5.88s/it] {'loss': 0.4873, 'learning_rate': 1.1045464303150892e-05, 'epoch': 0.48} + 48%|████▊ | 5769/11952 [1:59:11<10:06:04, 5.88s/it] 48%|████▊ | 5770/11952 [1:59:17<10:04:17, 5.87s/it] {'loss': 0.4881, 'learning_rate': 1.1042769210240248e-05, 'epoch': 0.48} + 48%|████▊ | 5770/11952 [1:59:17<10:04:17, 5.87s/it] 48%|████▊ | 5771/11952 [1:59:23<10:04:16, 5.87s/it] {'loss': 0.4759, 'learning_rate': 1.1040074040752971e-05, 'epoch': 0.48} + 48%|████▊ | 5771/11952 [1:59:23<10:04:16, 5.87s/it] 48%|████▊ | 5772/11952 [1:59:29<10:03:35, 5.86s/it] {'loss': 0.4723, 'learning_rate': 1.1037378794886977e-05, 'epoch': 0.48} + 48%|████▊ | 5772/11952 [1:59:29<10:03:35, 5.86s/it] 48%|████▊ | 5773/11952 [1:59:34<9:57:11, 5.80s/it] {'loss': 0.468, 'learning_rate': 1.1034683472840201e-05, 'epoch': 0.48} + 48%|████▊ | 5773/11952 [1:59:34<9:57:11, 5.80s/it] 48%|████▊ | 5774/11952 [1:59:40<9:55:22, 5.78s/it] {'loss': 0.4803, 'learning_rate': 1.1031988074810578e-05, 'epoch': 0.48} + 48%|████▊ | 5774/11952 [1:59:40<9:55:22, 5.78s/it] 48%|████▊ | 5775/11952 [1:59:46<9:52:19, 5.75s/it] {'loss': 0.5059, 'learning_rate': 1.1029292600996042e-05, 'epoch': 0.48} + 48%|████▊ | 5775/11952 [1:59:46<9:52:19, 5.75s/it] 48%|████▊ | 5776/11952 [1:59:51<9:50:42, 5.74s/it] {'loss': 0.4792, 'learning_rate': 1.1026597051594534e-05, 'epoch': 0.48} + 48%|████▊ | 5776/11952 [1:59:51<9:50:42, 5.74s/it] 48%|████▊ | 5777/11952 [1:59:57<9:51:24, 5.75s/it] {'loss': 0.4762, 'learning_rate': 1.102390142680401e-05, 'epoch': 0.48} + 48%|████▊ | 5777/11952 [1:59:57<9:51:24, 5.75s/it] 48%|████▊ | 5778/11952 [2:00:03<9:55:44, 5.79s/it] {'loss': 0.4988, 'learning_rate': 1.1021205726822429e-05, 'epoch': 0.48} + 48%|████▊ | 5778/11952 [2:00:03<9:55:44, 5.79s/it] 48%|████▊ | 5779/11952 [2:00:09<10:05:05, 5.88s/it] {'loss': 0.4742, 'learning_rate': 1.1018509951847743e-05, 'epoch': 0.48} + 48%|████▊ | 5779/11952 [2:00:09<10:05:05, 5.88s/it] 48%|████▊ | 5780/11952 [2:00:15<9:59:01, 5.82s/it] {'loss': 0.4762, 'learning_rate': 1.1015814102077921e-05, 'epoch': 0.48} + 48%|████▊ | 5780/11952 [2:00:15<9:59:01, 5.82s/it] 48%|████▊ | 5781/11952 [2:00:21<10:02:46, 5.86s/it] {'loss': 0.4947, 'learning_rate': 1.1013118177710942e-05, 'epoch': 0.48} + 48%|████▊ | 5781/11952 [2:00:21<10:02:46, 5.86s/it] 48%|████▊ | 5782/11952 [2:00:26<9:57:17, 5.81s/it] {'loss': 0.4727, 'learning_rate': 1.1010422178944772e-05, 'epoch': 0.48} + 48%|████▊ | 5782/11952 [2:00:26<9:57:17, 5.81s/it] 48%|████▊ | 5783/11952 [2:00:32<10:03:42, 5.87s/it] {'loss': 0.4662, 'learning_rate': 1.10077261059774e-05, 'epoch': 0.48} + 48%|████▊ | 5783/11952 [2:00:32<10:03:42, 5.87s/it] 48%|████▊ | 5784/11952 [2:00:38<10:03:10, 5.87s/it] {'loss': 0.4927, 'learning_rate': 1.1005029959006818e-05, 'epoch': 0.48} + 48%|████▊ | 5784/11952 [2:00:38<10:03:10, 5.87s/it] 48%|████▊ | 5785/11952 [2:00:44<10:05:52, 5.89s/it] {'loss': 0.4872, 'learning_rate': 1.1002333738231016e-05, 'epoch': 0.48} + 48%|████▊ | 5785/11952 [2:00:44<10:05:52, 5.89s/it] 48%|████▊ | 5786/11952 [2:00:50<10:03:27, 5.87s/it] {'loss': 0.4899, 'learning_rate': 1.099963744384799e-05, 'epoch': 0.48} + 48%|████▊ | 5786/11952 [2:00:50<10:03:27, 5.87s/it] 48%|████▊ | 5787/11952 [2:00:56<10:01:01, 5.85s/it] {'loss': 0.4824, 'learning_rate': 1.0996941076055751e-05, 'epoch': 0.48} + 48%|████▊ | 5787/11952 [2:00:56<10:01:01, 5.85s/it] 48%|████▊ | 5788/11952 [2:01:02<10:03:31, 5.87s/it] {'loss': 0.4645, 'learning_rate': 1.0994244635052304e-05, 'epoch': 0.48} + 48%|████▊ | 5788/11952 [2:01:02<10:03:31, 5.87s/it] 48%|████▊ | 5789/11952 [2:01:08<10:01:23, 5.85s/it] {'loss': 0.4843, 'learning_rate': 1.0991548121035664e-05, 'epoch': 0.48} + 48%|████▊ | 5789/11952 [2:01:08<10:01:23, 5.85s/it] 48%|████▊ | 5790/11952 [2:01:14<10:05:45, 5.90s/it] {'loss': 0.4767, 'learning_rate': 1.098885153420386e-05, 'epoch': 0.48} + 48%|████▊ | 5790/11952 [2:01:14<10:05:45, 5.90s/it] 48%|████▊ | 5791/11952 [2:01:20<10:06:49, 5.91s/it] {'loss': 0.4897, 'learning_rate': 1.098615487475491e-05, 'epoch': 0.48} + 48%|████▊ | 5791/11952 [2:01:20<10:06:49, 5.91s/it] 48%|████▊ | 5792/11952 [2:01:26<10:11:00, 5.95s/it] {'loss': 0.4754, 'learning_rate': 1.0983458142886848e-05, 'epoch': 0.48} + 48%|████▊ | 5792/11952 [2:01:26<10:11:00, 5.95s/it] 48%|████▊ | 5793/11952 [2:01:31<10:06:34, 5.91s/it] {'loss': 0.4671, 'learning_rate': 1.0980761338797707e-05, 'epoch': 0.48} + 48%|████▊ | 5793/11952 [2:01:31<10:06:34, 5.91s/it] 48%|████▊ | 5794/11952 [2:01:37<10:12:26, 5.97s/it] {'loss': 0.4932, 'learning_rate': 1.0978064462685536e-05, 'epoch': 0.48} + 48%|████▊ | 5794/11952 [2:01:38<10:12:26, 5.97s/it] 48%|████▊ | 5795/11952 [2:01:43<10:04:07, 5.89s/it] {'loss': 0.4822, 'learning_rate': 1.0975367514748378e-05, 'epoch': 0.48} + 48%|████▊ | 5795/11952 [2:01:43<10:04:07, 5.89s/it] 48%|████▊ | 5796/11952 [2:01:49<10:04:32, 5.89s/it] {'loss': 0.5096, 'learning_rate': 1.0972670495184286e-05, 'epoch': 0.48} + 48%|████▊ | 5796/11952 [2:01:49<10:04:32, 5.89s/it] 49%|████▊ | 5797/11952 [2:01:55<9:59:26, 5.84s/it] {'loss': 0.5035, 'learning_rate': 1.0969973404191322e-05, 'epoch': 0.49} + 49%|████▊ | 5797/11952 [2:01:55<9:59:26, 5.84s/it] 49%|████▊ | 5798/11952 [2:02:01<10:05:46, 5.91s/it] {'loss': 0.4778, 'learning_rate': 1.096727624196754e-05, 'epoch': 0.49} + 49%|████▊ | 5798/11952 [2:02:01<10:05:46, 5.91s/it] 49%|████▊ | 5799/11952 [2:02:07<10:08:33, 5.93s/it] {'loss': 0.4801, 'learning_rate': 1.0964579008711018e-05, 'epoch': 0.49} + 49%|████▊ | 5799/11952 [2:02:07<10:08:33, 5.93s/it]2 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +0 AutoResumeHook: Checking whether to suspend... + 49%|████▊ | 5800/11952 [2:02:13<10:10:29, 5.95s/it]5 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4845, 'learning_rate': 1.0961881704619823e-05, 'epoch': 0.49} + 49%|████▊ | 5800/11952 [2:02:13<10:10:29, 5.95s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-5800/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-5800/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/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%|████▊ | 5801/11952 [2:02:43<22:48:07, 13.35s/it] {'loss': 0.4793, 'learning_rate': 1.095918432989204e-05, 'epoch': 0.49} + 49%|████▊ | 5801/11952 [2:02:43<22:48:07, 13.35s/it] 49%|████▊ | 5802/11952 [2:02:49<18:55:07, 11.07s/it] {'loss': 0.4717, 'learning_rate': 1.0956486884725748e-05, 'epoch': 0.49} + 49%|████▊ | 5802/11952 [2:02:49<18:55:07, 11.07s/it] 49%|████▊ | 5803/11952 [2:02:55<16:13:14, 9.50s/it] {'loss': 0.4756, 'learning_rate': 1.0953789369319031e-05, 'epoch': 0.49} + 49%|████▊ | 5803/11952 [2:02:55<16:13:14, 9.50s/it] 49%|████▊ | 5804/11952 [2:03:01<14:36:13, 8.55s/it] {'loss': 0.485, 'learning_rate': 1.0951091783869998e-05, 'epoch': 0.49} + 49%|████▊ | 5804/11952 [2:03:01<14:36:13, 8.55s/it] 49%|████▊ | 5805/11952 [2:03:07<13:09:47, 7.71s/it] {'loss': 0.496, 'learning_rate': 1.0948394128576739e-05, 'epoch': 0.49} + 49%|████▊ | 5805/11952 [2:03:07<13:09:47, 7.71s/it] 49%|████▊ | 5806/11952 [2:03:13<12:11:37, 7.14s/it] {'loss': 0.4963, 'learning_rate': 1.094569640363736e-05, 'epoch': 0.49} + 49%|████▊ | 5806/11952 [2:03:13<12:11:37, 7.14s/it] 49%|████▊ | 5807/11952 [2:03:19<11:38:49, 6.82s/it] {'loss': 0.4884, 'learning_rate': 1.0942998609249968e-05, 'epoch': 0.49} + 49%|████▊ | 5807/11952 [2:03:19<11:38:49, 6.82s/it] 49%|████▊ | 5808/11952 [2:03:25<11:14:07, 6.58s/it] {'loss': 0.4687, 'learning_rate': 1.0940300745612679e-05, 'epoch': 0.49} + 49%|████▊ | 5808/11952 [2:03:25<11:14:07, 6.58s/it] 49%|████▊ | 5809/11952 [2:03:31<10:57:21, 6.42s/it] {'loss': 0.4779, 'learning_rate': 1.0937602812923617e-05, 'epoch': 0.49} + 49%|████▊ | 5809/11952 [2:03:31<10:57:21, 6.42s/it] 49%|████▊ | 5810/11952 [2:03:37<10:47:41, 6.33s/it] {'loss': 0.4892, 'learning_rate': 1.0934904811380904e-05, 'epoch': 0.49} + 49%|████▊ | 5810/11952 [2:03:37<10:47:41, 6.33s/it] 49%|████▊ | 5811/11952 [2:03:43<10:34:07, 6.20s/it] {'loss': 0.4831, 'learning_rate': 1.0932206741182672e-05, 'epoch': 0.49} + 49%|████▊ | 5811/11952 [2:03:43<10:34:07, 6.20s/it] 49%|████▊ | 5812/11952 [2:03:49<10:27:26, 6.13s/it] {'loss': 0.4711, 'learning_rate': 1.0929508602527052e-05, 'epoch': 0.49} + 49%|████▊ | 5812/11952 [2:03:49<10:27:26, 6.13s/it] 49%|████▊ | 5813/11952 [2:03:55<10:14:52, 6.01s/it] {'loss': 0.4934, 'learning_rate': 1.0926810395612187e-05, 'epoch': 0.49} + 49%|████▊ | 5813/11952 [2:03:55<10:14:52, 6.01s/it] 49%|████▊ | 5814/11952 [2:04:01<10:12:05, 5.98s/it] {'loss': 0.48, 'learning_rate': 1.0924112120636222e-05, 'epoch': 0.49} + 49%|████▊ | 5814/11952 [2:04:01<10:12:05, 5.98s/it] 49%|████▊ | 5815/11952 [2:04:07<10:07:15, 5.94s/it] {'loss': 0.4744, 'learning_rate': 1.0921413777797305e-05, 'epoch': 0.49} + 49%|████▊ | 5815/11952 [2:04:07<10:07:15, 5.94s/it] 49%|████▊ | 5816/11952 [2:04:12<10:00:58, 5.88s/it] {'loss': 0.4796, 'learning_rate': 1.0918715367293595e-05, 'epoch': 0.49} + 49%|████▊ | 5816/11952 [2:04:12<10:00:58, 5.88s/it] 49%|████▊ | 5817/11952 [2:04:18<10:01:37, 5.88s/it] {'loss': 0.4669, 'learning_rate': 1.0916016889323246e-05, 'epoch': 0.49} + 49%|████▊ | 5817/11952 [2:04:18<10:01:37, 5.88s/it] 49%|████▊ | 5818/11952 [2:04:24<9:53:14, 5.80s/it] {'loss': 0.4656, 'learning_rate': 1.0913318344084428e-05, 'epoch': 0.49} + 49%|████▊ | 5818/11952 [2:04:24<9:53:14, 5.80s/it] 49%|████▊ | 5819/11952 [2:04:30<10:00:04, 5.87s/it] {'loss': 0.4658, 'learning_rate': 1.0910619731775311e-05, 'epoch': 0.49} + 49%|████▊ | 5819/11952 [2:04:30<10:00:04, 5.87s/it] 49%|████▊ | 5820/11952 [2:04:36<10:02:33, 5.90s/it] {'loss': 0.4817, 'learning_rate': 1.0907921052594066e-05, 'epoch': 0.49} + 49%|████▊ | 5820/11952 [2:04:36<10:02:33, 5.90s/it] 49%|████▊ | 5821/11952 [2:04:42<10:03:57, 5.91s/it] {'loss': 0.4862, 'learning_rate': 1.0905222306738879e-05, 'epoch': 0.49} + 49%|████▊ | 5821/11952 [2:04:42<10:03:57, 5.91s/it] 49%|████▊ | 5822/11952 [2:04:48<9:59:54, 5.87s/it] {'loss': 0.4828, 'learning_rate': 1.0902523494407928e-05, 'epoch': 0.49} + 49%|████▊ | 5822/11952 [2:04:48<9:59:54, 5.87s/it] 49%|████▊ | 5823/11952 [2:04:53<9:58:16, 5.86s/it] {'loss': 0.4725, 'learning_rate': 1.0899824615799406e-05, 'epoch': 0.49} + 49%|████▊ | 5823/11952 [2:04:53<9:58:16, 5.86s/it] 49%|████▊ | 5824/11952 [2:04:59<9:51:11, 5.79s/it] {'loss': 0.4827, 'learning_rate': 1.0897125671111507e-05, 'epoch': 0.49} + 49%|████▊ | 5824/11952 [2:04:59<9:51:11, 5.79s/it] 49%|████▊ | 5825/11952 [2:05:05<9:45:33, 5.73s/it] {'loss': 0.4902, 'learning_rate': 1.089442666054243e-05, 'epoch': 0.49} + 49%|████▊ | 5825/11952 [2:05:05<9:45:33, 5.73s/it] 49%|████▊ | 5826/11952 [2:05:10<9:49:15, 5.77s/it] {'loss': 0.465, 'learning_rate': 1.0891727584290381e-05, 'epoch': 0.49} + 49%|████▊ | 5826/11952 [2:05:10<9:49:15, 5.77s/it] 49%|████▉ | 5827/11952 [2:05:16<9:49:25, 5.77s/it] {'loss': 0.4795, 'learning_rate': 1.0889028442553565e-05, 'epoch': 0.49} + 49%|████▉ | 5827/11952 [2:05:16<9:49:25, 5.77s/it] 49%|████▉ | 5828/11952 [2:05:22<9:54:44, 5.83s/it] {'loss': 0.4693, 'learning_rate': 1.08863292355302e-05, 'epoch': 0.49} + 49%|████▉ | 5828/11952 [2:05:22<9:54:44, 5.83s/it] 49%|████▉ | 5829/11952 [2:05:28<9:59:15, 5.87s/it] {'loss': 0.4781, 'learning_rate': 1.0883629963418501e-05, 'epoch': 0.49} + 49%|████▉ | 5829/11952 [2:05:28<9:59:15, 5.87s/it] 49%|████▉ | 5830/11952 [2:05:34<9:55:11, 5.83s/it] {'loss': 0.5004, 'learning_rate': 1.088093062641669e-05, 'epoch': 0.49} + 49%|████▉ | 5830/11952 [2:05:34<9:55:11, 5.83s/it] 49%|████▉ | 5831/11952 [2:05:40<9:49:36, 5.78s/it] {'loss': 0.4815, 'learning_rate': 1.0878231224723001e-05, 'epoch': 0.49} + 49%|████▉ | 5831/11952 [2:05:40<9:49:36, 5.78s/it] 49%|████▉ | 5832/11952 [2:05:46<10:06:41, 5.95s/it] {'loss': 0.4879, 'learning_rate': 1.0875531758535668e-05, 'epoch': 0.49} + 49%|████▉ | 5832/11952 [2:05:46<10:06:41, 5.95s/it] 49%|████▉ | 5833/11952 [2:05:52<10:04:21, 5.93s/it] {'loss': 0.4919, 'learning_rate': 1.0872832228052919e-05, 'epoch': 0.49} + 49%|████▉ | 5833/11952 [2:05:52<10:04:21, 5.93s/it] 49%|████▉ | 5834/11952 [2:05:57<9:54:01, 5.83s/it] {'loss': 0.5049, 'learning_rate': 1.0870132633472999e-05, 'epoch': 0.49} + 49%|████▉ | 5834/11952 [2:05:57<9:54:01, 5.83s/it] 49%|████▉ | 5835/11952 [2:06:03<9:58:27, 5.87s/it] {'loss': 0.4874, 'learning_rate': 1.0867432974994162e-05, 'epoch': 0.49} + 49%|████▉ | 5835/11952 [2:06:03<9:58:27, 5.87s/it] 49%|████▉ | 5836/11952 [2:06:09<10:00:39, 5.89s/it] {'loss': 0.4906, 'learning_rate': 1.0864733252814654e-05, 'epoch': 0.49} + 49%|████▉ | 5836/11952 [2:06:09<10:00:39, 5.89s/it] 49%|████▉ | 5837/11952 [2:06:15<9:58:19, 5.87s/it] {'loss': 0.4875, 'learning_rate': 1.0862033467132732e-05, 'epoch': 0.49} + 49%|████▉ | 5837/11952 [2:06:15<9:58:19, 5.87s/it] 49%|████▉ | 5838/11952 [2:06:21<9:48:34, 5.78s/it] {'loss': 0.4617, 'learning_rate': 1.0859333618146659e-05, 'epoch': 0.49} + 49%|████▉ | 5838/11952 [2:06:21<9:48:34, 5.78s/it] 49%|████▉ | 5839/11952 [2:06:27<9:57:21, 5.86s/it] {'loss': 0.4761, 'learning_rate': 1.0856633706054698e-05, 'epoch': 0.49} + 49%|████▉ | 5839/11952 [2:06:27<9:57:21, 5.86s/it] 49%|████▉ | 5840/11952 [2:06:33<10:00:37, 5.90s/it] {'loss': 0.4735, 'learning_rate': 1.0853933731055122e-05, 'epoch': 0.49} + 49%|████▉ | 5840/11952 [2:06:33<10:00:37, 5.90s/it] 49%|████▉ | 5841/11952 [2:06:39<9:59:49, 5.89s/it] {'loss': 0.4843, 'learning_rate': 1.0851233693346204e-05, 'epoch': 0.49} + 49%|████▉ | 5841/11952 [2:06:39<9:59:49, 5.89s/it] 49%|████▉ | 5842/11952 [2:06:45<10:15:36, 6.05s/it] {'loss': 0.4845, 'learning_rate': 1.0848533593126225e-05, 'epoch': 0.49} + 49%|████▉ | 5842/11952 [2:06:45<10:15:36, 6.05s/it] 49%|████▉ | 5843/11952 [2:06:51<10:03:38, 5.93s/it] {'loss': 0.4731, 'learning_rate': 1.0845833430593467e-05, 'epoch': 0.49} + 49%|████▉ | 5843/11952 [2:06:51<10:03:38, 5.93s/it] 49%|████▉ | 5844/11952 [2:06:56<9:58:27, 5.88s/it] {'loss': 0.4897, 'learning_rate': 1.0843133205946218e-05, 'epoch': 0.49} + 49%|████▉ | 5844/11952 [2:06:56<9:58:27, 5.88s/it] 49%|████▉ | 5845/11952 [2:07:02<10:02:11, 5.92s/it] {'loss': 0.501, 'learning_rate': 1.0840432919382774e-05, 'epoch': 0.49} + 49%|████▉ | 5845/11952 [2:07:02<10:02:11, 5.92s/it] 49%|████▉ | 5846/11952 [2:07:08<9:54:43, 5.84s/it] {'loss': 0.4934, 'learning_rate': 1.0837732571101437e-05, 'epoch': 0.49} + 49%|████▉ | 5846/11952 [2:07:08<9:54:43, 5.84s/it] 49%|████▉ | 5847/11952 [2:07:14<9:56:32, 5.86s/it] {'loss': 0.4878, 'learning_rate': 1.0835032161300499e-05, 'epoch': 0.49} + 49%|████▉ | 5847/11952 [2:07:14<9:56:32, 5.86s/it] 49%|████▉ | 5848/11952 [2:07:20<10:00:52, 5.91s/it] {'loss': 0.4885, 'learning_rate': 1.0832331690178274e-05, 'epoch': 0.49} + 49%|████▉ | 5848/11952 [2:07:20<10:00:52, 5.91s/it] 49%|████▉ | 5849/11952 [2:07:26<10:12:04, 6.02s/it] {'loss': 0.4741, 'learning_rate': 1.0829631157933071e-05, 'epoch': 0.49} + 49%|████▉ | 5849/11952 [2:07:26<10:12:04, 6.02s/it]2 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... +04 3AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... + 49%|████▉ | 5850/11952 [2:07:32<10:11:09, 6.01s/it] {'loss': 0.5027, 'learning_rate': 1.0826930564763207e-05, 'epoch': 0.49} + 49%|████▉ | 5850/11952 [2:07:32<10:11:09, 6.01s/it] 49%|████▉ | 5851/11952 [2:07:38<10:02:51, 5.93s/it] {'loss': 0.4769, 'learning_rate': 1.0824229910867002e-05, 'epoch': 0.49} + 49%|████▉ | 5851/11952 [2:07:38<10:02:51, 5.93s/it] 49%|████▉ | 5852/11952 [2:07:44<10:03:43, 5.94s/it] {'loss': 0.4863, 'learning_rate': 1.0821529196442782e-05, 'epoch': 0.49} + 49%|████▉ | 5852/11952 [2:07:44<10:03:43, 5.94s/it] 49%|████▉ | 5853/11952 [2:07:50<10:01:15, 5.92s/it] {'loss': 0.4707, 'learning_rate': 1.0818828421688873e-05, 'epoch': 0.49} + 49%|████▉ | 5853/11952 [2:07:50<10:01:15, 5.92s/it] 49%|████▉ | 5854/11952 [2:07:56<10:03:32, 5.94s/it] {'loss': 0.4718, 'learning_rate': 1.081612758680361e-05, 'epoch': 0.49} + 49%|████▉ | 5854/11952 [2:07:56<10:03:32, 5.94s/it] 49%|████▉ | 5855/11952 [2:08:02<9:58:08, 5.89s/it] {'loss': 0.469, 'learning_rate': 1.0813426691985331e-05, 'epoch': 0.49} + 49%|████▉ | 5855/11952 [2:08:02<9:58:08, 5.89s/it] 49%|████▉ | 5856/11952 [2:08:08<10:05:42, 5.96s/it] {'loss': 0.4993, 'learning_rate': 1.0810725737432381e-05, 'epoch': 0.49} + 49%|████▉ | 5856/11952 [2:08:08<10:05:42, 5.96s/it] 49%|████▉ | 5857/11952 [2:08:13<9:57:00, 5.88s/it] {'loss': 0.4695, 'learning_rate': 1.0808024723343104e-05, 'epoch': 0.49} + 49%|████▉ | 5857/11952 [2:08:13<9:57:00, 5.88s/it] 49%|████▉ | 5858/11952 [2:08:19<9:57:38, 5.88s/it] {'loss': 0.4555, 'learning_rate': 1.0805323649915854e-05, 'epoch': 0.49} + 49%|████▉ | 5858/11952 [2:08:19<9:57:38, 5.88s/it] 49%|████▉ | 5859/11952 [2:08:25<9:55:32, 5.86s/it] {'loss': 0.4673, 'learning_rate': 1.0802622517348982e-05, 'epoch': 0.49} + 49%|████▉ | 5859/11952 [2:08:25<9:55:32, 5.86s/it] 49%|████▉ | 5860/11952 [2:08:31<9:53:27, 5.85s/it] {'loss': 0.4788, 'learning_rate': 1.0799921325840851e-05, 'epoch': 0.49} + 49%|████▉ | 5860/11952 [2:08:31<9:53:27, 5.85s/it] 49%|████▉ | 5861/11952 [2:08:37<9:49:53, 5.81s/it] {'loss': 0.4518, 'learning_rate': 1.0797220075589825e-05, 'epoch': 0.49} + 49%|████▉ | 5861/11952 [2:08:37<9:49:53, 5.81s/it] 49%|████▉ | 5862/11952 [2:08:42<9:47:26, 5.79s/it] {'loss': 0.4822, 'learning_rate': 1.0794518766794272e-05, 'epoch': 0.49} + 49%|████▉ | 5862/11952 [2:08:42<9:47:26, 5.79s/it] 49%|████▉ | 5863/11952 [2:08:48<9:50:21, 5.82s/it] {'loss': 0.4787, 'learning_rate': 1.079181739965257e-05, 'epoch': 0.49} + 49%|████▉ | 5863/11952 [2:08:48<9:50:21, 5.82s/it] 49%|████▉ | 5864/11952 [2:08:54<9:54:49, 5.86s/it] {'loss': 0.4897, 'learning_rate': 1.0789115974363086e-05, 'epoch': 0.49} + 49%|████▉ | 5864/11952 [2:08:54<9:54:49, 5.86s/it] 49%|████▉ | 5865/11952 [2:09:00<9:56:55, 5.88s/it] {'loss': 0.4997, 'learning_rate': 1.0786414491124208e-05, 'epoch': 0.49} + 49%|████▉ | 5865/11952 [2:09:00<9:56:55, 5.88s/it] 49%|████▉ | 5866/11952 [2:09:06<10:02:39, 5.94s/it] {'loss': 0.4807, 'learning_rate': 1.0783712950134324e-05, 'epoch': 0.49} + 49%|████▉ | 5866/11952 [2:09:06<10:02:39, 5.94s/it] 49%|████▉ | 5867/11952 [2:09:12<10:11:41, 6.03s/it] {'loss': 0.4609, 'learning_rate': 1.0781011351591819e-05, 'epoch': 0.49} + 49%|████▉ | 5867/11952 [2:09:12<10:11:41, 6.03s/it] 49%|████▉ | 5868/11952 [2:09:18<10:02:34, 5.94s/it] {'loss': 0.4857, 'learning_rate': 1.0778309695695088e-05, 'epoch': 0.49} + 49%|████▉ | 5868/11952 [2:09:18<10:02:34, 5.94s/it] 49%|████▉ | 5869/11952 [2:09:24<10:02:39, 5.94s/it] {'loss': 0.4819, 'learning_rate': 1.077560798264253e-05, 'epoch': 0.49} + 49%|████▉ | 5869/11952 [2:09:24<10:02:39, 5.94s/it] 49%|████▉ | 5870/11952 [2:09:30<9:58:30, 5.90s/it] {'loss': 0.4784, 'learning_rate': 1.0772906212632547e-05, 'epoch': 0.49} + 49%|████▉ | 5870/11952 [2:09:30<9:58:30, 5.90s/it] 49%|████▉ | 5871/11952 [2:09:36<9:55:47, 5.88s/it] {'loss': 0.4976, 'learning_rate': 1.0770204385863547e-05, 'epoch': 0.49} + 49%|████▉ | 5871/11952 [2:09:36<9:55:47, 5.88s/it] 49%|████▉ | 5872/11952 [2:09:42<9:53:40, 5.86s/it] {'loss': 0.473, 'learning_rate': 1.0767502502533945e-05, 'epoch': 0.49} + 49%|████▉ | 5872/11952 [2:09:42<9:53:40, 5.86s/it] 49%|████▉ | 5873/11952 [2:09:48<9:56:03, 5.88s/it] {'loss': 0.4696, 'learning_rate': 1.0764800562842149e-05, 'epoch': 0.49} + 49%|████▉ | 5873/11952 [2:09:48<9:56:03, 5.88s/it] 49%|████▉ | 5874/11952 [2:09:53<9:52:22, 5.85s/it] {'loss': 0.4932, 'learning_rate': 1.0762098566986578e-05, 'epoch': 0.49} + 49%|████▉ | 5874/11952 [2:09:53<9:52:22, 5.85s/it] 49%|████▉ | 5875/11952 [2:09:59<9:51:37, 5.84s/it] {'loss': 0.4942, 'learning_rate': 1.0759396515165657e-05, 'epoch': 0.49} + 49%|████▉ | 5875/11952 [2:09:59<9:51:37, 5.84s/it] 49%|████▉ | 5876/11952 [2:10:05<9:43:44, 5.76s/it] {'loss': 0.4632, 'learning_rate': 1.075669440757782e-05, 'epoch': 0.49} + 49%|████▉ | 5876/11952 [2:10:05<9:43:44, 5.76s/it] 49%|████▉ | 5877/11952 [2:10:11<9:44:45, 5.78s/it] {'loss': 0.477, 'learning_rate': 1.075399224442149e-05, 'epoch': 0.49} + 49%|████▉ | 5877/11952 [2:10:11<9:44:45, 5.78s/it] 49%|████▉ | 5878/11952 [2:10:17<9:55:56, 5.89s/it] {'loss': 0.49, 'learning_rate': 1.0751290025895104e-05, 'epoch': 0.49} + 49%|████▉ | 5878/11952 [2:10:17<9:55:56, 5.89s/it] 49%|████▉ | 5879/11952 [2:10:22<9:46:41, 5.80s/it] {'loss': 0.4698, 'learning_rate': 1.0748587752197106e-05, 'epoch': 0.49} + 49%|████▉ | 5879/11952 [2:10:22<9:46:41, 5.80s/it] 49%|████▉ | 5880/11952 [2:10:28<9:47:56, 5.81s/it] {'loss': 0.4739, 'learning_rate': 1.0745885423525934e-05, 'epoch': 0.49} + 49%|████▉ | 5880/11952 [2:10:28<9:47:56, 5.81s/it] 49%|████▉ | 5881/11952 [2:10:34<9:47:21, 5.80s/it] {'loss': 0.4757, 'learning_rate': 1.0743183040080043e-05, 'epoch': 0.49} + 49%|████▉ | 5881/11952 [2:10:34<9:47:21, 5.80s/it] 49%|████▉ | 5882/11952 [2:10:39<9:39:03, 5.72s/it] {'loss': 0.4677, 'learning_rate': 1.0740480602057877e-05, 'epoch': 0.49} + 49%|████▉ | 5882/11952 [2:10:39<9:39:03, 5.72s/it] 49%|████▉ | 5883/11952 [2:10:45<9:41:33, 5.75s/it] {'loss': 0.4867, 'learning_rate': 1.0737778109657899e-05, 'epoch': 0.49} + 49%|████▉ | 5883/11952 [2:10:45<9:41:33, 5.75s/it] 49%|████▉ | 5884/11952 [2:10:51<9:41:14, 5.75s/it] {'loss': 0.4678, 'learning_rate': 1.0735075563078565e-05, 'epoch': 0.49} + 49%|████▉ | 5884/11952 [2:10:51<9:41:14, 5.75s/it] 49%|████▉ | 5885/11952 [2:10:57<9:43:24, 5.77s/it] {'loss': 0.4661, 'learning_rate': 1.0732372962518337e-05, 'epoch': 0.49} + 49%|████▉ | 5885/11952 [2:10:57<9:43:24, 5.77s/it] 49%|████▉ | 5886/11952 [2:11:02<9:40:53, 5.75s/it] {'loss': 0.4743, 'learning_rate': 1.0729670308175683e-05, 'epoch': 0.49} + 49%|████▉ | 5886/11952 [2:11:02<9:40:53, 5.75s/it] 49%|████▉ | 5887/11952 [2:11:08<9:37:41, 5.71s/it] {'loss': 0.4877, 'learning_rate': 1.072696760024908e-05, 'epoch': 0.49} + 49%|████▉ | 5887/11952 [2:11:08<9:37:41, 5.71s/it] 49%|████▉ | 5888/11952 [2:11:14<9:52:39, 5.86s/it] {'loss': 0.4869, 'learning_rate': 1.0724264838936998e-05, 'epoch': 0.49} + 49%|████▉ | 5888/11952 [2:11:14<9:52:39, 5.86s/it] 49%|████▉ | 5889/11952 [2:11:20<9:52:30, 5.86s/it] {'loss': 0.4722, 'learning_rate': 1.0721562024437919e-05, 'epoch': 0.49} + 49%|████▉ | 5889/11952 [2:11:20<9:52:30, 5.86s/it] 49%|████▉ | 5890/11952 [2:11:26<9:55:32, 5.89s/it] {'loss': 0.4959, 'learning_rate': 1.0718859156950329e-05, 'epoch': 0.49} + 49%|████▉ | 5890/11952 [2:11:26<9:55:32, 5.89s/it] 49%|████▉ | 5891/11952 [2:11:32<9:50:40, 5.85s/it] {'loss': 0.4653, 'learning_rate': 1.071615623667271e-05, 'epoch': 0.49} + 49%|████▉ | 5891/11952 [2:11:32<9:50:40, 5.85s/it] 49%|████▉ | 5892/11952 [2:11:38<9:43:56, 5.78s/it] {'loss': 0.4606, 'learning_rate': 1.0713453263803553e-05, 'epoch': 0.49} + 49%|████▉ | 5892/11952 [2:11:38<9:43:56, 5.78s/it] 49%|████▉ | 5893/11952 [2:11:43<9:44:15, 5.79s/it] {'loss': 0.49, 'learning_rate': 1.071075023854136e-05, 'epoch': 0.49} + 49%|████▉ | 5893/11952 [2:11:43<9:44:15, 5.79s/it] 49%|████▉ | 5894/11952 [2:11:49<9:49:59, 5.84s/it] {'loss': 0.4895, 'learning_rate': 1.0708047161084626e-05, 'epoch': 0.49} + 49%|████▉ | 5894/11952 [2:11:49<9:49:59, 5.84s/it] 49%|████▉ | 5895/11952 [2:11:56<10:02:30, 5.97s/it] {'loss': 0.4806, 'learning_rate': 1.070534403163185e-05, 'epoch': 0.49} + 49%|████▉ | 5895/11952 [2:11:56<10:02:30, 5.97s/it] 49%|████▉ | 5896/11952 [2:12:01<9:58:24, 5.93s/it] {'loss': 0.4713, 'learning_rate': 1.0702640850381542e-05, 'epoch': 0.49} + 49%|████▉ | 5896/11952 [2:12:01<9:58:24, 5.93s/it] 49%|████▉ | 5897/11952 [2:12:07<9:57:24, 5.92s/it] {'loss': 0.4832, 'learning_rate': 1.0699937617532216e-05, 'epoch': 0.49} + 49%|████▉ | 5897/11952 [2:12:07<9:57:24, 5.92s/it] 49%|████▉ | 5898/11952 [2:12:13<9:57:35, 5.92s/it] {'loss': 0.4784, 'learning_rate': 1.0697234333282382e-05, 'epoch': 0.49} + 49%|████▉ | 5898/11952 [2:12:13<9:57:35, 5.92s/it] 49%|████▉ | 5899/11952 [2:12:19<9:48:18, 5.83s/it] {'loss': 0.4696, 'learning_rate': 1.0694530997830556e-05, 'epoch': 0.49} + 49%|████▉ | 5899/11952 [2:12:19<9:48:18, 5.83s/it]4 AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... +013 AutoResumeHook: Checking whether to suspend...AutoResumeHook: Checking whether to suspend... + +7 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... + 49%|████▉ | 5900/11952 [2:12:25<9:47:07, 5.82s/it]5 AutoResumeHook: Checking whether to suspend... + {'loss': 0.5059, 'learning_rate': 1.0691827611375268e-05, 'epoch': 0.49} + 49%|████▉ | 5900/11952 [2:12:25<9:47:07, 5.82s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-5900/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-5900/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/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( + 49%|████▉ | 5901/11952 [2:12:56<22:34:38, 13.43s/it] {'loss': 0.4705, 'learning_rate': 1.068912417411503e-05, 'epoch': 0.49} + 49%|████▉ | 5901/11952 [2:12:56<22:34:38, 13.43s/it] 49%|████▉ | 5902/11952 [2:13:01<18:38:43, 11.09s/it] {'loss': 0.4696, 'learning_rate': 1.0686420686248382e-05, 'epoch': 0.49} + 49%|████▉ | 5902/11952 [2:13:01<18:38:43, 11.09s/it] 49%|████▉ | 5903/11952 [2:13:07<16:04:37, 9.57s/it] {'loss': 0.4935, 'learning_rate': 1.0683717147973856e-05, 'epoch': 0.49} + 49%|████▉ | 5903/11952 [2:13:07<16:04:37, 9.57s/it] 49%|████▉ | 5904/11952 [2:13:13<14:07:22, 8.41s/it] {'loss': 0.4837, 'learning_rate': 1.0681013559489985e-05, 'epoch': 0.49} + 49%|████▉ | 5904/11952 [2:13:13<14:07:22, 8.41s/it] 49%|████▉ | 5905/11952 [2:13:19<12:47:30, 7.62s/it] {'loss': 0.4748, 'learning_rate': 1.067830992099531e-05, 'epoch': 0.49} + 49%|████▉ | 5905/11952 [2:13:19<12:47:30, 7.62s/it] 49%|████▉ | 5906/11952 [2:13:25<12:02:42, 7.17s/it] {'loss': 0.4827, 'learning_rate': 1.0675606232688377e-05, 'epoch': 0.49} + 49%|████▉ | 5906/11952 [2:13:25<12:02:42, 7.17s/it] 49%|████▉ | 5907/11952 [2:13:31<11:24:15, 6.79s/it] {'loss': 0.5115, 'learning_rate': 1.0672902494767731e-05, 'epoch': 0.49} + 49%|████▉ | 5907/11952 [2:13:31<11:24:15, 6.79s/it] 49%|████▉ | 5908/11952 [2:13:37<11:07:09, 6.62s/it] {'loss': 0.4813, 'learning_rate': 1.0670198707431927e-05, 'epoch': 0.49} + 49%|████▉ | 5908/11952 [2:13:37<11:07:09, 6.62s/it] 49%|████▉ | 5909/11952 [2:13:43<10:45:37, 6.41s/it] {'loss': 0.4771, 'learning_rate': 1.0667494870879513e-05, 'epoch': 0.49} + 49%|████▉ | 5909/11952 [2:13:43<10:45:37, 6.41s/it] 49%|████▉ | 5910/11952 [2:13:49<10:42:53, 6.38s/it] {'loss': 0.5049, 'learning_rate': 1.0664790985309058e-05, 'epoch': 0.49} + 49%|████▉ | 5910/11952 [2:13:49<10:42:53, 6.38s/it] 49%|████▉ | 5911/11952 [2:13:55<10:26:15, 6.22s/it] {'loss': 0.4861, 'learning_rate': 1.0662087050919111e-05, 'epoch': 0.49} + 49%|████▉ | 5911/11952 [2:13:55<10:26:15, 6.22s/it] 49%|████▉ | 5912/11952 [2:14:01<10:13:25, 6.09s/it] {'loss': 0.4752, 'learning_rate': 1.065938306790825e-05, 'epoch': 0.49} + 49%|████▉ | 5912/11952 [2:14:01<10:13:25, 6.09s/it] 49%|████▉ | 5913/11952 [2:14:07<9:58:23, 5.95s/it] {'loss': 0.4789, 'learning_rate': 1.0656679036475038e-05, 'epoch': 0.49} + 49%|████▉ | 5913/11952 [2:14:07<9:58:23, 5.95s/it] 49%|████▉ | 5914/11952 [2:14:13<10:10:42, 6.07s/it] {'loss': 0.4715, 'learning_rate': 1.065397495681805e-05, 'epoch': 0.49} + 49%|████▉ | 5914/11952 [2:14:13<10:10:42, 6.07s/it] 49%|████▉ | 5915/11952 [2:14:19<9:57:32, 5.94s/it] {'loss': 0.4669, 'learning_rate': 1.065127082913586e-05, 'epoch': 0.49} + 49%|████▉ | 5915/11952 [2:14:19<9:57:32, 5.94s/it] 49%|████▉ | 5916/11952 [2:14:24<9:49:11, 5.86s/it] {'loss': 0.4878, 'learning_rate': 1.0648566653627048e-05, 'epoch': 0.49} + 49%|████▉ | 5916/11952 [2:14:24<9:49:11, 5.86s/it] 50%|████▉ | 5917/11952 [2:14:30<9:46:23, 5.83s/it] {'loss': 0.4657, 'learning_rate': 1.06458624304902e-05, 'epoch': 0.5} + 50%|████▉ | 5917/11952 [2:14:30<9:46:23, 5.83s/it] 50%|████▉ | 5918/11952 [2:14:36<9:57:42, 5.94s/it] {'loss': 0.4867, 'learning_rate': 1.0643158159923902e-05, 'epoch': 0.5} + 50%|████▉ | 5918/11952 [2:14:36<9:57:42, 5.94s/it] 50%|████▉ | 5919/11952 [2:14:42<9:51:19, 5.88s/it] {'loss': 0.4842, 'learning_rate': 1.0640453842126742e-05, 'epoch': 0.5} + 50%|████▉ | 5919/11952 [2:14:42<9:51:19, 5.88s/it] 50%|████▉ | 5920/11952 [2:14:48<9:46:49, 5.84s/it] {'loss': 0.4846, 'learning_rate': 1.0637749477297317e-05, 'epoch': 0.5} + 50%|████▉ | 5920/11952 [2:14:48<9:46:49, 5.84s/it] 50%|████▉ | 5921/11952 [2:14:53<9:37:39, 5.75s/it] {'loss': 0.4753, 'learning_rate': 1.063504506563422e-05, 'epoch': 0.5} + 50%|████▉ | 5921/11952 [2:14:53<9:37:39, 5.75s/it] 50%|████▉ | 5922/11952 [2:14:59<9:34:24, 5.72s/it] {'loss': 0.4803, 'learning_rate': 1.0632340607336056e-05, 'epoch': 0.5} + 50%|████▉ | 5922/11952 [2:14:59<9:34:24, 5.72s/it] 50%|████▉ | 5923/11952 [2:15:05<9:33:57, 5.71s/it] {'loss': 0.4649, 'learning_rate': 1.062963610260143e-05, 'epoch': 0.5} + 50%|████▉ | 5923/11952 [2:15:05<9:33:57, 5.71s/it] 50%|████▉ | 5924/11952 [2:15:11<9:40:58, 5.78s/it] {'loss': 0.5102, 'learning_rate': 1.0626931551628948e-05, 'epoch': 0.5} + 50%|████▉ | 5924/11952 [2:15:11<9:40:58, 5.78s/it] 50%|████▉ | 5925/11952 [2:15:17<9:47:56, 5.85s/it] {'loss': 0.4758, 'learning_rate': 1.0624226954617221e-05, 'epoch': 0.5} + 50%|████▉ | 5925/11952 [2:15:17<9:47:56, 5.85s/it] 50%|████▉ | 5926/11952 [2:15:23<9:51:37, 5.89s/it] {'loss': 0.4701, 'learning_rate': 1.0621522311764857e-05, 'epoch': 0.5} + 50%|████▉ | 5926/11952 [2:15:23<9:51:37, 5.89s/it] 50%|████▉ | 5927/11952 [2:15:29<9:52:39, 5.90s/it] {'loss': 0.4919, 'learning_rate': 1.0618817623270484e-05, 'epoch': 0.5} + 50%|████▉ | 5927/11952 [2:15:29<9:52:39, 5.90s/it] 50%|████▉ | 5928/11952 [2:15:35<9:57:34, 5.95s/it] {'loss': 0.5002, 'learning_rate': 1.061611288933272e-05, 'epoch': 0.5} + 50%|████▉ | 5928/11952 [2:15:35<9:57:34, 5.95s/it] 50%|████▉ | 5929/11952 [2:15:41<10:00:23, 5.98s/it] {'loss': 0.4994, 'learning_rate': 1.0613408110150185e-05, 'epoch': 0.5} + 50%|████▉ | 5929/11952 [2:15:41<10:00:23, 5.98s/it] 50%|████▉ | 5930/11952 [2:15:46<9:55:21, 5.93s/it] {'loss': 0.4734, 'learning_rate': 1.061070328592151e-05, 'epoch': 0.5} + 50%|████▉ | 5930/11952 [2:15:46<9:55:21, 5.93s/it] 50%|████▉ | 5931/11952 [2:15:52<9:49:15, 5.87s/it] {'loss': 0.4737, 'learning_rate': 1.0607998416845329e-05, 'epoch': 0.5} + 50%|████▉ | 5931/11952 [2:15:52<9:49:15, 5.87s/it] 50%|████▉ | 5932/11952 [2:15:58<9:42:40, 5.81s/it] {'loss': 0.4695, 'learning_rate': 1.0605293503120268e-05, 'epoch': 0.5} + 50%|████▉ | 5932/11952 [2:15:58<9:42:40, 5.81s/it] 50%|████▉ | 5933/11952 [2:16:04<9:41:48, 5.80s/it] {'loss': 0.4705, 'learning_rate': 1.0602588544944972e-05, 'epoch': 0.5} + 50%|████▉ | 5933/11952 [2:16:04<9:41:48, 5.80s/it] 50%|████▉ | 5934/11952 [2:16:09<9:38:44, 5.77s/it] {'loss': 0.4683, 'learning_rate': 1.059988354251808e-05, 'epoch': 0.5} + 50%|████▉ | 5934/11952 [2:16:09<9:38:44, 5.77s/it] 50%|████▉ | 5935/11952 [2:16:15<9:45:48, 5.84s/it] {'loss': 0.4895, 'learning_rate': 1.059717849603824e-05, 'epoch': 0.5} + 50%|████▉ | 5935/11952 [2:16:15<9:45:48, 5.84s/it] 50%|████▉ | 5936/11952 [2:16:21<9:44:26, 5.83s/it] {'loss': 0.4732, 'learning_rate': 1.0594473405704088e-05, 'epoch': 0.5} + 50%|████▉ | 5936/11952 [2:16:21<9:44:26, 5.83s/it] 50%|████▉ | 5937/11952 [2:16:27<9:49:29, 5.88s/it] {'loss': 0.4844, 'learning_rate': 1.0591768271714285e-05, 'epoch': 0.5} + 50%|████▉ | 5937/11952 [2:16:27<9:49:29, 5.88s/it] 50%|████▉ | 5938/11952 [2:16:33<9:59:24, 5.98s/it] {'loss': 0.4746, 'learning_rate': 1.058906309426748e-05, 'epoch': 0.5} + 50%|████▉ | 5938/11952 [2:16:33<9:59:24, 5.98s/it] 50%|████▉ | 5939/11952 [2:16:39<9:55:33, 5.94s/it] {'loss': 0.4765, 'learning_rate': 1.0586357873562332e-05, 'epoch': 0.5} + 50%|████▉ | 5939/11952 [2:16:39<9:55:33, 5.94s/it] 50%|████▉ | 5940/11952 [2:16:45<10:00:56, 6.00s/it] {'loss': 0.4753, 'learning_rate': 1.0583652609797501e-05, 'epoch': 0.5} + 50%|████▉ | 5940/11952 [2:16:45<10:00:56, 6.00s/it] 50%|████▉ | 5941/11952 [2:16:51<9:50:18, 5.89s/it] {'loss': 0.4755, 'learning_rate': 1.0580947303171651e-05, 'epoch': 0.5} + 50%|████▉ | 5941/11952 [2:16:51<9:50:18, 5.89s/it] 50%|████▉ | 5942/11952 [2:16:57<9:45:52, 5.85s/it] {'loss': 0.4855, 'learning_rate': 1.0578241953883445e-05, 'epoch': 0.5} + 50%|████▉ | 5942/11952 [2:16:57<9:45:52, 5.85s/it] 50%|████▉ | 5943/11952 [2:17:03<9:48:21, 5.87s/it] {'loss': 0.4863, 'learning_rate': 1.0575536562131556e-05, 'epoch': 0.5} + 50%|████▉ | 5943/11952 [2:17:03<9:48:21, 5.87s/it] 50%|████▉ | 5944/11952 [2:17:09<9:47:27, 5.87s/it] {'loss': 0.4672, 'learning_rate': 1.0572831128114658e-05, 'epoch': 0.5} + 50%|████▉ | 5944/11952 [2:17:09<9:47:27, 5.87s/it] 50%|████▉ | 5945/11952 [2:17:14<9:41:23, 5.81s/it] {'loss': 0.4928, 'learning_rate': 1.0570125652031425e-05, 'epoch': 0.5} + 50%|████▉ | 5945/11952 [2:17:14<9:41:23, 5.81s/it] 50%|████▉ | 5946/11952 [2:17:20<9:40:57, 5.80s/it] {'loss': 0.4896, 'learning_rate': 1.0567420134080531e-05, 'epoch': 0.5} + 50%|████▉ | 5946/11952 [2:17:20<9:40:57, 5.80s/it] 50%|████▉ | 5947/11952 [2:17:26<9:36:55, 5.76s/it] {'loss': 0.4839, 'learning_rate': 1.0564714574460664e-05, 'epoch': 0.5} + 50%|████▉ | 5947/11952 [2:17:26<9:36:55, 5.76s/it] 50%|████▉ | 5948/11952 [2:17:31<9:35:31, 5.75s/it] {'loss': 0.4808, 'learning_rate': 1.0562008973370508e-05, 'epoch': 0.5} + 50%|████▉ | 5948/11952 [2:17:31<9:35:31, 5.75s/it] 50%|████▉ | 5949/11952 [2:17:37<9:35:24, 5.75s/it] {'loss': 0.4783, 'learning_rate': 1.0559303331008752e-05, 'epoch': 0.5} + 50%|████▉ | 5949/11952 [2:17:37<9:35:24, 5.75s/it]2 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +06 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... + 50%|████▉ | 5950/11952 [2:17:43<9:52:09, 5.92s/it]5 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4887, 'learning_rate': 1.0556597647574083e-05, 'epoch': 0.5} + 50%|████▉ | 5950/11952 [2:17:43<9:52:09, 5.92s/it] 50%|████▉ | 5951/11952 [2:17:50<9:56:31, 5.96s/it] {'loss': 0.4867, 'learning_rate': 1.05538919232652e-05, 'epoch': 0.5} + 50%|████▉ | 5951/11952 [2:17:50<9:56:31, 5.96s/it] 50%|████▉ | 5952/11952 [2:17:55<9:53:08, 5.93s/it] {'loss': 0.5122, 'learning_rate': 1.0551186158280795e-05, 'epoch': 0.5} + 50%|████▉ | 5952/11952 [2:17:55<9:53:08, 5.93s/it] 50%|████▉ | 5953/11952 [2:18:01<9:46:44, 5.87s/it] {'loss': 0.4623, 'learning_rate': 1.0548480352819573e-05, 'epoch': 0.5} + 50%|████▉ | 5953/11952 [2:18:01<9:46:44, 5.87s/it] 50%|████▉ | 5954/11952 [2:18:07<9:45:19, 5.86s/it] {'loss': 0.4677, 'learning_rate': 1.0545774507080237e-05, 'epoch': 0.5} + 50%|████▉ | 5954/11952 [2:18:07<9:45:19, 5.86s/it] 50%|████▉ | 5955/11952 [2:18:13<9:51:50, 5.92s/it] {'loss': 0.4772, 'learning_rate': 1.054306862126149e-05, 'epoch': 0.5} + 50%|████▉ | 5955/11952 [2:18:13<9:51:50, 5.92s/it] 50%|████▉ | 5956/11952 [2:18:19<9:52:07, 5.93s/it] {'loss': 0.4747, 'learning_rate': 1.0540362695562043e-05, 'epoch': 0.5} + 50%|████▉ | 5956/11952 [2:18:19<9:52:07, 5.93s/it] 50%|████▉ | 5957/11952 [2:18:25<9:46:15, 5.87s/it] {'loss': 0.4751, 'learning_rate': 1.0537656730180606e-05, 'epoch': 0.5} + 50%|████▉ | 5957/11952 [2:18:25<9:46:15, 5.87s/it] 50%|████▉ | 5958/11952 [2:18:30<9:42:56, 5.84s/it] {'loss': 0.4904, 'learning_rate': 1.0534950725315893e-05, 'epoch': 0.5} + 50%|████▉ | 5958/11952 [2:18:30<9:42:56, 5.84s/it] 50%|████▉ | 5959/11952 [2:18:36<9:43:52, 5.85s/it] {'loss': 0.4845, 'learning_rate': 1.0532244681166628e-05, 'epoch': 0.5} + 50%|████▉ | 5959/11952 [2:18:36<9:43:52, 5.85s/it] 50%|████▉ | 5960/11952 [2:18:42<9:46:25, 5.87s/it] {'loss': 0.4788, 'learning_rate': 1.0529538597931524e-05, 'epoch': 0.5} + 50%|████▉ | 5960/11952 [2:18:42<9:46:25, 5.87s/it] 50%|████▉ | 5961/11952 [2:18:48<9:44:30, 5.85s/it] {'loss': 0.4771, 'learning_rate': 1.052683247580931e-05, 'epoch': 0.5} + 50%|████▉ | 5961/11952 [2:18:48<9:44:30, 5.85s/it] 50%|████▉ | 5962/11952 [2:18:54<9:41:54, 5.83s/it] {'loss': 0.4895, 'learning_rate': 1.0524126314998711e-05, 'epoch': 0.5} + 50%|████▉ | 5962/11952 [2:18:54<9:41:54, 5.83s/it] 50%|████▉ | 5963/11952 [2:19:00<9:39:20, 5.80s/it] {'loss': 0.4743, 'learning_rate': 1.0521420115698448e-05, 'epoch': 0.5} + 50%|████▉ | 5963/11952 [2:19:00<9:39:20, 5.80s/it] 50%|████▉ | 5964/11952 [2:19:06<9:44:23, 5.86s/it] {'loss': 0.4543, 'learning_rate': 1.0518713878107268e-05, 'epoch': 0.5} + 50%|████▉ | 5964/11952 [2:19:06<9:44:23, 5.86s/it] 50%|████▉ | 5965/11952 [2:19:12<9:56:26, 5.98s/it] {'loss': 0.4893, 'learning_rate': 1.0516007602423896e-05, 'epoch': 0.5} + 50%|████▉ | 5965/11952 [2:19:12<9:56:26, 5.98s/it] 50%|████▉ | 5966/11952 [2:19:18<9:54:57, 5.96s/it] {'loss': 0.4831, 'learning_rate': 1.0513301288847076e-05, 'epoch': 0.5} + 50%|████▉ | 5966/11952 [2:19:18<9:54:57, 5.96s/it] 50%|████▉ | 5967/11952 [2:19:23<9:44:33, 5.86s/it] {'loss': 0.4739, 'learning_rate': 1.0510594937575537e-05, 'epoch': 0.5} + 50%|████▉ | 5967/11952 [2:19:23<9:44:33, 5.86s/it] 50%|████▉ | 5968/11952 [2:19:29<9:51:41, 5.93s/it] {'loss': 0.4901, 'learning_rate': 1.0507888548808034e-05, 'epoch': 0.5} + 50%|████▉ | 5968/11952 [2:19:29<9:51:41, 5.93s/it] 50%|████▉ | 5969/11952 [2:19:35<9:53:55, 5.96s/it] {'loss': 0.4903, 'learning_rate': 1.0505182122743309e-05, 'epoch': 0.5} + 50%|████▉ | 5969/11952 [2:19:35<9:53:55, 5.96s/it] 50%|████▉ | 5970/11952 [2:19:42<9:57:43, 6.00s/it] {'loss': 0.4827, 'learning_rate': 1.0502475659580107e-05, 'epoch': 0.5} + 50%|████▉ | 5970/11952 [2:19:42<9:57:43, 6.00s/it] 50%|████▉ | 5971/11952 [2:19:48<10:05:22, 6.07s/it] {'loss': 0.4875, 'learning_rate': 1.0499769159517186e-05, 'epoch': 0.5} + 50%|████▉ | 5971/11952 [2:19:48<10:05:22, 6.07s/it] 50%|████▉ | 5972/11952 [2:19:53<9:51:07, 5.93s/it] {'loss': 0.4978, 'learning_rate': 1.0497062622753296e-05, 'epoch': 0.5} + 50%|████▉ | 5972/11952 [2:19:53<9:51:07, 5.93s/it] 50%|████▉ | 5973/11952 [2:19:59<9:42:32, 5.85s/it] {'loss': 0.4832, 'learning_rate': 1.049435604948719e-05, 'epoch': 0.5} + 50%|████▉ | 5973/11952 [2:19:59<9:42:32, 5.85s/it] 50%|████▉ | 5974/11952 [2:20:05<9:40:54, 5.83s/it] {'loss': 0.4586, 'learning_rate': 1.0491649439917636e-05, 'epoch': 0.5} + 50%|████▉ | 5974/11952 [2:20:05<9:40:54, 5.83s/it] 50%|████▉ | 5975/11952 [2:20:11<9:44:25, 5.87s/it] {'loss': 0.4639, 'learning_rate': 1.0488942794243393e-05, 'epoch': 0.5} + 50%|████▉ | 5975/11952 [2:20:11<9:44:25, 5.87s/it] 50%|█████ | 5976/11952 [2:20:17<9:53:28, 5.96s/it] {'loss': 0.4936, 'learning_rate': 1.0486236112663224e-05, 'epoch': 0.5} + 50%|█████ | 5976/11952 [2:20:17<9:53:28, 5.96s/it] 50%|█████ | 5977/11952 [2:20:23<9:41:59, 5.84s/it] {'loss': 0.4603, 'learning_rate': 1.0483529395375896e-05, 'epoch': 0.5} + 50%|█████ | 5977/11952 [2:20:23<9:41:59, 5.84s/it] 50%|█████ | 5978/11952 [2:20:28<9:42:04, 5.85s/it] {'loss': 0.4836, 'learning_rate': 1.0480822642580178e-05, 'epoch': 0.5} + 50%|█████ | 5978/11952 [2:20:28<9:42:04, 5.85s/it] 50%|█████ | 5979/11952 [2:20:34<9:43:15, 5.86s/it] {'loss': 0.5113, 'learning_rate': 1.0478115854474848e-05, 'epoch': 0.5} + 50%|█████ | 5979/11952 [2:20:34<9:43:15, 5.86s/it] 50%|█████ | 5980/11952 [2:20:40<9:38:56, 5.82s/it] {'loss': 0.4747, 'learning_rate': 1.0475409031258678e-05, 'epoch': 0.5} + 50%|█████ | 5980/11952 [2:20:40<9:38:56, 5.82s/it] 50%|█████ | 5981/11952 [2:20:46<9:38:41, 5.82s/it] {'loss': 0.4841, 'learning_rate': 1.0472702173130447e-05, 'epoch': 0.5} + 50%|█████ | 5981/11952 [2:20:46<9:38:41, 5.82s/it] 50%|█████ | 5982/11952 [2:20:51<9:31:51, 5.75s/it] {'loss': 0.4726, 'learning_rate': 1.0469995280288936e-05, 'epoch': 0.5} + 50%|█████ | 5982/11952 [2:20:51<9:31:51, 5.75s/it] 50%|█████ | 5983/11952 [2:20:57<9:30:55, 5.74s/it] {'loss': 0.47, 'learning_rate': 1.0467288352932923e-05, 'epoch': 0.5} + 50%|█████ | 5983/11952 [2:20:57<9:30:55, 5.74s/it] 50%|█████ | 5984/11952 [2:21:03<9:33:48, 5.77s/it] {'loss': 0.4819, 'learning_rate': 1.0464581391261198e-05, 'epoch': 0.5} + 50%|█████ | 5984/11952 [2:21:03<9:33:48, 5.77s/it] 50%|█████ | 5985/11952 [2:21:09<9:37:10, 5.80s/it] {'loss': 0.4767, 'learning_rate': 1.0461874395472549e-05, 'epoch': 0.5} + 50%|█████ | 5985/11952 [2:21:09<9:37:10, 5.80s/it] 50%|█████ | 5986/11952 [2:21:15<9:42:29, 5.86s/it] {'loss': 0.4681, 'learning_rate': 1.0459167365765765e-05, 'epoch': 0.5} + 50%|█████ | 5986/11952 [2:21:15<9:42:29, 5.86s/it] 50%|█████ | 5987/11952 [2:21:21<9:39:50, 5.83s/it] {'loss': 0.4776, 'learning_rate': 1.0456460302339636e-05, 'epoch': 0.5} + 50%|█████ | 5987/11952 [2:21:21<9:39:50, 5.83s/it] 50%|█████ | 5988/11952 [2:21:26<9:40:10, 5.84s/it] {'loss': 0.4719, 'learning_rate': 1.0453753205392967e-05, 'epoch': 0.5} + 50%|█████ | 5988/11952 [2:21:26<9:40:10, 5.84s/it] 50%|█████ | 5989/11952 [2:21:32<9:39:15, 5.83s/it] {'loss': 0.4728, 'learning_rate': 1.0451046075124544e-05, 'epoch': 0.5} + 50%|█████ | 5989/11952 [2:21:32<9:39:15, 5.83s/it] 50%|█████ | 5990/11952 [2:21:38<9:40:32, 5.84s/it] {'loss': 0.4883, 'learning_rate': 1.0448338911733178e-05, 'epoch': 0.5} + 50%|█████ | 5990/11952 [2:21:38<9:40:32, 5.84s/it] 50%|█████ | 5991/11952 [2:21:44<9:41:34, 5.85s/it] {'loss': 0.5035, 'learning_rate': 1.0445631715417666e-05, 'epoch': 0.5} + 50%|█████ | 5991/11952 [2:21:44<9:41:34, 5.85s/it] 50%|█████ | 5992/11952 [2:21:50<9:54:47, 5.99s/it] {'loss': 0.4744, 'learning_rate': 1.0442924486376813e-05, 'epoch': 0.5} + 50%|█████ | 5992/11952 [2:21:50<9:54:47, 5.99s/it] 50%|█████ | 5993/11952 [2:21:56<9:51:47, 5.96s/it] {'loss': 0.498, 'learning_rate': 1.0440217224809427e-05, 'epoch': 0.5} + 50%|█████ | 5993/11952 [2:21:56<9:51:47, 5.96s/it] 50%|█████ | 5994/11952 [2:22:02<9:43:30, 5.88s/it] {'loss': 0.4707, 'learning_rate': 1.043750993091432e-05, 'epoch': 0.5} + 50%|█████ | 5994/11952 [2:22:02<9:43:30, 5.88s/it] 50%|█████ | 5995/11952 [2:22:08<9:54:39, 5.99s/it] {'loss': 0.4854, 'learning_rate': 1.0434802604890306e-05, 'epoch': 0.5} + 50%|█████ | 5995/11952 [2:22:08<9:54:39, 5.99s/it] 50%|█████ | 5996/11952 [2:22:14<9:56:52, 6.01s/it] {'loss': 0.4768, 'learning_rate': 1.0432095246936195e-05, 'epoch': 0.5} + 50%|█████ | 5996/11952 [2:22:14<9:56:52, 6.01s/it] 50%|█████ | 5997/11952 [2:22:20<9:46:32, 5.91s/it] {'loss': 0.4729, 'learning_rate': 1.0429387857250806e-05, 'epoch': 0.5} + 50%|█████ | 5997/11952 [2:22:20<9:46:32, 5.91s/it] 50%|█████ | 5998/11952 [2:22:26<9:52:52, 5.97s/it] {'loss': 0.483, 'learning_rate': 1.042668043603296e-05, 'epoch': 0.5} + 50%|█████ | 5998/11952 [2:22:26<9:52:52, 5.97s/it] 50%|█████ | 5999/11952 [2:22:32<10:01:23, 6.06s/it] {'loss': 0.4757, 'learning_rate': 1.0423972983481477e-05, 'epoch': 0.5} + 50%|█████ | 5999/11952 [2:22:32<10:01:23, 6.06s/it]4 AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... +71 AutoResumeHook: Checking whether to suspend... +AutoResumeHook: Checking whether to suspend... +03 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... + 50%|█████ | 6000/11952 [2:22:38<9:52:18, 5.97s/it] 5 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4865, 'learning_rate': 1.0421265499795181e-05, 'epoch': 0.5} + 50%|█████ | 6000/11952 [2:22:38<9:52:18, 5.97s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-6000/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-6000/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/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( + 50%|█████ | 6001/11952 [2:23:07<21:21:51, 12.92s/it] {'loss': 0.4946, 'learning_rate': 1.0418557985172899e-05, 'epoch': 0.5} + 50%|█████ | 6001/11952 [2:23:07<21:21:51, 12.92s/it] 50%|█████ | 6002/11952 [2:23:13<17:55:26, 10.84s/it] {'loss': 0.4533, 'learning_rate': 1.0415850439813462e-05, 'epoch': 0.5} + 50%|█████ | 6002/11952 [2:23:13<17:55:26, 10.84s/it] 50%|█████ | 6003/11952 [2:23:19<15:22:13, 9.30s/it] {'loss': 0.4847, 'learning_rate': 1.0413142863915695e-05, 'epoch': 0.5} + 50%|█████ | 6003/11952 [2:23:19<15:22:13, 9.30s/it] 50%|█████ | 6004/11952 [2:23:25<13:39:19, 8.26s/it] {'loss': 0.4828, 'learning_rate': 1.0410435257678433e-05, 'epoch': 0.5} + 50%|█████ | 6004/11952 [2:23:25<13:39:19, 8.26s/it] 50%|█████ | 6005/11952 [2:23:30<12:20:46, 7.47s/it] {'loss': 0.4671, 'learning_rate': 1.0407727621300516e-05, 'epoch': 0.5} + 50%|█████ | 6005/11952 [2:23:30<12:20:46, 7.47s/it] 50%|█████ | 6006/11952 [2:23:36<11:29:48, 6.96s/it] {'loss': 0.4716, 'learning_rate': 1.0405019954980779e-05, 'epoch': 0.5} + 50%|█████ | 6006/11952 [2:23:36<11:29:48, 6.96s/it] 50%|█████ | 6007/11952 [2:23:42<10:52:26, 6.58s/it] {'loss': 0.4786, 'learning_rate': 1.0402312258918061e-05, 'epoch': 0.5} + 50%|█████ | 6007/11952 [2:23:42<10:52:26, 6.58s/it] 50%|█████ | 6008/11952 [2:23:48<10:41:16, 6.47s/it] {'loss': 0.4873, 'learning_rate': 1.03996045333112e-05, 'epoch': 0.5} + 50%|█████ | 6008/11952 [2:23:48<10:41:16, 6.47s/it] 50%|█████ | 6009/11952 [2:23:54<10:29:34, 6.36s/it] {'loss': 0.479, 'learning_rate': 1.0396896778359047e-05, 'epoch': 0.5} + 50%|█████ | 6009/11952 [2:23:54<10:29:34, 6.36s/it] 50%|█████ | 6010/11952 [2:24:00<10:12:49, 6.19s/it] {'loss': 0.463, 'learning_rate': 1.0394188994260445e-05, 'epoch': 0.5} + 50%|█████ | 6010/11952 [2:24:00<10:12:49, 6.19s/it] 50%|█████ | 6011/11952 [2:24:06<10:04:28, 6.10s/it] {'loss': 0.4551, 'learning_rate': 1.0391481181214244e-05, 'epoch': 0.5} + 50%|█████ | 6011/11952 [2:24:06<10:04:28, 6.10s/it] 50%|█████ | 6012/11952 [2:24:11<9:50:02, 5.96s/it] {'loss': 0.4634, 'learning_rate': 1.0388773339419294e-05, 'epoch': 0.5} + 50%|█████ | 6012/11952 [2:24:11<9:50:02, 5.96s/it] 50%|█████ | 6013/11952 [2:24:18<9:56:59, 6.03s/it] {'loss': 0.4834, 'learning_rate': 1.0386065469074447e-05, 'epoch': 0.5} + 50%|█████ | 6013/11952 [2:24:18<9:56:59, 6.03s/it] 50%|█████ | 6014/11952 [2:24:24<9:59:47, 6.06s/it] {'loss': 0.4901, 'learning_rate': 1.0383357570378553e-05, 'epoch': 0.5} + 50%|█████ | 6014/11952 [2:24:24<9:59:47, 6.06s/it] 50%|█████ | 6015/11952 [2:24:30<9:50:03, 5.96s/it] {'loss': 0.4779, 'learning_rate': 1.0380649643530476e-05, 'epoch': 0.5} + 50%|█████ | 6015/11952 [2:24:30<9:50:03, 5.96s/it] 50%|█████ | 6016/11952 [2:24:35<9:50:21, 5.97s/it] {'loss': 0.4925, 'learning_rate': 1.0377941688729074e-05, 'epoch': 0.5} + 50%|█████ | 6016/11952 [2:24:35<9:50:21, 5.97s/it] 50%|█████ | 6017/11952 [2:24:42<10:03:02, 6.10s/it] {'loss': 0.4912, 'learning_rate': 1.0375233706173207e-05, 'epoch': 0.5} + 50%|█████ | 6017/11952 [2:24:42<10:03:02, 6.10s/it] 50%|█████ | 6018/11952 [2:24:48<10:05:12, 6.12s/it] {'loss': 0.4781, 'learning_rate': 1.0372525696061735e-05, 'epoch': 0.5} + 50%|█████ | 6018/11952 [2:24:48<10:05:12, 6.12s/it] 50%|█████ | 6019/11952 [2:24:54<9:50:04, 5.97s/it] {'loss': 0.4854, 'learning_rate': 1.0369817658593524e-05, 'epoch': 0.5} + 50%|█████ | 6019/11952 [2:24:54<9:50:04, 5.97s/it] 50%|█████ | 6020/11952 [2:25:00<9:48:16, 5.95s/it] {'loss': 0.4858, 'learning_rate': 1.0367109593967445e-05, 'epoch': 0.5} + 50%|█████ | 6020/11952 [2:25:00<9:48:16, 5.95s/it] 50%|█████ | 6021/11952 [2:25:06<9:47:25, 5.94s/it] {'loss': 0.4811, 'learning_rate': 1.0364401502382364e-05, 'epoch': 0.5} + 50%|█████ | 6021/11952 [2:25:06<9:47:25, 5.94s/it] 50%|█████ | 6022/11952 [2:25:11<9:43:59, 5.91s/it] {'loss': 0.4865, 'learning_rate': 1.0361693384037154e-05, 'epoch': 0.5} + 50%|█████ | 6022/11952 [2:25:11<9:43:59, 5.91s/it] 50%|█████ | 6023/11952 [2:25:17<9:41:23, 5.88s/it] {'loss': 0.4867, 'learning_rate': 1.0358985239130685e-05, 'epoch': 0.5} + 50%|█████ | 6023/11952 [2:25:17<9:41:23, 5.88s/it] 50%|█████ | 6024/11952 [2:25:23<9:44:38, 5.92s/it] {'loss': 0.4796, 'learning_rate': 1.035627706786183e-05, 'epoch': 0.5} + 50%|█████ | 6024/11952 [2:25:23<9:44:38, 5.92s/it] 50%|█████ | 6025/11952 [2:25:29<9:40:47, 5.88s/it] {'loss': 0.486, 'learning_rate': 1.035356887042947e-05, 'epoch': 0.5} + 50%|█████ | 6025/11952 [2:25:29<9:40:47, 5.88s/it] 50%|█████ | 6026/11952 [2:25:35<9:49:56, 5.97s/it] {'loss': 0.4733, 'learning_rate': 1.0350860647032488e-05, 'epoch': 0.5} + 50%|█████ | 6026/11952 [2:25:35<9:49:56, 5.97s/it] 50%|█████ | 6027/11952 [2:25:41<9:50:18, 5.98s/it] {'loss': 0.4706, 'learning_rate': 1.0348152397869757e-05, 'epoch': 0.5} + 50%|█████ | 6027/11952 [2:25:41<9:50:18, 5.98s/it] 50%|█████ | 6028/11952 [2:25:47<9:42:49, 5.90s/it] {'loss': 0.4709, 'learning_rate': 1.0345444123140159e-05, 'epoch': 0.5} + 50%|█████ | 6028/11952 [2:25:47<9:42:49, 5.90s/it] 50%|█████ | 6029/11952 [2:25:52<9:34:45, 5.82s/it] {'loss': 0.4718, 'learning_rate': 1.0342735823042585e-05, 'epoch': 0.5} + 50%|█████ | 6029/11952 [2:25:52<9:34:45, 5.82s/it] 50%|█████ | 6030/11952 [2:25:58<9:36:00, 5.84s/it] {'loss': 0.476, 'learning_rate': 1.0340027497775915e-05, 'epoch': 0.5} + 50%|█████ | 6030/11952 [2:25:58<9:36:00, 5.84s/it] 50%|█████ | 6031/11952 [2:26:04<9:42:38, 5.90s/it] {'loss': 0.4838, 'learning_rate': 1.0337319147539042e-05, 'epoch': 0.5} + 50%|█████ | 6031/11952 [2:26:04<9:42:38, 5.90s/it] 50%|█████ | 6032/11952 [2:26:11<9:49:41, 5.98s/it] {'loss': 0.4914, 'learning_rate': 1.0334610772530851e-05, 'epoch': 0.5} + 50%|█████ | 6032/11952 [2:26:11<9:49:41, 5.98s/it] 50%|█████ | 6033/11952 [2:26:16<9:40:31, 5.88s/it] {'loss': 0.4516, 'learning_rate': 1.033190237295024e-05, 'epoch': 0.5} + 50%|█████ | 6033/11952 [2:26:16<9:40:31, 5.88s/it] 50%|█████ | 6034/11952 [2:26:22<9:41:00, 5.89s/it] {'loss': 0.4834, 'learning_rate': 1.0329193948996097e-05, 'epoch': 0.5} + 50%|█████ | 6034/11952 [2:26:22<9:41:00, 5.89s/it] 50%|█████ | 6035/11952 [2:26:28<9:42:04, 5.90s/it] {'loss': 0.4735, 'learning_rate': 1.0326485500867316e-05, 'epoch': 0.5} + 50%|█████ | 6035/11952 [2:26:28<9:42:04, 5.90s/it] 51%|█████ | 6036/11952 [2:26:34<9:40:24, 5.89s/it] {'loss': 0.4786, 'learning_rate': 1.0323777028762804e-05, 'epoch': 0.5} + 51%|█████ | 6036/11952 [2:26:34<9:40:24, 5.89s/it] 51%|█████ | 6037/11952 [2:26:40<9:31:24, 5.80s/it] {'loss': 0.4708, 'learning_rate': 1.0321068532881454e-05, 'epoch': 0.51} + 51%|█████ | 6037/11952 [2:26:40<9:31:24, 5.80s/it] 51%|█████ | 6038/11952 [2:26:45<9:34:20, 5.83s/it] {'loss': 0.5103, 'learning_rate': 1.0318360013422162e-05, 'epoch': 0.51} + 51%|█████ | 6038/11952 [2:26:45<9:34:20, 5.83s/it] 51%|█████ | 6039/11952 [2:26:51<9:32:10, 5.81s/it] {'loss': 0.5011, 'learning_rate': 1.0315651470583836e-05, 'epoch': 0.51} + 51%|█████ | 6039/11952 [2:26:51<9:32:10, 5.81s/it] 51%|█████ | 6040/11952 [2:26:57<9:35:28, 5.84s/it] {'loss': 0.4685, 'learning_rate': 1.0312942904565379e-05, 'epoch': 0.51} + 51%|█████ | 6040/11952 [2:26:57<9:35:28, 5.84s/it] 51%|█████ | 6041/11952 [2:27:03<9:46:46, 5.96s/it] {'loss': 0.4897, 'learning_rate': 1.0310234315565699e-05, 'epoch': 0.51} + 51%|█████ | 6041/11952 [2:27:03<9:46:46, 5.96s/it] 51%|█████ | 6042/11952 [2:27:09<9:35:45, 5.85s/it] {'loss': 0.489, 'learning_rate': 1.0307525703783698e-05, 'epoch': 0.51} + 51%|█████ | 6042/11952 [2:27:09<9:35:45, 5.85s/it] 51%|█████ | 6043/11952 [2:27:15<9:50:05, 5.99s/it] {'loss': 0.4754, 'learning_rate': 1.0304817069418292e-05, 'epoch': 0.51} + 51%|█████ | 6043/11952 [2:27:15<9:50:05, 5.99s/it] 51%|█████ | 6044/11952 [2:27:21<9:45:13, 5.94s/it] {'loss': 0.4889, 'learning_rate': 1.0302108412668387e-05, 'epoch': 0.51} + 51%|█████ | 6044/11952 [2:27:21<9:45:13, 5.94s/it] 51%|█████ | 6045/11952 [2:27:27<9:46:43, 5.96s/it] {'loss': 0.4967, 'learning_rate': 1.0299399733732893e-05, 'epoch': 0.51} + 51%|█████ | 6045/11952 [2:27:27<9:46:43, 5.96s/it] 51%|█████ | 6046/11952 [2:27:33<9:42:53, 5.92s/it] {'loss': 0.4701, 'learning_rate': 1.029669103281073e-05, 'epoch': 0.51} + 51%|█████ | 6046/11952 [2:27:33<9:42:53, 5.92s/it] 51%|█████ | 6047/11952 [2:27:39<9:44:37, 5.94s/it] {'loss': 0.4751, 'learning_rate': 1.0293982310100814e-05, 'epoch': 0.51} + 51%|█████ | 6047/11952 [2:27:39<9:44:37, 5.94s/it] 51%|█████ | 6048/11952 [2:27:45<9:41:47, 5.91s/it] {'loss': 0.4912, 'learning_rate': 1.0291273565802058e-05, 'epoch': 0.51} + 51%|█████ | 6048/11952 [2:27:45<9:41:47, 5.91s/it] 51%|█████ | 6049/11952 [2:27:50<9:30:21, 5.80s/it] {'loss': 0.4817, 'learning_rate': 1.0288564800113383e-05, 'epoch': 0.51} + 51%|█████ | 6049/11952 [2:27:50<9:30:21, 5.80s/it]02 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +AutoResumeHook: Checking whether to suspend... + 51%|█████ | 6050/11952 [2:27:56<9:22:35, 5.72s/it]7 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4599, 'learning_rate': 1.0285856013233708e-05, 'epoch': 0.51} + 51%|█████ | 6050/11952 [2:27:56<9:22:35, 5.72s/it] 51%|█████ | 6051/11952 [2:28:02<9:25:17, 5.75s/it] {'loss': 0.4964, 'learning_rate': 1.0283147205361959e-05, 'epoch': 0.51} + 51%|█████ | 6051/11952 [2:28:02<9:25:17, 5.75s/it] 51%|█████ | 6052/11952 [2:28:08<9:32:12, 5.82s/it] {'loss': 0.4632, 'learning_rate': 1.0280438376697056e-05, 'epoch': 0.51} + 51%|█████ | 6052/11952 [2:28:08<9:32:12, 5.82s/it] 51%|█████ | 6053/11952 [2:28:13<9:33:37, 5.83s/it] {'loss': 0.463, 'learning_rate': 1.0277729527437924e-05, 'epoch': 0.51} + 51%|█████ | 6053/11952 [2:28:13<9:33:37, 5.83s/it] 51%|█████ | 6054/11952 [2:28:19<9:32:21, 5.82s/it] {'loss': 0.493, 'learning_rate': 1.0275020657783492e-05, 'epoch': 0.51} + 51%|█████ | 6054/11952 [2:28:19<9:32:21, 5.82s/it] 51%|█████ | 6055/11952 [2:28:25<9:41:44, 5.92s/it] {'loss': 0.4833, 'learning_rate': 1.0272311767932686e-05, 'epoch': 0.51} + 51%|█████ | 6055/11952 [2:28:25<9:41:44, 5.92s/it] 51%|█████ | 6056/11952 [2:28:31<9:34:14, 5.84s/it] {'loss': 0.4912, 'learning_rate': 1.0269602858084435e-05, 'epoch': 0.51} + 51%|█████ | 6056/11952 [2:28:31<9:34:14, 5.84s/it] 51%|█████ | 6057/11952 [2:28:37<9:34:24, 5.85s/it] {'loss': 0.481, 'learning_rate': 1.0266893928437673e-05, 'epoch': 0.51} + 51%|█████ | 6057/11952 [2:28:37<9:34:24, 5.85s/it] 51%|█████ | 6058/11952 [2:28:43<9:42:30, 5.93s/it] {'loss': 0.4745, 'learning_rate': 1.0264184979191331e-05, 'epoch': 0.51} + 51%|█████ | 6058/11952 [2:28:43<9:42:30, 5.93s/it] 51%|█████ | 6059/11952 [2:28:49<9:38:47, 5.89s/it] {'loss': 0.4958, 'learning_rate': 1.0261476010544345e-05, 'epoch': 0.51} + 51%|█████ | 6059/11952 [2:28:49<9:38:47, 5.89s/it] 51%|█████ | 6060/11952 [2:28:55<9:38:41, 5.89s/it] {'loss': 0.491, 'learning_rate': 1.0258767022695645e-05, 'epoch': 0.51} + 51%|█████ | 6060/11952 [2:28:55<9:38:41, 5.89s/it] 51%|█████ | 6061/11952 [2:29:01<9:43:20, 5.94s/it] {'loss': 0.4881, 'learning_rate': 1.0256058015844173e-05, 'epoch': 0.51} + 51%|█████ | 6061/11952 [2:29:01<9:43:20, 5.94s/it] 51%|█████ | 6062/11952 [2:29:06<9:32:31, 5.83s/it] {'loss': 0.4736, 'learning_rate': 1.0253348990188863e-05, 'epoch': 0.51} + 51%|█████ | 6062/11952 [2:29:06<9:32:31, 5.83s/it] 51%|█████ | 6063/11952 [2:29:12<9:25:00, 5.76s/it] {'loss': 0.4744, 'learning_rate': 1.025063994592866e-05, 'epoch': 0.51} + 51%|█████ | 6063/11952 [2:29:12<9:25:00, 5.76s/it] 51%|█████ | 6064/11952 [2:29:18<9:27:13, 5.78s/it] {'loss': 0.4759, 'learning_rate': 1.02479308832625e-05, 'epoch': 0.51} + 51%|█████ | 6064/11952 [2:29:18<9:27:13, 5.78s/it] 51%|█████ | 6065/11952 [2:29:24<9:40:48, 5.92s/it] {'loss': 0.4655, 'learning_rate': 1.0245221802389328e-05, 'epoch': 0.51} + 51%|█████ | 6065/11952 [2:29:24<9:40:48, 5.92s/it] 51%|█████ | 6066/11952 [2:29:30<9:33:59, 5.85s/it] {'loss': 0.4912, 'learning_rate': 1.0242512703508085e-05, 'epoch': 0.51} + 51%|█████ | 6066/11952 [2:29:30<9:33:59, 5.85s/it] 51%|█████ | 6067/11952 [2:29:36<9:34:38, 5.86s/it] {'loss': 0.4852, 'learning_rate': 1.023980358681772e-05, 'epoch': 0.51} + 51%|█████ | 6067/11952 [2:29:36<9:34:38, 5.86s/it] 51%|█████ | 6068/11952 [2:29:42<9:37:58, 5.89s/it] {'loss': 0.4838, 'learning_rate': 1.0237094452517178e-05, 'epoch': 0.51} + 51%|█████ | 6068/11952 [2:29:42<9:37:58, 5.89s/it] 51%|█████ | 6069/11952 [2:29:48<9:39:52, 5.91s/it] {'loss': 0.4851, 'learning_rate': 1.0234385300805403e-05, 'epoch': 0.51} + 51%|█████ | 6069/11952 [2:29:48<9:39:52, 5.91s/it] 51%|█████ | 6070/11952 [2:29:53<9:33:04, 5.85s/it] {'loss': 0.4732, 'learning_rate': 1.0231676131881348e-05, 'epoch': 0.51} + 51%|█████ | 6070/11952 [2:29:53<9:33:04, 5.85s/it] 51%|█████ | 6071/11952 [2:30:00<9:50:33, 6.03s/it] {'loss': 0.4902, 'learning_rate': 1.022896694594396e-05, 'epoch': 0.51} + 51%|█████ | 6071/11952 [2:30:00<9:50:33, 6.03s/it] 51%|█████ | 6072/11952 [2:30:06<9:49:01, 6.01s/it] {'loss': 0.4603, 'learning_rate': 1.022625774319219e-05, 'epoch': 0.51} + 51%|█████ | 6072/11952 [2:30:06<9:49:01, 6.01s/it] 51%|█████ | 6073/11952 [2:30:11<9:40:23, 5.92s/it] {'loss': 0.4785, 'learning_rate': 1.0223548523824996e-05, 'epoch': 0.51} + 51%|█████ | 6073/11952 [2:30:11<9:40:23, 5.92s/it] 51%|█████ | 6074/11952 [2:30:17<9:30:47, 5.83s/it] {'loss': 0.4651, 'learning_rate': 1.0220839288041328e-05, 'epoch': 0.51} + 51%|█████ | 6074/11952 [2:30:17<9:30:47, 5.83s/it] 51%|█████ | 6075/11952 [2:30:23<9:28:03, 5.80s/it] {'loss': 0.4707, 'learning_rate': 1.021813003604014e-05, 'epoch': 0.51} + 51%|█████ | 6075/11952 [2:30:23<9:28:03, 5.80s/it] 51%|█████ | 6076/11952 [2:30:29<9:28:04, 5.80s/it] {'loss': 0.5073, 'learning_rate': 1.0215420768020388e-05, 'epoch': 0.51} + 51%|█████ | 6076/11952 [2:30:29<9:28:04, 5.80s/it] 51%|█████ | 6077/11952 [2:30:35<9:42:13, 5.95s/it] {'loss': 0.4872, 'learning_rate': 1.0212711484181034e-05, 'epoch': 0.51} + 51%|█████ | 6077/11952 [2:30:35<9:42:13, 5.95s/it] 51%|█████ | 6078/11952 [2:30:41<9:37:57, 5.90s/it] {'loss': 0.4836, 'learning_rate': 1.0210002184721033e-05, 'epoch': 0.51} + 51%|█████ | 6078/11952 [2:30:41<9:37:57, 5.90s/it] 51%|█████ | 6079/11952 [2:30:46<9:29:13, 5.82s/it] {'loss': 0.46, 'learning_rate': 1.0207292869839343e-05, 'epoch': 0.51} + 51%|█████ | 6079/11952 [2:30:46<9:29:13, 5.82s/it] 51%|█████ | 6080/11952 [2:30:52<9:24:00, 5.76s/it] {'loss': 0.4641, 'learning_rate': 1.020458353973493e-05, 'epoch': 0.51} + 51%|█████ | 6080/11952 [2:30:52<9:24:00, 5.76s/it] 51%|█████ | 6081/11952 [2:30:58<9:23:45, 5.76s/it] {'loss': 0.4703, 'learning_rate': 1.0201874194606748e-05, 'epoch': 0.51} + 51%|█████ | 6081/11952 [2:30:58<9:23:45, 5.76s/it] 51%|█████ | 6082/11952 [2:31:03<9:21:42, 5.74s/it] {'loss': 0.4775, 'learning_rate': 1.019916483465377e-05, 'epoch': 0.51} + 51%|█████ | 6082/11952 [2:31:03<9:21:42, 5.74s/it] 51%|█████ | 6083/11952 [2:31:09<9:20:14, 5.73s/it] {'loss': 0.4857, 'learning_rate': 1.019645546007495e-05, 'epoch': 0.51} + 51%|█████ | 6083/11952 [2:31:09<9:20:14, 5.73s/it] 51%|█████ | 6084/11952 [2:31:15<9:19:28, 5.72s/it] {'loss': 0.4703, 'learning_rate': 1.0193746071069262e-05, 'epoch': 0.51} + 51%|█████ | 6084/11952 [2:31:15<9:19:28, 5.72s/it] 51%|█████ | 6085/11952 [2:31:21<9:24:23, 5.77s/it] {'loss': 0.4713, 'learning_rate': 1.0191036667835668e-05, 'epoch': 0.51} + 51%|█████ | 6085/11952 [2:31:21<9:24:23, 5.77s/it] 51%|█████ | 6086/11952 [2:31:26<9:25:53, 5.79s/it] {'loss': 0.4823, 'learning_rate': 1.0188327250573133e-05, 'epoch': 0.51} + 51%|█████ | 6086/11952 [2:31:26<9:25:53, 5.79s/it] 51%|█████ | 6087/11952 [2:31:32<9:26:10, 5.79s/it] {'loss': 0.4943, 'learning_rate': 1.0185617819480628e-05, 'epoch': 0.51} + 51%|█████ | 6087/11952 [2:31:32<9:26:10, 5.79s/it] 51%|█████ | 6088/11952 [2:31:38<9:32:02, 5.85s/it] {'loss': 0.4849, 'learning_rate': 1.0182908374757126e-05, 'epoch': 0.51} + 51%|█████ | 6088/11952 [2:31:38<9:32:02, 5.85s/it] 51%|█████ | 6089/11952 [2:31:44<9:29:41, 5.83s/it] {'loss': 0.4815, 'learning_rate': 1.0180198916601592e-05, 'epoch': 0.51} + 51%|█████ | 6089/11952 [2:31:44<9:29:41, 5.83s/it] 51%|█████ | 6090/11952 [2:31:50<9:37:30, 5.91s/it] {'loss': 0.486, 'learning_rate': 1.0177489445212998e-05, 'epoch': 0.51} + 51%|█████ | 6090/11952 [2:31:50<9:37:30, 5.91s/it] 51%|█████ | 6091/11952 [2:31:56<9:39:51, 5.94s/it] {'loss': 0.4575, 'learning_rate': 1.0174779960790318e-05, 'epoch': 0.51} + 51%|█████ | 6091/11952 [2:31:56<9:39:51, 5.94s/it] 51%|█████ | 6092/11952 [2:32:02<9:34:36, 5.88s/it] {'loss': 0.4709, 'learning_rate': 1.0172070463532524e-05, 'epoch': 0.51} + 51%|█████ | 6092/11952 [2:32:02<9:34:36, 5.88s/it] 51%|█████ | 6093/11952 [2:32:08<9:39:33, 5.94s/it] {'loss': 0.4649, 'learning_rate': 1.016936095363859e-05, 'epoch': 0.51} + 51%|█████ | 6093/11952 [2:32:08<9:39:33, 5.94s/it] 51%|█████ | 6094/11952 [2:32:14<9:44:21, 5.99s/it] {'loss': 0.4872, 'learning_rate': 1.0166651431307494e-05, 'epoch': 0.51} + 51%|█████ | 6094/11952 [2:32:14<9:44:21, 5.99s/it] 51%|█████ | 6095/11952 [2:32:20<9:41:16, 5.95s/it] {'loss': 0.4819, 'learning_rate': 1.0163941896738213e-05, 'epoch': 0.51} + 51%|█████ | 6095/11952 [2:32:20<9:41:16, 5.95s/it] 51%|█████ | 6096/11952 [2:32:26<9:33:56, 5.88s/it] {'loss': 0.4658, 'learning_rate': 1.0161232350129715e-05, 'epoch': 0.51} + 51%|█████ | 6096/11952 [2:32:26<9:33:56, 5.88s/it] 51%|█████ | 6097/11952 [2:32:32<9:41:58, 5.96s/it] {'loss': 0.4744, 'learning_rate': 1.0158522791680985e-05, 'epoch': 0.51} + 51%|█████ | 6097/11952 [2:32:32<9:41:58, 5.96s/it] 51%|█████ | 6098/11952 [2:32:38<9:49:04, 6.04s/it] {'loss': 0.4849, 'learning_rate': 1.0155813221591004e-05, 'epoch': 0.51} + 51%|█████ | 6098/11952 [2:32:38<9:49:04, 6.04s/it] 51%|█████ | 6099/11952 [2:32:44<9:47:27, 6.02s/it] {'loss': 0.4775, 'learning_rate': 1.0153103640058745e-05, 'epoch': 0.51} + 51%|█████ | 6099/11952 [2:32:44<9:47:27, 6.02s/it]4 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... +07 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... + 51%|█████ | 6100/11952 [2:32:49<9:32:26, 5.87s/it]5 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4644, 'learning_rate': 1.0150394047283192e-05, 'epoch': 0.51} + 51%|█████ | 6100/11952 [2:32:49<9:32:26, 5.87s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-6100/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-6100/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/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( + 51%|█████ | 6101/11952 [2:33:19<20:57:58, 12.90s/it] {'loss': 0.4933, 'learning_rate': 1.0147684443463328e-05, 'epoch': 0.51} + 51%|█████ | 6101/11952 [2:33:19<20:57:58, 12.90s/it] 51%|█████ | 6102/11952 [2:33:25<17:28:24, 10.75s/it] {'loss': 0.4612, 'learning_rate': 1.0144974828798131e-05, 'epoch': 0.51} + 51%|█████ | 6102/11952 [2:33:25<17:28:24, 10.75s/it] 51%|█████ | 6103/11952 [2:33:30<15:00:04, 9.23s/it] {'loss': 0.4857, 'learning_rate': 1.0142265203486583e-05, 'epoch': 0.51} + 51%|█████ | 6103/11952 [2:33:30<15:00:04, 9.23s/it] 51%|█████ | 6104/11952 [2:33:36<13:17:27, 8.18s/it] {'loss': 0.4879, 'learning_rate': 1.0139555567727674e-05, 'epoch': 0.51} + 51%|█████ | 6104/11952 [2:33:36<13:17:27, 8.18s/it] 51%|█████ | 6105/11952 [2:33:42<12:14:00, 7.53s/it] {'loss': 0.4769, 'learning_rate': 1.0136845921720385e-05, 'epoch': 0.51} + 51%|█████ | 6105/11952 [2:33:42<12:14:00, 7.53s/it] 51%|█████ | 6106/11952 [2:33:48<11:21:57, 7.00s/it] {'loss': 0.4763, 'learning_rate': 1.0134136265663698e-05, 'epoch': 0.51} + 51%|█████ | 6106/11952 [2:33:48<11:21:57, 7.00s/it] 51%|█████ | 6107/11952 [2:33:54<10:47:03, 6.64s/it] {'loss': 0.4778, 'learning_rate': 1.01314265997566e-05, 'epoch': 0.51} + 51%|█████ | 6107/11952 [2:33:54<10:47:03, 6.64s/it] 51%|█████ | 6108/11952 [2:33:59<10:23:36, 6.40s/it] {'loss': 0.4715, 'learning_rate': 1.0128716924198083e-05, 'epoch': 0.51} + 51%|█████ | 6108/11952 [2:33:59<10:23:36, 6.40s/it] 51%|█████ | 6109/11952 [2:34:05<10:05:57, 6.22s/it] {'loss': 0.468, 'learning_rate': 1.012600723918713e-05, 'epoch': 0.51} + 51%|█████ | 6109/11952 [2:34:05<10:05:57, 6.22s/it] 51%|█████ | 6110/11952 [2:34:11<9:55:29, 6.12s/it] {'loss': 0.5026, 'learning_rate': 1.0123297544922728e-05, 'epoch': 0.51} + 51%|█████ | 6110/11952 [2:34:11<9:55:29, 6.12s/it] 51%|█████ | 6111/11952 [2:34:17<9:47:37, 6.04s/it] {'loss': 0.4965, 'learning_rate': 1.0120587841603868e-05, 'epoch': 0.51} + 51%|█████ | 6111/11952 [2:34:17<9:47:37, 6.04s/it] 51%|█████ | 6112/11952 [2:34:23<9:45:35, 6.02s/it] {'loss': 0.4759, 'learning_rate': 1.011787812942954e-05, 'epoch': 0.51} + 51%|█████ | 6112/11952 [2:34:23<9:45:35, 6.02s/it] 51%|█████ | 6113/11952 [2:34:29<9:43:26, 6.00s/it] {'loss': 0.4755, 'learning_rate': 1.0115168408598728e-05, 'epoch': 0.51} + 51%|█████ | 6113/11952 [2:34:29<9:43:26, 6.00s/it] 51%|█████ | 6114/11952 [2:34:34<9:30:44, 5.87s/it] {'loss': 0.4671, 'learning_rate': 1.011245867931043e-05, 'epoch': 0.51} + 51%|█████ | 6114/11952 [2:34:34<9:30:44, 5.87s/it] 51%|█████ | 6115/11952 [2:34:40<9:23:52, 5.80s/it] {'loss': 0.4646, 'learning_rate': 1.0109748941763635e-05, 'epoch': 0.51} + 51%|█████ | 6115/11952 [2:34:40<9:23:52, 5.80s/it] 51%|█████ | 6116/11952 [2:34:46<9:27:25, 5.83s/it] {'loss': 0.4868, 'learning_rate': 1.0107039196157335e-05, 'epoch': 0.51} + 51%|█████ | 6116/11952 [2:34:46<9:27:25, 5.83s/it] 51%|█████ | 6117/11952 [2:34:52<9:21:27, 5.77s/it] {'loss': 0.4626, 'learning_rate': 1.010432944269052e-05, 'epoch': 0.51} + 51%|█████ | 6117/11952 [2:34:52<9:21:27, 5.77s/it] 51%|█████ | 6118/11952 [2:34:58<9:28:23, 5.85s/it] {'loss': 0.4982, 'learning_rate': 1.0101619681562183e-05, 'epoch': 0.51} + 51%|█████ | 6118/11952 [2:34:58<9:28:23, 5.85s/it] 51%|█████ | 6119/11952 [2:35:04<9:35:57, 5.92s/it] {'loss': 0.4729, 'learning_rate': 1.0098909912971322e-05, 'epoch': 0.51} + 51%|█████ | 6119/11952 [2:35:04<9:35:57, 5.92s/it] 51%|█████ | 6120/11952 [2:35:09<9:31:52, 5.88s/it] {'loss': 0.4953, 'learning_rate': 1.0096200137116924e-05, 'epoch': 0.51} + 51%|█████ | 6120/11952 [2:35:09<9:31:52, 5.88s/it] 51%|█████ | 6121/11952 [2:35:15<9:31:06, 5.88s/it] {'loss': 0.4823, 'learning_rate': 1.0093490354197994e-05, 'epoch': 0.51} + 51%|█████ | 6121/11952 [2:35:15<9:31:06, 5.88s/it] 51%|█████ | 6122/11952 [2:35:21<9:27:36, 5.84s/it] {'loss': 0.4974, 'learning_rate': 1.0090780564413518e-05, 'epoch': 0.51} + 51%|█████ | 6122/11952 [2:35:21<9:27:36, 5.84s/it] 51%|█████ | 6123/11952 [2:35:27<9:24:46, 5.81s/it] {'loss': 0.4955, 'learning_rate': 1.0088070767962497e-05, 'epoch': 0.51} + 51%|█████ | 6123/11952 [2:35:27<9:24:46, 5.81s/it] 51%|█████ | 6124/11952 [2:35:33<9:39:02, 5.96s/it] {'loss': 0.4789, 'learning_rate': 1.0085360965043923e-05, 'epoch': 0.51} + 51%|█████ | 6124/11952 [2:35:33<9:39:02, 5.96s/it] 51%|█████ | 6125/11952 [2:35:39<9:37:10, 5.94s/it] {'loss': 0.4786, 'learning_rate': 1.0082651155856795e-05, 'epoch': 0.51} + 51%|█████ | 6125/11952 [2:35:39<9:37:10, 5.94s/it] 51%|█████▏ | 6126/11952 [2:35:45<9:40:17, 5.98s/it] {'loss': 0.4877, 'learning_rate': 1.007994134060011e-05, 'epoch': 0.51} + 51%|█████▏ | 6126/11952 [2:35:45<9:40:17, 5.98s/it] 51%|█████▏ | 6127/11952 [2:35:51<9:32:24, 5.90s/it] {'loss': 0.4656, 'learning_rate': 1.0077231519472866e-05, 'epoch': 0.51} + 51%|█████▏ | 6127/11952 [2:35:51<9:32:24, 5.90s/it] 51%|█████▏ | 6128/11952 [2:35:57<9:38:41, 5.96s/it] {'loss': 0.4981, 'learning_rate': 1.007452169267406e-05, 'epoch': 0.51} + 51%|█████▏ | 6128/11952 [2:35:57<9:38:41, 5.96s/it] 51%|█████▏ | 6129/11952 [2:36:03<9:30:42, 5.88s/it] {'loss': 0.5001, 'learning_rate': 1.0071811860402692e-05, 'epoch': 0.51} + 51%|█████▏ | 6129/11952 [2:36:03<9:30:42, 5.88s/it] 51%|█████▏ | 6130/11952 [2:36:09<9:41:34, 5.99s/it] {'loss': 0.4817, 'learning_rate': 1.0069102022857757e-05, 'epoch': 0.51} + 51%|█████▏ | 6130/11952 [2:36:09<9:41:34, 5.99s/it] 51%|█████▏ | 6131/11952 [2:36:15<9:36:59, 5.95s/it] {'loss': 0.4879, 'learning_rate': 1.0066392180238258e-05, 'epoch': 0.51} + 51%|█████▏ | 6131/11952 [2:36:15<9:36:59, 5.95s/it] 51%|█████▏ | 6132/11952 [2:36:20<9:28:43, 5.86s/it] {'loss': 0.4897, 'learning_rate': 1.0063682332743196e-05, 'epoch': 0.51} + 51%|█████▏ | 6132/11952 [2:36:20<9:28:43, 5.86s/it] 51%|█████▏ | 6133/11952 [2:36:26<9:33:18, 5.91s/it] {'loss': 0.4781, 'learning_rate': 1.0060972480571565e-05, 'epoch': 0.51} + 51%|█████▏ | 6133/11952 [2:36:26<9:33:18, 5.91s/it] 51%|█████▏ | 6134/11952 [2:36:32<9:31:13, 5.89s/it] {'loss': 0.4542, 'learning_rate': 1.0058262623922368e-05, 'epoch': 0.51} + 51%|█████▏ | 6134/11952 [2:36:32<9:31:13, 5.89s/it] 51%|█████▏ | 6135/11952 [2:36:38<9:25:25, 5.83s/it] {'loss': 0.4887, 'learning_rate': 1.005555276299461e-05, 'epoch': 0.51} + 51%|█████▏ | 6135/11952 [2:36:38<9:25:25, 5.83s/it] 51%|█████▏ | 6136/11952 [2:36:44<9:33:25, 5.92s/it] {'loss': 0.4949, 'learning_rate': 1.0052842897987288e-05, 'epoch': 0.51} + 51%|█████▏ | 6136/11952 [2:36:44<9:33:25, 5.92s/it] 51%|█████▏ | 6137/11952 [2:36:50<9:28:26, 5.87s/it] {'loss': 0.4703, 'learning_rate': 1.0050133029099401e-05, 'epoch': 0.51} + 51%|█████▏ | 6137/11952 [2:36:50<9:28:26, 5.87s/it] 51%|█████▏ | 6138/11952 [2:36:56<9:25:49, 5.84s/it] {'loss': 0.4776, 'learning_rate': 1.0047423156529952e-05, 'epoch': 0.51} + 51%|█████▏ | 6138/11952 [2:36:56<9:25:49, 5.84s/it] 51%|█████▏ | 6139/11952 [2:37:01<9:26:25, 5.85s/it] {'loss': 0.4973, 'learning_rate': 1.0044713280477946e-05, 'epoch': 0.51} + 51%|█████▏ | 6139/11952 [2:37:01<9:26:25, 5.85s/it] 51%|█████▏ | 6140/11952 [2:37:07<9:26:40, 5.85s/it] {'loss': 0.4845, 'learning_rate': 1.0042003401142383e-05, 'epoch': 0.51} + 51%|█████▏ | 6140/11952 [2:37:07<9:26:40, 5.85s/it] 51%|█████▏ | 6141/11952 [2:37:13<9:31:52, 5.90s/it] {'loss': 0.4794, 'learning_rate': 1.0039293518722262e-05, 'epoch': 0.51} + 51%|█████▏ | 6141/11952 [2:37:13<9:31:52, 5.90s/it] 51%|█████▏ | 6142/11952 [2:37:19<9:21:48, 5.80s/it] {'loss': 0.4974, 'learning_rate': 1.0036583633416593e-05, 'epoch': 0.51} + 51%|█████▏ | 6142/11952 [2:37:19<9:21:48, 5.80s/it] 51%|█████▏ | 6143/11952 [2:37:25<9:26:55, 5.86s/it] {'loss': 0.4832, 'learning_rate': 1.0033873745424369e-05, 'epoch': 0.51} + 51%|█████▏ | 6143/11952 [2:37:25<9:26:55, 5.86s/it] 51%|█████▏ | 6144/11952 [2:37:31<9:22:01, 5.81s/it] {'loss': 0.4864, 'learning_rate': 1.00311638549446e-05, 'epoch': 0.51} + 51%|█████▏ | 6144/11952 [2:37:31<9:22:01, 5.81s/it] 51%|█████▏ | 6145/11952 [2:37:37<9:28:48, 5.88s/it] {'loss': 0.4641, 'learning_rate': 1.0028453962176287e-05, 'epoch': 0.51} + 51%|█████▏ | 6145/11952 [2:37:37<9:28:48, 5.88s/it] 51%|█████▏ | 6146/11952 [2:37:42<9:22:47, 5.82s/it] {'loss': 0.4801, 'learning_rate': 1.0025744067318435e-05, 'epoch': 0.51} + 51%|█████▏ | 6146/11952 [2:37:42<9:22:47, 5.82s/it] 51%|█████▏ | 6147/11952 [2:37:48<9:28:05, 5.87s/it] {'loss': 0.4759, 'learning_rate': 1.0023034170570044e-05, 'epoch': 0.51} + 51%|█████▏ | 6147/11952 [2:37:48<9:28:05, 5.87s/it] 51%|█████▏ | 6148/11952 [2:37:54<9:28:23, 5.88s/it] {'loss': 0.4816, 'learning_rate': 1.0020324272130117e-05, 'epoch': 0.51} + 51%|█████▏ | 6148/11952 [2:37:54<9:28:23, 5.88s/it] 51%|█████▏ | 6149/11952 [2:38:00<9:24:50, 5.84s/it] {'loss': 0.4867, 'learning_rate': 1.0017614372197667e-05, 'epoch': 0.51} + 51%|█████▏ | 6149/11952 [2:38:00<9:24:50, 5.84s/it]7 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... +0 AutoResumeHook: Checking whether to suspend... +16 AutoResumeHook: Checking whether to suspend... +AutoResumeHook: Checking whether to suspend... + 51%|█████▏ | 6150/11952 [2:38:05<9:17:28, 5.77s/it]5 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4779, 'learning_rate': 1.0014904470971686e-05, 'epoch': 0.51} + 51%|█████▏ | 6150/11952 [2:38:05<9:17:28, 5.77s/it] 51%|█████▏ | 6151/11952 [2:38:12<9:24:32, 5.84s/it] {'loss': 0.4897, 'learning_rate': 1.0012194568651184e-05, 'epoch': 0.51} + 51%|█████▏ | 6151/11952 [2:38:12<9:24:32, 5.84s/it] 51%|█████▏ | 6152/11952 [2:38:17<9:26:24, 5.86s/it] {'loss': 0.4805, 'learning_rate': 1.0009484665435163e-05, 'epoch': 0.51} + 51%|█████▏ | 6152/11952 [2:38:17<9:26:24, 5.86s/it] 51%|█████▏ | 6153/11952 [2:38:23<9:21:25, 5.81s/it] {'loss': 0.4745, 'learning_rate': 1.0006774761522626e-05, 'epoch': 0.51} + 51%|█████▏ | 6153/11952 [2:38:23<9:21:25, 5.81s/it] 51%|█████▏ | 6154/11952 [2:38:29<9:21:52, 5.81s/it] {'loss': 0.4776, 'learning_rate': 1.000406485711258e-05, 'epoch': 0.51} + 51%|█████▏ | 6154/11952 [2:38:29<9:21:52, 5.81s/it] 51%|█████▏ | 6155/11952 [2:38:35<9:22:36, 5.82s/it] {'loss': 0.4708, 'learning_rate': 1.0001354952404027e-05, 'epoch': 0.51} + 51%|█████▏ | 6155/11952 [2:38:35<9:22:36, 5.82s/it] 52%|█████▏ | 6156/11952 [2:38:40<9:17:56, 5.78s/it] {'loss': 0.4719, 'learning_rate': 9.998645047595975e-06, 'epoch': 0.52} + 52%|█████▏ | 6156/11952 [2:38:40<9:17:56, 5.78s/it] 52%|█████▏ | 6157/11952 [2:38:46<9:20:41, 5.81s/it] {'loss': 0.4778, 'learning_rate': 9.995935142887424e-06, 'epoch': 0.52} + 52%|█████▏ | 6157/11952 [2:38:46<9:20:41, 5.81s/it] 52%|█████▏ | 6158/11952 [2:38:52<9:27:23, 5.88s/it] {'loss': 0.479, 'learning_rate': 9.993225238477377e-06, 'epoch': 0.52} + 52%|█████▏ | 6158/11952 [2:38:52<9:27:23, 5.88s/it] 52%|█████▏ | 6159/11952 [2:38:58<9:31:00, 5.91s/it] {'loss': 0.4616, 'learning_rate': 9.99051533456484e-06, 'epoch': 0.52} + 52%|█████▏ | 6159/11952 [2:38:58<9:31:00, 5.91s/it] 52%|█████▏ | 6160/11952 [2:39:04<9:30:38, 5.91s/it] {'loss': 0.4924, 'learning_rate': 9.987805431348818e-06, 'epoch': 0.52} + 52%|█████▏ | 6160/11952 [2:39:04<9:30:38, 5.91s/it] 52%|█████▏ | 6161/11952 [2:39:10<9:24:26, 5.85s/it] {'loss': 0.4886, 'learning_rate': 9.985095529028317e-06, 'epoch': 0.52} + 52%|█████▏ | 6161/11952 [2:39:10<9:24:26, 5.85s/it] 52%|█████▏ | 6162/11952 [2:39:16<9:22:30, 5.83s/it] {'loss': 0.473, 'learning_rate': 9.982385627802338e-06, 'epoch': 0.52} + 52%|█████▏ | 6162/11952 [2:39:16<9:22:30, 5.83s/it] 52%|█████▏ | 6163/11952 [2:39:21<9:15:22, 5.76s/it] {'loss': 0.5046, 'learning_rate': 9.979675727869884e-06, 'epoch': 0.52} + 52%|█████▏ | 6163/11952 [2:39:21<9:15:22, 5.76s/it] 52%|█████▏ | 6164/11952 [2:39:27<9:10:10, 5.70s/it] {'loss': 0.4845, 'learning_rate': 9.976965829429958e-06, 'epoch': 0.52} + 52%|█████▏ | 6164/11952 [2:39:27<9:10:10, 5.70s/it] 52%|█████▏ | 6165/11952 [2:39:33<9:18:23, 5.79s/it] {'loss': 0.4805, 'learning_rate': 9.97425593268157e-06, 'epoch': 0.52} + 52%|█████▏ | 6165/11952 [2:39:33<9:18:23, 5.79s/it] 52%|█████▏ | 6166/11952 [2:39:39<9:20:14, 5.81s/it] {'loss': 0.4887, 'learning_rate': 9.971546037823713e-06, 'epoch': 0.52} + 52%|█████▏ | 6166/11952 [2:39:39<9:20:14, 5.81s/it] 52%|█████▏ | 6167/11952 [2:39:44<9:16:27, 5.77s/it] {'loss': 0.4882, 'learning_rate': 9.968836145055402e-06, 'epoch': 0.52} + 52%|█████▏ | 6167/11952 [2:39:44<9:16:27, 5.77s/it] 52%|█████▏ | 6168/11952 [2:39:50<9:19:01, 5.80s/it] {'loss': 0.4744, 'learning_rate': 9.966126254575634e-06, 'epoch': 0.52} + 52%|█████▏ | 6168/11952 [2:39:50<9:19:01, 5.80s/it] 52%|█████▏ | 6169/11952 [2:39:56<9:14:06, 5.75s/it] {'loss': 0.4752, 'learning_rate': 9.963416366583412e-06, 'epoch': 0.52} + 52%|█████▏ | 6169/11952 [2:39:56<9:14:06, 5.75s/it] 52%|█████▏ | 6170/11952 [2:40:02<9:16:44, 5.78s/it] {'loss': 0.4858, 'learning_rate': 9.960706481277742e-06, 'epoch': 0.52} + 52%|█████▏ | 6170/11952 [2:40:02<9:16:44, 5.78s/it] 52%|█████▏ | 6171/11952 [2:40:08<9:21:14, 5.82s/it] {'loss': 0.4589, 'learning_rate': 9.957996598857622e-06, 'epoch': 0.52} + 52%|█████▏ | 6171/11952 [2:40:08<9:21:14, 5.82s/it] 52%|█████▏ | 6172/11952 [2:40:14<9:23:16, 5.85s/it] {'loss': 0.4713, 'learning_rate': 9.955286719522059e-06, 'epoch': 0.52} + 52%|█████▏ | 6172/11952 [2:40:14<9:23:16, 5.85s/it] 52%|█████▏ | 6173/11952 [2:40:20<9:29:14, 5.91s/it] {'loss': 0.5407, 'learning_rate': 9.952576843470048e-06, 'epoch': 0.52} + 52%|█████▏ | 6173/11952 [2:40:20<9:29:14, 5.91s/it] 52%|█████▏ | 6174/11952 [2:40:26<9:32:27, 5.94s/it] {'loss': 0.4929, 'learning_rate': 9.949866970900602e-06, 'epoch': 0.52} + 52%|█████▏ | 6174/11952 [2:40:26<9:32:27, 5.94s/it] 52%|█████▏ | 6175/11952 [2:40:32<9:38:52, 6.01s/it] {'loss': 0.4734, 'learning_rate': 9.947157102012716e-06, 'epoch': 0.52} + 52%|█████▏ | 6175/11952 [2:40:32<9:38:52, 6.01s/it] 52%|█████▏ | 6176/11952 [2:40:38<9:29:54, 5.92s/it] {'loss': 0.4758, 'learning_rate': 9.944447237005392e-06, 'epoch': 0.52} + 52%|█████▏ | 6176/11952 [2:40:38<9:29:54, 5.92s/it] 52%|█████▏ | 6177/11952 [2:40:43<9:26:47, 5.89s/it] {'loss': 0.4628, 'learning_rate': 9.941737376077634e-06, 'epoch': 0.52} + 52%|█████▏ | 6177/11952 [2:40:43<9:26:47, 5.89s/it] 52%|█████▏ | 6178/11952 [2:40:49<9:21:37, 5.84s/it] {'loss': 0.4739, 'learning_rate': 9.93902751942844e-06, 'epoch': 0.52} + 52%|█████▏ | 6178/11952 [2:40:49<9:21:37, 5.84s/it] 52%|█████▏ | 6179/11952 [2:40:55<9:20:03, 5.82s/it] {'loss': 0.4739, 'learning_rate': 9.93631766725681e-06, 'epoch': 0.52} + 52%|█████▏ | 6179/11952 [2:40:55<9:20:03, 5.82s/it] 52%|█████▏ | 6180/11952 [2:41:01<9:27:15, 5.90s/it] {'loss': 0.488, 'learning_rate': 9.93360781976174e-06, 'epoch': 0.52} + 52%|█████▏ | 6180/11952 [2:41:01<9:27:15, 5.90s/it] 52%|█████▏ | 6181/11952 [2:41:08<9:46:38, 6.10s/it] {'loss': 0.484, 'learning_rate': 9.930897977142245e-06, 'epoch': 0.52} + 52%|█████▏ | 6181/11952 [2:41:08<9:46:38, 6.10s/it] 52%|█████▏ | 6182/11952 [2:41:13<9:41:34, 6.05s/it] {'loss': 0.4858, 'learning_rate': 9.928188139597313e-06, 'epoch': 0.52} + 52%|█████▏ | 6182/11952 [2:41:13<9:41:34, 6.05s/it] 52%|█████▏ | 6183/11952 [2:41:19<9:34:17, 5.97s/it] {'loss': 0.4791, 'learning_rate': 9.925478307325944e-06, 'epoch': 0.52} + 52%|█████▏ | 6183/11952 [2:41:19<9:34:17, 5.97s/it] 52%|█████▏ | 6184/11952 [2:41:25<9:35:49, 5.99s/it] {'loss': 0.4836, 'learning_rate': 9.922768480527138e-06, 'epoch': 0.52} + 52%|█████▏ | 6184/11952 [2:41:25<9:35:49, 5.99s/it] 52%|█████▏ | 6185/11952 [2:41:31<9:26:49, 5.90s/it] {'loss': 0.471, 'learning_rate': 9.920058659399895e-06, 'epoch': 0.52} + 52%|█████▏ | 6185/11952 [2:41:31<9:26:49, 5.90s/it] 52%|█████▏ | 6186/11952 [2:41:37<9:21:08, 5.84s/it] {'loss': 0.4773, 'learning_rate': 9.91734884414321e-06, 'epoch': 0.52} + 52%|█████▏ | 6186/11952 [2:41:37<9:21:08, 5.84s/it] 52%|█████▏ | 6187/11952 [2:41:42<9:17:28, 5.80s/it] {'loss': 0.4778, 'learning_rate': 9.914639034956079e-06, 'epoch': 0.52} + 52%|█████▏ | 6187/11952 [2:41:42<9:17:28, 5.80s/it] 52%|█████▏ | 6188/11952 [2:41:48<9:14:48, 5.78s/it] {'loss': 0.4983, 'learning_rate': 9.911929232037507e-06, 'epoch': 0.52} + 52%|█████▏ | 6188/11952 [2:41:48<9:14:48, 5.78s/it] 52%|█████▏ | 6189/11952 [2:41:54<9:12:19, 5.75s/it] {'loss': 0.4768, 'learning_rate': 9.909219435586485e-06, 'epoch': 0.52} + 52%|█████▏ | 6189/11952 [2:41:54<9:12:19, 5.75s/it] 52%|█████▏ | 6190/11952 [2:42:00<9:11:36, 5.74s/it] {'loss': 0.4848, 'learning_rate': 9.906509645802009e-06, 'epoch': 0.52} + 52%|█████▏ | 6190/11952 [2:42:00<9:11:36, 5.74s/it] 52%|█████▏ | 6191/11952 [2:42:05<9:07:14, 5.70s/it] {'loss': 0.4802, 'learning_rate': 9.903799862883077e-06, 'epoch': 0.52} + 52%|█████▏ | 6191/11952 [2:42:05<9:07:14, 5.70s/it] 52%|█████▏ | 6192/11952 [2:42:11<9:15:43, 5.79s/it] {'loss': 0.4775, 'learning_rate': 9.901090087028685e-06, 'epoch': 0.52} + 52%|█████▏ | 6192/11952 [2:42:11<9:15:43, 5.79s/it] 52%|█████▏ | 6193/11952 [2:42:17<9:18:16, 5.82s/it] {'loss': 0.4846, 'learning_rate': 9.898380318437822e-06, 'epoch': 0.52} + 52%|█████▏ | 6193/11952 [2:42:17<9:18:16, 5.82s/it] 52%|█████▏ | 6194/11952 [2:42:23<9:20:21, 5.84s/it] {'loss': 0.4832, 'learning_rate': 9.895670557309484e-06, 'epoch': 0.52} + 52%|█████▏ | 6194/11952 [2:42:23<9:20:21, 5.84s/it] 52%|█████▏ | 6195/11952 [2:42:29<9:17:11, 5.81s/it] {'loss': 0.4866, 'learning_rate': 9.892960803842668e-06, 'epoch': 0.52} + 52%|█████▏ | 6195/11952 [2:42:29<9:17:11, 5.81s/it] 52%|█████▏ | 6196/11952 [2:42:34<9:10:27, 5.74s/it] {'loss': 0.4776, 'learning_rate': 9.890251058236368e-06, 'epoch': 0.52} + 52%|█████▏ | 6196/11952 [2:42:34<9:10:27, 5.74s/it] 52%|█████▏ | 6197/11952 [2:42:40<9:25:49, 5.90s/it] {'loss': 0.4772, 'learning_rate': 9.887541320689573e-06, 'epoch': 0.52} + 52%|█████▏ | 6197/11952 [2:42:40<9:25:49, 5.90s/it] 52%|█████▏ | 6198/11952 [2:42:46<9:24:02, 5.88s/it] {'loss': 0.5, 'learning_rate': 9.884831591401276e-06, 'epoch': 0.52} + 52%|█████▏ | 6198/11952 [2:42:46<9:24:02, 5.88s/it] 52%|█████▏ | 6199/11952 [2:42:52<9:24:29, 5.89s/it] {'loss': 0.4832, 'learning_rate': 9.882121870570465e-06, 'epoch': 0.52} + 52%|█████▏ | 6199/11952 [2:42:52<9:24:29, 5.89s/it]3 AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +07 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... + 5 AutoResumeHook: Checking whether to suspend... +1AutoResumeHook: Checking whether to suspend... AutoResumeHook: Checking whether to suspend... + + 52%|█████▏ | 6200/11952 [2:42:58<9:22:23, 5.87s/it] {'loss': 0.4802, 'learning_rate': 9.879412158396134e-06, 'epoch': 0.52} + 52%|█████▏ | 6200/11952 [2:42:58<9:22:23, 5.87s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-6200/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-6200/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/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( + 52%|█████▏ | 6201/11952 [2:43:23<18:28:25, 11.56s/it] {'loss': 0.4718, 'learning_rate': 9.876702455077272e-06, 'epoch': 0.52} + 52%|█████▏ | 6201/11952 [2:43:23<18:28:25, 11.56s/it] 52%|█████▏ | 6202/11952 [2:43:29<15:55:16, 9.97s/it] {'loss': 0.4742, 'learning_rate': 9.873992760812871e-06, 'epoch': 0.52} + 52%|█████▏ | 6202/11952 [2:43:29<15:55:16, 9.97s/it] 52%|█████▏ | 6203/11952 [2:43:35<13:57:54, 8.74s/it] {'loss': 0.4717, 'learning_rate': 9.87128307580192e-06, 'epoch': 0.52} + 52%|█████▏ | 6203/11952 [2:43:35<13:57:54, 8.74s/it] 52%|█████▏ | 6204/11952 [2:43:41<12:31:55, 7.85s/it] {'loss': 0.4813, 'learning_rate': 9.868573400243402e-06, 'epoch': 0.52} + 52%|█████▏ | 6204/11952 [2:43:41<12:31:55, 7.85s/it] 52%|█████▏ | 6205/11952 [2:43:47<11:38:34, 7.29s/it] {'loss': 0.4895, 'learning_rate': 9.865863734336305e-06, 'epoch': 0.52} + 52%|█████▏ | 6205/11952 [2:43:47<11:38:34, 7.29s/it] 52%|█████▏ | 6206/11952 [2:43:53<10:58:47, 6.88s/it] {'loss': 0.4889, 'learning_rate': 9.86315407827962e-06, 'epoch': 0.52} + 52%|█████▏ | 6206/11952 [2:43:53<10:58:47, 6.88s/it] 52%|█████▏ | 6207/11952 [2:43:58<10:22:24, 6.50s/it] {'loss': 0.4873, 'learning_rate': 9.860444432272328e-06, 'epoch': 0.52} + 52%|█████▏ | 6207/11952 [2:43:58<10:22:24, 6.50s/it] 52%|█████▏ | 6208/11952 [2:44:04<10:02:11, 6.29s/it] {'loss': 0.4915, 'learning_rate': 9.857734796513417e-06, 'epoch': 0.52} + 52%|█████▏ | 6208/11952 [2:44:04<10:02:11, 6.29s/it] 52%|█████▏ | 6209/11952 [2:44:10<9:50:20, 6.17s/it] {'loss': 0.4696, 'learning_rate': 9.855025171201874e-06, 'epoch': 0.52} + 52%|█████▏ | 6209/11952 [2:44:10<9:50:20, 6.17s/it] 52%|█████▏ | 6210/11952 [2:44:16<9:39:57, 6.06s/it] {'loss': 0.4605, 'learning_rate': 9.852315556536674e-06, 'epoch': 0.52} + 52%|█████▏ | 6210/11952 [2:44:16<9:39:57, 6.06s/it] 52%|█████▏ | 6211/11952 [2:44:21<9:25:54, 5.91s/it] {'loss': 0.4808, 'learning_rate': 9.84960595271681e-06, 'epoch': 0.52} + 52%|█████▏ | 6211/11952 [2:44:21<9:25:54, 5.91s/it] 52%|█████▏ | 6212/11952 [2:44:27<9:22:37, 5.88s/it] {'loss': 0.4867, 'learning_rate': 9.846896359941258e-06, 'epoch': 0.52} + 52%|█████▏ | 6212/11952 [2:44:27<9:22:37, 5.88s/it] 52%|█████▏ | 6213/11952 [2:44:33<9:26:03, 5.92s/it] {'loss': 0.4805, 'learning_rate': 9.844186778409002e-06, 'epoch': 0.52} + 52%|█████▏ | 6213/11952 [2:44:33<9:26:03, 5.92s/it] 52%|█████▏ | 6214/11952 [2:44:39<9:13:11, 5.78s/it] {'loss': 0.4754, 'learning_rate': 9.841477208319015e-06, 'epoch': 0.52} + 52%|█████▏ | 6214/11952 [2:44:39<9:13:11, 5.78s/it] 52%|█████▏ | 6215/11952 [2:44:44<9:05:49, 5.71s/it] {'loss': 0.4691, 'learning_rate': 9.838767649870287e-06, 'epoch': 0.52} + 52%|█████▏ | 6215/11952 [2:44:44<9:05:49, 5.71s/it] 52%|█████▏ | 6216/11952 [2:44:50<9:13:46, 5.79s/it] {'loss': 0.4701, 'learning_rate': 9.83605810326179e-06, 'epoch': 0.52} + 52%|█████▏ | 6216/11952 [2:44:50<9:13:46, 5.79s/it] 52%|█████▏ | 6217/11952 [2:44:56<9:21:48, 5.88s/it] {'loss': 0.4799, 'learning_rate': 9.833348568692507e-06, 'epoch': 0.52} + 52%|█████▏ | 6217/11952 [2:44:56<9:21:48, 5.88s/it] 52%|█████▏ | 6218/11952 [2:45:02<9:21:30, 5.88s/it] {'loss': 0.4803, 'learning_rate': 9.830639046361412e-06, 'epoch': 0.52} + 52%|█████▏ | 6218/11952 [2:45:02<9:21:30, 5.88s/it] 52%|█████▏ | 6219/11952 [2:45:08<9:20:24, 5.87s/it] {'loss': 0.4602, 'learning_rate': 9.82792953646748e-06, 'epoch': 0.52} + 52%|█████▏ | 6219/11952 [2:45:08<9:20:24, 5.87s/it] 52%|█████▏ | 6220/11952 [2:45:14<9:19:08, 5.85s/it] {'loss': 0.4757, 'learning_rate': 9.825220039209687e-06, 'epoch': 0.52} + 52%|█████▏ | 6220/11952 [2:45:14<9:19:08, 5.85s/it] 52%|█████▏ | 6221/11952 [2:45:19<9:14:29, 5.81s/it] {'loss': 0.4817, 'learning_rate': 9.822510554787004e-06, 'epoch': 0.52} + 52%|█████▏ | 6221/11952 [2:45:19<9:14:29, 5.81s/it] 52%|█████▏ | 6222/11952 [2:45:26<9:20:59, 5.87s/it] {'loss': 0.4772, 'learning_rate': 9.819801083398411e-06, 'epoch': 0.52} + 52%|█████▏ | 6222/11952 [2:45:26<9:20:59, 5.87s/it] 52%|█████▏ | 6223/11952 [2:45:31<9:20:11, 5.87s/it] {'loss': 0.4876, 'learning_rate': 9.817091625242879e-06, 'epoch': 0.52} + 52%|█████▏ | 6223/11952 [2:45:31<9:20:11, 5.87s/it] 52%|█████▏ | 6224/11952 [2:45:37<9:19:17, 5.86s/it] {'loss': 0.4803, 'learning_rate': 9.814382180519375e-06, 'epoch': 0.52} + 52%|█████▏ | 6224/11952 [2:45:37<9:19:17, 5.86s/it] 52%|█████▏ | 6225/11952 [2:45:43<9:17:41, 5.84s/it] {'loss': 0.4761, 'learning_rate': 9.81167274942687e-06, 'epoch': 0.52} + 52%|█████▏ | 6225/11952 [2:45:43<9:17:41, 5.84s/it] 52%|█████▏ | 6226/11952 [2:45:48<9:07:20, 5.74s/it] {'loss': 0.4727, 'learning_rate': 9.808963332164337e-06, 'epoch': 0.52} + 52%|█████▏ | 6226/11952 [2:45:48<9:07:20, 5.74s/it] 52%|█████▏ | 6227/11952 [2:45:54<9:13:06, 5.80s/it] {'loss': 0.468, 'learning_rate': 9.806253928930743e-06, 'epoch': 0.52} + 52%|█████▏ | 6227/11952 [2:45:54<9:13:06, 5.80s/it] 52%|█████▏ | 6228/11952 [2:46:00<9:12:40, 5.79s/it] {'loss': 0.4583, 'learning_rate': 9.80354453992505e-06, 'epoch': 0.52} + 52%|█████▏ | 6228/11952 [2:46:00<9:12:40, 5.79s/it] 52%|█████▏ | 6229/11952 [2:46:06<9:20:06, 5.87s/it] {'loss': 0.4972, 'learning_rate': 9.800835165346234e-06, 'epoch': 0.52} + 52%|█████▏ | 6229/11952 [2:46:06<9:20:06, 5.87s/it] 52%|█████▏ | 6230/11952 [2:46:12<9:11:49, 5.79s/it] {'loss': 0.4874, 'learning_rate': 9.798125805393255e-06, 'epoch': 0.52} + 52%|█████▏ | 6230/11952 [2:46:12<9:11:49, 5.79s/it] 52%|█████▏ | 6231/11952 [2:46:18<9:15:49, 5.83s/it] {'loss': 0.4627, 'learning_rate': 9.795416460265074e-06, 'epoch': 0.52} + 52%|█████▏ | 6231/11952 [2:46:18<9:15:49, 5.83s/it] 52%|█████▏ | 6232/11952 [2:46:24<9:20:07, 5.88s/it] {'loss': 0.5072, 'learning_rate': 9.79270713016066e-06, 'epoch': 0.52} + 52%|█████▏ | 6232/11952 [2:46:24<9:20:07, 5.88s/it] 52%|█████▏ | 6233/11952 [2:46:30<9:19:45, 5.87s/it] {'loss': 0.4845, 'learning_rate': 9.789997815278973e-06, 'epoch': 0.52} + 52%|█████▏ | 6233/11952 [2:46:30<9:19:45, 5.87s/it] 52%|█████▏ | 6234/11952 [2:46:36<9:26:49, 5.95s/it] {'loss': 0.4799, 'learning_rate': 9.787288515818968e-06, 'epoch': 0.52} + 52%|█████▏ | 6234/11952 [2:46:36<9:26:49, 5.95s/it] 52%|█████▏ | 6235/11952 [2:46:41<9:18:33, 5.86s/it] {'loss': 0.47, 'learning_rate': 9.784579231979612e-06, 'epoch': 0.52} + 52%|█████▏ | 6235/11952 [2:46:41<9:18:33, 5.86s/it] 52%|█████▏ | 6236/11952 [2:46:47<9:12:32, 5.80s/it] {'loss': 0.4865, 'learning_rate': 9.781869963959861e-06, 'epoch': 0.52} + 52%|█████▏ | 6236/11952 [2:46:47<9:12:32, 5.80s/it] 52%|█████▏ | 6237/11952 [2:46:53<9:18:12, 5.86s/it] {'loss': 0.4727, 'learning_rate': 9.779160711958673e-06, 'epoch': 0.52} + 52%|█████▏ | 6237/11952 [2:46:53<9:18:12, 5.86s/it] 52%|█████▏ | 6238/11952 [2:46:59<9:13:42, 5.81s/it] {'loss': 0.4904, 'learning_rate': 9.776451476175006e-06, 'epoch': 0.52} + 52%|█████▏ | 6238/11952 [2:46:59<9:13:42, 5.81s/it] 52%|█████▏ | 6239/11952 [2:47:04<9:07:54, 5.75s/it] {'loss': 0.4865, 'learning_rate': 9.773742256807812e-06, 'epoch': 0.52} + 52%|█████▏ | 6239/11952 [2:47:04<9:07:54, 5.75s/it] 52%|█████▏ | 6240/11952 [2:47:10<9:11:00, 5.79s/it] {'loss': 0.4669, 'learning_rate': 9.771033054056044e-06, 'epoch': 0.52} + 52%|█████▏ | 6240/11952 [2:47:10<9:11:00, 5.79s/it] 52%|█████▏ | 6241/11952 [2:47:16<9:11:35, 5.80s/it] {'loss': 0.4877, 'learning_rate': 9.768323868118656e-06, 'epoch': 0.52} + 52%|█████▏ | 6241/11952 [2:47:16<9:11:35, 5.80s/it] 52%|█████▏ | 6242/11952 [2:47:22<9:06:00, 5.74s/it] {'loss': 0.469, 'learning_rate': 9.765614699194598e-06, 'epoch': 0.52} + 52%|█████▏ | 6242/11952 [2:47:22<9:06:00, 5.74s/it] 52%|█████▏ | 6243/11952 [2:47:28<9:17:23, 5.86s/it] {'loss': 0.473, 'learning_rate': 9.762905547482825e-06, 'epoch': 0.52} + 52%|█████▏ | 6243/11952 [2:47:28<9:17:23, 5.86s/it] 52%|█████▏ | 6244/11952 [2:47:34<9:12:23, 5.81s/it] {'loss': 0.4738, 'learning_rate': 9.760196413182283e-06, 'epoch': 0.52} + 52%|█████▏ | 6244/11952 [2:47:34<9:12:23, 5.81s/it] 52%|█████▏ | 6245/11952 [2:47:40<9:18:18, 5.87s/it] {'loss': 0.4813, 'learning_rate': 9.757487296491918e-06, 'epoch': 0.52} + 52%|█████▏ | 6245/11952 [2:47:40<9:18:18, 5.87s/it] 52%|█████▏ | 6246/11952 [2:47:45<9:14:34, 5.83s/it] {'loss': 0.4992, 'learning_rate': 9.754778197610674e-06, 'epoch': 0.52} + 52%|█████▏ | 6246/11952 [2:47:45<9:14:34, 5.83s/it] 52%|█████▏ | 6247/11952 [2:47:51<9:14:09, 5.83s/it] {'loss': 0.4679, 'learning_rate': 9.752069116737504e-06, 'epoch': 0.52} + 52%|█████▏ | 6247/11952 [2:47:51<9:14:09, 5.83s/it] 52%|█████▏ | 6248/11952 [2:47:57<9:11:22, 5.80s/it] {'loss': 0.456, 'learning_rate': 9.74936005407134e-06, 'epoch': 0.52} + 52%|█████▏ | 6248/11952 [2:47:57<9:11:22, 5.80s/it] 52%|█████▏ | 6249/11952 [2:48:03<9:18:31, 5.88s/it] {'loss': 0.4749, 'learning_rate': 9.746651009811137e-06, 'epoch': 0.52} + 52%|█████▏ | 6249/11952 [2:48:03<9:18:31, 5.88s/it]4 AutoResumeHook: Checking whether to suspend... +072 AutoResumeHook: Checking whether to suspend...AutoResumeHook: Checking whether to suspend... + + AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... + 52%|█████▏ | 6250/11952 [2:48:09<9:22:55, 5.92s/it]3 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4758, 'learning_rate': 9.74394198415583e-06, 'epoch': 0.52} + 52%|█████▏ | 6250/11952 [2:48:09<9:22:55, 5.92s/it] 52%|█████▏ | 6251/11952 [2:48:15<9:27:51, 5.98s/it] {'loss': 0.4719, 'learning_rate': 9.741232977304356e-06, 'epoch': 0.52} + 52%|█████▏ | 6251/11952 [2:48:15<9:27:51, 5.98s/it] 52%|█████▏ | 6252/11952 [2:48:21<9:17:14, 5.87s/it] {'loss': 0.4639, 'learning_rate': 9.738523989455659e-06, 'epoch': 0.52} + 52%|█████▏ | 6252/11952 [2:48:21<9:17:14, 5.87s/it] 52%|█████▏ | 6253/11952 [2:48:26<9:15:41, 5.85s/it] {'loss': 0.4738, 'learning_rate': 9.735815020808672e-06, 'epoch': 0.52} + 52%|█████▏ | 6253/11952 [2:48:26<9:15:41, 5.85s/it] 52%|█████▏ | 6254/11952 [2:48:32<9:21:00, 5.91s/it] {'loss': 0.4639, 'learning_rate': 9.733106071562332e-06, 'epoch': 0.52} + 52%|█████▏ | 6254/11952 [2:48:32<9:21:00, 5.91s/it] 52%|█████▏ | 6255/11952 [2:48:38<9:15:41, 5.85s/it] {'loss': 0.4905, 'learning_rate': 9.730397141915567e-06, 'epoch': 0.52} + 52%|█████▏ | 6255/11952 [2:48:38<9:15:41, 5.85s/it] 52%|█████▏ | 6256/11952 [2:48:44<9:13:56, 5.83s/it] {'loss': 0.4697, 'learning_rate': 9.727688232067318e-06, 'epoch': 0.52} + 52%|█████▏ | 6256/11952 [2:48:44<9:13:56, 5.83s/it] 52%|█████▏ | 6257/11952 [2:48:50<9:19:24, 5.89s/it] {'loss': 0.4867, 'learning_rate': 9.72497934221651e-06, 'epoch': 0.52} + 52%|█████▏ | 6257/11952 [2:48:50<9:19:24, 5.89s/it] 52%|█████▏ | 6258/11952 [2:48:56<9:17:43, 5.88s/it] {'loss': 0.4721, 'learning_rate': 9.722270472562078e-06, 'epoch': 0.52} + 52%|█████▏ | 6258/11952 [2:48:56<9:17:43, 5.88s/it] 52%|█████▏ | 6259/11952 [2:49:02<9:10:53, 5.81s/it] {'loss': 0.4716, 'learning_rate': 9.71956162330295e-06, 'epoch': 0.52} + 52%|█████▏ | 6259/11952 [2:49:02<9:10:53, 5.81s/it] 52%|█████▏ | 6260/11952 [2:49:07<9:09:06, 5.79s/it] {'loss': 0.4712, 'learning_rate': 9.716852794638046e-06, 'epoch': 0.52} + 52%|█████▏ | 6260/11952 [2:49:07<9:09:06, 5.79s/it] 52%|█████▏ | 6261/11952 [2:49:13<9:05:41, 5.75s/it] {'loss': 0.4798, 'learning_rate': 9.714143986766294e-06, 'epoch': 0.52} + 52%|█████▏ | 6261/11952 [2:49:13<9:05:41, 5.75s/it] 52%|█████▏ | 6262/11952 [2:49:19<9:12:07, 5.82s/it] {'loss': 0.4679, 'learning_rate': 9.711435199886618e-06, 'epoch': 0.52} + 52%|█████▏ | 6262/11952 [2:49:19<9:12:07, 5.82s/it] 52%|█████▏ | 6263/11952 [2:49:25<9:19:07, 5.90s/it] {'loss': 0.4605, 'learning_rate': 9.708726434197944e-06, 'epoch': 0.52} + 52%|█████▏ | 6263/11952 [2:49:25<9:19:07, 5.90s/it] 52%|█████▏ | 6264/11952 [2:49:31<9:17:48, 5.88s/it] {'loss': 0.4812, 'learning_rate': 9.706017689899189e-06, 'epoch': 0.52} + 52%|█████▏ | 6264/11952 [2:49:31<9:17:48, 5.88s/it] 52%|█████▏ | 6265/11952 [2:49:37<9:13:43, 5.84s/it] {'loss': 0.4768, 'learning_rate': 9.703308967189273e-06, 'epoch': 0.52} + 52%|█████▏ | 6265/11952 [2:49:37<9:13:43, 5.84s/it] 52%|█████▏ | 6266/11952 [2:49:42<9:14:01, 5.85s/it] {'loss': 0.4735, 'learning_rate': 9.700600266267109e-06, 'epoch': 0.52} + 52%|█████▏ | 6266/11952 [2:49:42<9:14:01, 5.85s/it] 52%|█████▏ | 6267/11952 [2:49:49<9:23:08, 5.94s/it] {'loss': 0.4862, 'learning_rate': 9.697891587331618e-06, 'epoch': 0.52} + 52%|█████▏ | 6267/11952 [2:49:49<9:23:08, 5.94s/it] 52%|█████▏ | 6268/11952 [2:49:55<9:24:40, 5.96s/it] {'loss': 0.4751, 'learning_rate': 9.695182930581715e-06, 'epoch': 0.52} + 52%|█████▏ | 6268/11952 [2:49:55<9:24:40, 5.96s/it] 52%|█████▏ | 6269/11952 [2:50:00<9:18:02, 5.89s/it] {'loss': 0.4512, 'learning_rate': 9.692474296216303e-06, 'epoch': 0.52} + 52%|█████▏ | 6269/11952 [2:50:00<9:18:02, 5.89s/it] 52%|█████▏ | 6270/11952 [2:50:06<9:15:18, 5.86s/it] {'loss': 0.4947, 'learning_rate': 9.689765684434305e-06, 'epoch': 0.52} + 52%|█████▏ | 6270/11952 [2:50:06<9:15:18, 5.86s/it] 52%|█████▏ | 6271/11952 [2:50:12<9:15:21, 5.87s/it] {'loss': 0.4816, 'learning_rate': 9.687057095434624e-06, 'epoch': 0.52} + 52%|█████▏ | 6271/11952 [2:50:12<9:15:21, 5.87s/it] 52%|█████▏ | 6272/11952 [2:50:18<9:14:28, 5.86s/it] {'loss': 0.4744, 'learning_rate': 9.684348529416166e-06, 'epoch': 0.52} + 52%|█████▏ | 6272/11952 [2:50:18<9:14:28, 5.86s/it] 52%|█████▏ | 6273/11952 [2:50:24<9:17:10, 5.89s/it] {'loss': 0.4612, 'learning_rate': 9.681639986577841e-06, 'epoch': 0.52} + 52%|█████▏ | 6273/11952 [2:50:24<9:17:10, 5.89s/it] 52%|█████▏ | 6274/11952 [2:50:30<9:15:05, 5.87s/it] {'loss': 0.4734, 'learning_rate': 9.678931467118553e-06, 'epoch': 0.52} + 52%|█████▏ | 6274/11952 [2:50:30<9:15:05, 5.87s/it] 53%|█████▎ | 6275/11952 [2:50:35<9:07:07, 5.78s/it] {'loss': 0.4665, 'learning_rate': 9.676222971237197e-06, 'epoch': 0.52} + 53%|█████▎ | 6275/11952 [2:50:35<9:07:07, 5.78s/it] 53%|█████▎ | 6276/11952 [2:50:41<9:12:23, 5.84s/it] {'loss': 0.4761, 'learning_rate': 9.673514499132683e-06, 'epoch': 0.53} + 53%|█████▎ | 6276/11952 [2:50:41<9:12:23, 5.84s/it] 53%|█████▎ | 6277/11952 [2:50:47<9:04:47, 5.76s/it] {'loss': 0.4849, 'learning_rate': 9.670806051003906e-06, 'epoch': 0.53} + 53%|█████▎ | 6277/11952 [2:50:47<9:04:47, 5.76s/it] 53%|█████▎ | 6278/11952 [2:50:53<9:13:48, 5.86s/it] {'loss': 0.479, 'learning_rate': 9.668097627049765e-06, 'epoch': 0.53} + 53%|█████▎ | 6278/11952 [2:50:53<9:13:48, 5.86s/it] 53%|█████▎ | 6279/11952 [2:50:58<9:06:56, 5.78s/it] {'loss': 0.471, 'learning_rate': 9.665389227469152e-06, 'epoch': 0.53} + 53%|█████▎ | 6279/11952 [2:50:58<9:06:56, 5.78s/it] 53%|█████▎ | 6280/11952 [2:51:04<9:12:41, 5.85s/it] {'loss': 0.4824, 'learning_rate': 9.662680852460963e-06, 'epoch': 0.53} + 53%|█████▎ | 6280/11952 [2:51:04<9:12:41, 5.85s/it] 53%|█████▎ | 6281/11952 [2:51:10<9:09:29, 5.81s/it] {'loss': 0.4746, 'learning_rate': 9.659972502224089e-06, 'epoch': 0.53} + 53%|█████▎ | 6281/11952 [2:51:10<9:09:29, 5.81s/it] 53%|█████▎ | 6282/11952 [2:51:16<9:05:30, 5.77s/it] {'loss': 0.4834, 'learning_rate': 9.657264176957419e-06, 'epoch': 0.53} + 53%|█████▎ | 6282/11952 [2:51:16<9:05:30, 5.77s/it] 53%|█████▎ | 6283/11952 [2:51:22<9:09:06, 5.81s/it] {'loss': 0.4928, 'learning_rate': 9.654555876859841e-06, 'epoch': 0.53} + 53%|█████▎ | 6283/11952 [2:51:22<9:09:06, 5.81s/it] 53%|█████▎ | 6284/11952 [2:51:28<9:27:25, 6.01s/it] {'loss': 0.4866, 'learning_rate': 9.651847602130247e-06, 'epoch': 0.53} + 53%|█████▎ | 6284/11952 [2:51:28<9:27:25, 6.01s/it] 53%|█████▎ | 6285/11952 [2:51:34<9:26:47, 6.00s/it] {'loss': 0.4769, 'learning_rate': 9.649139352967515e-06, 'epoch': 0.53} + 53%|█████▎ | 6285/11952 [2:51:34<9:26:47, 6.00s/it] 53%|█████▎ | 6286/11952 [2:51:40<9:35:02, 6.09s/it] {'loss': 0.4794, 'learning_rate': 9.646431129570531e-06, 'epoch': 0.53} + 53%|█████▎ | 6286/11952 [2:51:40<9:35:02, 6.09s/it] 53%|█████▎ | 6287/11952 [2:51:46<9:28:45, 6.02s/it] {'loss': 0.4776, 'learning_rate': 9.643722932138172e-06, 'epoch': 0.53} + 53%|█████▎ | 6287/11952 [2:51:46<9:28:45, 6.02s/it] 53%|█████▎ | 6288/11952 [2:51:52<9:27:09, 6.01s/it] {'loss': 0.4743, 'learning_rate': 9.64101476086932e-06, 'epoch': 0.53} + 53%|█████▎ | 6288/11952 [2:51:52<9:27:09, 6.01s/it] 53%|█████▎ | 6289/11952 [2:51:58<9:18:07, 5.91s/it] {'loss': 0.4793, 'learning_rate': 9.638306615962847e-06, 'epoch': 0.53} + 53%|█████▎ | 6289/11952 [2:51:58<9:18:07, 5.91s/it] 53%|█████▎ | 6290/11952 [2:52:04<9:20:54, 5.94s/it] {'loss': 0.4823, 'learning_rate': 9.635598497617636e-06, 'epoch': 0.53} + 53%|█████▎ | 6290/11952 [2:52:04<9:20:54, 5.94s/it] 53%|█████▎ | 6291/11952 [2:52:10<9:15:44, 5.89s/it] {'loss': 0.467, 'learning_rate': 9.632890406032556e-06, 'epoch': 0.53} + 53%|█████▎ | 6291/11952 [2:52:10<9:15:44, 5.89s/it] 53%|█████▎ | 6292/11952 [2:52:16<9:13:03, 5.86s/it] {'loss': 0.4598, 'learning_rate': 9.630182341406477e-06, 'epoch': 0.53} + 53%|█████▎ | 6292/11952 [2:52:16<9:13:03, 5.86s/it] 53%|█████▎ | 6293/11952 [2:52:21<9:04:00, 5.77s/it] {'loss': 0.4697, 'learning_rate': 9.627474303938267e-06, 'epoch': 0.53} + 53%|█████▎ | 6293/11952 [2:52:21<9:04:00, 5.77s/it] 53%|█████▎ | 6294/11952 [2:52:27<9:10:18, 5.84s/it] {'loss': 0.4777, 'learning_rate': 9.624766293826798e-06, 'epoch': 0.53} + 53%|█████▎ | 6294/11952 [2:52:27<9:10:18, 5.84s/it] 53%|█████▎ | 6295/11952 [2:52:33<9:08:02, 5.81s/it] {'loss': 0.4762, 'learning_rate': 9.62205831127093e-06, 'epoch': 0.53} + 53%|█████▎ | 6295/11952 [2:52:33<9:08:02, 5.81s/it] 53%|█████▎ | 6296/11952 [2:52:39<9:11:58, 5.86s/it] {'loss': 0.4949, 'learning_rate': 9.619350356469524e-06, 'epoch': 0.53} + 53%|█████▎ | 6296/11952 [2:52:39<9:11:58, 5.86s/it] 53%|█████▎ | 6297/11952 [2:52:45<9:19:54, 5.94s/it] {'loss': 0.4867, 'learning_rate': 9.616642429621449e-06, 'epoch': 0.53} + 53%|█████▎ | 6297/11952 [2:52:45<9:19:54, 5.94s/it] 53%|█████▎ | 6298/11952 [2:52:51<9:11:48, 5.86s/it] {'loss': 0.4907, 'learning_rate': 9.613934530925556e-06, 'epoch': 0.53} + 53%|█████▎ | 6298/11952 [2:52:51<9:11:48, 5.86s/it] 53%|█████▎ | 6299/11952 [2:52:56<9:09:22, 5.83s/it] {'loss': 0.4929, 'learning_rate': 9.611226660580709e-06, 'epoch': 0.53} + 53%|█████▎ | 6299/11952 [2:52:56<9:09:22, 5.83s/it]4 AutoResumeHook: Checking whether to suspend... +072 AutoResumeHook: Checking whether to suspend... +AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... +AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... + 53%|█████▎ | 6300/11952 [2:53:02<9:08:13, 5.82s/it]1 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4616, 'learning_rate': 9.60851881878576e-06, 'epoch': 0.53} + 53%|█████▎ | 6300/11952 [2:53:02<9:08:13, 5.82s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-6300/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-6300/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/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( + 53%|█████▎ | 6301/11952 [2:53:31<20:03:55, 12.78s/it] {'loss': 0.4869, 'learning_rate': 9.605811005739558e-06, 'epoch': 0.53} + 53%|█████▎ | 6301/11952 [2:53:31<20:03:55, 12.78s/it] 53%|█████▎ | 6302/11952 [2:53:37<16:45:25, 10.68s/it] {'loss': 0.4846, 'learning_rate': 9.603103221640956e-06, 'epoch': 0.53} + 53%|█████▎ | 6302/11952 [2:53:37<16:45:25, 10.68s/it] 53%|█████▎ | 6303/11952 [2:53:43<14:28:11, 9.22s/it] {'loss': 0.4695, 'learning_rate': 9.600395466688801e-06, 'epoch': 0.53} + 53%|█████▎ | 6303/11952 [2:53:43<14:28:11, 9.22s/it] 53%|█████▎ | 6304/11952 [2:53:49<12:49:56, 8.18s/it] {'loss': 0.4904, 'learning_rate': 9.597687741081942e-06, 'epoch': 0.53} + 53%|█████▎ | 6304/11952 [2:53:49<12:49:56, 8.18s/it] 53%|█████▎ | 6305/11952 [2:53:55<11:47:40, 7.52s/it] {'loss': 0.4837, 'learning_rate': 9.594980045019224e-06, 'epoch': 0.53} + 53%|█████▎ | 6305/11952 [2:53:55<11:47:40, 7.52s/it] 53%|█████▎ | 6306/11952 [2:54:01<11:12:57, 7.15s/it] {'loss': 0.4682, 'learning_rate': 9.592272378699486e-06, 'epoch': 0.53} + 53%|█████▎ | 6306/11952 [2:54:01<11:12:57, 7.15s/it] 53%|█████▎ | 6307/11952 [2:54:07<10:35:32, 6.76s/it] {'loss': 0.4882, 'learning_rate': 9.589564742321569e-06, 'epoch': 0.53} + 53%|█████▎ | 6307/11952 [2:54:07<10:35:32, 6.76s/it] 53%|█████▎ | 6308/11952 [2:54:12<10:08:22, 6.47s/it] {'loss': 0.483, 'learning_rate': 9.586857136084309e-06, 'epoch': 0.53} + 53%|█████▎ | 6308/11952 [2:54:12<10:08:22, 6.47s/it] 53%|█████▎ | 6309/11952 [2:54:19<10:01:00, 6.39s/it] {'loss': 0.4886, 'learning_rate': 9.58414956018654e-06, 'epoch': 0.53} + 53%|█████▎ | 6309/11952 [2:54:19<10:01:00, 6.39s/it] 53%|█████▎ | 6310/11952 [2:54:24<9:43:39, 6.21s/it] {'loss': 0.491, 'learning_rate': 9.581442014827101e-06, 'epoch': 0.53} + 53%|█████▎ | 6310/11952 [2:54:24<9:43:39, 6.21s/it] 53%|█████▎ | 6311/11952 [2:54:30<9:25:38, 6.02s/it] {'loss': 0.4758, 'learning_rate': 9.57873450020482e-06, 'epoch': 0.53} + 53%|█████▎ | 6311/11952 [2:54:30<9:25:38, 6.02s/it] 53%|█████▎ | 6312/11952 [2:54:36<9:24:36, 6.01s/it] {'loss': 0.4617, 'learning_rate': 9.576027016518527e-06, 'epoch': 0.53} + 53%|█████▎ | 6312/11952 [2:54:36<9:24:36, 6.01s/it] 53%|█████▎ | 6313/11952 [2:54:42<9:20:04, 5.96s/it] {'loss': 0.4783, 'learning_rate': 9.573319563967043e-06, 'epoch': 0.53} + 53%|█████▎ | 6313/11952 [2:54:42<9:20:04, 5.96s/it] 53%|█████▎ | 6314/11952 [2:54:48<9:23:06, 5.99s/it] {'loss': 0.4769, 'learning_rate': 9.570612142749196e-06, 'epoch': 0.53} + 53%|█████▎ | 6314/11952 [2:54:48<9:23:06, 5.99s/it] 53%|█████▎ | 6315/11952 [2:54:54<9:13:13, 5.89s/it] {'loss': 0.4733, 'learning_rate': 9.56790475306381e-06, 'epoch': 0.53} + 53%|█████▎ | 6315/11952 [2:54:54<9:13:13, 5.89s/it] 53%|█████▎ | 6316/11952 [2:55:00<9:14:19, 5.90s/it] {'loss': 0.4816, 'learning_rate': 9.565197395109694e-06, 'epoch': 0.53} + 53%|█████▎ | 6316/11952 [2:55:00<9:14:19, 5.90s/it] 53%|█████▎ | 6317/11952 [2:55:05<9:12:52, 5.89s/it] {'loss': 0.4784, 'learning_rate': 9.56249006908568e-06, 'epoch': 0.53} + 53%|█████▎ | 6317/11952 [2:55:05<9:12:52, 5.89s/it] 53%|█████▎ | 6318/11952 [2:55:11<9:12:11, 5.88s/it] {'loss': 0.4769, 'learning_rate': 9.559782775190574e-06, 'epoch': 0.53} + 53%|█████▎ | 6318/11952 [2:55:11<9:12:11, 5.88s/it] 53%|█████▎ | 6319/11952 [2:55:17<9:04:12, 5.80s/it] {'loss': 0.4679, 'learning_rate': 9.55707551362319e-06, 'epoch': 0.53} + 53%|█████▎ | 6319/11952 [2:55:17<9:04:12, 5.80s/it] 53%|█████▎ | 6320/11952 [2:55:23<9:07:50, 5.84s/it] {'loss': 0.4917, 'learning_rate': 9.554368284582339e-06, 'epoch': 0.53} + 53%|█████▎ | 6320/11952 [2:55:23<9:07:50, 5.84s/it] 53%|█████▎ | 6321/11952 [2:55:29<9:08:01, 5.84s/it] {'loss': 0.4883, 'learning_rate': 9.551661088266825e-06, 'epoch': 0.53} + 53%|█████▎ | 6321/11952 [2:55:29<9:08:01, 5.84s/it] 53%|█████▎ | 6322/11952 [2:55:34<9:03:18, 5.79s/it] {'loss': 0.4608, 'learning_rate': 9.548953924875459e-06, 'epoch': 0.53} + 53%|█████▎ | 6322/11952 [2:55:34<9:03:18, 5.79s/it] 53%|█████▎ | 6323/11952 [2:55:40<9:00:28, 5.76s/it] {'loss': 0.4799, 'learning_rate': 9.546246794607037e-06, 'epoch': 0.53} + 53%|█████▎ | 6323/11952 [2:55:40<9:00:28, 5.76s/it] 53%|█████▎ | 6324/11952 [2:55:46<8:56:35, 5.72s/it] {'loss': 0.4842, 'learning_rate': 9.543539697660363e-06, 'epoch': 0.53} + 53%|█████▎ | 6324/11952 [2:55:46<8:56:35, 5.72s/it] 53%|█████▎ | 6325/11952 [2:55:52<9:05:04, 5.81s/it] {'loss': 0.4864, 'learning_rate': 9.540832634234238e-06, 'epoch': 0.53} + 53%|█████▎ | 6325/11952 [2:55:52<9:05:04, 5.81s/it] 53%|█████▎ | 6326/11952 [2:55:57<9:02:51, 5.79s/it] {'loss': 0.4847, 'learning_rate': 9.538125604527455e-06, 'epoch': 0.53} + 53%|█████▎ | 6326/11952 [2:55:57<9:02:51, 5.79s/it] 53%|█████▎ | 6327/11952 [2:56:03<9:07:27, 5.84s/it] {'loss': 0.5013, 'learning_rate': 9.535418608738808e-06, 'epoch': 0.53} + 53%|█████▎ | 6327/11952 [2:56:03<9:07:27, 5.84s/it] 53%|█████▎ | 6328/11952 [2:56:09<9:11:03, 5.88s/it] {'loss': 0.4738, 'learning_rate': 9.53271164706708e-06, 'epoch': 0.53} + 53%|█████▎ | 6328/11952 [2:56:09<9:11:03, 5.88s/it] 53%|█████▎ | 6329/11952 [2:56:15<9:04:14, 5.81s/it] {'loss': 0.4796, 'learning_rate': 9.53000471971107e-06, 'epoch': 0.53} + 53%|█████▎ | 6329/11952 [2:56:15<9:04:14, 5.81s/it] 53%|█████▎ | 6330/11952 [2:56:21<9:06:41, 5.83s/it] {'loss': 0.4594, 'learning_rate': 9.527297826869553e-06, 'epoch': 0.53} + 53%|█████▎ | 6330/11952 [2:56:21<9:06:41, 5.83s/it] 53%|█████▎ | 6331/11952 [2:56:27<9:14:55, 5.92s/it] {'loss': 0.4737, 'learning_rate': 9.524590968741324e-06, 'epoch': 0.53} + 53%|█████▎ | 6331/11952 [2:56:27<9:14:55, 5.92s/it] 53%|█████▎ | 6332/11952 [2:56:33<9:08:30, 5.86s/it] {'loss': 0.4757, 'learning_rate': 9.521884145525153e-06, 'epoch': 0.53} + 53%|█████▎ | 6332/11952 [2:56:33<9:08:30, 5.86s/it] 53%|█████▎ | 6333/11952 [2:56:39<9:09:19, 5.87s/it] {'loss': 0.5014, 'learning_rate': 9.519177357419824e-06, 'epoch': 0.53} + 53%|█████▎ | 6333/11952 [2:56:39<9:09:19, 5.87s/it] 53%|█████▎ | 6334/11952 [2:56:45<9:12:57, 5.91s/it] {'loss': 0.4906, 'learning_rate': 9.516470604624109e-06, 'epoch': 0.53} + 53%|█████▎ | 6334/11952 [2:56:45<9:12:57, 5.91s/it] 53%|█████▎ | 6335/11952 [2:56:50<9:06:34, 5.84s/it] {'loss': 0.4728, 'learning_rate': 9.513763887336781e-06, 'epoch': 0.53} + 53%|█████▎ | 6335/11952 [2:56:50<9:06:34, 5.84s/it] 53%|█████▎ | 6336/11952 [2:56:56<8:59:54, 5.77s/it] {'loss': 0.4792, 'learning_rate': 9.511057205756614e-06, 'epoch': 0.53} + 53%|█████▎ | 6336/11952 [2:56:56<8:59:54, 5.77s/it] 53%|█████▎ | 6337/11952 [2:57:01<8:51:20, 5.68s/it] {'loss': 0.4579, 'learning_rate': 9.508350560082364e-06, 'epoch': 0.53} + 53%|█████▎ | 6337/11952 [2:57:01<8:51:20, 5.68s/it] 53%|█████▎ | 6338/11952 [2:57:07<8:57:49, 5.75s/it] {'loss': 0.4688, 'learning_rate': 9.505643950512811e-06, 'epoch': 0.53} + 53%|█████▎ | 6338/11952 [2:57:07<8:57:49, 5.75s/it] 53%|█████▎ | 6339/11952 [2:57:13<9:09:45, 5.88s/it] {'loss': 0.489, 'learning_rate': 9.502937377246707e-06, 'epoch': 0.53} + 53%|█████▎ | 6339/11952 [2:57:13<9:09:45, 5.88s/it] 53%|█████▎ | 6340/11952 [2:57:19<9:14:12, 5.93s/it] {'loss': 0.4965, 'learning_rate': 9.500230840482817e-06, 'epoch': 0.53} + 53%|█████▎ | 6340/11952 [2:57:19<9:14:12, 5.93s/it] 53%|█████▎ | 6341/11952 [2:57:26<9:19:59, 5.99s/it] {'loss': 0.4631, 'learning_rate': 9.497524340419896e-06, 'epoch': 0.53} + 53%|█████▎ | 6341/11952 [2:57:26<9:19:59, 5.99s/it] 53%|█████▎ | 6342/11952 [2:57:32<9:22:07, 6.01s/it] {'loss': 0.4601, 'learning_rate': 9.494817877256696e-06, 'epoch': 0.53} + 53%|█████▎ | 6342/11952 [2:57:32<9:22:07, 6.01s/it] 53%|█████▎ | 6343/11952 [2:57:37<9:09:03, 5.87s/it] {'loss': 0.4815, 'learning_rate': 9.49211145119197e-06, 'epoch': 0.53} + 53%|█████▎ | 6343/11952 [2:57:37<9:09:03, 5.87s/it] 53%|█████▎ | 6344/11952 [2:57:43<9:15:05, 5.94s/it] {'loss': 0.4815, 'learning_rate': 9.489405062424464e-06, 'epoch': 0.53} + 53%|█████▎ | 6344/11952 [2:57:43<9:15:05, 5.94s/it] 53%|█████▎ | 6345/11952 [2:57:49<9:13:13, 5.92s/it] {'loss': 0.489, 'learning_rate': 9.486698711152928e-06, 'epoch': 0.53} + 53%|█████▎ | 6345/11952 [2:57:49<9:13:13, 5.92s/it] 53%|█████▎ | 6346/11952 [2:57:55<9:07:42, 5.86s/it] {'loss': 0.4806, 'learning_rate': 9.483992397576106e-06, 'epoch': 0.53} + 53%|█████▎ | 6346/11952 [2:57:55<9:07:42, 5.86s/it] 53%|█████▎ | 6347/11952 [2:58:01<9:02:34, 5.81s/it] {'loss': 0.4701, 'learning_rate': 9.481286121892734e-06, 'epoch': 0.53} + 53%|█████▎ | 6347/11952 [2:58:01<9:02:34, 5.81s/it] 53%|█████▎ | 6348/11952 [2:58:06<9:01:25, 5.80s/it] {'loss': 0.4687, 'learning_rate': 9.478579884301554e-06, 'epoch': 0.53} + 53%|█████▎ | 6348/11952 [2:58:06<9:01:25, 5.80s/it] 53%|█████▎ | 6349/11952 [2:58:12<9:06:01, 5.85s/it] {'loss': 0.4647, 'learning_rate': 9.475873685001295e-06, 'epoch': 0.53} + 53%|█████▎ | 6349/11952 [2:58:12<9:06:01, 5.85s/it]2 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend...0 + AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... + 53%|█████▎ | 6350/11952 [2:58:18<8:56:56, 5.75s/it]4 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4665, 'learning_rate': 9.473167524190692e-06, 'epoch': 0.53} + 53%|█████▎ | 6350/11952 [2:58:18<8:56:56, 5.75s/it] 53%|█████▎ | 6351/11952 [2:58:23<8:54:00, 5.72s/it] {'loss': 0.4681, 'learning_rate': 9.470461402068478e-06, 'epoch': 0.53} + 53%|█████▎ | 6351/11952 [2:58:23<8:54:00, 5.72s/it] 53%|█████▎ | 6352/11952 [2:58:29<8:48:53, 5.67s/it] {'loss': 0.482, 'learning_rate': 9.467755318833376e-06, 'epoch': 0.53} + 53%|█████▎ | 6352/11952 [2:58:29<8:48:53, 5.67s/it] 53%|█████▎ | 6353/11952 [2:58:35<8:51:02, 5.69s/it] {'loss': 0.4852, 'learning_rate': 9.46504927468411e-06, 'epoch': 0.53} + 53%|█████▎ | 6353/11952 [2:58:35<8:51:02, 5.69s/it] 53%|█████▎ | 6354/11952 [2:58:40<8:50:30, 5.69s/it] {'loss': 0.4887, 'learning_rate': 9.462343269819398e-06, 'epoch': 0.53} + 53%|█████▎ | 6354/11952 [2:58:40<8:50:30, 5.69s/it] 53%|█████▎ | 6355/11952 [2:58:46<8:48:07, 5.66s/it] {'loss': 0.4993, 'learning_rate': 9.459637304437962e-06, 'epoch': 0.53} + 53%|█████▎ | 6355/11952 [2:58:46<8:48:07, 5.66s/it] 53%|█████▎ | 6356/11952 [2:58:52<8:54:22, 5.73s/it] {'loss': 0.4926, 'learning_rate': 9.456931378738515e-06, 'epoch': 0.53} + 53%|█████▎ | 6356/11952 [2:58:52<8:54:22, 5.73s/it] 53%|█████▎ | 6357/11952 [2:58:58<9:02:59, 5.82s/it] {'loss': 0.4916, 'learning_rate': 9.454225492919765e-06, 'epoch': 0.53} + 53%|█████▎ | 6357/11952 [2:58:58<9:02:59, 5.82s/it] 53%|█████▎ | 6358/11952 [2:59:04<9:01:26, 5.81s/it] {'loss': 0.4718, 'learning_rate': 9.451519647180427e-06, 'epoch': 0.53} + 53%|█████▎ | 6358/11952 [2:59:04<9:01:26, 5.81s/it] 53%|█████▎ | 6359/11952 [2:59:09<8:54:55, 5.74s/it] {'loss': 0.4794, 'learning_rate': 9.448813841719207e-06, 'epoch': 0.53} + 53%|█████▎ | 6359/11952 [2:59:09<8:54:55, 5.74s/it] 53%|█████▎ | 6360/11952 [2:59:15<8:55:48, 5.75s/it] {'loss': 0.461, 'learning_rate': 9.446108076734803e-06, 'epoch': 0.53} + 53%|█████▎ | 6360/11952 [2:59:15<8:55:48, 5.75s/it] 53%|█████▎ | 6361/11952 [2:59:21<8:58:40, 5.78s/it] {'loss': 0.486, 'learning_rate': 9.44340235242592e-06, 'epoch': 0.53} + 53%|█████▎ | 6361/11952 [2:59:21<8:58:40, 5.78s/it] 53%|█████▎ | 6362/11952 [2:59:27<8:59:17, 5.79s/it] {'loss': 0.467, 'learning_rate': 9.440696668991253e-06, 'epoch': 0.53} + 53%|█████▎ | 6362/11952 [2:59:27<8:59:17, 5.79s/it] 53%|█████▎ | 6363/11952 [2:59:32<8:55:58, 5.75s/it] {'loss': 0.4657, 'learning_rate': 9.437991026629497e-06, 'epoch': 0.53} + 53%|█████▎ | 6363/11952 [2:59:32<8:55:58, 5.75s/it] 53%|█████▎ | 6364/11952 [2:59:38<8:52:40, 5.72s/it] {'loss': 0.4854, 'learning_rate': 9.435285425539337e-06, 'epoch': 0.53} + 53%|█████▎ | 6364/11952 [2:59:38<8:52:40, 5.72s/it] 53%|█████▎ | 6365/11952 [2:59:44<8:58:27, 5.78s/it] {'loss': 0.4839, 'learning_rate': 9.43257986591947e-06, 'epoch': 0.53} + 53%|█████▎ | 6365/11952 [2:59:44<8:58:27, 5.78s/it] 53%|█████▎ | 6366/11952 [2:59:50<8:55:36, 5.75s/it] {'loss': 0.4686, 'learning_rate': 9.42987434796858e-06, 'epoch': 0.53} + 53%|█████▎ | 6366/11952 [2:59:50<8:55:36, 5.75s/it] 53%|█████▎ | 6367/11952 [2:59:55<8:53:32, 5.73s/it] {'loss': 0.4639, 'learning_rate': 9.427168871885345e-06, 'epoch': 0.53} + 53%|█████▎ | 6367/11952 [2:59:55<8:53:32, 5.73s/it] 53%|█████▎ | 6368/11952 [3:00:02<9:07:04, 5.88s/it] {'loss': 0.4912, 'learning_rate': 9.424463437868445e-06, 'epoch': 0.53} + 53%|█████▎ | 6368/11952 [3:00:02<9:07:04, 5.88s/it] 53%|█████▎ | 6369/11952 [3:00:07<9:04:20, 5.85s/it] {'loss': 0.4673, 'learning_rate': 9.421758046116557e-06, 'epoch': 0.53} + 53%|█████▎ | 6369/11952 [3:00:07<9:04:20, 5.85s/it] 53%|█████▎ | 6370/11952 [3:00:13<9:04:32, 5.85s/it] {'loss': 0.4861, 'learning_rate': 9.419052696828352e-06, 'epoch': 0.53} + 53%|█████▎ | 6370/11952 [3:00:13<9:04:32, 5.85s/it] 53%|█████▎ | 6371/11952 [3:00:19<9:00:29, 5.81s/it] {'loss': 0.4816, 'learning_rate': 9.416347390202499e-06, 'epoch': 0.53} + 53%|█████▎ | 6371/11952 [3:00:19<9:00:29, 5.81s/it] 53%|█████▎ | 6372/11952 [3:00:25<8:58:50, 5.79s/it] {'loss': 0.4647, 'learning_rate': 9.41364212643767e-06, 'epoch': 0.53} + 53%|█████▎ | 6372/11952 [3:00:25<8:58:50, 5.79s/it] 53%|█████▎ | 6373/11952 [3:00:31<8:58:47, 5.79s/it] {'loss': 0.4781, 'learning_rate': 9.410936905732522e-06, 'epoch': 0.53} + 53%|█████▎ | 6373/11952 [3:00:31<8:58:47, 5.79s/it] 53%|█████▎ | 6374/11952 [3:00:36<9:01:25, 5.82s/it] {'loss': 0.4912, 'learning_rate': 9.40823172828572e-06, 'epoch': 0.53} + 53%|█████▎ | 6374/11952 [3:00:36<9:01:25, 5.82s/it] 53%|█████▎ | 6375/11952 [3:00:42<8:55:19, 5.76s/it] {'loss': 0.4641, 'learning_rate': 9.405526594295915e-06, 'epoch': 0.53} + 53%|█████▎ | 6375/11952 [3:00:42<8:55:19, 5.76s/it] 53%|█████▎ | 6376/11952 [3:00:48<8:57:01, 5.78s/it] {'loss': 0.4802, 'learning_rate': 9.402821503961766e-06, 'epoch': 0.53} + 53%|█████▎ | 6376/11952 [3:00:48<8:57:01, 5.78s/it] 53%|█████▎ | 6377/11952 [3:00:54<9:08:56, 5.91s/it] {'loss': 0.4938, 'learning_rate': 9.400116457481924e-06, 'epoch': 0.53} + 53%|█████▎ | 6377/11952 [3:00:54<9:08:56, 5.91s/it] 53%|█████▎ | 6378/11952 [3:01:00<9:08:59, 5.91s/it] {'loss': 0.4878, 'learning_rate': 9.397411455055028e-06, 'epoch': 0.53} + 53%|█████▎ | 6378/11952 [3:01:00<9:08:59, 5.91s/it] 53%|█████▎ | 6379/11952 [3:01:06<9:18:59, 6.02s/it] {'loss': 0.4762, 'learning_rate': 9.394706496879733e-06, 'epoch': 0.53} + 53%|█████▎ | 6379/11952 [3:01:06<9:18:59, 6.02s/it] 53%|█████▎ | 6380/11952 [3:01:12<9:21:01, 6.04s/it] {'loss': 0.4799, 'learning_rate': 9.392001583154675e-06, 'epoch': 0.53} + 53%|█████▎ | 6380/11952 [3:01:12<9:21:01, 6.04s/it] 53%|█████▎ | 6381/11952 [3:01:18<9:17:22, 6.00s/it] {'loss': 0.4966, 'learning_rate': 9.389296714078493e-06, 'epoch': 0.53} + 53%|█████▎ | 6381/11952 [3:01:18<9:17:22, 6.00s/it] 53%|█████▎ | 6382/11952 [3:01:24<9:18:03, 6.01s/it] {'loss': 0.4841, 'learning_rate': 9.386591889849819e-06, 'epoch': 0.53} + 53%|█████▎ | 6382/11952 [3:01:24<9:18:03, 6.01s/it] 53%|█████▎ | 6383/11952 [3:01:30<9:06:51, 5.89s/it] {'loss': 0.5037, 'learning_rate': 9.383887110667285e-06, 'epoch': 0.53} + 53%|█████▎ | 6383/11952 [3:01:30<9:06:51, 5.89s/it] 53%|█████▎ | 6384/11952 [3:01:35<8:59:10, 5.81s/it] {'loss': 0.4769, 'learning_rate': 9.381182376729516e-06, 'epoch': 0.53} + 53%|█████▎ | 6384/11952 [3:01:35<8:59:10, 5.81s/it] 53%|█████▎ | 6385/11952 [3:01:41<9:04:22, 5.87s/it] {'loss': 0.4716, 'learning_rate': 9.378477688235144e-06, 'epoch': 0.53} + 53%|█████▎ | 6385/11952 [3:01:41<9:04:22, 5.87s/it] 53%|█████▎ | 6386/11952 [3:01:47<8:55:30, 5.77s/it] {'loss': 0.4908, 'learning_rate': 9.375773045382782e-06, 'epoch': 0.53} + 53%|█████▎ | 6386/11952 [3:01:47<8:55:30, 5.77s/it] 53%|█████▎ | 6387/11952 [3:01:53<8:52:41, 5.74s/it] {'loss': 0.4506, 'learning_rate': 9.373068448371054e-06, 'epoch': 0.53} + 53%|█████▎ | 6387/11952 [3:01:53<8:52:41, 5.74s/it] 53%|█████▎ | 6388/11952 [3:01:59<9:01:30, 5.84s/it] {'loss': 0.4837, 'learning_rate': 9.370363897398573e-06, 'epoch': 0.53} + 53%|█████▎ | 6388/11952 [3:01:59<9:01:30, 5.84s/it] 53%|█████▎ | 6389/11952 [3:02:04<8:57:31, 5.80s/it] {'loss': 0.4797, 'learning_rate': 9.367659392663947e-06, 'epoch': 0.53} + 53%|█████▎ | 6389/11952 [3:02:04<8:57:31, 5.80s/it] 53%|█████▎ | 6390/11952 [3:02:10<8:59:36, 5.82s/it] {'loss': 0.4906, 'learning_rate': 9.364954934365783e-06, 'epoch': 0.53} + 53%|█████▎ | 6390/11952 [3:02:10<8:59:36, 5.82s/it] 53%|█████▎ | 6391/11952 [3:02:16<8:54:55, 5.77s/it] {'loss': 0.4653, 'learning_rate': 9.362250522702685e-06, 'epoch': 0.53} + 53%|█████▎ | 6391/11952 [3:02:16<8:54:55, 5.77s/it] 53%|█████▎ | 6392/11952 [3:02:22<8:52:28, 5.75s/it] {'loss': 0.4811, 'learning_rate': 9.35954615787326e-06, 'epoch': 0.53} + 53%|█████▎ | 6392/11952 [3:02:22<8:52:28, 5.75s/it] 53%|█████▎ | 6393/11952 [3:02:27<8:52:08, 5.74s/it] {'loss': 0.4746, 'learning_rate': 9.356841840076102e-06, 'epoch': 0.53} + 53%|█████▎ | 6393/11952 [3:02:27<8:52:08, 5.74s/it] 53%|█████▎ | 6394/11952 [3:02:33<8:52:21, 5.75s/it] {'loss': 0.4864, 'learning_rate': 9.354137569509804e-06, 'epoch': 0.53} + 53%|█████▎ | 6394/11952 [3:02:33<8:52:21, 5.75s/it] 54%|█████▎ | 6395/11952 [3:02:39<8:55:38, 5.78s/it] {'loss': 0.4882, 'learning_rate': 9.351433346372955e-06, 'epoch': 0.54} + 54%|█████▎ | 6395/11952 [3:02:39<8:55:38, 5.78s/it] 54%|█████▎ | 6396/11952 [3:02:45<8:52:18, 5.75s/it] {'loss': 0.4855, 'learning_rate': 9.348729170864145e-06, 'epoch': 0.54} + 54%|█████▎ | 6396/11952 [3:02:45<8:52:18, 5.75s/it] 54%|█████▎ | 6397/11952 [3:02:51<8:53:59, 5.77s/it] {'loss': 0.4606, 'learning_rate': 9.346025043181955e-06, 'epoch': 0.54} + 54%|█████▎ | 6397/11952 [3:02:51<8:53:59, 5.77s/it] 54%|█████▎ | 6398/11952 [3:02:57<9:06:28, 5.90s/it] {'loss': 0.482, 'learning_rate': 9.343320963524964e-06, 'epoch': 0.54} + 54%|█████▎ | 6398/11952 [3:02:57<9:06:28, 5.90s/it] 54%|█████▎ | 6399/11952 [3:03:03<9:05:35, 5.90s/it] {'loss': 0.4876, 'learning_rate': 9.340616932091752e-06, 'epoch': 0.54} + 54%|█████▎ | 6399/11952 [3:03:03<9:05:35, 5.90s/it]4 AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +53 AutoResumeHook: Checking whether to suspend...AutoResumeHook: Checking whether to suspend... + +01 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... + 54%|█████▎ | 6400/11952 [3:03:09<9:11:16, 5.96s/it] {'loss': 0.4936, 'learning_rate': 9.33791294908089e-06, 'epoch': 0.54} + 54%|█████▎ | 6400/11952 [3:03:09<9:11:16, 5.96s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-6400/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-6400/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/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( + 54%|█████▎ | 6401/11952 [3:03:40<20:42:50, 13.43s/it] {'loss': 0.495, 'learning_rate': 9.335209014690946e-06, 'epoch': 0.54} + 54%|█████▎ | 6401/11952 [3:03:40<20:42:50, 13.43s/it] 54%|█████▎ | 6402/11952 [3:03:45<17:12:49, 11.17s/it] {'loss': 0.4882, 'learning_rate': 9.332505129120489e-06, 'epoch': 0.54} + 54%|█████▎ | 6402/11952 [3:03:45<17:12:49, 11.17s/it] 54%|█████▎ | 6403/11952 [3:03:52<14:56:30, 9.69s/it] {'loss': 0.4871, 'learning_rate': 9.32980129256808e-06, 'epoch': 0.54} + 54%|█████▎ | 6403/11952 [3:03:52<14:56:30, 9.69s/it] 54%|█████▎ | 6404/11952 [3:03:58<13:18:20, 8.63s/it] {'loss': 0.4526, 'learning_rate': 9.327097505232274e-06, 'epoch': 0.54} + 54%|█████▎ | 6404/11952 [3:03:58<13:18:20, 8.63s/it] 54%|█████▎ | 6405/11952 [3:04:04<12:05:41, 7.85s/it] {'loss': 0.4816, 'learning_rate': 9.324393767311625e-06, 'epoch': 0.54} + 54%|█████▎ | 6405/11952 [3:04:04<12:05:41, 7.85s/it] 54%|█████▎ | 6406/11952 [3:04:10<11:24:53, 7.41s/it] {'loss': 0.4765, 'learning_rate': 9.321690079004691e-06, 'epoch': 0.54} + 54%|█████▎ | 6406/11952 [3:04:10<11:24:53, 7.41s/it] 54%|█████▎ | 6407/11952 [3:04:16<10:41:34, 6.94s/it] {'loss': 0.4737, 'learning_rate': 9.318986440510018e-06, 'epoch': 0.54} + 54%|█████▎ | 6407/11952 [3:04:16<10:41:34, 6.94s/it] 54%|█████▎ | 6408/11952 [3:04:22<10:21:35, 6.73s/it] {'loss': 0.4784, 'learning_rate': 9.316282852026147e-06, 'epoch': 0.54} + 54%|█████▎ | 6408/11952 [3:04:22<10:21:35, 6.73s/it] 54%|█████▎ | 6409/11952 [3:04:31<11:08:08, 7.23s/it] {'loss': 0.4744, 'learning_rate': 9.313579313751621e-06, 'epoch': 0.54} + 54%|█████▎ | 6409/11952 [3:04:31<11:08:08, 7.23s/it] 54%|█████▎ | 6410/11952 [3:04:37<10:28:27, 6.80s/it] {'loss': 0.4675, 'learning_rate': 9.310875825884972e-06, 'epoch': 0.54} + 54%|█████▎ | 6410/11952 [3:04:37<10:28:27, 6.80s/it] 54%|█████▎ | 6411/11952 [3:04:43<10:03:52, 6.54s/it] {'loss': 0.465, 'learning_rate': 9.308172388624739e-06, 'epoch': 0.54} + 54%|█████▎ | 6411/11952 [3:04:43<10:03:52, 6.54s/it] 54%|█████▎ | 6412/11952 [3:04:48<9:47:46, 6.37s/it] {'loss': 0.477, 'learning_rate': 9.305469002169442e-06, 'epoch': 0.54} + 54%|█████▎ | 6412/11952 [3:04:48<9:47:46, 6.37s/it] 54%|█████▎ | 6413/11952 [3:04:54<9:36:39, 6.25s/it] {'loss': 0.4649, 'learning_rate': 9.30276566671762e-06, 'epoch': 0.54} + 54%|█████▎ | 6413/11952 [3:04:54<9:36:39, 6.25s/it] 54%|█████▎ | 6414/11952 [3:05:00<9:24:00, 6.11s/it] {'loss': 0.4649, 'learning_rate': 9.300062382467785e-06, 'epoch': 0.54} + 54%|█████▎ | 6414/11952 [3:05:00<9:24:00, 6.11s/it] 54%|█████▎ | 6415/11952 [3:05:06<9:10:38, 5.97s/it] {'loss': 0.468, 'learning_rate': 9.29735914961846e-06, 'epoch': 0.54} + 54%|█████▎ | 6415/11952 [3:05:06<9:10:38, 5.97s/it] 54%|█████▎ | 6416/11952 [3:05:12<9:08:02, 5.94s/it] {'loss': 0.4863, 'learning_rate': 9.294655968368153e-06, 'epoch': 0.54} + 54%|█████▎ | 6416/11952 [3:05:12<9:08:02, 5.94s/it] 54%|█████▎ | 6417/11952 [3:05:18<9:08:03, 5.94s/it] {'loss': 0.4815, 'learning_rate': 9.291952838915379e-06, 'epoch': 0.54} + 54%|█████▎ | 6417/11952 [3:05:18<9:08:03, 5.94s/it] 54%|█████▎ | 6418/11952 [3:05:23<9:01:12, 5.87s/it] {'loss': 0.4916, 'learning_rate': 9.289249761458643e-06, 'epoch': 0.54} + 54%|█████▎ | 6418/11952 [3:05:23<9:01:12, 5.87s/it] 54%|█████▎ | 6419/11952 [3:05:29<8:57:59, 5.83s/it] {'loss': 0.4722, 'learning_rate': 9.286546736196447e-06, 'epoch': 0.54} + 54%|█████▎ | 6419/11952 [3:05:29<8:57:59, 5.83s/it] 54%|█████▎ | 6420/11952 [3:05:35<9:10:50, 5.97s/it] {'loss': 0.5097, 'learning_rate': 9.283843763327293e-06, 'epoch': 0.54} + 54%|█████▎ | 6420/11952 [3:05:35<9:10:50, 5.97s/it] 54%|█████▎ | 6421/11952 [3:05:41<9:10:49, 5.98s/it] {'loss': 0.4785, 'learning_rate': 9.281140843049674e-06, 'epoch': 0.54} + 54%|█████▎ | 6421/11952 [3:05:41<9:10:49, 5.98s/it] 54%|█████▎ | 6422/11952 [3:05:47<9:10:22, 5.97s/it] {'loss': 0.4712, 'learning_rate': 9.278437975562083e-06, 'epoch': 0.54} + 54%|█████▎ | 6422/11952 [3:05:47<9:10:22, 5.97s/it] 54%|█████▎ | 6423/11952 [3:05:53<9:02:27, 5.89s/it] {'loss': 0.4693, 'learning_rate': 9.275735161063006e-06, 'epoch': 0.54} + 54%|█████▎ | 6423/11952 [3:05:53<9:02:27, 5.89s/it] 54%|█████▎ | 6424/11952 [3:05:59<9:07:56, 5.95s/it] {'loss': 0.4631, 'learning_rate': 9.273032399750925e-06, 'epoch': 0.54} + 54%|█████▎ | 6424/11952 [3:05:59<9:07:56, 5.95s/it] 54%|█████▍ | 6425/11952 [3:06:05<9:03:45, 5.90s/it] {'loss': 0.4736, 'learning_rate': 9.270329691824318e-06, 'epoch': 0.54} + 54%|█████▍ | 6425/11952 [3:06:05<9:03:45, 5.90s/it] 54%|█████▍ | 6426/11952 [3:06:11<9:06:44, 5.94s/it] {'loss': 0.4763, 'learning_rate': 9.267627037481667e-06, 'epoch': 0.54} + 54%|█████▍ | 6426/11952 [3:06:11<9:06:44, 5.94s/it] 54%|█████▍ | 6427/11952 [3:06:17<9:09:02, 5.96s/it] {'loss': 0.475, 'learning_rate': 9.264924436921438e-06, 'epoch': 0.54} + 54%|█████▍ | 6427/11952 [3:06:17<9:09:02, 5.96s/it] 54%|█████▍ | 6428/11952 [3:06:23<9:09:53, 5.97s/it] {'loss': 0.5036, 'learning_rate': 9.262221890342104e-06, 'epoch': 0.54} + 54%|█████▍ | 6428/11952 [3:06:23<9:09:53, 5.97s/it] 54%|█████▍ | 6429/11952 [3:06:29<9:10:19, 5.98s/it] {'loss': 0.4682, 'learning_rate': 9.259519397942125e-06, 'epoch': 0.54} + 54%|█████▍ | 6429/11952 [3:06:29<9:10:19, 5.98s/it] 54%|█████▍ | 6430/11952 [3:06:35<9:03:11, 5.90s/it] {'loss': 0.4808, 'learning_rate': 9.256816959919962e-06, 'epoch': 0.54} + 54%|█████▍ | 6430/11952 [3:06:35<9:03:11, 5.90s/it] 54%|█████▍ | 6431/11952 [3:06:41<9:03:22, 5.91s/it] {'loss': 0.4676, 'learning_rate': 9.254114576474068e-06, 'epoch': 0.54} + 54%|█████▍ | 6431/11952 [3:06:41<9:03:22, 5.91s/it] 54%|█████▍ | 6432/11952 [3:06:47<9:03:04, 5.90s/it] {'loss': 0.4549, 'learning_rate': 9.251412247802896e-06, 'epoch': 0.54} + 54%|█████▍ | 6432/11952 [3:06:47<9:03:04, 5.90s/it] 54%|█████▍ | 6433/11952 [3:06:53<9:16:13, 6.05s/it] {'loss': 0.4904, 'learning_rate': 9.248709974104897e-06, 'epoch': 0.54} + 54%|█████▍ | 6433/11952 [3:06:53<9:16:13, 6.05s/it] 54%|█████▍ | 6434/11952 [3:06:59<9:16:21, 6.05s/it] {'loss': 0.4909, 'learning_rate': 9.246007755578514e-06, 'epoch': 0.54} + 54%|█████▍ | 6434/11952 [3:06:59<9:16:21, 6.05s/it] 54%|█████▍ | 6435/11952 [3:07:05<9:15:22, 6.04s/it] {'loss': 0.479, 'learning_rate': 9.243305592422184e-06, 'epoch': 0.54} + 54%|█████▍ | 6435/11952 [3:07:05<9:15:22, 6.04s/it] 54%|█████▍ | 6436/11952 [3:07:11<9:17:19, 6.06s/it] {'loss': 0.4879, 'learning_rate': 9.240603484834347e-06, 'epoch': 0.54} + 54%|█████▍ | 6436/11952 [3:07:11<9:17:19, 6.06s/it] 54%|█████▍ | 6437/11952 [3:07:17<9:18:24, 6.08s/it] {'loss': 0.4899, 'learning_rate': 9.237901433013427e-06, 'epoch': 0.54} + 54%|█████▍ | 6437/11952 [3:07:17<9:18:24, 6.08s/it] 54%|█████▍ | 6438/11952 [3:07:23<9:10:22, 5.99s/it] {'loss': 0.4525, 'learning_rate': 9.235199437157858e-06, 'epoch': 0.54} + 54%|█████▍ | 6438/11952 [3:07:23<9:10:22, 5.99s/it] 54%|█████▍ | 6439/11952 [3:07:29<9:08:45, 5.97s/it] {'loss': 0.4823, 'learning_rate': 9.232497497466057e-06, 'epoch': 0.54} + 54%|█████▍ | 6439/11952 [3:07:29<9:08:45, 5.97s/it] 54%|█████▍ | 6440/11952 [3:07:35<9:05:13, 5.94s/it] {'loss': 0.4723, 'learning_rate': 9.229795614136452e-06, 'epoch': 0.54} + 54%|█████▍ | 6440/11952 [3:07:35<9:05:13, 5.94s/it] 54%|█████▍ | 6441/11952 [3:07:41<9:03:30, 5.92s/it] {'loss': 0.4649, 'learning_rate': 9.227093787367454e-06, 'epoch': 0.54} + 54%|█████▍ | 6441/11952 [3:07:41<9:03:30, 5.92s/it] 54%|█████▍ | 6442/11952 [3:07:49<10:20:51, 6.76s/it] {'loss': 0.4885, 'learning_rate': 9.224392017357471e-06, 'epoch': 0.54} + 54%|█████▍ | 6442/11952 [3:07:49<10:20:51, 6.76s/it] 54%|█████▍ | 6443/11952 [3:07:55<9:54:24, 6.47s/it] {'loss': 0.4626, 'learning_rate': 9.221690304304915e-06, 'epoch': 0.54} + 54%|█████▍ | 6443/11952 [3:07:55<9:54:24, 6.47s/it] 54%|█████▍ | 6444/11952 [3:08:01<9:38:04, 6.30s/it] {'loss': 0.4568, 'learning_rate': 9.218988648408187e-06, 'epoch': 0.54} + 54%|█████▍ | 6444/11952 [3:08:01<9:38:04, 6.30s/it] 54%|█████▍ | 6445/11952 [3:08:07<9:29:02, 6.20s/it] {'loss': 0.4942, 'learning_rate': 9.216287049865681e-06, 'epoch': 0.54} + 54%|█████▍ | 6445/11952 [3:08:07<9:29:02, 6.20s/it] 54%|█████▍ | 6446/11952 [3:08:13<9:24:25, 6.15s/it] {'loss': 0.5012, 'learning_rate': 9.213585508875792e-06, 'epoch': 0.54} + 54%|█████▍ | 6446/11952 [3:08:13<9:24:25, 6.15s/it] 54%|█████▍ | 6447/11952 [3:08:19<9:12:19, 6.02s/it] {'loss': 0.4838, 'learning_rate': 9.210884025636916e-06, 'epoch': 0.54} + 54%|█████▍ | 6447/11952 [3:08:19<9:12:19, 6.02s/it] 54%|█████▍ | 6448/11952 [3:08:28<10:29:04, 6.86s/it] {'loss': 0.4744, 'learning_rate': 9.208182600347432e-06, 'epoch': 0.54} + 54%|█████▍ | 6448/11952 [3:08:28<10:29:04, 6.86s/it] 54%|█████▍ | 6449/11952 [3:08:34<10:05:32, 6.60s/it] {'loss': 0.4823, 'learning_rate': 9.20548123320573e-06, 'epoch': 0.54} + 54%|█████▍ | 6449/11952 [3:08:34<10:05:32, 6.60s/it]4 AutoResumeHook: Checking whether to suspend... +23 AutoResumeHook: Checking whether to suspend... +AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +06 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... + 54%|█████▍ | 6450/11952 [3:08:43<11:16:57, 7.38s/it]1 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4897, 'learning_rate': 9.20277992441018e-06, 'epoch': 0.54} + 54%|█████▍ | 6450/11952 [3:08:43<11:16:57, 7.38s/it] 54%|█████▍ | 6451/11952 [3:08:49<10:35:43, 6.93s/it] {'loss': 0.4671, 'learning_rate': 9.200078674159154e-06, 'epoch': 0.54} + 54%|█████▍ | 6451/11952 [3:08:49<10:35:43, 6.93s/it] 54%|█████▍ | 6452/11952 [3:08:54<10:03:23, 6.58s/it] {'loss': 0.4986, 'learning_rate': 9.197377482651023e-06, 'epoch': 0.54} + 54%|█████▍ | 6452/11952 [3:08:54<10:03:23, 6.58s/it] 54%|█████▍ | 6453/11952 [3:09:00<9:36:26, 6.29s/it] {'loss': 0.4702, 'learning_rate': 9.194676350084148e-06, 'epoch': 0.54} + 54%|█████▍ | 6453/11952 [3:09:00<9:36:26, 6.29s/it] 54%|█████▍ | 6454/11952 [3:09:09<10:43:48, 7.03s/it] {'loss': 0.4758, 'learning_rate': 9.191975276656898e-06, 'epoch': 0.54} + 54%|█████▍ | 6454/11952 [3:09:09<10:43:48, 7.03s/it] 54%|█████▍ | 6455/11952 [3:09:18<11:46:42, 7.71s/it] {'loss': 0.4712, 'learning_rate': 9.189274262567622e-06, 'epoch': 0.54} + 54%|█████▍ | 6455/11952 [3:09:18<11:46:42, 7.71s/it] 54%|█████▍ | 6456/11952 [3:09:24<10:59:22, 7.20s/it] {'loss': 0.4757, 'learning_rate': 9.186573308014672e-06, 'epoch': 0.54} + 54%|█████▍ | 6456/11952 [3:09:24<10:59:22, 7.20s/it] 54%|█████▍ | 6457/11952 [3:09:33<11:41:30, 7.66s/it] {'loss': 0.4419, 'learning_rate': 9.183872413196392e-06, 'epoch': 0.54} + 54%|█████▍ | 6457/11952 [3:09:33<11:41:30, 7.66s/it] 54%|█████▍ | 6458/11952 [3:09:39<10:48:15, 7.08s/it] {'loss': 0.483, 'learning_rate': 9.181171578311132e-06, 'epoch': 0.54} + 54%|█████▍ | 6458/11952 [3:09:39<10:48:15, 7.08s/it] 54%|█████▍ | 6459/11952 [3:09:44<10:08:07, 6.64s/it] {'loss': 0.4725, 'learning_rate': 9.17847080355722e-06, 'epoch': 0.54} + 54%|█████▍ | 6459/11952 [3:09:44<10:08:07, 6.64s/it] 54%|█████▍ | 6460/11952 [3:09:50<9:44:09, 6.38s/it] {'loss': 0.4854, 'learning_rate': 9.175770089133e-06, 'epoch': 0.54} + 54%|█████▍ | 6460/11952 [3:09:50<9:44:09, 6.38s/it] 54%|█████▍ | 6461/11952 [3:09:58<10:30:16, 6.89s/it] {'loss': 0.5029, 'learning_rate': 9.173069435236796e-06, 'epoch': 0.54} + 54%|█████▍ | 6461/11952 [3:09:58<10:30:16, 6.89s/it] 54%|█████▍ | 6462/11952 [3:10:04<10:04:36, 6.61s/it] {'loss': 0.4741, 'learning_rate': 9.170368842066932e-06, 'epoch': 0.54} + 54%|█████▍ | 6462/11952 [3:10:04<10:04:36, 6.61s/it] 54%|█████▍ | 6463/11952 [3:10:10<9:38:58, 6.33s/it] {'loss': 0.4736, 'learning_rate': 9.167668309821729e-06, 'epoch': 0.54} + 54%|█████▍ | 6463/11952 [3:10:10<9:38:58, 6.33s/it] 54%|█████▍ | 6464/11952 [3:10:16<9:37:40, 6.32s/it] {'loss': 0.5017, 'learning_rate': 9.164967838699504e-06, 'epoch': 0.54} + 54%|█████▍ | 6464/11952 [3:10:16<9:37:40, 6.32s/it] 54%|█████▍ | 6465/11952 [3:10:22<9:30:22, 6.24s/it] {'loss': 0.4903, 'learning_rate': 9.162267428898568e-06, 'epoch': 0.54} + 54%|█████▍ | 6465/11952 [3:10:22<9:30:22, 6.24s/it] 54%|█████▍ | 6466/11952 [3:10:28<9:12:54, 6.05s/it] {'loss': 0.4764, 'learning_rate': 9.159567080617226e-06, 'epoch': 0.54} + 54%|█████▍ | 6466/11952 [3:10:28<9:12:54, 6.05s/it] 54%|█████▍ | 6467/11952 [3:10:33<9:02:43, 5.94s/it] {'loss': 0.4889, 'learning_rate': 9.156866794053783e-06, 'epoch': 0.54} + 54%|█████▍ | 6467/11952 [3:10:33<9:02:43, 5.94s/it] 54%|█████▍ | 6468/11952 [3:10:39<9:00:07, 5.91s/it] {'loss': 0.4664, 'learning_rate': 9.154166569406537e-06, 'epoch': 0.54} + 54%|█████▍ | 6468/11952 [3:10:39<9:00:07, 5.91s/it] 54%|█████▍ | 6469/11952 [3:10:45<9:08:29, 6.00s/it] {'loss': 0.494, 'learning_rate': 9.15146640687378e-06, 'epoch': 0.54} + 54%|█████▍ | 6469/11952 [3:10:45<9:08:29, 6.00s/it] 54%|█████▍ | 6470/11952 [3:10:51<9:02:11, 5.93s/it] {'loss': 0.4731, 'learning_rate': 9.148766306653801e-06, 'epoch': 0.54} + 54%|█████▍ | 6470/11952 [3:10:51<9:02:11, 5.93s/it] 54%|█████▍ | 6471/11952 [3:10:57<9:02:50, 5.94s/it] {'loss': 0.4908, 'learning_rate': 9.146066268944883e-06, 'epoch': 0.54} + 54%|█████▍ | 6471/11952 [3:10:57<9:02:50, 5.94s/it] 54%|█████▍ | 6472/11952 [3:11:03<8:59:19, 5.90s/it] {'loss': 0.4881, 'learning_rate': 9.143366293945305e-06, 'epoch': 0.54} + 54%|█████▍ | 6472/11952 [3:11:03<8:59:19, 5.90s/it] 54%|█████▍ | 6473/11952 [3:11:09<8:59:51, 5.91s/it] {'loss': 0.4623, 'learning_rate': 9.140666381853343e-06, 'epoch': 0.54} + 54%|█████▍ | 6473/11952 [3:11:09<8:59:51, 5.91s/it] 54%|█████▍ | 6474/11952 [3:11:15<8:55:56, 5.87s/it] {'loss': 0.4839, 'learning_rate': 9.137966532867268e-06, 'epoch': 0.54} + 54%|█████▍ | 6474/11952 [3:11:15<8:55:56, 5.87s/it] 54%|█████▍ | 6475/11952 [3:11:20<8:45:54, 5.76s/it] {'loss': 0.484, 'learning_rate': 9.135266747185348e-06, 'epoch': 0.54} + 54%|█████▍ | 6475/11952 [3:11:20<8:45:54, 5.76s/it] 54%|█████▍ | 6476/11952 [3:11:26<8:57:50, 5.89s/it] {'loss': 0.4819, 'learning_rate': 9.132567025005842e-06, 'epoch': 0.54} + 54%|█████▍ | 6476/11952 [3:11:26<8:57:50, 5.89s/it] 54%|█████▍ | 6477/11952 [3:11:33<9:05:06, 5.97s/it] {'loss': 0.4728, 'learning_rate': 9.129867366527004e-06, 'epoch': 0.54} + 54%|█████▍ | 6477/11952 [3:11:33<9:05:06, 5.97s/it] 54%|█████▍ | 6478/11952 [3:11:38<8:58:09, 5.90s/it] {'loss': 0.4608, 'learning_rate': 9.127167771947086e-06, 'epoch': 0.54} + 54%|█████▍ | 6478/11952 [3:11:38<8:58:09, 5.90s/it] 54%|█████▍ | 6479/11952 [3:11:44<8:58:28, 5.90s/it] {'loss': 0.4677, 'learning_rate': 9.12446824146434e-06, 'epoch': 0.54} + 54%|█████▍ | 6479/11952 [3:11:44<8:58:28, 5.90s/it] 54%|█████▍ | 6480/11952 [3:11:50<8:49:31, 5.81s/it] {'loss': 0.4838, 'learning_rate': 9.121768775276997e-06, 'epoch': 0.54} + 54%|█████▍ | 6480/11952 [3:11:50<8:49:31, 5.81s/it] 54%|█████▍ | 6481/11952 [3:11:55<8:44:36, 5.75s/it] {'loss': 0.4658, 'learning_rate': 9.11906937358331e-06, 'epoch': 0.54} + 54%|█████▍ | 6481/11952 [3:11:55<8:44:36, 5.75s/it] 54%|█████▍ | 6482/11952 [3:12:01<8:48:03, 5.79s/it] {'loss': 0.4829, 'learning_rate': 9.116370036581504e-06, 'epoch': 0.54} + 54%|█████▍ | 6482/11952 [3:12:01<8:48:03, 5.79s/it] 54%|█████▍ | 6483/11952 [3:12:07<8:49:20, 5.81s/it] {'loss': 0.4701, 'learning_rate': 9.113670764469803e-06, 'epoch': 0.54} + 54%|█████▍ | 6483/11952 [3:12:07<8:49:20, 5.81s/it] 54%|█████▍ | 6484/11952 [3:12:13<8:45:47, 5.77s/it] {'loss': 0.4751, 'learning_rate': 9.110971557446437e-06, 'epoch': 0.54} + 54%|█████▍ | 6484/11952 [3:12:13<8:45:47, 5.77s/it] 54%|█████▍ | 6485/11952 [3:12:18<8:39:13, 5.70s/it] {'loss': 0.4502, 'learning_rate': 9.108272415709624e-06, 'epoch': 0.54} + 54%|█████▍ | 6485/11952 [3:12:18<8:39:13, 5.70s/it] 54%|█████▍ | 6486/11952 [3:12:24<8:47:50, 5.79s/it] {'loss': 0.4784, 'learning_rate': 9.105573339457574e-06, 'epoch': 0.54} + 54%|█████▍ | 6486/11952 [3:12:24<8:47:50, 5.79s/it] 54%|█████▍ | 6487/11952 [3:12:30<8:49:43, 5.82s/it] {'loss': 0.4574, 'learning_rate': 9.102874328888493e-06, 'epoch': 0.54} + 54%|█████▍ | 6487/11952 [3:12:30<8:49:43, 5.82s/it] 54%|█████▍ | 6488/11952 [3:12:36<8:47:58, 5.80s/it] {'loss': 0.4764, 'learning_rate': 9.100175384200595e-06, 'epoch': 0.54} + 54%|█████▍ | 6488/11952 [3:12:36<8:47:58, 5.80s/it] 54%|█████▍ | 6489/11952 [3:12:42<8:48:15, 5.80s/it] {'loss': 0.4746, 'learning_rate': 9.097476505592074e-06, 'epoch': 0.54} + 54%|█████▍ | 6489/11952 [3:12:42<8:48:15, 5.80s/it] 54%|█████▍ | 6490/11952 [3:12:48<8:51:22, 5.84s/it] {'loss': 0.4867, 'learning_rate': 9.094777693261124e-06, 'epoch': 0.54} + 54%|█████▍ | 6490/11952 [3:12:48<8:51:22, 5.84s/it] 54%|█████▍ | 6491/11952 [3:12:54<8:56:03, 5.89s/it] {'loss': 0.4723, 'learning_rate': 9.092078947405937e-06, 'epoch': 0.54} + 54%|█████▍ | 6491/11952 [3:12:54<8:56:03, 5.89s/it] 54%|█████▍ | 6492/11952 [3:13:00<8:55:06, 5.88s/it] {'loss': 0.4829, 'learning_rate': 9.089380268224694e-06, 'epoch': 0.54} + 54%|█████▍ | 6492/11952 [3:13:00<8:55:06, 5.88s/it] 54%|█████▍ | 6493/11952 [3:13:05<8:47:46, 5.80s/it] {'loss': 0.4703, 'learning_rate': 9.086681655915574e-06, 'epoch': 0.54} + 54%|█████▍ | 6493/11952 [3:13:05<8:47:46, 5.80s/it] 54%|█████▍ | 6494/11952 [3:13:11<8:49:17, 5.82s/it] {'loss': 0.4804, 'learning_rate': 9.083983110676755e-06, 'epoch': 0.54} + 54%|█████▍ | 6494/11952 [3:13:11<8:49:17, 5.82s/it] 54%|█████▍ | 6495/11952 [3:13:17<8:48:14, 5.81s/it] {'loss': 0.4808, 'learning_rate': 9.081284632706408e-06, 'epoch': 0.54} + 54%|█████▍ | 6495/11952 [3:13:17<8:48:14, 5.81s/it] 54%|█████▍ | 6496/11952 [3:13:22<8:42:23, 5.74s/it] {'loss': 0.4923, 'learning_rate': 9.078586222202698e-06, 'epoch': 0.54} + 54%|█████▍ | 6496/11952 [3:13:22<8:42:23, 5.74s/it] 54%|█████▍ | 6497/11952 [3:13:28<8:45:49, 5.78s/it] {'loss': 0.4779, 'learning_rate': 9.075887879363783e-06, 'epoch': 0.54} + 54%|█████▍ | 6497/11952 [3:13:28<8:45:49, 5.78s/it] 54%|█████▍ | 6498/11952 [3:13:34<8:54:40, 5.88s/it] {'loss': 0.4824, 'learning_rate': 9.073189604387815e-06, 'epoch': 0.54} + 54%|█████▍ | 6498/11952 [3:13:34<8:54:40, 5.88s/it] 54%|█████▍ | 6499/11952 [3:13:40<8:46:17, 5.79s/it] {'loss': 0.4912, 'learning_rate': 9.07049139747295e-06, 'epoch': 0.54} + 54%|█████▍ | 6499/11952 [3:13:40<8:46:17, 5.79s/it]4 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... +053 AutoResumeHook: Checking whether to suspend...AutoResumeHook: Checking whether to suspend... + + 2 AutoResumeHook: Checking whether to suspend... +AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... + 54%|█████▍ | 6500/11952 [3:13:46<9:01:35, 5.96s/it]1 AutoResumeHook: Checking whether to suspend... + {'loss': 0.477, 'learning_rate': 9.06779325881733e-06, 'epoch': 0.54} + 54%|█████▍ | 6500/11952 [3:13:46<9:01:35, 5.96s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-6500/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-6500/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/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( + 54%|█████▍ | 6501/11952 [3:14:16<19:37:08, 12.96s/it] {'loss': 0.4758, 'learning_rate': 9.065095188619096e-06, 'epoch': 0.54} + 54%|█████▍ | 6501/11952 [3:14:16<19:37:08, 12.96s/it] 54%|█████▍ | 6502/11952 [3:14:22<16:26:26, 10.86s/it] {'loss': 0.467, 'learning_rate': 9.062397187076384e-06, 'epoch': 0.54} + 54%|█████▍ | 6502/11952 [3:14:22<16:26:26, 10.86s/it] 54%|█████▍ | 6503/11952 [3:14:27<14:09:19, 9.35s/it] {'loss': 0.4954, 'learning_rate': 9.059699254387323e-06, 'epoch': 0.54} + 54%|█████▍ | 6503/11952 [3:14:27<14:09:19, 9.35s/it] 54%|█████▍ | 6504/11952 [3:14:33<12:37:15, 8.34s/it] {'loss': 0.4689, 'learning_rate': 9.057001390750035e-06, 'epoch': 0.54} + 54%|█████▍ | 6504/11952 [3:14:33<12:37:15, 8.34s/it] 54%|█████▍ | 6505/11952 [3:14:39<11:31:02, 7.61s/it] {'loss': 0.4764, 'learning_rate': 9.054303596362646e-06, 'epoch': 0.54} + 54%|█████▍ | 6505/11952 [3:14:39<11:31:02, 7.61s/it] 54%|█████▍ | 6506/11952 [3:14:45<10:39:22, 7.04s/it] {'loss': 0.4866, 'learning_rate': 9.051605871423266e-06, 'epoch': 0.54} + 54%|█████▍ | 6506/11952 [3:14:45<10:39:22, 7.04s/it] 54%|█████▍ | 6507/11952 [3:14:51<10:10:28, 6.73s/it] {'loss': 0.4834, 'learning_rate': 9.048908216130002e-06, 'epoch': 0.54} + 54%|█████▍ | 6507/11952 [3:14:51<10:10:28, 6.73s/it] 54%|█████▍ | 6508/11952 [3:14:57<9:43:57, 6.44s/it] {'loss': 0.4618, 'learning_rate': 9.046210630680968e-06, 'epoch': 0.54} + 54%|█████▍ | 6508/11952 [3:14:57<9:43:57, 6.44s/it] 54%|█████▍ | 6509/11952 [3:15:03<9:25:57, 6.24s/it] {'loss': 0.4803, 'learning_rate': 9.043513115274257e-06, 'epoch': 0.54} + 54%|█████▍ | 6509/11952 [3:15:03<9:25:57, 6.24s/it] 54%|█████▍ | 6510/11952 [3:15:09<9:20:04, 6.17s/it] {'loss': 0.4672, 'learning_rate': 9.040815670107964e-06, 'epoch': 0.54} + 54%|█████▍ | 6510/11952 [3:15:09<9:20:04, 6.17s/it] 54%|█████▍ | 6511/11952 [3:15:14<9:09:20, 6.06s/it] {'loss': 0.4937, 'learning_rate': 9.038118295380179e-06, 'epoch': 0.54} + 54%|█████▍ | 6511/11952 [3:15:14<9:09:20, 6.06s/it] 54%|█████▍ | 6512/11952 [3:15:20<9:07:37, 6.04s/it] {'loss': 0.4753, 'learning_rate': 9.035420991288987e-06, 'epoch': 0.54} + 54%|█████▍ | 6512/11952 [3:15:20<9:07:37, 6.04s/it] 54%|█████▍ | 6513/11952 [3:15:26<9:10:21, 6.07s/it] {'loss': 0.4871, 'learning_rate': 9.032723758032462e-06, 'epoch': 0.54} + 54%|█████▍ | 6513/11952 [3:15:26<9:10:21, 6.07s/it] 55%|█████▍ | 6514/11952 [3:15:33<9:10:32, 6.07s/it] {'loss': 0.4761, 'learning_rate': 9.030026595808682e-06, 'epoch': 0.54} + 55%|█████▍ | 6514/11952 [3:15:33<9:10:32, 6.07s/it] 55%|█████▍ | 6515/11952 [3:15:39<9:12:14, 6.09s/it] {'loss': 0.509, 'learning_rate': 9.027329504815714e-06, 'epoch': 0.55} + 55%|█████▍ | 6515/11952 [3:15:39<9:12:14, 6.09s/it] 55%|█████▍ | 6516/11952 [3:15:45<9:07:14, 6.04s/it] {'loss': 0.4935, 'learning_rate': 9.024632485251624e-06, 'epoch': 0.55} + 55%|█████▍ | 6516/11952 [3:15:45<9:07:14, 6.04s/it] 55%|█████▍ | 6517/11952 [3:15:50<8:58:12, 5.94s/it] {'loss': 0.4866, 'learning_rate': 9.021935537314467e-06, 'epoch': 0.55} + 55%|█████▍ | 6517/11952 [3:15:50<8:58:12, 5.94s/it] 55%|█████▍ | 6518/11952 [3:15:56<8:53:01, 5.89s/it] {'loss': 0.4957, 'learning_rate': 9.019238661202296e-06, 'epoch': 0.55} + 55%|█████▍ | 6518/11952 [3:15:56<8:53:01, 5.89s/it] 55%|█████▍ | 6519/11952 [3:16:02<8:52:42, 5.88s/it] {'loss': 0.4776, 'learning_rate': 9.016541857113157e-06, 'epoch': 0.55} + 55%|█████▍ | 6519/11952 [3:16:02<8:52:42, 5.88s/it] 55%|█████▍ | 6520/11952 [3:16:08<8:44:44, 5.80s/it] {'loss': 0.4852, 'learning_rate': 9.013845125245095e-06, 'epoch': 0.55} + 55%|█████▍ | 6520/11952 [3:16:08<8:44:44, 5.80s/it] 55%|█████▍ | 6521/11952 [3:16:13<8:45:04, 5.80s/it] {'loss': 0.4643, 'learning_rate': 9.01114846579614e-06, 'epoch': 0.55} + 55%|█████▍ | 6521/11952 [3:16:13<8:45:04, 5.80s/it] 55%|█████▍ | 6522/11952 [3:16:19<8:48:11, 5.84s/it] {'loss': 0.4801, 'learning_rate': 9.008451878964336e-06, 'epoch': 0.55} + 55%|█████▍ | 6522/11952 [3:16:19<8:48:11, 5.84s/it] 55%|█████▍ | 6523/11952 [3:16:25<8:51:39, 5.88s/it] {'loss': 0.4683, 'learning_rate': 9.005755364947699e-06, 'epoch': 0.55} + 55%|█████▍ | 6523/11952 [3:16:25<8:51:39, 5.88s/it] 55%|█████▍ | 6524/11952 [3:16:31<8:45:58, 5.81s/it] {'loss': 0.4803, 'learning_rate': 9.00305892394425e-06, 'epoch': 0.55} + 55%|█████▍ | 6524/11952 [3:16:31<8:45:58, 5.81s/it] 55%|█████▍ | 6525/11952 [3:16:37<8:48:24, 5.84s/it] {'loss': 0.4789, 'learning_rate': 9.000362556152013e-06, 'epoch': 0.55} + 55%|█████▍ | 6525/11952 [3:16:37<8:48:24, 5.84s/it] 55%|█████▍ | 6526/11952 [3:16:43<8:59:04, 5.96s/it] {'loss': 0.4686, 'learning_rate': 8.997666261768989e-06, 'epoch': 0.55} + 55%|█████▍ | 6526/11952 [3:16:43<8:59:04, 5.96s/it] 55%|█████▍ | 6527/11952 [3:16:49<9:02:10, 6.00s/it] {'loss': 0.5007, 'learning_rate': 8.994970040993187e-06, 'epoch': 0.55} + 55%|█████▍ | 6527/11952 [3:16:49<9:02:10, 6.00s/it] 55%|█████▍ | 6528/11952 [3:16:55<9:00:40, 5.98s/it] {'loss': 0.4736, 'learning_rate': 8.9922738940226e-06, 'epoch': 0.55} + 55%|█████▍ | 6528/11952 [3:16:55<9:00:40, 5.98s/it] 55%|█████▍ | 6529/11952 [3:17:01<9:00:52, 5.98s/it] {'loss': 0.4812, 'learning_rate': 8.989577821055231e-06, 'epoch': 0.55} + 55%|█████▍ | 6529/11952 [3:17:01<9:00:52, 5.98s/it] 55%|█████▍ | 6530/11952 [3:17:07<9:00:14, 5.98s/it] {'loss': 0.49, 'learning_rate': 8.986881822289062e-06, 'epoch': 0.55} + 55%|█████▍ | 6530/11952 [3:17:07<9:00:14, 5.98s/it] 55%|█████▍ | 6531/11952 [3:17:13<8:59:09, 5.97s/it] {'loss': 0.4833, 'learning_rate': 8.98418589792208e-06, 'epoch': 0.55} + 55%|█████▍ | 6531/11952 [3:17:13<8:59:09, 5.97s/it] 55%|█████▍ | 6532/11952 [3:17:19<9:05:15, 6.04s/it] {'loss': 0.4741, 'learning_rate': 8.98149004815226e-06, 'epoch': 0.55} + 55%|█████▍ | 6532/11952 [3:17:19<9:05:15, 6.04s/it] 55%|█████▍ | 6533/11952 [3:17:25<8:53:48, 5.91s/it] {'loss': 0.4823, 'learning_rate': 8.978794273177576e-06, 'epoch': 0.55} + 55%|█████▍ | 6533/11952 [3:17:25<8:53:48, 5.91s/it] 55%|█████▍ | 6534/11952 [3:17:31<8:52:08, 5.89s/it] {'loss': 0.4539, 'learning_rate': 8.97609857319599e-06, 'epoch': 0.55} + 55%|█████▍ | 6534/11952 [3:17:31<8:52:08, 5.89s/it] 55%|█████▍ | 6535/11952 [3:17:36<8:49:29, 5.86s/it] {'loss': 0.4686, 'learning_rate': 8.973402948405466e-06, 'epoch': 0.55} + 55%|█████▍ | 6535/11952 [3:17:36<8:49:29, 5.86s/it] 55%|█████▍ | 6536/11952 [3:17:42<8:44:11, 5.81s/it] {'loss': 0.4727, 'learning_rate': 8.970707399003961e-06, 'epoch': 0.55} + 55%|█████▍ | 6536/11952 [3:17:42<8:44:11, 5.81s/it] 55%|█████▍ | 6537/11952 [3:17:48<8:43:41, 5.80s/it] {'loss': 0.4807, 'learning_rate': 8.968011925189426e-06, 'epoch': 0.55} + 55%|█████▍ | 6537/11952 [3:17:48<8:43:41, 5.80s/it] 55%|█████▍ | 6538/11952 [3:17:54<8:40:53, 5.77s/it] {'loss': 0.4661, 'learning_rate': 8.9653165271598e-06, 'epoch': 0.55} + 55%|█████▍ | 6538/11952 [3:17:54<8:40:53, 5.77s/it] 55%|█████▍ | 6539/11952 [3:17:59<8:41:13, 5.78s/it] {'loss': 0.4563, 'learning_rate': 8.962621205113025e-06, 'epoch': 0.55} + 55%|█████▍ | 6539/11952 [3:17:59<8:41:13, 5.78s/it] 55%|█████▍ | 6540/11952 [3:18:05<8:48:37, 5.86s/it] {'loss': 0.4915, 'learning_rate': 8.959925959247036e-06, 'epoch': 0.55} + 55%|█████▍ | 6540/11952 [3:18:05<8:48:37, 5.86s/it] 55%|█████▍ | 6541/11952 [3:18:11<8:45:12, 5.82s/it] {'loss': 0.4776, 'learning_rate': 8.957230789759752e-06, 'epoch': 0.55} + 55%|█████▍ | 6541/11952 [3:18:11<8:45:12, 5.82s/it] 55%|█████▍ | 6542/11952 [3:18:17<8:46:06, 5.83s/it] {'loss': 0.4824, 'learning_rate': 8.954535696849108e-06, 'epoch': 0.55} + 55%|█████▍ | 6542/11952 [3:18:17<8:46:06, 5.83s/it] 55%|█████▍ | 6543/11952 [3:18:23<8:47:06, 5.85s/it] {'loss': 0.4858, 'learning_rate': 8.951840680713013e-06, 'epoch': 0.55} + 55%|█████▍ | 6543/11952 [3:18:23<8:47:06, 5.85s/it] 55%|█████▍ | 6544/11952 [3:18:28<8:38:48, 5.76s/it] {'loss': 0.4641, 'learning_rate': 8.949145741549378e-06, 'epoch': 0.55} + 55%|█████▍ | 6544/11952 [3:18:28<8:38:48, 5.76s/it] 55%|█████▍ | 6545/11952 [3:18:34<8:41:12, 5.78s/it] {'loss': 0.4672, 'learning_rate': 8.946450879556108e-06, 'epoch': 0.55} + 55%|█████▍ | 6545/11952 [3:18:34<8:41:12, 5.78s/it] 55%|█████▍ | 6546/11952 [3:18:40<8:47:04, 5.85s/it] {'loss': 0.4964, 'learning_rate': 8.943756094931106e-06, 'epoch': 0.55} + 55%|█████▍ | 6546/11952 [3:18:40<8:47:04, 5.85s/it] 55%|█████▍ | 6547/11952 [3:18:46<8:44:08, 5.82s/it] {'loss': 0.4896, 'learning_rate': 8.941061387872263e-06, 'epoch': 0.55} + 55%|█████▍ | 6547/11952 [3:18:46<8:44:08, 5.82s/it] 55%|█████▍ | 6548/11952 [3:18:52<8:46:43, 5.85s/it] {'loss': 0.4759, 'learning_rate': 8.938366758577462e-06, 'epoch': 0.55} + 55%|█████▍ | 6548/11952 [3:18:52<8:46:43, 5.85s/it] 55%|█████▍ | 6549/11952 [3:18:58<8:44:16, 5.82s/it] {'loss': 0.4772, 'learning_rate': 8.935672207244596e-06, 'epoch': 0.55} + 55%|█████▍ | 6549/11952 [3:18:58<8:44:16, 5.82s/it]02 AutoResumeHook: Checking whether to suspend... + 6 AutoResumeHook: Checking whether to suspend...AutoResumeHook: Checking whether to suspend... + +3 AutoResumeHook: Checking whether to suspend... + 55%|█████▍ | 6550/11952 [3:19:04<8:45:13, 5.83s/it]5 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4732, 'learning_rate': 8.932977734071533e-06, 'epoch': 0.55} + 55%|█████▍ | 6550/11952 [3:19:04<8:45:13, 5.83s/it] 55%|█████▍ | 6551/11952 [3:19:10<8:48:38, 5.87s/it] {'loss': 0.4791, 'learning_rate': 8.93028333925615e-06, 'epoch': 0.55} + 55%|█████▍ | 6551/11952 [3:19:10<8:48:38, 5.87s/it] 55%|█████▍ | 6552/11952 [3:19:15<8:49:28, 5.88s/it] {'loss': 0.4696, 'learning_rate': 8.927589022996308e-06, 'epoch': 0.55} + 55%|█████▍ | 6552/11952 [3:19:15<8:49:28, 5.88s/it] 55%|█████▍ | 6553/11952 [3:19:21<8:48:31, 5.87s/it] {'loss': 0.4734, 'learning_rate': 8.92489478548987e-06, 'epoch': 0.55} + 55%|█████▍ | 6553/11952 [3:19:21<8:48:31, 5.87s/it] 55%|█████▍ | 6554/11952 [3:19:27<8:46:33, 5.85s/it] {'loss': 0.4917, 'learning_rate': 8.922200626934682e-06, 'epoch': 0.55} + 55%|█████▍ | 6554/11952 [3:19:27<8:46:33, 5.85s/it] 55%|█████▍ | 6555/11952 [3:19:33<8:50:09, 5.89s/it] {'loss': 0.4855, 'learning_rate': 8.919506547528599e-06, 'epoch': 0.55} + 55%|█████▍ | 6555/11952 [3:19:33<8:50:09, 5.89s/it] 55%|█████▍ | 6556/11952 [3:19:39<8:57:41, 5.98s/it] {'loss': 0.4893, 'learning_rate': 8.916812547469461e-06, 'epoch': 0.55} + 55%|█████▍ | 6556/11952 [3:19:39<8:57:41, 5.98s/it] 55%|█████▍ | 6557/11952 [3:19:45<8:56:02, 5.96s/it] {'loss': 0.4473, 'learning_rate': 8.914118626955106e-06, 'epoch': 0.55} + 55%|█████▍ | 6557/11952 [3:19:45<8:56:02, 5.96s/it] 55%|█████▍ | 6558/11952 [3:19:51<8:53:09, 5.93s/it] {'loss': 0.4829, 'learning_rate': 8.911424786183362e-06, 'epoch': 0.55} + 55%|█████▍ | 6558/11952 [3:19:51<8:53:09, 5.93s/it] 55%|█████▍ | 6559/11952 [3:19:57<9:00:30, 6.01s/it] {'loss': 0.4882, 'learning_rate': 8.908731025352055e-06, 'epoch': 0.55} + 55%|█████▍ | 6559/11952 [3:19:57<9:00:30, 6.01s/it] 55%|█████▍ | 6560/11952 [3:20:03<8:53:29, 5.94s/it] {'loss': 0.4827, 'learning_rate': 8.906037344659e-06, 'epoch': 0.55} + 55%|█████▍ | 6560/11952 [3:20:03<8:53:29, 5.94s/it] 55%|█████▍ | 6561/11952 [3:20:10<9:08:21, 6.10s/it] {'loss': 0.469, 'learning_rate': 8.903343744302016e-06, 'epoch': 0.55} + 55%|█████▍ | 6561/11952 [3:20:10<9:08:21, 6.10s/it] 55%|█████▍ | 6562/11952 [3:20:15<9:03:07, 6.05s/it] {'loss': 0.4783, 'learning_rate': 8.900650224478899e-06, 'epoch': 0.55} + 55%|█████▍ | 6562/11952 [3:20:15<9:03:07, 6.05s/it] 55%|█████▍ | 6563/11952 [3:20:21<8:53:54, 5.94s/it] {'loss': 0.4845, 'learning_rate': 8.897956785387463e-06, 'epoch': 0.55} + 55%|█████▍ | 6563/11952 [3:20:21<8:53:54, 5.94s/it] 55%|█████▍ | 6564/11952 [3:20:27<8:53:23, 5.94s/it] {'loss': 0.4707, 'learning_rate': 8.895263427225497e-06, 'epoch': 0.55} + 55%|█████▍ | 6564/11952 [3:20:27<8:53:23, 5.94s/it] 55%|█████▍ | 6565/11952 [3:20:33<8:52:05, 5.93s/it] {'loss': 0.4974, 'learning_rate': 8.89257015019079e-06, 'epoch': 0.55} + 55%|█████▍ | 6565/11952 [3:20:33<8:52:05, 5.93s/it] 55%|█████▍ | 6566/11952 [3:20:39<8:49:31, 5.90s/it] {'loss': 0.4709, 'learning_rate': 8.889876954481122e-06, 'epoch': 0.55} + 55%|█████▍ | 6566/11952 [3:20:39<8:49:31, 5.90s/it] 55%|█████▍ | 6567/11952 [3:20:44<8:38:22, 5.78s/it] {'loss': 0.4527, 'learning_rate': 8.887183840294274e-06, 'epoch': 0.55} + 55%|█████▍ | 6567/11952 [3:20:44<8:38:22, 5.78s/it] 55%|█████▍ | 6568/11952 [3:20:50<8:37:24, 5.77s/it] {'loss': 0.4861, 'learning_rate': 8.88449080782802e-06, 'epoch': 0.55} + 55%|█████▍ | 6568/11952 [3:20:50<8:37:24, 5.77s/it] 55%|█████▍ | 6569/11952 [3:20:56<8:35:58, 5.75s/it] {'loss': 0.4684, 'learning_rate': 8.881797857280113e-06, 'epoch': 0.55} + 55%|█████▍ | 6569/11952 [3:20:56<8:35:58, 5.75s/it] 55%|█████▍ | 6570/11952 [3:21:02<8:36:53, 5.76s/it] {'loss': 0.4724, 'learning_rate': 8.879104988848326e-06, 'epoch': 0.55} + 55%|█████▍ | 6570/11952 [3:21:02<8:36:53, 5.76s/it] 55%|█████▍ | 6571/11952 [3:21:07<8:35:29, 5.75s/it] {'loss': 0.4827, 'learning_rate': 8.876412202730405e-06, 'epoch': 0.55} + 55%|█████▍ | 6571/11952 [3:21:07<8:35:29, 5.75s/it] 55%|█████▍ | 6572/11952 [3:21:13<8:43:44, 5.84s/it] {'loss': 0.4686, 'learning_rate': 8.873719499124101e-06, 'epoch': 0.55} + 55%|█████▍ | 6572/11952 [3:21:13<8:43:44, 5.84s/it] 55%|█████▍ | 6573/11952 [3:21:19<8:49:21, 5.90s/it] {'loss': 0.4915, 'learning_rate': 8.871026878227151e-06, 'epoch': 0.55} + 55%|█████▍ | 6573/11952 [3:21:19<8:49:21, 5.90s/it] 55%|█████▌ | 6574/11952 [3:21:25<8:47:29, 5.89s/it] {'loss': 0.4946, 'learning_rate': 8.868334340237293e-06, 'epoch': 0.55} + 55%|█████▌ | 6574/11952 [3:21:25<8:47:29, 5.89s/it] 55%|█████▌ | 6575/11952 [3:21:31<8:46:00, 5.87s/it] {'loss': 0.4845, 'learning_rate': 8.86564188535225e-06, 'epoch': 0.55} + 55%|█████▌ | 6575/11952 [3:21:31<8:46:00, 5.87s/it] 55%|█████▌ | 6576/11952 [3:21:37<8:38:45, 5.79s/it] {'loss': 0.4632, 'learning_rate': 8.86294951376975e-06, 'epoch': 0.55} + 55%|█████▌ | 6576/11952 [3:21:37<8:38:45, 5.79s/it] 55%|█████▌ | 6577/11952 [3:21:42<8:36:18, 5.76s/it] {'loss': 0.4733, 'learning_rate': 8.86025722568751e-06, 'epoch': 0.55} + 55%|█████▌ | 6577/11952 [3:21:42<8:36:18, 5.76s/it] 55%|█████▌ | 6578/11952 [3:21:48<8:37:50, 5.78s/it] {'loss': 0.4629, 'learning_rate': 8.857565021303238e-06, 'epoch': 0.55} + 55%|█████▌ | 6578/11952 [3:21:48<8:37:50, 5.78s/it] 55%|█████▌ | 6579/11952 [3:21:54<8:40:18, 5.81s/it] {'loss': 0.4984, 'learning_rate': 8.85487290081464e-06, 'epoch': 0.55} + 55%|█████▌ | 6579/11952 [3:21:54<8:40:18, 5.81s/it] 55%|█████▌ | 6580/11952 [3:22:00<8:37:40, 5.78s/it] {'loss': 0.4787, 'learning_rate': 8.852180864419413e-06, 'epoch': 0.55} + 55%|█████▌ | 6580/11952 [3:22:00<8:37:40, 5.78s/it] 55%|█████▌ | 6581/11952 [3:22:06<8:38:01, 5.79s/it] {'loss': 0.4913, 'learning_rate': 8.84948891231525e-06, 'epoch': 0.55} + 55%|█████▌ | 6581/11952 [3:22:06<8:38:01, 5.79s/it] 55%|█████▌ | 6582/11952 [3:22:11<8:31:48, 5.72s/it] {'loss': 0.4955, 'learning_rate': 8.846797044699831e-06, 'epoch': 0.55} + 55%|█████▌ | 6582/11952 [3:22:11<8:31:48, 5.72s/it] 55%|█████▌ | 6583/11952 [3:22:17<8:42:43, 5.84s/it] {'loss': 0.478, 'learning_rate': 8.844105261770844e-06, 'epoch': 0.55} + 55%|█████▌ | 6583/11952 [3:22:17<8:42:43, 5.84s/it] 55%|█████▌ | 6584/11952 [3:22:23<8:37:57, 5.79s/it] {'loss': 0.4816, 'learning_rate': 8.84141356372596e-06, 'epoch': 0.55} + 55%|█████▌ | 6584/11952 [3:22:23<8:37:57, 5.79s/it] 55%|█████▌ | 6585/11952 [3:22:29<8:43:59, 5.86s/it] {'loss': 0.4711, 'learning_rate': 8.838721950762845e-06, 'epoch': 0.55} + 55%|█████▌ | 6585/11952 [3:22:29<8:43:59, 5.86s/it] 55%|█████▌ | 6586/11952 [3:22:35<8:38:00, 5.79s/it] {'loss': 0.4757, 'learning_rate': 8.836030423079157e-06, 'epoch': 0.55} + 55%|█████▌ | 6586/11952 [3:22:35<8:38:00, 5.79s/it] 55%|█████▌ | 6587/11952 [3:22:40<8:39:21, 5.81s/it] {'loss': 0.4635, 'learning_rate': 8.833338980872558e-06, 'epoch': 0.55} + 55%|█████▌ | 6587/11952 [3:22:40<8:39:21, 5.81s/it] 55%|█████▌ | 6588/11952 [3:22:46<8:40:55, 5.83s/it] {'loss': 0.4623, 'learning_rate': 8.830647624340689e-06, 'epoch': 0.55} + 55%|█████▌ | 6588/11952 [3:22:46<8:40:55, 5.83s/it] 55%|█████▌ | 6589/11952 [3:22:52<8:31:56, 5.73s/it] {'loss': 0.4898, 'learning_rate': 8.827956353681191e-06, 'epoch': 0.55} + 55%|█████▌ | 6589/11952 [3:22:52<8:31:56, 5.73s/it] 55%|█████▌ | 6590/11952 [3:22:58<8:42:55, 5.85s/it] {'loss': 0.4753, 'learning_rate': 8.82526516909171e-06, 'epoch': 0.55} + 55%|█████▌ | 6590/11952 [3:22:58<8:42:55, 5.85s/it] 55%|█████▌ | 6591/11952 [3:23:04<8:48:15, 5.91s/it] {'loss': 0.4799, 'learning_rate': 8.822574070769867e-06, 'epoch': 0.55} + 55%|█████▌ | 6591/11952 [3:23:04<8:48:15, 5.91s/it] 55%|█████▌ | 6592/11952 [3:23:10<8:43:14, 5.86s/it] {'loss': 0.4814, 'learning_rate': 8.819883058913285e-06, 'epoch': 0.55} + 55%|█████▌ | 6592/11952 [3:23:10<8:43:14, 5.86s/it] 55%|█████▌ | 6593/11952 [3:23:16<8:45:28, 5.88s/it] {'loss': 0.5005, 'learning_rate': 8.817192133719583e-06, 'epoch': 0.55} + 55%|█████▌ | 6593/11952 [3:23:16<8:45:28, 5.88s/it] 55%|█████▌ | 6594/11952 [3:23:22<8:44:11, 5.87s/it] {'loss': 0.4939, 'learning_rate': 8.814501295386373e-06, 'epoch': 0.55} + 55%|█████▌ | 6594/11952 [3:23:22<8:44:11, 5.87s/it] 55%|█████▌ | 6595/11952 [3:23:27<8:41:35, 5.84s/it] {'loss': 0.4781, 'learning_rate': 8.811810544111258e-06, 'epoch': 0.55} + 55%|█████▌ | 6595/11952 [3:23:27<8:41:35, 5.84s/it] 55%|█████▌ | 6596/11952 [3:23:33<8:33:29, 5.75s/it] {'loss': 0.4704, 'learning_rate': 8.809119880091829e-06, 'epoch': 0.55} + 55%|█████▌ | 6596/11952 [3:23:33<8:33:29, 5.75s/it] 55%|█████▌ | 6597/11952 [3:23:39<8:32:27, 5.74s/it] {'loss': 0.4791, 'learning_rate': 8.806429303525685e-06, 'epoch': 0.55} + 55%|█████▌ | 6597/11952 [3:23:39<8:32:27, 5.74s/it] 55%|█████▌ | 6598/11952 [3:23:44<8:34:21, 5.76s/it] {'loss': 0.4631, 'learning_rate': 8.803738814610409e-06, 'epoch': 0.55} + 55%|█████▌ | 6598/11952 [3:23:44<8:34:21, 5.76s/it] 55%|█████▌ | 6599/11952 [3:23:50<8:36:56, 5.79s/it] {'loss': 0.4904, 'learning_rate': 8.801048413543581e-06, 'epoch': 0.55} + 55%|█████▌ | 6599/11952 [3:23:50<8:36:56, 5.79s/it]2 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... +0 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... + 55%|█████▌ | 6600/11952 [3:23:56<8:41:37, 5.85s/it]5 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4783, 'learning_rate': 8.79835810052277e-06, 'epoch': 0.55} + 55%|█████▌ | 6600/11952 [3:23:56<8:41:37, 5.85s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-6600/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-6600/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/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( + 55%|█████▌ | 6601/11952 [3:24:26<19:33:01, 13.15s/it] {'loss': 0.4744, 'learning_rate': 8.79566787574554e-06, 'epoch': 0.55} + 55%|█████▌ | 6601/11952 [3:24:26<19:33:01, 13.15s/it] 55%|█████▌ | 6602/11952 [3:24:33<16:28:42, 11.09s/it] {'loss': 0.4782, 'learning_rate': 8.792977739409455e-06, 'epoch': 0.55} + 55%|█████▌ | 6602/11952 [3:24:33<16:28:42, 11.09s/it] 55%|█████▌ | 6603/11952 [3:24:38<14:07:33, 9.51s/it] {'loss': 0.478, 'learning_rate': 8.790287691712059e-06, 'epoch': 0.55} + 55%|█████▌ | 6603/11952 [3:24:38<14:07:33, 9.51s/it] 55%|█████▌ | 6604/11952 [3:24:44<12:25:44, 8.37s/it] {'loss': 0.4799, 'learning_rate': 8.78759773285091e-06, 'epoch': 0.55} + 55%|█████▌ | 6604/11952 [3:24:44<12:25:44, 8.37s/it] 55%|█████▌ | 6605/11952 [3:24:50<11:23:29, 7.67s/it] {'loss': 0.4553, 'learning_rate': 8.784907863023537e-06, 'epoch': 0.55} + 55%|█████▌ | 6605/11952 [3:24:50<11:23:29, 7.67s/it] 55%|█████▌ | 6606/11952 [3:24:56<10:27:36, 7.04s/it] {'loss': 0.4705, 'learning_rate': 8.782218082427478e-06, 'epoch': 0.55} + 55%|█████▌ | 6606/11952 [3:24:56<10:27:36, 7.04s/it] 55%|█████▌ | 6607/11952 [3:25:02<9:52:37, 6.65s/it] {'loss': 0.4689, 'learning_rate': 8.779528391260257e-06, 'epoch': 0.55} + 55%|█████▌ | 6607/11952 [3:25:02<9:52:37, 6.65s/it] 55%|█████▌ | 6608/11952 [3:25:07<9:30:31, 6.41s/it] {'loss': 0.4538, 'learning_rate': 8.776838789719396e-06, 'epoch': 0.55} + 55%|█████▌ | 6608/11952 [3:25:07<9:30:31, 6.41s/it] 55%|█████▌ | 6609/11952 [3:25:13<9:20:04, 6.29s/it] {'loss': 0.4857, 'learning_rate': 8.774149278002402e-06, 'epoch': 0.55} + 55%|█████▌ | 6609/11952 [3:25:13<9:20:04, 6.29s/it] 55%|█████▌ | 6610/11952 [3:25:19<9:00:44, 6.07s/it] {'loss': 0.4831, 'learning_rate': 8.771459856306791e-06, 'epoch': 0.55} + 55%|█████▌ | 6610/11952 [3:25:19<9:00:44, 6.07s/it] 55%|█████▌ | 6611/11952 [3:25:25<8:57:57, 6.04s/it] {'loss': 0.4744, 'learning_rate': 8.768770524830058e-06, 'epoch': 0.55} + 55%|█████▌ | 6611/11952 [3:25:25<8:57:57, 6.04s/it] 55%|█████▌ | 6612/11952 [3:25:31<8:49:20, 5.95s/it] {'loss': 0.4704, 'learning_rate': 8.766081283769695e-06, 'epoch': 0.55} + 55%|█████▌ | 6612/11952 [3:25:31<8:49:20, 5.95s/it] 55%|█████▌ | 6613/11952 [3:25:37<8:48:46, 5.94s/it] {'loss': 0.476, 'learning_rate': 8.763392133323192e-06, 'epoch': 0.55} + 55%|█████▌ | 6613/11952 [3:25:37<8:48:46, 5.94s/it] 55%|█████▌ | 6614/11952 [3:25:43<8:56:44, 6.03s/it] {'loss': 0.4742, 'learning_rate': 8.760703073688027e-06, 'epoch': 0.55} + 55%|█████▌ | 6614/11952 [3:25:43<8:56:44, 6.03s/it] 55%|█████▌ | 6615/11952 [3:25:49<8:48:14, 5.94s/it] {'loss': 0.469, 'learning_rate': 8.758014105061674e-06, 'epoch': 0.55} + 55%|█████▌ | 6615/11952 [3:25:49<8:48:14, 5.94s/it] 55%|█████▌ | 6616/11952 [3:25:55<8:53:20, 6.00s/it] {'loss': 0.4838, 'learning_rate': 8.755325227641596e-06, 'epoch': 0.55} + 55%|█████▌ | 6616/11952 [3:25:55<8:53:20, 6.00s/it] 55%|█████▌ | 6617/11952 [3:26:01<8:57:16, 6.04s/it] {'loss': 0.4951, 'learning_rate': 8.752636441625259e-06, 'epoch': 0.55} + 55%|█████▌ | 6617/11952 [3:26:01<8:57:16, 6.04s/it] 55%|█████▌ | 6618/11952 [3:26:07<8:49:16, 5.95s/it] {'loss': 0.4718, 'learning_rate': 8.749947747210112e-06, 'epoch': 0.55} + 55%|█████▌ | 6618/11952 [3:26:07<8:49:16, 5.95s/it] 55%|█████▌ | 6619/11952 [3:26:12<8:43:55, 5.89s/it] {'loss': 0.4653, 'learning_rate': 8.747259144593604e-06, 'epoch': 0.55} + 55%|█████▌ | 6619/11952 [3:26:12<8:43:55, 5.89s/it] 55%|█████▌ | 6620/11952 [3:26:18<8:45:17, 5.91s/it] {'loss': 0.472, 'learning_rate': 8.744570633973177e-06, 'epoch': 0.55} + 55%|█████▌ | 6620/11952 [3:26:18<8:45:17, 5.91s/it] 55%|█████▌ | 6621/11952 [3:26:24<8:42:17, 5.88s/it] {'loss': 0.4854, 'learning_rate': 8.741882215546259e-06, 'epoch': 0.55} + 55%|█████▌ | 6621/11952 [3:26:24<8:42:17, 5.88s/it] 55%|█████▌ | 6622/11952 [3:26:30<8:35:11, 5.80s/it] {'loss': 0.4681, 'learning_rate': 8.739193889510276e-06, 'epoch': 0.55} + 55%|█████▌ | 6622/11952 [3:26:30<8:35:11, 5.80s/it] 55%|█████▌ | 6623/11952 [3:26:36<8:40:32, 5.86s/it] {'loss': 0.4679, 'learning_rate': 8.736505656062648e-06, 'epoch': 0.55} + 55%|█████▌ | 6623/11952 [3:26:36<8:40:32, 5.86s/it] 55%|█████▌ | 6624/11952 [3:26:42<8:44:03, 5.90s/it] {'loss': 0.4907, 'learning_rate': 8.733817515400793e-06, 'epoch': 0.55} + 55%|█████▌ | 6624/11952 [3:26:42<8:44:03, 5.90s/it] 55%|█████▌ | 6625/11952 [3:26:48<8:49:00, 5.96s/it] {'loss': 0.4657, 'learning_rate': 8.731129467722113e-06, 'epoch': 0.55} + 55%|█████▌ | 6625/11952 [3:26:48<8:49:00, 5.96s/it] 55%|█████▌ | 6626/11952 [3:26:54<8:45:43, 5.92s/it] {'loss': 0.4657, 'learning_rate': 8.728441513224008e-06, 'epoch': 0.55} + 55%|█████▌ | 6626/11952 [3:26:54<8:45:43, 5.92s/it] 55%|█████▌ | 6627/11952 [3:27:00<8:43:48, 5.90s/it] {'loss': 0.4826, 'learning_rate': 8.725753652103868e-06, 'epoch': 0.55} + 55%|█████▌ | 6627/11952 [3:27:00<8:43:48, 5.90s/it] 55%|█████▌ | 6628/11952 [3:27:05<8:39:03, 5.85s/it] {'loss': 0.4653, 'learning_rate': 8.72306588455908e-06, 'epoch': 0.55} + 55%|█████▌ | 6628/11952 [3:27:05<8:39:03, 5.85s/it] 55%|█████▌ | 6629/11952 [3:27:11<8:44:57, 5.92s/it] {'loss': 0.4729, 'learning_rate': 8.720378210787024e-06, 'epoch': 0.55} + 55%|█████▌ | 6629/11952 [3:27:11<8:44:57, 5.92s/it] 55%|█████▌ | 6630/11952 [3:27:17<8:39:34, 5.86s/it] {'loss': 0.4685, 'learning_rate': 8.717690630985065e-06, 'epoch': 0.55} + 55%|█████▌ | 6630/11952 [3:27:17<8:39:34, 5.86s/it] 55%|█████▌ | 6631/11952 [3:27:23<8:49:08, 5.97s/it] {'loss': 0.4579, 'learning_rate': 8.715003145350576e-06, 'epoch': 0.55} + 55%|█████▌ | 6631/11952 [3:27:23<8:49:08, 5.97s/it] 55%|█████▌ | 6632/11952 [3:27:29<8:49:14, 5.97s/it] {'loss': 0.4743, 'learning_rate': 8.712315754080913e-06, 'epoch': 0.55} + 55%|█████▌ | 6632/11952 [3:27:29<8:49:14, 5.97s/it] 55%|█████▌ | 6633/11952 [3:27:35<8:46:28, 5.94s/it] {'loss': 0.4584, 'learning_rate': 8.709628457373421e-06, 'epoch': 0.55} + 55%|█████▌ | 6633/11952 [3:27:35<8:46:28, 5.94s/it] 56%|█████▌ | 6634/11952 [3:27:41<8:42:35, 5.90s/it] {'loss': 0.4803, 'learning_rate': 8.706941255425452e-06, 'epoch': 0.56} + 56%|█████▌ | 6634/11952 [3:27:41<8:42:35, 5.90s/it] 56%|█████▌ | 6635/11952 [3:27:47<8:36:27, 5.83s/it] {'loss': 0.4585, 'learning_rate': 8.704254148434338e-06, 'epoch': 0.56} + 56%|█████▌ | 6635/11952 [3:27:47<8:36:27, 5.83s/it] 56%|█████▌ | 6636/11952 [3:27:52<8:34:58, 5.81s/it] {'loss': 0.4726, 'learning_rate': 8.70156713659741e-06, 'epoch': 0.56} + 56%|█████▌ | 6636/11952 [3:27:52<8:34:58, 5.81s/it] 56%|█████▌ | 6637/11952 [3:27:58<8:30:33, 5.76s/it] {'loss': 0.4588, 'learning_rate': 8.698880220111987e-06, 'epoch': 0.56} + 56%|█████▌ | 6637/11952 [3:27:58<8:30:33, 5.76s/it] 56%|█████▌ | 6638/11952 [3:28:04<8:30:31, 5.76s/it] {'loss': 0.4938, 'learning_rate': 8.69619339917539e-06, 'epoch': 0.56} + 56%|█████▌ | 6638/11952 [3:28:04<8:30:31, 5.76s/it] 56%|█████▌ | 6639/11952 [3:28:09<8:30:02, 5.76s/it] {'loss': 0.4575, 'learning_rate': 8.69350667398493e-06, 'epoch': 0.56} + 56%|█████▌ | 6639/11952 [3:28:09<8:30:02, 5.76s/it] 56%|█████▌ | 6640/11952 [3:28:16<8:39:40, 5.87s/it] {'loss': 0.4914, 'learning_rate': 8.690820044737905e-06, 'epoch': 0.56} + 56%|█████▌ | 6640/11952 [3:28:16<8:39:40, 5.87s/it] 56%|█████▌ | 6641/11952 [3:28:21<8:34:19, 5.81s/it] {'loss': 0.4948, 'learning_rate': 8.688133511631611e-06, 'epoch': 0.56} + 56%|█████▌ | 6641/11952 [3:28:21<8:34:19, 5.81s/it] 56%|█████▌ | 6642/11952 [3:28:27<8:42:01, 5.90s/it] {'loss': 0.4842, 'learning_rate': 8.685447074863333e-06, 'epoch': 0.56} + 56%|█████▌ | 6642/11952 [3:28:27<8:42:01, 5.90s/it] 56%|█████▌ | 6643/11952 [3:28:33<8:37:54, 5.85s/it] {'loss': 0.4749, 'learning_rate': 8.682760734630357e-06, 'epoch': 0.56} + 56%|█████▌ | 6643/11952 [3:28:33<8:37:54, 5.85s/it] 56%|█████▌ | 6644/11952 [3:28:39<8:36:49, 5.84s/it] {'loss': 0.4753, 'learning_rate': 8.68007449112995e-06, 'epoch': 0.56} + 56%|█████▌ | 6644/11952 [3:28:39<8:36:49, 5.84s/it] 56%|█████▌ | 6645/11952 [3:28:45<8:33:03, 5.80s/it] {'loss': 0.4793, 'learning_rate': 8.677388344559386e-06, 'epoch': 0.56} + 56%|█████▌ | 6645/11952 [3:28:45<8:33:03, 5.80s/it] 56%|█████▌ | 6646/11952 [3:28:50<8:30:47, 5.78s/it] {'loss': 0.4646, 'learning_rate': 8.67470229511592e-06, 'epoch': 0.56} + 56%|█████▌ | 6646/11952 [3:28:50<8:30:47, 5.78s/it] 56%|█████▌ | 6647/11952 [3:28:56<8:35:00, 5.82s/it] {'loss': 0.4625, 'learning_rate': 8.672016342996805e-06, 'epoch': 0.56} + 56%|█████▌ | 6647/11952 [3:28:56<8:35:00, 5.82s/it] 56%|█████▌ | 6648/11952 [3:29:02<8:42:03, 5.91s/it] {'loss': 0.4775, 'learning_rate': 8.669330488399286e-06, 'epoch': 0.56} + 56%|█████▌ | 6648/11952 [3:29:02<8:42:03, 5.91s/it] 56%|█████▌ | 6649/11952 [3:29:08<8:38:16, 5.86s/it] {'loss': 0.4756, 'learning_rate': 8.6666447315206e-06, 'epoch': 0.56} + 56%|█████▌ | 6649/11952 [3:29:08<8:38:16, 5.86s/it]2 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... +07 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +AutoResumeHook: Checking whether to suspend... + 56%|█████▌ | 6650/11952 [3:29:14<8:43:37, 5.93s/it]5 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4676, 'learning_rate': 8.663959072557979e-06, 'epoch': 0.56} + 56%|█████▌ | 6650/11952 [3:29:14<8:43:37, 5.93s/it] 56%|█████▌ | 6651/11952 [3:29:20<8:34:31, 5.82s/it] {'loss': 0.4726, 'learning_rate': 8.66127351170865e-06, 'epoch': 0.56} + 56%|█████▌ | 6651/11952 [3:29:20<8:34:31, 5.82s/it] 56%|█████▌ | 6652/11952 [3:29:26<8:44:03, 5.93s/it] {'loss': 0.4714, 'learning_rate': 8.658588049169825e-06, 'epoch': 0.56} + 56%|█████▌ | 6652/11952 [3:29:26<8:44:03, 5.93s/it] 56%|█████▌ | 6653/11952 [3:29:32<8:37:23, 5.86s/it] {'loss': 0.4803, 'learning_rate': 8.655902685138712e-06, 'epoch': 0.56} + 56%|█████▌ | 6653/11952 [3:29:32<8:37:23, 5.86s/it] 56%|█████▌ | 6654/11952 [3:29:38<8:40:03, 5.89s/it] {'loss': 0.4892, 'learning_rate': 8.653217419812517e-06, 'epoch': 0.56} + 56%|█████▌ | 6654/11952 [3:29:38<8:40:03, 5.89s/it] 56%|█████▌ | 6655/11952 [3:29:44<8:42:17, 5.92s/it] {'loss': 0.4818, 'learning_rate': 8.650532253388435e-06, 'epoch': 0.56} + 56%|█████▌ | 6655/11952 [3:29:44<8:42:17, 5.92s/it] 56%|█████▌ | 6656/11952 [3:29:49<8:33:24, 5.82s/it] {'loss': 0.4835, 'learning_rate': 8.64784718606365e-06, 'epoch': 0.56} + 56%|█████▌ | 6656/11952 [3:29:49<8:33:24, 5.82s/it] 56%|█████▌ | 6657/11952 [3:29:55<8:31:02, 5.79s/it] {'loss': 0.4779, 'learning_rate': 8.64516221803534e-06, 'epoch': 0.56} + 56%|█████▌ | 6657/11952 [3:29:55<8:31:02, 5.79s/it] 56%|█████▌ | 6658/11952 [3:30:01<8:29:56, 5.78s/it] {'loss': 0.4493, 'learning_rate': 8.642477349500686e-06, 'epoch': 0.56} + 56%|█████▌ | 6658/11952 [3:30:01<8:29:56, 5.78s/it] 56%|█████▌ | 6659/11952 [3:30:07<8:30:37, 5.79s/it] {'loss': 0.486, 'learning_rate': 8.639792580656845e-06, 'epoch': 0.56} + 56%|█████▌ | 6659/11952 [3:30:07<8:30:37, 5.79s/it] 56%|█████▌ | 6660/11952 [3:30:12<8:29:54, 5.78s/it] {'loss': 0.4814, 'learning_rate': 8.637107911700984e-06, 'epoch': 0.56} + 56%|█████▌ | 6660/11952 [3:30:12<8:29:54, 5.78s/it] 56%|█████▌ | 6661/11952 [3:30:18<8:33:07, 5.82s/it] {'loss': 0.4684, 'learning_rate': 8.634423342830247e-06, 'epoch': 0.56} + 56%|█████▌ | 6661/11952 [3:30:18<8:33:07, 5.82s/it] 56%|█████▌ | 6662/11952 [3:30:24<8:27:46, 5.76s/it] {'loss': 0.4948, 'learning_rate': 8.631738874241781e-06, 'epoch': 0.56} + 56%|█████▌ | 6662/11952 [3:30:24<8:27:46, 5.76s/it] 56%|█████▌ | 6663/11952 [3:30:30<8:33:18, 5.82s/it] {'loss': 0.4751, 'learning_rate': 8.629054506132719e-06, 'epoch': 0.56} + 56%|█████▌ | 6663/11952 [3:30:30<8:33:18, 5.82s/it] 56%|█████▌ | 6664/11952 [3:30:36<8:39:44, 5.90s/it] {'loss': 0.4949, 'learning_rate': 8.62637023870019e-06, 'epoch': 0.56} + 56%|█████▌ | 6664/11952 [3:30:36<8:39:44, 5.90s/it] 56%|█████▌ | 6665/11952 [3:30:42<8:33:28, 5.83s/it] {'loss': 0.4846, 'learning_rate': 8.623686072141322e-06, 'epoch': 0.56} + 56%|█████▌ | 6665/11952 [3:30:42<8:33:28, 5.83s/it] 56%|█████▌ | 6666/11952 [3:30:47<8:29:27, 5.78s/it] {'loss': 0.5014, 'learning_rate': 8.621002006653223e-06, 'epoch': 0.56} + 56%|█████▌ | 6666/11952 [3:30:47<8:29:27, 5.78s/it] 56%|█████▌ | 6667/11952 [3:30:53<8:41:02, 5.92s/it] {'loss': 0.4761, 'learning_rate': 8.618318042433001e-06, 'epoch': 0.56} + 56%|█████▌ | 6667/11952 [3:30:53<8:41:02, 5.92s/it] 56%|█████▌ | 6668/11952 [3:30:59<8:34:34, 5.84s/it] {'loss': 0.455, 'learning_rate': 8.615634179677754e-06, 'epoch': 0.56} + 56%|█████▌ | 6668/11952 [3:30:59<8:34:34, 5.84s/it] 56%|█████▌ | 6669/11952 [3:31:05<8:39:57, 5.91s/it] {'loss': 0.4812, 'learning_rate': 8.612950418584575e-06, 'epoch': 0.56} + 56%|█████▌ | 6669/11952 [3:31:05<8:39:57, 5.91s/it] 56%|█████▌ | 6670/11952 [3:31:11<8:32:48, 5.83s/it] {'loss': 0.445, 'learning_rate': 8.610266759350551e-06, 'epoch': 0.56} + 56%|█████▌ | 6670/11952 [3:31:11<8:32:48, 5.83s/it] 56%|█████▌ | 6671/11952 [3:31:17<8:34:30, 5.85s/it] {'loss': 0.4593, 'learning_rate': 8.60758320217275e-06, 'epoch': 0.56} + 56%|█████▌ | 6671/11952 [3:31:17<8:34:30, 5.85s/it] 56%|█████▌ | 6672/11952 [3:31:23<8:42:28, 5.94s/it] {'loss': 0.48, 'learning_rate': 8.604899747248251e-06, 'epoch': 0.56} + 56%|█████▌ | 6672/11952 [3:31:23<8:42:28, 5.94s/it] 56%|█████▌ | 6673/11952 [3:31:29<8:39:15, 5.90s/it] {'loss': 0.485, 'learning_rate': 8.602216394774114e-06, 'epoch': 0.56} + 56%|█████▌ | 6673/11952 [3:31:29<8:39:15, 5.90s/it] 56%|█████▌ | 6674/11952 [3:31:35<8:44:08, 5.96s/it] {'loss': 0.4597, 'learning_rate': 8.599533144947386e-06, 'epoch': 0.56} + 56%|█████▌ | 6674/11952 [3:31:35<8:44:08, 5.96s/it] 56%|█████▌ | 6675/11952 [3:31:41<8:46:08, 5.98s/it] {'loss': 0.4916, 'learning_rate': 8.596849997965122e-06, 'epoch': 0.56} + 56%|█████▌ | 6675/11952 [3:31:41<8:46:08, 5.98s/it] 56%|█████▌ | 6676/11952 [3:31:46<8:36:31, 5.87s/it] {'loss': 0.4836, 'learning_rate': 8.594166954024359e-06, 'epoch': 0.56} + 56%|█████▌ | 6676/11952 [3:31:46<8:36:31, 5.87s/it] 56%|█████▌ | 6677/11952 [3:31:52<8:33:59, 5.85s/it] {'loss': 0.4712, 'learning_rate': 8.591484013322128e-06, 'epoch': 0.56} + 56%|█████▌ | 6677/11952 [3:31:52<8:33:59, 5.85s/it] 56%|█████▌ | 6678/11952 [3:31:58<8:42:56, 5.95s/it] {'loss': 0.4779, 'learning_rate': 8.588801176055447e-06, 'epoch': 0.56} + 56%|█████▌ | 6678/11952 [3:31:58<8:42:56, 5.95s/it] 56%|█████▌ | 6679/11952 [3:32:04<8:45:49, 5.98s/it] {'loss': 0.4899, 'learning_rate': 8.586118442421341e-06, 'epoch': 0.56} + 56%|█████▌ | 6679/11952 [3:32:04<8:45:49, 5.98s/it] 56%|█████▌ | 6680/11952 [3:32:10<8:42:40, 5.95s/it] {'loss': 0.4701, 'learning_rate': 8.583435812616817e-06, 'epoch': 0.56} + 56%|█████▌ | 6680/11952 [3:32:10<8:42:40, 5.95s/it] 56%|█████▌ | 6681/11952 [3:32:16<8:44:16, 5.97s/it] {'loss': 0.4788, 'learning_rate': 8.580753286838875e-06, 'epoch': 0.56} + 56%|█████▌ | 6681/11952 [3:32:16<8:44:16, 5.97s/it] 56%|█████▌ | 6682/11952 [3:32:23<8:50:43, 6.04s/it] {'loss': 0.4701, 'learning_rate': 8.57807086528451e-06, 'epoch': 0.56} + 56%|█████▌ | 6682/11952 [3:32:23<8:50:43, 6.04s/it] 56%|█████▌ | 6683/11952 [3:32:28<8:44:03, 5.97s/it] {'loss': 0.4718, 'learning_rate': 8.575388548150702e-06, 'epoch': 0.56} + 56%|█████▌ | 6683/11952 [3:32:28<8:44:03, 5.97s/it] 56%|█████▌ | 6684/11952 [3:32:34<8:38:25, 5.90s/it] {'loss': 0.4727, 'learning_rate': 8.572706335634437e-06, 'epoch': 0.56} + 56%|█████▌ | 6684/11952 [3:32:34<8:38:25, 5.90s/it] 56%|█████▌ | 6685/11952 [3:32:40<8:43:31, 5.96s/it] {'loss': 0.4729, 'learning_rate': 8.570024227932678e-06, 'epoch': 0.56} + 56%|█████▌ | 6685/11952 [3:32:40<8:43:31, 5.96s/it] 56%|█████▌ | 6686/11952 [3:32:46<8:43:46, 5.97s/it] {'loss': 0.4713, 'learning_rate': 8.567342225242397e-06, 'epoch': 0.56} + 56%|█████▌ | 6686/11952 [3:32:46<8:43:46, 5.97s/it] 56%|█████▌ | 6687/11952 [3:32:52<8:46:07, 6.00s/it] {'loss': 0.4734, 'learning_rate': 8.564660327760543e-06, 'epoch': 0.56} + 56%|█████▌ | 6687/11952 [3:32:52<8:46:07, 6.00s/it] 56%|█████▌ | 6688/11952 [3:32:58<8:40:20, 5.93s/it] {'loss': 0.4841, 'learning_rate': 8.561978535684065e-06, 'epoch': 0.56} + 56%|█████▌ | 6688/11952 [3:32:58<8:40:20, 5.93s/it] 56%|█████▌ | 6689/11952 [3:33:04<8:40:31, 5.93s/it] {'loss': 0.4794, 'learning_rate': 8.5592968492099e-06, 'epoch': 0.56} + 56%|█████▌ | 6689/11952 [3:33:04<8:40:31, 5.93s/it] 56%|█████▌ | 6690/11952 [3:33:10<8:39:27, 5.92s/it] {'loss': 0.4915, 'learning_rate': 8.556615268534984e-06, 'epoch': 0.56} + 56%|█████▌ | 6690/11952 [3:33:10<8:39:27, 5.92s/it] 56%|█████▌ | 6691/11952 [3:33:16<8:38:56, 5.92s/it] {'loss': 0.4734, 'learning_rate': 8.553933793856234e-06, 'epoch': 0.56} + 56%|█████▌ | 6691/11952 [3:33:16<8:38:56, 5.92s/it] 56%|█████▌ | 6692/11952 [3:33:22<8:46:16, 6.00s/it] {'loss': 0.4661, 'learning_rate': 8.551252425370577e-06, 'epoch': 0.56} + 56%|█████▌ | 6692/11952 [3:33:22<8:46:16, 6.00s/it] 56%|█████▌ | 6693/11952 [3:33:28<8:38:32, 5.92s/it] {'loss': 0.4723, 'learning_rate': 8.548571163274915e-06, 'epoch': 0.56} + 56%|█████▌ | 6693/11952 [3:33:28<8:38:32, 5.92s/it] 56%|█████▌ | 6694/11952 [3:33:33<8:31:15, 5.83s/it] {'loss': 0.4812, 'learning_rate': 8.54589000776615e-06, 'epoch': 0.56} + 56%|█████▌ | 6694/11952 [3:33:33<8:31:15, 5.83s/it] 56%|█████▌ | 6695/11952 [3:33:39<8:35:02, 5.88s/it] {'loss': 0.4868, 'learning_rate': 8.543208959041174e-06, 'epoch': 0.56} + 56%|█████▌ | 6695/11952 [3:33:39<8:35:02, 5.88s/it] 56%|█████▌ | 6696/11952 [3:33:45<8:34:34, 5.87s/it] {'loss': 0.4789, 'learning_rate': 8.540528017296876e-06, 'epoch': 0.56} + 56%|█████▌ | 6696/11952 [3:33:45<8:34:34, 5.87s/it] 56%|█████▌ | 6697/11952 [3:33:51<8:36:02, 5.89s/it] {'loss': 0.4894, 'learning_rate': 8.537847182730126e-06, 'epoch': 0.56} + 56%|█████▌ | 6697/11952 [3:33:51<8:36:02, 5.89s/it] 56%|█████▌ | 6698/11952 [3:33:57<8:31:05, 5.84s/it] {'loss': 0.4734, 'learning_rate': 8.535166455537795e-06, 'epoch': 0.56} + 56%|█████▌ | 6698/11952 [3:33:57<8:31:05, 5.84s/it] 56%|█████▌ | 6699/11952 [3:34:02<8:25:11, 5.77s/it] {'loss': 0.4674, 'learning_rate': 8.532485835916754e-06, 'epoch': 0.56} + 56%|█████▌ | 6699/11952 [3:34:02<8:25:11, 5.77s/it]2 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... +03 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... + 56%|█████▌ | 6700/11952 [3:34:08<8:20:03, 5.71s/it]5 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4828, 'learning_rate': 8.529805324063843e-06, 'epoch': 0.56} + 56%|█████▌ | 6700/11952 [3:34:08<8:20:03, 5.71s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-6700/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-6700/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/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( + 56%|█████▌ | 6701/11952 [3:34:38<19:00:39, 13.03s/it] {'loss': 0.4801, 'learning_rate': 8.527124920175918e-06, 'epoch': 0.56} + 56%|█████▌ | 6701/11952 [3:34:38<19:00:39, 13.03s/it] 56%|█████▌ | 6702/11952 [3:34:44<15:47:57, 10.83s/it] {'loss': 0.4383, 'learning_rate': 8.524444624449812e-06, 'epoch': 0.56} + 56%|█████▌ | 6702/11952 [3:34:44<15:47:57, 10.83s/it] 56%|█████▌ | 6703/11952 [3:34:50<13:33:10, 9.30s/it] {'loss': 0.4693, 'learning_rate': 8.521764437082355e-06, 'epoch': 0.56} + 56%|█████▌ | 6703/11952 [3:34:50<13:33:10, 9.30s/it] 56%|█████▌ | 6704/11952 [3:34:56<12:07:33, 8.32s/it] {'loss': 0.4689, 'learning_rate': 8.519084358270368e-06, 'epoch': 0.56} + 56%|█████▌ | 6704/11952 [3:34:56<12:07:33, 8.32s/it] 56%|█████▌ | 6705/11952 [3:35:01<10:59:36, 7.54s/it] {'loss': 0.4543, 'learning_rate': 8.516404388210668e-06, 'epoch': 0.56} + 56%|█████▌ | 6705/11952 [3:35:01<10:59:36, 7.54s/it] 56%|█████▌ | 6706/11952 [3:35:07<10:14:15, 7.03s/it] {'loss': 0.4868, 'learning_rate': 8.513724527100055e-06, 'epoch': 0.56} + 56%|█████▌ | 6706/11952 [3:35:07<10:14:15, 7.03s/it] 56%|█████▌ | 6707/11952 [3:35:13<9:39:17, 6.63s/it] {'loss': 0.4848, 'learning_rate': 8.511044775135336e-06, 'epoch': 0.56} + 56%|█████▌ | 6707/11952 [3:35:13<9:39:17, 6.63s/it] 56%|█████▌ | 6708/11952 [3:35:19<9:15:45, 6.36s/it] {'loss': 0.4832, 'learning_rate': 8.508365132513296e-06, 'epoch': 0.56} + 56%|█████▌ | 6708/11952 [3:35:19<9:15:45, 6.36s/it] 56%|█████▌ | 6709/11952 [3:35:24<9:01:26, 6.20s/it] {'loss': 0.4872, 'learning_rate': 8.505685599430715e-06, 'epoch': 0.56} + 56%|█████▌ | 6709/11952 [3:35:24<9:01:26, 6.20s/it] 56%|█████▌ | 6710/11952 [3:35:30<8:58:36, 6.16s/it] {'loss': 0.4848, 'learning_rate': 8.503006176084366e-06, 'epoch': 0.56} + 56%|█████▌ | 6710/11952 [3:35:30<8:58:36, 6.16s/it] 56%|█████▌ | 6711/11952 [3:35:36<8:54:57, 6.12s/it] {'loss': 0.4751, 'learning_rate': 8.50032686267102e-06, 'epoch': 0.56} + 56%|█████▌ | 6711/11952 [3:35:36<8:54:57, 6.12s/it] 56%|█████▌ | 6712/11952 [3:35:42<8:50:41, 6.08s/it] {'loss': 0.4748, 'learning_rate': 8.497647659387426e-06, 'epoch': 0.56} + 56%|█████▌ | 6712/11952 [3:35:42<8:50:41, 6.08s/it] 56%|█████▌ | 6713/11952 [3:35:48<8:45:01, 6.01s/it] {'loss': 0.4774, 'learning_rate': 8.494968566430346e-06, 'epoch': 0.56} + 56%|█████▌ | 6713/11952 [3:35:48<8:45:01, 6.01s/it] 56%|█████▌ | 6714/11952 [3:35:54<8:36:24, 5.92s/it] {'loss': 0.4901, 'learning_rate': 8.492289583996511e-06, 'epoch': 0.56} + 56%|█████▌ | 6714/11952 [3:35:54<8:36:24, 5.92s/it] 56%|█████▌ | 6715/11952 [3:36:00<8:31:21, 5.86s/it] {'loss': 0.477, 'learning_rate': 8.489610712282658e-06, 'epoch': 0.56} + 56%|█████▌ | 6715/11952 [3:36:00<8:31:21, 5.86s/it] 56%|█████▌ | 6716/11952 [3:36:06<8:34:16, 5.89s/it] {'loss': 0.4673, 'learning_rate': 8.486931951485515e-06, 'epoch': 0.56} + 56%|█████▌ | 6716/11952 [3:36:06<8:34:16, 5.89s/it] 56%|█████▌ | 6717/11952 [3:36:11<8:31:18, 5.86s/it] {'loss': 0.4684, 'learning_rate': 8.484253301801794e-06, 'epoch': 0.56} + 56%|█████▌ | 6717/11952 [3:36:11<8:31:18, 5.86s/it] 56%|█████▌ | 6718/11952 [3:36:17<8:35:20, 5.91s/it] {'loss': 0.4901, 'learning_rate': 8.481574763428208e-06, 'epoch': 0.56} + 56%|█████▌ | 6718/11952 [3:36:17<8:35:20, 5.91s/it] 56%|█████▌ | 6719/11952 [3:36:23<8:29:27, 5.84s/it] {'loss': 0.4841, 'learning_rate': 8.47889633656145e-06, 'epoch': 0.56} + 56%|█████▌ | 6719/11952 [3:36:23<8:29:27, 5.84s/it] 56%|█████▌ | 6720/11952 [3:36:29<8:26:58, 5.81s/it] {'loss': 0.4742, 'learning_rate': 8.476218021398224e-06, 'epoch': 0.56} + 56%|█████▌ | 6720/11952 [3:36:29<8:26:58, 5.81s/it] 56%|█████▌ | 6721/11952 [3:36:35<8:28:06, 5.83s/it] {'loss': 0.473, 'learning_rate': 8.473539818135205e-06, 'epoch': 0.56} + 56%|█████▌ | 6721/11952 [3:36:35<8:28:06, 5.83s/it] 56%|█████▌ | 6722/11952 [3:36:41<8:31:47, 5.87s/it] {'loss': 0.4822, 'learning_rate': 8.470861726969075e-06, 'epoch': 0.56} + 56%|█████▌ | 6722/11952 [3:36:41<8:31:47, 5.87s/it] 56%|█████▋ | 6723/11952 [3:36:46<8:23:02, 5.77s/it] {'loss': 0.4779, 'learning_rate': 8.4681837480965e-06, 'epoch': 0.56} + 56%|█████▋ | 6723/11952 [3:36:46<8:23:02, 5.77s/it] 56%|█████▋ | 6724/11952 [3:36:52<8:30:11, 5.86s/it] {'loss': 0.4748, 'learning_rate': 8.46550588171414e-06, 'epoch': 0.56} + 56%|█████▋ | 6724/11952 [3:36:52<8:30:11, 5.86s/it] 56%|█████▋ | 6725/11952 [3:36:58<8:33:18, 5.89s/it] {'loss': 0.4784, 'learning_rate': 8.462828128018642e-06, 'epoch': 0.56} + 56%|█████▋ | 6725/11952 [3:36:58<8:33:18, 5.89s/it] 56%|█████▋ | 6726/11952 [3:37:04<8:27:48, 5.83s/it] {'loss': 0.4835, 'learning_rate': 8.460150487206652e-06, 'epoch': 0.56} + 56%|█████▋ | 6726/11952 [3:37:04<8:27:48, 5.83s/it] 56%|█████▋ | 6727/11952 [3:37:10<8:32:32, 5.89s/it] {'loss': 0.4796, 'learning_rate': 8.45747295947481e-06, 'epoch': 0.56} + 56%|█████▋ | 6727/11952 [3:37:10<8:32:32, 5.89s/it] 56%|█████▋ | 6728/11952 [3:37:16<8:27:23, 5.83s/it] {'loss': 0.4778, 'learning_rate': 8.454795545019737e-06, 'epoch': 0.56} + 56%|█████▋ | 6728/11952 [3:37:16<8:27:23, 5.83s/it] 56%|█████▋ | 6729/11952 [3:37:22<8:32:23, 5.89s/it] {'loss': 0.4831, 'learning_rate': 8.452118244038052e-06, 'epoch': 0.56} + 56%|█████▋ | 6729/11952 [3:37:22<8:32:23, 5.89s/it] 56%|█████▋ | 6730/11952 [3:37:27<8:25:23, 5.81s/it] {'loss': 0.4749, 'learning_rate': 8.449441056726364e-06, 'epoch': 0.56} + 56%|█████▋ | 6730/11952 [3:37:27<8:25:23, 5.81s/it] 56%|█████▋ | 6731/11952 [3:37:33<8:26:30, 5.82s/it] {'loss': 0.4853, 'learning_rate': 8.446763983281276e-06, 'epoch': 0.56} + 56%|█████▋ | 6731/11952 [3:37:33<8:26:30, 5.82s/it] 56%|█████▋ | 6732/11952 [3:37:39<8:23:26, 5.79s/it] {'loss': 0.491, 'learning_rate': 8.444087023899377e-06, 'epoch': 0.56} + 56%|█████▋ | 6732/11952 [3:37:39<8:23:26, 5.79s/it] 56%|█████▋ | 6733/11952 [3:37:45<8:32:30, 5.89s/it] {'loss': 0.4564, 'learning_rate': 8.44141017877726e-06, 'epoch': 0.56} + 56%|█████▋ | 6733/11952 [3:37:45<8:32:30, 5.89s/it] 56%|█████▋ | 6734/11952 [3:37:51<8:26:22, 5.82s/it] {'loss': 0.4818, 'learning_rate': 8.438733448111496e-06, 'epoch': 0.56} + 56%|█████▋ | 6734/11952 [3:37:51<8:26:22, 5.82s/it] 56%|█████▋ | 6735/11952 [3:37:57<8:25:43, 5.82s/it] {'loss': 0.4734, 'learning_rate': 8.436056832098655e-06, 'epoch': 0.56} + 56%|█████▋ | 6735/11952 [3:37:57<8:25:43, 5.82s/it] 56%|█████▋ | 6736/11952 [3:38:02<8:20:00, 5.75s/it] {'loss': 0.4585, 'learning_rate': 8.433380330935293e-06, 'epoch': 0.56} + 56%|█████▋ | 6736/11952 [3:38:02<8:20:00, 5.75s/it] 56%|█████▋ | 6737/11952 [3:38:08<8:19:42, 5.75s/it] {'loss': 0.4646, 'learning_rate': 8.430703944817967e-06, 'epoch': 0.56} + 56%|█████▋ | 6737/11952 [3:38:08<8:19:42, 5.75s/it] 56%|█████▋ | 6738/11952 [3:38:14<8:21:02, 5.77s/it] {'loss': 0.4824, 'learning_rate': 8.428027673943213e-06, 'epoch': 0.56} + 56%|█████▋ | 6738/11952 [3:38:14<8:21:02, 5.77s/it] 56%|█████▋ | 6739/11952 [3:38:20<8:22:45, 5.79s/it] {'loss': 0.4706, 'learning_rate': 8.425351518507565e-06, 'epoch': 0.56} + 56%|█████▋ | 6739/11952 [3:38:20<8:22:45, 5.79s/it] 56%|█████▋ | 6740/11952 [3:38:25<8:21:21, 5.77s/it] {'loss': 0.4733, 'learning_rate': 8.422675478707556e-06, 'epoch': 0.56} + 56%|█████▋ | 6740/11952 [3:38:25<8:21:21, 5.77s/it] 56%|█████▋ | 6741/11952 [3:38:31<8:25:21, 5.82s/it] {'loss': 0.5001, 'learning_rate': 8.4199995547397e-06, 'epoch': 0.56} + 56%|█████▋ | 6741/11952 [3:38:31<8:25:21, 5.82s/it] 56%|█████▋ | 6742/11952 [3:38:37<8:21:02, 5.77s/it] {'loss': 0.4803, 'learning_rate': 8.417323746800504e-06, 'epoch': 0.56} + 56%|█████▋ | 6742/11952 [3:38:37<8:21:02, 5.77s/it] 56%|█████▋ | 6743/11952 [3:38:43<8:34:36, 5.93s/it] {'loss': 0.4705, 'learning_rate': 8.414648055086471e-06, 'epoch': 0.56} + 56%|█████▋ | 6743/11952 [3:38:43<8:34:36, 5.93s/it] 56%|█████▋ | 6744/11952 [3:38:49<8:33:34, 5.92s/it] {'loss': 0.4768, 'learning_rate': 8.41197247979409e-06, 'epoch': 0.56} + 56%|█████▋ | 6744/11952 [3:38:49<8:33:34, 5.92s/it] 56%|█████▋ | 6745/11952 [3:38:55<8:32:59, 5.91s/it] {'loss': 0.4859, 'learning_rate': 8.409297021119843e-06, 'epoch': 0.56} + 56%|█████▋ | 6745/11952 [3:38:55<8:32:59, 5.91s/it] 56%|█████▋ | 6746/11952 [3:39:01<8:26:27, 5.84s/it] {'loss': 0.4715, 'learning_rate': 8.406621679260206e-06, 'epoch': 0.56} + 56%|█████▋ | 6746/11952 [3:39:01<8:26:27, 5.84s/it] 56%|█████▋ | 6747/11952 [3:39:06<8:20:42, 5.77s/it] {'loss': 0.462, 'learning_rate': 8.403946454411645e-06, 'epoch': 0.56} + 56%|█████▋ | 6747/11952 [3:39:06<8:20:42, 5.77s/it] 56%|█████▋ | 6748/11952 [3:39:12<8:21:29, 5.78s/it] {'loss': 0.4751, 'learning_rate': 8.401271346770622e-06, 'epoch': 0.56} + 56%|█████▋ | 6748/11952 [3:39:12<8:21:29, 5.78s/it] 56%|█████▋ | 6749/11952 [3:39:18<8:24:38, 5.82s/it] {'loss': 0.4768, 'learning_rate': 8.398596356533581e-06, 'epoch': 0.56} + 56%|█████▋ | 6749/11952 [3:39:18<8:24:38, 5.82s/it]2 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend...0 + 7 AutoResumeHook: Checking whether to suspend... +AutoResumeHook: Checking whether to suspend... + 56%|█████▋ | 6750/11952 [3:39:24<8:23:23, 5.81s/it]1 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... + {'loss': 0.471, 'learning_rate': 8.395921483896963e-06, 'epoch': 0.56} + 56%|█████▋ | 6750/11952 [3:39:24<8:23:23, 5.81s/it] 56%|█████▋ | 6751/11952 [3:39:29<8:22:49, 5.80s/it] {'loss': 0.5009, 'learning_rate': 8.393246729057196e-06, 'epoch': 0.56} + 56%|█████▋ | 6751/11952 [3:39:29<8:22:49, 5.80s/it] 56%|█████▋ | 6752/11952 [3:39:35<8:28:05, 5.86s/it] {'loss': 0.4724, 'learning_rate': 8.39057209221071e-06, 'epoch': 0.56} + 56%|█████▋ | 6752/11952 [3:39:35<8:28:05, 5.86s/it] 57%|█████▋ | 6753/11952 [3:39:41<8:25:52, 5.84s/it] {'loss': 0.471, 'learning_rate': 8.38789757355391e-06, 'epoch': 0.56} + 57%|█████▋ | 6753/11952 [3:39:41<8:25:52, 5.84s/it] 57%|█████▋ | 6754/11952 [3:39:47<8:22:55, 5.81s/it] {'loss': 0.4789, 'learning_rate': 8.38522317328321e-06, 'epoch': 0.57} + 57%|█████▋ | 6754/11952 [3:39:47<8:22:55, 5.81s/it] 57%|█████▋ | 6755/11952 [3:39:53<8:31:37, 5.91s/it] {'loss': 0.4581, 'learning_rate': 8.382548891595006e-06, 'epoch': 0.57} + 57%|█████▋ | 6755/11952 [3:39:53<8:31:37, 5.91s/it] 57%|█████▋ | 6756/11952 [3:39:59<8:35:47, 5.96s/it] {'loss': 0.4895, 'learning_rate': 8.379874728685681e-06, 'epoch': 0.57} + 57%|█████▋ | 6756/11952 [3:39:59<8:35:47, 5.96s/it] 57%|█████▋ | 6757/11952 [3:40:05<8:31:17, 5.91s/it] {'loss': 0.4833, 'learning_rate': 8.37720068475162e-06, 'epoch': 0.57} + 57%|█████▋ | 6757/11952 [3:40:05<8:31:17, 5.91s/it] 57%|█████▋ | 6758/11952 [3:40:11<8:29:08, 5.88s/it] {'loss': 0.4793, 'learning_rate': 8.37452675998919e-06, 'epoch': 0.57} + 57%|█████▋ | 6758/11952 [3:40:11<8:29:08, 5.88s/it] 57%|█████▋ | 6759/11952 [3:40:17<8:32:47, 5.92s/it] {'loss': 0.4747, 'learning_rate': 8.371852954594755e-06, 'epoch': 0.57} + 57%|█████▋ | 6759/11952 [3:40:17<8:32:47, 5.92s/it] 57%|█████▋ | 6760/11952 [3:40:23<8:32:46, 5.93s/it] {'loss': 0.4749, 'learning_rate': 8.369179268764662e-06, 'epoch': 0.57} + 57%|█████▋ | 6760/11952 [3:40:23<8:32:46, 5.93s/it] 57%|█████▋ | 6761/11952 [3:40:29<8:30:32, 5.90s/it] {'loss': 0.4625, 'learning_rate': 8.366505702695264e-06, 'epoch': 0.57} + 57%|█████▋ | 6761/11952 [3:40:29<8:30:32, 5.90s/it] 57%|█████▋ | 6762/11952 [3:40:34<8:28:28, 5.88s/it] {'loss': 0.4828, 'learning_rate': 8.363832256582892e-06, 'epoch': 0.57} + 57%|█████▋ | 6762/11952 [3:40:34<8:28:28, 5.88s/it] 57%|█████▋ | 6763/11952 [3:40:40<8:18:22, 5.76s/it] {'loss': 0.4782, 'learning_rate': 8.361158930623877e-06, 'epoch': 0.57} + 57%|█████▋ | 6763/11952 [3:40:40<8:18:22, 5.76s/it] 57%|█████▋ | 6764/11952 [3:40:46<8:28:16, 5.88s/it] {'loss': 0.4788, 'learning_rate': 8.358485725014531e-06, 'epoch': 0.57} + 57%|█████▋ | 6764/11952 [3:40:46<8:28:16, 5.88s/it] 57%|█████▋ | 6765/11952 [3:40:52<8:21:10, 5.80s/it] {'loss': 0.4712, 'learning_rate': 8.355812639951168e-06, 'epoch': 0.57} + 57%|█████▋ | 6765/11952 [3:40:52<8:21:10, 5.80s/it] 57%|█████▋ | 6766/11952 [3:40:58<8:31:11, 5.91s/it] {'loss': 0.4894, 'learning_rate': 8.35313967563008e-06, 'epoch': 0.57} + 57%|█████▋ | 6766/11952 [3:40:58<8:31:11, 5.91s/it] 57%|█████▋ | 6767/11952 [3:41:04<8:32:32, 5.93s/it] {'loss': 0.4702, 'learning_rate': 8.350466832247568e-06, 'epoch': 0.57} + 57%|█████▋ | 6767/11952 [3:41:04<8:32:32, 5.93s/it] 57%|█████▋ | 6768/11952 [3:41:10<8:31:53, 5.92s/it] {'loss': 0.4668, 'learning_rate': 8.347794109999912e-06, 'epoch': 0.57} + 57%|█████▋ | 6768/11952 [3:41:10<8:31:53, 5.92s/it] 57%|█████▋ | 6769/11952 [3:41:16<8:29:51, 5.90s/it] {'loss': 0.4578, 'learning_rate': 8.345121509083384e-06, 'epoch': 0.57} + 57%|█████▋ | 6769/11952 [3:41:16<8:29:51, 5.90s/it] 57%|█████▋ | 6770/11952 [3:41:21<8:23:36, 5.83s/it] {'loss': 0.4826, 'learning_rate': 8.34244902969425e-06, 'epoch': 0.57} + 57%|█████▋ | 6770/11952 [3:41:21<8:23:36, 5.83s/it] 57%|█████▋ | 6771/11952 [3:41:27<8:32:53, 5.94s/it] {'loss': 0.4897, 'learning_rate': 8.339776672028765e-06, 'epoch': 0.57} + 57%|█████▋ | 6771/11952 [3:41:27<8:32:53, 5.94s/it] 57%|█████▋ | 6772/11952 [3:41:33<8:26:17, 5.86s/it] {'loss': 0.4767, 'learning_rate': 8.337104436283176e-06, 'epoch': 0.57} + 57%|█████▋ | 6772/11952 [3:41:33<8:26:17, 5.86s/it] 57%|█████▋ | 6773/11952 [3:41:39<8:22:08, 5.82s/it] {'loss': 0.5019, 'learning_rate': 8.334432322653717e-06, 'epoch': 0.57} + 57%|█████▋ | 6773/11952 [3:41:39<8:22:08, 5.82s/it] 57%|█████▋ | 6774/11952 [3:41:45<8:28:28, 5.89s/it] {'loss': 0.4777, 'learning_rate': 8.331760331336622e-06, 'epoch': 0.57} + 57%|█████▋ | 6774/11952 [3:41:45<8:28:28, 5.89s/it] 57%|█████▋ | 6775/11952 [3:41:51<8:23:43, 5.84s/it] {'loss': 0.4643, 'learning_rate': 8.329088462528113e-06, 'epoch': 0.57} + 57%|█████▋ | 6775/11952 [3:41:51<8:23:43, 5.84s/it] 57%|█████▋ | 6776/11952 [3:41:57<8:25:23, 5.86s/it] {'loss': 0.4687, 'learning_rate': 8.326416716424396e-06, 'epoch': 0.57} + 57%|█████▋ | 6776/11952 [3:41:57<8:25:23, 5.86s/it] 57%|█████▋ | 6777/11952 [3:42:02<8:25:51, 5.87s/it] {'loss': 0.4902, 'learning_rate': 8.323745093221672e-06, 'epoch': 0.57} + 57%|█████▋ | 6777/11952 [3:42:02<8:25:51, 5.87s/it] 57%|█████▋ | 6778/11952 [3:42:08<8:27:43, 5.89s/it] {'loss': 0.4804, 'learning_rate': 8.32107359311614e-06, 'epoch': 0.57} + 57%|█████▋ | 6778/11952 [3:42:08<8:27:43, 5.89s/it] 57%|█████▋ | 6779/11952 [3:42:14<8:30:43, 5.92s/it] {'loss': 0.4833, 'learning_rate': 8.318402216303978e-06, 'epoch': 0.57} + 57%|█████▋ | 6779/11952 [3:42:14<8:30:43, 5.92s/it] 57%|█████▋ | 6780/11952 [3:42:20<8:26:19, 5.87s/it] {'loss': 0.4916, 'learning_rate': 8.31573096298136e-06, 'epoch': 0.57} + 57%|█████▋ | 6780/11952 [3:42:20<8:26:19, 5.87s/it] 57%|█████▋ | 6781/11952 [3:42:26<8:22:38, 5.83s/it] {'loss': 0.4769, 'learning_rate': 8.313059833344459e-06, 'epoch': 0.57} + 57%|█████▋ | 6781/11952 [3:42:26<8:22:38, 5.83s/it] 57%|█████▋ | 6782/11952 [3:42:32<8:28:21, 5.90s/it] {'loss': 0.4853, 'learning_rate': 8.310388827589424e-06, 'epoch': 0.57} + 57%|█████▋ | 6782/11952 [3:42:32<8:28:21, 5.90s/it] 57%|█████▋ | 6783/11952 [3:42:38<8:31:18, 5.94s/it] {'loss': 0.4967, 'learning_rate': 8.30771794591241e-06, 'epoch': 0.57} + 57%|█████▋ | 6783/11952 [3:42:38<8:31:18, 5.94s/it] 57%|█████▋ | 6784/11952 [3:42:44<8:23:30, 5.85s/it] {'loss': 0.4618, 'learning_rate': 8.30504718850955e-06, 'epoch': 0.57} + 57%|█████▋ | 6784/11952 [3:42:44<8:23:30, 5.85s/it] 57%|█████▋ | 6785/11952 [3:42:50<8:29:59, 5.92s/it] {'loss': 0.4827, 'learning_rate': 8.302376555576974e-06, 'epoch': 0.57} + 57%|█████▋ | 6785/11952 [3:42:50<8:29:59, 5.92s/it] 57%|█████▋ | 6786/11952 [3:42:55<8:23:56, 5.85s/it] {'loss': 0.458, 'learning_rate': 8.299706047310803e-06, 'epoch': 0.57} + 57%|█████▋ | 6786/11952 [3:42:55<8:23:56, 5.85s/it] 57%|█████▋ | 6787/11952 [3:43:02<8:36:02, 5.99s/it] {'loss': 0.4838, 'learning_rate': 8.297035663907146e-06, 'epoch': 0.57} + 57%|█████▋ | 6787/11952 [3:43:02<8:36:02, 5.99s/it] 57%|█████▋ | 6788/11952 [3:43:08<8:32:32, 5.96s/it] {'loss': 0.4725, 'learning_rate': 8.294365405562107e-06, 'epoch': 0.57} + 57%|█████▋ | 6788/11952 [3:43:08<8:32:32, 5.96s/it] 57%|█████▋ | 6789/11952 [3:43:13<8:30:26, 5.93s/it] {'loss': 0.4844, 'learning_rate': 8.29169527247178e-06, 'epoch': 0.57} + 57%|█████▋ | 6789/11952 [3:43:13<8:30:26, 5.93s/it] 57%|█████▋ | 6790/11952 [3:43:20<8:34:15, 5.98s/it] {'loss': 0.479, 'learning_rate': 8.289025264832247e-06, 'epoch': 0.57} + 57%|█████▋ | 6790/11952 [3:43:20<8:34:15, 5.98s/it] 57%|█████▋ | 6791/11952 [3:43:25<8:25:24, 5.88s/it] {'loss': 0.4811, 'learning_rate': 8.286355382839584e-06, 'epoch': 0.57} + 57%|█████▋ | 6791/11952 [3:43:25<8:25:24, 5.88s/it] 57%|█████▋ | 6792/11952 [3:43:31<8:27:02, 5.90s/it] {'loss': 0.4781, 'learning_rate': 8.283685626689851e-06, 'epoch': 0.57} + 57%|█████▋ | 6792/11952 [3:43:31<8:27:02, 5.90s/it] 57%|█████▋ | 6793/11952 [3:43:37<8:30:24, 5.94s/it] {'loss': 0.4775, 'learning_rate': 8.281015996579106e-06, 'epoch': 0.57} + 57%|█████▋ | 6793/11952 [3:43:37<8:30:24, 5.94s/it] 57%|█████▋ | 6794/11952 [3:43:43<8:23:56, 5.86s/it] {'loss': 0.4994, 'learning_rate': 8.278346492703394e-06, 'epoch': 0.57} + 57%|█████▋ | 6794/11952 [3:43:43<8:23:56, 5.86s/it] 57%|█████▋ | 6795/11952 [3:43:49<8:23:48, 5.86s/it] {'loss': 0.4812, 'learning_rate': 8.275677115258761e-06, 'epoch': 0.57} + 57%|█████▋ | 6795/11952 [3:43:49<8:23:48, 5.86s/it] 57%|█████▋ | 6796/11952 [3:43:55<8:32:24, 5.96s/it] {'loss': 0.4621, 'learning_rate': 8.273007864441227e-06, 'epoch': 0.57} + 57%|█████▋ | 6796/11952 [3:43:55<8:32:24, 5.96s/it] 57%|█████▋ | 6797/11952 [3:44:01<8:28:25, 5.92s/it] {'loss': 0.4713, 'learning_rate': 8.27033874044681e-06, 'epoch': 0.57} + 57%|█████▋ | 6797/11952 [3:44:01<8:28:25, 5.92s/it] 57%|█████▋ | 6798/11952 [3:44:07<8:34:36, 5.99s/it] {'loss': 0.4923, 'learning_rate': 8.267669743471525e-06, 'epoch': 0.57} + 57%|█████▋ | 6798/11952 [3:44:07<8:34:36, 5.99s/it] 57%|█████▋ | 6799/11952 [3:44:13<8:30:30, 5.94s/it] {'loss': 0.4829, 'learning_rate': 8.265000873711368e-06, 'epoch': 0.57} + 57%|█████▋ | 6799/11952 [3:44:13<8:30:30, 5.94s/it]07 AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... + 57%|█████▋ | 6800/11952 [3:44:19<8:29:29, 5.93s/it]1 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4658, 'learning_rate': 8.262332131362326e-06, 'epoch': 0.57} + 57%|█████▋ | 6800/11952 [3:44:19<8:29:29, 5.93s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-6800/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-6800/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/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( + 57%|█████▋ | 6801/11952 [3:44:50<19:16:27, 13.47s/it] {'loss': 0.5034, 'learning_rate': 8.259663516620389e-06, 'epoch': 0.57} + 57%|█████▋ | 6801/11952 [3:44:50<19:16:27, 13.47s/it] 57%|█████▋ | 6802/11952 [3:44:56<16:01:43, 11.20s/it] {'loss': 0.4598, 'learning_rate': 8.256995029681526e-06, 'epoch': 0.57} + 57%|█████▋ | 6802/11952 [3:44:56<16:01:43, 11.20s/it] 57%|█████▋ | 6803/11952 [3:45:01<13:39:04, 9.54s/it] {'loss': 0.4704, 'learning_rate': 8.254326670741694e-06, 'epoch': 0.57} + 57%|█████▋ | 6803/11952 [3:45:01<13:39:04, 9.54s/it] 57%|█████▋ | 6804/11952 [3:45:07<12:11:01, 8.52s/it] {'loss': 0.4928, 'learning_rate': 8.251658439996854e-06, 'epoch': 0.57} + 57%|█████▋ | 6804/11952 [3:45:07<12:11:01, 8.52s/it] 57%|█████▋ | 6805/11952 [3:45:13<10:58:45, 7.68s/it] {'loss': 0.4666, 'learning_rate': 8.248990337642946e-06, 'epoch': 0.57} + 57%|█████▋ | 6805/11952 [3:45:13<10:58:45, 7.68s/it] 57%|█████▋ | 6806/11952 [3:45:19<10:14:43, 7.17s/it] {'loss': 0.4721, 'learning_rate': 8.246322363875904e-06, 'epoch': 0.57} + 57%|█████▋ | 6806/11952 [3:45:19<10:14:43, 7.17s/it] 57%|█████▋ | 6807/11952 [3:45:25<9:40:13, 6.77s/it] {'loss': 0.474, 'learning_rate': 8.24365451889165e-06, 'epoch': 0.57} + 57%|█████▋ | 6807/11952 [3:45:25<9:40:13, 6.77s/it] 57%|█████▋ | 6808/11952 [3:45:31<9:13:58, 6.46s/it] {'loss': 0.4743, 'learning_rate': 8.240986802886105e-06, 'epoch': 0.57} + 57%|█████▋ | 6808/11952 [3:45:31<9:13:58, 6.46s/it] 57%|█████▋ | 6809/11952 [3:45:37<9:01:29, 6.32s/it] {'loss': 0.4705, 'learning_rate': 8.238319216055175e-06, 'epoch': 0.57} + 57%|█████▋ | 6809/11952 [3:45:37<9:01:29, 6.32s/it] 57%|█████▋ | 6810/11952 [3:45:43<8:53:44, 6.23s/it] {'loss': 0.4877, 'learning_rate': 8.235651758594753e-06, 'epoch': 0.57} + 57%|█████▋ | 6810/11952 [3:45:43<8:53:44, 6.23s/it] 57%|█████▋ | 6811/11952 [3:45:48<8:40:54, 6.08s/it] {'loss': 0.4727, 'learning_rate': 8.23298443070073e-06, 'epoch': 0.57} + 57%|█████▋ | 6811/11952 [3:45:48<8:40:54, 6.08s/it] 57%|█████▋ | 6812/11952 [3:45:54<8:35:41, 6.02s/it] {'loss': 0.4659, 'learning_rate': 8.230317232568977e-06, 'epoch': 0.57} + 57%|█████▋ | 6812/11952 [3:45:54<8:35:41, 6.02s/it] 57%|█████▋ | 6813/11952 [3:46:00<8:28:10, 5.93s/it] {'loss': 0.4665, 'learning_rate': 8.227650164395369e-06, 'epoch': 0.57} + 57%|█████▋ | 6813/11952 [3:46:00<8:28:10, 5.93s/it] 57%|█████▋ | 6814/11952 [3:46:06<8:32:34, 5.99s/it] {'loss': 0.461, 'learning_rate': 8.224983226375756e-06, 'epoch': 0.57} + 57%|█████▋ | 6814/11952 [3:46:06<8:32:34, 5.99s/it] 57%|█████▋ | 6815/11952 [3:46:12<8:25:12, 5.90s/it] {'loss': 0.4809, 'learning_rate': 8.222316418705995e-06, 'epoch': 0.57} + 57%|█████▋ | 6815/11952 [3:46:12<8:25:12, 5.90s/it] 57%|█████▋ | 6816/11952 [3:46:18<8:25:26, 5.90s/it] {'loss': 0.4596, 'learning_rate': 8.219649741581925e-06, 'epoch': 0.57} + 57%|█████▋ | 6816/11952 [3:46:18<8:25:26, 5.90s/it] 57%|█████▋ | 6817/11952 [3:46:23<8:21:19, 5.86s/it] {'loss': 0.4577, 'learning_rate': 8.216983195199372e-06, 'epoch': 0.57} + 57%|█████▋ | 6817/11952 [3:46:23<8:21:19, 5.86s/it] 57%|█████▋ | 6818/11952 [3:46:30<8:26:12, 5.92s/it] {'loss': 0.4787, 'learning_rate': 8.214316779754154e-06, 'epoch': 0.57} + 57%|█████▋ | 6818/11952 [3:46:30<8:26:12, 5.92s/it] 57%|█████▋ | 6819/11952 [3:46:36<8:32:16, 5.99s/it] {'loss': 0.4803, 'learning_rate': 8.211650495442088e-06, 'epoch': 0.57} + 57%|█████▋ | 6819/11952 [3:46:36<8:32:16, 5.99s/it] 57%|█████▋ | 6820/11952 [3:46:41<8:26:02, 5.92s/it] {'loss': 0.4821, 'learning_rate': 8.20898434245897e-06, 'epoch': 0.57} + 57%|█████▋ | 6820/11952 [3:46:41<8:26:02, 5.92s/it] 57%|█████▋ | 6821/11952 [3:46:47<8:24:47, 5.90s/it] {'loss': 0.4678, 'learning_rate': 8.206318321000588e-06, 'epoch': 0.57} + 57%|█████▋ | 6821/11952 [3:46:47<8:24:47, 5.90s/it] 57%|█████▋ | 6822/11952 [3:46:53<8:19:53, 5.85s/it] {'loss': 0.501, 'learning_rate': 8.203652431262733e-06, 'epoch': 0.57} + 57%|█████▋ | 6822/11952 [3:46:53<8:19:53, 5.85s/it] 57%|█████▋ | 6823/11952 [3:46:59<8:29:13, 5.96s/it] {'loss': 0.4752, 'learning_rate': 8.200986673441173e-06, 'epoch': 0.57} + 57%|█████▋ | 6823/11952 [3:46:59<8:29:13, 5.96s/it] 57%|█████▋ | 6824/11952 [3:47:05<8:26:00, 5.92s/it] {'loss': 0.4762, 'learning_rate': 8.198321047731665e-06, 'epoch': 0.57} + 57%|█████▋ | 6824/11952 [3:47:05<8:26:00, 5.92s/it] 57%|█████▋ | 6825/11952 [3:47:11<8:22:54, 5.89s/it] {'loss': 0.4846, 'learning_rate': 8.195655554329969e-06, 'epoch': 0.57} + 57%|█████▋ | 6825/11952 [3:47:11<8:22:54, 5.89s/it] 57%|█████▋ | 6826/11952 [3:47:17<8:23:05, 5.89s/it] {'loss': 0.4847, 'learning_rate': 8.192990193431824e-06, 'epoch': 0.57} + 57%|█████▋ | 6826/11952 [3:47:17<8:23:05, 5.89s/it] 57%|█████▋ | 6827/11952 [3:47:23<8:23:36, 5.90s/it] {'loss': 0.4782, 'learning_rate': 8.19032496523296e-06, 'epoch': 0.57} + 57%|█████▋ | 6827/11952 [3:47:23<8:23:36, 5.90s/it] 57%|█████▋ | 6828/11952 [3:47:28<8:21:26, 5.87s/it] {'loss': 0.4777, 'learning_rate': 8.187659869929104e-06, 'epoch': 0.57} + 57%|█████▋ | 6828/11952 [3:47:28<8:21:26, 5.87s/it] 57%|█████▋ | 6829/11952 [3:47:34<8:22:15, 5.88s/it] {'loss': 0.4826, 'learning_rate': 8.184994907715969e-06, 'epoch': 0.57} + 57%|█████▋ | 6829/11952 [3:47:34<8:22:15, 5.88s/it] 57%|█████▋ | 6830/11952 [3:47:40<8:26:51, 5.94s/it] {'loss': 0.4972, 'learning_rate': 8.182330078789262e-06, 'epoch': 0.57} + 57%|█████▋ | 6830/11952 [3:47:40<8:26:51, 5.94s/it] 57%|█████▋ | 6831/11952 [3:47:46<8:21:23, 5.87s/it] {'loss': 0.4655, 'learning_rate': 8.179665383344674e-06, 'epoch': 0.57} + 57%|█████▋ | 6831/11952 [3:47:46<8:21:23, 5.87s/it] 57%|█████▋ | 6832/11952 [3:47:52<8:27:57, 5.95s/it] {'loss': 0.4884, 'learning_rate': 8.177000821577888e-06, 'epoch': 0.57} + 57%|█████▋ | 6832/11952 [3:47:52<8:27:57, 5.95s/it] 57%|█████▋ | 6833/11952 [3:47:58<8:26:21, 5.94s/it] {'loss': 0.4607, 'learning_rate': 8.174336393684577e-06, 'epoch': 0.57} + 57%|█████▋ | 6833/11952 [3:47:58<8:26:21, 5.94s/it] 57%|█████▋ | 6834/11952 [3:48:04<8:28:41, 5.96s/it] {'loss': 0.4567, 'learning_rate': 8.17167209986041e-06, 'epoch': 0.57} + 57%|█████▋ | 6834/11952 [3:48:04<8:28:41, 5.96s/it] 57%|█████▋ | 6835/11952 [3:48:10<8:25:49, 5.93s/it] {'loss': 0.4858, 'learning_rate': 8.169007940301034e-06, 'epoch': 0.57} + 57%|█████▋ | 6835/11952 [3:48:10<8:25:49, 5.93s/it] 57%|█████▋ | 6836/11952 [3:48:16<8:21:37, 5.88s/it] {'loss': 0.473, 'learning_rate': 8.166343915202106e-06, 'epoch': 0.57} + 57%|█████▋ | 6836/11952 [3:48:16<8:21:37, 5.88s/it] 57%|█████▋ | 6837/11952 [3:48:22<8:21:59, 5.89s/it] {'loss': 0.4651, 'learning_rate': 8.163680024759252e-06, 'epoch': 0.57} + 57%|█████▋ | 6837/11952 [3:48:22<8:21:59, 5.89s/it] 57%|█████▋ | 6838/11952 [3:48:28<8:18:28, 5.85s/it] {'loss': 0.4667, 'learning_rate': 8.161016269168101e-06, 'epoch': 0.57} + 57%|█████▋ | 6838/11952 [3:48:28<8:18:28, 5.85s/it] 57%|█████▋ | 6839/11952 [3:48:33<8:18:14, 5.85s/it] {'loss': 0.5024, 'learning_rate': 8.158352648624263e-06, 'epoch': 0.57} + 57%|█████▋ | 6839/11952 [3:48:33<8:18:14, 5.85s/it] 57%|█████▋ | 6840/11952 [3:48:39<8:19:46, 5.87s/it] {'loss': 0.478, 'learning_rate': 8.155689163323348e-06, 'epoch': 0.57} + 57%|█████▋ | 6840/11952 [3:48:39<8:19:46, 5.87s/it] 57%|█████▋ | 6841/11952 [3:48:45<8:23:37, 5.91s/it] {'loss': 0.4516, 'learning_rate': 8.153025813460947e-06, 'epoch': 0.57} + 57%|█████▋ | 6841/11952 [3:48:45<8:23:37, 5.91s/it] 57%|█████▋ | 6842/11952 [3:48:51<8:24:55, 5.93s/it] {'loss': 0.478, 'learning_rate': 8.15036259923265e-06, 'epoch': 0.57} + 57%|█████▋ | 6842/11952 [3:48:51<8:24:55, 5.93s/it] 57%|█████▋ | 6843/11952 [3:48:57<8:25:46, 5.94s/it] {'loss': 0.4709, 'learning_rate': 8.147699520834033e-06, 'epoch': 0.57} + 57%|█████▋ | 6843/11952 [3:48:57<8:25:46, 5.94s/it] 57%|█████▋ | 6844/11952 [3:49:03<8:16:00, 5.83s/it] {'loss': 0.4604, 'learning_rate': 8.145036578460656e-06, 'epoch': 0.57} + 57%|█████▋ | 6844/11952 [3:49:03<8:16:00, 5.83s/it] 57%|█████▋ | 6845/11952 [3:49:09<8:20:40, 5.88s/it] {'loss': 0.4652, 'learning_rate': 8.142373772308078e-06, 'epoch': 0.57} + 57%|█████▋ | 6845/11952 [3:49:09<8:20:40, 5.88s/it] 57%|█████▋ | 6846/11952 [3:49:15<8:24:25, 5.93s/it] {'loss': 0.4943, 'learning_rate': 8.139711102571846e-06, 'epoch': 0.57} + 57%|█████▋ | 6846/11952 [3:49:15<8:24:25, 5.93s/it] 57%|█████▋ | 6847/11952 [3:49:21<8:23:54, 5.92s/it] {'loss': 0.4631, 'learning_rate': 8.137048569447492e-06, 'epoch': 0.57} + 57%|█████▋ | 6847/11952 [3:49:21<8:23:54, 5.92s/it] 57%|█████▋ | 6848/11952 [3:49:27<8:34:15, 6.05s/it] {'loss': 0.4891, 'learning_rate': 8.134386173130539e-06, 'epoch': 0.57} + 57%|█████▋ | 6848/11952 [3:49:27<8:34:15, 6.05s/it] 57%|█████▋ | 6849/11952 [3:49:33<8:26:39, 5.96s/it] {'loss': 0.4725, 'learning_rate': 8.131723913816508e-06, 'epoch': 0.57} + 57%|█████▋ | 6849/11952 [3:49:33<8:26:39, 5.96s/it]7 AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... +0 AutoResumeHook: Checking whether to suspend...6 AutoResumeHook: Checking whether to suspend... + + 57%|█████▋ | 6850/11952 [3:49:39<8:22:56, 5.91s/it]4 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4699, 'learning_rate': 8.129061791700903e-06, 'epoch': 0.57} + 57%|█████▋ | 6850/11952 [3:49:39<8:22:56, 5.91s/it] 57%|█████▋ | 6851/11952 [3:49:45<8:25:55, 5.95s/it] {'loss': 0.4892, 'learning_rate': 8.126399806979217e-06, 'epoch': 0.57} + 57%|█████▋ | 6851/11952 [3:49:45<8:25:55, 5.95s/it] 57%|█████▋ | 6852/11952 [3:49:50<8:18:30, 5.86s/it] {'loss': 0.4647, 'learning_rate': 8.123737959846937e-06, 'epoch': 0.57} + 57%|█████▋ | 6852/11952 [3:49:50<8:18:30, 5.86s/it] 57%|█████▋ | 6853/11952 [3:49:56<8:21:42, 5.90s/it] {'loss': 0.4725, 'learning_rate': 8.121076250499539e-06, 'epoch': 0.57} + 57%|█████▋ | 6853/11952 [3:49:56<8:21:42, 5.90s/it] 57%|█████▋ | 6854/11952 [3:50:02<8:15:18, 5.83s/it] {'loss': 0.4585, 'learning_rate': 8.118414679132484e-06, 'epoch': 0.57} + 57%|█████▋ | 6854/11952 [3:50:02<8:15:18, 5.83s/it] 57%|█████▋ | 6855/11952 [3:50:08<8:08:06, 5.75s/it] {'loss': 0.481, 'learning_rate': 8.115753245941225e-06, 'epoch': 0.57} + 57%|█████▋ | 6855/11952 [3:50:08<8:08:06, 5.75s/it] 57%|█████▋ | 6856/11952 [3:50:13<8:11:18, 5.78s/it] {'loss': 0.4593, 'learning_rate': 8.113091951121215e-06, 'epoch': 0.57} + 57%|█████▋ | 6856/11952 [3:50:13<8:11:18, 5.78s/it] 57%|█████▋ | 6857/11952 [3:50:19<8:14:41, 5.83s/it] {'loss': 0.4727, 'learning_rate': 8.110430794867884e-06, 'epoch': 0.57} + 57%|█████▋ | 6857/11952 [3:50:19<8:14:41, 5.83s/it] 57%|█████▋ | 6858/11952 [3:50:25<8:11:09, 5.79s/it] {'loss': 0.4692, 'learning_rate': 8.107769777376657e-06, 'epoch': 0.57} + 57%|█████▋ | 6858/11952 [3:50:25<8:11:09, 5.79s/it] 57%|█████▋ | 6859/11952 [3:50:31<8:14:13, 5.82s/it] {'loss': 0.4705, 'learning_rate': 8.105108898842946e-06, 'epoch': 0.57} + 57%|█████▋ | 6859/11952 [3:50:31<8:14:13, 5.82s/it] 57%|█████▋ | 6860/11952 [3:50:37<8:17:20, 5.86s/it] {'loss': 0.4907, 'learning_rate': 8.102448159462155e-06, 'epoch': 0.57} + 57%|█████▋ | 6860/11952 [3:50:37<8:17:20, 5.86s/it] 57%|█████▋ | 6861/11952 [3:50:43<8:14:21, 5.83s/it] {'loss': 0.4831, 'learning_rate': 8.099787559429682e-06, 'epoch': 0.57} + 57%|█████▋ | 6861/11952 [3:50:43<8:14:21, 5.83s/it] 57%|█████▋ | 6862/11952 [3:50:48<8:13:09, 5.81s/it] {'loss': 0.4815, 'learning_rate': 8.0971270989409e-06, 'epoch': 0.57} + 57%|█████▋ | 6862/11952 [3:50:48<8:13:09, 5.81s/it] 57%|█████▋ | 6863/11952 [3:50:54<8:15:22, 5.84s/it] {'loss': 0.4879, 'learning_rate': 8.094466778191194e-06, 'epoch': 0.57} + 57%|█████▋ | 6863/11952 [3:50:54<8:15:22, 5.84s/it] 57%|█████▋ | 6864/11952 [3:51:00<8:13:11, 5.82s/it] {'loss': 0.4851, 'learning_rate': 8.091806597375925e-06, 'epoch': 0.57} + 57%|█████▋ | 6864/11952 [3:51:00<8:13:11, 5.82s/it] 57%|█████▋ | 6865/11952 [3:51:06<8:11:17, 5.79s/it] {'loss': 0.4682, 'learning_rate': 8.089146556690437e-06, 'epoch': 0.57} + 57%|█████▋ | 6865/11952 [3:51:06<8:11:17, 5.79s/it] 57%|█████▋ | 6866/11952 [3:51:12<8:10:57, 5.79s/it] {'loss': 0.4849, 'learning_rate': 8.086486656330082e-06, 'epoch': 0.57} + 57%|█████▋ | 6866/11952 [3:51:12<8:10:57, 5.79s/it] 57%|█████▋ | 6867/11952 [3:51:17<8:11:28, 5.80s/it] {'loss': 0.4875, 'learning_rate': 8.083826896490186e-06, 'epoch': 0.57} + 57%|█████▋ | 6867/11952 [3:51:17<8:11:28, 5.80s/it] 57%|█████▋ | 6868/11952 [3:51:23<8:13:26, 5.82s/it] {'loss': 0.4755, 'learning_rate': 8.081167277366076e-06, 'epoch': 0.57} + 57%|█████▋ | 6868/11952 [3:51:23<8:13:26, 5.82s/it] 57%|█████▋ | 6869/11952 [3:51:29<8:08:49, 5.77s/it] {'loss': 0.4663, 'learning_rate': 8.078507799153053e-06, 'epoch': 0.57} + 57%|█████▋ | 6869/11952 [3:51:29<8:08:49, 5.77s/it] 57%|█████▋ | 6870/11952 [3:51:35<8:12:58, 5.82s/it] {'loss': 0.4806, 'learning_rate': 8.07584846204643e-06, 'epoch': 0.57} + 57%|█████▋ | 6870/11952 [3:51:35<8:12:58, 5.82s/it] 57%|█████▋ | 6871/11952 [3:51:41<8:15:24, 5.85s/it] {'loss': 0.4771, 'learning_rate': 8.073189266241492e-06, 'epoch': 0.57} + 57%|█████▋ | 6871/11952 [3:51:41<8:15:24, 5.85s/it] 57%|█████▋ | 6872/11952 [3:51:47<8:20:36, 5.91s/it] {'loss': 0.4727, 'learning_rate': 8.070530211933522e-06, 'epoch': 0.57} + 57%|█████▋ | 6872/11952 [3:51:47<8:20:36, 5.91s/it] 58%|█████▊ | 6873/11952 [3:51:53<8:16:28, 5.86s/it] {'loss': 0.4623, 'learning_rate': 8.067871299317786e-06, 'epoch': 0.58} + 58%|█████▊ | 6873/11952 [3:51:53<8:16:28, 5.86s/it] 58%|█████▊ | 6874/11952 [3:51:58<8:12:07, 5.81s/it] {'loss': 0.5038, 'learning_rate': 8.065212528589545e-06, 'epoch': 0.58} + 58%|█████▊ | 6874/11952 [3:51:58<8:12:07, 5.81s/it] 58%|█████▊ | 6875/11952 [3:52:04<8:19:44, 5.91s/it] {'loss': 0.4703, 'learning_rate': 8.062553899944049e-06, 'epoch': 0.58} + 58%|█████▊ | 6875/11952 [3:52:04<8:19:44, 5.91s/it] 58%|█████▊ | 6876/11952 [3:52:10<8:15:19, 5.85s/it] {'loss': 0.4934, 'learning_rate': 8.059895413576535e-06, 'epoch': 0.58} + 58%|█████▊ | 6876/11952 [3:52:10<8:15:19, 5.85s/it] 58%|█████▊ | 6877/11952 [3:52:16<8:15:46, 5.86s/it] {'loss': 0.4898, 'learning_rate': 8.057237069682235e-06, 'epoch': 0.58} + 58%|█████▊ | 6877/11952 [3:52:16<8:15:46, 5.86s/it] 58%|█████▊ | 6878/11952 [3:52:22<8:14:09, 5.84s/it] {'loss': 0.4677, 'learning_rate': 8.054578868456364e-06, 'epoch': 0.58} + 58%|█████▊ | 6878/11952 [3:52:22<8:14:09, 5.84s/it] 58%|█████▊ | 6879/11952 [3:52:28<8:18:43, 5.90s/it] {'loss': 0.5034, 'learning_rate': 8.05192081009413e-06, 'epoch': 0.58} + 58%|█████▊ | 6879/11952 [3:52:28<8:18:43, 5.90s/it] 58%|█████▊ | 6880/11952 [3:52:34<8:16:37, 5.87s/it] {'loss': 0.4796, 'learning_rate': 8.049262894790725e-06, 'epoch': 0.58} + 58%|█████▊ | 6880/11952 [3:52:34<8:16:37, 5.87s/it] 58%|█████▊ | 6881/11952 [3:52:39<8:14:19, 5.85s/it] {'loss': 0.4751, 'learning_rate': 8.046605122741343e-06, 'epoch': 0.58} + 58%|█████▊ | 6881/11952 [3:52:40<8:14:19, 5.85s/it] 58%|█████▊ | 6882/11952 [3:52:45<8:04:49, 5.74s/it] {'loss': 0.4621, 'learning_rate': 8.04394749414115e-06, 'epoch': 0.58} + 58%|█████▊ | 6882/11952 [3:52:45<8:04:49, 5.74s/it] 58%|█████▊ | 6883/11952 [3:52:51<8:03:19, 5.72s/it] {'loss': 0.4772, 'learning_rate': 8.041290009185325e-06, 'epoch': 0.58} + 58%|█████▊ | 6883/11952 [3:52:51<8:03:19, 5.72s/it] 58%|█████▊ | 6884/11952 [3:52:56<8:03:13, 5.72s/it] {'loss': 0.471, 'learning_rate': 8.038632668069011e-06, 'epoch': 0.58} + 58%|█████▊ | 6884/11952 [3:52:56<8:03:13, 5.72s/it] 58%|█████▊ | 6885/11952 [3:53:03<8:17:43, 5.89s/it] {'loss': 0.4558, 'learning_rate': 8.035975470987357e-06, 'epoch': 0.58} + 58%|█████▊ | 6885/11952 [3:53:03<8:17:43, 5.89s/it] 58%|█████▊ | 6886/11952 [3:53:09<8:16:14, 5.88s/it] {'loss': 0.4728, 'learning_rate': 8.033318418135494e-06, 'epoch': 0.58} + 58%|█████▊ | 6886/11952 [3:53:09<8:16:14, 5.88s/it] 58%|█████▊ | 6887/11952 [3:53:14<8:14:44, 5.86s/it] {'loss': 0.4667, 'learning_rate': 8.03066150970855e-06, 'epoch': 0.58} + 58%|█████▊ | 6887/11952 [3:53:14<8:14:44, 5.86s/it] 58%|█████▊ | 6888/11952 [3:53:20<8:13:42, 5.85s/it] {'loss': 0.4804, 'learning_rate': 8.02800474590163e-06, 'epoch': 0.58} + 58%|█████▊ | 6888/11952 [3:53:20<8:13:42, 5.85s/it] 58%|█████▊ | 6889/11952 [3:53:26<8:07:38, 5.78s/it] {'loss': 0.4809, 'learning_rate': 8.025348126909837e-06, 'epoch': 0.58} + 58%|█████▊ | 6889/11952 [3:53:26<8:07:38, 5.78s/it] 58%|█████▊ | 6890/11952 [3:53:32<8:21:15, 5.94s/it] {'loss': 0.4799, 'learning_rate': 8.02269165292827e-06, 'epoch': 0.58} + 58%|█████▊ | 6890/11952 [3:53:32<8:21:15, 5.94s/it] 58%|█████▊ | 6891/11952 [3:53:38<8:15:53, 5.88s/it] {'loss': 0.456, 'learning_rate': 8.020035324152e-06, 'epoch': 0.58} + 58%|█████▊ | 6891/11952 [3:53:38<8:15:53, 5.88s/it] 58%|█████▊ | 6892/11952 [3:53:43<8:08:04, 5.79s/it] {'loss': 0.4874, 'learning_rate': 8.017379140776103e-06, 'epoch': 0.58} + 58%|█████▊ | 6892/11952 [3:53:43<8:08:04, 5.79s/it] 58%|█████▊ | 6893/11952 [3:53:49<8:11:51, 5.83s/it] {'loss': 0.4772, 'learning_rate': 8.014723102995635e-06, 'epoch': 0.58} + 58%|█████▊ | 6893/11952 [3:53:49<8:11:51, 5.83s/it] 58%|█████▊ | 6894/11952 [3:53:55<8:08:59, 5.80s/it] {'loss': 0.4651, 'learning_rate': 8.012067211005645e-06, 'epoch': 0.58} + 58%|█████▊ | 6894/11952 [3:53:55<8:08:59, 5.80s/it] 58%|█████▊ | 6895/11952 [3:54:01<8:17:37, 5.90s/it] {'loss': 0.4828, 'learning_rate': 8.00941146500117e-06, 'epoch': 0.58} + 58%|█████▊ | 6895/11952 [3:54:01<8:17:37, 5.90s/it] 58%|█████▊ | 6896/11952 [3:54:07<8:15:42, 5.88s/it] {'loss': 0.4682, 'learning_rate': 8.006755865177233e-06, 'epoch': 0.58} + 58%|█████▊ | 6896/11952 [3:54:07<8:15:42, 5.88s/it] 58%|█████▊ | 6897/11952 [3:54:13<8:16:15, 5.89s/it] {'loss': 0.4852, 'learning_rate': 8.00410041172886e-06, 'epoch': 0.58} + 58%|█████▊ | 6897/11952 [3:54:13<8:16:15, 5.89s/it] 58%|█████▊ | 6898/11952 [3:54:19<8:17:18, 5.90s/it] {'loss': 0.4691, 'learning_rate': 8.001445104851052e-06, 'epoch': 0.58} + 58%|█████▊ | 6898/11952 [3:54:19<8:17:18, 5.90s/it] 58%|█████▊ | 6899/11952 [3:54:25<8:12:28, 5.85s/it] {'loss': 0.4742, 'learning_rate': 7.998789944738801e-06, 'epoch': 0.58} + 58%|█████▊ | 6899/11952 [3:54:25<8:12:28, 5.85s/it]2 AutoResumeHook: Checking whether to suspend... +063 AutoResumeHook: Checking whether to suspend... +AutoResumeHook: Checking whether to suspend... +AutoResumeHook: Checking whether to suspend...7 + AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... + 58%|█████▊ | 6900/11952 [3:54:31<8:19:48, 5.94s/it]5 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4673, 'learning_rate': 7.996134931587092e-06, 'epoch': 0.58} + 58%|█████▊ | 6900/11952 [3:54:31<8:19:48, 5.94s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-6900/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-6900/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/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( + 58%|█████▊ | 6901/11952 [3:54:59<17:48:02, 12.69s/it] {'loss': 0.502, 'learning_rate': 7.993480065590902e-06, 'epoch': 0.58} + 58%|█████▊ | 6901/11952 [3:54:59<17:48:02, 12.69s/it] 58%|█████▊ | 6902/11952 [3:55:05<14:55:20, 10.64s/it] {'loss': 0.4745, 'learning_rate': 7.990825346945188e-06, 'epoch': 0.58} + 58%|█████▊ | 6902/11952 [3:55:05<14:55:20, 10.64s/it] 58%|█████▊ | 6903/11952 [3:55:11<12:54:56, 9.21s/it] {'loss': 0.4806, 'learning_rate': 7.9881707758449e-06, 'epoch': 0.58} + 58%|█████▊ | 6903/11952 [3:55:11<12:54:56, 9.21s/it] 58%|█████▊ | 6904/11952 [3:55:17<11:37:36, 8.29s/it] {'loss': 0.4838, 'learning_rate': 7.985516352484987e-06, 'epoch': 0.58} + 58%|█████▊ | 6904/11952 [3:55:17<11:37:36, 8.29s/it] 58%|█████▊ | 6905/11952 [3:55:23<10:32:20, 7.52s/it] {'loss': 0.4686, 'learning_rate': 7.982862077060376e-06, 'epoch': 0.58} + 58%|█████▊ | 6905/11952 [3:55:23<10:32:20, 7.52s/it] 58%|█████▊ | 6906/11952 [3:55:29<9:47:57, 6.99s/it] {'loss': 0.466, 'learning_rate': 7.98020794976598e-06, 'epoch': 0.58} + 58%|█████▊ | 6906/11952 [3:55:29<9:47:57, 6.99s/it] 58%|█████▊ | 6907/11952 [3:55:34<9:14:55, 6.60s/it] {'loss': 0.4756, 'learning_rate': 7.977553970796713e-06, 'epoch': 0.58} + 58%|█████▊ | 6907/11952 [3:55:34<9:14:55, 6.60s/it] 58%|█████▊ | 6908/11952 [3:55:40<8:54:16, 6.36s/it] {'loss': 0.4717, 'learning_rate': 7.974900140347473e-06, 'epoch': 0.58} + 58%|█████▊ | 6908/11952 [3:55:40<8:54:16, 6.36s/it] 58%|█████▊ | 6909/11952 [3:55:46<8:36:59, 6.15s/it] {'loss': 0.4496, 'learning_rate': 7.97224645861314e-06, 'epoch': 0.58} + 58%|█████▊ | 6909/11952 [3:55:46<8:36:59, 6.15s/it] 58%|█████▊ | 6910/11952 [3:55:52<8:28:42, 6.05s/it] {'loss': 0.4874, 'learning_rate': 7.969592925788592e-06, 'epoch': 0.58} + 58%|█████▊ | 6910/11952 [3:55:52<8:28:42, 6.05s/it] 58%|█████▊ | 6911/11952 [3:55:57<8:21:31, 5.97s/it] {'loss': 0.482, 'learning_rate': 7.966939542068694e-06, 'epoch': 0.58} + 58%|█████▊ | 6911/11952 [3:55:57<8:21:31, 5.97s/it] 58%|█████▊ | 6912/11952 [3:56:03<8:23:51, 6.00s/it] {'loss': 0.4715, 'learning_rate': 7.964286307648305e-06, 'epoch': 0.58} + 58%|█████▊ | 6912/11952 [3:56:03<8:23:51, 6.00s/it] 58%|█████▊ | 6913/11952 [3:56:09<8:20:41, 5.96s/it] {'loss': 0.4723, 'learning_rate': 7.96163322272226e-06, 'epoch': 0.58} + 58%|█████▊ | 6913/11952 [3:56:09<8:20:41, 5.96s/it] 58%|█████▊ | 6914/11952 [3:56:15<8:12:20, 5.86s/it] {'loss': 0.4682, 'learning_rate': 7.958980287485394e-06, 'epoch': 0.58} + 58%|█████▊ | 6914/11952 [3:56:15<8:12:20, 5.86s/it] 58%|█████▊ | 6915/11952 [3:56:21<8:11:51, 5.86s/it] {'loss': 0.4634, 'learning_rate': 7.956327502132523e-06, 'epoch': 0.58} + 58%|█████▊ | 6915/11952 [3:56:21<8:11:51, 5.86s/it] 58%|█████▊ | 6916/11952 [3:56:27<8:10:07, 5.84s/it] {'loss': 0.4693, 'learning_rate': 7.953674866858462e-06, 'epoch': 0.58} + 58%|█████▊ | 6916/11952 [3:56:27<8:10:07, 5.84s/it] 58%|█████▊ | 6917/11952 [3:56:33<8:19:50, 5.96s/it] {'loss': 0.4736, 'learning_rate': 7.951022381858005e-06, 'epoch': 0.58} + 58%|█████▊ | 6917/11952 [3:56:33<8:19:50, 5.96s/it] 58%|█████▊ | 6918/11952 [3:56:38<8:14:30, 5.89s/it] {'loss': 0.4643, 'learning_rate': 7.948370047325946e-06, 'epoch': 0.58} + 58%|█████▊ | 6918/11952 [3:56:38<8:14:30, 5.89s/it] 58%|█████▊ | 6919/11952 [3:56:44<8:13:37, 5.88s/it] {'loss': 0.4887, 'learning_rate': 7.945717863457057e-06, 'epoch': 0.58} + 58%|█████▊ | 6919/11952 [3:56:44<8:13:37, 5.88s/it] 58%|█████▊ | 6920/11952 [3:56:50<8:14:20, 5.89s/it] {'loss': 0.4975, 'learning_rate': 7.943065830446104e-06, 'epoch': 0.58} + 58%|█████▊ | 6920/11952 [3:56:50<8:14:20, 5.89s/it] 58%|█████▊ | 6921/11952 [3:56:56<8:11:48, 5.87s/it] {'loss': 0.5002, 'learning_rate': 7.940413948487838e-06, 'epoch': 0.58} + 58%|█████▊ | 6921/11952 [3:56:56<8:11:48, 5.87s/it] 58%|█████▊ | 6922/11952 [3:57:02<8:17:07, 5.93s/it] {'loss': 0.4834, 'learning_rate': 7.937762217777007e-06, 'epoch': 0.58} + 58%|█████▊ | 6922/11952 [3:57:02<8:17:07, 5.93s/it] 58%|█████▊ | 6923/11952 [3:57:08<8:09:46, 5.84s/it] {'loss': 0.4903, 'learning_rate': 7.935110638508339e-06, 'epoch': 0.58} + 58%|█████▊ | 6923/11952 [3:57:08<8:09:46, 5.84s/it] 58%|█████▊ | 6924/11952 [3:57:14<8:08:31, 5.83s/it] {'loss': 0.4688, 'learning_rate': 7.93245921087656e-06, 'epoch': 0.58} + 58%|█████▊ | 6924/11952 [3:57:14<8:08:31, 5.83s/it] 58%|█████▊ | 6925/11952 [3:57:20<8:16:24, 5.92s/it] {'loss': 0.4765, 'learning_rate': 7.929807935076376e-06, 'epoch': 0.58} + 58%|█████▊ | 6925/11952 [3:57:20<8:16:24, 5.92s/it] 58%|█████▊ | 6926/11952 [3:57:26<8:19:25, 5.96s/it] {'loss': 0.4793, 'learning_rate': 7.927156811302486e-06, 'epoch': 0.58} + 58%|█████▊ | 6926/11952 [3:57:26<8:19:25, 5.96s/it] 58%|█████▊ | 6927/11952 [3:57:32<8:24:11, 6.02s/it] {'loss': 0.4832, 'learning_rate': 7.92450583974958e-06, 'epoch': 0.58} + 58%|█████▊ | 6927/11952 [3:57:32<8:24:11, 6.02s/it] 58%|█████▊ | 6928/11952 [3:57:38<8:15:35, 5.92s/it] {'loss': 0.4811, 'learning_rate': 7.921855020612333e-06, 'epoch': 0.58} + 58%|█████▊ | 6928/11952 [3:57:38<8:15:35, 5.92s/it] 58%|█████▊ | 6929/11952 [3:57:43<8:14:31, 5.91s/it] {'loss': 0.4649, 'learning_rate': 7.919204354085408e-06, 'epoch': 0.58} + 58%|█████▊ | 6929/11952 [3:57:43<8:14:31, 5.91s/it] 58%|█████▊ | 6930/11952 [3:57:49<8:13:18, 5.89s/it] {'loss': 0.4554, 'learning_rate': 7.916553840363458e-06, 'epoch': 0.58} + 58%|█████▊ | 6930/11952 [3:57:49<8:13:18, 5.89s/it] 58%|█████▊ | 6931/11952 [3:57:55<8:17:41, 5.95s/it] {'loss': 0.4636, 'learning_rate': 7.913903479641131e-06, 'epoch': 0.58} + 58%|█████▊ | 6931/11952 [3:57:55<8:17:41, 5.95s/it]Jun 10 20:39:24.547678 2777762 slurmstepd 0x155550ab8700: error: *** STEP 8833833.0 ON batch-block1-2091 CANCELLED AT 2025-06-10T20:39:24 DUE TO TIME LIMIT *** +srun: Job step aborted: Waiting up to 122 seconds for job step to finish. +srun: error: batch-block1-2091: task 0: Terminated +srun: Terminating StepId=8833833.0 +srun: job 8837928 queued and waiting for resources +srun: job 8837928 has been allocated resources +srun: Job 8837928 step creation temporarily disabled, retrying (Requested nodes are busy) +srun: Step created for StepId=8837928.0 +wandb: Currently logged in as: memmelma. Use `wandb login --relogin` to force relogin +MASTER_ADDR=batch-block1-0069 +JobID: 8837928 | Full list: batch-block1-0069 +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! +[2025-06-10 20:46:46,817] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-10 20:46:46,817] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-10 20:46:46,817] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-10 20:46:46,817] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-10 20:46:46,817] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-10 20:46:46,817] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-10 20:46:46,817] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-10 20:46:46,817] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-10 20:46:48,000] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-10 20:46:48,000] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-10 20:46:48,000] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-10 20:46:48,000] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-10 20:46:48,000] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-10 20:46:48,000] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-10 20:46:48,000] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-10 20:46:48,000] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-10 20:46:48,000] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-10 20:46:48,000] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-10 20:46:48,000] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-10 20:46:48,000] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-10 20:46:48,000] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-10 20:46:48,000] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-10 20:46:48,000] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-10 20:46:48,000] [INFO] [comm.py:625:init_distributed] Initializing TorchBackend in DeepSpeed with backend nccl +[2025-06-10 20:46:48,000] [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')`. +[2025-06-10 20:46:55,826] [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%|████████ | 9618/11952 [43:03<3:49:01, 5.89s/it] {'loss': 0.454, 'learning_rate': 1.934430202451549e-06, 'epoch': 0.8} + 80%|████████ | 9618/11952 [43:03<3:49:01, 5.89s/it] 80%|████████ | 9619/11952 [43:09<3:53:13, 6.00s/it] {'loss': 0.4657, 'learning_rate': 1.9328285211630847e-06, 'epoch': 0.8} + 80%|████████ | 9619/11952 [43:09<3:53:13, 6.00s/it] 80%|████████ | 9620/11952 [43:15<3:51:35, 5.96s/it] {'loss': 0.4621, 'learning_rate': 1.9312274322941426e-06, 'epoch': 0.8} + 80%|████████ | 9620/11952 [43:15<3:51:35, 5.96s/it] 80%|████████ | 9621/11952 [43:21<3:51:02, 5.95s/it] {'loss': 0.457, 'learning_rate': 1.9296269359622977e-06, 'epoch': 0.8} + 80%|████████ | 9621/11952 [43:21<3:51:02, 5.95s/it] 81%|████████ | 9622/11952 [43:27<3:47:32, 5.86s/it] {'loss': 0.4572, 'learning_rate': 1.9280270322850836e-06, 'epoch': 0.81} + 81%|████████ | 9622/11952 [43:27<3:47:32, 5.86s/it] 81%|████████ | 9623/11952 [43:32<3:46:57, 5.85s/it] {'loss': 0.4614, 'learning_rate': 1.92642772137999e-06, 'epoch': 0.81} + 81%|████████ | 9623/11952 [43:32<3:46:57, 5.85s/it] 81%|████████ | 9624/11952 [43:38<3:46:02, 5.83s/it] {'loss': 0.4545, 'learning_rate': 1.9248290033644614e-06, 'epoch': 0.81} + 81%|████████ | 9624/11952 [43:38<3:46:02, 5.83s/it] 81%|████████ | 9625/11952 [43:44<3:47:19, 5.86s/it] {'loss': 0.4749, 'learning_rate': 1.9232308783559064e-06, 'epoch': 0.81} + 81%|████████ | 9625/11952 [43:44<3:47:19, 5.86s/it] 81%|████████ | 9626/11952 [43:50<3:43:25, 5.76s/it] {'loss': 0.4872, 'learning_rate': 1.9216333464716817e-06, 'epoch': 0.81} + 81%|████████ | 9626/11952 [43:50<3:43:25, 5.76s/it] 81%|████████ | 9627/11952 [43:56<3:47:34, 5.87s/it] {'loss': 0.4565, 'learning_rate': 1.9200364078291032e-06, 'epoch': 0.81} + 81%|████████ | 9627/11952 [43:56<3:47:34, 5.87s/it] 81%|████████ | 9628/11952 [44:02<3:46:18, 5.84s/it] {'loss': 0.4787, 'learning_rate': 1.9184400625454413e-06, 'epoch': 0.81} + 81%|████████ | 9628/11952 [44:02<3:46:18, 5.84s/it] 81%|████████ | 9629/11952 [44:07<3:45:41, 5.83s/it] {'loss': 0.4553, 'learning_rate': 1.916844310737931e-06, 'epoch': 0.81} + 81%|████████ | 9629/11952 [44:07<3:45:41, 5.83s/it] 81%|████████ | 9630/11952 [44:13<3:45:46, 5.83s/it] {'loss': 0.4542, 'learning_rate': 1.9152491525237504e-06, 'epoch': 0.81} + 81%|████████ | 9630/11952 [44:13<3:45:46, 5.83s/it] 81%|████████ | 9631/11952 [44:19<3:48:05, 5.90s/it] {'loss': 0.4756, 'learning_rate': 1.9136545880200484e-06, 'epoch': 0.81} + 81%|████████ | 9631/11952 [44:19<3:48:05, 5.90s/it] 81%|████████ | 9632/11952 [44:25<3:45:41, 5.84s/it] {'loss': 0.4579, 'learning_rate': 1.912060617343919e-06, 'epoch': 0.81} + 81%|████████ | 9632/11952 [44:25<3:45:41, 5.84s/it] 81%|████████ | 9633/11952 [44:31<3:43:40, 5.79s/it] {'loss': 0.4656, 'learning_rate': 1.910467240612419e-06, 'epoch': 0.81} + 81%|████████ | 9633/11952 [44:31<3:43:40, 5.79s/it] 81%|████████ | 9634/11952 [44:36<3:43:28, 5.78s/it] {'loss': 0.4556, 'learning_rate': 1.9088744579425567e-06, 'epoch': 0.81} + 81%|████████ | 9634/11952 [44:36<3:43:28, 5.78s/it] 81%|████████ | 9635/11952 [44:42<3:42:30, 5.76s/it] {'loss': 0.4717, 'learning_rate': 1.9072822694513016e-06, 'epoch': 0.81} + 81%|████████ | 9635/11952 [44:42<3:42:30, 5.76s/it] 81%|████████ | 9636/11952 [44:48<3:42:12, 5.76s/it] {'loss': 0.4633, 'learning_rate': 1.9056906752555759e-06, 'epoch': 0.81} + 81%|████████ | 9636/11952 [44:48<3:42:12, 5.76s/it] 81%|████████ | 9637/11952 [44:54<3:44:11, 5.81s/it] {'loss': 0.4566, 'learning_rate': 1.9040996754722574e-06, 'epoch': 0.81} + 81%|████████ | 9637/11952 [44:54<3:44:11, 5.81s/it] 81%|████████ | 9638/11952 [45:00<3:44:31, 5.82s/it] {'loss': 0.4552, 'learning_rate': 1.902509270218189e-06, 'epoch': 0.81} + 81%|████████ | 9638/11952 [45:00<3:44:31, 5.82s/it] 81%|████████ | 9639/11952 [45:05<3:41:43, 5.75s/it] {'loss': 0.4667, 'learning_rate': 1.9009194596101566e-06, 'epoch': 0.81} + 81%|████████ | 9639/11952 [45:05<3:41:43, 5.75s/it] 81%|████████ | 9640/11952 [45:11<3:45:20, 5.85s/it] {'loss': 0.4566, 'learning_rate': 1.8993302437649143e-06, 'epoch': 0.81} + 81%|████████ | 9640/11952 [45:11<3:45:20, 5.85s/it] 81%|████████ | 9641/11952 [45:17<3:43:37, 5.81s/it] {'loss': 0.4585, 'learning_rate': 1.8977416227991663e-06, 'epoch': 0.81} + 81%|████████ | 9641/11952 [45:17<3:43:37, 5.81s/it] 81%|████████ | 9642/11952 [45:23<3:42:01, 5.77s/it] {'loss': 0.4518, 'learning_rate': 1.896153596829574e-06, 'epoch': 0.81} + 81%|████████ | 9642/11952 [45:23<3:42:01, 5.77s/it] 81%|████████ | 9643/11952 [45:29<3:49:58, 5.98s/it] {'loss': 0.4677, 'learning_rate': 1.8945661659727555e-06, 'epoch': 0.81} + 81%|████████ | 9643/11952 [45:29<3:49:58, 5.98s/it] 81%|████████ | 9644/11952 [45:35<3:49:45, 5.97s/it] {'loss': 0.4731, 'learning_rate': 1.8929793303452814e-06, 'epoch': 0.81} + 81%|████████ | 9644/11952 [45:35<3:49:45, 5.97s/it] 81%|████████ | 9645/11952 [45:41<3:50:49, 6.00s/it] {'loss': 0.4661, 'learning_rate': 1.891393090063688e-06, 'epoch': 0.81} + 81%|████████ | 9645/11952 [45:41<3:50:49, 6.00s/it] 81%|████████ | 9646/11952 [45:47<3:48:51, 5.95s/it] {'loss': 0.4539, 'learning_rate': 1.8898074452444604e-06, 'epoch': 0.81} + 81%|████████ | 9646/11952 [45:47<3:48:51, 5.95s/it] 81%|████████ | 9647/11952 [45:53<3:51:35, 6.03s/it] {'loss': 0.4814, 'learning_rate': 1.8882223960040413e-06, 'epoch': 0.81} + 81%|████████ | 9647/11952 [45:53<3:51:35, 6.03s/it] 81%|████████ | 9648/11952 [45:59<3:52:50, 6.06s/it] {'loss': 0.4711, 'learning_rate': 1.8866379424588287e-06, 'epoch': 0.81} + 81%|████████ | 9648/11952 [45:59<3:52:50, 6.06s/it] 81%|████████ | 9649/11952 [46:05<3:49:14, 5.97s/it] {'loss': 0.4454, 'learning_rate': 1.8850540847251786e-06, 'epoch': 0.81} + 81%|████████ | 9649/11952 [46:05<3:49:14, 5.97s/it]6 AutoResumeHook: Checking whether to suspend... +71 AutoResumeHook: Checking whether to suspend...AutoResumeHook: Checking whether to suspend... + +5 AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +0 AutoResumeHook: Checking whether to suspend... + 81%|████████ | 9650/11952 [46:11<3:52:14, 6.05s/it] {'loss': 0.4759, 'learning_rate': 1.8834708229194054e-06, 'epoch': 0.81} + 81%|████████ | 9650/11952 [46:11<3:52:14, 6.05s/it] 81%|████████ | 9651/11952 [46:17<3:49:23, 5.98s/it] {'loss': 0.4592, 'learning_rate': 1.8818881571577741e-06, 'epoch': 0.81} + 81%|████████ | 9651/11952 [46:17<3:49:23, 5.98s/it] 81%|████████ | 9652/11952 [46:23<3:45:04, 5.87s/it] {'loss': 0.4533, 'learning_rate': 1.8803060875565127e-06, 'epoch': 0.81} + 81%|████████ | 9652/11952 [46:23<3:45:04, 5.87s/it] 81%|████████ | 9653/11952 [46:29<3:48:14, 5.96s/it] {'loss': 0.484, 'learning_rate': 1.8787246142318006e-06, 'epoch': 0.81} + 81%|████████ | 9653/11952 [46:29<3:48:14, 5.96s/it] 81%|████████ | 9654/11952 [46:35<3:46:39, 5.92s/it] {'loss': 0.4713, 'learning_rate': 1.8771437372997736e-06, 'epoch': 0.81} + 81%|████████ | 9654/11952 [46:35<3:46:39, 5.92s/it] 81%|████████ | 9655/11952 [46:41<3:50:52, 6.03s/it] {'loss': 0.4474, 'learning_rate': 1.8755634568765246e-06, 'epoch': 0.81} + 81%|████████ | 9655/11952 [46:41<3:50:52, 6.03s/it] 81%|████████ | 9656/11952 [46:47<3:46:32, 5.92s/it] {'loss': 0.4372, 'learning_rate': 1.8739837730781029e-06, 'epoch': 0.81} + 81%|████████ | 9656/11952 [46:47<3:46:32, 5.92s/it] 81%|████████ | 9657/11952 [46:52<3:43:45, 5.85s/it] {'loss': 0.4562, 'learning_rate': 1.872404686020516e-06, 'epoch': 0.81} + 81%|████████ | 9657/11952 [46:52<3:43:45, 5.85s/it] 81%|████████ | 9658/11952 [46:58<3:42:41, 5.82s/it] {'loss': 0.4659, 'learning_rate': 1.8708261958197193e-06, 'epoch': 0.81} + 81%|████████ | 9658/11952 [46:58<3:42:41, 5.82s/it] 81%|████████ | 9659/11952 [47:04<3:45:21, 5.90s/it] {'loss': 0.4809, 'learning_rate': 1.8692483025916387e-06, 'epoch': 0.81} + 81%|████████ | 9659/11952 [47:04<3:45:21, 5.90s/it] 81%|████████ | 9660/11952 [47:10<3:43:43, 5.86s/it] {'loss': 0.4592, 'learning_rate': 1.8676710064521409e-06, 'epoch': 0.81} + 81%|████████ | 9660/11952 [47:10<3:43:43, 5.86s/it] 81%|████████ | 9661/11952 [47:16<3:44:00, 5.87s/it] {'loss': 0.4448, 'learning_rate': 1.8660943075170634e-06, 'epoch': 0.81} + 81%|████████ | 9661/11952 [47:16<3:44:00, 5.87s/it] 81%|████████ | 9662/11952 [47:22<3:46:31, 5.94s/it] {'loss': 0.4631, 'learning_rate': 1.864518205902187e-06, 'epoch': 0.81} + 81%|████████ | 9662/11952 [47:22<3:46:31, 5.94s/it] 81%|████████ | 9663/11952 [47:28<3:47:54, 5.97s/it] {'loss': 0.4671, 'learning_rate': 1.862942701723257e-06, 'epoch': 0.81} + 81%|████████ | 9663/11952 [47:28<3:47:54, 5.97s/it] 81%|████████ | 9664/11952 [47:34<3:48:11, 5.98s/it] {'loss': 0.4527, 'learning_rate': 1.8613677950959697e-06, 'epoch': 0.81} + 81%|████████ | 9664/11952 [47:34<3:48:11, 5.98s/it] 81%|████████ | 9665/11952 [47:40<3:47:46, 5.98s/it] {'loss': 0.4446, 'learning_rate': 1.8597934861359779e-06, 'epoch': 0.81} + 81%|████████ | 9665/11952 [47:40<3:47:46, 5.98s/it] 81%|████████ | 9666/11952 [47:46<3:45:05, 5.91s/it] {'loss': 0.4743, 'learning_rate': 1.858219774958897e-06, 'epoch': 0.81} + 81%|████████ | 9666/11952 [47:46<3:45:05, 5.91s/it] 81%|████████ | 9667/11952 [47:51<3:41:56, 5.83s/it] {'loss': 0.4744, 'learning_rate': 1.8566466616802914e-06, 'epoch': 0.81} + 81%|████████ | 9667/11952 [47:51<3:41:56, 5.83s/it] 81%|████████ | 9668/11952 [47:57<3:40:36, 5.80s/it] {'loss': 0.4457, 'learning_rate': 1.855074146415685e-06, 'epoch': 0.81} + 81%|████████ | 9668/11952 [47:57<3:40:36, 5.80s/it] 81%|████████ | 9669/11952 [48:03<3:43:47, 5.88s/it] {'loss': 0.4582, 'learning_rate': 1.8535022292805539e-06, 'epoch': 0.81} + 81%|████████ | 9669/11952 [48:03<3:43:47, 5.88s/it] 81%|████████ | 9670/11952 [48:09<3:41:59, 5.84s/it] {'loss': 0.4666, 'learning_rate': 1.851930910390337e-06, 'epoch': 0.81} + 81%|████████ | 9670/11952 [48:09<3:41:59, 5.84s/it] 81%|████████ | 9671/11952 [48:15<3:42:42, 5.86s/it] {'loss': 0.4709, 'learning_rate': 1.8503601898604207e-06, 'epoch': 0.81} + 81%|████████ | 9671/11952 [48:15<3:42:42, 5.86s/it] 81%|████████ | 9672/11952 [48:21<3:44:02, 5.90s/it] {'loss': 0.4568, 'learning_rate': 1.8487900678061588e-06, 'epoch': 0.81} + 81%|████████ | 9672/11952 [48:21<3:44:02, 5.90s/it] 81%|████████ | 9673/11952 [48:27<3:50:19, 6.06s/it] {'loss': 0.4638, 'learning_rate': 1.8472205443428504e-06, 'epoch': 0.81} + 81%|████████ | 9673/11952 [48:27<3:50:19, 6.06s/it] 81%|████████ | 9674/11952 [48:33<3:48:38, 6.02s/it] {'loss': 0.4657, 'learning_rate': 1.8456516195857543e-06, 'epoch': 0.81} + 81%|████████ | 9674/11952 [48:33<3:48:38, 6.02s/it] 81%|████████ | 9675/11952 [48:39<3:45:03, 5.93s/it] {'loss': 0.4578, 'learning_rate': 1.8440832936500875e-06, 'epoch': 0.81} + 81%|████████ | 9675/11952 [48:39<3:45:03, 5.93s/it] 81%|████████ | 9676/11952 [48:45<3:44:34, 5.92s/it] {'loss': 0.4629, 'learning_rate': 1.842515566651021e-06, 'epoch': 0.81} + 81%|████████ | 9676/11952 [48:45<3:44:34, 5.92s/it] 81%|████████ | 9677/11952 [48:51<3:44:26, 5.92s/it] {'loss': 0.4413, 'learning_rate': 1.8409484387036813e-06, 'epoch': 0.81} + 81%|████████ | 9677/11952 [48:51<3:44:26, 5.92s/it] 81%|████████ | 9678/11952 [48:57<3:43:09, 5.89s/it] {'loss': 0.4732, 'learning_rate': 1.8393819099231503e-06, 'epoch': 0.81} + 81%|████████ | 9678/11952 [48:57<3:43:09, 5.89s/it] 81%|████████ | 9679/11952 [49:03<3:44:26, 5.92s/it] {'loss': 0.4708, 'learning_rate': 1.837815980424471e-06, 'epoch': 0.81} + 81%|████████ | 9679/11952 [49:03<3:44:26, 5.92s/it] 81%|████████ | 9680/11952 [49:09<3:44:29, 5.93s/it] {'loss': 0.483, 'learning_rate': 1.8362506503226374e-06, 'epoch': 0.81} + 81%|████████ | 9680/11952 [49:09<3:44:29, 5.93s/it] 81%|████████ | 9681/11952 [49:14<3:43:22, 5.90s/it] {'loss': 0.4639, 'learning_rate': 1.8346859197325984e-06, 'epoch': 0.81} + 81%|████████ | 9681/11952 [49:14<3:43:22, 5.90s/it] 81%|████████ | 9682/11952 [49:21<3:48:06, 6.03s/it] {'loss': 0.4756, 'learning_rate': 1.8331217887692653e-06, 'epoch': 0.81} + 81%|████████ | 9682/11952 [49:21<3:48:06, 6.03s/it] 81%|████████ | 9683/11952 [49:27<3:48:47, 6.05s/it] {'loss': 0.4638, 'learning_rate': 1.8315582575475e-06, 'epoch': 0.81} + 81%|████████ | 9683/11952 [49:27<3:48:47, 6.05s/it] 81%|████████ | 9684/11952 [49:33<3:49:06, 6.06s/it] {'loss': 0.4641, 'learning_rate': 1.8299953261821202e-06, 'epoch': 0.81} + 81%|████████ | 9684/11952 [49:33<3:49:06, 6.06s/it] 81%|████████ | 9685/11952 [49:39<3:48:56, 6.06s/it] {'loss': 0.4882, 'learning_rate': 1.8284329947878999e-06, 'epoch': 0.81} + 81%|████████ | 9685/11952 [49:39<3:48:56, 6.06s/it] 81%|████████ | 9686/11952 [49:45<3:46:20, 5.99s/it] {'loss': 0.4464, 'learning_rate': 1.8268712634795749e-06, 'epoch': 0.81} + 81%|████████ | 9686/11952 [49:45<3:46:20, 5.99s/it] 81%|████████ | 9687/11952 [49:51<3:44:13, 5.94s/it] {'loss': 0.4501, 'learning_rate': 1.8253101323718303e-06, 'epoch': 0.81} + 81%|████████ | 9687/11952 [49:51<3:44:13, 5.94s/it] 81%|████████ | 9688/11952 [49:56<3:41:00, 5.86s/it] {'loss': 0.4642, 'learning_rate': 1.8237496015793077e-06, 'epoch': 0.81} + 81%|████████ | 9688/11952 [49:56<3:41:00, 5.86s/it] 81%|████████ | 9689/11952 [50:02<3:41:39, 5.88s/it] {'loss': 0.4618, 'learning_rate': 1.8221896712166075e-06, 'epoch': 0.81} + 81%|████████ | 9689/11952 [50:02<3:41:39, 5.88s/it] 81%|████████ | 9690/11952 [50:08<3:42:39, 5.91s/it] {'loss': 0.4548, 'learning_rate': 1.8206303413982806e-06, 'epoch': 0.81} + 81%|████████ | 9690/11952 [50:08<3:42:39, 5.91s/it] 81%|████████ | 9691/11952 [50:14<3:38:42, 5.80s/it] {'loss': 0.4565, 'learning_rate': 1.819071612238843e-06, 'epoch': 0.81} + 81%|████████ | 9691/11952 [50:14<3:38:42, 5.80s/it] 81%|████████ | 9692/11952 [50:19<3:37:58, 5.79s/it] {'loss': 0.4589, 'learning_rate': 1.8175134838527575e-06, 'epoch': 0.81} + 81%|████████ | 9692/11952 [50:19<3:37:58, 5.79s/it] 81%|████████ | 9693/11952 [50:26<3:42:05, 5.90s/it] {'loss': 0.4569, 'learning_rate': 1.8159559563544504e-06, 'epoch': 0.81} + 81%|████████ | 9693/11952 [50:26<3:42:05, 5.90s/it] 81%|████████ | 9694/11952 [50:32<3:46:32, 6.02s/it] {'loss': 0.4753, 'learning_rate': 1.814399029858298e-06, 'epoch': 0.81} + 81%|████████ | 9694/11952 [50:32<3:46:32, 6.02s/it] 81%|████████ | 9695/11952 [50:38<3:46:59, 6.03s/it] {'loss': 0.4571, 'learning_rate': 1.8128427044786345e-06, 'epoch': 0.81} + 81%|████████ | 9695/11952 [50:38<3:46:59, 6.03s/it] 81%|████████ | 9696/11952 [50:44<3:43:04, 5.93s/it] {'loss': 0.4539, 'learning_rate': 1.8112869803297494e-06, 'epoch': 0.81} + 81%|████████ | 9696/11952 [50:44<3:43:04, 5.93s/it] 81%|████████ | 9697/11952 [50:50<3:43:43, 5.95s/it] {'loss': 0.4814, 'learning_rate': 1.8097318575258894e-06, 'epoch': 0.81} + 81%|████████ | 9697/11952 [50:50<3:43:43, 5.95s/it] 81%|████████ | 9698/11952 [50:56<3:43:28, 5.95s/it] {'loss': 0.4669, 'learning_rate': 1.808177336181256e-06, 'epoch': 0.81} + 81%|████████ | 9698/11952 [50:56<3:43:28, 5.95s/it] 81%|████████ | 9699/11952 [51:02<3:43:21, 5.95s/it] {'loss': 0.4593, 'learning_rate': 1.8066234164100038e-06, 'epoch': 0.81} + 81%|████████ | 9699/11952 [51:02<3:43:21, 5.95s/it]6 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... +0 AutoResumeHook: Checking whether to suspend... + 81%|████████ | 9700/11952 [51:07<3:41:44, 5.91s/it] {'loss': 0.4782, 'learning_rate': 1.8050700983262526e-06, 'epoch': 0.81} + 81%|████████ | 9700/11952 [51:07<3:41:44, 5.91s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-9700/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-9700/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/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( + 81%|████████ | 9701/11952 [51:39<8:30:09, 13.60s/it] {'loss': 0.4736, 'learning_rate': 1.8035173820440643e-06, 'epoch': 0.81} + 81%|████████ | 9701/11952 [51:39<8:30:09, 13.60s/it] 81%|████████ | 9702/11952 [51:45<7:04:26, 11.32s/it] {'loss': 0.4838, 'learning_rate': 1.8019652676774703e-06, 'epoch': 0.81} + 81%|████████ | 9702/11952 [51:45<7:04:26, 11.32s/it] 81%|████████ | 9703/11952 [51:51<6:01:20, 9.64s/it] {'loss': 0.4489, 'learning_rate': 1.8004137553404498e-06, 'epoch': 0.81} + 81%|████████ | 9703/11952 [51:51<6:01:20, 9.64s/it] 81%|████████ | 9704/11952 [51:57<5:22:13, 8.60s/it] {'loss': 0.4896, 'learning_rate': 1.798862845146938e-06, 'epoch': 0.81} + 81%|████████ | 9704/11952 [51:57<5:22:13, 8.60s/it] 81%|████████ | 9705/11952 [52:03<4:52:55, 7.82s/it] {'loss': 0.4669, 'learning_rate': 1.797312537210827e-06, 'epoch': 0.81} + 81%|████████ | 9705/11952 [52:03<4:52:55, 7.82s/it] 81%|████████ | 9706/11952 [52:09<4:32:12, 7.27s/it] {'loss': 0.4614, 'learning_rate': 1.795762831645964e-06, 'epoch': 0.81} + 81%|████████ | 9706/11952 [52:09<4:32:12, 7.27s/it] 81%|████████ | 9707/11952 [52:15<4:19:42, 6.94s/it] {'loss': 0.4606, 'learning_rate': 1.7942137285661576e-06, 'epoch': 0.81} + 81%|████████ | 9707/11952 [52:15<4:19:42, 6.94s/it] 81%|████████ | 9708/11952 [52:21<4:09:52, 6.68s/it] {'loss': 0.4639, 'learning_rate': 1.7926652280851642e-06, 'epoch': 0.81} + 81%|████████ | 9708/11952 [52:21<4:09:52, 6.68s/it] 81%|████████ | 9709/11952 [52:27<3:58:49, 6.39s/it] {'loss': 0.4593, 'learning_rate': 1.7911173303166985e-06, 'epoch': 0.81} + 81%|████████ | 9709/11952 [52:27<3:58:49, 6.39s/it] 81%|████████ | 9710/11952 [52:33<3:57:18, 6.35s/it] {'loss': 0.4639, 'learning_rate': 1.789570035374434e-06, 'epoch': 0.81} + 81%|████████ | 9710/11952 [52:33<3:57:18, 6.35s/it] 81%|████████▏ | 9711/11952 [52:39<3:51:09, 6.19s/it] {'loss': 0.4737, 'learning_rate': 1.7880233433719929e-06, 'epoch': 0.81} + 81%|████████▏ | 9711/11952 [52:39<3:51:09, 6.19s/it] 81%|████████▏ | 9712/11952 [52:45<3:50:34, 6.18s/it] {'loss': 0.4641, 'learning_rate': 1.7864772544229626e-06, 'epoch': 0.81} + 81%|████████▏ | 9712/11952 [52:45<3:50:34, 6.18s/it] 81%|████████▏ | 9713/11952 [52:51<3:48:00, 6.11s/it] {'loss': 0.4718, 'learning_rate': 1.7849317686408817e-06, 'epoch': 0.81} + 81%|████████▏ | 9713/11952 [52:51<3:48:00, 6.11s/it] 81%|████████▏ | 9714/11952 [52:57<3:42:44, 5.97s/it] {'loss': 0.4658, 'learning_rate': 1.7833868861392423e-06, 'epoch': 0.81} + 81%|████████▏ | 9714/11952 [52:57<3:42:44, 5.97s/it] 81%|████████▏ | 9715/11952 [53:02<3:41:06, 5.93s/it] {'loss': 0.4595, 'learning_rate': 1.7818426070314953e-06, 'epoch': 0.81} + 81%|████████▏ | 9715/11952 [53:02<3:41:06, 5.93s/it] 81%|████████▏ | 9716/11952 [53:08<3:40:53, 5.93s/it] {'loss': 0.4852, 'learning_rate': 1.7802989314310449e-06, 'epoch': 0.81} + 81%|████████▏ | 9716/11952 [53:08<3:40:53, 5.93s/it] 81%|████████▏ | 9717/11952 [53:14<3:38:59, 5.88s/it] {'loss': 0.4482, 'learning_rate': 1.7787558594512533e-06, 'epoch': 0.81} + 81%|████████▏ | 9717/11952 [53:14<3:38:59, 5.88s/it] 81%|████████▏ | 9718/11952 [53:20<3:38:28, 5.87s/it] {'loss': 0.4569, 'learning_rate': 1.7772133912054367e-06, 'epoch': 0.81} + 81%|████████▏ | 9718/11952 [53:20<3:38:28, 5.87s/it] 81%|████████▏ | 9719/11952 [53:26<3:40:04, 5.91s/it] {'loss': 0.4792, 'learning_rate': 1.7756715268068635e-06, 'epoch': 0.81} + 81%|████████▏ | 9719/11952 [53:26<3:40:04, 5.91s/it] 81%|████████▏ | 9720/11952 [53:32<3:39:30, 5.90s/it] {'loss': 0.4654, 'learning_rate': 1.7741302663687697e-06, 'epoch': 0.81} + 81%|████████▏ | 9720/11952 [53:32<3:39:30, 5.90s/it] 81%|████████▏ | 9721/11952 [53:37<3:36:37, 5.83s/it] {'loss': 0.4532, 'learning_rate': 1.7725896100043349e-06, 'epoch': 0.81} + 81%|████████▏ | 9721/11952 [53:37<3:36:37, 5.83s/it] 81%|████████▏ | 9722/11952 [53:44<3:39:14, 5.90s/it] {'loss': 0.4619, 'learning_rate': 1.7710495578266963e-06, 'epoch': 0.81} + 81%|████████▏ | 9722/11952 [53:44<3:39:14, 5.90s/it] 81%|████████▏ | 9723/11952 [53:49<3:38:49, 5.89s/it] {'loss': 0.4695, 'learning_rate': 1.7695101099489542e-06, 'epoch': 0.81} + 81%|████████▏ | 9723/11952 [53:49<3:38:49, 5.89s/it] 81%|████████▏ | 9724/11952 [53:56<3:41:09, 5.96s/it] {'loss': 0.465, 'learning_rate': 1.7679712664841554e-06, 'epoch': 0.81} + 81%|████████▏ | 9724/11952 [53:56<3:41:09, 5.96s/it] 81%|████████▏ | 9725/11952 [54:01<3:39:20, 5.91s/it] {'loss': 0.4712, 'learning_rate': 1.766433027545308e-06, 'epoch': 0.81} + 81%|████████▏ | 9725/11952 [54:01<3:39:20, 5.91s/it] 81%|████████▏ | 9726/11952 [54:07<3:38:00, 5.88s/it] {'loss': 0.4926, 'learning_rate': 1.7648953932453706e-06, 'epoch': 0.81} + 81%|████████▏ | 9726/11952 [54:07<3:38:00, 5.88s/it] 81%|████████▏ | 9727/11952 [54:13<3:37:35, 5.87s/it] {'loss': 0.4681, 'learning_rate': 1.763358363697265e-06, 'epoch': 0.81} + 81%|████████▏ | 9727/11952 [54:13<3:37:35, 5.87s/it] 81%|████████▏ | 9728/11952 [54:19<3:40:22, 5.95s/it] {'loss': 0.4721, 'learning_rate': 1.7618219390138635e-06, 'epoch': 0.81} + 81%|████████▏ | 9728/11952 [54:19<3:40:22, 5.95s/it] 81%|████████▏ | 9729/11952 [54:25<3:36:07, 5.83s/it] {'loss': 0.4555, 'learning_rate': 1.7602861193079922e-06, 'epoch': 0.81} + 81%|████████▏ | 9729/11952 [54:25<3:36:07, 5.83s/it] 81%|████████▏ | 9730/11952 [54:30<3:34:06, 5.78s/it] {'loss': 0.4666, 'learning_rate': 1.7587509046924378e-06, 'epoch': 0.81} + 81%|████████▏ | 9730/11952 [54:30<3:34:06, 5.78s/it] 81%|████████▏ | 9731/11952 [54:36<3:33:06, 5.76s/it] {'loss': 0.4645, 'learning_rate': 1.7572162952799366e-06, 'epoch': 0.81} + 81%|████████▏ | 9731/11952 [54:36<3:33:06, 5.76s/it] 81%|████████▏ | 9732/11952 [54:42<3:33:39, 5.77s/it] {'loss': 0.4613, 'learning_rate': 1.7556822911831882e-06, 'epoch': 0.81} + 81%|████████▏ | 9732/11952 [54:42<3:33:39, 5.77s/it] 81%|████████▏ | 9733/11952 [54:48<3:33:38, 5.78s/it] {'loss': 0.4739, 'learning_rate': 1.7541488925148397e-06, 'epoch': 0.81} + 81%|████████▏ | 9733/11952 [54:48<3:33:38, 5.78s/it] 81%|████████▏ | 9734/11952 [54:53<3:34:17, 5.80s/it] {'loss': 0.455, 'learning_rate': 1.752616099387502e-06, 'epoch': 0.81} + 81%|████████▏ | 9734/11952 [54:53<3:34:17, 5.80s/it] 81%|████████▏ | 9735/11952 [54:59<3:35:35, 5.83s/it] {'loss': 0.4624, 'learning_rate': 1.7510839119137347e-06, 'epoch': 0.81} + 81%|████████▏ | 9735/11952 [54:59<3:35:35, 5.83s/it] 81%|████████▏ | 9736/11952 [55:05<3:33:49, 5.79s/it] {'loss': 0.4691, 'learning_rate': 1.7495523302060546e-06, 'epoch': 0.81} + 81%|████████▏ | 9736/11952 [55:05<3:33:49, 5.79s/it] 81%|████████▏ | 9737/11952 [55:11<3:35:25, 5.84s/it] {'loss': 0.4729, 'learning_rate': 1.7480213543769343e-06, 'epoch': 0.81} + 81%|████████▏ | 9737/11952 [55:11<3:35:25, 5.84s/it] 81%|████████▏ | 9738/11952 [55:17<3:36:46, 5.87s/it] {'loss': 0.4682, 'learning_rate': 1.7464909845388045e-06, 'epoch': 0.81} + 81%|████████▏ | 9738/11952 [55:17<3:36:46, 5.87s/it] 81%|████████▏ | 9739/11952 [55:23<3:37:28, 5.90s/it] {'loss': 0.4588, 'learning_rate': 1.7449612208040479e-06, 'epoch': 0.81} + 81%|████████▏ | 9739/11952 [55:23<3:37:28, 5.90s/it] 81%|████████▏ | 9740/11952 [55:29<3:37:21, 5.90s/it] {'loss': 0.464, 'learning_rate': 1.743432063285001e-06, 'epoch': 0.81} + 81%|████████▏ | 9740/11952 [55:29<3:37:21, 5.90s/it] 82%|████████▏ | 9741/11952 [55:35<3:36:49, 5.88s/it] {'loss': 0.4633, 'learning_rate': 1.7419035120939642e-06, 'epoch': 0.81} + 82%|████████▏ | 9741/11952 [55:35<3:36:49, 5.88s/it] 82%|████████▏ | 9742/11952 [55:41<3:37:00, 5.89s/it] {'loss': 0.4697, 'learning_rate': 1.740375567343182e-06, 'epoch': 0.82} + 82%|████████▏ | 9742/11952 [55:41<3:37:00, 5.89s/it] 82%|████████▏ | 9743/11952 [55:46<3:34:49, 5.83s/it] {'loss': 0.4564, 'learning_rate': 1.7388482291448684e-06, 'epoch': 0.82} + 82%|████████▏ | 9743/11952 [55:46<3:34:49, 5.83s/it] 82%|████████▏ | 9744/11952 [55:52<3:31:36, 5.75s/it] {'loss': 0.4541, 'learning_rate': 1.7373214976111786e-06, 'epoch': 0.82} + 82%|████████▏ | 9744/11952 [55:52<3:31:36, 5.75s/it] 82%|████████▏ | 9745/11952 [55:58<3:31:29, 5.75s/it] {'loss': 0.4673, 'learning_rate': 1.735795372854231e-06, 'epoch': 0.82} + 82%|████████▏ | 9745/11952 [55:58<3:31:29, 5.75s/it] 82%|████████▏ | 9746/11952 [56:04<3:34:36, 5.84s/it] {'loss': 0.4842, 'learning_rate': 1.7342698549860958e-06, 'epoch': 0.82} + 82%|████████▏ | 9746/11952 [56:04<3:34:36, 5.84s/it] 82%|████████▏ | 9747/11952 [56:09<3:34:12, 5.83s/it] {'loss': 0.459, 'learning_rate': 1.732744944118805e-06, 'epoch': 0.82} + 82%|████████▏ | 9747/11952 [56:09<3:34:12, 5.83s/it] 82%|████████▏ | 9748/11952 [56:15<3:34:11, 5.83s/it] {'loss': 0.4632, 'learning_rate': 1.7312206403643395e-06, 'epoch': 0.82} + 82%|████████▏ | 9748/11952 [56:15<3:34:11, 5.83s/it] 82%|████████▏ | 9749/11952 [56:21<3:33:51, 5.82s/it] {'loss': 0.4745, 'learning_rate': 1.7296969438346378e-06, 'epoch': 0.82} + 82%|████████▏ | 9749/11952 [56:21<3:33:51, 5.82s/it]4 2AutoResumeHook: Checking whether to suspend... +AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... +0 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... + 82%|████████▏ | 9750/11952 [56:27<3:35:07, 5.86s/it] {'loss': 0.4645, 'learning_rate': 1.7281738546415938e-06, 'epoch': 0.82} + 82%|████████▏ | 9750/11952 [56:27<3:35:07, 5.86s/it] 82%|████████▏ | 9751/11952 [56:33<3:40:17, 6.01s/it] {'loss': 0.4611, 'learning_rate': 1.726651372897057e-06, 'epoch': 0.82} + 82%|████████▏ | 9751/11952 [56:33<3:40:17, 6.01s/it] 82%|████████▏ | 9752/11952 [56:40<3:42:57, 6.08s/it] {'loss': 0.4632, 'learning_rate': 1.7251294987128287e-06, 'epoch': 0.82} + 82%|████████▏ | 9752/11952 [56:40<3:42:57, 6.08s/it] 82%|████████▏ | 9753/11952 [56:46<3:43:28, 6.10s/it] {'loss': 0.4493, 'learning_rate': 1.723608232200673e-06, 'epoch': 0.82} + 82%|████████▏ | 9753/11952 [56:46<3:43:28, 6.10s/it] 82%|████████▏ | 9754/11952 [56:52<3:40:11, 6.01s/it] {'loss': 0.4455, 'learning_rate': 1.7220875734723063e-06, 'epoch': 0.82} + 82%|████████▏ | 9754/11952 [56:52<3:40:11, 6.01s/it] 82%|████████▏ | 9755/11952 [56:58<3:39:50, 6.00s/it] {'loss': 0.4785, 'learning_rate': 1.720567522639398e-06, 'epoch': 0.82} + 82%|████████▏ | 9755/11952 [56:58<3:39:50, 6.00s/it] 82%|████████▏ | 9756/11952 [57:03<3:36:41, 5.92s/it] {'loss': 0.4574, 'learning_rate': 1.7190480798135745e-06, 'epoch': 0.82} + 82%|████████▏ | 9756/11952 [57:03<3:36:41, 5.92s/it] 82%|████████▏ | 9757/11952 [57:10<3:41:54, 6.07s/it] {'loss': 0.4784, 'learning_rate': 1.7175292451064174e-06, 'epoch': 0.82} + 82%|████████▏ | 9757/11952 [57:10<3:41:54, 6.07s/it] 82%|████████▏ | 9758/11952 [57:15<3:38:24, 5.97s/it] {'loss': 0.4608, 'learning_rate': 1.716011018629462e-06, 'epoch': 0.82} + 82%|████████▏ | 9758/11952 [57:15<3:38:24, 5.97s/it] 82%|████████▏ | 9759/11952 [57:21<3:38:34, 5.98s/it] {'loss': 0.4531, 'learning_rate': 1.7144934004942027e-06, 'epoch': 0.82} + 82%|████████▏ | 9759/11952 [57:21<3:38:34, 5.98s/it] 82%|████████▏ | 9760/11952 [57:27<3:36:27, 5.92s/it] {'loss': 0.4734, 'learning_rate': 1.7129763908120823e-06, 'epoch': 0.82} + 82%|████████▏ | 9760/11952 [57:27<3:36:27, 5.92s/it] 82%|████████▏ | 9761/11952 [57:33<3:31:35, 5.79s/it] {'loss': 0.4574, 'learning_rate': 1.7114599896945105e-06, 'epoch': 0.82} + 82%|████████▏ | 9761/11952 [57:33<3:31:35, 5.79s/it] 82%|████████▏ | 9762/11952 [57:38<3:30:57, 5.78s/it] {'loss': 0.4479, 'learning_rate': 1.709944197252843e-06, 'epoch': 0.82} + 82%|████████▏ | 9762/11952 [57:38<3:30:57, 5.78s/it] 82%|████████▏ | 9763/11952 [57:44<3:28:50, 5.72s/it] {'loss': 0.4544, 'learning_rate': 1.7084290135983895e-06, 'epoch': 0.82} + 82%|████████▏ | 9763/11952 [57:44<3:28:50, 5.72s/it] 82%|████████▏ | 9764/11952 [57:50<3:33:42, 5.86s/it] {'loss': 0.4866, 'learning_rate': 1.7069144388424253e-06, 'epoch': 0.82} + 82%|████████▏ | 9764/11952 [57:50<3:33:42, 5.86s/it] 82%|████████▏ | 9765/11952 [57:56<3:35:02, 5.90s/it] {'loss': 0.4746, 'learning_rate': 1.7054004730961704e-06, 'epoch': 0.82} + 82%|████████▏ | 9765/11952 [57:56<3:35:02, 5.90s/it] 82%|████████▏ | 9766/11952 [58:02<3:34:32, 5.89s/it] {'loss': 0.4562, 'learning_rate': 1.7038871164708059e-06, 'epoch': 0.82} + 82%|████████▏ | 9766/11952 [58:02<3:34:32, 5.89s/it] 82%|████████▏ | 9767/11952 [58:08<3:35:17, 5.91s/it] {'loss': 0.4627, 'learning_rate': 1.7023743690774619e-06, 'epoch': 0.82} + 82%|████████▏ | 9767/11952 [58:08<3:35:17, 5.91s/it] 82%|████████▏ | 9768/11952 [58:14<3:34:23, 5.89s/it] {'loss': 0.4512, 'learning_rate': 1.7008622310272349e-06, 'epoch': 0.82} + 82%|████████▏ | 9768/11952 [58:14<3:34:23, 5.89s/it] 82%|████████▏ | 9769/11952 [58:20<3:31:24, 5.81s/it] {'loss': 0.4584, 'learning_rate': 1.6993507024311661e-06, 'epoch': 0.82} + 82%|████████▏ | 9769/11952 [58:20<3:31:24, 5.81s/it] 82%|████████▏ | 9770/11952 [58:25<3:29:12, 5.75s/it] {'loss': 0.4578, 'learning_rate': 1.697839783400258e-06, 'epoch': 0.82} + 82%|████████▏ | 9770/11952 [58:25<3:29:12, 5.75s/it] 82%|████████▏ | 9771/11952 [58:31<3:30:56, 5.80s/it] {'loss': 0.4818, 'learning_rate': 1.6963294740454638e-06, 'epoch': 0.82} + 82%|████████▏ | 9771/11952 [58:31<3:30:56, 5.80s/it] 82%|████████▏ | 9772/11952 [58:37<3:31:58, 5.83s/it] {'loss': 0.4753, 'learning_rate': 1.694819774477694e-06, 'epoch': 0.82} + 82%|████████▏ | 9772/11952 [58:37<3:31:58, 5.83s/it] 82%|████████▏ | 9773/11952 [58:43<3:33:23, 5.88s/it] {'loss': 0.4678, 'learning_rate': 1.6933106848078174e-06, 'epoch': 0.82} + 82%|████████▏ | 9773/11952 [58:43<3:33:23, 5.88s/it] 82%|████████▏ | 9774/11952 [58:49<3:31:29, 5.83s/it] {'loss': 0.4589, 'learning_rate': 1.691802205146652e-06, 'epoch': 0.82} + 82%|████████▏ | 9774/11952 [58:49<3:31:29, 5.83s/it] 82%|████████▏ | 9775/11952 [58:54<3:30:16, 5.80s/it] {'loss': 0.4672, 'learning_rate': 1.6902943356049796e-06, 'epoch': 0.82} + 82%|████████▏ | 9775/11952 [58:54<3:30:16, 5.80s/it] 82%|████████▏ | 9776/11952 [59:00<3:30:54, 5.82s/it] {'loss': 0.4603, 'learning_rate': 1.6887870762935276e-06, 'epoch': 0.82} + 82%|████████▏ | 9776/11952 [59:00<3:30:54, 5.82s/it] 82%|████████▏ | 9777/11952 [59:06<3:35:06, 5.93s/it] {'loss': 0.4586, 'learning_rate': 1.6872804273229838e-06, 'epoch': 0.82} + 82%|████████▏ | 9777/11952 [59:06<3:35:06, 5.93s/it] 82%|████████▏ | 9778/11952 [59:12<3:33:41, 5.90s/it] {'loss': 0.4551, 'learning_rate': 1.6857743888039902e-06, 'epoch': 0.82} + 82%|████████▏ | 9778/11952 [59:12<3:33:41, 5.90s/it] 82%|████████▏ | 9779/11952 [59:18<3:34:14, 5.92s/it] {'loss': 0.4649, 'learning_rate': 1.6842689608471451e-06, 'epoch': 0.82} + 82%|████████▏ | 9779/11952 [59:18<3:34:14, 5.92s/it] 82%|████████▏ | 9780/11952 [59:24<3:36:45, 5.99s/it] {'loss': 0.4798, 'learning_rate': 1.6827641435629983e-06, 'epoch': 0.82} + 82%|████████▏ | 9780/11952 [59:24<3:36:45, 5.99s/it] 82%|████████▏ | 9781/11952 [59:30<3:35:14, 5.95s/it] {'loss': 0.4601, 'learning_rate': 1.6812599370620574e-06, 'epoch': 0.82} + 82%|████████▏ | 9781/11952 [59:30<3:35:14, 5.95s/it] 82%|████████▏ | 9782/11952 [59:36<3:32:49, 5.88s/it] {'loss': 0.4397, 'learning_rate': 1.679756341454788e-06, 'epoch': 0.82} + 82%|████████▏ | 9782/11952 [59:36<3:32:49, 5.88s/it] 82%|████████▏ | 9783/11952 [59:42<3:33:39, 5.91s/it] {'loss': 0.4517, 'learning_rate': 1.6782533568516047e-06, 'epoch': 0.82} + 82%|████████▏ | 9783/11952 [59:42<3:33:39, 5.91s/it] 82%|████████▏ | 9784/11952 [59:48<3:36:34, 5.99s/it] {'loss': 0.4718, 'learning_rate': 1.6767509833628847e-06, 'epoch': 0.82} + 82%|████████▏ | 9784/11952 [59:48<3:36:34, 5.99s/it] 82%|████████▏ | 9785/11952 [59:54<3:34:35, 5.94s/it] {'loss': 0.4713, 'learning_rate': 1.6752492210989523e-06, 'epoch': 0.82} + 82%|████████▏ | 9785/11952 [59:54<3:34:35, 5.94s/it] 82%|████████▏ | 9786/11952 [1:00:00<3:33:01, 5.90s/it] {'loss': 0.4593, 'learning_rate': 1.6737480701700936e-06, 'epoch': 0.82} + 82%|████████▏ | 9786/11952 [1:00:00<3:33:01, 5.90s/it] 82%|████████▏ | 9787/11952 [1:00:06<3:35:31, 5.97s/it] {'loss': 0.4871, 'learning_rate': 1.6722475306865415e-06, 'epoch': 0.82} + 82%|████████▏ | 9787/11952 [1:00:06<3:35:31, 5.97s/it] 82%|████████▏ | 9788/11952 [1:00:12<3:34:24, 5.94s/it] {'loss': 0.4819, 'learning_rate': 1.6707476027584956e-06, 'epoch': 0.82} + 82%|████████▏ | 9788/11952 [1:00:12<3:34:24, 5.94s/it] 82%|████████▏ | 9789/11952 [1:00:18<3:35:20, 5.97s/it] {'loss': 0.4736, 'learning_rate': 1.6692482864961024e-06, 'epoch': 0.82} + 82%|████████▏ | 9789/11952 [1:00:18<3:35:20, 5.97s/it] 82%|████████▏ | 9790/11952 [1:00:23<3:31:38, 5.87s/it] {'loss': 0.4608, 'learning_rate': 1.6677495820094635e-06, 'epoch': 0.82} + 82%|████████▏ | 9790/11952 [1:00:23<3:31:38, 5.87s/it] 82%|████████▏ | 9791/11952 [1:00:29<3:33:06, 5.92s/it] {'loss': 0.4389, 'learning_rate': 1.6662514894086402e-06, 'epoch': 0.82} + 82%|████████▏ | 9791/11952 [1:00:29<3:33:06, 5.92s/it] 82%|████████▏ | 9792/11952 [1:00:36<3:36:39, 6.02s/it] {'loss': 0.4748, 'learning_rate': 1.664754008803644e-06, 'epoch': 0.82} + 82%|████████▏ | 9792/11952 [1:00:36<3:36:39, 6.02s/it] 82%|████████▏ | 9793/11952 [1:00:42<3:34:47, 5.97s/it] {'loss': 0.4592, 'learning_rate': 1.6632571403044429e-06, 'epoch': 0.82} + 82%|████████▏ | 9793/11952 [1:00:42<3:34:47, 5.97s/it] 82%|████████▏ | 9794/11952 [1:00:47<3:33:27, 5.94s/it] {'loss': 0.4609, 'learning_rate': 1.6617608840209642e-06, 'epoch': 0.82} + 82%|████████▏ | 9794/11952 [1:00:47<3:33:27, 5.94s/it] 82%|████████▏ | 9795/11952 [1:00:53<3:32:13, 5.90s/it] {'loss': 0.4567, 'learning_rate': 1.6602652400630825e-06, 'epoch': 0.82} + 82%|████████▏ | 9795/11952 [1:00:53<3:32:13, 5.90s/it] 82%|████████▏ | 9796/11952 [1:00:59<3:31:42, 5.89s/it] {'loss': 0.5012, 'learning_rate': 1.6587702085406366e-06, 'epoch': 0.82} + 82%|████████▏ | 9796/11952 [1:00:59<3:31:42, 5.89s/it] 82%|████████▏ | 9797/11952 [1:01:05<3:30:28, 5.86s/it] {'loss': 0.4571, 'learning_rate': 1.6572757895634117e-06, 'epoch': 0.82} + 82%|████████▏ | 9797/11952 [1:01:05<3:30:28, 5.86s/it] 82%|████████▏ | 9798/11952 [1:01:11<3:28:56, 5.82s/it] {'loss': 0.4843, 'learning_rate': 1.6557819832411537e-06, 'epoch': 0.82} + 82%|████████▏ | 9798/11952 [1:01:11<3:28:56, 5.82s/it] 82%|████████▏ | 9799/11952 [1:01:17<3:29:25, 5.84s/it] {'loss': 0.4747, 'learning_rate': 1.6542887896835614e-06, 'epoch': 0.82} + 82%|████████▏ | 9799/11952 [1:01:17<3:29:25, 5.84s/it]6 AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +0 AutoResumeHook: Checking whether to suspend... + 82%|████████▏ | 9800/11952 [1:01:23<3:32:29, 5.92s/it] {'loss': 0.4576, 'learning_rate': 1.652796209000287e-06, 'epoch': 0.82} + 82%|████████▏ | 9800/11952 [1:01:23<3:32:29, 5.92s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-9800/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-9800/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/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( + 82%|████████▏ | 9801/11952 [1:01:52<7:39:23, 12.81s/it] {'loss': 0.4586, 'learning_rate': 1.6513042413009383e-06, 'epoch': 0.82} + 82%|████████▏ | 9801/11952 [1:01:52<7:39:23, 12.81s/it] 82%|████████▏ | 9802/11952 [1:01:58<6:25:18, 10.75s/it] {'loss': 0.4844, 'learning_rate': 1.6498128866950835e-06, 'epoch': 0.82} + 82%|████████▏ | 9802/11952 [1:01:58<6:25:18, 10.75s/it] 82%|████████▏ | 9803/11952 [1:02:03<5:33:13, 9.30s/it] {'loss': 0.4594, 'learning_rate': 1.6483221452922394e-06, 'epoch': 0.82} + 82%|████████▏ | 9803/11952 [1:02:03<5:33:13, 9.30s/it] 82%|████████▏ | 9804/11952 [1:02:09<4:53:31, 8.20s/it] {'loss': 0.4692, 'learning_rate': 1.646832017201877e-06, 'epoch': 0.82} + 82%|████████▏ | 9804/11952 [1:02:09<4:53:31, 8.20s/it] 82%|████████▏ | 9805/11952 [1:02:15<4:28:08, 7.49s/it] {'loss': 0.4718, 'learning_rate': 1.6453425025334302e-06, 'epoch': 0.82} + 82%|████████▏ | 9805/11952 [1:02:15<4:28:08, 7.49s/it] 82%|████████▏ | 9806/11952 [1:02:21<4:08:19, 6.94s/it] {'loss': 0.4611, 'learning_rate': 1.6438536013962814e-06, 'epoch': 0.82} + 82%|████████▏ | 9806/11952 [1:02:21<4:08:19, 6.94s/it] 82%|████████▏ | 9807/11952 [1:02:26<3:54:24, 6.56s/it] {'loss': 0.4661, 'learning_rate': 1.6423653138997675e-06, 'epoch': 0.82} + 82%|████████▏ | 9807/11952 [1:02:26<3:54:24, 6.56s/it] 82%|████████▏ | 9808/11952 [1:02:32<3:46:24, 6.34s/it] {'loss': 0.4553, 'learning_rate': 1.64087764015318e-06, 'epoch': 0.82} + 82%|████████▏ | 9808/11952 [1:02:32<3:46:24, 6.34s/it] 82%|████████▏ | 9809/11952 [1:02:38<3:43:06, 6.25s/it] {'loss': 0.4626, 'learning_rate': 1.639390580265774e-06, 'epoch': 0.82} + 82%|████████▏ | 9809/11952 [1:02:38<3:43:06, 6.25s/it] 82%|████████▏ | 9810/11952 [1:02:44<3:37:37, 6.10s/it] {'loss': 0.4576, 'learning_rate': 1.6379041343467484e-06, 'epoch': 0.82} + 82%|████████▏ | 9810/11952 [1:02:44<3:37:37, 6.10s/it] 82%|████████▏ | 9811/11952 [1:02:50<3:41:01, 6.19s/it] {'loss': 0.4766, 'learning_rate': 1.6364183025052626e-06, 'epoch': 0.82} + 82%|████████▏ | 9811/11952 [1:02:50<3:41:01, 6.19s/it] 82%|████████▏ | 9812/11952 [1:02:56<3:40:01, 6.17s/it] {'loss': 0.4571, 'learning_rate': 1.6349330848504308e-06, 'epoch': 0.82} + 82%|████████▏ | 9812/11952 [1:02:56<3:40:01, 6.17s/it] 82%|████████▏ | 9813/11952 [1:03:02<3:37:35, 6.10s/it] {'loss': 0.4734, 'learning_rate': 1.6334484814913165e-06, 'epoch': 0.82} + 82%|████████▏ | 9813/11952 [1:03:02<3:37:35, 6.10s/it] 82%|████████▏ | 9814/11952 [1:03:08<3:35:36, 6.05s/it] {'loss': 0.4534, 'learning_rate': 1.6319644925369504e-06, 'epoch': 0.82} + 82%|████████▏ | 9814/11952 [1:03:08<3:35:36, 6.05s/it] 82%|████████▏ | 9815/11952 [1:03:14<3:32:12, 5.96s/it] {'loss': 0.4627, 'learning_rate': 1.6304811180963032e-06, 'epoch': 0.82} + 82%|████████▏ | 9815/11952 [1:03:14<3:32:12, 5.96s/it] 82%|████████▏ | 9816/11952 [1:03:20<3:32:13, 5.96s/it] {'loss': 0.4361, 'learning_rate': 1.6289983582783142e-06, 'epoch': 0.82} + 82%|████████▏ | 9816/11952 [1:03:20<3:32:13, 5.96s/it] 82%|████████▏ | 9817/11952 [1:03:26<3:31:49, 5.95s/it] {'loss': 0.4706, 'learning_rate': 1.6275162131918688e-06, 'epoch': 0.82} + 82%|████████▏ | 9817/11952 [1:03:26<3:31:49, 5.95s/it] 82%|████████▏ | 9818/11952 [1:03:32<3:29:31, 5.89s/it] {'loss': 0.4615, 'learning_rate': 1.6260346829458084e-06, 'epoch': 0.82} + 82%|████████▏ | 9818/11952 [1:03:32<3:29:31, 5.89s/it] 82%|████████▏ | 9819/11952 [1:03:37<3:27:07, 5.83s/it] {'loss': 0.4508, 'learning_rate': 1.624553767648931e-06, 'epoch': 0.82} + 82%|████████▏ | 9819/11952 [1:03:37<3:27:07, 5.83s/it] 82%|████████▏ | 9820/11952 [1:03:43<3:24:29, 5.75s/it] {'loss': 0.4657, 'learning_rate': 1.623073467409988e-06, 'epoch': 0.82} + 82%|████████▏ | 9820/11952 [1:03:43<3:24:29, 5.75s/it] 82%|████████▏ | 9821/11952 [1:03:49<3:26:27, 5.81s/it] {'loss': 0.4634, 'learning_rate': 1.621593782337686e-06, 'epoch': 0.82} + 82%|████████▏ | 9821/11952 [1:03:49<3:26:27, 5.81s/it] 82%|████████▏ | 9822/11952 [1:03:55<3:25:37, 5.79s/it] {'loss': 0.4603, 'learning_rate': 1.62011471254069e-06, 'epoch': 0.82} + 82%|████████▏ | 9822/11952 [1:03:55<3:25:37, 5.79s/it] 82%|████████▏ | 9823/11952 [1:04:01<3:28:03, 5.86s/it] {'loss': 0.4654, 'learning_rate': 1.618636258127615e-06, 'epoch': 0.82} + 82%|████████▏ | 9823/11952 [1:04:01<3:28:03, 5.86s/it] 82%|████████▏ | 9824/11952 [1:04:07<3:30:17, 5.93s/it] {'loss': 0.46, 'learning_rate': 1.6171584192070322e-06, 'epoch': 0.82} + 82%|████████▏ | 9824/11952 [1:04:07<3:30:17, 5.93s/it] 82%|████████▏ | 9825/11952 [1:04:12<3:28:58, 5.89s/it] {'loss': 0.478, 'learning_rate': 1.6156811958874664e-06, 'epoch': 0.82} + 82%|████████▏ | 9825/11952 [1:04:12<3:28:58, 5.89s/it] 82%|████████▏ | 9826/11952 [1:04:18<3:28:45, 5.89s/it] {'loss': 0.4481, 'learning_rate': 1.6142045882774027e-06, 'epoch': 0.82} + 82%|████████▏ | 9826/11952 [1:04:18<3:28:45, 5.89s/it] 82%|████████▏ | 9827/11952 [1:04:24<3:30:12, 5.94s/it] {'loss': 0.4746, 'learning_rate': 1.6127285964852758e-06, 'epoch': 0.82} + 82%|████████▏ | 9827/11952 [1:04:24<3:30:12, 5.94s/it] 82%|████████▏ | 9828/11952 [1:04:30<3:29:20, 5.91s/it] {'loss': 0.4595, 'learning_rate': 1.6112532206194719e-06, 'epoch': 0.82} + 82%|████████▏ | 9828/11952 [1:04:30<3:29:20, 5.91s/it] 82%|████████▏ | 9829/11952 [1:04:36<3:27:47, 5.87s/it] {'loss': 0.4624, 'learning_rate': 1.6097784607883427e-06, 'epoch': 0.82} + 82%|████████▏ | 9829/11952 [1:04:36<3:27:47, 5.87s/it] 82%|████████▏ | 9830/11952 [1:04:42<3:26:32, 5.84s/it] {'loss': 0.4669, 'learning_rate': 1.6083043171001856e-06, 'epoch': 0.82} + 82%|████████▏ | 9830/11952 [1:04:42<3:26:32, 5.84s/it] 82%|████████▏ | 9831/11952 [1:04:48<3:29:13, 5.92s/it] {'loss': 0.456, 'learning_rate': 1.6068307896632562e-06, 'epoch': 0.82} + 82%|████████▏ | 9831/11952 [1:04:48<3:29:13, 5.92s/it] 82%|████████▏ | 9832/11952 [1:04:54<3:27:49, 5.88s/it] {'loss': 0.4572, 'learning_rate': 1.6053578785857637e-06, 'epoch': 0.82} + 82%|████████▏ | 9832/11952 [1:04:54<3:27:49, 5.88s/it] 82%|████████▏ | 9833/11952 [1:04:59<3:24:41, 5.80s/it] {'loss': 0.4696, 'learning_rate': 1.6038855839758727e-06, 'epoch': 0.82} + 82%|████████▏ | 9833/11952 [1:04:59<3:24:41, 5.80s/it] 82%|████████▏ | 9834/11952 [1:05:05<3:25:27, 5.82s/it] {'loss': 0.4707, 'learning_rate': 1.6024139059417e-06, 'epoch': 0.82} + 82%|████████▏ | 9834/11952 [1:05:05<3:25:27, 5.82s/it] 82%|████████▏ | 9835/11952 [1:05:11<3:23:33, 5.77s/it] {'loss': 0.4542, 'learning_rate': 1.6009428445913245e-06, 'epoch': 0.82} + 82%|████████▏ | 9835/11952 [1:05:11<3:23:33, 5.77s/it] 82%|████████▏ | 9836/11952 [1:05:17<3:24:19, 5.79s/it] {'loss': 0.4657, 'learning_rate': 1.5994724000327689e-06, 'epoch': 0.82} + 82%|████████▏ | 9836/11952 [1:05:17<3:24:19, 5.79s/it] 82%|████████▏ | 9837/11952 [1:05:23<3:27:09, 5.88s/it] {'loss': 0.4558, 'learning_rate': 1.5980025723740222e-06, 'epoch': 0.82} + 82%|████████▏ | 9837/11952 [1:05:23<3:27:09, 5.88s/it] 82%|████████▏ | 9838/11952 [1:05:29<3:27:27, 5.89s/it] {'loss': 0.4499, 'learning_rate': 1.5965333617230206e-06, 'epoch': 0.82} + 82%|████████▏ | 9838/11952 [1:05:29<3:27:27, 5.89s/it] 82%|████████▏ | 9839/11952 [1:05:34<3:25:40, 5.84s/it] {'loss': 0.4672, 'learning_rate': 1.5950647681876564e-06, 'epoch': 0.82} + 82%|████████▏ | 9839/11952 [1:05:34<3:25:40, 5.84s/it] 82%|████████▏ | 9840/11952 [1:05:40<3:27:31, 5.90s/it] {'loss': 0.4803, 'learning_rate': 1.5935967918757766e-06, 'epoch': 0.82} + 82%|████████▏ | 9840/11952 [1:05:40<3:27:31, 5.90s/it] 82%|████████▏ | 9841/11952 [1:05:46<3:27:29, 5.90s/it] {'loss': 0.4685, 'learning_rate': 1.5921294328951842e-06, 'epoch': 0.82} + 82%|████████▏ | 9841/11952 [1:05:46<3:27:29, 5.90s/it] 82%|████████▏ | 9842/11952 [1:05:52<3:26:22, 5.87s/it] {'loss': 0.4913, 'learning_rate': 1.5906626913536315e-06, 'epoch': 0.82} + 82%|████████▏ | 9842/11952 [1:05:52<3:26:22, 5.87s/it] 82%|████████▏ | 9843/11952 [1:05:58<3:29:09, 5.95s/it] {'loss': 0.4623, 'learning_rate': 1.5891965673588371e-06, 'epoch': 0.82} + 82%|████████▏ | 9843/11952 [1:05:58<3:29:09, 5.95s/it] 82%|████████▏ | 9844/11952 [1:06:04<3:28:20, 5.93s/it] {'loss': 0.467, 'learning_rate': 1.5877310610184638e-06, 'epoch': 0.82} + 82%|████████▏ | 9844/11952 [1:06:04<3:28:20, 5.93s/it] 82%|████████▏ | 9845/11952 [1:06:10<3:26:55, 5.89s/it] {'loss': 0.4534, 'learning_rate': 1.5862661724401296e-06, 'epoch': 0.82} + 82%|████████▏ | 9845/11952 [1:06:10<3:26:55, 5.89s/it] 82%|████████▏ | 9846/11952 [1:06:16<3:25:52, 5.87s/it] {'loss': 0.4589, 'learning_rate': 1.5848019017314143e-06, 'epoch': 0.82} + 82%|████████▏ | 9846/11952 [1:06:16<3:25:52, 5.87s/it] 82%|████████▏ | 9847/11952 [1:06:22<3:29:20, 5.97s/it] {'loss': 0.4532, 'learning_rate': 1.5833382489998461e-06, 'epoch': 0.82} + 82%|████████▏ | 9847/11952 [1:06:22<3:29:20, 5.97s/it] 82%|████████▏ | 9848/11952 [1:06:28<3:27:04, 5.90s/it] {'loss': 0.4563, 'learning_rate': 1.5818752143529092e-06, 'epoch': 0.82} + 82%|████████▏ | 9848/11952 [1:06:28<3:27:04, 5.90s/it] 82%|████████▏ | 9849/11952 [1:06:34<3:27:16, 5.91s/it] {'loss': 0.4748, 'learning_rate': 1.580412797898041e-06, 'epoch': 0.82} + 82%|████████▏ | 9849/11952 [1:06:34<3:27:16, 5.91s/it]6 AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +0 AutoResumeHook: Checking whether to suspend... + 82%|████████▏ | 9850/11952 [1:06:40<3:29:53, 5.99s/it] {'loss': 0.4534, 'learning_rate': 1.578950999742639e-06, 'epoch': 0.82} + 82%|████████▏ | 9850/11952 [1:06:40<3:29:53, 5.99s/it] 82%|████████▏ | 9851/11952 [1:06:46<3:26:28, 5.90s/it] {'loss': 0.4749, 'learning_rate': 1.5774898199940503e-06, 'epoch': 0.82} + 82%|████████▏ | 9851/11952 [1:06:46<3:26:28, 5.90s/it] 82%|████████▏ | 9852/11952 [1:06:51<3:26:02, 5.89s/it] {'loss': 0.4571, 'learning_rate': 1.576029258759577e-06, 'epoch': 0.82} + 82%|████████▏ | 9852/11952 [1:06:51<3:26:02, 5.89s/it] 82%|████████▏ | 9853/11952 [1:06:57<3:28:21, 5.96s/it] {'loss': 0.4619, 'learning_rate': 1.574569316146477e-06, 'epoch': 0.82} + 82%|████████▏ | 9853/11952 [1:06:57<3:28:21, 5.96s/it] 82%|████████▏ | 9854/11952 [1:07:03<3:25:58, 5.89s/it] {'loss': 0.4568, 'learning_rate': 1.573109992261963e-06, 'epoch': 0.82} + 82%|████████▏ | 9854/11952 [1:07:03<3:25:58, 5.89s/it] 82%|████████▏ | 9855/11952 [1:07:09<3:22:28, 5.79s/it] {'loss': 0.46, 'learning_rate': 1.5716512872131983e-06, 'epoch': 0.82} + 82%|████████▏ | 9855/11952 [1:07:09<3:22:28, 5.79s/it] 82%|████████▏ | 9856/11952 [1:07:15<3:23:38, 5.83s/it] {'loss': 0.464, 'learning_rate': 1.5701932011073072e-06, 'epoch': 0.82} + 82%|████████▏ | 9856/11952 [1:07:15<3:23:38, 5.83s/it] 82%|████████▏ | 9857/11952 [1:07:21<3:26:13, 5.91s/it] {'loss': 0.4505, 'learning_rate': 1.5687357340513676e-06, 'epoch': 0.82} + 82%|████████▏ | 9857/11952 [1:07:21<3:26:13, 5.91s/it] 82%|████████▏ | 9858/11952 [1:07:27<3:24:28, 5.86s/it] {'loss': 0.4821, 'learning_rate': 1.567278886152407e-06, 'epoch': 0.82} + 82%|████████▏ | 9858/11952 [1:07:27<3:24:28, 5.86s/it] 82%|████████▏ | 9859/11952 [1:07:32<3:23:15, 5.83s/it] {'loss': 0.4536, 'learning_rate': 1.5658226575174107e-06, 'epoch': 0.82} + 82%|████████▏ | 9859/11952 [1:07:32<3:23:15, 5.83s/it] 82%|████████▏ | 9860/11952 [1:07:38<3:21:15, 5.77s/it] {'loss': 0.4568, 'learning_rate': 1.564367048253318e-06, 'epoch': 0.82} + 82%|████████▏ | 9860/11952 [1:07:38<3:21:15, 5.77s/it] 83%|████████▎ | 9861/11952 [1:07:44<3:19:22, 5.72s/it] {'loss': 0.4723, 'learning_rate': 1.5629120584670233e-06, 'epoch': 0.83} + 83%|████████▎ | 9861/11952 [1:07:44<3:19:22, 5.72s/it] 83%|████████▎ | 9862/11952 [1:07:49<3:20:49, 5.77s/it] {'loss': 0.4438, 'learning_rate': 1.561457688265372e-06, 'epoch': 0.83} + 83%|████████▎ | 9862/11952 [1:07:49<3:20:49, 5.77s/it] 83%|████████▎ | 9863/11952 [1:07:56<3:24:35, 5.88s/it] {'loss': 0.4778, 'learning_rate': 1.5600039377551713e-06, 'epoch': 0.83} + 83%|████████▎ | 9863/11952 [1:07:56<3:24:35, 5.88s/it] 83%|████████▎ | 9864/11952 [1:08:02<3:26:35, 5.94s/it] {'loss': 0.4595, 'learning_rate': 1.5585508070431777e-06, 'epoch': 0.83} + 83%|████████▎ | 9864/11952 [1:08:02<3:26:35, 5.94s/it] 83%|████████▎ | 9865/11952 [1:08:07<3:25:08, 5.90s/it] {'loss': 0.4779, 'learning_rate': 1.5570982962361014e-06, 'epoch': 0.83} + 83%|████████▎ | 9865/11952 [1:08:07<3:25:08, 5.90s/it] 83%|████████▎ | 9866/11952 [1:08:13<3:26:14, 5.93s/it] {'loss': 0.4676, 'learning_rate': 1.5556464054406084e-06, 'epoch': 0.83} + 83%|████████▎ | 9866/11952 [1:08:13<3:26:14, 5.93s/it] 83%|████████▎ | 9867/11952 [1:08:19<3:23:48, 5.86s/it] {'loss': 0.4708, 'learning_rate': 1.5541951347633222e-06, 'epoch': 0.83} + 83%|████████▎ | 9867/11952 [1:08:19<3:23:48, 5.86s/it] 83%|████████▎ | 9868/11952 [1:08:25<3:21:48, 5.81s/it] {'loss': 0.4505, 'learning_rate': 1.5527444843108164e-06, 'epoch': 0.83} + 83%|████████▎ | 9868/11952 [1:08:25<3:21:48, 5.81s/it] 83%|████████▎ | 9869/11952 [1:08:31<3:24:27, 5.89s/it] {'loss': 0.4521, 'learning_rate': 1.5512944541896192e-06, 'epoch': 0.83} + 83%|████████▎ | 9869/11952 [1:08:31<3:24:27, 5.89s/it] 83%|████████▎ | 9870/11952 [1:08:37<3:22:58, 5.85s/it] {'loss': 0.4528, 'learning_rate': 1.5498450445062185e-06, 'epoch': 0.83} + 83%|████████▎ | 9870/11952 [1:08:37<3:22:58, 5.85s/it] 83%|████████▎ | 9871/11952 [1:08:42<3:20:17, 5.77s/it] {'loss': 0.4653, 'learning_rate': 1.5483962553670507e-06, 'epoch': 0.83} + 83%|████████▎ | 9871/11952 [1:08:42<3:20:17, 5.77s/it] 83%|████████▎ | 9872/11952 [1:08:48<3:20:04, 5.77s/it] {'loss': 0.4514, 'learning_rate': 1.5469480868785092e-06, 'epoch': 0.83} + 83%|████████▎ | 9872/11952 [1:08:48<3:20:04, 5.77s/it] 83%|████████▎ | 9873/11952 [1:08:54<3:19:42, 5.76s/it] {'loss': 0.4529, 'learning_rate': 1.5455005391469414e-06, 'epoch': 0.83} + 83%|████████▎ | 9873/11952 [1:08:54<3:19:42, 5.76s/it] 83%|████████▎ | 9874/11952 [1:09:00<3:22:31, 5.85s/it] {'loss': 0.4503, 'learning_rate': 1.5440536122786487e-06, 'epoch': 0.83} + 83%|████████▎ | 9874/11952 [1:09:00<3:22:31, 5.85s/it] 83%|████████▎ | 9875/11952 [1:09:05<3:19:40, 5.77s/it] {'loss': 0.4638, 'learning_rate': 1.5426073063798853e-06, 'epoch': 0.83} + 83%|████████▎ | 9875/11952 [1:09:05<3:19:40, 5.77s/it] 83%|████████▎ | 9876/11952 [1:09:11<3:21:51, 5.83s/it] {'loss': 0.4875, 'learning_rate': 1.541161621556867e-06, 'epoch': 0.83} + 83%|████████▎ | 9876/11952 [1:09:11<3:21:51, 5.83s/it] 83%|████████▎ | 9877/11952 [1:09:18<3:26:17, 5.96s/it] {'loss': 0.4691, 'learning_rate': 1.5397165579157547e-06, 'epoch': 0.83} + 83%|████████▎ | 9877/11952 [1:09:18<3:26:17, 5.96s/it] 83%|████████▎ | 9878/11952 [1:09:24<3:27:50, 6.01s/it] {'loss': 0.4669, 'learning_rate': 1.5382721155626701e-06, 'epoch': 0.83} + 83%|████████▎ | 9878/11952 [1:09:24<3:27:50, 6.01s/it] 83%|████████▎ | 9879/11952 [1:09:30<3:26:09, 5.97s/it] {'loss': 0.4839, 'learning_rate': 1.5368282946036884e-06, 'epoch': 0.83} + 83%|████████▎ | 9879/11952 [1:09:30<3:26:09, 5.97s/it] 83%|████████▎ | 9880/11952 [1:09:36<3:25:47, 5.96s/it] {'loss': 0.45, 'learning_rate': 1.5353850951448346e-06, 'epoch': 0.83} + 83%|████████▎ | 9880/11952 [1:09:36<3:25:47, 5.96s/it] 83%|████████▎ | 9881/11952 [1:09:42<3:25:49, 5.96s/it] {'loss': 0.4832, 'learning_rate': 1.533942517292092e-06, 'epoch': 0.83} + 83%|████████▎ | 9881/11952 [1:09:42<3:25:49, 5.96s/it] 83%|████████▎ | 9882/11952 [1:09:47<3:22:35, 5.87s/it] {'loss': 0.4552, 'learning_rate': 1.5325005611513988e-06, 'epoch': 0.83} + 83%|████████▎ | 9882/11952 [1:09:47<3:22:35, 5.87s/it] 83%|████████▎ | 9883/11952 [1:09:53<3:23:29, 5.90s/it] {'loss': 0.4636, 'learning_rate': 1.5310592268286427e-06, 'epoch': 0.83} + 83%|████████▎ | 9883/11952 [1:09:53<3:23:29, 5.90s/it] 83%|████████▎ | 9884/11952 [1:09:59<3:24:48, 5.94s/it] {'loss': 0.4557, 'learning_rate': 1.5296185144296737e-06, 'epoch': 0.83} + 83%|████████▎ | 9884/11952 [1:09:59<3:24:48, 5.94s/it] 83%|████████▎ | 9885/11952 [1:10:05<3:24:44, 5.94s/it] {'loss': 0.4538, 'learning_rate': 1.5281784240602915e-06, 'epoch': 0.83} + 83%|████████▎ | 9885/11952 [1:10:05<3:24:44, 5.94s/it] 83%|████████▎ | 9886/11952 [1:10:11<3:22:20, 5.88s/it] {'loss': 0.4727, 'learning_rate': 1.5267389558262458e-06, 'epoch': 0.83} + 83%|████████▎ | 9886/11952 [1:10:11<3:22:20, 5.88s/it] 83%|████████▎ | 9887/11952 [1:10:17<3:21:00, 5.84s/it] {'loss': 0.468, 'learning_rate': 1.525300109833251e-06, 'epoch': 0.83} + 83%|████████▎ | 9887/11952 [1:10:17<3:21:00, 5.84s/it] 83%|████████▎ | 9888/11952 [1:10:22<3:20:03, 5.82s/it] {'loss': 0.4555, 'learning_rate': 1.5238618861869657e-06, 'epoch': 0.83} + 83%|████████▎ | 9888/11952 [1:10:22<3:20:03, 5.82s/it] 83%|████████▎ | 9889/11952 [1:10:28<3:21:31, 5.86s/it] {'loss': 0.4554, 'learning_rate': 1.5224242849930104e-06, 'epoch': 0.83} + 83%|████████▎ | 9889/11952 [1:10:28<3:21:31, 5.86s/it] 83%|████████▎ | 9890/11952 [1:10:34<3:22:30, 5.89s/it] {'loss': 0.461, 'learning_rate': 1.5209873063569514e-06, 'epoch': 0.83} + 83%|████████▎ | 9890/11952 [1:10:34<3:22:30, 5.89s/it] 83%|████████▎ | 9891/11952 [1:10:40<3:22:01, 5.88s/it] {'loss': 0.4678, 'learning_rate': 1.5195509503843198e-06, 'epoch': 0.83} + 83%|████████▎ | 9891/11952 [1:10:40<3:22:01, 5.88s/it] 83%|████████▎ | 9892/11952 [1:10:46<3:24:05, 5.94s/it] {'loss': 0.4675, 'learning_rate': 1.5181152171805946e-06, 'epoch': 0.83} + 83%|████████▎ | 9892/11952 [1:10:46<3:24:05, 5.94s/it] 83%|████████▎ | 9893/11952 [1:10:52<3:20:11, 5.83s/it] {'loss': 0.4785, 'learning_rate': 1.5166801068512083e-06, 'epoch': 0.83} + 83%|████████▎ | 9893/11952 [1:10:52<3:20:11, 5.83s/it] 83%|████████▎ | 9894/11952 [1:10:58<3:22:08, 5.89s/it] {'loss': 0.4646, 'learning_rate': 1.5152456195015508e-06, 'epoch': 0.83} + 83%|████████▎ | 9894/11952 [1:10:58<3:22:08, 5.89s/it] 83%|████████▎ | 9895/11952 [1:11:04<3:24:03, 5.95s/it] {'loss': 0.4579, 'learning_rate': 1.5138117552369636e-06, 'epoch': 0.83} + 83%|████████▎ | 9895/11952 [1:11:04<3:24:03, 5.95s/it] 83%|████████▎ | 9896/11952 [1:11:10<3:27:00, 6.04s/it] {'loss': 0.4778, 'learning_rate': 1.5123785141627422e-06, 'epoch': 0.83} + 83%|████████▎ | 9896/11952 [1:11:10<3:27:00, 6.04s/it] 83%|████████▎ | 9897/11952 [1:11:16<3:24:20, 5.97s/it] {'loss': 0.4539, 'learning_rate': 1.5109458963841405e-06, 'epoch': 0.83} + 83%|████████▎ | 9897/11952 [1:11:16<3:24:20, 5.97s/it] 83%|████████▎ | 9898/11952 [1:11:22<3:25:07, 5.99s/it] {'loss': 0.4777, 'learning_rate': 1.5095139020063654e-06, 'epoch': 0.83} + 83%|████████▎ | 9898/11952 [1:11:22<3:25:07, 5.99s/it] 83%|████████▎ | 9899/11952 [1:11:28<3:24:41, 5.98s/it] {'loss': 0.4639, 'learning_rate': 1.5080825311345748e-06, 'epoch': 0.83} + 83%|████████▎ | 9899/11952 [1:11:28<3:24:41, 5.98s/it]6 AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... +14 AutoResumeHook: Checking whether to suspend...AutoResumeHook: Checking whether to suspend... + +5 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +0 AutoResumeHook: Checking whether to suspend... + 83%|████████▎ | 9900/11952 [1:11:34<3:28:12, 6.09s/it] {'loss': 0.4715, 'learning_rate': 1.5066517838738826e-06, 'epoch': 0.83} + 83%|████████▎ | 9900/11952 [1:11:34<3:28:12, 6.09s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-9900/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-9900/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/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( + 83%|████████▎ | 9901/11952 [1:12:04<7:29:11, 13.14s/it] {'loss': 0.4642, 'learning_rate': 1.5052216603293567e-06, 'epoch': 0.83} + 83%|████████▎ | 9901/11952 [1:12:04<7:29:11, 13.14s/it] 83%|████████▎ | 9902/11952 [1:12:10<6:16:27, 11.02s/it] {'loss': 0.4706, 'learning_rate': 1.5037921606060201e-06, 'epoch': 0.83} + 83%|████████▎ | 9902/11952 [1:12:10<6:16:27, 11.02s/it] 83%|████████▎ | 9903/11952 [1:12:16<5:22:38, 9.45s/it] {'loss': 0.4704, 'learning_rate': 1.5023632848088466e-06, 'epoch': 0.83} + 83%|████████▎ | 9903/11952 [1:12:16<5:22:38, 9.45s/it] 83%|████████▎ | 9904/11952 [1:12:22<4:44:11, 8.33s/it] {'loss': 0.4681, 'learning_rate': 1.5009350330427707e-06, 'epoch': 0.83} + 83%|████████▎ | 9904/11952 [1:12:22<4:44:11, 8.33s/it] 83%|████████▎ | 9905/11952 [1:12:27<4:17:05, 7.54s/it] {'loss': 0.4892, 'learning_rate': 1.4995074054126758e-06, 'epoch': 0.83} + 83%|████████▎ | 9905/11952 [1:12:27<4:17:05, 7.54s/it] 83%|████████▎ | 9906/11952 [1:12:33<4:00:38, 7.06s/it] {'loss': 0.4726, 'learning_rate': 1.4980804020234018e-06, 'epoch': 0.83} + 83%|████████▎ | 9906/11952 [1:12:33<4:00:38, 7.06s/it] 83%|████████▎ | 9907/11952 [1:12:39<3:48:44, 6.71s/it] {'loss': 0.449, 'learning_rate': 1.4966540229797377e-06, 'epoch': 0.83} + 83%|████████▎ | 9907/11952 [1:12:39<3:48:44, 6.71s/it] 83%|████████▎ | 9908/11952 [1:12:45<3:41:47, 6.51s/it] {'loss': 0.4921, 'learning_rate': 1.495228268386436e-06, 'epoch': 0.83} + 83%|████████▎ | 9908/11952 [1:12:45<3:41:47, 6.51s/it] 83%|████████▎ | 9909/11952 [1:12:51<3:33:24, 6.27s/it] {'loss': 0.4561, 'learning_rate': 1.4938031383481976e-06, 'epoch': 0.83} + 83%|████████▎ | 9909/11952 [1:12:51<3:33:24, 6.27s/it] 83%|████████▎ | 9910/11952 [1:12:57<3:29:22, 6.15s/it] {'loss': 0.4515, 'learning_rate': 1.4923786329696732e-06, 'epoch': 0.83} + 83%|████████▎ | 9910/11952 [1:12:57<3:29:22, 6.15s/it] 83%|████████▎ | 9911/11952 [1:13:03<3:27:38, 6.10s/it] {'loss': 0.4636, 'learning_rate': 1.490954752355479e-06, 'epoch': 0.83} + 83%|████████▎ | 9911/11952 [1:13:03<3:27:38, 6.10s/it] 83%|████████▎ | 9912/11952 [1:13:09<3:26:37, 6.08s/it] {'loss': 0.4696, 'learning_rate': 1.4895314966101771e-06, 'epoch': 0.83} + 83%|████████▎ | 9912/11952 [1:13:09<3:26:37, 6.08s/it] 83%|████████▎ | 9913/11952 [1:13:14<3:22:50, 5.97s/it] {'loss': 0.46, 'learning_rate': 1.4881088658382825e-06, 'epoch': 0.83} + 83%|████████▎ | 9913/11952 [1:13:14<3:22:50, 5.97s/it] 83%|████████▎ | 9914/11952 [1:13:20<3:20:54, 5.91s/it] {'loss': 0.4571, 'learning_rate': 1.4866868601442708e-06, 'epoch': 0.83} + 83%|████████▎ | 9914/11952 [1:13:20<3:20:54, 5.91s/it] 83%|████████▎ | 9915/11952 [1:13:26<3:21:23, 5.93s/it] {'loss': 0.4791, 'learning_rate': 1.4852654796325649e-06, 'epoch': 0.83} + 83%|████████▎ | 9915/11952 [1:13:26<3:21:23, 5.93s/it] 83%|████████▎ | 9916/11952 [1:13:32<3:22:15, 5.96s/it] {'loss': 0.4548, 'learning_rate': 1.483844724407546e-06, 'epoch': 0.83} + 83%|████████▎ | 9916/11952 [1:13:32<3:22:15, 5.96s/it] 83%|████████▎ | 9917/11952 [1:13:38<3:22:17, 5.96s/it] {'loss': 0.4757, 'learning_rate': 1.4824245945735504e-06, 'epoch': 0.83} + 83%|████████▎ | 9917/11952 [1:13:38<3:22:17, 5.96s/it] 83%|████████▎ | 9918/11952 [1:13:44<3:19:56, 5.90s/it] {'loss': 0.4646, 'learning_rate': 1.4810050902348637e-06, 'epoch': 0.83} + 83%|████████▎ | 9918/11952 [1:13:44<3:19:56, 5.90s/it] 83%|████████▎ | 9919/11952 [1:13:50<3:20:14, 5.91s/it] {'loss': 0.4581, 'learning_rate': 1.4795862114957316e-06, 'epoch': 0.83} + 83%|████████▎ | 9919/11952 [1:13:50<3:20:14, 5.91s/it] 83%|████████▎ | 9920/11952 [1:13:56<3:19:03, 5.88s/it] {'loss': 0.4629, 'learning_rate': 1.4781679584603502e-06, 'epoch': 0.83} + 83%|████████▎ | 9920/11952 [1:13:56<3:19:03, 5.88s/it] 83%|████████▎ | 9921/11952 [1:14:01<3:18:33, 5.87s/it] {'loss': 0.4577, 'learning_rate': 1.476750331232868e-06, 'epoch': 0.83} + 83%|████████▎ | 9921/11952 [1:14:01<3:18:33, 5.87s/it] 83%|████████▎ | 9922/11952 [1:14:08<3:22:59, 6.00s/it] {'loss': 0.4527, 'learning_rate': 1.475333329917391e-06, 'epoch': 0.83} + 83%|████████▎ | 9922/11952 [1:14:08<3:22:59, 6.00s/it] 83%|████████▎ | 9923/11952 [1:14:14<3:21:56, 5.97s/it] {'loss': 0.4807, 'learning_rate': 1.4739169546179765e-06, 'epoch': 0.83} + 83%|████████▎ | 9923/11952 [1:14:14<3:21:56, 5.97s/it] 83%|████████▎ | 9924/11952 [1:14:20<3:22:53, 6.00s/it] {'loss': 0.4923, 'learning_rate': 1.4725012054386378e-06, 'epoch': 0.83} + 83%|████████▎ | 9924/11952 [1:14:20<3:22:53, 6.00s/it] 83%|████████▎ | 9925/11952 [1:14:26<3:20:43, 5.94s/it] {'loss': 0.4598, 'learning_rate': 1.471086082483343e-06, 'epoch': 0.83} + 83%|████████▎ | 9925/11952 [1:14:26<3:20:43, 5.94s/it] 83%|████████▎ | 9926/11952 [1:14:31<3:19:45, 5.92s/it] {'loss': 0.4665, 'learning_rate': 1.4696715858560117e-06, 'epoch': 0.83} + 83%|████████▎ | 9926/11952 [1:14:31<3:19:45, 5.92s/it] 83%|████████▎ | 9927/11952 [1:14:37<3:17:39, 5.86s/it] {'loss': 0.4629, 'learning_rate': 1.4682577156605172e-06, 'epoch': 0.83} + 83%|████████▎ | 9927/11952 [1:14:37<3:17:39, 5.86s/it] 83%|████████▎ | 9928/11952 [1:14:43<3:17:12, 5.85s/it] {'loss': 0.4601, 'learning_rate': 1.4668444720006925e-06, 'epoch': 0.83} + 83%|████████▎ | 9928/11952 [1:14:43<3:17:12, 5.85s/it] 83%|████████▎ | 9929/11952 [1:14:49<3:18:39, 5.89s/it] {'loss': 0.4491, 'learning_rate': 1.465431854980317e-06, 'epoch': 0.83} + 83%|████████▎ | 9929/11952 [1:14:49<3:18:39, 5.89s/it] 83%|████████▎ | 9930/11952 [1:14:55<3:17:19, 5.86s/it] {'loss': 0.4712, 'learning_rate': 1.464019864703128e-06, 'epoch': 0.83} + 83%|████████▎ | 9930/11952 [1:14:55<3:17:19, 5.86s/it] 83%|████████▎ | 9931/11952 [1:15:01<3:19:04, 5.91s/it] {'loss': 0.4774, 'learning_rate': 1.462608501272814e-06, 'epoch': 0.83} + 83%|████████▎ | 9931/11952 [1:15:01<3:19:04, 5.91s/it] 83%|████████▎ | 9932/11952 [1:15:07<3:18:55, 5.91s/it] {'loss': 0.4513, 'learning_rate': 1.4611977647930253e-06, 'epoch': 0.83} + 83%|████████▎ | 9932/11952 [1:15:07<3:18:55, 5.91s/it] 83%|████████▎ | 9933/11952 [1:15:12<3:17:02, 5.86s/it] {'loss': 0.4563, 'learning_rate': 1.4597876553673563e-06, 'epoch': 0.83} + 83%|████████▎ | 9933/11952 [1:15:12<3:17:02, 5.86s/it] 83%|████████▎ | 9934/11952 [1:15:18<3:17:30, 5.87s/it] {'loss': 0.499, 'learning_rate': 1.4583781730993608e-06, 'epoch': 0.83} + 83%|████████▎ | 9934/11952 [1:15:18<3:17:30, 5.87s/it] 83%|████████▎ | 9935/11952 [1:15:24<3:14:11, 5.78s/it] {'loss': 0.4526, 'learning_rate': 1.4569693180925448e-06, 'epoch': 0.83} + 83%|████████▎ | 9935/11952 [1:15:24<3:14:11, 5.78s/it] 83%|████████▎ | 9936/11952 [1:15:30<3:18:07, 5.90s/it] {'loss': 0.4584, 'learning_rate': 1.4555610904503693e-06, 'epoch': 0.83} + 83%|████████▎ | 9936/11952 [1:15:30<3:18:07, 5.90s/it] 83%|████████▎ | 9937/11952 [1:15:36<3:19:49, 5.95s/it] {'loss': 0.4796, 'learning_rate': 1.4541534902762454e-06, 'epoch': 0.83} + 83%|████████▎ | 9937/11952 [1:15:36<3:19:49, 5.95s/it] 83%|████████▎ | 9938/11952 [1:15:42<3:16:05, 5.84s/it] {'loss': 0.4667, 'learning_rate': 1.4527465176735468e-06, 'epoch': 0.83} + 83%|████████▎ | 9938/11952 [1:15:42<3:16:05, 5.84s/it] 83%|████████▎ | 9939/11952 [1:15:47<3:13:59, 5.78s/it] {'loss': 0.4605, 'learning_rate': 1.4513401727455912e-06, 'epoch': 0.83} + 83%|████████▎ | 9939/11952 [1:15:47<3:13:59, 5.78s/it] 83%|████████▎ | 9940/11952 [1:15:53<3:15:34, 5.83s/it] {'loss': 0.4599, 'learning_rate': 1.4499344555956596e-06, 'epoch': 0.83} + 83%|████████▎ | 9940/11952 [1:15:53<3:15:34, 5.83s/it] 83%|████████▎ | 9941/11952 [1:15:59<3:13:33, 5.77s/it] {'loss': 0.4705, 'learning_rate': 1.4485293663269784e-06, 'epoch': 0.83} + 83%|████████▎ | 9941/11952 [1:15:59<3:13:33, 5.77s/it] 83%|████████▎ | 9942/11952 [1:16:05<3:17:34, 5.90s/it] {'loss': 0.4587, 'learning_rate': 1.4471249050427327e-06, 'epoch': 0.83} + 83%|████████▎ | 9942/11952 [1:16:05<3:17:34, 5.90s/it] 83%|████████▎ | 9943/11952 [1:16:11<3:17:39, 5.90s/it] {'loss': 0.4666, 'learning_rate': 1.445721071846059e-06, 'epoch': 0.83} + 83%|████████▎ | 9943/11952 [1:16:11<3:17:39, 5.90s/it] 83%|████████▎ | 9944/11952 [1:16:17<3:17:54, 5.91s/it] {'loss': 0.4746, 'learning_rate': 1.4443178668400482e-06, 'epoch': 0.83} + 83%|████████▎ | 9944/11952 [1:16:17<3:17:54, 5.91s/it] 83%|████████▎ | 9945/11952 [1:16:23<3:16:53, 5.89s/it] {'loss': 0.4541, 'learning_rate': 1.44291529012775e-06, 'epoch': 0.83} + 83%|████████▎ | 9945/11952 [1:16:23<3:16:53, 5.89s/it] 83%|████████▎ | 9946/11952 [1:16:29<3:15:15, 5.84s/it] {'loss': 0.4601, 'learning_rate': 1.4415133418121607e-06, 'epoch': 0.83} + 83%|████████▎ | 9946/11952 [1:16:29<3:15:15, 5.84s/it] 83%|████████▎ | 9947/11952 [1:16:35<3:17:17, 5.90s/it] {'loss': 0.4644, 'learning_rate': 1.440112021996235e-06, 'epoch': 0.83} + 83%|████████▎ | 9947/11952 [1:16:35<3:17:17, 5.90s/it] 83%|████████▎ | 9948/11952 [1:16:40<3:13:19, 5.79s/it] {'loss': 0.4746, 'learning_rate': 1.438711330782877e-06, 'epoch': 0.83} + 83%|████████▎ | 9948/11952 [1:16:40<3:13:19, 5.79s/it] 83%|████████▎ | 9949/11952 [1:16:46<3:14:41, 5.83s/it] {'loss': 0.453, 'learning_rate': 1.4373112682749513e-06, 'epoch': 0.83} + 83%|████████▎ | 9949/11952 [1:16:46<3:14:41, 5.83s/it]2 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... +35 AutoResumeHook: Checking whether to suspend...AutoResumeHook: Checking whether to suspend... + +41 AutoResumeHook: Checking whether to suspend...AutoResumeHook: Checking whether to suspend... + +7 AutoResumeHook: Checking whether to suspend... +0 AutoResumeHook: Checking whether to suspend... + 83%|████████▎ | 9950/11952 [1:16:52<3:13:16, 5.79s/it] {'loss': 0.4469, 'learning_rate': 1.435911834575271e-06, 'epoch': 0.83} + 83%|████████▎ | 9950/11952 [1:16:52<3:13:16, 5.79s/it] 83%|████████▎ | 9951/11952 [1:16:58<3:15:59, 5.88s/it] {'loss': 0.4831, 'learning_rate': 1.4345130297866028e-06, 'epoch': 0.83} + 83%|████████▎ | 9951/11952 [1:16:58<3:15:59, 5.88s/it] 83%|████████▎ | 9952/11952 [1:17:04<3:19:29, 5.98s/it] {'loss': 0.4721, 'learning_rate': 1.4331148540116736e-06, 'epoch': 0.83} + 83%|████████▎ | 9952/11952 [1:17:04<3:19:29, 5.98s/it] 83%|████████▎ | 9953/11952 [1:17:10<3:18:16, 5.95s/it] {'loss': 0.4719, 'learning_rate': 1.4317173073531577e-06, 'epoch': 0.83} + 83%|████████▎ | 9953/11952 [1:17:10<3:18:16, 5.95s/it] 83%|████████▎ | 9954/11952 [1:17:16<3:22:18, 6.08s/it] {'loss': 0.4573, 'learning_rate': 1.4303203899136841e-06, 'epoch': 0.83} + 83%|████████▎ | 9954/11952 [1:17:16<3:22:18, 6.08s/it] 83%|████████▎ | 9955/11952 [1:17:22<3:16:39, 5.91s/it] {'loss': 0.4556, 'learning_rate': 1.4289241017958366e-06, 'epoch': 0.83} + 83%|████████▎ | 9955/11952 [1:17:22<3:16:39, 5.91s/it] 83%|████████▎ | 9956/11952 [1:17:28<3:15:43, 5.88s/it] {'loss': 0.4715, 'learning_rate': 1.4275284431021541e-06, 'epoch': 0.83} + 83%|████████▎ | 9956/11952 [1:17:28<3:15:43, 5.88s/it] 83%|████████▎ | 9957/11952 [1:17:33<3:13:39, 5.82s/it] {'loss': 0.4622, 'learning_rate': 1.4261334139351269e-06, 'epoch': 0.83} + 83%|████████▎ | 9957/11952 [1:17:33<3:13:39, 5.82s/it] 83%|████████▎ | 9958/11952 [1:17:39<3:13:38, 5.83s/it] {'loss': 0.4679, 'learning_rate': 1.4247390143971972e-06, 'epoch': 0.83} + 83%|████████▎ | 9958/11952 [1:17:39<3:13:38, 5.83s/it] 83%|████████▎ | 9959/11952 [1:17:45<3:15:44, 5.89s/it] {'loss': 0.4744, 'learning_rate': 1.423345244590768e-06, 'epoch': 0.83} + 83%|████████▎ | 9959/11952 [1:17:45<3:15:44, 5.89s/it] 83%|████████▎ | 9960/11952 [1:17:51<3:14:26, 5.86s/it] {'loss': 0.4441, 'learning_rate': 1.4219521046181928e-06, 'epoch': 0.83} + 83%|████████▎ | 9960/11952 [1:17:51<3:14:26, 5.86s/it] 83%|████████▎ | 9961/11952 [1:17:57<3:14:51, 5.87s/it] {'loss': 0.4609, 'learning_rate': 1.4205595945817773e-06, 'epoch': 0.83} + 83%|████████▎ | 9961/11952 [1:17:57<3:14:51, 5.87s/it] 83%|████████▎ | 9962/11952 [1:18:03<3:14:12, 5.86s/it] {'loss': 0.4812, 'learning_rate': 1.41916771458378e-06, 'epoch': 0.83} + 83%|████████▎ | 9962/11952 [1:18:03<3:14:12, 5.86s/it] 83%|████████▎ | 9963/11952 [1:18:09<3:18:10, 5.98s/it] {'loss': 0.4526, 'learning_rate': 1.4177764647264148e-06, 'epoch': 0.83} + 83%|████████▎ | 9963/11952 [1:18:09<3:18:10, 5.98s/it] 83%|████████▎ | 9964/11952 [1:18:15<3:16:27, 5.93s/it] {'loss': 0.4531, 'learning_rate': 1.4163858451118506e-06, 'epoch': 0.83} + 83%|████████▎ | 9964/11952 [1:18:15<3:16:27, 5.93s/it] 83%|████████▎ | 9965/11952 [1:18:20<3:13:17, 5.84s/it] {'loss': 0.4603, 'learning_rate': 1.414995855842205e-06, 'epoch': 0.83} + 83%|████████▎ | 9965/11952 [1:18:20<3:13:17, 5.84s/it] 83%|████████▎ | 9966/11952 [1:18:26<3:14:14, 5.87s/it] {'loss': 0.447, 'learning_rate': 1.4136064970195595e-06, 'epoch': 0.83} + 83%|████████▎ | 9966/11952 [1:18:26<3:14:14, 5.87s/it] 83%|████████▎ | 9967/11952 [1:18:32<3:12:07, 5.81s/it] {'loss': 0.4504, 'learning_rate': 1.4122177687459382e-06, 'epoch': 0.83} + 83%|████████▎ | 9967/11952 [1:18:32<3:12:07, 5.81s/it] 83%|████████▎ | 9968/11952 [1:18:38<3:11:30, 5.79s/it] {'loss': 0.461, 'learning_rate': 1.4108296711233249e-06, 'epoch': 0.83} + 83%|████████▎ | 9968/11952 [1:18:38<3:11:30, 5.79s/it] 83%|████████▎ | 9969/11952 [1:18:44<3:12:37, 5.83s/it] {'loss': 0.458, 'learning_rate': 1.4094422042536538e-06, 'epoch': 0.83} + 83%|████████▎ | 9969/11952 [1:18:44<3:12:37, 5.83s/it] 83%|████████▎ | 9970/11952 [1:18:49<3:10:49, 5.78s/it] {'loss': 0.4563, 'learning_rate': 1.4080553682388188e-06, 'epoch': 0.83} + 83%|████████▎ | 9970/11952 [1:18:49<3:10:49, 5.78s/it] 83%|████████▎ | 9971/11952 [1:18:55<3:09:34, 5.74s/it] {'loss': 0.4701, 'learning_rate': 1.4066691631806574e-06, 'epoch': 0.83} + 83%|████████▎ | 9971/11952 [1:18:55<3:09:34, 5.74s/it] 83%|████████▎ | 9972/11952 [1:19:01<3:15:41, 5.93s/it] {'loss': 0.4579, 'learning_rate': 1.4052835891809735e-06, 'epoch': 0.83} + 83%|████████▎ | 9972/11952 [1:19:01<3:15:41, 5.93s/it] 83%|████████▎ | 9973/11952 [1:19:07<3:14:10, 5.89s/it] {'loss': 0.4772, 'learning_rate': 1.403898646341515e-06, 'epoch': 0.83} + 83%|████████▎ | 9973/11952 [1:19:07<3:14:10, 5.89s/it] 83%|████████▎ | 9974/11952 [1:19:13<3:14:17, 5.89s/it] {'loss': 0.467, 'learning_rate': 1.4025143347639858e-06, 'epoch': 0.83} + 83%|████████▎ | 9974/11952 [1:19:13<3:14:17, 5.89s/it] 83%|████████▎ | 9975/11952 [1:19:19<3:13:49, 5.88s/it] {'loss': 0.4744, 'learning_rate': 1.4011306545500435e-06, 'epoch': 0.83} + 83%|████████▎ | 9975/11952 [1:19:19<3:13:49, 5.88s/it] 83%|████████▎ | 9976/11952 [1:19:25<3:14:16, 5.90s/it] {'loss': 0.4634, 'learning_rate': 1.3997476058013016e-06, 'epoch': 0.83} + 83%|████████▎ | 9976/11952 [1:19:25<3:14:16, 5.90s/it] 83%|████████▎ | 9977/11952 [1:19:31<3:13:35, 5.88s/it] {'loss': 0.4809, 'learning_rate': 1.398365188619324e-06, 'epoch': 0.83} + 83%|████████▎ | 9977/11952 [1:19:31<3:13:35, 5.88s/it] 83%|████████▎ | 9978/11952 [1:19:36<3:11:39, 5.83s/it] {'loss': 0.4474, 'learning_rate': 1.3969834031056273e-06, 'epoch': 0.83} + 83%|████████▎ | 9978/11952 [1:19:36<3:11:39, 5.83s/it] 83%|████████▎ | 9979/11952 [1:19:42<3:09:36, 5.77s/it] {'loss': 0.4512, 'learning_rate': 1.3956022493616895e-06, 'epoch': 0.83} + 83%|████████▎ | 9979/11952 [1:19:42<3:09:36, 5.77s/it] 84%|████████▎ | 9980/11952 [1:19:48<3:12:19, 5.85s/it] {'loss': 0.4772, 'learning_rate': 1.3942217274889325e-06, 'epoch': 0.83} + 84%|████████▎ | 9980/11952 [1:19:48<3:12:19, 5.85s/it] 84%|████████▎ | 9981/11952 [1:19:54<3:13:09, 5.88s/it] {'loss': 0.4751, 'learning_rate': 1.3928418375887388e-06, 'epoch': 0.84} + 84%|████████▎ | 9981/11952 [1:19:54<3:13:09, 5.88s/it] 84%|████████▎ | 9982/11952 [1:20:00<3:16:33, 5.99s/it] {'loss': 0.4361, 'learning_rate': 1.3914625797624415e-06, 'epoch': 0.84} + 84%|████████▎ | 9982/11952 [1:20:00<3:16:33, 5.99s/it] 84%|████████▎ | 9983/11952 [1:20:06<3:17:35, 6.02s/it] {'loss': 0.4814, 'learning_rate': 1.3900839541113265e-06, 'epoch': 0.84} + 84%|████████▎ | 9983/11952 [1:20:06<3:17:35, 6.02s/it] 84%|████████▎ | 9984/11952 [1:20:12<3:14:55, 5.94s/it] {'loss': 0.4506, 'learning_rate': 1.3887059607366338e-06, 'epoch': 0.84} + 84%|████████▎ | 9984/11952 [1:20:12<3:14:55, 5.94s/it] 84%|████████▎ | 9985/11952 [1:20:18<3:13:32, 5.90s/it] {'loss': 0.4521, 'learning_rate': 1.3873285997395569e-06, 'epoch': 0.84} + 84%|████████▎ | 9985/11952 [1:20:18<3:13:32, 5.90s/it] 84%|████████▎ | 9986/11952 [1:20:24<3:11:50, 5.85s/it] {'loss': 0.4759, 'learning_rate': 1.3859518712212473e-06, 'epoch': 0.84} + 84%|████████▎ | 9986/11952 [1:20:24<3:11:50, 5.85s/it] 84%|████████▎ | 9987/11952 [1:20:30<3:13:35, 5.91s/it] {'loss': 0.4694, 'learning_rate': 1.3845757752828037e-06, 'epoch': 0.84} + 84%|████████▎ | 9987/11952 [1:20:30<3:13:35, 5.91s/it] 84%|████████▎ | 9988/11952 [1:20:36<3:13:27, 5.91s/it] {'loss': 0.4438, 'learning_rate': 1.3832003120252801e-06, 'epoch': 0.84} + 84%|████████▎ | 9988/11952 [1:20:36<3:13:27, 5.91s/it] 84%|████████▎ | 9989/11952 [1:20:41<3:11:49, 5.86s/it] {'loss': 0.4566, 'learning_rate': 1.3818254815496846e-06, 'epoch': 0.84} + 84%|████████▎ | 9989/11952 [1:20:41<3:11:49, 5.86s/it] 84%|████████▎ | 9990/11952 [1:20:47<3:11:48, 5.87s/it] {'loss': 0.4699, 'learning_rate': 1.3804512839569805e-06, 'epoch': 0.84} + 84%|████████▎ | 9990/11952 [1:20:47<3:11:48, 5.87s/it] 84%|████████▎ | 9991/11952 [1:20:53<3:15:03, 5.97s/it] {'loss': 0.4585, 'learning_rate': 1.3790777193480842e-06, 'epoch': 0.84} + 84%|████████▎ | 9991/11952 [1:20:53<3:15:03, 5.97s/it] 84%|████████▎ | 9992/11952 [1:21:00<3:15:58, 6.00s/it] {'loss': 0.4504, 'learning_rate': 1.3777047878238603e-06, 'epoch': 0.84} + 84%|████████▎ | 9992/11952 [1:21:00<3:15:58, 6.00s/it] 84%|████████▎ | 9993/11952 [1:21:05<3:13:29, 5.93s/it] {'loss': 0.4583, 'learning_rate': 1.3763324894851371e-06, 'epoch': 0.84} + 84%|████████▎ | 9993/11952 [1:21:05<3:13:29, 5.93s/it] 84%|████████▎ | 9994/11952 [1:21:11<3:13:37, 5.93s/it] {'loss': 0.461, 'learning_rate': 1.3749608244326862e-06, 'epoch': 0.84} + 84%|████████▎ | 9994/11952 [1:21:11<3:13:37, 5.93s/it] 84%|████████▎ | 9995/11952 [1:21:17<3:12:46, 5.91s/it] {'loss': 0.4712, 'learning_rate': 1.373589792767238e-06, 'epoch': 0.84} + 84%|████████▎ | 9995/11952 [1:21:17<3:12:46, 5.91s/it] 84%|████████▎ | 9996/11952 [1:21:23<3:11:53, 5.89s/it] {'loss': 0.4688, 'learning_rate': 1.372219394589477e-06, 'epoch': 0.84} + 84%|████████▎ | 9996/11952 [1:21:23<3:11:53, 5.89s/it] 84%|████████▎ | 9997/11952 [1:21:29<3:12:17, 5.90s/it] {'loss': 0.479, 'learning_rate': 1.3708496300000363e-06, 'epoch': 0.84} + 84%|████████▎ | 9997/11952 [1:21:29<3:12:17, 5.90s/it] 84%|████████▎ | 9998/11952 [1:21:35<3:12:15, 5.90s/it] {'loss': 0.4624, 'learning_rate': 1.369480499099508e-06, 'epoch': 0.84} + 84%|████████▎ | 9998/11952 [1:21:35<3:12:15, 5.90s/it] 84%|████████▎ | 9999/11952 [1:21:41<3:12:20, 5.91s/it] {'loss': 0.4708, 'learning_rate': 1.3681120019884331e-06, 'epoch': 0.84} + 84%|████████▎ | 9999/11952 [1:21:41<3:12:20, 5.91s/it]6 AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +0 AutoResumeHook: Checking whether to suspend... + 84%|████████▎ | 10000/11952 [1:21:46<3:11:12, 5.88s/it] {'loss': 0.4821, 'learning_rate': 1.3667441387673098e-06, 'epoch': 0.84} + 84%|████████▎ | 10000/11952 [1:21:46<3:11:12, 5.88s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-10000/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-10000/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/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( + 84%|████████▎ | 10001/11952 [1:22:16<7:05:33, 13.09s/it] {'loss': 0.4553, 'learning_rate': 1.36537690953659e-06, 'epoch': 0.84} + 84%|████████▎ | 10001/11952 [1:22:16<7:05:33, 13.09s/it] 84%|████████▎ | 10002/11952 [1:22:22<5:55:57, 10.95s/it] {'loss': 0.4771, 'learning_rate': 1.3640103143966765e-06, 'epoch': 0.84} + 84%|████████▎ | 10002/11952 [1:22:22<5:55:57, 10.95s/it] 84%|████████▎ | 10003/11952 [1:22:28<5:04:00, 9.36s/it] {'loss': 0.4618, 'learning_rate': 1.3626443534479262e-06, 'epoch': 0.84} + 84%|████████▎ | 10003/11952 [1:22:28<5:04:00, 9.36s/it] 84%|████████▎ | 10004/11952 [1:22:34<4:29:29, 8.30s/it] {'loss': 0.4534, 'learning_rate': 1.3612790267906484e-06, 'epoch': 0.84} + 84%|████████▎ | 10004/11952 [1:22:34<4:29:29, 8.30s/it] 84%|████████▎ | 10005/11952 [1:22:40<4:10:35, 7.72s/it] {'loss': 0.4711, 'learning_rate': 1.3599143345251075e-06, 'epoch': 0.84} + 84%|████████▎ | 10005/11952 [1:22:40<4:10:35, 7.72s/it] 84%|████████▎ | 10006/11952 [1:22:46<3:51:07, 7.13s/it] {'loss': 0.4506, 'learning_rate': 1.35855027675152e-06, 'epoch': 0.84} + 84%|████████▎ | 10006/11952 [1:22:46<3:51:07, 7.13s/it] 84%|████████▎ | 10007/11952 [1:22:52<3:39:12, 6.76s/it] {'loss': 0.4574, 'learning_rate': 1.3571868535700595e-06, 'epoch': 0.84} + 84%|████████▎ | 10007/11952 [1:22:52<3:39:12, 6.76s/it] 84%|████████▎ | 10008/11952 [1:22:58<3:30:02, 6.48s/it] {'loss': 0.4485, 'learning_rate': 1.3558240650808473e-06, 'epoch': 0.84} + 84%|████████▎ | 10008/11952 [1:22:58<3:30:02, 6.48s/it] 84%|████████▎ | 10009/11952 [1:23:03<3:22:56, 6.27s/it] {'loss': 0.4536, 'learning_rate': 1.354461911383963e-06, 'epoch': 0.84} + 84%|████████▎ | 10009/11952 [1:23:03<3:22:56, 6.27s/it] 84%|████████▍ | 10010/11952 [1:23:09<3:19:34, 6.17s/it] {'loss': 0.467, 'learning_rate': 1.353100392579434e-06, 'epoch': 0.84} + 84%|████████▍ | 10010/11952 [1:23:09<3:19:34, 6.17s/it] 84%|████████▍ | 10011/11952 [1:23:16<3:18:59, 6.15s/it] {'loss': 0.4719, 'learning_rate': 1.351739508767249e-06, 'epoch': 0.84} + 84%|████████▍ | 10011/11952 [1:23:16<3:18:59, 6.15s/it] 84%|████████▍ | 10012/11952 [1:23:21<3:15:37, 6.05s/it] {'loss': 0.4611, 'learning_rate': 1.3503792600473408e-06, 'epoch': 0.84} + 84%|████████▍ | 10012/11952 [1:23:21<3:15:37, 6.05s/it] 84%|████████▍ | 10013/11952 [1:23:27<3:12:24, 5.95s/it] {'loss': 0.4513, 'learning_rate': 1.349019646519607e-06, 'epoch': 0.84} + 84%|████████▍ | 10013/11952 [1:23:27<3:12:24, 5.95s/it] 84%|████████▍ | 10014/11952 [1:23:33<3:09:47, 5.88s/it] {'loss': 0.4686, 'learning_rate': 1.3476606682838866e-06, 'epoch': 0.84} + 84%|████████▍ | 10014/11952 [1:23:33<3:09:47, 5.88s/it] 84%|████████▍ | 10015/11952 [1:23:38<3:08:19, 5.83s/it] {'loss': 0.4681, 'learning_rate': 1.3463023254399798e-06, 'epoch': 0.84} + 84%|████████▍ | 10015/11952 [1:23:38<3:08:19, 5.83s/it] 84%|████████▍ | 10016/11952 [1:23:44<3:08:01, 5.83s/it] {'loss': 0.4556, 'learning_rate': 1.3449446180876369e-06, 'epoch': 0.84} + 84%|████████▍ | 10016/11952 [1:23:44<3:08:01, 5.83s/it] 84%|████████▍ | 10017/11952 [1:23:50<3:09:08, 5.86s/it] {'loss': 0.4678, 'learning_rate': 1.3435875463265624e-06, 'epoch': 0.84} + 84%|████████▍ | 10017/11952 [1:23:50<3:09:08, 5.86s/it] 84%|████████▍ | 10018/11952 [1:23:56<3:08:07, 5.84s/it] {'loss': 0.4727, 'learning_rate': 1.3422311102564134e-06, 'epoch': 0.84} + 84%|████████▍ | 10018/11952 [1:23:56<3:08:07, 5.84s/it] 84%|████████▍ | 10019/11952 [1:24:02<3:07:40, 5.83s/it] {'loss': 0.4818, 'learning_rate': 1.340875309976799e-06, 'epoch': 0.84} + 84%|████████▍ | 10019/11952 [1:24:02<3:07:40, 5.83s/it] 84%|████████▍ | 10020/11952 [1:24:08<3:09:04, 5.87s/it] {'loss': 0.4737, 'learning_rate': 1.3395201455872886e-06, 'epoch': 0.84} + 84%|████████▍ | 10020/11952 [1:24:08<3:09:04, 5.87s/it] 84%|████████▍ | 10021/11952 [1:24:14<3:08:27, 5.86s/it] {'loss': 0.4683, 'learning_rate': 1.3381656171873936e-06, 'epoch': 0.84} + 84%|████████▍ | 10021/11952 [1:24:14<3:08:27, 5.86s/it] 84%|████████▍ | 10022/11952 [1:24:20<3:09:11, 5.88s/it] {'loss': 0.4708, 'learning_rate': 1.336811724876592e-06, 'epoch': 0.84} + 84%|████████▍ | 10022/11952 [1:24:20<3:09:11, 5.88s/it] 84%|████████▍ | 10023/11952 [1:24:26<3:10:12, 5.92s/it] {'loss': 0.4664, 'learning_rate': 1.3354584687543037e-06, 'epoch': 0.84} + 84%|████████▍ | 10023/11952 [1:24:26<3:10:12, 5.92s/it] 84%|████████▍ | 10024/11952 [1:24:31<3:10:00, 5.91s/it] {'loss': 0.4535, 'learning_rate': 1.3341058489199065e-06, 'epoch': 0.84} + 84%|████████▍ | 10024/11952 [1:24:31<3:10:00, 5.91s/it] 84%|████████▍ | 10025/11952 [1:24:38<3:12:01, 5.98s/it] {'loss': 0.4832, 'learning_rate': 1.3327538654727323e-06, 'epoch': 0.84} + 84%|████████▍ | 10025/11952 [1:24:38<3:12:01, 5.98s/it] 84%|████████▍ | 10026/11952 [1:24:44<3:12:30, 6.00s/it] {'loss': 0.4402, 'learning_rate': 1.3314025185120616e-06, 'epoch': 0.84} + 84%|████████▍ | 10026/11952 [1:24:44<3:12:30, 6.00s/it] 84%|████████▍ | 10027/11952 [1:24:49<3:09:34, 5.91s/it] {'loss': 0.4713, 'learning_rate': 1.3300518081371373e-06, 'epoch': 0.84} + 84%|████████▍ | 10027/11952 [1:24:49<3:09:34, 5.91s/it] 84%|████████▍ | 10028/11952 [1:24:55<3:07:19, 5.84s/it] {'loss': 0.4847, 'learning_rate': 1.3287017344471477e-06, 'epoch': 0.84} + 84%|████████▍ | 10028/11952 [1:24:55<3:07:19, 5.84s/it] 84%|████████▍ | 10029/11952 [1:25:01<3:08:39, 5.89s/it] {'loss': 0.485, 'learning_rate': 1.3273522975412344e-06, 'epoch': 0.84} + 84%|████████▍ | 10029/11952 [1:25:01<3:08:39, 5.89s/it] 84%|████████▍ | 10030/11952 [1:25:07<3:11:08, 5.97s/it] {'loss': 0.4526, 'learning_rate': 1.3260034975184955e-06, 'epoch': 0.84} + 84%|████████▍ | 10030/11952 [1:25:07<3:11:08, 5.97s/it] 84%|████████▍ | 10031/11952 [1:25:13<3:07:52, 5.87s/it] {'loss': 0.4636, 'learning_rate': 1.3246553344779834e-06, 'epoch': 0.84} + 84%|████████▍ | 10031/11952 [1:25:13<3:07:52, 5.87s/it] 84%|████████▍ | 10032/11952 [1:25:19<3:06:49, 5.84s/it] {'loss': 0.4618, 'learning_rate': 1.3233078085187002e-06, 'epoch': 0.84} + 84%|████████▍ | 10032/11952 [1:25:19<3:06:49, 5.84s/it] 84%|████████▍ | 10033/11952 [1:25:24<3:06:22, 5.83s/it] {'loss': 0.4777, 'learning_rate': 1.3219609197396e-06, 'epoch': 0.84} + 84%|████████▍ | 10033/11952 [1:25:24<3:06:22, 5.83s/it] 84%|████████▍ | 10034/11952 [1:25:30<3:07:54, 5.88s/it] {'loss': 0.4768, 'learning_rate': 1.3206146682395983e-06, 'epoch': 0.84} + 84%|████████▍ | 10034/11952 [1:25:30<3:07:54, 5.88s/it] 84%|████████▍ | 10035/11952 [1:25:36<3:06:39, 5.84s/it] {'loss': 0.469, 'learning_rate': 1.3192690541175536e-06, 'epoch': 0.84} + 84%|████████▍ | 10035/11952 [1:25:36<3:06:39, 5.84s/it] 84%|████████▍ | 10036/11952 [1:25:42<3:06:10, 5.83s/it] {'loss': 0.4677, 'learning_rate': 1.3179240774722845e-06, 'epoch': 0.84} + 84%|████████▍ | 10036/11952 [1:25:42<3:06:10, 5.83s/it] 84%|████████▍ | 10037/11952 [1:25:48<3:08:26, 5.90s/it] {'loss': 0.4521, 'learning_rate': 1.3165797384025602e-06, 'epoch': 0.84} + 84%|████████▍ | 10037/11952 [1:25:48<3:08:26, 5.90s/it] 84%|████████▍ | 10038/11952 [1:25:54<3:05:30, 5.82s/it] {'loss': 0.458, 'learning_rate': 1.3152360370071016e-06, 'epoch': 0.84} + 84%|████████▍ | 10038/11952 [1:25:54<3:05:30, 5.82s/it] 84%|████████▍ | 10039/11952 [1:26:00<3:06:42, 5.86s/it] {'loss': 0.4684, 'learning_rate': 1.3138929733845873e-06, 'epoch': 0.84} + 84%|████████▍ | 10039/11952 [1:26:00<3:06:42, 5.86s/it] 84%|████████▍ | 10040/11952 [1:26:05<3:07:03, 5.87s/it] {'loss': 0.4928, 'learning_rate': 1.3125505476336408e-06, 'epoch': 0.84} + 84%|████████▍ | 10040/11952 [1:26:05<3:07:03, 5.87s/it] 84%|████████▍ | 10041/11952 [1:26:11<3:07:37, 5.89s/it] {'loss': 0.4457, 'learning_rate': 1.31120875985285e-06, 'epoch': 0.84} + 84%|████████▍ | 10041/11952 [1:26:11<3:07:37, 5.89s/it] 84%|████████▍ | 10042/11952 [1:26:17<3:07:06, 5.88s/it] {'loss': 0.4711, 'learning_rate': 1.3098676101407493e-06, 'epoch': 0.84} + 84%|████████▍ | 10042/11952 [1:26:17<3:07:06, 5.88s/it] 84%|████████▍ | 10043/11952 [1:26:23<3:04:21, 5.79s/it] {'loss': 0.4534, 'learning_rate': 1.3085270985958276e-06, 'epoch': 0.84} + 84%|████████▍ | 10043/11952 [1:26:23<3:04:21, 5.79s/it] 84%|████████▍ | 10044/11952 [1:26:29<3:08:28, 5.93s/it] {'loss': 0.4645, 'learning_rate': 1.307187225316524e-06, 'epoch': 0.84} + 84%|████████▍ | 10044/11952 [1:26:29<3:08:28, 5.93s/it] 84%|████████▍ | 10045/11952 [1:26:35<3:09:07, 5.95s/it] {'loss': 0.4482, 'learning_rate': 1.3058479904012356e-06, 'epoch': 0.84} + 84%|████████▍ | 10045/11952 [1:26:35<3:09:07, 5.95s/it] 84%|████████▍ | 10046/11952 [1:26:41<3:10:30, 6.00s/it] {'loss': 0.4551, 'learning_rate': 1.3045093939483066e-06, 'epoch': 0.84} + 84%|████████▍ | 10046/11952 [1:26:41<3:10:30, 6.00s/it] 84%|████████▍ | 10047/11952 [1:26:47<3:10:18, 5.99s/it] {'loss': 0.4767, 'learning_rate': 1.303171436056042e-06, 'epoch': 0.84} + 84%|████████▍ | 10047/11952 [1:26:47<3:10:18, 5.99s/it] 84%|████████▍ | 10048/11952 [1:26:53<3:08:30, 5.94s/it] {'loss': 0.4526, 'learning_rate': 1.3018341168226944e-06, 'epoch': 0.84} + 84%|████████▍ | 10048/11952 [1:26:53<3:08:30, 5.94s/it] 84%|████████▍ | 10049/11952 [1:26:59<3:05:58, 5.86s/it] {'loss': 0.4568, 'learning_rate': 1.3004974363464717e-06, 'epoch': 0.84} + 84%|████████▍ | 10049/11952 [1:26:59<3:05:58, 5.86s/it]5 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +0 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... + 84%|████████▍ | 10050/11952 [1:27:05<3:05:30, 5.85s/it] {'loss': 0.4566, 'learning_rate': 1.2991613947255321e-06, 'epoch': 0.84} + 84%|████████▍ | 10050/11952 [1:27:05<3:05:30, 5.85s/it] 84%|████████▍ | 10051/11952 [1:27:10<3:04:25, 5.82s/it] {'loss': 0.4475, 'learning_rate': 1.2978259920579895e-06, 'epoch': 0.84} + 84%|████████▍ | 10051/11952 [1:27:10<3:04:25, 5.82s/it] 84%|████████▍ | 10052/11952 [1:27:16<3:05:02, 5.84s/it] {'loss': 0.4601, 'learning_rate': 1.2964912284419119e-06, 'epoch': 0.84} + 84%|████████▍ | 10052/11952 [1:27:16<3:05:02, 5.84s/it] 84%|████████▍ | 10053/11952 [1:27:22<3:04:35, 5.83s/it] {'loss': 0.4661, 'learning_rate': 1.2951571039753163e-06, 'epoch': 0.84} + 84%|████████▍ | 10053/11952 [1:27:22<3:04:35, 5.83s/it] 84%|████████▍ | 10054/11952 [1:27:28<3:04:33, 5.83s/it] {'loss': 0.4581, 'learning_rate': 1.2938236187561782e-06, 'epoch': 0.84} + 84%|████████▍ | 10054/11952 [1:27:28<3:04:33, 5.83s/it] 84%|████████▍ | 10055/11952 [1:27:34<3:09:04, 5.98s/it] {'loss': 0.4995, 'learning_rate': 1.292490772882422e-06, 'epoch': 0.84} + 84%|████████▍ | 10055/11952 [1:27:34<3:09:04, 5.98s/it] 84%|████████▍ | 10056/11952 [1:27:40<3:07:21, 5.93s/it] {'loss': 0.4664, 'learning_rate': 1.2911585664519267e-06, 'epoch': 0.84} + 84%|████████▍ | 10056/11952 [1:27:40<3:07:21, 5.93s/it] 84%|████████▍ | 10057/11952 [1:27:46<3:06:06, 5.89s/it] {'loss': 0.4653, 'learning_rate': 1.2898269995625234e-06, 'epoch': 0.84} + 84%|████████▍ | 10057/11952 [1:27:46<3:06:06, 5.89s/it] 84%|████████▍ | 10058/11952 [1:27:52<3:05:12, 5.87s/it] {'loss': 0.4812, 'learning_rate': 1.2884960723119978e-06, 'epoch': 0.84} + 84%|████████▍ | 10058/11952 [1:27:52<3:05:12, 5.87s/it] 84%|████████▍ | 10059/11952 [1:27:58<3:07:33, 5.94s/it] {'loss': 0.4597, 'learning_rate': 1.2871657847980856e-06, 'epoch': 0.84} + 84%|████████▍ | 10059/11952 [1:27:58<3:07:33, 5.94s/it] 84%|████████▍ | 10060/11952 [1:28:04<3:09:21, 6.00s/it] {'loss': 0.4648, 'learning_rate': 1.285836137118477e-06, 'epoch': 0.84} + 84%|████████▍ | 10060/11952 [1:28:04<3:09:21, 6.00s/it] 84%|████████▍ | 10061/11952 [1:28:10<3:08:03, 5.97s/it] {'loss': 0.4471, 'learning_rate': 1.2845071293708188e-06, 'epoch': 0.84} + 84%|████████▍ | 10061/11952 [1:28:10<3:08:03, 5.97s/it] 84%|████████▍ | 10062/11952 [1:28:16<3:07:46, 5.96s/it] {'loss': 0.4796, 'learning_rate': 1.2831787616527058e-06, 'epoch': 0.84} + 84%|████████▍ | 10062/11952 [1:28:16<3:07:46, 5.96s/it] 84%|████████▍ | 10063/11952 [1:28:22<3:11:05, 6.07s/it] {'loss': 0.4558, 'learning_rate': 1.2818510340616896e-06, 'epoch': 0.84} + 84%|████████▍ | 10063/11952 [1:28:22<3:11:05, 6.07s/it] 84%|████████▍ | 10064/11952 [1:28:28<3:10:56, 6.07s/it] {'loss': 0.4706, 'learning_rate': 1.2805239466952723e-06, 'epoch': 0.84} + 84%|████████▍ | 10064/11952 [1:28:28<3:10:56, 6.07s/it] 84%|████████▍ | 10065/11952 [1:28:34<3:10:37, 6.06s/it] {'loss': 0.4646, 'learning_rate': 1.2791974996509094e-06, 'epoch': 0.84} + 84%|████████▍ | 10065/11952 [1:28:34<3:10:37, 6.06s/it] 84%|████████▍ | 10066/11952 [1:28:40<3:09:39, 6.03s/it] {'loss': 0.4734, 'learning_rate': 1.2778716930260105e-06, 'epoch': 0.84} + 84%|████████▍ | 10066/11952 [1:28:40<3:09:39, 6.03s/it] 84%|████████▍ | 10067/11952 [1:28:46<3:12:17, 6.12s/it] {'loss': 0.4534, 'learning_rate': 1.2765465269179334e-06, 'epoch': 0.84} + 84%|████████▍ | 10067/11952 [1:28:46<3:12:17, 6.12s/it] 84%|████████▍ | 10068/11952 [1:28:52<3:07:57, 5.99s/it] {'loss': 0.4768, 'learning_rate': 1.275222001423998e-06, 'epoch': 0.84} + 84%|████████▍ | 10068/11952 [1:28:52<3:07:57, 5.99s/it] 84%|████████▍ | 10069/11952 [1:28:58<3:05:39, 5.92s/it] {'loss': 0.467, 'learning_rate': 1.2738981166414688e-06, 'epoch': 0.84} + 84%|████████▍ | 10069/11952 [1:28:58<3:05:39, 5.92s/it] 84%|████████▍ | 10070/11952 [1:29:04<3:08:12, 6.00s/it] {'loss': 0.4768, 'learning_rate': 1.2725748726675691e-06, 'epoch': 0.84} + 84%|████████▍ | 10070/11952 [1:29:04<3:08:12, 6.00s/it] 84%|████████▍ | 10071/11952 [1:29:10<3:05:38, 5.92s/it] {'loss': 0.4946, 'learning_rate': 1.2712522695994666e-06, 'epoch': 0.84} + 84%|████████▍ | 10071/11952 [1:29:10<3:05:38, 5.92s/it] 84%|████████▍ | 10072/11952 [1:29:16<3:07:13, 5.98s/it] {'loss': 0.4539, 'learning_rate': 1.269930307534295e-06, 'epoch': 0.84} + 84%|████████▍ | 10072/11952 [1:29:16<3:07:13, 5.98s/it] 84%|████████▍ | 10073/11952 [1:29:22<3:10:27, 6.08s/it] {'loss': 0.4647, 'learning_rate': 1.268608986569131e-06, 'epoch': 0.84} + 84%|████████▍ | 10073/11952 [1:29:22<3:10:27, 6.08s/it] 84%|████████▍ | 10074/11952 [1:29:28<3:08:06, 6.01s/it] {'loss': 0.4726, 'learning_rate': 1.2672883068010033e-06, 'epoch': 0.84} + 84%|████████▍ | 10074/11952 [1:29:28<3:08:06, 6.01s/it] 84%|████████▍ | 10075/11952 [1:29:34<3:09:20, 6.05s/it] {'loss': 0.4771, 'learning_rate': 1.2659682683269036e-06, 'epoch': 0.84} + 84%|████████▍ | 10075/11952 [1:29:34<3:09:20, 6.05s/it] 84%|████████▍ | 10076/11952 [1:29:40<3:06:04, 5.95s/it] {'loss': 0.4556, 'learning_rate': 1.2646488712437654e-06, 'epoch': 0.84} + 84%|████████▍ | 10076/11952 [1:29:40<3:06:04, 5.95s/it] 84%|████████▍ | 10077/11952 [1:29:46<3:06:21, 5.96s/it] {'loss': 0.4647, 'learning_rate': 1.2633301156484822e-06, 'epoch': 0.84} + 84%|████████▍ | 10077/11952 [1:29:46<3:06:21, 5.96s/it] 84%|████████▍ | 10078/11952 [1:29:51<3:03:04, 5.86s/it] {'loss': 0.4549, 'learning_rate': 1.2620120016378956e-06, 'epoch': 0.84} + 84%|████████▍ | 10078/11952 [1:29:51<3:03:04, 5.86s/it] 84%|████████▍ | 10079/11952 [1:29:57<3:02:47, 5.86s/it] {'loss': 0.4467, 'learning_rate': 1.2606945293088047e-06, 'epoch': 0.84} + 84%|████████▍ | 10079/11952 [1:29:57<3:02:47, 5.86s/it] 84%|████████▍ | 10080/11952 [1:30:03<3:01:31, 5.82s/it] {'loss': 0.4639, 'learning_rate': 1.2593776987579576e-06, 'epoch': 0.84} + 84%|████████▍ | 10080/11952 [1:30:03<3:01:31, 5.82s/it] 84%|████████▍ | 10081/11952 [1:30:09<3:02:49, 5.86s/it] {'loss': 0.4664, 'learning_rate': 1.2580615100820548e-06, 'epoch': 0.84} + 84%|████████▍ | 10081/11952 [1:30:09<3:02:49, 5.86s/it] 84%|████████▍ | 10082/11952 [1:30:15<3:08:03, 6.03s/it] {'loss': 0.4634, 'learning_rate': 1.2567459633777567e-06, 'epoch': 0.84} + 84%|████████▍ | 10082/11952 [1:30:15<3:08:03, 6.03s/it] 84%|████████▍ | 10083/11952 [1:30:21<3:05:48, 5.96s/it] {'loss': 0.4713, 'learning_rate': 1.2554310587416674e-06, 'epoch': 0.84} + 84%|████████▍ | 10083/11952 [1:30:21<3:05:48, 5.96s/it] 84%|████████▍ | 10084/11952 [1:30:27<3:07:19, 6.02s/it] {'loss': 0.4783, 'learning_rate': 1.2541167962703515e-06, 'epoch': 0.84} + 84%|████████▍ | 10084/11952 [1:30:27<3:07:19, 6.02s/it] 84%|████████▍ | 10085/11952 [1:30:33<3:05:52, 5.97s/it] {'loss': 0.4557, 'learning_rate': 1.252803176060321e-06, 'epoch': 0.84} + 84%|████████▍ | 10085/11952 [1:30:33<3:05:52, 5.97s/it] 84%|████████▍ | 10086/11952 [1:30:39<3:03:14, 5.89s/it] {'loss': 0.4748, 'learning_rate': 1.251490198208043e-06, 'epoch': 0.84} + 84%|████████▍ | 10086/11952 [1:30:39<3:03:14, 5.89s/it] 84%|████████▍ | 10087/11952 [1:30:45<3:04:55, 5.95s/it] {'loss': 0.4805, 'learning_rate': 1.2501778628099349e-06, 'epoch': 0.84} + 84%|████████▍ | 10087/11952 [1:30:45<3:04:55, 5.95s/it] 84%|████████▍ | 10088/11952 [1:30:51<3:03:33, 5.91s/it] {'loss': 0.4657, 'learning_rate': 1.2488661699623739e-06, 'epoch': 0.84} + 84%|████████▍ | 10088/11952 [1:30:51<3:03:33, 5.91s/it] 84%|████████▍ | 10089/11952 [1:30:57<3:02:43, 5.88s/it] {'loss': 0.4644, 'learning_rate': 1.247555119761682e-06, 'epoch': 0.84} + 84%|████████▍ | 10089/11952 [1:30:57<3:02:43, 5.88s/it] 84%|████████▍ | 10090/11952 [1:31:03<3:04:12, 5.94s/it] {'loss': 0.464, 'learning_rate': 1.2462447123041388e-06, 'epoch': 0.84} + 84%|████████▍ | 10090/11952 [1:31:03<3:04:12, 5.94s/it] 84%|████████▍ | 10091/11952 [1:31:09<3:04:30, 5.95s/it] {'loss': 0.4735, 'learning_rate': 1.244934947685974e-06, 'epoch': 0.84} + 84%|████████▍ | 10091/11952 [1:31:09<3:04:30, 5.95s/it] 84%|████████▍ | 10092/11952 [1:31:14<3:02:41, 5.89s/it] {'loss': 0.4721, 'learning_rate': 1.2436258260033696e-06, 'epoch': 0.84} + 84%|████████▍ | 10092/11952 [1:31:14<3:02:41, 5.89s/it] 84%|████████▍ | 10093/11952 [1:31:20<3:00:13, 5.82s/it] {'loss': 0.4823, 'learning_rate': 1.2423173473524653e-06, 'epoch': 0.84} + 84%|████████▍ | 10093/11952 [1:31:20<3:00:13, 5.82s/it] 84%|████████▍ | 10094/11952 [1:31:26<3:02:19, 5.89s/it] {'loss': 0.4499, 'learning_rate': 1.2410095118293475e-06, 'epoch': 0.84} + 84%|████████▍ | 10094/11952 [1:31:26<3:02:19, 5.89s/it] 84%|████████▍ | 10095/11952 [1:31:32<3:04:22, 5.96s/it] {'loss': 0.4769, 'learning_rate': 1.2397023195300618e-06, 'epoch': 0.84} + 84%|████████▍ | 10095/11952 [1:31:32<3:04:22, 5.96s/it] 84%|████████▍ | 10096/11952 [1:31:38<3:01:27, 5.87s/it] {'loss': 0.4584, 'learning_rate': 1.238395770550601e-06, 'epoch': 0.84} + 84%|████████▍ | 10096/11952 [1:31:38<3:01:27, 5.87s/it] 84%|████████▍ | 10097/11952 [1:31:44<3:04:12, 5.96s/it] {'loss': 0.4785, 'learning_rate': 1.2370898649869122e-06, 'epoch': 0.84} + 84%|████████▍ | 10097/11952 [1:31:44<3:04:12, 5.96s/it] 84%|████████▍ | 10098/11952 [1:31:50<3:06:18, 6.03s/it] {'loss': 0.461, 'learning_rate': 1.2357846029348975e-06, 'epoch': 0.84} + 84%|████████▍ | 10098/11952 [1:31:50<3:06:18, 6.03s/it] 84%|████████▍ | 10099/11952 [1:31:56<3:05:17, 6.00s/it] {'loss': 0.4563, 'learning_rate': 1.2344799844904065e-06, 'epoch': 0.84} + 84%|████████▍ | 10099/11952 [1:31:56<3:05:17, 6.00s/it]2 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... +17 AutoResumeHook: Checking whether to suspend...AutoResumeHook: Checking whether to suspend... + +0 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... + 85%|████████▍ | 10100/11952 [1:32:02<3:06:37, 6.05s/it] {'loss': 0.4628, 'learning_rate': 1.2331760097492485e-06, 'epoch': 0.85} + 85%|████████▍ | 10100/11952 [1:32:02<3:06:37, 6.05s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-10100/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-10100/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/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( + 85%|████████▍ | 10101/11952 [1:32:34<6:59:33, 13.60s/it] {'loss': 0.4704, 'learning_rate': 1.2318726788071767e-06, 'epoch': 0.85} + 85%|████████▍ | 10101/11952 [1:32:34<6:59:33, 13.60s/it] 85%|████████▍ | 10102/11952 [1:32:40<5:48:31, 11.30s/it] {'loss': 0.473, 'learning_rate': 1.230569991759909e-06, 'epoch': 0.85} + 85%|████████▍ | 10102/11952 [1:32:40<5:48:31, 11.30s/it] 85%|████████▍ | 10103/11952 [1:32:45<4:56:33, 9.62s/it] {'loss': 0.4632, 'learning_rate': 1.2292679487031045e-06, 'epoch': 0.85} + 85%|████████▍ | 10103/11952 [1:32:45<4:56:33, 9.62s/it] 85%|████████▍ | 10104/11952 [1:32:51<4:22:50, 8.53s/it] {'loss': 0.4495, 'learning_rate': 1.2279665497323835e-06, 'epoch': 0.85} + 85%|████████▍ | 10104/11952 [1:32:51<4:22:50, 8.53s/it] 85%|████████▍ | 10105/11952 [1:32:58<4:01:33, 7.85s/it] {'loss': 0.4662, 'learning_rate': 1.2266657949433135e-06, 'epoch': 0.85} + 85%|████████▍ | 10105/11952 [1:32:58<4:01:33, 7.85s/it] 85%|████████▍ | 10106/11952 [1:33:03<3:42:28, 7.23s/it] {'loss': 0.4628, 'learning_rate': 1.2253656844314155e-06, 'epoch': 0.85} + 85%|████████▍ | 10106/11952 [1:33:03<3:42:28, 7.23s/it] 85%|████████▍ | 10107/11952 [1:33:09<3:29:55, 6.83s/it] {'loss': 0.4859, 'learning_rate': 1.224066218292167e-06, 'epoch': 0.85} + 85%|████████▍ | 10107/11952 [1:33:09<3:29:55, 6.83s/it] 85%|████████▍ | 10108/11952 [1:33:16<3:28:11, 6.77s/it] {'loss': 0.4671, 'learning_rate': 1.2227673966209896e-06, 'epoch': 0.85} + 85%|████████▍ | 10108/11952 [1:33:16<3:28:11, 6.77s/it] 85%|████████▍ | 10109/11952 [1:33:22<3:19:05, 6.48s/it] {'loss': 0.4454, 'learning_rate': 1.2214692195132705e-06, 'epoch': 0.85} + 85%|████████▍ | 10109/11952 [1:33:22<3:19:05, 6.48s/it] 85%|████████▍ | 10110/11952 [1:33:28<3:16:33, 6.40s/it] {'loss': 0.458, 'learning_rate': 1.2201716870643388e-06, 'epoch': 0.85} + 85%|████████▍ | 10110/11952 [1:33:28<3:16:33, 6.40s/it] 85%|████████▍ | 10111/11952 [1:33:33<3:09:16, 6.17s/it] {'loss': 0.452, 'learning_rate': 1.2188747993694805e-06, 'epoch': 0.85} + 85%|████████▍ | 10111/11952 [1:33:33<3:09:16, 6.17s/it] 85%|████████▍ | 10112/11952 [1:33:39<3:06:51, 6.09s/it] {'loss': 0.4621, 'learning_rate': 1.217578556523934e-06, 'epoch': 0.85} + 85%|████████▍ | 10112/11952 [1:33:39<3:06:51, 6.09s/it] 85%|████████▍ | 10113/11952 [1:33:45<3:03:37, 5.99s/it] {'loss': 0.4471, 'learning_rate': 1.2162829586228874e-06, 'epoch': 0.85} + 85%|████████▍ | 10113/11952 [1:33:45<3:03:37, 5.99s/it] 85%|████████▍ | 10114/11952 [1:33:51<3:01:55, 5.94s/it] {'loss': 0.4653, 'learning_rate': 1.214988005761487e-06, 'epoch': 0.85} + 85%|████████▍ | 10114/11952 [1:33:51<3:01:55, 5.94s/it] 85%|████████▍ | 10115/11952 [1:33:57<3:00:19, 5.89s/it] {'loss': 0.4649, 'learning_rate': 1.2136936980348267e-06, 'epoch': 0.85} + 85%|████████▍ | 10115/11952 [1:33:57<3:00:19, 5.89s/it] 85%|████████▍ | 10116/11952 [1:34:03<2:59:53, 5.88s/it] {'loss': 0.4577, 'learning_rate': 1.2124000355379583e-06, 'epoch': 0.85} + 85%|████████▍ | 10116/11952 [1:34:03<2:59:53, 5.88s/it] 85%|████████▍ | 10117/11952 [1:34:09<3:00:10, 5.89s/it] {'loss': 0.4553, 'learning_rate': 1.21110701836588e-06, 'epoch': 0.85} + 85%|████████▍ | 10117/11952 [1:34:09<3:00:10, 5.89s/it] 85%|████████▍ | 10118/11952 [1:34:14<3:00:38, 5.91s/it] {'loss': 0.4912, 'learning_rate': 1.2098146466135475e-06, 'epoch': 0.85} + 85%|████████▍ | 10118/11952 [1:34:14<3:00:38, 5.91s/it] 85%|████████▍ | 10119/11952 [1:34:20<3:01:20, 5.94s/it] {'loss': 0.4616, 'learning_rate': 1.2085229203758663e-06, 'epoch': 0.85} + 85%|████████▍ | 10119/11952 [1:34:20<3:01:20, 5.94s/it] 85%|████████▍ | 10120/11952 [1:34:26<2:59:28, 5.88s/it] {'loss': 0.4577, 'learning_rate': 1.2072318397476945e-06, 'epoch': 0.85} + 85%|████████▍ | 10120/11952 [1:34:26<2:59:28, 5.88s/it] 85%|████████▍ | 10121/11952 [1:34:32<2:59:46, 5.89s/it] {'loss': 0.4583, 'learning_rate': 1.2059414048238437e-06, 'epoch': 0.85} + 85%|████████▍ | 10121/11952 [1:34:32<2:59:46, 5.89s/it] 85%|████████▍ | 10122/11952 [1:34:38<2:59:11, 5.88s/it] {'loss': 0.4592, 'learning_rate': 1.2046516156990796e-06, 'epoch': 0.85} + 85%|████████▍ | 10122/11952 [1:34:38<2:59:11, 5.88s/it] 85%|████████▍ | 10123/11952 [1:34:44<2:58:25, 5.85s/it] {'loss': 0.468, 'learning_rate': 1.2033624724681191e-06, 'epoch': 0.85} + 85%|████████▍ | 10123/11952 [1:34:44<2:58:25, 5.85s/it] 85%|████████▍ | 10124/11952 [1:34:49<2:56:38, 5.80s/it] {'loss': 0.4817, 'learning_rate': 1.2020739752256282e-06, 'epoch': 0.85} + 85%|████████▍ | 10124/11952 [1:34:49<2:56:38, 5.80s/it] 85%|████████▍ | 10125/11952 [1:34:55<2:57:29, 5.83s/it] {'loss': 0.4542, 'learning_rate': 1.2007861240662334e-06, 'epoch': 0.85} + 85%|████████▍ | 10125/11952 [1:34:55<2:57:29, 5.83s/it] 85%|████████▍ | 10126/11952 [1:35:01<2:57:20, 5.83s/it] {'loss': 0.4465, 'learning_rate': 1.1994989190845075e-06, 'epoch': 0.85} + 85%|████████▍ | 10126/11952 [1:35:01<2:57:20, 5.83s/it] 85%|████████▍ | 10127/11952 [1:35:07<2:55:23, 5.77s/it] {'loss': 0.455, 'learning_rate': 1.1982123603749762e-06, 'epoch': 0.85} + 85%|████████▍ | 10127/11952 [1:35:07<2:55:23, 5.77s/it] 85%|████████▍ | 10128/11952 [1:35:13<2:56:34, 5.81s/it] {'loss': 0.465, 'learning_rate': 1.1969264480321175e-06, 'epoch': 0.85} + 85%|████████▍ | 10128/11952 [1:35:13<2:56:34, 5.81s/it] 85%|████████▍ | 10129/11952 [1:35:19<2:57:42, 5.85s/it] {'loss': 0.462, 'learning_rate': 1.1956411821503688e-06, 'epoch': 0.85} + 85%|████████▍ | 10129/11952 [1:35:19<2:57:42, 5.85s/it] 85%|████████▍ | 10130/11952 [1:35:24<2:57:05, 5.83s/it] {'loss': 0.4554, 'learning_rate': 1.1943565628241105e-06, 'epoch': 0.85} + 85%|████████▍ | 10130/11952 [1:35:24<2:57:05, 5.83s/it] 85%|████████▍ | 10131/11952 [1:35:30<2:56:31, 5.82s/it] {'loss': 0.4542, 'learning_rate': 1.1930725901476814e-06, 'epoch': 0.85} + 85%|████████▍ | 10131/11952 [1:35:30<2:56:31, 5.82s/it] 85%|████████▍ | 10132/11952 [1:35:36<2:57:31, 5.85s/it] {'loss': 0.469, 'learning_rate': 1.1917892642153706e-06, 'epoch': 0.85} + 85%|████████▍ | 10132/11952 [1:35:36<2:57:31, 5.85s/it] 85%|████████▍ | 10133/11952 [1:35:42<3:00:01, 5.94s/it] {'loss': 0.4819, 'learning_rate': 1.190506585121418e-06, 'epoch': 0.85} + 85%|████████▍ | 10133/11952 [1:35:42<3:00:01, 5.94s/it] 85%|████████▍ | 10134/11952 [1:35:48<2:58:02, 5.88s/it] {'loss': 0.4757, 'learning_rate': 1.1892245529600222e-06, 'epoch': 0.85} + 85%|████████▍ | 10134/11952 [1:35:48<2:58:02, 5.88s/it] 85%|████████▍ | 10135/11952 [1:35:54<2:56:18, 5.82s/it] {'loss': 0.4704, 'learning_rate': 1.1879431678253261e-06, 'epoch': 0.85} + 85%|████████▍ | 10135/11952 [1:35:54<2:56:18, 5.82s/it] 85%|████████▍ | 10136/11952 [1:36:00<2:57:37, 5.87s/it] {'loss': 0.459, 'learning_rate': 1.1866624298114338e-06, 'epoch': 0.85} + 85%|████████▍ | 10136/11952 [1:36:00<2:57:37, 5.87s/it] 85%|████████▍ | 10137/11952 [1:36:06<2:58:38, 5.91s/it] {'loss': 0.4646, 'learning_rate': 1.1853823390123964e-06, 'epoch': 0.85} + 85%|████████▍ | 10137/11952 [1:36:06<2:58:38, 5.91s/it] 85%|████████▍ | 10138/11952 [1:36:12<2:57:44, 5.88s/it] {'loss': 0.4662, 'learning_rate': 1.1841028955222155e-06, 'epoch': 0.85} + 85%|████████▍ | 10138/11952 [1:36:12<2:57:44, 5.88s/it] 85%|████████▍ | 10139/11952 [1:36:18<2:59:44, 5.95s/it] {'loss': 0.4671, 'learning_rate': 1.1828240994348517e-06, 'epoch': 0.85} + 85%|████████▍ | 10139/11952 [1:36:18<2:59:44, 5.95s/it] 85%|████████▍ | 10140/11952 [1:36:23<2:58:50, 5.92s/it] {'loss': 0.4511, 'learning_rate': 1.1815459508442118e-06, 'epoch': 0.85} + 85%|████████▍ | 10140/11952 [1:36:23<2:58:50, 5.92s/it] 85%|████████▍ | 10141/11952 [1:36:30<3:00:32, 5.98s/it] {'loss': 0.4797, 'learning_rate': 1.1802684498441585e-06, 'epoch': 0.85} + 85%|████████▍ | 10141/11952 [1:36:30<3:00:32, 5.98s/it] 85%|████████▍ | 10142/11952 [1:36:35<2:58:13, 5.91s/it] {'loss': 0.4553, 'learning_rate': 1.1789915965285037e-06, 'epoch': 0.85} + 85%|████████▍ | 10142/11952 [1:36:35<2:58:13, 5.91s/it] 85%|████████▍ | 10143/11952 [1:36:42<3:00:32, 5.99s/it] {'loss': 0.4775, 'learning_rate': 1.177715390991019e-06, 'epoch': 0.85} + 85%|████████▍ | 10143/11952 [1:36:42<3:00:32, 5.99s/it] 85%|████████▍ | 10144/11952 [1:36:47<2:58:20, 5.92s/it] {'loss': 0.4567, 'learning_rate': 1.1764398333254202e-06, 'epoch': 0.85} + 85%|████████▍ | 10144/11952 [1:36:47<2:58:20, 5.92s/it] 85%|████████▍ | 10145/11952 [1:36:53<2:58:25, 5.92s/it] {'loss': 0.4767, 'learning_rate': 1.1751649236253815e-06, 'epoch': 0.85} + 85%|████████▍ | 10145/11952 [1:36:53<2:58:25, 5.92s/it] 85%|████████▍ | 10146/11952 [1:36:59<3:01:03, 6.02s/it] {'loss': 0.4722, 'learning_rate': 1.1738906619845248e-06, 'epoch': 0.85} + 85%|████████▍ | 10146/11952 [1:36:59<3:01:03, 6.02s/it] 85%|████████▍ | 10147/11952 [1:37:06<3:01:55, 6.05s/it] {'loss': 0.4849, 'learning_rate': 1.1726170484964282e-06, 'epoch': 0.85} + 85%|████████▍ | 10147/11952 [1:37:06<3:01:55, 6.05s/it] 85%|████████▍ | 10148/11952 [1:37:11<2:58:56, 5.95s/it] {'loss': 0.4432, 'learning_rate': 1.1713440832546196e-06, 'epoch': 0.85} + 85%|████████▍ | 10148/11952 [1:37:11<2:58:56, 5.95s/it] 85%|████████▍ | 10149/11952 [1:37:17<2:58:33, 5.94s/it] {'loss': 0.4562, 'learning_rate': 1.1700717663525784e-06, 'epoch': 0.85} + 85%|████████▍ | 10149/11952 [1:37:17<2:58:33, 5.94s/it]7 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +0 AutoResumeHook: Checking whether to suspend... + 85%|████████▍ | 10150/11952 [1:37:23<2:58:09, 5.93s/it] {'loss': 0.478, 'learning_rate': 1.1688000978837423e-06, 'epoch': 0.85} + 85%|████████▍ | 10150/11952 [1:37:23<2:58:09, 5.93s/it] 85%|████████▍ | 10151/11952 [1:37:29<2:56:44, 5.89s/it] {'loss': 0.4653, 'learning_rate': 1.1675290779414949e-06, 'epoch': 0.85} + 85%|████████▍ | 10151/11952 [1:37:29<2:56:44, 5.89s/it] 85%|████████▍ | 10152/11952 [1:37:35<2:56:35, 5.89s/it] {'loss': 0.4584, 'learning_rate': 1.1662587066191755e-06, 'epoch': 0.85} + 85%|████████▍ | 10152/11952 [1:37:35<2:56:35, 5.89s/it] 85%|████████▍ | 10153/11952 [1:37:41<2:56:42, 5.89s/it] {'loss': 0.4666, 'learning_rate': 1.1649889840100737e-06, 'epoch': 0.85} + 85%|████████▍ | 10153/11952 [1:37:41<2:56:42, 5.89s/it] 85%|████████▍ | 10154/11952 [1:37:46<2:53:29, 5.79s/it] {'loss': 0.4629, 'learning_rate': 1.1637199102074326e-06, 'epoch': 0.85} + 85%|████████▍ | 10154/11952 [1:37:46<2:53:29, 5.79s/it] 85%|████████▍ | 10155/11952 [1:37:52<2:56:17, 5.89s/it] {'loss': 0.4594, 'learning_rate': 1.1624514853044488e-06, 'epoch': 0.85} + 85%|████████▍ | 10155/11952 [1:37:52<2:56:17, 5.89s/it] 85%|████████▍ | 10156/11952 [1:37:58<2:54:36, 5.83s/it] {'loss': 0.4912, 'learning_rate': 1.1611837093942691e-06, 'epoch': 0.85} + 85%|████████▍ | 10156/11952 [1:37:58<2:54:36, 5.83s/it] 85%|████████▍ | 10157/11952 [1:38:04<2:57:01, 5.92s/it] {'loss': 0.4794, 'learning_rate': 1.1599165825699955e-06, 'epoch': 0.85} + 85%|████████▍ | 10157/11952 [1:38:04<2:57:01, 5.92s/it] 85%|████████▍ | 10158/11952 [1:38:10<2:55:02, 5.85s/it] {'loss': 0.4589, 'learning_rate': 1.1586501049246801e-06, 'epoch': 0.85} + 85%|████████▍ | 10158/11952 [1:38:10<2:55:02, 5.85s/it] 85%|████████▍ | 10159/11952 [1:38:16<2:54:02, 5.82s/it] {'loss': 0.4812, 'learning_rate': 1.1573842765513266e-06, 'epoch': 0.85} + 85%|████████▍ | 10159/11952 [1:38:16<2:54:02, 5.82s/it] 85%|████████▌ | 10160/11952 [1:38:22<2:55:10, 5.87s/it] {'loss': 0.4629, 'learning_rate': 1.1561190975428926e-06, 'epoch': 0.85} + 85%|████████▌ | 10160/11952 [1:38:22<2:55:10, 5.87s/it] 85%|████████▌ | 10161/11952 [1:38:27<2:55:05, 5.87s/it] {'loss': 0.4512, 'learning_rate': 1.1548545679922885e-06, 'epoch': 0.85} + 85%|████████▌ | 10161/11952 [1:38:27<2:55:05, 5.87s/it] 85%|████████▌ | 10162/11952 [1:38:33<2:52:30, 5.78s/it] {'loss': 0.4553, 'learning_rate': 1.153590687992372e-06, 'epoch': 0.85} + 85%|████████▌ | 10162/11952 [1:38:33<2:52:30, 5.78s/it] 85%|████████▌ | 10163/11952 [1:38:39<2:52:50, 5.80s/it] {'loss': 0.4647, 'learning_rate': 1.1523274576359633e-06, 'epoch': 0.85} + 85%|████████▌ | 10163/11952 [1:38:39<2:52:50, 5.80s/it] 85%|████████▌ | 10164/11952 [1:38:45<2:52:07, 5.78s/it] {'loss': 0.4667, 'learning_rate': 1.151064877015825e-06, 'epoch': 0.85} + 85%|████████▌ | 10164/11952 [1:38:45<2:52:07, 5.78s/it] 85%|████████▌ | 10165/11952 [1:38:51<2:53:46, 5.83s/it] {'loss': 0.4664, 'learning_rate': 1.1498029462246752e-06, 'epoch': 0.85} + 85%|████████▌ | 10165/11952 [1:38:51<2:53:46, 5.83s/it] 85%|████████▌ | 10166/11952 [1:38:57<2:54:40, 5.87s/it] {'loss': 0.459, 'learning_rate': 1.1485416653551884e-06, 'epoch': 0.85} + 85%|████████▌ | 10166/11952 [1:38:57<2:54:40, 5.87s/it] 85%|████████▌ | 10167/11952 [1:39:02<2:53:03, 5.82s/it] {'loss': 0.4335, 'learning_rate': 1.1472810344999852e-06, 'epoch': 0.85} + 85%|████████▌ | 10167/11952 [1:39:02<2:53:03, 5.82s/it] 85%|████████▌ | 10168/11952 [1:39:09<2:58:31, 6.00s/it] {'loss': 0.4746, 'learning_rate': 1.1460210537516426e-06, 'epoch': 0.85} + 85%|████████▌ | 10168/11952 [1:39:09<2:58:31, 6.00s/it] 85%|████████▌ | 10169/11952 [1:39:15<2:58:49, 6.02s/it] {'loss': 0.4671, 'learning_rate': 1.1447617232026842e-06, 'epoch': 0.85} + 85%|████████▌ | 10169/11952 [1:39:15<2:58:49, 6.02s/it] 85%|████████▌ | 10170/11952 [1:39:21<2:57:32, 5.98s/it] {'loss': 0.4687, 'learning_rate': 1.1435030429455951e-06, 'epoch': 0.85} + 85%|████████▌ | 10170/11952 [1:39:21<2:57:32, 5.98s/it] 85%|████████▌ | 10171/11952 [1:39:26<2:55:51, 5.92s/it] {'loss': 0.4722, 'learning_rate': 1.1422450130728069e-06, 'epoch': 0.85} + 85%|████████▌ | 10171/11952 [1:39:26<2:55:51, 5.92s/it] 85%|████████▌ | 10172/11952 [1:39:32<2:56:03, 5.93s/it] {'loss': 0.4592, 'learning_rate': 1.1409876336767013e-06, 'epoch': 0.85} + 85%|████████▌ | 10172/11952 [1:39:32<2:56:03, 5.93s/it] 85%|████████▌ | 10173/11952 [1:39:38<2:54:18, 5.88s/it] {'loss': 0.4744, 'learning_rate': 1.1397309048496174e-06, 'epoch': 0.85} + 85%|████████▌ | 10173/11952 [1:39:38<2:54:18, 5.88s/it] 85%|████████▌ | 10174/11952 [1:39:44<2:53:15, 5.85s/it] {'loss': 0.4578, 'learning_rate': 1.1384748266838408e-06, 'epoch': 0.85} + 85%|████████▌ | 10174/11952 [1:39:44<2:53:15, 5.85s/it] 85%|████████▌ | 10175/11952 [1:39:50<2:51:36, 5.79s/it] {'loss': 0.467, 'learning_rate': 1.1372193992716175e-06, 'epoch': 0.85} + 85%|████████▌ | 10175/11952 [1:39:50<2:51:36, 5.79s/it] 85%|████████▌ | 10176/11952 [1:39:56<2:53:07, 5.85s/it] {'loss': 0.4537, 'learning_rate': 1.1359646227051357e-06, 'epoch': 0.85} + 85%|████████▌ | 10176/11952 [1:39:56<2:53:07, 5.85s/it] 85%|████████▌ | 10177/11952 [1:40:02<2:57:20, 5.99s/it] {'loss': 0.454, 'learning_rate': 1.1347104970765466e-06, 'epoch': 0.85} + 85%|████████▌ | 10177/11952 [1:40:02<2:57:20, 5.99s/it] 85%|████████▌ | 10178/11952 [1:40:08<3:00:00, 6.09s/it] {'loss': 0.475, 'learning_rate': 1.133457022477945e-06, 'epoch': 0.85} + 85%|████████▌ | 10178/11952 [1:40:08<3:00:00, 6.09s/it] 85%|████████▌ | 10179/11952 [1:40:14<2:58:58, 6.06s/it] {'loss': 0.4638, 'learning_rate': 1.1322041990013798e-06, 'epoch': 0.85} + 85%|████████▌ | 10179/11952 [1:40:14<2:58:58, 6.06s/it] 85%|████████▌ | 10180/11952 [1:40:20<2:56:36, 5.98s/it] {'loss': 0.4609, 'learning_rate': 1.130952026738855e-06, 'epoch': 0.85} + 85%|████████▌ | 10180/11952 [1:40:20<2:56:36, 5.98s/it] 85%|████████▌ | 10181/11952 [1:40:26<2:55:08, 5.93s/it] {'loss': 0.4676, 'learning_rate': 1.1297005057823251e-06, 'epoch': 0.85} + 85%|████████▌ | 10181/11952 [1:40:26<2:55:08, 5.93s/it] 85%|████████▌ | 10182/11952 [1:40:32<2:53:56, 5.90s/it] {'loss': 0.4789, 'learning_rate': 1.1284496362236952e-06, 'epoch': 0.85} + 85%|████████▌ | 10182/11952 [1:40:32<2:53:56, 5.90s/it] 85%|████████▌ | 10183/11952 [1:40:38<2:54:52, 5.93s/it] {'loss': 0.4718, 'learning_rate': 1.1271994181548217e-06, 'epoch': 0.85} + 85%|████████▌ | 10183/11952 [1:40:38<2:54:52, 5.93s/it] 85%|████████▌ | 10184/11952 [1:40:43<2:52:45, 5.86s/it] {'loss': 0.4717, 'learning_rate': 1.1259498516675204e-06, 'epoch': 0.85} + 85%|████████▌ | 10184/11952 [1:40:43<2:52:45, 5.86s/it] 85%|████████▌ | 10185/11952 [1:40:49<2:51:15, 5.82s/it] {'loss': 0.4607, 'learning_rate': 1.12470093685355e-06, 'epoch': 0.85} + 85%|████████▌ | 10185/11952 [1:40:49<2:51:15, 5.82s/it] 85%|████████▌ | 10186/11952 [1:40:55<2:51:20, 5.82s/it] {'loss': 0.4358, 'learning_rate': 1.1234526738046303e-06, 'epoch': 0.85} + 85%|████████▌ | 10186/11952 [1:40:55<2:51:20, 5.82s/it] 85%|████████▌ | 10187/11952 [1:41:01<2:51:07, 5.82s/it] {'loss': 0.474, 'learning_rate': 1.122205062612426e-06, 'epoch': 0.85} + 85%|████████▌ | 10187/11952 [1:41:01<2:51:07, 5.82s/it] 85%|████████▌ | 10188/11952 [1:41:07<2:53:53, 5.91s/it] {'loss': 0.4668, 'learning_rate': 1.1209581033685558e-06, 'epoch': 0.85} + 85%|████████▌ | 10188/11952 [1:41:07<2:53:53, 5.91s/it] 85%|████████▌ | 10189/11952 [1:41:13<2:55:05, 5.96s/it] {'loss': 0.4598, 'learning_rate': 1.1197117961645921e-06, 'epoch': 0.85} + 85%|████████▌ | 10189/11952 [1:41:13<2:55:05, 5.96s/it] 85%|████████▌ | 10190/11952 [1:41:19<2:53:50, 5.92s/it] {'loss': 0.4466, 'learning_rate': 1.118466141092055e-06, 'epoch': 0.85} + 85%|████████▌ | 10190/11952 [1:41:19<2:53:50, 5.92s/it] 85%|████████▌ | 10191/11952 [1:41:25<2:52:59, 5.89s/it] {'loss': 0.4796, 'learning_rate': 1.1172211382424269e-06, 'epoch': 0.85} + 85%|████████▌ | 10191/11952 [1:41:25<2:52:59, 5.89s/it] 85%|████████▌ | 10192/11952 [1:41:30<2:52:37, 5.88s/it] {'loss': 0.461, 'learning_rate': 1.1159767877071314e-06, 'epoch': 0.85} + 85%|████████▌ | 10192/11952 [1:41:30<2:52:37, 5.88s/it] 85%|████████▌ | 10193/11952 [1:41:36<2:54:26, 5.95s/it] {'loss': 0.472, 'learning_rate': 1.1147330895775498e-06, 'epoch': 0.85} + 85%|████████▌ | 10193/11952 [1:41:36<2:54:26, 5.95s/it] 85%|████████▌ | 10194/11952 [1:41:42<2:53:09, 5.91s/it] {'loss': 0.4753, 'learning_rate': 1.1134900439450124e-06, 'epoch': 0.85} + 85%|████████▌ | 10194/11952 [1:41:42<2:53:09, 5.91s/it] 85%|████████▌ | 10195/11952 [1:41:48<2:52:26, 5.89s/it] {'loss': 0.449, 'learning_rate': 1.112247650900804e-06, 'epoch': 0.85} + 85%|████████▌ | 10195/11952 [1:41:48<2:52:26, 5.89s/it] 85%|████████▌ | 10196/11952 [1:41:54<2:50:00, 5.81s/it] {'loss': 0.4559, 'learning_rate': 1.1110059105361616e-06, 'epoch': 0.85} + 85%|████████▌ | 10196/11952 [1:41:54<2:50:00, 5.81s/it] 85%|████████▌ | 10197/11952 [1:41:59<2:48:38, 5.77s/it] {'loss': 0.4649, 'learning_rate': 1.1097648229422719e-06, 'epoch': 0.85} + 85%|████████▌ | 10197/11952 [1:41:59<2:48:38, 5.77s/it] 85%|████████▌ | 10198/11952 [1:42:06<2:52:20, 5.90s/it] {'loss': 0.4535, 'learning_rate': 1.108524388210278e-06, 'epoch': 0.85} + 85%|████████▌ | 10198/11952 [1:42:06<2:52:20, 5.90s/it] 85%|████████▌ | 10199/11952 [1:42:11<2:50:21, 5.83s/it] {'loss': 0.4645, 'learning_rate': 1.1072846064312715e-06, 'epoch': 0.85} + 85%|████████▌ | 10199/11952 [1:42:11<2:50:21, 5.83s/it]6 AutoResumeHook: Checking whether to suspend... +57 AutoResumeHook: Checking whether to suspend...AutoResumeHook: Checking whether to suspend... + +2 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend...1 + AutoResumeHook: Checking whether to suspend... +0 AutoResumeHook: Checking whether to suspend... + 85%|████████▌ | 10200/11952 [1:42:17<2:49:54, 5.82s/it] {'loss': 0.4628, 'learning_rate': 1.1060454776962947e-06, 'epoch': 0.85} + 85%|████████▌ | 10200/11952 [1:42:17<2:49:54, 5.82s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-10200/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-10200/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/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( + 85%|████████▌ | 10201/11952 [1:42:48<6:26:06, 13.23s/it] {'loss': 0.4658, 'learning_rate': 1.1048070020963453e-06, 'epoch': 0.85} + 85%|████████▌ | 10201/11952 [1:42:48<6:26:06, 13.23s/it] 85%|████████▌ | 10202/11952 [1:42:54<5:24:49, 11.14s/it] {'loss': 0.4706, 'learning_rate': 1.1035691797223724e-06, 'epoch': 0.85} + 85%|████████▌ | 10202/11952 [1:42:54<5:24:49, 11.14s/it] 85%|████████▌ | 10203/11952 [1:43:00<4:37:22, 9.52s/it] {'loss': 0.4566, 'learning_rate': 1.1023320106652735e-06, 'epoch': 0.85} + 85%|████████▌ | 10203/11952 [1:43:00<4:37:22, 9.52s/it] 85%|████████▌ | 10204/11952 [1:43:05<4:05:15, 8.42s/it] {'loss': 0.4699, 'learning_rate': 1.1010954950159058e-06, 'epoch': 0.85} + 85%|████████▌ | 10204/11952 [1:43:05<4:05:15, 8.42s/it] 85%|████████▌ | 10205/11952 [1:43:11<3:42:09, 7.63s/it] {'loss': 0.4587, 'learning_rate': 1.0998596328650724e-06, 'epoch': 0.85} + 85%|████████▌ | 10205/11952 [1:43:11<3:42:09, 7.63s/it] 85%|████████▌ | 10206/11952 [1:43:17<3:25:35, 7.07s/it] {'loss': 0.4722, 'learning_rate': 1.098624424303526e-06, 'epoch': 0.85} + 85%|████████▌ | 10206/11952 [1:43:17<3:25:35, 7.07s/it] 85%|████████▌ | 10207/11952 [1:43:23<3:12:58, 6.64s/it] {'loss': 0.4548, 'learning_rate': 1.0973898694219809e-06, 'epoch': 0.85} + 85%|████████▌ | 10207/11952 [1:43:23<3:12:58, 6.64s/it] 85%|████████▌ | 10208/11952 [1:43:29<3:10:28, 6.55s/it] {'loss': 0.4523, 'learning_rate': 1.0961559683110946e-06, 'epoch': 0.85} + 85%|████████▌ | 10208/11952 [1:43:29<3:10:28, 6.55s/it] 85%|████████▌ | 10209/11952 [1:43:35<3:02:21, 6.28s/it] {'loss': 0.4467, 'learning_rate': 1.0949227210614798e-06, 'epoch': 0.85} + 85%|████████▌ | 10209/11952 [1:43:35<3:02:21, 6.28s/it] 85%|████████▌ | 10210/11952 [1:43:41<3:02:19, 6.28s/it] {'loss': 0.4952, 'learning_rate': 1.0936901277637002e-06, 'epoch': 0.85} + 85%|████████▌ | 10210/11952 [1:43:41<3:02:19, 6.28s/it] 85%|████████▌ | 10211/11952 [1:43:47<3:00:35, 6.22s/it] {'loss': 0.4745, 'learning_rate': 1.0924581885082753e-06, 'epoch': 0.85} + 85%|████████▌ | 10211/11952 [1:43:47<3:00:35, 6.22s/it] 85%|████████▌ | 10212/11952 [1:43:53<2:58:14, 6.15s/it] {'loss': 0.45, 'learning_rate': 1.0912269033856716e-06, 'epoch': 0.85} + 85%|████████▌ | 10212/11952 [1:43:53<2:58:14, 6.15s/it] 85%|████████▌ | 10213/11952 [1:43:59<2:53:22, 5.98s/it] {'loss': 0.4564, 'learning_rate': 1.089996272486309e-06, 'epoch': 0.85} + 85%|████████▌ | 10213/11952 [1:43:59<2:53:22, 5.98s/it] 85%|████████▌ | 10214/11952 [1:44:04<2:52:16, 5.95s/it] {'loss': 0.4536, 'learning_rate': 1.088766295900562e-06, 'epoch': 0.85} + 85%|████████▌ | 10214/11952 [1:44:04<2:52:16, 5.95s/it] 85%|████████▌ | 10215/11952 [1:44:10<2:49:31, 5.86s/it] {'loss': 0.4627, 'learning_rate': 1.0875369737187502e-06, 'epoch': 0.85} + 85%|████████▌ | 10215/11952 [1:44:10<2:49:31, 5.86s/it] 85%|████████▌ | 10216/11952 [1:44:16<2:50:37, 5.90s/it] {'loss': 0.4539, 'learning_rate': 1.0863083060311563e-06, 'epoch': 0.85} + 85%|████████▌ | 10216/11952 [1:44:16<2:50:37, 5.90s/it] 85%|████████▌ | 10217/11952 [1:44:22<2:54:16, 6.03s/it] {'loss': 0.474, 'learning_rate': 1.0850802929280034e-06, 'epoch': 0.85} + 85%|████████▌ | 10217/11952 [1:44:22<2:54:16, 6.03s/it] 85%|████████▌ | 10218/11952 [1:44:28<2:53:41, 6.01s/it] {'loss': 0.4448, 'learning_rate': 1.0838529344994763e-06, 'epoch': 0.85} + 85%|████████▌ | 10218/11952 [1:44:28<2:53:41, 6.01s/it] 86%|████████▌ | 10219/11952 [1:44:34<2:51:21, 5.93s/it] {'loss': 0.4548, 'learning_rate': 1.0826262308357038e-06, 'epoch': 0.85} + 86%|████████▌ | 10219/11952 [1:44:34<2:51:21, 5.93s/it] 86%|████████▌ | 10220/11952 [1:44:40<2:50:33, 5.91s/it] {'loss': 0.4531, 'learning_rate': 1.0814001820267717e-06, 'epoch': 0.86} + 86%|████████▌ | 10220/11952 [1:44:40<2:50:33, 5.91s/it] 86%|████████▌ | 10221/11952 [1:44:46<2:51:43, 5.95s/it] {'loss': 0.4624, 'learning_rate': 1.0801747881627134e-06, 'epoch': 0.86} + 86%|████████▌ | 10221/11952 [1:44:46<2:51:43, 5.95s/it] 86%|████████▌ | 10222/11952 [1:44:52<2:51:20, 5.94s/it] {'loss': 0.4819, 'learning_rate': 1.0789500493335191e-06, 'epoch': 0.86} + 86%|████████▌ | 10222/11952 [1:44:52<2:51:20, 5.94s/it] 86%|████████▌ | 10223/11952 [1:44:58<2:50:31, 5.92s/it] {'loss': 0.4558, 'learning_rate': 1.0777259656291284e-06, 'epoch': 0.86} + 86%|████████▌ | 10223/11952 [1:44:58<2:50:31, 5.92s/it] 86%|████████▌ | 10224/11952 [1:45:04<2:52:39, 6.00s/it] {'loss': 0.4588, 'learning_rate': 1.07650253713943e-06, 'epoch': 0.86} + 86%|████████▌ | 10224/11952 [1:45:04<2:52:39, 6.00s/it] 86%|████████▌ | 10225/11952 [1:45:10<2:50:29, 5.92s/it] {'loss': 0.4649, 'learning_rate': 1.0752797639542712e-06, 'epoch': 0.86} + 86%|████████▌ | 10225/11952 [1:45:10<2:50:29, 5.92s/it] 86%|████████▌ | 10226/11952 [1:45:16<2:49:48, 5.90s/it] {'loss': 0.4855, 'learning_rate': 1.0740576461634466e-06, 'epoch': 0.86} + 86%|████████▌ | 10226/11952 [1:45:16<2:49:48, 5.90s/it] 86%|████████▌ | 10227/11952 [1:45:22<2:51:12, 5.95s/it] {'loss': 0.4787, 'learning_rate': 1.0728361838567003e-06, 'epoch': 0.86} + 86%|████████▌ | 10227/11952 [1:45:22<2:51:12, 5.95s/it] 86%|████████▌ | 10228/11952 [1:45:27<2:48:30, 5.86s/it] {'loss': 0.4544, 'learning_rate': 1.0716153771237359e-06, 'epoch': 0.86} + 86%|████████▌ | 10228/11952 [1:45:27<2:48:30, 5.86s/it] 86%|████████▌ | 10229/11952 [1:45:33<2:49:31, 5.90s/it] {'loss': 0.4666, 'learning_rate': 1.0703952260542016e-06, 'epoch': 0.86} + 86%|████████▌ | 10229/11952 [1:45:33<2:49:31, 5.90s/it] 86%|████████▌ | 10230/11952 [1:45:40<2:53:03, 6.03s/it] {'loss': 0.4757, 'learning_rate': 1.0691757307377014e-06, 'epoch': 0.86} + 86%|████████▌ | 10230/11952 [1:45:40<2:53:03, 6.03s/it] 86%|████████▌ | 10231/11952 [1:45:46<2:53:28, 6.05s/it] {'loss': 0.4772, 'learning_rate': 1.0679568912637872e-06, 'epoch': 0.86} + 86%|████████▌ | 10231/11952 [1:45:46<2:53:28, 6.05s/it] 86%|████████▌ | 10232/11952 [1:45:52<2:51:36, 5.99s/it] {'loss': 0.4798, 'learning_rate': 1.0667387077219704e-06, 'epoch': 0.86} + 86%|████████▌ | 10232/11952 [1:45:52<2:51:36, 5.99s/it] 86%|████████▌ | 10233/11952 [1:45:57<2:49:04, 5.90s/it] {'loss': 0.4355, 'learning_rate': 1.0655211802017052e-06, 'epoch': 0.86} + 86%|████████▌ | 10233/11952 [1:45:57<2:49:04, 5.90s/it] 86%|████████▌ | 10234/11952 [1:46:03<2:49:04, 5.90s/it] {'loss': 0.4507, 'learning_rate': 1.0643043087924043e-06, 'epoch': 0.86} + 86%|████████▌ | 10234/11952 [1:46:03<2:49:04, 5.90s/it] 86%|████████▌ | 10235/11952 [1:46:09<2:49:12, 5.91s/it] {'loss': 0.4636, 'learning_rate': 1.0630880935834286e-06, 'epoch': 0.86} + 86%|████████▌ | 10235/11952 [1:46:09<2:49:12, 5.91s/it] 86%|████████▌ | 10236/11952 [1:46:15<2:50:49, 5.97s/it] {'loss': 0.4574, 'learning_rate': 1.0618725346640902e-06, 'epoch': 0.86} + 86%|████████▌ | 10236/11952 [1:46:15<2:50:49, 5.97s/it] 86%|████████▌ | 10237/11952 [1:46:21<2:52:32, 6.04s/it] {'loss': 0.473, 'learning_rate': 1.0606576321236585e-06, 'epoch': 0.86} + 86%|████████▌ | 10237/11952 [1:46:21<2:52:32, 6.04s/it] 86%|████████▌ | 10238/11952 [1:46:27<2:50:30, 5.97s/it] {'loss': 0.458, 'learning_rate': 1.0594433860513452e-06, 'epoch': 0.86} + 86%|████████▌ | 10238/11952 [1:46:27<2:50:30, 5.97s/it] 86%|████████▌ | 10239/11952 [1:46:33<2:50:08, 5.96s/it] {'loss': 0.4414, 'learning_rate': 1.0582297965363264e-06, 'epoch': 0.86} + 86%|████████▌ | 10239/11952 [1:46:33<2:50:08, 5.96s/it] 86%|████████▌ | 10240/11952 [1:46:39<2:49:48, 5.95s/it] {'loss': 0.4564, 'learning_rate': 1.0570168636677191e-06, 'epoch': 0.86} + 86%|████████▌ | 10240/11952 [1:46:39<2:49:48, 5.95s/it] 86%|████████▌ | 10241/11952 [1:46:45<2:49:40, 5.95s/it] {'loss': 0.4609, 'learning_rate': 1.055804587534598e-06, 'epoch': 0.86} + 86%|████████▌ | 10241/11952 [1:46:45<2:49:40, 5.95s/it] 86%|████████▌ | 10242/11952 [1:46:51<2:50:12, 5.97s/it] {'loss': 0.4552, 'learning_rate': 1.0545929682259847e-06, 'epoch': 0.86} + 86%|████████▌ | 10242/11952 [1:46:51<2:50:12, 5.97s/it] 86%|████████▌ | 10243/11952 [1:46:57<2:51:09, 6.01s/it] {'loss': 0.487, 'learning_rate': 1.0533820058308576e-06, 'epoch': 0.86} + 86%|████████▌ | 10243/11952 [1:46:57<2:51:09, 6.01s/it] 86%|████████▌ | 10244/11952 [1:47:03<2:48:19, 5.91s/it] {'loss': 0.4707, 'learning_rate': 1.0521717004381427e-06, 'epoch': 0.86} + 86%|████████▌ | 10244/11952 [1:47:03<2:48:19, 5.91s/it] 86%|████████▌ | 10245/11952 [1:47:09<2:46:53, 5.87s/it] {'loss': 0.4729, 'learning_rate': 1.0509620521367225e-06, 'epoch': 0.86} + 86%|████████▌ | 10245/11952 [1:47:09<2:46:53, 5.87s/it] 86%|████████▌ | 10246/11952 [1:47:14<2:45:51, 5.83s/it] {'loss': 0.4663, 'learning_rate': 1.0497530610154283e-06, 'epoch': 0.86} + 86%|████████▌ | 10246/11952 [1:47:14<2:45:51, 5.83s/it] 86%|████████▌ | 10247/11952 [1:47:20<2:46:57, 5.88s/it] {'loss': 0.4829, 'learning_rate': 1.04854472716304e-06, 'epoch': 0.86} + 86%|████████▌ | 10247/11952 [1:47:20<2:46:57, 5.88s/it] 86%|████████▌ | 10248/11952 [1:47:27<2:49:41, 5.98s/it] {'loss': 0.4565, 'learning_rate': 1.0473370506682968e-06, 'epoch': 0.86} + 86%|████████▌ | 10248/11952 [1:47:27<2:49:41, 5.98s/it] 86%|████████▌ | 10249/11952 [1:47:32<2:47:22, 5.90s/it] {'loss': 0.4666, 'learning_rate': 1.046130031619883e-06, 'epoch': 0.86} + 86%|████████▌ | 10249/11952 [1:47:32<2:47:22, 5.90s/it]76 AutoResumeHook: Checking whether to suspend...AutoResumeHook: Checking whether to suspend... + +4 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... +02 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... + 86%|████████▌ | 10250/11952 [1:47:38<2:46:44, 5.88s/it] {'loss': 0.4489, 'learning_rate': 1.044923670106439e-06, 'epoch': 0.86} + 86%|████████▌ | 10250/11952 [1:47:38<2:46:44, 5.88s/it] 86%|████████▌ | 10251/11952 [1:47:44<2:48:34, 5.95s/it] {'loss': 0.4793, 'learning_rate': 1.0437179662165508e-06, 'epoch': 0.86} + 86%|████████▌ | 10251/11952 [1:47:44<2:48:34, 5.95s/it] 86%|████████▌ | 10252/11952 [1:47:50<2:50:44, 6.03s/it] {'loss': 0.4564, 'learning_rate': 1.0425129200387662e-06, 'epoch': 0.86} + 86%|████████▌ | 10252/11952 [1:47:50<2:50:44, 6.03s/it] 86%|████████▌ | 10253/11952 [1:47:56<2:49:00, 5.97s/it] {'loss': 0.47, 'learning_rate': 1.0413085316615745e-06, 'epoch': 0.86} + 86%|████████▌ | 10253/11952 [1:47:56<2:49:00, 5.97s/it] 86%|████████▌ | 10254/11952 [1:48:02<2:48:12, 5.94s/it] {'loss': 0.4469, 'learning_rate': 1.0401048011734227e-06, 'epoch': 0.86} + 86%|████████▌ | 10254/11952 [1:48:02<2:48:12, 5.94s/it] 86%|████████▌ | 10255/11952 [1:48:08<2:47:40, 5.93s/it] {'loss': 0.4772, 'learning_rate': 1.0389017286627078e-06, 'epoch': 0.86} + 86%|████████▌ | 10255/11952 [1:48:08<2:47:40, 5.93s/it] 86%|████████▌ | 10256/11952 [1:48:14<2:49:02, 5.98s/it] {'loss': 0.475, 'learning_rate': 1.0376993142177771e-06, 'epoch': 0.86} + 86%|████████▌ | 10256/11952 [1:48:14<2:49:02, 5.98s/it] 86%|████████▌ | 10257/11952 [1:48:20<2:45:13, 5.85s/it] {'loss': 0.4524, 'learning_rate': 1.036497557926931e-06, 'epoch': 0.86} + 86%|████████▌ | 10257/11952 [1:48:20<2:45:13, 5.85s/it] 86%|████████▌ | 10258/11952 [1:48:26<2:45:26, 5.86s/it] {'loss': 0.4645, 'learning_rate': 1.035296459878421e-06, 'epoch': 0.86} + 86%|████████▌ | 10258/11952 [1:48:26<2:45:26, 5.86s/it] 86%|████████▌ | 10259/11952 [1:48:31<2:45:28, 5.86s/it] {'loss': 0.4579, 'learning_rate': 1.0340960201604544e-06, 'epoch': 0.86} + 86%|████████▌ | 10259/11952 [1:48:31<2:45:28, 5.86s/it] 86%|████████▌ | 10260/11952 [1:48:37<2:46:20, 5.90s/it] {'loss': 0.4659, 'learning_rate': 1.0328962388611841e-06, 'epoch': 0.86} + 86%|████████▌ | 10260/11952 [1:48:37<2:46:20, 5.90s/it] 86%|████████▌ | 10261/11952 [1:48:43<2:45:34, 5.87s/it] {'loss': 0.4552, 'learning_rate': 1.0316971160687172e-06, 'epoch': 0.86} + 86%|████████▌ | 10261/11952 [1:48:43<2:45:34, 5.87s/it] 86%|████████▌ | 10262/11952 [1:48:49<2:45:14, 5.87s/it] {'loss': 0.452, 'learning_rate': 1.0304986518711124e-06, 'epoch': 0.86} + 86%|████████▌ | 10262/11952 [1:48:49<2:45:14, 5.87s/it] 86%|████████▌ | 10263/11952 [1:48:55<2:47:02, 5.93s/it] {'loss': 0.4648, 'learning_rate': 1.029300846356379e-06, 'epoch': 0.86} + 86%|████████▌ | 10263/11952 [1:48:55<2:47:02, 5.93s/it] 86%|████████▌ | 10264/11952 [1:49:01<2:47:01, 5.94s/it] {'loss': 0.4696, 'learning_rate': 1.0281036996124793e-06, 'epoch': 0.86} + 86%|████████▌ | 10264/11952 [1:49:01<2:47:01, 5.94s/it] 86%|████████▌ | 10265/11952 [1:49:07<2:44:45, 5.86s/it] {'loss': 0.4558, 'learning_rate': 1.026907211727326e-06, 'epoch': 0.86} + 86%|████████▌ | 10265/11952 [1:49:07<2:44:45, 5.86s/it] 86%|████████▌ | 10266/11952 [1:49:13<2:44:19, 5.85s/it] {'loss': 0.4506, 'learning_rate': 1.0257113827887865e-06, 'epoch': 0.86} + 86%|████████▌ | 10266/11952 [1:49:13<2:44:19, 5.85s/it] 86%|████████▌ | 10267/11952 [1:49:18<2:43:04, 5.81s/it] {'loss': 0.4555, 'learning_rate': 1.0245162128846764e-06, 'epoch': 0.86} + 86%|████████▌ | 10267/11952 [1:49:18<2:43:04, 5.81s/it] 86%|████████▌ | 10268/11952 [1:49:24<2:42:34, 5.79s/it] {'loss': 0.4706, 'learning_rate': 1.023321702102762e-06, 'epoch': 0.86} + 86%|████████▌ | 10268/11952 [1:49:24<2:42:34, 5.79s/it] 86%|████████▌ | 10269/11952 [1:49:30<2:41:30, 5.76s/it] {'loss': 0.4593, 'learning_rate': 1.0221278505307665e-06, 'epoch': 0.86} + 86%|████████▌ | 10269/11952 [1:49:30<2:41:30, 5.76s/it] 86%|████████▌ | 10270/11952 [1:49:35<2:40:08, 5.71s/it] {'loss': 0.4606, 'learning_rate': 1.0209346582563596e-06, 'epoch': 0.86} + 86%|████████▌ | 10270/11952 [1:49:35<2:40:08, 5.71s/it] 86%|████████▌ | 10271/11952 [1:49:41<2:42:52, 5.81s/it] {'loss': 0.458, 'learning_rate': 1.0197421253671646e-06, 'epoch': 0.86} + 86%|████████▌ | 10271/11952 [1:49:41<2:42:52, 5.81s/it] 86%|████████▌ | 10272/11952 [1:49:47<2:43:26, 5.84s/it] {'loss': 0.4643, 'learning_rate': 1.018550251950755e-06, 'epoch': 0.86} + 86%|████████▌ | 10272/11952 [1:49:47<2:43:26, 5.84s/it] 86%|████████▌ | 10273/11952 [1:49:53<2:43:54, 5.86s/it] {'loss': 0.497, 'learning_rate': 1.0173590380946596e-06, 'epoch': 0.86} + 86%|████████▌ | 10273/11952 [1:49:53<2:43:54, 5.86s/it] 86%|████████▌ | 10274/11952 [1:49:59<2:44:22, 5.88s/it] {'loss': 0.4946, 'learning_rate': 1.016168483886356e-06, 'epoch': 0.86} + 86%|████████▌ | 10274/11952 [1:49:59<2:44:22, 5.88s/it] 86%|████████▌ | 10275/11952 [1:50:05<2:46:14, 5.95s/it] {'loss': 0.4545, 'learning_rate': 1.0149785894132714e-06, 'epoch': 0.86} + 86%|████████▌ | 10275/11952 [1:50:05<2:46:14, 5.95s/it] 86%|████████▌ | 10276/11952 [1:50:11<2:44:32, 5.89s/it] {'loss': 0.4669, 'learning_rate': 1.0137893547627875e-06, 'epoch': 0.86} + 86%|████████▌ | 10276/11952 [1:50:11<2:44:32, 5.89s/it] 86%|████████▌ | 10277/11952 [1:50:17<2:45:22, 5.92s/it] {'loss': 0.4839, 'learning_rate': 1.0126007800222347e-06, 'epoch': 0.86} + 86%|████████▌ | 10277/11952 [1:50:17<2:45:22, 5.92s/it] 86%|████████▌ | 10278/11952 [1:50:23<2:46:01, 5.95s/it] {'loss': 0.4633, 'learning_rate': 1.0114128652789023e-06, 'epoch': 0.86} + 86%|████████▌ | 10278/11952 [1:50:23<2:46:01, 5.95s/it] 86%|████████▌ | 10279/11952 [1:50:29<2:46:59, 5.99s/it] {'loss': 0.4627, 'learning_rate': 1.0102256106200203e-06, 'epoch': 0.86} + 86%|████████▌ | 10279/11952 [1:50:29<2:46:59, 5.99s/it] 86%|████████▌ | 10280/11952 [1:50:35<2:48:58, 6.06s/it] {'loss': 0.4656, 'learning_rate': 1.0090390161327801e-06, 'epoch': 0.86} + 86%|████████▌ | 10280/11952 [1:50:35<2:48:58, 6.06s/it] 86%|████████▌ | 10281/11952 [1:50:41<2:47:45, 6.02s/it] {'loss': 0.4692, 'learning_rate': 1.0078530819043174e-06, 'epoch': 0.86} + 86%|████████▌ | 10281/11952 [1:50:41<2:47:45, 6.02s/it] 86%|████████▌ | 10282/11952 [1:50:47<2:46:03, 5.97s/it] {'loss': 0.4646, 'learning_rate': 1.006667808021725e-06, 'epoch': 0.86} + 86%|████████▌ | 10282/11952 [1:50:47<2:46:03, 5.97s/it] 86%|████████▌ | 10283/11952 [1:50:53<2:48:11, 6.05s/it] {'loss': 0.4597, 'learning_rate': 1.0054831945720411e-06, 'epoch': 0.86} + 86%|████████▌ | 10283/11952 [1:50:53<2:48:11, 6.05s/it] 86%|████████▌ | 10284/11952 [1:50:59<2:48:59, 6.08s/it] {'loss': 0.4651, 'learning_rate': 1.0042992416422614e-06, 'epoch': 0.86} + 86%|████████▌ | 10284/11952 [1:50:59<2:48:59, 6.08s/it] 86%|████████▌ | 10285/11952 [1:51:06<2:51:04, 6.16s/it] {'loss': 0.4696, 'learning_rate': 1.0031159493193277e-06, 'epoch': 0.86} + 86%|████████▌ | 10285/11952 [1:51:06<2:51:04, 6.16s/it] 86%|████████▌ | 10286/11952 [1:51:12<2:47:10, 6.02s/it] {'loss': 0.4727, 'learning_rate': 1.001933317690139e-06, 'epoch': 0.86} + 86%|████████▌ | 10286/11952 [1:51:12<2:47:10, 6.02s/it] 86%|████████▌ | 10287/11952 [1:51:17<2:43:45, 5.90s/it] {'loss': 0.4629, 'learning_rate': 1.000751346841542e-06, 'epoch': 0.86} + 86%|████████▌ | 10287/11952 [1:51:17<2:43:45, 5.90s/it] 86%|████████▌ | 10288/11952 [1:51:23<2:44:50, 5.94s/it] {'loss': 0.4629, 'learning_rate': 9.995700368603333e-07, 'epoch': 0.86} + 86%|████████▌ | 10288/11952 [1:51:23<2:44:50, 5.94s/it] 86%|████████▌ | 10289/11952 [1:51:29<2:44:50, 5.95s/it] {'loss': 0.4644, 'learning_rate': 9.983893878332674e-07, 'epoch': 0.86} + 86%|████████▌ | 10289/11952 [1:51:29<2:44:50, 5.95s/it] 86%|████████▌ | 10290/11952 [1:51:35<2:44:02, 5.92s/it] {'loss': 0.4686, 'learning_rate': 9.972093998470444e-07, 'epoch': 0.86} + 86%|████████▌ | 10290/11952 [1:51:35<2:44:02, 5.92s/it] 86%|████████▌ | 10291/11952 [1:51:41<2:43:38, 5.91s/it] {'loss': 0.4609, 'learning_rate': 9.960300729883177e-07, 'epoch': 0.86} + 86%|████████▌ | 10291/11952 [1:51:41<2:43:38, 5.91s/it] 86%|████████▌ | 10292/11952 [1:51:47<2:42:40, 5.88s/it] {'loss': 0.4454, 'learning_rate': 9.9485140734369e-07, 'epoch': 0.86} + 86%|████████▌ | 10292/11952 [1:51:47<2:42:40, 5.88s/it] 86%|████████▌ | 10293/11952 [1:51:53<2:45:01, 5.97s/it] {'loss': 0.4597, 'learning_rate': 9.936734029997218e-07, 'epoch': 0.86} + 86%|████████▌ | 10293/11952 [1:51:53<2:45:01, 5.97s/it] 86%|████████▌ | 10294/11952 [1:51:59<2:43:52, 5.93s/it] {'loss': 0.4802, 'learning_rate': 9.92496060042919e-07, 'epoch': 0.86} + 86%|████████▌ | 10294/11952 [1:51:59<2:43:52, 5.93s/it] 86%|████████▌ | 10295/11952 [1:52:05<2:45:13, 5.98s/it] {'loss': 0.4629, 'learning_rate': 9.913193785597396e-07, 'epoch': 0.86} + 86%|████████▌ | 10295/11952 [1:52:05<2:45:13, 5.98s/it] 86%|████████▌ | 10296/11952 [1:52:11<2:48:24, 6.10s/it] {'loss': 0.4501, 'learning_rate': 9.90143358636596e-07, 'epoch': 0.86} + 86%|████████▌ | 10296/11952 [1:52:11<2:48:24, 6.10s/it] 86%|████████▌ | 10297/11952 [1:52:17<2:45:55, 6.02s/it] {'loss': 0.4537, 'learning_rate': 9.88968000359849e-07, 'epoch': 0.86} + 86%|████████▌ | 10297/11952 [1:52:17<2:45:55, 6.02s/it] 86%|████████▌ | 10298/11952 [1:52:23<2:47:04, 6.06s/it] {'loss': 0.464, 'learning_rate': 9.877933038158105e-07, 'epoch': 0.86} + 86%|████████▌ | 10298/11952 [1:52:23<2:47:04, 6.06s/it] 86%|████████▌ | 10299/11952 [1:52:29<2:43:39, 5.94s/it] {'loss': 0.4678, 'learning_rate': 9.866192690907472e-07, 'epoch': 0.86} + 86%|████████▌ | 10299/11952 [1:52:29<2:43:39, 5.94s/it]4 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +31 AutoResumeHook: Checking whether to suspend... AutoResumeHook: Checking whether to suspend... + +0 AutoResumeHook: Checking whether to suspend... + 86%|████████▌ | 10300/11952 [1:52:35<2:46:35, 6.05s/it]2 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4739, 'learning_rate': 9.85445896270878e-07, 'epoch': 0.86} + 86%|████████▌ | 10300/11952 [1:52:35<2:46:35, 6.05s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-10300/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-10300/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/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( + 86%|████████▌ | 10301/11952 [1:53:06<6:09:29, 13.43s/it] {'loss': 0.4806, 'learning_rate': 9.84273185442367e-07, 'epoch': 0.86} + 86%|████████▌ | 10301/11952 [1:53:06<6:09:29, 13.43s/it] 86%|████████▌ | 10302/11952 [1:53:12<5:06:33, 11.15s/it] {'loss': 0.4504, 'learning_rate': 9.831011366913335e-07, 'epoch': 0.86} + 86%|████████▌ | 10302/11952 [1:53:12<5:06:33, 11.15s/it] 86%|████████▌ | 10303/11952 [1:53:17<4:20:31, 9.48s/it] {'loss': 0.4628, 'learning_rate': 9.819297501038494e-07, 'epoch': 0.86} + 86%|████████▌ | 10303/11952 [1:53:17<4:20:31, 9.48s/it] 86%|████████▌ | 10304/11952 [1:53:23<3:51:40, 8.43s/it] {'loss': 0.4659, 'learning_rate': 9.80759025765935e-07, 'epoch': 0.86} + 86%|████████▌ | 10304/11952 [1:53:23<3:51:40, 8.43s/it] 86%|████████▌ | 10305/11952 [1:53:29<3:31:50, 7.72s/it] {'loss': 0.4496, 'learning_rate': 9.795889637635636e-07, 'epoch': 0.86} + 86%|████████▌ | 10305/11952 [1:53:29<3:31:50, 7.72s/it] 86%|████████▌ | 10306/11952 [1:53:35<3:14:37, 7.09s/it] {'loss': 0.4522, 'learning_rate': 9.78419564182659e-07, 'epoch': 0.86} + 86%|████████▌ | 10306/11952 [1:53:35<3:14:37, 7.09s/it] 86%|████████▌ | 10307/11952 [1:53:41<3:06:23, 6.80s/it] {'loss': 0.4757, 'learning_rate': 9.772508271090997e-07, 'epoch': 0.86} + 86%|████████▌ | 10307/11952 [1:53:41<3:06:23, 6.80s/it] 86%|████████▌ | 10308/11952 [1:53:47<2:59:32, 6.55s/it] {'loss': 0.4711, 'learning_rate': 9.760827526287108e-07, 'epoch': 0.86} + 86%|████████▌ | 10308/11952 [1:53:47<2:59:32, 6.55s/it] 86%|████████▋ | 10309/11952 [1:53:53<2:52:36, 6.30s/it] {'loss': 0.4507, 'learning_rate': 9.749153408272693e-07, 'epoch': 0.86} + 86%|████████▋ | 10309/11952 [1:53:53<2:52:36, 6.30s/it] 86%|████████▋ | 10310/11952 [1:54:00<3:01:10, 6.62s/it] {'loss': 0.4604, 'learning_rate': 9.737485917905088e-07, 'epoch': 0.86} + 86%|████████▋ | 10310/11952 [1:54:00<3:01:10, 6.62s/it] 86%|████████▋ | 10311/11952 [1:54:06<2:55:46, 6.43s/it] {'loss': 0.4598, 'learning_rate': 9.725825056041094e-07, 'epoch': 0.86} + 86%|████████▋ | 10311/11952 [1:54:06<2:55:46, 6.43s/it] 86%|████████▋ | 10312/11952 [1:54:12<2:51:02, 6.26s/it] {'loss': 0.471, 'learning_rate': 9.714170823537007e-07, 'epoch': 0.86} + 86%|████████▋ | 10312/11952 [1:54:12<2:51:02, 6.26s/it] 86%|████████▋ | 10313/11952 [1:54:18<2:47:15, 6.12s/it] {'loss': 0.4624, 'learning_rate': 9.702523221248706e-07, 'epoch': 0.86} + 86%|████████▋ | 10313/11952 [1:54:18<2:47:15, 6.12s/it] 86%|████████▋ | 10314/11952 [1:54:24<2:44:49, 6.04s/it] {'loss': 0.4548, 'learning_rate': 9.69088225003152e-07, 'epoch': 0.86} + 86%|████████▋ | 10314/11952 [1:54:24<2:44:49, 6.04s/it] 86%|████████▋ | 10315/11952 [1:54:29<2:42:24, 5.95s/it] {'loss': 0.4672, 'learning_rate': 9.679247910740331e-07, 'epoch': 0.86} + 86%|████████▋ | 10315/11952 [1:54:29<2:42:24, 5.95s/it] 86%|████████▋ | 10316/11952 [1:54:35<2:41:43, 5.93s/it] {'loss': 0.4596, 'learning_rate': 9.667620204229488e-07, 'epoch': 0.86} + 86%|████████▋ | 10316/11952 [1:54:35<2:41:43, 5.93s/it] 86%|████████▋ | 10317/11952 [1:54:41<2:39:48, 5.86s/it] {'loss': 0.447, 'learning_rate': 9.6559991313529e-07, 'epoch': 0.86} + 86%|████████▋ | 10317/11952 [1:54:41<2:39:48, 5.86s/it] 86%|████████▋ | 10318/11952 [1:54:47<2:40:47, 5.90s/it] {'loss': 0.4531, 'learning_rate': 9.64438469296396e-07, 'epoch': 0.86} + 86%|████████▋ | 10318/11952 [1:54:47<2:40:47, 5.90s/it] 86%|████████▋ | 10319/11952 [1:54:52<2:37:49, 5.80s/it] {'loss': 0.4692, 'learning_rate': 9.632776889915595e-07, 'epoch': 0.86} + 86%|████████▋ | 10319/11952 [1:54:52<2:37:49, 5.80s/it] 86%|████████▋ | 10320/11952 [1:54:58<2:38:55, 5.84s/it] {'loss': 0.4731, 'learning_rate': 9.621175723060216e-07, 'epoch': 0.86} + 86%|████████▋ | 10320/11952 [1:54:58<2:38:55, 5.84s/it] 86%|████████▋ | 10321/11952 [1:55:04<2:39:01, 5.85s/it] {'loss': 0.4477, 'learning_rate': 9.609581193249794e-07, 'epoch': 0.86} + 86%|████████▋ | 10321/11952 [1:55:04<2:39:01, 5.85s/it] 86%|████████▋ | 10322/11952 [1:55:10<2:39:49, 5.88s/it] {'loss': 0.48, 'learning_rate': 9.597993301335773e-07, 'epoch': 0.86} + 86%|████████▋ | 10322/11952 [1:55:10<2:39:49, 5.88s/it] 86%|████████▋ | 10323/11952 [1:55:16<2:38:50, 5.85s/it] {'loss': 0.4617, 'learning_rate': 9.586412048169114e-07, 'epoch': 0.86} + 86%|████████▋ | 10323/11952 [1:55:16<2:38:50, 5.85s/it] 86%|████████▋ | 10324/11952 [1:55:22<2:40:30, 5.92s/it] {'loss': 0.4565, 'learning_rate': 9.574837434600293e-07, 'epoch': 0.86} + 86%|████████▋ | 10324/11952 [1:55:22<2:40:30, 5.92s/it] 86%|████████▋ | 10325/11952 [1:55:28<2:38:26, 5.84s/it] {'loss': 0.4485, 'learning_rate': 9.563269461479307e-07, 'epoch': 0.86} + 86%|████████▋ | 10325/11952 [1:55:28<2:38:26, 5.84s/it] 86%|████████▋ | 10326/11952 [1:55:34<2:37:54, 5.83s/it] {'loss': 0.4653, 'learning_rate': 9.551708129655635e-07, 'epoch': 0.86} + 86%|████████▋ | 10326/11952 [1:55:34<2:37:54, 5.83s/it] 86%|████████▋ | 10327/11952 [1:55:39<2:38:22, 5.85s/it] {'loss': 0.46, 'learning_rate': 9.54015343997834e-07, 'epoch': 0.86} + 86%|████████▋ | 10327/11952 [1:55:39<2:38:22, 5.85s/it] 86%|████████▋ | 10328/11952 [1:55:46<2:44:27, 6.08s/it] {'loss': 0.4716, 'learning_rate': 9.528605393295909e-07, 'epoch': 0.86} + 86%|████████▋ | 10328/11952 [1:55:46<2:44:27, 6.08s/it] 86%|████████▋ | 10329/11952 [1:55:52<2:43:58, 6.06s/it] {'loss': 0.4637, 'learning_rate': 9.517063990456399e-07, 'epoch': 0.86} + 86%|████████▋ | 10329/11952 [1:55:52<2:43:58, 6.06s/it] 86%|████████▋ | 10330/11952 [1:55:58<2:42:55, 6.03s/it] {'loss': 0.4507, 'learning_rate': 9.505529232307376e-07, 'epoch': 0.86} + 86%|████████▋ | 10330/11952 [1:55:58<2:42:55, 6.03s/it] 86%|████████▋ | 10331/11952 [1:56:04<2:42:26, 6.01s/it] {'loss': 0.4772, 'learning_rate': 9.494001119695884e-07, 'epoch': 0.86} + 86%|████████▋ | 10331/11952 [1:56:04<2:42:26, 6.01s/it] 86%|████████▋ | 10332/11952 [1:56:10<2:40:00, 5.93s/it] {'loss': 0.4558, 'learning_rate': 9.482479653468512e-07, 'epoch': 0.86} + 86%|████████▋ | 10332/11952 [1:56:10<2:40:00, 5.93s/it] 86%|████████▋ | 10333/11952 [1:56:16<2:39:51, 5.92s/it] {'loss': 0.4491, 'learning_rate': 9.47096483447133e-07, 'epoch': 0.86} + 86%|████████▋ | 10333/11952 [1:56:16<2:39:51, 5.92s/it] 86%|████████▋ | 10334/11952 [1:56:22<2:39:33, 5.92s/it] {'loss': 0.4573, 'learning_rate': 9.459456663549959e-07, 'epoch': 0.86} + 86%|████████▋ | 10334/11952 [1:56:22<2:39:33, 5.92s/it] 86%|████████▋ | 10335/11952 [1:56:27<2:37:18, 5.84s/it] {'loss': 0.4429, 'learning_rate': 9.447955141549514e-07, 'epoch': 0.86} + 86%|████████▋ | 10335/11952 [1:56:27<2:37:18, 5.84s/it] 86%|████████▋ | 10336/11952 [1:56:33<2:38:59, 5.90s/it] {'loss': 0.4629, 'learning_rate': 9.436460269314607e-07, 'epoch': 0.86} + 86%|████████▋ | 10336/11952 [1:56:33<2:38:59, 5.90s/it] 86%|████████▋ | 10337/11952 [1:56:39<2:38:24, 5.89s/it] {'loss': 0.4625, 'learning_rate': 9.424972047689374e-07, 'epoch': 0.86} + 86%|████████▋ | 10337/11952 [1:56:39<2:38:24, 5.89s/it] 86%|████████▋ | 10338/11952 [1:56:45<2:39:18, 5.92s/it] {'loss': 0.4684, 'learning_rate': 9.413490477517462e-07, 'epoch': 0.86} + 86%|████████▋ | 10338/11952 [1:56:45<2:39:18, 5.92s/it] 87%|████████▋ | 10339/11952 [1:56:51<2:37:54, 5.87s/it] {'loss': 0.4807, 'learning_rate': 9.402015559642019e-07, 'epoch': 0.87} + 87%|████████▋ | 10339/11952 [1:56:51<2:37:54, 5.87s/it] 87%|████████▋ | 10340/11952 [1:56:57<2:39:14, 5.93s/it] {'loss': 0.4669, 'learning_rate': 9.390547294905739e-07, 'epoch': 0.87} + 87%|████████▋ | 10340/11952 [1:56:57<2:39:14, 5.93s/it] 87%|████████▋ | 10341/11952 [1:57:03<2:38:52, 5.92s/it] {'loss': 0.4493, 'learning_rate': 9.379085684150779e-07, 'epoch': 0.87} + 87%|████████▋ | 10341/11952 [1:57:03<2:38:52, 5.92s/it] 87%|████████▋ | 10342/11952 [1:57:09<2:40:31, 5.98s/it] {'loss': 0.4639, 'learning_rate': 9.367630728218868e-07, 'epoch': 0.87} + 87%|████████▋ | 10342/11952 [1:57:09<2:40:31, 5.98s/it] 87%|████████▋ | 10343/11952 [1:57:15<2:40:51, 6.00s/it] {'loss': 0.4678, 'learning_rate': 9.356182427951188e-07, 'epoch': 0.87} + 87%|████████▋ | 10343/11952 [1:57:15<2:40:51, 6.00s/it] 87%|████████▋ | 10344/11952 [1:57:21<2:37:45, 5.89s/it] {'loss': 0.4619, 'learning_rate': 9.344740784188445e-07, 'epoch': 0.87} + 87%|████████▋ | 10344/11952 [1:57:21<2:37:45, 5.89s/it] 87%|████████▋ | 10345/11952 [1:57:26<2:35:47, 5.82s/it] {'loss': 0.489, 'learning_rate': 9.333305797770887e-07, 'epoch': 0.87} + 87%|████████▋ | 10345/11952 [1:57:26<2:35:47, 5.82s/it] 87%|████████▋ | 10346/11952 [1:57:32<2:36:03, 5.83s/it] {'loss': 0.4565, 'learning_rate': 9.321877469538232e-07, 'epoch': 0.87} + 87%|████████▋ | 10346/11952 [1:57:32<2:36:03, 5.83s/it] 87%|████████▋ | 10347/11952 [1:57:38<2:35:37, 5.82s/it] {'loss': 0.4754, 'learning_rate': 9.31045580032972e-07, 'epoch': 0.87} + 87%|████████▋ | 10347/11952 [1:57:38<2:35:37, 5.82s/it] 87%|████████▋ | 10348/11952 [1:57:44<2:36:03, 5.84s/it] {'loss': 0.4564, 'learning_rate': 9.299040790984137e-07, 'epoch': 0.87} + 87%|████████▋ | 10348/11952 [1:57:44<2:36:03, 5.84s/it] 87%|████████▋ | 10349/11952 [1:57:50<2:36:03, 5.84s/it] {'loss': 0.472, 'learning_rate': 9.287632442339756e-07, 'epoch': 0.87} + 87%|████████▋ | 10349/11952 [1:57:50<2:36:03, 5.84s/it]4 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +03 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... + 87%|████████▋ | 10350/11952 [1:57:56<2:38:34, 5.94s/it] {'loss': 0.4752, 'learning_rate': 9.276230755234328e-07, 'epoch': 0.87} + 87%|████████▋ | 10350/11952 [1:57:56<2:38:34, 5.94s/it] 87%|████████▋ | 10351/11952 [1:58:02<2:39:36, 5.98s/it] {'loss': 0.4529, 'learning_rate': 9.264835730505184e-07, 'epoch': 0.87} + 87%|████████▋ | 10351/11952 [1:58:02<2:39:36, 5.98s/it] 87%|████████▋ | 10352/11952 [1:58:08<2:38:36, 5.95s/it] {'loss': 0.4372, 'learning_rate': 9.25344736898911e-07, 'epoch': 0.87} + 87%|████████▋ | 10352/11952 [1:58:08<2:38:36, 5.95s/it] 87%|████████▋ | 10353/11952 [1:58:14<2:37:36, 5.91s/it] {'loss': 0.4867, 'learning_rate': 9.242065671522393e-07, 'epoch': 0.87} + 87%|████████▋ | 10353/11952 [1:58:14<2:37:36, 5.91s/it] 87%|████████▋ | 10354/11952 [1:58:20<2:38:36, 5.96s/it] {'loss': 0.4552, 'learning_rate': 9.230690638940898e-07, 'epoch': 0.87} + 87%|████████▋ | 10354/11952 [1:58:20<2:38:36, 5.96s/it] 87%|████████▋ | 10355/11952 [1:58:26<2:40:40, 6.04s/it] {'loss': 0.47, 'learning_rate': 9.219322272079955e-07, 'epoch': 0.87} + 87%|████████▋ | 10355/11952 [1:58:26<2:40:40, 6.04s/it] 87%|████████▋ | 10356/11952 [1:58:32<2:37:59, 5.94s/it] {'loss': 0.459, 'learning_rate': 9.207960571774388e-07, 'epoch': 0.87} + 87%|████████▋ | 10356/11952 [1:58:32<2:37:59, 5.94s/it] 87%|████████▋ | 10357/11952 [1:58:37<2:37:44, 5.93s/it] {'loss': 0.4625, 'learning_rate': 9.196605538858571e-07, 'epoch': 0.87} + 87%|████████▋ | 10357/11952 [1:58:37<2:37:44, 5.93s/it] 87%|████████▋ | 10358/11952 [1:58:43<2:38:05, 5.95s/it] {'loss': 0.4528, 'learning_rate': 9.185257174166362e-07, 'epoch': 0.87} + 87%|████████▋ | 10358/11952 [1:58:43<2:38:05, 5.95s/it] 87%|████████▋ | 10359/11952 [1:58:49<2:36:49, 5.91s/it] {'loss': 0.4446, 'learning_rate': 9.173915478531148e-07, 'epoch': 0.87} + 87%|████████▋ | 10359/11952 [1:58:49<2:36:49, 5.91s/it] 87%|████████▋ | 10360/11952 [1:58:55<2:35:37, 5.87s/it] {'loss': 0.477, 'learning_rate': 9.162580452785775e-07, 'epoch': 0.87} + 87%|████████▋ | 10360/11952 [1:58:55<2:35:37, 5.87s/it] 87%|████████▋ | 10361/11952 [1:59:01<2:34:05, 5.81s/it] {'loss': 0.4613, 'learning_rate': 9.151252097762675e-07, 'epoch': 0.87} + 87%|████████▋ | 10361/11952 [1:59:01<2:34:05, 5.81s/it] 87%|████████▋ | 10362/11952 [1:59:07<2:35:47, 5.88s/it] {'loss': 0.4511, 'learning_rate': 9.139930414293774e-07, 'epoch': 0.87} + 87%|████████▋ | 10362/11952 [1:59:07<2:35:47, 5.88s/it] 87%|████████▋ | 10363/11952 [1:59:12<2:34:06, 5.82s/it] {'loss': 0.4492, 'learning_rate': 9.128615403210472e-07, 'epoch': 0.87} + 87%|████████▋ | 10363/11952 [1:59:12<2:34:06, 5.82s/it] 87%|████████▋ | 10364/11952 [1:59:19<2:36:01, 5.89s/it] {'loss': 0.4666, 'learning_rate': 9.117307065343683e-07, 'epoch': 0.87} + 87%|████████▋ | 10364/11952 [1:59:19<2:36:01, 5.89s/it] 87%|████████▋ | 10365/11952 [1:59:25<2:39:14, 6.02s/it] {'loss': 0.4672, 'learning_rate': 9.106005401523865e-07, 'epoch': 0.87} + 87%|████████▋ | 10365/11952 [1:59:25<2:39:14, 6.02s/it] 87%|████████▋ | 10366/11952 [1:59:31<2:39:01, 6.02s/it] {'loss': 0.4787, 'learning_rate': 9.094710412580942e-07, 'epoch': 0.87} + 87%|████████▋ | 10366/11952 [1:59:31<2:39:01, 6.02s/it] 87%|████████▋ | 10367/11952 [1:59:37<2:38:43, 6.01s/it] {'loss': 0.4664, 'learning_rate': 9.083422099344375e-07, 'epoch': 0.87} + 87%|████████▋ | 10367/11952 [1:59:37<2:38:43, 6.01s/it] 87%|████████▋ | 10368/11952 [1:59:43<2:41:46, 6.13s/it] {'loss': 0.4515, 'learning_rate': 9.072140462643154e-07, 'epoch': 0.87} + 87%|████████▋ | 10368/11952 [1:59:43<2:41:46, 6.13s/it] 87%|████████▋ | 10369/11952 [1:59:50<2:42:43, 6.17s/it] {'loss': 0.4508, 'learning_rate': 9.060865503305738e-07, 'epoch': 0.87} + 87%|████████▋ | 10369/11952 [1:59:50<2:42:43, 6.17s/it] 87%|████████▋ | 10370/11952 [1:59:55<2:40:25, 6.08s/it] {'loss': 0.4644, 'learning_rate': 9.049597222160111e-07, 'epoch': 0.87} + 87%|████████▋ | 10370/11952 [1:59:55<2:40:25, 6.08s/it] 87%|████████▋ | 10371/11952 [2:00:01<2:37:57, 5.99s/it] {'loss': 0.4454, 'learning_rate': 9.038335620033756e-07, 'epoch': 0.87} + 87%|████████▋ | 10371/11952 [2:00:01<2:37:57, 5.99s/it] 87%|████████▋ | 10372/11952 [2:00:07<2:37:31, 5.98s/it] {'loss': 0.4649, 'learning_rate': 9.02708069775372e-07, 'epoch': 0.87} + 87%|████████▋ | 10372/11952 [2:00:07<2:37:31, 5.98s/it] 87%|████████▋ | 10373/11952 [2:00:13<2:39:39, 6.07s/it] {'loss': 0.4778, 'learning_rate': 9.015832456146489e-07, 'epoch': 0.87} + 87%|████████▋ | 10373/11952 [2:00:13<2:39:39, 6.07s/it] 87%|████████▋ | 10374/11952 [2:00:19<2:36:58, 5.97s/it] {'loss': 0.4462, 'learning_rate': 9.004590896038068e-07, 'epoch': 0.87} + 87%|████████▋ | 10374/11952 [2:00:19<2:36:58, 5.97s/it] 87%|████████▋ | 10375/11952 [2:00:25<2:34:51, 5.89s/it] {'loss': 0.4462, 'learning_rate': 8.99335601825404e-07, 'epoch': 0.87} + 87%|████████▋ | 10375/11952 [2:00:25<2:34:51, 5.89s/it] 87%|████████▋ | 10376/11952 [2:00:31<2:34:57, 5.90s/it] {'loss': 0.4594, 'learning_rate': 8.982127823619413e-07, 'epoch': 0.87} + 87%|████████▋ | 10376/11952 [2:00:31<2:34:57, 5.90s/it] 87%|████████▋ | 10377/11952 [2:00:37<2:38:22, 6.03s/it] {'loss': 0.4522, 'learning_rate': 8.970906312958749e-07, 'epoch': 0.87} + 87%|████████▋ | 10377/11952 [2:00:37<2:38:22, 6.03s/it] 87%|████████▋ | 10378/11952 [2:00:43<2:36:09, 5.95s/it] {'loss': 0.482, 'learning_rate': 8.959691487096111e-07, 'epoch': 0.87} + 87%|████████▋ | 10378/11952 [2:00:43<2:36:09, 5.95s/it] 87%|████████▋ | 10379/11952 [2:00:49<2:36:51, 5.98s/it] {'loss': 0.4502, 'learning_rate': 8.948483346855064e-07, 'epoch': 0.87} + 87%|████████▋ | 10379/11952 [2:00:49<2:36:51, 5.98s/it] 87%|████████▋ | 10380/11952 [2:00:55<2:35:11, 5.92s/it] {'loss': 0.4623, 'learning_rate': 8.937281893058658e-07, 'epoch': 0.87} + 87%|████████▋ | 10380/11952 [2:00:55<2:35:11, 5.92s/it] 87%|████████▋ | 10381/11952 [2:01:01<2:38:09, 6.04s/it] {'loss': 0.4559, 'learning_rate': 8.926087126529548e-07, 'epoch': 0.87} + 87%|████████▋ | 10381/11952 [2:01:01<2:38:09, 6.04s/it] 87%|████████▋ | 10382/11952 [2:01:07<2:37:44, 6.03s/it] {'loss': 0.4734, 'learning_rate': 8.914899048089765e-07, 'epoch': 0.87} + 87%|████████▋ | 10382/11952 [2:01:07<2:37:44, 6.03s/it] 87%|████████▋ | 10383/11952 [2:01:13<2:35:41, 5.95s/it] {'loss': 0.4638, 'learning_rate': 8.903717658560961e-07, 'epoch': 0.87} + 87%|████████▋ | 10383/11952 [2:01:13<2:35:41, 5.95s/it] 87%|████████▋ | 10384/11952 [2:01:18<2:32:59, 5.85s/it] {'loss': 0.4368, 'learning_rate': 8.892542958764238e-07, 'epoch': 0.87} + 87%|████████▋ | 10384/11952 [2:01:18<2:32:59, 5.85s/it] 87%|████████▋ | 10385/11952 [2:01:25<2:35:17, 5.95s/it] {'loss': 0.4844, 'learning_rate': 8.881374949520216e-07, 'epoch': 0.87} + 87%|████████▋ | 10385/11952 [2:01:25<2:35:17, 5.95s/it] 87%|████████▋ | 10386/11952 [2:01:31<2:35:22, 5.95s/it] {'loss': 0.4673, 'learning_rate': 8.870213631649038e-07, 'epoch': 0.87} + 87%|████████▋ | 10386/11952 [2:01:31<2:35:22, 5.95s/it] 87%|████████▋ | 10387/11952 [2:01:37<2:36:17, 5.99s/it] {'loss': 0.4555, 'learning_rate': 8.859059005970305e-07, 'epoch': 0.87} + 87%|████████▋ | 10387/11952 [2:01:37<2:36:17, 5.99s/it] 87%|████████▋ | 10388/11952 [2:01:43<2:36:43, 6.01s/it] {'loss': 0.4701, 'learning_rate': 8.847911073303206e-07, 'epoch': 0.87} + 87%|████████▋ | 10388/11952 [2:01:43<2:36:43, 6.01s/it] 87%|████████▋ | 10389/11952 [2:01:49<2:39:04, 6.11s/it] {'loss': 0.4677, 'learning_rate': 8.836769834466397e-07, 'epoch': 0.87} + 87%|████████▋ | 10389/11952 [2:01:49<2:39:04, 6.11s/it] 87%|████████▋ | 10390/11952 [2:01:55<2:38:14, 6.08s/it] {'loss': 0.4631, 'learning_rate': 8.825635290278034e-07, 'epoch': 0.87} + 87%|████████▋ | 10390/11952 [2:01:55<2:38:14, 6.08s/it] 87%|████████▋ | 10391/11952 [2:02:01<2:37:02, 6.04s/it] {'loss': 0.4691, 'learning_rate': 8.814507441555775e-07, 'epoch': 0.87} + 87%|████████▋ | 10391/11952 [2:02:01<2:37:02, 6.04s/it] 87%|████████▋ | 10392/11952 [2:02:07<2:34:57, 5.96s/it] {'loss': 0.4743, 'learning_rate': 8.803386289116833e-07, 'epoch': 0.87} + 87%|████████▋ | 10392/11952 [2:02:07<2:34:57, 5.96s/it] 87%|████████▋ | 10393/11952 [2:02:13<2:35:08, 5.97s/it] {'loss': 0.4724, 'learning_rate': 8.792271833777888e-07, 'epoch': 0.87} + 87%|████████▋ | 10393/11952 [2:02:13<2:35:08, 5.97s/it] 87%|████████▋ | 10394/11952 [2:02:19<2:34:14, 5.94s/it] {'loss': 0.4461, 'learning_rate': 8.78116407635512e-07, 'epoch': 0.87} + 87%|████████▋ | 10394/11952 [2:02:19<2:34:14, 5.94s/it] 87%|████████▋ | 10395/11952 [2:02:25<2:34:56, 5.97s/it] {'loss': 0.4705, 'learning_rate': 8.770063017664276e-07, 'epoch': 0.87} + 87%|████████▋ | 10395/11952 [2:02:25<2:34:56, 5.97s/it] 87%|████████▋ | 10396/11952 [2:02:31<2:35:29, 6.00s/it] {'loss': 0.4547, 'learning_rate': 8.75896865852055e-07, 'epoch': 0.87} + 87%|████████▋ | 10396/11952 [2:02:31<2:35:29, 6.00s/it] 87%|████████▋ | 10397/11952 [2:02:37<2:33:47, 5.93s/it] {'loss': 0.4837, 'learning_rate': 8.747880999738667e-07, 'epoch': 0.87} + 87%|████████▋ | 10397/11952 [2:02:37<2:33:47, 5.93s/it] 87%|████████▋ | 10398/11952 [2:02:42<2:32:47, 5.90s/it] {'loss': 0.4696, 'learning_rate': 8.736800042132853e-07, 'epoch': 0.87} + 87%|████████▋ | 10398/11952 [2:02:42<2:32:47, 5.90s/it] 87%|████████▋ | 10399/11952 [2:02:49<2:35:25, 6.01s/it] {'loss': 0.4605, 'learning_rate': 8.725725786516858e-07, 'epoch': 0.87} + 87%|████████▋ | 10399/11952 [2:02:49<2:35:25, 6.01s/it]0 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... + 87%|████████▋ | 10400/11952 [2:02:55<2:36:18, 6.04s/it]6 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4868, 'learning_rate': 8.714658233703921e-07, 'epoch': 0.87} + 87%|████████▋ | 10400/11952 [2:02:55<2:36:18, 6.04s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-10400/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-10400/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/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( + 87%|████████▋ | 10401/11952 [2:03:25<5:42:51, 13.26s/it] {'loss': 0.4542, 'learning_rate': 8.703597384506779e-07, 'epoch': 0.87} + 87%|████████▋ | 10401/11952 [2:03:25<5:42:51, 13.26s/it] 87%|████████▋ | 10402/11952 [2:03:31<4:47:07, 11.11s/it] {'loss': 0.4542, 'learning_rate': 8.692543239737706e-07, 'epoch': 0.87} + 87%|████████▋ | 10402/11952 [2:03:31<4:47:07, 11.11s/it] 87%|████████▋ | 10403/11952 [2:03:37<4:04:52, 9.49s/it] {'loss': 0.4587, 'learning_rate': 8.681495800208517e-07, 'epoch': 0.87} + 87%|████████▋ | 10403/11952 [2:03:37<4:04:52, 9.49s/it] 87%|████████▋ | 10404/11952 [2:03:43<3:38:04, 8.45s/it] {'loss': 0.4659, 'learning_rate': 8.670455066730444e-07, 'epoch': 0.87} + 87%|████████▋ | 10404/11952 [2:03:43<3:38:04, 8.45s/it] 87%|████████▋ | 10405/11952 [2:03:49<3:18:40, 7.71s/it] {'loss': 0.474, 'learning_rate': 8.65942104011428e-07, 'epoch': 0.87} + 87%|████████▋ | 10405/11952 [2:03:49<3:18:40, 7.71s/it] 87%|████████▋ | 10406/11952 [2:03:55<3:07:07, 7.26s/it] {'loss': 0.4734, 'learning_rate': 8.648393721170323e-07, 'epoch': 0.87} + 87%|████████▋ | 10406/11952 [2:03:55<3:07:07, 7.26s/it] 87%|████████▋ | 10407/11952 [2:04:01<2:57:32, 6.90s/it] {'loss': 0.4765, 'learning_rate': 8.63737311070837e-07, 'epoch': 0.87} + 87%|████████▋ | 10407/11952 [2:04:01<2:57:32, 6.90s/it] 87%|████████▋ | 10408/11952 [2:04:07<2:49:39, 6.59s/it] {'loss': 0.4577, 'learning_rate': 8.626359209537716e-07, 'epoch': 0.87} + 87%|████████▋ | 10408/11952 [2:04:07<2:49:39, 6.59s/it] 87%|████████▋ | 10409/11952 [2:04:13<2:44:31, 6.40s/it] {'loss': 0.4625, 'learning_rate': 8.615352018467204e-07, 'epoch': 0.87} + 87%|████████▋ | 10409/11952 [2:04:13<2:44:31, 6.40s/it] 87%|████████▋ | 10410/11952 [2:04:19<2:41:30, 6.28s/it] {'loss': 0.4697, 'learning_rate': 8.604351538305156e-07, 'epoch': 0.87} + 87%|████████▋ | 10410/11952 [2:04:19<2:41:30, 6.28s/it] 87%|████████▋ | 10411/11952 [2:04:24<2:36:27, 6.09s/it] {'loss': 0.4622, 'learning_rate': 8.593357769859368e-07, 'epoch': 0.87} + 87%|████████▋ | 10411/11952 [2:04:24<2:36:27, 6.09s/it] 87%|████████▋ | 10412/11952 [2:04:30<2:35:15, 6.05s/it] {'loss': 0.4769, 'learning_rate': 8.582370713937193e-07, 'epoch': 0.87} + 87%|████████▋ | 10412/11952 [2:04:30<2:35:15, 6.05s/it] 87%|████████▋ | 10413/11952 [2:04:36<2:32:59, 5.96s/it] {'loss': 0.4899, 'learning_rate': 8.571390371345489e-07, 'epoch': 0.87} + 87%|████████▋ | 10413/11952 [2:04:36<2:32:59, 5.96s/it] 87%|████████▋ | 10414/11952 [2:04:42<2:33:43, 6.00s/it] {'loss': 0.4746, 'learning_rate': 8.560416742890599e-07, 'epoch': 0.87} + 87%|████████▋ | 10414/11952 [2:04:42<2:33:43, 6.00s/it] 87%|████████▋ | 10415/11952 [2:04:48<2:36:06, 6.09s/it] {'loss': 0.4566, 'learning_rate': 8.549449829378354e-07, 'epoch': 0.87} + 87%|████████▋ | 10415/11952 [2:04:48<2:36:06, 6.09s/it] 87%|████████▋ | 10416/11952 [2:04:54<2:34:52, 6.05s/it] {'loss': 0.4804, 'learning_rate': 8.538489631614167e-07, 'epoch': 0.87} + 87%|████████▋ | 10416/11952 [2:04:54<2:34:52, 6.05s/it] 87%|████████▋ | 10417/11952 [2:05:01<2:35:22, 6.07s/it] {'loss': 0.4592, 'learning_rate': 8.527536150402882e-07, 'epoch': 0.87} + 87%|████████▋ | 10417/11952 [2:05:01<2:35:22, 6.07s/it] 87%|████████▋ | 10418/11952 [2:05:06<2:33:52, 6.02s/it] {'loss': 0.4471, 'learning_rate': 8.516589386548879e-07, 'epoch': 0.87} + 87%|████████▋ | 10418/11952 [2:05:06<2:33:52, 6.02s/it] 87%|████████▋ | 10419/11952 [2:05:13<2:36:37, 6.13s/it] {'loss': 0.4799, 'learning_rate': 8.505649340856048e-07, 'epoch': 0.87} + 87%|████████▋ | 10419/11952 [2:05:13<2:36:37, 6.13s/it] 87%|████████▋ | 10420/11952 [2:05:19<2:37:05, 6.15s/it] {'loss': 0.4877, 'learning_rate': 8.494716014127768e-07, 'epoch': 0.87} + 87%|████████▋ | 10420/11952 [2:05:19<2:37:05, 6.15s/it] 87%|████████▋ | 10421/11952 [2:05:25<2:35:20, 6.09s/it] {'loss': 0.4582, 'learning_rate': 8.483789407166932e-07, 'epoch': 0.87} + 87%|████████▋ | 10421/11952 [2:05:25<2:35:20, 6.09s/it] 87%|████████▋ | 10422/11952 [2:05:31<2:33:33, 6.02s/it] {'loss': 0.4554, 'learning_rate': 8.472869520775972e-07, 'epoch': 0.87} + 87%|████████▋ | 10422/11952 [2:05:31<2:33:33, 6.02s/it] 87%|████████▋ | 10423/11952 [2:05:37<2:30:41, 5.91s/it] {'loss': 0.4487, 'learning_rate': 8.461956355756772e-07, 'epoch': 0.87} + 87%|████████▋ | 10423/11952 [2:05:37<2:30:41, 5.91s/it] 87%|████████▋ | 10424/11952 [2:05:42<2:30:20, 5.90s/it] {'loss': 0.4454, 'learning_rate': 8.451049912910769e-07, 'epoch': 0.87} + 87%|████████▋ | 10424/11952 [2:05:42<2:30:20, 5.90s/it] 87%|████████▋ | 10425/11952 [2:05:48<2:29:51, 5.89s/it] {'loss': 0.4578, 'learning_rate': 8.440150193038888e-07, 'epoch': 0.87} + 87%|████████▋ | 10425/11952 [2:05:48<2:29:51, 5.89s/it] 87%|████████▋ | 10426/11952 [2:05:54<2:29:46, 5.89s/it] {'loss': 0.4786, 'learning_rate': 8.429257196941554e-07, 'epoch': 0.87} + 87%|████████▋ | 10426/11952 [2:05:54<2:29:46, 5.89s/it] 87%|████████▋ | 10427/11952 [2:06:00<2:27:57, 5.82s/it] {'loss': 0.4635, 'learning_rate': 8.418370925418695e-07, 'epoch': 0.87} + 87%|████████▋ | 10427/11952 [2:06:00<2:27:57, 5.82s/it] 87%|████████▋ | 10428/11952 [2:06:05<2:26:46, 5.78s/it] {'loss': 0.4748, 'learning_rate': 8.407491379269739e-07, 'epoch': 0.87} + 87%|████████▋ | 10428/11952 [2:06:05<2:26:46, 5.78s/it] 87%|████████▋ | 10429/11952 [2:06:12<2:30:05, 5.91s/it] {'loss': 0.4652, 'learning_rate': 8.396618559293679e-07, 'epoch': 0.87} + 87%|████████▋ | 10429/11952 [2:06:12<2:30:05, 5.91s/it] 87%|████████▋ | 10430/11952 [2:06:18<2:29:46, 5.90s/it] {'loss': 0.4624, 'learning_rate': 8.385752466288933e-07, 'epoch': 0.87} + 87%|████████▋ | 10430/11952 [2:06:18<2:29:46, 5.90s/it] 87%|████████▋ | 10431/11952 [2:06:23<2:28:45, 5.87s/it] {'loss': 0.4563, 'learning_rate': 8.374893101053482e-07, 'epoch': 0.87} + 87%|████████▋ | 10431/11952 [2:06:23<2:28:45, 5.87s/it] 87%|████████▋ | 10432/11952 [2:06:29<2:28:57, 5.88s/it] {'loss': 0.4677, 'learning_rate': 8.364040464384771e-07, 'epoch': 0.87} + 87%|████████▋ | 10432/11952 [2:06:29<2:28:57, 5.88s/it] 87%|████████▋ | 10433/11952 [2:06:35<2:28:50, 5.88s/it] {'loss': 0.4588, 'learning_rate': 8.353194557079791e-07, 'epoch': 0.87} + 87%|████████▋ | 10433/11952 [2:06:35<2:28:50, 5.88s/it] 87%|████████▋ | 10434/11952 [2:06:41<2:28:20, 5.86s/it] {'loss': 0.4498, 'learning_rate': 8.34235537993503e-07, 'epoch': 0.87} + 87%|████████▋ | 10434/11952 [2:06:41<2:28:20, 5.86s/it] 87%|████████▋ | 10435/11952 [2:06:47<2:26:53, 5.81s/it] {'loss': 0.4734, 'learning_rate': 8.331522933746428e-07, 'epoch': 0.87} + 87%|████████▋ | 10435/11952 [2:06:47<2:26:53, 5.81s/it] 87%|████████▋ | 10436/11952 [2:06:53<2:27:20, 5.83s/it] {'loss': 0.4523, 'learning_rate': 8.320697219309526e-07, 'epoch': 0.87} + 87%|████████▋ | 10436/11952 [2:06:53<2:27:20, 5.83s/it] 87%|████████▋ | 10437/11952 [2:06:58<2:25:46, 5.77s/it] {'loss': 0.4687, 'learning_rate': 8.309878237419289e-07, 'epoch': 0.87} + 87%|████████▋ | 10437/11952 [2:06:58<2:25:46, 5.77s/it] 87%|████████▋ | 10438/11952 [2:07:04<2:29:26, 5.92s/it] {'loss': 0.4675, 'learning_rate': 8.299065988870236e-07, 'epoch': 0.87} + 87%|████████▋ | 10438/11952 [2:07:04<2:29:26, 5.92s/it] 87%|████████▋ | 10439/11952 [2:07:10<2:27:32, 5.85s/it] {'loss': 0.4673, 'learning_rate': 8.288260474456367e-07, 'epoch': 0.87} + 87%|████████▋ | 10439/11952 [2:07:10<2:27:32, 5.85s/it] 87%|████████▋ | 10440/11952 [2:07:16<2:26:05, 5.80s/it] {'loss': 0.4436, 'learning_rate': 8.277461694971178e-07, 'epoch': 0.87} + 87%|████████▋ | 10440/11952 [2:07:16<2:26:05, 5.80s/it] 87%|████████▋ | 10441/11952 [2:07:22<2:26:30, 5.82s/it] {'loss': 0.4659, 'learning_rate': 8.266669651207704e-07, 'epoch': 0.87} + 87%|████████▋ | 10441/11952 [2:07:22<2:26:30, 5.82s/it] 87%|████████▋ | 10442/11952 [2:07:28<2:29:44, 5.95s/it] {'loss': 0.4867, 'learning_rate': 8.255884343958453e-07, 'epoch': 0.87} + 87%|████████▋ | 10442/11952 [2:07:28<2:29:44, 5.95s/it] 87%|████████▋ | 10443/11952 [2:07:34<2:30:56, 6.00s/it] {'loss': 0.4468, 'learning_rate': 8.245105774015461e-07, 'epoch': 0.87} + 87%|████████▋ | 10443/11952 [2:07:34<2:30:56, 6.00s/it] 87%|████████▋ | 10444/11952 [2:07:40<2:28:31, 5.91s/it] {'loss': 0.4678, 'learning_rate': 8.234333942170281e-07, 'epoch': 0.87} + 87%|████████▋ | 10444/11952 [2:07:40<2:28:31, 5.91s/it] 87%|████████▋ | 10445/11952 [2:07:45<2:25:39, 5.80s/it] {'loss': 0.4726, 'learning_rate': 8.223568849213925e-07, 'epoch': 0.87} + 87%|████████▋ | 10445/11952 [2:07:45<2:25:39, 5.80s/it] 87%|████████▋ | 10446/11952 [2:07:51<2:25:40, 5.80s/it] {'loss': 0.4651, 'learning_rate': 8.212810495936952e-07, 'epoch': 0.87} + 87%|████████▋ | 10446/11952 [2:07:51<2:25:40, 5.80s/it] 87%|████████▋ | 10447/11952 [2:07:57<2:27:15, 5.87s/it] {'loss': 0.474, 'learning_rate': 8.202058883129404e-07, 'epoch': 0.87} + 87%|████████▋ | 10447/11952 [2:07:57<2:27:15, 5.87s/it] 87%|████████▋ | 10448/11952 [2:08:03<2:29:20, 5.96s/it] {'loss': 0.4809, 'learning_rate': 8.191314011580842e-07, 'epoch': 0.87} + 87%|████████▋ | 10448/11952 [2:08:03<2:29:20, 5.96s/it] 87%|████████▋ | 10449/11952 [2:08:09<2:27:33, 5.89s/it] {'loss': 0.4541, 'learning_rate': 8.180575882080288e-07, 'epoch': 0.87} + 87%|████████▋ | 10449/11952 [2:08:09<2:27:33, 5.89s/it]4 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... +0 AutoResumeHook: Checking whether to suspend... + 87%|████████▋ | 10450/11952 [2:08:15<2:26:20, 5.85s/it] {'loss': 0.4656, 'learning_rate': 8.169844495416368e-07, 'epoch': 0.87} + 87%|████████▋ | 10450/11952 [2:08:15<2:26:20, 5.85s/it] 87%|████████▋ | 10451/11952 [2:08:21<2:26:54, 5.87s/it] {'loss': 0.4456, 'learning_rate': 8.159119852377106e-07, 'epoch': 0.87} + 87%|████████▋ | 10451/11952 [2:08:21<2:26:54, 5.87s/it] 87%|████████▋ | 10452/11952 [2:08:27<2:28:41, 5.95s/it] {'loss': 0.4625, 'learning_rate': 8.148401953750096e-07, 'epoch': 0.87} + 87%|████████▋ | 10452/11952 [2:08:27<2:28:41, 5.95s/it] 87%|████████▋ | 10453/11952 [2:08:33<2:29:42, 5.99s/it] {'loss': 0.4638, 'learning_rate': 8.137690800322384e-07, 'epoch': 0.87} + 87%|████████▋ | 10453/11952 [2:08:33<2:29:42, 5.99s/it] 87%|████████▋ | 10454/11952 [2:08:39<2:29:54, 6.00s/it] {'loss': 0.4811, 'learning_rate': 8.126986392880587e-07, 'epoch': 0.87} + 87%|████████▋ | 10454/11952 [2:08:39<2:29:54, 6.00s/it] 87%|████████▋ | 10455/11952 [2:08:45<2:32:08, 6.10s/it] {'loss': 0.4776, 'learning_rate': 8.116288732210787e-07, 'epoch': 0.87} + 87%|████████▋ | 10455/11952 [2:08:45<2:32:08, 6.10s/it] 87%|████████▋ | 10456/11952 [2:08:51<2:30:56, 6.05s/it] {'loss': 0.4533, 'learning_rate': 8.105597819098554e-07, 'epoch': 0.87} + 87%|████████▋ | 10456/11952 [2:08:51<2:30:56, 6.05s/it] 87%|████████▋ | 10457/11952 [2:08:57<2:28:58, 5.98s/it] {'loss': 0.4689, 'learning_rate': 8.094913654329018e-07, 'epoch': 0.87} + 87%|████████▋ | 10457/11952 [2:08:57<2:28:58, 5.98s/it] 88%|████████▊ | 10458/11952 [2:09:03<2:28:10, 5.95s/it] {'loss': 0.4605, 'learning_rate': 8.08423623868676e-07, 'epoch': 0.87} + 88%|████████▊ | 10458/11952 [2:09:03<2:28:10, 5.95s/it] 88%|████████▊ | 10459/11952 [2:09:09<2:29:59, 6.03s/it] {'loss': 0.4652, 'learning_rate': 8.073565572955877e-07, 'epoch': 0.88} + 88%|████████▊ | 10459/11952 [2:09:09<2:29:59, 6.03s/it] 88%|████████▊ | 10460/11952 [2:09:15<2:29:09, 6.00s/it] {'loss': 0.4584, 'learning_rate': 8.062901657919998e-07, 'epoch': 0.88} + 88%|████████▊ | 10460/11952 [2:09:15<2:29:09, 6.00s/it] 88%|████████▊ | 10461/11952 [2:09:21<2:28:43, 5.98s/it] {'loss': 0.4699, 'learning_rate': 8.052244494362227e-07, 'epoch': 0.88} + 88%|████████▊ | 10461/11952 [2:09:21<2:28:43, 5.98s/it] 88%|████████▊ | 10462/11952 [2:09:27<2:30:17, 6.05s/it] {'loss': 0.4525, 'learning_rate': 8.041594083065152e-07, 'epoch': 0.88} + 88%|████████▊ | 10462/11952 [2:09:27<2:30:17, 6.05s/it] 88%|████████▊ | 10463/11952 [2:09:33<2:28:06, 5.97s/it] {'loss': 0.476, 'learning_rate': 8.030950424810946e-07, 'epoch': 0.88} + 88%|████████▊ | 10463/11952 [2:09:33<2:28:06, 5.97s/it] 88%|████████▊ | 10464/11952 [2:09:39<2:26:08, 5.89s/it] {'loss': 0.4795, 'learning_rate': 8.020313520381206e-07, 'epoch': 0.88} + 88%|████████▊ | 10464/11952 [2:09:39<2:26:08, 5.89s/it] 88%|████████▊ | 10465/11952 [2:09:44<2:25:17, 5.86s/it] {'loss': 0.4751, 'learning_rate': 8.009683370557075e-07, 'epoch': 0.88} + 88%|████████▊ | 10465/11952 [2:09:44<2:25:17, 5.86s/it] 88%|████████▊ | 10466/11952 [2:09:51<2:27:07, 5.94s/it] {'loss': 0.4427, 'learning_rate': 7.999059976119183e-07, 'epoch': 0.88} + 88%|████████▊ | 10466/11952 [2:09:51<2:27:07, 5.94s/it] 88%|████████▊ | 10467/11952 [2:09:56<2:25:03, 5.86s/it] {'loss': 0.4616, 'learning_rate': 7.988443337847673e-07, 'epoch': 0.88} + 88%|████████▊ | 10467/11952 [2:09:56<2:25:03, 5.86s/it] 88%|████████▊ | 10468/11952 [2:10:02<2:26:02, 5.90s/it] {'loss': 0.4687, 'learning_rate': 7.977833456522166e-07, 'epoch': 0.88} + 88%|████████▊ | 10468/11952 [2:10:02<2:26:02, 5.90s/it] 88%|████████▊ | 10469/11952 [2:10:09<2:29:31, 6.05s/it] {'loss': 0.4731, 'learning_rate': 7.967230332921816e-07, 'epoch': 0.88} + 88%|████████▊ | 10469/11952 [2:10:09<2:29:31, 6.05s/it] 88%|████████▊ | 10470/11952 [2:10:15<2:30:46, 6.10s/it] {'loss': 0.4715, 'learning_rate': 7.956633967825289e-07, 'epoch': 0.88} + 88%|████████▊ | 10470/11952 [2:10:15<2:30:46, 6.10s/it] 88%|████████▊ | 10471/11952 [2:10:21<2:29:12, 6.05s/it] {'loss': 0.4532, 'learning_rate': 7.946044362010718e-07, 'epoch': 0.88} + 88%|████████▊ | 10471/11952 [2:10:21<2:29:12, 6.05s/it] 88%|████████▊ | 10472/11952 [2:10:27<2:30:38, 6.11s/it] {'loss': 0.4768, 'learning_rate': 7.935461516255782e-07, 'epoch': 0.88} + 88%|████████▊ | 10472/11952 [2:10:27<2:30:38, 6.11s/it] 88%|████████▊ | 10473/11952 [2:10:33<2:31:12, 6.13s/it] {'loss': 0.4527, 'learning_rate': 7.924885431337604e-07, 'epoch': 0.88} + 88%|████████▊ | 10473/11952 [2:10:33<2:31:12, 6.13s/it] 88%|████████▊ | 10474/11952 [2:10:39<2:31:41, 6.16s/it] {'loss': 0.4693, 'learning_rate': 7.914316108032882e-07, 'epoch': 0.88} + 88%|████████▊ | 10474/11952 [2:10:39<2:31:41, 6.16s/it] 88%|████████▊ | 10475/11952 [2:10:46<2:30:50, 6.13s/it] {'loss': 0.4768, 'learning_rate': 7.903753547117788e-07, 'epoch': 0.88} + 88%|████████▊ | 10475/11952 [2:10:46<2:30:50, 6.13s/it] 88%|████████▊ | 10476/11952 [2:10:51<2:28:06, 6.02s/it] {'loss': 0.4678, 'learning_rate': 7.893197749367943e-07, 'epoch': 0.88} + 88%|████████▊ | 10476/11952 [2:10:51<2:28:06, 6.02s/it] 88%|████████▊ | 10477/11952 [2:10:57<2:26:23, 5.96s/it] {'loss': 0.4589, 'learning_rate': 7.882648715558583e-07, 'epoch': 0.88} + 88%|████████▊ | 10477/11952 [2:10:57<2:26:23, 5.96s/it] 88%|████████▊ | 10478/11952 [2:11:03<2:25:05, 5.91s/it] {'loss': 0.4649, 'learning_rate': 7.872106446464345e-07, 'epoch': 0.88} + 88%|████████▊ | 10478/11952 [2:11:03<2:25:05, 5.91s/it] 88%|████████▊ | 10479/11952 [2:11:09<2:24:37, 5.89s/it] {'loss': 0.4652, 'learning_rate': 7.861570942859431e-07, 'epoch': 0.88} + 88%|████████▊ | 10479/11952 [2:11:09<2:24:37, 5.89s/it] 88%|████████▊ | 10480/11952 [2:11:15<2:26:34, 5.97s/it] {'loss': 0.4853, 'learning_rate': 7.851042205517512e-07, 'epoch': 0.88} + 88%|████████▊ | 10480/11952 [2:11:15<2:26:34, 5.97s/it] 88%|████████▊ | 10481/11952 [2:11:21<2:27:46, 6.03s/it] {'loss': 0.4503, 'learning_rate': 7.840520235211768e-07, 'epoch': 0.88} + 88%|████████▊ | 10481/11952 [2:11:21<2:27:46, 6.03s/it] 88%|████████▊ | 10482/11952 [2:11:27<2:24:55, 5.92s/it] {'loss': 0.463, 'learning_rate': 7.830005032714905e-07, 'epoch': 0.88} + 88%|████████▊ | 10482/11952 [2:11:27<2:24:55, 5.92s/it] 88%|████████▊ | 10483/11952 [2:11:33<2:25:28, 5.94s/it] {'loss': 0.4523, 'learning_rate': 7.819496598799093e-07, 'epoch': 0.88} + 88%|████████▊ | 10483/11952 [2:11:33<2:25:28, 5.94s/it] 88%|████████▊ | 10484/11952 [2:11:39<2:25:00, 5.93s/it] {'loss': 0.4681, 'learning_rate': 7.808994934236058e-07, 'epoch': 0.88} + 88%|████████▊ | 10484/11952 [2:11:39<2:25:00, 5.93s/it] 88%|████████▊ | 10485/11952 [2:11:45<2:24:34, 5.91s/it] {'loss': 0.4989, 'learning_rate': 7.798500039796974e-07, 'epoch': 0.88} + 88%|████████▊ | 10485/11952 [2:11:45<2:24:34, 5.91s/it] 88%|████████▊ | 10486/11952 [2:11:50<2:22:38, 5.84s/it] {'loss': 0.4629, 'learning_rate': 7.788011916252558e-07, 'epoch': 0.88} + 88%|████████▊ | 10486/11952 [2:11:50<2:22:38, 5.84s/it] 88%|████████▊ | 10487/11952 [2:11:56<2:23:15, 5.87s/it] {'loss': 0.4475, 'learning_rate': 7.777530564373015e-07, 'epoch': 0.88} + 88%|████████▊ | 10487/11952 [2:11:56<2:23:15, 5.87s/it] 88%|████████▊ | 10488/11952 [2:12:02<2:22:14, 5.83s/it] {'loss': 0.4632, 'learning_rate': 7.767055984928041e-07, 'epoch': 0.88} + 88%|████████▊ | 10488/11952 [2:12:02<2:22:14, 5.83s/it] 88%|████████▊ | 10489/11952 [2:12:08<2:23:57, 5.90s/it] {'loss': 0.4704, 'learning_rate': 7.756588178686853e-07, 'epoch': 0.88} + 88%|████████▊ | 10489/11952 [2:12:08<2:23:57, 5.90s/it] 88%|████████▊ | 10490/11952 [2:12:14<2:24:35, 5.93s/it] {'loss': 0.4527, 'learning_rate': 7.746127146418148e-07, 'epoch': 0.88} + 88%|████████▊ | 10490/11952 [2:12:14<2:24:35, 5.93s/it] 88%|████████▊ | 10491/11952 [2:12:20<2:24:58, 5.95s/it] {'loss': 0.4651, 'learning_rate': 7.735672888890155e-07, 'epoch': 0.88} + 88%|████████▊ | 10491/11952 [2:12:20<2:24:58, 5.95s/it] 88%|████████▊ | 10492/11952 [2:12:26<2:23:49, 5.91s/it] {'loss': 0.4569, 'learning_rate': 7.725225406870607e-07, 'epoch': 0.88} + 88%|████████▊ | 10492/11952 [2:12:26<2:23:49, 5.91s/it] 88%|████████▊ | 10493/11952 [2:12:32<2:24:28, 5.94s/it] {'loss': 0.464, 'learning_rate': 7.714784701126687e-07, 'epoch': 0.88} + 88%|████████▊ | 10493/11952 [2:12:32<2:24:28, 5.94s/it] 88%|████████▊ | 10494/11952 [2:12:38<2:23:02, 5.89s/it] {'loss': 0.4621, 'learning_rate': 7.704350772425129e-07, 'epoch': 0.88} + 88%|████████▊ | 10494/11952 [2:12:38<2:23:02, 5.89s/it] 88%|████████▊ | 10495/11952 [2:12:43<2:22:23, 5.86s/it] {'loss': 0.4683, 'learning_rate': 7.693923621532184e-07, 'epoch': 0.88} + 88%|████████▊ | 10495/11952 [2:12:43<2:22:23, 5.86s/it] 88%|████████▊ | 10496/11952 [2:12:49<2:23:12, 5.90s/it] {'loss': 0.4905, 'learning_rate': 7.683503249213554e-07, 'epoch': 0.88} + 88%|████████▊ | 10496/11952 [2:12:49<2:23:12, 5.90s/it] 88%|████████▊ | 10497/11952 [2:12:55<2:24:57, 5.98s/it] {'loss': 0.4562, 'learning_rate': 7.673089656234456e-07, 'epoch': 0.88} + 88%|████████▊ | 10497/11952 [2:12:55<2:24:57, 5.98s/it] 88%|████████▊ | 10498/11952 [2:13:01<2:22:15, 5.87s/it] {'loss': 0.4489, 'learning_rate': 7.662682843359648e-07, 'epoch': 0.88} + 88%|████████▊ | 10498/11952 [2:13:01<2:22:15, 5.87s/it] 88%|████████▊ | 10499/11952 [2:13:07<2:21:30, 5.84s/it] {'loss': 0.4638, 'learning_rate': 7.652282811353362e-07, 'epoch': 0.88} + 88%|████████▊ | 10499/11952 [2:13:07<2:21:30, 5.84s/it]7 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... +01 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... + 88%|████████▊ | 10500/11952 [2:13:13<2:21:19, 5.84s/it]6 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4682, 'learning_rate': 7.641889560979321e-07, 'epoch': 0.88} + 88%|████████▊ | 10500/11952 [2:13:13<2:21:19, 5.84s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-10500/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-10500/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/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( + 88%|████████▊ | 10501/11952 [2:13:42<5:11:33, 12.88s/it] {'loss': 0.4702, 'learning_rate': 7.631503093000758e-07, 'epoch': 0.88} + 88%|████████▊ | 10501/11952 [2:13:42<5:11:33, 12.88s/it] 88%|████████▊ | 10502/11952 [2:13:48<4:20:45, 10.79s/it] {'loss': 0.4686, 'learning_rate': 7.621123408180419e-07, 'epoch': 0.88} + 88%|████████▊ | 10502/11952 [2:13:48<4:20:45, 10.79s/it] 88%|████████▊ | 10503/11952 [2:13:54<3:43:12, 9.24s/it] {'loss': 0.452, 'learning_rate': 7.61075050728054e-07, 'epoch': 0.88} + 88%|████████▊ | 10503/11952 [2:13:54<3:43:12, 9.24s/it] 88%|████████▊ | 10504/11952 [2:13:59<3:18:13, 8.21s/it] {'loss': 0.4584, 'learning_rate': 7.600384391062865e-07, 'epoch': 0.88} + 88%|████████▊ | 10504/11952 [2:13:59<3:18:13, 8.21s/it] 88%|████████▊ | 10505/11952 [2:14:05<3:02:39, 7.57s/it] {'loss': 0.4783, 'learning_rate': 7.590025060288642e-07, 'epoch': 0.88} + 88%|████████▊ | 10505/11952 [2:14:05<3:02:39, 7.57s/it] 88%|████████▊ | 10506/11952 [2:14:11<2:50:45, 7.09s/it] {'loss': 0.4468, 'learning_rate': 7.579672515718628e-07, 'epoch': 0.88} + 88%|████████▊ | 10506/11952 [2:14:11<2:50:45, 7.09s/it] 88%|████████▊ | 10507/11952 [2:14:17<2:42:45, 6.76s/it] {'loss': 0.4802, 'learning_rate': 7.569326758113049e-07, 'epoch': 0.88} + 88%|████████▊ | 10507/11952 [2:14:17<2:42:45, 6.76s/it] 88%|████████▊ | 10508/11952 [2:14:23<2:35:18, 6.45s/it] {'loss': 0.4594, 'learning_rate': 7.558987788231675e-07, 'epoch': 0.88} + 88%|████████▊ | 10508/11952 [2:14:23<2:35:18, 6.45s/it] 88%|████████▊ | 10509/11952 [2:14:29<2:30:14, 6.25s/it] {'loss': 0.4826, 'learning_rate': 7.548655606833755e-07, 'epoch': 0.88} + 88%|████████▊ | 10509/11952 [2:14:29<2:30:14, 6.25s/it] 88%|████████▊ | 10510/11952 [2:14:35<2:26:20, 6.09s/it] {'loss': 0.4664, 'learning_rate': 7.538330214678002e-07, 'epoch': 0.88} + 88%|████████▊ | 10510/11952 [2:14:35<2:26:20, 6.09s/it] 88%|████████▊ | 10511/11952 [2:14:40<2:23:11, 5.96s/it] {'loss': 0.4502, 'learning_rate': 7.528011612522723e-07, 'epoch': 0.88} + 88%|████████▊ | 10511/11952 [2:14:40<2:23:11, 5.96s/it] 88%|████████▊ | 10512/11952 [2:14:46<2:22:55, 5.96s/it] {'loss': 0.45, 'learning_rate': 7.517699801125655e-07, 'epoch': 0.88} + 88%|████████▊ | 10512/11952 [2:14:46<2:22:55, 5.96s/it] 88%|████████▊ | 10513/11952 [2:14:52<2:21:04, 5.88s/it] {'loss': 0.4798, 'learning_rate': 7.507394781244038e-07, 'epoch': 0.88} + 88%|████████▊ | 10513/11952 [2:14:52<2:21:04, 5.88s/it] 88%|████████▊ | 10514/11952 [2:14:58<2:19:21, 5.81s/it] {'loss': 0.4694, 'learning_rate': 7.497096553634653e-07, 'epoch': 0.88} + 88%|████████▊ | 10514/11952 [2:14:58<2:19:21, 5.81s/it] 88%|████████▊ | 10515/11952 [2:15:03<2:19:52, 5.84s/it] {'loss': 0.4539, 'learning_rate': 7.48680511905373e-07, 'epoch': 0.88} + 88%|████████▊ | 10515/11952 [2:15:03<2:19:52, 5.84s/it] 88%|████████▊ | 10516/11952 [2:15:10<2:22:25, 5.95s/it] {'loss': 0.466, 'learning_rate': 7.476520478257065e-07, 'epoch': 0.88} + 88%|████████▊ | 10516/11952 [2:15:10<2:22:25, 5.95s/it] 88%|████████▊ | 10517/11952 [2:15:16<2:22:04, 5.94s/it] {'loss': 0.4647, 'learning_rate': 7.466242631999887e-07, 'epoch': 0.88} + 88%|████████▊ | 10517/11952 [2:15:16<2:22:04, 5.94s/it] 88%|████████▊ | 10518/11952 [2:15:22<2:24:19, 6.04s/it] {'loss': 0.4704, 'learning_rate': 7.455971581036991e-07, 'epoch': 0.88} + 88%|████████▊ | 10518/11952 [2:15:22<2:24:19, 6.04s/it] 88%|████████▊ | 10519/11952 [2:15:28<2:22:52, 5.98s/it] {'loss': 0.4576, 'learning_rate': 7.44570732612262e-07, 'epoch': 0.88} + 88%|████████▊ | 10519/11952 [2:15:28<2:22:52, 5.98s/it] 88%|████████▊ | 10520/11952 [2:15:33<2:20:57, 5.91s/it] {'loss': 0.4648, 'learning_rate': 7.435449868010535e-07, 'epoch': 0.88} + 88%|████████▊ | 10520/11952 [2:15:33<2:20:57, 5.91s/it] 88%|████████▊ | 10521/11952 [2:15:39<2:20:29, 5.89s/it] {'loss': 0.4485, 'learning_rate': 7.425199207454014e-07, 'epoch': 0.88} + 88%|████████▊ | 10521/11952 [2:15:39<2:20:29, 5.89s/it] 88%|████████▊ | 10522/11952 [2:15:45<2:18:34, 5.81s/it] {'loss': 0.4636, 'learning_rate': 7.41495534520581e-07, 'epoch': 0.88} + 88%|████████▊ | 10522/11952 [2:15:45<2:18:34, 5.81s/it] 88%|████████▊ | 10523/11952 [2:15:51<2:18:09, 5.80s/it] {'loss': 0.4768, 'learning_rate': 7.404718282018197e-07, 'epoch': 0.88} + 88%|████████▊ | 10523/11952 [2:15:51<2:18:09, 5.80s/it] 88%|████████▊ | 10524/11952 [2:15:56<2:17:01, 5.76s/it] {'loss': 0.4482, 'learning_rate': 7.394488018642931e-07, 'epoch': 0.88} + 88%|████████▊ | 10524/11952 [2:15:56<2:17:01, 5.76s/it] 88%|████████▊ | 10525/11952 [2:16:02<2:16:17, 5.73s/it] {'loss': 0.4373, 'learning_rate': 7.3842645558313e-07, 'epoch': 0.88} + 88%|████████▊ | 10525/11952 [2:16:02<2:16:17, 5.73s/it] 88%|████████▊ | 10526/11952 [2:16:08<2:17:54, 5.80s/it] {'loss': 0.4618, 'learning_rate': 7.374047894334047e-07, 'epoch': 0.88} + 88%|████████▊ | 10526/11952 [2:16:08<2:17:54, 5.80s/it] 88%|████████▊ | 10527/11952 [2:16:14<2:17:25, 5.79s/it] {'loss': 0.4681, 'learning_rate': 7.363838034901471e-07, 'epoch': 0.88} + 88%|████████▊ | 10527/11952 [2:16:14<2:17:25, 5.79s/it] 88%|████████▊ | 10528/11952 [2:16:20<2:17:28, 5.79s/it] {'loss': 0.4577, 'learning_rate': 7.35363497828333e-07, 'epoch': 0.88} + 88%|████████▊ | 10528/11952 [2:16:20<2:17:28, 5.79s/it] 88%|████████▊ | 10529/11952 [2:16:25<2:18:01, 5.82s/it] {'loss': 0.4653, 'learning_rate': 7.343438725228891e-07, 'epoch': 0.88} + 88%|████████▊ | 10529/11952 [2:16:25<2:18:01, 5.82s/it] 88%|████████▊ | 10530/11952 [2:16:31<2:19:09, 5.87s/it] {'loss': 0.4989, 'learning_rate': 7.33324927648692e-07, 'epoch': 0.88} + 88%|████████▊ | 10530/11952 [2:16:31<2:19:09, 5.87s/it] 88%|████████▊ | 10531/11952 [2:16:37<2:19:43, 5.90s/it] {'loss': 0.4368, 'learning_rate': 7.323066632805676e-07, 'epoch': 0.88} + 88%|████████▊ | 10531/11952 [2:16:37<2:19:43, 5.90s/it] 88%|████████▊ | 10532/11952 [2:16:43<2:17:31, 5.81s/it] {'loss': 0.4771, 'learning_rate': 7.312890794932969e-07, 'epoch': 0.88} + 88%|████████▊ | 10532/11952 [2:16:43<2:17:31, 5.81s/it] 88%|████████▊ | 10533/11952 [2:16:49<2:17:32, 5.82s/it] {'loss': 0.4751, 'learning_rate': 7.302721763616039e-07, 'epoch': 0.88} + 88%|████████▊ | 10533/11952 [2:16:49<2:17:32, 5.82s/it] 88%|████████▊ | 10534/11952 [2:16:55<2:17:17, 5.81s/it] {'loss': 0.4537, 'learning_rate': 7.292559539601674e-07, 'epoch': 0.88} + 88%|████████▊ | 10534/11952 [2:16:55<2:17:17, 5.81s/it] 88%|████████▊ | 10535/11952 [2:17:01<2:18:05, 5.85s/it] {'loss': 0.4543, 'learning_rate': 7.28240412363611e-07, 'epoch': 0.88} + 88%|████████▊ | 10535/11952 [2:17:01<2:18:05, 5.85s/it] 88%|████████▊ | 10536/11952 [2:17:07<2:20:29, 5.95s/it] {'loss': 0.4839, 'learning_rate': 7.272255516465176e-07, 'epoch': 0.88} + 88%|████████▊ | 10536/11952 [2:17:07<2:20:29, 5.95s/it] 88%|████████▊ | 10537/11952 [2:17:13<2:22:21, 6.04s/it] {'loss': 0.4525, 'learning_rate': 7.262113718834086e-07, 'epoch': 0.88} + 88%|████████▊ | 10537/11952 [2:17:13<2:22:21, 6.04s/it] 88%|████████▊ | 10538/11952 [2:17:19<2:20:32, 5.96s/it] {'loss': 0.4823, 'learning_rate': 7.251978731487664e-07, 'epoch': 0.88} + 88%|████████▊ | 10538/11952 [2:17:19<2:20:32, 5.96s/it] 88%|████████▊ | 10539/11952 [2:17:25<2:19:11, 5.91s/it] {'loss': 0.4638, 'learning_rate': 7.241850555170149e-07, 'epoch': 0.88} + 88%|████████▊ | 10539/11952 [2:17:25<2:19:11, 5.91s/it] 88%|████████▊ | 10540/11952 [2:17:30<2:18:12, 5.87s/it] {'loss': 0.4807, 'learning_rate': 7.231729190625314e-07, 'epoch': 0.88} + 88%|████████▊ | 10540/11952 [2:17:30<2:18:12, 5.87s/it] 88%|████████▊ | 10541/11952 [2:17:36<2:18:59, 5.91s/it] {'loss': 0.4729, 'learning_rate': 7.221614638596441e-07, 'epoch': 0.88} + 88%|████████▊ | 10541/11952 [2:17:36<2:18:59, 5.91s/it] 88%|████████▊ | 10542/11952 [2:17:42<2:17:41, 5.86s/it] {'loss': 0.4802, 'learning_rate': 7.211506899826304e-07, 'epoch': 0.88} + 88%|████████▊ | 10542/11952 [2:17:42<2:17:41, 5.86s/it] 88%|████████▊ | 10543/11952 [2:17:48<2:15:12, 5.76s/it] {'loss': 0.4365, 'learning_rate': 7.201405975057152e-07, 'epoch': 0.88} + 88%|████████▊ | 10543/11952 [2:17:48<2:15:12, 5.76s/it] 88%|████████▊ | 10544/11952 [2:17:54<2:16:35, 5.82s/it] {'loss': 0.4644, 'learning_rate': 7.191311865030748e-07, 'epoch': 0.88} + 88%|████████▊ | 10544/11952 [2:17:54<2:16:35, 5.82s/it] 88%|████████▊ | 10545/11952 [2:17:59<2:16:55, 5.84s/it] {'loss': 0.4555, 'learning_rate': 7.18122457048841e-07, 'epoch': 0.88} + 88%|████████▊ | 10545/11952 [2:17:59<2:16:55, 5.84s/it] 88%|████████▊ | 10546/11952 [2:18:05<2:16:09, 5.81s/it] {'loss': 0.4495, 'learning_rate': 7.171144092170845e-07, 'epoch': 0.88} + 88%|████████▊ | 10546/11952 [2:18:05<2:16:09, 5.81s/it] 88%|████████▊ | 10547/11952 [2:18:11<2:17:53, 5.89s/it] {'loss': 0.4348, 'learning_rate': 7.161070430818385e-07, 'epoch': 0.88} + 88%|████████▊ | 10547/11952 [2:18:11<2:17:53, 5.89s/it] 88%|████████▊ | 10548/11952 [2:18:17<2:18:16, 5.91s/it] {'loss': 0.4765, 'learning_rate': 7.151003587170757e-07, 'epoch': 0.88} + 88%|████████▊ | 10548/11952 [2:18:17<2:18:16, 5.91s/it] 88%|████████▊ | 10549/11952 [2:18:23<2:18:22, 5.92s/it] {'loss': 0.4557, 'learning_rate': 7.14094356196724e-07, 'epoch': 0.88} + 88%|████████▊ | 10549/11952 [2:18:23<2:18:22, 5.92s/it]4 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +02 5AutoResumeHook: Checking whether to suspend... +AutoResumeHook: Checking whether to suspend... + 1AutoResumeHook: Checking whether to suspend... AutoResumeHook: Checking whether to suspend... + + 88%|████████▊ | 10550/11952 [2:18:29<2:19:28, 5.97s/it]3 6AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... + {'loss': 0.4436, 'learning_rate': 7.130890355946596e-07, 'epoch': 0.88} + 88%|████████▊ | 10550/11952 [2:18:29<2:19:28, 5.97s/it] 88%|████████▊ | 10551/11952 [2:18:35<2:17:16, 5.88s/it] {'loss': 0.4619, 'learning_rate': 7.12084396984708e-07, 'epoch': 0.88} + 88%|████████▊ | 10551/11952 [2:18:35<2:17:16, 5.88s/it] 88%|████████▊ | 10552/11952 [2:18:41<2:17:35, 5.90s/it] {'loss': 0.4572, 'learning_rate': 7.11080440440648e-07, 'epoch': 0.88} + 88%|████████▊ | 10552/11952 [2:18:41<2:17:35, 5.90s/it] 88%|████████▊ | 10553/11952 [2:18:47<2:17:01, 5.88s/it] {'loss': 0.464, 'learning_rate': 7.100771660362061e-07, 'epoch': 0.88} + 88%|████████▊ | 10553/11952 [2:18:47<2:17:01, 5.88s/it] 88%|████████▊ | 10554/11952 [2:18:53<2:17:47, 5.91s/it] {'loss': 0.465, 'learning_rate': 7.090745738450566e-07, 'epoch': 0.88} + 88%|████████▊ | 10554/11952 [2:18:53<2:17:47, 5.91s/it] 88%|████████▊ | 10555/11952 [2:18:59<2:18:40, 5.96s/it] {'loss': 0.4505, 'learning_rate': 7.080726639408264e-07, 'epoch': 0.88} + 88%|████████▊ | 10555/11952 [2:18:59<2:18:40, 5.96s/it] 88%|████████▊ | 10556/11952 [2:19:05<2:17:28, 5.91s/it] {'loss': 0.458, 'learning_rate': 7.070714363970899e-07, 'epoch': 0.88} + 88%|████████▊ | 10556/11952 [2:19:05<2:17:28, 5.91s/it] 88%|████████▊ | 10557/11952 [2:19:10<2:15:41, 5.84s/it] {'loss': 0.4661, 'learning_rate': 7.060708912873771e-07, 'epoch': 0.88} + 88%|████████▊ | 10557/11952 [2:19:10<2:15:41, 5.84s/it] 88%|████████▊ | 10558/11952 [2:19:16<2:15:21, 5.83s/it] {'loss': 0.4561, 'learning_rate': 7.050710286851603e-07, 'epoch': 0.88} + 88%|████████▊ | 10558/11952 [2:19:16<2:15:21, 5.83s/it] 88%|████████▊ | 10559/11952 [2:19:22<2:16:30, 5.88s/it] {'loss': 0.4619, 'learning_rate': 7.040718486638676e-07, 'epoch': 0.88} + 88%|████████▊ | 10559/11952 [2:19:22<2:16:30, 5.88s/it] 88%|████████▊ | 10560/11952 [2:19:28<2:16:24, 5.88s/it] {'loss': 0.4623, 'learning_rate': 7.030733512968735e-07, 'epoch': 0.88} + 88%|████████▊ | 10560/11952 [2:19:28<2:16:24, 5.88s/it] 88%|████████▊ | 10561/11952 [2:19:34<2:16:28, 5.89s/it] {'loss': 0.4636, 'learning_rate': 7.020755366575038e-07, 'epoch': 0.88} + 88%|████████▊ | 10561/11952 [2:19:34<2:16:28, 5.89s/it] 88%|████████▊ | 10562/11952 [2:19:39<2:13:43, 5.77s/it] {'loss': 0.4576, 'learning_rate': 7.010784048190344e-07, 'epoch': 0.88} + 88%|████████▊ | 10562/11952 [2:19:39<2:13:43, 5.77s/it] 88%|████████▊ | 10563/11952 [2:19:45<2:14:24, 5.81s/it] {'loss': 0.4482, 'learning_rate': 7.000819558546901e-07, 'epoch': 0.88} + 88%|████████▊ | 10563/11952 [2:19:45<2:14:24, 5.81s/it] 88%|████████▊ | 10564/11952 [2:19:51<2:14:11, 5.80s/it] {'loss': 0.4662, 'learning_rate': 6.990861898376444e-07, 'epoch': 0.88} + 88%|████████▊ | 10564/11952 [2:19:51<2:14:11, 5.80s/it] 88%|████████▊ | 10565/11952 [2:19:57<2:13:06, 5.76s/it] {'loss': 0.4577, 'learning_rate': 6.980911068410224e-07, 'epoch': 0.88} + 88%|████████▊ | 10565/11952 [2:19:57<2:13:06, 5.76s/it] 88%|████████▊ | 10566/11952 [2:20:03<2:16:33, 5.91s/it] {'loss': 0.4521, 'learning_rate': 6.97096706937902e-07, 'epoch': 0.88} + 88%|████████▊ | 10566/11952 [2:20:03<2:16:33, 5.91s/it] 88%|████████▊ | 10567/11952 [2:20:09<2:16:03, 5.89s/it] {'loss': 0.452, 'learning_rate': 6.961029902013039e-07, 'epoch': 0.88} + 88%|████████▊ | 10567/11952 [2:20:09<2:16:03, 5.89s/it] 88%|████████▊ | 10568/11952 [2:20:14<2:13:46, 5.80s/it] {'loss': 0.4763, 'learning_rate': 6.951099567042052e-07, 'epoch': 0.88} + 88%|████████▊ | 10568/11952 [2:20:14<2:13:46, 5.80s/it] 88%|████████▊ | 10569/11952 [2:20:20<2:15:28, 5.88s/it] {'loss': 0.4561, 'learning_rate': 6.941176065195299e-07, 'epoch': 0.88} + 88%|████████▊ | 10569/11952 [2:20:20<2:15:28, 5.88s/it] 88%|████████▊ | 10570/11952 [2:20:26<2:13:28, 5.79s/it] {'loss': 0.4594, 'learning_rate': 6.931259397201517e-07, 'epoch': 0.88} + 88%|████████▊ | 10570/11952 [2:20:26<2:13:28, 5.79s/it] 88%|████████▊ | 10571/11952 [2:20:32<2:13:22, 5.79s/it] {'loss': 0.4663, 'learning_rate': 6.921349563788949e-07, 'epoch': 0.88} + 88%|████████▊ | 10571/11952 [2:20:32<2:13:22, 5.79s/it] 88%|████████▊ | 10572/11952 [2:20:38<2:12:49, 5.77s/it] {'loss': 0.4581, 'learning_rate': 6.911446565685298e-07, 'epoch': 0.88} + 88%|████████▊ | 10572/11952 [2:20:38<2:12:49, 5.77s/it] 88%|████████▊ | 10573/11952 [2:20:44<2:15:55, 5.91s/it] {'loss': 0.4803, 'learning_rate': 6.901550403617852e-07, 'epoch': 0.88} + 88%|████████▊ | 10573/11952 [2:20:44<2:15:55, 5.91s/it] 88%|████████▊ | 10574/11952 [2:20:50<2:16:34, 5.95s/it] {'loss': 0.4621, 'learning_rate': 6.891661078313317e-07, 'epoch': 0.88} + 88%|████████▊ | 10574/11952 [2:20:50<2:16:34, 5.95s/it] 88%|████████▊ | 10575/11952 [2:20:56<2:15:01, 5.88s/it] {'loss': 0.4698, 'learning_rate': 6.881778590497923e-07, 'epoch': 0.88} + 88%|████████▊ | 10575/11952 [2:20:56<2:15:01, 5.88s/it] 88%|████████▊ | 10576/11952 [2:21:01<2:15:10, 5.89s/it] {'loss': 0.4748, 'learning_rate': 6.87190294089738e-07, 'epoch': 0.88} + 88%|████████▊ | 10576/11952 [2:21:01<2:15:10, 5.89s/it] 88%|████████▊ | 10577/11952 [2:21:07<2:14:09, 5.85s/it] {'loss': 0.453, 'learning_rate': 6.86203413023696e-07, 'epoch': 0.88} + 88%|████████▊ | 10577/11952 [2:21:07<2:14:09, 5.85s/it] 89%|████████▊ | 10578/11952 [2:21:13<2:13:49, 5.84s/it] {'loss': 0.4714, 'learning_rate': 6.852172159241343e-07, 'epoch': 0.89} + 89%|████████▊ | 10578/11952 [2:21:13<2:13:49, 5.84s/it] 89%|████████▊ | 10579/11952 [2:21:19<2:14:53, 5.89s/it] {'loss': 0.4762, 'learning_rate': 6.842317028634793e-07, 'epoch': 0.89} + 89%|████████▊ | 10579/11952 [2:21:19<2:14:53, 5.89s/it] 89%|████████▊ | 10580/11952 [2:21:25<2:13:24, 5.83s/it] {'loss': 0.4559, 'learning_rate': 6.832468739141007e-07, 'epoch': 0.89} + 89%|████████▊ | 10580/11952 [2:21:25<2:13:24, 5.83s/it] 89%|████████▊ | 10581/11952 [2:21:31<2:13:50, 5.86s/it] {'loss': 0.4699, 'learning_rate': 6.822627291483197e-07, 'epoch': 0.89} + 89%|████████▊ | 10581/11952 [2:21:31<2:13:50, 5.86s/it] 89%|████████▊ | 10582/11952 [2:21:37<2:13:52, 5.86s/it] {'loss': 0.4521, 'learning_rate': 6.812792686384095e-07, 'epoch': 0.89} + 89%|████████▊ | 10582/11952 [2:21:37<2:13:52, 5.86s/it] 89%|████████▊ | 10583/11952 [2:21:43<2:14:52, 5.91s/it] {'loss': 0.4515, 'learning_rate': 6.802964924565891e-07, 'epoch': 0.89} + 89%|████████▊ | 10583/11952 [2:21:43<2:14:52, 5.91s/it] 89%|████████▊ | 10584/11952 [2:21:48<2:14:36, 5.90s/it] {'loss': 0.4689, 'learning_rate': 6.793144006750318e-07, 'epoch': 0.89} + 89%|████████▊ | 10584/11952 [2:21:48<2:14:36, 5.90s/it] 89%|████████▊ | 10585/11952 [2:21:54<2:13:44, 5.87s/it] {'loss': 0.4531, 'learning_rate': 6.783329933658555e-07, 'epoch': 0.89} + 89%|████████▊ | 10585/11952 [2:21:54<2:13:44, 5.87s/it] 89%|████████▊ | 10586/11952 [2:22:00<2:12:56, 5.84s/it] {'loss': 0.4877, 'learning_rate': 6.773522706011337e-07, 'epoch': 0.89} + 89%|████████▊ | 10586/11952 [2:22:00<2:12:56, 5.84s/it] 89%|████████▊ | 10587/11952 [2:22:06<2:14:19, 5.90s/it] {'loss': 0.4599, 'learning_rate': 6.763722324528843e-07, 'epoch': 0.89} + 89%|████████▊ | 10587/11952 [2:22:06<2:14:19, 5.90s/it] 89%|████████▊ | 10588/11952 [2:22:12<2:15:15, 5.95s/it] {'loss': 0.469, 'learning_rate': 6.753928789930797e-07, 'epoch': 0.89} + 89%|████████▊ | 10588/11952 [2:22:12<2:15:15, 5.95s/it] 89%|████████▊ | 10589/11952 [2:22:18<2:13:49, 5.89s/it] {'loss': 0.4548, 'learning_rate': 6.74414210293638e-07, 'epoch': 0.89} + 89%|████████▊ | 10589/11952 [2:22:18<2:13:49, 5.89s/it] 89%|████████▊ | 10590/11952 [2:22:24<2:14:57, 5.95s/it] {'loss': 0.4717, 'learning_rate': 6.734362264264283e-07, 'epoch': 0.89} + 89%|████████▊ | 10590/11952 [2:22:24<2:14:57, 5.95s/it] 89%|████████▊ | 10591/11952 [2:22:30<2:12:58, 5.86s/it] {'loss': 0.4463, 'learning_rate': 6.724589274632698e-07, 'epoch': 0.89} + 89%|████████▊ | 10591/11952 [2:22:30<2:12:58, 5.86s/it] 89%|████████▊ | 10592/11952 [2:22:35<2:12:15, 5.83s/it] {'loss': 0.4454, 'learning_rate': 6.714823134759307e-07, 'epoch': 0.89} + 89%|████████▊ | 10592/11952 [2:22:35<2:12:15, 5.83s/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%|████████▊ | 10593/11952 [2:22:41<2:12:23, 5.85s/it] {'loss': 0.4723, 'learning_rate': 6.705063845361315e-07, 'epoch': 0.89} + 89%|████████▊ | 10593/11952 [2:22:41<2:12:23, 5.85s/it] 89%|████████▊ | 10594/11952 [2:22:47<2:11:24, 5.81s/it] {'loss': 0.4621, 'learning_rate': 6.695311407155391e-07, 'epoch': 0.89} + 89%|████████▊ | 10594/11952 [2:22:47<2:11:24, 5.81s/it] 89%|████████▊ | 10595/11952 [2:22:53<2:11:51, 5.83s/it] {'loss': 0.4683, 'learning_rate': 6.68556582085772e-07, 'epoch': 0.89} + 89%|████████▊ | 10595/11952 [2:22:53<2:11:51, 5.83s/it] 89%|████████▊ | 10596/11952 [2:22:59<2:11:47, 5.83s/it] {'loss': 0.4772, 'learning_rate': 6.675827087183961e-07, 'epoch': 0.89} + 89%|████████▊ | 10596/11952 [2:22:59<2:11:47, 5.83s/it] 89%|████████▊ | 10597/11952 [2:23:05<2:12:11, 5.85s/it] {'loss': 0.4646, 'learning_rate': 6.666095206849288e-07, 'epoch': 0.89} + 89%|████████▊ | 10597/11952 [2:23:05<2:12:11, 5.85s/it] 89%|████████▊ | 10598/11952 [2:23:10<2:12:05, 5.85s/it] {'loss': 0.4574, 'learning_rate': 6.656370180568395e-07, 'epoch': 0.89} + 89%|████████▊ | 10598/11952 [2:23:10<2:12:05, 5.85s/it] 89%|████████▊ | 10599/11952 [2:23:16<2:10:26, 5.78s/it] {'loss': 0.4854, 'learning_rate': 6.646652009055409e-07, 'epoch': 0.89} + 89%|████████▊ | 10599/11952 [2:23:16<2:10:26, 5.78s/it]7 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +02 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... + 89%|████████▊ | 10600/11952 [2:23:22<2:12:16, 5.87s/it]6 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4795, 'learning_rate': 6.63694069302403e-07, 'epoch': 0.89} + 89%|████████▊ | 10600/11952 [2:23:22<2:12:16, 5.87s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-10600/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-10600/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/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( + 89%|████████▊ | 10601/11952 [2:23:52<4:51:35, 12.95s/it] {'loss': 0.4678, 'learning_rate': 6.627236233187407e-07, 'epoch': 0.89} + 89%|████████▊ | 10601/11952 [2:23:52<4:51:35, 12.95s/it] 89%|████████▊ | 10602/11952 [2:23:58<4:03:55, 10.84s/it] {'loss': 0.4546, 'learning_rate': 6.61753863025818e-07, 'epoch': 0.89} + 89%|████████▊ | 10602/11952 [2:23:58<4:03:55, 10.84s/it] 89%|████████▊ | 10603/11952 [2:24:04<3:31:31, 9.41s/it] {'loss': 0.4514, 'learning_rate': 6.607847884948515e-07, 'epoch': 0.89} + 89%|████████▊ | 10603/11952 [2:24:04<3:31:31, 9.41s/it] 89%|████████▊ | 10604/11952 [2:24:10<3:08:08, 8.37s/it] {'loss': 0.4607, 'learning_rate': 6.598163997970053e-07, 'epoch': 0.89} + 89%|████████▊ | 10604/11952 [2:24:10<3:08:08, 8.37s/it] 89%|████████▊ | 10605/11952 [2:24:16<2:52:03, 7.66s/it] {'loss': 0.467, 'learning_rate': 6.588486970033936e-07, 'epoch': 0.89} + 89%|████████▊ | 10605/11952 [2:24:16<2:52:03, 7.66s/it] 89%|████████▊ | 10606/11952 [2:24:22<2:40:45, 7.17s/it] {'loss': 0.461, 'learning_rate': 6.578816801850796e-07, 'epoch': 0.89} + 89%|████████▊ | 10606/11952 [2:24:22<2:40:45, 7.17s/it] 89%|████████▊ | 10607/11952 [2:24:28<2:33:03, 6.83s/it] {'loss': 0.4654, 'learning_rate': 6.569153494130798e-07, 'epoch': 0.89} + 89%|████████▊ | 10607/11952 [2:24:28<2:33:03, 6.83s/it] 89%|████████▉ | 10608/11952 [2:24:34<2:29:27, 6.67s/it] {'loss': 0.485, 'learning_rate': 6.55949704758354e-07, 'epoch': 0.89} + 89%|████████▉ | 10608/11952 [2:24:34<2:29:27, 6.67s/it] 89%|████████▉ | 10609/11952 [2:24:40<2:24:50, 6.47s/it] {'loss': 0.4681, 'learning_rate': 6.549847462918191e-07, 'epoch': 0.89} + 89%|████████▉ | 10609/11952 [2:24:40<2:24:50, 6.47s/it] 89%|████████▉ | 10610/11952 [2:24:46<2:21:47, 6.34s/it] {'loss': 0.4647, 'learning_rate': 6.540204740843348e-07, 'epoch': 0.89} + 89%|████████▉ | 10610/11952 [2:24:46<2:21:47, 6.34s/it] 89%|████████▉ | 10611/11952 [2:24:52<2:18:02, 6.18s/it] {'loss': 0.4694, 'learning_rate': 6.530568882067145e-07, 'epoch': 0.89} + 89%|████████▉ | 10611/11952 [2:24:52<2:18:02, 6.18s/it] 89%|████████▉ | 10612/11952 [2:24:58<2:15:13, 6.05s/it] {'loss': 0.4592, 'learning_rate': 6.520939887297184e-07, 'epoch': 0.89} + 89%|████████▉ | 10612/11952 [2:24:58<2:15:13, 6.05s/it] 89%|████████▉ | 10613/11952 [2:25:04<2:14:44, 6.04s/it] {'loss': 0.4805, 'learning_rate': 6.511317757240598e-07, 'epoch': 0.89} + 89%|████████▉ | 10613/11952 [2:25:04<2:14:44, 6.04s/it] 89%|████████▉ | 10614/11952 [2:25:10<2:14:30, 6.03s/it] {'loss': 0.4699, 'learning_rate': 6.50170249260399e-07, 'epoch': 0.89} + 89%|████████▉ | 10614/11952 [2:25:10<2:14:30, 6.03s/it] 89%|████████▉ | 10615/11952 [2:25:15<2:12:52, 5.96s/it] {'loss': 0.4552, 'learning_rate': 6.492094094093459e-07, 'epoch': 0.89} + 89%|████████▉ | 10615/11952 [2:25:15<2:12:52, 5.96s/it] 89%|████████▉ | 10616/11952 [2:25:21<2:12:24, 5.95s/it] {'loss': 0.4495, 'learning_rate': 6.482492562414621e-07, 'epoch': 0.89} + 89%|████████▉ | 10616/11952 [2:25:21<2:12:24, 5.95s/it] 89%|████████▉ | 10617/11952 [2:25:27<2:12:17, 5.95s/it] {'loss': 0.4724, 'learning_rate': 6.472897898272534e-07, 'epoch': 0.89} + 89%|████████▉ | 10617/11952 [2:25:27<2:12:17, 5.95s/it] 89%|████████▉ | 10618/11952 [2:25:33<2:12:28, 5.96s/it] {'loss': 0.4603, 'learning_rate': 6.463310102371834e-07, 'epoch': 0.89} + 89%|████████▉ | 10618/11952 [2:25:33<2:12:28, 5.96s/it] 89%|████████▉ | 10619/11952 [2:25:39<2:12:34, 5.97s/it] {'loss': 0.4423, 'learning_rate': 6.453729175416579e-07, 'epoch': 0.89} + 89%|████████▉ | 10619/11952 [2:25:39<2:12:34, 5.97s/it] 89%|████████▉ | 10620/11952 [2:25:45<2:11:11, 5.91s/it] {'loss': 0.4421, 'learning_rate': 6.444155118110373e-07, 'epoch': 0.89} + 89%|████████▉ | 10620/11952 [2:25:45<2:11:11, 5.91s/it] 89%|████████▉ | 10621/11952 [2:25:51<2:10:35, 5.89s/it] {'loss': 0.4656, 'learning_rate': 6.434587931156299e-07, 'epoch': 0.89} + 89%|████████▉ | 10621/11952 [2:25:51<2:10:35, 5.89s/it] 89%|████████▉ | 10622/11952 [2:25:57<2:10:57, 5.91s/it] {'loss': 0.4639, 'learning_rate': 6.425027615256907e-07, 'epoch': 0.89} + 89%|████████▉ | 10622/11952 [2:25:57<2:10:57, 5.91s/it] 89%|████████▉ | 10623/11952 [2:26:03<2:11:08, 5.92s/it] {'loss': 0.4575, 'learning_rate': 6.415474171114288e-07, 'epoch': 0.89} + 89%|████████▉ | 10623/11952 [2:26:03<2:11:08, 5.92s/it] 89%|████████▉ | 10624/11952 [2:26:09<2:10:41, 5.90s/it] {'loss': 0.4592, 'learning_rate': 6.405927599429995e-07, 'epoch': 0.89} + 89%|████████▉ | 10624/11952 [2:26:09<2:10:41, 5.90s/it] 89%|████████▉ | 10625/11952 [2:26:15<2:11:31, 5.95s/it] {'loss': 0.4616, 'learning_rate': 6.396387900905099e-07, 'epoch': 0.89} + 89%|████████▉ | 10625/11952 [2:26:15<2:11:31, 5.95s/it] 89%|████████▉ | 10626/11952 [2:26:20<2:09:25, 5.86s/it] {'loss': 0.4553, 'learning_rate': 6.386855076240117e-07, 'epoch': 0.89} + 89%|████████▉ | 10626/11952 [2:26:20<2:09:25, 5.86s/it] 89%|████████▉ | 10627/11952 [2:26:26<2:09:01, 5.84s/it] {'loss': 0.4603, 'learning_rate': 6.377329126135168e-07, 'epoch': 0.89} + 89%|████████▉ | 10627/11952 [2:26:26<2:09:01, 5.84s/it] 89%|████████▉ | 10628/11952 [2:26:32<2:10:16, 5.90s/it] {'loss': 0.4622, 'learning_rate': 6.367810051289746e-07, 'epoch': 0.89} + 89%|████████▉ | 10628/11952 [2:26:32<2:10:16, 5.90s/it] 89%|████████▉ | 10629/11952 [2:26:38<2:11:33, 5.97s/it] {'loss': 0.4787, 'learning_rate': 6.358297852402894e-07, 'epoch': 0.89} + 89%|████████▉ | 10629/11952 [2:26:38<2:11:33, 5.97s/it] 89%|████████▉ | 10630/11952 [2:26:44<2:12:38, 6.02s/it] {'loss': 0.4648, 'learning_rate': 6.348792530173187e-07, 'epoch': 0.89} + 89%|████████▉ | 10630/11952 [2:26:44<2:12:38, 6.02s/it] 89%|████████▉ | 10631/11952 [2:26:50<2:11:05, 5.95s/it] {'loss': 0.4586, 'learning_rate': 6.339294085298631e-07, 'epoch': 0.89} + 89%|████████▉ | 10631/11952 [2:26:50<2:11:05, 5.95s/it] 89%|████████▉ | 10632/11952 [2:26:56<2:11:18, 5.97s/it] {'loss': 0.464, 'learning_rate': 6.329802518476746e-07, 'epoch': 0.89} + 89%|████████▉ | 10632/11952 [2:26:56<2:11:18, 5.97s/it] 89%|████████▉ | 10633/11952 [2:27:02<2:11:23, 5.98s/it] {'loss': 0.4964, 'learning_rate': 6.320317830404554e-07, 'epoch': 0.89} + 89%|████████▉ | 10633/11952 [2:27:02<2:11:23, 5.98s/it] 89%|████████▉ | 10634/11952 [2:27:08<2:10:40, 5.95s/it] {'loss': 0.4679, 'learning_rate': 6.310840021778586e-07, 'epoch': 0.89} + 89%|████████▉ | 10634/11952 [2:27:08<2:10:40, 5.95s/it] 89%|████████▉ | 10635/11952 [2:27:14<2:08:16, 5.84s/it] {'loss': 0.4348, 'learning_rate': 6.30136909329484e-07, 'epoch': 0.89} + 89%|████████▉ | 10635/11952 [2:27:14<2:08:16, 5.84s/it] 89%|████████▉ | 10636/11952 [2:27:19<2:07:57, 5.83s/it] {'loss': 0.4809, 'learning_rate': 6.291905045648839e-07, 'epoch': 0.89} + 89%|████████▉ | 10636/11952 [2:27:19<2:07:57, 5.83s/it] 89%|████████▉ | 10637/11952 [2:27:25<2:07:50, 5.83s/it] {'loss': 0.4575, 'learning_rate': 6.282447879535558e-07, 'epoch': 0.89} + 89%|████████▉ | 10637/11952 [2:27:25<2:07:50, 5.83s/it] 89%|████████▉ | 10638/11952 [2:27:31<2:07:47, 5.84s/it] {'loss': 0.4739, 'learning_rate': 6.272997595649499e-07, 'epoch': 0.89} + 89%|████████▉ | 10638/11952 [2:27:31<2:07:47, 5.84s/it] 89%|████████▉ | 10639/11952 [2:27:37<2:06:29, 5.78s/it] {'loss': 0.4522, 'learning_rate': 6.263554194684662e-07, 'epoch': 0.89} + 89%|████████▉ | 10639/11952 [2:27:37<2:06:29, 5.78s/it] 89%|████████▉ | 10640/11952 [2:27:43<2:06:12, 5.77s/it] {'loss': 0.4417, 'learning_rate': 6.254117677334514e-07, 'epoch': 0.89} + 89%|████████▉ | 10640/11952 [2:27:43<2:06:12, 5.77s/it] 89%|████████▉ | 10641/11952 [2:27:49<2:07:28, 5.83s/it] {'loss': 0.4564, 'learning_rate': 6.244688044292058e-07, 'epoch': 0.89} + 89%|████████▉ | 10641/11952 [2:27:49<2:07:28, 5.83s/it] 89%|████████▉ | 10642/11952 [2:27:55<2:10:27, 5.98s/it] {'loss': 0.4505, 'learning_rate': 6.23526529624976e-07, 'epoch': 0.89} + 89%|████████▉ | 10642/11952 [2:27:55<2:10:27, 5.98s/it] 89%|████████▉ | 10643/11952 [2:28:01<2:11:32, 6.03s/it] {'loss': 0.4596, 'learning_rate': 6.225849433899578e-07, 'epoch': 0.89} + 89%|████████▉ | 10643/11952 [2:28:01<2:11:32, 6.03s/it] 89%|████████▉ | 10644/11952 [2:28:07<2:10:07, 5.97s/it] {'loss': 0.4338, 'learning_rate': 6.216440457932981e-07, 'epoch': 0.89} + 89%|████████▉ | 10644/11952 [2:28:07<2:10:07, 5.97s/it] 89%|████████▉ | 10645/11952 [2:28:13<2:08:38, 5.91s/it] {'loss': 0.4676, 'learning_rate': 6.207038369040918e-07, 'epoch': 0.89} + 89%|████████▉ | 10645/11952 [2:28:13<2:08:38, 5.91s/it] 89%|████████▉ | 10646/11952 [2:28:18<2:08:06, 5.89s/it] {'loss': 0.4753, 'learning_rate': 6.197643167913847e-07, 'epoch': 0.89} + 89%|████████▉ | 10646/11952 [2:28:18<2:08:06, 5.89s/it] 89%|████████▉ | 10647/11952 [2:28:24<2:07:28, 5.86s/it] {'loss': 0.4584, 'learning_rate': 6.188254855241693e-07, 'epoch': 0.89} + 89%|████████▉ | 10647/11952 [2:28:24<2:07:28, 5.86s/it] 89%|████████▉ | 10648/11952 [2:28:30<2:07:14, 5.85s/it] {'loss': 0.4765, 'learning_rate': 6.178873431713928e-07, 'epoch': 0.89} + 89%|████████▉ | 10648/11952 [2:28:30<2:07:14, 5.85s/it] 89%|████████▉ | 10649/11952 [2:28:36<2:06:30, 5.83s/it] {'loss': 0.4592, 'learning_rate': 6.169498898019443e-07, 'epoch': 0.89} + 89%|████████▉ | 10649/11952 [2:28:36<2:06:30, 5.83s/it]01 AutoResumeHook: Checking whether to suspend... + 5 AutoResumeHook: Checking whether to suspend... +AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... + 89%|████████▉ | 10650/11952 [2:28:42<2:05:42, 5.79s/it]4 AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4643, 'learning_rate': 6.160131254846702e-07, 'epoch': 0.89} + 89%|████████▉ | 10650/11952 [2:28:42<2:05:42, 5.79s/it] 89%|████████▉ | 10651/11952 [2:28:47<2:05:16, 5.78s/it] {'loss': 0.4684, 'learning_rate': 6.150770502883618e-07, 'epoch': 0.89} + 89%|████████▉ | 10651/11952 [2:28:47<2:05:16, 5.78s/it] 89%|████████▉ | 10652/11952 [2:28:53<2:06:25, 5.84s/it] {'loss': 0.4886, 'learning_rate': 6.141416642817599e-07, 'epoch': 0.89} + 89%|████████▉ | 10652/11952 [2:28:53<2:06:25, 5.84s/it] 89%|████████▉ | 10653/11952 [2:28:59<2:05:48, 5.81s/it] {'loss': 0.4641, 'learning_rate': 6.13206967533555e-07, 'epoch': 0.89} + 89%|████████▉ | 10653/11952 [2:28:59<2:05:48, 5.81s/it] 89%|████████▉ | 10654/11952 [2:29:05<2:05:18, 5.79s/it] {'loss': 0.4639, 'learning_rate': 6.122729601123878e-07, 'epoch': 0.89} + 89%|████████▉ | 10654/11952 [2:29:05<2:05:18, 5.79s/it] 89%|████████▉ | 10655/11952 [2:29:11<2:07:08, 5.88s/it] {'loss': 0.4511, 'learning_rate': 6.113396420868489e-07, 'epoch': 0.89} + 89%|████████▉ | 10655/11952 [2:29:11<2:07:08, 5.88s/it] 89%|████████▉ | 10656/11952 [2:29:17<2:07:33, 5.91s/it] {'loss': 0.4748, 'learning_rate': 6.104070135254758e-07, 'epoch': 0.89} + 89%|████████▉ | 10656/11952 [2:29:17<2:07:33, 5.91s/it] 89%|████████▉ | 10657/11952 [2:29:23<2:09:44, 6.01s/it] {'loss': 0.4607, 'learning_rate': 6.09475074496757e-07, 'epoch': 0.89} + 89%|████████▉ | 10657/11952 [2:29:23<2:09:44, 6.01s/it] 89%|████████▉ | 10658/11952 [2:29:29<2:10:11, 6.04s/it] {'loss': 0.4689, 'learning_rate': 6.085438250691311e-07, 'epoch': 0.89} + 89%|████████▉ | 10658/11952 [2:29:29<2:10:11, 6.04s/it] 89%|████████▉ | 10659/11952 [2:29:35<2:08:09, 5.95s/it] {'loss': 0.4497, 'learning_rate': 6.076132653109834e-07, 'epoch': 0.89} + 89%|████████▉ | 10659/11952 [2:29:35<2:08:09, 5.95s/it] 89%|████████▉ | 10660/11952 [2:29:41<2:07:40, 5.93s/it] {'loss': 0.4615, 'learning_rate': 6.066833952906515e-07, 'epoch': 0.89} + 89%|████████▉ | 10660/11952 [2:29:41<2:07:40, 5.93s/it] 89%|████████▉ | 10661/11952 [2:29:47<2:09:17, 6.01s/it] {'loss': 0.4654, 'learning_rate': 6.057542150764218e-07, 'epoch': 0.89} + 89%|████████▉ | 10661/11952 [2:29:47<2:09:17, 6.01s/it] 89%|████████▉ | 10662/11952 [2:29:53<2:06:52, 5.90s/it] {'loss': 0.4703, 'learning_rate': 6.048257247365297e-07, 'epoch': 0.89} + 89%|████████▉ | 10662/11952 [2:29:53<2:06:52, 5.90s/it] 89%|████████▉ | 10663/11952 [2:29:59<2:09:00, 6.01s/it] {'loss': 0.4581, 'learning_rate': 6.038979243391597e-07, 'epoch': 0.89} + 89%|████████▉ | 10663/11952 [2:29:59<2:09:00, 6.01s/it] 89%|████████▉ | 10664/11952 [2:30:04<2:06:25, 5.89s/it] {'loss': 0.4653, 'learning_rate': 6.029708139524438e-07, 'epoch': 0.89} + 89%|████████▉ | 10664/11952 [2:30:04<2:06:25, 5.89s/it] 89%|████████▉ | 10665/11952 [2:30:10<2:06:38, 5.90s/it] {'loss': 0.4835, 'learning_rate': 6.020443936444664e-07, 'epoch': 0.89} + 89%|████████▉ | 10665/11952 [2:30:10<2:06:38, 5.90s/it] 89%|████████▉ | 10666/11952 [2:30:16<2:06:45, 5.91s/it] {'loss': 0.4538, 'learning_rate': 6.0111866348326e-07, 'epoch': 0.89} + 89%|████████▉ | 10666/11952 [2:30:16<2:06:45, 5.91s/it] 89%|████████▉ | 10667/11952 [2:30:22<2:07:25, 5.95s/it] {'loss': 0.4771, 'learning_rate': 6.001936235368044e-07, 'epoch': 0.89} + 89%|████████▉ | 10667/11952 [2:30:22<2:07:25, 5.95s/it] 89%|████████▉ | 10668/11952 [2:30:28<2:07:54, 5.98s/it] {'loss': 0.4604, 'learning_rate': 5.992692738730332e-07, 'epoch': 0.89} + 89%|████████▉ | 10668/11952 [2:30:28<2:07:54, 5.98s/it] 89%|████████▉ | 10669/11952 [2:30:34<2:06:06, 5.90s/it] {'loss': 0.4592, 'learning_rate': 5.983456145598266e-07, 'epoch': 0.89} + 89%|████████▉ | 10669/11952 [2:30:34<2:06:06, 5.90s/it] 89%|████████▉ | 10670/11952 [2:30:40<2:06:09, 5.90s/it] {'loss': 0.4773, 'learning_rate': 5.974226456650123e-07, 'epoch': 0.89} + 89%|████████▉ | 10670/11952 [2:30:40<2:06:09, 5.90s/it] 89%|████████▉ | 10671/11952 [2:30:46<2:04:51, 5.85s/it] {'loss': 0.472, 'learning_rate': 5.965003672563719e-07, 'epoch': 0.89} + 89%|████████▉ | 10671/11952 [2:30:46<2:04:51, 5.85s/it] 89%|████████▉ | 10672/11952 [2:30:52<2:04:31, 5.84s/it] {'loss': 0.4521, 'learning_rate': 5.955787794016321e-07, 'epoch': 0.89} + 89%|████████▉ | 10672/11952 [2:30:52<2:04:31, 5.84s/it] 89%|████████▉ | 10673/11952 [2:30:57<2:03:31, 5.79s/it] {'loss': 0.4492, 'learning_rate': 5.946578821684713e-07, 'epoch': 0.89} + 89%|████████▉ | 10673/11952 [2:30:57<2:03:31, 5.79s/it] 89%|████████▉ | 10674/11952 [2:31:03<2:05:06, 5.87s/it] {'loss': 0.4726, 'learning_rate': 5.937376756245139e-07, 'epoch': 0.89} + 89%|████████▉ | 10674/11952 [2:31:03<2:05:06, 5.87s/it] 89%|████████▉ | 10675/11952 [2:31:09<2:05:18, 5.89s/it] {'loss': 0.4556, 'learning_rate': 5.928181598373395e-07, 'epoch': 0.89} + 89%|████████▉ | 10675/11952 [2:31:09<2:05:18, 5.89s/it] 89%|████████▉ | 10676/11952 [2:31:15<2:02:51, 5.78s/it] {'loss': 0.4523, 'learning_rate': 5.918993348744728e-07, 'epoch': 0.89} + 89%|████████▉ | 10676/11952 [2:31:15<2:02:51, 5.78s/it] 89%|████████▉ | 10677/11952 [2:31:21<2:03:37, 5.82s/it] {'loss': 0.461, 'learning_rate': 5.909812008033866e-07, 'epoch': 0.89} + 89%|████████▉ | 10677/11952 [2:31:21<2:03:37, 5.82s/it] 89%|████████▉ | 10678/11952 [2:31:26<2:02:52, 5.79s/it] {'loss': 0.4729, 'learning_rate': 5.900637576915069e-07, 'epoch': 0.89} + 89%|████████▉ | 10678/11952 [2:31:26<2:02:52, 5.79s/it] 89%|████████▉ | 10679/11952 [2:31:32<2:02:04, 5.75s/it] {'loss': 0.4656, 'learning_rate': 5.891470056062043e-07, 'epoch': 0.89} + 89%|████████▉ | 10679/11952 [2:31:32<2:02:04, 5.75s/it] 89%|████████▉ | 10680/11952 [2:31:38<2:02:53, 5.80s/it] {'loss': 0.4639, 'learning_rate': 5.882309446148038e-07, 'epoch': 0.89} + 89%|████████▉ | 10680/11952 [2:31:38<2:02:53, 5.80s/it] 89%|████████▉ | 10681/11952 [2:31:44<2:03:40, 5.84s/it] {'loss': 0.4651, 'learning_rate': 5.87315574784576e-07, 'epoch': 0.89} + 89%|████████▉ | 10681/11952 [2:31:44<2:03:40, 5.84s/it] 89%|████████▉ | 10682/11952 [2:31:50<2:05:09, 5.91s/it] {'loss': 0.4665, 'learning_rate': 5.864008961827428e-07, 'epoch': 0.89} + 89%|████████▉ | 10682/11952 [2:31:50<2:05:09, 5.91s/it] 89%|████████▉ | 10683/11952 [2:31:56<2:02:57, 5.81s/it] {'loss': 0.4629, 'learning_rate': 5.854869088764737e-07, 'epoch': 0.89} + 89%|████████▉ | 10683/11952 [2:31:56<2:02:57, 5.81s/it] 89%|████████▉ | 10684/11952 [2:32:02<2:04:05, 5.87s/it] {'loss': 0.4569, 'learning_rate': 5.845736129328883e-07, 'epoch': 0.89} + 89%|████████▉ | 10684/11952 [2:32:02<2:04:05, 5.87s/it] 89%|████████▉ | 10685/11952 [2:32:07<2:03:03, 5.83s/it] {'loss': 0.455, 'learning_rate': 5.836610084190541e-07, 'epoch': 0.89} + 89%|████████▉ | 10685/11952 [2:32:07<2:03:03, 5.83s/it] 89%|████████▉ | 10686/11952 [2:32:13<2:02:26, 5.80s/it] {'loss': 0.4809, 'learning_rate': 5.82749095401991e-07, 'epoch': 0.89} + 89%|████████▉ | 10686/11952 [2:32:13<2:02:26, 5.80s/it] 89%|████████▉ | 10687/11952 [2:32:19<2:03:09, 5.84s/it] {'loss': 0.4639, 'learning_rate': 5.81837873948663e-07, 'epoch': 0.89} + 89%|████████▉ | 10687/11952 [2:32:19<2:03:09, 5.84s/it] 89%|████████▉ | 10688/11952 [2:32:25<2:02:23, 5.81s/it] {'loss': 0.4451, 'learning_rate': 5.809273441259899e-07, 'epoch': 0.89} + 89%|████████▉ | 10688/11952 [2:32:25<2:02:23, 5.81s/it] 89%|████████▉ | 10689/11952 [2:32:30<2:01:48, 5.79s/it] {'loss': 0.4691, 'learning_rate': 5.800175060008362e-07, 'epoch': 0.89} + 89%|████████▉ | 10689/11952 [2:32:30<2:01:48, 5.79s/it] 89%|████████▉ | 10690/11952 [2:32:36<2:01:49, 5.79s/it] {'loss': 0.467, 'learning_rate': 5.791083596400148e-07, 'epoch': 0.89} + 89%|████████▉ | 10690/11952 [2:32:36<2:01:49, 5.79s/it] 89%|████████▉ | 10691/11952 [2:32:42<2:04:07, 5.91s/it] {'loss': 0.463, 'learning_rate': 5.781999051102927e-07, 'epoch': 0.89} + 89%|████████▉ | 10691/11952 [2:32:42<2:04:07, 5.91s/it] 89%|████████▉ | 10692/11952 [2:32:48<2:04:46, 5.94s/it] {'loss': 0.4638, 'learning_rate': 5.772921424783806e-07, 'epoch': 0.89} + 89%|████████▉ | 10692/11952 [2:32:48<2:04:46, 5.94s/it] 89%|████████▉ | 10693/11952 [2:32:54<2:03:06, 5.87s/it] {'loss': 0.475, 'learning_rate': 5.763850718109421e-07, 'epoch': 0.89} + 89%|████████▉ | 10693/11952 [2:32:54<2:03:06, 5.87s/it] 89%|████████▉ | 10694/11952 [2:33:00<2:03:58, 5.91s/it] {'loss': 0.4652, 'learning_rate': 5.754786931745859e-07, 'epoch': 0.89} + 89%|████████▉ | 10694/11952 [2:33:00<2:03:58, 5.91s/it] 89%|████████▉ | 10695/11952 [2:33:06<2:01:40, 5.81s/it] {'loss': 0.4622, 'learning_rate': 5.745730066358779e-07, 'epoch': 0.89} + 89%|████████▉ | 10695/11952 [2:33:06<2:01:40, 5.81s/it] 89%|████████▉ | 10696/11952 [2:33:12<2:02:09, 5.84s/it] {'loss': 0.4608, 'learning_rate': 5.736680122613237e-07, 'epoch': 0.89} + 89%|████████▉ | 10696/11952 [2:33:12<2:02:09, 5.84s/it] 89%|████████▉ | 10697/11952 [2:33:17<2:02:07, 5.84s/it] {'loss': 0.4586, 'learning_rate': 5.727637101173844e-07, 'epoch': 0.89} + 89%|████████▉ | 10697/11952 [2:33:17<2:02:07, 5.84s/it] 90%|████████▉ | 10698/11952 [2:33:23<2:02:06, 5.84s/it] {'loss': 0.442, 'learning_rate': 5.718601002704671e-07, 'epoch': 0.9} + 90%|████████▉ | 10698/11952 [2:33:23<2:02:06, 5.84s/it] 90%|████████▉ | 10699/11952 [2:33:29<2:02:33, 5.87s/it] {'loss': 0.4706, 'learning_rate': 5.709571827869287e-07, 'epoch': 0.9} + 90%|████████▉ | 10699/11952 [2:33:29<2:02:33, 5.87s/it]4 AutoResumeHook: Checking whether to suspend... +05 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... + 90%|████████▉ | 10700/11952 [2:33:36<2:05:11, 6.00s/it]1 76AutoResumeHook: Checking whether to suspend... +AutoResumeHook: Checking whether to suspend...AutoResumeHook: Checking whether to suspend... + +3 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4871, 'learning_rate': 5.70054957733076e-07, 'epoch': 0.9} + 90%|████████▉ | 10700/11952 [2:33:36<2:05:11, 6.00s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-10700/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-10700/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/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( + 90%|████████▉ | 10701/11952 [2:34:06<4:35:42, 13.22s/it] {'loss': 0.4701, 'learning_rate': 5.691534251751652e-07, 'epoch': 0.9} + 90%|████████▉ | 10701/11952 [2:34:06<4:35:42, 13.22s/it] 90%|████████▉ | 10702/11952 [2:34:11<3:48:12, 10.95s/it] {'loss': 0.4756, 'learning_rate': 5.682525851794019e-07, 'epoch': 0.9} + 90%|████████▉ | 10702/11952 [2:34:11<3:48:12, 10.95s/it] 90%|████████▉ | 10703/11952 [2:34:17<3:16:37, 9.45s/it] {'loss': 0.4662, 'learning_rate': 5.673524378119388e-07, 'epoch': 0.9} + 90%|████████▉ | 10703/11952 [2:34:17<3:16:37, 9.45s/it] 90%|████████▉ | 10704/11952 [2:34:23<2:53:47, 8.36s/it] {'loss': 0.4683, 'learning_rate': 5.664529831388799e-07, 'epoch': 0.9} + 90%|████████▉ | 10704/11952 [2:34:23<2:53:47, 8.36s/it] 90%|████████▉ | 10705/11952 [2:34:29<2:37:09, 7.56s/it] {'loss': 0.4452, 'learning_rate': 5.655542212262766e-07, 'epoch': 0.9} + 90%|████████▉ | 10705/11952 [2:34:29<2:37:09, 7.56s/it] 90%|████████▉ | 10706/11952 [2:34:35<2:28:45, 7.16s/it] {'loss': 0.4809, 'learning_rate': 5.646561521401317e-07, 'epoch': 0.9} + 90%|████████▉ | 10706/11952 [2:34:35<2:28:45, 7.16s/it] 90%|████████▉ | 10707/11952 [2:34:41<2:21:21, 6.81s/it] {'loss': 0.4604, 'learning_rate': 5.637587759463925e-07, 'epoch': 0.9} + 90%|████████▉ | 10707/11952 [2:34:41<2:21:21, 6.81s/it] 90%|████████▉ | 10708/11952 [2:34:47<2:15:35, 6.54s/it] {'loss': 0.4794, 'learning_rate': 5.628620927109607e-07, 'epoch': 0.9} + 90%|████████▉ | 10708/11952 [2:34:47<2:15:35, 6.54s/it] 90%|████████▉ | 10709/11952 [2:34:53<2:10:15, 6.29s/it] {'loss': 0.4603, 'learning_rate': 5.619661024996848e-07, 'epoch': 0.9} + 90%|████████▉ | 10709/11952 [2:34:53<2:10:15, 6.29s/it] 90%|████████▉ | 10710/11952 [2:34:59<2:08:17, 6.20s/it] {'loss': 0.4669, 'learning_rate': 5.610708053783642e-07, 'epoch': 0.9} + 90%|████████▉ | 10710/11952 [2:34:59<2:08:17, 6.20s/it] 90%|████████▉ | 10711/11952 [2:35:04<2:05:47, 6.08s/it] {'loss': 0.471, 'learning_rate': 5.60176201412741e-07, 'epoch': 0.9} + 90%|████████▉ | 10711/11952 [2:35:04<2:05:47, 6.08s/it] 90%|████████▉ | 10712/11952 [2:35:10<2:04:44, 6.04s/it] {'loss': 0.4629, 'learning_rate': 5.59282290668517e-07, 'epoch': 0.9} + 90%|████████▉ | 10712/11952 [2:35:10<2:04:44, 6.04s/it] 90%|████████▉ | 10713/11952 [2:35:16<2:02:23, 5.93s/it] {'loss': 0.4513, 'learning_rate': 5.58389073211335e-07, 'epoch': 0.9} + 90%|████████▉ | 10713/11952 [2:35:16<2:02:23, 5.93s/it] 90%|████████▉ | 10714/11952 [2:35:22<2:02:03, 5.92s/it] {'loss': 0.5152, 'learning_rate': 5.574965491067874e-07, 'epoch': 0.9} + 90%|████████▉ | 10714/11952 [2:35:22<2:02:03, 5.92s/it] 90%|████████▉ | 10715/11952 [2:35:28<2:01:24, 5.89s/it] {'loss': 0.4614, 'learning_rate': 5.566047184204182e-07, 'epoch': 0.9} + 90%|████████▉ | 10715/11952 [2:35:28<2:01:24, 5.89s/it] 90%|████████▉ | 10716/11952 [2:35:34<2:01:23, 5.89s/it] {'loss': 0.4401, 'learning_rate': 5.557135812177228e-07, 'epoch': 0.9} + 90%|████████▉ | 10716/11952 [2:35:34<2:01:23, 5.89s/it] 90%|████████▉ | 10717/11952 [2:35:39<2:01:08, 5.89s/it] {'loss': 0.4655, 'learning_rate': 5.548231375641389e-07, 'epoch': 0.9} + 90%|████████▉ | 10717/11952 [2:35:39<2:01:08, 5.89s/it] 90%|████████▉ | 10718/11952 [2:35:46<2:02:24, 5.95s/it] {'loss': 0.4761, 'learning_rate': 5.539333875250596e-07, 'epoch': 0.9} + 90%|████████▉ | 10718/11952 [2:35:46<2:02:24, 5.95s/it] 90%|████████▉ | 10719/11952 [2:35:52<2:02:38, 5.97s/it] {'loss': 0.4628, 'learning_rate': 5.530443311658218e-07, 'epoch': 0.9} + 90%|████████▉ | 10719/11952 [2:35:52<2:02:38, 5.97s/it] 90%|████████▉ | 10720/11952 [2:35:58<2:02:22, 5.96s/it] {'loss': 0.4645, 'learning_rate': 5.521559685517153e-07, 'epoch': 0.9} + 90%|████████▉ | 10720/11952 [2:35:58<2:02:22, 5.96s/it] 90%|████████▉ | 10721/11952 [2:36:03<2:01:37, 5.93s/it] {'loss': 0.4947, 'learning_rate': 5.51268299747978e-07, 'epoch': 0.9} + 90%|████████▉ | 10721/11952 [2:36:03<2:01:37, 5.93s/it] 90%|████████▉ | 10722/11952 [2:36:09<1:59:37, 5.84s/it] {'loss': 0.4574, 'learning_rate': 5.503813248197965e-07, 'epoch': 0.9} + 90%|████████▉ | 10722/11952 [2:36:09<1:59:37, 5.84s/it] 90%|████████▉ | 10723/11952 [2:36:15<1:58:55, 5.81s/it] {'loss': 0.4685, 'learning_rate': 5.494950438323077e-07, 'epoch': 0.9} + 90%|████████▉ | 10723/11952 [2:36:15<1:58:55, 5.81s/it] 90%|████████▉ | 10724/11952 [2:36:21<2:00:34, 5.89s/it] {'loss': 0.4751, 'learning_rate': 5.48609456850594e-07, 'epoch': 0.9} + 90%|████████▉ | 10724/11952 [2:36:21<2:00:34, 5.89s/it] 90%|████████▉ | 10725/11952 [2:36:26<1:58:29, 5.79s/it] {'loss': 0.4682, 'learning_rate': 5.477245639396922e-07, 'epoch': 0.9} + 90%|████████▉ | 10725/11952 [2:36:26<1:58:29, 5.79s/it] 90%|████████▉ | 10726/11952 [2:36:32<1:58:14, 5.79s/it] {'loss': 0.4474, 'learning_rate': 5.468403651645826e-07, 'epoch': 0.9} + 90%|████████▉ | 10726/11952 [2:36:32<1:58:14, 5.79s/it] 90%|████████▉ | 10727/11952 [2:36:38<1:59:56, 5.87s/it] {'loss': 0.4704, 'learning_rate': 5.459568605901977e-07, 'epoch': 0.9} + 90%|████████▉ | 10727/11952 [2:36:38<1:59:56, 5.87s/it] 90%|████████▉ | 10728/11952 [2:36:44<2:00:14, 5.89s/it] {'loss': 0.4847, 'learning_rate': 5.450740502814178e-07, 'epoch': 0.9} + 90%|████████▉ | 10728/11952 [2:36:44<2:00:14, 5.89s/it] 90%|████████▉ | 10729/11952 [2:36:50<2:00:52, 5.93s/it] {'loss': 0.4695, 'learning_rate': 5.441919343030744e-07, 'epoch': 0.9} + 90%|████████▉ | 10729/11952 [2:36:50<2:00:52, 5.93s/it] 90%|████████▉ | 10730/11952 [2:36:56<2:02:35, 6.02s/it] {'loss': 0.4646, 'learning_rate': 5.433105127199467e-07, 'epoch': 0.9} + 90%|████████▉ | 10730/11952 [2:36:56<2:02:35, 6.02s/it] 90%|████████▉ | 10731/11952 [2:37:02<2:01:56, 5.99s/it] {'loss': 0.4771, 'learning_rate': 5.424297855967597e-07, 'epoch': 0.9} + 90%|████████▉ | 10731/11952 [2:37:02<2:01:56, 5.99s/it] 90%|████████▉ | 10732/11952 [2:37:08<2:02:44, 6.04s/it] {'loss': 0.4748, 'learning_rate': 5.415497529981928e-07, 'epoch': 0.9} + 90%|████████▉ | 10732/11952 [2:37:08<2:02:44, 6.04s/it] 90%|████████▉ | 10733/11952 [2:37:14<2:00:53, 5.95s/it] {'loss': 0.4688, 'learning_rate': 5.40670414988872e-07, 'epoch': 0.9} + 90%|████████▉ | 10733/11952 [2:37:14<2:00:53, 5.95s/it] 90%|████████▉ | 10734/11952 [2:37:20<1:59:54, 5.91s/it] {'loss': 0.4381, 'learning_rate': 5.397917716333723e-07, 'epoch': 0.9} + 90%|████████▉ | 10734/11952 [2:37:20<1:59:54, 5.91s/it] 90%|████████▉ | 10735/11952 [2:37:26<1:58:58, 5.87s/it] {'loss': 0.4684, 'learning_rate': 5.389138229962155e-07, 'epoch': 0.9} + 90%|████████▉ | 10735/11952 [2:37:26<1:58:58, 5.87s/it] 90%|████████▉ | 10736/11952 [2:37:32<1:59:19, 5.89s/it] {'loss': 0.4519, 'learning_rate': 5.380365691418765e-07, 'epoch': 0.9} + 90%|████████▉ | 10736/11952 [2:37:32<1:59:19, 5.89s/it] 90%|████████▉ | 10737/11952 [2:37:37<1:58:09, 5.83s/it] {'loss': 0.4714, 'learning_rate': 5.371600101347763e-07, 'epoch': 0.9} + 90%|████████▉ | 10737/11952 [2:37:37<1:58:09, 5.83s/it] 90%|████████▉ | 10738/11952 [2:37:43<1:57:50, 5.82s/it] {'loss': 0.4653, 'learning_rate': 5.362841460392875e-07, 'epoch': 0.9} + 90%|████████▉ | 10738/11952 [2:37:43<1:57:50, 5.82s/it] 90%|████████▉ | 10739/11952 [2:37:49<1:58:15, 5.85s/it] {'loss': 0.4803, 'learning_rate': 5.354089769197268e-07, 'epoch': 0.9} + 90%|████████▉ | 10739/11952 [2:37:49<1:58:15, 5.85s/it] 90%|████████▉ | 10740/11952 [2:37:55<1:56:20, 5.76s/it] {'loss': 0.4518, 'learning_rate': 5.345345028403659e-07, 'epoch': 0.9} + 90%|████████▉ | 10740/11952 [2:37:55<1:56:20, 5.76s/it] 90%|████████▉ | 10741/11952 [2:38:01<1:56:42, 5.78s/it] {'loss': 0.4649, 'learning_rate': 5.33660723865419e-07, 'epoch': 0.9} + 90%|████████▉ | 10741/11952 [2:38:01<1:56:42, 5.78s/it] 90%|████████▉ | 10742/11952 [2:38:06<1:56:19, 5.77s/it] {'loss': 0.461, 'learning_rate': 5.32787640059057e-07, 'epoch': 0.9} + 90%|████████▉ | 10742/11952 [2:38:06<1:56:19, 5.77s/it] 90%|████████▉ | 10743/11952 [2:38:13<1:59:25, 5.93s/it] {'loss': 0.4962, 'learning_rate': 5.31915251485392e-07, 'epoch': 0.9} + 90%|████████▉ | 10743/11952 [2:38:13<1:59:25, 5.93s/it] 90%|████████▉ | 10744/11952 [2:38:19<2:01:21, 6.03s/it] {'loss': 0.4649, 'learning_rate': 5.310435582084917e-07, 'epoch': 0.9} + 90%|████████▉ | 10744/11952 [2:38:19<2:01:21, 6.03s/it] 90%|████████▉ | 10745/11952 [2:38:25<2:00:26, 5.99s/it] {'loss': 0.4624, 'learning_rate': 5.301725602923691e-07, 'epoch': 0.9} + 90%|████████▉ | 10745/11952 [2:38:25<2:00:26, 5.99s/it] 90%|████████▉ | 10746/11952 [2:38:31<2:00:00, 5.97s/it] {'loss': 0.467, 'learning_rate': 5.293022578009843e-07, 'epoch': 0.9} + 90%|████████▉ | 10746/11952 [2:38:31<2:00:00, 5.97s/it] 90%|████████▉ | 10747/11952 [2:38:36<1:57:52, 5.87s/it] {'loss': 0.4678, 'learning_rate': 5.284326507982507e-07, 'epoch': 0.9} + 90%|████████▉ | 10747/11952 [2:38:36<1:57:52, 5.87s/it] 90%|████████▉ | 10748/11952 [2:38:42<1:57:34, 5.86s/it] {'loss': 0.4608, 'learning_rate': 5.275637393480282e-07, 'epoch': 0.9} + 90%|████████▉ | 10748/11952 [2:38:42<1:57:34, 5.86s/it] 90%|████████▉ | 10749/11952 [2:38:48<1:57:42, 5.87s/it] {'loss': 0.4783, 'learning_rate': 5.266955235141235e-07, 'epoch': 0.9} + 90%|████████▉ | 10749/11952 [2:38:48<1:57:42, 5.87s/it]07 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... + 90%|████████▉ | 10750/11952 [2:38:54<1:55:47, 5.78s/it]4 AutoResumeHook: Checking whether to suspend... +25 AutoResumeHook: Checking whether to suspend... +AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4863, 'learning_rate': 5.258280033602992e-07, 'epoch': 0.9} + 90%|████████▉ | 10750/11952 [2:38:54<1:55:47, 5.78s/it] 90%|████████▉ | 10751/11952 [2:38:59<1:55:46, 5.78s/it] {'loss': 0.4491, 'learning_rate': 5.249611789502607e-07, 'epoch': 0.9} + 90%|████████▉ | 10751/11952 [2:38:59<1:55:46, 5.78s/it] 90%|████████▉ | 10752/11952 [2:39:06<1:58:56, 5.95s/it] {'loss': 0.4695, 'learning_rate': 5.240950503476616e-07, 'epoch': 0.9} + 90%|████████▉ | 10752/11952 [2:39:06<1:58:56, 5.95s/it] 90%|████████▉ | 10753/11952 [2:39:12<2:00:04, 6.01s/it] {'loss': 0.4812, 'learning_rate': 5.232296176161101e-07, 'epoch': 0.9} + 90%|████████▉ | 10753/11952 [2:39:12<2:00:04, 6.01s/it] 90%|████████▉ | 10754/11952 [2:39:18<1:59:17, 5.97s/it] {'loss': 0.4459, 'learning_rate': 5.223648808191584e-07, 'epoch': 0.9} + 90%|████████▉ | 10754/11952 [2:39:18<1:59:17, 5.97s/it] 90%|████████▉ | 10755/11952 [2:39:24<2:00:24, 6.04s/it] {'loss': 0.4771, 'learning_rate': 5.215008400203103e-07, 'epoch': 0.9} + 90%|████████▉ | 10755/11952 [2:39:24<2:00:24, 6.04s/it] 90%|████████▉ | 10756/11952 [2:39:30<2:01:21, 6.09s/it] {'loss': 0.4675, 'learning_rate': 5.20637495283014e-07, 'epoch': 0.9} + 90%|████████▉ | 10756/11952 [2:39:30<2:01:21, 6.09s/it] 90%|█████████ | 10757/11952 [2:39:36<2:00:00, 6.03s/it] {'loss': 0.4509, 'learning_rate': 5.197748466706742e-07, 'epoch': 0.9} + 90%|█████████ | 10757/11952 [2:39:36<2:00:00, 6.03s/it] 90%|█████████ | 10758/11952 [2:39:42<1:57:23, 5.90s/it] {'loss': 0.4566, 'learning_rate': 5.189128942466393e-07, 'epoch': 0.9} + 90%|█████████ | 10758/11952 [2:39:42<1:57:23, 5.90s/it] 90%|█████████ | 10759/11952 [2:39:47<1:56:49, 5.88s/it] {'loss': 0.4632, 'learning_rate': 5.180516380742051e-07, 'epoch': 0.9} + 90%|█████████ | 10759/11952 [2:39:47<1:56:49, 5.88s/it] 90%|█████████ | 10760/11952 [2:39:53<1:56:15, 5.85s/it] {'loss': 0.4563, 'learning_rate': 5.171910782166212e-07, 'epoch': 0.9} + 90%|█████████ | 10760/11952 [2:39:53<1:56:15, 5.85s/it] 90%|█████████ | 10761/11952 [2:39:59<1:57:19, 5.91s/it] {'loss': 0.4507, 'learning_rate': 5.163312147370824e-07, 'epoch': 0.9} + 90%|█████████ | 10761/11952 [2:39:59<1:57:19, 5.91s/it] 90%|█████████ | 10762/11952 [2:40:05<1:56:39, 5.88s/it] {'loss': 0.4547, 'learning_rate': 5.154720476987329e-07, 'epoch': 0.9} + 90%|█████████ | 10762/11952 [2:40:05<1:56:39, 5.88s/it] 90%|█████████ | 10763/11952 [2:40:11<1:56:57, 5.90s/it] {'loss': 0.4596, 'learning_rate': 5.146135771646655e-07, 'epoch': 0.9} + 90%|█████████ | 10763/11952 [2:40:11<1:56:57, 5.90s/it] 90%|█████████ | 10764/11952 [2:40:17<1:57:53, 5.95s/it] {'loss': 0.4456, 'learning_rate': 5.137558031979273e-07, 'epoch': 0.9} + 90%|█████████ | 10764/11952 [2:40:17<1:57:53, 5.95s/it] 90%|█████████ | 10765/11952 [2:40:23<1:56:23, 5.88s/it] {'loss': 0.4591, 'learning_rate': 5.128987258615059e-07, 'epoch': 0.9} + 90%|█████████ | 10765/11952 [2:40:23<1:56:23, 5.88s/it] 90%|█████████ | 10766/11952 [2:40:29<1:56:49, 5.91s/it] {'loss': 0.4841, 'learning_rate': 5.12042345218342e-07, 'epoch': 0.9} + 90%|█████████ | 10766/11952 [2:40:29<1:56:49, 5.91s/it] 90%|█████████ | 10767/11952 [2:40:34<1:55:12, 5.83s/it] {'loss': 0.4637, 'learning_rate': 5.111866613313255e-07, 'epoch': 0.9} + 90%|█████████ | 10767/11952 [2:40:34<1:55:12, 5.83s/it] 90%|█████████ | 10768/11952 [2:40:41<1:56:53, 5.92s/it] {'loss': 0.4692, 'learning_rate': 5.103316742632935e-07, 'epoch': 0.9} + 90%|█████████ | 10768/11952 [2:40:41<1:56:53, 5.92s/it] 90%|█████████ | 10769/11952 [2:40:47<1:58:03, 5.99s/it] {'loss': 0.4977, 'learning_rate': 5.094773840770306e-07, 'epoch': 0.9} + 90%|█████████ | 10769/11952 [2:40:47<1:58:03, 5.99s/it] 90%|█████████ | 10770/11952 [2:40:53<1:57:59, 5.99s/it] {'loss': 0.4727, 'learning_rate': 5.086237908352776e-07, 'epoch': 0.9} + 90%|█████████ | 10770/11952 [2:40:53<1:57:59, 5.99s/it] 90%|█████████ | 10771/11952 [2:40:58<1:56:05, 5.90s/it] {'loss': 0.4818, 'learning_rate': 5.077708946007143e-07, 'epoch': 0.9} + 90%|█████████ | 10771/11952 [2:40:58<1:56:05, 5.90s/it] 90%|█████████ | 10772/11952 [2:41:04<1:54:50, 5.84s/it] {'loss': 0.4501, 'learning_rate': 5.069186954359761e-07, 'epoch': 0.9} + 90%|█████████ | 10772/11952 [2:41:04<1:54:50, 5.84s/it] 90%|█████████ | 10773/11952 [2:41:10<1:55:48, 5.89s/it] {'loss': 0.4501, 'learning_rate': 5.060671934036421e-07, 'epoch': 0.9} + 90%|█████████ | 10773/11952 [2:41:10<1:55:48, 5.89s/it] 90%|█████████ | 10774/11952 [2:41:16<1:54:54, 5.85s/it] {'loss': 0.4629, 'learning_rate': 5.052163885662476e-07, 'epoch': 0.9} + 90%|█████████ | 10774/11952 [2:41:16<1:54:54, 5.85s/it] 90%|█████████ | 10775/11952 [2:41:22<1:55:21, 5.88s/it] {'loss': 0.4542, 'learning_rate': 5.043662809862692e-07, 'epoch': 0.9} + 90%|█████████ | 10775/11952 [2:41:22<1:55:21, 5.88s/it] 90%|█████████ | 10776/11952 [2:41:28<1:54:20, 5.83s/it] {'loss': 0.4559, 'learning_rate': 5.03516870726134e-07, 'epoch': 0.9} + 90%|█████████ | 10776/11952 [2:41:28<1:54:20, 5.83s/it] 90%|█████████ | 10777/11952 [2:41:34<1:56:12, 5.93s/it] {'loss': 0.4821, 'learning_rate': 5.026681578482229e-07, 'epoch': 0.9} + 90%|█████████ | 10777/11952 [2:41:34<1:56:12, 5.93s/it] 90%|█████████ | 10778/11952 [2:41:40<1:55:29, 5.90s/it] {'loss': 0.4764, 'learning_rate': 5.018201424148606e-07, 'epoch': 0.9} + 90%|█████████ | 10778/11952 [2:41:40<1:55:29, 5.90s/it] 90%|█████████ | 10779/11952 [2:41:46<1:57:10, 5.99s/it] {'loss': 0.4775, 'learning_rate': 5.009728244883205e-07, 'epoch': 0.9} + 90%|█████████ | 10779/11952 [2:41:46<1:57:10, 5.99s/it] 90%|█████████ | 10780/11952 [2:41:52<1:57:15, 6.00s/it] {'loss': 0.4691, 'learning_rate': 5.001262041308263e-07, 'epoch': 0.9} + 90%|█████████ | 10780/11952 [2:41:52<1:57:15, 6.00s/it] 90%|█████████ | 10781/11952 [2:41:58<1:56:12, 5.95s/it] {'loss': 0.4439, 'learning_rate': 4.992802814045505e-07, 'epoch': 0.9} + 90%|█████████ | 10781/11952 [2:41:58<1:56:12, 5.95s/it] 90%|█████████ | 10782/11952 [2:42:04<1:56:47, 5.99s/it] {'loss': 0.4732, 'learning_rate': 4.984350563716145e-07, 'epoch': 0.9} + 90%|█████████ | 10782/11952 [2:42:04<1:56:47, 5.99s/it] 90%|█████████ | 10783/11952 [2:42:10<1:56:13, 5.97s/it] {'loss': 0.4788, 'learning_rate': 4.975905290940874e-07, 'epoch': 0.9} + 90%|█████████ | 10783/11952 [2:42:10<1:56:13, 5.97s/it] 90%|█████████ | 10784/11952 [2:42:16<1:56:43, 6.00s/it] {'loss': 0.471, 'learning_rate': 4.967466996339887e-07, 'epoch': 0.9} + 90%|█████████ | 10784/11952 [2:42:16<1:56:43, 6.00s/it] 90%|█████████ | 10785/11952 [2:42:22<1:57:43, 6.05s/it] {'loss': 0.4454, 'learning_rate': 4.959035680532854e-07, 'epoch': 0.9} + 90%|█████████ | 10785/11952 [2:42:22<1:57:43, 6.05s/it] 90%|█████████ | 10786/11952 [2:42:28<1:56:36, 6.00s/it] {'loss': 0.4511, 'learning_rate': 4.950611344138945e-07, 'epoch': 0.9} + 90%|█████████ | 10786/11952 [2:42:28<1:56:36, 6.00s/it] 90%|█████████ | 10787/11952 [2:42:34<1:55:58, 5.97s/it] {'loss': 0.4767, 'learning_rate': 4.9421939877768e-07, 'epoch': 0.9} + 90%|█████████ | 10787/11952 [2:42:34<1:55:58, 5.97s/it] 90%|█████████ | 10788/11952 [2:42:39<1:53:38, 5.86s/it] {'loss': 0.4464, 'learning_rate': 4.933783612064546e-07, 'epoch': 0.9} + 90%|█████████ | 10788/11952 [2:42:39<1:53:38, 5.86s/it] 90%|█████████ | 10789/11952 [2:42:45<1:53:39, 5.86s/it] {'loss': 0.4537, 'learning_rate': 4.925380217619813e-07, 'epoch': 0.9} + 90%|█████████ | 10789/11952 [2:42:45<1:53:39, 5.86s/it] 90%|█████████ | 10790/11952 [2:42:51<1:55:44, 5.98s/it] {'loss': 0.4717, 'learning_rate': 4.916983805059705e-07, 'epoch': 0.9} + 90%|█████████ | 10790/11952 [2:42:51<1:55:44, 5.98s/it] 90%|█████████ | 10791/11952 [2:42:57<1:55:20, 5.96s/it] {'loss': 0.4549, 'learning_rate': 4.90859437500083e-07, 'epoch': 0.9} + 90%|█████████ | 10791/11952 [2:42:57<1:55:20, 5.96s/it] 90%|█████████ | 10792/11952 [2:43:03<1:56:09, 6.01s/it] {'loss': 0.4547, 'learning_rate': 4.900211928059284e-07, 'epoch': 0.9} + 90%|█████████ | 10792/11952 [2:43:03<1:56:09, 6.01s/it] 90%|█████████ | 10793/11952 [2:43:09<1:54:30, 5.93s/it] {'loss': 0.4571, 'learning_rate': 4.891836464850596e-07, 'epoch': 0.9} + 90%|█████████ | 10793/11952 [2:43:09<1:54:30, 5.93s/it] 90%|█████████ | 10794/11952 [2:43:15<1:52:39, 5.84s/it] {'loss': 0.4762, 'learning_rate': 4.883467985989876e-07, 'epoch': 0.9} + 90%|█████████ | 10794/11952 [2:43:15<1:52:39, 5.84s/it] 90%|█████████ | 10795/11952 [2:43:21<1:53:47, 5.90s/it] {'loss': 0.4692, 'learning_rate': 4.875106492091642e-07, 'epoch': 0.9} + 90%|█████████ | 10795/11952 [2:43:21<1:53:47, 5.90s/it] 90%|█████████ | 10796/11952 [2:43:27<1:53:11, 5.88s/it] {'loss': 0.4702, 'learning_rate': 4.866751983769935e-07, 'epoch': 0.9} + 90%|█████████ | 10796/11952 [2:43:27<1:53:11, 5.88s/it] 90%|█████████ | 10797/11952 [2:43:33<1:53:23, 5.89s/it] {'loss': 0.4569, 'learning_rate': 4.858404461638266e-07, 'epoch': 0.9} + 90%|█████████ | 10797/11952 [2:43:33<1:53:23, 5.89s/it] 90%|█████████ | 10798/11952 [2:43:39<1:53:47, 5.92s/it] {'loss': 0.4488, 'learning_rate': 4.850063926309657e-07, 'epoch': 0.9} + 90%|█████████ | 10798/11952 [2:43:39<1:53:47, 5.92s/it] 90%|█████████ | 10799/11952 [2:43:44<1:53:07, 5.89s/it] {'loss': 0.4586, 'learning_rate': 4.841730378396592e-07, 'epoch': 0.9} + 90%|█████████ | 10799/11952 [2:43:44<1:53:07, 5.89s/it]03 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... + 90%|█████████ | 10800/11952 [2:43:50<1:52:01, 5.83s/it]1 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4559, 'learning_rate': 4.833403818511062e-07, 'epoch': 0.9} + 90%|█████████ | 10800/11952 [2:43:50<1:52:01, 5.83s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-10800/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-10800/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/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( + 90%|█████████ | 10801/11952 [2:44:28<4:54:16, 15.34s/it] {'loss': 0.4566, 'learning_rate': 4.825084247264522e-07, 'epoch': 0.9} + 90%|█████████ | 10801/11952 [2:44:28<4:54:16, 15.34s/it] 90%|█████████ | 10802/11952 [2:44:33<3:58:15, 12.43s/it] {'loss': 0.4449, 'learning_rate': 4.816771665267939e-07, 'epoch': 0.9} + 90%|█████████ | 10802/11952 [2:44:33<3:58:15, 12.43s/it] 90%|█████████ | 10803/11952 [2:44:39<3:19:39, 10.43s/it] {'loss': 0.4585, 'learning_rate': 4.808466073131735e-07, 'epoch': 0.9} + 90%|█████████ | 10803/11952 [2:44:39<3:19:39, 10.43s/it] 90%|█████████ | 10804/11952 [2:44:45<2:53:24, 9.06s/it] {'loss': 0.4537, 'learning_rate': 4.800167471465844e-07, 'epoch': 0.9} + 90%|█████████ | 10804/11952 [2:44:45<2:53:24, 9.06s/it] 90%|█████████ | 10805/11952 [2:44:50<2:33:19, 8.02s/it] {'loss': 0.4585, 'learning_rate': 4.791875860879703e-07, 'epoch': 0.9} + 90%|█████████ | 10805/11952 [2:44:50<2:33:19, 8.02s/it] 90%|█████████ | 10806/11952 [2:44:57<2:22:33, 7.46s/it] {'loss': 0.4525, 'learning_rate': 4.783591241982199e-07, 'epoch': 0.9} + 90%|█████████ | 10806/11952 [2:44:57<2:22:33, 7.46s/it] 90%|█████████ | 10807/11952 [2:45:03<2:14:30, 7.05s/it] {'loss': 0.4708, 'learning_rate': 4.775313615381716e-07, 'epoch': 0.9} + 90%|█████████ | 10807/11952 [2:45:03<2:14:30, 7.05s/it] 90%|█████████ | 10808/11952 [2:45:08<2:07:02, 6.66s/it] {'loss': 0.4424, 'learning_rate': 4.767042981686143e-07, 'epoch': 0.9} + 90%|█████████ | 10808/11952 [2:45:08<2:07:02, 6.66s/it] 90%|█████████ | 10809/11952 [2:45:14<2:01:32, 6.38s/it] {'loss': 0.47, 'learning_rate': 4.758779341502817e-07, 'epoch': 0.9} + 90%|█████████ | 10809/11952 [2:45:14<2:01:32, 6.38s/it] 90%|█████████ | 10810/11952 [2:45:20<1:59:06, 6.26s/it] {'loss': 0.453, 'learning_rate': 4.750522695438597e-07, 'epoch': 0.9} + 90%|█████████ | 10810/11952 [2:45:20<1:59:06, 6.26s/it] 90%|█████████ | 10811/11952 [2:45:26<1:56:13, 6.11s/it] {'loss': 0.4558, 'learning_rate': 4.742273044099821e-07, 'epoch': 0.9} + 90%|█████████ | 10811/11952 [2:45:26<1:56:13, 6.11s/it] 90%|█████████ | 10812/11952 [2:45:32<1:54:37, 6.03s/it] {'loss': 0.4708, 'learning_rate': 4.7340303880923145e-07, 'epoch': 0.9} + 90%|█████████ | 10812/11952 [2:45:32<1:54:37, 6.03s/it] 90%|█████████ | 10813/11952 [2:45:38<1:54:41, 6.04s/it] {'loss': 0.4453, 'learning_rate': 4.7257947280213713e-07, 'epoch': 0.9} + 90%|█████████ | 10813/11952 [2:45:38<1:54:41, 6.04s/it] 90%|█████████ | 10814/11952 [2:45:44<1:54:15, 6.02s/it] {'loss': 0.4709, 'learning_rate': 4.7175660644917745e-07, 'epoch': 0.9} + 90%|█████████ | 10814/11952 [2:45:44<1:54:15, 6.02s/it] 90%|█████████ | 10815/11952 [2:45:50<1:54:31, 6.04s/it] {'loss': 0.4792, 'learning_rate': 4.709344398107829e-07, 'epoch': 0.9} + 90%|█████████ | 10815/11952 [2:45:50<1:54:31, 6.04s/it] 90%|█████████ | 10816/11952 [2:45:56<1:53:33, 6.00s/it] {'loss': 0.4693, 'learning_rate': 4.701129729473286e-07, 'epoch': 0.9} + 90%|█████████ | 10816/11952 [2:45:56<1:53:33, 6.00s/it] 91%|█████████ | 10817/11952 [2:46:02<1:55:22, 6.10s/it] {'loss': 0.4548, 'learning_rate': 4.6929220591913847e-07, 'epoch': 0.9} + 91%|█████████ | 10817/11952 [2:46:02<1:55:22, 6.10s/it] 91%|█████████ | 10818/11952 [2:46:08<1:53:38, 6.01s/it] {'loss': 0.4827, 'learning_rate': 4.6847213878648876e-07, 'epoch': 0.91} + 91%|█████████ | 10818/11952 [2:46:08<1:53:38, 6.01s/it] 91%|█████████ | 10819/11952 [2:46:14<1:54:32, 6.07s/it] {'loss': 0.4751, 'learning_rate': 4.6765277160960133e-07, 'epoch': 0.91} + 91%|█████████ | 10819/11952 [2:46:14<1:54:32, 6.07s/it] 91%|█████████ | 10820/11952 [2:46:20<1:53:54, 6.04s/it] {'loss': 0.4529, 'learning_rate': 4.6683410444864573e-07, 'epoch': 0.91} + 91%|█████████ | 10820/11952 [2:46:20<1:53:54, 6.04s/it] 91%|█████████ | 10821/11952 [2:46:26<1:53:42, 6.03s/it] {'loss': 0.4748, 'learning_rate': 4.6601613736374173e-07, 'epoch': 0.91} + 91%|█████████ | 10821/11952 [2:46:26<1:53:42, 6.03s/it] 91%|█████████ | 10822/11952 [2:46:32<1:53:41, 6.04s/it] {'loss': 0.4607, 'learning_rate': 4.6519887041495905e-07, 'epoch': 0.91} + 91%|█████████ | 10822/11952 [2:46:32<1:53:41, 6.04s/it] 91%|█████████ | 10823/11952 [2:46:38<1:51:58, 5.95s/it] {'loss': 0.4451, 'learning_rate': 4.6438230366231075e-07, 'epoch': 0.91} + 91%|█████████ | 10823/11952 [2:46:38<1:51:58, 5.95s/it] 91%|█████████ | 10824/11952 [2:46:44<1:50:42, 5.89s/it] {'loss': 0.4693, 'learning_rate': 4.6356643716576557e-07, 'epoch': 0.91} + 91%|█████████ | 10824/11952 [2:46:44<1:50:42, 5.89s/it] 91%|█████████ | 10825/11952 [2:46:50<1:53:20, 6.03s/it] {'loss': 0.4662, 'learning_rate': 4.627512709852355e-07, 'epoch': 0.91} + 91%|█████████ | 10825/11952 [2:46:50<1:53:20, 6.03s/it] 91%|█████████ | 10826/11952 [2:46:56<1:52:22, 5.99s/it] {'loss': 0.4448, 'learning_rate': 4.61936805180585e-07, 'epoch': 0.91} + 91%|█████████ | 10826/11952 [2:46:56<1:52:22, 5.99s/it] 91%|█████████ | 10827/11952 [2:47:02<1:50:34, 5.90s/it] {'loss': 0.47, 'learning_rate': 4.611230398116229e-07, 'epoch': 0.91} + 91%|█████████ | 10827/11952 [2:47:02<1:50:34, 5.90s/it] 91%|█████████ | 10828/11952 [2:47:08<1:51:39, 5.96s/it] {'loss': 0.4645, 'learning_rate': 4.6030997493811126e-07, 'epoch': 0.91} + 91%|█████████ | 10828/11952 [2:47:08<1:51:39, 5.96s/it] 91%|█████████ | 10829/11952 [2:47:13<1:49:11, 5.83s/it] {'loss': 0.435, 'learning_rate': 4.594976106197546e-07, 'epoch': 0.91} + 91%|█████████ | 10829/11952 [2:47:13<1:49:11, 5.83s/it] 91%|█████████ | 10830/11952 [2:47:19<1:49:33, 5.86s/it] {'loss': 0.4691, 'learning_rate': 4.5868594691621304e-07, 'epoch': 0.91} + 91%|█████████ | 10830/11952 [2:47:19<1:49:33, 5.86s/it] 91%|█████████ | 10831/11952 [2:47:25<1:48:34, 5.81s/it] {'loss': 0.4661, 'learning_rate': 4.5787498388708774e-07, 'epoch': 0.91} + 91%|█████████ | 10831/11952 [2:47:25<1:48:34, 5.81s/it] 91%|█████████ | 10832/11952 [2:47:31<1:49:23, 5.86s/it] {'loss': 0.4651, 'learning_rate': 4.570647215919366e-07, 'epoch': 0.91} + 91%|█████████ | 10832/11952 [2:47:31<1:49:23, 5.86s/it] 91%|█████████ | 10833/11952 [2:47:37<1:48:25, 5.81s/it] {'loss': 0.4573, 'learning_rate': 4.5625516009026095e-07, 'epoch': 0.91} + 91%|█████████ | 10833/11952 [2:47:37<1:48:25, 5.81s/it] 91%|█████████ | 10834/11952 [2:47:43<1:49:06, 5.86s/it] {'loss': 0.4668, 'learning_rate': 4.5544629944150876e-07, 'epoch': 0.91} + 91%|█████████ | 10834/11952 [2:47:43<1:49:06, 5.86s/it] 91%|█████████ | 10835/11952 [2:47:48<1:48:28, 5.83s/it] {'loss': 0.461, 'learning_rate': 4.5463813970508364e-07, 'epoch': 0.91} + 91%|█████████ | 10835/11952 [2:47:48<1:48:28, 5.83s/it] 91%|█████████ | 10836/11952 [2:47:54<1:48:22, 5.83s/it] {'loss': 0.4437, 'learning_rate': 4.5383068094033036e-07, 'epoch': 0.91} + 91%|█████████ | 10836/11952 [2:47:54<1:48:22, 5.83s/it] 91%|█████████ | 10837/11952 [2:48:00<1:49:35, 5.90s/it] {'loss': 0.4601, 'learning_rate': 4.53023923206547e-07, 'epoch': 0.91} + 91%|█████████ | 10837/11952 [2:48:00<1:49:35, 5.90s/it] 91%|█████████ | 10838/11952 [2:48:06<1:49:07, 5.88s/it] {'loss': 0.4662, 'learning_rate': 4.5221786656297727e-07, 'epoch': 0.91} + 91%|█████████ | 10838/11952 [2:48:06<1:49:07, 5.88s/it] 91%|█████████ | 10839/11952 [2:48:12<1:47:46, 5.81s/it] {'loss': 0.4571, 'learning_rate': 4.51412511068815e-07, 'epoch': 0.91} + 91%|█████████ | 10839/11952 [2:48:12<1:47:46, 5.81s/it] 91%|█████████ | 10840/11952 [2:48:18<1:48:43, 5.87s/it] {'loss': 0.4747, 'learning_rate': 4.5060785678320397e-07, 'epoch': 0.91} + 91%|█████████ | 10840/11952 [2:48:18<1:48:43, 5.87s/it] 91%|█████████ | 10841/11952 [2:48:23<1:48:12, 5.84s/it] {'loss': 0.4635, 'learning_rate': 4.498039037652313e-07, 'epoch': 0.91} + 91%|█████████ | 10841/11952 [2:48:23<1:48:12, 5.84s/it] 91%|█████████ | 10842/11952 [2:48:29<1:46:38, 5.76s/it] {'loss': 0.4445, 'learning_rate': 4.490006520739387e-07, 'epoch': 0.91} + 91%|█████████ | 10842/11952 [2:48:29<1:46:38, 5.76s/it] 91%|█████████ | 10843/11952 [2:48:35<1:46:56, 5.79s/it] {'loss': 0.4579, 'learning_rate': 4.4819810176831235e-07, 'epoch': 0.91} + 91%|█████████ | 10843/11952 [2:48:35<1:46:56, 5.79s/it] 91%|█████████ | 10844/11952 [2:48:41<1:46:44, 5.78s/it] {'loss': 0.4499, 'learning_rate': 4.473962529072873e-07, 'epoch': 0.91} + 91%|█████████ | 10844/11952 [2:48:41<1:46:44, 5.78s/it] 91%|█████████ | 10845/11952 [2:48:47<1:47:14, 5.81s/it] {'loss': 0.4692, 'learning_rate': 4.465951055497497e-07, 'epoch': 0.91} + 91%|█████████ | 10845/11952 [2:48:47<1:47:14, 5.81s/it] 91%|█████████ | 10846/11952 [2:48:52<1:47:18, 5.82s/it] {'loss': 0.4776, 'learning_rate': 4.4579465975453264e-07, 'epoch': 0.91} + 91%|█████████ | 10846/11952 [2:48:52<1:47:18, 5.82s/it] 91%|█████████ | 10847/11952 [2:48:58<1:48:29, 5.89s/it] {'loss': 0.4795, 'learning_rate': 4.4499491558041673e-07, 'epoch': 0.91} + 91%|█████████ | 10847/11952 [2:48:58<1:48:29, 5.89s/it] 91%|█████████ | 10848/11952 [2:49:04<1:48:20, 5.89s/it] {'loss': 0.4559, 'learning_rate': 4.4419587308613285e-07, 'epoch': 0.91} + 91%|█████████ | 10848/11952 [2:49:04<1:48:20, 5.89s/it] 91%|█████████ | 10849/11952 [2:49:10<1:48:28, 5.90s/it] {'loss': 0.4781, 'learning_rate': 4.433975323303574e-07, 'epoch': 0.91} + 91%|█████████ | 10849/11952 [2:49:10<1:48:28, 5.90s/it]2 AutoResumeHook: Checking whether to suspend... +50 4AutoResumeHook: Checking whether to suspend... +AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend...3 AutoResumeHook: Checking whether to suspend... + + 91%|█████████ | 10850/11952 [2:49:16<1:48:22, 5.90s/it]6 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4636, 'learning_rate': 4.42599893371719e-07, 'epoch': 0.91} + 91%|█████████ | 10850/11952 [2:49:16<1:48:22, 5.90s/it] 91%|█████████ | 10851/11952 [2:49:22<1:49:13, 5.95s/it] {'loss': 0.462, 'learning_rate': 4.418029562687898e-07, 'epoch': 0.91} + 91%|█████████ | 10851/11952 [2:49:22<1:49:13, 5.95s/it] 91%|█████████ | 10852/11952 [2:49:28<1:47:16, 5.85s/it] {'loss': 0.4626, 'learning_rate': 4.4100672108009837e-07, 'epoch': 0.91} + 91%|█████████ | 10852/11952 [2:49:28<1:47:16, 5.85s/it] 91%|█████████ | 10853/11952 [2:49:34<1:48:47, 5.94s/it] {'loss': 0.4657, 'learning_rate': 4.4021118786411465e-07, 'epoch': 0.91} + 91%|█████████ | 10853/11952 [2:49:34<1:48:47, 5.94s/it] 91%|█████████ | 10854/11952 [2:49:40<1:47:48, 5.89s/it] {'loss': 0.4566, 'learning_rate': 4.3941635667925866e-07, 'epoch': 0.91} + 91%|█████████ | 10854/11952 [2:49:40<1:47:48, 5.89s/it] 91%|█████████ | 10855/11952 [2:49:46<1:47:23, 5.87s/it] {'loss': 0.4768, 'learning_rate': 4.3862222758389806e-07, 'epoch': 0.91} + 91%|█████████ | 10855/11952 [2:49:46<1:47:23, 5.87s/it] 91%|█████████ | 10856/11952 [2:49:51<1:46:42, 5.84s/it] {'loss': 0.4521, 'learning_rate': 4.3782880063635403e-07, 'epoch': 0.91} + 91%|█████████ | 10856/11952 [2:49:51<1:46:42, 5.84s/it] 91%|█████████ | 10857/11952 [2:49:58<1:49:26, 6.00s/it] {'loss': 0.471, 'learning_rate': 4.3703607589489105e-07, 'epoch': 0.91} + 91%|█████████ | 10857/11952 [2:49:58<1:49:26, 6.00s/it] 91%|█████████ | 10858/11952 [2:50:04<1:48:38, 5.96s/it] {'loss': 0.4468, 'learning_rate': 4.362440534177226e-07, 'epoch': 0.91} + 91%|█████████ | 10858/11952 [2:50:04<1:48:38, 5.96s/it] 91%|█████████ | 10859/11952 [2:50:09<1:47:46, 5.92s/it] {'loss': 0.4578, 'learning_rate': 4.3545273326301205e-07, 'epoch': 0.91} + 91%|█████████ | 10859/11952 [2:50:09<1:47:46, 5.92s/it] 91%|█████████ | 10860/11952 [2:50:15<1:47:20, 5.90s/it] {'loss': 0.4488, 'learning_rate': 4.3466211548887195e-07, 'epoch': 0.91} + 91%|█████████ | 10860/11952 [2:50:15<1:47:20, 5.90s/it] 91%|█████████ | 10861/11952 [2:50:21<1:48:20, 5.96s/it] {'loss': 0.4784, 'learning_rate': 4.338722001533602e-07, 'epoch': 0.91} + 91%|█████████ | 10861/11952 [2:50:21<1:48:20, 5.96s/it] 91%|█████████ | 10862/11952 [2:50:27<1:46:15, 5.85s/it] {'loss': 0.4639, 'learning_rate': 4.3308298731448596e-07, 'epoch': 0.91} + 91%|█████████ | 10862/11952 [2:50:27<1:46:15, 5.85s/it] 91%|█████████ | 10863/11952 [2:50:33<1:45:29, 5.81s/it] {'loss': 0.4591, 'learning_rate': 4.322944770302051e-07, 'epoch': 0.91} + 91%|█████████ | 10863/11952 [2:50:33<1:45:29, 5.81s/it] 91%|█████████ | 10864/11952 [2:50:38<1:45:10, 5.80s/it] {'loss': 0.4511, 'learning_rate': 4.3150666935842243e-07, 'epoch': 0.91} + 91%|█████████ | 10864/11952 [2:50:38<1:45:10, 5.80s/it] 91%|█████████ | 10865/11952 [2:50:44<1:44:37, 5.77s/it] {'loss': 0.459, 'learning_rate': 4.307195643569917e-07, 'epoch': 0.91} + 91%|█████████ | 10865/11952 [2:50:44<1:44:37, 5.77s/it] 91%|█████████ | 10866/11952 [2:50:50<1:44:47, 5.79s/it] {'loss': 0.4785, 'learning_rate': 4.299331620837133e-07, 'epoch': 0.91} + 91%|█████████ | 10866/11952 [2:50:50<1:44:47, 5.79s/it] 91%|█████████ | 10867/11952 [2:50:56<1:44:13, 5.76s/it] {'loss': 0.4438, 'learning_rate': 4.29147462596341e-07, 'epoch': 0.91} + 91%|█████████ | 10867/11952 [2:50:56<1:44:13, 5.76s/it] 91%|█████████ | 10868/11952 [2:51:02<1:45:19, 5.83s/it] {'loss': 0.465, 'learning_rate': 4.283624659525698e-07, 'epoch': 0.91} + 91%|█████████ | 10868/11952 [2:51:02<1:45:19, 5.83s/it] 91%|█████████ | 10869/11952 [2:51:08<1:46:48, 5.92s/it] {'loss': 0.4592, 'learning_rate': 4.2757817221004803e-07, 'epoch': 0.91} + 91%|█████████ | 10869/11952 [2:51:08<1:46:48, 5.92s/it] 91%|█████████ | 10870/11952 [2:51:14<1:47:49, 5.98s/it] {'loss': 0.4657, 'learning_rate': 4.267945814263708e-07, 'epoch': 0.91} + 91%|█████████ | 10870/11952 [2:51:14<1:47:49, 5.98s/it] 91%|█████████ | 10871/11952 [2:51:20<1:48:18, 6.01s/it] {'loss': 0.4765, 'learning_rate': 4.2601169365908077e-07, 'epoch': 0.91} + 91%|█████████ | 10871/11952 [2:51:20<1:48:18, 6.01s/it] 91%|█████████ | 10872/11952 [2:51:26<1:47:34, 5.98s/it] {'loss': 0.4664, 'learning_rate': 4.2522950896566994e-07, 'epoch': 0.91} + 91%|█████████ | 10872/11952 [2:51:26<1:47:34, 5.98s/it] 91%|█████████ | 10873/11952 [2:51:32<1:46:38, 5.93s/it] {'loss': 0.4634, 'learning_rate': 4.2444802740358114e-07, 'epoch': 0.91} + 91%|█████████ | 10873/11952 [2:51:32<1:46:38, 5.93s/it] 91%|█████████ | 10874/11952 [2:51:38<1:47:21, 5.98s/it] {'loss': 0.4695, 'learning_rate': 4.2366724903020076e-07, 'epoch': 0.91} + 91%|█████████ | 10874/11952 [2:51:38<1:47:21, 5.98s/it] 91%|█████████ | 10875/11952 [2:51:44<1:47:29, 5.99s/it] {'loss': 0.4691, 'learning_rate': 4.2288717390286614e-07, 'epoch': 0.91} + 91%|█████████ | 10875/11952 [2:51:44<1:47:29, 5.99s/it] 91%|█████████ | 10876/11952 [2:51:50<1:47:52, 6.02s/it] {'loss': 0.4936, 'learning_rate': 4.2210780207886383e-07, 'epoch': 0.91} + 91%|█████████ | 10876/11952 [2:51:50<1:47:52, 6.02s/it] 91%|█████████ | 10877/11952 [2:51:56<1:45:50, 5.91s/it] {'loss': 0.4619, 'learning_rate': 4.2132913361542683e-07, 'epoch': 0.91} + 91%|█████████ | 10877/11952 [2:51:56<1:45:50, 5.91s/it] 91%|█████████ | 10878/11952 [2:52:02<1:47:53, 6.03s/it] {'loss': 0.4653, 'learning_rate': 4.205511685697372e-07, 'epoch': 0.91} + 91%|█████████ | 10878/11952 [2:52:02<1:47:53, 6.03s/it] 91%|█████████ | 10879/11952 [2:52:08<1:46:32, 5.96s/it] {'loss': 0.4641, 'learning_rate': 4.1977390699892706e-07, 'epoch': 0.91} + 91%|█████████ | 10879/11952 [2:52:08<1:46:32, 5.96s/it] 91%|█████████ | 10880/11952 [2:52:14<1:46:45, 5.97s/it] {'loss': 0.4697, 'learning_rate': 4.1899734896007404e-07, 'epoch': 0.91} + 91%|█████████ | 10880/11952 [2:52:14<1:46:45, 5.97s/it] 91%|█████████ | 10881/11952 [2:52:19<1:45:17, 5.90s/it] {'loss': 0.4413, 'learning_rate': 4.1822149451020475e-07, 'epoch': 0.91} + 91%|█████████ | 10881/11952 [2:52:19<1:45:17, 5.90s/it] 91%|█████████ | 10882/11952 [2:52:25<1:44:09, 5.84s/it] {'loss': 0.4594, 'learning_rate': 4.1744634370629587e-07, 'epoch': 0.91} + 91%|█████████ | 10882/11952 [2:52:25<1:44:09, 5.84s/it] 91%|█████████ | 10883/11952 [2:52:31<1:45:23, 5.92s/it] {'loss': 0.4503, 'learning_rate': 4.166718966052696e-07, 'epoch': 0.91} + 91%|█████████ | 10883/11952 [2:52:31<1:45:23, 5.92s/it] 91%|█████████ | 10884/11952 [2:52:37<1:45:44, 5.94s/it] {'loss': 0.4772, 'learning_rate': 4.158981532640005e-07, 'epoch': 0.91} + 91%|█████████ | 10884/11952 [2:52:37<1:45:44, 5.94s/it] 91%|█████████ | 10885/11952 [2:52:43<1:45:11, 5.92s/it] {'loss': 0.4692, 'learning_rate': 4.1512511373930533e-07, 'epoch': 0.91} + 91%|█████████ | 10885/11952 [2:52:43<1:45:11, 5.92s/it] 91%|█████████ | 10886/11952 [2:52:49<1:46:41, 6.01s/it] {'loss': 0.4666, 'learning_rate': 4.143527780879575e-07, 'epoch': 0.91} + 91%|█████████ | 10886/11952 [2:52:49<1:46:41, 6.01s/it] 91%|█████████ | 10887/11952 [2:52:55<1:45:40, 5.95s/it] {'loss': 0.4712, 'learning_rate': 4.1358114636667056e-07, 'epoch': 0.91} + 91%|█████████ | 10887/11952 [2:52:55<1:45:40, 5.95s/it] 91%|█████████ | 10888/11952 [2:53:01<1:45:50, 5.97s/it] {'loss': 0.4737, 'learning_rate': 4.128102186321126e-07, 'epoch': 0.91} + 91%|█████████ | 10888/11952 [2:53:01<1:45:50, 5.97s/it] 91%|█████████ | 10889/11952 [2:53:07<1:44:44, 5.91s/it] {'loss': 0.45, 'learning_rate': 4.1203999494089596e-07, 'epoch': 0.91} + 91%|█████████ | 10889/11952 [2:53:07<1:44:44, 5.91s/it] 91%|█████████ | 10890/11952 [2:53:13<1:45:21, 5.95s/it] {'loss': 0.4695, 'learning_rate': 4.112704753495822e-07, 'epoch': 0.91} + 91%|█████████ | 10890/11952 [2:53:13<1:45:21, 5.95s/it] 91%|█████████ | 10891/11952 [2:53:19<1:45:24, 5.96s/it] {'loss': 0.4741, 'learning_rate': 4.1050165991468273e-07, 'epoch': 0.91} + 91%|█████████ | 10891/11952 [2:53:19<1:45:24, 5.96s/it] 91%|█████████ | 10892/11952 [2:53:25<1:45:54, 5.99s/it] {'loss': 0.4438, 'learning_rate': 4.097335486926546e-07, 'epoch': 0.91} + 91%|█████████ | 10892/11952 [2:53:25<1:45:54, 5.99s/it] 91%|█████████ | 10893/11952 [2:53:31<1:45:17, 5.97s/it] {'loss': 0.4623, 'learning_rate': 4.08966141739906e-07, 'epoch': 0.91} + 91%|█████████ | 10893/11952 [2:53:31<1:45:17, 5.97s/it] 91%|█████████ | 10894/11952 [2:53:37<1:44:20, 5.92s/it] {'loss': 0.4615, 'learning_rate': 4.08199439112793e-07, 'epoch': 0.91} + 91%|█████████ | 10894/11952 [2:53:37<1:44:20, 5.92s/it] 91%|█████████ | 10895/11952 [2:53:42<1:43:29, 5.87s/it] {'loss': 0.4557, 'learning_rate': 4.0743344086761725e-07, 'epoch': 0.91} + 91%|█████████ | 10895/11952 [2:53:42<1:43:29, 5.87s/it] 91%|█████████ | 10896/11952 [2:53:48<1:42:42, 5.84s/it] {'loss': 0.482, 'learning_rate': 4.066681470606304e-07, 'epoch': 0.91} + 91%|█████████ | 10896/11952 [2:53:48<1:42:42, 5.84s/it] 91%|█████████ | 10897/11952 [2:53:54<1:44:07, 5.92s/it] {'loss': 0.4708, 'learning_rate': 4.0590355774803416e-07, 'epoch': 0.91} + 91%|█████████ | 10897/11952 [2:53:54<1:44:07, 5.92s/it] 91%|█████████ | 10898/11952 [2:54:00<1:43:58, 5.92s/it] {'loss': 0.4756, 'learning_rate': 4.051396729859758e-07, 'epoch': 0.91} + 91%|█████████ | 10898/11952 [2:54:00<1:43:58, 5.92s/it] 91%|█████████ | 10899/11952 [2:54:06<1:44:26, 5.95s/it] {'loss': 0.466, 'learning_rate': 4.043764928305505e-07, 'epoch': 0.91} + 91%|█████████ | 10899/11952 [2:54:06<1:44:26, 5.95s/it]1 AutoResumeHook: Checking whether to suspend... +04 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... +5 2AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... + 7 AutoResumeHook: Checking whether to suspend... +AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... + 91%|█████████ | 10900/11952 [2:54:12<1:43:59, 5.93s/it] {'loss': 0.4491, 'learning_rate': 4.036140173378045e-07, 'epoch': 0.91} + 91%|█████████ | 10900/11952 [2:54:12<1:43:59, 5.93s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-10900/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-10900/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/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( + 91%|█████████ | 10901/11952 [2:54:44<3:59:18, 13.66s/it] {'loss': 0.4952, 'learning_rate': 4.028522465637319e-07, 'epoch': 0.91} + 91%|█████████ | 10901/11952 [2:54:44<3:59:18, 13.66s/it] 91%|█████████ | 10902/11952 [2:54:50<3:17:53, 11.31s/it] {'loss': 0.4506, 'learning_rate': 4.0209118056427356e-07, 'epoch': 0.91} + 91%|█████████ | 10902/11952 [2:54:50<3:17:53, 11.31s/it] 91%|█████████ | 10903/11952 [2:54:55<2:48:30, 9.64s/it] {'loss': 0.4513, 'learning_rate': 4.013308193953169e-07, 'epoch': 0.91} + 91%|█████████ | 10903/11952 [2:54:55<2:48:30, 9.64s/it] 91%|█████████ | 10904/11952 [2:55:01<2:28:04, 8.48s/it] {'loss': 0.4536, 'learning_rate': 4.0057116311270073e-07, 'epoch': 0.91} + 91%|█████████ | 10904/11952 [2:55:01<2:28:04, 8.48s/it] 91%|█████████ | 10905/11952 [2:55:07<2:14:09, 7.69s/it] {'loss': 0.4479, 'learning_rate': 3.998122117722125e-07, 'epoch': 0.91} + 91%|█████████ | 10905/11952 [2:55:07<2:14:09, 7.69s/it] 91%|█████████ | 10906/11952 [2:55:13<2:03:28, 7.08s/it] {'loss': 0.4539, 'learning_rate': 3.990539654295833e-07, 'epoch': 0.91} + 91%|█████████ | 10906/11952 [2:55:13<2:03:28, 7.08s/it] 91%|█████████▏| 10907/11952 [2:55:18<1:56:04, 6.66s/it] {'loss': 0.4578, 'learning_rate': 3.982964241404974e-07, 'epoch': 0.91} + 91%|█████████▏| 10907/11952 [2:55:18<1:56:04, 6.66s/it] 91%|█████████▏| 10908/11952 [2:55:25<1:53:31, 6.52s/it] {'loss': 0.4572, 'learning_rate': 3.975395879605881e-07, 'epoch': 0.91} + 91%|█████████▏| 10908/11952 [2:55:25<1:53:31, 6.52s/it] 91%|█████████▏| 10909/11952 [2:55:30<1:49:47, 6.32s/it] {'loss': 0.4333, 'learning_rate': 3.96783456945431e-07, 'epoch': 0.91} + 91%|█████████▏| 10909/11952 [2:55:30<1:49:47, 6.32s/it] 91%|█████████▏| 10910/11952 [2:55:36<1:46:04, 6.11s/it] {'loss': 0.4491, 'learning_rate': 3.960280311505538e-07, 'epoch': 0.91} + 91%|█████████▏| 10910/11952 [2:55:36<1:46:04, 6.11s/it] 91%|█████████▏| 10911/11952 [2:55:42<1:44:55, 6.05s/it] {'loss': 0.4693, 'learning_rate': 3.9527331063143215e-07, 'epoch': 0.91} + 91%|█████████▏| 10911/11952 [2:55:42<1:44:55, 6.05s/it] 91%|█████████▏| 10912/11952 [2:55:48<1:43:15, 5.96s/it] {'loss': 0.4599, 'learning_rate': 3.9451929544348956e-07, 'epoch': 0.91} + 91%|█████████▏| 10912/11952 [2:55:48<1:43:15, 5.96s/it] 91%|█████████▏| 10913/11952 [2:55:53<1:41:58, 5.89s/it] {'loss': 0.4722, 'learning_rate': 3.9376598564209614e-07, 'epoch': 0.91} + 91%|█████████▏| 10913/11952 [2:55:53<1:41:58, 5.89s/it] 91%|█████████▏| 10914/11952 [2:56:00<1:43:26, 5.98s/it] {'loss': 0.4704, 'learning_rate': 3.9301338128257536e-07, 'epoch': 0.91} + 91%|█████████▏| 10914/11952 [2:56:00<1:43:26, 5.98s/it] 91%|█████████▏| 10915/11952 [2:56:06<1:43:08, 5.97s/it] {'loss': 0.4599, 'learning_rate': 3.922614824201931e-07, 'epoch': 0.91} + 91%|█████████▏| 10915/11952 [2:56:06<1:43:08, 5.97s/it] 91%|█████████▏| 10916/11952 [2:56:11<1:41:28, 5.88s/it] {'loss': 0.4563, 'learning_rate': 3.915102891101652e-07, 'epoch': 0.91} + 91%|█████████▏| 10916/11952 [2:56:11<1:41:28, 5.88s/it] 91%|█████████▏| 10917/11952 [2:56:17<1:41:07, 5.86s/it] {'loss': 0.4605, 'learning_rate': 3.9075980140765637e-07, 'epoch': 0.91} + 91%|█████████▏| 10917/11952 [2:56:17<1:41:07, 5.86s/it] 91%|█████████▏| 10918/11952 [2:56:23<1:41:51, 5.91s/it] {'loss': 0.4588, 'learning_rate': 3.900100193677814e-07, 'epoch': 0.91} + 91%|█████████▏| 10918/11952 [2:56:23<1:41:51, 5.91s/it] 91%|█████████▏| 10919/11952 [2:56:29<1:42:22, 5.95s/it] {'loss': 0.4697, 'learning_rate': 3.892609430455985e-07, 'epoch': 0.91} + 91%|█████████▏| 10919/11952 [2:56:29<1:42:22, 5.95s/it] 91%|█████████▏| 10920/11952 [2:56:35<1:42:11, 5.94s/it] {'loss': 0.4797, 'learning_rate': 3.885125724961192e-07, 'epoch': 0.91} + 91%|█████████▏| 10920/11952 [2:56:35<1:42:11, 5.94s/it] 91%|█████████▏| 10921/11952 [2:56:41<1:41:55, 5.93s/it] {'loss': 0.4523, 'learning_rate': 3.877649077742984e-07, 'epoch': 0.91} + 91%|█████████▏| 10921/11952 [2:56:41<1:41:55, 5.93s/it] 91%|█████████▏| 10922/11952 [2:56:47<1:40:59, 5.88s/it] {'loss': 0.4725, 'learning_rate': 3.8701794893504343e-07, 'epoch': 0.91} + 91%|█████████▏| 10922/11952 [2:56:47<1:40:59, 5.88s/it] 91%|█████████▏| 10923/11952 [2:56:53<1:41:21, 5.91s/it] {'loss': 0.4492, 'learning_rate': 3.862716960332058e-07, 'epoch': 0.91} + 91%|█████████▏| 10923/11952 [2:56:53<1:41:21, 5.91s/it] 91%|█████████▏| 10924/11952 [2:56:58<1:40:11, 5.85s/it] {'loss': 0.435, 'learning_rate': 3.8552614912358956e-07, 'epoch': 0.91} + 91%|█████████▏| 10924/11952 [2:56:58<1:40:11, 5.85s/it] 91%|█████████▏| 10925/11952 [2:57:05<1:42:53, 6.01s/it] {'loss': 0.4606, 'learning_rate': 3.8478130826094307e-07, 'epoch': 0.91} + 91%|█████████▏| 10925/11952 [2:57:05<1:42:53, 6.01s/it] 91%|█████████▏| 10926/11952 [2:57:11<1:44:04, 6.09s/it] {'loss': 0.4684, 'learning_rate': 3.8403717349996263e-07, 'epoch': 0.91} + 91%|█████████▏| 10926/11952 [2:57:11<1:44:04, 6.09s/it] 91%|█████████▏| 10927/11952 [2:57:17<1:44:27, 6.11s/it] {'loss': 0.4579, 'learning_rate': 3.832937448952978e-07, 'epoch': 0.91} + 91%|█████████▏| 10927/11952 [2:57:17<1:44:27, 6.11s/it] 91%|█████████▏| 10928/11952 [2:57:23<1:44:16, 6.11s/it] {'loss': 0.4772, 'learning_rate': 3.8255102250154054e-07, 'epoch': 0.91} + 91%|█████████▏| 10928/11952 [2:57:23<1:44:16, 6.11s/it] 91%|█████████▏| 10929/11952 [2:57:29<1:42:57, 6.04s/it] {'loss': 0.4719, 'learning_rate': 3.81809006373236e-07, 'epoch': 0.91} + 91%|█████████▏| 10929/11952 [2:57:29<1:42:57, 6.04s/it] 91%|█████████▏| 10930/11952 [2:57:35<1:41:02, 5.93s/it] {'loss': 0.4419, 'learning_rate': 3.8106769656487184e-07, 'epoch': 0.91} + 91%|█████████▏| 10930/11952 [2:57:35<1:41:02, 5.93s/it] 91%|█████████▏| 10931/11952 [2:57:41<1:41:17, 5.95s/it] {'loss': 0.4684, 'learning_rate': 3.803270931308889e-07, 'epoch': 0.91} + 91%|█████████▏| 10931/11952 [2:57:41<1:41:17, 5.95s/it] 91%|█████████▏| 10932/11952 [2:57:47<1:40:30, 5.91s/it] {'loss': 0.4569, 'learning_rate': 3.795871961256725e-07, 'epoch': 0.91} + 91%|█████████▏| 10932/11952 [2:57:47<1:40:30, 5.91s/it] 91%|█████████▏| 10933/11952 [2:57:52<1:39:57, 5.89s/it] {'loss': 0.4644, 'learning_rate': 3.788480056035571e-07, 'epoch': 0.91} + 91%|█████████▏| 10933/11952 [2:57:52<1:39:57, 5.89s/it] 91%|█████████▏| 10934/11952 [2:57:59<1:42:16, 6.03s/it] {'loss': 0.4834, 'learning_rate': 3.78109521618828e-07, 'epoch': 0.91} + 91%|█████████▏| 10934/11952 [2:57:59<1:42:16, 6.03s/it] 91%|█████████▏| 10935/11952 [2:58:05<1:41:26, 5.98s/it] {'loss': 0.4578, 'learning_rate': 3.773717442257141e-07, 'epoch': 0.91} + 91%|█████████▏| 10935/11952 [2:58:05<1:41:26, 5.98s/it] 91%|█████████▏| 10936/11952 [2:58:11<1:40:26, 5.93s/it] {'loss': 0.4573, 'learning_rate': 3.7663467347839766e-07, 'epoch': 0.91} + 91%|█████████▏| 10936/11952 [2:58:11<1:40:26, 5.93s/it] 92%|█████████▏| 10937/11952 [2:58:16<1:38:33, 5.83s/it] {'loss': 0.4669, 'learning_rate': 3.7589830943100205e-07, 'epoch': 0.92} + 92%|█████████▏| 10937/11952 [2:58:16<1:38:33, 5.83s/it] 92%|█████████▏| 10938/11952 [2:58:22<1:37:32, 5.77s/it] {'loss': 0.4479, 'learning_rate': 3.7516265213760507e-07, 'epoch': 0.92} + 92%|█████████▏| 10938/11952 [2:58:22<1:37:32, 5.77s/it] 92%|█████████▏| 10939/11952 [2:58:28<1:40:10, 5.93s/it] {'loss': 0.4579, 'learning_rate': 3.7442770165223133e-07, 'epoch': 0.92} + 92%|█████████▏| 10939/11952 [2:58:28<1:40:10, 5.93s/it] 92%|█████████▏| 10940/11952 [2:58:34<1:39:21, 5.89s/it] {'loss': 0.4696, 'learning_rate': 3.7369345802885095e-07, 'epoch': 0.92} + 92%|█████████▏| 10940/11952 [2:58:34<1:39:21, 5.89s/it] 92%|█████████▏| 10941/11952 [2:58:40<1:38:34, 5.85s/it] {'loss': 0.4632, 'learning_rate': 3.7295992132138416e-07, 'epoch': 0.92} + 92%|█████████▏| 10941/11952 [2:58:40<1:38:34, 5.85s/it] 92%|█████████▏| 10942/11952 [2:58:45<1:38:37, 5.86s/it] {'loss': 0.4405, 'learning_rate': 3.7222709158369895e-07, 'epoch': 0.92} + 92%|█████████▏| 10942/11952 [2:58:46<1:38:37, 5.86s/it] 92%|█████████▏| 10943/11952 [2:58:52<1:39:45, 5.93s/it] {'loss': 0.4644, 'learning_rate': 3.714949688696123e-07, 'epoch': 0.92} + 92%|█████████▏| 10943/11952 [2:58:52<1:39:45, 5.93s/it] 92%|█████████▏| 10944/11952 [2:58:58<1:40:22, 5.97s/it] {'loss': 0.4782, 'learning_rate': 3.707635532328857e-07, 'epoch': 0.92} + 92%|█████████▏| 10944/11952 [2:58:58<1:40:22, 5.97s/it] 92%|█████████▏| 10945/11952 [2:59:03<1:39:22, 5.92s/it] {'loss': 0.4324, 'learning_rate': 3.700328447272339e-07, 'epoch': 0.92} + 92%|█████████▏| 10945/11952 [2:59:03<1:39:22, 5.92s/it] 92%|█████████▏| 10946/11952 [2:59:09<1:38:32, 5.88s/it] {'loss': 0.4569, 'learning_rate': 3.693028434063151e-07, 'epoch': 0.92} + 92%|█████████▏| 10946/11952 [2:59:09<1:38:32, 5.88s/it] 92%|█████████▏| 10947/11952 [2:59:15<1:40:08, 5.98s/it] {'loss': 0.454, 'learning_rate': 3.6857354932373857e-07, 'epoch': 0.92} + 92%|█████████▏| 10947/11952 [2:59:15<1:40:08, 5.98s/it] 92%|█████████▏| 10948/11952 [2:59:21<1:38:07, 5.86s/it] {'loss': 0.4474, 'learning_rate': 3.6784496253305937e-07, 'epoch': 0.92} + 92%|█████████▏| 10948/11952 [2:59:21<1:38:07, 5.86s/it] 92%|█████████▏| 10949/11952 [2:59:27<1:39:09, 5.93s/it] {'loss': 0.4524, 'learning_rate': 3.671170830877846e-07, 'epoch': 0.92} + 92%|█████████▏| 10949/11952 [2:59:27<1:39:09, 5.93s/it]4 AutoResumeHook: Checking whether to suspend... +012 AutoResumeHook: Checking whether to suspend... +AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... + 5 AutoResumeHook: Checking whether to suspend...AutoResumeHook: Checking whether to suspend... + + 92%|█████████▏| 10950/11952 [2:59:33<1:39:08, 5.94s/it]3 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4726, 'learning_rate': 3.663899110413638e-07, 'epoch': 0.92} + 92%|█████████▏| 10950/11952 [2:59:33<1:39:08, 5.94s/it] 92%|█████████▏| 10951/11952 [2:59:39<1:37:37, 5.85s/it] {'loss': 0.4711, 'learning_rate': 3.6566344644719974e-07, 'epoch': 0.92} + 92%|█████████▏| 10951/11952 [2:59:39<1:37:37, 5.85s/it] 92%|█████████▏| 10952/11952 [2:59:45<1:37:31, 5.85s/it] {'loss': 0.441, 'learning_rate': 3.649376893586398e-07, 'epoch': 0.92} + 92%|█████████▏| 10952/11952 [2:59:45<1:37:31, 5.85s/it] 92%|█████████▏| 10953/11952 [2:59:50<1:37:07, 5.83s/it] {'loss': 0.4742, 'learning_rate': 3.6421263982898023e-07, 'epoch': 0.92} + 92%|█████████▏| 10953/11952 [2:59:50<1:37:07, 5.83s/it] 92%|█████████▏| 10954/11952 [2:59:57<1:39:54, 6.01s/it] {'loss': 0.4701, 'learning_rate': 3.634882979114662e-07, 'epoch': 0.92} + 92%|█████████▏| 10954/11952 [2:59:57<1:39:54, 6.01s/it] 92%|█████████▏| 10955/11952 [3:00:03<1:38:18, 5.92s/it] {'loss': 0.4461, 'learning_rate': 3.627646636592919e-07, 'epoch': 0.92} + 92%|█████████▏| 10955/11952 [3:00:03<1:38:18, 5.92s/it] 92%|█████████▏| 10956/11952 [3:00:09<1:39:15, 5.98s/it] {'loss': 0.4677, 'learning_rate': 3.6204173712559464e-07, 'epoch': 0.92} + 92%|█████████▏| 10956/11952 [3:00:09<1:39:15, 5.98s/it] 92%|█████████▏| 10957/11952 [3:00:15<1:38:55, 5.97s/it] {'loss': 0.4643, 'learning_rate': 3.6131951836346544e-07, 'epoch': 0.92} + 92%|█████████▏| 10957/11952 [3:00:15<1:38:55, 5.97s/it] 92%|█████████▏| 10958/11952 [3:00:20<1:37:57, 5.91s/it] {'loss': 0.4507, 'learning_rate': 3.6059800742593963e-07, 'epoch': 0.92} + 92%|█████████▏| 10958/11952 [3:00:20<1:37:57, 5.91s/it] 92%|█████████▏| 10959/11952 [3:00:26<1:37:59, 5.92s/it] {'loss': 0.4745, 'learning_rate': 3.5987720436600483e-07, 'epoch': 0.92} + 92%|█████████▏| 10959/11952 [3:00:26<1:37:59, 5.92s/it] 92%|█████████▏| 10960/11952 [3:00:32<1:36:59, 5.87s/it] {'loss': 0.4839, 'learning_rate': 3.5915710923658974e-07, 'epoch': 0.92} + 92%|█████████▏| 10960/11952 [3:00:32<1:36:59, 5.87s/it] 92%|█████████▏| 10961/11952 [3:00:38<1:36:53, 5.87s/it] {'loss': 0.458, 'learning_rate': 3.584377220905788e-07, 'epoch': 0.92} + 92%|█████████▏| 10961/11952 [3:00:38<1:36:53, 5.87s/it] 92%|█████████▏| 10962/11952 [3:00:44<1:36:56, 5.88s/it] {'loss': 0.4535, 'learning_rate': 3.5771904298079864e-07, 'epoch': 0.92} + 92%|█████████▏| 10962/11952 [3:00:44<1:36:56, 5.88s/it] 92%|█████████▏| 10963/11952 [3:00:49<1:35:12, 5.78s/it] {'loss': 0.443, 'learning_rate': 3.57001071960027e-07, 'epoch': 0.92} + 92%|█████████▏| 10963/11952 [3:00:49<1:35:12, 5.78s/it] 92%|█████████▏| 10964/11952 [3:00:55<1:34:35, 5.74s/it] {'loss': 0.4507, 'learning_rate': 3.562838090809884e-07, 'epoch': 0.92} + 92%|█████████▏| 10964/11952 [3:00:55<1:34:35, 5.74s/it] 92%|█████████▏| 10965/11952 [3:01:01<1:35:47, 5.82s/it] {'loss': 0.4554, 'learning_rate': 3.555672543963562e-07, 'epoch': 0.92} + 92%|█████████▏| 10965/11952 [3:01:01<1:35:47, 5.82s/it] 92%|█████████▏| 10966/11952 [3:01:07<1:36:19, 5.86s/it] {'loss': 0.4864, 'learning_rate': 3.548514079587495e-07, 'epoch': 0.92} + 92%|█████████▏| 10966/11952 [3:01:07<1:36:19, 5.86s/it] 92%|█████████▏| 10967/11952 [3:01:13<1:36:01, 5.85s/it] {'loss': 0.4705, 'learning_rate': 3.541362698207373e-07, 'epoch': 0.92} + 92%|█████████▏| 10967/11952 [3:01:13<1:36:01, 5.85s/it] 92%|█████████▏| 10968/11952 [3:01:18<1:34:51, 5.78s/it] {'loss': 0.451, 'learning_rate': 3.5342184003483884e-07, 'epoch': 0.92} + 92%|█████████▏| 10968/11952 [3:01:18<1:34:51, 5.78s/it] 92%|█████████▏| 10969/11952 [3:01:24<1:35:58, 5.86s/it] {'loss': 0.4559, 'learning_rate': 3.527081186535164e-07, 'epoch': 0.92} + 92%|█████████▏| 10969/11952 [3:01:24<1:35:58, 5.86s/it] 92%|█████████▏| 10970/11952 [3:01:31<1:36:56, 5.92s/it] {'loss': 0.4681, 'learning_rate': 3.5199510572918484e-07, 'epoch': 0.92} + 92%|█████████▏| 10970/11952 [3:01:31<1:36:56, 5.92s/it] 92%|█████████▏| 10971/11952 [3:01:36<1:36:01, 5.87s/it] {'loss': 0.4597, 'learning_rate': 3.5128280131420333e-07, 'epoch': 0.92} + 92%|█████████▏| 10971/11952 [3:01:36<1:36:01, 5.87s/it] 92%|█████████▏| 10972/11952 [3:01:42<1:36:47, 5.93s/it] {'loss': 0.4551, 'learning_rate': 3.505712054608801e-07, 'epoch': 0.92} + 92%|█████████▏| 10972/11952 [3:01:42<1:36:47, 5.93s/it] 92%|█████████▏| 10973/11952 [3:01:48<1:36:10, 5.89s/it] {'loss': 0.4646, 'learning_rate': 3.4986031822147325e-07, 'epoch': 0.92} + 92%|█████████▏| 10973/11952 [3:01:48<1:36:10, 5.89s/it] 92%|█████████▏| 10974/11952 [3:01:54<1:36:59, 5.95s/it] {'loss': 0.4706, 'learning_rate': 3.4915013964818556e-07, 'epoch': 0.92} + 92%|█████████▏| 10974/11952 [3:01:54<1:36:59, 5.95s/it] 92%|█████████▏| 10975/11952 [3:02:00<1:35:19, 5.85s/it] {'loss': 0.4488, 'learning_rate': 3.4844066979317193e-07, 'epoch': 0.92} + 92%|█████████▏| 10975/11952 [3:02:00<1:35:19, 5.85s/it] 92%|█████████▏| 10976/11952 [3:02:06<1:36:07, 5.91s/it] {'loss': 0.4767, 'learning_rate': 3.477319087085318e-07, 'epoch': 0.92} + 92%|█████████▏| 10976/11952 [3:02:06<1:36:07, 5.91s/it] 92%|█████████▏| 10977/11952 [3:02:12<1:36:40, 5.95s/it] {'loss': 0.4695, 'learning_rate': 3.470238564463135e-07, 'epoch': 0.92} + 92%|█████████▏| 10977/11952 [3:02:12<1:36:40, 5.95s/it] 92%|█████████▏| 10978/11952 [3:02:18<1:36:43, 5.96s/it] {'loss': 0.4663, 'learning_rate': 3.4631651305851224e-07, 'epoch': 0.92} + 92%|█████████▏| 10978/11952 [3:02:18<1:36:43, 5.96s/it] 92%|█████████▏| 10979/11952 [3:02:24<1:35:04, 5.86s/it] {'loss': 0.455, 'learning_rate': 3.4560987859707407e-07, 'epoch': 0.92} + 92%|█████████▏| 10979/11952 [3:02:24<1:35:04, 5.86s/it] 92%|█████████▏| 10980/11952 [3:02:29<1:34:59, 5.86s/it] {'loss': 0.4549, 'learning_rate': 3.44903953113892e-07, 'epoch': 0.92} + 92%|█████████▏| 10980/11952 [3:02:29<1:34:59, 5.86s/it] 92%|█████████▏| 10981/11952 [3:02:36<1:36:21, 5.95s/it] {'loss': 0.4622, 'learning_rate': 3.4419873666080237e-07, 'epoch': 0.92} + 92%|█████████▏| 10981/11952 [3:02:36<1:36:21, 5.95s/it] 92%|█████████▏| 10982/11952 [3:02:42<1:36:42, 5.98s/it] {'loss': 0.4688, 'learning_rate': 3.434942292895982e-07, 'epoch': 0.92} + 92%|█████████▏| 10982/11952 [3:02:42<1:36:42, 5.98s/it] 92%|█████████▏| 10983/11952 [3:02:48<1:36:15, 5.96s/it] {'loss': 0.4463, 'learning_rate': 3.427904310520136e-07, 'epoch': 0.92} + 92%|█████████▏| 10983/11952 [3:02:48<1:36:15, 5.96s/it] 92%|█████████▏| 10984/11952 [3:02:53<1:35:36, 5.93s/it] {'loss': 0.4726, 'learning_rate': 3.420873419997317e-07, 'epoch': 0.92} + 92%|█████████▏| 10984/11952 [3:02:53<1:35:36, 5.93s/it] 92%|█████████▏| 10985/11952 [3:02:59<1:34:28, 5.86s/it] {'loss': 0.4541, 'learning_rate': 3.413849621843857e-07, 'epoch': 0.92} + 92%|█████████▏| 10985/11952 [3:02:59<1:34:28, 5.86s/it] 92%|█████████▏| 10986/11952 [3:03:05<1:35:14, 5.92s/it] {'loss': 0.4545, 'learning_rate': 3.406832916575542e-07, 'epoch': 0.92} + 92%|█████████▏| 10986/11952 [3:03:05<1:35:14, 5.92s/it] 92%|█████████▏| 10987/11952 [3:03:11<1:36:05, 5.97s/it] {'loss': 0.449, 'learning_rate': 3.3998233047076613e-07, 'epoch': 0.92} + 92%|█████████▏| 10987/11952 [3:03:11<1:36:05, 5.97s/it] 92%|█████████▏| 10988/11952 [3:03:17<1:35:47, 5.96s/it] {'loss': 0.4896, 'learning_rate': 3.3928207867549467e-07, 'epoch': 0.92} + 92%|█████████▏| 10988/11952 [3:03:17<1:35:47, 5.96s/it] 92%|█████████▏| 10989/11952 [3:03:23<1:34:42, 5.90s/it] {'loss': 0.4583, 'learning_rate': 3.385825363231665e-07, 'epoch': 0.92} + 92%|█████████▏| 10989/11952 [3:03:23<1:34:42, 5.90s/it] 92%|█████████▏| 10990/11952 [3:03:29<1:33:21, 5.82s/it] {'loss': 0.4388, 'learning_rate': 3.3788370346515274e-07, 'epoch': 0.92} + 92%|█████████▏| 10990/11952 [3:03:29<1:33:21, 5.82s/it] 92%|█████████▏| 10991/11952 [3:03:35<1:34:23, 5.89s/it] {'loss': 0.4818, 'learning_rate': 3.3718558015277237e-07, 'epoch': 0.92} + 92%|█████████▏| 10991/11952 [3:03:35<1:34:23, 5.89s/it] 92%|█████████▏| 10992/11952 [3:03:40<1:34:01, 5.88s/it] {'loss': 0.4601, 'learning_rate': 3.3648816643729207e-07, 'epoch': 0.92} + 92%|█████████▏| 10992/11952 [3:03:40<1:34:01, 5.88s/it] 92%|█████████▏| 10993/11952 [3:03:47<1:34:33, 5.92s/it] {'loss': 0.4561, 'learning_rate': 3.357914623699265e-07, 'epoch': 0.92} + 92%|█████████▏| 10993/11952 [3:03:47<1:34:33, 5.92s/it] 92%|█████████▏| 10994/11952 [3:03:52<1:34:05, 5.89s/it] {'loss': 0.4834, 'learning_rate': 3.3509546800183923e-07, 'epoch': 0.92} + 92%|█████████▏| 10994/11952 [3:03:52<1:34:05, 5.89s/it] 92%|█████████▏| 10995/11952 [3:03:58<1:33:44, 5.88s/it] {'loss': 0.4675, 'learning_rate': 3.344001833841426e-07, 'epoch': 0.92} + 92%|█████████▏| 10995/11952 [3:03:58<1:33:44, 5.88s/it] 92%|█████████▏| 10996/11952 [3:04:04<1:33:03, 5.84s/it] {'loss': 0.4454, 'learning_rate': 3.337056085678936e-07, 'epoch': 0.92} + 92%|█████████▏| 10996/11952 [3:04:04<1:33:03, 5.84s/it] 92%|█████████▏| 10997/11952 [3:04:10<1:32:53, 5.84s/it] {'loss': 0.4625, 'learning_rate': 3.3301174360410026e-07, 'epoch': 0.92} + 92%|█████████▏| 10997/11952 [3:04:10<1:32:53, 5.84s/it] 92%|█████████▏| 10998/11952 [3:04:16<1:33:01, 5.85s/it] {'loss': 0.462, 'learning_rate': 3.3231858854371634e-07, 'epoch': 0.92} + 92%|█████████▏| 10998/11952 [3:04:16<1:33:01, 5.85s/it] 92%|█████████▏| 10999/11952 [3:04:21<1:32:21, 5.81s/it] {'loss': 0.4516, 'learning_rate': 3.3162614343764334e-07, 'epoch': 0.92} + 92%|█████████▏| 10999/11952 [3:04:21<1:32:21, 5.81s/it]2 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +076 AutoResumeHook: Checking whether to suspend...AutoResumeHook: Checking whether to suspend... + +1 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... + 92%|█████████▏| 11000/11952 [3:04:28<1:33:48, 5.91s/it] {'loss': 0.4705, 'learning_rate': 3.309344083367327e-07, 'epoch': 0.92} + 92%|█████████▏| 11000/11952 [3:04:28<1:33:48, 5.91s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-11000/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-11000/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/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( + 92%|█████████▏| 11001/11952 [3:05:00<3:41:59, 14.01s/it] {'loss': 0.4631, 'learning_rate': 3.3024338329178285e-07, 'epoch': 0.92} + 92%|█████████▏| 11001/11952 [3:05:00<3:41:59, 14.01s/it] 92%|█████████▏| 11002/11952 [3:05:06<3:01:47, 11.48s/it] {'loss': 0.4625, 'learning_rate': 3.2955306835353863e-07, 'epoch': 0.92} + 92%|█████████▏| 11002/11952 [3:05:06<3:01:47, 11.48s/it] 92%|█████████▏| 11003/11952 [3:05:12<2:37:41, 9.97s/it] {'loss': 0.4815, 'learning_rate': 3.2886346357269614e-07, 'epoch': 0.92} + 92%|█████████▏| 11003/11952 [3:05:12<2:37:41, 9.97s/it] 92%|█████████▏| 11004/11952 [3:05:19<2:19:07, 8.80s/it] {'loss': 0.4582, 'learning_rate': 3.28174568999895e-07, 'epoch': 0.92} + 92%|█████████▏| 11004/11952 [3:05:19<2:19:07, 8.80s/it] 92%|█████████▏| 11005/11952 [3:05:24<2:05:01, 7.92s/it] {'loss': 0.4654, 'learning_rate': 3.274863846857257e-07, 'epoch': 0.92} + 92%|█████████▏| 11005/11952 [3:05:24<2:05:01, 7.92s/it] 92%|█████████▏| 11006/11952 [3:05:30<1:53:54, 7.22s/it] {'loss': 0.4465, 'learning_rate': 3.2679891068072566e-07, 'epoch': 0.92} + 92%|█████████▏| 11006/11952 [3:05:30<1:53:54, 7.22s/it] 92%|█████████▏| 11007/11952 [3:05:36<1:46:29, 6.76s/it] {'loss': 0.4808, 'learning_rate': 3.26112147035379e-07, 'epoch': 0.92} + 92%|█████████▏| 11007/11952 [3:05:36<1:46:29, 6.76s/it] 92%|█████████▏| 11008/11952 [3:05:41<1:41:35, 6.46s/it] {'loss': 0.4494, 'learning_rate': 3.254260938001186e-07, 'epoch': 0.92} + 92%|█████████▏| 11008/11952 [3:05:41<1:41:35, 6.46s/it] 92%|█████████▏| 11009/11952 [3:05:47<1:39:18, 6.32s/it] {'loss': 0.4643, 'learning_rate': 3.2474075102532756e-07, 'epoch': 0.92} + 92%|█████████▏| 11009/11952 [3:05:47<1:39:18, 6.32s/it] 92%|█████████▏| 11010/11952 [3:05:53<1:37:35, 6.22s/it] {'loss': 0.4687, 'learning_rate': 3.240561187613323e-07, 'epoch': 0.92} + 92%|█████████▏| 11010/11952 [3:05:53<1:37:35, 6.22s/it] 92%|█████████▏| 11011/11952 [3:05:59<1:35:18, 6.08s/it] {'loss': 0.4417, 'learning_rate': 3.233721970584114e-07, 'epoch': 0.92} + 92%|█████████▏| 11011/11952 [3:05:59<1:35:18, 6.08s/it] 92%|█████████▏| 11012/11952 [3:06:05<1:34:48, 6.05s/it] {'loss': 0.4668, 'learning_rate': 3.226889859667881e-07, 'epoch': 0.92} + 92%|█████████▏| 11012/11952 [3:06:05<1:34:48, 6.05s/it] 92%|█████████▏| 11013/11952 [3:06:11<1:34:35, 6.04s/it] {'loss': 0.4714, 'learning_rate': 3.220064855366345e-07, 'epoch': 0.92} + 92%|█████████▏| 11013/11952 [3:06:11<1:34:35, 6.04s/it] 92%|█████████▏| 11014/11952 [3:06:17<1:33:37, 5.99s/it] {'loss': 0.4715, 'learning_rate': 3.2132469581807046e-07, 'epoch': 0.92} + 92%|█████████▏| 11014/11952 [3:06:17<1:33:37, 5.99s/it] 92%|█████████▏| 11015/11952 [3:06:23<1:34:32, 6.05s/it] {'loss': 0.4557, 'learning_rate': 3.2064361686116377e-07, 'epoch': 0.92} + 92%|█████████▏| 11015/11952 [3:06:23<1:34:32, 6.05s/it] 92%|█████████▏| 11016/11952 [3:06:29<1:34:59, 6.09s/it] {'loss': 0.4709, 'learning_rate': 3.199632487159321e-07, 'epoch': 0.92} + 92%|█████████▏| 11016/11952 [3:06:29<1:34:59, 6.09s/it] 92%|█████████▏| 11017/11952 [3:06:35<1:33:33, 6.00s/it] {'loss': 0.4687, 'learning_rate': 3.1928359143233556e-07, 'epoch': 0.92} + 92%|█████████▏| 11017/11952 [3:06:35<1:33:33, 6.00s/it] 92%|█████████▏| 11018/11952 [3:06:41<1:33:08, 5.98s/it] {'loss': 0.4549, 'learning_rate': 3.1860464506028865e-07, 'epoch': 0.92} + 92%|█████████▏| 11018/11952 [3:06:41<1:33:08, 5.98s/it] 92%|█████████▏| 11019/11952 [3:06:47<1:32:24, 5.94s/it] {'loss': 0.4747, 'learning_rate': 3.1792640964964593e-07, 'epoch': 0.92} + 92%|█████████▏| 11019/11952 [3:06:47<1:32:24, 5.94s/it] 92%|█████████▏| 11020/11952 [3:06:53<1:32:07, 5.93s/it] {'loss': 0.4414, 'learning_rate': 3.172488852502187e-07, 'epoch': 0.92} + 92%|█████████▏| 11020/11952 [3:06:53<1:32:07, 5.93s/it] 92%|█████████▏| 11021/11952 [3:06:59<1:32:25, 5.96s/it] {'loss': 0.4593, 'learning_rate': 3.1657207191176043e-07, 'epoch': 0.92} + 92%|█████████▏| 11021/11952 [3:06:59<1:32:25, 5.96s/it] 92%|█████████▏| 11022/11952 [3:07:05<1:33:21, 6.02s/it] {'loss': 0.4616, 'learning_rate': 3.1589596968397027e-07, 'epoch': 0.92} + 92%|█████████▏| 11022/11952 [3:07:05<1:33:21, 6.02s/it] 92%|█████████▏| 11023/11952 [3:07:11<1:31:55, 5.94s/it] {'loss': 0.4688, 'learning_rate': 3.15220578616503e-07, 'epoch': 0.92} + 92%|█████████▏| 11023/11952 [3:07:11<1:31:55, 5.94s/it] 92%|█████████▏| 11024/11952 [3:07:17<1:31:38, 5.93s/it] {'loss': 0.4583, 'learning_rate': 3.1454589875895445e-07, 'epoch': 0.92} + 92%|█████████▏| 11024/11952 [3:07:17<1:31:38, 5.93s/it] 92%|█████████▏| 11025/11952 [3:07:23<1:31:33, 5.93s/it] {'loss': 0.4662, 'learning_rate': 3.1387193016086945e-07, 'epoch': 0.92} + 92%|█████████▏| 11025/11952 [3:07:23<1:31:33, 5.93s/it] 92%|█████████▏| 11026/11952 [3:07:29<1:31:24, 5.92s/it] {'loss': 0.4629, 'learning_rate': 3.131986728717429e-07, 'epoch': 0.92} + 92%|█████████▏| 11026/11952 [3:07:29<1:31:24, 5.92s/it] 92%|█████████▏| 11027/11952 [3:07:34<1:30:26, 5.87s/it] {'loss': 0.4678, 'learning_rate': 3.1252612694101515e-07, 'epoch': 0.92} + 92%|█████████▏| 11027/11952 [3:07:34<1:30:26, 5.87s/it] 92%|█████████▏| 11028/11952 [3:07:40<1:29:35, 5.82s/it] {'loss': 0.4724, 'learning_rate': 3.1185429241807453e-07, 'epoch': 0.92} + 92%|█████████▏| 11028/11952 [3:07:40<1:29:35, 5.82s/it] 92%|█████████▏| 11029/11952 [3:07:46<1:29:12, 5.80s/it] {'loss': 0.4607, 'learning_rate': 3.1118316935226043e-07, 'epoch': 0.92} + 92%|█████████▏| 11029/11952 [3:07:46<1:29:12, 5.80s/it] 92%|█████████▏| 11030/11952 [3:07:52<1:29:03, 5.80s/it] {'loss': 0.4534, 'learning_rate': 3.105127577928546e-07, 'epoch': 0.92} + 92%|█████████▏| 11030/11952 [3:07:52<1:29:03, 5.80s/it] 92%|█████████▏| 11031/11952 [3:07:57<1:29:30, 5.83s/it] {'loss': 0.4537, 'learning_rate': 3.0984305778908875e-07, 'epoch': 0.92} + 92%|█████████▏| 11031/11952 [3:07:57<1:29:30, 5.83s/it] 92%|█████████▏| 11032/11952 [3:08:03<1:30:08, 5.88s/it] {'loss': 0.4804, 'learning_rate': 3.091740693901468e-07, 'epoch': 0.92} + 92%|█████████▏| 11032/11952 [3:08:03<1:30:08, 5.88s/it] 92%|█████████▏| 11033/11952 [3:08:09<1:29:32, 5.85s/it] {'loss': 0.4322, 'learning_rate': 3.085057926451529e-07, 'epoch': 0.92} + 92%|█████████▏| 11033/11952 [3:08:09<1:29:32, 5.85s/it] 92%|█████████▏| 11034/11952 [3:08:17<1:40:29, 6.57s/it] {'loss': 0.4564, 'learning_rate': 3.078382276031833e-07, 'epoch': 0.92} + 92%|█████████▏| 11034/11952 [3:08:17<1:40:29, 6.57s/it] 92%|█████████▏| 11035/11952 [3:08:24<1:38:22, 6.44s/it] {'loss': 0.4704, 'learning_rate': 3.071713743132609e-07, 'epoch': 0.92} + 92%|█████████▏| 11035/11952 [3:08:24<1:38:22, 6.44s/it] 92%|█████████▏| 11036/11952 [3:08:30<1:36:10, 6.30s/it] {'loss': 0.4677, 'learning_rate': 3.0650523282435896e-07, 'epoch': 0.92} + 92%|█████████▏| 11036/11952 [3:08:30<1:36:10, 6.30s/it] 92%|█████████▏| 11037/11952 [3:08:36<1:35:24, 6.26s/it] {'loss': 0.467, 'learning_rate': 3.0583980318539377e-07, 'epoch': 0.92} + 92%|█████████▏| 11037/11952 [3:08:36<1:35:24, 6.26s/it] 92%|█████████▏| 11038/11952 [3:08:41<1:32:27, 6.07s/it] {'loss': 0.452, 'learning_rate': 3.051750854452329e-07, 'epoch': 0.92} + 92%|█████████▏| 11038/11952 [3:08:41<1:32:27, 6.07s/it] 92%|█████████▏| 11039/11952 [3:08:47<1:31:46, 6.03s/it] {'loss': 0.4757, 'learning_rate': 3.0451107965268956e-07, 'epoch': 0.92} + 92%|█████████▏| 11039/11952 [3:08:47<1:31:46, 6.03s/it] 92%|█████████▏| 11040/11952 [3:08:53<1:31:23, 6.01s/it] {'loss': 0.4601, 'learning_rate': 3.0384778585652477e-07, 'epoch': 0.92} + 92%|█████████▏| 11040/11952 [3:08:53<1:31:23, 6.01s/it] 92%|█████████▏| 11041/11952 [3:09:02<1:44:58, 6.91s/it] {'loss': 0.4614, 'learning_rate': 3.031852041054506e-07, 'epoch': 0.92} + 92%|█████████▏| 11041/11952 [3:09:02<1:44:58, 6.91s/it] 92%|█████████▏| 11042/11952 [3:09:08<1:40:50, 6.65s/it] {'loss': 0.4768, 'learning_rate': 3.0252333444812263e-07, 'epoch': 0.92} + 92%|█████████▏| 11042/11952 [3:09:08<1:40:50, 6.65s/it] 92%|█████████▏| 11043/11952 [3:09:15<1:39:22, 6.56s/it] {'loss': 0.4619, 'learning_rate': 3.0186217693314643e-07, 'epoch': 0.92} + 92%|█████████▏| 11043/11952 [3:09:15<1:39:22, 6.56s/it] 92%|█████████▏| 11044/11952 [3:09:23<1:46:34, 7.04s/it] {'loss': 0.4598, 'learning_rate': 3.012017316090743e-07, 'epoch': 0.92} + 92%|█████████▏| 11044/11952 [3:09:23<1:46:34, 7.04s/it] 92%|█████████▏| 11045/11952 [3:09:29<1:40:28, 6.65s/it] {'loss': 0.4628, 'learning_rate': 3.0054199852440626e-07, 'epoch': 0.92} + 92%|█████████▏| 11045/11952 [3:09:29<1:40:28, 6.65s/it] 92%|█████████▏| 11046/11952 [3:09:37<1:48:23, 7.18s/it] {'loss': 0.4393, 'learning_rate': 2.9988297772759136e-07, 'epoch': 0.92} + 92%|█████████▏| 11046/11952 [3:09:37<1:48:23, 7.18s/it] 92%|█████████▏| 11047/11952 [3:09:46<1:56:28, 7.72s/it] {'loss': 0.475, 'learning_rate': 2.992246692670242e-07, 'epoch': 0.92} + 92%|█████████▏| 11047/11952 [3:09:46<1:56:28, 7.72s/it] 92%|█████████▏| 11048/11952 [3:09:52<1:48:25, 7.20s/it] {'loss': 0.4703, 'learning_rate': 2.985670731910495e-07, 'epoch': 0.92} + 92%|█████████▏| 11048/11952 [3:09:52<1:48:25, 7.20s/it] 92%|█████████▏| 11049/11952 [3:10:01<1:55:59, 7.71s/it] {'loss': 0.4442, 'learning_rate': 2.9791018954795636e-07, 'epoch': 0.92} + 92%|█████████▏| 11049/11952 [3:10:01<1:55:59, 7.71s/it]2 AutoResumeHook: Checking whether to suspend... +03 AutoResumeHook: Checking whether to suspend...7 +5 4AutoResumeHook: Checking whether to suspend... +AutoResumeHook: Checking whether to suspend...AutoResumeHook: Checking whether to suspend... + +6 AutoResumeHook: Checking whether to suspend... +AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... + 92%|█████████▏| 11050/11952 [3:10:06<1:46:30, 7.09s/it] {'loss': 0.4694, 'learning_rate': 2.972540183859862e-07, 'epoch': 0.92} + 92%|█████████▏| 11050/11952 [3:10:06<1:46:30, 7.09s/it] 92%|█████████▏| 11051/11952 [3:10:13<1:42:10, 6.80s/it] {'loss': 0.4698, 'learning_rate': 2.9659855975332274e-07, 'epoch': 0.92} + 92%|█████████▏| 11051/11952 [3:10:13<1:42:10, 6.80s/it] 92%|█████████▏| 11052/11952 [3:10:19<1:38:11, 6.55s/it] {'loss': 0.4357, 'learning_rate': 2.959438136981019e-07, 'epoch': 0.92} + 92%|█████████▏| 11052/11952 [3:10:19<1:38:11, 6.55s/it] 92%|█████████▏| 11053/11952 [3:10:25<1:35:40, 6.39s/it] {'loss': 0.4585, 'learning_rate': 2.9528978026840625e-07, 'epoch': 0.92} + 92%|█████████▏| 11053/11952 [3:10:25<1:35:40, 6.39s/it] 92%|█████████▏| 11054/11952 [3:10:30<1:32:47, 6.20s/it] {'loss': 0.4864, 'learning_rate': 2.9463645951226415e-07, 'epoch': 0.92} + 92%|█████████▏| 11054/11952 [3:10:30<1:32:47, 6.20s/it] 92%|█████████▏| 11055/11952 [3:10:36<1:31:18, 6.11s/it] {'loss': 0.4584, 'learning_rate': 2.939838514776527e-07, 'epoch': 0.92} + 92%|█████████▏| 11055/11952 [3:10:36<1:31:18, 6.11s/it] 93%|█████████▎| 11056/11952 [3:10:42<1:29:34, 6.00s/it] {'loss': 0.4561, 'learning_rate': 2.933319562124959e-07, 'epoch': 0.92} + 93%|█████████▎| 11056/11952 [3:10:42<1:29:34, 6.00s/it] 93%|█████████▎| 11057/11952 [3:10:48<1:28:32, 5.94s/it] {'loss': 0.4795, 'learning_rate': 2.926807737646675e-07, 'epoch': 0.93} + 93%|█████████▎| 11057/11952 [3:10:48<1:28:32, 5.94s/it] 93%|█████████▎| 11058/11952 [3:10:54<1:29:23, 6.00s/it] {'loss': 0.4472, 'learning_rate': 2.920303041819872e-07, 'epoch': 0.93} + 93%|█████████▎| 11058/11952 [3:10:54<1:29:23, 6.00s/it] 93%|█████████▎| 11059/11952 [3:10:59<1:27:19, 5.87s/it] {'loss': 0.461, 'learning_rate': 2.9138054751222447e-07, 'epoch': 0.93} + 93%|█████████▎| 11059/11952 [3:10:59<1:27:19, 5.87s/it] 93%|█████████▎| 11060/11952 [3:11:05<1:26:23, 5.81s/it] {'loss': 0.4699, 'learning_rate': 2.907315038030911e-07, 'epoch': 0.93} + 93%|█████████▎| 11060/11952 [3:11:05<1:26:23, 5.81s/it] 93%|█████████▎| 11061/11952 [3:11:11<1:26:55, 5.85s/it] {'loss': 0.4574, 'learning_rate': 2.900831731022524e-07, 'epoch': 0.93} + 93%|█████████▎| 11061/11952 [3:11:11<1:26:55, 5.85s/it] 93%|█████████▎| 11062/11952 [3:11:18<1:29:56, 6.06s/it] {'loss': 0.4534, 'learning_rate': 2.894355554573203e-07, 'epoch': 0.93} + 93%|█████████▎| 11062/11952 [3:11:18<1:29:56, 6.06s/it] 93%|█████████▎| 11063/11952 [3:11:23<1:28:41, 5.99s/it] {'loss': 0.4645, 'learning_rate': 2.8878865091584993e-07, 'epoch': 0.93} + 93%|█████████▎| 11063/11952 [3:11:23<1:28:41, 5.99s/it] 93%|█████████▎| 11064/11952 [3:11:29<1:28:38, 5.99s/it] {'loss': 0.4718, 'learning_rate': 2.881424595253501e-07, 'epoch': 0.93} + 93%|█████████▎| 11064/11952 [3:11:29<1:28:38, 5.99s/it] 93%|█████████▎| 11065/11952 [3:11:35<1:28:35, 5.99s/it] {'loss': 0.4806, 'learning_rate': 2.8749698133327396e-07, 'epoch': 0.93} + 93%|█████████▎| 11065/11952 [3:11:35<1:28:35, 5.99s/it] 93%|█████████▎| 11066/11952 [3:11:41<1:28:21, 5.98s/it] {'loss': 0.4608, 'learning_rate': 2.868522163870213e-07, 'epoch': 0.93} + 93%|█████████▎| 11066/11952 [3:11:41<1:28:21, 5.98s/it] 93%|█████████▎| 11067/11952 [3:11:47<1:27:24, 5.93s/it] {'loss': 0.4613, 'learning_rate': 2.8620816473394206e-07, 'epoch': 0.93} + 93%|█████████▎| 11067/11952 [3:11:47<1:27:24, 5.93s/it] 93%|█████████▎| 11068/11952 [3:11:53<1:28:20, 6.00s/it] {'loss': 0.4636, 'learning_rate': 2.855648264213329e-07, 'epoch': 0.93} + 93%|█████████▎| 11068/11952 [3:11:53<1:28:20, 6.00s/it] 93%|█████████▎| 11069/11952 [3:11:59<1:26:22, 5.87s/it] {'loss': 0.4611, 'learning_rate': 2.84922201496437e-07, 'epoch': 0.93} + 93%|█████████▎| 11069/11952 [3:11:59<1:26:22, 5.87s/it] 93%|█████████▎| 11070/11952 [3:12:05<1:26:12, 5.86s/it] {'loss': 0.4624, 'learning_rate': 2.8428029000644676e-07, 'epoch': 0.93} + 93%|█████████▎| 11070/11952 [3:12:05<1:26:12, 5.86s/it] 93%|█████████▎| 11071/11952 [3:12:11<1:26:20, 5.88s/it] {'loss': 0.4557, 'learning_rate': 2.83639091998501e-07, 'epoch': 0.93} + 93%|█████████▎| 11071/11952 [3:12:11<1:26:20, 5.88s/it] 93%|█████████▎| 11072/11952 [3:12:16<1:25:36, 5.84s/it] {'loss': 0.4618, 'learning_rate': 2.8299860751968664e-07, 'epoch': 0.93} + 93%|█████████▎| 11072/11952 [3:12:16<1:25:36, 5.84s/it] 93%|█████████▎| 11073/11952 [3:12:23<1:27:03, 5.94s/it] {'loss': 0.4716, 'learning_rate': 2.823588366170393e-07, 'epoch': 0.93} + 93%|█████████▎| 11073/11952 [3:12:23<1:27:03, 5.94s/it] 93%|█████████▎| 11074/11952 [3:12:29<1:27:22, 5.97s/it] {'loss': 0.4572, 'learning_rate': 2.8171977933754036e-07, 'epoch': 0.93} + 93%|█████████▎| 11074/11952 [3:12:29<1:27:22, 5.97s/it] 93%|█████████▎| 11075/11952 [3:12:35<1:27:21, 5.98s/it] {'loss': 0.4798, 'learning_rate': 2.810814357281189e-07, 'epoch': 0.93} + 93%|█████████▎| 11075/11952 [3:12:35<1:27:21, 5.98s/it] 93%|█████████▎| 11076/11952 [3:12:41<1:27:52, 6.02s/it] {'loss': 0.4614, 'learning_rate': 2.804438058356529e-07, 'epoch': 0.93} + 93%|█████████▎| 11076/11952 [3:12:41<1:27:52, 6.02s/it] 93%|█████████▎| 11077/11952 [3:12:46<1:26:18, 5.92s/it] {'loss': 0.4506, 'learning_rate': 2.798068897069672e-07, 'epoch': 0.93} + 93%|█████████▎| 11077/11952 [3:12:46<1:26:18, 5.92s/it] 93%|█████████▎| 11078/11952 [3:12:52<1:25:46, 5.89s/it] {'loss': 0.4792, 'learning_rate': 2.791706873888345e-07, 'epoch': 0.93} + 93%|█████████▎| 11078/11952 [3:12:52<1:25:46, 5.89s/it] 93%|█████████▎| 11079/11952 [3:12:58<1:25:26, 5.87s/it] {'loss': 0.463, 'learning_rate': 2.78535198927975e-07, 'epoch': 0.93} + 93%|█████████▎| 11079/11952 [3:12:58<1:25:26, 5.87s/it] 93%|█████████▎| 11080/11952 [3:13:04<1:25:05, 5.86s/it] {'loss': 0.4493, 'learning_rate': 2.779004243710548e-07, 'epoch': 0.93} + 93%|█████████▎| 11080/11952 [3:13:04<1:25:05, 5.86s/it] 93%|█████████▎| 11081/11952 [3:13:10<1:24:38, 5.83s/it] {'loss': 0.4583, 'learning_rate': 2.7726636376468995e-07, 'epoch': 0.93} + 93%|█████████▎| 11081/11952 [3:13:10<1:24:38, 5.83s/it] 93%|█████████▎| 11082/11952 [3:13:15<1:24:09, 5.80s/it] {'loss': 0.4744, 'learning_rate': 2.766330171554443e-07, 'epoch': 0.93} + 93%|█████████▎| 11082/11952 [3:13:15<1:24:09, 5.80s/it] 93%|█████████▎| 11083/11952 [3:13:21<1:23:52, 5.79s/it] {'loss': 0.4577, 'learning_rate': 2.7600038458982626e-07, 'epoch': 0.93} + 93%|█████████▎| 11083/11952 [3:13:21<1:23:52, 5.79s/it] 93%|█████████▎| 11084/11952 [3:13:27<1:23:54, 5.80s/it] {'loss': 0.4498, 'learning_rate': 2.7536846611429524e-07, 'epoch': 0.93} + 93%|█████████▎| 11084/11952 [3:13:27<1:23:54, 5.80s/it] 93%|█████████▎| 11085/11952 [3:13:33<1:25:29, 5.92s/it] {'loss': 0.466, 'learning_rate': 2.747372617752575e-07, 'epoch': 0.93} + 93%|█████████▎| 11085/11952 [3:13:33<1:25:29, 5.92s/it] 93%|█████████▎| 11086/11952 [3:13:39<1:24:49, 5.88s/it] {'loss': 0.4466, 'learning_rate': 2.741067716190637e-07, 'epoch': 0.93} + 93%|█████████▎| 11086/11952 [3:13:39<1:24:49, 5.88s/it] 93%|█████████▎| 11087/11952 [3:13:45<1:25:40, 5.94s/it] {'loss': 0.4521, 'learning_rate': 2.734769956920169e-07, 'epoch': 0.93} + 93%|█████████▎| 11087/11952 [3:13:45<1:25:40, 5.94s/it] 93%|█████████▎| 11088/11952 [3:13:51<1:24:21, 5.86s/it] {'loss': 0.4548, 'learning_rate': 2.728479340403634e-07, 'epoch': 0.93} + 93%|█████████▎| 11088/11952 [3:13:51<1:24:21, 5.86s/it] 93%|█████████▎| 11089/11952 [3:13:57<1:23:50, 5.83s/it] {'loss': 0.464, 'learning_rate': 2.7221958671029834e-07, 'epoch': 0.93} + 93%|█████████▎| 11089/11952 [3:13:57<1:23:50, 5.83s/it] 93%|█████████▎| 11090/11952 [3:14:02<1:24:00, 5.85s/it] {'loss': 0.463, 'learning_rate': 2.715919537479661e-07, 'epoch': 0.93} + 93%|█████████▎| 11090/11952 [3:14:02<1:24:00, 5.85s/it] 93%|█████████▎| 11091/11952 [3:14:08<1:24:09, 5.86s/it] {'loss': 0.4979, 'learning_rate': 2.709650351994575e-07, 'epoch': 0.93} + 93%|█████████▎| 11091/11952 [3:14:08<1:24:09, 5.86s/it] 93%|█████████▎| 11092/11952 [3:14:14<1:24:51, 5.92s/it] {'loss': 0.46, 'learning_rate': 2.7033883111081014e-07, 'epoch': 0.93} + 93%|█████████▎| 11092/11952 [3:14:14<1:24:51, 5.92s/it] 93%|█████████▎| 11093/11952 [3:14:20<1:24:11, 5.88s/it] {'loss': 0.4618, 'learning_rate': 2.6971334152801063e-07, 'epoch': 0.93} + 93%|█████████▎| 11093/11952 [3:14:20<1:24:11, 5.88s/it] 93%|█████████▎| 11094/11952 [3:14:26<1:22:54, 5.80s/it] {'loss': 0.4493, 'learning_rate': 2.690885664969933e-07, 'epoch': 0.93} + 93%|█████████▎| 11094/11952 [3:14:26<1:22:54, 5.80s/it] 93%|█████████▎| 11095/11952 [3:14:32<1:23:15, 5.83s/it] {'loss': 0.4691, 'learning_rate': 2.6846450606363705e-07, 'epoch': 0.93} + 93%|█████████▎| 11095/11952 [3:14:32<1:23:15, 5.83s/it] 93%|█████████▎| 11096/11952 [3:14:37<1:22:27, 5.78s/it] {'loss': 0.4505, 'learning_rate': 2.678411602737707e-07, 'epoch': 0.93} + 93%|█████████▎| 11096/11952 [3:14:37<1:22:27, 5.78s/it] 93%|█████████▎| 11097/11952 [3:14:43<1:22:36, 5.80s/it] {'loss': 0.4586, 'learning_rate': 2.6721852917316995e-07, 'epoch': 0.93} + 93%|█████████▎| 11097/11952 [3:14:43<1:22:36, 5.80s/it] 93%|█████████▎| 11098/11952 [3:14:50<1:25:29, 6.01s/it] {'loss': 0.4665, 'learning_rate': 2.665966128075592e-07, 'epoch': 0.93} + 93%|█████████▎| 11098/11952 [3:14:50<1:25:29, 6.01s/it] 93%|█████████▎| 11099/11952 [3:14:56<1:26:34, 6.09s/it] {'loss': 0.4521, 'learning_rate': 2.659754112226087e-07, 'epoch': 0.93} + 93%|█████████▎| 11099/11952 [3:14:56<1:26:34, 6.09s/it]5 AutoResumeHook: Checking whether to suspend... +02 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... + 93%|█████████▎| 11100/11952 [3:15:02<1:25:34, 6.03s/it]1 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4666, 'learning_rate': 2.653549244639375e-07, 'epoch': 0.93} + 93%|█████████▎| 11100/11952 [3:15:02<1:25:34, 6.03s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-11100/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-11100/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/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( + 93%|█████████▎| 11101/11952 [3:15:32<3:07:19, 13.21s/it] {'loss': 0.456, 'learning_rate': 2.6473515257711136e-07, 'epoch': 0.93} + 93%|█████████▎| 11101/11952 [3:15:32<3:07:19, 13.21s/it] 93%|█████████▎| 11102/11952 [3:15:38<2:36:08, 11.02s/it] {'loss': 0.4674, 'learning_rate': 2.6411609560764273e-07, 'epoch': 0.93} + 93%|█████████▎| 11102/11952 [3:15:38<2:36:08, 11.02s/it] 93%|█████████▎| 11103/11952 [3:15:43<2:13:27, 9.43s/it] {'loss': 0.4626, 'learning_rate': 2.6349775360099306e-07, 'epoch': 0.93} + 93%|█████████▎| 11103/11952 [3:15:43<2:13:27, 9.43s/it] 93%|█████████▎| 11104/11952 [3:15:49<1:58:30, 8.39s/it] {'loss': 0.4403, 'learning_rate': 2.628801266025727e-07, 'epoch': 0.93} + 93%|█████████▎| 11104/11952 [3:15:49<1:58:30, 8.39s/it] 93%|█████████▎| 11105/11952 [3:15:55<1:47:22, 7.61s/it] {'loss': 0.4732, 'learning_rate': 2.622632146577364e-07, 'epoch': 0.93} + 93%|█████████▎| 11105/11952 [3:15:55<1:47:22, 7.61s/it] 93%|█████████▎| 11106/11952 [3:16:01<1:39:42, 7.07s/it] {'loss': 0.4657, 'learning_rate': 2.616470178117858e-07, 'epoch': 0.93} + 93%|█████████▎| 11106/11952 [3:16:01<1:39:42, 7.07s/it] 93%|█████████▎| 11107/11952 [3:16:07<1:33:32, 6.64s/it] {'loss': 0.4599, 'learning_rate': 2.6103153610997464e-07, 'epoch': 0.93} + 93%|█████████▎| 11107/11952 [3:16:07<1:33:32, 6.64s/it] 93%|█████████▎| 11108/11952 [3:16:12<1:29:06, 6.33s/it] {'loss': 0.4552, 'learning_rate': 2.604167695975002e-07, 'epoch': 0.93} + 93%|█████████▎| 11108/11952 [3:16:12<1:29:06, 6.33s/it] 93%|█████████▎| 11109/11952 [3:16:18<1:26:51, 6.18s/it] {'loss': 0.4677, 'learning_rate': 2.5980271831950734e-07, 'epoch': 0.93} + 93%|█████████▎| 11109/11952 [3:16:18<1:26:51, 6.18s/it] 93%|█████████▎| 11110/11952 [3:16:24<1:25:04, 6.06s/it] {'loss': 0.4628, 'learning_rate': 2.5918938232109004e-07, 'epoch': 0.93} + 93%|█████████▎| 11110/11952 [3:16:24<1:25:04, 6.06s/it] 93%|█████████▎| 11111/11952 [3:16:30<1:24:01, 5.99s/it] {'loss': 0.4507, 'learning_rate': 2.5857676164729006e-07, 'epoch': 0.93} + 93%|█████████▎| 11111/11952 [3:16:30<1:24:01, 5.99s/it] 93%|█████████▎| 11112/11952 [3:16:36<1:23:33, 5.97s/it] {'loss': 0.4524, 'learning_rate': 2.5796485634309477e-07, 'epoch': 0.93} + 93%|█████████▎| 11112/11952 [3:16:36<1:23:33, 5.97s/it] 93%|█████████▎| 11113/11952 [3:16:41<1:22:42, 5.91s/it] {'loss': 0.4644, 'learning_rate': 2.573536664534404e-07, 'epoch': 0.93} + 93%|█████████▎| 11113/11952 [3:16:41<1:22:42, 5.91s/it] 93%|█████████▎| 11114/11952 [3:16:47<1:21:10, 5.81s/it] {'loss': 0.4485, 'learning_rate': 2.5674319202320997e-07, 'epoch': 0.93} + 93%|█████████▎| 11114/11952 [3:16:47<1:21:10, 5.81s/it] 93%|█████████▎| 11115/11952 [3:16:53<1:22:50, 5.94s/it] {'loss': 0.4583, 'learning_rate': 2.5613343309723426e-07, 'epoch': 0.93} + 93%|█████████▎| 11115/11952 [3:16:53<1:22:50, 5.94s/it] 93%|█████████▎| 11116/11952 [3:16:59<1:22:54, 5.95s/it] {'loss': 0.4837, 'learning_rate': 2.555243897202919e-07, 'epoch': 0.93} + 93%|█████████▎| 11116/11952 [3:16:59<1:22:54, 5.95s/it] 93%|█████████▎| 11117/11952 [3:17:05<1:22:29, 5.93s/it] {'loss': 0.4759, 'learning_rate': 2.549160619371072e-07, 'epoch': 0.93} + 93%|█████████▎| 11117/11952 [3:17:05<1:22:29, 5.93s/it] 93%|█████████▎| 11118/11952 [3:17:11<1:22:29, 5.94s/it] {'loss': 0.4621, 'learning_rate': 2.5430844979235426e-07, 'epoch': 0.93} + 93%|█████████▎| 11118/11952 [3:17:11<1:22:29, 5.94s/it] 93%|█████████▎| 11119/11952 [3:17:17<1:21:57, 5.90s/it] {'loss': 0.4752, 'learning_rate': 2.5370155333065416e-07, 'epoch': 0.93} + 93%|█████████▎| 11119/11952 [3:17:17<1:21:57, 5.90s/it] 93%|█████████▎| 11120/11952 [3:17:23<1:21:37, 5.89s/it] {'loss': 0.4624, 'learning_rate': 2.5309537259657346e-07, 'epoch': 0.93} + 93%|█████████▎| 11120/11952 [3:17:23<1:21:37, 5.89s/it] 93%|█████████▎| 11121/11952 [3:17:28<1:21:10, 5.86s/it] {'loss': 0.4575, 'learning_rate': 2.524899076346288e-07, 'epoch': 0.93} + 93%|█████████▎| 11121/11952 [3:17:28<1:21:10, 5.86s/it] 93%|█████████▎| 11122/11952 [3:17:34<1:21:34, 5.90s/it] {'loss': 0.4817, 'learning_rate': 2.518851584892812e-07, 'epoch': 0.93} + 93%|█████████▎| 11122/11952 [3:17:34<1:21:34, 5.90s/it] 93%|█████████▎| 11123/11952 [3:17:40<1:21:00, 5.86s/it] {'loss': 0.4768, 'learning_rate': 2.5128112520494297e-07, 'epoch': 0.93} + 93%|█████████▎| 11123/11952 [3:17:40<1:21:00, 5.86s/it] 93%|█████████▎| 11124/11952 [3:17:46<1:20:07, 5.81s/it] {'loss': 0.4499, 'learning_rate': 2.5067780782596973e-07, 'epoch': 0.93} + 93%|█████████▎| 11124/11952 [3:17:46<1:20:07, 5.81s/it] 93%|█████████▎| 11125/11952 [3:17:52<1:20:04, 5.81s/it] {'loss': 0.4508, 'learning_rate': 2.500752063966694e-07, 'epoch': 0.93} + 93%|█████████▎| 11125/11952 [3:17:52<1:20:04, 5.81s/it] 93%|█████████▎| 11126/11952 [3:17:58<1:20:26, 5.84s/it] {'loss': 0.4726, 'learning_rate': 2.494733209612921e-07, 'epoch': 0.93} + 93%|█████████▎| 11126/11952 [3:17:58<1:20:26, 5.84s/it] 93%|█████████▎| 11127/11952 [3:18:04<1:20:42, 5.87s/it] {'loss': 0.4577, 'learning_rate': 2.488721515640391e-07, 'epoch': 0.93} + 93%|█████████▎| 11127/11952 [3:18:04<1:20:42, 5.87s/it] 93%|█████████▎| 11128/11952 [3:18:10<1:22:11, 5.99s/it] {'loss': 0.449, 'learning_rate': 2.482716982490574e-07, 'epoch': 0.93} + 93%|█████████▎| 11128/11952 [3:18:10<1:22:11, 5.99s/it] 93%|█████████▎| 11129/11952 [3:18:16<1:22:17, 6.00s/it] {'loss': 0.4783, 'learning_rate': 2.476719610604417e-07, 'epoch': 0.93} + 93%|█████████▎| 11129/11952 [3:18:16<1:22:17, 6.00s/it] 93%|█████████▎| 11130/11952 [3:18:22<1:20:44, 5.89s/it] {'loss': 0.483, 'learning_rate': 2.4707294004223335e-07, 'epoch': 0.93} + 93%|█████████▎| 11130/11952 [3:18:22<1:20:44, 5.89s/it] 93%|█████████▎| 11131/11952 [3:18:28<1:21:26, 5.95s/it] {'loss': 0.4561, 'learning_rate': 2.464746352384229e-07, 'epoch': 0.93} + 93%|█████████▎| 11131/11952 [3:18:28<1:21:26, 5.95s/it] 93%|█████████▎| 11132/11952 [3:18:33<1:20:29, 5.89s/it] {'loss': 0.4791, 'learning_rate': 2.4587704669294834e-07, 'epoch': 0.93} + 93%|█████████▎| 11132/11952 [3:18:33<1:20:29, 5.89s/it] 93%|█████████▎| 11133/11952 [3:18:39<1:20:00, 5.86s/it] {'loss': 0.4602, 'learning_rate': 2.452801744496913e-07, 'epoch': 0.93} + 93%|█████████▎| 11133/11952 [3:18:39<1:20:00, 5.86s/it] 93%|█████████▎| 11134/11952 [3:18:45<1:21:22, 5.97s/it] {'loss': 0.4529, 'learning_rate': 2.446840185524868e-07, 'epoch': 0.93} + 93%|█████████▎| 11134/11952 [3:18:45<1:21:22, 5.97s/it] 93%|█████████▎| 11135/11952 [3:18:51<1:19:52, 5.87s/it] {'loss': 0.4832, 'learning_rate': 2.4408857904511196e-07, 'epoch': 0.93} + 93%|█████████▎| 11135/11952 [3:18:51<1:19:52, 5.87s/it] 93%|█████████▎| 11136/11952 [3:18:57<1:19:12, 5.82s/it] {'loss': 0.4787, 'learning_rate': 2.4349385597129403e-07, 'epoch': 0.93} + 93%|█████████▎| 11136/11952 [3:18:57<1:19:12, 5.82s/it] 93%|█████████▎| 11137/11952 [3:19:03<1:19:06, 5.82s/it] {'loss': 0.4726, 'learning_rate': 2.428998493747081e-07, 'epoch': 0.93} + 93%|█████████▎| 11137/11952 [3:19:03<1:19:06, 5.82s/it] 93%|█████████▎| 11138/11952 [3:19:09<1:20:11, 5.91s/it] {'loss': 0.4646, 'learning_rate': 2.4230655929897263e-07, 'epoch': 0.93} + 93%|█████████▎| 11138/11952 [3:19:09<1:20:11, 5.91s/it] 93%|█████████▎| 11139/11952 [3:19:15<1:20:09, 5.92s/it] {'loss': 0.4458, 'learning_rate': 2.417139857876583e-07, 'epoch': 0.93} + 93%|█████████▎| 11139/11952 [3:19:15<1:20:09, 5.92s/it] 93%|█████████▎| 11140/11952 [3:19:20<1:19:49, 5.90s/it] {'loss': 0.4363, 'learning_rate': 2.4112212888428246e-07, 'epoch': 0.93} + 93%|█████████▎| 11140/11952 [3:19:20<1:19:49, 5.90s/it] 93%|█████████▎| 11141/11952 [3:19:27<1:21:10, 6.01s/it] {'loss': 0.4711, 'learning_rate': 2.4053098863230706e-07, 'epoch': 0.93} + 93%|█████████▎| 11141/11952 [3:19:27<1:21:10, 6.01s/it] 93%|█████████▎| 11142/11952 [3:19:33<1:20:45, 5.98s/it] {'loss': 0.4633, 'learning_rate': 2.3994056507514183e-07, 'epoch': 0.93} + 93%|█████████▎| 11142/11952 [3:19:33<1:20:45, 5.98s/it] 93%|█████████▎| 11143/11952 [3:19:39<1:21:27, 6.04s/it] {'loss': 0.4565, 'learning_rate': 2.3935085825614655e-07, 'epoch': 0.93} + 93%|█████████▎| 11143/11952 [3:19:39<1:21:27, 6.04s/it] 93%|█████████▎| 11144/11952 [3:19:45<1:21:25, 6.05s/it] {'loss': 0.4608, 'learning_rate': 2.387618682186277e-07, 'epoch': 0.93} + 93%|█████████▎| 11144/11952 [3:19:45<1:21:25, 6.05s/it] 93%|█████████▎| 11145/11952 [3:19:51<1:20:41, 6.00s/it] {'loss': 0.4632, 'learning_rate': 2.3817359500583615e-07, 'epoch': 0.93} + 93%|█████████▎| 11145/11952 [3:19:51<1:20:41, 6.00s/it] 93%|█████████▎| 11146/11952 [3:19:57<1:20:33, 6.00s/it] {'loss': 0.4617, 'learning_rate': 2.3758603866097406e-07, 'epoch': 0.93} + 93%|█████████▎| 11146/11952 [3:19:57<1:20:33, 6.00s/it] 93%|█████████▎| 11147/11952 [3:20:03<1:20:01, 5.96s/it] {'loss': 0.4715, 'learning_rate': 2.3699919922718805e-07, 'epoch': 0.93} + 93%|█████████▎| 11147/11952 [3:20:03<1:20:01, 5.96s/it] 93%|█████████▎| 11148/11952 [3:20:09<1:19:36, 5.94s/it] {'loss': 0.4526, 'learning_rate': 2.3641307674757362e-07, 'epoch': 0.93} + 93%|█████████▎| 11148/11952 [3:20:09<1:19:36, 5.94s/it] 93%|█████████▎| 11149/11952 [3:20:14<1:19:21, 5.93s/it] {'loss': 0.4631, 'learning_rate': 2.3582767126517302e-07, 'epoch': 0.93} + 93%|█████████▎| 11149/11952 [3:20:14<1:19:21, 5.93s/it]5 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +0 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... + 93%|█████████▎| 11150/11952 [3:20:20<1:19:01, 5.91s/it]2 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4627, 'learning_rate': 2.352429828229763e-07, 'epoch': 0.93} + 93%|█████████▎| 11150/11952 [3:20:20<1:19:01, 5.91s/it] 93%|█████████▎| 11151/11952 [3:20:26<1:17:54, 5.84s/it] {'loss': 0.4579, 'learning_rate': 2.3465901146391912e-07, 'epoch': 0.93} + 93%|█████████▎| 11151/11952 [3:20:26<1:17:54, 5.84s/it] 93%|█████████▎| 11152/11952 [3:20:32<1:17:16, 5.80s/it] {'loss': 0.4531, 'learning_rate': 2.3407575723088827e-07, 'epoch': 0.93} + 93%|█████████▎| 11152/11952 [3:20:32<1:17:16, 5.80s/it] 93%|█████████▎| 11153/11952 [3:20:37<1:17:01, 5.78s/it] {'loss': 0.4655, 'learning_rate': 2.3349322016671394e-07, 'epoch': 0.93} + 93%|█████████▎| 11153/11952 [3:20:37<1:17:01, 5.78s/it] 93%|█████████▎| 11154/11952 [3:20:43<1:16:16, 5.74s/it] {'loss': 0.4745, 'learning_rate': 2.3291140031417525e-07, 'epoch': 0.93} + 93%|█████████▎| 11154/11952 [3:20:43<1:16:16, 5.74s/it] 93%|█████████▎| 11155/11952 [3:20:49<1:16:08, 5.73s/it] {'loss': 0.4893, 'learning_rate': 2.3233029771599913e-07, 'epoch': 0.93} + 93%|█████████▎| 11155/11952 [3:20:49<1:16:08, 5.73s/it] 93%|█████████▎| 11156/11952 [3:20:55<1:16:03, 5.73s/it] {'loss': 0.4505, 'learning_rate': 2.3174991241485923e-07, 'epoch': 0.93} + 93%|█████████▎| 11156/11952 [3:20:55<1:16:03, 5.73s/it] 93%|█████████▎| 11157/11952 [3:21:01<1:17:46, 5.87s/it] {'loss': 0.4682, 'learning_rate': 2.31170244453377e-07, 'epoch': 0.93} + 93%|█████████▎| 11157/11952 [3:21:01<1:17:46, 5.87s/it] 93%|█████████▎| 11158/11952 [3:21:06<1:16:56, 5.81s/it] {'loss': 0.4609, 'learning_rate': 2.305912938741184e-07, 'epoch': 0.93} + 93%|█████████▎| 11158/11952 [3:21:06<1:16:56, 5.81s/it] 93%|█████████▎| 11159/11952 [3:21:12<1:16:11, 5.77s/it] {'loss': 0.4606, 'learning_rate': 2.3001306071960384e-07, 'epoch': 0.93} + 93%|█████████▎| 11159/11952 [3:21:12<1:16:11, 5.77s/it] 93%|█████████▎| 11160/11952 [3:21:18<1:16:54, 5.83s/it] {'loss': 0.4565, 'learning_rate': 2.294355450322916e-07, 'epoch': 0.93} + 93%|█████████▎| 11160/11952 [3:21:18<1:16:54, 5.83s/it] 93%|█████████▎| 11161/11952 [3:21:24<1:16:04, 5.77s/it] {'loss': 0.4542, 'learning_rate': 2.2885874685459553e-07, 'epoch': 0.93} + 93%|█████████▎| 11161/11952 [3:21:24<1:16:04, 5.77s/it] 93%|█████████▎| 11162/11952 [3:21:30<1:17:19, 5.87s/it] {'loss': 0.4691, 'learning_rate': 2.2828266622887173e-07, 'epoch': 0.93} + 93%|█████████▎| 11162/11952 [3:21:30<1:17:19, 5.87s/it] 93%|█████████▎| 11163/11952 [3:21:36<1:17:33, 5.90s/it] {'loss': 0.4622, 'learning_rate': 2.2770730319742528e-07, 'epoch': 0.93} + 93%|█████████▎| 11163/11952 [3:21:36<1:17:33, 5.90s/it] 93%|█████████▎| 11164/11952 [3:21:42<1:17:30, 5.90s/it] {'loss': 0.4703, 'learning_rate': 2.271326578025068e-07, 'epoch': 0.93} + 93%|█████████▎| 11164/11952 [3:21:42<1:17:30, 5.90s/it] 93%|█████████▎| 11165/11952 [3:21:48<1:17:30, 5.91s/it] {'loss': 0.4572, 'learning_rate': 2.2655873008631812e-07, 'epoch': 0.93} + 93%|█████████▎| 11165/11952 [3:21:48<1:17:30, 5.91s/it] 93%|█████████▎| 11166/11952 [3:21:54<1:18:01, 5.96s/it] {'loss': 0.4871, 'learning_rate': 2.259855200910066e-07, 'epoch': 0.93} + 93%|█████████▎| 11166/11952 [3:21:54<1:18:01, 5.96s/it] 93%|█████████▎| 11167/11952 [3:21:59<1:17:10, 5.90s/it] {'loss': 0.4661, 'learning_rate': 2.2541302785866525e-07, 'epoch': 0.93} + 93%|█████████▎| 11167/11952 [3:21:59<1:17:10, 5.90s/it] 93%|█████████▎| 11168/11952 [3:22:05<1:17:56, 5.96s/it] {'loss': 0.4621, 'learning_rate': 2.248412534313349e-07, 'epoch': 0.93} + 93%|█████████▎| 11168/11952 [3:22:05<1:17:56, 5.96s/it] 93%|█████████▎| 11169/11952 [3:22:11<1:17:29, 5.94s/it] {'loss': 0.4768, 'learning_rate': 2.2427019685100527e-07, 'epoch': 0.93} + 93%|█████████▎| 11169/11952 [3:22:11<1:17:29, 5.94s/it] 93%|█████████▎| 11170/11952 [3:22:17<1:17:15, 5.93s/it] {'loss': 0.4552, 'learning_rate': 2.236998581596128e-07, 'epoch': 0.93} + 93%|█████████▎| 11170/11952 [3:22:17<1:17:15, 5.93s/it] 93%|█████████▎| 11171/11952 [3:22:23<1:16:17, 5.86s/it] {'loss': 0.4535, 'learning_rate': 2.231302373990385e-07, 'epoch': 0.93} + 93%|█████████▎| 11171/11952 [3:22:23<1:16:17, 5.86s/it] 93%|█████████▎| 11172/11952 [3:22:29<1:16:02, 5.85s/it] {'loss': 0.4639, 'learning_rate': 2.225613346111155e-07, 'epoch': 0.93} + 93%|█████████▎| 11172/11952 [3:22:29<1:16:02, 5.85s/it] 93%|█████████▎| 11173/11952 [3:22:35<1:15:48, 5.84s/it] {'loss': 0.4708, 'learning_rate': 2.2199314983762043e-07, 'epoch': 0.93} + 93%|█████████▎| 11173/11952 [3:22:35<1:15:48, 5.84s/it] 93%|█████████▎| 11174/11952 [3:22:41<1:17:15, 5.96s/it] {'loss': 0.4768, 'learning_rate': 2.2142568312027879e-07, 'epoch': 0.93} + 93%|█████████▎| 11174/11952 [3:22:41<1:17:15, 5.96s/it] 93%|█████████▎| 11175/11952 [3:22:47<1:17:09, 5.96s/it] {'loss': 0.4697, 'learning_rate': 2.2085893450076167e-07, 'epoch': 0.93} + 93%|█████████▎| 11175/11952 [3:22:47<1:17:09, 5.96s/it] 94%|█████████▎| 11176/11952 [3:22:53<1:16:49, 5.94s/it] {'loss': 0.4648, 'learning_rate': 2.2029290402069137e-07, 'epoch': 0.94} + 94%|█████████▎| 11176/11952 [3:22:53<1:16:49, 5.94s/it] 94%|█████████▎| 11177/11952 [3:22:59<1:18:11, 6.05s/it] {'loss': 0.4732, 'learning_rate': 2.1972759172163239e-07, 'epoch': 0.94} + 94%|█████████▎| 11177/11952 [3:22:59<1:18:11, 6.05s/it] 94%|█████████▎| 11178/11952 [3:23:05<1:16:18, 5.92s/it] {'loss': 0.4662, 'learning_rate': 2.191629976451004e-07, 'epoch': 0.94} + 94%|█████████▎| 11178/11952 [3:23:05<1:16:18, 5.92s/it] 94%|█████████▎| 11179/11952 [3:23:10<1:16:00, 5.90s/it] {'loss': 0.458, 'learning_rate': 2.185991218325556e-07, 'epoch': 0.94} + 94%|█████████▎| 11179/11952 [3:23:10<1:16:00, 5.90s/it] 94%|█████████▎| 11180/11952 [3:23:16<1:16:05, 5.91s/it] {'loss': 0.4644, 'learning_rate': 2.1803596432540818e-07, 'epoch': 0.94} + 94%|█████████▎| 11180/11952 [3:23:16<1:16:05, 5.91s/it] 94%|█████████▎| 11181/11952 [3:23:22<1:15:14, 5.86s/it] {'loss': 0.4514, 'learning_rate': 2.1747352516501396e-07, 'epoch': 0.94} + 94%|█████████▎| 11181/11952 [3:23:22<1:15:14, 5.86s/it] 94%|█████████▎| 11182/11952 [3:23:28<1:14:10, 5.78s/it] {'loss': 0.477, 'learning_rate': 2.1691180439267434e-07, 'epoch': 0.94} + 94%|█████████▎| 11182/11952 [3:23:28<1:14:10, 5.78s/it] 94%|█████████▎| 11183/11952 [3:23:34<1:15:31, 5.89s/it] {'loss': 0.4799, 'learning_rate': 2.1635080204964187e-07, 'epoch': 0.94} + 94%|█████████▎| 11183/11952 [3:23:34<1:15:31, 5.89s/it] 94%|█████████▎| 11184/11952 [3:23:40<1:15:23, 5.89s/it] {'loss': 0.4699, 'learning_rate': 2.157905181771114e-07, 'epoch': 0.94} + 94%|█████████▎| 11184/11952 [3:23:40<1:15:23, 5.89s/it] 94%|█████████▎| 11185/11952 [3:23:45<1:14:18, 5.81s/it] {'loss': 0.4609, 'learning_rate': 2.1523095281623109e-07, 'epoch': 0.94} + 94%|█████████▎| 11185/11952 [3:23:45<1:14:18, 5.81s/it] 94%|█████████▎| 11186/11952 [3:23:52<1:15:20, 5.90s/it] {'loss': 0.446, 'learning_rate': 2.146721060080914e-07, 'epoch': 0.94} + 94%|█████████▎| 11186/11952 [3:23:52<1:15:20, 5.90s/it] 94%|█████████▎| 11187/11952 [3:23:58<1:16:12, 5.98s/it] {'loss': 0.4774, 'learning_rate': 2.141139777937318e-07, 'epoch': 0.94} + 94%|█████████▎| 11187/11952 [3:23:58<1:16:12, 5.98s/it] 94%|█████████▎| 11188/11952 [3:24:04<1:16:07, 5.98s/it] {'loss': 0.4701, 'learning_rate': 2.1355656821413938e-07, 'epoch': 0.94} + 94%|█████████▎| 11188/11952 [3:24:04<1:16:07, 5.98s/it] 94%|█████████▎| 11189/11952 [3:24:10<1:15:35, 5.94s/it] {'loss': 0.457, 'learning_rate': 2.1299987731024818e-07, 'epoch': 0.94} + 94%|█████████▎| 11189/11952 [3:24:10<1:15:35, 5.94s/it] 94%|█████████▎| 11190/11952 [3:24:15<1:15:21, 5.93s/it] {'loss': 0.4449, 'learning_rate': 2.1244390512293878e-07, 'epoch': 0.94} + 94%|█████████▎| 11190/11952 [3:24:15<1:15:21, 5.93s/it] 94%|█████████▎| 11191/11952 [3:24:21<1:15:06, 5.92s/it] {'loss': 0.4626, 'learning_rate': 2.1188865169303852e-07, 'epoch': 0.94} + 94%|█████████▎| 11191/11952 [3:24:21<1:15:06, 5.92s/it] 94%|█████████▎| 11192/11952 [3:24:27<1:14:00, 5.84s/it] {'loss': 0.4547, 'learning_rate': 2.1133411706132368e-07, 'epoch': 0.94} + 94%|█████████▎| 11192/11952 [3:24:27<1:14:00, 5.84s/it] 94%|█████████▎| 11193/11952 [3:24:33<1:13:29, 5.81s/it] {'loss': 0.4508, 'learning_rate': 2.1078030126851833e-07, 'epoch': 0.94} + 94%|█████████▎| 11193/11952 [3:24:33<1:13:29, 5.81s/it] 94%|█████████▎| 11194/11952 [3:24:39<1:13:18, 5.80s/it] {'loss': 0.4558, 'learning_rate': 2.1022720435529109e-07, 'epoch': 0.94} + 94%|█████████▎| 11194/11952 [3:24:39<1:13:18, 5.80s/it] 94%|█████████▎| 11195/11952 [3:24:45<1:14:43, 5.92s/it] {'loss': 0.4591, 'learning_rate': 2.0967482636225723e-07, 'epoch': 0.94} + 94%|█████████▎| 11195/11952 [3:24:45<1:14:43, 5.92s/it] 94%|█████████▎| 11196/11952 [3:24:51<1:14:18, 5.90s/it] {'loss': 0.4874, 'learning_rate': 2.0912316732998538e-07, 'epoch': 0.94} + 94%|█████████▎| 11196/11952 [3:24:51<1:14:18, 5.90s/it] 94%|█████████▎| 11197/11952 [3:24:56<1:13:51, 5.87s/it] {'loss': 0.4589, 'learning_rate': 2.0857222729898429e-07, 'epoch': 0.94} + 94%|█████████▎| 11197/11952 [3:24:56<1:13:51, 5.87s/it] 94%|█████████▎| 11198/11952 [3:25:02<1:13:07, 5.82s/it] {'loss': 0.4498, 'learning_rate': 2.0802200630971382e-07, 'epoch': 0.94} + 94%|█████████▎| 11198/11952 [3:25:02<1:13:07, 5.82s/it] 94%|█████████▎| 11199/11952 [3:25:08<1:12:37, 5.79s/it] {'loss': 0.4682, 'learning_rate': 2.0747250440257715e-07, 'epoch': 0.94} + 94%|█████████▎| 11199/11952 [3:25:08<1:12:37, 5.79s/it]5 AutoResumeHook: Checking whether to suspend... +04 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... + 94%|█████████▎| 11200/11952 [3:25:13<1:12:17, 5.77s/it]1 AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4665, 'learning_rate': 2.0692372161793094e-07, 'epoch': 0.94} + 94%|█████████▎| 11200/11952 [3:25:13<1:12:17, 5.77s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-11200/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-11200/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/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( + 94%|█████████▎| 11201/11952 [3:25:43<2:43:11, 13.04s/it] {'loss': 0.4639, 'learning_rate': 2.0637565799607517e-07, 'epoch': 0.94} + 94%|█████████▎| 11201/11952 [3:25:43<2:43:11, 13.04s/it] 94%|█████████▎| 11202/11952 [3:25:49<2:16:26, 10.92s/it] {'loss': 0.4561, 'learning_rate': 2.0582831357725542e-07, 'epoch': 0.94} + 94%|█████████▎| 11202/11952 [3:25:49<2:16:26, 10.92s/it] 94%|█████████▎| 11203/11952 [3:25:55<1:57:14, 9.39s/it] {'loss': 0.4466, 'learning_rate': 2.052816884016673e-07, 'epoch': 0.94} + 94%|█████████▎| 11203/11952 [3:25:55<1:57:14, 9.39s/it] 94%|█████████▎| 11204/11952 [3:26:01<1:43:33, 8.31s/it] {'loss': 0.4515, 'learning_rate': 2.0473578250945315e-07, 'epoch': 0.94} + 94%|█████████▎| 11204/11952 [3:26:01<1:43:33, 8.31s/it] 94%|█████████▍| 11205/11952 [3:26:07<1:34:47, 7.61s/it] {'loss': 0.4653, 'learning_rate': 2.0419059594069977e-07, 'epoch': 0.94} + 94%|█████████▍| 11205/11952 [3:26:07<1:34:47, 7.61s/it] 94%|█████████▍| 11206/11952 [3:26:13<1:29:40, 7.21s/it] {'loss': 0.4583, 'learning_rate': 2.0364612873544632e-07, 'epoch': 0.94} + 94%|█████████▍| 11206/11952 [3:26:13<1:29:40, 7.21s/it] 94%|█████████▍| 11207/11952 [3:26:19<1:24:34, 6.81s/it] {'loss': 0.4565, 'learning_rate': 2.0310238093367517e-07, 'epoch': 0.94} + 94%|█████████▍| 11207/11952 [3:26:19<1:24:34, 6.81s/it] 94%|█████████▍| 11208/11952 [3:26:25<1:20:41, 6.51s/it] {'loss': 0.4796, 'learning_rate': 2.0255935257531668e-07, 'epoch': 0.94} + 94%|█████████▍| 11208/11952 [3:26:25<1:20:41, 6.51s/it] 94%|█████████▍| 11209/11952 [3:26:31<1:18:07, 6.31s/it] {'loss': 0.4641, 'learning_rate': 2.0201704370024889e-07, 'epoch': 0.94} + 94%|█████████▍| 11209/11952 [3:26:31<1:18:07, 6.31s/it] 94%|█████████▍| 11210/11952 [3:26:37<1:16:24, 6.18s/it] {'loss': 0.4512, 'learning_rate': 2.0147545434829664e-07, 'epoch': 0.94} + 94%|█████████▍| 11210/11952 [3:26:37<1:16:24, 6.18s/it] 94%|█████████▍| 11211/11952 [3:26:43<1:16:16, 6.18s/it] {'loss': 0.4543, 'learning_rate': 2.0093458455923253e-07, 'epoch': 0.94} + 94%|█████████▍| 11211/11952 [3:26:43<1:16:16, 6.18s/it] 94%|█████████▍| 11212/11952 [3:26:49<1:14:42, 6.06s/it] {'loss': 0.4575, 'learning_rate': 2.0039443437277483e-07, 'epoch': 0.94} + 94%|█████████▍| 11212/11952 [3:26:49<1:14:42, 6.06s/it] 94%|█████████▍| 11213/11952 [3:26:54<1:13:17, 5.95s/it] {'loss': 0.4808, 'learning_rate': 1.9985500382858846e-07, 'epoch': 0.94} + 94%|█████████▍| 11213/11952 [3:26:54<1:13:17, 5.95s/it] 94%|█████████▍| 11214/11952 [3:27:00<1:12:46, 5.92s/it] {'loss': 0.4879, 'learning_rate': 1.9931629296629062e-07, 'epoch': 0.94} + 94%|█████████▍| 11214/11952 [3:27:00<1:12:46, 5.92s/it] 94%|█████████▍| 11215/11952 [3:27:06<1:11:51, 5.85s/it] {'loss': 0.4643, 'learning_rate': 1.9877830182543966e-07, 'epoch': 0.94} + 94%|█████████▍| 11215/11952 [3:27:06<1:11:51, 5.85s/it] 94%|█████████▍| 11216/11952 [3:27:12<1:12:35, 5.92s/it] {'loss': 0.4918, 'learning_rate': 1.982410304455429e-07, 'epoch': 0.94} + 94%|█████████▍| 11216/11952 [3:27:12<1:12:35, 5.92s/it] 94%|█████████▍| 11217/11952 [3:27:18<1:12:07, 5.89s/it] {'loss': 0.4732, 'learning_rate': 1.977044788660576e-07, 'epoch': 0.94} + 94%|█████████▍| 11217/11952 [3:27:18<1:12:07, 5.89s/it] 94%|█████████▍| 11218/11952 [3:27:24<1:12:32, 5.93s/it] {'loss': 0.458, 'learning_rate': 1.9716864712638452e-07, 'epoch': 0.94} + 94%|█████████▍| 11218/11952 [3:27:24<1:12:32, 5.93s/it] 94%|█████████▍| 11219/11952 [3:27:30<1:11:36, 5.86s/it] {'loss': 0.4465, 'learning_rate': 1.9663353526587104e-07, 'epoch': 0.94} + 94%|█████████▍| 11219/11952 [3:27:30<1:11:36, 5.86s/it] 94%|█████████▍| 11220/11952 [3:27:35<1:10:28, 5.78s/it] {'loss': 0.467, 'learning_rate': 1.9609914332381797e-07, 'epoch': 0.94} + 94%|█████████▍| 11220/11952 [3:27:35<1:10:28, 5.78s/it] 94%|█████████▍| 11221/11952 [3:27:41<1:11:15, 5.85s/it] {'loss': 0.471, 'learning_rate': 1.9556547133946503e-07, 'epoch': 0.94} + 94%|█████████▍| 11221/11952 [3:27:41<1:11:15, 5.85s/it] 94%|█████████▍| 11222/11952 [3:27:47<1:10:56, 5.83s/it] {'loss': 0.4334, 'learning_rate': 1.9503251935200418e-07, 'epoch': 0.94} + 94%|█████████▍| 11222/11952 [3:27:47<1:10:56, 5.83s/it] 94%|█████████▍| 11223/11952 [3:27:53<1:10:12, 5.78s/it] {'loss': 0.4527, 'learning_rate': 1.9450028740057415e-07, 'epoch': 0.94} + 94%|█████████▍| 11223/11952 [3:27:53<1:10:12, 5.78s/it] 94%|█████████▍| 11224/11952 [3:27:58<1:10:28, 5.81s/it] {'loss': 0.4616, 'learning_rate': 1.9396877552425808e-07, 'epoch': 0.94} + 94%|█████████▍| 11224/11952 [3:27:58<1:10:28, 5.81s/it] 94%|█████████▍| 11225/11952 [3:28:04<1:10:11, 5.79s/it] {'loss': 0.4508, 'learning_rate': 1.9343798376208812e-07, 'epoch': 0.94} + 94%|█████████▍| 11225/11952 [3:28:04<1:10:11, 5.79s/it] 94%|█████████▍| 11226/11952 [3:28:10<1:10:12, 5.80s/it] {'loss': 0.4742, 'learning_rate': 1.9290791215304527e-07, 'epoch': 0.94} + 94%|█████████▍| 11226/11952 [3:28:10<1:10:12, 5.80s/it] 94%|█████████▍| 11227/11952 [3:28:16<1:10:26, 5.83s/it] {'loss': 0.4621, 'learning_rate': 1.92378560736054e-07, 'epoch': 0.94} + 94%|█████████▍| 11227/11952 [3:28:16<1:10:26, 5.83s/it] 94%|█████████▍| 11228/11952 [3:28:22<1:10:06, 5.81s/it] {'loss': 0.4577, 'learning_rate': 1.918499295499887e-07, 'epoch': 0.94} + 94%|█████████▍| 11228/11952 [3:28:22<1:10:06, 5.81s/it] 94%|█████████▍| 11229/11952 [3:28:28<1:10:41, 5.87s/it] {'loss': 0.4754, 'learning_rate': 1.913220186336684e-07, 'epoch': 0.94} + 94%|█████████▍| 11229/11952 [3:28:28<1:10:41, 5.87s/it] 94%|█████████▍| 11230/11952 [3:28:34<1:10:36, 5.87s/it] {'loss': 0.4778, 'learning_rate': 1.9079482802586314e-07, 'epoch': 0.94} + 94%|█████████▍| 11230/11952 [3:28:34<1:10:36, 5.87s/it] 94%|█████████▍| 11231/11952 [3:28:39<1:10:22, 5.86s/it] {'loss': 0.443, 'learning_rate': 1.9026835776528529e-07, 'epoch': 0.94} + 94%|█████████▍| 11231/11952 [3:28:39<1:10:22, 5.86s/it] 94%|█████████▍| 11232/11952 [3:28:45<1:10:27, 5.87s/it] {'loss': 0.4614, 'learning_rate': 1.897426078905984e-07, 'epoch': 0.94} + 94%|█████████▍| 11232/11952 [3:28:45<1:10:27, 5.87s/it] 94%|█████████▍| 11233/11952 [3:28:51<1:10:47, 5.91s/it] {'loss': 0.4567, 'learning_rate': 1.8921757844040821e-07, 'epoch': 0.94} + 94%|█████████▍| 11233/11952 [3:28:51<1:10:47, 5.91s/it] 94%|█████████▍| 11234/11952 [3:28:57<1:10:43, 5.91s/it] {'loss': 0.4597, 'learning_rate': 1.8869326945327505e-07, 'epoch': 0.94} + 94%|█████████▍| 11234/11952 [3:28:57<1:10:43, 5.91s/it] 94%|█████████▍| 11235/11952 [3:29:03<1:10:29, 5.90s/it] {'loss': 0.4536, 'learning_rate': 1.8816968096769917e-07, 'epoch': 0.94} + 94%|█████████▍| 11235/11952 [3:29:03<1:10:29, 5.90s/it] 94%|█████████▍| 11236/11952 [3:29:09<1:10:26, 5.90s/it] {'loss': 0.4508, 'learning_rate': 1.8764681302213096e-07, 'epoch': 0.94} + 94%|█████████▍| 11236/11952 [3:29:09<1:10:26, 5.90s/it] 94%|█████████▍| 11237/11952 [3:29:15<1:11:08, 5.97s/it] {'loss': 0.4729, 'learning_rate': 1.8712466565496966e-07, 'epoch': 0.94} + 94%|█████████▍| 11237/11952 [3:29:15<1:11:08, 5.97s/it] 94%|█████████▍| 11238/11952 [3:29:21<1:11:11, 5.98s/it] {'loss': 0.4623, 'learning_rate': 1.866032389045569e-07, 'epoch': 0.94} + 94%|█████████▍| 11238/11952 [3:29:21<1:11:11, 5.98s/it] 94%|█████████▍| 11239/11952 [3:29:27<1:09:49, 5.88s/it] {'loss': 0.4619, 'learning_rate': 1.860825328091853e-07, 'epoch': 0.94} + 94%|█████████▍| 11239/11952 [3:29:27<1:09:49, 5.88s/it] 94%|█████████▍| 11240/11952 [3:29:33<1:09:35, 5.87s/it] {'loss': 0.4518, 'learning_rate': 1.8556254740709322e-07, 'epoch': 0.94} + 94%|█████████▍| 11240/11952 [3:29:33<1:09:35, 5.87s/it] 94%|█████████▍| 11241/11952 [3:29:39<1:09:38, 5.88s/it] {'loss': 0.4522, 'learning_rate': 1.8504328273646676e-07, 'epoch': 0.94} + 94%|█████████▍| 11241/11952 [3:29:39<1:09:38, 5.88s/it] 94%|█████████▍| 11242/11952 [3:29:44<1:09:51, 5.90s/it] {'loss': 0.4689, 'learning_rate': 1.8452473883543876e-07, 'epoch': 0.94} + 94%|█████████▍| 11242/11952 [3:29:44<1:09:51, 5.90s/it] 94%|█████████▍| 11243/11952 [3:29:51<1:10:21, 5.95s/it] {'loss': 0.4826, 'learning_rate': 1.8400691574208763e-07, 'epoch': 0.94} + 94%|█████████▍| 11243/11952 [3:29:51<1:10:21, 5.95s/it] 94%|█████████▍| 11244/11952 [3:29:57<1:10:46, 6.00s/it] {'loss': 0.4514, 'learning_rate': 1.8348981349444073e-07, 'epoch': 0.94} + 94%|█████████▍| 11244/11952 [3:29:57<1:10:46, 6.00s/it] 94%|█████████▍| 11245/11952 [3:30:03<1:10:21, 5.97s/it] {'loss': 0.4614, 'learning_rate': 1.8297343213047215e-07, 'epoch': 0.94} + 94%|█████████▍| 11245/11952 [3:30:03<1:10:21, 5.97s/it] 94%|█████████▍| 11246/11952 [3:30:08<1:09:38, 5.92s/it] {'loss': 0.4789, 'learning_rate': 1.8245777168810264e-07, 'epoch': 0.94} + 94%|█████████▍| 11246/11952 [3:30:08<1:09:38, 5.92s/it] 94%|█████████▍| 11247/11952 [3:30:14<1:09:37, 5.93s/it] {'loss': 0.4497, 'learning_rate': 1.8194283220519972e-07, 'epoch': 0.94} + 94%|█████████▍| 11247/11952 [3:30:14<1:09:37, 5.93s/it] 94%|█████████▍| 11248/11952 [3:30:20<1:09:16, 5.90s/it] {'loss': 0.4716, 'learning_rate': 1.8142861371957866e-07, 'epoch': 0.94} + 94%|█████████▍| 11248/11952 [3:30:20<1:09:16, 5.90s/it] 94%|█████████▍| 11249/11952 [3:30:26<1:08:26, 5.84s/it] {'loss': 0.4514, 'learning_rate': 1.809151162690026e-07, 'epoch': 0.94} + 94%|█████████▍| 11249/11952 [3:30:26<1:08:26, 5.84s/it]5 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +06 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend...3 AutoResumeHook: Checking whether to suspend... + +2 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... + 94%|█████████▍| 11250/11952 [3:30:32<1:08:17, 5.84s/it] {'loss': 0.4515, 'learning_rate': 1.8040233989117915e-07, 'epoch': 0.94} + 94%|█████████▍| 11250/11952 [3:30:32<1:08:17, 5.84s/it] 94%|█████████▍| 11251/11952 [3:30:38<1:09:07, 5.92s/it] {'loss': 0.4727, 'learning_rate': 1.79890284623766e-07, 'epoch': 0.94} + 94%|█████████▍| 11251/11952 [3:30:38<1:09:07, 5.92s/it] 94%|█████████▍| 11252/11952 [3:30:44<1:08:21, 5.86s/it] {'loss': 0.4491, 'learning_rate': 1.7937895050436528e-07, 'epoch': 0.94} + 94%|█████████▍| 11252/11952 [3:30:44<1:08:21, 5.86s/it] 94%|█████████▍| 11253/11952 [3:30:49<1:07:27, 5.79s/it] {'loss': 0.4514, 'learning_rate': 1.7886833757052692e-07, 'epoch': 0.94} + 94%|█████████▍| 11253/11952 [3:30:49<1:07:27, 5.79s/it] 94%|█████████▍| 11254/11952 [3:30:55<1:07:07, 5.77s/it] {'loss': 0.4681, 'learning_rate': 1.783584458597476e-07, 'epoch': 0.94} + 94%|█████████▍| 11254/11952 [3:30:55<1:07:07, 5.77s/it] 94%|█████████▍| 11255/11952 [3:31:01<1:07:38, 5.82s/it] {'loss': 0.4641, 'learning_rate': 1.7784927540947406e-07, 'epoch': 0.94} + 94%|█████████▍| 11255/11952 [3:31:01<1:07:38, 5.82s/it] 94%|█████████▍| 11256/11952 [3:31:07<1:07:09, 5.79s/it] {'loss': 0.4511, 'learning_rate': 1.7734082625709637e-07, 'epoch': 0.94} + 94%|█████████▍| 11256/11952 [3:31:07<1:07:09, 5.79s/it] 94%|█████████▍| 11257/11952 [3:31:12<1:07:29, 5.83s/it] {'loss': 0.4866, 'learning_rate': 1.7683309843995245e-07, 'epoch': 0.94} + 94%|█████████▍| 11257/11952 [3:31:12<1:07:29, 5.83s/it] 94%|█████████▍| 11258/11952 [3:31:18<1:07:28, 5.83s/it] {'loss': 0.4605, 'learning_rate': 1.76326091995328e-07, 'epoch': 0.94} + 94%|█████████▍| 11258/11952 [3:31:18<1:07:28, 5.83s/it] 94%|█████████▍| 11259/11952 [3:31:24<1:07:53, 5.88s/it] {'loss': 0.4512, 'learning_rate': 1.7581980696045665e-07, 'epoch': 0.94} + 94%|█████████▍| 11259/11952 [3:31:24<1:07:53, 5.88s/it] 94%|█████████▍| 11260/11952 [3:31:30<1:08:52, 5.97s/it] {'loss': 0.4494, 'learning_rate': 1.7531424337251523e-07, 'epoch': 0.94} + 94%|█████████▍| 11260/11952 [3:31:30<1:08:52, 5.97s/it] 94%|█████████▍| 11261/11952 [3:31:36<1:08:08, 5.92s/it] {'loss': 0.4466, 'learning_rate': 1.74809401268633e-07, 'epoch': 0.94} + 94%|█████████▍| 11261/11952 [3:31:36<1:08:08, 5.92s/it] 94%|█████████▍| 11262/11952 [3:31:42<1:07:44, 5.89s/it] {'loss': 0.4511, 'learning_rate': 1.7430528068588136e-07, 'epoch': 0.94} + 94%|█████████▍| 11262/11952 [3:31:42<1:07:44, 5.89s/it] 94%|█████████▍| 11263/11952 [3:31:48<1:07:35, 5.89s/it] {'loss': 0.4694, 'learning_rate': 1.73801881661283e-07, 'epoch': 0.94} + 94%|█████████▍| 11263/11952 [3:31:48<1:07:35, 5.89s/it] 94%|█████████▍| 11264/11952 [3:31:54<1:07:02, 5.85s/it] {'loss': 0.4656, 'learning_rate': 1.732992042318038e-07, 'epoch': 0.94} + 94%|█████████▍| 11264/11952 [3:31:54<1:07:02, 5.85s/it] 94%|█████████▍| 11265/11952 [3:32:00<1:07:15, 5.87s/it] {'loss': 0.4696, 'learning_rate': 1.7279724843435874e-07, 'epoch': 0.94} + 94%|█████████▍| 11265/11952 [3:32:00<1:07:15, 5.87s/it] 94%|█████████▍| 11266/11952 [3:32:06<1:07:47, 5.93s/it] {'loss': 0.4668, 'learning_rate': 1.7229601430580832e-07, 'epoch': 0.94} + 94%|█████████▍| 11266/11952 [3:32:06<1:07:47, 5.93s/it] 94%|█████████▍| 11267/11952 [3:32:12<1:08:10, 5.97s/it] {'loss': 0.4587, 'learning_rate': 1.7179550188296313e-07, 'epoch': 0.94} + 94%|█████████▍| 11267/11952 [3:32:12<1:08:10, 5.97s/it] 94%|█████████▍| 11268/11952 [3:32:17<1:06:37, 5.84s/it] {'loss': 0.4508, 'learning_rate': 1.7129571120257705e-07, 'epoch': 0.94} + 94%|█████████▍| 11268/11952 [3:32:17<1:06:37, 5.84s/it] 94%|█████████▍| 11269/11952 [3:32:23<1:07:01, 5.89s/it] {'loss': 0.4877, 'learning_rate': 1.7079664230135406e-07, 'epoch': 0.94} + 94%|█████████▍| 11269/11952 [3:32:23<1:07:01, 5.89s/it] 94%|█████████▍| 11270/11952 [3:32:29<1:06:08, 5.82s/it] {'loss': 0.4431, 'learning_rate': 1.7029829521594265e-07, 'epoch': 0.94} + 94%|█████████▍| 11270/11952 [3:32:29<1:06:08, 5.82s/it] 94%|█████████▍| 11271/11952 [3:32:35<1:06:06, 5.83s/it] {'loss': 0.4604, 'learning_rate': 1.698006699829402e-07, 'epoch': 0.94} + 94%|█████████▍| 11271/11952 [3:32:35<1:06:06, 5.83s/it] 94%|█████████▍| 11272/11952 [3:32:40<1:05:15, 5.76s/it] {'loss': 0.4764, 'learning_rate': 1.693037666388886e-07, 'epoch': 0.94} + 94%|█████████▍| 11272/11952 [3:32:40<1:05:15, 5.76s/it] 94%|█████████▍| 11273/11952 [3:32:46<1:05:09, 5.76s/it] {'loss': 0.449, 'learning_rate': 1.6880758522028083e-07, 'epoch': 0.94} + 94%|█████████▍| 11273/11952 [3:32:46<1:05:09, 5.76s/it] 94%|█████████▍| 11274/11952 [3:32:52<1:06:44, 5.91s/it] {'loss': 0.4654, 'learning_rate': 1.6831212576355116e-07, 'epoch': 0.94} + 94%|█████████▍| 11274/11952 [3:32:52<1:06:44, 5.91s/it] 94%|█████████▍| 11275/11952 [3:32:59<1:07:21, 5.97s/it] {'loss': 0.4697, 'learning_rate': 1.6781738830508708e-07, 'epoch': 0.94} + 94%|█████████▍| 11275/11952 [3:32:59<1:07:21, 5.97s/it] 94%|█████████▍| 11276/11952 [3:33:04<1:06:54, 5.94s/it] {'loss': 0.4456, 'learning_rate': 1.6732337288121848e-07, 'epoch': 0.94} + 94%|█████████▍| 11276/11952 [3:33:04<1:06:54, 5.94s/it] 94%|█████████▍| 11277/11952 [3:33:10<1:06:51, 5.94s/it] {'loss': 0.4683, 'learning_rate': 1.6683007952822405e-07, 'epoch': 0.94} + 94%|█████████▍| 11277/11952 [3:33:10<1:06:51, 5.94s/it] 94%|█████████▍| 11278/11952 [3:33:17<1:07:41, 6.03s/it] {'loss': 0.4491, 'learning_rate': 1.663375082823293e-07, 'epoch': 0.94} + 94%|█████████▍| 11278/11952 [3:33:17<1:07:41, 6.03s/it] 94%|█████████▍| 11279/11952 [3:33:22<1:07:04, 5.98s/it] {'loss': 0.4488, 'learning_rate': 1.658456591797075e-07, 'epoch': 0.94} + 94%|█████████▍| 11279/11952 [3:33:22<1:07:04, 5.98s/it] 94%|█████████▍| 11280/11952 [3:33:28<1:06:47, 5.96s/it] {'loss': 0.4635, 'learning_rate': 1.6535453225647645e-07, 'epoch': 0.94} + 94%|█████████▍| 11280/11952 [3:33:28<1:06:47, 5.96s/it] 94%|█████████▍| 11281/11952 [3:33:35<1:07:50, 6.07s/it] {'loss': 0.4656, 'learning_rate': 1.6486412754870286e-07, 'epoch': 0.94} + 94%|█████████▍| 11281/11952 [3:33:35<1:07:50, 6.07s/it] 94%|█████████▍| 11282/11952 [3:33:41<1:07:41, 6.06s/it] {'loss': 0.489, 'learning_rate': 1.643744450924012e-07, 'epoch': 0.94} + 94%|█████████▍| 11282/11952 [3:33:41<1:07:41, 6.06s/it] 94%|█████████▍| 11283/11952 [3:33:47<1:08:43, 6.16s/it] {'loss': 0.4561, 'learning_rate': 1.638854849235305e-07, 'epoch': 0.94} + 94%|█████████▍| 11283/11952 [3:33:47<1:08:43, 6.16s/it] 94%|█████████▍| 11284/11952 [3:33:53<1:07:45, 6.09s/it] {'loss': 0.458, 'learning_rate': 1.6339724707799875e-07, 'epoch': 0.94} + 94%|█████████▍| 11284/11952 [3:33:53<1:07:45, 6.09s/it] 94%|█████████▍| 11285/11952 [3:33:59<1:06:58, 6.03s/it] {'loss': 0.4563, 'learning_rate': 1.6290973159165945e-07, 'epoch': 0.94} + 94%|█████████▍| 11285/11952 [3:33:59<1:06:58, 6.03s/it] 94%|█████████▍| 11286/11952 [3:34:05<1:05:30, 5.90s/it] {'loss': 0.4512, 'learning_rate': 1.62422938500314e-07, 'epoch': 0.94} + 94%|█████████▍| 11286/11952 [3:34:05<1:05:30, 5.90s/it] 94%|█████████▍| 11287/11952 [3:34:10<1:04:49, 5.85s/it] {'loss': 0.4662, 'learning_rate': 1.619368678397093e-07, 'epoch': 0.94} + 94%|█████████▍| 11287/11952 [3:34:10<1:04:49, 5.85s/it] 94%|█████████▍| 11288/11952 [3:34:16<1:05:07, 5.89s/it] {'loss': 0.4656, 'learning_rate': 1.614515196455424e-07, 'epoch': 0.94} + 94%|█████████▍| 11288/11952 [3:34:16<1:05:07, 5.89s/it] 94%|█████████▍| 11289/11952 [3:34:22<1:05:05, 5.89s/it] {'loss': 0.4872, 'learning_rate': 1.6096689395345366e-07, 'epoch': 0.94} + 94%|█████████▍| 11289/11952 [3:34:22<1:05:05, 5.89s/it] 94%|█████████▍| 11290/11952 [3:34:28<1:04:51, 5.88s/it] {'loss': 0.4777, 'learning_rate': 1.604829907990335e-07, 'epoch': 0.94} + 94%|█████████▍| 11290/11952 [3:34:28<1:04:51, 5.88s/it] 94%|█████████▍| 11291/11952 [3:34:34<1:05:23, 5.94s/it] {'loss': 0.4589, 'learning_rate': 1.5999981021781685e-07, 'epoch': 0.94} + 94%|█████████▍| 11291/11952 [3:34:34<1:05:23, 5.94s/it] 94%|█████████▍| 11292/11952 [3:34:40<1:05:38, 5.97s/it] {'loss': 0.4641, 'learning_rate': 1.595173522452864e-07, 'epoch': 0.94} + 94%|█████████▍| 11292/11952 [3:34:40<1:05:38, 5.97s/it] 94%|█████████▍| 11293/11952 [3:34:46<1:05:13, 5.94s/it] {'loss': 0.4715, 'learning_rate': 1.5903561691687164e-07, 'epoch': 0.94} + 94%|█████████▍| 11293/11952 [3:34:46<1:05:13, 5.94s/it] 94%|█████████▍| 11294/11952 [3:34:52<1:04:39, 5.90s/it] {'loss': 0.446, 'learning_rate': 1.5855460426794865e-07, 'epoch': 0.94} + 94%|█████████▍| 11294/11952 [3:34:52<1:04:39, 5.90s/it] 95%|█████████▍| 11295/11952 [3:34:57<1:03:56, 5.84s/it] {'loss': 0.4725, 'learning_rate': 1.5807431433384368e-07, 'epoch': 0.94} + 95%|█████████▍| 11295/11952 [3:34:57<1:03:56, 5.84s/it] 95%|█████████▍| 11296/11952 [3:35:03<1:03:27, 5.80s/it] {'loss': 0.4727, 'learning_rate': 1.5759474714982405e-07, 'epoch': 0.95} + 95%|█████████▍| 11296/11952 [3:35:03<1:03:27, 5.80s/it] 95%|█████████▍| 11297/11952 [3:35:10<1:05:41, 6.02s/it] {'loss': 0.4476, 'learning_rate': 1.5711590275110933e-07, 'epoch': 0.95} + 95%|█████████▍| 11297/11952 [3:35:10<1:05:41, 6.02s/it] 95%|█████████▍| 11298/11952 [3:35:15<1:04:49, 5.95s/it] {'loss': 0.4618, 'learning_rate': 1.5663778117286254e-07, 'epoch': 0.95} + 95%|█████████▍| 11298/11952 [3:35:15<1:04:49, 5.95s/it] 95%|█████████▍| 11299/11952 [3:35:22<1:05:29, 6.02s/it] {'loss': 0.4643, 'learning_rate': 1.561603824501956e-07, 'epoch': 0.95} + 95%|█████████▍| 11299/11952 [3:35:22<1:05:29, 6.02s/it]2 AutoResumeHook: Checking whether to suspend... +3 5AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... +07 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... + 95%|█████████▍| 11300/11952 [3:35:28<1:04:52, 5.97s/it]1 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4793, 'learning_rate': 1.5568370661816713e-07, 'epoch': 0.95} + 95%|█████████▍| 11300/11952 [3:35:28<1:04:52, 5.97s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-11300/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-11300/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/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( + 95%|█████████▍| 11301/11952 [3:35:58<2:23:07, 13.19s/it] {'loss': 0.4569, 'learning_rate': 1.552077537117802e-07, 'epoch': 0.95} + 95%|█████████▍| 11301/11952 [3:35:58<2:23:07, 13.19s/it] 95%|█████████▍| 11302/11952 [3:36:04<2:00:15, 11.10s/it] {'loss': 0.4629, 'learning_rate': 1.5473252376598913e-07, 'epoch': 0.95} + 95%|█████████▍| 11302/11952 [3:36:04<2:00:15, 11.10s/it] 95%|█████████▍| 11303/11952 [3:36:10<1:43:16, 9.55s/it] {'loss': 0.4617, 'learning_rate': 1.5425801681569263e-07, 'epoch': 0.95} + 95%|█████████▍| 11303/11952 [3:36:10<1:43:16, 9.55s/it] 95%|█████████▍| 11304/11952 [3:36:16<1:31:02, 8.43s/it] {'loss': 0.4613, 'learning_rate': 1.5378423289573508e-07, 'epoch': 0.95} + 95%|█████████▍| 11304/11952 [3:36:16<1:31:02, 8.43s/it] 95%|█████████▍| 11305/11952 [3:36:21<1:22:29, 7.65s/it] {'loss': 0.45, 'learning_rate': 1.5331117204091085e-07, 'epoch': 0.95} + 95%|█████████▍| 11305/11952 [3:36:21<1:22:29, 7.65s/it] 95%|█████████▍| 11306/11952 [3:36:27<1:16:56, 7.15s/it] {'loss': 0.4758, 'learning_rate': 1.528388342859577e-07, 'epoch': 0.95} + 95%|█████████▍| 11306/11952 [3:36:27<1:16:56, 7.15s/it] 95%|█████████▍| 11307/11952 [3:36:33<1:13:07, 6.80s/it] {'loss': 0.4927, 'learning_rate': 1.5236721966556456e-07, 'epoch': 0.95} + 95%|█████████▍| 11307/11952 [3:36:33<1:13:07, 6.80s/it] 95%|█████████▍| 11308/11952 [3:36:39<1:09:48, 6.50s/it] {'loss': 0.4616, 'learning_rate': 1.518963282143615e-07, 'epoch': 0.95} + 95%|█████████▍| 11308/11952 [3:36:39<1:09:48, 6.50s/it] 95%|█████████▍| 11309/11952 [3:36:45<1:08:20, 6.38s/it] {'loss': 0.4713, 'learning_rate': 1.5142615996693087e-07, 'epoch': 0.95} + 95%|█████████▍| 11309/11952 [3:36:45<1:08:20, 6.38s/it] 95%|█████████▍| 11310/11952 [3:36:51<1:07:07, 6.27s/it] {'loss': 0.4613, 'learning_rate': 1.5095671495780062e-07, 'epoch': 0.95} + 95%|█████████▍| 11310/11952 [3:36:51<1:07:07, 6.27s/it] 95%|█████████▍| 11311/11952 [3:36:57<1:05:33, 6.14s/it] {'loss': 0.4549, 'learning_rate': 1.5048799322144426e-07, 'epoch': 0.95} + 95%|█████████▍| 11311/11952 [3:36:57<1:05:33, 6.14s/it] 95%|█████████▍| 11312/11952 [3:37:03<1:05:32, 6.14s/it] {'loss': 0.459, 'learning_rate': 1.5001999479228203e-07, 'epoch': 0.95} + 95%|█████████▍| 11312/11952 [3:37:03<1:05:32, 6.14s/it] 95%|█████████▍| 11313/11952 [3:37:09<1:04:15, 6.03s/it] {'loss': 0.4595, 'learning_rate': 1.49552719704682e-07, 'epoch': 0.95} + 95%|█████████▍| 11313/11952 [3:37:09<1:04:15, 6.03s/it] 95%|█████████▍| 11314/11952 [3:37:15<1:02:52, 5.91s/it] {'loss': 0.4503, 'learning_rate': 1.4908616799296006e-07, 'epoch': 0.95} + 95%|█████████▍| 11314/11952 [3:37:15<1:02:52, 5.91s/it] 95%|█████████▍| 11315/11952 [3:37:20<1:01:39, 5.81s/it] {'loss': 0.4753, 'learning_rate': 1.4862033969137545e-07, 'epoch': 0.95} + 95%|█████████▍| 11315/11952 [3:37:20<1:01:39, 5.81s/it] 95%|█████████▍| 11316/11952 [3:37:27<1:03:37, 6.00s/it] {'loss': 0.4399, 'learning_rate': 1.4815523483413864e-07, 'epoch': 0.95} + 95%|█████████▍| 11316/11952 [3:37:27<1:03:37, 6.00s/it] 95%|█████████▍| 11317/11952 [3:37:33<1:03:59, 6.05s/it] {'loss': 0.4847, 'learning_rate': 1.4769085345540556e-07, 'epoch': 0.95} + 95%|█████████▍| 11317/11952 [3:37:33<1:03:59, 6.05s/it] 95%|█████████▍| 11318/11952 [3:37:39<1:03:23, 6.00s/it] {'loss': 0.4602, 'learning_rate': 1.472271955892768e-07, 'epoch': 0.95} + 95%|█████████▍| 11318/11952 [3:37:39<1:03:23, 6.00s/it] 95%|█████████▍| 11319/11952 [3:37:44<1:02:29, 5.92s/it] {'loss': 0.4709, 'learning_rate': 1.4676426126980058e-07, 'epoch': 0.95} + 95%|█████████▍| 11319/11952 [3:37:44<1:02:29, 5.92s/it] 95%|█████████▍| 11320/11952 [3:37:50<1:02:33, 5.94s/it] {'loss': 0.4564, 'learning_rate': 1.4630205053097645e-07, 'epoch': 0.95} + 95%|█████████▍| 11320/11952 [3:37:50<1:02:33, 5.94s/it] 95%|█████████▍| 11321/11952 [3:37:56<1:02:23, 5.93s/it] {'loss': 0.4561, 'learning_rate': 1.4584056340674392e-07, 'epoch': 0.95} + 95%|█████████▍| 11321/11952 [3:37:56<1:02:23, 5.93s/it] 95%|█████████▍| 11322/11952 [3:38:02<1:02:39, 5.97s/it] {'loss': 0.4634, 'learning_rate': 1.4537979993099361e-07, 'epoch': 0.95} + 95%|█████████▍| 11322/11952 [3:38:02<1:02:39, 5.97s/it] 95%|█████████▍| 11323/11952 [3:38:08<1:02:15, 5.94s/it] {'loss': 0.462, 'learning_rate': 1.4491976013756292e-07, 'epoch': 0.95} + 95%|█████████▍| 11323/11952 [3:38:08<1:02:15, 5.94s/it] 95%|█████████▍| 11324/11952 [3:38:14<1:01:13, 5.85s/it] {'loss': 0.4504, 'learning_rate': 1.4446044406023485e-07, 'epoch': 0.95} + 95%|█████████▍| 11324/11952 [3:38:14<1:01:13, 5.85s/it] 95%|█████████▍| 11325/11952 [3:38:20<1:00:53, 5.83s/it] {'loss': 0.4507, 'learning_rate': 1.4400185173274018e-07, 'epoch': 0.95} + 95%|█████████▍| 11325/11952 [3:38:20<1:00:53, 5.83s/it] 95%|█████████▍| 11326/11952 [3:38:25<1:00:46, 5.83s/it] {'loss': 0.4674, 'learning_rate': 1.4354398318875417e-07, 'epoch': 0.95} + 95%|█████████▍| 11326/11952 [3:38:25<1:00:46, 5.83s/it] 95%|█████████▍| 11327/11952 [3:38:31<1:00:37, 5.82s/it] {'loss': 0.4756, 'learning_rate': 1.430868384619022e-07, 'epoch': 0.95} + 95%|█████████▍| 11327/11952 [3:38:31<1:00:37, 5.82s/it] 95%|█████████▍| 11328/11952 [3:38:37<1:00:39, 5.83s/it] {'loss': 0.4396, 'learning_rate': 1.4263041758575402e-07, 'epoch': 0.95} + 95%|█████████▍| 11328/11952 [3:38:37<1:00:39, 5.83s/it] 95%|█████████▍| 11329/11952 [3:38:43<1:01:49, 5.95s/it] {'loss': 0.464, 'learning_rate': 1.4217472059382952e-07, 'epoch': 0.95} + 95%|█████████▍| 11329/11952 [3:38:43<1:01:49, 5.95s/it] 95%|█████████▍| 11330/11952 [3:38:49<1:01:03, 5.89s/it] {'loss': 0.4678, 'learning_rate': 1.4171974751959082e-07, 'epoch': 0.95} + 95%|█████████▍| 11330/11952 [3:38:49<1:01:03, 5.89s/it] 95%|█████████▍| 11331/11952 [3:38:55<1:00:41, 5.86s/it] {'loss': 0.4847, 'learning_rate': 1.4126549839645009e-07, 'epoch': 0.95} + 95%|█████████▍| 11331/11952 [3:38:55<1:00:41, 5.86s/it] 95%|█████████▍| 11332/11952 [3:39:01<59:55, 5.80s/it] {'loss': 0.4553, 'learning_rate': 1.408119732577662e-07, 'epoch': 0.95} + 95%|█████████▍| 11332/11952 [3:39:01<59:55, 5.80s/it] 95%|█████████▍| 11333/11952 [3:39:07<1:00:18, 5.85s/it] {'loss': 0.4686, 'learning_rate': 1.4035917213684358e-07, 'epoch': 0.95} + 95%|█████████▍| 11333/11952 [3:39:07<1:00:18, 5.85s/it] 95%|█████████▍| 11334/11952 [3:39:12<59:48, 5.81s/it] {'loss': 0.4596, 'learning_rate': 1.3990709506693457e-07, 'epoch': 0.95} + 95%|█████████▍| 11334/11952 [3:39:12<59:48, 5.81s/it] 95%|█████████▍| 11335/11952 [3:39:18<59:24, 5.78s/it] {'loss': 0.443, 'learning_rate': 1.394557420812359e-07, 'epoch': 0.95} + 95%|█████████▍| 11335/11952 [3:39:18<59:24, 5.78s/it] 95%|█████████▍| 11336/11952 [3:39:24<59:18, 5.78s/it] {'loss': 0.4613, 'learning_rate': 1.3900511321289557e-07, 'epoch': 0.95} + 95%|█████████▍| 11336/11952 [3:39:24<59:18, 5.78s/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%|█████████▍| 11337/11952 [3:39:30<59:31, 5.81s/it] {'loss': 0.4579, 'learning_rate': 1.385552084950037e-07, 'epoch': 0.95} + 95%|█████████▍| 11337/11952 [3:39:30<59:31, 5.81s/it] 95%|█████████▍| 11338/11952 [3:39:35<59:20, 5.80s/it] {'loss': 0.4549, 'learning_rate': 1.381060279606017e-07, 'epoch': 0.95} + 95%|█████████▍| 11338/11952 [3:39:35<59:20, 5.80s/it] 95%|█████████▍| 11339/11952 [3:39:41<59:04, 5.78s/it] {'loss': 0.4551, 'learning_rate': 1.3765757164267313e-07, 'epoch': 0.95} + 95%|█████████▍| 11339/11952 [3:39:41<59:04, 5.78s/it] 95%|█████████▍| 11340/11952 [3:39:47<1:00:01, 5.88s/it] {'loss': 0.4749, 'learning_rate': 1.3720983957415278e-07, 'epoch': 0.95} + 95%|█████████▍| 11340/11952 [3:39:47<1:00:01, 5.88s/it] 95%|█████████▍| 11341/11952 [3:39:53<59:05, 5.80s/it] {'loss': 0.4428, 'learning_rate': 1.3676283178791882e-07, 'epoch': 0.95} + 95%|█████████▍| 11341/11952 [3:39:53<59:05, 5.80s/it] 95%|█████████▍| 11342/11952 [3:39:59<59:22, 5.84s/it] {'loss': 0.4797, 'learning_rate': 1.363165483167983e-07, 'epoch': 0.95} + 95%|█████████▍| 11342/11952 [3:39:59<59:22, 5.84s/it] 95%|█████████▍| 11343/11952 [3:40:05<1:00:42, 5.98s/it] {'loss': 0.4681, 'learning_rate': 1.35870989193565e-07, 'epoch': 0.95} + 95%|█████████▍| 11343/11952 [3:40:05<1:00:42, 5.98s/it] 95%|█████████▍| 11344/11952 [3:40:11<1:00:48, 6.00s/it] {'loss': 0.4495, 'learning_rate': 1.3542615445093722e-07, 'epoch': 0.95} + 95%|█████████▍| 11344/11952 [3:40:11<1:00:48, 6.00s/it] 95%|█████████▍| 11345/11952 [3:40:17<1:00:04, 5.94s/it] {'loss': 0.4612, 'learning_rate': 1.3498204412158434e-07, 'epoch': 0.95} + 95%|█████████▍| 11345/11952 [3:40:17<1:00:04, 5.94s/it] 95%|█████████▍| 11346/11952 [3:40:23<59:51, 5.93s/it] {'loss': 0.4608, 'learning_rate': 1.3453865823811696e-07, 'epoch': 0.95} + 95%|█████████▍| 11346/11952 [3:40:23<59:51, 5.93s/it] 95%|█████████▍| 11347/11952 [3:40:29<59:45, 5.93s/it] {'loss': 0.4477, 'learning_rate': 1.3409599683309793e-07, 'epoch': 0.95} + 95%|█████████▍| 11347/11952 [3:40:29<59:45, 5.93s/it] 95%|█████████▍| 11348/11952 [3:40:35<59:27, 5.91s/it] {'loss': 0.4679, 'learning_rate': 1.3365405993903347e-07, 'epoch': 0.95} + 95%|█████████▍| 11348/11952 [3:40:35<59:27, 5.91s/it] 95%|█████████▍| 11349/11952 [3:40:40<59:03, 5.88s/it] {'loss': 0.4465, 'learning_rate': 1.332128475883765e-07, 'epoch': 0.95} + 95%|█████████▍| 11349/11952 [3:40:40<59:03, 5.88s/it]0 AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... + 95%|█████████▍| 11350/11952 [3:40:47<59:46, 5.96s/it]5 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4629, 'learning_rate': 1.3277235981352887e-07, 'epoch': 0.95} + 95%|█████████▍| 11350/11952 [3:40:47<59:46, 5.96s/it] 95%|█████████▍| 11351/11952 [3:40:52<58:29, 5.84s/it] {'loss': 0.4655, 'learning_rate': 1.3233259664683916e-07, 'epoch': 0.95} + 95%|█████████▍| 11351/11952 [3:40:52<58:29, 5.84s/it] 95%|█████████▍| 11352/11952 [3:40:58<57:49, 5.78s/it] {'loss': 0.4558, 'learning_rate': 1.3189355812060157e-07, 'epoch': 0.95} + 95%|█████████▍| 11352/11952 [3:40:58<57:49, 5.78s/it] 95%|█████████▍| 11353/11952 [3:41:04<58:48, 5.89s/it] {'loss': 0.4475, 'learning_rate': 1.314552442670558e-07, 'epoch': 0.95} + 95%|█████████▍| 11353/11952 [3:41:04<58:48, 5.89s/it]/lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/VILA/llava/model/llava_arch.py:397: UserWarning: Inputs truncated! + warnings.warn("Inputs truncated!") + 95%|█████████▍| 11354/11952 [3:41:10<59:26, 5.96s/it] {'loss': 0.4415, 'learning_rate': 1.310176551183906e-07, 'epoch': 0.95} + 95%|█████████▍| 11354/11952 [3:41:10<59:26, 5.96s/it] 95%|█████████▌| 11355/11952 [3:41:16<58:23, 5.87s/it] {'loss': 0.4641, 'learning_rate': 1.3058079070674023e-07, 'epoch': 0.95} + 95%|█████████▌| 11355/11952 [3:41:16<58:23, 5.87s/it] 95%|█████████▌| 11356/11952 [3:41:22<59:16, 5.97s/it] {'loss': 0.4601, 'learning_rate': 1.3014465106418573e-07, 'epoch': 0.95} + 95%|█████████▌| 11356/11952 [3:41:22<59:16, 5.97s/it] 95%|█████████▌| 11357/11952 [3:41:28<1:00:08, 6.06s/it] {'loss': 0.4457, 'learning_rate': 1.297092362227581e-07, 'epoch': 0.95} + 95%|█████████▌| 11357/11952 [3:41:28<1:00:08, 6.06s/it] 95%|█████████▌| 11358/11952 [3:41:34<1:00:28, 6.11s/it] {'loss': 0.4609, 'learning_rate': 1.2927454621442959e-07, 'epoch': 0.95} + 95%|█████████▌| 11358/11952 [3:41:34<1:00:28, 6.11s/it] 95%|█████████▌| 11359/11952 [3:41:40<59:13, 5.99s/it] {'loss': 0.4725, 'learning_rate': 1.2884058107112353e-07, 'epoch': 0.95} + 95%|█████████▌| 11359/11952 [3:41:40<59:13, 5.99s/it] 95%|█████████▌| 11360/11952 [3:41:46<59:10, 6.00s/it] {'loss': 0.455, 'learning_rate': 1.2840734082470662e-07, 'epoch': 0.95} + 95%|█████████▌| 11360/11952 [3:41:46<59:10, 6.00s/it] 95%|█████████▌| 11361/11952 [3:41:52<58:38, 5.95s/it] {'loss': 0.453, 'learning_rate': 1.279748255069968e-07, 'epoch': 0.95} + 95%|█████████▌| 11361/11952 [3:41:52<58:38, 5.95s/it] 95%|█████████▌| 11362/11952 [3:41:58<58:44, 5.97s/it] {'loss': 0.4684, 'learning_rate': 1.275430351497542e-07, 'epoch': 0.95} + 95%|█████████▌| 11362/11952 [3:41:58<58:44, 5.97s/it] 95%|█████████▌| 11363/11952 [3:42:04<58:10, 5.93s/it] {'loss': 0.4651, 'learning_rate': 1.27111969784689e-07, 'epoch': 0.95} + 95%|█████████▌| 11363/11952 [3:42:04<58:10, 5.93s/it] 95%|█████████▌| 11364/11952 [3:42:10<57:34, 5.87s/it] {'loss': 0.4371, 'learning_rate': 1.2668162944345587e-07, 'epoch': 0.95} + 95%|█████████▌| 11364/11952 [3:42:10<57:34, 5.87s/it] 95%|█████████▌| 11365/11952 [3:42:16<57:37, 5.89s/it] {'loss': 0.4689, 'learning_rate': 1.262520141576584e-07, 'epoch': 0.95} + 95%|█████████▌| 11365/11952 [3:42:16<57:37, 5.89s/it] 95%|█████████▌| 11366/11952 [3:42:22<58:05, 5.95s/it] {'loss': 0.4626, 'learning_rate': 1.2582312395884476e-07, 'epoch': 0.95} + 95%|█████████▌| 11366/11952 [3:42:22<58:05, 5.95s/it] 95%|█████████▌| 11367/11952 [3:42:28<57:51, 5.93s/it] {'loss': 0.4517, 'learning_rate': 1.2539495887851083e-07, 'epoch': 0.95} + 95%|█████████▌| 11367/11952 [3:42:28<57:51, 5.93s/it] 95%|█████████▌| 11368/11952 [3:42:33<57:00, 5.86s/it] {'loss': 0.4605, 'learning_rate': 1.2496751894810032e-07, 'epoch': 0.95} + 95%|█████████▌| 11368/11952 [3:42:33<57:00, 5.86s/it] 95%|█████████▌| 11369/11952 [3:42:39<56:56, 5.86s/it] {'loss': 0.4645, 'learning_rate': 1.245408041990004e-07, 'epoch': 0.95} + 95%|█████████▌| 11369/11952 [3:42:39<56:56, 5.86s/it] 95%|█████████▌| 11370/11952 [3:42:45<56:33, 5.83s/it] {'loss': 0.4477, 'learning_rate': 1.2411481466254926e-07, 'epoch': 0.95} + 95%|█████████▌| 11370/11952 [3:42:45<56:33, 5.83s/it] 95%|█████████▌| 11371/11952 [3:42:51<57:47, 5.97s/it] {'loss': 0.4739, 'learning_rate': 1.2368955037002973e-07, 'epoch': 0.95} + 95%|█████████▌| 11371/11952 [3:42:51<57:47, 5.97s/it] 95%|█████████▌| 11372/11952 [3:42:57<57:39, 5.96s/it] {'loss': 0.4712, 'learning_rate': 1.232650113526701e-07, 'epoch': 0.95} + 95%|█████████▌| 11372/11952 [3:42:57<57:39, 5.96s/it] 95%|█████████▌| 11373/11952 [3:43:03<58:20, 6.05s/it] {'loss': 0.4649, 'learning_rate': 1.228411976416488e-07, 'epoch': 0.95} + 95%|█████████▌| 11373/11952 [3:43:03<58:20, 6.05s/it] 95%|█████████▌| 11374/11952 [3:43:09<57:10, 5.94s/it] {'loss': 0.4477, 'learning_rate': 1.2241810926808762e-07, 'epoch': 0.95} + 95%|█████████▌| 11374/11952 [3:43:09<57:10, 5.94s/it] 95%|█████████▌| 11375/11952 [3:43:15<56:45, 5.90s/it] {'loss': 0.4506, 'learning_rate': 1.219957462630561e-07, 'epoch': 0.95} + 95%|█████████▌| 11375/11952 [3:43:15<56:45, 5.90s/it] 95%|█████████▌| 11376/11952 [3:43:21<56:57, 5.93s/it] {'loss': 0.4762, 'learning_rate': 1.2157410865757057e-07, 'epoch': 0.95} + 95%|█████████▌| 11376/11952 [3:43:21<56:57, 5.93s/it] 95%|█████████▌| 11377/11952 [3:43:27<56:20, 5.88s/it] {'loss': 0.4677, 'learning_rate': 1.2115319648259516e-07, 'epoch': 0.95} + 95%|█████████▌| 11377/11952 [3:43:27<56:20, 5.88s/it] 95%|█████████▌| 11378/11952 [3:43:32<55:37, 5.81s/it] {'loss': 0.4585, 'learning_rate': 1.2073300976904067e-07, 'epoch': 0.95} + 95%|█████████▌| 11378/11952 [3:43:32<55:37, 5.81s/it] 95%|█████████▌| 11379/11952 [3:43:38<56:09, 5.88s/it] {'loss': 0.4589, 'learning_rate': 1.2031354854776356e-07, 'epoch': 0.95} + 95%|█████████▌| 11379/11952 [3:43:38<56:09, 5.88s/it] 95%|█████████▌| 11380/11952 [3:43:44<55:49, 5.86s/it] {'loss': 0.4742, 'learning_rate': 1.198948128495647e-07, 'epoch': 0.95} + 95%|█████████▌| 11380/11952 [3:43:44<55:49, 5.86s/it] 95%|█████████▌| 11381/11952 [3:43:50<56:27, 5.93s/it] {'loss': 0.4694, 'learning_rate': 1.1947680270519733e-07, 'epoch': 0.95} + 95%|█████████▌| 11381/11952 [3:43:50<56:27, 5.93s/it] 95%|█████████▌| 11382/11952 [3:43:56<55:46, 5.87s/it] {'loss': 0.4748, 'learning_rate': 1.19059518145358e-07, 'epoch': 0.95} + 95%|█████████▌| 11382/11952 [3:43:56<55:46, 5.87s/it] 95%|█████████▌| 11383/11952 [3:44:02<55:21, 5.84s/it] {'loss': 0.4683, 'learning_rate': 1.186429592006888e-07, 'epoch': 0.95} + 95%|█████████▌| 11383/11952 [3:44:02<55:21, 5.84s/it] 95%|█████████▌| 11384/11952 [3:44:07<54:58, 5.81s/it] {'loss': 0.4732, 'learning_rate': 1.1822712590178197e-07, 'epoch': 0.95} + 95%|█████████▌| 11384/11952 [3:44:07<54:58, 5.81s/it] 95%|█████████▌| 11385/11952 [3:44:13<54:43, 5.79s/it] {'loss': 0.4454, 'learning_rate': 1.178120182791731e-07, 'epoch': 0.95} + 95%|█████████▌| 11385/11952 [3:44:13<54:43, 5.79s/it] 95%|█████████▌| 11386/11952 [3:44:19<54:50, 5.81s/it] {'loss': 0.4684, 'learning_rate': 1.1739763636334667e-07, 'epoch': 0.95} + 95%|█████████▌| 11386/11952 [3:44:19<54:50, 5.81s/it] 95%|█████████▌| 11387/11952 [3:44:25<56:17, 5.98s/it] {'loss': 0.4555, 'learning_rate': 1.1698398018473278e-07, 'epoch': 0.95} + 95%|█████████▌| 11387/11952 [3:44:25<56:17, 5.98s/it] 95%|█████████▌| 11388/11952 [3:44:32<56:35, 6.02s/it] {'loss': 0.4729, 'learning_rate': 1.1657104977370937e-07, 'epoch': 0.95} + 95%|█████████▌| 11388/11952 [3:44:32<56:35, 6.02s/it] 95%|█████████▌| 11389/11952 [3:44:37<55:32, 5.92s/it] {'loss': 0.4459, 'learning_rate': 1.1615884516059883e-07, 'epoch': 0.95} + 95%|█████████▌| 11389/11952 [3:44:37<55:32, 5.92s/it] 95%|█████████▌| 11390/11952 [3:44:43<54:58, 5.87s/it] {'loss': 0.462, 'learning_rate': 1.1574736637567252e-07, 'epoch': 0.95} + 95%|█████████▌| 11390/11952 [3:44:43<54:58, 5.87s/it] 95%|█████████▌| 11391/11952 [3:44:49<56:11, 6.01s/it] {'loss': 0.4428, 'learning_rate': 1.1533661344914848e-07, 'epoch': 0.95} + 95%|█████████▌| 11391/11952 [3:44:49<56:11, 6.01s/it] 95%|█████████▌| 11392/11952 [3:44:55<55:22, 5.93s/it] {'loss': 0.4663, 'learning_rate': 1.1492658641119037e-07, 'epoch': 0.95} + 95%|█████████▌| 11392/11952 [3:44:55<55:22, 5.93s/it] 95%|█████████▌| 11393/11952 [3:45:01<54:29, 5.85s/it] {'loss': 0.4739, 'learning_rate': 1.1451728529190852e-07, 'epoch': 0.95} + 95%|█████████▌| 11393/11952 [3:45:01<54:29, 5.85s/it] 95%|█████████▌| 11394/11952 [3:45:07<55:06, 5.93s/it] {'loss': 0.4518, 'learning_rate': 1.1410871012136116e-07, 'epoch': 0.95} + 95%|█████████▌| 11394/11952 [3:45:07<55:06, 5.93s/it] 95%|█████████▌| 11395/11952 [3:45:12<54:21, 5.86s/it] {'loss': 0.4517, 'learning_rate': 1.137008609295509e-07, 'epoch': 0.95} + 95%|█████████▌| 11395/11952 [3:45:12<54:21, 5.86s/it] 95%|█████████▌| 11396/11952 [3:45:18<54:15, 5.86s/it] {'loss': 0.4603, 'learning_rate': 1.1329373774642938e-07, 'epoch': 0.95} + 95%|█████████▌| 11396/11952 [3:45:18<54:15, 5.86s/it] 95%|█████████▌| 11397/11952 [3:45:24<54:05, 5.85s/it] {'loss': 0.4487, 'learning_rate': 1.1288734060189267e-07, 'epoch': 0.95} + 95%|█████████▌| 11397/11952 [3:45:24<54:05, 5.85s/it] 95%|█████████▌| 11398/11952 [3:45:30<54:36, 5.91s/it] {'loss': 0.4477, 'learning_rate': 1.1248166952578799e-07, 'epoch': 0.95} + 95%|█████████▌| 11398/11952 [3:45:30<54:36, 5.91s/it] 95%|█████████▌| 11399/11952 [3:45:36<54:02, 5.86s/it] {'loss': 0.4674, 'learning_rate': 1.1207672454790264e-07, 'epoch': 0.95} + 95%|█████████▌| 11399/11952 [3:45:36<54:02, 5.86s/it]5 AutoResumeHook: Checking whether to suspend... +72 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... + 95%|█████████▌| 11400/11952 [3:45:42<53:38, 5.83s/it]3 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4888, 'learning_rate': 1.1167250569797728e-07, 'epoch': 0.95} + 95%|█████████▌| 11400/11952 [3:45:42<53:38, 5.83s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-11400/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-11400/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/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( + 95%|█████████▌| 11401/11952 [3:46:13<2:04:48, 13.59s/it] {'loss': 0.4248, 'learning_rate': 1.112690130056926e-07, 'epoch': 0.95} + 95%|█████████▌| 11401/11952 [3:46:13<2:04:48, 13.59s/it] 95%|█████████▌| 11402/11952 [3:46:19<1:43:02, 11.24s/it] {'loss': 0.4714, 'learning_rate': 1.1086624650068267e-07, 'epoch': 0.95} + 95%|█████████▌| 11402/11952 [3:46:19<1:43:02, 11.24s/it] 95%|█████████▌| 11403/11952 [3:46:25<1:27:46, 9.59s/it] {'loss': 0.4564, 'learning_rate': 1.1046420621252275e-07, 'epoch': 0.95} + 95%|█████████▌| 11403/11952 [3:46:25<1:27:46, 9.59s/it] 95%|█████████▌| 11404/11952 [3:46:31<1:16:55, 8.42s/it] {'loss': 0.4568, 'learning_rate': 1.1006289217073806e-07, 'epoch': 0.95} + 95%|█████████▌| 11404/11952 [3:46:31<1:16:55, 8.42s/it] 95%|█████████▌| 11405/11952 [3:46:36<1:09:13, 7.59s/it] {'loss': 0.4453, 'learning_rate': 1.0966230440479953e-07, 'epoch': 0.95} + 95%|█████████▌| 11405/11952 [3:46:36<1:09:13, 7.59s/it] 95%|█████████▌| 11406/11952 [3:46:42<1:04:28, 7.09s/it] {'loss': 0.4599, 'learning_rate': 1.0926244294412359e-07, 'epoch': 0.95} + 95%|█████████▌| 11406/11952 [3:46:42<1:04:28, 7.09s/it] 95%|█████████▌| 11407/11952 [3:46:48<1:01:59, 6.82s/it] {'loss': 0.4831, 'learning_rate': 1.0886330781807674e-07, 'epoch': 0.95} + 95%|█████████▌| 11407/11952 [3:46:48<1:01:59, 6.82s/it] 95%|█████████▌| 11408/11952 [3:46:54<59:09, 6.53s/it] {'loss': 0.459, 'learning_rate': 1.0846489905596669e-07, 'epoch': 0.95} + 95%|█████████▌| 11408/11952 [3:46:54<59:09, 6.53s/it] 95%|█████████▌| 11409/11952 [3:47:00<57:37, 6.37s/it] {'loss': 0.4722, 'learning_rate': 1.0806721668705333e-07, 'epoch': 0.95} + 95%|█████████▌| 11409/11952 [3:47:00<57:37, 6.37s/it] 95%|█████████▌| 11410/11952 [3:47:06<56:05, 6.21s/it] {'loss': 0.4564, 'learning_rate': 1.0767026074053888e-07, 'epoch': 0.95} + 95%|█████████▌| 11410/11952 [3:47:06<56:05, 6.21s/it] 95%|█████████▌| 11411/11952 [3:47:12<54:33, 6.05s/it] {'loss': 0.473, 'learning_rate': 1.0727403124557667e-07, 'epoch': 0.95} + 95%|█████████▌| 11411/11952 [3:47:12<54:33, 6.05s/it] 95%|█████████▌| 11412/11952 [3:47:18<54:18, 6.03s/it] {'loss': 0.4533, 'learning_rate': 1.0687852823126122e-07, 'epoch': 0.95} + 95%|█████████▌| 11412/11952 [3:47:18<54:18, 6.03s/it] 95%|█████████▌| 11413/11952 [3:47:24<53:43, 5.98s/it] {'loss': 0.466, 'learning_rate': 1.0648375172663927e-07, 'epoch': 0.95} + 95%|█████████▌| 11413/11952 [3:47:24<53:43, 5.98s/it] 95%|█████████▌| 11414/11952 [3:47:29<53:09, 5.93s/it] {'loss': 0.4882, 'learning_rate': 1.0608970176069987e-07, 'epoch': 0.95} + 95%|█████████▌| 11414/11952 [3:47:29<53:09, 5.93s/it] 96%|█████████▌| 11415/11952 [3:47:35<52:35, 5.88s/it] {'loss': 0.4757, 'learning_rate': 1.05696378362381e-07, 'epoch': 0.96} + 96%|█████████▌| 11415/11952 [3:47:35<52:35, 5.88s/it] 96%|█████████▌| 11416/11952 [3:47:41<52:29, 5.88s/it] {'loss': 0.4573, 'learning_rate': 1.053037815605662e-07, 'epoch': 0.96} + 96%|█████████▌| 11416/11952 [3:47:41<52:29, 5.88s/it] 96%|█████████▌| 11417/11952 [3:47:47<51:47, 5.81s/it] {'loss': 0.4652, 'learning_rate': 1.0491191138408685e-07, 'epoch': 0.96} + 96%|█████████▌| 11417/11952 [3:47:47<51:47, 5.81s/it] 96%|█████████▌| 11418/11952 [3:47:53<51:56, 5.84s/it] {'loss': 0.4586, 'learning_rate': 1.0452076786171994e-07, 'epoch': 0.96} + 96%|█████████▌| 11418/11952 [3:47:53<51:56, 5.84s/it] 96%|█████████▌| 11419/11952 [3:47:59<52:05, 5.86s/it] {'loss': 0.4461, 'learning_rate': 1.0413035102219027e-07, 'epoch': 0.96} + 96%|█████████▌| 11419/11952 [3:47:59<52:05, 5.86s/it] 96%|█████████▌| 11420/11952 [3:48:05<52:42, 5.95s/it] {'loss': 0.4575, 'learning_rate': 1.0374066089416602e-07, 'epoch': 0.96} + 96%|█████████▌| 11420/11952 [3:48:05<52:42, 5.95s/it] 96%|█████████▌| 11421/11952 [3:48:11<52:52, 5.97s/it] {'loss': 0.4532, 'learning_rate': 1.033516975062676e-07, 'epoch': 0.96} + 96%|█████████▌| 11421/11952 [3:48:11<52:52, 5.97s/it] 96%|█████████▌| 11422/11952 [3:48:17<52:39, 5.96s/it] {'loss': 0.4417, 'learning_rate': 1.0296346088705555e-07, 'epoch': 0.96} + 96%|█████████▌| 11422/11952 [3:48:17<52:39, 5.96s/it] 96%|█████████▌| 11423/11952 [3:48:22<51:59, 5.90s/it] {'loss': 0.4606, 'learning_rate': 1.025759510650437e-07, 'epoch': 0.96} + 96%|█████████▌| 11423/11952 [3:48:22<51:59, 5.90s/it] 96%|█████████▌| 11424/11952 [3:48:29<52:47, 6.00s/it] {'loss': 0.469, 'learning_rate': 1.0218916806868594e-07, 'epoch': 0.96} + 96%|█████████▌| 11424/11952 [3:48:29<52:47, 6.00s/it] 96%|█████████▌| 11425/11952 [3:48:35<52:34, 5.99s/it] {'loss': 0.4542, 'learning_rate': 1.0180311192638848e-07, 'epoch': 0.96} + 96%|█████████▌| 11425/11952 [3:48:35<52:34, 5.99s/it] 96%|█████████▌| 11426/11952 [3:48:40<51:45, 5.90s/it] {'loss': 0.4661, 'learning_rate': 1.0141778266650082e-07, 'epoch': 0.96} + 96%|█████████▌| 11426/11952 [3:48:40<51:45, 5.90s/it] 96%|█████████▌| 11427/11952 [3:48:46<51:31, 5.89s/it] {'loss': 0.4652, 'learning_rate': 1.0103318031732035e-07, 'epoch': 0.96} + 96%|█████████▌| 11427/11952 [3:48:46<51:31, 5.89s/it] 96%|█████████▌| 11428/11952 [3:48:52<52:00, 5.96s/it] {'loss': 0.4853, 'learning_rate': 1.006493049070889e-07, 'epoch': 0.96} + 96%|█████████▌| 11428/11952 [3:48:52<52:00, 5.96s/it] 96%|█████████▌| 11429/11952 [3:48:58<52:41, 6.05s/it] {'loss': 0.4559, 'learning_rate': 1.002661564639995e-07, 'epoch': 0.96} + 96%|█████████▌| 11429/11952 [3:48:59<52:41, 6.05s/it] 96%|█████████▌| 11430/11952 [3:49:04<51:58, 5.98s/it] {'loss': 0.4535, 'learning_rate': 9.988373501618631e-08, 'epoch': 0.96} + 96%|█████████▌| 11430/11952 [3:49:04<51:58, 5.98s/it] 96%|█████████▌| 11431/11952 [3:49:10<51:59, 5.99s/it] {'loss': 0.4537, 'learning_rate': 9.950204059173462e-08, 'epoch': 0.96} + 96%|█████████▌| 11431/11952 [3:49:10<51:59, 5.99s/it] 96%|█████████▌| 11432/11952 [3:49:17<52:34, 6.07s/it] {'loss': 0.462, 'learning_rate': 9.912107321867315e-08, 'epoch': 0.96} + 96%|█████████▌| 11432/11952 [3:49:17<52:34, 6.07s/it] 96%|█████████▌| 11433/11952 [3:49:22<51:37, 5.97s/it] {'loss': 0.4469, 'learning_rate': 9.87408329249795e-08, 'epoch': 0.96} + 96%|█████████▌| 11433/11952 [3:49:22<51:37, 5.97s/it] 96%|█████████▌| 11434/11952 [3:49:28<51:18, 5.94s/it] {'loss': 0.4602, 'learning_rate': 9.836131973857687e-08, 'epoch': 0.96} + 96%|█████████▌| 11434/11952 [3:49:28<51:18, 5.94s/it] 96%|█████████▌| 11435/11952 [3:49:34<51:42, 6.00s/it] {'loss': 0.4734, 'learning_rate': 9.798253368733523e-08, 'epoch': 0.96} + 96%|█████████▌| 11435/11952 [3:49:34<51:42, 6.00s/it] 96%|█████████▌| 11436/11952 [3:49:40<50:57, 5.92s/it] {'loss': 0.4662, 'learning_rate': 9.76044747990701e-08, 'epoch': 0.96} + 96%|█████████▌| 11436/11952 [3:49:40<50:57, 5.92s/it] 96%|█████████▌| 11437/11952 [3:49:46<50:34, 5.89s/it] {'loss': 0.4702, 'learning_rate': 9.722714310154591e-08, 'epoch': 0.96} + 96%|█████████▌| 11437/11952 [3:49:46<50:34, 5.89s/it] 96%|█████████▌| 11438/11952 [3:49:52<50:28, 5.89s/it] {'loss': 0.4542, 'learning_rate': 9.685053862247051e-08, 'epoch': 0.96} + 96%|█████████▌| 11438/11952 [3:49:52<50:28, 5.89s/it] 96%|█████████▌| 11439/11952 [3:49:58<50:22, 5.89s/it] {'loss': 0.4661, 'learning_rate': 9.647466138950178e-08, 'epoch': 0.96} + 96%|█████████▌| 11439/11952 [3:49:58<50:22, 5.89s/it] 96%|█████████▌| 11440/11952 [3:50:04<50:50, 5.96s/it] {'loss': 0.4739, 'learning_rate': 9.60995114302421e-08, 'epoch': 0.96} + 96%|█████████▌| 11440/11952 [3:50:04<50:50, 5.96s/it] 96%|█████████▌| 11441/11952 [3:50:10<51:17, 6.02s/it] {'loss': 0.4406, 'learning_rate': 9.572508877224163e-08, 'epoch': 0.96} + 96%|█████████▌| 11441/11952 [3:50:10<51:17, 6.02s/it] 96%|█████████▌| 11442/11952 [3:50:16<50:24, 5.93s/it] {'loss': 0.4697, 'learning_rate': 9.535139344299393e-08, 'epoch': 0.96} + 96%|█████████▌| 11442/11952 [3:50:16<50:24, 5.93s/it] 96%|█████████▌| 11443/11952 [3:50:21<49:59, 5.89s/it] {'loss': 0.4764, 'learning_rate': 9.497842546994485e-08, 'epoch': 0.96} + 96%|█████████▌| 11443/11952 [3:50:21<49:59, 5.89s/it] 96%|█████████▌| 11444/11952 [3:50:27<49:12, 5.81s/it] {'loss': 0.4497, 'learning_rate': 9.460618488048024e-08, 'epoch': 0.96} + 96%|█████████▌| 11444/11952 [3:50:27<49:12, 5.81s/it] 96%|█████████▌| 11445/11952 [3:50:33<50:20, 5.96s/it] {'loss': 0.4531, 'learning_rate': 9.423467170193933e-08, 'epoch': 0.96} + 96%|█████████▌| 11445/11952 [3:50:33<50:20, 5.96s/it] 96%|█████████▌| 11446/11952 [3:50:39<49:27, 5.86s/it] {'loss': 0.4582, 'learning_rate': 9.386388596160367e-08, 'epoch': 0.96} + 96%|█████████▌| 11446/11952 [3:50:39<49:27, 5.86s/it] 96%|█████████▌| 11447/11952 [3:50:45<49:37, 5.90s/it] {'loss': 0.4613, 'learning_rate': 9.349382768670034e-08, 'epoch': 0.96} + 96%|█████████▌| 11447/11952 [3:50:45<49:37, 5.90s/it] 96%|█████████▌| 11448/11952 [3:50:51<49:00, 5.83s/it] {'loss': 0.4622, 'learning_rate': 9.31244969044065e-08, 'epoch': 0.96} + 96%|█████████▌| 11448/11952 [3:50:51<49:00, 5.83s/it] 96%|█████████▌| 11449/11952 [3:50:57<49:03, 5.85s/it] {'loss': 0.4951, 'learning_rate': 9.275589364184379e-08, 'epoch': 0.96} + 96%|█████████▌| 11449/11952 [3:50:57<49:03, 5.85s/it]5 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... +04 AutoResumeHook: Checking whether to suspend... + AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... + 96%|█████████▌| 11450/11952 [3:51:03<49:15, 5.89s/it]1 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4514, 'learning_rate': 9.238801792608054e-08, 'epoch': 0.96} + 96%|█████████▌| 11450/11952 [3:51:03<49:15, 5.89s/it] 96%|█████████▌| 11451/11952 [3:51:09<49:23, 5.92s/it] {'loss': 0.4673, 'learning_rate': 9.202086978413294e-08, 'epoch': 0.96} + 96%|█████████▌| 11451/11952 [3:51:09<49:23, 5.92s/it] 96%|█████████▌| 11452/11952 [3:51:15<49:32, 5.94s/it] {'loss': 0.4674, 'learning_rate': 9.165444924296163e-08, 'epoch': 0.96} + 96%|█████████▌| 11452/11952 [3:51:15<49:32, 5.94s/it] 96%|█████████▌| 11453/11952 [3:51:20<49:02, 5.90s/it] {'loss': 0.462, 'learning_rate': 9.12887563294751e-08, 'epoch': 0.96} + 96%|█████████▌| 11453/11952 [3:51:20<49:02, 5.90s/it] 96%|█████████▌| 11454/11952 [3:51:26<48:35, 5.85s/it] {'loss': 0.4548, 'learning_rate': 9.092379107053074e-08, 'epoch': 0.96} + 96%|█████████▌| 11454/11952 [3:51:26<48:35, 5.85s/it] 96%|█████████▌| 11455/11952 [3:51:32<49:18, 5.95s/it] {'loss': 0.4618, 'learning_rate': 9.055955349292711e-08, 'epoch': 0.96} + 96%|█████████▌| 11455/11952 [3:51:32<49:18, 5.95s/it] 96%|█████████▌| 11456/11952 [3:51:38<49:26, 5.98s/it] {'loss': 0.4822, 'learning_rate': 9.019604362341394e-08, 'epoch': 0.96} + 96%|█████████▌| 11456/11952 [3:51:38<49:26, 5.98s/it] 96%|█████████▌| 11457/11952 [3:51:45<49:49, 6.04s/it] {'loss': 0.4545, 'learning_rate': 8.983326148868432e-08, 'epoch': 0.96} + 96%|█████████▌| 11457/11952 [3:51:45<49:49, 6.04s/it] 96%|█████████▌| 11458/11952 [3:51:50<49:23, 6.00s/it] {'loss': 0.4525, 'learning_rate': 8.947120711538138e-08, 'epoch': 0.96} + 96%|█████████▌| 11458/11952 [3:51:50<49:23, 6.00s/it] 96%|█████████▌| 11459/11952 [3:51:56<49:15, 5.99s/it] {'loss': 0.462, 'learning_rate': 8.910988053009162e-08, 'epoch': 0.96} + 96%|█████████▌| 11459/11952 [3:51:56<49:15, 5.99s/it] 96%|█████████▌| 11460/11952 [3:52:02<48:03, 5.86s/it] {'loss': 0.4336, 'learning_rate': 8.874928175934938e-08, 'epoch': 0.96} + 96%|█████████▌| 11460/11952 [3:52:02<48:03, 5.86s/it] 96%|█████████▌| 11461/11952 [3:52:08<47:52, 5.85s/it] {'loss': 0.4565, 'learning_rate': 8.838941082963681e-08, 'epoch': 0.96} + 96%|█████████▌| 11461/11952 [3:52:08<47:52, 5.85s/it] 96%|█████████▌| 11462/11952 [3:52:14<47:47, 5.85s/it] {'loss': 0.4647, 'learning_rate': 8.803026776738055e-08, 'epoch': 0.96} + 96%|█████████▌| 11462/11952 [3:52:14<47:47, 5.85s/it] 96%|█████████▌| 11463/11952 [3:52:19<47:25, 5.82s/it] {'loss': 0.4468, 'learning_rate': 8.767185259895284e-08, 'epoch': 0.96} + 96%|█████████▌| 11463/11952 [3:52:19<47:25, 5.82s/it] 96%|█████████▌| 11464/11952 [3:52:26<48:09, 5.92s/it] {'loss': 0.4473, 'learning_rate': 8.731416535067705e-08, 'epoch': 0.96} + 96%|█████████▌| 11464/11952 [3:52:26<48:09, 5.92s/it] 96%|█████████▌| 11465/11952 [3:52:31<47:16, 5.83s/it] {'loss': 0.4576, 'learning_rate': 8.695720604881886e-08, 'epoch': 0.96} + 96%|█████████▌| 11465/11952 [3:52:31<47:16, 5.83s/it] 96%|█████████▌| 11466/11952 [3:52:37<47:42, 5.89s/it] {'loss': 0.4786, 'learning_rate': 8.660097471959173e-08, 'epoch': 0.96} + 96%|█████████▌| 11466/11952 [3:52:37<47:42, 5.89s/it] 96%|█████████▌| 11467/11952 [3:52:44<48:48, 6.04s/it] {'loss': 0.4623, 'learning_rate': 8.624547138915696e-08, 'epoch': 0.96} + 96%|█████████▌| 11467/11952 [3:52:44<48:48, 6.04s/it] 96%|█████████▌| 11468/11952 [3:52:50<48:33, 6.02s/it] {'loss': 0.4606, 'learning_rate': 8.589069608361922e-08, 'epoch': 0.96} + 96%|█████████▌| 11468/11952 [3:52:50<48:33, 6.02s/it] 96%|█████████▌| 11469/11952 [3:52:55<47:51, 5.95s/it] {'loss': 0.4581, 'learning_rate': 8.553664882903323e-08, 'epoch': 0.96} + 96%|█████████▌| 11469/11952 [3:52:55<47:51, 5.95s/it] 96%|█████████▌| 11470/11952 [3:53:01<47:38, 5.93s/it] {'loss': 0.4398, 'learning_rate': 8.518332965139931e-08, 'epoch': 0.96} + 96%|█████████▌| 11470/11952 [3:53:01<47:38, 5.93s/it] 96%|█████████▌| 11471/11952 [3:53:08<48:34, 6.06s/it] {'loss': 0.4641, 'learning_rate': 8.483073857666224e-08, 'epoch': 0.96} + 96%|█████████▌| 11471/11952 [3:53:08<48:34, 6.06s/it] 96%|█████████▌| 11472/11952 [3:53:13<48:00, 6.00s/it] {'loss': 0.4707, 'learning_rate': 8.447887563071466e-08, 'epoch': 0.96} + 96%|█████████▌| 11472/11952 [3:53:13<48:00, 6.00s/it] 96%|█████████▌| 11473/11952 [3:53:20<48:17, 6.05s/it] {'loss': 0.4626, 'learning_rate': 8.4127740839397e-08, 'epoch': 0.96} + 96%|█████████▌| 11473/11952 [3:53:20<48:17, 6.05s/it] 96%|█████████▌| 11474/11952 [3:53:26<47:59, 6.02s/it] {'loss': 0.4563, 'learning_rate': 8.377733422849532e-08, 'epoch': 0.96} + 96%|█████████▌| 11474/11952 [3:53:26<47:59, 6.02s/it] 96%|█████████▌| 11475/11952 [3:53:31<47:01, 5.92s/it] {'loss': 0.4642, 'learning_rate': 8.342765582374124e-08, 'epoch': 0.96} + 96%|█████████▌| 11475/11952 [3:53:31<47:01, 5.92s/it] 96%|█████████▌| 11476/11952 [3:53:37<46:16, 5.83s/it] {'loss': 0.4385, 'learning_rate': 8.307870565081422e-08, 'epoch': 0.96} + 96%|█████████▌| 11476/11952 [3:53:37<46:16, 5.83s/it] 96%|█████████▌| 11477/11952 [3:53:43<46:24, 5.86s/it] {'loss': 0.4736, 'learning_rate': 8.273048373533932e-08, 'epoch': 0.96} + 96%|█████████▌| 11477/11952 [3:53:43<46:24, 5.86s/it] 96%|█████████▌| 11478/11952 [3:53:49<46:37, 5.90s/it] {'loss': 0.45, 'learning_rate': 8.23829901028883e-08, 'epoch': 0.96} + 96%|█████████▌| 11478/11952 [3:53:49<46:37, 5.90s/it] 96%|█████████▌| 11479/11952 [3:53:55<46:26, 5.89s/it] {'loss': 0.4565, 'learning_rate': 8.203622477898077e-08, 'epoch': 0.96} + 96%|█████████▌| 11479/11952 [3:53:55<46:26, 5.89s/it] 96%|█████████▌| 11480/11952 [3:54:00<46:11, 5.87s/it] {'loss': 0.4609, 'learning_rate': 8.169018778908078e-08, 'epoch': 0.96} + 96%|█████████▌| 11480/11952 [3:54:00<46:11, 5.87s/it] 96%|█████████▌| 11481/11952 [3:54:06<46:08, 5.88s/it] {'loss': 0.4565, 'learning_rate': 8.134487915860024e-08, 'epoch': 0.96} + 96%|█████████▌| 11481/11952 [3:54:06<46:08, 5.88s/it] 96%|█████████▌| 11482/11952 [3:54:12<46:28, 5.93s/it] {'loss': 0.4625, 'learning_rate': 8.100029891289662e-08, 'epoch': 0.96} + 96%|█████████▌| 11482/11952 [3:54:12<46:28, 5.93s/it] 96%|█████████▌| 11483/11952 [3:54:18<46:11, 5.91s/it] {'loss': 0.4632, 'learning_rate': 8.065644707727415e-08, 'epoch': 0.96} + 96%|█████████▌| 11483/11952 [3:54:18<46:11, 5.91s/it] 96%|█████████▌| 11484/11952 [3:54:24<45:33, 5.84s/it] {'loss': 0.4644, 'learning_rate': 8.031332367698486e-08, 'epoch': 0.96} + 96%|█████████▌| 11484/11952 [3:54:24<45:33, 5.84s/it] 96%|█████████▌| 11485/11952 [3:54:30<45:26, 5.84s/it] {'loss': 0.4493, 'learning_rate': 7.997092873722633e-08, 'epoch': 0.96} + 96%|█████████▌| 11485/11952 [3:54:30<45:26, 5.84s/it] 96%|█████████▌| 11486/11952 [3:54:36<45:36, 5.87s/it] {'loss': 0.4484, 'learning_rate': 7.962926228314293e-08, 'epoch': 0.96} + 96%|█████████▌| 11486/11952 [3:54:36<45:36, 5.87s/it] 96%|█████████▌| 11487/11952 [3:54:41<44:43, 5.77s/it] {'loss': 0.4623, 'learning_rate': 7.928832433982348e-08, 'epoch': 0.96} + 96%|█████████▌| 11487/11952 [3:54:41<44:43, 5.77s/it] 96%|█████████▌| 11488/11952 [3:54:47<44:41, 5.78s/it] {'loss': 0.4518, 'learning_rate': 7.89481149323068e-08, 'epoch': 0.96} + 96%|█████████▌| 11488/11952 [3:54:47<44:41, 5.78s/it] 96%|█████████▌| 11489/11952 [3:54:53<44:12, 5.73s/it] {'loss': 0.4552, 'learning_rate': 7.860863408557629e-08, 'epoch': 0.96} + 96%|█████████▌| 11489/11952 [3:54:53<44:12, 5.73s/it] 96%|█████████▌| 11490/11952 [3:54:58<44:08, 5.73s/it] {'loss': 0.4685, 'learning_rate': 7.826988182456086e-08, 'epoch': 0.96} + 96%|█████████▌| 11490/11952 [3:54:58<44:08, 5.73s/it] 96%|█████████▌| 11491/11952 [3:55:04<43:49, 5.70s/it] {'loss': 0.4479, 'learning_rate': 7.793185817413728e-08, 'epoch': 0.96} + 96%|█████████▌| 11491/11952 [3:55:04<43:49, 5.70s/it] 96%|█████████▌| 11492/11952 [3:55:10<44:00, 5.74s/it] {'loss': 0.478, 'learning_rate': 7.759456315912905e-08, 'epoch': 0.96} + 96%|█████████▌| 11492/11952 [3:55:10<44:00, 5.74s/it] 96%|█████████▌| 11493/11952 [3:55:16<44:44, 5.85s/it] {'loss': 0.4773, 'learning_rate': 7.725799680430634e-08, 'epoch': 0.96} + 96%|█████████▌| 11493/11952 [3:55:16<44:44, 5.85s/it] 96%|█████████▌| 11494/11952 [3:55:22<44:03, 5.77s/it] {'loss': 0.4452, 'learning_rate': 7.692215913438383e-08, 'epoch': 0.96} + 96%|█████████▌| 11494/11952 [3:55:22<44:03, 5.77s/it] 96%|█████████▌| 11495/11952 [3:55:28<44:49, 5.89s/it] {'loss': 0.4524, 'learning_rate': 7.658705017402623e-08, 'epoch': 0.96} + 96%|█████████▌| 11495/11952 [3:55:28<44:49, 5.89s/it] 96%|█████████▌| 11496/11952 [3:55:34<44:38, 5.87s/it] {'loss': 0.4712, 'learning_rate': 7.625266994784053e-08, 'epoch': 0.96} + 96%|█████████▌| 11496/11952 [3:55:34<44:38, 5.87s/it] 96%|█████████▌| 11497/11952 [3:55:39<44:36, 5.88s/it] {'loss': 0.4557, 'learning_rate': 7.591901848038263e-08, 'epoch': 0.96} + 96%|█████████▌| 11497/11952 [3:55:40<44:36, 5.88s/it] 96%|█████████▌| 11498/11952 [3:55:46<44:54, 5.94s/it] {'loss': 0.4618, 'learning_rate': 7.558609579615406e-08, 'epoch': 0.96} + 96%|█████████▌| 11498/11952 [3:55:46<44:54, 5.94s/it] 96%|█████████▌| 11499/11952 [3:55:51<44:16, 5.87s/it] {'loss': 0.4687, 'learning_rate': 7.525390191960413e-08, 'epoch': 0.96} + 96%|█████████▌| 11499/11952 [3:55:51<44:16, 5.87s/it]7 AutoResumeHook: Checking whether to suspend... +25 AutoResumeHook: Checking whether to suspend...AutoResumeHook: Checking whether to suspend... +0 + AutoResumeHook: Checking whether to suspend... +4 AutoResumeHook: Checking whether to suspend... + 96%|█████████▌| 11500/11952 [3:55:57<44:22, 5.89s/it]3 AutoResumeHook: Checking whether to suspend... +1 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4418, 'learning_rate': 7.49224368751278e-08, 'epoch': 0.96} + 96%|█████████▌| 11500/11952 [3:55:57<44:22, 5.89s/it]saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-11500/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/tmp-checkpoint-11500/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/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( + 96%|█████████▌| 11501/11952 [3:56:27<1:38:34, 13.11s/it] {'loss': 0.4609, 'learning_rate': 7.459170068706555e-08, 'epoch': 0.96} + 96%|█████████▌| 11501/11952 [3:56:27<1:38:34, 13.11s/it] 96%|█████████▌| 11502/11952 [3:56:33<1:21:44, 10.90s/it] {'loss': 0.4725, 'learning_rate': 7.42616933797069e-08, 'epoch': 0.96} + 96%|█████████▌| 11502/11952 [3:56:33<1:21:44, 10.90s/it] 96%|█████████▌| 11503/11952 [3:56:39<1:10:54, 9.48s/it] {'loss': 0.4742, 'learning_rate': 7.393241497728465e-08, 'epoch': 0.96} + 96%|█████████▌| 11503/11952 [3:56:39<1:10:54, 9.48s/it] 96%|█████████▋| 11504/11952 [3:56:45<1:02:36, 8.39s/it] {'loss': 0.479, 'learning_rate': 7.360386550398058e-08, 'epoch': 0.96} + 96%|█████████▋| 11504/11952 [3:56:45<1:02:36, 8.39s/it] 96%|█████████▋| 11505/11952 [3:56:51<56:36, 7.60s/it] {'loss': 0.4734, 'learning_rate': 7.327604498392094e-08, 'epoch': 0.96} + 96%|█████████▋| 11505/11952 [3:56:51<56:36, 7.60s/it] 96%|█████████▋| 11506/11952 [3:56:56<52:08, 7.01s/it] {'loss': 0.4444, 'learning_rate': 7.294895344118091e-08, 'epoch': 0.96} + 96%|█████████▋| 11506/11952 [3:56:56<52:08, 7.01s/it] 96%|█████████▋| 11507/11952 [3:57:02<49:43, 6.70s/it] {'loss': 0.4477, 'learning_rate': 7.262259089977907e-08, 'epoch': 0.96} + 96%|█████████▋| 11507/11952 [3:57:02<49:43, 6.70s/it] 96%|█████████▋| 11508/11952 [3:57:08<47:59, 6.48s/it] {'loss': 0.493, 'learning_rate': 7.229695738368403e-08, 'epoch': 0.96} + 96%|█████████▋| 11508/11952 [3:57:08<47:59, 6.48s/it] 96%|█████████▋| 11509/11952 [3:57:14<46:13, 6.26s/it] {'loss': 0.4547, 'learning_rate': 7.197205291680887e-08, 'epoch': 0.96} + 96%|█████████▋| 11509/11952 [3:57:14<46:13, 6.26s/it] 96%|█████████▋| 11510/11952 [3:57:20<45:21, 6.16s/it] {'loss': 0.4579, 'learning_rate': 7.164787752301117e-08, 'epoch': 0.96} + 96%|█████████▋| 11510/11952 [3:57:20<45:21, 6.16s/it] 96%|█████████▋| 11511/11952 [3:57:26<45:00, 6.12s/it] {'loss': 0.477, 'learning_rate': 7.132443122609856e-08, 'epoch': 0.96} + 96%|█████████▋| 11511/11952 [3:57:26<45:00, 6.12s/it] 96%|█████████▋| 11512/11952 [3:57:32<44:19, 6.04s/it] {'loss': 0.4626, 'learning_rate': 7.100171404982315e-08, 'epoch': 0.96} + 96%|█████████▋| 11512/11952 [3:57:32<44:19, 6.04s/it] 96%|█████████▋| 11513/11952 [3:57:38<43:29, 5.94s/it] {'loss': 0.4527, 'learning_rate': 7.067972601788376e-08, 'epoch': 0.96} + 96%|█████████▋| 11513/11952 [3:57:38<43:29, 5.94s/it]srun: Job step aborted: Waiting up to 122 seconds for job step to finish. +Jun 11 04:45:04.377618 2168900 slurmstepd 0x155550a06700: error: *** STEP 8846993.0 ON batch-block1-0082 CANCELLED AT 2025-06-11T04:45:04 DUE TO TIME LIMIT *** +srun: error: batch-block1-0082: task 0: Terminated +srun: Terminating StepId=8846993.0 +srun: job 8851917 queued and waiting for resources +srun: job 8857770 queued and waiting for resources +srun: job 8857770 has been allocated resources +wandb: Currently logged in as: memmelma. Use `wandb login --relogin` to force relogin +MASTER_ADDR=batch-block7-00972 +JobID: 8857770 | Full list: batch-block7-00972 +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! +[2025-06-11 14:27:07,290] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-11 14:27:07,290] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-11 14:27:07,290] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-11 14:27:07,290] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-11 14:27:07,290] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-11 14:27:07,290] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-11 14:27:07,290] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-11 14:27:07,290] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-11 14:27:08,465] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-11 14:27:08,465] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-11 14:27:08,465] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-11 14:27:08,465] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-11 14:27:08,465] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-11 14:27:08,465] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-11 14:27:08,465] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-11 14:27:08,465] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-11 14:27:08,465] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-11 14:27:08,465] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-11 14:27:08,465] [INFO] [comm.py:625:init_distributed] Initializing TorchBackend in DeepSpeed with backend nccl +[2025-06-11 14:27:08,465] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-11 14:27:08,465] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-11 14:27:08,465] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-11 14:27:08,465] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-11 14:27:08,465] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-11 14:27:08,465] [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')`. +[2025-06-11 14:27:17,421] [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%|█████████▉| 11906/11952 [41:14<05:23, 7.04s/it] {'loss': 0.4658, 'learning_rate': 7.769411383906633e-10, 'epoch': 1.0} + 100%|█████████▉| 11906/11952 [41:14<05:23, 7.04s/it] 100%|█████████▉| 11907/11952 [41:19<04:59, 6.65s/it] {'loss': 0.4539, 'learning_rate': 7.435286774104545e-10, 'epoch': 1.0} + 100%|█████████▉| 11907/11952 [41:19<04:59, 6.65s/it] 100%|█████████▉| 11908/11952 [41:25<04:40, 6.36s/it] {'loss': 0.4592, 'learning_rate': 7.108505202346739e-10, 'epoch': 1.0} + 100%|█████████▉| 11908/11952 [41:25<04:40, 6.36s/it] 100%|█████████▉| 11909/11952 [41:31<04:24, 6.16s/it] {'loss': 0.442, 'learning_rate': 6.789066692636237e-10, 'epoch': 1.0} + 100%|█████████▉| 11909/11952 [41:31<04:24, 6.16s/it] 100%|█████████▉| 11910/11952 [41:36<04:11, 5.99s/it] {'loss': 0.4526, 'learning_rate': 6.476971268443156e-10, 'epoch': 1.0} + 100%|█████████▉| 11910/11952 [41:36<04:11, 5.99s/it] 100%|█████████▉| 11911/11952 [41:42<04:06, 6.02s/it] {'loss': 0.4614, 'learning_rate': 6.172218952671394e-10, 'epoch': 1.0} + 100%|█████████▉| 11911/11952 [41:42<04:06, 6.02s/it] 100%|█████████▉| 11912/11952 [41:48<04:01, 6.03s/it] {'loss': 0.449, 'learning_rate': 5.874809767703049e-10, 'epoch': 1.0} + 100%|█████████▉| 11912/11952 [41:48<04:01, 6.03s/it] 100%|█████████▉| 11913/11952 [41:54<03:49, 5.89s/it] {'loss': 0.4503, 'learning_rate': 5.58474373538731e-10, 'epoch': 1.0} + 100%|█████████▉| 11913/11952 [41:54<03:49, 5.89s/it] 100%|█████████▉| 11914/11952 [42:00<03:40, 5.80s/it] {'loss': 0.4608, 'learning_rate': 5.302020877018255e-10, 'epoch': 1.0} + 100%|█████████▉| 11914/11952 [42:00<03:40, 5.80s/it] 100%|█████████▉| 11915/11952 [42:05<03:31, 5.71s/it] {'loss': 0.4489, 'learning_rate': 5.026641213357054e-10, 'epoch': 1.0} + 100%|█████████▉| 11915/11952 [42:05<03:31, 5.71s/it] 100%|█████████▉| 11916/11952 [42:11<03:24, 5.69s/it] {'loss': 0.4484, 'learning_rate': 4.758604764631969e-10, 'epoch': 1.0} + 100%|█████████▉| 11916/11952 [42:11<03:24, 5.69s/it] 100%|█████████▉| 11917/11952 [42:16<03:18, 5.67s/it] {'loss': 0.4652, 'learning_rate': 4.4979115505272566e-10, 'epoch': 1.0} + 100%|█████████▉| 11917/11952 [42:16<03:18, 5.67s/it] 100%|█████████▉| 11918/11952 [42:22<03:14, 5.73s/it] {'loss': 0.4656, 'learning_rate': 4.2445615901831607e-10, 'epoch': 1.0} + 100%|█████████▉| 11918/11952 [42:22<03:14, 5.73s/it] 100%|█████████▉| 11919/11952 [42:28<03:11, 5.80s/it] {'loss': 0.4683, 'learning_rate': 3.998554902195917e-10, 'epoch': 1.0} + 100%|█████████▉| 11919/11952 [42:28<03:11, 5.80s/it] 100%|█████████▉| 11920/11952 [42:34<03:04, 5.77s/it] {'loss': 0.4503, 'learning_rate': 3.7598915046510587e-10, 'epoch': 1.0} + 100%|█████████▉| 11920/11952 [42:34<03:04, 5.77s/it] 100%|█████████▉| 11921/11952 [42:40<02:59, 5.78s/it] {'loss': 0.489, 'learning_rate': 3.528571415056803e-10, 'epoch': 1.0} + 100%|█████████▉| 11921/11952 [42:40<02:59, 5.78s/it] 100%|█████████▉| 11922/11952 [42:45<02:52, 5.74s/it] {'loss': 0.4592, 'learning_rate': 3.304594650410664e-10, 'epoch': 1.0} + 100%|█████████▉| 11922/11952 [42:45<02:52, 5.74s/it]/lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/VILA/llava/model/llava_arch.py:397: UserWarning: Inputs truncated! + warnings.warn("Inputs truncated!") + 100%|█████████▉| 11923/11952 [42:51<02:48, 5.80s/it] {'loss': 0.4751, 'learning_rate': 3.0879612271550454e-10, 'epoch': 1.0} + 100%|█████████▉| 11923/11952 [42:51<02:48, 5.80s/it] 100%|█████████▉| 11924/11952 [42:57<02:41, 5.78s/it] {'loss': 0.466, 'learning_rate': 2.878671161199442e-10, 'epoch': 1.0} + 100%|█████████▉| 11924/11952 [42:57<02:41, 5.78s/it] 100%|█████████▉| 11925/11952 [43:03<02:34, 5.74s/it] {'loss': 0.45, 'learning_rate': 2.676724467920444e-10, 'epoch': 1.0} + 100%|█████████▉| 11925/11952 [43:03<02:34, 5.74s/it] 100%|█████████▉| 11926/11952 [43:09<02:30, 5.80s/it] {'loss': 0.4598, 'learning_rate': 2.482121162139528e-10, 'epoch': 1.0} + 100%|█████████▉| 11926/11952 [43:09<02:30, 5.80s/it] 100%|█████████▉| 11927/11952 [43:15<02:27, 5.89s/it] {'loss': 0.505, 'learning_rate': 2.2948612581452646e-10, 'epoch': 1.0} + 100%|█████████▉| 11927/11952 [43:15<02:27, 5.89s/it] 100%|█████████▉| 11928/11952 [43:21<02:22, 5.94s/it] {'loss': 0.4551, 'learning_rate': 2.114944769704419e-10, 'epoch': 1.0} + 100%|█████████▉| 11928/11952 [43:21<02:22, 5.94s/it] 100%|█████████▉| 11929/11952 [43:26<02:14, 5.86s/it] {'loss': 0.4501, 'learning_rate': 1.9423717100175432e-10, 'epoch': 1.0} + 100%|█████████▉| 11929/11952 [43:26<02:14, 5.86s/it] 100%|█████████▉| 11930/11952 [43:32<02:08, 5.86s/it] {'loss': 0.4932, 'learning_rate': 1.777142091752282e-10, 'epoch': 1.0} + 100%|█████████▉| 11930/11952 [43:32<02:08, 5.86s/it] 100%|█████████▉| 11931/11952 [43:38<02:01, 5.79s/it] {'loss': 0.455, 'learning_rate': 1.619255927054475e-10, 'epoch': 1.0} + 100%|█████████▉| 11931/11952 [43:38<02:01, 5.79s/it] 100%|█████████▉| 11932/11952 [43:43<01:54, 5.74s/it] {'loss': 0.4599, 'learning_rate': 1.468713227514851e-10, 'epoch': 1.0} + 100%|█████████▉| 11932/11952 [43:43<01:54, 5.74s/it] 100%|█████████▉| 11933/11952 [43:49<01:49, 5.76s/it] {'loss': 0.4578, 'learning_rate': 1.3255140041912306e-10, 'epoch': 1.0} + 100%|█████████▉| 11933/11952 [43:49<01:49, 5.76s/it] 100%|█████████▉| 11934/11952 [43:55<01:44, 5.81s/it] {'loss': 0.4442, 'learning_rate': 1.1896582675974266e-10, 'epoch': 1.0} + 100%|█████████▉| 11934/11952 [43:55<01:44, 5.81s/it] 100%|█████████▉| 11935/11952 [44:01<01:40, 5.89s/it] {'loss': 0.464, 'learning_rate': 1.0611460277032415e-10, 'epoch': 1.0} + 100%|█████████▉| 11935/11952 [44:01<01:40, 5.89s/it] 100%|█████████▉| 11936/11952 [44:07<01:33, 5.86s/it] {'loss': 0.4523, 'learning_rate': 9.399772939455709e-11, 'epoch': 1.0} + 100%|█████████▉| 11936/11952 [44:07<01:33, 5.86s/it] 100%|█████████▉| 11937/11952 [44:13<01:27, 5.83s/it] {'loss': 0.4593, 'learning_rate': 8.261520752395059e-11, 'epoch': 1.0} + 100%|█████████▉| 11937/11952 [44:13<01:27, 5.83s/it] 100%|█████████▉| 11938/11952 [44:19<01:21, 5.81s/it] {'loss': 0.4764, 'learning_rate': 7.19670379922821e-11, 'epoch': 1.0} + 100%|█████████▉| 11938/11952 [44:19<01:21, 5.81s/it] 100%|█████████▉| 11939/11952 [44:24<01:15, 5.82s/it] {'loss': 0.4706, 'learning_rate': 6.205322158336913e-11, 'epoch': 1.0} + 100%|█████████▉| 11939/11952 [44:24<01:15, 5.82s/it] 100%|█████████▉| 11940/11952 [44:30<01:10, 5.84s/it] {'loss': 0.4774, 'learning_rate': 5.287375902440772e-11, 'epoch': 1.0} + 100%|█████████▉| 11940/11952 [44:30<01:10, 5.84s/it] 100%|█████████▉| 11941/11952 [44:36<01:03, 5.73s/it] {'loss': 0.4738, 'learning_rate': 4.442865098930327e-11, 'epoch': 1.0} + 100%|█████████▉| 11941/11952 [44:36<01:03, 5.73s/it] 100%|█████████▉| 11942/11952 [44:41<00:57, 5.72s/it] {'loss': 0.4651, 'learning_rate': 3.671789809867043e-11, 'epoch': 1.0} + 100%|█████████▉| 11942/11952 [44:41<00:57, 5.72s/it] 100%|█████████▉| 11943/11952 [44:48<00:52, 5.82s/it] {'loss': 0.474, 'learning_rate': 2.974150091761274e-11, 'epoch': 1.0} + 100%|█████████▉| 11943/11952 [44:48<00:52, 5.82s/it] 100%|█████████▉| 11944/11952 [44:53<00:46, 5.84s/it] {'loss': 0.4763, 'learning_rate': 2.349945996016345e-11, 'epoch': 1.0} + 100%|█████████▉| 11944/11952 [44:53<00:46, 5.84s/it] 100%|█████████▉| 11945/11952 [44:59<00:40, 5.81s/it] {'loss': 0.457, 'learning_rate': 1.7991775683734448e-11, 'epoch': 1.0} + 100%|█████████▉| 11945/11952 [44:59<00:40, 5.81s/it] 100%|█████████▉| 11946/11952 [45:05<00:34, 5.76s/it] {'loss': 0.466, 'learning_rate': 1.3218448492446912e-11, 'epoch': 1.0} + 100%|█████████▉| 11946/11952 [45:05<00:34, 5.76s/it] 100%|█████████▉| 11947/11952 [45:10<00:28, 5.71s/it] {'loss': 0.45, 'learning_rate': 9.179478738241542e-12, 'epoch': 1.0} + 100%|█████████▉| 11947/11952 [45:10<00:28, 5.71s/it] 100%|█████████▉| 11948/11952 [45:16<00:22, 5.66s/it] {'loss': 0.4781, 'learning_rate': 5.874866715327443e-12, 'epoch': 1.0} + 100%|█████████▉| 11948/11952 [45:16<00:22, 5.66s/it] 100%|█████████▉| 11949/11952 [45:22<00:17, 5.73s/it] {'loss': 0.4753, 'learning_rate': 3.3046126690639002e-12, 'epoch': 1.0} + 100%|█████████▉| 11949/11952 [45:22<00:17, 5.73s/it]4 AutoResumeHook: Checking whether to suspend... +3 AutoResumeHook: Checking whether to suspend... +2 AutoResumeHook: Checking whether to suspend... +5 AutoResumeHook: Checking whether to suspend... +6 AutoResumeHook: Checking whether to suspend... +0 AutoResumeHook: Checking whether to suspend... +7 AutoResumeHook: Checking whether to suspend... + 100%|█████████▉| 11950/11952 [45:28<00:11, 5.72s/it]1 AutoResumeHook: Checking whether to suspend... + {'loss': 0.4425, 'learning_rate': 1.4687167870786056e-12, 'epoch': 1.0} + 100%|█████████▉| 11950/11952 [45:28<00:11, 5.72s/it] 100%|█████████▉| 11951/11952 [45:33<00:05, 5.77s/it] {'loss': 0.4705, 'learning_rate': 3.6717920370854533e-13, 'epoch': 1.0} + 100%|█████████▉| 11951/11952 [45:33<00:05, 5.77s/it] 100%|██████████| 11952/11952 [45:40<00:00, 5.88s/it] {'loss': 0.4708, 'learning_rate': 0.0, 'epoch': 1.0} + 100%|██████████| 11952/11952 [45:40<00:00, 5.88s/it] {'train_runtime': 2743.4428, 'train_samples_per_second': 1115.374, 'train_steps_per_second': 4.357, 'train_loss': 0.017490314920663514, 'epoch': 1.0} + 100%|██████████| 11952/11952 [45:41<00:00, 5.88s/it] 100%|██████████| 11952/11952 [45:41<00:00, 4.36it/s] +saving llm to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/llm +saving vision_tower to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/vision_tower +saving mm_projector to /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask/mm_projector +wandb: 🚀 View run vila_3b_path_mask at: https://wandb.ai/memmelma/VILA/runs/nh1vjmt9 +wandb: Find logs at: ../../../../../../../../fs12/portfolios/nvr/projects/nvr_srl_simpler/users/mmemmel/projects/vila/VILA/wandb/run-20250611_142850-nh1vjmt9/logs +srun: job 8858209 queued and waiting for resources +srun: job 8858209 has been allocated resources +wandb: Currently logged in as: memmelma. Use `wandb login --relogin` to force relogin +MASTER_ADDR=batch-block5-00334 +JobID: 8858209 | Full list: batch-block5-00334 +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! +[2025-06-11 15:17:52,669] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-11 15:17:52,669] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-11 15:17:52,669] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-11 15:17:52,669] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-11 15:17:52,669] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-11 15:17:52,669] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-11 15:17:52,669] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-11 15:17:52,669] [INFO] [real_accelerator.py:110:get_accelerator] Setting ds_accelerator to cuda (auto detect) +[2025-06-11 15:17:55,260] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-11 15:17:55,260] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-11 15:17:55,259] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-11 15:17:55,260] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-11 15:17:55,260] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-11 15:17:55,260] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-11 15:17:55,260] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-11 15:17:55,260] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-11 15:17:55,260] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-11 15:17:55,260] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-11 15:17:55,260] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-11 15:17:55,260] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-11 15:17:55,260] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-11 15:17:55,260] [INFO] [comm.py:625:init_distributed] Initializing TorchBackend in DeepSpeed with backend nccl +[2025-06-11 15:17:55,260] [INFO] [comm.py:594:init_distributed] cdb=None +[2025-06-11 15:17:55,260] [WARNING] [comm.py:152:init_deepspeed_backend] NCCL backend in DeepSpeed not yet implemented +[2025-06-11 15:17:55,260] [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. Skipp training +Models has been ready under /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask. Skipp trainingModels has been ready under /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask. Skipp training + +Models has been ready under /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask. Skipp training +Models has been ready under /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask. Skipp training +Models has been ready under /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask. Skipp training +Models has been ready under /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask. Skipp training +Models has been ready under /lustre/fs12/portfolios/nvr/users/mmemmel/projects/vila/checkpoints/finetuned/vila_3b_path_mask. Skipp training diff --git a/trainer_state.json b/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..f2bef9b30825b13ed30b44195dbf26400157d28f --- /dev/null +++ b/trainer_state.json @@ -0,0 +1,71742 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 0.9999581677473331, + "eval_steps": 500, + "global_step": 11952, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0, + "learning_rate": 5.571030640668524e-08, + "loss": 0.8031, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 1.1142061281337048e-07, + "loss": 0.8071, + "step": 2 + }, + { + "epoch": 0.0, + "learning_rate": 1.6713091922005573e-07, + "loss": 0.7913, + "step": 3 + }, + { + "epoch": 0.0, + "learning_rate": 2.2284122562674096e-07, + "loss": 0.8033, + "step": 4 + }, + { + "epoch": 0.0, + "learning_rate": 2.785515320334262e-07, + "loss": 0.805, + "step": 5 + }, + { + "epoch": 0.0, + "learning_rate": 3.3426183844011146e-07, + "loss": 0.8159, + "step": 6 + }, + { + "epoch": 0.0, + "learning_rate": 3.899721448467967e-07, + "loss": 0.8095, + "step": 7 + }, + { + "epoch": 0.0, + "learning_rate": 4.456824512534819e-07, + "loss": 0.7973, + "step": 8 + }, + { + "epoch": 0.0, + "learning_rate": 5.013927576601672e-07, + "loss": 0.7913, + "step": 9 + }, + { + "epoch": 0.0, + "learning_rate": 5.571030640668524e-07, + "loss": 0.8118, + "step": 10 + }, + { + "epoch": 0.0, + "learning_rate": 6.128133704735377e-07, + "loss": 0.7926, + "step": 11 + }, + { + "epoch": 0.0, + "learning_rate": 6.685236768802229e-07, + "loss": 0.7805, + "step": 12 + }, + { + "epoch": 0.0, + "learning_rate": 7.242339832869082e-07, + "loss": 0.7913, + "step": 13 + }, + { + "epoch": 0.0, + "learning_rate": 7.799442896935934e-07, + "loss": 0.7994, + "step": 14 + }, + { + "epoch": 0.0, + "learning_rate": 8.356545961002786e-07, + "loss": 0.7979, + "step": 15 + }, + { + "epoch": 0.0, + "learning_rate": 8.913649025069638e-07, + "loss": 0.7736, + "step": 16 + }, + { + "epoch": 0.0, + "learning_rate": 9.470752089136491e-07, + "loss": 0.7817, + "step": 17 + }, + { + "epoch": 0.0, + "learning_rate": 1.0027855153203343e-06, + "loss": 0.7678, + "step": 18 + }, + { + "epoch": 0.0, + "learning_rate": 1.0584958217270195e-06, + "loss": 0.7265, + "step": 19 + }, + { + "epoch": 0.0, + "learning_rate": 1.1142061281337048e-06, + "loss": 0.7331, + "step": 20 + }, + { + "epoch": 0.0, + "learning_rate": 1.16991643454039e-06, + "loss": 0.7349, + "step": 21 + }, + { + "epoch": 0.0, + "learning_rate": 1.2256267409470754e-06, + "loss": 0.7219, + "step": 22 + }, + { + "epoch": 0.0, + "learning_rate": 1.2813370473537607e-06, + "loss": 0.7335, + "step": 23 + }, + { + "epoch": 0.0, + "learning_rate": 1.3370473537604459e-06, + "loss": 0.7127, + "step": 24 + }, + { + "epoch": 0.0, + "learning_rate": 1.392757660167131e-06, + "loss": 0.7235, + "step": 25 + }, + { + "epoch": 0.0, + "learning_rate": 1.4484679665738164e-06, + "loss": 0.6903, + "step": 26 + }, + { + "epoch": 0.0, + "learning_rate": 1.5041782729805015e-06, + "loss": 0.6748, + "step": 27 + }, + { + "epoch": 0.0, + "learning_rate": 1.5598885793871869e-06, + "loss": 0.6899, + "step": 28 + }, + { + "epoch": 0.0, + "learning_rate": 1.615598885793872e-06, + "loss": 0.6611, + "step": 29 + }, + { + "epoch": 0.0, + "learning_rate": 1.6713091922005572e-06, + "loss": 0.6656, + "step": 30 + }, + { + "epoch": 0.0, + "learning_rate": 1.7270194986072425e-06, + "loss": 0.6954, + "step": 31 + }, + { + "epoch": 0.0, + "learning_rate": 1.7827298050139277e-06, + "loss": 0.683, + "step": 32 + }, + { + "epoch": 0.0, + "learning_rate": 1.838440111420613e-06, + "loss": 0.6812, + "step": 33 + }, + { + "epoch": 0.0, + "learning_rate": 1.8941504178272982e-06, + "loss": 0.6796, + "step": 34 + }, + { + "epoch": 0.0, + "learning_rate": 1.9498607242339835e-06, + "loss": 0.6593, + "step": 35 + }, + { + "epoch": 0.0, + "learning_rate": 2.0055710306406687e-06, + "loss": 0.6622, + "step": 36 + }, + { + "epoch": 0.0, + "learning_rate": 2.061281337047354e-06, + "loss": 0.6774, + "step": 37 + }, + { + "epoch": 0.0, + "learning_rate": 2.116991643454039e-06, + "loss": 0.6606, + "step": 38 + }, + { + "epoch": 0.0, + "learning_rate": 2.1727019498607245e-06, + "loss": 0.658, + "step": 39 + }, + { + "epoch": 0.0, + "learning_rate": 2.2284122562674097e-06, + "loss": 0.6551, + "step": 40 + }, + { + "epoch": 0.0, + "learning_rate": 2.284122562674095e-06, + "loss": 0.621, + "step": 41 + }, + { + "epoch": 0.0, + "learning_rate": 2.33983286908078e-06, + "loss": 0.6396, + "step": 42 + }, + { + "epoch": 0.0, + "learning_rate": 2.395543175487465e-06, + "loss": 0.6604, + "step": 43 + }, + { + "epoch": 0.0, + "learning_rate": 2.4512534818941507e-06, + "loss": 0.6269, + "step": 44 + }, + { + "epoch": 0.0, + "learning_rate": 2.506963788300836e-06, + "loss": 0.6314, + "step": 45 + }, + { + "epoch": 0.0, + "learning_rate": 2.5626740947075214e-06, + "loss": 0.623, + "step": 46 + }, + { + "epoch": 0.0, + "learning_rate": 2.618384401114206e-06, + "loss": 0.6306, + "step": 47 + }, + { + "epoch": 0.0, + "learning_rate": 2.6740947075208917e-06, + "loss": 0.6014, + "step": 48 + }, + { + "epoch": 0.0, + "learning_rate": 2.729805013927577e-06, + "loss": 0.6312, + "step": 49 + }, + { + "epoch": 0.0, + "learning_rate": 2.785515320334262e-06, + "loss": 0.617, + "step": 50 + }, + { + "epoch": 0.0, + "learning_rate": 2.841225626740947e-06, + "loss": 0.6195, + "step": 51 + }, + { + "epoch": 0.0, + "learning_rate": 2.8969359331476327e-06, + "loss": 0.6213, + "step": 52 + }, + { + "epoch": 0.0, + "learning_rate": 2.9526462395543174e-06, + "loss": 0.6236, + "step": 53 + }, + { + "epoch": 0.0, + "learning_rate": 3.008356545961003e-06, + "loss": 0.6158, + "step": 54 + }, + { + "epoch": 0.0, + "learning_rate": 3.064066852367688e-06, + "loss": 0.5968, + "step": 55 + }, + { + "epoch": 0.0, + "learning_rate": 3.1197771587743737e-06, + "loss": 0.6257, + "step": 56 + }, + { + "epoch": 0.0, + "learning_rate": 3.1754874651810585e-06, + "loss": 0.6096, + "step": 57 + }, + { + "epoch": 0.0, + "learning_rate": 3.231197771587744e-06, + "loss": 0.6253, + "step": 58 + }, + { + "epoch": 0.0, + "learning_rate": 3.286908077994429e-06, + "loss": 0.6213, + "step": 59 + }, + { + "epoch": 0.01, + "learning_rate": 3.3426183844011143e-06, + "loss": 0.6041, + "step": 60 + }, + { + "epoch": 0.01, + "learning_rate": 3.3983286908077995e-06, + "loss": 0.6098, + "step": 61 + }, + { + "epoch": 0.01, + "learning_rate": 3.454038997214485e-06, + "loss": 0.614, + "step": 62 + }, + { + "epoch": 0.01, + "learning_rate": 3.5097493036211698e-06, + "loss": 0.6163, + "step": 63 + }, + { + "epoch": 0.01, + "learning_rate": 3.5654596100278553e-06, + "loss": 0.6006, + "step": 64 + }, + { + "epoch": 0.01, + "learning_rate": 3.6211699164345405e-06, + "loss": 0.5992, + "step": 65 + }, + { + "epoch": 0.01, + "learning_rate": 3.676880222841226e-06, + "loss": 0.6079, + "step": 66 + }, + { + "epoch": 0.01, + "learning_rate": 3.7325905292479116e-06, + "loss": 0.607, + "step": 67 + }, + { + "epoch": 0.01, + "learning_rate": 3.7883008356545963e-06, + "loss": 0.6128, + "step": 68 + }, + { + "epoch": 0.01, + "learning_rate": 3.844011142061282e-06, + "loss": 0.6046, + "step": 69 + }, + { + "epoch": 0.01, + "learning_rate": 3.899721448467967e-06, + "loss": 0.5908, + "step": 70 + }, + { + "epoch": 0.01, + "learning_rate": 3.955431754874652e-06, + "loss": 0.6016, + "step": 71 + }, + { + "epoch": 0.01, + "learning_rate": 4.011142061281337e-06, + "loss": 0.615, + "step": 72 + }, + { + "epoch": 0.01, + "learning_rate": 4.0668523676880225e-06, + "loss": 0.6117, + "step": 73 + }, + { + "epoch": 0.01, + "learning_rate": 4.122562674094708e-06, + "loss": 0.5916, + "step": 74 + }, + { + "epoch": 0.01, + "learning_rate": 4.178272980501394e-06, + "loss": 0.6005, + "step": 75 + }, + { + "epoch": 0.01, + "learning_rate": 4.233983286908078e-06, + "loss": 0.5826, + "step": 76 + }, + { + "epoch": 0.01, + "learning_rate": 4.289693593314764e-06, + "loss": 0.6087, + "step": 77 + }, + { + "epoch": 0.01, + "learning_rate": 4.345403899721449e-06, + "loss": 0.5953, + "step": 78 + }, + { + "epoch": 0.01, + "learning_rate": 4.401114206128134e-06, + "loss": 0.581, + "step": 79 + }, + { + "epoch": 0.01, + "learning_rate": 4.456824512534819e-06, + "loss": 0.5961, + "step": 80 + }, + { + "epoch": 0.01, + "learning_rate": 4.5125348189415045e-06, + "loss": 0.5837, + "step": 81 + }, + { + "epoch": 0.01, + "learning_rate": 4.56824512534819e-06, + "loss": 0.5881, + "step": 82 + }, + { + "epoch": 0.01, + "learning_rate": 4.623955431754875e-06, + "loss": 0.6076, + "step": 83 + }, + { + "epoch": 0.01, + "learning_rate": 4.67966573816156e-06, + "loss": 0.5977, + "step": 84 + }, + { + "epoch": 0.01, + "learning_rate": 4.735376044568246e-06, + "loss": 0.6113, + "step": 85 + }, + { + "epoch": 0.01, + "learning_rate": 4.79108635097493e-06, + "loss": 0.5748, + "step": 86 + }, + { + "epoch": 0.01, + "learning_rate": 4.846796657381616e-06, + "loss": 0.6021, + "step": 87 + }, + { + "epoch": 0.01, + "learning_rate": 4.902506963788301e-06, + "loss": 0.5738, + "step": 88 + }, + { + "epoch": 0.01, + "learning_rate": 4.9582172701949865e-06, + "loss": 0.5804, + "step": 89 + }, + { + "epoch": 0.01, + "learning_rate": 5.013927576601672e-06, + "loss": 0.5796, + "step": 90 + }, + { + "epoch": 0.01, + "learning_rate": 5.069637883008357e-06, + "loss": 0.591, + "step": 91 + }, + { + "epoch": 0.01, + "learning_rate": 5.125348189415043e-06, + "loss": 0.5811, + "step": 92 + }, + { + "epoch": 0.01, + "learning_rate": 5.181058495821727e-06, + "loss": 0.5667, + "step": 93 + }, + { + "epoch": 0.01, + "learning_rate": 5.236768802228412e-06, + "loss": 0.6095, + "step": 94 + }, + { + "epoch": 0.01, + "learning_rate": 5.292479108635098e-06, + "loss": 0.5935, + "step": 95 + }, + { + "epoch": 0.01, + "learning_rate": 5.3481894150417834e-06, + "loss": 0.57, + "step": 96 + }, + { + "epoch": 0.01, + "learning_rate": 5.403899721448468e-06, + "loss": 0.5865, + "step": 97 + }, + { + "epoch": 0.01, + "learning_rate": 5.459610027855154e-06, + "loss": 0.6119, + "step": 98 + }, + { + "epoch": 0.01, + "learning_rate": 5.515320334261839e-06, + "loss": 0.6189, + "step": 99 + }, + { + "epoch": 0.01, + "learning_rate": 5.571030640668524e-06, + "loss": 0.6001, + "step": 100 + }, + { + "epoch": 0.01, + "learning_rate": 5.62674094707521e-06, + "loss": 0.5787, + "step": 101 + }, + { + "epoch": 0.01, + "learning_rate": 5.682451253481894e-06, + "loss": 0.5809, + "step": 102 + }, + { + "epoch": 0.01, + "learning_rate": 5.7381615598885795e-06, + "loss": 0.5708, + "step": 103 + }, + { + "epoch": 0.01, + "learning_rate": 5.7938718662952654e-06, + "loss": 0.6033, + "step": 104 + }, + { + "epoch": 0.01, + "learning_rate": 5.849582172701951e-06, + "loss": 0.5802, + "step": 105 + }, + { + "epoch": 0.01, + "learning_rate": 5.905292479108635e-06, + "loss": 0.587, + "step": 106 + }, + { + "epoch": 0.01, + "learning_rate": 5.961002785515321e-06, + "loss": 0.5665, + "step": 107 + }, + { + "epoch": 0.01, + "learning_rate": 6.016713091922006e-06, + "loss": 0.5883, + "step": 108 + }, + { + "epoch": 0.01, + "learning_rate": 6.072423398328692e-06, + "loss": 0.5707, + "step": 109 + }, + { + "epoch": 0.01, + "learning_rate": 6.128133704735376e-06, + "loss": 0.5862, + "step": 110 + }, + { + "epoch": 0.01, + "learning_rate": 6.1838440111420615e-06, + "loss": 0.5918, + "step": 111 + }, + { + "epoch": 0.01, + "learning_rate": 6.2395543175487475e-06, + "loss": 0.564, + "step": 112 + }, + { + "epoch": 0.01, + "learning_rate": 6.295264623955433e-06, + "loss": 0.571, + "step": 113 + }, + { + "epoch": 0.01, + "learning_rate": 6.350974930362117e-06, + "loss": 0.5589, + "step": 114 + }, + { + "epoch": 0.01, + "learning_rate": 6.406685236768803e-06, + "loss": 0.5875, + "step": 115 + }, + { + "epoch": 0.01, + "learning_rate": 6.462395543175488e-06, + "loss": 0.5771, + "step": 116 + }, + { + "epoch": 0.01, + "learning_rate": 6.518105849582173e-06, + "loss": 0.5563, + "step": 117 + }, + { + "epoch": 0.01, + "learning_rate": 6.573816155988858e-06, + "loss": 0.5947, + "step": 118 + }, + { + "epoch": 0.01, + "learning_rate": 6.6295264623955435e-06, + "loss": 0.5625, + "step": 119 + }, + { + "epoch": 0.01, + "learning_rate": 6.685236768802229e-06, + "loss": 0.5658, + "step": 120 + }, + { + "epoch": 0.01, + "learning_rate": 6.740947075208915e-06, + "loss": 0.5672, + "step": 121 + }, + { + "epoch": 0.01, + "learning_rate": 6.796657381615599e-06, + "loss": 0.5932, + "step": 122 + }, + { + "epoch": 0.01, + "learning_rate": 6.852367688022284e-06, + "loss": 0.5779, + "step": 123 + }, + { + "epoch": 0.01, + "learning_rate": 6.90807799442897e-06, + "loss": 0.5683, + "step": 124 + }, + { + "epoch": 0.01, + "learning_rate": 6.963788300835655e-06, + "loss": 0.565, + "step": 125 + }, + { + "epoch": 0.01, + "learning_rate": 7.0194986072423395e-06, + "loss": 0.5455, + "step": 126 + }, + { + "epoch": 0.01, + "learning_rate": 7.0752089136490255e-06, + "loss": 0.5816, + "step": 127 + }, + { + "epoch": 0.01, + "learning_rate": 7.130919220055711e-06, + "loss": 0.5675, + "step": 128 + }, + { + "epoch": 0.01, + "learning_rate": 7.186629526462397e-06, + "loss": 0.575, + "step": 129 + }, + { + "epoch": 0.01, + "learning_rate": 7.242339832869081e-06, + "loss": 0.5656, + "step": 130 + }, + { + "epoch": 0.01, + "learning_rate": 7.298050139275766e-06, + "loss": 0.5686, + "step": 131 + }, + { + "epoch": 0.01, + "learning_rate": 7.353760445682452e-06, + "loss": 0.5917, + "step": 132 + }, + { + "epoch": 0.01, + "learning_rate": 7.409470752089137e-06, + "loss": 0.5935, + "step": 133 + }, + { + "epoch": 0.01, + "learning_rate": 7.465181058495823e-06, + "loss": 0.5816, + "step": 134 + }, + { + "epoch": 0.01, + "learning_rate": 7.5208913649025075e-06, + "loss": 0.5658, + "step": 135 + }, + { + "epoch": 0.01, + "learning_rate": 7.576601671309193e-06, + "loss": 0.5707, + "step": 136 + }, + { + "epoch": 0.01, + "learning_rate": 7.632311977715879e-06, + "loss": 0.5605, + "step": 137 + }, + { + "epoch": 0.01, + "learning_rate": 7.688022284122564e-06, + "loss": 0.5882, + "step": 138 + }, + { + "epoch": 0.01, + "learning_rate": 7.743732590529249e-06, + "loss": 0.5645, + "step": 139 + }, + { + "epoch": 0.01, + "learning_rate": 7.799442896935934e-06, + "loss": 0.5875, + "step": 140 + }, + { + "epoch": 0.01, + "learning_rate": 7.85515320334262e-06, + "loss": 0.5554, + "step": 141 + }, + { + "epoch": 0.01, + "learning_rate": 7.910863509749304e-06, + "loss": 0.5579, + "step": 142 + }, + { + "epoch": 0.01, + "learning_rate": 7.96657381615599e-06, + "loss": 0.5873, + "step": 143 + }, + { + "epoch": 0.01, + "learning_rate": 8.022284122562675e-06, + "loss": 0.5785, + "step": 144 + }, + { + "epoch": 0.01, + "learning_rate": 8.07799442896936e-06, + "loss": 0.5596, + "step": 145 + }, + { + "epoch": 0.01, + "learning_rate": 8.133704735376045e-06, + "loss": 0.5765, + "step": 146 + }, + { + "epoch": 0.01, + "learning_rate": 8.18941504178273e-06, + "loss": 0.5682, + "step": 147 + }, + { + "epoch": 0.01, + "learning_rate": 8.245125348189415e-06, + "loss": 0.5593, + "step": 148 + }, + { + "epoch": 0.01, + "learning_rate": 8.3008356545961e-06, + "loss": 0.5568, + "step": 149 + }, + { + "epoch": 0.01, + "learning_rate": 8.356545961002787e-06, + "loss": 0.5685, + "step": 150 + }, + { + "epoch": 0.01, + "learning_rate": 8.41225626740947e-06, + "loss": 0.5681, + "step": 151 + }, + { + "epoch": 0.01, + "learning_rate": 8.467966573816156e-06, + "loss": 0.5858, + "step": 152 + }, + { + "epoch": 0.01, + "learning_rate": 8.523676880222843e-06, + "loss": 0.5611, + "step": 153 + }, + { + "epoch": 0.01, + "learning_rate": 8.579387186629528e-06, + "loss": 0.5584, + "step": 154 + }, + { + "epoch": 0.01, + "learning_rate": 8.635097493036211e-06, + "loss": 0.5517, + "step": 155 + }, + { + "epoch": 0.01, + "learning_rate": 8.690807799442898e-06, + "loss": 0.56, + "step": 156 + }, + { + "epoch": 0.01, + "learning_rate": 8.746518105849583e-06, + "loss": 0.5673, + "step": 157 + }, + { + "epoch": 0.01, + "learning_rate": 8.802228412256268e-06, + "loss": 0.5571, + "step": 158 + }, + { + "epoch": 0.01, + "learning_rate": 8.857938718662954e-06, + "loss": 0.5716, + "step": 159 + }, + { + "epoch": 0.01, + "learning_rate": 8.913649025069639e-06, + "loss": 0.5634, + "step": 160 + }, + { + "epoch": 0.01, + "learning_rate": 8.969359331476324e-06, + "loss": 0.5602, + "step": 161 + }, + { + "epoch": 0.01, + "learning_rate": 9.025069637883009e-06, + "loss": 0.5444, + "step": 162 + }, + { + "epoch": 0.01, + "learning_rate": 9.080779944289694e-06, + "loss": 0.5793, + "step": 163 + }, + { + "epoch": 0.01, + "learning_rate": 9.13649025069638e-06, + "loss": 0.5443, + "step": 164 + }, + { + "epoch": 0.01, + "learning_rate": 9.192200557103064e-06, + "loss": 0.5449, + "step": 165 + }, + { + "epoch": 0.01, + "learning_rate": 9.24791086350975e-06, + "loss": 0.5599, + "step": 166 + }, + { + "epoch": 0.01, + "learning_rate": 9.303621169916436e-06, + "loss": 0.5362, + "step": 167 + }, + { + "epoch": 0.01, + "learning_rate": 9.35933147632312e-06, + "loss": 0.5649, + "step": 168 + }, + { + "epoch": 0.01, + "learning_rate": 9.415041782729805e-06, + "loss": 0.5734, + "step": 169 + }, + { + "epoch": 0.01, + "learning_rate": 9.470752089136492e-06, + "loss": 0.5595, + "step": 170 + }, + { + "epoch": 0.01, + "learning_rate": 9.526462395543177e-06, + "loss": 0.5483, + "step": 171 + }, + { + "epoch": 0.01, + "learning_rate": 9.58217270194986e-06, + "loss": 0.5569, + "step": 172 + }, + { + "epoch": 0.01, + "learning_rate": 9.637883008356547e-06, + "loss": 0.5591, + "step": 173 + }, + { + "epoch": 0.01, + "learning_rate": 9.693593314763233e-06, + "loss": 0.5639, + "step": 174 + }, + { + "epoch": 0.01, + "learning_rate": 9.749303621169918e-06, + "loss": 0.5504, + "step": 175 + }, + { + "epoch": 0.01, + "learning_rate": 9.805013927576603e-06, + "loss": 0.5627, + "step": 176 + }, + { + "epoch": 0.01, + "learning_rate": 9.860724233983288e-06, + "loss": 0.5587, + "step": 177 + }, + { + "epoch": 0.01, + "learning_rate": 9.916434540389973e-06, + "loss": 0.5603, + "step": 178 + }, + { + "epoch": 0.01, + "learning_rate": 9.972144846796658e-06, + "loss": 0.5558, + "step": 179 + }, + { + "epoch": 0.02, + "learning_rate": 1.0027855153203343e-05, + "loss": 0.5519, + "step": 180 + }, + { + "epoch": 0.02, + "learning_rate": 1.008356545961003e-05, + "loss": 0.5488, + "step": 181 + }, + { + "epoch": 0.02, + "learning_rate": 1.0139275766016714e-05, + "loss": 0.5417, + "step": 182 + }, + { + "epoch": 0.02, + "learning_rate": 1.0194986072423399e-05, + "loss": 0.5537, + "step": 183 + }, + { + "epoch": 0.02, + "learning_rate": 1.0250696378830086e-05, + "loss": 0.5349, + "step": 184 + }, + { + "epoch": 0.02, + "learning_rate": 1.0306406685236769e-05, + "loss": 0.5355, + "step": 185 + }, + { + "epoch": 0.02, + "learning_rate": 1.0362116991643454e-05, + "loss": 0.5492, + "step": 186 + }, + { + "epoch": 0.02, + "learning_rate": 1.0417827298050141e-05, + "loss": 0.5627, + "step": 187 + }, + { + "epoch": 0.02, + "learning_rate": 1.0473537604456825e-05, + "loss": 0.5576, + "step": 188 + }, + { + "epoch": 0.02, + "learning_rate": 1.0529247910863511e-05, + "loss": 0.5411, + "step": 189 + }, + { + "epoch": 0.02, + "learning_rate": 1.0584958217270197e-05, + "loss": 0.5494, + "step": 190 + }, + { + "epoch": 0.02, + "learning_rate": 1.064066852367688e-05, + "loss": 0.5574, + "step": 191 + }, + { + "epoch": 0.02, + "learning_rate": 1.0696378830083567e-05, + "loss": 0.5522, + "step": 192 + }, + { + "epoch": 0.02, + "learning_rate": 1.0752089136490252e-05, + "loss": 0.546, + "step": 193 + }, + { + "epoch": 0.02, + "learning_rate": 1.0807799442896935e-05, + "loss": 0.5454, + "step": 194 + }, + { + "epoch": 0.02, + "learning_rate": 1.0863509749303622e-05, + "loss": 0.5463, + "step": 195 + }, + { + "epoch": 0.02, + "learning_rate": 1.0919220055710307e-05, + "loss": 0.5607, + "step": 196 + }, + { + "epoch": 0.02, + "learning_rate": 1.0974930362116993e-05, + "loss": 0.5493, + "step": 197 + }, + { + "epoch": 0.02, + "learning_rate": 1.1030640668523678e-05, + "loss": 0.5301, + "step": 198 + }, + { + "epoch": 0.02, + "learning_rate": 1.1086350974930363e-05, + "loss": 0.5335, + "step": 199 + }, + { + "epoch": 0.02, + "learning_rate": 1.1142061281337048e-05, + "loss": 0.5532, + "step": 200 + }, + { + "epoch": 0.02, + "learning_rate": 1.1197771587743733e-05, + "loss": 0.5332, + "step": 201 + }, + { + "epoch": 0.02, + "learning_rate": 1.125348189415042e-05, + "loss": 0.5719, + "step": 202 + }, + { + "epoch": 0.02, + "learning_rate": 1.1309192200557103e-05, + "loss": 0.5222, + "step": 203 + }, + { + "epoch": 0.02, + "learning_rate": 1.1364902506963789e-05, + "loss": 0.5481, + "step": 204 + }, + { + "epoch": 0.02, + "learning_rate": 1.1420612813370475e-05, + "loss": 0.5465, + "step": 205 + }, + { + "epoch": 0.02, + "learning_rate": 1.1476323119777159e-05, + "loss": 0.552, + "step": 206 + }, + { + "epoch": 0.02, + "learning_rate": 1.1532033426183844e-05, + "loss": 0.5473, + "step": 207 + }, + { + "epoch": 0.02, + "learning_rate": 1.1587743732590531e-05, + "loss": 0.5439, + "step": 208 + }, + { + "epoch": 0.02, + "learning_rate": 1.1643454038997214e-05, + "loss": 0.5462, + "step": 209 + }, + { + "epoch": 0.02, + "learning_rate": 1.1699164345403901e-05, + "loss": 0.5401, + "step": 210 + }, + { + "epoch": 0.02, + "learning_rate": 1.1754874651810586e-05, + "loss": 0.5498, + "step": 211 + }, + { + "epoch": 0.02, + "learning_rate": 1.181058495821727e-05, + "loss": 0.5567, + "step": 212 + }, + { + "epoch": 0.02, + "learning_rate": 1.1866295264623957e-05, + "loss": 0.5436, + "step": 213 + }, + { + "epoch": 0.02, + "learning_rate": 1.1922005571030642e-05, + "loss": 0.5484, + "step": 214 + }, + { + "epoch": 0.02, + "learning_rate": 1.1977715877437325e-05, + "loss": 0.5411, + "step": 215 + }, + { + "epoch": 0.02, + "learning_rate": 1.2033426183844012e-05, + "loss": 0.5581, + "step": 216 + }, + { + "epoch": 0.02, + "learning_rate": 1.2089136490250697e-05, + "loss": 0.5441, + "step": 217 + }, + { + "epoch": 0.02, + "learning_rate": 1.2144846796657384e-05, + "loss": 0.5574, + "step": 218 + }, + { + "epoch": 0.02, + "learning_rate": 1.2200557103064068e-05, + "loss": 0.5588, + "step": 219 + }, + { + "epoch": 0.02, + "learning_rate": 1.2256267409470753e-05, + "loss": 0.5554, + "step": 220 + }, + { + "epoch": 0.02, + "learning_rate": 1.231197771587744e-05, + "loss": 0.5342, + "step": 221 + }, + { + "epoch": 0.02, + "learning_rate": 1.2367688022284123e-05, + "loss": 0.568, + "step": 222 + }, + { + "epoch": 0.02, + "learning_rate": 1.2423398328690808e-05, + "loss": 0.5387, + "step": 223 + }, + { + "epoch": 0.02, + "learning_rate": 1.2479108635097495e-05, + "loss": 0.5469, + "step": 224 + }, + { + "epoch": 0.02, + "learning_rate": 1.2534818941504178e-05, + "loss": 0.5312, + "step": 225 + }, + { + "epoch": 0.02, + "learning_rate": 1.2590529247910865e-05, + "loss": 0.5462, + "step": 226 + }, + { + "epoch": 0.02, + "learning_rate": 1.264623955431755e-05, + "loss": 0.5595, + "step": 227 + }, + { + "epoch": 0.02, + "learning_rate": 1.2701949860724234e-05, + "loss": 0.5355, + "step": 228 + }, + { + "epoch": 0.02, + "learning_rate": 1.275766016713092e-05, + "loss": 0.548, + "step": 229 + }, + { + "epoch": 0.02, + "learning_rate": 1.2813370473537606e-05, + "loss": 0.547, + "step": 230 + }, + { + "epoch": 0.02, + "learning_rate": 1.2869080779944293e-05, + "loss": 0.5309, + "step": 231 + }, + { + "epoch": 0.02, + "learning_rate": 1.2924791086350976e-05, + "loss": 0.557, + "step": 232 + }, + { + "epoch": 0.02, + "learning_rate": 1.2980501392757661e-05, + "loss": 0.5592, + "step": 233 + }, + { + "epoch": 0.02, + "learning_rate": 1.3036211699164346e-05, + "loss": 0.5326, + "step": 234 + }, + { + "epoch": 0.02, + "learning_rate": 1.3091922005571032e-05, + "loss": 0.5262, + "step": 235 + }, + { + "epoch": 0.02, + "learning_rate": 1.3147632311977717e-05, + "loss": 0.5443, + "step": 236 + }, + { + "epoch": 0.02, + "learning_rate": 1.3203342618384402e-05, + "loss": 0.541, + "step": 237 + }, + { + "epoch": 0.02, + "learning_rate": 1.3259052924791087e-05, + "loss": 0.5411, + "step": 238 + }, + { + "epoch": 0.02, + "learning_rate": 1.3314763231197774e-05, + "loss": 0.5406, + "step": 239 + }, + { + "epoch": 0.02, + "learning_rate": 1.3370473537604457e-05, + "loss": 0.5488, + "step": 240 + }, + { + "epoch": 0.02, + "learning_rate": 1.3426183844011142e-05, + "loss": 0.5626, + "step": 241 + }, + { + "epoch": 0.02, + "learning_rate": 1.348189415041783e-05, + "loss": 0.5479, + "step": 242 + }, + { + "epoch": 0.02, + "learning_rate": 1.3537604456824513e-05, + "loss": 0.5583, + "step": 243 + }, + { + "epoch": 0.02, + "learning_rate": 1.3593314763231198e-05, + "loss": 0.5572, + "step": 244 + }, + { + "epoch": 0.02, + "learning_rate": 1.3649025069637885e-05, + "loss": 0.5438, + "step": 245 + }, + { + "epoch": 0.02, + "learning_rate": 1.3704735376044568e-05, + "loss": 0.5382, + "step": 246 + }, + { + "epoch": 0.02, + "learning_rate": 1.3760445682451255e-05, + "loss": 0.5321, + "step": 247 + }, + { + "epoch": 0.02, + "learning_rate": 1.381615598885794e-05, + "loss": 0.5513, + "step": 248 + }, + { + "epoch": 0.02, + "learning_rate": 1.3871866295264624e-05, + "loss": 0.546, + "step": 249 + }, + { + "epoch": 0.02, + "learning_rate": 1.392757660167131e-05, + "loss": 0.5539, + "step": 250 + }, + { + "epoch": 0.02, + "learning_rate": 1.3983286908077996e-05, + "loss": 0.5551, + "step": 251 + }, + { + "epoch": 0.02, + "learning_rate": 1.4038997214484679e-05, + "loss": 0.5484, + "step": 252 + }, + { + "epoch": 0.02, + "learning_rate": 1.4094707520891366e-05, + "loss": 0.5445, + "step": 253 + }, + { + "epoch": 0.02, + "learning_rate": 1.4150417827298051e-05, + "loss": 0.5497, + "step": 254 + }, + { + "epoch": 0.02, + "learning_rate": 1.4206128133704738e-05, + "loss": 0.5279, + "step": 255 + }, + { + "epoch": 0.02, + "learning_rate": 1.4261838440111421e-05, + "loss": 0.5312, + "step": 256 + }, + { + "epoch": 0.02, + "learning_rate": 1.4317548746518106e-05, + "loss": 0.5578, + "step": 257 + }, + { + "epoch": 0.02, + "learning_rate": 1.4373259052924793e-05, + "loss": 0.549, + "step": 258 + }, + { + "epoch": 0.02, + "learning_rate": 1.4428969359331477e-05, + "loss": 0.5359, + "step": 259 + }, + { + "epoch": 0.02, + "learning_rate": 1.4484679665738162e-05, + "loss": 0.5571, + "step": 260 + }, + { + "epoch": 0.02, + "learning_rate": 1.4540389972144849e-05, + "loss": 0.5211, + "step": 261 + }, + { + "epoch": 0.02, + "learning_rate": 1.4596100278551532e-05, + "loss": 0.5446, + "step": 262 + }, + { + "epoch": 0.02, + "learning_rate": 1.4651810584958219e-05, + "loss": 0.533, + "step": 263 + }, + { + "epoch": 0.02, + "learning_rate": 1.4707520891364904e-05, + "loss": 0.548, + "step": 264 + }, + { + "epoch": 0.02, + "learning_rate": 1.4763231197771588e-05, + "loss": 0.546, + "step": 265 + }, + { + "epoch": 0.02, + "learning_rate": 1.4818941504178274e-05, + "loss": 0.5171, + "step": 266 + }, + { + "epoch": 0.02, + "learning_rate": 1.487465181058496e-05, + "loss": 0.5478, + "step": 267 + }, + { + "epoch": 0.02, + "learning_rate": 1.4930362116991646e-05, + "loss": 0.5389, + "step": 268 + }, + { + "epoch": 0.02, + "learning_rate": 1.498607242339833e-05, + "loss": 0.5388, + "step": 269 + }, + { + "epoch": 0.02, + "learning_rate": 1.5041782729805015e-05, + "loss": 0.5412, + "step": 270 + }, + { + "epoch": 0.02, + "learning_rate": 1.5097493036211702e-05, + "loss": 0.5354, + "step": 271 + }, + { + "epoch": 0.02, + "learning_rate": 1.5153203342618385e-05, + "loss": 0.5453, + "step": 272 + }, + { + "epoch": 0.02, + "learning_rate": 1.520891364902507e-05, + "loss": 0.5322, + "step": 273 + }, + { + "epoch": 0.02, + "learning_rate": 1.5264623955431757e-05, + "loss": 0.5533, + "step": 274 + }, + { + "epoch": 0.02, + "learning_rate": 1.5320334261838443e-05, + "loss": 0.5358, + "step": 275 + }, + { + "epoch": 0.02, + "learning_rate": 1.5376044568245128e-05, + "loss": 0.5376, + "step": 276 + }, + { + "epoch": 0.02, + "learning_rate": 1.5431754874651813e-05, + "loss": 0.5359, + "step": 277 + }, + { + "epoch": 0.02, + "learning_rate": 1.5487465181058498e-05, + "loss": 0.5518, + "step": 278 + }, + { + "epoch": 0.02, + "learning_rate": 1.5543175487465183e-05, + "loss": 0.5365, + "step": 279 + }, + { + "epoch": 0.02, + "learning_rate": 1.5598885793871868e-05, + "loss": 0.5345, + "step": 280 + }, + { + "epoch": 0.02, + "learning_rate": 1.5654596100278553e-05, + "loss": 0.5424, + "step": 281 + }, + { + "epoch": 0.02, + "learning_rate": 1.571030640668524e-05, + "loss": 0.5337, + "step": 282 + }, + { + "epoch": 0.02, + "learning_rate": 1.5766016713091924e-05, + "loss": 0.5202, + "step": 283 + }, + { + "epoch": 0.02, + "learning_rate": 1.582172701949861e-05, + "loss": 0.5293, + "step": 284 + }, + { + "epoch": 0.02, + "learning_rate": 1.5877437325905294e-05, + "loss": 0.549, + "step": 285 + }, + { + "epoch": 0.02, + "learning_rate": 1.593314763231198e-05, + "loss": 0.5346, + "step": 286 + }, + { + "epoch": 0.02, + "learning_rate": 1.5988857938718664e-05, + "loss": 0.5482, + "step": 287 + }, + { + "epoch": 0.02, + "learning_rate": 1.604456824512535e-05, + "loss": 0.5549, + "step": 288 + }, + { + "epoch": 0.02, + "learning_rate": 1.6100278551532035e-05, + "loss": 0.5293, + "step": 289 + }, + { + "epoch": 0.02, + "learning_rate": 1.615598885793872e-05, + "loss": 0.5656, + "step": 290 + }, + { + "epoch": 0.02, + "learning_rate": 1.6211699164345405e-05, + "loss": 0.5305, + "step": 291 + }, + { + "epoch": 0.02, + "learning_rate": 1.626740947075209e-05, + "loss": 0.5557, + "step": 292 + }, + { + "epoch": 0.02, + "learning_rate": 1.6323119777158775e-05, + "loss": 0.5374, + "step": 293 + }, + { + "epoch": 0.02, + "learning_rate": 1.637883008356546e-05, + "loss": 0.5183, + "step": 294 + }, + { + "epoch": 0.02, + "learning_rate": 1.6434540389972145e-05, + "loss": 0.5629, + "step": 295 + }, + { + "epoch": 0.02, + "learning_rate": 1.649025069637883e-05, + "loss": 0.5362, + "step": 296 + }, + { + "epoch": 0.02, + "learning_rate": 1.654596100278552e-05, + "loss": 0.532, + "step": 297 + }, + { + "epoch": 0.02, + "learning_rate": 1.66016713091922e-05, + "loss": 0.5322, + "step": 298 + }, + { + "epoch": 0.03, + "learning_rate": 1.6657381615598886e-05, + "loss": 0.528, + "step": 299 + }, + { + "epoch": 0.03, + "learning_rate": 1.6713091922005575e-05, + "loss": 0.5609, + "step": 300 + }, + { + "epoch": 0.03, + "learning_rate": 1.6768802228412256e-05, + "loss": 0.5438, + "step": 301 + }, + { + "epoch": 0.03, + "learning_rate": 1.682451253481894e-05, + "loss": 0.5241, + "step": 302 + }, + { + "epoch": 0.03, + "learning_rate": 1.688022284122563e-05, + "loss": 0.5318, + "step": 303 + }, + { + "epoch": 0.03, + "learning_rate": 1.6935933147632312e-05, + "loss": 0.539, + "step": 304 + }, + { + "epoch": 0.03, + "learning_rate": 1.6991643454039e-05, + "loss": 0.5516, + "step": 305 + }, + { + "epoch": 0.03, + "learning_rate": 1.7047353760445685e-05, + "loss": 0.5418, + "step": 306 + }, + { + "epoch": 0.03, + "learning_rate": 1.7103064066852367e-05, + "loss": 0.5453, + "step": 307 + }, + { + "epoch": 0.03, + "learning_rate": 1.7158774373259056e-05, + "loss": 0.5144, + "step": 308 + }, + { + "epoch": 0.03, + "learning_rate": 1.721448467966574e-05, + "loss": 0.5553, + "step": 309 + }, + { + "epoch": 0.03, + "learning_rate": 1.7270194986072423e-05, + "loss": 0.5618, + "step": 310 + }, + { + "epoch": 0.03, + "learning_rate": 1.732590529247911e-05, + "loss": 0.525, + "step": 311 + }, + { + "epoch": 0.03, + "learning_rate": 1.7381615598885796e-05, + "loss": 0.5315, + "step": 312 + }, + { + "epoch": 0.03, + "learning_rate": 1.743732590529248e-05, + "loss": 0.5413, + "step": 313 + }, + { + "epoch": 0.03, + "learning_rate": 1.7493036211699167e-05, + "loss": 0.549, + "step": 314 + }, + { + "epoch": 0.03, + "learning_rate": 1.7548746518105852e-05, + "loss": 0.5299, + "step": 315 + }, + { + "epoch": 0.03, + "learning_rate": 1.7604456824512537e-05, + "loss": 0.5693, + "step": 316 + }, + { + "epoch": 0.03, + "learning_rate": 1.7660167130919222e-05, + "loss": 0.5535, + "step": 317 + }, + { + "epoch": 0.03, + "learning_rate": 1.7715877437325907e-05, + "loss": 0.5383, + "step": 318 + }, + { + "epoch": 0.03, + "learning_rate": 1.7771587743732592e-05, + "loss": 0.5564, + "step": 319 + }, + { + "epoch": 0.03, + "learning_rate": 1.7827298050139278e-05, + "loss": 0.5521, + "step": 320 + }, + { + "epoch": 0.03, + "learning_rate": 1.7883008356545963e-05, + "loss": 0.5272, + "step": 321 + }, + { + "epoch": 0.03, + "learning_rate": 1.7938718662952648e-05, + "loss": 0.5204, + "step": 322 + }, + { + "epoch": 0.03, + "learning_rate": 1.7994428969359333e-05, + "loss": 0.5537, + "step": 323 + }, + { + "epoch": 0.03, + "learning_rate": 1.8050139275766018e-05, + "loss": 0.5412, + "step": 324 + }, + { + "epoch": 0.03, + "learning_rate": 1.8105849582172703e-05, + "loss": 0.5343, + "step": 325 + }, + { + "epoch": 0.03, + "learning_rate": 1.816155988857939e-05, + "loss": 0.5388, + "step": 326 + }, + { + "epoch": 0.03, + "learning_rate": 1.8217270194986074e-05, + "loss": 0.5325, + "step": 327 + }, + { + "epoch": 0.03, + "learning_rate": 1.827298050139276e-05, + "loss": 0.525, + "step": 328 + }, + { + "epoch": 0.03, + "learning_rate": 1.8328690807799444e-05, + "loss": 0.5467, + "step": 329 + }, + { + "epoch": 0.03, + "learning_rate": 1.838440111420613e-05, + "loss": 0.5329, + "step": 330 + }, + { + "epoch": 0.03, + "learning_rate": 1.8440111420612814e-05, + "loss": 0.5338, + "step": 331 + }, + { + "epoch": 0.03, + "learning_rate": 1.84958217270195e-05, + "loss": 0.5236, + "step": 332 + }, + { + "epoch": 0.03, + "learning_rate": 1.8551532033426184e-05, + "loss": 0.5235, + "step": 333 + }, + { + "epoch": 0.03, + "learning_rate": 1.8607242339832873e-05, + "loss": 0.5295, + "step": 334 + }, + { + "epoch": 0.03, + "learning_rate": 1.8662952646239555e-05, + "loss": 0.5306, + "step": 335 + }, + { + "epoch": 0.03, + "learning_rate": 1.871866295264624e-05, + "loss": 0.5102, + "step": 336 + }, + { + "epoch": 0.03, + "learning_rate": 1.877437325905293e-05, + "loss": 0.5463, + "step": 337 + }, + { + "epoch": 0.03, + "learning_rate": 1.883008356545961e-05, + "loss": 0.5163, + "step": 338 + }, + { + "epoch": 0.03, + "learning_rate": 1.8885793871866295e-05, + "loss": 0.5452, + "step": 339 + }, + { + "epoch": 0.03, + "learning_rate": 1.8941504178272984e-05, + "loss": 0.547, + "step": 340 + }, + { + "epoch": 0.03, + "learning_rate": 1.8997214484679666e-05, + "loss": 0.5442, + "step": 341 + }, + { + "epoch": 0.03, + "learning_rate": 1.9052924791086354e-05, + "loss": 0.5389, + "step": 342 + }, + { + "epoch": 0.03, + "learning_rate": 1.910863509749304e-05, + "loss": 0.5253, + "step": 343 + }, + { + "epoch": 0.03, + "learning_rate": 1.916434540389972e-05, + "loss": 0.5252, + "step": 344 + }, + { + "epoch": 0.03, + "learning_rate": 1.922005571030641e-05, + "loss": 0.5388, + "step": 345 + }, + { + "epoch": 0.03, + "learning_rate": 1.9275766016713095e-05, + "loss": 0.5336, + "step": 346 + }, + { + "epoch": 0.03, + "learning_rate": 1.9331476323119776e-05, + "loss": 0.5342, + "step": 347 + }, + { + "epoch": 0.03, + "learning_rate": 1.9387186629526465e-05, + "loss": 0.5227, + "step": 348 + }, + { + "epoch": 0.03, + "learning_rate": 1.944289693593315e-05, + "loss": 0.5062, + "step": 349 + }, + { + "epoch": 0.03, + "learning_rate": 1.9498607242339835e-05, + "loss": 0.5286, + "step": 350 + }, + { + "epoch": 0.03, + "learning_rate": 1.955431754874652e-05, + "loss": 0.5326, + "step": 351 + }, + { + "epoch": 0.03, + "learning_rate": 1.9610027855153206e-05, + "loss": 0.5219, + "step": 352 + }, + { + "epoch": 0.03, + "learning_rate": 1.966573816155989e-05, + "loss": 0.5258, + "step": 353 + }, + { + "epoch": 0.03, + "learning_rate": 1.9721448467966576e-05, + "loss": 0.5307, + "step": 354 + }, + { + "epoch": 0.03, + "learning_rate": 1.977715877437326e-05, + "loss": 0.5314, + "step": 355 + }, + { + "epoch": 0.03, + "learning_rate": 1.9832869080779946e-05, + "loss": 0.5438, + "step": 356 + }, + { + "epoch": 0.03, + "learning_rate": 1.988857938718663e-05, + "loss": 0.5321, + "step": 357 + }, + { + "epoch": 0.03, + "learning_rate": 1.9944289693593316e-05, + "loss": 0.5139, + "step": 358 + }, + { + "epoch": 0.03, + "learning_rate": 2e-05, + "loss": 0.5207, + "step": 359 + }, + { + "epoch": 0.03, + "learning_rate": 1.99999996328208e-05, + "loss": 0.5364, + "step": 360 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999998531283215e-05, + "loss": 0.54, + "step": 361 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999996695387335e-05, + "loss": 0.5216, + "step": 362 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999994125133287e-05, + "loss": 0.5454, + "step": 363 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999990820521264e-05, + "loss": 0.5464, + "step": 364 + }, + { + "epoch": 0.03, + "learning_rate": 1.999998678155151e-05, + "loss": 0.5201, + "step": 365 + }, + { + "epoch": 0.03, + "learning_rate": 1.999998200822432e-05, + "loss": 0.541, + "step": 366 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999976500540042e-05, + "loss": 0.5372, + "step": 367 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999970258499083e-05, + "loss": 0.5408, + "step": 368 + }, + { + "epoch": 0.03, + "learning_rate": 1.99999632821019e-05, + "loss": 0.5416, + "step": 369 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999955571349014e-05, + "loss": 0.5459, + "step": 370 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999947126240977e-05, + "loss": 0.5258, + "step": 371 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999937946778418e-05, + "loss": 0.5256, + "step": 372 + }, + { + "epoch": 0.03, + "learning_rate": 1.999992803296201e-05, + "loss": 0.5362, + "step": 373 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999917384792477e-05, + "loss": 0.5381, + "step": 374 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999906002270605e-05, + "loss": 0.536, + "step": 375 + }, + { + "epoch": 0.03, + "learning_rate": 1.999989388539723e-05, + "loss": 0.5304, + "step": 376 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999881034173242e-05, + "loss": 0.5351, + "step": 377 + }, + { + "epoch": 0.03, + "learning_rate": 1.999986744859958e-05, + "loss": 0.5387, + "step": 378 + }, + { + "epoch": 0.03, + "learning_rate": 1.999985312867725e-05, + "loss": 0.5333, + "step": 379 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999838074407296e-05, + "loss": 0.5152, + "step": 380 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999822285790825e-05, + "loss": 0.516, + "step": 381 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999805762829e-05, + "loss": 0.539, + "step": 382 + }, + { + "epoch": 0.03, + "learning_rate": 1.999978850552303e-05, + "loss": 0.5299, + "step": 383 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999770513874187e-05, + "loss": 0.5556, + "step": 384 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999751787883787e-05, + "loss": 0.5509, + "step": 385 + }, + { + "epoch": 0.03, + "learning_rate": 1.999973232755321e-05, + "loss": 0.5262, + "step": 386 + }, + { + "epoch": 0.03, + "learning_rate": 1.999971213288388e-05, + "loss": 0.5146, + "step": 387 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999691203877286e-05, + "loss": 0.5112, + "step": 388 + }, + { + "epoch": 0.03, + "learning_rate": 1.999966954053496e-05, + "loss": 0.544, + "step": 389 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999647142858496e-05, + "loss": 0.519, + "step": 390 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999624010849536e-05, + "loss": 0.5349, + "step": 391 + }, + { + "epoch": 0.03, + "learning_rate": 1.999960014450978e-05, + "loss": 0.5184, + "step": 392 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999575543840982e-05, + "loss": 0.5374, + "step": 393 + }, + { + "epoch": 0.03, + "learning_rate": 1.999955020884495e-05, + "loss": 0.5205, + "step": 394 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999524139523538e-05, + "loss": 0.5536, + "step": 395 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999497335878666e-05, + "loss": 0.5277, + "step": 396 + }, + { + "epoch": 0.03, + "learning_rate": 1.99994697979123e-05, + "loss": 0.5181, + "step": 397 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999441525626464e-05, + "loss": 0.5173, + "step": 398 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999412519023233e-05, + "loss": 0.5443, + "step": 399 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999382778104734e-05, + "loss": 0.5279, + "step": 400 + }, + { + "epoch": 0.03, + "learning_rate": 1.999935230287316e-05, + "loss": 0.5472, + "step": 401 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999321093330736e-05, + "loss": 0.5348, + "step": 402 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999289149479767e-05, + "loss": 0.5534, + "step": 403 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999256471322593e-05, + "loss": 0.5447, + "step": 404 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999223058861613e-05, + "loss": 0.5312, + "step": 405 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999188912099278e-05, + "loss": 0.5267, + "step": 406 + }, + { + "epoch": 0.03, + "learning_rate": 1.99991540310381e-05, + "loss": 0.5221, + "step": 407 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999118415680642e-05, + "loss": 0.5456, + "step": 408 + }, + { + "epoch": 0.03, + "learning_rate": 1.999908206602952e-05, + "loss": 0.5202, + "step": 409 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999044982087394e-05, + "loss": 0.5202, + "step": 410 + }, + { + "epoch": 0.03, + "learning_rate": 1.9999007163856998e-05, + "loss": 0.5302, + "step": 411 + }, + { + "epoch": 0.03, + "learning_rate": 1.9998968611341102e-05, + "loss": 0.5081, + "step": 412 + }, + { + "epoch": 0.03, + "learning_rate": 1.9998929324542543e-05, + "loss": 0.5599, + "step": 413 + }, + { + "epoch": 0.03, + "learning_rate": 1.99988893034642e-05, + "loss": 0.5327, + "step": 414 + }, + { + "epoch": 0.03, + "learning_rate": 1.9998848548109017e-05, + "loss": 0.5236, + "step": 415 + }, + { + "epoch": 0.03, + "learning_rate": 1.9998807058479986e-05, + "loss": 0.5366, + "step": 416 + }, + { + "epoch": 0.03, + "learning_rate": 1.9998764834580147e-05, + "loss": 0.5525, + "step": 417 + }, + { + "epoch": 0.03, + "learning_rate": 1.9998721876412613e-05, + "loss": 0.5199, + "step": 418 + }, + { + "epoch": 0.04, + "learning_rate": 1.9998678183980532e-05, + "loss": 0.518, + "step": 419 + }, + { + "epoch": 0.04, + "learning_rate": 1.999863375728711e-05, + "loss": 0.5472, + "step": 420 + }, + { + "epoch": 0.04, + "learning_rate": 1.9998588596335612e-05, + "loss": 0.5363, + "step": 421 + }, + { + "epoch": 0.04, + "learning_rate": 1.9998542701129357e-05, + "loss": 0.5383, + "step": 422 + }, + { + "epoch": 0.04, + "learning_rate": 1.999849607167171e-05, + "loss": 0.5367, + "step": 423 + }, + { + "epoch": 0.04, + "learning_rate": 1.99984487079661e-05, + "loss": 0.5358, + "step": 424 + }, + { + "epoch": 0.04, + "learning_rate": 1.9998400610016003e-05, + "loss": 0.5414, + "step": 425 + }, + { + "epoch": 0.04, + "learning_rate": 1.9998351777824956e-05, + "loss": 0.5361, + "step": 426 + }, + { + "epoch": 0.04, + "learning_rate": 1.9998302211396537e-05, + "loss": 0.5266, + "step": 427 + }, + { + "epoch": 0.04, + "learning_rate": 1.999825191073439e-05, + "loss": 0.5149, + "step": 428 + }, + { + "epoch": 0.04, + "learning_rate": 1.9998200875842206e-05, + "loss": 0.5253, + "step": 429 + }, + { + "epoch": 0.04, + "learning_rate": 1.9998149106723737e-05, + "loss": 0.5362, + "step": 430 + }, + { + "epoch": 0.04, + "learning_rate": 1.9998096603382785e-05, + "loss": 0.5377, + "step": 431 + }, + { + "epoch": 0.04, + "learning_rate": 1.9998043365823205e-05, + "loss": 0.5397, + "step": 432 + }, + { + "epoch": 0.04, + "learning_rate": 1.99979893940489e-05, + "loss": 0.5267, + "step": 433 + }, + { + "epoch": 0.04, + "learning_rate": 1.999793468806384e-05, + "loss": 0.5379, + "step": 434 + }, + { + "epoch": 0.04, + "learning_rate": 1.9997879247872042e-05, + "loss": 0.5283, + "step": 435 + }, + { + "epoch": 0.04, + "learning_rate": 1.9997823073477577e-05, + "loss": 0.5098, + "step": 436 + }, + { + "epoch": 0.04, + "learning_rate": 1.9997766164884572e-05, + "loss": 0.5102, + "step": 437 + }, + { + "epoch": 0.04, + "learning_rate": 1.9997708522097202e-05, + "loss": 0.5374, + "step": 438 + }, + { + "epoch": 0.04, + "learning_rate": 1.9997650145119702e-05, + "loss": 0.5158, + "step": 439 + }, + { + "epoch": 0.04, + "learning_rate": 1.9997591033956353e-05, + "loss": 0.5019, + "step": 440 + }, + { + "epoch": 0.04, + "learning_rate": 1.9997531188611507e-05, + "loss": 0.5368, + "step": 441 + }, + { + "epoch": 0.04, + "learning_rate": 1.999747060908955e-05, + "loss": 0.5247, + "step": 442 + }, + { + "epoch": 0.04, + "learning_rate": 1.9997409295394938e-05, + "loss": 0.5346, + "step": 443 + }, + { + "epoch": 0.04, + "learning_rate": 1.999734724753217e-05, + "loss": 0.5386, + "step": 444 + }, + { + "epoch": 0.04, + "learning_rate": 1.99972844655058e-05, + "loss": 0.5305, + "step": 445 + }, + { + "epoch": 0.04, + "learning_rate": 1.999722094932044e-05, + "loss": 0.5347, + "step": 446 + }, + { + "epoch": 0.04, + "learning_rate": 1.9997156698980755e-05, + "loss": 0.5309, + "step": 447 + }, + { + "epoch": 0.04, + "learning_rate": 1.9997091714491465e-05, + "loss": 0.5383, + "step": 448 + }, + { + "epoch": 0.04, + "learning_rate": 1.999702599585734e-05, + "loss": 0.524, + "step": 449 + }, + { + "epoch": 0.04, + "learning_rate": 1.9996959543083207e-05, + "loss": 0.5387, + "step": 450 + }, + { + "epoch": 0.04, + "learning_rate": 1.9996892356173946e-05, + "loss": 0.5336, + "step": 451 + }, + { + "epoch": 0.04, + "learning_rate": 1.9996824435134486e-05, + "loss": 0.5338, + "step": 452 + }, + { + "epoch": 0.04, + "learning_rate": 1.9996755779969827e-05, + "loss": 0.5231, + "step": 453 + }, + { + "epoch": 0.04, + "learning_rate": 1.9996686390685e-05, + "loss": 0.5371, + "step": 454 + }, + { + "epoch": 0.04, + "learning_rate": 1.9996616267285104e-05, + "loss": 0.5467, + "step": 455 + }, + { + "epoch": 0.04, + "learning_rate": 1.9996545409775286e-05, + "loss": 0.5239, + "step": 456 + }, + { + "epoch": 0.04, + "learning_rate": 1.9996473818160752e-05, + "loss": 0.5296, + "step": 457 + }, + { + "epoch": 0.04, + "learning_rate": 1.999640149244676e-05, + "loss": 0.5514, + "step": 458 + }, + { + "epoch": 0.04, + "learning_rate": 1.9996328432638622e-05, + "loss": 0.5196, + "step": 459 + }, + { + "epoch": 0.04, + "learning_rate": 1.9996254638741702e-05, + "loss": 0.5297, + "step": 460 + }, + { + "epoch": 0.04, + "learning_rate": 1.999618011076142e-05, + "loss": 0.5309, + "step": 461 + }, + { + "epoch": 0.04, + "learning_rate": 1.9996104848703243e-05, + "loss": 0.5313, + "step": 462 + }, + { + "epoch": 0.04, + "learning_rate": 1.9996028852572705e-05, + "loss": 0.5292, + "step": 463 + }, + { + "epoch": 0.04, + "learning_rate": 1.9995952122375385e-05, + "loss": 0.5368, + "step": 464 + }, + { + "epoch": 0.04, + "learning_rate": 1.9995874658116917e-05, + "loss": 0.5373, + "step": 465 + }, + { + "epoch": 0.04, + "learning_rate": 1.999579645980299e-05, + "loss": 0.5392, + "step": 466 + }, + { + "epoch": 0.04, + "learning_rate": 1.9995717527439348e-05, + "loss": 0.5315, + "step": 467 + }, + { + "epoch": 0.04, + "learning_rate": 1.9995637861031786e-05, + "loss": 0.5325, + "step": 468 + }, + { + "epoch": 0.04, + "learning_rate": 1.9995557460586153e-05, + "loss": 0.5468, + "step": 469 + }, + { + "epoch": 0.04, + "learning_rate": 1.9995476326108355e-05, + "loss": 0.5525, + "step": 470 + }, + { + "epoch": 0.04, + "learning_rate": 1.9995394457604354e-05, + "loss": 0.5133, + "step": 471 + }, + { + "epoch": 0.04, + "learning_rate": 1.9995311855080155e-05, + "loss": 0.5228, + "step": 472 + }, + { + "epoch": 0.04, + "learning_rate": 1.9995228518541828e-05, + "loss": 0.5394, + "step": 473 + }, + { + "epoch": 0.04, + "learning_rate": 1.999514444799549e-05, + "loss": 0.5449, + "step": 474 + }, + { + "epoch": 0.04, + "learning_rate": 1.9995059643447313e-05, + "loss": 0.5181, + "step": 475 + }, + { + "epoch": 0.04, + "learning_rate": 1.9994974104903536e-05, + "loss": 0.533, + "step": 476 + }, + { + "epoch": 0.04, + "learning_rate": 1.999488783237043e-05, + "loss": 0.5344, + "step": 477 + }, + { + "epoch": 0.04, + "learning_rate": 1.999480082585433e-05, + "loss": 0.5248, + "step": 478 + }, + { + "epoch": 0.04, + "learning_rate": 1.999471308536163e-05, + "loss": 0.5394, + "step": 479 + }, + { + "epoch": 0.04, + "learning_rate": 1.9994624610898778e-05, + "loss": 0.5263, + "step": 480 + }, + { + "epoch": 0.04, + "learning_rate": 1.999453540247226e-05, + "loss": 0.5065, + "step": 481 + }, + { + "epoch": 0.04, + "learning_rate": 1.9994445460088635e-05, + "loss": 0.5423, + "step": 482 + }, + { + "epoch": 0.04, + "learning_rate": 1.9994354783754504e-05, + "loss": 0.5219, + "step": 483 + }, + { + "epoch": 0.04, + "learning_rate": 1.9994263373476526e-05, + "loss": 0.5298, + "step": 484 + }, + { + "epoch": 0.04, + "learning_rate": 1.9994171229261417e-05, + "loss": 0.5212, + "step": 485 + }, + { + "epoch": 0.04, + "learning_rate": 1.999407835111594e-05, + "loss": 0.5283, + "step": 486 + }, + { + "epoch": 0.04, + "learning_rate": 1.999398473904692e-05, + "loss": 0.5377, + "step": 487 + }, + { + "epoch": 0.04, + "learning_rate": 1.999389039306123e-05, + "loss": 0.536, + "step": 488 + }, + { + "epoch": 0.04, + "learning_rate": 1.9993795313165795e-05, + "loss": 0.5229, + "step": 489 + }, + { + "epoch": 0.04, + "learning_rate": 1.99936994993676e-05, + "loss": 0.5259, + "step": 490 + }, + { + "epoch": 0.04, + "learning_rate": 1.999360295167368e-05, + "loss": 0.5236, + "step": 491 + }, + { + "epoch": 0.04, + "learning_rate": 1.9993505670091123e-05, + "loss": 0.5245, + "step": 492 + }, + { + "epoch": 0.04, + "learning_rate": 1.999340765462708e-05, + "loss": 0.5348, + "step": 493 + }, + { + "epoch": 0.04, + "learning_rate": 1.9993308905288745e-05, + "loss": 0.5415, + "step": 494 + }, + { + "epoch": 0.04, + "learning_rate": 1.9993209422083367e-05, + "loss": 0.5391, + "step": 495 + }, + { + "epoch": 0.04, + "learning_rate": 1.999310920501825e-05, + "loss": 0.5202, + "step": 496 + }, + { + "epoch": 0.04, + "learning_rate": 1.9993008254100765e-05, + "loss": 0.5172, + "step": 497 + }, + { + "epoch": 0.04, + "learning_rate": 1.9992906569338314e-05, + "loss": 0.534, + "step": 498 + }, + { + "epoch": 0.04, + "learning_rate": 1.999280415073837e-05, + "loss": 0.5294, + "step": 499 + }, + { + "epoch": 0.04, + "learning_rate": 1.9992700998308453e-05, + "loss": 0.5486, + "step": 500 + }, + { + "epoch": 0.04, + "learning_rate": 1.9992597112056134e-05, + "loss": 0.5134, + "step": 501 + }, + { + "epoch": 0.04, + "learning_rate": 1.9992492491989045e-05, + "loss": 0.5241, + "step": 502 + }, + { + "epoch": 0.04, + "learning_rate": 1.999238713811487e-05, + "loss": 0.528, + "step": 503 + }, + { + "epoch": 0.04, + "learning_rate": 1.999228105044135e-05, + "loss": 0.5463, + "step": 504 + }, + { + "epoch": 0.04, + "learning_rate": 1.9992174228976265e-05, + "loss": 0.5119, + "step": 505 + }, + { + "epoch": 0.04, + "learning_rate": 1.999206667372747e-05, + "loss": 0.5352, + "step": 506 + }, + { + "epoch": 0.04, + "learning_rate": 1.9991958384702855e-05, + "loss": 0.5365, + "step": 507 + }, + { + "epoch": 0.04, + "learning_rate": 1.999184936191038e-05, + "loss": 0.5205, + "step": 508 + }, + { + "epoch": 0.04, + "learning_rate": 1.9991739605358042e-05, + "loss": 0.5034, + "step": 509 + }, + { + "epoch": 0.04, + "learning_rate": 1.9991629115053908e-05, + "loss": 0.5319, + "step": 510 + }, + { + "epoch": 0.04, + "learning_rate": 1.999151789100609e-05, + "loss": 0.5195, + "step": 511 + }, + { + "epoch": 0.04, + "learning_rate": 1.9991405933222758e-05, + "loss": 0.5319, + "step": 512 + }, + { + "epoch": 0.04, + "learning_rate": 1.9991293241712128e-05, + "loss": 0.5359, + "step": 513 + }, + { + "epoch": 0.04, + "learning_rate": 1.999117981648248e-05, + "loss": 0.5251, + "step": 514 + }, + { + "epoch": 0.04, + "learning_rate": 1.9991065657542146e-05, + "loss": 0.5134, + "step": 515 + }, + { + "epoch": 0.04, + "learning_rate": 1.9990950764899502e-05, + "loss": 0.5365, + "step": 516 + }, + { + "epoch": 0.04, + "learning_rate": 1.999083513856299e-05, + "loss": 0.5388, + "step": 517 + }, + { + "epoch": 0.04, + "learning_rate": 1.99907187785411e-05, + "loss": 0.5144, + "step": 518 + }, + { + "epoch": 0.04, + "learning_rate": 1.9990601684842385e-05, + "loss": 0.5203, + "step": 519 + }, + { + "epoch": 0.04, + "learning_rate": 1.9990483857475428e-05, + "loss": 0.5384, + "step": 520 + }, + { + "epoch": 0.04, + "learning_rate": 1.9990365296448892e-05, + "loss": 0.5309, + "step": 521 + }, + { + "epoch": 0.04, + "learning_rate": 1.999024600177148e-05, + "loss": 0.5405, + "step": 522 + }, + { + "epoch": 0.04, + "learning_rate": 1.9990125973451956e-05, + "loss": 0.5271, + "step": 523 + }, + { + "epoch": 0.04, + "learning_rate": 1.9990005211499137e-05, + "loss": 0.5266, + "step": 524 + }, + { + "epoch": 0.04, + "learning_rate": 1.998988371592188e-05, + "loss": 0.521, + "step": 525 + }, + { + "epoch": 0.04, + "learning_rate": 1.998976148672912e-05, + "loss": 0.5432, + "step": 526 + }, + { + "epoch": 0.04, + "learning_rate": 1.998963852392982e-05, + "loss": 0.5378, + "step": 527 + }, + { + "epoch": 0.04, + "learning_rate": 1.998951482753302e-05, + "loss": 0.5218, + "step": 528 + }, + { + "epoch": 0.04, + "learning_rate": 1.99893903975478e-05, + "loss": 0.5309, + "step": 529 + }, + { + "epoch": 0.04, + "learning_rate": 1.99892652339833e-05, + "loss": 0.5238, + "step": 530 + }, + { + "epoch": 0.04, + "learning_rate": 1.9989139336848708e-05, + "loss": 0.5364, + "step": 531 + }, + { + "epoch": 0.04, + "learning_rate": 1.9989012706153273e-05, + "loss": 0.5396, + "step": 532 + }, + { + "epoch": 0.04, + "learning_rate": 1.9988885341906292e-05, + "loss": 0.5236, + "step": 533 + }, + { + "epoch": 0.04, + "learning_rate": 1.9988757244117118e-05, + "loss": 0.5107, + "step": 534 + }, + { + "epoch": 0.04, + "learning_rate": 1.9988628412795158e-05, + "loss": 0.5068, + "step": 535 + }, + { + "epoch": 0.04, + "learning_rate": 1.9988498847949872e-05, + "loss": 0.5272, + "step": 536 + }, + { + "epoch": 0.04, + "learning_rate": 1.9988368549590778e-05, + "loss": 0.5193, + "step": 537 + }, + { + "epoch": 0.05, + "learning_rate": 1.998823751772744e-05, + "loss": 0.5314, + "step": 538 + }, + { + "epoch": 0.05, + "learning_rate": 1.9988105752369487e-05, + "loss": 0.524, + "step": 539 + }, + { + "epoch": 0.05, + "learning_rate": 1.998797325352659e-05, + "loss": 0.51, + "step": 540 + }, + { + "epoch": 0.05, + "learning_rate": 1.9987840021208477e-05, + "loss": 0.5412, + "step": 541 + }, + { + "epoch": 0.05, + "learning_rate": 1.9987706055424935e-05, + "loss": 0.5195, + "step": 542 + }, + { + "epoch": 0.05, + "learning_rate": 1.9987571356185807e-05, + "loss": 0.5251, + "step": 543 + }, + { + "epoch": 0.05, + "learning_rate": 1.9987435923500978e-05, + "loss": 0.5078, + "step": 544 + }, + { + "epoch": 0.05, + "learning_rate": 1.9987299757380393e-05, + "loss": 0.5461, + "step": 545 + }, + { + "epoch": 0.05, + "learning_rate": 1.998716285783406e-05, + "loss": 0.5278, + "step": 546 + }, + { + "epoch": 0.05, + "learning_rate": 1.998702522487202e-05, + "loss": 0.5154, + "step": 547 + }, + { + "epoch": 0.05, + "learning_rate": 1.998688685850439e-05, + "loss": 0.5246, + "step": 548 + }, + { + "epoch": 0.05, + "learning_rate": 1.998674775874133e-05, + "loss": 0.5102, + "step": 549 + }, + { + "epoch": 0.05, + "learning_rate": 1.9986607925593046e-05, + "loss": 0.5195, + "step": 550 + }, + { + "epoch": 0.05, + "learning_rate": 1.998646735906982e-05, + "loss": 0.5231, + "step": 551 + }, + { + "epoch": 0.05, + "learning_rate": 1.9986326059181965e-05, + "loss": 0.5364, + "step": 552 + }, + { + "epoch": 0.05, + "learning_rate": 1.998618402593986e-05, + "loss": 0.5223, + "step": 553 + }, + { + "epoch": 0.05, + "learning_rate": 1.9986041259353937e-05, + "loss": 0.5358, + "step": 554 + }, + { + "epoch": 0.05, + "learning_rate": 1.9985897759434677e-05, + "loss": 0.5318, + "step": 555 + }, + { + "epoch": 0.05, + "learning_rate": 1.998575352619262e-05, + "loss": 0.5339, + "step": 556 + }, + { + "epoch": 0.05, + "learning_rate": 1.9985608559638364e-05, + "loss": 0.5275, + "step": 557 + }, + { + "epoch": 0.05, + "learning_rate": 1.9985462859782544e-05, + "loss": 0.5343, + "step": 558 + }, + { + "epoch": 0.05, + "learning_rate": 1.9985316426635863e-05, + "loss": 0.5217, + "step": 559 + }, + { + "epoch": 0.05, + "learning_rate": 1.9985169260209075e-05, + "loss": 0.5284, + "step": 560 + }, + { + "epoch": 0.05, + "learning_rate": 1.998502136051299e-05, + "loss": 0.5254, + "step": 561 + }, + { + "epoch": 0.05, + "learning_rate": 1.9984872727558468e-05, + "loss": 0.5316, + "step": 562 + }, + { + "epoch": 0.05, + "learning_rate": 1.998472336135642e-05, + "loss": 0.525, + "step": 563 + }, + { + "epoch": 0.05, + "learning_rate": 1.9984573261917825e-05, + "loss": 0.5241, + "step": 564 + }, + { + "epoch": 0.05, + "learning_rate": 1.998442242925369e-05, + "loss": 0.5233, + "step": 565 + }, + { + "epoch": 0.05, + "learning_rate": 1.9984270863375105e-05, + "loss": 0.5282, + "step": 566 + }, + { + "epoch": 0.05, + "learning_rate": 1.9984118564293197e-05, + "loss": 0.5263, + "step": 567 + }, + { + "epoch": 0.05, + "learning_rate": 1.9983965532019142e-05, + "loss": 0.5201, + "step": 568 + }, + { + "epoch": 0.05, + "learning_rate": 1.998381176656419e-05, + "loss": 0.5317, + "step": 569 + }, + { + "epoch": 0.05, + "learning_rate": 1.9983657267939627e-05, + "loss": 0.5263, + "step": 570 + }, + { + "epoch": 0.05, + "learning_rate": 1.99835020361568e-05, + "loss": 0.5158, + "step": 571 + }, + { + "epoch": 0.05, + "learning_rate": 1.9983346071227107e-05, + "loss": 0.5344, + "step": 572 + }, + { + "epoch": 0.05, + "learning_rate": 1.9983189373162003e-05, + "loss": 0.5306, + "step": 573 + }, + { + "epoch": 0.05, + "learning_rate": 1.9983031941972994e-05, + "loss": 0.5402, + "step": 574 + }, + { + "epoch": 0.05, + "learning_rate": 1.998287377767164e-05, + "loss": 0.5339, + "step": 575 + }, + { + "epoch": 0.05, + "learning_rate": 1.9982714880269557e-05, + "loss": 0.5216, + "step": 576 + }, + { + "epoch": 0.05, + "learning_rate": 1.998255524977842e-05, + "loss": 0.5053, + "step": 577 + }, + { + "epoch": 0.05, + "learning_rate": 1.9982394886209943e-05, + "loss": 0.5199, + "step": 578 + }, + { + "epoch": 0.05, + "learning_rate": 1.9982233789575904e-05, + "loss": 0.5293, + "step": 579 + }, + { + "epoch": 0.05, + "learning_rate": 1.9982071959888138e-05, + "loss": 0.5093, + "step": 580 + }, + { + "epoch": 0.05, + "learning_rate": 1.998190939715852e-05, + "loss": 0.5355, + "step": 581 + }, + { + "epoch": 0.05, + "learning_rate": 1.9981746101399e-05, + "loss": 0.5191, + "step": 582 + }, + { + "epoch": 0.05, + "learning_rate": 1.998158207262156e-05, + "loss": 0.5267, + "step": 583 + }, + { + "epoch": 0.05, + "learning_rate": 1.998141731083825e-05, + "loss": 0.5117, + "step": 584 + }, + { + "epoch": 0.05, + "learning_rate": 1.9981251816061168e-05, + "loss": 0.5119, + "step": 585 + }, + { + "epoch": 0.05, + "learning_rate": 1.9981085588302468e-05, + "loss": 0.518, + "step": 586 + }, + { + "epoch": 0.05, + "learning_rate": 1.998091862757436e-05, + "loss": 0.5203, + "step": 587 + }, + { + "epoch": 0.05, + "learning_rate": 1.9980750933889098e-05, + "loss": 0.5326, + "step": 588 + }, + { + "epoch": 0.05, + "learning_rate": 1.9980582507259e-05, + "loss": 0.5318, + "step": 589 + }, + { + "epoch": 0.05, + "learning_rate": 1.998041334769644e-05, + "loss": 0.5275, + "step": 590 + }, + { + "epoch": 0.05, + "learning_rate": 1.998024345521383e-05, + "loss": 0.5346, + "step": 591 + }, + { + "epoch": 0.05, + "learning_rate": 1.9980072829823656e-05, + "loss": 0.5313, + "step": 592 + }, + { + "epoch": 0.05, + "learning_rate": 1.9979901471538442e-05, + "loss": 0.5433, + "step": 593 + }, + { + "epoch": 0.05, + "learning_rate": 1.997972938037077e-05, + "loss": 0.5223, + "step": 594 + }, + { + "epoch": 0.05, + "learning_rate": 1.9979556556333283e-05, + "loss": 0.5244, + "step": 595 + }, + { + "epoch": 0.05, + "learning_rate": 1.9979382999438672e-05, + "loss": 0.5391, + "step": 596 + }, + { + "epoch": 0.05, + "learning_rate": 1.997920870969968e-05, + "loss": 0.5366, + "step": 597 + }, + { + "epoch": 0.05, + "learning_rate": 1.997903368712911e-05, + "loss": 0.518, + "step": 598 + }, + { + "epoch": 0.05, + "learning_rate": 1.9978857931739805e-05, + "loss": 0.5125, + "step": 599 + }, + { + "epoch": 0.05, + "learning_rate": 1.9978681443544687e-05, + "loss": 0.5062, + "step": 600 + }, + { + "epoch": 0.05, + "learning_rate": 1.9978504222556704e-05, + "loss": 0.51, + "step": 601 + }, + { + "epoch": 0.05, + "learning_rate": 1.9978326268788873e-05, + "loss": 0.5224, + "step": 602 + }, + { + "epoch": 0.05, + "learning_rate": 1.9978147582254266e-05, + "loss": 0.5183, + "step": 603 + }, + { + "epoch": 0.05, + "learning_rate": 1.9977968162966e-05, + "loss": 0.529, + "step": 604 + }, + { + "epoch": 0.05, + "learning_rate": 1.997778801093726e-05, + "loss": 0.5163, + "step": 605 + }, + { + "epoch": 0.05, + "learning_rate": 1.9977607126181264e-05, + "loss": 0.508, + "step": 606 + }, + { + "epoch": 0.05, + "learning_rate": 1.9977425508711303e-05, + "loss": 0.5383, + "step": 607 + }, + { + "epoch": 0.05, + "learning_rate": 1.997724315854071e-05, + "loss": 0.5161, + "step": 608 + }, + { + "epoch": 0.05, + "learning_rate": 1.9977060075682878e-05, + "loss": 0.5294, + "step": 609 + }, + { + "epoch": 0.05, + "learning_rate": 1.997687626015125e-05, + "loss": 0.5113, + "step": 610 + }, + { + "epoch": 0.05, + "learning_rate": 1.997669171195933e-05, + "loss": 0.525, + "step": 611 + }, + { + "epoch": 0.05, + "learning_rate": 1.9976506431120665e-05, + "loss": 0.5313, + "step": 612 + }, + { + "epoch": 0.05, + "learning_rate": 1.9976320417648868e-05, + "loss": 0.5248, + "step": 613 + }, + { + "epoch": 0.05, + "learning_rate": 1.9976133671557587e-05, + "loss": 0.537, + "step": 614 + }, + { + "epoch": 0.05, + "learning_rate": 1.9975946192860544e-05, + "loss": 0.5232, + "step": 615 + }, + { + "epoch": 0.05, + "learning_rate": 1.9975757981571512e-05, + "loss": 0.5132, + "step": 616 + }, + { + "epoch": 0.05, + "learning_rate": 1.99755690377043e-05, + "loss": 0.531, + "step": 617 + }, + { + "epoch": 0.05, + "learning_rate": 1.997537936127279e-05, + "loss": 0.532, + "step": 618 + }, + { + "epoch": 0.05, + "learning_rate": 1.9975188952290915e-05, + "loss": 0.5399, + "step": 619 + }, + { + "epoch": 0.05, + "learning_rate": 1.997499781077265e-05, + "loss": 0.5195, + "step": 620 + }, + { + "epoch": 0.05, + "learning_rate": 1.997480593673203e-05, + "loss": 0.5213, + "step": 621 + }, + { + "epoch": 0.05, + "learning_rate": 1.9974613330183156e-05, + "loss": 0.5198, + "step": 622 + }, + { + "epoch": 0.05, + "learning_rate": 1.997441999114017e-05, + "loss": 0.5242, + "step": 623 + }, + { + "epoch": 0.05, + "learning_rate": 1.9974225919617258e-05, + "loss": 0.5376, + "step": 624 + }, + { + "epoch": 0.05, + "learning_rate": 1.9974031115628688e-05, + "loss": 0.521, + "step": 625 + }, + { + "epoch": 0.05, + "learning_rate": 1.9973835579188753e-05, + "loss": 0.5179, + "step": 626 + }, + { + "epoch": 0.05, + "learning_rate": 1.997363931031182e-05, + "loss": 0.5341, + "step": 627 + }, + { + "epoch": 0.05, + "learning_rate": 1.9973442309012296e-05, + "loss": 0.4995, + "step": 628 + }, + { + "epoch": 0.05, + "learning_rate": 1.9973244575304657e-05, + "loss": 0.5421, + "step": 629 + }, + { + "epoch": 0.05, + "learning_rate": 1.9973046109203414e-05, + "loss": 0.5164, + "step": 630 + }, + { + "epoch": 0.05, + "learning_rate": 1.9972846910723146e-05, + "loss": 0.5236, + "step": 631 + }, + { + "epoch": 0.05, + "learning_rate": 1.9972646979878483e-05, + "loss": 0.5341, + "step": 632 + }, + { + "epoch": 0.05, + "learning_rate": 1.9972446316684106e-05, + "loss": 0.5337, + "step": 633 + }, + { + "epoch": 0.05, + "learning_rate": 1.9972244921154746e-05, + "loss": 0.5226, + "step": 634 + }, + { + "epoch": 0.05, + "learning_rate": 1.9972042793305196e-05, + "loss": 0.5177, + "step": 635 + }, + { + "epoch": 0.05, + "learning_rate": 1.9971839933150307e-05, + "loss": 0.5229, + "step": 636 + }, + { + "epoch": 0.05, + "learning_rate": 1.997163634070496e-05, + "loss": 0.513, + "step": 637 + }, + { + "epoch": 0.05, + "learning_rate": 1.9971432015984126e-05, + "loss": 0.5055, + "step": 638 + }, + { + "epoch": 0.05, + "learning_rate": 1.9971226959002796e-05, + "loss": 0.4982, + "step": 639 + }, + { + "epoch": 0.05, + "learning_rate": 1.9971021169776024e-05, + "loss": 0.5206, + "step": 640 + }, + { + "epoch": 0.05, + "learning_rate": 1.9970814648318937e-05, + "loss": 0.4946, + "step": 641 + }, + { + "epoch": 0.05, + "learning_rate": 1.997060739464669e-05, + "loss": 0.5367, + "step": 642 + }, + { + "epoch": 0.05, + "learning_rate": 1.997039940877451e-05, + "loss": 0.5368, + "step": 643 + }, + { + "epoch": 0.05, + "learning_rate": 1.997019069071767e-05, + "loss": 0.5131, + "step": 644 + }, + { + "epoch": 0.05, + "learning_rate": 1.996998124049149e-05, + "loss": 0.5253, + "step": 645 + }, + { + "epoch": 0.05, + "learning_rate": 1.9969771058111357e-05, + "loss": 0.5273, + "step": 646 + }, + { + "epoch": 0.05, + "learning_rate": 1.9969560143592705e-05, + "loss": 0.5247, + "step": 647 + }, + { + "epoch": 0.05, + "learning_rate": 1.996934849695102e-05, + "loss": 0.5292, + "step": 648 + }, + { + "epoch": 0.05, + "learning_rate": 1.9969136118201852e-05, + "loss": 0.5262, + "step": 649 + }, + { + "epoch": 0.05, + "learning_rate": 1.9968923007360788e-05, + "loss": 0.5031, + "step": 650 + }, + { + "epoch": 0.05, + "learning_rate": 1.9968709164443483e-05, + "loss": 0.523, + "step": 651 + }, + { + "epoch": 0.05, + "learning_rate": 1.9968494589465645e-05, + "loss": 0.5326, + "step": 652 + }, + { + "epoch": 0.05, + "learning_rate": 1.996827928244302e-05, + "loss": 0.4976, + "step": 653 + }, + { + "epoch": 0.05, + "learning_rate": 1.996806324339143e-05, + "loss": 0.5387, + "step": 654 + }, + { + "epoch": 0.05, + "learning_rate": 1.996784647232673e-05, + "loss": 0.5141, + "step": 655 + }, + { + "epoch": 0.05, + "learning_rate": 1.996762896926485e-05, + "loss": 0.5372, + "step": 656 + }, + { + "epoch": 0.05, + "learning_rate": 1.9967410734221757e-05, + "loss": 0.5209, + "step": 657 + }, + { + "epoch": 0.06, + "learning_rate": 1.9967191767213475e-05, + "loss": 0.5474, + "step": 658 + }, + { + "epoch": 0.06, + "learning_rate": 1.9966972068256087e-05, + "loss": 0.5331, + "step": 659 + }, + { + "epoch": 0.06, + "learning_rate": 1.9966751637365726e-05, + "loss": 0.513, + "step": 660 + }, + { + "epoch": 0.06, + "learning_rate": 1.996653047455858e-05, + "loss": 0.5238, + "step": 661 + }, + { + "epoch": 0.06, + "learning_rate": 1.996630857985089e-05, + "loss": 0.5155, + "step": 662 + }, + { + "epoch": 0.06, + "learning_rate": 1.996608595325895e-05, + "loss": 0.5119, + "step": 663 + }, + { + "epoch": 0.06, + "learning_rate": 1.996586259479911e-05, + "loss": 0.5187, + "step": 664 + }, + { + "epoch": 0.06, + "learning_rate": 1.9965638504487773e-05, + "loss": 0.5293, + "step": 665 + }, + { + "epoch": 0.06, + "learning_rate": 1.9965413682341393e-05, + "loss": 0.5285, + "step": 666 + }, + { + "epoch": 0.06, + "learning_rate": 1.996518812837648e-05, + "loss": 0.5239, + "step": 667 + }, + { + "epoch": 0.06, + "learning_rate": 1.9964961842609602e-05, + "loss": 0.524, + "step": 668 + }, + { + "epoch": 0.06, + "learning_rate": 1.9964734825057374e-05, + "loss": 0.5324, + "step": 669 + }, + { + "epoch": 0.06, + "learning_rate": 1.9964507075736463e-05, + "loss": 0.5108, + "step": 670 + }, + { + "epoch": 0.06, + "learning_rate": 1.99642785946636e-05, + "loss": 0.5108, + "step": 671 + }, + { + "epoch": 0.06, + "learning_rate": 1.9964049381855566e-05, + "loss": 0.5037, + "step": 672 + }, + { + "epoch": 0.06, + "learning_rate": 1.9963819437329184e-05, + "loss": 0.5381, + "step": 673 + }, + { + "epoch": 0.06, + "learning_rate": 1.9963588761101347e-05, + "loss": 0.5213, + "step": 674 + }, + { + "epoch": 0.06, + "learning_rate": 1.9963357353188993e-05, + "loss": 0.5213, + "step": 675 + }, + { + "epoch": 0.06, + "learning_rate": 1.9963125213609113e-05, + "loss": 0.5493, + "step": 676 + }, + { + "epoch": 0.06, + "learning_rate": 1.996289234237876e-05, + "loss": 0.5336, + "step": 677 + }, + { + "epoch": 0.06, + "learning_rate": 1.996265873951503e-05, + "loss": 0.5166, + "step": 678 + }, + { + "epoch": 0.06, + "learning_rate": 1.996242440503508e-05, + "loss": 0.5261, + "step": 679 + }, + { + "epoch": 0.06, + "learning_rate": 1.9962189338956124e-05, + "loss": 0.516, + "step": 680 + }, + { + "epoch": 0.06, + "learning_rate": 1.9961953541295413e-05, + "loss": 0.5128, + "step": 681 + }, + { + "epoch": 0.06, + "learning_rate": 1.9961717012070273e-05, + "loss": 0.5057, + "step": 682 + }, + { + "epoch": 0.06, + "learning_rate": 1.9961479751298066e-05, + "loss": 0.514, + "step": 683 + }, + { + "epoch": 0.06, + "learning_rate": 1.996124175899622e-05, + "loss": 0.5306, + "step": 684 + }, + { + "epoch": 0.06, + "learning_rate": 1.996100303518221e-05, + "loss": 0.5231, + "step": 685 + }, + { + "epoch": 0.06, + "learning_rate": 1.9960763579873568e-05, + "loss": 0.5202, + "step": 686 + }, + { + "epoch": 0.06, + "learning_rate": 1.996052339308788e-05, + "loss": 0.5057, + "step": 687 + }, + { + "epoch": 0.06, + "learning_rate": 1.9960282474842784e-05, + "loss": 0.5059, + "step": 688 + }, + { + "epoch": 0.06, + "learning_rate": 1.9960040825155968e-05, + "loss": 0.5282, + "step": 689 + }, + { + "epoch": 0.06, + "learning_rate": 1.9959798444045184e-05, + "loss": 0.5417, + "step": 690 + }, + { + "epoch": 0.06, + "learning_rate": 1.9959555331528226e-05, + "loss": 0.5122, + "step": 691 + }, + { + "epoch": 0.06, + "learning_rate": 1.995931148762295e-05, + "loss": 0.5125, + "step": 692 + }, + { + "epoch": 0.06, + "learning_rate": 1.9959066912347262e-05, + "loss": 0.5131, + "step": 693 + }, + { + "epoch": 0.06, + "learning_rate": 1.9958821605719122e-05, + "loss": 0.5258, + "step": 694 + }, + { + "epoch": 0.06, + "learning_rate": 1.9958575567756546e-05, + "loss": 0.5234, + "step": 695 + }, + { + "epoch": 0.06, + "learning_rate": 1.9958328798477602e-05, + "loss": 0.5072, + "step": 696 + }, + { + "epoch": 0.06, + "learning_rate": 1.9958081297900413e-05, + "loss": 0.5149, + "step": 697 + }, + { + "epoch": 0.06, + "learning_rate": 1.995783306604315e-05, + "loss": 0.5273, + "step": 698 + }, + { + "epoch": 0.06, + "learning_rate": 1.995758410292404e-05, + "loss": 0.5115, + "step": 699 + }, + { + "epoch": 0.06, + "learning_rate": 1.9957334408561374e-05, + "loss": 0.5219, + "step": 700 + }, + { + "epoch": 0.06, + "learning_rate": 1.9957083982973488e-05, + "loss": 0.5097, + "step": 701 + }, + { + "epoch": 0.06, + "learning_rate": 1.9956832826178765e-05, + "loss": 0.5104, + "step": 702 + }, + { + "epoch": 0.06, + "learning_rate": 1.9956580938195654e-05, + "loss": 0.5237, + "step": 703 + }, + { + "epoch": 0.06, + "learning_rate": 1.9956328319042648e-05, + "loss": 0.519, + "step": 704 + }, + { + "epoch": 0.06, + "learning_rate": 1.9956074968738306e-05, + "loss": 0.5404, + "step": 705 + }, + { + "epoch": 0.06, + "learning_rate": 1.9955820887301227e-05, + "loss": 0.5104, + "step": 706 + }, + { + "epoch": 0.06, + "learning_rate": 1.995556607475007e-05, + "loss": 0.5055, + "step": 707 + }, + { + "epoch": 0.06, + "learning_rate": 1.9955310531103552e-05, + "loss": 0.5312, + "step": 708 + }, + { + "epoch": 0.06, + "learning_rate": 1.9955054256380436e-05, + "loss": 0.5138, + "step": 709 + }, + { + "epoch": 0.06, + "learning_rate": 1.995479725059954e-05, + "loss": 0.5236, + "step": 710 + }, + { + "epoch": 0.06, + "learning_rate": 1.9954539513779737e-05, + "loss": 0.5212, + "step": 711 + }, + { + "epoch": 0.06, + "learning_rate": 1.9954281045939958e-05, + "loss": 0.5143, + "step": 712 + }, + { + "epoch": 0.06, + "learning_rate": 1.995402184709918e-05, + "loss": 0.5225, + "step": 713 + }, + { + "epoch": 0.06, + "learning_rate": 1.9953761917276443e-05, + "loss": 0.5255, + "step": 714 + }, + { + "epoch": 0.06, + "learning_rate": 1.995350125649083e-05, + "loss": 0.5169, + "step": 715 + }, + { + "epoch": 0.06, + "learning_rate": 1.9953239864761486e-05, + "loss": 0.5122, + "step": 716 + }, + { + "epoch": 0.06, + "learning_rate": 1.9952977742107606e-05, + "loss": 0.5222, + "step": 717 + }, + { + "epoch": 0.06, + "learning_rate": 1.9952714888548432e-05, + "loss": 0.5347, + "step": 718 + }, + { + "epoch": 0.06, + "learning_rate": 1.9952451304103278e-05, + "loss": 0.5194, + "step": 719 + }, + { + "epoch": 0.06, + "learning_rate": 1.9952186988791494e-05, + "loss": 0.5115, + "step": 720 + }, + { + "epoch": 0.06, + "learning_rate": 1.9951921942632493e-05, + "loss": 0.521, + "step": 721 + }, + { + "epoch": 0.06, + "learning_rate": 1.9951656165645736e-05, + "loss": 0.5169, + "step": 722 + }, + { + "epoch": 0.06, + "learning_rate": 1.9951389657850744e-05, + "loss": 0.5083, + "step": 723 + }, + { + "epoch": 0.06, + "learning_rate": 1.9951122419267085e-05, + "loss": 0.5222, + "step": 724 + }, + { + "epoch": 0.06, + "learning_rate": 1.9950854449914384e-05, + "loss": 0.5328, + "step": 725 + }, + { + "epoch": 0.06, + "learning_rate": 1.9950585749812326e-05, + "loss": 0.502, + "step": 726 + }, + { + "epoch": 0.06, + "learning_rate": 1.9950316318980632e-05, + "loss": 0.5185, + "step": 727 + }, + { + "epoch": 0.06, + "learning_rate": 1.99500461574391e-05, + "loss": 0.528, + "step": 728 + }, + { + "epoch": 0.06, + "learning_rate": 1.994977526520756e-05, + "loss": 0.5134, + "step": 729 + }, + { + "epoch": 0.06, + "learning_rate": 1.9949503642305908e-05, + "loss": 0.5163, + "step": 730 + }, + { + "epoch": 0.06, + "learning_rate": 1.9949231288754094e-05, + "loss": 0.5277, + "step": 731 + }, + { + "epoch": 0.06, + "learning_rate": 1.9948958204572114e-05, + "loss": 0.5142, + "step": 732 + }, + { + "epoch": 0.06, + "learning_rate": 1.9948684389780026e-05, + "loss": 0.5133, + "step": 733 + }, + { + "epoch": 0.06, + "learning_rate": 1.9948409844397934e-05, + "loss": 0.5184, + "step": 734 + }, + { + "epoch": 0.06, + "learning_rate": 1.9948134568446006e-05, + "loss": 0.4933, + "step": 735 + }, + { + "epoch": 0.06, + "learning_rate": 1.994785856194445e-05, + "loss": 0.5337, + "step": 736 + }, + { + "epoch": 0.06, + "learning_rate": 1.9947581824913536e-05, + "loss": 0.5312, + "step": 737 + }, + { + "epoch": 0.06, + "learning_rate": 1.994730435737359e-05, + "loss": 0.5064, + "step": 738 + }, + { + "epoch": 0.06, + "learning_rate": 1.9947026159344985e-05, + "loss": 0.5289, + "step": 739 + }, + { + "epoch": 0.06, + "learning_rate": 1.9946747230848152e-05, + "loss": 0.5196, + "step": 740 + }, + { + "epoch": 0.06, + "learning_rate": 1.994646757190357e-05, + "loss": 0.5098, + "step": 741 + }, + { + "epoch": 0.06, + "learning_rate": 1.9946187182531785e-05, + "loss": 0.5362, + "step": 742 + }, + { + "epoch": 0.06, + "learning_rate": 1.9945906062753383e-05, + "loss": 0.5438, + "step": 743 + }, + { + "epoch": 0.06, + "learning_rate": 1.9945624212589007e-05, + "loss": 0.5376, + "step": 744 + }, + { + "epoch": 0.06, + "learning_rate": 1.9945341632059356e-05, + "loss": 0.508, + "step": 745 + }, + { + "epoch": 0.06, + "learning_rate": 1.9945058321185175e-05, + "loss": 0.5277, + "step": 746 + }, + { + "epoch": 0.06, + "learning_rate": 1.994477427998728e-05, + "loss": 0.528, + "step": 747 + }, + { + "epoch": 0.06, + "learning_rate": 1.9944489508486528e-05, + "loss": 0.515, + "step": 748 + }, + { + "epoch": 0.06, + "learning_rate": 1.9944204006703828e-05, + "loss": 0.5223, + "step": 749 + }, + { + "epoch": 0.06, + "learning_rate": 1.9943917774660145e-05, + "loss": 0.5251, + "step": 750 + }, + { + "epoch": 0.06, + "learning_rate": 1.99436308123765e-05, + "loss": 0.51, + "step": 751 + }, + { + "epoch": 0.06, + "learning_rate": 1.9943343119873966e-05, + "loss": 0.5188, + "step": 752 + }, + { + "epoch": 0.06, + "learning_rate": 1.9943054697173676e-05, + "loss": 0.5078, + "step": 753 + }, + { + "epoch": 0.06, + "learning_rate": 1.99427655442968e-05, + "loss": 0.505, + "step": 754 + }, + { + "epoch": 0.06, + "learning_rate": 1.994247566126458e-05, + "loss": 0.5079, + "step": 755 + }, + { + "epoch": 0.06, + "learning_rate": 1.99421850480983e-05, + "loss": 0.521, + "step": 756 + }, + { + "epoch": 0.06, + "learning_rate": 1.9941893704819307e-05, + "loss": 0.5151, + "step": 757 + }, + { + "epoch": 0.06, + "learning_rate": 1.9941601631448986e-05, + "loss": 0.5118, + "step": 758 + }, + { + "epoch": 0.06, + "learning_rate": 1.9941308828008794e-05, + "loss": 0.5173, + "step": 759 + }, + { + "epoch": 0.06, + "learning_rate": 1.994101529452023e-05, + "loss": 0.5219, + "step": 760 + }, + { + "epoch": 0.06, + "learning_rate": 1.9940721031004853e-05, + "loss": 0.5182, + "step": 761 + }, + { + "epoch": 0.06, + "learning_rate": 1.9940426037484268e-05, + "loss": 0.5159, + "step": 762 + }, + { + "epoch": 0.06, + "learning_rate": 1.994013031398014e-05, + "loss": 0.5232, + "step": 763 + }, + { + "epoch": 0.06, + "learning_rate": 1.9939833860514187e-05, + "loss": 0.5113, + "step": 764 + }, + { + "epoch": 0.06, + "learning_rate": 1.9939536677108176e-05, + "loss": 0.5284, + "step": 765 + }, + { + "epoch": 0.06, + "learning_rate": 1.993923876378393e-05, + "loss": 0.5181, + "step": 766 + }, + { + "epoch": 0.06, + "learning_rate": 1.993894012056334e-05, + "loss": 0.5263, + "step": 767 + }, + { + "epoch": 0.06, + "learning_rate": 1.993864074746832e-05, + "loss": 0.508, + "step": 768 + }, + { + "epoch": 0.06, + "learning_rate": 1.993834064452086e-05, + "loss": 0.5173, + "step": 769 + }, + { + "epoch": 0.06, + "learning_rate": 1.9938039811743e-05, + "loss": 0.5273, + "step": 770 + }, + { + "epoch": 0.06, + "learning_rate": 1.9937738249156836e-05, + "loss": 0.5169, + "step": 771 + }, + { + "epoch": 0.06, + "learning_rate": 1.9937435956784506e-05, + "loss": 0.5033, + "step": 772 + }, + { + "epoch": 0.06, + "learning_rate": 1.9937132934648213e-05, + "loss": 0.4927, + "step": 773 + }, + { + "epoch": 0.06, + "learning_rate": 1.993682918277021e-05, + "loss": 0.5177, + "step": 774 + }, + { + "epoch": 0.06, + "learning_rate": 1.99365247011728e-05, + "loss": 0.51, + "step": 775 + }, + { + "epoch": 0.06, + "learning_rate": 1.9936219489878343e-05, + "loss": 0.5046, + "step": 776 + }, + { + "epoch": 0.07, + "learning_rate": 1.9935913548909258e-05, + "loss": 0.5577, + "step": 777 + }, + { + "epoch": 0.07, + "learning_rate": 1.9935606878288008e-05, + "loss": 0.5247, + "step": 778 + }, + { + "epoch": 0.07, + "learning_rate": 1.9935299478037114e-05, + "loss": 0.5033, + "step": 779 + }, + { + "epoch": 0.07, + "learning_rate": 1.993499134817915e-05, + "loss": 0.5286, + "step": 780 + }, + { + "epoch": 0.07, + "learning_rate": 1.9934682488736745e-05, + "loss": 0.5342, + "step": 781 + }, + { + "epoch": 0.07, + "learning_rate": 1.993437289973258e-05, + "loss": 0.5145, + "step": 782 + }, + { + "epoch": 0.07, + "learning_rate": 1.993406258118939e-05, + "loss": 0.5139, + "step": 783 + }, + { + "epoch": 0.07, + "learning_rate": 1.993375153312996e-05, + "loss": 0.5159, + "step": 784 + }, + { + "epoch": 0.07, + "learning_rate": 1.9933439755577134e-05, + "loss": 0.506, + "step": 785 + }, + { + "epoch": 0.07, + "learning_rate": 1.9933127248553813e-05, + "loss": 0.5219, + "step": 786 + }, + { + "epoch": 0.07, + "learning_rate": 1.993281401208294e-05, + "loss": 0.5383, + "step": 787 + }, + { + "epoch": 0.07, + "learning_rate": 1.993250004618752e-05, + "loss": 0.5096, + "step": 788 + }, + { + "epoch": 0.07, + "learning_rate": 1.9932185350890606e-05, + "loss": 0.5199, + "step": 789 + }, + { + "epoch": 0.07, + "learning_rate": 1.9931869926215315e-05, + "loss": 0.5117, + "step": 790 + }, + { + "epoch": 0.07, + "learning_rate": 1.9931553772184805e-05, + "loss": 0.5312, + "step": 791 + }, + { + "epoch": 0.07, + "learning_rate": 1.9931236888822295e-05, + "loss": 0.5135, + "step": 792 + }, + { + "epoch": 0.07, + "learning_rate": 1.993091927615105e-05, + "loss": 0.5282, + "step": 793 + }, + { + "epoch": 0.07, + "learning_rate": 1.9930600934194405e-05, + "loss": 0.5438, + "step": 794 + }, + { + "epoch": 0.07, + "learning_rate": 1.993028186297573e-05, + "loss": 0.5087, + "step": 795 + }, + { + "epoch": 0.07, + "learning_rate": 1.9929962062518458e-05, + "loss": 0.5244, + "step": 796 + }, + { + "epoch": 0.07, + "learning_rate": 1.9929641532846074e-05, + "loss": 0.5054, + "step": 797 + }, + { + "epoch": 0.07, + "learning_rate": 1.992932027398212e-05, + "loss": 0.5353, + "step": 798 + }, + { + "epoch": 0.07, + "learning_rate": 1.992899828595018e-05, + "loss": 0.5065, + "step": 799 + }, + { + "epoch": 0.07, + "learning_rate": 1.9928675568773906e-05, + "loss": 0.5293, + "step": 800 + }, + { + "epoch": 0.07, + "learning_rate": 1.992835212247699e-05, + "loss": 0.5097, + "step": 801 + }, + { + "epoch": 0.07, + "learning_rate": 1.9928027947083195e-05, + "loss": 0.5242, + "step": 802 + }, + { + "epoch": 0.07, + "learning_rate": 1.992770304261632e-05, + "loss": 0.5199, + "step": 803 + }, + { + "epoch": 0.07, + "learning_rate": 1.9927377409100222e-05, + "loss": 0.5333, + "step": 804 + }, + { + "epoch": 0.07, + "learning_rate": 1.992705104655882e-05, + "loss": 0.5338, + "step": 805 + }, + { + "epoch": 0.07, + "learning_rate": 1.992672395501608e-05, + "loss": 0.5206, + "step": 806 + }, + { + "epoch": 0.07, + "learning_rate": 1.992639613449602e-05, + "loss": 0.5262, + "step": 807 + }, + { + "epoch": 0.07, + "learning_rate": 1.9926067585022718e-05, + "loss": 0.5317, + "step": 808 + }, + { + "epoch": 0.07, + "learning_rate": 1.9925738306620294e-05, + "loss": 0.5414, + "step": 809 + }, + { + "epoch": 0.07, + "learning_rate": 1.9925408299312935e-05, + "loss": 0.5112, + "step": 810 + }, + { + "epoch": 0.07, + "learning_rate": 1.992507756312487e-05, + "loss": 0.5168, + "step": 811 + }, + { + "epoch": 0.07, + "learning_rate": 1.99247460980804e-05, + "loss": 0.5242, + "step": 812 + }, + { + "epoch": 0.07, + "learning_rate": 1.9924413904203847e-05, + "loss": 0.51, + "step": 813 + }, + { + "epoch": 0.07, + "learning_rate": 1.992408098151962e-05, + "loss": 0.5168, + "step": 814 + }, + { + "epoch": 0.07, + "learning_rate": 1.992374733005216e-05, + "loss": 0.5223, + "step": 815 + }, + { + "epoch": 0.07, + "learning_rate": 1.9923412949825975e-05, + "loss": 0.5066, + "step": 816 + }, + { + "epoch": 0.07, + "learning_rate": 1.9923077840865615e-05, + "loss": 0.5063, + "step": 817 + }, + { + "epoch": 0.07, + "learning_rate": 1.9922742003195696e-05, + "loss": 0.5171, + "step": 818 + }, + { + "epoch": 0.07, + "learning_rate": 1.9922405436840872e-05, + "loss": 0.5278, + "step": 819 + }, + { + "epoch": 0.07, + "learning_rate": 1.9922068141825864e-05, + "loss": 0.5183, + "step": 820 + }, + { + "epoch": 0.07, + "learning_rate": 1.9921730118175443e-05, + "loss": 0.5055, + "step": 821 + }, + { + "epoch": 0.07, + "learning_rate": 1.9921391365914426e-05, + "loss": 0.5416, + "step": 822 + }, + { + "epoch": 0.07, + "learning_rate": 1.9921051885067695e-05, + "loss": 0.5098, + "step": 823 + }, + { + "epoch": 0.07, + "learning_rate": 1.9920711675660178e-05, + "loss": 0.543, + "step": 824 + }, + { + "epoch": 0.07, + "learning_rate": 1.992037073771686e-05, + "loss": 0.5269, + "step": 825 + }, + { + "epoch": 0.07, + "learning_rate": 1.9920029071262778e-05, + "loss": 0.4967, + "step": 826 + }, + { + "epoch": 0.07, + "learning_rate": 1.9919686676323015e-05, + "loss": 0.5036, + "step": 827 + }, + { + "epoch": 0.07, + "learning_rate": 1.9919343552922727e-05, + "loss": 0.518, + "step": 828 + }, + { + "epoch": 0.07, + "learning_rate": 1.9918999701087104e-05, + "loss": 0.5273, + "step": 829 + }, + { + "epoch": 0.07, + "learning_rate": 1.9918655120841403e-05, + "loss": 0.5271, + "step": 830 + }, + { + "epoch": 0.07, + "learning_rate": 1.991830981221092e-05, + "loss": 0.5263, + "step": 831 + }, + { + "epoch": 0.07, + "learning_rate": 1.991796377522102e-05, + "loss": 0.5187, + "step": 832 + }, + { + "epoch": 0.07, + "learning_rate": 1.9917617009897113e-05, + "loss": 0.5042, + "step": 833 + }, + { + "epoch": 0.07, + "learning_rate": 1.9917269516264662e-05, + "loss": 0.5248, + "step": 834 + }, + { + "epoch": 0.07, + "learning_rate": 1.9916921294349187e-05, + "loss": 0.4992, + "step": 835 + }, + { + "epoch": 0.07, + "learning_rate": 1.9916572344176258e-05, + "loss": 0.5347, + "step": 836 + }, + { + "epoch": 0.07, + "learning_rate": 1.9916222665771506e-05, + "loss": 0.5343, + "step": 837 + }, + { + "epoch": 0.07, + "learning_rate": 1.9915872259160603e-05, + "loss": 0.511, + "step": 838 + }, + { + "epoch": 0.07, + "learning_rate": 1.991552112436929e-05, + "loss": 0.5374, + "step": 839 + }, + { + "epoch": 0.07, + "learning_rate": 1.991516926142334e-05, + "loss": 0.5074, + "step": 840 + }, + { + "epoch": 0.07, + "learning_rate": 1.99148166703486e-05, + "loss": 0.5287, + "step": 841 + }, + { + "epoch": 0.07, + "learning_rate": 1.991446335117097e-05, + "loss": 0.5089, + "step": 842 + }, + { + "epoch": 0.07, + "learning_rate": 1.991410930391638e-05, + "loss": 0.5148, + "step": 843 + }, + { + "epoch": 0.07, + "learning_rate": 1.9913754528610846e-05, + "loss": 0.5282, + "step": 844 + }, + { + "epoch": 0.07, + "learning_rate": 1.991339902528041e-05, + "loss": 0.5093, + "step": 845 + }, + { + "epoch": 0.07, + "learning_rate": 1.9913042793951184e-05, + "loss": 0.5292, + "step": 846 + }, + { + "epoch": 0.07, + "learning_rate": 1.9912685834649324e-05, + "loss": 0.5164, + "step": 847 + }, + { + "epoch": 0.07, + "learning_rate": 1.991232814740105e-05, + "loss": 0.5011, + "step": 848 + }, + { + "epoch": 0.07, + "learning_rate": 1.991196973223262e-05, + "loss": 0.5238, + "step": 849 + }, + { + "epoch": 0.07, + "learning_rate": 1.9911610589170363e-05, + "loss": 0.5173, + "step": 850 + }, + { + "epoch": 0.07, + "learning_rate": 1.9911250718240653e-05, + "loss": 0.5082, + "step": 851 + }, + { + "epoch": 0.07, + "learning_rate": 1.991089011946991e-05, + "loss": 0.5063, + "step": 852 + }, + { + "epoch": 0.07, + "learning_rate": 1.991052879288462e-05, + "loss": 0.5203, + "step": 853 + }, + { + "epoch": 0.07, + "learning_rate": 1.9910166738511315e-05, + "loss": 0.5008, + "step": 854 + }, + { + "epoch": 0.07, + "learning_rate": 1.9909803956376588e-05, + "loss": 0.5135, + "step": 855 + }, + { + "epoch": 0.07, + "learning_rate": 1.9909440446507074e-05, + "loss": 0.5087, + "step": 856 + }, + { + "epoch": 0.07, + "learning_rate": 1.990907620892947e-05, + "loss": 0.5175, + "step": 857 + }, + { + "epoch": 0.07, + "learning_rate": 1.9908711243670526e-05, + "loss": 0.5173, + "step": 858 + }, + { + "epoch": 0.07, + "learning_rate": 1.990834555075704e-05, + "loss": 0.5081, + "step": 859 + }, + { + "epoch": 0.07, + "learning_rate": 1.9907979130215868e-05, + "loss": 0.517, + "step": 860 + }, + { + "epoch": 0.07, + "learning_rate": 1.990761198207392e-05, + "loss": 0.5276, + "step": 861 + }, + { + "epoch": 0.07, + "learning_rate": 1.9907244106358158e-05, + "loss": 0.5121, + "step": 862 + }, + { + "epoch": 0.07, + "learning_rate": 1.9906875503095594e-05, + "loss": 0.5236, + "step": 863 + }, + { + "epoch": 0.07, + "learning_rate": 1.99065061723133e-05, + "loss": 0.524, + "step": 864 + }, + { + "epoch": 0.07, + "learning_rate": 1.9906136114038398e-05, + "loss": 0.5112, + "step": 865 + }, + { + "epoch": 0.07, + "learning_rate": 1.990576532829806e-05, + "loss": 0.5318, + "step": 866 + }, + { + "epoch": 0.07, + "learning_rate": 1.990539381511952e-05, + "loss": 0.5188, + "step": 867 + }, + { + "epoch": 0.07, + "learning_rate": 1.9905021574530055e-05, + "loss": 0.5064, + "step": 868 + }, + { + "epoch": 0.07, + "learning_rate": 1.9904648606557007e-05, + "loss": 0.528, + "step": 869 + }, + { + "epoch": 0.07, + "learning_rate": 1.9904274911227762e-05, + "loss": 0.5179, + "step": 870 + }, + { + "epoch": 0.07, + "learning_rate": 1.990390048856976e-05, + "loss": 0.5177, + "step": 871 + }, + { + "epoch": 0.07, + "learning_rate": 1.99035253386105e-05, + "loss": 0.516, + "step": 872 + }, + { + "epoch": 0.07, + "learning_rate": 1.9903149461377532e-05, + "loss": 0.525, + "step": 873 + }, + { + "epoch": 0.07, + "learning_rate": 1.9902772856898457e-05, + "loss": 0.5407, + "step": 874 + }, + { + "epoch": 0.07, + "learning_rate": 1.9902395525200933e-05, + "loss": 0.5232, + "step": 875 + }, + { + "epoch": 0.07, + "learning_rate": 1.9902017466312668e-05, + "loss": 0.5302, + "step": 876 + }, + { + "epoch": 0.07, + "learning_rate": 1.9901638680261426e-05, + "loss": 0.5218, + "step": 877 + }, + { + "epoch": 0.07, + "learning_rate": 1.9901259167075023e-05, + "loss": 0.5213, + "step": 878 + }, + { + "epoch": 0.07, + "learning_rate": 1.9900878926781327e-05, + "loss": 0.5346, + "step": 879 + }, + { + "epoch": 0.07, + "learning_rate": 1.990049795940827e-05, + "loss": 0.5155, + "step": 880 + }, + { + "epoch": 0.07, + "learning_rate": 1.9900116264983815e-05, + "loss": 0.523, + "step": 881 + }, + { + "epoch": 0.07, + "learning_rate": 1.9899733843536e-05, + "loss": 0.5037, + "step": 882 + }, + { + "epoch": 0.07, + "learning_rate": 1.9899350695092914e-05, + "loss": 0.516, + "step": 883 + }, + { + "epoch": 0.07, + "learning_rate": 1.989896681968268e-05, + "loss": 0.5274, + "step": 884 + }, + { + "epoch": 0.07, + "learning_rate": 1.98985822173335e-05, + "loss": 0.5063, + "step": 885 + }, + { + "epoch": 0.07, + "learning_rate": 1.9898196888073612e-05, + "loss": 0.507, + "step": 886 + }, + { + "epoch": 0.07, + "learning_rate": 1.9897810831931314e-05, + "loss": 0.5332, + "step": 887 + }, + { + "epoch": 0.07, + "learning_rate": 1.989742404893496e-05, + "loss": 0.5391, + "step": 888 + }, + { + "epoch": 0.07, + "learning_rate": 1.9897036539112945e-05, + "loss": 0.5041, + "step": 889 + }, + { + "epoch": 0.07, + "learning_rate": 1.9896648302493734e-05, + "loss": 0.5138, + "step": 890 + }, + { + "epoch": 0.07, + "learning_rate": 1.9896259339105835e-05, + "loss": 0.5398, + "step": 891 + }, + { + "epoch": 0.07, + "learning_rate": 1.9895869648977812e-05, + "loss": 0.516, + "step": 892 + }, + { + "epoch": 0.07, + "learning_rate": 1.9895479232138282e-05, + "loss": 0.5177, + "step": 893 + }, + { + "epoch": 0.07, + "learning_rate": 1.9895088088615915e-05, + "loss": 0.4917, + "step": 894 + }, + { + "epoch": 0.07, + "learning_rate": 1.9894696218439436e-05, + "loss": 0.526, + "step": 895 + }, + { + "epoch": 0.07, + "learning_rate": 1.989430362163762e-05, + "loss": 0.5205, + "step": 896 + }, + { + "epoch": 0.08, + "learning_rate": 1.98939102982393e-05, + "loss": 0.5188, + "step": 897 + }, + { + "epoch": 0.08, + "learning_rate": 1.9893516248273362e-05, + "loss": 0.5392, + "step": 898 + }, + { + "epoch": 0.08, + "learning_rate": 1.989312147176874e-05, + "loss": 0.5131, + "step": 899 + }, + { + "epoch": 0.08, + "learning_rate": 1.9892725968754426e-05, + "loss": 0.5156, + "step": 900 + }, + { + "epoch": 0.08, + "learning_rate": 1.9892329739259462e-05, + "loss": 0.4967, + "step": 901 + }, + { + "epoch": 0.08, + "learning_rate": 1.9891932783312948e-05, + "loss": 0.5241, + "step": 902 + }, + { + "epoch": 0.08, + "learning_rate": 1.9891535100944033e-05, + "loss": 0.5174, + "step": 903 + }, + { + "epoch": 0.08, + "learning_rate": 1.9891136692181926e-05, + "loss": 0.5355, + "step": 904 + }, + { + "epoch": 0.08, + "learning_rate": 1.989073755705588e-05, + "loss": 0.5073, + "step": 905 + }, + { + "epoch": 0.08, + "learning_rate": 1.9890337695595202e-05, + "loss": 0.518, + "step": 906 + }, + { + "epoch": 0.08, + "learning_rate": 1.988993710782926e-05, + "loss": 0.5088, + "step": 907 + }, + { + "epoch": 0.08, + "learning_rate": 1.988953579378748e-05, + "loss": 0.5005, + "step": 908 + }, + { + "epoch": 0.08, + "learning_rate": 1.988913375349932e-05, + "loss": 0.5177, + "step": 909 + }, + { + "epoch": 0.08, + "learning_rate": 1.988873098699431e-05, + "loss": 0.5096, + "step": 910 + }, + { + "epoch": 0.08, + "learning_rate": 1.9888327494302025e-05, + "loss": 0.5153, + "step": 911 + }, + { + "epoch": 0.08, + "learning_rate": 1.98879232754521e-05, + "loss": 0.5335, + "step": 912 + }, + { + "epoch": 0.08, + "learning_rate": 1.9887518330474216e-05, + "loss": 0.5308, + "step": 913 + }, + { + "epoch": 0.08, + "learning_rate": 1.9887112659398108e-05, + "loss": 0.5303, + "step": 914 + }, + { + "epoch": 0.08, + "learning_rate": 1.9886706262253574e-05, + "loss": 0.5258, + "step": 915 + }, + { + "epoch": 0.08, + "learning_rate": 1.988629913907045e-05, + "loss": 0.5278, + "step": 916 + }, + { + "epoch": 0.08, + "learning_rate": 1.988589128987864e-05, + "loss": 0.5097, + "step": 917 + }, + { + "epoch": 0.08, + "learning_rate": 1.9885482714708093e-05, + "loss": 0.5024, + "step": 918 + }, + { + "epoch": 0.08, + "learning_rate": 1.988507341358881e-05, + "loss": 0.5346, + "step": 919 + }, + { + "epoch": 0.08, + "learning_rate": 1.9884663386550853e-05, + "loss": 0.5104, + "step": 920 + }, + { + "epoch": 0.08, + "learning_rate": 1.988425263362433e-05, + "loss": 0.5202, + "step": 921 + }, + { + "epoch": 0.08, + "learning_rate": 1.98838411548394e-05, + "loss": 0.5188, + "step": 922 + }, + { + "epoch": 0.08, + "learning_rate": 1.9883428950226294e-05, + "loss": 0.5121, + "step": 923 + }, + { + "epoch": 0.08, + "learning_rate": 1.9883016019815268e-05, + "loss": 0.5089, + "step": 924 + }, + { + "epoch": 0.08, + "learning_rate": 1.9882602363636656e-05, + "loss": 0.5172, + "step": 925 + }, + { + "epoch": 0.08, + "learning_rate": 1.9882187981720827e-05, + "loss": 0.52, + "step": 926 + }, + { + "epoch": 0.08, + "learning_rate": 1.9881772874098218e-05, + "loss": 0.5118, + "step": 927 + }, + { + "epoch": 0.08, + "learning_rate": 1.9881357040799312e-05, + "loss": 0.531, + "step": 928 + }, + { + "epoch": 0.08, + "learning_rate": 1.9880940481854646e-05, + "loss": 0.5273, + "step": 929 + }, + { + "epoch": 0.08, + "learning_rate": 1.9880523197294804e-05, + "loss": 0.5082, + "step": 930 + }, + { + "epoch": 0.08, + "learning_rate": 1.9880105187150435e-05, + "loss": 0.5142, + "step": 931 + }, + { + "epoch": 0.08, + "learning_rate": 1.987968645145224e-05, + "loss": 0.5217, + "step": 932 + }, + { + "epoch": 0.08, + "learning_rate": 1.987926699023096e-05, + "loss": 0.504, + "step": 933 + }, + { + "epoch": 0.08, + "learning_rate": 1.9878846803517408e-05, + "loss": 0.5272, + "step": 934 + }, + { + "epoch": 0.08, + "learning_rate": 1.987842589134243e-05, + "loss": 0.5336, + "step": 935 + }, + { + "epoch": 0.08, + "learning_rate": 1.9878004253736945e-05, + "loss": 0.5198, + "step": 936 + }, + { + "epoch": 0.08, + "learning_rate": 1.9877581890731915e-05, + "loss": 0.5233, + "step": 937 + }, + { + "epoch": 0.08, + "learning_rate": 1.987715880235835e-05, + "loss": 0.5315, + "step": 938 + }, + { + "epoch": 0.08, + "learning_rate": 1.9876734988647334e-05, + "loss": 0.5072, + "step": 939 + }, + { + "epoch": 0.08, + "learning_rate": 1.9876310449629973e-05, + "loss": 0.5278, + "step": 940 + }, + { + "epoch": 0.08, + "learning_rate": 1.9875885185337453e-05, + "loss": 0.5219, + "step": 941 + }, + { + "epoch": 0.08, + "learning_rate": 1.9875459195801e-05, + "loss": 0.5161, + "step": 942 + }, + { + "epoch": 0.08, + "learning_rate": 1.98750324810519e-05, + "loss": 0.5227, + "step": 943 + }, + { + "epoch": 0.08, + "learning_rate": 1.987460504112149e-05, + "loss": 0.5114, + "step": 944 + }, + { + "epoch": 0.08, + "learning_rate": 1.9874176876041157e-05, + "loss": 0.5262, + "step": 945 + }, + { + "epoch": 0.08, + "learning_rate": 1.9873747985842343e-05, + "loss": 0.508, + "step": 946 + }, + { + "epoch": 0.08, + "learning_rate": 1.9873318370556546e-05, + "loss": 0.5422, + "step": 947 + }, + { + "epoch": 0.08, + "learning_rate": 1.9872888030215313e-05, + "loss": 0.5087, + "step": 948 + }, + { + "epoch": 0.08, + "learning_rate": 1.9872456964850246e-05, + "loss": 0.5138, + "step": 949 + }, + { + "epoch": 0.08, + "learning_rate": 1.9872025174493003e-05, + "loss": 0.5138, + "step": 950 + }, + { + "epoch": 0.08, + "learning_rate": 1.9871592659175296e-05, + "loss": 0.5301, + "step": 951 + }, + { + "epoch": 0.08, + "learning_rate": 1.987115941892888e-05, + "loss": 0.4924, + "step": 952 + }, + { + "epoch": 0.08, + "learning_rate": 1.987072545378557e-05, + "loss": 0.5321, + "step": 953 + }, + { + "epoch": 0.08, + "learning_rate": 1.9870290763777243e-05, + "loss": 0.5333, + "step": 954 + }, + { + "epoch": 0.08, + "learning_rate": 1.9869855348935817e-05, + "loss": 0.5032, + "step": 955 + }, + { + "epoch": 0.08, + "learning_rate": 1.986941920929326e-05, + "loss": 0.5294, + "step": 956 + }, + { + "epoch": 0.08, + "learning_rate": 1.986898234488161e-05, + "loss": 0.5085, + "step": 957 + }, + { + "epoch": 0.08, + "learning_rate": 1.9868544755732948e-05, + "loss": 0.4924, + "step": 958 + }, + { + "epoch": 0.08, + "learning_rate": 1.9868106441879403e-05, + "loss": 0.496, + "step": 959 + }, + { + "epoch": 0.08, + "learning_rate": 1.9867667403353162e-05, + "loss": 0.5076, + "step": 960 + }, + { + "epoch": 0.08, + "learning_rate": 1.9867227640186474e-05, + "loss": 0.5201, + "step": 961 + }, + { + "epoch": 0.08, + "learning_rate": 1.9866787152411624e-05, + "loss": 0.5204, + "step": 962 + }, + { + "epoch": 0.08, + "learning_rate": 1.986634594006097e-05, + "loss": 0.5269, + "step": 963 + }, + { + "epoch": 0.08, + "learning_rate": 1.9865904003166904e-05, + "loss": 0.5226, + "step": 964 + }, + { + "epoch": 0.08, + "learning_rate": 1.9865461341761885e-05, + "loss": 0.5212, + "step": 965 + }, + { + "epoch": 0.08, + "learning_rate": 1.986501795587842e-05, + "loss": 0.5216, + "step": 966 + }, + { + "epoch": 0.08, + "learning_rate": 1.9864573845549063e-05, + "loss": 0.5174, + "step": 967 + }, + { + "epoch": 0.08, + "learning_rate": 1.9864129010806437e-05, + "loss": 0.5356, + "step": 968 + }, + { + "epoch": 0.08, + "learning_rate": 1.9863683451683204e-05, + "loss": 0.4997, + "step": 969 + }, + { + "epoch": 0.08, + "learning_rate": 1.9863237168212084e-05, + "loss": 0.5137, + "step": 970 + }, + { + "epoch": 0.08, + "learning_rate": 1.986279016042585e-05, + "loss": 0.5368, + "step": 971 + }, + { + "epoch": 0.08, + "learning_rate": 1.9862342428357327e-05, + "loss": 0.5209, + "step": 972 + }, + { + "epoch": 0.08, + "learning_rate": 1.9861893972039402e-05, + "loss": 0.5135, + "step": 973 + }, + { + "epoch": 0.08, + "learning_rate": 1.9861444791504997e-05, + "loss": 0.517, + "step": 974 + }, + { + "epoch": 0.08, + "learning_rate": 1.9860994886787106e-05, + "loss": 0.5308, + "step": 975 + }, + { + "epoch": 0.08, + "learning_rate": 1.9860544257918765e-05, + "loss": 0.5223, + "step": 976 + }, + { + "epoch": 0.08, + "learning_rate": 1.9860092904933065e-05, + "loss": 0.5231, + "step": 977 + }, + { + "epoch": 0.08, + "learning_rate": 1.9859640827863157e-05, + "loss": 0.5187, + "step": 978 + }, + { + "epoch": 0.08, + "learning_rate": 1.9859188026742235e-05, + "loss": 0.524, + "step": 979 + }, + { + "epoch": 0.08, + "learning_rate": 1.9858734501603553e-05, + "loss": 0.5258, + "step": 980 + }, + { + "epoch": 0.08, + "learning_rate": 1.985828025248041e-05, + "loss": 0.5138, + "step": 981 + }, + { + "epoch": 0.08, + "learning_rate": 1.985782527940617e-05, + "loss": 0.5222, + "step": 982 + }, + { + "epoch": 0.08, + "learning_rate": 1.9857369582414246e-05, + "loss": 0.5048, + "step": 983 + }, + { + "epoch": 0.08, + "learning_rate": 1.98569131615381e-05, + "loss": 0.498, + "step": 984 + }, + { + "epoch": 0.08, + "learning_rate": 1.985645601681125e-05, + "loss": 0.5268, + "step": 985 + }, + { + "epoch": 0.08, + "learning_rate": 1.9855998148267265e-05, + "loss": 0.5111, + "step": 986 + }, + { + "epoch": 0.08, + "learning_rate": 1.9855539555939768e-05, + "loss": 0.5131, + "step": 987 + }, + { + "epoch": 0.08, + "learning_rate": 1.985508023986244e-05, + "loss": 0.5085, + "step": 988 + }, + { + "epoch": 0.08, + "learning_rate": 1.985462020006901e-05, + "loss": 0.4973, + "step": 989 + }, + { + "epoch": 0.08, + "learning_rate": 1.9854159436593258e-05, + "loss": 0.5084, + "step": 990 + }, + { + "epoch": 0.08, + "learning_rate": 1.9853697949469027e-05, + "loss": 0.499, + "step": 991 + }, + { + "epoch": 0.08, + "learning_rate": 1.98532357387302e-05, + "loss": 0.5203, + "step": 992 + }, + { + "epoch": 0.08, + "learning_rate": 1.9852772804410728e-05, + "loss": 0.4915, + "step": 993 + }, + { + "epoch": 0.08, + "learning_rate": 1.98523091465446e-05, + "loss": 0.5183, + "step": 994 + }, + { + "epoch": 0.08, + "learning_rate": 1.9851844765165863e-05, + "loss": 0.505, + "step": 995 + }, + { + "epoch": 0.08, + "learning_rate": 1.9851379660308624e-05, + "loss": 0.5046, + "step": 996 + }, + { + "epoch": 0.08, + "learning_rate": 1.9850913832007042e-05, + "loss": 0.515, + "step": 997 + }, + { + "epoch": 0.08, + "learning_rate": 1.985044728029532e-05, + "loss": 0.503, + "step": 998 + }, + { + "epoch": 0.08, + "learning_rate": 1.984998000520772e-05, + "loss": 0.5179, + "step": 999 + }, + { + "epoch": 0.08, + "learning_rate": 1.9849512006778557e-05, + "loss": 0.5145, + "step": 1000 + }, + { + "epoch": 0.08, + "learning_rate": 1.9849043285042203e-05, + "loss": 0.5222, + "step": 1001 + }, + { + "epoch": 0.08, + "learning_rate": 1.9848573840033068e-05, + "loss": 0.4923, + "step": 1002 + }, + { + "epoch": 0.08, + "learning_rate": 1.984810367178564e-05, + "loss": 0.5156, + "step": 1003 + }, + { + "epoch": 0.08, + "learning_rate": 1.984763278033444e-05, + "loss": 0.5181, + "step": 1004 + }, + { + "epoch": 0.08, + "learning_rate": 1.9847161165714043e-05, + "loss": 0.5291, + "step": 1005 + }, + { + "epoch": 0.08, + "learning_rate": 1.984668882795909e-05, + "loss": 0.5196, + "step": 1006 + }, + { + "epoch": 0.08, + "learning_rate": 1.9846215767104266e-05, + "loss": 0.5165, + "step": 1007 + }, + { + "epoch": 0.08, + "learning_rate": 1.984574198318431e-05, + "loss": 0.5066, + "step": 1008 + }, + { + "epoch": 0.08, + "learning_rate": 1.9845267476234013e-05, + "loss": 0.5345, + "step": 1009 + }, + { + "epoch": 0.08, + "learning_rate": 1.984479224628822e-05, + "loss": 0.5275, + "step": 1010 + }, + { + "epoch": 0.08, + "learning_rate": 1.9844316293381834e-05, + "loss": 0.5111, + "step": 1011 + }, + { + "epoch": 0.08, + "learning_rate": 1.9843839617549805e-05, + "loss": 0.4976, + "step": 1012 + }, + { + "epoch": 0.08, + "learning_rate": 1.984336221882714e-05, + "loss": 0.5251, + "step": 1013 + }, + { + "epoch": 0.08, + "learning_rate": 1.9842884097248892e-05, + "loss": 0.5083, + "step": 1014 + }, + { + "epoch": 0.08, + "learning_rate": 1.9842405252850175e-05, + "loss": 0.5086, + "step": 1015 + }, + { + "epoch": 0.09, + "learning_rate": 1.984192568566616e-05, + "loss": 0.535, + "step": 1016 + }, + { + "epoch": 0.09, + "learning_rate": 1.9841445395732054e-05, + "loss": 0.5005, + "step": 1017 + }, + { + "epoch": 0.09, + "learning_rate": 1.984096438308313e-05, + "loss": 0.5042, + "step": 1018 + }, + { + "epoch": 0.09, + "learning_rate": 1.9840482647754716e-05, + "loss": 0.5152, + "step": 1019 + }, + { + "epoch": 0.09, + "learning_rate": 1.9840000189782184e-05, + "loss": 0.5217, + "step": 1020 + }, + { + "epoch": 0.09, + "learning_rate": 1.983951700920097e-05, + "loss": 0.5063, + "step": 1021 + }, + { + "epoch": 0.09, + "learning_rate": 1.9839033106046548e-05, + "loss": 0.5153, + "step": 1022 + }, + { + "epoch": 0.09, + "learning_rate": 1.983854848035446e-05, + "loss": 0.5272, + "step": 1023 + }, + { + "epoch": 0.09, + "learning_rate": 1.9838063132160292e-05, + "loss": 0.5123, + "step": 1024 + }, + { + "epoch": 0.09, + "learning_rate": 1.983757706149969e-05, + "loss": 0.5136, + "step": 1025 + }, + { + "epoch": 0.09, + "learning_rate": 1.9837090268408342e-05, + "loss": 0.5199, + "step": 1026 + }, + { + "epoch": 0.09, + "learning_rate": 1.9836602752922004e-05, + "loss": 0.5092, + "step": 1027 + }, + { + "epoch": 0.09, + "learning_rate": 1.9836114515076473e-05, + "loss": 0.5272, + "step": 1028 + }, + { + "epoch": 0.09, + "learning_rate": 1.98356255549076e-05, + "loss": 0.5041, + "step": 1029 + }, + { + "epoch": 0.09, + "learning_rate": 1.98351358724513e-05, + "loss": 0.529, + "step": 1030 + }, + { + "epoch": 0.09, + "learning_rate": 1.9834645467743524e-05, + "loss": 0.5032, + "step": 1031 + }, + { + "epoch": 0.09, + "learning_rate": 1.9834154340820296e-05, + "loss": 0.5256, + "step": 1032 + }, + { + "epoch": 0.09, + "learning_rate": 1.983366249171767e-05, + "loss": 0.5248, + "step": 1033 + }, + { + "epoch": 0.09, + "learning_rate": 1.9833169920471778e-05, + "loss": 0.5205, + "step": 1034 + }, + { + "epoch": 0.09, + "learning_rate": 1.9832676627118784e-05, + "loss": 0.5149, + "step": 1035 + }, + { + "epoch": 0.09, + "learning_rate": 1.9832182611694916e-05, + "loss": 0.5022, + "step": 1036 + }, + { + "epoch": 0.09, + "learning_rate": 1.983168787423645e-05, + "loss": 0.5143, + "step": 1037 + }, + { + "epoch": 0.09, + "learning_rate": 1.9831192414779724e-05, + "loss": 0.5363, + "step": 1038 + }, + { + "epoch": 0.09, + "learning_rate": 1.9830696233361113e-05, + "loss": 0.4941, + "step": 1039 + }, + { + "epoch": 0.09, + "learning_rate": 1.9830199330017063e-05, + "loss": 0.5166, + "step": 1040 + }, + { + "epoch": 0.09, + "learning_rate": 1.982970170478406e-05, + "loss": 0.5323, + "step": 1041 + }, + { + "epoch": 0.09, + "learning_rate": 1.9829203357698647e-05, + "loss": 0.5265, + "step": 1042 + }, + { + "epoch": 0.09, + "learning_rate": 1.9828704288797425e-05, + "loss": 0.5111, + "step": 1043 + }, + { + "epoch": 0.09, + "learning_rate": 1.982820449811704e-05, + "loss": 0.5161, + "step": 1044 + }, + { + "epoch": 0.09, + "learning_rate": 1.9827703985694194e-05, + "loss": 0.5233, + "step": 1045 + }, + { + "epoch": 0.09, + "learning_rate": 1.9827202751565644e-05, + "loss": 0.5273, + "step": 1046 + }, + { + "epoch": 0.09, + "learning_rate": 1.9826700795768197e-05, + "loss": 0.5168, + "step": 1047 + }, + { + "epoch": 0.09, + "learning_rate": 1.982619811833872e-05, + "loss": 0.504, + "step": 1048 + }, + { + "epoch": 0.09, + "learning_rate": 1.982569471931412e-05, + "loss": 0.5216, + "step": 1049 + }, + { + "epoch": 0.09, + "learning_rate": 1.982519059873137e-05, + "loss": 0.5331, + "step": 1050 + }, + { + "epoch": 0.09, + "learning_rate": 1.9824685756627487e-05, + "loss": 0.5473, + "step": 1051 + }, + { + "epoch": 0.09, + "learning_rate": 1.9824180193039545e-05, + "loss": 0.5213, + "step": 1052 + }, + { + "epoch": 0.09, + "learning_rate": 1.9823673908004673e-05, + "loss": 0.5104, + "step": 1053 + }, + { + "epoch": 0.09, + "learning_rate": 1.982316690156005e-05, + "loss": 0.5322, + "step": 1054 + }, + { + "epoch": 0.09, + "learning_rate": 1.9822659173742904e-05, + "loss": 0.52, + "step": 1055 + }, + { + "epoch": 0.09, + "learning_rate": 1.9822150724590528e-05, + "loss": 0.5226, + "step": 1056 + }, + { + "epoch": 0.09, + "learning_rate": 1.9821641554140252e-05, + "loss": 0.4941, + "step": 1057 + }, + { + "epoch": 0.09, + "learning_rate": 1.9821131662429476e-05, + "loss": 0.5173, + "step": 1058 + }, + { + "epoch": 0.09, + "learning_rate": 1.9820621049495637e-05, + "loss": 0.5042, + "step": 1059 + }, + { + "epoch": 0.09, + "learning_rate": 1.9820109715376236e-05, + "loss": 0.5264, + "step": 1060 + }, + { + "epoch": 0.09, + "learning_rate": 1.9819597660108823e-05, + "loss": 0.5155, + "step": 1061 + }, + { + "epoch": 0.09, + "learning_rate": 1.9819084883731e-05, + "loss": 0.5059, + "step": 1062 + }, + { + "epoch": 0.09, + "learning_rate": 1.9818571386280422e-05, + "loss": 0.5237, + "step": 1063 + }, + { + "epoch": 0.09, + "learning_rate": 1.9818057167794803e-05, + "loss": 0.5203, + "step": 1064 + }, + { + "epoch": 0.09, + "learning_rate": 1.98175422283119e-05, + "loss": 0.5128, + "step": 1065 + }, + { + "epoch": 0.09, + "learning_rate": 1.9817026567869527e-05, + "loss": 0.5125, + "step": 1066 + }, + { + "epoch": 0.09, + "learning_rate": 1.9816510186505562e-05, + "loss": 0.5056, + "step": 1067 + }, + { + "epoch": 0.09, + "learning_rate": 1.9815993084257913e-05, + "loss": 0.5249, + "step": 1068 + }, + { + "epoch": 0.09, + "learning_rate": 1.9815475261164563e-05, + "loss": 0.5111, + "step": 1069 + }, + { + "epoch": 0.09, + "learning_rate": 1.9814956717263534e-05, + "loss": 0.5204, + "step": 1070 + }, + { + "epoch": 0.09, + "learning_rate": 1.9814437452592908e-05, + "loss": 0.5045, + "step": 1071 + }, + { + "epoch": 0.09, + "learning_rate": 1.9813917467190817e-05, + "loss": 0.4943, + "step": 1072 + }, + { + "epoch": 0.09, + "learning_rate": 1.9813396761095446e-05, + "loss": 0.5294, + "step": 1073 + }, + { + "epoch": 0.09, + "learning_rate": 1.9812875334345032e-05, + "loss": 0.5243, + "step": 1074 + }, + { + "epoch": 0.09, + "learning_rate": 1.981235318697787e-05, + "loss": 0.508, + "step": 1075 + }, + { + "epoch": 0.09, + "learning_rate": 1.98118303190323e-05, + "loss": 0.5013, + "step": 1076 + }, + { + "epoch": 0.09, + "learning_rate": 1.9811306730546728e-05, + "loss": 0.494, + "step": 1077 + }, + { + "epoch": 0.09, + "learning_rate": 1.9810782421559595e-05, + "loss": 0.5325, + "step": 1078 + }, + { + "epoch": 0.09, + "learning_rate": 1.9810257392109405e-05, + "loss": 0.5255, + "step": 1079 + }, + { + "epoch": 0.09, + "learning_rate": 1.9809731642234715e-05, + "loss": 0.5053, + "step": 1080 + }, + { + "epoch": 0.09, + "learning_rate": 1.9809205171974136e-05, + "loss": 0.5062, + "step": 1081 + }, + { + "epoch": 0.09, + "learning_rate": 1.9808677981366334e-05, + "loss": 0.5201, + "step": 1082 + }, + { + "epoch": 0.09, + "learning_rate": 1.9808150070450015e-05, + "loss": 0.4957, + "step": 1083 + }, + { + "epoch": 0.09, + "learning_rate": 1.980762143926395e-05, + "loss": 0.5247, + "step": 1084 + }, + { + "epoch": 0.09, + "learning_rate": 1.9807092087846956e-05, + "loss": 0.5265, + "step": 1085 + }, + { + "epoch": 0.09, + "learning_rate": 1.9806562016237913e-05, + "loss": 0.528, + "step": 1086 + }, + { + "epoch": 0.09, + "learning_rate": 1.9806031224475743e-05, + "loss": 0.5301, + "step": 1087 + }, + { + "epoch": 0.09, + "learning_rate": 1.9805499712599426e-05, + "loss": 0.5281, + "step": 1088 + }, + { + "epoch": 0.09, + "learning_rate": 1.9804967480647996e-05, + "loss": 0.5024, + "step": 1089 + }, + { + "epoch": 0.09, + "learning_rate": 1.9804434528660536e-05, + "loss": 0.5087, + "step": 1090 + }, + { + "epoch": 0.09, + "learning_rate": 1.9803900856676182e-05, + "loss": 0.5004, + "step": 1091 + }, + { + "epoch": 0.09, + "learning_rate": 1.980336646473413e-05, + "loss": 0.5165, + "step": 1092 + }, + { + "epoch": 0.09, + "learning_rate": 1.980283135287362e-05, + "loss": 0.4901, + "step": 1093 + }, + { + "epoch": 0.09, + "learning_rate": 1.9802295521133942e-05, + "loss": 0.5026, + "step": 1094 + }, + { + "epoch": 0.09, + "learning_rate": 1.980175896955446e-05, + "loss": 0.5191, + "step": 1095 + }, + { + "epoch": 0.09, + "learning_rate": 1.9801221698174564e-05, + "loss": 0.5122, + "step": 1096 + }, + { + "epoch": 0.09, + "learning_rate": 1.980068370703371e-05, + "loss": 0.5061, + "step": 1097 + }, + { + "epoch": 0.09, + "learning_rate": 1.9800144996171415e-05, + "loss": 0.5216, + "step": 1098 + }, + { + "epoch": 0.09, + "learning_rate": 1.979960556562723e-05, + "loss": 0.5257, + "step": 1099 + }, + { + "epoch": 0.09, + "learning_rate": 1.979906541544077e-05, + "loss": 0.5028, + "step": 1100 + }, + { + "epoch": 0.09, + "learning_rate": 1.9798524545651705e-05, + "loss": 0.5225, + "step": 1101 + }, + { + "epoch": 0.09, + "learning_rate": 1.9797982956299754e-05, + "loss": 0.5049, + "step": 1102 + }, + { + "epoch": 0.09, + "learning_rate": 1.9797440647424687e-05, + "loss": 0.5348, + "step": 1103 + }, + { + "epoch": 0.09, + "learning_rate": 1.9796897619066327e-05, + "loss": 0.5152, + "step": 1104 + }, + { + "epoch": 0.09, + "learning_rate": 1.9796353871264555e-05, + "loss": 0.5002, + "step": 1105 + }, + { + "epoch": 0.09, + "learning_rate": 1.97958094040593e-05, + "loss": 0.5106, + "step": 1106 + }, + { + "epoch": 0.09, + "learning_rate": 1.9795264217490547e-05, + "loss": 0.5306, + "step": 1107 + }, + { + "epoch": 0.09, + "learning_rate": 1.9794718311598337e-05, + "loss": 0.5149, + "step": 1108 + }, + { + "epoch": 0.09, + "learning_rate": 1.9794171686422746e-05, + "loss": 0.4985, + "step": 1109 + }, + { + "epoch": 0.09, + "learning_rate": 1.9793624342003927e-05, + "loss": 0.526, + "step": 1110 + }, + { + "epoch": 0.09, + "learning_rate": 1.979307627838207e-05, + "loss": 0.5112, + "step": 1111 + }, + { + "epoch": 0.09, + "learning_rate": 1.9792527495597423e-05, + "loss": 0.5188, + "step": 1112 + }, + { + "epoch": 0.09, + "learning_rate": 1.9791977993690292e-05, + "loss": 0.5096, + "step": 1113 + }, + { + "epoch": 0.09, + "learning_rate": 1.9791427772701017e-05, + "loss": 0.5175, + "step": 1114 + }, + { + "epoch": 0.09, + "learning_rate": 1.9790876832670018e-05, + "loss": 0.5098, + "step": 1115 + }, + { + "epoch": 0.09, + "learning_rate": 1.9790325173637744e-05, + "loss": 0.5037, + "step": 1116 + }, + { + "epoch": 0.09, + "learning_rate": 1.9789772795644714e-05, + "loss": 0.5231, + "step": 1117 + }, + { + "epoch": 0.09, + "learning_rate": 1.9789219698731484e-05, + "loss": 0.5139, + "step": 1118 + }, + { + "epoch": 0.09, + "learning_rate": 1.9788665882938677e-05, + "loss": 0.5106, + "step": 1119 + }, + { + "epoch": 0.09, + "learning_rate": 1.9788111348306963e-05, + "loss": 0.522, + "step": 1120 + }, + { + "epoch": 0.09, + "learning_rate": 1.978755609487706e-05, + "loss": 0.4982, + "step": 1121 + }, + { + "epoch": 0.09, + "learning_rate": 1.9787000122689753e-05, + "loss": 0.5091, + "step": 1122 + }, + { + "epoch": 0.09, + "learning_rate": 1.978644343178586e-05, + "loss": 0.5313, + "step": 1123 + }, + { + "epoch": 0.09, + "learning_rate": 1.978588602220627e-05, + "loss": 0.5007, + "step": 1124 + }, + { + "epoch": 0.09, + "learning_rate": 1.978532789399191e-05, + "loss": 0.5144, + "step": 1125 + }, + { + "epoch": 0.09, + "learning_rate": 1.978476904718377e-05, + "loss": 0.5293, + "step": 1126 + }, + { + "epoch": 0.09, + "learning_rate": 1.9784209481822892e-05, + "loss": 0.5137, + "step": 1127 + }, + { + "epoch": 0.09, + "learning_rate": 1.9783649197950362e-05, + "loss": 0.4985, + "step": 1128 + }, + { + "epoch": 0.09, + "learning_rate": 1.978308819560733e-05, + "loss": 0.5455, + "step": 1129 + }, + { + "epoch": 0.09, + "learning_rate": 1.9782526474834988e-05, + "loss": 0.4913, + "step": 1130 + }, + { + "epoch": 0.09, + "learning_rate": 1.978196403567459e-05, + "loss": 0.5198, + "step": 1131 + }, + { + "epoch": 0.09, + "learning_rate": 1.9781400878167446e-05, + "loss": 0.5024, + "step": 1132 + }, + { + "epoch": 0.09, + "learning_rate": 1.97808370023549e-05, + "loss": 0.5142, + "step": 1133 + }, + { + "epoch": 0.09, + "learning_rate": 1.978027240827837e-05, + "loss": 0.5143, + "step": 1134 + }, + { + "epoch": 0.09, + "learning_rate": 1.977970709597931e-05, + "loss": 0.5094, + "step": 1135 + }, + { + "epoch": 0.1, + "learning_rate": 1.977914106549924e-05, + "loss": 0.5372, + "step": 1136 + }, + { + "epoch": 0.1, + "learning_rate": 1.9778574316879724e-05, + "loss": 0.5168, + "step": 1137 + }, + { + "epoch": 0.1, + "learning_rate": 1.9778006850162384e-05, + "loss": 0.4953, + "step": 1138 + }, + { + "epoch": 0.1, + "learning_rate": 1.9777438665388885e-05, + "loss": 0.5212, + "step": 1139 + }, + { + "epoch": 0.1, + "learning_rate": 1.9776869762600963e-05, + "loss": 0.5067, + "step": 1140 + }, + { + "epoch": 0.1, + "learning_rate": 1.977630014184039e-05, + "loss": 0.5148, + "step": 1141 + }, + { + "epoch": 0.1, + "learning_rate": 1.9775729803148994e-05, + "loss": 0.5136, + "step": 1142 + }, + { + "epoch": 0.1, + "learning_rate": 1.9775158746568665e-05, + "loss": 0.508, + "step": 1143 + }, + { + "epoch": 0.1, + "learning_rate": 1.9774586972141337e-05, + "loss": 0.5262, + "step": 1144 + }, + { + "epoch": 0.1, + "learning_rate": 1.9774014479908996e-05, + "loss": 0.5161, + "step": 1145 + }, + { + "epoch": 0.1, + "learning_rate": 1.977344126991368e-05, + "loss": 0.5174, + "step": 1146 + }, + { + "epoch": 0.1, + "learning_rate": 1.9772867342197494e-05, + "loss": 0.5228, + "step": 1147 + }, + { + "epoch": 0.1, + "learning_rate": 1.977229269680258e-05, + "loss": 0.5263, + "step": 1148 + }, + { + "epoch": 0.1, + "learning_rate": 1.9771717333771133e-05, + "loss": 0.4995, + "step": 1149 + }, + { + "epoch": 0.1, + "learning_rate": 1.9771141253145405e-05, + "loss": 0.5082, + "step": 1150 + }, + { + "epoch": 0.1, + "learning_rate": 1.977056445496771e-05, + "loss": 0.5178, + "step": 1151 + }, + { + "epoch": 0.1, + "learning_rate": 1.97699869392804e-05, + "loss": 0.5053, + "step": 1152 + }, + { + "epoch": 0.1, + "learning_rate": 1.9769408706125882e-05, + "loss": 0.5052, + "step": 1153 + }, + { + "epoch": 0.1, + "learning_rate": 1.9768829755546625e-05, + "loss": 0.5217, + "step": 1154 + }, + { + "epoch": 0.1, + "learning_rate": 1.9768250087585143e-05, + "loss": 0.5274, + "step": 1155 + }, + { + "epoch": 0.1, + "learning_rate": 1.9767669702284e-05, + "loss": 0.5186, + "step": 1156 + }, + { + "epoch": 0.1, + "learning_rate": 1.9767088599685828e-05, + "loss": 0.5069, + "step": 1157 + }, + { + "epoch": 0.1, + "learning_rate": 1.9766506779833288e-05, + "loss": 0.523, + "step": 1158 + }, + { + "epoch": 0.1, + "learning_rate": 1.976592424276911e-05, + "loss": 0.4902, + "step": 1159 + }, + { + "epoch": 0.1, + "learning_rate": 1.976534098853608e-05, + "loss": 0.5006, + "step": 1160 + }, + { + "epoch": 0.1, + "learning_rate": 1.9764757017177025e-05, + "loss": 0.5004, + "step": 1161 + }, + { + "epoch": 0.1, + "learning_rate": 1.9764172328734828e-05, + "loss": 0.5145, + "step": 1162 + }, + { + "epoch": 0.1, + "learning_rate": 1.9763586923252428e-05, + "loss": 0.493, + "step": 1163 + }, + { + "epoch": 0.1, + "learning_rate": 1.9763000800772812e-05, + "loss": 0.5021, + "step": 1164 + }, + { + "epoch": 0.1, + "learning_rate": 1.9762413961339025e-05, + "loss": 0.5073, + "step": 1165 + }, + { + "epoch": 0.1, + "learning_rate": 1.9761826404994166e-05, + "loss": 0.5356, + "step": 1166 + }, + { + "epoch": 0.1, + "learning_rate": 1.9761238131781373e-05, + "loss": 0.523, + "step": 1167 + }, + { + "epoch": 0.1, + "learning_rate": 1.9760649141743855e-05, + "loss": 0.513, + "step": 1168 + }, + { + "epoch": 0.1, + "learning_rate": 1.9760059434924857e-05, + "loss": 0.5363, + "step": 1169 + }, + { + "epoch": 0.1, + "learning_rate": 1.9759469011367695e-05, + "loss": 0.5097, + "step": 1170 + }, + { + "epoch": 0.1, + "learning_rate": 1.975887787111572e-05, + "loss": 0.5259, + "step": 1171 + }, + { + "epoch": 0.1, + "learning_rate": 1.975828601421234e-05, + "loss": 0.5167, + "step": 1172 + }, + { + "epoch": 0.1, + "learning_rate": 1.975769344070103e-05, + "loss": 0.4906, + "step": 1173 + }, + { + "epoch": 0.1, + "learning_rate": 1.9757100150625295e-05, + "loss": 0.525, + "step": 1174 + }, + { + "epoch": 0.1, + "learning_rate": 1.975650614402871e-05, + "loss": 0.5207, + "step": 1175 + }, + { + "epoch": 0.1, + "learning_rate": 1.975591142095489e-05, + "loss": 0.5033, + "step": 1176 + }, + { + "epoch": 0.1, + "learning_rate": 1.9755315981447513e-05, + "loss": 0.5178, + "step": 1177 + }, + { + "epoch": 0.1, + "learning_rate": 1.975471982555031e-05, + "loss": 0.4966, + "step": 1178 + }, + { + "epoch": 0.1, + "learning_rate": 1.9754122953307052e-05, + "loss": 0.524, + "step": 1179 + }, + { + "epoch": 0.1, + "learning_rate": 1.9753525364761577e-05, + "loss": 0.5143, + "step": 1180 + }, + { + "epoch": 0.1, + "learning_rate": 1.975292705995777e-05, + "loss": 0.5026, + "step": 1181 + }, + { + "epoch": 0.1, + "learning_rate": 1.9752328038939562e-05, + "loss": 0.5305, + "step": 1182 + }, + { + "epoch": 0.1, + "learning_rate": 1.9751728301750943e-05, + "loss": 0.5092, + "step": 1183 + }, + { + "epoch": 0.1, + "learning_rate": 1.975112784843596e-05, + "loss": 0.5055, + "step": 1184 + }, + { + "epoch": 0.1, + "learning_rate": 1.975052667903871e-05, + "loss": 0.5055, + "step": 1185 + }, + { + "epoch": 0.1, + "learning_rate": 1.9749924793603333e-05, + "loss": 0.5254, + "step": 1186 + }, + { + "epoch": 0.1, + "learning_rate": 1.974932219217403e-05, + "loss": 0.4859, + "step": 1187 + }, + { + "epoch": 0.1, + "learning_rate": 1.9748718874795057e-05, + "loss": 0.524, + "step": 1188 + }, + { + "epoch": 0.1, + "learning_rate": 1.9748114841510723e-05, + "loss": 0.5059, + "step": 1189 + }, + { + "epoch": 0.1, + "learning_rate": 1.9747510092365373e-05, + "loss": 0.4723, + "step": 1190 + }, + { + "epoch": 0.1, + "learning_rate": 1.974690462740343e-05, + "loss": 0.4963, + "step": 1191 + }, + { + "epoch": 0.1, + "learning_rate": 1.974629844666935e-05, + "loss": 0.522, + "step": 1192 + }, + { + "epoch": 0.1, + "learning_rate": 1.9745691550207647e-05, + "loss": 0.5129, + "step": 1193 + }, + { + "epoch": 0.1, + "learning_rate": 1.9745083938062896e-05, + "loss": 0.5143, + "step": 1194 + }, + { + "epoch": 0.1, + "learning_rate": 1.974447561027971e-05, + "loss": 0.51, + "step": 1195 + }, + { + "epoch": 0.1, + "learning_rate": 1.9743866566902766e-05, + "loss": 0.4938, + "step": 1196 + }, + { + "epoch": 0.1, + "learning_rate": 1.974325680797679e-05, + "loss": 0.5115, + "step": 1197 + }, + { + "epoch": 0.1, + "learning_rate": 1.9742646333546564e-05, + "loss": 0.5036, + "step": 1198 + }, + { + "epoch": 0.1, + "learning_rate": 1.9742035143656907e-05, + "loss": 0.5087, + "step": 1199 + }, + { + "epoch": 0.1, + "learning_rate": 1.9741423238352713e-05, + "loss": 0.5302, + "step": 1200 + }, + { + "epoch": 0.1, + "learning_rate": 1.9740810617678912e-05, + "loss": 0.5194, + "step": 1201 + }, + { + "epoch": 0.1, + "learning_rate": 1.9740197281680495e-05, + "loss": 0.5209, + "step": 1202 + }, + { + "epoch": 0.1, + "learning_rate": 1.9739583230402503e-05, + "loss": 0.5251, + "step": 1203 + }, + { + "epoch": 0.1, + "learning_rate": 1.9738968463890026e-05, + "loss": 0.4995, + "step": 1204 + }, + { + "epoch": 0.1, + "learning_rate": 1.9738352982188217e-05, + "loss": 0.5176, + "step": 1205 + }, + { + "epoch": 0.1, + "learning_rate": 1.9737736785342265e-05, + "loss": 0.4993, + "step": 1206 + }, + { + "epoch": 0.1, + "learning_rate": 1.9737119873397427e-05, + "loss": 0.5252, + "step": 1207 + }, + { + "epoch": 0.1, + "learning_rate": 1.9736502246399006e-05, + "loss": 0.5087, + "step": 1208 + }, + { + "epoch": 0.1, + "learning_rate": 1.973588390439236e-05, + "loss": 0.5036, + "step": 1209 + }, + { + "epoch": 0.1, + "learning_rate": 1.9735264847422893e-05, + "loss": 0.5247, + "step": 1210 + }, + { + "epoch": 0.1, + "learning_rate": 1.9734645075536063e-05, + "loss": 0.5141, + "step": 1211 + }, + { + "epoch": 0.1, + "learning_rate": 1.9734024588777393e-05, + "loss": 0.5, + "step": 1212 + }, + { + "epoch": 0.1, + "learning_rate": 1.9733403387192443e-05, + "loss": 0.5339, + "step": 1213 + }, + { + "epoch": 0.1, + "learning_rate": 1.973278147082683e-05, + "loss": 0.5397, + "step": 1214 + }, + { + "epoch": 0.1, + "learning_rate": 1.9732158839726233e-05, + "loss": 0.5121, + "step": 1215 + }, + { + "epoch": 0.1, + "learning_rate": 1.9731535493936365e-05, + "loss": 0.5215, + "step": 1216 + }, + { + "epoch": 0.1, + "learning_rate": 1.9730911433503007e-05, + "loss": 0.5149, + "step": 1217 + }, + { + "epoch": 0.1, + "learning_rate": 1.973028665847199e-05, + "loss": 0.4978, + "step": 1218 + }, + { + "epoch": 0.1, + "learning_rate": 1.9729661168889193e-05, + "loss": 0.5068, + "step": 1219 + }, + { + "epoch": 0.1, + "learning_rate": 1.9729034964800546e-05, + "loss": 0.5087, + "step": 1220 + }, + { + "epoch": 0.1, + "learning_rate": 1.9728408046252035e-05, + "loss": 0.5171, + "step": 1221 + }, + { + "epoch": 0.1, + "learning_rate": 1.9727780413289706e-05, + "loss": 0.4988, + "step": 1222 + }, + { + "epoch": 0.1, + "learning_rate": 1.972715206595964e-05, + "loss": 0.5109, + "step": 1223 + }, + { + "epoch": 0.1, + "learning_rate": 1.9726523004307987e-05, + "loss": 0.5163, + "step": 1224 + }, + { + "epoch": 0.1, + "learning_rate": 1.9725893228380938e-05, + "loss": 0.5143, + "step": 1225 + }, + { + "epoch": 0.1, + "learning_rate": 1.9725262738224743e-05, + "loss": 0.4988, + "step": 1226 + }, + { + "epoch": 0.1, + "learning_rate": 1.9724631533885706e-05, + "loss": 0.5187, + "step": 1227 + }, + { + "epoch": 0.1, + "learning_rate": 1.9723999615410175e-05, + "loss": 0.4917, + "step": 1228 + }, + { + "epoch": 0.1, + "learning_rate": 1.9723366982844555e-05, + "loss": 0.5087, + "step": 1229 + }, + { + "epoch": 0.1, + "learning_rate": 1.972273363623531e-05, + "loss": 0.5089, + "step": 1230 + }, + { + "epoch": 0.1, + "learning_rate": 1.9722099575628947e-05, + "loss": 0.5231, + "step": 1231 + }, + { + "epoch": 0.1, + "learning_rate": 1.9721464801072027e-05, + "loss": 0.526, + "step": 1232 + }, + { + "epoch": 0.1, + "learning_rate": 1.972082931261117e-05, + "loss": 0.5141, + "step": 1233 + }, + { + "epoch": 0.1, + "learning_rate": 1.9720193110293033e-05, + "loss": 0.5202, + "step": 1234 + }, + { + "epoch": 0.1, + "learning_rate": 1.971955619416435e-05, + "loss": 0.5147, + "step": 1235 + }, + { + "epoch": 0.1, + "learning_rate": 1.9718918564271883e-05, + "loss": 0.5051, + "step": 1236 + }, + { + "epoch": 0.1, + "learning_rate": 1.9718280220662463e-05, + "loss": 0.5223, + "step": 1237 + }, + { + "epoch": 0.1, + "learning_rate": 1.9717641163382963e-05, + "loss": 0.4992, + "step": 1238 + }, + { + "epoch": 0.1, + "learning_rate": 1.9717001392480316e-05, + "loss": 0.5245, + "step": 1239 + }, + { + "epoch": 0.1, + "learning_rate": 1.9716360908001498e-05, + "loss": 0.5031, + "step": 1240 + }, + { + "epoch": 0.1, + "learning_rate": 1.9715719709993557e-05, + "loss": 0.525, + "step": 1241 + }, + { + "epoch": 0.1, + "learning_rate": 1.9715077798503564e-05, + "loss": 0.5027, + "step": 1242 + }, + { + "epoch": 0.1, + "learning_rate": 1.971443517357867e-05, + "loss": 0.5122, + "step": 1243 + }, + { + "epoch": 0.1, + "learning_rate": 1.971379183526606e-05, + "loss": 0.5119, + "step": 1244 + }, + { + "epoch": 0.1, + "learning_rate": 1.971314778361298e-05, + "loss": 0.5363, + "step": 1245 + }, + { + "epoch": 0.1, + "learning_rate": 1.9712503018666725e-05, + "loss": 0.508, + "step": 1246 + }, + { + "epoch": 0.1, + "learning_rate": 1.9711857540474653e-05, + "loss": 0.5225, + "step": 1247 + }, + { + "epoch": 0.1, + "learning_rate": 1.971121134908415e-05, + "loss": 0.4993, + "step": 1248 + }, + { + "epoch": 0.1, + "learning_rate": 1.9710564444542683e-05, + "loss": 0.5271, + "step": 1249 + }, + { + "epoch": 0.1, + "learning_rate": 1.9709916826897747e-05, + "loss": 0.502, + "step": 1250 + }, + { + "epoch": 0.1, + "learning_rate": 1.9709268496196912e-05, + "loss": 0.519, + "step": 1251 + }, + { + "epoch": 0.1, + "learning_rate": 1.9708619452487777e-05, + "loss": 0.5257, + "step": 1252 + }, + { + "epoch": 0.1, + "learning_rate": 1.9707969695818013e-05, + "loss": 0.5047, + "step": 1253 + }, + { + "epoch": 0.1, + "learning_rate": 1.9707319226235337e-05, + "loss": 0.5178, + "step": 1254 + }, + { + "epoch": 0.1, + "learning_rate": 1.9706668043787505e-05, + "loss": 0.5169, + "step": 1255 + }, + { + "epoch": 0.11, + "learning_rate": 1.970601614852235e-05, + "loss": 0.5234, + "step": 1256 + }, + { + "epoch": 0.11, + "learning_rate": 1.9705363540487737e-05, + "loss": 0.5084, + "step": 1257 + }, + { + "epoch": 0.11, + "learning_rate": 1.9704710219731594e-05, + "loss": 0.5308, + "step": 1258 + }, + { + "epoch": 0.11, + "learning_rate": 1.9704056186301898e-05, + "loss": 0.4999, + "step": 1259 + }, + { + "epoch": 0.11, + "learning_rate": 1.970340144024668e-05, + "loss": 0.5197, + "step": 1260 + }, + { + "epoch": 0.11, + "learning_rate": 1.9702745981614018e-05, + "loss": 0.5139, + "step": 1261 + }, + { + "epoch": 0.11, + "learning_rate": 1.9702089810452046e-05, + "loss": 0.513, + "step": 1262 + }, + { + "epoch": 0.11, + "learning_rate": 1.9701432926808955e-05, + "loss": 0.5229, + "step": 1263 + }, + { + "epoch": 0.11, + "learning_rate": 1.9700775330732977e-05, + "loss": 0.5081, + "step": 1264 + }, + { + "epoch": 0.11, + "learning_rate": 1.970011702227241e-05, + "loss": 0.5058, + "step": 1265 + }, + { + "epoch": 0.11, + "learning_rate": 1.9699458001475594e-05, + "loss": 0.5179, + "step": 1266 + }, + { + "epoch": 0.11, + "learning_rate": 1.9698798268390927e-05, + "loss": 0.521, + "step": 1267 + }, + { + "epoch": 0.11, + "learning_rate": 1.9698137823066856e-05, + "loss": 0.5244, + "step": 1268 + }, + { + "epoch": 0.11, + "learning_rate": 1.969747666555188e-05, + "loss": 0.5232, + "step": 1269 + }, + { + "epoch": 0.11, + "learning_rate": 1.969681479589455e-05, + "loss": 0.4983, + "step": 1270 + }, + { + "epoch": 0.11, + "learning_rate": 1.9696152214143476e-05, + "loss": 0.4996, + "step": 1271 + }, + { + "epoch": 0.11, + "learning_rate": 1.9695488920347313e-05, + "loss": 0.5006, + "step": 1272 + }, + { + "epoch": 0.11, + "learning_rate": 1.969482491455477e-05, + "loss": 0.5173, + "step": 1273 + }, + { + "epoch": 0.11, + "learning_rate": 1.969416019681461e-05, + "loss": 0.5322, + "step": 1274 + }, + { + "epoch": 0.11, + "learning_rate": 1.9693494767175644e-05, + "loss": 0.5, + "step": 1275 + }, + { + "epoch": 0.11, + "learning_rate": 1.969282862568674e-05, + "loss": 0.5144, + "step": 1276 + }, + { + "epoch": 0.11, + "learning_rate": 1.969216177239682e-05, + "loss": 0.5095, + "step": 1277 + }, + { + "epoch": 0.11, + "learning_rate": 1.969149420735485e-05, + "loss": 0.4908, + "step": 1278 + }, + { + "epoch": 0.11, + "learning_rate": 1.9690825930609857e-05, + "loss": 0.5235, + "step": 1279 + }, + { + "epoch": 0.11, + "learning_rate": 1.9690156942210912e-05, + "loss": 0.5159, + "step": 1280 + }, + { + "epoch": 0.11, + "learning_rate": 1.968948724220715e-05, + "loss": 0.5012, + "step": 1281 + }, + { + "epoch": 0.11, + "learning_rate": 1.9688816830647743e-05, + "loss": 0.5233, + "step": 1282 + }, + { + "epoch": 0.11, + "learning_rate": 1.9688145707581927e-05, + "loss": 0.5285, + "step": 1283 + }, + { + "epoch": 0.11, + "learning_rate": 1.9687473873058987e-05, + "loss": 0.4938, + "step": 1284 + }, + { + "epoch": 0.11, + "learning_rate": 1.9686801327128256e-05, + "loss": 0.5234, + "step": 1285 + }, + { + "epoch": 0.11, + "learning_rate": 1.968612806983913e-05, + "loss": 0.5155, + "step": 1286 + }, + { + "epoch": 0.11, + "learning_rate": 1.9685454101241048e-05, + "loss": 0.5218, + "step": 1287 + }, + { + "epoch": 0.11, + "learning_rate": 1.9684779421383496e-05, + "loss": 0.5122, + "step": 1288 + }, + { + "epoch": 0.11, + "learning_rate": 1.968410403031603e-05, + "loss": 0.5191, + "step": 1289 + }, + { + "epoch": 0.11, + "learning_rate": 1.9683427928088243e-05, + "loss": 0.5145, + "step": 1290 + }, + { + "epoch": 0.11, + "learning_rate": 1.9682751114749783e-05, + "loss": 0.4944, + "step": 1291 + }, + { + "epoch": 0.11, + "learning_rate": 1.968207359035036e-05, + "loss": 0.5042, + "step": 1292 + }, + { + "epoch": 0.11, + "learning_rate": 1.9681395354939714e-05, + "loss": 0.5227, + "step": 1293 + }, + { + "epoch": 0.11, + "learning_rate": 1.9680716408567667e-05, + "loss": 0.4942, + "step": 1294 + }, + { + "epoch": 0.11, + "learning_rate": 1.968003675128407e-05, + "loss": 0.5026, + "step": 1295 + }, + { + "epoch": 0.11, + "learning_rate": 1.967935638313884e-05, + "loss": 0.5096, + "step": 1296 + }, + { + "epoch": 0.11, + "learning_rate": 1.9678675304181932e-05, + "loss": 0.5114, + "step": 1297 + }, + { + "epoch": 0.11, + "learning_rate": 1.9677993514463368e-05, + "loss": 0.5041, + "step": 1298 + }, + { + "epoch": 0.11, + "learning_rate": 1.9677311014033217e-05, + "loss": 0.5283, + "step": 1299 + }, + { + "epoch": 0.11, + "learning_rate": 1.967662780294159e-05, + "loss": 0.524, + "step": 1300 + }, + { + "epoch": 0.11, + "learning_rate": 1.9675943881238672e-05, + "loss": 0.5259, + "step": 1301 + }, + { + "epoch": 0.11, + "learning_rate": 1.9675259248974675e-05, + "loss": 0.5022, + "step": 1302 + }, + { + "epoch": 0.11, + "learning_rate": 1.967457390619988e-05, + "loss": 0.5028, + "step": 1303 + }, + { + "epoch": 0.11, + "learning_rate": 1.9673887852964623e-05, + "loss": 0.5134, + "step": 1304 + }, + { + "epoch": 0.11, + "learning_rate": 1.9673201089319275e-05, + "loss": 0.5189, + "step": 1305 + }, + { + "epoch": 0.11, + "learning_rate": 1.9672513615314278e-05, + "loss": 0.507, + "step": 1306 + }, + { + "epoch": 0.11, + "learning_rate": 1.9671825431000107e-05, + "loss": 0.5226, + "step": 1307 + }, + { + "epoch": 0.11, + "learning_rate": 1.9671136536427308e-05, + "loss": 0.5185, + "step": 1308 + }, + { + "epoch": 0.11, + "learning_rate": 1.9670446931646463e-05, + "loss": 0.5154, + "step": 1309 + }, + { + "epoch": 0.11, + "learning_rate": 1.966975661670822e-05, + "loss": 0.5179, + "step": 1310 + }, + { + "epoch": 0.11, + "learning_rate": 1.966906559166327e-05, + "loss": 0.541, + "step": 1311 + }, + { + "epoch": 0.11, + "learning_rate": 1.966837385656236e-05, + "loss": 0.5082, + "step": 1312 + }, + { + "epoch": 0.11, + "learning_rate": 1.9667681411456286e-05, + "loss": 0.4997, + "step": 1313 + }, + { + "epoch": 0.11, + "learning_rate": 1.96669882563959e-05, + "loss": 0.5202, + "step": 1314 + }, + { + "epoch": 0.11, + "learning_rate": 1.9666294391432108e-05, + "loss": 0.5297, + "step": 1315 + }, + { + "epoch": 0.11, + "learning_rate": 1.966559981661586e-05, + "loss": 0.5074, + "step": 1316 + }, + { + "epoch": 0.11, + "learning_rate": 1.9664904531998165e-05, + "loss": 0.4969, + "step": 1317 + }, + { + "epoch": 0.11, + "learning_rate": 1.9664208537630073e-05, + "loss": 0.5015, + "step": 1318 + }, + { + "epoch": 0.11, + "learning_rate": 1.966351183356271e-05, + "loss": 0.5037, + "step": 1319 + }, + { + "epoch": 0.11, + "learning_rate": 1.9662814419847228e-05, + "loss": 0.4986, + "step": 1320 + }, + { + "epoch": 0.11, + "learning_rate": 1.966211629653485e-05, + "loss": 0.5048, + "step": 1321 + }, + { + "epoch": 0.11, + "learning_rate": 1.9661417463676834e-05, + "loss": 0.5106, + "step": 1322 + }, + { + "epoch": 0.11, + "learning_rate": 1.966071792132451e-05, + "loss": 0.5144, + "step": 1323 + }, + { + "epoch": 0.11, + "learning_rate": 1.9660017669529236e-05, + "loss": 0.5227, + "step": 1324 + }, + { + "epoch": 0.11, + "learning_rate": 1.965931670834245e-05, + "loss": 0.5105, + "step": 1325 + }, + { + "epoch": 0.11, + "learning_rate": 1.965861503781562e-05, + "loss": 0.4987, + "step": 1326 + }, + { + "epoch": 0.11, + "learning_rate": 1.9657912658000272e-05, + "loss": 0.5063, + "step": 1327 + }, + { + "epoch": 0.11, + "learning_rate": 1.965720956894799e-05, + "loss": 0.5112, + "step": 1328 + }, + { + "epoch": 0.11, + "learning_rate": 1.9656505770710404e-05, + "loss": 0.5036, + "step": 1329 + }, + { + "epoch": 0.11, + "learning_rate": 1.9655801263339198e-05, + "loss": 0.4904, + "step": 1330 + }, + { + "epoch": 0.11, + "learning_rate": 1.965509604688611e-05, + "loss": 0.5203, + "step": 1331 + }, + { + "epoch": 0.11, + "learning_rate": 1.9654390121402927e-05, + "loss": 0.5097, + "step": 1332 + }, + { + "epoch": 0.11, + "learning_rate": 1.965368348694149e-05, + "loss": 0.5146, + "step": 1333 + }, + { + "epoch": 0.11, + "learning_rate": 1.965297614355369e-05, + "loss": 0.4991, + "step": 1334 + }, + { + "epoch": 0.11, + "learning_rate": 1.965226809129147e-05, + "loss": 0.5255, + "step": 1335 + }, + { + "epoch": 0.11, + "learning_rate": 1.9651559330206827e-05, + "loss": 0.5182, + "step": 1336 + }, + { + "epoch": 0.11, + "learning_rate": 1.9650849860351818e-05, + "loss": 0.5092, + "step": 1337 + }, + { + "epoch": 0.11, + "learning_rate": 1.9650139681778527e-05, + "loss": 0.537, + "step": 1338 + }, + { + "epoch": 0.11, + "learning_rate": 1.9649428794539122e-05, + "loss": 0.5066, + "step": 1339 + }, + { + "epoch": 0.11, + "learning_rate": 1.9648717198685798e-05, + "loss": 0.5199, + "step": 1340 + }, + { + "epoch": 0.11, + "learning_rate": 1.9648004894270816e-05, + "loss": 0.4998, + "step": 1341 + }, + { + "epoch": 0.11, + "learning_rate": 1.9647291881346485e-05, + "loss": 0.5155, + "step": 1342 + }, + { + "epoch": 0.11, + "learning_rate": 1.9646578159965163e-05, + "loss": 0.5068, + "step": 1343 + }, + { + "epoch": 0.11, + "learning_rate": 1.9645863730179263e-05, + "loss": 0.4993, + "step": 1344 + }, + { + "epoch": 0.11, + "learning_rate": 1.964514859204125e-05, + "loss": 0.5225, + "step": 1345 + }, + { + "epoch": 0.11, + "learning_rate": 1.9644432745603644e-05, + "loss": 0.5065, + "step": 1346 + }, + { + "epoch": 0.11, + "learning_rate": 1.9643716190919014e-05, + "loss": 0.5013, + "step": 1347 + }, + { + "epoch": 0.11, + "learning_rate": 1.9642998928039976e-05, + "loss": 0.499, + "step": 1348 + }, + { + "epoch": 0.11, + "learning_rate": 1.96422809570192e-05, + "loss": 0.515, + "step": 1349 + }, + { + "epoch": 0.11, + "learning_rate": 1.9641562277909424e-05, + "loss": 0.5082, + "step": 1350 + }, + { + "epoch": 0.11, + "learning_rate": 1.9640842890763413e-05, + "loss": 0.5162, + "step": 1351 + }, + { + "epoch": 0.11, + "learning_rate": 1.9640122795633997e-05, + "loss": 0.4928, + "step": 1352 + }, + { + "epoch": 0.11, + "learning_rate": 1.9639401992574065e-05, + "loss": 0.4976, + "step": 1353 + }, + { + "epoch": 0.11, + "learning_rate": 1.9638680481636535e-05, + "loss": 0.5015, + "step": 1354 + }, + { + "epoch": 0.11, + "learning_rate": 1.9637958262874404e-05, + "loss": 0.4962, + "step": 1355 + }, + { + "epoch": 0.11, + "learning_rate": 1.963723533634071e-05, + "loss": 0.5228, + "step": 1356 + }, + { + "epoch": 0.11, + "learning_rate": 1.9636511702088535e-05, + "loss": 0.5255, + "step": 1357 + }, + { + "epoch": 0.11, + "learning_rate": 1.963578736017102e-05, + "loss": 0.5213, + "step": 1358 + }, + { + "epoch": 0.11, + "learning_rate": 1.963506231064136e-05, + "loss": 0.5361, + "step": 1359 + }, + { + "epoch": 0.11, + "learning_rate": 1.9634336553552803e-05, + "loss": 0.5014, + "step": 1360 + }, + { + "epoch": 0.11, + "learning_rate": 1.9633610088958638e-05, + "loss": 0.5107, + "step": 1361 + }, + { + "epoch": 0.11, + "learning_rate": 1.9632882916912217e-05, + "loss": 0.501, + "step": 1362 + }, + { + "epoch": 0.11, + "learning_rate": 1.9632155037466942e-05, + "loss": 0.513, + "step": 1363 + }, + { + "epoch": 0.11, + "learning_rate": 1.9631426450676264e-05, + "loss": 0.4982, + "step": 1364 + }, + { + "epoch": 0.11, + "learning_rate": 1.9630697156593688e-05, + "loss": 0.5127, + "step": 1365 + }, + { + "epoch": 0.11, + "learning_rate": 1.962996715527277e-05, + "loss": 0.488, + "step": 1366 + }, + { + "epoch": 0.11, + "learning_rate": 1.9629236446767118e-05, + "loss": 0.5273, + "step": 1367 + }, + { + "epoch": 0.11, + "learning_rate": 1.962850503113039e-05, + "loss": 0.506, + "step": 1368 + }, + { + "epoch": 0.11, + "learning_rate": 1.9627772908416302e-05, + "loss": 0.4915, + "step": 1369 + }, + { + "epoch": 0.11, + "learning_rate": 1.9627040078678617e-05, + "loss": 0.506, + "step": 1370 + }, + { + "epoch": 0.11, + "learning_rate": 1.9626306541971153e-05, + "loss": 0.5139, + "step": 1371 + }, + { + "epoch": 0.11, + "learning_rate": 1.962557229834777e-05, + "loss": 0.4852, + "step": 1372 + }, + { + "epoch": 0.11, + "learning_rate": 1.9624837347862398e-05, + "loss": 0.532, + "step": 1373 + }, + { + "epoch": 0.11, + "learning_rate": 1.9624101690569e-05, + "loss": 0.5052, + "step": 1374 + }, + { + "epoch": 0.12, + "learning_rate": 1.9623365326521603e-05, + "loss": 0.5007, + "step": 1375 + }, + { + "epoch": 0.12, + "learning_rate": 1.9622628255774288e-05, + "loss": 0.4933, + "step": 1376 + }, + { + "epoch": 0.12, + "learning_rate": 1.9621890478381175e-05, + "loss": 0.5235, + "step": 1377 + }, + { + "epoch": 0.12, + "learning_rate": 1.9621151994396443e-05, + "loss": 0.5125, + "step": 1378 + }, + { + "epoch": 0.12, + "learning_rate": 1.962041280387433e-05, + "loss": 0.5039, + "step": 1379 + }, + { + "epoch": 0.12, + "learning_rate": 1.9619672906869114e-05, + "loss": 0.5263, + "step": 1380 + }, + { + "epoch": 0.12, + "learning_rate": 1.961893230343513e-05, + "loss": 0.5178, + "step": 1381 + }, + { + "epoch": 0.12, + "learning_rate": 1.9618190993626768e-05, + "loss": 0.5091, + "step": 1382 + }, + { + "epoch": 0.12, + "learning_rate": 1.961744897749846e-05, + "loss": 0.5201, + "step": 1383 + }, + { + "epoch": 0.12, + "learning_rate": 1.9616706255104705e-05, + "loss": 0.5166, + "step": 1384 + }, + { + "epoch": 0.12, + "learning_rate": 1.9615962826500038e-05, + "loss": 0.5028, + "step": 1385 + }, + { + "epoch": 0.12, + "learning_rate": 1.961521869173906e-05, + "loss": 0.5015, + "step": 1386 + }, + { + "epoch": 0.12, + "learning_rate": 1.9614473850876413e-05, + "loss": 0.507, + "step": 1387 + }, + { + "epoch": 0.12, + "learning_rate": 1.9613728303966794e-05, + "loss": 0.513, + "step": 1388 + }, + { + "epoch": 0.12, + "learning_rate": 1.961298205106496e-05, + "loss": 0.5002, + "step": 1389 + }, + { + "epoch": 0.12, + "learning_rate": 1.9612235092225704e-05, + "loss": 0.5226, + "step": 1390 + }, + { + "epoch": 0.12, + "learning_rate": 1.9611487427503883e-05, + "loss": 0.4932, + "step": 1391 + }, + { + "epoch": 0.12, + "learning_rate": 1.9610739056954406e-05, + "loss": 0.5077, + "step": 1392 + }, + { + "epoch": 0.12, + "learning_rate": 1.9609989980632222e-05, + "loss": 0.5023, + "step": 1393 + }, + { + "epoch": 0.12, + "learning_rate": 1.9609240198592344e-05, + "loss": 0.52, + "step": 1394 + }, + { + "epoch": 0.12, + "learning_rate": 1.9608489710889837e-05, + "loss": 0.488, + "step": 1395 + }, + { + "epoch": 0.12, + "learning_rate": 1.9607738517579807e-05, + "loss": 0.4979, + "step": 1396 + }, + { + "epoch": 0.12, + "learning_rate": 1.9606986618717428e-05, + "loss": 0.5187, + "step": 1397 + }, + { + "epoch": 0.12, + "learning_rate": 1.9606234014357905e-05, + "loss": 0.5141, + "step": 1398 + }, + { + "epoch": 0.12, + "learning_rate": 1.9605480704556516e-05, + "loss": 0.5124, + "step": 1399 + }, + { + "epoch": 0.12, + "learning_rate": 1.960472668936857e-05, + "loss": 0.4959, + "step": 1400 + }, + { + "epoch": 0.12, + "learning_rate": 1.960397196884945e-05, + "loss": 0.495, + "step": 1401 + }, + { + "epoch": 0.12, + "learning_rate": 1.960321654305457e-05, + "loss": 0.514, + "step": 1402 + }, + { + "epoch": 0.12, + "learning_rate": 1.9602460412039416e-05, + "loss": 0.5115, + "step": 1403 + }, + { + "epoch": 0.12, + "learning_rate": 1.9601703575859504e-05, + "loss": 0.527, + "step": 1404 + }, + { + "epoch": 0.12, + "learning_rate": 1.960094603457042e-05, + "loss": 0.5074, + "step": 1405 + }, + { + "epoch": 0.12, + "learning_rate": 1.960018778822779e-05, + "loss": 0.51, + "step": 1406 + }, + { + "epoch": 0.12, + "learning_rate": 1.9599428836887302e-05, + "loss": 0.5231, + "step": 1407 + }, + { + "epoch": 0.12, + "learning_rate": 1.9598669180604685e-05, + "loss": 0.5108, + "step": 1408 + }, + { + "epoch": 0.12, + "learning_rate": 1.959790881943573e-05, + "loss": 0.5175, + "step": 1409 + }, + { + "epoch": 0.12, + "learning_rate": 1.959714775343627e-05, + "loss": 0.4948, + "step": 1410 + }, + { + "epoch": 0.12, + "learning_rate": 1.9596385982662197e-05, + "loss": 0.5196, + "step": 1411 + }, + { + "epoch": 0.12, + "learning_rate": 1.959562350716945e-05, + "loss": 0.4951, + "step": 1412 + }, + { + "epoch": 0.12, + "learning_rate": 1.959486032701403e-05, + "loss": 0.5001, + "step": 1413 + }, + { + "epoch": 0.12, + "learning_rate": 1.959409644225197e-05, + "loss": 0.5112, + "step": 1414 + }, + { + "epoch": 0.12, + "learning_rate": 1.959333185293937e-05, + "loss": 0.5144, + "step": 1415 + }, + { + "epoch": 0.12, + "learning_rate": 1.9592566559132384e-05, + "loss": 0.5077, + "step": 1416 + }, + { + "epoch": 0.12, + "learning_rate": 1.9591800560887207e-05, + "loss": 0.5186, + "step": 1417 + }, + { + "epoch": 0.12, + "learning_rate": 1.9591033858260094e-05, + "loss": 0.5239, + "step": 1418 + }, + { + "epoch": 0.12, + "learning_rate": 1.9590266451307348e-05, + "loss": 0.5225, + "step": 1419 + }, + { + "epoch": 0.12, + "learning_rate": 1.958949834008532e-05, + "loss": 0.5016, + "step": 1420 + }, + { + "epoch": 0.12, + "learning_rate": 1.958872952465042e-05, + "loss": 0.4952, + "step": 1421 + }, + { + "epoch": 0.12, + "learning_rate": 1.9587960005059104e-05, + "loss": 0.4957, + "step": 1422 + }, + { + "epoch": 0.12, + "learning_rate": 1.9587189781367888e-05, + "loss": 0.5117, + "step": 1423 + }, + { + "epoch": 0.12, + "learning_rate": 1.958641885363333e-05, + "loss": 0.5254, + "step": 1424 + }, + { + "epoch": 0.12, + "learning_rate": 1.9585647221912044e-05, + "loss": 0.5041, + "step": 1425 + }, + { + "epoch": 0.12, + "learning_rate": 1.9584874886260695e-05, + "loss": 0.4954, + "step": 1426 + }, + { + "epoch": 0.12, + "learning_rate": 1.9584101846736002e-05, + "loss": 0.5099, + "step": 1427 + }, + { + "epoch": 0.12, + "learning_rate": 1.9583328103394733e-05, + "loss": 0.5261, + "step": 1428 + }, + { + "epoch": 0.12, + "learning_rate": 1.9582553656293707e-05, + "loss": 0.4948, + "step": 1429 + }, + { + "epoch": 0.12, + "learning_rate": 1.9581778505489797e-05, + "loss": 0.5298, + "step": 1430 + }, + { + "epoch": 0.12, + "learning_rate": 1.9581002651039928e-05, + "loss": 0.5066, + "step": 1431 + }, + { + "epoch": 0.12, + "learning_rate": 1.9580226093001077e-05, + "loss": 0.5078, + "step": 1432 + }, + { + "epoch": 0.12, + "learning_rate": 1.9579448831430264e-05, + "loss": 0.5214, + "step": 1433 + }, + { + "epoch": 0.12, + "learning_rate": 1.9578670866384574e-05, + "loss": 0.5257, + "step": 1434 + }, + { + "epoch": 0.12, + "learning_rate": 1.9577892197921136e-05, + "loss": 0.5086, + "step": 1435 + }, + { + "epoch": 0.12, + "learning_rate": 1.9577112826097134e-05, + "loss": 0.5219, + "step": 1436 + }, + { + "epoch": 0.12, + "learning_rate": 1.95763327509698e-05, + "loss": 0.509, + "step": 1437 + }, + { + "epoch": 0.12, + "learning_rate": 1.9575551972596422e-05, + "loss": 0.5082, + "step": 1438 + }, + { + "epoch": 0.12, + "learning_rate": 1.9574770491034333e-05, + "loss": 0.5165, + "step": 1439 + }, + { + "epoch": 0.12, + "learning_rate": 1.9573988306340924e-05, + "loss": 0.5104, + "step": 1440 + }, + { + "epoch": 0.12, + "learning_rate": 1.9573205418573634e-05, + "loss": 0.5131, + "step": 1441 + }, + { + "epoch": 0.12, + "learning_rate": 1.9572421827789954e-05, + "loss": 0.5001, + "step": 1442 + }, + { + "epoch": 0.12, + "learning_rate": 1.957163753404743e-05, + "loss": 0.5068, + "step": 1443 + }, + { + "epoch": 0.12, + "learning_rate": 1.957085253740366e-05, + "loss": 0.5094, + "step": 1444 + }, + { + "epoch": 0.12, + "learning_rate": 1.9570066837916285e-05, + "loss": 0.504, + "step": 1445 + }, + { + "epoch": 0.12, + "learning_rate": 1.956928043564301e-05, + "loss": 0.5258, + "step": 1446 + }, + { + "epoch": 0.12, + "learning_rate": 1.956849333064158e-05, + "loss": 0.5101, + "step": 1447 + }, + { + "epoch": 0.12, + "learning_rate": 1.9567705522969796e-05, + "loss": 0.5094, + "step": 1448 + }, + { + "epoch": 0.12, + "learning_rate": 1.9566917012685515e-05, + "loss": 0.5293, + "step": 1449 + }, + { + "epoch": 0.12, + "learning_rate": 1.9566127799846642e-05, + "loss": 0.515, + "step": 1450 + }, + { + "epoch": 0.12, + "learning_rate": 1.9565337884511128e-05, + "loss": 0.4926, + "step": 1451 + }, + { + "epoch": 0.12, + "learning_rate": 1.956454726673699e-05, + "loss": 0.5152, + "step": 1452 + }, + { + "epoch": 0.12, + "learning_rate": 1.9563755946582277e-05, + "loss": 0.5183, + "step": 1453 + }, + { + "epoch": 0.12, + "learning_rate": 1.956296392410511e-05, + "loss": 0.5313, + "step": 1454 + }, + { + "epoch": 0.12, + "learning_rate": 1.9562171199363646e-05, + "loss": 0.4952, + "step": 1455 + }, + { + "epoch": 0.12, + "learning_rate": 1.9561377772416103e-05, + "loss": 0.5244, + "step": 1456 + }, + { + "epoch": 0.12, + "learning_rate": 1.9560583643320745e-05, + "loss": 0.5044, + "step": 1457 + }, + { + "epoch": 0.12, + "learning_rate": 1.955978881213589e-05, + "loss": 0.5245, + "step": 1458 + }, + { + "epoch": 0.12, + "learning_rate": 1.9558993278919904e-05, + "loss": 0.5117, + "step": 1459 + }, + { + "epoch": 0.12, + "learning_rate": 1.9558197043731214e-05, + "loss": 0.4932, + "step": 1460 + }, + { + "epoch": 0.12, + "learning_rate": 1.9557400106628285e-05, + "loss": 0.4863, + "step": 1461 + }, + { + "epoch": 0.12, + "learning_rate": 1.9556602467669645e-05, + "loss": 0.5167, + "step": 1462 + }, + { + "epoch": 0.12, + "learning_rate": 1.9555804126913868e-05, + "loss": 0.5063, + "step": 1463 + }, + { + "epoch": 0.12, + "learning_rate": 1.9555005084419585e-05, + "loss": 0.5097, + "step": 1464 + }, + { + "epoch": 0.12, + "learning_rate": 1.9554205340245468e-05, + "loss": 0.5213, + "step": 1465 + }, + { + "epoch": 0.12, + "learning_rate": 1.955340489445025e-05, + "loss": 0.4985, + "step": 1466 + }, + { + "epoch": 0.12, + "learning_rate": 1.9552603747092714e-05, + "loss": 0.5026, + "step": 1467 + }, + { + "epoch": 0.12, + "learning_rate": 1.9551801898231692e-05, + "loss": 0.506, + "step": 1468 + }, + { + "epoch": 0.12, + "learning_rate": 1.9550999347926064e-05, + "loss": 0.5001, + "step": 1469 + }, + { + "epoch": 0.12, + "learning_rate": 1.955019609623477e-05, + "loss": 0.5154, + "step": 1470 + }, + { + "epoch": 0.12, + "learning_rate": 1.95493921432168e-05, + "loss": 0.5028, + "step": 1471 + }, + { + "epoch": 0.12, + "learning_rate": 1.9548587488931187e-05, + "loss": 0.5032, + "step": 1472 + }, + { + "epoch": 0.12, + "learning_rate": 1.9547782133437024e-05, + "loss": 0.508, + "step": 1473 + }, + { + "epoch": 0.12, + "learning_rate": 1.9546976076793456e-05, + "loss": 0.5321, + "step": 1474 + }, + { + "epoch": 0.12, + "learning_rate": 1.954616931905967e-05, + "loss": 0.4916, + "step": 1475 + }, + { + "epoch": 0.12, + "learning_rate": 1.954536186029492e-05, + "loss": 0.4889, + "step": 1476 + }, + { + "epoch": 0.12, + "learning_rate": 1.954455370055849e-05, + "loss": 0.5233, + "step": 1477 + }, + { + "epoch": 0.12, + "learning_rate": 1.9543744839909743e-05, + "loss": 0.4962, + "step": 1478 + }, + { + "epoch": 0.12, + "learning_rate": 1.9542935278408066e-05, + "loss": 0.4988, + "step": 1479 + }, + { + "epoch": 0.12, + "learning_rate": 1.9542125016112913e-05, + "loss": 0.5181, + "step": 1480 + }, + { + "epoch": 0.12, + "learning_rate": 1.954131405308379e-05, + "loss": 0.5045, + "step": 1481 + }, + { + "epoch": 0.12, + "learning_rate": 1.9540502389380245e-05, + "loss": 0.5008, + "step": 1482 + }, + { + "epoch": 0.12, + "learning_rate": 1.953969002506189e-05, + "loss": 0.522, + "step": 1483 + }, + { + "epoch": 0.12, + "learning_rate": 1.9538876960188378e-05, + "loss": 0.5198, + "step": 1484 + }, + { + "epoch": 0.12, + "learning_rate": 1.9538063194819418e-05, + "loss": 0.5029, + "step": 1485 + }, + { + "epoch": 0.12, + "learning_rate": 1.9537248729014767e-05, + "loss": 0.5282, + "step": 1486 + }, + { + "epoch": 0.12, + "learning_rate": 1.9536433562834235e-05, + "loss": 0.5243, + "step": 1487 + }, + { + "epoch": 0.12, + "learning_rate": 1.953561769633769e-05, + "loss": 0.5025, + "step": 1488 + }, + { + "epoch": 0.12, + "learning_rate": 1.9534801129585044e-05, + "loss": 0.5192, + "step": 1489 + }, + { + "epoch": 0.12, + "learning_rate": 1.953398386263626e-05, + "loss": 0.4863, + "step": 1490 + }, + { + "epoch": 0.12, + "learning_rate": 1.9533165895551356e-05, + "loss": 0.5097, + "step": 1491 + }, + { + "epoch": 0.12, + "learning_rate": 1.95323472283904e-05, + "loss": 0.5092, + "step": 1492 + }, + { + "epoch": 0.12, + "learning_rate": 1.9531527861213514e-05, + "loss": 0.5021, + "step": 1493 + }, + { + "epoch": 0.12, + "learning_rate": 1.9530707794080864e-05, + "loss": 0.5236, + "step": 1494 + }, + { + "epoch": 0.13, + "learning_rate": 1.9529887027052676e-05, + "loss": 0.5116, + "step": 1495 + }, + { + "epoch": 0.13, + "learning_rate": 1.952906556018922e-05, + "loss": 0.5081, + "step": 1496 + }, + { + "epoch": 0.13, + "learning_rate": 1.9528243393550825e-05, + "loss": 0.4812, + "step": 1497 + }, + { + "epoch": 0.13, + "learning_rate": 1.9527420527197867e-05, + "loss": 0.5272, + "step": 1498 + }, + { + "epoch": 0.13, + "learning_rate": 1.9526596961190772e-05, + "loss": 0.4959, + "step": 1499 + }, + { + "epoch": 0.13, + "learning_rate": 1.952577269559002e-05, + "loss": 0.5129, + "step": 1500 + }, + { + "epoch": 0.13, + "learning_rate": 1.952494773045614e-05, + "loss": 0.5061, + "step": 1501 + }, + { + "epoch": 0.13, + "learning_rate": 1.9524122065849722e-05, + "loss": 0.5036, + "step": 1502 + }, + { + "epoch": 0.13, + "learning_rate": 1.9523295701831388e-05, + "loss": 0.5044, + "step": 1503 + }, + { + "epoch": 0.13, + "learning_rate": 1.952246863846183e-05, + "loss": 0.516, + "step": 1504 + }, + { + "epoch": 0.13, + "learning_rate": 1.9521640875801783e-05, + "loss": 0.5064, + "step": 1505 + }, + { + "epoch": 0.13, + "learning_rate": 1.9520812413912032e-05, + "loss": 0.5003, + "step": 1506 + }, + { + "epoch": 0.13, + "learning_rate": 1.9519983252853415e-05, + "loss": 0.5019, + "step": 1507 + }, + { + "epoch": 0.13, + "learning_rate": 1.9519153392686828e-05, + "loss": 0.5233, + "step": 1508 + }, + { + "epoch": 0.13, + "learning_rate": 1.951832283347321e-05, + "loss": 0.516, + "step": 1509 + }, + { + "epoch": 0.13, + "learning_rate": 1.9517491575273552e-05, + "loss": 0.5068, + "step": 1510 + }, + { + "epoch": 0.13, + "learning_rate": 1.9516659618148897e-05, + "loss": 0.5093, + "step": 1511 + }, + { + "epoch": 0.13, + "learning_rate": 1.9515826962160342e-05, + "loss": 0.5433, + "step": 1512 + }, + { + "epoch": 0.13, + "learning_rate": 1.9514993607369037e-05, + "loss": 0.4968, + "step": 1513 + }, + { + "epoch": 0.13, + "learning_rate": 1.9514159553836177e-05, + "loss": 0.5295, + "step": 1514 + }, + { + "epoch": 0.13, + "learning_rate": 1.951332480162301e-05, + "loss": 0.5024, + "step": 1515 + }, + { + "epoch": 0.13, + "learning_rate": 1.9512489350790838e-05, + "loss": 0.4909, + "step": 1516 + }, + { + "epoch": 0.13, + "learning_rate": 1.9511653201401012e-05, + "loss": 0.5222, + "step": 1517 + }, + { + "epoch": 0.13, + "learning_rate": 1.951081635351494e-05, + "loss": 0.538, + "step": 1518 + }, + { + "epoch": 0.13, + "learning_rate": 1.9509978807194075e-05, + "loss": 0.5152, + "step": 1519 + }, + { + "epoch": 0.13, + "learning_rate": 1.950914056249992e-05, + "loss": 0.5195, + "step": 1520 + }, + { + "epoch": 0.13, + "learning_rate": 1.9508301619494033e-05, + "loss": 0.496, + "step": 1521 + }, + { + "epoch": 0.13, + "learning_rate": 1.950746197823802e-05, + "loss": 0.5049, + "step": 1522 + }, + { + "epoch": 0.13, + "learning_rate": 1.9506621638793548e-05, + "loss": 0.4945, + "step": 1523 + }, + { + "epoch": 0.13, + "learning_rate": 1.9505780601222323e-05, + "loss": 0.5202, + "step": 1524 + }, + { + "epoch": 0.13, + "learning_rate": 1.9504938865586107e-05, + "loss": 0.523, + "step": 1525 + }, + { + "epoch": 0.13, + "learning_rate": 1.9504096431946716e-05, + "loss": 0.522, + "step": 1526 + }, + { + "epoch": 0.13, + "learning_rate": 1.9503253300366013e-05, + "loss": 0.49, + "step": 1527 + }, + { + "epoch": 0.13, + "learning_rate": 1.9502409470905913e-05, + "loss": 0.5066, + "step": 1528 + }, + { + "epoch": 0.13, + "learning_rate": 1.950156494362839e-05, + "loss": 0.4991, + "step": 1529 + }, + { + "epoch": 0.13, + "learning_rate": 1.9500719718595454e-05, + "loss": 0.4954, + "step": 1530 + }, + { + "epoch": 0.13, + "learning_rate": 1.9499873795869178e-05, + "loss": 0.5012, + "step": 1531 + }, + { + "epoch": 0.13, + "learning_rate": 1.9499027175511682e-05, + "loss": 0.4998, + "step": 1532 + }, + { + "epoch": 0.13, + "learning_rate": 1.9498179857585143e-05, + "loss": 0.5168, + "step": 1533 + }, + { + "epoch": 0.13, + "learning_rate": 1.949733184215178e-05, + "loss": 0.5179, + "step": 1534 + }, + { + "epoch": 0.13, + "learning_rate": 1.9496483129273866e-05, + "loss": 0.5061, + "step": 1535 + }, + { + "epoch": 0.13, + "learning_rate": 1.9495633719013733e-05, + "loss": 0.527, + "step": 1536 + }, + { + "epoch": 0.13, + "learning_rate": 1.9494783611433754e-05, + "loss": 0.506, + "step": 1537 + }, + { + "epoch": 0.13, + "learning_rate": 1.9493932806596357e-05, + "loss": 0.5057, + "step": 1538 + }, + { + "epoch": 0.13, + "learning_rate": 1.9493081304564025e-05, + "loss": 0.5144, + "step": 1539 + }, + { + "epoch": 0.13, + "learning_rate": 1.9492229105399287e-05, + "loss": 0.518, + "step": 1540 + }, + { + "epoch": 0.13, + "learning_rate": 1.9491376209164726e-05, + "loss": 0.526, + "step": 1541 + }, + { + "epoch": 0.13, + "learning_rate": 1.949052261592297e-05, + "loss": 0.5012, + "step": 1542 + }, + { + "epoch": 0.13, + "learning_rate": 1.948966832573671e-05, + "loss": 0.5005, + "step": 1543 + }, + { + "epoch": 0.13, + "learning_rate": 1.9488813338668676e-05, + "loss": 0.5124, + "step": 1544 + }, + { + "epoch": 0.13, + "learning_rate": 1.948795765478166e-05, + "loss": 0.5017, + "step": 1545 + }, + { + "epoch": 0.13, + "learning_rate": 1.9487101274138494e-05, + "loss": 0.5069, + "step": 1546 + }, + { + "epoch": 0.13, + "learning_rate": 1.9486244196802075e-05, + "loss": 0.4965, + "step": 1547 + }, + { + "epoch": 0.13, + "learning_rate": 1.9485386422835334e-05, + "loss": 0.5156, + "step": 1548 + }, + { + "epoch": 0.13, + "learning_rate": 1.948452795230127e-05, + "loss": 0.5098, + "step": 1549 + }, + { + "epoch": 0.13, + "learning_rate": 1.948366878526292e-05, + "loss": 0.5146, + "step": 1550 + }, + { + "epoch": 0.13, + "learning_rate": 1.948280892178338e-05, + "loss": 0.4822, + "step": 1551 + }, + { + "epoch": 0.13, + "learning_rate": 1.9481948361925796e-05, + "loss": 0.52, + "step": 1552 + }, + { + "epoch": 0.13, + "learning_rate": 1.9481087105753364e-05, + "loss": 0.5043, + "step": 1553 + }, + { + "epoch": 0.13, + "learning_rate": 1.948022515332933e-05, + "loss": 0.4827, + "step": 1554 + }, + { + "epoch": 0.13, + "learning_rate": 1.9479362504716987e-05, + "loss": 0.5335, + "step": 1555 + }, + { + "epoch": 0.13, + "learning_rate": 1.9478499159979693e-05, + "loss": 0.5135, + "step": 1556 + }, + { + "epoch": 0.13, + "learning_rate": 1.9477635119180843e-05, + "loss": 0.5032, + "step": 1557 + }, + { + "epoch": 0.13, + "learning_rate": 1.947677038238389e-05, + "loss": 0.5122, + "step": 1558 + }, + { + "epoch": 0.13, + "learning_rate": 1.947590494965234e-05, + "loss": 0.5083, + "step": 1559 + }, + { + "epoch": 0.13, + "learning_rate": 1.9475038821049744e-05, + "loss": 0.5332, + "step": 1560 + }, + { + "epoch": 0.13, + "learning_rate": 1.9474171996639702e-05, + "loss": 0.4818, + "step": 1561 + }, + { + "epoch": 0.13, + "learning_rate": 1.947330447648588e-05, + "loss": 0.5206, + "step": 1562 + }, + { + "epoch": 0.13, + "learning_rate": 1.9472436260651976e-05, + "loss": 0.5059, + "step": 1563 + }, + { + "epoch": 0.13, + "learning_rate": 1.947156734920175e-05, + "loss": 0.5188, + "step": 1564 + }, + { + "epoch": 0.13, + "learning_rate": 1.9470697742199018e-05, + "loss": 0.5141, + "step": 1565 + }, + { + "epoch": 0.13, + "learning_rate": 1.9469827439707632e-05, + "loss": 0.505, + "step": 1566 + }, + { + "epoch": 0.13, + "learning_rate": 1.946895644179151e-05, + "loss": 0.5005, + "step": 1567 + }, + { + "epoch": 0.13, + "learning_rate": 1.946808474851461e-05, + "loss": 0.5152, + "step": 1568 + }, + { + "epoch": 0.13, + "learning_rate": 1.9467212359940944e-05, + "loss": 0.5156, + "step": 1569 + }, + { + "epoch": 0.13, + "learning_rate": 1.9466339276134584e-05, + "loss": 0.5007, + "step": 1570 + }, + { + "epoch": 0.13, + "learning_rate": 1.946546549715964e-05, + "loss": 0.514, + "step": 1571 + }, + { + "epoch": 0.13, + "learning_rate": 1.9464591023080274e-05, + "loss": 0.5101, + "step": 1572 + }, + { + "epoch": 0.13, + "learning_rate": 1.9463715853960714e-05, + "loss": 0.5019, + "step": 1573 + }, + { + "epoch": 0.13, + "learning_rate": 1.9462839989865226e-05, + "loss": 0.5165, + "step": 1574 + }, + { + "epoch": 0.13, + "learning_rate": 1.9461963430858125e-05, + "loss": 0.5078, + "step": 1575 + }, + { + "epoch": 0.13, + "learning_rate": 1.9461086177003788e-05, + "loss": 0.5235, + "step": 1576 + }, + { + "epoch": 0.13, + "learning_rate": 1.946020822836663e-05, + "loss": 0.4954, + "step": 1577 + }, + { + "epoch": 0.13, + "learning_rate": 1.945932958501113e-05, + "loss": 0.5357, + "step": 1578 + }, + { + "epoch": 0.13, + "learning_rate": 1.945845024700181e-05, + "loss": 0.4957, + "step": 1579 + }, + { + "epoch": 0.13, + "learning_rate": 1.9457570214403242e-05, + "loss": 0.5249, + "step": 1580 + }, + { + "epoch": 0.13, + "learning_rate": 1.9456689487280056e-05, + "loss": 0.5397, + "step": 1581 + }, + { + "epoch": 0.13, + "learning_rate": 1.9455808065696925e-05, + "loss": 0.5026, + "step": 1582 + }, + { + "epoch": 0.13, + "learning_rate": 1.9454925949718583e-05, + "loss": 0.4986, + "step": 1583 + }, + { + "epoch": 0.13, + "learning_rate": 1.9454043139409803e-05, + "loss": 0.5172, + "step": 1584 + }, + { + "epoch": 0.13, + "learning_rate": 1.945315963483542e-05, + "loss": 0.5243, + "step": 1585 + }, + { + "epoch": 0.13, + "learning_rate": 1.945227543606031e-05, + "loss": 0.4918, + "step": 1586 + }, + { + "epoch": 0.13, + "learning_rate": 1.945139054314941e-05, + "loss": 0.5084, + "step": 1587 + }, + { + "epoch": 0.13, + "learning_rate": 1.945050495616769e-05, + "loss": 0.5445, + "step": 1588 + }, + { + "epoch": 0.13, + "learning_rate": 1.9449618675180205e-05, + "loss": 0.5013, + "step": 1589 + }, + { + "epoch": 0.13, + "learning_rate": 1.9448731700252025e-05, + "loss": 0.5026, + "step": 1590 + }, + { + "epoch": 0.13, + "learning_rate": 1.9447844031448288e-05, + "loss": 0.5368, + "step": 1591 + }, + { + "epoch": 0.13, + "learning_rate": 1.944695566883418e-05, + "loss": 0.5089, + "step": 1592 + }, + { + "epoch": 0.13, + "learning_rate": 1.9446066612474942e-05, + "loss": 0.4996, + "step": 1593 + }, + { + "epoch": 0.13, + "learning_rate": 1.9445176862435864e-05, + "loss": 0.5315, + "step": 1594 + }, + { + "epoch": 0.13, + "learning_rate": 1.944428641878228e-05, + "loss": 0.4945, + "step": 1595 + }, + { + "epoch": 0.13, + "learning_rate": 1.9443395281579583e-05, + "loss": 0.5109, + "step": 1596 + }, + { + "epoch": 0.13, + "learning_rate": 1.9442503450893216e-05, + "loss": 0.4996, + "step": 1597 + }, + { + "epoch": 0.13, + "learning_rate": 1.944161092678867e-05, + "loss": 0.4923, + "step": 1598 + }, + { + "epoch": 0.13, + "learning_rate": 1.9440717709331484e-05, + "loss": 0.5056, + "step": 1599 + }, + { + "epoch": 0.13, + "learning_rate": 1.943982379858726e-05, + "loss": 0.5007, + "step": 1600 + }, + { + "epoch": 0.13, + "learning_rate": 1.943892919462164e-05, + "loss": 0.498, + "step": 1601 + }, + { + "epoch": 0.13, + "learning_rate": 1.943803389750032e-05, + "loss": 0.5099, + "step": 1602 + }, + { + "epoch": 0.13, + "learning_rate": 1.943713790728904e-05, + "loss": 0.5205, + "step": 1603 + }, + { + "epoch": 0.13, + "learning_rate": 1.943624122405361e-05, + "loss": 0.5158, + "step": 1604 + }, + { + "epoch": 0.13, + "learning_rate": 1.9435343847859873e-05, + "loss": 0.5149, + "step": 1605 + }, + { + "epoch": 0.13, + "learning_rate": 1.9434445778773724e-05, + "loss": 0.5091, + "step": 1606 + }, + { + "epoch": 0.13, + "learning_rate": 1.9433547016861124e-05, + "loss": 0.5026, + "step": 1607 + }, + { + "epoch": 0.13, + "learning_rate": 1.9432647562188062e-05, + "loss": 0.502, + "step": 1608 + }, + { + "epoch": 0.13, + "learning_rate": 1.9431747414820597e-05, + "loss": 0.4999, + "step": 1609 + }, + { + "epoch": 0.13, + "learning_rate": 1.9430846574824835e-05, + "loss": 0.5014, + "step": 1610 + }, + { + "epoch": 0.13, + "learning_rate": 1.9429945042266925e-05, + "loss": 0.4999, + "step": 1611 + }, + { + "epoch": 0.13, + "learning_rate": 1.9429042817213072e-05, + "loss": 0.5387, + "step": 1612 + }, + { + "epoch": 0.13, + "learning_rate": 1.9428139899729538e-05, + "loss": 0.5215, + "step": 1613 + }, + { + "epoch": 0.14, + "learning_rate": 1.9427236289882618e-05, + "loss": 0.49, + "step": 1614 + }, + { + "epoch": 0.14, + "learning_rate": 1.9426331987738678e-05, + "loss": 0.5053, + "step": 1615 + }, + { + "epoch": 0.14, + "learning_rate": 1.9425426993364126e-05, + "loss": 0.5108, + "step": 1616 + }, + { + "epoch": 0.14, + "learning_rate": 1.9424521306825414e-05, + "loss": 0.5044, + "step": 1617 + }, + { + "epoch": 0.14, + "learning_rate": 1.942361492818906e-05, + "loss": 0.5024, + "step": 1618 + }, + { + "epoch": 0.14, + "learning_rate": 1.942270785752162e-05, + "loss": 0.5122, + "step": 1619 + }, + { + "epoch": 0.14, + "learning_rate": 1.942180009488971e-05, + "loss": 0.4883, + "step": 1620 + }, + { + "epoch": 0.14, + "learning_rate": 1.9420891640359986e-05, + "loss": 0.5229, + "step": 1621 + }, + { + "epoch": 0.14, + "learning_rate": 1.9419982493999164e-05, + "loss": 0.5099, + "step": 1622 + }, + { + "epoch": 0.14, + "learning_rate": 1.941907265587401e-05, + "loss": 0.506, + "step": 1623 + }, + { + "epoch": 0.14, + "learning_rate": 1.941816212605134e-05, + "loss": 0.5054, + "step": 1624 + }, + { + "epoch": 0.14, + "learning_rate": 1.9417250904598012e-05, + "loss": 0.5049, + "step": 1625 + }, + { + "epoch": 0.14, + "learning_rate": 1.941633899158095e-05, + "loss": 0.4866, + "step": 1626 + }, + { + "epoch": 0.14, + "learning_rate": 1.9415426387067113e-05, + "loss": 0.5025, + "step": 1627 + }, + { + "epoch": 0.14, + "learning_rate": 1.9414513091123527e-05, + "loss": 0.4994, + "step": 1628 + }, + { + "epoch": 0.14, + "learning_rate": 1.941359910381726e-05, + "loss": 0.4944, + "step": 1629 + }, + { + "epoch": 0.14, + "learning_rate": 1.9412684425215426e-05, + "loss": 0.4999, + "step": 1630 + }, + { + "epoch": 0.14, + "learning_rate": 1.94117690553852e-05, + "loss": 0.5114, + "step": 1631 + }, + { + "epoch": 0.14, + "learning_rate": 1.94108529943938e-05, + "loss": 0.5099, + "step": 1632 + }, + { + "epoch": 0.14, + "learning_rate": 1.9409936242308496e-05, + "loss": 0.4935, + "step": 1633 + }, + { + "epoch": 0.14, + "learning_rate": 1.9409018799196615e-05, + "loss": 0.5183, + "step": 1634 + }, + { + "epoch": 0.14, + "learning_rate": 1.940810066512553e-05, + "loss": 0.5118, + "step": 1635 + }, + { + "epoch": 0.14, + "learning_rate": 1.9407181840162664e-05, + "loss": 0.4947, + "step": 1636 + }, + { + "epoch": 0.14, + "learning_rate": 1.940626232437549e-05, + "loss": 0.4854, + "step": 1637 + }, + { + "epoch": 0.14, + "learning_rate": 1.9405342117831533e-05, + "loss": 0.5058, + "step": 1638 + }, + { + "epoch": 0.14, + "learning_rate": 1.940442122059837e-05, + "loss": 0.5044, + "step": 1639 + }, + { + "epoch": 0.14, + "learning_rate": 1.940349963274363e-05, + "loss": 0.5109, + "step": 1640 + }, + { + "epoch": 0.14, + "learning_rate": 1.940257735433499e-05, + "loss": 0.5157, + "step": 1641 + }, + { + "epoch": 0.14, + "learning_rate": 1.9401654385440176e-05, + "loss": 0.5039, + "step": 1642 + }, + { + "epoch": 0.14, + "learning_rate": 1.9400730726126967e-05, + "loss": 0.5233, + "step": 1643 + }, + { + "epoch": 0.14, + "learning_rate": 1.9399806376463197e-05, + "loss": 0.5069, + "step": 1644 + }, + { + "epoch": 0.14, + "learning_rate": 1.9398881336516743e-05, + "loss": 0.4975, + "step": 1645 + }, + { + "epoch": 0.14, + "learning_rate": 1.9397955606355535e-05, + "loss": 0.4895, + "step": 1646 + }, + { + "epoch": 0.14, + "learning_rate": 1.939702918604756e-05, + "loss": 0.5138, + "step": 1647 + }, + { + "epoch": 0.14, + "learning_rate": 1.939610207566084e-05, + "loss": 0.5043, + "step": 1648 + }, + { + "epoch": 0.14, + "learning_rate": 1.9395174275263474e-05, + "loss": 0.5129, + "step": 1649 + }, + { + "epoch": 0.14, + "learning_rate": 1.939424578492358e-05, + "loss": 0.5204, + "step": 1650 + }, + { + "epoch": 0.14, + "learning_rate": 1.939331660470935e-05, + "loss": 0.5179, + "step": 1651 + }, + { + "epoch": 0.14, + "learning_rate": 1.939238673468902e-05, + "loss": 0.4908, + "step": 1652 + }, + { + "epoch": 0.14, + "learning_rate": 1.9391456174930872e-05, + "loss": 0.5208, + "step": 1653 + }, + { + "epoch": 0.14, + "learning_rate": 1.9390524925503244e-05, + "loss": 0.5036, + "step": 1654 + }, + { + "epoch": 0.14, + "learning_rate": 1.938959298647453e-05, + "loss": 0.5021, + "step": 1655 + }, + { + "epoch": 0.14, + "learning_rate": 1.9388660357913155e-05, + "loss": 0.4836, + "step": 1656 + }, + { + "epoch": 0.14, + "learning_rate": 1.9387727039887613e-05, + "loss": 0.5131, + "step": 1657 + }, + { + "epoch": 0.14, + "learning_rate": 1.9386793032466447e-05, + "loss": 0.4923, + "step": 1658 + }, + { + "epoch": 0.14, + "learning_rate": 1.938585833571824e-05, + "loss": 0.4989, + "step": 1659 + }, + { + "epoch": 0.14, + "learning_rate": 1.938492294971164e-05, + "loss": 0.4997, + "step": 1660 + }, + { + "epoch": 0.14, + "learning_rate": 1.938398687451533e-05, + "loss": 0.5122, + "step": 1661 + }, + { + "epoch": 0.14, + "learning_rate": 1.938305011019806e-05, + "loss": 0.5224, + "step": 1662 + }, + { + "epoch": 0.14, + "learning_rate": 1.938211265682861e-05, + "loss": 0.5035, + "step": 1663 + }, + { + "epoch": 0.14, + "learning_rate": 1.938117451447583e-05, + "loss": 0.4923, + "step": 1664 + }, + { + "epoch": 0.14, + "learning_rate": 1.938023568320862e-05, + "loss": 0.4831, + "step": 1665 + }, + { + "epoch": 0.14, + "learning_rate": 1.937929616309591e-05, + "loss": 0.5233, + "step": 1666 + }, + { + "epoch": 0.14, + "learning_rate": 1.9378355954206706e-05, + "loss": 0.4931, + "step": 1667 + }, + { + "epoch": 0.14, + "learning_rate": 1.9377415056610044e-05, + "loss": 0.5169, + "step": 1668 + }, + { + "epoch": 0.14, + "learning_rate": 1.9376473470375027e-05, + "loss": 0.5293, + "step": 1669 + }, + { + "epoch": 0.14, + "learning_rate": 1.9375531195570793e-05, + "loss": 0.4901, + "step": 1670 + }, + { + "epoch": 0.14, + "learning_rate": 1.937458823226655e-05, + "loss": 0.494, + "step": 1671 + }, + { + "epoch": 0.14, + "learning_rate": 1.9373644580531538e-05, + "loss": 0.4901, + "step": 1672 + }, + { + "epoch": 0.14, + "learning_rate": 1.9372700240435054e-05, + "loss": 0.4935, + "step": 1673 + }, + { + "epoch": 0.14, + "learning_rate": 1.9371755212046448e-05, + "loss": 0.5092, + "step": 1674 + }, + { + "epoch": 0.14, + "learning_rate": 1.937080949543512e-05, + "loss": 0.5221, + "step": 1675 + }, + { + "epoch": 0.14, + "learning_rate": 1.9369863090670518e-05, + "loss": 0.5167, + "step": 1676 + }, + { + "epoch": 0.14, + "learning_rate": 1.9368915997822143e-05, + "loss": 0.4965, + "step": 1677 + }, + { + "epoch": 0.14, + "learning_rate": 1.936796821695955e-05, + "loss": 0.5117, + "step": 1678 + }, + { + "epoch": 0.14, + "learning_rate": 1.9367019748152328e-05, + "loss": 0.4949, + "step": 1679 + }, + { + "epoch": 0.14, + "learning_rate": 1.936607059147014e-05, + "loss": 0.4979, + "step": 1680 + }, + { + "epoch": 0.14, + "learning_rate": 1.9365120746982683e-05, + "loss": 0.5053, + "step": 1681 + }, + { + "epoch": 0.14, + "learning_rate": 1.936417021475971e-05, + "loss": 0.5028, + "step": 1682 + }, + { + "epoch": 0.14, + "learning_rate": 1.9363218994871026e-05, + "loss": 0.4857, + "step": 1683 + }, + { + "epoch": 0.14, + "learning_rate": 1.9362267087386487e-05, + "loss": 0.5216, + "step": 1684 + }, + { + "epoch": 0.14, + "learning_rate": 1.936131449237599e-05, + "loss": 0.5015, + "step": 1685 + }, + { + "epoch": 0.14, + "learning_rate": 1.9360361209909494e-05, + "loss": 0.513, + "step": 1686 + }, + { + "epoch": 0.14, + "learning_rate": 1.9359407240057003e-05, + "loss": 0.4847, + "step": 1687 + }, + { + "epoch": 0.14, + "learning_rate": 1.9358452582888575e-05, + "loss": 0.5185, + "step": 1688 + }, + { + "epoch": 0.14, + "learning_rate": 1.935749723847431e-05, + "loss": 0.4861, + "step": 1689 + }, + { + "epoch": 0.14, + "learning_rate": 1.935654120688437e-05, + "loss": 0.5161, + "step": 1690 + }, + { + "epoch": 0.14, + "learning_rate": 1.9355584488188965e-05, + "loss": 0.4871, + "step": 1691 + }, + { + "epoch": 0.14, + "learning_rate": 1.9354627082458342e-05, + "loss": 0.525, + "step": 1692 + }, + { + "epoch": 0.14, + "learning_rate": 1.9353668989762817e-05, + "loss": 0.504, + "step": 1693 + }, + { + "epoch": 0.14, + "learning_rate": 1.935271021017275e-05, + "loss": 0.4978, + "step": 1694 + }, + { + "epoch": 0.14, + "learning_rate": 1.9351750743758543e-05, + "loss": 0.5007, + "step": 1695 + }, + { + "epoch": 0.14, + "learning_rate": 1.9350790590590657e-05, + "loss": 0.5096, + "step": 1696 + }, + { + "epoch": 0.14, + "learning_rate": 1.93498297507396e-05, + "loss": 0.5025, + "step": 1697 + }, + { + "epoch": 0.14, + "learning_rate": 1.9348868224275943e-05, + "loss": 0.5048, + "step": 1698 + }, + { + "epoch": 0.14, + "learning_rate": 1.9347906011270283e-05, + "loss": 0.5047, + "step": 1699 + }, + { + "epoch": 0.14, + "learning_rate": 1.9346943111793286e-05, + "loss": 0.512, + "step": 1700 + }, + { + "epoch": 0.14, + "learning_rate": 1.934597952591567e-05, + "loss": 0.5133, + "step": 1701 + }, + { + "epoch": 0.14, + "learning_rate": 1.934501525370818e-05, + "loss": 0.4905, + "step": 1702 + }, + { + "epoch": 0.14, + "learning_rate": 1.9344050295241648e-05, + "loss": 0.4937, + "step": 1703 + }, + { + "epoch": 0.14, + "learning_rate": 1.9343084650586922e-05, + "loss": 0.5147, + "step": 1704 + }, + { + "epoch": 0.14, + "learning_rate": 1.9342118319814923e-05, + "loss": 0.4967, + "step": 1705 + }, + { + "epoch": 0.14, + "learning_rate": 1.934115130299661e-05, + "loss": 0.5341, + "step": 1706 + }, + { + "epoch": 0.14, + "learning_rate": 1.9340183600202998e-05, + "loss": 0.4955, + "step": 1707 + }, + { + "epoch": 0.14, + "learning_rate": 1.933921521150515e-05, + "loss": 0.4864, + "step": 1708 + }, + { + "epoch": 0.14, + "learning_rate": 1.9338246136974182e-05, + "loss": 0.5248, + "step": 1709 + }, + { + "epoch": 0.14, + "learning_rate": 1.9337276376681264e-05, + "loss": 0.5103, + "step": 1710 + }, + { + "epoch": 0.14, + "learning_rate": 1.93363059306976e-05, + "loss": 0.5182, + "step": 1711 + }, + { + "epoch": 0.14, + "learning_rate": 1.933533479909446e-05, + "loss": 0.5186, + "step": 1712 + }, + { + "epoch": 0.14, + "learning_rate": 1.9334362981943163e-05, + "loss": 0.5112, + "step": 1713 + }, + { + "epoch": 0.14, + "learning_rate": 1.9333390479315074e-05, + "loss": 0.4874, + "step": 1714 + }, + { + "epoch": 0.14, + "learning_rate": 1.9332417291281608e-05, + "loss": 0.4948, + "step": 1715 + }, + { + "epoch": 0.14, + "learning_rate": 1.9331443417914232e-05, + "loss": 0.5153, + "step": 1716 + }, + { + "epoch": 0.14, + "learning_rate": 1.9330468859284462e-05, + "loss": 0.5004, + "step": 1717 + }, + { + "epoch": 0.14, + "learning_rate": 1.932949361546387e-05, + "loss": 0.4919, + "step": 1718 + }, + { + "epoch": 0.14, + "learning_rate": 1.9328517686524073e-05, + "loss": 0.5057, + "step": 1719 + }, + { + "epoch": 0.14, + "learning_rate": 1.9327541072536733e-05, + "loss": 0.5056, + "step": 1720 + }, + { + "epoch": 0.14, + "learning_rate": 1.9326563773573576e-05, + "loss": 0.4943, + "step": 1721 + }, + { + "epoch": 0.14, + "learning_rate": 1.9325585789706366e-05, + "loss": 0.5114, + "step": 1722 + }, + { + "epoch": 0.14, + "learning_rate": 1.932460712100692e-05, + "loss": 0.4955, + "step": 1723 + }, + { + "epoch": 0.14, + "learning_rate": 1.9323627767547118e-05, + "loss": 0.4962, + "step": 1724 + }, + { + "epoch": 0.14, + "learning_rate": 1.932264772939887e-05, + "loss": 0.5037, + "step": 1725 + }, + { + "epoch": 0.14, + "learning_rate": 1.9321667006634146e-05, + "loss": 0.5101, + "step": 1726 + }, + { + "epoch": 0.14, + "learning_rate": 1.932068559932497e-05, + "loss": 0.5041, + "step": 1727 + }, + { + "epoch": 0.14, + "learning_rate": 1.9319703507543415e-05, + "loss": 0.4974, + "step": 1728 + }, + { + "epoch": 0.14, + "learning_rate": 1.9318720731361593e-05, + "loss": 0.5173, + "step": 1729 + }, + { + "epoch": 0.14, + "learning_rate": 1.931773727085168e-05, + "loss": 0.5043, + "step": 1730 + }, + { + "epoch": 0.14, + "learning_rate": 1.9316753126085902e-05, + "loss": 0.5068, + "step": 1731 + }, + { + "epoch": 0.14, + "learning_rate": 1.9315768297136523e-05, + "loss": 0.5033, + "step": 1732 + }, + { + "epoch": 0.14, + "learning_rate": 1.9314782784075866e-05, + "loss": 0.5153, + "step": 1733 + }, + { + "epoch": 0.15, + "learning_rate": 1.9313796586976306e-05, + "loss": 0.5235, + "step": 1734 + }, + { + "epoch": 0.15, + "learning_rate": 1.9312809705910266e-05, + "loss": 0.4886, + "step": 1735 + }, + { + "epoch": 0.15, + "learning_rate": 1.9311822140950213e-05, + "loss": 0.493, + "step": 1736 + }, + { + "epoch": 0.15, + "learning_rate": 1.931083389216867e-05, + "loss": 0.5066, + "step": 1737 + }, + { + "epoch": 0.15, + "learning_rate": 1.930984495963822e-05, + "loss": 0.4965, + "step": 1738 + }, + { + "epoch": 0.15, + "learning_rate": 1.930885534343147e-05, + "loss": 0.497, + "step": 1739 + }, + { + "epoch": 0.15, + "learning_rate": 1.930786504362111e-05, + "loss": 0.4967, + "step": 1740 + }, + { + "epoch": 0.15, + "learning_rate": 1.930687406027985e-05, + "loss": 0.4892, + "step": 1741 + }, + { + "epoch": 0.15, + "learning_rate": 1.930588239348047e-05, + "loss": 0.5099, + "step": 1742 + }, + { + "epoch": 0.15, + "learning_rate": 1.9304890043295796e-05, + "loss": 0.5118, + "step": 1743 + }, + { + "epoch": 0.15, + "learning_rate": 1.93038970097987e-05, + "loss": 0.504, + "step": 1744 + }, + { + "epoch": 0.15, + "learning_rate": 1.93029032930621e-05, + "loss": 0.5056, + "step": 1745 + }, + { + "epoch": 0.15, + "learning_rate": 1.930190889315898e-05, + "loss": 0.499, + "step": 1746 + }, + { + "epoch": 0.15, + "learning_rate": 1.930091381016236e-05, + "loss": 0.5259, + "step": 1747 + }, + { + "epoch": 0.15, + "learning_rate": 1.9299918044145315e-05, + "loss": 0.5033, + "step": 1748 + }, + { + "epoch": 0.15, + "learning_rate": 1.9298921595180968e-05, + "loss": 0.5005, + "step": 1749 + }, + { + "epoch": 0.15, + "learning_rate": 1.9297924463342495e-05, + "loss": 0.518, + "step": 1750 + }, + { + "epoch": 0.15, + "learning_rate": 1.929692664870313e-05, + "loss": 0.5143, + "step": 1751 + }, + { + "epoch": 0.15, + "learning_rate": 1.9295928151336134e-05, + "loss": 0.5061, + "step": 1752 + }, + { + "epoch": 0.15, + "learning_rate": 1.9294928971314843e-05, + "loss": 0.5013, + "step": 1753 + }, + { + "epoch": 0.15, + "learning_rate": 1.9293929108712624e-05, + "loss": 0.5112, + "step": 1754 + }, + { + "epoch": 0.15, + "learning_rate": 1.9292928563602912e-05, + "loss": 0.4963, + "step": 1755 + }, + { + "epoch": 0.15, + "learning_rate": 1.9291927336059175e-05, + "loss": 0.5058, + "step": 1756 + }, + { + "epoch": 0.15, + "learning_rate": 1.9290925426154948e-05, + "loss": 0.4977, + "step": 1757 + }, + { + "epoch": 0.15, + "learning_rate": 1.9289922833963798e-05, + "loss": 0.5122, + "step": 1758 + }, + { + "epoch": 0.15, + "learning_rate": 1.9288919559559353e-05, + "loss": 0.5096, + "step": 1759 + }, + { + "epoch": 0.15, + "learning_rate": 1.928791560301529e-05, + "loss": 0.5032, + "step": 1760 + }, + { + "epoch": 0.15, + "learning_rate": 1.9286910964405345e-05, + "loss": 0.4987, + "step": 1761 + }, + { + "epoch": 0.15, + "learning_rate": 1.9285905643803277e-05, + "loss": 0.5022, + "step": 1762 + }, + { + "epoch": 0.15, + "learning_rate": 1.9284899641282925e-05, + "loss": 0.4889, + "step": 1763 + }, + { + "epoch": 0.15, + "learning_rate": 1.928389295691816e-05, + "loss": 0.5117, + "step": 1764 + }, + { + "epoch": 0.15, + "learning_rate": 1.9282885590782916e-05, + "loss": 0.5068, + "step": 1765 + }, + { + "epoch": 0.15, + "learning_rate": 1.928187754295116e-05, + "loss": 0.5271, + "step": 1766 + }, + { + "epoch": 0.15, + "learning_rate": 1.9280868813496927e-05, + "loss": 0.497, + "step": 1767 + }, + { + "epoch": 0.15, + "learning_rate": 1.9279859402494288e-05, + "loss": 0.5223, + "step": 1768 + }, + { + "epoch": 0.15, + "learning_rate": 1.9278849310017372e-05, + "loss": 0.5151, + "step": 1769 + }, + { + "epoch": 0.15, + "learning_rate": 1.9277838536140357e-05, + "loss": 0.5233, + "step": 1770 + }, + { + "epoch": 0.15, + "learning_rate": 1.927682708093747e-05, + "loss": 0.4949, + "step": 1771 + }, + { + "epoch": 0.15, + "learning_rate": 1.9275814944482988e-05, + "loss": 0.5211, + "step": 1772 + }, + { + "epoch": 0.15, + "learning_rate": 1.9274802126851237e-05, + "loss": 0.4977, + "step": 1773 + }, + { + "epoch": 0.15, + "learning_rate": 1.9273788628116593e-05, + "loss": 0.5169, + "step": 1774 + }, + { + "epoch": 0.15, + "learning_rate": 1.9272774448353484e-05, + "loss": 0.5062, + "step": 1775 + }, + { + "epoch": 0.15, + "learning_rate": 1.927175958763639e-05, + "loss": 0.4999, + "step": 1776 + }, + { + "epoch": 0.15, + "learning_rate": 1.9270744046039834e-05, + "loss": 0.5578, + "step": 1777 + }, + { + "epoch": 0.15, + "learning_rate": 1.92697278236384e-05, + "loss": 0.5188, + "step": 1778 + }, + { + "epoch": 0.15, + "learning_rate": 1.9268710920506707e-05, + "loss": 0.5076, + "step": 1779 + }, + { + "epoch": 0.15, + "learning_rate": 1.926769333671943e-05, + "loss": 0.4947, + "step": 1780 + }, + { + "epoch": 0.15, + "learning_rate": 1.926667507235131e-05, + "loss": 0.5049, + "step": 1781 + }, + { + "epoch": 0.15, + "learning_rate": 1.9265656127477114e-05, + "loss": 0.5118, + "step": 1782 + }, + { + "epoch": 0.15, + "learning_rate": 1.926463650217167e-05, + "loss": 0.489, + "step": 1783 + }, + { + "epoch": 0.15, + "learning_rate": 1.9263616196509855e-05, + "loss": 0.5062, + "step": 1784 + }, + { + "epoch": 0.15, + "learning_rate": 1.9262595210566598e-05, + "loss": 0.5238, + "step": 1785 + }, + { + "epoch": 0.15, + "learning_rate": 1.9261573544416872e-05, + "loss": 0.4939, + "step": 1786 + }, + { + "epoch": 0.15, + "learning_rate": 1.926055119813571e-05, + "loss": 0.491, + "step": 1787 + }, + { + "epoch": 0.15, + "learning_rate": 1.9259528171798184e-05, + "loss": 0.4932, + "step": 1788 + }, + { + "epoch": 0.15, + "learning_rate": 1.925850446547942e-05, + "loss": 0.5256, + "step": 1789 + }, + { + "epoch": 0.15, + "learning_rate": 1.92574800792546e-05, + "loss": 0.5049, + "step": 1790 + }, + { + "epoch": 0.15, + "learning_rate": 1.925645501319895e-05, + "loss": 0.4982, + "step": 1791 + }, + { + "epoch": 0.15, + "learning_rate": 1.925542926738774e-05, + "loss": 0.5154, + "step": 1792 + }, + { + "epoch": 0.15, + "learning_rate": 1.92544028418963e-05, + "loss": 0.5136, + "step": 1793 + }, + { + "epoch": 0.15, + "learning_rate": 1.9253375736800014e-05, + "loss": 0.4918, + "step": 1794 + }, + { + "epoch": 0.15, + "learning_rate": 1.9252347952174294e-05, + "loss": 0.5009, + "step": 1795 + }, + { + "epoch": 0.15, + "learning_rate": 1.925131948809463e-05, + "loss": 0.5235, + "step": 1796 + }, + { + "epoch": 0.15, + "learning_rate": 1.9250290344636537e-05, + "loss": 0.5012, + "step": 1797 + }, + { + "epoch": 0.15, + "learning_rate": 1.92492605218756e-05, + "loss": 0.4942, + "step": 1798 + }, + { + "epoch": 0.15, + "learning_rate": 1.9248230019887438e-05, + "loss": 0.5102, + "step": 1799 + }, + { + "epoch": 0.15, + "learning_rate": 1.924719883874773e-05, + "loss": 0.4946, + "step": 1800 + }, + { + "epoch": 0.15, + "learning_rate": 1.9246166978532203e-05, + "loss": 0.5077, + "step": 1801 + }, + { + "epoch": 0.15, + "learning_rate": 1.924513443931663e-05, + "loss": 0.5084, + "step": 1802 + }, + { + "epoch": 0.15, + "learning_rate": 1.9244101221176834e-05, + "loss": 0.4944, + "step": 1803 + }, + { + "epoch": 0.15, + "learning_rate": 1.9243067324188696e-05, + "loss": 0.5069, + "step": 1804 + }, + { + "epoch": 0.15, + "learning_rate": 1.9242032748428138e-05, + "loss": 0.4945, + "step": 1805 + }, + { + "epoch": 0.15, + "learning_rate": 1.924099749397114e-05, + "loss": 0.507, + "step": 1806 + }, + { + "epoch": 0.15, + "learning_rate": 1.9239961560893717e-05, + "loss": 0.5152, + "step": 1807 + }, + { + "epoch": 0.15, + "learning_rate": 1.923892494927195e-05, + "loss": 0.4897, + "step": 1808 + }, + { + "epoch": 0.15, + "learning_rate": 1.9237887659181963e-05, + "loss": 0.4968, + "step": 1809 + }, + { + "epoch": 0.15, + "learning_rate": 1.9236849690699924e-05, + "loss": 0.5118, + "step": 1810 + }, + { + "epoch": 0.15, + "learning_rate": 1.923581104390207e-05, + "loss": 0.5128, + "step": 1811 + }, + { + "epoch": 0.15, + "learning_rate": 1.9234771718864667e-05, + "loss": 0.4928, + "step": 1812 + }, + { + "epoch": 0.15, + "learning_rate": 1.9233731715664036e-05, + "loss": 0.5075, + "step": 1813 + }, + { + "epoch": 0.15, + "learning_rate": 1.9232691034376556e-05, + "loss": 0.5109, + "step": 1814 + }, + { + "epoch": 0.15, + "learning_rate": 1.9231649675078647e-05, + "loss": 0.4918, + "step": 1815 + }, + { + "epoch": 0.15, + "learning_rate": 1.9230607637846785e-05, + "loss": 0.5056, + "step": 1816 + }, + { + "epoch": 0.15, + "learning_rate": 1.9229564922757487e-05, + "loss": 0.4999, + "step": 1817 + }, + { + "epoch": 0.15, + "learning_rate": 1.9228521529887333e-05, + "loss": 0.5066, + "step": 1818 + }, + { + "epoch": 0.15, + "learning_rate": 1.9227477459312942e-05, + "loss": 0.4944, + "step": 1819 + }, + { + "epoch": 0.15, + "learning_rate": 1.9226432711110983e-05, + "loss": 0.5145, + "step": 1820 + }, + { + "epoch": 0.15, + "learning_rate": 1.922538728535819e-05, + "loss": 0.5033, + "step": 1821 + }, + { + "epoch": 0.15, + "learning_rate": 1.922434118213132e-05, + "loss": 0.5292, + "step": 1822 + }, + { + "epoch": 0.15, + "learning_rate": 1.9223294401507196e-05, + "loss": 0.5067, + "step": 1823 + }, + { + "epoch": 0.15, + "learning_rate": 1.9222246943562702e-05, + "loss": 0.5016, + "step": 1824 + }, + { + "epoch": 0.15, + "learning_rate": 1.9221198808374746e-05, + "loss": 0.4928, + "step": 1825 + }, + { + "epoch": 0.15, + "learning_rate": 1.9220149996020306e-05, + "loss": 0.5077, + "step": 1826 + }, + { + "epoch": 0.15, + "learning_rate": 1.9219100506576396e-05, + "loss": 0.4962, + "step": 1827 + }, + { + "epoch": 0.15, + "learning_rate": 1.9218050340120095e-05, + "loss": 0.5081, + "step": 1828 + }, + { + "epoch": 0.15, + "learning_rate": 1.9216999496728513e-05, + "loss": 0.5203, + "step": 1829 + }, + { + "epoch": 0.15, + "learning_rate": 1.9215947976478825e-05, + "loss": 0.511, + "step": 1830 + }, + { + "epoch": 0.15, + "learning_rate": 1.9214895779448254e-05, + "loss": 0.5018, + "step": 1831 + }, + { + "epoch": 0.15, + "learning_rate": 1.921384290571406e-05, + "loss": 0.4929, + "step": 1832 + }, + { + "epoch": 0.15, + "learning_rate": 1.9212789355353567e-05, + "loss": 0.4992, + "step": 1833 + }, + { + "epoch": 0.15, + "learning_rate": 1.921173512844414e-05, + "loss": 0.5106, + "step": 1834 + }, + { + "epoch": 0.15, + "learning_rate": 1.9210680225063204e-05, + "loss": 0.4934, + "step": 1835 + }, + { + "epoch": 0.15, + "learning_rate": 1.9209624645288224e-05, + "loss": 0.5013, + "step": 1836 + }, + { + "epoch": 0.15, + "learning_rate": 1.9208568389196715e-05, + "loss": 0.4948, + "step": 1837 + }, + { + "epoch": 0.15, + "learning_rate": 1.920751145686624e-05, + "loss": 0.4963, + "step": 1838 + }, + { + "epoch": 0.15, + "learning_rate": 1.9206453848374425e-05, + "loss": 0.499, + "step": 1839 + }, + { + "epoch": 0.15, + "learning_rate": 1.920539556379893e-05, + "loss": 0.4947, + "step": 1840 + }, + { + "epoch": 0.15, + "learning_rate": 1.920433660321747e-05, + "loss": 0.5145, + "step": 1841 + }, + { + "epoch": 0.15, + "learning_rate": 1.920327696670782e-05, + "loss": 0.4967, + "step": 1842 + }, + { + "epoch": 0.15, + "learning_rate": 1.9202216654347786e-05, + "loss": 0.52, + "step": 1843 + }, + { + "epoch": 0.15, + "learning_rate": 1.9201155666215237e-05, + "loss": 0.5103, + "step": 1844 + }, + { + "epoch": 0.15, + "learning_rate": 1.9200094002388084e-05, + "loss": 0.5124, + "step": 1845 + }, + { + "epoch": 0.15, + "learning_rate": 1.9199031662944294e-05, + "loss": 0.5054, + "step": 1846 + }, + { + "epoch": 0.15, + "learning_rate": 1.919796864796188e-05, + "loss": 0.4923, + "step": 1847 + }, + { + "epoch": 0.15, + "learning_rate": 1.919690495751891e-05, + "loss": 0.5264, + "step": 1848 + }, + { + "epoch": 0.15, + "learning_rate": 1.9195840591693486e-05, + "loss": 0.4979, + "step": 1849 + }, + { + "epoch": 0.15, + "learning_rate": 1.919477555056378e-05, + "loss": 0.5072, + "step": 1850 + }, + { + "epoch": 0.15, + "learning_rate": 1.9193709834208005e-05, + "loss": 0.5136, + "step": 1851 + }, + { + "epoch": 0.15, + "learning_rate": 1.9192643442704413e-05, + "loss": 0.5028, + "step": 1852 + }, + { + "epoch": 0.16, + "learning_rate": 1.9191576376131328e-05, + "loss": 0.52, + "step": 1853 + }, + { + "epoch": 0.16, + "learning_rate": 1.91905086345671e-05, + "loss": 0.5033, + "step": 1854 + }, + { + "epoch": 0.16, + "learning_rate": 1.9189440218090146e-05, + "loss": 0.5088, + "step": 1855 + }, + { + "epoch": 0.16, + "learning_rate": 1.9188371126778923e-05, + "loss": 0.5009, + "step": 1856 + }, + { + "epoch": 0.16, + "learning_rate": 1.9187301360711943e-05, + "loss": 0.5068, + "step": 1857 + }, + { + "epoch": 0.16, + "learning_rate": 1.9186230919967764e-05, + "loss": 0.4997, + "step": 1858 + }, + { + "epoch": 0.16, + "learning_rate": 1.9185159804624994e-05, + "loss": 0.5098, + "step": 1859 + }, + { + "epoch": 0.16, + "learning_rate": 1.9184088014762292e-05, + "loss": 0.4964, + "step": 1860 + }, + { + "epoch": 0.16, + "learning_rate": 1.9183015550458367e-05, + "loss": 0.5084, + "step": 1861 + }, + { + "epoch": 0.16, + "learning_rate": 1.918194241179197e-05, + "loss": 0.5049, + "step": 1862 + }, + { + "epoch": 0.16, + "learning_rate": 1.9180868598841916e-05, + "loss": 0.4998, + "step": 1863 + }, + { + "epoch": 0.16, + "learning_rate": 1.9179794111687063e-05, + "loss": 0.5073, + "step": 1864 + }, + { + "epoch": 0.16, + "learning_rate": 1.9178718950406304e-05, + "loss": 0.5088, + "step": 1865 + }, + { + "epoch": 0.16, + "learning_rate": 1.917764311507861e-05, + "loss": 0.4973, + "step": 1866 + }, + { + "epoch": 0.16, + "learning_rate": 1.9176566605782974e-05, + "loss": 0.5177, + "step": 1867 + }, + { + "epoch": 0.16, + "learning_rate": 1.9175489422598455e-05, + "loss": 0.5072, + "step": 1868 + }, + { + "epoch": 0.16, + "learning_rate": 1.9174411565604157e-05, + "loss": 0.5095, + "step": 1869 + }, + { + "epoch": 0.16, + "learning_rate": 1.917333303487923e-05, + "loss": 0.4966, + "step": 1870 + }, + { + "epoch": 0.16, + "learning_rate": 1.9172253830502883e-05, + "loss": 0.5067, + "step": 1871 + }, + { + "epoch": 0.16, + "learning_rate": 1.9171173952554367e-05, + "loss": 0.5058, + "step": 1872 + }, + { + "epoch": 0.16, + "learning_rate": 1.917009340111298e-05, + "loss": 0.5126, + "step": 1873 + }, + { + "epoch": 0.16, + "learning_rate": 1.916901217625807e-05, + "loss": 0.5041, + "step": 1874 + }, + { + "epoch": 0.16, + "learning_rate": 1.916793027806905e-05, + "loss": 0.4989, + "step": 1875 + }, + { + "epoch": 0.16, + "learning_rate": 1.9166847706625357e-05, + "loss": 0.5211, + "step": 1876 + }, + { + "epoch": 0.16, + "learning_rate": 1.91657644620065e-05, + "loss": 0.499, + "step": 1877 + }, + { + "epoch": 0.16, + "learning_rate": 1.9164680544292023e-05, + "loss": 0.4914, + "step": 1878 + }, + { + "epoch": 0.16, + "learning_rate": 1.9163595953561523e-05, + "loss": 0.5074, + "step": 1879 + }, + { + "epoch": 0.16, + "learning_rate": 1.9162510689894653e-05, + "loss": 0.534, + "step": 1880 + }, + { + "epoch": 0.16, + "learning_rate": 1.916142475337111e-05, + "loss": 0.5084, + "step": 1881 + }, + { + "epoch": 0.16, + "learning_rate": 1.9160338144070635e-05, + "loss": 0.5069, + "step": 1882 + }, + { + "epoch": 0.16, + "learning_rate": 1.9159250862073028e-05, + "loss": 0.5611, + "step": 1883 + }, + { + "epoch": 0.16, + "learning_rate": 1.9158162907458135e-05, + "loss": 0.4864, + "step": 1884 + }, + { + "epoch": 0.16, + "learning_rate": 1.9157074280305847e-05, + "loss": 0.5034, + "step": 1885 + }, + { + "epoch": 0.16, + "learning_rate": 1.9155984980696112e-05, + "loss": 0.5303, + "step": 1886 + }, + { + "epoch": 0.16, + "learning_rate": 1.9154895008708923e-05, + "loss": 0.4934, + "step": 1887 + }, + { + "epoch": 0.16, + "learning_rate": 1.9153804364424325e-05, + "loss": 0.4889, + "step": 1888 + }, + { + "epoch": 0.16, + "learning_rate": 1.9152713047922406e-05, + "loss": 0.5199, + "step": 1889 + }, + { + "epoch": 0.16, + "learning_rate": 1.9151621059283306e-05, + "loss": 0.5035, + "step": 1890 + }, + { + "epoch": 0.16, + "learning_rate": 1.9150528398587226e-05, + "loss": 0.5213, + "step": 1891 + }, + { + "epoch": 0.16, + "learning_rate": 1.9149435065914395e-05, + "loss": 0.4933, + "step": 1892 + }, + { + "epoch": 0.16, + "learning_rate": 1.9148341061345114e-05, + "loss": 0.4935, + "step": 1893 + }, + { + "epoch": 0.16, + "learning_rate": 1.9147246384959715e-05, + "loss": 0.5199, + "step": 1894 + }, + { + "epoch": 0.16, + "learning_rate": 1.9146151036838583e-05, + "loss": 0.5242, + "step": 1895 + }, + { + "epoch": 0.16, + "learning_rate": 1.9145055017062165e-05, + "loss": 0.4793, + "step": 1896 + }, + { + "epoch": 0.16, + "learning_rate": 1.914395832571094e-05, + "loss": 0.5142, + "step": 1897 + }, + { + "epoch": 0.16, + "learning_rate": 1.914286096286545e-05, + "loss": 0.4923, + "step": 1898 + }, + { + "epoch": 0.16, + "learning_rate": 1.9141762928606282e-05, + "loss": 0.4866, + "step": 1899 + }, + { + "epoch": 0.16, + "learning_rate": 1.9140664223014064e-05, + "loss": 0.4988, + "step": 1900 + }, + { + "epoch": 0.16, + "learning_rate": 1.9139564846169486e-05, + "loss": 0.4838, + "step": 1901 + }, + { + "epoch": 0.16, + "learning_rate": 1.913846479815328e-05, + "loss": 0.5151, + "step": 1902 + }, + { + "epoch": 0.16, + "learning_rate": 1.913736407904623e-05, + "loss": 0.493, + "step": 1903 + }, + { + "epoch": 0.16, + "learning_rate": 1.9136262688929167e-05, + "loss": 0.4959, + "step": 1904 + }, + { + "epoch": 0.16, + "learning_rate": 1.913516062788297e-05, + "loss": 0.5162, + "step": 1905 + }, + { + "epoch": 0.16, + "learning_rate": 1.9134057895988574e-05, + "loss": 0.4908, + "step": 1906 + }, + { + "epoch": 0.16, + "learning_rate": 1.913295449332696e-05, + "loss": 0.5083, + "step": 1907 + }, + { + "epoch": 0.16, + "learning_rate": 1.913185041997915e-05, + "loss": 0.5152, + "step": 1908 + }, + { + "epoch": 0.16, + "learning_rate": 1.913074567602623e-05, + "loss": 0.5059, + "step": 1909 + }, + { + "epoch": 0.16, + "learning_rate": 1.9129640261549324e-05, + "loss": 0.509, + "step": 1910 + }, + { + "epoch": 0.16, + "learning_rate": 1.9128534176629613e-05, + "loss": 0.5031, + "step": 1911 + }, + { + "epoch": 0.16, + "learning_rate": 1.9127427421348316e-05, + "loss": 0.5084, + "step": 1912 + }, + { + "epoch": 0.16, + "learning_rate": 1.9126319995786717e-05, + "loss": 0.5322, + "step": 1913 + }, + { + "epoch": 0.16, + "learning_rate": 1.912521190002614e-05, + "loss": 0.5027, + "step": 1914 + }, + { + "epoch": 0.16, + "learning_rate": 1.9124103134147945e-05, + "loss": 0.505, + "step": 1915 + }, + { + "epoch": 0.16, + "learning_rate": 1.9122993698233576e-05, + "loss": 0.5083, + "step": 1916 + }, + { + "epoch": 0.16, + "learning_rate": 1.9121883592364486e-05, + "loss": 0.5209, + "step": 1917 + }, + { + "epoch": 0.16, + "learning_rate": 1.9120772816622213e-05, + "loss": 0.509, + "step": 1918 + }, + { + "epoch": 0.16, + "learning_rate": 1.9119661371088318e-05, + "loss": 0.5019, + "step": 1919 + }, + { + "epoch": 0.16, + "learning_rate": 1.9118549255844425e-05, + "loss": 0.4998, + "step": 1920 + }, + { + "epoch": 0.16, + "learning_rate": 1.91174364709722e-05, + "loss": 0.4973, + "step": 1921 + }, + { + "epoch": 0.16, + "learning_rate": 1.9116323016553363e-05, + "loss": 0.5233, + "step": 1922 + }, + { + "epoch": 0.16, + "learning_rate": 1.911520889266968e-05, + "loss": 0.492, + "step": 1923 + }, + { + "epoch": 0.16, + "learning_rate": 1.911409409940297e-05, + "loss": 0.5242, + "step": 1924 + }, + { + "epoch": 0.16, + "learning_rate": 1.91129786368351e-05, + "loss": 0.5041, + "step": 1925 + }, + { + "epoch": 0.16, + "learning_rate": 1.911186250504798e-05, + "loss": 0.5142, + "step": 1926 + }, + { + "epoch": 0.16, + "learning_rate": 1.9110745704123577e-05, + "loss": 0.5063, + "step": 1927 + }, + { + "epoch": 0.16, + "learning_rate": 1.9109628234143905e-05, + "loss": 0.497, + "step": 1928 + }, + { + "epoch": 0.16, + "learning_rate": 1.9108510095191025e-05, + "loss": 0.4973, + "step": 1929 + }, + { + "epoch": 0.16, + "learning_rate": 1.910739128734705e-05, + "loss": 0.4926, + "step": 1930 + }, + { + "epoch": 0.16, + "learning_rate": 1.9106271810694137e-05, + "loss": 0.5205, + "step": 1931 + }, + { + "epoch": 0.16, + "learning_rate": 1.9105151665314497e-05, + "loss": 0.4997, + "step": 1932 + }, + { + "epoch": 0.16, + "learning_rate": 1.9104030851290393e-05, + "loss": 0.5069, + "step": 1933 + }, + { + "epoch": 0.16, + "learning_rate": 1.910290936870413e-05, + "loss": 0.5012, + "step": 1934 + }, + { + "epoch": 0.16, + "learning_rate": 1.910178721763806e-05, + "loss": 0.5198, + "step": 1935 + }, + { + "epoch": 0.16, + "learning_rate": 1.91006643981746e-05, + "loss": 0.5206, + "step": 1936 + }, + { + "epoch": 0.16, + "learning_rate": 1.9099540910396194e-05, + "loss": 0.4984, + "step": 1937 + }, + { + "epoch": 0.16, + "learning_rate": 1.9098416754385355e-05, + "loss": 0.5317, + "step": 1938 + }, + { + "epoch": 0.16, + "learning_rate": 1.909729193022463e-05, + "loss": 0.4949, + "step": 1939 + }, + { + "epoch": 0.16, + "learning_rate": 1.9096166437996626e-05, + "loss": 0.4801, + "step": 1940 + }, + { + "epoch": 0.16, + "learning_rate": 1.9095040277783993e-05, + "loss": 0.5191, + "step": 1941 + }, + { + "epoch": 0.16, + "learning_rate": 1.909391344966943e-05, + "loss": 0.5103, + "step": 1942 + }, + { + "epoch": 0.16, + "learning_rate": 1.909278595373569e-05, + "loss": 0.4988, + "step": 1943 + }, + { + "epoch": 0.16, + "learning_rate": 1.9091657790065565e-05, + "loss": 0.49, + "step": 1944 + }, + { + "epoch": 0.16, + "learning_rate": 1.909052895874191e-05, + "loss": 0.528, + "step": 1945 + }, + { + "epoch": 0.16, + "learning_rate": 1.9089399459847615e-05, + "loss": 0.4989, + "step": 1946 + }, + { + "epoch": 0.16, + "learning_rate": 1.9088269293465634e-05, + "loss": 0.4941, + "step": 1947 + }, + { + "epoch": 0.16, + "learning_rate": 1.9087138459678956e-05, + "loss": 0.5119, + "step": 1948 + }, + { + "epoch": 0.16, + "learning_rate": 1.908600695857062e-05, + "loss": 0.5093, + "step": 1949 + }, + { + "epoch": 0.16, + "learning_rate": 1.9084874790223735e-05, + "loss": 0.5122, + "step": 1950 + }, + { + "epoch": 0.16, + "learning_rate": 1.9083741954721423e-05, + "loss": 0.4985, + "step": 1951 + }, + { + "epoch": 0.16, + "learning_rate": 1.908260845214689e-05, + "loss": 0.5291, + "step": 1952 + }, + { + "epoch": 0.16, + "learning_rate": 1.9081474282583367e-05, + "loss": 0.5037, + "step": 1953 + }, + { + "epoch": 0.16, + "learning_rate": 1.9080339446114148e-05, + "loss": 0.4901, + "step": 1954 + }, + { + "epoch": 0.16, + "learning_rate": 1.907920394282256e-05, + "loss": 0.4888, + "step": 1955 + }, + { + "epoch": 0.16, + "learning_rate": 1.9078067772792006e-05, + "loss": 0.4985, + "step": 1956 + }, + { + "epoch": 0.16, + "learning_rate": 1.907693093610591e-05, + "loss": 0.5106, + "step": 1957 + }, + { + "epoch": 0.16, + "learning_rate": 1.9075793432847763e-05, + "loss": 0.5031, + "step": 1958 + }, + { + "epoch": 0.16, + "learning_rate": 1.907465526310109e-05, + "loss": 0.5117, + "step": 1959 + }, + { + "epoch": 0.16, + "learning_rate": 1.9073516426949485e-05, + "loss": 0.5219, + "step": 1960 + }, + { + "epoch": 0.16, + "learning_rate": 1.9072376924476568e-05, + "loss": 0.5064, + "step": 1961 + }, + { + "epoch": 0.16, + "learning_rate": 1.9071236755766028e-05, + "loss": 0.5332, + "step": 1962 + }, + { + "epoch": 0.16, + "learning_rate": 1.9070095920901588e-05, + "loss": 0.5191, + "step": 1963 + }, + { + "epoch": 0.16, + "learning_rate": 1.906895441996703e-05, + "loss": 0.5143, + "step": 1964 + }, + { + "epoch": 0.16, + "learning_rate": 1.906781225304618e-05, + "loss": 0.491, + "step": 1965 + }, + { + "epoch": 0.16, + "learning_rate": 1.9066669420222915e-05, + "loss": 0.5089, + "step": 1966 + }, + { + "epoch": 0.16, + "learning_rate": 1.9065525921581158e-05, + "loss": 0.5046, + "step": 1967 + }, + { + "epoch": 0.16, + "learning_rate": 1.9064381757204884e-05, + "loss": 0.501, + "step": 1968 + }, + { + "epoch": 0.16, + "learning_rate": 1.9063236927178116e-05, + "loss": 0.5061, + "step": 1969 + }, + { + "epoch": 0.16, + "learning_rate": 1.9062091431584924e-05, + "loss": 0.5049, + "step": 1970 + }, + { + "epoch": 0.16, + "learning_rate": 1.9060945270509427e-05, + "loss": 0.4905, + "step": 1971 + }, + { + "epoch": 0.16, + "learning_rate": 1.90597984440358e-05, + "loss": 0.4926, + "step": 1972 + }, + { + "epoch": 0.17, + "learning_rate": 1.9058650952248257e-05, + "loss": 0.4932, + "step": 1973 + }, + { + "epoch": 0.17, + "learning_rate": 1.9057502795231066e-05, + "loss": 0.5016, + "step": 1974 + }, + { + "epoch": 0.17, + "learning_rate": 1.9056353973068544e-05, + "loss": 0.4863, + "step": 1975 + }, + { + "epoch": 0.17, + "learning_rate": 1.905520448584505e-05, + "loss": 0.5144, + "step": 1976 + }, + { + "epoch": 0.17, + "learning_rate": 1.9054054333645006e-05, + "loss": 0.4898, + "step": 1977 + }, + { + "epoch": 0.17, + "learning_rate": 1.905290351655287e-05, + "loss": 0.4975, + "step": 1978 + }, + { + "epoch": 0.17, + "learning_rate": 1.9051752034653153e-05, + "loss": 0.526, + "step": 1979 + }, + { + "epoch": 0.17, + "learning_rate": 1.9050599888030413e-05, + "loss": 0.5172, + "step": 1980 + }, + { + "epoch": 0.17, + "learning_rate": 1.9049447076769265e-05, + "loss": 0.4884, + "step": 1981 + }, + { + "epoch": 0.17, + "learning_rate": 1.904829360095436e-05, + "loss": 0.5012, + "step": 1982 + }, + { + "epoch": 0.17, + "learning_rate": 1.904713946067041e-05, + "loss": 0.5017, + "step": 1983 + }, + { + "epoch": 0.17, + "learning_rate": 1.904598465600217e-05, + "loss": 0.5158, + "step": 1984 + }, + { + "epoch": 0.17, + "learning_rate": 1.904482918703444e-05, + "loss": 0.5017, + "step": 1985 + }, + { + "epoch": 0.17, + "learning_rate": 1.9043673053852073e-05, + "loss": 0.496, + "step": 1986 + }, + { + "epoch": 0.17, + "learning_rate": 1.9042516256539974e-05, + "loss": 0.5146, + "step": 1987 + }, + { + "epoch": 0.17, + "learning_rate": 1.904135879518309e-05, + "loss": 0.497, + "step": 1988 + }, + { + "epoch": 0.17, + "learning_rate": 1.9040200669866426e-05, + "loss": 0.5092, + "step": 1989 + }, + { + "epoch": 0.17, + "learning_rate": 1.903904188067502e-05, + "loss": 0.4902, + "step": 1990 + }, + { + "epoch": 0.17, + "learning_rate": 1.903788242769398e-05, + "loss": 0.5079, + "step": 1991 + }, + { + "epoch": 0.17, + "learning_rate": 1.9036722311008442e-05, + "loss": 0.5132, + "step": 1992 + }, + { + "epoch": 0.17, + "learning_rate": 1.9035561530703605e-05, + "loss": 0.5149, + "step": 1993 + }, + { + "epoch": 0.17, + "learning_rate": 1.903440008686471e-05, + "loss": 0.4911, + "step": 1994 + }, + { + "epoch": 0.17, + "learning_rate": 1.9033237979577053e-05, + "loss": 0.5114, + "step": 1995 + }, + { + "epoch": 0.17, + "learning_rate": 1.9032075208925967e-05, + "loss": 0.5084, + "step": 1996 + }, + { + "epoch": 0.17, + "learning_rate": 1.903091177499685e-05, + "loss": 0.4958, + "step": 1997 + }, + { + "epoch": 0.17, + "learning_rate": 1.9029747677875132e-05, + "loss": 0.5, + "step": 1998 + }, + { + "epoch": 0.17, + "learning_rate": 1.90285829176463e-05, + "loss": 0.5156, + "step": 1999 + }, + { + "epoch": 0.17, + "learning_rate": 1.9027417494395896e-05, + "loss": 0.501, + "step": 2000 + }, + { + "epoch": 0.17, + "learning_rate": 1.9026251408209494e-05, + "loss": 0.4945, + "step": 2001 + }, + { + "epoch": 0.17, + "learning_rate": 1.9025084659172733e-05, + "loss": 0.4951, + "step": 2002 + }, + { + "epoch": 0.17, + "learning_rate": 1.9023917247371292e-05, + "loss": 0.4994, + "step": 2003 + }, + { + "epoch": 0.17, + "learning_rate": 1.9022749172890904e-05, + "loss": 0.5328, + "step": 2004 + }, + { + "epoch": 0.17, + "learning_rate": 1.9021580435817343e-05, + "loss": 0.5034, + "step": 2005 + }, + { + "epoch": 0.17, + "learning_rate": 1.902041103623644e-05, + "loss": 0.5178, + "step": 2006 + }, + { + "epoch": 0.17, + "learning_rate": 1.901924097423407e-05, + "loss": 0.4987, + "step": 2007 + }, + { + "epoch": 0.17, + "learning_rate": 1.901807024989615e-05, + "loss": 0.4948, + "step": 2008 + }, + { + "epoch": 0.17, + "learning_rate": 1.9016898863308667e-05, + "loss": 0.4785, + "step": 2009 + }, + { + "epoch": 0.17, + "learning_rate": 1.9015726814557632e-05, + "loss": 0.496, + "step": 2010 + }, + { + "epoch": 0.17, + "learning_rate": 1.9014554103729125e-05, + "loss": 0.5314, + "step": 2011 + }, + { + "epoch": 0.17, + "learning_rate": 1.9013380730909255e-05, + "loss": 0.503, + "step": 2012 + }, + { + "epoch": 0.17, + "learning_rate": 1.901220669618419e-05, + "loss": 0.5094, + "step": 2013 + }, + { + "epoch": 0.17, + "learning_rate": 1.9011031999640152e-05, + "loss": 0.5112, + "step": 2014 + }, + { + "epoch": 0.17, + "learning_rate": 1.9009856641363406e-05, + "loss": 0.5092, + "step": 2015 + }, + { + "epoch": 0.17, + "learning_rate": 1.9008680621440262e-05, + "loss": 0.5008, + "step": 2016 + }, + { + "epoch": 0.17, + "learning_rate": 1.9007503939957085e-05, + "loss": 0.503, + "step": 2017 + }, + { + "epoch": 0.17, + "learning_rate": 1.900632659700028e-05, + "loss": 0.5023, + "step": 2018 + }, + { + "epoch": 0.17, + "learning_rate": 1.9005148592656312e-05, + "loss": 0.4859, + "step": 2019 + }, + { + "epoch": 0.17, + "learning_rate": 1.9003969927011683e-05, + "loss": 0.4745, + "step": 2020 + }, + { + "epoch": 0.17, + "learning_rate": 1.900279060015296e-05, + "loss": 0.5014, + "step": 2021 + }, + { + "epoch": 0.17, + "learning_rate": 1.9001610612166735e-05, + "loss": 0.4822, + "step": 2022 + }, + { + "epoch": 0.17, + "learning_rate": 1.9000429963139668e-05, + "loss": 0.4995, + "step": 2023 + }, + { + "epoch": 0.17, + "learning_rate": 1.8999248653158463e-05, + "loss": 0.5026, + "step": 2024 + }, + { + "epoch": 0.17, + "learning_rate": 1.8998066682309864e-05, + "loss": 0.5068, + "step": 2025 + }, + { + "epoch": 0.17, + "learning_rate": 1.8996884050680675e-05, + "loss": 0.5157, + "step": 2026 + }, + { + "epoch": 0.17, + "learning_rate": 1.8995700758357744e-05, + "loss": 0.4847, + "step": 2027 + }, + { + "epoch": 0.17, + "learning_rate": 1.899451680542796e-05, + "loss": 0.4887, + "step": 2028 + }, + { + "epoch": 0.17, + "learning_rate": 1.8993332191978277e-05, + "loss": 0.5107, + "step": 2029 + }, + { + "epoch": 0.17, + "learning_rate": 1.8992146918095684e-05, + "loss": 0.5014, + "step": 2030 + }, + { + "epoch": 0.17, + "learning_rate": 1.8990960983867222e-05, + "loss": 0.5074, + "step": 2031 + }, + { + "epoch": 0.17, + "learning_rate": 1.898977438937998e-05, + "loss": 0.5281, + "step": 2032 + }, + { + "epoch": 0.17, + "learning_rate": 1.8988587134721103e-05, + "loss": 0.4978, + "step": 2033 + }, + { + "epoch": 0.17, + "learning_rate": 1.8987399219977768e-05, + "loss": 0.5055, + "step": 2034 + }, + { + "epoch": 0.17, + "learning_rate": 1.8986210645237216e-05, + "loss": 0.5146, + "step": 2035 + }, + { + "epoch": 0.17, + "learning_rate": 1.8985021410586732e-05, + "loss": 0.5041, + "step": 2036 + }, + { + "epoch": 0.17, + "learning_rate": 1.8983831516113645e-05, + "loss": 0.5209, + "step": 2037 + }, + { + "epoch": 0.17, + "learning_rate": 1.898264096190534e-05, + "loss": 0.4876, + "step": 2038 + }, + { + "epoch": 0.17, + "learning_rate": 1.8981449748049248e-05, + "loss": 0.5127, + "step": 2039 + }, + { + "epoch": 0.17, + "learning_rate": 1.8980257874632836e-05, + "loss": 0.5006, + "step": 2040 + }, + { + "epoch": 0.17, + "learning_rate": 1.8979065341743642e-05, + "loss": 0.4796, + "step": 2041 + }, + { + "epoch": 0.17, + "learning_rate": 1.8977872149469236e-05, + "loss": 0.4946, + "step": 2042 + }, + { + "epoch": 0.17, + "learning_rate": 1.897667829789724e-05, + "loss": 0.5015, + "step": 2043 + }, + { + "epoch": 0.17, + "learning_rate": 1.8975483787115326e-05, + "loss": 0.4806, + "step": 2044 + }, + { + "epoch": 0.17, + "learning_rate": 1.8974288617211217e-05, + "loss": 0.5259, + "step": 2045 + }, + { + "epoch": 0.17, + "learning_rate": 1.8973092788272677e-05, + "loss": 0.5037, + "step": 2046 + }, + { + "epoch": 0.17, + "learning_rate": 1.8971896300387525e-05, + "loss": 0.506, + "step": 2047 + }, + { + "epoch": 0.17, + "learning_rate": 1.8970699153643623e-05, + "loss": 0.5138, + "step": 2048 + }, + { + "epoch": 0.17, + "learning_rate": 1.896950134812889e-05, + "loss": 0.5103, + "step": 2049 + }, + { + "epoch": 0.17, + "learning_rate": 1.8968302883931283e-05, + "loss": 0.4973, + "step": 2050 + }, + { + "epoch": 0.17, + "learning_rate": 1.8967103761138817e-05, + "loss": 0.524, + "step": 2051 + }, + { + "epoch": 0.17, + "learning_rate": 1.8965903979839547e-05, + "loss": 0.5037, + "step": 2052 + }, + { + "epoch": 0.17, + "learning_rate": 1.8964703540121577e-05, + "loss": 0.4964, + "step": 2053 + }, + { + "epoch": 0.17, + "learning_rate": 1.8963502442073073e-05, + "loss": 0.499, + "step": 2054 + }, + { + "epoch": 0.17, + "learning_rate": 1.8962300685782224e-05, + "loss": 0.507, + "step": 2055 + }, + { + "epoch": 0.17, + "learning_rate": 1.8961098271337296e-05, + "loss": 0.5196, + "step": 2056 + }, + { + "epoch": 0.17, + "learning_rate": 1.8959895198826582e-05, + "loss": 0.489, + "step": 2057 + }, + { + "epoch": 0.17, + "learning_rate": 1.895869146833843e-05, + "loss": 0.5034, + "step": 2058 + }, + { + "epoch": 0.17, + "learning_rate": 1.8957487079961235e-05, + "loss": 0.5135, + "step": 2059 + }, + { + "epoch": 0.17, + "learning_rate": 1.895628203378345e-05, + "loss": 0.4917, + "step": 2060 + }, + { + "epoch": 0.17, + "learning_rate": 1.8955076329893565e-05, + "loss": 0.503, + "step": 2061 + }, + { + "epoch": 0.17, + "learning_rate": 1.8953869968380117e-05, + "loss": 0.53, + "step": 2062 + }, + { + "epoch": 0.17, + "learning_rate": 1.8952662949331707e-05, + "loss": 0.4998, + "step": 2063 + }, + { + "epoch": 0.17, + "learning_rate": 1.8951455272836963e-05, + "loss": 0.4908, + "step": 2064 + }, + { + "epoch": 0.17, + "learning_rate": 1.8950246938984573e-05, + "loss": 0.5131, + "step": 2065 + }, + { + "epoch": 0.17, + "learning_rate": 1.894903794786328e-05, + "loss": 0.5325, + "step": 2066 + }, + { + "epoch": 0.17, + "learning_rate": 1.894782829956186e-05, + "loss": 0.5071, + "step": 2067 + }, + { + "epoch": 0.17, + "learning_rate": 1.8946617994169146e-05, + "loss": 0.5157, + "step": 2068 + }, + { + "epoch": 0.17, + "learning_rate": 1.8945407031774018e-05, + "loss": 0.4963, + "step": 2069 + }, + { + "epoch": 0.17, + "learning_rate": 1.8944195412465404e-05, + "loss": 0.5301, + "step": 2070 + }, + { + "epoch": 0.17, + "learning_rate": 1.8942983136332282e-05, + "loss": 0.5193, + "step": 2071 + }, + { + "epoch": 0.17, + "learning_rate": 1.8941770203463674e-05, + "loss": 0.4954, + "step": 2072 + }, + { + "epoch": 0.17, + "learning_rate": 1.8940556613948656e-05, + "loss": 0.5124, + "step": 2073 + }, + { + "epoch": 0.17, + "learning_rate": 1.8939342367876345e-05, + "loss": 0.51, + "step": 2074 + }, + { + "epoch": 0.17, + "learning_rate": 1.893812746533591e-05, + "loss": 0.4831, + "step": 2075 + }, + { + "epoch": 0.17, + "learning_rate": 1.8936911906416572e-05, + "loss": 0.4994, + "step": 2076 + }, + { + "epoch": 0.17, + "learning_rate": 1.8935695691207598e-05, + "loss": 0.5263, + "step": 2077 + }, + { + "epoch": 0.17, + "learning_rate": 1.8934478819798296e-05, + "loss": 0.4893, + "step": 2078 + }, + { + "epoch": 0.17, + "learning_rate": 1.8933261292278033e-05, + "loss": 0.5132, + "step": 2079 + }, + { + "epoch": 0.17, + "learning_rate": 1.8932043108736217e-05, + "loss": 0.5076, + "step": 2080 + }, + { + "epoch": 0.17, + "learning_rate": 1.89308242692623e-05, + "loss": 0.527, + "step": 2081 + }, + { + "epoch": 0.17, + "learning_rate": 1.89296047739458e-05, + "loss": 0.5058, + "step": 2082 + }, + { + "epoch": 0.17, + "learning_rate": 1.892838462287627e-05, + "loss": 0.5095, + "step": 2083 + }, + { + "epoch": 0.17, + "learning_rate": 1.8927163816143302e-05, + "loss": 0.4916, + "step": 2084 + }, + { + "epoch": 0.17, + "learning_rate": 1.8925942353836558e-05, + "loss": 0.4806, + "step": 2085 + }, + { + "epoch": 0.17, + "learning_rate": 1.892472023604573e-05, + "loss": 0.5076, + "step": 2086 + }, + { + "epoch": 0.17, + "learning_rate": 1.8923497462860572e-05, + "loss": 0.5209, + "step": 2087 + }, + { + "epoch": 0.17, + "learning_rate": 1.8922274034370875e-05, + "loss": 0.4888, + "step": 2088 + }, + { + "epoch": 0.17, + "learning_rate": 1.8921049950666484e-05, + "loss": 0.5002, + "step": 2089 + }, + { + "epoch": 0.17, + "learning_rate": 1.891982521183729e-05, + "loss": 0.5068, + "step": 2090 + }, + { + "epoch": 0.17, + "learning_rate": 1.891859981797323e-05, + "loss": 0.4904, + "step": 2091 + }, + { + "epoch": 0.18, + "learning_rate": 1.89173737691643e-05, + "loss": 0.5147, + "step": 2092 + }, + { + "epoch": 0.18, + "learning_rate": 1.8916147065500524e-05, + "loss": 0.489, + "step": 2093 + }, + { + "epoch": 0.18, + "learning_rate": 1.8914919707071997e-05, + "loss": 0.5265, + "step": 2094 + }, + { + "epoch": 0.18, + "learning_rate": 1.8913691693968846e-05, + "loss": 0.4928, + "step": 2095 + }, + { + "epoch": 0.18, + "learning_rate": 1.891246302628125e-05, + "loss": 0.5037, + "step": 2096 + }, + { + "epoch": 0.18, + "learning_rate": 1.891123370409944e-05, + "loss": 0.5027, + "step": 2097 + }, + { + "epoch": 0.18, + "learning_rate": 1.8910003727513697e-05, + "loss": 0.496, + "step": 2098 + }, + { + "epoch": 0.18, + "learning_rate": 1.8908773096614333e-05, + "loss": 0.4993, + "step": 2099 + }, + { + "epoch": 0.18, + "learning_rate": 1.8907541811491726e-05, + "loss": 0.4809, + "step": 2100 + }, + { + "epoch": 0.18, + "learning_rate": 1.89063098722363e-05, + "loss": 0.4981, + "step": 2101 + }, + { + "epoch": 0.18, + "learning_rate": 1.8905077278938524e-05, + "loss": 0.5007, + "step": 2102 + }, + { + "epoch": 0.18, + "learning_rate": 1.890384403168891e-05, + "loss": 0.5164, + "step": 2103 + }, + { + "epoch": 0.18, + "learning_rate": 1.890261013057802e-05, + "loss": 0.5046, + "step": 2104 + }, + { + "epoch": 0.18, + "learning_rate": 1.8901375575696476e-05, + "loss": 0.5137, + "step": 2105 + }, + { + "epoch": 0.18, + "learning_rate": 1.890014036713493e-05, + "loss": 0.5103, + "step": 2106 + }, + { + "epoch": 0.18, + "learning_rate": 1.8898904504984096e-05, + "loss": 0.5071, + "step": 2107 + }, + { + "epoch": 0.18, + "learning_rate": 1.8897667989334726e-05, + "loss": 0.5271, + "step": 2108 + }, + { + "epoch": 0.18, + "learning_rate": 1.889643082027763e-05, + "loss": 0.5044, + "step": 2109 + }, + { + "epoch": 0.18, + "learning_rate": 1.8895192997903657e-05, + "loss": 0.4989, + "step": 2110 + }, + { + "epoch": 0.18, + "learning_rate": 1.8893954522303707e-05, + "loss": 0.5072, + "step": 2111 + }, + { + "epoch": 0.18, + "learning_rate": 1.889271539356873e-05, + "loss": 0.4782, + "step": 2112 + }, + { + "epoch": 0.18, + "learning_rate": 1.889147561178972e-05, + "loss": 0.4853, + "step": 2113 + }, + { + "epoch": 0.18, + "learning_rate": 1.889023517705773e-05, + "loss": 0.5108, + "step": 2114 + }, + { + "epoch": 0.18, + "learning_rate": 1.888899408946384e-05, + "loss": 0.5195, + "step": 2115 + }, + { + "epoch": 0.18, + "learning_rate": 1.88877523490992e-05, + "loss": 0.4972, + "step": 2116 + }, + { + "epoch": 0.18, + "learning_rate": 1.888650995605499e-05, + "loss": 0.4881, + "step": 2117 + }, + { + "epoch": 0.18, + "learning_rate": 1.8885266910422454e-05, + "loss": 0.4766, + "step": 2118 + }, + { + "epoch": 0.18, + "learning_rate": 1.888402321229287e-05, + "loss": 0.4896, + "step": 2119 + }, + { + "epoch": 0.18, + "learning_rate": 1.8882778861757573e-05, + "loss": 0.5269, + "step": 2120 + }, + { + "epoch": 0.18, + "learning_rate": 1.8881533858907945e-05, + "loss": 0.5108, + "step": 2121 + }, + { + "epoch": 0.18, + "learning_rate": 1.888028820383541e-05, + "loss": 0.5037, + "step": 2122 + }, + { + "epoch": 0.18, + "learning_rate": 1.8879041896631448e-05, + "loss": 0.4973, + "step": 2123 + }, + { + "epoch": 0.18, + "learning_rate": 1.8877794937387576e-05, + "loss": 0.5348, + "step": 2124 + }, + { + "epoch": 0.18, + "learning_rate": 1.8876547326195373e-05, + "loss": 0.5247, + "step": 2125 + }, + { + "epoch": 0.18, + "learning_rate": 1.887529906314645e-05, + "loss": 0.5148, + "step": 2126 + }, + { + "epoch": 0.18, + "learning_rate": 1.8874050148332484e-05, + "loss": 0.5, + "step": 2127 + }, + { + "epoch": 0.18, + "learning_rate": 1.887280058184518e-05, + "loss": 0.4996, + "step": 2128 + }, + { + "epoch": 0.18, + "learning_rate": 1.8871550363776308e-05, + "loss": 0.5084, + "step": 2129 + }, + { + "epoch": 0.18, + "learning_rate": 1.8870299494217675e-05, + "loss": 0.5191, + "step": 2130 + }, + { + "epoch": 0.18, + "learning_rate": 1.8869047973261148e-05, + "loss": 0.5196, + "step": 2131 + }, + { + "epoch": 0.18, + "learning_rate": 1.8867795800998623e-05, + "loss": 0.5111, + "step": 2132 + }, + { + "epoch": 0.18, + "learning_rate": 1.8866542977522057e-05, + "loss": 0.4926, + "step": 2133 + }, + { + "epoch": 0.18, + "learning_rate": 1.8865289502923455e-05, + "loss": 0.5095, + "step": 2134 + }, + { + "epoch": 0.18, + "learning_rate": 1.8864035377294865e-05, + "loss": 0.5105, + "step": 2135 + }, + { + "epoch": 0.18, + "learning_rate": 1.8862780600728384e-05, + "loss": 0.507, + "step": 2136 + }, + { + "epoch": 0.18, + "learning_rate": 1.886152517331616e-05, + "loss": 0.486, + "step": 2137 + }, + { + "epoch": 0.18, + "learning_rate": 1.8860269095150387e-05, + "loss": 0.5058, + "step": 2138 + }, + { + "epoch": 0.18, + "learning_rate": 1.88590123663233e-05, + "loss": 0.4886, + "step": 2139 + }, + { + "epoch": 0.18, + "learning_rate": 1.8857754986927196e-05, + "loss": 0.5001, + "step": 2140 + }, + { + "epoch": 0.18, + "learning_rate": 1.8856496957054406e-05, + "loss": 0.5071, + "step": 2141 + }, + { + "epoch": 0.18, + "learning_rate": 1.8855238276797315e-05, + "loss": 0.5145, + "step": 2142 + }, + { + "epoch": 0.18, + "learning_rate": 1.885397894624836e-05, + "loss": 0.5025, + "step": 2143 + }, + { + "epoch": 0.18, + "learning_rate": 1.8852718965500018e-05, + "loss": 0.4977, + "step": 2144 + }, + { + "epoch": 0.18, + "learning_rate": 1.8851458334644814e-05, + "loss": 0.4879, + "step": 2145 + }, + { + "epoch": 0.18, + "learning_rate": 1.8850197053775326e-05, + "loss": 0.499, + "step": 2146 + }, + { + "epoch": 0.18, + "learning_rate": 1.8848935122984177e-05, + "loss": 0.4959, + "step": 2147 + }, + { + "epoch": 0.18, + "learning_rate": 1.884767254236404e-05, + "loss": 0.4981, + "step": 2148 + }, + { + "epoch": 0.18, + "learning_rate": 1.884640931200763e-05, + "loss": 0.5005, + "step": 2149 + }, + { + "epoch": 0.18, + "learning_rate": 1.8845145432007715e-05, + "loss": 0.4988, + "step": 2150 + }, + { + "epoch": 0.18, + "learning_rate": 1.884388090245711e-05, + "loss": 0.4929, + "step": 2151 + }, + { + "epoch": 0.18, + "learning_rate": 1.8842615723448678e-05, + "loss": 0.5127, + "step": 2152 + }, + { + "epoch": 0.18, + "learning_rate": 1.884134989507532e-05, + "loss": 0.5139, + "step": 2153 + }, + { + "epoch": 0.18, + "learning_rate": 1.8840083417430003e-05, + "loss": 0.4953, + "step": 2154 + }, + { + "epoch": 0.18, + "learning_rate": 1.8838816290605732e-05, + "loss": 0.5164, + "step": 2155 + }, + { + "epoch": 0.18, + "learning_rate": 1.883754851469555e-05, + "loss": 0.5008, + "step": 2156 + }, + { + "epoch": 0.18, + "learning_rate": 1.883628008979257e-05, + "loss": 0.4822, + "step": 2157 + }, + { + "epoch": 0.18, + "learning_rate": 1.8835011015989927e-05, + "loss": 0.5138, + "step": 2158 + }, + { + "epoch": 0.18, + "learning_rate": 1.8833741293380826e-05, + "loss": 0.5049, + "step": 2159 + }, + { + "epoch": 0.18, + "learning_rate": 1.883247092205851e-05, + "loss": 0.5085, + "step": 2160 + }, + { + "epoch": 0.18, + "learning_rate": 1.883119990211626e-05, + "loss": 0.4884, + "step": 2161 + }, + { + "epoch": 0.18, + "learning_rate": 1.8829928233647422e-05, + "loss": 0.5028, + "step": 2162 + }, + { + "epoch": 0.18, + "learning_rate": 1.8828655916745383e-05, + "loss": 0.5221, + "step": 2163 + }, + { + "epoch": 0.18, + "learning_rate": 1.8827382951503575e-05, + "loss": 0.5228, + "step": 2164 + }, + { + "epoch": 0.18, + "learning_rate": 1.8826109338015478e-05, + "loss": 0.5035, + "step": 2165 + }, + { + "epoch": 0.18, + "learning_rate": 1.8824835076374622e-05, + "loss": 0.4917, + "step": 2166 + }, + { + "epoch": 0.18, + "learning_rate": 1.882356016667458e-05, + "loss": 0.5087, + "step": 2167 + }, + { + "epoch": 0.18, + "learning_rate": 1.8822284609008985e-05, + "loss": 0.4921, + "step": 2168 + }, + { + "epoch": 0.18, + "learning_rate": 1.8821008403471497e-05, + "loss": 0.5027, + "step": 2169 + }, + { + "epoch": 0.18, + "learning_rate": 1.8819731550155845e-05, + "loss": 0.5117, + "step": 2170 + }, + { + "epoch": 0.18, + "learning_rate": 1.8818454049155792e-05, + "loss": 0.4992, + "step": 2171 + }, + { + "epoch": 0.18, + "learning_rate": 1.881717590056515e-05, + "loss": 0.4923, + "step": 2172 + }, + { + "epoch": 0.18, + "learning_rate": 1.8815897104477786e-05, + "loss": 0.4898, + "step": 2173 + }, + { + "epoch": 0.18, + "learning_rate": 1.8814617660987603e-05, + "loss": 0.523, + "step": 2174 + }, + { + "epoch": 0.18, + "learning_rate": 1.881333757018857e-05, + "loss": 0.5144, + "step": 2175 + }, + { + "epoch": 0.18, + "learning_rate": 1.8812056832174673e-05, + "loss": 0.4931, + "step": 2176 + }, + { + "epoch": 0.18, + "learning_rate": 1.881077544703998e-05, + "loss": 0.4996, + "step": 2177 + }, + { + "epoch": 0.18, + "learning_rate": 1.8809493414878585e-05, + "loss": 0.4943, + "step": 2178 + }, + { + "epoch": 0.18, + "learning_rate": 1.880821073578463e-05, + "loss": 0.4915, + "step": 2179 + }, + { + "epoch": 0.18, + "learning_rate": 1.8806927409852323e-05, + "loss": 0.5129, + "step": 2180 + }, + { + "epoch": 0.18, + "learning_rate": 1.8805643437175892e-05, + "loss": 0.4973, + "step": 2181 + }, + { + "epoch": 0.18, + "learning_rate": 1.8804358817849634e-05, + "loss": 0.4808, + "step": 2182 + }, + { + "epoch": 0.18, + "learning_rate": 1.8803073551967884e-05, + "loss": 0.5014, + "step": 2183 + }, + { + "epoch": 0.18, + "learning_rate": 1.8801787639625025e-05, + "loss": 0.5324, + "step": 2184 + }, + { + "epoch": 0.18, + "learning_rate": 1.8800501080915496e-05, + "loss": 0.4964, + "step": 2185 + }, + { + "epoch": 0.18, + "learning_rate": 1.879921387593377e-05, + "loss": 0.5127, + "step": 2186 + }, + { + "epoch": 0.18, + "learning_rate": 1.8797926024774375e-05, + "loss": 0.5176, + "step": 2187 + }, + { + "epoch": 0.18, + "learning_rate": 1.8796637527531883e-05, + "loss": 0.5158, + "step": 2188 + }, + { + "epoch": 0.18, + "learning_rate": 1.8795348384300922e-05, + "loss": 0.5075, + "step": 2189 + }, + { + "epoch": 0.18, + "learning_rate": 1.879405859517616e-05, + "loss": 0.4952, + "step": 2190 + }, + { + "epoch": 0.18, + "learning_rate": 1.8792768160252308e-05, + "loss": 0.5071, + "step": 2191 + }, + { + "epoch": 0.18, + "learning_rate": 1.8791477079624138e-05, + "loss": 0.5143, + "step": 2192 + }, + { + "epoch": 0.18, + "learning_rate": 1.8790185353386453e-05, + "loss": 0.4903, + "step": 2193 + }, + { + "epoch": 0.18, + "learning_rate": 1.878889298163412e-05, + "loss": 0.5099, + "step": 2194 + }, + { + "epoch": 0.18, + "learning_rate": 1.8787599964462044e-05, + "loss": 0.5002, + "step": 2195 + }, + { + "epoch": 0.18, + "learning_rate": 1.8786306301965175e-05, + "loss": 0.4997, + "step": 2196 + }, + { + "epoch": 0.18, + "learning_rate": 1.8785011994238516e-05, + "loss": 0.5037, + "step": 2197 + }, + { + "epoch": 0.18, + "learning_rate": 1.8783717041377113e-05, + "loss": 0.5111, + "step": 2198 + }, + { + "epoch": 0.18, + "learning_rate": 1.8782421443476072e-05, + "loss": 0.4795, + "step": 2199 + }, + { + "epoch": 0.18, + "learning_rate": 1.878112520063052e-05, + "loss": 0.4958, + "step": 2200 + }, + { + "epoch": 0.18, + "learning_rate": 1.8779828312935664e-05, + "loss": 0.5096, + "step": 2201 + }, + { + "epoch": 0.18, + "learning_rate": 1.877853078048673e-05, + "loss": 0.5011, + "step": 2202 + }, + { + "epoch": 0.18, + "learning_rate": 1.8777232603379012e-05, + "loss": 0.5011, + "step": 2203 + }, + { + "epoch": 0.18, + "learning_rate": 1.8775933781707836e-05, + "loss": 0.4967, + "step": 2204 + }, + { + "epoch": 0.18, + "learning_rate": 1.8774634315568583e-05, + "loss": 0.5074, + "step": 2205 + }, + { + "epoch": 0.18, + "learning_rate": 1.8773334205056687e-05, + "loss": 0.4919, + "step": 2206 + }, + { + "epoch": 0.18, + "learning_rate": 1.8772033450267617e-05, + "loss": 0.5044, + "step": 2207 + }, + { + "epoch": 0.18, + "learning_rate": 1.8770732051296895e-05, + "loss": 0.5007, + "step": 2208 + }, + { + "epoch": 0.18, + "learning_rate": 1.876943000824009e-05, + "loss": 0.5067, + "step": 2209 + }, + { + "epoch": 0.18, + "learning_rate": 1.8768127321192825e-05, + "loss": 0.4923, + "step": 2210 + }, + { + "epoch": 0.18, + "learning_rate": 1.8766823990250756e-05, + "loss": 0.4937, + "step": 2211 + }, + { + "epoch": 0.19, + "learning_rate": 1.8765520015509597e-05, + "loss": 0.5473, + "step": 2212 + }, + { + "epoch": 0.19, + "learning_rate": 1.8764215397065105e-05, + "loss": 0.5043, + "step": 2213 + }, + { + "epoch": 0.19, + "learning_rate": 1.8762910135013088e-05, + "loss": 0.4941, + "step": 2214 + }, + { + "epoch": 0.19, + "learning_rate": 1.8761604229449402e-05, + "loss": 0.5032, + "step": 2215 + }, + { + "epoch": 0.19, + "learning_rate": 1.8760297680469938e-05, + "loss": 0.4992, + "step": 2216 + }, + { + "epoch": 0.19, + "learning_rate": 1.875899048817065e-05, + "loss": 0.4925, + "step": 2217 + }, + { + "epoch": 0.19, + "learning_rate": 1.8757682652647538e-05, + "loss": 0.5178, + "step": 2218 + }, + { + "epoch": 0.19, + "learning_rate": 1.875637417399663e-05, + "loss": 0.5141, + "step": 2219 + }, + { + "epoch": 0.19, + "learning_rate": 1.875506505231403e-05, + "loss": 0.4848, + "step": 2220 + }, + { + "epoch": 0.19, + "learning_rate": 1.8753755287695866e-05, + "loss": 0.4989, + "step": 2221 + }, + { + "epoch": 0.19, + "learning_rate": 1.875244488023832e-05, + "loss": 0.4951, + "step": 2222 + }, + { + "epoch": 0.19, + "learning_rate": 1.875113383003763e-05, + "loss": 0.4867, + "step": 2223 + }, + { + "epoch": 0.19, + "learning_rate": 1.8749822137190065e-05, + "loss": 0.4955, + "step": 2224 + }, + { + "epoch": 0.19, + "learning_rate": 1.8748509801791962e-05, + "loss": 0.514, + "step": 2225 + }, + { + "epoch": 0.19, + "learning_rate": 1.874719682393968e-05, + "loss": 0.4934, + "step": 2226 + }, + { + "epoch": 0.19, + "learning_rate": 1.8745883203729648e-05, + "loss": 0.504, + "step": 2227 + }, + { + "epoch": 0.19, + "learning_rate": 1.8744568941258335e-05, + "loss": 0.5041, + "step": 2228 + }, + { + "epoch": 0.19, + "learning_rate": 1.8743254036622243e-05, + "loss": 0.4908, + "step": 2229 + }, + { + "epoch": 0.19, + "learning_rate": 1.874193848991795e-05, + "loss": 0.5062, + "step": 2230 + }, + { + "epoch": 0.19, + "learning_rate": 1.8740622301242045e-05, + "loss": 0.5084, + "step": 2231 + }, + { + "epoch": 0.19, + "learning_rate": 1.8739305470691197e-05, + "loss": 0.4935, + "step": 2232 + }, + { + "epoch": 0.19, + "learning_rate": 1.8737987998362106e-05, + "loss": 0.4952, + "step": 2233 + }, + { + "epoch": 0.19, + "learning_rate": 1.8736669884351523e-05, + "loss": 0.5139, + "step": 2234 + }, + { + "epoch": 0.19, + "learning_rate": 1.8735351128756238e-05, + "loss": 0.4954, + "step": 2235 + }, + { + "epoch": 0.19, + "learning_rate": 1.8734031731673096e-05, + "loss": 0.5215, + "step": 2236 + }, + { + "epoch": 0.19, + "learning_rate": 1.8732711693199e-05, + "loss": 0.5039, + "step": 2237 + }, + { + "epoch": 0.19, + "learning_rate": 1.873139101343087e-05, + "loss": 0.5171, + "step": 2238 + }, + { + "epoch": 0.19, + "learning_rate": 1.8730069692465708e-05, + "loss": 0.4796, + "step": 2239 + }, + { + "epoch": 0.19, + "learning_rate": 1.8728747730400533e-05, + "loss": 0.5093, + "step": 2240 + }, + { + "epoch": 0.19, + "learning_rate": 1.872742512733243e-05, + "loss": 0.5096, + "step": 2241 + }, + { + "epoch": 0.19, + "learning_rate": 1.8726101883358534e-05, + "loss": 0.4824, + "step": 2242 + }, + { + "epoch": 0.19, + "learning_rate": 1.8724777998576006e-05, + "loss": 0.5057, + "step": 2243 + }, + { + "epoch": 0.19, + "learning_rate": 1.872345347308207e-05, + "loss": 0.5089, + "step": 2244 + }, + { + "epoch": 0.19, + "learning_rate": 1.872212830697399e-05, + "loss": 0.501, + "step": 2245 + }, + { + "epoch": 0.19, + "learning_rate": 1.8720802500349095e-05, + "loss": 0.5236, + "step": 2246 + }, + { + "epoch": 0.19, + "learning_rate": 1.871947605330473e-05, + "loss": 0.5291, + "step": 2247 + }, + { + "epoch": 0.19, + "learning_rate": 1.8718148965938312e-05, + "loss": 0.5228, + "step": 2248 + }, + { + "epoch": 0.19, + "learning_rate": 1.8716821238347296e-05, + "loss": 0.4989, + "step": 2249 + }, + { + "epoch": 0.19, + "learning_rate": 1.8715492870629183e-05, + "loss": 0.4978, + "step": 2250 + }, + { + "epoch": 0.19, + "learning_rate": 1.8714163862881527e-05, + "loss": 0.4955, + "step": 2251 + }, + { + "epoch": 0.19, + "learning_rate": 1.8712834215201918e-05, + "loss": 0.5113, + "step": 2252 + }, + { + "epoch": 0.19, + "learning_rate": 1.8711503927688007e-05, + "loss": 0.5227, + "step": 2253 + }, + { + "epoch": 0.19, + "learning_rate": 1.871017300043748e-05, + "loss": 0.5006, + "step": 2254 + }, + { + "epoch": 0.19, + "learning_rate": 1.8708841433548076e-05, + "loss": 0.5215, + "step": 2255 + }, + { + "epoch": 0.19, + "learning_rate": 1.8707509227117578e-05, + "loss": 0.5261, + "step": 2256 + }, + { + "epoch": 0.19, + "learning_rate": 1.8706176381243822e-05, + "loss": 0.5057, + "step": 2257 + }, + { + "epoch": 0.19, + "learning_rate": 1.8704842896024685e-05, + "loss": 0.4915, + "step": 2258 + }, + { + "epoch": 0.19, + "learning_rate": 1.8703508771558093e-05, + "loss": 0.4977, + "step": 2259 + }, + { + "epoch": 0.19, + "learning_rate": 1.8702174007942012e-05, + "loss": 0.4921, + "step": 2260 + }, + { + "epoch": 0.19, + "learning_rate": 1.870083860527447e-05, + "loss": 0.4881, + "step": 2261 + }, + { + "epoch": 0.19, + "learning_rate": 1.869950256365353e-05, + "loss": 0.5051, + "step": 2262 + }, + { + "epoch": 0.19, + "learning_rate": 1.8698165883177308e-05, + "loss": 0.5007, + "step": 2263 + }, + { + "epoch": 0.19, + "learning_rate": 1.8696828563943962e-05, + "loss": 0.5076, + "step": 2264 + }, + { + "epoch": 0.19, + "learning_rate": 1.8695490606051694e-05, + "loss": 0.4853, + "step": 2265 + }, + { + "epoch": 0.19, + "learning_rate": 1.8694152009598767e-05, + "loss": 0.5068, + "step": 2266 + }, + { + "epoch": 0.19, + "learning_rate": 1.8692812774683477e-05, + "loss": 0.4871, + "step": 2267 + }, + { + "epoch": 0.19, + "learning_rate": 1.8691472901404174e-05, + "loss": 0.4977, + "step": 2268 + }, + { + "epoch": 0.19, + "learning_rate": 1.8690132389859254e-05, + "loss": 0.4994, + "step": 2269 + }, + { + "epoch": 0.19, + "learning_rate": 1.868879124014715e-05, + "loss": 0.4928, + "step": 2270 + }, + { + "epoch": 0.19, + "learning_rate": 1.8687449452366362e-05, + "loss": 0.5154, + "step": 2271 + }, + { + "epoch": 0.19, + "learning_rate": 1.8686107026615418e-05, + "loss": 0.5094, + "step": 2272 + }, + { + "epoch": 0.19, + "learning_rate": 1.8684763962992903e-05, + "loss": 0.4799, + "step": 2273 + }, + { + "epoch": 0.19, + "learning_rate": 1.8683420261597445e-05, + "loss": 0.5091, + "step": 2274 + }, + { + "epoch": 0.19, + "learning_rate": 1.8682075922527717e-05, + "loss": 0.5067, + "step": 2275 + }, + { + "epoch": 0.19, + "learning_rate": 1.868073094588245e-05, + "loss": 0.5016, + "step": 2276 + }, + { + "epoch": 0.19, + "learning_rate": 1.8679385331760405e-05, + "loss": 0.5159, + "step": 2277 + }, + { + "epoch": 0.19, + "learning_rate": 1.8678039080260403e-05, + "loss": 0.5221, + "step": 2278 + }, + { + "epoch": 0.19, + "learning_rate": 1.8676692191481303e-05, + "loss": 0.4992, + "step": 2279 + }, + { + "epoch": 0.19, + "learning_rate": 1.867534466552202e-05, + "loss": 0.5096, + "step": 2280 + }, + { + "epoch": 0.19, + "learning_rate": 1.8673996502481507e-05, + "loss": 0.5064, + "step": 2281 + }, + { + "epoch": 0.19, + "learning_rate": 1.867264770245877e-05, + "loss": 0.4879, + "step": 2282 + }, + { + "epoch": 0.19, + "learning_rate": 1.8671298265552855e-05, + "loss": 0.5101, + "step": 2283 + }, + { + "epoch": 0.19, + "learning_rate": 1.8669948191862866e-05, + "loss": 0.5155, + "step": 2284 + }, + { + "epoch": 0.19, + "learning_rate": 1.866859748148794e-05, + "loss": 0.5111, + "step": 2285 + }, + { + "epoch": 0.19, + "learning_rate": 1.866724613452727e-05, + "loss": 0.4805, + "step": 2286 + }, + { + "epoch": 0.19, + "learning_rate": 1.8665894151080097e-05, + "loss": 0.5088, + "step": 2287 + }, + { + "epoch": 0.19, + "learning_rate": 1.8664541531245698e-05, + "loss": 0.5163, + "step": 2288 + }, + { + "epoch": 0.19, + "learning_rate": 1.866318827512341e-05, + "loss": 0.5177, + "step": 2289 + }, + { + "epoch": 0.19, + "learning_rate": 1.8661834382812608e-05, + "loss": 0.4867, + "step": 2290 + }, + { + "epoch": 0.19, + "learning_rate": 1.8660479854412713e-05, + "loss": 0.5183, + "step": 2291 + }, + { + "epoch": 0.19, + "learning_rate": 1.8659124690023205e-05, + "loss": 0.4917, + "step": 2292 + }, + { + "epoch": 0.19, + "learning_rate": 1.865776888974359e-05, + "loss": 0.5098, + "step": 2293 + }, + { + "epoch": 0.19, + "learning_rate": 1.865641245367344e-05, + "loss": 0.4977, + "step": 2294 + }, + { + "epoch": 0.19, + "learning_rate": 1.8655055381912367e-05, + "loss": 0.5151, + "step": 2295 + }, + { + "epoch": 0.19, + "learning_rate": 1.8653697674560023e-05, + "loss": 0.524, + "step": 2296 + }, + { + "epoch": 0.19, + "learning_rate": 1.8652339331716114e-05, + "loss": 0.4991, + "step": 2297 + }, + { + "epoch": 0.19, + "learning_rate": 1.8650980353480395e-05, + "loss": 0.5015, + "step": 2298 + }, + { + "epoch": 0.19, + "learning_rate": 1.8649620739952658e-05, + "loss": 0.5034, + "step": 2299 + }, + { + "epoch": 0.19, + "learning_rate": 1.8648260491232753e-05, + "loss": 0.4985, + "step": 2300 + }, + { + "epoch": 0.19, + "learning_rate": 1.8646899607420567e-05, + "loss": 0.4961, + "step": 2301 + }, + { + "epoch": 0.19, + "learning_rate": 1.8645538088616038e-05, + "loss": 0.5044, + "step": 2302 + }, + { + "epoch": 0.19, + "learning_rate": 1.8644175934919156e-05, + "loss": 0.5092, + "step": 2303 + }, + { + "epoch": 0.19, + "learning_rate": 1.8642813146429943e-05, + "loss": 0.5069, + "step": 2304 + }, + { + "epoch": 0.19, + "learning_rate": 1.8641449723248482e-05, + "loss": 0.5064, + "step": 2305 + }, + { + "epoch": 0.19, + "learning_rate": 1.8640085665474898e-05, + "loss": 0.5085, + "step": 2306 + }, + { + "epoch": 0.19, + "learning_rate": 1.8638720973209353e-05, + "loss": 0.5056, + "step": 2307 + }, + { + "epoch": 0.19, + "learning_rate": 1.863735564655208e-05, + "loss": 0.4973, + "step": 2308 + }, + { + "epoch": 0.19, + "learning_rate": 1.8635989685603327e-05, + "loss": 0.5089, + "step": 2309 + }, + { + "epoch": 0.19, + "learning_rate": 1.8634623090463413e-05, + "loss": 0.4941, + "step": 2310 + }, + { + "epoch": 0.19, + "learning_rate": 1.8633255861232692e-05, + "loss": 0.4903, + "step": 2311 + }, + { + "epoch": 0.19, + "learning_rate": 1.863188799801157e-05, + "loss": 0.5029, + "step": 2312 + }, + { + "epoch": 0.19, + "learning_rate": 1.8630519500900495e-05, + "loss": 0.4915, + "step": 2313 + }, + { + "epoch": 0.19, + "learning_rate": 1.8629150369999967e-05, + "loss": 0.4913, + "step": 2314 + }, + { + "epoch": 0.19, + "learning_rate": 1.8627780605410528e-05, + "loss": 0.5075, + "step": 2315 + }, + { + "epoch": 0.19, + "learning_rate": 1.8626410207232762e-05, + "loss": 0.4993, + "step": 2316 + }, + { + "epoch": 0.19, + "learning_rate": 1.8625039175567316e-05, + "loss": 0.5164, + "step": 2317 + }, + { + "epoch": 0.19, + "learning_rate": 1.8623667510514867e-05, + "loss": 0.4919, + "step": 2318 + }, + { + "epoch": 0.19, + "learning_rate": 1.8622295212176142e-05, + "loss": 0.5125, + "step": 2319 + }, + { + "epoch": 0.19, + "learning_rate": 1.862092228065192e-05, + "loss": 0.5005, + "step": 2320 + }, + { + "epoch": 0.19, + "learning_rate": 1.861954871604302e-05, + "loss": 0.4824, + "step": 2321 + }, + { + "epoch": 0.19, + "learning_rate": 1.8618174518450317e-05, + "loss": 0.4943, + "step": 2322 + }, + { + "epoch": 0.19, + "learning_rate": 1.8616799687974724e-05, + "loss": 0.5029, + "step": 2323 + }, + { + "epoch": 0.19, + "learning_rate": 1.86154242247172e-05, + "loss": 0.4923, + "step": 2324 + }, + { + "epoch": 0.19, + "learning_rate": 1.8614048128778755e-05, + "loss": 0.5028, + "step": 2325 + }, + { + "epoch": 0.19, + "learning_rate": 1.8612671400260445e-05, + "loss": 0.4956, + "step": 2326 + }, + { + "epoch": 0.19, + "learning_rate": 1.861129403926337e-05, + "loss": 0.5067, + "step": 2327 + }, + { + "epoch": 0.19, + "learning_rate": 1.8609916045888677e-05, + "loss": 0.4775, + "step": 2328 + }, + { + "epoch": 0.19, + "learning_rate": 1.860853742023756e-05, + "loss": 0.4859, + "step": 2329 + }, + { + "epoch": 0.19, + "learning_rate": 1.860715816241126e-05, + "loss": 0.5, + "step": 2330 + }, + { + "epoch": 0.2, + "learning_rate": 1.860577827251107e-05, + "loss": 0.5103, + "step": 2331 + }, + { + "epoch": 0.2, + "learning_rate": 1.8604397750638314e-05, + "loss": 0.5085, + "step": 2332 + }, + { + "epoch": 0.2, + "learning_rate": 1.8603016596894375e-05, + "loss": 0.4992, + "step": 2333 + }, + { + "epoch": 0.2, + "learning_rate": 1.860163481138068e-05, + "loss": 0.5093, + "step": 2334 + }, + { + "epoch": 0.2, + "learning_rate": 1.8600252394198702e-05, + "loss": 0.5172, + "step": 2335 + }, + { + "epoch": 0.2, + "learning_rate": 1.8598869345449957e-05, + "loss": 0.4971, + "step": 2336 + }, + { + "epoch": 0.2, + "learning_rate": 1.8597485665236016e-05, + "loss": 0.5007, + "step": 2337 + }, + { + "epoch": 0.2, + "learning_rate": 1.8596101353658488e-05, + "loss": 0.4957, + "step": 2338 + }, + { + "epoch": 0.2, + "learning_rate": 1.8594716410819027e-05, + "loss": 0.4941, + "step": 2339 + }, + { + "epoch": 0.2, + "learning_rate": 1.8593330836819342e-05, + "loss": 0.4833, + "step": 2340 + }, + { + "epoch": 0.2, + "learning_rate": 1.8591944631761185e-05, + "loss": 0.4959, + "step": 2341 + }, + { + "epoch": 0.2, + "learning_rate": 1.859055779574635e-05, + "loss": 0.5065, + "step": 2342 + }, + { + "epoch": 0.2, + "learning_rate": 1.858917032887668e-05, + "loss": 0.5085, + "step": 2343 + }, + { + "epoch": 0.2, + "learning_rate": 1.8587782231254065e-05, + "loss": 0.5195, + "step": 2344 + }, + { + "epoch": 0.2, + "learning_rate": 1.8586393502980442e-05, + "loss": 0.5003, + "step": 2345 + }, + { + "epoch": 0.2, + "learning_rate": 1.8585004144157798e-05, + "loss": 0.4933, + "step": 2346 + }, + { + "epoch": 0.2, + "learning_rate": 1.8583614154888154e-05, + "loss": 0.5186, + "step": 2347 + }, + { + "epoch": 0.2, + "learning_rate": 1.8582223535273587e-05, + "loss": 0.4988, + "step": 2348 + }, + { + "epoch": 0.2, + "learning_rate": 1.8580832285416223e-05, + "loss": 0.5032, + "step": 2349 + }, + { + "epoch": 0.2, + "learning_rate": 1.8579440405418222e-05, + "loss": 0.5109, + "step": 2350 + }, + { + "epoch": 0.2, + "learning_rate": 1.857804789538181e-05, + "loss": 0.503, + "step": 2351 + }, + { + "epoch": 0.2, + "learning_rate": 1.8576654755409233e-05, + "loss": 0.5101, + "step": 2352 + }, + { + "epoch": 0.2, + "learning_rate": 1.8575260985602806e-05, + "loss": 0.5242, + "step": 2353 + }, + { + "epoch": 0.2, + "learning_rate": 1.8573866586064877e-05, + "loss": 0.5165, + "step": 2354 + }, + { + "epoch": 0.2, + "learning_rate": 1.857247155689785e-05, + "loss": 0.5158, + "step": 2355 + }, + { + "epoch": 0.2, + "learning_rate": 1.8571075898204167e-05, + "loss": 0.4967, + "step": 2356 + }, + { + "epoch": 0.2, + "learning_rate": 1.856967961008632e-05, + "loss": 0.5094, + "step": 2357 + }, + { + "epoch": 0.2, + "learning_rate": 1.8568282692646844e-05, + "loss": 0.4908, + "step": 2358 + }, + { + "epoch": 0.2, + "learning_rate": 1.8566885145988326e-05, + "loss": 0.48, + "step": 2359 + }, + { + "epoch": 0.2, + "learning_rate": 1.8565486970213397e-05, + "loss": 0.5177, + "step": 2360 + }, + { + "epoch": 0.2, + "learning_rate": 1.8564088165424733e-05, + "loss": 0.496, + "step": 2361 + }, + { + "epoch": 0.2, + "learning_rate": 1.8562688731725053e-05, + "loss": 0.5195, + "step": 2362 + }, + { + "epoch": 0.2, + "learning_rate": 1.8561288669217125e-05, + "loss": 0.4852, + "step": 2363 + }, + { + "epoch": 0.2, + "learning_rate": 1.8559887978003766e-05, + "loss": 0.4954, + "step": 2364 + }, + { + "epoch": 0.2, + "learning_rate": 1.8558486658187843e-05, + "loss": 0.5074, + "step": 2365 + }, + { + "epoch": 0.2, + "learning_rate": 1.8557084709872253e-05, + "loss": 0.4885, + "step": 2366 + }, + { + "epoch": 0.2, + "learning_rate": 1.8555682133159952e-05, + "loss": 0.4868, + "step": 2367 + }, + { + "epoch": 0.2, + "learning_rate": 1.8554278928153942e-05, + "loss": 0.5194, + "step": 2368 + }, + { + "epoch": 0.2, + "learning_rate": 1.855287509495727e-05, + "loss": 0.4986, + "step": 2369 + }, + { + "epoch": 0.2, + "learning_rate": 1.8551470633673023e-05, + "loss": 0.5032, + "step": 2370 + }, + { + "epoch": 0.2, + "learning_rate": 1.855006554440434e-05, + "loss": 0.5006, + "step": 2371 + }, + { + "epoch": 0.2, + "learning_rate": 1.8548659827254408e-05, + "loss": 0.5124, + "step": 2372 + }, + { + "epoch": 0.2, + "learning_rate": 1.8547253482326458e-05, + "loss": 0.4894, + "step": 2373 + }, + { + "epoch": 0.2, + "learning_rate": 1.8545846509723757e-05, + "loss": 0.5089, + "step": 2374 + }, + { + "epoch": 0.2, + "learning_rate": 1.8544438909549636e-05, + "loss": 0.4991, + "step": 2375 + }, + { + "epoch": 0.2, + "learning_rate": 1.854303068190746e-05, + "loss": 0.5044, + "step": 2376 + }, + { + "epoch": 0.2, + "learning_rate": 1.854162182690064e-05, + "loss": 0.5011, + "step": 2377 + }, + { + "epoch": 0.2, + "learning_rate": 1.8540212344632646e-05, + "loss": 0.4879, + "step": 2378 + }, + { + "epoch": 0.2, + "learning_rate": 1.8538802235206977e-05, + "loss": 0.5249, + "step": 2379 + }, + { + "epoch": 0.2, + "learning_rate": 1.8537391498727187e-05, + "loss": 0.489, + "step": 2380 + }, + { + "epoch": 0.2, + "learning_rate": 1.8535980135296876e-05, + "loss": 0.5214, + "step": 2381 + }, + { + "epoch": 0.2, + "learning_rate": 1.8534568145019687e-05, + "loss": 0.5325, + "step": 2382 + }, + { + "epoch": 0.2, + "learning_rate": 1.853315552799931e-05, + "loss": 0.5143, + "step": 2383 + }, + { + "epoch": 0.2, + "learning_rate": 1.8531742284339486e-05, + "loss": 0.5069, + "step": 2384 + }, + { + "epoch": 0.2, + "learning_rate": 1.853032841414399e-05, + "loss": 0.4942, + "step": 2385 + }, + { + "epoch": 0.2, + "learning_rate": 1.852891391751666e-05, + "loss": 0.4831, + "step": 2386 + }, + { + "epoch": 0.2, + "learning_rate": 1.8527498794561367e-05, + "loss": 0.4999, + "step": 2387 + }, + { + "epoch": 0.2, + "learning_rate": 1.8526083045382025e-05, + "loss": 0.4998, + "step": 2388 + }, + { + "epoch": 0.2, + "learning_rate": 1.852466667008261e-05, + "loss": 0.5075, + "step": 2389 + }, + { + "epoch": 0.2, + "learning_rate": 1.8523249668767135e-05, + "loss": 0.5047, + "step": 2390 + }, + { + "epoch": 0.2, + "learning_rate": 1.852183204153965e-05, + "loss": 0.5177, + "step": 2391 + }, + { + "epoch": 0.2, + "learning_rate": 1.852041378850427e-05, + "loss": 0.486, + "step": 2392 + }, + { + "epoch": 0.2, + "learning_rate": 1.851899490976514e-05, + "loss": 0.4809, + "step": 2393 + }, + { + "epoch": 0.2, + "learning_rate": 1.851757540542645e-05, + "loss": 0.5098, + "step": 2394 + }, + { + "epoch": 0.2, + "learning_rate": 1.8516155275592457e-05, + "loss": 0.4916, + "step": 2395 + }, + { + "epoch": 0.2, + "learning_rate": 1.8514734520367438e-05, + "loss": 0.5143, + "step": 2396 + }, + { + "epoch": 0.2, + "learning_rate": 1.8513313139855734e-05, + "loss": 0.4984, + "step": 2397 + }, + { + "epoch": 0.2, + "learning_rate": 1.8511891134161718e-05, + "loss": 0.4834, + "step": 2398 + }, + { + "epoch": 0.2, + "learning_rate": 1.8510468503389825e-05, + "loss": 0.4972, + "step": 2399 + }, + { + "epoch": 0.2, + "learning_rate": 1.8509045247644524e-05, + "loss": 0.4988, + "step": 2400 + }, + { + "epoch": 0.2, + "learning_rate": 1.8507621367030326e-05, + "loss": 0.5079, + "step": 2401 + }, + { + "epoch": 0.2, + "learning_rate": 1.8506196861651802e-05, + "loss": 0.514, + "step": 2402 + }, + { + "epoch": 0.2, + "learning_rate": 1.8504771731613568e-05, + "loss": 0.4905, + "step": 2403 + }, + { + "epoch": 0.2, + "learning_rate": 1.8503345977020262e-05, + "loss": 0.5006, + "step": 2404 + }, + { + "epoch": 0.2, + "learning_rate": 1.8501919597976602e-05, + "loss": 0.4949, + "step": 2405 + }, + { + "epoch": 0.2, + "learning_rate": 1.850049259458733e-05, + "loss": 0.5129, + "step": 2406 + }, + { + "epoch": 0.2, + "learning_rate": 1.8499064966957233e-05, + "loss": 0.498, + "step": 2407 + }, + { + "epoch": 0.2, + "learning_rate": 1.8497636715191153e-05, + "loss": 0.499, + "step": 2408 + }, + { + "epoch": 0.2, + "learning_rate": 1.8496207839393984e-05, + "loss": 0.4932, + "step": 2409 + }, + { + "epoch": 0.2, + "learning_rate": 1.849477833967065e-05, + "loss": 0.5081, + "step": 2410 + }, + { + "epoch": 0.2, + "learning_rate": 1.849334821612612e-05, + "loss": 0.497, + "step": 2411 + }, + { + "epoch": 0.2, + "learning_rate": 1.8491917468865426e-05, + "loss": 0.5113, + "step": 2412 + }, + { + "epoch": 0.2, + "learning_rate": 1.8490486097993635e-05, + "loss": 0.5037, + "step": 2413 + }, + { + "epoch": 0.2, + "learning_rate": 1.848905410361586e-05, + "loss": 0.4858, + "step": 2414 + }, + { + "epoch": 0.2, + "learning_rate": 1.848762148583726e-05, + "loss": 0.4957, + "step": 2415 + }, + { + "epoch": 0.2, + "learning_rate": 1.8486188244763038e-05, + "loss": 0.5217, + "step": 2416 + }, + { + "epoch": 0.2, + "learning_rate": 1.8484754380498452e-05, + "loss": 0.496, + "step": 2417 + }, + { + "epoch": 0.2, + "learning_rate": 1.8483319893148794e-05, + "loss": 0.4957, + "step": 2418 + }, + { + "epoch": 0.2, + "learning_rate": 1.848188478281941e-05, + "loss": 0.4935, + "step": 2419 + }, + { + "epoch": 0.2, + "learning_rate": 1.8480449049615684e-05, + "loss": 0.4964, + "step": 2420 + }, + { + "epoch": 0.2, + "learning_rate": 1.847901269364305e-05, + "loss": 0.4948, + "step": 2421 + }, + { + "epoch": 0.2, + "learning_rate": 1.847757571500699e-05, + "loss": 0.4968, + "step": 2422 + }, + { + "epoch": 0.2, + "learning_rate": 1.8476138113813037e-05, + "loss": 0.5153, + "step": 2423 + }, + { + "epoch": 0.2, + "learning_rate": 1.8474699890166753e-05, + "loss": 0.513, + "step": 2424 + }, + { + "epoch": 0.2, + "learning_rate": 1.8473261044173756e-05, + "loss": 0.5264, + "step": 2425 + }, + { + "epoch": 0.2, + "learning_rate": 1.8471821575939713e-05, + "loss": 0.4933, + "step": 2426 + }, + { + "epoch": 0.2, + "learning_rate": 1.8470381485570327e-05, + "loss": 0.5192, + "step": 2427 + }, + { + "epoch": 0.2, + "learning_rate": 1.8468940773171357e-05, + "loss": 0.4959, + "step": 2428 + }, + { + "epoch": 0.2, + "learning_rate": 1.8467499438848606e-05, + "loss": 0.5083, + "step": 2429 + }, + { + "epoch": 0.2, + "learning_rate": 1.846605748270791e-05, + "loss": 0.5058, + "step": 2430 + }, + { + "epoch": 0.2, + "learning_rate": 1.8464614904855168e-05, + "loss": 0.5126, + "step": 2431 + }, + { + "epoch": 0.2, + "learning_rate": 1.8463171705396313e-05, + "loss": 0.5123, + "step": 2432 + }, + { + "epoch": 0.2, + "learning_rate": 1.846172788443733e-05, + "loss": 0.4949, + "step": 2433 + }, + { + "epoch": 0.2, + "learning_rate": 1.8460283442084246e-05, + "loss": 0.497, + "step": 2434 + }, + { + "epoch": 0.2, + "learning_rate": 1.8458838378443134e-05, + "loss": 0.5059, + "step": 2435 + }, + { + "epoch": 0.2, + "learning_rate": 1.8457392693620114e-05, + "loss": 0.5048, + "step": 2436 + }, + { + "epoch": 0.2, + "learning_rate": 1.8455946387721356e-05, + "loss": 0.518, + "step": 2437 + }, + { + "epoch": 0.2, + "learning_rate": 1.845449946085306e-05, + "loss": 0.5013, + "step": 2438 + }, + { + "epoch": 0.2, + "learning_rate": 1.8453051913121494e-05, + "loss": 0.4975, + "step": 2439 + }, + { + "epoch": 0.2, + "learning_rate": 1.8451603744632952e-05, + "loss": 0.504, + "step": 2440 + }, + { + "epoch": 0.2, + "learning_rate": 1.845015495549378e-05, + "loss": 0.5083, + "step": 2441 + }, + { + "epoch": 0.2, + "learning_rate": 1.844870554581038e-05, + "loss": 0.5114, + "step": 2442 + }, + { + "epoch": 0.2, + "learning_rate": 1.8447255515689185e-05, + "loss": 0.4908, + "step": 2443 + }, + { + "epoch": 0.2, + "learning_rate": 1.844580486523668e-05, + "loss": 0.4994, + "step": 2444 + }, + { + "epoch": 0.2, + "learning_rate": 1.8444353594559392e-05, + "loss": 0.5013, + "step": 2445 + }, + { + "epoch": 0.2, + "learning_rate": 1.84429017037639e-05, + "loss": 0.5016, + "step": 2446 + }, + { + "epoch": 0.2, + "learning_rate": 1.8441449192956823e-05, + "loss": 0.5037, + "step": 2447 + }, + { + "epoch": 0.2, + "learning_rate": 1.8439996062244828e-05, + "loss": 0.4919, + "step": 2448 + }, + { + "epoch": 0.2, + "learning_rate": 1.843854231173463e-05, + "loss": 0.4875, + "step": 2449 + }, + { + "epoch": 0.2, + "learning_rate": 1.8437087941532982e-05, + "loss": 0.4861, + "step": 2450 + }, + { + "epoch": 0.21, + "learning_rate": 1.8435632951746685e-05, + "loss": 0.5123, + "step": 2451 + }, + { + "epoch": 0.21, + "learning_rate": 1.8434177342482594e-05, + "loss": 0.4923, + "step": 2452 + }, + { + "epoch": 0.21, + "learning_rate": 1.8432721113847596e-05, + "loss": 0.5275, + "step": 2453 + }, + { + "epoch": 0.21, + "learning_rate": 1.8431264265948636e-05, + "loss": 0.529, + "step": 2454 + }, + { + "epoch": 0.21, + "learning_rate": 1.8429806798892694e-05, + "loss": 0.5048, + "step": 2455 + }, + { + "epoch": 0.21, + "learning_rate": 1.8428348712786803e-05, + "loss": 0.485, + "step": 2456 + }, + { + "epoch": 0.21, + "learning_rate": 1.842689000773804e-05, + "loss": 0.5057, + "step": 2457 + }, + { + "epoch": 0.21, + "learning_rate": 1.8425430683853527e-05, + "loss": 0.5013, + "step": 2458 + }, + { + "epoch": 0.21, + "learning_rate": 1.8423970741240426e-05, + "loss": 0.4978, + "step": 2459 + }, + { + "epoch": 0.21, + "learning_rate": 1.842251018000595e-05, + "loss": 0.4971, + "step": 2460 + }, + { + "epoch": 0.21, + "learning_rate": 1.8421049000257362e-05, + "loss": 0.5246, + "step": 2461 + }, + { + "epoch": 0.21, + "learning_rate": 1.841958720210196e-05, + "loss": 0.4989, + "step": 2462 + }, + { + "epoch": 0.21, + "learning_rate": 1.8418124785647092e-05, + "loss": 0.5098, + "step": 2463 + }, + { + "epoch": 0.21, + "learning_rate": 1.8416661751000156e-05, + "loss": 0.5075, + "step": 2464 + }, + { + "epoch": 0.21, + "learning_rate": 1.841519809826859e-05, + "loss": 0.4991, + "step": 2465 + }, + { + "epoch": 0.21, + "learning_rate": 1.8413733827559873e-05, + "loss": 0.4971, + "step": 2466 + }, + { + "epoch": 0.21, + "learning_rate": 1.841226893898154e-05, + "loss": 0.5031, + "step": 2467 + }, + { + "epoch": 0.21, + "learning_rate": 1.8410803432641165e-05, + "loss": 0.4909, + "step": 2468 + }, + { + "epoch": 0.21, + "learning_rate": 1.840933730864637e-05, + "loss": 0.5077, + "step": 2469 + }, + { + "epoch": 0.21, + "learning_rate": 1.840787056710482e-05, + "loss": 0.5273, + "step": 2470 + }, + { + "epoch": 0.21, + "learning_rate": 1.8406403208124227e-05, + "loss": 0.5063, + "step": 2471 + }, + { + "epoch": 0.21, + "learning_rate": 1.8404935231812348e-05, + "loss": 0.5041, + "step": 2472 + }, + { + "epoch": 0.21, + "learning_rate": 1.8403466638276983e-05, + "loss": 0.493, + "step": 2473 + }, + { + "epoch": 0.21, + "learning_rate": 1.840199742762598e-05, + "loss": 0.4928, + "step": 2474 + }, + { + "epoch": 0.21, + "learning_rate": 1.840052759996723e-05, + "loss": 0.506, + "step": 2475 + }, + { + "epoch": 0.21, + "learning_rate": 1.839905715540868e-05, + "loss": 0.503, + "step": 2476 + }, + { + "epoch": 0.21, + "learning_rate": 1.8397586094058303e-05, + "loss": 0.4865, + "step": 2477 + }, + { + "epoch": 0.21, + "learning_rate": 1.839611441602413e-05, + "loss": 0.4936, + "step": 2478 + }, + { + "epoch": 0.21, + "learning_rate": 1.8394642121414238e-05, + "loss": 0.501, + "step": 2479 + }, + { + "epoch": 0.21, + "learning_rate": 1.8393169210336747e-05, + "loss": 0.4826, + "step": 2480 + }, + { + "epoch": 0.21, + "learning_rate": 1.8391695682899814e-05, + "loss": 0.5122, + "step": 2481 + }, + { + "epoch": 0.21, + "learning_rate": 1.839022153921166e-05, + "loss": 0.5038, + "step": 2482 + }, + { + "epoch": 0.21, + "learning_rate": 1.8388746779380532e-05, + "loss": 0.4954, + "step": 2483 + }, + { + "epoch": 0.21, + "learning_rate": 1.838727140351473e-05, + "loss": 0.5098, + "step": 2484 + }, + { + "epoch": 0.21, + "learning_rate": 1.83857954117226e-05, + "loss": 0.4984, + "step": 2485 + }, + { + "epoch": 0.21, + "learning_rate": 1.8384318804112533e-05, + "loss": 0.5117, + "step": 2486 + }, + { + "epoch": 0.21, + "learning_rate": 1.838284158079297e-05, + "loss": 0.4905, + "step": 2487 + }, + { + "epoch": 0.21, + "learning_rate": 1.8381363741872386e-05, + "loss": 0.4969, + "step": 2488 + }, + { + "epoch": 0.21, + "learning_rate": 1.8379885287459315e-05, + "loss": 0.5055, + "step": 2489 + }, + { + "epoch": 0.21, + "learning_rate": 1.8378406217662314e-05, + "loss": 0.4903, + "step": 2490 + }, + { + "epoch": 0.21, + "learning_rate": 1.8376926532590012e-05, + "loss": 0.4854, + "step": 2491 + }, + { + "epoch": 0.21, + "learning_rate": 1.837544623235107e-05, + "loss": 0.5033, + "step": 2492 + }, + { + "epoch": 0.21, + "learning_rate": 1.8373965317054195e-05, + "loss": 0.5127, + "step": 2493 + }, + { + "epoch": 0.21, + "learning_rate": 1.8372483786808133e-05, + "loss": 0.488, + "step": 2494 + }, + { + "epoch": 0.21, + "learning_rate": 1.8371001641721685e-05, + "loss": 0.4882, + "step": 2495 + }, + { + "epoch": 0.21, + "learning_rate": 1.8369518881903698e-05, + "loss": 0.5022, + "step": 2496 + }, + { + "epoch": 0.21, + "learning_rate": 1.8368035507463053e-05, + "loss": 0.4967, + "step": 2497 + }, + { + "epoch": 0.21, + "learning_rate": 1.8366551518508685e-05, + "loss": 0.4857, + "step": 2498 + }, + { + "epoch": 0.21, + "learning_rate": 1.8365066915149573e-05, + "loss": 0.4862, + "step": 2499 + }, + { + "epoch": 0.21, + "learning_rate": 1.8363581697494738e-05, + "loss": 0.4842, + "step": 2500 + }, + { + "epoch": 0.21, + "learning_rate": 1.8362095865653257e-05, + "loss": 0.4985, + "step": 2501 + }, + { + "epoch": 0.21, + "learning_rate": 1.8360609419734227e-05, + "loss": 0.5008, + "step": 2502 + }, + { + "epoch": 0.21, + "learning_rate": 1.835912235984682e-05, + "loss": 0.5087, + "step": 2503 + }, + { + "epoch": 0.21, + "learning_rate": 1.8357634686100236e-05, + "loss": 0.4947, + "step": 2504 + }, + { + "epoch": 0.21, + "learning_rate": 1.835614639860372e-05, + "loss": 0.4921, + "step": 2505 + }, + { + "epoch": 0.21, + "learning_rate": 1.835465749746657e-05, + "loss": 0.4997, + "step": 2506 + }, + { + "epoch": 0.21, + "learning_rate": 1.8353167982798124e-05, + "loss": 0.5113, + "step": 2507 + }, + { + "epoch": 0.21, + "learning_rate": 1.8351677854707763e-05, + "loss": 0.4809, + "step": 2508 + }, + { + "epoch": 0.21, + "learning_rate": 1.8350187113304918e-05, + "loss": 0.5035, + "step": 2509 + }, + { + "epoch": 0.21, + "learning_rate": 1.8348695758699065e-05, + "loss": 0.5228, + "step": 2510 + }, + { + "epoch": 0.21, + "learning_rate": 1.8347203790999716e-05, + "loss": 0.5196, + "step": 2511 + }, + { + "epoch": 0.21, + "learning_rate": 1.834571121031644e-05, + "loss": 0.4999, + "step": 2512 + }, + { + "epoch": 0.21, + "learning_rate": 1.8344218016758847e-05, + "loss": 0.5013, + "step": 2513 + }, + { + "epoch": 0.21, + "learning_rate": 1.834272421043659e-05, + "loss": 0.5062, + "step": 2514 + }, + { + "epoch": 0.21, + "learning_rate": 1.8341229791459365e-05, + "loss": 0.5037, + "step": 2515 + }, + { + "epoch": 0.21, + "learning_rate": 1.833973475993692e-05, + "loss": 0.5002, + "step": 2516 + }, + { + "epoch": 0.21, + "learning_rate": 1.8338239115979038e-05, + "loss": 0.501, + "step": 2517 + }, + { + "epoch": 0.21, + "learning_rate": 1.833674285969556e-05, + "loss": 0.4984, + "step": 2518 + }, + { + "epoch": 0.21, + "learning_rate": 1.833524599119636e-05, + "loss": 0.4887, + "step": 2519 + }, + { + "epoch": 0.21, + "learning_rate": 1.8333748510591364e-05, + "loss": 0.5059, + "step": 2520 + }, + { + "epoch": 0.21, + "learning_rate": 1.833225041799054e-05, + "loss": 0.5056, + "step": 2521 + }, + { + "epoch": 0.21, + "learning_rate": 1.8330751713503902e-05, + "loss": 0.494, + "step": 2522 + }, + { + "epoch": 0.21, + "learning_rate": 1.8329252397241504e-05, + "loss": 0.497, + "step": 2523 + }, + { + "epoch": 0.21, + "learning_rate": 1.832775246931346e-05, + "loss": 0.5149, + "step": 2524 + }, + { + "epoch": 0.21, + "learning_rate": 1.832625192982991e-05, + "loss": 0.4997, + "step": 2525 + }, + { + "epoch": 0.21, + "learning_rate": 1.8324750778901047e-05, + "loss": 0.5015, + "step": 2526 + }, + { + "epoch": 0.21, + "learning_rate": 1.8323249016637118e-05, + "loss": 0.5, + "step": 2527 + }, + { + "epoch": 0.21, + "learning_rate": 1.8321746643148394e-05, + "loss": 0.5136, + "step": 2528 + }, + { + "epoch": 0.21, + "learning_rate": 1.8320243658545215e-05, + "loss": 0.5003, + "step": 2529 + }, + { + "epoch": 0.21, + "learning_rate": 1.8318740062937944e-05, + "loss": 0.482, + "step": 2530 + }, + { + "epoch": 0.21, + "learning_rate": 1.8317235856437006e-05, + "loss": 0.476, + "step": 2531 + }, + { + "epoch": 0.21, + "learning_rate": 1.831573103915286e-05, + "loss": 0.4906, + "step": 2532 + }, + { + "epoch": 0.21, + "learning_rate": 1.8314225611196013e-05, + "loss": 0.5128, + "step": 2533 + }, + { + "epoch": 0.21, + "learning_rate": 1.8312719572677018e-05, + "loss": 0.5126, + "step": 2534 + }, + { + "epoch": 0.21, + "learning_rate": 1.8311212923706473e-05, + "loss": 0.5084, + "step": 2535 + }, + { + "epoch": 0.21, + "learning_rate": 1.8309705664395024e-05, + "loss": 0.5062, + "step": 2536 + }, + { + "epoch": 0.21, + "learning_rate": 1.830819779485335e-05, + "loss": 0.4906, + "step": 2537 + }, + { + "epoch": 0.21, + "learning_rate": 1.8306689315192187e-05, + "loss": 0.5119, + "step": 2538 + }, + { + "epoch": 0.21, + "learning_rate": 1.8305180225522306e-05, + "loss": 0.4949, + "step": 2539 + }, + { + "epoch": 0.21, + "learning_rate": 1.830367052595454e-05, + "loss": 0.4931, + "step": 2540 + }, + { + "epoch": 0.21, + "learning_rate": 1.8302160216599745e-05, + "loss": 0.5127, + "step": 2541 + }, + { + "epoch": 0.21, + "learning_rate": 1.8300649297568837e-05, + "loss": 0.488, + "step": 2542 + }, + { + "epoch": 0.21, + "learning_rate": 1.8299137768972766e-05, + "loss": 0.5083, + "step": 2543 + }, + { + "epoch": 0.21, + "learning_rate": 1.829762563092254e-05, + "loss": 0.4948, + "step": 2544 + }, + { + "epoch": 0.21, + "learning_rate": 1.8296112883529197e-05, + "loss": 0.5074, + "step": 2545 + }, + { + "epoch": 0.21, + "learning_rate": 1.829459952690383e-05, + "loss": 0.5196, + "step": 2546 + }, + { + "epoch": 0.21, + "learning_rate": 1.8293085561157578e-05, + "loss": 0.4939, + "step": 2547 + }, + { + "epoch": 0.21, + "learning_rate": 1.829157098640161e-05, + "loss": 0.4937, + "step": 2548 + }, + { + "epoch": 0.21, + "learning_rate": 1.829005580274716e-05, + "loss": 0.4949, + "step": 2549 + }, + { + "epoch": 0.21, + "learning_rate": 1.828854001030549e-05, + "loss": 0.4918, + "step": 2550 + }, + { + "epoch": 0.21, + "learning_rate": 1.828702360918792e-05, + "loss": 0.5065, + "step": 2551 + }, + { + "epoch": 0.21, + "learning_rate": 1.8285506599505803e-05, + "loss": 0.4884, + "step": 2552 + }, + { + "epoch": 0.21, + "learning_rate": 1.8283988981370543e-05, + "loss": 0.5058, + "step": 2553 + }, + { + "epoch": 0.21, + "learning_rate": 1.8282470754893585e-05, + "loss": 0.5247, + "step": 2554 + }, + { + "epoch": 0.21, + "learning_rate": 1.828095192018643e-05, + "loss": 0.5005, + "step": 2555 + }, + { + "epoch": 0.21, + "learning_rate": 1.82794324773606e-05, + "loss": 0.4886, + "step": 2556 + }, + { + "epoch": 0.21, + "learning_rate": 1.8277912426527696e-05, + "loss": 0.5016, + "step": 2557 + }, + { + "epoch": 0.21, + "learning_rate": 1.8276391767799326e-05, + "loss": 0.4991, + "step": 2558 + }, + { + "epoch": 0.21, + "learning_rate": 1.8274870501287174e-05, + "loss": 0.5007, + "step": 2559 + }, + { + "epoch": 0.21, + "learning_rate": 1.8273348627102948e-05, + "loss": 0.4941, + "step": 2560 + }, + { + "epoch": 0.21, + "learning_rate": 1.827182614535841e-05, + "loss": 0.4995, + "step": 2561 + }, + { + "epoch": 0.21, + "learning_rate": 1.8270303056165364e-05, + "loss": 0.4974, + "step": 2562 + }, + { + "epoch": 0.21, + "learning_rate": 1.826877935963566e-05, + "loss": 0.5034, + "step": 2563 + }, + { + "epoch": 0.21, + "learning_rate": 1.8267255055881197e-05, + "loss": 0.4848, + "step": 2564 + }, + { + "epoch": 0.21, + "learning_rate": 1.8265730145013903e-05, + "loss": 0.5114, + "step": 2565 + }, + { + "epoch": 0.21, + "learning_rate": 1.826420462714577e-05, + "loss": 0.5084, + "step": 2566 + }, + { + "epoch": 0.21, + "learning_rate": 1.8262678502388824e-05, + "loss": 0.5176, + "step": 2567 + }, + { + "epoch": 0.21, + "learning_rate": 1.8261151770855134e-05, + "loss": 0.4974, + "step": 2568 + }, + { + "epoch": 0.21, + "learning_rate": 1.8259624432656816e-05, + "loss": 0.5196, + "step": 2569 + }, + { + "epoch": 0.22, + "learning_rate": 1.825809648790604e-05, + "loss": 0.4914, + "step": 2570 + }, + { + "epoch": 0.22, + "learning_rate": 1.8256567936715e-05, + "loss": 0.4887, + "step": 2571 + }, + { + "epoch": 0.22, + "learning_rate": 1.8255038779195957e-05, + "loss": 0.513, + "step": 2572 + }, + { + "epoch": 0.22, + "learning_rate": 1.82535090154612e-05, + "loss": 0.4801, + "step": 2573 + }, + { + "epoch": 0.22, + "learning_rate": 1.825197864562307e-05, + "loss": 0.4912, + "step": 2574 + }, + { + "epoch": 0.22, + "learning_rate": 1.825044766979395e-05, + "loss": 0.5092, + "step": 2575 + }, + { + "epoch": 0.22, + "learning_rate": 1.8248916088086268e-05, + "loss": 0.5197, + "step": 2576 + }, + { + "epoch": 0.22, + "learning_rate": 1.82473839006125e-05, + "loss": 0.4776, + "step": 2577 + }, + { + "epoch": 0.22, + "learning_rate": 1.824585110748516e-05, + "loss": 0.4789, + "step": 2578 + }, + { + "epoch": 0.22, + "learning_rate": 1.8244317708816815e-05, + "loss": 0.5079, + "step": 2579 + }, + { + "epoch": 0.22, + "learning_rate": 1.8242783704720066e-05, + "loss": 0.5039, + "step": 2580 + }, + { + "epoch": 0.22, + "learning_rate": 1.8241249095307566e-05, + "loss": 0.4892, + "step": 2581 + }, + { + "epoch": 0.22, + "learning_rate": 1.823971388069201e-05, + "loss": 0.4991, + "step": 2582 + }, + { + "epoch": 0.22, + "learning_rate": 1.823817806098614e-05, + "loss": 0.4969, + "step": 2583 + }, + { + "epoch": 0.22, + "learning_rate": 1.8236641636302737e-05, + "loss": 0.4987, + "step": 2584 + }, + { + "epoch": 0.22, + "learning_rate": 1.823510460675463e-05, + "loss": 0.49, + "step": 2585 + }, + { + "epoch": 0.22, + "learning_rate": 1.8233566972454696e-05, + "loss": 0.4967, + "step": 2586 + }, + { + "epoch": 0.22, + "learning_rate": 1.823202873351585e-05, + "loss": 0.4846, + "step": 2587 + }, + { + "epoch": 0.22, + "learning_rate": 1.8230489890051048e-05, + "loss": 0.5066, + "step": 2588 + }, + { + "epoch": 0.22, + "learning_rate": 1.8228950442173304e-05, + "loss": 0.513, + "step": 2589 + }, + { + "epoch": 0.22, + "learning_rate": 1.8227410389995668e-05, + "loss": 0.4966, + "step": 2590 + }, + { + "epoch": 0.22, + "learning_rate": 1.8225869733631234e-05, + "loss": 0.5062, + "step": 2591 + }, + { + "epoch": 0.22, + "learning_rate": 1.8224328473193137e-05, + "loss": 0.488, + "step": 2592 + }, + { + "epoch": 0.22, + "learning_rate": 1.822278660879457e-05, + "loss": 0.4971, + "step": 2593 + }, + { + "epoch": 0.22, + "learning_rate": 1.822124414054875e-05, + "loss": 0.5029, + "step": 2594 + }, + { + "epoch": 0.22, + "learning_rate": 1.8219701068568957e-05, + "loss": 0.4926, + "step": 2595 + }, + { + "epoch": 0.22, + "learning_rate": 1.8218157392968505e-05, + "loss": 0.4797, + "step": 2596 + }, + { + "epoch": 0.22, + "learning_rate": 1.821661311386076e-05, + "loss": 0.5108, + "step": 2597 + }, + { + "epoch": 0.22, + "learning_rate": 1.8215068231359118e-05, + "loss": 0.5117, + "step": 2598 + }, + { + "epoch": 0.22, + "learning_rate": 1.821352274557704e-05, + "loss": 0.4963, + "step": 2599 + }, + { + "epoch": 0.22, + "learning_rate": 1.8211976656628007e-05, + "loss": 0.5159, + "step": 2600 + }, + { + "epoch": 0.22, + "learning_rate": 1.821042996462557e-05, + "loss": 0.4822, + "step": 2601 + }, + { + "epoch": 0.22, + "learning_rate": 1.8208882669683305e-05, + "loss": 0.4933, + "step": 2602 + }, + { + "epoch": 0.22, + "learning_rate": 1.820733477191484e-05, + "loss": 0.4897, + "step": 2603 + }, + { + "epoch": 0.22, + "learning_rate": 1.8205786271433845e-05, + "loss": 0.4959, + "step": 2604 + }, + { + "epoch": 0.22, + "learning_rate": 1.8204237168354038e-05, + "loss": 0.5009, + "step": 2605 + }, + { + "epoch": 0.22, + "learning_rate": 1.8202687462789175e-05, + "loss": 0.4853, + "step": 2606 + }, + { + "epoch": 0.22, + "learning_rate": 1.8201137154853065e-05, + "loss": 0.523, + "step": 2607 + }, + { + "epoch": 0.22, + "learning_rate": 1.8199586244659554e-05, + "loss": 0.512, + "step": 2608 + }, + { + "epoch": 0.22, + "learning_rate": 1.8198034732322532e-05, + "loss": 0.4876, + "step": 2609 + }, + { + "epoch": 0.22, + "learning_rate": 1.8196482617955938e-05, + "loss": 0.5184, + "step": 2610 + }, + { + "epoch": 0.22, + "learning_rate": 1.8194929901673752e-05, + "loss": 0.536, + "step": 2611 + }, + { + "epoch": 0.22, + "learning_rate": 1.819337658359e-05, + "loss": 0.4823, + "step": 2612 + }, + { + "epoch": 0.22, + "learning_rate": 1.819182266381875e-05, + "loss": 0.504, + "step": 2613 + }, + { + "epoch": 0.22, + "learning_rate": 1.8190268142474113e-05, + "loss": 0.5123, + "step": 2614 + }, + { + "epoch": 0.22, + "learning_rate": 1.8188713019670253e-05, + "loss": 0.4874, + "step": 2615 + }, + { + "epoch": 0.22, + "learning_rate": 1.8187157295521366e-05, + "loss": 0.4956, + "step": 2616 + }, + { + "epoch": 0.22, + "learning_rate": 1.8185600970141703e-05, + "loss": 0.5148, + "step": 2617 + }, + { + "epoch": 0.22, + "learning_rate": 1.818404404364555e-05, + "loss": 0.4907, + "step": 2618 + }, + { + "epoch": 0.22, + "learning_rate": 1.818248651614724e-05, + "loss": 0.4943, + "step": 2619 + }, + { + "epoch": 0.22, + "learning_rate": 1.8180928387761157e-05, + "loss": 0.5055, + "step": 2620 + }, + { + "epoch": 0.22, + "learning_rate": 1.817936965860172e-05, + "loss": 0.4992, + "step": 2621 + }, + { + "epoch": 0.22, + "learning_rate": 1.8177810328783395e-05, + "loss": 0.5033, + "step": 2622 + }, + { + "epoch": 0.22, + "learning_rate": 1.8176250398420694e-05, + "loss": 0.4799, + "step": 2623 + }, + { + "epoch": 0.22, + "learning_rate": 1.817468986762817e-05, + "loss": 0.4893, + "step": 2624 + }, + { + "epoch": 0.22, + "learning_rate": 1.8173128736520427e-05, + "loss": 0.5092, + "step": 2625 + }, + { + "epoch": 0.22, + "learning_rate": 1.81715670052121e-05, + "loss": 0.4862, + "step": 2626 + }, + { + "epoch": 0.22, + "learning_rate": 1.8170004673817882e-05, + "loss": 0.5004, + "step": 2627 + }, + { + "epoch": 0.22, + "learning_rate": 1.8168441742452502e-05, + "loss": 0.4948, + "step": 2628 + }, + { + "epoch": 0.22, + "learning_rate": 1.8166878211230736e-05, + "loss": 0.5071, + "step": 2629 + }, + { + "epoch": 0.22, + "learning_rate": 1.8165314080267406e-05, + "loss": 0.5127, + "step": 2630 + }, + { + "epoch": 0.22, + "learning_rate": 1.8163749349677363e-05, + "loss": 0.5117, + "step": 2631 + }, + { + "epoch": 0.22, + "learning_rate": 1.8162184019575534e-05, + "loss": 0.5178, + "step": 2632 + }, + { + "epoch": 0.22, + "learning_rate": 1.816061809007685e-05, + "loss": 0.5083, + "step": 2633 + }, + { + "epoch": 0.22, + "learning_rate": 1.8159051561296323e-05, + "loss": 0.5078, + "step": 2634 + }, + { + "epoch": 0.22, + "learning_rate": 1.815748443334898e-05, + "loss": 0.5072, + "step": 2635 + }, + { + "epoch": 0.22, + "learning_rate": 1.8155916706349913e-05, + "loss": 0.4987, + "step": 2636 + }, + { + "epoch": 0.22, + "learning_rate": 1.8154348380414245e-05, + "loss": 0.5096, + "step": 2637 + }, + { + "epoch": 0.22, + "learning_rate": 1.815277945565715e-05, + "loss": 0.5288, + "step": 2638 + }, + { + "epoch": 0.22, + "learning_rate": 1.8151209932193844e-05, + "loss": 0.4849, + "step": 2639 + }, + { + "epoch": 0.22, + "learning_rate": 1.814963981013958e-05, + "loss": 0.4918, + "step": 2640 + }, + { + "epoch": 0.22, + "learning_rate": 1.8148069089609667e-05, + "loss": 0.4967, + "step": 2641 + }, + { + "epoch": 0.22, + "learning_rate": 1.8146497770719448e-05, + "loss": 0.5129, + "step": 2642 + }, + { + "epoch": 0.22, + "learning_rate": 1.8144925853584315e-05, + "loss": 0.4814, + "step": 2643 + }, + { + "epoch": 0.22, + "learning_rate": 1.8143353338319712e-05, + "loss": 0.5177, + "step": 2644 + }, + { + "epoch": 0.22, + "learning_rate": 1.8141780225041104e-05, + "loss": 0.5168, + "step": 2645 + }, + { + "epoch": 0.22, + "learning_rate": 1.8140206513864026e-05, + "loss": 0.5167, + "step": 2646 + }, + { + "epoch": 0.22, + "learning_rate": 1.8138632204904033e-05, + "loss": 0.4849, + "step": 2647 + }, + { + "epoch": 0.22, + "learning_rate": 1.8137057298276745e-05, + "loss": 0.4971, + "step": 2648 + }, + { + "epoch": 0.22, + "learning_rate": 1.8135481794097814e-05, + "loss": 0.5189, + "step": 2649 + }, + { + "epoch": 0.22, + "learning_rate": 1.813390569248294e-05, + "loss": 0.4916, + "step": 2650 + }, + { + "epoch": 0.22, + "learning_rate": 1.813232899354786e-05, + "loss": 0.5015, + "step": 2651 + }, + { + "epoch": 0.22, + "learning_rate": 1.8130751697408364e-05, + "loss": 0.499, + "step": 2652 + }, + { + "epoch": 0.22, + "learning_rate": 1.8129173804180285e-05, + "loss": 0.4776, + "step": 2653 + }, + { + "epoch": 0.22, + "learning_rate": 1.812759531397949e-05, + "loss": 0.4923, + "step": 2654 + }, + { + "epoch": 0.22, + "learning_rate": 1.8126016226921898e-05, + "loss": 0.5178, + "step": 2655 + }, + { + "epoch": 0.22, + "learning_rate": 1.812443654312348e-05, + "loss": 0.4954, + "step": 2656 + }, + { + "epoch": 0.22, + "learning_rate": 1.8122856262700227e-05, + "loss": 0.5286, + "step": 2657 + }, + { + "epoch": 0.22, + "learning_rate": 1.81212753857682e-05, + "loss": 0.5092, + "step": 2658 + }, + { + "epoch": 0.22, + "learning_rate": 1.8119693912443487e-05, + "loss": 0.5141, + "step": 2659 + }, + { + "epoch": 0.22, + "learning_rate": 1.8118111842842227e-05, + "loss": 0.5079, + "step": 2660 + }, + { + "epoch": 0.22, + "learning_rate": 1.8116529177080594e-05, + "loss": 0.4833, + "step": 2661 + }, + { + "epoch": 0.22, + "learning_rate": 1.8114945915274826e-05, + "loss": 0.5262, + "step": 2662 + }, + { + "epoch": 0.22, + "learning_rate": 1.8113362057541175e-05, + "loss": 0.5065, + "step": 2663 + }, + { + "epoch": 0.22, + "learning_rate": 1.811177760399596e-05, + "loss": 0.492, + "step": 2664 + }, + { + "epoch": 0.22, + "learning_rate": 1.811019255475554e-05, + "loss": 0.4939, + "step": 2665 + }, + { + "epoch": 0.22, + "learning_rate": 1.8108606909936312e-05, + "loss": 0.4864, + "step": 2666 + }, + { + "epoch": 0.22, + "learning_rate": 1.810702066965472e-05, + "loss": 0.4914, + "step": 2667 + }, + { + "epoch": 0.22, + "learning_rate": 1.810543383402725e-05, + "loss": 0.5023, + "step": 2668 + }, + { + "epoch": 0.22, + "learning_rate": 1.8103846403170427e-05, + "loss": 0.4967, + "step": 2669 + }, + { + "epoch": 0.22, + "learning_rate": 1.8102258377200837e-05, + "loss": 0.4998, + "step": 2670 + }, + { + "epoch": 0.22, + "learning_rate": 1.8100669756235087e-05, + "loss": 0.5019, + "step": 2671 + }, + { + "epoch": 0.22, + "learning_rate": 1.8099080540389845e-05, + "loss": 0.5198, + "step": 2672 + }, + { + "epoch": 0.22, + "learning_rate": 1.8097490729781815e-05, + "loss": 0.5041, + "step": 2673 + }, + { + "epoch": 0.22, + "learning_rate": 1.8095900324527745e-05, + "loss": 0.4983, + "step": 2674 + }, + { + "epoch": 0.22, + "learning_rate": 1.8094309324744428e-05, + "loss": 0.4895, + "step": 2675 + }, + { + "epoch": 0.22, + "learning_rate": 1.8092717730548702e-05, + "loss": 0.5035, + "step": 2676 + }, + { + "epoch": 0.22, + "learning_rate": 1.8091125542057442e-05, + "loss": 0.51, + "step": 2677 + }, + { + "epoch": 0.22, + "learning_rate": 1.8089532759387586e-05, + "loss": 0.4928, + "step": 2678 + }, + { + "epoch": 0.22, + "learning_rate": 1.8087939382656082e-05, + "loss": 0.4932, + "step": 2679 + }, + { + "epoch": 0.22, + "learning_rate": 1.8086345411979952e-05, + "loss": 0.5225, + "step": 2680 + }, + { + "epoch": 0.22, + "learning_rate": 1.808475084747625e-05, + "loss": 0.4933, + "step": 2681 + }, + { + "epoch": 0.22, + "learning_rate": 1.808315568926207e-05, + "loss": 0.5014, + "step": 2682 + }, + { + "epoch": 0.22, + "learning_rate": 1.808155993745456e-05, + "loss": 0.4988, + "step": 2683 + }, + { + "epoch": 0.22, + "learning_rate": 1.8079963592170903e-05, + "loss": 0.4932, + "step": 2684 + }, + { + "epoch": 0.22, + "learning_rate": 1.807836665352832e-05, + "loss": 0.4945, + "step": 2685 + }, + { + "epoch": 0.22, + "learning_rate": 1.8076769121644097e-05, + "loss": 0.4966, + "step": 2686 + }, + { + "epoch": 0.22, + "learning_rate": 1.8075170996635538e-05, + "loss": 0.516, + "step": 2687 + }, + { + "epoch": 0.22, + "learning_rate": 1.8073572278620015e-05, + "loss": 0.5308, + "step": 2688 + }, + { + "epoch": 0.22, + "learning_rate": 1.8071972967714918e-05, + "loss": 0.4975, + "step": 2689 + }, + { + "epoch": 0.23, + "learning_rate": 1.8070373064037702e-05, + "loss": 0.5108, + "step": 2690 + }, + { + "epoch": 0.23, + "learning_rate": 1.8068772567705858e-05, + "loss": 0.4995, + "step": 2691 + }, + { + "epoch": 0.23, + "learning_rate": 1.8067171478836916e-05, + "loss": 0.4989, + "step": 2692 + }, + { + "epoch": 0.23, + "learning_rate": 1.8065569797548453e-05, + "loss": 0.4833, + "step": 2693 + }, + { + "epoch": 0.23, + "learning_rate": 1.8063967523958093e-05, + "loss": 0.4976, + "step": 2694 + }, + { + "epoch": 0.23, + "learning_rate": 1.80623646581835e-05, + "loss": 0.5101, + "step": 2695 + }, + { + "epoch": 0.23, + "learning_rate": 1.8060761200342376e-05, + "loss": 0.5045, + "step": 2696 + }, + { + "epoch": 0.23, + "learning_rate": 1.8059157150552477e-05, + "loss": 0.4985, + "step": 2697 + }, + { + "epoch": 0.23, + "learning_rate": 1.80575525089316e-05, + "loss": 0.4916, + "step": 2698 + }, + { + "epoch": 0.23, + "learning_rate": 1.805594727559758e-05, + "loss": 0.4951, + "step": 2699 + }, + { + "epoch": 0.23, + "learning_rate": 1.80543414506683e-05, + "loss": 0.5025, + "step": 2700 + }, + { + "epoch": 0.23, + "learning_rate": 1.8052735034261683e-05, + "loss": 0.5244, + "step": 2701 + }, + { + "epoch": 0.23, + "learning_rate": 1.8051128026495703e-05, + "loss": 0.4934, + "step": 2702 + }, + { + "epoch": 0.23, + "learning_rate": 1.8049520427488362e-05, + "loss": 0.5106, + "step": 2703 + }, + { + "epoch": 0.23, + "learning_rate": 1.8047912237357724e-05, + "loss": 0.5032, + "step": 2704 + }, + { + "epoch": 0.23, + "learning_rate": 1.8046303456221885e-05, + "loss": 0.4925, + "step": 2705 + }, + { + "epoch": 0.23, + "learning_rate": 1.8044694084198985e-05, + "loss": 0.4961, + "step": 2706 + }, + { + "epoch": 0.23, + "learning_rate": 1.8043084121407214e-05, + "loss": 0.4993, + "step": 2707 + }, + { + "epoch": 0.23, + "learning_rate": 1.80414735679648e-05, + "loss": 0.5052, + "step": 2708 + }, + { + "epoch": 0.23, + "learning_rate": 1.8039862423990012e-05, + "loss": 0.5097, + "step": 2709 + }, + { + "epoch": 0.23, + "learning_rate": 1.803825068960117e-05, + "loss": 0.5066, + "step": 2710 + }, + { + "epoch": 0.23, + "learning_rate": 1.803663836491663e-05, + "loss": 0.5189, + "step": 2711 + }, + { + "epoch": 0.23, + "learning_rate": 1.8035025450054796e-05, + "loss": 0.4867, + "step": 2712 + }, + { + "epoch": 0.23, + "learning_rate": 1.803341194513411e-05, + "loss": 0.4937, + "step": 2713 + }, + { + "epoch": 0.23, + "learning_rate": 1.803179785027307e-05, + "loss": 0.512, + "step": 2714 + }, + { + "epoch": 0.23, + "learning_rate": 1.8030183165590197e-05, + "loss": 0.4938, + "step": 2715 + }, + { + "epoch": 0.23, + "learning_rate": 1.8028567891204074e-05, + "loss": 0.4957, + "step": 2716 + }, + { + "epoch": 0.23, + "learning_rate": 1.802695202723332e-05, + "loss": 0.4973, + "step": 2717 + }, + { + "epoch": 0.23, + "learning_rate": 1.8025335573796596e-05, + "loss": 0.5068, + "step": 2718 + }, + { + "epoch": 0.23, + "learning_rate": 1.8023718531012602e-05, + "loss": 0.4977, + "step": 2719 + }, + { + "epoch": 0.23, + "learning_rate": 1.80221008990001e-05, + "loss": 0.4864, + "step": 2720 + }, + { + "epoch": 0.23, + "learning_rate": 1.8020482677877868e-05, + "loss": 0.5293, + "step": 2721 + }, + { + "epoch": 0.23, + "learning_rate": 1.801886386776475e-05, + "loss": 0.4882, + "step": 2722 + }, + { + "epoch": 0.23, + "learning_rate": 1.8017244468779625e-05, + "loss": 0.4978, + "step": 2723 + }, + { + "epoch": 0.23, + "learning_rate": 1.8015624481041408e-05, + "loss": 0.4887, + "step": 2724 + }, + { + "epoch": 0.23, + "learning_rate": 1.8014003904669073e-05, + "loss": 0.4994, + "step": 2725 + }, + { + "epoch": 0.23, + "learning_rate": 1.8012382739781623e-05, + "loss": 0.498, + "step": 2726 + }, + { + "epoch": 0.23, + "learning_rate": 1.801076098649811e-05, + "loss": 0.5084, + "step": 2727 + }, + { + "epoch": 0.23, + "learning_rate": 1.8009138644937626e-05, + "loss": 0.5097, + "step": 2728 + }, + { + "epoch": 0.23, + "learning_rate": 1.8007515715219317e-05, + "loss": 0.5071, + "step": 2729 + }, + { + "epoch": 0.23, + "learning_rate": 1.8005892197462355e-05, + "loss": 0.5053, + "step": 2730 + }, + { + "epoch": 0.23, + "learning_rate": 1.8004268091785973e-05, + "loss": 0.4957, + "step": 2731 + }, + { + "epoch": 0.23, + "learning_rate": 1.8002643398309434e-05, + "loss": 0.4895, + "step": 2732 + }, + { + "epoch": 0.23, + "learning_rate": 1.800101811715205e-05, + "loss": 0.4991, + "step": 2733 + }, + { + "epoch": 0.23, + "learning_rate": 1.799939224843317e-05, + "loss": 0.4882, + "step": 2734 + }, + { + "epoch": 0.23, + "learning_rate": 1.7997765792272203e-05, + "loss": 0.4993, + "step": 2735 + }, + { + "epoch": 0.23, + "learning_rate": 1.7996138748788573e-05, + "loss": 0.4852, + "step": 2736 + }, + { + "epoch": 0.23, + "learning_rate": 1.799451111810178e-05, + "loss": 0.5067, + "step": 2737 + }, + { + "epoch": 0.23, + "learning_rate": 1.7992882900331336e-05, + "loss": 0.5039, + "step": 2738 + }, + { + "epoch": 0.23, + "learning_rate": 1.799125409559682e-05, + "loss": 0.4889, + "step": 2739 + }, + { + "epoch": 0.23, + "learning_rate": 1.7989624704017838e-05, + "loss": 0.4925, + "step": 2740 + }, + { + "epoch": 0.23, + "learning_rate": 1.798799472571405e-05, + "loss": 0.4827, + "step": 2741 + }, + { + "epoch": 0.23, + "learning_rate": 1.7986364160805156e-05, + "loss": 0.4894, + "step": 2742 + }, + { + "epoch": 0.23, + "learning_rate": 1.7984733009410896e-05, + "loss": 0.5013, + "step": 2743 + }, + { + "epoch": 0.23, + "learning_rate": 1.7983101271651052e-05, + "loss": 0.4842, + "step": 2744 + }, + { + "epoch": 0.23, + "learning_rate": 1.798146894764546e-05, + "loss": 0.5058, + "step": 2745 + }, + { + "epoch": 0.23, + "learning_rate": 1.7979836037513977e-05, + "loss": 0.5045, + "step": 2746 + }, + { + "epoch": 0.23, + "learning_rate": 1.7978202541376533e-05, + "loss": 0.4997, + "step": 2747 + }, + { + "epoch": 0.23, + "learning_rate": 1.7976568459353078e-05, + "loss": 0.5177, + "step": 2748 + }, + { + "epoch": 0.23, + "learning_rate": 1.797493379156361e-05, + "loss": 0.4966, + "step": 2749 + }, + { + "epoch": 0.23, + "learning_rate": 1.7973298538128174e-05, + "loss": 0.4932, + "step": 2750 + }, + { + "epoch": 0.23, + "learning_rate": 1.797166269916686e-05, + "loss": 0.4896, + "step": 2751 + }, + { + "epoch": 0.23, + "learning_rate": 1.797002627479979e-05, + "loss": 0.4984, + "step": 2752 + }, + { + "epoch": 0.23, + "learning_rate": 1.7968389265147142e-05, + "loss": 0.5047, + "step": 2753 + }, + { + "epoch": 0.23, + "learning_rate": 1.796675167032913e-05, + "loss": 0.4992, + "step": 2754 + }, + { + "epoch": 0.23, + "learning_rate": 1.7965113490466013e-05, + "loss": 0.4927, + "step": 2755 + }, + { + "epoch": 0.23, + "learning_rate": 1.796347472567809e-05, + "loss": 0.4969, + "step": 2756 + }, + { + "epoch": 0.23, + "learning_rate": 1.7961835376085702e-05, + "loss": 0.497, + "step": 2757 + }, + { + "epoch": 0.23, + "learning_rate": 1.7960195441809242e-05, + "loss": 0.4832, + "step": 2758 + }, + { + "epoch": 0.23, + "learning_rate": 1.795855492296914e-05, + "loss": 0.5121, + "step": 2759 + }, + { + "epoch": 0.23, + "learning_rate": 1.7956913819685865e-05, + "loss": 0.5147, + "step": 2760 + }, + { + "epoch": 0.23, + "learning_rate": 1.7955272132079935e-05, + "loss": 0.4937, + "step": 2761 + }, + { + "epoch": 0.23, + "learning_rate": 1.7953629860271906e-05, + "loss": 0.5006, + "step": 2762 + }, + { + "epoch": 0.23, + "learning_rate": 1.7951987004382384e-05, + "loss": 0.4956, + "step": 2763 + }, + { + "epoch": 0.23, + "learning_rate": 1.795034356453201e-05, + "loss": 0.5006, + "step": 2764 + }, + { + "epoch": 0.23, + "learning_rate": 1.794869954084147e-05, + "loss": 0.51, + "step": 2765 + }, + { + "epoch": 0.23, + "learning_rate": 1.79470549334315e-05, + "loss": 0.4736, + "step": 2766 + }, + { + "epoch": 0.23, + "learning_rate": 1.794540974242287e-05, + "loss": 0.5055, + "step": 2767 + }, + { + "epoch": 0.23, + "learning_rate": 1.7943763967936395e-05, + "loss": 0.5209, + "step": 2768 + }, + { + "epoch": 0.23, + "learning_rate": 1.7942117610092938e-05, + "loss": 0.493, + "step": 2769 + }, + { + "epoch": 0.23, + "learning_rate": 1.794047066901339e-05, + "loss": 0.4909, + "step": 2770 + }, + { + "epoch": 0.23, + "learning_rate": 1.7938823144818712e-05, + "loss": 0.5175, + "step": 2771 + }, + { + "epoch": 0.23, + "learning_rate": 1.7937175037629876e-05, + "loss": 0.4814, + "step": 2772 + }, + { + "epoch": 0.23, + "learning_rate": 1.793552634756792e-05, + "loss": 0.5145, + "step": 2773 + }, + { + "epoch": 0.23, + "learning_rate": 1.793387707475392e-05, + "loss": 0.5087, + "step": 2774 + }, + { + "epoch": 0.23, + "learning_rate": 1.793222721930898e-05, + "loss": 0.504, + "step": 2775 + }, + { + "epoch": 0.23, + "learning_rate": 1.793057678135427e-05, + "loss": 0.4912, + "step": 2776 + }, + { + "epoch": 0.23, + "learning_rate": 1.7928925761010984e-05, + "loss": 0.5088, + "step": 2777 + }, + { + "epoch": 0.23, + "learning_rate": 1.792727415840037e-05, + "loss": 0.484, + "step": 2778 + }, + { + "epoch": 0.23, + "learning_rate": 1.7925621973643713e-05, + "loss": 0.5029, + "step": 2779 + }, + { + "epoch": 0.23, + "learning_rate": 1.7923969206862347e-05, + "loss": 0.5131, + "step": 2780 + }, + { + "epoch": 0.23, + "learning_rate": 1.7922315858177638e-05, + "loss": 0.4955, + "step": 2781 + }, + { + "epoch": 0.23, + "learning_rate": 1.7920661927711002e-05, + "loss": 0.5075, + "step": 2782 + }, + { + "epoch": 0.23, + "learning_rate": 1.7919007415583903e-05, + "loss": 0.469, + "step": 2783 + }, + { + "epoch": 0.23, + "learning_rate": 1.7917352321917834e-05, + "loss": 0.5087, + "step": 2784 + }, + { + "epoch": 0.23, + "learning_rate": 1.7915696646834343e-05, + "loss": 0.4729, + "step": 2785 + }, + { + "epoch": 0.23, + "learning_rate": 1.7914040390455014e-05, + "loss": 0.4914, + "step": 2786 + }, + { + "epoch": 0.23, + "learning_rate": 1.7912383552901473e-05, + "loss": 0.5058, + "step": 2787 + }, + { + "epoch": 0.23, + "learning_rate": 1.7910726134295396e-05, + "loss": 0.4916, + "step": 2788 + }, + { + "epoch": 0.23, + "learning_rate": 1.7909068134758497e-05, + "loss": 0.5064, + "step": 2789 + }, + { + "epoch": 0.23, + "learning_rate": 1.7907409554412526e-05, + "loss": 0.501, + "step": 2790 + }, + { + "epoch": 0.23, + "learning_rate": 1.790575039337929e-05, + "loss": 0.5054, + "step": 2791 + }, + { + "epoch": 0.23, + "learning_rate": 1.7904090651780624e-05, + "loss": 0.4934, + "step": 2792 + }, + { + "epoch": 0.23, + "learning_rate": 1.790243032973842e-05, + "loss": 0.5042, + "step": 2793 + }, + { + "epoch": 0.23, + "learning_rate": 1.79007694273746e-05, + "loss": 0.4681, + "step": 2794 + }, + { + "epoch": 0.23, + "learning_rate": 1.7899107944811133e-05, + "loss": 0.5011, + "step": 2795 + }, + { + "epoch": 0.23, + "learning_rate": 1.7897445882170038e-05, + "loss": 0.5067, + "step": 2796 + }, + { + "epoch": 0.23, + "learning_rate": 1.789578323957336e-05, + "loss": 0.5044, + "step": 2797 + }, + { + "epoch": 0.23, + "learning_rate": 1.7894120017143205e-05, + "loss": 0.5046, + "step": 2798 + }, + { + "epoch": 0.23, + "learning_rate": 1.789245621500171e-05, + "loss": 0.4989, + "step": 2799 + }, + { + "epoch": 0.23, + "learning_rate": 1.7890791833271058e-05, + "loss": 0.4721, + "step": 2800 + }, + { + "epoch": 0.23, + "learning_rate": 1.7889126872073473e-05, + "loss": 0.5095, + "step": 2801 + }, + { + "epoch": 0.23, + "learning_rate": 1.7887461331531224e-05, + "loss": 0.496, + "step": 2802 + }, + { + "epoch": 0.23, + "learning_rate": 1.788579521176662e-05, + "loss": 0.4881, + "step": 2803 + }, + { + "epoch": 0.23, + "learning_rate": 1.7884128512902018e-05, + "loss": 0.5057, + "step": 2804 + }, + { + "epoch": 0.23, + "learning_rate": 1.788246123505981e-05, + "loss": 0.5034, + "step": 2805 + }, + { + "epoch": 0.23, + "learning_rate": 1.7880793378362432e-05, + "loss": 0.4997, + "step": 2806 + }, + { + "epoch": 0.23, + "learning_rate": 1.787912494293237e-05, + "loss": 0.4959, + "step": 2807 + }, + { + "epoch": 0.23, + "learning_rate": 1.787745592889214e-05, + "loss": 0.4812, + "step": 2808 + }, + { + "epoch": 0.24, + "learning_rate": 1.7875786336364316e-05, + "loss": 0.5047, + "step": 2809 + }, + { + "epoch": 0.24, + "learning_rate": 1.78741161654715e-05, + "loss": 0.4924, + "step": 2810 + }, + { + "epoch": 0.24, + "learning_rate": 1.7872445416336343e-05, + "loss": 0.5078, + "step": 2811 + }, + { + "epoch": 0.24, + "learning_rate": 1.7870774089081537e-05, + "loss": 0.4883, + "step": 2812 + }, + { + "epoch": 0.24, + "learning_rate": 1.786910218382982e-05, + "loss": 0.5038, + "step": 2813 + }, + { + "epoch": 0.24, + "learning_rate": 1.7867429700703967e-05, + "loss": 0.5137, + "step": 2814 + }, + { + "epoch": 0.24, + "learning_rate": 1.7865756639826805e-05, + "loss": 0.5147, + "step": 2815 + }, + { + "epoch": 0.24, + "learning_rate": 1.786408300132119e-05, + "loss": 0.4802, + "step": 2816 + }, + { + "epoch": 0.24, + "learning_rate": 1.7862408785310025e-05, + "loss": 0.5072, + "step": 2817 + }, + { + "epoch": 0.24, + "learning_rate": 1.7860733991916263e-05, + "loss": 0.5101, + "step": 2818 + }, + { + "epoch": 0.24, + "learning_rate": 1.7859058621262893e-05, + "loss": 0.4928, + "step": 2819 + }, + { + "epoch": 0.24, + "learning_rate": 1.7857382673472946e-05, + "loss": 0.499, + "step": 2820 + }, + { + "epoch": 0.24, + "learning_rate": 1.7855706148669494e-05, + "loss": 0.5024, + "step": 2821 + }, + { + "epoch": 0.24, + "learning_rate": 1.785402904697566e-05, + "loss": 0.4932, + "step": 2822 + }, + { + "epoch": 0.24, + "learning_rate": 1.7852351368514597e-05, + "loss": 0.5075, + "step": 2823 + }, + { + "epoch": 0.24, + "learning_rate": 1.7850673113409514e-05, + "loss": 0.499, + "step": 2824 + }, + { + "epoch": 0.24, + "learning_rate": 1.7848994281783648e-05, + "loss": 0.5007, + "step": 2825 + }, + { + "epoch": 0.24, + "learning_rate": 1.784731487376029e-05, + "loss": 0.5201, + "step": 2826 + }, + { + "epoch": 0.24, + "learning_rate": 1.7845634889462763e-05, + "loss": 0.4836, + "step": 2827 + }, + { + "epoch": 0.24, + "learning_rate": 1.784395432901445e-05, + "loss": 0.5021, + "step": 2828 + }, + { + "epoch": 0.24, + "learning_rate": 1.784227319253875e-05, + "loss": 0.5008, + "step": 2829 + }, + { + "epoch": 0.24, + "learning_rate": 1.7840591480159127e-05, + "loss": 0.5007, + "step": 2830 + }, + { + "epoch": 0.24, + "learning_rate": 1.7838909191999077e-05, + "loss": 0.4969, + "step": 2831 + }, + { + "epoch": 0.24, + "learning_rate": 1.783722632818214e-05, + "loss": 0.4959, + "step": 2832 + }, + { + "epoch": 0.24, + "learning_rate": 1.78355428888319e-05, + "loss": 0.5112, + "step": 2833 + }, + { + "epoch": 0.24, + "learning_rate": 1.783385887407198e-05, + "loss": 0.5032, + "step": 2834 + }, + { + "epoch": 0.24, + "learning_rate": 1.783217428402605e-05, + "loss": 0.5036, + "step": 2835 + }, + { + "epoch": 0.24, + "learning_rate": 1.7830489118817812e-05, + "loss": 0.5104, + "step": 2836 + }, + { + "epoch": 0.24, + "learning_rate": 1.7828803378571028e-05, + "loss": 0.4815, + "step": 2837 + }, + { + "epoch": 0.24, + "learning_rate": 1.7827117063409483e-05, + "loss": 0.4726, + "step": 2838 + }, + { + "epoch": 0.24, + "learning_rate": 1.782543017345702e-05, + "loss": 0.4989, + "step": 2839 + }, + { + "epoch": 0.24, + "learning_rate": 1.782374270883751e-05, + "loss": 0.4892, + "step": 2840 + }, + { + "epoch": 0.24, + "learning_rate": 1.7822054669674878e-05, + "loss": 0.4928, + "step": 2841 + }, + { + "epoch": 0.24, + "learning_rate": 1.7820366056093083e-05, + "loss": 0.4805, + "step": 2842 + }, + { + "epoch": 0.24, + "learning_rate": 1.7818676868216137e-05, + "loss": 0.4995, + "step": 2843 + }, + { + "epoch": 0.24, + "learning_rate": 1.781698710616808e-05, + "loss": 0.4744, + "step": 2844 + }, + { + "epoch": 0.24, + "learning_rate": 1.7815296770073002e-05, + "loss": 0.4918, + "step": 2845 + }, + { + "epoch": 0.24, + "learning_rate": 1.7813605860055034e-05, + "loss": 0.5363, + "step": 2846 + }, + { + "epoch": 0.24, + "learning_rate": 1.7811914376238354e-05, + "loss": 0.4904, + "step": 2847 + }, + { + "epoch": 0.24, + "learning_rate": 1.7810222318747173e-05, + "loss": 0.4744, + "step": 2848 + }, + { + "epoch": 0.24, + "learning_rate": 1.780852968770575e-05, + "loss": 0.4957, + "step": 2849 + }, + { + "epoch": 0.24, + "learning_rate": 1.7806836483238387e-05, + "loss": 0.521, + "step": 2850 + }, + { + "epoch": 0.24, + "learning_rate": 1.780514270546942e-05, + "loss": 0.4905, + "step": 2851 + }, + { + "epoch": 0.24, + "learning_rate": 1.780344835452324e-05, + "loss": 0.494, + "step": 2852 + }, + { + "epoch": 0.24, + "learning_rate": 1.780175343052427e-05, + "loss": 0.4928, + "step": 2853 + }, + { + "epoch": 0.24, + "learning_rate": 1.7800057933596975e-05, + "loss": 0.4872, + "step": 2854 + }, + { + "epoch": 0.24, + "learning_rate": 1.779836186386587e-05, + "loss": 0.4856, + "step": 2855 + }, + { + "epoch": 0.24, + "learning_rate": 1.7796665221455503e-05, + "loss": 0.5121, + "step": 2856 + }, + { + "epoch": 0.24, + "learning_rate": 1.7794968006490475e-05, + "loss": 0.4866, + "step": 2857 + }, + { + "epoch": 0.24, + "learning_rate": 1.7793270219095418e-05, + "loss": 0.498, + "step": 2858 + }, + { + "epoch": 0.24, + "learning_rate": 1.779157185939501e-05, + "loss": 0.4983, + "step": 2859 + }, + { + "epoch": 0.24, + "learning_rate": 1.778987292751397e-05, + "loss": 0.501, + "step": 2860 + }, + { + "epoch": 0.24, + "learning_rate": 1.7788173423577063e-05, + "loss": 0.5019, + "step": 2861 + }, + { + "epoch": 0.24, + "learning_rate": 1.7786473347709094e-05, + "loss": 0.5126, + "step": 2862 + }, + { + "epoch": 0.24, + "learning_rate": 1.778477270003491e-05, + "loss": 0.5096, + "step": 2863 + }, + { + "epoch": 0.24, + "learning_rate": 1.7783071480679397e-05, + "loss": 0.506, + "step": 2864 + }, + { + "epoch": 0.24, + "learning_rate": 1.7781369689767488e-05, + "loss": 0.4847, + "step": 2865 + }, + { + "epoch": 0.24, + "learning_rate": 1.7779667327424152e-05, + "loss": 0.5061, + "step": 2866 + }, + { + "epoch": 0.24, + "learning_rate": 1.777796439377441e-05, + "loss": 0.5108, + "step": 2867 + }, + { + "epoch": 0.24, + "learning_rate": 1.777626088894331e-05, + "loss": 0.486, + "step": 2868 + }, + { + "epoch": 0.24, + "learning_rate": 1.7774556813055956e-05, + "loss": 0.4891, + "step": 2869 + }, + { + "epoch": 0.24, + "learning_rate": 1.7772852166237483e-05, + "loss": 0.5196, + "step": 2870 + }, + { + "epoch": 0.24, + "learning_rate": 1.7771146948613078e-05, + "loss": 0.507, + "step": 2871 + }, + { + "epoch": 0.24, + "learning_rate": 1.7769441160307967e-05, + "loss": 0.5085, + "step": 2872 + }, + { + "epoch": 0.24, + "learning_rate": 1.776773480144741e-05, + "loss": 0.4863, + "step": 2873 + }, + { + "epoch": 0.24, + "learning_rate": 1.776602787215672e-05, + "loss": 0.4874, + "step": 2874 + }, + { + "epoch": 0.24, + "learning_rate": 1.7764320372561238e-05, + "loss": 0.5047, + "step": 2875 + }, + { + "epoch": 0.24, + "learning_rate": 1.7762612302786372e-05, + "loss": 0.495, + "step": 2876 + }, + { + "epoch": 0.24, + "learning_rate": 1.776090366295754e-05, + "loss": 0.5146, + "step": 2877 + }, + { + "epoch": 0.24, + "learning_rate": 1.775919445320022e-05, + "loss": 0.4959, + "step": 2878 + }, + { + "epoch": 0.24, + "learning_rate": 1.7757484673639936e-05, + "loss": 0.4918, + "step": 2879 + }, + { + "epoch": 0.24, + "learning_rate": 1.7755774324402244e-05, + "loss": 0.4994, + "step": 2880 + }, + { + "epoch": 0.24, + "learning_rate": 1.7754063405612744e-05, + "loss": 0.4843, + "step": 2881 + }, + { + "epoch": 0.24, + "learning_rate": 1.7752351917397078e-05, + "loss": 0.5114, + "step": 2882 + }, + { + "epoch": 0.24, + "learning_rate": 1.775063985988093e-05, + "loss": 0.4892, + "step": 2883 + }, + { + "epoch": 0.24, + "learning_rate": 1.774892723319003e-05, + "loss": 0.5053, + "step": 2884 + }, + { + "epoch": 0.24, + "learning_rate": 1.7747214037450146e-05, + "loss": 0.4994, + "step": 2885 + }, + { + "epoch": 0.24, + "learning_rate": 1.7745500272787084e-05, + "loss": 0.4916, + "step": 2886 + }, + { + "epoch": 0.24, + "learning_rate": 1.7743785939326697e-05, + "loss": 0.5066, + "step": 2887 + }, + { + "epoch": 0.24, + "learning_rate": 1.7742071037194882e-05, + "loss": 0.484, + "step": 2888 + }, + { + "epoch": 0.24, + "learning_rate": 1.7740355566517567e-05, + "loss": 0.5008, + "step": 2889 + }, + { + "epoch": 0.24, + "learning_rate": 1.7738639527420738e-05, + "loss": 0.4982, + "step": 2890 + }, + { + "epoch": 0.24, + "learning_rate": 1.773692292003041e-05, + "loss": 0.4913, + "step": 2891 + }, + { + "epoch": 0.24, + "learning_rate": 1.7735205744472642e-05, + "loss": 0.5338, + "step": 2892 + }, + { + "epoch": 0.24, + "learning_rate": 1.7733488000873538e-05, + "loss": 0.5042, + "step": 2893 + }, + { + "epoch": 0.24, + "learning_rate": 1.773176968935924e-05, + "loss": 0.4934, + "step": 2894 + }, + { + "epoch": 0.24, + "learning_rate": 1.7730050810055935e-05, + "loss": 0.499, + "step": 2895 + }, + { + "epoch": 0.24, + "learning_rate": 1.772833136308985e-05, + "loss": 0.5032, + "step": 2896 + }, + { + "epoch": 0.24, + "learning_rate": 1.7726611348587255e-05, + "loss": 0.5151, + "step": 2897 + }, + { + "epoch": 0.24, + "learning_rate": 1.7724890766674457e-05, + "loss": 0.4901, + "step": 2898 + }, + { + "epoch": 0.24, + "learning_rate": 1.7723169617477815e-05, + "loss": 0.5074, + "step": 2899 + }, + { + "epoch": 0.24, + "learning_rate": 1.772144790112372e-05, + "loss": 0.4803, + "step": 2900 + }, + { + "epoch": 0.24, + "learning_rate": 1.7719725617738605e-05, + "loss": 0.4699, + "step": 2901 + }, + { + "epoch": 0.24, + "learning_rate": 1.771800276744895e-05, + "loss": 0.5076, + "step": 2902 + }, + { + "epoch": 0.24, + "learning_rate": 1.771627935038127e-05, + "loss": 0.4943, + "step": 2903 + }, + { + "epoch": 0.24, + "learning_rate": 1.7714555366662133e-05, + "loss": 0.4933, + "step": 2904 + }, + { + "epoch": 0.24, + "learning_rate": 1.7712830816418137e-05, + "loss": 0.5069, + "step": 2905 + }, + { + "epoch": 0.24, + "learning_rate": 1.7711105699775925e-05, + "loss": 0.4909, + "step": 2906 + }, + { + "epoch": 0.24, + "learning_rate": 1.7709380016862182e-05, + "loss": 0.4913, + "step": 2907 + }, + { + "epoch": 0.24, + "learning_rate": 1.7707653767803638e-05, + "loss": 0.4997, + "step": 2908 + }, + { + "epoch": 0.24, + "learning_rate": 1.770592695272706e-05, + "loss": 0.4943, + "step": 2909 + }, + { + "epoch": 0.24, + "learning_rate": 1.7704199571759257e-05, + "loss": 0.5002, + "step": 2910 + }, + { + "epoch": 0.24, + "learning_rate": 1.770247162502708e-05, + "loss": 0.4869, + "step": 2911 + }, + { + "epoch": 0.24, + "learning_rate": 1.7700743112657427e-05, + "loss": 0.504, + "step": 2912 + }, + { + "epoch": 0.24, + "learning_rate": 1.7699014034777227e-05, + "loss": 0.4923, + "step": 2913 + }, + { + "epoch": 0.24, + "learning_rate": 1.7697284391513462e-05, + "loss": 0.5013, + "step": 2914 + }, + { + "epoch": 0.24, + "learning_rate": 1.7695554182993145e-05, + "loss": 0.5073, + "step": 2915 + }, + { + "epoch": 0.24, + "learning_rate": 1.7693823409343335e-05, + "loss": 0.4885, + "step": 2916 + }, + { + "epoch": 0.24, + "learning_rate": 1.769209207069114e-05, + "loss": 0.5021, + "step": 2917 + }, + { + "epoch": 0.24, + "learning_rate": 1.7690360167163693e-05, + "loss": 0.4975, + "step": 2918 + }, + { + "epoch": 0.24, + "learning_rate": 1.768862769888818e-05, + "loss": 0.5013, + "step": 2919 + }, + { + "epoch": 0.24, + "learning_rate": 1.7686894665991837e-05, + "loss": 0.5013, + "step": 2920 + }, + { + "epoch": 0.24, + "learning_rate": 1.7685161068601915e-05, + "loss": 0.4903, + "step": 2921 + }, + { + "epoch": 0.24, + "learning_rate": 1.768342690684573e-05, + "loss": 0.4874, + "step": 2922 + }, + { + "epoch": 0.24, + "learning_rate": 1.768169218085063e-05, + "loss": 0.5023, + "step": 2923 + }, + { + "epoch": 0.24, + "learning_rate": 1.7679956890744008e-05, + "loss": 0.4943, + "step": 2924 + }, + { + "epoch": 0.24, + "learning_rate": 1.7678221036653295e-05, + "loss": 0.505, + "step": 2925 + }, + { + "epoch": 0.24, + "learning_rate": 1.7676484618705966e-05, + "loss": 0.4858, + "step": 2926 + }, + { + "epoch": 0.24, + "learning_rate": 1.7674747637029533e-05, + "loss": 0.4885, + "step": 2927 + }, + { + "epoch": 0.24, + "learning_rate": 1.7673010091751557e-05, + "loss": 0.4894, + "step": 2928 + }, + { + "epoch": 0.25, + "learning_rate": 1.7671271982999637e-05, + "loss": 0.4983, + "step": 2929 + }, + { + "epoch": 0.25, + "learning_rate": 1.7669533310901405e-05, + "loss": 0.4914, + "step": 2930 + }, + { + "epoch": 0.25, + "learning_rate": 1.766779407558455e-05, + "loss": 0.5021, + "step": 2931 + }, + { + "epoch": 0.25, + "learning_rate": 1.7666054277176788e-05, + "loss": 0.4882, + "step": 2932 + }, + { + "epoch": 0.25, + "learning_rate": 1.7664313915805885e-05, + "loss": 0.4862, + "step": 2933 + }, + { + "epoch": 0.25, + "learning_rate": 1.7662572991599648e-05, + "loss": 0.5032, + "step": 2934 + }, + { + "epoch": 0.25, + "learning_rate": 1.7660831504685923e-05, + "loss": 0.4968, + "step": 2935 + }, + { + "epoch": 0.25, + "learning_rate": 1.7659089455192594e-05, + "loss": 0.4915, + "step": 2936 + }, + { + "epoch": 0.25, + "learning_rate": 1.7657346843247595e-05, + "loss": 0.5019, + "step": 2937 + }, + { + "epoch": 0.25, + "learning_rate": 1.765560366897889e-05, + "loss": 0.4972, + "step": 2938 + }, + { + "epoch": 0.25, + "learning_rate": 1.7653859932514494e-05, + "loss": 0.4978, + "step": 2939 + }, + { + "epoch": 0.25, + "learning_rate": 1.765211563398246e-05, + "loss": 0.5023, + "step": 2940 + }, + { + "epoch": 0.25, + "learning_rate": 1.7650370773510885e-05, + "loss": 0.5064, + "step": 2941 + }, + { + "epoch": 0.25, + "learning_rate": 1.7648625351227894e-05, + "loss": 0.481, + "step": 2942 + }, + { + "epoch": 0.25, + "learning_rate": 1.7646879367261673e-05, + "loss": 0.4964, + "step": 2943 + }, + { + "epoch": 0.25, + "learning_rate": 1.7645132821740437e-05, + "loss": 0.4971, + "step": 2944 + }, + { + "epoch": 0.25, + "learning_rate": 1.7643385714792446e-05, + "loss": 0.4873, + "step": 2945 + }, + { + "epoch": 0.25, + "learning_rate": 1.7641638046546e-05, + "loss": 0.4941, + "step": 2946 + }, + { + "epoch": 0.25, + "learning_rate": 1.7639889817129435e-05, + "loss": 0.4745, + "step": 2947 + }, + { + "epoch": 0.25, + "learning_rate": 1.763814102667114e-05, + "loss": 0.4895, + "step": 2948 + }, + { + "epoch": 0.25, + "learning_rate": 1.7636391675299546e-05, + "loss": 0.5155, + "step": 2949 + }, + { + "epoch": 0.25, + "learning_rate": 1.76346417631431e-05, + "loss": 0.4832, + "step": 2950 + }, + { + "epoch": 0.25, + "learning_rate": 1.763289129033032e-05, + "loss": 0.4912, + "step": 2951 + }, + { + "epoch": 0.25, + "learning_rate": 1.7631140256989753e-05, + "loss": 0.5079, + "step": 2952 + }, + { + "epoch": 0.25, + "learning_rate": 1.762938866324998e-05, + "loss": 0.4972, + "step": 2953 + }, + { + "epoch": 0.25, + "learning_rate": 1.7627636509239646e-05, + "loss": 0.4955, + "step": 2954 + }, + { + "epoch": 0.25, + "learning_rate": 1.7625883795087405e-05, + "loss": 0.4958, + "step": 2955 + }, + { + "epoch": 0.25, + "learning_rate": 1.762413052092198e-05, + "loss": 0.4923, + "step": 2956 + }, + { + "epoch": 0.25, + "learning_rate": 1.7622376686872122e-05, + "loss": 0.4913, + "step": 2957 + }, + { + "epoch": 0.25, + "learning_rate": 1.762062229306662e-05, + "loss": 0.51, + "step": 2958 + }, + { + "epoch": 0.25, + "learning_rate": 1.7618867339634314e-05, + "loss": 0.4916, + "step": 2959 + }, + { + "epoch": 0.25, + "learning_rate": 1.7617111826704083e-05, + "loss": 0.5067, + "step": 2960 + }, + { + "epoch": 0.25, + "learning_rate": 1.761535575440484e-05, + "loss": 0.517, + "step": 2961 + }, + { + "epoch": 0.25, + "learning_rate": 1.7613599122865545e-05, + "loss": 0.4977, + "step": 2962 + }, + { + "epoch": 0.25, + "learning_rate": 1.76118419322152e-05, + "loss": 0.5007, + "step": 2963 + }, + { + "epoch": 0.25, + "learning_rate": 1.761008418258284e-05, + "loss": 0.4947, + "step": 2964 + }, + { + "epoch": 0.25, + "learning_rate": 1.7608325874097548e-05, + "loss": 0.5109, + "step": 2965 + }, + { + "epoch": 0.25, + "learning_rate": 1.7606567006888453e-05, + "loss": 0.4925, + "step": 2966 + }, + { + "epoch": 0.25, + "learning_rate": 1.7604807581084714e-05, + "loss": 0.4935, + "step": 2967 + }, + { + "epoch": 0.25, + "learning_rate": 1.7603047596815538e-05, + "loss": 0.4883, + "step": 2968 + }, + { + "epoch": 0.25, + "learning_rate": 1.760128705421017e-05, + "loss": 0.5063, + "step": 2969 + }, + { + "epoch": 0.25, + "learning_rate": 1.7599525953397898e-05, + "loss": 0.4865, + "step": 2970 + }, + { + "epoch": 0.25, + "learning_rate": 1.7597764294508048e-05, + "loss": 0.5095, + "step": 2971 + }, + { + "epoch": 0.25, + "learning_rate": 1.7596002077669988e-05, + "loss": 0.4756, + "step": 2972 + }, + { + "epoch": 0.25, + "learning_rate": 1.759423930301313e-05, + "loss": 0.4943, + "step": 2973 + }, + { + "epoch": 0.25, + "learning_rate": 1.7592475970666926e-05, + "loss": 0.5059, + "step": 2974 + }, + { + "epoch": 0.25, + "learning_rate": 1.7590712080760865e-05, + "loss": 0.493, + "step": 2975 + }, + { + "epoch": 0.25, + "learning_rate": 1.7588947633424478e-05, + "loss": 0.4919, + "step": 2976 + }, + { + "epoch": 0.25, + "learning_rate": 1.7587182628787343e-05, + "loss": 0.492, + "step": 2977 + }, + { + "epoch": 0.25, + "learning_rate": 1.758541706697908e-05, + "loss": 0.5072, + "step": 2978 + }, + { + "epoch": 0.25, + "learning_rate": 1.758365094812933e-05, + "loss": 0.4911, + "step": 2979 + }, + { + "epoch": 0.25, + "learning_rate": 1.75818842723678e-05, + "loss": 0.4993, + "step": 2980 + }, + { + "epoch": 0.25, + "learning_rate": 1.7580117039824224e-05, + "loss": 0.5072, + "step": 2981 + }, + { + "epoch": 0.25, + "learning_rate": 1.757834925062838e-05, + "loss": 0.4968, + "step": 2982 + }, + { + "epoch": 0.25, + "learning_rate": 1.7576580904910088e-05, + "loss": 0.4873, + "step": 2983 + }, + { + "epoch": 0.25, + "learning_rate": 1.757481200279921e-05, + "loss": 0.5004, + "step": 2984 + }, + { + "epoch": 0.25, + "learning_rate": 1.7573042544425644e-05, + "loss": 0.5078, + "step": 2985 + }, + { + "epoch": 0.25, + "learning_rate": 1.757127252991933e-05, + "loss": 0.486, + "step": 2986 + }, + { + "epoch": 0.25, + "learning_rate": 1.7569501959410253e-05, + "loss": 0.5065, + "step": 2987 + }, + { + "epoch": 0.25, + "learning_rate": 1.7567730833028436e-05, + "loss": 0.5147, + "step": 2988 + }, + { + "epoch": 0.25, + "learning_rate": 1.7565959150903943e-05, + "loss": 0.4804, + "step": 2989 + }, + { + "epoch": 0.25, + "learning_rate": 1.756418691316688e-05, + "loss": 0.4937, + "step": 2990 + }, + { + "epoch": 0.25, + "learning_rate": 1.7562414119947392e-05, + "loss": 0.4972, + "step": 2991 + }, + { + "epoch": 0.25, + "learning_rate": 1.7560640771375668e-05, + "loss": 0.4794, + "step": 2992 + }, + { + "epoch": 0.25, + "learning_rate": 1.755886686758193e-05, + "loss": 0.5034, + "step": 2993 + }, + { + "epoch": 0.25, + "learning_rate": 1.7557092408696446e-05, + "loss": 0.5085, + "step": 2994 + }, + { + "epoch": 0.25, + "learning_rate": 1.7555317394849532e-05, + "loss": 0.4924, + "step": 2995 + }, + { + "epoch": 0.25, + "learning_rate": 1.7553541826171535e-05, + "loss": 0.5068, + "step": 2996 + }, + { + "epoch": 0.25, + "learning_rate": 1.755176570279284e-05, + "loss": 0.4977, + "step": 2997 + }, + { + "epoch": 0.25, + "learning_rate": 1.7549989024843883e-05, + "loss": 0.4948, + "step": 2998 + }, + { + "epoch": 0.25, + "learning_rate": 1.7548211792455134e-05, + "loss": 0.5113, + "step": 2999 + }, + { + "epoch": 0.25, + "learning_rate": 1.754643400575711e-05, + "loss": 0.4921, + "step": 3000 + }, + { + "epoch": 0.25, + "learning_rate": 1.7544655664880357e-05, + "loss": 0.4879, + "step": 3001 + }, + { + "epoch": 0.25, + "learning_rate": 1.7542876769955475e-05, + "loss": 0.5032, + "step": 3002 + }, + { + "epoch": 0.25, + "learning_rate": 1.7541097321113093e-05, + "loss": 0.4926, + "step": 3003 + }, + { + "epoch": 0.25, + "learning_rate": 1.7539317318483893e-05, + "loss": 0.4976, + "step": 3004 + }, + { + "epoch": 0.25, + "learning_rate": 1.7537536762198584e-05, + "loss": 0.4868, + "step": 3005 + }, + { + "epoch": 0.25, + "learning_rate": 1.753575565238793e-05, + "loss": 0.5015, + "step": 3006 + }, + { + "epoch": 0.25, + "learning_rate": 1.753397398918272e-05, + "loss": 0.4932, + "step": 3007 + }, + { + "epoch": 0.25, + "learning_rate": 1.75321917727138e-05, + "loss": 0.5025, + "step": 3008 + }, + { + "epoch": 0.25, + "learning_rate": 1.7530409003112042e-05, + "loss": 0.5077, + "step": 3009 + }, + { + "epoch": 0.25, + "learning_rate": 1.7528625680508372e-05, + "loss": 0.5092, + "step": 3010 + }, + { + "epoch": 0.25, + "learning_rate": 1.7526841805033742e-05, + "loss": 0.483, + "step": 3011 + }, + { + "epoch": 0.25, + "learning_rate": 1.752505737681916e-05, + "loss": 0.4801, + "step": 3012 + }, + { + "epoch": 0.25, + "learning_rate": 1.7523272395995657e-05, + "loss": 0.5236, + "step": 3013 + }, + { + "epoch": 0.25, + "learning_rate": 1.752148686269433e-05, + "loss": 0.4854, + "step": 3014 + }, + { + "epoch": 0.25, + "learning_rate": 1.7519700777046285e-05, + "loss": 0.4899, + "step": 3015 + }, + { + "epoch": 0.25, + "learning_rate": 1.7517914139182694e-05, + "loss": 0.4946, + "step": 3016 + }, + { + "epoch": 0.25, + "learning_rate": 1.751612694923476e-05, + "loss": 0.4829, + "step": 3017 + }, + { + "epoch": 0.25, + "learning_rate": 1.751433920733372e-05, + "loss": 0.4841, + "step": 3018 + }, + { + "epoch": 0.25, + "learning_rate": 1.7512550913610867e-05, + "loss": 0.5057, + "step": 3019 + }, + { + "epoch": 0.25, + "learning_rate": 1.751076206819752e-05, + "loss": 0.4959, + "step": 3020 + }, + { + "epoch": 0.25, + "learning_rate": 1.750897267122505e-05, + "loss": 0.5034, + "step": 3021 + }, + { + "epoch": 0.25, + "learning_rate": 1.7507182722824854e-05, + "loss": 0.4933, + "step": 3022 + }, + { + "epoch": 0.25, + "learning_rate": 1.7505392223128385e-05, + "loss": 0.5029, + "step": 3023 + }, + { + "epoch": 0.25, + "learning_rate": 1.750360117226713e-05, + "loss": 0.5082, + "step": 3024 + }, + { + "epoch": 0.25, + "learning_rate": 1.7501809570372614e-05, + "loss": 0.4933, + "step": 3025 + }, + { + "epoch": 0.25, + "learning_rate": 1.7500017417576406e-05, + "loss": 0.4984, + "step": 3026 + }, + { + "epoch": 0.25, + "learning_rate": 1.7498224714010113e-05, + "loss": 0.5161, + "step": 3027 + }, + { + "epoch": 0.25, + "learning_rate": 1.7496431459805387e-05, + "loss": 0.5026, + "step": 3028 + }, + { + "epoch": 0.25, + "learning_rate": 1.749463765509391e-05, + "loss": 0.5023, + "step": 3029 + }, + { + "epoch": 0.25, + "learning_rate": 1.749284330000742e-05, + "loss": 0.5051, + "step": 3030 + }, + { + "epoch": 0.25, + "learning_rate": 1.7491048394677682e-05, + "loss": 0.503, + "step": 3031 + }, + { + "epoch": 0.25, + "learning_rate": 1.7489252939236506e-05, + "loss": 0.5008, + "step": 3032 + }, + { + "epoch": 0.25, + "learning_rate": 1.7487456933815746e-05, + "loss": 0.507, + "step": 3033 + }, + { + "epoch": 0.25, + "learning_rate": 1.7485660378547293e-05, + "loss": 0.5189, + "step": 3034 + }, + { + "epoch": 0.25, + "learning_rate": 1.7483863273563072e-05, + "loss": 0.4798, + "step": 3035 + }, + { + "epoch": 0.25, + "learning_rate": 1.7482065618995063e-05, + "loss": 0.4859, + "step": 3036 + }, + { + "epoch": 0.25, + "learning_rate": 1.7480267414975274e-05, + "loss": 0.5047, + "step": 3037 + }, + { + "epoch": 0.25, + "learning_rate": 1.7478468661635763e-05, + "loss": 0.4966, + "step": 3038 + }, + { + "epoch": 0.25, + "learning_rate": 1.7476669359108614e-05, + "loss": 0.4787, + "step": 3039 + }, + { + "epoch": 0.25, + "learning_rate": 1.7474869507525967e-05, + "loss": 0.4912, + "step": 3040 + }, + { + "epoch": 0.25, + "learning_rate": 1.7473069107019993e-05, + "loss": 0.4911, + "step": 3041 + }, + { + "epoch": 0.25, + "learning_rate": 1.7471268157722907e-05, + "loss": 0.4955, + "step": 3042 + }, + { + "epoch": 0.25, + "learning_rate": 1.7469466659766963e-05, + "loss": 0.4862, + "step": 3043 + }, + { + "epoch": 0.25, + "learning_rate": 1.7467664613284455e-05, + "loss": 0.5016, + "step": 3044 + }, + { + "epoch": 0.25, + "learning_rate": 1.7465862018407718e-05, + "loss": 0.5008, + "step": 3045 + }, + { + "epoch": 0.25, + "learning_rate": 1.746405887526913e-05, + "loss": 0.5055, + "step": 3046 + }, + { + "epoch": 0.25, + "learning_rate": 1.74622551840011e-05, + "loss": 0.4982, + "step": 3047 + }, + { + "epoch": 0.26, + "learning_rate": 1.7460450944736087e-05, + "loss": 0.5026, + "step": 3048 + }, + { + "epoch": 0.26, + "learning_rate": 1.7458646157606585e-05, + "loss": 0.4959, + "step": 3049 + }, + { + "epoch": 0.26, + "learning_rate": 1.745684082274514e-05, + "loss": 0.4894, + "step": 3050 + }, + { + "epoch": 0.26, + "learning_rate": 1.7455034940284313e-05, + "loss": 0.4976, + "step": 3051 + }, + { + "epoch": 0.26, + "learning_rate": 1.745322851035673e-05, + "loss": 0.4959, + "step": 3052 + }, + { + "epoch": 0.26, + "learning_rate": 1.7451421533095047e-05, + "loss": 0.4848, + "step": 3053 + }, + { + "epoch": 0.26, + "learning_rate": 1.744961400863196e-05, + "loss": 0.5046, + "step": 3054 + }, + { + "epoch": 0.26, + "learning_rate": 1.7447805937100203e-05, + "loss": 0.4826, + "step": 3055 + }, + { + "epoch": 0.26, + "learning_rate": 1.7445997318632555e-05, + "loss": 0.4998, + "step": 3056 + }, + { + "epoch": 0.26, + "learning_rate": 1.7444188153361836e-05, + "loss": 0.4941, + "step": 3057 + }, + { + "epoch": 0.26, + "learning_rate": 1.74423784414209e-05, + "loss": 0.4904, + "step": 3058 + }, + { + "epoch": 0.26, + "learning_rate": 1.744056818294265e-05, + "loss": 0.4982, + "step": 3059 + }, + { + "epoch": 0.26, + "learning_rate": 1.743875737806002e-05, + "loss": 0.4896, + "step": 3060 + }, + { + "epoch": 0.26, + "learning_rate": 1.7436946026905986e-05, + "loss": 0.5043, + "step": 3061 + }, + { + "epoch": 0.26, + "learning_rate": 1.743513412961357e-05, + "loss": 0.4901, + "step": 3062 + }, + { + "epoch": 0.26, + "learning_rate": 1.7433321686315824e-05, + "loss": 0.4888, + "step": 3063 + }, + { + "epoch": 0.26, + "learning_rate": 1.7431508697145855e-05, + "loss": 0.498, + "step": 3064 + }, + { + "epoch": 0.26, + "learning_rate": 1.7429695162236798e-05, + "loss": 0.5043, + "step": 3065 + }, + { + "epoch": 0.26, + "learning_rate": 1.7427881081721828e-05, + "loss": 0.4807, + "step": 3066 + }, + { + "epoch": 0.26, + "learning_rate": 1.7426066455734167e-05, + "loss": 0.483, + "step": 3067 + }, + { + "epoch": 0.26, + "learning_rate": 1.7424251284407075e-05, + "loss": 0.5025, + "step": 3068 + }, + { + "epoch": 0.26, + "learning_rate": 1.7422435567873846e-05, + "loss": 0.5057, + "step": 3069 + }, + { + "epoch": 0.26, + "learning_rate": 1.742061930626782e-05, + "loss": 0.4982, + "step": 3070 + }, + { + "epoch": 0.26, + "learning_rate": 1.7418802499722377e-05, + "loss": 0.5053, + "step": 3071 + }, + { + "epoch": 0.26, + "learning_rate": 1.7416985148370938e-05, + "loss": 0.5214, + "step": 3072 + }, + { + "epoch": 0.26, + "learning_rate": 1.741516725234696e-05, + "loss": 0.4795, + "step": 3073 + }, + { + "epoch": 0.26, + "learning_rate": 1.7413348811783938e-05, + "loss": 0.4918, + "step": 3074 + }, + { + "epoch": 0.26, + "learning_rate": 1.7411529826815416e-05, + "loss": 0.4958, + "step": 3075 + }, + { + "epoch": 0.26, + "learning_rate": 1.740971029757497e-05, + "loss": 0.502, + "step": 3076 + }, + { + "epoch": 0.26, + "learning_rate": 1.7407890224196217e-05, + "loss": 0.4911, + "step": 3077 + }, + { + "epoch": 0.26, + "learning_rate": 1.7406069606812822e-05, + "loss": 0.503, + "step": 3078 + }, + { + "epoch": 0.26, + "learning_rate": 1.7404248445558476e-05, + "loss": 0.4926, + "step": 3079 + }, + { + "epoch": 0.26, + "learning_rate": 1.7402426740566922e-05, + "loss": 0.4967, + "step": 3080 + }, + { + "epoch": 0.26, + "learning_rate": 1.7400604491971937e-05, + "loss": 0.4957, + "step": 3081 + }, + { + "epoch": 0.26, + "learning_rate": 1.7398781699907337e-05, + "loss": 0.4982, + "step": 3082 + }, + { + "epoch": 0.26, + "learning_rate": 1.7396958364506983e-05, + "loss": 0.4722, + "step": 3083 + }, + { + "epoch": 0.26, + "learning_rate": 1.7395134485904775e-05, + "loss": 0.4908, + "step": 3084 + }, + { + "epoch": 0.26, + "learning_rate": 1.739331006423465e-05, + "loss": 0.5098, + "step": 3085 + }, + { + "epoch": 0.26, + "learning_rate": 1.7391485099630584e-05, + "loss": 0.4836, + "step": 3086 + }, + { + "epoch": 0.26, + "learning_rate": 1.7389659592226597e-05, + "loss": 0.5039, + "step": 3087 + }, + { + "epoch": 0.26, + "learning_rate": 1.7387833542156743e-05, + "loss": 0.4989, + "step": 3088 + }, + { + "epoch": 0.26, + "learning_rate": 1.7386006949555124e-05, + "loss": 0.4883, + "step": 3089 + }, + { + "epoch": 0.26, + "learning_rate": 1.7384179814555872e-05, + "loss": 0.4955, + "step": 3090 + }, + { + "epoch": 0.26, + "learning_rate": 1.7382352137293172e-05, + "loss": 0.5069, + "step": 3091 + }, + { + "epoch": 0.26, + "learning_rate": 1.7380523917901233e-05, + "loss": 0.4878, + "step": 3092 + }, + { + "epoch": 0.26, + "learning_rate": 1.7378695156514318e-05, + "loss": 0.4928, + "step": 3093 + }, + { + "epoch": 0.26, + "learning_rate": 1.7376865853266717e-05, + "loss": 0.5107, + "step": 3094 + }, + { + "epoch": 0.26, + "learning_rate": 1.7375036008292775e-05, + "loss": 0.4845, + "step": 3095 + }, + { + "epoch": 0.26, + "learning_rate": 1.7373205621726864e-05, + "loss": 0.5126, + "step": 3096 + }, + { + "epoch": 0.26, + "learning_rate": 1.7371374693703395e-05, + "loss": 0.4847, + "step": 3097 + }, + { + "epoch": 0.26, + "learning_rate": 1.736954322435683e-05, + "loss": 0.5076, + "step": 3098 + }, + { + "epoch": 0.26, + "learning_rate": 1.7367711213821663e-05, + "loss": 0.4967, + "step": 3099 + }, + { + "epoch": 0.26, + "learning_rate": 1.736587866223243e-05, + "loss": 0.508, + "step": 3100 + }, + { + "epoch": 0.26, + "learning_rate": 1.7364045569723706e-05, + "loss": 0.4877, + "step": 3101 + }, + { + "epoch": 0.26, + "learning_rate": 1.7362211936430103e-05, + "loss": 0.4913, + "step": 3102 + }, + { + "epoch": 0.26, + "learning_rate": 1.7360377762486277e-05, + "loss": 0.5046, + "step": 3103 + }, + { + "epoch": 0.26, + "learning_rate": 1.7358543048026925e-05, + "loss": 0.5047, + "step": 3104 + }, + { + "epoch": 0.26, + "learning_rate": 1.7356707793186777e-05, + "loss": 0.4684, + "step": 3105 + }, + { + "epoch": 0.26, + "learning_rate": 1.7354871998100605e-05, + "loss": 0.5183, + "step": 3106 + }, + { + "epoch": 0.26, + "learning_rate": 1.7353035662903225e-05, + "loss": 0.4857, + "step": 3107 + }, + { + "epoch": 0.26, + "learning_rate": 1.735119878772949e-05, + "loss": 0.4787, + "step": 3108 + }, + { + "epoch": 0.26, + "learning_rate": 1.7349361372714294e-05, + "loss": 0.4873, + "step": 3109 + }, + { + "epoch": 0.26, + "learning_rate": 1.7347523417992564e-05, + "loss": 0.4822, + "step": 3110 + }, + { + "epoch": 0.26, + "learning_rate": 1.7345684923699277e-05, + "loss": 0.4815, + "step": 3111 + }, + { + "epoch": 0.26, + "learning_rate": 1.734384588996944e-05, + "loss": 0.5008, + "step": 3112 + }, + { + "epoch": 0.26, + "learning_rate": 1.734200631693811e-05, + "loss": 0.5086, + "step": 3113 + }, + { + "epoch": 0.26, + "learning_rate": 1.7340166204740373e-05, + "loss": 0.4907, + "step": 3114 + }, + { + "epoch": 0.26, + "learning_rate": 1.7338325553511357e-05, + "loss": 0.4919, + "step": 3115 + }, + { + "epoch": 0.26, + "learning_rate": 1.7336484363386237e-05, + "loss": 0.5166, + "step": 3116 + }, + { + "epoch": 0.26, + "learning_rate": 1.7334642634500217e-05, + "loss": 0.4958, + "step": 3117 + }, + { + "epoch": 0.26, + "learning_rate": 1.7332800366988552e-05, + "loss": 0.4995, + "step": 3118 + }, + { + "epoch": 0.26, + "learning_rate": 1.733095756098653e-05, + "loss": 0.5063, + "step": 3119 + }, + { + "epoch": 0.26, + "learning_rate": 1.732911421662947e-05, + "loss": 0.4965, + "step": 3120 + }, + { + "epoch": 0.26, + "learning_rate": 1.732727033405275e-05, + "loss": 0.5028, + "step": 3121 + }, + { + "epoch": 0.26, + "learning_rate": 1.7325425913391772e-05, + "loss": 0.484, + "step": 3122 + }, + { + "epoch": 0.26, + "learning_rate": 1.7323580954781986e-05, + "loss": 0.516, + "step": 3123 + }, + { + "epoch": 0.26, + "learning_rate": 1.7321735458358872e-05, + "loss": 0.4818, + "step": 3124 + }, + { + "epoch": 0.26, + "learning_rate": 1.731988942425796e-05, + "loss": 0.4944, + "step": 3125 + }, + { + "epoch": 0.26, + "learning_rate": 1.7318042852614817e-05, + "loss": 0.5021, + "step": 3126 + }, + { + "epoch": 0.26, + "learning_rate": 1.7316195743565045e-05, + "loss": 0.5114, + "step": 3127 + }, + { + "epoch": 0.26, + "learning_rate": 1.7314348097244288e-05, + "loss": 0.5076, + "step": 3128 + }, + { + "epoch": 0.26, + "learning_rate": 1.7312499913788225e-05, + "loss": 0.503, + "step": 3129 + }, + { + "epoch": 0.26, + "learning_rate": 1.7310651193332586e-05, + "loss": 0.4836, + "step": 3130 + }, + { + "epoch": 0.26, + "learning_rate": 1.730880193601313e-05, + "loss": 0.4987, + "step": 3131 + }, + { + "epoch": 0.26, + "learning_rate": 1.7306952141965664e-05, + "loss": 0.4865, + "step": 3132 + }, + { + "epoch": 0.26, + "learning_rate": 1.7305101811326017e-05, + "loss": 0.4911, + "step": 3133 + }, + { + "epoch": 0.26, + "learning_rate": 1.7303250944230084e-05, + "loss": 0.5219, + "step": 3134 + }, + { + "epoch": 0.26, + "learning_rate": 1.7301399540813773e-05, + "loss": 0.4941, + "step": 3135 + }, + { + "epoch": 0.26, + "learning_rate": 1.729954760121305e-05, + "loss": 0.4856, + "step": 3136 + }, + { + "epoch": 0.26, + "learning_rate": 1.7297695125563915e-05, + "loss": 0.496, + "step": 3137 + }, + { + "epoch": 0.26, + "learning_rate": 1.72958421140024e-05, + "loss": 0.4944, + "step": 3138 + }, + { + "epoch": 0.26, + "learning_rate": 1.7293988566664586e-05, + "loss": 0.4983, + "step": 3139 + }, + { + "epoch": 0.26, + "learning_rate": 1.7292134483686594e-05, + "loss": 0.4886, + "step": 3140 + }, + { + "epoch": 0.26, + "learning_rate": 1.7290279865204567e-05, + "loss": 0.498, + "step": 3141 + }, + { + "epoch": 0.26, + "learning_rate": 1.728842471135472e-05, + "loss": 0.4731, + "step": 3142 + }, + { + "epoch": 0.26, + "learning_rate": 1.728656902227327e-05, + "loss": 0.5268, + "step": 3143 + }, + { + "epoch": 0.26, + "learning_rate": 1.72847127980965e-05, + "loss": 0.5159, + "step": 3144 + }, + { + "epoch": 0.26, + "learning_rate": 1.7282856038960724e-05, + "loss": 0.5017, + "step": 3145 + }, + { + "epoch": 0.26, + "learning_rate": 1.7280998745002286e-05, + "loss": 0.4799, + "step": 3146 + }, + { + "epoch": 0.26, + "learning_rate": 1.7279140916357588e-05, + "loss": 0.4828, + "step": 3147 + }, + { + "epoch": 0.26, + "learning_rate": 1.727728255316306e-05, + "loss": 0.5081, + "step": 3148 + }, + { + "epoch": 0.26, + "learning_rate": 1.7275423655555163e-05, + "loss": 0.4772, + "step": 3149 + }, + { + "epoch": 0.26, + "learning_rate": 1.7273564223670422e-05, + "loss": 0.5074, + "step": 3150 + }, + { + "epoch": 0.26, + "learning_rate": 1.727170425764537e-05, + "loss": 0.4899, + "step": 3151 + }, + { + "epoch": 0.26, + "learning_rate": 1.7269843757616605e-05, + "loss": 0.4881, + "step": 3152 + }, + { + "epoch": 0.26, + "learning_rate": 1.7267982723720755e-05, + "loss": 0.4807, + "step": 3153 + }, + { + "epoch": 0.26, + "learning_rate": 1.726612115609448e-05, + "loss": 0.5115, + "step": 3154 + }, + { + "epoch": 0.26, + "learning_rate": 1.7264259054874492e-05, + "loss": 0.5049, + "step": 3155 + }, + { + "epoch": 0.26, + "learning_rate": 1.726239642019753e-05, + "loss": 0.496, + "step": 3156 + }, + { + "epoch": 0.26, + "learning_rate": 1.7260533252200383e-05, + "loss": 0.4848, + "step": 3157 + }, + { + "epoch": 0.26, + "learning_rate": 1.7258669551019872e-05, + "loss": 0.5023, + "step": 3158 + }, + { + "epoch": 0.26, + "learning_rate": 1.725680531679286e-05, + "loss": 0.5088, + "step": 3159 + }, + { + "epoch": 0.26, + "learning_rate": 1.725494054965625e-05, + "loss": 0.5108, + "step": 3160 + }, + { + "epoch": 0.26, + "learning_rate": 1.7253075249746984e-05, + "loss": 0.4842, + "step": 3161 + }, + { + "epoch": 0.26, + "learning_rate": 1.7251209417202036e-05, + "loss": 0.4926, + "step": 3162 + }, + { + "epoch": 0.26, + "learning_rate": 1.724934305215843e-05, + "loss": 0.5006, + "step": 3163 + }, + { + "epoch": 0.26, + "learning_rate": 1.7247476154753222e-05, + "loss": 0.4902, + "step": 3164 + }, + { + "epoch": 0.26, + "learning_rate": 1.724560872512351e-05, + "loss": 0.5061, + "step": 3165 + }, + { + "epoch": 0.26, + "learning_rate": 1.724374076340643e-05, + "loss": 0.4807, + "step": 3166 + }, + { + "epoch": 0.26, + "learning_rate": 1.724187226973916e-05, + "loss": 0.4988, + "step": 3167 + }, + { + "epoch": 0.27, + "learning_rate": 1.7240003244258904e-05, + "loss": 0.4889, + "step": 3168 + }, + { + "epoch": 0.27, + "learning_rate": 1.723813368710293e-05, + "loss": 0.488, + "step": 3169 + }, + { + "epoch": 0.27, + "learning_rate": 1.723626359840852e-05, + "loss": 0.5014, + "step": 3170 + }, + { + "epoch": 0.27, + "learning_rate": 1.7234392978313012e-05, + "loss": 0.4979, + "step": 3171 + }, + { + "epoch": 0.27, + "learning_rate": 1.7232521826953773e-05, + "loss": 0.4916, + "step": 3172 + }, + { + "epoch": 0.27, + "learning_rate": 1.7230650144468212e-05, + "loss": 0.5112, + "step": 3173 + }, + { + "epoch": 0.27, + "learning_rate": 1.7228777930993784e-05, + "loss": 0.477, + "step": 3174 + }, + { + "epoch": 0.27, + "learning_rate": 1.7226905186667965e-05, + "loss": 0.5136, + "step": 3175 + }, + { + "epoch": 0.27, + "learning_rate": 1.722503191162829e-05, + "loss": 0.5031, + "step": 3176 + }, + { + "epoch": 0.27, + "learning_rate": 1.7223158106012326e-05, + "loss": 0.4908, + "step": 3177 + }, + { + "epoch": 0.27, + "learning_rate": 1.722128376995767e-05, + "loss": 0.4848, + "step": 3178 + }, + { + "epoch": 0.27, + "learning_rate": 1.721940890360197e-05, + "loss": 0.4897, + "step": 3179 + }, + { + "epoch": 0.27, + "learning_rate": 1.7217533507082907e-05, + "loss": 0.489, + "step": 3180 + }, + { + "epoch": 0.27, + "learning_rate": 1.721565758053821e-05, + "loss": 0.5087, + "step": 3181 + }, + { + "epoch": 0.27, + "learning_rate": 1.7213781124105623e-05, + "loss": 0.5086, + "step": 3182 + }, + { + "epoch": 0.27, + "learning_rate": 1.7211904137922962e-05, + "loss": 0.4942, + "step": 3183 + }, + { + "epoch": 0.27, + "learning_rate": 1.721002662212805e-05, + "loss": 0.4779, + "step": 3184 + }, + { + "epoch": 0.27, + "learning_rate": 1.720814857685878e-05, + "loss": 0.4938, + "step": 3185 + }, + { + "epoch": 0.27, + "learning_rate": 1.7206270002253056e-05, + "loss": 0.4867, + "step": 3186 + }, + { + "epoch": 0.27, + "learning_rate": 1.7204390898448837e-05, + "loss": 0.4784, + "step": 3187 + }, + { + "epoch": 0.27, + "learning_rate": 1.720251126558411e-05, + "loss": 0.4861, + "step": 3188 + }, + { + "epoch": 0.27, + "learning_rate": 1.720063110379692e-05, + "loss": 0.5038, + "step": 3189 + }, + { + "epoch": 0.27, + "learning_rate": 1.7198750413225327e-05, + "loss": 0.5021, + "step": 3190 + }, + { + "epoch": 0.27, + "learning_rate": 1.7196869194007448e-05, + "loss": 0.4814, + "step": 3191 + }, + { + "epoch": 0.27, + "learning_rate": 1.719498744628143e-05, + "loss": 0.4862, + "step": 3192 + }, + { + "epoch": 0.27, + "learning_rate": 1.719310517018546e-05, + "loss": 0.5017, + "step": 3193 + }, + { + "epoch": 0.27, + "learning_rate": 1.7191222365857764e-05, + "loss": 0.4901, + "step": 3194 + }, + { + "epoch": 0.27, + "learning_rate": 1.7189339033436607e-05, + "loss": 0.4953, + "step": 3195 + }, + { + "epoch": 0.27, + "learning_rate": 1.7187455173060294e-05, + "loss": 0.5086, + "step": 3196 + }, + { + "epoch": 0.27, + "learning_rate": 1.7185570784867168e-05, + "loss": 0.4942, + "step": 3197 + }, + { + "epoch": 0.27, + "learning_rate": 1.7183685868995616e-05, + "loss": 0.5027, + "step": 3198 + }, + { + "epoch": 0.27, + "learning_rate": 1.718180042558405e-05, + "loss": 0.4924, + "step": 3199 + }, + { + "epoch": 0.27, + "learning_rate": 1.717991445477093e-05, + "loss": 0.517, + "step": 3200 + }, + { + "epoch": 0.27, + "learning_rate": 1.7178027956694753e-05, + "loss": 0.4834, + "step": 3201 + }, + { + "epoch": 0.27, + "learning_rate": 1.7176140931494064e-05, + "loss": 0.4947, + "step": 3202 + }, + { + "epoch": 0.27, + "learning_rate": 1.717425337930743e-05, + "loss": 0.5267, + "step": 3203 + }, + { + "epoch": 0.27, + "learning_rate": 1.7172365300273467e-05, + "loss": 0.5019, + "step": 3204 + }, + { + "epoch": 0.27, + "learning_rate": 1.7170476694530834e-05, + "loss": 0.4692, + "step": 3205 + }, + { + "epoch": 0.27, + "learning_rate": 1.716858756221821e-05, + "loss": 0.4858, + "step": 3206 + }, + { + "epoch": 0.27, + "learning_rate": 1.7166697903474335e-05, + "loss": 0.5162, + "step": 3207 + }, + { + "epoch": 0.27, + "learning_rate": 1.716480771843798e-05, + "loss": 0.493, + "step": 3208 + }, + { + "epoch": 0.27, + "learning_rate": 1.7162917007247937e-05, + "loss": 0.4835, + "step": 3209 + }, + { + "epoch": 0.27, + "learning_rate": 1.7161025770043065e-05, + "loss": 0.5061, + "step": 3210 + }, + { + "epoch": 0.27, + "learning_rate": 1.7159134006962248e-05, + "loss": 0.4877, + "step": 3211 + }, + { + "epoch": 0.27, + "learning_rate": 1.7157241718144404e-05, + "loss": 0.4893, + "step": 3212 + }, + { + "epoch": 0.27, + "learning_rate": 1.7155348903728497e-05, + "loss": 0.4832, + "step": 3213 + }, + { + "epoch": 0.27, + "learning_rate": 1.715345556385353e-05, + "loss": 0.4912, + "step": 3214 + }, + { + "epoch": 0.27, + "learning_rate": 1.715156169865854e-05, + "loss": 0.4865, + "step": 3215 + }, + { + "epoch": 0.27, + "learning_rate": 1.7149667308282604e-05, + "loss": 0.4766, + "step": 3216 + }, + { + "epoch": 0.27, + "learning_rate": 1.714777239286484e-05, + "loss": 0.5137, + "step": 3217 + }, + { + "epoch": 0.27, + "learning_rate": 1.7145876952544395e-05, + "loss": 0.4717, + "step": 3218 + }, + { + "epoch": 0.27, + "learning_rate": 1.7143980987460475e-05, + "loss": 0.5099, + "step": 3219 + }, + { + "epoch": 0.27, + "learning_rate": 1.7142084497752304e-05, + "loss": 0.5271, + "step": 3220 + }, + { + "epoch": 0.27, + "learning_rate": 1.714018748355915e-05, + "loss": 0.4995, + "step": 3221 + }, + { + "epoch": 0.27, + "learning_rate": 1.713828994502033e-05, + "loss": 0.522, + "step": 3222 + }, + { + "epoch": 0.27, + "learning_rate": 1.7136391882275186e-05, + "loss": 0.4746, + "step": 3223 + }, + { + "epoch": 0.27, + "learning_rate": 1.7134493295463104e-05, + "loss": 0.4952, + "step": 3224 + }, + { + "epoch": 0.27, + "learning_rate": 1.713259418472351e-05, + "loss": 0.4802, + "step": 3225 + }, + { + "epoch": 0.27, + "learning_rate": 1.713069455019586e-05, + "loss": 0.4934, + "step": 3226 + }, + { + "epoch": 0.27, + "learning_rate": 1.712879439201967e-05, + "loss": 0.5037, + "step": 3227 + }, + { + "epoch": 0.27, + "learning_rate": 1.7126893710334465e-05, + "loss": 0.497, + "step": 3228 + }, + { + "epoch": 0.27, + "learning_rate": 1.7124992505279833e-05, + "loss": 0.4945, + "step": 3229 + }, + { + "epoch": 0.27, + "learning_rate": 1.712309077699538e-05, + "loss": 0.4899, + "step": 3230 + }, + { + "epoch": 0.27, + "learning_rate": 1.712118852562077e-05, + "loss": 0.5034, + "step": 3231 + }, + { + "epoch": 0.27, + "learning_rate": 1.71192857512957e-05, + "loss": 0.4879, + "step": 3232 + }, + { + "epoch": 0.27, + "learning_rate": 1.7117382454159887e-05, + "loss": 0.4883, + "step": 3233 + }, + { + "epoch": 0.27, + "learning_rate": 1.7115478634353117e-05, + "loss": 0.4988, + "step": 3234 + }, + { + "epoch": 0.27, + "learning_rate": 1.7113574292015185e-05, + "loss": 0.4861, + "step": 3235 + }, + { + "epoch": 0.27, + "learning_rate": 1.711166942728595e-05, + "loss": 0.5031, + "step": 3236 + }, + { + "epoch": 0.27, + "learning_rate": 1.710976404030529e-05, + "loss": 0.4695, + "step": 3237 + }, + { + "epoch": 0.27, + "learning_rate": 1.710785813121313e-05, + "loss": 0.4973, + "step": 3238 + }, + { + "epoch": 0.27, + "learning_rate": 1.7105951700149433e-05, + "loss": 0.5143, + "step": 3239 + }, + { + "epoch": 0.27, + "learning_rate": 1.7104044747254202e-05, + "loss": 0.4813, + "step": 3240 + }, + { + "epoch": 0.27, + "learning_rate": 1.7102137272667466e-05, + "loss": 0.513, + "step": 3241 + }, + { + "epoch": 0.27, + "learning_rate": 1.7100229276529314e-05, + "loss": 0.4643, + "step": 3242 + }, + { + "epoch": 0.27, + "learning_rate": 1.7098320758979854e-05, + "loss": 0.492, + "step": 3243 + }, + { + "epoch": 0.27, + "learning_rate": 1.7096411720159244e-05, + "loss": 0.4903, + "step": 3244 + }, + { + "epoch": 0.27, + "learning_rate": 1.7094502160207672e-05, + "loss": 0.5142, + "step": 3245 + }, + { + "epoch": 0.27, + "learning_rate": 1.7092592079265368e-05, + "loss": 0.4952, + "step": 3246 + }, + { + "epoch": 0.27, + "learning_rate": 1.7090681477472605e-05, + "loss": 0.491, + "step": 3247 + }, + { + "epoch": 0.27, + "learning_rate": 1.7088770354969685e-05, + "loss": 0.5151, + "step": 3248 + }, + { + "epoch": 0.27, + "learning_rate": 1.708685871189695e-05, + "loss": 0.503, + "step": 3249 + }, + { + "epoch": 0.27, + "learning_rate": 1.7084946548394797e-05, + "loss": 0.5048, + "step": 3250 + }, + { + "epoch": 0.27, + "learning_rate": 1.7083033864603632e-05, + "loss": 0.4966, + "step": 3251 + }, + { + "epoch": 0.27, + "learning_rate": 1.7081120660663923e-05, + "loss": 0.5089, + "step": 3252 + }, + { + "epoch": 0.27, + "learning_rate": 1.7079206936716163e-05, + "loss": 0.4987, + "step": 3253 + }, + { + "epoch": 0.27, + "learning_rate": 1.707729269290089e-05, + "loss": 0.4891, + "step": 3254 + }, + { + "epoch": 0.27, + "learning_rate": 1.707537792935868e-05, + "loss": 0.4912, + "step": 3255 + }, + { + "epoch": 0.27, + "learning_rate": 1.7073462646230144e-05, + "loss": 0.4958, + "step": 3256 + }, + { + "epoch": 0.27, + "learning_rate": 1.7071546843655932e-05, + "loss": 0.4796, + "step": 3257 + }, + { + "epoch": 0.27, + "learning_rate": 1.706963052177673e-05, + "loss": 0.494, + "step": 3258 + }, + { + "epoch": 0.27, + "learning_rate": 1.706771368073327e-05, + "loss": 0.5072, + "step": 3259 + }, + { + "epoch": 0.27, + "learning_rate": 1.7065796320666312e-05, + "loss": 0.5034, + "step": 3260 + }, + { + "epoch": 0.27, + "learning_rate": 1.7063878441716665e-05, + "loss": 0.5014, + "step": 3261 + }, + { + "epoch": 0.27, + "learning_rate": 1.7061960044025162e-05, + "loss": 0.509, + "step": 3262 + }, + { + "epoch": 0.27, + "learning_rate": 1.706004112773269e-05, + "loss": 0.504, + "step": 3263 + }, + { + "epoch": 0.27, + "learning_rate": 1.7058121692980157e-05, + "loss": 0.494, + "step": 3264 + }, + { + "epoch": 0.27, + "learning_rate": 1.7056201739908528e-05, + "loss": 0.494, + "step": 3265 + }, + { + "epoch": 0.27, + "learning_rate": 1.705428126865879e-05, + "loss": 0.4973, + "step": 3266 + }, + { + "epoch": 0.27, + "learning_rate": 1.7052360279371978e-05, + "loss": 0.4877, + "step": 3267 + }, + { + "epoch": 0.27, + "learning_rate": 1.705043877218916e-05, + "loss": 0.4844, + "step": 3268 + }, + { + "epoch": 0.27, + "learning_rate": 1.7048516747251444e-05, + "loss": 0.5011, + "step": 3269 + }, + { + "epoch": 0.27, + "learning_rate": 1.704659420469997e-05, + "loss": 0.4979, + "step": 3270 + }, + { + "epoch": 0.27, + "learning_rate": 1.7044671144675935e-05, + "loss": 0.4596, + "step": 3271 + }, + { + "epoch": 0.27, + "learning_rate": 1.7042747567320548e-05, + "loss": 0.5083, + "step": 3272 + }, + { + "epoch": 0.27, + "learning_rate": 1.704082347277507e-05, + "loss": 0.4956, + "step": 3273 + }, + { + "epoch": 0.27, + "learning_rate": 1.7038898861180805e-05, + "loss": 0.481, + "step": 3274 + }, + { + "epoch": 0.27, + "learning_rate": 1.7036973732679084e-05, + "loss": 0.507, + "step": 3275 + }, + { + "epoch": 0.27, + "learning_rate": 1.7035048087411283e-05, + "loss": 0.4831, + "step": 3276 + }, + { + "epoch": 0.27, + "learning_rate": 1.703312192551881e-05, + "loss": 0.4758, + "step": 3277 + }, + { + "epoch": 0.27, + "learning_rate": 1.703119524714311e-05, + "loss": 0.503, + "step": 3278 + }, + { + "epoch": 0.27, + "learning_rate": 1.702926805242568e-05, + "loss": 0.508, + "step": 3279 + }, + { + "epoch": 0.27, + "learning_rate": 1.7027340341508043e-05, + "loss": 0.5148, + "step": 3280 + }, + { + "epoch": 0.27, + "learning_rate": 1.702541211453176e-05, + "loss": 0.469, + "step": 3281 + }, + { + "epoch": 0.27, + "learning_rate": 1.702348337163843e-05, + "loss": 0.4877, + "step": 3282 + }, + { + "epoch": 0.27, + "learning_rate": 1.7021554112969696e-05, + "loss": 0.5001, + "step": 3283 + }, + { + "epoch": 0.27, + "learning_rate": 1.701962433866723e-05, + "loss": 0.4817, + "step": 3284 + }, + { + "epoch": 0.27, + "learning_rate": 1.7017694048872756e-05, + "loss": 0.5152, + "step": 3285 + }, + { + "epoch": 0.27, + "learning_rate": 1.7015763243728014e-05, + "loss": 0.5012, + "step": 3286 + }, + { + "epoch": 0.28, + "learning_rate": 1.70138319233748e-05, + "loss": 0.4863, + "step": 3287 + }, + { + "epoch": 0.28, + "learning_rate": 1.7011900087954945e-05, + "loss": 0.4832, + "step": 3288 + }, + { + "epoch": 0.28, + "learning_rate": 1.7009967737610312e-05, + "loss": 0.5042, + "step": 3289 + }, + { + "epoch": 0.28, + "learning_rate": 1.70080348724828e-05, + "loss": 0.5057, + "step": 3290 + }, + { + "epoch": 0.28, + "learning_rate": 1.7006101492714362e-05, + "loss": 0.5154, + "step": 3291 + }, + { + "epoch": 0.28, + "learning_rate": 1.7004167598446967e-05, + "loss": 0.4931, + "step": 3292 + }, + { + "epoch": 0.28, + "learning_rate": 1.700223318982264e-05, + "loss": 0.5065, + "step": 3293 + }, + { + "epoch": 0.28, + "learning_rate": 1.7000298266983428e-05, + "loss": 0.4968, + "step": 3294 + }, + { + "epoch": 0.28, + "learning_rate": 1.699836283007143e-05, + "loss": 0.4878, + "step": 3295 + }, + { + "epoch": 0.28, + "learning_rate": 1.6996426879228775e-05, + "loss": 0.4811, + "step": 3296 + }, + { + "epoch": 0.28, + "learning_rate": 1.6994490414597627e-05, + "loss": 0.5043, + "step": 3297 + }, + { + "epoch": 0.28, + "learning_rate": 1.6992553436320195e-05, + "loss": 0.4804, + "step": 3298 + }, + { + "epoch": 0.28, + "learning_rate": 1.6990615944538725e-05, + "loss": 0.481, + "step": 3299 + }, + { + "epoch": 0.28, + "learning_rate": 1.6988677939395496e-05, + "loss": 0.4824, + "step": 3300 + }, + { + "epoch": 0.28, + "learning_rate": 1.698673942103283e-05, + "loss": 0.4943, + "step": 3301 + }, + { + "epoch": 0.28, + "learning_rate": 1.6984800389593076e-05, + "loss": 0.4982, + "step": 3302 + }, + { + "epoch": 0.28, + "learning_rate": 1.6982860845218637e-05, + "loss": 0.4838, + "step": 3303 + }, + { + "epoch": 0.28, + "learning_rate": 1.698092078805194e-05, + "loss": 0.5223, + "step": 3304 + }, + { + "epoch": 0.28, + "learning_rate": 1.6978980218235454e-05, + "loss": 0.4791, + "step": 3305 + }, + { + "epoch": 0.28, + "learning_rate": 1.697703913591169e-05, + "loss": 0.4881, + "step": 3306 + }, + { + "epoch": 0.28, + "learning_rate": 1.6975097541223195e-05, + "loss": 0.4824, + "step": 3307 + }, + { + "epoch": 0.28, + "learning_rate": 1.6973155434312544e-05, + "loss": 0.4667, + "step": 3308 + }, + { + "epoch": 0.28, + "learning_rate": 1.6971212815322365e-05, + "loss": 0.509, + "step": 3309 + }, + { + "epoch": 0.28, + "learning_rate": 1.696926968439531e-05, + "loss": 0.5058, + "step": 3310 + }, + { + "epoch": 0.28, + "learning_rate": 1.6967326041674076e-05, + "loss": 0.5017, + "step": 3311 + }, + { + "epoch": 0.28, + "learning_rate": 1.69653818873014e-05, + "loss": 0.4986, + "step": 3312 + }, + { + "epoch": 0.28, + "learning_rate": 1.6963437221420046e-05, + "loss": 0.5003, + "step": 3313 + }, + { + "epoch": 0.28, + "learning_rate": 1.6961492044172824e-05, + "loss": 0.4991, + "step": 3314 + }, + { + "epoch": 0.28, + "learning_rate": 1.6959546355702584e-05, + "loss": 0.495, + "step": 3315 + }, + { + "epoch": 0.28, + "learning_rate": 1.6957600156152206e-05, + "loss": 0.4848, + "step": 3316 + }, + { + "epoch": 0.28, + "learning_rate": 1.6955653445664612e-05, + "loss": 0.4958, + "step": 3317 + }, + { + "epoch": 0.28, + "learning_rate": 1.695370622438276e-05, + "loss": 0.4899, + "step": 3318 + }, + { + "epoch": 0.28, + "learning_rate": 1.6951758492449646e-05, + "loss": 0.4963, + "step": 3319 + }, + { + "epoch": 0.28, + "learning_rate": 1.6949810250008302e-05, + "loss": 0.4902, + "step": 3320 + }, + { + "epoch": 0.28, + "learning_rate": 1.69478614972018e-05, + "loss": 0.4889, + "step": 3321 + }, + { + "epoch": 0.28, + "learning_rate": 1.694591223417325e-05, + "loss": 0.4899, + "step": 3322 + }, + { + "epoch": 0.28, + "learning_rate": 1.694396246106579e-05, + "loss": 0.4928, + "step": 3323 + }, + { + "epoch": 0.28, + "learning_rate": 1.6942012178022613e-05, + "loss": 0.5079, + "step": 3324 + }, + { + "epoch": 0.28, + "learning_rate": 1.6940061385186936e-05, + "loss": 0.48, + "step": 3325 + }, + { + "epoch": 0.28, + "learning_rate": 1.6938110082702014e-05, + "loss": 0.4855, + "step": 3326 + }, + { + "epoch": 0.28, + "learning_rate": 1.6936158270711148e-05, + "loss": 0.4925, + "step": 3327 + }, + { + "epoch": 0.28, + "learning_rate": 1.6934205949357666e-05, + "loss": 0.4942, + "step": 3328 + }, + { + "epoch": 0.28, + "learning_rate": 1.693225311878494e-05, + "loss": 0.507, + "step": 3329 + }, + { + "epoch": 0.28, + "learning_rate": 1.6930299779136382e-05, + "loss": 0.4764, + "step": 3330 + }, + { + "epoch": 0.28, + "learning_rate": 1.6928345930555432e-05, + "loss": 0.49, + "step": 3331 + }, + { + "epoch": 0.28, + "learning_rate": 1.6926391573185576e-05, + "loss": 0.4877, + "step": 3332 + }, + { + "epoch": 0.28, + "learning_rate": 1.692443670717033e-05, + "loss": 0.491, + "step": 3333 + }, + { + "epoch": 0.28, + "learning_rate": 1.6922481332653248e-05, + "loss": 0.4942, + "step": 3334 + }, + { + "epoch": 0.28, + "learning_rate": 1.6920525449777937e-05, + "loss": 0.4978, + "step": 3335 + }, + { + "epoch": 0.28, + "learning_rate": 1.691856905868802e-05, + "loss": 0.4789, + "step": 3336 + }, + { + "epoch": 0.28, + "learning_rate": 1.6916612159527166e-05, + "loss": 0.4907, + "step": 3337 + }, + { + "epoch": 0.28, + "learning_rate": 1.6914654752439083e-05, + "loss": 0.5074, + "step": 3338 + }, + { + "epoch": 0.28, + "learning_rate": 1.691269683756752e-05, + "loss": 0.4883, + "step": 3339 + }, + { + "epoch": 0.28, + "learning_rate": 1.6910738415056245e-05, + "loss": 0.4935, + "step": 3340 + }, + { + "epoch": 0.28, + "learning_rate": 1.6908779485049093e-05, + "loss": 0.5326, + "step": 3341 + }, + { + "epoch": 0.28, + "learning_rate": 1.6906820047689907e-05, + "loss": 0.5007, + "step": 3342 + }, + { + "epoch": 0.28, + "learning_rate": 1.6904860103122587e-05, + "loss": 0.473, + "step": 3343 + }, + { + "epoch": 0.28, + "learning_rate": 1.6902899651491056e-05, + "loss": 0.4961, + "step": 3344 + }, + { + "epoch": 0.28, + "learning_rate": 1.690093869293929e-05, + "loss": 0.4919, + "step": 3345 + }, + { + "epoch": 0.28, + "learning_rate": 1.6898977227611288e-05, + "loss": 0.5026, + "step": 3346 + }, + { + "epoch": 0.28, + "learning_rate": 1.6897015255651093e-05, + "loss": 0.5022, + "step": 3347 + }, + { + "epoch": 0.28, + "learning_rate": 1.6895052777202784e-05, + "loss": 0.4966, + "step": 3348 + }, + { + "epoch": 0.28, + "learning_rate": 1.689308979241048e-05, + "loss": 0.511, + "step": 3349 + }, + { + "epoch": 0.28, + "learning_rate": 1.6891126301418334e-05, + "loss": 0.4936, + "step": 3350 + }, + { + "epoch": 0.28, + "learning_rate": 1.688916230437053e-05, + "loss": 0.4949, + "step": 3351 + }, + { + "epoch": 0.28, + "learning_rate": 1.68871978014113e-05, + "loss": 0.504, + "step": 3352 + }, + { + "epoch": 0.28, + "learning_rate": 1.6885232792684914e-05, + "loss": 0.4937, + "step": 3353 + }, + { + "epoch": 0.28, + "learning_rate": 1.6883267278335668e-05, + "loss": 0.5026, + "step": 3354 + }, + { + "epoch": 0.28, + "learning_rate": 1.68813012585079e-05, + "loss": 0.4734, + "step": 3355 + }, + { + "epoch": 0.28, + "learning_rate": 1.687933473334599e-05, + "loss": 0.4808, + "step": 3356 + }, + { + "epoch": 0.28, + "learning_rate": 1.6877367702994353e-05, + "loss": 0.4932, + "step": 3357 + }, + { + "epoch": 0.28, + "learning_rate": 1.6875400167597433e-05, + "loss": 0.5041, + "step": 3358 + }, + { + "epoch": 0.28, + "learning_rate": 1.6873432127299725e-05, + "loss": 0.4932, + "step": 3359 + }, + { + "epoch": 0.28, + "learning_rate": 1.6871463582245753e-05, + "loss": 0.4834, + "step": 3360 + }, + { + "epoch": 0.28, + "learning_rate": 1.6869494532580072e-05, + "loss": 0.499, + "step": 3361 + }, + { + "epoch": 0.28, + "learning_rate": 1.6867524978447286e-05, + "loss": 0.4741, + "step": 3362 + }, + { + "epoch": 0.28, + "learning_rate": 1.6865554919992026e-05, + "loss": 0.5121, + "step": 3363 + }, + { + "epoch": 0.28, + "learning_rate": 1.6863584357358974e-05, + "loss": 0.5057, + "step": 3364 + }, + { + "epoch": 0.28, + "learning_rate": 1.686161329069283e-05, + "loss": 0.4854, + "step": 3365 + }, + { + "epoch": 0.28, + "learning_rate": 1.685964172013835e-05, + "loss": 0.4994, + "step": 3366 + }, + { + "epoch": 0.28, + "learning_rate": 1.685766964584031e-05, + "loss": 0.4862, + "step": 3367 + }, + { + "epoch": 0.28, + "learning_rate": 1.685569706794354e-05, + "loss": 0.4974, + "step": 3368 + }, + { + "epoch": 0.28, + "learning_rate": 1.6853723986592885e-05, + "loss": 0.5175, + "step": 3369 + }, + { + "epoch": 0.28, + "learning_rate": 1.685175040193325e-05, + "loss": 0.5038, + "step": 3370 + }, + { + "epoch": 0.28, + "learning_rate": 1.6849776314109568e-05, + "loss": 0.5083, + "step": 3371 + }, + { + "epoch": 0.28, + "learning_rate": 1.6847801723266798e-05, + "loss": 0.5001, + "step": 3372 + }, + { + "epoch": 0.28, + "learning_rate": 1.6845826629549952e-05, + "loss": 0.5107, + "step": 3373 + }, + { + "epoch": 0.28, + "learning_rate": 1.6843851033104076e-05, + "loss": 0.5127, + "step": 3374 + }, + { + "epoch": 0.28, + "learning_rate": 1.6841874934074244e-05, + "loss": 0.491, + "step": 3375 + }, + { + "epoch": 0.28, + "learning_rate": 1.6839898332605575e-05, + "loss": 0.495, + "step": 3376 + }, + { + "epoch": 0.28, + "learning_rate": 1.683792122884322e-05, + "loss": 0.4971, + "step": 3377 + }, + { + "epoch": 0.28, + "learning_rate": 1.6835943622932377e-05, + "loss": 0.5114, + "step": 3378 + }, + { + "epoch": 0.28, + "learning_rate": 1.6833965515018257e-05, + "loss": 0.4907, + "step": 3379 + }, + { + "epoch": 0.28, + "learning_rate": 1.683198690524614e-05, + "loss": 0.519, + "step": 3380 + }, + { + "epoch": 0.28, + "learning_rate": 1.6830007793761323e-05, + "loss": 0.4936, + "step": 3381 + }, + { + "epoch": 0.28, + "learning_rate": 1.682802818070914e-05, + "loss": 0.4878, + "step": 3382 + }, + { + "epoch": 0.28, + "learning_rate": 1.6826048066234967e-05, + "loss": 0.4965, + "step": 3383 + }, + { + "epoch": 0.28, + "learning_rate": 1.6824067450484214e-05, + "loss": 0.5071, + "step": 3384 + }, + { + "epoch": 0.28, + "learning_rate": 1.682208633360233e-05, + "loss": 0.4647, + "step": 3385 + }, + { + "epoch": 0.28, + "learning_rate": 1.6820104715734803e-05, + "loss": 0.484, + "step": 3386 + }, + { + "epoch": 0.28, + "learning_rate": 1.6818122597027152e-05, + "loss": 0.4863, + "step": 3387 + }, + { + "epoch": 0.28, + "learning_rate": 1.681613997762494e-05, + "loss": 0.4965, + "step": 3388 + }, + { + "epoch": 0.28, + "learning_rate": 1.6814156857673753e-05, + "loss": 0.4948, + "step": 3389 + }, + { + "epoch": 0.28, + "learning_rate": 1.6812173237319232e-05, + "loss": 0.4834, + "step": 3390 + }, + { + "epoch": 0.28, + "learning_rate": 1.6810189116707042e-05, + "loss": 0.5055, + "step": 3391 + }, + { + "epoch": 0.28, + "learning_rate": 1.6808204495982887e-05, + "loss": 0.5029, + "step": 3392 + }, + { + "epoch": 0.28, + "learning_rate": 1.6806219375292513e-05, + "loss": 0.495, + "step": 3393 + }, + { + "epoch": 0.28, + "learning_rate": 1.68042337547817e-05, + "loss": 0.4815, + "step": 3394 + }, + { + "epoch": 0.28, + "learning_rate": 1.6802247634596256e-05, + "loss": 0.4937, + "step": 3395 + }, + { + "epoch": 0.28, + "learning_rate": 1.680026101488204e-05, + "loss": 0.5125, + "step": 3396 + }, + { + "epoch": 0.28, + "learning_rate": 1.679827389578494e-05, + "loss": 0.4883, + "step": 3397 + }, + { + "epoch": 0.28, + "learning_rate": 1.6796286277450882e-05, + "loss": 0.503, + "step": 3398 + }, + { + "epoch": 0.28, + "learning_rate": 1.6794298160025822e-05, + "loss": 0.4779, + "step": 3399 + }, + { + "epoch": 0.28, + "learning_rate": 1.6792309543655774e-05, + "loss": 0.4657, + "step": 3400 + }, + { + "epoch": 0.28, + "learning_rate": 1.6790320428486757e-05, + "loss": 0.5017, + "step": 3401 + }, + { + "epoch": 0.28, + "learning_rate": 1.6788330814664856e-05, + "loss": 0.4918, + "step": 3402 + }, + { + "epoch": 0.28, + "learning_rate": 1.678634070233617e-05, + "loss": 0.4799, + "step": 3403 + }, + { + "epoch": 0.28, + "learning_rate": 1.6784350091646852e-05, + "loss": 0.4953, + "step": 3404 + }, + { + "epoch": 0.28, + "learning_rate": 1.6782358982743084e-05, + "loss": 0.5107, + "step": 3405 + }, + { + "epoch": 0.28, + "learning_rate": 1.6780367375771075e-05, + "loss": 0.4833, + "step": 3406 + }, + { + "epoch": 0.29, + "learning_rate": 1.6778375270877095e-05, + "loss": 0.493, + "step": 3407 + }, + { + "epoch": 0.29, + "learning_rate": 1.6776382668207424e-05, + "loss": 0.4983, + "step": 3408 + }, + { + "epoch": 0.29, + "learning_rate": 1.6774389567908394e-05, + "loss": 0.482, + "step": 3409 + }, + { + "epoch": 0.29, + "learning_rate": 1.677239597012638e-05, + "loss": 0.502, + "step": 3410 + }, + { + "epoch": 0.29, + "learning_rate": 1.6770401875007766e-05, + "loss": 0.5169, + "step": 3411 + }, + { + "epoch": 0.29, + "learning_rate": 1.6768407282699e-05, + "loss": 0.4878, + "step": 3412 + }, + { + "epoch": 0.29, + "learning_rate": 1.6766412193346555e-05, + "loss": 0.5064, + "step": 3413 + }, + { + "epoch": 0.29, + "learning_rate": 1.6764416607096942e-05, + "loss": 0.5101, + "step": 3414 + }, + { + "epoch": 0.29, + "learning_rate": 1.6762420524096712e-05, + "loss": 0.5111, + "step": 3415 + }, + { + "epoch": 0.29, + "learning_rate": 1.6760423944492442e-05, + "loss": 0.4933, + "step": 3416 + }, + { + "epoch": 0.29, + "learning_rate": 1.6758426868430758e-05, + "loss": 0.4991, + "step": 3417 + }, + { + "epoch": 0.29, + "learning_rate": 1.6756429296058314e-05, + "loss": 0.5079, + "step": 3418 + }, + { + "epoch": 0.29, + "learning_rate": 1.6754431227521806e-05, + "loss": 0.4799, + "step": 3419 + }, + { + "epoch": 0.29, + "learning_rate": 1.6752432662967958e-05, + "loss": 0.4992, + "step": 3420 + }, + { + "epoch": 0.29, + "learning_rate": 1.6750433602543546e-05, + "loss": 0.5113, + "step": 3421 + }, + { + "epoch": 0.29, + "learning_rate": 1.674843404639537e-05, + "loss": 0.4779, + "step": 3422 + }, + { + "epoch": 0.29, + "learning_rate": 1.6746433994670258e-05, + "loss": 0.509, + "step": 3423 + }, + { + "epoch": 0.29, + "learning_rate": 1.6744433447515098e-05, + "loss": 0.4972, + "step": 3424 + }, + { + "epoch": 0.29, + "learning_rate": 1.67424324050768e-05, + "loss": 0.4903, + "step": 3425 + }, + { + "epoch": 0.29, + "learning_rate": 1.6740430867502307e-05, + "loss": 0.4894, + "step": 3426 + }, + { + "epoch": 0.29, + "learning_rate": 1.6738428834938606e-05, + "loss": 0.4954, + "step": 3427 + }, + { + "epoch": 0.29, + "learning_rate": 1.6736426307532722e-05, + "loss": 0.4985, + "step": 3428 + }, + { + "epoch": 0.29, + "learning_rate": 1.6734423285431705e-05, + "loss": 0.4952, + "step": 3429 + }, + { + "epoch": 0.29, + "learning_rate": 1.6732419768782656e-05, + "loss": 0.5189, + "step": 3430 + }, + { + "epoch": 0.29, + "learning_rate": 1.6730415757732702e-05, + "loss": 0.4859, + "step": 3431 + }, + { + "epoch": 0.29, + "learning_rate": 1.6728411252429006e-05, + "loss": 0.5037, + "step": 3432 + }, + { + "epoch": 0.29, + "learning_rate": 1.672640625301877e-05, + "loss": 0.4977, + "step": 3433 + }, + { + "epoch": 0.29, + "learning_rate": 1.6724400759649243e-05, + "loss": 0.4831, + "step": 3434 + }, + { + "epoch": 0.29, + "learning_rate": 1.672239477246769e-05, + "loss": 0.4928, + "step": 3435 + }, + { + "epoch": 0.29, + "learning_rate": 1.6720388291621423e-05, + "loss": 0.4899, + "step": 3436 + }, + { + "epoch": 0.29, + "learning_rate": 1.6718381317257793e-05, + "loss": 0.4841, + "step": 3437 + }, + { + "epoch": 0.29, + "learning_rate": 1.6716373849524187e-05, + "loss": 0.5012, + "step": 3438 + }, + { + "epoch": 0.29, + "learning_rate": 1.671436588856802e-05, + "loss": 0.5064, + "step": 3439 + }, + { + "epoch": 0.29, + "learning_rate": 1.6712357434536747e-05, + "loss": 0.4881, + "step": 3440 + }, + { + "epoch": 0.29, + "learning_rate": 1.6710348487577863e-05, + "loss": 0.4914, + "step": 3441 + }, + { + "epoch": 0.29, + "learning_rate": 1.6708339047838897e-05, + "loss": 0.4985, + "step": 3442 + }, + { + "epoch": 0.29, + "learning_rate": 1.6706329115467412e-05, + "loss": 0.4928, + "step": 3443 + }, + { + "epoch": 0.29, + "learning_rate": 1.670431869061101e-05, + "loss": 0.4741, + "step": 3444 + }, + { + "epoch": 0.29, + "learning_rate": 1.6702307773417334e-05, + "loss": 0.4799, + "step": 3445 + }, + { + "epoch": 0.29, + "learning_rate": 1.6700296364034048e-05, + "loss": 0.5049, + "step": 3446 + }, + { + "epoch": 0.29, + "learning_rate": 1.6698284462608866e-05, + "loss": 0.5034, + "step": 3447 + }, + { + "epoch": 0.29, + "learning_rate": 1.6696272069289533e-05, + "loss": 0.4924, + "step": 3448 + }, + { + "epoch": 0.29, + "learning_rate": 1.6694259184223833e-05, + "loss": 0.5037, + "step": 3449 + }, + { + "epoch": 0.29, + "learning_rate": 1.6692245807559578e-05, + "loss": 0.4939, + "step": 3450 + }, + { + "epoch": 0.29, + "learning_rate": 1.669023193944463e-05, + "loss": 0.4952, + "step": 3451 + }, + { + "epoch": 0.29, + "learning_rate": 1.668821758002688e-05, + "loss": 0.4887, + "step": 3452 + }, + { + "epoch": 0.29, + "learning_rate": 1.668620272945424e-05, + "loss": 0.5063, + "step": 3453 + }, + { + "epoch": 0.29, + "learning_rate": 1.6684187387874686e-05, + "loss": 0.4739, + "step": 3454 + }, + { + "epoch": 0.29, + "learning_rate": 1.668217155543621e-05, + "loss": 0.5013, + "step": 3455 + }, + { + "epoch": 0.29, + "learning_rate": 1.668015523228685e-05, + "loss": 0.4862, + "step": 3456 + }, + { + "epoch": 0.29, + "learning_rate": 1.6678138418574673e-05, + "loss": 0.4973, + "step": 3457 + }, + { + "epoch": 0.29, + "learning_rate": 1.6676121114447784e-05, + "loss": 0.4797, + "step": 3458 + }, + { + "epoch": 0.29, + "learning_rate": 1.6674103320054335e-05, + "loss": 0.5063, + "step": 3459 + }, + { + "epoch": 0.29, + "learning_rate": 1.6672085035542497e-05, + "loss": 0.4745, + "step": 3460 + }, + { + "epoch": 0.29, + "learning_rate": 1.667006626106048e-05, + "loss": 0.4841, + "step": 3461 + }, + { + "epoch": 0.29, + "learning_rate": 1.6668046996756544e-05, + "loss": 0.4975, + "step": 3462 + }, + { + "epoch": 0.29, + "learning_rate": 1.6666027242778972e-05, + "loss": 0.5235, + "step": 3463 + }, + { + "epoch": 0.29, + "learning_rate": 1.666400699927608e-05, + "loss": 0.4883, + "step": 3464 + }, + { + "epoch": 0.29, + "learning_rate": 1.6661986266396235e-05, + "loss": 0.5063, + "step": 3465 + }, + { + "epoch": 0.29, + "learning_rate": 1.6659965044287826e-05, + "loss": 0.4858, + "step": 3466 + }, + { + "epoch": 0.29, + "learning_rate": 1.6657943333099287e-05, + "loss": 0.4754, + "step": 3467 + }, + { + "epoch": 0.29, + "learning_rate": 1.6655921132979082e-05, + "loss": 0.4743, + "step": 3468 + }, + { + "epoch": 0.29, + "learning_rate": 1.6653898444075713e-05, + "loss": 0.4887, + "step": 3469 + }, + { + "epoch": 0.29, + "learning_rate": 1.6651875266537718e-05, + "loss": 0.4948, + "step": 3470 + }, + { + "epoch": 0.29, + "learning_rate": 1.664985160051367e-05, + "loss": 0.4873, + "step": 3471 + }, + { + "epoch": 0.29, + "learning_rate": 1.6647827446152183e-05, + "loss": 0.486, + "step": 3472 + }, + { + "epoch": 0.29, + "learning_rate": 1.6645802803601893e-05, + "loss": 0.4984, + "step": 3473 + }, + { + "epoch": 0.29, + "learning_rate": 1.664377767301149e-05, + "loss": 0.5056, + "step": 3474 + }, + { + "epoch": 0.29, + "learning_rate": 1.664175205452969e-05, + "loss": 0.4926, + "step": 3475 + }, + { + "epoch": 0.29, + "learning_rate": 1.663972594830524e-05, + "loss": 0.5159, + "step": 3476 + }, + { + "epoch": 0.29, + "learning_rate": 1.6637699354486936e-05, + "loss": 0.5252, + "step": 3477 + }, + { + "epoch": 0.29, + "learning_rate": 1.6635672273223597e-05, + "loss": 0.4872, + "step": 3478 + }, + { + "epoch": 0.29, + "learning_rate": 1.663364470466409e-05, + "loss": 0.4877, + "step": 3479 + }, + { + "epoch": 0.29, + "learning_rate": 1.6631616648957303e-05, + "loss": 0.4879, + "step": 3480 + }, + { + "epoch": 0.29, + "learning_rate": 1.6629588106252173e-05, + "loss": 0.4756, + "step": 3481 + }, + { + "epoch": 0.29, + "learning_rate": 1.6627559076697672e-05, + "loss": 0.5409, + "step": 3482 + }, + { + "epoch": 0.29, + "learning_rate": 1.6625529560442793e-05, + "loss": 0.5017, + "step": 3483 + }, + { + "epoch": 0.29, + "learning_rate": 1.6623499557636584e-05, + "loss": 0.4925, + "step": 3484 + }, + { + "epoch": 0.29, + "learning_rate": 1.6621469068428114e-05, + "loss": 0.4936, + "step": 3485 + }, + { + "epoch": 0.29, + "learning_rate": 1.66194380929665e-05, + "loss": 0.5126, + "step": 3486 + }, + { + "epoch": 0.29, + "learning_rate": 1.6617406631400884e-05, + "loss": 0.4967, + "step": 3487 + }, + { + "epoch": 0.29, + "learning_rate": 1.6615374683880445e-05, + "loss": 0.4864, + "step": 3488 + }, + { + "epoch": 0.29, + "learning_rate": 1.6613342250554406e-05, + "loss": 0.4922, + "step": 3489 + }, + { + "epoch": 0.29, + "learning_rate": 1.6611309331572022e-05, + "loss": 0.4962, + "step": 3490 + }, + { + "epoch": 0.29, + "learning_rate": 1.6609275927082577e-05, + "loss": 0.4899, + "step": 3491 + }, + { + "epoch": 0.29, + "learning_rate": 1.66072420372354e-05, + "loss": 0.4947, + "step": 3492 + }, + { + "epoch": 0.29, + "learning_rate": 1.660520766217985e-05, + "loss": 0.5001, + "step": 3493 + }, + { + "epoch": 0.29, + "learning_rate": 1.6603172802065317e-05, + "loss": 0.5018, + "step": 3494 + }, + { + "epoch": 0.29, + "learning_rate": 1.6601137457041242e-05, + "loss": 0.5025, + "step": 3495 + }, + { + "epoch": 0.29, + "learning_rate": 1.6599101627257087e-05, + "loss": 0.4887, + "step": 3496 + }, + { + "epoch": 0.29, + "learning_rate": 1.6597065312862358e-05, + "loss": 0.4875, + "step": 3497 + }, + { + "epoch": 0.29, + "learning_rate": 1.659502851400659e-05, + "loss": 0.5023, + "step": 3498 + }, + { + "epoch": 0.29, + "learning_rate": 1.6592991230839355e-05, + "loss": 0.4966, + "step": 3499 + }, + { + "epoch": 0.29, + "learning_rate": 1.659095346351027e-05, + "loss": 0.5032, + "step": 3500 + }, + { + "epoch": 0.29, + "learning_rate": 1.6588915212168977e-05, + "loss": 0.4823, + "step": 3501 + }, + { + "epoch": 0.29, + "learning_rate": 1.658687647696516e-05, + "loss": 0.5014, + "step": 3502 + }, + { + "epoch": 0.29, + "learning_rate": 1.658483725804853e-05, + "loss": 0.4557, + "step": 3503 + }, + { + "epoch": 0.29, + "learning_rate": 1.6582797555568834e-05, + "loss": 0.5108, + "step": 3504 + }, + { + "epoch": 0.29, + "learning_rate": 1.658075736967587e-05, + "loss": 0.5026, + "step": 3505 + }, + { + "epoch": 0.29, + "learning_rate": 1.6578716700519454e-05, + "loss": 0.5017, + "step": 3506 + }, + { + "epoch": 0.29, + "learning_rate": 1.657667554824945e-05, + "loss": 0.4901, + "step": 3507 + }, + { + "epoch": 0.29, + "learning_rate": 1.6574633913015742e-05, + "loss": 0.4907, + "step": 3508 + }, + { + "epoch": 0.29, + "learning_rate": 1.657259179496827e-05, + "loss": 0.4864, + "step": 3509 + }, + { + "epoch": 0.29, + "learning_rate": 1.6570549194256995e-05, + "loss": 0.495, + "step": 3510 + }, + { + "epoch": 0.29, + "learning_rate": 1.6568506111031913e-05, + "loss": 0.5021, + "step": 3511 + }, + { + "epoch": 0.29, + "learning_rate": 1.6566462545443066e-05, + "loss": 0.5074, + "step": 3512 + }, + { + "epoch": 0.29, + "learning_rate": 1.656441849764052e-05, + "loss": 0.4989, + "step": 3513 + }, + { + "epoch": 0.29, + "learning_rate": 1.6562373967774382e-05, + "loss": 0.509, + "step": 3514 + }, + { + "epoch": 0.29, + "learning_rate": 1.6560328955994796e-05, + "loss": 0.5201, + "step": 3515 + }, + { + "epoch": 0.29, + "learning_rate": 1.655828346245194e-05, + "loss": 0.5027, + "step": 3516 + }, + { + "epoch": 0.29, + "learning_rate": 1.655623748729602e-05, + "loss": 0.4831, + "step": 3517 + }, + { + "epoch": 0.29, + "learning_rate": 1.655419103067729e-05, + "loss": 0.5112, + "step": 3518 + }, + { + "epoch": 0.29, + "learning_rate": 1.6552144092746032e-05, + "loss": 0.4874, + "step": 3519 + }, + { + "epoch": 0.29, + "learning_rate": 1.6550096673652565e-05, + "loss": 0.4991, + "step": 3520 + }, + { + "epoch": 0.29, + "learning_rate": 1.654804877354724e-05, + "loss": 0.4899, + "step": 3521 + }, + { + "epoch": 0.29, + "learning_rate": 1.654600039258045e-05, + "loss": 0.5151, + "step": 3522 + }, + { + "epoch": 0.29, + "learning_rate": 1.6543951530902618e-05, + "loss": 0.5163, + "step": 3523 + }, + { + "epoch": 0.29, + "learning_rate": 1.6541902188664206e-05, + "loss": 0.4763, + "step": 3524 + }, + { + "epoch": 0.29, + "learning_rate": 1.6539852366015702e-05, + "loss": 0.5012, + "step": 3525 + }, + { + "epoch": 0.3, + "learning_rate": 1.6537802063107646e-05, + "loss": 0.4732, + "step": 3526 + }, + { + "epoch": 0.3, + "learning_rate": 1.6535751280090598e-05, + "loss": 0.51, + "step": 3527 + }, + { + "epoch": 0.3, + "learning_rate": 1.6533700017115162e-05, + "loss": 0.5077, + "step": 3528 + }, + { + "epoch": 0.3, + "learning_rate": 1.653164827433197e-05, + "loss": 0.5029, + "step": 3529 + }, + { + "epoch": 0.3, + "learning_rate": 1.6529596051891696e-05, + "loss": 0.4791, + "step": 3530 + }, + { + "epoch": 0.3, + "learning_rate": 1.6527543349945047e-05, + "loss": 0.5035, + "step": 3531 + }, + { + "epoch": 0.3, + "learning_rate": 1.6525490168642765e-05, + "loss": 0.4892, + "step": 3532 + }, + { + "epoch": 0.3, + "learning_rate": 1.6523436508135624e-05, + "loss": 0.4915, + "step": 3533 + }, + { + "epoch": 0.3, + "learning_rate": 1.6521382368574442e-05, + "loss": 0.4816, + "step": 3534 + }, + { + "epoch": 0.3, + "learning_rate": 1.651932775011006e-05, + "loss": 0.481, + "step": 3535 + }, + { + "epoch": 0.3, + "learning_rate": 1.6517272652893367e-05, + "loss": 0.4885, + "step": 3536 + }, + { + "epoch": 0.3, + "learning_rate": 1.6515217077075276e-05, + "loss": 0.506, + "step": 3537 + }, + { + "epoch": 0.3, + "learning_rate": 1.651316102280674e-05, + "loss": 0.4849, + "step": 3538 + }, + { + "epoch": 0.3, + "learning_rate": 1.6511104490238753e-05, + "loss": 0.5038, + "step": 3539 + }, + { + "epoch": 0.3, + "learning_rate": 1.6509047479522332e-05, + "loss": 0.5172, + "step": 3540 + }, + { + "epoch": 0.3, + "learning_rate": 1.650698999080854e-05, + "loss": 0.4906, + "step": 3541 + }, + { + "epoch": 0.3, + "learning_rate": 1.6504932024248462e-05, + "loss": 0.4895, + "step": 3542 + }, + { + "epoch": 0.3, + "learning_rate": 1.6502873579993238e-05, + "loss": 0.4769, + "step": 3543 + }, + { + "epoch": 0.3, + "learning_rate": 1.6500814658194024e-05, + "loss": 0.5035, + "step": 3544 + }, + { + "epoch": 0.3, + "learning_rate": 1.649875525900202e-05, + "loss": 0.5003, + "step": 3545 + }, + { + "epoch": 0.3, + "learning_rate": 1.649669538256846e-05, + "loss": 0.4854, + "step": 3546 + }, + { + "epoch": 0.3, + "learning_rate": 1.6494635029044613e-05, + "loss": 0.4941, + "step": 3547 + }, + { + "epoch": 0.3, + "learning_rate": 1.649257419858178e-05, + "loss": 0.4851, + "step": 3548 + }, + { + "epoch": 0.3, + "learning_rate": 1.6490512891331304e-05, + "loss": 0.4964, + "step": 3549 + }, + { + "epoch": 0.3, + "learning_rate": 1.6488451107444556e-05, + "loss": 0.5009, + "step": 3550 + }, + { + "epoch": 0.3, + "learning_rate": 1.648638884707295e-05, + "loss": 0.496, + "step": 3551 + }, + { + "epoch": 0.3, + "learning_rate": 1.6484326110367924e-05, + "loss": 0.5007, + "step": 3552 + }, + { + "epoch": 0.3, + "learning_rate": 1.648226289748096e-05, + "loss": 0.5075, + "step": 3553 + }, + { + "epoch": 0.3, + "learning_rate": 1.648019920856357e-05, + "loss": 0.4816, + "step": 3554 + }, + { + "epoch": 0.3, + "learning_rate": 1.6478135043767303e-05, + "loss": 0.5059, + "step": 3555 + }, + { + "epoch": 0.3, + "learning_rate": 1.647607040324374e-05, + "loss": 0.4913, + "step": 3556 + }, + { + "epoch": 0.3, + "learning_rate": 1.6474005287144507e-05, + "loss": 0.4945, + "step": 3557 + }, + { + "epoch": 0.3, + "learning_rate": 1.647193969562125e-05, + "loss": 0.4799, + "step": 3558 + }, + { + "epoch": 0.3, + "learning_rate": 1.6469873628825665e-05, + "loss": 0.5039, + "step": 3559 + }, + { + "epoch": 0.3, + "learning_rate": 1.6467807086909468e-05, + "loss": 0.4956, + "step": 3560 + }, + { + "epoch": 0.3, + "learning_rate": 1.646574007002442e-05, + "loss": 0.5098, + "step": 3561 + }, + { + "epoch": 0.3, + "learning_rate": 1.6463672578322315e-05, + "loss": 0.4929, + "step": 3562 + }, + { + "epoch": 0.3, + "learning_rate": 1.646160461195498e-05, + "loss": 0.4958, + "step": 3563 + }, + { + "epoch": 0.3, + "learning_rate": 1.6459536171074278e-05, + "loss": 0.4969, + "step": 3564 + }, + { + "epoch": 0.3, + "learning_rate": 1.6457467255832108e-05, + "loss": 0.5093, + "step": 3565 + }, + { + "epoch": 0.3, + "learning_rate": 1.64553978663804e-05, + "loss": 0.4717, + "step": 3566 + }, + { + "epoch": 0.3, + "learning_rate": 1.645332800287112e-05, + "loss": 0.498, + "step": 3567 + }, + { + "epoch": 0.3, + "learning_rate": 1.645125766545628e-05, + "loss": 0.5006, + "step": 3568 + }, + { + "epoch": 0.3, + "learning_rate": 1.6449186854287903e-05, + "loss": 0.5093, + "step": 3569 + }, + { + "epoch": 0.3, + "learning_rate": 1.644711556951807e-05, + "loss": 0.5111, + "step": 3570 + }, + { + "epoch": 0.3, + "learning_rate": 1.6445043811298887e-05, + "loss": 0.5057, + "step": 3571 + }, + { + "epoch": 0.3, + "learning_rate": 1.644297157978249e-05, + "loss": 0.4916, + "step": 3572 + }, + { + "epoch": 0.3, + "learning_rate": 1.644089887512106e-05, + "loss": 0.4835, + "step": 3573 + }, + { + "epoch": 0.3, + "learning_rate": 1.6438825697466808e-05, + "loss": 0.4892, + "step": 3574 + }, + { + "epoch": 0.3, + "learning_rate": 1.6436752046971975e-05, + "loss": 0.4817, + "step": 3575 + }, + { + "epoch": 0.3, + "learning_rate": 1.6434677923788848e-05, + "loss": 0.483, + "step": 3576 + }, + { + "epoch": 0.3, + "learning_rate": 1.6432603328069732e-05, + "loss": 0.5143, + "step": 3577 + }, + { + "epoch": 0.3, + "learning_rate": 1.643052825996699e-05, + "loss": 0.507, + "step": 3578 + }, + { + "epoch": 0.3, + "learning_rate": 1.6428452719632994e-05, + "loss": 0.4962, + "step": 3579 + }, + { + "epoch": 0.3, + "learning_rate": 1.642637670722017e-05, + "loss": 0.5072, + "step": 3580 + }, + { + "epoch": 0.3, + "learning_rate": 1.642430022288097e-05, + "loss": 0.4931, + "step": 3581 + }, + { + "epoch": 0.3, + "learning_rate": 1.6422223266767883e-05, + "loss": 0.4838, + "step": 3582 + }, + { + "epoch": 0.3, + "learning_rate": 1.642014583903343e-05, + "loss": 0.5034, + "step": 3583 + }, + { + "epoch": 0.3, + "learning_rate": 1.641806793983017e-05, + "loss": 0.5004, + "step": 3584 + }, + { + "epoch": 0.3, + "learning_rate": 1.6415989569310698e-05, + "loss": 0.4913, + "step": 3585 + }, + { + "epoch": 0.3, + "learning_rate": 1.6413910727627637e-05, + "loss": 0.4919, + "step": 3586 + }, + { + "epoch": 0.3, + "learning_rate": 1.6411831414933647e-05, + "loss": 0.5063, + "step": 3587 + }, + { + "epoch": 0.3, + "learning_rate": 1.6409751631381428e-05, + "loss": 0.481, + "step": 3588 + }, + { + "epoch": 0.3, + "learning_rate": 1.640767137712371e-05, + "loss": 0.5164, + "step": 3589 + }, + { + "epoch": 0.3, + "learning_rate": 1.6405590652313256e-05, + "loss": 0.4764, + "step": 3590 + }, + { + "epoch": 0.3, + "learning_rate": 1.640350945710287e-05, + "loss": 0.4895, + "step": 3591 + }, + { + "epoch": 0.3, + "learning_rate": 1.640142779164538e-05, + "loss": 0.5138, + "step": 3592 + }, + { + "epoch": 0.3, + "learning_rate": 1.6399345656093663e-05, + "loss": 0.476, + "step": 3593 + }, + { + "epoch": 0.3, + "learning_rate": 1.6397263050600615e-05, + "loss": 0.4773, + "step": 3594 + }, + { + "epoch": 0.3, + "learning_rate": 1.6395179975319178e-05, + "loss": 0.5097, + "step": 3595 + }, + { + "epoch": 0.3, + "learning_rate": 1.6393096430402323e-05, + "loss": 0.5019, + "step": 3596 + }, + { + "epoch": 0.3, + "learning_rate": 1.6391012416003053e-05, + "loss": 0.4923, + "step": 3597 + }, + { + "epoch": 0.3, + "learning_rate": 1.638892793227442e-05, + "loss": 0.4851, + "step": 3598 + }, + { + "epoch": 0.3, + "learning_rate": 1.6386842979369487e-05, + "loss": 0.4981, + "step": 3599 + }, + { + "epoch": 0.3, + "learning_rate": 1.6384757557441373e-05, + "loss": 0.5019, + "step": 3600 + }, + { + "epoch": 0.3, + "learning_rate": 1.6382671666643223e-05, + "loss": 0.492, + "step": 3601 + }, + { + "epoch": 0.3, + "learning_rate": 1.638058530712821e-05, + "loss": 0.4817, + "step": 3602 + }, + { + "epoch": 0.3, + "learning_rate": 1.6378498479049553e-05, + "loss": 0.5039, + "step": 3603 + }, + { + "epoch": 0.3, + "learning_rate": 1.6376411182560498e-05, + "loss": 0.5044, + "step": 3604 + }, + { + "epoch": 0.3, + "learning_rate": 1.6374323417814325e-05, + "loss": 0.5089, + "step": 3605 + }, + { + "epoch": 0.3, + "learning_rate": 1.6372235184964357e-05, + "loss": 0.4915, + "step": 3606 + }, + { + "epoch": 0.3, + "learning_rate": 1.6370146484163935e-05, + "loss": 0.4752, + "step": 3607 + }, + { + "epoch": 0.3, + "learning_rate": 1.6368057315566454e-05, + "loss": 0.5043, + "step": 3608 + }, + { + "epoch": 0.3, + "learning_rate": 1.636596767932533e-05, + "loss": 0.5013, + "step": 3609 + }, + { + "epoch": 0.3, + "learning_rate": 1.636387757559402e-05, + "loss": 0.482, + "step": 3610 + }, + { + "epoch": 0.3, + "learning_rate": 1.6361787004526006e-05, + "loss": 0.524, + "step": 3611 + }, + { + "epoch": 0.3, + "learning_rate": 1.635969596627482e-05, + "loss": 0.5078, + "step": 3612 + }, + { + "epoch": 0.3, + "learning_rate": 1.635760446099401e-05, + "loss": 0.4964, + "step": 3613 + }, + { + "epoch": 0.3, + "learning_rate": 1.6355512488837173e-05, + "loss": 0.4827, + "step": 3614 + }, + { + "epoch": 0.3, + "learning_rate": 1.6353420049957932e-05, + "loss": 0.4924, + "step": 3615 + }, + { + "epoch": 0.3, + "learning_rate": 1.6351327144509954e-05, + "loss": 0.5235, + "step": 3616 + }, + { + "epoch": 0.3, + "learning_rate": 1.6349233772646923e-05, + "loss": 0.4919, + "step": 3617 + }, + { + "epoch": 0.3, + "learning_rate": 1.6347139934522572e-05, + "loss": 0.5046, + "step": 3618 + }, + { + "epoch": 0.3, + "learning_rate": 1.6345045630290664e-05, + "loss": 0.5007, + "step": 3619 + }, + { + "epoch": 0.3, + "learning_rate": 1.6342950860105e-05, + "loss": 0.4592, + "step": 3620 + }, + { + "epoch": 0.3, + "learning_rate": 1.63408556241194e-05, + "loss": 0.4886, + "step": 3621 + }, + { + "epoch": 0.3, + "learning_rate": 1.633875992248774e-05, + "loss": 0.4956, + "step": 3622 + }, + { + "epoch": 0.3, + "learning_rate": 1.633666375536392e-05, + "loss": 0.4919, + "step": 3623 + }, + { + "epoch": 0.3, + "learning_rate": 1.6334567122901862e-05, + "loss": 0.5073, + "step": 3624 + }, + { + "epoch": 0.3, + "learning_rate": 1.633247002525555e-05, + "loss": 0.5198, + "step": 3625 + }, + { + "epoch": 0.3, + "learning_rate": 1.6330372462578972e-05, + "loss": 0.481, + "step": 3626 + }, + { + "epoch": 0.3, + "learning_rate": 1.6328274435026174e-05, + "loss": 0.4838, + "step": 3627 + }, + { + "epoch": 0.3, + "learning_rate": 1.6326175942751222e-05, + "loss": 0.4937, + "step": 3628 + }, + { + "epoch": 0.3, + "learning_rate": 1.632407698590822e-05, + "loss": 0.4734, + "step": 3629 + }, + { + "epoch": 0.3, + "learning_rate": 1.6321977564651313e-05, + "loss": 0.4866, + "step": 3630 + }, + { + "epoch": 0.3, + "learning_rate": 1.6319877679134662e-05, + "loss": 0.5065, + "step": 3631 + }, + { + "epoch": 0.3, + "learning_rate": 1.6317777329512485e-05, + "loss": 0.4771, + "step": 3632 + }, + { + "epoch": 0.3, + "learning_rate": 1.6315676515939015e-05, + "loss": 0.4991, + "step": 3633 + }, + { + "epoch": 0.3, + "learning_rate": 1.6313575238568535e-05, + "loss": 0.494, + "step": 3634 + }, + { + "epoch": 0.3, + "learning_rate": 1.6311473497555343e-05, + "loss": 0.4731, + "step": 3635 + }, + { + "epoch": 0.3, + "learning_rate": 1.6309371293053793e-05, + "loss": 0.5089, + "step": 3636 + }, + { + "epoch": 0.3, + "learning_rate": 1.630726862521826e-05, + "loss": 0.4857, + "step": 3637 + }, + { + "epoch": 0.3, + "learning_rate": 1.6305165494203147e-05, + "loss": 0.4843, + "step": 3638 + }, + { + "epoch": 0.3, + "learning_rate": 1.6303061900162912e-05, + "loss": 0.5002, + "step": 3639 + }, + { + "epoch": 0.3, + "learning_rate": 1.6300957843252027e-05, + "loss": 0.4996, + "step": 3640 + }, + { + "epoch": 0.3, + "learning_rate": 1.6298853323625003e-05, + "loss": 0.4843, + "step": 3641 + }, + { + "epoch": 0.3, + "learning_rate": 1.6296748341436386e-05, + "loss": 0.491, + "step": 3642 + }, + { + "epoch": 0.3, + "learning_rate": 1.6294642896840768e-05, + "loss": 0.4923, + "step": 3643 + }, + { + "epoch": 0.3, + "learning_rate": 1.6292536989992754e-05, + "loss": 0.4955, + "step": 3644 + }, + { + "epoch": 0.3, + "learning_rate": 1.6290430621046994e-05, + "loss": 0.4928, + "step": 3645 + }, + { + "epoch": 0.31, + "learning_rate": 1.6288323790158175e-05, + "loss": 0.4971, + "step": 3646 + }, + { + "epoch": 0.31, + "learning_rate": 1.6286216497481014e-05, + "loss": 0.488, + "step": 3647 + }, + { + "epoch": 0.31, + "learning_rate": 1.6284108743170256e-05, + "loss": 0.493, + "step": 3648 + }, + { + "epoch": 0.31, + "learning_rate": 1.628200052738069e-05, + "loss": 0.4973, + "step": 3649 + }, + { + "epoch": 0.31, + "learning_rate": 1.6279891850267134e-05, + "loss": 0.4951, + "step": 3650 + }, + { + "epoch": 0.31, + "learning_rate": 1.6277782711984446e-05, + "loss": 0.4991, + "step": 3651 + }, + { + "epoch": 0.31, + "learning_rate": 1.62756731126875e-05, + "loss": 0.4884, + "step": 3652 + }, + { + "epoch": 0.31, + "learning_rate": 1.6273563052531227e-05, + "loss": 0.4774, + "step": 3653 + }, + { + "epoch": 0.31, + "learning_rate": 1.6271452531670577e-05, + "loss": 0.4959, + "step": 3654 + }, + { + "epoch": 0.31, + "learning_rate": 1.6269341550260537e-05, + "loss": 0.4922, + "step": 3655 + }, + { + "epoch": 0.31, + "learning_rate": 1.6267230108456126e-05, + "loss": 0.5079, + "step": 3656 + }, + { + "epoch": 0.31, + "learning_rate": 1.6265118206412412e-05, + "loss": 0.482, + "step": 3657 + }, + { + "epoch": 0.31, + "learning_rate": 1.6263005844284468e-05, + "loss": 0.4812, + "step": 3658 + }, + { + "epoch": 0.31, + "learning_rate": 1.6260893022227425e-05, + "loss": 0.521, + "step": 3659 + }, + { + "epoch": 0.31, + "learning_rate": 1.6258779740396443e-05, + "loss": 0.4847, + "step": 3660 + }, + { + "epoch": 0.31, + "learning_rate": 1.6256665998946708e-05, + "loss": 0.499, + "step": 3661 + }, + { + "epoch": 0.31, + "learning_rate": 1.6254551798033444e-05, + "loss": 0.4978, + "step": 3662 + }, + { + "epoch": 0.31, + "learning_rate": 1.6252437137811913e-05, + "loss": 0.4887, + "step": 3663 + }, + { + "epoch": 0.31, + "learning_rate": 1.62503220184374e-05, + "loss": 0.4927, + "step": 3664 + }, + { + "epoch": 0.31, + "learning_rate": 1.624820644006524e-05, + "loss": 0.4999, + "step": 3665 + }, + { + "epoch": 0.31, + "learning_rate": 1.6246090402850783e-05, + "loss": 0.5203, + "step": 3666 + }, + { + "epoch": 0.31, + "learning_rate": 1.6243973906949434e-05, + "loss": 0.4929, + "step": 3667 + }, + { + "epoch": 0.31, + "learning_rate": 1.6241856952516604e-05, + "loss": 0.4796, + "step": 3668 + }, + { + "epoch": 0.31, + "learning_rate": 1.623973953970776e-05, + "loss": 0.4937, + "step": 3669 + }, + { + "epoch": 0.31, + "learning_rate": 1.6237621668678406e-05, + "loss": 0.4927, + "step": 3670 + }, + { + "epoch": 0.31, + "learning_rate": 1.6235503339584052e-05, + "loss": 0.4964, + "step": 3671 + }, + { + "epoch": 0.31, + "learning_rate": 1.6233384552580272e-05, + "loss": 0.4833, + "step": 3672 + }, + { + "epoch": 0.31, + "learning_rate": 1.6231265307822658e-05, + "loss": 0.4704, + "step": 3673 + }, + { + "epoch": 0.31, + "learning_rate": 1.622914560546684e-05, + "loss": 0.5002, + "step": 3674 + }, + { + "epoch": 0.31, + "learning_rate": 1.6227025445668473e-05, + "loss": 0.4905, + "step": 3675 + }, + { + "epoch": 0.31, + "learning_rate": 1.622490482858326e-05, + "loss": 0.4894, + "step": 3676 + }, + { + "epoch": 0.31, + "learning_rate": 1.6222783754366926e-05, + "loss": 0.4877, + "step": 3677 + }, + { + "epoch": 0.31, + "learning_rate": 1.6220662223175233e-05, + "loss": 0.4793, + "step": 3678 + }, + { + "epoch": 0.31, + "learning_rate": 1.6218540235163983e-05, + "loss": 0.4839, + "step": 3679 + }, + { + "epoch": 0.31, + "learning_rate": 1.6216417790489005e-05, + "loss": 0.4906, + "step": 3680 + }, + { + "epoch": 0.31, + "learning_rate": 1.6214294889306158e-05, + "loss": 0.4857, + "step": 3681 + }, + { + "epoch": 0.31, + "learning_rate": 1.621217153177134e-05, + "loss": 0.4932, + "step": 3682 + }, + { + "epoch": 0.31, + "learning_rate": 1.621004771804049e-05, + "loss": 0.4943, + "step": 3683 + }, + { + "epoch": 0.31, + "learning_rate": 1.620792344826956e-05, + "loss": 0.517, + "step": 3684 + }, + { + "epoch": 0.31, + "learning_rate": 1.6205798722614552e-05, + "loss": 0.4828, + "step": 3685 + }, + { + "epoch": 0.31, + "learning_rate": 1.6203673541231497e-05, + "loss": 0.473, + "step": 3686 + }, + { + "epoch": 0.31, + "learning_rate": 1.6201547904276463e-05, + "loss": 0.4931, + "step": 3687 + }, + { + "epoch": 0.31, + "learning_rate": 1.6199421811905542e-05, + "loss": 0.508, + "step": 3688 + }, + { + "epoch": 0.31, + "learning_rate": 1.619729526427487e-05, + "loss": 0.4883, + "step": 3689 + }, + { + "epoch": 0.31, + "learning_rate": 1.6195168261540612e-05, + "loss": 0.4819, + "step": 3690 + }, + { + "epoch": 0.31, + "learning_rate": 1.6193040803858965e-05, + "loss": 0.5097, + "step": 3691 + }, + { + "epoch": 0.31, + "learning_rate": 1.6190912891386154e-05, + "loss": 0.5071, + "step": 3692 + }, + { + "epoch": 0.31, + "learning_rate": 1.6188784524278455e-05, + "loss": 0.4829, + "step": 3693 + }, + { + "epoch": 0.31, + "learning_rate": 1.6186655702692162e-05, + "loss": 0.4916, + "step": 3694 + }, + { + "epoch": 0.31, + "learning_rate": 1.6184526426783607e-05, + "loss": 0.5002, + "step": 3695 + }, + { + "epoch": 0.31, + "learning_rate": 1.618239669670915e-05, + "loss": 0.4863, + "step": 3696 + }, + { + "epoch": 0.31, + "learning_rate": 1.61802665126252e-05, + "loss": 0.5061, + "step": 3697 + }, + { + "epoch": 0.31, + "learning_rate": 1.6178135874688183e-05, + "loss": 0.4785, + "step": 3698 + }, + { + "epoch": 0.31, + "learning_rate": 1.6176004783054556e-05, + "loss": 0.5046, + "step": 3699 + }, + { + "epoch": 0.31, + "learning_rate": 1.6173873237880832e-05, + "loss": 0.5005, + "step": 3700 + }, + { + "epoch": 0.31, + "learning_rate": 1.6171741239323537e-05, + "loss": 0.4856, + "step": 3701 + }, + { + "epoch": 0.31, + "learning_rate": 1.6169608787539234e-05, + "loss": 0.5233, + "step": 3702 + }, + { + "epoch": 0.31, + "learning_rate": 1.6167475882684522e-05, + "loss": 0.4767, + "step": 3703 + }, + { + "epoch": 0.31, + "learning_rate": 1.6165342524916035e-05, + "loss": 0.5088, + "step": 3704 + }, + { + "epoch": 0.31, + "learning_rate": 1.6163208714390437e-05, + "loss": 0.5114, + "step": 3705 + }, + { + "epoch": 0.31, + "learning_rate": 1.6161074451264425e-05, + "loss": 0.503, + "step": 3706 + }, + { + "epoch": 0.31, + "learning_rate": 1.615893973569473e-05, + "loss": 0.4942, + "step": 3707 + }, + { + "epoch": 0.31, + "learning_rate": 1.615680456783812e-05, + "loss": 0.4998, + "step": 3708 + }, + { + "epoch": 0.31, + "learning_rate": 1.615466894785139e-05, + "loss": 0.5169, + "step": 3709 + }, + { + "epoch": 0.31, + "learning_rate": 1.6152532875891372e-05, + "loss": 0.4753, + "step": 3710 + }, + { + "epoch": 0.31, + "learning_rate": 1.6150396352114926e-05, + "loss": 0.481, + "step": 3711 + }, + { + "epoch": 0.31, + "learning_rate": 1.6148259376678957e-05, + "loss": 0.4966, + "step": 3712 + }, + { + "epoch": 0.31, + "learning_rate": 1.6146121949740393e-05, + "loss": 0.5167, + "step": 3713 + }, + { + "epoch": 0.31, + "learning_rate": 1.6143984071456197e-05, + "loss": 0.4961, + "step": 3714 + }, + { + "epoch": 0.31, + "learning_rate": 1.614184574198336e-05, + "loss": 0.5012, + "step": 3715 + }, + { + "epoch": 0.31, + "learning_rate": 1.613970696147892e-05, + "loss": 0.4894, + "step": 3716 + }, + { + "epoch": 0.31, + "learning_rate": 1.613756773009994e-05, + "loss": 0.4937, + "step": 3717 + }, + { + "epoch": 0.31, + "learning_rate": 1.6135428048003513e-05, + "loss": 0.4853, + "step": 3718 + }, + { + "epoch": 0.31, + "learning_rate": 1.6133287915346772e-05, + "loss": 0.5156, + "step": 3719 + }, + { + "epoch": 0.31, + "learning_rate": 1.6131147332286872e-05, + "loss": 0.4906, + "step": 3720 + }, + { + "epoch": 0.31, + "learning_rate": 1.6129006298981015e-05, + "loss": 0.4942, + "step": 3721 + }, + { + "epoch": 0.31, + "learning_rate": 1.6126864815586427e-05, + "loss": 0.5072, + "step": 3722 + }, + { + "epoch": 0.31, + "learning_rate": 1.6124722882260372e-05, + "loss": 0.5006, + "step": 3723 + }, + { + "epoch": 0.31, + "learning_rate": 1.6122580499160144e-05, + "loss": 0.4895, + "step": 3724 + }, + { + "epoch": 0.31, + "learning_rate": 1.6120437666443067e-05, + "loss": 0.5041, + "step": 3725 + }, + { + "epoch": 0.31, + "learning_rate": 1.6118294384266506e-05, + "loss": 0.4864, + "step": 3726 + }, + { + "epoch": 0.31, + "learning_rate": 1.6116150652787852e-05, + "loss": 0.4983, + "step": 3727 + }, + { + "epoch": 0.31, + "learning_rate": 1.6114006472164535e-05, + "loss": 0.5044, + "step": 3728 + }, + { + "epoch": 0.31, + "learning_rate": 1.6111861842554014e-05, + "loss": 0.4779, + "step": 3729 + }, + { + "epoch": 0.31, + "learning_rate": 1.6109716764113778e-05, + "loss": 0.4895, + "step": 3730 + }, + { + "epoch": 0.31, + "learning_rate": 1.6107571237001356e-05, + "loss": 0.4795, + "step": 3731 + }, + { + "epoch": 0.31, + "learning_rate": 1.6105425261374305e-05, + "loss": 0.4991, + "step": 3732 + }, + { + "epoch": 0.31, + "learning_rate": 1.6103278837390218e-05, + "loss": 0.4792, + "step": 3733 + }, + { + "epoch": 0.31, + "learning_rate": 1.6101131965206714e-05, + "loss": 0.4891, + "step": 3734 + }, + { + "epoch": 0.31, + "learning_rate": 1.6098984644981463e-05, + "loss": 0.5137, + "step": 3735 + }, + { + "epoch": 0.31, + "learning_rate": 1.6096836876872143e-05, + "loss": 0.5098, + "step": 3736 + }, + { + "epoch": 0.31, + "learning_rate": 1.6094688661036483e-05, + "loss": 0.5053, + "step": 3737 + }, + { + "epoch": 0.31, + "learning_rate": 1.6092539997632236e-05, + "loss": 0.4915, + "step": 3738 + }, + { + "epoch": 0.31, + "learning_rate": 1.609039088681719e-05, + "loss": 0.4916, + "step": 3739 + }, + { + "epoch": 0.31, + "learning_rate": 1.6088241328749172e-05, + "loss": 0.484, + "step": 3740 + }, + { + "epoch": 0.31, + "learning_rate": 1.6086091323586034e-05, + "loss": 0.5012, + "step": 3741 + }, + { + "epoch": 0.31, + "learning_rate": 1.6083940871485663e-05, + "loss": 0.4669, + "step": 3742 + }, + { + "epoch": 0.31, + "learning_rate": 1.608178997260598e-05, + "loss": 0.4923, + "step": 3743 + }, + { + "epoch": 0.31, + "learning_rate": 1.6079638627104937e-05, + "loss": 0.4927, + "step": 3744 + }, + { + "epoch": 0.31, + "learning_rate": 1.6077486835140518e-05, + "loss": 0.4755, + "step": 3745 + }, + { + "epoch": 0.31, + "learning_rate": 1.6075334596870746e-05, + "loss": 0.4855, + "step": 3746 + }, + { + "epoch": 0.31, + "learning_rate": 1.607318191245367e-05, + "loss": 0.4979, + "step": 3747 + }, + { + "epoch": 0.31, + "learning_rate": 1.607102878204738e-05, + "loss": 0.4754, + "step": 3748 + }, + { + "epoch": 0.31, + "learning_rate": 1.6068875205809978e-05, + "loss": 0.5086, + "step": 3749 + }, + { + "epoch": 0.31, + "learning_rate": 1.606672118389963e-05, + "loss": 0.5113, + "step": 3750 + }, + { + "epoch": 0.31, + "learning_rate": 1.6064566716474506e-05, + "loss": 0.5014, + "step": 3751 + }, + { + "epoch": 0.31, + "learning_rate": 1.606241180369283e-05, + "loss": 0.4899, + "step": 3752 + }, + { + "epoch": 0.31, + "learning_rate": 1.606025644571285e-05, + "loss": 0.5102, + "step": 3753 + }, + { + "epoch": 0.31, + "learning_rate": 1.6058100642692837e-05, + "loss": 0.4875, + "step": 3754 + }, + { + "epoch": 0.31, + "learning_rate": 1.6055944394791113e-05, + "loss": 0.5025, + "step": 3755 + }, + { + "epoch": 0.31, + "learning_rate": 1.605378770216602e-05, + "loss": 0.4748, + "step": 3756 + }, + { + "epoch": 0.31, + "learning_rate": 1.605163056497594e-05, + "loss": 0.4893, + "step": 3757 + }, + { + "epoch": 0.31, + "learning_rate": 1.6049472983379285e-05, + "loss": 0.4999, + "step": 3758 + }, + { + "epoch": 0.31, + "learning_rate": 1.6047314957534487e-05, + "loss": 0.5149, + "step": 3759 + }, + { + "epoch": 0.31, + "learning_rate": 1.604515648760004e-05, + "loss": 0.4722, + "step": 3760 + }, + { + "epoch": 0.31, + "learning_rate": 1.6042997573734437e-05, + "loss": 0.5037, + "step": 3761 + }, + { + "epoch": 0.31, + "learning_rate": 1.6040838216096233e-05, + "loss": 0.4684, + "step": 3762 + }, + { + "epoch": 0.31, + "learning_rate": 1.6038678414843994e-05, + "loss": 0.5232, + "step": 3763 + }, + { + "epoch": 0.31, + "learning_rate": 1.6036518170136326e-05, + "loss": 0.4807, + "step": 3764 + }, + { + "epoch": 0.31, + "learning_rate": 1.603435748213187e-05, + "loss": 0.4972, + "step": 3765 + }, + { + "epoch": 0.32, + "learning_rate": 1.6032196350989306e-05, + "loss": 0.4843, + "step": 3766 + }, + { + "epoch": 0.32, + "learning_rate": 1.603003477686733e-05, + "loss": 0.4668, + "step": 3767 + }, + { + "epoch": 0.32, + "learning_rate": 1.6027872759924678e-05, + "loss": 0.4949, + "step": 3768 + }, + { + "epoch": 0.32, + "learning_rate": 1.6025710300320124e-05, + "loss": 0.4948, + "step": 3769 + }, + { + "epoch": 0.32, + "learning_rate": 1.6023547398212467e-05, + "loss": 0.4746, + "step": 3770 + }, + { + "epoch": 0.32, + "learning_rate": 1.6021384053760546e-05, + "loss": 0.476, + "step": 3771 + }, + { + "epoch": 0.32, + "learning_rate": 1.6019220267123223e-05, + "loss": 0.4951, + "step": 3772 + }, + { + "epoch": 0.32, + "learning_rate": 1.60170560384594e-05, + "loss": 0.4662, + "step": 3773 + }, + { + "epoch": 0.32, + "learning_rate": 1.601489136792801e-05, + "loss": 0.4972, + "step": 3774 + }, + { + "epoch": 0.32, + "learning_rate": 1.6012726255688013e-05, + "loss": 0.4956, + "step": 3775 + }, + { + "epoch": 0.32, + "learning_rate": 1.6010560701898405e-05, + "loss": 0.4779, + "step": 3776 + }, + { + "epoch": 0.32, + "learning_rate": 1.6008394706718224e-05, + "loss": 0.5058, + "step": 3777 + }, + { + "epoch": 0.32, + "learning_rate": 1.6006228270306526e-05, + "loss": 0.5015, + "step": 3778 + }, + { + "epoch": 0.32, + "learning_rate": 1.6004061392822407e-05, + "loss": 0.4791, + "step": 3779 + }, + { + "epoch": 0.32, + "learning_rate": 1.6001894074424987e-05, + "loss": 0.4736, + "step": 3780 + }, + { + "epoch": 0.32, + "learning_rate": 1.5999726315273435e-05, + "loss": 0.4803, + "step": 3781 + }, + { + "epoch": 0.32, + "learning_rate": 1.599755811552693e-05, + "loss": 0.5038, + "step": 3782 + }, + { + "epoch": 0.32, + "learning_rate": 1.5995389475344715e-05, + "loss": 0.4888, + "step": 3783 + }, + { + "epoch": 0.32, + "learning_rate": 1.5993220394886024e-05, + "loss": 0.4943, + "step": 3784 + }, + { + "epoch": 0.32, + "learning_rate": 1.5991050874310156e-05, + "loss": 0.5088, + "step": 3785 + }, + { + "epoch": 0.32, + "learning_rate": 1.5988880913776434e-05, + "loss": 0.4833, + "step": 3786 + }, + { + "epoch": 0.32, + "learning_rate": 1.5986710513444205e-05, + "loss": 0.499, + "step": 3787 + }, + { + "epoch": 0.32, + "learning_rate": 1.5984539673472856e-05, + "loss": 0.4909, + "step": 3788 + }, + { + "epoch": 0.32, + "learning_rate": 1.5982368394021804e-05, + "loss": 0.4929, + "step": 3789 + }, + { + "epoch": 0.32, + "learning_rate": 1.5980196675250504e-05, + "loss": 0.4894, + "step": 3790 + }, + { + "epoch": 0.32, + "learning_rate": 1.5978024517318428e-05, + "loss": 0.4776, + "step": 3791 + }, + { + "epoch": 0.32, + "learning_rate": 1.5975851920385103e-05, + "loss": 0.4832, + "step": 3792 + }, + { + "epoch": 0.32, + "learning_rate": 1.5973678884610062e-05, + "loss": 0.4832, + "step": 3793 + }, + { + "epoch": 0.32, + "learning_rate": 1.597150541015289e-05, + "loss": 0.4827, + "step": 3794 + }, + { + "epoch": 0.32, + "learning_rate": 1.5969331497173203e-05, + "loss": 0.4805, + "step": 3795 + }, + { + "epoch": 0.32, + "learning_rate": 1.5967157145830638e-05, + "loss": 0.4961, + "step": 3796 + }, + { + "epoch": 0.32, + "learning_rate": 1.596498235628487e-05, + "loss": 0.5165, + "step": 3797 + }, + { + "epoch": 0.32, + "learning_rate": 1.5962807128695606e-05, + "loss": 0.4927, + "step": 3798 + }, + { + "epoch": 0.32, + "learning_rate": 1.5960631463222592e-05, + "loss": 0.5033, + "step": 3799 + }, + { + "epoch": 0.32, + "learning_rate": 1.595845536002559e-05, + "loss": 0.4744, + "step": 3800 + }, + { + "epoch": 0.32, + "learning_rate": 1.5956278819264417e-05, + "loss": 0.4675, + "step": 3801 + }, + { + "epoch": 0.32, + "learning_rate": 1.5954101841098895e-05, + "loss": 0.4773, + "step": 3802 + }, + { + "epoch": 0.32, + "learning_rate": 1.59519244256889e-05, + "loss": 0.4848, + "step": 3803 + }, + { + "epoch": 0.32, + "learning_rate": 1.5949746573194334e-05, + "loss": 0.4883, + "step": 3804 + }, + { + "epoch": 0.32, + "learning_rate": 1.5947568283775125e-05, + "loss": 0.4869, + "step": 3805 + }, + { + "epoch": 0.32, + "learning_rate": 1.5945389557591237e-05, + "loss": 0.4972, + "step": 3806 + }, + { + "epoch": 0.32, + "learning_rate": 1.594321039480267e-05, + "loss": 0.4711, + "step": 3807 + }, + { + "epoch": 0.32, + "learning_rate": 1.5941030795569452e-05, + "loss": 0.4634, + "step": 3808 + }, + { + "epoch": 0.32, + "learning_rate": 1.5938850760051643e-05, + "loss": 0.4964, + "step": 3809 + }, + { + "epoch": 0.32, + "learning_rate": 1.5936670288409335e-05, + "loss": 0.4977, + "step": 3810 + }, + { + "epoch": 0.32, + "learning_rate": 1.5934489380802653e-05, + "loss": 0.5042, + "step": 3811 + }, + { + "epoch": 0.32, + "learning_rate": 1.5932308037391756e-05, + "loss": 0.493, + "step": 3812 + }, + { + "epoch": 0.32, + "learning_rate": 1.593012625833683e-05, + "loss": 0.4989, + "step": 3813 + }, + { + "epoch": 0.32, + "learning_rate": 1.59279440437981e-05, + "loss": 0.4855, + "step": 3814 + }, + { + "epoch": 0.32, + "learning_rate": 1.592576139393581e-05, + "loss": 0.483, + "step": 3815 + }, + { + "epoch": 0.32, + "learning_rate": 1.5923578308910254e-05, + "loss": 0.4849, + "step": 3816 + }, + { + "epoch": 0.32, + "learning_rate": 1.592139478888174e-05, + "loss": 0.483, + "step": 3817 + }, + { + "epoch": 0.32, + "learning_rate": 1.5919210834010628e-05, + "loss": 0.511, + "step": 3818 + }, + { + "epoch": 0.32, + "learning_rate": 1.5917026444457288e-05, + "loss": 0.4953, + "step": 3819 + }, + { + "epoch": 0.32, + "learning_rate": 1.591484162038214e-05, + "loss": 0.4849, + "step": 3820 + }, + { + "epoch": 0.32, + "learning_rate": 1.5912656361945626e-05, + "loss": 0.4783, + "step": 3821 + }, + { + "epoch": 0.32, + "learning_rate": 1.5910470669308217e-05, + "loss": 0.4872, + "step": 3822 + }, + { + "epoch": 0.32, + "learning_rate": 1.5908284542630425e-05, + "loss": 0.5001, + "step": 3823 + }, + { + "epoch": 0.32, + "learning_rate": 1.5906097982072793e-05, + "loss": 0.4711, + "step": 3824 + }, + { + "epoch": 0.32, + "learning_rate": 1.590391098779589e-05, + "loss": 0.468, + "step": 3825 + }, + { + "epoch": 0.32, + "learning_rate": 1.5901723559960322e-05, + "loss": 0.5036, + "step": 3826 + }, + { + "epoch": 0.32, + "learning_rate": 1.5899535698726723e-05, + "loss": 0.483, + "step": 3827 + }, + { + "epoch": 0.32, + "learning_rate": 1.5897347404255757e-05, + "loss": 0.4843, + "step": 3828 + }, + { + "epoch": 0.32, + "learning_rate": 1.589515867670813e-05, + "loss": 0.4897, + "step": 3829 + }, + { + "epoch": 0.32, + "learning_rate": 1.589296951624457e-05, + "loss": 0.4886, + "step": 3830 + }, + { + "epoch": 0.32, + "learning_rate": 1.5890779923025832e-05, + "loss": 0.4777, + "step": 3831 + }, + { + "epoch": 0.32, + "learning_rate": 1.5888589897212726e-05, + "loss": 0.495, + "step": 3832 + }, + { + "epoch": 0.32, + "learning_rate": 1.5886399438966068e-05, + "loss": 0.4896, + "step": 3833 + }, + { + "epoch": 0.32, + "learning_rate": 1.5884208548446716e-05, + "loss": 0.4846, + "step": 3834 + }, + { + "epoch": 0.32, + "learning_rate": 1.5882017225815566e-05, + "loss": 0.4673, + "step": 3835 + }, + { + "epoch": 0.32, + "learning_rate": 1.5879825471233538e-05, + "loss": 0.4854, + "step": 3836 + }, + { + "epoch": 0.32, + "learning_rate": 1.5877633284861577e-05, + "loss": 0.4916, + "step": 3837 + }, + { + "epoch": 0.32, + "learning_rate": 1.587544066686068e-05, + "loss": 0.4774, + "step": 3838 + }, + { + "epoch": 0.32, + "learning_rate": 1.5873247617391854e-05, + "loss": 0.4825, + "step": 3839 + }, + { + "epoch": 0.32, + "learning_rate": 1.5871054136616154e-05, + "loss": 0.4933, + "step": 3840 + }, + { + "epoch": 0.32, + "learning_rate": 1.5868860224694656e-05, + "loss": 0.5059, + "step": 3841 + }, + { + "epoch": 0.32, + "learning_rate": 1.586666588178848e-05, + "loss": 0.4819, + "step": 3842 + }, + { + "epoch": 0.32, + "learning_rate": 1.5864471108058755e-05, + "loss": 0.4753, + "step": 3843 + }, + { + "epoch": 0.32, + "learning_rate": 1.586227590366667e-05, + "loss": 0.5028, + "step": 3844 + }, + { + "epoch": 0.32, + "learning_rate": 1.586008026877342e-05, + "loss": 0.5122, + "step": 3845 + }, + { + "epoch": 0.32, + "learning_rate": 1.585788420354025e-05, + "loss": 0.5066, + "step": 3846 + }, + { + "epoch": 0.32, + "learning_rate": 1.5855687708128433e-05, + "loss": 0.4991, + "step": 3847 + }, + { + "epoch": 0.32, + "learning_rate": 1.5853490782699266e-05, + "loss": 0.4953, + "step": 3848 + }, + { + "epoch": 0.32, + "learning_rate": 1.5851293427414075e-05, + "loss": 0.4834, + "step": 3849 + }, + { + "epoch": 0.32, + "learning_rate": 1.584909564243424e-05, + "loss": 0.49, + "step": 3850 + }, + { + "epoch": 0.32, + "learning_rate": 1.5846897427921147e-05, + "loss": 0.4989, + "step": 3851 + }, + { + "epoch": 0.32, + "learning_rate": 1.584469878403623e-05, + "loss": 0.481, + "step": 3852 + }, + { + "epoch": 0.32, + "learning_rate": 1.5842499710940936e-05, + "loss": 0.5093, + "step": 3853 + }, + { + "epoch": 0.32, + "learning_rate": 1.5840300208796767e-05, + "loss": 0.4943, + "step": 3854 + }, + { + "epoch": 0.32, + "learning_rate": 1.5838100277765244e-05, + "loss": 0.4794, + "step": 3855 + }, + { + "epoch": 0.32, + "learning_rate": 1.5835899918007917e-05, + "loss": 0.4951, + "step": 3856 + }, + { + "epoch": 0.32, + "learning_rate": 1.5833699129686376e-05, + "loss": 0.4958, + "step": 3857 + }, + { + "epoch": 0.32, + "learning_rate": 1.5831497912962235e-05, + "loss": 0.5049, + "step": 3858 + }, + { + "epoch": 0.32, + "learning_rate": 1.5829296267997142e-05, + "loss": 0.4801, + "step": 3859 + }, + { + "epoch": 0.32, + "learning_rate": 1.582709419495277e-05, + "loss": 0.4781, + "step": 3860 + }, + { + "epoch": 0.32, + "learning_rate": 1.5824891693990845e-05, + "loss": 0.5053, + "step": 3861 + }, + { + "epoch": 0.32, + "learning_rate": 1.58226887652731e-05, + "loss": 0.5095, + "step": 3862 + }, + { + "epoch": 0.32, + "learning_rate": 1.582048540896131e-05, + "loss": 0.5, + "step": 3863 + }, + { + "epoch": 0.32, + "learning_rate": 1.581828162521728e-05, + "loss": 0.4818, + "step": 3864 + }, + { + "epoch": 0.32, + "learning_rate": 1.5816077414202848e-05, + "loss": 0.4957, + "step": 3865 + }, + { + "epoch": 0.32, + "learning_rate": 1.5813872776079882e-05, + "loss": 0.477, + "step": 3866 + }, + { + "epoch": 0.32, + "learning_rate": 1.581166771101028e-05, + "loss": 0.4875, + "step": 3867 + }, + { + "epoch": 0.32, + "learning_rate": 1.5809462219155976e-05, + "loss": 0.4905, + "step": 3868 + }, + { + "epoch": 0.32, + "learning_rate": 1.580725630067893e-05, + "loss": 0.4993, + "step": 3869 + }, + { + "epoch": 0.32, + "learning_rate": 1.5805049955741135e-05, + "loss": 0.486, + "step": 3870 + }, + { + "epoch": 0.32, + "learning_rate": 1.5802843184504614e-05, + "loss": 0.4895, + "step": 3871 + }, + { + "epoch": 0.32, + "learning_rate": 1.5800635987131426e-05, + "loss": 0.5033, + "step": 3872 + }, + { + "epoch": 0.32, + "learning_rate": 1.579842836378366e-05, + "loss": 0.4842, + "step": 3873 + }, + { + "epoch": 0.32, + "learning_rate": 1.579622031462343e-05, + "loss": 0.479, + "step": 3874 + }, + { + "epoch": 0.32, + "learning_rate": 1.5794011839812888e-05, + "loss": 0.5077, + "step": 3875 + }, + { + "epoch": 0.32, + "learning_rate": 1.579180293951422e-05, + "loss": 0.4942, + "step": 3876 + }, + { + "epoch": 0.32, + "learning_rate": 1.5789593613889632e-05, + "loss": 0.4722, + "step": 3877 + }, + { + "epoch": 0.32, + "learning_rate": 1.5787383863101366e-05, + "loss": 0.48, + "step": 3878 + }, + { + "epoch": 0.32, + "learning_rate": 1.5785173687311704e-05, + "loss": 0.4909, + "step": 3879 + }, + { + "epoch": 0.32, + "learning_rate": 1.5782963086682946e-05, + "loss": 0.4962, + "step": 3880 + }, + { + "epoch": 0.32, + "learning_rate": 1.5780752061377436e-05, + "loss": 0.502, + "step": 3881 + }, + { + "epoch": 0.32, + "learning_rate": 1.5778540611557538e-05, + "loss": 0.4961, + "step": 3882 + }, + { + "epoch": 0.32, + "learning_rate": 1.577632873738565e-05, + "loss": 0.506, + "step": 3883 + }, + { + "epoch": 0.32, + "learning_rate": 1.5774116439024206e-05, + "loss": 0.4868, + "step": 3884 + }, + { + "epoch": 0.33, + "learning_rate": 1.5771903716635666e-05, + "loss": 0.4888, + "step": 3885 + }, + { + "epoch": 0.33, + "learning_rate": 1.576969057038253e-05, + "loss": 0.5003, + "step": 3886 + }, + { + "epoch": 0.33, + "learning_rate": 1.5767477000427306e-05, + "loss": 0.4854, + "step": 3887 + }, + { + "epoch": 0.33, + "learning_rate": 1.576526300693257e-05, + "loss": 0.4996, + "step": 3888 + }, + { + "epoch": 0.33, + "learning_rate": 1.5763048590060894e-05, + "loss": 0.4976, + "step": 3889 + }, + { + "epoch": 0.33, + "learning_rate": 1.5760833749974898e-05, + "loss": 0.4881, + "step": 3890 + }, + { + "epoch": 0.33, + "learning_rate": 1.5758618486837232e-05, + "loss": 0.494, + "step": 3891 + }, + { + "epoch": 0.33, + "learning_rate": 1.5756402800810582e-05, + "loss": 0.4804, + "step": 3892 + }, + { + "epoch": 0.33, + "learning_rate": 1.575418669205765e-05, + "loss": 0.4861, + "step": 3893 + }, + { + "epoch": 0.33, + "learning_rate": 1.575197016074118e-05, + "loss": 0.4914, + "step": 3894 + }, + { + "epoch": 0.33, + "learning_rate": 1.5749753207023944e-05, + "loss": 0.4872, + "step": 3895 + }, + { + "epoch": 0.33, + "learning_rate": 1.574753583106875e-05, + "loss": 0.489, + "step": 3896 + }, + { + "epoch": 0.33, + "learning_rate": 1.574531803303843e-05, + "loss": 0.4924, + "step": 3897 + }, + { + "epoch": 0.33, + "learning_rate": 1.574309981309585e-05, + "loss": 0.4816, + "step": 3898 + }, + { + "epoch": 0.33, + "learning_rate": 1.574088117140391e-05, + "loss": 0.4639, + "step": 3899 + }, + { + "epoch": 0.33, + "learning_rate": 1.573866210812553e-05, + "loss": 0.4816, + "step": 3900 + }, + { + "epoch": 0.33, + "learning_rate": 1.5736442623423675e-05, + "loss": 0.4962, + "step": 3901 + }, + { + "epoch": 0.33, + "learning_rate": 1.5734222717461338e-05, + "loss": 0.4772, + "step": 3902 + }, + { + "epoch": 0.33, + "learning_rate": 1.5732002390401527e-05, + "loss": 0.5055, + "step": 3903 + }, + { + "epoch": 0.33, + "learning_rate": 1.5729781642407305e-05, + "loss": 0.5134, + "step": 3904 + }, + { + "epoch": 0.33, + "learning_rate": 1.5727560473641755e-05, + "loss": 0.4845, + "step": 3905 + }, + { + "epoch": 0.33, + "learning_rate": 1.572533888426798e-05, + "loss": 0.4959, + "step": 3906 + }, + { + "epoch": 0.33, + "learning_rate": 1.5723116874449136e-05, + "loss": 0.5198, + "step": 3907 + }, + { + "epoch": 0.33, + "learning_rate": 1.5720894444348393e-05, + "loss": 0.4905, + "step": 3908 + }, + { + "epoch": 0.33, + "learning_rate": 1.5718671594128957e-05, + "loss": 0.4815, + "step": 3909 + }, + { + "epoch": 0.33, + "learning_rate": 1.571644832395406e-05, + "loss": 0.5216, + "step": 3910 + }, + { + "epoch": 0.33, + "learning_rate": 1.5714224633986978e-05, + "loss": 0.4948, + "step": 3911 + }, + { + "epoch": 0.33, + "learning_rate": 1.5712000524391004e-05, + "loss": 0.4868, + "step": 3912 + }, + { + "epoch": 0.33, + "learning_rate": 1.5709775995329475e-05, + "loss": 0.488, + "step": 3913 + }, + { + "epoch": 0.33, + "learning_rate": 1.570755104696574e-05, + "loss": 0.4918, + "step": 3914 + }, + { + "epoch": 0.33, + "learning_rate": 1.5705325679463198e-05, + "loss": 0.4765, + "step": 3915 + }, + { + "epoch": 0.33, + "learning_rate": 1.5703099892985267e-05, + "loss": 0.501, + "step": 3916 + }, + { + "epoch": 0.33, + "learning_rate": 1.5700873687695405e-05, + "loss": 0.4919, + "step": 3917 + }, + { + "epoch": 0.33, + "learning_rate": 1.5698647063757086e-05, + "loss": 0.4837, + "step": 3918 + }, + { + "epoch": 0.33, + "learning_rate": 1.5696420021333828e-05, + "loss": 0.4798, + "step": 3919 + }, + { + "epoch": 0.33, + "learning_rate": 1.5694192560589184e-05, + "loss": 0.4893, + "step": 3920 + }, + { + "epoch": 0.33, + "learning_rate": 1.5691964681686715e-05, + "loss": 0.4969, + "step": 3921 + }, + { + "epoch": 0.33, + "learning_rate": 1.5689736384790038e-05, + "loss": 0.4692, + "step": 3922 + }, + { + "epoch": 0.33, + "learning_rate": 1.5687507670062788e-05, + "loss": 0.4862, + "step": 3923 + }, + { + "epoch": 0.33, + "learning_rate": 1.5685278537668627e-05, + "loss": 0.4888, + "step": 3924 + }, + { + "epoch": 0.33, + "learning_rate": 1.568304898777126e-05, + "loss": 0.518, + "step": 3925 + }, + { + "epoch": 0.33, + "learning_rate": 1.568081902053441e-05, + "loss": 0.4963, + "step": 3926 + }, + { + "epoch": 0.33, + "learning_rate": 1.567858863612184e-05, + "loss": 0.4802, + "step": 3927 + }, + { + "epoch": 0.33, + "learning_rate": 1.5676357834697342e-05, + "loss": 0.5066, + "step": 3928 + }, + { + "epoch": 0.33, + "learning_rate": 1.5674126616424735e-05, + "loss": 0.495, + "step": 3929 + }, + { + "epoch": 0.33, + "learning_rate": 1.5671894981467866e-05, + "loss": 0.4616, + "step": 3930 + }, + { + "epoch": 0.33, + "learning_rate": 1.5669662929990622e-05, + "loss": 0.4896, + "step": 3931 + }, + { + "epoch": 0.33, + "learning_rate": 1.5667430462156918e-05, + "loss": 0.4981, + "step": 3932 + }, + { + "epoch": 0.33, + "learning_rate": 1.566519757813069e-05, + "loss": 0.4783, + "step": 3933 + }, + { + "epoch": 0.33, + "learning_rate": 1.5662964278075913e-05, + "loss": 0.5017, + "step": 3934 + }, + { + "epoch": 0.33, + "learning_rate": 1.5660730562156596e-05, + "loss": 0.4876, + "step": 3935 + }, + { + "epoch": 0.33, + "learning_rate": 1.5658496430536772e-05, + "loss": 0.4888, + "step": 3936 + }, + { + "epoch": 0.33, + "learning_rate": 1.5656261883380504e-05, + "loss": 0.484, + "step": 3937 + }, + { + "epoch": 0.33, + "learning_rate": 1.565402692085189e-05, + "loss": 0.5082, + "step": 3938 + }, + { + "epoch": 0.33, + "learning_rate": 1.5651791543115056e-05, + "loss": 0.4958, + "step": 3939 + }, + { + "epoch": 0.33, + "learning_rate": 1.564955575033416e-05, + "loss": 0.4958, + "step": 3940 + }, + { + "epoch": 0.33, + "learning_rate": 1.5647319542673386e-05, + "loss": 0.5015, + "step": 3941 + }, + { + "epoch": 0.33, + "learning_rate": 1.564508292029695e-05, + "loss": 0.4872, + "step": 3942 + }, + { + "epoch": 0.33, + "learning_rate": 1.5642845883369114e-05, + "loss": 0.471, + "step": 3943 + }, + { + "epoch": 0.33, + "learning_rate": 1.564060843205414e-05, + "loss": 0.484, + "step": 3944 + }, + { + "epoch": 0.33, + "learning_rate": 1.5638370566516344e-05, + "loss": 0.4949, + "step": 3945 + }, + { + "epoch": 0.33, + "learning_rate": 1.5636132286920066e-05, + "loss": 0.4749, + "step": 3946 + }, + { + "epoch": 0.33, + "learning_rate": 1.5633893593429677e-05, + "loss": 0.4953, + "step": 3947 + }, + { + "epoch": 0.33, + "learning_rate": 1.5631654486209572e-05, + "loss": 0.513, + "step": 3948 + }, + { + "epoch": 0.33, + "learning_rate": 1.5629414965424187e-05, + "loss": 0.4946, + "step": 3949 + }, + { + "epoch": 0.33, + "learning_rate": 1.5627175031237986e-05, + "loss": 0.4743, + "step": 3950 + }, + { + "epoch": 0.33, + "learning_rate": 1.562493468381545e-05, + "loss": 0.4942, + "step": 3951 + }, + { + "epoch": 0.33, + "learning_rate": 1.5622693923321105e-05, + "loss": 0.5027, + "step": 3952 + }, + { + "epoch": 0.33, + "learning_rate": 1.562045274991951e-05, + "loss": 0.5063, + "step": 3953 + }, + { + "epoch": 0.33, + "learning_rate": 1.5618211163775242e-05, + "loss": 0.5087, + "step": 3954 + }, + { + "epoch": 0.33, + "learning_rate": 1.561596916505291e-05, + "loss": 0.4906, + "step": 3955 + }, + { + "epoch": 0.33, + "learning_rate": 1.5613726753917166e-05, + "loss": 0.4729, + "step": 3956 + }, + { + "epoch": 0.33, + "learning_rate": 1.5611483930532677e-05, + "loss": 0.4925, + "step": 3957 + }, + { + "epoch": 0.33, + "learning_rate": 1.5609240695064146e-05, + "loss": 0.4867, + "step": 3958 + }, + { + "epoch": 0.33, + "learning_rate": 1.560699704767631e-05, + "loss": 0.4978, + "step": 3959 + }, + { + "epoch": 0.33, + "learning_rate": 1.5604752988533933e-05, + "loss": 0.4827, + "step": 3960 + }, + { + "epoch": 0.33, + "learning_rate": 1.560250851780181e-05, + "loss": 0.4758, + "step": 3961 + }, + { + "epoch": 0.33, + "learning_rate": 1.560026363564476e-05, + "loss": 0.5156, + "step": 3962 + }, + { + "epoch": 0.33, + "learning_rate": 1.5598018342227645e-05, + "loss": 0.4874, + "step": 3963 + }, + { + "epoch": 0.33, + "learning_rate": 1.5595772637715345e-05, + "loss": 0.4942, + "step": 3964 + }, + { + "epoch": 0.33, + "learning_rate": 1.5593526522272774e-05, + "loss": 0.4825, + "step": 3965 + }, + { + "epoch": 0.33, + "learning_rate": 1.5591279996064884e-05, + "loss": 0.4938, + "step": 3966 + }, + { + "epoch": 0.33, + "learning_rate": 1.558903305925665e-05, + "loss": 0.5092, + "step": 3967 + }, + { + "epoch": 0.33, + "learning_rate": 1.5586785712013073e-05, + "loss": 0.4806, + "step": 3968 + }, + { + "epoch": 0.33, + "learning_rate": 1.5584537954499186e-05, + "loss": 0.5001, + "step": 3969 + }, + { + "epoch": 0.33, + "learning_rate": 1.5582289786880064e-05, + "loss": 0.4897, + "step": 3970 + }, + { + "epoch": 0.33, + "learning_rate": 1.5580041209320797e-05, + "loss": 0.4813, + "step": 3971 + }, + { + "epoch": 0.33, + "learning_rate": 1.5577792221986512e-05, + "loss": 0.4873, + "step": 3972 + }, + { + "epoch": 0.33, + "learning_rate": 1.5575542825042368e-05, + "loss": 0.4936, + "step": 3973 + }, + { + "epoch": 0.33, + "learning_rate": 1.557329301865355e-05, + "loss": 0.4823, + "step": 3974 + }, + { + "epoch": 0.33, + "learning_rate": 1.557104280298527e-05, + "loss": 0.4738, + "step": 3975 + }, + { + "epoch": 0.33, + "learning_rate": 1.556879217820278e-05, + "loss": 0.4857, + "step": 3976 + }, + { + "epoch": 0.33, + "learning_rate": 1.5566541144471355e-05, + "loss": 0.4782, + "step": 3977 + }, + { + "epoch": 0.33, + "learning_rate": 1.55642897019563e-05, + "loss": 0.5053, + "step": 3978 + }, + { + "epoch": 0.33, + "learning_rate": 1.5562037850822954e-05, + "loss": 0.4842, + "step": 3979 + }, + { + "epoch": 0.33, + "learning_rate": 1.5559785591236683e-05, + "loss": 0.4971, + "step": 3980 + }, + { + "epoch": 0.33, + "learning_rate": 1.5557532923362883e-05, + "loss": 0.4861, + "step": 3981 + }, + { + "epoch": 0.33, + "learning_rate": 1.555527984736698e-05, + "loss": 0.4977, + "step": 3982 + }, + { + "epoch": 0.33, + "learning_rate": 1.555302636341443e-05, + "loss": 0.5032, + "step": 3983 + }, + { + "epoch": 0.33, + "learning_rate": 1.5550772471670724e-05, + "loss": 0.4829, + "step": 3984 + }, + { + "epoch": 0.33, + "learning_rate": 1.5548518172301373e-05, + "loss": 0.5062, + "step": 3985 + }, + { + "epoch": 0.33, + "learning_rate": 1.5546263465471926e-05, + "loss": 0.4957, + "step": 3986 + }, + { + "epoch": 0.33, + "learning_rate": 1.554400835134796e-05, + "loss": 0.4942, + "step": 3987 + }, + { + "epoch": 0.33, + "learning_rate": 1.554175283009508e-05, + "loss": 0.4794, + "step": 3988 + }, + { + "epoch": 0.33, + "learning_rate": 1.5539496901878915e-05, + "loss": 0.4872, + "step": 3989 + }, + { + "epoch": 0.33, + "learning_rate": 1.5537240566865145e-05, + "loss": 0.4901, + "step": 3990 + }, + { + "epoch": 0.33, + "learning_rate": 1.553498382521946e-05, + "loss": 0.4855, + "step": 3991 + }, + { + "epoch": 0.33, + "learning_rate": 1.5532726677107583e-05, + "loss": 0.4874, + "step": 3992 + }, + { + "epoch": 0.33, + "learning_rate": 1.553046912269527e-05, + "loss": 0.4815, + "step": 3993 + }, + { + "epoch": 0.33, + "learning_rate": 1.5528211162148305e-05, + "loss": 0.5012, + "step": 3994 + }, + { + "epoch": 0.33, + "learning_rate": 1.552595279563251e-05, + "loss": 0.4831, + "step": 3995 + }, + { + "epoch": 0.33, + "learning_rate": 1.5523694023313723e-05, + "loss": 0.487, + "step": 3996 + }, + { + "epoch": 0.33, + "learning_rate": 1.5521434845357824e-05, + "loss": 0.4729, + "step": 3997 + }, + { + "epoch": 0.33, + "learning_rate": 1.5519175261930716e-05, + "loss": 0.4859, + "step": 3998 + }, + { + "epoch": 0.33, + "learning_rate": 1.551691527319833e-05, + "loss": 0.4979, + "step": 3999 + }, + { + "epoch": 0.33, + "learning_rate": 1.551465487932663e-05, + "loss": 0.4947, + "step": 4000 + }, + { + "epoch": 0.33, + "learning_rate": 1.551239408048162e-05, + "loss": 0.48, + "step": 4001 + }, + { + "epoch": 0.33, + "learning_rate": 1.5510132876829313e-05, + "loss": 0.4818, + "step": 4002 + }, + { + "epoch": 0.33, + "learning_rate": 1.5507871268535765e-05, + "loss": 0.4845, + "step": 4003 + }, + { + "epoch": 0.33, + "learning_rate": 1.550560925576706e-05, + "loss": 0.5188, + "step": 4004 + }, + { + "epoch": 0.34, + "learning_rate": 1.5503346838689314e-05, + "loss": 0.479, + "step": 4005 + }, + { + "epoch": 0.34, + "learning_rate": 1.5501084017468665e-05, + "loss": 0.5038, + "step": 4006 + }, + { + "epoch": 0.34, + "learning_rate": 1.5498820792271284e-05, + "loss": 0.5002, + "step": 4007 + }, + { + "epoch": 0.34, + "learning_rate": 1.549655716326338e-05, + "loss": 0.5109, + "step": 4008 + }, + { + "epoch": 0.34, + "learning_rate": 1.5494293130611175e-05, + "loss": 0.4899, + "step": 4009 + }, + { + "epoch": 0.34, + "learning_rate": 1.5492028694480938e-05, + "loss": 0.4973, + "step": 4010 + }, + { + "epoch": 0.34, + "learning_rate": 1.5489763855038954e-05, + "loss": 0.4873, + "step": 4011 + }, + { + "epoch": 0.34, + "learning_rate": 1.548749861245155e-05, + "loss": 0.4707, + "step": 4012 + }, + { + "epoch": 0.34, + "learning_rate": 1.548523296688507e-05, + "loss": 0.48, + "step": 4013 + }, + { + "epoch": 0.34, + "learning_rate": 1.5482966918505897e-05, + "loss": 0.4909, + "step": 4014 + }, + { + "epoch": 0.34, + "learning_rate": 1.5480700467480437e-05, + "loss": 0.496, + "step": 4015 + }, + { + "epoch": 0.34, + "learning_rate": 1.547843361397513e-05, + "loss": 0.4784, + "step": 4016 + }, + { + "epoch": 0.34, + "learning_rate": 1.5476166358156446e-05, + "loss": 0.49, + "step": 4017 + }, + { + "epoch": 0.34, + "learning_rate": 1.5473898700190884e-05, + "loss": 0.5039, + "step": 4018 + }, + { + "epoch": 0.34, + "learning_rate": 1.5471630640244966e-05, + "loss": 0.4724, + "step": 4019 + }, + { + "epoch": 0.34, + "learning_rate": 1.5469362178485252e-05, + "loss": 0.481, + "step": 4020 + }, + { + "epoch": 0.34, + "learning_rate": 1.546709331507833e-05, + "loss": 0.5026, + "step": 4021 + }, + { + "epoch": 0.34, + "learning_rate": 1.5464824050190816e-05, + "loss": 0.4854, + "step": 4022 + }, + { + "epoch": 0.34, + "learning_rate": 1.5462554383989347e-05, + "loss": 0.5195, + "step": 4023 + }, + { + "epoch": 0.34, + "learning_rate": 1.546028431664061e-05, + "loss": 0.4913, + "step": 4024 + }, + { + "epoch": 0.34, + "learning_rate": 1.5458013848311305e-05, + "loss": 0.4944, + "step": 4025 + }, + { + "epoch": 0.34, + "learning_rate": 1.545574297916816e-05, + "loss": 0.4911, + "step": 4026 + }, + { + "epoch": 0.34, + "learning_rate": 1.5453471709377945e-05, + "loss": 0.4948, + "step": 4027 + }, + { + "epoch": 0.34, + "learning_rate": 1.545120003910745e-05, + "loss": 0.4996, + "step": 4028 + }, + { + "epoch": 0.34, + "learning_rate": 1.54489279685235e-05, + "loss": 0.4778, + "step": 4029 + }, + { + "epoch": 0.34, + "learning_rate": 1.544665549779294e-05, + "loss": 0.4836, + "step": 4030 + }, + { + "epoch": 0.34, + "learning_rate": 1.5444382627082657e-05, + "loss": 0.4674, + "step": 4031 + }, + { + "epoch": 0.34, + "learning_rate": 1.5442109356559556e-05, + "loss": 0.4828, + "step": 4032 + }, + { + "epoch": 0.34, + "learning_rate": 1.543983568639058e-05, + "loss": 0.4952, + "step": 4033 + }, + { + "epoch": 0.34, + "learning_rate": 1.5437561616742703e-05, + "loss": 0.4733, + "step": 4034 + }, + { + "epoch": 0.34, + "learning_rate": 1.543528714778291e-05, + "loss": 0.4976, + "step": 4035 + }, + { + "epoch": 0.34, + "learning_rate": 1.543301227967824e-05, + "loss": 0.4952, + "step": 4036 + }, + { + "epoch": 0.34, + "learning_rate": 1.543073701259574e-05, + "loss": 0.496, + "step": 4037 + }, + { + "epoch": 0.34, + "learning_rate": 1.542846134670251e-05, + "loss": 0.4901, + "step": 4038 + }, + { + "epoch": 0.34, + "learning_rate": 1.5426185282165652e-05, + "loss": 0.5044, + "step": 4039 + }, + { + "epoch": 0.34, + "learning_rate": 1.5423908819152317e-05, + "loss": 0.4779, + "step": 4040 + }, + { + "epoch": 0.34, + "learning_rate": 1.542163195782968e-05, + "loss": 0.5076, + "step": 4041 + }, + { + "epoch": 0.34, + "learning_rate": 1.5419354698364944e-05, + "loss": 0.4836, + "step": 4042 + }, + { + "epoch": 0.34, + "learning_rate": 1.5417077040925334e-05, + "loss": 0.4994, + "step": 4043 + }, + { + "epoch": 0.34, + "learning_rate": 1.541479898567812e-05, + "loss": 0.5221, + "step": 4044 + }, + { + "epoch": 0.34, + "learning_rate": 1.541252053279059e-05, + "loss": 0.4938, + "step": 4045 + }, + { + "epoch": 0.34, + "learning_rate": 1.541024168243007e-05, + "loss": 0.4794, + "step": 4046 + }, + { + "epoch": 0.34, + "learning_rate": 1.5407962434763897e-05, + "loss": 0.4798, + "step": 4047 + }, + { + "epoch": 0.34, + "learning_rate": 1.5405682789959455e-05, + "loss": 0.4878, + "step": 4048 + }, + { + "epoch": 0.34, + "learning_rate": 1.5403402748184156e-05, + "loss": 0.5025, + "step": 4049 + }, + { + "epoch": 0.34, + "learning_rate": 1.5401122309605437e-05, + "loss": 0.4778, + "step": 4050 + }, + { + "epoch": 0.34, + "learning_rate": 1.5398841474390754e-05, + "loss": 0.4801, + "step": 4051 + }, + { + "epoch": 0.34, + "learning_rate": 1.5396560242707613e-05, + "loss": 0.4845, + "step": 4052 + }, + { + "epoch": 0.34, + "learning_rate": 1.5394278614723535e-05, + "loss": 0.4736, + "step": 4053 + }, + { + "epoch": 0.34, + "learning_rate": 1.5391996590606066e-05, + "loss": 0.5036, + "step": 4054 + }, + { + "epoch": 0.34, + "learning_rate": 1.53897141705228e-05, + "loss": 0.5004, + "step": 4055 + }, + { + "epoch": 0.34, + "learning_rate": 1.538743135464134e-05, + "loss": 0.4898, + "step": 4056 + }, + { + "epoch": 0.34, + "learning_rate": 1.5385148143129328e-05, + "loss": 0.4723, + "step": 4057 + }, + { + "epoch": 0.34, + "learning_rate": 1.5382864536154437e-05, + "loss": 0.5157, + "step": 4058 + }, + { + "epoch": 0.34, + "learning_rate": 1.5380580533884364e-05, + "loss": 0.4803, + "step": 4059 + }, + { + "epoch": 0.34, + "learning_rate": 1.5378296136486837e-05, + "loss": 0.5016, + "step": 4060 + }, + { + "epoch": 0.34, + "learning_rate": 1.5376011344129608e-05, + "loss": 0.5045, + "step": 4061 + }, + { + "epoch": 0.34, + "learning_rate": 1.537372615698047e-05, + "loss": 0.4805, + "step": 4062 + }, + { + "epoch": 0.34, + "learning_rate": 1.5371440575207233e-05, + "loss": 0.5004, + "step": 4063 + }, + { + "epoch": 0.34, + "learning_rate": 1.536915459897774e-05, + "loss": 0.4941, + "step": 4064 + }, + { + "epoch": 0.34, + "learning_rate": 1.5366868228459866e-05, + "loss": 0.4623, + "step": 4065 + }, + { + "epoch": 0.34, + "learning_rate": 1.536458146382151e-05, + "loss": 0.4911, + "step": 4066 + }, + { + "epoch": 0.34, + "learning_rate": 1.536229430523061e-05, + "loss": 0.4749, + "step": 4067 + }, + { + "epoch": 0.34, + "learning_rate": 1.5360006752855113e-05, + "loss": 0.4797, + "step": 4068 + }, + { + "epoch": 0.34, + "learning_rate": 1.535771880686302e-05, + "loss": 0.4853, + "step": 4069 + }, + { + "epoch": 0.34, + "learning_rate": 1.5355430467422343e-05, + "loss": 0.4968, + "step": 4070 + }, + { + "epoch": 0.34, + "learning_rate": 1.535314173470112e-05, + "loss": 0.4907, + "step": 4071 + }, + { + "epoch": 0.34, + "learning_rate": 1.5350852608867436e-05, + "loss": 0.4847, + "step": 4072 + }, + { + "epoch": 0.34, + "learning_rate": 1.5348563090089394e-05, + "loss": 0.5151, + "step": 4073 + }, + { + "epoch": 0.34, + "learning_rate": 1.5346273178535126e-05, + "loss": 0.4775, + "step": 4074 + }, + { + "epoch": 0.34, + "learning_rate": 1.534398287437279e-05, + "loss": 0.4907, + "step": 4075 + }, + { + "epoch": 0.34, + "learning_rate": 1.5341692177770583e-05, + "loss": 0.466, + "step": 4076 + }, + { + "epoch": 0.34, + "learning_rate": 1.5339401088896715e-05, + "loss": 0.5019, + "step": 4077 + }, + { + "epoch": 0.34, + "learning_rate": 1.533710960791944e-05, + "loss": 0.4801, + "step": 4078 + }, + { + "epoch": 0.34, + "learning_rate": 1.5334817735007037e-05, + "loss": 0.4967, + "step": 4079 + }, + { + "epoch": 0.34, + "learning_rate": 1.533252547032781e-05, + "loss": 0.4966, + "step": 4080 + }, + { + "epoch": 0.34, + "learning_rate": 1.533023281405009e-05, + "loss": 0.5023, + "step": 4081 + }, + { + "epoch": 0.34, + "learning_rate": 1.5327939766342237e-05, + "loss": 0.5038, + "step": 4082 + }, + { + "epoch": 0.34, + "learning_rate": 1.5325646327372658e-05, + "loss": 0.4999, + "step": 4083 + }, + { + "epoch": 0.34, + "learning_rate": 1.532335249730976e-05, + "loss": 0.4819, + "step": 4084 + }, + { + "epoch": 0.34, + "learning_rate": 1.5321058276321988e-05, + "loss": 0.4924, + "step": 4085 + }, + { + "epoch": 0.34, + "learning_rate": 1.5318763664577838e-05, + "loss": 0.4895, + "step": 4086 + }, + { + "epoch": 0.34, + "learning_rate": 1.5316468662245805e-05, + "loss": 0.4882, + "step": 4087 + }, + { + "epoch": 0.34, + "learning_rate": 1.531417326949442e-05, + "loss": 0.4849, + "step": 4088 + }, + { + "epoch": 0.34, + "learning_rate": 1.5311877486492264e-05, + "loss": 0.4824, + "step": 4089 + }, + { + "epoch": 0.34, + "learning_rate": 1.5309581313407914e-05, + "loss": 0.483, + "step": 4090 + }, + { + "epoch": 0.34, + "learning_rate": 1.5307284750409993e-05, + "loss": 0.4939, + "step": 4091 + }, + { + "epoch": 0.34, + "learning_rate": 1.530498779766716e-05, + "loss": 0.5149, + "step": 4092 + }, + { + "epoch": 0.34, + "learning_rate": 1.5302690455348085e-05, + "loss": 0.4828, + "step": 4093 + }, + { + "epoch": 0.34, + "learning_rate": 1.530039272362148e-05, + "loss": 0.4805, + "step": 4094 + }, + { + "epoch": 0.34, + "learning_rate": 1.5298094602656077e-05, + "loss": 0.4946, + "step": 4095 + }, + { + "epoch": 0.34, + "learning_rate": 1.5295796092620646e-05, + "loss": 0.4826, + "step": 4096 + }, + { + "epoch": 0.34, + "learning_rate": 1.5293497193683974e-05, + "loss": 0.5091, + "step": 4097 + }, + { + "epoch": 0.34, + "learning_rate": 1.5291197906014886e-05, + "loss": 0.4893, + "step": 4098 + }, + { + "epoch": 0.34, + "learning_rate": 1.5288898229782234e-05, + "loss": 0.4873, + "step": 4099 + }, + { + "epoch": 0.34, + "learning_rate": 1.5286598165154892e-05, + "loss": 0.4815, + "step": 4100 + }, + { + "epoch": 0.34, + "learning_rate": 1.5284297712301773e-05, + "loss": 0.4878, + "step": 4101 + }, + { + "epoch": 0.34, + "learning_rate": 1.5281996871391805e-05, + "loss": 0.4834, + "step": 4102 + }, + { + "epoch": 0.34, + "learning_rate": 1.5279695642593958e-05, + "loss": 0.4621, + "step": 4103 + }, + { + "epoch": 0.34, + "learning_rate": 1.527739402607722e-05, + "loss": 0.4742, + "step": 4104 + }, + { + "epoch": 0.34, + "learning_rate": 1.527509202201062e-05, + "loss": 0.4787, + "step": 4105 + }, + { + "epoch": 0.34, + "learning_rate": 1.5272789630563202e-05, + "loss": 0.495, + "step": 4106 + }, + { + "epoch": 0.34, + "learning_rate": 1.527048685190404e-05, + "loss": 0.495, + "step": 4107 + }, + { + "epoch": 0.34, + "learning_rate": 1.5268183686202245e-05, + "loss": 0.51, + "step": 4108 + }, + { + "epoch": 0.34, + "learning_rate": 1.5265880133626956e-05, + "loss": 0.4721, + "step": 4109 + }, + { + "epoch": 0.34, + "learning_rate": 1.5263576194347334e-05, + "loss": 0.498, + "step": 4110 + }, + { + "epoch": 0.34, + "learning_rate": 1.5261271868532568e-05, + "loss": 0.5005, + "step": 4111 + }, + { + "epoch": 0.34, + "learning_rate": 1.5258967156351878e-05, + "loss": 0.4735, + "step": 4112 + }, + { + "epoch": 0.34, + "learning_rate": 1.525666205797451e-05, + "loss": 0.4863, + "step": 4113 + }, + { + "epoch": 0.34, + "learning_rate": 1.5254356573569748e-05, + "loss": 0.4886, + "step": 4114 + }, + { + "epoch": 0.34, + "learning_rate": 1.5252050703306895e-05, + "loss": 0.4866, + "step": 4115 + }, + { + "epoch": 0.34, + "learning_rate": 1.5249744447355282e-05, + "loss": 0.5044, + "step": 4116 + }, + { + "epoch": 0.34, + "learning_rate": 1.5247437805884273e-05, + "loss": 0.4863, + "step": 4117 + }, + { + "epoch": 0.34, + "learning_rate": 1.5245130779063255e-05, + "loss": 0.5085, + "step": 4118 + }, + { + "epoch": 0.34, + "learning_rate": 1.524282336706165e-05, + "loss": 0.4725, + "step": 4119 + }, + { + "epoch": 0.34, + "learning_rate": 1.5240515570048903e-05, + "loss": 0.4866, + "step": 4120 + }, + { + "epoch": 0.34, + "learning_rate": 1.5238207388194493e-05, + "loss": 0.485, + "step": 4121 + }, + { + "epoch": 0.34, + "learning_rate": 1.5235898821667916e-05, + "loss": 0.5004, + "step": 4122 + }, + { + "epoch": 0.34, + "learning_rate": 1.5233589870638708e-05, + "loss": 0.4852, + "step": 4123 + }, + { + "epoch": 0.35, + "learning_rate": 1.5231280535276426e-05, + "loss": 0.4778, + "step": 4124 + }, + { + "epoch": 0.35, + "learning_rate": 1.5228970815750666e-05, + "loss": 0.4932, + "step": 4125 + }, + { + "epoch": 0.35, + "learning_rate": 1.5226660712231032e-05, + "loss": 0.4973, + "step": 4126 + }, + { + "epoch": 0.35, + "learning_rate": 1.5224350224887179e-05, + "loss": 0.4899, + "step": 4127 + }, + { + "epoch": 0.35, + "learning_rate": 1.5222039353888774e-05, + "loss": 0.4763, + "step": 4128 + }, + { + "epoch": 0.35, + "learning_rate": 1.5219728099405516e-05, + "loss": 0.4994, + "step": 4129 + }, + { + "epoch": 0.35, + "learning_rate": 1.521741646160714e-05, + "loss": 0.4798, + "step": 4130 + }, + { + "epoch": 0.35, + "learning_rate": 1.5215104440663399e-05, + "loss": 0.4698, + "step": 4131 + }, + { + "epoch": 0.35, + "learning_rate": 1.521279203674408e-05, + "loss": 0.472, + "step": 4132 + }, + { + "epoch": 0.35, + "learning_rate": 1.5210479250018995e-05, + "loss": 0.4933, + "step": 4133 + }, + { + "epoch": 0.35, + "learning_rate": 1.5208166080657982e-05, + "loss": 0.4828, + "step": 4134 + }, + { + "epoch": 0.35, + "learning_rate": 1.520585252883092e-05, + "loss": 0.497, + "step": 4135 + }, + { + "epoch": 0.35, + "learning_rate": 1.5203538594707699e-05, + "loss": 0.4824, + "step": 4136 + }, + { + "epoch": 0.35, + "learning_rate": 1.520122427845825e-05, + "loss": 0.4743, + "step": 4137 + }, + { + "epoch": 0.35, + "learning_rate": 1.5198909580252517e-05, + "loss": 0.5035, + "step": 4138 + }, + { + "epoch": 0.35, + "learning_rate": 1.519659450026049e-05, + "loss": 0.5019, + "step": 4139 + }, + { + "epoch": 0.35, + "learning_rate": 1.519427903865218e-05, + "loss": 0.5058, + "step": 4140 + }, + { + "epoch": 0.35, + "learning_rate": 1.519196319559762e-05, + "loss": 0.4959, + "step": 4141 + }, + { + "epoch": 0.35, + "learning_rate": 1.518964697126688e-05, + "loss": 0.4922, + "step": 4142 + }, + { + "epoch": 0.35, + "learning_rate": 1.518733036583005e-05, + "loss": 0.5021, + "step": 4143 + }, + { + "epoch": 0.35, + "learning_rate": 1.5185013379457254e-05, + "loss": 0.4927, + "step": 4144 + }, + { + "epoch": 0.35, + "learning_rate": 1.5182696012318641e-05, + "loss": 0.5034, + "step": 4145 + }, + { + "epoch": 0.35, + "learning_rate": 1.518037826458439e-05, + "loss": 0.498, + "step": 4146 + }, + { + "epoch": 0.35, + "learning_rate": 1.5178060136424706e-05, + "loss": 0.5033, + "step": 4147 + }, + { + "epoch": 0.35, + "learning_rate": 1.5175741628009824e-05, + "loss": 0.4818, + "step": 4148 + }, + { + "epoch": 0.35, + "learning_rate": 1.5173422739510003e-05, + "loss": 0.5017, + "step": 4149 + }, + { + "epoch": 0.35, + "learning_rate": 1.5171103471095533e-05, + "loss": 0.4716, + "step": 4150 + }, + { + "epoch": 0.35, + "learning_rate": 1.5168783822936735e-05, + "loss": 0.4648, + "step": 4151 + }, + { + "epoch": 0.35, + "learning_rate": 1.516646379520395e-05, + "loss": 0.4952, + "step": 4152 + }, + { + "epoch": 0.35, + "learning_rate": 1.5164143388067554e-05, + "loss": 0.4907, + "step": 4153 + }, + { + "epoch": 0.35, + "learning_rate": 1.5161822601697945e-05, + "loss": 0.4882, + "step": 4154 + }, + { + "epoch": 0.35, + "learning_rate": 1.5159501436265553e-05, + "loss": 0.4774, + "step": 4155 + }, + { + "epoch": 0.35, + "learning_rate": 1.5157179891940837e-05, + "loss": 0.4901, + "step": 4156 + }, + { + "epoch": 0.35, + "learning_rate": 1.5154857968894278e-05, + "loss": 0.4773, + "step": 4157 + }, + { + "epoch": 0.35, + "learning_rate": 1.5152535667296395e-05, + "loss": 0.4894, + "step": 4158 + }, + { + "epoch": 0.35, + "learning_rate": 1.5150212987317721e-05, + "loss": 0.4976, + "step": 4159 + }, + { + "epoch": 0.35, + "learning_rate": 1.5147889929128825e-05, + "loss": 0.4964, + "step": 4160 + }, + { + "epoch": 0.35, + "learning_rate": 1.5145566492900305e-05, + "loss": 0.4747, + "step": 4161 + }, + { + "epoch": 0.35, + "learning_rate": 1.5143242678802787e-05, + "loss": 0.4627, + "step": 4162 + }, + { + "epoch": 0.35, + "learning_rate": 1.5140918487006918e-05, + "loss": 0.483, + "step": 4163 + }, + { + "epoch": 0.35, + "learning_rate": 1.5138593917683374e-05, + "loss": 0.4939, + "step": 4164 + }, + { + "epoch": 0.35, + "learning_rate": 1.513626897100287e-05, + "loss": 0.4938, + "step": 4165 + }, + { + "epoch": 0.35, + "learning_rate": 1.5133943647136131e-05, + "loss": 0.4925, + "step": 4166 + }, + { + "epoch": 0.35, + "learning_rate": 1.5131617946253928e-05, + "loss": 0.4871, + "step": 4167 + }, + { + "epoch": 0.35, + "learning_rate": 1.5129291868527052e-05, + "loss": 0.4939, + "step": 4168 + }, + { + "epoch": 0.35, + "learning_rate": 1.5126965414126309e-05, + "loss": 0.4752, + "step": 4169 + }, + { + "epoch": 0.35, + "learning_rate": 1.512463858322255e-05, + "loss": 0.4781, + "step": 4170 + }, + { + "epoch": 0.35, + "learning_rate": 1.5122311375986649e-05, + "loss": 0.4782, + "step": 4171 + }, + { + "epoch": 0.35, + "learning_rate": 1.511998379258951e-05, + "loss": 0.4739, + "step": 4172 + }, + { + "epoch": 0.35, + "learning_rate": 1.5117655833202052e-05, + "loss": 0.5065, + "step": 4173 + }, + { + "epoch": 0.35, + "learning_rate": 1.5115327497995238e-05, + "loss": 0.5288, + "step": 4174 + }, + { + "epoch": 0.35, + "learning_rate": 1.511299878714005e-05, + "loss": 0.4939, + "step": 4175 + }, + { + "epoch": 0.35, + "learning_rate": 1.5110669700807496e-05, + "loss": 0.5027, + "step": 4176 + }, + { + "epoch": 0.35, + "learning_rate": 1.5108340239168614e-05, + "loss": 0.5097, + "step": 4177 + }, + { + "epoch": 0.35, + "learning_rate": 1.5106010402394477e-05, + "loss": 0.4741, + "step": 4178 + }, + { + "epoch": 0.35, + "learning_rate": 1.5103680190656169e-05, + "loss": 0.4856, + "step": 4179 + }, + { + "epoch": 0.35, + "learning_rate": 1.5101349604124816e-05, + "loss": 0.5238, + "step": 4180 + }, + { + "epoch": 0.35, + "learning_rate": 1.5099018642971568e-05, + "loss": 0.4797, + "step": 4181 + }, + { + "epoch": 0.35, + "learning_rate": 1.5096687307367601e-05, + "loss": 0.5027, + "step": 4182 + }, + { + "epoch": 0.35, + "learning_rate": 1.5094355597484111e-05, + "loss": 0.481, + "step": 4183 + }, + { + "epoch": 0.35, + "learning_rate": 1.509202351349234e-05, + "loss": 0.5015, + "step": 4184 + }, + { + "epoch": 0.35, + "learning_rate": 1.508969105556354e-05, + "loss": 0.4847, + "step": 4185 + }, + { + "epoch": 0.35, + "learning_rate": 1.5087358223869e-05, + "loss": 0.4803, + "step": 4186 + }, + { + "epoch": 0.35, + "learning_rate": 1.5085025018580029e-05, + "loss": 0.4904, + "step": 4187 + }, + { + "epoch": 0.35, + "learning_rate": 1.5082691439867973e-05, + "loss": 0.4654, + "step": 4188 + }, + { + "epoch": 0.35, + "learning_rate": 1.5080357487904198e-05, + "loss": 0.4828, + "step": 4189 + }, + { + "epoch": 0.35, + "learning_rate": 1.5078023162860099e-05, + "loss": 0.5049, + "step": 4190 + }, + { + "epoch": 0.35, + "learning_rate": 1.5075688464907099e-05, + "loss": 0.4923, + "step": 4191 + }, + { + "epoch": 0.35, + "learning_rate": 1.5073353394216652e-05, + "loss": 0.4693, + "step": 4192 + }, + { + "epoch": 0.35, + "learning_rate": 1.5071017950960234e-05, + "loss": 0.4917, + "step": 4193 + }, + { + "epoch": 0.35, + "learning_rate": 1.5068682135309347e-05, + "loss": 0.495, + "step": 4194 + }, + { + "epoch": 0.35, + "learning_rate": 1.5066345947435525e-05, + "loss": 0.4869, + "step": 4195 + }, + { + "epoch": 0.35, + "learning_rate": 1.5064009387510333e-05, + "loss": 0.4836, + "step": 4196 + }, + { + "epoch": 0.35, + "learning_rate": 1.5061672455705352e-05, + "loss": 0.4999, + "step": 4197 + }, + { + "epoch": 0.35, + "learning_rate": 1.50593351521922e-05, + "loss": 0.5058, + "step": 4198 + }, + { + "epoch": 0.35, + "learning_rate": 1.505699747714252e-05, + "loss": 0.4897, + "step": 4199 + }, + { + "epoch": 0.35, + "learning_rate": 1.5054659430727974e-05, + "loss": 0.4752, + "step": 4200 + }, + { + "epoch": 0.35, + "learning_rate": 1.5052321013120263e-05, + "loss": 0.4942, + "step": 4201 + }, + { + "epoch": 0.35, + "learning_rate": 1.5049982224491115e-05, + "loss": 0.4665, + "step": 4202 + }, + { + "epoch": 0.35, + "learning_rate": 1.5047643065012276e-05, + "loss": 0.497, + "step": 4203 + }, + { + "epoch": 0.35, + "learning_rate": 1.5045303534855524e-05, + "loss": 0.5008, + "step": 4204 + }, + { + "epoch": 0.35, + "learning_rate": 1.5042963634192667e-05, + "loss": 0.4908, + "step": 4205 + }, + { + "epoch": 0.35, + "learning_rate": 1.5040623363195535e-05, + "loss": 0.498, + "step": 4206 + }, + { + "epoch": 0.35, + "learning_rate": 1.5038282722035986e-05, + "loss": 0.4864, + "step": 4207 + }, + { + "epoch": 0.35, + "learning_rate": 1.5035941710885915e-05, + "loss": 0.5004, + "step": 4208 + }, + { + "epoch": 0.35, + "learning_rate": 1.5033600329917227e-05, + "loss": 0.5207, + "step": 4209 + }, + { + "epoch": 0.35, + "learning_rate": 1.5031258579301868e-05, + "loss": 0.4731, + "step": 4210 + }, + { + "epoch": 0.35, + "learning_rate": 1.5028916459211804e-05, + "loss": 0.4995, + "step": 4211 + }, + { + "epoch": 0.35, + "learning_rate": 1.5026573969819035e-05, + "loss": 0.4928, + "step": 4212 + }, + { + "epoch": 0.35, + "learning_rate": 1.502423111129558e-05, + "loss": 0.4968, + "step": 4213 + }, + { + "epoch": 0.35, + "learning_rate": 1.5021887883813488e-05, + "loss": 0.4896, + "step": 4214 + }, + { + "epoch": 0.35, + "learning_rate": 1.501954428754484e-05, + "loss": 0.4845, + "step": 4215 + }, + { + "epoch": 0.35, + "learning_rate": 1.5017200322661735e-05, + "loss": 0.4936, + "step": 4216 + }, + { + "epoch": 0.35, + "learning_rate": 1.5014855989336308e-05, + "loss": 0.4902, + "step": 4217 + }, + { + "epoch": 0.35, + "learning_rate": 1.5012511287740715e-05, + "loss": 0.4821, + "step": 4218 + }, + { + "epoch": 0.35, + "learning_rate": 1.5010166218047139e-05, + "loss": 0.4979, + "step": 4219 + }, + { + "epoch": 0.35, + "learning_rate": 1.50078207804278e-05, + "loss": 0.4948, + "step": 4220 + }, + { + "epoch": 0.35, + "learning_rate": 1.5005474975054928e-05, + "loss": 0.4824, + "step": 4221 + }, + { + "epoch": 0.35, + "learning_rate": 1.5003128802100792e-05, + "loss": 0.4921, + "step": 4222 + }, + { + "epoch": 0.35, + "learning_rate": 1.500078226173769e-05, + "loss": 0.4964, + "step": 4223 + }, + { + "epoch": 0.35, + "learning_rate": 1.4998435354137937e-05, + "loss": 0.4867, + "step": 4224 + }, + { + "epoch": 0.35, + "learning_rate": 1.4996088079473884e-05, + "loss": 0.4999, + "step": 4225 + }, + { + "epoch": 0.35, + "learning_rate": 1.4993740437917898e-05, + "loss": 0.5114, + "step": 4226 + }, + { + "epoch": 0.35, + "learning_rate": 1.4991392429642389e-05, + "loss": 0.4886, + "step": 4227 + }, + { + "epoch": 0.35, + "learning_rate": 1.498904405481978e-05, + "loss": 0.4818, + "step": 4228 + }, + { + "epoch": 0.35, + "learning_rate": 1.4986695313622525e-05, + "loss": 0.5041, + "step": 4229 + }, + { + "epoch": 0.35, + "learning_rate": 1.4984346206223108e-05, + "loss": 0.4954, + "step": 4230 + }, + { + "epoch": 0.35, + "learning_rate": 1.4981996732794038e-05, + "loss": 0.494, + "step": 4231 + }, + { + "epoch": 0.35, + "learning_rate": 1.4979646893507847e-05, + "loss": 0.4941, + "step": 4232 + }, + { + "epoch": 0.35, + "learning_rate": 1.4977296688537101e-05, + "loss": 0.4994, + "step": 4233 + }, + { + "epoch": 0.35, + "learning_rate": 1.4974946118054392e-05, + "loss": 0.4972, + "step": 4234 + }, + { + "epoch": 0.35, + "learning_rate": 1.4972595182232328e-05, + "loss": 0.4681, + "step": 4235 + }, + { + "epoch": 0.35, + "learning_rate": 1.4970243881243558e-05, + "loss": 0.4936, + "step": 4236 + }, + { + "epoch": 0.35, + "learning_rate": 1.4967892215260751e-05, + "loss": 0.4879, + "step": 4237 + }, + { + "epoch": 0.35, + "learning_rate": 1.49655401844566e-05, + "loss": 0.4786, + "step": 4238 + }, + { + "epoch": 0.35, + "learning_rate": 1.4963187789003835e-05, + "loss": 0.4921, + "step": 4239 + }, + { + "epoch": 0.35, + "learning_rate": 1.49608350290752e-05, + "loss": 0.4926, + "step": 4240 + }, + { + "epoch": 0.35, + "learning_rate": 1.4958481904843473e-05, + "loss": 0.4689, + "step": 4241 + }, + { + "epoch": 0.35, + "learning_rate": 1.4956128416481459e-05, + "loss": 0.478, + "step": 4242 + }, + { + "epoch": 0.35, + "learning_rate": 1.4953774564161991e-05, + "loss": 0.4967, + "step": 4243 + }, + { + "epoch": 0.36, + "learning_rate": 1.495142034805792e-05, + "loss": 0.4759, + "step": 4244 + }, + { + "epoch": 0.36, + "learning_rate": 1.4949065768342136e-05, + "loss": 0.4725, + "step": 4245 + }, + { + "epoch": 0.36, + "learning_rate": 1.4946710825187545e-05, + "loss": 0.4913, + "step": 4246 + }, + { + "epoch": 0.36, + "learning_rate": 1.4944355518767086e-05, + "loss": 0.4778, + "step": 4247 + }, + { + "epoch": 0.36, + "learning_rate": 1.4941999849253723e-05, + "loss": 0.4754, + "step": 4248 + }, + { + "epoch": 0.36, + "learning_rate": 1.4939643816820449e-05, + "loss": 0.4989, + "step": 4249 + }, + { + "epoch": 0.36, + "learning_rate": 1.4937287421640277e-05, + "loss": 0.4903, + "step": 4250 + }, + { + "epoch": 0.36, + "learning_rate": 1.493493066388625e-05, + "loss": 0.4936, + "step": 4251 + }, + { + "epoch": 0.36, + "learning_rate": 1.4932573543731441e-05, + "loss": 0.4945, + "step": 4252 + }, + { + "epoch": 0.36, + "learning_rate": 1.493021606134895e-05, + "loss": 0.5001, + "step": 4253 + }, + { + "epoch": 0.36, + "learning_rate": 1.4927858216911897e-05, + "loss": 0.4595, + "step": 4254 + }, + { + "epoch": 0.36, + "learning_rate": 1.492550001059343e-05, + "loss": 0.4922, + "step": 4255 + }, + { + "epoch": 0.36, + "learning_rate": 1.4923141442566732e-05, + "loss": 0.4985, + "step": 4256 + }, + { + "epoch": 0.36, + "learning_rate": 1.4920782513005003e-05, + "loss": 0.5076, + "step": 4257 + }, + { + "epoch": 0.36, + "learning_rate": 1.4918423222081473e-05, + "loss": 0.5075, + "step": 4258 + }, + { + "epoch": 0.36, + "learning_rate": 1.4916063569969398e-05, + "loss": 0.5165, + "step": 4259 + }, + { + "epoch": 0.36, + "learning_rate": 1.4913703556842066e-05, + "loss": 0.4758, + "step": 4260 + }, + { + "epoch": 0.36, + "learning_rate": 1.491134318287278e-05, + "loss": 0.4828, + "step": 4261 + }, + { + "epoch": 0.36, + "learning_rate": 1.4908982448234875e-05, + "loss": 0.4891, + "step": 4262 + }, + { + "epoch": 0.36, + "learning_rate": 1.490662135310172e-05, + "loss": 0.4657, + "step": 4263 + }, + { + "epoch": 0.36, + "learning_rate": 1.49042598976467e-05, + "loss": 0.5058, + "step": 4264 + }, + { + "epoch": 0.36, + "learning_rate": 1.4901898082043232e-05, + "loss": 0.4888, + "step": 4265 + }, + { + "epoch": 0.36, + "learning_rate": 1.4899535906464757e-05, + "loss": 0.4943, + "step": 4266 + }, + { + "epoch": 0.36, + "learning_rate": 1.4897173371084743e-05, + "loss": 0.4916, + "step": 4267 + }, + { + "epoch": 0.36, + "learning_rate": 1.4894810476076688e-05, + "loss": 0.4967, + "step": 4268 + }, + { + "epoch": 0.36, + "learning_rate": 1.489244722161411e-05, + "loss": 0.5103, + "step": 4269 + }, + { + "epoch": 0.36, + "learning_rate": 1.4890083607870559e-05, + "loss": 0.4885, + "step": 4270 + }, + { + "epoch": 0.36, + "learning_rate": 1.4887719635019605e-05, + "loss": 0.5045, + "step": 4271 + }, + { + "epoch": 0.36, + "learning_rate": 1.488535530323485e-05, + "loss": 0.4692, + "step": 4272 + }, + { + "epoch": 0.36, + "learning_rate": 1.4882990612689918e-05, + "loss": 0.5159, + "step": 4273 + }, + { + "epoch": 0.36, + "learning_rate": 1.488062556355847e-05, + "loss": 0.4899, + "step": 4274 + }, + { + "epoch": 0.36, + "learning_rate": 1.4878260156014182e-05, + "loss": 0.4831, + "step": 4275 + }, + { + "epoch": 0.36, + "learning_rate": 1.4875894390230757e-05, + "loss": 0.4664, + "step": 4276 + }, + { + "epoch": 0.36, + "learning_rate": 1.4873528266381927e-05, + "loss": 0.4861, + "step": 4277 + }, + { + "epoch": 0.36, + "learning_rate": 1.487116178464145e-05, + "loss": 0.4937, + "step": 4278 + }, + { + "epoch": 0.36, + "learning_rate": 1.4868794945183113e-05, + "loss": 0.4788, + "step": 4279 + }, + { + "epoch": 0.36, + "learning_rate": 1.4866427748180729e-05, + "loss": 0.4746, + "step": 4280 + }, + { + "epoch": 0.36, + "learning_rate": 1.4864060193808133e-05, + "loss": 0.5078, + "step": 4281 + }, + { + "epoch": 0.36, + "learning_rate": 1.4861692282239181e-05, + "loss": 0.4726, + "step": 4282 + }, + { + "epoch": 0.36, + "learning_rate": 1.4859324013647773e-05, + "loss": 0.4855, + "step": 4283 + }, + { + "epoch": 0.36, + "learning_rate": 1.4856955388207821e-05, + "loss": 0.4965, + "step": 4284 + }, + { + "epoch": 0.36, + "learning_rate": 1.485458640609327e-05, + "loss": 0.4585, + "step": 4285 + }, + { + "epoch": 0.36, + "learning_rate": 1.4852217067478082e-05, + "loss": 0.4939, + "step": 4286 + }, + { + "epoch": 0.36, + "learning_rate": 1.4849847372536252e-05, + "loss": 0.4907, + "step": 4287 + }, + { + "epoch": 0.36, + "learning_rate": 1.4847477321441806e-05, + "loss": 0.4992, + "step": 4288 + }, + { + "epoch": 0.36, + "learning_rate": 1.4845106914368786e-05, + "loss": 0.4741, + "step": 4289 + }, + { + "epoch": 0.36, + "learning_rate": 1.4842736151491268e-05, + "loss": 0.5102, + "step": 4290 + }, + { + "epoch": 0.36, + "learning_rate": 1.484036503298335e-05, + "loss": 0.4947, + "step": 4291 + }, + { + "epoch": 0.36, + "learning_rate": 1.4837993559019157e-05, + "loss": 0.5033, + "step": 4292 + }, + { + "epoch": 0.36, + "learning_rate": 1.4835621729772838e-05, + "loss": 0.4976, + "step": 4293 + }, + { + "epoch": 0.36, + "learning_rate": 1.4833249545418572e-05, + "loss": 0.4881, + "step": 4294 + }, + { + "epoch": 0.36, + "learning_rate": 1.4830877006130561e-05, + "loss": 0.4842, + "step": 4295 + }, + { + "epoch": 0.36, + "learning_rate": 1.4828504112083038e-05, + "loss": 0.5006, + "step": 4296 + }, + { + "epoch": 0.36, + "learning_rate": 1.4826130863450257e-05, + "loss": 0.4883, + "step": 4297 + }, + { + "epoch": 0.36, + "learning_rate": 1.4823757260406498e-05, + "loss": 0.4763, + "step": 4298 + }, + { + "epoch": 0.36, + "learning_rate": 1.4821383303126067e-05, + "loss": 0.4734, + "step": 4299 + }, + { + "epoch": 0.36, + "learning_rate": 1.48190089917833e-05, + "loss": 0.5042, + "step": 4300 + }, + { + "epoch": 0.36, + "learning_rate": 1.4816634326552561e-05, + "loss": 0.4874, + "step": 4301 + }, + { + "epoch": 0.36, + "learning_rate": 1.481425930760823e-05, + "loss": 0.4944, + "step": 4302 + }, + { + "epoch": 0.36, + "learning_rate": 1.4811883935124716e-05, + "loss": 0.512, + "step": 4303 + }, + { + "epoch": 0.36, + "learning_rate": 1.480950820927646e-05, + "loss": 0.5002, + "step": 4304 + }, + { + "epoch": 0.36, + "learning_rate": 1.480713213023793e-05, + "loss": 0.4948, + "step": 4305 + }, + { + "epoch": 0.36, + "learning_rate": 1.4804755698183606e-05, + "loss": 0.4853, + "step": 4306 + }, + { + "epoch": 0.36, + "learning_rate": 1.4802378913288009e-05, + "loss": 0.4656, + "step": 4307 + }, + { + "epoch": 0.36, + "learning_rate": 1.4800001775725684e-05, + "loss": 0.4808, + "step": 4308 + }, + { + "epoch": 0.36, + "learning_rate": 1.4797624285671187e-05, + "loss": 0.4804, + "step": 4309 + }, + { + "epoch": 0.36, + "learning_rate": 1.4795246443299119e-05, + "loss": 0.4866, + "step": 4310 + }, + { + "epoch": 0.36, + "learning_rate": 1.4792868248784098e-05, + "loss": 0.5026, + "step": 4311 + }, + { + "epoch": 0.36, + "learning_rate": 1.4790489702300768e-05, + "loss": 0.4892, + "step": 4312 + }, + { + "epoch": 0.36, + "learning_rate": 1.4788110804023798e-05, + "loss": 0.4854, + "step": 4313 + }, + { + "epoch": 0.36, + "learning_rate": 1.4785731554127885e-05, + "loss": 0.4904, + "step": 4314 + }, + { + "epoch": 0.36, + "learning_rate": 1.4783351952787754e-05, + "loss": 0.4885, + "step": 4315 + }, + { + "epoch": 0.36, + "learning_rate": 1.4780972000178151e-05, + "loss": 0.4908, + "step": 4316 + }, + { + "epoch": 0.36, + "learning_rate": 1.477859169647385e-05, + "loss": 0.4939, + "step": 4317 + }, + { + "epoch": 0.36, + "learning_rate": 1.4776211041849651e-05, + "loss": 0.4988, + "step": 4318 + }, + { + "epoch": 0.36, + "learning_rate": 1.4773830036480377e-05, + "loss": 0.4819, + "step": 4319 + }, + { + "epoch": 0.36, + "learning_rate": 1.4771448680540881e-05, + "loss": 0.4991, + "step": 4320 + }, + { + "epoch": 0.36, + "learning_rate": 1.4769066974206041e-05, + "loss": 0.4881, + "step": 4321 + }, + { + "epoch": 0.36, + "learning_rate": 1.476668491765076e-05, + "loss": 0.511, + "step": 4322 + }, + { + "epoch": 0.36, + "learning_rate": 1.4764302511049962e-05, + "loss": 0.4744, + "step": 4323 + }, + { + "epoch": 0.36, + "learning_rate": 1.4761919754578603e-05, + "loss": 0.4949, + "step": 4324 + }, + { + "epoch": 0.36, + "learning_rate": 1.4759536648411668e-05, + "loss": 0.4802, + "step": 4325 + }, + { + "epoch": 0.36, + "learning_rate": 1.4757153192724154e-05, + "loss": 0.4845, + "step": 4326 + }, + { + "epoch": 0.36, + "learning_rate": 1.4754769387691096e-05, + "loss": 0.4661, + "step": 4327 + }, + { + "epoch": 0.36, + "learning_rate": 1.4752385233487554e-05, + "loss": 0.4855, + "step": 4328 + }, + { + "epoch": 0.36, + "learning_rate": 1.4750000730288605e-05, + "loss": 0.465, + "step": 4329 + }, + { + "epoch": 0.36, + "learning_rate": 1.4747615878269358e-05, + "loss": 0.4894, + "step": 4330 + }, + { + "epoch": 0.36, + "learning_rate": 1.474523067760495e-05, + "loss": 0.5, + "step": 4331 + }, + { + "epoch": 0.36, + "learning_rate": 1.4742845128470538e-05, + "loss": 0.5042, + "step": 4332 + }, + { + "epoch": 0.36, + "learning_rate": 1.4740459231041306e-05, + "loss": 0.4949, + "step": 4333 + }, + { + "epoch": 0.36, + "learning_rate": 1.4738072985492462e-05, + "loss": 0.505, + "step": 4334 + }, + { + "epoch": 0.36, + "learning_rate": 1.4735686391999249e-05, + "loss": 0.4786, + "step": 4335 + }, + { + "epoch": 0.36, + "learning_rate": 1.4733299450736925e-05, + "loss": 0.482, + "step": 4336 + }, + { + "epoch": 0.36, + "learning_rate": 1.4730912161880772e-05, + "loss": 0.4861, + "step": 4337 + }, + { + "epoch": 0.36, + "learning_rate": 1.4728524525606111e-05, + "loss": 0.4779, + "step": 4338 + }, + { + "epoch": 0.36, + "learning_rate": 1.4726136542088277e-05, + "loss": 0.4865, + "step": 4339 + }, + { + "epoch": 0.36, + "learning_rate": 1.4723748211502628e-05, + "loss": 0.4938, + "step": 4340 + }, + { + "epoch": 0.36, + "learning_rate": 1.4721359534024562e-05, + "loss": 0.4721, + "step": 4341 + }, + { + "epoch": 0.36, + "learning_rate": 1.4718970509829489e-05, + "loss": 0.4929, + "step": 4342 + }, + { + "epoch": 0.36, + "learning_rate": 1.4716581139092851e-05, + "loss": 0.5027, + "step": 4343 + }, + { + "epoch": 0.36, + "learning_rate": 1.471419142199011e-05, + "loss": 0.4993, + "step": 4344 + }, + { + "epoch": 0.36, + "learning_rate": 1.4711801358696755e-05, + "loss": 0.4877, + "step": 4345 + }, + { + "epoch": 0.36, + "learning_rate": 1.4709410949388311e-05, + "loss": 0.491, + "step": 4346 + }, + { + "epoch": 0.36, + "learning_rate": 1.4707020194240313e-05, + "loss": 0.5074, + "step": 4347 + }, + { + "epoch": 0.36, + "learning_rate": 1.4704629093428331e-05, + "loss": 0.5038, + "step": 4348 + }, + { + "epoch": 0.36, + "learning_rate": 1.4702237647127957e-05, + "loss": 0.4815, + "step": 4349 + }, + { + "epoch": 0.36, + "learning_rate": 1.4699845855514807e-05, + "loss": 0.5135, + "step": 4350 + }, + { + "epoch": 0.36, + "learning_rate": 1.4697453718764525e-05, + "loss": 0.4867, + "step": 4351 + }, + { + "epoch": 0.36, + "learning_rate": 1.4695061237052781e-05, + "loss": 0.5028, + "step": 4352 + }, + { + "epoch": 0.36, + "learning_rate": 1.4692668410555269e-05, + "loss": 0.5103, + "step": 4353 + }, + { + "epoch": 0.36, + "learning_rate": 1.4690275239447704e-05, + "loss": 0.486, + "step": 4354 + }, + { + "epoch": 0.36, + "learning_rate": 1.4687881723905834e-05, + "loss": 0.4773, + "step": 4355 + }, + { + "epoch": 0.36, + "learning_rate": 1.4685487864105431e-05, + "loss": 0.486, + "step": 4356 + }, + { + "epoch": 0.36, + "learning_rate": 1.4683093660222288e-05, + "loss": 0.502, + "step": 4357 + }, + { + "epoch": 0.36, + "learning_rate": 1.4680699112432223e-05, + "loss": 0.5118, + "step": 4358 + }, + { + "epoch": 0.36, + "learning_rate": 1.4678304220911086e-05, + "loss": 0.475, + "step": 4359 + }, + { + "epoch": 0.36, + "learning_rate": 1.4675908985834744e-05, + "loss": 0.4904, + "step": 4360 + }, + { + "epoch": 0.36, + "learning_rate": 1.4673513407379095e-05, + "loss": 0.494, + "step": 4361 + }, + { + "epoch": 0.36, + "learning_rate": 1.4671117485720058e-05, + "loss": 0.4699, + "step": 4362 + }, + { + "epoch": 0.37, + "learning_rate": 1.4668721221033586e-05, + "loss": 0.4813, + "step": 4363 + }, + { + "epoch": 0.37, + "learning_rate": 1.4666324613495641e-05, + "loss": 0.5052, + "step": 4364 + }, + { + "epoch": 0.37, + "learning_rate": 1.4663927663282228e-05, + "loss": 0.5067, + "step": 4365 + }, + { + "epoch": 0.37, + "learning_rate": 1.4661530370569366e-05, + "loss": 0.4903, + "step": 4366 + }, + { + "epoch": 0.37, + "learning_rate": 1.4659132735533104e-05, + "loss": 0.4757, + "step": 4367 + }, + { + "epoch": 0.37, + "learning_rate": 1.4656734758349509e-05, + "loss": 0.4849, + "step": 4368 + }, + { + "epoch": 0.37, + "learning_rate": 1.4654336439194686e-05, + "loss": 0.5033, + "step": 4369 + }, + { + "epoch": 0.37, + "learning_rate": 1.4651937778244748e-05, + "loss": 0.4794, + "step": 4370 + }, + { + "epoch": 0.37, + "learning_rate": 1.464953877567585e-05, + "loss": 0.4982, + "step": 4371 + }, + { + "epoch": 0.37, + "learning_rate": 1.4647139431664167e-05, + "loss": 0.4785, + "step": 4372 + }, + { + "epoch": 0.37, + "learning_rate": 1.4644739746385894e-05, + "loss": 0.4746, + "step": 4373 + }, + { + "epoch": 0.37, + "learning_rate": 1.4642339720017249e-05, + "loss": 0.4791, + "step": 4374 + }, + { + "epoch": 0.37, + "learning_rate": 1.4639939352734484e-05, + "loss": 0.482, + "step": 4375 + }, + { + "epoch": 0.37, + "learning_rate": 1.4637538644713873e-05, + "loss": 0.4858, + "step": 4376 + }, + { + "epoch": 0.37, + "learning_rate": 1.4635137596131715e-05, + "loss": 0.4855, + "step": 4377 + }, + { + "epoch": 0.37, + "learning_rate": 1.4632736207164326e-05, + "loss": 0.4978, + "step": 4378 + }, + { + "epoch": 0.37, + "learning_rate": 1.4630334477988064e-05, + "loss": 0.4673, + "step": 4379 + }, + { + "epoch": 0.37, + "learning_rate": 1.4627932408779295e-05, + "loss": 0.4958, + "step": 4380 + }, + { + "epoch": 0.37, + "learning_rate": 1.4625529999714416e-05, + "loss": 0.5042, + "step": 4381 + }, + { + "epoch": 0.37, + "learning_rate": 1.4623127250969858e-05, + "loss": 0.4891, + "step": 4382 + }, + { + "epoch": 0.37, + "learning_rate": 1.4620724162722062e-05, + "loss": 0.5032, + "step": 4383 + }, + { + "epoch": 0.37, + "learning_rate": 1.4618320735147501e-05, + "loss": 0.4884, + "step": 4384 + }, + { + "epoch": 0.37, + "learning_rate": 1.4615916968422674e-05, + "loss": 0.4967, + "step": 4385 + }, + { + "epoch": 0.37, + "learning_rate": 1.4613512862724103e-05, + "loss": 0.4824, + "step": 4386 + }, + { + "epoch": 0.37, + "learning_rate": 1.4611108418228342e-05, + "loss": 0.4766, + "step": 4387 + }, + { + "epoch": 0.37, + "learning_rate": 1.460870363511195e-05, + "loss": 0.4905, + "step": 4388 + }, + { + "epoch": 0.37, + "learning_rate": 1.460629851355154e-05, + "loss": 0.4821, + "step": 4389 + }, + { + "epoch": 0.37, + "learning_rate": 1.460389305372372e-05, + "loss": 0.4958, + "step": 4390 + }, + { + "epoch": 0.37, + "learning_rate": 1.4601487255805146e-05, + "loss": 0.4676, + "step": 4391 + }, + { + "epoch": 0.37, + "learning_rate": 1.4599081119972486e-05, + "loss": 0.501, + "step": 4392 + }, + { + "epoch": 0.37, + "learning_rate": 1.459667464640244e-05, + "loss": 0.4787, + "step": 4393 + }, + { + "epoch": 0.37, + "learning_rate": 1.4594267835271725e-05, + "loss": 0.5029, + "step": 4394 + }, + { + "epoch": 0.37, + "learning_rate": 1.4591860686757089e-05, + "loss": 0.5047, + "step": 4395 + }, + { + "epoch": 0.37, + "learning_rate": 1.4589453201035302e-05, + "loss": 0.5009, + "step": 4396 + }, + { + "epoch": 0.37, + "learning_rate": 1.4587045378283162e-05, + "loss": 0.4818, + "step": 4397 + }, + { + "epoch": 0.37, + "learning_rate": 1.4584637218677488e-05, + "loss": 0.4601, + "step": 4398 + }, + { + "epoch": 0.37, + "learning_rate": 1.4582228722395128e-05, + "loss": 0.504, + "step": 4399 + }, + { + "epoch": 0.37, + "learning_rate": 1.4579819889612949e-05, + "loss": 0.4719, + "step": 4400 + }, + { + "epoch": 0.37, + "learning_rate": 1.4577410720507842e-05, + "loss": 0.5031, + "step": 4401 + }, + { + "epoch": 0.37, + "learning_rate": 1.4575001215256735e-05, + "loss": 0.4812, + "step": 4402 + }, + { + "epoch": 0.37, + "learning_rate": 1.4572591374036567e-05, + "loss": 0.4906, + "step": 4403 + }, + { + "epoch": 0.37, + "learning_rate": 1.4570181197024307e-05, + "loss": 0.4945, + "step": 4404 + }, + { + "epoch": 0.37, + "learning_rate": 1.4567770684396947e-05, + "loss": 0.4849, + "step": 4405 + }, + { + "epoch": 0.37, + "learning_rate": 1.456535983633151e-05, + "loss": 0.4788, + "step": 4406 + }, + { + "epoch": 0.37, + "learning_rate": 1.4562948653005032e-05, + "loss": 0.4917, + "step": 4407 + }, + { + "epoch": 0.37, + "learning_rate": 1.4560537134594586e-05, + "loss": 0.4728, + "step": 4408 + }, + { + "epoch": 0.37, + "learning_rate": 1.455812528127726e-05, + "loss": 0.4997, + "step": 4409 + }, + { + "epoch": 0.37, + "learning_rate": 1.4555713093230173e-05, + "loss": 0.493, + "step": 4410 + }, + { + "epoch": 0.37, + "learning_rate": 1.4553300570630464e-05, + "loss": 0.4758, + "step": 4411 + }, + { + "epoch": 0.37, + "learning_rate": 1.4550887713655297e-05, + "loss": 0.4887, + "step": 4412 + }, + { + "epoch": 0.37, + "learning_rate": 1.454847452248187e-05, + "loss": 0.4892, + "step": 4413 + }, + { + "epoch": 0.37, + "learning_rate": 1.4546060997287392e-05, + "loss": 0.4678, + "step": 4414 + }, + { + "epoch": 0.37, + "learning_rate": 1.45436471382491e-05, + "loss": 0.5012, + "step": 4415 + }, + { + "epoch": 0.37, + "learning_rate": 1.4541232945544263e-05, + "loss": 0.5001, + "step": 4416 + }, + { + "epoch": 0.37, + "learning_rate": 1.4538818419350164e-05, + "loss": 0.4674, + "step": 4417 + }, + { + "epoch": 0.37, + "learning_rate": 1.4536403559844123e-05, + "loss": 0.5016, + "step": 4418 + }, + { + "epoch": 0.37, + "learning_rate": 1.453398836720347e-05, + "loss": 0.4768, + "step": 4419 + }, + { + "epoch": 0.37, + "learning_rate": 1.453157284160557e-05, + "loss": 0.4941, + "step": 4420 + }, + { + "epoch": 0.37, + "learning_rate": 1.452915698322781e-05, + "loss": 0.4916, + "step": 4421 + }, + { + "epoch": 0.37, + "learning_rate": 1.4526740792247597e-05, + "loss": 0.4901, + "step": 4422 + }, + { + "epoch": 0.37, + "learning_rate": 1.4524324268842369e-05, + "loss": 0.4863, + "step": 4423 + }, + { + "epoch": 0.37, + "learning_rate": 1.4521907413189587e-05, + "loss": 0.4917, + "step": 4424 + }, + { + "epoch": 0.37, + "learning_rate": 1.4519490225466733e-05, + "loss": 0.4962, + "step": 4425 + }, + { + "epoch": 0.37, + "learning_rate": 1.4517072705851312e-05, + "loss": 0.485, + "step": 4426 + }, + { + "epoch": 0.37, + "learning_rate": 1.451465485452086e-05, + "loss": 0.4956, + "step": 4427 + }, + { + "epoch": 0.37, + "learning_rate": 1.4512236671652932e-05, + "loss": 0.4826, + "step": 4428 + }, + { + "epoch": 0.37, + "learning_rate": 1.4509818157425112e-05, + "loss": 0.4832, + "step": 4429 + }, + { + "epoch": 0.37, + "learning_rate": 1.4507399312015005e-05, + "loss": 0.4936, + "step": 4430 + }, + { + "epoch": 0.37, + "learning_rate": 1.4504980135600242e-05, + "loss": 0.4902, + "step": 4431 + }, + { + "epoch": 0.37, + "learning_rate": 1.4502560628358473e-05, + "loss": 0.4943, + "step": 4432 + }, + { + "epoch": 0.37, + "learning_rate": 1.4500140790467377e-05, + "loss": 0.4822, + "step": 4433 + }, + { + "epoch": 0.37, + "learning_rate": 1.449772062210466e-05, + "loss": 0.4996, + "step": 4434 + }, + { + "epoch": 0.37, + "learning_rate": 1.449530012344805e-05, + "loss": 0.5047, + "step": 4435 + }, + { + "epoch": 0.37, + "learning_rate": 1.4492879294675297e-05, + "loss": 0.4677, + "step": 4436 + }, + { + "epoch": 0.37, + "learning_rate": 1.4490458135964173e-05, + "loss": 0.4872, + "step": 4437 + }, + { + "epoch": 0.37, + "learning_rate": 1.4488036647492482e-05, + "loss": 0.4731, + "step": 4438 + }, + { + "epoch": 0.37, + "learning_rate": 1.4485614829438046e-05, + "loss": 0.4759, + "step": 4439 + }, + { + "epoch": 0.37, + "learning_rate": 1.4483192681978715e-05, + "loss": 0.4946, + "step": 4440 + }, + { + "epoch": 0.37, + "learning_rate": 1.4480770205292363e-05, + "loss": 0.4783, + "step": 4441 + }, + { + "epoch": 0.37, + "learning_rate": 1.4478347399556878e-05, + "loss": 0.4796, + "step": 4442 + }, + { + "epoch": 0.37, + "learning_rate": 1.447592426495019e-05, + "loss": 0.495, + "step": 4443 + }, + { + "epoch": 0.37, + "learning_rate": 1.4473500801650243e-05, + "loss": 0.4885, + "step": 4444 + }, + { + "epoch": 0.37, + "learning_rate": 1.4471077009835001e-05, + "loss": 0.4771, + "step": 4445 + }, + { + "epoch": 0.37, + "learning_rate": 1.446865288968246e-05, + "loss": 0.4934, + "step": 4446 + }, + { + "epoch": 0.37, + "learning_rate": 1.4466228441370638e-05, + "loss": 0.5003, + "step": 4447 + }, + { + "epoch": 0.37, + "learning_rate": 1.4463803665077573e-05, + "loss": 0.4921, + "step": 4448 + }, + { + "epoch": 0.37, + "learning_rate": 1.4461378560981335e-05, + "loss": 0.4844, + "step": 4449 + }, + { + "epoch": 0.37, + "learning_rate": 1.4458953129260014e-05, + "loss": 0.484, + "step": 4450 + }, + { + "epoch": 0.37, + "learning_rate": 1.4456527370091722e-05, + "loss": 0.477, + "step": 4451 + }, + { + "epoch": 0.37, + "learning_rate": 1.4454101283654594e-05, + "loss": 0.4759, + "step": 4452 + }, + { + "epoch": 0.37, + "learning_rate": 1.445167487012679e-05, + "loss": 0.4673, + "step": 4453 + }, + { + "epoch": 0.37, + "learning_rate": 1.4449248129686504e-05, + "loss": 0.4975, + "step": 4454 + }, + { + "epoch": 0.37, + "learning_rate": 1.4446821062511942e-05, + "loss": 0.5007, + "step": 4455 + }, + { + "epoch": 0.37, + "learning_rate": 1.4444393668781334e-05, + "loss": 0.5061, + "step": 4456 + }, + { + "epoch": 0.37, + "learning_rate": 1.4441965948672943e-05, + "loss": 0.4783, + "step": 4457 + }, + { + "epoch": 0.37, + "learning_rate": 1.4439537902365047e-05, + "loss": 0.5025, + "step": 4458 + }, + { + "epoch": 0.37, + "learning_rate": 1.4437109530035951e-05, + "loss": 0.4762, + "step": 4459 + }, + { + "epoch": 0.37, + "learning_rate": 1.443468083186399e-05, + "loss": 0.503, + "step": 4460 + }, + { + "epoch": 0.37, + "learning_rate": 1.443225180802751e-05, + "loss": 0.4933, + "step": 4461 + }, + { + "epoch": 0.37, + "learning_rate": 1.4429822458704896e-05, + "loss": 0.4887, + "step": 4462 + }, + { + "epoch": 0.37, + "learning_rate": 1.4427392784074545e-05, + "loss": 0.4973, + "step": 4463 + }, + { + "epoch": 0.37, + "learning_rate": 1.442496278431488e-05, + "loss": 0.5274, + "step": 4464 + }, + { + "epoch": 0.37, + "learning_rate": 1.4422532459604357e-05, + "loss": 0.4956, + "step": 4465 + }, + { + "epoch": 0.37, + "learning_rate": 1.442010181012144e-05, + "loss": 0.4856, + "step": 4466 + }, + { + "epoch": 0.37, + "learning_rate": 1.4417670836044635e-05, + "loss": 0.5036, + "step": 4467 + }, + { + "epoch": 0.37, + "learning_rate": 1.4415239537552457e-05, + "loss": 0.5218, + "step": 4468 + }, + { + "epoch": 0.37, + "learning_rate": 1.4412807914823452e-05, + "loss": 0.4733, + "step": 4469 + }, + { + "epoch": 0.37, + "learning_rate": 1.4410375968036185e-05, + "loss": 0.4742, + "step": 4470 + }, + { + "epoch": 0.37, + "learning_rate": 1.4407943697369255e-05, + "loss": 0.4971, + "step": 4471 + }, + { + "epoch": 0.37, + "learning_rate": 1.4405511103001274e-05, + "loss": 0.4941, + "step": 4472 + }, + { + "epoch": 0.37, + "learning_rate": 1.440307818511088e-05, + "loss": 0.4734, + "step": 4473 + }, + { + "epoch": 0.37, + "learning_rate": 1.4400644943876736e-05, + "loss": 0.494, + "step": 4474 + }, + { + "epoch": 0.37, + "learning_rate": 1.4398211379477534e-05, + "loss": 0.5102, + "step": 4475 + }, + { + "epoch": 0.37, + "learning_rate": 1.439577749209198e-05, + "loss": 0.4926, + "step": 4476 + }, + { + "epoch": 0.37, + "learning_rate": 1.439334328189881e-05, + "loss": 0.4995, + "step": 4477 + }, + { + "epoch": 0.37, + "learning_rate": 1.4390908749076787e-05, + "loss": 0.5003, + "step": 4478 + }, + { + "epoch": 0.37, + "learning_rate": 1.4388473893804683e-05, + "loss": 0.5023, + "step": 4479 + }, + { + "epoch": 0.37, + "learning_rate": 1.438603871626131e-05, + "loss": 0.4786, + "step": 4480 + }, + { + "epoch": 0.37, + "learning_rate": 1.4383603216625499e-05, + "loss": 0.4957, + "step": 4481 + }, + { + "epoch": 0.37, + "learning_rate": 1.4381167395076101e-05, + "loss": 0.5121, + "step": 4482 + }, + { + "epoch": 0.38, + "learning_rate": 1.4378731251791989e-05, + "loss": 0.4638, + "step": 4483 + }, + { + "epoch": 0.38, + "learning_rate": 1.4376294786952067e-05, + "loss": 0.4954, + "step": 4484 + }, + { + "epoch": 0.38, + "learning_rate": 1.4373858000735262e-05, + "loss": 0.4954, + "step": 4485 + }, + { + "epoch": 0.38, + "learning_rate": 1.4371420893320515e-05, + "loss": 0.4881, + "step": 4486 + }, + { + "epoch": 0.38, + "learning_rate": 1.4368983464886799e-05, + "loss": 0.5036, + "step": 4487 + }, + { + "epoch": 0.38, + "learning_rate": 1.4366545715613112e-05, + "loss": 0.4723, + "step": 4488 + }, + { + "epoch": 0.38, + "learning_rate": 1.4364107645678465e-05, + "loss": 0.4846, + "step": 4489 + }, + { + "epoch": 0.38, + "learning_rate": 1.4361669255261905e-05, + "loss": 0.4819, + "step": 4490 + }, + { + "epoch": 0.38, + "learning_rate": 1.43592305445425e-05, + "loss": 0.4875, + "step": 4491 + }, + { + "epoch": 0.38, + "learning_rate": 1.4356791513699334e-05, + "loss": 0.4895, + "step": 4492 + }, + { + "epoch": 0.38, + "learning_rate": 1.4354352162911522e-05, + "loss": 0.4762, + "step": 4493 + }, + { + "epoch": 0.38, + "learning_rate": 1.4351912492358196e-05, + "loss": 0.4905, + "step": 4494 + }, + { + "epoch": 0.38, + "learning_rate": 1.4349472502218515e-05, + "loss": 0.4592, + "step": 4495 + }, + { + "epoch": 0.38, + "learning_rate": 1.4347032192671668e-05, + "loss": 0.4966, + "step": 4496 + }, + { + "epoch": 0.38, + "learning_rate": 1.4344591563896857e-05, + "loss": 0.4847, + "step": 4497 + }, + { + "epoch": 0.38, + "learning_rate": 1.4342150616073312e-05, + "loss": 0.4795, + "step": 4498 + }, + { + "epoch": 0.38, + "learning_rate": 1.4339709349380285e-05, + "loss": 0.5128, + "step": 4499 + }, + { + "epoch": 0.38, + "learning_rate": 1.4337267763997054e-05, + "loss": 0.4757, + "step": 4500 + }, + { + "epoch": 0.38, + "learning_rate": 1.4334825860102917e-05, + "loss": 0.4912, + "step": 4501 + }, + { + "epoch": 0.38, + "learning_rate": 1.4332383637877203e-05, + "loss": 0.4773, + "step": 4502 + }, + { + "epoch": 0.38, + "learning_rate": 1.432994109749925e-05, + "loss": 0.4955, + "step": 4503 + }, + { + "epoch": 0.38, + "learning_rate": 1.4327498239148434e-05, + "loss": 0.4786, + "step": 4504 + }, + { + "epoch": 0.38, + "learning_rate": 1.4325055063004145e-05, + "loss": 0.4953, + "step": 4505 + }, + { + "epoch": 0.38, + "learning_rate": 1.4322611569245806e-05, + "loss": 0.4892, + "step": 4506 + }, + { + "epoch": 0.38, + "learning_rate": 1.4320167758052848e-05, + "loss": 0.4917, + "step": 4507 + }, + { + "epoch": 0.38, + "learning_rate": 1.4317723629604743e-05, + "loss": 0.4832, + "step": 4508 + }, + { + "epoch": 0.38, + "learning_rate": 1.431527918408097e-05, + "loss": 0.4878, + "step": 4509 + }, + { + "epoch": 0.38, + "learning_rate": 1.4312834421661044e-05, + "loss": 0.4948, + "step": 4510 + }, + { + "epoch": 0.38, + "learning_rate": 1.4310389342524494e-05, + "loss": 0.4869, + "step": 4511 + }, + { + "epoch": 0.38, + "learning_rate": 1.4307943946850883e-05, + "loss": 0.491, + "step": 4512 + }, + { + "epoch": 0.38, + "learning_rate": 1.4305498234819783e-05, + "loss": 0.4886, + "step": 4513 + }, + { + "epoch": 0.38, + "learning_rate": 1.4303052206610801e-05, + "loss": 0.4815, + "step": 4514 + }, + { + "epoch": 0.38, + "learning_rate": 1.4300605862403563e-05, + "loss": 0.4738, + "step": 4515 + }, + { + "epoch": 0.38, + "learning_rate": 1.4298159202377719e-05, + "loss": 0.5164, + "step": 4516 + }, + { + "epoch": 0.38, + "learning_rate": 1.4295712226712941e-05, + "loss": 0.4937, + "step": 4517 + }, + { + "epoch": 0.38, + "learning_rate": 1.4293264935588921e-05, + "loss": 0.4743, + "step": 4518 + }, + { + "epoch": 0.38, + "learning_rate": 1.4290817329185388e-05, + "loss": 0.4843, + "step": 4519 + }, + { + "epoch": 0.38, + "learning_rate": 1.428836940768207e-05, + "loss": 0.4989, + "step": 4520 + }, + { + "epoch": 0.38, + "learning_rate": 1.4285921171258741e-05, + "loss": 0.4858, + "step": 4521 + }, + { + "epoch": 0.38, + "learning_rate": 1.4283472620095192e-05, + "loss": 0.477, + "step": 4522 + }, + { + "epoch": 0.38, + "learning_rate": 1.4281023754371226e-05, + "loss": 0.4741, + "step": 4523 + }, + { + "epoch": 0.38, + "learning_rate": 1.4278574574266681e-05, + "loss": 0.4952, + "step": 4524 + }, + { + "epoch": 0.38, + "learning_rate": 1.4276125079961417e-05, + "loss": 0.4953, + "step": 4525 + }, + { + "epoch": 0.38, + "learning_rate": 1.4273675271635313e-05, + "loss": 0.5021, + "step": 4526 + }, + { + "epoch": 0.38, + "learning_rate": 1.4271225149468272e-05, + "loss": 0.4825, + "step": 4527 + }, + { + "epoch": 0.38, + "learning_rate": 1.426877471364022e-05, + "loss": 0.4693, + "step": 4528 + }, + { + "epoch": 0.38, + "learning_rate": 1.4266323964331112e-05, + "loss": 0.4788, + "step": 4529 + }, + { + "epoch": 0.38, + "learning_rate": 1.4263872901720914e-05, + "loss": 0.469, + "step": 4530 + }, + { + "epoch": 0.38, + "learning_rate": 1.4261421525989625e-05, + "loss": 0.4949, + "step": 4531 + }, + { + "epoch": 0.38, + "learning_rate": 1.4258969837317265e-05, + "loss": 0.4905, + "step": 4532 + }, + { + "epoch": 0.38, + "learning_rate": 1.4256517835883874e-05, + "loss": 0.488, + "step": 4533 + }, + { + "epoch": 0.38, + "learning_rate": 1.4254065521869519e-05, + "loss": 0.5049, + "step": 4534 + }, + { + "epoch": 0.38, + "learning_rate": 1.4251612895454282e-05, + "loss": 0.5057, + "step": 4535 + }, + { + "epoch": 0.38, + "learning_rate": 1.4249159956818279e-05, + "loss": 0.4912, + "step": 4536 + }, + { + "epoch": 0.38, + "learning_rate": 1.4246706706141646e-05, + "loss": 0.5032, + "step": 4537 + }, + { + "epoch": 0.38, + "learning_rate": 1.4244253143604531e-05, + "loss": 0.4765, + "step": 4538 + }, + { + "epoch": 0.38, + "learning_rate": 1.4241799269387122e-05, + "loss": 0.4854, + "step": 4539 + }, + { + "epoch": 0.38, + "learning_rate": 1.4239345083669615e-05, + "loss": 0.4815, + "step": 4540 + }, + { + "epoch": 0.38, + "learning_rate": 1.423689058663224e-05, + "loss": 0.5124, + "step": 4541 + }, + { + "epoch": 0.38, + "learning_rate": 1.4234435778455242e-05, + "loss": 0.4851, + "step": 4542 + }, + { + "epoch": 0.38, + "learning_rate": 1.4231980659318891e-05, + "loss": 0.5049, + "step": 4543 + }, + { + "epoch": 0.38, + "learning_rate": 1.4229525229403486e-05, + "loss": 0.4756, + "step": 4544 + }, + { + "epoch": 0.38, + "learning_rate": 1.4227069488889338e-05, + "loss": 0.4865, + "step": 4545 + }, + { + "epoch": 0.38, + "learning_rate": 1.422461343795679e-05, + "loss": 0.4887, + "step": 4546 + }, + { + "epoch": 0.38, + "learning_rate": 1.4222157076786201e-05, + "loss": 0.4804, + "step": 4547 + }, + { + "epoch": 0.38, + "learning_rate": 1.4219700405557958e-05, + "loss": 0.4999, + "step": 4548 + }, + { + "epoch": 0.38, + "learning_rate": 1.4217243424452466e-05, + "loss": 0.4974, + "step": 4549 + }, + { + "epoch": 0.38, + "learning_rate": 1.4214786133650162e-05, + "loss": 0.5029, + "step": 4550 + }, + { + "epoch": 0.38, + "learning_rate": 1.4212328533331493e-05, + "loss": 0.4983, + "step": 4551 + }, + { + "epoch": 0.38, + "learning_rate": 1.4209870623676934e-05, + "loss": 0.5079, + "step": 4552 + }, + { + "epoch": 0.38, + "learning_rate": 1.4207412404866992e-05, + "loss": 0.5062, + "step": 4553 + }, + { + "epoch": 0.38, + "learning_rate": 1.420495387708218e-05, + "loss": 0.496, + "step": 4554 + }, + { + "epoch": 0.38, + "learning_rate": 1.4202495040503043e-05, + "loss": 0.5021, + "step": 4555 + }, + { + "epoch": 0.38, + "learning_rate": 1.4200035895310151e-05, + "loss": 0.492, + "step": 4556 + }, + { + "epoch": 0.38, + "learning_rate": 1.4197576441684096e-05, + "loss": 0.4871, + "step": 4557 + }, + { + "epoch": 0.38, + "learning_rate": 1.4195116679805483e-05, + "loss": 0.4845, + "step": 4558 + }, + { + "epoch": 0.38, + "learning_rate": 1.4192656609854949e-05, + "loss": 0.4746, + "step": 4559 + }, + { + "epoch": 0.38, + "learning_rate": 1.4190196232013154e-05, + "loss": 0.486, + "step": 4560 + }, + { + "epoch": 0.38, + "learning_rate": 1.4187735546460775e-05, + "loss": 0.4918, + "step": 4561 + }, + { + "epoch": 0.38, + "learning_rate": 1.4185274553378513e-05, + "loss": 0.5124, + "step": 4562 + }, + { + "epoch": 0.38, + "learning_rate": 1.41828132529471e-05, + "loss": 0.4785, + "step": 4563 + }, + { + "epoch": 0.38, + "learning_rate": 1.4180351645347279e-05, + "loss": 0.4927, + "step": 4564 + }, + { + "epoch": 0.38, + "learning_rate": 1.417788973075982e-05, + "loss": 0.5018, + "step": 4565 + }, + { + "epoch": 0.38, + "learning_rate": 1.4175427509365516e-05, + "loss": 0.4941, + "step": 4566 + }, + { + "epoch": 0.38, + "learning_rate": 1.417296498134518e-05, + "loss": 0.4783, + "step": 4567 + }, + { + "epoch": 0.38, + "learning_rate": 1.4170502146879656e-05, + "loss": 0.5057, + "step": 4568 + }, + { + "epoch": 0.38, + "learning_rate": 1.4168039006149799e-05, + "loss": 0.5271, + "step": 4569 + }, + { + "epoch": 0.38, + "learning_rate": 1.4165575559336496e-05, + "loss": 0.4779, + "step": 4570 + }, + { + "epoch": 0.38, + "learning_rate": 1.4163111806620646e-05, + "loss": 0.4642, + "step": 4571 + }, + { + "epoch": 0.38, + "learning_rate": 1.416064774818318e-05, + "loss": 0.5108, + "step": 4572 + }, + { + "epoch": 0.38, + "learning_rate": 1.4158183384205052e-05, + "loss": 0.4914, + "step": 4573 + }, + { + "epoch": 0.38, + "learning_rate": 1.4155718714867232e-05, + "loss": 0.4902, + "step": 4574 + }, + { + "epoch": 0.38, + "learning_rate": 1.4153253740350717e-05, + "loss": 0.4846, + "step": 4575 + }, + { + "epoch": 0.38, + "learning_rate": 1.4150788460836516e-05, + "loss": 0.4685, + "step": 4576 + }, + { + "epoch": 0.38, + "learning_rate": 1.4148322876505675e-05, + "loss": 0.4808, + "step": 4577 + }, + { + "epoch": 0.38, + "learning_rate": 1.4145856987539261e-05, + "loss": 0.4915, + "step": 4578 + }, + { + "epoch": 0.38, + "learning_rate": 1.414339079411835e-05, + "loss": 0.4938, + "step": 4579 + }, + { + "epoch": 0.38, + "learning_rate": 1.4140924296424055e-05, + "loss": 0.4984, + "step": 4580 + }, + { + "epoch": 0.38, + "learning_rate": 1.4138457494637501e-05, + "loss": 0.4884, + "step": 4581 + }, + { + "epoch": 0.38, + "learning_rate": 1.4135990388939839e-05, + "loss": 0.4833, + "step": 4582 + }, + { + "epoch": 0.38, + "learning_rate": 1.4133522979512252e-05, + "loss": 0.4856, + "step": 4583 + }, + { + "epoch": 0.38, + "learning_rate": 1.4131055266535926e-05, + "loss": 0.4952, + "step": 4584 + }, + { + "epoch": 0.38, + "learning_rate": 1.4128587250192087e-05, + "loss": 0.5056, + "step": 4585 + }, + { + "epoch": 0.38, + "learning_rate": 1.412611893066197e-05, + "loss": 0.4818, + "step": 4586 + }, + { + "epoch": 0.38, + "learning_rate": 1.4123650308126839e-05, + "loss": 0.4854, + "step": 4587 + }, + { + "epoch": 0.38, + "learning_rate": 1.4121181382767986e-05, + "loss": 0.4762, + "step": 4588 + }, + { + "epoch": 0.38, + "learning_rate": 1.4118712154766708e-05, + "loss": 0.4713, + "step": 4589 + }, + { + "epoch": 0.38, + "learning_rate": 1.4116242624304343e-05, + "loss": 0.4836, + "step": 4590 + }, + { + "epoch": 0.38, + "learning_rate": 1.411377279156224e-05, + "loss": 0.4767, + "step": 4591 + }, + { + "epoch": 0.38, + "learning_rate": 1.4111302656721775e-05, + "loss": 0.4845, + "step": 4592 + }, + { + "epoch": 0.38, + "learning_rate": 1.410883221996434e-05, + "loss": 0.4769, + "step": 4593 + }, + { + "epoch": 0.38, + "learning_rate": 1.410636148147136e-05, + "loss": 0.4906, + "step": 4594 + }, + { + "epoch": 0.38, + "learning_rate": 1.4103890441424271e-05, + "loss": 0.4971, + "step": 4595 + }, + { + "epoch": 0.38, + "learning_rate": 1.4101419100004537e-05, + "loss": 0.481, + "step": 4596 + }, + { + "epoch": 0.38, + "learning_rate": 1.4098947457393641e-05, + "loss": 0.4774, + "step": 4597 + }, + { + "epoch": 0.38, + "learning_rate": 1.4096475513773097e-05, + "loss": 0.4893, + "step": 4598 + }, + { + "epoch": 0.38, + "learning_rate": 1.4094003269324428e-05, + "loss": 0.4874, + "step": 4599 + }, + { + "epoch": 0.38, + "learning_rate": 1.4091530724229188e-05, + "loss": 0.5024, + "step": 4600 + }, + { + "epoch": 0.38, + "learning_rate": 1.408905787866895e-05, + "loss": 0.5141, + "step": 4601 + }, + { + "epoch": 0.39, + "learning_rate": 1.4086584732825306e-05, + "loss": 0.4768, + "step": 4602 + }, + { + "epoch": 0.39, + "learning_rate": 1.4084111286879878e-05, + "loss": 0.5029, + "step": 4603 + }, + { + "epoch": 0.39, + "learning_rate": 1.4081637541014306e-05, + "loss": 0.4939, + "step": 4604 + }, + { + "epoch": 0.39, + "learning_rate": 1.4079163495410248e-05, + "loss": 0.4798, + "step": 4605 + }, + { + "epoch": 0.39, + "learning_rate": 1.407668915024939e-05, + "loss": 0.4618, + "step": 4606 + }, + { + "epoch": 0.39, + "learning_rate": 1.4074214505713437e-05, + "loss": 0.4803, + "step": 4607 + }, + { + "epoch": 0.39, + "learning_rate": 1.4071739561984115e-05, + "loss": 0.4847, + "step": 4608 + }, + { + "epoch": 0.39, + "learning_rate": 1.4069264319243178e-05, + "loss": 0.4754, + "step": 4609 + }, + { + "epoch": 0.39, + "learning_rate": 1.4066788777672393e-05, + "loss": 0.5171, + "step": 4610 + }, + { + "epoch": 0.39, + "learning_rate": 1.4064312937453556e-05, + "loss": 0.4757, + "step": 4611 + }, + { + "epoch": 0.39, + "learning_rate": 1.406183679876848e-05, + "loss": 0.5263, + "step": 4612 + }, + { + "epoch": 0.39, + "learning_rate": 1.4059360361799004e-05, + "loss": 0.4928, + "step": 4613 + }, + { + "epoch": 0.39, + "learning_rate": 1.4056883626726989e-05, + "loss": 0.4916, + "step": 4614 + }, + { + "epoch": 0.39, + "learning_rate": 1.4054406593734316e-05, + "loss": 0.482, + "step": 4615 + }, + { + "epoch": 0.39, + "learning_rate": 1.4051929263002884e-05, + "loss": 0.4772, + "step": 4616 + }, + { + "epoch": 0.39, + "learning_rate": 1.404945163471462e-05, + "loss": 0.4909, + "step": 4617 + }, + { + "epoch": 0.39, + "learning_rate": 1.4046973709051467e-05, + "loss": 0.4879, + "step": 4618 + }, + { + "epoch": 0.39, + "learning_rate": 1.4044495486195404e-05, + "loss": 0.492, + "step": 4619 + }, + { + "epoch": 0.39, + "learning_rate": 1.4042016966328411e-05, + "loss": 0.4755, + "step": 4620 + }, + { + "epoch": 0.39, + "learning_rate": 1.4039538149632508e-05, + "loss": 0.526, + "step": 4621 + }, + { + "epoch": 0.39, + "learning_rate": 1.4037059036289722e-05, + "loss": 0.4765, + "step": 4622 + }, + { + "epoch": 0.39, + "learning_rate": 1.4034579626482112e-05, + "loss": 0.4763, + "step": 4623 + }, + { + "epoch": 0.39, + "learning_rate": 1.4032099920391753e-05, + "loss": 0.4879, + "step": 4624 + }, + { + "epoch": 0.39, + "learning_rate": 1.402961991820075e-05, + "loss": 0.4795, + "step": 4625 + }, + { + "epoch": 0.39, + "learning_rate": 1.4027139620091221e-05, + "loss": 0.4731, + "step": 4626 + }, + { + "epoch": 0.39, + "learning_rate": 1.4024659026245307e-05, + "loss": 0.4775, + "step": 4627 + }, + { + "epoch": 0.39, + "learning_rate": 1.4022178136845173e-05, + "loss": 0.5075, + "step": 4628 + }, + { + "epoch": 0.39, + "learning_rate": 1.4019696952073008e-05, + "loss": 0.4915, + "step": 4629 + }, + { + "epoch": 0.39, + "learning_rate": 1.4017215472111016e-05, + "loss": 0.4835, + "step": 4630 + }, + { + "epoch": 0.39, + "learning_rate": 1.401473369714143e-05, + "loss": 0.4964, + "step": 4631 + }, + { + "epoch": 0.39, + "learning_rate": 1.40122516273465e-05, + "loss": 0.4938, + "step": 4632 + }, + { + "epoch": 0.39, + "learning_rate": 1.4009769262908498e-05, + "loss": 0.4688, + "step": 4633 + }, + { + "epoch": 0.39, + "learning_rate": 1.4007286604009717e-05, + "loss": 0.4844, + "step": 4634 + }, + { + "epoch": 0.39, + "learning_rate": 1.400480365083248e-05, + "loss": 0.5028, + "step": 4635 + }, + { + "epoch": 0.39, + "learning_rate": 1.400232040355912e-05, + "loss": 0.4694, + "step": 4636 + }, + { + "epoch": 0.39, + "learning_rate": 1.3999836862371992e-05, + "loss": 0.5068, + "step": 4637 + }, + { + "epoch": 0.39, + "learning_rate": 1.3997353027453484e-05, + "loss": 0.526, + "step": 4638 + }, + { + "epoch": 0.39, + "learning_rate": 1.3994868898985996e-05, + "loss": 0.5087, + "step": 4639 + }, + { + "epoch": 0.39, + "learning_rate": 1.399238447715195e-05, + "loss": 0.4647, + "step": 4640 + }, + { + "epoch": 0.39, + "learning_rate": 1.3989899762133797e-05, + "loss": 0.5089, + "step": 4641 + }, + { + "epoch": 0.39, + "learning_rate": 1.3987414754114e-05, + "loss": 0.477, + "step": 4642 + }, + { + "epoch": 0.39, + "learning_rate": 1.3984929453275045e-05, + "loss": 0.4633, + "step": 4643 + }, + { + "epoch": 0.39, + "learning_rate": 1.3982443859799446e-05, + "loss": 0.4792, + "step": 4644 + }, + { + "epoch": 0.39, + "learning_rate": 1.3979957973869738e-05, + "loss": 0.508, + "step": 4645 + }, + { + "epoch": 0.39, + "learning_rate": 1.397747179566847e-05, + "loss": 0.4722, + "step": 4646 + }, + { + "epoch": 0.39, + "learning_rate": 1.3974985325378215e-05, + "loss": 0.4924, + "step": 4647 + }, + { + "epoch": 0.39, + "learning_rate": 1.397249856318157e-05, + "loss": 0.4871, + "step": 4648 + }, + { + "epoch": 0.39, + "learning_rate": 1.3970011509261155e-05, + "loss": 0.4978, + "step": 4649 + }, + { + "epoch": 0.39, + "learning_rate": 1.3967524163799606e-05, + "loss": 0.4922, + "step": 4650 + }, + { + "epoch": 0.39, + "learning_rate": 1.3965036526979586e-05, + "loss": 0.4957, + "step": 4651 + }, + { + "epoch": 0.39, + "learning_rate": 1.3962548598983774e-05, + "loss": 0.4908, + "step": 4652 + }, + { + "epoch": 0.39, + "learning_rate": 1.3960060379994875e-05, + "loss": 0.489, + "step": 4653 + }, + { + "epoch": 0.39, + "learning_rate": 1.395757187019561e-05, + "loss": 0.4736, + "step": 4654 + }, + { + "epoch": 0.39, + "learning_rate": 1.3955083069768733e-05, + "loss": 0.4822, + "step": 4655 + }, + { + "epoch": 0.39, + "learning_rate": 1.3952593978897002e-05, + "loss": 0.4798, + "step": 4656 + }, + { + "epoch": 0.39, + "learning_rate": 1.3950104597763212e-05, + "loss": 0.4925, + "step": 4657 + }, + { + "epoch": 0.39, + "learning_rate": 1.3947614926550168e-05, + "loss": 0.4817, + "step": 4658 + }, + { + "epoch": 0.39, + "learning_rate": 1.3945124965440701e-05, + "loss": 0.4935, + "step": 4659 + }, + { + "epoch": 0.39, + "learning_rate": 1.3942634714617671e-05, + "loss": 0.5021, + "step": 4660 + }, + { + "epoch": 0.39, + "learning_rate": 1.3940144174263943e-05, + "loss": 0.492, + "step": 4661 + }, + { + "epoch": 0.39, + "learning_rate": 1.3937653344562417e-05, + "loss": 0.4698, + "step": 4662 + }, + { + "epoch": 0.39, + "learning_rate": 1.3935162225696006e-05, + "loss": 0.4974, + "step": 4663 + }, + { + "epoch": 0.39, + "learning_rate": 1.3932670817847647e-05, + "loss": 0.4825, + "step": 4664 + }, + { + "epoch": 0.39, + "learning_rate": 1.3930179121200303e-05, + "loss": 0.4825, + "step": 4665 + }, + { + "epoch": 0.39, + "learning_rate": 1.392768713593695e-05, + "loss": 0.4866, + "step": 4666 + }, + { + "epoch": 0.39, + "learning_rate": 1.3925194862240589e-05, + "loss": 0.498, + "step": 4667 + }, + { + "epoch": 0.39, + "learning_rate": 1.3922702300294246e-05, + "loss": 0.4945, + "step": 4668 + }, + { + "epoch": 0.39, + "learning_rate": 1.3920209450280959e-05, + "loss": 0.4962, + "step": 4669 + }, + { + "epoch": 0.39, + "learning_rate": 1.3917716312383797e-05, + "loss": 0.4794, + "step": 4670 + }, + { + "epoch": 0.39, + "learning_rate": 1.3915222886785844e-05, + "loss": 0.4718, + "step": 4671 + }, + { + "epoch": 0.39, + "learning_rate": 1.3912729173670207e-05, + "loss": 0.485, + "step": 4672 + }, + { + "epoch": 0.39, + "learning_rate": 1.3910235173220015e-05, + "loss": 0.4924, + "step": 4673 + }, + { + "epoch": 0.39, + "learning_rate": 1.3907740885618415e-05, + "loss": 0.4844, + "step": 4674 + }, + { + "epoch": 0.39, + "learning_rate": 1.3905246311048575e-05, + "loss": 0.4807, + "step": 4675 + }, + { + "epoch": 0.39, + "learning_rate": 1.3902751449693693e-05, + "loss": 0.4933, + "step": 4676 + }, + { + "epoch": 0.39, + "learning_rate": 1.3900256301736976e-05, + "loss": 0.4699, + "step": 4677 + }, + { + "epoch": 0.39, + "learning_rate": 1.3897760867361657e-05, + "loss": 0.4775, + "step": 4678 + }, + { + "epoch": 0.39, + "learning_rate": 1.3895265146750994e-05, + "loss": 0.4956, + "step": 4679 + }, + { + "epoch": 0.39, + "learning_rate": 1.3892769140088259e-05, + "loss": 0.4707, + "step": 4680 + }, + { + "epoch": 0.39, + "learning_rate": 1.3890272847556747e-05, + "loss": 0.4774, + "step": 4681 + }, + { + "epoch": 0.39, + "learning_rate": 1.3887776269339783e-05, + "loss": 0.4832, + "step": 4682 + }, + { + "epoch": 0.39, + "learning_rate": 1.38852794056207e-05, + "loss": 0.4933, + "step": 4683 + }, + { + "epoch": 0.39, + "learning_rate": 1.3882782256582852e-05, + "loss": 0.4934, + "step": 4684 + }, + { + "epoch": 0.39, + "learning_rate": 1.388028482240963e-05, + "loss": 0.4822, + "step": 4685 + }, + { + "epoch": 0.39, + "learning_rate": 1.3877787103284428e-05, + "loss": 0.4891, + "step": 4686 + }, + { + "epoch": 0.39, + "learning_rate": 1.3875289099390672e-05, + "loss": 0.4905, + "step": 4687 + }, + { + "epoch": 0.39, + "learning_rate": 1.38727908109118e-05, + "loss": 0.5032, + "step": 4688 + }, + { + "epoch": 0.39, + "learning_rate": 1.3870292238031283e-05, + "loss": 0.4791, + "step": 4689 + }, + { + "epoch": 0.39, + "learning_rate": 1.3867793380932597e-05, + "loss": 0.4809, + "step": 4690 + }, + { + "epoch": 0.39, + "learning_rate": 1.3865294239799254e-05, + "loss": 0.4697, + "step": 4691 + }, + { + "epoch": 0.39, + "learning_rate": 1.386279481481478e-05, + "loss": 0.5101, + "step": 4692 + }, + { + "epoch": 0.39, + "learning_rate": 1.3860295106162722e-05, + "loss": 0.477, + "step": 4693 + }, + { + "epoch": 0.39, + "learning_rate": 1.3857795114026648e-05, + "loss": 0.4973, + "step": 4694 + }, + { + "epoch": 0.39, + "learning_rate": 1.3855294838590143e-05, + "loss": 0.4843, + "step": 4695 + }, + { + "epoch": 0.39, + "learning_rate": 1.3852794280036823e-05, + "loss": 0.4937, + "step": 4696 + }, + { + "epoch": 0.39, + "learning_rate": 1.3850293438550317e-05, + "loss": 0.481, + "step": 4697 + }, + { + "epoch": 0.39, + "learning_rate": 1.3847792314314272e-05, + "loss": 0.4813, + "step": 4698 + }, + { + "epoch": 0.39, + "learning_rate": 1.3845290907512367e-05, + "loss": 0.4771, + "step": 4699 + }, + { + "epoch": 0.39, + "learning_rate": 1.3842789218328289e-05, + "loss": 0.5068, + "step": 4700 + }, + { + "epoch": 0.39, + "learning_rate": 1.3840287246945759e-05, + "loss": 0.4914, + "step": 4701 + }, + { + "epoch": 0.39, + "learning_rate": 1.38377849935485e-05, + "loss": 0.4749, + "step": 4702 + }, + { + "epoch": 0.39, + "learning_rate": 1.3835282458320278e-05, + "loss": 0.4946, + "step": 4703 + }, + { + "epoch": 0.39, + "learning_rate": 1.3832779641444864e-05, + "loss": 0.4967, + "step": 4704 + }, + { + "epoch": 0.39, + "learning_rate": 1.3830276543106053e-05, + "loss": 0.4846, + "step": 4705 + }, + { + "epoch": 0.39, + "learning_rate": 1.3827773163487663e-05, + "loss": 0.4776, + "step": 4706 + }, + { + "epoch": 0.39, + "learning_rate": 1.3825269502773538e-05, + "loss": 0.505, + "step": 4707 + }, + { + "epoch": 0.39, + "learning_rate": 1.3822765561147529e-05, + "loss": 0.465, + "step": 4708 + }, + { + "epoch": 0.39, + "learning_rate": 1.3820261338793515e-05, + "loss": 0.4896, + "step": 4709 + }, + { + "epoch": 0.39, + "learning_rate": 1.3817756835895399e-05, + "loss": 0.5086, + "step": 4710 + }, + { + "epoch": 0.39, + "learning_rate": 1.38152520526371e-05, + "loss": 0.5081, + "step": 4711 + }, + { + "epoch": 0.39, + "learning_rate": 1.3812746989202559e-05, + "loss": 0.4698, + "step": 4712 + }, + { + "epoch": 0.39, + "learning_rate": 1.3810241645775738e-05, + "loss": 0.497, + "step": 4713 + }, + { + "epoch": 0.39, + "learning_rate": 1.380773602254062e-05, + "loss": 0.4849, + "step": 4714 + }, + { + "epoch": 0.39, + "learning_rate": 1.3805230119681203e-05, + "loss": 0.4766, + "step": 4715 + }, + { + "epoch": 0.39, + "learning_rate": 1.3802723937381512e-05, + "loss": 0.4944, + "step": 4716 + }, + { + "epoch": 0.39, + "learning_rate": 1.3800217475825597e-05, + "loss": 0.489, + "step": 4717 + }, + { + "epoch": 0.39, + "learning_rate": 1.3797710735197516e-05, + "loss": 0.4637, + "step": 4718 + }, + { + "epoch": 0.39, + "learning_rate": 1.379520371568135e-05, + "loss": 0.482, + "step": 4719 + }, + { + "epoch": 0.39, + "learning_rate": 1.3792696417461213e-05, + "loss": 0.5144, + "step": 4720 + }, + { + "epoch": 0.39, + "learning_rate": 1.3790188840721223e-05, + "loss": 0.4927, + "step": 4721 + }, + { + "epoch": 0.4, + "learning_rate": 1.378768098564553e-05, + "loss": 0.4736, + "step": 4722 + }, + { + "epoch": 0.4, + "learning_rate": 1.3785172852418303e-05, + "loss": 0.4891, + "step": 4723 + }, + { + "epoch": 0.4, + "learning_rate": 1.3782664441223724e-05, + "loss": 0.495, + "step": 4724 + }, + { + "epoch": 0.4, + "learning_rate": 1.3780155752246e-05, + "loss": 0.4943, + "step": 4725 + }, + { + "epoch": 0.4, + "learning_rate": 1.3777646785669357e-05, + "loss": 0.4907, + "step": 4726 + }, + { + "epoch": 0.4, + "learning_rate": 1.3775137541678052e-05, + "loss": 0.4822, + "step": 4727 + }, + { + "epoch": 0.4, + "learning_rate": 1.3772628020456346e-05, + "loss": 0.4896, + "step": 4728 + }, + { + "epoch": 0.4, + "learning_rate": 1.3770118222188529e-05, + "loss": 0.4812, + "step": 4729 + }, + { + "epoch": 0.4, + "learning_rate": 1.3767608147058913e-05, + "loss": 0.4859, + "step": 4730 + }, + { + "epoch": 0.4, + "learning_rate": 1.3765097795251822e-05, + "loss": 0.4721, + "step": 4731 + }, + { + "epoch": 0.4, + "learning_rate": 1.376258716695161e-05, + "loss": 0.4959, + "step": 4732 + }, + { + "epoch": 0.4, + "learning_rate": 1.376007626234265e-05, + "loss": 0.4818, + "step": 4733 + }, + { + "epoch": 0.4, + "learning_rate": 1.3757565081609327e-05, + "loss": 0.4732, + "step": 4734 + }, + { + "epoch": 0.4, + "learning_rate": 1.3755053624936055e-05, + "loss": 0.4902, + "step": 4735 + }, + { + "epoch": 0.4, + "learning_rate": 1.375254189250726e-05, + "loss": 0.4942, + "step": 4736 + }, + { + "epoch": 0.4, + "learning_rate": 1.3750029884507394e-05, + "loss": 0.4723, + "step": 4737 + }, + { + "epoch": 0.4, + "learning_rate": 1.3747517601120934e-05, + "loss": 0.5007, + "step": 4738 + }, + { + "epoch": 0.4, + "learning_rate": 1.3745005042532369e-05, + "loss": 0.5025, + "step": 4739 + }, + { + "epoch": 0.4, + "learning_rate": 1.374249220892621e-05, + "loss": 0.4768, + "step": 4740 + }, + { + "epoch": 0.4, + "learning_rate": 1.3739979100486986e-05, + "loss": 0.494, + "step": 4741 + }, + { + "epoch": 0.4, + "learning_rate": 1.3737465717399259e-05, + "loss": 0.5006, + "step": 4742 + }, + { + "epoch": 0.4, + "learning_rate": 1.3734952059847589e-05, + "loss": 0.4787, + "step": 4743 + }, + { + "epoch": 0.4, + "learning_rate": 1.3732438128016578e-05, + "loss": 0.486, + "step": 4744 + }, + { + "epoch": 0.4, + "learning_rate": 1.3729923922090836e-05, + "loss": 0.5041, + "step": 4745 + }, + { + "epoch": 0.4, + "learning_rate": 1.3727409442254994e-05, + "loss": 0.4867, + "step": 4746 + }, + { + "epoch": 0.4, + "learning_rate": 1.3724894688693704e-05, + "loss": 0.5076, + "step": 4747 + }, + { + "epoch": 0.4, + "learning_rate": 1.3722379661591643e-05, + "loss": 0.5011, + "step": 4748 + }, + { + "epoch": 0.4, + "learning_rate": 1.3719864361133502e-05, + "loss": 0.4931, + "step": 4749 + }, + { + "epoch": 0.4, + "learning_rate": 1.3717348787503993e-05, + "loss": 0.4803, + "step": 4750 + }, + { + "epoch": 0.4, + "learning_rate": 1.3714832940887854e-05, + "loss": 0.4869, + "step": 4751 + }, + { + "epoch": 0.4, + "learning_rate": 1.3712316821469831e-05, + "loss": 0.4963, + "step": 4752 + }, + { + "epoch": 0.4, + "learning_rate": 1.3709800429434702e-05, + "loss": 0.4769, + "step": 4753 + }, + { + "epoch": 0.4, + "learning_rate": 1.370728376496726e-05, + "loss": 0.477, + "step": 4754 + }, + { + "epoch": 0.4, + "learning_rate": 1.3704766828252321e-05, + "loss": 0.5086, + "step": 4755 + }, + { + "epoch": 0.4, + "learning_rate": 1.3702249619474712e-05, + "loss": 0.4896, + "step": 4756 + }, + { + "epoch": 0.4, + "learning_rate": 1.369973213881929e-05, + "loss": 0.4693, + "step": 4757 + }, + { + "epoch": 0.4, + "learning_rate": 1.3697214386470932e-05, + "loss": 0.4847, + "step": 4758 + }, + { + "epoch": 0.4, + "learning_rate": 1.3694696362614524e-05, + "loss": 0.4807, + "step": 4759 + }, + { + "epoch": 0.4, + "learning_rate": 1.3692178067434982e-05, + "loss": 0.4717, + "step": 4760 + }, + { + "epoch": 0.4, + "learning_rate": 1.3689659501117243e-05, + "loss": 0.4815, + "step": 4761 + }, + { + "epoch": 0.4, + "learning_rate": 1.3687140663846252e-05, + "loss": 0.4829, + "step": 4762 + }, + { + "epoch": 0.4, + "learning_rate": 1.3684621555806988e-05, + "loss": 0.4869, + "step": 4763 + }, + { + "epoch": 0.4, + "learning_rate": 1.3682102177184444e-05, + "loss": 0.4915, + "step": 4764 + }, + { + "epoch": 0.4, + "learning_rate": 1.3679582528163633e-05, + "loss": 0.4821, + "step": 4765 + }, + { + "epoch": 0.4, + "learning_rate": 1.3677062608929583e-05, + "loss": 0.4984, + "step": 4766 + }, + { + "epoch": 0.4, + "learning_rate": 1.3674542419667347e-05, + "loss": 0.4911, + "step": 4767 + }, + { + "epoch": 0.4, + "learning_rate": 1.3672021960562001e-05, + "loss": 0.4761, + "step": 4768 + }, + { + "epoch": 0.4, + "learning_rate": 1.3669501231798638e-05, + "loss": 0.4801, + "step": 4769 + }, + { + "epoch": 0.4, + "learning_rate": 1.3666980233562364e-05, + "loss": 0.5164, + "step": 4770 + }, + { + "epoch": 0.4, + "learning_rate": 1.3664458966038314e-05, + "loss": 0.4852, + "step": 4771 + }, + { + "epoch": 0.4, + "learning_rate": 1.366193742941164e-05, + "loss": 0.4944, + "step": 4772 + }, + { + "epoch": 0.4, + "learning_rate": 1.365941562386751e-05, + "loss": 0.4886, + "step": 4773 + }, + { + "epoch": 0.4, + "learning_rate": 1.3656893549591121e-05, + "loss": 0.4837, + "step": 4774 + }, + { + "epoch": 0.4, + "learning_rate": 1.3654371206767678e-05, + "loss": 0.4903, + "step": 4775 + }, + { + "epoch": 0.4, + "learning_rate": 1.3651848595582416e-05, + "loss": 0.4611, + "step": 4776 + }, + { + "epoch": 0.4, + "learning_rate": 1.3649325716220579e-05, + "loss": 0.4914, + "step": 4777 + }, + { + "epoch": 0.4, + "learning_rate": 1.364680256886744e-05, + "loss": 0.4672, + "step": 4778 + }, + { + "epoch": 0.4, + "learning_rate": 1.364427915370829e-05, + "loss": 0.4768, + "step": 4779 + }, + { + "epoch": 0.4, + "learning_rate": 1.3641755470928435e-05, + "loss": 0.4871, + "step": 4780 + }, + { + "epoch": 0.4, + "learning_rate": 1.3639231520713207e-05, + "loss": 0.4953, + "step": 4781 + }, + { + "epoch": 0.4, + "learning_rate": 1.3636707303247953e-05, + "loss": 0.4642, + "step": 4782 + }, + { + "epoch": 0.4, + "learning_rate": 1.363418281871804e-05, + "loss": 0.5042, + "step": 4783 + }, + { + "epoch": 0.4, + "learning_rate": 1.3631658067308857e-05, + "loss": 0.485, + "step": 4784 + }, + { + "epoch": 0.4, + "learning_rate": 1.362913304920581e-05, + "loss": 0.4988, + "step": 4785 + }, + { + "epoch": 0.4, + "learning_rate": 1.3626607764594329e-05, + "loss": 0.4921, + "step": 4786 + }, + { + "epoch": 0.4, + "learning_rate": 1.3624082213659854e-05, + "loss": 0.5012, + "step": 4787 + }, + { + "epoch": 0.4, + "learning_rate": 1.3621556396587856e-05, + "loss": 0.4926, + "step": 4788 + }, + { + "epoch": 0.4, + "learning_rate": 1.3619030313563821e-05, + "loss": 0.4879, + "step": 4789 + }, + { + "epoch": 0.4, + "learning_rate": 1.3616503964773252e-05, + "loss": 0.4911, + "step": 4790 + }, + { + "epoch": 0.4, + "learning_rate": 1.3613977350401675e-05, + "loss": 0.4665, + "step": 4791 + }, + { + "epoch": 0.4, + "learning_rate": 1.3611450470634631e-05, + "loss": 0.4938, + "step": 4792 + }, + { + "epoch": 0.4, + "learning_rate": 1.3608923325657686e-05, + "loss": 0.4847, + "step": 4793 + }, + { + "epoch": 0.4, + "learning_rate": 1.3606395915656423e-05, + "loss": 0.5109, + "step": 4794 + }, + { + "epoch": 0.4, + "learning_rate": 1.3603868240816445e-05, + "loss": 0.4765, + "step": 4795 + }, + { + "epoch": 0.4, + "learning_rate": 1.3601340301323371e-05, + "loss": 0.4859, + "step": 4796 + }, + { + "epoch": 0.4, + "learning_rate": 1.3598812097362846e-05, + "loss": 0.505, + "step": 4797 + }, + { + "epoch": 0.4, + "learning_rate": 1.3596283629120527e-05, + "loss": 0.5041, + "step": 4798 + }, + { + "epoch": 0.4, + "learning_rate": 1.3593754896782099e-05, + "loss": 0.4924, + "step": 4799 + }, + { + "epoch": 0.4, + "learning_rate": 1.359122590053326e-05, + "loss": 0.467, + "step": 4800 + }, + { + "epoch": 0.4, + "learning_rate": 1.3588696640559725e-05, + "loss": 0.5029, + "step": 4801 + }, + { + "epoch": 0.4, + "learning_rate": 1.3586167117047238e-05, + "loss": 0.4932, + "step": 4802 + }, + { + "epoch": 0.4, + "learning_rate": 1.358363733018155e-05, + "loss": 0.4759, + "step": 4803 + }, + { + "epoch": 0.4, + "learning_rate": 1.3581107280148443e-05, + "loss": 0.5209, + "step": 4804 + }, + { + "epoch": 0.4, + "learning_rate": 1.3578576967133712e-05, + "loss": 0.4676, + "step": 4805 + }, + { + "epoch": 0.4, + "learning_rate": 1.3576046391323176e-05, + "loss": 0.4666, + "step": 4806 + }, + { + "epoch": 0.4, + "learning_rate": 1.3573515552902663e-05, + "loss": 0.4912, + "step": 4807 + }, + { + "epoch": 0.4, + "learning_rate": 1.3570984452058035e-05, + "loss": 0.4882, + "step": 4808 + }, + { + "epoch": 0.4, + "learning_rate": 1.356845308897516e-05, + "loss": 0.475, + "step": 4809 + }, + { + "epoch": 0.4, + "learning_rate": 1.3565921463839934e-05, + "loss": 0.4938, + "step": 4810 + }, + { + "epoch": 0.4, + "learning_rate": 1.3563389576838264e-05, + "loss": 0.4858, + "step": 4811 + }, + { + "epoch": 0.4, + "learning_rate": 1.3560857428156086e-05, + "loss": 0.4817, + "step": 4812 + }, + { + "epoch": 0.4, + "learning_rate": 1.355832501797935e-05, + "loss": 0.5182, + "step": 4813 + }, + { + "epoch": 0.4, + "learning_rate": 1.3555792346494023e-05, + "loss": 0.5071, + "step": 4814 + }, + { + "epoch": 0.4, + "learning_rate": 1.35532594138861e-05, + "loss": 0.486, + "step": 4815 + }, + { + "epoch": 0.4, + "learning_rate": 1.355072622034158e-05, + "loss": 0.4677, + "step": 4816 + }, + { + "epoch": 0.4, + "learning_rate": 1.3548192766046499e-05, + "loss": 0.4871, + "step": 4817 + }, + { + "epoch": 0.4, + "learning_rate": 1.3545659051186897e-05, + "loss": 0.505, + "step": 4818 + }, + { + "epoch": 0.4, + "learning_rate": 1.3543125075948842e-05, + "loss": 0.4679, + "step": 4819 + }, + { + "epoch": 0.4, + "learning_rate": 1.354059084051842e-05, + "loss": 0.518, + "step": 4820 + }, + { + "epoch": 0.4, + "learning_rate": 1.3538056345081729e-05, + "loss": 0.4902, + "step": 4821 + }, + { + "epoch": 0.4, + "learning_rate": 1.35355215898249e-05, + "loss": 0.4813, + "step": 4822 + }, + { + "epoch": 0.4, + "learning_rate": 1.3532986574934071e-05, + "loss": 0.4975, + "step": 4823 + }, + { + "epoch": 0.4, + "learning_rate": 1.35304513005954e-05, + "loss": 0.4795, + "step": 4824 + }, + { + "epoch": 0.4, + "learning_rate": 1.352791576699507e-05, + "loss": 0.4782, + "step": 4825 + }, + { + "epoch": 0.4, + "learning_rate": 1.3525379974319282e-05, + "loss": 0.491, + "step": 4826 + }, + { + "epoch": 0.4, + "learning_rate": 1.352284392275425e-05, + "loss": 0.4788, + "step": 4827 + }, + { + "epoch": 0.4, + "learning_rate": 1.3520307612486211e-05, + "loss": 0.4711, + "step": 4828 + }, + { + "epoch": 0.4, + "learning_rate": 1.3517771043701427e-05, + "loss": 0.4901, + "step": 4829 + }, + { + "epoch": 0.4, + "learning_rate": 1.3515234216586169e-05, + "loss": 0.4877, + "step": 4830 + }, + { + "epoch": 0.4, + "learning_rate": 1.3512697131326726e-05, + "loss": 0.4863, + "step": 4831 + }, + { + "epoch": 0.4, + "learning_rate": 1.351015978810942e-05, + "loss": 0.4971, + "step": 4832 + }, + { + "epoch": 0.4, + "learning_rate": 1.3507622187120582e-05, + "loss": 0.4835, + "step": 4833 + }, + { + "epoch": 0.4, + "learning_rate": 1.3505084328546554e-05, + "loss": 0.4859, + "step": 4834 + }, + { + "epoch": 0.4, + "learning_rate": 1.3502546212573715e-05, + "loss": 0.4858, + "step": 4835 + }, + { + "epoch": 0.4, + "learning_rate": 1.350000783938845e-05, + "loss": 0.4833, + "step": 4836 + }, + { + "epoch": 0.4, + "learning_rate": 1.3497469209177166e-05, + "loss": 0.4879, + "step": 4837 + }, + { + "epoch": 0.4, + "learning_rate": 1.349493032212629e-05, + "loss": 0.4848, + "step": 4838 + }, + { + "epoch": 0.4, + "learning_rate": 1.3492391178422271e-05, + "loss": 0.4863, + "step": 4839 + }, + { + "epoch": 0.4, + "learning_rate": 1.3489851778251563e-05, + "loss": 0.48, + "step": 4840 + }, + { + "epoch": 0.41, + "learning_rate": 1.3487312121800661e-05, + "loss": 0.4777, + "step": 4841 + }, + { + "epoch": 0.41, + "learning_rate": 1.3484772209256061e-05, + "loss": 0.4783, + "step": 4842 + }, + { + "epoch": 0.41, + "learning_rate": 1.3482232040804286e-05, + "loss": 0.5042, + "step": 4843 + }, + { + "epoch": 0.41, + "learning_rate": 1.3479691616631869e-05, + "loss": 0.4642, + "step": 4844 + }, + { + "epoch": 0.41, + "learning_rate": 1.3477150936925374e-05, + "loss": 0.4839, + "step": 4845 + }, + { + "epoch": 0.41, + "learning_rate": 1.3474610001871379e-05, + "loss": 0.4922, + "step": 4846 + }, + { + "epoch": 0.41, + "learning_rate": 1.3472068811656477e-05, + "loss": 0.4956, + "step": 4847 + }, + { + "epoch": 0.41, + "learning_rate": 1.3469527366467281e-05, + "loss": 0.479, + "step": 4848 + }, + { + "epoch": 0.41, + "learning_rate": 1.3466985666490428e-05, + "loss": 0.502, + "step": 4849 + }, + { + "epoch": 0.41, + "learning_rate": 1.3464443711912566e-05, + "loss": 0.4734, + "step": 4850 + }, + { + "epoch": 0.41, + "learning_rate": 1.3461901502920371e-05, + "loss": 0.4976, + "step": 4851 + }, + { + "epoch": 0.41, + "learning_rate": 1.3459359039700525e-05, + "loss": 0.4828, + "step": 4852 + }, + { + "epoch": 0.41, + "learning_rate": 1.3456816322439742e-05, + "loss": 0.488, + "step": 4853 + }, + { + "epoch": 0.41, + "learning_rate": 1.3454273351324747e-05, + "loss": 0.4822, + "step": 4854 + }, + { + "epoch": 0.41, + "learning_rate": 1.345173012654228e-05, + "loss": 0.4855, + "step": 4855 + }, + { + "epoch": 0.41, + "learning_rate": 1.3449186648279114e-05, + "loss": 0.4978, + "step": 4856 + }, + { + "epoch": 0.41, + "learning_rate": 1.3446642916722027e-05, + "loss": 0.4827, + "step": 4857 + }, + { + "epoch": 0.41, + "learning_rate": 1.3444098932057818e-05, + "loss": 0.5126, + "step": 4858 + }, + { + "epoch": 0.41, + "learning_rate": 1.3441554694473307e-05, + "loss": 0.4707, + "step": 4859 + }, + { + "epoch": 0.41, + "learning_rate": 1.3439010204155334e-05, + "loss": 0.5114, + "step": 4860 + }, + { + "epoch": 0.41, + "learning_rate": 1.3436465461290757e-05, + "loss": 0.5015, + "step": 4861 + }, + { + "epoch": 0.41, + "learning_rate": 1.343392046606645e-05, + "loss": 0.4831, + "step": 4862 + }, + { + "epoch": 0.41, + "learning_rate": 1.3431375218669307e-05, + "loss": 0.4898, + "step": 4863 + }, + { + "epoch": 0.41, + "learning_rate": 1.342882971928624e-05, + "loss": 0.4893, + "step": 4864 + }, + { + "epoch": 0.41, + "learning_rate": 1.3426283968104178e-05, + "loss": 0.4799, + "step": 4865 + }, + { + "epoch": 0.41, + "learning_rate": 1.3423737965310073e-05, + "loss": 0.4845, + "step": 4866 + }, + { + "epoch": 0.41, + "learning_rate": 1.3421191711090895e-05, + "loss": 0.4986, + "step": 4867 + }, + { + "epoch": 0.41, + "learning_rate": 1.3418645205633625e-05, + "loss": 0.4814, + "step": 4868 + }, + { + "epoch": 0.41, + "learning_rate": 1.341609844912527e-05, + "loss": 0.4772, + "step": 4869 + }, + { + "epoch": 0.41, + "learning_rate": 1.3413551441752855e-05, + "loss": 0.4904, + "step": 4870 + }, + { + "epoch": 0.41, + "learning_rate": 1.341100418370342e-05, + "loss": 0.4926, + "step": 4871 + }, + { + "epoch": 0.41, + "learning_rate": 1.3408456675164023e-05, + "loss": 0.4714, + "step": 4872 + }, + { + "epoch": 0.41, + "learning_rate": 1.3405908916321748e-05, + "loss": 0.471, + "step": 4873 + }, + { + "epoch": 0.41, + "learning_rate": 1.3403360907363687e-05, + "loss": 0.5065, + "step": 4874 + }, + { + "epoch": 0.41, + "learning_rate": 1.3400812648476956e-05, + "loss": 0.4832, + "step": 4875 + }, + { + "epoch": 0.41, + "learning_rate": 1.3398264139848687e-05, + "loss": 0.4877, + "step": 4876 + }, + { + "epoch": 0.41, + "learning_rate": 1.3395715381666038e-05, + "loss": 0.4762, + "step": 4877 + }, + { + "epoch": 0.41, + "learning_rate": 1.3393166374116175e-05, + "loss": 0.4868, + "step": 4878 + }, + { + "epoch": 0.41, + "learning_rate": 1.3390617117386285e-05, + "loss": 0.4823, + "step": 4879 + }, + { + "epoch": 0.41, + "learning_rate": 1.3388067611663578e-05, + "loss": 0.4737, + "step": 4880 + }, + { + "epoch": 0.41, + "learning_rate": 1.3385517857135274e-05, + "loss": 0.4901, + "step": 4881 + }, + { + "epoch": 0.41, + "learning_rate": 1.3382967853988623e-05, + "loss": 0.4653, + "step": 4882 + }, + { + "epoch": 0.41, + "learning_rate": 1.3380417602410884e-05, + "loss": 0.4864, + "step": 4883 + }, + { + "epoch": 0.41, + "learning_rate": 1.3377867102589336e-05, + "loss": 0.4931, + "step": 4884 + }, + { + "epoch": 0.41, + "learning_rate": 1.3375316354711277e-05, + "loss": 0.4761, + "step": 4885 + }, + { + "epoch": 0.41, + "learning_rate": 1.3372765358964024e-05, + "loss": 0.489, + "step": 4886 + }, + { + "epoch": 0.41, + "learning_rate": 1.3370214115534912e-05, + "loss": 0.4897, + "step": 4887 + }, + { + "epoch": 0.41, + "learning_rate": 1.3367662624611293e-05, + "loss": 0.4856, + "step": 4888 + }, + { + "epoch": 0.41, + "learning_rate": 1.3365110886380537e-05, + "loss": 0.5125, + "step": 4889 + }, + { + "epoch": 0.41, + "learning_rate": 1.3362558901030035e-05, + "loss": 0.4959, + "step": 4890 + }, + { + "epoch": 0.41, + "learning_rate": 1.3360006668747195e-05, + "loss": 0.4597, + "step": 4891 + }, + { + "epoch": 0.41, + "learning_rate": 1.3357454189719437e-05, + "loss": 0.5056, + "step": 4892 + }, + { + "epoch": 0.41, + "learning_rate": 1.3354901464134208e-05, + "loss": 0.4856, + "step": 4893 + }, + { + "epoch": 0.41, + "learning_rate": 1.3352348492178972e-05, + "loss": 0.4788, + "step": 4894 + }, + { + "epoch": 0.41, + "learning_rate": 1.3349795274041208e-05, + "loss": 0.4858, + "step": 4895 + }, + { + "epoch": 0.41, + "learning_rate": 1.3347241809908408e-05, + "loss": 0.4982, + "step": 4896 + }, + { + "epoch": 0.41, + "learning_rate": 1.3344688099968092e-05, + "loss": 0.4558, + "step": 4897 + }, + { + "epoch": 0.41, + "learning_rate": 1.3342134144407796e-05, + "loss": 0.482, + "step": 4898 + }, + { + "epoch": 0.41, + "learning_rate": 1.3339579943415069e-05, + "loss": 0.5045, + "step": 4899 + }, + { + "epoch": 0.41, + "learning_rate": 1.333702549717748e-05, + "loss": 0.4684, + "step": 4900 + }, + { + "epoch": 0.41, + "learning_rate": 1.3334470805882615e-05, + "loss": 0.4804, + "step": 4901 + }, + { + "epoch": 0.41, + "learning_rate": 1.3331915869718088e-05, + "loss": 0.4914, + "step": 4902 + }, + { + "epoch": 0.41, + "learning_rate": 1.3329360688871518e-05, + "loss": 0.4885, + "step": 4903 + }, + { + "epoch": 0.41, + "learning_rate": 1.3326805263530545e-05, + "loss": 0.4959, + "step": 4904 + }, + { + "epoch": 0.41, + "learning_rate": 1.3324249593882832e-05, + "loss": 0.4996, + "step": 4905 + }, + { + "epoch": 0.41, + "learning_rate": 1.3321693680116054e-05, + "loss": 0.4728, + "step": 4906 + }, + { + "epoch": 0.41, + "learning_rate": 1.3319137522417908e-05, + "loss": 0.4861, + "step": 4907 + }, + { + "epoch": 0.41, + "learning_rate": 1.3316581120976109e-05, + "loss": 0.4854, + "step": 4908 + }, + { + "epoch": 0.41, + "learning_rate": 1.3314024475978388e-05, + "loss": 0.4933, + "step": 4909 + }, + { + "epoch": 0.41, + "learning_rate": 1.331146758761249e-05, + "loss": 0.4676, + "step": 4910 + }, + { + "epoch": 0.41, + "learning_rate": 1.3308910456066191e-05, + "loss": 0.4983, + "step": 4911 + }, + { + "epoch": 0.41, + "learning_rate": 1.3306353081527265e-05, + "loss": 0.5059, + "step": 4912 + }, + { + "epoch": 0.41, + "learning_rate": 1.3303795464183522e-05, + "loss": 0.4859, + "step": 4913 + }, + { + "epoch": 0.41, + "learning_rate": 1.3301237604222786e-05, + "loss": 0.5003, + "step": 4914 + }, + { + "epoch": 0.41, + "learning_rate": 1.329867950183289e-05, + "loss": 0.4709, + "step": 4915 + }, + { + "epoch": 0.41, + "learning_rate": 1.3296121157201689e-05, + "loss": 0.5096, + "step": 4916 + }, + { + "epoch": 0.41, + "learning_rate": 1.329356257051706e-05, + "loss": 0.4888, + "step": 4917 + }, + { + "epoch": 0.41, + "learning_rate": 1.3291003741966898e-05, + "loss": 0.4876, + "step": 4918 + }, + { + "epoch": 0.41, + "learning_rate": 1.3288444671739106e-05, + "loss": 0.4887, + "step": 4919 + }, + { + "epoch": 0.41, + "learning_rate": 1.3285885360021615e-05, + "loss": 0.4732, + "step": 4920 + }, + { + "epoch": 0.41, + "learning_rate": 1.3283325807002374e-05, + "loss": 0.4874, + "step": 4921 + }, + { + "epoch": 0.41, + "learning_rate": 1.3280766012869338e-05, + "loss": 0.4845, + "step": 4922 + }, + { + "epoch": 0.41, + "learning_rate": 1.3278205977810492e-05, + "loss": 0.4866, + "step": 4923 + }, + { + "epoch": 0.41, + "learning_rate": 1.3275645702013836e-05, + "loss": 0.4692, + "step": 4924 + }, + { + "epoch": 0.41, + "learning_rate": 1.3273085185667385e-05, + "loss": 0.4743, + "step": 4925 + }, + { + "epoch": 0.41, + "learning_rate": 1.327052442895917e-05, + "loss": 0.4811, + "step": 4926 + }, + { + "epoch": 0.41, + "learning_rate": 1.3267963432077242e-05, + "loss": 0.4902, + "step": 4927 + }, + { + "epoch": 0.41, + "learning_rate": 1.3265402195209675e-05, + "loss": 0.475, + "step": 4928 + }, + { + "epoch": 0.41, + "learning_rate": 1.3262840718544552e-05, + "loss": 0.4967, + "step": 4929 + }, + { + "epoch": 0.41, + "learning_rate": 1.3260279002269977e-05, + "loss": 0.4948, + "step": 4930 + }, + { + "epoch": 0.41, + "learning_rate": 1.3257717046574074e-05, + "loss": 0.467, + "step": 4931 + }, + { + "epoch": 0.41, + "learning_rate": 1.325515485164498e-05, + "loss": 0.4723, + "step": 4932 + }, + { + "epoch": 0.41, + "learning_rate": 1.3252592417670856e-05, + "loss": 0.4997, + "step": 4933 + }, + { + "epoch": 0.41, + "learning_rate": 1.3250029744839867e-05, + "loss": 0.4764, + "step": 4934 + }, + { + "epoch": 0.41, + "learning_rate": 1.3247466833340216e-05, + "loss": 0.492, + "step": 4935 + }, + { + "epoch": 0.41, + "learning_rate": 1.324490368336011e-05, + "loss": 0.4627, + "step": 4936 + }, + { + "epoch": 0.41, + "learning_rate": 1.324234029508777e-05, + "loss": 0.484, + "step": 4937 + }, + { + "epoch": 0.41, + "learning_rate": 1.3239776668711444e-05, + "loss": 0.4789, + "step": 4938 + }, + { + "epoch": 0.41, + "learning_rate": 1.3237212804419398e-05, + "loss": 0.4715, + "step": 4939 + }, + { + "epoch": 0.41, + "learning_rate": 1.3234648702399903e-05, + "loss": 0.4995, + "step": 4940 + }, + { + "epoch": 0.41, + "learning_rate": 1.3232084362841267e-05, + "loss": 0.4747, + "step": 4941 + }, + { + "epoch": 0.41, + "learning_rate": 1.3229519785931795e-05, + "loss": 0.4898, + "step": 4942 + }, + { + "epoch": 0.41, + "learning_rate": 1.3226954971859827e-05, + "loss": 0.5059, + "step": 4943 + }, + { + "epoch": 0.41, + "learning_rate": 1.3224389920813703e-05, + "loss": 0.4816, + "step": 4944 + }, + { + "epoch": 0.41, + "learning_rate": 1.3221824632981797e-05, + "loss": 0.474, + "step": 4945 + }, + { + "epoch": 0.41, + "learning_rate": 1.3219259108552488e-05, + "loss": 0.4707, + "step": 4946 + }, + { + "epoch": 0.41, + "learning_rate": 1.3216693347714183e-05, + "loss": 0.4751, + "step": 4947 + }, + { + "epoch": 0.41, + "learning_rate": 1.3214127350655294e-05, + "loss": 0.4763, + "step": 4948 + }, + { + "epoch": 0.41, + "learning_rate": 1.3211561117564267e-05, + "loss": 0.517, + "step": 4949 + }, + { + "epoch": 0.41, + "learning_rate": 1.3208994648629546e-05, + "loss": 0.4788, + "step": 4950 + }, + { + "epoch": 0.41, + "learning_rate": 1.3206427944039604e-05, + "loss": 0.4886, + "step": 4951 + }, + { + "epoch": 0.41, + "learning_rate": 1.3203861003982933e-05, + "loss": 0.4797, + "step": 4952 + }, + { + "epoch": 0.41, + "learning_rate": 1.3201293828648032e-05, + "loss": 0.4796, + "step": 4953 + }, + { + "epoch": 0.41, + "learning_rate": 1.3198726418223428e-05, + "loss": 0.4591, + "step": 4954 + }, + { + "epoch": 0.41, + "learning_rate": 1.3196158772897663e-05, + "loss": 0.4763, + "step": 4955 + }, + { + "epoch": 0.41, + "learning_rate": 1.3193590892859291e-05, + "loss": 0.4906, + "step": 4956 + }, + { + "epoch": 0.41, + "learning_rate": 1.3191022778296887e-05, + "loss": 0.492, + "step": 4957 + }, + { + "epoch": 0.41, + "learning_rate": 1.318845442939904e-05, + "loss": 0.4808, + "step": 4958 + }, + { + "epoch": 0.41, + "learning_rate": 1.3185885846354365e-05, + "loss": 0.495, + "step": 4959 + }, + { + "epoch": 0.41, + "learning_rate": 1.3183317029351483e-05, + "loss": 0.4769, + "step": 4960 + }, + { + "epoch": 0.42, + "learning_rate": 1.3180747978579039e-05, + "loss": 0.4781, + "step": 4961 + }, + { + "epoch": 0.42, + "learning_rate": 1.3178178694225695e-05, + "loss": 0.4663, + "step": 4962 + }, + { + "epoch": 0.42, + "learning_rate": 1.3175609176480122e-05, + "loss": 0.4681, + "step": 4963 + }, + { + "epoch": 0.42, + "learning_rate": 1.317303942553102e-05, + "loss": 0.4945, + "step": 4964 + }, + { + "epoch": 0.42, + "learning_rate": 1.3170469441567104e-05, + "loss": 0.47, + "step": 4965 + }, + { + "epoch": 0.42, + "learning_rate": 1.3167899224777098e-05, + "loss": 0.4708, + "step": 4966 + }, + { + "epoch": 0.42, + "learning_rate": 1.316532877534975e-05, + "loss": 0.5071, + "step": 4967 + }, + { + "epoch": 0.42, + "learning_rate": 1.316275809347382e-05, + "loss": 0.4788, + "step": 4968 + }, + { + "epoch": 0.42, + "learning_rate": 1.316018717933809e-05, + "loss": 0.4694, + "step": 4969 + }, + { + "epoch": 0.42, + "learning_rate": 1.3157616033131361e-05, + "loss": 0.4749, + "step": 4970 + }, + { + "epoch": 0.42, + "learning_rate": 1.315504465504244e-05, + "loss": 0.4792, + "step": 4971 + }, + { + "epoch": 0.42, + "learning_rate": 1.3152473045260168e-05, + "loss": 0.4936, + "step": 4972 + }, + { + "epoch": 0.42, + "learning_rate": 1.3149901203973383e-05, + "loss": 0.5079, + "step": 4973 + }, + { + "epoch": 0.42, + "learning_rate": 1.3147329131370956e-05, + "loss": 0.4884, + "step": 4974 + }, + { + "epoch": 0.42, + "learning_rate": 1.3144756827641769e-05, + "loss": 0.4967, + "step": 4975 + }, + { + "epoch": 0.42, + "learning_rate": 1.3142184292974723e-05, + "loss": 0.48, + "step": 4976 + }, + { + "epoch": 0.42, + "learning_rate": 1.3139611527558729e-05, + "loss": 0.502, + "step": 4977 + }, + { + "epoch": 0.42, + "learning_rate": 1.3137038531582721e-05, + "loss": 0.4875, + "step": 4978 + }, + { + "epoch": 0.42, + "learning_rate": 1.3134465305235653e-05, + "loss": 0.4827, + "step": 4979 + }, + { + "epoch": 0.42, + "learning_rate": 1.3131891848706492e-05, + "loss": 0.479, + "step": 4980 + }, + { + "epoch": 0.42, + "learning_rate": 1.3129318162184216e-05, + "loss": 0.4702, + "step": 4981 + }, + { + "epoch": 0.42, + "learning_rate": 1.3126744245857835e-05, + "loss": 0.4727, + "step": 4982 + }, + { + "epoch": 0.42, + "learning_rate": 1.312417009991636e-05, + "loss": 0.4882, + "step": 4983 + }, + { + "epoch": 0.42, + "learning_rate": 1.3121595724548825e-05, + "loss": 0.4865, + "step": 4984 + }, + { + "epoch": 0.42, + "learning_rate": 1.3119021119944287e-05, + "loss": 0.4924, + "step": 4985 + }, + { + "epoch": 0.42, + "learning_rate": 1.3116446286291811e-05, + "loss": 0.499, + "step": 4986 + }, + { + "epoch": 0.42, + "learning_rate": 1.3113871223780481e-05, + "loss": 0.4787, + "step": 4987 + }, + { + "epoch": 0.42, + "learning_rate": 1.3111295932599396e-05, + "loss": 0.478, + "step": 4988 + }, + { + "epoch": 0.42, + "learning_rate": 1.3108720412937681e-05, + "loss": 0.4822, + "step": 4989 + }, + { + "epoch": 0.42, + "learning_rate": 1.3106144664984473e-05, + "loss": 0.4804, + "step": 4990 + }, + { + "epoch": 0.42, + "learning_rate": 1.3103568688928917e-05, + "loss": 0.4707, + "step": 4991 + }, + { + "epoch": 0.42, + "learning_rate": 1.3100992484960185e-05, + "loss": 0.4968, + "step": 4992 + }, + { + "epoch": 0.42, + "learning_rate": 1.3098416053267463e-05, + "loss": 0.4693, + "step": 4993 + }, + { + "epoch": 0.42, + "learning_rate": 1.3095839394039953e-05, + "loss": 0.4758, + "step": 4994 + }, + { + "epoch": 0.42, + "learning_rate": 1.3093262507466873e-05, + "loss": 0.5018, + "step": 4995 + }, + { + "epoch": 0.42, + "learning_rate": 1.3090685393737464e-05, + "loss": 0.4784, + "step": 4996 + }, + { + "epoch": 0.42, + "learning_rate": 1.3088108053040974e-05, + "loss": 0.4755, + "step": 4997 + }, + { + "epoch": 0.42, + "learning_rate": 1.308553048556667e-05, + "loss": 0.4867, + "step": 4998 + }, + { + "epoch": 0.42, + "learning_rate": 1.3082952691503843e-05, + "loss": 0.4803, + "step": 4999 + }, + { + "epoch": 0.42, + "learning_rate": 1.3080374671041793e-05, + "loss": 0.4798, + "step": 5000 + }, + { + "epoch": 0.42, + "learning_rate": 1.3077796424369842e-05, + "loss": 0.4852, + "step": 5001 + }, + { + "epoch": 0.42, + "learning_rate": 1.307521795167732e-05, + "loss": 0.4841, + "step": 5002 + }, + { + "epoch": 0.42, + "learning_rate": 1.3072639253153583e-05, + "loss": 0.5082, + "step": 5003 + }, + { + "epoch": 0.42, + "learning_rate": 1.3070060328988e-05, + "loss": 0.4823, + "step": 5004 + }, + { + "epoch": 0.42, + "learning_rate": 1.3067481179369951e-05, + "loss": 0.4915, + "step": 5005 + }, + { + "epoch": 0.42, + "learning_rate": 1.306490180448885e-05, + "loss": 0.5137, + "step": 5006 + }, + { + "epoch": 0.42, + "learning_rate": 1.3062322204534105e-05, + "loss": 0.509, + "step": 5007 + }, + { + "epoch": 0.42, + "learning_rate": 1.3059742379695158e-05, + "loss": 0.4846, + "step": 5008 + }, + { + "epoch": 0.42, + "learning_rate": 1.3057162330161453e-05, + "loss": 0.4945, + "step": 5009 + }, + { + "epoch": 0.42, + "learning_rate": 1.305458205612246e-05, + "loss": 0.4883, + "step": 5010 + }, + { + "epoch": 0.42, + "learning_rate": 1.3052001557767671e-05, + "loss": 0.4953, + "step": 5011 + }, + { + "epoch": 0.42, + "learning_rate": 1.304942083528658e-05, + "loss": 0.5003, + "step": 5012 + }, + { + "epoch": 0.42, + "learning_rate": 1.3046839888868706e-05, + "loss": 0.4656, + "step": 5013 + }, + { + "epoch": 0.42, + "learning_rate": 1.3044258718703581e-05, + "loss": 0.492, + "step": 5014 + }, + { + "epoch": 0.42, + "learning_rate": 1.304167732498076e-05, + "loss": 0.4865, + "step": 5015 + }, + { + "epoch": 0.42, + "learning_rate": 1.3039095707889808e-05, + "loss": 0.486, + "step": 5016 + }, + { + "epoch": 0.42, + "learning_rate": 1.3036513867620309e-05, + "loss": 0.4977, + "step": 5017 + }, + { + "epoch": 0.42, + "learning_rate": 1.303393180436186e-05, + "loss": 0.4894, + "step": 5018 + }, + { + "epoch": 0.42, + "learning_rate": 1.3031349518304078e-05, + "loss": 0.4717, + "step": 5019 + }, + { + "epoch": 0.42, + "learning_rate": 1.3028767009636593e-05, + "loss": 0.5052, + "step": 5020 + }, + { + "epoch": 0.42, + "learning_rate": 1.3026184278549062e-05, + "loss": 0.4768, + "step": 5021 + }, + { + "epoch": 0.42, + "learning_rate": 1.302360132523114e-05, + "loss": 0.4759, + "step": 5022 + }, + { + "epoch": 0.42, + "learning_rate": 1.3021018149872516e-05, + "loss": 0.4861, + "step": 5023 + }, + { + "epoch": 0.42, + "learning_rate": 1.3018434752662882e-05, + "loss": 0.5004, + "step": 5024 + }, + { + "epoch": 0.42, + "learning_rate": 1.3015851133791955e-05, + "loss": 0.4867, + "step": 5025 + }, + { + "epoch": 0.42, + "learning_rate": 1.3013267293449463e-05, + "loss": 0.4708, + "step": 5026 + }, + { + "epoch": 0.42, + "learning_rate": 1.3010683231825158e-05, + "loss": 0.4981, + "step": 5027 + }, + { + "epoch": 0.42, + "learning_rate": 1.30080989491088e-05, + "loss": 0.4881, + "step": 5028 + }, + { + "epoch": 0.42, + "learning_rate": 1.300551444549016e-05, + "loss": 0.4787, + "step": 5029 + }, + { + "epoch": 0.42, + "learning_rate": 1.3002929721159043e-05, + "loss": 0.504, + "step": 5030 + }, + { + "epoch": 0.42, + "learning_rate": 1.3000344776305258e-05, + "loss": 0.511, + "step": 5031 + }, + { + "epoch": 0.42, + "learning_rate": 1.2997759611118634e-05, + "loss": 0.4751, + "step": 5032 + }, + { + "epoch": 0.42, + "learning_rate": 1.2995174225789008e-05, + "loss": 0.5148, + "step": 5033 + }, + { + "epoch": 0.42, + "learning_rate": 1.2992588620506251e-05, + "loss": 0.5013, + "step": 5034 + }, + { + "epoch": 0.42, + "learning_rate": 1.2990002795460228e-05, + "loss": 0.4959, + "step": 5035 + }, + { + "epoch": 0.42, + "learning_rate": 1.2987416750840836e-05, + "loss": 0.4788, + "step": 5036 + }, + { + "epoch": 0.42, + "learning_rate": 1.2984830486837985e-05, + "loss": 0.4932, + "step": 5037 + }, + { + "epoch": 0.42, + "learning_rate": 1.2982244003641599e-05, + "loss": 0.487, + "step": 5038 + }, + { + "epoch": 0.42, + "learning_rate": 1.2979657301441615e-05, + "loss": 0.4873, + "step": 5039 + }, + { + "epoch": 0.42, + "learning_rate": 1.2977070380427993e-05, + "loss": 0.4762, + "step": 5040 + }, + { + "epoch": 0.42, + "learning_rate": 1.2974483240790705e-05, + "loss": 0.4804, + "step": 5041 + }, + { + "epoch": 0.42, + "learning_rate": 1.2971895882719741e-05, + "loss": 0.4935, + "step": 5042 + }, + { + "epoch": 0.42, + "learning_rate": 1.2969308306405102e-05, + "loss": 0.4742, + "step": 5043 + }, + { + "epoch": 0.42, + "learning_rate": 1.2966720512036813e-05, + "loss": 0.5088, + "step": 5044 + }, + { + "epoch": 0.42, + "learning_rate": 1.2964132499804907e-05, + "loss": 0.4828, + "step": 5045 + }, + { + "epoch": 0.42, + "learning_rate": 1.296154426989944e-05, + "loss": 0.4859, + "step": 5046 + }, + { + "epoch": 0.42, + "learning_rate": 1.2958955822510482e-05, + "loss": 0.4948, + "step": 5047 + }, + { + "epoch": 0.42, + "learning_rate": 1.2956367157828113e-05, + "loss": 0.4609, + "step": 5048 + }, + { + "epoch": 0.42, + "learning_rate": 1.295377827604244e-05, + "loss": 0.5, + "step": 5049 + }, + { + "epoch": 0.42, + "learning_rate": 1.295118917734357e-05, + "loss": 0.4859, + "step": 5050 + }, + { + "epoch": 0.42, + "learning_rate": 1.2948599861921644e-05, + "loss": 0.4748, + "step": 5051 + }, + { + "epoch": 0.42, + "learning_rate": 1.2946010329966811e-05, + "loss": 0.4679, + "step": 5052 + }, + { + "epoch": 0.42, + "learning_rate": 1.2943420581669231e-05, + "loss": 0.4995, + "step": 5053 + }, + { + "epoch": 0.42, + "learning_rate": 1.2940830617219087e-05, + "loss": 0.5, + "step": 5054 + }, + { + "epoch": 0.42, + "learning_rate": 1.2938240436806575e-05, + "loss": 0.4732, + "step": 5055 + }, + { + "epoch": 0.42, + "learning_rate": 1.2935650040621901e-05, + "loss": 0.4839, + "step": 5056 + }, + { + "epoch": 0.42, + "learning_rate": 1.2933059428855303e-05, + "loss": 0.4713, + "step": 5057 + }, + { + "epoch": 0.42, + "learning_rate": 1.2930468601697022e-05, + "loss": 0.4795, + "step": 5058 + }, + { + "epoch": 0.42, + "learning_rate": 1.2927877559337311e-05, + "loss": 0.4778, + "step": 5059 + }, + { + "epoch": 0.42, + "learning_rate": 1.2925286301966451e-05, + "loss": 0.4813, + "step": 5060 + }, + { + "epoch": 0.42, + "learning_rate": 1.2922694829774733e-05, + "loss": 0.5003, + "step": 5061 + }, + { + "epoch": 0.42, + "learning_rate": 1.2920103142952465e-05, + "loss": 0.4835, + "step": 5062 + }, + { + "epoch": 0.42, + "learning_rate": 1.2917511241689963e-05, + "loss": 0.4714, + "step": 5063 + }, + { + "epoch": 0.42, + "learning_rate": 1.2914919126177576e-05, + "loss": 0.5055, + "step": 5064 + }, + { + "epoch": 0.42, + "learning_rate": 1.291232679660565e-05, + "loss": 0.4942, + "step": 5065 + }, + { + "epoch": 0.42, + "learning_rate": 1.2909734253164557e-05, + "loss": 0.4614, + "step": 5066 + }, + { + "epoch": 0.42, + "learning_rate": 1.2907141496044679e-05, + "loss": 0.4689, + "step": 5067 + }, + { + "epoch": 0.42, + "learning_rate": 1.2904548525436429e-05, + "loss": 0.4843, + "step": 5068 + }, + { + "epoch": 0.42, + "learning_rate": 1.2901955341530213e-05, + "loss": 0.472, + "step": 5069 + }, + { + "epoch": 0.42, + "learning_rate": 1.2899361944516464e-05, + "loss": 0.489, + "step": 5070 + }, + { + "epoch": 0.42, + "learning_rate": 1.2896768334585635e-05, + "loss": 0.5033, + "step": 5071 + }, + { + "epoch": 0.42, + "learning_rate": 1.2894174511928189e-05, + "loss": 0.4797, + "step": 5072 + }, + { + "epoch": 0.42, + "learning_rate": 1.2891580476734602e-05, + "loss": 0.4992, + "step": 5073 + }, + { + "epoch": 0.42, + "learning_rate": 1.2888986229195375e-05, + "loss": 0.4896, + "step": 5074 + }, + { + "epoch": 0.42, + "learning_rate": 1.2886391769501016e-05, + "loss": 0.4872, + "step": 5075 + }, + { + "epoch": 0.42, + "learning_rate": 1.2883797097842048e-05, + "loss": 0.4663, + "step": 5076 + }, + { + "epoch": 0.42, + "learning_rate": 1.2881202214409016e-05, + "loss": 0.4954, + "step": 5077 + }, + { + "epoch": 0.42, + "learning_rate": 1.2878607119392479e-05, + "loss": 0.5041, + "step": 5078 + }, + { + "epoch": 0.42, + "learning_rate": 1.2876011812983009e-05, + "loss": 0.4777, + "step": 5079 + }, + { + "epoch": 0.43, + "learning_rate": 1.287341629537119e-05, + "loss": 0.5026, + "step": 5080 + }, + { + "epoch": 0.43, + "learning_rate": 1.2870820566747633e-05, + "loss": 0.471, + "step": 5081 + }, + { + "epoch": 0.43, + "learning_rate": 1.2868224627302952e-05, + "loss": 0.4873, + "step": 5082 + }, + { + "epoch": 0.43, + "learning_rate": 1.2865628477227787e-05, + "loss": 0.488, + "step": 5083 + }, + { + "epoch": 0.43, + "learning_rate": 1.2863032116712781e-05, + "loss": 0.4907, + "step": 5084 + }, + { + "epoch": 0.43, + "learning_rate": 1.2860435545948609e-05, + "loss": 0.4816, + "step": 5085 + }, + { + "epoch": 0.43, + "learning_rate": 1.2857838765125945e-05, + "loss": 0.4917, + "step": 5086 + }, + { + "epoch": 0.43, + "learning_rate": 1.285524177443549e-05, + "loss": 0.4916, + "step": 5087 + }, + { + "epoch": 0.43, + "learning_rate": 1.2852644574067955e-05, + "loss": 0.4771, + "step": 5088 + }, + { + "epoch": 0.43, + "learning_rate": 1.285004716421407e-05, + "loss": 0.4911, + "step": 5089 + }, + { + "epoch": 0.43, + "learning_rate": 1.2847449545064572e-05, + "loss": 0.4913, + "step": 5090 + }, + { + "epoch": 0.43, + "learning_rate": 1.2844851716810225e-05, + "loss": 0.4803, + "step": 5091 + }, + { + "epoch": 0.43, + "learning_rate": 1.2842253679641799e-05, + "loss": 0.4891, + "step": 5092 + }, + { + "epoch": 0.43, + "learning_rate": 1.2839655433750084e-05, + "loss": 0.4777, + "step": 5093 + }, + { + "epoch": 0.43, + "learning_rate": 1.2837056979325886e-05, + "loss": 0.4791, + "step": 5094 + }, + { + "epoch": 0.43, + "learning_rate": 1.2834458316560023e-05, + "loss": 0.4653, + "step": 5095 + }, + { + "epoch": 0.43, + "learning_rate": 1.2831859445643333e-05, + "loss": 0.4935, + "step": 5096 + }, + { + "epoch": 0.43, + "learning_rate": 1.282926036676666e-05, + "loss": 0.5006, + "step": 5097 + }, + { + "epoch": 0.43, + "learning_rate": 1.2826661080120877e-05, + "loss": 0.463, + "step": 5098 + }, + { + "epoch": 0.43, + "learning_rate": 1.282406158589686e-05, + "loss": 0.4902, + "step": 5099 + }, + { + "epoch": 0.43, + "learning_rate": 1.2821461884285506e-05, + "loss": 0.4759, + "step": 5100 + }, + { + "epoch": 0.43, + "learning_rate": 1.2818861975477728e-05, + "loss": 0.4796, + "step": 5101 + }, + { + "epoch": 0.43, + "learning_rate": 1.2816261859664448e-05, + "loss": 0.4833, + "step": 5102 + }, + { + "epoch": 0.43, + "learning_rate": 1.2813661537036613e-05, + "loss": 0.4863, + "step": 5103 + }, + { + "epoch": 0.43, + "learning_rate": 1.2811061007785175e-05, + "loss": 0.4719, + "step": 5104 + }, + { + "epoch": 0.43, + "learning_rate": 1.2808460272101113e-05, + "loss": 0.4843, + "step": 5105 + }, + { + "epoch": 0.43, + "learning_rate": 1.280585933017541e-05, + "loss": 0.4763, + "step": 5106 + }, + { + "epoch": 0.43, + "learning_rate": 1.2803258182199064e-05, + "loss": 0.4812, + "step": 5107 + }, + { + "epoch": 0.43, + "learning_rate": 1.2800656828363098e-05, + "loss": 0.4878, + "step": 5108 + }, + { + "epoch": 0.43, + "learning_rate": 1.2798055268858544e-05, + "loss": 0.4949, + "step": 5109 + }, + { + "epoch": 0.43, + "learning_rate": 1.2795453503876449e-05, + "loss": 0.5089, + "step": 5110 + }, + { + "epoch": 0.43, + "learning_rate": 1.2792851533607875e-05, + "loss": 0.482, + "step": 5111 + }, + { + "epoch": 0.43, + "learning_rate": 1.2790249358243902e-05, + "loss": 0.5057, + "step": 5112 + }, + { + "epoch": 0.43, + "learning_rate": 1.2787646977975623e-05, + "loss": 0.5177, + "step": 5113 + }, + { + "epoch": 0.43, + "learning_rate": 1.2785044392994142e-05, + "loss": 0.461, + "step": 5114 + }, + { + "epoch": 0.43, + "learning_rate": 1.2782441603490585e-05, + "loss": 0.479, + "step": 5115 + }, + { + "epoch": 0.43, + "learning_rate": 1.277983860965609e-05, + "loss": 0.5029, + "step": 5116 + }, + { + "epoch": 0.43, + "learning_rate": 1.277723541168181e-05, + "loss": 0.475, + "step": 5117 + }, + { + "epoch": 0.43, + "learning_rate": 1.2774632009758911e-05, + "loss": 0.4754, + "step": 5118 + }, + { + "epoch": 0.43, + "learning_rate": 1.2772028404078581e-05, + "loss": 0.483, + "step": 5119 + }, + { + "epoch": 0.43, + "learning_rate": 1.2769424594832014e-05, + "loss": 0.4806, + "step": 5120 + }, + { + "epoch": 0.43, + "learning_rate": 1.2766820582210421e-05, + "loss": 0.4651, + "step": 5121 + }, + { + "epoch": 0.43, + "learning_rate": 1.2764216366405036e-05, + "loss": 0.4875, + "step": 5122 + }, + { + "epoch": 0.43, + "learning_rate": 1.2761611947607095e-05, + "loss": 0.4948, + "step": 5123 + }, + { + "epoch": 0.43, + "learning_rate": 1.2759007326007862e-05, + "loss": 0.4835, + "step": 5124 + }, + { + "epoch": 0.43, + "learning_rate": 1.2756402501798606e-05, + "loss": 0.4828, + "step": 5125 + }, + { + "epoch": 0.43, + "learning_rate": 1.2753797475170613e-05, + "loss": 0.4781, + "step": 5126 + }, + { + "epoch": 0.43, + "learning_rate": 1.275119224631519e-05, + "loss": 0.4875, + "step": 5127 + }, + { + "epoch": 0.43, + "learning_rate": 1.2748586815423646e-05, + "loss": 0.4688, + "step": 5128 + }, + { + "epoch": 0.43, + "learning_rate": 1.2745981182687323e-05, + "loss": 0.479, + "step": 5129 + }, + { + "epoch": 0.43, + "learning_rate": 1.2743375348297567e-05, + "loss": 0.4941, + "step": 5130 + }, + { + "epoch": 0.43, + "learning_rate": 1.274076931244573e-05, + "loss": 0.5048, + "step": 5131 + }, + { + "epoch": 0.43, + "learning_rate": 1.2738163075323198e-05, + "loss": 0.4627, + "step": 5132 + }, + { + "epoch": 0.43, + "learning_rate": 1.2735556637121356e-05, + "loss": 0.4784, + "step": 5133 + }, + { + "epoch": 0.43, + "learning_rate": 1.2732949998031612e-05, + "loss": 0.4883, + "step": 5134 + }, + { + "epoch": 0.43, + "learning_rate": 1.2730343158245389e-05, + "loss": 0.4992, + "step": 5135 + }, + { + "epoch": 0.43, + "learning_rate": 1.2727736117954122e-05, + "loss": 0.4715, + "step": 5136 + }, + { + "epoch": 0.43, + "learning_rate": 1.272512887734926e-05, + "loss": 0.4769, + "step": 5137 + }, + { + "epoch": 0.43, + "learning_rate": 1.2722521436622263e-05, + "loss": 0.5004, + "step": 5138 + }, + { + "epoch": 0.43, + "learning_rate": 1.2719913795964618e-05, + "loss": 0.4909, + "step": 5139 + }, + { + "epoch": 0.43, + "learning_rate": 1.271730595556782e-05, + "loss": 0.4747, + "step": 5140 + }, + { + "epoch": 0.43, + "learning_rate": 1.2714697915623374e-05, + "loss": 0.4969, + "step": 5141 + }, + { + "epoch": 0.43, + "learning_rate": 1.2712089676322803e-05, + "loss": 0.479, + "step": 5142 + }, + { + "epoch": 0.43, + "learning_rate": 1.2709481237857643e-05, + "loss": 0.4771, + "step": 5143 + }, + { + "epoch": 0.43, + "learning_rate": 1.2706872600419456e-05, + "loss": 0.5098, + "step": 5144 + }, + { + "epoch": 0.43, + "learning_rate": 1.2704263764199803e-05, + "loss": 0.4819, + "step": 5145 + }, + { + "epoch": 0.43, + "learning_rate": 1.2701654729390264e-05, + "loss": 0.4838, + "step": 5146 + }, + { + "epoch": 0.43, + "learning_rate": 1.2699045496182442e-05, + "loss": 0.4829, + "step": 5147 + }, + { + "epoch": 0.43, + "learning_rate": 1.2696436064767943e-05, + "loss": 0.4952, + "step": 5148 + }, + { + "epoch": 0.43, + "learning_rate": 1.2693826435338394e-05, + "loss": 0.4854, + "step": 5149 + }, + { + "epoch": 0.43, + "learning_rate": 1.269121660808544e-05, + "loss": 0.483, + "step": 5150 + }, + { + "epoch": 0.43, + "learning_rate": 1.2688606583200728e-05, + "loss": 0.4843, + "step": 5151 + }, + { + "epoch": 0.43, + "learning_rate": 1.2685996360875933e-05, + "loss": 0.4863, + "step": 5152 + }, + { + "epoch": 0.43, + "learning_rate": 1.2683385941302737e-05, + "loss": 0.4922, + "step": 5153 + }, + { + "epoch": 0.43, + "learning_rate": 1.2680775324672839e-05, + "loss": 0.4687, + "step": 5154 + }, + { + "epoch": 0.43, + "learning_rate": 1.2678164511177948e-05, + "loss": 0.494, + "step": 5155 + }, + { + "epoch": 0.43, + "learning_rate": 1.26755535010098e-05, + "loss": 0.4872, + "step": 5156 + }, + { + "epoch": 0.43, + "learning_rate": 1.267294229436013e-05, + "loss": 0.4892, + "step": 5157 + }, + { + "epoch": 0.43, + "learning_rate": 1.2670330891420694e-05, + "loss": 0.4867, + "step": 5158 + }, + { + "epoch": 0.43, + "learning_rate": 1.266771929238326e-05, + "loss": 0.4676, + "step": 5159 + }, + { + "epoch": 0.43, + "learning_rate": 1.2665107497439623e-05, + "loss": 0.4976, + "step": 5160 + }, + { + "epoch": 0.43, + "learning_rate": 1.2662495506781575e-05, + "loss": 0.4855, + "step": 5161 + }, + { + "epoch": 0.43, + "learning_rate": 1.265988332060093e-05, + "loss": 0.4878, + "step": 5162 + }, + { + "epoch": 0.43, + "learning_rate": 1.265727093908952e-05, + "loss": 0.4841, + "step": 5163 + }, + { + "epoch": 0.43, + "learning_rate": 1.265465836243918e-05, + "loss": 0.4876, + "step": 5164 + }, + { + "epoch": 0.43, + "learning_rate": 1.2652045590841774e-05, + "loss": 0.4905, + "step": 5165 + }, + { + "epoch": 0.43, + "learning_rate": 1.2649432624489171e-05, + "loss": 0.4761, + "step": 5166 + }, + { + "epoch": 0.43, + "learning_rate": 1.2646819463573257e-05, + "loss": 0.4716, + "step": 5167 + }, + { + "epoch": 0.43, + "learning_rate": 1.264420610828593e-05, + "loss": 0.4791, + "step": 5168 + }, + { + "epoch": 0.43, + "learning_rate": 1.2641592558819102e-05, + "loss": 0.4844, + "step": 5169 + }, + { + "epoch": 0.43, + "learning_rate": 1.2638978815364705e-05, + "loss": 0.4864, + "step": 5170 + }, + { + "epoch": 0.43, + "learning_rate": 1.2636364878114682e-05, + "loss": 0.4723, + "step": 5171 + }, + { + "epoch": 0.43, + "learning_rate": 1.2633750747260985e-05, + "loss": 0.4821, + "step": 5172 + }, + { + "epoch": 0.43, + "learning_rate": 1.263113642299559e-05, + "loss": 0.4819, + "step": 5173 + }, + { + "epoch": 0.43, + "learning_rate": 1.2628521905510476e-05, + "loss": 0.4784, + "step": 5174 + }, + { + "epoch": 0.43, + "learning_rate": 1.2625907194997652e-05, + "loss": 0.4812, + "step": 5175 + }, + { + "epoch": 0.43, + "learning_rate": 1.2623292291649119e-05, + "loss": 0.4735, + "step": 5176 + }, + { + "epoch": 0.43, + "learning_rate": 1.2620677195656916e-05, + "loss": 0.4846, + "step": 5177 + }, + { + "epoch": 0.43, + "learning_rate": 1.261806190721308e-05, + "loss": 0.5012, + "step": 5178 + }, + { + "epoch": 0.43, + "learning_rate": 1.2615446426509663e-05, + "loss": 0.5073, + "step": 5179 + }, + { + "epoch": 0.43, + "learning_rate": 1.261283075373874e-05, + "loss": 0.4963, + "step": 5180 + }, + { + "epoch": 0.43, + "learning_rate": 1.2610214889092399e-05, + "loss": 0.4903, + "step": 5181 + }, + { + "epoch": 0.43, + "learning_rate": 1.2607598832762728e-05, + "loss": 0.485, + "step": 5182 + }, + { + "epoch": 0.43, + "learning_rate": 1.2604982584941846e-05, + "loss": 0.4773, + "step": 5183 + }, + { + "epoch": 0.43, + "learning_rate": 1.2602366145821879e-05, + "loss": 0.4819, + "step": 5184 + }, + { + "epoch": 0.43, + "learning_rate": 1.2599749515594964e-05, + "loss": 0.4781, + "step": 5185 + }, + { + "epoch": 0.43, + "learning_rate": 1.2597132694453258e-05, + "loss": 0.4648, + "step": 5186 + }, + { + "epoch": 0.43, + "learning_rate": 1.259451568258893e-05, + "loss": 0.4819, + "step": 5187 + }, + { + "epoch": 0.43, + "learning_rate": 1.2591898480194165e-05, + "loss": 0.5044, + "step": 5188 + }, + { + "epoch": 0.43, + "learning_rate": 1.2589281087461152e-05, + "loss": 0.4943, + "step": 5189 + }, + { + "epoch": 0.43, + "learning_rate": 1.2586663504582104e-05, + "loss": 0.4827, + "step": 5190 + }, + { + "epoch": 0.43, + "learning_rate": 1.258404573174925e-05, + "loss": 0.4828, + "step": 5191 + }, + { + "epoch": 0.43, + "learning_rate": 1.2581427769154826e-05, + "loss": 0.4685, + "step": 5192 + }, + { + "epoch": 0.43, + "learning_rate": 1.2578809616991081e-05, + "loss": 0.4819, + "step": 5193 + }, + { + "epoch": 0.43, + "learning_rate": 1.2576191275450287e-05, + "loss": 0.4996, + "step": 5194 + }, + { + "epoch": 0.43, + "learning_rate": 1.2573572744724718e-05, + "loss": 0.4831, + "step": 5195 + }, + { + "epoch": 0.43, + "learning_rate": 1.2570954025006672e-05, + "loss": 0.499, + "step": 5196 + }, + { + "epoch": 0.43, + "learning_rate": 1.2568335116488457e-05, + "loss": 0.4894, + "step": 5197 + }, + { + "epoch": 0.43, + "learning_rate": 1.2565716019362393e-05, + "loss": 0.4802, + "step": 5198 + }, + { + "epoch": 0.43, + "learning_rate": 1.2563096733820816e-05, + "loss": 0.479, + "step": 5199 + }, + { + "epoch": 0.44, + "learning_rate": 1.2560477260056072e-05, + "loss": 0.4739, + "step": 5200 + }, + { + "epoch": 0.44, + "learning_rate": 1.2557857598260532e-05, + "loss": 0.4864, + "step": 5201 + }, + { + "epoch": 0.44, + "learning_rate": 1.255523774862657e-05, + "loss": 0.4791, + "step": 5202 + }, + { + "epoch": 0.44, + "learning_rate": 1.2552617711346572e-05, + "loss": 0.4939, + "step": 5203 + }, + { + "epoch": 0.44, + "learning_rate": 1.254999748661295e-05, + "loss": 0.4796, + "step": 5204 + }, + { + "epoch": 0.44, + "learning_rate": 1.2547377074618114e-05, + "loss": 0.4678, + "step": 5205 + }, + { + "epoch": 0.44, + "learning_rate": 1.2544756475554505e-05, + "loss": 0.4995, + "step": 5206 + }, + { + "epoch": 0.44, + "learning_rate": 1.2542135689614565e-05, + "loss": 0.483, + "step": 5207 + }, + { + "epoch": 0.44, + "learning_rate": 1.2539514716990753e-05, + "loss": 0.4679, + "step": 5208 + }, + { + "epoch": 0.44, + "learning_rate": 1.2536893557875543e-05, + "loss": 0.4865, + "step": 5209 + }, + { + "epoch": 0.44, + "learning_rate": 1.253427221246142e-05, + "loss": 0.4795, + "step": 5210 + }, + { + "epoch": 0.44, + "learning_rate": 1.2531650680940888e-05, + "loss": 0.4777, + "step": 5211 + }, + { + "epoch": 0.44, + "learning_rate": 1.252902896350646e-05, + "loss": 0.4953, + "step": 5212 + }, + { + "epoch": 0.44, + "learning_rate": 1.252640706035066e-05, + "loss": 0.5058, + "step": 5213 + }, + { + "epoch": 0.44, + "learning_rate": 1.2523784971666039e-05, + "loss": 0.4991, + "step": 5214 + }, + { + "epoch": 0.44, + "learning_rate": 1.2521162697645144e-05, + "loss": 0.4984, + "step": 5215 + }, + { + "epoch": 0.44, + "learning_rate": 1.251854023848055e-05, + "loss": 0.4979, + "step": 5216 + }, + { + "epoch": 0.44, + "learning_rate": 1.251591759436483e-05, + "loss": 0.4866, + "step": 5217 + }, + { + "epoch": 0.44, + "learning_rate": 1.2513294765490593e-05, + "loss": 0.4815, + "step": 5218 + }, + { + "epoch": 0.44, + "learning_rate": 1.2510671752050441e-05, + "loss": 0.4922, + "step": 5219 + }, + { + "epoch": 0.44, + "learning_rate": 1.2508048554236996e-05, + "loss": 0.4619, + "step": 5220 + }, + { + "epoch": 0.44, + "learning_rate": 1.2505425172242895e-05, + "loss": 0.4701, + "step": 5221 + }, + { + "epoch": 0.44, + "learning_rate": 1.2502801606260792e-05, + "loss": 0.4784, + "step": 5222 + }, + { + "epoch": 0.44, + "learning_rate": 1.2500177856483351e-05, + "loss": 0.4772, + "step": 5223 + }, + { + "epoch": 0.44, + "learning_rate": 1.2497553923103247e-05, + "loss": 0.4912, + "step": 5224 + }, + { + "epoch": 0.44, + "learning_rate": 1.249492980631317e-05, + "loss": 0.4981, + "step": 5225 + }, + { + "epoch": 0.44, + "learning_rate": 1.2492305506305824e-05, + "loss": 0.4649, + "step": 5226 + }, + { + "epoch": 0.44, + "learning_rate": 1.2489681023273927e-05, + "loss": 0.4915, + "step": 5227 + }, + { + "epoch": 0.44, + "learning_rate": 1.2487056357410215e-05, + "loss": 0.4691, + "step": 5228 + }, + { + "epoch": 0.44, + "learning_rate": 1.2484431508907429e-05, + "loss": 0.4756, + "step": 5229 + }, + { + "epoch": 0.44, + "learning_rate": 1.2481806477958323e-05, + "loss": 0.4938, + "step": 5230 + }, + { + "epoch": 0.44, + "learning_rate": 1.247918126475567e-05, + "loss": 0.4832, + "step": 5231 + }, + { + "epoch": 0.44, + "learning_rate": 1.2476555869492262e-05, + "loss": 0.4856, + "step": 5232 + }, + { + "epoch": 0.44, + "learning_rate": 1.2473930292360889e-05, + "loss": 0.4804, + "step": 5233 + }, + { + "epoch": 0.44, + "learning_rate": 1.2471304533554364e-05, + "loss": 0.5037, + "step": 5234 + }, + { + "epoch": 0.44, + "learning_rate": 1.2468678593265518e-05, + "loss": 0.4744, + "step": 5235 + }, + { + "epoch": 0.44, + "learning_rate": 1.2466052471687178e-05, + "loss": 0.4723, + "step": 5236 + }, + { + "epoch": 0.44, + "learning_rate": 1.2463426169012204e-05, + "loss": 0.4755, + "step": 5237 + }, + { + "epoch": 0.44, + "learning_rate": 1.2460799685433457e-05, + "loss": 0.4816, + "step": 5238 + }, + { + "epoch": 0.44, + "learning_rate": 1.245817302114382e-05, + "loss": 0.4794, + "step": 5239 + }, + { + "epoch": 0.44, + "learning_rate": 1.2455546176336177e-05, + "loss": 0.4817, + "step": 5240 + }, + { + "epoch": 0.44, + "learning_rate": 1.2452919151203439e-05, + "loss": 0.5024, + "step": 5241 + }, + { + "epoch": 0.44, + "learning_rate": 1.245029194593852e-05, + "loss": 0.4645, + "step": 5242 + }, + { + "epoch": 0.44, + "learning_rate": 1.2447664560734352e-05, + "loss": 0.4934, + "step": 5243 + }, + { + "epoch": 0.44, + "learning_rate": 1.2445036995783876e-05, + "loss": 0.4699, + "step": 5244 + }, + { + "epoch": 0.44, + "learning_rate": 1.2442409251280058e-05, + "loss": 0.4868, + "step": 5245 + }, + { + "epoch": 0.44, + "learning_rate": 1.2439781327415858e-05, + "loss": 0.4947, + "step": 5246 + }, + { + "epoch": 0.44, + "learning_rate": 1.2437153224384269e-05, + "loss": 0.4851, + "step": 5247 + }, + { + "epoch": 0.44, + "learning_rate": 1.2434524942378283e-05, + "loss": 0.5058, + "step": 5248 + }, + { + "epoch": 0.44, + "learning_rate": 1.2431896481590912e-05, + "loss": 0.4728, + "step": 5249 + }, + { + "epoch": 0.44, + "learning_rate": 1.2429267842215181e-05, + "loss": 0.4873, + "step": 5250 + }, + { + "epoch": 0.44, + "learning_rate": 1.2426639024444118e-05, + "loss": 0.4701, + "step": 5251 + }, + { + "epoch": 0.44, + "learning_rate": 1.2424010028470779e-05, + "loss": 0.4963, + "step": 5252 + }, + { + "epoch": 0.44, + "learning_rate": 1.242138085448823e-05, + "loss": 0.501, + "step": 5253 + }, + { + "epoch": 0.44, + "learning_rate": 1.2418751502689537e-05, + "loss": 0.4718, + "step": 5254 + }, + { + "epoch": 0.44, + "learning_rate": 1.24161219732678e-05, + "loss": 0.5091, + "step": 5255 + }, + { + "epoch": 0.44, + "learning_rate": 1.241349226641611e-05, + "loss": 0.493, + "step": 5256 + }, + { + "epoch": 0.44, + "learning_rate": 1.2410862382327587e-05, + "loss": 0.4905, + "step": 5257 + }, + { + "epoch": 0.44, + "learning_rate": 1.240823232119536e-05, + "loss": 0.4691, + "step": 5258 + }, + { + "epoch": 0.44, + "learning_rate": 1.2405602083212567e-05, + "loss": 0.4941, + "step": 5259 + }, + { + "epoch": 0.44, + "learning_rate": 1.2402971668572364e-05, + "loss": 0.4871, + "step": 5260 + }, + { + "epoch": 0.44, + "learning_rate": 1.2400341077467912e-05, + "loss": 0.4755, + "step": 5261 + }, + { + "epoch": 0.44, + "learning_rate": 1.2397710310092396e-05, + "loss": 0.4886, + "step": 5262 + }, + { + "epoch": 0.44, + "learning_rate": 1.2395079366639011e-05, + "loss": 0.5008, + "step": 5263 + }, + { + "epoch": 0.44, + "learning_rate": 1.2392448247300959e-05, + "loss": 0.4723, + "step": 5264 + }, + { + "epoch": 0.44, + "learning_rate": 1.2389816952271456e-05, + "loss": 0.4819, + "step": 5265 + }, + { + "epoch": 0.44, + "learning_rate": 1.238718548174374e-05, + "loss": 0.4801, + "step": 5266 + }, + { + "epoch": 0.44, + "learning_rate": 1.2384553835911049e-05, + "loss": 0.5106, + "step": 5267 + }, + { + "epoch": 0.44, + "learning_rate": 1.2381922014966641e-05, + "loss": 0.5061, + "step": 5268 + }, + { + "epoch": 0.44, + "learning_rate": 1.237929001910379e-05, + "loss": 0.4961, + "step": 5269 + }, + { + "epoch": 0.44, + "learning_rate": 1.2376657848515774e-05, + "loss": 0.4996, + "step": 5270 + }, + { + "epoch": 0.44, + "learning_rate": 1.237402550339589e-05, + "loss": 0.4873, + "step": 5271 + }, + { + "epoch": 0.44, + "learning_rate": 1.2371392983937449e-05, + "loss": 0.4964, + "step": 5272 + }, + { + "epoch": 0.44, + "learning_rate": 1.2368760290333771e-05, + "loss": 0.493, + "step": 5273 + }, + { + "epoch": 0.44, + "learning_rate": 1.2366127422778192e-05, + "loss": 0.4932, + "step": 5274 + }, + { + "epoch": 0.44, + "learning_rate": 1.2363494381464052e-05, + "loss": 0.4952, + "step": 5275 + }, + { + "epoch": 0.44, + "learning_rate": 1.2360861166584717e-05, + "loss": 0.4878, + "step": 5276 + }, + { + "epoch": 0.44, + "learning_rate": 1.2358227778333556e-05, + "loss": 0.4842, + "step": 5277 + }, + { + "epoch": 0.44, + "learning_rate": 1.2355594216903956e-05, + "loss": 0.4739, + "step": 5278 + }, + { + "epoch": 0.44, + "learning_rate": 1.2352960482489317e-05, + "loss": 0.4898, + "step": 5279 + }, + { + "epoch": 0.44, + "learning_rate": 1.2350326575283047e-05, + "loss": 0.45, + "step": 5280 + }, + { + "epoch": 0.44, + "learning_rate": 1.2347692495478565e-05, + "loss": 0.4845, + "step": 5281 + }, + { + "epoch": 0.44, + "learning_rate": 1.2345058243269314e-05, + "loss": 0.4905, + "step": 5282 + }, + { + "epoch": 0.44, + "learning_rate": 1.234242381884874e-05, + "loss": 0.4936, + "step": 5283 + }, + { + "epoch": 0.44, + "learning_rate": 1.2339789222410301e-05, + "loss": 0.4803, + "step": 5284 + }, + { + "epoch": 0.44, + "learning_rate": 1.2337154454147476e-05, + "loss": 0.4985, + "step": 5285 + }, + { + "epoch": 0.44, + "learning_rate": 1.2334519514253747e-05, + "loss": 0.4824, + "step": 5286 + }, + { + "epoch": 0.44, + "learning_rate": 1.2331884402922613e-05, + "loss": 0.4794, + "step": 5287 + }, + { + "epoch": 0.44, + "learning_rate": 1.2329249120347591e-05, + "loss": 0.4644, + "step": 5288 + }, + { + "epoch": 0.44, + "learning_rate": 1.23266136667222e-05, + "loss": 0.4718, + "step": 5289 + }, + { + "epoch": 0.44, + "learning_rate": 1.2323978042239982e-05, + "loss": 0.4865, + "step": 5290 + }, + { + "epoch": 0.44, + "learning_rate": 1.232134224709448e-05, + "loss": 0.4865, + "step": 5291 + }, + { + "epoch": 0.44, + "learning_rate": 1.2318706281479256e-05, + "loss": 0.4886, + "step": 5292 + }, + { + "epoch": 0.44, + "learning_rate": 1.2316070145587888e-05, + "loss": 0.4689, + "step": 5293 + }, + { + "epoch": 0.44, + "learning_rate": 1.2313433839613964e-05, + "loss": 0.4984, + "step": 5294 + }, + { + "epoch": 0.44, + "learning_rate": 1.2310797363751078e-05, + "loss": 0.497, + "step": 5295 + }, + { + "epoch": 0.44, + "learning_rate": 1.230816071819285e-05, + "loss": 0.4869, + "step": 5296 + }, + { + "epoch": 0.44, + "learning_rate": 1.2305523903132897e-05, + "loss": 0.5057, + "step": 5297 + }, + { + "epoch": 0.44, + "learning_rate": 1.2302886918764856e-05, + "loss": 0.4959, + "step": 5298 + }, + { + "epoch": 0.44, + "learning_rate": 1.230024976528238e-05, + "loss": 0.4867, + "step": 5299 + }, + { + "epoch": 0.44, + "learning_rate": 1.2297612442879129e-05, + "loss": 0.4817, + "step": 5300 + }, + { + "epoch": 0.44, + "learning_rate": 1.2294974951748775e-05, + "loss": 0.4834, + "step": 5301 + }, + { + "epoch": 0.44, + "learning_rate": 1.2292337292085006e-05, + "loss": 0.4934, + "step": 5302 + }, + { + "epoch": 0.44, + "learning_rate": 1.2289699464081521e-05, + "loss": 0.4969, + "step": 5303 + }, + { + "epoch": 0.44, + "learning_rate": 1.2287061467932033e-05, + "loss": 0.4713, + "step": 5304 + }, + { + "epoch": 0.44, + "learning_rate": 1.228442330383026e-05, + "loss": 0.4615, + "step": 5305 + }, + { + "epoch": 0.44, + "learning_rate": 1.2281784971969944e-05, + "loss": 0.4634, + "step": 5306 + }, + { + "epoch": 0.44, + "learning_rate": 1.227914647254483e-05, + "loss": 0.4882, + "step": 5307 + }, + { + "epoch": 0.44, + "learning_rate": 1.2276507805748676e-05, + "loss": 0.4769, + "step": 5308 + }, + { + "epoch": 0.44, + "learning_rate": 1.227386897177526e-05, + "loss": 0.4874, + "step": 5309 + }, + { + "epoch": 0.44, + "learning_rate": 1.2271229970818366e-05, + "loss": 0.504, + "step": 5310 + }, + { + "epoch": 0.44, + "learning_rate": 1.2268590803071787e-05, + "loss": 0.4827, + "step": 5311 + }, + { + "epoch": 0.44, + "learning_rate": 1.2265951468729336e-05, + "loss": 0.4654, + "step": 5312 + }, + { + "epoch": 0.44, + "learning_rate": 1.2263311967984834e-05, + "loss": 0.5182, + "step": 5313 + }, + { + "epoch": 0.44, + "learning_rate": 1.2260672301032116e-05, + "loss": 0.4757, + "step": 5314 + }, + { + "epoch": 0.44, + "learning_rate": 1.2258032468065024e-05, + "loss": 0.4899, + "step": 5315 + }, + { + "epoch": 0.44, + "learning_rate": 1.2255392469277421e-05, + "loss": 0.4886, + "step": 5316 + }, + { + "epoch": 0.44, + "learning_rate": 1.2252752304863178e-05, + "loss": 0.4833, + "step": 5317 + }, + { + "epoch": 0.44, + "learning_rate": 1.2250111975016173e-05, + "loss": 0.4766, + "step": 5318 + }, + { + "epoch": 0.45, + "learning_rate": 1.2247471479930303e-05, + "loss": 0.4942, + "step": 5319 + }, + { + "epoch": 0.45, + "learning_rate": 1.2244830819799478e-05, + "loss": 0.4695, + "step": 5320 + }, + { + "epoch": 0.45, + "learning_rate": 1.2242189994817614e-05, + "loss": 0.4811, + "step": 5321 + }, + { + "epoch": 0.45, + "learning_rate": 1.2239549005178642e-05, + "loss": 0.4927, + "step": 5322 + }, + { + "epoch": 0.45, + "learning_rate": 1.2236907851076505e-05, + "loss": 0.4838, + "step": 5323 + }, + { + "epoch": 0.45, + "learning_rate": 1.2234266532705161e-05, + "loss": 0.4872, + "step": 5324 + }, + { + "epoch": 0.45, + "learning_rate": 1.2231625050258576e-05, + "loss": 0.492, + "step": 5325 + }, + { + "epoch": 0.45, + "learning_rate": 1.2228983403930727e-05, + "loss": 0.4847, + "step": 5326 + }, + { + "epoch": 0.45, + "learning_rate": 1.2226341593915612e-05, + "loss": 0.4641, + "step": 5327 + }, + { + "epoch": 0.45, + "learning_rate": 1.2223699620407227e-05, + "loss": 0.5174, + "step": 5328 + }, + { + "epoch": 0.45, + "learning_rate": 1.222105748359959e-05, + "loss": 0.4728, + "step": 5329 + }, + { + "epoch": 0.45, + "learning_rate": 1.2218415183686732e-05, + "loss": 0.4889, + "step": 5330 + }, + { + "epoch": 0.45, + "learning_rate": 1.2215772720862691e-05, + "loss": 0.5182, + "step": 5331 + }, + { + "epoch": 0.45, + "learning_rate": 1.2213130095321517e-05, + "loss": 0.4757, + "step": 5332 + }, + { + "epoch": 0.45, + "learning_rate": 1.221048730725727e-05, + "loss": 0.4729, + "step": 5333 + }, + { + "epoch": 0.45, + "learning_rate": 1.2207844356864031e-05, + "loss": 0.4839, + "step": 5334 + }, + { + "epoch": 0.45, + "learning_rate": 1.2205201244335889e-05, + "loss": 0.4946, + "step": 5335 + }, + { + "epoch": 0.45, + "learning_rate": 1.2202557969866934e-05, + "loss": 0.4686, + "step": 5336 + }, + { + "epoch": 0.45, + "learning_rate": 1.2199914533651289e-05, + "loss": 0.4722, + "step": 5337 + }, + { + "epoch": 0.45, + "learning_rate": 1.2197270935883068e-05, + "loss": 0.4708, + "step": 5338 + }, + { + "epoch": 0.45, + "learning_rate": 1.2194627176756408e-05, + "loss": 0.5, + "step": 5339 + }, + { + "epoch": 0.45, + "learning_rate": 1.2191983256465455e-05, + "loss": 0.463, + "step": 5340 + }, + { + "epoch": 0.45, + "learning_rate": 1.2189339175204373e-05, + "loss": 0.4606, + "step": 5341 + }, + { + "epoch": 0.45, + "learning_rate": 1.2186694933167326e-05, + "loss": 0.5079, + "step": 5342 + }, + { + "epoch": 0.45, + "learning_rate": 1.2184050530548496e-05, + "loss": 0.4716, + "step": 5343 + }, + { + "epoch": 0.45, + "learning_rate": 1.2181405967542082e-05, + "loss": 0.4788, + "step": 5344 + }, + { + "epoch": 0.45, + "learning_rate": 1.2178761244342286e-05, + "loss": 0.488, + "step": 5345 + }, + { + "epoch": 0.45, + "learning_rate": 1.2176116361143326e-05, + "loss": 0.4836, + "step": 5346 + }, + { + "epoch": 0.45, + "learning_rate": 1.2173471318139431e-05, + "loss": 0.4844, + "step": 5347 + }, + { + "epoch": 0.45, + "learning_rate": 1.2170826115524845e-05, + "loss": 0.4895, + "step": 5348 + }, + { + "epoch": 0.45, + "learning_rate": 1.2168180753493817e-05, + "loss": 0.4887, + "step": 5349 + }, + { + "epoch": 0.45, + "learning_rate": 1.2165535232240611e-05, + "loss": 0.4839, + "step": 5350 + }, + { + "epoch": 0.45, + "learning_rate": 1.2162889551959506e-05, + "loss": 0.4759, + "step": 5351 + }, + { + "epoch": 0.45, + "learning_rate": 1.216024371284479e-05, + "loss": 0.4753, + "step": 5352 + }, + { + "epoch": 0.45, + "learning_rate": 1.215759771509076e-05, + "loss": 0.4875, + "step": 5353 + }, + { + "epoch": 0.45, + "learning_rate": 1.2154951558891728e-05, + "loss": 0.4858, + "step": 5354 + }, + { + "epoch": 0.45, + "learning_rate": 1.2152305244442014e-05, + "loss": 0.4829, + "step": 5355 + }, + { + "epoch": 0.45, + "learning_rate": 1.2149658771935955e-05, + "loss": 0.4784, + "step": 5356 + }, + { + "epoch": 0.45, + "learning_rate": 1.21470121415679e-05, + "loss": 0.4715, + "step": 5357 + }, + { + "epoch": 0.45, + "learning_rate": 1.2144365353532204e-05, + "loss": 0.4761, + "step": 5358 + }, + { + "epoch": 0.45, + "learning_rate": 1.2141718408023233e-05, + "loss": 0.4941, + "step": 5359 + }, + { + "epoch": 0.45, + "learning_rate": 1.2139071305235368e-05, + "loss": 0.4754, + "step": 5360 + }, + { + "epoch": 0.45, + "learning_rate": 1.2136424045363007e-05, + "loss": 0.4846, + "step": 5361 + }, + { + "epoch": 0.45, + "learning_rate": 1.2133776628600552e-05, + "loss": 0.4779, + "step": 5362 + }, + { + "epoch": 0.45, + "learning_rate": 1.2131129055142411e-05, + "loss": 0.481, + "step": 5363 + }, + { + "epoch": 0.45, + "learning_rate": 1.2128481325183022e-05, + "loss": 0.4914, + "step": 5364 + }, + { + "epoch": 0.45, + "learning_rate": 1.2125833438916812e-05, + "loss": 0.4922, + "step": 5365 + }, + { + "epoch": 0.45, + "learning_rate": 1.2123185396538242e-05, + "loss": 0.4835, + "step": 5366 + }, + { + "epoch": 0.45, + "learning_rate": 1.2120537198241763e-05, + "loss": 0.4769, + "step": 5367 + }, + { + "epoch": 0.45, + "learning_rate": 1.2117888844221852e-05, + "loss": 0.4646, + "step": 5368 + }, + { + "epoch": 0.45, + "learning_rate": 1.2115240334672997e-05, + "loss": 0.4822, + "step": 5369 + }, + { + "epoch": 0.45, + "learning_rate": 1.2112591669789685e-05, + "loss": 0.4844, + "step": 5370 + }, + { + "epoch": 0.45, + "learning_rate": 1.2109942849766432e-05, + "loss": 0.4739, + "step": 5371 + }, + { + "epoch": 0.45, + "learning_rate": 1.210729387479775e-05, + "loss": 0.4888, + "step": 5372 + }, + { + "epoch": 0.45, + "learning_rate": 1.210464474507817e-05, + "loss": 0.496, + "step": 5373 + }, + { + "epoch": 0.45, + "learning_rate": 1.2101995460802235e-05, + "loss": 0.4643, + "step": 5374 + }, + { + "epoch": 0.45, + "learning_rate": 1.2099346022164496e-05, + "loss": 0.4959, + "step": 5375 + }, + { + "epoch": 0.45, + "learning_rate": 1.2096696429359518e-05, + "loss": 0.4997, + "step": 5376 + }, + { + "epoch": 0.45, + "learning_rate": 1.2094046682581872e-05, + "loss": 0.5001, + "step": 5377 + }, + { + "epoch": 0.45, + "learning_rate": 1.209139678202615e-05, + "loss": 0.4878, + "step": 5378 + }, + { + "epoch": 0.45, + "learning_rate": 1.2088746727886949e-05, + "loss": 0.4932, + "step": 5379 + }, + { + "epoch": 0.45, + "learning_rate": 1.2086096520358872e-05, + "loss": 0.4941, + "step": 5380 + }, + { + "epoch": 0.45, + "learning_rate": 1.2083446159636543e-05, + "loss": 0.4906, + "step": 5381 + }, + { + "epoch": 0.45, + "learning_rate": 1.2080795645914595e-05, + "loss": 0.4808, + "step": 5382 + }, + { + "epoch": 0.45, + "learning_rate": 1.2078144979387674e-05, + "loss": 0.5055, + "step": 5383 + }, + { + "epoch": 0.45, + "learning_rate": 1.2075494160250423e-05, + "loss": 0.4768, + "step": 5384 + }, + { + "epoch": 0.45, + "learning_rate": 1.2072843188697516e-05, + "loss": 0.4818, + "step": 5385 + }, + { + "epoch": 0.45, + "learning_rate": 1.2070192064923627e-05, + "loss": 0.4919, + "step": 5386 + }, + { + "epoch": 0.45, + "learning_rate": 1.2067540789123441e-05, + "loss": 0.4866, + "step": 5387 + }, + { + "epoch": 0.45, + "learning_rate": 1.2064889361491663e-05, + "loss": 0.4826, + "step": 5388 + }, + { + "epoch": 0.45, + "learning_rate": 1.2062237782222996e-05, + "loss": 0.4683, + "step": 5389 + }, + { + "epoch": 0.45, + "learning_rate": 1.2059586051512164e-05, + "loss": 0.4713, + "step": 5390 + }, + { + "epoch": 0.45, + "learning_rate": 1.20569341695539e-05, + "loss": 0.4872, + "step": 5391 + }, + { + "epoch": 0.45, + "learning_rate": 1.2054282136542946e-05, + "loss": 0.5091, + "step": 5392 + }, + { + "epoch": 0.45, + "learning_rate": 1.2051629952674055e-05, + "loss": 0.4817, + "step": 5393 + }, + { + "epoch": 0.45, + "learning_rate": 1.2048977618141995e-05, + "loss": 0.5097, + "step": 5394 + }, + { + "epoch": 0.45, + "learning_rate": 1.2046325133141542e-05, + "loss": 0.4779, + "step": 5395 + }, + { + "epoch": 0.45, + "learning_rate": 1.2043672497867479e-05, + "loss": 0.4591, + "step": 5396 + }, + { + "epoch": 0.45, + "learning_rate": 1.2041019712514607e-05, + "loss": 0.4957, + "step": 5397 + }, + { + "epoch": 0.45, + "learning_rate": 1.2038366777277743e-05, + "loss": 0.475, + "step": 5398 + }, + { + "epoch": 0.45, + "learning_rate": 1.2035713692351698e-05, + "loss": 0.483, + "step": 5399 + }, + { + "epoch": 0.45, + "learning_rate": 1.2033060457931308e-05, + "loss": 0.4841, + "step": 5400 + }, + { + "epoch": 0.45, + "learning_rate": 1.203040707421141e-05, + "loss": 0.4775, + "step": 5401 + }, + { + "epoch": 0.45, + "learning_rate": 1.2027753541386865e-05, + "loss": 0.466, + "step": 5402 + }, + { + "epoch": 0.45, + "learning_rate": 1.2025099859652532e-05, + "loss": 0.4859, + "step": 5403 + }, + { + "epoch": 0.45, + "learning_rate": 1.202244602920329e-05, + "loss": 0.4848, + "step": 5404 + }, + { + "epoch": 0.45, + "learning_rate": 1.2019792050234022e-05, + "loss": 0.4779, + "step": 5405 + }, + { + "epoch": 0.45, + "learning_rate": 1.2017137922939629e-05, + "loss": 0.4719, + "step": 5406 + }, + { + "epoch": 0.45, + "learning_rate": 1.2014483647515014e-05, + "loss": 0.4811, + "step": 5407 + }, + { + "epoch": 0.45, + "learning_rate": 1.2011829224155101e-05, + "loss": 0.4836, + "step": 5408 + }, + { + "epoch": 0.45, + "learning_rate": 1.2009174653054815e-05, + "loss": 0.4754, + "step": 5409 + }, + { + "epoch": 0.45, + "learning_rate": 1.2006519934409105e-05, + "loss": 0.4843, + "step": 5410 + }, + { + "epoch": 0.45, + "learning_rate": 1.200386506841291e-05, + "loss": 0.4793, + "step": 5411 + }, + { + "epoch": 0.45, + "learning_rate": 1.20012100552612e-05, + "loss": 0.4602, + "step": 5412 + }, + { + "epoch": 0.45, + "learning_rate": 1.1998554895148953e-05, + "loss": 0.4766, + "step": 5413 + }, + { + "epoch": 0.45, + "learning_rate": 1.199589958827114e-05, + "loss": 0.4675, + "step": 5414 + }, + { + "epoch": 0.45, + "learning_rate": 1.1993244134822767e-05, + "loss": 0.4753, + "step": 5415 + }, + { + "epoch": 0.45, + "learning_rate": 1.1990588534998834e-05, + "loss": 0.4726, + "step": 5416 + }, + { + "epoch": 0.45, + "learning_rate": 1.1987932788994362e-05, + "loss": 0.4837, + "step": 5417 + }, + { + "epoch": 0.45, + "learning_rate": 1.1985276897004367e-05, + "loss": 0.475, + "step": 5418 + }, + { + "epoch": 0.45, + "learning_rate": 1.1982620859223902e-05, + "loss": 0.4957, + "step": 5419 + }, + { + "epoch": 0.45, + "learning_rate": 1.1979964675848004e-05, + "loss": 0.5041, + "step": 5420 + }, + { + "epoch": 0.45, + "learning_rate": 1.1977308347071735e-05, + "loss": 0.4591, + "step": 5421 + }, + { + "epoch": 0.45, + "learning_rate": 1.1974651873090163e-05, + "loss": 0.4675, + "step": 5422 + }, + { + "epoch": 0.45, + "learning_rate": 1.1971995254098374e-05, + "loss": 0.4879, + "step": 5423 + }, + { + "epoch": 0.45, + "learning_rate": 1.1969338490291455e-05, + "loss": 0.464, + "step": 5424 + }, + { + "epoch": 0.45, + "learning_rate": 1.1966681581864507e-05, + "loss": 0.4879, + "step": 5425 + }, + { + "epoch": 0.45, + "learning_rate": 1.1964024529012648e-05, + "loss": 0.5053, + "step": 5426 + }, + { + "epoch": 0.45, + "learning_rate": 1.196136733193099e-05, + "loss": 0.5042, + "step": 5427 + }, + { + "epoch": 0.45, + "learning_rate": 1.1958709990814677e-05, + "loss": 0.4944, + "step": 5428 + }, + { + "epoch": 0.45, + "learning_rate": 1.1956052505858851e-05, + "loss": 0.4783, + "step": 5429 + }, + { + "epoch": 0.45, + "learning_rate": 1.1953394877258662e-05, + "loss": 0.5042, + "step": 5430 + }, + { + "epoch": 0.45, + "learning_rate": 1.1950737105209278e-05, + "loss": 0.4801, + "step": 5431 + }, + { + "epoch": 0.45, + "learning_rate": 1.1948079189905872e-05, + "loss": 0.502, + "step": 5432 + }, + { + "epoch": 0.45, + "learning_rate": 1.1945421131543639e-05, + "loss": 0.4985, + "step": 5433 + }, + { + "epoch": 0.45, + "learning_rate": 1.1942762930317768e-05, + "loss": 0.4746, + "step": 5434 + }, + { + "epoch": 0.45, + "learning_rate": 1.1940104586423465e-05, + "loss": 0.4948, + "step": 5435 + }, + { + "epoch": 0.45, + "learning_rate": 1.1937446100055954e-05, + "loss": 0.4836, + "step": 5436 + }, + { + "epoch": 0.45, + "learning_rate": 1.1934787471410457e-05, + "loss": 0.4663, + "step": 5437 + }, + { + "epoch": 0.45, + "learning_rate": 1.1932128700682216e-05, + "loss": 0.5137, + "step": 5438 + }, + { + "epoch": 0.46, + "learning_rate": 1.1929469788066481e-05, + "loss": 0.4803, + "step": 5439 + }, + { + "epoch": 0.46, + "learning_rate": 1.1926810733758511e-05, + "loss": 0.4849, + "step": 5440 + }, + { + "epoch": 0.46, + "learning_rate": 1.1924151537953574e-05, + "loss": 0.4916, + "step": 5441 + }, + { + "epoch": 0.46, + "learning_rate": 1.1921492200846949e-05, + "loss": 0.4784, + "step": 5442 + }, + { + "epoch": 0.46, + "learning_rate": 1.191883272263393e-05, + "loss": 0.4805, + "step": 5443 + }, + { + "epoch": 0.46, + "learning_rate": 1.1916173103509819e-05, + "loss": 0.4756, + "step": 5444 + }, + { + "epoch": 0.46, + "learning_rate": 1.191351334366992e-05, + "loss": 0.5125, + "step": 5445 + }, + { + "epoch": 0.46, + "learning_rate": 1.1910853443309566e-05, + "loss": 0.4804, + "step": 5446 + }, + { + "epoch": 0.46, + "learning_rate": 1.190819340262408e-05, + "loss": 0.4834, + "step": 5447 + }, + { + "epoch": 0.46, + "learning_rate": 1.1905533221808805e-05, + "loss": 0.4813, + "step": 5448 + }, + { + "epoch": 0.46, + "learning_rate": 1.1902872901059102e-05, + "loss": 0.501, + "step": 5449 + }, + { + "epoch": 0.46, + "learning_rate": 1.1900212440570324e-05, + "loss": 0.4523, + "step": 5450 + }, + { + "epoch": 0.46, + "learning_rate": 1.1897551840537848e-05, + "loss": 0.4583, + "step": 5451 + }, + { + "epoch": 0.46, + "learning_rate": 1.1894891101157058e-05, + "loss": 0.4717, + "step": 5452 + }, + { + "epoch": 0.46, + "learning_rate": 1.1892230222623345e-05, + "loss": 0.4813, + "step": 5453 + }, + { + "epoch": 0.46, + "learning_rate": 1.1889569205132119e-05, + "loss": 0.495, + "step": 5454 + }, + { + "epoch": 0.46, + "learning_rate": 1.1886908048878785e-05, + "loss": 0.4842, + "step": 5455 + }, + { + "epoch": 0.46, + "learning_rate": 1.1884246754058775e-05, + "loss": 0.4882, + "step": 5456 + }, + { + "epoch": 0.46, + "learning_rate": 1.1881585320867521e-05, + "loss": 0.4802, + "step": 5457 + }, + { + "epoch": 0.46, + "learning_rate": 1.1878923749500466e-05, + "loss": 0.4653, + "step": 5458 + }, + { + "epoch": 0.46, + "learning_rate": 1.1876262040153064e-05, + "loss": 0.4861, + "step": 5459 + }, + { + "epoch": 0.46, + "learning_rate": 1.1873600193020786e-05, + "loss": 0.4977, + "step": 5460 + }, + { + "epoch": 0.46, + "learning_rate": 1.18709382082991e-05, + "loss": 0.4697, + "step": 5461 + }, + { + "epoch": 0.46, + "learning_rate": 1.1868276086183494e-05, + "loss": 0.4973, + "step": 5462 + }, + { + "epoch": 0.46, + "learning_rate": 1.1865613826869463e-05, + "loss": 0.5125, + "step": 5463 + }, + { + "epoch": 0.46, + "learning_rate": 1.1862951430552514e-05, + "loss": 0.4998, + "step": 5464 + }, + { + "epoch": 0.46, + "learning_rate": 1.1860288897428158e-05, + "loss": 0.4609, + "step": 5465 + }, + { + "epoch": 0.46, + "learning_rate": 1.1857626227691924e-05, + "loss": 0.47, + "step": 5466 + }, + { + "epoch": 0.46, + "learning_rate": 1.1854963421539348e-05, + "loss": 0.4728, + "step": 5467 + }, + { + "epoch": 0.46, + "learning_rate": 1.185230047916597e-05, + "loss": 0.4885, + "step": 5468 + }, + { + "epoch": 0.46, + "learning_rate": 1.1849637400767351e-05, + "loss": 0.49, + "step": 5469 + }, + { + "epoch": 0.46, + "learning_rate": 1.1846974186539055e-05, + "loss": 0.5007, + "step": 5470 + }, + { + "epoch": 0.46, + "learning_rate": 1.1844310836676658e-05, + "loss": 0.4694, + "step": 5471 + }, + { + "epoch": 0.46, + "learning_rate": 1.184164735137574e-05, + "loss": 0.4736, + "step": 5472 + }, + { + "epoch": 0.46, + "learning_rate": 1.1838983730831904e-05, + "loss": 0.5052, + "step": 5473 + }, + { + "epoch": 0.46, + "learning_rate": 1.1836319975240751e-05, + "loss": 0.4826, + "step": 5474 + }, + { + "epoch": 0.46, + "learning_rate": 1.1833656084797898e-05, + "loss": 0.4675, + "step": 5475 + }, + { + "epoch": 0.46, + "learning_rate": 1.1830992059698967e-05, + "loss": 0.4842, + "step": 5476 + }, + { + "epoch": 0.46, + "learning_rate": 1.1828327900139596e-05, + "loss": 0.4937, + "step": 5477 + }, + { + "epoch": 0.46, + "learning_rate": 1.1825663606315425e-05, + "loss": 0.4691, + "step": 5478 + }, + { + "epoch": 0.46, + "learning_rate": 1.1822999178422114e-05, + "loss": 0.4715, + "step": 5479 + }, + { + "epoch": 0.46, + "learning_rate": 1.182033461665533e-05, + "loss": 0.4987, + "step": 5480 + }, + { + "epoch": 0.46, + "learning_rate": 1.181766992121074e-05, + "loss": 0.4855, + "step": 5481 + }, + { + "epoch": 0.46, + "learning_rate": 1.1815005092284033e-05, + "loss": 0.4915, + "step": 5482 + }, + { + "epoch": 0.46, + "learning_rate": 1.18123401300709e-05, + "loss": 0.469, + "step": 5483 + }, + { + "epoch": 0.46, + "learning_rate": 1.1809675034767043e-05, + "loss": 0.4964, + "step": 5484 + }, + { + "epoch": 0.46, + "learning_rate": 1.1807009806568181e-05, + "loss": 0.4829, + "step": 5485 + }, + { + "epoch": 0.46, + "learning_rate": 1.1804344445670034e-05, + "loss": 0.4707, + "step": 5486 + }, + { + "epoch": 0.46, + "learning_rate": 1.1801678952268338e-05, + "loss": 0.4788, + "step": 5487 + }, + { + "epoch": 0.46, + "learning_rate": 1.179901332655883e-05, + "loss": 0.4759, + "step": 5488 + }, + { + "epoch": 0.46, + "learning_rate": 1.1796347568737268e-05, + "loss": 0.4847, + "step": 5489 + }, + { + "epoch": 0.46, + "learning_rate": 1.1793681678999412e-05, + "loss": 0.4786, + "step": 5490 + }, + { + "epoch": 0.46, + "learning_rate": 1.1791015657541037e-05, + "loss": 0.4953, + "step": 5491 + }, + { + "epoch": 0.46, + "learning_rate": 1.1788349504557917e-05, + "loss": 0.4832, + "step": 5492 + }, + { + "epoch": 0.46, + "learning_rate": 1.1785683220245849e-05, + "loss": 0.4776, + "step": 5493 + }, + { + "epoch": 0.46, + "learning_rate": 1.1783016804800631e-05, + "loss": 0.4789, + "step": 5494 + }, + { + "epoch": 0.46, + "learning_rate": 1.1780350258418078e-05, + "loss": 0.4819, + "step": 5495 + }, + { + "epoch": 0.46, + "learning_rate": 1.1777683581294003e-05, + "loss": 0.4795, + "step": 5496 + }, + { + "epoch": 0.46, + "learning_rate": 1.1775016773624246e-05, + "loss": 0.4736, + "step": 5497 + }, + { + "epoch": 0.46, + "learning_rate": 1.1772349835604638e-05, + "loss": 0.5113, + "step": 5498 + }, + { + "epoch": 0.46, + "learning_rate": 1.1769682767431026e-05, + "loss": 0.4702, + "step": 5499 + }, + { + "epoch": 0.46, + "learning_rate": 1.1767015569299274e-05, + "loss": 0.4802, + "step": 5500 + }, + { + "epoch": 0.46, + "learning_rate": 1.1764348241405249e-05, + "loss": 0.4804, + "step": 5501 + }, + { + "epoch": 0.46, + "learning_rate": 1.1761680783944829e-05, + "loss": 0.4852, + "step": 5502 + }, + { + "epoch": 0.46, + "learning_rate": 1.1759013197113895e-05, + "loss": 0.4836, + "step": 5503 + }, + { + "epoch": 0.46, + "learning_rate": 1.175634548110835e-05, + "loss": 0.4939, + "step": 5504 + }, + { + "epoch": 0.46, + "learning_rate": 1.1753677636124101e-05, + "loss": 0.5088, + "step": 5505 + }, + { + "epoch": 0.46, + "learning_rate": 1.1751009662357059e-05, + "loss": 0.471, + "step": 5506 + }, + { + "epoch": 0.46, + "learning_rate": 1.1748341560003149e-05, + "loss": 0.489, + "step": 5507 + }, + { + "epoch": 0.46, + "learning_rate": 1.174567332925831e-05, + "loss": 0.4822, + "step": 5508 + }, + { + "epoch": 0.46, + "learning_rate": 1.174300497031848e-05, + "loss": 0.4794, + "step": 5509 + }, + { + "epoch": 0.46, + "learning_rate": 1.1740336483379613e-05, + "loss": 0.4821, + "step": 5510 + }, + { + "epoch": 0.46, + "learning_rate": 1.1737667868637674e-05, + "loss": 0.4755, + "step": 5511 + }, + { + "epoch": 0.46, + "learning_rate": 1.1734999126288637e-05, + "loss": 0.4849, + "step": 5512 + }, + { + "epoch": 0.46, + "learning_rate": 1.1732330256528477e-05, + "loss": 0.4922, + "step": 5513 + }, + { + "epoch": 0.46, + "learning_rate": 1.1729661259553193e-05, + "loss": 0.4849, + "step": 5514 + }, + { + "epoch": 0.46, + "learning_rate": 1.1726992135558776e-05, + "loss": 0.4955, + "step": 5515 + }, + { + "epoch": 0.46, + "learning_rate": 1.1724322884741242e-05, + "loss": 0.4834, + "step": 5516 + }, + { + "epoch": 0.46, + "learning_rate": 1.1721653507296604e-05, + "loss": 0.5012, + "step": 5517 + }, + { + "epoch": 0.46, + "learning_rate": 1.1718984003420899e-05, + "loss": 0.4802, + "step": 5518 + }, + { + "epoch": 0.46, + "learning_rate": 1.1716314373310154e-05, + "loss": 0.4789, + "step": 5519 + }, + { + "epoch": 0.46, + "learning_rate": 1.171364461716042e-05, + "loss": 0.4883, + "step": 5520 + }, + { + "epoch": 0.46, + "learning_rate": 1.1710974735167755e-05, + "loss": 0.4702, + "step": 5521 + }, + { + "epoch": 0.46, + "learning_rate": 1.1708304727528223e-05, + "loss": 0.4768, + "step": 5522 + }, + { + "epoch": 0.46, + "learning_rate": 1.1705634594437893e-05, + "loss": 0.4884, + "step": 5523 + }, + { + "epoch": 0.46, + "learning_rate": 1.1702964336092857e-05, + "loss": 0.4935, + "step": 5524 + }, + { + "epoch": 0.46, + "learning_rate": 1.17002939526892e-05, + "loss": 0.4804, + "step": 5525 + }, + { + "epoch": 0.46, + "learning_rate": 1.169762344442303e-05, + "loss": 0.4896, + "step": 5526 + }, + { + "epoch": 0.46, + "learning_rate": 1.1694952811490451e-05, + "loss": 0.4846, + "step": 5527 + }, + { + "epoch": 0.46, + "learning_rate": 1.1692282054087594e-05, + "loss": 0.4812, + "step": 5528 + }, + { + "epoch": 0.46, + "learning_rate": 1.1689611172410577e-05, + "loss": 0.5226, + "step": 5529 + }, + { + "epoch": 0.46, + "learning_rate": 1.1686940166655543e-05, + "loss": 0.4731, + "step": 5530 + }, + { + "epoch": 0.46, + "learning_rate": 1.1684269037018641e-05, + "loss": 0.475, + "step": 5531 + }, + { + "epoch": 0.46, + "learning_rate": 1.1681597783696027e-05, + "loss": 0.5193, + "step": 5532 + }, + { + "epoch": 0.46, + "learning_rate": 1.1678926406883866e-05, + "loss": 0.4724, + "step": 5533 + }, + { + "epoch": 0.46, + "learning_rate": 1.1676254906778331e-05, + "loss": 0.4698, + "step": 5534 + }, + { + "epoch": 0.46, + "learning_rate": 1.1673583283575607e-05, + "loss": 0.4757, + "step": 5535 + }, + { + "epoch": 0.46, + "learning_rate": 1.1670911537471889e-05, + "loss": 0.48, + "step": 5536 + }, + { + "epoch": 0.46, + "learning_rate": 1.1668239668663377e-05, + "loss": 0.4737, + "step": 5537 + }, + { + "epoch": 0.46, + "learning_rate": 1.1665567677346285e-05, + "loss": 0.4547, + "step": 5538 + }, + { + "epoch": 0.46, + "learning_rate": 1.166289556371683e-05, + "loss": 0.4934, + "step": 5539 + }, + { + "epoch": 0.46, + "learning_rate": 1.1660223327971239e-05, + "loss": 0.4754, + "step": 5540 + }, + { + "epoch": 0.46, + "learning_rate": 1.1657550970305752e-05, + "loss": 0.473, + "step": 5541 + }, + { + "epoch": 0.46, + "learning_rate": 1.1654878490916617e-05, + "loss": 0.4748, + "step": 5542 + }, + { + "epoch": 0.46, + "learning_rate": 1.165220589000009e-05, + "loss": 0.486, + "step": 5543 + }, + { + "epoch": 0.46, + "learning_rate": 1.1649533167752434e-05, + "loss": 0.4595, + "step": 5544 + }, + { + "epoch": 0.46, + "learning_rate": 1.164686032436992e-05, + "loss": 0.4842, + "step": 5545 + }, + { + "epoch": 0.46, + "learning_rate": 1.1644187360048838e-05, + "loss": 0.4897, + "step": 5546 + }, + { + "epoch": 0.46, + "learning_rate": 1.164151427498547e-05, + "loss": 0.4752, + "step": 5547 + }, + { + "epoch": 0.46, + "learning_rate": 1.1638841069376125e-05, + "loss": 0.4937, + "step": 5548 + }, + { + "epoch": 0.46, + "learning_rate": 1.1636167743417111e-05, + "loss": 0.4841, + "step": 5549 + }, + { + "epoch": 0.46, + "learning_rate": 1.1633494297304738e-05, + "loss": 0.4826, + "step": 5550 + }, + { + "epoch": 0.46, + "learning_rate": 1.163082073123534e-05, + "loss": 0.4777, + "step": 5551 + }, + { + "epoch": 0.46, + "learning_rate": 1.1628147045405248e-05, + "loss": 0.4806, + "step": 5552 + }, + { + "epoch": 0.46, + "learning_rate": 1.1625473240010814e-05, + "loss": 0.4643, + "step": 5553 + }, + { + "epoch": 0.46, + "learning_rate": 1.1622799315248382e-05, + "loss": 0.5037, + "step": 5554 + }, + { + "epoch": 0.46, + "learning_rate": 1.1620125271314322e-05, + "loss": 0.4654, + "step": 5555 + }, + { + "epoch": 0.46, + "learning_rate": 1.1617451108404996e-05, + "loss": 0.4785, + "step": 5556 + }, + { + "epoch": 0.46, + "learning_rate": 1.1614776826716791e-05, + "loss": 0.4712, + "step": 5557 + }, + { + "epoch": 0.47, + "learning_rate": 1.161210242644609e-05, + "loss": 0.4797, + "step": 5558 + }, + { + "epoch": 0.47, + "learning_rate": 1.1609427907789294e-05, + "loss": 0.4672, + "step": 5559 + }, + { + "epoch": 0.47, + "learning_rate": 1.160675327094281e-05, + "loss": 0.5135, + "step": 5560 + }, + { + "epoch": 0.47, + "learning_rate": 1.160407851610304e-05, + "loss": 0.5052, + "step": 5561 + }, + { + "epoch": 0.47, + "learning_rate": 1.1601403643466422e-05, + "loss": 0.4833, + "step": 5562 + }, + { + "epoch": 0.47, + "learning_rate": 1.159872865322938e-05, + "loss": 0.5247, + "step": 5563 + }, + { + "epoch": 0.47, + "learning_rate": 1.1596053545588355e-05, + "loss": 0.5032, + "step": 5564 + }, + { + "epoch": 0.47, + "learning_rate": 1.1593378320739796e-05, + "loss": 0.4918, + "step": 5565 + }, + { + "epoch": 0.47, + "learning_rate": 1.1590702978880159e-05, + "loss": 0.4745, + "step": 5566 + }, + { + "epoch": 0.47, + "learning_rate": 1.1588027520205915e-05, + "loss": 0.4933, + "step": 5567 + }, + { + "epoch": 0.47, + "learning_rate": 1.1585351944913532e-05, + "loss": 0.4832, + "step": 5568 + }, + { + "epoch": 0.47, + "learning_rate": 1.1582676253199498e-05, + "loss": 0.4923, + "step": 5569 + }, + { + "epoch": 0.47, + "learning_rate": 1.1580000445260305e-05, + "loss": 0.4878, + "step": 5570 + }, + { + "epoch": 0.47, + "learning_rate": 1.1577324521292445e-05, + "loss": 0.4873, + "step": 5571 + }, + { + "epoch": 0.47, + "learning_rate": 1.1574648481492434e-05, + "loss": 0.4808, + "step": 5572 + }, + { + "epoch": 0.47, + "learning_rate": 1.1571972326056794e-05, + "loss": 0.4868, + "step": 5573 + }, + { + "epoch": 0.47, + "learning_rate": 1.156929605518204e-05, + "loss": 0.49, + "step": 5574 + }, + { + "epoch": 0.47, + "learning_rate": 1.1566619669064709e-05, + "loss": 0.468, + "step": 5575 + }, + { + "epoch": 0.47, + "learning_rate": 1.1563943167901348e-05, + "loss": 0.4702, + "step": 5576 + }, + { + "epoch": 0.47, + "learning_rate": 1.1561266551888505e-05, + "loss": 0.4777, + "step": 5577 + }, + { + "epoch": 0.47, + "learning_rate": 1.1558589821222742e-05, + "loss": 0.4819, + "step": 5578 + }, + { + "epoch": 0.47, + "learning_rate": 1.1555912976100623e-05, + "loss": 0.4927, + "step": 5579 + }, + { + "epoch": 0.47, + "learning_rate": 1.155323601671873e-05, + "loss": 0.4894, + "step": 5580 + }, + { + "epoch": 0.47, + "learning_rate": 1.155055894327364e-05, + "loss": 0.4895, + "step": 5581 + }, + { + "epoch": 0.47, + "learning_rate": 1.1547881755961952e-05, + "loss": 0.4753, + "step": 5582 + }, + { + "epoch": 0.47, + "learning_rate": 1.1545204454980268e-05, + "loss": 0.483, + "step": 5583 + }, + { + "epoch": 0.47, + "learning_rate": 1.1542527040525192e-05, + "loss": 0.4889, + "step": 5584 + }, + { + "epoch": 0.47, + "learning_rate": 1.1539849512793348e-05, + "loss": 0.4702, + "step": 5585 + }, + { + "epoch": 0.47, + "learning_rate": 1.1537171871981363e-05, + "loss": 0.4892, + "step": 5586 + }, + { + "epoch": 0.47, + "learning_rate": 1.1534494118285865e-05, + "loss": 0.4854, + "step": 5587 + }, + { + "epoch": 0.47, + "learning_rate": 1.1531816251903503e-05, + "loss": 0.4915, + "step": 5588 + }, + { + "epoch": 0.47, + "learning_rate": 1.1529138273030927e-05, + "loss": 0.4627, + "step": 5589 + }, + { + "epoch": 0.47, + "learning_rate": 1.1526460181864799e-05, + "loss": 0.4904, + "step": 5590 + }, + { + "epoch": 0.47, + "learning_rate": 1.152378197860178e-05, + "loss": 0.5022, + "step": 5591 + }, + { + "epoch": 0.47, + "learning_rate": 1.1521103663438551e-05, + "loss": 0.4974, + "step": 5592 + }, + { + "epoch": 0.47, + "learning_rate": 1.1518425236571797e-05, + "loss": 0.48, + "step": 5593 + }, + { + "epoch": 0.47, + "learning_rate": 1.1515746698198211e-05, + "loss": 0.4676, + "step": 5594 + }, + { + "epoch": 0.47, + "learning_rate": 1.1513068048514489e-05, + "loss": 0.4756, + "step": 5595 + }, + { + "epoch": 0.47, + "learning_rate": 1.1510389287717345e-05, + "loss": 0.4957, + "step": 5596 + }, + { + "epoch": 0.47, + "learning_rate": 1.150771041600349e-05, + "loss": 0.4611, + "step": 5597 + }, + { + "epoch": 0.47, + "learning_rate": 1.1505031433569658e-05, + "loss": 0.4657, + "step": 5598 + }, + { + "epoch": 0.47, + "learning_rate": 1.1502352340612576e-05, + "loss": 0.4936, + "step": 5599 + }, + { + "epoch": 0.47, + "learning_rate": 1.1499673137328986e-05, + "loss": 0.4698, + "step": 5600 + }, + { + "epoch": 0.47, + "learning_rate": 1.1496993823915639e-05, + "loss": 0.4816, + "step": 5601 + }, + { + "epoch": 0.47, + "learning_rate": 1.1494314400569288e-05, + "loss": 0.4927, + "step": 5602 + }, + { + "epoch": 0.47, + "learning_rate": 1.1491634867486707e-05, + "loss": 0.4541, + "step": 5603 + }, + { + "epoch": 0.47, + "learning_rate": 1.1488955224864667e-05, + "loss": 0.48, + "step": 5604 + }, + { + "epoch": 0.47, + "learning_rate": 1.1486275472899943e-05, + "loss": 0.4936, + "step": 5605 + }, + { + "epoch": 0.47, + "learning_rate": 1.1483595611789336e-05, + "loss": 0.4853, + "step": 5606 + }, + { + "epoch": 0.47, + "learning_rate": 1.1480915641729633e-05, + "loss": 0.4817, + "step": 5607 + }, + { + "epoch": 0.47, + "learning_rate": 1.147823556291765e-05, + "loss": 0.4931, + "step": 5608 + }, + { + "epoch": 0.47, + "learning_rate": 1.1475555375550191e-05, + "loss": 0.4849, + "step": 5609 + }, + { + "epoch": 0.47, + "learning_rate": 1.1472875079824087e-05, + "loss": 0.4649, + "step": 5610 + }, + { + "epoch": 0.47, + "learning_rate": 1.1470194675936159e-05, + "loss": 0.4762, + "step": 5611 + }, + { + "epoch": 0.47, + "learning_rate": 1.1467514164083252e-05, + "loss": 0.4908, + "step": 5612 + }, + { + "epoch": 0.47, + "learning_rate": 1.1464833544462203e-05, + "loss": 0.4826, + "step": 5613 + }, + { + "epoch": 0.47, + "learning_rate": 1.1462152817269879e-05, + "loss": 0.4964, + "step": 5614 + }, + { + "epoch": 0.47, + "learning_rate": 1.145947198270313e-05, + "loss": 0.4881, + "step": 5615 + }, + { + "epoch": 0.47, + "learning_rate": 1.1456791040958828e-05, + "loss": 0.4719, + "step": 5616 + }, + { + "epoch": 0.47, + "learning_rate": 1.1454109992233851e-05, + "loss": 0.4977, + "step": 5617 + }, + { + "epoch": 0.47, + "learning_rate": 1.1451428836725087e-05, + "loss": 0.4921, + "step": 5618 + }, + { + "epoch": 0.47, + "learning_rate": 1.1448747574629424e-05, + "loss": 0.476, + "step": 5619 + }, + { + "epoch": 0.47, + "learning_rate": 1.1446066206143766e-05, + "loss": 0.4831, + "step": 5620 + }, + { + "epoch": 0.47, + "learning_rate": 1.1443384731465021e-05, + "loss": 0.4824, + "step": 5621 + }, + { + "epoch": 0.47, + "learning_rate": 1.1440703150790102e-05, + "loss": 0.4794, + "step": 5622 + }, + { + "epoch": 0.47, + "learning_rate": 1.1438021464315939e-05, + "loss": 0.4919, + "step": 5623 + }, + { + "epoch": 0.47, + "learning_rate": 1.143533967223946e-05, + "loss": 0.4893, + "step": 5624 + }, + { + "epoch": 0.47, + "learning_rate": 1.1432657774757607e-05, + "loss": 0.4674, + "step": 5625 + }, + { + "epoch": 0.47, + "learning_rate": 1.1429975772067322e-05, + "loss": 0.4806, + "step": 5626 + }, + { + "epoch": 0.47, + "learning_rate": 1.1427293664365568e-05, + "loss": 0.5062, + "step": 5627 + }, + { + "epoch": 0.47, + "learning_rate": 1.1424611451849301e-05, + "loss": 0.4882, + "step": 5628 + }, + { + "epoch": 0.47, + "learning_rate": 1.1421929134715492e-05, + "loss": 0.4883, + "step": 5629 + }, + { + "epoch": 0.47, + "learning_rate": 1.1419246713161128e-05, + "loss": 0.4493, + "step": 5630 + }, + { + "epoch": 0.47, + "learning_rate": 1.1416564187383185e-05, + "loss": 0.4925, + "step": 5631 + }, + { + "epoch": 0.47, + "learning_rate": 1.1413881557578662e-05, + "loss": 0.4814, + "step": 5632 + }, + { + "epoch": 0.47, + "learning_rate": 1.1411198823944553e-05, + "loss": 0.4868, + "step": 5633 + }, + { + "epoch": 0.47, + "learning_rate": 1.1408515986677877e-05, + "loss": 0.4744, + "step": 5634 + }, + { + "epoch": 0.47, + "learning_rate": 1.1405833045975644e-05, + "loss": 0.4786, + "step": 5635 + }, + { + "epoch": 0.47, + "learning_rate": 1.140315000203488e-05, + "loss": 0.4724, + "step": 5636 + }, + { + "epoch": 0.47, + "learning_rate": 1.1400466855052617e-05, + "loss": 0.4885, + "step": 5637 + }, + { + "epoch": 0.47, + "learning_rate": 1.139778360522589e-05, + "loss": 0.4876, + "step": 5638 + }, + { + "epoch": 0.47, + "learning_rate": 1.139510025275175e-05, + "loss": 0.4921, + "step": 5639 + }, + { + "epoch": 0.47, + "learning_rate": 1.139241679782725e-05, + "loss": 0.5004, + "step": 5640 + }, + { + "epoch": 0.47, + "learning_rate": 1.1389733240649454e-05, + "loss": 0.4859, + "step": 5641 + }, + { + "epoch": 0.47, + "learning_rate": 1.1387049581415428e-05, + "loss": 0.4938, + "step": 5642 + }, + { + "epoch": 0.47, + "learning_rate": 1.138436582032225e-05, + "loss": 0.4681, + "step": 5643 + }, + { + "epoch": 0.47, + "learning_rate": 1.1381681957567e-05, + "loss": 0.4845, + "step": 5644 + }, + { + "epoch": 0.47, + "learning_rate": 1.1378997993346782e-05, + "loss": 0.4733, + "step": 5645 + }, + { + "epoch": 0.47, + "learning_rate": 1.137631392785868e-05, + "loss": 0.4937, + "step": 5646 + }, + { + "epoch": 0.47, + "learning_rate": 1.1373629761299811e-05, + "loss": 0.4775, + "step": 5647 + }, + { + "epoch": 0.47, + "learning_rate": 1.1370945493867284e-05, + "loss": 0.471, + "step": 5648 + }, + { + "epoch": 0.47, + "learning_rate": 1.1368261125758224e-05, + "loss": 0.4901, + "step": 5649 + }, + { + "epoch": 0.47, + "learning_rate": 1.1365576657169754e-05, + "loss": 0.4707, + "step": 5650 + }, + { + "epoch": 0.47, + "learning_rate": 1.136289208829902e-05, + "loss": 0.4803, + "step": 5651 + }, + { + "epoch": 0.47, + "learning_rate": 1.1360207419343157e-05, + "loss": 0.4749, + "step": 5652 + }, + { + "epoch": 0.47, + "learning_rate": 1.1357522650499317e-05, + "loss": 0.4835, + "step": 5653 + }, + { + "epoch": 0.47, + "learning_rate": 1.135483778196466e-05, + "loss": 0.4921, + "step": 5654 + }, + { + "epoch": 0.47, + "learning_rate": 1.1352152813936354e-05, + "loss": 0.4825, + "step": 5655 + }, + { + "epoch": 0.47, + "learning_rate": 1.1349467746611569e-05, + "loss": 0.4778, + "step": 5656 + }, + { + "epoch": 0.47, + "learning_rate": 1.1346782580187486e-05, + "loss": 0.4877, + "step": 5657 + }, + { + "epoch": 0.47, + "learning_rate": 1.1344097314861292e-05, + "loss": 0.5045, + "step": 5658 + }, + { + "epoch": 0.47, + "learning_rate": 1.1341411950830179e-05, + "loss": 0.4885, + "step": 5659 + }, + { + "epoch": 0.47, + "learning_rate": 1.1338726488291351e-05, + "loss": 0.4939, + "step": 5660 + }, + { + "epoch": 0.47, + "learning_rate": 1.1336040927442023e-05, + "loss": 0.4826, + "step": 5661 + }, + { + "epoch": 0.47, + "learning_rate": 1.1333355268479403e-05, + "loss": 0.4694, + "step": 5662 + }, + { + "epoch": 0.47, + "learning_rate": 1.1330669511600716e-05, + "loss": 0.467, + "step": 5663 + }, + { + "epoch": 0.47, + "learning_rate": 1.1327983657003197e-05, + "loss": 0.5067, + "step": 5664 + }, + { + "epoch": 0.47, + "learning_rate": 1.1325297704884081e-05, + "loss": 0.4779, + "step": 5665 + }, + { + "epoch": 0.47, + "learning_rate": 1.132261165544062e-05, + "loss": 0.4802, + "step": 5666 + }, + { + "epoch": 0.47, + "learning_rate": 1.131992550887005e-05, + "loss": 0.4811, + "step": 5667 + }, + { + "epoch": 0.47, + "learning_rate": 1.1317239265369648e-05, + "loss": 0.5074, + "step": 5668 + }, + { + "epoch": 0.47, + "learning_rate": 1.131455292513667e-05, + "loss": 0.4494, + "step": 5669 + }, + { + "epoch": 0.47, + "learning_rate": 1.1311866488368392e-05, + "loss": 0.4755, + "step": 5670 + }, + { + "epoch": 0.47, + "learning_rate": 1.1309179955262097e-05, + "loss": 0.5055, + "step": 5671 + }, + { + "epoch": 0.47, + "learning_rate": 1.1306493326015074e-05, + "loss": 0.4714, + "step": 5672 + }, + { + "epoch": 0.47, + "learning_rate": 1.1303806600824613e-05, + "loss": 0.4855, + "step": 5673 + }, + { + "epoch": 0.47, + "learning_rate": 1.1301119779888015e-05, + "loss": 0.4815, + "step": 5674 + }, + { + "epoch": 0.47, + "learning_rate": 1.1298432863402595e-05, + "loss": 0.4807, + "step": 5675 + }, + { + "epoch": 0.47, + "learning_rate": 1.1295745851565667e-05, + "loss": 0.4727, + "step": 5676 + }, + { + "epoch": 0.47, + "learning_rate": 1.1293058744574552e-05, + "loss": 0.4793, + "step": 5677 + }, + { + "epoch": 0.48, + "learning_rate": 1.129037154262658e-05, + "loss": 0.4741, + "step": 5678 + }, + { + "epoch": 0.48, + "learning_rate": 1.128768424591909e-05, + "loss": 0.4584, + "step": 5679 + }, + { + "epoch": 0.48, + "learning_rate": 1.1284996854649424e-05, + "loss": 0.4911, + "step": 5680 + }, + { + "epoch": 0.48, + "learning_rate": 1.1282309369014937e-05, + "loss": 0.4811, + "step": 5681 + }, + { + "epoch": 0.48, + "learning_rate": 1.127962178921298e-05, + "loss": 0.4769, + "step": 5682 + }, + { + "epoch": 0.48, + "learning_rate": 1.1276934115440924e-05, + "loss": 0.4743, + "step": 5683 + }, + { + "epoch": 0.48, + "learning_rate": 1.1274246347896136e-05, + "loss": 0.48, + "step": 5684 + }, + { + "epoch": 0.48, + "learning_rate": 1.1271558486775995e-05, + "loss": 0.4874, + "step": 5685 + }, + { + "epoch": 0.48, + "learning_rate": 1.1268870532277889e-05, + "loss": 0.463, + "step": 5686 + }, + { + "epoch": 0.48, + "learning_rate": 1.1266182484599209e-05, + "loss": 0.4752, + "step": 5687 + }, + { + "epoch": 0.48, + "learning_rate": 1.1263494343937354e-05, + "loss": 0.4682, + "step": 5688 + }, + { + "epoch": 0.48, + "learning_rate": 1.1260806110489726e-05, + "loss": 0.4947, + "step": 5689 + }, + { + "epoch": 0.48, + "learning_rate": 1.1258117784453746e-05, + "loss": 0.4735, + "step": 5690 + }, + { + "epoch": 0.48, + "learning_rate": 1.1255429366026826e-05, + "loss": 0.4578, + "step": 5691 + }, + { + "epoch": 0.48, + "learning_rate": 1.1252740855406397e-05, + "loss": 0.4827, + "step": 5692 + }, + { + "epoch": 0.48, + "learning_rate": 1.1250052252789891e-05, + "loss": 0.4848, + "step": 5693 + }, + { + "epoch": 0.48, + "learning_rate": 1.1247363558374745e-05, + "loss": 0.4687, + "step": 5694 + }, + { + "epoch": 0.48, + "learning_rate": 1.1244674772358406e-05, + "loss": 0.473, + "step": 5695 + }, + { + "epoch": 0.48, + "learning_rate": 1.124198589493833e-05, + "loss": 0.4834, + "step": 5696 + }, + { + "epoch": 0.48, + "learning_rate": 1.1239296926311975e-05, + "loss": 0.4675, + "step": 5697 + }, + { + "epoch": 0.48, + "learning_rate": 1.123660786667681e-05, + "loss": 0.4829, + "step": 5698 + }, + { + "epoch": 0.48, + "learning_rate": 1.1233918716230308e-05, + "loss": 0.4824, + "step": 5699 + }, + { + "epoch": 0.48, + "learning_rate": 1.1231229475169945e-05, + "loss": 0.4713, + "step": 5700 + }, + { + "epoch": 0.48, + "learning_rate": 1.1228540143693209e-05, + "loss": 0.4831, + "step": 5701 + }, + { + "epoch": 0.48, + "learning_rate": 1.12258507219976e-05, + "loss": 0.4796, + "step": 5702 + }, + { + "epoch": 0.48, + "learning_rate": 1.122316121028061e-05, + "loss": 0.4962, + "step": 5703 + }, + { + "epoch": 0.48, + "learning_rate": 1.1220471608739748e-05, + "loss": 0.4918, + "step": 5704 + }, + { + "epoch": 0.48, + "learning_rate": 1.1217781917572524e-05, + "loss": 0.4789, + "step": 5705 + }, + { + "epoch": 0.48, + "learning_rate": 1.1215092136976466e-05, + "loss": 0.5123, + "step": 5706 + }, + { + "epoch": 0.48, + "learning_rate": 1.1212402267149094e-05, + "loss": 0.478, + "step": 5707 + }, + { + "epoch": 0.48, + "learning_rate": 1.1209712308287941e-05, + "loss": 0.4826, + "step": 5708 + }, + { + "epoch": 0.48, + "learning_rate": 1.120702226059055e-05, + "loss": 0.4965, + "step": 5709 + }, + { + "epoch": 0.48, + "learning_rate": 1.1204332124254463e-05, + "loss": 0.469, + "step": 5710 + }, + { + "epoch": 0.48, + "learning_rate": 1.1201641899477231e-05, + "loss": 0.4617, + "step": 5711 + }, + { + "epoch": 0.48, + "learning_rate": 1.119895158645642e-05, + "loss": 0.4843, + "step": 5712 + }, + { + "epoch": 0.48, + "learning_rate": 1.1196261185389593e-05, + "loss": 0.4833, + "step": 5713 + }, + { + "epoch": 0.48, + "learning_rate": 1.1193570696474317e-05, + "loss": 0.4829, + "step": 5714 + }, + { + "epoch": 0.48, + "learning_rate": 1.1190880119908175e-05, + "loss": 0.4845, + "step": 5715 + }, + { + "epoch": 0.48, + "learning_rate": 1.1188189455888747e-05, + "loss": 0.4692, + "step": 5716 + }, + { + "epoch": 0.48, + "learning_rate": 1.1185498704613632e-05, + "loss": 0.4786, + "step": 5717 + }, + { + "epoch": 0.48, + "learning_rate": 1.1182807866280419e-05, + "loss": 0.4714, + "step": 5718 + }, + { + "epoch": 0.48, + "learning_rate": 1.1180116941086719e-05, + "loss": 0.4922, + "step": 5719 + }, + { + "epoch": 0.48, + "learning_rate": 1.1177425929230137e-05, + "loss": 0.4893, + "step": 5720 + }, + { + "epoch": 0.48, + "learning_rate": 1.117473483090829e-05, + "loss": 0.476, + "step": 5721 + }, + { + "epoch": 0.48, + "learning_rate": 1.1172043646318809e-05, + "loss": 0.4827, + "step": 5722 + }, + { + "epoch": 0.48, + "learning_rate": 1.1169352375659314e-05, + "loss": 0.4936, + "step": 5723 + }, + { + "epoch": 0.48, + "learning_rate": 1.1166661019127447e-05, + "loss": 0.4858, + "step": 5724 + }, + { + "epoch": 0.48, + "learning_rate": 1.1163969576920846e-05, + "loss": 0.4639, + "step": 5725 + }, + { + "epoch": 0.48, + "learning_rate": 1.1161278049237157e-05, + "loss": 0.5047, + "step": 5726 + }, + { + "epoch": 0.48, + "learning_rate": 1.1158586436274042e-05, + "loss": 0.4743, + "step": 5727 + }, + { + "epoch": 0.48, + "learning_rate": 1.1155894738229156e-05, + "loss": 0.485, + "step": 5728 + }, + { + "epoch": 0.48, + "learning_rate": 1.115320295530017e-05, + "loss": 0.4729, + "step": 5729 + }, + { + "epoch": 0.48, + "learning_rate": 1.1150511087684757e-05, + "loss": 0.4761, + "step": 5730 + }, + { + "epoch": 0.48, + "learning_rate": 1.1147819135580588e-05, + "loss": 0.4886, + "step": 5731 + }, + { + "epoch": 0.48, + "learning_rate": 1.1145127099185363e-05, + "loss": 0.4789, + "step": 5732 + }, + { + "epoch": 0.48, + "learning_rate": 1.1142434978696763e-05, + "loss": 0.495, + "step": 5733 + }, + { + "epoch": 0.48, + "learning_rate": 1.1139742774312495e-05, + "loss": 0.4717, + "step": 5734 + }, + { + "epoch": 0.48, + "learning_rate": 1.1137050486230251e-05, + "loss": 0.495, + "step": 5735 + }, + { + "epoch": 0.48, + "learning_rate": 1.1134358114647752e-05, + "loss": 0.4825, + "step": 5736 + }, + { + "epoch": 0.48, + "learning_rate": 1.1131665659762712e-05, + "loss": 0.476, + "step": 5737 + }, + { + "epoch": 0.48, + "learning_rate": 1.112897312177285e-05, + "loss": 0.4794, + "step": 5738 + }, + { + "epoch": 0.48, + "learning_rate": 1.11262805008759e-05, + "loss": 0.4632, + "step": 5739 + }, + { + "epoch": 0.48, + "learning_rate": 1.1123587797269596e-05, + "loss": 0.5031, + "step": 5740 + }, + { + "epoch": 0.48, + "learning_rate": 1.1120895011151675e-05, + "loss": 0.4687, + "step": 5741 + }, + { + "epoch": 0.48, + "learning_rate": 1.1118202142719887e-05, + "loss": 0.5017, + "step": 5742 + }, + { + "epoch": 0.48, + "learning_rate": 1.1115509192171988e-05, + "loss": 0.4941, + "step": 5743 + }, + { + "epoch": 0.48, + "learning_rate": 1.111281615970573e-05, + "loss": 0.4736, + "step": 5744 + }, + { + "epoch": 0.48, + "learning_rate": 1.1110123045518882e-05, + "loss": 0.4698, + "step": 5745 + }, + { + "epoch": 0.48, + "learning_rate": 1.1107429849809215e-05, + "loss": 0.491, + "step": 5746 + }, + { + "epoch": 0.48, + "learning_rate": 1.1104736572774506e-05, + "loss": 0.4839, + "step": 5747 + }, + { + "epoch": 0.48, + "learning_rate": 1.1102043214612539e-05, + "loss": 0.4779, + "step": 5748 + }, + { + "epoch": 0.48, + "learning_rate": 1.1099349775521103e-05, + "loss": 0.4833, + "step": 5749 + }, + { + "epoch": 0.48, + "learning_rate": 1.1096656255697991e-05, + "loss": 0.4852, + "step": 5750 + }, + { + "epoch": 0.48, + "learning_rate": 1.1093962655341002e-05, + "loss": 0.4684, + "step": 5751 + }, + { + "epoch": 0.48, + "learning_rate": 1.1091268974647947e-05, + "loss": 0.4879, + "step": 5752 + }, + { + "epoch": 0.48, + "learning_rate": 1.108857521381664e-05, + "loss": 0.4902, + "step": 5753 + }, + { + "epoch": 0.48, + "learning_rate": 1.1085881373044895e-05, + "loss": 0.4738, + "step": 5754 + }, + { + "epoch": 0.48, + "learning_rate": 1.1083187452530539e-05, + "loss": 0.4899, + "step": 5755 + }, + { + "epoch": 0.48, + "learning_rate": 1.1080493452471403e-05, + "loss": 0.4831, + "step": 5756 + }, + { + "epoch": 0.48, + "learning_rate": 1.1077799373065321e-05, + "loss": 0.4738, + "step": 5757 + }, + { + "epoch": 0.48, + "learning_rate": 1.1075105214510135e-05, + "loss": 0.4864, + "step": 5758 + }, + { + "epoch": 0.48, + "learning_rate": 1.1072410977003693e-05, + "loss": 0.4776, + "step": 5759 + }, + { + "epoch": 0.48, + "learning_rate": 1.1069716660743852e-05, + "loss": 0.4847, + "step": 5760 + }, + { + "epoch": 0.48, + "learning_rate": 1.1067022265928472e-05, + "loss": 0.482, + "step": 5761 + }, + { + "epoch": 0.48, + "learning_rate": 1.1064327792755405e-05, + "loss": 0.4857, + "step": 5762 + }, + { + "epoch": 0.48, + "learning_rate": 1.1061633241422538e-05, + "loss": 0.4833, + "step": 5763 + }, + { + "epoch": 0.48, + "learning_rate": 1.1058938612127744e-05, + "loss": 0.4706, + "step": 5764 + }, + { + "epoch": 0.48, + "learning_rate": 1.1056243905068899e-05, + "loss": 0.481, + "step": 5765 + }, + { + "epoch": 0.48, + "learning_rate": 1.1053549120443893e-05, + "loss": 0.4646, + "step": 5766 + }, + { + "epoch": 0.48, + "learning_rate": 1.1050854258450623e-05, + "loss": 0.4928, + "step": 5767 + }, + { + "epoch": 0.48, + "learning_rate": 1.104815931928699e-05, + "loss": 0.4864, + "step": 5768 + }, + { + "epoch": 0.48, + "learning_rate": 1.1045464303150892e-05, + "loss": 0.4873, + "step": 5769 + }, + { + "epoch": 0.48, + "learning_rate": 1.1042769210240248e-05, + "loss": 0.4881, + "step": 5770 + }, + { + "epoch": 0.48, + "learning_rate": 1.1040074040752971e-05, + "loss": 0.4759, + "step": 5771 + }, + { + "epoch": 0.48, + "learning_rate": 1.1037378794886977e-05, + "loss": 0.4723, + "step": 5772 + }, + { + "epoch": 0.48, + "learning_rate": 1.1034683472840201e-05, + "loss": 0.468, + "step": 5773 + }, + { + "epoch": 0.48, + "learning_rate": 1.1031988074810578e-05, + "loss": 0.4803, + "step": 5774 + }, + { + "epoch": 0.48, + "learning_rate": 1.1029292600996042e-05, + "loss": 0.5059, + "step": 5775 + }, + { + "epoch": 0.48, + "learning_rate": 1.1026597051594534e-05, + "loss": 0.4792, + "step": 5776 + }, + { + "epoch": 0.48, + "learning_rate": 1.102390142680401e-05, + "loss": 0.4762, + "step": 5777 + }, + { + "epoch": 0.48, + "learning_rate": 1.1021205726822429e-05, + "loss": 0.4988, + "step": 5778 + }, + { + "epoch": 0.48, + "learning_rate": 1.1018509951847743e-05, + "loss": 0.4742, + "step": 5779 + }, + { + "epoch": 0.48, + "learning_rate": 1.1015814102077921e-05, + "loss": 0.4762, + "step": 5780 + }, + { + "epoch": 0.48, + "learning_rate": 1.1013118177710942e-05, + "loss": 0.4947, + "step": 5781 + }, + { + "epoch": 0.48, + "learning_rate": 1.1010422178944772e-05, + "loss": 0.4727, + "step": 5782 + }, + { + "epoch": 0.48, + "learning_rate": 1.10077261059774e-05, + "loss": 0.4662, + "step": 5783 + }, + { + "epoch": 0.48, + "learning_rate": 1.1005029959006818e-05, + "loss": 0.4927, + "step": 5784 + }, + { + "epoch": 0.48, + "learning_rate": 1.1002333738231016e-05, + "loss": 0.4872, + "step": 5785 + }, + { + "epoch": 0.48, + "learning_rate": 1.099963744384799e-05, + "loss": 0.4899, + "step": 5786 + }, + { + "epoch": 0.48, + "learning_rate": 1.0996941076055751e-05, + "loss": 0.4824, + "step": 5787 + }, + { + "epoch": 0.48, + "learning_rate": 1.0994244635052304e-05, + "loss": 0.4645, + "step": 5788 + }, + { + "epoch": 0.48, + "learning_rate": 1.0991548121035664e-05, + "loss": 0.4843, + "step": 5789 + }, + { + "epoch": 0.48, + "learning_rate": 1.098885153420386e-05, + "loss": 0.4767, + "step": 5790 + }, + { + "epoch": 0.48, + "learning_rate": 1.098615487475491e-05, + "loss": 0.4897, + "step": 5791 + }, + { + "epoch": 0.48, + "learning_rate": 1.0983458142886848e-05, + "loss": 0.4754, + "step": 5792 + }, + { + "epoch": 0.48, + "learning_rate": 1.0980761338797707e-05, + "loss": 0.4671, + "step": 5793 + }, + { + "epoch": 0.48, + "learning_rate": 1.0978064462685536e-05, + "loss": 0.4932, + "step": 5794 + }, + { + "epoch": 0.48, + "learning_rate": 1.0975367514748378e-05, + "loss": 0.4822, + "step": 5795 + }, + { + "epoch": 0.48, + "learning_rate": 1.0972670495184286e-05, + "loss": 0.5096, + "step": 5796 + }, + { + "epoch": 0.49, + "learning_rate": 1.0969973404191322e-05, + "loss": 0.5035, + "step": 5797 + }, + { + "epoch": 0.49, + "learning_rate": 1.096727624196754e-05, + "loss": 0.4778, + "step": 5798 + }, + { + "epoch": 0.49, + "learning_rate": 1.0964579008711018e-05, + "loss": 0.4801, + "step": 5799 + }, + { + "epoch": 0.49, + "learning_rate": 1.0961881704619823e-05, + "loss": 0.4845, + "step": 5800 + }, + { + "epoch": 0.49, + "learning_rate": 1.095918432989204e-05, + "loss": 0.4793, + "step": 5801 + }, + { + "epoch": 0.49, + "learning_rate": 1.0956486884725748e-05, + "loss": 0.4717, + "step": 5802 + }, + { + "epoch": 0.49, + "learning_rate": 1.0953789369319031e-05, + "loss": 0.4756, + "step": 5803 + }, + { + "epoch": 0.49, + "learning_rate": 1.0951091783869998e-05, + "loss": 0.485, + "step": 5804 + }, + { + "epoch": 0.49, + "learning_rate": 1.0948394128576739e-05, + "loss": 0.496, + "step": 5805 + }, + { + "epoch": 0.49, + "learning_rate": 1.094569640363736e-05, + "loss": 0.4963, + "step": 5806 + }, + { + "epoch": 0.49, + "learning_rate": 1.0942998609249968e-05, + "loss": 0.4884, + "step": 5807 + }, + { + "epoch": 0.49, + "learning_rate": 1.0940300745612679e-05, + "loss": 0.4687, + "step": 5808 + }, + { + "epoch": 0.49, + "learning_rate": 1.0937602812923617e-05, + "loss": 0.4779, + "step": 5809 + }, + { + "epoch": 0.49, + "learning_rate": 1.0934904811380904e-05, + "loss": 0.4892, + "step": 5810 + }, + { + "epoch": 0.49, + "learning_rate": 1.0932206741182672e-05, + "loss": 0.4831, + "step": 5811 + }, + { + "epoch": 0.49, + "learning_rate": 1.0929508602527052e-05, + "loss": 0.4711, + "step": 5812 + }, + { + "epoch": 0.49, + "learning_rate": 1.0926810395612187e-05, + "loss": 0.4934, + "step": 5813 + }, + { + "epoch": 0.49, + "learning_rate": 1.0924112120636222e-05, + "loss": 0.48, + "step": 5814 + }, + { + "epoch": 0.49, + "learning_rate": 1.0921413777797305e-05, + "loss": 0.4744, + "step": 5815 + }, + { + "epoch": 0.49, + "learning_rate": 1.0918715367293595e-05, + "loss": 0.4796, + "step": 5816 + }, + { + "epoch": 0.49, + "learning_rate": 1.0916016889323246e-05, + "loss": 0.4669, + "step": 5817 + }, + { + "epoch": 0.49, + "learning_rate": 1.0913318344084428e-05, + "loss": 0.4656, + "step": 5818 + }, + { + "epoch": 0.49, + "learning_rate": 1.0910619731775311e-05, + "loss": 0.4658, + "step": 5819 + }, + { + "epoch": 0.49, + "learning_rate": 1.0907921052594066e-05, + "loss": 0.4817, + "step": 5820 + }, + { + "epoch": 0.49, + "learning_rate": 1.0905222306738879e-05, + "loss": 0.4862, + "step": 5821 + }, + { + "epoch": 0.49, + "learning_rate": 1.0902523494407928e-05, + "loss": 0.4828, + "step": 5822 + }, + { + "epoch": 0.49, + "learning_rate": 1.0899824615799406e-05, + "loss": 0.4725, + "step": 5823 + }, + { + "epoch": 0.49, + "learning_rate": 1.0897125671111507e-05, + "loss": 0.4827, + "step": 5824 + }, + { + "epoch": 0.49, + "learning_rate": 1.089442666054243e-05, + "loss": 0.4902, + "step": 5825 + }, + { + "epoch": 0.49, + "learning_rate": 1.0891727584290381e-05, + "loss": 0.465, + "step": 5826 + }, + { + "epoch": 0.49, + "learning_rate": 1.0889028442553565e-05, + "loss": 0.4795, + "step": 5827 + }, + { + "epoch": 0.49, + "learning_rate": 1.08863292355302e-05, + "loss": 0.4693, + "step": 5828 + }, + { + "epoch": 0.49, + "learning_rate": 1.0883629963418501e-05, + "loss": 0.4781, + "step": 5829 + }, + { + "epoch": 0.49, + "learning_rate": 1.088093062641669e-05, + "loss": 0.5004, + "step": 5830 + }, + { + "epoch": 0.49, + "learning_rate": 1.0878231224723001e-05, + "loss": 0.4815, + "step": 5831 + }, + { + "epoch": 0.49, + "learning_rate": 1.0875531758535668e-05, + "loss": 0.4879, + "step": 5832 + }, + { + "epoch": 0.49, + "learning_rate": 1.0872832228052919e-05, + "loss": 0.4919, + "step": 5833 + }, + { + "epoch": 0.49, + "learning_rate": 1.0870132633472999e-05, + "loss": 0.5049, + "step": 5834 + }, + { + "epoch": 0.49, + "learning_rate": 1.0867432974994162e-05, + "loss": 0.4874, + "step": 5835 + }, + { + "epoch": 0.49, + "learning_rate": 1.0864733252814654e-05, + "loss": 0.4906, + "step": 5836 + }, + { + "epoch": 0.49, + "learning_rate": 1.0862033467132732e-05, + "loss": 0.4875, + "step": 5837 + }, + { + "epoch": 0.49, + "learning_rate": 1.0859333618146659e-05, + "loss": 0.4617, + "step": 5838 + }, + { + "epoch": 0.49, + "learning_rate": 1.0856633706054698e-05, + "loss": 0.4761, + "step": 5839 + }, + { + "epoch": 0.49, + "learning_rate": 1.0853933731055122e-05, + "loss": 0.4735, + "step": 5840 + }, + { + "epoch": 0.49, + "learning_rate": 1.0851233693346204e-05, + "loss": 0.4843, + "step": 5841 + }, + { + "epoch": 0.49, + "learning_rate": 1.0848533593126225e-05, + "loss": 0.4845, + "step": 5842 + }, + { + "epoch": 0.49, + "learning_rate": 1.0845833430593467e-05, + "loss": 0.4731, + "step": 5843 + }, + { + "epoch": 0.49, + "learning_rate": 1.0843133205946218e-05, + "loss": 0.4897, + "step": 5844 + }, + { + "epoch": 0.49, + "learning_rate": 1.0840432919382774e-05, + "loss": 0.501, + "step": 5845 + }, + { + "epoch": 0.49, + "learning_rate": 1.0837732571101437e-05, + "loss": 0.4934, + "step": 5846 + }, + { + "epoch": 0.49, + "learning_rate": 1.0835032161300499e-05, + "loss": 0.4878, + "step": 5847 + }, + { + "epoch": 0.49, + "learning_rate": 1.0832331690178274e-05, + "loss": 0.4885, + "step": 5848 + }, + { + "epoch": 0.49, + "learning_rate": 1.0829631157933071e-05, + "loss": 0.4741, + "step": 5849 + }, + { + "epoch": 0.49, + "learning_rate": 1.0826930564763207e-05, + "loss": 0.5027, + "step": 5850 + }, + { + "epoch": 0.49, + "learning_rate": 1.0824229910867002e-05, + "loss": 0.4769, + "step": 5851 + }, + { + "epoch": 0.49, + "learning_rate": 1.0821529196442782e-05, + "loss": 0.4863, + "step": 5852 + }, + { + "epoch": 0.49, + "learning_rate": 1.0818828421688873e-05, + "loss": 0.4707, + "step": 5853 + }, + { + "epoch": 0.49, + "learning_rate": 1.081612758680361e-05, + "loss": 0.4718, + "step": 5854 + }, + { + "epoch": 0.49, + "learning_rate": 1.0813426691985331e-05, + "loss": 0.469, + "step": 5855 + }, + { + "epoch": 0.49, + "learning_rate": 1.0810725737432381e-05, + "loss": 0.4993, + "step": 5856 + }, + { + "epoch": 0.49, + "learning_rate": 1.0808024723343104e-05, + "loss": 0.4695, + "step": 5857 + }, + { + "epoch": 0.49, + "learning_rate": 1.0805323649915854e-05, + "loss": 0.4555, + "step": 5858 + }, + { + "epoch": 0.49, + "learning_rate": 1.0802622517348982e-05, + "loss": 0.4673, + "step": 5859 + }, + { + "epoch": 0.49, + "learning_rate": 1.0799921325840851e-05, + "loss": 0.4788, + "step": 5860 + }, + { + "epoch": 0.49, + "learning_rate": 1.0797220075589825e-05, + "loss": 0.4518, + "step": 5861 + }, + { + "epoch": 0.49, + "learning_rate": 1.0794518766794272e-05, + "loss": 0.4822, + "step": 5862 + }, + { + "epoch": 0.49, + "learning_rate": 1.079181739965257e-05, + "loss": 0.4787, + "step": 5863 + }, + { + "epoch": 0.49, + "learning_rate": 1.0789115974363086e-05, + "loss": 0.4897, + "step": 5864 + }, + { + "epoch": 0.49, + "learning_rate": 1.0786414491124208e-05, + "loss": 0.4997, + "step": 5865 + }, + { + "epoch": 0.49, + "learning_rate": 1.0783712950134324e-05, + "loss": 0.4807, + "step": 5866 + }, + { + "epoch": 0.49, + "learning_rate": 1.0781011351591819e-05, + "loss": 0.4609, + "step": 5867 + }, + { + "epoch": 0.49, + "learning_rate": 1.0778309695695088e-05, + "loss": 0.4857, + "step": 5868 + }, + { + "epoch": 0.49, + "learning_rate": 1.077560798264253e-05, + "loss": 0.4819, + "step": 5869 + }, + { + "epoch": 0.49, + "learning_rate": 1.0772906212632547e-05, + "loss": 0.4784, + "step": 5870 + }, + { + "epoch": 0.49, + "learning_rate": 1.0770204385863547e-05, + "loss": 0.4976, + "step": 5871 + }, + { + "epoch": 0.49, + "learning_rate": 1.0767502502533945e-05, + "loss": 0.473, + "step": 5872 + }, + { + "epoch": 0.49, + "learning_rate": 1.0764800562842149e-05, + "loss": 0.4696, + "step": 5873 + }, + { + "epoch": 0.49, + "learning_rate": 1.0762098566986578e-05, + "loss": 0.4932, + "step": 5874 + }, + { + "epoch": 0.49, + "learning_rate": 1.0759396515165657e-05, + "loss": 0.4942, + "step": 5875 + }, + { + "epoch": 0.49, + "learning_rate": 1.075669440757782e-05, + "loss": 0.4632, + "step": 5876 + }, + { + "epoch": 0.49, + "learning_rate": 1.075399224442149e-05, + "loss": 0.477, + "step": 5877 + }, + { + "epoch": 0.49, + "learning_rate": 1.0751290025895104e-05, + "loss": 0.49, + "step": 5878 + }, + { + "epoch": 0.49, + "learning_rate": 1.0748587752197106e-05, + "loss": 0.4698, + "step": 5879 + }, + { + "epoch": 0.49, + "learning_rate": 1.0745885423525934e-05, + "loss": 0.4739, + "step": 5880 + }, + { + "epoch": 0.49, + "learning_rate": 1.0743183040080043e-05, + "loss": 0.4757, + "step": 5881 + }, + { + "epoch": 0.49, + "learning_rate": 1.0740480602057877e-05, + "loss": 0.4677, + "step": 5882 + }, + { + "epoch": 0.49, + "learning_rate": 1.0737778109657899e-05, + "loss": 0.4867, + "step": 5883 + }, + { + "epoch": 0.49, + "learning_rate": 1.0735075563078565e-05, + "loss": 0.4678, + "step": 5884 + }, + { + "epoch": 0.49, + "learning_rate": 1.0732372962518337e-05, + "loss": 0.4661, + "step": 5885 + }, + { + "epoch": 0.49, + "learning_rate": 1.0729670308175683e-05, + "loss": 0.4743, + "step": 5886 + }, + { + "epoch": 0.49, + "learning_rate": 1.072696760024908e-05, + "loss": 0.4877, + "step": 5887 + }, + { + "epoch": 0.49, + "learning_rate": 1.0724264838936998e-05, + "loss": 0.4869, + "step": 5888 + }, + { + "epoch": 0.49, + "learning_rate": 1.0721562024437919e-05, + "loss": 0.4722, + "step": 5889 + }, + { + "epoch": 0.49, + "learning_rate": 1.0718859156950329e-05, + "loss": 0.4959, + "step": 5890 + }, + { + "epoch": 0.49, + "learning_rate": 1.071615623667271e-05, + "loss": 0.4653, + "step": 5891 + }, + { + "epoch": 0.49, + "learning_rate": 1.0713453263803553e-05, + "loss": 0.4606, + "step": 5892 + }, + { + "epoch": 0.49, + "learning_rate": 1.071075023854136e-05, + "loss": 0.49, + "step": 5893 + }, + { + "epoch": 0.49, + "learning_rate": 1.0708047161084626e-05, + "loss": 0.4895, + "step": 5894 + }, + { + "epoch": 0.49, + "learning_rate": 1.070534403163185e-05, + "loss": 0.4806, + "step": 5895 + }, + { + "epoch": 0.49, + "learning_rate": 1.0702640850381542e-05, + "loss": 0.4713, + "step": 5896 + }, + { + "epoch": 0.49, + "learning_rate": 1.0699937617532216e-05, + "loss": 0.4832, + "step": 5897 + }, + { + "epoch": 0.49, + "learning_rate": 1.0697234333282382e-05, + "loss": 0.4784, + "step": 5898 + }, + { + "epoch": 0.49, + "learning_rate": 1.0694530997830556e-05, + "loss": 0.4696, + "step": 5899 + }, + { + "epoch": 0.49, + "learning_rate": 1.0691827611375268e-05, + "loss": 0.5059, + "step": 5900 + }, + { + "epoch": 0.49, + "learning_rate": 1.068912417411503e-05, + "loss": 0.4705, + "step": 5901 + }, + { + "epoch": 0.49, + "learning_rate": 1.0686420686248382e-05, + "loss": 0.4696, + "step": 5902 + }, + { + "epoch": 0.49, + "learning_rate": 1.0683717147973856e-05, + "loss": 0.4935, + "step": 5903 + }, + { + "epoch": 0.49, + "learning_rate": 1.0681013559489985e-05, + "loss": 0.4837, + "step": 5904 + }, + { + "epoch": 0.49, + "learning_rate": 1.067830992099531e-05, + "loss": 0.4748, + "step": 5905 + }, + { + "epoch": 0.49, + "learning_rate": 1.0675606232688377e-05, + "loss": 0.4827, + "step": 5906 + }, + { + "epoch": 0.49, + "learning_rate": 1.0672902494767731e-05, + "loss": 0.5115, + "step": 5907 + }, + { + "epoch": 0.49, + "learning_rate": 1.0670198707431927e-05, + "loss": 0.4813, + "step": 5908 + }, + { + "epoch": 0.49, + "learning_rate": 1.0667494870879513e-05, + "loss": 0.4771, + "step": 5909 + }, + { + "epoch": 0.49, + "learning_rate": 1.0664790985309058e-05, + "loss": 0.5049, + "step": 5910 + }, + { + "epoch": 0.49, + "learning_rate": 1.0662087050919111e-05, + "loss": 0.4861, + "step": 5911 + }, + { + "epoch": 0.49, + "learning_rate": 1.065938306790825e-05, + "loss": 0.4752, + "step": 5912 + }, + { + "epoch": 0.49, + "learning_rate": 1.0656679036475038e-05, + "loss": 0.4789, + "step": 5913 + }, + { + "epoch": 0.49, + "learning_rate": 1.065397495681805e-05, + "loss": 0.4715, + "step": 5914 + }, + { + "epoch": 0.49, + "learning_rate": 1.065127082913586e-05, + "loss": 0.4669, + "step": 5915 + }, + { + "epoch": 0.49, + "learning_rate": 1.0648566653627048e-05, + "loss": 0.4878, + "step": 5916 + }, + { + "epoch": 0.5, + "learning_rate": 1.06458624304902e-05, + "loss": 0.4657, + "step": 5917 + }, + { + "epoch": 0.5, + "learning_rate": 1.0643158159923902e-05, + "loss": 0.4867, + "step": 5918 + }, + { + "epoch": 0.5, + "learning_rate": 1.0640453842126742e-05, + "loss": 0.4842, + "step": 5919 + }, + { + "epoch": 0.5, + "learning_rate": 1.0637749477297317e-05, + "loss": 0.4846, + "step": 5920 + }, + { + "epoch": 0.5, + "learning_rate": 1.063504506563422e-05, + "loss": 0.4753, + "step": 5921 + }, + { + "epoch": 0.5, + "learning_rate": 1.0632340607336056e-05, + "loss": 0.4803, + "step": 5922 + }, + { + "epoch": 0.5, + "learning_rate": 1.062963610260143e-05, + "loss": 0.4649, + "step": 5923 + }, + { + "epoch": 0.5, + "learning_rate": 1.0626931551628948e-05, + "loss": 0.5102, + "step": 5924 + }, + { + "epoch": 0.5, + "learning_rate": 1.0624226954617221e-05, + "loss": 0.4758, + "step": 5925 + }, + { + "epoch": 0.5, + "learning_rate": 1.0621522311764857e-05, + "loss": 0.4701, + "step": 5926 + }, + { + "epoch": 0.5, + "learning_rate": 1.0618817623270484e-05, + "loss": 0.4919, + "step": 5927 + }, + { + "epoch": 0.5, + "learning_rate": 1.061611288933272e-05, + "loss": 0.5002, + "step": 5928 + }, + { + "epoch": 0.5, + "learning_rate": 1.0613408110150185e-05, + "loss": 0.4994, + "step": 5929 + }, + { + "epoch": 0.5, + "learning_rate": 1.061070328592151e-05, + "loss": 0.4734, + "step": 5930 + }, + { + "epoch": 0.5, + "learning_rate": 1.0607998416845329e-05, + "loss": 0.4737, + "step": 5931 + }, + { + "epoch": 0.5, + "learning_rate": 1.0605293503120268e-05, + "loss": 0.4695, + "step": 5932 + }, + { + "epoch": 0.5, + "learning_rate": 1.0602588544944972e-05, + "loss": 0.4705, + "step": 5933 + }, + { + "epoch": 0.5, + "learning_rate": 1.059988354251808e-05, + "loss": 0.4683, + "step": 5934 + }, + { + "epoch": 0.5, + "learning_rate": 1.059717849603824e-05, + "loss": 0.4895, + "step": 5935 + }, + { + "epoch": 0.5, + "learning_rate": 1.0594473405704088e-05, + "loss": 0.4732, + "step": 5936 + }, + { + "epoch": 0.5, + "learning_rate": 1.0591768271714285e-05, + "loss": 0.4844, + "step": 5937 + }, + { + "epoch": 0.5, + "learning_rate": 1.058906309426748e-05, + "loss": 0.4746, + "step": 5938 + }, + { + "epoch": 0.5, + "learning_rate": 1.0586357873562332e-05, + "loss": 0.4765, + "step": 5939 + }, + { + "epoch": 0.5, + "learning_rate": 1.0583652609797501e-05, + "loss": 0.4753, + "step": 5940 + }, + { + "epoch": 0.5, + "learning_rate": 1.0580947303171651e-05, + "loss": 0.4755, + "step": 5941 + }, + { + "epoch": 0.5, + "learning_rate": 1.0578241953883445e-05, + "loss": 0.4855, + "step": 5942 + }, + { + "epoch": 0.5, + "learning_rate": 1.0575536562131556e-05, + "loss": 0.4863, + "step": 5943 + }, + { + "epoch": 0.5, + "learning_rate": 1.0572831128114658e-05, + "loss": 0.4672, + "step": 5944 + }, + { + "epoch": 0.5, + "learning_rate": 1.0570125652031425e-05, + "loss": 0.4928, + "step": 5945 + }, + { + "epoch": 0.5, + "learning_rate": 1.0567420134080531e-05, + "loss": 0.4896, + "step": 5946 + }, + { + "epoch": 0.5, + "learning_rate": 1.0564714574460664e-05, + "loss": 0.4839, + "step": 5947 + }, + { + "epoch": 0.5, + "learning_rate": 1.0562008973370508e-05, + "loss": 0.4808, + "step": 5948 + }, + { + "epoch": 0.5, + "learning_rate": 1.0559303331008752e-05, + "loss": 0.4783, + "step": 5949 + }, + { + "epoch": 0.5, + "learning_rate": 1.0556597647574083e-05, + "loss": 0.4887, + "step": 5950 + }, + { + "epoch": 0.5, + "learning_rate": 1.05538919232652e-05, + "loss": 0.4867, + "step": 5951 + }, + { + "epoch": 0.5, + "learning_rate": 1.0551186158280795e-05, + "loss": 0.5122, + "step": 5952 + }, + { + "epoch": 0.5, + "learning_rate": 1.0548480352819573e-05, + "loss": 0.4623, + "step": 5953 + }, + { + "epoch": 0.5, + "learning_rate": 1.0545774507080237e-05, + "loss": 0.4677, + "step": 5954 + }, + { + "epoch": 0.5, + "learning_rate": 1.054306862126149e-05, + "loss": 0.4772, + "step": 5955 + }, + { + "epoch": 0.5, + "learning_rate": 1.0540362695562043e-05, + "loss": 0.4747, + "step": 5956 + }, + { + "epoch": 0.5, + "learning_rate": 1.0537656730180606e-05, + "loss": 0.4751, + "step": 5957 + }, + { + "epoch": 0.5, + "learning_rate": 1.0534950725315893e-05, + "loss": 0.4904, + "step": 5958 + }, + { + "epoch": 0.5, + "learning_rate": 1.0532244681166628e-05, + "loss": 0.4845, + "step": 5959 + }, + { + "epoch": 0.5, + "learning_rate": 1.0529538597931524e-05, + "loss": 0.4788, + "step": 5960 + }, + { + "epoch": 0.5, + "learning_rate": 1.052683247580931e-05, + "loss": 0.4771, + "step": 5961 + }, + { + "epoch": 0.5, + "learning_rate": 1.0524126314998711e-05, + "loss": 0.4895, + "step": 5962 + }, + { + "epoch": 0.5, + "learning_rate": 1.0521420115698448e-05, + "loss": 0.4743, + "step": 5963 + }, + { + "epoch": 0.5, + "learning_rate": 1.0518713878107268e-05, + "loss": 0.4543, + "step": 5964 + }, + { + "epoch": 0.5, + "learning_rate": 1.0516007602423896e-05, + "loss": 0.4893, + "step": 5965 + }, + { + "epoch": 0.5, + "learning_rate": 1.0513301288847076e-05, + "loss": 0.4831, + "step": 5966 + }, + { + "epoch": 0.5, + "learning_rate": 1.0510594937575537e-05, + "loss": 0.4739, + "step": 5967 + }, + { + "epoch": 0.5, + "learning_rate": 1.0507888548808034e-05, + "loss": 0.4901, + "step": 5968 + }, + { + "epoch": 0.5, + "learning_rate": 1.0505182122743309e-05, + "loss": 0.4903, + "step": 5969 + }, + { + "epoch": 0.5, + "learning_rate": 1.0502475659580107e-05, + "loss": 0.4827, + "step": 5970 + }, + { + "epoch": 0.5, + "learning_rate": 1.0499769159517186e-05, + "loss": 0.4875, + "step": 5971 + }, + { + "epoch": 0.5, + "learning_rate": 1.0497062622753296e-05, + "loss": 0.4978, + "step": 5972 + }, + { + "epoch": 0.5, + "learning_rate": 1.049435604948719e-05, + "loss": 0.4832, + "step": 5973 + }, + { + "epoch": 0.5, + "learning_rate": 1.0491649439917636e-05, + "loss": 0.4586, + "step": 5974 + }, + { + "epoch": 0.5, + "learning_rate": 1.0488942794243393e-05, + "loss": 0.4639, + "step": 5975 + }, + { + "epoch": 0.5, + "learning_rate": 1.0486236112663224e-05, + "loss": 0.4936, + "step": 5976 + }, + { + "epoch": 0.5, + "learning_rate": 1.0483529395375896e-05, + "loss": 0.4603, + "step": 5977 + }, + { + "epoch": 0.5, + "learning_rate": 1.0480822642580178e-05, + "loss": 0.4836, + "step": 5978 + }, + { + "epoch": 0.5, + "learning_rate": 1.0478115854474848e-05, + "loss": 0.5113, + "step": 5979 + }, + { + "epoch": 0.5, + "learning_rate": 1.0475409031258678e-05, + "loss": 0.4747, + "step": 5980 + }, + { + "epoch": 0.5, + "learning_rate": 1.0472702173130447e-05, + "loss": 0.4841, + "step": 5981 + }, + { + "epoch": 0.5, + "learning_rate": 1.0469995280288936e-05, + "loss": 0.4726, + "step": 5982 + }, + { + "epoch": 0.5, + "learning_rate": 1.0467288352932923e-05, + "loss": 0.47, + "step": 5983 + }, + { + "epoch": 0.5, + "learning_rate": 1.0464581391261198e-05, + "loss": 0.4819, + "step": 5984 + }, + { + "epoch": 0.5, + "learning_rate": 1.0461874395472549e-05, + "loss": 0.4767, + "step": 5985 + }, + { + "epoch": 0.5, + "learning_rate": 1.0459167365765765e-05, + "loss": 0.4681, + "step": 5986 + }, + { + "epoch": 0.5, + "learning_rate": 1.0456460302339636e-05, + "loss": 0.4776, + "step": 5987 + }, + { + "epoch": 0.5, + "learning_rate": 1.0453753205392967e-05, + "loss": 0.4719, + "step": 5988 + }, + { + "epoch": 0.5, + "learning_rate": 1.0451046075124544e-05, + "loss": 0.4728, + "step": 5989 + }, + { + "epoch": 0.5, + "learning_rate": 1.0448338911733178e-05, + "loss": 0.4883, + "step": 5990 + }, + { + "epoch": 0.5, + "learning_rate": 1.0445631715417666e-05, + "loss": 0.5035, + "step": 5991 + }, + { + "epoch": 0.5, + "learning_rate": 1.0442924486376813e-05, + "loss": 0.4744, + "step": 5992 + }, + { + "epoch": 0.5, + "learning_rate": 1.0440217224809427e-05, + "loss": 0.498, + "step": 5993 + }, + { + "epoch": 0.5, + "learning_rate": 1.043750993091432e-05, + "loss": 0.4707, + "step": 5994 + }, + { + "epoch": 0.5, + "learning_rate": 1.0434802604890306e-05, + "loss": 0.4854, + "step": 5995 + }, + { + "epoch": 0.5, + "learning_rate": 1.0432095246936195e-05, + "loss": 0.4768, + "step": 5996 + }, + { + "epoch": 0.5, + "learning_rate": 1.0429387857250806e-05, + "loss": 0.4729, + "step": 5997 + }, + { + "epoch": 0.5, + "learning_rate": 1.042668043603296e-05, + "loss": 0.483, + "step": 5998 + }, + { + "epoch": 0.5, + "learning_rate": 1.0423972983481477e-05, + "loss": 0.4757, + "step": 5999 + }, + { + "epoch": 0.5, + "learning_rate": 1.0421265499795181e-05, + "loss": 0.4865, + "step": 6000 + }, + { + "epoch": 0.5, + "learning_rate": 1.0418557985172899e-05, + "loss": 0.4946, + "step": 6001 + }, + { + "epoch": 0.5, + "learning_rate": 1.0415850439813462e-05, + "loss": 0.4533, + "step": 6002 + }, + { + "epoch": 0.5, + "learning_rate": 1.0413142863915695e-05, + "loss": 0.4847, + "step": 6003 + }, + { + "epoch": 0.5, + "learning_rate": 1.0410435257678433e-05, + "loss": 0.4828, + "step": 6004 + }, + { + "epoch": 0.5, + "learning_rate": 1.0407727621300516e-05, + "loss": 0.4671, + "step": 6005 + }, + { + "epoch": 0.5, + "learning_rate": 1.0405019954980779e-05, + "loss": 0.4716, + "step": 6006 + }, + { + "epoch": 0.5, + "learning_rate": 1.0402312258918061e-05, + "loss": 0.4786, + "step": 6007 + }, + { + "epoch": 0.5, + "learning_rate": 1.03996045333112e-05, + "loss": 0.4873, + "step": 6008 + }, + { + "epoch": 0.5, + "learning_rate": 1.0396896778359047e-05, + "loss": 0.479, + "step": 6009 + }, + { + "epoch": 0.5, + "learning_rate": 1.0394188994260445e-05, + "loss": 0.463, + "step": 6010 + }, + { + "epoch": 0.5, + "learning_rate": 1.0391481181214244e-05, + "loss": 0.4551, + "step": 6011 + }, + { + "epoch": 0.5, + "learning_rate": 1.0388773339419294e-05, + "loss": 0.4634, + "step": 6012 + }, + { + "epoch": 0.5, + "learning_rate": 1.0386065469074447e-05, + "loss": 0.4834, + "step": 6013 + }, + { + "epoch": 0.5, + "learning_rate": 1.0383357570378553e-05, + "loss": 0.4901, + "step": 6014 + }, + { + "epoch": 0.5, + "learning_rate": 1.0380649643530476e-05, + "loss": 0.4779, + "step": 6015 + }, + { + "epoch": 0.5, + "learning_rate": 1.0377941688729074e-05, + "loss": 0.4925, + "step": 6016 + }, + { + "epoch": 0.5, + "learning_rate": 1.0375233706173207e-05, + "loss": 0.4912, + "step": 6017 + }, + { + "epoch": 0.5, + "learning_rate": 1.0372525696061735e-05, + "loss": 0.4781, + "step": 6018 + }, + { + "epoch": 0.5, + "learning_rate": 1.0369817658593524e-05, + "loss": 0.4854, + "step": 6019 + }, + { + "epoch": 0.5, + "learning_rate": 1.0367109593967445e-05, + "loss": 0.4858, + "step": 6020 + }, + { + "epoch": 0.5, + "learning_rate": 1.0364401502382364e-05, + "loss": 0.4811, + "step": 6021 + }, + { + "epoch": 0.5, + "learning_rate": 1.0361693384037154e-05, + "loss": 0.4865, + "step": 6022 + }, + { + "epoch": 0.5, + "learning_rate": 1.0358985239130685e-05, + "loss": 0.4867, + "step": 6023 + }, + { + "epoch": 0.5, + "learning_rate": 1.035627706786183e-05, + "loss": 0.4796, + "step": 6024 + }, + { + "epoch": 0.5, + "learning_rate": 1.035356887042947e-05, + "loss": 0.486, + "step": 6025 + }, + { + "epoch": 0.5, + "learning_rate": 1.0350860647032488e-05, + "loss": 0.4733, + "step": 6026 + }, + { + "epoch": 0.5, + "learning_rate": 1.0348152397869757e-05, + "loss": 0.4706, + "step": 6027 + }, + { + "epoch": 0.5, + "learning_rate": 1.0345444123140159e-05, + "loss": 0.4709, + "step": 6028 + }, + { + "epoch": 0.5, + "learning_rate": 1.0342735823042585e-05, + "loss": 0.4718, + "step": 6029 + }, + { + "epoch": 0.5, + "learning_rate": 1.0340027497775915e-05, + "loss": 0.476, + "step": 6030 + }, + { + "epoch": 0.5, + "learning_rate": 1.0337319147539042e-05, + "loss": 0.4838, + "step": 6031 + }, + { + "epoch": 0.5, + "learning_rate": 1.0334610772530851e-05, + "loss": 0.4914, + "step": 6032 + }, + { + "epoch": 0.5, + "learning_rate": 1.033190237295024e-05, + "loss": 0.4516, + "step": 6033 + }, + { + "epoch": 0.5, + "learning_rate": 1.0329193948996097e-05, + "loss": 0.4834, + "step": 6034 + }, + { + "epoch": 0.5, + "learning_rate": 1.0326485500867316e-05, + "loss": 0.4735, + "step": 6035 + }, + { + "epoch": 0.5, + "learning_rate": 1.0323777028762804e-05, + "loss": 0.4786, + "step": 6036 + }, + { + "epoch": 0.51, + "learning_rate": 1.0321068532881454e-05, + "loss": 0.4708, + "step": 6037 + }, + { + "epoch": 0.51, + "learning_rate": 1.0318360013422162e-05, + "loss": 0.5103, + "step": 6038 + }, + { + "epoch": 0.51, + "learning_rate": 1.0315651470583836e-05, + "loss": 0.5011, + "step": 6039 + }, + { + "epoch": 0.51, + "learning_rate": 1.0312942904565379e-05, + "loss": 0.4685, + "step": 6040 + }, + { + "epoch": 0.51, + "learning_rate": 1.0310234315565699e-05, + "loss": 0.4897, + "step": 6041 + }, + { + "epoch": 0.51, + "learning_rate": 1.0307525703783698e-05, + "loss": 0.489, + "step": 6042 + }, + { + "epoch": 0.51, + "learning_rate": 1.0304817069418292e-05, + "loss": 0.4754, + "step": 6043 + }, + { + "epoch": 0.51, + "learning_rate": 1.0302108412668387e-05, + "loss": 0.4889, + "step": 6044 + }, + { + "epoch": 0.51, + "learning_rate": 1.0299399733732893e-05, + "loss": 0.4967, + "step": 6045 + }, + { + "epoch": 0.51, + "learning_rate": 1.029669103281073e-05, + "loss": 0.4701, + "step": 6046 + }, + { + "epoch": 0.51, + "learning_rate": 1.0293982310100814e-05, + "loss": 0.4751, + "step": 6047 + }, + { + "epoch": 0.51, + "learning_rate": 1.0291273565802058e-05, + "loss": 0.4912, + "step": 6048 + }, + { + "epoch": 0.51, + "learning_rate": 1.0288564800113383e-05, + "loss": 0.4817, + "step": 6049 + }, + { + "epoch": 0.51, + "learning_rate": 1.0285856013233708e-05, + "loss": 0.4599, + "step": 6050 + }, + { + "epoch": 0.51, + "learning_rate": 1.0283147205361959e-05, + "loss": 0.4964, + "step": 6051 + }, + { + "epoch": 0.51, + "learning_rate": 1.0280438376697056e-05, + "loss": 0.4632, + "step": 6052 + }, + { + "epoch": 0.51, + "learning_rate": 1.0277729527437924e-05, + "loss": 0.463, + "step": 6053 + }, + { + "epoch": 0.51, + "learning_rate": 1.0275020657783492e-05, + "loss": 0.493, + "step": 6054 + }, + { + "epoch": 0.51, + "learning_rate": 1.0272311767932686e-05, + "loss": 0.4833, + "step": 6055 + }, + { + "epoch": 0.51, + "learning_rate": 1.0269602858084435e-05, + "loss": 0.4912, + "step": 6056 + }, + { + "epoch": 0.51, + "learning_rate": 1.0266893928437673e-05, + "loss": 0.481, + "step": 6057 + }, + { + "epoch": 0.51, + "learning_rate": 1.0264184979191331e-05, + "loss": 0.4745, + "step": 6058 + }, + { + "epoch": 0.51, + "learning_rate": 1.0261476010544345e-05, + "loss": 0.4958, + "step": 6059 + }, + { + "epoch": 0.51, + "learning_rate": 1.0258767022695645e-05, + "loss": 0.491, + "step": 6060 + }, + { + "epoch": 0.51, + "learning_rate": 1.0256058015844173e-05, + "loss": 0.4881, + "step": 6061 + }, + { + "epoch": 0.51, + "learning_rate": 1.0253348990188863e-05, + "loss": 0.4736, + "step": 6062 + }, + { + "epoch": 0.51, + "learning_rate": 1.025063994592866e-05, + "loss": 0.4744, + "step": 6063 + }, + { + "epoch": 0.51, + "learning_rate": 1.02479308832625e-05, + "loss": 0.4759, + "step": 6064 + }, + { + "epoch": 0.51, + "learning_rate": 1.0245221802389328e-05, + "loss": 0.4655, + "step": 6065 + }, + { + "epoch": 0.51, + "learning_rate": 1.0242512703508085e-05, + "loss": 0.4912, + "step": 6066 + }, + { + "epoch": 0.51, + "learning_rate": 1.023980358681772e-05, + "loss": 0.4852, + "step": 6067 + }, + { + "epoch": 0.51, + "learning_rate": 1.0237094452517178e-05, + "loss": 0.4838, + "step": 6068 + }, + { + "epoch": 0.51, + "learning_rate": 1.0234385300805403e-05, + "loss": 0.4851, + "step": 6069 + }, + { + "epoch": 0.51, + "learning_rate": 1.0231676131881348e-05, + "loss": 0.4732, + "step": 6070 + }, + { + "epoch": 0.51, + "learning_rate": 1.022896694594396e-05, + "loss": 0.4902, + "step": 6071 + }, + { + "epoch": 0.51, + "learning_rate": 1.022625774319219e-05, + "loss": 0.4603, + "step": 6072 + }, + { + "epoch": 0.51, + "learning_rate": 1.0223548523824996e-05, + "loss": 0.4785, + "step": 6073 + }, + { + "epoch": 0.51, + "learning_rate": 1.0220839288041328e-05, + "loss": 0.4651, + "step": 6074 + }, + { + "epoch": 0.51, + "learning_rate": 1.021813003604014e-05, + "loss": 0.4707, + "step": 6075 + }, + { + "epoch": 0.51, + "learning_rate": 1.0215420768020388e-05, + "loss": 0.5073, + "step": 6076 + }, + { + "epoch": 0.51, + "learning_rate": 1.0212711484181034e-05, + "loss": 0.4872, + "step": 6077 + }, + { + "epoch": 0.51, + "learning_rate": 1.0210002184721033e-05, + "loss": 0.4836, + "step": 6078 + }, + { + "epoch": 0.51, + "learning_rate": 1.0207292869839343e-05, + "loss": 0.46, + "step": 6079 + }, + { + "epoch": 0.51, + "learning_rate": 1.020458353973493e-05, + "loss": 0.4641, + "step": 6080 + }, + { + "epoch": 0.51, + "learning_rate": 1.0201874194606748e-05, + "loss": 0.4703, + "step": 6081 + }, + { + "epoch": 0.51, + "learning_rate": 1.019916483465377e-05, + "loss": 0.4775, + "step": 6082 + }, + { + "epoch": 0.51, + "learning_rate": 1.019645546007495e-05, + "loss": 0.4857, + "step": 6083 + }, + { + "epoch": 0.51, + "learning_rate": 1.0193746071069262e-05, + "loss": 0.4703, + "step": 6084 + }, + { + "epoch": 0.51, + "learning_rate": 1.0191036667835668e-05, + "loss": 0.4713, + "step": 6085 + }, + { + "epoch": 0.51, + "learning_rate": 1.0188327250573133e-05, + "loss": 0.4823, + "step": 6086 + }, + { + "epoch": 0.51, + "learning_rate": 1.0185617819480628e-05, + "loss": 0.4943, + "step": 6087 + }, + { + "epoch": 0.51, + "learning_rate": 1.0182908374757126e-05, + "loss": 0.4849, + "step": 6088 + }, + { + "epoch": 0.51, + "learning_rate": 1.0180198916601592e-05, + "loss": 0.4815, + "step": 6089 + }, + { + "epoch": 0.51, + "learning_rate": 1.0177489445212998e-05, + "loss": 0.486, + "step": 6090 + }, + { + "epoch": 0.51, + "learning_rate": 1.0174779960790318e-05, + "loss": 0.4575, + "step": 6091 + }, + { + "epoch": 0.51, + "learning_rate": 1.0172070463532524e-05, + "loss": 0.4709, + "step": 6092 + }, + { + "epoch": 0.51, + "learning_rate": 1.016936095363859e-05, + "loss": 0.4649, + "step": 6093 + }, + { + "epoch": 0.51, + "learning_rate": 1.0166651431307494e-05, + "loss": 0.4872, + "step": 6094 + }, + { + "epoch": 0.51, + "learning_rate": 1.0163941896738213e-05, + "loss": 0.4819, + "step": 6095 + }, + { + "epoch": 0.51, + "learning_rate": 1.0161232350129715e-05, + "loss": 0.4658, + "step": 6096 + }, + { + "epoch": 0.51, + "learning_rate": 1.0158522791680985e-05, + "loss": 0.4744, + "step": 6097 + }, + { + "epoch": 0.51, + "learning_rate": 1.0155813221591004e-05, + "loss": 0.4849, + "step": 6098 + }, + { + "epoch": 0.51, + "learning_rate": 1.0153103640058745e-05, + "loss": 0.4775, + "step": 6099 + }, + { + "epoch": 0.51, + "learning_rate": 1.0150394047283192e-05, + "loss": 0.4644, + "step": 6100 + }, + { + "epoch": 0.51, + "learning_rate": 1.0147684443463328e-05, + "loss": 0.4933, + "step": 6101 + }, + { + "epoch": 0.51, + "learning_rate": 1.0144974828798131e-05, + "loss": 0.4612, + "step": 6102 + }, + { + "epoch": 0.51, + "learning_rate": 1.0142265203486583e-05, + "loss": 0.4857, + "step": 6103 + }, + { + "epoch": 0.51, + "learning_rate": 1.0139555567727674e-05, + "loss": 0.4879, + "step": 6104 + }, + { + "epoch": 0.51, + "learning_rate": 1.0136845921720385e-05, + "loss": 0.4769, + "step": 6105 + }, + { + "epoch": 0.51, + "learning_rate": 1.0134136265663698e-05, + "loss": 0.4763, + "step": 6106 + }, + { + "epoch": 0.51, + "learning_rate": 1.01314265997566e-05, + "loss": 0.4778, + "step": 6107 + }, + { + "epoch": 0.51, + "learning_rate": 1.0128716924198083e-05, + "loss": 0.4715, + "step": 6108 + }, + { + "epoch": 0.51, + "learning_rate": 1.012600723918713e-05, + "loss": 0.468, + "step": 6109 + }, + { + "epoch": 0.51, + "learning_rate": 1.0123297544922728e-05, + "loss": 0.5026, + "step": 6110 + }, + { + "epoch": 0.51, + "learning_rate": 1.0120587841603868e-05, + "loss": 0.4965, + "step": 6111 + }, + { + "epoch": 0.51, + "learning_rate": 1.011787812942954e-05, + "loss": 0.4759, + "step": 6112 + }, + { + "epoch": 0.51, + "learning_rate": 1.0115168408598728e-05, + "loss": 0.4755, + "step": 6113 + }, + { + "epoch": 0.51, + "learning_rate": 1.011245867931043e-05, + "loss": 0.4671, + "step": 6114 + }, + { + "epoch": 0.51, + "learning_rate": 1.0109748941763635e-05, + "loss": 0.4646, + "step": 6115 + }, + { + "epoch": 0.51, + "learning_rate": 1.0107039196157335e-05, + "loss": 0.4868, + "step": 6116 + }, + { + "epoch": 0.51, + "learning_rate": 1.010432944269052e-05, + "loss": 0.4626, + "step": 6117 + }, + { + "epoch": 0.51, + "learning_rate": 1.0101619681562183e-05, + "loss": 0.4982, + "step": 6118 + }, + { + "epoch": 0.51, + "learning_rate": 1.0098909912971322e-05, + "loss": 0.4729, + "step": 6119 + }, + { + "epoch": 0.51, + "learning_rate": 1.0096200137116924e-05, + "loss": 0.4953, + "step": 6120 + }, + { + "epoch": 0.51, + "learning_rate": 1.0093490354197994e-05, + "loss": 0.4823, + "step": 6121 + }, + { + "epoch": 0.51, + "learning_rate": 1.0090780564413518e-05, + "loss": 0.4974, + "step": 6122 + }, + { + "epoch": 0.51, + "learning_rate": 1.0088070767962497e-05, + "loss": 0.4955, + "step": 6123 + }, + { + "epoch": 0.51, + "learning_rate": 1.0085360965043923e-05, + "loss": 0.4789, + "step": 6124 + }, + { + "epoch": 0.51, + "learning_rate": 1.0082651155856795e-05, + "loss": 0.4786, + "step": 6125 + }, + { + "epoch": 0.51, + "learning_rate": 1.007994134060011e-05, + "loss": 0.4877, + "step": 6126 + }, + { + "epoch": 0.51, + "learning_rate": 1.0077231519472866e-05, + "loss": 0.4656, + "step": 6127 + }, + { + "epoch": 0.51, + "learning_rate": 1.007452169267406e-05, + "loss": 0.4981, + "step": 6128 + }, + { + "epoch": 0.51, + "learning_rate": 1.0071811860402692e-05, + "loss": 0.5001, + "step": 6129 + }, + { + "epoch": 0.51, + "learning_rate": 1.0069102022857757e-05, + "loss": 0.4817, + "step": 6130 + }, + { + "epoch": 0.51, + "learning_rate": 1.0066392180238258e-05, + "loss": 0.4879, + "step": 6131 + }, + { + "epoch": 0.51, + "learning_rate": 1.0063682332743196e-05, + "loss": 0.4897, + "step": 6132 + }, + { + "epoch": 0.51, + "learning_rate": 1.0060972480571565e-05, + "loss": 0.4781, + "step": 6133 + }, + { + "epoch": 0.51, + "learning_rate": 1.0058262623922368e-05, + "loss": 0.4542, + "step": 6134 + }, + { + "epoch": 0.51, + "learning_rate": 1.005555276299461e-05, + "loss": 0.4887, + "step": 6135 + }, + { + "epoch": 0.51, + "learning_rate": 1.0052842897987288e-05, + "loss": 0.4949, + "step": 6136 + }, + { + "epoch": 0.51, + "learning_rate": 1.0050133029099401e-05, + "loss": 0.4703, + "step": 6137 + }, + { + "epoch": 0.51, + "learning_rate": 1.0047423156529952e-05, + "loss": 0.4776, + "step": 6138 + }, + { + "epoch": 0.51, + "learning_rate": 1.0044713280477946e-05, + "loss": 0.4973, + "step": 6139 + }, + { + "epoch": 0.51, + "learning_rate": 1.0042003401142383e-05, + "loss": 0.4845, + "step": 6140 + }, + { + "epoch": 0.51, + "learning_rate": 1.0039293518722262e-05, + "loss": 0.4794, + "step": 6141 + }, + { + "epoch": 0.51, + "learning_rate": 1.0036583633416593e-05, + "loss": 0.4974, + "step": 6142 + }, + { + "epoch": 0.51, + "learning_rate": 1.0033873745424369e-05, + "loss": 0.4832, + "step": 6143 + }, + { + "epoch": 0.51, + "learning_rate": 1.00311638549446e-05, + "loss": 0.4864, + "step": 6144 + }, + { + "epoch": 0.51, + "learning_rate": 1.0028453962176287e-05, + "loss": 0.4641, + "step": 6145 + }, + { + "epoch": 0.51, + "learning_rate": 1.0025744067318435e-05, + "loss": 0.4801, + "step": 6146 + }, + { + "epoch": 0.51, + "learning_rate": 1.0023034170570044e-05, + "loss": 0.4759, + "step": 6147 + }, + { + "epoch": 0.51, + "learning_rate": 1.0020324272130117e-05, + "loss": 0.4816, + "step": 6148 + }, + { + "epoch": 0.51, + "learning_rate": 1.0017614372197667e-05, + "loss": 0.4867, + "step": 6149 + }, + { + "epoch": 0.51, + "learning_rate": 1.0014904470971686e-05, + "loss": 0.4779, + "step": 6150 + }, + { + "epoch": 0.51, + "learning_rate": 1.0012194568651184e-05, + "loss": 0.4897, + "step": 6151 + }, + { + "epoch": 0.51, + "learning_rate": 1.0009484665435163e-05, + "loss": 0.4805, + "step": 6152 + }, + { + "epoch": 0.51, + "learning_rate": 1.0006774761522626e-05, + "loss": 0.4745, + "step": 6153 + }, + { + "epoch": 0.51, + "learning_rate": 1.000406485711258e-05, + "loss": 0.4776, + "step": 6154 + }, + { + "epoch": 0.51, + "learning_rate": 1.0001354952404027e-05, + "loss": 0.4708, + "step": 6155 + }, + { + "epoch": 0.52, + "learning_rate": 9.998645047595975e-06, + "loss": 0.4719, + "step": 6156 + }, + { + "epoch": 0.52, + "learning_rate": 9.995935142887424e-06, + "loss": 0.4778, + "step": 6157 + }, + { + "epoch": 0.52, + "learning_rate": 9.993225238477377e-06, + "loss": 0.479, + "step": 6158 + }, + { + "epoch": 0.52, + "learning_rate": 9.99051533456484e-06, + "loss": 0.4616, + "step": 6159 + }, + { + "epoch": 0.52, + "learning_rate": 9.987805431348818e-06, + "loss": 0.4924, + "step": 6160 + }, + { + "epoch": 0.52, + "learning_rate": 9.985095529028317e-06, + "loss": 0.4886, + "step": 6161 + }, + { + "epoch": 0.52, + "learning_rate": 9.982385627802338e-06, + "loss": 0.473, + "step": 6162 + }, + { + "epoch": 0.52, + "learning_rate": 9.979675727869884e-06, + "loss": 0.5046, + "step": 6163 + }, + { + "epoch": 0.52, + "learning_rate": 9.976965829429958e-06, + "loss": 0.4845, + "step": 6164 + }, + { + "epoch": 0.52, + "learning_rate": 9.97425593268157e-06, + "loss": 0.4805, + "step": 6165 + }, + { + "epoch": 0.52, + "learning_rate": 9.971546037823713e-06, + "loss": 0.4887, + "step": 6166 + }, + { + "epoch": 0.52, + "learning_rate": 9.968836145055402e-06, + "loss": 0.4882, + "step": 6167 + }, + { + "epoch": 0.52, + "learning_rate": 9.966126254575634e-06, + "loss": 0.4744, + "step": 6168 + }, + { + "epoch": 0.52, + "learning_rate": 9.963416366583412e-06, + "loss": 0.4752, + "step": 6169 + }, + { + "epoch": 0.52, + "learning_rate": 9.960706481277742e-06, + "loss": 0.4858, + "step": 6170 + }, + { + "epoch": 0.52, + "learning_rate": 9.957996598857622e-06, + "loss": 0.4589, + "step": 6171 + }, + { + "epoch": 0.52, + "learning_rate": 9.955286719522059e-06, + "loss": 0.4713, + "step": 6172 + }, + { + "epoch": 0.52, + "learning_rate": 9.952576843470048e-06, + "loss": 0.5407, + "step": 6173 + }, + { + "epoch": 0.52, + "learning_rate": 9.949866970900602e-06, + "loss": 0.4929, + "step": 6174 + }, + { + "epoch": 0.52, + "learning_rate": 9.947157102012716e-06, + "loss": 0.4734, + "step": 6175 + }, + { + "epoch": 0.52, + "learning_rate": 9.944447237005392e-06, + "loss": 0.4758, + "step": 6176 + }, + { + "epoch": 0.52, + "learning_rate": 9.941737376077634e-06, + "loss": 0.4628, + "step": 6177 + }, + { + "epoch": 0.52, + "learning_rate": 9.93902751942844e-06, + "loss": 0.4739, + "step": 6178 + }, + { + "epoch": 0.52, + "learning_rate": 9.93631766725681e-06, + "loss": 0.4739, + "step": 6179 + }, + { + "epoch": 0.52, + "learning_rate": 9.93360781976174e-06, + "loss": 0.488, + "step": 6180 + }, + { + "epoch": 0.52, + "learning_rate": 9.930897977142245e-06, + "loss": 0.484, + "step": 6181 + }, + { + "epoch": 0.52, + "learning_rate": 9.928188139597313e-06, + "loss": 0.4858, + "step": 6182 + }, + { + "epoch": 0.52, + "learning_rate": 9.925478307325944e-06, + "loss": 0.4791, + "step": 6183 + }, + { + "epoch": 0.52, + "learning_rate": 9.922768480527138e-06, + "loss": 0.4836, + "step": 6184 + }, + { + "epoch": 0.52, + "learning_rate": 9.920058659399895e-06, + "loss": 0.471, + "step": 6185 + }, + { + "epoch": 0.52, + "learning_rate": 9.91734884414321e-06, + "loss": 0.4773, + "step": 6186 + }, + { + "epoch": 0.52, + "learning_rate": 9.914639034956079e-06, + "loss": 0.4778, + "step": 6187 + }, + { + "epoch": 0.52, + "learning_rate": 9.911929232037507e-06, + "loss": 0.4983, + "step": 6188 + }, + { + "epoch": 0.52, + "learning_rate": 9.909219435586485e-06, + "loss": 0.4768, + "step": 6189 + }, + { + "epoch": 0.52, + "learning_rate": 9.906509645802009e-06, + "loss": 0.4848, + "step": 6190 + }, + { + "epoch": 0.52, + "learning_rate": 9.903799862883077e-06, + "loss": 0.4802, + "step": 6191 + }, + { + "epoch": 0.52, + "learning_rate": 9.901090087028685e-06, + "loss": 0.4775, + "step": 6192 + }, + { + "epoch": 0.52, + "learning_rate": 9.898380318437822e-06, + "loss": 0.4846, + "step": 6193 + }, + { + "epoch": 0.52, + "learning_rate": 9.895670557309484e-06, + "loss": 0.4832, + "step": 6194 + }, + { + "epoch": 0.52, + "learning_rate": 9.892960803842668e-06, + "loss": 0.4866, + "step": 6195 + }, + { + "epoch": 0.52, + "learning_rate": 9.890251058236368e-06, + "loss": 0.4776, + "step": 6196 + }, + { + "epoch": 0.52, + "learning_rate": 9.887541320689573e-06, + "loss": 0.4772, + "step": 6197 + }, + { + "epoch": 0.52, + "learning_rate": 9.884831591401276e-06, + "loss": 0.5, + "step": 6198 + }, + { + "epoch": 0.52, + "learning_rate": 9.882121870570465e-06, + "loss": 0.4832, + "step": 6199 + }, + { + "epoch": 0.52, + "learning_rate": 9.879412158396134e-06, + "loss": 0.4802, + "step": 6200 + }, + { + "epoch": 0.52, + "learning_rate": 9.876702455077272e-06, + "loss": 0.4718, + "step": 6201 + }, + { + "epoch": 0.52, + "learning_rate": 9.873992760812871e-06, + "loss": 0.4742, + "step": 6202 + }, + { + "epoch": 0.52, + "learning_rate": 9.87128307580192e-06, + "loss": 0.4717, + "step": 6203 + }, + { + "epoch": 0.52, + "learning_rate": 9.868573400243402e-06, + "loss": 0.4813, + "step": 6204 + }, + { + "epoch": 0.52, + "learning_rate": 9.865863734336305e-06, + "loss": 0.4895, + "step": 6205 + }, + { + "epoch": 0.52, + "learning_rate": 9.86315407827962e-06, + "loss": 0.4889, + "step": 6206 + }, + { + "epoch": 0.52, + "learning_rate": 9.860444432272328e-06, + "loss": 0.4873, + "step": 6207 + }, + { + "epoch": 0.52, + "learning_rate": 9.857734796513417e-06, + "loss": 0.4915, + "step": 6208 + }, + { + "epoch": 0.52, + "learning_rate": 9.855025171201874e-06, + "loss": 0.4696, + "step": 6209 + }, + { + "epoch": 0.52, + "learning_rate": 9.852315556536674e-06, + "loss": 0.4605, + "step": 6210 + }, + { + "epoch": 0.52, + "learning_rate": 9.84960595271681e-06, + "loss": 0.4808, + "step": 6211 + }, + { + "epoch": 0.52, + "learning_rate": 9.846896359941258e-06, + "loss": 0.4867, + "step": 6212 + }, + { + "epoch": 0.52, + "learning_rate": 9.844186778409002e-06, + "loss": 0.4805, + "step": 6213 + }, + { + "epoch": 0.52, + "learning_rate": 9.841477208319015e-06, + "loss": 0.4754, + "step": 6214 + }, + { + "epoch": 0.52, + "learning_rate": 9.838767649870287e-06, + "loss": 0.4691, + "step": 6215 + }, + { + "epoch": 0.52, + "learning_rate": 9.83605810326179e-06, + "loss": 0.4701, + "step": 6216 + }, + { + "epoch": 0.52, + "learning_rate": 9.833348568692507e-06, + "loss": 0.4799, + "step": 6217 + }, + { + "epoch": 0.52, + "learning_rate": 9.830639046361412e-06, + "loss": 0.4803, + "step": 6218 + }, + { + "epoch": 0.52, + "learning_rate": 9.82792953646748e-06, + "loss": 0.4602, + "step": 6219 + }, + { + "epoch": 0.52, + "learning_rate": 9.825220039209687e-06, + "loss": 0.4757, + "step": 6220 + }, + { + "epoch": 0.52, + "learning_rate": 9.822510554787004e-06, + "loss": 0.4817, + "step": 6221 + }, + { + "epoch": 0.52, + "learning_rate": 9.819801083398411e-06, + "loss": 0.4772, + "step": 6222 + }, + { + "epoch": 0.52, + "learning_rate": 9.817091625242879e-06, + "loss": 0.4876, + "step": 6223 + }, + { + "epoch": 0.52, + "learning_rate": 9.814382180519375e-06, + "loss": 0.4803, + "step": 6224 + }, + { + "epoch": 0.52, + "learning_rate": 9.81167274942687e-06, + "loss": 0.4761, + "step": 6225 + }, + { + "epoch": 0.52, + "learning_rate": 9.808963332164337e-06, + "loss": 0.4727, + "step": 6226 + }, + { + "epoch": 0.52, + "learning_rate": 9.806253928930743e-06, + "loss": 0.468, + "step": 6227 + }, + { + "epoch": 0.52, + "learning_rate": 9.80354453992505e-06, + "loss": 0.4583, + "step": 6228 + }, + { + "epoch": 0.52, + "learning_rate": 9.800835165346234e-06, + "loss": 0.4972, + "step": 6229 + }, + { + "epoch": 0.52, + "learning_rate": 9.798125805393255e-06, + "loss": 0.4874, + "step": 6230 + }, + { + "epoch": 0.52, + "learning_rate": 9.795416460265074e-06, + "loss": 0.4627, + "step": 6231 + }, + { + "epoch": 0.52, + "learning_rate": 9.79270713016066e-06, + "loss": 0.5072, + "step": 6232 + }, + { + "epoch": 0.52, + "learning_rate": 9.789997815278973e-06, + "loss": 0.4845, + "step": 6233 + }, + { + "epoch": 0.52, + "learning_rate": 9.787288515818968e-06, + "loss": 0.4799, + "step": 6234 + }, + { + "epoch": 0.52, + "learning_rate": 9.784579231979612e-06, + "loss": 0.47, + "step": 6235 + }, + { + "epoch": 0.52, + "learning_rate": 9.781869963959861e-06, + "loss": 0.4865, + "step": 6236 + }, + { + "epoch": 0.52, + "learning_rate": 9.779160711958673e-06, + "loss": 0.4727, + "step": 6237 + }, + { + "epoch": 0.52, + "learning_rate": 9.776451476175006e-06, + "loss": 0.4904, + "step": 6238 + }, + { + "epoch": 0.52, + "learning_rate": 9.773742256807812e-06, + "loss": 0.4865, + "step": 6239 + }, + { + "epoch": 0.52, + "learning_rate": 9.771033054056044e-06, + "loss": 0.4669, + "step": 6240 + }, + { + "epoch": 0.52, + "learning_rate": 9.768323868118656e-06, + "loss": 0.4877, + "step": 6241 + }, + { + "epoch": 0.52, + "learning_rate": 9.765614699194598e-06, + "loss": 0.469, + "step": 6242 + }, + { + "epoch": 0.52, + "learning_rate": 9.762905547482825e-06, + "loss": 0.473, + "step": 6243 + }, + { + "epoch": 0.52, + "learning_rate": 9.760196413182283e-06, + "loss": 0.4738, + "step": 6244 + }, + { + "epoch": 0.52, + "learning_rate": 9.757487296491918e-06, + "loss": 0.4813, + "step": 6245 + }, + { + "epoch": 0.52, + "learning_rate": 9.754778197610674e-06, + "loss": 0.4992, + "step": 6246 + }, + { + "epoch": 0.52, + "learning_rate": 9.752069116737504e-06, + "loss": 0.4679, + "step": 6247 + }, + { + "epoch": 0.52, + "learning_rate": 9.74936005407134e-06, + "loss": 0.456, + "step": 6248 + }, + { + "epoch": 0.52, + "learning_rate": 9.746651009811137e-06, + "loss": 0.4749, + "step": 6249 + }, + { + "epoch": 0.52, + "learning_rate": 9.74394198415583e-06, + "loss": 0.4758, + "step": 6250 + }, + { + "epoch": 0.52, + "learning_rate": 9.741232977304356e-06, + "loss": 0.4719, + "step": 6251 + }, + { + "epoch": 0.52, + "learning_rate": 9.738523989455659e-06, + "loss": 0.4639, + "step": 6252 + }, + { + "epoch": 0.52, + "learning_rate": 9.735815020808672e-06, + "loss": 0.4738, + "step": 6253 + }, + { + "epoch": 0.52, + "learning_rate": 9.733106071562332e-06, + "loss": 0.4639, + "step": 6254 + }, + { + "epoch": 0.52, + "learning_rate": 9.730397141915567e-06, + "loss": 0.4905, + "step": 6255 + }, + { + "epoch": 0.52, + "learning_rate": 9.727688232067318e-06, + "loss": 0.4697, + "step": 6256 + }, + { + "epoch": 0.52, + "learning_rate": 9.72497934221651e-06, + "loss": 0.4867, + "step": 6257 + }, + { + "epoch": 0.52, + "learning_rate": 9.722270472562078e-06, + "loss": 0.4721, + "step": 6258 + }, + { + "epoch": 0.52, + "learning_rate": 9.71956162330295e-06, + "loss": 0.4716, + "step": 6259 + }, + { + "epoch": 0.52, + "learning_rate": 9.716852794638046e-06, + "loss": 0.4712, + "step": 6260 + }, + { + "epoch": 0.52, + "learning_rate": 9.714143986766294e-06, + "loss": 0.4798, + "step": 6261 + }, + { + "epoch": 0.52, + "learning_rate": 9.711435199886618e-06, + "loss": 0.4679, + "step": 6262 + }, + { + "epoch": 0.52, + "learning_rate": 9.708726434197944e-06, + "loss": 0.4605, + "step": 6263 + }, + { + "epoch": 0.52, + "learning_rate": 9.706017689899189e-06, + "loss": 0.4812, + "step": 6264 + }, + { + "epoch": 0.52, + "learning_rate": 9.703308967189273e-06, + "loss": 0.4768, + "step": 6265 + }, + { + "epoch": 0.52, + "learning_rate": 9.700600266267109e-06, + "loss": 0.4735, + "step": 6266 + }, + { + "epoch": 0.52, + "learning_rate": 9.697891587331618e-06, + "loss": 0.4862, + "step": 6267 + }, + { + "epoch": 0.52, + "learning_rate": 9.695182930581715e-06, + "loss": 0.4751, + "step": 6268 + }, + { + "epoch": 0.52, + "learning_rate": 9.692474296216303e-06, + "loss": 0.4512, + "step": 6269 + }, + { + "epoch": 0.52, + "learning_rate": 9.689765684434305e-06, + "loss": 0.4947, + "step": 6270 + }, + { + "epoch": 0.52, + "learning_rate": 9.687057095434624e-06, + "loss": 0.4816, + "step": 6271 + }, + { + "epoch": 0.52, + "learning_rate": 9.684348529416166e-06, + "loss": 0.4744, + "step": 6272 + }, + { + "epoch": 0.52, + "learning_rate": 9.681639986577841e-06, + "loss": 0.4612, + "step": 6273 + }, + { + "epoch": 0.52, + "learning_rate": 9.678931467118553e-06, + "loss": 0.4734, + "step": 6274 + }, + { + "epoch": 0.52, + "learning_rate": 9.676222971237197e-06, + "loss": 0.4665, + "step": 6275 + }, + { + "epoch": 0.53, + "learning_rate": 9.673514499132683e-06, + "loss": 0.4761, + "step": 6276 + }, + { + "epoch": 0.53, + "learning_rate": 9.670806051003906e-06, + "loss": 0.4849, + "step": 6277 + }, + { + "epoch": 0.53, + "learning_rate": 9.668097627049765e-06, + "loss": 0.479, + "step": 6278 + }, + { + "epoch": 0.53, + "learning_rate": 9.665389227469152e-06, + "loss": 0.471, + "step": 6279 + }, + { + "epoch": 0.53, + "learning_rate": 9.662680852460963e-06, + "loss": 0.4824, + "step": 6280 + }, + { + "epoch": 0.53, + "learning_rate": 9.659972502224089e-06, + "loss": 0.4746, + "step": 6281 + }, + { + "epoch": 0.53, + "learning_rate": 9.657264176957419e-06, + "loss": 0.4834, + "step": 6282 + }, + { + "epoch": 0.53, + "learning_rate": 9.654555876859841e-06, + "loss": 0.4928, + "step": 6283 + }, + { + "epoch": 0.53, + "learning_rate": 9.651847602130247e-06, + "loss": 0.4866, + "step": 6284 + }, + { + "epoch": 0.53, + "learning_rate": 9.649139352967515e-06, + "loss": 0.4769, + "step": 6285 + }, + { + "epoch": 0.53, + "learning_rate": 9.646431129570531e-06, + "loss": 0.4794, + "step": 6286 + }, + { + "epoch": 0.53, + "learning_rate": 9.643722932138172e-06, + "loss": 0.4776, + "step": 6287 + }, + { + "epoch": 0.53, + "learning_rate": 9.64101476086932e-06, + "loss": 0.4743, + "step": 6288 + }, + { + "epoch": 0.53, + "learning_rate": 9.638306615962847e-06, + "loss": 0.4793, + "step": 6289 + }, + { + "epoch": 0.53, + "learning_rate": 9.635598497617636e-06, + "loss": 0.4823, + "step": 6290 + }, + { + "epoch": 0.53, + "learning_rate": 9.632890406032556e-06, + "loss": 0.467, + "step": 6291 + }, + { + "epoch": 0.53, + "learning_rate": 9.630182341406477e-06, + "loss": 0.4598, + "step": 6292 + }, + { + "epoch": 0.53, + "learning_rate": 9.627474303938267e-06, + "loss": 0.4697, + "step": 6293 + }, + { + "epoch": 0.53, + "learning_rate": 9.624766293826798e-06, + "loss": 0.4777, + "step": 6294 + }, + { + "epoch": 0.53, + "learning_rate": 9.62205831127093e-06, + "loss": 0.4762, + "step": 6295 + }, + { + "epoch": 0.53, + "learning_rate": 9.619350356469524e-06, + "loss": 0.4949, + "step": 6296 + }, + { + "epoch": 0.53, + "learning_rate": 9.616642429621449e-06, + "loss": 0.4867, + "step": 6297 + }, + { + "epoch": 0.53, + "learning_rate": 9.613934530925556e-06, + "loss": 0.4907, + "step": 6298 + }, + { + "epoch": 0.53, + "learning_rate": 9.611226660580709e-06, + "loss": 0.4929, + "step": 6299 + }, + { + "epoch": 0.53, + "learning_rate": 9.60851881878576e-06, + "loss": 0.4616, + "step": 6300 + }, + { + "epoch": 0.53, + "learning_rate": 9.605811005739558e-06, + "loss": 0.4869, + "step": 6301 + }, + { + "epoch": 0.53, + "learning_rate": 9.603103221640956e-06, + "loss": 0.4846, + "step": 6302 + }, + { + "epoch": 0.53, + "learning_rate": 9.600395466688801e-06, + "loss": 0.4695, + "step": 6303 + }, + { + "epoch": 0.53, + "learning_rate": 9.597687741081942e-06, + "loss": 0.4904, + "step": 6304 + }, + { + "epoch": 0.53, + "learning_rate": 9.594980045019224e-06, + "loss": 0.4837, + "step": 6305 + }, + { + "epoch": 0.53, + "learning_rate": 9.592272378699486e-06, + "loss": 0.4682, + "step": 6306 + }, + { + "epoch": 0.53, + "learning_rate": 9.589564742321569e-06, + "loss": 0.4882, + "step": 6307 + }, + { + "epoch": 0.53, + "learning_rate": 9.586857136084309e-06, + "loss": 0.483, + "step": 6308 + }, + { + "epoch": 0.53, + "learning_rate": 9.58414956018654e-06, + "loss": 0.4886, + "step": 6309 + }, + { + "epoch": 0.53, + "learning_rate": 9.581442014827101e-06, + "loss": 0.491, + "step": 6310 + }, + { + "epoch": 0.53, + "learning_rate": 9.57873450020482e-06, + "loss": 0.4758, + "step": 6311 + }, + { + "epoch": 0.53, + "learning_rate": 9.576027016518527e-06, + "loss": 0.4617, + "step": 6312 + }, + { + "epoch": 0.53, + "learning_rate": 9.573319563967043e-06, + "loss": 0.4783, + "step": 6313 + }, + { + "epoch": 0.53, + "learning_rate": 9.570612142749196e-06, + "loss": 0.4769, + "step": 6314 + }, + { + "epoch": 0.53, + "learning_rate": 9.56790475306381e-06, + "loss": 0.4733, + "step": 6315 + }, + { + "epoch": 0.53, + "learning_rate": 9.565197395109694e-06, + "loss": 0.4816, + "step": 6316 + }, + { + "epoch": 0.53, + "learning_rate": 9.56249006908568e-06, + "loss": 0.4784, + "step": 6317 + }, + { + "epoch": 0.53, + "learning_rate": 9.559782775190574e-06, + "loss": 0.4769, + "step": 6318 + }, + { + "epoch": 0.53, + "learning_rate": 9.55707551362319e-06, + "loss": 0.4679, + "step": 6319 + }, + { + "epoch": 0.53, + "learning_rate": 9.554368284582339e-06, + "loss": 0.4917, + "step": 6320 + }, + { + "epoch": 0.53, + "learning_rate": 9.551661088266825e-06, + "loss": 0.4883, + "step": 6321 + }, + { + "epoch": 0.53, + "learning_rate": 9.548953924875459e-06, + "loss": 0.4608, + "step": 6322 + }, + { + "epoch": 0.53, + "learning_rate": 9.546246794607037e-06, + "loss": 0.4799, + "step": 6323 + }, + { + "epoch": 0.53, + "learning_rate": 9.543539697660363e-06, + "loss": 0.4842, + "step": 6324 + }, + { + "epoch": 0.53, + "learning_rate": 9.540832634234238e-06, + "loss": 0.4864, + "step": 6325 + }, + { + "epoch": 0.53, + "learning_rate": 9.538125604527455e-06, + "loss": 0.4847, + "step": 6326 + }, + { + "epoch": 0.53, + "learning_rate": 9.535418608738808e-06, + "loss": 0.5013, + "step": 6327 + }, + { + "epoch": 0.53, + "learning_rate": 9.53271164706708e-06, + "loss": 0.4738, + "step": 6328 + }, + { + "epoch": 0.53, + "learning_rate": 9.53000471971107e-06, + "loss": 0.4796, + "step": 6329 + }, + { + "epoch": 0.53, + "learning_rate": 9.527297826869553e-06, + "loss": 0.4594, + "step": 6330 + }, + { + "epoch": 0.53, + "learning_rate": 9.524590968741324e-06, + "loss": 0.4737, + "step": 6331 + }, + { + "epoch": 0.53, + "learning_rate": 9.521884145525153e-06, + "loss": 0.4757, + "step": 6332 + }, + { + "epoch": 0.53, + "learning_rate": 9.519177357419824e-06, + "loss": 0.5014, + "step": 6333 + }, + { + "epoch": 0.53, + "learning_rate": 9.516470604624109e-06, + "loss": 0.4906, + "step": 6334 + }, + { + "epoch": 0.53, + "learning_rate": 9.513763887336781e-06, + "loss": 0.4728, + "step": 6335 + }, + { + "epoch": 0.53, + "learning_rate": 9.511057205756614e-06, + "loss": 0.4792, + "step": 6336 + }, + { + "epoch": 0.53, + "learning_rate": 9.508350560082364e-06, + "loss": 0.4579, + "step": 6337 + }, + { + "epoch": 0.53, + "learning_rate": 9.505643950512811e-06, + "loss": 0.4688, + "step": 6338 + }, + { + "epoch": 0.53, + "learning_rate": 9.502937377246707e-06, + "loss": 0.489, + "step": 6339 + }, + { + "epoch": 0.53, + "learning_rate": 9.500230840482817e-06, + "loss": 0.4965, + "step": 6340 + }, + { + "epoch": 0.53, + "learning_rate": 9.497524340419896e-06, + "loss": 0.4631, + "step": 6341 + }, + { + "epoch": 0.53, + "learning_rate": 9.494817877256696e-06, + "loss": 0.4601, + "step": 6342 + }, + { + "epoch": 0.53, + "learning_rate": 9.49211145119197e-06, + "loss": 0.4815, + "step": 6343 + }, + { + "epoch": 0.53, + "learning_rate": 9.489405062424464e-06, + "loss": 0.4815, + "step": 6344 + }, + { + "epoch": 0.53, + "learning_rate": 9.486698711152928e-06, + "loss": 0.489, + "step": 6345 + }, + { + "epoch": 0.53, + "learning_rate": 9.483992397576106e-06, + "loss": 0.4806, + "step": 6346 + }, + { + "epoch": 0.53, + "learning_rate": 9.481286121892734e-06, + "loss": 0.4701, + "step": 6347 + }, + { + "epoch": 0.53, + "learning_rate": 9.478579884301554e-06, + "loss": 0.4687, + "step": 6348 + }, + { + "epoch": 0.53, + "learning_rate": 9.475873685001295e-06, + "loss": 0.4647, + "step": 6349 + }, + { + "epoch": 0.53, + "learning_rate": 9.473167524190692e-06, + "loss": 0.4665, + "step": 6350 + }, + { + "epoch": 0.53, + "learning_rate": 9.470461402068478e-06, + "loss": 0.4681, + "step": 6351 + }, + { + "epoch": 0.53, + "learning_rate": 9.467755318833376e-06, + "loss": 0.482, + "step": 6352 + }, + { + "epoch": 0.53, + "learning_rate": 9.46504927468411e-06, + "loss": 0.4852, + "step": 6353 + }, + { + "epoch": 0.53, + "learning_rate": 9.462343269819398e-06, + "loss": 0.4887, + "step": 6354 + }, + { + "epoch": 0.53, + "learning_rate": 9.459637304437962e-06, + "loss": 0.4993, + "step": 6355 + }, + { + "epoch": 0.53, + "learning_rate": 9.456931378738515e-06, + "loss": 0.4926, + "step": 6356 + }, + { + "epoch": 0.53, + "learning_rate": 9.454225492919765e-06, + "loss": 0.4916, + "step": 6357 + }, + { + "epoch": 0.53, + "learning_rate": 9.451519647180427e-06, + "loss": 0.4718, + "step": 6358 + }, + { + "epoch": 0.53, + "learning_rate": 9.448813841719207e-06, + "loss": 0.4794, + "step": 6359 + }, + { + "epoch": 0.53, + "learning_rate": 9.446108076734803e-06, + "loss": 0.461, + "step": 6360 + }, + { + "epoch": 0.53, + "learning_rate": 9.44340235242592e-06, + "loss": 0.486, + "step": 6361 + }, + { + "epoch": 0.53, + "learning_rate": 9.440696668991253e-06, + "loss": 0.467, + "step": 6362 + }, + { + "epoch": 0.53, + "learning_rate": 9.437991026629497e-06, + "loss": 0.4657, + "step": 6363 + }, + { + "epoch": 0.53, + "learning_rate": 9.435285425539337e-06, + "loss": 0.4854, + "step": 6364 + }, + { + "epoch": 0.53, + "learning_rate": 9.43257986591947e-06, + "loss": 0.4839, + "step": 6365 + }, + { + "epoch": 0.53, + "learning_rate": 9.42987434796858e-06, + "loss": 0.4686, + "step": 6366 + }, + { + "epoch": 0.53, + "learning_rate": 9.427168871885345e-06, + "loss": 0.4639, + "step": 6367 + }, + { + "epoch": 0.53, + "learning_rate": 9.424463437868445e-06, + "loss": 0.4912, + "step": 6368 + }, + { + "epoch": 0.53, + "learning_rate": 9.421758046116557e-06, + "loss": 0.4673, + "step": 6369 + }, + { + "epoch": 0.53, + "learning_rate": 9.419052696828352e-06, + "loss": 0.4861, + "step": 6370 + }, + { + "epoch": 0.53, + "learning_rate": 9.416347390202499e-06, + "loss": 0.4816, + "step": 6371 + }, + { + "epoch": 0.53, + "learning_rate": 9.41364212643767e-06, + "loss": 0.4647, + "step": 6372 + }, + { + "epoch": 0.53, + "learning_rate": 9.410936905732522e-06, + "loss": 0.4781, + "step": 6373 + }, + { + "epoch": 0.53, + "learning_rate": 9.40823172828572e-06, + "loss": 0.4912, + "step": 6374 + }, + { + "epoch": 0.53, + "learning_rate": 9.405526594295915e-06, + "loss": 0.4641, + "step": 6375 + }, + { + "epoch": 0.53, + "learning_rate": 9.402821503961766e-06, + "loss": 0.4802, + "step": 6376 + }, + { + "epoch": 0.53, + "learning_rate": 9.400116457481924e-06, + "loss": 0.4938, + "step": 6377 + }, + { + "epoch": 0.53, + "learning_rate": 9.397411455055028e-06, + "loss": 0.4878, + "step": 6378 + }, + { + "epoch": 0.53, + "learning_rate": 9.394706496879733e-06, + "loss": 0.4762, + "step": 6379 + }, + { + "epoch": 0.53, + "learning_rate": 9.392001583154675e-06, + "loss": 0.4799, + "step": 6380 + }, + { + "epoch": 0.53, + "learning_rate": 9.389296714078493e-06, + "loss": 0.4966, + "step": 6381 + }, + { + "epoch": 0.53, + "learning_rate": 9.386591889849819e-06, + "loss": 0.4841, + "step": 6382 + }, + { + "epoch": 0.53, + "learning_rate": 9.383887110667285e-06, + "loss": 0.5037, + "step": 6383 + }, + { + "epoch": 0.53, + "learning_rate": 9.381182376729516e-06, + "loss": 0.4769, + "step": 6384 + }, + { + "epoch": 0.53, + "learning_rate": 9.378477688235144e-06, + "loss": 0.4716, + "step": 6385 + }, + { + "epoch": 0.53, + "learning_rate": 9.375773045382782e-06, + "loss": 0.4908, + "step": 6386 + }, + { + "epoch": 0.53, + "learning_rate": 9.373068448371054e-06, + "loss": 0.4506, + "step": 6387 + }, + { + "epoch": 0.53, + "learning_rate": 9.370363897398573e-06, + "loss": 0.4837, + "step": 6388 + }, + { + "epoch": 0.53, + "learning_rate": 9.367659392663947e-06, + "loss": 0.4797, + "step": 6389 + }, + { + "epoch": 0.53, + "learning_rate": 9.364954934365783e-06, + "loss": 0.4906, + "step": 6390 + }, + { + "epoch": 0.53, + "learning_rate": 9.362250522702685e-06, + "loss": 0.4653, + "step": 6391 + }, + { + "epoch": 0.53, + "learning_rate": 9.35954615787326e-06, + "loss": 0.4811, + "step": 6392 + }, + { + "epoch": 0.53, + "learning_rate": 9.356841840076102e-06, + "loss": 0.4746, + "step": 6393 + }, + { + "epoch": 0.53, + "learning_rate": 9.354137569509804e-06, + "loss": 0.4864, + "step": 6394 + }, + { + "epoch": 0.54, + "learning_rate": 9.351433346372955e-06, + "loss": 0.4882, + "step": 6395 + }, + { + "epoch": 0.54, + "learning_rate": 9.348729170864145e-06, + "loss": 0.4855, + "step": 6396 + }, + { + "epoch": 0.54, + "learning_rate": 9.346025043181955e-06, + "loss": 0.4606, + "step": 6397 + }, + { + "epoch": 0.54, + "learning_rate": 9.343320963524964e-06, + "loss": 0.482, + "step": 6398 + }, + { + "epoch": 0.54, + "learning_rate": 9.340616932091752e-06, + "loss": 0.4876, + "step": 6399 + }, + { + "epoch": 0.54, + "learning_rate": 9.33791294908089e-06, + "loss": 0.4936, + "step": 6400 + }, + { + "epoch": 0.54, + "learning_rate": 9.335209014690946e-06, + "loss": 0.495, + "step": 6401 + }, + { + "epoch": 0.54, + "learning_rate": 9.332505129120489e-06, + "loss": 0.4882, + "step": 6402 + }, + { + "epoch": 0.54, + "learning_rate": 9.32980129256808e-06, + "loss": 0.4871, + "step": 6403 + }, + { + "epoch": 0.54, + "learning_rate": 9.327097505232274e-06, + "loss": 0.4526, + "step": 6404 + }, + { + "epoch": 0.54, + "learning_rate": 9.324393767311625e-06, + "loss": 0.4816, + "step": 6405 + }, + { + "epoch": 0.54, + "learning_rate": 9.321690079004691e-06, + "loss": 0.4765, + "step": 6406 + }, + { + "epoch": 0.54, + "learning_rate": 9.318986440510018e-06, + "loss": 0.4737, + "step": 6407 + }, + { + "epoch": 0.54, + "learning_rate": 9.316282852026147e-06, + "loss": 0.4784, + "step": 6408 + }, + { + "epoch": 0.54, + "learning_rate": 9.313579313751621e-06, + "loss": 0.4744, + "step": 6409 + }, + { + "epoch": 0.54, + "learning_rate": 9.310875825884972e-06, + "loss": 0.4675, + "step": 6410 + }, + { + "epoch": 0.54, + "learning_rate": 9.308172388624739e-06, + "loss": 0.465, + "step": 6411 + }, + { + "epoch": 0.54, + "learning_rate": 9.305469002169442e-06, + "loss": 0.477, + "step": 6412 + }, + { + "epoch": 0.54, + "learning_rate": 9.30276566671762e-06, + "loss": 0.4649, + "step": 6413 + }, + { + "epoch": 0.54, + "learning_rate": 9.300062382467785e-06, + "loss": 0.4649, + "step": 6414 + }, + { + "epoch": 0.54, + "learning_rate": 9.29735914961846e-06, + "loss": 0.468, + "step": 6415 + }, + { + "epoch": 0.54, + "learning_rate": 9.294655968368153e-06, + "loss": 0.4863, + "step": 6416 + }, + { + "epoch": 0.54, + "learning_rate": 9.291952838915379e-06, + "loss": 0.4815, + "step": 6417 + }, + { + "epoch": 0.54, + "learning_rate": 9.289249761458643e-06, + "loss": 0.4916, + "step": 6418 + }, + { + "epoch": 0.54, + "learning_rate": 9.286546736196447e-06, + "loss": 0.4722, + "step": 6419 + }, + { + "epoch": 0.54, + "learning_rate": 9.283843763327293e-06, + "loss": 0.5097, + "step": 6420 + }, + { + "epoch": 0.54, + "learning_rate": 9.281140843049674e-06, + "loss": 0.4785, + "step": 6421 + }, + { + "epoch": 0.54, + "learning_rate": 9.278437975562083e-06, + "loss": 0.4712, + "step": 6422 + }, + { + "epoch": 0.54, + "learning_rate": 9.275735161063006e-06, + "loss": 0.4693, + "step": 6423 + }, + { + "epoch": 0.54, + "learning_rate": 9.273032399750925e-06, + "loss": 0.4631, + "step": 6424 + }, + { + "epoch": 0.54, + "learning_rate": 9.270329691824318e-06, + "loss": 0.4736, + "step": 6425 + }, + { + "epoch": 0.54, + "learning_rate": 9.267627037481667e-06, + "loss": 0.4763, + "step": 6426 + }, + { + "epoch": 0.54, + "learning_rate": 9.264924436921438e-06, + "loss": 0.475, + "step": 6427 + }, + { + "epoch": 0.54, + "learning_rate": 9.262221890342104e-06, + "loss": 0.5036, + "step": 6428 + }, + { + "epoch": 0.54, + "learning_rate": 9.259519397942125e-06, + "loss": 0.4682, + "step": 6429 + }, + { + "epoch": 0.54, + "learning_rate": 9.256816959919962e-06, + "loss": 0.4808, + "step": 6430 + }, + { + "epoch": 0.54, + "learning_rate": 9.254114576474068e-06, + "loss": 0.4676, + "step": 6431 + }, + { + "epoch": 0.54, + "learning_rate": 9.251412247802896e-06, + "loss": 0.4549, + "step": 6432 + }, + { + "epoch": 0.54, + "learning_rate": 9.248709974104897e-06, + "loss": 0.4904, + "step": 6433 + }, + { + "epoch": 0.54, + "learning_rate": 9.246007755578514e-06, + "loss": 0.4909, + "step": 6434 + }, + { + "epoch": 0.54, + "learning_rate": 9.243305592422184e-06, + "loss": 0.479, + "step": 6435 + }, + { + "epoch": 0.54, + "learning_rate": 9.240603484834347e-06, + "loss": 0.4879, + "step": 6436 + }, + { + "epoch": 0.54, + "learning_rate": 9.237901433013427e-06, + "loss": 0.4899, + "step": 6437 + }, + { + "epoch": 0.54, + "learning_rate": 9.235199437157858e-06, + "loss": 0.4525, + "step": 6438 + }, + { + "epoch": 0.54, + "learning_rate": 9.232497497466057e-06, + "loss": 0.4823, + "step": 6439 + }, + { + "epoch": 0.54, + "learning_rate": 9.229795614136452e-06, + "loss": 0.4723, + "step": 6440 + }, + { + "epoch": 0.54, + "learning_rate": 9.227093787367454e-06, + "loss": 0.4649, + "step": 6441 + }, + { + "epoch": 0.54, + "learning_rate": 9.224392017357471e-06, + "loss": 0.4885, + "step": 6442 + }, + { + "epoch": 0.54, + "learning_rate": 9.221690304304915e-06, + "loss": 0.4626, + "step": 6443 + }, + { + "epoch": 0.54, + "learning_rate": 9.218988648408187e-06, + "loss": 0.4568, + "step": 6444 + }, + { + "epoch": 0.54, + "learning_rate": 9.216287049865681e-06, + "loss": 0.4942, + "step": 6445 + }, + { + "epoch": 0.54, + "learning_rate": 9.213585508875792e-06, + "loss": 0.5012, + "step": 6446 + }, + { + "epoch": 0.54, + "learning_rate": 9.210884025636916e-06, + "loss": 0.4838, + "step": 6447 + }, + { + "epoch": 0.54, + "learning_rate": 9.208182600347432e-06, + "loss": 0.4744, + "step": 6448 + }, + { + "epoch": 0.54, + "learning_rate": 9.20548123320573e-06, + "loss": 0.4823, + "step": 6449 + }, + { + "epoch": 0.54, + "learning_rate": 9.20277992441018e-06, + "loss": 0.4897, + "step": 6450 + }, + { + "epoch": 0.54, + "learning_rate": 9.200078674159154e-06, + "loss": 0.4671, + "step": 6451 + }, + { + "epoch": 0.54, + "learning_rate": 9.197377482651023e-06, + "loss": 0.4986, + "step": 6452 + }, + { + "epoch": 0.54, + "learning_rate": 9.194676350084148e-06, + "loss": 0.4702, + "step": 6453 + }, + { + "epoch": 0.54, + "learning_rate": 9.191975276656898e-06, + "loss": 0.4758, + "step": 6454 + }, + { + "epoch": 0.54, + "learning_rate": 9.189274262567622e-06, + "loss": 0.4712, + "step": 6455 + }, + { + "epoch": 0.54, + "learning_rate": 9.186573308014672e-06, + "loss": 0.4757, + "step": 6456 + }, + { + "epoch": 0.54, + "learning_rate": 9.183872413196392e-06, + "loss": 0.4419, + "step": 6457 + }, + { + "epoch": 0.54, + "learning_rate": 9.181171578311132e-06, + "loss": 0.483, + "step": 6458 + }, + { + "epoch": 0.54, + "learning_rate": 9.17847080355722e-06, + "loss": 0.4725, + "step": 6459 + }, + { + "epoch": 0.54, + "learning_rate": 9.175770089133e-06, + "loss": 0.4854, + "step": 6460 + }, + { + "epoch": 0.54, + "learning_rate": 9.173069435236796e-06, + "loss": 0.5029, + "step": 6461 + }, + { + "epoch": 0.54, + "learning_rate": 9.170368842066932e-06, + "loss": 0.4741, + "step": 6462 + }, + { + "epoch": 0.54, + "learning_rate": 9.167668309821729e-06, + "loss": 0.4736, + "step": 6463 + }, + { + "epoch": 0.54, + "learning_rate": 9.164967838699504e-06, + "loss": 0.5017, + "step": 6464 + }, + { + "epoch": 0.54, + "learning_rate": 9.162267428898568e-06, + "loss": 0.4903, + "step": 6465 + }, + { + "epoch": 0.54, + "learning_rate": 9.159567080617226e-06, + "loss": 0.4764, + "step": 6466 + }, + { + "epoch": 0.54, + "learning_rate": 9.156866794053783e-06, + "loss": 0.4889, + "step": 6467 + }, + { + "epoch": 0.54, + "learning_rate": 9.154166569406537e-06, + "loss": 0.4664, + "step": 6468 + }, + { + "epoch": 0.54, + "learning_rate": 9.15146640687378e-06, + "loss": 0.494, + "step": 6469 + }, + { + "epoch": 0.54, + "learning_rate": 9.148766306653801e-06, + "loss": 0.4731, + "step": 6470 + }, + { + "epoch": 0.54, + "learning_rate": 9.146066268944883e-06, + "loss": 0.4908, + "step": 6471 + }, + { + "epoch": 0.54, + "learning_rate": 9.143366293945305e-06, + "loss": 0.4881, + "step": 6472 + }, + { + "epoch": 0.54, + "learning_rate": 9.140666381853343e-06, + "loss": 0.4623, + "step": 6473 + }, + { + "epoch": 0.54, + "learning_rate": 9.137966532867268e-06, + "loss": 0.4839, + "step": 6474 + }, + { + "epoch": 0.54, + "learning_rate": 9.135266747185348e-06, + "loss": 0.484, + "step": 6475 + }, + { + "epoch": 0.54, + "learning_rate": 9.132567025005842e-06, + "loss": 0.4819, + "step": 6476 + }, + { + "epoch": 0.54, + "learning_rate": 9.129867366527004e-06, + "loss": 0.4728, + "step": 6477 + }, + { + "epoch": 0.54, + "learning_rate": 9.127167771947086e-06, + "loss": 0.4608, + "step": 6478 + }, + { + "epoch": 0.54, + "learning_rate": 9.12446824146434e-06, + "loss": 0.4677, + "step": 6479 + }, + { + "epoch": 0.54, + "learning_rate": 9.121768775276997e-06, + "loss": 0.4838, + "step": 6480 + }, + { + "epoch": 0.54, + "learning_rate": 9.11906937358331e-06, + "loss": 0.4658, + "step": 6481 + }, + { + "epoch": 0.54, + "learning_rate": 9.116370036581504e-06, + "loss": 0.4829, + "step": 6482 + }, + { + "epoch": 0.54, + "learning_rate": 9.113670764469803e-06, + "loss": 0.4701, + "step": 6483 + }, + { + "epoch": 0.54, + "learning_rate": 9.110971557446437e-06, + "loss": 0.4751, + "step": 6484 + }, + { + "epoch": 0.54, + "learning_rate": 9.108272415709624e-06, + "loss": 0.4502, + "step": 6485 + }, + { + "epoch": 0.54, + "learning_rate": 9.105573339457574e-06, + "loss": 0.4784, + "step": 6486 + }, + { + "epoch": 0.54, + "learning_rate": 9.102874328888493e-06, + "loss": 0.4574, + "step": 6487 + }, + { + "epoch": 0.54, + "learning_rate": 9.100175384200595e-06, + "loss": 0.4764, + "step": 6488 + }, + { + "epoch": 0.54, + "learning_rate": 9.097476505592074e-06, + "loss": 0.4746, + "step": 6489 + }, + { + "epoch": 0.54, + "learning_rate": 9.094777693261124e-06, + "loss": 0.4867, + "step": 6490 + }, + { + "epoch": 0.54, + "learning_rate": 9.092078947405937e-06, + "loss": 0.4723, + "step": 6491 + }, + { + "epoch": 0.54, + "learning_rate": 9.089380268224694e-06, + "loss": 0.4829, + "step": 6492 + }, + { + "epoch": 0.54, + "learning_rate": 9.086681655915574e-06, + "loss": 0.4703, + "step": 6493 + }, + { + "epoch": 0.54, + "learning_rate": 9.083983110676755e-06, + "loss": 0.4804, + "step": 6494 + }, + { + "epoch": 0.54, + "learning_rate": 9.081284632706408e-06, + "loss": 0.4808, + "step": 6495 + }, + { + "epoch": 0.54, + "learning_rate": 9.078586222202698e-06, + "loss": 0.4923, + "step": 6496 + }, + { + "epoch": 0.54, + "learning_rate": 9.075887879363783e-06, + "loss": 0.4779, + "step": 6497 + }, + { + "epoch": 0.54, + "learning_rate": 9.073189604387815e-06, + "loss": 0.4824, + "step": 6498 + }, + { + "epoch": 0.54, + "learning_rate": 9.07049139747295e-06, + "loss": 0.4912, + "step": 6499 + }, + { + "epoch": 0.54, + "learning_rate": 9.06779325881733e-06, + "loss": 0.477, + "step": 6500 + }, + { + "epoch": 0.54, + "learning_rate": 9.065095188619096e-06, + "loss": 0.4758, + "step": 6501 + }, + { + "epoch": 0.54, + "learning_rate": 9.062397187076384e-06, + "loss": 0.467, + "step": 6502 + }, + { + "epoch": 0.54, + "learning_rate": 9.059699254387323e-06, + "loss": 0.4954, + "step": 6503 + }, + { + "epoch": 0.54, + "learning_rate": 9.057001390750035e-06, + "loss": 0.4689, + "step": 6504 + }, + { + "epoch": 0.54, + "learning_rate": 9.054303596362646e-06, + "loss": 0.4764, + "step": 6505 + }, + { + "epoch": 0.54, + "learning_rate": 9.051605871423266e-06, + "loss": 0.4866, + "step": 6506 + }, + { + "epoch": 0.54, + "learning_rate": 9.048908216130002e-06, + "loss": 0.4834, + "step": 6507 + }, + { + "epoch": 0.54, + "learning_rate": 9.046210630680968e-06, + "loss": 0.4618, + "step": 6508 + }, + { + "epoch": 0.54, + "learning_rate": 9.043513115274257e-06, + "loss": 0.4803, + "step": 6509 + }, + { + "epoch": 0.54, + "learning_rate": 9.040815670107964e-06, + "loss": 0.4672, + "step": 6510 + }, + { + "epoch": 0.54, + "learning_rate": 9.038118295380179e-06, + "loss": 0.4937, + "step": 6511 + }, + { + "epoch": 0.54, + "learning_rate": 9.035420991288987e-06, + "loss": 0.4753, + "step": 6512 + }, + { + "epoch": 0.54, + "learning_rate": 9.032723758032462e-06, + "loss": 0.4871, + "step": 6513 + }, + { + "epoch": 0.54, + "learning_rate": 9.030026595808682e-06, + "loss": 0.4761, + "step": 6514 + }, + { + "epoch": 0.55, + "learning_rate": 9.027329504815714e-06, + "loss": 0.509, + "step": 6515 + }, + { + "epoch": 0.55, + "learning_rate": 9.024632485251624e-06, + "loss": 0.4935, + "step": 6516 + }, + { + "epoch": 0.55, + "learning_rate": 9.021935537314467e-06, + "loss": 0.4866, + "step": 6517 + }, + { + "epoch": 0.55, + "learning_rate": 9.019238661202296e-06, + "loss": 0.4957, + "step": 6518 + }, + { + "epoch": 0.55, + "learning_rate": 9.016541857113157e-06, + "loss": 0.4776, + "step": 6519 + }, + { + "epoch": 0.55, + "learning_rate": 9.013845125245095e-06, + "loss": 0.4852, + "step": 6520 + }, + { + "epoch": 0.55, + "learning_rate": 9.01114846579614e-06, + "loss": 0.4643, + "step": 6521 + }, + { + "epoch": 0.55, + "learning_rate": 9.008451878964336e-06, + "loss": 0.4801, + "step": 6522 + }, + { + "epoch": 0.55, + "learning_rate": 9.005755364947699e-06, + "loss": 0.4683, + "step": 6523 + }, + { + "epoch": 0.55, + "learning_rate": 9.00305892394425e-06, + "loss": 0.4803, + "step": 6524 + }, + { + "epoch": 0.55, + "learning_rate": 9.000362556152013e-06, + "loss": 0.4789, + "step": 6525 + }, + { + "epoch": 0.55, + "learning_rate": 8.997666261768989e-06, + "loss": 0.4686, + "step": 6526 + }, + { + "epoch": 0.55, + "learning_rate": 8.994970040993187e-06, + "loss": 0.5007, + "step": 6527 + }, + { + "epoch": 0.55, + "learning_rate": 8.9922738940226e-06, + "loss": 0.4736, + "step": 6528 + }, + { + "epoch": 0.55, + "learning_rate": 8.989577821055231e-06, + "loss": 0.4812, + "step": 6529 + }, + { + "epoch": 0.55, + "learning_rate": 8.986881822289062e-06, + "loss": 0.49, + "step": 6530 + }, + { + "epoch": 0.55, + "learning_rate": 8.98418589792208e-06, + "loss": 0.4833, + "step": 6531 + }, + { + "epoch": 0.55, + "learning_rate": 8.98149004815226e-06, + "loss": 0.4741, + "step": 6532 + }, + { + "epoch": 0.55, + "learning_rate": 8.978794273177576e-06, + "loss": 0.4823, + "step": 6533 + }, + { + "epoch": 0.55, + "learning_rate": 8.97609857319599e-06, + "loss": 0.4539, + "step": 6534 + }, + { + "epoch": 0.55, + "learning_rate": 8.973402948405466e-06, + "loss": 0.4686, + "step": 6535 + }, + { + "epoch": 0.55, + "learning_rate": 8.970707399003961e-06, + "loss": 0.4727, + "step": 6536 + }, + { + "epoch": 0.55, + "learning_rate": 8.968011925189426e-06, + "loss": 0.4807, + "step": 6537 + }, + { + "epoch": 0.55, + "learning_rate": 8.9653165271598e-06, + "loss": 0.4661, + "step": 6538 + }, + { + "epoch": 0.55, + "learning_rate": 8.962621205113025e-06, + "loss": 0.4563, + "step": 6539 + }, + { + "epoch": 0.55, + "learning_rate": 8.959925959247036e-06, + "loss": 0.4915, + "step": 6540 + }, + { + "epoch": 0.55, + "learning_rate": 8.957230789759752e-06, + "loss": 0.4776, + "step": 6541 + }, + { + "epoch": 0.55, + "learning_rate": 8.954535696849108e-06, + "loss": 0.4824, + "step": 6542 + }, + { + "epoch": 0.55, + "learning_rate": 8.951840680713013e-06, + "loss": 0.4858, + "step": 6543 + }, + { + "epoch": 0.55, + "learning_rate": 8.949145741549378e-06, + "loss": 0.4641, + "step": 6544 + }, + { + "epoch": 0.55, + "learning_rate": 8.946450879556108e-06, + "loss": 0.4672, + "step": 6545 + }, + { + "epoch": 0.55, + "learning_rate": 8.943756094931106e-06, + "loss": 0.4964, + "step": 6546 + }, + { + "epoch": 0.55, + "learning_rate": 8.941061387872263e-06, + "loss": 0.4896, + "step": 6547 + }, + { + "epoch": 0.55, + "learning_rate": 8.938366758577462e-06, + "loss": 0.4759, + "step": 6548 + }, + { + "epoch": 0.55, + "learning_rate": 8.935672207244596e-06, + "loss": 0.4772, + "step": 6549 + }, + { + "epoch": 0.55, + "learning_rate": 8.932977734071533e-06, + "loss": 0.4732, + "step": 6550 + }, + { + "epoch": 0.55, + "learning_rate": 8.93028333925615e-06, + "loss": 0.4791, + "step": 6551 + }, + { + "epoch": 0.55, + "learning_rate": 8.927589022996308e-06, + "loss": 0.4696, + "step": 6552 + }, + { + "epoch": 0.55, + "learning_rate": 8.92489478548987e-06, + "loss": 0.4734, + "step": 6553 + }, + { + "epoch": 0.55, + "learning_rate": 8.922200626934682e-06, + "loss": 0.4917, + "step": 6554 + }, + { + "epoch": 0.55, + "learning_rate": 8.919506547528599e-06, + "loss": 0.4855, + "step": 6555 + }, + { + "epoch": 0.55, + "learning_rate": 8.916812547469461e-06, + "loss": 0.4893, + "step": 6556 + }, + { + "epoch": 0.55, + "learning_rate": 8.914118626955106e-06, + "loss": 0.4473, + "step": 6557 + }, + { + "epoch": 0.55, + "learning_rate": 8.911424786183362e-06, + "loss": 0.4829, + "step": 6558 + }, + { + "epoch": 0.55, + "learning_rate": 8.908731025352055e-06, + "loss": 0.4882, + "step": 6559 + }, + { + "epoch": 0.55, + "learning_rate": 8.906037344659e-06, + "loss": 0.4827, + "step": 6560 + }, + { + "epoch": 0.55, + "learning_rate": 8.903343744302016e-06, + "loss": 0.469, + "step": 6561 + }, + { + "epoch": 0.55, + "learning_rate": 8.900650224478899e-06, + "loss": 0.4783, + "step": 6562 + }, + { + "epoch": 0.55, + "learning_rate": 8.897956785387463e-06, + "loss": 0.4845, + "step": 6563 + }, + { + "epoch": 0.55, + "learning_rate": 8.895263427225497e-06, + "loss": 0.4707, + "step": 6564 + }, + { + "epoch": 0.55, + "learning_rate": 8.89257015019079e-06, + "loss": 0.4974, + "step": 6565 + }, + { + "epoch": 0.55, + "learning_rate": 8.889876954481122e-06, + "loss": 0.4709, + "step": 6566 + }, + { + "epoch": 0.55, + "learning_rate": 8.887183840294274e-06, + "loss": 0.4527, + "step": 6567 + }, + { + "epoch": 0.55, + "learning_rate": 8.88449080782802e-06, + "loss": 0.4861, + "step": 6568 + }, + { + "epoch": 0.55, + "learning_rate": 8.881797857280113e-06, + "loss": 0.4684, + "step": 6569 + }, + { + "epoch": 0.55, + "learning_rate": 8.879104988848326e-06, + "loss": 0.4724, + "step": 6570 + }, + { + "epoch": 0.55, + "learning_rate": 8.876412202730405e-06, + "loss": 0.4827, + "step": 6571 + }, + { + "epoch": 0.55, + "learning_rate": 8.873719499124101e-06, + "loss": 0.4686, + "step": 6572 + }, + { + "epoch": 0.55, + "learning_rate": 8.871026878227151e-06, + "loss": 0.4915, + "step": 6573 + }, + { + "epoch": 0.55, + "learning_rate": 8.868334340237293e-06, + "loss": 0.4946, + "step": 6574 + }, + { + "epoch": 0.55, + "learning_rate": 8.86564188535225e-06, + "loss": 0.4845, + "step": 6575 + }, + { + "epoch": 0.55, + "learning_rate": 8.86294951376975e-06, + "loss": 0.4632, + "step": 6576 + }, + { + "epoch": 0.55, + "learning_rate": 8.86025722568751e-06, + "loss": 0.4733, + "step": 6577 + }, + { + "epoch": 0.55, + "learning_rate": 8.857565021303238e-06, + "loss": 0.4629, + "step": 6578 + }, + { + "epoch": 0.55, + "learning_rate": 8.85487290081464e-06, + "loss": 0.4984, + "step": 6579 + }, + { + "epoch": 0.55, + "learning_rate": 8.852180864419413e-06, + "loss": 0.4787, + "step": 6580 + }, + { + "epoch": 0.55, + "learning_rate": 8.84948891231525e-06, + "loss": 0.4913, + "step": 6581 + }, + { + "epoch": 0.55, + "learning_rate": 8.846797044699831e-06, + "loss": 0.4955, + "step": 6582 + }, + { + "epoch": 0.55, + "learning_rate": 8.844105261770844e-06, + "loss": 0.478, + "step": 6583 + }, + { + "epoch": 0.55, + "learning_rate": 8.84141356372596e-06, + "loss": 0.4816, + "step": 6584 + }, + { + "epoch": 0.55, + "learning_rate": 8.838721950762845e-06, + "loss": 0.4711, + "step": 6585 + }, + { + "epoch": 0.55, + "learning_rate": 8.836030423079157e-06, + "loss": 0.4757, + "step": 6586 + }, + { + "epoch": 0.55, + "learning_rate": 8.833338980872558e-06, + "loss": 0.4635, + "step": 6587 + }, + { + "epoch": 0.55, + "learning_rate": 8.830647624340689e-06, + "loss": 0.4623, + "step": 6588 + }, + { + "epoch": 0.55, + "learning_rate": 8.827956353681191e-06, + "loss": 0.4898, + "step": 6589 + }, + { + "epoch": 0.55, + "learning_rate": 8.82526516909171e-06, + "loss": 0.4753, + "step": 6590 + }, + { + "epoch": 0.55, + "learning_rate": 8.822574070769867e-06, + "loss": 0.4799, + "step": 6591 + }, + { + "epoch": 0.55, + "learning_rate": 8.819883058913285e-06, + "loss": 0.4814, + "step": 6592 + }, + { + "epoch": 0.55, + "learning_rate": 8.817192133719583e-06, + "loss": 0.5005, + "step": 6593 + }, + { + "epoch": 0.55, + "learning_rate": 8.814501295386373e-06, + "loss": 0.4939, + "step": 6594 + }, + { + "epoch": 0.55, + "learning_rate": 8.811810544111258e-06, + "loss": 0.4781, + "step": 6595 + }, + { + "epoch": 0.55, + "learning_rate": 8.809119880091829e-06, + "loss": 0.4704, + "step": 6596 + }, + { + "epoch": 0.55, + "learning_rate": 8.806429303525685e-06, + "loss": 0.4791, + "step": 6597 + }, + { + "epoch": 0.55, + "learning_rate": 8.803738814610409e-06, + "loss": 0.4631, + "step": 6598 + }, + { + "epoch": 0.55, + "learning_rate": 8.801048413543581e-06, + "loss": 0.4904, + "step": 6599 + }, + { + "epoch": 0.55, + "learning_rate": 8.79835810052277e-06, + "loss": 0.4783, + "step": 6600 + }, + { + "epoch": 0.55, + "learning_rate": 8.79566787574554e-06, + "loss": 0.4744, + "step": 6601 + }, + { + "epoch": 0.55, + "learning_rate": 8.792977739409455e-06, + "loss": 0.4782, + "step": 6602 + }, + { + "epoch": 0.55, + "learning_rate": 8.790287691712059e-06, + "loss": 0.478, + "step": 6603 + }, + { + "epoch": 0.55, + "learning_rate": 8.78759773285091e-06, + "loss": 0.4799, + "step": 6604 + }, + { + "epoch": 0.55, + "learning_rate": 8.784907863023537e-06, + "loss": 0.4553, + "step": 6605 + }, + { + "epoch": 0.55, + "learning_rate": 8.782218082427478e-06, + "loss": 0.4705, + "step": 6606 + }, + { + "epoch": 0.55, + "learning_rate": 8.779528391260257e-06, + "loss": 0.4689, + "step": 6607 + }, + { + "epoch": 0.55, + "learning_rate": 8.776838789719396e-06, + "loss": 0.4538, + "step": 6608 + }, + { + "epoch": 0.55, + "learning_rate": 8.774149278002402e-06, + "loss": 0.4857, + "step": 6609 + }, + { + "epoch": 0.55, + "learning_rate": 8.771459856306791e-06, + "loss": 0.4831, + "step": 6610 + }, + { + "epoch": 0.55, + "learning_rate": 8.768770524830058e-06, + "loss": 0.4744, + "step": 6611 + }, + { + "epoch": 0.55, + "learning_rate": 8.766081283769695e-06, + "loss": 0.4704, + "step": 6612 + }, + { + "epoch": 0.55, + "learning_rate": 8.763392133323192e-06, + "loss": 0.476, + "step": 6613 + }, + { + "epoch": 0.55, + "learning_rate": 8.760703073688027e-06, + "loss": 0.4742, + "step": 6614 + }, + { + "epoch": 0.55, + "learning_rate": 8.758014105061674e-06, + "loss": 0.469, + "step": 6615 + }, + { + "epoch": 0.55, + "learning_rate": 8.755325227641596e-06, + "loss": 0.4838, + "step": 6616 + }, + { + "epoch": 0.55, + "learning_rate": 8.752636441625259e-06, + "loss": 0.4951, + "step": 6617 + }, + { + "epoch": 0.55, + "learning_rate": 8.749947747210112e-06, + "loss": 0.4718, + "step": 6618 + }, + { + "epoch": 0.55, + "learning_rate": 8.747259144593604e-06, + "loss": 0.4653, + "step": 6619 + }, + { + "epoch": 0.55, + "learning_rate": 8.744570633973177e-06, + "loss": 0.472, + "step": 6620 + }, + { + "epoch": 0.55, + "learning_rate": 8.741882215546259e-06, + "loss": 0.4854, + "step": 6621 + }, + { + "epoch": 0.55, + "learning_rate": 8.739193889510276e-06, + "loss": 0.4681, + "step": 6622 + }, + { + "epoch": 0.55, + "learning_rate": 8.736505656062648e-06, + "loss": 0.4679, + "step": 6623 + }, + { + "epoch": 0.55, + "learning_rate": 8.733817515400793e-06, + "loss": 0.4907, + "step": 6624 + }, + { + "epoch": 0.55, + "learning_rate": 8.731129467722113e-06, + "loss": 0.4657, + "step": 6625 + }, + { + "epoch": 0.55, + "learning_rate": 8.728441513224008e-06, + "loss": 0.4657, + "step": 6626 + }, + { + "epoch": 0.55, + "learning_rate": 8.725753652103868e-06, + "loss": 0.4826, + "step": 6627 + }, + { + "epoch": 0.55, + "learning_rate": 8.72306588455908e-06, + "loss": 0.4653, + "step": 6628 + }, + { + "epoch": 0.55, + "learning_rate": 8.720378210787024e-06, + "loss": 0.4729, + "step": 6629 + }, + { + "epoch": 0.55, + "learning_rate": 8.717690630985065e-06, + "loss": 0.4685, + "step": 6630 + }, + { + "epoch": 0.55, + "learning_rate": 8.715003145350576e-06, + "loss": 0.4579, + "step": 6631 + }, + { + "epoch": 0.55, + "learning_rate": 8.712315754080913e-06, + "loss": 0.4743, + "step": 6632 + }, + { + "epoch": 0.55, + "learning_rate": 8.709628457373421e-06, + "loss": 0.4584, + "step": 6633 + }, + { + "epoch": 0.56, + "learning_rate": 8.706941255425452e-06, + "loss": 0.4803, + "step": 6634 + }, + { + "epoch": 0.56, + "learning_rate": 8.704254148434338e-06, + "loss": 0.4585, + "step": 6635 + }, + { + "epoch": 0.56, + "learning_rate": 8.70156713659741e-06, + "loss": 0.4726, + "step": 6636 + }, + { + "epoch": 0.56, + "learning_rate": 8.698880220111987e-06, + "loss": 0.4588, + "step": 6637 + }, + { + "epoch": 0.56, + "learning_rate": 8.69619339917539e-06, + "loss": 0.4938, + "step": 6638 + }, + { + "epoch": 0.56, + "learning_rate": 8.69350667398493e-06, + "loss": 0.4575, + "step": 6639 + }, + { + "epoch": 0.56, + "learning_rate": 8.690820044737905e-06, + "loss": 0.4914, + "step": 6640 + }, + { + "epoch": 0.56, + "learning_rate": 8.688133511631611e-06, + "loss": 0.4948, + "step": 6641 + }, + { + "epoch": 0.56, + "learning_rate": 8.685447074863333e-06, + "loss": 0.4842, + "step": 6642 + }, + { + "epoch": 0.56, + "learning_rate": 8.682760734630357e-06, + "loss": 0.4749, + "step": 6643 + }, + { + "epoch": 0.56, + "learning_rate": 8.68007449112995e-06, + "loss": 0.4753, + "step": 6644 + }, + { + "epoch": 0.56, + "learning_rate": 8.677388344559386e-06, + "loss": 0.4793, + "step": 6645 + }, + { + "epoch": 0.56, + "learning_rate": 8.67470229511592e-06, + "loss": 0.4646, + "step": 6646 + }, + { + "epoch": 0.56, + "learning_rate": 8.672016342996805e-06, + "loss": 0.4625, + "step": 6647 + }, + { + "epoch": 0.56, + "learning_rate": 8.669330488399286e-06, + "loss": 0.4775, + "step": 6648 + }, + { + "epoch": 0.56, + "learning_rate": 8.6666447315206e-06, + "loss": 0.4756, + "step": 6649 + }, + { + "epoch": 0.56, + "learning_rate": 8.663959072557979e-06, + "loss": 0.4676, + "step": 6650 + }, + { + "epoch": 0.56, + "learning_rate": 8.66127351170865e-06, + "loss": 0.4726, + "step": 6651 + }, + { + "epoch": 0.56, + "learning_rate": 8.658588049169825e-06, + "loss": 0.4714, + "step": 6652 + }, + { + "epoch": 0.56, + "learning_rate": 8.655902685138712e-06, + "loss": 0.4803, + "step": 6653 + }, + { + "epoch": 0.56, + "learning_rate": 8.653217419812517e-06, + "loss": 0.4892, + "step": 6654 + }, + { + "epoch": 0.56, + "learning_rate": 8.650532253388435e-06, + "loss": 0.4818, + "step": 6655 + }, + { + "epoch": 0.56, + "learning_rate": 8.64784718606365e-06, + "loss": 0.4835, + "step": 6656 + }, + { + "epoch": 0.56, + "learning_rate": 8.64516221803534e-06, + "loss": 0.4779, + "step": 6657 + }, + { + "epoch": 0.56, + "learning_rate": 8.642477349500686e-06, + "loss": 0.4493, + "step": 6658 + }, + { + "epoch": 0.56, + "learning_rate": 8.639792580656845e-06, + "loss": 0.486, + "step": 6659 + }, + { + "epoch": 0.56, + "learning_rate": 8.637107911700984e-06, + "loss": 0.4814, + "step": 6660 + }, + { + "epoch": 0.56, + "learning_rate": 8.634423342830247e-06, + "loss": 0.4684, + "step": 6661 + }, + { + "epoch": 0.56, + "learning_rate": 8.631738874241781e-06, + "loss": 0.4948, + "step": 6662 + }, + { + "epoch": 0.56, + "learning_rate": 8.629054506132719e-06, + "loss": 0.4751, + "step": 6663 + }, + { + "epoch": 0.56, + "learning_rate": 8.62637023870019e-06, + "loss": 0.4949, + "step": 6664 + }, + { + "epoch": 0.56, + "learning_rate": 8.623686072141322e-06, + "loss": 0.4846, + "step": 6665 + }, + { + "epoch": 0.56, + "learning_rate": 8.621002006653223e-06, + "loss": 0.5014, + "step": 6666 + }, + { + "epoch": 0.56, + "learning_rate": 8.618318042433001e-06, + "loss": 0.4761, + "step": 6667 + }, + { + "epoch": 0.56, + "learning_rate": 8.615634179677754e-06, + "loss": 0.455, + "step": 6668 + }, + { + "epoch": 0.56, + "learning_rate": 8.612950418584575e-06, + "loss": 0.4812, + "step": 6669 + }, + { + "epoch": 0.56, + "learning_rate": 8.610266759350551e-06, + "loss": 0.445, + "step": 6670 + }, + { + "epoch": 0.56, + "learning_rate": 8.60758320217275e-06, + "loss": 0.4593, + "step": 6671 + }, + { + "epoch": 0.56, + "learning_rate": 8.604899747248251e-06, + "loss": 0.48, + "step": 6672 + }, + { + "epoch": 0.56, + "learning_rate": 8.602216394774114e-06, + "loss": 0.485, + "step": 6673 + }, + { + "epoch": 0.56, + "learning_rate": 8.599533144947386e-06, + "loss": 0.4597, + "step": 6674 + }, + { + "epoch": 0.56, + "learning_rate": 8.596849997965122e-06, + "loss": 0.4916, + "step": 6675 + }, + { + "epoch": 0.56, + "learning_rate": 8.594166954024359e-06, + "loss": 0.4836, + "step": 6676 + }, + { + "epoch": 0.56, + "learning_rate": 8.591484013322128e-06, + "loss": 0.4712, + "step": 6677 + }, + { + "epoch": 0.56, + "learning_rate": 8.588801176055447e-06, + "loss": 0.4779, + "step": 6678 + }, + { + "epoch": 0.56, + "learning_rate": 8.586118442421341e-06, + "loss": 0.4899, + "step": 6679 + }, + { + "epoch": 0.56, + "learning_rate": 8.583435812616817e-06, + "loss": 0.4701, + "step": 6680 + }, + { + "epoch": 0.56, + "learning_rate": 8.580753286838875e-06, + "loss": 0.4788, + "step": 6681 + }, + { + "epoch": 0.56, + "learning_rate": 8.57807086528451e-06, + "loss": 0.4701, + "step": 6682 + }, + { + "epoch": 0.56, + "learning_rate": 8.575388548150702e-06, + "loss": 0.4718, + "step": 6683 + }, + { + "epoch": 0.56, + "learning_rate": 8.572706335634437e-06, + "loss": 0.4727, + "step": 6684 + }, + { + "epoch": 0.56, + "learning_rate": 8.570024227932678e-06, + "loss": 0.4729, + "step": 6685 + }, + { + "epoch": 0.56, + "learning_rate": 8.567342225242397e-06, + "loss": 0.4713, + "step": 6686 + }, + { + "epoch": 0.56, + "learning_rate": 8.564660327760543e-06, + "loss": 0.4734, + "step": 6687 + }, + { + "epoch": 0.56, + "learning_rate": 8.561978535684065e-06, + "loss": 0.4841, + "step": 6688 + }, + { + "epoch": 0.56, + "learning_rate": 8.5592968492099e-06, + "loss": 0.4794, + "step": 6689 + }, + { + "epoch": 0.56, + "learning_rate": 8.556615268534984e-06, + "loss": 0.4915, + "step": 6690 + }, + { + "epoch": 0.56, + "learning_rate": 8.553933793856234e-06, + "loss": 0.4734, + "step": 6691 + }, + { + "epoch": 0.56, + "learning_rate": 8.551252425370577e-06, + "loss": 0.4661, + "step": 6692 + }, + { + "epoch": 0.56, + "learning_rate": 8.548571163274915e-06, + "loss": 0.4723, + "step": 6693 + }, + { + "epoch": 0.56, + "learning_rate": 8.54589000776615e-06, + "loss": 0.4812, + "step": 6694 + }, + { + "epoch": 0.56, + "learning_rate": 8.543208959041174e-06, + "loss": 0.4868, + "step": 6695 + }, + { + "epoch": 0.56, + "learning_rate": 8.540528017296876e-06, + "loss": 0.4789, + "step": 6696 + }, + { + "epoch": 0.56, + "learning_rate": 8.537847182730126e-06, + "loss": 0.4894, + "step": 6697 + }, + { + "epoch": 0.56, + "learning_rate": 8.535166455537795e-06, + "loss": 0.4734, + "step": 6698 + }, + { + "epoch": 0.56, + "learning_rate": 8.532485835916754e-06, + "loss": 0.4674, + "step": 6699 + }, + { + "epoch": 0.56, + "learning_rate": 8.529805324063843e-06, + "loss": 0.4828, + "step": 6700 + }, + { + "epoch": 0.56, + "learning_rate": 8.527124920175918e-06, + "loss": 0.4801, + "step": 6701 + }, + { + "epoch": 0.56, + "learning_rate": 8.524444624449812e-06, + "loss": 0.4383, + "step": 6702 + }, + { + "epoch": 0.56, + "learning_rate": 8.521764437082355e-06, + "loss": 0.4693, + "step": 6703 + }, + { + "epoch": 0.56, + "learning_rate": 8.519084358270368e-06, + "loss": 0.4689, + "step": 6704 + }, + { + "epoch": 0.56, + "learning_rate": 8.516404388210668e-06, + "loss": 0.4543, + "step": 6705 + }, + { + "epoch": 0.56, + "learning_rate": 8.513724527100055e-06, + "loss": 0.4868, + "step": 6706 + }, + { + "epoch": 0.56, + "learning_rate": 8.511044775135336e-06, + "loss": 0.4848, + "step": 6707 + }, + { + "epoch": 0.56, + "learning_rate": 8.508365132513296e-06, + "loss": 0.4832, + "step": 6708 + }, + { + "epoch": 0.56, + "learning_rate": 8.505685599430715e-06, + "loss": 0.4872, + "step": 6709 + }, + { + "epoch": 0.56, + "learning_rate": 8.503006176084366e-06, + "loss": 0.4848, + "step": 6710 + }, + { + "epoch": 0.56, + "learning_rate": 8.50032686267102e-06, + "loss": 0.4751, + "step": 6711 + }, + { + "epoch": 0.56, + "learning_rate": 8.497647659387426e-06, + "loss": 0.4748, + "step": 6712 + }, + { + "epoch": 0.56, + "learning_rate": 8.494968566430346e-06, + "loss": 0.4774, + "step": 6713 + }, + { + "epoch": 0.56, + "learning_rate": 8.492289583996511e-06, + "loss": 0.4901, + "step": 6714 + }, + { + "epoch": 0.56, + "learning_rate": 8.489610712282658e-06, + "loss": 0.477, + "step": 6715 + }, + { + "epoch": 0.56, + "learning_rate": 8.486931951485515e-06, + "loss": 0.4673, + "step": 6716 + }, + { + "epoch": 0.56, + "learning_rate": 8.484253301801794e-06, + "loss": 0.4684, + "step": 6717 + }, + { + "epoch": 0.56, + "learning_rate": 8.481574763428208e-06, + "loss": 0.4901, + "step": 6718 + }, + { + "epoch": 0.56, + "learning_rate": 8.47889633656145e-06, + "loss": 0.4841, + "step": 6719 + }, + { + "epoch": 0.56, + "learning_rate": 8.476218021398224e-06, + "loss": 0.4742, + "step": 6720 + }, + { + "epoch": 0.56, + "learning_rate": 8.473539818135205e-06, + "loss": 0.473, + "step": 6721 + }, + { + "epoch": 0.56, + "learning_rate": 8.470861726969075e-06, + "loss": 0.4822, + "step": 6722 + }, + { + "epoch": 0.56, + "learning_rate": 8.4681837480965e-06, + "loss": 0.4779, + "step": 6723 + }, + { + "epoch": 0.56, + "learning_rate": 8.46550588171414e-06, + "loss": 0.4748, + "step": 6724 + }, + { + "epoch": 0.56, + "learning_rate": 8.462828128018642e-06, + "loss": 0.4784, + "step": 6725 + }, + { + "epoch": 0.56, + "learning_rate": 8.460150487206652e-06, + "loss": 0.4835, + "step": 6726 + }, + { + "epoch": 0.56, + "learning_rate": 8.45747295947481e-06, + "loss": 0.4796, + "step": 6727 + }, + { + "epoch": 0.56, + "learning_rate": 8.454795545019737e-06, + "loss": 0.4778, + "step": 6728 + }, + { + "epoch": 0.56, + "learning_rate": 8.452118244038052e-06, + "loss": 0.4831, + "step": 6729 + }, + { + "epoch": 0.56, + "learning_rate": 8.449441056726364e-06, + "loss": 0.4749, + "step": 6730 + }, + { + "epoch": 0.56, + "learning_rate": 8.446763983281276e-06, + "loss": 0.4853, + "step": 6731 + }, + { + "epoch": 0.56, + "learning_rate": 8.444087023899377e-06, + "loss": 0.491, + "step": 6732 + }, + { + "epoch": 0.56, + "learning_rate": 8.44141017877726e-06, + "loss": 0.4564, + "step": 6733 + }, + { + "epoch": 0.56, + "learning_rate": 8.438733448111496e-06, + "loss": 0.4818, + "step": 6734 + }, + { + "epoch": 0.56, + "learning_rate": 8.436056832098655e-06, + "loss": 0.4734, + "step": 6735 + }, + { + "epoch": 0.56, + "learning_rate": 8.433380330935293e-06, + "loss": 0.4585, + "step": 6736 + }, + { + "epoch": 0.56, + "learning_rate": 8.430703944817967e-06, + "loss": 0.4646, + "step": 6737 + }, + { + "epoch": 0.56, + "learning_rate": 8.428027673943213e-06, + "loss": 0.4824, + "step": 6738 + }, + { + "epoch": 0.56, + "learning_rate": 8.425351518507565e-06, + "loss": 0.4706, + "step": 6739 + }, + { + "epoch": 0.56, + "learning_rate": 8.422675478707556e-06, + "loss": 0.4733, + "step": 6740 + }, + { + "epoch": 0.56, + "learning_rate": 8.4199995547397e-06, + "loss": 0.5001, + "step": 6741 + }, + { + "epoch": 0.56, + "learning_rate": 8.417323746800504e-06, + "loss": 0.4803, + "step": 6742 + }, + { + "epoch": 0.56, + "learning_rate": 8.414648055086471e-06, + "loss": 0.4705, + "step": 6743 + }, + { + "epoch": 0.56, + "learning_rate": 8.41197247979409e-06, + "loss": 0.4768, + "step": 6744 + }, + { + "epoch": 0.56, + "learning_rate": 8.409297021119843e-06, + "loss": 0.4859, + "step": 6745 + }, + { + "epoch": 0.56, + "learning_rate": 8.406621679260206e-06, + "loss": 0.4715, + "step": 6746 + }, + { + "epoch": 0.56, + "learning_rate": 8.403946454411645e-06, + "loss": 0.462, + "step": 6747 + }, + { + "epoch": 0.56, + "learning_rate": 8.401271346770622e-06, + "loss": 0.4751, + "step": 6748 + }, + { + "epoch": 0.56, + "learning_rate": 8.398596356533581e-06, + "loss": 0.4768, + "step": 6749 + }, + { + "epoch": 0.56, + "learning_rate": 8.395921483896963e-06, + "loss": 0.471, + "step": 6750 + }, + { + "epoch": 0.56, + "learning_rate": 8.393246729057196e-06, + "loss": 0.5009, + "step": 6751 + }, + { + "epoch": 0.56, + "learning_rate": 8.39057209221071e-06, + "loss": 0.4724, + "step": 6752 + }, + { + "epoch": 0.56, + "learning_rate": 8.38789757355391e-06, + "loss": 0.471, + "step": 6753 + }, + { + "epoch": 0.57, + "learning_rate": 8.38522317328321e-06, + "loss": 0.4789, + "step": 6754 + }, + { + "epoch": 0.57, + "learning_rate": 8.382548891595006e-06, + "loss": 0.4581, + "step": 6755 + }, + { + "epoch": 0.57, + "learning_rate": 8.379874728685681e-06, + "loss": 0.4895, + "step": 6756 + }, + { + "epoch": 0.57, + "learning_rate": 8.37720068475162e-06, + "loss": 0.4833, + "step": 6757 + }, + { + "epoch": 0.57, + "learning_rate": 8.37452675998919e-06, + "loss": 0.4793, + "step": 6758 + }, + { + "epoch": 0.57, + "learning_rate": 8.371852954594755e-06, + "loss": 0.4747, + "step": 6759 + }, + { + "epoch": 0.57, + "learning_rate": 8.369179268764662e-06, + "loss": 0.4749, + "step": 6760 + }, + { + "epoch": 0.57, + "learning_rate": 8.366505702695264e-06, + "loss": 0.4625, + "step": 6761 + }, + { + "epoch": 0.57, + "learning_rate": 8.363832256582892e-06, + "loss": 0.4828, + "step": 6762 + }, + { + "epoch": 0.57, + "learning_rate": 8.361158930623877e-06, + "loss": 0.4782, + "step": 6763 + }, + { + "epoch": 0.57, + "learning_rate": 8.358485725014531e-06, + "loss": 0.4788, + "step": 6764 + }, + { + "epoch": 0.57, + "learning_rate": 8.355812639951168e-06, + "loss": 0.4712, + "step": 6765 + }, + { + "epoch": 0.57, + "learning_rate": 8.35313967563008e-06, + "loss": 0.4894, + "step": 6766 + }, + { + "epoch": 0.57, + "learning_rate": 8.350466832247568e-06, + "loss": 0.4702, + "step": 6767 + }, + { + "epoch": 0.57, + "learning_rate": 8.347794109999912e-06, + "loss": 0.4668, + "step": 6768 + }, + { + "epoch": 0.57, + "learning_rate": 8.345121509083384e-06, + "loss": 0.4578, + "step": 6769 + }, + { + "epoch": 0.57, + "learning_rate": 8.34244902969425e-06, + "loss": 0.4826, + "step": 6770 + }, + { + "epoch": 0.57, + "learning_rate": 8.339776672028765e-06, + "loss": 0.4897, + "step": 6771 + }, + { + "epoch": 0.57, + "learning_rate": 8.337104436283176e-06, + "loss": 0.4767, + "step": 6772 + }, + { + "epoch": 0.57, + "learning_rate": 8.334432322653717e-06, + "loss": 0.5019, + "step": 6773 + }, + { + "epoch": 0.57, + "learning_rate": 8.331760331336622e-06, + "loss": 0.4777, + "step": 6774 + }, + { + "epoch": 0.57, + "learning_rate": 8.329088462528113e-06, + "loss": 0.4643, + "step": 6775 + }, + { + "epoch": 0.57, + "learning_rate": 8.326416716424396e-06, + "loss": 0.4687, + "step": 6776 + }, + { + "epoch": 0.57, + "learning_rate": 8.323745093221672e-06, + "loss": 0.4902, + "step": 6777 + }, + { + "epoch": 0.57, + "learning_rate": 8.32107359311614e-06, + "loss": 0.4804, + "step": 6778 + }, + { + "epoch": 0.57, + "learning_rate": 8.318402216303978e-06, + "loss": 0.4833, + "step": 6779 + }, + { + "epoch": 0.57, + "learning_rate": 8.31573096298136e-06, + "loss": 0.4916, + "step": 6780 + }, + { + "epoch": 0.57, + "learning_rate": 8.313059833344459e-06, + "loss": 0.4769, + "step": 6781 + }, + { + "epoch": 0.57, + "learning_rate": 8.310388827589424e-06, + "loss": 0.4853, + "step": 6782 + }, + { + "epoch": 0.57, + "learning_rate": 8.30771794591241e-06, + "loss": 0.4967, + "step": 6783 + }, + { + "epoch": 0.57, + "learning_rate": 8.30504718850955e-06, + "loss": 0.4618, + "step": 6784 + }, + { + "epoch": 0.57, + "learning_rate": 8.302376555576974e-06, + "loss": 0.4827, + "step": 6785 + }, + { + "epoch": 0.57, + "learning_rate": 8.299706047310803e-06, + "loss": 0.458, + "step": 6786 + }, + { + "epoch": 0.57, + "learning_rate": 8.297035663907146e-06, + "loss": 0.4838, + "step": 6787 + }, + { + "epoch": 0.57, + "learning_rate": 8.294365405562107e-06, + "loss": 0.4725, + "step": 6788 + }, + { + "epoch": 0.57, + "learning_rate": 8.29169527247178e-06, + "loss": 0.4844, + "step": 6789 + }, + { + "epoch": 0.57, + "learning_rate": 8.289025264832247e-06, + "loss": 0.479, + "step": 6790 + }, + { + "epoch": 0.57, + "learning_rate": 8.286355382839584e-06, + "loss": 0.4811, + "step": 6791 + }, + { + "epoch": 0.57, + "learning_rate": 8.283685626689851e-06, + "loss": 0.4781, + "step": 6792 + }, + { + "epoch": 0.57, + "learning_rate": 8.281015996579106e-06, + "loss": 0.4775, + "step": 6793 + }, + { + "epoch": 0.57, + "learning_rate": 8.278346492703394e-06, + "loss": 0.4994, + "step": 6794 + }, + { + "epoch": 0.57, + "learning_rate": 8.275677115258761e-06, + "loss": 0.4812, + "step": 6795 + }, + { + "epoch": 0.57, + "learning_rate": 8.273007864441227e-06, + "loss": 0.4621, + "step": 6796 + }, + { + "epoch": 0.57, + "learning_rate": 8.27033874044681e-06, + "loss": 0.4713, + "step": 6797 + }, + { + "epoch": 0.57, + "learning_rate": 8.267669743471525e-06, + "loss": 0.4923, + "step": 6798 + }, + { + "epoch": 0.57, + "learning_rate": 8.265000873711368e-06, + "loss": 0.4829, + "step": 6799 + }, + { + "epoch": 0.57, + "learning_rate": 8.262332131362326e-06, + "loss": 0.4658, + "step": 6800 + }, + { + "epoch": 0.57, + "learning_rate": 8.259663516620389e-06, + "loss": 0.5034, + "step": 6801 + }, + { + "epoch": 0.57, + "learning_rate": 8.256995029681526e-06, + "loss": 0.4598, + "step": 6802 + }, + { + "epoch": 0.57, + "learning_rate": 8.254326670741694e-06, + "loss": 0.4704, + "step": 6803 + }, + { + "epoch": 0.57, + "learning_rate": 8.251658439996854e-06, + "loss": 0.4928, + "step": 6804 + }, + { + "epoch": 0.57, + "learning_rate": 8.248990337642946e-06, + "loss": 0.4666, + "step": 6805 + }, + { + "epoch": 0.57, + "learning_rate": 8.246322363875904e-06, + "loss": 0.4721, + "step": 6806 + }, + { + "epoch": 0.57, + "learning_rate": 8.24365451889165e-06, + "loss": 0.474, + "step": 6807 + }, + { + "epoch": 0.57, + "learning_rate": 8.240986802886105e-06, + "loss": 0.4743, + "step": 6808 + }, + { + "epoch": 0.57, + "learning_rate": 8.238319216055175e-06, + "loss": 0.4705, + "step": 6809 + }, + { + "epoch": 0.57, + "learning_rate": 8.235651758594753e-06, + "loss": 0.4877, + "step": 6810 + }, + { + "epoch": 0.57, + "learning_rate": 8.23298443070073e-06, + "loss": 0.4727, + "step": 6811 + }, + { + "epoch": 0.57, + "learning_rate": 8.230317232568977e-06, + "loss": 0.4659, + "step": 6812 + }, + { + "epoch": 0.57, + "learning_rate": 8.227650164395369e-06, + "loss": 0.4665, + "step": 6813 + }, + { + "epoch": 0.57, + "learning_rate": 8.224983226375756e-06, + "loss": 0.461, + "step": 6814 + }, + { + "epoch": 0.57, + "learning_rate": 8.222316418705995e-06, + "loss": 0.4809, + "step": 6815 + }, + { + "epoch": 0.57, + "learning_rate": 8.219649741581925e-06, + "loss": 0.4596, + "step": 6816 + }, + { + "epoch": 0.57, + "learning_rate": 8.216983195199372e-06, + "loss": 0.4577, + "step": 6817 + }, + { + "epoch": 0.57, + "learning_rate": 8.214316779754154e-06, + "loss": 0.4787, + "step": 6818 + }, + { + "epoch": 0.57, + "learning_rate": 8.211650495442088e-06, + "loss": 0.4803, + "step": 6819 + }, + { + "epoch": 0.57, + "learning_rate": 8.20898434245897e-06, + "loss": 0.4821, + "step": 6820 + }, + { + "epoch": 0.57, + "learning_rate": 8.206318321000588e-06, + "loss": 0.4678, + "step": 6821 + }, + { + "epoch": 0.57, + "learning_rate": 8.203652431262733e-06, + "loss": 0.501, + "step": 6822 + }, + { + "epoch": 0.57, + "learning_rate": 8.200986673441173e-06, + "loss": 0.4752, + "step": 6823 + }, + { + "epoch": 0.57, + "learning_rate": 8.198321047731665e-06, + "loss": 0.4762, + "step": 6824 + }, + { + "epoch": 0.57, + "learning_rate": 8.195655554329969e-06, + "loss": 0.4846, + "step": 6825 + }, + { + "epoch": 0.57, + "learning_rate": 8.192990193431824e-06, + "loss": 0.4847, + "step": 6826 + }, + { + "epoch": 0.57, + "learning_rate": 8.19032496523296e-06, + "loss": 0.4782, + "step": 6827 + }, + { + "epoch": 0.57, + "learning_rate": 8.187659869929104e-06, + "loss": 0.4777, + "step": 6828 + }, + { + "epoch": 0.57, + "learning_rate": 8.184994907715969e-06, + "loss": 0.4826, + "step": 6829 + }, + { + "epoch": 0.57, + "learning_rate": 8.182330078789262e-06, + "loss": 0.4972, + "step": 6830 + }, + { + "epoch": 0.57, + "learning_rate": 8.179665383344674e-06, + "loss": 0.4655, + "step": 6831 + }, + { + "epoch": 0.57, + "learning_rate": 8.177000821577888e-06, + "loss": 0.4884, + "step": 6832 + }, + { + "epoch": 0.57, + "learning_rate": 8.174336393684577e-06, + "loss": 0.4607, + "step": 6833 + }, + { + "epoch": 0.57, + "learning_rate": 8.17167209986041e-06, + "loss": 0.4567, + "step": 6834 + }, + { + "epoch": 0.57, + "learning_rate": 8.169007940301034e-06, + "loss": 0.4858, + "step": 6835 + }, + { + "epoch": 0.57, + "learning_rate": 8.166343915202106e-06, + "loss": 0.473, + "step": 6836 + }, + { + "epoch": 0.57, + "learning_rate": 8.163680024759252e-06, + "loss": 0.4651, + "step": 6837 + }, + { + "epoch": 0.57, + "learning_rate": 8.161016269168101e-06, + "loss": 0.4667, + "step": 6838 + }, + { + "epoch": 0.57, + "learning_rate": 8.158352648624263e-06, + "loss": 0.5024, + "step": 6839 + }, + { + "epoch": 0.57, + "learning_rate": 8.155689163323348e-06, + "loss": 0.478, + "step": 6840 + }, + { + "epoch": 0.57, + "learning_rate": 8.153025813460947e-06, + "loss": 0.4516, + "step": 6841 + }, + { + "epoch": 0.57, + "learning_rate": 8.15036259923265e-06, + "loss": 0.478, + "step": 6842 + }, + { + "epoch": 0.57, + "learning_rate": 8.147699520834033e-06, + "loss": 0.4709, + "step": 6843 + }, + { + "epoch": 0.57, + "learning_rate": 8.145036578460656e-06, + "loss": 0.4604, + "step": 6844 + }, + { + "epoch": 0.57, + "learning_rate": 8.142373772308078e-06, + "loss": 0.4652, + "step": 6845 + }, + { + "epoch": 0.57, + "learning_rate": 8.139711102571846e-06, + "loss": 0.4943, + "step": 6846 + }, + { + "epoch": 0.57, + "learning_rate": 8.137048569447492e-06, + "loss": 0.4631, + "step": 6847 + }, + { + "epoch": 0.57, + "learning_rate": 8.134386173130539e-06, + "loss": 0.4891, + "step": 6848 + }, + { + "epoch": 0.57, + "learning_rate": 8.131723913816508e-06, + "loss": 0.4725, + "step": 6849 + }, + { + "epoch": 0.57, + "learning_rate": 8.129061791700903e-06, + "loss": 0.4699, + "step": 6850 + }, + { + "epoch": 0.57, + "learning_rate": 8.126399806979217e-06, + "loss": 0.4892, + "step": 6851 + }, + { + "epoch": 0.57, + "learning_rate": 8.123737959846937e-06, + "loss": 0.4647, + "step": 6852 + }, + { + "epoch": 0.57, + "learning_rate": 8.121076250499539e-06, + "loss": 0.4725, + "step": 6853 + }, + { + "epoch": 0.57, + "learning_rate": 8.118414679132484e-06, + "loss": 0.4585, + "step": 6854 + }, + { + "epoch": 0.57, + "learning_rate": 8.115753245941225e-06, + "loss": 0.481, + "step": 6855 + }, + { + "epoch": 0.57, + "learning_rate": 8.113091951121215e-06, + "loss": 0.4593, + "step": 6856 + }, + { + "epoch": 0.57, + "learning_rate": 8.110430794867884e-06, + "loss": 0.4727, + "step": 6857 + }, + { + "epoch": 0.57, + "learning_rate": 8.107769777376657e-06, + "loss": 0.4692, + "step": 6858 + }, + { + "epoch": 0.57, + "learning_rate": 8.105108898842946e-06, + "loss": 0.4705, + "step": 6859 + }, + { + "epoch": 0.57, + "learning_rate": 8.102448159462155e-06, + "loss": 0.4907, + "step": 6860 + }, + { + "epoch": 0.57, + "learning_rate": 8.099787559429682e-06, + "loss": 0.4831, + "step": 6861 + }, + { + "epoch": 0.57, + "learning_rate": 8.0971270989409e-06, + "loss": 0.4815, + "step": 6862 + }, + { + "epoch": 0.57, + "learning_rate": 8.094466778191194e-06, + "loss": 0.4879, + "step": 6863 + }, + { + "epoch": 0.57, + "learning_rate": 8.091806597375925e-06, + "loss": 0.4851, + "step": 6864 + }, + { + "epoch": 0.57, + "learning_rate": 8.089146556690437e-06, + "loss": 0.4682, + "step": 6865 + }, + { + "epoch": 0.57, + "learning_rate": 8.086486656330082e-06, + "loss": 0.4849, + "step": 6866 + }, + { + "epoch": 0.57, + "learning_rate": 8.083826896490186e-06, + "loss": 0.4875, + "step": 6867 + }, + { + "epoch": 0.57, + "learning_rate": 8.081167277366076e-06, + "loss": 0.4755, + "step": 6868 + }, + { + "epoch": 0.57, + "learning_rate": 8.078507799153053e-06, + "loss": 0.4663, + "step": 6869 + }, + { + "epoch": 0.57, + "learning_rate": 8.07584846204643e-06, + "loss": 0.4806, + "step": 6870 + }, + { + "epoch": 0.57, + "learning_rate": 8.073189266241492e-06, + "loss": 0.4771, + "step": 6871 + }, + { + "epoch": 0.57, + "learning_rate": 8.070530211933522e-06, + "loss": 0.4727, + "step": 6872 + }, + { + "epoch": 0.58, + "learning_rate": 8.067871299317786e-06, + "loss": 0.4623, + "step": 6873 + }, + { + "epoch": 0.58, + "learning_rate": 8.065212528589545e-06, + "loss": 0.5038, + "step": 6874 + }, + { + "epoch": 0.58, + "learning_rate": 8.062553899944049e-06, + "loss": 0.4703, + "step": 6875 + }, + { + "epoch": 0.58, + "learning_rate": 8.059895413576535e-06, + "loss": 0.4934, + "step": 6876 + }, + { + "epoch": 0.58, + "learning_rate": 8.057237069682235e-06, + "loss": 0.4898, + "step": 6877 + }, + { + "epoch": 0.58, + "learning_rate": 8.054578868456364e-06, + "loss": 0.4677, + "step": 6878 + }, + { + "epoch": 0.58, + "learning_rate": 8.05192081009413e-06, + "loss": 0.5034, + "step": 6879 + }, + { + "epoch": 0.58, + "learning_rate": 8.049262894790725e-06, + "loss": 0.4796, + "step": 6880 + }, + { + "epoch": 0.58, + "learning_rate": 8.046605122741343e-06, + "loss": 0.4751, + "step": 6881 + }, + { + "epoch": 0.58, + "learning_rate": 8.04394749414115e-06, + "loss": 0.4621, + "step": 6882 + }, + { + "epoch": 0.58, + "learning_rate": 8.041290009185325e-06, + "loss": 0.4772, + "step": 6883 + }, + { + "epoch": 0.58, + "learning_rate": 8.038632668069011e-06, + "loss": 0.471, + "step": 6884 + }, + { + "epoch": 0.58, + "learning_rate": 8.035975470987357e-06, + "loss": 0.4558, + "step": 6885 + }, + { + "epoch": 0.58, + "learning_rate": 8.033318418135494e-06, + "loss": 0.4728, + "step": 6886 + }, + { + "epoch": 0.58, + "learning_rate": 8.03066150970855e-06, + "loss": 0.4667, + "step": 6887 + }, + { + "epoch": 0.58, + "learning_rate": 8.02800474590163e-06, + "loss": 0.4804, + "step": 6888 + }, + { + "epoch": 0.58, + "learning_rate": 8.025348126909837e-06, + "loss": 0.4809, + "step": 6889 + }, + { + "epoch": 0.58, + "learning_rate": 8.02269165292827e-06, + "loss": 0.4799, + "step": 6890 + }, + { + "epoch": 0.58, + "learning_rate": 8.020035324152e-06, + "loss": 0.456, + "step": 6891 + }, + { + "epoch": 0.58, + "learning_rate": 8.017379140776103e-06, + "loss": 0.4874, + "step": 6892 + }, + { + "epoch": 0.58, + "learning_rate": 8.014723102995635e-06, + "loss": 0.4772, + "step": 6893 + }, + { + "epoch": 0.58, + "learning_rate": 8.012067211005645e-06, + "loss": 0.4651, + "step": 6894 + }, + { + "epoch": 0.58, + "learning_rate": 8.00941146500117e-06, + "loss": 0.4828, + "step": 6895 + }, + { + "epoch": 0.58, + "learning_rate": 8.006755865177233e-06, + "loss": 0.4682, + "step": 6896 + }, + { + "epoch": 0.58, + "learning_rate": 8.00410041172886e-06, + "loss": 0.4852, + "step": 6897 + }, + { + "epoch": 0.58, + "learning_rate": 8.001445104851052e-06, + "loss": 0.4691, + "step": 6898 + }, + { + "epoch": 0.58, + "learning_rate": 7.998789944738801e-06, + "loss": 0.4742, + "step": 6899 + }, + { + "epoch": 0.58, + "learning_rate": 7.996134931587092e-06, + "loss": 0.4673, + "step": 6900 + }, + { + "epoch": 0.58, + "learning_rate": 7.993480065590902e-06, + "loss": 0.502, + "step": 6901 + }, + { + "epoch": 0.58, + "learning_rate": 7.990825346945188e-06, + "loss": 0.4744, + "step": 6902 + }, + { + "epoch": 0.58, + "learning_rate": 7.9881707758449e-06, + "loss": 0.4806, + "step": 6903 + }, + { + "epoch": 0.58, + "learning_rate": 7.985516352484987e-06, + "loss": 0.4837, + "step": 6904 + }, + { + "epoch": 0.58, + "learning_rate": 7.982862077060376e-06, + "loss": 0.4685, + "step": 6905 + }, + { + "epoch": 0.58, + "learning_rate": 7.98020794976598e-06, + "loss": 0.466, + "step": 6906 + }, + { + "epoch": 0.58, + "learning_rate": 7.977553970796713e-06, + "loss": 0.4756, + "step": 6907 + }, + { + "epoch": 0.58, + "learning_rate": 7.974900140347473e-06, + "loss": 0.472, + "step": 6908 + }, + { + "epoch": 0.58, + "learning_rate": 7.97224645861314e-06, + "loss": 0.4496, + "step": 6909 + }, + { + "epoch": 0.58, + "learning_rate": 7.969592925788592e-06, + "loss": 0.4872, + "step": 6910 + }, + { + "epoch": 0.58, + "learning_rate": 7.966939542068694e-06, + "loss": 0.4819, + "step": 6911 + }, + { + "epoch": 0.58, + "learning_rate": 7.964286307648305e-06, + "loss": 0.4716, + "step": 6912 + }, + { + "epoch": 0.58, + "learning_rate": 7.96163322272226e-06, + "loss": 0.4722, + "step": 6913 + }, + { + "epoch": 0.58, + "learning_rate": 7.958980287485394e-06, + "loss": 0.4683, + "step": 6914 + }, + { + "epoch": 0.58, + "learning_rate": 7.956327502132523e-06, + "loss": 0.4634, + "step": 6915 + }, + { + "epoch": 0.58, + "learning_rate": 7.953674866858462e-06, + "loss": 0.4692, + "step": 6916 + }, + { + "epoch": 0.58, + "learning_rate": 7.951022381858005e-06, + "loss": 0.4735, + "step": 6917 + }, + { + "epoch": 0.58, + "learning_rate": 7.948370047325946e-06, + "loss": 0.4642, + "step": 6918 + }, + { + "epoch": 0.58, + "learning_rate": 7.945717863457057e-06, + "loss": 0.4884, + "step": 6919 + }, + { + "epoch": 0.58, + "learning_rate": 7.943065830446104e-06, + "loss": 0.4975, + "step": 6920 + }, + { + "epoch": 0.58, + "learning_rate": 7.940413948487838e-06, + "loss": 0.5001, + "step": 6921 + }, + { + "epoch": 0.58, + "learning_rate": 7.937762217777007e-06, + "loss": 0.4835, + "step": 6922 + }, + { + "epoch": 0.58, + "learning_rate": 7.935110638508339e-06, + "loss": 0.4903, + "step": 6923 + }, + { + "epoch": 0.58, + "learning_rate": 7.93245921087656e-06, + "loss": 0.4688, + "step": 6924 + }, + { + "epoch": 0.58, + "learning_rate": 7.929807935076376e-06, + "loss": 0.4764, + "step": 6925 + }, + { + "epoch": 0.58, + "learning_rate": 7.927156811302486e-06, + "loss": 0.4792, + "step": 6926 + }, + { + "epoch": 0.58, + "learning_rate": 7.92450583974958e-06, + "loss": 0.4833, + "step": 6927 + }, + { + "epoch": 0.58, + "learning_rate": 7.921855020612333e-06, + "loss": 0.4812, + "step": 6928 + }, + { + "epoch": 0.58, + "learning_rate": 7.919204354085408e-06, + "loss": 0.4649, + "step": 6929 + }, + { + "epoch": 0.58, + "learning_rate": 7.916553840363458e-06, + "loss": 0.4554, + "step": 6930 + }, + { + "epoch": 0.58, + "learning_rate": 7.913903479641131e-06, + "loss": 0.4636, + "step": 6931 + }, + { + "epoch": 0.58, + "learning_rate": 7.911253272113056e-06, + "loss": 0.5109, + "step": 6932 + }, + { + "epoch": 0.58, + "learning_rate": 7.908603217973853e-06, + "loss": 0.4811, + "step": 6933 + }, + { + "epoch": 0.58, + "learning_rate": 7.905953317418131e-06, + "loss": 0.4753, + "step": 6934 + }, + { + "epoch": 0.58, + "learning_rate": 7.903303570640488e-06, + "loss": 0.4691, + "step": 6935 + }, + { + "epoch": 0.58, + "learning_rate": 7.900653977835507e-06, + "loss": 0.4661, + "step": 6936 + }, + { + "epoch": 0.58, + "learning_rate": 7.898004539197766e-06, + "loss": 0.4696, + "step": 6937 + }, + { + "epoch": 0.58, + "learning_rate": 7.89535525492183e-06, + "loss": 0.4606, + "step": 6938 + }, + { + "epoch": 0.58, + "learning_rate": 7.892706125202254e-06, + "loss": 0.4798, + "step": 6939 + }, + { + "epoch": 0.58, + "learning_rate": 7.890057150233572e-06, + "loss": 0.4586, + "step": 6940 + }, + { + "epoch": 0.58, + "learning_rate": 7.887408330210316e-06, + "loss": 0.4835, + "step": 6941 + }, + { + "epoch": 0.58, + "learning_rate": 7.884759665327008e-06, + "loss": 0.4821, + "step": 6942 + }, + { + "epoch": 0.58, + "learning_rate": 7.882111155778152e-06, + "loss": 0.4927, + "step": 6943 + }, + { + "epoch": 0.58, + "learning_rate": 7.879462801758239e-06, + "loss": 0.4873, + "step": 6944 + }, + { + "epoch": 0.58, + "learning_rate": 7.876814603461763e-06, + "loss": 0.4801, + "step": 6945 + }, + { + "epoch": 0.58, + "learning_rate": 7.87416656108319e-06, + "loss": 0.476, + "step": 6946 + }, + { + "epoch": 0.58, + "learning_rate": 7.871518674816982e-06, + "loss": 0.464, + "step": 6947 + }, + { + "epoch": 0.58, + "learning_rate": 7.86887094485759e-06, + "loss": 0.4831, + "step": 6948 + }, + { + "epoch": 0.58, + "learning_rate": 7.866223371399453e-06, + "loss": 0.4791, + "step": 6949 + }, + { + "epoch": 0.58, + "learning_rate": 7.863575954636993e-06, + "loss": 0.4936, + "step": 6950 + }, + { + "epoch": 0.58, + "learning_rate": 7.860928694764632e-06, + "loss": 0.4846, + "step": 6951 + }, + { + "epoch": 0.58, + "learning_rate": 7.858281591976768e-06, + "loss": 0.4687, + "step": 6952 + }, + { + "epoch": 0.58, + "learning_rate": 7.8556346464678e-06, + "loss": 0.4587, + "step": 6953 + }, + { + "epoch": 0.58, + "learning_rate": 7.852987858432104e-06, + "loss": 0.4825, + "step": 6954 + }, + { + "epoch": 0.58, + "learning_rate": 7.850341228064048e-06, + "loss": 0.4723, + "step": 6955 + }, + { + "epoch": 0.58, + "learning_rate": 7.84769475555799e-06, + "loss": 0.4522, + "step": 6956 + }, + { + "epoch": 0.58, + "learning_rate": 7.845048441108276e-06, + "loss": 0.484, + "step": 6957 + }, + { + "epoch": 0.58, + "learning_rate": 7.842402284909242e-06, + "loss": 0.4794, + "step": 6958 + }, + { + "epoch": 0.58, + "learning_rate": 7.839756287155213e-06, + "loss": 0.4794, + "step": 6959 + }, + { + "epoch": 0.58, + "learning_rate": 7.837110448040495e-06, + "loss": 0.4825, + "step": 6960 + }, + { + "epoch": 0.58, + "learning_rate": 7.834464767759392e-06, + "loss": 0.4612, + "step": 6961 + }, + { + "epoch": 0.58, + "learning_rate": 7.831819246506187e-06, + "loss": 0.4708, + "step": 6962 + }, + { + "epoch": 0.58, + "learning_rate": 7.829173884475158e-06, + "loss": 0.4607, + "step": 6963 + }, + { + "epoch": 0.58, + "learning_rate": 7.826528681860567e-06, + "loss": 0.4605, + "step": 6964 + }, + { + "epoch": 0.58, + "learning_rate": 7.823883638856675e-06, + "loss": 0.4779, + "step": 6965 + }, + { + "epoch": 0.58, + "learning_rate": 7.821238755657716e-06, + "loss": 0.4447, + "step": 6966 + }, + { + "epoch": 0.58, + "learning_rate": 7.818594032457922e-06, + "loss": 0.4876, + "step": 6967 + }, + { + "epoch": 0.58, + "learning_rate": 7.815949469451506e-06, + "loss": 0.4654, + "step": 6968 + }, + { + "epoch": 0.58, + "learning_rate": 7.813305066832679e-06, + "loss": 0.4654, + "step": 6969 + }, + { + "epoch": 0.58, + "learning_rate": 7.810660824795632e-06, + "loss": 0.4729, + "step": 6970 + }, + { + "epoch": 0.58, + "learning_rate": 7.808016743534546e-06, + "loss": 0.4886, + "step": 6971 + }, + { + "epoch": 0.58, + "learning_rate": 7.805372823243595e-06, + "loss": 0.4669, + "step": 6972 + }, + { + "epoch": 0.58, + "learning_rate": 7.802729064116933e-06, + "loss": 0.4781, + "step": 6973 + }, + { + "epoch": 0.58, + "learning_rate": 7.800085466348715e-06, + "loss": 0.485, + "step": 6974 + }, + { + "epoch": 0.58, + "learning_rate": 7.797442030133067e-06, + "loss": 0.4754, + "step": 6975 + }, + { + "epoch": 0.58, + "learning_rate": 7.794798755664116e-06, + "loss": 0.4706, + "step": 6976 + }, + { + "epoch": 0.58, + "learning_rate": 7.79215564313597e-06, + "loss": 0.476, + "step": 6977 + }, + { + "epoch": 0.58, + "learning_rate": 7.789512692742731e-06, + "loss": 0.4709, + "step": 6978 + }, + { + "epoch": 0.58, + "learning_rate": 7.786869904678486e-06, + "loss": 0.481, + "step": 6979 + }, + { + "epoch": 0.58, + "learning_rate": 7.784227279137314e-06, + "loss": 0.4754, + "step": 6980 + }, + { + "epoch": 0.58, + "learning_rate": 7.781584816313271e-06, + "loss": 0.4683, + "step": 6981 + }, + { + "epoch": 0.58, + "learning_rate": 7.778942516400413e-06, + "loss": 0.4823, + "step": 6982 + }, + { + "epoch": 0.58, + "learning_rate": 7.776300379592778e-06, + "loss": 0.4723, + "step": 6983 + }, + { + "epoch": 0.58, + "learning_rate": 7.773658406084395e-06, + "loss": 0.4722, + "step": 6984 + }, + { + "epoch": 0.58, + "learning_rate": 7.771016596069273e-06, + "loss": 0.478, + "step": 6985 + }, + { + "epoch": 0.58, + "learning_rate": 7.768374949741427e-06, + "loss": 0.474, + "step": 6986 + }, + { + "epoch": 0.58, + "learning_rate": 7.765733467294842e-06, + "loss": 0.4582, + "step": 6987 + }, + { + "epoch": 0.58, + "learning_rate": 7.763092148923496e-06, + "loss": 0.4778, + "step": 6988 + }, + { + "epoch": 0.58, + "learning_rate": 7.760450994821363e-06, + "loss": 0.4914, + "step": 6989 + }, + { + "epoch": 0.58, + "learning_rate": 7.757810005182391e-06, + "loss": 0.4729, + "step": 6990 + }, + { + "epoch": 0.58, + "learning_rate": 7.755169180200524e-06, + "loss": 0.4858, + "step": 6991 + }, + { + "epoch": 0.58, + "learning_rate": 7.752528520069697e-06, + "loss": 0.4731, + "step": 6992 + }, + { + "epoch": 0.59, + "learning_rate": 7.74988802498383e-06, + "loss": 0.4915, + "step": 6993 + }, + { + "epoch": 0.59, + "learning_rate": 7.747247695136825e-06, + "loss": 0.4868, + "step": 6994 + }, + { + "epoch": 0.59, + "learning_rate": 7.74460753072258e-06, + "loss": 0.484, + "step": 6995 + }, + { + "epoch": 0.59, + "learning_rate": 7.74196753193498e-06, + "loss": 0.4831, + "step": 6996 + }, + { + "epoch": 0.59, + "learning_rate": 7.739327698967891e-06, + "loss": 0.4833, + "step": 6997 + }, + { + "epoch": 0.59, + "learning_rate": 7.736688032015168e-06, + "loss": 0.4727, + "step": 6998 + }, + { + "epoch": 0.59, + "learning_rate": 7.734048531270664e-06, + "loss": 0.4703, + "step": 6999 + }, + { + "epoch": 0.59, + "learning_rate": 7.731409196928214e-06, + "loss": 0.438, + "step": 7000 + }, + { + "epoch": 0.59, + "learning_rate": 7.728770029181638e-06, + "loss": 0.4715, + "step": 7001 + }, + { + "epoch": 0.59, + "learning_rate": 7.726131028224742e-06, + "loss": 0.4702, + "step": 7002 + }, + { + "epoch": 0.59, + "learning_rate": 7.723492194251326e-06, + "loss": 0.4689, + "step": 7003 + }, + { + "epoch": 0.59, + "learning_rate": 7.720853527455174e-06, + "loss": 0.4701, + "step": 7004 + }, + { + "epoch": 0.59, + "learning_rate": 7.718215028030056e-06, + "loss": 0.475, + "step": 7005 + }, + { + "epoch": 0.59, + "learning_rate": 7.71557669616974e-06, + "loss": 0.4504, + "step": 7006 + }, + { + "epoch": 0.59, + "learning_rate": 7.71293853206797e-06, + "loss": 0.4582, + "step": 7007 + }, + { + "epoch": 0.59, + "learning_rate": 7.710300535918482e-06, + "loss": 0.4723, + "step": 7008 + }, + { + "epoch": 0.59, + "learning_rate": 7.707662707914997e-06, + "loss": 0.4739, + "step": 7009 + }, + { + "epoch": 0.59, + "learning_rate": 7.705025048251228e-06, + "loss": 0.4664, + "step": 7010 + }, + { + "epoch": 0.59, + "learning_rate": 7.702387557120876e-06, + "loss": 0.4789, + "step": 7011 + }, + { + "epoch": 0.59, + "learning_rate": 7.699750234717622e-06, + "loss": 0.4828, + "step": 7012 + }, + { + "epoch": 0.59, + "learning_rate": 7.697113081235147e-06, + "loss": 0.4587, + "step": 7013 + }, + { + "epoch": 0.59, + "learning_rate": 7.694476096867105e-06, + "loss": 0.4863, + "step": 7014 + }, + { + "epoch": 0.59, + "learning_rate": 7.691839281807153e-06, + "loss": 0.4657, + "step": 7015 + }, + { + "epoch": 0.59, + "learning_rate": 7.689202636248923e-06, + "loss": 0.4932, + "step": 7016 + }, + { + "epoch": 0.59, + "learning_rate": 7.68656616038604e-06, + "loss": 0.4581, + "step": 7017 + }, + { + "epoch": 0.59, + "learning_rate": 7.683929854412114e-06, + "loss": 0.4734, + "step": 7018 + }, + { + "epoch": 0.59, + "learning_rate": 7.681293718520746e-06, + "loss": 0.4629, + "step": 7019 + }, + { + "epoch": 0.59, + "learning_rate": 7.678657752905522e-06, + "loss": 0.4578, + "step": 7020 + }, + { + "epoch": 0.59, + "learning_rate": 7.676021957760023e-06, + "loss": 0.4507, + "step": 7021 + }, + { + "epoch": 0.59, + "learning_rate": 7.673386333277802e-06, + "loss": 0.4571, + "step": 7022 + }, + { + "epoch": 0.59, + "learning_rate": 7.670750879652414e-06, + "loss": 0.4914, + "step": 7023 + }, + { + "epoch": 0.59, + "learning_rate": 7.668115597077388e-06, + "loss": 0.4869, + "step": 7024 + }, + { + "epoch": 0.59, + "learning_rate": 7.665480485746255e-06, + "loss": 0.4831, + "step": 7025 + }, + { + "epoch": 0.59, + "learning_rate": 7.662845545852526e-06, + "loss": 0.4795, + "step": 7026 + }, + { + "epoch": 0.59, + "learning_rate": 7.6602107775897e-06, + "loss": 0.4938, + "step": 7027 + }, + { + "epoch": 0.59, + "learning_rate": 7.657576181151266e-06, + "loss": 0.4709, + "step": 7028 + }, + { + "epoch": 0.59, + "learning_rate": 7.654941756730687e-06, + "loss": 0.4714, + "step": 7029 + }, + { + "epoch": 0.59, + "learning_rate": 7.652307504521437e-06, + "loss": 0.4525, + "step": 7030 + }, + { + "epoch": 0.59, + "learning_rate": 7.649673424716958e-06, + "loss": 0.4659, + "step": 7031 + }, + { + "epoch": 0.59, + "learning_rate": 7.647039517510685e-06, + "loss": 0.4626, + "step": 7032 + }, + { + "epoch": 0.59, + "learning_rate": 7.644405783096044e-06, + "loss": 0.4977, + "step": 7033 + }, + { + "epoch": 0.59, + "learning_rate": 7.641772221666446e-06, + "loss": 0.4793, + "step": 7034 + }, + { + "epoch": 0.59, + "learning_rate": 7.639138833415285e-06, + "loss": 0.4711, + "step": 7035 + }, + { + "epoch": 0.59, + "learning_rate": 7.636505618535953e-06, + "loss": 0.4851, + "step": 7036 + }, + { + "epoch": 0.59, + "learning_rate": 7.633872577221815e-06, + "loss": 0.4648, + "step": 7037 + }, + { + "epoch": 0.59, + "learning_rate": 7.631239709666234e-06, + "loss": 0.4492, + "step": 7038 + }, + { + "epoch": 0.59, + "learning_rate": 7.628607016062553e-06, + "loss": 0.4862, + "step": 7039 + }, + { + "epoch": 0.59, + "learning_rate": 7.625974496604109e-06, + "loss": 0.4618, + "step": 7040 + }, + { + "epoch": 0.59, + "learning_rate": 7.623342151484229e-06, + "loss": 0.457, + "step": 7041 + }, + { + "epoch": 0.59, + "learning_rate": 7.620709980896215e-06, + "loss": 0.4916, + "step": 7042 + }, + { + "epoch": 0.59, + "learning_rate": 7.618077985033363e-06, + "loss": 0.5061, + "step": 7043 + }, + { + "epoch": 0.59, + "learning_rate": 7.6154461640889555e-06, + "loss": 0.4657, + "step": 7044 + }, + { + "epoch": 0.59, + "learning_rate": 7.612814518256265e-06, + "loss": 0.4678, + "step": 7045 + }, + { + "epoch": 0.59, + "learning_rate": 7.610183047728543e-06, + "loss": 0.4981, + "step": 7046 + }, + { + "epoch": 0.59, + "learning_rate": 7.607551752699043e-06, + "loss": 0.4745, + "step": 7047 + }, + { + "epoch": 0.59, + "learning_rate": 7.604920633360991e-06, + "loss": 0.4684, + "step": 7048 + }, + { + "epoch": 0.59, + "learning_rate": 7.6022896899076045e-06, + "loss": 0.4702, + "step": 7049 + }, + { + "epoch": 0.59, + "learning_rate": 7.59965892253209e-06, + "loss": 0.4809, + "step": 7050 + }, + { + "epoch": 0.59, + "learning_rate": 7.597028331427643e-06, + "loss": 0.4865, + "step": 7051 + }, + { + "epoch": 0.59, + "learning_rate": 7.594397916787439e-06, + "loss": 0.4956, + "step": 7052 + }, + { + "epoch": 0.59, + "learning_rate": 7.591767678804642e-06, + "loss": 0.4843, + "step": 7053 + }, + { + "epoch": 0.59, + "learning_rate": 7.589137617672415e-06, + "loss": 0.4779, + "step": 7054 + }, + { + "epoch": 0.59, + "learning_rate": 7.586507733583892e-06, + "loss": 0.4786, + "step": 7055 + }, + { + "epoch": 0.59, + "learning_rate": 7.583878026732204e-06, + "loss": 0.4609, + "step": 7056 + }, + { + "epoch": 0.59, + "learning_rate": 7.581248497310465e-06, + "loss": 0.4686, + "step": 7057 + }, + { + "epoch": 0.59, + "learning_rate": 7.5786191455117765e-06, + "loss": 0.479, + "step": 7058 + }, + { + "epoch": 0.59, + "learning_rate": 7.575989971529223e-06, + "loss": 0.4769, + "step": 7059 + }, + { + "epoch": 0.59, + "learning_rate": 7.573360975555885e-06, + "loss": 0.4699, + "step": 7060 + }, + { + "epoch": 0.59, + "learning_rate": 7.570732157784823e-06, + "loss": 0.5061, + "step": 7061 + }, + { + "epoch": 0.59, + "learning_rate": 7.56810351840909e-06, + "loss": 0.4889, + "step": 7062 + }, + { + "epoch": 0.59, + "learning_rate": 7.56547505762172e-06, + "loss": 0.4664, + "step": 7063 + }, + { + "epoch": 0.59, + "learning_rate": 7.562846775615734e-06, + "loss": 0.4808, + "step": 7064 + }, + { + "epoch": 0.59, + "learning_rate": 7.560218672584143e-06, + "loss": 0.487, + "step": 7065 + }, + { + "epoch": 0.59, + "learning_rate": 7.557590748719943e-06, + "loss": 0.4975, + "step": 7066 + }, + { + "epoch": 0.59, + "learning_rate": 7.5549630042161236e-06, + "loss": 0.4613, + "step": 7067 + }, + { + "epoch": 0.59, + "learning_rate": 7.552335439265652e-06, + "loss": 0.4905, + "step": 7068 + }, + { + "epoch": 0.59, + "learning_rate": 7.549708054061484e-06, + "loss": 0.4649, + "step": 7069 + }, + { + "epoch": 0.59, + "learning_rate": 7.547080848796564e-06, + "loss": 0.5153, + "step": 7070 + }, + { + "epoch": 0.59, + "learning_rate": 7.544453823663825e-06, + "loss": 0.4835, + "step": 7071 + }, + { + "epoch": 0.59, + "learning_rate": 7.541826978856185e-06, + "loss": 0.4816, + "step": 7072 + }, + { + "epoch": 0.59, + "learning_rate": 7.539200314566543e-06, + "loss": 0.465, + "step": 7073 + }, + { + "epoch": 0.59, + "learning_rate": 7.536573830987798e-06, + "loss": 0.4549, + "step": 7074 + }, + { + "epoch": 0.59, + "learning_rate": 7.533947528312825e-06, + "loss": 0.4682, + "step": 7075 + }, + { + "epoch": 0.59, + "learning_rate": 7.531321406734486e-06, + "loss": 0.456, + "step": 7076 + }, + { + "epoch": 0.59, + "learning_rate": 7.528695466445638e-06, + "loss": 0.4794, + "step": 7077 + }, + { + "epoch": 0.59, + "learning_rate": 7.526069707639115e-06, + "loss": 0.461, + "step": 7078 + }, + { + "epoch": 0.59, + "learning_rate": 7.523444130507743e-06, + "loss": 0.4683, + "step": 7079 + }, + { + "epoch": 0.59, + "learning_rate": 7.52081873524433e-06, + "loss": 0.471, + "step": 7080 + }, + { + "epoch": 0.59, + "learning_rate": 7.518193522041679e-06, + "loss": 0.4773, + "step": 7081 + }, + { + "epoch": 0.59, + "learning_rate": 7.5155684910925754e-06, + "loss": 0.472, + "step": 7082 + }, + { + "epoch": 0.59, + "learning_rate": 7.5129436425897876e-06, + "loss": 0.4755, + "step": 7083 + }, + { + "epoch": 0.59, + "learning_rate": 7.510318976726074e-06, + "loss": 0.4634, + "step": 7084 + }, + { + "epoch": 0.59, + "learning_rate": 7.507694493694179e-06, + "loss": 0.476, + "step": 7085 + }, + { + "epoch": 0.59, + "learning_rate": 7.505070193686835e-06, + "loss": 0.4749, + "step": 7086 + }, + { + "epoch": 0.59, + "learning_rate": 7.502446076896754e-06, + "loss": 0.4622, + "step": 7087 + }, + { + "epoch": 0.59, + "learning_rate": 7.4998221435166504e-06, + "loss": 0.4815, + "step": 7088 + }, + { + "epoch": 0.59, + "learning_rate": 7.497198393739209e-06, + "loss": 0.4569, + "step": 7089 + }, + { + "epoch": 0.59, + "learning_rate": 7.494574827757107e-06, + "loss": 0.4719, + "step": 7090 + }, + { + "epoch": 0.59, + "learning_rate": 7.4919514457630085e-06, + "loss": 0.4518, + "step": 7091 + }, + { + "epoch": 0.59, + "learning_rate": 7.489328247949565e-06, + "loss": 0.4851, + "step": 7092 + }, + { + "epoch": 0.59, + "learning_rate": 7.486705234509412e-06, + "loss": 0.4957, + "step": 7093 + }, + { + "epoch": 0.59, + "learning_rate": 7.484082405635169e-06, + "loss": 0.4889, + "step": 7094 + }, + { + "epoch": 0.59, + "learning_rate": 7.481459761519454e-06, + "loss": 0.4776, + "step": 7095 + }, + { + "epoch": 0.59, + "learning_rate": 7.478837302354859e-06, + "loss": 0.4728, + "step": 7096 + }, + { + "epoch": 0.59, + "learning_rate": 7.476215028333964e-06, + "loss": 0.4643, + "step": 7097 + }, + { + "epoch": 0.59, + "learning_rate": 7.473592939649341e-06, + "loss": 0.468, + "step": 7098 + }, + { + "epoch": 0.59, + "learning_rate": 7.470971036493546e-06, + "loss": 0.4845, + "step": 7099 + }, + { + "epoch": 0.59, + "learning_rate": 7.468349319059114e-06, + "loss": 0.4818, + "step": 7100 + }, + { + "epoch": 0.59, + "learning_rate": 7.465727787538584e-06, + "loss": 0.4749, + "step": 7101 + }, + { + "epoch": 0.59, + "learning_rate": 7.463106442124459e-06, + "loss": 0.477, + "step": 7102 + }, + { + "epoch": 0.59, + "learning_rate": 7.46048528300925e-06, + "loss": 0.4793, + "step": 7103 + }, + { + "epoch": 0.59, + "learning_rate": 7.457864310385439e-06, + "loss": 0.4767, + "step": 7104 + }, + { + "epoch": 0.59, + "learning_rate": 7.455243524445499e-06, + "loss": 0.474, + "step": 7105 + }, + { + "epoch": 0.59, + "learning_rate": 7.452622925381887e-06, + "loss": 0.4725, + "step": 7106 + }, + { + "epoch": 0.59, + "learning_rate": 7.450002513387053e-06, + "loss": 0.4833, + "step": 7107 + }, + { + "epoch": 0.59, + "learning_rate": 7.4473822886534285e-06, + "loss": 0.4849, + "step": 7108 + }, + { + "epoch": 0.59, + "learning_rate": 7.444762251373433e-06, + "loss": 0.498, + "step": 7109 + }, + { + "epoch": 0.59, + "learning_rate": 7.442142401739469e-06, + "loss": 0.4671, + "step": 7110 + }, + { + "epoch": 0.59, + "learning_rate": 7.439522739943929e-06, + "loss": 0.4719, + "step": 7111 + }, + { + "epoch": 0.6, + "learning_rate": 7.436903266179187e-06, + "loss": 0.4683, + "step": 7112 + }, + { + "epoch": 0.6, + "learning_rate": 7.434283980637611e-06, + "loss": 0.4745, + "step": 7113 + }, + { + "epoch": 0.6, + "learning_rate": 7.4316648835115445e-06, + "loss": 0.4699, + "step": 7114 + }, + { + "epoch": 0.6, + "learning_rate": 7.4290459749933296e-06, + "loss": 0.4847, + "step": 7115 + }, + { + "epoch": 0.6, + "learning_rate": 7.426427255275284e-06, + "loss": 0.5188, + "step": 7116 + }, + { + "epoch": 0.6, + "learning_rate": 7.423808724549715e-06, + "loss": 0.483, + "step": 7117 + }, + { + "epoch": 0.6, + "learning_rate": 7.421190383008921e-06, + "loss": 0.4699, + "step": 7118 + }, + { + "epoch": 0.6, + "learning_rate": 7.418572230845178e-06, + "loss": 0.4695, + "step": 7119 + }, + { + "epoch": 0.6, + "learning_rate": 7.4159542682507535e-06, + "loss": 0.4848, + "step": 7120 + }, + { + "epoch": 0.6, + "learning_rate": 7.413336495417896e-06, + "loss": 0.4621, + "step": 7121 + }, + { + "epoch": 0.6, + "learning_rate": 7.410718912538853e-06, + "loss": 0.464, + "step": 7122 + }, + { + "epoch": 0.6, + "learning_rate": 7.40810151980584e-06, + "loss": 0.4818, + "step": 7123 + }, + { + "epoch": 0.6, + "learning_rate": 7.405484317411071e-06, + "loss": 0.4593, + "step": 7124 + }, + { + "epoch": 0.6, + "learning_rate": 7.4028673055467456e-06, + "loss": 0.4669, + "step": 7125 + }, + { + "epoch": 0.6, + "learning_rate": 7.400250484405041e-06, + "loss": 0.4662, + "step": 7126 + }, + { + "epoch": 0.6, + "learning_rate": 7.397633854178125e-06, + "loss": 0.4847, + "step": 7127 + }, + { + "epoch": 0.6, + "learning_rate": 7.395017415058154e-06, + "loss": 0.4946, + "step": 7128 + }, + { + "epoch": 0.6, + "learning_rate": 7.3924011672372745e-06, + "loss": 0.4734, + "step": 7129 + }, + { + "epoch": 0.6, + "learning_rate": 7.3897851109076055e-06, + "loss": 0.4795, + "step": 7130 + }, + { + "epoch": 0.6, + "learning_rate": 7.387169246261262e-06, + "loss": 0.4637, + "step": 7131 + }, + { + "epoch": 0.6, + "learning_rate": 7.3845535734903385e-06, + "loss": 0.4562, + "step": 7132 + }, + { + "epoch": 0.6, + "learning_rate": 7.381938092786926e-06, + "loss": 0.4704, + "step": 7133 + }, + { + "epoch": 0.6, + "learning_rate": 7.37932280434309e-06, + "loss": 0.5288, + "step": 7134 + }, + { + "epoch": 0.6, + "learning_rate": 7.376707708350881e-06, + "loss": 0.4919, + "step": 7135 + }, + { + "epoch": 0.6, + "learning_rate": 7.374092805002353e-06, + "loss": 0.476, + "step": 7136 + }, + { + "epoch": 0.6, + "learning_rate": 7.371478094489526e-06, + "loss": 0.4844, + "step": 7137 + }, + { + "epoch": 0.6, + "learning_rate": 7.368863577004415e-06, + "loss": 0.4514, + "step": 7138 + }, + { + "epoch": 0.6, + "learning_rate": 7.3662492527390195e-06, + "loss": 0.4578, + "step": 7139 + }, + { + "epoch": 0.6, + "learning_rate": 7.363635121885324e-06, + "loss": 0.4904, + "step": 7140 + }, + { + "epoch": 0.6, + "learning_rate": 7.361021184635296e-06, + "loss": 0.4677, + "step": 7141 + }, + { + "epoch": 0.6, + "learning_rate": 7.358407441180901e-06, + "loss": 0.4727, + "step": 7142 + }, + { + "epoch": 0.6, + "learning_rate": 7.355793891714073e-06, + "loss": 0.4931, + "step": 7143 + }, + { + "epoch": 0.6, + "learning_rate": 7.353180536426746e-06, + "loss": 0.4635, + "step": 7144 + }, + { + "epoch": 0.6, + "learning_rate": 7.350567375510831e-06, + "loss": 0.4627, + "step": 7145 + }, + { + "epoch": 0.6, + "learning_rate": 7.347954409158229e-06, + "loss": 0.4851, + "step": 7146 + }, + { + "epoch": 0.6, + "learning_rate": 7.345341637560822e-06, + "loss": 0.4668, + "step": 7147 + }, + { + "epoch": 0.6, + "learning_rate": 7.3427290609104825e-06, + "loss": 0.4759, + "step": 7148 + }, + { + "epoch": 0.6, + "learning_rate": 7.34011667939907e-06, + "loss": 0.4839, + "step": 7149 + }, + { + "epoch": 0.6, + "learning_rate": 7.337504493218427e-06, + "loss": 0.4695, + "step": 7150 + }, + { + "epoch": 0.6, + "learning_rate": 7.33489250256038e-06, + "loss": 0.4707, + "step": 7151 + }, + { + "epoch": 0.6, + "learning_rate": 7.332280707616742e-06, + "loss": 0.4862, + "step": 7152 + }, + { + "epoch": 0.6, + "learning_rate": 7.329669108579312e-06, + "loss": 0.4982, + "step": 7153 + }, + { + "epoch": 0.6, + "learning_rate": 7.3270577056398765e-06, + "loss": 0.4853, + "step": 7154 + }, + { + "epoch": 0.6, + "learning_rate": 7.324446498990202e-06, + "loss": 0.46, + "step": 7155 + }, + { + "epoch": 0.6, + "learning_rate": 7.321835488822052e-06, + "loss": 0.489, + "step": 7156 + }, + { + "epoch": 0.6, + "learning_rate": 7.319224675327165e-06, + "loss": 0.4728, + "step": 7157 + }, + { + "epoch": 0.6, + "learning_rate": 7.316614058697264e-06, + "loss": 0.4661, + "step": 7158 + }, + { + "epoch": 0.6, + "learning_rate": 7.31400363912407e-06, + "loss": 0.4589, + "step": 7159 + }, + { + "epoch": 0.6, + "learning_rate": 7.311393416799275e-06, + "loss": 0.477, + "step": 7160 + }, + { + "epoch": 0.6, + "learning_rate": 7.308783391914566e-06, + "loss": 0.4748, + "step": 7161 + }, + { + "epoch": 0.6, + "learning_rate": 7.306173564661606e-06, + "loss": 0.4859, + "step": 7162 + }, + { + "epoch": 0.6, + "learning_rate": 7.303563935232059e-06, + "loss": 0.4681, + "step": 7163 + }, + { + "epoch": 0.6, + "learning_rate": 7.30095450381756e-06, + "loss": 0.4732, + "step": 7164 + }, + { + "epoch": 0.6, + "learning_rate": 7.298345270609738e-06, + "loss": 0.4953, + "step": 7165 + }, + { + "epoch": 0.6, + "learning_rate": 7.295736235800202e-06, + "loss": 0.4648, + "step": 7166 + }, + { + "epoch": 0.6, + "learning_rate": 7.293127399580548e-06, + "loss": 0.4667, + "step": 7167 + }, + { + "epoch": 0.6, + "learning_rate": 7.290518762142359e-06, + "loss": 0.4753, + "step": 7168 + }, + { + "epoch": 0.6, + "learning_rate": 7.287910323677199e-06, + "loss": 0.4855, + "step": 7169 + }, + { + "epoch": 0.6, + "learning_rate": 7.285302084376629e-06, + "loss": 0.4779, + "step": 7170 + }, + { + "epoch": 0.6, + "learning_rate": 7.282694044432182e-06, + "loss": 0.4729, + "step": 7171 + }, + { + "epoch": 0.6, + "learning_rate": 7.2800862040353834e-06, + "loss": 0.4795, + "step": 7172 + }, + { + "epoch": 0.6, + "learning_rate": 7.277478563377738e-06, + "loss": 0.4546, + "step": 7173 + }, + { + "epoch": 0.6, + "learning_rate": 7.274871122650746e-06, + "loss": 0.4783, + "step": 7174 + }, + { + "epoch": 0.6, + "learning_rate": 7.272263882045884e-06, + "loss": 0.484, + "step": 7175 + }, + { + "epoch": 0.6, + "learning_rate": 7.269656841754612e-06, + "loss": 0.4802, + "step": 7176 + }, + { + "epoch": 0.6, + "learning_rate": 7.2670500019683895e-06, + "loss": 0.4704, + "step": 7177 + }, + { + "epoch": 0.6, + "learning_rate": 7.264443362878648e-06, + "loss": 0.4744, + "step": 7178 + }, + { + "epoch": 0.6, + "learning_rate": 7.261836924676806e-06, + "loss": 0.4763, + "step": 7179 + }, + { + "epoch": 0.6, + "learning_rate": 7.259230687554273e-06, + "loss": 0.4847, + "step": 7180 + }, + { + "epoch": 0.6, + "learning_rate": 7.25662465170244e-06, + "loss": 0.4645, + "step": 7181 + }, + { + "epoch": 0.6, + "learning_rate": 7.254018817312676e-06, + "loss": 0.4808, + "step": 7182 + }, + { + "epoch": 0.6, + "learning_rate": 7.2514131845763535e-06, + "loss": 0.4698, + "step": 7183 + }, + { + "epoch": 0.6, + "learning_rate": 7.248807753684812e-06, + "loss": 0.4562, + "step": 7184 + }, + { + "epoch": 0.6, + "learning_rate": 7.246202524829389e-06, + "loss": 0.4745, + "step": 7185 + }, + { + "epoch": 0.6, + "learning_rate": 7.243597498201398e-06, + "loss": 0.474, + "step": 7186 + }, + { + "epoch": 0.6, + "learning_rate": 7.240992673992142e-06, + "loss": 0.4557, + "step": 7187 + }, + { + "epoch": 0.6, + "learning_rate": 7.238388052392906e-06, + "loss": 0.4624, + "step": 7188 + }, + { + "epoch": 0.6, + "learning_rate": 7.235783633594966e-06, + "loss": 0.4785, + "step": 7189 + }, + { + "epoch": 0.6, + "learning_rate": 7.2331794177895785e-06, + "loss": 0.4791, + "step": 7190 + }, + { + "epoch": 0.6, + "learning_rate": 7.230575405167989e-06, + "loss": 0.4867, + "step": 7191 + }, + { + "epoch": 0.6, + "learning_rate": 7.2279715959214216e-06, + "loss": 0.473, + "step": 7192 + }, + { + "epoch": 0.6, + "learning_rate": 7.2253679902410914e-06, + "loss": 0.4794, + "step": 7193 + }, + { + "epoch": 0.6, + "learning_rate": 7.2227645883181926e-06, + "loss": 0.4752, + "step": 7194 + }, + { + "epoch": 0.6, + "learning_rate": 7.220161390343914e-06, + "loss": 0.4562, + "step": 7195 + }, + { + "epoch": 0.6, + "learning_rate": 7.217558396509416e-06, + "loss": 0.4697, + "step": 7196 + }, + { + "epoch": 0.6, + "learning_rate": 7.214955607005861e-06, + "loss": 0.479, + "step": 7197 + }, + { + "epoch": 0.6, + "learning_rate": 7.212353022024381e-06, + "loss": 0.4691, + "step": 7198 + }, + { + "epoch": 0.6, + "learning_rate": 7.209750641756099e-06, + "loss": 0.5009, + "step": 7199 + }, + { + "epoch": 0.6, + "learning_rate": 7.2071484663921265e-06, + "loss": 0.4813, + "step": 7200 + }, + { + "epoch": 0.6, + "learning_rate": 7.2045464961235545e-06, + "loss": 0.4723, + "step": 7201 + }, + { + "epoch": 0.6, + "learning_rate": 7.2019447311414615e-06, + "loss": 0.4889, + "step": 7202 + }, + { + "epoch": 0.6, + "learning_rate": 7.199343171636903e-06, + "loss": 0.4896, + "step": 7203 + }, + { + "epoch": 0.6, + "learning_rate": 7.1967418178009396e-06, + "loss": 0.4664, + "step": 7204 + }, + { + "epoch": 0.6, + "learning_rate": 7.1941406698245945e-06, + "loss": 0.465, + "step": 7205 + }, + { + "epoch": 0.6, + "learning_rate": 7.1915397278988895e-06, + "loss": 0.4895, + "step": 7206 + }, + { + "epoch": 0.6, + "learning_rate": 7.188938992214827e-06, + "loss": 0.4543, + "step": 7207 + }, + { + "epoch": 0.6, + "learning_rate": 7.186338462963392e-06, + "loss": 0.4568, + "step": 7208 + }, + { + "epoch": 0.6, + "learning_rate": 7.183738140335556e-06, + "loss": 0.4777, + "step": 7209 + }, + { + "epoch": 0.6, + "learning_rate": 7.181138024522274e-06, + "loss": 0.4731, + "step": 7210 + }, + { + "epoch": 0.6, + "learning_rate": 7.1785381157144954e-06, + "loss": 0.4658, + "step": 7211 + }, + { + "epoch": 0.6, + "learning_rate": 7.175938414103143e-06, + "loss": 0.4924, + "step": 7212 + }, + { + "epoch": 0.6, + "learning_rate": 7.173338919879127e-06, + "loss": 0.4749, + "step": 7213 + }, + { + "epoch": 0.6, + "learning_rate": 7.170739633233341e-06, + "loss": 0.46, + "step": 7214 + }, + { + "epoch": 0.6, + "learning_rate": 7.168140554356671e-06, + "loss": 0.486, + "step": 7215 + }, + { + "epoch": 0.6, + "learning_rate": 7.165541683439976e-06, + "loss": 0.4737, + "step": 7216 + }, + { + "epoch": 0.6, + "learning_rate": 7.162943020674116e-06, + "loss": 0.4437, + "step": 7217 + }, + { + "epoch": 0.6, + "learning_rate": 7.160344566249918e-06, + "loss": 0.4727, + "step": 7218 + }, + { + "epoch": 0.6, + "learning_rate": 7.1577463203582056e-06, + "loss": 0.4749, + "step": 7219 + }, + { + "epoch": 0.6, + "learning_rate": 7.155148283189779e-06, + "loss": 0.4594, + "step": 7220 + }, + { + "epoch": 0.6, + "learning_rate": 7.152550454935432e-06, + "loss": 0.4536, + "step": 7221 + }, + { + "epoch": 0.6, + "learning_rate": 7.149952835785936e-06, + "loss": 0.4791, + "step": 7222 + }, + { + "epoch": 0.6, + "learning_rate": 7.147355425932045e-06, + "loss": 0.4786, + "step": 7223 + }, + { + "epoch": 0.6, + "learning_rate": 7.144758225564511e-06, + "loss": 0.4874, + "step": 7224 + }, + { + "epoch": 0.6, + "learning_rate": 7.1421612348740564e-06, + "loss": 0.4724, + "step": 7225 + }, + { + "epoch": 0.6, + "learning_rate": 7.139564454051393e-06, + "loss": 0.4492, + "step": 7226 + }, + { + "epoch": 0.6, + "learning_rate": 7.1369678832872205e-06, + "loss": 0.4765, + "step": 7227 + }, + { + "epoch": 0.6, + "learning_rate": 7.134371522772218e-06, + "loss": 0.4604, + "step": 7228 + }, + { + "epoch": 0.6, + "learning_rate": 7.131775372697051e-06, + "loss": 0.4776, + "step": 7229 + }, + { + "epoch": 0.6, + "learning_rate": 7.129179433252369e-06, + "loss": 0.4757, + "step": 7230 + }, + { + "epoch": 0.6, + "learning_rate": 7.126583704628811e-06, + "loss": 0.4783, + "step": 7231 + }, + { + "epoch": 0.61, + "learning_rate": 7.123988187016994e-06, + "loss": 0.4575, + "step": 7232 + }, + { + "epoch": 0.61, + "learning_rate": 7.121392880607524e-06, + "loss": 0.4542, + "step": 7233 + }, + { + "epoch": 0.61, + "learning_rate": 7.118797785590987e-06, + "loss": 0.4811, + "step": 7234 + }, + { + "epoch": 0.61, + "learning_rate": 7.116202902157955e-06, + "loss": 0.4668, + "step": 7235 + }, + { + "epoch": 0.61, + "learning_rate": 7.113608230498989e-06, + "loss": 0.4617, + "step": 7236 + }, + { + "epoch": 0.61, + "learning_rate": 7.1110137708046245e-06, + "loss": 0.4798, + "step": 7237 + }, + { + "epoch": 0.61, + "learning_rate": 7.108419523265398e-06, + "loss": 0.4776, + "step": 7238 + }, + { + "epoch": 0.61, + "learning_rate": 7.105825488071814e-06, + "loss": 0.4692, + "step": 7239 + }, + { + "epoch": 0.61, + "learning_rate": 7.1032316654143685e-06, + "loss": 0.5049, + "step": 7240 + }, + { + "epoch": 0.61, + "learning_rate": 7.100638055483539e-06, + "loss": 0.497, + "step": 7241 + }, + { + "epoch": 0.61, + "learning_rate": 7.098044658469794e-06, + "loss": 0.4646, + "step": 7242 + }, + { + "epoch": 0.61, + "learning_rate": 7.095451474563577e-06, + "loss": 0.4768, + "step": 7243 + }, + { + "epoch": 0.61, + "learning_rate": 7.0928585039553196e-06, + "loss": 0.4877, + "step": 7244 + }, + { + "epoch": 0.61, + "learning_rate": 7.090265746835448e-06, + "loss": 0.4736, + "step": 7245 + }, + { + "epoch": 0.61, + "learning_rate": 7.087673203394353e-06, + "loss": 0.4889, + "step": 7246 + }, + { + "epoch": 0.61, + "learning_rate": 7.085080873822427e-06, + "loss": 0.4775, + "step": 7247 + }, + { + "epoch": 0.61, + "learning_rate": 7.082488758310039e-06, + "loss": 0.4754, + "step": 7248 + }, + { + "epoch": 0.61, + "learning_rate": 7.079896857047541e-06, + "loss": 0.4945, + "step": 7249 + }, + { + "epoch": 0.61, + "learning_rate": 7.07730517022527e-06, + "loss": 0.4771, + "step": 7250 + }, + { + "epoch": 0.61, + "learning_rate": 7.074713698033551e-06, + "loss": 0.4622, + "step": 7251 + }, + { + "epoch": 0.61, + "learning_rate": 7.0721224406626895e-06, + "loss": 0.4601, + "step": 7252 + }, + { + "epoch": 0.61, + "learning_rate": 7.069531398302982e-06, + "loss": 0.4758, + "step": 7253 + }, + { + "epoch": 0.61, + "learning_rate": 7.0669405711447e-06, + "loss": 0.4787, + "step": 7254 + }, + { + "epoch": 0.61, + "learning_rate": 7.064349959378102e-06, + "loss": 0.4817, + "step": 7255 + }, + { + "epoch": 0.61, + "learning_rate": 7.061759563193431e-06, + "loss": 0.4727, + "step": 7256 + }, + { + "epoch": 0.61, + "learning_rate": 7.059169382780914e-06, + "loss": 0.4839, + "step": 7257 + }, + { + "epoch": 0.61, + "learning_rate": 7.05657941833077e-06, + "loss": 0.4819, + "step": 7258 + }, + { + "epoch": 0.61, + "learning_rate": 7.053989670033191e-06, + "loss": 0.4709, + "step": 7259 + }, + { + "epoch": 0.61, + "learning_rate": 7.051400138078357e-06, + "loss": 0.5036, + "step": 7260 + }, + { + "epoch": 0.61, + "learning_rate": 7.048810822656431e-06, + "loss": 0.4635, + "step": 7261 + }, + { + "epoch": 0.61, + "learning_rate": 7.046221723957566e-06, + "loss": 0.4943, + "step": 7262 + }, + { + "epoch": 0.61, + "learning_rate": 7.043632842171891e-06, + "loss": 0.466, + "step": 7263 + }, + { + "epoch": 0.61, + "learning_rate": 7.04104417748952e-06, + "loss": 0.487, + "step": 7264 + }, + { + "epoch": 0.61, + "learning_rate": 7.038455730100562e-06, + "loss": 0.5054, + "step": 7265 + }, + { + "epoch": 0.61, + "learning_rate": 7.035867500195095e-06, + "loss": 0.4723, + "step": 7266 + }, + { + "epoch": 0.61, + "learning_rate": 7.033279487963189e-06, + "loss": 0.4646, + "step": 7267 + }, + { + "epoch": 0.61, + "learning_rate": 7.030691693594901e-06, + "loss": 0.49, + "step": 7268 + }, + { + "epoch": 0.61, + "learning_rate": 7.028104117280265e-06, + "loss": 0.4855, + "step": 7269 + }, + { + "epoch": 0.61, + "learning_rate": 7.0255167592092995e-06, + "loss": 0.4694, + "step": 7270 + }, + { + "epoch": 0.61, + "learning_rate": 7.022929619572009e-06, + "loss": 0.4606, + "step": 7271 + }, + { + "epoch": 0.61, + "learning_rate": 7.020342698558387e-06, + "loss": 0.4617, + "step": 7272 + }, + { + "epoch": 0.61, + "learning_rate": 7.017755996358404e-06, + "loss": 0.4771, + "step": 7273 + }, + { + "epoch": 0.61, + "learning_rate": 7.015169513162018e-06, + "loss": 0.4914, + "step": 7274 + }, + { + "epoch": 0.61, + "learning_rate": 7.012583249159167e-06, + "loss": 0.4829, + "step": 7275 + }, + { + "epoch": 0.61, + "learning_rate": 7.009997204539775e-06, + "loss": 0.488, + "step": 7276 + }, + { + "epoch": 0.61, + "learning_rate": 7.007411379493755e-06, + "loss": 0.4732, + "step": 7277 + }, + { + "epoch": 0.61, + "learning_rate": 7.004825774210992e-06, + "loss": 0.4704, + "step": 7278 + }, + { + "epoch": 0.61, + "learning_rate": 7.002240388881369e-06, + "loss": 0.4658, + "step": 7279 + }, + { + "epoch": 0.61, + "learning_rate": 6.999655223694743e-06, + "loss": 0.4793, + "step": 7280 + }, + { + "epoch": 0.61, + "learning_rate": 6.997070278840961e-06, + "loss": 0.4676, + "step": 7281 + }, + { + "epoch": 0.61, + "learning_rate": 6.994485554509842e-06, + "loss": 0.4818, + "step": 7282 + }, + { + "epoch": 0.61, + "learning_rate": 6.9919010508912075e-06, + "loss": 0.4762, + "step": 7283 + }, + { + "epoch": 0.61, + "learning_rate": 6.989316768174848e-06, + "loss": 0.4686, + "step": 7284 + }, + { + "epoch": 0.61, + "learning_rate": 6.986732706550536e-06, + "loss": 0.4748, + "step": 7285 + }, + { + "epoch": 0.61, + "learning_rate": 6.984148866208047e-06, + "loss": 0.4721, + "step": 7286 + }, + { + "epoch": 0.61, + "learning_rate": 6.98156524733712e-06, + "loss": 0.48, + "step": 7287 + }, + { + "epoch": 0.61, + "learning_rate": 6.978981850127487e-06, + "loss": 0.4841, + "step": 7288 + }, + { + "epoch": 0.61, + "learning_rate": 6.976398674768863e-06, + "loss": 0.4418, + "step": 7289 + }, + { + "epoch": 0.61, + "learning_rate": 6.973815721450942e-06, + "loss": 0.4861, + "step": 7290 + }, + { + "epoch": 0.61, + "learning_rate": 6.971232990363406e-06, + "loss": 0.4719, + "step": 7291 + }, + { + "epoch": 0.61, + "learning_rate": 6.968650481695926e-06, + "loss": 0.4704, + "step": 7292 + }, + { + "epoch": 0.61, + "learning_rate": 6.966068195638143e-06, + "loss": 0.4914, + "step": 7293 + }, + { + "epoch": 0.61, + "learning_rate": 6.963486132379694e-06, + "loss": 0.4566, + "step": 7294 + }, + { + "epoch": 0.61, + "learning_rate": 6.960904292110194e-06, + "loss": 0.4767, + "step": 7295 + }, + { + "epoch": 0.61, + "learning_rate": 6.958322675019243e-06, + "loss": 0.4918, + "step": 7296 + }, + { + "epoch": 0.61, + "learning_rate": 6.955741281296421e-06, + "loss": 0.4656, + "step": 7297 + }, + { + "epoch": 0.61, + "learning_rate": 6.953160111131295e-06, + "loss": 0.4493, + "step": 7298 + }, + { + "epoch": 0.61, + "learning_rate": 6.950579164713422e-06, + "loss": 0.4678, + "step": 7299 + }, + { + "epoch": 0.61, + "learning_rate": 6.947998442232332e-06, + "loss": 0.4811, + "step": 7300 + }, + { + "epoch": 0.61, + "learning_rate": 6.945417943877541e-06, + "loss": 0.4744, + "step": 7301 + }, + { + "epoch": 0.61, + "learning_rate": 6.942837669838552e-06, + "loss": 0.4583, + "step": 7302 + }, + { + "epoch": 0.61, + "learning_rate": 6.9402576203048474e-06, + "loss": 0.498, + "step": 7303 + }, + { + "epoch": 0.61, + "learning_rate": 6.937677795465898e-06, + "loss": 0.4433, + "step": 7304 + }, + { + "epoch": 0.61, + "learning_rate": 6.935098195511151e-06, + "loss": 0.4787, + "step": 7305 + }, + { + "epoch": 0.61, + "learning_rate": 6.932518820630048e-06, + "loss": 0.4839, + "step": 7306 + }, + { + "epoch": 0.61, + "learning_rate": 6.929939671012005e-06, + "loss": 0.4922, + "step": 7307 + }, + { + "epoch": 0.61, + "learning_rate": 6.9273607468464185e-06, + "loss": 0.451, + "step": 7308 + }, + { + "epoch": 0.61, + "learning_rate": 6.924782048322683e-06, + "loss": 0.4665, + "step": 7309 + }, + { + "epoch": 0.61, + "learning_rate": 6.922203575630164e-06, + "loss": 0.4927, + "step": 7310 + }, + { + "epoch": 0.61, + "learning_rate": 6.9196253289582104e-06, + "loss": 0.4512, + "step": 7311 + }, + { + "epoch": 0.61, + "learning_rate": 6.917047308496159e-06, + "loss": 0.4649, + "step": 7312 + }, + { + "epoch": 0.61, + "learning_rate": 6.914469514433331e-06, + "loss": 0.4551, + "step": 7313 + }, + { + "epoch": 0.61, + "learning_rate": 6.9118919469590285e-06, + "loss": 0.4659, + "step": 7314 + }, + { + "epoch": 0.61, + "learning_rate": 6.9093146062625395e-06, + "loss": 0.4642, + "step": 7315 + }, + { + "epoch": 0.61, + "learning_rate": 6.906737492533129e-06, + "loss": 0.4668, + "step": 7316 + }, + { + "epoch": 0.61, + "learning_rate": 6.904160605960051e-06, + "loss": 0.4703, + "step": 7317 + }, + { + "epoch": 0.61, + "learning_rate": 6.901583946732542e-06, + "loss": 0.4792, + "step": 7318 + }, + { + "epoch": 0.61, + "learning_rate": 6.899007515039817e-06, + "loss": 0.4782, + "step": 7319 + }, + { + "epoch": 0.61, + "learning_rate": 6.896431311071086e-06, + "loss": 0.4555, + "step": 7320 + }, + { + "epoch": 0.61, + "learning_rate": 6.893855335015532e-06, + "loss": 0.4866, + "step": 7321 + }, + { + "epoch": 0.61, + "learning_rate": 6.891279587062321e-06, + "loss": 0.4725, + "step": 7322 + }, + { + "epoch": 0.61, + "learning_rate": 6.888704067400605e-06, + "loss": 0.4588, + "step": 7323 + }, + { + "epoch": 0.61, + "learning_rate": 6.886128776219525e-06, + "loss": 0.4671, + "step": 7324 + }, + { + "epoch": 0.61, + "learning_rate": 6.8835537137081955e-06, + "loss": 0.4611, + "step": 7325 + }, + { + "epoch": 0.61, + "learning_rate": 6.880978880055716e-06, + "loss": 0.4666, + "step": 7326 + }, + { + "epoch": 0.61, + "learning_rate": 6.878404275451176e-06, + "loss": 0.473, + "step": 7327 + }, + { + "epoch": 0.61, + "learning_rate": 6.875829900083642e-06, + "loss": 0.4906, + "step": 7328 + }, + { + "epoch": 0.61, + "learning_rate": 6.873255754142167e-06, + "loss": 0.4585, + "step": 7329 + }, + { + "epoch": 0.61, + "learning_rate": 6.870681837815784e-06, + "loss": 0.4581, + "step": 7330 + }, + { + "epoch": 0.61, + "learning_rate": 6.868108151293513e-06, + "loss": 0.4791, + "step": 7331 + }, + { + "epoch": 0.61, + "learning_rate": 6.865534694764348e-06, + "loss": 0.4673, + "step": 7332 + }, + { + "epoch": 0.61, + "learning_rate": 6.86296146841728e-06, + "loss": 0.4584, + "step": 7333 + }, + { + "epoch": 0.61, + "learning_rate": 6.860388472441274e-06, + "loss": 0.4574, + "step": 7334 + }, + { + "epoch": 0.61, + "learning_rate": 6.8578157070252815e-06, + "loss": 0.4765, + "step": 7335 + }, + { + "epoch": 0.61, + "learning_rate": 6.8552431723582335e-06, + "loss": 0.4709, + "step": 7336 + }, + { + "epoch": 0.61, + "learning_rate": 6.852670868629048e-06, + "loss": 0.4589, + "step": 7337 + }, + { + "epoch": 0.61, + "learning_rate": 6.85009879602662e-06, + "loss": 0.4735, + "step": 7338 + }, + { + "epoch": 0.61, + "learning_rate": 6.8475269547398335e-06, + "loss": 0.4506, + "step": 7339 + }, + { + "epoch": 0.61, + "learning_rate": 6.844955344957559e-06, + "loss": 0.488, + "step": 7340 + }, + { + "epoch": 0.61, + "learning_rate": 6.842383966868642e-06, + "loss": 0.4864, + "step": 7341 + }, + { + "epoch": 0.61, + "learning_rate": 6.839812820661912e-06, + "loss": 0.4675, + "step": 7342 + }, + { + "epoch": 0.61, + "learning_rate": 6.837241906526182e-06, + "loss": 0.4823, + "step": 7343 + }, + { + "epoch": 0.61, + "learning_rate": 6.834671224650254e-06, + "loss": 0.4612, + "step": 7344 + }, + { + "epoch": 0.61, + "learning_rate": 6.832100775222906e-06, + "loss": 0.478, + "step": 7345 + }, + { + "epoch": 0.61, + "learning_rate": 6.829530558432898e-06, + "loss": 0.4456, + "step": 7346 + }, + { + "epoch": 0.61, + "learning_rate": 6.8269605744689805e-06, + "loss": 0.4765, + "step": 7347 + }, + { + "epoch": 0.61, + "learning_rate": 6.824390823519882e-06, + "loss": 0.481, + "step": 7348 + }, + { + "epoch": 0.61, + "learning_rate": 6.82182130577431e-06, + "loss": 0.4775, + "step": 7349 + }, + { + "epoch": 0.61, + "learning_rate": 6.819252021420966e-06, + "loss": 0.4842, + "step": 7350 + }, + { + "epoch": 0.62, + "learning_rate": 6.816682970648522e-06, + "loss": 0.4671, + "step": 7351 + }, + { + "epoch": 0.62, + "learning_rate": 6.814114153645641e-06, + "loss": 0.4894, + "step": 7352 + }, + { + "epoch": 0.62, + "learning_rate": 6.811545570600961e-06, + "loss": 0.4694, + "step": 7353 + }, + { + "epoch": 0.62, + "learning_rate": 6.808977221703115e-06, + "loss": 0.4797, + "step": 7354 + }, + { + "epoch": 0.62, + "learning_rate": 6.8064091071407115e-06, + "loss": 0.4816, + "step": 7355 + }, + { + "epoch": 0.62, + "learning_rate": 6.803841227102339e-06, + "loss": 0.4575, + "step": 7356 + }, + { + "epoch": 0.62, + "learning_rate": 6.801273581776575e-06, + "loss": 0.4852, + "step": 7357 + }, + { + "epoch": 0.62, + "learning_rate": 6.798706171351971e-06, + "loss": 0.4799, + "step": 7358 + }, + { + "epoch": 0.62, + "learning_rate": 6.796138996017073e-06, + "loss": 0.4692, + "step": 7359 + }, + { + "epoch": 0.62, + "learning_rate": 6.793572055960398e-06, + "loss": 0.4631, + "step": 7360 + }, + { + "epoch": 0.62, + "learning_rate": 6.791005351370458e-06, + "loss": 0.47, + "step": 7361 + }, + { + "epoch": 0.62, + "learning_rate": 6.788438882435737e-06, + "loss": 0.4797, + "step": 7362 + }, + { + "epoch": 0.62, + "learning_rate": 6.7858726493447084e-06, + "loss": 0.4582, + "step": 7363 + }, + { + "epoch": 0.62, + "learning_rate": 6.78330665228582e-06, + "loss": 0.4842, + "step": 7364 + }, + { + "epoch": 0.62, + "learning_rate": 6.780740891447515e-06, + "loss": 0.4711, + "step": 7365 + }, + { + "epoch": 0.62, + "learning_rate": 6.778175367018205e-06, + "loss": 0.4705, + "step": 7366 + }, + { + "epoch": 0.62, + "learning_rate": 6.775610079186299e-06, + "loss": 0.4719, + "step": 7367 + }, + { + "epoch": 0.62, + "learning_rate": 6.773045028140177e-06, + "loss": 0.474, + "step": 7368 + }, + { + "epoch": 0.62, + "learning_rate": 6.770480214068207e-06, + "loss": 0.4711, + "step": 7369 + }, + { + "epoch": 0.62, + "learning_rate": 6.767915637158735e-06, + "loss": 0.4732, + "step": 7370 + }, + { + "epoch": 0.62, + "learning_rate": 6.765351297600098e-06, + "loss": 0.5037, + "step": 7371 + }, + { + "epoch": 0.62, + "learning_rate": 6.762787195580609e-06, + "loss": 0.4625, + "step": 7372 + }, + { + "epoch": 0.62, + "learning_rate": 6.760223331288558e-06, + "loss": 0.4838, + "step": 7373 + }, + { + "epoch": 0.62, + "learning_rate": 6.757659704912234e-06, + "loss": 0.4613, + "step": 7374 + }, + { + "epoch": 0.62, + "learning_rate": 6.755096316639894e-06, + "loss": 0.4719, + "step": 7375 + }, + { + "epoch": 0.62, + "learning_rate": 6.752533166659786e-06, + "loss": 0.4777, + "step": 7376 + }, + { + "epoch": 0.62, + "learning_rate": 6.749970255160134e-06, + "loss": 0.4718, + "step": 7377 + }, + { + "epoch": 0.62, + "learning_rate": 6.747407582329151e-06, + "loss": 0.4682, + "step": 7378 + }, + { + "epoch": 0.62, + "learning_rate": 6.744845148355023e-06, + "loss": 0.4711, + "step": 7379 + }, + { + "epoch": 0.62, + "learning_rate": 6.742282953425928e-06, + "loss": 0.4649, + "step": 7380 + }, + { + "epoch": 0.62, + "learning_rate": 6.739720997730024e-06, + "loss": 0.4666, + "step": 7381 + }, + { + "epoch": 0.62, + "learning_rate": 6.73715928145545e-06, + "loss": 0.4793, + "step": 7382 + }, + { + "epoch": 0.62, + "learning_rate": 6.734597804790328e-06, + "loss": 0.4825, + "step": 7383 + }, + { + "epoch": 0.62, + "learning_rate": 6.732036567922761e-06, + "loss": 0.4683, + "step": 7384 + }, + { + "epoch": 0.62, + "learning_rate": 6.729475571040835e-06, + "loss": 0.4744, + "step": 7385 + }, + { + "epoch": 0.62, + "learning_rate": 6.726914814332621e-06, + "loss": 0.4606, + "step": 7386 + }, + { + "epoch": 0.62, + "learning_rate": 6.724354297986164e-06, + "loss": 0.4713, + "step": 7387 + }, + { + "epoch": 0.62, + "learning_rate": 6.7217940221895095e-06, + "loss": 0.5145, + "step": 7388 + }, + { + "epoch": 0.62, + "learning_rate": 6.7192339871306655e-06, + "loss": 0.4723, + "step": 7389 + }, + { + "epoch": 0.62, + "learning_rate": 6.7166741929976295e-06, + "loss": 0.4768, + "step": 7390 + }, + { + "epoch": 0.62, + "learning_rate": 6.7141146399783875e-06, + "loss": 0.4662, + "step": 7391 + }, + { + "epoch": 0.62, + "learning_rate": 6.711555328260899e-06, + "loss": 0.4682, + "step": 7392 + }, + { + "epoch": 0.62, + "learning_rate": 6.708996258033109e-06, + "loss": 0.4747, + "step": 7393 + }, + { + "epoch": 0.62, + "learning_rate": 6.706437429482942e-06, + "loss": 0.4901, + "step": 7394 + }, + { + "epoch": 0.62, + "learning_rate": 6.703878842798315e-06, + "loss": 0.4792, + "step": 7395 + }, + { + "epoch": 0.62, + "learning_rate": 6.701320498167115e-06, + "loss": 0.4451, + "step": 7396 + }, + { + "epoch": 0.62, + "learning_rate": 6.6987623957772165e-06, + "loss": 0.4769, + "step": 7397 + }, + { + "epoch": 0.62, + "learning_rate": 6.696204535816479e-06, + "loss": 0.4691, + "step": 7398 + }, + { + "epoch": 0.62, + "learning_rate": 6.693646918472739e-06, + "loss": 0.4577, + "step": 7399 + }, + { + "epoch": 0.62, + "learning_rate": 6.691089543933815e-06, + "loss": 0.4784, + "step": 7400 + }, + { + "epoch": 0.62, + "learning_rate": 6.68853241238751e-06, + "loss": 0.4884, + "step": 7401 + }, + { + "epoch": 0.62, + "learning_rate": 6.685975524021615e-06, + "loss": 0.4705, + "step": 7402 + }, + { + "epoch": 0.62, + "learning_rate": 6.683418879023893e-06, + "loss": 0.4748, + "step": 7403 + }, + { + "epoch": 0.62, + "learning_rate": 6.6808624775820954e-06, + "loss": 0.49, + "step": 7404 + }, + { + "epoch": 0.62, + "learning_rate": 6.678306319883948e-06, + "loss": 0.456, + "step": 7405 + }, + { + "epoch": 0.62, + "learning_rate": 6.675750406117172e-06, + "loss": 0.447, + "step": 7406 + }, + { + "epoch": 0.62, + "learning_rate": 6.673194736469455e-06, + "loss": 0.4794, + "step": 7407 + }, + { + "epoch": 0.62, + "learning_rate": 6.670639311128484e-06, + "loss": 0.4712, + "step": 7408 + }, + { + "epoch": 0.62, + "learning_rate": 6.668084130281913e-06, + "loss": 0.4512, + "step": 7409 + }, + { + "epoch": 0.62, + "learning_rate": 6.665529194117386e-06, + "loss": 0.4734, + "step": 7410 + }, + { + "epoch": 0.62, + "learning_rate": 6.662974502822524e-06, + "loss": 0.4735, + "step": 7411 + }, + { + "epoch": 0.62, + "learning_rate": 6.660420056584935e-06, + "loss": 0.4767, + "step": 7412 + }, + { + "epoch": 0.62, + "learning_rate": 6.65786585559221e-06, + "loss": 0.4643, + "step": 7413 + }, + { + "epoch": 0.62, + "learning_rate": 6.655311900031909e-06, + "loss": 0.4899, + "step": 7414 + }, + { + "epoch": 0.62, + "learning_rate": 6.652758190091595e-06, + "loss": 0.4542, + "step": 7415 + }, + { + "epoch": 0.62, + "learning_rate": 6.650204725958795e-06, + "loss": 0.4742, + "step": 7416 + }, + { + "epoch": 0.62, + "learning_rate": 6.647651507821029e-06, + "loss": 0.4802, + "step": 7417 + }, + { + "epoch": 0.62, + "learning_rate": 6.645098535865793e-06, + "loss": 0.4728, + "step": 7418 + }, + { + "epoch": 0.62, + "learning_rate": 6.642545810280567e-06, + "loss": 0.4773, + "step": 7419 + }, + { + "epoch": 0.62, + "learning_rate": 6.63999333125281e-06, + "loss": 0.4743, + "step": 7420 + }, + { + "epoch": 0.62, + "learning_rate": 6.637441098969967e-06, + "loss": 0.4709, + "step": 7421 + }, + { + "epoch": 0.62, + "learning_rate": 6.634889113619463e-06, + "loss": 0.4619, + "step": 7422 + }, + { + "epoch": 0.62, + "learning_rate": 6.632337375388709e-06, + "loss": 0.4638, + "step": 7423 + }, + { + "epoch": 0.62, + "learning_rate": 6.629785884465091e-06, + "loss": 0.4739, + "step": 7424 + }, + { + "epoch": 0.62, + "learning_rate": 6.62723464103598e-06, + "loss": 0.4845, + "step": 7425 + }, + { + "epoch": 0.62, + "learning_rate": 6.624683645288726e-06, + "loss": 0.46, + "step": 7426 + }, + { + "epoch": 0.62, + "learning_rate": 6.622132897410668e-06, + "loss": 0.4822, + "step": 7427 + }, + { + "epoch": 0.62, + "learning_rate": 6.619582397589117e-06, + "loss": 0.4872, + "step": 7428 + }, + { + "epoch": 0.62, + "learning_rate": 6.617032146011377e-06, + "loss": 0.4577, + "step": 7429 + }, + { + "epoch": 0.62, + "learning_rate": 6.614482142864728e-06, + "loss": 0.4661, + "step": 7430 + }, + { + "epoch": 0.62, + "learning_rate": 6.611932388336425e-06, + "loss": 0.4734, + "step": 7431 + }, + { + "epoch": 0.62, + "learning_rate": 6.609382882613717e-06, + "loss": 0.5089, + "step": 7432 + }, + { + "epoch": 0.62, + "learning_rate": 6.606833625883829e-06, + "loss": 0.4623, + "step": 7433 + }, + { + "epoch": 0.62, + "learning_rate": 6.604284618333967e-06, + "loss": 0.4694, + "step": 7434 + }, + { + "epoch": 0.62, + "learning_rate": 6.601735860151313e-06, + "loss": 0.4794, + "step": 7435 + }, + { + "epoch": 0.62, + "learning_rate": 6.599187351523046e-06, + "loss": 0.4663, + "step": 7436 + }, + { + "epoch": 0.62, + "learning_rate": 6.596639092636315e-06, + "loss": 0.4743, + "step": 7437 + }, + { + "epoch": 0.62, + "learning_rate": 6.594091083678256e-06, + "loss": 0.4755, + "step": 7438 + }, + { + "epoch": 0.62, + "learning_rate": 6.5915433248359795e-06, + "loss": 0.4826, + "step": 7439 + }, + { + "epoch": 0.62, + "learning_rate": 6.588995816296585e-06, + "loss": 0.4959, + "step": 7440 + }, + { + "epoch": 0.62, + "learning_rate": 6.586448558247147e-06, + "loss": 0.4803, + "step": 7441 + }, + { + "epoch": 0.62, + "learning_rate": 6.58390155087473e-06, + "loss": 0.4815, + "step": 7442 + }, + { + "epoch": 0.62, + "learning_rate": 6.581354794366377e-06, + "loss": 0.4684, + "step": 7443 + }, + { + "epoch": 0.62, + "learning_rate": 6.578808288909109e-06, + "loss": 0.4681, + "step": 7444 + }, + { + "epoch": 0.62, + "learning_rate": 6.576262034689929e-06, + "loss": 0.4779, + "step": 7445 + }, + { + "epoch": 0.62, + "learning_rate": 6.573716031895825e-06, + "loss": 0.4647, + "step": 7446 + }, + { + "epoch": 0.62, + "learning_rate": 6.571170280713765e-06, + "loss": 0.4679, + "step": 7447 + }, + { + "epoch": 0.62, + "learning_rate": 6.568624781330694e-06, + "loss": 0.472, + "step": 7448 + }, + { + "epoch": 0.62, + "learning_rate": 6.566079533933551e-06, + "loss": 0.4853, + "step": 7449 + }, + { + "epoch": 0.62, + "learning_rate": 6.563534538709244e-06, + "loss": 0.4819, + "step": 7450 + }, + { + "epoch": 0.62, + "learning_rate": 6.560989795844668e-06, + "loss": 0.4661, + "step": 7451 + }, + { + "epoch": 0.62, + "learning_rate": 6.558445305526695e-06, + "loss": 0.4871, + "step": 7452 + }, + { + "epoch": 0.62, + "learning_rate": 6.555901067942188e-06, + "loss": 0.4697, + "step": 7453 + }, + { + "epoch": 0.62, + "learning_rate": 6.553357083277979e-06, + "loss": 0.4684, + "step": 7454 + }, + { + "epoch": 0.62, + "learning_rate": 6.550813351720888e-06, + "loss": 0.448, + "step": 7455 + }, + { + "epoch": 0.62, + "learning_rate": 6.54826987345772e-06, + "loss": 0.4641, + "step": 7456 + }, + { + "epoch": 0.62, + "learning_rate": 6.545726648675255e-06, + "loss": 0.4725, + "step": 7457 + }, + { + "epoch": 0.62, + "learning_rate": 6.54318367756026e-06, + "loss": 0.4737, + "step": 7458 + }, + { + "epoch": 0.62, + "learning_rate": 6.540640960299477e-06, + "loss": 0.4911, + "step": 7459 + }, + { + "epoch": 0.62, + "learning_rate": 6.538098497079634e-06, + "loss": 0.4779, + "step": 7460 + }, + { + "epoch": 0.62, + "learning_rate": 6.5355562880874345e-06, + "loss": 0.4593, + "step": 7461 + }, + { + "epoch": 0.62, + "learning_rate": 6.533014333509573e-06, + "loss": 0.4589, + "step": 7462 + }, + { + "epoch": 0.62, + "learning_rate": 6.530472633532718e-06, + "loss": 0.485, + "step": 7463 + }, + { + "epoch": 0.62, + "learning_rate": 6.527931188343525e-06, + "loss": 0.5078, + "step": 7464 + }, + { + "epoch": 0.62, + "learning_rate": 6.525389998128624e-06, + "loss": 0.4716, + "step": 7465 + }, + { + "epoch": 0.62, + "learning_rate": 6.522849063074628e-06, + "loss": 0.4613, + "step": 7466 + }, + { + "epoch": 0.62, + "learning_rate": 6.520308383368134e-06, + "loss": 0.4736, + "step": 7467 + }, + { + "epoch": 0.62, + "learning_rate": 6.51776795919572e-06, + "loss": 0.4775, + "step": 7468 + }, + { + "epoch": 0.62, + "learning_rate": 6.515227790743939e-06, + "loss": 0.4675, + "step": 7469 + }, + { + "epoch": 0.62, + "learning_rate": 6.51268787819934e-06, + "loss": 0.5053, + "step": 7470 + }, + { + "epoch": 0.63, + "learning_rate": 6.510148221748438e-06, + "loss": 0.4562, + "step": 7471 + }, + { + "epoch": 0.63, + "learning_rate": 6.507608821577733e-06, + "loss": 0.4942, + "step": 7472 + }, + { + "epoch": 0.63, + "learning_rate": 6.505069677873712e-06, + "loss": 0.4833, + "step": 7473 + }, + { + "epoch": 0.63, + "learning_rate": 6.502530790822838e-06, + "loss": 0.4595, + "step": 7474 + }, + { + "epoch": 0.63, + "learning_rate": 6.499992160611556e-06, + "loss": 0.4807, + "step": 7475 + }, + { + "epoch": 0.63, + "learning_rate": 6.4974537874262865e-06, + "loss": 0.4696, + "step": 7476 + }, + { + "epoch": 0.63, + "learning_rate": 6.494915671453448e-06, + "loss": 0.4573, + "step": 7477 + }, + { + "epoch": 0.63, + "learning_rate": 6.492377812879422e-06, + "loss": 0.4639, + "step": 7478 + }, + { + "epoch": 0.63, + "learning_rate": 6.489840211890581e-06, + "loss": 0.4548, + "step": 7479 + }, + { + "epoch": 0.63, + "learning_rate": 6.4873028686732755e-06, + "loss": 0.4844, + "step": 7480 + }, + { + "epoch": 0.63, + "learning_rate": 6.484765783413838e-06, + "loss": 0.4707, + "step": 7481 + }, + { + "epoch": 0.63, + "learning_rate": 6.482228956298575e-06, + "loss": 0.4791, + "step": 7482 + }, + { + "epoch": 0.63, + "learning_rate": 6.479692387513788e-06, + "loss": 0.4717, + "step": 7483 + }, + { + "epoch": 0.63, + "learning_rate": 6.477156077245752e-06, + "loss": 0.4769, + "step": 7484 + }, + { + "epoch": 0.63, + "learning_rate": 6.474620025680722e-06, + "loss": 0.487, + "step": 7485 + }, + { + "epoch": 0.63, + "learning_rate": 6.472084233004934e-06, + "loss": 0.4828, + "step": 7486 + }, + { + "epoch": 0.63, + "learning_rate": 6.469548699404603e-06, + "loss": 0.4782, + "step": 7487 + }, + { + "epoch": 0.63, + "learning_rate": 6.467013425065935e-06, + "loss": 0.4786, + "step": 7488 + }, + { + "epoch": 0.63, + "learning_rate": 6.464478410175101e-06, + "loss": 0.4812, + "step": 7489 + }, + { + "epoch": 0.63, + "learning_rate": 6.461943654918271e-06, + "loss": 0.4729, + "step": 7490 + }, + { + "epoch": 0.63, + "learning_rate": 6.459409159481584e-06, + "loss": 0.4727, + "step": 7491 + }, + { + "epoch": 0.63, + "learning_rate": 6.456874924051162e-06, + "loss": 0.4939, + "step": 7492 + }, + { + "epoch": 0.63, + "learning_rate": 6.454340948813105e-06, + "loss": 0.4628, + "step": 7493 + }, + { + "epoch": 0.63, + "learning_rate": 6.451807233953504e-06, + "loss": 0.4971, + "step": 7494 + }, + { + "epoch": 0.63, + "learning_rate": 6.4492737796584225e-06, + "loss": 0.4719, + "step": 7495 + }, + { + "epoch": 0.63, + "learning_rate": 6.446740586113902e-06, + "loss": 0.4494, + "step": 7496 + }, + { + "epoch": 0.63, + "learning_rate": 6.4442076535059774e-06, + "loss": 0.4809, + "step": 7497 + }, + { + "epoch": 0.63, + "learning_rate": 6.441674982020654e-06, + "loss": 0.4808, + "step": 7498 + }, + { + "epoch": 0.63, + "learning_rate": 6.439142571843915e-06, + "loss": 0.4673, + "step": 7499 + }, + { + "epoch": 0.63, + "learning_rate": 6.43661042316174e-06, + "loss": 0.4685, + "step": 7500 + }, + { + "epoch": 0.63, + "learning_rate": 6.434078536160072e-06, + "loss": 0.4587, + "step": 7501 + }, + { + "epoch": 0.63, + "learning_rate": 6.431546911024844e-06, + "loss": 0.4609, + "step": 7502 + }, + { + "epoch": 0.63, + "learning_rate": 6.429015547941968e-06, + "loss": 0.4694, + "step": 7503 + }, + { + "epoch": 0.63, + "learning_rate": 6.426484447097336e-06, + "loss": 0.4861, + "step": 7504 + }, + { + "epoch": 0.63, + "learning_rate": 6.423953608676827e-06, + "loss": 0.4696, + "step": 7505 + }, + { + "epoch": 0.63, + "learning_rate": 6.42142303286629e-06, + "loss": 0.483, + "step": 7506 + }, + { + "epoch": 0.63, + "learning_rate": 6.418892719851561e-06, + "loss": 0.4773, + "step": 7507 + }, + { + "epoch": 0.63, + "learning_rate": 6.416362669818454e-06, + "loss": 0.4661, + "step": 7508 + }, + { + "epoch": 0.63, + "learning_rate": 6.413832882952769e-06, + "loss": 0.4772, + "step": 7509 + }, + { + "epoch": 0.63, + "learning_rate": 6.411303359440277e-06, + "loss": 0.4728, + "step": 7510 + }, + { + "epoch": 0.63, + "learning_rate": 6.408774099466744e-06, + "loss": 0.4697, + "step": 7511 + }, + { + "epoch": 0.63, + "learning_rate": 6.406245103217903e-06, + "loss": 0.4669, + "step": 7512 + }, + { + "epoch": 0.63, + "learning_rate": 6.403716370879476e-06, + "loss": 0.4848, + "step": 7513 + }, + { + "epoch": 0.63, + "learning_rate": 6.401187902637157e-06, + "loss": 0.4847, + "step": 7514 + }, + { + "epoch": 0.63, + "learning_rate": 6.398659698676632e-06, + "loss": 0.4871, + "step": 7515 + }, + { + "epoch": 0.63, + "learning_rate": 6.396131759183557e-06, + "loss": 0.4799, + "step": 7516 + }, + { + "epoch": 0.63, + "learning_rate": 6.393604084343579e-06, + "loss": 0.4634, + "step": 7517 + }, + { + "epoch": 0.63, + "learning_rate": 6.391076674342316e-06, + "loss": 0.4661, + "step": 7518 + }, + { + "epoch": 0.63, + "learning_rate": 6.388549529365371e-06, + "loss": 0.4611, + "step": 7519 + }, + { + "epoch": 0.63, + "learning_rate": 6.3860226495983295e-06, + "loss": 0.4653, + "step": 7520 + }, + { + "epoch": 0.63, + "learning_rate": 6.383496035226752e-06, + "loss": 0.4802, + "step": 7521 + }, + { + "epoch": 0.63, + "learning_rate": 6.380969686436183e-06, + "loss": 0.4697, + "step": 7522 + }, + { + "epoch": 0.63, + "learning_rate": 6.378443603412145e-06, + "loss": 0.47, + "step": 7523 + }, + { + "epoch": 0.63, + "learning_rate": 6.375917786340149e-06, + "loss": 0.4656, + "step": 7524 + }, + { + "epoch": 0.63, + "learning_rate": 6.373392235405674e-06, + "loss": 0.4674, + "step": 7525 + }, + { + "epoch": 0.63, + "learning_rate": 6.3708669507941925e-06, + "loss": 0.454, + "step": 7526 + }, + { + "epoch": 0.63, + "learning_rate": 6.368341932691146e-06, + "loss": 0.4648, + "step": 7527 + }, + { + "epoch": 0.63, + "learning_rate": 6.365817181281965e-06, + "loss": 0.4764, + "step": 7528 + }, + { + "epoch": 0.63, + "learning_rate": 6.36329269675205e-06, + "loss": 0.4925, + "step": 7529 + }, + { + "epoch": 0.63, + "learning_rate": 6.360768479286793e-06, + "loss": 0.4803, + "step": 7530 + }, + { + "epoch": 0.63, + "learning_rate": 6.358244529071565e-06, + "loss": 0.4688, + "step": 7531 + }, + { + "epoch": 0.63, + "learning_rate": 6.355720846291713e-06, + "loss": 0.4638, + "step": 7532 + }, + { + "epoch": 0.63, + "learning_rate": 6.3531974311325625e-06, + "loss": 0.4732, + "step": 7533 + }, + { + "epoch": 0.63, + "learning_rate": 6.350674283779424e-06, + "loss": 0.4725, + "step": 7534 + }, + { + "epoch": 0.63, + "learning_rate": 6.348151404417589e-06, + "loss": 0.46, + "step": 7535 + }, + { + "epoch": 0.63, + "learning_rate": 6.3456287932323255e-06, + "loss": 0.4699, + "step": 7536 + }, + { + "epoch": 0.63, + "learning_rate": 6.34310645040888e-06, + "loss": 0.464, + "step": 7537 + }, + { + "epoch": 0.63, + "learning_rate": 6.34058437613249e-06, + "loss": 0.4604, + "step": 7538 + }, + { + "epoch": 0.63, + "learning_rate": 6.338062570588363e-06, + "loss": 0.4868, + "step": 7539 + }, + { + "epoch": 0.63, + "learning_rate": 6.335541033961687e-06, + "loss": 0.4638, + "step": 7540 + }, + { + "epoch": 0.63, + "learning_rate": 6.33301976643764e-06, + "loss": 0.4742, + "step": 7541 + }, + { + "epoch": 0.63, + "learning_rate": 6.330498768201367e-06, + "loss": 0.4737, + "step": 7542 + }, + { + "epoch": 0.63, + "learning_rate": 6.327978039438003e-06, + "loss": 0.476, + "step": 7543 + }, + { + "epoch": 0.63, + "learning_rate": 6.325457580332655e-06, + "loss": 0.4563, + "step": 7544 + }, + { + "epoch": 0.63, + "learning_rate": 6.3229373910704205e-06, + "loss": 0.4869, + "step": 7545 + }, + { + "epoch": 0.63, + "learning_rate": 6.3204174718363705e-06, + "loss": 0.4795, + "step": 7546 + }, + { + "epoch": 0.63, + "learning_rate": 6.317897822815559e-06, + "loss": 0.4641, + "step": 7547 + }, + { + "epoch": 0.63, + "learning_rate": 6.315378444193014e-06, + "loss": 0.4707, + "step": 7548 + }, + { + "epoch": 0.63, + "learning_rate": 6.31285933615375e-06, + "loss": 0.4488, + "step": 7549 + }, + { + "epoch": 0.63, + "learning_rate": 6.310340498882763e-06, + "loss": 0.4658, + "step": 7550 + }, + { + "epoch": 0.63, + "learning_rate": 6.30782193256502e-06, + "loss": 0.4589, + "step": 7551 + }, + { + "epoch": 0.63, + "learning_rate": 6.305303637385478e-06, + "loss": 0.4657, + "step": 7552 + }, + { + "epoch": 0.63, + "learning_rate": 6.302785613529072e-06, + "loss": 0.4786, + "step": 7553 + }, + { + "epoch": 0.63, + "learning_rate": 6.300267861180713e-06, + "loss": 0.4664, + "step": 7554 + }, + { + "epoch": 0.63, + "learning_rate": 6.297750380525289e-06, + "loss": 0.4712, + "step": 7555 + }, + { + "epoch": 0.63, + "learning_rate": 6.295233171747683e-06, + "loss": 0.4753, + "step": 7556 + }, + { + "epoch": 0.63, + "learning_rate": 6.292716235032738e-06, + "loss": 0.4655, + "step": 7557 + }, + { + "epoch": 0.63, + "learning_rate": 6.290199570565298e-06, + "loss": 0.4664, + "step": 7558 + }, + { + "epoch": 0.63, + "learning_rate": 6.287683178530172e-06, + "loss": 0.4774, + "step": 7559 + }, + { + "epoch": 0.63, + "learning_rate": 6.285167059112149e-06, + "loss": 0.482, + "step": 7560 + }, + { + "epoch": 0.63, + "learning_rate": 6.282651212496009e-06, + "loss": 0.4864, + "step": 7561 + }, + { + "epoch": 0.63, + "learning_rate": 6.280135638866502e-06, + "loss": 0.4768, + "step": 7562 + }, + { + "epoch": 0.63, + "learning_rate": 6.277620338408362e-06, + "loss": 0.4789, + "step": 7563 + }, + { + "epoch": 0.63, + "learning_rate": 6.275105311306298e-06, + "loss": 0.4865, + "step": 7564 + }, + { + "epoch": 0.63, + "learning_rate": 6.272590557745011e-06, + "loss": 0.4426, + "step": 7565 + }, + { + "epoch": 0.63, + "learning_rate": 6.270076077909166e-06, + "loss": 0.4658, + "step": 7566 + }, + { + "epoch": 0.63, + "learning_rate": 6.267561871983424e-06, + "loss": 0.4645, + "step": 7567 + }, + { + "epoch": 0.63, + "learning_rate": 6.265047940152413e-06, + "loss": 0.4599, + "step": 7568 + }, + { + "epoch": 0.63, + "learning_rate": 6.262534282600747e-06, + "loss": 0.4751, + "step": 7569 + }, + { + "epoch": 0.63, + "learning_rate": 6.2600208995130156e-06, + "loss": 0.4681, + "step": 7570 + }, + { + "epoch": 0.63, + "learning_rate": 6.257507791073792e-06, + "loss": 0.4576, + "step": 7571 + }, + { + "epoch": 0.63, + "learning_rate": 6.254994957467633e-06, + "loss": 0.4755, + "step": 7572 + }, + { + "epoch": 0.63, + "learning_rate": 6.252482398879068e-06, + "loss": 0.4781, + "step": 7573 + }, + { + "epoch": 0.63, + "learning_rate": 6.249970115492609e-06, + "loss": 0.4545, + "step": 7574 + }, + { + "epoch": 0.63, + "learning_rate": 6.247458107492745e-06, + "loss": 0.4745, + "step": 7575 + }, + { + "epoch": 0.63, + "learning_rate": 6.244946375063951e-06, + "loss": 0.4892, + "step": 7576 + }, + { + "epoch": 0.63, + "learning_rate": 6.242434918390678e-06, + "loss": 0.4818, + "step": 7577 + }, + { + "epoch": 0.63, + "learning_rate": 6.239923737657351e-06, + "loss": 0.4687, + "step": 7578 + }, + { + "epoch": 0.63, + "learning_rate": 6.237412833048389e-06, + "loss": 0.4732, + "step": 7579 + }, + { + "epoch": 0.63, + "learning_rate": 6.2349022047481784e-06, + "loss": 0.4699, + "step": 7580 + }, + { + "epoch": 0.63, + "learning_rate": 6.2323918529410895e-06, + "loss": 0.4839, + "step": 7581 + }, + { + "epoch": 0.63, + "learning_rate": 6.2298817778114725e-06, + "loss": 0.4702, + "step": 7582 + }, + { + "epoch": 0.63, + "learning_rate": 6.227371979543658e-06, + "loss": 0.4687, + "step": 7583 + }, + { + "epoch": 0.63, + "learning_rate": 6.224862458321954e-06, + "loss": 0.5033, + "step": 7584 + }, + { + "epoch": 0.63, + "learning_rate": 6.222353214330643e-06, + "loss": 0.4622, + "step": 7585 + }, + { + "epoch": 0.63, + "learning_rate": 6.2198442477540036e-06, + "loss": 0.4653, + "step": 7586 + }, + { + "epoch": 0.63, + "learning_rate": 6.2173355587762805e-06, + "loss": 0.4618, + "step": 7587 + }, + { + "epoch": 0.63, + "learning_rate": 6.214827147581701e-06, + "loss": 0.4721, + "step": 7588 + }, + { + "epoch": 0.63, + "learning_rate": 6.212319014354472e-06, + "loss": 0.4822, + "step": 7589 + }, + { + "epoch": 0.64, + "learning_rate": 6.209811159278778e-06, + "loss": 0.4573, + "step": 7590 + }, + { + "epoch": 0.64, + "learning_rate": 6.207303582538789e-06, + "loss": 0.4765, + "step": 7591 + }, + { + "epoch": 0.64, + "learning_rate": 6.2047962843186495e-06, + "loss": 0.4657, + "step": 7592 + }, + { + "epoch": 0.64, + "learning_rate": 6.202289264802488e-06, + "loss": 0.4607, + "step": 7593 + }, + { + "epoch": 0.64, + "learning_rate": 6.199782524174406e-06, + "loss": 0.4389, + "step": 7594 + }, + { + "epoch": 0.64, + "learning_rate": 6.197276062618489e-06, + "loss": 0.4819, + "step": 7595 + }, + { + "epoch": 0.64, + "learning_rate": 6.194769880318801e-06, + "loss": 0.4754, + "step": 7596 + }, + { + "epoch": 0.64, + "learning_rate": 6.192263977459385e-06, + "loss": 0.4634, + "step": 7597 + }, + { + "epoch": 0.64, + "learning_rate": 6.189758354224262e-06, + "loss": 0.4707, + "step": 7598 + }, + { + "epoch": 0.64, + "learning_rate": 6.187253010797443e-06, + "loss": 0.4694, + "step": 7599 + }, + { + "epoch": 0.64, + "learning_rate": 6.1847479473629035e-06, + "loss": 0.4673, + "step": 7600 + }, + { + "epoch": 0.64, + "learning_rate": 6.1822431641046045e-06, + "loss": 0.4739, + "step": 7601 + }, + { + "epoch": 0.64, + "learning_rate": 6.1797386612064895e-06, + "loss": 0.4772, + "step": 7602 + }, + { + "epoch": 0.64, + "learning_rate": 6.177234438852477e-06, + "loss": 0.4582, + "step": 7603 + }, + { + "epoch": 0.64, + "learning_rate": 6.174730497226467e-06, + "loss": 0.4811, + "step": 7604 + }, + { + "epoch": 0.64, + "learning_rate": 6.172226836512336e-06, + "loss": 0.4807, + "step": 7605 + }, + { + "epoch": 0.64, + "learning_rate": 6.16972345689395e-06, + "loss": 0.4766, + "step": 7606 + }, + { + "epoch": 0.64, + "learning_rate": 6.167220358555138e-06, + "loss": 0.4655, + "step": 7607 + }, + { + "epoch": 0.64, + "learning_rate": 6.164717541679724e-06, + "loss": 0.4603, + "step": 7608 + }, + { + "epoch": 0.64, + "learning_rate": 6.162215006451502e-06, + "loss": 0.4671, + "step": 7609 + }, + { + "epoch": 0.64, + "learning_rate": 6.159712753054248e-06, + "loss": 0.4648, + "step": 7610 + }, + { + "epoch": 0.64, + "learning_rate": 6.157210781671713e-06, + "loss": 0.4749, + "step": 7611 + }, + { + "epoch": 0.64, + "learning_rate": 6.154709092487633e-06, + "loss": 0.4573, + "step": 7612 + }, + { + "epoch": 0.64, + "learning_rate": 6.152207685685727e-06, + "loss": 0.4714, + "step": 7613 + }, + { + "epoch": 0.64, + "learning_rate": 6.1497065614496866e-06, + "loss": 0.4892, + "step": 7614 + }, + { + "epoch": 0.64, + "learning_rate": 6.147205719963181e-06, + "loss": 0.4641, + "step": 7615 + }, + { + "epoch": 0.64, + "learning_rate": 6.144705161409858e-06, + "loss": 0.4658, + "step": 7616 + }, + { + "epoch": 0.64, + "learning_rate": 6.142204885973358e-06, + "loss": 0.4738, + "step": 7617 + }, + { + "epoch": 0.64, + "learning_rate": 6.1397048938372825e-06, + "loss": 0.4532, + "step": 7618 + }, + { + "epoch": 0.64, + "learning_rate": 6.13720518518522e-06, + "loss": 0.481, + "step": 7619 + }, + { + "epoch": 0.64, + "learning_rate": 6.134705760200747e-06, + "loss": 0.4683, + "step": 7620 + }, + { + "epoch": 0.64, + "learning_rate": 6.132206619067407e-06, + "loss": 0.4594, + "step": 7621 + }, + { + "epoch": 0.64, + "learning_rate": 6.1297077619687216e-06, + "loss": 0.4808, + "step": 7622 + }, + { + "epoch": 0.64, + "learning_rate": 6.127209189088204e-06, + "loss": 0.4638, + "step": 7623 + }, + { + "epoch": 0.64, + "learning_rate": 6.1247109006093345e-06, + "loss": 0.4768, + "step": 7624 + }, + { + "epoch": 0.64, + "learning_rate": 6.122212896715577e-06, + "loss": 0.4717, + "step": 7625 + }, + { + "epoch": 0.64, + "learning_rate": 6.119715177590373e-06, + "loss": 0.4688, + "step": 7626 + }, + { + "epoch": 0.64, + "learning_rate": 6.1172177434171495e-06, + "loss": 0.4736, + "step": 7627 + }, + { + "epoch": 0.64, + "learning_rate": 6.114720594379304e-06, + "loss": 0.5022, + "step": 7628 + }, + { + "epoch": 0.64, + "learning_rate": 6.112223730660221e-06, + "loss": 0.4698, + "step": 7629 + }, + { + "epoch": 0.64, + "learning_rate": 6.109727152443254e-06, + "loss": 0.4825, + "step": 7630 + }, + { + "epoch": 0.64, + "learning_rate": 6.1072308599117445e-06, + "loss": 0.4657, + "step": 7631 + }, + { + "epoch": 0.64, + "learning_rate": 6.104734853249009e-06, + "loss": 0.4716, + "step": 7632 + }, + { + "epoch": 0.64, + "learning_rate": 6.102239132638343e-06, + "loss": 0.4828, + "step": 7633 + }, + { + "epoch": 0.64, + "learning_rate": 6.099743698263028e-06, + "loss": 0.4588, + "step": 7634 + }, + { + "epoch": 0.64, + "learning_rate": 6.097248550306311e-06, + "loss": 0.4679, + "step": 7635 + }, + { + "epoch": 0.64, + "learning_rate": 6.094753688951428e-06, + "loss": 0.4711, + "step": 7636 + }, + { + "epoch": 0.64, + "learning_rate": 6.092259114381589e-06, + "loss": 0.4754, + "step": 7637 + }, + { + "epoch": 0.64, + "learning_rate": 6.089764826779989e-06, + "loss": 0.4503, + "step": 7638 + }, + { + "epoch": 0.64, + "learning_rate": 6.087270826329793e-06, + "loss": 0.4527, + "step": 7639 + }, + { + "epoch": 0.64, + "learning_rate": 6.084777113214156e-06, + "loss": 0.4627, + "step": 7640 + }, + { + "epoch": 0.64, + "learning_rate": 6.082283687616204e-06, + "loss": 0.4812, + "step": 7641 + }, + { + "epoch": 0.64, + "learning_rate": 6.079790549719044e-06, + "loss": 0.4899, + "step": 7642 + }, + { + "epoch": 0.64, + "learning_rate": 6.077297699705758e-06, + "loss": 0.4577, + "step": 7643 + }, + { + "epoch": 0.64, + "learning_rate": 6.074805137759414e-06, + "loss": 0.4823, + "step": 7644 + }, + { + "epoch": 0.64, + "learning_rate": 6.072312864063054e-06, + "loss": 0.4605, + "step": 7645 + }, + { + "epoch": 0.64, + "learning_rate": 6.0698208787996995e-06, + "loss": 0.4674, + "step": 7646 + }, + { + "epoch": 0.64, + "learning_rate": 6.067329182152355e-06, + "loss": 0.4326, + "step": 7647 + }, + { + "epoch": 0.64, + "learning_rate": 6.064837774303997e-06, + "loss": 0.4767, + "step": 7648 + }, + { + "epoch": 0.64, + "learning_rate": 6.0623466554375864e-06, + "loss": 0.4843, + "step": 7649 + }, + { + "epoch": 0.64, + "learning_rate": 6.059855825736061e-06, + "loss": 0.4827, + "step": 7650 + }, + { + "epoch": 0.64, + "learning_rate": 6.057365285382333e-06, + "loss": 0.4549, + "step": 7651 + }, + { + "epoch": 0.64, + "learning_rate": 6.0548750345593e-06, + "loss": 0.4818, + "step": 7652 + }, + { + "epoch": 0.64, + "learning_rate": 6.052385073449833e-06, + "loss": 0.4602, + "step": 7653 + }, + { + "epoch": 0.64, + "learning_rate": 6.049895402236789e-06, + "loss": 0.4846, + "step": 7654 + }, + { + "epoch": 0.64, + "learning_rate": 6.047406021103e-06, + "loss": 0.4772, + "step": 7655 + }, + { + "epoch": 0.64, + "learning_rate": 6.04491693023127e-06, + "loss": 0.4602, + "step": 7656 + }, + { + "epoch": 0.64, + "learning_rate": 6.042428129804392e-06, + "loss": 0.4973, + "step": 7657 + }, + { + "epoch": 0.64, + "learning_rate": 6.0399396200051285e-06, + "loss": 0.4907, + "step": 7658 + }, + { + "epoch": 0.64, + "learning_rate": 6.0374514010162296e-06, + "loss": 0.4616, + "step": 7659 + }, + { + "epoch": 0.64, + "learning_rate": 6.034963473020417e-06, + "loss": 0.4955, + "step": 7660 + }, + { + "epoch": 0.64, + "learning_rate": 6.0324758362003956e-06, + "loss": 0.4642, + "step": 7661 + }, + { + "epoch": 0.64, + "learning_rate": 6.029988490738849e-06, + "loss": 0.4725, + "step": 7662 + }, + { + "epoch": 0.64, + "learning_rate": 6.027501436818433e-06, + "loss": 0.4769, + "step": 7663 + }, + { + "epoch": 0.64, + "learning_rate": 6.0250146746217895e-06, + "loss": 0.4685, + "step": 7664 + }, + { + "epoch": 0.64, + "learning_rate": 6.022528204331534e-06, + "loss": 0.4556, + "step": 7665 + }, + { + "epoch": 0.64, + "learning_rate": 6.020042026130262e-06, + "loss": 0.4587, + "step": 7666 + }, + { + "epoch": 0.64, + "learning_rate": 6.017556140200553e-06, + "loss": 0.4977, + "step": 7667 + }, + { + "epoch": 0.64, + "learning_rate": 6.015070546724957e-06, + "loss": 0.4682, + "step": 7668 + }, + { + "epoch": 0.64, + "learning_rate": 6.012585245886004e-06, + "loss": 0.4524, + "step": 7669 + }, + { + "epoch": 0.64, + "learning_rate": 6.0101002378662066e-06, + "loss": 0.4828, + "step": 7670 + }, + { + "epoch": 0.64, + "learning_rate": 6.007615522848053e-06, + "loss": 0.4578, + "step": 7671 + }, + { + "epoch": 0.64, + "learning_rate": 6.00513110101401e-06, + "loss": 0.4576, + "step": 7672 + }, + { + "epoch": 0.64, + "learning_rate": 6.002646972546517e-06, + "loss": 0.4703, + "step": 7673 + }, + { + "epoch": 0.64, + "learning_rate": 6.000163137628009e-06, + "loss": 0.4826, + "step": 7674 + }, + { + "epoch": 0.64, + "learning_rate": 5.997679596440884e-06, + "loss": 0.4883, + "step": 7675 + }, + { + "epoch": 0.64, + "learning_rate": 5.995196349167523e-06, + "loss": 0.4739, + "step": 7676 + }, + { + "epoch": 0.64, + "learning_rate": 5.992713395990285e-06, + "loss": 0.485, + "step": 7677 + }, + { + "epoch": 0.64, + "learning_rate": 5.990230737091505e-06, + "loss": 0.4745, + "step": 7678 + }, + { + "epoch": 0.64, + "learning_rate": 5.987748372653504e-06, + "loss": 0.4834, + "step": 7679 + }, + { + "epoch": 0.64, + "learning_rate": 5.9852663028585704e-06, + "loss": 0.466, + "step": 7680 + }, + { + "epoch": 0.64, + "learning_rate": 5.982784527888985e-06, + "loss": 0.4647, + "step": 7681 + }, + { + "epoch": 0.64, + "learning_rate": 5.980303047926996e-06, + "loss": 0.476, + "step": 7682 + }, + { + "epoch": 0.64, + "learning_rate": 5.977821863154832e-06, + "loss": 0.4727, + "step": 7683 + }, + { + "epoch": 0.64, + "learning_rate": 5.975340973754697e-06, + "loss": 0.463, + "step": 7684 + }, + { + "epoch": 0.64, + "learning_rate": 5.972860379908784e-06, + "loss": 0.474, + "step": 7685 + }, + { + "epoch": 0.64, + "learning_rate": 5.970380081799254e-06, + "loss": 0.4732, + "step": 7686 + }, + { + "epoch": 0.64, + "learning_rate": 5.967900079608247e-06, + "loss": 0.4832, + "step": 7687 + }, + { + "epoch": 0.64, + "learning_rate": 5.965420373517892e-06, + "loss": 0.4749, + "step": 7688 + }, + { + "epoch": 0.64, + "learning_rate": 5.96294096371028e-06, + "loss": 0.4943, + "step": 7689 + }, + { + "epoch": 0.64, + "learning_rate": 5.960461850367496e-06, + "loss": 0.4747, + "step": 7690 + }, + { + "epoch": 0.64, + "learning_rate": 5.9579830336715905e-06, + "loss": 0.4638, + "step": 7691 + }, + { + "epoch": 0.64, + "learning_rate": 5.9555045138046e-06, + "loss": 0.4821, + "step": 7692 + }, + { + "epoch": 0.64, + "learning_rate": 5.953026290948534e-06, + "loss": 0.4843, + "step": 7693 + }, + { + "epoch": 0.64, + "learning_rate": 5.950548365285383e-06, + "loss": 0.4715, + "step": 7694 + }, + { + "epoch": 0.64, + "learning_rate": 5.948070736997118e-06, + "loss": 0.4683, + "step": 7695 + }, + { + "epoch": 0.64, + "learning_rate": 5.9455934062656874e-06, + "loss": 0.4626, + "step": 7696 + }, + { + "epoch": 0.64, + "learning_rate": 5.943116373273012e-06, + "loss": 0.4571, + "step": 7697 + }, + { + "epoch": 0.64, + "learning_rate": 5.940639638200998e-06, + "loss": 0.48, + "step": 7698 + }, + { + "epoch": 0.64, + "learning_rate": 5.938163201231523e-06, + "loss": 0.4771, + "step": 7699 + }, + { + "epoch": 0.64, + "learning_rate": 5.935687062546449e-06, + "loss": 0.4547, + "step": 7700 + }, + { + "epoch": 0.64, + "learning_rate": 5.933211222327608e-06, + "loss": 0.4689, + "step": 7701 + }, + { + "epoch": 0.64, + "learning_rate": 5.930735680756825e-06, + "loss": 0.4698, + "step": 7702 + }, + { + "epoch": 0.64, + "learning_rate": 5.928260438015887e-06, + "loss": 0.4458, + "step": 7703 + }, + { + "epoch": 0.64, + "learning_rate": 5.925785494286566e-06, + "loss": 0.4599, + "step": 7704 + }, + { + "epoch": 0.64, + "learning_rate": 5.923310849750614e-06, + "loss": 0.4897, + "step": 7705 + }, + { + "epoch": 0.64, + "learning_rate": 5.920836504589756e-06, + "loss": 0.4731, + "step": 7706 + }, + { + "epoch": 0.64, + "learning_rate": 5.9183624589856956e-06, + "loss": 0.4675, + "step": 7707 + }, + { + "epoch": 0.64, + "learning_rate": 5.915888713120124e-06, + "loss": 0.4822, + "step": 7708 + }, + { + "epoch": 0.64, + "learning_rate": 5.913415267174696e-06, + "loss": 0.4777, + "step": 7709 + }, + { + "epoch": 0.65, + "learning_rate": 5.910942121331054e-06, + "loss": 0.4775, + "step": 7710 + }, + { + "epoch": 0.65, + "learning_rate": 5.908469275770815e-06, + "loss": 0.4773, + "step": 7711 + }, + { + "epoch": 0.65, + "learning_rate": 5.905996730675575e-06, + "loss": 0.4766, + "step": 7712 + }, + { + "epoch": 0.65, + "learning_rate": 5.903524486226907e-06, + "loss": 0.4699, + "step": 7713 + }, + { + "epoch": 0.65, + "learning_rate": 5.901052542606358e-06, + "loss": 0.4748, + "step": 7714 + }, + { + "epoch": 0.65, + "learning_rate": 5.898580899995463e-06, + "loss": 0.4859, + "step": 7715 + }, + { + "epoch": 0.65, + "learning_rate": 5.896109558575731e-06, + "loss": 0.4632, + "step": 7716 + }, + { + "epoch": 0.65, + "learning_rate": 5.893638518528643e-06, + "loss": 0.4726, + "step": 7717 + }, + { + "epoch": 0.65, + "learning_rate": 5.891167780035663e-06, + "loss": 0.4775, + "step": 7718 + }, + { + "epoch": 0.65, + "learning_rate": 5.888697343278229e-06, + "loss": 0.4747, + "step": 7719 + }, + { + "epoch": 0.65, + "learning_rate": 5.886227208437763e-06, + "loss": 0.4684, + "step": 7720 + }, + { + "epoch": 0.65, + "learning_rate": 5.8837573756956575e-06, + "loss": 0.4646, + "step": 7721 + }, + { + "epoch": 0.65, + "learning_rate": 5.881287845233292e-06, + "loss": 0.4675, + "step": 7722 + }, + { + "epoch": 0.65, + "learning_rate": 5.878818617232018e-06, + "loss": 0.4882, + "step": 7723 + }, + { + "epoch": 0.65, + "learning_rate": 5.876349691873162e-06, + "loss": 0.4614, + "step": 7724 + }, + { + "epoch": 0.65, + "learning_rate": 5.873881069338032e-06, + "loss": 0.4633, + "step": 7725 + }, + { + "epoch": 0.65, + "learning_rate": 5.871412749807917e-06, + "loss": 0.4684, + "step": 7726 + }, + { + "epoch": 0.65, + "learning_rate": 5.868944733464077e-06, + "loss": 0.4677, + "step": 7727 + }, + { + "epoch": 0.65, + "learning_rate": 5.866477020487748e-06, + "loss": 0.4895, + "step": 7728 + }, + { + "epoch": 0.65, + "learning_rate": 5.86400961106016e-06, + "loss": 0.4697, + "step": 7729 + }, + { + "epoch": 0.65, + "learning_rate": 5.8615425053625005e-06, + "loss": 0.4953, + "step": 7730 + }, + { + "epoch": 0.65, + "learning_rate": 5.859075703575949e-06, + "loss": 0.464, + "step": 7731 + }, + { + "epoch": 0.65, + "learning_rate": 5.856609205881654e-06, + "loss": 0.4749, + "step": 7732 + }, + { + "epoch": 0.65, + "learning_rate": 5.854143012460745e-06, + "loss": 0.4698, + "step": 7733 + }, + { + "epoch": 0.65, + "learning_rate": 5.851677123494326e-06, + "loss": 0.4582, + "step": 7734 + }, + { + "epoch": 0.65, + "learning_rate": 5.849211539163486e-06, + "loss": 0.4782, + "step": 7735 + }, + { + "epoch": 0.65, + "learning_rate": 5.846746259649288e-06, + "loss": 0.4867, + "step": 7736 + }, + { + "epoch": 0.65, + "learning_rate": 5.844281285132769e-06, + "loss": 0.4811, + "step": 7737 + }, + { + "epoch": 0.65, + "learning_rate": 5.841816615794948e-06, + "loss": 0.4702, + "step": 7738 + }, + { + "epoch": 0.65, + "learning_rate": 5.839352251816821e-06, + "loss": 0.4787, + "step": 7739 + }, + { + "epoch": 0.65, + "learning_rate": 5.836888193379359e-06, + "loss": 0.4668, + "step": 7740 + }, + { + "epoch": 0.65, + "learning_rate": 5.834424440663512e-06, + "loss": 0.4868, + "step": 7741 + }, + { + "epoch": 0.65, + "learning_rate": 5.831960993850203e-06, + "loss": 0.4854, + "step": 7742 + }, + { + "epoch": 0.65, + "learning_rate": 5.829497853120345e-06, + "loss": 0.4697, + "step": 7743 + }, + { + "epoch": 0.65, + "learning_rate": 5.827035018654821e-06, + "loss": 0.4569, + "step": 7744 + }, + { + "epoch": 0.65, + "learning_rate": 5.824572490634488e-06, + "loss": 0.464, + "step": 7745 + }, + { + "epoch": 0.65, + "learning_rate": 5.822110269240184e-06, + "loss": 0.5041, + "step": 7746 + }, + { + "epoch": 0.65, + "learning_rate": 5.819648354652725e-06, + "loss": 0.4528, + "step": 7747 + }, + { + "epoch": 0.65, + "learning_rate": 5.8171867470529e-06, + "loss": 0.4847, + "step": 7748 + }, + { + "epoch": 0.65, + "learning_rate": 5.8147254466214865e-06, + "loss": 0.4592, + "step": 7749 + }, + { + "epoch": 0.65, + "learning_rate": 5.812264453539228e-06, + "loss": 0.4716, + "step": 7750 + }, + { + "epoch": 0.65, + "learning_rate": 5.809803767986851e-06, + "loss": 0.473, + "step": 7751 + }, + { + "epoch": 0.65, + "learning_rate": 5.807343390145055e-06, + "loss": 0.4787, + "step": 7752 + }, + { + "epoch": 0.65, + "learning_rate": 5.80488332019452e-06, + "loss": 0.4637, + "step": 7753 + }, + { + "epoch": 0.65, + "learning_rate": 5.802423558315908e-06, + "loss": 0.4845, + "step": 7754 + }, + { + "epoch": 0.65, + "learning_rate": 5.799964104689847e-06, + "loss": 0.4641, + "step": 7755 + }, + { + "epoch": 0.65, + "learning_rate": 5.797504959496957e-06, + "loss": 0.4473, + "step": 7756 + }, + { + "epoch": 0.65, + "learning_rate": 5.795046122917823e-06, + "loss": 0.4654, + "step": 7757 + }, + { + "epoch": 0.65, + "learning_rate": 5.792587595133012e-06, + "loss": 0.4761, + "step": 7758 + }, + { + "epoch": 0.65, + "learning_rate": 5.790129376323068e-06, + "loss": 0.4757, + "step": 7759 + }, + { + "epoch": 0.65, + "learning_rate": 5.787671466668513e-06, + "loss": 0.4667, + "step": 7760 + }, + { + "epoch": 0.65, + "learning_rate": 5.785213866349844e-06, + "loss": 0.5057, + "step": 7761 + }, + { + "epoch": 0.65, + "learning_rate": 5.782756575547535e-06, + "loss": 0.4902, + "step": 7762 + }, + { + "epoch": 0.65, + "learning_rate": 5.780299594442047e-06, + "loss": 0.4814, + "step": 7763 + }, + { + "epoch": 0.65, + "learning_rate": 5.777842923213801e-06, + "loss": 0.4806, + "step": 7764 + }, + { + "epoch": 0.65, + "learning_rate": 5.775386562043212e-06, + "loss": 0.4772, + "step": 7765 + }, + { + "epoch": 0.65, + "learning_rate": 5.7729305111106645e-06, + "loss": 0.4515, + "step": 7766 + }, + { + "epoch": 0.65, + "learning_rate": 5.770474770596518e-06, + "loss": 0.4629, + "step": 7767 + }, + { + "epoch": 0.65, + "learning_rate": 5.768019340681113e-06, + "loss": 0.4687, + "step": 7768 + }, + { + "epoch": 0.65, + "learning_rate": 5.765564221544759e-06, + "loss": 0.458, + "step": 7769 + }, + { + "epoch": 0.65, + "learning_rate": 5.763109413367762e-06, + "loss": 0.4801, + "step": 7770 + }, + { + "epoch": 0.65, + "learning_rate": 5.760654916330388e-06, + "loss": 0.5006, + "step": 7771 + }, + { + "epoch": 0.65, + "learning_rate": 5.758200730612883e-06, + "loss": 0.4343, + "step": 7772 + }, + { + "epoch": 0.65, + "learning_rate": 5.75574685639547e-06, + "loss": 0.4685, + "step": 7773 + }, + { + "epoch": 0.65, + "learning_rate": 5.7532932938583575e-06, + "loss": 0.4836, + "step": 7774 + }, + { + "epoch": 0.65, + "learning_rate": 5.750840043181722e-06, + "loss": 0.4585, + "step": 7775 + }, + { + "epoch": 0.65, + "learning_rate": 5.7483871045457185e-06, + "loss": 0.4923, + "step": 7776 + }, + { + "epoch": 0.65, + "learning_rate": 5.745934478130484e-06, + "loss": 0.4916, + "step": 7777 + }, + { + "epoch": 0.65, + "learning_rate": 5.7434821641161285e-06, + "loss": 0.4803, + "step": 7778 + }, + { + "epoch": 0.65, + "learning_rate": 5.74103016268274e-06, + "loss": 0.4627, + "step": 7779 + }, + { + "epoch": 0.65, + "learning_rate": 5.738578474010379e-06, + "loss": 0.4538, + "step": 7780 + }, + { + "epoch": 0.65, + "learning_rate": 5.736127098279092e-06, + "loss": 0.4798, + "step": 7781 + }, + { + "epoch": 0.65, + "learning_rate": 5.733676035668891e-06, + "loss": 0.4515, + "step": 7782 + }, + { + "epoch": 0.65, + "learning_rate": 5.731225286359781e-06, + "loss": 0.4924, + "step": 7783 + }, + { + "epoch": 0.65, + "learning_rate": 5.728774850531733e-06, + "loss": 0.468, + "step": 7784 + }, + { + "epoch": 0.65, + "learning_rate": 5.726324728364688e-06, + "loss": 0.4704, + "step": 7785 + }, + { + "epoch": 0.65, + "learning_rate": 5.723874920038586e-06, + "loss": 0.4524, + "step": 7786 + }, + { + "epoch": 0.65, + "learning_rate": 5.721425425733322e-06, + "loss": 0.4711, + "step": 7787 + }, + { + "epoch": 0.65, + "learning_rate": 5.718976245628779e-06, + "loss": 0.4704, + "step": 7788 + }, + { + "epoch": 0.65, + "learning_rate": 5.7165273799048105e-06, + "loss": 0.475, + "step": 7789 + }, + { + "epoch": 0.65, + "learning_rate": 5.71407882874126e-06, + "loss": 0.4684, + "step": 7790 + }, + { + "epoch": 0.65, + "learning_rate": 5.711630592317933e-06, + "loss": 0.4576, + "step": 7791 + }, + { + "epoch": 0.65, + "learning_rate": 5.709182670814619e-06, + "loss": 0.4713, + "step": 7792 + }, + { + "epoch": 0.65, + "learning_rate": 5.706735064411082e-06, + "loss": 0.4866, + "step": 7793 + }, + { + "epoch": 0.65, + "learning_rate": 5.704287773287061e-06, + "loss": 0.4498, + "step": 7794 + }, + { + "epoch": 0.65, + "learning_rate": 5.701840797622284e-06, + "loss": 0.4883, + "step": 7795 + }, + { + "epoch": 0.65, + "learning_rate": 5.699394137596437e-06, + "loss": 0.4998, + "step": 7796 + }, + { + "epoch": 0.65, + "learning_rate": 5.6969477933892e-06, + "loss": 0.4451, + "step": 7797 + }, + { + "epoch": 0.65, + "learning_rate": 5.69450176518022e-06, + "loss": 0.4563, + "step": 7798 + }, + { + "epoch": 0.65, + "learning_rate": 5.692056053149122e-06, + "loss": 0.4794, + "step": 7799 + }, + { + "epoch": 0.65, + "learning_rate": 5.68961065747551e-06, + "loss": 0.4454, + "step": 7800 + }, + { + "epoch": 0.65, + "learning_rate": 5.687165578338962e-06, + "loss": 0.4627, + "step": 7801 + }, + { + "epoch": 0.65, + "learning_rate": 5.684720815919036e-06, + "loss": 0.4788, + "step": 7802 + }, + { + "epoch": 0.65, + "learning_rate": 5.682276370395261e-06, + "loss": 0.4744, + "step": 7803 + }, + { + "epoch": 0.65, + "learning_rate": 5.679832241947154e-06, + "loss": 0.4643, + "step": 7804 + }, + { + "epoch": 0.65, + "learning_rate": 5.677388430754196e-06, + "loss": 0.4488, + "step": 7805 + }, + { + "epoch": 0.65, + "learning_rate": 5.674944936995854e-06, + "loss": 0.4716, + "step": 7806 + }, + { + "epoch": 0.65, + "learning_rate": 5.672501760851568e-06, + "loss": 0.4773, + "step": 7807 + }, + { + "epoch": 0.65, + "learning_rate": 5.6700589025007535e-06, + "loss": 0.4811, + "step": 7808 + }, + { + "epoch": 0.65, + "learning_rate": 5.667616362122803e-06, + "loss": 0.491, + "step": 7809 + }, + { + "epoch": 0.65, + "learning_rate": 5.665174139897083e-06, + "loss": 0.4657, + "step": 7810 + }, + { + "epoch": 0.65, + "learning_rate": 5.662732236002949e-06, + "loss": 0.4906, + "step": 7811 + }, + { + "epoch": 0.65, + "learning_rate": 5.660290650619719e-06, + "loss": 0.481, + "step": 7812 + }, + { + "epoch": 0.65, + "learning_rate": 5.657849383926693e-06, + "loss": 0.4664, + "step": 7813 + }, + { + "epoch": 0.65, + "learning_rate": 5.655408436103149e-06, + "loss": 0.4844, + "step": 7814 + }, + { + "epoch": 0.65, + "learning_rate": 5.652967807328334e-06, + "loss": 0.4665, + "step": 7815 + }, + { + "epoch": 0.65, + "learning_rate": 5.6505274977814875e-06, + "loss": 0.4795, + "step": 7816 + }, + { + "epoch": 0.65, + "learning_rate": 5.648087507641806e-06, + "loss": 0.4739, + "step": 7817 + }, + { + "epoch": 0.65, + "learning_rate": 5.6456478370884815e-06, + "loss": 0.508, + "step": 7818 + }, + { + "epoch": 0.65, + "learning_rate": 5.643208486300669e-06, + "loss": 0.4686, + "step": 7819 + }, + { + "epoch": 0.65, + "learning_rate": 5.640769455457502e-06, + "loss": 0.4812, + "step": 7820 + }, + { + "epoch": 0.65, + "learning_rate": 5.6383307447380965e-06, + "loss": 0.4453, + "step": 7821 + }, + { + "epoch": 0.65, + "learning_rate": 5.635892354321539e-06, + "loss": 0.4728, + "step": 7822 + }, + { + "epoch": 0.65, + "learning_rate": 5.633454284386893e-06, + "loss": 0.4947, + "step": 7823 + }, + { + "epoch": 0.65, + "learning_rate": 5.631016535113204e-06, + "loss": 0.4628, + "step": 7824 + }, + { + "epoch": 0.65, + "learning_rate": 5.628579106679491e-06, + "loss": 0.4684, + "step": 7825 + }, + { + "epoch": 0.65, + "learning_rate": 5.62614199926474e-06, + "loss": 0.4589, + "step": 7826 + }, + { + "epoch": 0.65, + "learning_rate": 5.623705213047933e-06, + "loss": 0.483, + "step": 7827 + }, + { + "epoch": 0.65, + "learning_rate": 5.621268748208013e-06, + "loss": 0.4802, + "step": 7828 + }, + { + "epoch": 0.66, + "learning_rate": 5.618832604923904e-06, + "loss": 0.4595, + "step": 7829 + }, + { + "epoch": 0.66, + "learning_rate": 5.616396783374501e-06, + "loss": 0.4818, + "step": 7830 + }, + { + "epoch": 0.66, + "learning_rate": 5.613961283738692e-06, + "loss": 0.4592, + "step": 7831 + }, + { + "epoch": 0.66, + "learning_rate": 5.61152610619532e-06, + "loss": 0.4717, + "step": 7832 + }, + { + "epoch": 0.66, + "learning_rate": 5.60909125092322e-06, + "loss": 0.4754, + "step": 7833 + }, + { + "epoch": 0.66, + "learning_rate": 5.606656718101193e-06, + "loss": 0.4837, + "step": 7834 + }, + { + "epoch": 0.66, + "learning_rate": 5.604222507908021e-06, + "loss": 0.4693, + "step": 7835 + }, + { + "epoch": 0.66, + "learning_rate": 5.60178862052247e-06, + "loss": 0.4601, + "step": 7836 + }, + { + "epoch": 0.66, + "learning_rate": 5.599355056123263e-06, + "loss": 0.5122, + "step": 7837 + }, + { + "epoch": 0.66, + "learning_rate": 5.596921814889122e-06, + "loss": 0.4721, + "step": 7838 + }, + { + "epoch": 0.66, + "learning_rate": 5.594488896998729e-06, + "loss": 0.481, + "step": 7839 + }, + { + "epoch": 0.66, + "learning_rate": 5.592056302630748e-06, + "loss": 0.4778, + "step": 7840 + }, + { + "epoch": 0.66, + "learning_rate": 5.589624031963816e-06, + "loss": 0.4752, + "step": 7841 + }, + { + "epoch": 0.66, + "learning_rate": 5.5871920851765535e-06, + "loss": 0.4595, + "step": 7842 + }, + { + "epoch": 0.66, + "learning_rate": 5.584760462447548e-06, + "loss": 0.4692, + "step": 7843 + }, + { + "epoch": 0.66, + "learning_rate": 5.582329163955367e-06, + "loss": 0.47, + "step": 7844 + }, + { + "epoch": 0.66, + "learning_rate": 5.579898189878561e-06, + "loss": 0.4761, + "step": 7845 + }, + { + "epoch": 0.66, + "learning_rate": 5.577467540395645e-06, + "loss": 0.473, + "step": 7846 + }, + { + "epoch": 0.66, + "learning_rate": 5.575037215685119e-06, + "loss": 0.4554, + "step": 7847 + }, + { + "epoch": 0.66, + "learning_rate": 5.572607215925458e-06, + "loss": 0.4822, + "step": 7848 + }, + { + "epoch": 0.66, + "learning_rate": 5.570177541295107e-06, + "loss": 0.4727, + "step": 7849 + }, + { + "epoch": 0.66, + "learning_rate": 5.567748191972493e-06, + "loss": 0.4875, + "step": 7850 + }, + { + "epoch": 0.66, + "learning_rate": 5.565319168136012e-06, + "loss": 0.4617, + "step": 7851 + }, + { + "epoch": 0.66, + "learning_rate": 5.56289046996405e-06, + "loss": 0.4695, + "step": 7852 + }, + { + "epoch": 0.66, + "learning_rate": 5.5604620976349575e-06, + "loss": 0.4883, + "step": 7853 + }, + { + "epoch": 0.66, + "learning_rate": 5.558034051327061e-06, + "loss": 0.4778, + "step": 7854 + }, + { + "epoch": 0.66, + "learning_rate": 5.55560633121867e-06, + "loss": 0.4758, + "step": 7855 + }, + { + "epoch": 0.66, + "learning_rate": 5.553178937488061e-06, + "loss": 0.4683, + "step": 7856 + }, + { + "epoch": 0.66, + "learning_rate": 5.550751870313494e-06, + "loss": 0.4598, + "step": 7857 + }, + { + "epoch": 0.66, + "learning_rate": 5.548325129873209e-06, + "loss": 0.5035, + "step": 7858 + }, + { + "epoch": 0.66, + "learning_rate": 5.545898716345408e-06, + "loss": 0.4741, + "step": 7859 + }, + { + "epoch": 0.66, + "learning_rate": 5.543472629908282e-06, + "loss": 0.4689, + "step": 7860 + }, + { + "epoch": 0.66, + "learning_rate": 5.541046870739987e-06, + "loss": 0.4767, + "step": 7861 + }, + { + "epoch": 0.66, + "learning_rate": 5.538621439018666e-06, + "loss": 0.4579, + "step": 7862 + }, + { + "epoch": 0.66, + "learning_rate": 5.53619633492243e-06, + "loss": 0.4773, + "step": 7863 + }, + { + "epoch": 0.66, + "learning_rate": 5.533771558629365e-06, + "loss": 0.4711, + "step": 7864 + }, + { + "epoch": 0.66, + "learning_rate": 5.531347110317544e-06, + "loss": 0.482, + "step": 7865 + }, + { + "epoch": 0.66, + "learning_rate": 5.528922990165004e-06, + "loss": 0.443, + "step": 7866 + }, + { + "epoch": 0.66, + "learning_rate": 5.52649919834976e-06, + "loss": 0.4557, + "step": 7867 + }, + { + "epoch": 0.66, + "learning_rate": 5.524075735049812e-06, + "loss": 0.4646, + "step": 7868 + }, + { + "epoch": 0.66, + "learning_rate": 5.521652600443124e-06, + "loss": 0.4632, + "step": 7869 + }, + { + "epoch": 0.66, + "learning_rate": 5.519229794707643e-06, + "loss": 0.4557, + "step": 7870 + }, + { + "epoch": 0.66, + "learning_rate": 5.516807318021286e-06, + "loss": 0.475, + "step": 7871 + }, + { + "epoch": 0.66, + "learning_rate": 5.514385170561956e-06, + "loss": 0.4735, + "step": 7872 + }, + { + "epoch": 0.66, + "learning_rate": 5.511963352507521e-06, + "loss": 0.4566, + "step": 7873 + }, + { + "epoch": 0.66, + "learning_rate": 5.50954186403583e-06, + "loss": 0.4755, + "step": 7874 + }, + { + "epoch": 0.66, + "learning_rate": 5.507120705324709e-06, + "loss": 0.4943, + "step": 7875 + }, + { + "epoch": 0.66, + "learning_rate": 5.504699876551951e-06, + "loss": 0.4656, + "step": 7876 + }, + { + "epoch": 0.66, + "learning_rate": 5.502279377895341e-06, + "loss": 0.4863, + "step": 7877 + }, + { + "epoch": 0.66, + "learning_rate": 5.499859209532622e-06, + "loss": 0.4729, + "step": 7878 + }, + { + "epoch": 0.66, + "learning_rate": 5.497439371641528e-06, + "loss": 0.4802, + "step": 7879 + }, + { + "epoch": 0.66, + "learning_rate": 5.495019864399761e-06, + "loss": 0.4667, + "step": 7880 + }, + { + "epoch": 0.66, + "learning_rate": 5.492600687984997e-06, + "loss": 0.4724, + "step": 7881 + }, + { + "epoch": 0.66, + "learning_rate": 5.490181842574891e-06, + "loss": 0.4769, + "step": 7882 + }, + { + "epoch": 0.66, + "learning_rate": 5.487763328347071e-06, + "loss": 0.4641, + "step": 7883 + }, + { + "epoch": 0.66, + "learning_rate": 5.485345145479147e-06, + "loss": 0.485, + "step": 7884 + }, + { + "epoch": 0.66, + "learning_rate": 5.482927294148691e-06, + "loss": 0.4727, + "step": 7885 + }, + { + "epoch": 0.66, + "learning_rate": 5.480509774533271e-06, + "loss": 0.4835, + "step": 7886 + }, + { + "epoch": 0.66, + "learning_rate": 5.478092586810413e-06, + "loss": 0.4731, + "step": 7887 + }, + { + "epoch": 0.66, + "learning_rate": 5.47567573115763e-06, + "loss": 0.4807, + "step": 7888 + }, + { + "epoch": 0.66, + "learning_rate": 5.473259207752404e-06, + "loss": 0.4883, + "step": 7889 + }, + { + "epoch": 0.66, + "learning_rate": 5.470843016772194e-06, + "loss": 0.4636, + "step": 7890 + }, + { + "epoch": 0.66, + "learning_rate": 5.468427158394434e-06, + "loss": 0.4616, + "step": 7891 + }, + { + "epoch": 0.66, + "learning_rate": 5.466011632796531e-06, + "loss": 0.4808, + "step": 7892 + }, + { + "epoch": 0.66, + "learning_rate": 5.463596440155878e-06, + "loss": 0.4907, + "step": 7893 + }, + { + "epoch": 0.66, + "learning_rate": 5.461181580649837e-06, + "loss": 0.4812, + "step": 7894 + }, + { + "epoch": 0.66, + "learning_rate": 5.4587670544557404e-06, + "loss": 0.4711, + "step": 7895 + }, + { + "epoch": 0.66, + "learning_rate": 5.456352861750904e-06, + "loss": 0.4735, + "step": 7896 + }, + { + "epoch": 0.66, + "learning_rate": 5.453939002712611e-06, + "loss": 0.4667, + "step": 7897 + }, + { + "epoch": 0.66, + "learning_rate": 5.451525477518133e-06, + "loss": 0.4629, + "step": 7898 + }, + { + "epoch": 0.66, + "learning_rate": 5.4491122863447e-06, + "loss": 0.4739, + "step": 7899 + }, + { + "epoch": 0.66, + "learning_rate": 5.446699429369538e-06, + "loss": 0.4901, + "step": 7900 + }, + { + "epoch": 0.66, + "learning_rate": 5.444286906769831e-06, + "loss": 0.4603, + "step": 7901 + }, + { + "epoch": 0.66, + "learning_rate": 5.441874718722744e-06, + "loss": 0.474, + "step": 7902 + }, + { + "epoch": 0.66, + "learning_rate": 5.439462865405419e-06, + "loss": 0.4659, + "step": 7903 + }, + { + "epoch": 0.66, + "learning_rate": 5.437051346994973e-06, + "loss": 0.4519, + "step": 7904 + }, + { + "epoch": 0.66, + "learning_rate": 5.434640163668494e-06, + "loss": 0.4696, + "step": 7905 + }, + { + "epoch": 0.66, + "learning_rate": 5.432229315603054e-06, + "loss": 0.5035, + "step": 7906 + }, + { + "epoch": 0.66, + "learning_rate": 5.429818802975697e-06, + "loss": 0.4653, + "step": 7907 + }, + { + "epoch": 0.66, + "learning_rate": 5.427408625963434e-06, + "loss": 0.473, + "step": 7908 + }, + { + "epoch": 0.66, + "learning_rate": 5.424998784743266e-06, + "loss": 0.5055, + "step": 7909 + }, + { + "epoch": 0.66, + "learning_rate": 5.4225892794921585e-06, + "loss": 0.4932, + "step": 7910 + }, + { + "epoch": 0.66, + "learning_rate": 5.420180110387056e-06, + "loss": 0.4689, + "step": 7911 + }, + { + "epoch": 0.66, + "learning_rate": 5.417771277604873e-06, + "loss": 0.4671, + "step": 7912 + }, + { + "epoch": 0.66, + "learning_rate": 5.4153627813225114e-06, + "loss": 0.4679, + "step": 7913 + }, + { + "epoch": 0.66, + "learning_rate": 5.412954621716839e-06, + "loss": 0.4852, + "step": 7914 + }, + { + "epoch": 0.66, + "learning_rate": 5.410546798964701e-06, + "loss": 0.4746, + "step": 7915 + }, + { + "epoch": 0.66, + "learning_rate": 5.408139313242916e-06, + "loss": 0.4582, + "step": 7916 + }, + { + "epoch": 0.66, + "learning_rate": 5.405732164728276e-06, + "loss": 0.4603, + "step": 7917 + }, + { + "epoch": 0.66, + "learning_rate": 5.4033253535975635e-06, + "loss": 0.4852, + "step": 7918 + }, + { + "epoch": 0.66, + "learning_rate": 5.400918880027513e-06, + "loss": 0.4561, + "step": 7919 + }, + { + "epoch": 0.66, + "learning_rate": 5.398512744194854e-06, + "loss": 0.4665, + "step": 7920 + }, + { + "epoch": 0.66, + "learning_rate": 5.3961069462762804e-06, + "loss": 0.4571, + "step": 7921 + }, + { + "epoch": 0.66, + "learning_rate": 5.3937014864484635e-06, + "loss": 0.4624, + "step": 7922 + }, + { + "epoch": 0.66, + "learning_rate": 5.39129636488805e-06, + "loss": 0.4613, + "step": 7923 + }, + { + "epoch": 0.66, + "learning_rate": 5.388891581771664e-06, + "loss": 0.4828, + "step": 7924 + }, + { + "epoch": 0.66, + "learning_rate": 5.3864871372759e-06, + "loss": 0.4632, + "step": 7925 + }, + { + "epoch": 0.66, + "learning_rate": 5.384083031577327e-06, + "loss": 0.4565, + "step": 7926 + }, + { + "epoch": 0.66, + "learning_rate": 5.381679264852503e-06, + "loss": 0.4787, + "step": 7927 + }, + { + "epoch": 0.66, + "learning_rate": 5.379275837277944e-06, + "loss": 0.4624, + "step": 7928 + }, + { + "epoch": 0.66, + "learning_rate": 5.3768727490301445e-06, + "loss": 0.4692, + "step": 7929 + }, + { + "epoch": 0.66, + "learning_rate": 5.374470000285584e-06, + "loss": 0.454, + "step": 7930 + }, + { + "epoch": 0.66, + "learning_rate": 5.3720675912207085e-06, + "loss": 0.4773, + "step": 7931 + }, + { + "epoch": 0.66, + "learning_rate": 5.369665522011938e-06, + "loss": 0.4697, + "step": 7932 + }, + { + "epoch": 0.66, + "learning_rate": 5.367263792835673e-06, + "loss": 0.4758, + "step": 7933 + }, + { + "epoch": 0.66, + "learning_rate": 5.3648624038682886e-06, + "loss": 0.4822, + "step": 7934 + }, + { + "epoch": 0.66, + "learning_rate": 5.362461355286129e-06, + "loss": 0.4614, + "step": 7935 + }, + { + "epoch": 0.66, + "learning_rate": 5.360060647265519e-06, + "loss": 0.4877, + "step": 7936 + }, + { + "epoch": 0.66, + "learning_rate": 5.357660279982757e-06, + "loss": 0.4527, + "step": 7937 + }, + { + "epoch": 0.66, + "learning_rate": 5.35526025361411e-06, + "loss": 0.4733, + "step": 7938 + }, + { + "epoch": 0.66, + "learning_rate": 5.352860568335835e-06, + "loss": 0.4525, + "step": 7939 + }, + { + "epoch": 0.66, + "learning_rate": 5.3504612243241474e-06, + "loss": 0.4608, + "step": 7940 + }, + { + "epoch": 0.66, + "learning_rate": 5.3480622217552524e-06, + "loss": 0.4853, + "step": 7941 + }, + { + "epoch": 0.66, + "learning_rate": 5.3456635608053186e-06, + "loss": 0.4678, + "step": 7942 + }, + { + "epoch": 0.66, + "learning_rate": 5.343265241650495e-06, + "loss": 0.4678, + "step": 7943 + }, + { + "epoch": 0.66, + "learning_rate": 5.340867264466902e-06, + "loss": 0.471, + "step": 7944 + }, + { + "epoch": 0.66, + "learning_rate": 5.338469629430638e-06, + "loss": 0.4485, + "step": 7945 + }, + { + "epoch": 0.66, + "learning_rate": 5.336072336717773e-06, + "loss": 0.4902, + "step": 7946 + }, + { + "epoch": 0.66, + "learning_rate": 5.333675386504361e-06, + "loss": 0.47, + "step": 7947 + }, + { + "epoch": 0.66, + "learning_rate": 5.33127877896642e-06, + "loss": 0.4581, + "step": 7948 + }, + { + "epoch": 0.67, + "learning_rate": 5.328882514279942e-06, + "loss": 0.4655, + "step": 7949 + }, + { + "epoch": 0.67, + "learning_rate": 5.3264865926209076e-06, + "loss": 0.4873, + "step": 7950 + }, + { + "epoch": 0.67, + "learning_rate": 5.324091014165259e-06, + "loss": 0.4545, + "step": 7951 + }, + { + "epoch": 0.67, + "learning_rate": 5.3216957790889176e-06, + "loss": 0.4819, + "step": 7952 + }, + { + "epoch": 0.67, + "learning_rate": 5.319300887567777e-06, + "loss": 0.4598, + "step": 7953 + }, + { + "epoch": 0.67, + "learning_rate": 5.316906339777714e-06, + "loss": 0.4577, + "step": 7954 + }, + { + "epoch": 0.67, + "learning_rate": 5.31451213589457e-06, + "loss": 0.4706, + "step": 7955 + }, + { + "epoch": 0.67, + "learning_rate": 5.312118276094167e-06, + "loss": 0.4746, + "step": 7956 + }, + { + "epoch": 0.67, + "learning_rate": 5.3097247605522996e-06, + "loss": 0.4613, + "step": 7957 + }, + { + "epoch": 0.67, + "learning_rate": 5.307331589444737e-06, + "loss": 0.469, + "step": 7958 + }, + { + "epoch": 0.67, + "learning_rate": 5.304938762947221e-06, + "loss": 0.4634, + "step": 7959 + }, + { + "epoch": 0.67, + "learning_rate": 5.3025462812354744e-06, + "loss": 0.4984, + "step": 7960 + }, + { + "epoch": 0.67, + "learning_rate": 5.300154144485194e-06, + "loss": 0.4598, + "step": 7961 + }, + { + "epoch": 0.67, + "learning_rate": 5.297762352872044e-06, + "loss": 0.448, + "step": 7962 + }, + { + "epoch": 0.67, + "learning_rate": 5.2953709065716704e-06, + "loss": 0.4654, + "step": 7963 + }, + { + "epoch": 0.67, + "learning_rate": 5.292979805759689e-06, + "loss": 0.4789, + "step": 7964 + }, + { + "epoch": 0.67, + "learning_rate": 5.290589050611692e-06, + "loss": 0.4614, + "step": 7965 + }, + { + "epoch": 0.67, + "learning_rate": 5.288198641303248e-06, + "loss": 0.4794, + "step": 7966 + }, + { + "epoch": 0.67, + "learning_rate": 5.285808578009894e-06, + "loss": 0.454, + "step": 7967 + }, + { + "epoch": 0.67, + "learning_rate": 5.283418860907155e-06, + "loss": 0.4548, + "step": 7968 + }, + { + "epoch": 0.67, + "learning_rate": 5.281029490170515e-06, + "loss": 0.469, + "step": 7969 + }, + { + "epoch": 0.67, + "learning_rate": 5.2786404659754375e-06, + "loss": 0.4638, + "step": 7970 + }, + { + "epoch": 0.67, + "learning_rate": 5.276251788497373e-06, + "loss": 0.4919, + "step": 7971 + }, + { + "epoch": 0.67, + "learning_rate": 5.273863457911728e-06, + "loss": 0.4731, + "step": 7972 + }, + { + "epoch": 0.67, + "learning_rate": 5.271475474393889e-06, + "loss": 0.4618, + "step": 7973 + }, + { + "epoch": 0.67, + "learning_rate": 5.269087838119229e-06, + "loss": 0.4624, + "step": 7974 + }, + { + "epoch": 0.67, + "learning_rate": 5.266700549263079e-06, + "loss": 0.4752, + "step": 7975 + }, + { + "epoch": 0.67, + "learning_rate": 5.264313608000755e-06, + "loss": 0.4623, + "step": 7976 + }, + { + "epoch": 0.67, + "learning_rate": 5.261927014507542e-06, + "loss": 0.4629, + "step": 7977 + }, + { + "epoch": 0.67, + "learning_rate": 5.2595407689587006e-06, + "loss": 0.457, + "step": 7978 + }, + { + "epoch": 0.67, + "learning_rate": 5.2571548715294664e-06, + "loss": 0.4797, + "step": 7979 + }, + { + "epoch": 0.67, + "learning_rate": 5.254769322395053e-06, + "loss": 0.474, + "step": 7980 + }, + { + "epoch": 0.67, + "learning_rate": 5.2523841217306415e-06, + "loss": 0.456, + "step": 7981 + }, + { + "epoch": 0.67, + "learning_rate": 5.249999269711396e-06, + "loss": 0.454, + "step": 7982 + }, + { + "epoch": 0.67, + "learning_rate": 5.247614766512449e-06, + "loss": 0.4753, + "step": 7983 + }, + { + "epoch": 0.67, + "learning_rate": 5.245230612308906e-06, + "loss": 0.4781, + "step": 7984 + }, + { + "epoch": 0.67, + "learning_rate": 5.24284680727585e-06, + "loss": 0.4845, + "step": 7985 + }, + { + "epoch": 0.67, + "learning_rate": 5.240463351588339e-06, + "loss": 0.4856, + "step": 7986 + }, + { + "epoch": 0.67, + "learning_rate": 5.238080245421397e-06, + "loss": 0.4736, + "step": 7987 + }, + { + "epoch": 0.67, + "learning_rate": 5.235697488950041e-06, + "loss": 0.4765, + "step": 7988 + }, + { + "epoch": 0.67, + "learning_rate": 5.233315082349245e-06, + "loss": 0.4583, + "step": 7989 + }, + { + "epoch": 0.67, + "learning_rate": 5.2309330257939596e-06, + "loss": 0.467, + "step": 7990 + }, + { + "epoch": 0.67, + "learning_rate": 5.22855131945912e-06, + "loss": 0.4896, + "step": 7991 + }, + { + "epoch": 0.67, + "learning_rate": 5.226169963519625e-06, + "loss": 0.4487, + "step": 7992 + }, + { + "epoch": 0.67, + "learning_rate": 5.223788958150353e-06, + "loss": 0.4804, + "step": 7993 + }, + { + "epoch": 0.67, + "learning_rate": 5.221408303526151e-06, + "loss": 0.4854, + "step": 7994 + }, + { + "epoch": 0.67, + "learning_rate": 5.219027999821851e-06, + "loss": 0.4575, + "step": 7995 + }, + { + "epoch": 0.67, + "learning_rate": 5.2166480472122475e-06, + "loss": 0.4674, + "step": 7996 + }, + { + "epoch": 0.67, + "learning_rate": 5.214268445872117e-06, + "loss": 0.4684, + "step": 7997 + }, + { + "epoch": 0.67, + "learning_rate": 5.211889195976207e-06, + "loss": 0.4653, + "step": 7998 + }, + { + "epoch": 0.67, + "learning_rate": 5.209510297699239e-06, + "loss": 0.4578, + "step": 7999 + }, + { + "epoch": 0.67, + "learning_rate": 5.2071317512159055e-06, + "loss": 0.4672, + "step": 8000 + }, + { + "epoch": 0.67, + "learning_rate": 5.204753556700881e-06, + "loss": 0.4591, + "step": 8001 + }, + { + "epoch": 0.67, + "learning_rate": 5.202375714328814e-06, + "loss": 0.4749, + "step": 8002 + }, + { + "epoch": 0.67, + "learning_rate": 5.199998224274321e-06, + "loss": 0.483, + "step": 8003 + }, + { + "epoch": 0.67, + "learning_rate": 5.197621086711993e-06, + "loss": 0.4896, + "step": 8004 + }, + { + "epoch": 0.67, + "learning_rate": 5.195244301816398e-06, + "loss": 0.4701, + "step": 8005 + }, + { + "epoch": 0.67, + "learning_rate": 5.192867869762076e-06, + "loss": 0.4645, + "step": 8006 + }, + { + "epoch": 0.67, + "learning_rate": 5.1904917907235395e-06, + "loss": 0.4561, + "step": 8007 + }, + { + "epoch": 0.67, + "learning_rate": 5.188116064875286e-06, + "loss": 0.4791, + "step": 8008 + }, + { + "epoch": 0.67, + "learning_rate": 5.185740692391774e-06, + "loss": 0.4797, + "step": 8009 + }, + { + "epoch": 0.67, + "learning_rate": 5.183365673447442e-06, + "loss": 0.4743, + "step": 8010 + }, + { + "epoch": 0.67, + "learning_rate": 5.180991008216698e-06, + "loss": 0.4652, + "step": 8011 + }, + { + "epoch": 0.67, + "learning_rate": 5.178616696873935e-06, + "loss": 0.4932, + "step": 8012 + }, + { + "epoch": 0.67, + "learning_rate": 5.1762427395935065e-06, + "loss": 0.4888, + "step": 8013 + }, + { + "epoch": 0.67, + "learning_rate": 5.173869136549744e-06, + "loss": 0.48, + "step": 8014 + }, + { + "epoch": 0.67, + "learning_rate": 5.171495887916962e-06, + "loss": 0.465, + "step": 8015 + }, + { + "epoch": 0.67, + "learning_rate": 5.1691229938694396e-06, + "loss": 0.4495, + "step": 8016 + }, + { + "epoch": 0.67, + "learning_rate": 5.166750454581432e-06, + "loss": 0.4761, + "step": 8017 + }, + { + "epoch": 0.67, + "learning_rate": 5.164378270227167e-06, + "loss": 0.4633, + "step": 8018 + }, + { + "epoch": 0.67, + "learning_rate": 5.162006440980849e-06, + "loss": 0.4559, + "step": 8019 + }, + { + "epoch": 0.67, + "learning_rate": 5.159634967016653e-06, + "loss": 0.4589, + "step": 8020 + }, + { + "epoch": 0.67, + "learning_rate": 5.157263848508735e-06, + "loss": 0.4933, + "step": 8021 + }, + { + "epoch": 0.67, + "learning_rate": 5.154893085631213e-06, + "loss": 0.4685, + "step": 8022 + }, + { + "epoch": 0.67, + "learning_rate": 5.152522678558195e-06, + "loss": 0.4722, + "step": 8023 + }, + { + "epoch": 0.67, + "learning_rate": 5.150152627463749e-06, + "loss": 0.473, + "step": 8024 + }, + { + "epoch": 0.67, + "learning_rate": 5.1477829325219235e-06, + "loss": 0.4841, + "step": 8025 + }, + { + "epoch": 0.67, + "learning_rate": 5.1454135939067365e-06, + "loss": 0.4842, + "step": 8026 + }, + { + "epoch": 0.67, + "learning_rate": 5.143044611792183e-06, + "loss": 0.4715, + "step": 8027 + }, + { + "epoch": 0.67, + "learning_rate": 5.140675986352228e-06, + "loss": 0.4933, + "step": 8028 + }, + { + "epoch": 0.67, + "learning_rate": 5.13830771776082e-06, + "loss": 0.4563, + "step": 8029 + }, + { + "epoch": 0.67, + "learning_rate": 5.135939806191874e-06, + "loss": 0.4535, + "step": 8030 + }, + { + "epoch": 0.67, + "learning_rate": 5.133572251819272e-06, + "loss": 0.4683, + "step": 8031 + }, + { + "epoch": 0.67, + "learning_rate": 5.131205054816888e-06, + "loss": 0.4829, + "step": 8032 + }, + { + "epoch": 0.67, + "learning_rate": 5.128838215358553e-06, + "loss": 0.4593, + "step": 8033 + }, + { + "epoch": 0.67, + "learning_rate": 5.126471733618079e-06, + "loss": 0.4618, + "step": 8034 + }, + { + "epoch": 0.67, + "learning_rate": 5.124105609769246e-06, + "loss": 0.4798, + "step": 8035 + }, + { + "epoch": 0.67, + "learning_rate": 5.12173984398582e-06, + "loss": 0.4731, + "step": 8036 + }, + { + "epoch": 0.67, + "learning_rate": 5.119374436441531e-06, + "loss": 0.4838, + "step": 8037 + }, + { + "epoch": 0.67, + "learning_rate": 5.117009387310083e-06, + "loss": 0.4896, + "step": 8038 + }, + { + "epoch": 0.67, + "learning_rate": 5.114644696765157e-06, + "loss": 0.4656, + "step": 8039 + }, + { + "epoch": 0.67, + "learning_rate": 5.112280364980402e-06, + "loss": 0.4628, + "step": 8040 + }, + { + "epoch": 0.67, + "learning_rate": 5.109916392129446e-06, + "loss": 0.469, + "step": 8041 + }, + { + "epoch": 0.67, + "learning_rate": 5.1075527783858934e-06, + "loss": 0.4615, + "step": 8042 + }, + { + "epoch": 0.67, + "learning_rate": 5.105189523923312e-06, + "loss": 0.4725, + "step": 8043 + }, + { + "epoch": 0.67, + "learning_rate": 5.1028266289152565e-06, + "loss": 0.4601, + "step": 8044 + }, + { + "epoch": 0.67, + "learning_rate": 5.100464093535244e-06, + "loss": 0.4656, + "step": 8045 + }, + { + "epoch": 0.67, + "learning_rate": 5.098101917956771e-06, + "loss": 0.4931, + "step": 8046 + }, + { + "epoch": 0.67, + "learning_rate": 5.0957401023533036e-06, + "loss": 0.4619, + "step": 8047 + }, + { + "epoch": 0.67, + "learning_rate": 5.093378646898282e-06, + "loss": 0.4562, + "step": 8048 + }, + { + "epoch": 0.67, + "learning_rate": 5.091017551765127e-06, + "loss": 0.4753, + "step": 8049 + }, + { + "epoch": 0.67, + "learning_rate": 5.0886568171272265e-06, + "loss": 0.475, + "step": 8050 + }, + { + "epoch": 0.67, + "learning_rate": 5.08629644315794e-06, + "loss": 0.453, + "step": 8051 + }, + { + "epoch": 0.67, + "learning_rate": 5.0839364300306016e-06, + "loss": 0.4629, + "step": 8052 + }, + { + "epoch": 0.67, + "learning_rate": 5.081576777918529e-06, + "loss": 0.4749, + "step": 8053 + }, + { + "epoch": 0.67, + "learning_rate": 5.079217486994999e-06, + "loss": 0.4747, + "step": 8054 + }, + { + "epoch": 0.67, + "learning_rate": 5.0768585574332675e-06, + "loss": 0.4711, + "step": 8055 + }, + { + "epoch": 0.67, + "learning_rate": 5.074499989406569e-06, + "loss": 0.4655, + "step": 8056 + }, + { + "epoch": 0.67, + "learning_rate": 5.072141783088107e-06, + "loss": 0.4468, + "step": 8057 + }, + { + "epoch": 0.67, + "learning_rate": 5.069783938651054e-06, + "loss": 0.45, + "step": 8058 + }, + { + "epoch": 0.67, + "learning_rate": 5.067426456268563e-06, + "loss": 0.4939, + "step": 8059 + }, + { + "epoch": 0.67, + "learning_rate": 5.065069336113756e-06, + "loss": 0.4619, + "step": 8060 + }, + { + "epoch": 0.67, + "learning_rate": 5.062712578359728e-06, + "loss": 0.4636, + "step": 8061 + }, + { + "epoch": 0.67, + "learning_rate": 5.060356183179556e-06, + "loss": 0.4795, + "step": 8062 + }, + { + "epoch": 0.67, + "learning_rate": 5.058000150746276e-06, + "loss": 0.471, + "step": 8063 + }, + { + "epoch": 0.67, + "learning_rate": 5.055644481232914e-06, + "loss": 0.4677, + "step": 8064 + }, + { + "epoch": 0.67, + "learning_rate": 5.0532891748124565e-06, + "loss": 0.4624, + "step": 8065 + }, + { + "epoch": 0.67, + "learning_rate": 5.050934231657867e-06, + "loss": 0.4759, + "step": 8066 + }, + { + "epoch": 0.67, + "learning_rate": 5.048579651942083e-06, + "loss": 0.4778, + "step": 8067 + }, + { + "epoch": 0.68, + "learning_rate": 5.046225435838015e-06, + "loss": 0.4734, + "step": 8068 + }, + { + "epoch": 0.68, + "learning_rate": 5.043871583518542e-06, + "loss": 0.4746, + "step": 8069 + }, + { + "epoch": 0.68, + "learning_rate": 5.04151809515653e-06, + "loss": 0.4566, + "step": 8070 + }, + { + "epoch": 0.68, + "learning_rate": 5.039164970924805e-06, + "loss": 0.4637, + "step": 8071 + }, + { + "epoch": 0.68, + "learning_rate": 5.0368122109961716e-06, + "loss": 0.453, + "step": 8072 + }, + { + "epoch": 0.68, + "learning_rate": 5.034459815543401e-06, + "loss": 0.4528, + "step": 8073 + }, + { + "epoch": 0.68, + "learning_rate": 5.032107784739253e-06, + "loss": 0.4723, + "step": 8074 + }, + { + "epoch": 0.68, + "learning_rate": 5.029756118756446e-06, + "loss": 0.4791, + "step": 8075 + }, + { + "epoch": 0.68, + "learning_rate": 5.027404817767672e-06, + "loss": 0.4692, + "step": 8076 + }, + { + "epoch": 0.68, + "learning_rate": 5.025053881945612e-06, + "loss": 0.4452, + "step": 8077 + }, + { + "epoch": 0.68, + "learning_rate": 5.0227033114629e-06, + "loss": 0.4711, + "step": 8078 + }, + { + "epoch": 0.68, + "learning_rate": 5.020353106492156e-06, + "loss": 0.4609, + "step": 8079 + }, + { + "epoch": 0.68, + "learning_rate": 5.018003267205969e-06, + "loss": 0.4732, + "step": 8080 + }, + { + "epoch": 0.68, + "learning_rate": 5.015653793776898e-06, + "loss": 0.4574, + "step": 8081 + }, + { + "epoch": 0.68, + "learning_rate": 5.013304686377478e-06, + "loss": 0.4587, + "step": 8082 + }, + { + "epoch": 0.68, + "learning_rate": 5.010955945180225e-06, + "loss": 0.4708, + "step": 8083 + }, + { + "epoch": 0.68, + "learning_rate": 5.008607570357612e-06, + "loss": 0.4685, + "step": 8084 + }, + { + "epoch": 0.68, + "learning_rate": 5.006259562082102e-06, + "loss": 0.4661, + "step": 8085 + }, + { + "epoch": 0.68, + "learning_rate": 5.003911920526119e-06, + "loss": 0.4538, + "step": 8086 + }, + { + "epoch": 0.68, + "learning_rate": 5.0015646458620645e-06, + "loss": 0.4543, + "step": 8087 + }, + { + "epoch": 0.68, + "learning_rate": 4.999217738262313e-06, + "loss": 0.4777, + "step": 8088 + }, + { + "epoch": 0.68, + "learning_rate": 4.996871197899207e-06, + "loss": 0.4714, + "step": 8089 + }, + { + "epoch": 0.68, + "learning_rate": 4.994525024945075e-06, + "loss": 0.4666, + "step": 8090 + }, + { + "epoch": 0.68, + "learning_rate": 4.992179219572204e-06, + "loss": 0.4673, + "step": 8091 + }, + { + "epoch": 0.68, + "learning_rate": 4.989833781952864e-06, + "loss": 0.4602, + "step": 8092 + }, + { + "epoch": 0.68, + "learning_rate": 4.987488712259288e-06, + "loss": 0.4727, + "step": 8093 + }, + { + "epoch": 0.68, + "learning_rate": 4.985144010663695e-06, + "loss": 0.4598, + "step": 8094 + }, + { + "epoch": 0.68, + "learning_rate": 4.982799677338268e-06, + "loss": 0.4775, + "step": 8095 + }, + { + "epoch": 0.68, + "learning_rate": 4.980455712455161e-06, + "loss": 0.4617, + "step": 8096 + }, + { + "epoch": 0.68, + "learning_rate": 4.978112116186512e-06, + "loss": 0.4769, + "step": 8097 + }, + { + "epoch": 0.68, + "learning_rate": 4.975768888704422e-06, + "loss": 0.4757, + "step": 8098 + }, + { + "epoch": 0.68, + "learning_rate": 4.973426030180968e-06, + "loss": 0.4748, + "step": 8099 + }, + { + "epoch": 0.68, + "learning_rate": 4.971083540788199e-06, + "loss": 0.4697, + "step": 8100 + }, + { + "epoch": 0.68, + "learning_rate": 4.968741420698137e-06, + "loss": 0.4743, + "step": 8101 + }, + { + "epoch": 0.68, + "learning_rate": 4.966399670082779e-06, + "loss": 0.4653, + "step": 8102 + }, + { + "epoch": 0.68, + "learning_rate": 4.964058289114089e-06, + "loss": 0.4759, + "step": 8103 + }, + { + "epoch": 0.68, + "learning_rate": 4.961717277964012e-06, + "loss": 0.5013, + "step": 8104 + }, + { + "epoch": 0.68, + "learning_rate": 4.959376636804467e-06, + "loss": 0.4803, + "step": 8105 + }, + { + "epoch": 0.68, + "learning_rate": 4.9570363658073366e-06, + "loss": 0.4712, + "step": 8106 + }, + { + "epoch": 0.68, + "learning_rate": 4.954696465144479e-06, + "loss": 0.4678, + "step": 8107 + }, + { + "epoch": 0.68, + "learning_rate": 4.952356934987728e-06, + "loss": 0.4561, + "step": 8108 + }, + { + "epoch": 0.68, + "learning_rate": 4.95001777550889e-06, + "loss": 0.4624, + "step": 8109 + }, + { + "epoch": 0.68, + "learning_rate": 4.947678986879737e-06, + "loss": 0.4786, + "step": 8110 + }, + { + "epoch": 0.68, + "learning_rate": 4.945340569272029e-06, + "loss": 0.4465, + "step": 8111 + }, + { + "epoch": 0.68, + "learning_rate": 4.943002522857487e-06, + "loss": 0.477, + "step": 8112 + }, + { + "epoch": 0.68, + "learning_rate": 4.940664847807804e-06, + "loss": 0.4772, + "step": 8113 + }, + { + "epoch": 0.68, + "learning_rate": 4.9383275442946495e-06, + "loss": 0.4757, + "step": 8114 + }, + { + "epoch": 0.68, + "learning_rate": 4.935990612489671e-06, + "loss": 0.4488, + "step": 8115 + }, + { + "epoch": 0.68, + "learning_rate": 4.933654052564477e-06, + "loss": 0.4872, + "step": 8116 + }, + { + "epoch": 0.68, + "learning_rate": 4.931317864690655e-06, + "loss": 0.4675, + "step": 8117 + }, + { + "epoch": 0.68, + "learning_rate": 4.92898204903977e-06, + "loss": 0.4818, + "step": 8118 + }, + { + "epoch": 0.68, + "learning_rate": 4.92664660578335e-06, + "loss": 0.4752, + "step": 8119 + }, + { + "epoch": 0.68, + "learning_rate": 4.924311535092904e-06, + "loss": 0.4517, + "step": 8120 + }, + { + "epoch": 0.68, + "learning_rate": 4.9219768371399055e-06, + "loss": 0.4548, + "step": 8121 + }, + { + "epoch": 0.68, + "learning_rate": 4.919642512095808e-06, + "loss": 0.454, + "step": 8122 + }, + { + "epoch": 0.68, + "learning_rate": 4.917308560132029e-06, + "loss": 0.4802, + "step": 8123 + }, + { + "epoch": 0.68, + "learning_rate": 4.914974981419974e-06, + "loss": 0.4431, + "step": 8124 + }, + { + "epoch": 0.68, + "learning_rate": 4.9126417761310005e-06, + "loss": 0.4663, + "step": 8125 + }, + { + "epoch": 0.68, + "learning_rate": 4.9103089444364605e-06, + "loss": 0.4542, + "step": 8126 + }, + { + "epoch": 0.68, + "learning_rate": 4.9079764865076615e-06, + "loss": 0.4589, + "step": 8127 + }, + { + "epoch": 0.68, + "learning_rate": 4.90564440251589e-06, + "loss": 0.4767, + "step": 8128 + }, + { + "epoch": 0.68, + "learning_rate": 4.903312692632405e-06, + "loss": 0.463, + "step": 8129 + }, + { + "epoch": 0.68, + "learning_rate": 4.9009813570284326e-06, + "loss": 0.4729, + "step": 8130 + }, + { + "epoch": 0.68, + "learning_rate": 4.898650395875185e-06, + "loss": 0.4562, + "step": 8131 + }, + { + "epoch": 0.68, + "learning_rate": 4.896319809343834e-06, + "loss": 0.4701, + "step": 8132 + }, + { + "epoch": 0.68, + "learning_rate": 4.893989597605528e-06, + "loss": 0.4578, + "step": 8133 + }, + { + "epoch": 0.68, + "learning_rate": 4.8916597608313855e-06, + "loss": 0.4918, + "step": 8134 + }, + { + "epoch": 0.68, + "learning_rate": 4.8893302991925075e-06, + "loss": 0.4608, + "step": 8135 + }, + { + "epoch": 0.68, + "learning_rate": 4.887001212859954e-06, + "loss": 0.4662, + "step": 8136 + }, + { + "epoch": 0.68, + "learning_rate": 4.884672502004762e-06, + "loss": 0.4747, + "step": 8137 + }, + { + "epoch": 0.68, + "learning_rate": 4.8823441667979475e-06, + "loss": 0.4636, + "step": 8138 + }, + { + "epoch": 0.68, + "learning_rate": 4.880016207410493e-06, + "loss": 0.4709, + "step": 8139 + }, + { + "epoch": 0.68, + "learning_rate": 4.877688624013353e-06, + "loss": 0.4848, + "step": 8140 + }, + { + "epoch": 0.68, + "learning_rate": 4.875361416777453e-06, + "loss": 0.4728, + "step": 8141 + }, + { + "epoch": 0.68, + "learning_rate": 4.873034585873697e-06, + "loss": 0.494, + "step": 8142 + }, + { + "epoch": 0.68, + "learning_rate": 4.870708131472957e-06, + "loss": 0.4538, + "step": 8143 + }, + { + "epoch": 0.68, + "learning_rate": 4.868382053746072e-06, + "loss": 0.4667, + "step": 8144 + }, + { + "epoch": 0.68, + "learning_rate": 4.866056352863866e-06, + "loss": 0.4854, + "step": 8145 + }, + { + "epoch": 0.68, + "learning_rate": 4.8637310289971314e-06, + "loss": 0.4811, + "step": 8146 + }, + { + "epoch": 0.68, + "learning_rate": 4.861406082316626e-06, + "loss": 0.471, + "step": 8147 + }, + { + "epoch": 0.68, + "learning_rate": 4.8590815129930865e-06, + "loss": 0.4748, + "step": 8148 + }, + { + "epoch": 0.68, + "learning_rate": 4.8567573211972175e-06, + "loss": 0.4685, + "step": 8149 + }, + { + "epoch": 0.68, + "learning_rate": 4.854433507099698e-06, + "loss": 0.4846, + "step": 8150 + }, + { + "epoch": 0.68, + "learning_rate": 4.852110070871175e-06, + "loss": 0.4754, + "step": 8151 + }, + { + "epoch": 0.68, + "learning_rate": 4.849787012682282e-06, + "loss": 0.464, + "step": 8152 + }, + { + "epoch": 0.68, + "learning_rate": 4.8474643327036095e-06, + "loss": 0.4705, + "step": 8153 + }, + { + "epoch": 0.68, + "learning_rate": 4.845142031105724e-06, + "loss": 0.4814, + "step": 8154 + }, + { + "epoch": 0.68, + "learning_rate": 4.8428201080591645e-06, + "loss": 0.4669, + "step": 8155 + }, + { + "epoch": 0.68, + "learning_rate": 4.840498563734449e-06, + "loss": 0.4703, + "step": 8156 + }, + { + "epoch": 0.68, + "learning_rate": 4.838177398302056e-06, + "loss": 0.4661, + "step": 8157 + }, + { + "epoch": 0.68, + "learning_rate": 4.8358566119324494e-06, + "loss": 0.4684, + "step": 8158 + }, + { + "epoch": 0.68, + "learning_rate": 4.833536204796052e-06, + "loss": 0.4745, + "step": 8159 + }, + { + "epoch": 0.68, + "learning_rate": 4.831216177063268e-06, + "loss": 0.4634, + "step": 8160 + }, + { + "epoch": 0.68, + "learning_rate": 4.82889652890447e-06, + "loss": 0.4606, + "step": 8161 + }, + { + "epoch": 0.68, + "learning_rate": 4.8265772604900015e-06, + "loss": 0.4659, + "step": 8162 + }, + { + "epoch": 0.68, + "learning_rate": 4.824258371990181e-06, + "loss": 0.4668, + "step": 8163 + }, + { + "epoch": 0.68, + "learning_rate": 4.821939863575295e-06, + "loss": 0.4562, + "step": 8164 + }, + { + "epoch": 0.68, + "learning_rate": 4.819621735415613e-06, + "loss": 0.4466, + "step": 8165 + }, + { + "epoch": 0.68, + "learning_rate": 4.817303987681359e-06, + "loss": 0.4877, + "step": 8166 + }, + { + "epoch": 0.68, + "learning_rate": 4.814986620542747e-06, + "loss": 0.4766, + "step": 8167 + }, + { + "epoch": 0.68, + "learning_rate": 4.8126696341699515e-06, + "loss": 0.4601, + "step": 8168 + }, + { + "epoch": 0.68, + "learning_rate": 4.810353028733123e-06, + "loss": 0.4765, + "step": 8169 + }, + { + "epoch": 0.68, + "learning_rate": 4.808036804402383e-06, + "loss": 0.4913, + "step": 8170 + }, + { + "epoch": 0.68, + "learning_rate": 4.80572096134782e-06, + "loss": 0.4553, + "step": 8171 + }, + { + "epoch": 0.68, + "learning_rate": 4.803405499739511e-06, + "loss": 0.4824, + "step": 8172 + }, + { + "epoch": 0.68, + "learning_rate": 4.801090419747486e-06, + "loss": 0.466, + "step": 8173 + }, + { + "epoch": 0.68, + "learning_rate": 4.798775721541757e-06, + "loss": 0.4502, + "step": 8174 + }, + { + "epoch": 0.68, + "learning_rate": 4.796461405292302e-06, + "loss": 0.453, + "step": 8175 + }, + { + "epoch": 0.68, + "learning_rate": 4.794147471169082e-06, + "loss": 0.4768, + "step": 8176 + }, + { + "epoch": 0.68, + "learning_rate": 4.7918339193420195e-06, + "loss": 0.4754, + "step": 8177 + }, + { + "epoch": 0.68, + "learning_rate": 4.789520749981007e-06, + "loss": 0.4688, + "step": 8178 + }, + { + "epoch": 0.68, + "learning_rate": 4.787207963255922e-06, + "loss": 0.4925, + "step": 8179 + }, + { + "epoch": 0.68, + "learning_rate": 4.7848955593366035e-06, + "loss": 0.4751, + "step": 8180 + }, + { + "epoch": 0.68, + "learning_rate": 4.782583538392863e-06, + "loss": 0.4647, + "step": 8181 + }, + { + "epoch": 0.68, + "learning_rate": 4.7802719005944875e-06, + "loss": 0.4637, + "step": 8182 + }, + { + "epoch": 0.68, + "learning_rate": 4.777960646111233e-06, + "loss": 0.4859, + "step": 8183 + }, + { + "epoch": 0.68, + "learning_rate": 4.775649775112828e-06, + "loss": 0.4761, + "step": 8184 + }, + { + "epoch": 0.68, + "learning_rate": 4.77333928776897e-06, + "loss": 0.4867, + "step": 8185 + }, + { + "epoch": 0.68, + "learning_rate": 4.771029184249339e-06, + "loss": 0.4683, + "step": 8186 + }, + { + "epoch": 0.68, + "learning_rate": 4.768719464723572e-06, + "loss": 0.4825, + "step": 8187 + }, + { + "epoch": 0.69, + "learning_rate": 4.766410129361294e-06, + "loss": 0.4661, + "step": 8188 + }, + { + "epoch": 0.69, + "learning_rate": 4.7641011783320866e-06, + "loss": 0.4592, + "step": 8189 + }, + { + "epoch": 0.69, + "learning_rate": 4.7617926118055125e-06, + "loss": 0.4794, + "step": 8190 + }, + { + "epoch": 0.69, + "learning_rate": 4.7594844299511e-06, + "loss": 0.4742, + "step": 8191 + }, + { + "epoch": 0.69, + "learning_rate": 4.757176632938351e-06, + "loss": 0.4719, + "step": 8192 + }, + { + "epoch": 0.69, + "learning_rate": 4.754869220936748e-06, + "loss": 0.4626, + "step": 8193 + }, + { + "epoch": 0.69, + "learning_rate": 4.752562194115732e-06, + "loss": 0.4645, + "step": 8194 + }, + { + "epoch": 0.69, + "learning_rate": 4.750255552644722e-06, + "loss": 0.4626, + "step": 8195 + }, + { + "epoch": 0.69, + "learning_rate": 4.7479492966931076e-06, + "loss": 0.4671, + "step": 8196 + }, + { + "epoch": 0.69, + "learning_rate": 4.745643426430254e-06, + "loss": 0.4699, + "step": 8197 + }, + { + "epoch": 0.69, + "learning_rate": 4.743337942025489e-06, + "loss": 0.4682, + "step": 8198 + }, + { + "epoch": 0.69, + "learning_rate": 4.741032843648126e-06, + "loss": 0.4568, + "step": 8199 + }, + { + "epoch": 0.69, + "learning_rate": 4.738728131467436e-06, + "loss": 0.4775, + "step": 8200 + }, + { + "epoch": 0.69, + "learning_rate": 4.73642380565267e-06, + "loss": 0.4795, + "step": 8201 + }, + { + "epoch": 0.69, + "learning_rate": 4.734119866373046e-06, + "loss": 0.4591, + "step": 8202 + }, + { + "epoch": 0.69, + "learning_rate": 4.731816313797757e-06, + "loss": 0.4689, + "step": 8203 + }, + { + "epoch": 0.69, + "learning_rate": 4.7295131480959655e-06, + "loss": 0.4534, + "step": 8204 + }, + { + "epoch": 0.69, + "learning_rate": 4.727210369436803e-06, + "loss": 0.4792, + "step": 8205 + }, + { + "epoch": 0.69, + "learning_rate": 4.724907977989384e-06, + "loss": 0.4638, + "step": 8206 + }, + { + "epoch": 0.69, + "learning_rate": 4.7226059739227796e-06, + "loss": 0.4603, + "step": 8207 + }, + { + "epoch": 0.69, + "learning_rate": 4.720304357406044e-06, + "loss": 0.4847, + "step": 8208 + }, + { + "epoch": 0.69, + "learning_rate": 4.7180031286081975e-06, + "loss": 0.464, + "step": 8209 + }, + { + "epoch": 0.69, + "learning_rate": 4.715702287698232e-06, + "loss": 0.4724, + "step": 8210 + }, + { + "epoch": 0.69, + "learning_rate": 4.71340183484511e-06, + "loss": 0.4716, + "step": 8211 + }, + { + "epoch": 0.69, + "learning_rate": 4.711101770217766e-06, + "loss": 0.471, + "step": 8212 + }, + { + "epoch": 0.69, + "learning_rate": 4.708802093985113e-06, + "loss": 0.473, + "step": 8213 + }, + { + "epoch": 0.69, + "learning_rate": 4.706502806316028e-06, + "loss": 0.4778, + "step": 8214 + }, + { + "epoch": 0.69, + "learning_rate": 4.704203907379358e-06, + "loss": 0.4548, + "step": 8215 + }, + { + "epoch": 0.69, + "learning_rate": 4.7019053973439265e-06, + "loss": 0.484, + "step": 8216 + }, + { + "epoch": 0.69, + "learning_rate": 4.6996072763785225e-06, + "loss": 0.473, + "step": 8217 + }, + { + "epoch": 0.69, + "learning_rate": 4.697309544651918e-06, + "loss": 0.4642, + "step": 8218 + }, + { + "epoch": 0.69, + "learning_rate": 4.6950122023328415e-06, + "loss": 0.4716, + "step": 8219 + }, + { + "epoch": 0.69, + "learning_rate": 4.692715249590007e-06, + "loss": 0.4708, + "step": 8220 + }, + { + "epoch": 0.69, + "learning_rate": 4.69041868659209e-06, + "loss": 0.4752, + "step": 8221 + }, + { + "epoch": 0.69, + "learning_rate": 4.68812251350774e-06, + "loss": 0.4551, + "step": 8222 + }, + { + "epoch": 0.69, + "learning_rate": 4.685826730505581e-06, + "loss": 0.4794, + "step": 8223 + }, + { + "epoch": 0.69, + "learning_rate": 4.683531337754201e-06, + "loss": 0.4568, + "step": 8224 + }, + { + "epoch": 0.69, + "learning_rate": 4.6812363354221675e-06, + "loss": 0.4637, + "step": 8225 + }, + { + "epoch": 0.69, + "learning_rate": 4.678941723678012e-06, + "loss": 0.4712, + "step": 8226 + }, + { + "epoch": 0.69, + "learning_rate": 4.676647502690248e-06, + "loss": 0.4848, + "step": 8227 + }, + { + "epoch": 0.69, + "learning_rate": 4.674353672627345e-06, + "loss": 0.4672, + "step": 8228 + }, + { + "epoch": 0.69, + "learning_rate": 4.672060233657762e-06, + "loss": 0.4781, + "step": 8229 + }, + { + "epoch": 0.69, + "learning_rate": 4.669767185949915e-06, + "loss": 0.4555, + "step": 8230 + }, + { + "epoch": 0.69, + "learning_rate": 4.667474529672196e-06, + "loss": 0.4874, + "step": 8231 + }, + { + "epoch": 0.69, + "learning_rate": 4.665182264992966e-06, + "loss": 0.4607, + "step": 8232 + }, + { + "epoch": 0.69, + "learning_rate": 4.66289039208056e-06, + "loss": 0.4571, + "step": 8233 + }, + { + "epoch": 0.69, + "learning_rate": 4.660598911103288e-06, + "loss": 0.4561, + "step": 8234 + }, + { + "epoch": 0.69, + "learning_rate": 4.658307822229423e-06, + "loss": 0.4632, + "step": 8235 + }, + { + "epoch": 0.69, + "learning_rate": 4.656017125627214e-06, + "loss": 0.4754, + "step": 8236 + }, + { + "epoch": 0.69, + "learning_rate": 4.653726821464876e-06, + "loss": 0.483, + "step": 8237 + }, + { + "epoch": 0.69, + "learning_rate": 4.651436909910607e-06, + "loss": 0.4668, + "step": 8238 + }, + { + "epoch": 0.69, + "learning_rate": 4.649147391132562e-06, + "loss": 0.4958, + "step": 8239 + }, + { + "epoch": 0.69, + "learning_rate": 4.646858265298881e-06, + "loss": 0.4723, + "step": 8240 + }, + { + "epoch": 0.69, + "learning_rate": 4.644569532577662e-06, + "loss": 0.4746, + "step": 8241 + }, + { + "epoch": 0.69, + "learning_rate": 4.6422811931369825e-06, + "loss": 0.4718, + "step": 8242 + }, + { + "epoch": 0.69, + "learning_rate": 4.639993247144889e-06, + "loss": 0.4667, + "step": 8243 + }, + { + "epoch": 0.69, + "learning_rate": 4.637705694769396e-06, + "loss": 0.4615, + "step": 8244 + }, + { + "epoch": 0.69, + "learning_rate": 4.635418536178492e-06, + "loss": 0.4802, + "step": 8245 + }, + { + "epoch": 0.69, + "learning_rate": 4.633131771540136e-06, + "loss": 0.471, + "step": 8246 + }, + { + "epoch": 0.69, + "learning_rate": 4.630845401022264e-06, + "loss": 0.4659, + "step": 8247 + }, + { + "epoch": 0.69, + "learning_rate": 4.628559424792769e-06, + "loss": 0.48, + "step": 8248 + }, + { + "epoch": 0.69, + "learning_rate": 4.626273843019532e-06, + "loss": 0.4433, + "step": 8249 + }, + { + "epoch": 0.69, + "learning_rate": 4.623988655870394e-06, + "loss": 0.4805, + "step": 8250 + }, + { + "epoch": 0.69, + "learning_rate": 4.621703863513168e-06, + "loss": 0.4693, + "step": 8251 + }, + { + "epoch": 0.69, + "learning_rate": 4.61941946611564e-06, + "loss": 0.4697, + "step": 8252 + }, + { + "epoch": 0.69, + "learning_rate": 4.617135463845563e-06, + "loss": 0.4931, + "step": 8253 + }, + { + "epoch": 0.69, + "learning_rate": 4.614851856870673e-06, + "loss": 0.4724, + "step": 8254 + }, + { + "epoch": 0.69, + "learning_rate": 4.612568645358664e-06, + "loss": 0.4771, + "step": 8255 + }, + { + "epoch": 0.69, + "learning_rate": 4.6102858294772055e-06, + "loss": 0.4438, + "step": 8256 + }, + { + "epoch": 0.69, + "learning_rate": 4.608003409393939e-06, + "loss": 0.49, + "step": 8257 + }, + { + "epoch": 0.69, + "learning_rate": 4.60572138527647e-06, + "loss": 0.4572, + "step": 8258 + }, + { + "epoch": 0.69, + "learning_rate": 4.60343975729239e-06, + "loss": 0.4596, + "step": 8259 + }, + { + "epoch": 0.69, + "learning_rate": 4.601158525609245e-06, + "loss": 0.4777, + "step": 8260 + }, + { + "epoch": 0.69, + "learning_rate": 4.598877690394565e-06, + "loss": 0.4661, + "step": 8261 + }, + { + "epoch": 0.69, + "learning_rate": 4.596597251815844e-06, + "loss": 0.458, + "step": 8262 + }, + { + "epoch": 0.69, + "learning_rate": 4.5943172100405455e-06, + "loss": 0.4684, + "step": 8263 + }, + { + "epoch": 0.69, + "learning_rate": 4.592037565236108e-06, + "loss": 0.4587, + "step": 8264 + }, + { + "epoch": 0.69, + "learning_rate": 4.589758317569938e-06, + "loss": 0.4612, + "step": 8265 + }, + { + "epoch": 0.69, + "learning_rate": 4.5874794672094135e-06, + "loss": 0.475, + "step": 8266 + }, + { + "epoch": 0.69, + "learning_rate": 4.585201014321882e-06, + "loss": 0.4665, + "step": 8267 + }, + { + "epoch": 0.69, + "learning_rate": 4.582922959074668e-06, + "loss": 0.4585, + "step": 8268 + }, + { + "epoch": 0.69, + "learning_rate": 4.5806453016350584e-06, + "loss": 0.4705, + "step": 8269 + }, + { + "epoch": 0.69, + "learning_rate": 4.5783680421703205e-06, + "loss": 0.4901, + "step": 8270 + }, + { + "epoch": 0.69, + "learning_rate": 4.576091180847684e-06, + "loss": 0.4554, + "step": 8271 + }, + { + "epoch": 0.69, + "learning_rate": 4.57381471783435e-06, + "loss": 0.4782, + "step": 8272 + }, + { + "epoch": 0.69, + "learning_rate": 4.571538653297491e-06, + "loss": 0.4807, + "step": 8273 + }, + { + "epoch": 0.69, + "learning_rate": 4.5692629874042585e-06, + "loss": 0.4598, + "step": 8274 + }, + { + "epoch": 0.69, + "learning_rate": 4.566987720321764e-06, + "loss": 0.4618, + "step": 8275 + }, + { + "epoch": 0.69, + "learning_rate": 4.564712852217094e-06, + "loss": 0.47, + "step": 8276 + }, + { + "epoch": 0.69, + "learning_rate": 4.562438383257304e-06, + "loss": 0.4723, + "step": 8277 + }, + { + "epoch": 0.69, + "learning_rate": 4.5601643136094195e-06, + "loss": 0.4548, + "step": 8278 + }, + { + "epoch": 0.69, + "learning_rate": 4.557890643440445e-06, + "loss": 0.4667, + "step": 8279 + }, + { + "epoch": 0.69, + "learning_rate": 4.5556173729173434e-06, + "loss": 0.4726, + "step": 8280 + }, + { + "epoch": 0.69, + "learning_rate": 4.55334450220706e-06, + "loss": 0.4704, + "step": 8281 + }, + { + "epoch": 0.69, + "learning_rate": 4.551072031476504e-06, + "loss": 0.4842, + "step": 8282 + }, + { + "epoch": 0.69, + "learning_rate": 4.548799960892552e-06, + "loss": 0.4802, + "step": 8283 + }, + { + "epoch": 0.69, + "learning_rate": 4.546528290622058e-06, + "loss": 0.4843, + "step": 8284 + }, + { + "epoch": 0.69, + "learning_rate": 4.544257020831843e-06, + "loss": 0.4921, + "step": 8285 + }, + { + "epoch": 0.69, + "learning_rate": 4.541986151688702e-06, + "loss": 0.4769, + "step": 8286 + }, + { + "epoch": 0.69, + "learning_rate": 4.539715683359391e-06, + "loss": 0.45, + "step": 8287 + }, + { + "epoch": 0.69, + "learning_rate": 4.537445616010655e-06, + "loss": 0.4646, + "step": 8288 + }, + { + "epoch": 0.69, + "learning_rate": 4.535175949809188e-06, + "loss": 0.4756, + "step": 8289 + }, + { + "epoch": 0.69, + "learning_rate": 4.532906684921672e-06, + "loss": 0.4601, + "step": 8290 + }, + { + "epoch": 0.69, + "learning_rate": 4.53063782151475e-06, + "loss": 0.486, + "step": 8291 + }, + { + "epoch": 0.69, + "learning_rate": 4.5283693597550384e-06, + "loss": 0.4705, + "step": 8292 + }, + { + "epoch": 0.69, + "learning_rate": 4.526101299809122e-06, + "loss": 0.4619, + "step": 8293 + }, + { + "epoch": 0.69, + "learning_rate": 4.523833641843554e-06, + "loss": 0.4683, + "step": 8294 + }, + { + "epoch": 0.69, + "learning_rate": 4.521566386024871e-06, + "loss": 0.4627, + "step": 8295 + }, + { + "epoch": 0.69, + "learning_rate": 4.519299532519566e-06, + "loss": 0.483, + "step": 8296 + }, + { + "epoch": 0.69, + "learning_rate": 4.517033081494109e-06, + "loss": 0.4766, + "step": 8297 + }, + { + "epoch": 0.69, + "learning_rate": 4.514767033114935e-06, + "loss": 0.4708, + "step": 8298 + }, + { + "epoch": 0.69, + "learning_rate": 4.512501387548453e-06, + "loss": 0.4741, + "step": 8299 + }, + { + "epoch": 0.69, + "learning_rate": 4.510236144961047e-06, + "loss": 0.4742, + "step": 8300 + }, + { + "epoch": 0.69, + "learning_rate": 4.507971305519062e-06, + "loss": 0.4632, + "step": 8301 + }, + { + "epoch": 0.69, + "learning_rate": 4.505706869388825e-06, + "loss": 0.468, + "step": 8302 + }, + { + "epoch": 0.69, + "learning_rate": 4.503442836736624e-06, + "loss": 0.4569, + "step": 8303 + }, + { + "epoch": 0.69, + "learning_rate": 4.5011792077287175e-06, + "loss": 0.4734, + "step": 8304 + }, + { + "epoch": 0.69, + "learning_rate": 4.498915982531339e-06, + "loss": 0.4751, + "step": 8305 + }, + { + "epoch": 0.69, + "learning_rate": 4.49665316131069e-06, + "loss": 0.4773, + "step": 8306 + }, + { + "epoch": 0.7, + "learning_rate": 4.494390744232943e-06, + "loss": 0.4506, + "step": 8307 + }, + { + "epoch": 0.7, + "learning_rate": 4.492128731464237e-06, + "loss": 0.4594, + "step": 8308 + }, + { + "epoch": 0.7, + "learning_rate": 4.489867123170692e-06, + "loss": 0.4719, + "step": 8309 + }, + { + "epoch": 0.7, + "learning_rate": 4.487605919518382e-06, + "loss": 0.4808, + "step": 8310 + }, + { + "epoch": 0.7, + "learning_rate": 4.485345120673369e-06, + "loss": 0.4713, + "step": 8311 + }, + { + "epoch": 0.7, + "learning_rate": 4.4830847268016745e-06, + "loss": 0.4824, + "step": 8312 + }, + { + "epoch": 0.7, + "learning_rate": 4.480824738069291e-06, + "loss": 0.4813, + "step": 8313 + }, + { + "epoch": 0.7, + "learning_rate": 4.478565154642178e-06, + "loss": 0.477, + "step": 8314 + }, + { + "epoch": 0.7, + "learning_rate": 4.476305976686279e-06, + "loss": 0.4704, + "step": 8315 + }, + { + "epoch": 0.7, + "learning_rate": 4.474047204367494e-06, + "loss": 0.4748, + "step": 8316 + }, + { + "epoch": 0.7, + "learning_rate": 4.4717888378516986e-06, + "loss": 0.454, + "step": 8317 + }, + { + "epoch": 0.7, + "learning_rate": 4.469530877304737e-06, + "loss": 0.4577, + "step": 8318 + }, + { + "epoch": 0.7, + "learning_rate": 4.467273322892421e-06, + "loss": 0.4852, + "step": 8319 + }, + { + "epoch": 0.7, + "learning_rate": 4.465016174780544e-06, + "loss": 0.4551, + "step": 8320 + }, + { + "epoch": 0.7, + "learning_rate": 4.462759433134855e-06, + "loss": 0.4726, + "step": 8321 + }, + { + "epoch": 0.7, + "learning_rate": 4.4605030981210824e-06, + "loss": 0.5028, + "step": 8322 + }, + { + "epoch": 0.7, + "learning_rate": 4.4582471699049245e-06, + "loss": 0.4718, + "step": 8323 + }, + { + "epoch": 0.7, + "learning_rate": 4.455991648652044e-06, + "loss": 0.479, + "step": 8324 + }, + { + "epoch": 0.7, + "learning_rate": 4.453736534528077e-06, + "loss": 0.4514, + "step": 8325 + }, + { + "epoch": 0.7, + "learning_rate": 4.45148182769863e-06, + "loss": 0.467, + "step": 8326 + }, + { + "epoch": 0.7, + "learning_rate": 4.449227528329281e-06, + "loss": 0.489, + "step": 8327 + }, + { + "epoch": 0.7, + "learning_rate": 4.446973636585571e-06, + "loss": 0.4569, + "step": 8328 + }, + { + "epoch": 0.7, + "learning_rate": 4.444720152633023e-06, + "loss": 0.4732, + "step": 8329 + }, + { + "epoch": 0.7, + "learning_rate": 4.442467076637121e-06, + "loss": 0.4608, + "step": 8330 + }, + { + "epoch": 0.7, + "learning_rate": 4.440214408763318e-06, + "loss": 0.4619, + "step": 8331 + }, + { + "epoch": 0.7, + "learning_rate": 4.437962149177047e-06, + "loss": 0.469, + "step": 8332 + }, + { + "epoch": 0.7, + "learning_rate": 4.435710298043703e-06, + "loss": 0.4816, + "step": 8333 + }, + { + "epoch": 0.7, + "learning_rate": 4.43345885552865e-06, + "loss": 0.4489, + "step": 8334 + }, + { + "epoch": 0.7, + "learning_rate": 4.431207821797222e-06, + "loss": 0.4529, + "step": 8335 + }, + { + "epoch": 0.7, + "learning_rate": 4.428957197014732e-06, + "loss": 0.4827, + "step": 8336 + }, + { + "epoch": 0.7, + "learning_rate": 4.426706981346456e-06, + "loss": 0.4554, + "step": 8337 + }, + { + "epoch": 0.7, + "learning_rate": 4.424457174957637e-06, + "loss": 0.4698, + "step": 8338 + }, + { + "epoch": 0.7, + "learning_rate": 4.422207778013493e-06, + "loss": 0.4708, + "step": 8339 + }, + { + "epoch": 0.7, + "learning_rate": 4.419958790679205e-06, + "loss": 0.4747, + "step": 8340 + }, + { + "epoch": 0.7, + "learning_rate": 4.4177102131199405e-06, + "loss": 0.4694, + "step": 8341 + }, + { + "epoch": 0.7, + "learning_rate": 4.415462045500813e-06, + "loss": 0.4597, + "step": 8342 + }, + { + "epoch": 0.7, + "learning_rate": 4.41321428798693e-06, + "loss": 0.4661, + "step": 8343 + }, + { + "epoch": 0.7, + "learning_rate": 4.410966940743353e-06, + "loss": 0.4799, + "step": 8344 + }, + { + "epoch": 0.7, + "learning_rate": 4.408720003935116e-06, + "loss": 0.4642, + "step": 8345 + }, + { + "epoch": 0.7, + "learning_rate": 4.406473477727228e-06, + "loss": 0.4708, + "step": 8346 + }, + { + "epoch": 0.7, + "learning_rate": 4.404227362284661e-06, + "loss": 0.4911, + "step": 8347 + }, + { + "epoch": 0.7, + "learning_rate": 4.401981657772359e-06, + "loss": 0.4707, + "step": 8348 + }, + { + "epoch": 0.7, + "learning_rate": 4.399736364355243e-06, + "loss": 0.4633, + "step": 8349 + }, + { + "epoch": 0.7, + "learning_rate": 4.397491482198195e-06, + "loss": 0.4862, + "step": 8350 + }, + { + "epoch": 0.7, + "learning_rate": 4.395247011466067e-06, + "loss": 0.461, + "step": 8351 + }, + { + "epoch": 0.7, + "learning_rate": 4.393002952323691e-06, + "loss": 0.4619, + "step": 8352 + }, + { + "epoch": 0.7, + "learning_rate": 4.3907593049358555e-06, + "loss": 0.4857, + "step": 8353 + }, + { + "epoch": 0.7, + "learning_rate": 4.388516069467327e-06, + "loss": 0.482, + "step": 8354 + }, + { + "epoch": 0.7, + "learning_rate": 4.386273246082834e-06, + "loss": 0.4656, + "step": 8355 + }, + { + "epoch": 0.7, + "learning_rate": 4.384030834947088e-06, + "loss": 0.4777, + "step": 8356 + }, + { + "epoch": 0.7, + "learning_rate": 4.381788836224759e-06, + "loss": 0.4786, + "step": 8357 + }, + { + "epoch": 0.7, + "learning_rate": 4.379547250080491e-06, + "loss": 0.4525, + "step": 8358 + }, + { + "epoch": 0.7, + "learning_rate": 4.377306076678895e-06, + "loss": 0.4711, + "step": 8359 + }, + { + "epoch": 0.7, + "learning_rate": 4.375065316184556e-06, + "loss": 0.4986, + "step": 8360 + }, + { + "epoch": 0.7, + "learning_rate": 4.372824968762019e-06, + "loss": 0.4564, + "step": 8361 + }, + { + "epoch": 0.7, + "learning_rate": 4.37058503457581e-06, + "loss": 0.4666, + "step": 8362 + }, + { + "epoch": 0.7, + "learning_rate": 4.368345513790427e-06, + "loss": 0.4745, + "step": 8363 + }, + { + "epoch": 0.7, + "learning_rate": 4.366106406570325e-06, + "loss": 0.5115, + "step": 8364 + }, + { + "epoch": 0.7, + "learning_rate": 4.363867713079935e-06, + "loss": 0.4606, + "step": 8365 + }, + { + "epoch": 0.7, + "learning_rate": 4.361629433483659e-06, + "loss": 0.4698, + "step": 8366 + }, + { + "epoch": 0.7, + "learning_rate": 4.3593915679458645e-06, + "loss": 0.4697, + "step": 8367 + }, + { + "epoch": 0.7, + "learning_rate": 4.3571541166308926e-06, + "loss": 0.4661, + "step": 8368 + }, + { + "epoch": 0.7, + "learning_rate": 4.354917079703049e-06, + "loss": 0.4622, + "step": 8369 + }, + { + "epoch": 0.7, + "learning_rate": 4.352680457326617e-06, + "loss": 0.4748, + "step": 8370 + }, + { + "epoch": 0.7, + "learning_rate": 4.350444249665845e-06, + "loss": 0.4748, + "step": 8371 + }, + { + "epoch": 0.7, + "learning_rate": 4.348208456884945e-06, + "loss": 0.4493, + "step": 8372 + }, + { + "epoch": 0.7, + "learning_rate": 4.345973079148111e-06, + "loss": 0.486, + "step": 8373 + }, + { + "epoch": 0.7, + "learning_rate": 4.343738116619499e-06, + "loss": 0.4661, + "step": 8374 + }, + { + "epoch": 0.7, + "learning_rate": 4.3415035694632326e-06, + "loss": 0.4423, + "step": 8375 + }, + { + "epoch": 0.7, + "learning_rate": 4.339269437843405e-06, + "loss": 0.4572, + "step": 8376 + }, + { + "epoch": 0.7, + "learning_rate": 4.337035721924089e-06, + "loss": 0.4763, + "step": 8377 + }, + { + "epoch": 0.7, + "learning_rate": 4.334802421869316e-06, + "loss": 0.4874, + "step": 8378 + }, + { + "epoch": 0.7, + "learning_rate": 4.332569537843089e-06, + "loss": 0.4534, + "step": 8379 + }, + { + "epoch": 0.7, + "learning_rate": 4.330337070009382e-06, + "loss": 0.4533, + "step": 8380 + }, + { + "epoch": 0.7, + "learning_rate": 4.328105018532136e-06, + "loss": 0.461, + "step": 8381 + }, + { + "epoch": 0.7, + "learning_rate": 4.32587338357527e-06, + "loss": 0.4669, + "step": 8382 + }, + { + "epoch": 0.7, + "learning_rate": 4.323642165302658e-06, + "loss": 0.4619, + "step": 8383 + }, + { + "epoch": 0.7, + "learning_rate": 4.321411363878159e-06, + "loss": 0.4544, + "step": 8384 + }, + { + "epoch": 0.7, + "learning_rate": 4.319180979465592e-06, + "loss": 0.4866, + "step": 8385 + }, + { + "epoch": 0.7, + "learning_rate": 4.316951012228744e-06, + "loss": 0.4647, + "step": 8386 + }, + { + "epoch": 0.7, + "learning_rate": 4.314721462331376e-06, + "loss": 0.4605, + "step": 8387 + }, + { + "epoch": 0.7, + "learning_rate": 4.312492329937218e-06, + "loss": 0.4656, + "step": 8388 + }, + { + "epoch": 0.7, + "learning_rate": 4.310263615209963e-06, + "loss": 0.4996, + "step": 8389 + }, + { + "epoch": 0.7, + "learning_rate": 4.308035318313286e-06, + "loss": 0.4711, + "step": 8390 + }, + { + "epoch": 0.7, + "learning_rate": 4.305807439410822e-06, + "loss": 0.4672, + "step": 8391 + }, + { + "epoch": 0.7, + "learning_rate": 4.30357997866617e-06, + "loss": 0.4885, + "step": 8392 + }, + { + "epoch": 0.7, + "learning_rate": 4.301352936242916e-06, + "loss": 0.4748, + "step": 8393 + }, + { + "epoch": 0.7, + "learning_rate": 4.2991263123046005e-06, + "loss": 0.4615, + "step": 8394 + }, + { + "epoch": 0.7, + "learning_rate": 4.296900107014735e-06, + "loss": 0.4693, + "step": 8395 + }, + { + "epoch": 0.7, + "learning_rate": 4.294674320536803e-06, + "loss": 0.4776, + "step": 8396 + }, + { + "epoch": 0.7, + "learning_rate": 4.292448953034261e-06, + "loss": 0.4694, + "step": 8397 + }, + { + "epoch": 0.7, + "learning_rate": 4.290224004670529e-06, + "loss": 0.4633, + "step": 8398 + }, + { + "epoch": 0.7, + "learning_rate": 4.287999475608997e-06, + "loss": 0.4731, + "step": 8399 + }, + { + "epoch": 0.7, + "learning_rate": 4.285775366013026e-06, + "loss": 0.4514, + "step": 8400 + }, + { + "epoch": 0.7, + "learning_rate": 4.283551676045945e-06, + "loss": 0.4551, + "step": 8401 + }, + { + "epoch": 0.7, + "learning_rate": 4.281328405871048e-06, + "loss": 0.4775, + "step": 8402 + }, + { + "epoch": 0.7, + "learning_rate": 4.279105555651608e-06, + "loss": 0.4647, + "step": 8403 + }, + { + "epoch": 0.7, + "learning_rate": 4.276883125550864e-06, + "loss": 0.47, + "step": 8404 + }, + { + "epoch": 0.7, + "learning_rate": 4.27466111573202e-06, + "loss": 0.4737, + "step": 8405 + }, + { + "epoch": 0.7, + "learning_rate": 4.272439526358249e-06, + "loss": 0.4676, + "step": 8406 + }, + { + "epoch": 0.7, + "learning_rate": 4.270218357592696e-06, + "loss": 0.459, + "step": 8407 + }, + { + "epoch": 0.7, + "learning_rate": 4.267997609598477e-06, + "loss": 0.4788, + "step": 8408 + }, + { + "epoch": 0.7, + "learning_rate": 4.26577728253867e-06, + "loss": 0.4554, + "step": 8409 + }, + { + "epoch": 0.7, + "learning_rate": 4.263557376576326e-06, + "loss": 0.4793, + "step": 8410 + }, + { + "epoch": 0.7, + "learning_rate": 4.261337891874473e-06, + "loss": 0.4776, + "step": 8411 + }, + { + "epoch": 0.7, + "learning_rate": 4.259118828596096e-06, + "loss": 0.4613, + "step": 8412 + }, + { + "epoch": 0.7, + "learning_rate": 4.25690018690415e-06, + "loss": 0.4708, + "step": 8413 + }, + { + "epoch": 0.7, + "learning_rate": 4.254681966961571e-06, + "loss": 0.4675, + "step": 8414 + }, + { + "epoch": 0.7, + "learning_rate": 4.2524641689312526e-06, + "loss": 0.4669, + "step": 8415 + }, + { + "epoch": 0.7, + "learning_rate": 4.250246792976058e-06, + "loss": 0.4417, + "step": 8416 + }, + { + "epoch": 0.7, + "learning_rate": 4.248029839258821e-06, + "loss": 0.4719, + "step": 8417 + }, + { + "epoch": 0.7, + "learning_rate": 4.245813307942354e-06, + "loss": 0.4622, + "step": 8418 + }, + { + "epoch": 0.7, + "learning_rate": 4.243597199189422e-06, + "loss": 0.4852, + "step": 8419 + }, + { + "epoch": 0.7, + "learning_rate": 4.241381513162769e-06, + "loss": 0.4809, + "step": 8420 + }, + { + "epoch": 0.7, + "learning_rate": 4.239166250025106e-06, + "loss": 0.4711, + "step": 8421 + }, + { + "epoch": 0.7, + "learning_rate": 4.236951409939109e-06, + "loss": 0.4572, + "step": 8422 + }, + { + "epoch": 0.7, + "learning_rate": 4.234736993067434e-06, + "loss": 0.4833, + "step": 8423 + }, + { + "epoch": 0.7, + "learning_rate": 4.2325229995726915e-06, + "loss": 0.4804, + "step": 8424 + }, + { + "epoch": 0.7, + "learning_rate": 4.230309429617474e-06, + "loss": 0.456, + "step": 8425 + }, + { + "epoch": 0.7, + "learning_rate": 4.228096283364335e-06, + "loss": 0.4626, + "step": 8426 + }, + { + "epoch": 0.71, + "learning_rate": 4.2258835609757965e-06, + "loss": 0.4777, + "step": 8427 + }, + { + "epoch": 0.71, + "learning_rate": 4.223671262614354e-06, + "loss": 0.4482, + "step": 8428 + }, + { + "epoch": 0.71, + "learning_rate": 4.221459388442467e-06, + "loss": 0.4631, + "step": 8429 + }, + { + "epoch": 0.71, + "learning_rate": 4.219247938622566e-06, + "loss": 0.451, + "step": 8430 + }, + { + "epoch": 0.71, + "learning_rate": 4.217036913317054e-06, + "loss": 0.4781, + "step": 8431 + }, + { + "epoch": 0.71, + "learning_rate": 4.214826312688299e-06, + "loss": 0.4649, + "step": 8432 + }, + { + "epoch": 0.71, + "learning_rate": 4.212616136898634e-06, + "loss": 0.4937, + "step": 8433 + }, + { + "epoch": 0.71, + "learning_rate": 4.210406386110371e-06, + "loss": 0.4511, + "step": 8434 + }, + { + "epoch": 0.71, + "learning_rate": 4.208197060485783e-06, + "loss": 0.4606, + "step": 8435 + }, + { + "epoch": 0.71, + "learning_rate": 4.205988160187113e-06, + "loss": 0.4546, + "step": 8436 + }, + { + "epoch": 0.71, + "learning_rate": 4.20377968537657e-06, + "loss": 0.4751, + "step": 8437 + }, + { + "epoch": 0.71, + "learning_rate": 4.201571636216343e-06, + "loss": 0.4677, + "step": 8438 + }, + { + "epoch": 0.71, + "learning_rate": 4.199364012868575e-06, + "loss": 0.4771, + "step": 8439 + }, + { + "epoch": 0.71, + "learning_rate": 4.197156815495389e-06, + "loss": 0.4534, + "step": 8440 + }, + { + "epoch": 0.71, + "learning_rate": 4.194950044258871e-06, + "loss": 0.4552, + "step": 8441 + }, + { + "epoch": 0.71, + "learning_rate": 4.192743699321075e-06, + "loss": 0.4798, + "step": 8442 + }, + { + "epoch": 0.71, + "learning_rate": 4.190537780844026e-06, + "loss": 0.4611, + "step": 8443 + }, + { + "epoch": 0.71, + "learning_rate": 4.188332288989721e-06, + "loss": 0.4666, + "step": 8444 + }, + { + "epoch": 0.71, + "learning_rate": 4.186127223920118e-06, + "loss": 0.4572, + "step": 8445 + }, + { + "epoch": 0.71, + "learning_rate": 4.183922585797152e-06, + "loss": 0.4646, + "step": 8446 + }, + { + "epoch": 0.71, + "learning_rate": 4.181718374782722e-06, + "loss": 0.4711, + "step": 8447 + }, + { + "epoch": 0.71, + "learning_rate": 4.179514591038692e-06, + "loss": 0.4616, + "step": 8448 + }, + { + "epoch": 0.71, + "learning_rate": 4.177311234726904e-06, + "loss": 0.473, + "step": 8449 + }, + { + "epoch": 0.71, + "learning_rate": 4.175108306009159e-06, + "loss": 0.4671, + "step": 8450 + }, + { + "epoch": 0.71, + "learning_rate": 4.172905805047229e-06, + "loss": 0.4892, + "step": 8451 + }, + { + "epoch": 0.71, + "learning_rate": 4.170703732002864e-06, + "loss": 0.4654, + "step": 8452 + }, + { + "epoch": 0.71, + "learning_rate": 4.168502087037771e-06, + "loss": 0.4498, + "step": 8453 + }, + { + "epoch": 0.71, + "learning_rate": 4.166300870313625e-06, + "loss": 0.493, + "step": 8454 + }, + { + "epoch": 0.71, + "learning_rate": 4.164100081992084e-06, + "loss": 0.4726, + "step": 8455 + }, + { + "epoch": 0.71, + "learning_rate": 4.161899722234759e-06, + "loss": 0.4567, + "step": 8456 + }, + { + "epoch": 0.71, + "learning_rate": 4.159699791203237e-06, + "loss": 0.4695, + "step": 8457 + }, + { + "epoch": 0.71, + "learning_rate": 4.157500289059065e-06, + "loss": 0.4722, + "step": 8458 + }, + { + "epoch": 0.71, + "learning_rate": 4.155301215963776e-06, + "loss": 0.4779, + "step": 8459 + }, + { + "epoch": 0.71, + "learning_rate": 4.153102572078855e-06, + "loss": 0.4611, + "step": 8460 + }, + { + "epoch": 0.71, + "learning_rate": 4.150904357565763e-06, + "loss": 0.4846, + "step": 8461 + }, + { + "epoch": 0.71, + "learning_rate": 4.148706572585927e-06, + "loss": 0.4619, + "step": 8462 + }, + { + "epoch": 0.71, + "learning_rate": 4.146509217300738e-06, + "loss": 0.4694, + "step": 8463 + }, + { + "epoch": 0.71, + "learning_rate": 4.14431229187157e-06, + "loss": 0.4676, + "step": 8464 + }, + { + "epoch": 0.71, + "learning_rate": 4.142115796459748e-06, + "loss": 0.4772, + "step": 8465 + }, + { + "epoch": 0.71, + "learning_rate": 4.13991973122658e-06, + "loss": 0.4591, + "step": 8466 + }, + { + "epoch": 0.71, + "learning_rate": 4.137724096333334e-06, + "loss": 0.4703, + "step": 8467 + }, + { + "epoch": 0.71, + "learning_rate": 4.135528891941246e-06, + "loss": 0.4667, + "step": 8468 + }, + { + "epoch": 0.71, + "learning_rate": 4.133334118211526e-06, + "loss": 0.4814, + "step": 8469 + }, + { + "epoch": 0.71, + "learning_rate": 4.131139775305346e-06, + "loss": 0.463, + "step": 8470 + }, + { + "epoch": 0.71, + "learning_rate": 4.128945863383846e-06, + "loss": 0.4672, + "step": 8471 + }, + { + "epoch": 0.71, + "learning_rate": 4.126752382608147e-06, + "loss": 0.4525, + "step": 8472 + }, + { + "epoch": 0.71, + "learning_rate": 4.124559333139324e-06, + "loss": 0.4729, + "step": 8473 + }, + { + "epoch": 0.71, + "learning_rate": 4.122366715138426e-06, + "loss": 0.4727, + "step": 8474 + }, + { + "epoch": 0.71, + "learning_rate": 4.1201745287664664e-06, + "loss": 0.4635, + "step": 8475 + }, + { + "epoch": 0.71, + "learning_rate": 4.117982774184436e-06, + "loss": 0.4769, + "step": 8476 + }, + { + "epoch": 0.71, + "learning_rate": 4.115791451553286e-06, + "loss": 0.4583, + "step": 8477 + }, + { + "epoch": 0.71, + "learning_rate": 4.1136005610339335e-06, + "loss": 0.476, + "step": 8478 + }, + { + "epoch": 0.71, + "learning_rate": 4.111410102787276e-06, + "loss": 0.4648, + "step": 8479 + }, + { + "epoch": 0.71, + "learning_rate": 4.109220076974168e-06, + "loss": 0.4614, + "step": 8480 + }, + { + "epoch": 0.71, + "learning_rate": 4.107030483755436e-06, + "loss": 0.482, + "step": 8481 + }, + { + "epoch": 0.71, + "learning_rate": 4.104841323291876e-06, + "loss": 0.4816, + "step": 8482 + }, + { + "epoch": 0.71, + "learning_rate": 4.102652595744248e-06, + "loss": 0.4644, + "step": 8483 + }, + { + "epoch": 0.71, + "learning_rate": 4.100464301273282e-06, + "loss": 0.4676, + "step": 8484 + }, + { + "epoch": 0.71, + "learning_rate": 4.098276440039681e-06, + "loss": 0.4865, + "step": 8485 + }, + { + "epoch": 0.71, + "learning_rate": 4.0960890122041095e-06, + "loss": 0.472, + "step": 8486 + }, + { + "epoch": 0.71, + "learning_rate": 4.093902017927208e-06, + "loss": 0.4773, + "step": 8487 + }, + { + "epoch": 0.71, + "learning_rate": 4.091715457369577e-06, + "loss": 0.4894, + "step": 8488 + }, + { + "epoch": 0.71, + "learning_rate": 4.089529330691789e-06, + "loss": 0.4876, + "step": 8489 + }, + { + "epoch": 0.71, + "learning_rate": 4.087343638054382e-06, + "loss": 0.4657, + "step": 8490 + }, + { + "epoch": 0.71, + "learning_rate": 4.085158379617866e-06, + "loss": 0.4594, + "step": 8491 + }, + { + "epoch": 0.71, + "learning_rate": 4.082973555542713e-06, + "loss": 0.4669, + "step": 8492 + }, + { + "epoch": 0.71, + "learning_rate": 4.080789165989376e-06, + "loss": 0.484, + "step": 8493 + }, + { + "epoch": 0.71, + "learning_rate": 4.0786052111182625e-06, + "loss": 0.4446, + "step": 8494 + }, + { + "epoch": 0.71, + "learning_rate": 4.0764216910897496e-06, + "loss": 0.4834, + "step": 8495 + }, + { + "epoch": 0.71, + "learning_rate": 4.074238606064194e-06, + "loss": 0.4814, + "step": 8496 + }, + { + "epoch": 0.71, + "learning_rate": 4.072055956201907e-06, + "loss": 0.4433, + "step": 8497 + }, + { + "epoch": 0.71, + "learning_rate": 4.069873741663171e-06, + "loss": 0.466, + "step": 8498 + }, + { + "epoch": 0.71, + "learning_rate": 4.067691962608245e-06, + "loss": 0.4694, + "step": 8499 + }, + { + "epoch": 0.71, + "learning_rate": 4.0655106191973485e-06, + "loss": 0.4718, + "step": 8500 + }, + { + "epoch": 0.71, + "learning_rate": 4.063329711590668e-06, + "loss": 0.4776, + "step": 8501 + }, + { + "epoch": 0.71, + "learning_rate": 4.061149239948361e-06, + "loss": 0.4952, + "step": 8502 + }, + { + "epoch": 0.71, + "learning_rate": 4.058969204430553e-06, + "loss": 0.4696, + "step": 8503 + }, + { + "epoch": 0.71, + "learning_rate": 4.056789605197335e-06, + "loss": 0.4936, + "step": 8504 + }, + { + "epoch": 0.71, + "learning_rate": 4.054610442408765e-06, + "loss": 0.4689, + "step": 8505 + }, + { + "epoch": 0.71, + "learning_rate": 4.052431716224876e-06, + "loss": 0.4777, + "step": 8506 + }, + { + "epoch": 0.71, + "learning_rate": 4.050253426805668e-06, + "loss": 0.4714, + "step": 8507 + }, + { + "epoch": 0.71, + "learning_rate": 4.048075574311101e-06, + "loss": 0.4638, + "step": 8508 + }, + { + "epoch": 0.71, + "learning_rate": 4.045898158901108e-06, + "loss": 0.4809, + "step": 8509 + }, + { + "epoch": 0.71, + "learning_rate": 4.043721180735589e-06, + "loss": 0.4672, + "step": 8510 + }, + { + "epoch": 0.71, + "learning_rate": 4.041544639974413e-06, + "loss": 0.4507, + "step": 8511 + }, + { + "epoch": 0.71, + "learning_rate": 4.03936853677741e-06, + "loss": 0.4801, + "step": 8512 + }, + { + "epoch": 0.71, + "learning_rate": 4.037192871304396e-06, + "loss": 0.4604, + "step": 8513 + }, + { + "epoch": 0.71, + "learning_rate": 4.035017643715135e-06, + "loss": 0.462, + "step": 8514 + }, + { + "epoch": 0.71, + "learning_rate": 4.032842854169368e-06, + "loss": 0.465, + "step": 8515 + }, + { + "epoch": 0.71, + "learning_rate": 4.030668502826799e-06, + "loss": 0.4692, + "step": 8516 + }, + { + "epoch": 0.71, + "learning_rate": 4.028494589847109e-06, + "loss": 0.4676, + "step": 8517 + }, + { + "epoch": 0.71, + "learning_rate": 4.026321115389942e-06, + "loss": 0.475, + "step": 8518 + }, + { + "epoch": 0.71, + "learning_rate": 4.0241480796149e-06, + "loss": 0.4485, + "step": 8519 + }, + { + "epoch": 0.71, + "learning_rate": 4.021975482681571e-06, + "loss": 0.4837, + "step": 8520 + }, + { + "epoch": 0.71, + "learning_rate": 4.0198033247494995e-06, + "loss": 0.4756, + "step": 8521 + }, + { + "epoch": 0.71, + "learning_rate": 4.017631605978198e-06, + "loss": 0.4693, + "step": 8522 + }, + { + "epoch": 0.71, + "learning_rate": 4.015460326527149e-06, + "loss": 0.4934, + "step": 8523 + }, + { + "epoch": 0.71, + "learning_rate": 4.013289486555801e-06, + "loss": 0.4677, + "step": 8524 + }, + { + "epoch": 0.71, + "learning_rate": 4.01111908622357e-06, + "loss": 0.4588, + "step": 8525 + }, + { + "epoch": 0.71, + "learning_rate": 4.008949125689846e-06, + "loss": 0.4807, + "step": 8526 + }, + { + "epoch": 0.71, + "learning_rate": 4.0067796051139775e-06, + "loss": 0.4802, + "step": 8527 + }, + { + "epoch": 0.71, + "learning_rate": 4.0046105246552895e-06, + "loss": 0.4561, + "step": 8528 + }, + { + "epoch": 0.71, + "learning_rate": 4.002441884473069e-06, + "loss": 0.4578, + "step": 8529 + }, + { + "epoch": 0.71, + "learning_rate": 4.000273684726569e-06, + "loss": 0.469, + "step": 8530 + }, + { + "epoch": 0.71, + "learning_rate": 3.998105925575017e-06, + "loss": 0.4794, + "step": 8531 + }, + { + "epoch": 0.71, + "learning_rate": 3.995938607177599e-06, + "loss": 0.4589, + "step": 8532 + }, + { + "epoch": 0.71, + "learning_rate": 3.993771729693476e-06, + "loss": 0.4691, + "step": 8533 + }, + { + "epoch": 0.71, + "learning_rate": 3.991605293281779e-06, + "loss": 0.4729, + "step": 8534 + }, + { + "epoch": 0.71, + "learning_rate": 3.989439298101597e-06, + "loss": 0.477, + "step": 8535 + }, + { + "epoch": 0.71, + "learning_rate": 3.9872737443119914e-06, + "loss": 0.4653, + "step": 8536 + }, + { + "epoch": 0.71, + "learning_rate": 3.985108632071995e-06, + "loss": 0.4654, + "step": 8537 + }, + { + "epoch": 0.71, + "learning_rate": 3.982943961540604e-06, + "loss": 0.4591, + "step": 8538 + }, + { + "epoch": 0.71, + "learning_rate": 3.980779732876777e-06, + "loss": 0.4844, + "step": 8539 + }, + { + "epoch": 0.71, + "learning_rate": 3.978615946239456e-06, + "loss": 0.4753, + "step": 8540 + }, + { + "epoch": 0.71, + "learning_rate": 3.9764526017875326e-06, + "loss": 0.4698, + "step": 8541 + }, + { + "epoch": 0.71, + "learning_rate": 3.974289699679879e-06, + "loss": 0.4496, + "step": 8542 + }, + { + "epoch": 0.71, + "learning_rate": 3.972127240075325e-06, + "loss": 0.4753, + "step": 8543 + }, + { + "epoch": 0.71, + "learning_rate": 3.969965223132675e-06, + "loss": 0.4723, + "step": 8544 + }, + { + "epoch": 0.71, + "learning_rate": 3.967803649010698e-06, + "loss": 0.4615, + "step": 8545 + }, + { + "epoch": 0.71, + "learning_rate": 3.965642517868129e-06, + "loss": 0.4637, + "step": 8546 + }, + { + "epoch": 0.72, + "learning_rate": 3.963481829863673e-06, + "loss": 0.4717, + "step": 8547 + }, + { + "epoch": 0.72, + "learning_rate": 3.9613215851560094e-06, + "loss": 0.4675, + "step": 8548 + }, + { + "epoch": 0.72, + "learning_rate": 3.95916178390377e-06, + "loss": 0.4737, + "step": 8549 + }, + { + "epoch": 0.72, + "learning_rate": 3.957002426265564e-06, + "loss": 0.4573, + "step": 8550 + }, + { + "epoch": 0.72, + "learning_rate": 3.954843512399965e-06, + "loss": 0.477, + "step": 8551 + }, + { + "epoch": 0.72, + "learning_rate": 3.952685042465515e-06, + "loss": 0.4955, + "step": 8552 + }, + { + "epoch": 0.72, + "learning_rate": 3.950527016620719e-06, + "loss": 0.4608, + "step": 8553 + }, + { + "epoch": 0.72, + "learning_rate": 3.948369435024061e-06, + "loss": 0.4601, + "step": 8554 + }, + { + "epoch": 0.72, + "learning_rate": 3.9462122978339815e-06, + "loss": 0.4654, + "step": 8555 + }, + { + "epoch": 0.72, + "learning_rate": 3.944055605208891e-06, + "loss": 0.4643, + "step": 8556 + }, + { + "epoch": 0.72, + "learning_rate": 3.941899357307164e-06, + "loss": 0.4667, + "step": 8557 + }, + { + "epoch": 0.72, + "learning_rate": 3.939743554287154e-06, + "loss": 0.4756, + "step": 8558 + }, + { + "epoch": 0.72, + "learning_rate": 3.937588196307172e-06, + "loss": 0.4816, + "step": 8559 + }, + { + "epoch": 0.72, + "learning_rate": 3.9354332835254935e-06, + "loss": 0.4623, + "step": 8560 + }, + { + "epoch": 0.72, + "learning_rate": 3.933278816100373e-06, + "loss": 0.468, + "step": 8561 + }, + { + "epoch": 0.72, + "learning_rate": 3.9311247941900245e-06, + "loss": 0.4859, + "step": 8562 + }, + { + "epoch": 0.72, + "learning_rate": 3.9289712179526275e-06, + "loss": 0.4537, + "step": 8563 + }, + { + "epoch": 0.72, + "learning_rate": 3.926818087546333e-06, + "loss": 0.4717, + "step": 8564 + }, + { + "epoch": 0.72, + "learning_rate": 3.924665403129259e-06, + "loss": 0.4674, + "step": 8565 + }, + { + "epoch": 0.72, + "learning_rate": 3.9225131648594835e-06, + "loss": 0.4457, + "step": 8566 + }, + { + "epoch": 0.72, + "learning_rate": 3.920361372895067e-06, + "loss": 0.4414, + "step": 8567 + }, + { + "epoch": 0.72, + "learning_rate": 3.918210027394021e-06, + "loss": 0.4717, + "step": 8568 + }, + { + "epoch": 0.72, + "learning_rate": 3.9160591285143375e-06, + "loss": 0.462, + "step": 8569 + }, + { + "epoch": 0.72, + "learning_rate": 3.9139086764139675e-06, + "loss": 0.4642, + "step": 8570 + }, + { + "epoch": 0.72, + "learning_rate": 3.911758671250829e-06, + "loss": 0.4636, + "step": 8571 + }, + { + "epoch": 0.72, + "learning_rate": 3.909609113182812e-06, + "loss": 0.462, + "step": 8572 + }, + { + "epoch": 0.72, + "learning_rate": 3.907460002367766e-06, + "loss": 0.4626, + "step": 8573 + }, + { + "epoch": 0.72, + "learning_rate": 3.90531133896352e-06, + "loss": 0.4717, + "step": 8574 + }, + { + "epoch": 0.72, + "learning_rate": 3.90316312312786e-06, + "loss": 0.4724, + "step": 8575 + }, + { + "epoch": 0.72, + "learning_rate": 3.901015355018541e-06, + "loss": 0.4667, + "step": 8576 + }, + { + "epoch": 0.72, + "learning_rate": 3.8988680347932836e-06, + "loss": 0.4813, + "step": 8577 + }, + { + "epoch": 0.72, + "learning_rate": 3.896721162609785e-06, + "loss": 0.4612, + "step": 8578 + }, + { + "epoch": 0.72, + "learning_rate": 3.894574738625699e-06, + "loss": 0.4741, + "step": 8579 + }, + { + "epoch": 0.72, + "learning_rate": 3.892428762998644e-06, + "loss": 0.4814, + "step": 8580 + }, + { + "epoch": 0.72, + "learning_rate": 3.890283235886223e-06, + "loss": 0.4944, + "step": 8581 + }, + { + "epoch": 0.72, + "learning_rate": 3.888138157445989e-06, + "loss": 0.433, + "step": 8582 + }, + { + "epoch": 0.72, + "learning_rate": 3.885993527835466e-06, + "loss": 0.4921, + "step": 8583 + }, + { + "epoch": 0.72, + "learning_rate": 3.883849347212151e-06, + "loss": 0.4568, + "step": 8584 + }, + { + "epoch": 0.72, + "learning_rate": 3.8817056157334985e-06, + "loss": 0.4738, + "step": 8585 + }, + { + "epoch": 0.72, + "learning_rate": 3.879562333556939e-06, + "loss": 0.4914, + "step": 8586 + }, + { + "epoch": 0.72, + "learning_rate": 3.877419500839861e-06, + "loss": 0.4677, + "step": 8587 + }, + { + "epoch": 0.72, + "learning_rate": 3.875277117739632e-06, + "loss": 0.4613, + "step": 8588 + }, + { + "epoch": 0.72, + "learning_rate": 3.873135184413573e-06, + "loss": 0.4628, + "step": 8589 + }, + { + "epoch": 0.72, + "learning_rate": 3.870993701018988e-06, + "loss": 0.4649, + "step": 8590 + }, + { + "epoch": 0.72, + "learning_rate": 3.868852667713131e-06, + "loss": 0.4456, + "step": 8591 + }, + { + "epoch": 0.72, + "learning_rate": 3.8667120846532335e-06, + "loss": 0.4777, + "step": 8592 + }, + { + "epoch": 0.72, + "learning_rate": 3.864571951996491e-06, + "loss": 0.476, + "step": 8593 + }, + { + "epoch": 0.72, + "learning_rate": 3.862432269900062e-06, + "loss": 0.4743, + "step": 8594 + }, + { + "epoch": 0.72, + "learning_rate": 3.860293038521082e-06, + "loss": 0.4484, + "step": 8595 + }, + { + "epoch": 0.72, + "learning_rate": 3.858154258016643e-06, + "loss": 0.4882, + "step": 8596 + }, + { + "epoch": 0.72, + "learning_rate": 3.856015928543811e-06, + "loss": 0.4718, + "step": 8597 + }, + { + "epoch": 0.72, + "learning_rate": 3.85387805025961e-06, + "loss": 0.4623, + "step": 8598 + }, + { + "epoch": 0.72, + "learning_rate": 3.8517406233210445e-06, + "loss": 0.4816, + "step": 8599 + }, + { + "epoch": 0.72, + "learning_rate": 3.849603647885076e-06, + "loss": 0.47, + "step": 8600 + }, + { + "epoch": 0.72, + "learning_rate": 3.84746712410863e-06, + "loss": 0.4653, + "step": 8601 + }, + { + "epoch": 0.72, + "learning_rate": 3.845331052148612e-06, + "loss": 0.4681, + "step": 8602 + }, + { + "epoch": 0.72, + "learning_rate": 3.843195432161883e-06, + "loss": 0.4579, + "step": 8603 + }, + { + "epoch": 0.72, + "learning_rate": 3.841060264305272e-06, + "loss": 0.4616, + "step": 8604 + }, + { + "epoch": 0.72, + "learning_rate": 3.838925548735579e-06, + "loss": 0.4761, + "step": 8605 + }, + { + "epoch": 0.72, + "learning_rate": 3.836791285609568e-06, + "loss": 0.4677, + "step": 8606 + }, + { + "epoch": 0.72, + "learning_rate": 3.834657475083967e-06, + "loss": 0.4562, + "step": 8607 + }, + { + "epoch": 0.72, + "learning_rate": 3.83252411731548e-06, + "loss": 0.492, + "step": 8608 + }, + { + "epoch": 0.72, + "learning_rate": 3.830391212460767e-06, + "loss": 0.4816, + "step": 8609 + }, + { + "epoch": 0.72, + "learning_rate": 3.828258760676464e-06, + "loss": 0.4645, + "step": 8610 + }, + { + "epoch": 0.72, + "learning_rate": 3.826126762119169e-06, + "loss": 0.4629, + "step": 8611 + }, + { + "epoch": 0.72, + "learning_rate": 3.823995216945445e-06, + "loss": 0.4651, + "step": 8612 + }, + { + "epoch": 0.72, + "learning_rate": 3.821864125311824e-06, + "loss": 0.4499, + "step": 8613 + }, + { + "epoch": 0.72, + "learning_rate": 3.819733487374801e-06, + "loss": 0.4697, + "step": 8614 + }, + { + "epoch": 0.72, + "learning_rate": 3.81760330329085e-06, + "loss": 0.4748, + "step": 8615 + }, + { + "epoch": 0.72, + "learning_rate": 3.815473573216397e-06, + "loss": 0.4666, + "step": 8616 + }, + { + "epoch": 0.72, + "learning_rate": 3.8133442973078415e-06, + "loss": 0.4688, + "step": 8617 + }, + { + "epoch": 0.72, + "learning_rate": 3.811215475721548e-06, + "loss": 0.4636, + "step": 8618 + }, + { + "epoch": 0.72, + "learning_rate": 3.809087108613846e-06, + "loss": 0.452, + "step": 8619 + }, + { + "epoch": 0.72, + "learning_rate": 3.8069591961410402e-06, + "loss": 0.458, + "step": 8620 + }, + { + "epoch": 0.72, + "learning_rate": 3.804831738459388e-06, + "loss": 0.4557, + "step": 8621 + }, + { + "epoch": 0.72, + "learning_rate": 3.80270473572513e-06, + "loss": 0.483, + "step": 8622 + }, + { + "epoch": 0.72, + "learning_rate": 3.800578188094459e-06, + "loss": 0.4682, + "step": 8623 + }, + { + "epoch": 0.72, + "learning_rate": 3.7984520957235403e-06, + "loss": 0.4645, + "step": 8624 + }, + { + "epoch": 0.72, + "learning_rate": 3.7963264587685067e-06, + "loss": 0.4688, + "step": 8625 + }, + { + "epoch": 0.72, + "learning_rate": 3.7942012773854532e-06, + "loss": 0.4634, + "step": 8626 + }, + { + "epoch": 0.72, + "learning_rate": 3.792076551730447e-06, + "loss": 0.4708, + "step": 8627 + }, + { + "epoch": 0.72, + "learning_rate": 3.789952281959515e-06, + "loss": 0.4622, + "step": 8628 + }, + { + "epoch": 0.72, + "learning_rate": 3.7878284682286615e-06, + "loss": 0.4641, + "step": 8629 + }, + { + "epoch": 0.72, + "learning_rate": 3.7857051106938425e-06, + "loss": 0.4655, + "step": 8630 + }, + { + "epoch": 0.72, + "learning_rate": 3.7835822095109966e-06, + "loss": 0.4844, + "step": 8631 + }, + { + "epoch": 0.72, + "learning_rate": 3.7814597648360176e-06, + "loss": 0.4661, + "step": 8632 + }, + { + "epoch": 0.72, + "learning_rate": 3.7793377768247685e-06, + "loss": 0.4646, + "step": 8633 + }, + { + "epoch": 0.72, + "learning_rate": 3.7772162456330796e-06, + "loss": 0.49, + "step": 8634 + }, + { + "epoch": 0.72, + "learning_rate": 3.775095171416744e-06, + "loss": 0.4759, + "step": 8635 + }, + { + "epoch": 0.72, + "learning_rate": 3.77297455433153e-06, + "loss": 0.4735, + "step": 8636 + }, + { + "epoch": 0.72, + "learning_rate": 3.7708543945331654e-06, + "loss": 0.4817, + "step": 8637 + }, + { + "epoch": 0.72, + "learning_rate": 3.768734692177345e-06, + "loss": 0.449, + "step": 8638 + }, + { + "epoch": 0.72, + "learning_rate": 3.766615447419727e-06, + "loss": 0.4656, + "step": 8639 + }, + { + "epoch": 0.72, + "learning_rate": 3.764496660415948e-06, + "loss": 0.4704, + "step": 8640 + }, + { + "epoch": 0.72, + "learning_rate": 3.762378331321599e-06, + "loss": 0.4846, + "step": 8641 + }, + { + "epoch": 0.72, + "learning_rate": 3.7602604602922365e-06, + "loss": 0.4714, + "step": 8642 + }, + { + "epoch": 0.72, + "learning_rate": 3.758143047483398e-06, + "loss": 0.4686, + "step": 8643 + }, + { + "epoch": 0.72, + "learning_rate": 3.756026093050571e-06, + "loss": 0.4748, + "step": 8644 + }, + { + "epoch": 0.72, + "learning_rate": 3.7539095971492177e-06, + "loss": 0.4507, + "step": 8645 + }, + { + "epoch": 0.72, + "learning_rate": 3.7517935599347634e-06, + "loss": 0.4642, + "step": 8646 + }, + { + "epoch": 0.72, + "learning_rate": 3.7496779815626026e-06, + "loss": 0.4805, + "step": 8647 + }, + { + "epoch": 0.72, + "learning_rate": 3.74756286218809e-06, + "loss": 0.4671, + "step": 8648 + }, + { + "epoch": 0.72, + "learning_rate": 3.745448201966558e-06, + "loss": 0.4739, + "step": 8649 + }, + { + "epoch": 0.72, + "learning_rate": 3.7433340010532926e-06, + "loss": 0.4768, + "step": 8650 + }, + { + "epoch": 0.72, + "learning_rate": 3.7412202596035586e-06, + "loss": 0.4509, + "step": 8651 + }, + { + "epoch": 0.72, + "learning_rate": 3.739106977772575e-06, + "loss": 0.4845, + "step": 8652 + }, + { + "epoch": 0.72, + "learning_rate": 3.7369941557155354e-06, + "loss": 0.4621, + "step": 8653 + }, + { + "epoch": 0.72, + "learning_rate": 3.7348817935875947e-06, + "loss": 0.4534, + "step": 8654 + }, + { + "epoch": 0.72, + "learning_rate": 3.7327698915438725e-06, + "loss": 0.4751, + "step": 8655 + }, + { + "epoch": 0.72, + "learning_rate": 3.730658449739466e-06, + "loss": 0.4679, + "step": 8656 + }, + { + "epoch": 0.72, + "learning_rate": 3.7285474683294274e-06, + "loss": 0.4685, + "step": 8657 + }, + { + "epoch": 0.72, + "learning_rate": 3.7264369474687767e-06, + "loss": 0.4646, + "step": 8658 + }, + { + "epoch": 0.72, + "learning_rate": 3.7243268873125038e-06, + "loss": 0.4867, + "step": 8659 + }, + { + "epoch": 0.72, + "learning_rate": 3.7222172880155585e-06, + "loss": 0.473, + "step": 8660 + }, + { + "epoch": 0.72, + "learning_rate": 3.720108149732866e-06, + "loss": 0.4919, + "step": 8661 + }, + { + "epoch": 0.72, + "learning_rate": 3.717999472619309e-06, + "loss": 0.4689, + "step": 8662 + }, + { + "epoch": 0.72, + "learning_rate": 3.7158912568297458e-06, + "loss": 0.482, + "step": 8663 + }, + { + "epoch": 0.72, + "learning_rate": 3.7137835025189894e-06, + "loss": 0.4459, + "step": 8664 + }, + { + "epoch": 0.72, + "learning_rate": 3.711676209841828e-06, + "loss": 0.4706, + "step": 8665 + }, + { + "epoch": 0.73, + "learning_rate": 3.7095693789530096e-06, + "loss": 0.4603, + "step": 8666 + }, + { + "epoch": 0.73, + "learning_rate": 3.707463010007252e-06, + "loss": 0.4563, + "step": 8667 + }, + { + "epoch": 0.73, + "learning_rate": 3.7053571031592393e-06, + "loss": 0.4674, + "step": 8668 + }, + { + "epoch": 0.73, + "learning_rate": 3.703251658563615e-06, + "loss": 0.4673, + "step": 8669 + }, + { + "epoch": 0.73, + "learning_rate": 3.7011466763750026e-06, + "loss": 0.4479, + "step": 8670 + }, + { + "epoch": 0.73, + "learning_rate": 3.6990421567479764e-06, + "loss": 0.465, + "step": 8671 + }, + { + "epoch": 0.73, + "learning_rate": 3.6969380998370896e-06, + "loss": 0.4908, + "step": 8672 + }, + { + "epoch": 0.73, + "learning_rate": 3.6948345057968525e-06, + "loss": 0.4905, + "step": 8673 + }, + { + "epoch": 0.73, + "learning_rate": 3.692731374781744e-06, + "loss": 0.4654, + "step": 8674 + }, + { + "epoch": 0.73, + "learning_rate": 3.69062870694621e-06, + "loss": 0.4858, + "step": 8675 + }, + { + "epoch": 0.73, + "learning_rate": 3.688526502444657e-06, + "loss": 0.4783, + "step": 8676 + }, + { + "epoch": 0.73, + "learning_rate": 3.6864247614314696e-06, + "loss": 0.4673, + "step": 8677 + }, + { + "epoch": 0.73, + "learning_rate": 3.6843234840609877e-06, + "loss": 0.4805, + "step": 8678 + }, + { + "epoch": 0.73, + "learning_rate": 3.6822226704875208e-06, + "loss": 0.4687, + "step": 8679 + }, + { + "epoch": 0.73, + "learning_rate": 3.6801223208653392e-06, + "loss": 0.4843, + "step": 8680 + }, + { + "epoch": 0.73, + "learning_rate": 3.6780224353486916e-06, + "loss": 0.4707, + "step": 8681 + }, + { + "epoch": 0.73, + "learning_rate": 3.675923014091781e-06, + "loss": 0.4632, + "step": 8682 + }, + { + "epoch": 0.73, + "learning_rate": 3.673824057248778e-06, + "loss": 0.4782, + "step": 8683 + }, + { + "epoch": 0.73, + "learning_rate": 3.671725564973827e-06, + "loss": 0.4764, + "step": 8684 + }, + { + "epoch": 0.73, + "learning_rate": 3.669627537421029e-06, + "loss": 0.4581, + "step": 8685 + }, + { + "epoch": 0.73, + "learning_rate": 3.6675299747444536e-06, + "loss": 0.4726, + "step": 8686 + }, + { + "epoch": 0.73, + "learning_rate": 3.6654328770981396e-06, + "loss": 0.4647, + "step": 8687 + }, + { + "epoch": 0.73, + "learning_rate": 3.6633362446360865e-06, + "loss": 0.4703, + "step": 8688 + }, + { + "epoch": 0.73, + "learning_rate": 3.6612400775122603e-06, + "loss": 0.448, + "step": 8689 + }, + { + "epoch": 0.73, + "learning_rate": 3.659144375880602e-06, + "loss": 0.4705, + "step": 8690 + }, + { + "epoch": 0.73, + "learning_rate": 3.6570491398950038e-06, + "loss": 0.4516, + "step": 8691 + }, + { + "epoch": 0.73, + "learning_rate": 3.654954369709337e-06, + "loss": 0.449, + "step": 8692 + }, + { + "epoch": 0.73, + "learning_rate": 3.6528600654774306e-06, + "loss": 0.466, + "step": 8693 + }, + { + "epoch": 0.73, + "learning_rate": 3.650766227353081e-06, + "loss": 0.464, + "step": 8694 + }, + { + "epoch": 0.73, + "learning_rate": 3.648672855490052e-06, + "loss": 0.4556, + "step": 8695 + }, + { + "epoch": 0.73, + "learning_rate": 3.6465799500420673e-06, + "loss": 0.4629, + "step": 8696 + }, + { + "epoch": 0.73, + "learning_rate": 3.6444875111628287e-06, + "loss": 0.4737, + "step": 8697 + }, + { + "epoch": 0.73, + "learning_rate": 3.642395539005993e-06, + "loss": 0.4636, + "step": 8698 + }, + { + "epoch": 0.73, + "learning_rate": 3.640304033725185e-06, + "loss": 0.4655, + "step": 8699 + }, + { + "epoch": 0.73, + "learning_rate": 3.6382129954739975e-06, + "loss": 0.4755, + "step": 8700 + }, + { + "epoch": 0.73, + "learning_rate": 3.6361224244059823e-06, + "loss": 0.4662, + "step": 8701 + }, + { + "epoch": 0.73, + "learning_rate": 3.634032320674672e-06, + "loss": 0.4579, + "step": 8702 + }, + { + "epoch": 0.73, + "learning_rate": 3.631942684433546e-06, + "loss": 0.4519, + "step": 8703 + }, + { + "epoch": 0.73, + "learning_rate": 3.629853515836065e-06, + "loss": 0.4656, + "step": 8704 + }, + { + "epoch": 0.73, + "learning_rate": 3.627764815035647e-06, + "loss": 0.463, + "step": 8705 + }, + { + "epoch": 0.73, + "learning_rate": 3.6256765821856775e-06, + "loss": 0.4798, + "step": 8706 + }, + { + "epoch": 0.73, + "learning_rate": 3.6235888174395062e-06, + "loss": 0.4823, + "step": 8707 + }, + { + "epoch": 0.73, + "learning_rate": 3.621501520950451e-06, + "loss": 0.4671, + "step": 8708 + }, + { + "epoch": 0.73, + "learning_rate": 3.6194146928717942e-06, + "loss": 0.4839, + "step": 8709 + }, + { + "epoch": 0.73, + "learning_rate": 3.61732833335678e-06, + "loss": 0.4805, + "step": 8710 + }, + { + "epoch": 0.73, + "learning_rate": 3.6152424425586285e-06, + "loss": 0.4655, + "step": 8711 + }, + { + "epoch": 0.73, + "learning_rate": 3.613157020630512e-06, + "loss": 0.4648, + "step": 8712 + }, + { + "epoch": 0.73, + "learning_rate": 3.611072067725583e-06, + "loss": 0.4541, + "step": 8713 + }, + { + "epoch": 0.73, + "learning_rate": 3.608987583996948e-06, + "loss": 0.4756, + "step": 8714 + }, + { + "epoch": 0.73, + "learning_rate": 3.606903569597683e-06, + "loss": 0.4576, + "step": 8715 + }, + { + "epoch": 0.73, + "learning_rate": 3.6048200246808273e-06, + "loss": 0.4836, + "step": 8716 + }, + { + "epoch": 0.73, + "learning_rate": 3.602736949399388e-06, + "loss": 0.473, + "step": 8717 + }, + { + "epoch": 0.73, + "learning_rate": 3.600654343906341e-06, + "loss": 0.4894, + "step": 8718 + }, + { + "epoch": 0.73, + "learning_rate": 3.5985722083546228e-06, + "loss": 0.4522, + "step": 8719 + }, + { + "epoch": 0.73, + "learning_rate": 3.5964905428971354e-06, + "loss": 0.473, + "step": 8720 + }, + { + "epoch": 0.73, + "learning_rate": 3.594409347686746e-06, + "loss": 0.4861, + "step": 8721 + }, + { + "epoch": 0.73, + "learning_rate": 3.5923286228762934e-06, + "loss": 0.4682, + "step": 8722 + }, + { + "epoch": 0.73, + "learning_rate": 3.5902483686185764e-06, + "loss": 0.457, + "step": 8723 + }, + { + "epoch": 0.73, + "learning_rate": 3.588168585066355e-06, + "loss": 0.4876, + "step": 8724 + }, + { + "epoch": 0.73, + "learning_rate": 3.5860892723723674e-06, + "loss": 0.4721, + "step": 8725 + }, + { + "epoch": 0.73, + "learning_rate": 3.5840104306893055e-06, + "loss": 0.4603, + "step": 8726 + }, + { + "epoch": 0.73, + "learning_rate": 3.5819320601698324e-06, + "loss": 0.4653, + "step": 8727 + }, + { + "epoch": 0.73, + "learning_rate": 3.579854160966574e-06, + "loss": 0.4754, + "step": 8728 + }, + { + "epoch": 0.73, + "learning_rate": 3.5777767332321222e-06, + "loss": 0.4538, + "step": 8729 + }, + { + "epoch": 0.73, + "learning_rate": 3.5756997771190317e-06, + "loss": 0.4826, + "step": 8730 + }, + { + "epoch": 0.73, + "learning_rate": 3.573623292779832e-06, + "loss": 0.4565, + "step": 8731 + }, + { + "epoch": 0.73, + "learning_rate": 3.5715472803670092e-06, + "loss": 0.4866, + "step": 8732 + }, + { + "epoch": 0.73, + "learning_rate": 3.5694717400330125e-06, + "loss": 0.4571, + "step": 8733 + }, + { + "epoch": 0.73, + "learning_rate": 3.5673966719302677e-06, + "loss": 0.4778, + "step": 8734 + }, + { + "epoch": 0.73, + "learning_rate": 3.565322076211156e-06, + "loss": 0.4611, + "step": 8735 + }, + { + "epoch": 0.73, + "learning_rate": 3.5632479530280273e-06, + "loss": 0.4616, + "step": 8736 + }, + { + "epoch": 0.73, + "learning_rate": 3.5611743025331933e-06, + "loss": 0.4913, + "step": 8737 + }, + { + "epoch": 0.73, + "learning_rate": 3.559101124878941e-06, + "loss": 0.46, + "step": 8738 + }, + { + "epoch": 0.73, + "learning_rate": 3.557028420217512e-06, + "loss": 0.4664, + "step": 8739 + }, + { + "epoch": 0.73, + "learning_rate": 3.5549561887011186e-06, + "loss": 0.47, + "step": 8740 + }, + { + "epoch": 0.73, + "learning_rate": 3.552884430481934e-06, + "loss": 0.4343, + "step": 8741 + }, + { + "epoch": 0.73, + "learning_rate": 3.5508131457120986e-06, + "loss": 0.4623, + "step": 8742 + }, + { + "epoch": 0.73, + "learning_rate": 3.5487423345437253e-06, + "loss": 0.4712, + "step": 8743 + }, + { + "epoch": 0.73, + "learning_rate": 3.546671997128879e-06, + "loss": 0.4623, + "step": 8744 + }, + { + "epoch": 0.73, + "learning_rate": 3.5446021336196024e-06, + "loss": 0.4617, + "step": 8745 + }, + { + "epoch": 0.73, + "learning_rate": 3.5425327441678956e-06, + "loss": 0.4594, + "step": 8746 + }, + { + "epoch": 0.73, + "learning_rate": 3.5404638289257256e-06, + "loss": 0.4785, + "step": 8747 + }, + { + "epoch": 0.73, + "learning_rate": 3.538395388045024e-06, + "loss": 0.4682, + "step": 8748 + }, + { + "epoch": 0.73, + "learning_rate": 3.53632742167769e-06, + "loss": 0.4745, + "step": 8749 + }, + { + "epoch": 0.73, + "learning_rate": 3.5342599299755854e-06, + "loss": 0.4562, + "step": 8750 + }, + { + "epoch": 0.73, + "learning_rate": 3.532192913090534e-06, + "loss": 0.4783, + "step": 8751 + }, + { + "epoch": 0.73, + "learning_rate": 3.5301263711743384e-06, + "loss": 0.4638, + "step": 8752 + }, + { + "epoch": 0.73, + "learning_rate": 3.528060304378749e-06, + "loss": 0.4599, + "step": 8753 + }, + { + "epoch": 0.73, + "learning_rate": 3.525994712855494e-06, + "loss": 0.4589, + "step": 8754 + }, + { + "epoch": 0.73, + "learning_rate": 3.5239295967562603e-06, + "loss": 0.4726, + "step": 8755 + }, + { + "epoch": 0.73, + "learning_rate": 3.5218649562327e-06, + "loss": 0.492, + "step": 8756 + }, + { + "epoch": 0.73, + "learning_rate": 3.519800791436434e-06, + "loss": 0.45, + "step": 8757 + }, + { + "epoch": 0.73, + "learning_rate": 3.517737102519041e-06, + "loss": 0.4591, + "step": 8758 + }, + { + "epoch": 0.73, + "learning_rate": 3.5156738896320773e-06, + "loss": 0.4785, + "step": 8759 + }, + { + "epoch": 0.73, + "learning_rate": 3.513611152927052e-06, + "loss": 0.4613, + "step": 8760 + }, + { + "epoch": 0.73, + "learning_rate": 3.5115488925554453e-06, + "loss": 0.46, + "step": 8761 + }, + { + "epoch": 0.73, + "learning_rate": 3.5094871086686997e-06, + "loss": 0.46, + "step": 8762 + }, + { + "epoch": 0.73, + "learning_rate": 3.507425801418223e-06, + "loss": 0.4892, + "step": 8763 + }, + { + "epoch": 0.73, + "learning_rate": 3.5053649709553893e-06, + "loss": 0.4579, + "step": 8764 + }, + { + "epoch": 0.73, + "learning_rate": 3.5033046174315422e-06, + "loss": 0.4607, + "step": 8765 + }, + { + "epoch": 0.73, + "learning_rate": 3.5012447409979832e-06, + "loss": 0.4775, + "step": 8766 + }, + { + "epoch": 0.73, + "learning_rate": 3.4991853418059798e-06, + "loss": 0.4502, + "step": 8767 + }, + { + "epoch": 0.73, + "learning_rate": 3.4971264200067657e-06, + "loss": 0.4841, + "step": 8768 + }, + { + "epoch": 0.73, + "learning_rate": 3.4950679757515395e-06, + "loss": 0.4704, + "step": 8769 + }, + { + "epoch": 0.73, + "learning_rate": 3.4930100091914655e-06, + "loss": 0.4668, + "step": 8770 + }, + { + "epoch": 0.73, + "learning_rate": 3.4909525204776684e-06, + "loss": 0.4685, + "step": 8771 + }, + { + "epoch": 0.73, + "learning_rate": 3.4888955097612487e-06, + "loss": 0.4771, + "step": 8772 + }, + { + "epoch": 0.73, + "learning_rate": 3.4868389771932608e-06, + "loss": 0.4739, + "step": 8773 + }, + { + "epoch": 0.73, + "learning_rate": 3.4847829229247243e-06, + "loss": 0.4764, + "step": 8774 + }, + { + "epoch": 0.73, + "learning_rate": 3.482727347106636e-06, + "loss": 0.4639, + "step": 8775 + }, + { + "epoch": 0.73, + "learning_rate": 3.4806722498899424e-06, + "loss": 0.4862, + "step": 8776 + }, + { + "epoch": 0.73, + "learning_rate": 3.4786176314255626e-06, + "loss": 0.4599, + "step": 8777 + }, + { + "epoch": 0.73, + "learning_rate": 3.4765634918643778e-06, + "loss": 0.4675, + "step": 8778 + }, + { + "epoch": 0.73, + "learning_rate": 3.474509831357239e-06, + "loss": 0.4556, + "step": 8779 + }, + { + "epoch": 0.73, + "learning_rate": 3.472456650054957e-06, + "loss": 0.4535, + "step": 8780 + }, + { + "epoch": 0.73, + "learning_rate": 3.4704039481083086e-06, + "loss": 0.4802, + "step": 8781 + }, + { + "epoch": 0.73, + "learning_rate": 3.4683517256680365e-06, + "loss": 0.4857, + "step": 8782 + }, + { + "epoch": 0.73, + "learning_rate": 3.466299982884842e-06, + "loss": 0.4661, + "step": 8783 + }, + { + "epoch": 0.73, + "learning_rate": 3.4642487199094042e-06, + "loss": 0.4644, + "step": 8784 + }, + { + "epoch": 0.73, + "learning_rate": 3.462197936892354e-06, + "loss": 0.4719, + "step": 8785 + }, + { + "epoch": 0.74, + "learning_rate": 3.4601476339842976e-06, + "loss": 0.4574, + "step": 8786 + }, + { + "epoch": 0.74, + "learning_rate": 3.4580978113357967e-06, + "loss": 0.4828, + "step": 8787 + }, + { + "epoch": 0.74, + "learning_rate": 3.4560484690973838e-06, + "loss": 0.4778, + "step": 8788 + }, + { + "epoch": 0.74, + "learning_rate": 3.4539996074195526e-06, + "loss": 0.4658, + "step": 8789 + }, + { + "epoch": 0.74, + "learning_rate": 3.4519512264527633e-06, + "loss": 0.4703, + "step": 8790 + }, + { + "epoch": 0.74, + "learning_rate": 3.44990332634744e-06, + "loss": 0.4833, + "step": 8791 + }, + { + "epoch": 0.74, + "learning_rate": 3.447855907253971e-06, + "loss": 0.464, + "step": 8792 + }, + { + "epoch": 0.74, + "learning_rate": 3.4458089693227127e-06, + "loss": 0.4666, + "step": 8793 + }, + { + "epoch": 0.74, + "learning_rate": 3.443762512703981e-06, + "loss": 0.4895, + "step": 8794 + }, + { + "epoch": 0.74, + "learning_rate": 3.4417165375480644e-06, + "loss": 0.4448, + "step": 8795 + }, + { + "epoch": 0.74, + "learning_rate": 3.439671044005206e-06, + "loss": 0.4548, + "step": 8796 + }, + { + "epoch": 0.74, + "learning_rate": 3.4376260322256207e-06, + "loss": 0.4647, + "step": 8797 + }, + { + "epoch": 0.74, + "learning_rate": 3.435581502359484e-06, + "loss": 0.4641, + "step": 8798 + }, + { + "epoch": 0.74, + "learning_rate": 3.4335374545569355e-06, + "loss": 0.4555, + "step": 8799 + }, + { + "epoch": 0.74, + "learning_rate": 3.431493888968087e-06, + "loss": 0.4594, + "step": 8800 + }, + { + "epoch": 0.74, + "learning_rate": 3.4294508057430077e-06, + "loss": 0.4741, + "step": 8801 + }, + { + "epoch": 0.74, + "learning_rate": 3.4274082050317324e-06, + "loss": 0.4444, + "step": 8802 + }, + { + "epoch": 0.74, + "learning_rate": 3.425366086984261e-06, + "loss": 0.4935, + "step": 8803 + }, + { + "epoch": 0.74, + "learning_rate": 3.4233244517505535e-06, + "loss": 0.4806, + "step": 8804 + }, + { + "epoch": 0.74, + "learning_rate": 3.4212832994805445e-06, + "loss": 0.4512, + "step": 8805 + }, + { + "epoch": 0.74, + "learning_rate": 3.419242630324131e-06, + "loss": 0.4563, + "step": 8806 + }, + { + "epoch": 0.74, + "learning_rate": 3.417202444431167e-06, + "loss": 0.4666, + "step": 8807 + }, + { + "epoch": 0.74, + "learning_rate": 3.4151627419514753e-06, + "loss": 0.4755, + "step": 8808 + }, + { + "epoch": 0.74, + "learning_rate": 3.4131235230348434e-06, + "loss": 0.4383, + "step": 8809 + }, + { + "epoch": 0.74, + "learning_rate": 3.411084787831024e-06, + "loss": 0.4517, + "step": 8810 + }, + { + "epoch": 0.74, + "learning_rate": 3.4090465364897317e-06, + "loss": 0.4664, + "step": 8811 + }, + { + "epoch": 0.74, + "learning_rate": 3.4070087691606446e-06, + "loss": 0.4844, + "step": 8812 + }, + { + "epoch": 0.74, + "learning_rate": 3.4049714859934144e-06, + "loss": 0.4634, + "step": 8813 + }, + { + "epoch": 0.74, + "learning_rate": 3.4029346871376477e-06, + "loss": 0.4492, + "step": 8814 + }, + { + "epoch": 0.74, + "learning_rate": 3.4008983727429147e-06, + "loss": 0.4665, + "step": 8815 + }, + { + "epoch": 0.74, + "learning_rate": 3.398862542958761e-06, + "loss": 0.4744, + "step": 8816 + }, + { + "epoch": 0.74, + "learning_rate": 3.3968271979346857e-06, + "loss": 0.4571, + "step": 8817 + }, + { + "epoch": 0.74, + "learning_rate": 3.3947923378201576e-06, + "loss": 0.4543, + "step": 8818 + }, + { + "epoch": 0.74, + "learning_rate": 3.3927579627646024e-06, + "loss": 0.4386, + "step": 8819 + }, + { + "epoch": 0.74, + "learning_rate": 3.390724072917424e-06, + "loss": 0.4878, + "step": 8820 + }, + { + "epoch": 0.74, + "learning_rate": 3.3886906684279806e-06, + "loss": 0.4807, + "step": 8821 + }, + { + "epoch": 0.74, + "learning_rate": 3.3866577494455953e-06, + "loss": 0.485, + "step": 8822 + }, + { + "epoch": 0.74, + "learning_rate": 3.3846253161195584e-06, + "loss": 0.46, + "step": 8823 + }, + { + "epoch": 0.74, + "learning_rate": 3.3825933685991184e-06, + "loss": 0.4907, + "step": 8824 + }, + { + "epoch": 0.74, + "learning_rate": 3.3805619070335026e-06, + "loss": 0.4913, + "step": 8825 + }, + { + "epoch": 0.74, + "learning_rate": 3.378530931571884e-06, + "loss": 0.4608, + "step": 8826 + }, + { + "epoch": 0.74, + "learning_rate": 3.3765004423634164e-06, + "loss": 0.4769, + "step": 8827 + }, + { + "epoch": 0.74, + "learning_rate": 3.374470439557207e-06, + "loss": 0.4694, + "step": 8828 + }, + { + "epoch": 0.74, + "learning_rate": 3.37244092330233e-06, + "loss": 0.4434, + "step": 8829 + }, + { + "epoch": 0.74, + "learning_rate": 3.370411893747827e-06, + "loss": 0.4433, + "step": 8830 + }, + { + "epoch": 0.74, + "learning_rate": 3.368383351042699e-06, + "loss": 0.4656, + "step": 8831 + }, + { + "epoch": 0.74, + "learning_rate": 3.366355295335915e-06, + "loss": 0.4648, + "step": 8832 + }, + { + "epoch": 0.74, + "learning_rate": 3.364327726776403e-06, + "loss": 0.4587, + "step": 8833 + }, + { + "epoch": 0.74, + "learning_rate": 3.362300645513067e-06, + "loss": 0.4806, + "step": 8834 + }, + { + "epoch": 0.74, + "learning_rate": 3.3602740516947595e-06, + "loss": 0.4774, + "step": 8835 + }, + { + "epoch": 0.74, + "learning_rate": 3.358247945470313e-06, + "loss": 0.4611, + "step": 8836 + }, + { + "epoch": 0.74, + "learning_rate": 3.356222326988512e-06, + "loss": 0.4639, + "step": 8837 + }, + { + "epoch": 0.74, + "learning_rate": 3.354197196398109e-06, + "loss": 0.4685, + "step": 8838 + }, + { + "epoch": 0.74, + "learning_rate": 3.352172553847819e-06, + "loss": 0.4648, + "step": 8839 + }, + { + "epoch": 0.74, + "learning_rate": 3.3501483994863293e-06, + "loss": 0.4667, + "step": 8840 + }, + { + "epoch": 0.74, + "learning_rate": 3.3481247334622822e-06, + "loss": 0.4724, + "step": 8841 + }, + { + "epoch": 0.74, + "learning_rate": 3.346101555924288e-06, + "loss": 0.4687, + "step": 8842 + }, + { + "epoch": 0.74, + "learning_rate": 3.34407886702092e-06, + "loss": 0.4531, + "step": 8843 + }, + { + "epoch": 0.74, + "learning_rate": 3.342056666900716e-06, + "loss": 0.4567, + "step": 8844 + }, + { + "epoch": 0.74, + "learning_rate": 3.3400349557121748e-06, + "loss": 0.4598, + "step": 8845 + }, + { + "epoch": 0.74, + "learning_rate": 3.338013733603768e-06, + "loss": 0.489, + "step": 8846 + }, + { + "epoch": 0.74, + "learning_rate": 3.3359930007239204e-06, + "loss": 0.4647, + "step": 8847 + }, + { + "epoch": 0.74, + "learning_rate": 3.3339727572210323e-06, + "loss": 0.4698, + "step": 8848 + }, + { + "epoch": 0.74, + "learning_rate": 3.3319530032434588e-06, + "loss": 0.4671, + "step": 8849 + }, + { + "epoch": 0.74, + "learning_rate": 3.3299337389395225e-06, + "loss": 0.4578, + "step": 8850 + }, + { + "epoch": 0.74, + "learning_rate": 3.327914964457509e-06, + "loss": 0.4684, + "step": 8851 + }, + { + "epoch": 0.74, + "learning_rate": 3.3258966799456705e-06, + "loss": 0.4679, + "step": 8852 + }, + { + "epoch": 0.74, + "learning_rate": 3.3238788855522164e-06, + "loss": 0.4732, + "step": 8853 + }, + { + "epoch": 0.74, + "learning_rate": 3.3218615814253306e-06, + "loss": 0.471, + "step": 8854 + }, + { + "epoch": 0.74, + "learning_rate": 3.319844767713155e-06, + "loss": 0.4485, + "step": 8855 + }, + { + "epoch": 0.74, + "learning_rate": 3.317828444563792e-06, + "loss": 0.4604, + "step": 8856 + }, + { + "epoch": 0.74, + "learning_rate": 3.3158126121253178e-06, + "loss": 0.4795, + "step": 8857 + }, + { + "epoch": 0.74, + "learning_rate": 3.3137972705457632e-06, + "loss": 0.4728, + "step": 8858 + }, + { + "epoch": 0.74, + "learning_rate": 3.3117824199731274e-06, + "loss": 0.4833, + "step": 8859 + }, + { + "epoch": 0.74, + "learning_rate": 3.3097680605553697e-06, + "loss": 0.4926, + "step": 8860 + }, + { + "epoch": 0.74, + "learning_rate": 3.307754192440421e-06, + "loss": 0.4609, + "step": 8861 + }, + { + "epoch": 0.74, + "learning_rate": 3.3057408157761696e-06, + "loss": 0.4956, + "step": 8862 + }, + { + "epoch": 0.74, + "learning_rate": 3.3037279307104685e-06, + "loss": 0.4779, + "step": 8863 + }, + { + "epoch": 0.74, + "learning_rate": 3.3017155373911382e-06, + "loss": 0.4621, + "step": 8864 + }, + { + "epoch": 0.74, + "learning_rate": 3.299703635965953e-06, + "loss": 0.4677, + "step": 8865 + }, + { + "epoch": 0.74, + "learning_rate": 3.2976922265826695e-06, + "loss": 0.4607, + "step": 8866 + }, + { + "epoch": 0.74, + "learning_rate": 3.295681309388987e-06, + "loss": 0.4671, + "step": 8867 + }, + { + "epoch": 0.74, + "learning_rate": 3.2936708845325882e-06, + "loss": 0.4555, + "step": 8868 + }, + { + "epoch": 0.74, + "learning_rate": 3.2916609521611052e-06, + "loss": 0.4641, + "step": 8869 + }, + { + "epoch": 0.74, + "learning_rate": 3.2896515124221395e-06, + "loss": 0.4775, + "step": 8870 + }, + { + "epoch": 0.74, + "learning_rate": 3.287642565463257e-06, + "loss": 0.4471, + "step": 8871 + }, + { + "epoch": 0.74, + "learning_rate": 3.2856341114319856e-06, + "loss": 0.467, + "step": 8872 + }, + { + "epoch": 0.74, + "learning_rate": 3.283626150475818e-06, + "loss": 0.4799, + "step": 8873 + }, + { + "epoch": 0.74, + "learning_rate": 3.281618682742207e-06, + "loss": 0.4601, + "step": 8874 + }, + { + "epoch": 0.74, + "learning_rate": 3.2796117083785793e-06, + "loss": 0.4666, + "step": 8875 + }, + { + "epoch": 0.74, + "learning_rate": 3.2776052275323155e-06, + "loss": 0.461, + "step": 8876 + }, + { + "epoch": 0.74, + "learning_rate": 3.2755992403507595e-06, + "loss": 0.4508, + "step": 8877 + }, + { + "epoch": 0.74, + "learning_rate": 3.2735937469812308e-06, + "loss": 0.4643, + "step": 8878 + }, + { + "epoch": 0.74, + "learning_rate": 3.2715887475709994e-06, + "loss": 0.4558, + "step": 8879 + }, + { + "epoch": 0.74, + "learning_rate": 3.269584242267301e-06, + "loss": 0.4459, + "step": 8880 + }, + { + "epoch": 0.74, + "learning_rate": 3.2675802312173468e-06, + "loss": 0.4652, + "step": 8881 + }, + { + "epoch": 0.74, + "learning_rate": 3.265576714568296e-06, + "loss": 0.4812, + "step": 8882 + }, + { + "epoch": 0.74, + "learning_rate": 3.263573692467282e-06, + "loss": 0.4507, + "step": 8883 + }, + { + "epoch": 0.74, + "learning_rate": 3.2615711650613978e-06, + "loss": 0.4705, + "step": 8884 + }, + { + "epoch": 0.74, + "learning_rate": 3.2595691324976987e-06, + "loss": 0.4785, + "step": 8885 + }, + { + "epoch": 0.74, + "learning_rate": 3.2575675949232044e-06, + "loss": 0.4464, + "step": 8886 + }, + { + "epoch": 0.74, + "learning_rate": 3.2555665524849056e-06, + "loss": 0.4793, + "step": 8887 + }, + { + "epoch": 0.74, + "learning_rate": 3.2535660053297426e-06, + "loss": 0.467, + "step": 8888 + }, + { + "epoch": 0.74, + "learning_rate": 3.2515659536046362e-06, + "loss": 0.4741, + "step": 8889 + }, + { + "epoch": 0.74, + "learning_rate": 3.249566397456456e-06, + "loss": 0.456, + "step": 8890 + }, + { + "epoch": 0.74, + "learning_rate": 3.2475673370320437e-06, + "loss": 0.4789, + "step": 8891 + }, + { + "epoch": 0.74, + "learning_rate": 3.2455687724781993e-06, + "loss": 0.4689, + "step": 8892 + }, + { + "epoch": 0.74, + "learning_rate": 3.243570703941692e-06, + "loss": 0.4554, + "step": 8893 + }, + { + "epoch": 0.74, + "learning_rate": 3.2415731315692456e-06, + "loss": 0.4697, + "step": 8894 + }, + { + "epoch": 0.74, + "learning_rate": 3.2395760555075616e-06, + "loss": 0.4546, + "step": 8895 + }, + { + "epoch": 0.74, + "learning_rate": 3.237579475903294e-06, + "loss": 0.4439, + "step": 8896 + }, + { + "epoch": 0.74, + "learning_rate": 3.235583392903059e-06, + "loss": 0.4737, + "step": 8897 + }, + { + "epoch": 0.74, + "learning_rate": 3.2335878066534464e-06, + "loss": 0.4907, + "step": 8898 + }, + { + "epoch": 0.74, + "learning_rate": 3.231592717301003e-06, + "loss": 0.4479, + "step": 8899 + }, + { + "epoch": 0.74, + "learning_rate": 3.229598124992238e-06, + "loss": 0.4761, + "step": 8900 + }, + { + "epoch": 0.74, + "learning_rate": 3.2276040298736246e-06, + "loss": 0.4905, + "step": 8901 + }, + { + "epoch": 0.74, + "learning_rate": 3.225610432091604e-06, + "loss": 0.4728, + "step": 8902 + }, + { + "epoch": 0.74, + "learning_rate": 3.223617331792578e-06, + "loss": 0.4552, + "step": 8903 + }, + { + "epoch": 0.74, + "learning_rate": 3.2216247291229087e-06, + "loss": 0.4697, + "step": 8904 + }, + { + "epoch": 0.75, + "learning_rate": 3.2196326242289266e-06, + "loss": 0.4414, + "step": 8905 + }, + { + "epoch": 0.75, + "learning_rate": 3.217641017256923e-06, + "loss": 0.4574, + "step": 8906 + }, + { + "epoch": 0.75, + "learning_rate": 3.21564990835315e-06, + "loss": 0.4696, + "step": 8907 + }, + { + "epoch": 0.75, + "learning_rate": 3.2136592976638293e-06, + "loss": 0.4626, + "step": 8908 + }, + { + "epoch": 0.75, + "learning_rate": 3.2116691853351455e-06, + "loss": 0.448, + "step": 8909 + }, + { + "epoch": 0.75, + "learning_rate": 3.2096795715132436e-06, + "loss": 0.4561, + "step": 8910 + }, + { + "epoch": 0.75, + "learning_rate": 3.2076904563442303e-06, + "loss": 0.4295, + "step": 8911 + }, + { + "epoch": 0.75, + "learning_rate": 3.2057018399741777e-06, + "loss": 0.4665, + "step": 8912 + }, + { + "epoch": 0.75, + "learning_rate": 3.2037137225491233e-06, + "loss": 0.4557, + "step": 8913 + }, + { + "epoch": 0.75, + "learning_rate": 3.2017261042150625e-06, + "loss": 0.4629, + "step": 8914 + }, + { + "epoch": 0.75, + "learning_rate": 3.199738985117963e-06, + "loss": 0.455, + "step": 8915 + }, + { + "epoch": 0.75, + "learning_rate": 3.197752365403748e-06, + "loss": 0.4552, + "step": 8916 + }, + { + "epoch": 0.75, + "learning_rate": 3.195766245218307e-06, + "loss": 0.469, + "step": 8917 + }, + { + "epoch": 0.75, + "learning_rate": 3.1937806247074875e-06, + "loss": 0.4608, + "step": 8918 + }, + { + "epoch": 0.75, + "learning_rate": 3.1917955040171146e-06, + "loss": 0.4603, + "step": 8919 + }, + { + "epoch": 0.75, + "learning_rate": 3.189810883292961e-06, + "loss": 0.4671, + "step": 8920 + }, + { + "epoch": 0.75, + "learning_rate": 3.187826762680768e-06, + "loss": 0.4597, + "step": 8921 + }, + { + "epoch": 0.75, + "learning_rate": 3.185843142326247e-06, + "loss": 0.4783, + "step": 8922 + }, + { + "epoch": 0.75, + "learning_rate": 3.1838600223750625e-06, + "loss": 0.4879, + "step": 8923 + }, + { + "epoch": 0.75, + "learning_rate": 3.181877402972848e-06, + "loss": 0.452, + "step": 8924 + }, + { + "epoch": 0.75, + "learning_rate": 3.1798952842651985e-06, + "loss": 0.4763, + "step": 8925 + }, + { + "epoch": 0.75, + "learning_rate": 3.177913666397673e-06, + "loss": 0.4543, + "step": 8926 + }, + { + "epoch": 0.75, + "learning_rate": 3.175932549515789e-06, + "loss": 0.4596, + "step": 8927 + }, + { + "epoch": 0.75, + "learning_rate": 3.173951933765038e-06, + "loss": 0.4473, + "step": 8928 + }, + { + "epoch": 0.75, + "learning_rate": 3.171971819290862e-06, + "loss": 0.4753, + "step": 8929 + }, + { + "epoch": 0.75, + "learning_rate": 3.169992206238679e-06, + "loss": 0.4606, + "step": 8930 + }, + { + "epoch": 0.75, + "learning_rate": 3.16801309475386e-06, + "loss": 0.4574, + "step": 8931 + }, + { + "epoch": 0.75, + "learning_rate": 3.166034484981744e-06, + "loss": 0.4675, + "step": 8932 + }, + { + "epoch": 0.75, + "learning_rate": 3.1640563770676305e-06, + "loss": 0.473, + "step": 8933 + }, + { + "epoch": 0.75, + "learning_rate": 3.1620787711567823e-06, + "loss": 0.4408, + "step": 8934 + }, + { + "epoch": 0.75, + "learning_rate": 3.1601016673944262e-06, + "loss": 0.4406, + "step": 8935 + }, + { + "epoch": 0.75, + "learning_rate": 3.158125065925758e-06, + "loss": 0.4783, + "step": 8936 + }, + { + "epoch": 0.75, + "learning_rate": 3.1561489668959268e-06, + "loss": 0.4705, + "step": 8937 + }, + { + "epoch": 0.75, + "learning_rate": 3.1541733704500464e-06, + "loss": 0.4587, + "step": 8938 + }, + { + "epoch": 0.75, + "learning_rate": 3.1521982767332038e-06, + "loss": 0.4524, + "step": 8939 + }, + { + "epoch": 0.75, + "learning_rate": 3.150223685890437e-06, + "loss": 0.4647, + "step": 8940 + }, + { + "epoch": 0.75, + "learning_rate": 3.1482495980667516e-06, + "loss": 0.4681, + "step": 8941 + }, + { + "epoch": 0.75, + "learning_rate": 3.1462760134071145e-06, + "loss": 0.4533, + "step": 8942 + }, + { + "epoch": 0.75, + "learning_rate": 3.1443029320564642e-06, + "loss": 0.4697, + "step": 8943 + }, + { + "epoch": 0.75, + "learning_rate": 3.1423303541596904e-06, + "loss": 0.4745, + "step": 8944 + }, + { + "epoch": 0.75, + "learning_rate": 3.1403582798616527e-06, + "loss": 0.4818, + "step": 8945 + }, + { + "epoch": 0.75, + "learning_rate": 3.1383867093071717e-06, + "loss": 0.4557, + "step": 8946 + }, + { + "epoch": 0.75, + "learning_rate": 3.1364156426410307e-06, + "loss": 0.4594, + "step": 8947 + }, + { + "epoch": 0.75, + "learning_rate": 3.1344450800079753e-06, + "loss": 0.4624, + "step": 8948 + }, + { + "epoch": 0.75, + "learning_rate": 3.1324750215527157e-06, + "loss": 0.4538, + "step": 8949 + }, + { + "epoch": 0.75, + "learning_rate": 3.1305054674199297e-06, + "loss": 0.4745, + "step": 8950 + }, + { + "epoch": 0.75, + "learning_rate": 3.12853641775425e-06, + "loss": 0.4548, + "step": 8951 + }, + { + "epoch": 0.75, + "learning_rate": 3.1265678727002758e-06, + "loss": 0.4664, + "step": 8952 + }, + { + "epoch": 0.75, + "learning_rate": 3.124599832402567e-06, + "loss": 0.459, + "step": 8953 + }, + { + "epoch": 0.75, + "learning_rate": 3.122632297005651e-06, + "loss": 0.4514, + "step": 8954 + }, + { + "epoch": 0.75, + "learning_rate": 3.1206652666540107e-06, + "loss": 0.5009, + "step": 8955 + }, + { + "epoch": 0.75, + "learning_rate": 3.1186987414921023e-06, + "loss": 0.451, + "step": 8956 + }, + { + "epoch": 0.75, + "learning_rate": 3.1167327216643374e-06, + "loss": 0.4915, + "step": 8957 + }, + { + "epoch": 0.75, + "learning_rate": 3.1147672073150916e-06, + "loss": 0.4549, + "step": 8958 + }, + { + "epoch": 0.75, + "learning_rate": 3.1128021985887004e-06, + "loss": 0.4543, + "step": 8959 + }, + { + "epoch": 0.75, + "learning_rate": 3.110837695629473e-06, + "loss": 0.4726, + "step": 8960 + }, + { + "epoch": 0.75, + "learning_rate": 3.1088736985816716e-06, + "loss": 0.4673, + "step": 8961 + }, + { + "epoch": 0.75, + "learning_rate": 3.1069102075895207e-06, + "loss": 0.4575, + "step": 8962 + }, + { + "epoch": 0.75, + "learning_rate": 3.1049472227972157e-06, + "loss": 0.4507, + "step": 8963 + }, + { + "epoch": 0.75, + "learning_rate": 3.1029847443489093e-06, + "loss": 0.4733, + "step": 8964 + }, + { + "epoch": 0.75, + "learning_rate": 3.1010227723887153e-06, + "loss": 0.4522, + "step": 8965 + }, + { + "epoch": 0.75, + "learning_rate": 3.0990613070607145e-06, + "loss": 0.4629, + "step": 8966 + }, + { + "epoch": 0.75, + "learning_rate": 3.0971003485089477e-06, + "loss": 0.4818, + "step": 8967 + }, + { + "epoch": 0.75, + "learning_rate": 3.095139896877417e-06, + "loss": 0.4479, + "step": 8968 + }, + { + "epoch": 0.75, + "learning_rate": 3.093179952310096e-06, + "loss": 0.4705, + "step": 8969 + }, + { + "epoch": 0.75, + "learning_rate": 3.091220514950908e-06, + "loss": 0.4932, + "step": 8970 + }, + { + "epoch": 0.75, + "learning_rate": 3.0892615849437533e-06, + "loss": 0.4519, + "step": 8971 + }, + { + "epoch": 0.75, + "learning_rate": 3.0873031624324835e-06, + "loss": 0.4589, + "step": 8972 + }, + { + "epoch": 0.75, + "learning_rate": 3.085345247560918e-06, + "loss": 0.4546, + "step": 8973 + }, + { + "epoch": 0.75, + "learning_rate": 3.0833878404728366e-06, + "loss": 0.4622, + "step": 8974 + }, + { + "epoch": 0.75, + "learning_rate": 3.081430941311985e-06, + "loss": 0.4992, + "step": 8975 + }, + { + "epoch": 0.75, + "learning_rate": 3.0794745502220646e-06, + "loss": 0.4815, + "step": 8976 + }, + { + "epoch": 0.75, + "learning_rate": 3.077518667346752e-06, + "loss": 0.4669, + "step": 8977 + }, + { + "epoch": 0.75, + "learning_rate": 3.075563292829675e-06, + "loss": 0.4699, + "step": 8978 + }, + { + "epoch": 0.75, + "learning_rate": 3.0736084268144264e-06, + "loss": 0.4627, + "step": 8979 + }, + { + "epoch": 0.75, + "learning_rate": 3.0716540694445694e-06, + "loss": 0.4654, + "step": 8980 + }, + { + "epoch": 0.75, + "learning_rate": 3.0697002208636195e-06, + "loss": 0.4628, + "step": 8981 + }, + { + "epoch": 0.75, + "learning_rate": 3.0677468812150612e-06, + "loss": 0.4558, + "step": 8982 + }, + { + "epoch": 0.75, + "learning_rate": 3.0657940506423345e-06, + "loss": 0.4844, + "step": 8983 + }, + { + "epoch": 0.75, + "learning_rate": 3.0638417292888546e-06, + "loss": 0.4778, + "step": 8984 + }, + { + "epoch": 0.75, + "learning_rate": 3.0618899172979875e-06, + "loss": 0.4671, + "step": 8985 + }, + { + "epoch": 0.75, + "learning_rate": 3.0599386148130684e-06, + "loss": 0.4511, + "step": 8986 + }, + { + "epoch": 0.75, + "learning_rate": 3.0579878219773917e-06, + "loss": 0.4486, + "step": 8987 + }, + { + "epoch": 0.75, + "learning_rate": 3.0560375389342147e-06, + "loss": 0.4686, + "step": 8988 + }, + { + "epoch": 0.75, + "learning_rate": 3.0540877658267555e-06, + "loss": 0.4589, + "step": 8989 + }, + { + "epoch": 0.75, + "learning_rate": 3.0521385027982033e-06, + "loss": 0.4522, + "step": 8990 + }, + { + "epoch": 0.75, + "learning_rate": 3.050189749991699e-06, + "loss": 0.4682, + "step": 8991 + }, + { + "epoch": 0.75, + "learning_rate": 3.0482415075503556e-06, + "loss": 0.4816, + "step": 8992 + }, + { + "epoch": 0.75, + "learning_rate": 3.0462937756172417e-06, + "loss": 0.4533, + "step": 8993 + }, + { + "epoch": 0.75, + "learning_rate": 3.0443465543353902e-06, + "loss": 0.4747, + "step": 8994 + }, + { + "epoch": 0.75, + "learning_rate": 3.0423998438477964e-06, + "loss": 0.4747, + "step": 8995 + }, + { + "epoch": 0.75, + "learning_rate": 3.0404536442974165e-06, + "loss": 0.4568, + "step": 8996 + }, + { + "epoch": 0.75, + "learning_rate": 3.0385079558271768e-06, + "loss": 0.4665, + "step": 8997 + }, + { + "epoch": 0.75, + "learning_rate": 3.036562778579959e-06, + "loss": 0.4617, + "step": 8998 + }, + { + "epoch": 0.75, + "learning_rate": 3.0346181126986063e-06, + "loss": 0.4713, + "step": 8999 + }, + { + "epoch": 0.75, + "learning_rate": 3.0326739583259255e-06, + "loss": 0.4868, + "step": 9000 + }, + { + "epoch": 0.75, + "learning_rate": 3.030730315604693e-06, + "loss": 0.4813, + "step": 9001 + }, + { + "epoch": 0.75, + "learning_rate": 3.0287871846776397e-06, + "loss": 0.4769, + "step": 9002 + }, + { + "epoch": 0.75, + "learning_rate": 3.0268445656874555e-06, + "loss": 0.4529, + "step": 9003 + }, + { + "epoch": 0.75, + "learning_rate": 3.0249024587768074e-06, + "loss": 0.4653, + "step": 9004 + }, + { + "epoch": 0.75, + "learning_rate": 3.02296086408831e-06, + "loss": 0.4987, + "step": 9005 + }, + { + "epoch": 0.75, + "learning_rate": 3.0210197817645472e-06, + "loss": 0.445, + "step": 9006 + }, + { + "epoch": 0.75, + "learning_rate": 3.0190792119480638e-06, + "loss": 0.4692, + "step": 9007 + }, + { + "epoch": 0.75, + "learning_rate": 3.017139154781368e-06, + "loss": 0.4617, + "step": 9008 + }, + { + "epoch": 0.75, + "learning_rate": 3.015199610406925e-06, + "loss": 0.4727, + "step": 9009 + }, + { + "epoch": 0.75, + "learning_rate": 3.0132605789671744e-06, + "loss": 0.4471, + "step": 9010 + }, + { + "epoch": 0.75, + "learning_rate": 3.0113220606045035e-06, + "loss": 0.4654, + "step": 9011 + }, + { + "epoch": 0.75, + "learning_rate": 3.0093840554612753e-06, + "loss": 0.4895, + "step": 9012 + }, + { + "epoch": 0.75, + "learning_rate": 3.0074465636798056e-06, + "loss": 0.4657, + "step": 9013 + }, + { + "epoch": 0.75, + "learning_rate": 3.0055095854023764e-06, + "loss": 0.483, + "step": 9014 + }, + { + "epoch": 0.75, + "learning_rate": 3.0035731207712305e-06, + "loss": 0.4526, + "step": 9015 + }, + { + "epoch": 0.75, + "learning_rate": 3.001637169928575e-06, + "loss": 0.4655, + "step": 9016 + }, + { + "epoch": 0.75, + "learning_rate": 2.9997017330165736e-06, + "loss": 0.4689, + "step": 9017 + }, + { + "epoch": 0.75, + "learning_rate": 2.9977668101773636e-06, + "loss": 0.4669, + "step": 9018 + }, + { + "epoch": 0.75, + "learning_rate": 2.995832401553035e-06, + "loss": 0.4726, + "step": 9019 + }, + { + "epoch": 0.75, + "learning_rate": 2.993898507285643e-06, + "loss": 0.4629, + "step": 9020 + }, + { + "epoch": 0.75, + "learning_rate": 2.9919651275172e-06, + "loss": 0.4591, + "step": 9021 + }, + { + "epoch": 0.75, + "learning_rate": 2.990032262389693e-06, + "loss": 0.4758, + "step": 9022 + }, + { + "epoch": 0.75, + "learning_rate": 2.9880999120450595e-06, + "loss": 0.4545, + "step": 9023 + }, + { + "epoch": 0.75, + "learning_rate": 2.9861680766252e-06, + "loss": 0.4509, + "step": 9024 + }, + { + "epoch": 0.76, + "learning_rate": 2.9842367562719887e-06, + "loss": 0.4604, + "step": 9025 + }, + { + "epoch": 0.76, + "learning_rate": 2.982305951127249e-06, + "loss": 0.46, + "step": 9026 + }, + { + "epoch": 0.76, + "learning_rate": 2.9803756613327704e-06, + "loss": 0.4715, + "step": 9027 + }, + { + "epoch": 0.76, + "learning_rate": 2.978445887030308e-06, + "loss": 0.4413, + "step": 9028 + }, + { + "epoch": 0.76, + "learning_rate": 2.976516628361574e-06, + "loss": 0.4943, + "step": 9029 + }, + { + "epoch": 0.76, + "learning_rate": 2.974587885468243e-06, + "loss": 0.4575, + "step": 9030 + }, + { + "epoch": 0.76, + "learning_rate": 2.9726596584919596e-06, + "loss": 0.4496, + "step": 9031 + }, + { + "epoch": 0.76, + "learning_rate": 2.970731947574319e-06, + "loss": 0.4542, + "step": 9032 + }, + { + "epoch": 0.76, + "learning_rate": 2.968804752856891e-06, + "loss": 0.4855, + "step": 9033 + }, + { + "epoch": 0.76, + "learning_rate": 2.9668780744811967e-06, + "loss": 0.4437, + "step": 9034 + }, + { + "epoch": 0.76, + "learning_rate": 2.9649519125887227e-06, + "loss": 0.4699, + "step": 9035 + }, + { + "epoch": 0.76, + "learning_rate": 2.96302626732092e-06, + "loss": 0.4794, + "step": 9036 + }, + { + "epoch": 0.76, + "learning_rate": 2.9611011388191956e-06, + "loss": 0.4607, + "step": 9037 + }, + { + "epoch": 0.76, + "learning_rate": 2.9591765272249305e-06, + "loss": 0.472, + "step": 9038 + }, + { + "epoch": 0.76, + "learning_rate": 2.9572524326794562e-06, + "loss": 0.4636, + "step": 9039 + }, + { + "epoch": 0.76, + "learning_rate": 2.9553288553240698e-06, + "loss": 0.4749, + "step": 9040 + }, + { + "epoch": 0.76, + "learning_rate": 2.9534057953000283e-06, + "loss": 0.4753, + "step": 9041 + }, + { + "epoch": 0.76, + "learning_rate": 2.9514832527485593e-06, + "loss": 0.4424, + "step": 9042 + }, + { + "epoch": 0.76, + "learning_rate": 2.949561227810843e-06, + "loss": 0.4706, + "step": 9043 + }, + { + "epoch": 0.76, + "learning_rate": 2.947639720628023e-06, + "loss": 0.4448, + "step": 9044 + }, + { + "epoch": 0.76, + "learning_rate": 2.945718731341212e-06, + "loss": 0.4846, + "step": 9045 + }, + { + "epoch": 0.76, + "learning_rate": 2.943798260091475e-06, + "loss": 0.4563, + "step": 9046 + }, + { + "epoch": 0.76, + "learning_rate": 2.9418783070198455e-06, + "loss": 0.4693, + "step": 9047 + }, + { + "epoch": 0.76, + "learning_rate": 2.9399588722673165e-06, + "loss": 0.4424, + "step": 9048 + }, + { + "epoch": 0.76, + "learning_rate": 2.938039955974843e-06, + "loss": 0.4605, + "step": 9049 + }, + { + "epoch": 0.76, + "learning_rate": 2.9361215582833425e-06, + "loss": 0.474, + "step": 9050 + }, + { + "epoch": 0.76, + "learning_rate": 2.9342036793336904e-06, + "loss": 0.4644, + "step": 9051 + }, + { + "epoch": 0.76, + "learning_rate": 2.9322863192667306e-06, + "loss": 0.4739, + "step": 9052 + }, + { + "epoch": 0.76, + "learning_rate": 2.9303694782232706e-06, + "loss": 0.451, + "step": 9053 + }, + { + "epoch": 0.76, + "learning_rate": 2.928453156344071e-06, + "loss": 0.4632, + "step": 9054 + }, + { + "epoch": 0.76, + "learning_rate": 2.9265373537698595e-06, + "loss": 0.4599, + "step": 9055 + }, + { + "epoch": 0.76, + "learning_rate": 2.924622070641323e-06, + "loss": 0.4581, + "step": 9056 + }, + { + "epoch": 0.76, + "learning_rate": 2.922707307099113e-06, + "loss": 0.4745, + "step": 9057 + }, + { + "epoch": 0.76, + "learning_rate": 2.920793063283839e-06, + "loss": 0.4713, + "step": 9058 + }, + { + "epoch": 0.76, + "learning_rate": 2.9188793393360813e-06, + "loss": 0.4605, + "step": 9059 + }, + { + "epoch": 0.76, + "learning_rate": 2.916966135396372e-06, + "loss": 0.4687, + "step": 9060 + }, + { + "epoch": 0.76, + "learning_rate": 2.9150534516052085e-06, + "loss": 0.4748, + "step": 9061 + }, + { + "epoch": 0.76, + "learning_rate": 2.9131412881030487e-06, + "loss": 0.454, + "step": 9062 + }, + { + "epoch": 0.76, + "learning_rate": 2.911229645030319e-06, + "loss": 0.4901, + "step": 9063 + }, + { + "epoch": 0.76, + "learning_rate": 2.909318522527397e-06, + "loss": 0.4588, + "step": 9064 + }, + { + "epoch": 0.76, + "learning_rate": 2.9074079207346328e-06, + "loss": 0.4642, + "step": 9065 + }, + { + "epoch": 0.76, + "learning_rate": 2.9054978397923306e-06, + "loss": 0.4733, + "step": 9066 + }, + { + "epoch": 0.76, + "learning_rate": 2.903588279840759e-06, + "loss": 0.4799, + "step": 9067 + }, + { + "epoch": 0.76, + "learning_rate": 2.901679241020149e-06, + "loss": 0.472, + "step": 9068 + }, + { + "epoch": 0.76, + "learning_rate": 2.8997707234706894e-06, + "loss": 0.4813, + "step": 9069 + }, + { + "epoch": 0.76, + "learning_rate": 2.8978627273325378e-06, + "loss": 0.4612, + "step": 9070 + }, + { + "epoch": 0.76, + "learning_rate": 2.8959552527458025e-06, + "loss": 0.4695, + "step": 9071 + }, + { + "epoch": 0.76, + "learning_rate": 2.8940482998505703e-06, + "loss": 0.4619, + "step": 9072 + }, + { + "epoch": 0.76, + "learning_rate": 2.892141868786871e-06, + "loss": 0.452, + "step": 9073 + }, + { + "epoch": 0.76, + "learning_rate": 2.8902359596947127e-06, + "loss": 0.4722, + "step": 9074 + }, + { + "epoch": 0.76, + "learning_rate": 2.8883305727140533e-06, + "loss": 0.442, + "step": 9075 + }, + { + "epoch": 0.76, + "learning_rate": 2.8864257079848166e-06, + "loss": 0.4708, + "step": 9076 + }, + { + "epoch": 0.76, + "learning_rate": 2.8845213656468896e-06, + "loss": 0.4646, + "step": 9077 + }, + { + "epoch": 0.76, + "learning_rate": 2.882617545840114e-06, + "loss": 0.4648, + "step": 9078 + }, + { + "epoch": 0.76, + "learning_rate": 2.8807142487043047e-06, + "loss": 0.4804, + "step": 9079 + }, + { + "epoch": 0.76, + "learning_rate": 2.8788114743792317e-06, + "loss": 0.46, + "step": 9080 + }, + { + "epoch": 0.76, + "learning_rate": 2.8769092230046236e-06, + "loss": 0.455, + "step": 9081 + }, + { + "epoch": 0.76, + "learning_rate": 2.875007494720171e-06, + "loss": 0.4514, + "step": 9082 + }, + { + "epoch": 0.76, + "learning_rate": 2.8731062896655383e-06, + "loss": 0.4745, + "step": 9083 + }, + { + "epoch": 0.76, + "learning_rate": 2.871205607980335e-06, + "loss": 0.4647, + "step": 9084 + }, + { + "epoch": 0.76, + "learning_rate": 2.8693054498041383e-06, + "loss": 0.4675, + "step": 9085 + }, + { + "epoch": 0.76, + "learning_rate": 2.867405815276494e-06, + "loss": 0.4572, + "step": 9086 + }, + { + "epoch": 0.76, + "learning_rate": 2.865506704536899e-06, + "loss": 0.4301, + "step": 9087 + }, + { + "epoch": 0.76, + "learning_rate": 2.8636081177248176e-06, + "loss": 0.4656, + "step": 9088 + }, + { + "epoch": 0.76, + "learning_rate": 2.861710054979674e-06, + "loss": 0.4682, + "step": 9089 + }, + { + "epoch": 0.76, + "learning_rate": 2.859812516440853e-06, + "loss": 0.4671, + "step": 9090 + }, + { + "epoch": 0.76, + "learning_rate": 2.8579155022477024e-06, + "loss": 0.4713, + "step": 9091 + }, + { + "epoch": 0.76, + "learning_rate": 2.856019012539528e-06, + "loss": 0.4732, + "step": 9092 + }, + { + "epoch": 0.76, + "learning_rate": 2.8541230474556035e-06, + "loss": 0.4658, + "step": 9093 + }, + { + "epoch": 0.76, + "learning_rate": 2.852227607135164e-06, + "loss": 0.4677, + "step": 9094 + }, + { + "epoch": 0.76, + "learning_rate": 2.850332691717399e-06, + "loss": 0.4676, + "step": 9095 + }, + { + "epoch": 0.76, + "learning_rate": 2.8484383013414627e-06, + "loss": 0.4892, + "step": 9096 + }, + { + "epoch": 0.76, + "learning_rate": 2.846544436146473e-06, + "loss": 0.4541, + "step": 9097 + }, + { + "epoch": 0.76, + "learning_rate": 2.8446510962715055e-06, + "loss": 0.464, + "step": 9098 + }, + { + "epoch": 0.76, + "learning_rate": 2.8427582818555976e-06, + "loss": 0.4755, + "step": 9099 + }, + { + "epoch": 0.76, + "learning_rate": 2.8408659930377556e-06, + "loss": 0.4582, + "step": 9100 + }, + { + "epoch": 0.76, + "learning_rate": 2.838974229956938e-06, + "loss": 0.4648, + "step": 9101 + }, + { + "epoch": 0.76, + "learning_rate": 2.837082992752067e-06, + "loss": 0.4542, + "step": 9102 + }, + { + "epoch": 0.76, + "learning_rate": 2.835192281562027e-06, + "loss": 0.4401, + "step": 9103 + }, + { + "epoch": 0.76, + "learning_rate": 2.8333020965256666e-06, + "loss": 0.4844, + "step": 9104 + }, + { + "epoch": 0.76, + "learning_rate": 2.8314124377817888e-06, + "loss": 0.4815, + "step": 9105 + }, + { + "epoch": 0.76, + "learning_rate": 2.8295233054691685e-06, + "loss": 0.479, + "step": 9106 + }, + { + "epoch": 0.76, + "learning_rate": 2.8276346997265324e-06, + "loss": 0.4473, + "step": 9107 + }, + { + "epoch": 0.76, + "learning_rate": 2.8257466206925723e-06, + "loss": 0.4676, + "step": 9108 + }, + { + "epoch": 0.76, + "learning_rate": 2.82385906850594e-06, + "loss": 0.4612, + "step": 9109 + }, + { + "epoch": 0.76, + "learning_rate": 2.82197204330525e-06, + "loss": 0.4752, + "step": 9110 + }, + { + "epoch": 0.76, + "learning_rate": 2.820085545229078e-06, + "loss": 0.4496, + "step": 9111 + }, + { + "epoch": 0.76, + "learning_rate": 2.8181995744159553e-06, + "loss": 0.4537, + "step": 9112 + }, + { + "epoch": 0.76, + "learning_rate": 2.8163141310043886e-06, + "loss": 0.4666, + "step": 9113 + }, + { + "epoch": 0.76, + "learning_rate": 2.81442921513283e-06, + "loss": 0.4734, + "step": 9114 + }, + { + "epoch": 0.76, + "learning_rate": 2.812544826939706e-06, + "loss": 0.4739, + "step": 9115 + }, + { + "epoch": 0.76, + "learning_rate": 2.8106609665633943e-06, + "loss": 0.4542, + "step": 9116 + }, + { + "epoch": 0.76, + "learning_rate": 2.808777634142239e-06, + "loss": 0.4808, + "step": 9117 + }, + { + "epoch": 0.76, + "learning_rate": 2.8068948298145437e-06, + "loss": 0.4737, + "step": 9118 + }, + { + "epoch": 0.76, + "learning_rate": 2.80501255371857e-06, + "loss": 0.453, + "step": 9119 + }, + { + "epoch": 0.76, + "learning_rate": 2.803130805992552e-06, + "loss": 0.4852, + "step": 9120 + }, + { + "epoch": 0.76, + "learning_rate": 2.8012495867746735e-06, + "loss": 0.4509, + "step": 9121 + }, + { + "epoch": 0.76, + "learning_rate": 2.799368896203084e-06, + "loss": 0.447, + "step": 9122 + }, + { + "epoch": 0.76, + "learning_rate": 2.7974887344158897e-06, + "loss": 0.4753, + "step": 9123 + }, + { + "epoch": 0.76, + "learning_rate": 2.7956091015511676e-06, + "loss": 0.4621, + "step": 9124 + }, + { + "epoch": 0.76, + "learning_rate": 2.793729997746948e-06, + "loss": 0.4722, + "step": 9125 + }, + { + "epoch": 0.76, + "learning_rate": 2.791851423141222e-06, + "loss": 0.4903, + "step": 9126 + }, + { + "epoch": 0.76, + "learning_rate": 2.7899733778719483e-06, + "loss": 0.4797, + "step": 9127 + }, + { + "epoch": 0.76, + "learning_rate": 2.7880958620770415e-06, + "loss": 0.4619, + "step": 9128 + }, + { + "epoch": 0.76, + "learning_rate": 2.7862188758943788e-06, + "loss": 0.4626, + "step": 9129 + }, + { + "epoch": 0.76, + "learning_rate": 2.7843424194617964e-06, + "loss": 0.4839, + "step": 9130 + }, + { + "epoch": 0.76, + "learning_rate": 2.7824664929170953e-06, + "loss": 0.4832, + "step": 9131 + }, + { + "epoch": 0.76, + "learning_rate": 2.7805910963980343e-06, + "loss": 0.5038, + "step": 9132 + }, + { + "epoch": 0.76, + "learning_rate": 2.778716230042333e-06, + "loss": 0.4822, + "step": 9133 + }, + { + "epoch": 0.76, + "learning_rate": 2.7768418939876794e-06, + "loss": 0.4542, + "step": 9134 + }, + { + "epoch": 0.76, + "learning_rate": 2.7749680883717102e-06, + "loss": 0.4602, + "step": 9135 + }, + { + "epoch": 0.76, + "learning_rate": 2.773094813332037e-06, + "loss": 0.4747, + "step": 9136 + }, + { + "epoch": 0.76, + "learning_rate": 2.7712220690062208e-06, + "loss": 0.4595, + "step": 9137 + }, + { + "epoch": 0.76, + "learning_rate": 2.769349855531789e-06, + "loss": 0.4627, + "step": 9138 + }, + { + "epoch": 0.76, + "learning_rate": 2.7674781730462273e-06, + "loss": 0.4563, + "step": 9139 + }, + { + "epoch": 0.76, + "learning_rate": 2.765607021686989e-06, + "loss": 0.4852, + "step": 9140 + }, + { + "epoch": 0.76, + "learning_rate": 2.7637364015914803e-06, + "loss": 0.4463, + "step": 9141 + }, + { + "epoch": 0.76, + "learning_rate": 2.7618663128970722e-06, + "loss": 0.4673, + "step": 9142 + }, + { + "epoch": 0.76, + "learning_rate": 2.759996755741098e-06, + "loss": 0.446, + "step": 9143 + }, + { + "epoch": 0.77, + "learning_rate": 2.7581277302608446e-06, + "loss": 0.4693, + "step": 9144 + }, + { + "epoch": 0.77, + "learning_rate": 2.7562592365935724e-06, + "loss": 0.4751, + "step": 9145 + }, + { + "epoch": 0.77, + "learning_rate": 2.75439127487649e-06, + "loss": 0.4539, + "step": 9146 + }, + { + "epoch": 0.77, + "learning_rate": 2.7525238452467783e-06, + "loss": 0.4628, + "step": 9147 + }, + { + "epoch": 0.77, + "learning_rate": 2.7506569478415713e-06, + "loss": 0.4756, + "step": 9148 + }, + { + "epoch": 0.77, + "learning_rate": 2.7487905827979654e-06, + "loss": 0.4652, + "step": 9149 + }, + { + "epoch": 0.77, + "learning_rate": 2.7469247502530194e-06, + "loss": 0.4361, + "step": 9150 + }, + { + "epoch": 0.77, + "learning_rate": 2.745059450343752e-06, + "loss": 0.4724, + "step": 9151 + }, + { + "epoch": 0.77, + "learning_rate": 2.7431946832071433e-06, + "loss": 0.4707, + "step": 9152 + }, + { + "epoch": 0.77, + "learning_rate": 2.7413304489801296e-06, + "loss": 0.4704, + "step": 9153 + }, + { + "epoch": 0.77, + "learning_rate": 2.7394667477996207e-06, + "loss": 0.4542, + "step": 9154 + }, + { + "epoch": 0.77, + "learning_rate": 2.737603579802471e-06, + "loss": 0.4505, + "step": 9155 + }, + { + "epoch": 0.77, + "learning_rate": 2.7357409451255113e-06, + "loss": 0.458, + "step": 9156 + }, + { + "epoch": 0.77, + "learning_rate": 2.733878843905523e-06, + "loss": 0.4673, + "step": 9157 + }, + { + "epoch": 0.77, + "learning_rate": 2.7320172762792497e-06, + "loss": 0.4914, + "step": 9158 + }, + { + "epoch": 0.77, + "learning_rate": 2.7301562423833985e-06, + "loss": 0.4658, + "step": 9159 + }, + { + "epoch": 0.77, + "learning_rate": 2.728295742354631e-06, + "loss": 0.449, + "step": 9160 + }, + { + "epoch": 0.77, + "learning_rate": 2.7264357763295822e-06, + "loss": 0.4757, + "step": 9161 + }, + { + "epoch": 0.77, + "learning_rate": 2.7245763444448383e-06, + "loss": 0.4689, + "step": 9162 + }, + { + "epoch": 0.77, + "learning_rate": 2.7227174468369454e-06, + "loss": 0.4551, + "step": 9163 + }, + { + "epoch": 0.77, + "learning_rate": 2.720859083642415e-06, + "loss": 0.4712, + "step": 9164 + }, + { + "epoch": 0.77, + "learning_rate": 2.7190012549977153e-06, + "loss": 0.4821, + "step": 9165 + }, + { + "epoch": 0.77, + "learning_rate": 2.7171439610392815e-06, + "loss": 0.4558, + "step": 9166 + }, + { + "epoch": 0.77, + "learning_rate": 2.7152872019035005e-06, + "loss": 0.4696, + "step": 9167 + }, + { + "epoch": 0.77, + "learning_rate": 2.7134309777267307e-06, + "loss": 0.4633, + "step": 9168 + }, + { + "epoch": 0.77, + "learning_rate": 2.711575288645284e-06, + "loss": 0.4628, + "step": 9169 + }, + { + "epoch": 0.77, + "learning_rate": 2.7097201347954318e-06, + "loss": 0.466, + "step": 9170 + }, + { + "epoch": 0.77, + "learning_rate": 2.7078655163134117e-06, + "loss": 0.4747, + "step": 9171 + }, + { + "epoch": 0.77, + "learning_rate": 2.706011433335417e-06, + "loss": 0.4617, + "step": 9172 + }, + { + "epoch": 0.77, + "learning_rate": 2.704157885997605e-06, + "loss": 0.4672, + "step": 9173 + }, + { + "epoch": 0.77, + "learning_rate": 2.702304874436089e-06, + "loss": 0.453, + "step": 9174 + }, + { + "epoch": 0.77, + "learning_rate": 2.7004523987869526e-06, + "loss": 0.4688, + "step": 9175 + }, + { + "epoch": 0.77, + "learning_rate": 2.698600459186228e-06, + "loss": 0.4595, + "step": 9176 + }, + { + "epoch": 0.77, + "learning_rate": 2.6967490557699196e-06, + "loss": 0.4421, + "step": 9177 + }, + { + "epoch": 0.77, + "learning_rate": 2.6948981886739846e-06, + "loss": 0.4677, + "step": 9178 + }, + { + "epoch": 0.77, + "learning_rate": 2.693047858034342e-06, + "loss": 0.4797, + "step": 9179 + }, + { + "epoch": 0.77, + "learning_rate": 2.6911980639868696e-06, + "loss": 0.4518, + "step": 9180 + }, + { + "epoch": 0.77, + "learning_rate": 2.6893488066674154e-06, + "loss": 0.4681, + "step": 9181 + }, + { + "epoch": 0.77, + "learning_rate": 2.687500086211777e-06, + "loss": 0.4684, + "step": 9182 + }, + { + "epoch": 0.77, + "learning_rate": 2.685651902755717e-06, + "loss": 0.465, + "step": 9183 + }, + { + "epoch": 0.77, + "learning_rate": 2.6838042564349597e-06, + "loss": 0.4633, + "step": 9184 + }, + { + "epoch": 0.77, + "learning_rate": 2.6819571473851836e-06, + "loss": 0.4565, + "step": 9185 + }, + { + "epoch": 0.77, + "learning_rate": 2.6801105757420397e-06, + "loss": 0.4577, + "step": 9186 + }, + { + "epoch": 0.77, + "learning_rate": 2.6782645416411267e-06, + "loss": 0.4726, + "step": 9187 + }, + { + "epoch": 0.77, + "learning_rate": 2.676419045218016e-06, + "loss": 0.4555, + "step": 9188 + }, + { + "epoch": 0.77, + "learning_rate": 2.674574086608228e-06, + "loss": 0.4847, + "step": 9189 + }, + { + "epoch": 0.77, + "learning_rate": 2.672729665947251e-06, + "loss": 0.4464, + "step": 9190 + }, + { + "epoch": 0.77, + "learning_rate": 2.6708857833705315e-06, + "loss": 0.4601, + "step": 9191 + }, + { + "epoch": 0.77, + "learning_rate": 2.669042439013476e-06, + "loss": 0.4795, + "step": 9192 + }, + { + "epoch": 0.77, + "learning_rate": 2.6671996330114514e-06, + "loss": 0.4571, + "step": 9193 + }, + { + "epoch": 0.77, + "learning_rate": 2.6653573654997835e-06, + "loss": 0.4686, + "step": 9194 + }, + { + "epoch": 0.77, + "learning_rate": 2.6635156366137672e-06, + "loss": 0.4599, + "step": 9195 + }, + { + "epoch": 0.77, + "learning_rate": 2.6616744464886437e-06, + "loss": 0.4802, + "step": 9196 + }, + { + "epoch": 0.77, + "learning_rate": 2.65983379525963e-06, + "loss": 0.4669, + "step": 9197 + }, + { + "epoch": 0.77, + "learning_rate": 2.6579936830618926e-06, + "loss": 0.4458, + "step": 9198 + }, + { + "epoch": 0.77, + "learning_rate": 2.656154110030561e-06, + "loss": 0.466, + "step": 9199 + }, + { + "epoch": 0.77, + "learning_rate": 2.6543150763007265e-06, + "loss": 0.4608, + "step": 9200 + }, + { + "epoch": 0.77, + "learning_rate": 2.652476582007436e-06, + "loss": 0.4676, + "step": 9201 + }, + { + "epoch": 0.77, + "learning_rate": 2.6506386272857086e-06, + "loss": 0.4696, + "step": 9202 + }, + { + "epoch": 0.77, + "learning_rate": 2.648801212270512e-06, + "loss": 0.463, + "step": 9203 + }, + { + "epoch": 0.77, + "learning_rate": 2.646964337096778e-06, + "loss": 0.4484, + "step": 9204 + }, + { + "epoch": 0.77, + "learning_rate": 2.6451280018993996e-06, + "loss": 0.4569, + "step": 9205 + }, + { + "epoch": 0.77, + "learning_rate": 2.643292206813227e-06, + "loss": 0.4825, + "step": 9206 + }, + { + "epoch": 0.77, + "learning_rate": 2.6414569519730793e-06, + "loss": 0.4526, + "step": 9207 + }, + { + "epoch": 0.77, + "learning_rate": 2.6396222375137227e-06, + "loss": 0.4555, + "step": 9208 + }, + { + "epoch": 0.77, + "learning_rate": 2.6377880635698973e-06, + "loss": 0.4824, + "step": 9209 + }, + { + "epoch": 0.77, + "learning_rate": 2.635954430276296e-06, + "loss": 0.4683, + "step": 9210 + }, + { + "epoch": 0.77, + "learning_rate": 2.634121337767571e-06, + "loss": 0.4648, + "step": 9211 + }, + { + "epoch": 0.77, + "learning_rate": 2.6322887861783385e-06, + "loss": 0.4767, + "step": 9212 + }, + { + "epoch": 0.77, + "learning_rate": 2.630456775643173e-06, + "loss": 0.4557, + "step": 9213 + }, + { + "epoch": 0.77, + "learning_rate": 2.6286253062966096e-06, + "loss": 0.4721, + "step": 9214 + }, + { + "epoch": 0.77, + "learning_rate": 2.6267943782731407e-06, + "loss": 0.4695, + "step": 9215 + }, + { + "epoch": 0.77, + "learning_rate": 2.624963991707228e-06, + "loss": 0.4559, + "step": 9216 + }, + { + "epoch": 0.77, + "learning_rate": 2.6231341467332827e-06, + "loss": 0.477, + "step": 9217 + }, + { + "epoch": 0.77, + "learning_rate": 2.6213048434856846e-06, + "loss": 0.4626, + "step": 9218 + }, + { + "epoch": 0.77, + "learning_rate": 2.61947608209877e-06, + "loss": 0.4592, + "step": 9219 + }, + { + "epoch": 0.77, + "learning_rate": 2.6176478627068324e-06, + "loss": 0.5004, + "step": 9220 + }, + { + "epoch": 0.77, + "learning_rate": 2.615820185444128e-06, + "loss": 0.488, + "step": 9221 + }, + { + "epoch": 0.77, + "learning_rate": 2.6139930504448785e-06, + "loss": 0.4704, + "step": 9222 + }, + { + "epoch": 0.77, + "learning_rate": 2.6121664578432593e-06, + "loss": 0.4755, + "step": 9223 + }, + { + "epoch": 0.77, + "learning_rate": 2.6103404077734075e-06, + "loss": 0.4581, + "step": 9224 + }, + { + "epoch": 0.77, + "learning_rate": 2.60851490036942e-06, + "loss": 0.4553, + "step": 9225 + }, + { + "epoch": 0.77, + "learning_rate": 2.606689935765351e-06, + "loss": 0.4777, + "step": 9226 + }, + { + "epoch": 0.77, + "learning_rate": 2.604865514095225e-06, + "loss": 0.4676, + "step": 9227 + }, + { + "epoch": 0.77, + "learning_rate": 2.6030416354930154e-06, + "loss": 0.4463, + "step": 9228 + }, + { + "epoch": 0.77, + "learning_rate": 2.6012183000926638e-06, + "loss": 0.4546, + "step": 9229 + }, + { + "epoch": 0.77, + "learning_rate": 2.5993955080280663e-06, + "loss": 0.483, + "step": 9230 + }, + { + "epoch": 0.77, + "learning_rate": 2.5975732594330816e-06, + "loss": 0.4715, + "step": 9231 + }, + { + "epoch": 0.77, + "learning_rate": 2.595751554441527e-06, + "loss": 0.4556, + "step": 9232 + }, + { + "epoch": 0.77, + "learning_rate": 2.5939303931871827e-06, + "loss": 0.4788, + "step": 9233 + }, + { + "epoch": 0.77, + "learning_rate": 2.592109775803785e-06, + "loss": 0.4724, + "step": 9234 + }, + { + "epoch": 0.77, + "learning_rate": 2.590289702425032e-06, + "loss": 0.4611, + "step": 9235 + }, + { + "epoch": 0.77, + "learning_rate": 2.5884701731845862e-06, + "loss": 0.4714, + "step": 9236 + }, + { + "epoch": 0.77, + "learning_rate": 2.5866511882160604e-06, + "loss": 0.4642, + "step": 9237 + }, + { + "epoch": 0.77, + "learning_rate": 2.584832747653041e-06, + "loss": 0.4718, + "step": 9238 + }, + { + "epoch": 0.77, + "learning_rate": 2.583014851629062e-06, + "loss": 0.4696, + "step": 9239 + }, + { + "epoch": 0.77, + "learning_rate": 2.5811975002776233e-06, + "loss": 0.4488, + "step": 9240 + }, + { + "epoch": 0.77, + "learning_rate": 2.579380693732183e-06, + "loss": 0.4678, + "step": 9241 + }, + { + "epoch": 0.77, + "learning_rate": 2.577564432126156e-06, + "loss": 0.4598, + "step": 9242 + }, + { + "epoch": 0.77, + "learning_rate": 2.5757487155929285e-06, + "loss": 0.482, + "step": 9243 + }, + { + "epoch": 0.77, + "learning_rate": 2.573933544265835e-06, + "loss": 0.4572, + "step": 9244 + }, + { + "epoch": 0.77, + "learning_rate": 2.572118918278176e-06, + "loss": 0.4634, + "step": 9245 + }, + { + "epoch": 0.77, + "learning_rate": 2.570304837763208e-06, + "loss": 0.4784, + "step": 9246 + }, + { + "epoch": 0.77, + "learning_rate": 2.568491302854147e-06, + "loss": 0.458, + "step": 9247 + }, + { + "epoch": 0.77, + "learning_rate": 2.5666783136841777e-06, + "loss": 0.4777, + "step": 9248 + }, + { + "epoch": 0.77, + "learning_rate": 2.564865870386433e-06, + "loss": 0.4558, + "step": 9249 + }, + { + "epoch": 0.77, + "learning_rate": 2.5630539730940163e-06, + "loss": 0.4666, + "step": 9250 + }, + { + "epoch": 0.77, + "learning_rate": 2.5612426219399834e-06, + "loss": 0.4487, + "step": 9251 + }, + { + "epoch": 0.77, + "learning_rate": 2.5594318170573527e-06, + "loss": 0.4581, + "step": 9252 + }, + { + "epoch": 0.77, + "learning_rate": 2.5576215585791007e-06, + "loss": 0.4659, + "step": 9253 + }, + { + "epoch": 0.77, + "learning_rate": 2.5558118466381675e-06, + "loss": 0.4502, + "step": 9254 + }, + { + "epoch": 0.77, + "learning_rate": 2.5540026813674458e-06, + "loss": 0.4941, + "step": 9255 + }, + { + "epoch": 0.77, + "learning_rate": 2.5521940628998e-06, + "loss": 0.4728, + "step": 9256 + }, + { + "epoch": 0.77, + "learning_rate": 2.550385991368044e-06, + "loss": 0.4579, + "step": 9257 + }, + { + "epoch": 0.77, + "learning_rate": 2.548578466904953e-06, + "loss": 0.4819, + "step": 9258 + }, + { + "epoch": 0.77, + "learning_rate": 2.5467714896432704e-06, + "loss": 0.4623, + "step": 9259 + }, + { + "epoch": 0.77, + "learning_rate": 2.5449650597156884e-06, + "loss": 0.4512, + "step": 9260 + }, + { + "epoch": 0.77, + "learning_rate": 2.5431591772548647e-06, + "loss": 0.469, + "step": 9261 + }, + { + "epoch": 0.77, + "learning_rate": 2.5413538423934125e-06, + "loss": 0.4628, + "step": 9262 + }, + { + "epoch": 0.77, + "learning_rate": 2.5395490552639145e-06, + "loss": 0.4641, + "step": 9263 + }, + { + "epoch": 0.78, + "learning_rate": 2.5377448159989037e-06, + "loss": 0.458, + "step": 9264 + }, + { + "epoch": 0.78, + "learning_rate": 2.5359411247308753e-06, + "loss": 0.4823, + "step": 9265 + }, + { + "epoch": 0.78, + "learning_rate": 2.5341379815922853e-06, + "loss": 0.467, + "step": 9266 + }, + { + "epoch": 0.78, + "learning_rate": 2.5323353867155465e-06, + "loss": 0.4686, + "step": 9267 + }, + { + "epoch": 0.78, + "learning_rate": 2.53053334023304e-06, + "loss": 0.4559, + "step": 9268 + }, + { + "epoch": 0.78, + "learning_rate": 2.5287318422770934e-06, + "loss": 0.4608, + "step": 9269 + }, + { + "epoch": 0.78, + "learning_rate": 2.5269308929800084e-06, + "loss": 0.4619, + "step": 9270 + }, + { + "epoch": 0.78, + "learning_rate": 2.525130492474035e-06, + "loss": 0.4805, + "step": 9271 + }, + { + "epoch": 0.78, + "learning_rate": 2.523330640891388e-06, + "loss": 0.4584, + "step": 9272 + }, + { + "epoch": 0.78, + "learning_rate": 2.5215313383642414e-06, + "loss": 0.4771, + "step": 9273 + }, + { + "epoch": 0.78, + "learning_rate": 2.519732585024729e-06, + "loss": 0.4555, + "step": 9274 + }, + { + "epoch": 0.78, + "learning_rate": 2.5179343810049418e-06, + "loss": 0.466, + "step": 9275 + }, + { + "epoch": 0.78, + "learning_rate": 2.5161367264369296e-06, + "loss": 0.4694, + "step": 9276 + }, + { + "epoch": 0.78, + "learning_rate": 2.5143396214527127e-06, + "loss": 0.4603, + "step": 9277 + }, + { + "epoch": 0.78, + "learning_rate": 2.5125430661842587e-06, + "loss": 0.4644, + "step": 9278 + }, + { + "epoch": 0.78, + "learning_rate": 2.5107470607634956e-06, + "loss": 0.4647, + "step": 9279 + }, + { + "epoch": 0.78, + "learning_rate": 2.5089516053223216e-06, + "loss": 0.4704, + "step": 9280 + }, + { + "epoch": 0.78, + "learning_rate": 2.5071566999925833e-06, + "loss": 0.4869, + "step": 9281 + }, + { + "epoch": 0.78, + "learning_rate": 2.5053623449060927e-06, + "loss": 0.4826, + "step": 9282 + }, + { + "epoch": 0.78, + "learning_rate": 2.5035685401946163e-06, + "loss": 0.4694, + "step": 9283 + }, + { + "epoch": 0.78, + "learning_rate": 2.5017752859898892e-06, + "loss": 0.4598, + "step": 9284 + }, + { + "epoch": 0.78, + "learning_rate": 2.499982582423597e-06, + "loss": 0.4522, + "step": 9285 + }, + { + "epoch": 0.78, + "learning_rate": 2.4981904296273884e-06, + "loss": 0.4609, + "step": 9286 + }, + { + "epoch": 0.78, + "learning_rate": 2.4963988277328733e-06, + "loss": 0.4702, + "step": 9287 + }, + { + "epoch": 0.78, + "learning_rate": 2.494607776871616e-06, + "loss": 0.4667, + "step": 9288 + }, + { + "epoch": 0.78, + "learning_rate": 2.492817277175148e-06, + "loss": 0.4737, + "step": 9289 + }, + { + "epoch": 0.78, + "learning_rate": 2.491027328774952e-06, + "loss": 0.4664, + "step": 9290 + }, + { + "epoch": 0.78, + "learning_rate": 2.4892379318024806e-06, + "loss": 0.4345, + "step": 9291 + }, + { + "epoch": 0.78, + "learning_rate": 2.4874490863891355e-06, + "loss": 0.4877, + "step": 9292 + }, + { + "epoch": 0.78, + "learning_rate": 2.485660792666281e-06, + "loss": 0.4726, + "step": 9293 + }, + { + "epoch": 0.78, + "learning_rate": 2.4838730507652455e-06, + "loss": 0.4508, + "step": 9294 + }, + { + "epoch": 0.78, + "learning_rate": 2.482085860817309e-06, + "loss": 0.4623, + "step": 9295 + }, + { + "epoch": 0.78, + "learning_rate": 2.480299222953716e-06, + "loss": 0.4561, + "step": 9296 + }, + { + "epoch": 0.78, + "learning_rate": 2.478513137305675e-06, + "loss": 0.4565, + "step": 9297 + }, + { + "epoch": 0.78, + "learning_rate": 2.4767276040043433e-06, + "loss": 0.4553, + "step": 9298 + }, + { + "epoch": 0.78, + "learning_rate": 2.4749426231808427e-06, + "loss": 0.4781, + "step": 9299 + }, + { + "epoch": 0.78, + "learning_rate": 2.4731581949662597e-06, + "loss": 0.4629, + "step": 9300 + }, + { + "epoch": 0.78, + "learning_rate": 2.4713743194916318e-06, + "loss": 0.4546, + "step": 9301 + }, + { + "epoch": 0.78, + "learning_rate": 2.4695909968879607e-06, + "loss": 0.466, + "step": 9302 + }, + { + "epoch": 0.78, + "learning_rate": 2.4678082272862025e-06, + "loss": 0.4552, + "step": 9303 + }, + { + "epoch": 0.78, + "learning_rate": 2.4660260108172816e-06, + "loss": 0.4513, + "step": 9304 + }, + { + "epoch": 0.78, + "learning_rate": 2.4642443476120746e-06, + "loss": 0.4539, + "step": 9305 + }, + { + "epoch": 0.78, + "learning_rate": 2.462463237801419e-06, + "loss": 0.4682, + "step": 9306 + }, + { + "epoch": 0.78, + "learning_rate": 2.460682681516112e-06, + "loss": 0.453, + "step": 9307 + }, + { + "epoch": 0.78, + "learning_rate": 2.4589026788869117e-06, + "loss": 0.4768, + "step": 9308 + }, + { + "epoch": 0.78, + "learning_rate": 2.4571232300445293e-06, + "loss": 0.4839, + "step": 9309 + }, + { + "epoch": 0.78, + "learning_rate": 2.4553443351196426e-06, + "loss": 0.4596, + "step": 9310 + }, + { + "epoch": 0.78, + "learning_rate": 2.453565994242891e-06, + "loss": 0.4595, + "step": 9311 + }, + { + "epoch": 0.78, + "learning_rate": 2.4517882075448663e-06, + "loss": 0.4475, + "step": 9312 + }, + { + "epoch": 0.78, + "learning_rate": 2.4500109751561187e-06, + "loss": 0.4539, + "step": 9313 + }, + { + "epoch": 0.78, + "learning_rate": 2.4482342972071626e-06, + "loss": 0.4622, + "step": 9314 + }, + { + "epoch": 0.78, + "learning_rate": 2.44645817382847e-06, + "loss": 0.4861, + "step": 9315 + }, + { + "epoch": 0.78, + "learning_rate": 2.444682605150471e-06, + "loss": 0.4707, + "step": 9316 + }, + { + "epoch": 0.78, + "learning_rate": 2.442907591303554e-06, + "loss": 0.479, + "step": 9317 + }, + { + "epoch": 0.78, + "learning_rate": 2.441133132418073e-06, + "loss": 0.4697, + "step": 9318 + }, + { + "epoch": 0.78, + "learning_rate": 2.4393592286243363e-06, + "loss": 0.4657, + "step": 9319 + }, + { + "epoch": 0.78, + "learning_rate": 2.4375858800526077e-06, + "loss": 0.4666, + "step": 9320 + }, + { + "epoch": 0.78, + "learning_rate": 2.43581308683312e-06, + "loss": 0.4637, + "step": 9321 + }, + { + "epoch": 0.78, + "learning_rate": 2.4340408490960575e-06, + "loss": 0.4706, + "step": 9322 + }, + { + "epoch": 0.78, + "learning_rate": 2.432269166971567e-06, + "loss": 0.4753, + "step": 9323 + }, + { + "epoch": 0.78, + "learning_rate": 2.4304980405897483e-06, + "loss": 0.4751, + "step": 9324 + }, + { + "epoch": 0.78, + "learning_rate": 2.4287274700806727e-06, + "loss": 0.4541, + "step": 9325 + }, + { + "epoch": 0.78, + "learning_rate": 2.42695745557436e-06, + "loss": 0.4487, + "step": 9326 + }, + { + "epoch": 0.78, + "learning_rate": 2.4251879972007943e-06, + "loss": 0.4575, + "step": 9327 + }, + { + "epoch": 0.78, + "learning_rate": 2.423419095089915e-06, + "loss": 0.4677, + "step": 9328 + }, + { + "epoch": 0.78, + "learning_rate": 2.4216507493716213e-06, + "loss": 0.4627, + "step": 9329 + }, + { + "epoch": 0.78, + "learning_rate": 2.4198829601757787e-06, + "loss": 0.4684, + "step": 9330 + }, + { + "epoch": 0.78, + "learning_rate": 2.418115727632201e-06, + "loss": 0.4892, + "step": 9331 + }, + { + "epoch": 0.78, + "learning_rate": 2.4163490518706713e-06, + "loss": 0.4636, + "step": 9332 + }, + { + "epoch": 0.78, + "learning_rate": 2.414582933020924e-06, + "loss": 0.459, + "step": 9333 + }, + { + "epoch": 0.78, + "learning_rate": 2.412817371212657e-06, + "loss": 0.4632, + "step": 9334 + }, + { + "epoch": 0.78, + "learning_rate": 2.4110523665755236e-06, + "loss": 0.4559, + "step": 9335 + }, + { + "epoch": 0.78, + "learning_rate": 2.4092879192391406e-06, + "loss": 0.4697, + "step": 9336 + }, + { + "epoch": 0.78, + "learning_rate": 2.407524029333077e-06, + "loss": 0.4719, + "step": 9337 + }, + { + "epoch": 0.78, + "learning_rate": 2.405760696986873e-06, + "loss": 0.4609, + "step": 9338 + }, + { + "epoch": 0.78, + "learning_rate": 2.403997922330016e-06, + "loss": 0.4663, + "step": 9339 + }, + { + "epoch": 0.78, + "learning_rate": 2.4022357054919545e-06, + "loss": 0.4537, + "step": 9340 + }, + { + "epoch": 0.78, + "learning_rate": 2.4004740466021047e-06, + "loss": 0.4711, + "step": 9341 + }, + { + "epoch": 0.78, + "learning_rate": 2.398712945789832e-06, + "loss": 0.4591, + "step": 9342 + }, + { + "epoch": 0.78, + "learning_rate": 2.3969524031844638e-06, + "loss": 0.4759, + "step": 9343 + }, + { + "epoch": 0.78, + "learning_rate": 2.3951924189152854e-06, + "loss": 0.4557, + "step": 9344 + }, + { + "epoch": 0.78, + "learning_rate": 2.3934329931115474e-06, + "loss": 0.4759, + "step": 9345 + }, + { + "epoch": 0.78, + "learning_rate": 2.391674125902452e-06, + "loss": 0.4565, + "step": 9346 + }, + { + "epoch": 0.78, + "learning_rate": 2.3899158174171644e-06, + "loss": 0.4823, + "step": 9347 + }, + { + "epoch": 0.78, + "learning_rate": 2.388158067784806e-06, + "loss": 0.4724, + "step": 9348 + }, + { + "epoch": 0.78, + "learning_rate": 2.3864008771344595e-06, + "loss": 0.4682, + "step": 9349 + }, + { + "epoch": 0.78, + "learning_rate": 2.3846442455951612e-06, + "loss": 0.4776, + "step": 9350 + }, + { + "epoch": 0.78, + "learning_rate": 2.3828881732959163e-06, + "loss": 0.4587, + "step": 9351 + }, + { + "epoch": 0.78, + "learning_rate": 2.381132660365684e-06, + "loss": 0.4814, + "step": 9352 + }, + { + "epoch": 0.78, + "learning_rate": 2.37937770693338e-06, + "loss": 0.4737, + "step": 9353 + }, + { + "epoch": 0.78, + "learning_rate": 2.3776233131278805e-06, + "loss": 0.447, + "step": 9354 + }, + { + "epoch": 0.78, + "learning_rate": 2.3758694790780214e-06, + "loss": 0.4658, + "step": 9355 + }, + { + "epoch": 0.78, + "learning_rate": 2.3741162049125964e-06, + "loss": 0.4719, + "step": 9356 + }, + { + "epoch": 0.78, + "learning_rate": 2.372363490760359e-06, + "loss": 0.4448, + "step": 9357 + }, + { + "epoch": 0.78, + "learning_rate": 2.3706113367500183e-06, + "loss": 0.4582, + "step": 9358 + }, + { + "epoch": 0.78, + "learning_rate": 2.36885974301025e-06, + "loss": 0.4683, + "step": 9359 + }, + { + "epoch": 0.78, + "learning_rate": 2.367108709669683e-06, + "loss": 0.4571, + "step": 9360 + }, + { + "epoch": 0.78, + "learning_rate": 2.3653582368569017e-06, + "loss": 0.4503, + "step": 9361 + }, + { + "epoch": 0.78, + "learning_rate": 2.3636083247004592e-06, + "loss": 0.4537, + "step": 9362 + }, + { + "epoch": 0.78, + "learning_rate": 2.3618589733288588e-06, + "loss": 0.4668, + "step": 9363 + }, + { + "epoch": 0.78, + "learning_rate": 2.3601101828705664e-06, + "loss": 0.4526, + "step": 9364 + }, + { + "epoch": 0.78, + "learning_rate": 2.358361953454004e-06, + "loss": 0.478, + "step": 9365 + }, + { + "epoch": 0.78, + "learning_rate": 2.356614285207557e-06, + "loss": 0.4649, + "step": 9366 + }, + { + "epoch": 0.78, + "learning_rate": 2.3548671782595655e-06, + "loss": 0.4418, + "step": 9367 + }, + { + "epoch": 0.78, + "learning_rate": 2.3531206327383305e-06, + "loss": 0.4629, + "step": 9368 + }, + { + "epoch": 0.78, + "learning_rate": 2.35137464877211e-06, + "loss": 0.4576, + "step": 9369 + }, + { + "epoch": 0.78, + "learning_rate": 2.3496292264891194e-06, + "loss": 0.4573, + "step": 9370 + }, + { + "epoch": 0.78, + "learning_rate": 2.3478843660175423e-06, + "loss": 0.4696, + "step": 9371 + }, + { + "epoch": 0.78, + "learning_rate": 2.346140067485506e-06, + "loss": 0.4837, + "step": 9372 + }, + { + "epoch": 0.78, + "learning_rate": 2.3443963310211105e-06, + "loss": 0.476, + "step": 9373 + }, + { + "epoch": 0.78, + "learning_rate": 2.342653156752408e-06, + "loss": 0.4577, + "step": 9374 + }, + { + "epoch": 0.78, + "learning_rate": 2.3409105448074067e-06, + "loss": 0.4761, + "step": 9375 + }, + { + "epoch": 0.78, + "learning_rate": 2.339168495314079e-06, + "loss": 0.4755, + "step": 9376 + }, + { + "epoch": 0.78, + "learning_rate": 2.3374270084003535e-06, + "loss": 0.4652, + "step": 9377 + }, + { + "epoch": 0.78, + "learning_rate": 2.3356860841941152e-06, + "loss": 0.4781, + "step": 9378 + }, + { + "epoch": 0.78, + "learning_rate": 2.3339457228232142e-06, + "loss": 0.4703, + "step": 9379 + }, + { + "epoch": 0.78, + "learning_rate": 2.332205924415455e-06, + "loss": 0.4699, + "step": 9380 + }, + { + "epoch": 0.78, + "learning_rate": 2.330466689098596e-06, + "loss": 0.4769, + "step": 9381 + }, + { + "epoch": 0.78, + "learning_rate": 2.328728017000367e-06, + "loss": 0.47, + "step": 9382 + }, + { + "epoch": 0.79, + "learning_rate": 2.3269899082484447e-06, + "loss": 0.4821, + "step": 9383 + }, + { + "epoch": 0.79, + "learning_rate": 2.325252362970469e-06, + "loss": 0.4785, + "step": 9384 + }, + { + "epoch": 0.79, + "learning_rate": 2.3235153812940357e-06, + "loss": 0.4489, + "step": 9385 + }, + { + "epoch": 0.79, + "learning_rate": 2.321778963346707e-06, + "loss": 0.4619, + "step": 9386 + }, + { + "epoch": 0.79, + "learning_rate": 2.3200431092559948e-06, + "loss": 0.4659, + "step": 9387 + }, + { + "epoch": 0.79, + "learning_rate": 2.3183078191493734e-06, + "loss": 0.4701, + "step": 9388 + }, + { + "epoch": 0.79, + "learning_rate": 2.3165730931542753e-06, + "loss": 0.4658, + "step": 9389 + }, + { + "epoch": 0.79, + "learning_rate": 2.3148389313980912e-06, + "loss": 0.4866, + "step": 9390 + }, + { + "epoch": 0.79, + "learning_rate": 2.3131053340081675e-06, + "loss": 0.4773, + "step": 9391 + }, + { + "epoch": 0.79, + "learning_rate": 2.3113723011118196e-06, + "loss": 0.4558, + "step": 9392 + }, + { + "epoch": 0.79, + "learning_rate": 2.3096398328363078e-06, + "loss": 0.4641, + "step": 9393 + }, + { + "epoch": 0.79, + "learning_rate": 2.3079079293088623e-06, + "loss": 0.4733, + "step": 9394 + }, + { + "epoch": 0.79, + "learning_rate": 2.3061765906566644e-06, + "loss": 0.4505, + "step": 9395 + }, + { + "epoch": 0.79, + "learning_rate": 2.304445817006857e-06, + "loss": 0.4527, + "step": 9396 + }, + { + "epoch": 0.79, + "learning_rate": 2.302715608486541e-06, + "loss": 0.4698, + "step": 9397 + }, + { + "epoch": 0.79, + "learning_rate": 2.300985965222775e-06, + "loss": 0.4587, + "step": 9398 + }, + { + "epoch": 0.79, + "learning_rate": 2.2992568873425746e-06, + "loss": 0.4571, + "step": 9399 + }, + { + "epoch": 0.79, + "learning_rate": 2.2975283749729205e-06, + "loss": 0.4801, + "step": 9400 + }, + { + "epoch": 0.79, + "learning_rate": 2.2958004282407466e-06, + "loss": 0.464, + "step": 9401 + }, + { + "epoch": 0.79, + "learning_rate": 2.2940730472729423e-06, + "loss": 0.4576, + "step": 9402 + }, + { + "epoch": 0.79, + "learning_rate": 2.292346232196364e-06, + "loss": 0.468, + "step": 9403 + }, + { + "epoch": 0.79, + "learning_rate": 2.2906199831378194e-06, + "loss": 0.4632, + "step": 9404 + }, + { + "epoch": 0.79, + "learning_rate": 2.288894300224076e-06, + "loss": 0.4746, + "step": 9405 + }, + { + "epoch": 0.79, + "learning_rate": 2.2871691835818642e-06, + "loss": 0.4696, + "step": 9406 + }, + { + "epoch": 0.79, + "learning_rate": 2.285444633337869e-06, + "loss": 0.4789, + "step": 9407 + }, + { + "epoch": 0.79, + "learning_rate": 2.2837206496187314e-06, + "loss": 0.4654, + "step": 9408 + }, + { + "epoch": 0.79, + "learning_rate": 2.281997232551055e-06, + "loss": 0.4687, + "step": 9409 + }, + { + "epoch": 0.79, + "learning_rate": 2.2802743822614003e-06, + "loss": 0.4548, + "step": 9410 + }, + { + "epoch": 0.79, + "learning_rate": 2.2785520988762833e-06, + "loss": 0.4527, + "step": 9411 + }, + { + "epoch": 0.79, + "learning_rate": 2.276830382522187e-06, + "loss": 0.4528, + "step": 9412 + }, + { + "epoch": 0.79, + "learning_rate": 2.275109233325542e-06, + "loss": 0.4684, + "step": 9413 + }, + { + "epoch": 0.79, + "learning_rate": 2.2733886514127466e-06, + "loss": 0.4661, + "step": 9414 + }, + { + "epoch": 0.79, + "learning_rate": 2.2716686369101525e-06, + "loss": 0.4706, + "step": 9415 + }, + { + "epoch": 0.79, + "learning_rate": 2.2699491899440683e-06, + "loss": 0.4721, + "step": 9416 + }, + { + "epoch": 0.79, + "learning_rate": 2.2682303106407645e-06, + "loss": 0.4519, + "step": 9417 + }, + { + "epoch": 0.79, + "learning_rate": 2.2665119991264673e-06, + "loss": 0.4758, + "step": 9418 + }, + { + "epoch": 0.79, + "learning_rate": 2.2647942555273592e-06, + "loss": 0.4432, + "step": 9419 + }, + { + "epoch": 0.79, + "learning_rate": 2.2630770799695922e-06, + "loss": 0.4654, + "step": 9420 + }, + { + "epoch": 0.79, + "learning_rate": 2.2613604725792636e-06, + "loss": 0.4654, + "step": 9421 + }, + { + "epoch": 0.79, + "learning_rate": 2.259644433482434e-06, + "loss": 0.4582, + "step": 9422 + }, + { + "epoch": 0.79, + "learning_rate": 2.2579289628051203e-06, + "loss": 0.4455, + "step": 9423 + }, + { + "epoch": 0.79, + "learning_rate": 2.256214060673305e-06, + "loss": 0.4711, + "step": 9424 + }, + { + "epoch": 0.79, + "learning_rate": 2.2544997272129197e-06, + "loss": 0.4694, + "step": 9425 + }, + { + "epoch": 0.79, + "learning_rate": 2.252785962549856e-06, + "loss": 0.4452, + "step": 9426 + }, + { + "epoch": 0.79, + "learning_rate": 2.2510727668099706e-06, + "loss": 0.4767, + "step": 9427 + }, + { + "epoch": 0.79, + "learning_rate": 2.2493601401190723e-06, + "loss": 0.4607, + "step": 9428 + }, + { + "epoch": 0.79, + "learning_rate": 2.247648082602927e-06, + "loss": 0.4478, + "step": 9429 + }, + { + "epoch": 0.79, + "learning_rate": 2.2459365943872613e-06, + "loss": 0.4754, + "step": 9430 + }, + { + "epoch": 0.79, + "learning_rate": 2.244225675597761e-06, + "loss": 0.4856, + "step": 9431 + }, + { + "epoch": 0.79, + "learning_rate": 2.242515326360066e-06, + "loss": 0.4694, + "step": 9432 + }, + { + "epoch": 0.79, + "learning_rate": 2.2408055467997823e-06, + "loss": 0.4513, + "step": 9433 + }, + { + "epoch": 0.79, + "learning_rate": 2.2390963370424635e-06, + "loss": 0.4721, + "step": 9434 + }, + { + "epoch": 0.79, + "learning_rate": 2.237387697213632e-06, + "loss": 0.4726, + "step": 9435 + }, + { + "epoch": 0.79, + "learning_rate": 2.2356796274387617e-06, + "loss": 0.4632, + "step": 9436 + }, + { + "epoch": 0.79, + "learning_rate": 2.2339721278432847e-06, + "loss": 0.4877, + "step": 9437 + }, + { + "epoch": 0.79, + "learning_rate": 2.2322651985525932e-06, + "loss": 0.4796, + "step": 9438 + }, + { + "epoch": 0.79, + "learning_rate": 2.2305588396920375e-06, + "loss": 0.4482, + "step": 9439 + }, + { + "epoch": 0.79, + "learning_rate": 2.228853051386922e-06, + "loss": 0.4621, + "step": 9440 + }, + { + "epoch": 0.79, + "learning_rate": 2.22714783376252e-06, + "loss": 0.4697, + "step": 9441 + }, + { + "epoch": 0.79, + "learning_rate": 2.2254431869440496e-06, + "loss": 0.4766, + "step": 9442 + }, + { + "epoch": 0.79, + "learning_rate": 2.223739111056692e-06, + "loss": 0.4686, + "step": 9443 + }, + { + "epoch": 0.79, + "learning_rate": 2.222035606225593e-06, + "loss": 0.46, + "step": 9444 + }, + { + "epoch": 0.79, + "learning_rate": 2.220332672575849e-06, + "loss": 0.4642, + "step": 9445 + }, + { + "epoch": 0.79, + "learning_rate": 2.2186303102325125e-06, + "loss": 0.4591, + "step": 9446 + }, + { + "epoch": 0.79, + "learning_rate": 2.2169285193206038e-06, + "loss": 0.4726, + "step": 9447 + }, + { + "epoch": 0.79, + "learning_rate": 2.2152272999650916e-06, + "loss": 0.4684, + "step": 9448 + }, + { + "epoch": 0.79, + "learning_rate": 2.2135266522909073e-06, + "loss": 0.491, + "step": 9449 + }, + { + "epoch": 0.79, + "learning_rate": 2.2118265764229396e-06, + "loss": 0.4728, + "step": 9450 + }, + { + "epoch": 0.79, + "learning_rate": 2.2101270724860345e-06, + "loss": 0.4598, + "step": 9451 + }, + { + "epoch": 0.79, + "learning_rate": 2.2084281406049966e-06, + "loss": 0.4708, + "step": 9452 + }, + { + "epoch": 0.79, + "learning_rate": 2.2067297809045863e-06, + "loss": 0.4778, + "step": 9453 + }, + { + "epoch": 0.79, + "learning_rate": 2.2050319935095254e-06, + "loss": 0.4637, + "step": 9454 + }, + { + "epoch": 0.79, + "learning_rate": 2.203334778544497e-06, + "loss": 0.4553, + "step": 9455 + }, + { + "epoch": 0.79, + "learning_rate": 2.201638136134132e-06, + "loss": 0.4488, + "step": 9456 + }, + { + "epoch": 0.79, + "learning_rate": 2.199942066403028e-06, + "loss": 0.4643, + "step": 9457 + }, + { + "epoch": 0.79, + "learning_rate": 2.198246569475735e-06, + "loss": 0.4453, + "step": 9458 + }, + { + "epoch": 0.79, + "learning_rate": 2.1965516454767645e-06, + "loss": 0.4703, + "step": 9459 + }, + { + "epoch": 0.79, + "learning_rate": 2.1948572945305813e-06, + "loss": 0.4579, + "step": 9460 + }, + { + "epoch": 0.79, + "learning_rate": 2.193163516761617e-06, + "loss": 0.4486, + "step": 9461 + }, + { + "epoch": 0.79, + "learning_rate": 2.1914703122942525e-06, + "loss": 0.4719, + "step": 9462 + }, + { + "epoch": 0.79, + "learning_rate": 2.1897776812528317e-06, + "loss": 0.4651, + "step": 9463 + }, + { + "epoch": 0.79, + "learning_rate": 2.188085623761649e-06, + "loss": 0.4757, + "step": 9464 + }, + { + "epoch": 0.79, + "learning_rate": 2.1863941399449685e-06, + "loss": 0.4875, + "step": 9465 + }, + { + "epoch": 0.79, + "learning_rate": 2.1847032299270032e-06, + "loss": 0.4704, + "step": 9466 + }, + { + "epoch": 0.79, + "learning_rate": 2.1830128938319238e-06, + "loss": 0.455, + "step": 9467 + }, + { + "epoch": 0.79, + "learning_rate": 2.1813231317838667e-06, + "loss": 0.4656, + "step": 9468 + }, + { + "epoch": 0.79, + "learning_rate": 2.179633943906918e-06, + "loss": 0.454, + "step": 9469 + }, + { + "epoch": 0.79, + "learning_rate": 2.1779453303251262e-06, + "loss": 0.4647, + "step": 9470 + }, + { + "epoch": 0.79, + "learning_rate": 2.176257291162495e-06, + "loss": 0.4512, + "step": 9471 + }, + { + "epoch": 0.79, + "learning_rate": 2.174569826542986e-06, + "loss": 0.473, + "step": 9472 + }, + { + "epoch": 0.79, + "learning_rate": 2.172882936590518e-06, + "loss": 0.4463, + "step": 9473 + }, + { + "epoch": 0.79, + "learning_rate": 2.1711966214289747e-06, + "loss": 0.4627, + "step": 9474 + }, + { + "epoch": 0.79, + "learning_rate": 2.1695108811821863e-06, + "loss": 0.4592, + "step": 9475 + }, + { + "epoch": 0.79, + "learning_rate": 2.1678257159739524e-06, + "loss": 0.4872, + "step": 9476 + }, + { + "epoch": 0.79, + "learning_rate": 2.1661411259280206e-06, + "loss": 0.4719, + "step": 9477 + }, + { + "epoch": 0.79, + "learning_rate": 2.1644571111681023e-06, + "loss": 0.4569, + "step": 9478 + }, + { + "epoch": 0.79, + "learning_rate": 2.1627736718178626e-06, + "loss": 0.4524, + "step": 9479 + }, + { + "epoch": 0.79, + "learning_rate": 2.161090808000924e-06, + "loss": 0.4584, + "step": 9480 + }, + { + "epoch": 0.79, + "learning_rate": 2.1594085198408756e-06, + "loss": 0.4599, + "step": 9481 + }, + { + "epoch": 0.79, + "learning_rate": 2.1577268074612535e-06, + "loss": 0.4763, + "step": 9482 + }, + { + "epoch": 0.79, + "learning_rate": 2.156045670985556e-06, + "loss": 0.4584, + "step": 9483 + }, + { + "epoch": 0.79, + "learning_rate": 2.1543651105372352e-06, + "loss": 0.4735, + "step": 9484 + }, + { + "epoch": 0.79, + "learning_rate": 2.152685126239713e-06, + "loss": 0.4688, + "step": 9485 + }, + { + "epoch": 0.79, + "learning_rate": 2.1510057182163547e-06, + "loss": 0.4492, + "step": 9486 + }, + { + "epoch": 0.79, + "learning_rate": 2.1493268865904872e-06, + "loss": 0.4916, + "step": 9487 + }, + { + "epoch": 0.79, + "learning_rate": 2.1476486314854027e-06, + "loss": 0.4659, + "step": 9488 + }, + { + "epoch": 0.79, + "learning_rate": 2.1459709530243423e-06, + "loss": 0.4438, + "step": 9489 + }, + { + "epoch": 0.79, + "learning_rate": 2.144293851330508e-06, + "loss": 0.4826, + "step": 9490 + }, + { + "epoch": 0.79, + "learning_rate": 2.1426173265270578e-06, + "loss": 0.4829, + "step": 9491 + }, + { + "epoch": 0.79, + "learning_rate": 2.1409413787371114e-06, + "loss": 0.4722, + "step": 9492 + }, + { + "epoch": 0.79, + "learning_rate": 2.13926600808374e-06, + "loss": 0.4796, + "step": 9493 + }, + { + "epoch": 0.79, + "learning_rate": 2.1375912146899767e-06, + "loss": 0.4647, + "step": 9494 + }, + { + "epoch": 0.79, + "learning_rate": 2.135916998678812e-06, + "loss": 0.4497, + "step": 9495 + }, + { + "epoch": 0.79, + "learning_rate": 2.134243360173196e-06, + "loss": 0.4972, + "step": 9496 + }, + { + "epoch": 0.79, + "learning_rate": 2.1325702992960317e-06, + "loss": 0.4788, + "step": 9497 + }, + { + "epoch": 0.79, + "learning_rate": 2.130897816170181e-06, + "loss": 0.4516, + "step": 9498 + }, + { + "epoch": 0.79, + "learning_rate": 2.1292259109184654e-06, + "loss": 0.4556, + "step": 9499 + }, + { + "epoch": 0.79, + "learning_rate": 2.1275545836636625e-06, + "loss": 0.4519, + "step": 9500 + }, + { + "epoch": 0.79, + "learning_rate": 2.1258838345285027e-06, + "loss": 0.4905, + "step": 9501 + }, + { + "epoch": 0.79, + "learning_rate": 2.124213663635687e-06, + "loss": 0.4682, + "step": 9502 + }, + { + "epoch": 0.8, + "learning_rate": 2.1225440711078615e-06, + "loss": 0.4862, + "step": 9503 + }, + { + "epoch": 0.8, + "learning_rate": 2.120875057067635e-06, + "loss": 0.4761, + "step": 9504 + }, + { + "epoch": 0.8, + "learning_rate": 2.1192066216375695e-06, + "loss": 0.4625, + "step": 9505 + }, + { + "epoch": 0.8, + "learning_rate": 2.1175387649401935e-06, + "loss": 0.4456, + "step": 9506 + }, + { + "epoch": 0.8, + "learning_rate": 2.1158714870979856e-06, + "loss": 0.4596, + "step": 9507 + }, + { + "epoch": 0.8, + "learning_rate": 2.114204788233379e-06, + "loss": 0.4775, + "step": 9508 + }, + { + "epoch": 0.8, + "learning_rate": 2.1125386684687774e-06, + "loss": 0.4652, + "step": 9509 + }, + { + "epoch": 0.8, + "learning_rate": 2.110873127926529e-06, + "loss": 0.4516, + "step": 9510 + }, + { + "epoch": 0.8, + "learning_rate": 2.1092081667289454e-06, + "loss": 0.4667, + "step": 9511 + }, + { + "epoch": 0.8, + "learning_rate": 2.1075437849982937e-06, + "loss": 0.4646, + "step": 9512 + }, + { + "epoch": 0.8, + "learning_rate": 2.105879982856799e-06, + "loss": 0.473, + "step": 9513 + }, + { + "epoch": 0.8, + "learning_rate": 2.1042167604266415e-06, + "loss": 0.4532, + "step": 9514 + }, + { + "epoch": 0.8, + "learning_rate": 2.102554117829967e-06, + "loss": 0.4778, + "step": 9515 + }, + { + "epoch": 0.8, + "learning_rate": 2.100892055188867e-06, + "loss": 0.4789, + "step": 9516 + }, + { + "epoch": 0.8, + "learning_rate": 2.0992305726254026e-06, + "loss": 0.4668, + "step": 9517 + }, + { + "epoch": 0.8, + "learning_rate": 2.0975696702615823e-06, + "loss": 0.483, + "step": 9518 + }, + { + "epoch": 0.8, + "learning_rate": 2.0959093482193783e-06, + "loss": 0.4624, + "step": 9519 + }, + { + "epoch": 0.8, + "learning_rate": 2.094249606620715e-06, + "loss": 0.4581, + "step": 9520 + }, + { + "epoch": 0.8, + "learning_rate": 2.092590445587476e-06, + "loss": 0.4768, + "step": 9521 + }, + { + "epoch": 0.8, + "learning_rate": 2.0909318652415078e-06, + "loss": 0.4691, + "step": 9522 + }, + { + "epoch": 0.8, + "learning_rate": 2.0892738657046065e-06, + "loss": 0.4657, + "step": 9523 + }, + { + "epoch": 0.8, + "learning_rate": 2.0876164470985305e-06, + "loss": 0.4549, + "step": 9524 + }, + { + "epoch": 0.8, + "learning_rate": 2.0859596095449886e-06, + "loss": 0.4605, + "step": 9525 + }, + { + "epoch": 0.8, + "learning_rate": 2.0843033531656596e-06, + "loss": 0.4536, + "step": 9526 + }, + { + "epoch": 0.8, + "learning_rate": 2.0826476780821683e-06, + "loss": 0.4656, + "step": 9527 + }, + { + "epoch": 0.8, + "learning_rate": 2.080992584416097e-06, + "loss": 0.4637, + "step": 9528 + }, + { + "epoch": 0.8, + "learning_rate": 2.079338072288997e-06, + "loss": 0.4756, + "step": 9529 + }, + { + "epoch": 0.8, + "learning_rate": 2.0776841418223635e-06, + "loss": 0.4659, + "step": 9530 + }, + { + "epoch": 0.8, + "learning_rate": 2.0760307931376555e-06, + "loss": 0.4654, + "step": 9531 + }, + { + "epoch": 0.8, + "learning_rate": 2.0743780263562884e-06, + "loss": 0.4624, + "step": 9532 + }, + { + "epoch": 0.8, + "learning_rate": 2.0727258415996334e-06, + "loss": 0.4591, + "step": 9533 + }, + { + "epoch": 0.8, + "learning_rate": 2.0710742389890205e-06, + "loss": 0.4664, + "step": 9534 + }, + { + "epoch": 0.8, + "learning_rate": 2.069423218645734e-06, + "loss": 0.4513, + "step": 9535 + }, + { + "epoch": 0.8, + "learning_rate": 2.067772780691023e-06, + "loss": 0.4584, + "step": 9536 + }, + { + "epoch": 0.8, + "learning_rate": 2.0661229252460835e-06, + "loss": 0.4804, + "step": 9537 + }, + { + "epoch": 0.8, + "learning_rate": 2.064473652432081e-06, + "loss": 0.4685, + "step": 9538 + }, + { + "epoch": 0.8, + "learning_rate": 2.0628249623701255e-06, + "loss": 0.457, + "step": 9539 + }, + { + "epoch": 0.8, + "learning_rate": 2.061176855181293e-06, + "loss": 0.4696, + "step": 9540 + }, + { + "epoch": 0.8, + "learning_rate": 2.0595293309866107e-06, + "loss": 0.4725, + "step": 9541 + }, + { + "epoch": 0.8, + "learning_rate": 2.0578823899070653e-06, + "loss": 0.4579, + "step": 9542 + }, + { + "epoch": 0.8, + "learning_rate": 2.0562360320636064e-06, + "loss": 0.4803, + "step": 9543 + }, + { + "epoch": 0.8, + "learning_rate": 2.0545902575771326e-06, + "loss": 0.4821, + "step": 9544 + }, + { + "epoch": 0.8, + "learning_rate": 2.0529450665685023e-06, + "loss": 0.4638, + "step": 9545 + }, + { + "epoch": 0.8, + "learning_rate": 2.0513004591585305e-06, + "loss": 0.4593, + "step": 9546 + }, + { + "epoch": 0.8, + "learning_rate": 2.049656435467994e-06, + "loss": 0.473, + "step": 9547 + }, + { + "epoch": 0.8, + "learning_rate": 2.04801299561762e-06, + "loss": 0.4585, + "step": 9548 + }, + { + "epoch": 0.8, + "learning_rate": 2.0463701397280953e-06, + "loss": 0.4658, + "step": 9549 + }, + { + "epoch": 0.8, + "learning_rate": 2.0447278679200676e-06, + "loss": 0.4673, + "step": 9550 + }, + { + "epoch": 0.8, + "learning_rate": 2.0430861803141377e-06, + "loss": 0.4683, + "step": 9551 + }, + { + "epoch": 0.8, + "learning_rate": 2.0414450770308638e-06, + "loss": 0.4636, + "step": 9552 + }, + { + "epoch": 0.8, + "learning_rate": 2.03980455819076e-06, + "loss": 0.4777, + "step": 9553 + }, + { + "epoch": 0.8, + "learning_rate": 2.0381646239143017e-06, + "loss": 0.453, + "step": 9554 + }, + { + "epoch": 0.8, + "learning_rate": 2.0365252743219143e-06, + "loss": 0.4474, + "step": 9555 + }, + { + "epoch": 0.8, + "learning_rate": 2.034886509533991e-06, + "loss": 0.4671, + "step": 9556 + }, + { + "epoch": 0.8, + "learning_rate": 2.0332483296708693e-06, + "loss": 0.4719, + "step": 9557 + }, + { + "epoch": 0.8, + "learning_rate": 2.031610734852858e-06, + "loss": 0.4555, + "step": 9558 + }, + { + "epoch": 0.8, + "learning_rate": 2.029973725200212e-06, + "loss": 0.4698, + "step": 9559 + }, + { + "epoch": 0.8, + "learning_rate": 2.028337300833144e-06, + "loss": 0.4783, + "step": 9560 + }, + { + "epoch": 0.8, + "learning_rate": 2.0267014618718295e-06, + "loss": 0.4447, + "step": 9561 + }, + { + "epoch": 0.8, + "learning_rate": 2.0250662084363928e-06, + "loss": 0.4752, + "step": 9562 + }, + { + "epoch": 0.8, + "learning_rate": 2.023431540646926e-06, + "loss": 0.4757, + "step": 9563 + }, + { + "epoch": 0.8, + "learning_rate": 2.02179745862347e-06, + "loss": 0.4496, + "step": 9564 + }, + { + "epoch": 0.8, + "learning_rate": 2.0201639624860246e-06, + "loss": 0.4651, + "step": 9565 + }, + { + "epoch": 0.8, + "learning_rate": 2.0185310523545475e-06, + "loss": 0.4539, + "step": 9566 + }, + { + "epoch": 0.8, + "learning_rate": 2.0168987283489494e-06, + "loss": 0.4631, + "step": 9567 + }, + { + "epoch": 0.8, + "learning_rate": 2.0152669905891075e-06, + "loss": 0.4478, + "step": 9568 + }, + { + "epoch": 0.8, + "learning_rate": 2.013635839194844e-06, + "loss": 0.4758, + "step": 9569 + }, + { + "epoch": 0.8, + "learning_rate": 2.0120052742859497e-06, + "loss": 0.4786, + "step": 9570 + }, + { + "epoch": 0.8, + "learning_rate": 2.010375295982163e-06, + "loss": 0.4593, + "step": 9571 + }, + { + "epoch": 0.8, + "learning_rate": 2.0087459044031843e-06, + "loss": 0.466, + "step": 9572 + }, + { + "epoch": 0.8, + "learning_rate": 2.0071170996686674e-06, + "loss": 0.4639, + "step": 9573 + }, + { + "epoch": 0.8, + "learning_rate": 2.0054888818982254e-06, + "loss": 0.4788, + "step": 9574 + }, + { + "epoch": 0.8, + "learning_rate": 2.0038612512114285e-06, + "loss": 0.4549, + "step": 9575 + }, + { + "epoch": 0.8, + "learning_rate": 2.0022342077278014e-06, + "loss": 0.454, + "step": 9576 + }, + { + "epoch": 0.8, + "learning_rate": 2.00060775156683e-06, + "loss": 0.4759, + "step": 9577 + }, + { + "epoch": 0.8, + "learning_rate": 1.998981882847951e-06, + "loss": 0.4794, + "step": 9578 + }, + { + "epoch": 0.8, + "learning_rate": 1.9973566016905666e-06, + "loss": 0.4785, + "step": 9579 + }, + { + "epoch": 0.8, + "learning_rate": 1.995731908214028e-06, + "loss": 0.4464, + "step": 9580 + }, + { + "epoch": 0.8, + "learning_rate": 1.994107802537646e-06, + "loss": 0.4696, + "step": 9581 + }, + { + "epoch": 0.8, + "learning_rate": 1.9924842847806867e-06, + "loss": 0.4567, + "step": 9582 + }, + { + "epoch": 0.8, + "learning_rate": 1.9908613550623746e-06, + "loss": 0.4601, + "step": 9583 + }, + { + "epoch": 0.8, + "learning_rate": 1.9892390135018945e-06, + "loss": 0.4741, + "step": 9584 + }, + { + "epoch": 0.8, + "learning_rate": 1.987617260218382e-06, + "loss": 0.4543, + "step": 9585 + }, + { + "epoch": 0.8, + "learning_rate": 1.985996095330931e-06, + "loss": 0.4632, + "step": 9586 + }, + { + "epoch": 0.8, + "learning_rate": 1.984375518958592e-06, + "loss": 0.4491, + "step": 9587 + }, + { + "epoch": 0.8, + "learning_rate": 1.9827555312203785e-06, + "loss": 0.4767, + "step": 9588 + }, + { + "epoch": 0.8, + "learning_rate": 1.9811361322352517e-06, + "loss": 0.473, + "step": 9589 + }, + { + "epoch": 0.8, + "learning_rate": 1.9795173221221318e-06, + "loss": 0.4599, + "step": 9590 + }, + { + "epoch": 0.8, + "learning_rate": 1.9778991009999036e-06, + "loss": 0.482, + "step": 9591 + }, + { + "epoch": 0.8, + "learning_rate": 1.9762814689873987e-06, + "loss": 0.4809, + "step": 9592 + }, + { + "epoch": 0.8, + "learning_rate": 1.974664426203409e-06, + "loss": 0.4695, + "step": 9593 + }, + { + "epoch": 0.8, + "learning_rate": 1.973047972766684e-06, + "loss": 0.4676, + "step": 9594 + }, + { + "epoch": 0.8, + "learning_rate": 1.9714321087959296e-06, + "loss": 0.4593, + "step": 9595 + }, + { + "epoch": 0.8, + "learning_rate": 1.9698168344098056e-06, + "loss": 0.4615, + "step": 9596 + }, + { + "epoch": 0.8, + "learning_rate": 1.9682021497269357e-06, + "loss": 0.4768, + "step": 9597 + }, + { + "epoch": 0.8, + "learning_rate": 1.9665880548658888e-06, + "loss": 0.457, + "step": 9598 + }, + { + "epoch": 0.8, + "learning_rate": 1.9649745499452067e-06, + "loss": 0.4568, + "step": 9599 + }, + { + "epoch": 0.8, + "learning_rate": 1.9633616350833717e-06, + "loss": 0.4788, + "step": 9600 + }, + { + "epoch": 0.8, + "learning_rate": 1.961749310398833e-06, + "loss": 0.4911, + "step": 9601 + }, + { + "epoch": 0.8, + "learning_rate": 1.9601375760099895e-06, + "loss": 0.4736, + "step": 9602 + }, + { + "epoch": 0.8, + "learning_rate": 1.9585264320352003e-06, + "loss": 0.464, + "step": 9603 + }, + { + "epoch": 0.8, + "learning_rate": 1.9569158785927867e-06, + "loss": 0.4649, + "step": 9604 + }, + { + "epoch": 0.8, + "learning_rate": 1.955305915801016e-06, + "loss": 0.4484, + "step": 9605 + }, + { + "epoch": 0.8, + "learning_rate": 1.9536965437781186e-06, + "loss": 0.4635, + "step": 9606 + }, + { + "epoch": 0.8, + "learning_rate": 1.9520877626422794e-06, + "loss": 0.4572, + "step": 9607 + }, + { + "epoch": 0.8, + "learning_rate": 1.95047957251164e-06, + "loss": 0.4729, + "step": 9608 + }, + { + "epoch": 0.8, + "learning_rate": 1.9488719735043018e-06, + "loss": 0.4615, + "step": 9609 + }, + { + "epoch": 0.8, + "learning_rate": 1.9472649657383157e-06, + "loss": 0.4654, + "step": 9610 + }, + { + "epoch": 0.8, + "learning_rate": 1.9456585493317004e-06, + "loss": 0.4707, + "step": 9611 + }, + { + "epoch": 0.8, + "learning_rate": 1.94405272440242e-06, + "loss": 0.4773, + "step": 9612 + }, + { + "epoch": 0.8, + "learning_rate": 1.942447491068401e-06, + "loss": 0.4667, + "step": 9613 + }, + { + "epoch": 0.8, + "learning_rate": 1.940842849447524e-06, + "loss": 0.4603, + "step": 9614 + }, + { + "epoch": 0.8, + "learning_rate": 1.9392387996576277e-06, + "loss": 0.4447, + "step": 9615 + }, + { + "epoch": 0.8, + "learning_rate": 1.937635341816506e-06, + "loss": 0.4665, + "step": 9616 + }, + { + "epoch": 0.8, + "learning_rate": 1.9360324760419093e-06, + "loss": 0.4667, + "step": 9617 + }, + { + "epoch": 0.8, + "learning_rate": 1.934430202451549e-06, + "loss": 0.454, + "step": 9618 + }, + { + "epoch": 0.8, + "learning_rate": 1.9328285211630847e-06, + "loss": 0.4657, + "step": 9619 + }, + { + "epoch": 0.8, + "learning_rate": 1.9312274322941426e-06, + "loss": 0.4621, + "step": 9620 + }, + { + "epoch": 0.8, + "learning_rate": 1.9296269359622977e-06, + "loss": 0.457, + "step": 9621 + }, + { + "epoch": 0.81, + "learning_rate": 1.9280270322850836e-06, + "loss": 0.4572, + "step": 9622 + }, + { + "epoch": 0.81, + "learning_rate": 1.92642772137999e-06, + "loss": 0.4614, + "step": 9623 + }, + { + "epoch": 0.81, + "learning_rate": 1.9248290033644614e-06, + "loss": 0.4545, + "step": 9624 + }, + { + "epoch": 0.81, + "learning_rate": 1.9232308783559064e-06, + "loss": 0.4749, + "step": 9625 + }, + { + "epoch": 0.81, + "learning_rate": 1.9216333464716817e-06, + "loss": 0.4872, + "step": 9626 + }, + { + "epoch": 0.81, + "learning_rate": 1.9200364078291032e-06, + "loss": 0.4565, + "step": 9627 + }, + { + "epoch": 0.81, + "learning_rate": 1.9184400625454413e-06, + "loss": 0.4787, + "step": 9628 + }, + { + "epoch": 0.81, + "learning_rate": 1.916844310737931e-06, + "loss": 0.4553, + "step": 9629 + }, + { + "epoch": 0.81, + "learning_rate": 1.9152491525237504e-06, + "loss": 0.4542, + "step": 9630 + }, + { + "epoch": 0.81, + "learning_rate": 1.9136545880200484e-06, + "loss": 0.4756, + "step": 9631 + }, + { + "epoch": 0.81, + "learning_rate": 1.912060617343919e-06, + "loss": 0.4579, + "step": 9632 + }, + { + "epoch": 0.81, + "learning_rate": 1.910467240612419e-06, + "loss": 0.4656, + "step": 9633 + }, + { + "epoch": 0.81, + "learning_rate": 1.9088744579425567e-06, + "loss": 0.4556, + "step": 9634 + }, + { + "epoch": 0.81, + "learning_rate": 1.9072822694513016e-06, + "loss": 0.4717, + "step": 9635 + }, + { + "epoch": 0.81, + "learning_rate": 1.9056906752555759e-06, + "loss": 0.4633, + "step": 9636 + }, + { + "epoch": 0.81, + "learning_rate": 1.9040996754722574e-06, + "loss": 0.4566, + "step": 9637 + }, + { + "epoch": 0.81, + "learning_rate": 1.902509270218189e-06, + "loss": 0.4552, + "step": 9638 + }, + { + "epoch": 0.81, + "learning_rate": 1.9009194596101566e-06, + "loss": 0.4667, + "step": 9639 + }, + { + "epoch": 0.81, + "learning_rate": 1.8993302437649143e-06, + "loss": 0.4566, + "step": 9640 + }, + { + "epoch": 0.81, + "learning_rate": 1.8977416227991663e-06, + "loss": 0.4585, + "step": 9641 + }, + { + "epoch": 0.81, + "learning_rate": 1.896153596829574e-06, + "loss": 0.4518, + "step": 9642 + }, + { + "epoch": 0.81, + "learning_rate": 1.8945661659727555e-06, + "loss": 0.4677, + "step": 9643 + }, + { + "epoch": 0.81, + "learning_rate": 1.8929793303452814e-06, + "loss": 0.4731, + "step": 9644 + }, + { + "epoch": 0.81, + "learning_rate": 1.891393090063688e-06, + "loss": 0.4661, + "step": 9645 + }, + { + "epoch": 0.81, + "learning_rate": 1.8898074452444604e-06, + "loss": 0.4539, + "step": 9646 + }, + { + "epoch": 0.81, + "learning_rate": 1.8882223960040413e-06, + "loss": 0.4814, + "step": 9647 + }, + { + "epoch": 0.81, + "learning_rate": 1.8866379424588287e-06, + "loss": 0.4711, + "step": 9648 + }, + { + "epoch": 0.81, + "learning_rate": 1.8850540847251786e-06, + "loss": 0.4454, + "step": 9649 + }, + { + "epoch": 0.81, + "learning_rate": 1.8834708229194054e-06, + "loss": 0.4759, + "step": 9650 + }, + { + "epoch": 0.81, + "learning_rate": 1.8818881571577741e-06, + "loss": 0.4592, + "step": 9651 + }, + { + "epoch": 0.81, + "learning_rate": 1.8803060875565127e-06, + "loss": 0.4533, + "step": 9652 + }, + { + "epoch": 0.81, + "learning_rate": 1.8787246142318006e-06, + "loss": 0.484, + "step": 9653 + }, + { + "epoch": 0.81, + "learning_rate": 1.8771437372997736e-06, + "loss": 0.4713, + "step": 9654 + }, + { + "epoch": 0.81, + "learning_rate": 1.8755634568765246e-06, + "loss": 0.4474, + "step": 9655 + }, + { + "epoch": 0.81, + "learning_rate": 1.8739837730781029e-06, + "loss": 0.4372, + "step": 9656 + }, + { + "epoch": 0.81, + "learning_rate": 1.872404686020516e-06, + "loss": 0.4562, + "step": 9657 + }, + { + "epoch": 0.81, + "learning_rate": 1.8708261958197193e-06, + "loss": 0.4659, + "step": 9658 + }, + { + "epoch": 0.81, + "learning_rate": 1.8692483025916387e-06, + "loss": 0.4809, + "step": 9659 + }, + { + "epoch": 0.81, + "learning_rate": 1.8676710064521409e-06, + "loss": 0.4592, + "step": 9660 + }, + { + "epoch": 0.81, + "learning_rate": 1.8660943075170634e-06, + "loss": 0.4448, + "step": 9661 + }, + { + "epoch": 0.81, + "learning_rate": 1.864518205902187e-06, + "loss": 0.4631, + "step": 9662 + }, + { + "epoch": 0.81, + "learning_rate": 1.862942701723257e-06, + "loss": 0.4671, + "step": 9663 + }, + { + "epoch": 0.81, + "learning_rate": 1.8613677950959697e-06, + "loss": 0.4527, + "step": 9664 + }, + { + "epoch": 0.81, + "learning_rate": 1.8597934861359779e-06, + "loss": 0.4446, + "step": 9665 + }, + { + "epoch": 0.81, + "learning_rate": 1.858219774958897e-06, + "loss": 0.4743, + "step": 9666 + }, + { + "epoch": 0.81, + "learning_rate": 1.8566466616802914e-06, + "loss": 0.4744, + "step": 9667 + }, + { + "epoch": 0.81, + "learning_rate": 1.855074146415685e-06, + "loss": 0.4457, + "step": 9668 + }, + { + "epoch": 0.81, + "learning_rate": 1.8535022292805539e-06, + "loss": 0.4582, + "step": 9669 + }, + { + "epoch": 0.81, + "learning_rate": 1.851930910390337e-06, + "loss": 0.4666, + "step": 9670 + }, + { + "epoch": 0.81, + "learning_rate": 1.8503601898604207e-06, + "loss": 0.4709, + "step": 9671 + }, + { + "epoch": 0.81, + "learning_rate": 1.8487900678061588e-06, + "loss": 0.4568, + "step": 9672 + }, + { + "epoch": 0.81, + "learning_rate": 1.8472205443428504e-06, + "loss": 0.4638, + "step": 9673 + }, + { + "epoch": 0.81, + "learning_rate": 1.8456516195857543e-06, + "loss": 0.4657, + "step": 9674 + }, + { + "epoch": 0.81, + "learning_rate": 1.8440832936500875e-06, + "loss": 0.4578, + "step": 9675 + }, + { + "epoch": 0.81, + "learning_rate": 1.842515566651021e-06, + "loss": 0.4629, + "step": 9676 + }, + { + "epoch": 0.81, + "learning_rate": 1.8409484387036813e-06, + "loss": 0.4413, + "step": 9677 + }, + { + "epoch": 0.81, + "learning_rate": 1.8393819099231503e-06, + "loss": 0.4732, + "step": 9678 + }, + { + "epoch": 0.81, + "learning_rate": 1.837815980424471e-06, + "loss": 0.4708, + "step": 9679 + }, + { + "epoch": 0.81, + "learning_rate": 1.8362506503226374e-06, + "loss": 0.483, + "step": 9680 + }, + { + "epoch": 0.81, + "learning_rate": 1.8346859197325984e-06, + "loss": 0.4639, + "step": 9681 + }, + { + "epoch": 0.81, + "learning_rate": 1.8331217887692653e-06, + "loss": 0.4756, + "step": 9682 + }, + { + "epoch": 0.81, + "learning_rate": 1.8315582575475e-06, + "loss": 0.4638, + "step": 9683 + }, + { + "epoch": 0.81, + "learning_rate": 1.8299953261821202e-06, + "loss": 0.4641, + "step": 9684 + }, + { + "epoch": 0.81, + "learning_rate": 1.8284329947878999e-06, + "loss": 0.4882, + "step": 9685 + }, + { + "epoch": 0.81, + "learning_rate": 1.8268712634795749e-06, + "loss": 0.4464, + "step": 9686 + }, + { + "epoch": 0.81, + "learning_rate": 1.8253101323718303e-06, + "loss": 0.4501, + "step": 9687 + }, + { + "epoch": 0.81, + "learning_rate": 1.8237496015793077e-06, + "loss": 0.4642, + "step": 9688 + }, + { + "epoch": 0.81, + "learning_rate": 1.8221896712166075e-06, + "loss": 0.4618, + "step": 9689 + }, + { + "epoch": 0.81, + "learning_rate": 1.8206303413982806e-06, + "loss": 0.4548, + "step": 9690 + }, + { + "epoch": 0.81, + "learning_rate": 1.819071612238843e-06, + "loss": 0.4565, + "step": 9691 + }, + { + "epoch": 0.81, + "learning_rate": 1.8175134838527575e-06, + "loss": 0.4589, + "step": 9692 + }, + { + "epoch": 0.81, + "learning_rate": 1.8159559563544504e-06, + "loss": 0.4569, + "step": 9693 + }, + { + "epoch": 0.81, + "learning_rate": 1.814399029858298e-06, + "loss": 0.4753, + "step": 9694 + }, + { + "epoch": 0.81, + "learning_rate": 1.8128427044786345e-06, + "loss": 0.4571, + "step": 9695 + }, + { + "epoch": 0.81, + "learning_rate": 1.8112869803297494e-06, + "loss": 0.4539, + "step": 9696 + }, + { + "epoch": 0.81, + "learning_rate": 1.8097318575258894e-06, + "loss": 0.4814, + "step": 9697 + }, + { + "epoch": 0.81, + "learning_rate": 1.808177336181256e-06, + "loss": 0.4669, + "step": 9698 + }, + { + "epoch": 0.81, + "learning_rate": 1.8066234164100038e-06, + "loss": 0.4593, + "step": 9699 + }, + { + "epoch": 0.81, + "learning_rate": 1.8050700983262526e-06, + "loss": 0.4782, + "step": 9700 + }, + { + "epoch": 0.81, + "learning_rate": 1.8035173820440643e-06, + "loss": 0.4736, + "step": 9701 + }, + { + "epoch": 0.81, + "learning_rate": 1.8019652676774703e-06, + "loss": 0.4838, + "step": 9702 + }, + { + "epoch": 0.81, + "learning_rate": 1.8004137553404498e-06, + "loss": 0.4489, + "step": 9703 + }, + { + "epoch": 0.81, + "learning_rate": 1.798862845146938e-06, + "loss": 0.4896, + "step": 9704 + }, + { + "epoch": 0.81, + "learning_rate": 1.797312537210827e-06, + "loss": 0.4669, + "step": 9705 + }, + { + "epoch": 0.81, + "learning_rate": 1.795762831645964e-06, + "loss": 0.4614, + "step": 9706 + }, + { + "epoch": 0.81, + "learning_rate": 1.7942137285661576e-06, + "loss": 0.4606, + "step": 9707 + }, + { + "epoch": 0.81, + "learning_rate": 1.7926652280851642e-06, + "loss": 0.4639, + "step": 9708 + }, + { + "epoch": 0.81, + "learning_rate": 1.7911173303166985e-06, + "loss": 0.4593, + "step": 9709 + }, + { + "epoch": 0.81, + "learning_rate": 1.789570035374434e-06, + "loss": 0.4639, + "step": 9710 + }, + { + "epoch": 0.81, + "learning_rate": 1.7880233433719929e-06, + "loss": 0.4737, + "step": 9711 + }, + { + "epoch": 0.81, + "learning_rate": 1.7864772544229626e-06, + "loss": 0.4641, + "step": 9712 + }, + { + "epoch": 0.81, + "learning_rate": 1.7849317686408817e-06, + "loss": 0.4718, + "step": 9713 + }, + { + "epoch": 0.81, + "learning_rate": 1.7833868861392423e-06, + "loss": 0.4658, + "step": 9714 + }, + { + "epoch": 0.81, + "learning_rate": 1.7818426070314953e-06, + "loss": 0.4595, + "step": 9715 + }, + { + "epoch": 0.81, + "learning_rate": 1.7802989314310449e-06, + "loss": 0.4852, + "step": 9716 + }, + { + "epoch": 0.81, + "learning_rate": 1.7787558594512533e-06, + "loss": 0.4482, + "step": 9717 + }, + { + "epoch": 0.81, + "learning_rate": 1.7772133912054367e-06, + "loss": 0.4569, + "step": 9718 + }, + { + "epoch": 0.81, + "learning_rate": 1.7756715268068635e-06, + "loss": 0.4792, + "step": 9719 + }, + { + "epoch": 0.81, + "learning_rate": 1.7741302663687697e-06, + "loss": 0.4654, + "step": 9720 + }, + { + "epoch": 0.81, + "learning_rate": 1.7725896100043349e-06, + "loss": 0.4532, + "step": 9721 + }, + { + "epoch": 0.81, + "learning_rate": 1.7710495578266963e-06, + "loss": 0.4619, + "step": 9722 + }, + { + "epoch": 0.81, + "learning_rate": 1.7695101099489542e-06, + "loss": 0.4695, + "step": 9723 + }, + { + "epoch": 0.81, + "learning_rate": 1.7679712664841554e-06, + "loss": 0.465, + "step": 9724 + }, + { + "epoch": 0.81, + "learning_rate": 1.766433027545308e-06, + "loss": 0.4712, + "step": 9725 + }, + { + "epoch": 0.81, + "learning_rate": 1.7648953932453706e-06, + "loss": 0.4926, + "step": 9726 + }, + { + "epoch": 0.81, + "learning_rate": 1.763358363697265e-06, + "loss": 0.4681, + "step": 9727 + }, + { + "epoch": 0.81, + "learning_rate": 1.7618219390138635e-06, + "loss": 0.4721, + "step": 9728 + }, + { + "epoch": 0.81, + "learning_rate": 1.7602861193079922e-06, + "loss": 0.4555, + "step": 9729 + }, + { + "epoch": 0.81, + "learning_rate": 1.7587509046924378e-06, + "loss": 0.4666, + "step": 9730 + }, + { + "epoch": 0.81, + "learning_rate": 1.7572162952799366e-06, + "loss": 0.4645, + "step": 9731 + }, + { + "epoch": 0.81, + "learning_rate": 1.7556822911831882e-06, + "loss": 0.4613, + "step": 9732 + }, + { + "epoch": 0.81, + "learning_rate": 1.7541488925148397e-06, + "loss": 0.4739, + "step": 9733 + }, + { + "epoch": 0.81, + "learning_rate": 1.752616099387502e-06, + "loss": 0.455, + "step": 9734 + }, + { + "epoch": 0.81, + "learning_rate": 1.7510839119137347e-06, + "loss": 0.4624, + "step": 9735 + }, + { + "epoch": 0.81, + "learning_rate": 1.7495523302060546e-06, + "loss": 0.4691, + "step": 9736 + }, + { + "epoch": 0.81, + "learning_rate": 1.7480213543769343e-06, + "loss": 0.4729, + "step": 9737 + }, + { + "epoch": 0.81, + "learning_rate": 1.7464909845388045e-06, + "loss": 0.4682, + "step": 9738 + }, + { + "epoch": 0.81, + "learning_rate": 1.7449612208040479e-06, + "loss": 0.4588, + "step": 9739 + }, + { + "epoch": 0.81, + "learning_rate": 1.743432063285001e-06, + "loss": 0.464, + "step": 9740 + }, + { + "epoch": 0.81, + "learning_rate": 1.7419035120939642e-06, + "loss": 0.4633, + "step": 9741 + }, + { + "epoch": 0.82, + "learning_rate": 1.740375567343182e-06, + "loss": 0.4697, + "step": 9742 + }, + { + "epoch": 0.82, + "learning_rate": 1.7388482291448684e-06, + "loss": 0.4564, + "step": 9743 + }, + { + "epoch": 0.82, + "learning_rate": 1.7373214976111786e-06, + "loss": 0.4541, + "step": 9744 + }, + { + "epoch": 0.82, + "learning_rate": 1.735795372854231e-06, + "loss": 0.4673, + "step": 9745 + }, + { + "epoch": 0.82, + "learning_rate": 1.7342698549860958e-06, + "loss": 0.4842, + "step": 9746 + }, + { + "epoch": 0.82, + "learning_rate": 1.732744944118805e-06, + "loss": 0.459, + "step": 9747 + }, + { + "epoch": 0.82, + "learning_rate": 1.7312206403643395e-06, + "loss": 0.4632, + "step": 9748 + }, + { + "epoch": 0.82, + "learning_rate": 1.7296969438346378e-06, + "loss": 0.4745, + "step": 9749 + }, + { + "epoch": 0.82, + "learning_rate": 1.7281738546415938e-06, + "loss": 0.4645, + "step": 9750 + }, + { + "epoch": 0.82, + "learning_rate": 1.726651372897057e-06, + "loss": 0.4611, + "step": 9751 + }, + { + "epoch": 0.82, + "learning_rate": 1.7251294987128287e-06, + "loss": 0.4632, + "step": 9752 + }, + { + "epoch": 0.82, + "learning_rate": 1.723608232200673e-06, + "loss": 0.4493, + "step": 9753 + }, + { + "epoch": 0.82, + "learning_rate": 1.7220875734723063e-06, + "loss": 0.4455, + "step": 9754 + }, + { + "epoch": 0.82, + "learning_rate": 1.720567522639398e-06, + "loss": 0.4785, + "step": 9755 + }, + { + "epoch": 0.82, + "learning_rate": 1.7190480798135745e-06, + "loss": 0.4574, + "step": 9756 + }, + { + "epoch": 0.82, + "learning_rate": 1.7175292451064174e-06, + "loss": 0.4784, + "step": 9757 + }, + { + "epoch": 0.82, + "learning_rate": 1.716011018629462e-06, + "loss": 0.4608, + "step": 9758 + }, + { + "epoch": 0.82, + "learning_rate": 1.7144934004942027e-06, + "loss": 0.4531, + "step": 9759 + }, + { + "epoch": 0.82, + "learning_rate": 1.7129763908120823e-06, + "loss": 0.4734, + "step": 9760 + }, + { + "epoch": 0.82, + "learning_rate": 1.7114599896945105e-06, + "loss": 0.4574, + "step": 9761 + }, + { + "epoch": 0.82, + "learning_rate": 1.709944197252843e-06, + "loss": 0.4479, + "step": 9762 + }, + { + "epoch": 0.82, + "learning_rate": 1.7084290135983895e-06, + "loss": 0.4544, + "step": 9763 + }, + { + "epoch": 0.82, + "learning_rate": 1.7069144388424253e-06, + "loss": 0.4866, + "step": 9764 + }, + { + "epoch": 0.82, + "learning_rate": 1.7054004730961704e-06, + "loss": 0.4746, + "step": 9765 + }, + { + "epoch": 0.82, + "learning_rate": 1.7038871164708059e-06, + "loss": 0.4562, + "step": 9766 + }, + { + "epoch": 0.82, + "learning_rate": 1.7023743690774619e-06, + "loss": 0.4627, + "step": 9767 + }, + { + "epoch": 0.82, + "learning_rate": 1.7008622310272349e-06, + "loss": 0.4512, + "step": 9768 + }, + { + "epoch": 0.82, + "learning_rate": 1.6993507024311661e-06, + "loss": 0.4584, + "step": 9769 + }, + { + "epoch": 0.82, + "learning_rate": 1.697839783400258e-06, + "loss": 0.4578, + "step": 9770 + }, + { + "epoch": 0.82, + "learning_rate": 1.6963294740454638e-06, + "loss": 0.4818, + "step": 9771 + }, + { + "epoch": 0.82, + "learning_rate": 1.694819774477694e-06, + "loss": 0.4753, + "step": 9772 + }, + { + "epoch": 0.82, + "learning_rate": 1.6933106848078174e-06, + "loss": 0.4678, + "step": 9773 + }, + { + "epoch": 0.82, + "learning_rate": 1.691802205146652e-06, + "loss": 0.4589, + "step": 9774 + }, + { + "epoch": 0.82, + "learning_rate": 1.6902943356049796e-06, + "loss": 0.4672, + "step": 9775 + }, + { + "epoch": 0.82, + "learning_rate": 1.6887870762935276e-06, + "loss": 0.4603, + "step": 9776 + }, + { + "epoch": 0.82, + "learning_rate": 1.6872804273229838e-06, + "loss": 0.4586, + "step": 9777 + }, + { + "epoch": 0.82, + "learning_rate": 1.6857743888039902e-06, + "loss": 0.4551, + "step": 9778 + }, + { + "epoch": 0.82, + "learning_rate": 1.6842689608471451e-06, + "loss": 0.4649, + "step": 9779 + }, + { + "epoch": 0.82, + "learning_rate": 1.6827641435629983e-06, + "loss": 0.4798, + "step": 9780 + }, + { + "epoch": 0.82, + "learning_rate": 1.6812599370620574e-06, + "loss": 0.4601, + "step": 9781 + }, + { + "epoch": 0.82, + "learning_rate": 1.679756341454788e-06, + "loss": 0.4397, + "step": 9782 + }, + { + "epoch": 0.82, + "learning_rate": 1.6782533568516047e-06, + "loss": 0.4517, + "step": 9783 + }, + { + "epoch": 0.82, + "learning_rate": 1.6767509833628847e-06, + "loss": 0.4718, + "step": 9784 + }, + { + "epoch": 0.82, + "learning_rate": 1.6752492210989523e-06, + "loss": 0.4713, + "step": 9785 + }, + { + "epoch": 0.82, + "learning_rate": 1.6737480701700936e-06, + "loss": 0.4593, + "step": 9786 + }, + { + "epoch": 0.82, + "learning_rate": 1.6722475306865415e-06, + "loss": 0.4871, + "step": 9787 + }, + { + "epoch": 0.82, + "learning_rate": 1.6707476027584956e-06, + "loss": 0.4819, + "step": 9788 + }, + { + "epoch": 0.82, + "learning_rate": 1.6692482864961024e-06, + "loss": 0.4736, + "step": 9789 + }, + { + "epoch": 0.82, + "learning_rate": 1.6677495820094635e-06, + "loss": 0.4608, + "step": 9790 + }, + { + "epoch": 0.82, + "learning_rate": 1.6662514894086402e-06, + "loss": 0.4389, + "step": 9791 + }, + { + "epoch": 0.82, + "learning_rate": 1.664754008803644e-06, + "loss": 0.4748, + "step": 9792 + }, + { + "epoch": 0.82, + "learning_rate": 1.6632571403044429e-06, + "loss": 0.4592, + "step": 9793 + }, + { + "epoch": 0.82, + "learning_rate": 1.6617608840209642e-06, + "loss": 0.4609, + "step": 9794 + }, + { + "epoch": 0.82, + "learning_rate": 1.6602652400630825e-06, + "loss": 0.4567, + "step": 9795 + }, + { + "epoch": 0.82, + "learning_rate": 1.6587702085406366e-06, + "loss": 0.5012, + "step": 9796 + }, + { + "epoch": 0.82, + "learning_rate": 1.6572757895634117e-06, + "loss": 0.4571, + "step": 9797 + }, + { + "epoch": 0.82, + "learning_rate": 1.6557819832411537e-06, + "loss": 0.4843, + "step": 9798 + }, + { + "epoch": 0.82, + "learning_rate": 1.6542887896835614e-06, + "loss": 0.4747, + "step": 9799 + }, + { + "epoch": 0.82, + "learning_rate": 1.652796209000287e-06, + "loss": 0.4576, + "step": 9800 + }, + { + "epoch": 0.82, + "learning_rate": 1.6513042413009383e-06, + "loss": 0.4586, + "step": 9801 + }, + { + "epoch": 0.82, + "learning_rate": 1.6498128866950835e-06, + "loss": 0.4844, + "step": 9802 + }, + { + "epoch": 0.82, + "learning_rate": 1.6483221452922394e-06, + "loss": 0.4594, + "step": 9803 + }, + { + "epoch": 0.82, + "learning_rate": 1.646832017201877e-06, + "loss": 0.4692, + "step": 9804 + }, + { + "epoch": 0.82, + "learning_rate": 1.6453425025334302e-06, + "loss": 0.4718, + "step": 9805 + }, + { + "epoch": 0.82, + "learning_rate": 1.6438536013962814e-06, + "loss": 0.4611, + "step": 9806 + }, + { + "epoch": 0.82, + "learning_rate": 1.6423653138997675e-06, + "loss": 0.4661, + "step": 9807 + }, + { + "epoch": 0.82, + "learning_rate": 1.64087764015318e-06, + "loss": 0.4553, + "step": 9808 + }, + { + "epoch": 0.82, + "learning_rate": 1.639390580265774e-06, + "loss": 0.4626, + "step": 9809 + }, + { + "epoch": 0.82, + "learning_rate": 1.6379041343467484e-06, + "loss": 0.4576, + "step": 9810 + }, + { + "epoch": 0.82, + "learning_rate": 1.6364183025052626e-06, + "loss": 0.4766, + "step": 9811 + }, + { + "epoch": 0.82, + "learning_rate": 1.6349330848504308e-06, + "loss": 0.4571, + "step": 9812 + }, + { + "epoch": 0.82, + "learning_rate": 1.6334484814913165e-06, + "loss": 0.4734, + "step": 9813 + }, + { + "epoch": 0.82, + "learning_rate": 1.6319644925369504e-06, + "loss": 0.4534, + "step": 9814 + }, + { + "epoch": 0.82, + "learning_rate": 1.6304811180963032e-06, + "loss": 0.4627, + "step": 9815 + }, + { + "epoch": 0.82, + "learning_rate": 1.6289983582783142e-06, + "loss": 0.4361, + "step": 9816 + }, + { + "epoch": 0.82, + "learning_rate": 1.6275162131918688e-06, + "loss": 0.4706, + "step": 9817 + }, + { + "epoch": 0.82, + "learning_rate": 1.6260346829458084e-06, + "loss": 0.4615, + "step": 9818 + }, + { + "epoch": 0.82, + "learning_rate": 1.624553767648931e-06, + "loss": 0.4508, + "step": 9819 + }, + { + "epoch": 0.82, + "learning_rate": 1.623073467409988e-06, + "loss": 0.4657, + "step": 9820 + }, + { + "epoch": 0.82, + "learning_rate": 1.621593782337686e-06, + "loss": 0.4634, + "step": 9821 + }, + { + "epoch": 0.82, + "learning_rate": 1.62011471254069e-06, + "loss": 0.4603, + "step": 9822 + }, + { + "epoch": 0.82, + "learning_rate": 1.618636258127615e-06, + "loss": 0.4654, + "step": 9823 + }, + { + "epoch": 0.82, + "learning_rate": 1.6171584192070322e-06, + "loss": 0.46, + "step": 9824 + }, + { + "epoch": 0.82, + "learning_rate": 1.6156811958874664e-06, + "loss": 0.478, + "step": 9825 + }, + { + "epoch": 0.82, + "learning_rate": 1.6142045882774027e-06, + "loss": 0.4481, + "step": 9826 + }, + { + "epoch": 0.82, + "learning_rate": 1.6127285964852758e-06, + "loss": 0.4746, + "step": 9827 + }, + { + "epoch": 0.82, + "learning_rate": 1.6112532206194719e-06, + "loss": 0.4595, + "step": 9828 + }, + { + "epoch": 0.82, + "learning_rate": 1.6097784607883427e-06, + "loss": 0.4624, + "step": 9829 + }, + { + "epoch": 0.82, + "learning_rate": 1.6083043171001856e-06, + "loss": 0.4669, + "step": 9830 + }, + { + "epoch": 0.82, + "learning_rate": 1.6068307896632562e-06, + "loss": 0.456, + "step": 9831 + }, + { + "epoch": 0.82, + "learning_rate": 1.6053578785857637e-06, + "loss": 0.4572, + "step": 9832 + }, + { + "epoch": 0.82, + "learning_rate": 1.6038855839758727e-06, + "loss": 0.4696, + "step": 9833 + }, + { + "epoch": 0.82, + "learning_rate": 1.6024139059417e-06, + "loss": 0.4707, + "step": 9834 + }, + { + "epoch": 0.82, + "learning_rate": 1.6009428445913245e-06, + "loss": 0.4542, + "step": 9835 + }, + { + "epoch": 0.82, + "learning_rate": 1.5994724000327689e-06, + "loss": 0.4657, + "step": 9836 + }, + { + "epoch": 0.82, + "learning_rate": 1.5980025723740222e-06, + "loss": 0.4558, + "step": 9837 + }, + { + "epoch": 0.82, + "learning_rate": 1.5965333617230206e-06, + "loss": 0.4499, + "step": 9838 + }, + { + "epoch": 0.82, + "learning_rate": 1.5950647681876564e-06, + "loss": 0.4672, + "step": 9839 + }, + { + "epoch": 0.82, + "learning_rate": 1.5935967918757766e-06, + "loss": 0.4803, + "step": 9840 + }, + { + "epoch": 0.82, + "learning_rate": 1.5921294328951842e-06, + "loss": 0.4685, + "step": 9841 + }, + { + "epoch": 0.82, + "learning_rate": 1.5906626913536315e-06, + "loss": 0.4913, + "step": 9842 + }, + { + "epoch": 0.82, + "learning_rate": 1.5891965673588371e-06, + "loss": 0.4623, + "step": 9843 + }, + { + "epoch": 0.82, + "learning_rate": 1.5877310610184638e-06, + "loss": 0.467, + "step": 9844 + }, + { + "epoch": 0.82, + "learning_rate": 1.5862661724401296e-06, + "loss": 0.4534, + "step": 9845 + }, + { + "epoch": 0.82, + "learning_rate": 1.5848019017314143e-06, + "loss": 0.4589, + "step": 9846 + }, + { + "epoch": 0.82, + "learning_rate": 1.5833382489998461e-06, + "loss": 0.4532, + "step": 9847 + }, + { + "epoch": 0.82, + "learning_rate": 1.5818752143529092e-06, + "loss": 0.4563, + "step": 9848 + }, + { + "epoch": 0.82, + "learning_rate": 1.580412797898041e-06, + "loss": 0.4748, + "step": 9849 + }, + { + "epoch": 0.82, + "learning_rate": 1.578950999742639e-06, + "loss": 0.4534, + "step": 9850 + }, + { + "epoch": 0.82, + "learning_rate": 1.5774898199940503e-06, + "loss": 0.4749, + "step": 9851 + }, + { + "epoch": 0.82, + "learning_rate": 1.576029258759577e-06, + "loss": 0.4571, + "step": 9852 + }, + { + "epoch": 0.82, + "learning_rate": 1.574569316146477e-06, + "loss": 0.4619, + "step": 9853 + }, + { + "epoch": 0.82, + "learning_rate": 1.573109992261963e-06, + "loss": 0.4568, + "step": 9854 + }, + { + "epoch": 0.82, + "learning_rate": 1.5716512872131983e-06, + "loss": 0.46, + "step": 9855 + }, + { + "epoch": 0.82, + "learning_rate": 1.5701932011073072e-06, + "loss": 0.464, + "step": 9856 + }, + { + "epoch": 0.82, + "learning_rate": 1.5687357340513676e-06, + "loss": 0.4505, + "step": 9857 + }, + { + "epoch": 0.82, + "learning_rate": 1.567278886152407e-06, + "loss": 0.4821, + "step": 9858 + }, + { + "epoch": 0.82, + "learning_rate": 1.5658226575174107e-06, + "loss": 0.4536, + "step": 9859 + }, + { + "epoch": 0.82, + "learning_rate": 1.564367048253318e-06, + "loss": 0.4568, + "step": 9860 + }, + { + "epoch": 0.83, + "learning_rate": 1.5629120584670233e-06, + "loss": 0.4723, + "step": 9861 + }, + { + "epoch": 0.83, + "learning_rate": 1.561457688265372e-06, + "loss": 0.4438, + "step": 9862 + }, + { + "epoch": 0.83, + "learning_rate": 1.5600039377551713e-06, + "loss": 0.4778, + "step": 9863 + }, + { + "epoch": 0.83, + "learning_rate": 1.5585508070431777e-06, + "loss": 0.4595, + "step": 9864 + }, + { + "epoch": 0.83, + "learning_rate": 1.5570982962361014e-06, + "loss": 0.4779, + "step": 9865 + }, + { + "epoch": 0.83, + "learning_rate": 1.5556464054406084e-06, + "loss": 0.4676, + "step": 9866 + }, + { + "epoch": 0.83, + "learning_rate": 1.5541951347633222e-06, + "loss": 0.4708, + "step": 9867 + }, + { + "epoch": 0.83, + "learning_rate": 1.5527444843108164e-06, + "loss": 0.4505, + "step": 9868 + }, + { + "epoch": 0.83, + "learning_rate": 1.5512944541896192e-06, + "loss": 0.4521, + "step": 9869 + }, + { + "epoch": 0.83, + "learning_rate": 1.5498450445062185e-06, + "loss": 0.4528, + "step": 9870 + }, + { + "epoch": 0.83, + "learning_rate": 1.5483962553670507e-06, + "loss": 0.4653, + "step": 9871 + }, + { + "epoch": 0.83, + "learning_rate": 1.5469480868785092e-06, + "loss": 0.4514, + "step": 9872 + }, + { + "epoch": 0.83, + "learning_rate": 1.5455005391469414e-06, + "loss": 0.4529, + "step": 9873 + }, + { + "epoch": 0.83, + "learning_rate": 1.5440536122786487e-06, + "loss": 0.4503, + "step": 9874 + }, + { + "epoch": 0.83, + "learning_rate": 1.5426073063798853e-06, + "loss": 0.4638, + "step": 9875 + }, + { + "epoch": 0.83, + "learning_rate": 1.541161621556867e-06, + "loss": 0.4875, + "step": 9876 + }, + { + "epoch": 0.83, + "learning_rate": 1.5397165579157547e-06, + "loss": 0.4691, + "step": 9877 + }, + { + "epoch": 0.83, + "learning_rate": 1.5382721155626701e-06, + "loss": 0.4669, + "step": 9878 + }, + { + "epoch": 0.83, + "learning_rate": 1.5368282946036884e-06, + "loss": 0.4839, + "step": 9879 + }, + { + "epoch": 0.83, + "learning_rate": 1.5353850951448346e-06, + "loss": 0.45, + "step": 9880 + }, + { + "epoch": 0.83, + "learning_rate": 1.533942517292092e-06, + "loss": 0.4832, + "step": 9881 + }, + { + "epoch": 0.83, + "learning_rate": 1.5325005611513988e-06, + "loss": 0.4552, + "step": 9882 + }, + { + "epoch": 0.83, + "learning_rate": 1.5310592268286427e-06, + "loss": 0.4636, + "step": 9883 + }, + { + "epoch": 0.83, + "learning_rate": 1.5296185144296737e-06, + "loss": 0.4557, + "step": 9884 + }, + { + "epoch": 0.83, + "learning_rate": 1.5281784240602915e-06, + "loss": 0.4538, + "step": 9885 + }, + { + "epoch": 0.83, + "learning_rate": 1.5267389558262458e-06, + "loss": 0.4727, + "step": 9886 + }, + { + "epoch": 0.83, + "learning_rate": 1.525300109833251e-06, + "loss": 0.468, + "step": 9887 + }, + { + "epoch": 0.83, + "learning_rate": 1.5238618861869657e-06, + "loss": 0.4555, + "step": 9888 + }, + { + "epoch": 0.83, + "learning_rate": 1.5224242849930104e-06, + "loss": 0.4554, + "step": 9889 + }, + { + "epoch": 0.83, + "learning_rate": 1.5209873063569514e-06, + "loss": 0.461, + "step": 9890 + }, + { + "epoch": 0.83, + "learning_rate": 1.5195509503843198e-06, + "loss": 0.4678, + "step": 9891 + }, + { + "epoch": 0.83, + "learning_rate": 1.5181152171805946e-06, + "loss": 0.4675, + "step": 9892 + }, + { + "epoch": 0.83, + "learning_rate": 1.5166801068512083e-06, + "loss": 0.4785, + "step": 9893 + }, + { + "epoch": 0.83, + "learning_rate": 1.5152456195015508e-06, + "loss": 0.4646, + "step": 9894 + }, + { + "epoch": 0.83, + "learning_rate": 1.5138117552369636e-06, + "loss": 0.4579, + "step": 9895 + }, + { + "epoch": 0.83, + "learning_rate": 1.5123785141627422e-06, + "loss": 0.4778, + "step": 9896 + }, + { + "epoch": 0.83, + "learning_rate": 1.5109458963841405e-06, + "loss": 0.4539, + "step": 9897 + }, + { + "epoch": 0.83, + "learning_rate": 1.5095139020063654e-06, + "loss": 0.4777, + "step": 9898 + }, + { + "epoch": 0.83, + "learning_rate": 1.5080825311345748e-06, + "loss": 0.4639, + "step": 9899 + }, + { + "epoch": 0.83, + "learning_rate": 1.5066517838738826e-06, + "loss": 0.4715, + "step": 9900 + }, + { + "epoch": 0.83, + "learning_rate": 1.5052216603293567e-06, + "loss": 0.4642, + "step": 9901 + }, + { + "epoch": 0.83, + "learning_rate": 1.5037921606060201e-06, + "loss": 0.4706, + "step": 9902 + }, + { + "epoch": 0.83, + "learning_rate": 1.5023632848088466e-06, + "loss": 0.4704, + "step": 9903 + }, + { + "epoch": 0.83, + "learning_rate": 1.5009350330427707e-06, + "loss": 0.4681, + "step": 9904 + }, + { + "epoch": 0.83, + "learning_rate": 1.4995074054126758e-06, + "loss": 0.4892, + "step": 9905 + }, + { + "epoch": 0.83, + "learning_rate": 1.4980804020234018e-06, + "loss": 0.4726, + "step": 9906 + }, + { + "epoch": 0.83, + "learning_rate": 1.4966540229797377e-06, + "loss": 0.449, + "step": 9907 + }, + { + "epoch": 0.83, + "learning_rate": 1.495228268386436e-06, + "loss": 0.4921, + "step": 9908 + }, + { + "epoch": 0.83, + "learning_rate": 1.4938031383481976e-06, + "loss": 0.4561, + "step": 9909 + }, + { + "epoch": 0.83, + "learning_rate": 1.4923786329696732e-06, + "loss": 0.4515, + "step": 9910 + }, + { + "epoch": 0.83, + "learning_rate": 1.490954752355479e-06, + "loss": 0.4636, + "step": 9911 + }, + { + "epoch": 0.83, + "learning_rate": 1.4895314966101771e-06, + "loss": 0.4696, + "step": 9912 + }, + { + "epoch": 0.83, + "learning_rate": 1.4881088658382825e-06, + "loss": 0.46, + "step": 9913 + }, + { + "epoch": 0.83, + "learning_rate": 1.4866868601442708e-06, + "loss": 0.4571, + "step": 9914 + }, + { + "epoch": 0.83, + "learning_rate": 1.4852654796325649e-06, + "loss": 0.4791, + "step": 9915 + }, + { + "epoch": 0.83, + "learning_rate": 1.483844724407546e-06, + "loss": 0.4548, + "step": 9916 + }, + { + "epoch": 0.83, + "learning_rate": 1.4824245945735504e-06, + "loss": 0.4757, + "step": 9917 + }, + { + "epoch": 0.83, + "learning_rate": 1.4810050902348637e-06, + "loss": 0.4646, + "step": 9918 + }, + { + "epoch": 0.83, + "learning_rate": 1.4795862114957316e-06, + "loss": 0.4581, + "step": 9919 + }, + { + "epoch": 0.83, + "learning_rate": 1.4781679584603502e-06, + "loss": 0.4629, + "step": 9920 + }, + { + "epoch": 0.83, + "learning_rate": 1.476750331232868e-06, + "loss": 0.4577, + "step": 9921 + }, + { + "epoch": 0.83, + "learning_rate": 1.475333329917391e-06, + "loss": 0.4527, + "step": 9922 + }, + { + "epoch": 0.83, + "learning_rate": 1.4739169546179765e-06, + "loss": 0.4807, + "step": 9923 + }, + { + "epoch": 0.83, + "learning_rate": 1.4725012054386378e-06, + "loss": 0.4923, + "step": 9924 + }, + { + "epoch": 0.83, + "learning_rate": 1.471086082483343e-06, + "loss": 0.4598, + "step": 9925 + }, + { + "epoch": 0.83, + "learning_rate": 1.4696715858560117e-06, + "loss": 0.4665, + "step": 9926 + }, + { + "epoch": 0.83, + "learning_rate": 1.4682577156605172e-06, + "loss": 0.4629, + "step": 9927 + }, + { + "epoch": 0.83, + "learning_rate": 1.4668444720006925e-06, + "loss": 0.4601, + "step": 9928 + }, + { + "epoch": 0.83, + "learning_rate": 1.465431854980317e-06, + "loss": 0.4491, + "step": 9929 + }, + { + "epoch": 0.83, + "learning_rate": 1.464019864703128e-06, + "loss": 0.4712, + "step": 9930 + }, + { + "epoch": 0.83, + "learning_rate": 1.462608501272814e-06, + "loss": 0.4774, + "step": 9931 + }, + { + "epoch": 0.83, + "learning_rate": 1.4611977647930253e-06, + "loss": 0.4513, + "step": 9932 + }, + { + "epoch": 0.83, + "learning_rate": 1.4597876553673563e-06, + "loss": 0.4563, + "step": 9933 + }, + { + "epoch": 0.83, + "learning_rate": 1.4583781730993608e-06, + "loss": 0.499, + "step": 9934 + }, + { + "epoch": 0.83, + "learning_rate": 1.4569693180925448e-06, + "loss": 0.4526, + "step": 9935 + }, + { + "epoch": 0.83, + "learning_rate": 1.4555610904503693e-06, + "loss": 0.4584, + "step": 9936 + }, + { + "epoch": 0.83, + "learning_rate": 1.4541534902762454e-06, + "loss": 0.4796, + "step": 9937 + }, + { + "epoch": 0.83, + "learning_rate": 1.4527465176735468e-06, + "loss": 0.4667, + "step": 9938 + }, + { + "epoch": 0.83, + "learning_rate": 1.4513401727455912e-06, + "loss": 0.4605, + "step": 9939 + }, + { + "epoch": 0.83, + "learning_rate": 1.4499344555956596e-06, + "loss": 0.4599, + "step": 9940 + }, + { + "epoch": 0.83, + "learning_rate": 1.4485293663269784e-06, + "loss": 0.4705, + "step": 9941 + }, + { + "epoch": 0.83, + "learning_rate": 1.4471249050427327e-06, + "loss": 0.4587, + "step": 9942 + }, + { + "epoch": 0.83, + "learning_rate": 1.445721071846059e-06, + "loss": 0.4666, + "step": 9943 + }, + { + "epoch": 0.83, + "learning_rate": 1.4443178668400482e-06, + "loss": 0.4746, + "step": 9944 + }, + { + "epoch": 0.83, + "learning_rate": 1.44291529012775e-06, + "loss": 0.4541, + "step": 9945 + }, + { + "epoch": 0.83, + "learning_rate": 1.4415133418121607e-06, + "loss": 0.4601, + "step": 9946 + }, + { + "epoch": 0.83, + "learning_rate": 1.440112021996235e-06, + "loss": 0.4644, + "step": 9947 + }, + { + "epoch": 0.83, + "learning_rate": 1.438711330782877e-06, + "loss": 0.4746, + "step": 9948 + }, + { + "epoch": 0.83, + "learning_rate": 1.4373112682749513e-06, + "loss": 0.453, + "step": 9949 + }, + { + "epoch": 0.83, + "learning_rate": 1.435911834575271e-06, + "loss": 0.4469, + "step": 9950 + }, + { + "epoch": 0.83, + "learning_rate": 1.4345130297866028e-06, + "loss": 0.4831, + "step": 9951 + }, + { + "epoch": 0.83, + "learning_rate": 1.4331148540116736e-06, + "loss": 0.4721, + "step": 9952 + }, + { + "epoch": 0.83, + "learning_rate": 1.4317173073531577e-06, + "loss": 0.4719, + "step": 9953 + }, + { + "epoch": 0.83, + "learning_rate": 1.4303203899136841e-06, + "loss": 0.4573, + "step": 9954 + }, + { + "epoch": 0.83, + "learning_rate": 1.4289241017958366e-06, + "loss": 0.4556, + "step": 9955 + }, + { + "epoch": 0.83, + "learning_rate": 1.4275284431021541e-06, + "loss": 0.4715, + "step": 9956 + }, + { + "epoch": 0.83, + "learning_rate": 1.4261334139351269e-06, + "loss": 0.4622, + "step": 9957 + }, + { + "epoch": 0.83, + "learning_rate": 1.4247390143971972e-06, + "loss": 0.4679, + "step": 9958 + }, + { + "epoch": 0.83, + "learning_rate": 1.423345244590768e-06, + "loss": 0.4744, + "step": 9959 + }, + { + "epoch": 0.83, + "learning_rate": 1.4219521046181928e-06, + "loss": 0.4441, + "step": 9960 + }, + { + "epoch": 0.83, + "learning_rate": 1.4205595945817773e-06, + "loss": 0.4609, + "step": 9961 + }, + { + "epoch": 0.83, + "learning_rate": 1.41916771458378e-06, + "loss": 0.4812, + "step": 9962 + }, + { + "epoch": 0.83, + "learning_rate": 1.4177764647264148e-06, + "loss": 0.4526, + "step": 9963 + }, + { + "epoch": 0.83, + "learning_rate": 1.4163858451118506e-06, + "loss": 0.4531, + "step": 9964 + }, + { + "epoch": 0.83, + "learning_rate": 1.414995855842205e-06, + "loss": 0.4603, + "step": 9965 + }, + { + "epoch": 0.83, + "learning_rate": 1.4136064970195595e-06, + "loss": 0.447, + "step": 9966 + }, + { + "epoch": 0.83, + "learning_rate": 1.4122177687459382e-06, + "loss": 0.4504, + "step": 9967 + }, + { + "epoch": 0.83, + "learning_rate": 1.4108296711233249e-06, + "loss": 0.461, + "step": 9968 + }, + { + "epoch": 0.83, + "learning_rate": 1.4094422042536538e-06, + "loss": 0.458, + "step": 9969 + }, + { + "epoch": 0.83, + "learning_rate": 1.4080553682388188e-06, + "loss": 0.4563, + "step": 9970 + }, + { + "epoch": 0.83, + "learning_rate": 1.4066691631806574e-06, + "loss": 0.4701, + "step": 9971 + }, + { + "epoch": 0.83, + "learning_rate": 1.4052835891809735e-06, + "loss": 0.4579, + "step": 9972 + }, + { + "epoch": 0.83, + "learning_rate": 1.403898646341515e-06, + "loss": 0.4772, + "step": 9973 + }, + { + "epoch": 0.83, + "learning_rate": 1.4025143347639858e-06, + "loss": 0.467, + "step": 9974 + }, + { + "epoch": 0.83, + "learning_rate": 1.4011306545500435e-06, + "loss": 0.4744, + "step": 9975 + }, + { + "epoch": 0.83, + "learning_rate": 1.3997476058013016e-06, + "loss": 0.4634, + "step": 9976 + }, + { + "epoch": 0.83, + "learning_rate": 1.398365188619324e-06, + "loss": 0.4809, + "step": 9977 + }, + { + "epoch": 0.83, + "learning_rate": 1.3969834031056273e-06, + "loss": 0.4474, + "step": 9978 + }, + { + "epoch": 0.83, + "learning_rate": 1.3956022493616895e-06, + "loss": 0.4512, + "step": 9979 + }, + { + "epoch": 0.83, + "learning_rate": 1.3942217274889325e-06, + "loss": 0.4772, + "step": 9980 + }, + { + "epoch": 0.84, + "learning_rate": 1.3928418375887388e-06, + "loss": 0.4751, + "step": 9981 + }, + { + "epoch": 0.84, + "learning_rate": 1.3914625797624415e-06, + "loss": 0.4361, + "step": 9982 + }, + { + "epoch": 0.84, + "learning_rate": 1.3900839541113265e-06, + "loss": 0.4814, + "step": 9983 + }, + { + "epoch": 0.84, + "learning_rate": 1.3887059607366338e-06, + "loss": 0.4506, + "step": 9984 + }, + { + "epoch": 0.84, + "learning_rate": 1.3873285997395569e-06, + "loss": 0.4521, + "step": 9985 + }, + { + "epoch": 0.84, + "learning_rate": 1.3859518712212473e-06, + "loss": 0.4759, + "step": 9986 + }, + { + "epoch": 0.84, + "learning_rate": 1.3845757752828037e-06, + "loss": 0.4694, + "step": 9987 + }, + { + "epoch": 0.84, + "learning_rate": 1.3832003120252801e-06, + "loss": 0.4438, + "step": 9988 + }, + { + "epoch": 0.84, + "learning_rate": 1.3818254815496846e-06, + "loss": 0.4566, + "step": 9989 + }, + { + "epoch": 0.84, + "learning_rate": 1.3804512839569805e-06, + "loss": 0.4699, + "step": 9990 + }, + { + "epoch": 0.84, + "learning_rate": 1.3790777193480842e-06, + "loss": 0.4585, + "step": 9991 + }, + { + "epoch": 0.84, + "learning_rate": 1.3777047878238603e-06, + "loss": 0.4504, + "step": 9992 + }, + { + "epoch": 0.84, + "learning_rate": 1.3763324894851371e-06, + "loss": 0.4583, + "step": 9993 + }, + { + "epoch": 0.84, + "learning_rate": 1.3749608244326862e-06, + "loss": 0.461, + "step": 9994 + }, + { + "epoch": 0.84, + "learning_rate": 1.373589792767238e-06, + "loss": 0.4712, + "step": 9995 + }, + { + "epoch": 0.84, + "learning_rate": 1.372219394589477e-06, + "loss": 0.4688, + "step": 9996 + }, + { + "epoch": 0.84, + "learning_rate": 1.3708496300000363e-06, + "loss": 0.479, + "step": 9997 + }, + { + "epoch": 0.84, + "learning_rate": 1.369480499099508e-06, + "loss": 0.4624, + "step": 9998 + }, + { + "epoch": 0.84, + "learning_rate": 1.3681120019884331e-06, + "loss": 0.4708, + "step": 9999 + }, + { + "epoch": 0.84, + "learning_rate": 1.3667441387673098e-06, + "loss": 0.4821, + "step": 10000 + }, + { + "epoch": 0.84, + "learning_rate": 1.36537690953659e-06, + "loss": 0.4553, + "step": 10001 + }, + { + "epoch": 0.84, + "learning_rate": 1.3640103143966765e-06, + "loss": 0.4771, + "step": 10002 + }, + { + "epoch": 0.84, + "learning_rate": 1.3626443534479262e-06, + "loss": 0.4618, + "step": 10003 + }, + { + "epoch": 0.84, + "learning_rate": 1.3612790267906484e-06, + "loss": 0.4534, + "step": 10004 + }, + { + "epoch": 0.84, + "learning_rate": 1.3599143345251075e-06, + "loss": 0.4711, + "step": 10005 + }, + { + "epoch": 0.84, + "learning_rate": 1.35855027675152e-06, + "loss": 0.4506, + "step": 10006 + }, + { + "epoch": 0.84, + "learning_rate": 1.3571868535700595e-06, + "loss": 0.4574, + "step": 10007 + }, + { + "epoch": 0.84, + "learning_rate": 1.3558240650808473e-06, + "loss": 0.4485, + "step": 10008 + }, + { + "epoch": 0.84, + "learning_rate": 1.354461911383963e-06, + "loss": 0.4536, + "step": 10009 + }, + { + "epoch": 0.84, + "learning_rate": 1.353100392579434e-06, + "loss": 0.467, + "step": 10010 + }, + { + "epoch": 0.84, + "learning_rate": 1.351739508767249e-06, + "loss": 0.4719, + "step": 10011 + }, + { + "epoch": 0.84, + "learning_rate": 1.3503792600473408e-06, + "loss": 0.4611, + "step": 10012 + }, + { + "epoch": 0.84, + "learning_rate": 1.349019646519607e-06, + "loss": 0.4513, + "step": 10013 + }, + { + "epoch": 0.84, + "learning_rate": 1.3476606682838866e-06, + "loss": 0.4686, + "step": 10014 + }, + { + "epoch": 0.84, + "learning_rate": 1.3463023254399798e-06, + "loss": 0.4681, + "step": 10015 + }, + { + "epoch": 0.84, + "learning_rate": 1.3449446180876369e-06, + "loss": 0.4556, + "step": 10016 + }, + { + "epoch": 0.84, + "learning_rate": 1.3435875463265624e-06, + "loss": 0.4678, + "step": 10017 + }, + { + "epoch": 0.84, + "learning_rate": 1.3422311102564134e-06, + "loss": 0.4727, + "step": 10018 + }, + { + "epoch": 0.84, + "learning_rate": 1.340875309976799e-06, + "loss": 0.4818, + "step": 10019 + }, + { + "epoch": 0.84, + "learning_rate": 1.3395201455872886e-06, + "loss": 0.4737, + "step": 10020 + }, + { + "epoch": 0.84, + "learning_rate": 1.3381656171873936e-06, + "loss": 0.4683, + "step": 10021 + }, + { + "epoch": 0.84, + "learning_rate": 1.336811724876592e-06, + "loss": 0.4708, + "step": 10022 + }, + { + "epoch": 0.84, + "learning_rate": 1.3354584687543037e-06, + "loss": 0.4664, + "step": 10023 + }, + { + "epoch": 0.84, + "learning_rate": 1.3341058489199065e-06, + "loss": 0.4535, + "step": 10024 + }, + { + "epoch": 0.84, + "learning_rate": 1.3327538654727323e-06, + "loss": 0.4832, + "step": 10025 + }, + { + "epoch": 0.84, + "learning_rate": 1.3314025185120616e-06, + "loss": 0.4402, + "step": 10026 + }, + { + "epoch": 0.84, + "learning_rate": 1.3300518081371373e-06, + "loss": 0.4713, + "step": 10027 + }, + { + "epoch": 0.84, + "learning_rate": 1.3287017344471477e-06, + "loss": 0.4847, + "step": 10028 + }, + { + "epoch": 0.84, + "learning_rate": 1.3273522975412344e-06, + "loss": 0.485, + "step": 10029 + }, + { + "epoch": 0.84, + "learning_rate": 1.3260034975184955e-06, + "loss": 0.4526, + "step": 10030 + }, + { + "epoch": 0.84, + "learning_rate": 1.3246553344779834e-06, + "loss": 0.4636, + "step": 10031 + }, + { + "epoch": 0.84, + "learning_rate": 1.3233078085187002e-06, + "loss": 0.4618, + "step": 10032 + }, + { + "epoch": 0.84, + "learning_rate": 1.3219609197396e-06, + "loss": 0.4777, + "step": 10033 + }, + { + "epoch": 0.84, + "learning_rate": 1.3206146682395983e-06, + "loss": 0.4768, + "step": 10034 + }, + { + "epoch": 0.84, + "learning_rate": 1.3192690541175536e-06, + "loss": 0.469, + "step": 10035 + }, + { + "epoch": 0.84, + "learning_rate": 1.3179240774722845e-06, + "loss": 0.4677, + "step": 10036 + }, + { + "epoch": 0.84, + "learning_rate": 1.3165797384025602e-06, + "loss": 0.4521, + "step": 10037 + }, + { + "epoch": 0.84, + "learning_rate": 1.3152360370071016e-06, + "loss": 0.458, + "step": 10038 + }, + { + "epoch": 0.84, + "learning_rate": 1.3138929733845873e-06, + "loss": 0.4684, + "step": 10039 + }, + { + "epoch": 0.84, + "learning_rate": 1.3125505476336408e-06, + "loss": 0.4928, + "step": 10040 + }, + { + "epoch": 0.84, + "learning_rate": 1.31120875985285e-06, + "loss": 0.4457, + "step": 10041 + }, + { + "epoch": 0.84, + "learning_rate": 1.3098676101407493e-06, + "loss": 0.4711, + "step": 10042 + }, + { + "epoch": 0.84, + "learning_rate": 1.3085270985958276e-06, + "loss": 0.4534, + "step": 10043 + }, + { + "epoch": 0.84, + "learning_rate": 1.307187225316524e-06, + "loss": 0.4645, + "step": 10044 + }, + { + "epoch": 0.84, + "learning_rate": 1.3058479904012356e-06, + "loss": 0.4482, + "step": 10045 + }, + { + "epoch": 0.84, + "learning_rate": 1.3045093939483066e-06, + "loss": 0.4551, + "step": 10046 + }, + { + "epoch": 0.84, + "learning_rate": 1.303171436056042e-06, + "loss": 0.4767, + "step": 10047 + }, + { + "epoch": 0.84, + "learning_rate": 1.3018341168226944e-06, + "loss": 0.4526, + "step": 10048 + }, + { + "epoch": 0.84, + "learning_rate": 1.3004974363464717e-06, + "loss": 0.4568, + "step": 10049 + }, + { + "epoch": 0.84, + "learning_rate": 1.2991613947255321e-06, + "loss": 0.4566, + "step": 10050 + }, + { + "epoch": 0.84, + "learning_rate": 1.2978259920579895e-06, + "loss": 0.4475, + "step": 10051 + }, + { + "epoch": 0.84, + "learning_rate": 1.2964912284419119e-06, + "loss": 0.4601, + "step": 10052 + }, + { + "epoch": 0.84, + "learning_rate": 1.2951571039753163e-06, + "loss": 0.4661, + "step": 10053 + }, + { + "epoch": 0.84, + "learning_rate": 1.2938236187561782e-06, + "loss": 0.4581, + "step": 10054 + }, + { + "epoch": 0.84, + "learning_rate": 1.292490772882422e-06, + "loss": 0.4995, + "step": 10055 + }, + { + "epoch": 0.84, + "learning_rate": 1.2911585664519267e-06, + "loss": 0.4664, + "step": 10056 + }, + { + "epoch": 0.84, + "learning_rate": 1.2898269995625234e-06, + "loss": 0.4653, + "step": 10057 + }, + { + "epoch": 0.84, + "learning_rate": 1.2884960723119978e-06, + "loss": 0.4812, + "step": 10058 + }, + { + "epoch": 0.84, + "learning_rate": 1.2871657847980856e-06, + "loss": 0.4597, + "step": 10059 + }, + { + "epoch": 0.84, + "learning_rate": 1.285836137118477e-06, + "loss": 0.4648, + "step": 10060 + }, + { + "epoch": 0.84, + "learning_rate": 1.2845071293708188e-06, + "loss": 0.4471, + "step": 10061 + }, + { + "epoch": 0.84, + "learning_rate": 1.2831787616527058e-06, + "loss": 0.4796, + "step": 10062 + }, + { + "epoch": 0.84, + "learning_rate": 1.2818510340616896e-06, + "loss": 0.4558, + "step": 10063 + }, + { + "epoch": 0.84, + "learning_rate": 1.2805239466952723e-06, + "loss": 0.4706, + "step": 10064 + }, + { + "epoch": 0.84, + "learning_rate": 1.2791974996509094e-06, + "loss": 0.4646, + "step": 10065 + }, + { + "epoch": 0.84, + "learning_rate": 1.2778716930260105e-06, + "loss": 0.4734, + "step": 10066 + }, + { + "epoch": 0.84, + "learning_rate": 1.2765465269179334e-06, + "loss": 0.4534, + "step": 10067 + }, + { + "epoch": 0.84, + "learning_rate": 1.275222001423998e-06, + "loss": 0.4768, + "step": 10068 + }, + { + "epoch": 0.84, + "learning_rate": 1.2738981166414688e-06, + "loss": 0.467, + "step": 10069 + }, + { + "epoch": 0.84, + "learning_rate": 1.2725748726675691e-06, + "loss": 0.4768, + "step": 10070 + }, + { + "epoch": 0.84, + "learning_rate": 1.2712522695994666e-06, + "loss": 0.4946, + "step": 10071 + }, + { + "epoch": 0.84, + "learning_rate": 1.269930307534295e-06, + "loss": 0.4539, + "step": 10072 + }, + { + "epoch": 0.84, + "learning_rate": 1.268608986569131e-06, + "loss": 0.4647, + "step": 10073 + }, + { + "epoch": 0.84, + "learning_rate": 1.2672883068010033e-06, + "loss": 0.4726, + "step": 10074 + }, + { + "epoch": 0.84, + "learning_rate": 1.2659682683269036e-06, + "loss": 0.4771, + "step": 10075 + }, + { + "epoch": 0.84, + "learning_rate": 1.2646488712437654e-06, + "loss": 0.4556, + "step": 10076 + }, + { + "epoch": 0.84, + "learning_rate": 1.2633301156484822e-06, + "loss": 0.4647, + "step": 10077 + }, + { + "epoch": 0.84, + "learning_rate": 1.2620120016378956e-06, + "loss": 0.4549, + "step": 10078 + }, + { + "epoch": 0.84, + "learning_rate": 1.2606945293088047e-06, + "loss": 0.4467, + "step": 10079 + }, + { + "epoch": 0.84, + "learning_rate": 1.2593776987579576e-06, + "loss": 0.4639, + "step": 10080 + }, + { + "epoch": 0.84, + "learning_rate": 1.2580615100820548e-06, + "loss": 0.4664, + "step": 10081 + }, + { + "epoch": 0.84, + "learning_rate": 1.2567459633777567e-06, + "loss": 0.4634, + "step": 10082 + }, + { + "epoch": 0.84, + "learning_rate": 1.2554310587416674e-06, + "loss": 0.4713, + "step": 10083 + }, + { + "epoch": 0.84, + "learning_rate": 1.2541167962703515e-06, + "loss": 0.4783, + "step": 10084 + }, + { + "epoch": 0.84, + "learning_rate": 1.252803176060321e-06, + "loss": 0.4557, + "step": 10085 + }, + { + "epoch": 0.84, + "learning_rate": 1.251490198208043e-06, + "loss": 0.4748, + "step": 10086 + }, + { + "epoch": 0.84, + "learning_rate": 1.2501778628099349e-06, + "loss": 0.4805, + "step": 10087 + }, + { + "epoch": 0.84, + "learning_rate": 1.2488661699623739e-06, + "loss": 0.4657, + "step": 10088 + }, + { + "epoch": 0.84, + "learning_rate": 1.247555119761682e-06, + "loss": 0.4644, + "step": 10089 + }, + { + "epoch": 0.84, + "learning_rate": 1.2462447123041388e-06, + "loss": 0.464, + "step": 10090 + }, + { + "epoch": 0.84, + "learning_rate": 1.244934947685974e-06, + "loss": 0.4735, + "step": 10091 + }, + { + "epoch": 0.84, + "learning_rate": 1.2436258260033696e-06, + "loss": 0.4721, + "step": 10092 + }, + { + "epoch": 0.84, + "learning_rate": 1.2423173473524653e-06, + "loss": 0.4823, + "step": 10093 + }, + { + "epoch": 0.84, + "learning_rate": 1.2410095118293475e-06, + "loss": 0.4499, + "step": 10094 + }, + { + "epoch": 0.84, + "learning_rate": 1.2397023195300618e-06, + "loss": 0.4769, + "step": 10095 + }, + { + "epoch": 0.84, + "learning_rate": 1.238395770550601e-06, + "loss": 0.4584, + "step": 10096 + }, + { + "epoch": 0.84, + "learning_rate": 1.2370898649869122e-06, + "loss": 0.4785, + "step": 10097 + }, + { + "epoch": 0.84, + "learning_rate": 1.2357846029348975e-06, + "loss": 0.461, + "step": 10098 + }, + { + "epoch": 0.84, + "learning_rate": 1.2344799844904065e-06, + "loss": 0.4563, + "step": 10099 + }, + { + "epoch": 0.85, + "learning_rate": 1.2331760097492485e-06, + "loss": 0.4628, + "step": 10100 + }, + { + "epoch": 0.85, + "learning_rate": 1.2318726788071767e-06, + "loss": 0.4704, + "step": 10101 + }, + { + "epoch": 0.85, + "learning_rate": 1.230569991759909e-06, + "loss": 0.473, + "step": 10102 + }, + { + "epoch": 0.85, + "learning_rate": 1.2292679487031045e-06, + "loss": 0.4632, + "step": 10103 + }, + { + "epoch": 0.85, + "learning_rate": 1.2279665497323835e-06, + "loss": 0.4495, + "step": 10104 + }, + { + "epoch": 0.85, + "learning_rate": 1.2266657949433135e-06, + "loss": 0.4662, + "step": 10105 + }, + { + "epoch": 0.85, + "learning_rate": 1.2253656844314155e-06, + "loss": 0.4628, + "step": 10106 + }, + { + "epoch": 0.85, + "learning_rate": 1.224066218292167e-06, + "loss": 0.4859, + "step": 10107 + }, + { + "epoch": 0.85, + "learning_rate": 1.2227673966209896e-06, + "loss": 0.4671, + "step": 10108 + }, + { + "epoch": 0.85, + "learning_rate": 1.2214692195132705e-06, + "loss": 0.4454, + "step": 10109 + }, + { + "epoch": 0.85, + "learning_rate": 1.2201716870643388e-06, + "loss": 0.458, + "step": 10110 + }, + { + "epoch": 0.85, + "learning_rate": 1.2188747993694805e-06, + "loss": 0.452, + "step": 10111 + }, + { + "epoch": 0.85, + "learning_rate": 1.217578556523934e-06, + "loss": 0.4621, + "step": 10112 + }, + { + "epoch": 0.85, + "learning_rate": 1.2162829586228874e-06, + "loss": 0.4471, + "step": 10113 + }, + { + "epoch": 0.85, + "learning_rate": 1.214988005761487e-06, + "loss": 0.4653, + "step": 10114 + }, + { + "epoch": 0.85, + "learning_rate": 1.2136936980348267e-06, + "loss": 0.4649, + "step": 10115 + }, + { + "epoch": 0.85, + "learning_rate": 1.2124000355379583e-06, + "loss": 0.4577, + "step": 10116 + }, + { + "epoch": 0.85, + "learning_rate": 1.21110701836588e-06, + "loss": 0.4553, + "step": 10117 + }, + { + "epoch": 0.85, + "learning_rate": 1.2098146466135475e-06, + "loss": 0.4912, + "step": 10118 + }, + { + "epoch": 0.85, + "learning_rate": 1.2085229203758663e-06, + "loss": 0.4616, + "step": 10119 + }, + { + "epoch": 0.85, + "learning_rate": 1.2072318397476945e-06, + "loss": 0.4577, + "step": 10120 + }, + { + "epoch": 0.85, + "learning_rate": 1.2059414048238437e-06, + "loss": 0.4583, + "step": 10121 + }, + { + "epoch": 0.85, + "learning_rate": 1.2046516156990796e-06, + "loss": 0.4592, + "step": 10122 + }, + { + "epoch": 0.85, + "learning_rate": 1.2033624724681191e-06, + "loss": 0.468, + "step": 10123 + }, + { + "epoch": 0.85, + "learning_rate": 1.2020739752256282e-06, + "loss": 0.4817, + "step": 10124 + }, + { + "epoch": 0.85, + "learning_rate": 1.2007861240662334e-06, + "loss": 0.4542, + "step": 10125 + }, + { + "epoch": 0.85, + "learning_rate": 1.1994989190845075e-06, + "loss": 0.4465, + "step": 10126 + }, + { + "epoch": 0.85, + "learning_rate": 1.1982123603749762e-06, + "loss": 0.455, + "step": 10127 + }, + { + "epoch": 0.85, + "learning_rate": 1.1969264480321175e-06, + "loss": 0.465, + "step": 10128 + }, + { + "epoch": 0.85, + "learning_rate": 1.1956411821503688e-06, + "loss": 0.462, + "step": 10129 + }, + { + "epoch": 0.85, + "learning_rate": 1.1943565628241105e-06, + "loss": 0.4554, + "step": 10130 + }, + { + "epoch": 0.85, + "learning_rate": 1.1930725901476814e-06, + "loss": 0.4542, + "step": 10131 + }, + { + "epoch": 0.85, + "learning_rate": 1.1917892642153706e-06, + "loss": 0.469, + "step": 10132 + }, + { + "epoch": 0.85, + "learning_rate": 1.190506585121418e-06, + "loss": 0.4819, + "step": 10133 + }, + { + "epoch": 0.85, + "learning_rate": 1.1892245529600222e-06, + "loss": 0.4757, + "step": 10134 + }, + { + "epoch": 0.85, + "learning_rate": 1.1879431678253261e-06, + "loss": 0.4704, + "step": 10135 + }, + { + "epoch": 0.85, + "learning_rate": 1.1866624298114338e-06, + "loss": 0.459, + "step": 10136 + }, + { + "epoch": 0.85, + "learning_rate": 1.1853823390123964e-06, + "loss": 0.4646, + "step": 10137 + }, + { + "epoch": 0.85, + "learning_rate": 1.1841028955222155e-06, + "loss": 0.4662, + "step": 10138 + }, + { + "epoch": 0.85, + "learning_rate": 1.1828240994348517e-06, + "loss": 0.4671, + "step": 10139 + }, + { + "epoch": 0.85, + "learning_rate": 1.1815459508442118e-06, + "loss": 0.4511, + "step": 10140 + }, + { + "epoch": 0.85, + "learning_rate": 1.1802684498441585e-06, + "loss": 0.4797, + "step": 10141 + }, + { + "epoch": 0.85, + "learning_rate": 1.1789915965285037e-06, + "loss": 0.4553, + "step": 10142 + }, + { + "epoch": 0.85, + "learning_rate": 1.177715390991019e-06, + "loss": 0.4775, + "step": 10143 + }, + { + "epoch": 0.85, + "learning_rate": 1.1764398333254202e-06, + "loss": 0.4567, + "step": 10144 + }, + { + "epoch": 0.85, + "learning_rate": 1.1751649236253815e-06, + "loss": 0.4767, + "step": 10145 + }, + { + "epoch": 0.85, + "learning_rate": 1.1738906619845248e-06, + "loss": 0.4722, + "step": 10146 + }, + { + "epoch": 0.85, + "learning_rate": 1.1726170484964282e-06, + "loss": 0.4849, + "step": 10147 + }, + { + "epoch": 0.85, + "learning_rate": 1.1713440832546196e-06, + "loss": 0.4432, + "step": 10148 + }, + { + "epoch": 0.85, + "learning_rate": 1.1700717663525784e-06, + "loss": 0.4562, + "step": 10149 + }, + { + "epoch": 0.85, + "learning_rate": 1.1688000978837423e-06, + "loss": 0.478, + "step": 10150 + }, + { + "epoch": 0.85, + "learning_rate": 1.1675290779414949e-06, + "loss": 0.4653, + "step": 10151 + }, + { + "epoch": 0.85, + "learning_rate": 1.1662587066191755e-06, + "loss": 0.4584, + "step": 10152 + }, + { + "epoch": 0.85, + "learning_rate": 1.1649889840100737e-06, + "loss": 0.4666, + "step": 10153 + }, + { + "epoch": 0.85, + "learning_rate": 1.1637199102074326e-06, + "loss": 0.4629, + "step": 10154 + }, + { + "epoch": 0.85, + "learning_rate": 1.1624514853044488e-06, + "loss": 0.4594, + "step": 10155 + }, + { + "epoch": 0.85, + "learning_rate": 1.1611837093942691e-06, + "loss": 0.4912, + "step": 10156 + }, + { + "epoch": 0.85, + "learning_rate": 1.1599165825699955e-06, + "loss": 0.4794, + "step": 10157 + }, + { + "epoch": 0.85, + "learning_rate": 1.1586501049246801e-06, + "loss": 0.4589, + "step": 10158 + }, + { + "epoch": 0.85, + "learning_rate": 1.1573842765513266e-06, + "loss": 0.4812, + "step": 10159 + }, + { + "epoch": 0.85, + "learning_rate": 1.1561190975428926e-06, + "loss": 0.4629, + "step": 10160 + }, + { + "epoch": 0.85, + "learning_rate": 1.1548545679922885e-06, + "loss": 0.4512, + "step": 10161 + }, + { + "epoch": 0.85, + "learning_rate": 1.153590687992372e-06, + "loss": 0.4553, + "step": 10162 + }, + { + "epoch": 0.85, + "learning_rate": 1.1523274576359633e-06, + "loss": 0.4647, + "step": 10163 + }, + { + "epoch": 0.85, + "learning_rate": 1.151064877015825e-06, + "loss": 0.4667, + "step": 10164 + }, + { + "epoch": 0.85, + "learning_rate": 1.1498029462246752e-06, + "loss": 0.4664, + "step": 10165 + }, + { + "epoch": 0.85, + "learning_rate": 1.1485416653551884e-06, + "loss": 0.459, + "step": 10166 + }, + { + "epoch": 0.85, + "learning_rate": 1.1472810344999852e-06, + "loss": 0.4335, + "step": 10167 + }, + { + "epoch": 0.85, + "learning_rate": 1.1460210537516426e-06, + "loss": 0.4746, + "step": 10168 + }, + { + "epoch": 0.85, + "learning_rate": 1.1447617232026842e-06, + "loss": 0.4671, + "step": 10169 + }, + { + "epoch": 0.85, + "learning_rate": 1.1435030429455951e-06, + "loss": 0.4687, + "step": 10170 + }, + { + "epoch": 0.85, + "learning_rate": 1.1422450130728069e-06, + "loss": 0.4722, + "step": 10171 + }, + { + "epoch": 0.85, + "learning_rate": 1.1409876336767013e-06, + "loss": 0.4592, + "step": 10172 + }, + { + "epoch": 0.85, + "learning_rate": 1.1397309048496174e-06, + "loss": 0.4744, + "step": 10173 + }, + { + "epoch": 0.85, + "learning_rate": 1.1384748266838408e-06, + "loss": 0.4578, + "step": 10174 + }, + { + "epoch": 0.85, + "learning_rate": 1.1372193992716175e-06, + "loss": 0.467, + "step": 10175 + }, + { + "epoch": 0.85, + "learning_rate": 1.1359646227051357e-06, + "loss": 0.4537, + "step": 10176 + }, + { + "epoch": 0.85, + "learning_rate": 1.1347104970765466e-06, + "loss": 0.454, + "step": 10177 + }, + { + "epoch": 0.85, + "learning_rate": 1.133457022477945e-06, + "loss": 0.475, + "step": 10178 + }, + { + "epoch": 0.85, + "learning_rate": 1.1322041990013798e-06, + "loss": 0.4638, + "step": 10179 + }, + { + "epoch": 0.85, + "learning_rate": 1.130952026738855e-06, + "loss": 0.4609, + "step": 10180 + }, + { + "epoch": 0.85, + "learning_rate": 1.1297005057823251e-06, + "loss": 0.4676, + "step": 10181 + }, + { + "epoch": 0.85, + "learning_rate": 1.1284496362236952e-06, + "loss": 0.4789, + "step": 10182 + }, + { + "epoch": 0.85, + "learning_rate": 1.1271994181548217e-06, + "loss": 0.4718, + "step": 10183 + }, + { + "epoch": 0.85, + "learning_rate": 1.1259498516675204e-06, + "loss": 0.4717, + "step": 10184 + }, + { + "epoch": 0.85, + "learning_rate": 1.12470093685355e-06, + "loss": 0.4607, + "step": 10185 + }, + { + "epoch": 0.85, + "learning_rate": 1.1234526738046303e-06, + "loss": 0.4358, + "step": 10186 + }, + { + "epoch": 0.85, + "learning_rate": 1.122205062612426e-06, + "loss": 0.474, + "step": 10187 + }, + { + "epoch": 0.85, + "learning_rate": 1.1209581033685558e-06, + "loss": 0.4668, + "step": 10188 + }, + { + "epoch": 0.85, + "learning_rate": 1.1197117961645921e-06, + "loss": 0.4598, + "step": 10189 + }, + { + "epoch": 0.85, + "learning_rate": 1.118466141092055e-06, + "loss": 0.4466, + "step": 10190 + }, + { + "epoch": 0.85, + "learning_rate": 1.1172211382424269e-06, + "loss": 0.4796, + "step": 10191 + }, + { + "epoch": 0.85, + "learning_rate": 1.1159767877071314e-06, + "loss": 0.461, + "step": 10192 + }, + { + "epoch": 0.85, + "learning_rate": 1.1147330895775498e-06, + "loss": 0.472, + "step": 10193 + }, + { + "epoch": 0.85, + "learning_rate": 1.1134900439450124e-06, + "loss": 0.4753, + "step": 10194 + }, + { + "epoch": 0.85, + "learning_rate": 1.112247650900804e-06, + "loss": 0.449, + "step": 10195 + }, + { + "epoch": 0.85, + "learning_rate": 1.1110059105361616e-06, + "loss": 0.4559, + "step": 10196 + }, + { + "epoch": 0.85, + "learning_rate": 1.1097648229422719e-06, + "loss": 0.4649, + "step": 10197 + }, + { + "epoch": 0.85, + "learning_rate": 1.108524388210278e-06, + "loss": 0.4535, + "step": 10198 + }, + { + "epoch": 0.85, + "learning_rate": 1.1072846064312715e-06, + "loss": 0.4645, + "step": 10199 + }, + { + "epoch": 0.85, + "learning_rate": 1.1060454776962947e-06, + "loss": 0.4628, + "step": 10200 + }, + { + "epoch": 0.85, + "learning_rate": 1.1048070020963453e-06, + "loss": 0.4658, + "step": 10201 + }, + { + "epoch": 0.85, + "learning_rate": 1.1035691797223724e-06, + "loss": 0.4706, + "step": 10202 + }, + { + "epoch": 0.85, + "learning_rate": 1.1023320106652735e-06, + "loss": 0.4566, + "step": 10203 + }, + { + "epoch": 0.85, + "learning_rate": 1.1010954950159058e-06, + "loss": 0.4699, + "step": 10204 + }, + { + "epoch": 0.85, + "learning_rate": 1.0998596328650724e-06, + "loss": 0.4587, + "step": 10205 + }, + { + "epoch": 0.85, + "learning_rate": 1.098624424303526e-06, + "loss": 0.4722, + "step": 10206 + }, + { + "epoch": 0.85, + "learning_rate": 1.0973898694219809e-06, + "loss": 0.4548, + "step": 10207 + }, + { + "epoch": 0.85, + "learning_rate": 1.0961559683110946e-06, + "loss": 0.4523, + "step": 10208 + }, + { + "epoch": 0.85, + "learning_rate": 1.0949227210614798e-06, + "loss": 0.4467, + "step": 10209 + }, + { + "epoch": 0.85, + "learning_rate": 1.0936901277637002e-06, + "loss": 0.4952, + "step": 10210 + }, + { + "epoch": 0.85, + "learning_rate": 1.0924581885082753e-06, + "loss": 0.4745, + "step": 10211 + }, + { + "epoch": 0.85, + "learning_rate": 1.0912269033856716e-06, + "loss": 0.45, + "step": 10212 + }, + { + "epoch": 0.85, + "learning_rate": 1.089996272486309e-06, + "loss": 0.4564, + "step": 10213 + }, + { + "epoch": 0.85, + "learning_rate": 1.088766295900562e-06, + "loss": 0.4536, + "step": 10214 + }, + { + "epoch": 0.85, + "learning_rate": 1.0875369737187502e-06, + "loss": 0.4627, + "step": 10215 + }, + { + "epoch": 0.85, + "learning_rate": 1.0863083060311563e-06, + "loss": 0.4539, + "step": 10216 + }, + { + "epoch": 0.85, + "learning_rate": 1.0850802929280034e-06, + "loss": 0.474, + "step": 10217 + }, + { + "epoch": 0.85, + "learning_rate": 1.0838529344994763e-06, + "loss": 0.4448, + "step": 10218 + }, + { + "epoch": 0.85, + "learning_rate": 1.0826262308357038e-06, + "loss": 0.4548, + "step": 10219 + }, + { + "epoch": 0.86, + "learning_rate": 1.0814001820267717e-06, + "loss": 0.4531, + "step": 10220 + }, + { + "epoch": 0.86, + "learning_rate": 1.0801747881627134e-06, + "loss": 0.4624, + "step": 10221 + }, + { + "epoch": 0.86, + "learning_rate": 1.0789500493335191e-06, + "loss": 0.4819, + "step": 10222 + }, + { + "epoch": 0.86, + "learning_rate": 1.0777259656291284e-06, + "loss": 0.4558, + "step": 10223 + }, + { + "epoch": 0.86, + "learning_rate": 1.07650253713943e-06, + "loss": 0.4588, + "step": 10224 + }, + { + "epoch": 0.86, + "learning_rate": 1.0752797639542712e-06, + "loss": 0.4649, + "step": 10225 + }, + { + "epoch": 0.86, + "learning_rate": 1.0740576461634466e-06, + "loss": 0.4855, + "step": 10226 + }, + { + "epoch": 0.86, + "learning_rate": 1.0728361838567003e-06, + "loss": 0.4787, + "step": 10227 + }, + { + "epoch": 0.86, + "learning_rate": 1.0716153771237359e-06, + "loss": 0.4544, + "step": 10228 + }, + { + "epoch": 0.86, + "learning_rate": 1.0703952260542016e-06, + "loss": 0.4666, + "step": 10229 + }, + { + "epoch": 0.86, + "learning_rate": 1.0691757307377014e-06, + "loss": 0.4757, + "step": 10230 + }, + { + "epoch": 0.86, + "learning_rate": 1.0679568912637872e-06, + "loss": 0.4772, + "step": 10231 + }, + { + "epoch": 0.86, + "learning_rate": 1.0667387077219704e-06, + "loss": 0.4798, + "step": 10232 + }, + { + "epoch": 0.86, + "learning_rate": 1.0655211802017052e-06, + "loss": 0.4355, + "step": 10233 + }, + { + "epoch": 0.86, + "learning_rate": 1.0643043087924043e-06, + "loss": 0.4507, + "step": 10234 + }, + { + "epoch": 0.86, + "learning_rate": 1.0630880935834286e-06, + "loss": 0.4636, + "step": 10235 + }, + { + "epoch": 0.86, + "learning_rate": 1.0618725346640902e-06, + "loss": 0.4574, + "step": 10236 + }, + { + "epoch": 0.86, + "learning_rate": 1.0606576321236585e-06, + "loss": 0.473, + "step": 10237 + }, + { + "epoch": 0.86, + "learning_rate": 1.0594433860513452e-06, + "loss": 0.458, + "step": 10238 + }, + { + "epoch": 0.86, + "learning_rate": 1.0582297965363264e-06, + "loss": 0.4414, + "step": 10239 + }, + { + "epoch": 0.86, + "learning_rate": 1.0570168636677191e-06, + "loss": 0.4564, + "step": 10240 + }, + { + "epoch": 0.86, + "learning_rate": 1.055804587534598e-06, + "loss": 0.4609, + "step": 10241 + }, + { + "epoch": 0.86, + "learning_rate": 1.0545929682259847e-06, + "loss": 0.4552, + "step": 10242 + }, + { + "epoch": 0.86, + "learning_rate": 1.0533820058308576e-06, + "loss": 0.487, + "step": 10243 + }, + { + "epoch": 0.86, + "learning_rate": 1.0521717004381427e-06, + "loss": 0.4707, + "step": 10244 + }, + { + "epoch": 0.86, + "learning_rate": 1.0509620521367225e-06, + "loss": 0.4729, + "step": 10245 + }, + { + "epoch": 0.86, + "learning_rate": 1.0497530610154283e-06, + "loss": 0.4663, + "step": 10246 + }, + { + "epoch": 0.86, + "learning_rate": 1.04854472716304e-06, + "loss": 0.4829, + "step": 10247 + }, + { + "epoch": 0.86, + "learning_rate": 1.0473370506682968e-06, + "loss": 0.4565, + "step": 10248 + }, + { + "epoch": 0.86, + "learning_rate": 1.046130031619883e-06, + "loss": 0.4666, + "step": 10249 + }, + { + "epoch": 0.86, + "learning_rate": 1.044923670106439e-06, + "loss": 0.4489, + "step": 10250 + }, + { + "epoch": 0.86, + "learning_rate": 1.0437179662165508e-06, + "loss": 0.4793, + "step": 10251 + }, + { + "epoch": 0.86, + "learning_rate": 1.0425129200387662e-06, + "loss": 0.4564, + "step": 10252 + }, + { + "epoch": 0.86, + "learning_rate": 1.0413085316615745e-06, + "loss": 0.47, + "step": 10253 + }, + { + "epoch": 0.86, + "learning_rate": 1.0401048011734227e-06, + "loss": 0.4469, + "step": 10254 + }, + { + "epoch": 0.86, + "learning_rate": 1.0389017286627078e-06, + "loss": 0.4772, + "step": 10255 + }, + { + "epoch": 0.86, + "learning_rate": 1.0376993142177771e-06, + "loss": 0.475, + "step": 10256 + }, + { + "epoch": 0.86, + "learning_rate": 1.036497557926931e-06, + "loss": 0.4524, + "step": 10257 + }, + { + "epoch": 0.86, + "learning_rate": 1.035296459878421e-06, + "loss": 0.4645, + "step": 10258 + }, + { + "epoch": 0.86, + "learning_rate": 1.0340960201604544e-06, + "loss": 0.4579, + "step": 10259 + }, + { + "epoch": 0.86, + "learning_rate": 1.0328962388611841e-06, + "loss": 0.4659, + "step": 10260 + }, + { + "epoch": 0.86, + "learning_rate": 1.0316971160687172e-06, + "loss": 0.4552, + "step": 10261 + }, + { + "epoch": 0.86, + "learning_rate": 1.0304986518711124e-06, + "loss": 0.452, + "step": 10262 + }, + { + "epoch": 0.86, + "learning_rate": 1.029300846356379e-06, + "loss": 0.4648, + "step": 10263 + }, + { + "epoch": 0.86, + "learning_rate": 1.0281036996124793e-06, + "loss": 0.4696, + "step": 10264 + }, + { + "epoch": 0.86, + "learning_rate": 1.026907211727326e-06, + "loss": 0.4558, + "step": 10265 + }, + { + "epoch": 0.86, + "learning_rate": 1.0257113827887865e-06, + "loss": 0.4506, + "step": 10266 + }, + { + "epoch": 0.86, + "learning_rate": 1.0245162128846764e-06, + "loss": 0.4555, + "step": 10267 + }, + { + "epoch": 0.86, + "learning_rate": 1.023321702102762e-06, + "loss": 0.4706, + "step": 10268 + }, + { + "epoch": 0.86, + "learning_rate": 1.0221278505307665e-06, + "loss": 0.4593, + "step": 10269 + }, + { + "epoch": 0.86, + "learning_rate": 1.0209346582563596e-06, + "loss": 0.4606, + "step": 10270 + }, + { + "epoch": 0.86, + "learning_rate": 1.0197421253671646e-06, + "loss": 0.458, + "step": 10271 + }, + { + "epoch": 0.86, + "learning_rate": 1.018550251950755e-06, + "loss": 0.4643, + "step": 10272 + }, + { + "epoch": 0.86, + "learning_rate": 1.0173590380946596e-06, + "loss": 0.497, + "step": 10273 + }, + { + "epoch": 0.86, + "learning_rate": 1.016168483886356e-06, + "loss": 0.4946, + "step": 10274 + }, + { + "epoch": 0.86, + "learning_rate": 1.0149785894132714e-06, + "loss": 0.4545, + "step": 10275 + }, + { + "epoch": 0.86, + "learning_rate": 1.0137893547627875e-06, + "loss": 0.4669, + "step": 10276 + }, + { + "epoch": 0.86, + "learning_rate": 1.0126007800222347e-06, + "loss": 0.4839, + "step": 10277 + }, + { + "epoch": 0.86, + "learning_rate": 1.0114128652789023e-06, + "loss": 0.4633, + "step": 10278 + }, + { + "epoch": 0.86, + "learning_rate": 1.0102256106200203e-06, + "loss": 0.4627, + "step": 10279 + }, + { + "epoch": 0.86, + "learning_rate": 1.0090390161327801e-06, + "loss": 0.4656, + "step": 10280 + }, + { + "epoch": 0.86, + "learning_rate": 1.0078530819043174e-06, + "loss": 0.4692, + "step": 10281 + }, + { + "epoch": 0.86, + "learning_rate": 1.006667808021725e-06, + "loss": 0.4646, + "step": 10282 + }, + { + "epoch": 0.86, + "learning_rate": 1.0054831945720411e-06, + "loss": 0.4597, + "step": 10283 + }, + { + "epoch": 0.86, + "learning_rate": 1.0042992416422614e-06, + "loss": 0.4651, + "step": 10284 + }, + { + "epoch": 0.86, + "learning_rate": 1.0031159493193277e-06, + "loss": 0.4696, + "step": 10285 + }, + { + "epoch": 0.86, + "learning_rate": 1.001933317690139e-06, + "loss": 0.4727, + "step": 10286 + }, + { + "epoch": 0.86, + "learning_rate": 1.000751346841542e-06, + "loss": 0.4629, + "step": 10287 + }, + { + "epoch": 0.86, + "learning_rate": 9.995700368603333e-07, + "loss": 0.4629, + "step": 10288 + }, + { + "epoch": 0.86, + "learning_rate": 9.983893878332674e-07, + "loss": 0.4644, + "step": 10289 + }, + { + "epoch": 0.86, + "learning_rate": 9.972093998470444e-07, + "loss": 0.4686, + "step": 10290 + }, + { + "epoch": 0.86, + "learning_rate": 9.960300729883177e-07, + "loss": 0.4609, + "step": 10291 + }, + { + "epoch": 0.86, + "learning_rate": 9.9485140734369e-07, + "loss": 0.4454, + "step": 10292 + }, + { + "epoch": 0.86, + "learning_rate": 9.936734029997218e-07, + "loss": 0.4597, + "step": 10293 + }, + { + "epoch": 0.86, + "learning_rate": 9.92496060042919e-07, + "loss": 0.4802, + "step": 10294 + }, + { + "epoch": 0.86, + "learning_rate": 9.913193785597396e-07, + "loss": 0.4629, + "step": 10295 + }, + { + "epoch": 0.86, + "learning_rate": 9.90143358636596e-07, + "loss": 0.4501, + "step": 10296 + }, + { + "epoch": 0.86, + "learning_rate": 9.88968000359849e-07, + "loss": 0.4537, + "step": 10297 + }, + { + "epoch": 0.86, + "learning_rate": 9.877933038158105e-07, + "loss": 0.464, + "step": 10298 + }, + { + "epoch": 0.86, + "learning_rate": 9.866192690907472e-07, + "loss": 0.4678, + "step": 10299 + }, + { + "epoch": 0.86, + "learning_rate": 9.85445896270878e-07, + "loss": 0.4739, + "step": 10300 + }, + { + "epoch": 0.86, + "learning_rate": 9.84273185442367e-07, + "loss": 0.4806, + "step": 10301 + }, + { + "epoch": 0.86, + "learning_rate": 9.831011366913335e-07, + "loss": 0.4504, + "step": 10302 + }, + { + "epoch": 0.86, + "learning_rate": 9.819297501038494e-07, + "loss": 0.4628, + "step": 10303 + }, + { + "epoch": 0.86, + "learning_rate": 9.80759025765935e-07, + "loss": 0.4659, + "step": 10304 + }, + { + "epoch": 0.86, + "learning_rate": 9.795889637635636e-07, + "loss": 0.4496, + "step": 10305 + }, + { + "epoch": 0.86, + "learning_rate": 9.78419564182659e-07, + "loss": 0.4522, + "step": 10306 + }, + { + "epoch": 0.86, + "learning_rate": 9.772508271090997e-07, + "loss": 0.4757, + "step": 10307 + }, + { + "epoch": 0.86, + "learning_rate": 9.760827526287108e-07, + "loss": 0.4711, + "step": 10308 + }, + { + "epoch": 0.86, + "learning_rate": 9.749153408272693e-07, + "loss": 0.4507, + "step": 10309 + }, + { + "epoch": 0.86, + "learning_rate": 9.737485917905088e-07, + "loss": 0.4604, + "step": 10310 + }, + { + "epoch": 0.86, + "learning_rate": 9.725825056041094e-07, + "loss": 0.4598, + "step": 10311 + }, + { + "epoch": 0.86, + "learning_rate": 9.714170823537007e-07, + "loss": 0.471, + "step": 10312 + }, + { + "epoch": 0.86, + "learning_rate": 9.702523221248706e-07, + "loss": 0.4624, + "step": 10313 + }, + { + "epoch": 0.86, + "learning_rate": 9.69088225003152e-07, + "loss": 0.4548, + "step": 10314 + }, + { + "epoch": 0.86, + "learning_rate": 9.679247910740331e-07, + "loss": 0.4672, + "step": 10315 + }, + { + "epoch": 0.86, + "learning_rate": 9.667620204229488e-07, + "loss": 0.4596, + "step": 10316 + }, + { + "epoch": 0.86, + "learning_rate": 9.6559991313529e-07, + "loss": 0.447, + "step": 10317 + }, + { + "epoch": 0.86, + "learning_rate": 9.64438469296396e-07, + "loss": 0.4531, + "step": 10318 + }, + { + "epoch": 0.86, + "learning_rate": 9.632776889915595e-07, + "loss": 0.4692, + "step": 10319 + }, + { + "epoch": 0.86, + "learning_rate": 9.621175723060216e-07, + "loss": 0.4731, + "step": 10320 + }, + { + "epoch": 0.86, + "learning_rate": 9.609581193249794e-07, + "loss": 0.4477, + "step": 10321 + }, + { + "epoch": 0.86, + "learning_rate": 9.597993301335773e-07, + "loss": 0.48, + "step": 10322 + }, + { + "epoch": 0.86, + "learning_rate": 9.586412048169114e-07, + "loss": 0.4617, + "step": 10323 + }, + { + "epoch": 0.86, + "learning_rate": 9.574837434600293e-07, + "loss": 0.4565, + "step": 10324 + }, + { + "epoch": 0.86, + "learning_rate": 9.563269461479307e-07, + "loss": 0.4485, + "step": 10325 + }, + { + "epoch": 0.86, + "learning_rate": 9.551708129655635e-07, + "loss": 0.4653, + "step": 10326 + }, + { + "epoch": 0.86, + "learning_rate": 9.54015343997834e-07, + "loss": 0.46, + "step": 10327 + }, + { + "epoch": 0.86, + "learning_rate": 9.528605393295909e-07, + "loss": 0.4716, + "step": 10328 + }, + { + "epoch": 0.86, + "learning_rate": 9.517063990456399e-07, + "loss": 0.4637, + "step": 10329 + }, + { + "epoch": 0.86, + "learning_rate": 9.505529232307376e-07, + "loss": 0.4507, + "step": 10330 + }, + { + "epoch": 0.86, + "learning_rate": 9.494001119695884e-07, + "loss": 0.4772, + "step": 10331 + }, + { + "epoch": 0.86, + "learning_rate": 9.482479653468512e-07, + "loss": 0.4558, + "step": 10332 + }, + { + "epoch": 0.86, + "learning_rate": 9.47096483447133e-07, + "loss": 0.4491, + "step": 10333 + }, + { + "epoch": 0.86, + "learning_rate": 9.459456663549959e-07, + "loss": 0.4573, + "step": 10334 + }, + { + "epoch": 0.86, + "learning_rate": 9.447955141549514e-07, + "loss": 0.4429, + "step": 10335 + }, + { + "epoch": 0.86, + "learning_rate": 9.436460269314607e-07, + "loss": 0.4629, + "step": 10336 + }, + { + "epoch": 0.86, + "learning_rate": 9.424972047689374e-07, + "loss": 0.4625, + "step": 10337 + }, + { + "epoch": 0.86, + "learning_rate": 9.413490477517462e-07, + "loss": 0.4684, + "step": 10338 + }, + { + "epoch": 0.87, + "learning_rate": 9.402015559642019e-07, + "loss": 0.4807, + "step": 10339 + }, + { + "epoch": 0.87, + "learning_rate": 9.390547294905739e-07, + "loss": 0.4669, + "step": 10340 + }, + { + "epoch": 0.87, + "learning_rate": 9.379085684150779e-07, + "loss": 0.4493, + "step": 10341 + }, + { + "epoch": 0.87, + "learning_rate": 9.367630728218868e-07, + "loss": 0.4639, + "step": 10342 + }, + { + "epoch": 0.87, + "learning_rate": 9.356182427951188e-07, + "loss": 0.4678, + "step": 10343 + }, + { + "epoch": 0.87, + "learning_rate": 9.344740784188445e-07, + "loss": 0.4619, + "step": 10344 + }, + { + "epoch": 0.87, + "learning_rate": 9.333305797770887e-07, + "loss": 0.489, + "step": 10345 + }, + { + "epoch": 0.87, + "learning_rate": 9.321877469538232e-07, + "loss": 0.4565, + "step": 10346 + }, + { + "epoch": 0.87, + "learning_rate": 9.31045580032972e-07, + "loss": 0.4754, + "step": 10347 + }, + { + "epoch": 0.87, + "learning_rate": 9.299040790984137e-07, + "loss": 0.4564, + "step": 10348 + }, + { + "epoch": 0.87, + "learning_rate": 9.287632442339756e-07, + "loss": 0.472, + "step": 10349 + }, + { + "epoch": 0.87, + "learning_rate": 9.276230755234328e-07, + "loss": 0.4752, + "step": 10350 + }, + { + "epoch": 0.87, + "learning_rate": 9.264835730505184e-07, + "loss": 0.4529, + "step": 10351 + }, + { + "epoch": 0.87, + "learning_rate": 9.25344736898911e-07, + "loss": 0.4372, + "step": 10352 + }, + { + "epoch": 0.87, + "learning_rate": 9.242065671522393e-07, + "loss": 0.4867, + "step": 10353 + }, + { + "epoch": 0.87, + "learning_rate": 9.230690638940898e-07, + "loss": 0.4552, + "step": 10354 + }, + { + "epoch": 0.87, + "learning_rate": 9.219322272079955e-07, + "loss": 0.47, + "step": 10355 + }, + { + "epoch": 0.87, + "learning_rate": 9.207960571774388e-07, + "loss": 0.459, + "step": 10356 + }, + { + "epoch": 0.87, + "learning_rate": 9.196605538858571e-07, + "loss": 0.4625, + "step": 10357 + }, + { + "epoch": 0.87, + "learning_rate": 9.185257174166362e-07, + "loss": 0.4528, + "step": 10358 + }, + { + "epoch": 0.87, + "learning_rate": 9.173915478531148e-07, + "loss": 0.4446, + "step": 10359 + }, + { + "epoch": 0.87, + "learning_rate": 9.162580452785775e-07, + "loss": 0.477, + "step": 10360 + }, + { + "epoch": 0.87, + "learning_rate": 9.151252097762675e-07, + "loss": 0.4613, + "step": 10361 + }, + { + "epoch": 0.87, + "learning_rate": 9.139930414293774e-07, + "loss": 0.4511, + "step": 10362 + }, + { + "epoch": 0.87, + "learning_rate": 9.128615403210472e-07, + "loss": 0.4492, + "step": 10363 + }, + { + "epoch": 0.87, + "learning_rate": 9.117307065343683e-07, + "loss": 0.4666, + "step": 10364 + }, + { + "epoch": 0.87, + "learning_rate": 9.106005401523865e-07, + "loss": 0.4672, + "step": 10365 + }, + { + "epoch": 0.87, + "learning_rate": 9.094710412580942e-07, + "loss": 0.4787, + "step": 10366 + }, + { + "epoch": 0.87, + "learning_rate": 9.083422099344375e-07, + "loss": 0.4664, + "step": 10367 + }, + { + "epoch": 0.87, + "learning_rate": 9.072140462643154e-07, + "loss": 0.4515, + "step": 10368 + }, + { + "epoch": 0.87, + "learning_rate": 9.060865503305738e-07, + "loss": 0.4508, + "step": 10369 + }, + { + "epoch": 0.87, + "learning_rate": 9.049597222160111e-07, + "loss": 0.4644, + "step": 10370 + }, + { + "epoch": 0.87, + "learning_rate": 9.038335620033756e-07, + "loss": 0.4454, + "step": 10371 + }, + { + "epoch": 0.87, + "learning_rate": 9.02708069775372e-07, + "loss": 0.4649, + "step": 10372 + }, + { + "epoch": 0.87, + "learning_rate": 9.015832456146489e-07, + "loss": 0.4778, + "step": 10373 + }, + { + "epoch": 0.87, + "learning_rate": 9.004590896038068e-07, + "loss": 0.4462, + "step": 10374 + }, + { + "epoch": 0.87, + "learning_rate": 8.99335601825404e-07, + "loss": 0.4462, + "step": 10375 + }, + { + "epoch": 0.87, + "learning_rate": 8.982127823619413e-07, + "loss": 0.4594, + "step": 10376 + }, + { + "epoch": 0.87, + "learning_rate": 8.970906312958749e-07, + "loss": 0.4522, + "step": 10377 + }, + { + "epoch": 0.87, + "learning_rate": 8.959691487096111e-07, + "loss": 0.482, + "step": 10378 + }, + { + "epoch": 0.87, + "learning_rate": 8.948483346855064e-07, + "loss": 0.4502, + "step": 10379 + }, + { + "epoch": 0.87, + "learning_rate": 8.937281893058658e-07, + "loss": 0.4623, + "step": 10380 + }, + { + "epoch": 0.87, + "learning_rate": 8.926087126529548e-07, + "loss": 0.4559, + "step": 10381 + }, + { + "epoch": 0.87, + "learning_rate": 8.914899048089765e-07, + "loss": 0.4734, + "step": 10382 + }, + { + "epoch": 0.87, + "learning_rate": 8.903717658560961e-07, + "loss": 0.4638, + "step": 10383 + }, + { + "epoch": 0.87, + "learning_rate": 8.892542958764238e-07, + "loss": 0.4368, + "step": 10384 + }, + { + "epoch": 0.87, + "learning_rate": 8.881374949520216e-07, + "loss": 0.4844, + "step": 10385 + }, + { + "epoch": 0.87, + "learning_rate": 8.870213631649038e-07, + "loss": 0.4673, + "step": 10386 + }, + { + "epoch": 0.87, + "learning_rate": 8.859059005970305e-07, + "loss": 0.4555, + "step": 10387 + }, + { + "epoch": 0.87, + "learning_rate": 8.847911073303206e-07, + "loss": 0.4701, + "step": 10388 + }, + { + "epoch": 0.87, + "learning_rate": 8.836769834466397e-07, + "loss": 0.4677, + "step": 10389 + }, + { + "epoch": 0.87, + "learning_rate": 8.825635290278034e-07, + "loss": 0.4631, + "step": 10390 + }, + { + "epoch": 0.87, + "learning_rate": 8.814507441555775e-07, + "loss": 0.4691, + "step": 10391 + }, + { + "epoch": 0.87, + "learning_rate": 8.803386289116833e-07, + "loss": 0.4743, + "step": 10392 + }, + { + "epoch": 0.87, + "learning_rate": 8.792271833777888e-07, + "loss": 0.4724, + "step": 10393 + }, + { + "epoch": 0.87, + "learning_rate": 8.78116407635512e-07, + "loss": 0.4461, + "step": 10394 + }, + { + "epoch": 0.87, + "learning_rate": 8.770063017664276e-07, + "loss": 0.4705, + "step": 10395 + }, + { + "epoch": 0.87, + "learning_rate": 8.75896865852055e-07, + "loss": 0.4547, + "step": 10396 + }, + { + "epoch": 0.87, + "learning_rate": 8.747880999738667e-07, + "loss": 0.4837, + "step": 10397 + }, + { + "epoch": 0.87, + "learning_rate": 8.736800042132853e-07, + "loss": 0.4696, + "step": 10398 + }, + { + "epoch": 0.87, + "learning_rate": 8.725725786516858e-07, + "loss": 0.4605, + "step": 10399 + }, + { + "epoch": 0.87, + "learning_rate": 8.714658233703921e-07, + "loss": 0.4868, + "step": 10400 + }, + { + "epoch": 0.87, + "learning_rate": 8.703597384506779e-07, + "loss": 0.4542, + "step": 10401 + }, + { + "epoch": 0.87, + "learning_rate": 8.692543239737706e-07, + "loss": 0.4542, + "step": 10402 + }, + { + "epoch": 0.87, + "learning_rate": 8.681495800208517e-07, + "loss": 0.4587, + "step": 10403 + }, + { + "epoch": 0.87, + "learning_rate": 8.670455066730444e-07, + "loss": 0.4659, + "step": 10404 + }, + { + "epoch": 0.87, + "learning_rate": 8.65942104011428e-07, + "loss": 0.474, + "step": 10405 + }, + { + "epoch": 0.87, + "learning_rate": 8.648393721170323e-07, + "loss": 0.4734, + "step": 10406 + }, + { + "epoch": 0.87, + "learning_rate": 8.63737311070837e-07, + "loss": 0.4765, + "step": 10407 + }, + { + "epoch": 0.87, + "learning_rate": 8.626359209537716e-07, + "loss": 0.4577, + "step": 10408 + }, + { + "epoch": 0.87, + "learning_rate": 8.615352018467204e-07, + "loss": 0.4625, + "step": 10409 + }, + { + "epoch": 0.87, + "learning_rate": 8.604351538305156e-07, + "loss": 0.4697, + "step": 10410 + }, + { + "epoch": 0.87, + "learning_rate": 8.593357769859368e-07, + "loss": 0.4622, + "step": 10411 + }, + { + "epoch": 0.87, + "learning_rate": 8.582370713937193e-07, + "loss": 0.4769, + "step": 10412 + }, + { + "epoch": 0.87, + "learning_rate": 8.571390371345489e-07, + "loss": 0.4899, + "step": 10413 + }, + { + "epoch": 0.87, + "learning_rate": 8.560416742890599e-07, + "loss": 0.4746, + "step": 10414 + }, + { + "epoch": 0.87, + "learning_rate": 8.549449829378354e-07, + "loss": 0.4566, + "step": 10415 + }, + { + "epoch": 0.87, + "learning_rate": 8.538489631614167e-07, + "loss": 0.4804, + "step": 10416 + }, + { + "epoch": 0.87, + "learning_rate": 8.527536150402882e-07, + "loss": 0.4592, + "step": 10417 + }, + { + "epoch": 0.87, + "learning_rate": 8.516589386548879e-07, + "loss": 0.4471, + "step": 10418 + }, + { + "epoch": 0.87, + "learning_rate": 8.505649340856048e-07, + "loss": 0.4799, + "step": 10419 + }, + { + "epoch": 0.87, + "learning_rate": 8.494716014127768e-07, + "loss": 0.4877, + "step": 10420 + }, + { + "epoch": 0.87, + "learning_rate": 8.483789407166932e-07, + "loss": 0.4582, + "step": 10421 + }, + { + "epoch": 0.87, + "learning_rate": 8.472869520775972e-07, + "loss": 0.4554, + "step": 10422 + }, + { + "epoch": 0.87, + "learning_rate": 8.461956355756772e-07, + "loss": 0.4487, + "step": 10423 + }, + { + "epoch": 0.87, + "learning_rate": 8.451049912910769e-07, + "loss": 0.4454, + "step": 10424 + }, + { + "epoch": 0.87, + "learning_rate": 8.440150193038888e-07, + "loss": 0.4578, + "step": 10425 + }, + { + "epoch": 0.87, + "learning_rate": 8.429257196941554e-07, + "loss": 0.4786, + "step": 10426 + }, + { + "epoch": 0.87, + "learning_rate": 8.418370925418695e-07, + "loss": 0.4635, + "step": 10427 + }, + { + "epoch": 0.87, + "learning_rate": 8.407491379269739e-07, + "loss": 0.4748, + "step": 10428 + }, + { + "epoch": 0.87, + "learning_rate": 8.396618559293679e-07, + "loss": 0.4652, + "step": 10429 + }, + { + "epoch": 0.87, + "learning_rate": 8.385752466288933e-07, + "loss": 0.4624, + "step": 10430 + }, + { + "epoch": 0.87, + "learning_rate": 8.374893101053482e-07, + "loss": 0.4563, + "step": 10431 + }, + { + "epoch": 0.87, + "learning_rate": 8.364040464384771e-07, + "loss": 0.4677, + "step": 10432 + }, + { + "epoch": 0.87, + "learning_rate": 8.353194557079791e-07, + "loss": 0.4588, + "step": 10433 + }, + { + "epoch": 0.87, + "learning_rate": 8.34235537993503e-07, + "loss": 0.4498, + "step": 10434 + }, + { + "epoch": 0.87, + "learning_rate": 8.331522933746428e-07, + "loss": 0.4734, + "step": 10435 + }, + { + "epoch": 0.87, + "learning_rate": 8.320697219309526e-07, + "loss": 0.4523, + "step": 10436 + }, + { + "epoch": 0.87, + "learning_rate": 8.309878237419289e-07, + "loss": 0.4687, + "step": 10437 + }, + { + "epoch": 0.87, + "learning_rate": 8.299065988870236e-07, + "loss": 0.4675, + "step": 10438 + }, + { + "epoch": 0.87, + "learning_rate": 8.288260474456367e-07, + "loss": 0.4673, + "step": 10439 + }, + { + "epoch": 0.87, + "learning_rate": 8.277461694971178e-07, + "loss": 0.4436, + "step": 10440 + }, + { + "epoch": 0.87, + "learning_rate": 8.266669651207704e-07, + "loss": 0.4659, + "step": 10441 + }, + { + "epoch": 0.87, + "learning_rate": 8.255884343958453e-07, + "loss": 0.4867, + "step": 10442 + }, + { + "epoch": 0.87, + "learning_rate": 8.245105774015461e-07, + "loss": 0.4468, + "step": 10443 + }, + { + "epoch": 0.87, + "learning_rate": 8.234333942170281e-07, + "loss": 0.4678, + "step": 10444 + }, + { + "epoch": 0.87, + "learning_rate": 8.223568849213925e-07, + "loss": 0.4726, + "step": 10445 + }, + { + "epoch": 0.87, + "learning_rate": 8.212810495936952e-07, + "loss": 0.4651, + "step": 10446 + }, + { + "epoch": 0.87, + "learning_rate": 8.202058883129404e-07, + "loss": 0.474, + "step": 10447 + }, + { + "epoch": 0.87, + "learning_rate": 8.191314011580842e-07, + "loss": 0.4809, + "step": 10448 + }, + { + "epoch": 0.87, + "learning_rate": 8.180575882080288e-07, + "loss": 0.4541, + "step": 10449 + }, + { + "epoch": 0.87, + "learning_rate": 8.169844495416368e-07, + "loss": 0.4656, + "step": 10450 + }, + { + "epoch": 0.87, + "learning_rate": 8.159119852377106e-07, + "loss": 0.4456, + "step": 10451 + }, + { + "epoch": 0.87, + "learning_rate": 8.148401953750096e-07, + "loss": 0.4625, + "step": 10452 + }, + { + "epoch": 0.87, + "learning_rate": 8.137690800322384e-07, + "loss": 0.4638, + "step": 10453 + }, + { + "epoch": 0.87, + "learning_rate": 8.126986392880587e-07, + "loss": 0.4811, + "step": 10454 + }, + { + "epoch": 0.87, + "learning_rate": 8.116288732210787e-07, + "loss": 0.4776, + "step": 10455 + }, + { + "epoch": 0.87, + "learning_rate": 8.105597819098554e-07, + "loss": 0.4533, + "step": 10456 + }, + { + "epoch": 0.87, + "learning_rate": 8.094913654329018e-07, + "loss": 0.4689, + "step": 10457 + }, + { + "epoch": 0.87, + "learning_rate": 8.08423623868676e-07, + "loss": 0.4605, + "step": 10458 + }, + { + "epoch": 0.88, + "learning_rate": 8.073565572955877e-07, + "loss": 0.4652, + "step": 10459 + }, + { + "epoch": 0.88, + "learning_rate": 8.062901657919998e-07, + "loss": 0.4584, + "step": 10460 + }, + { + "epoch": 0.88, + "learning_rate": 8.052244494362227e-07, + "loss": 0.4699, + "step": 10461 + }, + { + "epoch": 0.88, + "learning_rate": 8.041594083065152e-07, + "loss": 0.4525, + "step": 10462 + }, + { + "epoch": 0.88, + "learning_rate": 8.030950424810946e-07, + "loss": 0.476, + "step": 10463 + }, + { + "epoch": 0.88, + "learning_rate": 8.020313520381206e-07, + "loss": 0.4795, + "step": 10464 + }, + { + "epoch": 0.88, + "learning_rate": 8.009683370557075e-07, + "loss": 0.4751, + "step": 10465 + }, + { + "epoch": 0.88, + "learning_rate": 7.999059976119183e-07, + "loss": 0.4427, + "step": 10466 + }, + { + "epoch": 0.88, + "learning_rate": 7.988443337847673e-07, + "loss": 0.4616, + "step": 10467 + }, + { + "epoch": 0.88, + "learning_rate": 7.977833456522166e-07, + "loss": 0.4687, + "step": 10468 + }, + { + "epoch": 0.88, + "learning_rate": 7.967230332921816e-07, + "loss": 0.4731, + "step": 10469 + }, + { + "epoch": 0.88, + "learning_rate": 7.956633967825289e-07, + "loss": 0.4715, + "step": 10470 + }, + { + "epoch": 0.88, + "learning_rate": 7.946044362010718e-07, + "loss": 0.4532, + "step": 10471 + }, + { + "epoch": 0.88, + "learning_rate": 7.935461516255782e-07, + "loss": 0.4768, + "step": 10472 + }, + { + "epoch": 0.88, + "learning_rate": 7.924885431337604e-07, + "loss": 0.4527, + "step": 10473 + }, + { + "epoch": 0.88, + "learning_rate": 7.914316108032882e-07, + "loss": 0.4693, + "step": 10474 + }, + { + "epoch": 0.88, + "learning_rate": 7.903753547117788e-07, + "loss": 0.4768, + "step": 10475 + }, + { + "epoch": 0.88, + "learning_rate": 7.893197749367943e-07, + "loss": 0.4678, + "step": 10476 + }, + { + "epoch": 0.88, + "learning_rate": 7.882648715558583e-07, + "loss": 0.4589, + "step": 10477 + }, + { + "epoch": 0.88, + "learning_rate": 7.872106446464345e-07, + "loss": 0.4649, + "step": 10478 + }, + { + "epoch": 0.88, + "learning_rate": 7.861570942859431e-07, + "loss": 0.4652, + "step": 10479 + }, + { + "epoch": 0.88, + "learning_rate": 7.851042205517512e-07, + "loss": 0.4853, + "step": 10480 + }, + { + "epoch": 0.88, + "learning_rate": 7.840520235211768e-07, + "loss": 0.4503, + "step": 10481 + }, + { + "epoch": 0.88, + "learning_rate": 7.830005032714905e-07, + "loss": 0.463, + "step": 10482 + }, + { + "epoch": 0.88, + "learning_rate": 7.819496598799093e-07, + "loss": 0.4523, + "step": 10483 + }, + { + "epoch": 0.88, + "learning_rate": 7.808994934236058e-07, + "loss": 0.4681, + "step": 10484 + }, + { + "epoch": 0.88, + "learning_rate": 7.798500039796974e-07, + "loss": 0.4989, + "step": 10485 + }, + { + "epoch": 0.88, + "learning_rate": 7.788011916252558e-07, + "loss": 0.4629, + "step": 10486 + }, + { + "epoch": 0.88, + "learning_rate": 7.777530564373015e-07, + "loss": 0.4475, + "step": 10487 + }, + { + "epoch": 0.88, + "learning_rate": 7.767055984928041e-07, + "loss": 0.4632, + "step": 10488 + }, + { + "epoch": 0.88, + "learning_rate": 7.756588178686853e-07, + "loss": 0.4704, + "step": 10489 + }, + { + "epoch": 0.88, + "learning_rate": 7.746127146418148e-07, + "loss": 0.4527, + "step": 10490 + }, + { + "epoch": 0.88, + "learning_rate": 7.735672888890155e-07, + "loss": 0.4651, + "step": 10491 + }, + { + "epoch": 0.88, + "learning_rate": 7.725225406870607e-07, + "loss": 0.4569, + "step": 10492 + }, + { + "epoch": 0.88, + "learning_rate": 7.714784701126687e-07, + "loss": 0.464, + "step": 10493 + }, + { + "epoch": 0.88, + "learning_rate": 7.704350772425129e-07, + "loss": 0.4621, + "step": 10494 + }, + { + "epoch": 0.88, + "learning_rate": 7.693923621532184e-07, + "loss": 0.4683, + "step": 10495 + }, + { + "epoch": 0.88, + "learning_rate": 7.683503249213554e-07, + "loss": 0.4905, + "step": 10496 + }, + { + "epoch": 0.88, + "learning_rate": 7.673089656234456e-07, + "loss": 0.4562, + "step": 10497 + }, + { + "epoch": 0.88, + "learning_rate": 7.662682843359648e-07, + "loss": 0.4489, + "step": 10498 + }, + { + "epoch": 0.88, + "learning_rate": 7.652282811353362e-07, + "loss": 0.4638, + "step": 10499 + }, + { + "epoch": 0.88, + "learning_rate": 7.641889560979321e-07, + "loss": 0.4682, + "step": 10500 + }, + { + "epoch": 0.88, + "learning_rate": 7.631503093000758e-07, + "loss": 0.4702, + "step": 10501 + }, + { + "epoch": 0.88, + "learning_rate": 7.621123408180419e-07, + "loss": 0.4686, + "step": 10502 + }, + { + "epoch": 0.88, + "learning_rate": 7.61075050728054e-07, + "loss": 0.452, + "step": 10503 + }, + { + "epoch": 0.88, + "learning_rate": 7.600384391062865e-07, + "loss": 0.4584, + "step": 10504 + }, + { + "epoch": 0.88, + "learning_rate": 7.590025060288642e-07, + "loss": 0.4783, + "step": 10505 + }, + { + "epoch": 0.88, + "learning_rate": 7.579672515718628e-07, + "loss": 0.4468, + "step": 10506 + }, + { + "epoch": 0.88, + "learning_rate": 7.569326758113049e-07, + "loss": 0.4802, + "step": 10507 + }, + { + "epoch": 0.88, + "learning_rate": 7.558987788231675e-07, + "loss": 0.4594, + "step": 10508 + }, + { + "epoch": 0.88, + "learning_rate": 7.548655606833755e-07, + "loss": 0.4826, + "step": 10509 + }, + { + "epoch": 0.88, + "learning_rate": 7.538330214678002e-07, + "loss": 0.4664, + "step": 10510 + }, + { + "epoch": 0.88, + "learning_rate": 7.528011612522723e-07, + "loss": 0.4502, + "step": 10511 + }, + { + "epoch": 0.88, + "learning_rate": 7.517699801125655e-07, + "loss": 0.45, + "step": 10512 + }, + { + "epoch": 0.88, + "learning_rate": 7.507394781244038e-07, + "loss": 0.4798, + "step": 10513 + }, + { + "epoch": 0.88, + "learning_rate": 7.497096553634653e-07, + "loss": 0.4694, + "step": 10514 + }, + { + "epoch": 0.88, + "learning_rate": 7.48680511905373e-07, + "loss": 0.4539, + "step": 10515 + }, + { + "epoch": 0.88, + "learning_rate": 7.476520478257065e-07, + "loss": 0.466, + "step": 10516 + }, + { + "epoch": 0.88, + "learning_rate": 7.466242631999887e-07, + "loss": 0.4647, + "step": 10517 + }, + { + "epoch": 0.88, + "learning_rate": 7.455971581036991e-07, + "loss": 0.4704, + "step": 10518 + }, + { + "epoch": 0.88, + "learning_rate": 7.44570732612262e-07, + "loss": 0.4576, + "step": 10519 + }, + { + "epoch": 0.88, + "learning_rate": 7.435449868010535e-07, + "loss": 0.4648, + "step": 10520 + }, + { + "epoch": 0.88, + "learning_rate": 7.425199207454014e-07, + "loss": 0.4485, + "step": 10521 + }, + { + "epoch": 0.88, + "learning_rate": 7.41495534520581e-07, + "loss": 0.4636, + "step": 10522 + }, + { + "epoch": 0.88, + "learning_rate": 7.404718282018197e-07, + "loss": 0.4768, + "step": 10523 + }, + { + "epoch": 0.88, + "learning_rate": 7.394488018642931e-07, + "loss": 0.4482, + "step": 10524 + }, + { + "epoch": 0.88, + "learning_rate": 7.3842645558313e-07, + "loss": 0.4373, + "step": 10525 + }, + { + "epoch": 0.88, + "learning_rate": 7.374047894334047e-07, + "loss": 0.4618, + "step": 10526 + }, + { + "epoch": 0.88, + "learning_rate": 7.363838034901471e-07, + "loss": 0.4681, + "step": 10527 + }, + { + "epoch": 0.88, + "learning_rate": 7.35363497828333e-07, + "loss": 0.4577, + "step": 10528 + }, + { + "epoch": 0.88, + "learning_rate": 7.343438725228891e-07, + "loss": 0.4653, + "step": 10529 + }, + { + "epoch": 0.88, + "learning_rate": 7.33324927648692e-07, + "loss": 0.4989, + "step": 10530 + }, + { + "epoch": 0.88, + "learning_rate": 7.323066632805676e-07, + "loss": 0.4368, + "step": 10531 + }, + { + "epoch": 0.88, + "learning_rate": 7.312890794932969e-07, + "loss": 0.4771, + "step": 10532 + }, + { + "epoch": 0.88, + "learning_rate": 7.302721763616039e-07, + "loss": 0.4751, + "step": 10533 + }, + { + "epoch": 0.88, + "learning_rate": 7.292559539601674e-07, + "loss": 0.4537, + "step": 10534 + }, + { + "epoch": 0.88, + "learning_rate": 7.28240412363611e-07, + "loss": 0.4543, + "step": 10535 + }, + { + "epoch": 0.88, + "learning_rate": 7.272255516465176e-07, + "loss": 0.4839, + "step": 10536 + }, + { + "epoch": 0.88, + "learning_rate": 7.262113718834086e-07, + "loss": 0.4525, + "step": 10537 + }, + { + "epoch": 0.88, + "learning_rate": 7.251978731487664e-07, + "loss": 0.4823, + "step": 10538 + }, + { + "epoch": 0.88, + "learning_rate": 7.241850555170149e-07, + "loss": 0.4638, + "step": 10539 + }, + { + "epoch": 0.88, + "learning_rate": 7.231729190625314e-07, + "loss": 0.4807, + "step": 10540 + }, + { + "epoch": 0.88, + "learning_rate": 7.221614638596441e-07, + "loss": 0.4729, + "step": 10541 + }, + { + "epoch": 0.88, + "learning_rate": 7.211506899826304e-07, + "loss": 0.4802, + "step": 10542 + }, + { + "epoch": 0.88, + "learning_rate": 7.201405975057152e-07, + "loss": 0.4365, + "step": 10543 + }, + { + "epoch": 0.88, + "learning_rate": 7.191311865030748e-07, + "loss": 0.4644, + "step": 10544 + }, + { + "epoch": 0.88, + "learning_rate": 7.18122457048841e-07, + "loss": 0.4555, + "step": 10545 + }, + { + "epoch": 0.88, + "learning_rate": 7.171144092170845e-07, + "loss": 0.4495, + "step": 10546 + }, + { + "epoch": 0.88, + "learning_rate": 7.161070430818385e-07, + "loss": 0.4348, + "step": 10547 + }, + { + "epoch": 0.88, + "learning_rate": 7.151003587170757e-07, + "loss": 0.4765, + "step": 10548 + }, + { + "epoch": 0.88, + "learning_rate": 7.14094356196724e-07, + "loss": 0.4557, + "step": 10549 + }, + { + "epoch": 0.88, + "learning_rate": 7.130890355946596e-07, + "loss": 0.4436, + "step": 10550 + }, + { + "epoch": 0.88, + "learning_rate": 7.12084396984708e-07, + "loss": 0.4619, + "step": 10551 + }, + { + "epoch": 0.88, + "learning_rate": 7.11080440440648e-07, + "loss": 0.4572, + "step": 10552 + }, + { + "epoch": 0.88, + "learning_rate": 7.100771660362061e-07, + "loss": 0.464, + "step": 10553 + }, + { + "epoch": 0.88, + "learning_rate": 7.090745738450566e-07, + "loss": 0.465, + "step": 10554 + }, + { + "epoch": 0.88, + "learning_rate": 7.080726639408264e-07, + "loss": 0.4505, + "step": 10555 + }, + { + "epoch": 0.88, + "learning_rate": 7.070714363970899e-07, + "loss": 0.458, + "step": 10556 + }, + { + "epoch": 0.88, + "learning_rate": 7.060708912873771e-07, + "loss": 0.4661, + "step": 10557 + }, + { + "epoch": 0.88, + "learning_rate": 7.050710286851603e-07, + "loss": 0.4561, + "step": 10558 + }, + { + "epoch": 0.88, + "learning_rate": 7.040718486638676e-07, + "loss": 0.4619, + "step": 10559 + }, + { + "epoch": 0.88, + "learning_rate": 7.030733512968735e-07, + "loss": 0.4623, + "step": 10560 + }, + { + "epoch": 0.88, + "learning_rate": 7.020755366575038e-07, + "loss": 0.4636, + "step": 10561 + }, + { + "epoch": 0.88, + "learning_rate": 7.010784048190344e-07, + "loss": 0.4576, + "step": 10562 + }, + { + "epoch": 0.88, + "learning_rate": 7.000819558546901e-07, + "loss": 0.4482, + "step": 10563 + }, + { + "epoch": 0.88, + "learning_rate": 6.990861898376444e-07, + "loss": 0.4662, + "step": 10564 + }, + { + "epoch": 0.88, + "learning_rate": 6.980911068410224e-07, + "loss": 0.4577, + "step": 10565 + }, + { + "epoch": 0.88, + "learning_rate": 6.97096706937902e-07, + "loss": 0.4521, + "step": 10566 + }, + { + "epoch": 0.88, + "learning_rate": 6.961029902013039e-07, + "loss": 0.452, + "step": 10567 + }, + { + "epoch": 0.88, + "learning_rate": 6.951099567042052e-07, + "loss": 0.4763, + "step": 10568 + }, + { + "epoch": 0.88, + "learning_rate": 6.941176065195299e-07, + "loss": 0.4561, + "step": 10569 + }, + { + "epoch": 0.88, + "learning_rate": 6.931259397201517e-07, + "loss": 0.4594, + "step": 10570 + }, + { + "epoch": 0.88, + "learning_rate": 6.921349563788949e-07, + "loss": 0.4663, + "step": 10571 + }, + { + "epoch": 0.88, + "learning_rate": 6.911446565685298e-07, + "loss": 0.4581, + "step": 10572 + }, + { + "epoch": 0.88, + "learning_rate": 6.901550403617852e-07, + "loss": 0.4803, + "step": 10573 + }, + { + "epoch": 0.88, + "learning_rate": 6.891661078313317e-07, + "loss": 0.4621, + "step": 10574 + }, + { + "epoch": 0.88, + "learning_rate": 6.881778590497923e-07, + "loss": 0.4698, + "step": 10575 + }, + { + "epoch": 0.88, + "learning_rate": 6.87190294089738e-07, + "loss": 0.4748, + "step": 10576 + }, + { + "epoch": 0.88, + "learning_rate": 6.86203413023696e-07, + "loss": 0.453, + "step": 10577 + }, + { + "epoch": 0.89, + "learning_rate": 6.852172159241343e-07, + "loss": 0.4714, + "step": 10578 + }, + { + "epoch": 0.89, + "learning_rate": 6.842317028634793e-07, + "loss": 0.4762, + "step": 10579 + }, + { + "epoch": 0.89, + "learning_rate": 6.832468739141007e-07, + "loss": 0.4559, + "step": 10580 + }, + { + "epoch": 0.89, + "learning_rate": 6.822627291483197e-07, + "loss": 0.4699, + "step": 10581 + }, + { + "epoch": 0.89, + "learning_rate": 6.812792686384095e-07, + "loss": 0.4521, + "step": 10582 + }, + { + "epoch": 0.89, + "learning_rate": 6.802964924565891e-07, + "loss": 0.4515, + "step": 10583 + }, + { + "epoch": 0.89, + "learning_rate": 6.793144006750318e-07, + "loss": 0.4689, + "step": 10584 + }, + { + "epoch": 0.89, + "learning_rate": 6.783329933658555e-07, + "loss": 0.4531, + "step": 10585 + }, + { + "epoch": 0.89, + "learning_rate": 6.773522706011337e-07, + "loss": 0.4877, + "step": 10586 + }, + { + "epoch": 0.89, + "learning_rate": 6.763722324528843e-07, + "loss": 0.4599, + "step": 10587 + }, + { + "epoch": 0.89, + "learning_rate": 6.753928789930797e-07, + "loss": 0.469, + "step": 10588 + }, + { + "epoch": 0.89, + "learning_rate": 6.74414210293638e-07, + "loss": 0.4548, + "step": 10589 + }, + { + "epoch": 0.89, + "learning_rate": 6.734362264264283e-07, + "loss": 0.4717, + "step": 10590 + }, + { + "epoch": 0.89, + "learning_rate": 6.724589274632698e-07, + "loss": 0.4463, + "step": 10591 + }, + { + "epoch": 0.89, + "learning_rate": 6.714823134759307e-07, + "loss": 0.4454, + "step": 10592 + }, + { + "epoch": 0.89, + "learning_rate": 6.705063845361315e-07, + "loss": 0.4723, + "step": 10593 + }, + { + "epoch": 0.89, + "learning_rate": 6.695311407155391e-07, + "loss": 0.4621, + "step": 10594 + }, + { + "epoch": 0.89, + "learning_rate": 6.68556582085772e-07, + "loss": 0.4683, + "step": 10595 + }, + { + "epoch": 0.89, + "learning_rate": 6.675827087183961e-07, + "loss": 0.4772, + "step": 10596 + }, + { + "epoch": 0.89, + "learning_rate": 6.666095206849288e-07, + "loss": 0.4646, + "step": 10597 + }, + { + "epoch": 0.89, + "learning_rate": 6.656370180568395e-07, + "loss": 0.4574, + "step": 10598 + }, + { + "epoch": 0.89, + "learning_rate": 6.646652009055409e-07, + "loss": 0.4854, + "step": 10599 + }, + { + "epoch": 0.89, + "learning_rate": 6.63694069302403e-07, + "loss": 0.4795, + "step": 10600 + }, + { + "epoch": 0.89, + "learning_rate": 6.627236233187407e-07, + "loss": 0.4678, + "step": 10601 + }, + { + "epoch": 0.89, + "learning_rate": 6.61753863025818e-07, + "loss": 0.4546, + "step": 10602 + }, + { + "epoch": 0.89, + "learning_rate": 6.607847884948515e-07, + "loss": 0.4514, + "step": 10603 + }, + { + "epoch": 0.89, + "learning_rate": 6.598163997970053e-07, + "loss": 0.4607, + "step": 10604 + }, + { + "epoch": 0.89, + "learning_rate": 6.588486970033936e-07, + "loss": 0.467, + "step": 10605 + }, + { + "epoch": 0.89, + "learning_rate": 6.578816801850796e-07, + "loss": 0.461, + "step": 10606 + }, + { + "epoch": 0.89, + "learning_rate": 6.569153494130798e-07, + "loss": 0.4654, + "step": 10607 + }, + { + "epoch": 0.89, + "learning_rate": 6.55949704758354e-07, + "loss": 0.485, + "step": 10608 + }, + { + "epoch": 0.89, + "learning_rate": 6.549847462918191e-07, + "loss": 0.4681, + "step": 10609 + }, + { + "epoch": 0.89, + "learning_rate": 6.540204740843348e-07, + "loss": 0.4647, + "step": 10610 + }, + { + "epoch": 0.89, + "learning_rate": 6.530568882067145e-07, + "loss": 0.4694, + "step": 10611 + }, + { + "epoch": 0.89, + "learning_rate": 6.520939887297184e-07, + "loss": 0.4592, + "step": 10612 + }, + { + "epoch": 0.89, + "learning_rate": 6.511317757240598e-07, + "loss": 0.4805, + "step": 10613 + }, + { + "epoch": 0.89, + "learning_rate": 6.50170249260399e-07, + "loss": 0.4699, + "step": 10614 + }, + { + "epoch": 0.89, + "learning_rate": 6.492094094093459e-07, + "loss": 0.4552, + "step": 10615 + }, + { + "epoch": 0.89, + "learning_rate": 6.482492562414621e-07, + "loss": 0.4495, + "step": 10616 + }, + { + "epoch": 0.89, + "learning_rate": 6.472897898272534e-07, + "loss": 0.4724, + "step": 10617 + }, + { + "epoch": 0.89, + "learning_rate": 6.463310102371834e-07, + "loss": 0.4603, + "step": 10618 + }, + { + "epoch": 0.89, + "learning_rate": 6.453729175416579e-07, + "loss": 0.4423, + "step": 10619 + }, + { + "epoch": 0.89, + "learning_rate": 6.444155118110373e-07, + "loss": 0.4421, + "step": 10620 + }, + { + "epoch": 0.89, + "learning_rate": 6.434587931156299e-07, + "loss": 0.4656, + "step": 10621 + }, + { + "epoch": 0.89, + "learning_rate": 6.425027615256907e-07, + "loss": 0.4639, + "step": 10622 + }, + { + "epoch": 0.89, + "learning_rate": 6.415474171114288e-07, + "loss": 0.4575, + "step": 10623 + }, + { + "epoch": 0.89, + "learning_rate": 6.405927599429995e-07, + "loss": 0.4592, + "step": 10624 + }, + { + "epoch": 0.89, + "learning_rate": 6.396387900905099e-07, + "loss": 0.4616, + "step": 10625 + }, + { + "epoch": 0.89, + "learning_rate": 6.386855076240117e-07, + "loss": 0.4553, + "step": 10626 + }, + { + "epoch": 0.89, + "learning_rate": 6.377329126135168e-07, + "loss": 0.4603, + "step": 10627 + }, + { + "epoch": 0.89, + "learning_rate": 6.367810051289746e-07, + "loss": 0.4622, + "step": 10628 + }, + { + "epoch": 0.89, + "learning_rate": 6.358297852402894e-07, + "loss": 0.4787, + "step": 10629 + }, + { + "epoch": 0.89, + "learning_rate": 6.348792530173187e-07, + "loss": 0.4648, + "step": 10630 + }, + { + "epoch": 0.89, + "learning_rate": 6.339294085298631e-07, + "loss": 0.4586, + "step": 10631 + }, + { + "epoch": 0.89, + "learning_rate": 6.329802518476746e-07, + "loss": 0.464, + "step": 10632 + }, + { + "epoch": 0.89, + "learning_rate": 6.320317830404554e-07, + "loss": 0.4964, + "step": 10633 + }, + { + "epoch": 0.89, + "learning_rate": 6.310840021778586e-07, + "loss": 0.4679, + "step": 10634 + }, + { + "epoch": 0.89, + "learning_rate": 6.30136909329484e-07, + "loss": 0.4348, + "step": 10635 + }, + { + "epoch": 0.89, + "learning_rate": 6.291905045648839e-07, + "loss": 0.4809, + "step": 10636 + }, + { + "epoch": 0.89, + "learning_rate": 6.282447879535558e-07, + "loss": 0.4575, + "step": 10637 + }, + { + "epoch": 0.89, + "learning_rate": 6.272997595649499e-07, + "loss": 0.4739, + "step": 10638 + }, + { + "epoch": 0.89, + "learning_rate": 6.263554194684662e-07, + "loss": 0.4522, + "step": 10639 + }, + { + "epoch": 0.89, + "learning_rate": 6.254117677334514e-07, + "loss": 0.4417, + "step": 10640 + }, + { + "epoch": 0.89, + "learning_rate": 6.244688044292058e-07, + "loss": 0.4564, + "step": 10641 + }, + { + "epoch": 0.89, + "learning_rate": 6.23526529624976e-07, + "loss": 0.4505, + "step": 10642 + }, + { + "epoch": 0.89, + "learning_rate": 6.225849433899578e-07, + "loss": 0.4596, + "step": 10643 + }, + { + "epoch": 0.89, + "learning_rate": 6.216440457932981e-07, + "loss": 0.4338, + "step": 10644 + }, + { + "epoch": 0.89, + "learning_rate": 6.207038369040918e-07, + "loss": 0.4676, + "step": 10645 + }, + { + "epoch": 0.89, + "learning_rate": 6.197643167913847e-07, + "loss": 0.4753, + "step": 10646 + }, + { + "epoch": 0.89, + "learning_rate": 6.188254855241693e-07, + "loss": 0.4584, + "step": 10647 + }, + { + "epoch": 0.89, + "learning_rate": 6.178873431713928e-07, + "loss": 0.4765, + "step": 10648 + }, + { + "epoch": 0.89, + "learning_rate": 6.169498898019443e-07, + "loss": 0.4592, + "step": 10649 + }, + { + "epoch": 0.89, + "learning_rate": 6.160131254846702e-07, + "loss": 0.4643, + "step": 10650 + }, + { + "epoch": 0.89, + "learning_rate": 6.150770502883618e-07, + "loss": 0.4684, + "step": 10651 + }, + { + "epoch": 0.89, + "learning_rate": 6.141416642817599e-07, + "loss": 0.4886, + "step": 10652 + }, + { + "epoch": 0.89, + "learning_rate": 6.13206967533555e-07, + "loss": 0.4641, + "step": 10653 + }, + { + "epoch": 0.89, + "learning_rate": 6.122729601123878e-07, + "loss": 0.4639, + "step": 10654 + }, + { + "epoch": 0.89, + "learning_rate": 6.113396420868489e-07, + "loss": 0.4511, + "step": 10655 + }, + { + "epoch": 0.89, + "learning_rate": 6.104070135254758e-07, + "loss": 0.4748, + "step": 10656 + }, + { + "epoch": 0.89, + "learning_rate": 6.09475074496757e-07, + "loss": 0.4607, + "step": 10657 + }, + { + "epoch": 0.89, + "learning_rate": 6.085438250691311e-07, + "loss": 0.4689, + "step": 10658 + }, + { + "epoch": 0.89, + "learning_rate": 6.076132653109834e-07, + "loss": 0.4497, + "step": 10659 + }, + { + "epoch": 0.89, + "learning_rate": 6.066833952906515e-07, + "loss": 0.4615, + "step": 10660 + }, + { + "epoch": 0.89, + "learning_rate": 6.057542150764218e-07, + "loss": 0.4654, + "step": 10661 + }, + { + "epoch": 0.89, + "learning_rate": 6.048257247365297e-07, + "loss": 0.4703, + "step": 10662 + }, + { + "epoch": 0.89, + "learning_rate": 6.038979243391597e-07, + "loss": 0.4581, + "step": 10663 + }, + { + "epoch": 0.89, + "learning_rate": 6.029708139524438e-07, + "loss": 0.4653, + "step": 10664 + }, + { + "epoch": 0.89, + "learning_rate": 6.020443936444664e-07, + "loss": 0.4835, + "step": 10665 + }, + { + "epoch": 0.89, + "learning_rate": 6.0111866348326e-07, + "loss": 0.4538, + "step": 10666 + }, + { + "epoch": 0.89, + "learning_rate": 6.001936235368044e-07, + "loss": 0.4771, + "step": 10667 + }, + { + "epoch": 0.89, + "learning_rate": 5.992692738730332e-07, + "loss": 0.4604, + "step": 10668 + }, + { + "epoch": 0.89, + "learning_rate": 5.983456145598266e-07, + "loss": 0.4592, + "step": 10669 + }, + { + "epoch": 0.89, + "learning_rate": 5.974226456650123e-07, + "loss": 0.4773, + "step": 10670 + }, + { + "epoch": 0.89, + "learning_rate": 5.965003672563719e-07, + "loss": 0.472, + "step": 10671 + }, + { + "epoch": 0.89, + "learning_rate": 5.955787794016321e-07, + "loss": 0.4521, + "step": 10672 + }, + { + "epoch": 0.89, + "learning_rate": 5.946578821684713e-07, + "loss": 0.4492, + "step": 10673 + }, + { + "epoch": 0.89, + "learning_rate": 5.937376756245139e-07, + "loss": 0.4726, + "step": 10674 + }, + { + "epoch": 0.89, + "learning_rate": 5.928181598373395e-07, + "loss": 0.4556, + "step": 10675 + }, + { + "epoch": 0.89, + "learning_rate": 5.918993348744728e-07, + "loss": 0.4523, + "step": 10676 + }, + { + "epoch": 0.89, + "learning_rate": 5.909812008033866e-07, + "loss": 0.461, + "step": 10677 + }, + { + "epoch": 0.89, + "learning_rate": 5.900637576915069e-07, + "loss": 0.4729, + "step": 10678 + }, + { + "epoch": 0.89, + "learning_rate": 5.891470056062043e-07, + "loss": 0.4656, + "step": 10679 + }, + { + "epoch": 0.89, + "learning_rate": 5.882309446148038e-07, + "loss": 0.4639, + "step": 10680 + }, + { + "epoch": 0.89, + "learning_rate": 5.87315574784576e-07, + "loss": 0.4651, + "step": 10681 + }, + { + "epoch": 0.89, + "learning_rate": 5.864008961827428e-07, + "loss": 0.4665, + "step": 10682 + }, + { + "epoch": 0.89, + "learning_rate": 5.854869088764737e-07, + "loss": 0.4629, + "step": 10683 + }, + { + "epoch": 0.89, + "learning_rate": 5.845736129328883e-07, + "loss": 0.4569, + "step": 10684 + }, + { + "epoch": 0.89, + "learning_rate": 5.836610084190541e-07, + "loss": 0.455, + "step": 10685 + }, + { + "epoch": 0.89, + "learning_rate": 5.82749095401991e-07, + "loss": 0.4809, + "step": 10686 + }, + { + "epoch": 0.89, + "learning_rate": 5.81837873948663e-07, + "loss": 0.4639, + "step": 10687 + }, + { + "epoch": 0.89, + "learning_rate": 5.809273441259899e-07, + "loss": 0.4451, + "step": 10688 + }, + { + "epoch": 0.89, + "learning_rate": 5.800175060008362e-07, + "loss": 0.4691, + "step": 10689 + }, + { + "epoch": 0.89, + "learning_rate": 5.791083596400148e-07, + "loss": 0.467, + "step": 10690 + }, + { + "epoch": 0.89, + "learning_rate": 5.781999051102927e-07, + "loss": 0.463, + "step": 10691 + }, + { + "epoch": 0.89, + "learning_rate": 5.772921424783806e-07, + "loss": 0.4638, + "step": 10692 + }, + { + "epoch": 0.89, + "learning_rate": 5.763850718109421e-07, + "loss": 0.475, + "step": 10693 + }, + { + "epoch": 0.89, + "learning_rate": 5.754786931745859e-07, + "loss": 0.4652, + "step": 10694 + }, + { + "epoch": 0.89, + "learning_rate": 5.745730066358779e-07, + "loss": 0.4622, + "step": 10695 + }, + { + "epoch": 0.89, + "learning_rate": 5.736680122613237e-07, + "loss": 0.4608, + "step": 10696 + }, + { + "epoch": 0.89, + "learning_rate": 5.727637101173844e-07, + "loss": 0.4586, + "step": 10697 + }, + { + "epoch": 0.9, + "learning_rate": 5.718601002704671e-07, + "loss": 0.442, + "step": 10698 + }, + { + "epoch": 0.9, + "learning_rate": 5.709571827869287e-07, + "loss": 0.4706, + "step": 10699 + }, + { + "epoch": 0.9, + "learning_rate": 5.70054957733076e-07, + "loss": 0.4871, + "step": 10700 + }, + { + "epoch": 0.9, + "learning_rate": 5.691534251751652e-07, + "loss": 0.4701, + "step": 10701 + }, + { + "epoch": 0.9, + "learning_rate": 5.682525851794019e-07, + "loss": 0.4756, + "step": 10702 + }, + { + "epoch": 0.9, + "learning_rate": 5.673524378119388e-07, + "loss": 0.4662, + "step": 10703 + }, + { + "epoch": 0.9, + "learning_rate": 5.664529831388799e-07, + "loss": 0.4683, + "step": 10704 + }, + { + "epoch": 0.9, + "learning_rate": 5.655542212262766e-07, + "loss": 0.4452, + "step": 10705 + }, + { + "epoch": 0.9, + "learning_rate": 5.646561521401317e-07, + "loss": 0.4809, + "step": 10706 + }, + { + "epoch": 0.9, + "learning_rate": 5.637587759463925e-07, + "loss": 0.4604, + "step": 10707 + }, + { + "epoch": 0.9, + "learning_rate": 5.628620927109607e-07, + "loss": 0.4794, + "step": 10708 + }, + { + "epoch": 0.9, + "learning_rate": 5.619661024996848e-07, + "loss": 0.4603, + "step": 10709 + }, + { + "epoch": 0.9, + "learning_rate": 5.610708053783642e-07, + "loss": 0.4669, + "step": 10710 + }, + { + "epoch": 0.9, + "learning_rate": 5.60176201412741e-07, + "loss": 0.471, + "step": 10711 + }, + { + "epoch": 0.9, + "learning_rate": 5.59282290668517e-07, + "loss": 0.4629, + "step": 10712 + }, + { + "epoch": 0.9, + "learning_rate": 5.58389073211335e-07, + "loss": 0.4513, + "step": 10713 + }, + { + "epoch": 0.9, + "learning_rate": 5.574965491067874e-07, + "loss": 0.5152, + "step": 10714 + }, + { + "epoch": 0.9, + "learning_rate": 5.566047184204182e-07, + "loss": 0.4614, + "step": 10715 + }, + { + "epoch": 0.9, + "learning_rate": 5.557135812177228e-07, + "loss": 0.4401, + "step": 10716 + }, + { + "epoch": 0.9, + "learning_rate": 5.548231375641389e-07, + "loss": 0.4655, + "step": 10717 + }, + { + "epoch": 0.9, + "learning_rate": 5.539333875250596e-07, + "loss": 0.4761, + "step": 10718 + }, + { + "epoch": 0.9, + "learning_rate": 5.530443311658218e-07, + "loss": 0.4628, + "step": 10719 + }, + { + "epoch": 0.9, + "learning_rate": 5.521559685517153e-07, + "loss": 0.4645, + "step": 10720 + }, + { + "epoch": 0.9, + "learning_rate": 5.51268299747978e-07, + "loss": 0.4947, + "step": 10721 + }, + { + "epoch": 0.9, + "learning_rate": 5.503813248197965e-07, + "loss": 0.4574, + "step": 10722 + }, + { + "epoch": 0.9, + "learning_rate": 5.494950438323077e-07, + "loss": 0.4685, + "step": 10723 + }, + { + "epoch": 0.9, + "learning_rate": 5.48609456850594e-07, + "loss": 0.4751, + "step": 10724 + }, + { + "epoch": 0.9, + "learning_rate": 5.477245639396922e-07, + "loss": 0.4682, + "step": 10725 + }, + { + "epoch": 0.9, + "learning_rate": 5.468403651645826e-07, + "loss": 0.4474, + "step": 10726 + }, + { + "epoch": 0.9, + "learning_rate": 5.459568605901977e-07, + "loss": 0.4704, + "step": 10727 + }, + { + "epoch": 0.9, + "learning_rate": 5.450740502814178e-07, + "loss": 0.4847, + "step": 10728 + }, + { + "epoch": 0.9, + "learning_rate": 5.441919343030744e-07, + "loss": 0.4695, + "step": 10729 + }, + { + "epoch": 0.9, + "learning_rate": 5.433105127199467e-07, + "loss": 0.4646, + "step": 10730 + }, + { + "epoch": 0.9, + "learning_rate": 5.424297855967597e-07, + "loss": 0.4771, + "step": 10731 + }, + { + "epoch": 0.9, + "learning_rate": 5.415497529981928e-07, + "loss": 0.4748, + "step": 10732 + }, + { + "epoch": 0.9, + "learning_rate": 5.40670414988872e-07, + "loss": 0.4688, + "step": 10733 + }, + { + "epoch": 0.9, + "learning_rate": 5.397917716333723e-07, + "loss": 0.4381, + "step": 10734 + }, + { + "epoch": 0.9, + "learning_rate": 5.389138229962155e-07, + "loss": 0.4684, + "step": 10735 + }, + { + "epoch": 0.9, + "learning_rate": 5.380365691418765e-07, + "loss": 0.4519, + "step": 10736 + }, + { + "epoch": 0.9, + "learning_rate": 5.371600101347763e-07, + "loss": 0.4714, + "step": 10737 + }, + { + "epoch": 0.9, + "learning_rate": 5.362841460392875e-07, + "loss": 0.4653, + "step": 10738 + }, + { + "epoch": 0.9, + "learning_rate": 5.354089769197268e-07, + "loss": 0.4803, + "step": 10739 + }, + { + "epoch": 0.9, + "learning_rate": 5.345345028403659e-07, + "loss": 0.4518, + "step": 10740 + }, + { + "epoch": 0.9, + "learning_rate": 5.33660723865419e-07, + "loss": 0.4649, + "step": 10741 + }, + { + "epoch": 0.9, + "learning_rate": 5.32787640059057e-07, + "loss": 0.461, + "step": 10742 + }, + { + "epoch": 0.9, + "learning_rate": 5.31915251485392e-07, + "loss": 0.4962, + "step": 10743 + }, + { + "epoch": 0.9, + "learning_rate": 5.310435582084917e-07, + "loss": 0.4649, + "step": 10744 + }, + { + "epoch": 0.9, + "learning_rate": 5.301725602923691e-07, + "loss": 0.4624, + "step": 10745 + }, + { + "epoch": 0.9, + "learning_rate": 5.293022578009843e-07, + "loss": 0.467, + "step": 10746 + }, + { + "epoch": 0.9, + "learning_rate": 5.284326507982507e-07, + "loss": 0.4678, + "step": 10747 + }, + { + "epoch": 0.9, + "learning_rate": 5.275637393480282e-07, + "loss": 0.4608, + "step": 10748 + }, + { + "epoch": 0.9, + "learning_rate": 5.266955235141235e-07, + "loss": 0.4783, + "step": 10749 + }, + { + "epoch": 0.9, + "learning_rate": 5.258280033602992e-07, + "loss": 0.4863, + "step": 10750 + }, + { + "epoch": 0.9, + "learning_rate": 5.249611789502607e-07, + "loss": 0.4491, + "step": 10751 + }, + { + "epoch": 0.9, + "learning_rate": 5.240950503476616e-07, + "loss": 0.4695, + "step": 10752 + }, + { + "epoch": 0.9, + "learning_rate": 5.232296176161101e-07, + "loss": 0.4812, + "step": 10753 + }, + { + "epoch": 0.9, + "learning_rate": 5.223648808191584e-07, + "loss": 0.4459, + "step": 10754 + }, + { + "epoch": 0.9, + "learning_rate": 5.215008400203103e-07, + "loss": 0.4771, + "step": 10755 + }, + { + "epoch": 0.9, + "learning_rate": 5.20637495283014e-07, + "loss": 0.4675, + "step": 10756 + }, + { + "epoch": 0.9, + "learning_rate": 5.197748466706742e-07, + "loss": 0.4509, + "step": 10757 + }, + { + "epoch": 0.9, + "learning_rate": 5.189128942466393e-07, + "loss": 0.4566, + "step": 10758 + }, + { + "epoch": 0.9, + "learning_rate": 5.180516380742051e-07, + "loss": 0.4632, + "step": 10759 + }, + { + "epoch": 0.9, + "learning_rate": 5.171910782166212e-07, + "loss": 0.4563, + "step": 10760 + }, + { + "epoch": 0.9, + "learning_rate": 5.163312147370824e-07, + "loss": 0.4507, + "step": 10761 + }, + { + "epoch": 0.9, + "learning_rate": 5.154720476987329e-07, + "loss": 0.4547, + "step": 10762 + }, + { + "epoch": 0.9, + "learning_rate": 5.146135771646655e-07, + "loss": 0.4596, + "step": 10763 + }, + { + "epoch": 0.9, + "learning_rate": 5.137558031979273e-07, + "loss": 0.4456, + "step": 10764 + }, + { + "epoch": 0.9, + "learning_rate": 5.128987258615059e-07, + "loss": 0.4591, + "step": 10765 + }, + { + "epoch": 0.9, + "learning_rate": 5.12042345218342e-07, + "loss": 0.4841, + "step": 10766 + }, + { + "epoch": 0.9, + "learning_rate": 5.111866613313255e-07, + "loss": 0.4637, + "step": 10767 + }, + { + "epoch": 0.9, + "learning_rate": 5.103316742632935e-07, + "loss": 0.4692, + "step": 10768 + }, + { + "epoch": 0.9, + "learning_rate": 5.094773840770306e-07, + "loss": 0.4977, + "step": 10769 + }, + { + "epoch": 0.9, + "learning_rate": 5.086237908352776e-07, + "loss": 0.4727, + "step": 10770 + }, + { + "epoch": 0.9, + "learning_rate": 5.077708946007143e-07, + "loss": 0.4818, + "step": 10771 + }, + { + "epoch": 0.9, + "learning_rate": 5.069186954359761e-07, + "loss": 0.4501, + "step": 10772 + }, + { + "epoch": 0.9, + "learning_rate": 5.060671934036421e-07, + "loss": 0.4501, + "step": 10773 + }, + { + "epoch": 0.9, + "learning_rate": 5.052163885662476e-07, + "loss": 0.4629, + "step": 10774 + }, + { + "epoch": 0.9, + "learning_rate": 5.043662809862692e-07, + "loss": 0.4542, + "step": 10775 + }, + { + "epoch": 0.9, + "learning_rate": 5.03516870726134e-07, + "loss": 0.4559, + "step": 10776 + }, + { + "epoch": 0.9, + "learning_rate": 5.026681578482229e-07, + "loss": 0.4821, + "step": 10777 + }, + { + "epoch": 0.9, + "learning_rate": 5.018201424148606e-07, + "loss": 0.4764, + "step": 10778 + }, + { + "epoch": 0.9, + "learning_rate": 5.009728244883205e-07, + "loss": 0.4775, + "step": 10779 + }, + { + "epoch": 0.9, + "learning_rate": 5.001262041308263e-07, + "loss": 0.4691, + "step": 10780 + }, + { + "epoch": 0.9, + "learning_rate": 4.992802814045505e-07, + "loss": 0.4439, + "step": 10781 + }, + { + "epoch": 0.9, + "learning_rate": 4.984350563716145e-07, + "loss": 0.4732, + "step": 10782 + }, + { + "epoch": 0.9, + "learning_rate": 4.975905290940874e-07, + "loss": 0.4788, + "step": 10783 + }, + { + "epoch": 0.9, + "learning_rate": 4.967466996339887e-07, + "loss": 0.471, + "step": 10784 + }, + { + "epoch": 0.9, + "learning_rate": 4.959035680532854e-07, + "loss": 0.4454, + "step": 10785 + }, + { + "epoch": 0.9, + "learning_rate": 4.950611344138945e-07, + "loss": 0.4511, + "step": 10786 + }, + { + "epoch": 0.9, + "learning_rate": 4.9421939877768e-07, + "loss": 0.4767, + "step": 10787 + }, + { + "epoch": 0.9, + "learning_rate": 4.933783612064546e-07, + "loss": 0.4464, + "step": 10788 + }, + { + "epoch": 0.9, + "learning_rate": 4.925380217619813e-07, + "loss": 0.4537, + "step": 10789 + }, + { + "epoch": 0.9, + "learning_rate": 4.916983805059705e-07, + "loss": 0.4717, + "step": 10790 + }, + { + "epoch": 0.9, + "learning_rate": 4.90859437500083e-07, + "loss": 0.4549, + "step": 10791 + }, + { + "epoch": 0.9, + "learning_rate": 4.900211928059284e-07, + "loss": 0.4547, + "step": 10792 + }, + { + "epoch": 0.9, + "learning_rate": 4.891836464850596e-07, + "loss": 0.4571, + "step": 10793 + }, + { + "epoch": 0.9, + "learning_rate": 4.883467985989876e-07, + "loss": 0.4762, + "step": 10794 + }, + { + "epoch": 0.9, + "learning_rate": 4.875106492091642e-07, + "loss": 0.4692, + "step": 10795 + }, + { + "epoch": 0.9, + "learning_rate": 4.866751983769935e-07, + "loss": 0.4702, + "step": 10796 + }, + { + "epoch": 0.9, + "learning_rate": 4.858404461638266e-07, + "loss": 0.4569, + "step": 10797 + }, + { + "epoch": 0.9, + "learning_rate": 4.850063926309657e-07, + "loss": 0.4488, + "step": 10798 + }, + { + "epoch": 0.9, + "learning_rate": 4.841730378396592e-07, + "loss": 0.4586, + "step": 10799 + }, + { + "epoch": 0.9, + "learning_rate": 4.833403818511062e-07, + "loss": 0.4559, + "step": 10800 + }, + { + "epoch": 0.9, + "learning_rate": 4.825084247264522e-07, + "loss": 0.4566, + "step": 10801 + }, + { + "epoch": 0.9, + "learning_rate": 4.816771665267939e-07, + "loss": 0.4449, + "step": 10802 + }, + { + "epoch": 0.9, + "learning_rate": 4.808466073131735e-07, + "loss": 0.4585, + "step": 10803 + }, + { + "epoch": 0.9, + "learning_rate": 4.800167471465844e-07, + "loss": 0.4537, + "step": 10804 + }, + { + "epoch": 0.9, + "learning_rate": 4.791875860879703e-07, + "loss": 0.4585, + "step": 10805 + }, + { + "epoch": 0.9, + "learning_rate": 4.783591241982199e-07, + "loss": 0.4525, + "step": 10806 + }, + { + "epoch": 0.9, + "learning_rate": 4.775313615381716e-07, + "loss": 0.4708, + "step": 10807 + }, + { + "epoch": 0.9, + "learning_rate": 4.767042981686143e-07, + "loss": 0.4424, + "step": 10808 + }, + { + "epoch": 0.9, + "learning_rate": 4.758779341502817e-07, + "loss": 0.47, + "step": 10809 + }, + { + "epoch": 0.9, + "learning_rate": 4.750522695438597e-07, + "loss": 0.453, + "step": 10810 + }, + { + "epoch": 0.9, + "learning_rate": 4.742273044099821e-07, + "loss": 0.4558, + "step": 10811 + }, + { + "epoch": 0.9, + "learning_rate": 4.7340303880923145e-07, + "loss": 0.4708, + "step": 10812 + }, + { + "epoch": 0.9, + "learning_rate": 4.7257947280213713e-07, + "loss": 0.4453, + "step": 10813 + }, + { + "epoch": 0.9, + "learning_rate": 4.7175660644917745e-07, + "loss": 0.4709, + "step": 10814 + }, + { + "epoch": 0.9, + "learning_rate": 4.709344398107829e-07, + "loss": 0.4792, + "step": 10815 + }, + { + "epoch": 0.9, + "learning_rate": 4.701129729473286e-07, + "loss": 0.4693, + "step": 10816 + }, + { + "epoch": 0.9, + "learning_rate": 4.6929220591913847e-07, + "loss": 0.4548, + "step": 10817 + }, + { + "epoch": 0.91, + "learning_rate": 4.6847213878648876e-07, + "loss": 0.4827, + "step": 10818 + }, + { + "epoch": 0.91, + "learning_rate": 4.6765277160960133e-07, + "loss": 0.4751, + "step": 10819 + }, + { + "epoch": 0.91, + "learning_rate": 4.6683410444864573e-07, + "loss": 0.4529, + "step": 10820 + }, + { + "epoch": 0.91, + "learning_rate": 4.6601613736374173e-07, + "loss": 0.4748, + "step": 10821 + }, + { + "epoch": 0.91, + "learning_rate": 4.6519887041495905e-07, + "loss": 0.4607, + "step": 10822 + }, + { + "epoch": 0.91, + "learning_rate": 4.6438230366231075e-07, + "loss": 0.4451, + "step": 10823 + }, + { + "epoch": 0.91, + "learning_rate": 4.6356643716576557e-07, + "loss": 0.4693, + "step": 10824 + }, + { + "epoch": 0.91, + "learning_rate": 4.627512709852355e-07, + "loss": 0.4662, + "step": 10825 + }, + { + "epoch": 0.91, + "learning_rate": 4.61936805180585e-07, + "loss": 0.4448, + "step": 10826 + }, + { + "epoch": 0.91, + "learning_rate": 4.611230398116229e-07, + "loss": 0.47, + "step": 10827 + }, + { + "epoch": 0.91, + "learning_rate": 4.6030997493811126e-07, + "loss": 0.4645, + "step": 10828 + }, + { + "epoch": 0.91, + "learning_rate": 4.594976106197546e-07, + "loss": 0.435, + "step": 10829 + }, + { + "epoch": 0.91, + "learning_rate": 4.5868594691621304e-07, + "loss": 0.4691, + "step": 10830 + }, + { + "epoch": 0.91, + "learning_rate": 4.5787498388708774e-07, + "loss": 0.4661, + "step": 10831 + }, + { + "epoch": 0.91, + "learning_rate": 4.570647215919366e-07, + "loss": 0.4651, + "step": 10832 + }, + { + "epoch": 0.91, + "learning_rate": 4.5625516009026095e-07, + "loss": 0.4573, + "step": 10833 + }, + { + "epoch": 0.91, + "learning_rate": 4.5544629944150876e-07, + "loss": 0.4668, + "step": 10834 + }, + { + "epoch": 0.91, + "learning_rate": 4.5463813970508364e-07, + "loss": 0.461, + "step": 10835 + }, + { + "epoch": 0.91, + "learning_rate": 4.5383068094033036e-07, + "loss": 0.4437, + "step": 10836 + }, + { + "epoch": 0.91, + "learning_rate": 4.53023923206547e-07, + "loss": 0.4601, + "step": 10837 + }, + { + "epoch": 0.91, + "learning_rate": 4.5221786656297727e-07, + "loss": 0.4662, + "step": 10838 + }, + { + "epoch": 0.91, + "learning_rate": 4.51412511068815e-07, + "loss": 0.4571, + "step": 10839 + }, + { + "epoch": 0.91, + "learning_rate": 4.5060785678320397e-07, + "loss": 0.4747, + "step": 10840 + }, + { + "epoch": 0.91, + "learning_rate": 4.498039037652313e-07, + "loss": 0.4635, + "step": 10841 + }, + { + "epoch": 0.91, + "learning_rate": 4.490006520739387e-07, + "loss": 0.4445, + "step": 10842 + }, + { + "epoch": 0.91, + "learning_rate": 4.4819810176831235e-07, + "loss": 0.4579, + "step": 10843 + }, + { + "epoch": 0.91, + "learning_rate": 4.473962529072873e-07, + "loss": 0.4499, + "step": 10844 + }, + { + "epoch": 0.91, + "learning_rate": 4.465951055497497e-07, + "loss": 0.4692, + "step": 10845 + }, + { + "epoch": 0.91, + "learning_rate": 4.4579465975453264e-07, + "loss": 0.4776, + "step": 10846 + }, + { + "epoch": 0.91, + "learning_rate": 4.4499491558041673e-07, + "loss": 0.4795, + "step": 10847 + }, + { + "epoch": 0.91, + "learning_rate": 4.4419587308613285e-07, + "loss": 0.4559, + "step": 10848 + }, + { + "epoch": 0.91, + "learning_rate": 4.433975323303574e-07, + "loss": 0.4781, + "step": 10849 + }, + { + "epoch": 0.91, + "learning_rate": 4.42599893371719e-07, + "loss": 0.4636, + "step": 10850 + }, + { + "epoch": 0.91, + "learning_rate": 4.418029562687898e-07, + "loss": 0.462, + "step": 10851 + }, + { + "epoch": 0.91, + "learning_rate": 4.4100672108009837e-07, + "loss": 0.4626, + "step": 10852 + }, + { + "epoch": 0.91, + "learning_rate": 4.4021118786411465e-07, + "loss": 0.4657, + "step": 10853 + }, + { + "epoch": 0.91, + "learning_rate": 4.3941635667925866e-07, + "loss": 0.4566, + "step": 10854 + }, + { + "epoch": 0.91, + "learning_rate": 4.3862222758389806e-07, + "loss": 0.4768, + "step": 10855 + }, + { + "epoch": 0.91, + "learning_rate": 4.3782880063635403e-07, + "loss": 0.4521, + "step": 10856 + }, + { + "epoch": 0.91, + "learning_rate": 4.3703607589489105e-07, + "loss": 0.471, + "step": 10857 + }, + { + "epoch": 0.91, + "learning_rate": 4.362440534177226e-07, + "loss": 0.4468, + "step": 10858 + }, + { + "epoch": 0.91, + "learning_rate": 4.3545273326301205e-07, + "loss": 0.4578, + "step": 10859 + }, + { + "epoch": 0.91, + "learning_rate": 4.3466211548887195e-07, + "loss": 0.4488, + "step": 10860 + }, + { + "epoch": 0.91, + "learning_rate": 4.338722001533602e-07, + "loss": 0.4784, + "step": 10861 + }, + { + "epoch": 0.91, + "learning_rate": 4.3308298731448596e-07, + "loss": 0.4639, + "step": 10862 + }, + { + "epoch": 0.91, + "learning_rate": 4.322944770302051e-07, + "loss": 0.4591, + "step": 10863 + }, + { + "epoch": 0.91, + "learning_rate": 4.3150666935842243e-07, + "loss": 0.4511, + "step": 10864 + }, + { + "epoch": 0.91, + "learning_rate": 4.307195643569917e-07, + "loss": 0.459, + "step": 10865 + }, + { + "epoch": 0.91, + "learning_rate": 4.299331620837133e-07, + "loss": 0.4785, + "step": 10866 + }, + { + "epoch": 0.91, + "learning_rate": 4.29147462596341e-07, + "loss": 0.4438, + "step": 10867 + }, + { + "epoch": 0.91, + "learning_rate": 4.283624659525698e-07, + "loss": 0.465, + "step": 10868 + }, + { + "epoch": 0.91, + "learning_rate": 4.2757817221004803e-07, + "loss": 0.4592, + "step": 10869 + }, + { + "epoch": 0.91, + "learning_rate": 4.267945814263708e-07, + "loss": 0.4657, + "step": 10870 + }, + { + "epoch": 0.91, + "learning_rate": 4.2601169365908077e-07, + "loss": 0.4765, + "step": 10871 + }, + { + "epoch": 0.91, + "learning_rate": 4.2522950896566994e-07, + "loss": 0.4664, + "step": 10872 + }, + { + "epoch": 0.91, + "learning_rate": 4.2444802740358114e-07, + "loss": 0.4634, + "step": 10873 + }, + { + "epoch": 0.91, + "learning_rate": 4.2366724903020076e-07, + "loss": 0.4695, + "step": 10874 + }, + { + "epoch": 0.91, + "learning_rate": 4.2288717390286614e-07, + "loss": 0.4691, + "step": 10875 + }, + { + "epoch": 0.91, + "learning_rate": 4.2210780207886383e-07, + "loss": 0.4936, + "step": 10876 + }, + { + "epoch": 0.91, + "learning_rate": 4.2132913361542683e-07, + "loss": 0.4619, + "step": 10877 + }, + { + "epoch": 0.91, + "learning_rate": 4.205511685697372e-07, + "loss": 0.4653, + "step": 10878 + }, + { + "epoch": 0.91, + "learning_rate": 4.1977390699892706e-07, + "loss": 0.4641, + "step": 10879 + }, + { + "epoch": 0.91, + "learning_rate": 4.1899734896007404e-07, + "loss": 0.4697, + "step": 10880 + }, + { + "epoch": 0.91, + "learning_rate": 4.1822149451020475e-07, + "loss": 0.4413, + "step": 10881 + }, + { + "epoch": 0.91, + "learning_rate": 4.1744634370629587e-07, + "loss": 0.4594, + "step": 10882 + }, + { + "epoch": 0.91, + "learning_rate": 4.166718966052696e-07, + "loss": 0.4503, + "step": 10883 + }, + { + "epoch": 0.91, + "learning_rate": 4.158981532640005e-07, + "loss": 0.4772, + "step": 10884 + }, + { + "epoch": 0.91, + "learning_rate": 4.1512511373930533e-07, + "loss": 0.4692, + "step": 10885 + }, + { + "epoch": 0.91, + "learning_rate": 4.143527780879575e-07, + "loss": 0.4666, + "step": 10886 + }, + { + "epoch": 0.91, + "learning_rate": 4.1358114636667056e-07, + "loss": 0.4712, + "step": 10887 + }, + { + "epoch": 0.91, + "learning_rate": 4.128102186321126e-07, + "loss": 0.4737, + "step": 10888 + }, + { + "epoch": 0.91, + "learning_rate": 4.1203999494089596e-07, + "loss": 0.45, + "step": 10889 + }, + { + "epoch": 0.91, + "learning_rate": 4.112704753495822e-07, + "loss": 0.4695, + "step": 10890 + }, + { + "epoch": 0.91, + "learning_rate": 4.1050165991468273e-07, + "loss": 0.4741, + "step": 10891 + }, + { + "epoch": 0.91, + "learning_rate": 4.097335486926546e-07, + "loss": 0.4438, + "step": 10892 + }, + { + "epoch": 0.91, + "learning_rate": 4.08966141739906e-07, + "loss": 0.4623, + "step": 10893 + }, + { + "epoch": 0.91, + "learning_rate": 4.08199439112793e-07, + "loss": 0.4615, + "step": 10894 + }, + { + "epoch": 0.91, + "learning_rate": 4.0743344086761725e-07, + "loss": 0.4557, + "step": 10895 + }, + { + "epoch": 0.91, + "learning_rate": 4.066681470606304e-07, + "loss": 0.482, + "step": 10896 + }, + { + "epoch": 0.91, + "learning_rate": 4.0590355774803416e-07, + "loss": 0.4708, + "step": 10897 + }, + { + "epoch": 0.91, + "learning_rate": 4.051396729859758e-07, + "loss": 0.4756, + "step": 10898 + }, + { + "epoch": 0.91, + "learning_rate": 4.043764928305505e-07, + "loss": 0.466, + "step": 10899 + }, + { + "epoch": 0.91, + "learning_rate": 4.036140173378045e-07, + "loss": 0.4491, + "step": 10900 + }, + { + "epoch": 0.91, + "learning_rate": 4.028522465637319e-07, + "loss": 0.4952, + "step": 10901 + }, + { + "epoch": 0.91, + "learning_rate": 4.0209118056427356e-07, + "loss": 0.4506, + "step": 10902 + }, + { + "epoch": 0.91, + "learning_rate": 4.013308193953169e-07, + "loss": 0.4513, + "step": 10903 + }, + { + "epoch": 0.91, + "learning_rate": 4.0057116311270073e-07, + "loss": 0.4536, + "step": 10904 + }, + { + "epoch": 0.91, + "learning_rate": 3.998122117722125e-07, + "loss": 0.4479, + "step": 10905 + }, + { + "epoch": 0.91, + "learning_rate": 3.990539654295833e-07, + "loss": 0.4539, + "step": 10906 + }, + { + "epoch": 0.91, + "learning_rate": 3.982964241404974e-07, + "loss": 0.4578, + "step": 10907 + }, + { + "epoch": 0.91, + "learning_rate": 3.975395879605881e-07, + "loss": 0.4572, + "step": 10908 + }, + { + "epoch": 0.91, + "learning_rate": 3.96783456945431e-07, + "loss": 0.4333, + "step": 10909 + }, + { + "epoch": 0.91, + "learning_rate": 3.960280311505538e-07, + "loss": 0.4491, + "step": 10910 + }, + { + "epoch": 0.91, + "learning_rate": 3.9527331063143215e-07, + "loss": 0.4693, + "step": 10911 + }, + { + "epoch": 0.91, + "learning_rate": 3.9451929544348956e-07, + "loss": 0.4599, + "step": 10912 + }, + { + "epoch": 0.91, + "learning_rate": 3.9376598564209614e-07, + "loss": 0.4722, + "step": 10913 + }, + { + "epoch": 0.91, + "learning_rate": 3.9301338128257536e-07, + "loss": 0.4704, + "step": 10914 + }, + { + "epoch": 0.91, + "learning_rate": 3.922614824201931e-07, + "loss": 0.4599, + "step": 10915 + }, + { + "epoch": 0.91, + "learning_rate": 3.915102891101652e-07, + "loss": 0.4563, + "step": 10916 + }, + { + "epoch": 0.91, + "learning_rate": 3.9075980140765637e-07, + "loss": 0.4605, + "step": 10917 + }, + { + "epoch": 0.91, + "learning_rate": 3.900100193677814e-07, + "loss": 0.4588, + "step": 10918 + }, + { + "epoch": 0.91, + "learning_rate": 3.892609430455985e-07, + "loss": 0.4697, + "step": 10919 + }, + { + "epoch": 0.91, + "learning_rate": 3.885125724961192e-07, + "loss": 0.4797, + "step": 10920 + }, + { + "epoch": 0.91, + "learning_rate": 3.877649077742984e-07, + "loss": 0.4523, + "step": 10921 + }, + { + "epoch": 0.91, + "learning_rate": 3.8701794893504343e-07, + "loss": 0.4725, + "step": 10922 + }, + { + "epoch": 0.91, + "learning_rate": 3.862716960332058e-07, + "loss": 0.4492, + "step": 10923 + }, + { + "epoch": 0.91, + "learning_rate": 3.8552614912358956e-07, + "loss": 0.435, + "step": 10924 + }, + { + "epoch": 0.91, + "learning_rate": 3.8478130826094307e-07, + "loss": 0.4606, + "step": 10925 + }, + { + "epoch": 0.91, + "learning_rate": 3.8403717349996263e-07, + "loss": 0.4684, + "step": 10926 + }, + { + "epoch": 0.91, + "learning_rate": 3.832937448952978e-07, + "loss": 0.4579, + "step": 10927 + }, + { + "epoch": 0.91, + "learning_rate": 3.8255102250154054e-07, + "loss": 0.4772, + "step": 10928 + }, + { + "epoch": 0.91, + "learning_rate": 3.81809006373236e-07, + "loss": 0.4719, + "step": 10929 + }, + { + "epoch": 0.91, + "learning_rate": 3.8106769656487184e-07, + "loss": 0.4419, + "step": 10930 + }, + { + "epoch": 0.91, + "learning_rate": 3.803270931308889e-07, + "loss": 0.4684, + "step": 10931 + }, + { + "epoch": 0.91, + "learning_rate": 3.795871961256725e-07, + "loss": 0.4569, + "step": 10932 + }, + { + "epoch": 0.91, + "learning_rate": 3.788480056035571e-07, + "loss": 0.4644, + "step": 10933 + }, + { + "epoch": 0.91, + "learning_rate": 3.78109521618828e-07, + "loss": 0.4834, + "step": 10934 + }, + { + "epoch": 0.91, + "learning_rate": 3.773717442257141e-07, + "loss": 0.4578, + "step": 10935 + }, + { + "epoch": 0.91, + "learning_rate": 3.7663467347839766e-07, + "loss": 0.4573, + "step": 10936 + }, + { + "epoch": 0.92, + "learning_rate": 3.7589830943100205e-07, + "loss": 0.4669, + "step": 10937 + }, + { + "epoch": 0.92, + "learning_rate": 3.7516265213760507e-07, + "loss": 0.4479, + "step": 10938 + }, + { + "epoch": 0.92, + "learning_rate": 3.7442770165223133e-07, + "loss": 0.4579, + "step": 10939 + }, + { + "epoch": 0.92, + "learning_rate": 3.7369345802885095e-07, + "loss": 0.4696, + "step": 10940 + }, + { + "epoch": 0.92, + "learning_rate": 3.7295992132138416e-07, + "loss": 0.4632, + "step": 10941 + }, + { + "epoch": 0.92, + "learning_rate": 3.7222709158369895e-07, + "loss": 0.4405, + "step": 10942 + }, + { + "epoch": 0.92, + "learning_rate": 3.714949688696123e-07, + "loss": 0.4644, + "step": 10943 + }, + { + "epoch": 0.92, + "learning_rate": 3.707635532328857e-07, + "loss": 0.4782, + "step": 10944 + }, + { + "epoch": 0.92, + "learning_rate": 3.700328447272339e-07, + "loss": 0.4324, + "step": 10945 + }, + { + "epoch": 0.92, + "learning_rate": 3.693028434063151e-07, + "loss": 0.4569, + "step": 10946 + }, + { + "epoch": 0.92, + "learning_rate": 3.6857354932373857e-07, + "loss": 0.454, + "step": 10947 + }, + { + "epoch": 0.92, + "learning_rate": 3.6784496253305937e-07, + "loss": 0.4474, + "step": 10948 + }, + { + "epoch": 0.92, + "learning_rate": 3.671170830877846e-07, + "loss": 0.4524, + "step": 10949 + }, + { + "epoch": 0.92, + "learning_rate": 3.663899110413638e-07, + "loss": 0.4726, + "step": 10950 + }, + { + "epoch": 0.92, + "learning_rate": 3.6566344644719974e-07, + "loss": 0.4711, + "step": 10951 + }, + { + "epoch": 0.92, + "learning_rate": 3.649376893586398e-07, + "loss": 0.441, + "step": 10952 + }, + { + "epoch": 0.92, + "learning_rate": 3.6421263982898023e-07, + "loss": 0.4742, + "step": 10953 + }, + { + "epoch": 0.92, + "learning_rate": 3.634882979114662e-07, + "loss": 0.4701, + "step": 10954 + }, + { + "epoch": 0.92, + "learning_rate": 3.627646636592919e-07, + "loss": 0.4461, + "step": 10955 + }, + { + "epoch": 0.92, + "learning_rate": 3.6204173712559464e-07, + "loss": 0.4677, + "step": 10956 + }, + { + "epoch": 0.92, + "learning_rate": 3.6131951836346544e-07, + "loss": 0.4643, + "step": 10957 + }, + { + "epoch": 0.92, + "learning_rate": 3.6059800742593963e-07, + "loss": 0.4507, + "step": 10958 + }, + { + "epoch": 0.92, + "learning_rate": 3.5987720436600483e-07, + "loss": 0.4745, + "step": 10959 + }, + { + "epoch": 0.92, + "learning_rate": 3.5915710923658974e-07, + "loss": 0.4839, + "step": 10960 + }, + { + "epoch": 0.92, + "learning_rate": 3.584377220905788e-07, + "loss": 0.458, + "step": 10961 + }, + { + "epoch": 0.92, + "learning_rate": 3.5771904298079864e-07, + "loss": 0.4535, + "step": 10962 + }, + { + "epoch": 0.92, + "learning_rate": 3.57001071960027e-07, + "loss": 0.443, + "step": 10963 + }, + { + "epoch": 0.92, + "learning_rate": 3.562838090809884e-07, + "loss": 0.4507, + "step": 10964 + }, + { + "epoch": 0.92, + "learning_rate": 3.555672543963562e-07, + "loss": 0.4554, + "step": 10965 + }, + { + "epoch": 0.92, + "learning_rate": 3.548514079587495e-07, + "loss": 0.4864, + "step": 10966 + }, + { + "epoch": 0.92, + "learning_rate": 3.541362698207373e-07, + "loss": 0.4705, + "step": 10967 + }, + { + "epoch": 0.92, + "learning_rate": 3.5342184003483884e-07, + "loss": 0.451, + "step": 10968 + }, + { + "epoch": 0.92, + "learning_rate": 3.527081186535164e-07, + "loss": 0.4559, + "step": 10969 + }, + { + "epoch": 0.92, + "learning_rate": 3.5199510572918484e-07, + "loss": 0.4681, + "step": 10970 + }, + { + "epoch": 0.92, + "learning_rate": 3.5128280131420333e-07, + "loss": 0.4597, + "step": 10971 + }, + { + "epoch": 0.92, + "learning_rate": 3.505712054608801e-07, + "loss": 0.4551, + "step": 10972 + }, + { + "epoch": 0.92, + "learning_rate": 3.4986031822147325e-07, + "loss": 0.4646, + "step": 10973 + }, + { + "epoch": 0.92, + "learning_rate": 3.4915013964818556e-07, + "loss": 0.4706, + "step": 10974 + }, + { + "epoch": 0.92, + "learning_rate": 3.4844066979317193e-07, + "loss": 0.4488, + "step": 10975 + }, + { + "epoch": 0.92, + "learning_rate": 3.477319087085318e-07, + "loss": 0.4767, + "step": 10976 + }, + { + "epoch": 0.92, + "learning_rate": 3.470238564463135e-07, + "loss": 0.4695, + "step": 10977 + }, + { + "epoch": 0.92, + "learning_rate": 3.4631651305851224e-07, + "loss": 0.4663, + "step": 10978 + }, + { + "epoch": 0.92, + "learning_rate": 3.4560987859707407e-07, + "loss": 0.455, + "step": 10979 + }, + { + "epoch": 0.92, + "learning_rate": 3.44903953113892e-07, + "loss": 0.4549, + "step": 10980 + }, + { + "epoch": 0.92, + "learning_rate": 3.4419873666080237e-07, + "loss": 0.4622, + "step": 10981 + }, + { + "epoch": 0.92, + "learning_rate": 3.434942292895982e-07, + "loss": 0.4688, + "step": 10982 + }, + { + "epoch": 0.92, + "learning_rate": 3.427904310520136e-07, + "loss": 0.4463, + "step": 10983 + }, + { + "epoch": 0.92, + "learning_rate": 3.420873419997317e-07, + "loss": 0.4726, + "step": 10984 + }, + { + "epoch": 0.92, + "learning_rate": 3.413849621843857e-07, + "loss": 0.4541, + "step": 10985 + }, + { + "epoch": 0.92, + "learning_rate": 3.406832916575542e-07, + "loss": 0.4545, + "step": 10986 + }, + { + "epoch": 0.92, + "learning_rate": 3.3998233047076613e-07, + "loss": 0.449, + "step": 10987 + }, + { + "epoch": 0.92, + "learning_rate": 3.3928207867549467e-07, + "loss": 0.4896, + "step": 10988 + }, + { + "epoch": 0.92, + "learning_rate": 3.385825363231665e-07, + "loss": 0.4583, + "step": 10989 + }, + { + "epoch": 0.92, + "learning_rate": 3.3788370346515274e-07, + "loss": 0.4388, + "step": 10990 + }, + { + "epoch": 0.92, + "learning_rate": 3.3718558015277237e-07, + "loss": 0.4818, + "step": 10991 + }, + { + "epoch": 0.92, + "learning_rate": 3.3648816643729207e-07, + "loss": 0.4601, + "step": 10992 + }, + { + "epoch": 0.92, + "learning_rate": 3.357914623699265e-07, + "loss": 0.4561, + "step": 10993 + }, + { + "epoch": 0.92, + "learning_rate": 3.3509546800183923e-07, + "loss": 0.4834, + "step": 10994 + }, + { + "epoch": 0.92, + "learning_rate": 3.344001833841426e-07, + "loss": 0.4675, + "step": 10995 + }, + { + "epoch": 0.92, + "learning_rate": 3.337056085678936e-07, + "loss": 0.4454, + "step": 10996 + }, + { + "epoch": 0.92, + "learning_rate": 3.3301174360410026e-07, + "loss": 0.4625, + "step": 10997 + }, + { + "epoch": 0.92, + "learning_rate": 3.3231858854371634e-07, + "loss": 0.462, + "step": 10998 + }, + { + "epoch": 0.92, + "learning_rate": 3.3162614343764334e-07, + "loss": 0.4516, + "step": 10999 + }, + { + "epoch": 0.92, + "learning_rate": 3.309344083367327e-07, + "loss": 0.4705, + "step": 11000 + }, + { + "epoch": 0.92, + "learning_rate": 3.3024338329178285e-07, + "loss": 0.4631, + "step": 11001 + }, + { + "epoch": 0.92, + "learning_rate": 3.2955306835353863e-07, + "loss": 0.4625, + "step": 11002 + }, + { + "epoch": 0.92, + "learning_rate": 3.2886346357269614e-07, + "loss": 0.4815, + "step": 11003 + }, + { + "epoch": 0.92, + "learning_rate": 3.28174568999895e-07, + "loss": 0.4582, + "step": 11004 + }, + { + "epoch": 0.92, + "learning_rate": 3.274863846857257e-07, + "loss": 0.4654, + "step": 11005 + }, + { + "epoch": 0.92, + "learning_rate": 3.2679891068072566e-07, + "loss": 0.4465, + "step": 11006 + }, + { + "epoch": 0.92, + "learning_rate": 3.26112147035379e-07, + "loss": 0.4808, + "step": 11007 + }, + { + "epoch": 0.92, + "learning_rate": 3.254260938001186e-07, + "loss": 0.4494, + "step": 11008 + }, + { + "epoch": 0.92, + "learning_rate": 3.2474075102532756e-07, + "loss": 0.4643, + "step": 11009 + }, + { + "epoch": 0.92, + "learning_rate": 3.240561187613323e-07, + "loss": 0.4687, + "step": 11010 + }, + { + "epoch": 0.92, + "learning_rate": 3.233721970584114e-07, + "loss": 0.4417, + "step": 11011 + }, + { + "epoch": 0.92, + "learning_rate": 3.226889859667881e-07, + "loss": 0.4668, + "step": 11012 + }, + { + "epoch": 0.92, + "learning_rate": 3.220064855366345e-07, + "loss": 0.4714, + "step": 11013 + }, + { + "epoch": 0.92, + "learning_rate": 3.2132469581807046e-07, + "loss": 0.4715, + "step": 11014 + }, + { + "epoch": 0.92, + "learning_rate": 3.2064361686116377e-07, + "loss": 0.4557, + "step": 11015 + }, + { + "epoch": 0.92, + "learning_rate": 3.199632487159321e-07, + "loss": 0.4709, + "step": 11016 + }, + { + "epoch": 0.92, + "learning_rate": 3.1928359143233556e-07, + "loss": 0.4687, + "step": 11017 + }, + { + "epoch": 0.92, + "learning_rate": 3.1860464506028865e-07, + "loss": 0.4549, + "step": 11018 + }, + { + "epoch": 0.92, + "learning_rate": 3.1792640964964593e-07, + "loss": 0.4747, + "step": 11019 + }, + { + "epoch": 0.92, + "learning_rate": 3.172488852502187e-07, + "loss": 0.4414, + "step": 11020 + }, + { + "epoch": 0.92, + "learning_rate": 3.1657207191176043e-07, + "loss": 0.4593, + "step": 11021 + }, + { + "epoch": 0.92, + "learning_rate": 3.1589596968397027e-07, + "loss": 0.4616, + "step": 11022 + }, + { + "epoch": 0.92, + "learning_rate": 3.15220578616503e-07, + "loss": 0.4688, + "step": 11023 + }, + { + "epoch": 0.92, + "learning_rate": 3.1454589875895445e-07, + "loss": 0.4583, + "step": 11024 + }, + { + "epoch": 0.92, + "learning_rate": 3.1387193016086945e-07, + "loss": 0.4662, + "step": 11025 + }, + { + "epoch": 0.92, + "learning_rate": 3.131986728717429e-07, + "loss": 0.4629, + "step": 11026 + }, + { + "epoch": 0.92, + "learning_rate": 3.1252612694101515e-07, + "loss": 0.4678, + "step": 11027 + }, + { + "epoch": 0.92, + "learning_rate": 3.1185429241807453e-07, + "loss": 0.4724, + "step": 11028 + }, + { + "epoch": 0.92, + "learning_rate": 3.1118316935226043e-07, + "loss": 0.4607, + "step": 11029 + }, + { + "epoch": 0.92, + "learning_rate": 3.105127577928546e-07, + "loss": 0.4534, + "step": 11030 + }, + { + "epoch": 0.92, + "learning_rate": 3.0984305778908875e-07, + "loss": 0.4537, + "step": 11031 + }, + { + "epoch": 0.92, + "learning_rate": 3.091740693901468e-07, + "loss": 0.4804, + "step": 11032 + }, + { + "epoch": 0.92, + "learning_rate": 3.085057926451529e-07, + "loss": 0.4322, + "step": 11033 + }, + { + "epoch": 0.92, + "learning_rate": 3.078382276031833e-07, + "loss": 0.4564, + "step": 11034 + }, + { + "epoch": 0.92, + "learning_rate": 3.071713743132609e-07, + "loss": 0.4704, + "step": 11035 + }, + { + "epoch": 0.92, + "learning_rate": 3.0650523282435896e-07, + "loss": 0.4677, + "step": 11036 + }, + { + "epoch": 0.92, + "learning_rate": 3.0583980318539377e-07, + "loss": 0.467, + "step": 11037 + }, + { + "epoch": 0.92, + "learning_rate": 3.051750854452329e-07, + "loss": 0.452, + "step": 11038 + }, + { + "epoch": 0.92, + "learning_rate": 3.0451107965268956e-07, + "loss": 0.4757, + "step": 11039 + }, + { + "epoch": 0.92, + "learning_rate": 3.0384778585652477e-07, + "loss": 0.4601, + "step": 11040 + }, + { + "epoch": 0.92, + "learning_rate": 3.031852041054506e-07, + "loss": 0.4614, + "step": 11041 + }, + { + "epoch": 0.92, + "learning_rate": 3.0252333444812263e-07, + "loss": 0.4768, + "step": 11042 + }, + { + "epoch": 0.92, + "learning_rate": 3.0186217693314643e-07, + "loss": 0.4619, + "step": 11043 + }, + { + "epoch": 0.92, + "learning_rate": 3.012017316090743e-07, + "loss": 0.4598, + "step": 11044 + }, + { + "epoch": 0.92, + "learning_rate": 3.0054199852440626e-07, + "loss": 0.4628, + "step": 11045 + }, + { + "epoch": 0.92, + "learning_rate": 2.9988297772759136e-07, + "loss": 0.4393, + "step": 11046 + }, + { + "epoch": 0.92, + "learning_rate": 2.992246692670242e-07, + "loss": 0.475, + "step": 11047 + }, + { + "epoch": 0.92, + "learning_rate": 2.985670731910495e-07, + "loss": 0.4703, + "step": 11048 + }, + { + "epoch": 0.92, + "learning_rate": 2.9791018954795636e-07, + "loss": 0.4442, + "step": 11049 + }, + { + "epoch": 0.92, + "learning_rate": 2.972540183859862e-07, + "loss": 0.4694, + "step": 11050 + }, + { + "epoch": 0.92, + "learning_rate": 2.9659855975332274e-07, + "loss": 0.4698, + "step": 11051 + }, + { + "epoch": 0.92, + "learning_rate": 2.959438136981019e-07, + "loss": 0.4357, + "step": 11052 + }, + { + "epoch": 0.92, + "learning_rate": 2.9528978026840625e-07, + "loss": 0.4585, + "step": 11053 + }, + { + "epoch": 0.92, + "learning_rate": 2.9463645951226415e-07, + "loss": 0.4864, + "step": 11054 + }, + { + "epoch": 0.92, + "learning_rate": 2.939838514776527e-07, + "loss": 0.4584, + "step": 11055 + }, + { + "epoch": 0.92, + "learning_rate": 2.933319562124959e-07, + "loss": 0.4561, + "step": 11056 + }, + { + "epoch": 0.93, + "learning_rate": 2.926807737646675e-07, + "loss": 0.4795, + "step": 11057 + }, + { + "epoch": 0.93, + "learning_rate": 2.920303041819872e-07, + "loss": 0.4472, + "step": 11058 + }, + { + "epoch": 0.93, + "learning_rate": 2.9138054751222447e-07, + "loss": 0.461, + "step": 11059 + }, + { + "epoch": 0.93, + "learning_rate": 2.907315038030911e-07, + "loss": 0.4699, + "step": 11060 + }, + { + "epoch": 0.93, + "learning_rate": 2.900831731022524e-07, + "loss": 0.4574, + "step": 11061 + }, + { + "epoch": 0.93, + "learning_rate": 2.894355554573203e-07, + "loss": 0.4534, + "step": 11062 + }, + { + "epoch": 0.93, + "learning_rate": 2.8878865091584993e-07, + "loss": 0.4645, + "step": 11063 + }, + { + "epoch": 0.93, + "learning_rate": 2.881424595253501e-07, + "loss": 0.4718, + "step": 11064 + }, + { + "epoch": 0.93, + "learning_rate": 2.8749698133327396e-07, + "loss": 0.4806, + "step": 11065 + }, + { + "epoch": 0.93, + "learning_rate": 2.868522163870213e-07, + "loss": 0.4608, + "step": 11066 + }, + { + "epoch": 0.93, + "learning_rate": 2.8620816473394206e-07, + "loss": 0.4613, + "step": 11067 + }, + { + "epoch": 0.93, + "learning_rate": 2.855648264213329e-07, + "loss": 0.4636, + "step": 11068 + }, + { + "epoch": 0.93, + "learning_rate": 2.84922201496437e-07, + "loss": 0.4611, + "step": 11069 + }, + { + "epoch": 0.93, + "learning_rate": 2.8428029000644676e-07, + "loss": 0.4624, + "step": 11070 + }, + { + "epoch": 0.93, + "learning_rate": 2.83639091998501e-07, + "loss": 0.4557, + "step": 11071 + }, + { + "epoch": 0.93, + "learning_rate": 2.8299860751968664e-07, + "loss": 0.4618, + "step": 11072 + }, + { + "epoch": 0.93, + "learning_rate": 2.823588366170393e-07, + "loss": 0.4716, + "step": 11073 + }, + { + "epoch": 0.93, + "learning_rate": 2.8171977933754036e-07, + "loss": 0.4572, + "step": 11074 + }, + { + "epoch": 0.93, + "learning_rate": 2.810814357281189e-07, + "loss": 0.4798, + "step": 11075 + }, + { + "epoch": 0.93, + "learning_rate": 2.804438058356529e-07, + "loss": 0.4614, + "step": 11076 + }, + { + "epoch": 0.93, + "learning_rate": 2.798068897069672e-07, + "loss": 0.4506, + "step": 11077 + }, + { + "epoch": 0.93, + "learning_rate": 2.791706873888345e-07, + "loss": 0.4792, + "step": 11078 + }, + { + "epoch": 0.93, + "learning_rate": 2.78535198927975e-07, + "loss": 0.463, + "step": 11079 + }, + { + "epoch": 0.93, + "learning_rate": 2.779004243710548e-07, + "loss": 0.4493, + "step": 11080 + }, + { + "epoch": 0.93, + "learning_rate": 2.7726636376468995e-07, + "loss": 0.4583, + "step": 11081 + }, + { + "epoch": 0.93, + "learning_rate": 2.766330171554443e-07, + "loss": 0.4744, + "step": 11082 + }, + { + "epoch": 0.93, + "learning_rate": 2.7600038458982626e-07, + "loss": 0.4577, + "step": 11083 + }, + { + "epoch": 0.93, + "learning_rate": 2.7536846611429524e-07, + "loss": 0.4498, + "step": 11084 + }, + { + "epoch": 0.93, + "learning_rate": 2.747372617752575e-07, + "loss": 0.466, + "step": 11085 + }, + { + "epoch": 0.93, + "learning_rate": 2.741067716190637e-07, + "loss": 0.4466, + "step": 11086 + }, + { + "epoch": 0.93, + "learning_rate": 2.734769956920169e-07, + "loss": 0.4521, + "step": 11087 + }, + { + "epoch": 0.93, + "learning_rate": 2.728479340403634e-07, + "loss": 0.4548, + "step": 11088 + }, + { + "epoch": 0.93, + "learning_rate": 2.7221958671029834e-07, + "loss": 0.464, + "step": 11089 + }, + { + "epoch": 0.93, + "learning_rate": 2.715919537479661e-07, + "loss": 0.463, + "step": 11090 + }, + { + "epoch": 0.93, + "learning_rate": 2.709650351994575e-07, + "loss": 0.4979, + "step": 11091 + }, + { + "epoch": 0.93, + "learning_rate": 2.7033883111081014e-07, + "loss": 0.46, + "step": 11092 + }, + { + "epoch": 0.93, + "learning_rate": 2.6971334152801063e-07, + "loss": 0.4618, + "step": 11093 + }, + { + "epoch": 0.93, + "learning_rate": 2.690885664969933e-07, + "loss": 0.4493, + "step": 11094 + }, + { + "epoch": 0.93, + "learning_rate": 2.6846450606363705e-07, + "loss": 0.4691, + "step": 11095 + }, + { + "epoch": 0.93, + "learning_rate": 2.678411602737707e-07, + "loss": 0.4505, + "step": 11096 + }, + { + "epoch": 0.93, + "learning_rate": 2.6721852917316995e-07, + "loss": 0.4586, + "step": 11097 + }, + { + "epoch": 0.93, + "learning_rate": 2.665966128075592e-07, + "loss": 0.4665, + "step": 11098 + }, + { + "epoch": 0.93, + "learning_rate": 2.659754112226087e-07, + "loss": 0.4521, + "step": 11099 + }, + { + "epoch": 0.93, + "learning_rate": 2.653549244639375e-07, + "loss": 0.4666, + "step": 11100 + }, + { + "epoch": 0.93, + "learning_rate": 2.6473515257711136e-07, + "loss": 0.456, + "step": 11101 + }, + { + "epoch": 0.93, + "learning_rate": 2.6411609560764273e-07, + "loss": 0.4674, + "step": 11102 + }, + { + "epoch": 0.93, + "learning_rate": 2.6349775360099306e-07, + "loss": 0.4626, + "step": 11103 + }, + { + "epoch": 0.93, + "learning_rate": 2.628801266025727e-07, + "loss": 0.4403, + "step": 11104 + }, + { + "epoch": 0.93, + "learning_rate": 2.622632146577364e-07, + "loss": 0.4732, + "step": 11105 + }, + { + "epoch": 0.93, + "learning_rate": 2.616470178117858e-07, + "loss": 0.4657, + "step": 11106 + }, + { + "epoch": 0.93, + "learning_rate": 2.6103153610997464e-07, + "loss": 0.4599, + "step": 11107 + }, + { + "epoch": 0.93, + "learning_rate": 2.604167695975002e-07, + "loss": 0.4552, + "step": 11108 + }, + { + "epoch": 0.93, + "learning_rate": 2.5980271831950734e-07, + "loss": 0.4677, + "step": 11109 + }, + { + "epoch": 0.93, + "learning_rate": 2.5918938232109004e-07, + "loss": 0.4628, + "step": 11110 + }, + { + "epoch": 0.93, + "learning_rate": 2.5857676164729006e-07, + "loss": 0.4507, + "step": 11111 + }, + { + "epoch": 0.93, + "learning_rate": 2.5796485634309477e-07, + "loss": 0.4524, + "step": 11112 + }, + { + "epoch": 0.93, + "learning_rate": 2.573536664534404e-07, + "loss": 0.4644, + "step": 11113 + }, + { + "epoch": 0.93, + "learning_rate": 2.5674319202320997e-07, + "loss": 0.4485, + "step": 11114 + }, + { + "epoch": 0.93, + "learning_rate": 2.5613343309723426e-07, + "loss": 0.4583, + "step": 11115 + }, + { + "epoch": 0.93, + "learning_rate": 2.555243897202919e-07, + "loss": 0.4837, + "step": 11116 + }, + { + "epoch": 0.93, + "learning_rate": 2.549160619371072e-07, + "loss": 0.4759, + "step": 11117 + }, + { + "epoch": 0.93, + "learning_rate": 2.5430844979235426e-07, + "loss": 0.4621, + "step": 11118 + }, + { + "epoch": 0.93, + "learning_rate": 2.5370155333065416e-07, + "loss": 0.4752, + "step": 11119 + }, + { + "epoch": 0.93, + "learning_rate": 2.5309537259657346e-07, + "loss": 0.4624, + "step": 11120 + }, + { + "epoch": 0.93, + "learning_rate": 2.524899076346288e-07, + "loss": 0.4575, + "step": 11121 + }, + { + "epoch": 0.93, + "learning_rate": 2.518851584892812e-07, + "loss": 0.4817, + "step": 11122 + }, + { + "epoch": 0.93, + "learning_rate": 2.5128112520494297e-07, + "loss": 0.4768, + "step": 11123 + }, + { + "epoch": 0.93, + "learning_rate": 2.5067780782596973e-07, + "loss": 0.4499, + "step": 11124 + }, + { + "epoch": 0.93, + "learning_rate": 2.500752063966694e-07, + "loss": 0.4508, + "step": 11125 + }, + { + "epoch": 0.93, + "learning_rate": 2.494733209612921e-07, + "loss": 0.4726, + "step": 11126 + }, + { + "epoch": 0.93, + "learning_rate": 2.488721515640391e-07, + "loss": 0.4577, + "step": 11127 + }, + { + "epoch": 0.93, + "learning_rate": 2.482716982490574e-07, + "loss": 0.449, + "step": 11128 + }, + { + "epoch": 0.93, + "learning_rate": 2.476719610604417e-07, + "loss": 0.4783, + "step": 11129 + }, + { + "epoch": 0.93, + "learning_rate": 2.4707294004223335e-07, + "loss": 0.483, + "step": 11130 + }, + { + "epoch": 0.93, + "learning_rate": 2.464746352384229e-07, + "loss": 0.4561, + "step": 11131 + }, + { + "epoch": 0.93, + "learning_rate": 2.4587704669294834e-07, + "loss": 0.4791, + "step": 11132 + }, + { + "epoch": 0.93, + "learning_rate": 2.452801744496913e-07, + "loss": 0.4602, + "step": 11133 + }, + { + "epoch": 0.93, + "learning_rate": 2.446840185524868e-07, + "loss": 0.4529, + "step": 11134 + }, + { + "epoch": 0.93, + "learning_rate": 2.4408857904511196e-07, + "loss": 0.4832, + "step": 11135 + }, + { + "epoch": 0.93, + "learning_rate": 2.4349385597129403e-07, + "loss": 0.4787, + "step": 11136 + }, + { + "epoch": 0.93, + "learning_rate": 2.428998493747081e-07, + "loss": 0.4726, + "step": 11137 + }, + { + "epoch": 0.93, + "learning_rate": 2.4230655929897263e-07, + "loss": 0.4646, + "step": 11138 + }, + { + "epoch": 0.93, + "learning_rate": 2.417139857876583e-07, + "loss": 0.4458, + "step": 11139 + }, + { + "epoch": 0.93, + "learning_rate": 2.4112212888428246e-07, + "loss": 0.4363, + "step": 11140 + }, + { + "epoch": 0.93, + "learning_rate": 2.4053098863230706e-07, + "loss": 0.4711, + "step": 11141 + }, + { + "epoch": 0.93, + "learning_rate": 2.3994056507514183e-07, + "loss": 0.4633, + "step": 11142 + }, + { + "epoch": 0.93, + "learning_rate": 2.3935085825614655e-07, + "loss": 0.4565, + "step": 11143 + }, + { + "epoch": 0.93, + "learning_rate": 2.387618682186277e-07, + "loss": 0.4608, + "step": 11144 + }, + { + "epoch": 0.93, + "learning_rate": 2.3817359500583615e-07, + "loss": 0.4632, + "step": 11145 + }, + { + "epoch": 0.93, + "learning_rate": 2.3758603866097406e-07, + "loss": 0.4617, + "step": 11146 + }, + { + "epoch": 0.93, + "learning_rate": 2.3699919922718805e-07, + "loss": 0.4715, + "step": 11147 + }, + { + "epoch": 0.93, + "learning_rate": 2.3641307674757362e-07, + "loss": 0.4526, + "step": 11148 + }, + { + "epoch": 0.93, + "learning_rate": 2.3582767126517302e-07, + "loss": 0.4631, + "step": 11149 + }, + { + "epoch": 0.93, + "learning_rate": 2.352429828229763e-07, + "loss": 0.4627, + "step": 11150 + }, + { + "epoch": 0.93, + "learning_rate": 2.3465901146391912e-07, + "loss": 0.4579, + "step": 11151 + }, + { + "epoch": 0.93, + "learning_rate": 2.3407575723088827e-07, + "loss": 0.4531, + "step": 11152 + }, + { + "epoch": 0.93, + "learning_rate": 2.3349322016671394e-07, + "loss": 0.4655, + "step": 11153 + }, + { + "epoch": 0.93, + "learning_rate": 2.3291140031417525e-07, + "loss": 0.4745, + "step": 11154 + }, + { + "epoch": 0.93, + "learning_rate": 2.3233029771599913e-07, + "loss": 0.4893, + "step": 11155 + }, + { + "epoch": 0.93, + "learning_rate": 2.3174991241485923e-07, + "loss": 0.4505, + "step": 11156 + }, + { + "epoch": 0.93, + "learning_rate": 2.31170244453377e-07, + "loss": 0.4682, + "step": 11157 + }, + { + "epoch": 0.93, + "learning_rate": 2.305912938741184e-07, + "loss": 0.4609, + "step": 11158 + }, + { + "epoch": 0.93, + "learning_rate": 2.3001306071960384e-07, + "loss": 0.4606, + "step": 11159 + }, + { + "epoch": 0.93, + "learning_rate": 2.294355450322916e-07, + "loss": 0.4565, + "step": 11160 + }, + { + "epoch": 0.93, + "learning_rate": 2.2885874685459553e-07, + "loss": 0.4542, + "step": 11161 + }, + { + "epoch": 0.93, + "learning_rate": 2.2828266622887173e-07, + "loss": 0.4691, + "step": 11162 + }, + { + "epoch": 0.93, + "learning_rate": 2.2770730319742528e-07, + "loss": 0.4622, + "step": 11163 + }, + { + "epoch": 0.93, + "learning_rate": 2.271326578025068e-07, + "loss": 0.4703, + "step": 11164 + }, + { + "epoch": 0.93, + "learning_rate": 2.2655873008631812e-07, + "loss": 0.4572, + "step": 11165 + }, + { + "epoch": 0.93, + "learning_rate": 2.259855200910066e-07, + "loss": 0.4871, + "step": 11166 + }, + { + "epoch": 0.93, + "learning_rate": 2.2541302785866525e-07, + "loss": 0.4661, + "step": 11167 + }, + { + "epoch": 0.93, + "learning_rate": 2.248412534313349e-07, + "loss": 0.4621, + "step": 11168 + }, + { + "epoch": 0.93, + "learning_rate": 2.2427019685100527e-07, + "loss": 0.4768, + "step": 11169 + }, + { + "epoch": 0.93, + "learning_rate": 2.236998581596128e-07, + "loss": 0.4552, + "step": 11170 + }, + { + "epoch": 0.93, + "learning_rate": 2.231302373990385e-07, + "loss": 0.4535, + "step": 11171 + }, + { + "epoch": 0.93, + "learning_rate": 2.225613346111155e-07, + "loss": 0.4639, + "step": 11172 + }, + { + "epoch": 0.93, + "learning_rate": 2.2199314983762043e-07, + "loss": 0.4708, + "step": 11173 + }, + { + "epoch": 0.93, + "learning_rate": 2.2142568312027879e-07, + "loss": 0.4768, + "step": 11174 + }, + { + "epoch": 0.93, + "learning_rate": 2.2085893450076167e-07, + "loss": 0.4697, + "step": 11175 + }, + { + "epoch": 0.94, + "learning_rate": 2.2029290402069137e-07, + "loss": 0.4648, + "step": 11176 + }, + { + "epoch": 0.94, + "learning_rate": 2.1972759172163239e-07, + "loss": 0.4732, + "step": 11177 + }, + { + "epoch": 0.94, + "learning_rate": 2.191629976451004e-07, + "loss": 0.4662, + "step": 11178 + }, + { + "epoch": 0.94, + "learning_rate": 2.185991218325556e-07, + "loss": 0.458, + "step": 11179 + }, + { + "epoch": 0.94, + "learning_rate": 2.1803596432540818e-07, + "loss": 0.4644, + "step": 11180 + }, + { + "epoch": 0.94, + "learning_rate": 2.1747352516501396e-07, + "loss": 0.4514, + "step": 11181 + }, + { + "epoch": 0.94, + "learning_rate": 2.1691180439267434e-07, + "loss": 0.477, + "step": 11182 + }, + { + "epoch": 0.94, + "learning_rate": 2.1635080204964187e-07, + "loss": 0.4799, + "step": 11183 + }, + { + "epoch": 0.94, + "learning_rate": 2.157905181771114e-07, + "loss": 0.4699, + "step": 11184 + }, + { + "epoch": 0.94, + "learning_rate": 2.1523095281623109e-07, + "loss": 0.4609, + "step": 11185 + }, + { + "epoch": 0.94, + "learning_rate": 2.146721060080914e-07, + "loss": 0.446, + "step": 11186 + }, + { + "epoch": 0.94, + "learning_rate": 2.141139777937318e-07, + "loss": 0.4774, + "step": 11187 + }, + { + "epoch": 0.94, + "learning_rate": 2.1355656821413938e-07, + "loss": 0.4701, + "step": 11188 + }, + { + "epoch": 0.94, + "learning_rate": 2.1299987731024818e-07, + "loss": 0.457, + "step": 11189 + }, + { + "epoch": 0.94, + "learning_rate": 2.1244390512293878e-07, + "loss": 0.4449, + "step": 11190 + }, + { + "epoch": 0.94, + "learning_rate": 2.1188865169303852e-07, + "loss": 0.4626, + "step": 11191 + }, + { + "epoch": 0.94, + "learning_rate": 2.1133411706132368e-07, + "loss": 0.4547, + "step": 11192 + }, + { + "epoch": 0.94, + "learning_rate": 2.1078030126851833e-07, + "loss": 0.4508, + "step": 11193 + }, + { + "epoch": 0.94, + "learning_rate": 2.1022720435529109e-07, + "loss": 0.4558, + "step": 11194 + }, + { + "epoch": 0.94, + "learning_rate": 2.0967482636225723e-07, + "loss": 0.4591, + "step": 11195 + }, + { + "epoch": 0.94, + "learning_rate": 2.0912316732998538e-07, + "loss": 0.4874, + "step": 11196 + }, + { + "epoch": 0.94, + "learning_rate": 2.0857222729898429e-07, + "loss": 0.4589, + "step": 11197 + }, + { + "epoch": 0.94, + "learning_rate": 2.0802200630971382e-07, + "loss": 0.4498, + "step": 11198 + }, + { + "epoch": 0.94, + "learning_rate": 2.0747250440257715e-07, + "loss": 0.4682, + "step": 11199 + }, + { + "epoch": 0.94, + "learning_rate": 2.0692372161793094e-07, + "loss": 0.4665, + "step": 11200 + }, + { + "epoch": 0.94, + "learning_rate": 2.0637565799607517e-07, + "loss": 0.4639, + "step": 11201 + }, + { + "epoch": 0.94, + "learning_rate": 2.0582831357725542e-07, + "loss": 0.4561, + "step": 11202 + }, + { + "epoch": 0.94, + "learning_rate": 2.052816884016673e-07, + "loss": 0.4466, + "step": 11203 + }, + { + "epoch": 0.94, + "learning_rate": 2.0473578250945315e-07, + "loss": 0.4515, + "step": 11204 + }, + { + "epoch": 0.94, + "learning_rate": 2.0419059594069977e-07, + "loss": 0.4653, + "step": 11205 + }, + { + "epoch": 0.94, + "learning_rate": 2.0364612873544632e-07, + "loss": 0.4583, + "step": 11206 + }, + { + "epoch": 0.94, + "learning_rate": 2.0310238093367517e-07, + "loss": 0.4565, + "step": 11207 + }, + { + "epoch": 0.94, + "learning_rate": 2.0255935257531668e-07, + "loss": 0.4796, + "step": 11208 + }, + { + "epoch": 0.94, + "learning_rate": 2.0201704370024889e-07, + "loss": 0.4641, + "step": 11209 + }, + { + "epoch": 0.94, + "learning_rate": 2.0147545434829664e-07, + "loss": 0.4512, + "step": 11210 + }, + { + "epoch": 0.94, + "learning_rate": 2.0093458455923253e-07, + "loss": 0.4543, + "step": 11211 + }, + { + "epoch": 0.94, + "learning_rate": 2.0039443437277483e-07, + "loss": 0.4575, + "step": 11212 + }, + { + "epoch": 0.94, + "learning_rate": 1.9985500382858846e-07, + "loss": 0.4808, + "step": 11213 + }, + { + "epoch": 0.94, + "learning_rate": 1.9931629296629062e-07, + "loss": 0.4879, + "step": 11214 + }, + { + "epoch": 0.94, + "learning_rate": 1.9877830182543966e-07, + "loss": 0.4643, + "step": 11215 + }, + { + "epoch": 0.94, + "learning_rate": 1.982410304455429e-07, + "loss": 0.4918, + "step": 11216 + }, + { + "epoch": 0.94, + "learning_rate": 1.977044788660576e-07, + "loss": 0.4732, + "step": 11217 + }, + { + "epoch": 0.94, + "learning_rate": 1.9716864712638452e-07, + "loss": 0.458, + "step": 11218 + }, + { + "epoch": 0.94, + "learning_rate": 1.9663353526587104e-07, + "loss": 0.4465, + "step": 11219 + }, + { + "epoch": 0.94, + "learning_rate": 1.9609914332381797e-07, + "loss": 0.467, + "step": 11220 + }, + { + "epoch": 0.94, + "learning_rate": 1.9556547133946503e-07, + "loss": 0.471, + "step": 11221 + }, + { + "epoch": 0.94, + "learning_rate": 1.9503251935200418e-07, + "loss": 0.4334, + "step": 11222 + }, + { + "epoch": 0.94, + "learning_rate": 1.9450028740057415e-07, + "loss": 0.4527, + "step": 11223 + }, + { + "epoch": 0.94, + "learning_rate": 1.9396877552425808e-07, + "loss": 0.4616, + "step": 11224 + }, + { + "epoch": 0.94, + "learning_rate": 1.9343798376208812e-07, + "loss": 0.4508, + "step": 11225 + }, + { + "epoch": 0.94, + "learning_rate": 1.9290791215304527e-07, + "loss": 0.4742, + "step": 11226 + }, + { + "epoch": 0.94, + "learning_rate": 1.92378560736054e-07, + "loss": 0.4621, + "step": 11227 + }, + { + "epoch": 0.94, + "learning_rate": 1.918499295499887e-07, + "loss": 0.4577, + "step": 11228 + }, + { + "epoch": 0.94, + "learning_rate": 1.913220186336684e-07, + "loss": 0.4754, + "step": 11229 + }, + { + "epoch": 0.94, + "learning_rate": 1.9079482802586314e-07, + "loss": 0.4778, + "step": 11230 + }, + { + "epoch": 0.94, + "learning_rate": 1.9026835776528529e-07, + "loss": 0.443, + "step": 11231 + }, + { + "epoch": 0.94, + "learning_rate": 1.897426078905984e-07, + "loss": 0.4614, + "step": 11232 + }, + { + "epoch": 0.94, + "learning_rate": 1.8921757844040821e-07, + "loss": 0.4567, + "step": 11233 + }, + { + "epoch": 0.94, + "learning_rate": 1.8869326945327505e-07, + "loss": 0.4597, + "step": 11234 + }, + { + "epoch": 0.94, + "learning_rate": 1.8816968096769917e-07, + "loss": 0.4536, + "step": 11235 + }, + { + "epoch": 0.94, + "learning_rate": 1.8764681302213096e-07, + "loss": 0.4508, + "step": 11236 + }, + { + "epoch": 0.94, + "learning_rate": 1.8712466565496966e-07, + "loss": 0.4729, + "step": 11237 + }, + { + "epoch": 0.94, + "learning_rate": 1.866032389045569e-07, + "loss": 0.4623, + "step": 11238 + }, + { + "epoch": 0.94, + "learning_rate": 1.860825328091853e-07, + "loss": 0.4619, + "step": 11239 + }, + { + "epoch": 0.94, + "learning_rate": 1.8556254740709322e-07, + "loss": 0.4518, + "step": 11240 + }, + { + "epoch": 0.94, + "learning_rate": 1.8504328273646676e-07, + "loss": 0.4522, + "step": 11241 + }, + { + "epoch": 0.94, + "learning_rate": 1.8452473883543876e-07, + "loss": 0.4689, + "step": 11242 + }, + { + "epoch": 0.94, + "learning_rate": 1.8400691574208763e-07, + "loss": 0.4826, + "step": 11243 + }, + { + "epoch": 0.94, + "learning_rate": 1.8348981349444073e-07, + "loss": 0.4514, + "step": 11244 + }, + { + "epoch": 0.94, + "learning_rate": 1.8297343213047215e-07, + "loss": 0.4614, + "step": 11245 + }, + { + "epoch": 0.94, + "learning_rate": 1.8245777168810264e-07, + "loss": 0.4789, + "step": 11246 + }, + { + "epoch": 0.94, + "learning_rate": 1.8194283220519972e-07, + "loss": 0.4497, + "step": 11247 + }, + { + "epoch": 0.94, + "learning_rate": 1.8142861371957866e-07, + "loss": 0.4716, + "step": 11248 + }, + { + "epoch": 0.94, + "learning_rate": 1.809151162690026e-07, + "loss": 0.4514, + "step": 11249 + }, + { + "epoch": 0.94, + "learning_rate": 1.8040233989117915e-07, + "loss": 0.4515, + "step": 11250 + }, + { + "epoch": 0.94, + "learning_rate": 1.79890284623766e-07, + "loss": 0.4727, + "step": 11251 + }, + { + "epoch": 0.94, + "learning_rate": 1.7937895050436528e-07, + "loss": 0.4491, + "step": 11252 + }, + { + "epoch": 0.94, + "learning_rate": 1.7886833757052692e-07, + "loss": 0.4514, + "step": 11253 + }, + { + "epoch": 0.94, + "learning_rate": 1.783584458597476e-07, + "loss": 0.4681, + "step": 11254 + }, + { + "epoch": 0.94, + "learning_rate": 1.7784927540947406e-07, + "loss": 0.4641, + "step": 11255 + }, + { + "epoch": 0.94, + "learning_rate": 1.7734082625709637e-07, + "loss": 0.4511, + "step": 11256 + }, + { + "epoch": 0.94, + "learning_rate": 1.7683309843995245e-07, + "loss": 0.4866, + "step": 11257 + }, + { + "epoch": 0.94, + "learning_rate": 1.76326091995328e-07, + "loss": 0.4605, + "step": 11258 + }, + { + "epoch": 0.94, + "learning_rate": 1.7581980696045665e-07, + "loss": 0.4512, + "step": 11259 + }, + { + "epoch": 0.94, + "learning_rate": 1.7531424337251523e-07, + "loss": 0.4494, + "step": 11260 + }, + { + "epoch": 0.94, + "learning_rate": 1.74809401268633e-07, + "loss": 0.4466, + "step": 11261 + }, + { + "epoch": 0.94, + "learning_rate": 1.7430528068588136e-07, + "loss": 0.4511, + "step": 11262 + }, + { + "epoch": 0.94, + "learning_rate": 1.73801881661283e-07, + "loss": 0.4694, + "step": 11263 + }, + { + "epoch": 0.94, + "learning_rate": 1.732992042318038e-07, + "loss": 0.4656, + "step": 11264 + }, + { + "epoch": 0.94, + "learning_rate": 1.7279724843435874e-07, + "loss": 0.4696, + "step": 11265 + }, + { + "epoch": 0.94, + "learning_rate": 1.7229601430580832e-07, + "loss": 0.4668, + "step": 11266 + }, + { + "epoch": 0.94, + "learning_rate": 1.7179550188296313e-07, + "loss": 0.4587, + "step": 11267 + }, + { + "epoch": 0.94, + "learning_rate": 1.7129571120257705e-07, + "loss": 0.4508, + "step": 11268 + }, + { + "epoch": 0.94, + "learning_rate": 1.7079664230135406e-07, + "loss": 0.4877, + "step": 11269 + }, + { + "epoch": 0.94, + "learning_rate": 1.7029829521594265e-07, + "loss": 0.4431, + "step": 11270 + }, + { + "epoch": 0.94, + "learning_rate": 1.698006699829402e-07, + "loss": 0.4604, + "step": 11271 + }, + { + "epoch": 0.94, + "learning_rate": 1.693037666388886e-07, + "loss": 0.4764, + "step": 11272 + }, + { + "epoch": 0.94, + "learning_rate": 1.6880758522028083e-07, + "loss": 0.449, + "step": 11273 + }, + { + "epoch": 0.94, + "learning_rate": 1.6831212576355116e-07, + "loss": 0.4654, + "step": 11274 + }, + { + "epoch": 0.94, + "learning_rate": 1.6781738830508708e-07, + "loss": 0.4697, + "step": 11275 + }, + { + "epoch": 0.94, + "learning_rate": 1.6732337288121848e-07, + "loss": 0.4456, + "step": 11276 + }, + { + "epoch": 0.94, + "learning_rate": 1.6683007952822405e-07, + "loss": 0.4683, + "step": 11277 + }, + { + "epoch": 0.94, + "learning_rate": 1.663375082823293e-07, + "loss": 0.4491, + "step": 11278 + }, + { + "epoch": 0.94, + "learning_rate": 1.658456591797075e-07, + "loss": 0.4488, + "step": 11279 + }, + { + "epoch": 0.94, + "learning_rate": 1.6535453225647645e-07, + "loss": 0.4635, + "step": 11280 + }, + { + "epoch": 0.94, + "learning_rate": 1.6486412754870286e-07, + "loss": 0.4656, + "step": 11281 + }, + { + "epoch": 0.94, + "learning_rate": 1.643744450924012e-07, + "loss": 0.489, + "step": 11282 + }, + { + "epoch": 0.94, + "learning_rate": 1.638854849235305e-07, + "loss": 0.4561, + "step": 11283 + }, + { + "epoch": 0.94, + "learning_rate": 1.6339724707799875e-07, + "loss": 0.458, + "step": 11284 + }, + { + "epoch": 0.94, + "learning_rate": 1.6290973159165945e-07, + "loss": 0.4563, + "step": 11285 + }, + { + "epoch": 0.94, + "learning_rate": 1.62422938500314e-07, + "loss": 0.4512, + "step": 11286 + }, + { + "epoch": 0.94, + "learning_rate": 1.619368678397093e-07, + "loss": 0.4662, + "step": 11287 + }, + { + "epoch": 0.94, + "learning_rate": 1.614515196455424e-07, + "loss": 0.4656, + "step": 11288 + }, + { + "epoch": 0.94, + "learning_rate": 1.6096689395345366e-07, + "loss": 0.4872, + "step": 11289 + }, + { + "epoch": 0.94, + "learning_rate": 1.604829907990335e-07, + "loss": 0.4777, + "step": 11290 + }, + { + "epoch": 0.94, + "learning_rate": 1.5999981021781685e-07, + "loss": 0.4589, + "step": 11291 + }, + { + "epoch": 0.94, + "learning_rate": 1.595173522452864e-07, + "loss": 0.4641, + "step": 11292 + }, + { + "epoch": 0.94, + "learning_rate": 1.5903561691687164e-07, + "loss": 0.4715, + "step": 11293 + }, + { + "epoch": 0.94, + "learning_rate": 1.5855460426794865e-07, + "loss": 0.446, + "step": 11294 + }, + { + "epoch": 0.94, + "learning_rate": 1.5807431433384368e-07, + "loss": 0.4725, + "step": 11295 + }, + { + "epoch": 0.95, + "learning_rate": 1.5759474714982405e-07, + "loss": 0.4727, + "step": 11296 + }, + { + "epoch": 0.95, + "learning_rate": 1.5711590275110933e-07, + "loss": 0.4476, + "step": 11297 + }, + { + "epoch": 0.95, + "learning_rate": 1.5663778117286254e-07, + "loss": 0.4618, + "step": 11298 + }, + { + "epoch": 0.95, + "learning_rate": 1.561603824501956e-07, + "loss": 0.4643, + "step": 11299 + }, + { + "epoch": 0.95, + "learning_rate": 1.5568370661816713e-07, + "loss": 0.4793, + "step": 11300 + }, + { + "epoch": 0.95, + "learning_rate": 1.552077537117802e-07, + "loss": 0.4569, + "step": 11301 + }, + { + "epoch": 0.95, + "learning_rate": 1.5473252376598913e-07, + "loss": 0.4629, + "step": 11302 + }, + { + "epoch": 0.95, + "learning_rate": 1.5425801681569263e-07, + "loss": 0.4617, + "step": 11303 + }, + { + "epoch": 0.95, + "learning_rate": 1.5378423289573508e-07, + "loss": 0.4613, + "step": 11304 + }, + { + "epoch": 0.95, + "learning_rate": 1.5331117204091085e-07, + "loss": 0.45, + "step": 11305 + }, + { + "epoch": 0.95, + "learning_rate": 1.528388342859577e-07, + "loss": 0.4758, + "step": 11306 + }, + { + "epoch": 0.95, + "learning_rate": 1.5236721966556456e-07, + "loss": 0.4927, + "step": 11307 + }, + { + "epoch": 0.95, + "learning_rate": 1.518963282143615e-07, + "loss": 0.4616, + "step": 11308 + }, + { + "epoch": 0.95, + "learning_rate": 1.5142615996693087e-07, + "loss": 0.4713, + "step": 11309 + }, + { + "epoch": 0.95, + "learning_rate": 1.5095671495780062e-07, + "loss": 0.4613, + "step": 11310 + }, + { + "epoch": 0.95, + "learning_rate": 1.5048799322144426e-07, + "loss": 0.4549, + "step": 11311 + }, + { + "epoch": 0.95, + "learning_rate": 1.5001999479228203e-07, + "loss": 0.459, + "step": 11312 + }, + { + "epoch": 0.95, + "learning_rate": 1.49552719704682e-07, + "loss": 0.4595, + "step": 11313 + }, + { + "epoch": 0.95, + "learning_rate": 1.4908616799296006e-07, + "loss": 0.4503, + "step": 11314 + }, + { + "epoch": 0.95, + "learning_rate": 1.4862033969137545e-07, + "loss": 0.4753, + "step": 11315 + }, + { + "epoch": 0.95, + "learning_rate": 1.4815523483413864e-07, + "loss": 0.4399, + "step": 11316 + }, + { + "epoch": 0.95, + "learning_rate": 1.4769085345540556e-07, + "loss": 0.4847, + "step": 11317 + }, + { + "epoch": 0.95, + "learning_rate": 1.472271955892768e-07, + "loss": 0.4602, + "step": 11318 + }, + { + "epoch": 0.95, + "learning_rate": 1.4676426126980058e-07, + "loss": 0.4709, + "step": 11319 + }, + { + "epoch": 0.95, + "learning_rate": 1.4630205053097645e-07, + "loss": 0.4564, + "step": 11320 + }, + { + "epoch": 0.95, + "learning_rate": 1.4584056340674392e-07, + "loss": 0.4561, + "step": 11321 + }, + { + "epoch": 0.95, + "learning_rate": 1.4537979993099361e-07, + "loss": 0.4634, + "step": 11322 + }, + { + "epoch": 0.95, + "learning_rate": 1.4491976013756292e-07, + "loss": 0.462, + "step": 11323 + }, + { + "epoch": 0.95, + "learning_rate": 1.4446044406023485e-07, + "loss": 0.4504, + "step": 11324 + }, + { + "epoch": 0.95, + "learning_rate": 1.4400185173274018e-07, + "loss": 0.4507, + "step": 11325 + }, + { + "epoch": 0.95, + "learning_rate": 1.4354398318875417e-07, + "loss": 0.4674, + "step": 11326 + }, + { + "epoch": 0.95, + "learning_rate": 1.430868384619022e-07, + "loss": 0.4756, + "step": 11327 + }, + { + "epoch": 0.95, + "learning_rate": 1.4263041758575402e-07, + "loss": 0.4396, + "step": 11328 + }, + { + "epoch": 0.95, + "learning_rate": 1.4217472059382952e-07, + "loss": 0.464, + "step": 11329 + }, + { + "epoch": 0.95, + "learning_rate": 1.4171974751959082e-07, + "loss": 0.4678, + "step": 11330 + }, + { + "epoch": 0.95, + "learning_rate": 1.4126549839645009e-07, + "loss": 0.4847, + "step": 11331 + }, + { + "epoch": 0.95, + "learning_rate": 1.408119732577662e-07, + "loss": 0.4553, + "step": 11332 + }, + { + "epoch": 0.95, + "learning_rate": 1.4035917213684358e-07, + "loss": 0.4686, + "step": 11333 + }, + { + "epoch": 0.95, + "learning_rate": 1.3990709506693457e-07, + "loss": 0.4596, + "step": 11334 + }, + { + "epoch": 0.95, + "learning_rate": 1.394557420812359e-07, + "loss": 0.443, + "step": 11335 + }, + { + "epoch": 0.95, + "learning_rate": 1.3900511321289557e-07, + "loss": 0.4613, + "step": 11336 + }, + { + "epoch": 0.95, + "learning_rate": 1.385552084950037e-07, + "loss": 0.4579, + "step": 11337 + }, + { + "epoch": 0.95, + "learning_rate": 1.381060279606017e-07, + "loss": 0.4549, + "step": 11338 + }, + { + "epoch": 0.95, + "learning_rate": 1.3765757164267313e-07, + "loss": 0.4551, + "step": 11339 + }, + { + "epoch": 0.95, + "learning_rate": 1.3720983957415278e-07, + "loss": 0.4749, + "step": 11340 + }, + { + "epoch": 0.95, + "learning_rate": 1.3676283178791882e-07, + "loss": 0.4428, + "step": 11341 + }, + { + "epoch": 0.95, + "learning_rate": 1.363165483167983e-07, + "loss": 0.4797, + "step": 11342 + }, + { + "epoch": 0.95, + "learning_rate": 1.35870989193565e-07, + "loss": 0.4681, + "step": 11343 + }, + { + "epoch": 0.95, + "learning_rate": 1.3542615445093722e-07, + "loss": 0.4495, + "step": 11344 + }, + { + "epoch": 0.95, + "learning_rate": 1.3498204412158434e-07, + "loss": 0.4612, + "step": 11345 + }, + { + "epoch": 0.95, + "learning_rate": 1.3453865823811696e-07, + "loss": 0.4608, + "step": 11346 + }, + { + "epoch": 0.95, + "learning_rate": 1.3409599683309793e-07, + "loss": 0.4477, + "step": 11347 + }, + { + "epoch": 0.95, + "learning_rate": 1.3365405993903347e-07, + "loss": 0.4679, + "step": 11348 + }, + { + "epoch": 0.95, + "learning_rate": 1.332128475883765e-07, + "loss": 0.4465, + "step": 11349 + }, + { + "epoch": 0.95, + "learning_rate": 1.3277235981352887e-07, + "loss": 0.4629, + "step": 11350 + }, + { + "epoch": 0.95, + "learning_rate": 1.3233259664683916e-07, + "loss": 0.4655, + "step": 11351 + }, + { + "epoch": 0.95, + "learning_rate": 1.3189355812060157e-07, + "loss": 0.4558, + "step": 11352 + }, + { + "epoch": 0.95, + "learning_rate": 1.314552442670558e-07, + "loss": 0.4475, + "step": 11353 + }, + { + "epoch": 0.95, + "learning_rate": 1.310176551183906e-07, + "loss": 0.4415, + "step": 11354 + }, + { + "epoch": 0.95, + "learning_rate": 1.3058079070674023e-07, + "loss": 0.4641, + "step": 11355 + }, + { + "epoch": 0.95, + "learning_rate": 1.3014465106418573e-07, + "loss": 0.4601, + "step": 11356 + }, + { + "epoch": 0.95, + "learning_rate": 1.297092362227581e-07, + "loss": 0.4457, + "step": 11357 + }, + { + "epoch": 0.95, + "learning_rate": 1.2927454621442959e-07, + "loss": 0.4609, + "step": 11358 + }, + { + "epoch": 0.95, + "learning_rate": 1.2884058107112353e-07, + "loss": 0.4725, + "step": 11359 + }, + { + "epoch": 0.95, + "learning_rate": 1.2840734082470662e-07, + "loss": 0.455, + "step": 11360 + }, + { + "epoch": 0.95, + "learning_rate": 1.279748255069968e-07, + "loss": 0.453, + "step": 11361 + }, + { + "epoch": 0.95, + "learning_rate": 1.275430351497542e-07, + "loss": 0.4684, + "step": 11362 + }, + { + "epoch": 0.95, + "learning_rate": 1.27111969784689e-07, + "loss": 0.4651, + "step": 11363 + }, + { + "epoch": 0.95, + "learning_rate": 1.2668162944345587e-07, + "loss": 0.4371, + "step": 11364 + }, + { + "epoch": 0.95, + "learning_rate": 1.262520141576584e-07, + "loss": 0.4689, + "step": 11365 + }, + { + "epoch": 0.95, + "learning_rate": 1.2582312395884476e-07, + "loss": 0.4626, + "step": 11366 + }, + { + "epoch": 0.95, + "learning_rate": 1.2539495887851083e-07, + "loss": 0.4517, + "step": 11367 + }, + { + "epoch": 0.95, + "learning_rate": 1.2496751894810032e-07, + "loss": 0.4605, + "step": 11368 + }, + { + "epoch": 0.95, + "learning_rate": 1.245408041990004e-07, + "loss": 0.4645, + "step": 11369 + }, + { + "epoch": 0.95, + "learning_rate": 1.2411481466254926e-07, + "loss": 0.4477, + "step": 11370 + }, + { + "epoch": 0.95, + "learning_rate": 1.2368955037002973e-07, + "loss": 0.4739, + "step": 11371 + }, + { + "epoch": 0.95, + "learning_rate": 1.232650113526701e-07, + "loss": 0.4712, + "step": 11372 + }, + { + "epoch": 0.95, + "learning_rate": 1.228411976416488e-07, + "loss": 0.4649, + "step": 11373 + }, + { + "epoch": 0.95, + "learning_rate": 1.2241810926808762e-07, + "loss": 0.4477, + "step": 11374 + }, + { + "epoch": 0.95, + "learning_rate": 1.219957462630561e-07, + "loss": 0.4506, + "step": 11375 + }, + { + "epoch": 0.95, + "learning_rate": 1.2157410865757057e-07, + "loss": 0.4762, + "step": 11376 + }, + { + "epoch": 0.95, + "learning_rate": 1.2115319648259516e-07, + "loss": 0.4677, + "step": 11377 + }, + { + "epoch": 0.95, + "learning_rate": 1.2073300976904067e-07, + "loss": 0.4585, + "step": 11378 + }, + { + "epoch": 0.95, + "learning_rate": 1.2031354854776356e-07, + "loss": 0.4589, + "step": 11379 + }, + { + "epoch": 0.95, + "learning_rate": 1.198948128495647e-07, + "loss": 0.4742, + "step": 11380 + }, + { + "epoch": 0.95, + "learning_rate": 1.1947680270519733e-07, + "loss": 0.4694, + "step": 11381 + }, + { + "epoch": 0.95, + "learning_rate": 1.19059518145358e-07, + "loss": 0.4748, + "step": 11382 + }, + { + "epoch": 0.95, + "learning_rate": 1.186429592006888e-07, + "loss": 0.4683, + "step": 11383 + }, + { + "epoch": 0.95, + "learning_rate": 1.1822712590178197e-07, + "loss": 0.4732, + "step": 11384 + }, + { + "epoch": 0.95, + "learning_rate": 1.178120182791731e-07, + "loss": 0.4454, + "step": 11385 + }, + { + "epoch": 0.95, + "learning_rate": 1.1739763636334667e-07, + "loss": 0.4684, + "step": 11386 + }, + { + "epoch": 0.95, + "learning_rate": 1.1698398018473278e-07, + "loss": 0.4555, + "step": 11387 + }, + { + "epoch": 0.95, + "learning_rate": 1.1657104977370937e-07, + "loss": 0.4729, + "step": 11388 + }, + { + "epoch": 0.95, + "learning_rate": 1.1615884516059883e-07, + "loss": 0.4459, + "step": 11389 + }, + { + "epoch": 0.95, + "learning_rate": 1.1574736637567252e-07, + "loss": 0.462, + "step": 11390 + }, + { + "epoch": 0.95, + "learning_rate": 1.1533661344914848e-07, + "loss": 0.4428, + "step": 11391 + }, + { + "epoch": 0.95, + "learning_rate": 1.1492658641119037e-07, + "loss": 0.4663, + "step": 11392 + }, + { + "epoch": 0.95, + "learning_rate": 1.1451728529190852e-07, + "loss": 0.4739, + "step": 11393 + }, + { + "epoch": 0.95, + "learning_rate": 1.1410871012136116e-07, + "loss": 0.4518, + "step": 11394 + }, + { + "epoch": 0.95, + "learning_rate": 1.137008609295509e-07, + "loss": 0.4517, + "step": 11395 + }, + { + "epoch": 0.95, + "learning_rate": 1.1329373774642938e-07, + "loss": 0.4603, + "step": 11396 + }, + { + "epoch": 0.95, + "learning_rate": 1.1288734060189267e-07, + "loss": 0.4487, + "step": 11397 + }, + { + "epoch": 0.95, + "learning_rate": 1.1248166952578799e-07, + "loss": 0.4477, + "step": 11398 + }, + { + "epoch": 0.95, + "learning_rate": 1.1207672454790264e-07, + "loss": 0.4674, + "step": 11399 + }, + { + "epoch": 0.95, + "learning_rate": 1.1167250569797728e-07, + "loss": 0.4888, + "step": 11400 + }, + { + "epoch": 0.95, + "learning_rate": 1.112690130056926e-07, + "loss": 0.4248, + "step": 11401 + }, + { + "epoch": 0.95, + "learning_rate": 1.1086624650068267e-07, + "loss": 0.4714, + "step": 11402 + }, + { + "epoch": 0.95, + "learning_rate": 1.1046420621252275e-07, + "loss": 0.4564, + "step": 11403 + }, + { + "epoch": 0.95, + "learning_rate": 1.1006289217073806e-07, + "loss": 0.4568, + "step": 11404 + }, + { + "epoch": 0.95, + "learning_rate": 1.0966230440479953e-07, + "loss": 0.4453, + "step": 11405 + }, + { + "epoch": 0.95, + "learning_rate": 1.0926244294412359e-07, + "loss": 0.4599, + "step": 11406 + }, + { + "epoch": 0.95, + "learning_rate": 1.0886330781807674e-07, + "loss": 0.4831, + "step": 11407 + }, + { + "epoch": 0.95, + "learning_rate": 1.0846489905596669e-07, + "loss": 0.459, + "step": 11408 + }, + { + "epoch": 0.95, + "learning_rate": 1.0806721668705333e-07, + "loss": 0.4722, + "step": 11409 + }, + { + "epoch": 0.95, + "learning_rate": 1.0767026074053888e-07, + "loss": 0.4564, + "step": 11410 + }, + { + "epoch": 0.95, + "learning_rate": 1.0727403124557667e-07, + "loss": 0.473, + "step": 11411 + }, + { + "epoch": 0.95, + "learning_rate": 1.0687852823126122e-07, + "loss": 0.4533, + "step": 11412 + }, + { + "epoch": 0.95, + "learning_rate": 1.0648375172663927e-07, + "loss": 0.466, + "step": 11413 + }, + { + "epoch": 0.95, + "learning_rate": 1.0608970176069987e-07, + "loss": 0.4882, + "step": 11414 + }, + { + "epoch": 0.96, + "learning_rate": 1.05696378362381e-07, + "loss": 0.4757, + "step": 11415 + }, + { + "epoch": 0.96, + "learning_rate": 1.053037815605662e-07, + "loss": 0.4573, + "step": 11416 + }, + { + "epoch": 0.96, + "learning_rate": 1.0491191138408685e-07, + "loss": 0.4652, + "step": 11417 + }, + { + "epoch": 0.96, + "learning_rate": 1.0452076786171994e-07, + "loss": 0.4586, + "step": 11418 + }, + { + "epoch": 0.96, + "learning_rate": 1.0413035102219027e-07, + "loss": 0.4461, + "step": 11419 + }, + { + "epoch": 0.96, + "learning_rate": 1.0374066089416602e-07, + "loss": 0.4575, + "step": 11420 + }, + { + "epoch": 0.96, + "learning_rate": 1.033516975062676e-07, + "loss": 0.4532, + "step": 11421 + }, + { + "epoch": 0.96, + "learning_rate": 1.0296346088705555e-07, + "loss": 0.4417, + "step": 11422 + }, + { + "epoch": 0.96, + "learning_rate": 1.025759510650437e-07, + "loss": 0.4606, + "step": 11423 + }, + { + "epoch": 0.96, + "learning_rate": 1.0218916806868594e-07, + "loss": 0.469, + "step": 11424 + }, + { + "epoch": 0.96, + "learning_rate": 1.0180311192638848e-07, + "loss": 0.4542, + "step": 11425 + }, + { + "epoch": 0.96, + "learning_rate": 1.0141778266650082e-07, + "loss": 0.4661, + "step": 11426 + }, + { + "epoch": 0.96, + "learning_rate": 1.0103318031732035e-07, + "loss": 0.4652, + "step": 11427 + }, + { + "epoch": 0.96, + "learning_rate": 1.006493049070889e-07, + "loss": 0.4853, + "step": 11428 + }, + { + "epoch": 0.96, + "learning_rate": 1.002661564639995e-07, + "loss": 0.4559, + "step": 11429 + }, + { + "epoch": 0.96, + "learning_rate": 9.988373501618631e-08, + "loss": 0.4535, + "step": 11430 + }, + { + "epoch": 0.96, + "learning_rate": 9.950204059173462e-08, + "loss": 0.4537, + "step": 11431 + }, + { + "epoch": 0.96, + "learning_rate": 9.912107321867315e-08, + "loss": 0.462, + "step": 11432 + }, + { + "epoch": 0.96, + "learning_rate": 9.87408329249795e-08, + "loss": 0.4469, + "step": 11433 + }, + { + "epoch": 0.96, + "learning_rate": 9.836131973857687e-08, + "loss": 0.4602, + "step": 11434 + }, + { + "epoch": 0.96, + "learning_rate": 9.798253368733523e-08, + "loss": 0.4734, + "step": 11435 + }, + { + "epoch": 0.96, + "learning_rate": 9.76044747990701e-08, + "loss": 0.4662, + "step": 11436 + }, + { + "epoch": 0.96, + "learning_rate": 9.722714310154591e-08, + "loss": 0.4702, + "step": 11437 + }, + { + "epoch": 0.96, + "learning_rate": 9.685053862247051e-08, + "loss": 0.4542, + "step": 11438 + }, + { + "epoch": 0.96, + "learning_rate": 9.647466138950178e-08, + "loss": 0.4661, + "step": 11439 + }, + { + "epoch": 0.96, + "learning_rate": 9.60995114302421e-08, + "loss": 0.4739, + "step": 11440 + }, + { + "epoch": 0.96, + "learning_rate": 9.572508877224163e-08, + "loss": 0.4406, + "step": 11441 + }, + { + "epoch": 0.96, + "learning_rate": 9.535139344299393e-08, + "loss": 0.4697, + "step": 11442 + }, + { + "epoch": 0.96, + "learning_rate": 9.497842546994485e-08, + "loss": 0.4764, + "step": 11443 + }, + { + "epoch": 0.96, + "learning_rate": 9.460618488048024e-08, + "loss": 0.4497, + "step": 11444 + }, + { + "epoch": 0.96, + "learning_rate": 9.423467170193933e-08, + "loss": 0.4531, + "step": 11445 + }, + { + "epoch": 0.96, + "learning_rate": 9.386388596160367e-08, + "loss": 0.4582, + "step": 11446 + }, + { + "epoch": 0.96, + "learning_rate": 9.349382768670034e-08, + "loss": 0.4613, + "step": 11447 + }, + { + "epoch": 0.96, + "learning_rate": 9.31244969044065e-08, + "loss": 0.4622, + "step": 11448 + }, + { + "epoch": 0.96, + "learning_rate": 9.275589364184379e-08, + "loss": 0.4951, + "step": 11449 + }, + { + "epoch": 0.96, + "learning_rate": 9.238801792608054e-08, + "loss": 0.4514, + "step": 11450 + }, + { + "epoch": 0.96, + "learning_rate": 9.202086978413294e-08, + "loss": 0.4673, + "step": 11451 + }, + { + "epoch": 0.96, + "learning_rate": 9.165444924296163e-08, + "loss": 0.4674, + "step": 11452 + }, + { + "epoch": 0.96, + "learning_rate": 9.12887563294751e-08, + "loss": 0.462, + "step": 11453 + }, + { + "epoch": 0.96, + "learning_rate": 9.092379107053074e-08, + "loss": 0.4548, + "step": 11454 + }, + { + "epoch": 0.96, + "learning_rate": 9.055955349292711e-08, + "loss": 0.4618, + "step": 11455 + }, + { + "epoch": 0.96, + "learning_rate": 9.019604362341394e-08, + "loss": 0.4822, + "step": 11456 + }, + { + "epoch": 0.96, + "learning_rate": 8.983326148868432e-08, + "loss": 0.4545, + "step": 11457 + }, + { + "epoch": 0.96, + "learning_rate": 8.947120711538138e-08, + "loss": 0.4525, + "step": 11458 + }, + { + "epoch": 0.96, + "learning_rate": 8.910988053009162e-08, + "loss": 0.462, + "step": 11459 + }, + { + "epoch": 0.96, + "learning_rate": 8.874928175934938e-08, + "loss": 0.4336, + "step": 11460 + }, + { + "epoch": 0.96, + "learning_rate": 8.838941082963681e-08, + "loss": 0.4565, + "step": 11461 + }, + { + "epoch": 0.96, + "learning_rate": 8.803026776738055e-08, + "loss": 0.4647, + "step": 11462 + }, + { + "epoch": 0.96, + "learning_rate": 8.767185259895284e-08, + "loss": 0.4468, + "step": 11463 + }, + { + "epoch": 0.96, + "learning_rate": 8.731416535067705e-08, + "loss": 0.4473, + "step": 11464 + }, + { + "epoch": 0.96, + "learning_rate": 8.695720604881886e-08, + "loss": 0.4576, + "step": 11465 + }, + { + "epoch": 0.96, + "learning_rate": 8.660097471959173e-08, + "loss": 0.4786, + "step": 11466 + }, + { + "epoch": 0.96, + "learning_rate": 8.624547138915696e-08, + "loss": 0.4623, + "step": 11467 + }, + { + "epoch": 0.96, + "learning_rate": 8.589069608361922e-08, + "loss": 0.4606, + "step": 11468 + }, + { + "epoch": 0.96, + "learning_rate": 8.553664882903323e-08, + "loss": 0.4581, + "step": 11469 + }, + { + "epoch": 0.96, + "learning_rate": 8.518332965139931e-08, + "loss": 0.4398, + "step": 11470 + }, + { + "epoch": 0.96, + "learning_rate": 8.483073857666224e-08, + "loss": 0.4641, + "step": 11471 + }, + { + "epoch": 0.96, + "learning_rate": 8.447887563071466e-08, + "loss": 0.4707, + "step": 11472 + }, + { + "epoch": 0.96, + "learning_rate": 8.4127740839397e-08, + "loss": 0.4626, + "step": 11473 + }, + { + "epoch": 0.96, + "learning_rate": 8.377733422849532e-08, + "loss": 0.4563, + "step": 11474 + }, + { + "epoch": 0.96, + "learning_rate": 8.342765582374124e-08, + "loss": 0.4642, + "step": 11475 + }, + { + "epoch": 0.96, + "learning_rate": 8.307870565081422e-08, + "loss": 0.4385, + "step": 11476 + }, + { + "epoch": 0.96, + "learning_rate": 8.273048373533932e-08, + "loss": 0.4736, + "step": 11477 + }, + { + "epoch": 0.96, + "learning_rate": 8.23829901028883e-08, + "loss": 0.45, + "step": 11478 + }, + { + "epoch": 0.96, + "learning_rate": 8.203622477898077e-08, + "loss": 0.4565, + "step": 11479 + }, + { + "epoch": 0.96, + "learning_rate": 8.169018778908078e-08, + "loss": 0.4609, + "step": 11480 + }, + { + "epoch": 0.96, + "learning_rate": 8.134487915860024e-08, + "loss": 0.4565, + "step": 11481 + }, + { + "epoch": 0.96, + "learning_rate": 8.100029891289662e-08, + "loss": 0.4625, + "step": 11482 + }, + { + "epoch": 0.96, + "learning_rate": 8.065644707727415e-08, + "loss": 0.4632, + "step": 11483 + }, + { + "epoch": 0.96, + "learning_rate": 8.031332367698486e-08, + "loss": 0.4644, + "step": 11484 + }, + { + "epoch": 0.96, + "learning_rate": 7.997092873722633e-08, + "loss": 0.4493, + "step": 11485 + }, + { + "epoch": 0.96, + "learning_rate": 7.962926228314293e-08, + "loss": 0.4484, + "step": 11486 + }, + { + "epoch": 0.96, + "learning_rate": 7.928832433982348e-08, + "loss": 0.4623, + "step": 11487 + }, + { + "epoch": 0.96, + "learning_rate": 7.89481149323068e-08, + "loss": 0.4518, + "step": 11488 + }, + { + "epoch": 0.96, + "learning_rate": 7.860863408557629e-08, + "loss": 0.4552, + "step": 11489 + }, + { + "epoch": 0.96, + "learning_rate": 7.826988182456086e-08, + "loss": 0.4685, + "step": 11490 + }, + { + "epoch": 0.96, + "learning_rate": 7.793185817413728e-08, + "loss": 0.4479, + "step": 11491 + }, + { + "epoch": 0.96, + "learning_rate": 7.759456315912905e-08, + "loss": 0.478, + "step": 11492 + }, + { + "epoch": 0.96, + "learning_rate": 7.725799680430634e-08, + "loss": 0.4773, + "step": 11493 + }, + { + "epoch": 0.96, + "learning_rate": 7.692215913438383e-08, + "loss": 0.4452, + "step": 11494 + }, + { + "epoch": 0.96, + "learning_rate": 7.658705017402623e-08, + "loss": 0.4524, + "step": 11495 + }, + { + "epoch": 0.96, + "learning_rate": 7.625266994784053e-08, + "loss": 0.4712, + "step": 11496 + }, + { + "epoch": 0.96, + "learning_rate": 7.591901848038263e-08, + "loss": 0.4557, + "step": 11497 + }, + { + "epoch": 0.96, + "learning_rate": 7.558609579615406e-08, + "loss": 0.4618, + "step": 11498 + }, + { + "epoch": 0.96, + "learning_rate": 7.525390191960413e-08, + "loss": 0.4687, + "step": 11499 + }, + { + "epoch": 0.96, + "learning_rate": 7.49224368751278e-08, + "loss": 0.4418, + "step": 11500 + }, + { + "epoch": 0.96, + "learning_rate": 7.459170068706555e-08, + "loss": 0.4609, + "step": 11501 + }, + { + "epoch": 0.96, + "learning_rate": 7.42616933797069e-08, + "loss": 0.4724, + "step": 11502 + }, + { + "epoch": 0.96, + "learning_rate": 7.393241497728465e-08, + "loss": 0.4743, + "step": 11503 + }, + { + "epoch": 0.96, + "learning_rate": 7.360386550398058e-08, + "loss": 0.4792, + "step": 11504 + }, + { + "epoch": 0.96, + "learning_rate": 7.327604498392094e-08, + "loss": 0.4734, + "step": 11505 + }, + { + "epoch": 0.96, + "learning_rate": 7.294895344118091e-08, + "loss": 0.4442, + "step": 11506 + }, + { + "epoch": 0.96, + "learning_rate": 7.262259089977907e-08, + "loss": 0.4476, + "step": 11507 + }, + { + "epoch": 0.96, + "learning_rate": 7.229695738368403e-08, + "loss": 0.493, + "step": 11508 + }, + { + "epoch": 0.96, + "learning_rate": 7.197205291680887e-08, + "loss": 0.4545, + "step": 11509 + }, + { + "epoch": 0.96, + "learning_rate": 7.164787752301117e-08, + "loss": 0.4578, + "step": 11510 + }, + { + "epoch": 0.96, + "learning_rate": 7.132443122609856e-08, + "loss": 0.4767, + "step": 11511 + }, + { + "epoch": 0.96, + "learning_rate": 7.100171404982315e-08, + "loss": 0.4626, + "step": 11512 + }, + { + "epoch": 0.96, + "learning_rate": 7.067972601788376e-08, + "loss": 0.4525, + "step": 11513 + }, + { + "epoch": 0.96, + "learning_rate": 7.035846715392591e-08, + "loss": 0.4466, + "step": 11514 + }, + { + "epoch": 0.96, + "learning_rate": 7.003793748154186e-08, + "loss": 0.4565, + "step": 11515 + }, + { + "epoch": 0.96, + "learning_rate": 6.971813702427055e-08, + "loss": 0.4513, + "step": 11516 + }, + { + "epoch": 0.96, + "learning_rate": 6.939906580559542e-08, + "loss": 0.4462, + "step": 11517 + }, + { + "epoch": 0.96, + "learning_rate": 6.908072384894881e-08, + "loss": 0.4708, + "step": 11518 + }, + { + "epoch": 0.96, + "learning_rate": 6.876311117770762e-08, + "loss": 0.4715, + "step": 11519 + }, + { + "epoch": 0.96, + "learning_rate": 6.844622781519649e-08, + "loss": 0.4652, + "step": 11520 + }, + { + "epoch": 0.96, + "learning_rate": 6.813007378468684e-08, + "loss": 0.4617, + "step": 11521 + }, + { + "epoch": 0.96, + "learning_rate": 6.78146491093945e-08, + "loss": 0.4697, + "step": 11522 + }, + { + "epoch": 0.96, + "learning_rate": 6.74999538124832e-08, + "loss": 0.4436, + "step": 11523 + }, + { + "epoch": 0.96, + "learning_rate": 6.718598791706221e-08, + "loss": 0.4746, + "step": 11524 + }, + { + "epoch": 0.96, + "learning_rate": 6.687275144618865e-08, + "loss": 0.4787, + "step": 11525 + }, + { + "epoch": 0.96, + "learning_rate": 6.656024442286524e-08, + "loss": 0.4546, + "step": 11526 + }, + { + "epoch": 0.96, + "learning_rate": 6.62484668700425e-08, + "loss": 0.4944, + "step": 11527 + }, + { + "epoch": 0.96, + "learning_rate": 6.593741881061321e-08, + "loss": 0.4772, + "step": 11528 + }, + { + "epoch": 0.96, + "learning_rate": 6.562710026742248e-08, + "loss": 0.4597, + "step": 11529 + }, + { + "epoch": 0.96, + "learning_rate": 6.531751126325647e-08, + "loss": 0.462, + "step": 11530 + }, + { + "epoch": 0.96, + "learning_rate": 6.500865182085148e-08, + "loss": 0.4656, + "step": 11531 + }, + { + "epoch": 0.96, + "learning_rate": 6.470052196288712e-08, + "loss": 0.4457, + "step": 11532 + }, + { + "epoch": 0.96, + "learning_rate": 6.439312171199308e-08, + "loss": 0.462, + "step": 11533 + }, + { + "epoch": 0.96, + "learning_rate": 6.408645109074352e-08, + "loss": 0.4589, + "step": 11534 + }, + { + "epoch": 0.97, + "learning_rate": 6.37805101216571e-08, + "loss": 0.4681, + "step": 11535 + }, + { + "epoch": 0.97, + "learning_rate": 6.34752988272036e-08, + "loss": 0.4498, + "step": 11536 + }, + { + "epoch": 0.97, + "learning_rate": 6.317081722979402e-08, + "loss": 0.4609, + "step": 11537 + }, + { + "epoch": 0.97, + "learning_rate": 6.286706535179044e-08, + "loss": 0.4832, + "step": 11538 + }, + { + "epoch": 0.97, + "learning_rate": 6.256404321549725e-08, + "loss": 0.4635, + "step": 11539 + }, + { + "epoch": 0.97, + "learning_rate": 6.226175084316666e-08, + "loss": 0.4608, + "step": 11540 + }, + { + "epoch": 0.97, + "learning_rate": 6.19601882570009e-08, + "loss": 0.4557, + "step": 11541 + }, + { + "epoch": 0.97, + "learning_rate": 6.165935547914225e-08, + "loss": 0.458, + "step": 11542 + }, + { + "epoch": 0.97, + "learning_rate": 6.135925253168417e-08, + "loss": 0.4766, + "step": 11543 + }, + { + "epoch": 0.97, + "learning_rate": 6.105987943666459e-08, + "loss": 0.455, + "step": 11544 + }, + { + "epoch": 0.97, + "learning_rate": 6.07612362160681e-08, + "loss": 0.4563, + "step": 11545 + }, + { + "epoch": 0.97, + "learning_rate": 6.046332289182722e-08, + "loss": 0.4636, + "step": 11546 + }, + { + "epoch": 0.97, + "learning_rate": 6.016613948581662e-08, + "loss": 0.4598, + "step": 11547 + }, + { + "epoch": 0.97, + "learning_rate": 5.98696860198622e-08, + "loss": 0.4772, + "step": 11548 + }, + { + "epoch": 0.97, + "learning_rate": 5.957396251573433e-08, + "loss": 0.4755, + "step": 11549 + }, + { + "epoch": 0.97, + "learning_rate": 5.9278968995150066e-08, + "loss": 0.4486, + "step": 11550 + }, + { + "epoch": 0.97, + "learning_rate": 5.898470547977098e-08, + "loss": 0.4531, + "step": 11551 + }, + { + "epoch": 0.97, + "learning_rate": 5.8691171991207554e-08, + "loss": 0.4647, + "step": 11552 + }, + { + "epoch": 0.97, + "learning_rate": 5.8398368551014774e-08, + "loss": 0.4795, + "step": 11553 + }, + { + "epoch": 0.97, + "learning_rate": 5.810629518069655e-08, + "loss": 0.4659, + "step": 11554 + }, + { + "epoch": 0.97, + "learning_rate": 5.781495190170017e-08, + "loss": 0.4633, + "step": 11555 + }, + { + "epoch": 0.97, + "learning_rate": 5.7524338735420734e-08, + "loss": 0.4726, + "step": 11556 + }, + { + "epoch": 0.97, + "learning_rate": 5.7234455703200073e-08, + "loss": 0.4533, + "step": 11557 + }, + { + "epoch": 0.97, + "learning_rate": 5.69453028263256e-08, + "loss": 0.4576, + "step": 11558 + }, + { + "epoch": 0.97, + "learning_rate": 5.6656880126032544e-08, + "loss": 0.5139, + "step": 11559 + }, + { + "epoch": 0.97, + "learning_rate": 5.636918762350063e-08, + "loss": 0.4825, + "step": 11560 + }, + { + "epoch": 0.97, + "learning_rate": 5.60822253398563e-08, + "loss": 0.4501, + "step": 11561 + }, + { + "epoch": 0.97, + "learning_rate": 5.57959932961738e-08, + "loss": 0.4619, + "step": 11562 + }, + { + "epoch": 0.97, + "learning_rate": 5.551049151347299e-08, + "loss": 0.4715, + "step": 11563 + }, + { + "epoch": 0.97, + "learning_rate": 5.522572001271931e-08, + "loss": 0.4353, + "step": 11564 + }, + { + "epoch": 0.97, + "learning_rate": 5.494167881482493e-08, + "loss": 0.4583, + "step": 11565 + }, + { + "epoch": 0.97, + "learning_rate": 5.4658367940648716e-08, + "loss": 0.4748, + "step": 11566 + }, + { + "epoch": 0.97, + "learning_rate": 5.437578741099625e-08, + "loss": 0.4489, + "step": 11567 + }, + { + "epoch": 0.97, + "learning_rate": 5.409393724661982e-08, + "loss": 0.4516, + "step": 11568 + }, + { + "epoch": 0.97, + "learning_rate": 5.381281746821621e-08, + "loss": 0.4539, + "step": 11569 + }, + { + "epoch": 0.97, + "learning_rate": 5.353242809643e-08, + "loss": 0.4893, + "step": 11570 + }, + { + "epoch": 0.97, + "learning_rate": 5.3252769151851404e-08, + "loss": 0.4578, + "step": 11571 + }, + { + "epoch": 0.97, + "learning_rate": 5.297384065501843e-08, + "loss": 0.4645, + "step": 11572 + }, + { + "epoch": 0.97, + "learning_rate": 5.269564262641358e-08, + "loss": 0.45, + "step": 11573 + }, + { + "epoch": 0.97, + "learning_rate": 5.241817508646607e-08, + "loss": 0.4595, + "step": 11574 + }, + { + "epoch": 0.97, + "learning_rate": 5.214143805555294e-08, + "loss": 0.4711, + "step": 11575 + }, + { + "epoch": 0.97, + "learning_rate": 5.1865431553996814e-08, + "loss": 0.4387, + "step": 11576 + }, + { + "epoch": 0.97, + "learning_rate": 5.159015560206593e-08, + "loss": 0.4737, + "step": 11577 + }, + { + "epoch": 0.97, + "learning_rate": 5.131561021997522e-08, + "loss": 0.4596, + "step": 11578 + }, + { + "epoch": 0.97, + "learning_rate": 5.104179542788634e-08, + "loss": 0.4678, + "step": 11579 + }, + { + "epoch": 0.97, + "learning_rate": 5.0768711245907654e-08, + "loss": 0.458, + "step": 11580 + }, + { + "epoch": 0.97, + "learning_rate": 5.049635769409311e-08, + "loss": 0.4588, + "step": 11581 + }, + { + "epoch": 0.97, + "learning_rate": 5.022473479244228e-08, + "loss": 0.4621, + "step": 11582 + }, + { + "epoch": 0.97, + "learning_rate": 4.995384256090252e-08, + "loss": 0.4776, + "step": 11583 + }, + { + "epoch": 0.97, + "learning_rate": 4.9683681019367935e-08, + "loss": 0.5035, + "step": 11584 + }, + { + "epoch": 0.97, + "learning_rate": 4.941425018767709e-08, + "loss": 0.4653, + "step": 11585 + }, + { + "epoch": 0.97, + "learning_rate": 4.914555008561528e-08, + "loss": 0.4472, + "step": 11586 + }, + { + "epoch": 0.97, + "learning_rate": 4.8877580732916706e-08, + "loss": 0.4582, + "step": 11587 + }, + { + "epoch": 0.97, + "learning_rate": 4.861034214925786e-08, + "loss": 0.4557, + "step": 11588 + }, + { + "epoch": 0.97, + "learning_rate": 4.834383435426526e-08, + "loss": 0.4401, + "step": 11589 + }, + { + "epoch": 0.97, + "learning_rate": 4.807805736750881e-08, + "loss": 0.4679, + "step": 11590 + }, + { + "epoch": 0.97, + "learning_rate": 4.7813011208507344e-08, + "loss": 0.4689, + "step": 11591 + }, + { + "epoch": 0.97, + "learning_rate": 4.754869589672306e-08, + "loss": 0.4587, + "step": 11592 + }, + { + "epoch": 0.97, + "learning_rate": 4.728511145156822e-08, + "loss": 0.4385, + "step": 11593 + }, + { + "epoch": 0.97, + "learning_rate": 4.702225789239734e-08, + "loss": 0.4664, + "step": 11594 + }, + { + "epoch": 0.97, + "learning_rate": 4.676013523851497e-08, + "loss": 0.4549, + "step": 11595 + }, + { + "epoch": 0.97, + "learning_rate": 4.6498743509170165e-08, + "loss": 0.4589, + "step": 11596 + }, + { + "epoch": 0.97, + "learning_rate": 4.6238082723557566e-08, + "loss": 0.479, + "step": 11597 + }, + { + "epoch": 0.97, + "learning_rate": 4.597815290081853e-08, + "loss": 0.4623, + "step": 11598 + }, + { + "epoch": 0.97, + "learning_rate": 4.571895406004334e-08, + "loss": 0.4538, + "step": 11599 + }, + { + "epoch": 0.97, + "learning_rate": 4.546048622026455e-08, + "loss": 0.4619, + "step": 11600 + }, + { + "epoch": 0.97, + "learning_rate": 4.520274940046254e-08, + "loss": 0.4445, + "step": 11601 + }, + { + "epoch": 0.97, + "learning_rate": 4.494574361956661e-08, + "loss": 0.4731, + "step": 11602 + }, + { + "epoch": 0.97, + "learning_rate": 4.4689468896449426e-08, + "loss": 0.4714, + "step": 11603 + }, + { + "epoch": 0.97, + "learning_rate": 4.44339252499304e-08, + "loss": 0.4801, + "step": 11604 + }, + { + "epoch": 0.97, + "learning_rate": 4.4179112698774505e-08, + "loss": 0.4417, + "step": 11605 + }, + { + "epoch": 0.97, + "learning_rate": 4.392503126169678e-08, + "loss": 0.4605, + "step": 11606 + }, + { + "epoch": 0.97, + "learning_rate": 4.3671680957352304e-08, + "loss": 0.4555, + "step": 11607 + }, + { + "epoch": 0.97, + "learning_rate": 4.341906180434952e-08, + "loss": 0.4503, + "step": 11608 + }, + { + "epoch": 0.97, + "learning_rate": 4.3167173821238026e-08, + "loss": 0.4642, + "step": 11609 + }, + { + "epoch": 0.97, + "learning_rate": 4.291601702651527e-08, + "loss": 0.4799, + "step": 11610 + }, + { + "epoch": 0.97, + "learning_rate": 4.2665591438626474e-08, + "loss": 0.4446, + "step": 11611 + }, + { + "epoch": 0.97, + "learning_rate": 4.241589707596028e-08, + "loss": 0.4713, + "step": 11612 + }, + { + "epoch": 0.97, + "learning_rate": 4.216693395685423e-08, + "loss": 0.4628, + "step": 11613 + }, + { + "epoch": 0.97, + "learning_rate": 4.191870209959037e-08, + "loss": 0.4603, + "step": 11614 + }, + { + "epoch": 0.97, + "learning_rate": 4.167120152239856e-08, + "loss": 0.4876, + "step": 11615 + }, + { + "epoch": 0.97, + "learning_rate": 4.142443224345427e-08, + "loss": 0.4624, + "step": 11616 + }, + { + "epoch": 0.97, + "learning_rate": 4.1178394280878554e-08, + "loss": 0.4711, + "step": 11617 + }, + { + "epoch": 0.97, + "learning_rate": 4.093308765273918e-08, + "loss": 0.4748, + "step": 11618 + }, + { + "epoch": 0.97, + "learning_rate": 4.068851237705174e-08, + "loss": 0.4544, + "step": 11619 + }, + { + "epoch": 0.97, + "learning_rate": 4.044466847177519e-08, + "loss": 0.4416, + "step": 11620 + }, + { + "epoch": 0.97, + "learning_rate": 4.0201555954818563e-08, + "loss": 0.4559, + "step": 11621 + }, + { + "epoch": 0.97, + "learning_rate": 3.9959174844032e-08, + "loss": 0.4686, + "step": 11622 + }, + { + "epoch": 0.97, + "learning_rate": 3.971752515721794e-08, + "loss": 0.4665, + "step": 11623 + }, + { + "epoch": 0.97, + "learning_rate": 3.9476606912121073e-08, + "loss": 0.4777, + "step": 11624 + }, + { + "epoch": 0.97, + "learning_rate": 3.9236420126432806e-08, + "loss": 0.469, + "step": 11625 + }, + { + "epoch": 0.97, + "learning_rate": 3.899696481779236e-08, + "loss": 0.4729, + "step": 11626 + }, + { + "epoch": 0.97, + "learning_rate": 3.8758241003782336e-08, + "loss": 0.4659, + "step": 11627 + }, + { + "epoch": 0.97, + "learning_rate": 3.852024870193649e-08, + "loss": 0.4463, + "step": 11628 + }, + { + "epoch": 0.97, + "learning_rate": 3.8282987929730844e-08, + "loss": 0.4729, + "step": 11629 + }, + { + "epoch": 0.97, + "learning_rate": 3.804645870458812e-08, + "loss": 0.4636, + "step": 11630 + }, + { + "epoch": 0.97, + "learning_rate": 3.781066104387887e-08, + "loss": 0.4568, + "step": 11631 + }, + { + "epoch": 0.97, + "learning_rate": 3.757559496491925e-08, + "loss": 0.457, + "step": 11632 + }, + { + "epoch": 0.97, + "learning_rate": 3.7341260484969885e-08, + "loss": 0.4333, + "step": 11633 + }, + { + "epoch": 0.97, + "learning_rate": 3.710765762124147e-08, + "loss": 0.4622, + "step": 11634 + }, + { + "epoch": 0.97, + "learning_rate": 3.687478639088804e-08, + "loss": 0.4611, + "step": 11635 + }, + { + "epoch": 0.97, + "learning_rate": 3.6642646811010375e-08, + "loss": 0.4524, + "step": 11636 + }, + { + "epoch": 0.97, + "learning_rate": 3.6411238898655943e-08, + "loss": 0.4486, + "step": 11637 + }, + { + "epoch": 0.97, + "learning_rate": 3.618056267081782e-08, + "loss": 0.4561, + "step": 11638 + }, + { + "epoch": 0.97, + "learning_rate": 3.59506181444369e-08, + "loss": 0.465, + "step": 11639 + }, + { + "epoch": 0.97, + "learning_rate": 3.5721405336398565e-08, + "loss": 0.4843, + "step": 11640 + }, + { + "epoch": 0.97, + "learning_rate": 3.5492924263537124e-08, + "loss": 0.458, + "step": 11641 + }, + { + "epoch": 0.97, + "learning_rate": 3.526517494262804e-08, + "loss": 0.4535, + "step": 11642 + }, + { + "epoch": 0.97, + "learning_rate": 3.5038157390399067e-08, + "loss": 0.4647, + "step": 11643 + }, + { + "epoch": 0.97, + "learning_rate": 3.481187162352018e-08, + "loss": 0.4704, + "step": 11644 + }, + { + "epoch": 0.97, + "learning_rate": 3.4586317658609205e-08, + "loss": 0.4537, + "step": 11645 + }, + { + "epoch": 0.97, + "learning_rate": 3.436149551223067e-08, + "loss": 0.4813, + "step": 11646 + }, + { + "epoch": 0.97, + "learning_rate": 3.413740520089248e-08, + "loss": 0.4698, + "step": 11647 + }, + { + "epoch": 0.97, + "learning_rate": 3.3914046741052585e-08, + "loss": 0.4612, + "step": 11648 + }, + { + "epoch": 0.97, + "learning_rate": 3.369142014911231e-08, + "loss": 0.4437, + "step": 11649 + }, + { + "epoch": 0.97, + "learning_rate": 3.34695254414219e-08, + "loss": 0.4877, + "step": 11650 + }, + { + "epoch": 0.97, + "learning_rate": 3.3248362634275e-08, + "loss": 0.4612, + "step": 11651 + }, + { + "epoch": 0.97, + "learning_rate": 3.302793174391417e-08, + "loss": 0.4605, + "step": 11652 + }, + { + "epoch": 0.97, + "learning_rate": 3.280823278652645e-08, + "loss": 0.466, + "step": 11653 + }, + { + "epoch": 0.98, + "learning_rate": 3.2589265778244505e-08, + "loss": 0.4523, + "step": 11654 + }, + { + "epoch": 0.98, + "learning_rate": 3.237103073514991e-08, + "loss": 0.4371, + "step": 11655 + }, + { + "epoch": 0.98, + "learning_rate": 3.215352767326873e-08, + "loss": 0.4783, + "step": 11656 + }, + { + "epoch": 0.98, + "learning_rate": 3.193675660857265e-08, + "loss": 0.4543, + "step": 11657 + }, + { + "epoch": 0.98, + "learning_rate": 3.172071755698114e-08, + "loss": 0.471, + "step": 11658 + }, + { + "epoch": 0.98, + "learning_rate": 3.150541053435818e-08, + "loss": 0.4686, + "step": 11659 + }, + { + "epoch": 0.98, + "learning_rate": 3.129083555651668e-08, + "loss": 0.4683, + "step": 11660 + }, + { + "epoch": 0.98, + "learning_rate": 3.1076992639211824e-08, + "loss": 0.452, + "step": 11661 + }, + { + "epoch": 0.98, + "learning_rate": 3.086388179814992e-08, + "loss": 0.4614, + "step": 11662 + }, + { + "epoch": 0.98, + "learning_rate": 3.065150304897957e-08, + "loss": 0.469, + "step": 11663 + }, + { + "epoch": 0.98, + "learning_rate": 3.043985640729718e-08, + "loss": 0.4555, + "step": 11664 + }, + { + "epoch": 0.98, + "learning_rate": 3.022894188864589e-08, + "loss": 0.4715, + "step": 11665 + }, + { + "epoch": 0.98, + "learning_rate": 3.0018759508513297e-08, + "loss": 0.4541, + "step": 11666 + }, + { + "epoch": 0.98, + "learning_rate": 2.980930928233372e-08, + "loss": 0.4638, + "step": 11667 + }, + { + "epoch": 0.98, + "learning_rate": 2.9600591225490415e-08, + "loss": 0.4959, + "step": 11668 + }, + { + "epoch": 0.98, + "learning_rate": 2.93926053533089e-08, + "loss": 0.4738, + "step": 11669 + }, + { + "epoch": 0.98, + "learning_rate": 2.918535168106473e-08, + "loss": 0.4592, + "step": 11670 + }, + { + "epoch": 0.98, + "learning_rate": 2.897883022397574e-08, + "loss": 0.468, + "step": 11671 + }, + { + "epoch": 0.98, + "learning_rate": 2.8773040997208678e-08, + "loss": 0.4645, + "step": 11672 + }, + { + "epoch": 0.98, + "learning_rate": 2.8567984015877014e-08, + "loss": 0.4617, + "step": 11673 + }, + { + "epoch": 0.98, + "learning_rate": 2.8363659295037592e-08, + "loss": 0.4605, + "step": 11674 + }, + { + "epoch": 0.98, + "learning_rate": 2.8160066849696187e-08, + "loss": 0.4509, + "step": 11675 + }, + { + "epoch": 0.98, + "learning_rate": 2.7957206694803064e-08, + "loss": 0.4641, + "step": 11676 + }, + { + "epoch": 0.98, + "learning_rate": 2.77550788452563e-08, + "loss": 0.4295, + "step": 11677 + }, + { + "epoch": 0.98, + "learning_rate": 2.755368331589847e-08, + "loss": 0.4568, + "step": 11678 + }, + { + "epoch": 0.98, + "learning_rate": 2.7353020121518857e-08, + "loss": 0.4661, + "step": 11679 + }, + { + "epoch": 0.98, + "learning_rate": 2.715308927685567e-08, + "loss": 0.4596, + "step": 11680 + }, + { + "epoch": 0.98, + "learning_rate": 2.6953890796588276e-08, + "loss": 0.4582, + "step": 11681 + }, + { + "epoch": 0.98, + "learning_rate": 2.67554246953472e-08, + "loss": 0.4804, + "step": 11682 + }, + { + "epoch": 0.98, + "learning_rate": 2.655769098770522e-08, + "loss": 0.439, + "step": 11683 + }, + { + "epoch": 0.98, + "learning_rate": 2.636068968818295e-08, + "loss": 0.4728, + "step": 11684 + }, + { + "epoch": 0.98, + "learning_rate": 2.6164420811249925e-08, + "loss": 0.465, + "step": 11685 + }, + { + "epoch": 0.98, + "learning_rate": 2.5968884371315728e-08, + "loss": 0.4494, + "step": 11686 + }, + { + "epoch": 0.98, + "learning_rate": 2.5774080382743317e-08, + "loss": 0.4401, + "step": 11687 + }, + { + "epoch": 0.98, + "learning_rate": 2.5580008859835692e-08, + "loss": 0.4924, + "step": 11688 + }, + { + "epoch": 0.98, + "learning_rate": 2.538666981684479e-08, + "loss": 0.4549, + "step": 11689 + }, + { + "epoch": 0.98, + "learning_rate": 2.5194063267970358e-08, + "loss": 0.4631, + "step": 11690 + }, + { + "epoch": 0.98, + "learning_rate": 2.5002189227354425e-08, + "loss": 0.4868, + "step": 11691 + }, + { + "epoch": 0.98, + "learning_rate": 2.481104770908904e-08, + "loss": 0.4634, + "step": 11692 + }, + { + "epoch": 0.98, + "learning_rate": 2.4620638727210766e-08, + "loss": 0.4397, + "step": 11693 + }, + { + "epoch": 0.98, + "learning_rate": 2.4430962295701743e-08, + "loss": 0.4728, + "step": 11694 + }, + { + "epoch": 0.98, + "learning_rate": 2.4242018428491944e-08, + "loss": 0.4633, + "step": 11695 + }, + { + "epoch": 0.98, + "learning_rate": 2.405380713945582e-08, + "loss": 0.4515, + "step": 11696 + }, + { + "epoch": 0.98, + "learning_rate": 2.3866328442414545e-08, + "loss": 0.4745, + "step": 11697 + }, + { + "epoch": 0.98, + "learning_rate": 2.3679582351137098e-08, + "loss": 0.4766, + "step": 11698 + }, + { + "epoch": 0.98, + "learning_rate": 2.349356887933585e-08, + "loss": 0.4631, + "step": 11699 + }, + { + "epoch": 0.98, + "learning_rate": 2.330828804067098e-08, + "loss": 0.4695, + "step": 11700 + }, + { + "epoch": 0.98, + "learning_rate": 2.3123739848749382e-08, + "loss": 0.4665, + "step": 11701 + }, + { + "epoch": 0.98, + "learning_rate": 2.2939924317124663e-08, + "loss": 0.46, + "step": 11702 + }, + { + "epoch": 0.98, + "learning_rate": 2.275684145929269e-08, + "loss": 0.4722, + "step": 11703 + }, + { + "epoch": 0.98, + "learning_rate": 2.2574491288700485e-08, + "loss": 0.4655, + "step": 11704 + }, + { + "epoch": 0.98, + "learning_rate": 2.2392873818738447e-08, + "loss": 0.4503, + "step": 11705 + }, + { + "epoch": 0.98, + "learning_rate": 2.2211989062743688e-08, + "loss": 0.4614, + "step": 11706 + }, + { + "epoch": 0.98, + "learning_rate": 2.2031837034000024e-08, + "loss": 0.4405, + "step": 11707 + }, + { + "epoch": 0.98, + "learning_rate": 2.1852417745735764e-08, + "loss": 0.4648, + "step": 11708 + }, + { + "epoch": 0.98, + "learning_rate": 2.1673731211129255e-08, + "loss": 0.4791, + "step": 11709 + }, + { + "epoch": 0.98, + "learning_rate": 2.1495777443300005e-08, + "loss": 0.467, + "step": 11710 + }, + { + "epoch": 0.98, + "learning_rate": 2.131855645531644e-08, + "loss": 0.4428, + "step": 11711 + }, + { + "epoch": 0.98, + "learning_rate": 2.1142068260194827e-08, + "loss": 0.4568, + "step": 11712 + }, + { + "epoch": 0.98, + "learning_rate": 2.0966312870893678e-08, + "loss": 0.4525, + "step": 11713 + }, + { + "epoch": 0.98, + "learning_rate": 2.0791290300321564e-08, + "loss": 0.4744, + "step": 11714 + }, + { + "epoch": 0.98, + "learning_rate": 2.0617000561329315e-08, + "loss": 0.4685, + "step": 11715 + }, + { + "epoch": 0.98, + "learning_rate": 2.04434436667178e-08, + "loss": 0.4811, + "step": 11716 + }, + { + "epoch": 0.98, + "learning_rate": 2.027061962923127e-08, + "loss": 0.4609, + "step": 11717 + }, + { + "epoch": 0.98, + "learning_rate": 2.0098528461562906e-08, + "loss": 0.4709, + "step": 11718 + }, + { + "epoch": 0.98, + "learning_rate": 1.9927170176348155e-08, + "loss": 0.4597, + "step": 11719 + }, + { + "epoch": 0.98, + "learning_rate": 1.9756544786171393e-08, + "loss": 0.4651, + "step": 11720 + }, + { + "epoch": 0.98, + "learning_rate": 1.9586652303562603e-08, + "loss": 0.4463, + "step": 11721 + }, + { + "epoch": 0.98, + "learning_rate": 1.941749274099958e-08, + "loss": 0.4751, + "step": 11722 + }, + { + "epoch": 0.98, + "learning_rate": 1.924906611090349e-08, + "loss": 0.4505, + "step": 11723 + }, + { + "epoch": 0.98, + "learning_rate": 1.9081372425642232e-08, + "loss": 0.4564, + "step": 11724 + }, + { + "epoch": 0.98, + "learning_rate": 1.8914411697531498e-08, + "loss": 0.4579, + "step": 11725 + }, + { + "epoch": 0.98, + "learning_rate": 1.8748183938832597e-08, + "loss": 0.4747, + "step": 11726 + }, + { + "epoch": 0.98, + "learning_rate": 1.8582689161751323e-08, + "loss": 0.4637, + "step": 11727 + }, + { + "epoch": 0.98, + "learning_rate": 1.841792737844128e-08, + "loss": 0.4701, + "step": 11728 + }, + { + "epoch": 0.98, + "learning_rate": 1.8253898601002794e-08, + "loss": 0.4685, + "step": 11729 + }, + { + "epoch": 0.98, + "learning_rate": 1.8090602841479566e-08, + "loss": 0.4487, + "step": 11730 + }, + { + "epoch": 0.98, + "learning_rate": 1.792804011186533e-08, + "loss": 0.4494, + "step": 11731 + }, + { + "epoch": 0.98, + "learning_rate": 1.7766210424097207e-08, + "loss": 0.4415, + "step": 11732 + }, + { + "epoch": 0.98, + "learning_rate": 1.7605113790059024e-08, + "loss": 0.4635, + "step": 11733 + }, + { + "epoch": 0.98, + "learning_rate": 1.744475022158243e-08, + "loss": 0.459, + "step": 11734 + }, + { + "epoch": 0.98, + "learning_rate": 1.7285119730442446e-08, + "loss": 0.4558, + "step": 11735 + }, + { + "epoch": 0.98, + "learning_rate": 1.712622232836192e-08, + "loss": 0.4716, + "step": 11736 + }, + { + "epoch": 0.98, + "learning_rate": 1.6968058027009292e-08, + "loss": 0.4586, + "step": 11737 + }, + { + "epoch": 0.98, + "learning_rate": 1.6810626837999722e-08, + "loss": 0.4835, + "step": 11738 + }, + { + "epoch": 0.98, + "learning_rate": 1.6653928772895067e-08, + "loss": 0.4461, + "step": 11739 + }, + { + "epoch": 0.98, + "learning_rate": 1.649796384320168e-08, + "loss": 0.4419, + "step": 11740 + }, + { + "epoch": 0.98, + "learning_rate": 1.6342732060373733e-08, + "loss": 0.4625, + "step": 11741 + }, + { + "epoch": 0.98, + "learning_rate": 1.6188233435809887e-08, + "loss": 0.4593, + "step": 11742 + }, + { + "epoch": 0.98, + "learning_rate": 1.6034467980857727e-08, + "loss": 0.4429, + "step": 11743 + }, + { + "epoch": 0.98, + "learning_rate": 1.5881435706806002e-08, + "loss": 0.4512, + "step": 11744 + }, + { + "epoch": 0.98, + "learning_rate": 1.5729136624895723e-08, + "loss": 0.4645, + "step": 11745 + }, + { + "epoch": 0.98, + "learning_rate": 1.5577570746309057e-08, + "loss": 0.4584, + "step": 11746 + }, + { + "epoch": 0.98, + "learning_rate": 1.5426738082178206e-08, + "loss": 0.4629, + "step": 11747 + }, + { + "epoch": 0.98, + "learning_rate": 1.5276638643578756e-08, + "loss": 0.4594, + "step": 11748 + }, + { + "epoch": 0.98, + "learning_rate": 1.5127272441533004e-08, + "loss": 0.4414, + "step": 11749 + }, + { + "epoch": 0.98, + "learning_rate": 1.497863948700995e-08, + "loss": 0.4754, + "step": 11750 + }, + { + "epoch": 0.98, + "learning_rate": 1.4830739790925308e-08, + "loss": 0.4389, + "step": 11751 + }, + { + "epoch": 0.98, + "learning_rate": 1.4683573364138171e-08, + "loss": 0.4845, + "step": 11752 + }, + { + "epoch": 0.98, + "learning_rate": 1.4537140217458778e-08, + "loss": 0.4612, + "step": 11753 + }, + { + "epoch": 0.98, + "learning_rate": 1.439144036163964e-08, + "loss": 0.4562, + "step": 11754 + }, + { + "epoch": 0.98, + "learning_rate": 1.4246473807378869e-08, + "loss": 0.4516, + "step": 11755 + }, + { + "epoch": 0.98, + "learning_rate": 1.41022405653235e-08, + "loss": 0.4753, + "step": 11756 + }, + { + "epoch": 0.98, + "learning_rate": 1.395874064606506e-08, + "loss": 0.4545, + "step": 11757 + }, + { + "epoch": 0.98, + "learning_rate": 1.381597406014179e-08, + "loss": 0.4614, + "step": 11758 + }, + { + "epoch": 0.98, + "learning_rate": 1.3673940818037523e-08, + "loss": 0.4941, + "step": 11759 + }, + { + "epoch": 0.98, + "learning_rate": 1.3532640930182806e-08, + "loss": 0.4754, + "step": 11760 + }, + { + "epoch": 0.98, + "learning_rate": 1.339207440695378e-08, + "loss": 0.4795, + "step": 11761 + }, + { + "epoch": 0.98, + "learning_rate": 1.3252241258673305e-08, + "loss": 0.4604, + "step": 11762 + }, + { + "epoch": 0.98, + "learning_rate": 1.3113141495610937e-08, + "loss": 0.4656, + "step": 11763 + }, + { + "epoch": 0.98, + "learning_rate": 1.2974775127980732e-08, + "loss": 0.4797, + "step": 11764 + }, + { + "epoch": 0.98, + "learning_rate": 1.283714216594345e-08, + "loss": 0.4449, + "step": 11765 + }, + { + "epoch": 0.98, + "learning_rate": 1.2700242619606562e-08, + "loss": 0.4625, + "step": 11766 + }, + { + "epoch": 0.98, + "learning_rate": 1.2564076499024247e-08, + "loss": 0.4635, + "step": 11767 + }, + { + "epoch": 0.98, + "learning_rate": 1.2428643814195174e-08, + "loss": 0.4668, + "step": 11768 + }, + { + "epoch": 0.98, + "learning_rate": 1.229394457506472e-08, + "loss": 0.4709, + "step": 11769 + }, + { + "epoch": 0.98, + "learning_rate": 1.2159978791524973e-08, + "loss": 0.4454, + "step": 11770 + }, + { + "epoch": 0.98, + "learning_rate": 1.202674647341362e-08, + "loss": 0.474, + "step": 11771 + }, + { + "epoch": 0.98, + "learning_rate": 1.1894247630516165e-08, + "loss": 0.4544, + "step": 11772 + }, + { + "epoch": 0.98, + "learning_rate": 1.1762482272560382e-08, + "loss": 0.4765, + "step": 11773 + }, + { + "epoch": 0.99, + "learning_rate": 1.1631450409224088e-08, + "loss": 0.4647, + "step": 11774 + }, + { + "epoch": 0.99, + "learning_rate": 1.1501152050128472e-08, + "loss": 0.4871, + "step": 11775 + }, + { + "epoch": 0.99, + "learning_rate": 1.1371587204843659e-08, + "loss": 0.4494, + "step": 11776 + }, + { + "epoch": 0.99, + "learning_rate": 1.124275588288426e-08, + "loss": 0.4947, + "step": 11777 + }, + { + "epoch": 0.99, + "learning_rate": 1.1114658093709373e-08, + "loss": 0.4682, + "step": 11778 + }, + { + "epoch": 0.99, + "learning_rate": 1.0987293846728141e-08, + "loss": 0.4486, + "step": 11779 + }, + { + "epoch": 0.99, + "learning_rate": 1.0860663151291973e-08, + "loss": 0.4312, + "step": 11780 + }, + { + "epoch": 0.99, + "learning_rate": 1.0734766016700093e-08, + "loss": 0.4613, + "step": 11781 + }, + { + "epoch": 0.99, + "learning_rate": 1.0609602452199553e-08, + "loss": 0.4764, + "step": 11782 + }, + { + "epoch": 0.99, + "learning_rate": 1.0485172466980776e-08, + "loss": 0.4795, + "step": 11783 + }, + { + "epoch": 0.99, + "learning_rate": 1.0361476070180899e-08, + "loss": 0.4585, + "step": 11784 + }, + { + "epoch": 0.99, + "learning_rate": 1.0238513270884876e-08, + "loss": 0.459, + "step": 11785 + }, + { + "epoch": 0.99, + "learning_rate": 1.0116284078121042e-08, + "loss": 0.4561, + "step": 11786 + }, + { + "epoch": 0.99, + "learning_rate": 9.994788500866659e-09, + "loss": 0.4608, + "step": 11787 + }, + { + "epoch": 0.99, + "learning_rate": 9.87402654804348e-09, + "loss": 0.4812, + "step": 11788 + }, + { + "epoch": 0.99, + "learning_rate": 9.753998228519967e-09, + "loss": 0.4629, + "step": 11789 + }, + { + "epoch": 0.99, + "learning_rate": 9.634703551110181e-09, + "loss": 0.4569, + "step": 11790 + }, + { + "epoch": 0.99, + "learning_rate": 9.516142524574889e-09, + "loss": 0.4736, + "step": 11791 + }, + { + "epoch": 0.99, + "learning_rate": 9.398315157619354e-09, + "loss": 0.4595, + "step": 11792 + }, + { + "epoch": 0.99, + "learning_rate": 9.281221458898871e-09, + "loss": 0.456, + "step": 11793 + }, + { + "epoch": 0.99, + "learning_rate": 9.164861437009897e-09, + "loss": 0.4692, + "step": 11794 + }, + { + "epoch": 0.99, + "learning_rate": 9.049235100500042e-09, + "loss": 0.4546, + "step": 11795 + }, + { + "epoch": 0.99, + "learning_rate": 8.93434245785696e-09, + "loss": 0.4422, + "step": 11796 + }, + { + "epoch": 0.99, + "learning_rate": 8.820183517521675e-09, + "loss": 0.4557, + "step": 11797 + }, + { + "epoch": 0.99, + "learning_rate": 8.706758287874151e-09, + "loss": 0.4557, + "step": 11798 + }, + { + "epoch": 0.99, + "learning_rate": 8.594066777246613e-09, + "loss": 0.4656, + "step": 11799 + }, + { + "epoch": 0.99, + "learning_rate": 8.482108993912441e-09, + "loss": 0.501, + "step": 11800 + }, + { + "epoch": 0.99, + "learning_rate": 8.370884946095059e-09, + "loss": 0.4627, + "step": 11801 + }, + { + "epoch": 0.99, + "learning_rate": 8.260394641961267e-09, + "loss": 0.4597, + "step": 11802 + }, + { + "epoch": 0.99, + "learning_rate": 8.150638089624574e-09, + "loss": 0.4844, + "step": 11803 + }, + { + "epoch": 0.99, + "learning_rate": 8.04161529714631e-09, + "loss": 0.4403, + "step": 11804 + }, + { + "epoch": 0.99, + "learning_rate": 7.933326272532294e-09, + "loss": 0.4704, + "step": 11805 + }, + { + "epoch": 0.99, + "learning_rate": 7.825771023735051e-09, + "loss": 0.4568, + "step": 11806 + }, + { + "epoch": 0.99, + "learning_rate": 7.7189495586516e-09, + "loss": 0.4704, + "step": 11807 + }, + { + "epoch": 0.99, + "learning_rate": 7.612861885128997e-09, + "loss": 0.4585, + "step": 11808 + }, + { + "epoch": 0.99, + "learning_rate": 7.507508010955455e-09, + "loss": 0.4507, + "step": 11809 + }, + { + "epoch": 0.99, + "learning_rate": 7.40288794386812e-09, + "loss": 0.4675, + "step": 11810 + }, + { + "epoch": 0.99, + "learning_rate": 7.299001691550844e-09, + "loss": 0.4525, + "step": 11811 + }, + { + "epoch": 0.99, + "learning_rate": 7.195849261631971e-09, + "loss": 0.4645, + "step": 11812 + }, + { + "epoch": 0.99, + "learning_rate": 7.093430661686551e-09, + "loss": 0.4757, + "step": 11813 + }, + { + "epoch": 0.99, + "learning_rate": 6.991745899236346e-09, + "loss": 0.4585, + "step": 11814 + }, + { + "epoch": 0.99, + "learning_rate": 6.890794981748717e-09, + "loss": 0.4569, + "step": 11815 + }, + { + "epoch": 0.99, + "learning_rate": 6.79057791663551e-09, + "loss": 0.4858, + "step": 11816 + }, + { + "epoch": 0.99, + "learning_rate": 6.691094711258617e-09, + "loss": 0.4416, + "step": 11817 + }, + { + "epoch": 0.99, + "learning_rate": 6.5923453729221935e-09, + "loss": 0.4474, + "step": 11818 + }, + { + "epoch": 0.99, + "learning_rate": 6.4943299088771065e-09, + "loss": 0.4492, + "step": 11819 + }, + { + "epoch": 0.99, + "learning_rate": 6.397048326323152e-09, + "loss": 0.4803, + "step": 11820 + }, + { + "epoch": 0.99, + "learning_rate": 6.300500632403505e-09, + "loss": 0.458, + "step": 11821 + }, + { + "epoch": 0.99, + "learning_rate": 6.204686834208051e-09, + "loss": 0.4613, + "step": 11822 + }, + { + "epoch": 0.99, + "learning_rate": 6.1096069387733825e-09, + "loss": 0.4649, + "step": 11823 + }, + { + "epoch": 0.99, + "learning_rate": 6.015260953080582e-09, + "loss": 0.4637, + "step": 11824 + }, + { + "epoch": 0.99, + "learning_rate": 5.921648884059661e-09, + "loss": 0.4679, + "step": 11825 + }, + { + "epoch": 0.99, + "learning_rate": 5.828770738584011e-09, + "loss": 0.4586, + "step": 11826 + }, + { + "epoch": 0.99, + "learning_rate": 5.736626523474842e-09, + "loss": 0.4494, + "step": 11827 + }, + { + "epoch": 0.99, + "learning_rate": 5.645216245497853e-09, + "loss": 0.446, + "step": 11828 + }, + { + "epoch": 0.99, + "learning_rate": 5.554539911367673e-09, + "loss": 0.4763, + "step": 11829 + }, + { + "epoch": 0.99, + "learning_rate": 5.4645975277412004e-09, + "loss": 0.4616, + "step": 11830 + }, + { + "epoch": 0.99, + "learning_rate": 5.37538910122426e-09, + "loss": 0.4542, + "step": 11831 + }, + { + "epoch": 0.99, + "learning_rate": 5.2869146383682794e-09, + "loss": 0.4753, + "step": 11832 + }, + { + "epoch": 0.99, + "learning_rate": 5.199174145670283e-09, + "loss": 0.488, + "step": 11833 + }, + { + "epoch": 0.99, + "learning_rate": 5.112167629572895e-09, + "loss": 0.4638, + "step": 11834 + }, + { + "epoch": 0.99, + "learning_rate": 5.02589509646656e-09, + "loss": 0.479, + "step": 11835 + }, + { + "epoch": 0.99, + "learning_rate": 4.94035655268621e-09, + "loss": 0.4608, + "step": 11836 + }, + { + "epoch": 0.99, + "learning_rate": 4.855552004513486e-09, + "loss": 0.4786, + "step": 11837 + }, + { + "epoch": 0.99, + "learning_rate": 4.7714814581756305e-09, + "loss": 0.4579, + "step": 11838 + }, + { + "epoch": 0.99, + "learning_rate": 4.6881449198477035e-09, + "loss": 0.4622, + "step": 11839 + }, + { + "epoch": 0.99, + "learning_rate": 4.605542395648144e-09, + "loss": 0.4534, + "step": 11840 + }, + { + "epoch": 0.99, + "learning_rate": 4.52367389164432e-09, + "loss": 0.469, + "step": 11841 + }, + { + "epoch": 0.99, + "learning_rate": 4.44253941384698e-09, + "loss": 0.4853, + "step": 11842 + }, + { + "epoch": 0.99, + "learning_rate": 4.362138968214691e-09, + "loss": 0.4447, + "step": 11843 + }, + { + "epoch": 0.99, + "learning_rate": 4.282472560651618e-09, + "loss": 0.4573, + "step": 11844 + }, + { + "epoch": 0.99, + "learning_rate": 4.203540197009748e-09, + "loss": 0.461, + "step": 11845 + }, + { + "epoch": 0.99, + "learning_rate": 4.125341883083334e-09, + "loss": 0.4492, + "step": 11846 + }, + { + "epoch": 0.99, + "learning_rate": 4.047877624615559e-09, + "loss": 0.4663, + "step": 11847 + }, + { + "epoch": 0.99, + "learning_rate": 3.971147427296318e-09, + "loss": 0.455, + "step": 11848 + }, + { + "epoch": 0.99, + "learning_rate": 3.895151296758881e-09, + "loss": 0.4424, + "step": 11849 + }, + { + "epoch": 0.99, + "learning_rate": 3.81988923858434e-09, + "loss": 0.4672, + "step": 11850 + }, + { + "epoch": 0.99, + "learning_rate": 3.745361258300495e-09, + "loss": 0.4656, + "step": 11851 + }, + { + "epoch": 0.99, + "learning_rate": 3.6715673613796353e-09, + "loss": 0.4624, + "step": 11852 + }, + { + "epoch": 0.99, + "learning_rate": 3.59850755324076e-09, + "loss": 0.4421, + "step": 11853 + }, + { + "epoch": 0.99, + "learning_rate": 3.5261818392484657e-09, + "loss": 0.4816, + "step": 11854 + }, + { + "epoch": 0.99, + "learning_rate": 3.454590224716281e-09, + "loss": 0.4464, + "step": 11855 + }, + { + "epoch": 0.99, + "learning_rate": 3.383732714900001e-09, + "loss": 0.45, + "step": 11856 + }, + { + "epoch": 0.99, + "learning_rate": 3.313609315003241e-09, + "loss": 0.4448, + "step": 11857 + }, + { + "epoch": 0.99, + "learning_rate": 3.244220030175216e-09, + "loss": 0.4695, + "step": 11858 + }, + { + "epoch": 0.99, + "learning_rate": 3.175564865512959e-09, + "loss": 0.4581, + "step": 11859 + }, + { + "epoch": 0.99, + "learning_rate": 3.107643826055773e-09, + "loss": 0.4873, + "step": 11860 + }, + { + "epoch": 0.99, + "learning_rate": 3.04045691679411e-09, + "loss": 0.4794, + "step": 11861 + }, + { + "epoch": 0.99, + "learning_rate": 2.9740041426606915e-09, + "loss": 0.4446, + "step": 11862 + }, + { + "epoch": 0.99, + "learning_rate": 2.908285508536057e-09, + "loss": 0.4744, + "step": 11863 + }, + { + "epoch": 0.99, + "learning_rate": 2.843301019245237e-09, + "loss": 0.442, + "step": 11864 + }, + { + "epoch": 0.99, + "learning_rate": 2.7790506795610793e-09, + "loss": 0.46, + "step": 11865 + }, + { + "epoch": 0.99, + "learning_rate": 2.7155344942020324e-09, + "loss": 0.4449, + "step": 11866 + }, + { + "epoch": 0.99, + "learning_rate": 2.6527524678321424e-09, + "loss": 0.4606, + "step": 11867 + }, + { + "epoch": 0.99, + "learning_rate": 2.5907046050632767e-09, + "loss": 0.4512, + "step": 11868 + }, + { + "epoch": 0.99, + "learning_rate": 2.5293909104495696e-09, + "loss": 0.467, + "step": 11869 + }, + { + "epoch": 0.99, + "learning_rate": 2.4688113884940855e-09, + "loss": 0.4508, + "step": 11870 + }, + { + "epoch": 0.99, + "learning_rate": 2.4089660436477093e-09, + "loss": 0.4537, + "step": 11871 + }, + { + "epoch": 0.99, + "learning_rate": 2.3498548803024825e-09, + "loss": 0.4676, + "step": 11872 + }, + { + "epoch": 0.99, + "learning_rate": 2.2914779028015976e-09, + "loss": 0.472, + "step": 11873 + }, + { + "epoch": 0.99, + "learning_rate": 2.233835115430516e-09, + "loss": 0.4748, + "step": 11874 + }, + { + "epoch": 0.99, + "learning_rate": 2.1769265224225176e-09, + "loss": 0.4612, + "step": 11875 + }, + { + "epoch": 0.99, + "learning_rate": 2.1207521279575925e-09, + "loss": 0.4694, + "step": 11876 + }, + { + "epoch": 0.99, + "learning_rate": 2.065311936160219e-09, + "loss": 0.4486, + "step": 11877 + }, + { + "epoch": 0.99, + "learning_rate": 2.0106059511015853e-09, + "loss": 0.4707, + "step": 11878 + }, + { + "epoch": 0.99, + "learning_rate": 1.9566341767984774e-09, + "loss": 0.4409, + "step": 11879 + }, + { + "epoch": 0.99, + "learning_rate": 1.903396617216613e-09, + "loss": 0.4728, + "step": 11880 + }, + { + "epoch": 0.99, + "learning_rate": 1.8508932762628662e-09, + "loss": 0.4348, + "step": 11881 + }, + { + "epoch": 0.99, + "learning_rate": 1.7991241577952624e-09, + "loss": 0.4634, + "step": 11882 + }, + { + "epoch": 0.99, + "learning_rate": 1.7480892656129845e-09, + "loss": 0.4532, + "step": 11883 + }, + { + "epoch": 0.99, + "learning_rate": 1.697788603466366e-09, + "loss": 0.4515, + "step": 11884 + }, + { + "epoch": 0.99, + "learning_rate": 1.6482221750468984e-09, + "loss": 0.4701, + "step": 11885 + }, + { + "epoch": 0.99, + "learning_rate": 1.5993899839972239e-09, + "loss": 0.4458, + "step": 11886 + }, + { + "epoch": 0.99, + "learning_rate": 1.5512920339011416e-09, + "loss": 0.4809, + "step": 11887 + }, + { + "epoch": 0.99, + "learning_rate": 1.503928328291382e-09, + "loss": 0.4552, + "step": 11888 + }, + { + "epoch": 0.99, + "learning_rate": 1.4572988706462732e-09, + "loss": 0.4768, + "step": 11889 + }, + { + "epoch": 0.99, + "learning_rate": 1.4114036643897434e-09, + "loss": 0.4614, + "step": 11890 + }, + { + "epoch": 0.99, + "learning_rate": 1.3662427128924294e-09, + "loss": 0.4842, + "step": 11891 + }, + { + "epoch": 0.99, + "learning_rate": 1.3218160194716778e-09, + "loss": 0.4597, + "step": 11892 + }, + { + "epoch": 1.0, + "learning_rate": 1.2781235873882136e-09, + "loss": 0.456, + "step": 11893 + }, + { + "epoch": 1.0, + "learning_rate": 1.2351654198528018e-09, + "loss": 0.4666, + "step": 11894 + }, + { + "epoch": 1.0, + "learning_rate": 1.1929415200173656e-09, + "loss": 0.4657, + "step": 11895 + }, + { + "epoch": 1.0, + "learning_rate": 1.151451890984978e-09, + "loss": 0.4713, + "step": 11896 + }, + { + "epoch": 1.0, + "learning_rate": 1.1106965358009814e-09, + "loss": 0.4443, + "step": 11897 + }, + { + "epoch": 1.0, + "learning_rate": 1.0706754574596468e-09, + "loss": 0.4491, + "step": 11898 + }, + { + "epoch": 1.0, + "learning_rate": 1.0313886588986244e-09, + "loss": 0.4913, + "step": 11899 + }, + { + "epoch": 1.0, + "learning_rate": 9.928361430044941e-10, + "loss": 0.4457, + "step": 11900 + }, + { + "epoch": 1.0, + "learning_rate": 9.550179126072146e-10, + "loss": 0.4564, + "step": 11901 + }, + { + "epoch": 1.0, + "learning_rate": 9.179339704834533e-10, + "loss": 0.4475, + "step": 11902 + }, + { + "epoch": 1.0, + "learning_rate": 8.815843193576979e-10, + "loss": 0.4701, + "step": 11903 + }, + { + "epoch": 1.0, + "learning_rate": 8.459689618989241e-10, + "loss": 0.4604, + "step": 11904 + }, + { + "epoch": 1.0, + "learning_rate": 8.110879007228178e-10, + "loss": 0.4639, + "step": 11905 + }, + { + "epoch": 1.0, + "learning_rate": 7.769411383906633e-10, + "loss": 0.4658, + "step": 11906 + }, + { + "epoch": 1.0, + "learning_rate": 7.435286774104545e-10, + "loss": 0.4539, + "step": 11907 + }, + { + "epoch": 1.0, + "learning_rate": 7.108505202346739e-10, + "loss": 0.4592, + "step": 11908 + }, + { + "epoch": 1.0, + "learning_rate": 6.789066692636237e-10, + "loss": 0.442, + "step": 11909 + }, + { + "epoch": 1.0, + "learning_rate": 6.476971268443156e-10, + "loss": 0.4526, + "step": 11910 + }, + { + "epoch": 1.0, + "learning_rate": 6.172218952671394e-10, + "loss": 0.4614, + "step": 11911 + }, + { + "epoch": 1.0, + "learning_rate": 5.874809767703049e-10, + "loss": 0.449, + "step": 11912 + }, + { + "epoch": 1.0, + "learning_rate": 5.58474373538731e-10, + "loss": 0.4503, + "step": 11913 + }, + { + "epoch": 1.0, + "learning_rate": 5.302020877018255e-10, + "loss": 0.4608, + "step": 11914 + }, + { + "epoch": 1.0, + "learning_rate": 5.026641213357054e-10, + "loss": 0.4489, + "step": 11915 + }, + { + "epoch": 1.0, + "learning_rate": 4.758604764631969e-10, + "loss": 0.4484, + "step": 11916 + }, + { + "epoch": 1.0, + "learning_rate": 4.4979115505272566e-10, + "loss": 0.4652, + "step": 11917 + }, + { + "epoch": 1.0, + "learning_rate": 4.2445615901831607e-10, + "loss": 0.4656, + "step": 11918 + }, + { + "epoch": 1.0, + "learning_rate": 3.998554902195917e-10, + "loss": 0.4683, + "step": 11919 + }, + { + "epoch": 1.0, + "learning_rate": 3.7598915046510587e-10, + "loss": 0.4503, + "step": 11920 + }, + { + "epoch": 1.0, + "learning_rate": 3.528571415056803e-10, + "loss": 0.489, + "step": 11921 + }, + { + "epoch": 1.0, + "learning_rate": 3.304594650410664e-10, + "loss": 0.4592, + "step": 11922 + }, + { + "epoch": 1.0, + "learning_rate": 3.0879612271550454e-10, + "loss": 0.4751, + "step": 11923 + }, + { + "epoch": 1.0, + "learning_rate": 2.878671161199442e-10, + "loss": 0.466, + "step": 11924 + }, + { + "epoch": 1.0, + "learning_rate": 2.676724467920444e-10, + "loss": 0.45, + "step": 11925 + }, + { + "epoch": 1.0, + "learning_rate": 2.482121162139528e-10, + "loss": 0.4598, + "step": 11926 + }, + { + "epoch": 1.0, + "learning_rate": 2.2948612581452646e-10, + "loss": 0.505, + "step": 11927 + }, + { + "epoch": 1.0, + "learning_rate": 2.114944769704419e-10, + "loss": 0.4551, + "step": 11928 + }, + { + "epoch": 1.0, + "learning_rate": 1.9423717100175432e-10, + "loss": 0.4501, + "step": 11929 + }, + { + "epoch": 1.0, + "learning_rate": 1.777142091752282e-10, + "loss": 0.4932, + "step": 11930 + }, + { + "epoch": 1.0, + "learning_rate": 1.619255927054475e-10, + "loss": 0.455, + "step": 11931 + }, + { + "epoch": 1.0, + "learning_rate": 1.468713227514851e-10, + "loss": 0.4599, + "step": 11932 + }, + { + "epoch": 1.0, + "learning_rate": 1.3255140041912306e-10, + "loss": 0.4578, + "step": 11933 + }, + { + "epoch": 1.0, + "learning_rate": 1.1896582675974266e-10, + "loss": 0.4442, + "step": 11934 + }, + { + "epoch": 1.0, + "learning_rate": 1.0611460277032415e-10, + "loss": 0.464, + "step": 11935 + }, + { + "epoch": 1.0, + "learning_rate": 9.399772939455709e-11, + "loss": 0.4523, + "step": 11936 + }, + { + "epoch": 1.0, + "learning_rate": 8.261520752395059e-11, + "loss": 0.4593, + "step": 11937 + }, + { + "epoch": 1.0, + "learning_rate": 7.19670379922821e-11, + "loss": 0.4764, + "step": 11938 + }, + { + "epoch": 1.0, + "learning_rate": 6.205322158336913e-11, + "loss": 0.4706, + "step": 11939 + }, + { + "epoch": 1.0, + "learning_rate": 5.287375902440772e-11, + "loss": 0.4774, + "step": 11940 + }, + { + "epoch": 1.0, + "learning_rate": 4.442865098930327e-11, + "loss": 0.4738, + "step": 11941 + }, + { + "epoch": 1.0, + "learning_rate": 3.671789809867043e-11, + "loss": 0.4651, + "step": 11942 + }, + { + "epoch": 1.0, + "learning_rate": 2.974150091761274e-11, + "loss": 0.474, + "step": 11943 + }, + { + "epoch": 1.0, + "learning_rate": 2.349945996016345e-11, + "loss": 0.4763, + "step": 11944 + }, + { + "epoch": 1.0, + "learning_rate": 1.7991775683734448e-11, + "loss": 0.457, + "step": 11945 + }, + { + "epoch": 1.0, + "learning_rate": 1.3218448492446912e-11, + "loss": 0.466, + "step": 11946 + }, + { + "epoch": 1.0, + "learning_rate": 9.179478738241542e-12, + "loss": 0.45, + "step": 11947 + }, + { + "epoch": 1.0, + "learning_rate": 5.874866715327443e-12, + "loss": 0.4781, + "step": 11948 + }, + { + "epoch": 1.0, + "learning_rate": 3.3046126690639002e-12, + "loss": 0.4753, + "step": 11949 + }, + { + "epoch": 1.0, + "learning_rate": 1.4687167870786056e-12, + "loss": 0.4425, + "step": 11950 + }, + { + "epoch": 1.0, + "learning_rate": 3.6717920370854533e-13, + "loss": 0.4705, + "step": 11951 + }, + { + "epoch": 1.0, + "learning_rate": 0.0, + "loss": 0.4708, + "step": 11952 + }, + { + "epoch": 1.0, + "step": 11952, + "total_flos": 0.0, + "train_loss": 0.017490314920663514, + "train_runtime": 2743.4428, + "train_samples_per_second": 1115.374, + "train_steps_per_second": 4.357 + } + ], + "logging_steps": 1.0, + "max_steps": 11952, + "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..d206ea4893c85cf612a9ca5e15094655e3a3a453 --- /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/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..b6c2935653809218cfd3df65ea542edc40ad4b72 --- /dev/null +++ b/vision_tower/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a21d59235b9ff110c123480bb55cb2893ebab59faf902cbc648113251d9d29e6 +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 + } +}