diff --git a/.gitattributes b/.gitattributes index a6344aac8c09253b3b630fb776ae94478aa0275b..e2e76dcd2dd1b68dd3fb681118731aad09700b0e 100644 --- a/.gitattributes +++ b/.gitattributes @@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text *.zip filter=lfs diff=lfs merge=lfs -text *.zst filter=lfs diff=lfs merge=lfs -text *tfevents* filter=lfs diff=lfs merge=lfs -text +rag_truth_hal_detection_model/checkpoint-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text +rag_truth_hal_detection_model/checkpoint-1413/tokenizer.json filter=lfs diff=lfs merge=lfs -text +rag_truth_hal_detection_model/tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/rag_truth_hal_detection_model/README.md b/rag_truth_hal_detection_model/README.md new file mode 100644 index 0000000000000000000000000000000000000000..f70ac77eb3f249a754465b2cc94ef0e0eb90852d --- /dev/null +++ b/rag_truth_hal_detection_model/README.md @@ -0,0 +1,61 @@ +--- +library_name: transformers +license: other +base_model: meta-llama/Meta-Llama-3-8B-Instruct +tags: +- llama-factory +- full +- generated_from_trainer +model-index: +- name: train_2024-11-25-07-46-41 + results: [] +--- + + + +# train_2024-11-25-07-46-41 + +This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the train_hal_detection_1125 dataset. + +## Model description + +More information needed + +## Intended uses & limitations + +More information needed + +## Training and evaluation data + +More information needed + +## Training procedure + +### Training hyperparameters + +The following hyperparameters were used during training: +- learning_rate: 5e-06 +- train_batch_size: 1 +- eval_batch_size: 8 +- seed: 42 +- distributed_type: multi-GPU +- num_devices: 4 +- gradient_accumulation_steps: 8 +- total_train_batch_size: 32 +- total_eval_batch_size: 32 +- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments +- lr_scheduler_type: cosine +- lr_scheduler_warmup_steps: 10 +- num_epochs: 3.0 + +### Training results + + + +### Framework versions + +- Transformers 4.46.1 +- Pytorch 2.3.0a0+ebedce2 +- Datasets 3.1.0 +- Tokenizers 0.20.3 diff --git a/rag_truth_hal_detection_model/all_results.json b/rag_truth_hal_detection_model/all_results.json new file mode 100644 index 0000000000000000000000000000000000000000..685d6db0c045936cb9613c32540ca67f045ff161 --- /dev/null +++ b/rag_truth_hal_detection_model/all_results.json @@ -0,0 +1,8 @@ +{ + "epoch": 2.9976146302676914, + "total_flos": 1.9412022010031636e+18, + "train_loss": 0.22161940554313767, + "train_runtime": 29847.081, + "train_samples_per_second": 1.517, + "train_steps_per_second": 0.047 +} \ No newline at end of file diff --git a/rag_truth_hal_detection_model/checkpoint-1000/config.json b/rag_truth_hal_detection_model/checkpoint-1000/config.json new file mode 100644 index 0000000000000000000000000000000000000000..f79ee026750c76a1b06a7152a3fca58830d69257 --- /dev/null +++ b/rag_truth_hal_detection_model/checkpoint-1000/config.json @@ -0,0 +1,30 @@ +{ + "_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "eos_token_id": 128009, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 8192, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.46.1", + "use_cache": false, + "vocab_size": 128256 +} diff --git a/rag_truth_hal_detection_model/checkpoint-1000/generation_config.json b/rag_truth_hal_detection_model/checkpoint-1000/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..db0ea5c7647aac3cdc0802b1e95a53d09351382a --- /dev/null +++ b/rag_truth_hal_detection_model/checkpoint-1000/generation_config.json @@ -0,0 +1,12 @@ +{ + "bos_token_id": 128000, + "do_sample": true, + "eos_token_id": [ + 128001, + 128009 + ], + "max_length": 4096, + "temperature": 0.6, + "top_p": 0.9, + "transformers_version": "4.46.1" +} diff --git a/rag_truth_hal_detection_model/checkpoint-1000/global_step1000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/rag_truth_hal_detection_model/checkpoint-1000/global_step1000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..33105cb477081c408528c7695adaa0a5ec9b3b4b --- /dev/null +++ b/rag_truth_hal_detection_model/checkpoint-1000/global_step1000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79d74783e713065f55c8afd0e769890e65366d65fca00760775a4f7502382ca1 +size 24090793600 diff --git a/rag_truth_hal_detection_model/checkpoint-1000/global_step1000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/rag_truth_hal_detection_model/checkpoint-1000/global_step1000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3fd7b1f10c81595964674d91b5cb6b26687c7fa5 --- /dev/null +++ b/rag_truth_hal_detection_model/checkpoint-1000/global_step1000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29b8cd353679ad2958d5cdd0776f89235aae78646b0f76ce13916a1543f5defd +size 24090794752 diff --git a/rag_truth_hal_detection_model/checkpoint-1000/global_step1000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt b/rag_truth_hal_detection_model/checkpoint-1000/global_step1000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..c6eef9b4bf191c8adb5f350d553ef4a241d61d5c --- /dev/null +++ b/rag_truth_hal_detection_model/checkpoint-1000/global_step1000/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:b6d228e627e660e16db1776f0e3d76ff5601a804b38ced316ac91f1578d90b70 +size 24090795072 diff --git a/rag_truth_hal_detection_model/checkpoint-1000/global_step1000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt b/rag_truth_hal_detection_model/checkpoint-1000/global_step1000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..952db622deb8d3376cb7891e4a06433750e831eb --- /dev/null +++ b/rag_truth_hal_detection_model/checkpoint-1000/global_step1000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b894c1ee08903203df10f60884dcbe744b72a5ffd1f157391ff019bed0b6704 +size 24090793280 diff --git a/rag_truth_hal_detection_model/checkpoint-1000/global_step1000/mp_rank_00_model_states.pt b/rag_truth_hal_detection_model/checkpoint-1000/global_step1000/mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..14067fce5edbc22c1d6acca86a1c18ce12f6fed5 --- /dev/null +++ b/rag_truth_hal_detection_model/checkpoint-1000/global_step1000/mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7f31940a9d33dee4f9b182db36230fd2fad0430ae4195cd286079eb826de381 +size 16060610744 diff --git a/rag_truth_hal_detection_model/checkpoint-1000/latest b/rag_truth_hal_detection_model/checkpoint-1000/latest new file mode 100644 index 0000000000000000000000000000000000000000..e2d3435fb1acf8913e6bd6c51b01adfc69b11ac6 --- /dev/null +++ b/rag_truth_hal_detection_model/checkpoint-1000/latest @@ -0,0 +1 @@ +global_step1000 \ No newline at end of file diff --git a/rag_truth_hal_detection_model/checkpoint-1000/model-00001-of-00004.safetensors b/rag_truth_hal_detection_model/checkpoint-1000/model-00001-of-00004.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7e5aa3206b838bf37d6b2979222d910965350d69 --- /dev/null +++ b/rag_truth_hal_detection_model/checkpoint-1000/model-00001-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31c9860dd55db5c077d4babdf84882d622a30cb875fc5914f634bf731c5da510 +size 4976698672 diff --git a/rag_truth_hal_detection_model/checkpoint-1000/model-00002-of-00004.safetensors b/rag_truth_hal_detection_model/checkpoint-1000/model-00002-of-00004.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6fdd06b89b3afb372128b2000ef4badc110d4e83 --- /dev/null +++ b/rag_truth_hal_detection_model/checkpoint-1000/model-00002-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:733270aa41c2c8a4c2a9410884018fca89b7ed0a024a66e6e8a367d505d07824 +size 4999802720 diff --git a/rag_truth_hal_detection_model/checkpoint-1000/model-00003-of-00004.safetensors b/rag_truth_hal_detection_model/checkpoint-1000/model-00003-of-00004.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6d59c09fe814adcfbc31aae41a46466d5871ae01 --- /dev/null +++ b/rag_truth_hal_detection_model/checkpoint-1000/model-00003-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96d50f40e31dc7fddc65eb742c6892d8bb9565d130718df8bce828f0ae6b0c53 +size 4915916176 diff --git a/rag_truth_hal_detection_model/checkpoint-1000/model-00004-of-00004.safetensors b/rag_truth_hal_detection_model/checkpoint-1000/model-00004-of-00004.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b489edd0a76179199686541fbd22db79a36ca158 --- /dev/null +++ b/rag_truth_hal_detection_model/checkpoint-1000/model-00004-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:777577b476b3af27b952c4f8f3f112c064b72fb057c7d4840232c259cc489174 +size 1168138808 diff --git a/rag_truth_hal_detection_model/checkpoint-1000/model.safetensors.index.json b/rag_truth_hal_detection_model/checkpoint-1000/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..0fd8120f1c6acddc268ebc2583058efaf699a771 --- /dev/null +++ b/rag_truth_hal_detection_model/checkpoint-1000/model.safetensors.index.json @@ -0,0 +1,298 @@ +{ + "metadata": { + "total_size": 16060522496 + }, + "weight_map": { + "lm_head.weight": "model-00004-of-00004.safetensors", + "model.embed_tokens.weight": "model-00001-of-00004.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.norm.weight": "model-00004-of-00004.safetensors" + } +} diff --git a/rag_truth_hal_detection_model/checkpoint-1000/rng_state_0.pth b/rag_truth_hal_detection_model/checkpoint-1000/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..5a7c482c30381cd512ccc35fe322d8a34fbf5207 --- /dev/null +++ b/rag_truth_hal_detection_model/checkpoint-1000/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:308f94f9a5c24e1bad5c393d56ae7af7782600f4e791d9c6ac35b22fff2105b6 +size 15024 diff --git a/rag_truth_hal_detection_model/checkpoint-1000/rng_state_1.pth b/rag_truth_hal_detection_model/checkpoint-1000/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..7b862c21b28bbd89ce6b4fb681d41be05f175599 --- /dev/null +++ b/rag_truth_hal_detection_model/checkpoint-1000/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b056f3c23cb32dc77a2ec9e7651e0b64e4440e21f0fdf969b86bfc56a1cbdf06 +size 15024 diff --git a/rag_truth_hal_detection_model/checkpoint-1000/rng_state_2.pth b/rag_truth_hal_detection_model/checkpoint-1000/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..d86ce886844e0298f058d67065e5eeb27ffe7e48 --- /dev/null +++ b/rag_truth_hal_detection_model/checkpoint-1000/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3f8a05714bc528f4885a2816181652f2303b3e8150f89b56aaee6bec56aa520 +size 15024 diff --git a/rag_truth_hal_detection_model/checkpoint-1000/rng_state_3.pth b/rag_truth_hal_detection_model/checkpoint-1000/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..10733f5da657367adf3f67760028644c0839660f --- /dev/null +++ b/rag_truth_hal_detection_model/checkpoint-1000/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f755bd3c330281961e5c03af9d10ce8c1e1678619d384f6f1fd5fd7dce2ff50 +size 15024 diff --git a/rag_truth_hal_detection_model/checkpoint-1000/scheduler.pt b/rag_truth_hal_detection_model/checkpoint-1000/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..5c4eb2328a4b9dd8d5799577590210b2f5e7b56d --- /dev/null +++ b/rag_truth_hal_detection_model/checkpoint-1000/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ff53ba5304a643d71444d167894d0ea3127a741891763dae43f791b1f8a7817 +size 1064 diff --git a/rag_truth_hal_detection_model/checkpoint-1000/special_tokens_map.json b/rag_truth_hal_detection_model/checkpoint-1000/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..b43be96621d147110fb8a18b5776ec6e38516127 --- /dev/null +++ b/rag_truth_hal_detection_model/checkpoint-1000/special_tokens_map.json @@ -0,0 +1,17 @@ +{ + "bos_token": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "<|eot_id|>" +} diff --git a/rag_truth_hal_detection_model/checkpoint-1000/tokenizer.json b/rag_truth_hal_detection_model/checkpoint-1000/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..86a33946b0c77216d2cce91bb28c8fada4a5e80b --- /dev/null +++ b/rag_truth_hal_detection_model/checkpoint-1000/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c5cf44023714fb39b05e71e425f8d7b92805ff73f7988b083b8c87f0bf87393 +size 17209961 diff --git a/rag_truth_hal_detection_model/checkpoint-1000/tokenizer_config.json b/rag_truth_hal_detection_model/checkpoint-1000/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..82b337616471d4177c3b572a92a182f302f28430 --- /dev/null +++ b/rag_truth_hal_detection_model/checkpoint-1000/tokenizer_config.json @@ -0,0 +1,2065 @@ +{ + "added_tokens_decoder": { + "128000": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128001": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128002": { + "content": "<|reserved_special_token_0|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128003": { + "content": "<|reserved_special_token_1|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128004": { + "content": "<|reserved_special_token_2|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128005": { + "content": "<|reserved_special_token_3|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128006": { + "content": "<|start_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128007": { + "content": "<|end_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128008": { + "content": "<|reserved_special_token_4|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128009": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128010": { + "content": "<|reserved_special_token_5|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128011": { + "content": "<|reserved_special_token_6|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128012": { + "content": "<|reserved_special_token_7|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128013": { + "content": "<|reserved_special_token_8|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128014": { + "content": "<|reserved_special_token_9|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128015": { + "content": "<|reserved_special_token_10|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128016": { + "content": "<|reserved_special_token_11|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128017": { + "content": "<|reserved_special_token_12|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128018": { + "content": "<|reserved_special_token_13|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128019": { + "content": "<|reserved_special_token_14|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128020": { + "content": "<|reserved_special_token_15|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128021": { + "content": "<|reserved_special_token_16|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128022": { + "content": "<|reserved_special_token_17|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128023": { + "content": "<|reserved_special_token_18|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128024": { + "content": "<|reserved_special_token_19|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128025": { + "content": "<|reserved_special_token_20|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128026": { + "content": "<|reserved_special_token_21|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128027": { + "content": "<|reserved_special_token_22|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128028": { + "content": "<|reserved_special_token_23|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128029": { + "content": "<|reserved_special_token_24|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128030": { + "content": "<|reserved_special_token_25|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128031": { + "content": "<|reserved_special_token_26|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128032": { + "content": "<|reserved_special_token_27|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128033": { + "content": "<|reserved_special_token_28|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128034": { + "content": "<|reserved_special_token_29|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128035": { + "content": "<|reserved_special_token_30|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128036": { + "content": "<|reserved_special_token_31|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128037": { + "content": "<|reserved_special_token_32|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128038": { + "content": "<|reserved_special_token_33|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128039": { + "content": "<|reserved_special_token_34|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128040": { + "content": "<|reserved_special_token_35|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128041": { + "content": "<|reserved_special_token_36|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128042": { + "content": "<|reserved_special_token_37|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128043": { + "content": "<|reserved_special_token_38|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128044": { + "content": "<|reserved_special_token_39|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128045": { + "content": "<|reserved_special_token_40|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128046": { + "content": "<|reserved_special_token_41|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128047": { + "content": "<|reserved_special_token_42|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128048": { + "content": "<|reserved_special_token_43|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128049": { + "content": "<|reserved_special_token_44|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128050": { + "content": "<|reserved_special_token_45|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128051": { + "content": "<|reserved_special_token_46|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128052": { + "content": "<|reserved_special_token_47|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128053": { + "content": "<|reserved_special_token_48|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128054": { + "content": "<|reserved_special_token_49|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128055": { + "content": "<|reserved_special_token_50|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128056": { + "content": "<|reserved_special_token_51|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128057": { + "content": "<|reserved_special_token_52|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128058": { + "content": "<|reserved_special_token_53|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128059": { + "content": "<|reserved_special_token_54|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128060": { + "content": "<|reserved_special_token_55|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128061": { + "content": "<|reserved_special_token_56|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128062": { + "content": "<|reserved_special_token_57|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128063": { + "content": "<|reserved_special_token_58|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128064": { + "content": "<|reserved_special_token_59|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128065": { + "content": "<|reserved_special_token_60|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128066": { + "content": "<|reserved_special_token_61|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128067": { + "content": "<|reserved_special_token_62|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128068": { + "content": "<|reserved_special_token_63|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128069": { + "content": "<|reserved_special_token_64|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128070": { + "content": "<|reserved_special_token_65|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128071": { + "content": "<|reserved_special_token_66|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128072": { + "content": "<|reserved_special_token_67|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128073": { + "content": "<|reserved_special_token_68|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128074": { + "content": "<|reserved_special_token_69|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128075": { + "content": "<|reserved_special_token_70|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128076": { + "content": "<|reserved_special_token_71|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128077": { + "content": "<|reserved_special_token_72|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128078": { + "content": "<|reserved_special_token_73|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128079": { + "content": "<|reserved_special_token_74|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128080": { + "content": "<|reserved_special_token_75|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128081": { + "content": "<|reserved_special_token_76|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128082": { + "content": "<|reserved_special_token_77|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128083": { + "content": "<|reserved_special_token_78|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128084": { + "content": "<|reserved_special_token_79|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128085": { + "content": "<|reserved_special_token_80|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128086": { + "content": "<|reserved_special_token_81|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128087": { + "content": "<|reserved_special_token_82|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128088": { + "content": "<|reserved_special_token_83|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128089": { + "content": "<|reserved_special_token_84|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128090": { + "content": "<|reserved_special_token_85|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128091": { + "content": "<|reserved_special_token_86|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128092": { + "content": "<|reserved_special_token_87|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128093": { + "content": "<|reserved_special_token_88|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128094": { + "content": "<|reserved_special_token_89|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128095": { + "content": "<|reserved_special_token_90|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128096": { + "content": "<|reserved_special_token_91|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128097": { + "content": "<|reserved_special_token_92|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128098": { + "content": "<|reserved_special_token_93|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128099": { + "content": "<|reserved_special_token_94|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128100": { + "content": "<|reserved_special_token_95|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128101": { + "content": "<|reserved_special_token_96|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128102": { + "content": "<|reserved_special_token_97|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128103": { + "content": "<|reserved_special_token_98|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128104": { + "content": "<|reserved_special_token_99|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128105": { + "content": "<|reserved_special_token_100|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128106": { + "content": "<|reserved_special_token_101|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128107": { + "content": "<|reserved_special_token_102|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128108": { + "content": "<|reserved_special_token_103|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128109": { + "content": "<|reserved_special_token_104|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128110": { + "content": "<|reserved_special_token_105|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128111": { + "content": "<|reserved_special_token_106|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128112": { + "content": "<|reserved_special_token_107|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128113": { + "content": "<|reserved_special_token_108|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128114": { + "content": "<|reserved_special_token_109|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128115": { + "content": "<|reserved_special_token_110|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128116": { + "content": "<|reserved_special_token_111|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128117": { + "content": "<|reserved_special_token_112|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128118": { + "content": "<|reserved_special_token_113|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128119": { + "content": "<|reserved_special_token_114|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128120": { + "content": "<|reserved_special_token_115|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128121": { + "content": "<|reserved_special_token_116|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128122": { + "content": "<|reserved_special_token_117|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128123": { + "content": "<|reserved_special_token_118|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128124": { + "content": "<|reserved_special_token_119|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128125": { + "content": "<|reserved_special_token_120|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128126": { + "content": "<|reserved_special_token_121|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128127": { + "content": "<|reserved_special_token_122|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128128": { + "content": "<|reserved_special_token_123|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128129": { + "content": "<|reserved_special_token_124|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128130": { + "content": "<|reserved_special_token_125|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128131": { + "content": "<|reserved_special_token_126|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128132": { + "content": "<|reserved_special_token_127|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128133": { + "content": "<|reserved_special_token_128|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128134": { + "content": "<|reserved_special_token_129|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128135": { + "content": "<|reserved_special_token_130|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128136": { + "content": "<|reserved_special_token_131|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128137": { + "content": "<|reserved_special_token_132|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128138": { + "content": "<|reserved_special_token_133|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128139": { + "content": "<|reserved_special_token_134|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128140": { + "content": "<|reserved_special_token_135|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128141": { + "content": "<|reserved_special_token_136|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128142": { + "content": "<|reserved_special_token_137|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128143": { + "content": "<|reserved_special_token_138|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128144": { + "content": "<|reserved_special_token_139|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128145": { + "content": "<|reserved_special_token_140|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128146": { + "content": "<|reserved_special_token_141|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128147": { + "content": "<|reserved_special_token_142|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128148": { + "content": "<|reserved_special_token_143|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128149": { + "content": "<|reserved_special_token_144|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128150": { + "content": "<|reserved_special_token_145|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128151": { + "content": "<|reserved_special_token_146|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128152": { + "content": "<|reserved_special_token_147|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128153": { + "content": "<|reserved_special_token_148|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128154": { + "content": "<|reserved_special_token_149|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128155": { + "content": "<|reserved_special_token_150|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128156": { + "content": "<|reserved_special_token_151|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128157": { + "content": "<|reserved_special_token_152|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128158": { + "content": "<|reserved_special_token_153|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128159": { + "content": "<|reserved_special_token_154|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128160": { + "content": "<|reserved_special_token_155|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128161": { + "content": "<|reserved_special_token_156|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128162": { + "content": "<|reserved_special_token_157|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128163": { + "content": "<|reserved_special_token_158|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128164": { + "content": "<|reserved_special_token_159|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128165": { + "content": "<|reserved_special_token_160|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128166": { + "content": "<|reserved_special_token_161|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128167": { + "content": "<|reserved_special_token_162|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128168": { + "content": "<|reserved_special_token_163|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128169": { + "content": "<|reserved_special_token_164|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128170": { + "content": "<|reserved_special_token_165|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128171": { + "content": "<|reserved_special_token_166|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128172": { + "content": "<|reserved_special_token_167|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128173": { + "content": "<|reserved_special_token_168|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128174": { + "content": "<|reserved_special_token_169|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128175": { + "content": "<|reserved_special_token_170|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128176": { + "content": "<|reserved_special_token_171|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128177": { + "content": "<|reserved_special_token_172|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128178": { + "content": "<|reserved_special_token_173|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128179": { + "content": "<|reserved_special_token_174|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128180": { + "content": "<|reserved_special_token_175|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128181": { + "content": "<|reserved_special_token_176|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128182": { + "content": "<|reserved_special_token_177|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128183": { + "content": "<|reserved_special_token_178|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128184": { + "content": "<|reserved_special_token_179|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128185": { + "content": "<|reserved_special_token_180|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128186": { + "content": "<|reserved_special_token_181|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128187": { + "content": "<|reserved_special_token_182|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128188": { + "content": "<|reserved_special_token_183|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128189": { + "content": "<|reserved_special_token_184|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128190": { + "content": "<|reserved_special_token_185|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128191": { + "content": "<|reserved_special_token_186|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128192": { + "content": "<|reserved_special_token_187|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128193": { + "content": "<|reserved_special_token_188|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128194": { + "content": "<|reserved_special_token_189|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128195": { + "content": "<|reserved_special_token_190|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128196": { + "content": "<|reserved_special_token_191|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128197": { + "content": "<|reserved_special_token_192|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128198": { + "content": "<|reserved_special_token_193|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128199": { + "content": "<|reserved_special_token_194|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128200": { + "content": "<|reserved_special_token_195|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128201": { + "content": "<|reserved_special_token_196|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128202": { + "content": "<|reserved_special_token_197|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128203": { + "content": "<|reserved_special_token_198|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128204": { + "content": "<|reserved_special_token_199|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128205": { + "content": "<|reserved_special_token_200|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128206": { + "content": "<|reserved_special_token_201|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128207": { + "content": "<|reserved_special_token_202|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128208": { + "content": "<|reserved_special_token_203|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128209": { + "content": "<|reserved_special_token_204|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128210": { + "content": "<|reserved_special_token_205|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128211": { + "content": "<|reserved_special_token_206|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128212": { + "content": "<|reserved_special_token_207|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128213": { + "content": "<|reserved_special_token_208|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128214": { + "content": "<|reserved_special_token_209|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128215": { + "content": "<|reserved_special_token_210|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128216": { + "content": "<|reserved_special_token_211|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128217": { + "content": "<|reserved_special_token_212|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128218": { + "content": "<|reserved_special_token_213|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128219": { + "content": "<|reserved_special_token_214|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128220": { + "content": "<|reserved_special_token_215|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128221": { + "content": "<|reserved_special_token_216|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128222": { + "content": "<|reserved_special_token_217|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128223": { + "content": "<|reserved_special_token_218|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128224": { + "content": "<|reserved_special_token_219|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128225": { + "content": "<|reserved_special_token_220|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128226": { + "content": "<|reserved_special_token_221|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128227": { + "content": "<|reserved_special_token_222|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128228": { + "content": "<|reserved_special_token_223|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128229": { + "content": "<|reserved_special_token_224|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128230": { + "content": "<|reserved_special_token_225|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128231": { + "content": "<|reserved_special_token_226|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128232": { + "content": "<|reserved_special_token_227|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128233": { + "content": "<|reserved_special_token_228|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128234": { + "content": "<|reserved_special_token_229|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128235": { + "content": "<|reserved_special_token_230|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128236": { + "content": "<|reserved_special_token_231|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128237": { + "content": "<|reserved_special_token_232|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128238": { + "content": "<|reserved_special_token_233|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128239": { + "content": "<|reserved_special_token_234|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128240": { + "content": "<|reserved_special_token_235|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128241": { + "content": "<|reserved_special_token_236|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128242": { + "content": "<|reserved_special_token_237|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128243": { + "content": "<|reserved_special_token_238|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128244": { + "content": "<|reserved_special_token_239|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128245": { + "content": "<|reserved_special_token_240|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128246": { + "content": "<|reserved_special_token_241|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128247": { + "content": "<|reserved_special_token_242|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128248": { + "content": "<|reserved_special_token_243|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128249": { + "content": "<|reserved_special_token_244|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128250": { + "content": "<|reserved_special_token_245|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128251": { + "content": "<|reserved_special_token_246|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128252": { + "content": "<|reserved_special_token_247|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128253": { + "content": "<|reserved_special_token_248|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128254": { + "content": "<|reserved_special_token_249|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128255": { + "content": "<|reserved_special_token_250|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "<|begin_of_text|>", + "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}", + "clean_up_tokenization_spaces": true, + "eos_token": "<|eot_id|>", + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 1000000000000000019884624838656, + "pad_token": "<|eot_id|>", + "padding_side": "right", + "split_special_tokens": false, + "tokenizer_class": "PreTrainedTokenizerFast" +} diff --git a/rag_truth_hal_detection_model/checkpoint-1000/trainer_state.json b/rag_truth_hal_detection_model/checkpoint-1000/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..58871f3fb26c3e9bc43331a6c8254702459269bd --- /dev/null +++ b/rag_truth_hal_detection_model/checkpoint-1000/trainer_state.json @@ -0,0 +1,7033 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 2.1219188974291017, + "eval_steps": 500, + "global_step": 1000, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0021203286509408957, + "grad_norm": 25.949520111083984, + "learning_rate": 5.000000000000001e-07, + "loss": 1.2577, + "step": 1 + }, + { + "epoch": 0.004240657301881791, + "grad_norm": 27.748842239379883, + "learning_rate": 1.0000000000000002e-06, + "loss": 1.1764, + "step": 2 + }, + { + "epoch": 0.0063609859528226875, + "grad_norm": 25.2868595123291, + "learning_rate": 1.5e-06, + "loss": 1.1581, + "step": 3 + }, + { + "epoch": 0.008481314603763583, + "grad_norm": 26.029958724975586, + "learning_rate": 2.0000000000000003e-06, + "loss": 0.9151, + "step": 4 + }, + { + "epoch": 0.010601643254704479, + "grad_norm": 15.586308479309082, + "learning_rate": 2.5e-06, + "loss": 0.5946, + "step": 5 + }, + { + "epoch": 0.012721971905645375, + "grad_norm": 24.38088607788086, + "learning_rate": 3e-06, + "loss": 0.514, + "step": 6 + }, + { + "epoch": 0.014842300556586271, + "grad_norm": 15.221429824829102, + "learning_rate": 3.5e-06, + "loss": 0.3226, + "step": 7 + }, + { + "epoch": 0.016962629207527165, + "grad_norm": 12.0006742477417, + "learning_rate": 4.000000000000001e-06, + "loss": 0.3853, + "step": 8 + }, + { + "epoch": 0.01908295785846806, + "grad_norm": 4.748922348022461, + "learning_rate": 4.5e-06, + "loss": 0.2983, + "step": 9 + }, + { + "epoch": 0.021203286509408958, + "grad_norm": 2.3620359897613525, + "learning_rate": 5e-06, + "loss": 0.4318, + "step": 10 + }, + { + "epoch": 0.023323615160349854, + "grad_norm": 8.839906692504883, + "learning_rate": 4.9999937325015554e-06, + "loss": 0.4925, + "step": 11 + }, + { + "epoch": 0.02544394381129075, + "grad_norm": 4.359335422515869, + "learning_rate": 4.999974930037645e-06, + "loss": 0.4128, + "step": 12 + }, + { + "epoch": 0.027564272462231646, + "grad_norm": 2.051809310913086, + "learning_rate": 4.999943592702547e-06, + "loss": 0.3941, + "step": 13 + }, + { + "epoch": 0.029684601113172542, + "grad_norm": 4.041887283325195, + "learning_rate": 4.999899720653384e-06, + "loss": 0.527, + "step": 14 + }, + { + "epoch": 0.031804929764113435, + "grad_norm": 4.354254245758057, + "learning_rate": 4.999843314110132e-06, + "loss": 0.5217, + "step": 15 + }, + { + "epoch": 0.03392525841505433, + "grad_norm": 4.818948268890381, + "learning_rate": 4.999774373355613e-06, + "loss": 0.262, + "step": 16 + }, + { + "epoch": 0.03604558706599523, + "grad_norm": 4.6067585945129395, + "learning_rate": 4.999692898735496e-06, + "loss": 0.5101, + "step": 17 + }, + { + "epoch": 0.03816591571693612, + "grad_norm": 4.296671390533447, + "learning_rate": 4.999598890658294e-06, + "loss": 0.376, + "step": 18 + }, + { + "epoch": 0.04028624436787702, + "grad_norm": 5.08732795715332, + "learning_rate": 4.999492349595364e-06, + "loss": 0.3747, + "step": 19 + }, + { + "epoch": 0.042406573018817915, + "grad_norm": 4.986461639404297, + "learning_rate": 4.999373276080902e-06, + "loss": 0.3933, + "step": 20 + }, + { + "epoch": 0.04452690166975881, + "grad_norm": 3.174241781234741, + "learning_rate": 4.999241670711944e-06, + "loss": 0.3696, + "step": 21 + }, + { + "epoch": 0.04664723032069971, + "grad_norm": 2.13350510597229, + "learning_rate": 4.999097534148358e-06, + "loss": 0.3125, + "step": 22 + }, + { + "epoch": 0.048767558971640604, + "grad_norm": 15.487786293029785, + "learning_rate": 4.998940867112844e-06, + "loss": 0.4218, + "step": 23 + }, + { + "epoch": 0.0508878876225815, + "grad_norm": 4.8160552978515625, + "learning_rate": 4.998771670390931e-06, + "loss": 0.3827, + "step": 24 + }, + { + "epoch": 0.053008216273522396, + "grad_norm": 3.281799077987671, + "learning_rate": 4.998589944830973e-06, + "loss": 0.4637, + "step": 25 + }, + { + "epoch": 0.05512854492446329, + "grad_norm": 3.690784454345703, + "learning_rate": 4.998395691344138e-06, + "loss": 0.3562, + "step": 26 + }, + { + "epoch": 0.05724887357540419, + "grad_norm": 3.4011573791503906, + "learning_rate": 4.998188910904416e-06, + "loss": 0.3842, + "step": 27 + }, + { + "epoch": 0.059369202226345084, + "grad_norm": 4.38139533996582, + "learning_rate": 4.997969604548602e-06, + "loss": 0.3048, + "step": 28 + }, + { + "epoch": 0.06148953087728598, + "grad_norm": 2.751617908477783, + "learning_rate": 4.997737773376298e-06, + "loss": 0.3621, + "step": 29 + }, + { + "epoch": 0.06360985952822687, + "grad_norm": 4.899576187133789, + "learning_rate": 4.997493418549905e-06, + "loss": 0.2974, + "step": 30 + }, + { + "epoch": 0.06573018817916777, + "grad_norm": 1.5958459377288818, + "learning_rate": 4.99723654129462e-06, + "loss": 0.445, + "step": 31 + }, + { + "epoch": 0.06785051683010866, + "grad_norm": 4.093502521514893, + "learning_rate": 4.996967142898423e-06, + "loss": 0.3759, + "step": 32 + }, + { + "epoch": 0.06997084548104957, + "grad_norm": 0.6687224507331848, + "learning_rate": 4.996685224712077e-06, + "loss": 0.3232, + "step": 33 + }, + { + "epoch": 0.07209117413199045, + "grad_norm": 3.0124692916870117, + "learning_rate": 4.99639078814912e-06, + "loss": 0.4248, + "step": 34 + }, + { + "epoch": 0.07421150278293136, + "grad_norm": 2.5640933513641357, + "learning_rate": 4.996083834685858e-06, + "loss": 0.2229, + "step": 35 + }, + { + "epoch": 0.07633183143387225, + "grad_norm": 6.7540812492370605, + "learning_rate": 4.995764365861354e-06, + "loss": 0.316, + "step": 36 + }, + { + "epoch": 0.07845216008481315, + "grad_norm": 4.984259605407715, + "learning_rate": 4.9954323832774235e-06, + "loss": 0.3061, + "step": 37 + }, + { + "epoch": 0.08057248873575404, + "grad_norm": 2.3390185832977295, + "learning_rate": 4.995087888598629e-06, + "loss": 0.3889, + "step": 38 + }, + { + "epoch": 0.08269281738669494, + "grad_norm": 3.226795196533203, + "learning_rate": 4.994730883552263e-06, + "loss": 0.3944, + "step": 39 + }, + { + "epoch": 0.08481314603763583, + "grad_norm": 3.2235963344573975, + "learning_rate": 4.994361369928352e-06, + "loss": 0.5437, + "step": 40 + }, + { + "epoch": 0.08693347468857673, + "grad_norm": 5.956916809082031, + "learning_rate": 4.993979349579635e-06, + "loss": 0.357, + "step": 41 + }, + { + "epoch": 0.08905380333951762, + "grad_norm": 5.488076210021973, + "learning_rate": 4.9935848244215615e-06, + "loss": 0.3081, + "step": 42 + }, + { + "epoch": 0.09117413199045853, + "grad_norm": 2.534620761871338, + "learning_rate": 4.993177796432281e-06, + "loss": 0.3468, + "step": 43 + }, + { + "epoch": 0.09329446064139942, + "grad_norm": 3.6338629722595215, + "learning_rate": 4.99275826765263e-06, + "loss": 0.3266, + "step": 44 + }, + { + "epoch": 0.09541478929234032, + "grad_norm": 3.6629638671875, + "learning_rate": 4.992326240186127e-06, + "loss": 0.3799, + "step": 45 + }, + { + "epoch": 0.09753511794328121, + "grad_norm": 3.4478704929351807, + "learning_rate": 4.991881716198955e-06, + "loss": 0.3149, + "step": 46 + }, + { + "epoch": 0.09965544659422211, + "grad_norm": 1.566508412361145, + "learning_rate": 4.9914246979199586e-06, + "loss": 0.2163, + "step": 47 + }, + { + "epoch": 0.101775775245163, + "grad_norm": 2.76956844329834, + "learning_rate": 4.990955187640627e-06, + "loss": 0.4008, + "step": 48 + }, + { + "epoch": 0.1038961038961039, + "grad_norm": 3.9344685077667236, + "learning_rate": 4.990473187715082e-06, + "loss": 0.3937, + "step": 49 + }, + { + "epoch": 0.10601643254704479, + "grad_norm": 2.5321309566497803, + "learning_rate": 4.989978700560073e-06, + "loss": 0.381, + "step": 50 + }, + { + "epoch": 0.10813676119798568, + "grad_norm": 3.8619720935821533, + "learning_rate": 4.9894717286549566e-06, + "loss": 0.2995, + "step": 51 + }, + { + "epoch": 0.11025708984892658, + "grad_norm": 8.722846031188965, + "learning_rate": 4.98895227454169e-06, + "loss": 0.2401, + "step": 52 + }, + { + "epoch": 0.11237741849986747, + "grad_norm": 1.9420874118804932, + "learning_rate": 4.9884203408248145e-06, + "loss": 0.3294, + "step": 53 + }, + { + "epoch": 0.11449774715080838, + "grad_norm": 2.523827314376831, + "learning_rate": 4.987875930171446e-06, + "loss": 0.4972, + "step": 54 + }, + { + "epoch": 0.11661807580174927, + "grad_norm": 3.6966936588287354, + "learning_rate": 4.987319045311259e-06, + "loss": 0.4146, + "step": 55 + }, + { + "epoch": 0.11873840445269017, + "grad_norm": 2.447277069091797, + "learning_rate": 4.9867496890364734e-06, + "loss": 0.3277, + "step": 56 + }, + { + "epoch": 0.12085873310363106, + "grad_norm": 2.2751476764678955, + "learning_rate": 4.98616786420184e-06, + "loss": 0.2963, + "step": 57 + }, + { + "epoch": 0.12297906175457196, + "grad_norm": 1.655998706817627, + "learning_rate": 4.985573573724628e-06, + "loss": 0.2798, + "step": 58 + }, + { + "epoch": 0.12509939040551285, + "grad_norm": 5.7478837966918945, + "learning_rate": 4.98496682058461e-06, + "loss": 0.3764, + "step": 59 + }, + { + "epoch": 0.12721971905645374, + "grad_norm": 1.5899176597595215, + "learning_rate": 4.984347607824045e-06, + "loss": 0.2544, + "step": 60 + }, + { + "epoch": 0.12934004770739466, + "grad_norm": 2.066739082336426, + "learning_rate": 4.9837159385476655e-06, + "loss": 0.3421, + "step": 61 + }, + { + "epoch": 0.13146037635833555, + "grad_norm": 4.85571813583374, + "learning_rate": 4.983071815922659e-06, + "loss": 0.4167, + "step": 62 + }, + { + "epoch": 0.13358070500927643, + "grad_norm": 4.446200370788574, + "learning_rate": 4.9824152431786565e-06, + "loss": 0.1973, + "step": 63 + }, + { + "epoch": 0.13570103366021732, + "grad_norm": 2.905205011367798, + "learning_rate": 4.981746223607713e-06, + "loss": 0.3211, + "step": 64 + }, + { + "epoch": 0.13782136231115824, + "grad_norm": 1.2360762357711792, + "learning_rate": 4.981064760564292e-06, + "loss": 0.2813, + "step": 65 + }, + { + "epoch": 0.13994169096209913, + "grad_norm": 2.0999205112457275, + "learning_rate": 4.9803708574652475e-06, + "loss": 0.2489, + "step": 66 + }, + { + "epoch": 0.14206201961304002, + "grad_norm": 4.240612030029297, + "learning_rate": 4.979664517789811e-06, + "loss": 0.3817, + "step": 67 + }, + { + "epoch": 0.1441823482639809, + "grad_norm": 2.3623316287994385, + "learning_rate": 4.978945745079565e-06, + "loss": 0.2673, + "step": 68 + }, + { + "epoch": 0.14630267691492183, + "grad_norm": 3.3251216411590576, + "learning_rate": 4.978214542938438e-06, + "loss": 0.2844, + "step": 69 + }, + { + "epoch": 0.14842300556586271, + "grad_norm": 1.5501821041107178, + "learning_rate": 4.977470915032676e-06, + "loss": 0.2262, + "step": 70 + }, + { + "epoch": 0.1505433342168036, + "grad_norm": 2.6850452423095703, + "learning_rate": 4.976714865090827e-06, + "loss": 0.265, + "step": 71 + }, + { + "epoch": 0.1526636628677445, + "grad_norm": 3.2187998294830322, + "learning_rate": 4.975946396903727e-06, + "loss": 0.3004, + "step": 72 + }, + { + "epoch": 0.1547839915186854, + "grad_norm": 2.397681951522827, + "learning_rate": 4.9751655143244715e-06, + "loss": 0.3076, + "step": 73 + }, + { + "epoch": 0.1569043201696263, + "grad_norm": 4.3145952224731445, + "learning_rate": 4.974372221268408e-06, + "loss": 0.237, + "step": 74 + }, + { + "epoch": 0.1590246488205672, + "grad_norm": 1.271013617515564, + "learning_rate": 4.973566521713104e-06, + "loss": 0.3886, + "step": 75 + }, + { + "epoch": 0.16114497747150808, + "grad_norm": 3.8556087017059326, + "learning_rate": 4.972748419698337e-06, + "loss": 0.4216, + "step": 76 + }, + { + "epoch": 0.16326530612244897, + "grad_norm": 2.6716325283050537, + "learning_rate": 4.971917919326071e-06, + "loss": 0.2869, + "step": 77 + }, + { + "epoch": 0.16538563477338988, + "grad_norm": 3.054572820663452, + "learning_rate": 4.971075024760432e-06, + "loss": 0.2688, + "step": 78 + }, + { + "epoch": 0.16750596342433077, + "grad_norm": 2.3528730869293213, + "learning_rate": 4.970219740227693e-06, + "loss": 0.3894, + "step": 79 + }, + { + "epoch": 0.16962629207527166, + "grad_norm": 2.507408857345581, + "learning_rate": 4.96935207001625e-06, + "loss": 0.3129, + "step": 80 + }, + { + "epoch": 0.17174662072621255, + "grad_norm": 3.135934829711914, + "learning_rate": 4.968472018476599e-06, + "loss": 0.322, + "step": 81 + }, + { + "epoch": 0.17386694937715347, + "grad_norm": 2.3163411617279053, + "learning_rate": 4.967579590021319e-06, + "loss": 0.3069, + "step": 82 + }, + { + "epoch": 0.17598727802809436, + "grad_norm": 4.409370422363281, + "learning_rate": 4.966674789125044e-06, + "loss": 0.3893, + "step": 83 + }, + { + "epoch": 0.17810760667903525, + "grad_norm": 3.5317368507385254, + "learning_rate": 4.965757620324445e-06, + "loss": 0.3198, + "step": 84 + }, + { + "epoch": 0.18022793532997614, + "grad_norm": 2.794269561767578, + "learning_rate": 4.9648280882182056e-06, + "loss": 0.3547, + "step": 85 + }, + { + "epoch": 0.18234826398091705, + "grad_norm": 1.2279053926467896, + "learning_rate": 4.963886197466998e-06, + "loss": 0.2338, + "step": 86 + }, + { + "epoch": 0.18446859263185794, + "grad_norm": 3.633697509765625, + "learning_rate": 4.962931952793461e-06, + "loss": 0.3118, + "step": 87 + }, + { + "epoch": 0.18658892128279883, + "grad_norm": 1.3397223949432373, + "learning_rate": 4.961965358982177e-06, + "loss": 0.2744, + "step": 88 + }, + { + "epoch": 0.18870924993373972, + "grad_norm": 2.2551627159118652, + "learning_rate": 4.960986420879645e-06, + "loss": 0.3339, + "step": 89 + }, + { + "epoch": 0.19082957858468064, + "grad_norm": 2.727034330368042, + "learning_rate": 4.9599951433942614e-06, + "loss": 0.2318, + "step": 90 + }, + { + "epoch": 0.19294990723562153, + "grad_norm": 2.2735791206359863, + "learning_rate": 4.958991531496289e-06, + "loss": 0.3198, + "step": 91 + }, + { + "epoch": 0.19507023588656242, + "grad_norm": 3.066884756088257, + "learning_rate": 4.957975590217836e-06, + "loss": 0.2254, + "step": 92 + }, + { + "epoch": 0.1971905645375033, + "grad_norm": 2.4200687408447266, + "learning_rate": 4.956947324652832e-06, + "loss": 0.277, + "step": 93 + }, + { + "epoch": 0.19931089318844422, + "grad_norm": 3.770292043685913, + "learning_rate": 4.955906739956999e-06, + "loss": 0.3462, + "step": 94 + }, + { + "epoch": 0.2014312218393851, + "grad_norm": 2.9880192279815674, + "learning_rate": 4.954853841347827e-06, + "loss": 0.2103, + "step": 95 + }, + { + "epoch": 0.203551550490326, + "grad_norm": 2.8914637565612793, + "learning_rate": 4.9537886341045475e-06, + "loss": 0.246, + "step": 96 + }, + { + "epoch": 0.2056718791412669, + "grad_norm": 4.304288864135742, + "learning_rate": 4.95271112356811e-06, + "loss": 0.3306, + "step": 97 + }, + { + "epoch": 0.2077922077922078, + "grad_norm": 6.69378662109375, + "learning_rate": 4.951621315141149e-06, + "loss": 0.37, + "step": 98 + }, + { + "epoch": 0.2099125364431487, + "grad_norm": 4.184510231018066, + "learning_rate": 4.950519214287966e-06, + "loss": 0.3687, + "step": 99 + }, + { + "epoch": 0.21203286509408958, + "grad_norm": 3.177889585494995, + "learning_rate": 4.9494048265344896e-06, + "loss": 0.4234, + "step": 100 + }, + { + "epoch": 0.21415319374503047, + "grad_norm": 1.1268483400344849, + "learning_rate": 4.94827815746826e-06, + "loss": 0.3633, + "step": 101 + }, + { + "epoch": 0.21627352239597136, + "grad_norm": 3.196904420852661, + "learning_rate": 4.947139212738395e-06, + "loss": 0.3335, + "step": 102 + }, + { + "epoch": 0.21839385104691228, + "grad_norm": 3.6721370220184326, + "learning_rate": 4.945987998055562e-06, + "loss": 0.186, + "step": 103 + }, + { + "epoch": 0.22051417969785317, + "grad_norm": 2.374629497528076, + "learning_rate": 4.944824519191949e-06, + "loss": 0.2399, + "step": 104 + }, + { + "epoch": 0.22263450834879406, + "grad_norm": 3.0888235569000244, + "learning_rate": 4.943648781981239e-06, + "loss": 0.2794, + "step": 105 + }, + { + "epoch": 0.22475483699973495, + "grad_norm": 2.1860692501068115, + "learning_rate": 4.942460792318575e-06, + "loss": 0.2431, + "step": 106 + }, + { + "epoch": 0.22687516565067586, + "grad_norm": 2.057961940765381, + "learning_rate": 4.9412605561605365e-06, + "loss": 0.258, + "step": 107 + }, + { + "epoch": 0.22899549430161675, + "grad_norm": 2.826047420501709, + "learning_rate": 4.940048079525108e-06, + "loss": 0.3056, + "step": 108 + }, + { + "epoch": 0.23111582295255764, + "grad_norm": 1.93588125705719, + "learning_rate": 4.9388233684916434e-06, + "loss": 0.3374, + "step": 109 + }, + { + "epoch": 0.23323615160349853, + "grad_norm": 1.4116945266723633, + "learning_rate": 4.937586429200842e-06, + "loss": 0.1877, + "step": 110 + }, + { + "epoch": 0.23535648025443945, + "grad_norm": 3.5607080459594727, + "learning_rate": 4.936337267854719e-06, + "loss": 0.319, + "step": 111 + }, + { + "epoch": 0.23747680890538034, + "grad_norm": 1.9677248001098633, + "learning_rate": 4.935075890716565e-06, + "loss": 0.2615, + "step": 112 + }, + { + "epoch": 0.23959713755632123, + "grad_norm": 1.2864681482315063, + "learning_rate": 4.933802304110925e-06, + "loss": 0.2038, + "step": 113 + }, + { + "epoch": 0.24171746620726212, + "grad_norm": 3.6011598110198975, + "learning_rate": 4.932516514423559e-06, + "loss": 0.2945, + "step": 114 + }, + { + "epoch": 0.24383779485820303, + "grad_norm": 0.8037973642349243, + "learning_rate": 4.931218528101416e-06, + "loss": 0.2102, + "step": 115 + }, + { + "epoch": 0.24595812350914392, + "grad_norm": 5.048084259033203, + "learning_rate": 4.929908351652598e-06, + "loss": 0.3449, + "step": 116 + }, + { + "epoch": 0.2480784521600848, + "grad_norm": 3.8754634857177734, + "learning_rate": 4.928585991646327e-06, + "loss": 0.3072, + "step": 117 + }, + { + "epoch": 0.2501987808110257, + "grad_norm": 3.335463523864746, + "learning_rate": 4.927251454712915e-06, + "loss": 0.3457, + "step": 118 + }, + { + "epoch": 0.2523191094619666, + "grad_norm": 2.5155117511749268, + "learning_rate": 4.925904747543729e-06, + "loss": 0.3305, + "step": 119 + }, + { + "epoch": 0.2544394381129075, + "grad_norm": 3.2518768310546875, + "learning_rate": 4.924545876891157e-06, + "loss": 0.4029, + "step": 120 + }, + { + "epoch": 0.2565597667638484, + "grad_norm": 3.0308430194854736, + "learning_rate": 4.9231748495685745e-06, + "loss": 0.3313, + "step": 121 + }, + { + "epoch": 0.2586800954147893, + "grad_norm": 4.494399070739746, + "learning_rate": 4.921791672450311e-06, + "loss": 0.263, + "step": 122 + }, + { + "epoch": 0.2608004240657302, + "grad_norm": 3.257610321044922, + "learning_rate": 4.920396352471613e-06, + "loss": 0.4046, + "step": 123 + }, + { + "epoch": 0.2629207527166711, + "grad_norm": 2.162080764770508, + "learning_rate": 4.918988896628617e-06, + "loss": 0.2562, + "step": 124 + }, + { + "epoch": 0.26504108136761195, + "grad_norm": 1.7331904172897339, + "learning_rate": 4.917569311978301e-06, + "loss": 0.2157, + "step": 125 + }, + { + "epoch": 0.26716141001855287, + "grad_norm": 2.089783191680908, + "learning_rate": 4.916137605638463e-06, + "loss": 0.2177, + "step": 126 + }, + { + "epoch": 0.2692817386694938, + "grad_norm": 2.637751817703247, + "learning_rate": 4.914693784787676e-06, + "loss": 0.2717, + "step": 127 + }, + { + "epoch": 0.27140206732043465, + "grad_norm": 1.1012979745864868, + "learning_rate": 4.913237856665256e-06, + "loss": 0.2845, + "step": 128 + }, + { + "epoch": 0.27352239597137556, + "grad_norm": 2.7496721744537354, + "learning_rate": 4.911769828571224e-06, + "loss": 0.2839, + "step": 129 + }, + { + "epoch": 0.2756427246223165, + "grad_norm": 3.16662335395813, + "learning_rate": 4.910289707866273e-06, + "loss": 0.3791, + "step": 130 + }, + { + "epoch": 0.27776305327325734, + "grad_norm": 3.3091320991516113, + "learning_rate": 4.908797501971725e-06, + "loss": 0.3046, + "step": 131 + }, + { + "epoch": 0.27988338192419826, + "grad_norm": 2.08532452583313, + "learning_rate": 4.907293218369499e-06, + "loss": 0.2242, + "step": 132 + }, + { + "epoch": 0.2820037105751391, + "grad_norm": 1.4009634256362915, + "learning_rate": 4.90577686460207e-06, + "loss": 0.2657, + "step": 133 + }, + { + "epoch": 0.28412403922608004, + "grad_norm": 2.2569682598114014, + "learning_rate": 4.904248448272435e-06, + "loss": 0.2321, + "step": 134 + }, + { + "epoch": 0.28624436787702096, + "grad_norm": 2.43658709526062, + "learning_rate": 4.902707977044071e-06, + "loss": 0.2339, + "step": 135 + }, + { + "epoch": 0.2883646965279618, + "grad_norm": 1.7777557373046875, + "learning_rate": 4.9011554586409005e-06, + "loss": 0.2703, + "step": 136 + }, + { + "epoch": 0.29048502517890273, + "grad_norm": 4.1074347496032715, + "learning_rate": 4.8995909008472465e-06, + "loss": 0.3249, + "step": 137 + }, + { + "epoch": 0.29260535382984365, + "grad_norm": 2.1729867458343506, + "learning_rate": 4.898014311507801e-06, + "loss": 0.229, + "step": 138 + }, + { + "epoch": 0.2947256824807845, + "grad_norm": 3.032817840576172, + "learning_rate": 4.8964256985275805e-06, + "loss": 0.2925, + "step": 139 + }, + { + "epoch": 0.29684601113172543, + "grad_norm": 1.834567904472351, + "learning_rate": 4.8948250698718895e-06, + "loss": 0.2349, + "step": 140 + }, + { + "epoch": 0.2989663397826663, + "grad_norm": 3.393310785293579, + "learning_rate": 4.893212433566277e-06, + "loss": 0.3615, + "step": 141 + }, + { + "epoch": 0.3010866684336072, + "grad_norm": 4.021195888519287, + "learning_rate": 4.8915877976964995e-06, + "loss": 0.4128, + "step": 142 + }, + { + "epoch": 0.3032069970845481, + "grad_norm": 1.6174540519714355, + "learning_rate": 4.889951170408479e-06, + "loss": 0.2398, + "step": 143 + }, + { + "epoch": 0.305327325735489, + "grad_norm": 2.0691730976104736, + "learning_rate": 4.888302559908265e-06, + "loss": 0.3333, + "step": 144 + }, + { + "epoch": 0.3074476543864299, + "grad_norm": 0.9198992848396301, + "learning_rate": 4.886641974461985e-06, + "loss": 0.2091, + "step": 145 + }, + { + "epoch": 0.3095679830373708, + "grad_norm": 2.2674360275268555, + "learning_rate": 4.884969422395815e-06, + "loss": 0.2042, + "step": 146 + }, + { + "epoch": 0.3116883116883117, + "grad_norm": 2.365835428237915, + "learning_rate": 4.883284912095928e-06, + "loss": 0.3742, + "step": 147 + }, + { + "epoch": 0.3138086403392526, + "grad_norm": 3.322329521179199, + "learning_rate": 4.881588452008457e-06, + "loss": 0.3228, + "step": 148 + }, + { + "epoch": 0.31592896899019346, + "grad_norm": 6.298361301422119, + "learning_rate": 4.87988005063945e-06, + "loss": 0.452, + "step": 149 + }, + { + "epoch": 0.3180492976411344, + "grad_norm": 3.925762414932251, + "learning_rate": 4.87815971655483e-06, + "loss": 0.3467, + "step": 150 + }, + { + "epoch": 0.3201696262920753, + "grad_norm": 4.023056507110596, + "learning_rate": 4.876427458380349e-06, + "loss": 0.3558, + "step": 151 + }, + { + "epoch": 0.32228995494301615, + "grad_norm": 3.4093480110168457, + "learning_rate": 4.874683284801548e-06, + "loss": 0.2739, + "step": 152 + }, + { + "epoch": 0.32441028359395707, + "grad_norm": 0.9935247302055359, + "learning_rate": 4.872927204563712e-06, + "loss": 0.2131, + "step": 153 + }, + { + "epoch": 0.32653061224489793, + "grad_norm": 1.8300209045410156, + "learning_rate": 4.871159226471825e-06, + "loss": 0.329, + "step": 154 + }, + { + "epoch": 0.32865094089583885, + "grad_norm": 2.8266682624816895, + "learning_rate": 4.869379359390524e-06, + "loss": 0.2388, + "step": 155 + }, + { + "epoch": 0.33077126954677977, + "grad_norm": 3.9147934913635254, + "learning_rate": 4.867587612244064e-06, + "loss": 0.3476, + "step": 156 + }, + { + "epoch": 0.33289159819772063, + "grad_norm": 2.4226462841033936, + "learning_rate": 4.865783994016261e-06, + "loss": 0.3471, + "step": 157 + }, + { + "epoch": 0.33501192684866155, + "grad_norm": 2.4413650035858154, + "learning_rate": 4.863968513750456e-06, + "loss": 0.3026, + "step": 158 + }, + { + "epoch": 0.33713225549960246, + "grad_norm": 2.6878299713134766, + "learning_rate": 4.862141180549464e-06, + "loss": 0.3127, + "step": 159 + }, + { + "epoch": 0.3392525841505433, + "grad_norm": 2.855107545852661, + "learning_rate": 4.86030200357553e-06, + "loss": 0.2059, + "step": 160 + }, + { + "epoch": 0.34137291280148424, + "grad_norm": 2.976635217666626, + "learning_rate": 4.858450992050287e-06, + "loss": 0.2706, + "step": 161 + }, + { + "epoch": 0.3434932414524251, + "grad_norm": 4.121407508850098, + "learning_rate": 4.856588155254704e-06, + "loss": 0.2539, + "step": 162 + }, + { + "epoch": 0.345613570103366, + "grad_norm": 0.857638955116272, + "learning_rate": 4.854713502529042e-06, + "loss": 0.2923, + "step": 163 + }, + { + "epoch": 0.34773389875430694, + "grad_norm": 1.6652028560638428, + "learning_rate": 4.852827043272808e-06, + "loss": 0.2357, + "step": 164 + }, + { + "epoch": 0.3498542274052478, + "grad_norm": 3.286330223083496, + "learning_rate": 4.850928786944706e-06, + "loss": 0.2745, + "step": 165 + }, + { + "epoch": 0.3519745560561887, + "grad_norm": 3.9806864261627197, + "learning_rate": 4.84901874306259e-06, + "loss": 0.2503, + "step": 166 + }, + { + "epoch": 0.35409488470712963, + "grad_norm": 2.8622264862060547, + "learning_rate": 4.847096921203419e-06, + "loss": 0.3615, + "step": 167 + }, + { + "epoch": 0.3562152133580705, + "grad_norm": 3.0431885719299316, + "learning_rate": 4.845163331003205e-06, + "loss": 0.187, + "step": 168 + }, + { + "epoch": 0.3583355420090114, + "grad_norm": 1.8177791833877563, + "learning_rate": 4.843217982156968e-06, + "loss": 0.2641, + "step": 169 + }, + { + "epoch": 0.36045587065995227, + "grad_norm": 0.6192033290863037, + "learning_rate": 4.841260884418682e-06, + "loss": 0.2323, + "step": 170 + }, + { + "epoch": 0.3625761993108932, + "grad_norm": 4.052712917327881, + "learning_rate": 4.839292047601234e-06, + "loss": 0.3339, + "step": 171 + }, + { + "epoch": 0.3646965279618341, + "grad_norm": 1.8390997648239136, + "learning_rate": 4.83731148157637e-06, + "loss": 0.2844, + "step": 172 + }, + { + "epoch": 0.36681685661277497, + "grad_norm": 1.4040610790252686, + "learning_rate": 4.835319196274646e-06, + "loss": 0.3137, + "step": 173 + }, + { + "epoch": 0.3689371852637159, + "grad_norm": 3.0023269653320312, + "learning_rate": 4.833315201685375e-06, + "loss": 0.2336, + "step": 174 + }, + { + "epoch": 0.37105751391465674, + "grad_norm": 1.7594302892684937, + "learning_rate": 4.831299507856587e-06, + "loss": 0.2312, + "step": 175 + }, + { + "epoch": 0.37317784256559766, + "grad_norm": 1.7524633407592773, + "learning_rate": 4.829272124894967e-06, + "loss": 0.3141, + "step": 176 + }, + { + "epoch": 0.3752981712165386, + "grad_norm": 9.093369483947754, + "learning_rate": 4.827233062965811e-06, + "loss": 0.259, + "step": 177 + }, + { + "epoch": 0.37741849986747944, + "grad_norm": 2.2024335861206055, + "learning_rate": 4.82518233229297e-06, + "loss": 0.23, + "step": 178 + }, + { + "epoch": 0.37953882851842036, + "grad_norm": 0.7254531979560852, + "learning_rate": 4.823119943158809e-06, + "loss": 0.2643, + "step": 179 + }, + { + "epoch": 0.3816591571693613, + "grad_norm": 2.181795120239258, + "learning_rate": 4.821045905904143e-06, + "loss": 0.2215, + "step": 180 + }, + { + "epoch": 0.38377948582030214, + "grad_norm": 1.5816072225570679, + "learning_rate": 4.818960230928192e-06, + "loss": 0.2168, + "step": 181 + }, + { + "epoch": 0.38589981447124305, + "grad_norm": 2.4816792011260986, + "learning_rate": 4.816862928688528e-06, + "loss": 0.2618, + "step": 182 + }, + { + "epoch": 0.3880201431221839, + "grad_norm": 2.069082260131836, + "learning_rate": 4.814754009701023e-06, + "loss": 0.3713, + "step": 183 + }, + { + "epoch": 0.39014047177312483, + "grad_norm": 2.61807918548584, + "learning_rate": 4.8126334845397914e-06, + "loss": 0.3274, + "step": 184 + }, + { + "epoch": 0.39226080042406575, + "grad_norm": 2.7736072540283203, + "learning_rate": 4.8105013638371454e-06, + "loss": 0.231, + "step": 185 + }, + { + "epoch": 0.3943811290750066, + "grad_norm": 3.6297597885131836, + "learning_rate": 4.8083576582835366e-06, + "loss": 0.3412, + "step": 186 + }, + { + "epoch": 0.3965014577259475, + "grad_norm": 2.2494869232177734, + "learning_rate": 4.8062023786274996e-06, + "loss": 0.247, + "step": 187 + }, + { + "epoch": 0.39862178637688844, + "grad_norm": 1.3295131921768188, + "learning_rate": 4.804035535675606e-06, + "loss": 0.2412, + "step": 188 + }, + { + "epoch": 0.4007421150278293, + "grad_norm": 2.058772325515747, + "learning_rate": 4.801857140292402e-06, + "loss": 0.2943, + "step": 189 + }, + { + "epoch": 0.4028624436787702, + "grad_norm": 1.5720592737197876, + "learning_rate": 4.799667203400361e-06, + "loss": 0.274, + "step": 190 + }, + { + "epoch": 0.4049827723297111, + "grad_norm": 2.5041348934173584, + "learning_rate": 4.7974657359798224e-06, + "loss": 0.245, + "step": 191 + }, + { + "epoch": 0.407103100980652, + "grad_norm": 1.9566255807876587, + "learning_rate": 4.795252749068942e-06, + "loss": 0.3203, + "step": 192 + }, + { + "epoch": 0.4092234296315929, + "grad_norm": 4.478713035583496, + "learning_rate": 4.793028253763633e-06, + "loss": 0.3274, + "step": 193 + }, + { + "epoch": 0.4113437582825338, + "grad_norm": 3.3313329219818115, + "learning_rate": 4.790792261217513e-06, + "loss": 0.3502, + "step": 194 + }, + { + "epoch": 0.4134640869334747, + "grad_norm": 2.875757932662964, + "learning_rate": 4.7885447826418435e-06, + "loss": 0.4093, + "step": 195 + }, + { + "epoch": 0.4155844155844156, + "grad_norm": 2.094299793243408, + "learning_rate": 4.786285829305481e-06, + "loss": 0.3394, + "step": 196 + }, + { + "epoch": 0.4177047442353565, + "grad_norm": 3.40802264213562, + "learning_rate": 4.784015412534816e-06, + "loss": 0.2579, + "step": 197 + }, + { + "epoch": 0.4198250728862974, + "grad_norm": 2.5901896953582764, + "learning_rate": 4.781733543713714e-06, + "loss": 0.3256, + "step": 198 + }, + { + "epoch": 0.42194540153723825, + "grad_norm": 2.649927854537964, + "learning_rate": 4.779440234283461e-06, + "loss": 0.2552, + "step": 199 + }, + { + "epoch": 0.42406573018817917, + "grad_norm": 2.827615261077881, + "learning_rate": 4.77713549574271e-06, + "loss": 0.345, + "step": 200 + }, + { + "epoch": 0.4261860588391201, + "grad_norm": 2.3520429134368896, + "learning_rate": 4.774819339647415e-06, + "loss": 0.3555, + "step": 201 + }, + { + "epoch": 0.42830638749006095, + "grad_norm": 2.04105281829834, + "learning_rate": 4.772491777610782e-06, + "loss": 0.3845, + "step": 202 + }, + { + "epoch": 0.43042671614100186, + "grad_norm": 2.4335427284240723, + "learning_rate": 4.770152821303203e-06, + "loss": 0.226, + "step": 203 + }, + { + "epoch": 0.4325470447919427, + "grad_norm": 3.064467191696167, + "learning_rate": 4.767802482452202e-06, + "loss": 0.2998, + "step": 204 + }, + { + "epoch": 0.43466737344288364, + "grad_norm": 1.1668577194213867, + "learning_rate": 4.7654407728423745e-06, + "loss": 0.2627, + "step": 205 + }, + { + "epoch": 0.43678770209382456, + "grad_norm": 1.9054539203643799, + "learning_rate": 4.763067704315331e-06, + "loss": 0.3959, + "step": 206 + }, + { + "epoch": 0.4389080307447654, + "grad_norm": 2.3456785678863525, + "learning_rate": 4.760683288769634e-06, + "loss": 0.3076, + "step": 207 + }, + { + "epoch": 0.44102835939570634, + "grad_norm": 3.0187900066375732, + "learning_rate": 4.758287538160738e-06, + "loss": 0.2894, + "step": 208 + }, + { + "epoch": 0.44314868804664725, + "grad_norm": 2.9057319164276123, + "learning_rate": 4.755880464500936e-06, + "loss": 0.289, + "step": 209 + }, + { + "epoch": 0.4452690166975881, + "grad_norm": 2.7487642765045166, + "learning_rate": 4.753462079859291e-06, + "loss": 0.2759, + "step": 210 + }, + { + "epoch": 0.44738934534852903, + "grad_norm": 1.8765803575515747, + "learning_rate": 4.7510323963615815e-06, + "loss": 0.2892, + "step": 211 + }, + { + "epoch": 0.4495096739994699, + "grad_norm": 1.8452672958374023, + "learning_rate": 4.748591426190237e-06, + "loss": 0.2232, + "step": 212 + }, + { + "epoch": 0.4516300026504108, + "grad_norm": 3.8514230251312256, + "learning_rate": 4.746139181584278e-06, + "loss": 0.2904, + "step": 213 + }, + { + "epoch": 0.45375033130135173, + "grad_norm": 1.5355229377746582, + "learning_rate": 4.743675674839258e-06, + "loss": 0.3108, + "step": 214 + }, + { + "epoch": 0.4558706599522926, + "grad_norm": 2.429868698120117, + "learning_rate": 4.741200918307194e-06, + "loss": 0.3254, + "step": 215 + }, + { + "epoch": 0.4579909886032335, + "grad_norm": 1.8861596584320068, + "learning_rate": 4.738714924396514e-06, + "loss": 0.3318, + "step": 216 + }, + { + "epoch": 0.4601113172541744, + "grad_norm": 2.709230661392212, + "learning_rate": 4.736217705571989e-06, + "loss": 0.2817, + "step": 217 + }, + { + "epoch": 0.4622316459051153, + "grad_norm": 1.2253323793411255, + "learning_rate": 4.73370927435467e-06, + "loss": 0.3168, + "step": 218 + }, + { + "epoch": 0.4643519745560562, + "grad_norm": 2.5226621627807617, + "learning_rate": 4.731189643321829e-06, + "loss": 0.263, + "step": 219 + }, + { + "epoch": 0.46647230320699706, + "grad_norm": 3.8697330951690674, + "learning_rate": 4.728658825106891e-06, + "loss": 0.237, + "step": 220 + }, + { + "epoch": 0.468592631857938, + "grad_norm": 1.7124079465866089, + "learning_rate": 4.726116832399376e-06, + "loss": 0.1574, + "step": 221 + }, + { + "epoch": 0.4707129605088789, + "grad_norm": 1.372372031211853, + "learning_rate": 4.723563677944833e-06, + "loss": 0.287, + "step": 222 + }, + { + "epoch": 0.47283328915981976, + "grad_norm": 1.5783618688583374, + "learning_rate": 4.720999374544776e-06, + "loss": 0.2368, + "step": 223 + }, + { + "epoch": 0.4749536178107607, + "grad_norm": 2.918891191482544, + "learning_rate": 4.718423935056617e-06, + "loss": 0.3074, + "step": 224 + }, + { + "epoch": 0.47707394646170154, + "grad_norm": 2.4617486000061035, + "learning_rate": 4.715837372393607e-06, + "loss": 0.2073, + "step": 225 + }, + { + "epoch": 0.47919427511264245, + "grad_norm": 2.3654730319976807, + "learning_rate": 4.71323969952477e-06, + "loss": 0.2204, + "step": 226 + }, + { + "epoch": 0.48131460376358337, + "grad_norm": 2.3249452114105225, + "learning_rate": 4.7106309294748315e-06, + "loss": 0.378, + "step": 227 + }, + { + "epoch": 0.48343493241452423, + "grad_norm": 5.216866493225098, + "learning_rate": 4.708011075324163e-06, + "loss": 0.2746, + "step": 228 + }, + { + "epoch": 0.48555526106546515, + "grad_norm": 2.4934608936309814, + "learning_rate": 4.70538015020871e-06, + "loss": 0.3171, + "step": 229 + }, + { + "epoch": 0.48767558971640607, + "grad_norm": 3.2651522159576416, + "learning_rate": 4.702738167319927e-06, + "loss": 0.3478, + "step": 230 + }, + { + "epoch": 0.4897959183673469, + "grad_norm": 2.3438186645507812, + "learning_rate": 4.700085139904714e-06, + "loss": 0.1753, + "step": 231 + }, + { + "epoch": 0.49191624701828784, + "grad_norm": 3.3518893718719482, + "learning_rate": 4.697421081265346e-06, + "loss": 0.2202, + "step": 232 + }, + { + "epoch": 0.4940365756692287, + "grad_norm": 5.121367931365967, + "learning_rate": 4.6947460047594105e-06, + "loss": 0.2557, + "step": 233 + }, + { + "epoch": 0.4961569043201696, + "grad_norm": 2.5385594367980957, + "learning_rate": 4.692059923799736e-06, + "loss": 0.3656, + "step": 234 + }, + { + "epoch": 0.49827723297111054, + "grad_norm": 2.5510666370391846, + "learning_rate": 4.689362851854333e-06, + "loss": 0.3637, + "step": 235 + }, + { + "epoch": 0.5003975616220514, + "grad_norm": 2.288750171661377, + "learning_rate": 4.686654802446313e-06, + "loss": 0.2433, + "step": 236 + }, + { + "epoch": 0.5025178902729923, + "grad_norm": 2.547922372817993, + "learning_rate": 4.683935789153834e-06, + "loss": 0.3574, + "step": 237 + }, + { + "epoch": 0.5046382189239332, + "grad_norm": 1.7912276983261108, + "learning_rate": 4.681205825610025e-06, + "loss": 0.3007, + "step": 238 + }, + { + "epoch": 0.5067585475748742, + "grad_norm": 1.9286338090896606, + "learning_rate": 4.67846492550292e-06, + "loss": 0.2679, + "step": 239 + }, + { + "epoch": 0.508878876225815, + "grad_norm": 2.0864994525909424, + "learning_rate": 4.675713102575389e-06, + "loss": 0.423, + "step": 240 + }, + { + "epoch": 0.5109992048767559, + "grad_norm": 1.037505030632019, + "learning_rate": 4.672950370625067e-06, + "loss": 0.2192, + "step": 241 + }, + { + "epoch": 0.5131195335276968, + "grad_norm": 1.936712384223938, + "learning_rate": 4.670176743504291e-06, + "loss": 0.3557, + "step": 242 + }, + { + "epoch": 0.5152398621786377, + "grad_norm": 2.4721193313598633, + "learning_rate": 4.667392235120023e-06, + "loss": 0.2169, + "step": 243 + }, + { + "epoch": 0.5173601908295786, + "grad_norm": 2.0251030921936035, + "learning_rate": 4.664596859433784e-06, + "loss": 0.2279, + "step": 244 + }, + { + "epoch": 0.5194805194805194, + "grad_norm": 2.416062593460083, + "learning_rate": 4.661790630461585e-06, + "loss": 0.235, + "step": 245 + }, + { + "epoch": 0.5216008481314603, + "grad_norm": 2.3397867679595947, + "learning_rate": 4.658973562273853e-06, + "loss": 0.2745, + "step": 246 + }, + { + "epoch": 0.5237211767824013, + "grad_norm": 3.574948787689209, + "learning_rate": 4.6561456689953665e-06, + "loss": 0.2579, + "step": 247 + }, + { + "epoch": 0.5258415054333422, + "grad_norm": 2.3914096355438232, + "learning_rate": 4.653306964805178e-06, + "loss": 0.3445, + "step": 248 + }, + { + "epoch": 0.5279618340842831, + "grad_norm": 1.807157278060913, + "learning_rate": 4.650457463936547e-06, + "loss": 0.2752, + "step": 249 + }, + { + "epoch": 0.5300821627352239, + "grad_norm": 1.997169017791748, + "learning_rate": 4.647597180676866e-06, + "loss": 0.2539, + "step": 250 + }, + { + "epoch": 0.5322024913861648, + "grad_norm": 2.018228530883789, + "learning_rate": 4.644726129367594e-06, + "loss": 0.2548, + "step": 251 + }, + { + "epoch": 0.5343228200371057, + "grad_norm": 1.5280331373214722, + "learning_rate": 4.6418443244041775e-06, + "loss": 0.2473, + "step": 252 + }, + { + "epoch": 0.5364431486880467, + "grad_norm": 2.8328475952148438, + "learning_rate": 4.638951780235982e-06, + "loss": 0.2633, + "step": 253 + }, + { + "epoch": 0.5385634773389876, + "grad_norm": 1.2343734502792358, + "learning_rate": 4.636048511366222e-06, + "loss": 0.2015, + "step": 254 + }, + { + "epoch": 0.5406838059899285, + "grad_norm": 2.285114049911499, + "learning_rate": 4.633134532351883e-06, + "loss": 0.242, + "step": 255 + }, + { + "epoch": 0.5428041346408693, + "grad_norm": 1.9822317361831665, + "learning_rate": 4.630209857803653e-06, + "loss": 0.1624, + "step": 256 + }, + { + "epoch": 0.5449244632918102, + "grad_norm": 1.7463964223861694, + "learning_rate": 4.6272745023858445e-06, + "loss": 0.266, + "step": 257 + }, + { + "epoch": 0.5470447919427511, + "grad_norm": 1.835262656211853, + "learning_rate": 4.624328480816329e-06, + "loss": 0.2686, + "step": 258 + }, + { + "epoch": 0.549165120593692, + "grad_norm": 3.0902907848358154, + "learning_rate": 4.621371807866452e-06, + "loss": 0.2292, + "step": 259 + }, + { + "epoch": 0.551285449244633, + "grad_norm": 1.0292060375213623, + "learning_rate": 4.618404498360971e-06, + "loss": 0.1938, + "step": 260 + }, + { + "epoch": 0.5534057778955738, + "grad_norm": 1.2217211723327637, + "learning_rate": 4.6154265671779695e-06, + "loss": 0.2923, + "step": 261 + }, + { + "epoch": 0.5555261065465147, + "grad_norm": 0.7709723711013794, + "learning_rate": 4.612438029248792e-06, + "loss": 0.2513, + "step": 262 + }, + { + "epoch": 0.5576464351974556, + "grad_norm": 1.7595287561416626, + "learning_rate": 4.609438899557964e-06, + "loss": 0.1831, + "step": 263 + }, + { + "epoch": 0.5597667638483965, + "grad_norm": 1.169548749923706, + "learning_rate": 4.606429193143118e-06, + "loss": 0.3138, + "step": 264 + }, + { + "epoch": 0.5618870924993374, + "grad_norm": 3.089507579803467, + "learning_rate": 4.6034089250949184e-06, + "loss": 0.2822, + "step": 265 + }, + { + "epoch": 0.5640074211502782, + "grad_norm": 4.917386531829834, + "learning_rate": 4.600378110556985e-06, + "loss": 0.3735, + "step": 266 + }, + { + "epoch": 0.5661277498012192, + "grad_norm": 1.7424579858779907, + "learning_rate": 4.597336764725817e-06, + "loss": 0.2993, + "step": 267 + }, + { + "epoch": 0.5682480784521601, + "grad_norm": 3.4557604789733887, + "learning_rate": 4.594284902850721e-06, + "loss": 0.2737, + "step": 268 + }, + { + "epoch": 0.570368407103101, + "grad_norm": 1.8935794830322266, + "learning_rate": 4.591222540233726e-06, + "loss": 0.2369, + "step": 269 + }, + { + "epoch": 0.5724887357540419, + "grad_norm": 3.673444986343384, + "learning_rate": 4.5881496922295176e-06, + "loss": 0.2901, + "step": 270 + }, + { + "epoch": 0.5746090644049828, + "grad_norm": 2.3238632678985596, + "learning_rate": 4.585066374245349e-06, + "loss": 0.2711, + "step": 271 + }, + { + "epoch": 0.5767293930559236, + "grad_norm": 3.2917137145996094, + "learning_rate": 4.581972601740974e-06, + "loss": 0.202, + "step": 272 + }, + { + "epoch": 0.5788497217068646, + "grad_norm": 2.7594401836395264, + "learning_rate": 4.5788683902285644e-06, + "loss": 0.2347, + "step": 273 + }, + { + "epoch": 0.5809700503578055, + "grad_norm": 2.7743582725524902, + "learning_rate": 4.5757537552726315e-06, + "loss": 0.2795, + "step": 274 + }, + { + "epoch": 0.5830903790087464, + "grad_norm": 2.2841763496398926, + "learning_rate": 4.572628712489953e-06, + "loss": 0.3109, + "step": 275 + }, + { + "epoch": 0.5852107076596873, + "grad_norm": 2.3819563388824463, + "learning_rate": 4.569493277549487e-06, + "loss": 0.2391, + "step": 276 + }, + { + "epoch": 0.5873310363106281, + "grad_norm": 1.7411075830459595, + "learning_rate": 4.566347466172303e-06, + "loss": 0.1732, + "step": 277 + }, + { + "epoch": 0.589451364961569, + "grad_norm": 0.9455245733261108, + "learning_rate": 4.563191294131494e-06, + "loss": 0.2278, + "step": 278 + }, + { + "epoch": 0.5915716936125099, + "grad_norm": 1.5805822610855103, + "learning_rate": 4.560024777252103e-06, + "loss": 0.2911, + "step": 279 + }, + { + "epoch": 0.5936920222634509, + "grad_norm": 2.25376033782959, + "learning_rate": 4.556847931411042e-06, + "loss": 0.327, + "step": 280 + }, + { + "epoch": 0.5958123509143918, + "grad_norm": 3.1903650760650635, + "learning_rate": 4.553660772537011e-06, + "loss": 0.2883, + "step": 281 + }, + { + "epoch": 0.5979326795653326, + "grad_norm": 0.6892781853675842, + "learning_rate": 4.550463316610422e-06, + "loss": 0.2981, + "step": 282 + }, + { + "epoch": 0.6000530082162735, + "grad_norm": 3.3684580326080322, + "learning_rate": 4.547255579663314e-06, + "loss": 0.3031, + "step": 283 + }, + { + "epoch": 0.6021733368672144, + "grad_norm": 1.6963587999343872, + "learning_rate": 4.544037577779276e-06, + "loss": 0.3123, + "step": 284 + }, + { + "epoch": 0.6042936655181553, + "grad_norm": 2.595681667327881, + "learning_rate": 4.540809327093366e-06, + "loss": 0.2838, + "step": 285 + }, + { + "epoch": 0.6064139941690962, + "grad_norm": 3.383328437805176, + "learning_rate": 4.537570843792028e-06, + "loss": 0.3393, + "step": 286 + }, + { + "epoch": 0.608534322820037, + "grad_norm": 2.2130298614501953, + "learning_rate": 4.534322144113016e-06, + "loss": 0.2278, + "step": 287 + }, + { + "epoch": 0.610654651470978, + "grad_norm": 1.0078691244125366, + "learning_rate": 4.531063244345303e-06, + "loss": 0.2498, + "step": 288 + }, + { + "epoch": 0.6127749801219189, + "grad_norm": 0.9451133608818054, + "learning_rate": 4.52779416082901e-06, + "loss": 0.2269, + "step": 289 + }, + { + "epoch": 0.6148953087728598, + "grad_norm": 1.5240414142608643, + "learning_rate": 4.524514909955316e-06, + "loss": 0.3268, + "step": 290 + }, + { + "epoch": 0.6170156374238007, + "grad_norm": 1.5782700777053833, + "learning_rate": 4.521225508166383e-06, + "loss": 0.3014, + "step": 291 + }, + { + "epoch": 0.6191359660747416, + "grad_norm": 1.9916071891784668, + "learning_rate": 4.517925971955267e-06, + "loss": 0.2863, + "step": 292 + }, + { + "epoch": 0.6212562947256824, + "grad_norm": 1.9299273490905762, + "learning_rate": 4.514616317865838e-06, + "loss": 0.3096, + "step": 293 + }, + { + "epoch": 0.6233766233766234, + "grad_norm": 1.721146583557129, + "learning_rate": 4.5112965624926965e-06, + "loss": 0.284, + "step": 294 + }, + { + "epoch": 0.6254969520275643, + "grad_norm": 2.213865280151367, + "learning_rate": 4.507966722481093e-06, + "loss": 0.3541, + "step": 295 + }, + { + "epoch": 0.6276172806785052, + "grad_norm": 5.646588325500488, + "learning_rate": 4.504626814526841e-06, + "loss": 0.287, + "step": 296 + }, + { + "epoch": 0.6297376093294461, + "grad_norm": 1.9379154443740845, + "learning_rate": 4.501276855376235e-06, + "loss": 0.266, + "step": 297 + }, + { + "epoch": 0.6318579379803869, + "grad_norm": 4.37392520904541, + "learning_rate": 4.497916861825966e-06, + "loss": 0.3637, + "step": 298 + }, + { + "epoch": 0.6339782666313278, + "grad_norm": 1.6309797763824463, + "learning_rate": 4.494546850723037e-06, + "loss": 0.2331, + "step": 299 + }, + { + "epoch": 0.6360985952822688, + "grad_norm": 1.2552251815795898, + "learning_rate": 4.4911668389646795e-06, + "loss": 0.2661, + "step": 300 + }, + { + "epoch": 0.6382189239332097, + "grad_norm": 2.0839784145355225, + "learning_rate": 4.487776843498268e-06, + "loss": 0.2305, + "step": 301 + }, + { + "epoch": 0.6403392525841506, + "grad_norm": 2.6097898483276367, + "learning_rate": 4.484376881321237e-06, + "loss": 0.3038, + "step": 302 + }, + { + "epoch": 0.6424595812350914, + "grad_norm": 1.4699310064315796, + "learning_rate": 4.480966969480992e-06, + "loss": 0.1923, + "step": 303 + }, + { + "epoch": 0.6445799098860323, + "grad_norm": 1.1542787551879883, + "learning_rate": 4.477547125074826e-06, + "loss": 0.2522, + "step": 304 + }, + { + "epoch": 0.6467002385369732, + "grad_norm": 3.114525556564331, + "learning_rate": 4.474117365249835e-06, + "loss": 0.3941, + "step": 305 + }, + { + "epoch": 0.6488205671879141, + "grad_norm": 3.131681442260742, + "learning_rate": 4.4706777072028305e-06, + "loss": 0.2683, + "step": 306 + }, + { + "epoch": 0.6509408958388551, + "grad_norm": 2.522207021713257, + "learning_rate": 4.4672281681802536e-06, + "loss": 0.4248, + "step": 307 + }, + { + "epoch": 0.6530612244897959, + "grad_norm": 2.6396241188049316, + "learning_rate": 4.463768765478088e-06, + "loss": 0.3615, + "step": 308 + }, + { + "epoch": 0.6551815531407368, + "grad_norm": 1.8852202892303467, + "learning_rate": 4.460299516441777e-06, + "loss": 0.1891, + "step": 309 + }, + { + "epoch": 0.6573018817916777, + "grad_norm": 1.5633989572525024, + "learning_rate": 4.456820438466127e-06, + "loss": 0.3321, + "step": 310 + }, + { + "epoch": 0.6594222104426186, + "grad_norm": 0.9212223291397095, + "learning_rate": 4.453331548995235e-06, + "loss": 0.1842, + "step": 311 + }, + { + "epoch": 0.6615425390935595, + "grad_norm": 0.9008169174194336, + "learning_rate": 4.449832865522386e-06, + "loss": 0.2623, + "step": 312 + }, + { + "epoch": 0.6636628677445005, + "grad_norm": 2.3239521980285645, + "learning_rate": 4.446324405589973e-06, + "loss": 0.2996, + "step": 313 + }, + { + "epoch": 0.6657831963954413, + "grad_norm": 1.245194911956787, + "learning_rate": 4.442806186789414e-06, + "loss": 0.292, + "step": 314 + }, + { + "epoch": 0.6679035250463822, + "grad_norm": 1.7970019578933716, + "learning_rate": 4.43927822676105e-06, + "loss": 0.3205, + "step": 315 + }, + { + "epoch": 0.6700238536973231, + "grad_norm": 2.037053346633911, + "learning_rate": 4.43574054319407e-06, + "loss": 0.3059, + "step": 316 + }, + { + "epoch": 0.672144182348264, + "grad_norm": 2.7384984493255615, + "learning_rate": 4.432193153826414e-06, + "loss": 0.1772, + "step": 317 + }, + { + "epoch": 0.6742645109992049, + "grad_norm": 2.5001444816589355, + "learning_rate": 4.428636076444689e-06, + "loss": 0.2689, + "step": 318 + }, + { + "epoch": 0.6763848396501457, + "grad_norm": 2.1559765338897705, + "learning_rate": 4.425069328884076e-06, + "loss": 0.3262, + "step": 319 + }, + { + "epoch": 0.6785051683010866, + "grad_norm": 2.2558753490448, + "learning_rate": 4.421492929028243e-06, + "loss": 0.2938, + "step": 320 + }, + { + "epoch": 0.6806254969520276, + "grad_norm": 2.5780105590820312, + "learning_rate": 4.417906894809254e-06, + "loss": 0.287, + "step": 321 + }, + { + "epoch": 0.6827458256029685, + "grad_norm": 1.2815518379211426, + "learning_rate": 4.41431124420748e-06, + "loss": 0.2534, + "step": 322 + }, + { + "epoch": 0.6848661542539094, + "grad_norm": 1.6378668546676636, + "learning_rate": 4.410705995251509e-06, + "loss": 0.2202, + "step": 323 + }, + { + "epoch": 0.6869864829048502, + "grad_norm": 1.0137518644332886, + "learning_rate": 4.4070911660180546e-06, + "loss": 0.2868, + "step": 324 + }, + { + "epoch": 0.6891068115557911, + "grad_norm": 1.8886064291000366, + "learning_rate": 4.403466774631867e-06, + "loss": 0.1661, + "step": 325 + }, + { + "epoch": 0.691227140206732, + "grad_norm": 1.7047724723815918, + "learning_rate": 4.39983283926564e-06, + "loss": 0.2195, + "step": 326 + }, + { + "epoch": 0.693347468857673, + "grad_norm": 3.3912291526794434, + "learning_rate": 4.3961893781399186e-06, + "loss": 0.2696, + "step": 327 + }, + { + "epoch": 0.6954677975086139, + "grad_norm": 1.9746174812316895, + "learning_rate": 4.392536409523015e-06, + "loss": 0.3592, + "step": 328 + }, + { + "epoch": 0.6975881261595547, + "grad_norm": 5.287510395050049, + "learning_rate": 4.388873951730909e-06, + "loss": 0.2301, + "step": 329 + }, + { + "epoch": 0.6997084548104956, + "grad_norm": 3.351943254470825, + "learning_rate": 4.385202023127158e-06, + "loss": 0.2445, + "step": 330 + }, + { + "epoch": 0.7018287834614365, + "grad_norm": 1.951226830482483, + "learning_rate": 4.381520642122808e-06, + "loss": 0.283, + "step": 331 + }, + { + "epoch": 0.7039491121123774, + "grad_norm": 2.763387441635132, + "learning_rate": 4.3778298271762995e-06, + "loss": 0.423, + "step": 332 + }, + { + "epoch": 0.7060694407633183, + "grad_norm": 5.014280796051025, + "learning_rate": 4.374129596793375e-06, + "loss": 0.3269, + "step": 333 + }, + { + "epoch": 0.7081897694142593, + "grad_norm": 1.114488124847412, + "learning_rate": 4.370419969526982e-06, + "loss": 0.2774, + "step": 334 + }, + { + "epoch": 0.7103100980652001, + "grad_norm": 2.432865619659424, + "learning_rate": 4.366700963977188e-06, + "loss": 0.2744, + "step": 335 + }, + { + "epoch": 0.712430426716141, + "grad_norm": 1.1525187492370605, + "learning_rate": 4.362972598791085e-06, + "loss": 0.3201, + "step": 336 + }, + { + "epoch": 0.7145507553670819, + "grad_norm": 2.6614933013916016, + "learning_rate": 4.3592348926626886e-06, + "loss": 0.1742, + "step": 337 + }, + { + "epoch": 0.7166710840180228, + "grad_norm": 3.2576396465301514, + "learning_rate": 4.355487864332853e-06, + "loss": 0.3311, + "step": 338 + }, + { + "epoch": 0.7187914126689637, + "grad_norm": 2.1801483631134033, + "learning_rate": 4.351731532589173e-06, + "loss": 0.2022, + "step": 339 + }, + { + "epoch": 0.7209117413199045, + "grad_norm": 2.8371381759643555, + "learning_rate": 4.347965916265893e-06, + "loss": 0.3076, + "step": 340 + }, + { + "epoch": 0.7230320699708455, + "grad_norm": 2.4353699684143066, + "learning_rate": 4.3441910342438076e-06, + "loss": 0.2187, + "step": 341 + }, + { + "epoch": 0.7251523986217864, + "grad_norm": 0.7535296678543091, + "learning_rate": 4.340406905450171e-06, + "loss": 0.282, + "step": 342 + }, + { + "epoch": 0.7272727272727273, + "grad_norm": 1.656532883644104, + "learning_rate": 4.3366135488586e-06, + "loss": 0.2898, + "step": 343 + }, + { + "epoch": 0.7293930559236682, + "grad_norm": 1.5099116563796997, + "learning_rate": 4.332810983488979e-06, + "loss": 0.2422, + "step": 344 + }, + { + "epoch": 0.731513384574609, + "grad_norm": 1.4573249816894531, + "learning_rate": 4.3289992284073675e-06, + "loss": 0.2781, + "step": 345 + }, + { + "epoch": 0.7336337132255499, + "grad_norm": 1.6948301792144775, + "learning_rate": 4.325178302725901e-06, + "loss": 0.1749, + "step": 346 + }, + { + "epoch": 0.7357540418764908, + "grad_norm": 2.298999547958374, + "learning_rate": 4.321348225602694e-06, + "loss": 0.287, + "step": 347 + }, + { + "epoch": 0.7378743705274318, + "grad_norm": 1.248860239982605, + "learning_rate": 4.31750901624175e-06, + "loss": 0.2698, + "step": 348 + }, + { + "epoch": 0.7399946991783727, + "grad_norm": 1.6918904781341553, + "learning_rate": 4.31366069389286e-06, + "loss": 0.2312, + "step": 349 + }, + { + "epoch": 0.7421150278293135, + "grad_norm": 3.1004738807678223, + "learning_rate": 4.309803277851507e-06, + "loss": 0.2886, + "step": 350 + }, + { + "epoch": 0.7442353564802544, + "grad_norm": 2.718191623687744, + "learning_rate": 4.305936787458769e-06, + "loss": 0.2501, + "step": 351 + }, + { + "epoch": 0.7463556851311953, + "grad_norm": 1.4747895002365112, + "learning_rate": 4.302061242101226e-06, + "loss": 0.1851, + "step": 352 + }, + { + "epoch": 0.7484760137821362, + "grad_norm": 1.5939568281173706, + "learning_rate": 4.2981766612108576e-06, + "loss": 0.2419, + "step": 353 + }, + { + "epoch": 0.7505963424330772, + "grad_norm": 1.2325273752212524, + "learning_rate": 4.294283064264947e-06, + "loss": 0.2165, + "step": 354 + }, + { + "epoch": 0.7527166710840181, + "grad_norm": 5.181772232055664, + "learning_rate": 4.290380470785984e-06, + "loss": 0.2562, + "step": 355 + }, + { + "epoch": 0.7548369997349589, + "grad_norm": 1.3235808610916138, + "learning_rate": 4.2864689003415675e-06, + "loss": 0.318, + "step": 356 + }, + { + "epoch": 0.7569573283858998, + "grad_norm": 2.194802761077881, + "learning_rate": 4.282548372544307e-06, + "loss": 0.2193, + "step": 357 + }, + { + "epoch": 0.7590776570368407, + "grad_norm": 2.330679178237915, + "learning_rate": 4.278618907051724e-06, + "loss": 0.2466, + "step": 358 + }, + { + "epoch": 0.7611979856877816, + "grad_norm": 2.1647789478302, + "learning_rate": 4.274680523566154e-06, + "loss": 0.2749, + "step": 359 + }, + { + "epoch": 0.7633183143387225, + "grad_norm": 1.5459215641021729, + "learning_rate": 4.270733241834647e-06, + "loss": 0.3133, + "step": 360 + }, + { + "epoch": 0.7654386429896634, + "grad_norm": 0.6741765141487122, + "learning_rate": 4.266777081648868e-06, + "loss": 0.3188, + "step": 361 + }, + { + "epoch": 0.7675589716406043, + "grad_norm": 2.7495875358581543, + "learning_rate": 4.262812062844999e-06, + "loss": 0.3409, + "step": 362 + }, + { + "epoch": 0.7696793002915452, + "grad_norm": 4.160212993621826, + "learning_rate": 4.25883820530364e-06, + "loss": 0.2538, + "step": 363 + }, + { + "epoch": 0.7717996289424861, + "grad_norm": 2.0317301750183105, + "learning_rate": 4.254855528949709e-06, + "loss": 0.2741, + "step": 364 + }, + { + "epoch": 0.773919957593427, + "grad_norm": 2.1977953910827637, + "learning_rate": 4.250864053752337e-06, + "loss": 0.2353, + "step": 365 + }, + { + "epoch": 0.7760402862443678, + "grad_norm": 3.028444290161133, + "learning_rate": 4.2468637997247794e-06, + "loss": 0.2585, + "step": 366 + }, + { + "epoch": 0.7781606148953087, + "grad_norm": 1.4199281930923462, + "learning_rate": 4.242854786924302e-06, + "loss": 0.2143, + "step": 367 + }, + { + "epoch": 0.7802809435462497, + "grad_norm": 1.7088114023208618, + "learning_rate": 4.238837035452092e-06, + "loss": 0.1835, + "step": 368 + }, + { + "epoch": 0.7824012721971906, + "grad_norm": 1.4326963424682617, + "learning_rate": 4.234810565453148e-06, + "loss": 0.2107, + "step": 369 + }, + { + "epoch": 0.7845216008481315, + "grad_norm": 1.337410569190979, + "learning_rate": 4.230775397116188e-06, + "loss": 0.2497, + "step": 370 + }, + { + "epoch": 0.7866419294990723, + "grad_norm": 1.4517322778701782, + "learning_rate": 4.2267315506735394e-06, + "loss": 0.2577, + "step": 371 + }, + { + "epoch": 0.7887622581500132, + "grad_norm": 0.9060394167900085, + "learning_rate": 4.2226790464010445e-06, + "loss": 0.1978, + "step": 372 + }, + { + "epoch": 0.7908825868009541, + "grad_norm": 2.3969204425811768, + "learning_rate": 4.218617904617953e-06, + "loss": 0.2462, + "step": 373 + }, + { + "epoch": 0.793002915451895, + "grad_norm": 2.8702633380889893, + "learning_rate": 4.2145481456868265e-06, + "loss": 0.274, + "step": 374 + }, + { + "epoch": 0.795123244102836, + "grad_norm": 1.4537705183029175, + "learning_rate": 4.210469790013431e-06, + "loss": 0.3099, + "step": 375 + }, + { + "epoch": 0.7972435727537769, + "grad_norm": 2.5505456924438477, + "learning_rate": 4.206382858046636e-06, + "loss": 0.4174, + "step": 376 + }, + { + "epoch": 0.7993639014047177, + "grad_norm": 0.903439462184906, + "learning_rate": 4.202287370278313e-06, + "loss": 0.2273, + "step": 377 + }, + { + "epoch": 0.8014842300556586, + "grad_norm": 2.118838310241699, + "learning_rate": 4.198183347243233e-06, + "loss": 0.1472, + "step": 378 + }, + { + "epoch": 0.8036045587065995, + "grad_norm": 1.7555965185165405, + "learning_rate": 4.194070809518963e-06, + "loss": 0.3014, + "step": 379 + }, + { + "epoch": 0.8057248873575404, + "grad_norm": 1.575334072113037, + "learning_rate": 4.1899497777257615e-06, + "loss": 0.2107, + "step": 380 + }, + { + "epoch": 0.8078452160084814, + "grad_norm": 1.020128607749939, + "learning_rate": 4.185820272526477e-06, + "loss": 0.2336, + "step": 381 + }, + { + "epoch": 0.8099655446594222, + "grad_norm": 2.3840348720550537, + "learning_rate": 4.181682314626443e-06, + "loss": 0.3076, + "step": 382 + }, + { + "epoch": 0.8120858733103631, + "grad_norm": 0.7766013741493225, + "learning_rate": 4.177535924773375e-06, + "loss": 0.2436, + "step": 383 + }, + { + "epoch": 0.814206201961304, + "grad_norm": 2.136934757232666, + "learning_rate": 4.173381123757268e-06, + "loss": 0.3278, + "step": 384 + }, + { + "epoch": 0.8163265306122449, + "grad_norm": 2.10295033454895, + "learning_rate": 4.169217932410288e-06, + "loss": 0.3002, + "step": 385 + }, + { + "epoch": 0.8184468592631858, + "grad_norm": 2.8707754611968994, + "learning_rate": 4.165046371606671e-06, + "loss": 0.2263, + "step": 386 + }, + { + "epoch": 0.8205671879141266, + "grad_norm": 2.254936933517456, + "learning_rate": 4.160866462262618e-06, + "loss": 0.2967, + "step": 387 + }, + { + "epoch": 0.8226875165650676, + "grad_norm": 1.71103036403656, + "learning_rate": 4.15667822533619e-06, + "loss": 0.2266, + "step": 388 + }, + { + "epoch": 0.8248078452160085, + "grad_norm": 3.3162853717803955, + "learning_rate": 4.152481681827201e-06, + "loss": 0.3302, + "step": 389 + }, + { + "epoch": 0.8269281738669494, + "grad_norm": 2.03659987449646, + "learning_rate": 4.1482768527771155e-06, + "loss": 0.2646, + "step": 390 + }, + { + "epoch": 0.8290485025178903, + "grad_norm": 3.0324466228485107, + "learning_rate": 4.14406375926894e-06, + "loss": 0.3638, + "step": 391 + }, + { + "epoch": 0.8311688311688312, + "grad_norm": 1.9642225503921509, + "learning_rate": 4.13984242242712e-06, + "loss": 0.1704, + "step": 392 + }, + { + "epoch": 0.833289159819772, + "grad_norm": 1.727362036705017, + "learning_rate": 4.135612863417435e-06, + "loss": 0.2594, + "step": 393 + }, + { + "epoch": 0.835409488470713, + "grad_norm": 1.6325123310089111, + "learning_rate": 4.131375103446889e-06, + "loss": 0.2068, + "step": 394 + }, + { + "epoch": 0.8375298171216539, + "grad_norm": 1.1266484260559082, + "learning_rate": 4.127129163763601e-06, + "loss": 0.1623, + "step": 395 + }, + { + "epoch": 0.8396501457725948, + "grad_norm": 0.7224255800247192, + "learning_rate": 4.122875065656712e-06, + "loss": 0.1622, + "step": 396 + }, + { + "epoch": 0.8417704744235357, + "grad_norm": 2.530782699584961, + "learning_rate": 4.118612830456262e-06, + "loss": 0.3365, + "step": 397 + }, + { + "epoch": 0.8438908030744765, + "grad_norm": 2.0396225452423096, + "learning_rate": 4.114342479533094e-06, + "loss": 0.2857, + "step": 398 + }, + { + "epoch": 0.8460111317254174, + "grad_norm": 1.927078127861023, + "learning_rate": 4.110064034298741e-06, + "loss": 0.2944, + "step": 399 + }, + { + "epoch": 0.8481314603763583, + "grad_norm": 3.6908702850341797, + "learning_rate": 4.105777516205324e-06, + "loss": 0.2156, + "step": 400 + }, + { + "epoch": 0.8502517890272993, + "grad_norm": 0.6398283243179321, + "learning_rate": 4.101482946745438e-06, + "loss": 0.2235, + "step": 401 + }, + { + "epoch": 0.8523721176782402, + "grad_norm": 1.541572093963623, + "learning_rate": 4.09718034745205e-06, + "loss": 0.1273, + "step": 402 + }, + { + "epoch": 0.854492446329181, + "grad_norm": 3.8959381580352783, + "learning_rate": 4.092869739898386e-06, + "loss": 0.3338, + "step": 403 + }, + { + "epoch": 0.8566127749801219, + "grad_norm": 1.9765669107437134, + "learning_rate": 4.0885511456978275e-06, + "loss": 0.2359, + "step": 404 + }, + { + "epoch": 0.8587331036310628, + "grad_norm": 2.276289939880371, + "learning_rate": 4.084224586503801e-06, + "loss": 0.2267, + "step": 405 + }, + { + "epoch": 0.8608534322820037, + "grad_norm": 0.6204816102981567, + "learning_rate": 4.0798900840096694e-06, + "loss": 0.1329, + "step": 406 + }, + { + "epoch": 0.8629737609329446, + "grad_norm": 1.452314853668213, + "learning_rate": 4.075547659948621e-06, + "loss": 0.2221, + "step": 407 + }, + { + "epoch": 0.8650940895838855, + "grad_norm": 1.0840950012207031, + "learning_rate": 4.071197336093566e-06, + "loss": 0.3571, + "step": 408 + }, + { + "epoch": 0.8672144182348264, + "grad_norm": 3.603943347930908, + "learning_rate": 4.0668391342570225e-06, + "loss": 0.247, + "step": 409 + }, + { + "epoch": 0.8693347468857673, + "grad_norm": 1.4998263120651245, + "learning_rate": 4.062473076291009e-06, + "loss": 0.2483, + "step": 410 + }, + { + "epoch": 0.8714550755367082, + "grad_norm": 1.4034696817398071, + "learning_rate": 4.058099184086934e-06, + "loss": 0.2748, + "step": 411 + }, + { + "epoch": 0.8735754041876491, + "grad_norm": 1.1534749269485474, + "learning_rate": 4.05371747957549e-06, + "loss": 0.1534, + "step": 412 + }, + { + "epoch": 0.87569573283859, + "grad_norm": 1.709837555885315, + "learning_rate": 4.049327984726535e-06, + "loss": 0.3573, + "step": 413 + }, + { + "epoch": 0.8778160614895308, + "grad_norm": 1.9228962659835815, + "learning_rate": 4.044930721548992e-06, + "loss": 0.3242, + "step": 414 + }, + { + "epoch": 0.8799363901404718, + "grad_norm": 2.2846219539642334, + "learning_rate": 4.040525712090733e-06, + "loss": 0.2101, + "step": 415 + }, + { + "epoch": 0.8820567187914127, + "grad_norm": 2.0104122161865234, + "learning_rate": 4.0361129784384705e-06, + "loss": 0.2115, + "step": 416 + }, + { + "epoch": 0.8841770474423536, + "grad_norm": 2.7587649822235107, + "learning_rate": 4.031692542717645e-06, + "loss": 0.274, + "step": 417 + }, + { + "epoch": 0.8862973760932945, + "grad_norm": 4.8226542472839355, + "learning_rate": 4.027264427092316e-06, + "loss": 0.4542, + "step": 418 + }, + { + "epoch": 0.8884177047442353, + "grad_norm": 2.651845693588257, + "learning_rate": 4.022828653765049e-06, + "loss": 0.2008, + "step": 419 + }, + { + "epoch": 0.8905380333951762, + "grad_norm": 1.5795021057128906, + "learning_rate": 4.018385244976807e-06, + "loss": 0.2777, + "step": 420 + }, + { + "epoch": 0.8926583620461171, + "grad_norm": 1.470374584197998, + "learning_rate": 4.0139342230068355e-06, + "loss": 0.2378, + "step": 421 + }, + { + "epoch": 0.8947786906970581, + "grad_norm": 2.2073006629943848, + "learning_rate": 4.009475610172553e-06, + "loss": 0.2469, + "step": 422 + }, + { + "epoch": 0.896899019347999, + "grad_norm": 3.0384535789489746, + "learning_rate": 4.005009428829439e-06, + "loss": 0.2247, + "step": 423 + }, + { + "epoch": 0.8990193479989398, + "grad_norm": 1.5634294748306274, + "learning_rate": 4.0005357013709215e-06, + "loss": 0.2117, + "step": 424 + }, + { + "epoch": 0.9011396766498807, + "grad_norm": 0.9764052033424377, + "learning_rate": 3.996054450228263e-06, + "loss": 0.2591, + "step": 425 + }, + { + "epoch": 0.9032600053008216, + "grad_norm": 1.669441819190979, + "learning_rate": 3.991565697870453e-06, + "loss": 0.2905, + "step": 426 + }, + { + "epoch": 0.9053803339517625, + "grad_norm": 2.682272434234619, + "learning_rate": 3.987069466804089e-06, + "loss": 0.298, + "step": 427 + }, + { + "epoch": 0.9075006626027035, + "grad_norm": 0.5667883157730103, + "learning_rate": 3.982565779573269e-06, + "loss": 0.4034, + "step": 428 + }, + { + "epoch": 0.9096209912536443, + "grad_norm": 2.6494028568267822, + "learning_rate": 3.978054658759474e-06, + "loss": 0.2176, + "step": 429 + }, + { + "epoch": 0.9117413199045852, + "grad_norm": 1.3368819952011108, + "learning_rate": 3.973536126981459e-06, + "loss": 0.2228, + "step": 430 + }, + { + "epoch": 0.9138616485555261, + "grad_norm": 2.0899736881256104, + "learning_rate": 3.969010206895136e-06, + "loss": 0.2471, + "step": 431 + }, + { + "epoch": 0.915981977206467, + "grad_norm": 0.29745158553123474, + "learning_rate": 3.964476921193464e-06, + "loss": 0.1858, + "step": 432 + }, + { + "epoch": 0.9181023058574079, + "grad_norm": 2.4237589836120605, + "learning_rate": 3.9599362926063315e-06, + "loss": 0.2178, + "step": 433 + }, + { + "epoch": 0.9202226345083488, + "grad_norm": 2.9499125480651855, + "learning_rate": 3.955388343900443e-06, + "loss": 0.2695, + "step": 434 + }, + { + "epoch": 0.9223429631592897, + "grad_norm": 1.6062681674957275, + "learning_rate": 3.950833097879208e-06, + "loss": 0.2193, + "step": 435 + }, + { + "epoch": 0.9244632918102306, + "grad_norm": 3.3054378032684326, + "learning_rate": 3.946270577382626e-06, + "loss": 0.2479, + "step": 436 + }, + { + "epoch": 0.9265836204611715, + "grad_norm": 1.836806058883667, + "learning_rate": 3.941700805287169e-06, + "loss": 0.3304, + "step": 437 + }, + { + "epoch": 0.9287039491121124, + "grad_norm": 2.154625654220581, + "learning_rate": 3.937123804505666e-06, + "loss": 0.2871, + "step": 438 + }, + { + "epoch": 0.9308242777630533, + "grad_norm": 1.1884167194366455, + "learning_rate": 3.932539597987196e-06, + "loss": 0.2042, + "step": 439 + }, + { + "epoch": 0.9329446064139941, + "grad_norm": 1.345928430557251, + "learning_rate": 3.927948208716964e-06, + "loss": 0.25, + "step": 440 + }, + { + "epoch": 0.935064935064935, + "grad_norm": 1.952118992805481, + "learning_rate": 3.92334965971619e-06, + "loss": 0.2686, + "step": 441 + }, + { + "epoch": 0.937185263715876, + "grad_norm": 2.034341335296631, + "learning_rate": 3.918743974041992e-06, + "loss": 0.2693, + "step": 442 + }, + { + "epoch": 0.9393055923668169, + "grad_norm": 1.5500835180282593, + "learning_rate": 3.914131174787274e-06, + "loss": 0.2578, + "step": 443 + }, + { + "epoch": 0.9414259210177578, + "grad_norm": 1.8623617887496948, + "learning_rate": 3.909511285080605e-06, + "loss": 0.278, + "step": 444 + }, + { + "epoch": 0.9435462496686986, + "grad_norm": 3.387428045272827, + "learning_rate": 3.9048843280861055e-06, + "loss": 0.2269, + "step": 445 + }, + { + "epoch": 0.9456665783196395, + "grad_norm": 3.092822551727295, + "learning_rate": 3.900250327003333e-06, + "loss": 0.2526, + "step": 446 + }, + { + "epoch": 0.9477869069705804, + "grad_norm": 2.328296422958374, + "learning_rate": 3.895609305067162e-06, + "loss": 0.2397, + "step": 447 + }, + { + "epoch": 0.9499072356215214, + "grad_norm": 1.579817533493042, + "learning_rate": 3.890961285547672e-06, + "loss": 0.2516, + "step": 448 + }, + { + "epoch": 0.9520275642724623, + "grad_norm": 1.765915870666504, + "learning_rate": 3.886306291750028e-06, + "loss": 0.2889, + "step": 449 + }, + { + "epoch": 0.9541478929234031, + "grad_norm": 2.5610663890838623, + "learning_rate": 3.881644347014361e-06, + "loss": 0.3136, + "step": 450 + }, + { + "epoch": 0.956268221574344, + "grad_norm": 1.9422125816345215, + "learning_rate": 3.876975474715656e-06, + "loss": 0.2424, + "step": 451 + }, + { + "epoch": 0.9583885502252849, + "grad_norm": 2.0714170932769775, + "learning_rate": 3.872299698263634e-06, + "loss": 0.2841, + "step": 452 + }, + { + "epoch": 0.9605088788762258, + "grad_norm": 1.0616906881332397, + "learning_rate": 3.867617041102633e-06, + "loss": 0.2141, + "step": 453 + }, + { + "epoch": 0.9626292075271667, + "grad_norm": 1.4508030414581299, + "learning_rate": 3.862927526711488e-06, + "loss": 0.2419, + "step": 454 + }, + { + "epoch": 0.9647495361781077, + "grad_norm": 1.6528363227844238, + "learning_rate": 3.858231178603421e-06, + "loss": 0.2179, + "step": 455 + }, + { + "epoch": 0.9668698648290485, + "grad_norm": 2.853685140609741, + "learning_rate": 3.853528020325913e-06, + "loss": 0.2963, + "step": 456 + }, + { + "epoch": 0.9689901934799894, + "grad_norm": 1.16892671585083, + "learning_rate": 3.848818075460595e-06, + "loss": 0.2386, + "step": 457 + }, + { + "epoch": 0.9711105221309303, + "grad_norm": 1.986411452293396, + "learning_rate": 3.8441013676231255e-06, + "loss": 0.1932, + "step": 458 + }, + { + "epoch": 0.9732308507818712, + "grad_norm": 1.9140475988388062, + "learning_rate": 3.83937792046307e-06, + "loss": 0.2455, + "step": 459 + }, + { + "epoch": 0.9753511794328121, + "grad_norm": 1.5750322341918945, + "learning_rate": 3.834647757663788e-06, + "loss": 0.2605, + "step": 460 + }, + { + "epoch": 0.9774715080837529, + "grad_norm": 1.1858994960784912, + "learning_rate": 3.829910902942309e-06, + "loss": 0.26, + "step": 461 + }, + { + "epoch": 0.9795918367346939, + "grad_norm": 3.8463196754455566, + "learning_rate": 3.825167380049218e-06, + "loss": 0.2549, + "step": 462 + }, + { + "epoch": 0.9817121653856348, + "grad_norm": 2.046649217605591, + "learning_rate": 3.820417212768531e-06, + "loss": 0.1391, + "step": 463 + }, + { + "epoch": 0.9838324940365757, + "grad_norm": 1.923967957496643, + "learning_rate": 3.8156604249175825e-06, + "loss": 0.305, + "step": 464 + }, + { + "epoch": 0.9859528226875166, + "grad_norm": 3.389587879180908, + "learning_rate": 3.810897040346899e-06, + "loss": 0.3457, + "step": 465 + }, + { + "epoch": 0.9880731513384574, + "grad_norm": 1.8285034894943237, + "learning_rate": 3.8061270829400876e-06, + "loss": 0.2261, + "step": 466 + }, + { + "epoch": 0.9901934799893983, + "grad_norm": 2.468703031539917, + "learning_rate": 3.801350576613706e-06, + "loss": 0.2855, + "step": 467 + }, + { + "epoch": 0.9923138086403392, + "grad_norm": 2.497868776321411, + "learning_rate": 3.796567545317153e-06, + "loss": 0.1904, + "step": 468 + }, + { + "epoch": 0.9944341372912802, + "grad_norm": 1.1878782510757446, + "learning_rate": 3.79177801303254e-06, + "loss": 0.2144, + "step": 469 + }, + { + "epoch": 0.9965544659422211, + "grad_norm": 1.0926648378372192, + "learning_rate": 3.7869820037745773e-06, + "loss": 0.1962, + "step": 470 + }, + { + "epoch": 0.9986747945931619, + "grad_norm": 1.597976803779602, + "learning_rate": 3.7821795415904482e-06, + "loss": 0.2887, + "step": 471 + }, + { + "epoch": 1.0015902464882056, + "grad_norm": 1.37874174118042, + "learning_rate": 3.777370650559693e-06, + "loss": 0.2933, + "step": 472 + }, + { + "epoch": 1.0037105751391466, + "grad_norm": 1.9284913539886475, + "learning_rate": 3.772555354794085e-06, + "loss": 0.2159, + "step": 473 + }, + { + "epoch": 1.0058309037900874, + "grad_norm": 3.890476942062378, + "learning_rate": 3.7677336784375107e-06, + "loss": 0.3206, + "step": 474 + }, + { + "epoch": 1.0079512324410285, + "grad_norm": 2.379439353942871, + "learning_rate": 3.76290564566585e-06, + "loss": 0.2397, + "step": 475 + }, + { + "epoch": 1.0100715610919693, + "grad_norm": 1.771033525466919, + "learning_rate": 3.7580712806868536e-06, + "loss": 0.2207, + "step": 476 + }, + { + "epoch": 1.01219188974291, + "grad_norm": 1.5666189193725586, + "learning_rate": 3.7532306077400206e-06, + "loss": 0.2817, + "step": 477 + }, + { + "epoch": 1.014312218393851, + "grad_norm": 0.6713786125183105, + "learning_rate": 3.7483836510964792e-06, + "loss": 0.2123, + "step": 478 + }, + { + "epoch": 1.016432547044792, + "grad_norm": 1.3699878454208374, + "learning_rate": 3.7435304350588643e-06, + "loss": 0.2889, + "step": 479 + }, + { + "epoch": 1.018552875695733, + "grad_norm": 1.747329592704773, + "learning_rate": 3.738670983961195e-06, + "loss": 0.2517, + "step": 480 + }, + { + "epoch": 1.0206732043466737, + "grad_norm": 2.277524471282959, + "learning_rate": 3.7338053221687533e-06, + "loss": 0.2451, + "step": 481 + }, + { + "epoch": 1.0227935329976146, + "grad_norm": 2.4319913387298584, + "learning_rate": 3.728933474077961e-06, + "loss": 0.2594, + "step": 482 + }, + { + "epoch": 1.0249138616485556, + "grad_norm": 1.2065045833587646, + "learning_rate": 3.7240554641162585e-06, + "loss": 0.2706, + "step": 483 + }, + { + "epoch": 1.0270341902994964, + "grad_norm": 1.6133732795715332, + "learning_rate": 3.7191713167419814e-06, + "loss": 0.2099, + "step": 484 + }, + { + "epoch": 1.0291545189504374, + "grad_norm": 2.497514486312866, + "learning_rate": 3.7142810564442388e-06, + "loss": 0.3406, + "step": 485 + }, + { + "epoch": 1.0312748476013782, + "grad_norm": 2.1485133171081543, + "learning_rate": 3.7093847077427904e-06, + "loss": 0.2251, + "step": 486 + }, + { + "epoch": 1.033395176252319, + "grad_norm": 2.118579149246216, + "learning_rate": 3.7044822951879224e-06, + "loss": 0.1466, + "step": 487 + }, + { + "epoch": 1.03551550490326, + "grad_norm": 1.457202672958374, + "learning_rate": 3.6995738433603234e-06, + "loss": 0.3749, + "step": 488 + }, + { + "epoch": 1.0376358335542009, + "grad_norm": 1.4717838764190674, + "learning_rate": 3.6946593768709667e-06, + "loss": 0.2145, + "step": 489 + }, + { + "epoch": 1.0397561622051419, + "grad_norm": 1.1702837944030762, + "learning_rate": 3.68973892036098e-06, + "loss": 0.1499, + "step": 490 + }, + { + "epoch": 1.0418764908560827, + "grad_norm": 1.9794777631759644, + "learning_rate": 3.684812498501528e-06, + "loss": 0.2445, + "step": 491 + }, + { + "epoch": 1.0439968195070235, + "grad_norm": 5.563566207885742, + "learning_rate": 3.6798801359936808e-06, + "loss": 0.2568, + "step": 492 + }, + { + "epoch": 1.0461171481579645, + "grad_norm": 1.5425770282745361, + "learning_rate": 3.6749418575683005e-06, + "loss": 0.1574, + "step": 493 + }, + { + "epoch": 1.0482374768089053, + "grad_norm": 2.789044141769409, + "learning_rate": 3.669997687985908e-06, + "loss": 0.2175, + "step": 494 + }, + { + "epoch": 1.0503578054598464, + "grad_norm": 2.0900280475616455, + "learning_rate": 3.665047652036563e-06, + "loss": 0.2276, + "step": 495 + }, + { + "epoch": 1.0524781341107872, + "grad_norm": 1.0383256673812866, + "learning_rate": 3.6600917745397403e-06, + "loss": 0.1829, + "step": 496 + }, + { + "epoch": 1.054598462761728, + "grad_norm": 1.5721336603164673, + "learning_rate": 3.6551300803442035e-06, + "loss": 0.1972, + "step": 497 + }, + { + "epoch": 1.056718791412669, + "grad_norm": 0.5374338030815125, + "learning_rate": 3.650162594327881e-06, + "loss": 0.1839, + "step": 498 + }, + { + "epoch": 1.0588391200636098, + "grad_norm": 2.335890054702759, + "learning_rate": 3.6451893413977413e-06, + "loss": 0.2619, + "step": 499 + }, + { + "epoch": 1.0609594487145508, + "grad_norm": 2.4904046058654785, + "learning_rate": 3.6402103464896676e-06, + "loss": 0.2554, + "step": 500 + }, + { + "epoch": 1.0630797773654916, + "grad_norm": 2.201873540878296, + "learning_rate": 3.6352256345683358e-06, + "loss": 0.2435, + "step": 501 + }, + { + "epoch": 1.0652001060164324, + "grad_norm": 1.2125855684280396, + "learning_rate": 3.630235230627085e-06, + "loss": 0.2017, + "step": 502 + }, + { + "epoch": 1.0673204346673735, + "grad_norm": 1.4849168062210083, + "learning_rate": 3.6252391596877923e-06, + "loss": 0.2504, + "step": 503 + }, + { + "epoch": 1.0694407633183143, + "grad_norm": 1.445149302482605, + "learning_rate": 3.620237446800754e-06, + "loss": 0.2066, + "step": 504 + }, + { + "epoch": 1.0715610919692553, + "grad_norm": 2.7715039253234863, + "learning_rate": 3.615230117044551e-06, + "loss": 0.3272, + "step": 505 + }, + { + "epoch": 1.0736814206201961, + "grad_norm": 1.57020902633667, + "learning_rate": 3.610217195525928e-06, + "loss": 0.1846, + "step": 506 + }, + { + "epoch": 1.075801749271137, + "grad_norm": 1.8669289350509644, + "learning_rate": 3.6051987073796684e-06, + "loss": 0.1817, + "step": 507 + }, + { + "epoch": 1.077922077922078, + "grad_norm": 1.7587169408798218, + "learning_rate": 3.600174677768465e-06, + "loss": 0.1909, + "step": 508 + }, + { + "epoch": 1.0800424065730188, + "grad_norm": 2.2706751823425293, + "learning_rate": 3.595145131882795e-06, + "loss": 0.2923, + "step": 509 + }, + { + "epoch": 1.0821627352239598, + "grad_norm": 1.3291329145431519, + "learning_rate": 3.5901100949407967e-06, + "loss": 0.1405, + "step": 510 + }, + { + "epoch": 1.0842830638749006, + "grad_norm": 1.3454506397247314, + "learning_rate": 3.5850695921881383e-06, + "loss": 0.1853, + "step": 511 + }, + { + "epoch": 1.0864033925258414, + "grad_norm": 1.4152384996414185, + "learning_rate": 3.5800236488978946e-06, + "loss": 0.1181, + "step": 512 + }, + { + "epoch": 1.0885237211767824, + "grad_norm": 3.2865519523620605, + "learning_rate": 3.574972290370419e-06, + "loss": 0.2086, + "step": 513 + }, + { + "epoch": 1.0906440498277232, + "grad_norm": 1.90707528591156, + "learning_rate": 3.569915541933217e-06, + "loss": 0.202, + "step": 514 + }, + { + "epoch": 1.0927643784786643, + "grad_norm": 1.0512449741363525, + "learning_rate": 3.564853428940819e-06, + "loss": 0.1522, + "step": 515 + }, + { + "epoch": 1.094884707129605, + "grad_norm": 1.8712276220321655, + "learning_rate": 3.5597859767746524e-06, + "loss": 0.1442, + "step": 516 + }, + { + "epoch": 1.0970050357805459, + "grad_norm": 0.539580225944519, + "learning_rate": 3.5547132108429163e-06, + "loss": 0.2109, + "step": 517 + }, + { + "epoch": 1.099125364431487, + "grad_norm": 0.8322845101356506, + "learning_rate": 3.5496351565804542e-06, + "loss": 0.2269, + "step": 518 + }, + { + "epoch": 1.1012456930824277, + "grad_norm": 3.7564239501953125, + "learning_rate": 3.5445518394486215e-06, + "loss": 0.2547, + "step": 519 + }, + { + "epoch": 1.1033660217333687, + "grad_norm": 1.5247739553451538, + "learning_rate": 3.5394632849351663e-06, + "loss": 0.1796, + "step": 520 + }, + { + "epoch": 1.1054863503843095, + "grad_norm": 2.528141498565674, + "learning_rate": 3.5343695185540927e-06, + "loss": 0.1957, + "step": 521 + }, + { + "epoch": 1.1076066790352506, + "grad_norm": 1.748477578163147, + "learning_rate": 3.5292705658455406e-06, + "loss": 0.2102, + "step": 522 + }, + { + "epoch": 1.1097270076861914, + "grad_norm": 2.315608024597168, + "learning_rate": 3.524166452375652e-06, + "loss": 0.1964, + "step": 523 + }, + { + "epoch": 1.1118473363371322, + "grad_norm": 3.3954997062683105, + "learning_rate": 3.5190572037364445e-06, + "loss": 0.2761, + "step": 524 + }, + { + "epoch": 1.1139676649880732, + "grad_norm": 2.1260130405426025, + "learning_rate": 3.513942845545686e-06, + "loss": 0.1444, + "step": 525 + }, + { + "epoch": 1.116087993639014, + "grad_norm": 3.0516886711120605, + "learning_rate": 3.5088234034467604e-06, + "loss": 0.2643, + "step": 526 + }, + { + "epoch": 1.118208322289955, + "grad_norm": 1.948144555091858, + "learning_rate": 3.5036989031085455e-06, + "loss": 0.1631, + "step": 527 + }, + { + "epoch": 1.1203286509408958, + "grad_norm": 3.5732581615448, + "learning_rate": 3.498569370225279e-06, + "loss": 0.2681, + "step": 528 + }, + { + "epoch": 1.1224489795918366, + "grad_norm": 2.172426462173462, + "learning_rate": 3.4934348305164324e-06, + "loss": 0.2678, + "step": 529 + }, + { + "epoch": 1.1245693082427777, + "grad_norm": 1.3486807346343994, + "learning_rate": 3.4882953097265814e-06, + "loss": 0.207, + "step": 530 + }, + { + "epoch": 1.1266896368937185, + "grad_norm": 0.8123583793640137, + "learning_rate": 3.4831508336252766e-06, + "loss": 0.205, + "step": 531 + }, + { + "epoch": 1.1288099655446595, + "grad_norm": 1.3351538181304932, + "learning_rate": 3.4780014280069153e-06, + "loss": 0.1029, + "step": 532 + }, + { + "epoch": 1.1309302941956003, + "grad_norm": 1.3779995441436768, + "learning_rate": 3.472847118690611e-06, + "loss": 0.2622, + "step": 533 + }, + { + "epoch": 1.1330506228465411, + "grad_norm": 1.0775947570800781, + "learning_rate": 3.467687931520064e-06, + "loss": 0.1952, + "step": 534 + }, + { + "epoch": 1.1351709514974822, + "grad_norm": 2.4154770374298096, + "learning_rate": 3.462523892363432e-06, + "loss": 0.1626, + "step": 535 + }, + { + "epoch": 1.137291280148423, + "grad_norm": 2.120819091796875, + "learning_rate": 3.4573550271132e-06, + "loss": 0.2611, + "step": 536 + }, + { + "epoch": 1.139411608799364, + "grad_norm": 1.0421452522277832, + "learning_rate": 3.4521813616860545e-06, + "loss": 0.1755, + "step": 537 + }, + { + "epoch": 1.1415319374503048, + "grad_norm": 2.1693243980407715, + "learning_rate": 3.4470029220227445e-06, + "loss": 0.299, + "step": 538 + }, + { + "epoch": 1.1436522661012458, + "grad_norm": 1.831677794456482, + "learning_rate": 3.441819734087963e-06, + "loss": 0.1295, + "step": 539 + }, + { + "epoch": 1.1457725947521866, + "grad_norm": 1.4600670337677002, + "learning_rate": 3.4366318238702063e-06, + "loss": 0.1765, + "step": 540 + }, + { + "epoch": 1.1478929234031274, + "grad_norm": 1.2835088968276978, + "learning_rate": 3.4314392173816495e-06, + "loss": 0.1285, + "step": 541 + }, + { + "epoch": 1.1500132520540685, + "grad_norm": 2.4741337299346924, + "learning_rate": 3.426241940658015e-06, + "loss": 0.3035, + "step": 542 + }, + { + "epoch": 1.1521335807050093, + "grad_norm": 1.5897051095962524, + "learning_rate": 3.421040019758443e-06, + "loss": 0.2073, + "step": 543 + }, + { + "epoch": 1.1542539093559503, + "grad_norm": 1.9757038354873657, + "learning_rate": 3.4158334807653577e-06, + "loss": 0.1855, + "step": 544 + }, + { + "epoch": 1.156374238006891, + "grad_norm": 2.5434279441833496, + "learning_rate": 3.4106223497843395e-06, + "loss": 0.2083, + "step": 545 + }, + { + "epoch": 1.158494566657832, + "grad_norm": 1.7457334995269775, + "learning_rate": 3.4054066529439916e-06, + "loss": 0.2057, + "step": 546 + }, + { + "epoch": 1.160614895308773, + "grad_norm": 2.125014305114746, + "learning_rate": 3.4001864163958125e-06, + "loss": 0.2622, + "step": 547 + }, + { + "epoch": 1.1627352239597137, + "grad_norm": 1.9452868700027466, + "learning_rate": 3.394961666314061e-06, + "loss": 0.2356, + "step": 548 + }, + { + "epoch": 1.1648555526106548, + "grad_norm": 1.8804444074630737, + "learning_rate": 3.389732428895629e-06, + "loss": 0.2543, + "step": 549 + }, + { + "epoch": 1.1669758812615956, + "grad_norm": 1.7958191633224487, + "learning_rate": 3.384498730359905e-06, + "loss": 0.1877, + "step": 550 + }, + { + "epoch": 1.1690962099125364, + "grad_norm": 2.4635379314422607, + "learning_rate": 3.379260596948646e-06, + "loss": 0.2394, + "step": 551 + }, + { + "epoch": 1.1712165385634774, + "grad_norm": 1.7975070476531982, + "learning_rate": 3.3740180549258496e-06, + "loss": 0.251, + "step": 552 + }, + { + "epoch": 1.1733368672144182, + "grad_norm": 1.1541494131088257, + "learning_rate": 3.368771130577613e-06, + "loss": 0.1074, + "step": 553 + }, + { + "epoch": 1.1754571958653592, + "grad_norm": 1.4837067127227783, + "learning_rate": 3.363519850212007e-06, + "loss": 0.1926, + "step": 554 + }, + { + "epoch": 1.1775775245163, + "grad_norm": 3.1769111156463623, + "learning_rate": 3.358264240158947e-06, + "loss": 0.1456, + "step": 555 + }, + { + "epoch": 1.1796978531672409, + "grad_norm": 1.6445987224578857, + "learning_rate": 3.353004326770055e-06, + "loss": 0.2445, + "step": 556 + }, + { + "epoch": 1.1818181818181819, + "grad_norm": 0.7336058020591736, + "learning_rate": 3.347740136418529e-06, + "loss": 0.2098, + "step": 557 + }, + { + "epoch": 1.1839385104691227, + "grad_norm": 0.853908121585846, + "learning_rate": 3.342471695499014e-06, + "loss": 0.2096, + "step": 558 + }, + { + "epoch": 1.1860588391200637, + "grad_norm": 0.5674437880516052, + "learning_rate": 3.3371990304274654e-06, + "loss": 0.2537, + "step": 559 + }, + { + "epoch": 1.1881791677710045, + "grad_norm": 1.4246636629104614, + "learning_rate": 3.33192216764102e-06, + "loss": 0.1266, + "step": 560 + }, + { + "epoch": 1.1902994964219453, + "grad_norm": 0.6851096153259277, + "learning_rate": 3.3266411335978618e-06, + "loss": 0.2436, + "step": 561 + }, + { + "epoch": 1.1924198250728864, + "grad_norm": 2.390455722808838, + "learning_rate": 3.3213559547770873e-06, + "loss": 0.272, + "step": 562 + }, + { + "epoch": 1.1945401537238272, + "grad_norm": 0.6653962731361389, + "learning_rate": 3.316066657678577e-06, + "loss": 0.1754, + "step": 563 + }, + { + "epoch": 1.1966604823747682, + "grad_norm": 3.227832555770874, + "learning_rate": 3.310773268822861e-06, + "loss": 0.2089, + "step": 564 + }, + { + "epoch": 1.198780811025709, + "grad_norm": 1.3733195066452026, + "learning_rate": 3.3054758147509837e-06, + "loss": 0.1492, + "step": 565 + }, + { + "epoch": 1.2009011396766498, + "grad_norm": 2.4527945518493652, + "learning_rate": 3.300174322024373e-06, + "loss": 0.1841, + "step": 566 + }, + { + "epoch": 1.2030214683275908, + "grad_norm": 1.4190953969955444, + "learning_rate": 3.294868817224707e-06, + "loss": 0.1904, + "step": 567 + }, + { + "epoch": 1.2051417969785316, + "grad_norm": 1.0891777276992798, + "learning_rate": 3.2895593269537806e-06, + "loss": 0.2079, + "step": 568 + }, + { + "epoch": 1.2072621256294727, + "grad_norm": 3.3715262413024902, + "learning_rate": 3.284245877833371e-06, + "loss": 0.2065, + "step": 569 + }, + { + "epoch": 1.2093824542804135, + "grad_norm": 1.8128390312194824, + "learning_rate": 3.2789284965051053e-06, + "loss": 0.1667, + "step": 570 + }, + { + "epoch": 1.2115027829313543, + "grad_norm": 2.6780452728271484, + "learning_rate": 3.2736072096303277e-06, + "loss": 0.1957, + "step": 571 + }, + { + "epoch": 1.2136231115822953, + "grad_norm": 1.6943888664245605, + "learning_rate": 3.268282043889963e-06, + "loss": 0.1717, + "step": 572 + }, + { + "epoch": 1.215743440233236, + "grad_norm": 2.704658269882202, + "learning_rate": 3.2629530259843862e-06, + "loss": 0.2692, + "step": 573 + }, + { + "epoch": 1.2178637688841771, + "grad_norm": 2.5095183849334717, + "learning_rate": 3.2576201826332864e-06, + "loss": 0.223, + "step": 574 + }, + { + "epoch": 1.219984097535118, + "grad_norm": 0.9887157678604126, + "learning_rate": 3.252283540575533e-06, + "loss": 0.2378, + "step": 575 + }, + { + "epoch": 1.2221044261860587, + "grad_norm": 1.8679485321044922, + "learning_rate": 3.2469431265690432e-06, + "loss": 0.3113, + "step": 576 + }, + { + "epoch": 1.2242247548369998, + "grad_norm": 2.1015641689300537, + "learning_rate": 3.2415989673906454e-06, + "loss": 0.2094, + "step": 577 + }, + { + "epoch": 1.2263450834879406, + "grad_norm": 3.247260808944702, + "learning_rate": 3.2362510898359484e-06, + "loss": 0.286, + "step": 578 + }, + { + "epoch": 1.2284654121388816, + "grad_norm": 2.1203606128692627, + "learning_rate": 3.2308995207192028e-06, + "loss": 0.1752, + "step": 579 + }, + { + "epoch": 1.2305857407898224, + "grad_norm": 3.4415900707244873, + "learning_rate": 3.225544286873169e-06, + "loss": 0.2184, + "step": 580 + }, + { + "epoch": 1.2327060694407632, + "grad_norm": 4.078723430633545, + "learning_rate": 3.220185415148984e-06, + "loss": 0.2721, + "step": 581 + }, + { + "epoch": 1.2348263980917042, + "grad_norm": 2.06363844871521, + "learning_rate": 3.2148229324160235e-06, + "loss": 0.3589, + "step": 582 + }, + { + "epoch": 1.236946726742645, + "grad_norm": 1.6750868558883667, + "learning_rate": 3.2094568655617692e-06, + "loss": 0.2667, + "step": 583 + }, + { + "epoch": 1.239067055393586, + "grad_norm": 2.284876823425293, + "learning_rate": 3.204087241491673e-06, + "loss": 0.2865, + "step": 584 + }, + { + "epoch": 1.2411873840445269, + "grad_norm": 1.0437135696411133, + "learning_rate": 3.198714087129024e-06, + "loss": 0.2693, + "step": 585 + }, + { + "epoch": 1.2433077126954677, + "grad_norm": 1.643754005432129, + "learning_rate": 3.1933374294148112e-06, + "loss": 0.1966, + "step": 586 + }, + { + "epoch": 1.2454280413464087, + "grad_norm": 0.8333995342254639, + "learning_rate": 3.187957295307591e-06, + "loss": 0.1645, + "step": 587 + }, + { + "epoch": 1.2475483699973495, + "grad_norm": 0.7705175280570984, + "learning_rate": 3.1825737117833465e-06, + "loss": 0.2136, + "step": 588 + }, + { + "epoch": 1.2496686986482906, + "grad_norm": 1.509788155555725, + "learning_rate": 3.177186705835361e-06, + "loss": 0.1812, + "step": 589 + }, + { + "epoch": 1.2517890272992314, + "grad_norm": 0.5960215926170349, + "learning_rate": 3.171796304474074e-06, + "loss": 0.1438, + "step": 590 + }, + { + "epoch": 1.2539093559501722, + "grad_norm": 2.9289567470550537, + "learning_rate": 3.1664025347269533e-06, + "loss": 0.224, + "step": 591 + }, + { + "epoch": 1.2560296846011132, + "grad_norm": 1.6071057319641113, + "learning_rate": 3.1610054236383526e-06, + "loss": 0.1427, + "step": 592 + }, + { + "epoch": 1.258150013252054, + "grad_norm": 2.266662359237671, + "learning_rate": 3.1556049982693794e-06, + "loss": 0.3275, + "step": 593 + }, + { + "epoch": 1.260270341902995, + "grad_norm": 0.8570841550827026, + "learning_rate": 3.1502012856977606e-06, + "loss": 0.228, + "step": 594 + }, + { + "epoch": 1.2623906705539358, + "grad_norm": 2.0917248725891113, + "learning_rate": 3.144794313017704e-06, + "loss": 0.1597, + "step": 595 + }, + { + "epoch": 1.2645109992048766, + "grad_norm": 2.6728296279907227, + "learning_rate": 3.1393841073397636e-06, + "loss": 0.2749, + "step": 596 + }, + { + "epoch": 1.2666313278558177, + "grad_norm": 0.8114733695983887, + "learning_rate": 3.1339706957907058e-06, + "loss": 0.2947, + "step": 597 + }, + { + "epoch": 1.2687516565067585, + "grad_norm": 3.9571282863616943, + "learning_rate": 3.128554105513367e-06, + "loss": 0.2116, + "step": 598 + }, + { + "epoch": 1.2708719851576995, + "grad_norm": 1.4085323810577393, + "learning_rate": 3.123134363666525e-06, + "loss": 0.3044, + "step": 599 + }, + { + "epoch": 1.2729923138086403, + "grad_norm": 1.3042069673538208, + "learning_rate": 3.117711497424759e-06, + "loss": 0.2365, + "step": 600 + }, + { + "epoch": 1.2751126424595811, + "grad_norm": 9.497270584106445, + "learning_rate": 3.1122855339783135e-06, + "loss": 0.2351, + "step": 601 + }, + { + "epoch": 1.2772329711105221, + "grad_norm": 2.055746078491211, + "learning_rate": 3.106856500532962e-06, + "loss": 0.2982, + "step": 602 + }, + { + "epoch": 1.279353299761463, + "grad_norm": 1.661730408668518, + "learning_rate": 3.1014244243098723e-06, + "loss": 0.2545, + "step": 603 + }, + { + "epoch": 1.281473628412404, + "grad_norm": 2.3598806858062744, + "learning_rate": 3.0959893325454675e-06, + "loss": 0.2081, + "step": 604 + }, + { + "epoch": 1.2835939570633448, + "grad_norm": 2.3903353214263916, + "learning_rate": 3.09055125249129e-06, + "loss": 0.2386, + "step": 605 + }, + { + "epoch": 1.2857142857142856, + "grad_norm": 2.1055004596710205, + "learning_rate": 3.0851102114138677e-06, + "loss": 0.123, + "step": 606 + }, + { + "epoch": 1.2878346143652266, + "grad_norm": 2.7721481323242188, + "learning_rate": 3.079666236594573e-06, + "loss": 0.2888, + "step": 607 + }, + { + "epoch": 1.2899549430161676, + "grad_norm": 1.0820283889770508, + "learning_rate": 3.0742193553294896e-06, + "loss": 0.4641, + "step": 608 + }, + { + "epoch": 1.2920752716671084, + "grad_norm": 1.0403881072998047, + "learning_rate": 3.0687695949292724e-06, + "loss": 0.1544, + "step": 609 + }, + { + "epoch": 1.2941956003180493, + "grad_norm": 1.1737229824066162, + "learning_rate": 3.063316982719014e-06, + "loss": 0.2008, + "step": 610 + }, + { + "epoch": 1.29631592896899, + "grad_norm": 1.0275263786315918, + "learning_rate": 3.0578615460381047e-06, + "loss": 0.1276, + "step": 611 + }, + { + "epoch": 1.298436257619931, + "grad_norm": 1.435745120048523, + "learning_rate": 3.0524033122400974e-06, + "loss": 0.256, + "step": 612 + }, + { + "epoch": 1.3005565862708721, + "grad_norm": 1.1113966703414917, + "learning_rate": 3.04694230869257e-06, + "loss": 0.2078, + "step": 613 + }, + { + "epoch": 1.302676914921813, + "grad_norm": 0.7453861236572266, + "learning_rate": 3.0414785627769884e-06, + "loss": 0.2638, + "step": 614 + }, + { + "epoch": 1.3047972435727537, + "grad_norm": 2.004967212677002, + "learning_rate": 3.036012101888565e-06, + "loss": 0.1654, + "step": 615 + }, + { + "epoch": 1.3069175722236945, + "grad_norm": 1.6051661968231201, + "learning_rate": 3.0305429534361304e-06, + "loss": 0.1348, + "step": 616 + }, + { + "epoch": 1.3090379008746356, + "grad_norm": 2.3148880004882812, + "learning_rate": 3.0250711448419867e-06, + "loss": 0.1318, + "step": 617 + }, + { + "epoch": 1.3111582295255766, + "grad_norm": 1.5317455530166626, + "learning_rate": 3.0195967035417765e-06, + "loss": 0.2081, + "step": 618 + }, + { + "epoch": 1.3132785581765174, + "grad_norm": 2.321281671524048, + "learning_rate": 3.014119656984341e-06, + "loss": 0.1596, + "step": 619 + }, + { + "epoch": 1.3153988868274582, + "grad_norm": 2.7379441261291504, + "learning_rate": 3.0086400326315853e-06, + "loss": 0.2253, + "step": 620 + }, + { + "epoch": 1.3175192154783992, + "grad_norm": 1.8512643575668335, + "learning_rate": 3.0031578579583375e-06, + "loss": 0.2683, + "step": 621 + }, + { + "epoch": 1.31963954412934, + "grad_norm": 3.2570621967315674, + "learning_rate": 2.9976731604522175e-06, + "loss": 0.1977, + "step": 622 + }, + { + "epoch": 1.321759872780281, + "grad_norm": 1.7534589767456055, + "learning_rate": 2.992185967613489e-06, + "loss": 0.171, + "step": 623 + }, + { + "epoch": 1.3238802014312219, + "grad_norm": 0.5050146579742432, + "learning_rate": 2.9866963069549315e-06, + "loss": 0.2047, + "step": 624 + }, + { + "epoch": 1.3260005300821627, + "grad_norm": 1.552862524986267, + "learning_rate": 2.9812042060016968e-06, + "loss": 0.1553, + "step": 625 + }, + { + "epoch": 1.3281208587331037, + "grad_norm": 1.942893385887146, + "learning_rate": 2.975709692291171e-06, + "loss": 0.1797, + "step": 626 + }, + { + "epoch": 1.3302411873840445, + "grad_norm": 1.2831542491912842, + "learning_rate": 2.9702127933728403e-06, + "loss": 0.16, + "step": 627 + }, + { + "epoch": 1.3323615160349855, + "grad_norm": 1.4484132528305054, + "learning_rate": 2.9647135368081488e-06, + "loss": 0.1923, + "step": 628 + }, + { + "epoch": 1.3344818446859263, + "grad_norm": 3.5186307430267334, + "learning_rate": 2.9592119501703607e-06, + "loss": 0.3373, + "step": 629 + }, + { + "epoch": 1.3366021733368671, + "grad_norm": 1.9385162591934204, + "learning_rate": 2.9537080610444274e-06, + "loss": 0.2003, + "step": 630 + }, + { + "epoch": 1.3387225019878082, + "grad_norm": 1.2267210483551025, + "learning_rate": 2.9482018970268395e-06, + "loss": 0.1736, + "step": 631 + }, + { + "epoch": 1.340842830638749, + "grad_norm": 0.9191475510597229, + "learning_rate": 2.9426934857254975e-06, + "loss": 0.2854, + "step": 632 + }, + { + "epoch": 1.34296315928969, + "grad_norm": 1.7922972440719604, + "learning_rate": 2.9371828547595695e-06, + "loss": 0.1429, + "step": 633 + }, + { + "epoch": 1.3450834879406308, + "grad_norm": 1.5351743698120117, + "learning_rate": 2.9316700317593507e-06, + "loss": 0.1374, + "step": 634 + }, + { + "epoch": 1.3472038165915716, + "grad_norm": 1.2162325382232666, + "learning_rate": 2.92615504436613e-06, + "loss": 0.1429, + "step": 635 + }, + { + "epoch": 1.3493241452425127, + "grad_norm": 1.7114899158477783, + "learning_rate": 2.920637920232047e-06, + "loss": 0.2211, + "step": 636 + }, + { + "epoch": 1.3514444738934535, + "grad_norm": 1.5543713569641113, + "learning_rate": 2.9151186870199556e-06, + "loss": 0.1726, + "step": 637 + }, + { + "epoch": 1.3535648025443945, + "grad_norm": 2.1046950817108154, + "learning_rate": 2.9095973724032832e-06, + "loss": 0.2319, + "step": 638 + }, + { + "epoch": 1.3556851311953353, + "grad_norm": 2.058473587036133, + "learning_rate": 2.9040740040658954e-06, + "loss": 0.2942, + "step": 639 + }, + { + "epoch": 1.357805459846276, + "grad_norm": 1.5705662965774536, + "learning_rate": 2.8985486097019543e-06, + "loss": 0.2206, + "step": 640 + }, + { + "epoch": 1.3599257884972171, + "grad_norm": 2.0310404300689697, + "learning_rate": 2.89302121701578e-06, + "loss": 0.1729, + "step": 641 + }, + { + "epoch": 1.362046117148158, + "grad_norm": 1.455135703086853, + "learning_rate": 2.8874918537217118e-06, + "loss": 0.26, + "step": 642 + }, + { + "epoch": 1.364166445799099, + "grad_norm": 2.1307947635650635, + "learning_rate": 2.8819605475439716e-06, + "loss": 0.1996, + "step": 643 + }, + { + "epoch": 1.3662867744500398, + "grad_norm": 1.6828829050064087, + "learning_rate": 2.876427326216521e-06, + "loss": 0.1706, + "step": 644 + }, + { + "epoch": 1.3684071031009806, + "grad_norm": 2.5645523071289062, + "learning_rate": 2.870892217482925e-06, + "loss": 0.2089, + "step": 645 + }, + { + "epoch": 1.3705274317519216, + "grad_norm": 3.5876777172088623, + "learning_rate": 2.8653552490962122e-06, + "loss": 0.3736, + "step": 646 + }, + { + "epoch": 1.3726477604028624, + "grad_norm": 1.182286262512207, + "learning_rate": 2.8598164488187354e-06, + "loss": 0.2904, + "step": 647 + }, + { + "epoch": 1.3747680890538034, + "grad_norm": 1.9589124917984009, + "learning_rate": 2.8542758444220303e-06, + "loss": 0.2265, + "step": 648 + }, + { + "epoch": 1.3768884177047442, + "grad_norm": 0.8725947737693787, + "learning_rate": 2.848733463686683e-06, + "loss": 0.2266, + "step": 649 + }, + { + "epoch": 1.379008746355685, + "grad_norm": 2.0674960613250732, + "learning_rate": 2.843189334402183e-06, + "loss": 0.1478, + "step": 650 + }, + { + "epoch": 1.381129075006626, + "grad_norm": 0.9025703072547913, + "learning_rate": 2.837643484366787e-06, + "loss": 0.1831, + "step": 651 + }, + { + "epoch": 1.3832494036575669, + "grad_norm": 2.652928352355957, + "learning_rate": 2.83209594138738e-06, + "loss": 0.3069, + "step": 652 + }, + { + "epoch": 1.385369732308508, + "grad_norm": 0.8679104447364807, + "learning_rate": 2.8265467332793358e-06, + "loss": 0.1158, + "step": 653 + }, + { + "epoch": 1.3874900609594487, + "grad_norm": 2.065187692642212, + "learning_rate": 2.820995887866378e-06, + "loss": 0.3263, + "step": 654 + }, + { + "epoch": 1.3896103896103895, + "grad_norm": 1.9065489768981934, + "learning_rate": 2.8154434329804366e-06, + "loss": 0.2294, + "step": 655 + }, + { + "epoch": 1.3917307182613305, + "grad_norm": 2.2654645442962646, + "learning_rate": 2.8098893964615165e-06, + "loss": 0.2063, + "step": 656 + }, + { + "epoch": 1.3938510469122714, + "grad_norm": 1.9993574619293213, + "learning_rate": 2.8043338061575464e-06, + "loss": 0.2116, + "step": 657 + }, + { + "epoch": 1.3959713755632124, + "grad_norm": 1.850152850151062, + "learning_rate": 2.7987766899242513e-06, + "loss": 0.1887, + "step": 658 + }, + { + "epoch": 1.3980917042141532, + "grad_norm": 0.9010924696922302, + "learning_rate": 2.7932180756250042e-06, + "loss": 0.2322, + "step": 659 + }, + { + "epoch": 1.400212032865094, + "grad_norm": 1.3110419511795044, + "learning_rate": 2.787657991130692e-06, + "loss": 0.1766, + "step": 660 + }, + { + "epoch": 1.402332361516035, + "grad_norm": 0.9936445951461792, + "learning_rate": 2.7820964643195685e-06, + "loss": 0.1912, + "step": 661 + }, + { + "epoch": 1.4044526901669758, + "grad_norm": 1.7485136985778809, + "learning_rate": 2.7765335230771255e-06, + "loss": 0.1987, + "step": 662 + }, + { + "epoch": 1.4065730188179169, + "grad_norm": 1.2912129163742065, + "learning_rate": 2.7709691952959406e-06, + "loss": 0.1324, + "step": 663 + }, + { + "epoch": 1.4086933474688577, + "grad_norm": 2.263025999069214, + "learning_rate": 2.765403508875548e-06, + "loss": 0.2485, + "step": 664 + }, + { + "epoch": 1.4108136761197985, + "grad_norm": 1.1566165685653687, + "learning_rate": 2.759836491722292e-06, + "loss": 0.173, + "step": 665 + }, + { + "epoch": 1.4129340047707395, + "grad_norm": 1.7113949060440063, + "learning_rate": 2.75426817174919e-06, + "loss": 0.1933, + "step": 666 + }, + { + "epoch": 1.4150543334216803, + "grad_norm": 2.519707679748535, + "learning_rate": 2.7486985768757905e-06, + "loss": 0.1837, + "step": 667 + }, + { + "epoch": 1.4171746620726213, + "grad_norm": 2.177272319793701, + "learning_rate": 2.743127735028037e-06, + "loss": 0.3647, + "step": 668 + }, + { + "epoch": 1.4192949907235621, + "grad_norm": 2.8958051204681396, + "learning_rate": 2.7375556741381216e-06, + "loss": 0.3015, + "step": 669 + }, + { + "epoch": 1.421415319374503, + "grad_norm": 1.972503662109375, + "learning_rate": 2.731982422144352e-06, + "loss": 0.2581, + "step": 670 + }, + { + "epoch": 1.423535648025444, + "grad_norm": 0.32309406995773315, + "learning_rate": 2.726408006991006e-06, + "loss": 0.2046, + "step": 671 + }, + { + "epoch": 1.4256559766763848, + "grad_norm": 0.9400335550308228, + "learning_rate": 2.7208324566281946e-06, + "loss": 0.2459, + "step": 672 + }, + { + "epoch": 1.4277763053273258, + "grad_norm": 2.608882188796997, + "learning_rate": 2.715255799011721e-06, + "loss": 0.2656, + "step": 673 + }, + { + "epoch": 1.4298966339782666, + "grad_norm": 1.6778721809387207, + "learning_rate": 2.7096780621029386e-06, + "loss": 0.1731, + "step": 674 + }, + { + "epoch": 1.4320169626292074, + "grad_norm": 1.2319176197052002, + "learning_rate": 2.7040992738686135e-06, + "loss": 0.3142, + "step": 675 + }, + { + "epoch": 1.4341372912801484, + "grad_norm": 2.1388039588928223, + "learning_rate": 2.6985194622807835e-06, + "loss": 0.1379, + "step": 676 + }, + { + "epoch": 1.4362576199310892, + "grad_norm": 2.897584915161133, + "learning_rate": 2.6929386553166165e-06, + "loss": 0.2351, + "step": 677 + }, + { + "epoch": 1.4383779485820303, + "grad_norm": 1.4169594049453735, + "learning_rate": 2.687356880958271e-06, + "loss": 0.0984, + "step": 678 + }, + { + "epoch": 1.440498277232971, + "grad_norm": 1.3336187601089478, + "learning_rate": 2.6817741671927587e-06, + "loss": 0.1528, + "step": 679 + }, + { + "epoch": 1.4426186058839119, + "grad_norm": 1.822395920753479, + "learning_rate": 2.676190542011797e-06, + "loss": 0.1678, + "step": 680 + }, + { + "epoch": 1.444738934534853, + "grad_norm": 1.3622679710388184, + "learning_rate": 2.670606033411678e-06, + "loss": 0.17, + "step": 681 + }, + { + "epoch": 1.4468592631857937, + "grad_norm": 2.184080123901367, + "learning_rate": 2.6650206693931184e-06, + "loss": 0.2781, + "step": 682 + }, + { + "epoch": 1.4489795918367347, + "grad_norm": 1.511780858039856, + "learning_rate": 2.659434477961129e-06, + "loss": 0.2947, + "step": 683 + }, + { + "epoch": 1.4510999204876756, + "grad_norm": 1.5842374563217163, + "learning_rate": 2.653847487124865e-06, + "loss": 0.1783, + "step": 684 + }, + { + "epoch": 1.4532202491386164, + "grad_norm": 1.9350712299346924, + "learning_rate": 2.648259724897492e-06, + "loss": 0.2216, + "step": 685 + }, + { + "epoch": 1.4553405777895574, + "grad_norm": 2.5653059482574463, + "learning_rate": 2.6426712192960423e-06, + "loss": 0.2853, + "step": 686 + }, + { + "epoch": 1.4574609064404984, + "grad_norm": 3.479128837585449, + "learning_rate": 2.637081998341277e-06, + "loss": 0.1873, + "step": 687 + }, + { + "epoch": 1.4595812350914392, + "grad_norm": 2.4509148597717285, + "learning_rate": 2.631492090057543e-06, + "loss": 0.2065, + "step": 688 + }, + { + "epoch": 1.46170156374238, + "grad_norm": 1.770412564277649, + "learning_rate": 2.6259015224726325e-06, + "loss": 0.1938, + "step": 689 + }, + { + "epoch": 1.4638218923933208, + "grad_norm": 1.4200644493103027, + "learning_rate": 2.6203103236176446e-06, + "loss": 0.2258, + "step": 690 + }, + { + "epoch": 1.4659422210442619, + "grad_norm": 2.0753350257873535, + "learning_rate": 2.6147185215268446e-06, + "loss": 0.2049, + "step": 691 + }, + { + "epoch": 1.468062549695203, + "grad_norm": 1.6016238927841187, + "learning_rate": 2.609126144237519e-06, + "loss": 0.2649, + "step": 692 + }, + { + "epoch": 1.4701828783461437, + "grad_norm": 1.9330469369888306, + "learning_rate": 2.603533219789844e-06, + "loss": 0.2249, + "step": 693 + }, + { + "epoch": 1.4723032069970845, + "grad_norm": 2.1735124588012695, + "learning_rate": 2.597939776226732e-06, + "loss": 0.2629, + "step": 694 + }, + { + "epoch": 1.4744235356480253, + "grad_norm": 1.841036319732666, + "learning_rate": 2.5923458415937048e-06, + "loss": 0.1787, + "step": 695 + }, + { + "epoch": 1.4765438642989663, + "grad_norm": 2.6332991123199463, + "learning_rate": 2.586751443938742e-06, + "loss": 0.2431, + "step": 696 + }, + { + "epoch": 1.4786641929499074, + "grad_norm": 1.6684833765029907, + "learning_rate": 2.581156611312148e-06, + "loss": 0.2282, + "step": 697 + }, + { + "epoch": 1.4807845216008482, + "grad_norm": 0.7805116772651672, + "learning_rate": 2.5755613717664053e-06, + "loss": 0.1392, + "step": 698 + }, + { + "epoch": 1.482904850251789, + "grad_norm": 0.9408957958221436, + "learning_rate": 2.5699657533560386e-06, + "loss": 0.1325, + "step": 699 + }, + { + "epoch": 1.48502517890273, + "grad_norm": 2.233403444290161, + "learning_rate": 2.5643697841374722e-06, + "loss": 0.2908, + "step": 700 + }, + { + "epoch": 1.4871455075536708, + "grad_norm": 0.5273526310920715, + "learning_rate": 2.5587734921688873e-06, + "loss": 0.1575, + "step": 701 + }, + { + "epoch": 1.4892658362046118, + "grad_norm": 1.2741076946258545, + "learning_rate": 2.553176905510086e-06, + "loss": 0.2134, + "step": 702 + }, + { + "epoch": 1.4913861648555526, + "grad_norm": 1.4551169872283936, + "learning_rate": 2.547580052222347e-06, + "loss": 0.1237, + "step": 703 + }, + { + "epoch": 1.4935064935064934, + "grad_norm": 2.193265914916992, + "learning_rate": 2.5419829603682857e-06, + "loss": 0.2685, + "step": 704 + }, + { + "epoch": 1.4956268221574345, + "grad_norm": 1.1736443042755127, + "learning_rate": 2.5363856580117126e-06, + "loss": 0.1412, + "step": 705 + }, + { + "epoch": 1.4977471508083753, + "grad_norm": 2.0331931114196777, + "learning_rate": 2.5307881732174954e-06, + "loss": 0.3377, + "step": 706 + }, + { + "epoch": 1.4998674794593163, + "grad_norm": 1.456709861755371, + "learning_rate": 2.525190534051416e-06, + "loss": 0.2192, + "step": 707 + }, + { + "epoch": 1.5019878081102571, + "grad_norm": 3.0361955165863037, + "learning_rate": 2.519592768580031e-06, + "loss": 0.2958, + "step": 708 + }, + { + "epoch": 1.504108136761198, + "grad_norm": 1.2546547651290894, + "learning_rate": 2.513994904870528e-06, + "loss": 0.2331, + "step": 709 + }, + { + "epoch": 1.5062284654121387, + "grad_norm": 1.4712584018707275, + "learning_rate": 2.5083969709905904e-06, + "loss": 0.1968, + "step": 710 + }, + { + "epoch": 1.5083487940630798, + "grad_norm": 1.318629264831543, + "learning_rate": 2.502798995008249e-06, + "loss": 0.2898, + "step": 711 + }, + { + "epoch": 1.5104691227140208, + "grad_norm": 3.635026693344116, + "learning_rate": 2.4972010049917513e-06, + "loss": 0.1849, + "step": 712 + }, + { + "epoch": 1.5125894513649616, + "grad_norm": 1.7475965023040771, + "learning_rate": 2.491603029009411e-06, + "loss": 0.1244, + "step": 713 + }, + { + "epoch": 1.5147097800159024, + "grad_norm": 2.1681947708129883, + "learning_rate": 2.4860050951294723e-06, + "loss": 0.186, + "step": 714 + }, + { + "epoch": 1.5168301086668432, + "grad_norm": 1.8500131368637085, + "learning_rate": 2.480407231419969e-06, + "loss": 0.1995, + "step": 715 + }, + { + "epoch": 1.5189504373177842, + "grad_norm": 1.4108548164367676, + "learning_rate": 2.474809465948584e-06, + "loss": 0.1875, + "step": 716 + }, + { + "epoch": 1.5210707659687253, + "grad_norm": 1.5259912014007568, + "learning_rate": 2.469211826782506e-06, + "loss": 0.2135, + "step": 717 + }, + { + "epoch": 1.523191094619666, + "grad_norm": 1.7771860361099243, + "learning_rate": 2.4636143419882887e-06, + "loss": 0.1819, + "step": 718 + }, + { + "epoch": 1.5253114232706069, + "grad_norm": 1.3263814449310303, + "learning_rate": 2.4580170396317156e-06, + "loss": 0.1927, + "step": 719 + }, + { + "epoch": 1.5274317519215477, + "grad_norm": 3.3468446731567383, + "learning_rate": 2.452419947777654e-06, + "loss": 0.1666, + "step": 720 + }, + { + "epoch": 1.5295520805724887, + "grad_norm": 1.9386024475097656, + "learning_rate": 2.4468230944899147e-06, + "loss": 0.2549, + "step": 721 + }, + { + "epoch": 1.5316724092234297, + "grad_norm": 0.590383768081665, + "learning_rate": 2.4412265078311135e-06, + "loss": 0.1705, + "step": 722 + }, + { + "epoch": 1.5337927378743705, + "grad_norm": 1.4284600019454956, + "learning_rate": 2.435630215862529e-06, + "loss": 0.1925, + "step": 723 + }, + { + "epoch": 1.5359130665253113, + "grad_norm": 1.2749354839324951, + "learning_rate": 2.4300342466439623e-06, + "loss": 0.2595, + "step": 724 + }, + { + "epoch": 1.5380333951762524, + "grad_norm": 1.1233924627304077, + "learning_rate": 2.424438628233595e-06, + "loss": 0.2232, + "step": 725 + }, + { + "epoch": 1.5401537238271932, + "grad_norm": 1.092596173286438, + "learning_rate": 2.418843388687853e-06, + "loss": 0.1417, + "step": 726 + }, + { + "epoch": 1.5422740524781342, + "grad_norm": 2.1619231700897217, + "learning_rate": 2.4132485560612583e-06, + "loss": 0.2102, + "step": 727 + }, + { + "epoch": 1.544394381129075, + "grad_norm": 1.9228898286819458, + "learning_rate": 2.4076541584062965e-06, + "loss": 0.1773, + "step": 728 + }, + { + "epoch": 1.5465147097800158, + "grad_norm": 2.4524118900299072, + "learning_rate": 2.402060223773269e-06, + "loss": 0.2415, + "step": 729 + }, + { + "epoch": 1.5486350384309568, + "grad_norm": 1.9279297590255737, + "learning_rate": 2.3964667802101574e-06, + "loss": 0.2973, + "step": 730 + }, + { + "epoch": 1.5507553670818977, + "grad_norm": 1.126503348350525, + "learning_rate": 2.3908738557624812e-06, + "loss": 0.2207, + "step": 731 + }, + { + "epoch": 1.5528756957328387, + "grad_norm": 1.8187668323516846, + "learning_rate": 2.385281478473156e-06, + "loss": 0.2319, + "step": 732 + }, + { + "epoch": 1.5549960243837795, + "grad_norm": 1.953602910041809, + "learning_rate": 2.379689676382356e-06, + "loss": 0.2266, + "step": 733 + }, + { + "epoch": 1.5571163530347203, + "grad_norm": 1.342537522315979, + "learning_rate": 2.3740984775273684e-06, + "loss": 0.1672, + "step": 734 + }, + { + "epoch": 1.5592366816856613, + "grad_norm": 3.2077980041503906, + "learning_rate": 2.368507909942458e-06, + "loss": 0.2455, + "step": 735 + }, + { + "epoch": 1.5613570103366021, + "grad_norm": 1.859153151512146, + "learning_rate": 2.362918001658723e-06, + "loss": 0.1731, + "step": 736 + }, + { + "epoch": 1.5634773389875432, + "grad_norm": 2.042102813720703, + "learning_rate": 2.3573287807039577e-06, + "loss": 0.182, + "step": 737 + }, + { + "epoch": 1.565597667638484, + "grad_norm": 2.096276044845581, + "learning_rate": 2.3517402751025083e-06, + "loss": 0.2215, + "step": 738 + }, + { + "epoch": 1.5677179962894248, + "grad_norm": 0.925915002822876, + "learning_rate": 2.3461525128751364e-06, + "loss": 0.1727, + "step": 739 + }, + { + "epoch": 1.5698383249403658, + "grad_norm": 1.1790268421173096, + "learning_rate": 2.3405655220388718e-06, + "loss": 0.1117, + "step": 740 + }, + { + "epoch": 1.5719586535913066, + "grad_norm": 6.514387607574463, + "learning_rate": 2.334979330606882e-06, + "loss": 0.2172, + "step": 741 + }, + { + "epoch": 1.5740789822422476, + "grad_norm": 2.039428949356079, + "learning_rate": 2.3293939665883233e-06, + "loss": 0.1758, + "step": 742 + }, + { + "epoch": 1.5761993108931884, + "grad_norm": 2.0858302116394043, + "learning_rate": 2.3238094579882037e-06, + "loss": 0.1564, + "step": 743 + }, + { + "epoch": 1.5783196395441292, + "grad_norm": 2.3777787685394287, + "learning_rate": 2.318225832807242e-06, + "loss": 0.2507, + "step": 744 + }, + { + "epoch": 1.5804399681950703, + "grad_norm": 1.0911935567855835, + "learning_rate": 2.3126431190417294e-06, + "loss": 0.2025, + "step": 745 + }, + { + "epoch": 1.5825602968460113, + "grad_norm": 1.207847237586975, + "learning_rate": 2.3070613446833843e-06, + "loss": 0.2627, + "step": 746 + }, + { + "epoch": 1.584680625496952, + "grad_norm": 1.059277892112732, + "learning_rate": 2.3014805377192173e-06, + "loss": 0.1475, + "step": 747 + }, + { + "epoch": 1.586800954147893, + "grad_norm": 1.6303125619888306, + "learning_rate": 2.2959007261313865e-06, + "loss": 0.1478, + "step": 748 + }, + { + "epoch": 1.5889212827988337, + "grad_norm": 0.9721236824989319, + "learning_rate": 2.2903219378970623e-06, + "loss": 0.169, + "step": 749 + }, + { + "epoch": 1.5910416114497747, + "grad_norm": 2.5028750896453857, + "learning_rate": 2.2847442009882805e-06, + "loss": 0.2719, + "step": 750 + }, + { + "epoch": 1.5931619401007158, + "grad_norm": 1.3091676235198975, + "learning_rate": 2.2791675433718058e-06, + "loss": 0.1815, + "step": 751 + }, + { + "epoch": 1.5952822687516566, + "grad_norm": 1.014621615409851, + "learning_rate": 2.273591993008995e-06, + "loss": 0.1354, + "step": 752 + }, + { + "epoch": 1.5974025974025974, + "grad_norm": 1.3206697702407837, + "learning_rate": 2.268017577855649e-06, + "loss": 0.2361, + "step": 753 + }, + { + "epoch": 1.5995229260535382, + "grad_norm": 1.9211969375610352, + "learning_rate": 2.262444325861879e-06, + "loss": 0.2273, + "step": 754 + }, + { + "epoch": 1.6016432547044792, + "grad_norm": 0.9052472710609436, + "learning_rate": 2.2568722649719637e-06, + "loss": 0.1695, + "step": 755 + }, + { + "epoch": 1.6037635833554202, + "grad_norm": 0.7492967844009399, + "learning_rate": 2.25130142312421e-06, + "loss": 0.2105, + "step": 756 + }, + { + "epoch": 1.605883912006361, + "grad_norm": 1.8103669881820679, + "learning_rate": 2.2457318282508105e-06, + "loss": 0.2822, + "step": 757 + }, + { + "epoch": 1.6080042406573019, + "grad_norm": 1.9676963090896606, + "learning_rate": 2.2401635082777086e-06, + "loss": 0.2802, + "step": 758 + }, + { + "epoch": 1.6101245693082427, + "grad_norm": 1.3851075172424316, + "learning_rate": 2.234596491124452e-06, + "loss": 0.1117, + "step": 759 + }, + { + "epoch": 1.6122448979591837, + "grad_norm": 0.9123232960700989, + "learning_rate": 2.2290308047040607e-06, + "loss": 0.2573, + "step": 760 + }, + { + "epoch": 1.6143652266101247, + "grad_norm": 1.3736172914505005, + "learning_rate": 2.2234664769228758e-06, + "loss": 0.1806, + "step": 761 + }, + { + "epoch": 1.6164855552610655, + "grad_norm": 0.8288306593894958, + "learning_rate": 2.217903535680432e-06, + "loss": 0.1327, + "step": 762 + }, + { + "epoch": 1.6186058839120063, + "grad_norm": 0.9833022952079773, + "learning_rate": 2.212342008869309e-06, + "loss": 0.1819, + "step": 763 + }, + { + "epoch": 1.6207262125629471, + "grad_norm": 1.44596266746521, + "learning_rate": 2.206781924374996e-06, + "loss": 0.1626, + "step": 764 + }, + { + "epoch": 1.6228465412138882, + "grad_norm": 2.6636288166046143, + "learning_rate": 2.201223310075749e-06, + "loss": 0.2006, + "step": 765 + }, + { + "epoch": 1.6249668698648292, + "grad_norm": 1.4887255430221558, + "learning_rate": 2.1956661938424544e-06, + "loss": 0.1135, + "step": 766 + }, + { + "epoch": 1.62708719851577, + "grad_norm": 2.366757392883301, + "learning_rate": 2.1901106035384843e-06, + "loss": 0.2926, + "step": 767 + }, + { + "epoch": 1.6292075271667108, + "grad_norm": 1.6054885387420654, + "learning_rate": 2.1845565670195634e-06, + "loss": 0.2127, + "step": 768 + }, + { + "epoch": 1.6313278558176516, + "grad_norm": 1.424625277519226, + "learning_rate": 2.1790041121336223e-06, + "loss": 0.256, + "step": 769 + }, + { + "epoch": 1.6334481844685926, + "grad_norm": 1.324894905090332, + "learning_rate": 2.173453266720665e-06, + "loss": 0.2511, + "step": 770 + }, + { + "epoch": 1.6355685131195337, + "grad_norm": 1.541780710220337, + "learning_rate": 2.1679040586126214e-06, + "loss": 0.1786, + "step": 771 + }, + { + "epoch": 1.6376888417704745, + "grad_norm": 1.0855908393859863, + "learning_rate": 2.1623565156332145e-06, + "loss": 0.2015, + "step": 772 + }, + { + "epoch": 1.6398091704214153, + "grad_norm": 1.2004632949829102, + "learning_rate": 2.1568106655978184e-06, + "loss": 0.1488, + "step": 773 + }, + { + "epoch": 1.641929499072356, + "grad_norm": 2.120727300643921, + "learning_rate": 2.1512665363133173e-06, + "loss": 0.3628, + "step": 774 + }, + { + "epoch": 1.644049827723297, + "grad_norm": 1.992598056793213, + "learning_rate": 2.14572415557797e-06, + "loss": 0.2429, + "step": 775 + }, + { + "epoch": 1.6461701563742381, + "grad_norm": 1.2479114532470703, + "learning_rate": 2.140183551181266e-06, + "loss": 0.1817, + "step": 776 + }, + { + "epoch": 1.648290485025179, + "grad_norm": 1.3581926822662354, + "learning_rate": 2.1346447509037886e-06, + "loss": 0.1804, + "step": 777 + }, + { + "epoch": 1.6504108136761197, + "grad_norm": 1.578666090965271, + "learning_rate": 2.1291077825170756e-06, + "loss": 0.1714, + "step": 778 + }, + { + "epoch": 1.6525311423270606, + "grad_norm": 1.6858261823654175, + "learning_rate": 2.1235726737834794e-06, + "loss": 0.2376, + "step": 779 + }, + { + "epoch": 1.6546514709780016, + "grad_norm": 1.8544155359268188, + "learning_rate": 2.118039452456029e-06, + "loss": 0.1878, + "step": 780 + }, + { + "epoch": 1.6567717996289426, + "grad_norm": 1.179569959640503, + "learning_rate": 2.112508146278289e-06, + "loss": 0.2489, + "step": 781 + }, + { + "epoch": 1.6588921282798834, + "grad_norm": 1.2655270099639893, + "learning_rate": 2.106978782984221e-06, + "loss": 0.1492, + "step": 782 + }, + { + "epoch": 1.6610124569308242, + "grad_norm": 0.9758352041244507, + "learning_rate": 2.101451390298047e-06, + "loss": 0.1525, + "step": 783 + }, + { + "epoch": 1.663132785581765, + "grad_norm": 1.285880208015442, + "learning_rate": 2.095925995934105e-06, + "loss": 0.2749, + "step": 784 + }, + { + "epoch": 1.665253114232706, + "grad_norm": 0.683684766292572, + "learning_rate": 2.0904026275967176e-06, + "loss": 0.1183, + "step": 785 + }, + { + "epoch": 1.667373442883647, + "grad_norm": 1.4306302070617676, + "learning_rate": 2.084881312980045e-06, + "loss": 0.1484, + "step": 786 + }, + { + "epoch": 1.669493771534588, + "grad_norm": 1.3516453504562378, + "learning_rate": 2.0793620797679537e-06, + "loss": 0.2783, + "step": 787 + }, + { + "epoch": 1.6716141001855287, + "grad_norm": 1.849977731704712, + "learning_rate": 2.0738449556338704e-06, + "loss": 0.2064, + "step": 788 + }, + { + "epoch": 1.6737344288364695, + "grad_norm": 2.6501619815826416, + "learning_rate": 2.0683299682406497e-06, + "loss": 0.1742, + "step": 789 + }, + { + "epoch": 1.6758547574874105, + "grad_norm": 1.9885671138763428, + "learning_rate": 2.062817145240431e-06, + "loss": 0.2273, + "step": 790 + }, + { + "epoch": 1.6779750861383516, + "grad_norm": 1.9040833711624146, + "learning_rate": 2.057306514274503e-06, + "loss": 0.2515, + "step": 791 + }, + { + "epoch": 1.6800954147892924, + "grad_norm": 1.9295481443405151, + "learning_rate": 2.0517981029731613e-06, + "loss": 0.2791, + "step": 792 + }, + { + "epoch": 1.6822157434402332, + "grad_norm": 1.2951781749725342, + "learning_rate": 2.0462919389555734e-06, + "loss": 0.1838, + "step": 793 + }, + { + "epoch": 1.684336072091174, + "grad_norm": 1.2169189453125, + "learning_rate": 2.0407880498296397e-06, + "loss": 0.188, + "step": 794 + }, + { + "epoch": 1.686456400742115, + "grad_norm": 1.4646093845367432, + "learning_rate": 2.035286463191852e-06, + "loss": 0.2529, + "step": 795 + }, + { + "epoch": 1.688576729393056, + "grad_norm": 1.2175997495651245, + "learning_rate": 2.0297872066271606e-06, + "loss": 0.1882, + "step": 796 + }, + { + "epoch": 1.6906970580439968, + "grad_norm": 1.482407808303833, + "learning_rate": 2.02429030770883e-06, + "loss": 0.2542, + "step": 797 + }, + { + "epoch": 1.6928173866949376, + "grad_norm": 1.4033699035644531, + "learning_rate": 2.0187957939983045e-06, + "loss": 0.2018, + "step": 798 + }, + { + "epoch": 1.6949377153458784, + "grad_norm": 2.2561542987823486, + "learning_rate": 2.0133036930450694e-06, + "loss": 0.1885, + "step": 799 + }, + { + "epoch": 1.6970580439968195, + "grad_norm": 1.9615060091018677, + "learning_rate": 2.0078140323865114e-06, + "loss": 0.1909, + "step": 800 + }, + { + "epoch": 1.6991783726477605, + "grad_norm": 1.5575997829437256, + "learning_rate": 2.0023268395477833e-06, + "loss": 0.1939, + "step": 801 + }, + { + "epoch": 1.7012987012987013, + "grad_norm": 1.2603005170822144, + "learning_rate": 1.9968421420416633e-06, + "loss": 0.2151, + "step": 802 + }, + { + "epoch": 1.7034190299496421, + "grad_norm": 1.56342613697052, + "learning_rate": 1.991359967368416e-06, + "loss": 0.2121, + "step": 803 + }, + { + "epoch": 1.7055393586005831, + "grad_norm": 0.8418555855751038, + "learning_rate": 1.9858803430156602e-06, + "loss": 0.1356, + "step": 804 + }, + { + "epoch": 1.707659687251524, + "grad_norm": 2.612060308456421, + "learning_rate": 1.9804032964582243e-06, + "loss": 0.1723, + "step": 805 + }, + { + "epoch": 1.709780015902465, + "grad_norm": 1.789333462715149, + "learning_rate": 1.974928855158014e-06, + "loss": 0.2443, + "step": 806 + }, + { + "epoch": 1.7119003445534058, + "grad_norm": 2.306417226791382, + "learning_rate": 1.96945704656387e-06, + "loss": 0.1573, + "step": 807 + }, + { + "epoch": 1.7140206732043466, + "grad_norm": 1.3851442337036133, + "learning_rate": 1.9639878981114358e-06, + "loss": 0.2239, + "step": 808 + }, + { + "epoch": 1.7161410018552876, + "grad_norm": 1.9788298606872559, + "learning_rate": 1.958521437223013e-06, + "loss": 0.1589, + "step": 809 + }, + { + "epoch": 1.7182613305062284, + "grad_norm": 1.2567238807678223, + "learning_rate": 1.95305769130743e-06, + "loss": 0.1738, + "step": 810 + }, + { + "epoch": 1.7203816591571695, + "grad_norm": 1.2289453744888306, + "learning_rate": 1.947596687759902e-06, + "loss": 0.1698, + "step": 811 + }, + { + "epoch": 1.7225019878081103, + "grad_norm": 1.1884444952011108, + "learning_rate": 1.9421384539618957e-06, + "loss": 0.1406, + "step": 812 + }, + { + "epoch": 1.724622316459051, + "grad_norm": 2.408679485321045, + "learning_rate": 1.9366830172809877e-06, + "loss": 0.214, + "step": 813 + }, + { + "epoch": 1.726742645109992, + "grad_norm": 1.555776596069336, + "learning_rate": 1.9312304050707293e-06, + "loss": 0.1675, + "step": 814 + }, + { + "epoch": 1.728862973760933, + "grad_norm": 1.8956245183944702, + "learning_rate": 1.9257806446705116e-06, + "loss": 0.1727, + "step": 815 + }, + { + "epoch": 1.730983302411874, + "grad_norm": 2.6797003746032715, + "learning_rate": 1.920333763405428e-06, + "loss": 0.2671, + "step": 816 + }, + { + "epoch": 1.7331036310628147, + "grad_norm": 5.029034614562988, + "learning_rate": 1.914889788586133e-06, + "loss": 0.1879, + "step": 817 + }, + { + "epoch": 1.7352239597137555, + "grad_norm": 1.3859666585922241, + "learning_rate": 1.909448747508711e-06, + "loss": 0.2305, + "step": 818 + }, + { + "epoch": 1.7373442883646966, + "grad_norm": 1.9923025369644165, + "learning_rate": 1.9040106674545333e-06, + "loss": 0.3013, + "step": 819 + }, + { + "epoch": 1.7394646170156374, + "grad_norm": 2.2539119720458984, + "learning_rate": 1.898575575690128e-06, + "loss": 0.145, + "step": 820 + }, + { + "epoch": 1.7415849456665784, + "grad_norm": 1.2624527215957642, + "learning_rate": 1.8931434994670377e-06, + "loss": 0.2027, + "step": 821 + }, + { + "epoch": 1.7437052743175192, + "grad_norm": 1.10843825340271, + "learning_rate": 1.8877144660216867e-06, + "loss": 0.1941, + "step": 822 + }, + { + "epoch": 1.74582560296846, + "grad_norm": 1.4225454330444336, + "learning_rate": 1.8822885025752408e-06, + "loss": 0.2453, + "step": 823 + }, + { + "epoch": 1.747945931619401, + "grad_norm": 0.7526883482933044, + "learning_rate": 1.8768656363334759e-06, + "loss": 0.1622, + "step": 824 + }, + { + "epoch": 1.750066260270342, + "grad_norm": 0.6890954375267029, + "learning_rate": 1.8714458944866342e-06, + "loss": 0.1394, + "step": 825 + }, + { + "epoch": 1.7521865889212829, + "grad_norm": 1.9675222635269165, + "learning_rate": 1.8660293042092953e-06, + "loss": 0.165, + "step": 826 + }, + { + "epoch": 1.7543069175722237, + "grad_norm": 1.5908443927764893, + "learning_rate": 1.8606158926602368e-06, + "loss": 0.1421, + "step": 827 + }, + { + "epoch": 1.7564272462231645, + "grad_norm": 2.1363799571990967, + "learning_rate": 1.8552056869822968e-06, + "loss": 0.2401, + "step": 828 + }, + { + "epoch": 1.7585475748741055, + "grad_norm": 1.3258087635040283, + "learning_rate": 1.8497987143022405e-06, + "loss": 0.2401, + "step": 829 + }, + { + "epoch": 1.7606679035250465, + "grad_norm": 2.014814615249634, + "learning_rate": 1.8443950017306214e-06, + "loss": 0.2251, + "step": 830 + }, + { + "epoch": 1.7627882321759873, + "grad_norm": 0.8224743604660034, + "learning_rate": 1.8389945763616485e-06, + "loss": 0.113, + "step": 831 + }, + { + "epoch": 1.7649085608269282, + "grad_norm": 1.5032809972763062, + "learning_rate": 1.8335974652730467e-06, + "loss": 0.2415, + "step": 832 + }, + { + "epoch": 1.767028889477869, + "grad_norm": 2.1641783714294434, + "learning_rate": 1.8282036955259258e-06, + "loss": 0.2079, + "step": 833 + }, + { + "epoch": 1.76914921812881, + "grad_norm": 1.787461519241333, + "learning_rate": 1.8228132941646404e-06, + "loss": 0.2262, + "step": 834 + }, + { + "epoch": 1.771269546779751, + "grad_norm": 0.7867398858070374, + "learning_rate": 1.817426288216655e-06, + "loss": 0.2094, + "step": 835 + }, + { + "epoch": 1.7733898754306918, + "grad_norm": 1.3670313358306885, + "learning_rate": 1.8120427046924106e-06, + "loss": 0.1674, + "step": 836 + }, + { + "epoch": 1.7755102040816326, + "grad_norm": 1.9899623394012451, + "learning_rate": 1.8066625705851896e-06, + "loss": 0.255, + "step": 837 + }, + { + "epoch": 1.7776305327325734, + "grad_norm": 1.7844711542129517, + "learning_rate": 1.8012859128709766e-06, + "loss": 0.1705, + "step": 838 + }, + { + "epoch": 1.7797508613835145, + "grad_norm": 2.2082679271698, + "learning_rate": 1.7959127585083281e-06, + "loss": 0.3657, + "step": 839 + }, + { + "epoch": 1.7818711900344555, + "grad_norm": 3.0161192417144775, + "learning_rate": 1.7905431344382318e-06, + "loss": 0.1641, + "step": 840 + }, + { + "epoch": 1.7839915186853963, + "grad_norm": 2.1656365394592285, + "learning_rate": 1.7851770675839771e-06, + "loss": 0.2821, + "step": 841 + }, + { + "epoch": 1.786111847336337, + "grad_norm": 1.0514625310897827, + "learning_rate": 1.7798145848510162e-06, + "loss": 0.18, + "step": 842 + }, + { + "epoch": 1.788232175987278, + "grad_norm": 1.528306245803833, + "learning_rate": 1.7744557131268312e-06, + "loss": 0.2798, + "step": 843 + }, + { + "epoch": 1.790352504638219, + "grad_norm": 1.0451114177703857, + "learning_rate": 1.7691004792807976e-06, + "loss": 0.2194, + "step": 844 + }, + { + "epoch": 1.79247283328916, + "grad_norm": 1.3756572008132935, + "learning_rate": 1.7637489101640526e-06, + "loss": 0.1493, + "step": 845 + }, + { + "epoch": 1.7945931619401008, + "grad_norm": 2.324673652648926, + "learning_rate": 1.7584010326093554e-06, + "loss": 0.1907, + "step": 846 + }, + { + "epoch": 1.7967134905910416, + "grad_norm": 1.8477604389190674, + "learning_rate": 1.7530568734309578e-06, + "loss": 0.1661, + "step": 847 + }, + { + "epoch": 1.7988338192419824, + "grad_norm": 1.0166375637054443, + "learning_rate": 1.747716459424468e-06, + "loss": 0.1454, + "step": 848 + }, + { + "epoch": 1.8009541478929234, + "grad_norm": 1.7437880039215088, + "learning_rate": 1.7423798173667144e-06, + "loss": 0.1912, + "step": 849 + }, + { + "epoch": 1.8030744765438644, + "grad_norm": 0.8157974481582642, + "learning_rate": 1.7370469740156146e-06, + "loss": 0.1125, + "step": 850 + }, + { + "epoch": 1.8051948051948052, + "grad_norm": 1.758787989616394, + "learning_rate": 1.7317179561100372e-06, + "loss": 0.2471, + "step": 851 + }, + { + "epoch": 1.807315133845746, + "grad_norm": 1.253186821937561, + "learning_rate": 1.726392790369673e-06, + "loss": 0.1341, + "step": 852 + }, + { + "epoch": 1.8094354624966869, + "grad_norm": 0.8312148451805115, + "learning_rate": 1.7210715034948949e-06, + "loss": 0.1579, + "step": 853 + }, + { + "epoch": 1.8115557911476279, + "grad_norm": 0.9796281456947327, + "learning_rate": 1.7157541221666291e-06, + "loss": 0.0722, + "step": 854 + }, + { + "epoch": 1.813676119798569, + "grad_norm": 1.192187786102295, + "learning_rate": 1.7104406730462203e-06, + "loss": 0.1729, + "step": 855 + }, + { + "epoch": 1.8157964484495097, + "grad_norm": 1.2145785093307495, + "learning_rate": 1.705131182775294e-06, + "loss": 0.1131, + "step": 856 + }, + { + "epoch": 1.8179167771004505, + "grad_norm": 1.1818413734436035, + "learning_rate": 1.6998256779756279e-06, + "loss": 0.1515, + "step": 857 + }, + { + "epoch": 1.8200371057513913, + "grad_norm": 1.1990983486175537, + "learning_rate": 1.6945241852490173e-06, + "loss": 0.2163, + "step": 858 + }, + { + "epoch": 1.8221574344023324, + "grad_norm": 3.079540491104126, + "learning_rate": 1.6892267311771395e-06, + "loss": 0.1602, + "step": 859 + }, + { + "epoch": 1.8242777630532734, + "grad_norm": 1.5485817193984985, + "learning_rate": 1.6839333423214235e-06, + "loss": 0.2203, + "step": 860 + }, + { + "epoch": 1.8263980917042142, + "grad_norm": 2.226602554321289, + "learning_rate": 1.6786440452229134e-06, + "loss": 0.2015, + "step": 861 + }, + { + "epoch": 1.828518420355155, + "grad_norm": 1.1683058738708496, + "learning_rate": 1.673358866402139e-06, + "loss": 0.2026, + "step": 862 + }, + { + "epoch": 1.8306387490060958, + "grad_norm": 1.8131059408187866, + "learning_rate": 1.6680778323589798e-06, + "loss": 0.1659, + "step": 863 + }, + { + "epoch": 1.8327590776570368, + "grad_norm": 1.0971344709396362, + "learning_rate": 1.6628009695725348e-06, + "loss": 0.128, + "step": 864 + }, + { + "epoch": 1.8348794063079779, + "grad_norm": 2.1698126792907715, + "learning_rate": 1.657528304500986e-06, + "loss": 0.2637, + "step": 865 + }, + { + "epoch": 1.8369997349589187, + "grad_norm": 1.535143494606018, + "learning_rate": 1.6522598635814718e-06, + "loss": 0.1259, + "step": 866 + }, + { + "epoch": 1.8391200636098595, + "grad_norm": 1.4739115238189697, + "learning_rate": 1.6469956732299463e-06, + "loss": 0.2048, + "step": 867 + }, + { + "epoch": 1.8412403922608003, + "grad_norm": 0.9692105054855347, + "learning_rate": 1.6417357598410539e-06, + "loss": 0.1192, + "step": 868 + }, + { + "epoch": 1.8433607209117413, + "grad_norm": 1.028839349746704, + "learning_rate": 1.636480149787994e-06, + "loss": 0.1157, + "step": 869 + }, + { + "epoch": 1.8454810495626823, + "grad_norm": 1.9451359510421753, + "learning_rate": 1.6312288694223882e-06, + "loss": 0.1635, + "step": 870 + }, + { + "epoch": 1.8476013782136231, + "grad_norm": 1.6668827533721924, + "learning_rate": 1.6259819450741512e-06, + "loss": 0.234, + "step": 871 + }, + { + "epoch": 1.849721706864564, + "grad_norm": 0.971024751663208, + "learning_rate": 1.620739403051354e-06, + "loss": 0.1229, + "step": 872 + }, + { + "epoch": 1.8518420355155047, + "grad_norm": 2.122507095336914, + "learning_rate": 1.6155012696400959e-06, + "loss": 0.2016, + "step": 873 + }, + { + "epoch": 1.8539623641664458, + "grad_norm": 2.7607994079589844, + "learning_rate": 1.6102675711043719e-06, + "loss": 0.2195, + "step": 874 + }, + { + "epoch": 1.8560826928173868, + "grad_norm": 1.627505898475647, + "learning_rate": 1.6050383336859388e-06, + "loss": 0.2128, + "step": 875 + }, + { + "epoch": 1.8582030214683276, + "grad_norm": 2.6249325275421143, + "learning_rate": 1.599813583604188e-06, + "loss": 0.2381, + "step": 876 + }, + { + "epoch": 1.8603233501192684, + "grad_norm": 1.4043858051300049, + "learning_rate": 1.5945933470560097e-06, + "loss": 0.158, + "step": 877 + }, + { + "epoch": 1.8624436787702092, + "grad_norm": 2.1411776542663574, + "learning_rate": 1.5893776502156616e-06, + "loss": 0.1924, + "step": 878 + }, + { + "epoch": 1.8645640074211502, + "grad_norm": 0.7305095195770264, + "learning_rate": 1.5841665192346432e-06, + "loss": 0.201, + "step": 879 + }, + { + "epoch": 1.8666843360720913, + "grad_norm": 3.2844574451446533, + "learning_rate": 1.5789599802415572e-06, + "loss": 0.234, + "step": 880 + }, + { + "epoch": 1.868804664723032, + "grad_norm": 1.5105334520339966, + "learning_rate": 1.5737580593419854e-06, + "loss": 0.1891, + "step": 881 + }, + { + "epoch": 1.8709249933739729, + "grad_norm": 3.2038848400115967, + "learning_rate": 1.5685607826183514e-06, + "loss": 0.1912, + "step": 882 + }, + { + "epoch": 1.873045322024914, + "grad_norm": 1.120902180671692, + "learning_rate": 1.5633681761297948e-06, + "loss": 0.1075, + "step": 883 + }, + { + "epoch": 1.8751656506758547, + "grad_norm": 2.2855780124664307, + "learning_rate": 1.558180265912037e-06, + "loss": 0.1945, + "step": 884 + }, + { + "epoch": 1.8772859793267958, + "grad_norm": 1.1479313373565674, + "learning_rate": 1.5529970779772552e-06, + "loss": 0.1465, + "step": 885 + }, + { + "epoch": 1.8794063079777366, + "grad_norm": 1.4228770732879639, + "learning_rate": 1.5478186383139459e-06, + "loss": 0.2768, + "step": 886 + }, + { + "epoch": 1.8815266366286774, + "grad_norm": 1.2616146802902222, + "learning_rate": 1.5426449728868004e-06, + "loss": 0.2076, + "step": 887 + }, + { + "epoch": 1.8836469652796184, + "grad_norm": 2.149235248565674, + "learning_rate": 1.5374761076365695e-06, + "loss": 0.2828, + "step": 888 + }, + { + "epoch": 1.8857672939305592, + "grad_norm": 1.1656577587127686, + "learning_rate": 1.5323120684799374e-06, + "loss": 0.2031, + "step": 889 + }, + { + "epoch": 1.8878876225815002, + "grad_norm": 1.62466299533844, + "learning_rate": 1.5271528813093896e-06, + "loss": 0.2678, + "step": 890 + }, + { + "epoch": 1.890007951232441, + "grad_norm": 0.9776110053062439, + "learning_rate": 1.5219985719930851e-06, + "loss": 0.221, + "step": 891 + }, + { + "epoch": 1.8921282798833818, + "grad_norm": 0.5721087455749512, + "learning_rate": 1.5168491663747236e-06, + "loss": 0.1595, + "step": 892 + }, + { + "epoch": 1.8942486085343229, + "grad_norm": 1.2385927438735962, + "learning_rate": 1.5117046902734194e-06, + "loss": 0.2665, + "step": 893 + }, + { + "epoch": 1.8963689371852637, + "grad_norm": 1.5480061769485474, + "learning_rate": 1.5065651694835682e-06, + "loss": 0.1806, + "step": 894 + }, + { + "epoch": 1.8984892658362047, + "grad_norm": 1.9919331073760986, + "learning_rate": 1.5014306297747217e-06, + "loss": 0.2988, + "step": 895 + }, + { + "epoch": 1.9006095944871455, + "grad_norm": 0.4841969311237335, + "learning_rate": 1.4963010968914549e-06, + "loss": 0.1248, + "step": 896 + }, + { + "epoch": 1.9027299231380863, + "grad_norm": 2.00504994392395, + "learning_rate": 1.4911765965532398e-06, + "loss": 0.3798, + "step": 897 + }, + { + "epoch": 1.9048502517890273, + "grad_norm": 0.846325695514679, + "learning_rate": 1.4860571544543157e-06, + "loss": 0.2455, + "step": 898 + }, + { + "epoch": 1.9069705804399681, + "grad_norm": 1.6753747463226318, + "learning_rate": 1.480942796263556e-06, + "loss": 0.1762, + "step": 899 + }, + { + "epoch": 1.9090909090909092, + "grad_norm": 1.3008391857147217, + "learning_rate": 1.475833547624349e-06, + "loss": 0.3043, + "step": 900 + }, + { + "epoch": 1.91121123774185, + "grad_norm": 0.8818872570991516, + "learning_rate": 1.4707294341544598e-06, + "loss": 0.1608, + "step": 901 + }, + { + "epoch": 1.9133315663927908, + "grad_norm": 0.6332581639289856, + "learning_rate": 1.4656304814459077e-06, + "loss": 0.1494, + "step": 902 + }, + { + "epoch": 1.9154518950437318, + "grad_norm": 1.6962636709213257, + "learning_rate": 1.4605367150648341e-06, + "loss": 0.1819, + "step": 903 + }, + { + "epoch": 1.9175722236946728, + "grad_norm": 0.4807201623916626, + "learning_rate": 1.455448160551378e-06, + "loss": 0.1381, + "step": 904 + }, + { + "epoch": 1.9196925523456136, + "grad_norm": 1.2451565265655518, + "learning_rate": 1.4503648434195466e-06, + "loss": 0.1973, + "step": 905 + }, + { + "epoch": 1.9218128809965545, + "grad_norm": 1.3982090950012207, + "learning_rate": 1.445286789157084e-06, + "loss": 0.2893, + "step": 906 + }, + { + "epoch": 1.9239332096474953, + "grad_norm": 1.4739251136779785, + "learning_rate": 1.4402140232253486e-06, + "loss": 0.1968, + "step": 907 + }, + { + "epoch": 1.9260535382984363, + "grad_norm": 2.5440287590026855, + "learning_rate": 1.435146571059181e-06, + "loss": 0.1978, + "step": 908 + }, + { + "epoch": 1.9281738669493773, + "grad_norm": 3.4602210521698, + "learning_rate": 1.430084458066784e-06, + "loss": 0.2572, + "step": 909 + }, + { + "epoch": 1.9302941956003181, + "grad_norm": 0.7656342387199402, + "learning_rate": 1.4250277096295817e-06, + "loss": 0.1473, + "step": 910 + }, + { + "epoch": 1.932414524251259, + "grad_norm": 4.068082332611084, + "learning_rate": 1.4199763511021065e-06, + "loss": 0.2889, + "step": 911 + }, + { + "epoch": 1.9345348529021997, + "grad_norm": 0.7085794806480408, + "learning_rate": 1.4149304078118619e-06, + "loss": 0.1495, + "step": 912 + }, + { + "epoch": 1.9366551815531408, + "grad_norm": 0.3622530996799469, + "learning_rate": 1.4098899050592037e-06, + "loss": 0.1174, + "step": 913 + }, + { + "epoch": 1.9387755102040818, + "grad_norm": 1.3513684272766113, + "learning_rate": 1.404854868117206e-06, + "loss": 0.1357, + "step": 914 + }, + { + "epoch": 1.9408958388550226, + "grad_norm": 1.4065253734588623, + "learning_rate": 1.3998253222315363e-06, + "loss": 0.1929, + "step": 915 + }, + { + "epoch": 1.9430161675059634, + "grad_norm": 1.104533076286316, + "learning_rate": 1.394801292620332e-06, + "loss": 0.2133, + "step": 916 + }, + { + "epoch": 1.9451364961569042, + "grad_norm": 1.756828784942627, + "learning_rate": 1.389782804474072e-06, + "loss": 0.2032, + "step": 917 + }, + { + "epoch": 1.9472568248078452, + "grad_norm": 1.4066181182861328, + "learning_rate": 1.3847698829554496e-06, + "loss": 0.1907, + "step": 918 + }, + { + "epoch": 1.9493771534587863, + "grad_norm": 2.111950397491455, + "learning_rate": 1.3797625531992464e-06, + "loss": 0.2204, + "step": 919 + }, + { + "epoch": 1.951497482109727, + "grad_norm": 1.4993287324905396, + "learning_rate": 1.374760840312208e-06, + "loss": 0.2518, + "step": 920 + }, + { + "epoch": 1.9536178107606679, + "grad_norm": 0.8992859125137329, + "learning_rate": 1.3697647693729166e-06, + "loss": 0.1671, + "step": 921 + }, + { + "epoch": 1.9557381394116087, + "grad_norm": 0.6463199853897095, + "learning_rate": 1.3647743654316653e-06, + "loss": 0.1723, + "step": 922 + }, + { + "epoch": 1.9578584680625497, + "grad_norm": 0.7732374668121338, + "learning_rate": 1.3597896535103328e-06, + "loss": 0.1485, + "step": 923 + }, + { + "epoch": 1.9599787967134907, + "grad_norm": 1.8219809532165527, + "learning_rate": 1.3548106586022597e-06, + "loss": 0.1481, + "step": 924 + }, + { + "epoch": 1.9620991253644315, + "grad_norm": 2.0674850940704346, + "learning_rate": 1.3498374056721198e-06, + "loss": 0.2583, + "step": 925 + }, + { + "epoch": 1.9642194540153723, + "grad_norm": 2.160161256790161, + "learning_rate": 1.3448699196557973e-06, + "loss": 0.2165, + "step": 926 + }, + { + "epoch": 1.9663397826663132, + "grad_norm": 1.0526455640792847, + "learning_rate": 1.3399082254602594e-06, + "loss": 0.1807, + "step": 927 + }, + { + "epoch": 1.9684601113172542, + "grad_norm": 2.217966079711914, + "learning_rate": 1.3349523479634368e-06, + "loss": 0.249, + "step": 928 + }, + { + "epoch": 1.9705804399681952, + "grad_norm": 1.8820593357086182, + "learning_rate": 1.3300023120140926e-06, + "loss": 0.1337, + "step": 929 + }, + { + "epoch": 1.972700768619136, + "grad_norm": 2.38179349899292, + "learning_rate": 1.3250581424317012e-06, + "loss": 0.2563, + "step": 930 + }, + { + "epoch": 1.9748210972700768, + "grad_norm": 1.0373716354370117, + "learning_rate": 1.3201198640063196e-06, + "loss": 0.2068, + "step": 931 + }, + { + "epoch": 1.9769414259210176, + "grad_norm": 2.2542104721069336, + "learning_rate": 1.3151875014984734e-06, + "loss": 0.1813, + "step": 932 + }, + { + "epoch": 1.9790617545719587, + "grad_norm": 0.9453467130661011, + "learning_rate": 1.3102610796390209e-06, + "loss": 0.2077, + "step": 933 + }, + { + "epoch": 1.9811820832228997, + "grad_norm": 2.0382044315338135, + "learning_rate": 1.3053406231290348e-06, + "loss": 0.1782, + "step": 934 + }, + { + "epoch": 1.9833024118738405, + "grad_norm": 1.4644185304641724, + "learning_rate": 1.300426156639677e-06, + "loss": 0.2884, + "step": 935 + }, + { + "epoch": 1.9854227405247813, + "grad_norm": 1.245954990386963, + "learning_rate": 1.2955177048120786e-06, + "loss": 0.192, + "step": 936 + }, + { + "epoch": 1.987543069175722, + "grad_norm": 0.672512412071228, + "learning_rate": 1.2906152922572102e-06, + "loss": 0.1134, + "step": 937 + }, + { + "epoch": 1.9896633978266631, + "grad_norm": 1.7579939365386963, + "learning_rate": 1.2857189435557616e-06, + "loss": 0.1924, + "step": 938 + }, + { + "epoch": 1.9917837264776042, + "grad_norm": 1.3811734914779663, + "learning_rate": 1.2808286832580186e-06, + "loss": 0.2068, + "step": 939 + }, + { + "epoch": 1.993904055128545, + "grad_norm": 2.4520797729492188, + "learning_rate": 1.2759445358837419e-06, + "loss": 0.1122, + "step": 940 + }, + { + "epoch": 1.9960243837794858, + "grad_norm": 1.866734266281128, + "learning_rate": 1.2710665259220403e-06, + "loss": 0.2615, + "step": 941 + }, + { + "epoch": 1.9981447124304266, + "grad_norm": 1.1177961826324463, + "learning_rate": 1.2661946778312473e-06, + "loss": 0.1196, + "step": 942 + }, + { + "epoch": 2.0010601643254704, + "grad_norm": 1.9562182426452637, + "learning_rate": 1.2613290160388052e-06, + "loss": 0.2324, + "step": 943 + }, + { + "epoch": 2.003180492976411, + "grad_norm": 1.1798341274261475, + "learning_rate": 1.2564695649411363e-06, + "loss": 0.1671, + "step": 944 + }, + { + "epoch": 2.0053008216273525, + "grad_norm": 1.4037326574325562, + "learning_rate": 1.2516163489035216e-06, + "loss": 0.1219, + "step": 945 + }, + { + "epoch": 2.0074211502782933, + "grad_norm": 1.7019480466842651, + "learning_rate": 1.2467693922599805e-06, + "loss": 0.1258, + "step": 946 + }, + { + "epoch": 2.009541478929234, + "grad_norm": 1.0615661144256592, + "learning_rate": 1.2419287193131468e-06, + "loss": 0.2731, + "step": 947 + }, + { + "epoch": 2.011661807580175, + "grad_norm": 1.3318649530410767, + "learning_rate": 1.23709435433415e-06, + "loss": 0.151, + "step": 948 + }, + { + "epoch": 2.0137821362311157, + "grad_norm": 1.8564578294754028, + "learning_rate": 1.2322663215624898e-06, + "loss": 0.187, + "step": 949 + }, + { + "epoch": 2.015902464882057, + "grad_norm": 1.6483088731765747, + "learning_rate": 1.2274446452059158e-06, + "loss": 0.1094, + "step": 950 + }, + { + "epoch": 2.0180227935329977, + "grad_norm": 1.7207893133163452, + "learning_rate": 1.222629349440308e-06, + "loss": 0.2884, + "step": 951 + }, + { + "epoch": 2.0201431221839385, + "grad_norm": 1.4903310537338257, + "learning_rate": 1.2178204584095526e-06, + "loss": 0.1166, + "step": 952 + }, + { + "epoch": 2.0222634508348794, + "grad_norm": 2.676420211791992, + "learning_rate": 1.213017996225424e-06, + "loss": 0.2639, + "step": 953 + }, + { + "epoch": 2.02438377948582, + "grad_norm": 1.2780916690826416, + "learning_rate": 1.2082219869674603e-06, + "loss": 0.2392, + "step": 954 + }, + { + "epoch": 2.0265041081367614, + "grad_norm": 0.6168650984764099, + "learning_rate": 1.2034324546828477e-06, + "loss": 0.1054, + "step": 955 + }, + { + "epoch": 2.028624436787702, + "grad_norm": 1.404857873916626, + "learning_rate": 1.1986494233862948e-06, + "loss": 0.2579, + "step": 956 + }, + { + "epoch": 2.030744765438643, + "grad_norm": 2.3824305534362793, + "learning_rate": 1.1938729170599136e-06, + "loss": 0.1962, + "step": 957 + }, + { + "epoch": 2.032865094089584, + "grad_norm": 0.960718035697937, + "learning_rate": 1.1891029596531005e-06, + "loss": 0.139, + "step": 958 + }, + { + "epoch": 2.0349854227405246, + "grad_norm": 1.5871549844741821, + "learning_rate": 1.1843395750824183e-06, + "loss": 0.1442, + "step": 959 + }, + { + "epoch": 2.037105751391466, + "grad_norm": 1.264162540435791, + "learning_rate": 1.1795827872314694e-06, + "loss": 0.1862, + "step": 960 + }, + { + "epoch": 2.0392260800424067, + "grad_norm": 0.9427124261856079, + "learning_rate": 1.1748326199507829e-06, + "loss": 0.187, + "step": 961 + }, + { + "epoch": 2.0413464086933475, + "grad_norm": 1.307521939277649, + "learning_rate": 1.1700890970576914e-06, + "loss": 0.1043, + "step": 962 + }, + { + "epoch": 2.0434667373442883, + "grad_norm": 0.6865214109420776, + "learning_rate": 1.1653522423362129e-06, + "loss": 0.1359, + "step": 963 + }, + { + "epoch": 2.045587065995229, + "grad_norm": 1.6144641637802124, + "learning_rate": 1.1606220795369307e-06, + "loss": 0.1808, + "step": 964 + }, + { + "epoch": 2.0477073946461704, + "grad_norm": 0.6050888299942017, + "learning_rate": 1.1558986323768758e-06, + "loss": 0.1454, + "step": 965 + }, + { + "epoch": 2.049827723297111, + "grad_norm": 1.202744483947754, + "learning_rate": 1.1511819245394051e-06, + "loss": 0.1273, + "step": 966 + }, + { + "epoch": 2.051948051948052, + "grad_norm": 0.35640886425971985, + "learning_rate": 1.1464719796740875e-06, + "loss": 0.1516, + "step": 967 + }, + { + "epoch": 2.0540683805989928, + "grad_norm": 2.3331637382507324, + "learning_rate": 1.1417688213965803e-06, + "loss": 0.2406, + "step": 968 + }, + { + "epoch": 2.0561887092499336, + "grad_norm": 1.4808611869812012, + "learning_rate": 1.1370724732885126e-06, + "loss": 0.2046, + "step": 969 + }, + { + "epoch": 2.058309037900875, + "grad_norm": 0.8104944229125977, + "learning_rate": 1.1323829588973676e-06, + "loss": 0.1645, + "step": 970 + }, + { + "epoch": 2.0604293665518156, + "grad_norm": 1.5165859460830688, + "learning_rate": 1.1277003017363661e-06, + "loss": 0.1562, + "step": 971 + }, + { + "epoch": 2.0625496952027564, + "grad_norm": 1.645854115486145, + "learning_rate": 1.1230245252843456e-06, + "loss": 0.1089, + "step": 972 + }, + { + "epoch": 2.0646700238536972, + "grad_norm": 1.7471455335617065, + "learning_rate": 1.1183556529856404e-06, + "loss": 0.216, + "step": 973 + }, + { + "epoch": 2.066790352504638, + "grad_norm": 1.2812058925628662, + "learning_rate": 1.1136937082499733e-06, + "loss": 0.0965, + "step": 974 + }, + { + "epoch": 2.0689106811555793, + "grad_norm": 1.1503514051437378, + "learning_rate": 1.1090387144523284e-06, + "loss": 0.2348, + "step": 975 + }, + { + "epoch": 2.07103100980652, + "grad_norm": 1.0059962272644043, + "learning_rate": 1.1043906949328387e-06, + "loss": 0.1252, + "step": 976 + }, + { + "epoch": 2.073151338457461, + "grad_norm": 1.8063433170318604, + "learning_rate": 1.0997496729966679e-06, + "loss": 0.228, + "step": 977 + }, + { + "epoch": 2.0752716671084017, + "grad_norm": 1.0282273292541504, + "learning_rate": 1.0951156719138953e-06, + "loss": 0.1241, + "step": 978 + }, + { + "epoch": 2.0773919957593425, + "grad_norm": 1.623639464378357, + "learning_rate": 1.090488714919396e-06, + "loss": 0.1477, + "step": 979 + }, + { + "epoch": 2.0795123244102838, + "grad_norm": 1.7182891368865967, + "learning_rate": 1.0858688252127268e-06, + "loss": 0.1195, + "step": 980 + }, + { + "epoch": 2.0816326530612246, + "grad_norm": 1.336841344833374, + "learning_rate": 1.0812560259580076e-06, + "loss": 0.1273, + "step": 981 + }, + { + "epoch": 2.0837529817121654, + "grad_norm": 1.0584746599197388, + "learning_rate": 1.0766503402838103e-06, + "loss": 0.1584, + "step": 982 + }, + { + "epoch": 2.085873310363106, + "grad_norm": 2.303407669067383, + "learning_rate": 1.0720517912830371e-06, + "loss": 0.1586, + "step": 983 + }, + { + "epoch": 2.087993639014047, + "grad_norm": 1.6193451881408691, + "learning_rate": 1.0674604020128051e-06, + "loss": 0.1341, + "step": 984 + }, + { + "epoch": 2.0901139676649882, + "grad_norm": 1.0736302137374878, + "learning_rate": 1.0628761954943343e-06, + "loss": 0.1727, + "step": 985 + }, + { + "epoch": 2.092234296315929, + "grad_norm": 0.9856461882591248, + "learning_rate": 1.0582991947128324e-06, + "loss": 0.1506, + "step": 986 + }, + { + "epoch": 2.09435462496687, + "grad_norm": 0.495143324136734, + "learning_rate": 1.0537294226173748e-06, + "loss": 0.1112, + "step": 987 + }, + { + "epoch": 2.0964749536178107, + "grad_norm": 1.2475007772445679, + "learning_rate": 1.0491669021207929e-06, + "loss": 0.2002, + "step": 988 + }, + { + "epoch": 2.0985952822687515, + "grad_norm": 1.5196057558059692, + "learning_rate": 1.0446116560995582e-06, + "loss": 0.2054, + "step": 989 + }, + { + "epoch": 2.1007156109196927, + "grad_norm": 0.9226682186126709, + "learning_rate": 1.0400637073936697e-06, + "loss": 0.153, + "step": 990 + }, + { + "epoch": 2.1028359395706335, + "grad_norm": 0.7360610961914062, + "learning_rate": 1.0355230788065365e-06, + "loss": 0.1552, + "step": 991 + }, + { + "epoch": 2.1049562682215743, + "grad_norm": 0.5949102640151978, + "learning_rate": 1.030989793104864e-06, + "loss": 0.2001, + "step": 992 + }, + { + "epoch": 2.107076596872515, + "grad_norm": 0.2589457929134369, + "learning_rate": 1.0264638730185409e-06, + "loss": 0.1307, + "step": 993 + }, + { + "epoch": 2.109196925523456, + "grad_norm": 0.5593380928039551, + "learning_rate": 1.021945341240527e-06, + "loss": 0.1668, + "step": 994 + }, + { + "epoch": 2.111317254174397, + "grad_norm": 0.8510894775390625, + "learning_rate": 1.0174342204267323e-06, + "loss": 0.1635, + "step": 995 + }, + { + "epoch": 2.113437582825338, + "grad_norm": 2.4190611839294434, + "learning_rate": 1.012930533195911e-06, + "loss": 0.2443, + "step": 996 + }, + { + "epoch": 2.115557911476279, + "grad_norm": 1.0228517055511475, + "learning_rate": 1.0084343021295476e-06, + "loss": 0.1109, + "step": 997 + }, + { + "epoch": 2.1176782401272196, + "grad_norm": 1.9541192054748535, + "learning_rate": 1.0039455497717376e-06, + "loss": 0.1842, + "step": 998 + }, + { + "epoch": 2.1197985687781604, + "grad_norm": 1.7048015594482422, + "learning_rate": 9.994642986290797e-07, + "loss": 0.1828, + "step": 999 + }, + { + "epoch": 2.1219188974291017, + "grad_norm": 1.2028521299362183, + "learning_rate": 9.949905711705613e-07, + "loss": 0.1531, + "step": 1000 + } + ], + "logging_steps": 1, + "max_steps": 1413, + "num_input_tokens_seen": 0, + "num_train_epochs": 3, + "save_steps": 1000, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 1.373622761187967e+18, + "train_batch_size": 1, + "trial_name": null, + "trial_params": null +} diff --git a/rag_truth_hal_detection_model/checkpoint-1000/training_args.bin b/rag_truth_hal_detection_model/checkpoint-1000/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..7c2f22d4d5100bea19a9b524d6fe22f4b61ba2b8 --- /dev/null +++ b/rag_truth_hal_detection_model/checkpoint-1000/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8cba5214263bc92d48c42393a60c4f497265c69e8a26b939f349b78bea897898 +size 7160 diff --git a/rag_truth_hal_detection_model/checkpoint-1000/zero_to_fp32.py b/rag_truth_hal_detection_model/checkpoint-1000/zero_to_fp32.py new file mode 100644 index 0000000000000000000000000000000000000000..e69ecd9acb5a235ffbf927091051106d902b3d39 --- /dev/null +++ b/rag_truth_hal_detection_model/checkpoint-1000/zero_to_fp32.py @@ -0,0 +1,674 @@ +#!/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 1, 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 . output_dir/ +# or +# python zero_to_fp32.py . output_dir/ --safe_serialization + +import argparse +import torch +import glob +import math +import os +import re +import json +from tqdm import tqdm +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_dict = torch.load(f, map_location=device) + # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights + # and also handle the case where it was already removed by another helper script + state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None) + state_dicts.append(state_dict) + + 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, exclude_frozen_parameters): + """ + 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, + exclude_frozen_parameters) + elif zero_stage == 3: + return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states, + exclude_frozen_parameters) + + +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 _has_callable(obj, fn): + attr = getattr(obj, fn, None) + return callable(attr) + + +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() if _has_callable(shape, 'numel') else math.prod(shape) + 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, + exclude_frozen_parameters): + state_dict = OrderedDict() + + # buffers + buffers = zero_model_states[0].buffers + state_dict.update(buffers) + if debug: + print(f"added {len(buffers)} buffers") + + if not exclude_frozen_parameters: + _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 tqdm(param_shapes.items(), desc='Gathering Sharded Weights'): + 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, + exclude_frozen_parameters): + state_dict = OrderedDict() + + # buffers + buffers = zero_model_states[0].buffers + state_dict.update(buffers) + if debug: + print(f"added {len(buffers)} buffers") + + if not exclude_frozen_parameters: + _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, exclude_frozen_parameters=False): + """ + 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`` + - ``exclude_frozen_parameters``: exclude frozen parameters + + 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, exclude_frozen_parameters) + + +def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, + output_dir, + max_shard_size="5GB", + safe_serialization=False, + tag=None, + exclude_frozen_parameters=False): + """ + 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_dir``: directory to the pytorch fp32 state_dict output files + - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB + - ``safe_serialization``: whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`). + - ``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`` + - ``exclude_frozen_parameters``: exclude frozen parameters + """ + # Dependency pre-check + if safe_serialization: + try: + from safetensors.torch import save_file + except ImportError: + print('If you want to use `safe_serialization`, please `pip install safetensors`') + raise + if max_shard_size is not None: + try: + from huggingface_hub import split_torch_state_dict_into_shards + except ImportError: + print('If you want to use `max_shard_size`, please `pip install huggingface_hub`') + raise + + # Convert zero checkpoint to state_dict + state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters) + + # Shard the model if it is too big. + weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin" + if max_shard_size is not None: + filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors") + state_dict_split = split_torch_state_dict_into_shards(state_dict, + filename_pattern=filename_pattern, + max_shard_size=max_shard_size) + else: + from collections import namedtuple + StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"]) + state_dict_split = StateDictSplit(is_sharded=False, + filename_to_tensors={weights_name: list(state_dict.keys())}) + + # Save the model + filename_to_tensors = state_dict_split.filename_to_tensors.items() + for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"): + shard = {tensor: state_dict[tensor].contiguous() for tensor in tensors} + output_path = os.path.join(output_dir, shard_file) + if safe_serialization: + save_file(shard, output_path, metadata={"format": "pt"}) + else: + torch.save(shard, output_path) + + # Save index if sharded + if state_dict_split.is_sharded: + index = { + "metadata": state_dict_split.metadata, + "weight_map": state_dict_split.tensor_to_filename, + } + save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json" + save_index_file = os.path.join(output_dir, save_index_file) + with open(save_index_file, "w", encoding="utf-8") as f: + content = json.dumps(index, indent=2, sort_keys=True) + "\n" + f.write(content) + + +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_dir", + type=str, + help="directory to the pytorch fp32 state_dict output files" + "(e.g. path/checkpoint-12-output/)") + parser.add_argument( + "--max_shard_size", + type=str, + default="5GB", + help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size" + "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`" + "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances" + "without CPU OOM issues.") + parser.add_argument( + "--safe_serialization", + default=False, + action='store_true', + help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).") + parser.add_argument("-t", + "--tag", + type=str, + default=None, + help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1") + parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters") + 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_dir, + max_shard_size=args.max_shard_size, + safe_serialization=args.safe_serialization, + tag=args.tag, + exclude_frozen_parameters=args.exclude_frozen_parameters) diff --git a/rag_truth_hal_detection_model/checkpoint-1413/config.json b/rag_truth_hal_detection_model/checkpoint-1413/config.json new file mode 100644 index 0000000000000000000000000000000000000000..f79ee026750c76a1b06a7152a3fca58830d69257 --- /dev/null +++ b/rag_truth_hal_detection_model/checkpoint-1413/config.json @@ -0,0 +1,30 @@ +{ + "_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "eos_token_id": 128009, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 8192, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.46.1", + "use_cache": false, + "vocab_size": 128256 +} diff --git a/rag_truth_hal_detection_model/checkpoint-1413/generation_config.json b/rag_truth_hal_detection_model/checkpoint-1413/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..db0ea5c7647aac3cdc0802b1e95a53d09351382a --- /dev/null +++ b/rag_truth_hal_detection_model/checkpoint-1413/generation_config.json @@ -0,0 +1,12 @@ +{ + "bos_token_id": 128000, + "do_sample": true, + "eos_token_id": [ + 128001, + 128009 + ], + "max_length": 4096, + "temperature": 0.6, + "top_p": 0.9, + "transformers_version": "4.46.1" +} diff --git a/rag_truth_hal_detection_model/checkpoint-1413/global_step1413/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt b/rag_truth_hal_detection_model/checkpoint-1413/global_step1413/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..2f017af830e37e85795ea5c55a8afb4711aefd25 --- /dev/null +++ b/rag_truth_hal_detection_model/checkpoint-1413/global_step1413/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:a41810222c1ba77e38b84fc885b7a9984cea58e8c2c72b9521dde7230625b50b +size 24090793600 diff --git a/rag_truth_hal_detection_model/checkpoint-1413/global_step1413/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt b/rag_truth_hal_detection_model/checkpoint-1413/global_step1413/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..3c36497220e128b93a054c27a31298df3471ab9d --- /dev/null +++ b/rag_truth_hal_detection_model/checkpoint-1413/global_step1413/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e8b8a1269e31f31c590acded7bd62b6bf6f317d4c3f7a9c0da6dca268d79517 +size 24090794752 diff --git a/rag_truth_hal_detection_model/checkpoint-1413/global_step1413/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt b/rag_truth_hal_detection_model/checkpoint-1413/global_step1413/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..85a815807667e307858acafbfdc4989d7690f106 --- /dev/null +++ b/rag_truth_hal_detection_model/checkpoint-1413/global_step1413/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12a4c1703d5ddefd8e1d709a2fc80f5bad6e99b2d0b3aa0af05cb16fa9377203 +size 24090795072 diff --git a/rag_truth_hal_detection_model/checkpoint-1413/global_step1413/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt b/rag_truth_hal_detection_model/checkpoint-1413/global_step1413/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..0a93187e9ba17b2b73b1dd1ea69db8b2bfed0774 --- /dev/null +++ b/rag_truth_hal_detection_model/checkpoint-1413/global_step1413/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0196088a03cb040108bf144e5fb0259e4a84a90d2280428bbe2043aaaa391bd4 +size 24090793280 diff --git a/rag_truth_hal_detection_model/checkpoint-1413/global_step1413/mp_rank_00_model_states.pt b/rag_truth_hal_detection_model/checkpoint-1413/global_step1413/mp_rank_00_model_states.pt new file mode 100644 index 0000000000000000000000000000000000000000..cfe06e478271201f178c1830c8f0af374ab04699 --- /dev/null +++ b/rag_truth_hal_detection_model/checkpoint-1413/global_step1413/mp_rank_00_model_states.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c50cdbe9b57d5a0615ed49717a30ec9d2292611eb078c7ce3ef51cac84519d1 +size 16060610744 diff --git a/rag_truth_hal_detection_model/checkpoint-1413/latest b/rag_truth_hal_detection_model/checkpoint-1413/latest new file mode 100644 index 0000000000000000000000000000000000000000..4ab5cf27f545219a10e440f21cd67c9f9a50c257 --- /dev/null +++ b/rag_truth_hal_detection_model/checkpoint-1413/latest @@ -0,0 +1 @@ +global_step1413 \ No newline at end of file diff --git a/rag_truth_hal_detection_model/checkpoint-1413/model-00001-of-00004.safetensors b/rag_truth_hal_detection_model/checkpoint-1413/model-00001-of-00004.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..05b4f012dc56f55b5b637540e457ab80ccd30870 --- /dev/null +++ b/rag_truth_hal_detection_model/checkpoint-1413/model-00001-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6dcbabfb5aa90e49da2f74b8cd606eca124c05b928a709f0cd0089f8de8f8ca +size 4976698672 diff --git a/rag_truth_hal_detection_model/checkpoint-1413/model-00002-of-00004.safetensors b/rag_truth_hal_detection_model/checkpoint-1413/model-00002-of-00004.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9d55e8b109089210358018dfcce8ac0a4fcf52f2 --- /dev/null +++ b/rag_truth_hal_detection_model/checkpoint-1413/model-00002-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0835acd1f3b1bf1e719cf7031e92121f25e53758325b490785093185d1e4d6a +size 4999802720 diff --git a/rag_truth_hal_detection_model/checkpoint-1413/model-00003-of-00004.safetensors b/rag_truth_hal_detection_model/checkpoint-1413/model-00003-of-00004.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0908f389554f6ab9cbf67f7ef2edeb8a6d1797be --- /dev/null +++ b/rag_truth_hal_detection_model/checkpoint-1413/model-00003-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:473a41b96d7ff16e2e4b502b7103abbd861bad929138990987618cb47dd098f1 +size 4915916176 diff --git a/rag_truth_hal_detection_model/checkpoint-1413/model-00004-of-00004.safetensors b/rag_truth_hal_detection_model/checkpoint-1413/model-00004-of-00004.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..17efbf01269845f06244546ce121b43167dc531f --- /dev/null +++ b/rag_truth_hal_detection_model/checkpoint-1413/model-00004-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abc9304c6a0db86d38ce5a5b7b199fc900360e842415c16223714aaf76e30005 +size 1168138808 diff --git a/rag_truth_hal_detection_model/checkpoint-1413/model.safetensors.index.json b/rag_truth_hal_detection_model/checkpoint-1413/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..0fd8120f1c6acddc268ebc2583058efaf699a771 --- /dev/null +++ b/rag_truth_hal_detection_model/checkpoint-1413/model.safetensors.index.json @@ -0,0 +1,298 @@ +{ + "metadata": { + "total_size": 16060522496 + }, + "weight_map": { + "lm_head.weight": "model-00004-of-00004.safetensors", + "model.embed_tokens.weight": "model-00001-of-00004.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.norm.weight": "model-00004-of-00004.safetensors" + } +} diff --git a/rag_truth_hal_detection_model/checkpoint-1413/rng_state_0.pth b/rag_truth_hal_detection_model/checkpoint-1413/rng_state_0.pth new file mode 100644 index 0000000000000000000000000000000000000000..5a7c482c30381cd512ccc35fe322d8a34fbf5207 --- /dev/null +++ b/rag_truth_hal_detection_model/checkpoint-1413/rng_state_0.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:308f94f9a5c24e1bad5c393d56ae7af7782600f4e791d9c6ac35b22fff2105b6 +size 15024 diff --git a/rag_truth_hal_detection_model/checkpoint-1413/rng_state_1.pth b/rag_truth_hal_detection_model/checkpoint-1413/rng_state_1.pth new file mode 100644 index 0000000000000000000000000000000000000000..7b862c21b28bbd89ce6b4fb681d41be05f175599 --- /dev/null +++ b/rag_truth_hal_detection_model/checkpoint-1413/rng_state_1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b056f3c23cb32dc77a2ec9e7651e0b64e4440e21f0fdf969b86bfc56a1cbdf06 +size 15024 diff --git a/rag_truth_hal_detection_model/checkpoint-1413/rng_state_2.pth b/rag_truth_hal_detection_model/checkpoint-1413/rng_state_2.pth new file mode 100644 index 0000000000000000000000000000000000000000..d86ce886844e0298f058d67065e5eeb27ffe7e48 --- /dev/null +++ b/rag_truth_hal_detection_model/checkpoint-1413/rng_state_2.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3f8a05714bc528f4885a2816181652f2303b3e8150f89b56aaee6bec56aa520 +size 15024 diff --git a/rag_truth_hal_detection_model/checkpoint-1413/rng_state_3.pth b/rag_truth_hal_detection_model/checkpoint-1413/rng_state_3.pth new file mode 100644 index 0000000000000000000000000000000000000000..10733f5da657367adf3f67760028644c0839660f --- /dev/null +++ b/rag_truth_hal_detection_model/checkpoint-1413/rng_state_3.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f755bd3c330281961e5c03af9d10ce8c1e1678619d384f6f1fd5fd7dce2ff50 +size 15024 diff --git a/rag_truth_hal_detection_model/checkpoint-1413/scheduler.pt b/rag_truth_hal_detection_model/checkpoint-1413/scheduler.pt new file mode 100644 index 0000000000000000000000000000000000000000..33fc4bb87c7ad3246dd21b12a37f7f9fd1a6c969 --- /dev/null +++ b/rag_truth_hal_detection_model/checkpoint-1413/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02ab6711d9a882f3d736de3e1b2cfe1a8e5157ec16da89a19fae03e881c393ee +size 1064 diff --git a/rag_truth_hal_detection_model/checkpoint-1413/special_tokens_map.json b/rag_truth_hal_detection_model/checkpoint-1413/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..b43be96621d147110fb8a18b5776ec6e38516127 --- /dev/null +++ b/rag_truth_hal_detection_model/checkpoint-1413/special_tokens_map.json @@ -0,0 +1,17 @@ +{ + "bos_token": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "<|eot_id|>" +} diff --git a/rag_truth_hal_detection_model/checkpoint-1413/tokenizer.json b/rag_truth_hal_detection_model/checkpoint-1413/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..86a33946b0c77216d2cce91bb28c8fada4a5e80b --- /dev/null +++ b/rag_truth_hal_detection_model/checkpoint-1413/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c5cf44023714fb39b05e71e425f8d7b92805ff73f7988b083b8c87f0bf87393 +size 17209961 diff --git a/rag_truth_hal_detection_model/checkpoint-1413/tokenizer_config.json b/rag_truth_hal_detection_model/checkpoint-1413/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..82b337616471d4177c3b572a92a182f302f28430 --- /dev/null +++ b/rag_truth_hal_detection_model/checkpoint-1413/tokenizer_config.json @@ -0,0 +1,2065 @@ +{ + "added_tokens_decoder": { + "128000": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128001": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128002": { + "content": "<|reserved_special_token_0|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128003": { + "content": "<|reserved_special_token_1|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128004": { + "content": "<|reserved_special_token_2|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128005": { + "content": "<|reserved_special_token_3|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128006": { + "content": "<|start_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128007": { + "content": "<|end_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128008": { + "content": "<|reserved_special_token_4|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128009": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128010": { + "content": "<|reserved_special_token_5|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128011": { + "content": "<|reserved_special_token_6|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128012": { + "content": "<|reserved_special_token_7|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128013": { + "content": "<|reserved_special_token_8|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128014": { + "content": "<|reserved_special_token_9|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128015": { + "content": "<|reserved_special_token_10|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128016": { + "content": "<|reserved_special_token_11|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128017": { + "content": "<|reserved_special_token_12|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128018": { + "content": "<|reserved_special_token_13|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128019": { + "content": "<|reserved_special_token_14|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128020": { + "content": "<|reserved_special_token_15|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128021": { + "content": "<|reserved_special_token_16|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128022": { + "content": "<|reserved_special_token_17|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128023": { + "content": "<|reserved_special_token_18|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128024": { + "content": "<|reserved_special_token_19|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128025": { + "content": "<|reserved_special_token_20|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128026": { + "content": "<|reserved_special_token_21|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128027": { + "content": "<|reserved_special_token_22|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128028": { + "content": "<|reserved_special_token_23|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128029": { + "content": "<|reserved_special_token_24|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128030": { + "content": "<|reserved_special_token_25|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128031": { + "content": "<|reserved_special_token_26|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128032": { + "content": "<|reserved_special_token_27|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128033": { + "content": "<|reserved_special_token_28|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128034": { + "content": "<|reserved_special_token_29|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128035": { + "content": "<|reserved_special_token_30|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128036": { + "content": "<|reserved_special_token_31|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128037": { + "content": "<|reserved_special_token_32|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128038": { + "content": "<|reserved_special_token_33|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128039": { + "content": "<|reserved_special_token_34|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128040": { + "content": "<|reserved_special_token_35|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128041": { + "content": "<|reserved_special_token_36|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128042": { + "content": "<|reserved_special_token_37|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128043": { + "content": "<|reserved_special_token_38|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128044": { + "content": "<|reserved_special_token_39|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128045": { + "content": "<|reserved_special_token_40|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128046": { + "content": "<|reserved_special_token_41|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128047": { + "content": "<|reserved_special_token_42|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128048": { + "content": "<|reserved_special_token_43|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128049": { + "content": "<|reserved_special_token_44|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128050": { + "content": "<|reserved_special_token_45|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128051": { + "content": "<|reserved_special_token_46|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128052": { + "content": "<|reserved_special_token_47|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128053": { + "content": "<|reserved_special_token_48|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128054": { + "content": "<|reserved_special_token_49|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128055": { + "content": "<|reserved_special_token_50|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128056": { + "content": "<|reserved_special_token_51|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128057": { + "content": "<|reserved_special_token_52|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128058": { + "content": "<|reserved_special_token_53|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128059": { + "content": "<|reserved_special_token_54|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128060": { + "content": "<|reserved_special_token_55|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128061": { + "content": "<|reserved_special_token_56|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128062": { + "content": "<|reserved_special_token_57|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128063": { + "content": "<|reserved_special_token_58|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128064": { + "content": "<|reserved_special_token_59|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128065": { + "content": "<|reserved_special_token_60|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128066": { + "content": "<|reserved_special_token_61|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128067": { + "content": "<|reserved_special_token_62|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128068": { + "content": "<|reserved_special_token_63|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128069": { + "content": "<|reserved_special_token_64|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128070": { + "content": "<|reserved_special_token_65|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128071": { + "content": "<|reserved_special_token_66|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128072": { + "content": "<|reserved_special_token_67|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128073": { + "content": "<|reserved_special_token_68|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128074": { + "content": "<|reserved_special_token_69|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128075": { + "content": "<|reserved_special_token_70|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128076": { + "content": "<|reserved_special_token_71|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128077": { + "content": "<|reserved_special_token_72|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128078": { + "content": "<|reserved_special_token_73|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128079": { + "content": "<|reserved_special_token_74|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128080": { + "content": "<|reserved_special_token_75|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128081": { + "content": "<|reserved_special_token_76|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128082": { + "content": "<|reserved_special_token_77|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128083": { + "content": "<|reserved_special_token_78|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128084": { + "content": "<|reserved_special_token_79|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128085": { + "content": "<|reserved_special_token_80|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128086": { + "content": "<|reserved_special_token_81|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128087": { + "content": "<|reserved_special_token_82|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128088": { + "content": "<|reserved_special_token_83|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128089": { + "content": "<|reserved_special_token_84|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128090": { + "content": "<|reserved_special_token_85|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128091": { + "content": "<|reserved_special_token_86|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128092": { + "content": "<|reserved_special_token_87|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128093": { + "content": "<|reserved_special_token_88|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128094": { + "content": "<|reserved_special_token_89|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128095": { + "content": "<|reserved_special_token_90|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128096": { + "content": "<|reserved_special_token_91|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128097": { + "content": "<|reserved_special_token_92|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128098": { + "content": "<|reserved_special_token_93|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128099": { + "content": "<|reserved_special_token_94|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128100": { + "content": "<|reserved_special_token_95|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128101": { + "content": "<|reserved_special_token_96|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128102": { + "content": "<|reserved_special_token_97|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128103": { + "content": "<|reserved_special_token_98|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128104": { + "content": "<|reserved_special_token_99|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128105": { + "content": "<|reserved_special_token_100|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128106": { + "content": "<|reserved_special_token_101|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128107": { + "content": "<|reserved_special_token_102|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128108": { + "content": "<|reserved_special_token_103|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128109": { + "content": "<|reserved_special_token_104|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128110": { + "content": "<|reserved_special_token_105|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128111": { + "content": "<|reserved_special_token_106|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128112": { + "content": "<|reserved_special_token_107|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128113": { + "content": "<|reserved_special_token_108|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128114": { + "content": "<|reserved_special_token_109|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128115": { + "content": "<|reserved_special_token_110|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128116": { + "content": "<|reserved_special_token_111|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128117": { + "content": "<|reserved_special_token_112|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128118": { + "content": "<|reserved_special_token_113|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128119": { + "content": "<|reserved_special_token_114|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128120": { + "content": "<|reserved_special_token_115|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128121": { + "content": "<|reserved_special_token_116|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128122": { + "content": "<|reserved_special_token_117|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128123": { + "content": "<|reserved_special_token_118|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128124": { + "content": "<|reserved_special_token_119|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128125": { + "content": "<|reserved_special_token_120|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128126": { + "content": "<|reserved_special_token_121|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128127": { + "content": "<|reserved_special_token_122|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128128": { + "content": "<|reserved_special_token_123|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128129": { + "content": "<|reserved_special_token_124|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128130": { + "content": "<|reserved_special_token_125|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128131": { + "content": "<|reserved_special_token_126|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128132": { + "content": "<|reserved_special_token_127|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128133": { + "content": "<|reserved_special_token_128|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128134": { + "content": "<|reserved_special_token_129|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128135": { + "content": "<|reserved_special_token_130|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128136": { + "content": "<|reserved_special_token_131|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128137": { + "content": "<|reserved_special_token_132|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128138": { + "content": "<|reserved_special_token_133|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128139": { + "content": "<|reserved_special_token_134|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128140": { + "content": "<|reserved_special_token_135|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128141": { + "content": "<|reserved_special_token_136|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128142": { + "content": "<|reserved_special_token_137|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128143": { + "content": "<|reserved_special_token_138|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128144": { + "content": "<|reserved_special_token_139|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128145": { + "content": "<|reserved_special_token_140|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128146": { + "content": "<|reserved_special_token_141|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128147": { + "content": "<|reserved_special_token_142|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128148": { + "content": "<|reserved_special_token_143|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128149": { + "content": "<|reserved_special_token_144|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128150": { + "content": "<|reserved_special_token_145|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128151": { + "content": "<|reserved_special_token_146|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128152": { + "content": "<|reserved_special_token_147|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128153": { + "content": "<|reserved_special_token_148|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128154": { + "content": "<|reserved_special_token_149|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128155": { + "content": "<|reserved_special_token_150|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128156": { + "content": "<|reserved_special_token_151|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128157": { + "content": "<|reserved_special_token_152|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128158": { + "content": "<|reserved_special_token_153|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128159": { + "content": "<|reserved_special_token_154|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128160": { + "content": "<|reserved_special_token_155|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128161": { + "content": "<|reserved_special_token_156|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128162": { + "content": "<|reserved_special_token_157|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128163": { + "content": "<|reserved_special_token_158|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128164": { + "content": "<|reserved_special_token_159|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128165": { + "content": "<|reserved_special_token_160|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128166": { + "content": "<|reserved_special_token_161|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128167": { + "content": "<|reserved_special_token_162|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128168": { + "content": "<|reserved_special_token_163|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128169": { + "content": "<|reserved_special_token_164|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128170": { + "content": "<|reserved_special_token_165|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128171": { + "content": "<|reserved_special_token_166|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128172": { + "content": "<|reserved_special_token_167|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128173": { + "content": "<|reserved_special_token_168|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128174": { + "content": "<|reserved_special_token_169|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128175": { + "content": "<|reserved_special_token_170|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128176": { + "content": "<|reserved_special_token_171|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128177": { + "content": "<|reserved_special_token_172|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128178": { + "content": "<|reserved_special_token_173|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128179": { + "content": "<|reserved_special_token_174|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128180": { + "content": "<|reserved_special_token_175|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128181": { + "content": "<|reserved_special_token_176|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128182": { + "content": "<|reserved_special_token_177|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128183": { + "content": "<|reserved_special_token_178|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128184": { + "content": "<|reserved_special_token_179|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128185": { + "content": "<|reserved_special_token_180|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128186": { + "content": "<|reserved_special_token_181|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128187": { + "content": "<|reserved_special_token_182|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128188": { + "content": "<|reserved_special_token_183|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128189": { + "content": "<|reserved_special_token_184|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128190": { + "content": "<|reserved_special_token_185|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128191": { + "content": "<|reserved_special_token_186|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128192": { + "content": "<|reserved_special_token_187|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128193": { + "content": "<|reserved_special_token_188|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128194": { + "content": "<|reserved_special_token_189|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128195": { + "content": "<|reserved_special_token_190|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128196": { + "content": "<|reserved_special_token_191|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128197": { + "content": "<|reserved_special_token_192|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128198": { + "content": "<|reserved_special_token_193|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128199": { + "content": "<|reserved_special_token_194|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128200": { + "content": "<|reserved_special_token_195|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128201": { + "content": "<|reserved_special_token_196|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128202": { + "content": "<|reserved_special_token_197|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128203": { + "content": "<|reserved_special_token_198|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128204": { + "content": "<|reserved_special_token_199|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128205": { + "content": "<|reserved_special_token_200|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128206": { + "content": "<|reserved_special_token_201|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128207": { + "content": "<|reserved_special_token_202|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128208": { + "content": "<|reserved_special_token_203|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128209": { + "content": "<|reserved_special_token_204|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128210": { + "content": "<|reserved_special_token_205|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128211": { + "content": "<|reserved_special_token_206|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128212": { + "content": "<|reserved_special_token_207|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128213": { + "content": "<|reserved_special_token_208|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128214": { + "content": "<|reserved_special_token_209|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128215": { + "content": "<|reserved_special_token_210|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128216": { + "content": "<|reserved_special_token_211|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128217": { + "content": "<|reserved_special_token_212|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128218": { + "content": "<|reserved_special_token_213|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128219": { + "content": "<|reserved_special_token_214|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128220": { + "content": "<|reserved_special_token_215|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128221": { + "content": "<|reserved_special_token_216|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128222": { + "content": "<|reserved_special_token_217|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128223": { + "content": "<|reserved_special_token_218|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128224": { + "content": "<|reserved_special_token_219|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128225": { + "content": "<|reserved_special_token_220|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128226": { + "content": "<|reserved_special_token_221|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128227": { + "content": "<|reserved_special_token_222|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128228": { + "content": "<|reserved_special_token_223|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128229": { + "content": "<|reserved_special_token_224|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128230": { + "content": "<|reserved_special_token_225|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128231": { + "content": "<|reserved_special_token_226|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128232": { + "content": "<|reserved_special_token_227|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128233": { + "content": "<|reserved_special_token_228|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128234": { + "content": "<|reserved_special_token_229|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128235": { + "content": "<|reserved_special_token_230|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128236": { + "content": "<|reserved_special_token_231|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128237": { + "content": "<|reserved_special_token_232|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128238": { + "content": "<|reserved_special_token_233|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128239": { + "content": "<|reserved_special_token_234|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128240": { + "content": "<|reserved_special_token_235|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128241": { + "content": "<|reserved_special_token_236|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128242": { + "content": "<|reserved_special_token_237|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128243": { + "content": "<|reserved_special_token_238|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128244": { + "content": "<|reserved_special_token_239|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128245": { + "content": "<|reserved_special_token_240|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128246": { + "content": "<|reserved_special_token_241|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128247": { + "content": "<|reserved_special_token_242|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128248": { + "content": "<|reserved_special_token_243|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128249": { + "content": "<|reserved_special_token_244|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128250": { + "content": "<|reserved_special_token_245|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128251": { + "content": "<|reserved_special_token_246|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128252": { + "content": "<|reserved_special_token_247|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128253": { + "content": "<|reserved_special_token_248|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128254": { + "content": "<|reserved_special_token_249|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128255": { + "content": "<|reserved_special_token_250|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "<|begin_of_text|>", + "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}", + "clean_up_tokenization_spaces": true, + "eos_token": "<|eot_id|>", + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 1000000000000000019884624838656, + "pad_token": "<|eot_id|>", + "padding_side": "right", + "split_special_tokens": false, + "tokenizer_class": "PreTrainedTokenizerFast" +} diff --git a/rag_truth_hal_detection_model/checkpoint-1413/trainer_state.json b/rag_truth_hal_detection_model/checkpoint-1413/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..a3fb8f34a50b9cb2376a5af93a08324db8d30ed9 --- /dev/null +++ b/rag_truth_hal_detection_model/checkpoint-1413/trainer_state.json @@ -0,0 +1,9924 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 2.9976146302676914, + "eval_steps": 500, + "global_step": 1413, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0021203286509408957, + "grad_norm": 25.949520111083984, + "learning_rate": 5.000000000000001e-07, + "loss": 1.2577, + "step": 1 + }, + { + "epoch": 0.004240657301881791, + "grad_norm": 27.748842239379883, + "learning_rate": 1.0000000000000002e-06, + "loss": 1.1764, + "step": 2 + }, + { + "epoch": 0.0063609859528226875, + "grad_norm": 25.2868595123291, + "learning_rate": 1.5e-06, + "loss": 1.1581, + "step": 3 + }, + { + "epoch": 0.008481314603763583, + "grad_norm": 26.029958724975586, + "learning_rate": 2.0000000000000003e-06, + "loss": 0.9151, + "step": 4 + }, + { + "epoch": 0.010601643254704479, + "grad_norm": 15.586308479309082, + "learning_rate": 2.5e-06, + "loss": 0.5946, + "step": 5 + }, + { + "epoch": 0.012721971905645375, + "grad_norm": 24.38088607788086, + "learning_rate": 3e-06, + "loss": 0.514, + "step": 6 + }, + { + "epoch": 0.014842300556586271, + "grad_norm": 15.221429824829102, + "learning_rate": 3.5e-06, + "loss": 0.3226, + "step": 7 + }, + { + "epoch": 0.016962629207527165, + "grad_norm": 12.0006742477417, + "learning_rate": 4.000000000000001e-06, + "loss": 0.3853, + "step": 8 + }, + { + "epoch": 0.01908295785846806, + "grad_norm": 4.748922348022461, + "learning_rate": 4.5e-06, + "loss": 0.2983, + "step": 9 + }, + { + "epoch": 0.021203286509408958, + "grad_norm": 2.3620359897613525, + "learning_rate": 5e-06, + "loss": 0.4318, + "step": 10 + }, + { + "epoch": 0.023323615160349854, + "grad_norm": 8.839906692504883, + "learning_rate": 4.9999937325015554e-06, + "loss": 0.4925, + "step": 11 + }, + { + "epoch": 0.02544394381129075, + "grad_norm": 4.359335422515869, + "learning_rate": 4.999974930037645e-06, + "loss": 0.4128, + "step": 12 + }, + { + "epoch": 0.027564272462231646, + "grad_norm": 2.051809310913086, + "learning_rate": 4.999943592702547e-06, + "loss": 0.3941, + "step": 13 + }, + { + "epoch": 0.029684601113172542, + "grad_norm": 4.041887283325195, + "learning_rate": 4.999899720653384e-06, + "loss": 0.527, + "step": 14 + }, + { + "epoch": 0.031804929764113435, + "grad_norm": 4.354254245758057, + "learning_rate": 4.999843314110132e-06, + "loss": 0.5217, + "step": 15 + }, + { + "epoch": 0.03392525841505433, + "grad_norm": 4.818948268890381, + "learning_rate": 4.999774373355613e-06, + "loss": 0.262, + "step": 16 + }, + { + "epoch": 0.03604558706599523, + "grad_norm": 4.6067585945129395, + "learning_rate": 4.999692898735496e-06, + "loss": 0.5101, + "step": 17 + }, + { + "epoch": 0.03816591571693612, + "grad_norm": 4.296671390533447, + "learning_rate": 4.999598890658294e-06, + "loss": 0.376, + "step": 18 + }, + { + "epoch": 0.04028624436787702, + "grad_norm": 5.08732795715332, + "learning_rate": 4.999492349595364e-06, + "loss": 0.3747, + "step": 19 + }, + { + "epoch": 0.042406573018817915, + "grad_norm": 4.986461639404297, + "learning_rate": 4.999373276080902e-06, + "loss": 0.3933, + "step": 20 + }, + { + "epoch": 0.04452690166975881, + "grad_norm": 3.174241781234741, + "learning_rate": 4.999241670711944e-06, + "loss": 0.3696, + "step": 21 + }, + { + "epoch": 0.04664723032069971, + "grad_norm": 2.13350510597229, + "learning_rate": 4.999097534148358e-06, + "loss": 0.3125, + "step": 22 + }, + { + "epoch": 0.048767558971640604, + "grad_norm": 15.487786293029785, + "learning_rate": 4.998940867112844e-06, + "loss": 0.4218, + "step": 23 + }, + { + "epoch": 0.0508878876225815, + "grad_norm": 4.8160552978515625, + "learning_rate": 4.998771670390931e-06, + "loss": 0.3827, + "step": 24 + }, + { + "epoch": 0.053008216273522396, + "grad_norm": 3.281799077987671, + "learning_rate": 4.998589944830973e-06, + "loss": 0.4637, + "step": 25 + }, + { + "epoch": 0.05512854492446329, + "grad_norm": 3.690784454345703, + "learning_rate": 4.998395691344138e-06, + "loss": 0.3562, + "step": 26 + }, + { + "epoch": 0.05724887357540419, + "grad_norm": 3.4011573791503906, + "learning_rate": 4.998188910904416e-06, + "loss": 0.3842, + "step": 27 + }, + { + "epoch": 0.059369202226345084, + "grad_norm": 4.38139533996582, + "learning_rate": 4.997969604548602e-06, + "loss": 0.3048, + "step": 28 + }, + { + "epoch": 0.06148953087728598, + "grad_norm": 2.751617908477783, + "learning_rate": 4.997737773376298e-06, + "loss": 0.3621, + "step": 29 + }, + { + "epoch": 0.06360985952822687, + "grad_norm": 4.899576187133789, + "learning_rate": 4.997493418549905e-06, + "loss": 0.2974, + "step": 30 + }, + { + "epoch": 0.06573018817916777, + "grad_norm": 1.5958459377288818, + "learning_rate": 4.99723654129462e-06, + "loss": 0.445, + "step": 31 + }, + { + "epoch": 0.06785051683010866, + "grad_norm": 4.093502521514893, + "learning_rate": 4.996967142898423e-06, + "loss": 0.3759, + "step": 32 + }, + { + "epoch": 0.06997084548104957, + "grad_norm": 0.6687224507331848, + "learning_rate": 4.996685224712077e-06, + "loss": 0.3232, + "step": 33 + }, + { + "epoch": 0.07209117413199045, + "grad_norm": 3.0124692916870117, + "learning_rate": 4.99639078814912e-06, + "loss": 0.4248, + "step": 34 + }, + { + "epoch": 0.07421150278293136, + "grad_norm": 2.5640933513641357, + "learning_rate": 4.996083834685858e-06, + "loss": 0.2229, + "step": 35 + }, + { + "epoch": 0.07633183143387225, + "grad_norm": 6.7540812492370605, + "learning_rate": 4.995764365861354e-06, + "loss": 0.316, + "step": 36 + }, + { + "epoch": 0.07845216008481315, + "grad_norm": 4.984259605407715, + "learning_rate": 4.9954323832774235e-06, + "loss": 0.3061, + "step": 37 + }, + { + "epoch": 0.08057248873575404, + "grad_norm": 2.3390185832977295, + "learning_rate": 4.995087888598629e-06, + "loss": 0.3889, + "step": 38 + }, + { + "epoch": 0.08269281738669494, + "grad_norm": 3.226795196533203, + "learning_rate": 4.994730883552263e-06, + "loss": 0.3944, + "step": 39 + }, + { + "epoch": 0.08481314603763583, + "grad_norm": 3.2235963344573975, + "learning_rate": 4.994361369928352e-06, + "loss": 0.5437, + "step": 40 + }, + { + "epoch": 0.08693347468857673, + "grad_norm": 5.956916809082031, + "learning_rate": 4.993979349579635e-06, + "loss": 0.357, + "step": 41 + }, + { + "epoch": 0.08905380333951762, + "grad_norm": 5.488076210021973, + "learning_rate": 4.9935848244215615e-06, + "loss": 0.3081, + "step": 42 + }, + { + "epoch": 0.09117413199045853, + "grad_norm": 2.534620761871338, + "learning_rate": 4.993177796432281e-06, + "loss": 0.3468, + "step": 43 + }, + { + "epoch": 0.09329446064139942, + "grad_norm": 3.6338629722595215, + "learning_rate": 4.99275826765263e-06, + "loss": 0.3266, + "step": 44 + }, + { + "epoch": 0.09541478929234032, + "grad_norm": 3.6629638671875, + "learning_rate": 4.992326240186127e-06, + "loss": 0.3799, + "step": 45 + }, + { + "epoch": 0.09753511794328121, + "grad_norm": 3.4478704929351807, + "learning_rate": 4.991881716198955e-06, + "loss": 0.3149, + "step": 46 + }, + { + "epoch": 0.09965544659422211, + "grad_norm": 1.566508412361145, + "learning_rate": 4.9914246979199586e-06, + "loss": 0.2163, + "step": 47 + }, + { + "epoch": 0.101775775245163, + "grad_norm": 2.76956844329834, + "learning_rate": 4.990955187640627e-06, + "loss": 0.4008, + "step": 48 + }, + { + "epoch": 0.1038961038961039, + "grad_norm": 3.9344685077667236, + "learning_rate": 4.990473187715082e-06, + "loss": 0.3937, + "step": 49 + }, + { + "epoch": 0.10601643254704479, + "grad_norm": 2.5321309566497803, + "learning_rate": 4.989978700560073e-06, + "loss": 0.381, + "step": 50 + }, + { + "epoch": 0.10813676119798568, + "grad_norm": 3.8619720935821533, + "learning_rate": 4.9894717286549566e-06, + "loss": 0.2995, + "step": 51 + }, + { + "epoch": 0.11025708984892658, + "grad_norm": 8.722846031188965, + "learning_rate": 4.98895227454169e-06, + "loss": 0.2401, + "step": 52 + }, + { + "epoch": 0.11237741849986747, + "grad_norm": 1.9420874118804932, + "learning_rate": 4.9884203408248145e-06, + "loss": 0.3294, + "step": 53 + }, + { + "epoch": 0.11449774715080838, + "grad_norm": 2.523827314376831, + "learning_rate": 4.987875930171446e-06, + "loss": 0.4972, + "step": 54 + }, + { + "epoch": 0.11661807580174927, + "grad_norm": 3.6966936588287354, + "learning_rate": 4.987319045311259e-06, + "loss": 0.4146, + "step": 55 + }, + { + "epoch": 0.11873840445269017, + "grad_norm": 2.447277069091797, + "learning_rate": 4.9867496890364734e-06, + "loss": 0.3277, + "step": 56 + }, + { + "epoch": 0.12085873310363106, + "grad_norm": 2.2751476764678955, + "learning_rate": 4.98616786420184e-06, + "loss": 0.2963, + "step": 57 + }, + { + "epoch": 0.12297906175457196, + "grad_norm": 1.655998706817627, + "learning_rate": 4.985573573724628e-06, + "loss": 0.2798, + "step": 58 + }, + { + "epoch": 0.12509939040551285, + "grad_norm": 5.7478837966918945, + "learning_rate": 4.98496682058461e-06, + "loss": 0.3764, + "step": 59 + }, + { + "epoch": 0.12721971905645374, + "grad_norm": 1.5899176597595215, + "learning_rate": 4.984347607824045e-06, + "loss": 0.2544, + "step": 60 + }, + { + "epoch": 0.12934004770739466, + "grad_norm": 2.066739082336426, + "learning_rate": 4.9837159385476655e-06, + "loss": 0.3421, + "step": 61 + }, + { + "epoch": 0.13146037635833555, + "grad_norm": 4.85571813583374, + "learning_rate": 4.983071815922659e-06, + "loss": 0.4167, + "step": 62 + }, + { + "epoch": 0.13358070500927643, + "grad_norm": 4.446200370788574, + "learning_rate": 4.9824152431786565e-06, + "loss": 0.1973, + "step": 63 + }, + { + "epoch": 0.13570103366021732, + "grad_norm": 2.905205011367798, + "learning_rate": 4.981746223607713e-06, + "loss": 0.3211, + "step": 64 + }, + { + "epoch": 0.13782136231115824, + "grad_norm": 1.2360762357711792, + "learning_rate": 4.981064760564292e-06, + "loss": 0.2813, + "step": 65 + }, + { + "epoch": 0.13994169096209913, + "grad_norm": 2.0999205112457275, + "learning_rate": 4.9803708574652475e-06, + "loss": 0.2489, + "step": 66 + }, + { + "epoch": 0.14206201961304002, + "grad_norm": 4.240612030029297, + "learning_rate": 4.979664517789811e-06, + "loss": 0.3817, + "step": 67 + }, + { + "epoch": 0.1441823482639809, + "grad_norm": 2.3623316287994385, + "learning_rate": 4.978945745079565e-06, + "loss": 0.2673, + "step": 68 + }, + { + "epoch": 0.14630267691492183, + "grad_norm": 3.3251216411590576, + "learning_rate": 4.978214542938438e-06, + "loss": 0.2844, + "step": 69 + }, + { + "epoch": 0.14842300556586271, + "grad_norm": 1.5501821041107178, + "learning_rate": 4.977470915032676e-06, + "loss": 0.2262, + "step": 70 + }, + { + "epoch": 0.1505433342168036, + "grad_norm": 2.6850452423095703, + "learning_rate": 4.976714865090827e-06, + "loss": 0.265, + "step": 71 + }, + { + "epoch": 0.1526636628677445, + "grad_norm": 3.2187998294830322, + "learning_rate": 4.975946396903727e-06, + "loss": 0.3004, + "step": 72 + }, + { + "epoch": 0.1547839915186854, + "grad_norm": 2.397681951522827, + "learning_rate": 4.9751655143244715e-06, + "loss": 0.3076, + "step": 73 + }, + { + "epoch": 0.1569043201696263, + "grad_norm": 4.3145952224731445, + "learning_rate": 4.974372221268408e-06, + "loss": 0.237, + "step": 74 + }, + { + "epoch": 0.1590246488205672, + "grad_norm": 1.271013617515564, + "learning_rate": 4.973566521713104e-06, + "loss": 0.3886, + "step": 75 + }, + { + "epoch": 0.16114497747150808, + "grad_norm": 3.8556087017059326, + "learning_rate": 4.972748419698337e-06, + "loss": 0.4216, + "step": 76 + }, + { + "epoch": 0.16326530612244897, + "grad_norm": 2.6716325283050537, + "learning_rate": 4.971917919326071e-06, + "loss": 0.2869, + "step": 77 + }, + { + "epoch": 0.16538563477338988, + "grad_norm": 3.054572820663452, + "learning_rate": 4.971075024760432e-06, + "loss": 0.2688, + "step": 78 + }, + { + "epoch": 0.16750596342433077, + "grad_norm": 2.3528730869293213, + "learning_rate": 4.970219740227693e-06, + "loss": 0.3894, + "step": 79 + }, + { + "epoch": 0.16962629207527166, + "grad_norm": 2.507408857345581, + "learning_rate": 4.96935207001625e-06, + "loss": 0.3129, + "step": 80 + }, + { + "epoch": 0.17174662072621255, + "grad_norm": 3.135934829711914, + "learning_rate": 4.968472018476599e-06, + "loss": 0.322, + "step": 81 + }, + { + "epoch": 0.17386694937715347, + "grad_norm": 2.3163411617279053, + "learning_rate": 4.967579590021319e-06, + "loss": 0.3069, + "step": 82 + }, + { + "epoch": 0.17598727802809436, + "grad_norm": 4.409370422363281, + "learning_rate": 4.966674789125044e-06, + "loss": 0.3893, + "step": 83 + }, + { + "epoch": 0.17810760667903525, + "grad_norm": 3.5317368507385254, + "learning_rate": 4.965757620324445e-06, + "loss": 0.3198, + "step": 84 + }, + { + "epoch": 0.18022793532997614, + "grad_norm": 2.794269561767578, + "learning_rate": 4.9648280882182056e-06, + "loss": 0.3547, + "step": 85 + }, + { + "epoch": 0.18234826398091705, + "grad_norm": 1.2279053926467896, + "learning_rate": 4.963886197466998e-06, + "loss": 0.2338, + "step": 86 + }, + { + "epoch": 0.18446859263185794, + "grad_norm": 3.633697509765625, + "learning_rate": 4.962931952793461e-06, + "loss": 0.3118, + "step": 87 + }, + { + "epoch": 0.18658892128279883, + "grad_norm": 1.3397223949432373, + "learning_rate": 4.961965358982177e-06, + "loss": 0.2744, + "step": 88 + }, + { + "epoch": 0.18870924993373972, + "grad_norm": 2.2551627159118652, + "learning_rate": 4.960986420879645e-06, + "loss": 0.3339, + "step": 89 + }, + { + "epoch": 0.19082957858468064, + "grad_norm": 2.727034330368042, + "learning_rate": 4.9599951433942614e-06, + "loss": 0.2318, + "step": 90 + }, + { + "epoch": 0.19294990723562153, + "grad_norm": 2.2735791206359863, + "learning_rate": 4.958991531496289e-06, + "loss": 0.3198, + "step": 91 + }, + { + "epoch": 0.19507023588656242, + "grad_norm": 3.066884756088257, + "learning_rate": 4.957975590217836e-06, + "loss": 0.2254, + "step": 92 + }, + { + "epoch": 0.1971905645375033, + "grad_norm": 2.4200687408447266, + "learning_rate": 4.956947324652832e-06, + "loss": 0.277, + "step": 93 + }, + { + "epoch": 0.19931089318844422, + "grad_norm": 3.770292043685913, + "learning_rate": 4.955906739956999e-06, + "loss": 0.3462, + "step": 94 + }, + { + "epoch": 0.2014312218393851, + "grad_norm": 2.9880192279815674, + "learning_rate": 4.954853841347827e-06, + "loss": 0.2103, + "step": 95 + }, + { + "epoch": 0.203551550490326, + "grad_norm": 2.8914637565612793, + "learning_rate": 4.9537886341045475e-06, + "loss": 0.246, + "step": 96 + }, + { + "epoch": 0.2056718791412669, + "grad_norm": 4.304288864135742, + "learning_rate": 4.95271112356811e-06, + "loss": 0.3306, + "step": 97 + }, + { + "epoch": 0.2077922077922078, + "grad_norm": 6.69378662109375, + "learning_rate": 4.951621315141149e-06, + "loss": 0.37, + "step": 98 + }, + { + "epoch": 0.2099125364431487, + "grad_norm": 4.184510231018066, + "learning_rate": 4.950519214287966e-06, + "loss": 0.3687, + "step": 99 + }, + { + "epoch": 0.21203286509408958, + "grad_norm": 3.177889585494995, + "learning_rate": 4.9494048265344896e-06, + "loss": 0.4234, + "step": 100 + }, + { + "epoch": 0.21415319374503047, + "grad_norm": 1.1268483400344849, + "learning_rate": 4.94827815746826e-06, + "loss": 0.3633, + "step": 101 + }, + { + "epoch": 0.21627352239597136, + "grad_norm": 3.196904420852661, + "learning_rate": 4.947139212738395e-06, + "loss": 0.3335, + "step": 102 + }, + { + "epoch": 0.21839385104691228, + "grad_norm": 3.6721370220184326, + "learning_rate": 4.945987998055562e-06, + "loss": 0.186, + "step": 103 + }, + { + "epoch": 0.22051417969785317, + "grad_norm": 2.374629497528076, + "learning_rate": 4.944824519191949e-06, + "loss": 0.2399, + "step": 104 + }, + { + "epoch": 0.22263450834879406, + "grad_norm": 3.0888235569000244, + "learning_rate": 4.943648781981239e-06, + "loss": 0.2794, + "step": 105 + }, + { + "epoch": 0.22475483699973495, + "grad_norm": 2.1860692501068115, + "learning_rate": 4.942460792318575e-06, + "loss": 0.2431, + "step": 106 + }, + { + "epoch": 0.22687516565067586, + "grad_norm": 2.057961940765381, + "learning_rate": 4.9412605561605365e-06, + "loss": 0.258, + "step": 107 + }, + { + "epoch": 0.22899549430161675, + "grad_norm": 2.826047420501709, + "learning_rate": 4.940048079525108e-06, + "loss": 0.3056, + "step": 108 + }, + { + "epoch": 0.23111582295255764, + "grad_norm": 1.93588125705719, + "learning_rate": 4.9388233684916434e-06, + "loss": 0.3374, + "step": 109 + }, + { + "epoch": 0.23323615160349853, + "grad_norm": 1.4116945266723633, + "learning_rate": 4.937586429200842e-06, + "loss": 0.1877, + "step": 110 + }, + { + "epoch": 0.23535648025443945, + "grad_norm": 3.5607080459594727, + "learning_rate": 4.936337267854719e-06, + "loss": 0.319, + "step": 111 + }, + { + "epoch": 0.23747680890538034, + "grad_norm": 1.9677248001098633, + "learning_rate": 4.935075890716565e-06, + "loss": 0.2615, + "step": 112 + }, + { + "epoch": 0.23959713755632123, + "grad_norm": 1.2864681482315063, + "learning_rate": 4.933802304110925e-06, + "loss": 0.2038, + "step": 113 + }, + { + "epoch": 0.24171746620726212, + "grad_norm": 3.6011598110198975, + "learning_rate": 4.932516514423559e-06, + "loss": 0.2945, + "step": 114 + }, + { + "epoch": 0.24383779485820303, + "grad_norm": 0.8037973642349243, + "learning_rate": 4.931218528101416e-06, + "loss": 0.2102, + "step": 115 + }, + { + "epoch": 0.24595812350914392, + "grad_norm": 5.048084259033203, + "learning_rate": 4.929908351652598e-06, + "loss": 0.3449, + "step": 116 + }, + { + "epoch": 0.2480784521600848, + "grad_norm": 3.8754634857177734, + "learning_rate": 4.928585991646327e-06, + "loss": 0.3072, + "step": 117 + }, + { + "epoch": 0.2501987808110257, + "grad_norm": 3.335463523864746, + "learning_rate": 4.927251454712915e-06, + "loss": 0.3457, + "step": 118 + }, + { + "epoch": 0.2523191094619666, + "grad_norm": 2.5155117511749268, + "learning_rate": 4.925904747543729e-06, + "loss": 0.3305, + "step": 119 + }, + { + "epoch": 0.2544394381129075, + "grad_norm": 3.2518768310546875, + "learning_rate": 4.924545876891157e-06, + "loss": 0.4029, + "step": 120 + }, + { + "epoch": 0.2565597667638484, + "grad_norm": 3.0308430194854736, + "learning_rate": 4.9231748495685745e-06, + "loss": 0.3313, + "step": 121 + }, + { + "epoch": 0.2586800954147893, + "grad_norm": 4.494399070739746, + "learning_rate": 4.921791672450311e-06, + "loss": 0.263, + "step": 122 + }, + { + "epoch": 0.2608004240657302, + "grad_norm": 3.257610321044922, + "learning_rate": 4.920396352471613e-06, + "loss": 0.4046, + "step": 123 + }, + { + "epoch": 0.2629207527166711, + "grad_norm": 2.162080764770508, + "learning_rate": 4.918988896628617e-06, + "loss": 0.2562, + "step": 124 + }, + { + "epoch": 0.26504108136761195, + "grad_norm": 1.7331904172897339, + "learning_rate": 4.917569311978301e-06, + "loss": 0.2157, + "step": 125 + }, + { + "epoch": 0.26716141001855287, + "grad_norm": 2.089783191680908, + "learning_rate": 4.916137605638463e-06, + "loss": 0.2177, + "step": 126 + }, + { + "epoch": 0.2692817386694938, + "grad_norm": 2.637751817703247, + "learning_rate": 4.914693784787676e-06, + "loss": 0.2717, + "step": 127 + }, + { + "epoch": 0.27140206732043465, + "grad_norm": 1.1012979745864868, + "learning_rate": 4.913237856665256e-06, + "loss": 0.2845, + "step": 128 + }, + { + "epoch": 0.27352239597137556, + "grad_norm": 2.7496721744537354, + "learning_rate": 4.911769828571224e-06, + "loss": 0.2839, + "step": 129 + }, + { + "epoch": 0.2756427246223165, + "grad_norm": 3.16662335395813, + "learning_rate": 4.910289707866273e-06, + "loss": 0.3791, + "step": 130 + }, + { + "epoch": 0.27776305327325734, + "grad_norm": 3.3091320991516113, + "learning_rate": 4.908797501971725e-06, + "loss": 0.3046, + "step": 131 + }, + { + "epoch": 0.27988338192419826, + "grad_norm": 2.08532452583313, + "learning_rate": 4.907293218369499e-06, + "loss": 0.2242, + "step": 132 + }, + { + "epoch": 0.2820037105751391, + "grad_norm": 1.4009634256362915, + "learning_rate": 4.90577686460207e-06, + "loss": 0.2657, + "step": 133 + }, + { + "epoch": 0.28412403922608004, + "grad_norm": 2.2569682598114014, + "learning_rate": 4.904248448272435e-06, + "loss": 0.2321, + "step": 134 + }, + { + "epoch": 0.28624436787702096, + "grad_norm": 2.43658709526062, + "learning_rate": 4.902707977044071e-06, + "loss": 0.2339, + "step": 135 + }, + { + "epoch": 0.2883646965279618, + "grad_norm": 1.7777557373046875, + "learning_rate": 4.9011554586409005e-06, + "loss": 0.2703, + "step": 136 + }, + { + "epoch": 0.29048502517890273, + "grad_norm": 4.1074347496032715, + "learning_rate": 4.8995909008472465e-06, + "loss": 0.3249, + "step": 137 + }, + { + "epoch": 0.29260535382984365, + "grad_norm": 2.1729867458343506, + "learning_rate": 4.898014311507801e-06, + "loss": 0.229, + "step": 138 + }, + { + "epoch": 0.2947256824807845, + "grad_norm": 3.032817840576172, + "learning_rate": 4.8964256985275805e-06, + "loss": 0.2925, + "step": 139 + }, + { + "epoch": 0.29684601113172543, + "grad_norm": 1.834567904472351, + "learning_rate": 4.8948250698718895e-06, + "loss": 0.2349, + "step": 140 + }, + { + "epoch": 0.2989663397826663, + "grad_norm": 3.393310785293579, + "learning_rate": 4.893212433566277e-06, + "loss": 0.3615, + "step": 141 + }, + { + "epoch": 0.3010866684336072, + "grad_norm": 4.021195888519287, + "learning_rate": 4.8915877976964995e-06, + "loss": 0.4128, + "step": 142 + }, + { + "epoch": 0.3032069970845481, + "grad_norm": 1.6174540519714355, + "learning_rate": 4.889951170408479e-06, + "loss": 0.2398, + "step": 143 + }, + { + "epoch": 0.305327325735489, + "grad_norm": 2.0691730976104736, + "learning_rate": 4.888302559908265e-06, + "loss": 0.3333, + "step": 144 + }, + { + "epoch": 0.3074476543864299, + "grad_norm": 0.9198992848396301, + "learning_rate": 4.886641974461985e-06, + "loss": 0.2091, + "step": 145 + }, + { + "epoch": 0.3095679830373708, + "grad_norm": 2.2674360275268555, + "learning_rate": 4.884969422395815e-06, + "loss": 0.2042, + "step": 146 + }, + { + "epoch": 0.3116883116883117, + "grad_norm": 2.365835428237915, + "learning_rate": 4.883284912095928e-06, + "loss": 0.3742, + "step": 147 + }, + { + "epoch": 0.3138086403392526, + "grad_norm": 3.322329521179199, + "learning_rate": 4.881588452008457e-06, + "loss": 0.3228, + "step": 148 + }, + { + "epoch": 0.31592896899019346, + "grad_norm": 6.298361301422119, + "learning_rate": 4.87988005063945e-06, + "loss": 0.452, + "step": 149 + }, + { + "epoch": 0.3180492976411344, + "grad_norm": 3.925762414932251, + "learning_rate": 4.87815971655483e-06, + "loss": 0.3467, + "step": 150 + }, + { + "epoch": 0.3201696262920753, + "grad_norm": 4.023056507110596, + "learning_rate": 4.876427458380349e-06, + "loss": 0.3558, + "step": 151 + }, + { + "epoch": 0.32228995494301615, + "grad_norm": 3.4093480110168457, + "learning_rate": 4.874683284801548e-06, + "loss": 0.2739, + "step": 152 + }, + { + "epoch": 0.32441028359395707, + "grad_norm": 0.9935247302055359, + "learning_rate": 4.872927204563712e-06, + "loss": 0.2131, + "step": 153 + }, + { + "epoch": 0.32653061224489793, + "grad_norm": 1.8300209045410156, + "learning_rate": 4.871159226471825e-06, + "loss": 0.329, + "step": 154 + }, + { + "epoch": 0.32865094089583885, + "grad_norm": 2.8266682624816895, + "learning_rate": 4.869379359390524e-06, + "loss": 0.2388, + "step": 155 + }, + { + "epoch": 0.33077126954677977, + "grad_norm": 3.9147934913635254, + "learning_rate": 4.867587612244064e-06, + "loss": 0.3476, + "step": 156 + }, + { + "epoch": 0.33289159819772063, + "grad_norm": 2.4226462841033936, + "learning_rate": 4.865783994016261e-06, + "loss": 0.3471, + "step": 157 + }, + { + "epoch": 0.33501192684866155, + "grad_norm": 2.4413650035858154, + "learning_rate": 4.863968513750456e-06, + "loss": 0.3026, + "step": 158 + }, + { + "epoch": 0.33713225549960246, + "grad_norm": 2.6878299713134766, + "learning_rate": 4.862141180549464e-06, + "loss": 0.3127, + "step": 159 + }, + { + "epoch": 0.3392525841505433, + "grad_norm": 2.855107545852661, + "learning_rate": 4.86030200357553e-06, + "loss": 0.2059, + "step": 160 + }, + { + "epoch": 0.34137291280148424, + "grad_norm": 2.976635217666626, + "learning_rate": 4.858450992050287e-06, + "loss": 0.2706, + "step": 161 + }, + { + "epoch": 0.3434932414524251, + "grad_norm": 4.121407508850098, + "learning_rate": 4.856588155254704e-06, + "loss": 0.2539, + "step": 162 + }, + { + "epoch": 0.345613570103366, + "grad_norm": 0.857638955116272, + "learning_rate": 4.854713502529042e-06, + "loss": 0.2923, + "step": 163 + }, + { + "epoch": 0.34773389875430694, + "grad_norm": 1.6652028560638428, + "learning_rate": 4.852827043272808e-06, + "loss": 0.2357, + "step": 164 + }, + { + "epoch": 0.3498542274052478, + "grad_norm": 3.286330223083496, + "learning_rate": 4.850928786944706e-06, + "loss": 0.2745, + "step": 165 + }, + { + "epoch": 0.3519745560561887, + "grad_norm": 3.9806864261627197, + "learning_rate": 4.84901874306259e-06, + "loss": 0.2503, + "step": 166 + }, + { + "epoch": 0.35409488470712963, + "grad_norm": 2.8622264862060547, + "learning_rate": 4.847096921203419e-06, + "loss": 0.3615, + "step": 167 + }, + { + "epoch": 0.3562152133580705, + "grad_norm": 3.0431885719299316, + "learning_rate": 4.845163331003205e-06, + "loss": 0.187, + "step": 168 + }, + { + "epoch": 0.3583355420090114, + "grad_norm": 1.8177791833877563, + "learning_rate": 4.843217982156968e-06, + "loss": 0.2641, + "step": 169 + }, + { + "epoch": 0.36045587065995227, + "grad_norm": 0.6192033290863037, + "learning_rate": 4.841260884418682e-06, + "loss": 0.2323, + "step": 170 + }, + { + "epoch": 0.3625761993108932, + "grad_norm": 4.052712917327881, + "learning_rate": 4.839292047601234e-06, + "loss": 0.3339, + "step": 171 + }, + { + "epoch": 0.3646965279618341, + "grad_norm": 1.8390997648239136, + "learning_rate": 4.83731148157637e-06, + "loss": 0.2844, + "step": 172 + }, + { + "epoch": 0.36681685661277497, + "grad_norm": 1.4040610790252686, + "learning_rate": 4.835319196274646e-06, + "loss": 0.3137, + "step": 173 + }, + { + "epoch": 0.3689371852637159, + "grad_norm": 3.0023269653320312, + "learning_rate": 4.833315201685375e-06, + "loss": 0.2336, + "step": 174 + }, + { + "epoch": 0.37105751391465674, + "grad_norm": 1.7594302892684937, + "learning_rate": 4.831299507856587e-06, + "loss": 0.2312, + "step": 175 + }, + { + "epoch": 0.37317784256559766, + "grad_norm": 1.7524633407592773, + "learning_rate": 4.829272124894967e-06, + "loss": 0.3141, + "step": 176 + }, + { + "epoch": 0.3752981712165386, + "grad_norm": 9.093369483947754, + "learning_rate": 4.827233062965811e-06, + "loss": 0.259, + "step": 177 + }, + { + "epoch": 0.37741849986747944, + "grad_norm": 2.2024335861206055, + "learning_rate": 4.82518233229297e-06, + "loss": 0.23, + "step": 178 + }, + { + "epoch": 0.37953882851842036, + "grad_norm": 0.7254531979560852, + "learning_rate": 4.823119943158809e-06, + "loss": 0.2643, + "step": 179 + }, + { + "epoch": 0.3816591571693613, + "grad_norm": 2.181795120239258, + "learning_rate": 4.821045905904143e-06, + "loss": 0.2215, + "step": 180 + }, + { + "epoch": 0.38377948582030214, + "grad_norm": 1.5816072225570679, + "learning_rate": 4.818960230928192e-06, + "loss": 0.2168, + "step": 181 + }, + { + "epoch": 0.38589981447124305, + "grad_norm": 2.4816792011260986, + "learning_rate": 4.816862928688528e-06, + "loss": 0.2618, + "step": 182 + }, + { + "epoch": 0.3880201431221839, + "grad_norm": 2.069082260131836, + "learning_rate": 4.814754009701023e-06, + "loss": 0.3713, + "step": 183 + }, + { + "epoch": 0.39014047177312483, + "grad_norm": 2.61807918548584, + "learning_rate": 4.8126334845397914e-06, + "loss": 0.3274, + "step": 184 + }, + { + "epoch": 0.39226080042406575, + "grad_norm": 2.7736072540283203, + "learning_rate": 4.8105013638371454e-06, + "loss": 0.231, + "step": 185 + }, + { + "epoch": 0.3943811290750066, + "grad_norm": 3.6297597885131836, + "learning_rate": 4.8083576582835366e-06, + "loss": 0.3412, + "step": 186 + }, + { + "epoch": 0.3965014577259475, + "grad_norm": 2.2494869232177734, + "learning_rate": 4.8062023786274996e-06, + "loss": 0.247, + "step": 187 + }, + { + "epoch": 0.39862178637688844, + "grad_norm": 1.3295131921768188, + "learning_rate": 4.804035535675606e-06, + "loss": 0.2412, + "step": 188 + }, + { + "epoch": 0.4007421150278293, + "grad_norm": 2.058772325515747, + "learning_rate": 4.801857140292402e-06, + "loss": 0.2943, + "step": 189 + }, + { + "epoch": 0.4028624436787702, + "grad_norm": 1.5720592737197876, + "learning_rate": 4.799667203400361e-06, + "loss": 0.274, + "step": 190 + }, + { + "epoch": 0.4049827723297111, + "grad_norm": 2.5041348934173584, + "learning_rate": 4.7974657359798224e-06, + "loss": 0.245, + "step": 191 + }, + { + "epoch": 0.407103100980652, + "grad_norm": 1.9566255807876587, + "learning_rate": 4.795252749068942e-06, + "loss": 0.3203, + "step": 192 + }, + { + "epoch": 0.4092234296315929, + "grad_norm": 4.478713035583496, + "learning_rate": 4.793028253763633e-06, + "loss": 0.3274, + "step": 193 + }, + { + "epoch": 0.4113437582825338, + "grad_norm": 3.3313329219818115, + "learning_rate": 4.790792261217513e-06, + "loss": 0.3502, + "step": 194 + }, + { + "epoch": 0.4134640869334747, + "grad_norm": 2.875757932662964, + "learning_rate": 4.7885447826418435e-06, + "loss": 0.4093, + "step": 195 + }, + { + "epoch": 0.4155844155844156, + "grad_norm": 2.094299793243408, + "learning_rate": 4.786285829305481e-06, + "loss": 0.3394, + "step": 196 + }, + { + "epoch": 0.4177047442353565, + "grad_norm": 3.40802264213562, + "learning_rate": 4.784015412534816e-06, + "loss": 0.2579, + "step": 197 + }, + { + "epoch": 0.4198250728862974, + "grad_norm": 2.5901896953582764, + "learning_rate": 4.781733543713714e-06, + "loss": 0.3256, + "step": 198 + }, + { + "epoch": 0.42194540153723825, + "grad_norm": 2.649927854537964, + "learning_rate": 4.779440234283461e-06, + "loss": 0.2552, + "step": 199 + }, + { + "epoch": 0.42406573018817917, + "grad_norm": 2.827615261077881, + "learning_rate": 4.77713549574271e-06, + "loss": 0.345, + "step": 200 + }, + { + "epoch": 0.4261860588391201, + "grad_norm": 2.3520429134368896, + "learning_rate": 4.774819339647415e-06, + "loss": 0.3555, + "step": 201 + }, + { + "epoch": 0.42830638749006095, + "grad_norm": 2.04105281829834, + "learning_rate": 4.772491777610782e-06, + "loss": 0.3845, + "step": 202 + }, + { + "epoch": 0.43042671614100186, + "grad_norm": 2.4335427284240723, + "learning_rate": 4.770152821303203e-06, + "loss": 0.226, + "step": 203 + }, + { + "epoch": 0.4325470447919427, + "grad_norm": 3.064467191696167, + "learning_rate": 4.767802482452202e-06, + "loss": 0.2998, + "step": 204 + }, + { + "epoch": 0.43466737344288364, + "grad_norm": 1.1668577194213867, + "learning_rate": 4.7654407728423745e-06, + "loss": 0.2627, + "step": 205 + }, + { + "epoch": 0.43678770209382456, + "grad_norm": 1.9054539203643799, + "learning_rate": 4.763067704315331e-06, + "loss": 0.3959, + "step": 206 + }, + { + "epoch": 0.4389080307447654, + "grad_norm": 2.3456785678863525, + "learning_rate": 4.760683288769634e-06, + "loss": 0.3076, + "step": 207 + }, + { + "epoch": 0.44102835939570634, + "grad_norm": 3.0187900066375732, + "learning_rate": 4.758287538160738e-06, + "loss": 0.2894, + "step": 208 + }, + { + "epoch": 0.44314868804664725, + "grad_norm": 2.9057319164276123, + "learning_rate": 4.755880464500936e-06, + "loss": 0.289, + "step": 209 + }, + { + "epoch": 0.4452690166975881, + "grad_norm": 2.7487642765045166, + "learning_rate": 4.753462079859291e-06, + "loss": 0.2759, + "step": 210 + }, + { + "epoch": 0.44738934534852903, + "grad_norm": 1.8765803575515747, + "learning_rate": 4.7510323963615815e-06, + "loss": 0.2892, + "step": 211 + }, + { + "epoch": 0.4495096739994699, + "grad_norm": 1.8452672958374023, + "learning_rate": 4.748591426190237e-06, + "loss": 0.2232, + "step": 212 + }, + { + "epoch": 0.4516300026504108, + "grad_norm": 3.8514230251312256, + "learning_rate": 4.746139181584278e-06, + "loss": 0.2904, + "step": 213 + }, + { + "epoch": 0.45375033130135173, + "grad_norm": 1.5355229377746582, + "learning_rate": 4.743675674839258e-06, + "loss": 0.3108, + "step": 214 + }, + { + "epoch": 0.4558706599522926, + "grad_norm": 2.429868698120117, + "learning_rate": 4.741200918307194e-06, + "loss": 0.3254, + "step": 215 + }, + { + "epoch": 0.4579909886032335, + "grad_norm": 1.8861596584320068, + "learning_rate": 4.738714924396514e-06, + "loss": 0.3318, + "step": 216 + }, + { + "epoch": 0.4601113172541744, + "grad_norm": 2.709230661392212, + "learning_rate": 4.736217705571989e-06, + "loss": 0.2817, + "step": 217 + }, + { + "epoch": 0.4622316459051153, + "grad_norm": 1.2253323793411255, + "learning_rate": 4.73370927435467e-06, + "loss": 0.3168, + "step": 218 + }, + { + "epoch": 0.4643519745560562, + "grad_norm": 2.5226621627807617, + "learning_rate": 4.731189643321829e-06, + "loss": 0.263, + "step": 219 + }, + { + "epoch": 0.46647230320699706, + "grad_norm": 3.8697330951690674, + "learning_rate": 4.728658825106891e-06, + "loss": 0.237, + "step": 220 + }, + { + "epoch": 0.468592631857938, + "grad_norm": 1.7124079465866089, + "learning_rate": 4.726116832399376e-06, + "loss": 0.1574, + "step": 221 + }, + { + "epoch": 0.4707129605088789, + "grad_norm": 1.372372031211853, + "learning_rate": 4.723563677944833e-06, + "loss": 0.287, + "step": 222 + }, + { + "epoch": 0.47283328915981976, + "grad_norm": 1.5783618688583374, + "learning_rate": 4.720999374544776e-06, + "loss": 0.2368, + "step": 223 + }, + { + "epoch": 0.4749536178107607, + "grad_norm": 2.918891191482544, + "learning_rate": 4.718423935056617e-06, + "loss": 0.3074, + "step": 224 + }, + { + "epoch": 0.47707394646170154, + "grad_norm": 2.4617486000061035, + "learning_rate": 4.715837372393607e-06, + "loss": 0.2073, + "step": 225 + }, + { + "epoch": 0.47919427511264245, + "grad_norm": 2.3654730319976807, + "learning_rate": 4.71323969952477e-06, + "loss": 0.2204, + "step": 226 + }, + { + "epoch": 0.48131460376358337, + "grad_norm": 2.3249452114105225, + "learning_rate": 4.7106309294748315e-06, + "loss": 0.378, + "step": 227 + }, + { + "epoch": 0.48343493241452423, + "grad_norm": 5.216866493225098, + "learning_rate": 4.708011075324163e-06, + "loss": 0.2746, + "step": 228 + }, + { + "epoch": 0.48555526106546515, + "grad_norm": 2.4934608936309814, + "learning_rate": 4.70538015020871e-06, + "loss": 0.3171, + "step": 229 + }, + { + "epoch": 0.48767558971640607, + "grad_norm": 3.2651522159576416, + "learning_rate": 4.702738167319927e-06, + "loss": 0.3478, + "step": 230 + }, + { + "epoch": 0.4897959183673469, + "grad_norm": 2.3438186645507812, + "learning_rate": 4.700085139904714e-06, + "loss": 0.1753, + "step": 231 + }, + { + "epoch": 0.49191624701828784, + "grad_norm": 3.3518893718719482, + "learning_rate": 4.697421081265346e-06, + "loss": 0.2202, + "step": 232 + }, + { + "epoch": 0.4940365756692287, + "grad_norm": 5.121367931365967, + "learning_rate": 4.6947460047594105e-06, + "loss": 0.2557, + "step": 233 + }, + { + "epoch": 0.4961569043201696, + "grad_norm": 2.5385594367980957, + "learning_rate": 4.692059923799736e-06, + "loss": 0.3656, + "step": 234 + }, + { + "epoch": 0.49827723297111054, + "grad_norm": 2.5510666370391846, + "learning_rate": 4.689362851854333e-06, + "loss": 0.3637, + "step": 235 + }, + { + "epoch": 0.5003975616220514, + "grad_norm": 2.288750171661377, + "learning_rate": 4.686654802446313e-06, + "loss": 0.2433, + "step": 236 + }, + { + "epoch": 0.5025178902729923, + "grad_norm": 2.547922372817993, + "learning_rate": 4.683935789153834e-06, + "loss": 0.3574, + "step": 237 + }, + { + "epoch": 0.5046382189239332, + "grad_norm": 1.7912276983261108, + "learning_rate": 4.681205825610025e-06, + "loss": 0.3007, + "step": 238 + }, + { + "epoch": 0.5067585475748742, + "grad_norm": 1.9286338090896606, + "learning_rate": 4.67846492550292e-06, + "loss": 0.2679, + "step": 239 + }, + { + "epoch": 0.508878876225815, + "grad_norm": 2.0864994525909424, + "learning_rate": 4.675713102575389e-06, + "loss": 0.423, + "step": 240 + }, + { + "epoch": 0.5109992048767559, + "grad_norm": 1.037505030632019, + "learning_rate": 4.672950370625067e-06, + "loss": 0.2192, + "step": 241 + }, + { + "epoch": 0.5131195335276968, + "grad_norm": 1.936712384223938, + "learning_rate": 4.670176743504291e-06, + "loss": 0.3557, + "step": 242 + }, + { + "epoch": 0.5152398621786377, + "grad_norm": 2.4721193313598633, + "learning_rate": 4.667392235120023e-06, + "loss": 0.2169, + "step": 243 + }, + { + "epoch": 0.5173601908295786, + "grad_norm": 2.0251030921936035, + "learning_rate": 4.664596859433784e-06, + "loss": 0.2279, + "step": 244 + }, + { + "epoch": 0.5194805194805194, + "grad_norm": 2.416062593460083, + "learning_rate": 4.661790630461585e-06, + "loss": 0.235, + "step": 245 + }, + { + "epoch": 0.5216008481314603, + "grad_norm": 2.3397867679595947, + "learning_rate": 4.658973562273853e-06, + "loss": 0.2745, + "step": 246 + }, + { + "epoch": 0.5237211767824013, + "grad_norm": 3.574948787689209, + "learning_rate": 4.6561456689953665e-06, + "loss": 0.2579, + "step": 247 + }, + { + "epoch": 0.5258415054333422, + "grad_norm": 2.3914096355438232, + "learning_rate": 4.653306964805178e-06, + "loss": 0.3445, + "step": 248 + }, + { + "epoch": 0.5279618340842831, + "grad_norm": 1.807157278060913, + "learning_rate": 4.650457463936547e-06, + "loss": 0.2752, + "step": 249 + }, + { + "epoch": 0.5300821627352239, + "grad_norm": 1.997169017791748, + "learning_rate": 4.647597180676866e-06, + "loss": 0.2539, + "step": 250 + }, + { + "epoch": 0.5322024913861648, + "grad_norm": 2.018228530883789, + "learning_rate": 4.644726129367594e-06, + "loss": 0.2548, + "step": 251 + }, + { + "epoch": 0.5343228200371057, + "grad_norm": 1.5280331373214722, + "learning_rate": 4.6418443244041775e-06, + "loss": 0.2473, + "step": 252 + }, + { + "epoch": 0.5364431486880467, + "grad_norm": 2.8328475952148438, + "learning_rate": 4.638951780235982e-06, + "loss": 0.2633, + "step": 253 + }, + { + "epoch": 0.5385634773389876, + "grad_norm": 1.2343734502792358, + "learning_rate": 4.636048511366222e-06, + "loss": 0.2015, + "step": 254 + }, + { + "epoch": 0.5406838059899285, + "grad_norm": 2.285114049911499, + "learning_rate": 4.633134532351883e-06, + "loss": 0.242, + "step": 255 + }, + { + "epoch": 0.5428041346408693, + "grad_norm": 1.9822317361831665, + "learning_rate": 4.630209857803653e-06, + "loss": 0.1624, + "step": 256 + }, + { + "epoch": 0.5449244632918102, + "grad_norm": 1.7463964223861694, + "learning_rate": 4.6272745023858445e-06, + "loss": 0.266, + "step": 257 + }, + { + "epoch": 0.5470447919427511, + "grad_norm": 1.835262656211853, + "learning_rate": 4.624328480816329e-06, + "loss": 0.2686, + "step": 258 + }, + { + "epoch": 0.549165120593692, + "grad_norm": 3.0902907848358154, + "learning_rate": 4.621371807866452e-06, + "loss": 0.2292, + "step": 259 + }, + { + "epoch": 0.551285449244633, + "grad_norm": 1.0292060375213623, + "learning_rate": 4.618404498360971e-06, + "loss": 0.1938, + "step": 260 + }, + { + "epoch": 0.5534057778955738, + "grad_norm": 1.2217211723327637, + "learning_rate": 4.6154265671779695e-06, + "loss": 0.2923, + "step": 261 + }, + { + "epoch": 0.5555261065465147, + "grad_norm": 0.7709723711013794, + "learning_rate": 4.612438029248792e-06, + "loss": 0.2513, + "step": 262 + }, + { + "epoch": 0.5576464351974556, + "grad_norm": 1.7595287561416626, + "learning_rate": 4.609438899557964e-06, + "loss": 0.1831, + "step": 263 + }, + { + "epoch": 0.5597667638483965, + "grad_norm": 1.169548749923706, + "learning_rate": 4.606429193143118e-06, + "loss": 0.3138, + "step": 264 + }, + { + "epoch": 0.5618870924993374, + "grad_norm": 3.089507579803467, + "learning_rate": 4.6034089250949184e-06, + "loss": 0.2822, + "step": 265 + }, + { + "epoch": 0.5640074211502782, + "grad_norm": 4.917386531829834, + "learning_rate": 4.600378110556985e-06, + "loss": 0.3735, + "step": 266 + }, + { + "epoch": 0.5661277498012192, + "grad_norm": 1.7424579858779907, + "learning_rate": 4.597336764725817e-06, + "loss": 0.2993, + "step": 267 + }, + { + "epoch": 0.5682480784521601, + "grad_norm": 3.4557604789733887, + "learning_rate": 4.594284902850721e-06, + "loss": 0.2737, + "step": 268 + }, + { + "epoch": 0.570368407103101, + "grad_norm": 1.8935794830322266, + "learning_rate": 4.591222540233726e-06, + "loss": 0.2369, + "step": 269 + }, + { + "epoch": 0.5724887357540419, + "grad_norm": 3.673444986343384, + "learning_rate": 4.5881496922295176e-06, + "loss": 0.2901, + "step": 270 + }, + { + "epoch": 0.5746090644049828, + "grad_norm": 2.3238632678985596, + "learning_rate": 4.585066374245349e-06, + "loss": 0.2711, + "step": 271 + }, + { + "epoch": 0.5767293930559236, + "grad_norm": 3.2917137145996094, + "learning_rate": 4.581972601740974e-06, + "loss": 0.202, + "step": 272 + }, + { + "epoch": 0.5788497217068646, + "grad_norm": 2.7594401836395264, + "learning_rate": 4.5788683902285644e-06, + "loss": 0.2347, + "step": 273 + }, + { + "epoch": 0.5809700503578055, + "grad_norm": 2.7743582725524902, + "learning_rate": 4.5757537552726315e-06, + "loss": 0.2795, + "step": 274 + }, + { + "epoch": 0.5830903790087464, + "grad_norm": 2.2841763496398926, + "learning_rate": 4.572628712489953e-06, + "loss": 0.3109, + "step": 275 + }, + { + "epoch": 0.5852107076596873, + "grad_norm": 2.3819563388824463, + "learning_rate": 4.569493277549487e-06, + "loss": 0.2391, + "step": 276 + }, + { + "epoch": 0.5873310363106281, + "grad_norm": 1.7411075830459595, + "learning_rate": 4.566347466172303e-06, + "loss": 0.1732, + "step": 277 + }, + { + "epoch": 0.589451364961569, + "grad_norm": 0.9455245733261108, + "learning_rate": 4.563191294131494e-06, + "loss": 0.2278, + "step": 278 + }, + { + "epoch": 0.5915716936125099, + "grad_norm": 1.5805822610855103, + "learning_rate": 4.560024777252103e-06, + "loss": 0.2911, + "step": 279 + }, + { + "epoch": 0.5936920222634509, + "grad_norm": 2.25376033782959, + "learning_rate": 4.556847931411042e-06, + "loss": 0.327, + "step": 280 + }, + { + "epoch": 0.5958123509143918, + "grad_norm": 3.1903650760650635, + "learning_rate": 4.553660772537011e-06, + "loss": 0.2883, + "step": 281 + }, + { + "epoch": 0.5979326795653326, + "grad_norm": 0.6892781853675842, + "learning_rate": 4.550463316610422e-06, + "loss": 0.2981, + "step": 282 + }, + { + "epoch": 0.6000530082162735, + "grad_norm": 3.3684580326080322, + "learning_rate": 4.547255579663314e-06, + "loss": 0.3031, + "step": 283 + }, + { + "epoch": 0.6021733368672144, + "grad_norm": 1.6963587999343872, + "learning_rate": 4.544037577779276e-06, + "loss": 0.3123, + "step": 284 + }, + { + "epoch": 0.6042936655181553, + "grad_norm": 2.595681667327881, + "learning_rate": 4.540809327093366e-06, + "loss": 0.2838, + "step": 285 + }, + { + "epoch": 0.6064139941690962, + "grad_norm": 3.383328437805176, + "learning_rate": 4.537570843792028e-06, + "loss": 0.3393, + "step": 286 + }, + { + "epoch": 0.608534322820037, + "grad_norm": 2.2130298614501953, + "learning_rate": 4.534322144113016e-06, + "loss": 0.2278, + "step": 287 + }, + { + "epoch": 0.610654651470978, + "grad_norm": 1.0078691244125366, + "learning_rate": 4.531063244345303e-06, + "loss": 0.2498, + "step": 288 + }, + { + "epoch": 0.6127749801219189, + "grad_norm": 0.9451133608818054, + "learning_rate": 4.52779416082901e-06, + "loss": 0.2269, + "step": 289 + }, + { + "epoch": 0.6148953087728598, + "grad_norm": 1.5240414142608643, + "learning_rate": 4.524514909955316e-06, + "loss": 0.3268, + "step": 290 + }, + { + "epoch": 0.6170156374238007, + "grad_norm": 1.5782700777053833, + "learning_rate": 4.521225508166383e-06, + "loss": 0.3014, + "step": 291 + }, + { + "epoch": 0.6191359660747416, + "grad_norm": 1.9916071891784668, + "learning_rate": 4.517925971955267e-06, + "loss": 0.2863, + "step": 292 + }, + { + "epoch": 0.6212562947256824, + "grad_norm": 1.9299273490905762, + "learning_rate": 4.514616317865838e-06, + "loss": 0.3096, + "step": 293 + }, + { + "epoch": 0.6233766233766234, + "grad_norm": 1.721146583557129, + "learning_rate": 4.5112965624926965e-06, + "loss": 0.284, + "step": 294 + }, + { + "epoch": 0.6254969520275643, + "grad_norm": 2.213865280151367, + "learning_rate": 4.507966722481093e-06, + "loss": 0.3541, + "step": 295 + }, + { + "epoch": 0.6276172806785052, + "grad_norm": 5.646588325500488, + "learning_rate": 4.504626814526841e-06, + "loss": 0.287, + "step": 296 + }, + { + "epoch": 0.6297376093294461, + "grad_norm": 1.9379154443740845, + "learning_rate": 4.501276855376235e-06, + "loss": 0.266, + "step": 297 + }, + { + "epoch": 0.6318579379803869, + "grad_norm": 4.37392520904541, + "learning_rate": 4.497916861825966e-06, + "loss": 0.3637, + "step": 298 + }, + { + "epoch": 0.6339782666313278, + "grad_norm": 1.6309797763824463, + "learning_rate": 4.494546850723037e-06, + "loss": 0.2331, + "step": 299 + }, + { + "epoch": 0.6360985952822688, + "grad_norm": 1.2552251815795898, + "learning_rate": 4.4911668389646795e-06, + "loss": 0.2661, + "step": 300 + }, + { + "epoch": 0.6382189239332097, + "grad_norm": 2.0839784145355225, + "learning_rate": 4.487776843498268e-06, + "loss": 0.2305, + "step": 301 + }, + { + "epoch": 0.6403392525841506, + "grad_norm": 2.6097898483276367, + "learning_rate": 4.484376881321237e-06, + "loss": 0.3038, + "step": 302 + }, + { + "epoch": 0.6424595812350914, + "grad_norm": 1.4699310064315796, + "learning_rate": 4.480966969480992e-06, + "loss": 0.1923, + "step": 303 + }, + { + "epoch": 0.6445799098860323, + "grad_norm": 1.1542787551879883, + "learning_rate": 4.477547125074826e-06, + "loss": 0.2522, + "step": 304 + }, + { + "epoch": 0.6467002385369732, + "grad_norm": 3.114525556564331, + "learning_rate": 4.474117365249835e-06, + "loss": 0.3941, + "step": 305 + }, + { + "epoch": 0.6488205671879141, + "grad_norm": 3.131681442260742, + "learning_rate": 4.4706777072028305e-06, + "loss": 0.2683, + "step": 306 + }, + { + "epoch": 0.6509408958388551, + "grad_norm": 2.522207021713257, + "learning_rate": 4.4672281681802536e-06, + "loss": 0.4248, + "step": 307 + }, + { + "epoch": 0.6530612244897959, + "grad_norm": 2.6396241188049316, + "learning_rate": 4.463768765478088e-06, + "loss": 0.3615, + "step": 308 + }, + { + "epoch": 0.6551815531407368, + "grad_norm": 1.8852202892303467, + "learning_rate": 4.460299516441777e-06, + "loss": 0.1891, + "step": 309 + }, + { + "epoch": 0.6573018817916777, + "grad_norm": 1.5633989572525024, + "learning_rate": 4.456820438466127e-06, + "loss": 0.3321, + "step": 310 + }, + { + "epoch": 0.6594222104426186, + "grad_norm": 0.9212223291397095, + "learning_rate": 4.453331548995235e-06, + "loss": 0.1842, + "step": 311 + }, + { + "epoch": 0.6615425390935595, + "grad_norm": 0.9008169174194336, + "learning_rate": 4.449832865522386e-06, + "loss": 0.2623, + "step": 312 + }, + { + "epoch": 0.6636628677445005, + "grad_norm": 2.3239521980285645, + "learning_rate": 4.446324405589973e-06, + "loss": 0.2996, + "step": 313 + }, + { + "epoch": 0.6657831963954413, + "grad_norm": 1.245194911956787, + "learning_rate": 4.442806186789414e-06, + "loss": 0.292, + "step": 314 + }, + { + "epoch": 0.6679035250463822, + "grad_norm": 1.7970019578933716, + "learning_rate": 4.43927822676105e-06, + "loss": 0.3205, + "step": 315 + }, + { + "epoch": 0.6700238536973231, + "grad_norm": 2.037053346633911, + "learning_rate": 4.43574054319407e-06, + "loss": 0.3059, + "step": 316 + }, + { + "epoch": 0.672144182348264, + "grad_norm": 2.7384984493255615, + "learning_rate": 4.432193153826414e-06, + "loss": 0.1772, + "step": 317 + }, + { + "epoch": 0.6742645109992049, + "grad_norm": 2.5001444816589355, + "learning_rate": 4.428636076444689e-06, + "loss": 0.2689, + "step": 318 + }, + { + "epoch": 0.6763848396501457, + "grad_norm": 2.1559765338897705, + "learning_rate": 4.425069328884076e-06, + "loss": 0.3262, + "step": 319 + }, + { + "epoch": 0.6785051683010866, + "grad_norm": 2.2558753490448, + "learning_rate": 4.421492929028243e-06, + "loss": 0.2938, + "step": 320 + }, + { + "epoch": 0.6806254969520276, + "grad_norm": 2.5780105590820312, + "learning_rate": 4.417906894809254e-06, + "loss": 0.287, + "step": 321 + }, + { + "epoch": 0.6827458256029685, + "grad_norm": 1.2815518379211426, + "learning_rate": 4.41431124420748e-06, + "loss": 0.2534, + "step": 322 + }, + { + "epoch": 0.6848661542539094, + "grad_norm": 1.6378668546676636, + "learning_rate": 4.410705995251509e-06, + "loss": 0.2202, + "step": 323 + }, + { + "epoch": 0.6869864829048502, + "grad_norm": 1.0137518644332886, + "learning_rate": 4.4070911660180546e-06, + "loss": 0.2868, + "step": 324 + }, + { + "epoch": 0.6891068115557911, + "grad_norm": 1.8886064291000366, + "learning_rate": 4.403466774631867e-06, + "loss": 0.1661, + "step": 325 + }, + { + "epoch": 0.691227140206732, + "grad_norm": 1.7047724723815918, + "learning_rate": 4.39983283926564e-06, + "loss": 0.2195, + "step": 326 + }, + { + "epoch": 0.693347468857673, + "grad_norm": 3.3912291526794434, + "learning_rate": 4.3961893781399186e-06, + "loss": 0.2696, + "step": 327 + }, + { + "epoch": 0.6954677975086139, + "grad_norm": 1.9746174812316895, + "learning_rate": 4.392536409523015e-06, + "loss": 0.3592, + "step": 328 + }, + { + "epoch": 0.6975881261595547, + "grad_norm": 5.287510395050049, + "learning_rate": 4.388873951730909e-06, + "loss": 0.2301, + "step": 329 + }, + { + "epoch": 0.6997084548104956, + "grad_norm": 3.351943254470825, + "learning_rate": 4.385202023127158e-06, + "loss": 0.2445, + "step": 330 + }, + { + "epoch": 0.7018287834614365, + "grad_norm": 1.951226830482483, + "learning_rate": 4.381520642122808e-06, + "loss": 0.283, + "step": 331 + }, + { + "epoch": 0.7039491121123774, + "grad_norm": 2.763387441635132, + "learning_rate": 4.3778298271762995e-06, + "loss": 0.423, + "step": 332 + }, + { + "epoch": 0.7060694407633183, + "grad_norm": 5.014280796051025, + "learning_rate": 4.374129596793375e-06, + "loss": 0.3269, + "step": 333 + }, + { + "epoch": 0.7081897694142593, + "grad_norm": 1.114488124847412, + "learning_rate": 4.370419969526982e-06, + "loss": 0.2774, + "step": 334 + }, + { + "epoch": 0.7103100980652001, + "grad_norm": 2.432865619659424, + "learning_rate": 4.366700963977188e-06, + "loss": 0.2744, + "step": 335 + }, + { + "epoch": 0.712430426716141, + "grad_norm": 1.1525187492370605, + "learning_rate": 4.362972598791085e-06, + "loss": 0.3201, + "step": 336 + }, + { + "epoch": 0.7145507553670819, + "grad_norm": 2.6614933013916016, + "learning_rate": 4.3592348926626886e-06, + "loss": 0.1742, + "step": 337 + }, + { + "epoch": 0.7166710840180228, + "grad_norm": 3.2576396465301514, + "learning_rate": 4.355487864332853e-06, + "loss": 0.3311, + "step": 338 + }, + { + "epoch": 0.7187914126689637, + "grad_norm": 2.1801483631134033, + "learning_rate": 4.351731532589173e-06, + "loss": 0.2022, + "step": 339 + }, + { + "epoch": 0.7209117413199045, + "grad_norm": 2.8371381759643555, + "learning_rate": 4.347965916265893e-06, + "loss": 0.3076, + "step": 340 + }, + { + "epoch": 0.7230320699708455, + "grad_norm": 2.4353699684143066, + "learning_rate": 4.3441910342438076e-06, + "loss": 0.2187, + "step": 341 + }, + { + "epoch": 0.7251523986217864, + "grad_norm": 0.7535296678543091, + "learning_rate": 4.340406905450171e-06, + "loss": 0.282, + "step": 342 + }, + { + "epoch": 0.7272727272727273, + "grad_norm": 1.656532883644104, + "learning_rate": 4.3366135488586e-06, + "loss": 0.2898, + "step": 343 + }, + { + "epoch": 0.7293930559236682, + "grad_norm": 1.5099116563796997, + "learning_rate": 4.332810983488979e-06, + "loss": 0.2422, + "step": 344 + }, + { + "epoch": 0.731513384574609, + "grad_norm": 1.4573249816894531, + "learning_rate": 4.3289992284073675e-06, + "loss": 0.2781, + "step": 345 + }, + { + "epoch": 0.7336337132255499, + "grad_norm": 1.6948301792144775, + "learning_rate": 4.325178302725901e-06, + "loss": 0.1749, + "step": 346 + }, + { + "epoch": 0.7357540418764908, + "grad_norm": 2.298999547958374, + "learning_rate": 4.321348225602694e-06, + "loss": 0.287, + "step": 347 + }, + { + "epoch": 0.7378743705274318, + "grad_norm": 1.248860239982605, + "learning_rate": 4.31750901624175e-06, + "loss": 0.2698, + "step": 348 + }, + { + "epoch": 0.7399946991783727, + "grad_norm": 1.6918904781341553, + "learning_rate": 4.31366069389286e-06, + "loss": 0.2312, + "step": 349 + }, + { + "epoch": 0.7421150278293135, + "grad_norm": 3.1004738807678223, + "learning_rate": 4.309803277851507e-06, + "loss": 0.2886, + "step": 350 + }, + { + "epoch": 0.7442353564802544, + "grad_norm": 2.718191623687744, + "learning_rate": 4.305936787458769e-06, + "loss": 0.2501, + "step": 351 + }, + { + "epoch": 0.7463556851311953, + "grad_norm": 1.4747895002365112, + "learning_rate": 4.302061242101226e-06, + "loss": 0.1851, + "step": 352 + }, + { + "epoch": 0.7484760137821362, + "grad_norm": 1.5939568281173706, + "learning_rate": 4.2981766612108576e-06, + "loss": 0.2419, + "step": 353 + }, + { + "epoch": 0.7505963424330772, + "grad_norm": 1.2325273752212524, + "learning_rate": 4.294283064264947e-06, + "loss": 0.2165, + "step": 354 + }, + { + "epoch": 0.7527166710840181, + "grad_norm": 5.181772232055664, + "learning_rate": 4.290380470785984e-06, + "loss": 0.2562, + "step": 355 + }, + { + "epoch": 0.7548369997349589, + "grad_norm": 1.3235808610916138, + "learning_rate": 4.2864689003415675e-06, + "loss": 0.318, + "step": 356 + }, + { + "epoch": 0.7569573283858998, + "grad_norm": 2.194802761077881, + "learning_rate": 4.282548372544307e-06, + "loss": 0.2193, + "step": 357 + }, + { + "epoch": 0.7590776570368407, + "grad_norm": 2.330679178237915, + "learning_rate": 4.278618907051724e-06, + "loss": 0.2466, + "step": 358 + }, + { + "epoch": 0.7611979856877816, + "grad_norm": 2.1647789478302, + "learning_rate": 4.274680523566154e-06, + "loss": 0.2749, + "step": 359 + }, + { + "epoch": 0.7633183143387225, + "grad_norm": 1.5459215641021729, + "learning_rate": 4.270733241834647e-06, + "loss": 0.3133, + "step": 360 + }, + { + "epoch": 0.7654386429896634, + "grad_norm": 0.6741765141487122, + "learning_rate": 4.266777081648868e-06, + "loss": 0.3188, + "step": 361 + }, + { + "epoch": 0.7675589716406043, + "grad_norm": 2.7495875358581543, + "learning_rate": 4.262812062844999e-06, + "loss": 0.3409, + "step": 362 + }, + { + "epoch": 0.7696793002915452, + "grad_norm": 4.160212993621826, + "learning_rate": 4.25883820530364e-06, + "loss": 0.2538, + "step": 363 + }, + { + "epoch": 0.7717996289424861, + "grad_norm": 2.0317301750183105, + "learning_rate": 4.254855528949709e-06, + "loss": 0.2741, + "step": 364 + }, + { + "epoch": 0.773919957593427, + "grad_norm": 2.1977953910827637, + "learning_rate": 4.250864053752337e-06, + "loss": 0.2353, + "step": 365 + }, + { + "epoch": 0.7760402862443678, + "grad_norm": 3.028444290161133, + "learning_rate": 4.2468637997247794e-06, + "loss": 0.2585, + "step": 366 + }, + { + "epoch": 0.7781606148953087, + "grad_norm": 1.4199281930923462, + "learning_rate": 4.242854786924302e-06, + "loss": 0.2143, + "step": 367 + }, + { + "epoch": 0.7802809435462497, + "grad_norm": 1.7088114023208618, + "learning_rate": 4.238837035452092e-06, + "loss": 0.1835, + "step": 368 + }, + { + "epoch": 0.7824012721971906, + "grad_norm": 1.4326963424682617, + "learning_rate": 4.234810565453148e-06, + "loss": 0.2107, + "step": 369 + }, + { + "epoch": 0.7845216008481315, + "grad_norm": 1.337410569190979, + "learning_rate": 4.230775397116188e-06, + "loss": 0.2497, + "step": 370 + }, + { + "epoch": 0.7866419294990723, + "grad_norm": 1.4517322778701782, + "learning_rate": 4.2267315506735394e-06, + "loss": 0.2577, + "step": 371 + }, + { + "epoch": 0.7887622581500132, + "grad_norm": 0.9060394167900085, + "learning_rate": 4.2226790464010445e-06, + "loss": 0.1978, + "step": 372 + }, + { + "epoch": 0.7908825868009541, + "grad_norm": 2.3969204425811768, + "learning_rate": 4.218617904617953e-06, + "loss": 0.2462, + "step": 373 + }, + { + "epoch": 0.793002915451895, + "grad_norm": 2.8702633380889893, + "learning_rate": 4.2145481456868265e-06, + "loss": 0.274, + "step": 374 + }, + { + "epoch": 0.795123244102836, + "grad_norm": 1.4537705183029175, + "learning_rate": 4.210469790013431e-06, + "loss": 0.3099, + "step": 375 + }, + { + "epoch": 0.7972435727537769, + "grad_norm": 2.5505456924438477, + "learning_rate": 4.206382858046636e-06, + "loss": 0.4174, + "step": 376 + }, + { + "epoch": 0.7993639014047177, + "grad_norm": 0.903439462184906, + "learning_rate": 4.202287370278313e-06, + "loss": 0.2273, + "step": 377 + }, + { + "epoch": 0.8014842300556586, + "grad_norm": 2.118838310241699, + "learning_rate": 4.198183347243233e-06, + "loss": 0.1472, + "step": 378 + }, + { + "epoch": 0.8036045587065995, + "grad_norm": 1.7555965185165405, + "learning_rate": 4.194070809518963e-06, + "loss": 0.3014, + "step": 379 + }, + { + "epoch": 0.8057248873575404, + "grad_norm": 1.575334072113037, + "learning_rate": 4.1899497777257615e-06, + "loss": 0.2107, + "step": 380 + }, + { + "epoch": 0.8078452160084814, + "grad_norm": 1.020128607749939, + "learning_rate": 4.185820272526477e-06, + "loss": 0.2336, + "step": 381 + }, + { + "epoch": 0.8099655446594222, + "grad_norm": 2.3840348720550537, + "learning_rate": 4.181682314626443e-06, + "loss": 0.3076, + "step": 382 + }, + { + "epoch": 0.8120858733103631, + "grad_norm": 0.7766013741493225, + "learning_rate": 4.177535924773375e-06, + "loss": 0.2436, + "step": 383 + }, + { + "epoch": 0.814206201961304, + "grad_norm": 2.136934757232666, + "learning_rate": 4.173381123757268e-06, + "loss": 0.3278, + "step": 384 + }, + { + "epoch": 0.8163265306122449, + "grad_norm": 2.10295033454895, + "learning_rate": 4.169217932410288e-06, + "loss": 0.3002, + "step": 385 + }, + { + "epoch": 0.8184468592631858, + "grad_norm": 2.8707754611968994, + "learning_rate": 4.165046371606671e-06, + "loss": 0.2263, + "step": 386 + }, + { + "epoch": 0.8205671879141266, + "grad_norm": 2.254936933517456, + "learning_rate": 4.160866462262618e-06, + "loss": 0.2967, + "step": 387 + }, + { + "epoch": 0.8226875165650676, + "grad_norm": 1.71103036403656, + "learning_rate": 4.15667822533619e-06, + "loss": 0.2266, + "step": 388 + }, + { + "epoch": 0.8248078452160085, + "grad_norm": 3.3162853717803955, + "learning_rate": 4.152481681827201e-06, + "loss": 0.3302, + "step": 389 + }, + { + "epoch": 0.8269281738669494, + "grad_norm": 2.03659987449646, + "learning_rate": 4.1482768527771155e-06, + "loss": 0.2646, + "step": 390 + }, + { + "epoch": 0.8290485025178903, + "grad_norm": 3.0324466228485107, + "learning_rate": 4.14406375926894e-06, + "loss": 0.3638, + "step": 391 + }, + { + "epoch": 0.8311688311688312, + "grad_norm": 1.9642225503921509, + "learning_rate": 4.13984242242712e-06, + "loss": 0.1704, + "step": 392 + }, + { + "epoch": 0.833289159819772, + "grad_norm": 1.727362036705017, + "learning_rate": 4.135612863417435e-06, + "loss": 0.2594, + "step": 393 + }, + { + "epoch": 0.835409488470713, + "grad_norm": 1.6325123310089111, + "learning_rate": 4.131375103446889e-06, + "loss": 0.2068, + "step": 394 + }, + { + "epoch": 0.8375298171216539, + "grad_norm": 1.1266484260559082, + "learning_rate": 4.127129163763601e-06, + "loss": 0.1623, + "step": 395 + }, + { + "epoch": 0.8396501457725948, + "grad_norm": 0.7224255800247192, + "learning_rate": 4.122875065656712e-06, + "loss": 0.1622, + "step": 396 + }, + { + "epoch": 0.8417704744235357, + "grad_norm": 2.530782699584961, + "learning_rate": 4.118612830456262e-06, + "loss": 0.3365, + "step": 397 + }, + { + "epoch": 0.8438908030744765, + "grad_norm": 2.0396225452423096, + "learning_rate": 4.114342479533094e-06, + "loss": 0.2857, + "step": 398 + }, + { + "epoch": 0.8460111317254174, + "grad_norm": 1.927078127861023, + "learning_rate": 4.110064034298741e-06, + "loss": 0.2944, + "step": 399 + }, + { + "epoch": 0.8481314603763583, + "grad_norm": 3.6908702850341797, + "learning_rate": 4.105777516205324e-06, + "loss": 0.2156, + "step": 400 + }, + { + "epoch": 0.8502517890272993, + "grad_norm": 0.6398283243179321, + "learning_rate": 4.101482946745438e-06, + "loss": 0.2235, + "step": 401 + }, + { + "epoch": 0.8523721176782402, + "grad_norm": 1.541572093963623, + "learning_rate": 4.09718034745205e-06, + "loss": 0.1273, + "step": 402 + }, + { + "epoch": 0.854492446329181, + "grad_norm": 3.8959381580352783, + "learning_rate": 4.092869739898386e-06, + "loss": 0.3338, + "step": 403 + }, + { + "epoch": 0.8566127749801219, + "grad_norm": 1.9765669107437134, + "learning_rate": 4.0885511456978275e-06, + "loss": 0.2359, + "step": 404 + }, + { + "epoch": 0.8587331036310628, + "grad_norm": 2.276289939880371, + "learning_rate": 4.084224586503801e-06, + "loss": 0.2267, + "step": 405 + }, + { + "epoch": 0.8608534322820037, + "grad_norm": 0.6204816102981567, + "learning_rate": 4.0798900840096694e-06, + "loss": 0.1329, + "step": 406 + }, + { + "epoch": 0.8629737609329446, + "grad_norm": 1.452314853668213, + "learning_rate": 4.075547659948621e-06, + "loss": 0.2221, + "step": 407 + }, + { + "epoch": 0.8650940895838855, + "grad_norm": 1.0840950012207031, + "learning_rate": 4.071197336093566e-06, + "loss": 0.3571, + "step": 408 + }, + { + "epoch": 0.8672144182348264, + "grad_norm": 3.603943347930908, + "learning_rate": 4.0668391342570225e-06, + "loss": 0.247, + "step": 409 + }, + { + "epoch": 0.8693347468857673, + "grad_norm": 1.4998263120651245, + "learning_rate": 4.062473076291009e-06, + "loss": 0.2483, + "step": 410 + }, + { + "epoch": 0.8714550755367082, + "grad_norm": 1.4034696817398071, + "learning_rate": 4.058099184086934e-06, + "loss": 0.2748, + "step": 411 + }, + { + "epoch": 0.8735754041876491, + "grad_norm": 1.1534749269485474, + "learning_rate": 4.05371747957549e-06, + "loss": 0.1534, + "step": 412 + }, + { + "epoch": 0.87569573283859, + "grad_norm": 1.709837555885315, + "learning_rate": 4.049327984726535e-06, + "loss": 0.3573, + "step": 413 + }, + { + "epoch": 0.8778160614895308, + "grad_norm": 1.9228962659835815, + "learning_rate": 4.044930721548992e-06, + "loss": 0.3242, + "step": 414 + }, + { + "epoch": 0.8799363901404718, + "grad_norm": 2.2846219539642334, + "learning_rate": 4.040525712090733e-06, + "loss": 0.2101, + "step": 415 + }, + { + "epoch": 0.8820567187914127, + "grad_norm": 2.0104122161865234, + "learning_rate": 4.0361129784384705e-06, + "loss": 0.2115, + "step": 416 + }, + { + "epoch": 0.8841770474423536, + "grad_norm": 2.7587649822235107, + "learning_rate": 4.031692542717645e-06, + "loss": 0.274, + "step": 417 + }, + { + "epoch": 0.8862973760932945, + "grad_norm": 4.8226542472839355, + "learning_rate": 4.027264427092316e-06, + "loss": 0.4542, + "step": 418 + }, + { + "epoch": 0.8884177047442353, + "grad_norm": 2.651845693588257, + "learning_rate": 4.022828653765049e-06, + "loss": 0.2008, + "step": 419 + }, + { + "epoch": 0.8905380333951762, + "grad_norm": 1.5795021057128906, + "learning_rate": 4.018385244976807e-06, + "loss": 0.2777, + "step": 420 + }, + { + "epoch": 0.8926583620461171, + "grad_norm": 1.470374584197998, + "learning_rate": 4.0139342230068355e-06, + "loss": 0.2378, + "step": 421 + }, + { + "epoch": 0.8947786906970581, + "grad_norm": 2.2073006629943848, + "learning_rate": 4.009475610172553e-06, + "loss": 0.2469, + "step": 422 + }, + { + "epoch": 0.896899019347999, + "grad_norm": 3.0384535789489746, + "learning_rate": 4.005009428829439e-06, + "loss": 0.2247, + "step": 423 + }, + { + "epoch": 0.8990193479989398, + "grad_norm": 1.5634294748306274, + "learning_rate": 4.0005357013709215e-06, + "loss": 0.2117, + "step": 424 + }, + { + "epoch": 0.9011396766498807, + "grad_norm": 0.9764052033424377, + "learning_rate": 3.996054450228263e-06, + "loss": 0.2591, + "step": 425 + }, + { + "epoch": 0.9032600053008216, + "grad_norm": 1.669441819190979, + "learning_rate": 3.991565697870453e-06, + "loss": 0.2905, + "step": 426 + }, + { + "epoch": 0.9053803339517625, + "grad_norm": 2.682272434234619, + "learning_rate": 3.987069466804089e-06, + "loss": 0.298, + "step": 427 + }, + { + "epoch": 0.9075006626027035, + "grad_norm": 0.5667883157730103, + "learning_rate": 3.982565779573269e-06, + "loss": 0.4034, + "step": 428 + }, + { + "epoch": 0.9096209912536443, + "grad_norm": 2.6494028568267822, + "learning_rate": 3.978054658759474e-06, + "loss": 0.2176, + "step": 429 + }, + { + "epoch": 0.9117413199045852, + "grad_norm": 1.3368819952011108, + "learning_rate": 3.973536126981459e-06, + "loss": 0.2228, + "step": 430 + }, + { + "epoch": 0.9138616485555261, + "grad_norm": 2.0899736881256104, + "learning_rate": 3.969010206895136e-06, + "loss": 0.2471, + "step": 431 + }, + { + "epoch": 0.915981977206467, + "grad_norm": 0.29745158553123474, + "learning_rate": 3.964476921193464e-06, + "loss": 0.1858, + "step": 432 + }, + { + "epoch": 0.9181023058574079, + "grad_norm": 2.4237589836120605, + "learning_rate": 3.9599362926063315e-06, + "loss": 0.2178, + "step": 433 + }, + { + "epoch": 0.9202226345083488, + "grad_norm": 2.9499125480651855, + "learning_rate": 3.955388343900443e-06, + "loss": 0.2695, + "step": 434 + }, + { + "epoch": 0.9223429631592897, + "grad_norm": 1.6062681674957275, + "learning_rate": 3.950833097879208e-06, + "loss": 0.2193, + "step": 435 + }, + { + "epoch": 0.9244632918102306, + "grad_norm": 3.3054378032684326, + "learning_rate": 3.946270577382626e-06, + "loss": 0.2479, + "step": 436 + }, + { + "epoch": 0.9265836204611715, + "grad_norm": 1.836806058883667, + "learning_rate": 3.941700805287169e-06, + "loss": 0.3304, + "step": 437 + }, + { + "epoch": 0.9287039491121124, + "grad_norm": 2.154625654220581, + "learning_rate": 3.937123804505666e-06, + "loss": 0.2871, + "step": 438 + }, + { + "epoch": 0.9308242777630533, + "grad_norm": 1.1884167194366455, + "learning_rate": 3.932539597987196e-06, + "loss": 0.2042, + "step": 439 + }, + { + "epoch": 0.9329446064139941, + "grad_norm": 1.345928430557251, + "learning_rate": 3.927948208716964e-06, + "loss": 0.25, + "step": 440 + }, + { + "epoch": 0.935064935064935, + "grad_norm": 1.952118992805481, + "learning_rate": 3.92334965971619e-06, + "loss": 0.2686, + "step": 441 + }, + { + "epoch": 0.937185263715876, + "grad_norm": 2.034341335296631, + "learning_rate": 3.918743974041992e-06, + "loss": 0.2693, + "step": 442 + }, + { + "epoch": 0.9393055923668169, + "grad_norm": 1.5500835180282593, + "learning_rate": 3.914131174787274e-06, + "loss": 0.2578, + "step": 443 + }, + { + "epoch": 0.9414259210177578, + "grad_norm": 1.8623617887496948, + "learning_rate": 3.909511285080605e-06, + "loss": 0.278, + "step": 444 + }, + { + "epoch": 0.9435462496686986, + "grad_norm": 3.387428045272827, + "learning_rate": 3.9048843280861055e-06, + "loss": 0.2269, + "step": 445 + }, + { + "epoch": 0.9456665783196395, + "grad_norm": 3.092822551727295, + "learning_rate": 3.900250327003333e-06, + "loss": 0.2526, + "step": 446 + }, + { + "epoch": 0.9477869069705804, + "grad_norm": 2.328296422958374, + "learning_rate": 3.895609305067162e-06, + "loss": 0.2397, + "step": 447 + }, + { + "epoch": 0.9499072356215214, + "grad_norm": 1.579817533493042, + "learning_rate": 3.890961285547672e-06, + "loss": 0.2516, + "step": 448 + }, + { + "epoch": 0.9520275642724623, + "grad_norm": 1.765915870666504, + "learning_rate": 3.886306291750028e-06, + "loss": 0.2889, + "step": 449 + }, + { + "epoch": 0.9541478929234031, + "grad_norm": 2.5610663890838623, + "learning_rate": 3.881644347014361e-06, + "loss": 0.3136, + "step": 450 + }, + { + "epoch": 0.956268221574344, + "grad_norm": 1.9422125816345215, + "learning_rate": 3.876975474715656e-06, + "loss": 0.2424, + "step": 451 + }, + { + "epoch": 0.9583885502252849, + "grad_norm": 2.0714170932769775, + "learning_rate": 3.872299698263634e-06, + "loss": 0.2841, + "step": 452 + }, + { + "epoch": 0.9605088788762258, + "grad_norm": 1.0616906881332397, + "learning_rate": 3.867617041102633e-06, + "loss": 0.2141, + "step": 453 + }, + { + "epoch": 0.9626292075271667, + "grad_norm": 1.4508030414581299, + "learning_rate": 3.862927526711488e-06, + "loss": 0.2419, + "step": 454 + }, + { + "epoch": 0.9647495361781077, + "grad_norm": 1.6528363227844238, + "learning_rate": 3.858231178603421e-06, + "loss": 0.2179, + "step": 455 + }, + { + "epoch": 0.9668698648290485, + "grad_norm": 2.853685140609741, + "learning_rate": 3.853528020325913e-06, + "loss": 0.2963, + "step": 456 + }, + { + "epoch": 0.9689901934799894, + "grad_norm": 1.16892671585083, + "learning_rate": 3.848818075460595e-06, + "loss": 0.2386, + "step": 457 + }, + { + "epoch": 0.9711105221309303, + "grad_norm": 1.986411452293396, + "learning_rate": 3.8441013676231255e-06, + "loss": 0.1932, + "step": 458 + }, + { + "epoch": 0.9732308507818712, + "grad_norm": 1.9140475988388062, + "learning_rate": 3.83937792046307e-06, + "loss": 0.2455, + "step": 459 + }, + { + "epoch": 0.9753511794328121, + "grad_norm": 1.5750322341918945, + "learning_rate": 3.834647757663788e-06, + "loss": 0.2605, + "step": 460 + }, + { + "epoch": 0.9774715080837529, + "grad_norm": 1.1858994960784912, + "learning_rate": 3.829910902942309e-06, + "loss": 0.26, + "step": 461 + }, + { + "epoch": 0.9795918367346939, + "grad_norm": 3.8463196754455566, + "learning_rate": 3.825167380049218e-06, + "loss": 0.2549, + "step": 462 + }, + { + "epoch": 0.9817121653856348, + "grad_norm": 2.046649217605591, + "learning_rate": 3.820417212768531e-06, + "loss": 0.1391, + "step": 463 + }, + { + "epoch": 0.9838324940365757, + "grad_norm": 1.923967957496643, + "learning_rate": 3.8156604249175825e-06, + "loss": 0.305, + "step": 464 + }, + { + "epoch": 0.9859528226875166, + "grad_norm": 3.389587879180908, + "learning_rate": 3.810897040346899e-06, + "loss": 0.3457, + "step": 465 + }, + { + "epoch": 0.9880731513384574, + "grad_norm": 1.8285034894943237, + "learning_rate": 3.8061270829400876e-06, + "loss": 0.2261, + "step": 466 + }, + { + "epoch": 0.9901934799893983, + "grad_norm": 2.468703031539917, + "learning_rate": 3.801350576613706e-06, + "loss": 0.2855, + "step": 467 + }, + { + "epoch": 0.9923138086403392, + "grad_norm": 2.497868776321411, + "learning_rate": 3.796567545317153e-06, + "loss": 0.1904, + "step": 468 + }, + { + "epoch": 0.9944341372912802, + "grad_norm": 1.1878782510757446, + "learning_rate": 3.79177801303254e-06, + "loss": 0.2144, + "step": 469 + }, + { + "epoch": 0.9965544659422211, + "grad_norm": 1.0926648378372192, + "learning_rate": 3.7869820037745773e-06, + "loss": 0.1962, + "step": 470 + }, + { + "epoch": 0.9986747945931619, + "grad_norm": 1.597976803779602, + "learning_rate": 3.7821795415904482e-06, + "loss": 0.2887, + "step": 471 + }, + { + "epoch": 1.0015902464882056, + "grad_norm": 1.37874174118042, + "learning_rate": 3.777370650559693e-06, + "loss": 0.2933, + "step": 472 + }, + { + "epoch": 1.0037105751391466, + "grad_norm": 1.9284913539886475, + "learning_rate": 3.772555354794085e-06, + "loss": 0.2159, + "step": 473 + }, + { + "epoch": 1.0058309037900874, + "grad_norm": 3.890476942062378, + "learning_rate": 3.7677336784375107e-06, + "loss": 0.3206, + "step": 474 + }, + { + "epoch": 1.0079512324410285, + "grad_norm": 2.379439353942871, + "learning_rate": 3.76290564566585e-06, + "loss": 0.2397, + "step": 475 + }, + { + "epoch": 1.0100715610919693, + "grad_norm": 1.771033525466919, + "learning_rate": 3.7580712806868536e-06, + "loss": 0.2207, + "step": 476 + }, + { + "epoch": 1.01219188974291, + "grad_norm": 1.5666189193725586, + "learning_rate": 3.7532306077400206e-06, + "loss": 0.2817, + "step": 477 + }, + { + "epoch": 1.014312218393851, + "grad_norm": 0.6713786125183105, + "learning_rate": 3.7483836510964792e-06, + "loss": 0.2123, + "step": 478 + }, + { + "epoch": 1.016432547044792, + "grad_norm": 1.3699878454208374, + "learning_rate": 3.7435304350588643e-06, + "loss": 0.2889, + "step": 479 + }, + { + "epoch": 1.018552875695733, + "grad_norm": 1.747329592704773, + "learning_rate": 3.738670983961195e-06, + "loss": 0.2517, + "step": 480 + }, + { + "epoch": 1.0206732043466737, + "grad_norm": 2.277524471282959, + "learning_rate": 3.7338053221687533e-06, + "loss": 0.2451, + "step": 481 + }, + { + "epoch": 1.0227935329976146, + "grad_norm": 2.4319913387298584, + "learning_rate": 3.728933474077961e-06, + "loss": 0.2594, + "step": 482 + }, + { + "epoch": 1.0249138616485556, + "grad_norm": 1.2065045833587646, + "learning_rate": 3.7240554641162585e-06, + "loss": 0.2706, + "step": 483 + }, + { + "epoch": 1.0270341902994964, + "grad_norm": 1.6133732795715332, + "learning_rate": 3.7191713167419814e-06, + "loss": 0.2099, + "step": 484 + }, + { + "epoch": 1.0291545189504374, + "grad_norm": 2.497514486312866, + "learning_rate": 3.7142810564442388e-06, + "loss": 0.3406, + "step": 485 + }, + { + "epoch": 1.0312748476013782, + "grad_norm": 2.1485133171081543, + "learning_rate": 3.7093847077427904e-06, + "loss": 0.2251, + "step": 486 + }, + { + "epoch": 1.033395176252319, + "grad_norm": 2.118579149246216, + "learning_rate": 3.7044822951879224e-06, + "loss": 0.1466, + "step": 487 + }, + { + "epoch": 1.03551550490326, + "grad_norm": 1.457202672958374, + "learning_rate": 3.6995738433603234e-06, + "loss": 0.3749, + "step": 488 + }, + { + "epoch": 1.0376358335542009, + "grad_norm": 1.4717838764190674, + "learning_rate": 3.6946593768709667e-06, + "loss": 0.2145, + "step": 489 + }, + { + "epoch": 1.0397561622051419, + "grad_norm": 1.1702837944030762, + "learning_rate": 3.68973892036098e-06, + "loss": 0.1499, + "step": 490 + }, + { + "epoch": 1.0418764908560827, + "grad_norm": 1.9794777631759644, + "learning_rate": 3.684812498501528e-06, + "loss": 0.2445, + "step": 491 + }, + { + "epoch": 1.0439968195070235, + "grad_norm": 5.563566207885742, + "learning_rate": 3.6798801359936808e-06, + "loss": 0.2568, + "step": 492 + }, + { + "epoch": 1.0461171481579645, + "grad_norm": 1.5425770282745361, + "learning_rate": 3.6749418575683005e-06, + "loss": 0.1574, + "step": 493 + }, + { + "epoch": 1.0482374768089053, + "grad_norm": 2.789044141769409, + "learning_rate": 3.669997687985908e-06, + "loss": 0.2175, + "step": 494 + }, + { + "epoch": 1.0503578054598464, + "grad_norm": 2.0900280475616455, + "learning_rate": 3.665047652036563e-06, + "loss": 0.2276, + "step": 495 + }, + { + "epoch": 1.0524781341107872, + "grad_norm": 1.0383256673812866, + "learning_rate": 3.6600917745397403e-06, + "loss": 0.1829, + "step": 496 + }, + { + "epoch": 1.054598462761728, + "grad_norm": 1.5721336603164673, + "learning_rate": 3.6551300803442035e-06, + "loss": 0.1972, + "step": 497 + }, + { + "epoch": 1.056718791412669, + "grad_norm": 0.5374338030815125, + "learning_rate": 3.650162594327881e-06, + "loss": 0.1839, + "step": 498 + }, + { + "epoch": 1.0588391200636098, + "grad_norm": 2.335890054702759, + "learning_rate": 3.6451893413977413e-06, + "loss": 0.2619, + "step": 499 + }, + { + "epoch": 1.0609594487145508, + "grad_norm": 2.4904046058654785, + "learning_rate": 3.6402103464896676e-06, + "loss": 0.2554, + "step": 500 + }, + { + "epoch": 1.0630797773654916, + "grad_norm": 2.201873540878296, + "learning_rate": 3.6352256345683358e-06, + "loss": 0.2435, + "step": 501 + }, + { + "epoch": 1.0652001060164324, + "grad_norm": 1.2125855684280396, + "learning_rate": 3.630235230627085e-06, + "loss": 0.2017, + "step": 502 + }, + { + "epoch": 1.0673204346673735, + "grad_norm": 1.4849168062210083, + "learning_rate": 3.6252391596877923e-06, + "loss": 0.2504, + "step": 503 + }, + { + "epoch": 1.0694407633183143, + "grad_norm": 1.445149302482605, + "learning_rate": 3.620237446800754e-06, + "loss": 0.2066, + "step": 504 + }, + { + "epoch": 1.0715610919692553, + "grad_norm": 2.7715039253234863, + "learning_rate": 3.615230117044551e-06, + "loss": 0.3272, + "step": 505 + }, + { + "epoch": 1.0736814206201961, + "grad_norm": 1.57020902633667, + "learning_rate": 3.610217195525928e-06, + "loss": 0.1846, + "step": 506 + }, + { + "epoch": 1.075801749271137, + "grad_norm": 1.8669289350509644, + "learning_rate": 3.6051987073796684e-06, + "loss": 0.1817, + "step": 507 + }, + { + "epoch": 1.077922077922078, + "grad_norm": 1.7587169408798218, + "learning_rate": 3.600174677768465e-06, + "loss": 0.1909, + "step": 508 + }, + { + "epoch": 1.0800424065730188, + "grad_norm": 2.2706751823425293, + "learning_rate": 3.595145131882795e-06, + "loss": 0.2923, + "step": 509 + }, + { + "epoch": 1.0821627352239598, + "grad_norm": 1.3291329145431519, + "learning_rate": 3.5901100949407967e-06, + "loss": 0.1405, + "step": 510 + }, + { + "epoch": 1.0842830638749006, + "grad_norm": 1.3454506397247314, + "learning_rate": 3.5850695921881383e-06, + "loss": 0.1853, + "step": 511 + }, + { + "epoch": 1.0864033925258414, + "grad_norm": 1.4152384996414185, + "learning_rate": 3.5800236488978946e-06, + "loss": 0.1181, + "step": 512 + }, + { + "epoch": 1.0885237211767824, + "grad_norm": 3.2865519523620605, + "learning_rate": 3.574972290370419e-06, + "loss": 0.2086, + "step": 513 + }, + { + "epoch": 1.0906440498277232, + "grad_norm": 1.90707528591156, + "learning_rate": 3.569915541933217e-06, + "loss": 0.202, + "step": 514 + }, + { + "epoch": 1.0927643784786643, + "grad_norm": 1.0512449741363525, + "learning_rate": 3.564853428940819e-06, + "loss": 0.1522, + "step": 515 + }, + { + "epoch": 1.094884707129605, + "grad_norm": 1.8712276220321655, + "learning_rate": 3.5597859767746524e-06, + "loss": 0.1442, + "step": 516 + }, + { + "epoch": 1.0970050357805459, + "grad_norm": 0.539580225944519, + "learning_rate": 3.5547132108429163e-06, + "loss": 0.2109, + "step": 517 + }, + { + "epoch": 1.099125364431487, + "grad_norm": 0.8322845101356506, + "learning_rate": 3.5496351565804542e-06, + "loss": 0.2269, + "step": 518 + }, + { + "epoch": 1.1012456930824277, + "grad_norm": 3.7564239501953125, + "learning_rate": 3.5445518394486215e-06, + "loss": 0.2547, + "step": 519 + }, + { + "epoch": 1.1033660217333687, + "grad_norm": 1.5247739553451538, + "learning_rate": 3.5394632849351663e-06, + "loss": 0.1796, + "step": 520 + }, + { + "epoch": 1.1054863503843095, + "grad_norm": 2.528141498565674, + "learning_rate": 3.5343695185540927e-06, + "loss": 0.1957, + "step": 521 + }, + { + "epoch": 1.1076066790352506, + "grad_norm": 1.748477578163147, + "learning_rate": 3.5292705658455406e-06, + "loss": 0.2102, + "step": 522 + }, + { + "epoch": 1.1097270076861914, + "grad_norm": 2.315608024597168, + "learning_rate": 3.524166452375652e-06, + "loss": 0.1964, + "step": 523 + }, + { + "epoch": 1.1118473363371322, + "grad_norm": 3.3954997062683105, + "learning_rate": 3.5190572037364445e-06, + "loss": 0.2761, + "step": 524 + }, + { + "epoch": 1.1139676649880732, + "grad_norm": 2.1260130405426025, + "learning_rate": 3.513942845545686e-06, + "loss": 0.1444, + "step": 525 + }, + { + "epoch": 1.116087993639014, + "grad_norm": 3.0516886711120605, + "learning_rate": 3.5088234034467604e-06, + "loss": 0.2643, + "step": 526 + }, + { + "epoch": 1.118208322289955, + "grad_norm": 1.948144555091858, + "learning_rate": 3.5036989031085455e-06, + "loss": 0.1631, + "step": 527 + }, + { + "epoch": 1.1203286509408958, + "grad_norm": 3.5732581615448, + "learning_rate": 3.498569370225279e-06, + "loss": 0.2681, + "step": 528 + }, + { + "epoch": 1.1224489795918366, + "grad_norm": 2.172426462173462, + "learning_rate": 3.4934348305164324e-06, + "loss": 0.2678, + "step": 529 + }, + { + "epoch": 1.1245693082427777, + "grad_norm": 1.3486807346343994, + "learning_rate": 3.4882953097265814e-06, + "loss": 0.207, + "step": 530 + }, + { + "epoch": 1.1266896368937185, + "grad_norm": 0.8123583793640137, + "learning_rate": 3.4831508336252766e-06, + "loss": 0.205, + "step": 531 + }, + { + "epoch": 1.1288099655446595, + "grad_norm": 1.3351538181304932, + "learning_rate": 3.4780014280069153e-06, + "loss": 0.1029, + "step": 532 + }, + { + "epoch": 1.1309302941956003, + "grad_norm": 1.3779995441436768, + "learning_rate": 3.472847118690611e-06, + "loss": 0.2622, + "step": 533 + }, + { + "epoch": 1.1330506228465411, + "grad_norm": 1.0775947570800781, + "learning_rate": 3.467687931520064e-06, + "loss": 0.1952, + "step": 534 + }, + { + "epoch": 1.1351709514974822, + "grad_norm": 2.4154770374298096, + "learning_rate": 3.462523892363432e-06, + "loss": 0.1626, + "step": 535 + }, + { + "epoch": 1.137291280148423, + "grad_norm": 2.120819091796875, + "learning_rate": 3.4573550271132e-06, + "loss": 0.2611, + "step": 536 + }, + { + "epoch": 1.139411608799364, + "grad_norm": 1.0421452522277832, + "learning_rate": 3.4521813616860545e-06, + "loss": 0.1755, + "step": 537 + }, + { + "epoch": 1.1415319374503048, + "grad_norm": 2.1693243980407715, + "learning_rate": 3.4470029220227445e-06, + "loss": 0.299, + "step": 538 + }, + { + "epoch": 1.1436522661012458, + "grad_norm": 1.831677794456482, + "learning_rate": 3.441819734087963e-06, + "loss": 0.1295, + "step": 539 + }, + { + "epoch": 1.1457725947521866, + "grad_norm": 1.4600670337677002, + "learning_rate": 3.4366318238702063e-06, + "loss": 0.1765, + "step": 540 + }, + { + "epoch": 1.1478929234031274, + "grad_norm": 1.2835088968276978, + "learning_rate": 3.4314392173816495e-06, + "loss": 0.1285, + "step": 541 + }, + { + "epoch": 1.1500132520540685, + "grad_norm": 2.4741337299346924, + "learning_rate": 3.426241940658015e-06, + "loss": 0.3035, + "step": 542 + }, + { + "epoch": 1.1521335807050093, + "grad_norm": 1.5897051095962524, + "learning_rate": 3.421040019758443e-06, + "loss": 0.2073, + "step": 543 + }, + { + "epoch": 1.1542539093559503, + "grad_norm": 1.9757038354873657, + "learning_rate": 3.4158334807653577e-06, + "loss": 0.1855, + "step": 544 + }, + { + "epoch": 1.156374238006891, + "grad_norm": 2.5434279441833496, + "learning_rate": 3.4106223497843395e-06, + "loss": 0.2083, + "step": 545 + }, + { + "epoch": 1.158494566657832, + "grad_norm": 1.7457334995269775, + "learning_rate": 3.4054066529439916e-06, + "loss": 0.2057, + "step": 546 + }, + { + "epoch": 1.160614895308773, + "grad_norm": 2.125014305114746, + "learning_rate": 3.4001864163958125e-06, + "loss": 0.2622, + "step": 547 + }, + { + "epoch": 1.1627352239597137, + "grad_norm": 1.9452868700027466, + "learning_rate": 3.394961666314061e-06, + "loss": 0.2356, + "step": 548 + }, + { + "epoch": 1.1648555526106548, + "grad_norm": 1.8804444074630737, + "learning_rate": 3.389732428895629e-06, + "loss": 0.2543, + "step": 549 + }, + { + "epoch": 1.1669758812615956, + "grad_norm": 1.7958191633224487, + "learning_rate": 3.384498730359905e-06, + "loss": 0.1877, + "step": 550 + }, + { + "epoch": 1.1690962099125364, + "grad_norm": 2.4635379314422607, + "learning_rate": 3.379260596948646e-06, + "loss": 0.2394, + "step": 551 + }, + { + "epoch": 1.1712165385634774, + "grad_norm": 1.7975070476531982, + "learning_rate": 3.3740180549258496e-06, + "loss": 0.251, + "step": 552 + }, + { + "epoch": 1.1733368672144182, + "grad_norm": 1.1541494131088257, + "learning_rate": 3.368771130577613e-06, + "loss": 0.1074, + "step": 553 + }, + { + "epoch": 1.1754571958653592, + "grad_norm": 1.4837067127227783, + "learning_rate": 3.363519850212007e-06, + "loss": 0.1926, + "step": 554 + }, + { + "epoch": 1.1775775245163, + "grad_norm": 3.1769111156463623, + "learning_rate": 3.358264240158947e-06, + "loss": 0.1456, + "step": 555 + }, + { + "epoch": 1.1796978531672409, + "grad_norm": 1.6445987224578857, + "learning_rate": 3.353004326770055e-06, + "loss": 0.2445, + "step": 556 + }, + { + "epoch": 1.1818181818181819, + "grad_norm": 0.7336058020591736, + "learning_rate": 3.347740136418529e-06, + "loss": 0.2098, + "step": 557 + }, + { + "epoch": 1.1839385104691227, + "grad_norm": 0.853908121585846, + "learning_rate": 3.342471695499014e-06, + "loss": 0.2096, + "step": 558 + }, + { + "epoch": 1.1860588391200637, + "grad_norm": 0.5674437880516052, + "learning_rate": 3.3371990304274654e-06, + "loss": 0.2537, + "step": 559 + }, + { + "epoch": 1.1881791677710045, + "grad_norm": 1.4246636629104614, + "learning_rate": 3.33192216764102e-06, + "loss": 0.1266, + "step": 560 + }, + { + "epoch": 1.1902994964219453, + "grad_norm": 0.6851096153259277, + "learning_rate": 3.3266411335978618e-06, + "loss": 0.2436, + "step": 561 + }, + { + "epoch": 1.1924198250728864, + "grad_norm": 2.390455722808838, + "learning_rate": 3.3213559547770873e-06, + "loss": 0.272, + "step": 562 + }, + { + "epoch": 1.1945401537238272, + "grad_norm": 0.6653962731361389, + "learning_rate": 3.316066657678577e-06, + "loss": 0.1754, + "step": 563 + }, + { + "epoch": 1.1966604823747682, + "grad_norm": 3.227832555770874, + "learning_rate": 3.310773268822861e-06, + "loss": 0.2089, + "step": 564 + }, + { + "epoch": 1.198780811025709, + "grad_norm": 1.3733195066452026, + "learning_rate": 3.3054758147509837e-06, + "loss": 0.1492, + "step": 565 + }, + { + "epoch": 1.2009011396766498, + "grad_norm": 2.4527945518493652, + "learning_rate": 3.300174322024373e-06, + "loss": 0.1841, + "step": 566 + }, + { + "epoch": 1.2030214683275908, + "grad_norm": 1.4190953969955444, + "learning_rate": 3.294868817224707e-06, + "loss": 0.1904, + "step": 567 + }, + { + "epoch": 1.2051417969785316, + "grad_norm": 1.0891777276992798, + "learning_rate": 3.2895593269537806e-06, + "loss": 0.2079, + "step": 568 + }, + { + "epoch": 1.2072621256294727, + "grad_norm": 3.3715262413024902, + "learning_rate": 3.284245877833371e-06, + "loss": 0.2065, + "step": 569 + }, + { + "epoch": 1.2093824542804135, + "grad_norm": 1.8128390312194824, + "learning_rate": 3.2789284965051053e-06, + "loss": 0.1667, + "step": 570 + }, + { + "epoch": 1.2115027829313543, + "grad_norm": 2.6780452728271484, + "learning_rate": 3.2736072096303277e-06, + "loss": 0.1957, + "step": 571 + }, + { + "epoch": 1.2136231115822953, + "grad_norm": 1.6943888664245605, + "learning_rate": 3.268282043889963e-06, + "loss": 0.1717, + "step": 572 + }, + { + "epoch": 1.215743440233236, + "grad_norm": 2.704658269882202, + "learning_rate": 3.2629530259843862e-06, + "loss": 0.2692, + "step": 573 + }, + { + "epoch": 1.2178637688841771, + "grad_norm": 2.5095183849334717, + "learning_rate": 3.2576201826332864e-06, + "loss": 0.223, + "step": 574 + }, + { + "epoch": 1.219984097535118, + "grad_norm": 0.9887157678604126, + "learning_rate": 3.252283540575533e-06, + "loss": 0.2378, + "step": 575 + }, + { + "epoch": 1.2221044261860587, + "grad_norm": 1.8679485321044922, + "learning_rate": 3.2469431265690432e-06, + "loss": 0.3113, + "step": 576 + }, + { + "epoch": 1.2242247548369998, + "grad_norm": 2.1015641689300537, + "learning_rate": 3.2415989673906454e-06, + "loss": 0.2094, + "step": 577 + }, + { + "epoch": 1.2263450834879406, + "grad_norm": 3.247260808944702, + "learning_rate": 3.2362510898359484e-06, + "loss": 0.286, + "step": 578 + }, + { + "epoch": 1.2284654121388816, + "grad_norm": 2.1203606128692627, + "learning_rate": 3.2308995207192028e-06, + "loss": 0.1752, + "step": 579 + }, + { + "epoch": 1.2305857407898224, + "grad_norm": 3.4415900707244873, + "learning_rate": 3.225544286873169e-06, + "loss": 0.2184, + "step": 580 + }, + { + "epoch": 1.2327060694407632, + "grad_norm": 4.078723430633545, + "learning_rate": 3.220185415148984e-06, + "loss": 0.2721, + "step": 581 + }, + { + "epoch": 1.2348263980917042, + "grad_norm": 2.06363844871521, + "learning_rate": 3.2148229324160235e-06, + "loss": 0.3589, + "step": 582 + }, + { + "epoch": 1.236946726742645, + "grad_norm": 1.6750868558883667, + "learning_rate": 3.2094568655617692e-06, + "loss": 0.2667, + "step": 583 + }, + { + "epoch": 1.239067055393586, + "grad_norm": 2.284876823425293, + "learning_rate": 3.204087241491673e-06, + "loss": 0.2865, + "step": 584 + }, + { + "epoch": 1.2411873840445269, + "grad_norm": 1.0437135696411133, + "learning_rate": 3.198714087129024e-06, + "loss": 0.2693, + "step": 585 + }, + { + "epoch": 1.2433077126954677, + "grad_norm": 1.643754005432129, + "learning_rate": 3.1933374294148112e-06, + "loss": 0.1966, + "step": 586 + }, + { + "epoch": 1.2454280413464087, + "grad_norm": 0.8333995342254639, + "learning_rate": 3.187957295307591e-06, + "loss": 0.1645, + "step": 587 + }, + { + "epoch": 1.2475483699973495, + "grad_norm": 0.7705175280570984, + "learning_rate": 3.1825737117833465e-06, + "loss": 0.2136, + "step": 588 + }, + { + "epoch": 1.2496686986482906, + "grad_norm": 1.509788155555725, + "learning_rate": 3.177186705835361e-06, + "loss": 0.1812, + "step": 589 + }, + { + "epoch": 1.2517890272992314, + "grad_norm": 0.5960215926170349, + "learning_rate": 3.171796304474074e-06, + "loss": 0.1438, + "step": 590 + }, + { + "epoch": 1.2539093559501722, + "grad_norm": 2.9289567470550537, + "learning_rate": 3.1664025347269533e-06, + "loss": 0.224, + "step": 591 + }, + { + "epoch": 1.2560296846011132, + "grad_norm": 1.6071057319641113, + "learning_rate": 3.1610054236383526e-06, + "loss": 0.1427, + "step": 592 + }, + { + "epoch": 1.258150013252054, + "grad_norm": 2.266662359237671, + "learning_rate": 3.1556049982693794e-06, + "loss": 0.3275, + "step": 593 + }, + { + "epoch": 1.260270341902995, + "grad_norm": 0.8570841550827026, + "learning_rate": 3.1502012856977606e-06, + "loss": 0.228, + "step": 594 + }, + { + "epoch": 1.2623906705539358, + "grad_norm": 2.0917248725891113, + "learning_rate": 3.144794313017704e-06, + "loss": 0.1597, + "step": 595 + }, + { + "epoch": 1.2645109992048766, + "grad_norm": 2.6728296279907227, + "learning_rate": 3.1393841073397636e-06, + "loss": 0.2749, + "step": 596 + }, + { + "epoch": 1.2666313278558177, + "grad_norm": 0.8114733695983887, + "learning_rate": 3.1339706957907058e-06, + "loss": 0.2947, + "step": 597 + }, + { + "epoch": 1.2687516565067585, + "grad_norm": 3.9571282863616943, + "learning_rate": 3.128554105513367e-06, + "loss": 0.2116, + "step": 598 + }, + { + "epoch": 1.2708719851576995, + "grad_norm": 1.4085323810577393, + "learning_rate": 3.123134363666525e-06, + "loss": 0.3044, + "step": 599 + }, + { + "epoch": 1.2729923138086403, + "grad_norm": 1.3042069673538208, + "learning_rate": 3.117711497424759e-06, + "loss": 0.2365, + "step": 600 + }, + { + "epoch": 1.2751126424595811, + "grad_norm": 9.497270584106445, + "learning_rate": 3.1122855339783135e-06, + "loss": 0.2351, + "step": 601 + }, + { + "epoch": 1.2772329711105221, + "grad_norm": 2.055746078491211, + "learning_rate": 3.106856500532962e-06, + "loss": 0.2982, + "step": 602 + }, + { + "epoch": 1.279353299761463, + "grad_norm": 1.661730408668518, + "learning_rate": 3.1014244243098723e-06, + "loss": 0.2545, + "step": 603 + }, + { + "epoch": 1.281473628412404, + "grad_norm": 2.3598806858062744, + "learning_rate": 3.0959893325454675e-06, + "loss": 0.2081, + "step": 604 + }, + { + "epoch": 1.2835939570633448, + "grad_norm": 2.3903353214263916, + "learning_rate": 3.09055125249129e-06, + "loss": 0.2386, + "step": 605 + }, + { + "epoch": 1.2857142857142856, + "grad_norm": 2.1055004596710205, + "learning_rate": 3.0851102114138677e-06, + "loss": 0.123, + "step": 606 + }, + { + "epoch": 1.2878346143652266, + "grad_norm": 2.7721481323242188, + "learning_rate": 3.079666236594573e-06, + "loss": 0.2888, + "step": 607 + }, + { + "epoch": 1.2899549430161676, + "grad_norm": 1.0820283889770508, + "learning_rate": 3.0742193553294896e-06, + "loss": 0.4641, + "step": 608 + }, + { + "epoch": 1.2920752716671084, + "grad_norm": 1.0403881072998047, + "learning_rate": 3.0687695949292724e-06, + "loss": 0.1544, + "step": 609 + }, + { + "epoch": 1.2941956003180493, + "grad_norm": 1.1737229824066162, + "learning_rate": 3.063316982719014e-06, + "loss": 0.2008, + "step": 610 + }, + { + "epoch": 1.29631592896899, + "grad_norm": 1.0275263786315918, + "learning_rate": 3.0578615460381047e-06, + "loss": 0.1276, + "step": 611 + }, + { + "epoch": 1.298436257619931, + "grad_norm": 1.435745120048523, + "learning_rate": 3.0524033122400974e-06, + "loss": 0.256, + "step": 612 + }, + { + "epoch": 1.3005565862708721, + "grad_norm": 1.1113966703414917, + "learning_rate": 3.04694230869257e-06, + "loss": 0.2078, + "step": 613 + }, + { + "epoch": 1.302676914921813, + "grad_norm": 0.7453861236572266, + "learning_rate": 3.0414785627769884e-06, + "loss": 0.2638, + "step": 614 + }, + { + "epoch": 1.3047972435727537, + "grad_norm": 2.004967212677002, + "learning_rate": 3.036012101888565e-06, + "loss": 0.1654, + "step": 615 + }, + { + "epoch": 1.3069175722236945, + "grad_norm": 1.6051661968231201, + "learning_rate": 3.0305429534361304e-06, + "loss": 0.1348, + "step": 616 + }, + { + "epoch": 1.3090379008746356, + "grad_norm": 2.3148880004882812, + "learning_rate": 3.0250711448419867e-06, + "loss": 0.1318, + "step": 617 + }, + { + "epoch": 1.3111582295255766, + "grad_norm": 1.5317455530166626, + "learning_rate": 3.0195967035417765e-06, + "loss": 0.2081, + "step": 618 + }, + { + "epoch": 1.3132785581765174, + "grad_norm": 2.321281671524048, + "learning_rate": 3.014119656984341e-06, + "loss": 0.1596, + "step": 619 + }, + { + "epoch": 1.3153988868274582, + "grad_norm": 2.7379441261291504, + "learning_rate": 3.0086400326315853e-06, + "loss": 0.2253, + "step": 620 + }, + { + "epoch": 1.3175192154783992, + "grad_norm": 1.8512643575668335, + "learning_rate": 3.0031578579583375e-06, + "loss": 0.2683, + "step": 621 + }, + { + "epoch": 1.31963954412934, + "grad_norm": 3.2570621967315674, + "learning_rate": 2.9976731604522175e-06, + "loss": 0.1977, + "step": 622 + }, + { + "epoch": 1.321759872780281, + "grad_norm": 1.7534589767456055, + "learning_rate": 2.992185967613489e-06, + "loss": 0.171, + "step": 623 + }, + { + "epoch": 1.3238802014312219, + "grad_norm": 0.5050146579742432, + "learning_rate": 2.9866963069549315e-06, + "loss": 0.2047, + "step": 624 + }, + { + "epoch": 1.3260005300821627, + "grad_norm": 1.552862524986267, + "learning_rate": 2.9812042060016968e-06, + "loss": 0.1553, + "step": 625 + }, + { + "epoch": 1.3281208587331037, + "grad_norm": 1.942893385887146, + "learning_rate": 2.975709692291171e-06, + "loss": 0.1797, + "step": 626 + }, + { + "epoch": 1.3302411873840445, + "grad_norm": 1.2831542491912842, + "learning_rate": 2.9702127933728403e-06, + "loss": 0.16, + "step": 627 + }, + { + "epoch": 1.3323615160349855, + "grad_norm": 1.4484132528305054, + "learning_rate": 2.9647135368081488e-06, + "loss": 0.1923, + "step": 628 + }, + { + "epoch": 1.3344818446859263, + "grad_norm": 3.5186307430267334, + "learning_rate": 2.9592119501703607e-06, + "loss": 0.3373, + "step": 629 + }, + { + "epoch": 1.3366021733368671, + "grad_norm": 1.9385162591934204, + "learning_rate": 2.9537080610444274e-06, + "loss": 0.2003, + "step": 630 + }, + { + "epoch": 1.3387225019878082, + "grad_norm": 1.2267210483551025, + "learning_rate": 2.9482018970268395e-06, + "loss": 0.1736, + "step": 631 + }, + { + "epoch": 1.340842830638749, + "grad_norm": 0.9191475510597229, + "learning_rate": 2.9426934857254975e-06, + "loss": 0.2854, + "step": 632 + }, + { + "epoch": 1.34296315928969, + "grad_norm": 1.7922972440719604, + "learning_rate": 2.9371828547595695e-06, + "loss": 0.1429, + "step": 633 + }, + { + "epoch": 1.3450834879406308, + "grad_norm": 1.5351743698120117, + "learning_rate": 2.9316700317593507e-06, + "loss": 0.1374, + "step": 634 + }, + { + "epoch": 1.3472038165915716, + "grad_norm": 1.2162325382232666, + "learning_rate": 2.92615504436613e-06, + "loss": 0.1429, + "step": 635 + }, + { + "epoch": 1.3493241452425127, + "grad_norm": 1.7114899158477783, + "learning_rate": 2.920637920232047e-06, + "loss": 0.2211, + "step": 636 + }, + { + "epoch": 1.3514444738934535, + "grad_norm": 1.5543713569641113, + "learning_rate": 2.9151186870199556e-06, + "loss": 0.1726, + "step": 637 + }, + { + "epoch": 1.3535648025443945, + "grad_norm": 2.1046950817108154, + "learning_rate": 2.9095973724032832e-06, + "loss": 0.2319, + "step": 638 + }, + { + "epoch": 1.3556851311953353, + "grad_norm": 2.058473587036133, + "learning_rate": 2.9040740040658954e-06, + "loss": 0.2942, + "step": 639 + }, + { + "epoch": 1.357805459846276, + "grad_norm": 1.5705662965774536, + "learning_rate": 2.8985486097019543e-06, + "loss": 0.2206, + "step": 640 + }, + { + "epoch": 1.3599257884972171, + "grad_norm": 2.0310404300689697, + "learning_rate": 2.89302121701578e-06, + "loss": 0.1729, + "step": 641 + }, + { + "epoch": 1.362046117148158, + "grad_norm": 1.455135703086853, + "learning_rate": 2.8874918537217118e-06, + "loss": 0.26, + "step": 642 + }, + { + "epoch": 1.364166445799099, + "grad_norm": 2.1307947635650635, + "learning_rate": 2.8819605475439716e-06, + "loss": 0.1996, + "step": 643 + }, + { + "epoch": 1.3662867744500398, + "grad_norm": 1.6828829050064087, + "learning_rate": 2.876427326216521e-06, + "loss": 0.1706, + "step": 644 + }, + { + "epoch": 1.3684071031009806, + "grad_norm": 2.5645523071289062, + "learning_rate": 2.870892217482925e-06, + "loss": 0.2089, + "step": 645 + }, + { + "epoch": 1.3705274317519216, + "grad_norm": 3.5876777172088623, + "learning_rate": 2.8653552490962122e-06, + "loss": 0.3736, + "step": 646 + }, + { + "epoch": 1.3726477604028624, + "grad_norm": 1.182286262512207, + "learning_rate": 2.8598164488187354e-06, + "loss": 0.2904, + "step": 647 + }, + { + "epoch": 1.3747680890538034, + "grad_norm": 1.9589124917984009, + "learning_rate": 2.8542758444220303e-06, + "loss": 0.2265, + "step": 648 + }, + { + "epoch": 1.3768884177047442, + "grad_norm": 0.8725947737693787, + "learning_rate": 2.848733463686683e-06, + "loss": 0.2266, + "step": 649 + }, + { + "epoch": 1.379008746355685, + "grad_norm": 2.0674960613250732, + "learning_rate": 2.843189334402183e-06, + "loss": 0.1478, + "step": 650 + }, + { + "epoch": 1.381129075006626, + "grad_norm": 0.9025703072547913, + "learning_rate": 2.837643484366787e-06, + "loss": 0.1831, + "step": 651 + }, + { + "epoch": 1.3832494036575669, + "grad_norm": 2.652928352355957, + "learning_rate": 2.83209594138738e-06, + "loss": 0.3069, + "step": 652 + }, + { + "epoch": 1.385369732308508, + "grad_norm": 0.8679104447364807, + "learning_rate": 2.8265467332793358e-06, + "loss": 0.1158, + "step": 653 + }, + { + "epoch": 1.3874900609594487, + "grad_norm": 2.065187692642212, + "learning_rate": 2.820995887866378e-06, + "loss": 0.3263, + "step": 654 + }, + { + "epoch": 1.3896103896103895, + "grad_norm": 1.9065489768981934, + "learning_rate": 2.8154434329804366e-06, + "loss": 0.2294, + "step": 655 + }, + { + "epoch": 1.3917307182613305, + "grad_norm": 2.2654645442962646, + "learning_rate": 2.8098893964615165e-06, + "loss": 0.2063, + "step": 656 + }, + { + "epoch": 1.3938510469122714, + "grad_norm": 1.9993574619293213, + "learning_rate": 2.8043338061575464e-06, + "loss": 0.2116, + "step": 657 + }, + { + "epoch": 1.3959713755632124, + "grad_norm": 1.850152850151062, + "learning_rate": 2.7987766899242513e-06, + "loss": 0.1887, + "step": 658 + }, + { + "epoch": 1.3980917042141532, + "grad_norm": 0.9010924696922302, + "learning_rate": 2.7932180756250042e-06, + "loss": 0.2322, + "step": 659 + }, + { + "epoch": 1.400212032865094, + "grad_norm": 1.3110419511795044, + "learning_rate": 2.787657991130692e-06, + "loss": 0.1766, + "step": 660 + }, + { + "epoch": 1.402332361516035, + "grad_norm": 0.9936445951461792, + "learning_rate": 2.7820964643195685e-06, + "loss": 0.1912, + "step": 661 + }, + { + "epoch": 1.4044526901669758, + "grad_norm": 1.7485136985778809, + "learning_rate": 2.7765335230771255e-06, + "loss": 0.1987, + "step": 662 + }, + { + "epoch": 1.4065730188179169, + "grad_norm": 1.2912129163742065, + "learning_rate": 2.7709691952959406e-06, + "loss": 0.1324, + "step": 663 + }, + { + "epoch": 1.4086933474688577, + "grad_norm": 2.263025999069214, + "learning_rate": 2.765403508875548e-06, + "loss": 0.2485, + "step": 664 + }, + { + "epoch": 1.4108136761197985, + "grad_norm": 1.1566165685653687, + "learning_rate": 2.759836491722292e-06, + "loss": 0.173, + "step": 665 + }, + { + "epoch": 1.4129340047707395, + "grad_norm": 1.7113949060440063, + "learning_rate": 2.75426817174919e-06, + "loss": 0.1933, + "step": 666 + }, + { + "epoch": 1.4150543334216803, + "grad_norm": 2.519707679748535, + "learning_rate": 2.7486985768757905e-06, + "loss": 0.1837, + "step": 667 + }, + { + "epoch": 1.4171746620726213, + "grad_norm": 2.177272319793701, + "learning_rate": 2.743127735028037e-06, + "loss": 0.3647, + "step": 668 + }, + { + "epoch": 1.4192949907235621, + "grad_norm": 2.8958051204681396, + "learning_rate": 2.7375556741381216e-06, + "loss": 0.3015, + "step": 669 + }, + { + "epoch": 1.421415319374503, + "grad_norm": 1.972503662109375, + "learning_rate": 2.731982422144352e-06, + "loss": 0.2581, + "step": 670 + }, + { + "epoch": 1.423535648025444, + "grad_norm": 0.32309406995773315, + "learning_rate": 2.726408006991006e-06, + "loss": 0.2046, + "step": 671 + }, + { + "epoch": 1.4256559766763848, + "grad_norm": 0.9400335550308228, + "learning_rate": 2.7208324566281946e-06, + "loss": 0.2459, + "step": 672 + }, + { + "epoch": 1.4277763053273258, + "grad_norm": 2.608882188796997, + "learning_rate": 2.715255799011721e-06, + "loss": 0.2656, + "step": 673 + }, + { + "epoch": 1.4298966339782666, + "grad_norm": 1.6778721809387207, + "learning_rate": 2.7096780621029386e-06, + "loss": 0.1731, + "step": 674 + }, + { + "epoch": 1.4320169626292074, + "grad_norm": 1.2319176197052002, + "learning_rate": 2.7040992738686135e-06, + "loss": 0.3142, + "step": 675 + }, + { + "epoch": 1.4341372912801484, + "grad_norm": 2.1388039588928223, + "learning_rate": 2.6985194622807835e-06, + "loss": 0.1379, + "step": 676 + }, + { + "epoch": 1.4362576199310892, + "grad_norm": 2.897584915161133, + "learning_rate": 2.6929386553166165e-06, + "loss": 0.2351, + "step": 677 + }, + { + "epoch": 1.4383779485820303, + "grad_norm": 1.4169594049453735, + "learning_rate": 2.687356880958271e-06, + "loss": 0.0984, + "step": 678 + }, + { + "epoch": 1.440498277232971, + "grad_norm": 1.3336187601089478, + "learning_rate": 2.6817741671927587e-06, + "loss": 0.1528, + "step": 679 + }, + { + "epoch": 1.4426186058839119, + "grad_norm": 1.822395920753479, + "learning_rate": 2.676190542011797e-06, + "loss": 0.1678, + "step": 680 + }, + { + "epoch": 1.444738934534853, + "grad_norm": 1.3622679710388184, + "learning_rate": 2.670606033411678e-06, + "loss": 0.17, + "step": 681 + }, + { + "epoch": 1.4468592631857937, + "grad_norm": 2.184080123901367, + "learning_rate": 2.6650206693931184e-06, + "loss": 0.2781, + "step": 682 + }, + { + "epoch": 1.4489795918367347, + "grad_norm": 1.511780858039856, + "learning_rate": 2.659434477961129e-06, + "loss": 0.2947, + "step": 683 + }, + { + "epoch": 1.4510999204876756, + "grad_norm": 1.5842374563217163, + "learning_rate": 2.653847487124865e-06, + "loss": 0.1783, + "step": 684 + }, + { + "epoch": 1.4532202491386164, + "grad_norm": 1.9350712299346924, + "learning_rate": 2.648259724897492e-06, + "loss": 0.2216, + "step": 685 + }, + { + "epoch": 1.4553405777895574, + "grad_norm": 2.5653059482574463, + "learning_rate": 2.6426712192960423e-06, + "loss": 0.2853, + "step": 686 + }, + { + "epoch": 1.4574609064404984, + "grad_norm": 3.479128837585449, + "learning_rate": 2.637081998341277e-06, + "loss": 0.1873, + "step": 687 + }, + { + "epoch": 1.4595812350914392, + "grad_norm": 2.4509148597717285, + "learning_rate": 2.631492090057543e-06, + "loss": 0.2065, + "step": 688 + }, + { + "epoch": 1.46170156374238, + "grad_norm": 1.770412564277649, + "learning_rate": 2.6259015224726325e-06, + "loss": 0.1938, + "step": 689 + }, + { + "epoch": 1.4638218923933208, + "grad_norm": 1.4200644493103027, + "learning_rate": 2.6203103236176446e-06, + "loss": 0.2258, + "step": 690 + }, + { + "epoch": 1.4659422210442619, + "grad_norm": 2.0753350257873535, + "learning_rate": 2.6147185215268446e-06, + "loss": 0.2049, + "step": 691 + }, + { + "epoch": 1.468062549695203, + "grad_norm": 1.6016238927841187, + "learning_rate": 2.609126144237519e-06, + "loss": 0.2649, + "step": 692 + }, + { + "epoch": 1.4701828783461437, + "grad_norm": 1.9330469369888306, + "learning_rate": 2.603533219789844e-06, + "loss": 0.2249, + "step": 693 + }, + { + "epoch": 1.4723032069970845, + "grad_norm": 2.1735124588012695, + "learning_rate": 2.597939776226732e-06, + "loss": 0.2629, + "step": 694 + }, + { + "epoch": 1.4744235356480253, + "grad_norm": 1.841036319732666, + "learning_rate": 2.5923458415937048e-06, + "loss": 0.1787, + "step": 695 + }, + { + "epoch": 1.4765438642989663, + "grad_norm": 2.6332991123199463, + "learning_rate": 2.586751443938742e-06, + "loss": 0.2431, + "step": 696 + }, + { + "epoch": 1.4786641929499074, + "grad_norm": 1.6684833765029907, + "learning_rate": 2.581156611312148e-06, + "loss": 0.2282, + "step": 697 + }, + { + "epoch": 1.4807845216008482, + "grad_norm": 0.7805116772651672, + "learning_rate": 2.5755613717664053e-06, + "loss": 0.1392, + "step": 698 + }, + { + "epoch": 1.482904850251789, + "grad_norm": 0.9408957958221436, + "learning_rate": 2.5699657533560386e-06, + "loss": 0.1325, + "step": 699 + }, + { + "epoch": 1.48502517890273, + "grad_norm": 2.233403444290161, + "learning_rate": 2.5643697841374722e-06, + "loss": 0.2908, + "step": 700 + }, + { + "epoch": 1.4871455075536708, + "grad_norm": 0.5273526310920715, + "learning_rate": 2.5587734921688873e-06, + "loss": 0.1575, + "step": 701 + }, + { + "epoch": 1.4892658362046118, + "grad_norm": 1.2741076946258545, + "learning_rate": 2.553176905510086e-06, + "loss": 0.2134, + "step": 702 + }, + { + "epoch": 1.4913861648555526, + "grad_norm": 1.4551169872283936, + "learning_rate": 2.547580052222347e-06, + "loss": 0.1237, + "step": 703 + }, + { + "epoch": 1.4935064935064934, + "grad_norm": 2.193265914916992, + "learning_rate": 2.5419829603682857e-06, + "loss": 0.2685, + "step": 704 + }, + { + "epoch": 1.4956268221574345, + "grad_norm": 1.1736443042755127, + "learning_rate": 2.5363856580117126e-06, + "loss": 0.1412, + "step": 705 + }, + { + "epoch": 1.4977471508083753, + "grad_norm": 2.0331931114196777, + "learning_rate": 2.5307881732174954e-06, + "loss": 0.3377, + "step": 706 + }, + { + "epoch": 1.4998674794593163, + "grad_norm": 1.456709861755371, + "learning_rate": 2.525190534051416e-06, + "loss": 0.2192, + "step": 707 + }, + { + "epoch": 1.5019878081102571, + "grad_norm": 3.0361955165863037, + "learning_rate": 2.519592768580031e-06, + "loss": 0.2958, + "step": 708 + }, + { + "epoch": 1.504108136761198, + "grad_norm": 1.2546547651290894, + "learning_rate": 2.513994904870528e-06, + "loss": 0.2331, + "step": 709 + }, + { + "epoch": 1.5062284654121387, + "grad_norm": 1.4712584018707275, + "learning_rate": 2.5083969709905904e-06, + "loss": 0.1968, + "step": 710 + }, + { + "epoch": 1.5083487940630798, + "grad_norm": 1.318629264831543, + "learning_rate": 2.502798995008249e-06, + "loss": 0.2898, + "step": 711 + }, + { + "epoch": 1.5104691227140208, + "grad_norm": 3.635026693344116, + "learning_rate": 2.4972010049917513e-06, + "loss": 0.1849, + "step": 712 + }, + { + "epoch": 1.5125894513649616, + "grad_norm": 1.7475965023040771, + "learning_rate": 2.491603029009411e-06, + "loss": 0.1244, + "step": 713 + }, + { + "epoch": 1.5147097800159024, + "grad_norm": 2.1681947708129883, + "learning_rate": 2.4860050951294723e-06, + "loss": 0.186, + "step": 714 + }, + { + "epoch": 1.5168301086668432, + "grad_norm": 1.8500131368637085, + "learning_rate": 2.480407231419969e-06, + "loss": 0.1995, + "step": 715 + }, + { + "epoch": 1.5189504373177842, + "grad_norm": 1.4108548164367676, + "learning_rate": 2.474809465948584e-06, + "loss": 0.1875, + "step": 716 + }, + { + "epoch": 1.5210707659687253, + "grad_norm": 1.5259912014007568, + "learning_rate": 2.469211826782506e-06, + "loss": 0.2135, + "step": 717 + }, + { + "epoch": 1.523191094619666, + "grad_norm": 1.7771860361099243, + "learning_rate": 2.4636143419882887e-06, + "loss": 0.1819, + "step": 718 + }, + { + "epoch": 1.5253114232706069, + "grad_norm": 1.3263814449310303, + "learning_rate": 2.4580170396317156e-06, + "loss": 0.1927, + "step": 719 + }, + { + "epoch": 1.5274317519215477, + "grad_norm": 3.3468446731567383, + "learning_rate": 2.452419947777654e-06, + "loss": 0.1666, + "step": 720 + }, + { + "epoch": 1.5295520805724887, + "grad_norm": 1.9386024475097656, + "learning_rate": 2.4468230944899147e-06, + "loss": 0.2549, + "step": 721 + }, + { + "epoch": 1.5316724092234297, + "grad_norm": 0.590383768081665, + "learning_rate": 2.4412265078311135e-06, + "loss": 0.1705, + "step": 722 + }, + { + "epoch": 1.5337927378743705, + "grad_norm": 1.4284600019454956, + "learning_rate": 2.435630215862529e-06, + "loss": 0.1925, + "step": 723 + }, + { + "epoch": 1.5359130665253113, + "grad_norm": 1.2749354839324951, + "learning_rate": 2.4300342466439623e-06, + "loss": 0.2595, + "step": 724 + }, + { + "epoch": 1.5380333951762524, + "grad_norm": 1.1233924627304077, + "learning_rate": 2.424438628233595e-06, + "loss": 0.2232, + "step": 725 + }, + { + "epoch": 1.5401537238271932, + "grad_norm": 1.092596173286438, + "learning_rate": 2.418843388687853e-06, + "loss": 0.1417, + "step": 726 + }, + { + "epoch": 1.5422740524781342, + "grad_norm": 2.1619231700897217, + "learning_rate": 2.4132485560612583e-06, + "loss": 0.2102, + "step": 727 + }, + { + "epoch": 1.544394381129075, + "grad_norm": 1.9228898286819458, + "learning_rate": 2.4076541584062965e-06, + "loss": 0.1773, + "step": 728 + }, + { + "epoch": 1.5465147097800158, + "grad_norm": 2.4524118900299072, + "learning_rate": 2.402060223773269e-06, + "loss": 0.2415, + "step": 729 + }, + { + "epoch": 1.5486350384309568, + "grad_norm": 1.9279297590255737, + "learning_rate": 2.3964667802101574e-06, + "loss": 0.2973, + "step": 730 + }, + { + "epoch": 1.5507553670818977, + "grad_norm": 1.126503348350525, + "learning_rate": 2.3908738557624812e-06, + "loss": 0.2207, + "step": 731 + }, + { + "epoch": 1.5528756957328387, + "grad_norm": 1.8187668323516846, + "learning_rate": 2.385281478473156e-06, + "loss": 0.2319, + "step": 732 + }, + { + "epoch": 1.5549960243837795, + "grad_norm": 1.953602910041809, + "learning_rate": 2.379689676382356e-06, + "loss": 0.2266, + "step": 733 + }, + { + "epoch": 1.5571163530347203, + "grad_norm": 1.342537522315979, + "learning_rate": 2.3740984775273684e-06, + "loss": 0.1672, + "step": 734 + }, + { + "epoch": 1.5592366816856613, + "grad_norm": 3.2077980041503906, + "learning_rate": 2.368507909942458e-06, + "loss": 0.2455, + "step": 735 + }, + { + "epoch": 1.5613570103366021, + "grad_norm": 1.859153151512146, + "learning_rate": 2.362918001658723e-06, + "loss": 0.1731, + "step": 736 + }, + { + "epoch": 1.5634773389875432, + "grad_norm": 2.042102813720703, + "learning_rate": 2.3573287807039577e-06, + "loss": 0.182, + "step": 737 + }, + { + "epoch": 1.565597667638484, + "grad_norm": 2.096276044845581, + "learning_rate": 2.3517402751025083e-06, + "loss": 0.2215, + "step": 738 + }, + { + "epoch": 1.5677179962894248, + "grad_norm": 0.925915002822876, + "learning_rate": 2.3461525128751364e-06, + "loss": 0.1727, + "step": 739 + }, + { + "epoch": 1.5698383249403658, + "grad_norm": 1.1790268421173096, + "learning_rate": 2.3405655220388718e-06, + "loss": 0.1117, + "step": 740 + }, + { + "epoch": 1.5719586535913066, + "grad_norm": 6.514387607574463, + "learning_rate": 2.334979330606882e-06, + "loss": 0.2172, + "step": 741 + }, + { + "epoch": 1.5740789822422476, + "grad_norm": 2.039428949356079, + "learning_rate": 2.3293939665883233e-06, + "loss": 0.1758, + "step": 742 + }, + { + "epoch": 1.5761993108931884, + "grad_norm": 2.0858302116394043, + "learning_rate": 2.3238094579882037e-06, + "loss": 0.1564, + "step": 743 + }, + { + "epoch": 1.5783196395441292, + "grad_norm": 2.3777787685394287, + "learning_rate": 2.318225832807242e-06, + "loss": 0.2507, + "step": 744 + }, + { + "epoch": 1.5804399681950703, + "grad_norm": 1.0911935567855835, + "learning_rate": 2.3126431190417294e-06, + "loss": 0.2025, + "step": 745 + }, + { + "epoch": 1.5825602968460113, + "grad_norm": 1.207847237586975, + "learning_rate": 2.3070613446833843e-06, + "loss": 0.2627, + "step": 746 + }, + { + "epoch": 1.584680625496952, + "grad_norm": 1.059277892112732, + "learning_rate": 2.3014805377192173e-06, + "loss": 0.1475, + "step": 747 + }, + { + "epoch": 1.586800954147893, + "grad_norm": 1.6303125619888306, + "learning_rate": 2.2959007261313865e-06, + "loss": 0.1478, + "step": 748 + }, + { + "epoch": 1.5889212827988337, + "grad_norm": 0.9721236824989319, + "learning_rate": 2.2903219378970623e-06, + "loss": 0.169, + "step": 749 + }, + { + "epoch": 1.5910416114497747, + "grad_norm": 2.5028750896453857, + "learning_rate": 2.2847442009882805e-06, + "loss": 0.2719, + "step": 750 + }, + { + "epoch": 1.5931619401007158, + "grad_norm": 1.3091676235198975, + "learning_rate": 2.2791675433718058e-06, + "loss": 0.1815, + "step": 751 + }, + { + "epoch": 1.5952822687516566, + "grad_norm": 1.014621615409851, + "learning_rate": 2.273591993008995e-06, + "loss": 0.1354, + "step": 752 + }, + { + "epoch": 1.5974025974025974, + "grad_norm": 1.3206697702407837, + "learning_rate": 2.268017577855649e-06, + "loss": 0.2361, + "step": 753 + }, + { + "epoch": 1.5995229260535382, + "grad_norm": 1.9211969375610352, + "learning_rate": 2.262444325861879e-06, + "loss": 0.2273, + "step": 754 + }, + { + "epoch": 1.6016432547044792, + "grad_norm": 0.9052472710609436, + "learning_rate": 2.2568722649719637e-06, + "loss": 0.1695, + "step": 755 + }, + { + "epoch": 1.6037635833554202, + "grad_norm": 0.7492967844009399, + "learning_rate": 2.25130142312421e-06, + "loss": 0.2105, + "step": 756 + }, + { + "epoch": 1.605883912006361, + "grad_norm": 1.8103669881820679, + "learning_rate": 2.2457318282508105e-06, + "loss": 0.2822, + "step": 757 + }, + { + "epoch": 1.6080042406573019, + "grad_norm": 1.9676963090896606, + "learning_rate": 2.2401635082777086e-06, + "loss": 0.2802, + "step": 758 + }, + { + "epoch": 1.6101245693082427, + "grad_norm": 1.3851075172424316, + "learning_rate": 2.234596491124452e-06, + "loss": 0.1117, + "step": 759 + }, + { + "epoch": 1.6122448979591837, + "grad_norm": 0.9123232960700989, + "learning_rate": 2.2290308047040607e-06, + "loss": 0.2573, + "step": 760 + }, + { + "epoch": 1.6143652266101247, + "grad_norm": 1.3736172914505005, + "learning_rate": 2.2234664769228758e-06, + "loss": 0.1806, + "step": 761 + }, + { + "epoch": 1.6164855552610655, + "grad_norm": 0.8288306593894958, + "learning_rate": 2.217903535680432e-06, + "loss": 0.1327, + "step": 762 + }, + { + "epoch": 1.6186058839120063, + "grad_norm": 0.9833022952079773, + "learning_rate": 2.212342008869309e-06, + "loss": 0.1819, + "step": 763 + }, + { + "epoch": 1.6207262125629471, + "grad_norm": 1.44596266746521, + "learning_rate": 2.206781924374996e-06, + "loss": 0.1626, + "step": 764 + }, + { + "epoch": 1.6228465412138882, + "grad_norm": 2.6636288166046143, + "learning_rate": 2.201223310075749e-06, + "loss": 0.2006, + "step": 765 + }, + { + "epoch": 1.6249668698648292, + "grad_norm": 1.4887255430221558, + "learning_rate": 2.1956661938424544e-06, + "loss": 0.1135, + "step": 766 + }, + { + "epoch": 1.62708719851577, + "grad_norm": 2.366757392883301, + "learning_rate": 2.1901106035384843e-06, + "loss": 0.2926, + "step": 767 + }, + { + "epoch": 1.6292075271667108, + "grad_norm": 1.6054885387420654, + "learning_rate": 2.1845565670195634e-06, + "loss": 0.2127, + "step": 768 + }, + { + "epoch": 1.6313278558176516, + "grad_norm": 1.424625277519226, + "learning_rate": 2.1790041121336223e-06, + "loss": 0.256, + "step": 769 + }, + { + "epoch": 1.6334481844685926, + "grad_norm": 1.324894905090332, + "learning_rate": 2.173453266720665e-06, + "loss": 0.2511, + "step": 770 + }, + { + "epoch": 1.6355685131195337, + "grad_norm": 1.541780710220337, + "learning_rate": 2.1679040586126214e-06, + "loss": 0.1786, + "step": 771 + }, + { + "epoch": 1.6376888417704745, + "grad_norm": 1.0855908393859863, + "learning_rate": 2.1623565156332145e-06, + "loss": 0.2015, + "step": 772 + }, + { + "epoch": 1.6398091704214153, + "grad_norm": 1.2004632949829102, + "learning_rate": 2.1568106655978184e-06, + "loss": 0.1488, + "step": 773 + }, + { + "epoch": 1.641929499072356, + "grad_norm": 2.120727300643921, + "learning_rate": 2.1512665363133173e-06, + "loss": 0.3628, + "step": 774 + }, + { + "epoch": 1.644049827723297, + "grad_norm": 1.992598056793213, + "learning_rate": 2.14572415557797e-06, + "loss": 0.2429, + "step": 775 + }, + { + "epoch": 1.6461701563742381, + "grad_norm": 1.2479114532470703, + "learning_rate": 2.140183551181266e-06, + "loss": 0.1817, + "step": 776 + }, + { + "epoch": 1.648290485025179, + "grad_norm": 1.3581926822662354, + "learning_rate": 2.1346447509037886e-06, + "loss": 0.1804, + "step": 777 + }, + { + "epoch": 1.6504108136761197, + "grad_norm": 1.578666090965271, + "learning_rate": 2.1291077825170756e-06, + "loss": 0.1714, + "step": 778 + }, + { + "epoch": 1.6525311423270606, + "grad_norm": 1.6858261823654175, + "learning_rate": 2.1235726737834794e-06, + "loss": 0.2376, + "step": 779 + }, + { + "epoch": 1.6546514709780016, + "grad_norm": 1.8544155359268188, + "learning_rate": 2.118039452456029e-06, + "loss": 0.1878, + "step": 780 + }, + { + "epoch": 1.6567717996289426, + "grad_norm": 1.179569959640503, + "learning_rate": 2.112508146278289e-06, + "loss": 0.2489, + "step": 781 + }, + { + "epoch": 1.6588921282798834, + "grad_norm": 1.2655270099639893, + "learning_rate": 2.106978782984221e-06, + "loss": 0.1492, + "step": 782 + }, + { + "epoch": 1.6610124569308242, + "grad_norm": 0.9758352041244507, + "learning_rate": 2.101451390298047e-06, + "loss": 0.1525, + "step": 783 + }, + { + "epoch": 1.663132785581765, + "grad_norm": 1.285880208015442, + "learning_rate": 2.095925995934105e-06, + "loss": 0.2749, + "step": 784 + }, + { + "epoch": 1.665253114232706, + "grad_norm": 0.683684766292572, + "learning_rate": 2.0904026275967176e-06, + "loss": 0.1183, + "step": 785 + }, + { + "epoch": 1.667373442883647, + "grad_norm": 1.4306302070617676, + "learning_rate": 2.084881312980045e-06, + "loss": 0.1484, + "step": 786 + }, + { + "epoch": 1.669493771534588, + "grad_norm": 1.3516453504562378, + "learning_rate": 2.0793620797679537e-06, + "loss": 0.2783, + "step": 787 + }, + { + "epoch": 1.6716141001855287, + "grad_norm": 1.849977731704712, + "learning_rate": 2.0738449556338704e-06, + "loss": 0.2064, + "step": 788 + }, + { + "epoch": 1.6737344288364695, + "grad_norm": 2.6501619815826416, + "learning_rate": 2.0683299682406497e-06, + "loss": 0.1742, + "step": 789 + }, + { + "epoch": 1.6758547574874105, + "grad_norm": 1.9885671138763428, + "learning_rate": 2.062817145240431e-06, + "loss": 0.2273, + "step": 790 + }, + { + "epoch": 1.6779750861383516, + "grad_norm": 1.9040833711624146, + "learning_rate": 2.057306514274503e-06, + "loss": 0.2515, + "step": 791 + }, + { + "epoch": 1.6800954147892924, + "grad_norm": 1.9295481443405151, + "learning_rate": 2.0517981029731613e-06, + "loss": 0.2791, + "step": 792 + }, + { + "epoch": 1.6822157434402332, + "grad_norm": 1.2951781749725342, + "learning_rate": 2.0462919389555734e-06, + "loss": 0.1838, + "step": 793 + }, + { + "epoch": 1.684336072091174, + "grad_norm": 1.2169189453125, + "learning_rate": 2.0407880498296397e-06, + "loss": 0.188, + "step": 794 + }, + { + "epoch": 1.686456400742115, + "grad_norm": 1.4646093845367432, + "learning_rate": 2.035286463191852e-06, + "loss": 0.2529, + "step": 795 + }, + { + "epoch": 1.688576729393056, + "grad_norm": 1.2175997495651245, + "learning_rate": 2.0297872066271606e-06, + "loss": 0.1882, + "step": 796 + }, + { + "epoch": 1.6906970580439968, + "grad_norm": 1.482407808303833, + "learning_rate": 2.02429030770883e-06, + "loss": 0.2542, + "step": 797 + }, + { + "epoch": 1.6928173866949376, + "grad_norm": 1.4033699035644531, + "learning_rate": 2.0187957939983045e-06, + "loss": 0.2018, + "step": 798 + }, + { + "epoch": 1.6949377153458784, + "grad_norm": 2.2561542987823486, + "learning_rate": 2.0133036930450694e-06, + "loss": 0.1885, + "step": 799 + }, + { + "epoch": 1.6970580439968195, + "grad_norm": 1.9615060091018677, + "learning_rate": 2.0078140323865114e-06, + "loss": 0.1909, + "step": 800 + }, + { + "epoch": 1.6991783726477605, + "grad_norm": 1.5575997829437256, + "learning_rate": 2.0023268395477833e-06, + "loss": 0.1939, + "step": 801 + }, + { + "epoch": 1.7012987012987013, + "grad_norm": 1.2603005170822144, + "learning_rate": 1.9968421420416633e-06, + "loss": 0.2151, + "step": 802 + }, + { + "epoch": 1.7034190299496421, + "grad_norm": 1.56342613697052, + "learning_rate": 1.991359967368416e-06, + "loss": 0.2121, + "step": 803 + }, + { + "epoch": 1.7055393586005831, + "grad_norm": 0.8418555855751038, + "learning_rate": 1.9858803430156602e-06, + "loss": 0.1356, + "step": 804 + }, + { + "epoch": 1.707659687251524, + "grad_norm": 2.612060308456421, + "learning_rate": 1.9804032964582243e-06, + "loss": 0.1723, + "step": 805 + }, + { + "epoch": 1.709780015902465, + "grad_norm": 1.789333462715149, + "learning_rate": 1.974928855158014e-06, + "loss": 0.2443, + "step": 806 + }, + { + "epoch": 1.7119003445534058, + "grad_norm": 2.306417226791382, + "learning_rate": 1.96945704656387e-06, + "loss": 0.1573, + "step": 807 + }, + { + "epoch": 1.7140206732043466, + "grad_norm": 1.3851442337036133, + "learning_rate": 1.9639878981114358e-06, + "loss": 0.2239, + "step": 808 + }, + { + "epoch": 1.7161410018552876, + "grad_norm": 1.9788298606872559, + "learning_rate": 1.958521437223013e-06, + "loss": 0.1589, + "step": 809 + }, + { + "epoch": 1.7182613305062284, + "grad_norm": 1.2567238807678223, + "learning_rate": 1.95305769130743e-06, + "loss": 0.1738, + "step": 810 + }, + { + "epoch": 1.7203816591571695, + "grad_norm": 1.2289453744888306, + "learning_rate": 1.947596687759902e-06, + "loss": 0.1698, + "step": 811 + }, + { + "epoch": 1.7225019878081103, + "grad_norm": 1.1884444952011108, + "learning_rate": 1.9421384539618957e-06, + "loss": 0.1406, + "step": 812 + }, + { + "epoch": 1.724622316459051, + "grad_norm": 2.408679485321045, + "learning_rate": 1.9366830172809877e-06, + "loss": 0.214, + "step": 813 + }, + { + "epoch": 1.726742645109992, + "grad_norm": 1.555776596069336, + "learning_rate": 1.9312304050707293e-06, + "loss": 0.1675, + "step": 814 + }, + { + "epoch": 1.728862973760933, + "grad_norm": 1.8956245183944702, + "learning_rate": 1.9257806446705116e-06, + "loss": 0.1727, + "step": 815 + }, + { + "epoch": 1.730983302411874, + "grad_norm": 2.6797003746032715, + "learning_rate": 1.920333763405428e-06, + "loss": 0.2671, + "step": 816 + }, + { + "epoch": 1.7331036310628147, + "grad_norm": 5.029034614562988, + "learning_rate": 1.914889788586133e-06, + "loss": 0.1879, + "step": 817 + }, + { + "epoch": 1.7352239597137555, + "grad_norm": 1.3859666585922241, + "learning_rate": 1.909448747508711e-06, + "loss": 0.2305, + "step": 818 + }, + { + "epoch": 1.7373442883646966, + "grad_norm": 1.9923025369644165, + "learning_rate": 1.9040106674545333e-06, + "loss": 0.3013, + "step": 819 + }, + { + "epoch": 1.7394646170156374, + "grad_norm": 2.2539119720458984, + "learning_rate": 1.898575575690128e-06, + "loss": 0.145, + "step": 820 + }, + { + "epoch": 1.7415849456665784, + "grad_norm": 1.2624527215957642, + "learning_rate": 1.8931434994670377e-06, + "loss": 0.2027, + "step": 821 + }, + { + "epoch": 1.7437052743175192, + "grad_norm": 1.10843825340271, + "learning_rate": 1.8877144660216867e-06, + "loss": 0.1941, + "step": 822 + }, + { + "epoch": 1.74582560296846, + "grad_norm": 1.4225454330444336, + "learning_rate": 1.8822885025752408e-06, + "loss": 0.2453, + "step": 823 + }, + { + "epoch": 1.747945931619401, + "grad_norm": 0.7526883482933044, + "learning_rate": 1.8768656363334759e-06, + "loss": 0.1622, + "step": 824 + }, + { + "epoch": 1.750066260270342, + "grad_norm": 0.6890954375267029, + "learning_rate": 1.8714458944866342e-06, + "loss": 0.1394, + "step": 825 + }, + { + "epoch": 1.7521865889212829, + "grad_norm": 1.9675222635269165, + "learning_rate": 1.8660293042092953e-06, + "loss": 0.165, + "step": 826 + }, + { + "epoch": 1.7543069175722237, + "grad_norm": 1.5908443927764893, + "learning_rate": 1.8606158926602368e-06, + "loss": 0.1421, + "step": 827 + }, + { + "epoch": 1.7564272462231645, + "grad_norm": 2.1363799571990967, + "learning_rate": 1.8552056869822968e-06, + "loss": 0.2401, + "step": 828 + }, + { + "epoch": 1.7585475748741055, + "grad_norm": 1.3258087635040283, + "learning_rate": 1.8497987143022405e-06, + "loss": 0.2401, + "step": 829 + }, + { + "epoch": 1.7606679035250465, + "grad_norm": 2.014814615249634, + "learning_rate": 1.8443950017306214e-06, + "loss": 0.2251, + "step": 830 + }, + { + "epoch": 1.7627882321759873, + "grad_norm": 0.8224743604660034, + "learning_rate": 1.8389945763616485e-06, + "loss": 0.113, + "step": 831 + }, + { + "epoch": 1.7649085608269282, + "grad_norm": 1.5032809972763062, + "learning_rate": 1.8335974652730467e-06, + "loss": 0.2415, + "step": 832 + }, + { + "epoch": 1.767028889477869, + "grad_norm": 2.1641783714294434, + "learning_rate": 1.8282036955259258e-06, + "loss": 0.2079, + "step": 833 + }, + { + "epoch": 1.76914921812881, + "grad_norm": 1.787461519241333, + "learning_rate": 1.8228132941646404e-06, + "loss": 0.2262, + "step": 834 + }, + { + "epoch": 1.771269546779751, + "grad_norm": 0.7867398858070374, + "learning_rate": 1.817426288216655e-06, + "loss": 0.2094, + "step": 835 + }, + { + "epoch": 1.7733898754306918, + "grad_norm": 1.3670313358306885, + "learning_rate": 1.8120427046924106e-06, + "loss": 0.1674, + "step": 836 + }, + { + "epoch": 1.7755102040816326, + "grad_norm": 1.9899623394012451, + "learning_rate": 1.8066625705851896e-06, + "loss": 0.255, + "step": 837 + }, + { + "epoch": 1.7776305327325734, + "grad_norm": 1.7844711542129517, + "learning_rate": 1.8012859128709766e-06, + "loss": 0.1705, + "step": 838 + }, + { + "epoch": 1.7797508613835145, + "grad_norm": 2.2082679271698, + "learning_rate": 1.7959127585083281e-06, + "loss": 0.3657, + "step": 839 + }, + { + "epoch": 1.7818711900344555, + "grad_norm": 3.0161192417144775, + "learning_rate": 1.7905431344382318e-06, + "loss": 0.1641, + "step": 840 + }, + { + "epoch": 1.7839915186853963, + "grad_norm": 2.1656365394592285, + "learning_rate": 1.7851770675839771e-06, + "loss": 0.2821, + "step": 841 + }, + { + "epoch": 1.786111847336337, + "grad_norm": 1.0514625310897827, + "learning_rate": 1.7798145848510162e-06, + "loss": 0.18, + "step": 842 + }, + { + "epoch": 1.788232175987278, + "grad_norm": 1.528306245803833, + "learning_rate": 1.7744557131268312e-06, + "loss": 0.2798, + "step": 843 + }, + { + "epoch": 1.790352504638219, + "grad_norm": 1.0451114177703857, + "learning_rate": 1.7691004792807976e-06, + "loss": 0.2194, + "step": 844 + }, + { + "epoch": 1.79247283328916, + "grad_norm": 1.3756572008132935, + "learning_rate": 1.7637489101640526e-06, + "loss": 0.1493, + "step": 845 + }, + { + "epoch": 1.7945931619401008, + "grad_norm": 2.324673652648926, + "learning_rate": 1.7584010326093554e-06, + "loss": 0.1907, + "step": 846 + }, + { + "epoch": 1.7967134905910416, + "grad_norm": 1.8477604389190674, + "learning_rate": 1.7530568734309578e-06, + "loss": 0.1661, + "step": 847 + }, + { + "epoch": 1.7988338192419824, + "grad_norm": 1.0166375637054443, + "learning_rate": 1.747716459424468e-06, + "loss": 0.1454, + "step": 848 + }, + { + "epoch": 1.8009541478929234, + "grad_norm": 1.7437880039215088, + "learning_rate": 1.7423798173667144e-06, + "loss": 0.1912, + "step": 849 + }, + { + "epoch": 1.8030744765438644, + "grad_norm": 0.8157974481582642, + "learning_rate": 1.7370469740156146e-06, + "loss": 0.1125, + "step": 850 + }, + { + "epoch": 1.8051948051948052, + "grad_norm": 1.758787989616394, + "learning_rate": 1.7317179561100372e-06, + "loss": 0.2471, + "step": 851 + }, + { + "epoch": 1.807315133845746, + "grad_norm": 1.253186821937561, + "learning_rate": 1.726392790369673e-06, + "loss": 0.1341, + "step": 852 + }, + { + "epoch": 1.8094354624966869, + "grad_norm": 0.8312148451805115, + "learning_rate": 1.7210715034948949e-06, + "loss": 0.1579, + "step": 853 + }, + { + "epoch": 1.8115557911476279, + "grad_norm": 0.9796281456947327, + "learning_rate": 1.7157541221666291e-06, + "loss": 0.0722, + "step": 854 + }, + { + "epoch": 1.813676119798569, + "grad_norm": 1.192187786102295, + "learning_rate": 1.7104406730462203e-06, + "loss": 0.1729, + "step": 855 + }, + { + "epoch": 1.8157964484495097, + "grad_norm": 1.2145785093307495, + "learning_rate": 1.705131182775294e-06, + "loss": 0.1131, + "step": 856 + }, + { + "epoch": 1.8179167771004505, + "grad_norm": 1.1818413734436035, + "learning_rate": 1.6998256779756279e-06, + "loss": 0.1515, + "step": 857 + }, + { + "epoch": 1.8200371057513913, + "grad_norm": 1.1990983486175537, + "learning_rate": 1.6945241852490173e-06, + "loss": 0.2163, + "step": 858 + }, + { + "epoch": 1.8221574344023324, + "grad_norm": 3.079540491104126, + "learning_rate": 1.6892267311771395e-06, + "loss": 0.1602, + "step": 859 + }, + { + "epoch": 1.8242777630532734, + "grad_norm": 1.5485817193984985, + "learning_rate": 1.6839333423214235e-06, + "loss": 0.2203, + "step": 860 + }, + { + "epoch": 1.8263980917042142, + "grad_norm": 2.226602554321289, + "learning_rate": 1.6786440452229134e-06, + "loss": 0.2015, + "step": 861 + }, + { + "epoch": 1.828518420355155, + "grad_norm": 1.1683058738708496, + "learning_rate": 1.673358866402139e-06, + "loss": 0.2026, + "step": 862 + }, + { + "epoch": 1.8306387490060958, + "grad_norm": 1.8131059408187866, + "learning_rate": 1.6680778323589798e-06, + "loss": 0.1659, + "step": 863 + }, + { + "epoch": 1.8327590776570368, + "grad_norm": 1.0971344709396362, + "learning_rate": 1.6628009695725348e-06, + "loss": 0.128, + "step": 864 + }, + { + "epoch": 1.8348794063079779, + "grad_norm": 2.1698126792907715, + "learning_rate": 1.657528304500986e-06, + "loss": 0.2637, + "step": 865 + }, + { + "epoch": 1.8369997349589187, + "grad_norm": 1.535143494606018, + "learning_rate": 1.6522598635814718e-06, + "loss": 0.1259, + "step": 866 + }, + { + "epoch": 1.8391200636098595, + "grad_norm": 1.4739115238189697, + "learning_rate": 1.6469956732299463e-06, + "loss": 0.2048, + "step": 867 + }, + { + "epoch": 1.8412403922608003, + "grad_norm": 0.9692105054855347, + "learning_rate": 1.6417357598410539e-06, + "loss": 0.1192, + "step": 868 + }, + { + "epoch": 1.8433607209117413, + "grad_norm": 1.028839349746704, + "learning_rate": 1.636480149787994e-06, + "loss": 0.1157, + "step": 869 + }, + { + "epoch": 1.8454810495626823, + "grad_norm": 1.9451359510421753, + "learning_rate": 1.6312288694223882e-06, + "loss": 0.1635, + "step": 870 + }, + { + "epoch": 1.8476013782136231, + "grad_norm": 1.6668827533721924, + "learning_rate": 1.6259819450741512e-06, + "loss": 0.234, + "step": 871 + }, + { + "epoch": 1.849721706864564, + "grad_norm": 0.971024751663208, + "learning_rate": 1.620739403051354e-06, + "loss": 0.1229, + "step": 872 + }, + { + "epoch": 1.8518420355155047, + "grad_norm": 2.122507095336914, + "learning_rate": 1.6155012696400959e-06, + "loss": 0.2016, + "step": 873 + }, + { + "epoch": 1.8539623641664458, + "grad_norm": 2.7607994079589844, + "learning_rate": 1.6102675711043719e-06, + "loss": 0.2195, + "step": 874 + }, + { + "epoch": 1.8560826928173868, + "grad_norm": 1.627505898475647, + "learning_rate": 1.6050383336859388e-06, + "loss": 0.2128, + "step": 875 + }, + { + "epoch": 1.8582030214683276, + "grad_norm": 2.6249325275421143, + "learning_rate": 1.599813583604188e-06, + "loss": 0.2381, + "step": 876 + }, + { + "epoch": 1.8603233501192684, + "grad_norm": 1.4043858051300049, + "learning_rate": 1.5945933470560097e-06, + "loss": 0.158, + "step": 877 + }, + { + "epoch": 1.8624436787702092, + "grad_norm": 2.1411776542663574, + "learning_rate": 1.5893776502156616e-06, + "loss": 0.1924, + "step": 878 + }, + { + "epoch": 1.8645640074211502, + "grad_norm": 0.7305095195770264, + "learning_rate": 1.5841665192346432e-06, + "loss": 0.201, + "step": 879 + }, + { + "epoch": 1.8666843360720913, + "grad_norm": 3.2844574451446533, + "learning_rate": 1.5789599802415572e-06, + "loss": 0.234, + "step": 880 + }, + { + "epoch": 1.868804664723032, + "grad_norm": 1.5105334520339966, + "learning_rate": 1.5737580593419854e-06, + "loss": 0.1891, + "step": 881 + }, + { + "epoch": 1.8709249933739729, + "grad_norm": 3.2038848400115967, + "learning_rate": 1.5685607826183514e-06, + "loss": 0.1912, + "step": 882 + }, + { + "epoch": 1.873045322024914, + "grad_norm": 1.120902180671692, + "learning_rate": 1.5633681761297948e-06, + "loss": 0.1075, + "step": 883 + }, + { + "epoch": 1.8751656506758547, + "grad_norm": 2.2855780124664307, + "learning_rate": 1.558180265912037e-06, + "loss": 0.1945, + "step": 884 + }, + { + "epoch": 1.8772859793267958, + "grad_norm": 1.1479313373565674, + "learning_rate": 1.5529970779772552e-06, + "loss": 0.1465, + "step": 885 + }, + { + "epoch": 1.8794063079777366, + "grad_norm": 1.4228770732879639, + "learning_rate": 1.5478186383139459e-06, + "loss": 0.2768, + "step": 886 + }, + { + "epoch": 1.8815266366286774, + "grad_norm": 1.2616146802902222, + "learning_rate": 1.5426449728868004e-06, + "loss": 0.2076, + "step": 887 + }, + { + "epoch": 1.8836469652796184, + "grad_norm": 2.149235248565674, + "learning_rate": 1.5374761076365695e-06, + "loss": 0.2828, + "step": 888 + }, + { + "epoch": 1.8857672939305592, + "grad_norm": 1.1656577587127686, + "learning_rate": 1.5323120684799374e-06, + "loss": 0.2031, + "step": 889 + }, + { + "epoch": 1.8878876225815002, + "grad_norm": 1.62466299533844, + "learning_rate": 1.5271528813093896e-06, + "loss": 0.2678, + "step": 890 + }, + { + "epoch": 1.890007951232441, + "grad_norm": 0.9776110053062439, + "learning_rate": 1.5219985719930851e-06, + "loss": 0.221, + "step": 891 + }, + { + "epoch": 1.8921282798833818, + "grad_norm": 0.5721087455749512, + "learning_rate": 1.5168491663747236e-06, + "loss": 0.1595, + "step": 892 + }, + { + "epoch": 1.8942486085343229, + "grad_norm": 1.2385927438735962, + "learning_rate": 1.5117046902734194e-06, + "loss": 0.2665, + "step": 893 + }, + { + "epoch": 1.8963689371852637, + "grad_norm": 1.5480061769485474, + "learning_rate": 1.5065651694835682e-06, + "loss": 0.1806, + "step": 894 + }, + { + "epoch": 1.8984892658362047, + "grad_norm": 1.9919331073760986, + "learning_rate": 1.5014306297747217e-06, + "loss": 0.2988, + "step": 895 + }, + { + "epoch": 1.9006095944871455, + "grad_norm": 0.4841969311237335, + "learning_rate": 1.4963010968914549e-06, + "loss": 0.1248, + "step": 896 + }, + { + "epoch": 1.9027299231380863, + "grad_norm": 2.00504994392395, + "learning_rate": 1.4911765965532398e-06, + "loss": 0.3798, + "step": 897 + }, + { + "epoch": 1.9048502517890273, + "grad_norm": 0.846325695514679, + "learning_rate": 1.4860571544543157e-06, + "loss": 0.2455, + "step": 898 + }, + { + "epoch": 1.9069705804399681, + "grad_norm": 1.6753747463226318, + "learning_rate": 1.480942796263556e-06, + "loss": 0.1762, + "step": 899 + }, + { + "epoch": 1.9090909090909092, + "grad_norm": 1.3008391857147217, + "learning_rate": 1.475833547624349e-06, + "loss": 0.3043, + "step": 900 + }, + { + "epoch": 1.91121123774185, + "grad_norm": 0.8818872570991516, + "learning_rate": 1.4707294341544598e-06, + "loss": 0.1608, + "step": 901 + }, + { + "epoch": 1.9133315663927908, + "grad_norm": 0.6332581639289856, + "learning_rate": 1.4656304814459077e-06, + "loss": 0.1494, + "step": 902 + }, + { + "epoch": 1.9154518950437318, + "grad_norm": 1.6962636709213257, + "learning_rate": 1.4605367150648341e-06, + "loss": 0.1819, + "step": 903 + }, + { + "epoch": 1.9175722236946728, + "grad_norm": 0.4807201623916626, + "learning_rate": 1.455448160551378e-06, + "loss": 0.1381, + "step": 904 + }, + { + "epoch": 1.9196925523456136, + "grad_norm": 1.2451565265655518, + "learning_rate": 1.4503648434195466e-06, + "loss": 0.1973, + "step": 905 + }, + { + "epoch": 1.9218128809965545, + "grad_norm": 1.3982090950012207, + "learning_rate": 1.445286789157084e-06, + "loss": 0.2893, + "step": 906 + }, + { + "epoch": 1.9239332096474953, + "grad_norm": 1.4739251136779785, + "learning_rate": 1.4402140232253486e-06, + "loss": 0.1968, + "step": 907 + }, + { + "epoch": 1.9260535382984363, + "grad_norm": 2.5440287590026855, + "learning_rate": 1.435146571059181e-06, + "loss": 0.1978, + "step": 908 + }, + { + "epoch": 1.9281738669493773, + "grad_norm": 3.4602210521698, + "learning_rate": 1.430084458066784e-06, + "loss": 0.2572, + "step": 909 + }, + { + "epoch": 1.9302941956003181, + "grad_norm": 0.7656342387199402, + "learning_rate": 1.4250277096295817e-06, + "loss": 0.1473, + "step": 910 + }, + { + "epoch": 1.932414524251259, + "grad_norm": 4.068082332611084, + "learning_rate": 1.4199763511021065e-06, + "loss": 0.2889, + "step": 911 + }, + { + "epoch": 1.9345348529021997, + "grad_norm": 0.7085794806480408, + "learning_rate": 1.4149304078118619e-06, + "loss": 0.1495, + "step": 912 + }, + { + "epoch": 1.9366551815531408, + "grad_norm": 0.3622530996799469, + "learning_rate": 1.4098899050592037e-06, + "loss": 0.1174, + "step": 913 + }, + { + "epoch": 1.9387755102040818, + "grad_norm": 1.3513684272766113, + "learning_rate": 1.404854868117206e-06, + "loss": 0.1357, + "step": 914 + }, + { + "epoch": 1.9408958388550226, + "grad_norm": 1.4065253734588623, + "learning_rate": 1.3998253222315363e-06, + "loss": 0.1929, + "step": 915 + }, + { + "epoch": 1.9430161675059634, + "grad_norm": 1.104533076286316, + "learning_rate": 1.394801292620332e-06, + "loss": 0.2133, + "step": 916 + }, + { + "epoch": 1.9451364961569042, + "grad_norm": 1.756828784942627, + "learning_rate": 1.389782804474072e-06, + "loss": 0.2032, + "step": 917 + }, + { + "epoch": 1.9472568248078452, + "grad_norm": 1.4066181182861328, + "learning_rate": 1.3847698829554496e-06, + "loss": 0.1907, + "step": 918 + }, + { + "epoch": 1.9493771534587863, + "grad_norm": 2.111950397491455, + "learning_rate": 1.3797625531992464e-06, + "loss": 0.2204, + "step": 919 + }, + { + "epoch": 1.951497482109727, + "grad_norm": 1.4993287324905396, + "learning_rate": 1.374760840312208e-06, + "loss": 0.2518, + "step": 920 + }, + { + "epoch": 1.9536178107606679, + "grad_norm": 0.8992859125137329, + "learning_rate": 1.3697647693729166e-06, + "loss": 0.1671, + "step": 921 + }, + { + "epoch": 1.9557381394116087, + "grad_norm": 0.6463199853897095, + "learning_rate": 1.3647743654316653e-06, + "loss": 0.1723, + "step": 922 + }, + { + "epoch": 1.9578584680625497, + "grad_norm": 0.7732374668121338, + "learning_rate": 1.3597896535103328e-06, + "loss": 0.1485, + "step": 923 + }, + { + "epoch": 1.9599787967134907, + "grad_norm": 1.8219809532165527, + "learning_rate": 1.3548106586022597e-06, + "loss": 0.1481, + "step": 924 + }, + { + "epoch": 1.9620991253644315, + "grad_norm": 2.0674850940704346, + "learning_rate": 1.3498374056721198e-06, + "loss": 0.2583, + "step": 925 + }, + { + "epoch": 1.9642194540153723, + "grad_norm": 2.160161256790161, + "learning_rate": 1.3448699196557973e-06, + "loss": 0.2165, + "step": 926 + }, + { + "epoch": 1.9663397826663132, + "grad_norm": 1.0526455640792847, + "learning_rate": 1.3399082254602594e-06, + "loss": 0.1807, + "step": 927 + }, + { + "epoch": 1.9684601113172542, + "grad_norm": 2.217966079711914, + "learning_rate": 1.3349523479634368e-06, + "loss": 0.249, + "step": 928 + }, + { + "epoch": 1.9705804399681952, + "grad_norm": 1.8820593357086182, + "learning_rate": 1.3300023120140926e-06, + "loss": 0.1337, + "step": 929 + }, + { + "epoch": 1.972700768619136, + "grad_norm": 2.38179349899292, + "learning_rate": 1.3250581424317012e-06, + "loss": 0.2563, + "step": 930 + }, + { + "epoch": 1.9748210972700768, + "grad_norm": 1.0373716354370117, + "learning_rate": 1.3201198640063196e-06, + "loss": 0.2068, + "step": 931 + }, + { + "epoch": 1.9769414259210176, + "grad_norm": 2.2542104721069336, + "learning_rate": 1.3151875014984734e-06, + "loss": 0.1813, + "step": 932 + }, + { + "epoch": 1.9790617545719587, + "grad_norm": 0.9453467130661011, + "learning_rate": 1.3102610796390209e-06, + "loss": 0.2077, + "step": 933 + }, + { + "epoch": 1.9811820832228997, + "grad_norm": 2.0382044315338135, + "learning_rate": 1.3053406231290348e-06, + "loss": 0.1782, + "step": 934 + }, + { + "epoch": 1.9833024118738405, + "grad_norm": 1.4644185304641724, + "learning_rate": 1.300426156639677e-06, + "loss": 0.2884, + "step": 935 + }, + { + "epoch": 1.9854227405247813, + "grad_norm": 1.245954990386963, + "learning_rate": 1.2955177048120786e-06, + "loss": 0.192, + "step": 936 + }, + { + "epoch": 1.987543069175722, + "grad_norm": 0.672512412071228, + "learning_rate": 1.2906152922572102e-06, + "loss": 0.1134, + "step": 937 + }, + { + "epoch": 1.9896633978266631, + "grad_norm": 1.7579939365386963, + "learning_rate": 1.2857189435557616e-06, + "loss": 0.1924, + "step": 938 + }, + { + "epoch": 1.9917837264776042, + "grad_norm": 1.3811734914779663, + "learning_rate": 1.2808286832580186e-06, + "loss": 0.2068, + "step": 939 + }, + { + "epoch": 1.993904055128545, + "grad_norm": 2.4520797729492188, + "learning_rate": 1.2759445358837419e-06, + "loss": 0.1122, + "step": 940 + }, + { + "epoch": 1.9960243837794858, + "grad_norm": 1.866734266281128, + "learning_rate": 1.2710665259220403e-06, + "loss": 0.2615, + "step": 941 + }, + { + "epoch": 1.9981447124304266, + "grad_norm": 1.1177961826324463, + "learning_rate": 1.2661946778312473e-06, + "loss": 0.1196, + "step": 942 + }, + { + "epoch": 2.0010601643254704, + "grad_norm": 1.9562182426452637, + "learning_rate": 1.2613290160388052e-06, + "loss": 0.2324, + "step": 943 + }, + { + "epoch": 2.003180492976411, + "grad_norm": 1.1798341274261475, + "learning_rate": 1.2564695649411363e-06, + "loss": 0.1671, + "step": 944 + }, + { + "epoch": 2.0053008216273525, + "grad_norm": 1.4037326574325562, + "learning_rate": 1.2516163489035216e-06, + "loss": 0.1219, + "step": 945 + }, + { + "epoch": 2.0074211502782933, + "grad_norm": 1.7019480466842651, + "learning_rate": 1.2467693922599805e-06, + "loss": 0.1258, + "step": 946 + }, + { + "epoch": 2.009541478929234, + "grad_norm": 1.0615661144256592, + "learning_rate": 1.2419287193131468e-06, + "loss": 0.2731, + "step": 947 + }, + { + "epoch": 2.011661807580175, + "grad_norm": 1.3318649530410767, + "learning_rate": 1.23709435433415e-06, + "loss": 0.151, + "step": 948 + }, + { + "epoch": 2.0137821362311157, + "grad_norm": 1.8564578294754028, + "learning_rate": 1.2322663215624898e-06, + "loss": 0.187, + "step": 949 + }, + { + "epoch": 2.015902464882057, + "grad_norm": 1.6483088731765747, + "learning_rate": 1.2274446452059158e-06, + "loss": 0.1094, + "step": 950 + }, + { + "epoch": 2.0180227935329977, + "grad_norm": 1.7207893133163452, + "learning_rate": 1.222629349440308e-06, + "loss": 0.2884, + "step": 951 + }, + { + "epoch": 2.0201431221839385, + "grad_norm": 1.4903310537338257, + "learning_rate": 1.2178204584095526e-06, + "loss": 0.1166, + "step": 952 + }, + { + "epoch": 2.0222634508348794, + "grad_norm": 2.676420211791992, + "learning_rate": 1.213017996225424e-06, + "loss": 0.2639, + "step": 953 + }, + { + "epoch": 2.02438377948582, + "grad_norm": 1.2780916690826416, + "learning_rate": 1.2082219869674603e-06, + "loss": 0.2392, + "step": 954 + }, + { + "epoch": 2.0265041081367614, + "grad_norm": 0.6168650984764099, + "learning_rate": 1.2034324546828477e-06, + "loss": 0.1054, + "step": 955 + }, + { + "epoch": 2.028624436787702, + "grad_norm": 1.404857873916626, + "learning_rate": 1.1986494233862948e-06, + "loss": 0.2579, + "step": 956 + }, + { + "epoch": 2.030744765438643, + "grad_norm": 2.3824305534362793, + "learning_rate": 1.1938729170599136e-06, + "loss": 0.1962, + "step": 957 + }, + { + "epoch": 2.032865094089584, + "grad_norm": 0.960718035697937, + "learning_rate": 1.1891029596531005e-06, + "loss": 0.139, + "step": 958 + }, + { + "epoch": 2.0349854227405246, + "grad_norm": 1.5871549844741821, + "learning_rate": 1.1843395750824183e-06, + "loss": 0.1442, + "step": 959 + }, + { + "epoch": 2.037105751391466, + "grad_norm": 1.264162540435791, + "learning_rate": 1.1795827872314694e-06, + "loss": 0.1862, + "step": 960 + }, + { + "epoch": 2.0392260800424067, + "grad_norm": 0.9427124261856079, + "learning_rate": 1.1748326199507829e-06, + "loss": 0.187, + "step": 961 + }, + { + "epoch": 2.0413464086933475, + "grad_norm": 1.307521939277649, + "learning_rate": 1.1700890970576914e-06, + "loss": 0.1043, + "step": 962 + }, + { + "epoch": 2.0434667373442883, + "grad_norm": 0.6865214109420776, + "learning_rate": 1.1653522423362129e-06, + "loss": 0.1359, + "step": 963 + }, + { + "epoch": 2.045587065995229, + "grad_norm": 1.6144641637802124, + "learning_rate": 1.1606220795369307e-06, + "loss": 0.1808, + "step": 964 + }, + { + "epoch": 2.0477073946461704, + "grad_norm": 0.6050888299942017, + "learning_rate": 1.1558986323768758e-06, + "loss": 0.1454, + "step": 965 + }, + { + "epoch": 2.049827723297111, + "grad_norm": 1.202744483947754, + "learning_rate": 1.1511819245394051e-06, + "loss": 0.1273, + "step": 966 + }, + { + "epoch": 2.051948051948052, + "grad_norm": 0.35640886425971985, + "learning_rate": 1.1464719796740875e-06, + "loss": 0.1516, + "step": 967 + }, + { + "epoch": 2.0540683805989928, + "grad_norm": 2.3331637382507324, + "learning_rate": 1.1417688213965803e-06, + "loss": 0.2406, + "step": 968 + }, + { + "epoch": 2.0561887092499336, + "grad_norm": 1.4808611869812012, + "learning_rate": 1.1370724732885126e-06, + "loss": 0.2046, + "step": 969 + }, + { + "epoch": 2.058309037900875, + "grad_norm": 0.8104944229125977, + "learning_rate": 1.1323829588973676e-06, + "loss": 0.1645, + "step": 970 + }, + { + "epoch": 2.0604293665518156, + "grad_norm": 1.5165859460830688, + "learning_rate": 1.1277003017363661e-06, + "loss": 0.1562, + "step": 971 + }, + { + "epoch": 2.0625496952027564, + "grad_norm": 1.645854115486145, + "learning_rate": 1.1230245252843456e-06, + "loss": 0.1089, + "step": 972 + }, + { + "epoch": 2.0646700238536972, + "grad_norm": 1.7471455335617065, + "learning_rate": 1.1183556529856404e-06, + "loss": 0.216, + "step": 973 + }, + { + "epoch": 2.066790352504638, + "grad_norm": 1.2812058925628662, + "learning_rate": 1.1136937082499733e-06, + "loss": 0.0965, + "step": 974 + }, + { + "epoch": 2.0689106811555793, + "grad_norm": 1.1503514051437378, + "learning_rate": 1.1090387144523284e-06, + "loss": 0.2348, + "step": 975 + }, + { + "epoch": 2.07103100980652, + "grad_norm": 1.0059962272644043, + "learning_rate": 1.1043906949328387e-06, + "loss": 0.1252, + "step": 976 + }, + { + "epoch": 2.073151338457461, + "grad_norm": 1.8063433170318604, + "learning_rate": 1.0997496729966679e-06, + "loss": 0.228, + "step": 977 + }, + { + "epoch": 2.0752716671084017, + "grad_norm": 1.0282273292541504, + "learning_rate": 1.0951156719138953e-06, + "loss": 0.1241, + "step": 978 + }, + { + "epoch": 2.0773919957593425, + "grad_norm": 1.623639464378357, + "learning_rate": 1.090488714919396e-06, + "loss": 0.1477, + "step": 979 + }, + { + "epoch": 2.0795123244102838, + "grad_norm": 1.7182891368865967, + "learning_rate": 1.0858688252127268e-06, + "loss": 0.1195, + "step": 980 + }, + { + "epoch": 2.0816326530612246, + "grad_norm": 1.336841344833374, + "learning_rate": 1.0812560259580076e-06, + "loss": 0.1273, + "step": 981 + }, + { + "epoch": 2.0837529817121654, + "grad_norm": 1.0584746599197388, + "learning_rate": 1.0766503402838103e-06, + "loss": 0.1584, + "step": 982 + }, + { + "epoch": 2.085873310363106, + "grad_norm": 2.303407669067383, + "learning_rate": 1.0720517912830371e-06, + "loss": 0.1586, + "step": 983 + }, + { + "epoch": 2.087993639014047, + "grad_norm": 1.6193451881408691, + "learning_rate": 1.0674604020128051e-06, + "loss": 0.1341, + "step": 984 + }, + { + "epoch": 2.0901139676649882, + "grad_norm": 1.0736302137374878, + "learning_rate": 1.0628761954943343e-06, + "loss": 0.1727, + "step": 985 + }, + { + "epoch": 2.092234296315929, + "grad_norm": 0.9856461882591248, + "learning_rate": 1.0582991947128324e-06, + "loss": 0.1506, + "step": 986 + }, + { + "epoch": 2.09435462496687, + "grad_norm": 0.495143324136734, + "learning_rate": 1.0537294226173748e-06, + "loss": 0.1112, + "step": 987 + }, + { + "epoch": 2.0964749536178107, + "grad_norm": 1.2475007772445679, + "learning_rate": 1.0491669021207929e-06, + "loss": 0.2002, + "step": 988 + }, + { + "epoch": 2.0985952822687515, + "grad_norm": 1.5196057558059692, + "learning_rate": 1.0446116560995582e-06, + "loss": 0.2054, + "step": 989 + }, + { + "epoch": 2.1007156109196927, + "grad_norm": 0.9226682186126709, + "learning_rate": 1.0400637073936697e-06, + "loss": 0.153, + "step": 990 + }, + { + "epoch": 2.1028359395706335, + "grad_norm": 0.7360610961914062, + "learning_rate": 1.0355230788065365e-06, + "loss": 0.1552, + "step": 991 + }, + { + "epoch": 2.1049562682215743, + "grad_norm": 0.5949102640151978, + "learning_rate": 1.030989793104864e-06, + "loss": 0.2001, + "step": 992 + }, + { + "epoch": 2.107076596872515, + "grad_norm": 0.2589457929134369, + "learning_rate": 1.0264638730185409e-06, + "loss": 0.1307, + "step": 993 + }, + { + "epoch": 2.109196925523456, + "grad_norm": 0.5593380928039551, + "learning_rate": 1.021945341240527e-06, + "loss": 0.1668, + "step": 994 + }, + { + "epoch": 2.111317254174397, + "grad_norm": 0.8510894775390625, + "learning_rate": 1.0174342204267323e-06, + "loss": 0.1635, + "step": 995 + }, + { + "epoch": 2.113437582825338, + "grad_norm": 2.4190611839294434, + "learning_rate": 1.012930533195911e-06, + "loss": 0.2443, + "step": 996 + }, + { + "epoch": 2.115557911476279, + "grad_norm": 1.0228517055511475, + "learning_rate": 1.0084343021295476e-06, + "loss": 0.1109, + "step": 997 + }, + { + "epoch": 2.1176782401272196, + "grad_norm": 1.9541192054748535, + "learning_rate": 1.0039455497717376e-06, + "loss": 0.1842, + "step": 998 + }, + { + "epoch": 2.1197985687781604, + "grad_norm": 1.7048015594482422, + "learning_rate": 9.994642986290797e-07, + "loss": 0.1828, + "step": 999 + }, + { + "epoch": 2.1219188974291017, + "grad_norm": 1.2028521299362183, + "learning_rate": 9.949905711705613e-07, + "loss": 0.1531, + "step": 1000 + }, + { + "epoch": 2.1240392260800425, + "grad_norm": 0.7890755534172058, + "learning_rate": 9.905243898274476e-07, + "loss": 0.1289, + "step": 1001 + }, + { + "epoch": 2.1261595547309833, + "grad_norm": 1.3331317901611328, + "learning_rate": 9.86065776993165e-07, + "loss": 0.1114, + "step": 1002 + }, + { + "epoch": 2.128279883381924, + "grad_norm": 1.6627100706100464, + "learning_rate": 9.816147550231936e-07, + "loss": 0.1902, + "step": 1003 + }, + { + "epoch": 2.130400212032865, + "grad_norm": 1.721989393234253, + "learning_rate": 9.771713462349517e-07, + "loss": 0.1395, + "step": 1004 + }, + { + "epoch": 2.132520540683806, + "grad_norm": 2.435530662536621, + "learning_rate": 9.727355729076848e-07, + "loss": 0.141, + "step": 1005 + }, + { + "epoch": 2.134640869334747, + "grad_norm": 1.3753666877746582, + "learning_rate": 9.683074572823558e-07, + "loss": 0.1943, + "step": 1006 + }, + { + "epoch": 2.1367611979856878, + "grad_norm": 0.669357419013977, + "learning_rate": 9.638870215615304e-07, + "loss": 0.0903, + "step": 1007 + }, + { + "epoch": 2.1388815266366286, + "grad_norm": 1.5727747678756714, + "learning_rate": 9.594742879092673e-07, + "loss": 0.1862, + "step": 1008 + }, + { + "epoch": 2.1410018552875694, + "grad_norm": 1.037684440612793, + "learning_rate": 9.550692784510085e-07, + "loss": 0.114, + "step": 1009 + }, + { + "epoch": 2.1431221839385106, + "grad_norm": 1.0889723300933838, + "learning_rate": 9.50672015273466e-07, + "loss": 0.1046, + "step": 1010 + }, + { + "epoch": 2.1452425125894514, + "grad_norm": 2.344956398010254, + "learning_rate": 9.462825204245113e-07, + "loss": 0.1864, + "step": 1011 + }, + { + "epoch": 2.1473628412403922, + "grad_norm": 0.6746013760566711, + "learning_rate": 9.419008159130658e-07, + "loss": 0.064, + "step": 1012 + }, + { + "epoch": 2.149483169891333, + "grad_norm": 1.1768742799758911, + "learning_rate": 9.375269237089915e-07, + "loss": 0.1237, + "step": 1013 + }, + { + "epoch": 2.151603498542274, + "grad_norm": 1.0476148128509521, + "learning_rate": 9.331608657429781e-07, + "loss": 0.1576, + "step": 1014 + }, + { + "epoch": 2.153723827193215, + "grad_norm": 1.505977749824524, + "learning_rate": 9.288026639064346e-07, + "loss": 0.1716, + "step": 1015 + }, + { + "epoch": 2.155844155844156, + "grad_norm": 1.6064363718032837, + "learning_rate": 9.244523400513797e-07, + "loss": 0.1497, + "step": 1016 + }, + { + "epoch": 2.1579644844950967, + "grad_norm": 0.21721459925174713, + "learning_rate": 9.201099159903318e-07, + "loss": 0.0957, + "step": 1017 + }, + { + "epoch": 2.1600848131460375, + "grad_norm": 1.4369566440582275, + "learning_rate": 9.157754134961997e-07, + "loss": 0.2541, + "step": 1018 + }, + { + "epoch": 2.1622051417969788, + "grad_norm": 2.7585020065307617, + "learning_rate": 9.114488543021724e-07, + "loss": 0.1664, + "step": 1019 + }, + { + "epoch": 2.1643254704479196, + "grad_norm": 2.044339179992676, + "learning_rate": 9.071302601016147e-07, + "loss": 0.2169, + "step": 1020 + }, + { + "epoch": 2.1664457990988604, + "grad_norm": 1.5984207391738892, + "learning_rate": 9.02819652547951e-07, + "loss": 0.1863, + "step": 1021 + }, + { + "epoch": 2.168566127749801, + "grad_norm": 0.9591246247291565, + "learning_rate": 8.985170532545623e-07, + "loss": 0.1827, + "step": 1022 + }, + { + "epoch": 2.170686456400742, + "grad_norm": 2.260664939880371, + "learning_rate": 8.942224837946767e-07, + "loss": 0.2556, + "step": 1023 + }, + { + "epoch": 2.172806785051683, + "grad_norm": 1.4247132539749146, + "learning_rate": 8.899359657012585e-07, + "loss": 0.1713, + "step": 1024 + }, + { + "epoch": 2.174927113702624, + "grad_norm": 0.177411288022995, + "learning_rate": 8.856575204669066e-07, + "loss": 0.1403, + "step": 1025 + }, + { + "epoch": 2.177047442353565, + "grad_norm": 1.4643137454986572, + "learning_rate": 8.813871695437392e-07, + "loss": 0.2385, + "step": 1026 + }, + { + "epoch": 2.1791677710045056, + "grad_norm": 0.7702186107635498, + "learning_rate": 8.771249343432886e-07, + "loss": 0.1823, + "step": 1027 + }, + { + "epoch": 2.1812880996554465, + "grad_norm": 1.4628134965896606, + "learning_rate": 8.728708362363991e-07, + "loss": 0.0917, + "step": 1028 + }, + { + "epoch": 2.1834084283063877, + "grad_norm": 1.2553027868270874, + "learning_rate": 8.686248965531124e-07, + "loss": 0.1308, + "step": 1029 + }, + { + "epoch": 2.1855287569573285, + "grad_norm": 1.879456639289856, + "learning_rate": 8.643871365825651e-07, + "loss": 0.181, + "step": 1030 + }, + { + "epoch": 2.1876490856082693, + "grad_norm": 0.45591041445732117, + "learning_rate": 8.601575775728793e-07, + "loss": 0.1376, + "step": 1031 + }, + { + "epoch": 2.18976941425921, + "grad_norm": 2.5236010551452637, + "learning_rate": 8.559362407310607e-07, + "loss": 0.1826, + "step": 1032 + }, + { + "epoch": 2.191889742910151, + "grad_norm": 1.757652997970581, + "learning_rate": 8.517231472228854e-07, + "loss": 0.2169, + "step": 1033 + }, + { + "epoch": 2.1940100715610917, + "grad_norm": 1.7674883604049683, + "learning_rate": 8.475183181727995e-07, + "loss": 0.2092, + "step": 1034 + }, + { + "epoch": 2.196130400212033, + "grad_norm": 1.4368592500686646, + "learning_rate": 8.433217746638098e-07, + "loss": 0.1093, + "step": 1035 + }, + { + "epoch": 2.198250728862974, + "grad_norm": 3.643383264541626, + "learning_rate": 8.391335377373825e-07, + "loss": 0.1931, + "step": 1036 + }, + { + "epoch": 2.2003710575139146, + "grad_norm": 1.120516300201416, + "learning_rate": 8.349536283933302e-07, + "loss": 0.226, + "step": 1037 + }, + { + "epoch": 2.2024913861648554, + "grad_norm": 1.6171327829360962, + "learning_rate": 8.307820675897127e-07, + "loss": 0.1644, + "step": 1038 + }, + { + "epoch": 2.2046117148157967, + "grad_norm": 0.962647557258606, + "learning_rate": 8.266188762427327e-07, + "loss": 0.1338, + "step": 1039 + }, + { + "epoch": 2.2067320434667375, + "grad_norm": 2.5459415912628174, + "learning_rate": 8.224640752266256e-07, + "loss": 0.2425, + "step": 1040 + }, + { + "epoch": 2.2088523721176783, + "grad_norm": 1.1007134914398193, + "learning_rate": 8.18317685373558e-07, + "loss": 0.0995, + "step": 1041 + }, + { + "epoch": 2.210972700768619, + "grad_norm": 1.3371065855026245, + "learning_rate": 8.141797274735242e-07, + "loss": 0.1023, + "step": 1042 + }, + { + "epoch": 2.21309302941956, + "grad_norm": 1.4020932912826538, + "learning_rate": 8.100502222742387e-07, + "loss": 0.2438, + "step": 1043 + }, + { + "epoch": 2.215213358070501, + "grad_norm": 0.8787581324577332, + "learning_rate": 8.059291904810373e-07, + "loss": 0.18, + "step": 1044 + }, + { + "epoch": 2.217333686721442, + "grad_norm": 2.061732292175293, + "learning_rate": 8.018166527567672e-07, + "loss": 0.1664, + "step": 1045 + }, + { + "epoch": 2.2194540153723827, + "grad_norm": 1.4549061059951782, + "learning_rate": 7.977126297216878e-07, + "loss": 0.1453, + "step": 1046 + }, + { + "epoch": 2.2215743440233235, + "grad_norm": 1.787046194076538, + "learning_rate": 7.936171419533653e-07, + "loss": 0.1826, + "step": 1047 + }, + { + "epoch": 2.2236946726742643, + "grad_norm": 1.2680433988571167, + "learning_rate": 7.895302099865701e-07, + "loss": 0.1264, + "step": 1048 + }, + { + "epoch": 2.2258150013252056, + "grad_norm": 1.716055989265442, + "learning_rate": 7.854518543131742e-07, + "loss": 0.1218, + "step": 1049 + }, + { + "epoch": 2.2279353299761464, + "grad_norm": 1.614372730255127, + "learning_rate": 7.813820953820469e-07, + "loss": 0.1772, + "step": 1050 + }, + { + "epoch": 2.230055658627087, + "grad_norm": 1.2348659038543701, + "learning_rate": 7.773209535989562e-07, + "loss": 0.2343, + "step": 1051 + }, + { + "epoch": 2.232175987278028, + "grad_norm": 0.6399396657943726, + "learning_rate": 7.732684493264611e-07, + "loss": 0.1654, + "step": 1052 + }, + { + "epoch": 2.234296315928969, + "grad_norm": 0.7470250129699707, + "learning_rate": 7.69224602883813e-07, + "loss": 0.1807, + "step": 1053 + }, + { + "epoch": 2.23641664457991, + "grad_norm": 1.0854237079620361, + "learning_rate": 7.651894345468522e-07, + "loss": 0.1645, + "step": 1054 + }, + { + "epoch": 2.238536973230851, + "grad_norm": 1.6901220083236694, + "learning_rate": 7.61162964547909e-07, + "loss": 0.1378, + "step": 1055 + }, + { + "epoch": 2.2406573018817917, + "grad_norm": 1.3711787462234497, + "learning_rate": 7.571452130756984e-07, + "loss": 0.2183, + "step": 1056 + }, + { + "epoch": 2.2427776305327325, + "grad_norm": 2.0862414836883545, + "learning_rate": 7.531362002752224e-07, + "loss": 0.184, + "step": 1057 + }, + { + "epoch": 2.2448979591836733, + "grad_norm": 1.5051991939544678, + "learning_rate": 7.491359462476632e-07, + "loss": 0.1685, + "step": 1058 + }, + { + "epoch": 2.2470182878346145, + "grad_norm": 1.7202171087265015, + "learning_rate": 7.451444710502923e-07, + "loss": 0.1379, + "step": 1059 + }, + { + "epoch": 2.2491386164855554, + "grad_norm": 1.7147220373153687, + "learning_rate": 7.411617946963604e-07, + "loss": 0.1665, + "step": 1060 + }, + { + "epoch": 2.251258945136496, + "grad_norm": 2.444573402404785, + "learning_rate": 7.371879371550017e-07, + "loss": 0.1337, + "step": 1061 + }, + { + "epoch": 2.253379273787437, + "grad_norm": 0.8904200792312622, + "learning_rate": 7.332229183511325e-07, + "loss": 0.3001, + "step": 1062 + }, + { + "epoch": 2.2554996024383778, + "grad_norm": 2.107675075531006, + "learning_rate": 7.292667581653537e-07, + "loss": 0.1673, + "step": 1063 + }, + { + "epoch": 2.257619931089319, + "grad_norm": 1.31276273727417, + "learning_rate": 7.253194764338465e-07, + "loss": 0.1727, + "step": 1064 + }, + { + "epoch": 2.25974025974026, + "grad_norm": 1.6621828079223633, + "learning_rate": 7.213810929482765e-07, + "loss": 0.1634, + "step": 1065 + }, + { + "epoch": 2.2618605883912006, + "grad_norm": 1.0999544858932495, + "learning_rate": 7.174516274556931e-07, + "loss": 0.2101, + "step": 1066 + }, + { + "epoch": 2.2639809170421414, + "grad_norm": 1.487066626548767, + "learning_rate": 7.13531099658433e-07, + "loss": 0.2167, + "step": 1067 + }, + { + "epoch": 2.2661012456930822, + "grad_norm": 1.1154425144195557, + "learning_rate": 7.096195292140173e-07, + "loss": 0.1175, + "step": 1068 + }, + { + "epoch": 2.2682215743440235, + "grad_norm": 1.7825549840927124, + "learning_rate": 7.057169357350535e-07, + "loss": 0.1834, + "step": 1069 + }, + { + "epoch": 2.2703419029949643, + "grad_norm": 2.048605442047119, + "learning_rate": 7.018233387891426e-07, + "loss": 0.0926, + "step": 1070 + }, + { + "epoch": 2.272462231645905, + "grad_norm": 1.7023017406463623, + "learning_rate": 6.97938757898774e-07, + "loss": 0.1592, + "step": 1071 + }, + { + "epoch": 2.274582560296846, + "grad_norm": 2.4371001720428467, + "learning_rate": 6.940632125412314e-07, + "loss": 0.1927, + "step": 1072 + }, + { + "epoch": 2.2767028889477867, + "grad_norm": 1.6496391296386719, + "learning_rate": 6.901967221484937e-07, + "loss": 0.2078, + "step": 1073 + }, + { + "epoch": 2.278823217598728, + "grad_norm": 0.7623432278633118, + "learning_rate": 6.863393061071407e-07, + "loss": 0.1582, + "step": 1074 + }, + { + "epoch": 2.2809435462496688, + "grad_norm": 1.767440915107727, + "learning_rate": 6.824909837582505e-07, + "loss": 0.1972, + "step": 1075 + }, + { + "epoch": 2.2830638749006096, + "grad_norm": 1.3551329374313354, + "learning_rate": 6.786517743973065e-07, + "loss": 0.1635, + "step": 1076 + }, + { + "epoch": 2.2851842035515504, + "grad_norm": 1.824154019355774, + "learning_rate": 6.748216972740992e-07, + "loss": 0.1746, + "step": 1077 + }, + { + "epoch": 2.2873045322024916, + "grad_norm": 1.9137120246887207, + "learning_rate": 6.71000771592632e-07, + "loss": 0.1611, + "step": 1078 + }, + { + "epoch": 2.2894248608534324, + "grad_norm": 1.8039703369140625, + "learning_rate": 6.671890165110214e-07, + "loss": 0.1905, + "step": 1079 + }, + { + "epoch": 2.2915451895043732, + "grad_norm": 1.7576533555984497, + "learning_rate": 6.633864511414015e-07, + "loss": 0.1512, + "step": 1080 + }, + { + "epoch": 2.293665518155314, + "grad_norm": 0.6087268590927124, + "learning_rate": 6.595930945498297e-07, + "loss": 0.1088, + "step": 1081 + }, + { + "epoch": 2.295785846806255, + "grad_norm": 0.9811050891876221, + "learning_rate": 6.558089657561931e-07, + "loss": 0.1399, + "step": 1082 + }, + { + "epoch": 2.2979061754571957, + "grad_norm": 2.133836507797241, + "learning_rate": 6.520340837341079e-07, + "loss": 0.231, + "step": 1083 + }, + { + "epoch": 2.300026504108137, + "grad_norm": 1.9858092069625854, + "learning_rate": 6.482684674108281e-07, + "loss": 0.1828, + "step": 1084 + }, + { + "epoch": 2.3021468327590777, + "grad_norm": 1.1744147539138794, + "learning_rate": 6.445121356671483e-07, + "loss": 0.1228, + "step": 1085 + }, + { + "epoch": 2.3042671614100185, + "grad_norm": 1.6011583805084229, + "learning_rate": 6.407651073373125e-07, + "loss": 0.1959, + "step": 1086 + }, + { + "epoch": 2.3063874900609593, + "grad_norm": 1.8023475408554077, + "learning_rate": 6.370274012089159e-07, + "loss": 0.1723, + "step": 1087 + }, + { + "epoch": 2.3085078187119006, + "grad_norm": 0.8929461240768433, + "learning_rate": 6.332990360228119e-07, + "loss": 0.1399, + "step": 1088 + }, + { + "epoch": 2.3106281473628414, + "grad_norm": 1.1111611127853394, + "learning_rate": 6.29580030473019e-07, + "loss": 0.124, + "step": 1089 + }, + { + "epoch": 2.312748476013782, + "grad_norm": 2.0618672370910645, + "learning_rate": 6.258704032066265e-07, + "loss": 0.2, + "step": 1090 + }, + { + "epoch": 2.314868804664723, + "grad_norm": 1.5747716426849365, + "learning_rate": 6.221701728237008e-07, + "loss": 0.2478, + "step": 1091 + }, + { + "epoch": 2.316989133315664, + "grad_norm": 1.6358662843704224, + "learning_rate": 6.184793578771919e-07, + "loss": 0.2235, + "step": 1092 + }, + { + "epoch": 2.3191094619666046, + "grad_norm": 1.1135793924331665, + "learning_rate": 6.147979768728427e-07, + "loss": 0.259, + "step": 1093 + }, + { + "epoch": 2.321229790617546, + "grad_norm": 1.4510762691497803, + "learning_rate": 6.11126048269092e-07, + "loss": 0.1029, + "step": 1094 + }, + { + "epoch": 2.3233501192684867, + "grad_norm": 1.924076795578003, + "learning_rate": 6.074635904769855e-07, + "loss": 0.2121, + "step": 1095 + }, + { + "epoch": 2.3254704479194275, + "grad_norm": 2.4901790618896484, + "learning_rate": 6.03810621860082e-07, + "loss": 0.1593, + "step": 1096 + }, + { + "epoch": 2.3275907765703683, + "grad_norm": 2.7300894260406494, + "learning_rate": 6.001671607343609e-07, + "loss": 0.2646, + "step": 1097 + }, + { + "epoch": 2.3297111052213095, + "grad_norm": 0.29893285036087036, + "learning_rate": 5.96533225368133e-07, + "loss": 0.0587, + "step": 1098 + }, + { + "epoch": 2.3318314338722503, + "grad_norm": 2.7989368438720703, + "learning_rate": 5.929088339819452e-07, + "loss": 0.2278, + "step": 1099 + }, + { + "epoch": 2.333951762523191, + "grad_norm": 1.3706281185150146, + "learning_rate": 5.892940047484915e-07, + "loss": 0.2335, + "step": 1100 + }, + { + "epoch": 2.336072091174132, + "grad_norm": 0.9056196808815002, + "learning_rate": 5.856887557925209e-07, + "loss": 0.1164, + "step": 1101 + }, + { + "epoch": 2.3381924198250728, + "grad_norm": 0.811579167842865, + "learning_rate": 5.820931051907471e-07, + "loss": 0.1564, + "step": 1102 + }, + { + "epoch": 2.3403127484760136, + "grad_norm": 1.3035115003585815, + "learning_rate": 5.785070709717583e-07, + "loss": 0.1035, + "step": 1103 + }, + { + "epoch": 2.342433077126955, + "grad_norm": 1.7552999258041382, + "learning_rate": 5.749306711159245e-07, + "loss": 0.1593, + "step": 1104 + }, + { + "epoch": 2.3445534057778956, + "grad_norm": 1.4544363021850586, + "learning_rate": 5.713639235553115e-07, + "loss": 0.2125, + "step": 1105 + }, + { + "epoch": 2.3466737344288364, + "grad_norm": 1.2122842073440552, + "learning_rate": 5.678068461735864e-07, + "loss": 0.2044, + "step": 1106 + }, + { + "epoch": 2.3487940630797772, + "grad_norm": 3.637741804122925, + "learning_rate": 5.642594568059309e-07, + "loss": 0.1786, + "step": 1107 + }, + { + "epoch": 2.3509143917307185, + "grad_norm": 1.0546187162399292, + "learning_rate": 5.607217732389503e-07, + "loss": 0.2013, + "step": 1108 + }, + { + "epoch": 2.3530347203816593, + "grad_norm": 0.7517843246459961, + "learning_rate": 5.571938132105867e-07, + "loss": 0.0689, + "step": 1109 + }, + { + "epoch": 2.3551550490326, + "grad_norm": 1.7113940715789795, + "learning_rate": 5.536755944100269e-07, + "loss": 0.1401, + "step": 1110 + }, + { + "epoch": 2.357275377683541, + "grad_norm": 0.45268720388412476, + "learning_rate": 5.501671344776152e-07, + "loss": 0.1351, + "step": 1111 + }, + { + "epoch": 2.3593957063344817, + "grad_norm": 1.2750608921051025, + "learning_rate": 5.466684510047659e-07, + "loss": 0.1929, + "step": 1112 + }, + { + "epoch": 2.3615160349854225, + "grad_norm": 1.2814080715179443, + "learning_rate": 5.43179561533873e-07, + "loss": 0.1553, + "step": 1113 + }, + { + "epoch": 2.3636363636363638, + "grad_norm": 0.29188236594200134, + "learning_rate": 5.397004835582242e-07, + "loss": 0.1258, + "step": 1114 + }, + { + "epoch": 2.3657566922873046, + "grad_norm": 1.2712785005569458, + "learning_rate": 5.362312345219125e-07, + "loss": 0.1353, + "step": 1115 + }, + { + "epoch": 2.3678770209382454, + "grad_norm": 1.9240132570266724, + "learning_rate": 5.327718318197469e-07, + "loss": 0.2128, + "step": 1116 + }, + { + "epoch": 2.369997349589186, + "grad_norm": 0.3361606299877167, + "learning_rate": 5.293222927971703e-07, + "loss": 0.0749, + "step": 1117 + }, + { + "epoch": 2.3721176782401274, + "grad_norm": 0.9936760663986206, + "learning_rate": 5.258826347501655e-07, + "loss": 0.2372, + "step": 1118 + }, + { + "epoch": 2.3742380068910682, + "grad_norm": 1.9898719787597656, + "learning_rate": 5.224528749251747e-07, + "loss": 0.1649, + "step": 1119 + }, + { + "epoch": 2.376358335542009, + "grad_norm": 2.3979244232177734, + "learning_rate": 5.190330305190081e-07, + "loss": 0.1553, + "step": 1120 + }, + { + "epoch": 2.37847866419295, + "grad_norm": 1.371147632598877, + "learning_rate": 5.156231186787633e-07, + "loss": 0.1436, + "step": 1121 + }, + { + "epoch": 2.3805989928438906, + "grad_norm": 2.101191759109497, + "learning_rate": 5.122231565017321e-07, + "loss": 0.1716, + "step": 1122 + }, + { + "epoch": 2.3827193214948315, + "grad_norm": 3.039147138595581, + "learning_rate": 5.088331610353209e-07, + "loss": 0.1668, + "step": 1123 + }, + { + "epoch": 2.3848396501457727, + "grad_norm": 1.054470181465149, + "learning_rate": 5.054531492769637e-07, + "loss": 0.1036, + "step": 1124 + }, + { + "epoch": 2.3869599787967135, + "grad_norm": 2.9882962703704834, + "learning_rate": 5.020831381740348e-07, + "loss": 0.1721, + "step": 1125 + }, + { + "epoch": 2.3890803074476543, + "grad_norm": 0.9891959428787231, + "learning_rate": 4.987231446237656e-07, + "loss": 0.0804, + "step": 1126 + }, + { + "epoch": 2.391200636098595, + "grad_norm": 1.865025520324707, + "learning_rate": 4.953731854731591e-07, + "loss": 0.1742, + "step": 1127 + }, + { + "epoch": 2.3933209647495364, + "grad_norm": 1.979583740234375, + "learning_rate": 4.920332775189074e-07, + "loss": 0.2472, + "step": 1128 + }, + { + "epoch": 2.395441293400477, + "grad_norm": 1.5632679462432861, + "learning_rate": 4.887034375073041e-07, + "loss": 0.1866, + "step": 1129 + }, + { + "epoch": 2.397561622051418, + "grad_norm": 0.98792564868927, + "learning_rate": 4.853836821341632e-07, + "loss": 0.0903, + "step": 1130 + }, + { + "epoch": 2.399681950702359, + "grad_norm": 1.7451393604278564, + "learning_rate": 4.820740280447331e-07, + "loss": 0.1345, + "step": 1131 + }, + { + "epoch": 2.4018022793532996, + "grad_norm": 1.910881757736206, + "learning_rate": 4.787744918336173e-07, + "loss": 0.1936, + "step": 1132 + }, + { + "epoch": 2.403922608004241, + "grad_norm": 1.0377843379974365, + "learning_rate": 4.7548509004468444e-07, + "loss": 0.1536, + "step": 1133 + }, + { + "epoch": 2.4060429366551817, + "grad_norm": 1.5963490009307861, + "learning_rate": 4.7220583917099135e-07, + "loss": 0.1719, + "step": 1134 + }, + { + "epoch": 2.4081632653061225, + "grad_norm": 1.8249528408050537, + "learning_rate": 4.6893675565469754e-07, + "loss": 0.1753, + "step": 1135 + }, + { + "epoch": 2.4102835939570633, + "grad_norm": 1.2173981666564941, + "learning_rate": 4.656778558869848e-07, + "loss": 0.1237, + "step": 1136 + }, + { + "epoch": 2.412403922608004, + "grad_norm": 2.324706554412842, + "learning_rate": 4.624291562079719e-07, + "loss": 0.1424, + "step": 1137 + }, + { + "epoch": 2.4145242512589453, + "grad_norm": 0.6716301441192627, + "learning_rate": 4.5919067290663503e-07, + "loss": 0.1932, + "step": 1138 + }, + { + "epoch": 2.416644579909886, + "grad_norm": 0.7555845379829407, + "learning_rate": 4.5596242222072457e-07, + "loss": 0.1664, + "step": 1139 + }, + { + "epoch": 2.418764908560827, + "grad_norm": 1.272320032119751, + "learning_rate": 4.527444203366868e-07, + "loss": 0.2251, + "step": 1140 + }, + { + "epoch": 2.4208852372117677, + "grad_norm": 1.8669896125793457, + "learning_rate": 4.4953668338957896e-07, + "loss": 0.1409, + "step": 1141 + }, + { + "epoch": 2.4230055658627085, + "grad_norm": 1.2830485105514526, + "learning_rate": 4.4633922746298965e-07, + "loss": 0.191, + "step": 1142 + }, + { + "epoch": 2.42512589451365, + "grad_norm": 1.8277826309204102, + "learning_rate": 4.431520685889587e-07, + "loss": 0.2368, + "step": 1143 + }, + { + "epoch": 2.4272462231645906, + "grad_norm": 0.8286747336387634, + "learning_rate": 4.3997522274789735e-07, + "loss": 0.1493, + "step": 1144 + }, + { + "epoch": 2.4293665518155314, + "grad_norm": 1.1364187002182007, + "learning_rate": 4.3680870586850636e-07, + "loss": 0.1692, + "step": 1145 + }, + { + "epoch": 2.431486880466472, + "grad_norm": 1.0993447303771973, + "learning_rate": 4.33652533827697e-07, + "loss": 0.1777, + "step": 1146 + }, + { + "epoch": 2.433607209117413, + "grad_norm": 1.555851697921753, + "learning_rate": 4.30506722450513e-07, + "loss": 0.1687, + "step": 1147 + }, + { + "epoch": 2.4357275377683543, + "grad_norm": 1.4744566679000854, + "learning_rate": 4.2737128751004804e-07, + "loss": 0.1453, + "step": 1148 + }, + { + "epoch": 2.437847866419295, + "grad_norm": 1.0803353786468506, + "learning_rate": 4.2424624472736904e-07, + "loss": 0.1837, + "step": 1149 + }, + { + "epoch": 2.439968195070236, + "grad_norm": 2.3968465328216553, + "learning_rate": 4.21131609771436e-07, + "loss": 0.1461, + "step": 1150 + }, + { + "epoch": 2.4420885237211767, + "grad_norm": 0.953355610370636, + "learning_rate": 4.1802739825902604e-07, + "loss": 0.1405, + "step": 1151 + }, + { + "epoch": 2.4442088523721175, + "grad_norm": 1.5285724401474, + "learning_rate": 4.149336257546513e-07, + "loss": 0.1662, + "step": 1152 + }, + { + "epoch": 2.4463291810230587, + "grad_norm": 1.5645101070404053, + "learning_rate": 4.1185030777048385e-07, + "loss": 0.1365, + "step": 1153 + }, + { + "epoch": 2.4484495096739995, + "grad_norm": 1.1964720487594604, + "learning_rate": 4.0877745976627416e-07, + "loss": 0.1012, + "step": 1154 + }, + { + "epoch": 2.4505698383249404, + "grad_norm": 0.9920772314071655, + "learning_rate": 4.0571509714928015e-07, + "loss": 0.16, + "step": 1155 + }, + { + "epoch": 2.452690166975881, + "grad_norm": 1.2442920207977295, + "learning_rate": 4.0266323527418384e-07, + "loss": 0.1339, + "step": 1156 + }, + { + "epoch": 2.454810495626822, + "grad_norm": 2.105613946914673, + "learning_rate": 3.996218894430165e-07, + "loss": 0.1725, + "step": 1157 + }, + { + "epoch": 2.456930824277763, + "grad_norm": 2.082643985748291, + "learning_rate": 3.965910749050822e-07, + "loss": 0.1981, + "step": 1158 + }, + { + "epoch": 2.459051152928704, + "grad_norm": 1.1390914916992188, + "learning_rate": 3.935708068568822e-07, + "loss": 0.1306, + "step": 1159 + }, + { + "epoch": 2.461171481579645, + "grad_norm": 2.3896877765655518, + "learning_rate": 3.9056110044203594e-07, + "loss": 0.1381, + "step": 1160 + }, + { + "epoch": 2.4632918102305856, + "grad_norm": 2.7147066593170166, + "learning_rate": 3.875619707512082e-07, + "loss": 0.1665, + "step": 1161 + }, + { + "epoch": 2.4654121388815264, + "grad_norm": 1.8762184381484985, + "learning_rate": 3.845734328220302e-07, + "loss": 0.153, + "step": 1162 + }, + { + "epoch": 2.4675324675324677, + "grad_norm": 1.4341996908187866, + "learning_rate": 3.8159550163902936e-07, + "loss": 0.2096, + "step": 1163 + }, + { + "epoch": 2.4696527961834085, + "grad_norm": 0.6933192014694214, + "learning_rate": 3.786281921335483e-07, + "loss": 0.1243, + "step": 1164 + }, + { + "epoch": 2.4717731248343493, + "grad_norm": 1.4996116161346436, + "learning_rate": 3.7567151918367156e-07, + "loss": 0.1478, + "step": 1165 + }, + { + "epoch": 2.47389345348529, + "grad_norm": 1.3368818759918213, + "learning_rate": 3.727254976141556e-07, + "loss": 0.1344, + "step": 1166 + }, + { + "epoch": 2.4760137821362314, + "grad_norm": 1.774940013885498, + "learning_rate": 3.697901421963482e-07, + "loss": 0.1596, + "step": 1167 + }, + { + "epoch": 2.478134110787172, + "grad_norm": 1.6905888319015503, + "learning_rate": 3.6686546764811787e-07, + "loss": 0.1897, + "step": 1168 + }, + { + "epoch": 2.480254439438113, + "grad_norm": 1.100188136100769, + "learning_rate": 3.639514886337786e-07, + "loss": 0.123, + "step": 1169 + }, + { + "epoch": 2.4823747680890538, + "grad_norm": 1.1606425046920776, + "learning_rate": 3.6104821976401834e-07, + "loss": 0.1602, + "step": 1170 + }, + { + "epoch": 2.4844950967399946, + "grad_norm": 0.8431051969528198, + "learning_rate": 3.581556755958232e-07, + "loss": 0.1281, + "step": 1171 + }, + { + "epoch": 2.4866154253909354, + "grad_norm": 3.2979464530944824, + "learning_rate": 3.552738706324063e-07, + "loss": 0.2761, + "step": 1172 + }, + { + "epoch": 2.4887357540418766, + "grad_norm": 1.7223345041275024, + "learning_rate": 3.524028193231338e-07, + "loss": 0.1354, + "step": 1173 + }, + { + "epoch": 2.4908560826928174, + "grad_norm": 0.983549952507019, + "learning_rate": 3.4954253606345386e-07, + "loss": 0.2041, + "step": 1174 + }, + { + "epoch": 2.4929764113437582, + "grad_norm": 3.322826385498047, + "learning_rate": 3.466930351948225e-07, + "loss": 0.1717, + "step": 1175 + }, + { + "epoch": 2.495096739994699, + "grad_norm": 1.789494514465332, + "learning_rate": 3.438543310046341e-07, + "loss": 0.2393, + "step": 1176 + }, + { + "epoch": 2.4972170686456403, + "grad_norm": 2.312497138977051, + "learning_rate": 3.4102643772614713e-07, + "loss": 0.2275, + "step": 1177 + }, + { + "epoch": 2.499337397296581, + "grad_norm": 1.2368191480636597, + "learning_rate": 3.3820936953841585e-07, + "loss": 0.1546, + "step": 1178 + }, + { + "epoch": 2.501457725947522, + "grad_norm": 1.659166932106018, + "learning_rate": 3.354031405662167e-07, + "loss": 0.1479, + "step": 1179 + }, + { + "epoch": 2.5035780545984627, + "grad_norm": 0.9831505417823792, + "learning_rate": 3.3260776487997803e-07, + "loss": 0.1361, + "step": 1180 + }, + { + "epoch": 2.5056983832494035, + "grad_norm": 2.298849105834961, + "learning_rate": 3.2982325649570907e-07, + "loss": 0.1951, + "step": 1181 + }, + { + "epoch": 2.5078187119003443, + "grad_norm": 0.6283709406852722, + "learning_rate": 3.2704962937493314e-07, + "loss": 0.0913, + "step": 1182 + }, + { + "epoch": 2.5099390405512856, + "grad_norm": 1.612980604171753, + "learning_rate": 3.2428689742461187e-07, + "loss": 0.182, + "step": 1183 + }, + { + "epoch": 2.5120593692022264, + "grad_norm": 0.8001376390457153, + "learning_rate": 3.215350744970808e-07, + "loss": 0.1474, + "step": 1184 + }, + { + "epoch": 2.514179697853167, + "grad_norm": 1.5370627641677856, + "learning_rate": 3.1879417438997583e-07, + "loss": 0.2535, + "step": 1185 + }, + { + "epoch": 2.516300026504108, + "grad_norm": 0.8482860922813416, + "learning_rate": 3.16064210846167e-07, + "loss": 0.0681, + "step": 1186 + }, + { + "epoch": 2.5184203551550493, + "grad_norm": 0.5224332213401794, + "learning_rate": 3.1334519755368805e-07, + "loss": 0.1279, + "step": 1187 + }, + { + "epoch": 2.52054068380599, + "grad_norm": 0.6476213932037354, + "learning_rate": 3.106371481456677e-07, + "loss": 0.1971, + "step": 1188 + }, + { + "epoch": 2.522661012456931, + "grad_norm": 2.0311484336853027, + "learning_rate": 3.079400762002635e-07, + "loss": 0.2494, + "step": 1189 + }, + { + "epoch": 2.5247813411078717, + "grad_norm": 1.1243444681167603, + "learning_rate": 3.0525399524059055e-07, + "loss": 0.183, + "step": 1190 + }, + { + "epoch": 2.5269016697588125, + "grad_norm": 0.8074027895927429, + "learning_rate": 3.025789187346548e-07, + "loss": 0.1433, + "step": 1191 + }, + { + "epoch": 2.5290219984097533, + "grad_norm": 2.325946092605591, + "learning_rate": 2.9991486009528696e-07, + "loss": 0.2281, + "step": 1192 + }, + { + "epoch": 2.5311423270606945, + "grad_norm": 1.595554232597351, + "learning_rate": 2.9726183268007304e-07, + "loss": 0.183, + "step": 1193 + }, + { + "epoch": 2.5332626557116353, + "grad_norm": 1.5321136713027954, + "learning_rate": 2.9461984979129056e-07, + "loss": 0.1823, + "step": 1194 + }, + { + "epoch": 2.535382984362576, + "grad_norm": 1.1611591577529907, + "learning_rate": 2.919889246758373e-07, + "loss": 0.1234, + "step": 1195 + }, + { + "epoch": 2.537503313013517, + "grad_norm": 2.7219529151916504, + "learning_rate": 2.8936907052516923e-07, + "loss": 0.2472, + "step": 1196 + }, + { + "epoch": 2.539623641664458, + "grad_norm": 1.3693172931671143, + "learning_rate": 2.8676030047523115e-07, + "loss": 0.1547, + "step": 1197 + }, + { + "epoch": 2.541743970315399, + "grad_norm": 0.7124255895614624, + "learning_rate": 2.841626276063933e-07, + "loss": 0.1421, + "step": 1198 + }, + { + "epoch": 2.54386429896634, + "grad_norm": 0.7943392992019653, + "learning_rate": 2.815760649433841e-07, + "loss": 0.0918, + "step": 1199 + }, + { + "epoch": 2.5459846276172806, + "grad_norm": 2.9632608890533447, + "learning_rate": 2.7900062545522493e-07, + "loss": 0.1396, + "step": 1200 + }, + { + "epoch": 2.5481049562682214, + "grad_norm": 0.6642888188362122, + "learning_rate": 2.764363220551672e-07, + "loss": 0.1228, + "step": 1201 + }, + { + "epoch": 2.5502252849191622, + "grad_norm": 1.34070885181427, + "learning_rate": 2.7388316760062457e-07, + "loss": 0.1093, + "step": 1202 + }, + { + "epoch": 2.5523456135701035, + "grad_norm": 1.1793408393859863, + "learning_rate": 2.7134117489311023e-07, + "loss": 0.1161, + "step": 1203 + }, + { + "epoch": 2.5544659422210443, + "grad_norm": 0.8148817420005798, + "learning_rate": 2.688103566781719e-07, + "loss": 0.087, + "step": 1204 + }, + { + "epoch": 2.556586270871985, + "grad_norm": 1.3565353155136108, + "learning_rate": 2.6629072564533007e-07, + "loss": 0.163, + "step": 1205 + }, + { + "epoch": 2.558706599522926, + "grad_norm": 0.799563467502594, + "learning_rate": 2.6378229442801163e-07, + "loss": 0.2213, + "step": 1206 + }, + { + "epoch": 2.560826928173867, + "grad_norm": 2.457230806350708, + "learning_rate": 2.6128507560348626e-07, + "loss": 0.1643, + "step": 1207 + }, + { + "epoch": 2.562947256824808, + "grad_norm": 1.6923904418945312, + "learning_rate": 2.5879908169280653e-07, + "loss": 0.1321, + "step": 1208 + }, + { + "epoch": 2.5650675854757488, + "grad_norm": 0.8046866655349731, + "learning_rate": 2.563243251607433e-07, + "loss": 0.1203, + "step": 1209 + }, + { + "epoch": 2.5671879141266896, + "grad_norm": 1.798595905303955, + "learning_rate": 2.538608184157229e-07, + "loss": 0.1767, + "step": 1210 + }, + { + "epoch": 2.5693082427776304, + "grad_norm": 0.4894849359989166, + "learning_rate": 2.5140857380976436e-07, + "loss": 0.1699, + "step": 1211 + }, + { + "epoch": 2.571428571428571, + "grad_norm": 0.8975478410720825, + "learning_rate": 2.489676036384192e-07, + "loss": 0.1116, + "step": 1212 + }, + { + "epoch": 2.5735489000795124, + "grad_norm": 0.9097894430160522, + "learning_rate": 2.4653792014070923e-07, + "loss": 0.1551, + "step": 1213 + }, + { + "epoch": 2.5756692287304532, + "grad_norm": 1.2728402614593506, + "learning_rate": 2.441195354990644e-07, + "loss": 0.1659, + "step": 1214 + }, + { + "epoch": 2.577789557381394, + "grad_norm": 0.8073611259460449, + "learning_rate": 2.4171246183926247e-07, + "loss": 0.1267, + "step": 1215 + }, + { + "epoch": 2.5799098860323353, + "grad_norm": 1.5247647762298584, + "learning_rate": 2.393167112303668e-07, + "loss": 0.2032, + "step": 1216 + }, + { + "epoch": 2.582030214683276, + "grad_norm": 1.960932970046997, + "learning_rate": 2.3693229568466952e-07, + "loss": 0.1342, + "step": 1217 + }, + { + "epoch": 2.584150543334217, + "grad_norm": 1.18437659740448, + "learning_rate": 2.345592271576261e-07, + "loss": 0.2205, + "step": 1218 + }, + { + "epoch": 2.5862708719851577, + "grad_norm": 1.630253791809082, + "learning_rate": 2.3219751754779862e-07, + "loss": 0.1616, + "step": 1219 + }, + { + "epoch": 2.5883912006360985, + "grad_norm": 1.5184342861175537, + "learning_rate": 2.2984717869679762e-07, + "loss": 0.0837, + "step": 1220 + }, + { + "epoch": 2.5905115292870393, + "grad_norm": 1.1323899030685425, + "learning_rate": 2.2750822238921861e-07, + "loss": 0.1858, + "step": 1221 + }, + { + "epoch": 2.59263185793798, + "grad_norm": 1.345180869102478, + "learning_rate": 2.251806603525855e-07, + "loss": 0.1615, + "step": 1222 + }, + { + "epoch": 2.5947521865889214, + "grad_norm": 2.1184494495391846, + "learning_rate": 2.228645042572908e-07, + "loss": 0.1641, + "step": 1223 + }, + { + "epoch": 2.596872515239862, + "grad_norm": 1.658331274986267, + "learning_rate": 2.2055976571653953e-07, + "loss": 0.1021, + "step": 1224 + }, + { + "epoch": 2.598992843890803, + "grad_norm": 1.2527090311050415, + "learning_rate": 2.1826645628628712e-07, + "loss": 0.1784, + "step": 1225 + }, + { + "epoch": 2.6011131725417442, + "grad_norm": 1.1310408115386963, + "learning_rate": 2.1598458746518448e-07, + "loss": 0.099, + "step": 1226 + }, + { + "epoch": 2.603233501192685, + "grad_norm": 1.2051087617874146, + "learning_rate": 2.1371417069451867e-07, + "loss": 0.1403, + "step": 1227 + }, + { + "epoch": 2.605353829843626, + "grad_norm": 1.2487993240356445, + "learning_rate": 2.1145521735815716e-07, + "loss": 0.0802, + "step": 1228 + }, + { + "epoch": 2.6074741584945667, + "grad_norm": 1.7651934623718262, + "learning_rate": 2.092077387824884e-07, + "loss": 0.2204, + "step": 1229 + }, + { + "epoch": 2.6095944871455075, + "grad_norm": 1.2847148180007935, + "learning_rate": 2.0697174623636795e-07, + "loss": 0.2012, + "step": 1230 + }, + { + "epoch": 2.6117148157964483, + "grad_norm": 1.5150816440582275, + "learning_rate": 2.0474725093105857e-07, + "loss": 0.1189, + "step": 1231 + }, + { + "epoch": 2.613835144447389, + "grad_norm": 2.1295809745788574, + "learning_rate": 2.025342640201783e-07, + "loss": 0.1462, + "step": 1232 + }, + { + "epoch": 2.6159554730983303, + "grad_norm": 2.1882126331329346, + "learning_rate": 2.003327965996399e-07, + "loss": 0.1963, + "step": 1233 + }, + { + "epoch": 2.618075801749271, + "grad_norm": 0.8546215891838074, + "learning_rate": 1.981428597075985e-07, + "loss": 0.1338, + "step": 1234 + }, + { + "epoch": 2.620196130400212, + "grad_norm": 2.6739611625671387, + "learning_rate": 1.9596446432439465e-07, + "loss": 0.1657, + "step": 1235 + }, + { + "epoch": 2.622316459051153, + "grad_norm": 1.686671495437622, + "learning_rate": 1.9379762137250069e-07, + "loss": 0.1489, + "step": 1236 + }, + { + "epoch": 2.624436787702094, + "grad_norm": 1.1274560689926147, + "learning_rate": 1.9164234171646423e-07, + "loss": 0.16, + "step": 1237 + }, + { + "epoch": 2.626557116353035, + "grad_norm": 1.799912691116333, + "learning_rate": 1.894986361628548e-07, + "loss": 0.149, + "step": 1238 + }, + { + "epoch": 2.6286774450039756, + "grad_norm": 0.9930972456932068, + "learning_rate": 1.8736651546020946e-07, + "loss": 0.1035, + "step": 1239 + }, + { + "epoch": 2.6307977736549164, + "grad_norm": 2.4395933151245117, + "learning_rate": 1.852459902989784e-07, + "loss": 0.1697, + "step": 1240 + }, + { + "epoch": 2.632918102305857, + "grad_norm": 1.3282368183135986, + "learning_rate": 1.8313707131147217e-07, + "loss": 0.1162, + "step": 1241 + }, + { + "epoch": 2.6350384309567985, + "grad_norm": 0.9472673535346985, + "learning_rate": 1.8103976907180798e-07, + "loss": 0.1021, + "step": 1242 + }, + { + "epoch": 2.6371587596077393, + "grad_norm": 1.8185752630233765, + "learning_rate": 1.789540940958573e-07, + "loss": 0.1861, + "step": 1243 + }, + { + "epoch": 2.63927908825868, + "grad_norm": 3.4913649559020996, + "learning_rate": 1.768800568411913e-07, + "loss": 0.1493, + "step": 1244 + }, + { + "epoch": 2.641399416909621, + "grad_norm": 1.3419857025146484, + "learning_rate": 1.7481766770703013e-07, + "loss": 0.1817, + "step": 1245 + }, + { + "epoch": 2.643519745560562, + "grad_norm": 1.4055255651474, + "learning_rate": 1.7276693703419058e-07, + "loss": 0.1297, + "step": 1246 + }, + { + "epoch": 2.645640074211503, + "grad_norm": 0.5878762006759644, + "learning_rate": 1.7072787510503313e-07, + "loss": 0.171, + "step": 1247 + }, + { + "epoch": 2.6477604028624437, + "grad_norm": 1.682094931602478, + "learning_rate": 1.6870049214341266e-07, + "loss": 0.2401, + "step": 1248 + }, + { + "epoch": 2.6498807315133845, + "grad_norm": 1.5442759990692139, + "learning_rate": 1.6668479831462498e-07, + "loss": 0.1526, + "step": 1249 + }, + { + "epoch": 2.6520010601643254, + "grad_norm": 2.29052734375, + "learning_rate": 1.6468080372535472e-07, + "loss": 0.1687, + "step": 1250 + }, + { + "epoch": 2.654121388815266, + "grad_norm": 1.219740390777588, + "learning_rate": 1.6268851842362988e-07, + "loss": 0.1425, + "step": 1251 + }, + { + "epoch": 2.6562417174662074, + "grad_norm": 0.8430941700935364, + "learning_rate": 1.607079523987662e-07, + "loss": 0.1047, + "step": 1252 + }, + { + "epoch": 2.658362046117148, + "grad_norm": 0.7257691621780396, + "learning_rate": 1.5873911558131866e-07, + "loss": 0.0906, + "step": 1253 + }, + { + "epoch": 2.660482374768089, + "grad_norm": 2.1663389205932617, + "learning_rate": 1.5678201784303293e-07, + "loss": 0.2841, + "step": 1254 + }, + { + "epoch": 2.66260270341903, + "grad_norm": 3.093027114868164, + "learning_rate": 1.548366689967948e-07, + "loss": 0.189, + "step": 1255 + }, + { + "epoch": 2.664723032069971, + "grad_norm": 1.9395819902420044, + "learning_rate": 1.52903078796581e-07, + "loss": 0.1188, + "step": 1256 + }, + { + "epoch": 2.666843360720912, + "grad_norm": 2.172022819519043, + "learning_rate": 1.5098125693741027e-07, + "loss": 0.1719, + "step": 1257 + }, + { + "epoch": 2.6689636893718527, + "grad_norm": 1.5533020496368408, + "learning_rate": 1.490712130552946e-07, + "loss": 0.1993, + "step": 1258 + }, + { + "epoch": 2.6710840180227935, + "grad_norm": 1.4032930135726929, + "learning_rate": 1.471729567271929e-07, + "loss": 0.0885, + "step": 1259 + }, + { + "epoch": 2.6732043466737343, + "grad_norm": 1.226884365081787, + "learning_rate": 1.4528649747095863e-07, + "loss": 0.1655, + "step": 1260 + }, + { + "epoch": 2.675324675324675, + "grad_norm": 0.9834424257278442, + "learning_rate": 1.4341184474529646e-07, + "loss": 0.1801, + "step": 1261 + }, + { + "epoch": 2.6774450039756164, + "grad_norm": 0.732979416847229, + "learning_rate": 1.4154900794971337e-07, + "loss": 0.094, + "step": 1262 + }, + { + "epoch": 2.679565332626557, + "grad_norm": 1.6163511276245117, + "learning_rate": 1.3969799642447047e-07, + "loss": 0.1391, + "step": 1263 + }, + { + "epoch": 2.681685661277498, + "grad_norm": 2.8434619903564453, + "learning_rate": 1.378588194505373e-07, + "loss": 0.1501, + "step": 1264 + }, + { + "epoch": 2.6838059899284388, + "grad_norm": 1.1843012571334839, + "learning_rate": 1.3603148624954488e-07, + "loss": 0.1566, + "step": 1265 + }, + { + "epoch": 2.68592631857938, + "grad_norm": 2.1769988536834717, + "learning_rate": 1.3421600598373886e-07, + "loss": 0.2451, + "step": 1266 + }, + { + "epoch": 2.688046647230321, + "grad_norm": 1.3834940195083618, + "learning_rate": 1.3241238775593634e-07, + "loss": 0.1454, + "step": 1267 + }, + { + "epoch": 2.6901669758812616, + "grad_norm": 1.287031650543213, + "learning_rate": 1.306206406094762e-07, + "loss": 0.1908, + "step": 1268 + }, + { + "epoch": 2.6922873045322024, + "grad_norm": 0.7013579607009888, + "learning_rate": 1.2884077352817659e-07, + "loss": 0.1143, + "step": 1269 + }, + { + "epoch": 2.6944076331831432, + "grad_norm": 2.7400264739990234, + "learning_rate": 1.2707279543628853e-07, + "loss": 0.1197, + "step": 1270 + }, + { + "epoch": 2.696527961834084, + "grad_norm": 0.6707156300544739, + "learning_rate": 1.2531671519845218e-07, + "loss": 0.1989, + "step": 1271 + }, + { + "epoch": 2.6986482904850253, + "grad_norm": 1.2751717567443848, + "learning_rate": 1.2357254161965176e-07, + "loss": 0.1403, + "step": 1272 + }, + { + "epoch": 2.700768619135966, + "grad_norm": 2.0241830348968506, + "learning_rate": 1.2184028344517096e-07, + "loss": 0.2304, + "step": 1273 + }, + { + "epoch": 2.702888947786907, + "grad_norm": 1.743528127670288, + "learning_rate": 1.2011994936055066e-07, + "loss": 0.1451, + "step": 1274 + }, + { + "epoch": 2.7050092764378477, + "grad_norm": 0.3977453410625458, + "learning_rate": 1.1841154799154376e-07, + "loss": 0.0898, + "step": 1275 + }, + { + "epoch": 2.707129605088789, + "grad_norm": 2.3948724269866943, + "learning_rate": 1.1671508790407238e-07, + "loss": 0.1182, + "step": 1276 + }, + { + "epoch": 2.7092499337397298, + "grad_norm": 1.9363933801651, + "learning_rate": 1.1503057760418518e-07, + "loss": 0.1747, + "step": 1277 + }, + { + "epoch": 2.7113702623906706, + "grad_norm": 2.442246198654175, + "learning_rate": 1.1335802553801512e-07, + "loss": 0.1696, + "step": 1278 + }, + { + "epoch": 2.7134905910416114, + "grad_norm": 1.0210362672805786, + "learning_rate": 1.1169744009173588e-07, + "loss": 0.1617, + "step": 1279 + }, + { + "epoch": 2.715610919692552, + "grad_norm": 1.444462776184082, + "learning_rate": 1.1004882959152085e-07, + "loss": 0.1001, + "step": 1280 + }, + { + "epoch": 2.717731248343493, + "grad_norm": 1.7707880735397339, + "learning_rate": 1.0841220230350142e-07, + "loss": 0.1711, + "step": 1281 + }, + { + "epoch": 2.7198515769944343, + "grad_norm": 1.8543199300765991, + "learning_rate": 1.0678756643372423e-07, + "loss": 0.0921, + "step": 1282 + }, + { + "epoch": 2.721971905645375, + "grad_norm": 1.4447288513183594, + "learning_rate": 1.0517493012811159e-07, + "loss": 0.1551, + "step": 1283 + }, + { + "epoch": 2.724092234296316, + "grad_norm": 1.2040534019470215, + "learning_rate": 1.0357430147242026e-07, + "loss": 0.1658, + "step": 1284 + }, + { + "epoch": 2.7262125629472567, + "grad_norm": 1.268929123878479, + "learning_rate": 1.0198568849219964e-07, + "loss": 0.1094, + "step": 1285 + }, + { + "epoch": 2.728332891598198, + "grad_norm": 1.3716996908187866, + "learning_rate": 1.0040909915275399e-07, + "loss": 0.2643, + "step": 1286 + }, + { + "epoch": 2.7304532202491387, + "grad_norm": 1.3784637451171875, + "learning_rate": 9.884454135910021e-08, + "loss": 0.0869, + "step": 1287 + }, + { + "epoch": 2.7325735489000795, + "grad_norm": 0.7445333003997803, + "learning_rate": 9.729202295592877e-08, + "loss": 0.1214, + "step": 1288 + }, + { + "epoch": 2.7346938775510203, + "grad_norm": 1.653314232826233, + "learning_rate": 9.575155172756506e-08, + "loss": 0.2651, + "step": 1289 + }, + { + "epoch": 2.736814206201961, + "grad_norm": 1.1880884170532227, + "learning_rate": 9.422313539793032e-08, + "loss": 0.0823, + "step": 1290 + }, + { + "epoch": 2.738934534852902, + "grad_norm": 1.2698768377304077, + "learning_rate": 9.270678163050218e-08, + "loss": 0.1873, + "step": 1291 + }, + { + "epoch": 2.741054863503843, + "grad_norm": 1.7306122779846191, + "learning_rate": 9.120249802827525e-08, + "loss": 0.2122, + "step": 1292 + }, + { + "epoch": 2.743175192154784, + "grad_norm": 1.6289342641830444, + "learning_rate": 8.971029213372729e-08, + "loss": 0.1604, + "step": 1293 + }, + { + "epoch": 2.745295520805725, + "grad_norm": 1.374562382698059, + "learning_rate": 8.823017142877587e-08, + "loss": 0.1293, + "step": 1294 + }, + { + "epoch": 2.747415849456666, + "grad_norm": 1.2182096242904663, + "learning_rate": 8.676214333474458e-08, + "loss": 0.1202, + "step": 1295 + }, + { + "epoch": 2.749536178107607, + "grad_norm": 0.7654268741607666, + "learning_rate": 8.530621521232435e-08, + "loss": 0.163, + "step": 1296 + }, + { + "epoch": 2.7516565067585477, + "grad_norm": 1.4261541366577148, + "learning_rate": 8.386239436153742e-08, + "loss": 0.1314, + "step": 1297 + }, + { + "epoch": 2.7537768354094885, + "grad_norm": 0.9270122647285461, + "learning_rate": 8.243068802169906e-08, + "loss": 0.1117, + "step": 1298 + }, + { + "epoch": 2.7558971640604293, + "grad_norm": 1.9634398221969604, + "learning_rate": 8.101110337138369e-08, + "loss": 0.2353, + "step": 1299 + }, + { + "epoch": 2.75801749271137, + "grad_norm": 1.8488718271255493, + "learning_rate": 7.96036475283865e-08, + "loss": 0.1271, + "step": 1300 + }, + { + "epoch": 2.760137821362311, + "grad_norm": 0.47494515776634216, + "learning_rate": 7.820832754968976e-08, + "loss": 0.1141, + "step": 1301 + }, + { + "epoch": 2.762258150013252, + "grad_norm": 1.7033765316009521, + "learning_rate": 7.682515043142602e-08, + "loss": 0.1758, + "step": 1302 + }, + { + "epoch": 2.764378478664193, + "grad_norm": 1.3400825262069702, + "learning_rate": 7.545412310884347e-08, + "loss": 0.0946, + "step": 1303 + }, + { + "epoch": 2.7664988073151338, + "grad_norm": 1.8070900440216064, + "learning_rate": 7.409525245627103e-08, + "loss": 0.1267, + "step": 1304 + }, + { + "epoch": 2.768619135966075, + "grad_norm": 1.3982330560684204, + "learning_rate": 7.27485452870852e-08, + "loss": 0.1801, + "step": 1305 + }, + { + "epoch": 2.770739464617016, + "grad_norm": 1.0061707496643066, + "learning_rate": 7.141400835367379e-08, + "loss": 0.165, + "step": 1306 + }, + { + "epoch": 2.7728597932679566, + "grad_norm": 0.810421884059906, + "learning_rate": 7.009164834740318e-08, + "loss": 0.1933, + "step": 1307 + }, + { + "epoch": 2.7749801219188974, + "grad_norm": 4.0556535720825195, + "learning_rate": 6.878147189858464e-08, + "loss": 0.1828, + "step": 1308 + }, + { + "epoch": 2.7771004505698382, + "grad_norm": 1.9069404602050781, + "learning_rate": 6.748348557644169e-08, + "loss": 0.1831, + "step": 1309 + }, + { + "epoch": 2.779220779220779, + "grad_norm": 1.4549925327301025, + "learning_rate": 6.619769588907588e-08, + "loss": 0.2365, + "step": 1310 + }, + { + "epoch": 2.78134110787172, + "grad_norm": 1.3765535354614258, + "learning_rate": 6.492410928343545e-08, + "loss": 0.1281, + "step": 1311 + }, + { + "epoch": 2.783461436522661, + "grad_norm": 1.1901353597640991, + "learning_rate": 6.366273214528124e-08, + "loss": 0.1193, + "step": 1312 + }, + { + "epoch": 2.785581765173602, + "grad_norm": 0.7537523508071899, + "learning_rate": 6.241357079915771e-08, + "loss": 0.0859, + "step": 1313 + }, + { + "epoch": 2.7877020938245427, + "grad_norm": 2.4557838439941406, + "learning_rate": 6.117663150835756e-08, + "loss": 0.1035, + "step": 1314 + }, + { + "epoch": 2.789822422475484, + "grad_norm": 1.539157509803772, + "learning_rate": 5.995192047489301e-08, + "loss": 0.1114, + "step": 1315 + }, + { + "epoch": 2.7919427511264248, + "grad_norm": 0.7973776459693909, + "learning_rate": 5.8739443839463675e-08, + "loss": 0.0927, + "step": 1316 + }, + { + "epoch": 2.7940630797773656, + "grad_norm": 1.1481491327285767, + "learning_rate": 5.7539207681426015e-08, + "loss": 0.1889, + "step": 1317 + }, + { + "epoch": 2.7961834084283064, + "grad_norm": 1.7523208856582642, + "learning_rate": 5.635121801876253e-08, + "loss": 0.201, + "step": 1318 + }, + { + "epoch": 2.798303737079247, + "grad_norm": 0.6877788305282593, + "learning_rate": 5.5175480808051515e-08, + "loss": 0.1615, + "step": 1319 + }, + { + "epoch": 2.800424065730188, + "grad_norm": 7.792228698730469, + "learning_rate": 5.401200194443873e-08, + "loss": 0.1195, + "step": 1320 + }, + { + "epoch": 2.8025443943811292, + "grad_norm": 1.1625345945358276, + "learning_rate": 5.2860787261605485e-08, + "loss": 0.1593, + "step": 1321 + }, + { + "epoch": 2.80466472303207, + "grad_norm": 1.4142205715179443, + "learning_rate": 5.172184253174034e-08, + "loss": 0.0893, + "step": 1322 + }, + { + "epoch": 2.806785051683011, + "grad_norm": 2.7474701404571533, + "learning_rate": 5.059517346551107e-08, + "loss": 0.2956, + "step": 1323 + }, + { + "epoch": 2.8089053803339517, + "grad_norm": 2.946167469024658, + "learning_rate": 4.948078571203496e-08, + "loss": 0.1717, + "step": 1324 + }, + { + "epoch": 2.811025708984893, + "grad_norm": 1.3838998079299927, + "learning_rate": 4.83786848588505e-08, + "loss": 0.0977, + "step": 1325 + }, + { + "epoch": 2.8131460376358337, + "grad_norm": 1.9812895059585571, + "learning_rate": 4.728887643189073e-08, + "loss": 0.1553, + "step": 1326 + }, + { + "epoch": 2.8152663662867745, + "grad_norm": 2.396117687225342, + "learning_rate": 4.621136589545272e-08, + "loss": 0.1686, + "step": 1327 + }, + { + "epoch": 2.8173866949377153, + "grad_norm": 1.9404491186141968, + "learning_rate": 4.5146158652173696e-08, + "loss": 0.1846, + "step": 1328 + }, + { + "epoch": 2.819507023588656, + "grad_norm": 0.7136148810386658, + "learning_rate": 4.4093260043001626e-08, + "loss": 0.1363, + "step": 1329 + }, + { + "epoch": 2.821627352239597, + "grad_norm": 1.5374301671981812, + "learning_rate": 4.305267534716828e-08, + "loss": 0.1339, + "step": 1330 + }, + { + "epoch": 2.823747680890538, + "grad_norm": 1.3492411375045776, + "learning_rate": 4.202440978216399e-08, + "loss": 0.1288, + "step": 1331 + }, + { + "epoch": 2.825868009541479, + "grad_norm": 1.5458908081054688, + "learning_rate": 4.1008468503711266e-08, + "loss": 0.1397, + "step": 1332 + }, + { + "epoch": 2.82798833819242, + "grad_norm": 0.7465994358062744, + "learning_rate": 4.000485660573872e-08, + "loss": 0.1248, + "step": 1333 + }, + { + "epoch": 2.8301086668433606, + "grad_norm": 1.4333218336105347, + "learning_rate": 3.9013579120354696e-08, + "loss": 0.1981, + "step": 1334 + }, + { + "epoch": 2.832228995494302, + "grad_norm": 1.3847651481628418, + "learning_rate": 3.803464101782367e-08, + "loss": 0.1387, + "step": 1335 + }, + { + "epoch": 2.8343493241452427, + "grad_norm": 1.7092586755752563, + "learning_rate": 3.706804720653962e-08, + "loss": 0.1013, + "step": 1336 + }, + { + "epoch": 2.8364696527961835, + "grad_norm": 0.910914957523346, + "learning_rate": 3.611380253300267e-08, + "loss": 0.2936, + "step": 1337 + }, + { + "epoch": 2.8385899814471243, + "grad_norm": 0.823289692401886, + "learning_rate": 3.517191178179474e-08, + "loss": 0.1551, + "step": 1338 + }, + { + "epoch": 2.840710310098065, + "grad_norm": 1.4775550365447998, + "learning_rate": 3.4242379675555046e-08, + "loss": 0.1314, + "step": 1339 + }, + { + "epoch": 2.842830638749006, + "grad_norm": 1.5959218740463257, + "learning_rate": 3.332521087495627e-08, + "loss": 0.1936, + "step": 1340 + }, + { + "epoch": 2.844950967399947, + "grad_norm": 1.1180788278579712, + "learning_rate": 3.242040997868123e-08, + "loss": 0.1696, + "step": 1341 + }, + { + "epoch": 2.847071296050888, + "grad_norm": 1.3411235809326172, + "learning_rate": 3.1527981523400974e-08, + "loss": 0.0762, + "step": 1342 + }, + { + "epoch": 2.8491916247018287, + "grad_norm": 1.4830942153930664, + "learning_rate": 3.064792998375032e-08, + "loss": 0.1341, + "step": 1343 + }, + { + "epoch": 2.8513119533527695, + "grad_norm": 1.154703140258789, + "learning_rate": 2.9780259772307362e-08, + "loss": 0.1482, + "step": 1344 + }, + { + "epoch": 2.853432282003711, + "grad_norm": 2.1193814277648926, + "learning_rate": 2.8924975239568444e-08, + "loss": 0.136, + "step": 1345 + }, + { + "epoch": 2.8555526106546516, + "grad_norm": 1.6052285432815552, + "learning_rate": 2.8082080673929312e-08, + "loss": 0.1296, + "step": 1346 + }, + { + "epoch": 2.8576729393055924, + "grad_norm": 1.887386441230774, + "learning_rate": 2.7251580301662916e-08, + "loss": 0.1119, + "step": 1347 + }, + { + "epoch": 2.859793267956533, + "grad_norm": 2.486104726791382, + "learning_rate": 2.643347828689663e-08, + "loss": 0.1892, + "step": 1348 + }, + { + "epoch": 2.861913596607474, + "grad_norm": 1.018723726272583, + "learning_rate": 2.562777873159311e-08, + "loss": 0.1666, + "step": 1349 + }, + { + "epoch": 2.864033925258415, + "grad_norm": 1.8284214735031128, + "learning_rate": 2.4834485675528653e-08, + "loss": 0.1364, + "step": 1350 + }, + { + "epoch": 2.866154253909356, + "grad_norm": 1.6964608430862427, + "learning_rate": 2.4053603096274027e-08, + "loss": 0.1658, + "step": 1351 + }, + { + "epoch": 2.868274582560297, + "grad_norm": 2.2789952754974365, + "learning_rate": 2.3285134909173113e-08, + "loss": 0.1677, + "step": 1352 + }, + { + "epoch": 2.8703949112112377, + "grad_norm": 1.1281884908676147, + "learning_rate": 2.2529084967324867e-08, + "loss": 0.1026, + "step": 1353 + }, + { + "epoch": 2.8725152398621785, + "grad_norm": 1.7842395305633545, + "learning_rate": 2.178545706156221e-08, + "loss": 0.1761, + "step": 1354 + }, + { + "epoch": 2.8746355685131197, + "grad_norm": 4.740082263946533, + "learning_rate": 2.105425492043539e-08, + "loss": 0.2169, + "step": 1355 + }, + { + "epoch": 2.8767558971640605, + "grad_norm": 1.7496134042739868, + "learning_rate": 2.0335482210190327e-08, + "loss": 0.199, + "step": 1356 + }, + { + "epoch": 2.8788762258150014, + "grad_norm": 1.1270558834075928, + "learning_rate": 1.962914253475251e-08, + "loss": 0.1348, + "step": 1357 + }, + { + "epoch": 2.880996554465942, + "grad_norm": 1.2198997735977173, + "learning_rate": 1.893523943570841e-08, + "loss": 0.0994, + "step": 1358 + }, + { + "epoch": 2.883116883116883, + "grad_norm": 1.9801288843154907, + "learning_rate": 1.8253776392287147e-08, + "loss": 0.1815, + "step": 1359 + }, + { + "epoch": 2.8852372117678238, + "grad_norm": 1.704171061515808, + "learning_rate": 1.7584756821343864e-08, + "loss": 0.1956, + "step": 1360 + }, + { + "epoch": 2.887357540418765, + "grad_norm": 1.9090226888656616, + "learning_rate": 1.692818407734165e-08, + "loss": 0.1832, + "step": 1361 + }, + { + "epoch": 2.889477869069706, + "grad_norm": 1.2632900476455688, + "learning_rate": 1.6284061452335464e-08, + "loss": 0.2045, + "step": 1362 + }, + { + "epoch": 2.8915981977206466, + "grad_norm": 1.6799594163894653, + "learning_rate": 1.565239217595549e-08, + "loss": 0.1563, + "step": 1363 + }, + { + "epoch": 2.8937185263715874, + "grad_norm": 0.9902015924453735, + "learning_rate": 1.5033179415390176e-08, + "loss": 0.1395, + "step": 1364 + }, + { + "epoch": 2.8958388550225287, + "grad_norm": 1.852407455444336, + "learning_rate": 1.4426426275372385e-08, + "loss": 0.1354, + "step": 1365 + }, + { + "epoch": 2.8979591836734695, + "grad_norm": 1.5521894693374634, + "learning_rate": 1.3832135798160783e-08, + "loss": 0.1807, + "step": 1366 + }, + { + "epoch": 2.9000795123244103, + "grad_norm": 4.004573822021484, + "learning_rate": 1.3250310963527358e-08, + "loss": 0.2193, + "step": 1367 + }, + { + "epoch": 2.902199840975351, + "grad_norm": 1.0895882844924927, + "learning_rate": 1.268095468874131e-08, + "loss": 0.1427, + "step": 1368 + }, + { + "epoch": 2.904320169626292, + "grad_norm": 1.187664270401001, + "learning_rate": 1.2124069828554075e-08, + "loss": 0.1666, + "step": 1369 + }, + { + "epoch": 2.9064404982772327, + "grad_norm": 1.6270695924758911, + "learning_rate": 1.1579659175185998e-08, + "loss": 0.1087, + "step": 1370 + }, + { + "epoch": 2.908560826928174, + "grad_norm": 1.6206939220428467, + "learning_rate": 1.1047725458310788e-08, + "loss": 0.1042, + "step": 1371 + }, + { + "epoch": 2.9106811555791148, + "grad_norm": 0.5481939315795898, + "learning_rate": 1.0528271345044139e-08, + "loss": 0.123, + "step": 1372 + }, + { + "epoch": 2.9128014842300556, + "grad_norm": 1.871779441833496, + "learning_rate": 1.0021299439927635e-08, + "loss": 0.2518, + "step": 1373 + }, + { + "epoch": 2.914921812880997, + "grad_norm": 1.5158265829086304, + "learning_rate": 9.526812284918196e-09, + "loss": 0.1938, + "step": 1374 + }, + { + "epoch": 2.9170421415319376, + "grad_norm": 1.6060808897018433, + "learning_rate": 9.044812359373933e-09, + "loss": 0.1524, + "step": 1375 + }, + { + "epoch": 2.9191624701828784, + "grad_norm": 1.282213807106018, + "learning_rate": 8.575302080041648e-09, + "loss": 0.0865, + "step": 1376 + }, + { + "epoch": 2.9212827988338192, + "grad_norm": 1.064220666885376, + "learning_rate": 8.118283801045179e-09, + "loss": 0.1245, + "step": 1377 + }, + { + "epoch": 2.92340312748476, + "grad_norm": 1.623093605041504, + "learning_rate": 7.673759813873749e-09, + "loss": 0.1392, + "step": 1378 + }, + { + "epoch": 2.925523456135701, + "grad_norm": 1.3206197023391724, + "learning_rate": 7.2417323473703005e-09, + "loss": 0.1392, + "step": 1379 + }, + { + "epoch": 2.9276437847866417, + "grad_norm": 1.0642672777175903, + "learning_rate": 6.8222035677195655e-09, + "loss": 0.1728, + "step": 1380 + }, + { + "epoch": 2.929764113437583, + "grad_norm": 1.2734618186950684, + "learning_rate": 6.415175578438626e-09, + "loss": 0.1577, + "step": 1381 + }, + { + "epoch": 2.9318844420885237, + "grad_norm": 1.2089275121688843, + "learning_rate": 6.0206504203652595e-09, + "loss": 0.1659, + "step": 1382 + }, + { + "epoch": 2.9340047707394645, + "grad_norm": 1.001374363899231, + "learning_rate": 5.638630071648221e-09, + "loss": 0.1507, + "step": 1383 + }, + { + "epoch": 2.936125099390406, + "grad_norm": 2.069044589996338, + "learning_rate": 5.2691164477367e-09, + "loss": 0.1365, + "step": 1384 + }, + { + "epoch": 2.9382454280413466, + "grad_norm": 1.3570106029510498, + "learning_rate": 4.9121114013719886e-09, + "loss": 0.1626, + "step": 1385 + }, + { + "epoch": 2.9403657566922874, + "grad_norm": 0.8516995906829834, + "learning_rate": 4.5676167225766625e-09, + "loss": 0.1482, + "step": 1386 + }, + { + "epoch": 2.942486085343228, + "grad_norm": 2.186077117919922, + "learning_rate": 4.2356341386468045e-09, + "loss": 0.1666, + "step": 1387 + }, + { + "epoch": 2.944606413994169, + "grad_norm": 1.2149814367294312, + "learning_rate": 3.916165314142295e-09, + "loss": 0.1035, + "step": 1388 + }, + { + "epoch": 2.94672674264511, + "grad_norm": 1.4955745935440063, + "learning_rate": 3.609211850879868e-09, + "loss": 0.1345, + "step": 1389 + }, + { + "epoch": 2.9488470712960506, + "grad_norm": 0.9449958801269531, + "learning_rate": 3.3147752879236773e-09, + "loss": 0.1287, + "step": 1390 + }, + { + "epoch": 2.950967399946992, + "grad_norm": 1.2510886192321777, + "learning_rate": 3.032857101578357e-09, + "loss": 0.1304, + "step": 1391 + }, + { + "epoch": 2.9530877285979327, + "grad_norm": 2.1328423023223877, + "learning_rate": 2.7634587053809723e-09, + "loss": 0.1966, + "step": 1392 + }, + { + "epoch": 2.9552080572488735, + "grad_norm": 2.7924039363861084, + "learning_rate": 2.5065814500951914e-09, + "loss": 0.16, + "step": 1393 + }, + { + "epoch": 2.9573283858998147, + "grad_norm": 2.112011671066284, + "learning_rate": 2.2622266237029565e-09, + "loss": 0.2442, + "step": 1394 + }, + { + "epoch": 2.9594487145507555, + "grad_norm": 1.9325287342071533, + "learning_rate": 2.030395451399214e-09, + "loss": 0.1084, + "step": 1395 + }, + { + "epoch": 2.9615690432016963, + "grad_norm": 1.0809413194656372, + "learning_rate": 1.8110890955849724e-09, + "loss": 0.1805, + "step": 1396 + }, + { + "epoch": 2.963689371852637, + "grad_norm": 1.6688867807388306, + "learning_rate": 1.6043086558623078e-09, + "loss": 0.1576, + "step": 1397 + }, + { + "epoch": 2.965809700503578, + "grad_norm": 1.1752701997756958, + "learning_rate": 1.4100551690279796e-09, + "loss": 0.1739, + "step": 1398 + }, + { + "epoch": 2.9679300291545188, + "grad_norm": 2.4213781356811523, + "learning_rate": 1.2283296090687125e-09, + "loss": 0.1755, + "step": 1399 + }, + { + "epoch": 2.97005035780546, + "grad_norm": 0.7826443314552307, + "learning_rate": 1.0591328871562e-09, + "loss": 0.1123, + "step": 1400 + }, + { + "epoch": 2.972170686456401, + "grad_norm": 1.7806673049926758, + "learning_rate": 9.024658516426643e-10, + "loss": 0.1952, + "step": 1401 + }, + { + "epoch": 2.9742910151073416, + "grad_norm": 1.3985880613327026, + "learning_rate": 7.583292880564142e-10, + "loss": 0.1802, + "step": 1402 + }, + { + "epoch": 2.9764113437582824, + "grad_norm": 0.9030689001083374, + "learning_rate": 6.267239190979601e-10, + "loss": 0.1862, + "step": 1403 + }, + { + "epoch": 2.9785316724092237, + "grad_norm": 1.05217707157135, + "learning_rate": 5.076504046364061e-10, + "loss": 0.1186, + "step": 1404 + }, + { + "epoch": 2.9806520010601645, + "grad_norm": 2.4997191429138184, + "learning_rate": 4.0110934170639603e-10, + "loss": 0.202, + "step": 1405 + }, + { + "epoch": 2.9827723297111053, + "grad_norm": 0.7951033711433411, + "learning_rate": 3.0710126450450574e-10, + "loss": 0.1106, + "step": 1406 + }, + { + "epoch": 2.984892658362046, + "grad_norm": 1.5203306674957275, + "learning_rate": 2.2562664438730008e-10, + "loss": 0.2274, + "step": 1407 + }, + { + "epoch": 2.987012987012987, + "grad_norm": 1.2033835649490356, + "learning_rate": 1.5668588986800237e-10, + "loss": 0.098, + "step": 1408 + }, + { + "epoch": 2.9891333156639277, + "grad_norm": 2.494394063949585, + "learning_rate": 1.0027934661593908e-10, + "loss": 0.1817, + "step": 1409 + }, + { + "epoch": 2.991253644314869, + "grad_norm": 1.0664846897125244, + "learning_rate": 5.640729745348683e-11, + "loss": 0.1669, + "step": 1410 + }, + { + "epoch": 2.9933739729658098, + "grad_norm": 0.9831266403198242, + "learning_rate": 2.5069962354684618e-11, + "loss": 0.1413, + "step": 1411 + }, + { + "epoch": 2.9954943016167506, + "grad_norm": 17.356966018676758, + "learning_rate": 6.267498444956222e-12, + "loss": 0.3418, + "step": 1412 + }, + { + "epoch": 2.9976146302676914, + "grad_norm": 1.7750447988510132, + "learning_rate": 0.0, + "loss": 0.1737, + "step": 1413 + } + ], + "logging_steps": 1, + "max_steps": 1413, + "num_input_tokens_seen": 0, + "num_train_epochs": 3, + "save_steps": 1000, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": true + }, + "attributes": {} + } + }, + "total_flos": 1.9412022010031636e+18, + "train_batch_size": 1, + "trial_name": null, + "trial_params": null +} diff --git a/rag_truth_hal_detection_model/checkpoint-1413/training_args.bin b/rag_truth_hal_detection_model/checkpoint-1413/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..7c2f22d4d5100bea19a9b524d6fe22f4b61ba2b8 --- /dev/null +++ b/rag_truth_hal_detection_model/checkpoint-1413/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8cba5214263bc92d48c42393a60c4f497265c69e8a26b939f349b78bea897898 +size 7160 diff --git a/rag_truth_hal_detection_model/checkpoint-1413/zero_to_fp32.py b/rag_truth_hal_detection_model/checkpoint-1413/zero_to_fp32.py new file mode 100644 index 0000000000000000000000000000000000000000..e69ecd9acb5a235ffbf927091051106d902b3d39 --- /dev/null +++ b/rag_truth_hal_detection_model/checkpoint-1413/zero_to_fp32.py @@ -0,0 +1,674 @@ +#!/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 1, 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 . output_dir/ +# or +# python zero_to_fp32.py . output_dir/ --safe_serialization + +import argparse +import torch +import glob +import math +import os +import re +import json +from tqdm import tqdm +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_dict = torch.load(f, map_location=device) + # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights + # and also handle the case where it was already removed by another helper script + state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None) + state_dicts.append(state_dict) + + 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, exclude_frozen_parameters): + """ + 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, + exclude_frozen_parameters) + elif zero_stage == 3: + return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states, + exclude_frozen_parameters) + + +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 _has_callable(obj, fn): + attr = getattr(obj, fn, None) + return callable(attr) + + +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() if _has_callable(shape, 'numel') else math.prod(shape) + 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, + exclude_frozen_parameters): + state_dict = OrderedDict() + + # buffers + buffers = zero_model_states[0].buffers + state_dict.update(buffers) + if debug: + print(f"added {len(buffers)} buffers") + + if not exclude_frozen_parameters: + _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 tqdm(param_shapes.items(), desc='Gathering Sharded Weights'): + 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, + exclude_frozen_parameters): + state_dict = OrderedDict() + + # buffers + buffers = zero_model_states[0].buffers + state_dict.update(buffers) + if debug: + print(f"added {len(buffers)} buffers") + + if not exclude_frozen_parameters: + _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, exclude_frozen_parameters=False): + """ + 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`` + - ``exclude_frozen_parameters``: exclude frozen parameters + + 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, exclude_frozen_parameters) + + +def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, + output_dir, + max_shard_size="5GB", + safe_serialization=False, + tag=None, + exclude_frozen_parameters=False): + """ + 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_dir``: directory to the pytorch fp32 state_dict output files + - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB + - ``safe_serialization``: whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`). + - ``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`` + - ``exclude_frozen_parameters``: exclude frozen parameters + """ + # Dependency pre-check + if safe_serialization: + try: + from safetensors.torch import save_file + except ImportError: + print('If you want to use `safe_serialization`, please `pip install safetensors`') + raise + if max_shard_size is not None: + try: + from huggingface_hub import split_torch_state_dict_into_shards + except ImportError: + print('If you want to use `max_shard_size`, please `pip install huggingface_hub`') + raise + + # Convert zero checkpoint to state_dict + state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters) + + # Shard the model if it is too big. + weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin" + if max_shard_size is not None: + filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors") + state_dict_split = split_torch_state_dict_into_shards(state_dict, + filename_pattern=filename_pattern, + max_shard_size=max_shard_size) + else: + from collections import namedtuple + StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"]) + state_dict_split = StateDictSplit(is_sharded=False, + filename_to_tensors={weights_name: list(state_dict.keys())}) + + # Save the model + filename_to_tensors = state_dict_split.filename_to_tensors.items() + for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"): + shard = {tensor: state_dict[tensor].contiguous() for tensor in tensors} + output_path = os.path.join(output_dir, shard_file) + if safe_serialization: + save_file(shard, output_path, metadata={"format": "pt"}) + else: + torch.save(shard, output_path) + + # Save index if sharded + if state_dict_split.is_sharded: + index = { + "metadata": state_dict_split.metadata, + "weight_map": state_dict_split.tensor_to_filename, + } + save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json" + save_index_file = os.path.join(output_dir, save_index_file) + with open(save_index_file, "w", encoding="utf-8") as f: + content = json.dumps(index, indent=2, sort_keys=True) + "\n" + f.write(content) + + +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_dir", + type=str, + help="directory to the pytorch fp32 state_dict output files" + "(e.g. path/checkpoint-12-output/)") + parser.add_argument( + "--max_shard_size", + type=str, + default="5GB", + help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size" + "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`" + "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances" + "without CPU OOM issues.") + parser.add_argument( + "--safe_serialization", + default=False, + action='store_true', + help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).") + parser.add_argument("-t", + "--tag", + type=str, + default=None, + help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1") + parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters") + 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_dir, + max_shard_size=args.max_shard_size, + safe_serialization=args.safe_serialization, + tag=args.tag, + exclude_frozen_parameters=args.exclude_frozen_parameters) diff --git a/rag_truth_hal_detection_model/config.json b/rag_truth_hal_detection_model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..f79ee026750c76a1b06a7152a3fca58830d69257 --- /dev/null +++ b/rag_truth_hal_detection_model/config.json @@ -0,0 +1,30 @@ +{ + "_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "eos_token_id": 128009, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 8192, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.46.1", + "use_cache": false, + "vocab_size": 128256 +} diff --git a/rag_truth_hal_detection_model/generation_config.json b/rag_truth_hal_detection_model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..db0ea5c7647aac3cdc0802b1e95a53d09351382a --- /dev/null +++ b/rag_truth_hal_detection_model/generation_config.json @@ -0,0 +1,12 @@ +{ + "bos_token_id": 128000, + "do_sample": true, + "eos_token_id": [ + 128001, + 128009 + ], + "max_length": 4096, + "temperature": 0.6, + "top_p": 0.9, + "transformers_version": "4.46.1" +} diff --git a/rag_truth_hal_detection_model/llamaboard_config.yaml b/rag_truth_hal_detection_model/llamaboard_config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..3df21bb0ddb7b408fc883fe016ce914ff639f8ac --- /dev/null +++ b/rag_truth_hal_detection_model/llamaboard_config.yaml @@ -0,0 +1,66 @@ +top.booster: auto +top.checkpoint_path: null +top.finetuning_type: full +top.model_name: Llama-3-8B-Instruct +top.quantization_bit: none +top.quantization_method: bitsandbytes +top.rope_scaling: none +top.template: llama3 +train.additional_target: '' +train.badam_mode: layer +train.badam_switch_interval: 50 +train.badam_switch_mode: ascending +train.badam_update_ratio: 0.05 +train.batch_size: 1 +train.compute_type: bf16 +train.create_new_adapter: false +train.cutoff_len: 4096 +train.dataset: +- train_hal_detection_1125 +train.dataset_dir: data +train.ds_offload: true +train.ds_stage: '2' +train.extra_args: '{"optim": "adamw_torch"}' +train.freeze_extra_modules: '' +train.freeze_trainable_layers: 2 +train.freeze_trainable_modules: all +train.galore_rank: 16 +train.galore_scale: 0.25 +train.galore_target: all +train.galore_update_interval: 200 +train.gradient_accumulation_steps: 8 +train.learning_rate: 5e-6 +train.logging_steps: 1 +train.lora_alpha: 16 +train.lora_dropout: 0 +train.lora_rank: 8 +train.lora_target: '' +train.loraplus_lr_ratio: 0 +train.lr_scheduler_type: cosine +train.mask_history: false +train.max_grad_norm: '1.0' +train.max_samples: '100000' +train.neat_packing: false +train.neftune_alpha: 0 +train.num_train_epochs: '3.0' +train.packing: false +train.ppo_score_norm: false +train.ppo_whiten_rewards: false +train.pref_beta: 0.1 +train.pref_ftx: 0 +train.pref_loss: sigmoid +train.report_to: false +train.resize_vocab: false +train.reward_model: null +train.save_steps: 1000 +train.shift_attn: false +train.train_on_prompt: false +train.training_stage: Supervised Fine-Tuning +train.use_badam: false +train.use_dora: false +train.use_galore: false +train.use_llama_pro: false +train.use_pissa: false +train.use_rslora: false +train.val_size: 0 +train.warmup_steps: 10 diff --git a/rag_truth_hal_detection_model/model-00001-of-00004.safetensors b/rag_truth_hal_detection_model/model-00001-of-00004.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..05b4f012dc56f55b5b637540e457ab80ccd30870 --- /dev/null +++ b/rag_truth_hal_detection_model/model-00001-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6dcbabfb5aa90e49da2f74b8cd606eca124c05b928a709f0cd0089f8de8f8ca +size 4976698672 diff --git a/rag_truth_hal_detection_model/model-00002-of-00004.safetensors b/rag_truth_hal_detection_model/model-00002-of-00004.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9d55e8b109089210358018dfcce8ac0a4fcf52f2 --- /dev/null +++ b/rag_truth_hal_detection_model/model-00002-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0835acd1f3b1bf1e719cf7031e92121f25e53758325b490785093185d1e4d6a +size 4999802720 diff --git a/rag_truth_hal_detection_model/model-00003-of-00004.safetensors b/rag_truth_hal_detection_model/model-00003-of-00004.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0908f389554f6ab9cbf67f7ef2edeb8a6d1797be --- /dev/null +++ b/rag_truth_hal_detection_model/model-00003-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:473a41b96d7ff16e2e4b502b7103abbd861bad929138990987618cb47dd098f1 +size 4915916176 diff --git a/rag_truth_hal_detection_model/model-00004-of-00004.safetensors b/rag_truth_hal_detection_model/model-00004-of-00004.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..17efbf01269845f06244546ce121b43167dc531f --- /dev/null +++ b/rag_truth_hal_detection_model/model-00004-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abc9304c6a0db86d38ce5a5b7b199fc900360e842415c16223714aaf76e30005 +size 1168138808 diff --git a/rag_truth_hal_detection_model/model.safetensors.index.json b/rag_truth_hal_detection_model/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..0fd8120f1c6acddc268ebc2583058efaf699a771 --- /dev/null +++ b/rag_truth_hal_detection_model/model.safetensors.index.json @@ -0,0 +1,298 @@ +{ + "metadata": { + "total_size": 16060522496 + }, + "weight_map": { + "lm_head.weight": "model-00004-of-00004.safetensors", + "model.embed_tokens.weight": "model-00001-of-00004.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.norm.weight": "model-00004-of-00004.safetensors" + } +} diff --git a/rag_truth_hal_detection_model/running_log.txt b/rag_truth_hal_detection_model/running_log.txt new file mode 100644 index 0000000000000000000000000000000000000000..62d01e3e207d193712e82b48f182c6fdceb6fc86 --- /dev/null +++ b/rag_truth_hal_detection_model/running_log.txt @@ -0,0 +1,3076 @@ +[INFO|2024-11-25 07:48:02] parser.py:355 >> Process rank: 0, device: cuda:0, n_gpu: 1, distributed training: True, compute dtype: torch.bfloat16 + +[INFO|2024-11-25 07:48:02] parser.py:355 >> Process rank: 3, device: cuda:3, n_gpu: 1, distributed training: True, compute dtype: torch.bfloat16 + +[INFO|2024-11-25 07:48:02] parser.py:355 >> Process rank: 2, device: cuda:2, n_gpu: 1, distributed training: True, compute dtype: torch.bfloat16 + +[INFO|2024-11-25 07:48:02] parser.py:355 >> Process rank: 1, device: cuda:1, n_gpu: 1, distributed training: True, compute dtype: torch.bfloat16 + +[INFO|2024-11-25 07:48:02] configuration_utils.py:679 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Meta-Llama-3-8B-Instruct/snapshots/5f0b02c75b57c5855da9ae460ce51323ea669d8a/config.json + +[INFO|2024-11-25 07:48:02] configuration_utils.py:746 >> Model config LlamaConfig { + "_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "eos_token_id": 128009, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 8192, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.46.1", + "use_cache": true, + "vocab_size": 128256 +} + + +[INFO|2024-11-25 07:48:03] tokenization_utils_base.py:2211 >> loading file tokenizer.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Meta-Llama-3-8B-Instruct/snapshots/5f0b02c75b57c5855da9ae460ce51323ea669d8a/tokenizer.json + +[INFO|2024-11-25 07:48:03] tokenization_utils_base.py:2211 >> loading file tokenizer.model from cache at None + +[INFO|2024-11-25 07:48:03] tokenization_utils_base.py:2211 >> loading file added_tokens.json from cache at None + +[INFO|2024-11-25 07:48:03] tokenization_utils_base.py:2211 >> loading file special_tokens_map.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Meta-Llama-3-8B-Instruct/snapshots/5f0b02c75b57c5855da9ae460ce51323ea669d8a/special_tokens_map.json + +[INFO|2024-11-25 07:48:03] tokenization_utils_base.py:2211 >> loading file tokenizer_config.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Meta-Llama-3-8B-Instruct/snapshots/5f0b02c75b57c5855da9ae460ce51323ea669d8a/tokenizer_config.json + +[INFO|2024-11-25 07:48:03] tokenization_utils_base.py:2475 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. + +[INFO|2024-11-25 07:48:04] configuration_utils.py:679 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Meta-Llama-3-8B-Instruct/snapshots/5f0b02c75b57c5855da9ae460ce51323ea669d8a/config.json + +[INFO|2024-11-25 07:48:04] configuration_utils.py:746 >> Model config LlamaConfig { + "_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "eos_token_id": 128009, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 8192, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.46.1", + "use_cache": true, + "vocab_size": 128256 +} + + +[INFO|2024-11-25 07:48:05] tokenization_utils_base.py:2211 >> loading file tokenizer.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Meta-Llama-3-8B-Instruct/snapshots/5f0b02c75b57c5855da9ae460ce51323ea669d8a/tokenizer.json + +[INFO|2024-11-25 07:48:05] tokenization_utils_base.py:2211 >> loading file tokenizer.model from cache at None + +[INFO|2024-11-25 07:48:05] tokenization_utils_base.py:2211 >> loading file added_tokens.json from cache at None + +[INFO|2024-11-25 07:48:05] tokenization_utils_base.py:2211 >> loading file special_tokens_map.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Meta-Llama-3-8B-Instruct/snapshots/5f0b02c75b57c5855da9ae460ce51323ea669d8a/special_tokens_map.json + +[INFO|2024-11-25 07:48:05] tokenization_utils_base.py:2211 >> loading file tokenizer_config.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Meta-Llama-3-8B-Instruct/snapshots/5f0b02c75b57c5855da9ae460ce51323ea669d8a/tokenizer_config.json + +[INFO|2024-11-25 07:48:05] tokenization_utils_base.py:2475 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. + +[INFO|2024-11-25 07:48:05] logging.py:157 >> Replace eos token: <|eot_id|> + +[INFO|2024-11-25 07:48:05] logging.py:157 >> Add pad token: <|eot_id|> + +[INFO|2024-11-25 07:48:05] logging.py:157 >> Loading dataset ragtruth_base_data/train_hallucination_detection_1125.json... + +[INFO|2024-11-25 07:48:15] configuration_utils.py:679 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Meta-Llama-3-8B-Instruct/snapshots/5f0b02c75b57c5855da9ae460ce51323ea669d8a/config.json + +[INFO|2024-11-25 07:48:15] configuration_utils.py:746 >> Model config LlamaConfig { + "_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "eos_token_id": 128009, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 8192, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.46.1", + "use_cache": true, + "vocab_size": 128256 +} + + +[INFO|2024-11-25 07:48:15] modeling_utils.py:3937 >> loading weights file model.safetensors from cache at /root/.cache/huggingface/hub/models--meta-llama--Meta-Llama-3-8B-Instruct/snapshots/5f0b02c75b57c5855da9ae460ce51323ea669d8a/model.safetensors.index.json + +[INFO|2024-11-25 07:48:15] modeling_utils.py:1670 >> Instantiating LlamaForCausalLM model under default dtype torch.bfloat16. + +[INFO|2024-11-25 07:48:15] configuration_utils.py:1096 >> Generate config GenerationConfig { + "bos_token_id": 128000, + "eos_token_id": 128009 +} + + +[INFO|2024-11-25 07:48:19] modeling_utils.py:4800 >> All model checkpoint weights were used when initializing LlamaForCausalLM. + + +[INFO|2024-11-25 07:48:19] modeling_utils.py:4808 >> All the weights of LlamaForCausalLM were initialized from the model checkpoint at meta-llama/Meta-Llama-3-8B-Instruct. +If your task is similar to the task the model of the checkpoint was trained on, you can already use LlamaForCausalLM for predictions without further training. + +[INFO|2024-11-25 07:48:19] configuration_utils.py:1051 >> loading configuration file generation_config.json from cache at /root/.cache/huggingface/hub/models--meta-llama--Meta-Llama-3-8B-Instruct/snapshots/5f0b02c75b57c5855da9ae460ce51323ea669d8a/generation_config.json + +[INFO|2024-11-25 07:48:19] configuration_utils.py:1096 >> Generate config GenerationConfig { + "bos_token_id": 128000, + "do_sample": true, + "eos_token_id": [ + 128001, + 128009 + ], + "max_length": 4096, + "temperature": 0.6, + "top_p": 0.9 +} + + +[INFO|2024-11-25 07:48:19] logging.py:157 >> Gradient checkpointing enabled. + +[INFO|2024-11-25 07:48:19] logging.py:157 >> Using torch SDPA for faster training and inference. + +[INFO|2024-11-25 07:48:19] logging.py:157 >> Upcasting trainable params to float32. + +[INFO|2024-11-25 07:48:19] logging.py:157 >> Fine-tuning method: Full + +[INFO|2024-11-25 07:48:19] logging.py:157 >> trainable params: 8,030,261,248 || all params: 8,030,261,248 || trainable%: 100.0000 + +[INFO|2024-11-25 07:48:19] trainer.py:698 >> Using auto half precision backend + +[INFO|2024-11-25 07:48:19] deepspeed.py:334 >> Detected ZeRO Offload and non-DeepSpeed optimizers: This combination should work as long as the custom optimizer has both CPU and GPU implementation (except LAMB) + +[INFO|2024-11-25 07:49:10] trainer.py:2313 >> ***** Running training ***** + +[INFO|2024-11-25 07:49:10] trainer.py:2314 >> Num examples = 15,090 + +[INFO|2024-11-25 07:49:10] trainer.py:2315 >> Num Epochs = 3 + +[INFO|2024-11-25 07:49:10] trainer.py:2316 >> Instantaneous batch size per device = 1 + +[INFO|2024-11-25 07:49:10] trainer.py:2319 >> Total train batch size (w. parallel, distributed & accumulation) = 32 + +[INFO|2024-11-25 07:49:10] trainer.py:2320 >> Gradient Accumulation steps = 8 + +[INFO|2024-11-25 07:49:10] trainer.py:2321 >> Total optimization steps = 1,413 + +[INFO|2024-11-25 07:49:10] trainer.py:2322 >> Number of trainable parameters = 8,030,261,248 + +[INFO|2024-11-25 07:49:39] logging.py:157 >> {'loss': 1.2577, 'learning_rate': 5.0000e-07, 'epoch': 0.00} + +[INFO|2024-11-25 07:50:00] logging.py:157 >> {'loss': 1.1764, 'learning_rate': 1.0000e-06, 'epoch': 0.00} + +[INFO|2024-11-25 07:50:21] logging.py:157 >> {'loss': 1.1581, 'learning_rate': 1.5000e-06, 'epoch': 0.01} + +[INFO|2024-11-25 07:50:42] logging.py:157 >> {'loss': 0.9151, 'learning_rate': 2.0000e-06, 'epoch': 0.01} + +[INFO|2024-11-25 07:51:03] logging.py:157 >> {'loss': 0.5946, 'learning_rate': 2.5000e-06, 'epoch': 0.01} + +[INFO|2024-11-25 07:51:23] logging.py:157 >> {'loss': 0.5140, 'learning_rate': 3.0000e-06, 'epoch': 0.01} + +[INFO|2024-11-25 07:51:46] logging.py:157 >> {'loss': 0.3226, 'learning_rate': 3.5000e-06, 'epoch': 0.01} + +[INFO|2024-11-25 07:52:07] logging.py:157 >> {'loss': 0.3853, 'learning_rate': 4.0000e-06, 'epoch': 0.02} + +[INFO|2024-11-25 07:52:28] logging.py:157 >> {'loss': 0.2983, 'learning_rate': 4.5000e-06, 'epoch': 0.02} + +[INFO|2024-11-25 07:52:49] logging.py:157 >> {'loss': 0.4318, 'learning_rate': 5.0000e-06, 'epoch': 0.02} + +[INFO|2024-11-25 07:53:10] logging.py:157 >> {'loss': 0.4925, 'learning_rate': 5.0000e-06, 'epoch': 0.02} + +[INFO|2024-11-25 07:53:31] logging.py:157 >> {'loss': 0.4128, 'learning_rate': 5.0000e-06, 'epoch': 0.03} + +[INFO|2024-11-25 07:53:52] logging.py:157 >> {'loss': 0.3941, 'learning_rate': 4.9999e-06, 'epoch': 0.03} + +[INFO|2024-11-25 07:54:13] logging.py:157 >> {'loss': 0.5270, 'learning_rate': 4.9999e-06, 'epoch': 0.03} + +[INFO|2024-11-25 07:54:35] logging.py:157 >> {'loss': 0.5217, 'learning_rate': 4.9998e-06, 'epoch': 0.03} + +[INFO|2024-11-25 07:54:56] logging.py:157 >> {'loss': 0.2620, 'learning_rate': 4.9998e-06, 'epoch': 0.03} + +[INFO|2024-11-25 07:55:18] logging.py:157 >> {'loss': 0.5101, 'learning_rate': 4.9997e-06, 'epoch': 0.04} + +[INFO|2024-11-25 07:55:39] logging.py:157 >> {'loss': 0.3760, 'learning_rate': 4.9996e-06, 'epoch': 0.04} + +[INFO|2024-11-25 07:56:00] logging.py:157 >> {'loss': 0.3747, 'learning_rate': 4.9995e-06, 'epoch': 0.04} + +[INFO|2024-11-25 07:56:20] logging.py:157 >> {'loss': 0.3933, 'learning_rate': 4.9994e-06, 'epoch': 0.04} + +[INFO|2024-11-25 07:56:44] logging.py:157 >> {'loss': 0.3696, 'learning_rate': 4.9992e-06, 'epoch': 0.04} + +[INFO|2024-11-25 07:57:06] logging.py:157 >> {'loss': 0.3125, 'learning_rate': 4.9991e-06, 'epoch': 0.05} + +[INFO|2024-11-25 07:57:26] logging.py:157 >> {'loss': 0.4218, 'learning_rate': 4.9989e-06, 'epoch': 0.05} + +[INFO|2024-11-25 07:57:48] logging.py:157 >> {'loss': 0.3827, 'learning_rate': 4.9988e-06, 'epoch': 0.05} + +[INFO|2024-11-25 07:58:08] logging.py:157 >> {'loss': 0.4637, 'learning_rate': 4.9986e-06, 'epoch': 0.05} + +[INFO|2024-11-25 07:58:29] logging.py:157 >> {'loss': 0.3562, 'learning_rate': 4.9984e-06, 'epoch': 0.06} + +[INFO|2024-11-25 07:58:50] logging.py:157 >> {'loss': 0.3842, 'learning_rate': 4.9982e-06, 'epoch': 0.06} + +[INFO|2024-11-25 07:59:12] logging.py:157 >> {'loss': 0.3048, 'learning_rate': 4.9980e-06, 'epoch': 0.06} + +[INFO|2024-11-25 07:59:34] logging.py:157 >> {'loss': 0.3621, 'learning_rate': 4.9977e-06, 'epoch': 0.06} + +[INFO|2024-11-25 07:59:54] logging.py:157 >> {'loss': 0.2974, 'learning_rate': 4.9975e-06, 'epoch': 0.06} + +[INFO|2024-11-25 08:00:15] logging.py:157 >> {'loss': 0.4450, 'learning_rate': 4.9972e-06, 'epoch': 0.07} + +[INFO|2024-11-25 08:00:37] logging.py:157 >> {'loss': 0.3759, 'learning_rate': 4.9970e-06, 'epoch': 0.07} + +[INFO|2024-11-25 08:00:57] logging.py:157 >> {'loss': 0.3232, 'learning_rate': 4.9967e-06, 'epoch': 0.07} + +[INFO|2024-11-25 08:01:18] logging.py:157 >> {'loss': 0.4248, 'learning_rate': 4.9964e-06, 'epoch': 0.07} + +[INFO|2024-11-25 08:01:39] logging.py:157 >> {'loss': 0.2229, 'learning_rate': 4.9961e-06, 'epoch': 0.07} + +[INFO|2024-11-25 08:01:59] logging.py:157 >> {'loss': 0.3160, 'learning_rate': 4.9958e-06, 'epoch': 0.08} + +[INFO|2024-11-25 08:02:20] logging.py:157 >> {'loss': 0.3061, 'learning_rate': 4.9954e-06, 'epoch': 0.08} + +[INFO|2024-11-25 08:02:41] logging.py:157 >> {'loss': 0.3889, 'learning_rate': 4.9951e-06, 'epoch': 0.08} + +[INFO|2024-11-25 08:03:02] logging.py:157 >> {'loss': 0.3944, 'learning_rate': 4.9947e-06, 'epoch': 0.08} + +[INFO|2024-11-25 08:03:22] logging.py:157 >> {'loss': 0.5437, 'learning_rate': 4.9944e-06, 'epoch': 0.08} + +[INFO|2024-11-25 08:03:43] logging.py:157 >> {'loss': 0.3570, 'learning_rate': 4.9940e-06, 'epoch': 0.09} + +[INFO|2024-11-25 08:04:03] logging.py:157 >> {'loss': 0.3081, 'learning_rate': 4.9936e-06, 'epoch': 0.09} + +[INFO|2024-11-25 08:04:25] logging.py:157 >> {'loss': 0.3468, 'learning_rate': 4.9932e-06, 'epoch': 0.09} + +[INFO|2024-11-25 08:04:46] logging.py:157 >> {'loss': 0.3266, 'learning_rate': 4.9928e-06, 'epoch': 0.09} + +[INFO|2024-11-25 08:05:07] logging.py:157 >> {'loss': 0.3799, 'learning_rate': 4.9923e-06, 'epoch': 0.10} + +[INFO|2024-11-25 08:05:30] logging.py:157 >> {'loss': 0.3149, 'learning_rate': 4.9919e-06, 'epoch': 0.10} + +[INFO|2024-11-25 08:05:51] logging.py:157 >> {'loss': 0.2163, 'learning_rate': 4.9914e-06, 'epoch': 0.10} + +[INFO|2024-11-25 08:06:12] logging.py:157 >> {'loss': 0.4008, 'learning_rate': 4.9910e-06, 'epoch': 0.10} + +[INFO|2024-11-25 08:06:33] logging.py:157 >> {'loss': 0.3937, 'learning_rate': 4.9905e-06, 'epoch': 0.10} + +[INFO|2024-11-25 08:06:54] logging.py:157 >> {'loss': 0.3810, 'learning_rate': 4.9900e-06, 'epoch': 0.11} + +[INFO|2024-11-25 08:07:14] logging.py:157 >> {'loss': 0.2995, 'learning_rate': 4.9895e-06, 'epoch': 0.11} + +[INFO|2024-11-25 08:07:35] logging.py:157 >> {'loss': 0.2401, 'learning_rate': 4.9890e-06, 'epoch': 0.11} + +[INFO|2024-11-25 08:07:56] logging.py:157 >> {'loss': 0.3294, 'learning_rate': 4.9884e-06, 'epoch': 0.11} + +[INFO|2024-11-25 08:08:16] logging.py:157 >> {'loss': 0.4972, 'learning_rate': 4.9879e-06, 'epoch': 0.11} + +[INFO|2024-11-25 08:08:37] logging.py:157 >> {'loss': 0.4146, 'learning_rate': 4.9873e-06, 'epoch': 0.12} + +[INFO|2024-11-25 08:08:58] logging.py:157 >> {'loss': 0.3277, 'learning_rate': 4.9867e-06, 'epoch': 0.12} + +[INFO|2024-11-25 08:09:20] logging.py:157 >> {'loss': 0.2963, 'learning_rate': 4.9862e-06, 'epoch': 0.12} + +[INFO|2024-11-25 08:09:41] logging.py:157 >> {'loss': 0.2798, 'learning_rate': 4.9856e-06, 'epoch': 0.12} + +[INFO|2024-11-25 08:10:02] logging.py:157 >> {'loss': 0.3764, 'learning_rate': 4.9850e-06, 'epoch': 0.13} + +[INFO|2024-11-25 08:10:25] logging.py:157 >> {'loss': 0.2544, 'learning_rate': 4.9843e-06, 'epoch': 0.13} + +[INFO|2024-11-25 08:10:47] logging.py:157 >> {'loss': 0.3421, 'learning_rate': 4.9837e-06, 'epoch': 0.13} + +[INFO|2024-11-25 08:11:08] logging.py:157 >> {'loss': 0.4167, 'learning_rate': 4.9831e-06, 'epoch': 0.13} + +[INFO|2024-11-25 08:11:29] logging.py:157 >> {'loss': 0.1973, 'learning_rate': 4.9824e-06, 'epoch': 0.13} + +[INFO|2024-11-25 08:11:49] logging.py:157 >> {'loss': 0.3211, 'learning_rate': 4.9817e-06, 'epoch': 0.14} + +[INFO|2024-11-25 08:12:10] logging.py:157 >> {'loss': 0.2813, 'learning_rate': 4.9811e-06, 'epoch': 0.14} + +[INFO|2024-11-25 08:12:30] logging.py:157 >> {'loss': 0.2489, 'learning_rate': 4.9804e-06, 'epoch': 0.14} + +[INFO|2024-11-25 08:12:52] logging.py:157 >> {'loss': 0.3817, 'learning_rate': 4.9797e-06, 'epoch': 0.14} + +[INFO|2024-11-25 08:13:12] logging.py:157 >> {'loss': 0.2673, 'learning_rate': 4.9789e-06, 'epoch': 0.14} + +[INFO|2024-11-25 08:13:33] logging.py:157 >> {'loss': 0.2844, 'learning_rate': 4.9782e-06, 'epoch': 0.15} + +[INFO|2024-11-25 08:13:53] logging.py:157 >> {'loss': 0.2262, 'learning_rate': 4.9775e-06, 'epoch': 0.15} + +[INFO|2024-11-25 08:14:13] logging.py:157 >> {'loss': 0.2650, 'learning_rate': 4.9767e-06, 'epoch': 0.15} + +[INFO|2024-11-25 08:14:34] logging.py:157 >> {'loss': 0.3004, 'learning_rate': 4.9759e-06, 'epoch': 0.15} + +[INFO|2024-11-25 08:14:55] logging.py:157 >> {'loss': 0.3076, 'learning_rate': 4.9752e-06, 'epoch': 0.15} + +[INFO|2024-11-25 08:15:15] logging.py:157 >> {'loss': 0.2370, 'learning_rate': 4.9744e-06, 'epoch': 0.16} + +[INFO|2024-11-25 08:15:36] logging.py:157 >> {'loss': 0.3886, 'learning_rate': 4.9736e-06, 'epoch': 0.16} + +[INFO|2024-11-25 08:15:57] logging.py:157 >> {'loss': 0.4216, 'learning_rate': 4.9727e-06, 'epoch': 0.16} + +[INFO|2024-11-25 08:16:17] logging.py:157 >> {'loss': 0.2869, 'learning_rate': 4.9719e-06, 'epoch': 0.16} + +[INFO|2024-11-25 08:16:40] logging.py:157 >> {'loss': 0.2688, 'learning_rate': 4.9711e-06, 'epoch': 0.17} + +[INFO|2024-11-25 08:17:01] logging.py:157 >> {'loss': 0.3894, 'learning_rate': 4.9702e-06, 'epoch': 0.17} + +[INFO|2024-11-25 08:17:22] logging.py:157 >> {'loss': 0.3129, 'learning_rate': 4.9694e-06, 'epoch': 0.17} + +[INFO|2024-11-25 08:17:43] logging.py:157 >> {'loss': 0.3220, 'learning_rate': 4.9685e-06, 'epoch': 0.17} + +[INFO|2024-11-25 08:18:03] logging.py:157 >> {'loss': 0.3069, 'learning_rate': 4.9676e-06, 'epoch': 0.17} + +[INFO|2024-11-25 08:18:26] logging.py:157 >> {'loss': 0.3893, 'learning_rate': 4.9667e-06, 'epoch': 0.18} + +[INFO|2024-11-25 08:18:46] logging.py:157 >> {'loss': 0.3198, 'learning_rate': 4.9658e-06, 'epoch': 0.18} + +[INFO|2024-11-25 08:19:06] logging.py:157 >> {'loss': 0.3547, 'learning_rate': 4.9648e-06, 'epoch': 0.18} + +[INFO|2024-11-25 08:19:27] logging.py:157 >> {'loss': 0.2338, 'learning_rate': 4.9639e-06, 'epoch': 0.18} + +[INFO|2024-11-25 08:19:48] logging.py:157 >> {'loss': 0.3118, 'learning_rate': 4.9629e-06, 'epoch': 0.18} + +[INFO|2024-11-25 08:20:09] logging.py:157 >> {'loss': 0.2744, 'learning_rate': 4.9620e-06, 'epoch': 0.19} + +[INFO|2024-11-25 08:20:30] logging.py:157 >> {'loss': 0.3339, 'learning_rate': 4.9610e-06, 'epoch': 0.19} + +[INFO|2024-11-25 08:20:52] logging.py:157 >> {'loss': 0.2318, 'learning_rate': 4.9600e-06, 'epoch': 0.19} + +[INFO|2024-11-25 08:21:14] logging.py:157 >> {'loss': 0.3198, 'learning_rate': 4.9590e-06, 'epoch': 0.19} + +[INFO|2024-11-25 08:21:35] logging.py:157 >> {'loss': 0.2254, 'learning_rate': 4.9580e-06, 'epoch': 0.20} + +[INFO|2024-11-25 08:21:57] logging.py:157 >> {'loss': 0.2770, 'learning_rate': 4.9569e-06, 'epoch': 0.20} + +[INFO|2024-11-25 08:22:18] logging.py:157 >> {'loss': 0.3462, 'learning_rate': 4.9559e-06, 'epoch': 0.20} + +[INFO|2024-11-25 08:22:39] logging.py:157 >> {'loss': 0.2103, 'learning_rate': 4.9549e-06, 'epoch': 0.20} + +[INFO|2024-11-25 08:23:01] logging.py:157 >> {'loss': 0.2460, 'learning_rate': 4.9538e-06, 'epoch': 0.20} + +[INFO|2024-11-25 08:23:22] logging.py:157 >> {'loss': 0.3306, 'learning_rate': 4.9527e-06, 'epoch': 0.21} + +[INFO|2024-11-25 08:23:42] logging.py:157 >> {'loss': 0.3700, 'learning_rate': 4.9516e-06, 'epoch': 0.21} + +[INFO|2024-11-25 08:24:02] logging.py:157 >> {'loss': 0.3687, 'learning_rate': 4.9505e-06, 'epoch': 0.21} + +[INFO|2024-11-25 08:24:23] logging.py:157 >> {'loss': 0.4234, 'learning_rate': 4.9494e-06, 'epoch': 0.21} + +[INFO|2024-11-25 08:24:44] logging.py:157 >> {'loss': 0.3633, 'learning_rate': 4.9483e-06, 'epoch': 0.21} + +[INFO|2024-11-25 08:25:06] logging.py:157 >> {'loss': 0.3335, 'learning_rate': 4.9471e-06, 'epoch': 0.22} + +[INFO|2024-11-25 08:25:27] logging.py:157 >> {'loss': 0.1860, 'learning_rate': 4.9460e-06, 'epoch': 0.22} + +[INFO|2024-11-25 08:25:49] logging.py:157 >> {'loss': 0.2399, 'learning_rate': 4.9448e-06, 'epoch': 0.22} + +[INFO|2024-11-25 08:26:09] logging.py:157 >> {'loss': 0.2794, 'learning_rate': 4.9436e-06, 'epoch': 0.22} + +[INFO|2024-11-25 08:26:30] logging.py:157 >> {'loss': 0.2431, 'learning_rate': 4.9425e-06, 'epoch': 0.22} + +[INFO|2024-11-25 08:26:51] logging.py:157 >> {'loss': 0.2580, 'learning_rate': 4.9413e-06, 'epoch': 0.23} + +[INFO|2024-11-25 08:27:11] logging.py:157 >> {'loss': 0.3056, 'learning_rate': 4.9400e-06, 'epoch': 0.23} + +[INFO|2024-11-25 08:27:32] logging.py:157 >> {'loss': 0.3374, 'learning_rate': 4.9388e-06, 'epoch': 0.23} + +[INFO|2024-11-25 08:27:54] logging.py:157 >> {'loss': 0.1877, 'learning_rate': 4.9376e-06, 'epoch': 0.23} + +[INFO|2024-11-25 08:28:16] logging.py:157 >> {'loss': 0.3190, 'learning_rate': 4.9363e-06, 'epoch': 0.24} + +[INFO|2024-11-25 08:28:36] logging.py:157 >> {'loss': 0.2615, 'learning_rate': 4.9351e-06, 'epoch': 0.24} + +[INFO|2024-11-25 08:28:57] logging.py:157 >> {'loss': 0.2038, 'learning_rate': 4.9338e-06, 'epoch': 0.24} + +[INFO|2024-11-25 08:29:18] logging.py:157 >> {'loss': 0.2945, 'learning_rate': 4.9325e-06, 'epoch': 0.24} + +[INFO|2024-11-25 08:29:39] logging.py:157 >> {'loss': 0.2102, 'learning_rate': 4.9312e-06, 'epoch': 0.24} + +[INFO|2024-11-25 08:30:00] logging.py:157 >> {'loss': 0.3449, 'learning_rate': 4.9299e-06, 'epoch': 0.25} + +[INFO|2024-11-25 08:30:24] logging.py:157 >> {'loss': 0.3072, 'learning_rate': 4.9286e-06, 'epoch': 0.25} + +[INFO|2024-11-25 08:30:44] logging.py:157 >> {'loss': 0.3457, 'learning_rate': 4.9273e-06, 'epoch': 0.25} + +[INFO|2024-11-25 08:31:05] logging.py:157 >> {'loss': 0.3305, 'learning_rate': 4.9259e-06, 'epoch': 0.25} + +[INFO|2024-11-25 08:31:26] logging.py:157 >> {'loss': 0.4029, 'learning_rate': 4.9245e-06, 'epoch': 0.25} + +[INFO|2024-11-25 08:31:47] logging.py:157 >> {'loss': 0.3313, 'learning_rate': 4.9232e-06, 'epoch': 0.26} + +[INFO|2024-11-25 08:32:07] logging.py:157 >> {'loss': 0.2630, 'learning_rate': 4.9218e-06, 'epoch': 0.26} + +[INFO|2024-11-25 08:32:28] logging.py:157 >> {'loss': 0.4046, 'learning_rate': 4.9204e-06, 'epoch': 0.26} + +[INFO|2024-11-25 08:32:49] logging.py:157 >> {'loss': 0.2562, 'learning_rate': 4.9190e-06, 'epoch': 0.26} + +[INFO|2024-11-25 08:33:10] logging.py:157 >> {'loss': 0.2157, 'learning_rate': 4.9176e-06, 'epoch': 0.27} + +[INFO|2024-11-25 08:33:31] logging.py:157 >> {'loss': 0.2177, 'learning_rate': 4.9161e-06, 'epoch': 0.27} + +[INFO|2024-11-25 08:33:52] logging.py:157 >> {'loss': 0.2717, 'learning_rate': 4.9147e-06, 'epoch': 0.27} + +[INFO|2024-11-25 08:34:12] logging.py:157 >> {'loss': 0.2845, 'learning_rate': 4.9132e-06, 'epoch': 0.27} + +[INFO|2024-11-25 08:34:33] logging.py:157 >> {'loss': 0.2839, 'learning_rate': 4.9118e-06, 'epoch': 0.27} + +[INFO|2024-11-25 08:34:54] logging.py:157 >> {'loss': 0.3791, 'learning_rate': 4.9103e-06, 'epoch': 0.28} + +[INFO|2024-11-25 08:35:14] logging.py:157 >> {'loss': 0.3046, 'learning_rate': 4.9088e-06, 'epoch': 0.28} + +[INFO|2024-11-25 08:35:36] logging.py:157 >> {'loss': 0.2242, 'learning_rate': 4.9073e-06, 'epoch': 0.28} + +[INFO|2024-11-25 08:35:57] logging.py:157 >> {'loss': 0.2657, 'learning_rate': 4.9058e-06, 'epoch': 0.28} + +[INFO|2024-11-25 08:36:19] logging.py:157 >> {'loss': 0.2321, 'learning_rate': 4.9042e-06, 'epoch': 0.28} + +[INFO|2024-11-25 08:36:40] logging.py:157 >> {'loss': 0.2339, 'learning_rate': 4.9027e-06, 'epoch': 0.29} + +[INFO|2024-11-25 08:37:01] logging.py:157 >> {'loss': 0.2703, 'learning_rate': 4.9012e-06, 'epoch': 0.29} + +[INFO|2024-11-25 08:37:21] logging.py:157 >> {'loss': 0.3249, 'learning_rate': 4.8996e-06, 'epoch': 0.29} + +[INFO|2024-11-25 08:37:42] logging.py:157 >> {'loss': 0.2290, 'learning_rate': 4.8980e-06, 'epoch': 0.29} + +[INFO|2024-11-25 08:38:03] logging.py:157 >> {'loss': 0.2925, 'learning_rate': 4.8964e-06, 'epoch': 0.29} + +[INFO|2024-11-25 08:38:23] logging.py:157 >> {'loss': 0.2349, 'learning_rate': 4.8948e-06, 'epoch': 0.30} + +[INFO|2024-11-25 08:38:45] logging.py:157 >> {'loss': 0.3615, 'learning_rate': 4.8932e-06, 'epoch': 0.30} + +[INFO|2024-11-25 08:39:06] logging.py:157 >> {'loss': 0.4128, 'learning_rate': 4.8916e-06, 'epoch': 0.30} + +[INFO|2024-11-25 08:39:26] logging.py:157 >> {'loss': 0.2398, 'learning_rate': 4.8900e-06, 'epoch': 0.30} + +[INFO|2024-11-25 08:39:47] logging.py:157 >> {'loss': 0.3333, 'learning_rate': 4.8883e-06, 'epoch': 0.31} + +[INFO|2024-11-25 08:40:09] logging.py:157 >> {'loss': 0.2091, 'learning_rate': 4.8866e-06, 'epoch': 0.31} + +[INFO|2024-11-25 08:40:29] logging.py:157 >> {'loss': 0.2042, 'learning_rate': 4.8850e-06, 'epoch': 0.31} + +[INFO|2024-11-25 08:40:51] logging.py:157 >> {'loss': 0.3742, 'learning_rate': 4.8833e-06, 'epoch': 0.31} + +[INFO|2024-11-25 08:41:11] logging.py:157 >> {'loss': 0.3228, 'learning_rate': 4.8816e-06, 'epoch': 0.31} + +[INFO|2024-11-25 08:41:32] logging.py:157 >> {'loss': 0.4520, 'learning_rate': 4.8799e-06, 'epoch': 0.32} + +[INFO|2024-11-25 08:41:53] logging.py:157 >> {'loss': 0.3467, 'learning_rate': 4.8782e-06, 'epoch': 0.32} + +[INFO|2024-11-25 08:42:14] logging.py:157 >> {'loss': 0.3558, 'learning_rate': 4.8764e-06, 'epoch': 0.32} + +[INFO|2024-11-25 08:42:36] logging.py:157 >> {'loss': 0.2739, 'learning_rate': 4.8747e-06, 'epoch': 0.32} + +[INFO|2024-11-25 08:42:56] logging.py:157 >> {'loss': 0.2131, 'learning_rate': 4.8729e-06, 'epoch': 0.32} + +[INFO|2024-11-25 08:43:17] logging.py:157 >> {'loss': 0.3290, 'learning_rate': 4.8712e-06, 'epoch': 0.33} + +[INFO|2024-11-25 08:43:39] logging.py:157 >> {'loss': 0.2388, 'learning_rate': 4.8694e-06, 'epoch': 0.33} + +[INFO|2024-11-25 08:44:01] logging.py:157 >> {'loss': 0.3476, 'learning_rate': 4.8676e-06, 'epoch': 0.33} + +[INFO|2024-11-25 08:44:22] logging.py:157 >> {'loss': 0.3471, 'learning_rate': 4.8658e-06, 'epoch': 0.33} + +[INFO|2024-11-25 08:44:43] logging.py:157 >> {'loss': 0.3026, 'learning_rate': 4.8640e-06, 'epoch': 0.34} + +[INFO|2024-11-25 08:45:04] logging.py:157 >> {'loss': 0.3127, 'learning_rate': 4.8621e-06, 'epoch': 0.34} + +[INFO|2024-11-25 08:45:25] logging.py:157 >> {'loss': 0.2059, 'learning_rate': 4.8603e-06, 'epoch': 0.34} + +[INFO|2024-11-25 08:45:47] logging.py:157 >> {'loss': 0.2706, 'learning_rate': 4.8585e-06, 'epoch': 0.34} + +[INFO|2024-11-25 08:46:07] logging.py:157 >> {'loss': 0.2539, 'learning_rate': 4.8566e-06, 'epoch': 0.34} + +[INFO|2024-11-25 08:46:29] logging.py:157 >> {'loss': 0.2923, 'learning_rate': 4.8547e-06, 'epoch': 0.35} + +[INFO|2024-11-25 08:46:50] logging.py:157 >> {'loss': 0.2357, 'learning_rate': 4.8528e-06, 'epoch': 0.35} + +[INFO|2024-11-25 08:47:11] logging.py:157 >> {'loss': 0.2745, 'learning_rate': 4.8509e-06, 'epoch': 0.35} + +[INFO|2024-11-25 08:47:32] logging.py:157 >> {'loss': 0.2503, 'learning_rate': 4.8490e-06, 'epoch': 0.35} + +[INFO|2024-11-25 08:47:54] logging.py:157 >> {'loss': 0.3615, 'learning_rate': 4.8471e-06, 'epoch': 0.35} + +[INFO|2024-11-25 08:48:15] logging.py:157 >> {'loss': 0.1870, 'learning_rate': 4.8452e-06, 'epoch': 0.36} + +[INFO|2024-11-25 08:48:37] logging.py:157 >> {'loss': 0.2641, 'learning_rate': 4.8432e-06, 'epoch': 0.36} + +[INFO|2024-11-25 08:48:57] logging.py:157 >> {'loss': 0.2323, 'learning_rate': 4.8413e-06, 'epoch': 0.36} + +[INFO|2024-11-25 08:49:19] logging.py:157 >> {'loss': 0.3339, 'learning_rate': 4.8393e-06, 'epoch': 0.36} + +[INFO|2024-11-25 08:49:40] logging.py:157 >> {'loss': 0.2844, 'learning_rate': 4.8373e-06, 'epoch': 0.36} + +[INFO|2024-11-25 08:50:01] logging.py:157 >> {'loss': 0.3137, 'learning_rate': 4.8353e-06, 'epoch': 0.37} + +[INFO|2024-11-25 08:50:21] logging.py:157 >> {'loss': 0.2336, 'learning_rate': 4.8333e-06, 'epoch': 0.37} + +[INFO|2024-11-25 08:50:42] logging.py:157 >> {'loss': 0.2312, 'learning_rate': 4.8313e-06, 'epoch': 0.37} + +[INFO|2024-11-25 08:51:03] logging.py:157 >> {'loss': 0.3141, 'learning_rate': 4.8293e-06, 'epoch': 0.37} + +[INFO|2024-11-25 08:51:24] logging.py:157 >> {'loss': 0.2590, 'learning_rate': 4.8272e-06, 'epoch': 0.38} + +[INFO|2024-11-25 08:51:46] logging.py:157 >> {'loss': 0.2300, 'learning_rate': 4.8252e-06, 'epoch': 0.38} + +[INFO|2024-11-25 08:52:08] logging.py:157 >> {'loss': 0.2643, 'learning_rate': 4.8231e-06, 'epoch': 0.38} + +[INFO|2024-11-25 08:52:29] logging.py:157 >> {'loss': 0.2215, 'learning_rate': 4.8210e-06, 'epoch': 0.38} + +[INFO|2024-11-25 08:52:50] logging.py:157 >> {'loss': 0.2168, 'learning_rate': 4.8190e-06, 'epoch': 0.38} + +[INFO|2024-11-25 08:53:11] logging.py:157 >> {'loss': 0.2618, 'learning_rate': 4.8169e-06, 'epoch': 0.39} + +[INFO|2024-11-25 08:53:32] logging.py:157 >> {'loss': 0.3713, 'learning_rate': 4.8148e-06, 'epoch': 0.39} + +[INFO|2024-11-25 08:53:53] logging.py:157 >> {'loss': 0.3274, 'learning_rate': 4.8126e-06, 'epoch': 0.39} + +[INFO|2024-11-25 08:54:13] logging.py:157 >> {'loss': 0.2310, 'learning_rate': 4.8105e-06, 'epoch': 0.39} + +[INFO|2024-11-25 08:54:34] logging.py:157 >> {'loss': 0.3412, 'learning_rate': 4.8084e-06, 'epoch': 0.39} + +[INFO|2024-11-25 08:54:55] logging.py:157 >> {'loss': 0.2470, 'learning_rate': 4.8062e-06, 'epoch': 0.40} + +[INFO|2024-11-25 08:55:16] logging.py:157 >> {'loss': 0.2412, 'learning_rate': 4.8040e-06, 'epoch': 0.40} + +[INFO|2024-11-25 08:55:37] logging.py:157 >> {'loss': 0.2943, 'learning_rate': 4.8019e-06, 'epoch': 0.40} + +[INFO|2024-11-25 08:55:58] logging.py:157 >> {'loss': 0.2740, 'learning_rate': 4.7997e-06, 'epoch': 0.40} + +[INFO|2024-11-25 08:56:18] logging.py:157 >> {'loss': 0.2450, 'learning_rate': 4.7975e-06, 'epoch': 0.40} + +[INFO|2024-11-25 08:56:39] logging.py:157 >> {'loss': 0.3203, 'learning_rate': 4.7953e-06, 'epoch': 0.41} + +[INFO|2024-11-25 08:57:00] logging.py:157 >> {'loss': 0.3274, 'learning_rate': 4.7930e-06, 'epoch': 0.41} + +[INFO|2024-11-25 08:57:21] logging.py:157 >> {'loss': 0.3502, 'learning_rate': 4.7908e-06, 'epoch': 0.41} + +[INFO|2024-11-25 08:57:42] logging.py:157 >> {'loss': 0.4093, 'learning_rate': 4.7885e-06, 'epoch': 0.41} + +[INFO|2024-11-25 08:58:03] logging.py:157 >> {'loss': 0.3394, 'learning_rate': 4.7863e-06, 'epoch': 0.42} + +[INFO|2024-11-25 08:58:24] logging.py:157 >> {'loss': 0.2579, 'learning_rate': 4.7840e-06, 'epoch': 0.42} + +[INFO|2024-11-25 08:58:45] logging.py:157 >> {'loss': 0.3256, 'learning_rate': 4.7817e-06, 'epoch': 0.42} + +[INFO|2024-11-25 08:59:06] logging.py:157 >> {'loss': 0.2552, 'learning_rate': 4.7794e-06, 'epoch': 0.42} + +[INFO|2024-11-25 08:59:27] logging.py:157 >> {'loss': 0.3450, 'learning_rate': 4.7771e-06, 'epoch': 0.42} + +[INFO|2024-11-25 08:59:49] logging.py:157 >> {'loss': 0.3555, 'learning_rate': 4.7748e-06, 'epoch': 0.43} + +[INFO|2024-11-25 09:00:10] logging.py:157 >> {'loss': 0.3845, 'learning_rate': 4.7725e-06, 'epoch': 0.43} + +[INFO|2024-11-25 09:00:31] logging.py:157 >> {'loss': 0.2260, 'learning_rate': 4.7702e-06, 'epoch': 0.43} + +[INFO|2024-11-25 09:00:53] logging.py:157 >> {'loss': 0.2998, 'learning_rate': 4.7678e-06, 'epoch': 0.43} + +[INFO|2024-11-25 09:01:14] logging.py:157 >> {'loss': 0.2627, 'learning_rate': 4.7654e-06, 'epoch': 0.43} + +[INFO|2024-11-25 09:01:34] logging.py:157 >> {'loss': 0.3959, 'learning_rate': 4.7631e-06, 'epoch': 0.44} + +[INFO|2024-11-25 09:01:55] logging.py:157 >> {'loss': 0.3076, 'learning_rate': 4.7607e-06, 'epoch': 0.44} + +[INFO|2024-11-25 09:02:16] logging.py:157 >> {'loss': 0.2894, 'learning_rate': 4.7583e-06, 'epoch': 0.44} + +[INFO|2024-11-25 09:02:36] logging.py:157 >> {'loss': 0.2890, 'learning_rate': 4.7559e-06, 'epoch': 0.44} + +[INFO|2024-11-25 09:02:58] logging.py:157 >> {'loss': 0.2759, 'learning_rate': 4.7535e-06, 'epoch': 0.45} + +[INFO|2024-11-25 09:03:18] logging.py:157 >> {'loss': 0.2892, 'learning_rate': 4.7510e-06, 'epoch': 0.45} + +[INFO|2024-11-25 09:03:40] logging.py:157 >> {'loss': 0.2232, 'learning_rate': 4.7486e-06, 'epoch': 0.45} + +[INFO|2024-11-25 09:04:01] logging.py:157 >> {'loss': 0.2904, 'learning_rate': 4.7461e-06, 'epoch': 0.45} + +[INFO|2024-11-25 09:04:23] logging.py:157 >> {'loss': 0.3108, 'learning_rate': 4.7437e-06, 'epoch': 0.45} + +[INFO|2024-11-25 09:04:43] logging.py:157 >> {'loss': 0.3254, 'learning_rate': 4.7412e-06, 'epoch': 0.46} + +[INFO|2024-11-25 09:05:04] logging.py:157 >> {'loss': 0.3318, 'learning_rate': 4.7387e-06, 'epoch': 0.46} + +[INFO|2024-11-25 09:05:25] logging.py:157 >> {'loss': 0.2817, 'learning_rate': 4.7362e-06, 'epoch': 0.46} + +[INFO|2024-11-25 09:05:46] logging.py:157 >> {'loss': 0.3168, 'learning_rate': 4.7337e-06, 'epoch': 0.46} + +[INFO|2024-11-25 09:06:08] logging.py:157 >> {'loss': 0.2630, 'learning_rate': 4.7312e-06, 'epoch': 0.46} + +[INFO|2024-11-25 09:06:29] logging.py:157 >> {'loss': 0.2370, 'learning_rate': 4.7287e-06, 'epoch': 0.47} + +[INFO|2024-11-25 09:06:51] logging.py:157 >> {'loss': 0.1574, 'learning_rate': 4.7261e-06, 'epoch': 0.47} + +[INFO|2024-11-25 09:07:11] logging.py:157 >> {'loss': 0.2870, 'learning_rate': 4.7236e-06, 'epoch': 0.47} + +[INFO|2024-11-25 09:07:33] logging.py:157 >> {'loss': 0.2368, 'learning_rate': 4.7210e-06, 'epoch': 0.47} + +[INFO|2024-11-25 09:07:55] logging.py:157 >> {'loss': 0.3074, 'learning_rate': 4.7184e-06, 'epoch': 0.47} + +[INFO|2024-11-25 09:08:16] logging.py:157 >> {'loss': 0.2073, 'learning_rate': 4.7158e-06, 'epoch': 0.48} + +[INFO|2024-11-25 09:08:36] logging.py:157 >> {'loss': 0.2204, 'learning_rate': 4.7132e-06, 'epoch': 0.48} + +[INFO|2024-11-25 09:08:57] logging.py:157 >> {'loss': 0.3780, 'learning_rate': 4.7106e-06, 'epoch': 0.48} + +[INFO|2024-11-25 09:09:17] logging.py:157 >> {'loss': 0.2746, 'learning_rate': 4.7080e-06, 'epoch': 0.48} + +[INFO|2024-11-25 09:09:39] logging.py:157 >> {'loss': 0.3171, 'learning_rate': 4.7054e-06, 'epoch': 0.49} + +[INFO|2024-11-25 09:10:00] logging.py:157 >> {'loss': 0.3478, 'learning_rate': 4.7027e-06, 'epoch': 0.49} + +[INFO|2024-11-25 09:10:19] logging.py:157 >> {'loss': 0.1753, 'learning_rate': 4.7001e-06, 'epoch': 0.49} + +[INFO|2024-11-25 09:10:42] logging.py:157 >> {'loss': 0.2202, 'learning_rate': 4.6974e-06, 'epoch': 0.49} + +[INFO|2024-11-25 09:11:02] logging.py:157 >> {'loss': 0.2557, 'learning_rate': 4.6947e-06, 'epoch': 0.49} + +[INFO|2024-11-25 09:11:23] logging.py:157 >> {'loss': 0.3656, 'learning_rate': 4.6921e-06, 'epoch': 0.50} + +[INFO|2024-11-25 09:11:43] logging.py:157 >> {'loss': 0.3637, 'learning_rate': 4.6894e-06, 'epoch': 0.50} + +[INFO|2024-11-25 09:12:04] logging.py:157 >> {'loss': 0.2433, 'learning_rate': 4.6867e-06, 'epoch': 0.50} + +[INFO|2024-11-25 09:12:26] logging.py:157 >> {'loss': 0.3574, 'learning_rate': 4.6839e-06, 'epoch': 0.50} + +[INFO|2024-11-25 09:12:47] logging.py:157 >> {'loss': 0.3007, 'learning_rate': 4.6812e-06, 'epoch': 0.50} + +[INFO|2024-11-25 09:13:07] logging.py:157 >> {'loss': 0.2679, 'learning_rate': 4.6785e-06, 'epoch': 0.51} + +[INFO|2024-11-25 09:13:27] logging.py:157 >> {'loss': 0.4230, 'learning_rate': 4.6757e-06, 'epoch': 0.51} + +[INFO|2024-11-25 09:13:48] logging.py:157 >> {'loss': 0.2192, 'learning_rate': 4.6730e-06, 'epoch': 0.51} + +[INFO|2024-11-25 09:14:08] logging.py:157 >> {'loss': 0.3557, 'learning_rate': 4.6702e-06, 'epoch': 0.51} + +[INFO|2024-11-25 09:14:29] logging.py:157 >> {'loss': 0.2169, 'learning_rate': 4.6674e-06, 'epoch': 0.52} + +[INFO|2024-11-25 09:14:50] logging.py:157 >> {'loss': 0.2279, 'learning_rate': 4.6646e-06, 'epoch': 0.52} + +[INFO|2024-11-25 09:15:12] logging.py:157 >> {'loss': 0.2350, 'learning_rate': 4.6618e-06, 'epoch': 0.52} + +[INFO|2024-11-25 09:15:32] logging.py:157 >> {'loss': 0.2745, 'learning_rate': 4.6590e-06, 'epoch': 0.52} + +[INFO|2024-11-25 09:15:53] logging.py:157 >> {'loss': 0.2579, 'learning_rate': 4.6561e-06, 'epoch': 0.52} + +[INFO|2024-11-25 09:16:14] logging.py:157 >> {'loss': 0.3445, 'learning_rate': 4.6533e-06, 'epoch': 0.53} + +[INFO|2024-11-25 09:16:37] logging.py:157 >> {'loss': 0.2752, 'learning_rate': 4.6505e-06, 'epoch': 0.53} + +[INFO|2024-11-25 09:16:57] logging.py:157 >> {'loss': 0.2539, 'learning_rate': 4.6476e-06, 'epoch': 0.53} + +[INFO|2024-11-25 09:17:18] logging.py:157 >> {'loss': 0.2548, 'learning_rate': 4.6447e-06, 'epoch': 0.53} + +[INFO|2024-11-25 09:17:39] logging.py:157 >> {'loss': 0.2473, 'learning_rate': 4.6418e-06, 'epoch': 0.53} + +[INFO|2024-11-25 09:17:59] logging.py:157 >> {'loss': 0.2633, 'learning_rate': 4.6390e-06, 'epoch': 0.54} + +[INFO|2024-11-25 09:18:20] logging.py:157 >> {'loss': 0.2015, 'learning_rate': 4.6360e-06, 'epoch': 0.54} + +[INFO|2024-11-25 09:18:40] logging.py:157 >> {'loss': 0.2420, 'learning_rate': 4.6331e-06, 'epoch': 0.54} + +[INFO|2024-11-25 09:19:02] logging.py:157 >> {'loss': 0.1624, 'learning_rate': 4.6302e-06, 'epoch': 0.54} + +[INFO|2024-11-25 09:19:24] logging.py:157 >> {'loss': 0.2660, 'learning_rate': 4.6273e-06, 'epoch': 0.54} + +[INFO|2024-11-25 09:19:45] logging.py:157 >> {'loss': 0.2686, 'learning_rate': 4.6243e-06, 'epoch': 0.55} + +[INFO|2024-11-25 09:20:06] logging.py:157 >> {'loss': 0.2292, 'learning_rate': 4.6214e-06, 'epoch': 0.55} + +[INFO|2024-11-25 09:20:28] logging.py:157 >> {'loss': 0.1938, 'learning_rate': 4.6184e-06, 'epoch': 0.55} + +[INFO|2024-11-25 09:20:49] logging.py:157 >> {'loss': 0.2923, 'learning_rate': 4.6154e-06, 'epoch': 0.55} + +[INFO|2024-11-25 09:21:11] logging.py:157 >> {'loss': 0.2513, 'learning_rate': 4.6124e-06, 'epoch': 0.56} + +[INFO|2024-11-25 09:21:32] logging.py:157 >> {'loss': 0.1831, 'learning_rate': 4.6094e-06, 'epoch': 0.56} + +[INFO|2024-11-25 09:21:53] logging.py:157 >> {'loss': 0.3138, 'learning_rate': 4.6064e-06, 'epoch': 0.56} + +[INFO|2024-11-25 09:22:13] logging.py:157 >> {'loss': 0.2822, 'learning_rate': 4.6034e-06, 'epoch': 0.56} + +[INFO|2024-11-25 09:22:34] logging.py:157 >> {'loss': 0.3735, 'learning_rate': 4.6004e-06, 'epoch': 0.56} + +[INFO|2024-11-25 09:22:55] logging.py:157 >> {'loss': 0.2993, 'learning_rate': 4.5973e-06, 'epoch': 0.57} + +[INFO|2024-11-25 09:23:15] logging.py:157 >> {'loss': 0.2737, 'learning_rate': 4.5943e-06, 'epoch': 0.57} + +[INFO|2024-11-25 09:23:37] logging.py:157 >> {'loss': 0.2369, 'learning_rate': 4.5912e-06, 'epoch': 0.57} + +[INFO|2024-11-25 09:23:59] logging.py:157 >> {'loss': 0.2901, 'learning_rate': 4.5881e-06, 'epoch': 0.57} + +[INFO|2024-11-25 09:24:20] logging.py:157 >> {'loss': 0.2711, 'learning_rate': 4.5851e-06, 'epoch': 0.57} + +[INFO|2024-11-25 09:24:40] logging.py:157 >> {'loss': 0.2020, 'learning_rate': 4.5820e-06, 'epoch': 0.58} + +[INFO|2024-11-25 09:25:02] logging.py:157 >> {'loss': 0.2347, 'learning_rate': 4.5789e-06, 'epoch': 0.58} + +[INFO|2024-11-25 09:25:24] logging.py:157 >> {'loss': 0.2795, 'learning_rate': 4.5758e-06, 'epoch': 0.58} + +[INFO|2024-11-25 09:25:44] logging.py:157 >> {'loss': 0.3109, 'learning_rate': 4.5726e-06, 'epoch': 0.58} + +[INFO|2024-11-25 09:26:05] logging.py:157 >> {'loss': 0.2391, 'learning_rate': 4.5695e-06, 'epoch': 0.59} + +[INFO|2024-11-25 09:26:26] logging.py:157 >> {'loss': 0.1732, 'learning_rate': 4.5663e-06, 'epoch': 0.59} + +[INFO|2024-11-25 09:26:47] logging.py:157 >> {'loss': 0.2278, 'learning_rate': 4.5632e-06, 'epoch': 0.59} + +[INFO|2024-11-25 09:27:09] logging.py:157 >> {'loss': 0.2911, 'learning_rate': 4.5600e-06, 'epoch': 0.59} + +[INFO|2024-11-25 09:27:30] logging.py:157 >> {'loss': 0.3270, 'learning_rate': 4.5568e-06, 'epoch': 0.59} + +[INFO|2024-11-25 09:27:52] logging.py:157 >> {'loss': 0.2883, 'learning_rate': 4.5537e-06, 'epoch': 0.60} + +[INFO|2024-11-25 09:28:13] logging.py:157 >> {'loss': 0.2981, 'learning_rate': 4.5505e-06, 'epoch': 0.60} + +[INFO|2024-11-25 09:28:34] logging.py:157 >> {'loss': 0.3031, 'learning_rate': 4.5473e-06, 'epoch': 0.60} + +[INFO|2024-11-25 09:28:55] logging.py:157 >> {'loss': 0.3123, 'learning_rate': 4.5440e-06, 'epoch': 0.60} + +[INFO|2024-11-25 09:29:16] logging.py:157 >> {'loss': 0.2838, 'learning_rate': 4.5408e-06, 'epoch': 0.60} + +[INFO|2024-11-25 09:29:38] logging.py:157 >> {'loss': 0.3393, 'learning_rate': 4.5376e-06, 'epoch': 0.61} + +[INFO|2024-11-25 09:29:59] logging.py:157 >> {'loss': 0.2278, 'learning_rate': 4.5343e-06, 'epoch': 0.61} + +[INFO|2024-11-25 09:30:20] logging.py:157 >> {'loss': 0.2498, 'learning_rate': 4.5311e-06, 'epoch': 0.61} + +[INFO|2024-11-25 09:30:41] logging.py:157 >> {'loss': 0.2269, 'learning_rate': 4.5278e-06, 'epoch': 0.61} + +[INFO|2024-11-25 09:31:03] logging.py:157 >> {'loss': 0.3268, 'learning_rate': 4.5245e-06, 'epoch': 0.61} + +[INFO|2024-11-25 09:31:23] logging.py:157 >> {'loss': 0.3014, 'learning_rate': 4.5212e-06, 'epoch': 0.62} + +[INFO|2024-11-25 09:31:44] logging.py:157 >> {'loss': 0.2863, 'learning_rate': 4.5179e-06, 'epoch': 0.62} + +[INFO|2024-11-25 09:32:05] logging.py:157 >> {'loss': 0.3096, 'learning_rate': 4.5146e-06, 'epoch': 0.62} + +[INFO|2024-11-25 09:32:27] logging.py:157 >> {'loss': 0.2840, 'learning_rate': 4.5113e-06, 'epoch': 0.62} + +[INFO|2024-11-25 09:32:48] logging.py:157 >> {'loss': 0.3541, 'learning_rate': 4.5080e-06, 'epoch': 0.63} + +[INFO|2024-11-25 09:33:08] logging.py:157 >> {'loss': 0.2870, 'learning_rate': 4.5046e-06, 'epoch': 0.63} + +[INFO|2024-11-25 09:33:29] logging.py:157 >> {'loss': 0.2660, 'learning_rate': 4.5013e-06, 'epoch': 0.63} + +[INFO|2024-11-25 09:33:50] logging.py:157 >> {'loss': 0.3637, 'learning_rate': 4.4979e-06, 'epoch': 0.63} + +[INFO|2024-11-25 09:34:11] logging.py:157 >> {'loss': 0.2331, 'learning_rate': 4.4945e-06, 'epoch': 0.63} + +[INFO|2024-11-25 09:34:32] logging.py:157 >> {'loss': 0.2661, 'learning_rate': 4.4912e-06, 'epoch': 0.64} + +[INFO|2024-11-25 09:34:53] logging.py:157 >> {'loss': 0.2305, 'learning_rate': 4.4878e-06, 'epoch': 0.64} + +[INFO|2024-11-25 09:35:15] logging.py:157 >> {'loss': 0.3038, 'learning_rate': 4.4844e-06, 'epoch': 0.64} + +[INFO|2024-11-25 09:35:36] logging.py:157 >> {'loss': 0.1923, 'learning_rate': 4.4810e-06, 'epoch': 0.64} + +[INFO|2024-11-25 09:35:57] logging.py:157 >> {'loss': 0.2522, 'learning_rate': 4.4775e-06, 'epoch': 0.64} + +[INFO|2024-11-25 09:36:18] logging.py:157 >> {'loss': 0.3941, 'learning_rate': 4.4741e-06, 'epoch': 0.65} + +[INFO|2024-11-25 09:36:40] logging.py:157 >> {'loss': 0.2683, 'learning_rate': 4.4707e-06, 'epoch': 0.65} + +[INFO|2024-11-25 09:37:00] logging.py:157 >> {'loss': 0.4248, 'learning_rate': 4.4672e-06, 'epoch': 0.65} + +[INFO|2024-11-25 09:37:21] logging.py:157 >> {'loss': 0.3615, 'learning_rate': 4.4638e-06, 'epoch': 0.65} + +[INFO|2024-11-25 09:37:42] logging.py:157 >> {'loss': 0.1891, 'learning_rate': 4.4603e-06, 'epoch': 0.66} + +[INFO|2024-11-25 09:38:05] logging.py:157 >> {'loss': 0.3321, 'learning_rate': 4.4568e-06, 'epoch': 0.66} + +[INFO|2024-11-25 09:38:26] logging.py:157 >> {'loss': 0.1842, 'learning_rate': 4.4533e-06, 'epoch': 0.66} + +[INFO|2024-11-25 09:38:46] logging.py:157 >> {'loss': 0.2623, 'learning_rate': 4.4498e-06, 'epoch': 0.66} + +[INFO|2024-11-25 09:39:07] logging.py:157 >> {'loss': 0.2996, 'learning_rate': 4.4463e-06, 'epoch': 0.66} + +[INFO|2024-11-25 09:39:29] logging.py:157 >> {'loss': 0.2920, 'learning_rate': 4.4428e-06, 'epoch': 0.67} + +[INFO|2024-11-25 09:39:49] logging.py:157 >> {'loss': 0.3205, 'learning_rate': 4.4393e-06, 'epoch': 0.67} + +[INFO|2024-11-25 09:40:10] logging.py:157 >> {'loss': 0.3059, 'learning_rate': 4.4357e-06, 'epoch': 0.67} + +[INFO|2024-11-25 09:40:32] logging.py:157 >> {'loss': 0.1772, 'learning_rate': 4.4322e-06, 'epoch': 0.67} + +[INFO|2024-11-25 09:40:52] logging.py:157 >> {'loss': 0.2689, 'learning_rate': 4.4286e-06, 'epoch': 0.67} + +[INFO|2024-11-25 09:41:13] logging.py:157 >> {'loss': 0.3262, 'learning_rate': 4.4251e-06, 'epoch': 0.68} + +[INFO|2024-11-25 09:41:33] logging.py:157 >> {'loss': 0.2938, 'learning_rate': 4.4215e-06, 'epoch': 0.68} + +[INFO|2024-11-25 09:41:55] logging.py:157 >> {'loss': 0.2870, 'learning_rate': 4.4179e-06, 'epoch': 0.68} + +[INFO|2024-11-25 09:42:16] logging.py:157 >> {'loss': 0.2534, 'learning_rate': 4.4143e-06, 'epoch': 0.68} + +[INFO|2024-11-25 09:42:37] logging.py:157 >> {'loss': 0.2202, 'learning_rate': 4.4107e-06, 'epoch': 0.68} + +[INFO|2024-11-25 09:42:57] logging.py:157 >> {'loss': 0.2868, 'learning_rate': 4.4071e-06, 'epoch': 0.69} + +[INFO|2024-11-25 09:43:18] logging.py:157 >> {'loss': 0.1661, 'learning_rate': 4.4035e-06, 'epoch': 0.69} + +[INFO|2024-11-25 09:43:38] logging.py:157 >> {'loss': 0.2195, 'learning_rate': 4.3998e-06, 'epoch': 0.69} + +[INFO|2024-11-25 09:43:59] logging.py:157 >> {'loss': 0.2696, 'learning_rate': 4.3962e-06, 'epoch': 0.69} + +[INFO|2024-11-25 09:44:19] logging.py:157 >> {'loss': 0.3592, 'learning_rate': 4.3925e-06, 'epoch': 0.70} + +[INFO|2024-11-25 09:44:39] logging.py:157 >> {'loss': 0.2301, 'learning_rate': 4.3889e-06, 'epoch': 0.70} + +[INFO|2024-11-25 09:44:59] logging.py:157 >> {'loss': 0.2445, 'learning_rate': 4.3852e-06, 'epoch': 0.70} + +[INFO|2024-11-25 09:45:20] logging.py:157 >> {'loss': 0.2830, 'learning_rate': 4.3815e-06, 'epoch': 0.70} + +[INFO|2024-11-25 09:45:42] logging.py:157 >> {'loss': 0.4230, 'learning_rate': 4.3778e-06, 'epoch': 0.70} + +[INFO|2024-11-25 09:46:02] logging.py:157 >> {'loss': 0.3269, 'learning_rate': 4.3741e-06, 'epoch': 0.71} + +[INFO|2024-11-25 09:46:23] logging.py:157 >> {'loss': 0.2774, 'learning_rate': 4.3704e-06, 'epoch': 0.71} + +[INFO|2024-11-25 09:46:46] logging.py:157 >> {'loss': 0.2744, 'learning_rate': 4.3667e-06, 'epoch': 0.71} + +[INFO|2024-11-25 09:47:07] logging.py:157 >> {'loss': 0.3201, 'learning_rate': 4.3630e-06, 'epoch': 0.71} + +[INFO|2024-11-25 09:47:29] logging.py:157 >> {'loss': 0.1742, 'learning_rate': 4.3592e-06, 'epoch': 0.71} + +[INFO|2024-11-25 09:47:51] logging.py:157 >> {'loss': 0.3311, 'learning_rate': 4.3555e-06, 'epoch': 0.72} + +[INFO|2024-11-25 09:48:12] logging.py:157 >> {'loss': 0.2022, 'learning_rate': 4.3517e-06, 'epoch': 0.72} + +[INFO|2024-11-25 09:48:33] logging.py:157 >> {'loss': 0.3076, 'learning_rate': 4.3480e-06, 'epoch': 0.72} + +[INFO|2024-11-25 09:48:54] logging.py:157 >> {'loss': 0.2187, 'learning_rate': 4.3442e-06, 'epoch': 0.72} + +[INFO|2024-11-25 09:49:15] logging.py:157 >> {'loss': 0.2820, 'learning_rate': 4.3404e-06, 'epoch': 0.73} + +[INFO|2024-11-25 09:49:35] logging.py:157 >> {'loss': 0.2898, 'learning_rate': 4.3366e-06, 'epoch': 0.73} + +[INFO|2024-11-25 09:49:56] logging.py:157 >> {'loss': 0.2422, 'learning_rate': 4.3328e-06, 'epoch': 0.73} + +[INFO|2024-11-25 09:50:17] logging.py:157 >> {'loss': 0.2781, 'learning_rate': 4.3290e-06, 'epoch': 0.73} + +[INFO|2024-11-25 09:50:38] logging.py:157 >> {'loss': 0.1749, 'learning_rate': 4.3252e-06, 'epoch': 0.73} + +[INFO|2024-11-25 09:50:59] logging.py:157 >> {'loss': 0.2870, 'learning_rate': 4.3213e-06, 'epoch': 0.74} + +[INFO|2024-11-25 09:51:20] logging.py:157 >> {'loss': 0.2698, 'learning_rate': 4.3175e-06, 'epoch': 0.74} + +[INFO|2024-11-25 09:51:42] logging.py:157 >> {'loss': 0.2312, 'learning_rate': 4.3137e-06, 'epoch': 0.74} + +[INFO|2024-11-25 09:52:04] logging.py:157 >> {'loss': 0.2886, 'learning_rate': 4.3098e-06, 'epoch': 0.74} + +[INFO|2024-11-25 09:52:26] logging.py:157 >> {'loss': 0.2501, 'learning_rate': 4.3059e-06, 'epoch': 0.74} + +[INFO|2024-11-25 09:52:46] logging.py:157 >> {'loss': 0.1851, 'learning_rate': 4.3021e-06, 'epoch': 0.75} + +[INFO|2024-11-25 09:53:07] logging.py:157 >> {'loss': 0.2419, 'learning_rate': 4.2982e-06, 'epoch': 0.75} + +[INFO|2024-11-25 09:53:27] logging.py:157 >> {'loss': 0.2165, 'learning_rate': 4.2943e-06, 'epoch': 0.75} + +[INFO|2024-11-25 09:53:48] logging.py:157 >> {'loss': 0.2562, 'learning_rate': 4.2904e-06, 'epoch': 0.75} + +[INFO|2024-11-25 09:54:08] logging.py:157 >> {'loss': 0.3180, 'learning_rate': 4.2865e-06, 'epoch': 0.75} + +[INFO|2024-11-25 09:54:30] logging.py:157 >> {'loss': 0.2193, 'learning_rate': 4.2825e-06, 'epoch': 0.76} + +[INFO|2024-11-25 09:54:51] logging.py:157 >> {'loss': 0.2466, 'learning_rate': 4.2786e-06, 'epoch': 0.76} + +[INFO|2024-11-25 09:55:11] logging.py:157 >> {'loss': 0.2749, 'learning_rate': 4.2747e-06, 'epoch': 0.76} + +[INFO|2024-11-25 09:55:32] logging.py:157 >> {'loss': 0.3133, 'learning_rate': 4.2707e-06, 'epoch': 0.76} + +[INFO|2024-11-25 09:55:52] logging.py:157 >> {'loss': 0.3188, 'learning_rate': 4.2668e-06, 'epoch': 0.77} + +[INFO|2024-11-25 09:56:14] logging.py:157 >> {'loss': 0.3409, 'learning_rate': 4.2628e-06, 'epoch': 0.77} + +[INFO|2024-11-25 09:56:35] logging.py:157 >> {'loss': 0.2538, 'learning_rate': 4.2588e-06, 'epoch': 0.77} + +[INFO|2024-11-25 09:56:57] logging.py:157 >> {'loss': 0.2741, 'learning_rate': 4.2549e-06, 'epoch': 0.77} + +[INFO|2024-11-25 09:57:18] logging.py:157 >> {'loss': 0.2353, 'learning_rate': 4.2509e-06, 'epoch': 0.77} + +[INFO|2024-11-25 09:57:38] logging.py:157 >> {'loss': 0.2585, 'learning_rate': 4.2469e-06, 'epoch': 0.78} + +[INFO|2024-11-25 09:58:00] logging.py:157 >> {'loss': 0.2143, 'learning_rate': 4.2429e-06, 'epoch': 0.78} + +[INFO|2024-11-25 09:58:22] logging.py:157 >> {'loss': 0.1835, 'learning_rate': 4.2388e-06, 'epoch': 0.78} + +[INFO|2024-11-25 09:58:44] logging.py:157 >> {'loss': 0.2107, 'learning_rate': 4.2348e-06, 'epoch': 0.78} + +[INFO|2024-11-25 09:59:05] logging.py:157 >> {'loss': 0.2497, 'learning_rate': 4.2308e-06, 'epoch': 0.78} + +[INFO|2024-11-25 09:59:26] logging.py:157 >> {'loss': 0.2577, 'learning_rate': 4.2267e-06, 'epoch': 0.79} + +[INFO|2024-11-25 09:59:48] logging.py:157 >> {'loss': 0.1978, 'learning_rate': 4.2227e-06, 'epoch': 0.79} + +[INFO|2024-11-25 10:00:09] logging.py:157 >> {'loss': 0.2462, 'learning_rate': 4.2186e-06, 'epoch': 0.79} + +[INFO|2024-11-25 10:00:32] logging.py:157 >> {'loss': 0.2740, 'learning_rate': 4.2145e-06, 'epoch': 0.79} + +[INFO|2024-11-25 10:00:53] logging.py:157 >> {'loss': 0.3099, 'learning_rate': 4.2105e-06, 'epoch': 0.80} + +[INFO|2024-11-25 10:01:14] logging.py:157 >> {'loss': 0.4174, 'learning_rate': 4.2064e-06, 'epoch': 0.80} + +[INFO|2024-11-25 10:01:35] logging.py:157 >> {'loss': 0.2273, 'learning_rate': 4.2023e-06, 'epoch': 0.80} + +[INFO|2024-11-25 10:01:57] logging.py:157 >> {'loss': 0.1472, 'learning_rate': 4.1982e-06, 'epoch': 0.80} + +[INFO|2024-11-25 10:02:19] logging.py:157 >> {'loss': 0.3014, 'learning_rate': 4.1941e-06, 'epoch': 0.80} + +[INFO|2024-11-25 10:02:39] logging.py:157 >> {'loss': 0.2107, 'learning_rate': 4.1899e-06, 'epoch': 0.81} + +[INFO|2024-11-25 10:03:00] logging.py:157 >> {'loss': 0.2336, 'learning_rate': 4.1858e-06, 'epoch': 0.81} + +[INFO|2024-11-25 10:03:22] logging.py:157 >> {'loss': 0.3076, 'learning_rate': 4.1817e-06, 'epoch': 0.81} + +[INFO|2024-11-25 10:03:42] logging.py:157 >> {'loss': 0.2436, 'learning_rate': 4.1775e-06, 'epoch': 0.81} + +[INFO|2024-11-25 10:04:03] logging.py:157 >> {'loss': 0.3278, 'learning_rate': 4.1734e-06, 'epoch': 0.81} + +[INFO|2024-11-25 10:04:25] logging.py:157 >> {'loss': 0.3002, 'learning_rate': 4.1692e-06, 'epoch': 0.82} + +[INFO|2024-11-25 10:04:45] logging.py:157 >> {'loss': 0.2263, 'learning_rate': 4.1650e-06, 'epoch': 0.82} + +[INFO|2024-11-25 10:05:06] logging.py:157 >> {'loss': 0.2967, 'learning_rate': 4.1609e-06, 'epoch': 0.82} + +[INFO|2024-11-25 10:05:27] logging.py:157 >> {'loss': 0.2266, 'learning_rate': 4.1567e-06, 'epoch': 0.82} + +[INFO|2024-11-25 10:05:48] logging.py:157 >> {'loss': 0.3302, 'learning_rate': 4.1525e-06, 'epoch': 0.82} + +[INFO|2024-11-25 10:06:09] logging.py:157 >> {'loss': 0.2646, 'learning_rate': 4.1483e-06, 'epoch': 0.83} + +[INFO|2024-11-25 10:06:30] logging.py:157 >> {'loss': 0.3638, 'learning_rate': 4.1441e-06, 'epoch': 0.83} + +[INFO|2024-11-25 10:06:51] logging.py:157 >> {'loss': 0.1704, 'learning_rate': 4.1398e-06, 'epoch': 0.83} + +[INFO|2024-11-25 10:07:11] logging.py:157 >> {'loss': 0.2594, 'learning_rate': 4.1356e-06, 'epoch': 0.83} + +[INFO|2024-11-25 10:07:32] logging.py:157 >> {'loss': 0.2068, 'learning_rate': 4.1314e-06, 'epoch': 0.84} + +[INFO|2024-11-25 10:07:53] logging.py:157 >> {'loss': 0.1623, 'learning_rate': 4.1271e-06, 'epoch': 0.84} + +[INFO|2024-11-25 10:08:14] logging.py:157 >> {'loss': 0.1622, 'learning_rate': 4.1229e-06, 'epoch': 0.84} + +[INFO|2024-11-25 10:08:35] logging.py:157 >> {'loss': 0.3365, 'learning_rate': 4.1186e-06, 'epoch': 0.84} + +[INFO|2024-11-25 10:08:55] logging.py:157 >> {'loss': 0.2857, 'learning_rate': 4.1143e-06, 'epoch': 0.84} + +[INFO|2024-11-25 10:09:16] logging.py:157 >> {'loss': 0.2944, 'learning_rate': 4.1101e-06, 'epoch': 0.85} + +[INFO|2024-11-25 10:09:37] logging.py:157 >> {'loss': 0.2156, 'learning_rate': 4.1058e-06, 'epoch': 0.85} + +[INFO|2024-11-25 10:09:56] logging.py:157 >> {'loss': 0.2235, 'learning_rate': 4.1015e-06, 'epoch': 0.85} + +[INFO|2024-11-25 10:10:18] logging.py:157 >> {'loss': 0.1273, 'learning_rate': 4.0972e-06, 'epoch': 0.85} + +[INFO|2024-11-25 10:10:40] logging.py:157 >> {'loss': 0.3338, 'learning_rate': 4.0929e-06, 'epoch': 0.85} + +[INFO|2024-11-25 10:11:01] logging.py:157 >> {'loss': 0.2359, 'learning_rate': 4.0886e-06, 'epoch': 0.86} + +[INFO|2024-11-25 10:11:21] logging.py:157 >> {'loss': 0.2267, 'learning_rate': 4.0842e-06, 'epoch': 0.86} + +[INFO|2024-11-25 10:11:43] logging.py:157 >> {'loss': 0.1329, 'learning_rate': 4.0799e-06, 'epoch': 0.86} + +[INFO|2024-11-25 10:12:04] logging.py:157 >> {'loss': 0.2221, 'learning_rate': 4.0755e-06, 'epoch': 0.86} + +[INFO|2024-11-25 10:12:25] logging.py:157 >> {'loss': 0.3571, 'learning_rate': 4.0712e-06, 'epoch': 0.87} + +[INFO|2024-11-25 10:12:47] logging.py:157 >> {'loss': 0.2470, 'learning_rate': 4.0668e-06, 'epoch': 0.87} + +[INFO|2024-11-25 10:13:07] logging.py:157 >> {'loss': 0.2483, 'learning_rate': 4.0625e-06, 'epoch': 0.87} + +[INFO|2024-11-25 10:13:28] logging.py:157 >> {'loss': 0.2748, 'learning_rate': 4.0581e-06, 'epoch': 0.87} + +[INFO|2024-11-25 10:13:49] logging.py:157 >> {'loss': 0.1534, 'learning_rate': 4.0537e-06, 'epoch': 0.87} + +[INFO|2024-11-25 10:14:09] logging.py:157 >> {'loss': 0.3573, 'learning_rate': 4.0493e-06, 'epoch': 0.88} + +[INFO|2024-11-25 10:14:30] logging.py:157 >> {'loss': 0.3242, 'learning_rate': 4.0449e-06, 'epoch': 0.88} + +[INFO|2024-11-25 10:14:50] logging.py:157 >> {'loss': 0.2101, 'learning_rate': 4.0405e-06, 'epoch': 0.88} + +[INFO|2024-11-25 10:15:12] logging.py:157 >> {'loss': 0.2115, 'learning_rate': 4.0361e-06, 'epoch': 0.88} + +[INFO|2024-11-25 10:15:34] logging.py:157 >> {'loss': 0.2740, 'learning_rate': 4.0317e-06, 'epoch': 0.88} + +[INFO|2024-11-25 10:15:55] logging.py:157 >> {'loss': 0.4542, 'learning_rate': 4.0273e-06, 'epoch': 0.89} + +[INFO|2024-11-25 10:16:18] logging.py:157 >> {'loss': 0.2008, 'learning_rate': 4.0228e-06, 'epoch': 0.89} + +[INFO|2024-11-25 10:16:38] logging.py:157 >> {'loss': 0.2777, 'learning_rate': 4.0184e-06, 'epoch': 0.89} + +[INFO|2024-11-25 10:16:59] logging.py:157 >> {'loss': 0.2378, 'learning_rate': 4.0139e-06, 'epoch': 0.89} + +[INFO|2024-11-25 10:17:20] logging.py:157 >> {'loss': 0.2469, 'learning_rate': 4.0095e-06, 'epoch': 0.89} + +[INFO|2024-11-25 10:17:41] logging.py:157 >> {'loss': 0.2247, 'learning_rate': 4.0050e-06, 'epoch': 0.90} + +[INFO|2024-11-25 10:18:01] logging.py:157 >> {'loss': 0.2117, 'learning_rate': 4.0005e-06, 'epoch': 0.90} + +[INFO|2024-11-25 10:18:22] logging.py:157 >> {'loss': 0.2591, 'learning_rate': 3.9961e-06, 'epoch': 0.90} + +[INFO|2024-11-25 10:18:42] logging.py:157 >> {'loss': 0.2905, 'learning_rate': 3.9916e-06, 'epoch': 0.90} + +[INFO|2024-11-25 10:19:02] logging.py:157 >> {'loss': 0.2980, 'learning_rate': 3.9871e-06, 'epoch': 0.91} + +[INFO|2024-11-25 10:19:24] logging.py:157 >> {'loss': 0.4034, 'learning_rate': 3.9826e-06, 'epoch': 0.91} + +[INFO|2024-11-25 10:19:46] logging.py:157 >> {'loss': 0.2176, 'learning_rate': 3.9781e-06, 'epoch': 0.91} + +[INFO|2024-11-25 10:20:08] logging.py:157 >> {'loss': 0.2228, 'learning_rate': 3.9735e-06, 'epoch': 0.91} + +[INFO|2024-11-25 10:20:29] logging.py:157 >> {'loss': 0.2471, 'learning_rate': 3.9690e-06, 'epoch': 0.91} + +[INFO|2024-11-25 10:20:49] logging.py:157 >> {'loss': 0.1858, 'learning_rate': 3.9645e-06, 'epoch': 0.92} + +[INFO|2024-11-25 10:21:11] logging.py:157 >> {'loss': 0.2178, 'learning_rate': 3.9599e-06, 'epoch': 0.92} + +[INFO|2024-11-25 10:21:32] logging.py:157 >> {'loss': 0.2695, 'learning_rate': 3.9554e-06, 'epoch': 0.92} + +[INFO|2024-11-25 10:21:53] logging.py:157 >> {'loss': 0.2193, 'learning_rate': 3.9508e-06, 'epoch': 0.92} + +[INFO|2024-11-25 10:22:14] logging.py:157 >> {'loss': 0.2479, 'learning_rate': 3.9463e-06, 'epoch': 0.92} + +[INFO|2024-11-25 10:22:36] logging.py:157 >> {'loss': 0.3304, 'learning_rate': 3.9417e-06, 'epoch': 0.93} + +[INFO|2024-11-25 10:22:57] logging.py:157 >> {'loss': 0.2871, 'learning_rate': 3.9371e-06, 'epoch': 0.93} + +[INFO|2024-11-25 10:23:18] logging.py:157 >> {'loss': 0.2042, 'learning_rate': 3.9325e-06, 'epoch': 0.93} + +[INFO|2024-11-25 10:23:40] logging.py:157 >> {'loss': 0.2500, 'learning_rate': 3.9279e-06, 'epoch': 0.93} + +[INFO|2024-11-25 10:24:01] logging.py:157 >> {'loss': 0.2686, 'learning_rate': 3.9233e-06, 'epoch': 0.94} + +[INFO|2024-11-25 10:24:23] logging.py:157 >> {'loss': 0.2693, 'learning_rate': 3.9187e-06, 'epoch': 0.94} + +[INFO|2024-11-25 10:24:47] logging.py:157 >> {'loss': 0.2578, 'learning_rate': 3.9141e-06, 'epoch': 0.94} + +[INFO|2024-11-25 10:25:08] logging.py:157 >> {'loss': 0.2780, 'learning_rate': 3.9095e-06, 'epoch': 0.94} + +[INFO|2024-11-25 10:25:29] logging.py:157 >> {'loss': 0.2269, 'learning_rate': 3.9049e-06, 'epoch': 0.94} + +[INFO|2024-11-25 10:25:49] logging.py:157 >> {'loss': 0.2526, 'learning_rate': 3.9003e-06, 'epoch': 0.95} + +[INFO|2024-11-25 10:26:09] logging.py:157 >> {'loss': 0.2397, 'learning_rate': 3.8956e-06, 'epoch': 0.95} + +[INFO|2024-11-25 10:26:30] logging.py:157 >> {'loss': 0.2516, 'learning_rate': 3.8910e-06, 'epoch': 0.95} + +[INFO|2024-11-25 10:26:51] logging.py:157 >> {'loss': 0.2889, 'learning_rate': 3.8863e-06, 'epoch': 0.95} + +[INFO|2024-11-25 10:27:12] logging.py:157 >> {'loss': 0.3136, 'learning_rate': 3.8816e-06, 'epoch': 0.95} + +[INFO|2024-11-25 10:27:33] logging.py:157 >> {'loss': 0.2424, 'learning_rate': 3.8770e-06, 'epoch': 0.96} + +[INFO|2024-11-25 10:27:56] logging.py:157 >> {'loss': 0.2841, 'learning_rate': 3.8723e-06, 'epoch': 0.96} + +[INFO|2024-11-25 10:28:17] logging.py:157 >> {'loss': 0.2141, 'learning_rate': 3.8676e-06, 'epoch': 0.96} + +[INFO|2024-11-25 10:28:39] logging.py:157 >> {'loss': 0.2419, 'learning_rate': 3.8629e-06, 'epoch': 0.96} + +[INFO|2024-11-25 10:29:03] logging.py:157 >> {'loss': 0.2179, 'learning_rate': 3.8582e-06, 'epoch': 0.96} + +[INFO|2024-11-25 10:29:26] logging.py:157 >> {'loss': 0.2963, 'learning_rate': 3.8535e-06, 'epoch': 0.97} + +[INFO|2024-11-25 10:29:48] logging.py:157 >> {'loss': 0.2386, 'learning_rate': 3.8488e-06, 'epoch': 0.97} + +[INFO|2024-11-25 10:30:11] logging.py:157 >> {'loss': 0.1932, 'learning_rate': 3.8441e-06, 'epoch': 0.97} + +[INFO|2024-11-25 10:30:33] logging.py:157 >> {'loss': 0.2455, 'learning_rate': 3.8394e-06, 'epoch': 0.97} + +[INFO|2024-11-25 10:30:55] logging.py:157 >> {'loss': 0.2605, 'learning_rate': 3.8346e-06, 'epoch': 0.98} + +[INFO|2024-11-25 10:31:16] logging.py:157 >> {'loss': 0.2600, 'learning_rate': 3.8299e-06, 'epoch': 0.98} + +[INFO|2024-11-25 10:31:37] logging.py:157 >> {'loss': 0.2549, 'learning_rate': 3.8252e-06, 'epoch': 0.98} + +[INFO|2024-11-25 10:31:58] logging.py:157 >> {'loss': 0.1391, 'learning_rate': 3.8204e-06, 'epoch': 0.98} + +[INFO|2024-11-25 10:32:20] logging.py:157 >> {'loss': 0.3050, 'learning_rate': 3.8157e-06, 'epoch': 0.98} + +[INFO|2024-11-25 10:32:40] logging.py:157 >> {'loss': 0.3457, 'learning_rate': 3.8109e-06, 'epoch': 0.99} + +[INFO|2024-11-25 10:33:00] logging.py:157 >> {'loss': 0.2261, 'learning_rate': 3.8061e-06, 'epoch': 0.99} + +[INFO|2024-11-25 10:33:21] logging.py:157 >> {'loss': 0.2855, 'learning_rate': 3.8014e-06, 'epoch': 0.99} + +[INFO|2024-11-25 10:33:42] logging.py:157 >> {'loss': 0.1904, 'learning_rate': 3.7966e-06, 'epoch': 0.99} + +[INFO|2024-11-25 10:34:04] logging.py:157 >> {'loss': 0.2144, 'learning_rate': 3.7918e-06, 'epoch': 0.99} + +[INFO|2024-11-25 10:34:25] logging.py:157 >> {'loss': 0.1962, 'learning_rate': 3.7870e-06, 'epoch': 1.00} + +[INFO|2024-11-25 10:34:47] logging.py:157 >> {'loss': 0.2887, 'learning_rate': 3.7822e-06, 'epoch': 1.00} + +[INFO|2024-11-25 10:35:08] logging.py:157 >> {'loss': 0.2933, 'learning_rate': 3.7774e-06, 'epoch': 1.00} + +[INFO|2024-11-25 10:35:28] logging.py:157 >> {'loss': 0.2159, 'learning_rate': 3.7726e-06, 'epoch': 1.00} + +[INFO|2024-11-25 10:35:50] logging.py:157 >> {'loss': 0.3206, 'learning_rate': 3.7677e-06, 'epoch': 1.01} + +[INFO|2024-11-25 10:36:11] logging.py:157 >> {'loss': 0.2397, 'learning_rate': 3.7629e-06, 'epoch': 1.01} + +[INFO|2024-11-25 10:36:32] logging.py:157 >> {'loss': 0.2207, 'learning_rate': 3.7581e-06, 'epoch': 1.01} + +[INFO|2024-11-25 10:36:54] logging.py:157 >> {'loss': 0.2817, 'learning_rate': 3.7532e-06, 'epoch': 1.01} + +[INFO|2024-11-25 10:37:16] logging.py:157 >> {'loss': 0.2123, 'learning_rate': 3.7484e-06, 'epoch': 1.01} + +[INFO|2024-11-25 10:37:37] logging.py:157 >> {'loss': 0.2889, 'learning_rate': 3.7435e-06, 'epoch': 1.02} + +[INFO|2024-11-25 10:37:59] logging.py:157 >> {'loss': 0.2517, 'learning_rate': 3.7387e-06, 'epoch': 1.02} + +[INFO|2024-11-25 10:38:20] logging.py:157 >> {'loss': 0.2451, 'learning_rate': 3.7338e-06, 'epoch': 1.02} + +[INFO|2024-11-25 10:38:41] logging.py:157 >> {'loss': 0.2594, 'learning_rate': 3.7289e-06, 'epoch': 1.02} + +[INFO|2024-11-25 10:39:02] logging.py:157 >> {'loss': 0.2706, 'learning_rate': 3.7241e-06, 'epoch': 1.02} + +[INFO|2024-11-25 10:39:23] logging.py:157 >> {'loss': 0.2099, 'learning_rate': 3.7192e-06, 'epoch': 1.03} + +[INFO|2024-11-25 10:39:44] logging.py:157 >> {'loss': 0.3406, 'learning_rate': 3.7143e-06, 'epoch': 1.03} + +[INFO|2024-11-25 10:40:05] logging.py:157 >> {'loss': 0.2251, 'learning_rate': 3.7094e-06, 'epoch': 1.03} + +[INFO|2024-11-25 10:40:27] logging.py:157 >> {'loss': 0.1466, 'learning_rate': 3.7045e-06, 'epoch': 1.03} + +[INFO|2024-11-25 10:40:47] logging.py:157 >> {'loss': 0.3749, 'learning_rate': 3.6996e-06, 'epoch': 1.04} + +[INFO|2024-11-25 10:41:08] logging.py:157 >> {'loss': 0.2145, 'learning_rate': 3.6947e-06, 'epoch': 1.04} + +[INFO|2024-11-25 10:41:29] logging.py:157 >> {'loss': 0.1499, 'learning_rate': 3.6897e-06, 'epoch': 1.04} + +[INFO|2024-11-25 10:41:50] logging.py:157 >> {'loss': 0.2445, 'learning_rate': 3.6848e-06, 'epoch': 1.04} + +[INFO|2024-11-25 10:42:11] logging.py:157 >> {'loss': 0.2568, 'learning_rate': 3.6799e-06, 'epoch': 1.04} + +[INFO|2024-11-25 10:42:34] logging.py:157 >> {'loss': 0.1574, 'learning_rate': 3.6749e-06, 'epoch': 1.05} + +[INFO|2024-11-25 10:42:55] logging.py:157 >> {'loss': 0.2175, 'learning_rate': 3.6700e-06, 'epoch': 1.05} + +[INFO|2024-11-25 10:43:15] logging.py:157 >> {'loss': 0.2276, 'learning_rate': 3.6650e-06, 'epoch': 1.05} + +[INFO|2024-11-25 10:43:36] logging.py:157 >> {'loss': 0.1829, 'learning_rate': 3.6601e-06, 'epoch': 1.05} + +[INFO|2024-11-25 10:43:58] logging.py:157 >> {'loss': 0.1972, 'learning_rate': 3.6551e-06, 'epoch': 1.05} + +[INFO|2024-11-25 10:44:18] logging.py:157 >> {'loss': 0.1839, 'learning_rate': 3.6502e-06, 'epoch': 1.06} + +[INFO|2024-11-25 10:44:40] logging.py:157 >> {'loss': 0.2619, 'learning_rate': 3.6452e-06, 'epoch': 1.06} + +[INFO|2024-11-25 10:45:01] logging.py:157 >> {'loss': 0.2554, 'learning_rate': 3.6402e-06, 'epoch': 1.06} + +[INFO|2024-11-25 10:45:22] logging.py:157 >> {'loss': 0.2435, 'learning_rate': 3.6352e-06, 'epoch': 1.06} + +[INFO|2024-11-25 10:45:43] logging.py:157 >> {'loss': 0.2017, 'learning_rate': 3.6302e-06, 'epoch': 1.07} + +[INFO|2024-11-25 10:46:03] logging.py:157 >> {'loss': 0.2504, 'learning_rate': 3.6252e-06, 'epoch': 1.07} + +[INFO|2024-11-25 10:46:23] logging.py:157 >> {'loss': 0.2066, 'learning_rate': 3.6202e-06, 'epoch': 1.07} + +[INFO|2024-11-25 10:46:44] logging.py:157 >> {'loss': 0.3272, 'learning_rate': 3.6152e-06, 'epoch': 1.07} + +[INFO|2024-11-25 10:47:05] logging.py:157 >> {'loss': 0.1846, 'learning_rate': 3.6102e-06, 'epoch': 1.07} + +[INFO|2024-11-25 10:47:26] logging.py:157 >> {'loss': 0.1817, 'learning_rate': 3.6052e-06, 'epoch': 1.08} + +[INFO|2024-11-25 10:47:48] logging.py:157 >> {'loss': 0.1909, 'learning_rate': 3.6002e-06, 'epoch': 1.08} + +[INFO|2024-11-25 10:48:08] logging.py:157 >> {'loss': 0.2923, 'learning_rate': 3.5951e-06, 'epoch': 1.08} + +[INFO|2024-11-25 10:48:29] logging.py:157 >> {'loss': 0.1405, 'learning_rate': 3.5901e-06, 'epoch': 1.08} + +[INFO|2024-11-25 10:48:50] logging.py:157 >> {'loss': 0.1853, 'learning_rate': 3.5851e-06, 'epoch': 1.08} + +[INFO|2024-11-25 10:49:10] logging.py:157 >> {'loss': 0.1181, 'learning_rate': 3.5800e-06, 'epoch': 1.09} + +[INFO|2024-11-25 10:49:31] logging.py:157 >> {'loss': 0.2086, 'learning_rate': 3.5750e-06, 'epoch': 1.09} + +[INFO|2024-11-25 10:49:53] logging.py:157 >> {'loss': 0.2020, 'learning_rate': 3.5699e-06, 'epoch': 1.09} + +[INFO|2024-11-25 10:50:15] logging.py:157 >> {'loss': 0.1522, 'learning_rate': 3.5649e-06, 'epoch': 1.09} + +[INFO|2024-11-25 10:50:36] logging.py:157 >> {'loss': 0.1442, 'learning_rate': 3.5598e-06, 'epoch': 1.09} + +[INFO|2024-11-25 10:50:57] logging.py:157 >> {'loss': 0.2109, 'learning_rate': 3.5547e-06, 'epoch': 1.10} + +[INFO|2024-11-25 10:51:20] logging.py:157 >> {'loss': 0.2269, 'learning_rate': 3.5496e-06, 'epoch': 1.10} + +[INFO|2024-11-25 10:51:41] logging.py:157 >> {'loss': 0.2547, 'learning_rate': 3.5446e-06, 'epoch': 1.10} + +[INFO|2024-11-25 10:52:03] logging.py:157 >> {'loss': 0.1796, 'learning_rate': 3.5395e-06, 'epoch': 1.10} + +[INFO|2024-11-25 10:52:25] logging.py:157 >> {'loss': 0.1957, 'learning_rate': 3.5344e-06, 'epoch': 1.11} + +[INFO|2024-11-25 10:52:46] logging.py:157 >> {'loss': 0.2102, 'learning_rate': 3.5293e-06, 'epoch': 1.11} + +[INFO|2024-11-25 10:53:06] logging.py:157 >> {'loss': 0.1964, 'learning_rate': 3.5242e-06, 'epoch': 1.11} + +[INFO|2024-11-25 10:53:27] logging.py:157 >> {'loss': 0.2761, 'learning_rate': 3.5191e-06, 'epoch': 1.11} + +[INFO|2024-11-25 10:53:48] logging.py:157 >> {'loss': 0.1444, 'learning_rate': 3.5139e-06, 'epoch': 1.11} + +[INFO|2024-11-25 10:54:10] logging.py:157 >> {'loss': 0.2643, 'learning_rate': 3.5088e-06, 'epoch': 1.12} + +[INFO|2024-11-25 10:54:30] logging.py:157 >> {'loss': 0.1631, 'learning_rate': 3.5037e-06, 'epoch': 1.12} + +[INFO|2024-11-25 10:54:51] logging.py:157 >> {'loss': 0.2681, 'learning_rate': 3.4986e-06, 'epoch': 1.12} + +[INFO|2024-11-25 10:55:12] logging.py:157 >> {'loss': 0.2678, 'learning_rate': 3.4934e-06, 'epoch': 1.12} + +[INFO|2024-11-25 10:55:33] logging.py:157 >> {'loss': 0.2070, 'learning_rate': 3.4883e-06, 'epoch': 1.12} + +[INFO|2024-11-25 10:55:53] logging.py:157 >> {'loss': 0.2050, 'learning_rate': 3.4832e-06, 'epoch': 1.13} + +[INFO|2024-11-25 10:56:16] logging.py:157 >> {'loss': 0.1029, 'learning_rate': 3.4780e-06, 'epoch': 1.13} + +[INFO|2024-11-25 10:56:36] logging.py:157 >> {'loss': 0.2622, 'learning_rate': 3.4728e-06, 'epoch': 1.13} + +[INFO|2024-11-25 10:56:58] logging.py:157 >> {'loss': 0.1952, 'learning_rate': 3.4677e-06, 'epoch': 1.13} + +[INFO|2024-11-25 10:57:19] logging.py:157 >> {'loss': 0.1626, 'learning_rate': 3.4625e-06, 'epoch': 1.14} + +[INFO|2024-11-25 10:57:40] logging.py:157 >> {'loss': 0.2611, 'learning_rate': 3.4574e-06, 'epoch': 1.14} + +[INFO|2024-11-25 10:58:02] logging.py:157 >> {'loss': 0.1755, 'learning_rate': 3.4522e-06, 'epoch': 1.14} + +[INFO|2024-11-25 10:58:23] logging.py:157 >> {'loss': 0.2990, 'learning_rate': 3.4470e-06, 'epoch': 1.14} + +[INFO|2024-11-25 10:58:43] logging.py:157 >> {'loss': 0.1295, 'learning_rate': 3.4418e-06, 'epoch': 1.14} + +[INFO|2024-11-25 10:59:05] logging.py:157 >> {'loss': 0.1765, 'learning_rate': 3.4366e-06, 'epoch': 1.15} + +[INFO|2024-11-25 10:59:25] logging.py:157 >> {'loss': 0.1285, 'learning_rate': 3.4314e-06, 'epoch': 1.15} + +[INFO|2024-11-25 10:59:45] logging.py:157 >> {'loss': 0.3035, 'learning_rate': 3.4262e-06, 'epoch': 1.15} + +[INFO|2024-11-25 11:00:07] logging.py:157 >> {'loss': 0.2073, 'learning_rate': 3.4210e-06, 'epoch': 1.15} + +[INFO|2024-11-25 11:00:28] logging.py:157 >> {'loss': 0.1855, 'learning_rate': 3.4158e-06, 'epoch': 1.15} + +[INFO|2024-11-25 11:00:48] logging.py:157 >> {'loss': 0.2083, 'learning_rate': 3.4106e-06, 'epoch': 1.16} + +[INFO|2024-11-25 11:01:09] logging.py:157 >> {'loss': 0.2057, 'learning_rate': 3.4054e-06, 'epoch': 1.16} + +[INFO|2024-11-25 11:01:32] logging.py:157 >> {'loss': 0.2622, 'learning_rate': 3.4002e-06, 'epoch': 1.16} + +[INFO|2024-11-25 11:01:53] logging.py:157 >> {'loss': 0.2356, 'learning_rate': 3.3950e-06, 'epoch': 1.16} + +[INFO|2024-11-25 11:02:15] logging.py:157 >> {'loss': 0.2543, 'learning_rate': 3.3897e-06, 'epoch': 1.16} + +[INFO|2024-11-25 11:02:35] logging.py:157 >> {'loss': 0.1877, 'learning_rate': 3.3845e-06, 'epoch': 1.17} + +[INFO|2024-11-25 11:02:57] logging.py:157 >> {'loss': 0.2394, 'learning_rate': 3.3793e-06, 'epoch': 1.17} + +[INFO|2024-11-25 11:03:19] logging.py:157 >> {'loss': 0.2510, 'learning_rate': 3.3740e-06, 'epoch': 1.17} + +[INFO|2024-11-25 11:03:41] logging.py:157 >> {'loss': 0.1074, 'learning_rate': 3.3688e-06, 'epoch': 1.17} + +[INFO|2024-11-25 11:04:04] logging.py:157 >> {'loss': 0.1926, 'learning_rate': 3.3635e-06, 'epoch': 1.18} + +[INFO|2024-11-25 11:04:24] logging.py:157 >> {'loss': 0.1456, 'learning_rate': 3.3583e-06, 'epoch': 1.18} + +[INFO|2024-11-25 11:04:46] logging.py:157 >> {'loss': 0.2445, 'learning_rate': 3.3530e-06, 'epoch': 1.18} + +[INFO|2024-11-25 11:05:07] logging.py:157 >> {'loss': 0.2098, 'learning_rate': 3.3477e-06, 'epoch': 1.18} + +[INFO|2024-11-25 11:05:28] logging.py:157 >> {'loss': 0.2096, 'learning_rate': 3.3425e-06, 'epoch': 1.18} + +[INFO|2024-11-25 11:05:50] logging.py:157 >> {'loss': 0.2537, 'learning_rate': 3.3372e-06, 'epoch': 1.19} + +[INFO|2024-11-25 11:06:11] logging.py:157 >> {'loss': 0.1266, 'learning_rate': 3.3319e-06, 'epoch': 1.19} + +[INFO|2024-11-25 11:06:33] logging.py:157 >> {'loss': 0.2436, 'learning_rate': 3.3266e-06, 'epoch': 1.19} + +[INFO|2024-11-25 11:06:54] logging.py:157 >> {'loss': 0.2720, 'learning_rate': 3.3214e-06, 'epoch': 1.19} + +[INFO|2024-11-25 11:07:15] logging.py:157 >> {'loss': 0.1754, 'learning_rate': 3.3161e-06, 'epoch': 1.19} + +[INFO|2024-11-25 11:07:36] logging.py:157 >> {'loss': 0.2089, 'learning_rate': 3.3108e-06, 'epoch': 1.20} + +[INFO|2024-11-25 11:07:57] logging.py:157 >> {'loss': 0.1492, 'learning_rate': 3.3055e-06, 'epoch': 1.20} + +[INFO|2024-11-25 11:08:18] logging.py:157 >> {'loss': 0.1841, 'learning_rate': 3.3002e-06, 'epoch': 1.20} + +[INFO|2024-11-25 11:08:40] logging.py:157 >> {'loss': 0.1904, 'learning_rate': 3.2949e-06, 'epoch': 1.20} + +[INFO|2024-11-25 11:09:01] logging.py:157 >> {'loss': 0.2079, 'learning_rate': 3.2896e-06, 'epoch': 1.21} + +[INFO|2024-11-25 11:09:22] logging.py:157 >> {'loss': 0.2065, 'learning_rate': 3.2842e-06, 'epoch': 1.21} + +[INFO|2024-11-25 11:09:43] logging.py:157 >> {'loss': 0.1667, 'learning_rate': 3.2789e-06, 'epoch': 1.21} + +[INFO|2024-11-25 11:10:05] logging.py:157 >> {'loss': 0.1957, 'learning_rate': 3.2736e-06, 'epoch': 1.21} + +[INFO|2024-11-25 11:10:27] logging.py:157 >> {'loss': 0.1717, 'learning_rate': 3.2683e-06, 'epoch': 1.21} + +[INFO|2024-11-25 11:10:47] logging.py:157 >> {'loss': 0.2692, 'learning_rate': 3.2630e-06, 'epoch': 1.22} + +[INFO|2024-11-25 11:11:08] logging.py:157 >> {'loss': 0.2230, 'learning_rate': 3.2576e-06, 'epoch': 1.22} + +[INFO|2024-11-25 11:11:28] logging.py:157 >> {'loss': 0.2378, 'learning_rate': 3.2523e-06, 'epoch': 1.22} + +[INFO|2024-11-25 11:11:50] logging.py:157 >> {'loss': 0.3113, 'learning_rate': 3.2469e-06, 'epoch': 1.22} + +[INFO|2024-11-25 11:12:11] logging.py:157 >> {'loss': 0.2094, 'learning_rate': 3.2416e-06, 'epoch': 1.22} + +[INFO|2024-11-25 11:12:31] logging.py:157 >> {'loss': 0.2860, 'learning_rate': 3.2363e-06, 'epoch': 1.23} + +[INFO|2024-11-25 11:12:54] logging.py:157 >> {'loss': 0.1752, 'learning_rate': 3.2309e-06, 'epoch': 1.23} + +[INFO|2024-11-25 11:13:14] logging.py:157 >> {'loss': 0.2184, 'learning_rate': 3.2255e-06, 'epoch': 1.23} + +[INFO|2024-11-25 11:13:34] logging.py:157 >> {'loss': 0.2721, 'learning_rate': 3.2202e-06, 'epoch': 1.23} + +[INFO|2024-11-25 11:13:55] logging.py:157 >> {'loss': 0.3589, 'learning_rate': 3.2148e-06, 'epoch': 1.23} + +[INFO|2024-11-25 11:14:16] logging.py:157 >> {'loss': 0.2667, 'learning_rate': 3.2095e-06, 'epoch': 1.24} + +[INFO|2024-11-25 11:14:37] logging.py:157 >> {'loss': 0.2865, 'learning_rate': 3.2041e-06, 'epoch': 1.24} + +[INFO|2024-11-25 11:14:58] logging.py:157 >> {'loss': 0.2693, 'learning_rate': 3.1987e-06, 'epoch': 1.24} + +[INFO|2024-11-25 11:15:18] logging.py:157 >> {'loss': 0.1966, 'learning_rate': 3.1933e-06, 'epoch': 1.24} + +[INFO|2024-11-25 11:15:39] logging.py:157 >> {'loss': 0.1645, 'learning_rate': 3.1880e-06, 'epoch': 1.25} + +[INFO|2024-11-25 11:16:00] logging.py:157 >> {'loss': 0.2136, 'learning_rate': 3.1826e-06, 'epoch': 1.25} + +[INFO|2024-11-25 11:16:21] logging.py:157 >> {'loss': 0.1812, 'learning_rate': 3.1772e-06, 'epoch': 1.25} + +[INFO|2024-11-25 11:16:43] logging.py:157 >> {'loss': 0.1438, 'learning_rate': 3.1718e-06, 'epoch': 1.25} + +[INFO|2024-11-25 11:17:04] logging.py:157 >> {'loss': 0.2240, 'learning_rate': 3.1664e-06, 'epoch': 1.25} + +[INFO|2024-11-25 11:17:24] logging.py:157 >> {'loss': 0.1427, 'learning_rate': 3.1610e-06, 'epoch': 1.26} + +[INFO|2024-11-25 11:17:45] logging.py:157 >> {'loss': 0.3275, 'learning_rate': 3.1556e-06, 'epoch': 1.26} + +[INFO|2024-11-25 11:18:07] logging.py:157 >> {'loss': 0.2280, 'learning_rate': 3.1502e-06, 'epoch': 1.26} + +[INFO|2024-11-25 11:18:27] logging.py:157 >> {'loss': 0.1597, 'learning_rate': 3.1448e-06, 'epoch': 1.26} + +[INFO|2024-11-25 11:18:47] logging.py:157 >> {'loss': 0.2749, 'learning_rate': 3.1394e-06, 'epoch': 1.26} + +[INFO|2024-11-25 11:19:08] logging.py:157 >> {'loss': 0.2947, 'learning_rate': 3.1340e-06, 'epoch': 1.27} + +[INFO|2024-11-25 11:19:30] logging.py:157 >> {'loss': 0.2116, 'learning_rate': 3.1286e-06, 'epoch': 1.27} + +[INFO|2024-11-25 11:19:51] logging.py:157 >> {'loss': 0.3044, 'learning_rate': 3.1231e-06, 'epoch': 1.27} + +[INFO|2024-11-25 11:20:12] logging.py:157 >> {'loss': 0.2365, 'learning_rate': 3.1177e-06, 'epoch': 1.27} + +[INFO|2024-11-25 11:20:34] logging.py:157 >> {'loss': 0.2351, 'learning_rate': 3.1123e-06, 'epoch': 1.28} + +[INFO|2024-11-25 11:20:55] logging.py:157 >> {'loss': 0.2982, 'learning_rate': 3.1069e-06, 'epoch': 1.28} + +[INFO|2024-11-25 11:21:15] logging.py:157 >> {'loss': 0.2545, 'learning_rate': 3.1014e-06, 'epoch': 1.28} + +[INFO|2024-11-25 11:21:36] logging.py:157 >> {'loss': 0.2081, 'learning_rate': 3.0960e-06, 'epoch': 1.28} + +[INFO|2024-11-25 11:21:58] logging.py:157 >> {'loss': 0.2386, 'learning_rate': 3.0906e-06, 'epoch': 1.28} + +[INFO|2024-11-25 11:22:22] logging.py:157 >> {'loss': 0.1230, 'learning_rate': 3.0851e-06, 'epoch': 1.29} + +[INFO|2024-11-25 11:22:44] logging.py:157 >> {'loss': 0.2888, 'learning_rate': 3.0797e-06, 'epoch': 1.29} + +[INFO|2024-11-25 11:23:08] logging.py:157 >> {'loss': 0.4641, 'learning_rate': 3.0742e-06, 'epoch': 1.29} + +[INFO|2024-11-25 11:23:29] logging.py:157 >> {'loss': 0.1544, 'learning_rate': 3.0688e-06, 'epoch': 1.29} + +[INFO|2024-11-25 11:23:51] logging.py:157 >> {'loss': 0.2008, 'learning_rate': 3.0633e-06, 'epoch': 1.29} + +[INFO|2024-11-25 11:24:12] logging.py:157 >> {'loss': 0.1276, 'learning_rate': 3.0579e-06, 'epoch': 1.30} + +[INFO|2024-11-25 11:24:33] logging.py:157 >> {'loss': 0.2560, 'learning_rate': 3.0524e-06, 'epoch': 1.30} + +[INFO|2024-11-25 11:24:54] logging.py:157 >> {'loss': 0.2078, 'learning_rate': 3.0469e-06, 'epoch': 1.30} + +[INFO|2024-11-25 11:25:15] logging.py:157 >> {'loss': 0.2638, 'learning_rate': 3.0415e-06, 'epoch': 1.30} + +[INFO|2024-11-25 11:25:34] logging.py:157 >> {'loss': 0.1654, 'learning_rate': 3.0360e-06, 'epoch': 1.30} + +[INFO|2024-11-25 11:25:56] logging.py:157 >> {'loss': 0.1348, 'learning_rate': 3.0305e-06, 'epoch': 1.31} + +[INFO|2024-11-25 11:26:17] logging.py:157 >> {'loss': 0.1318, 'learning_rate': 3.0251e-06, 'epoch': 1.31} + +[INFO|2024-11-25 11:26:38] logging.py:157 >> {'loss': 0.2081, 'learning_rate': 3.0196e-06, 'epoch': 1.31} + +[INFO|2024-11-25 11:26:58] logging.py:157 >> {'loss': 0.1596, 'learning_rate': 3.0141e-06, 'epoch': 1.31} + +[INFO|2024-11-25 11:27:18] logging.py:157 >> {'loss': 0.2253, 'learning_rate': 3.0086e-06, 'epoch': 1.32} + +[INFO|2024-11-25 11:27:38] logging.py:157 >> {'loss': 0.2683, 'learning_rate': 3.0032e-06, 'epoch': 1.32} + +[INFO|2024-11-25 11:28:00] logging.py:157 >> {'loss': 0.1977, 'learning_rate': 2.9977e-06, 'epoch': 1.32} + +[INFO|2024-11-25 11:28:21] logging.py:157 >> {'loss': 0.1710, 'learning_rate': 2.9922e-06, 'epoch': 1.32} + +[INFO|2024-11-25 11:28:41] logging.py:157 >> {'loss': 0.2047, 'learning_rate': 2.9867e-06, 'epoch': 1.32} + +[INFO|2024-11-25 11:29:02] logging.py:157 >> {'loss': 0.1553, 'learning_rate': 2.9812e-06, 'epoch': 1.33} + +[INFO|2024-11-25 11:29:22] logging.py:157 >> {'loss': 0.1797, 'learning_rate': 2.9757e-06, 'epoch': 1.33} + +[INFO|2024-11-25 11:29:42] logging.py:157 >> {'loss': 0.1600, 'learning_rate': 2.9702e-06, 'epoch': 1.33} + +[INFO|2024-11-25 11:30:03] logging.py:157 >> {'loss': 0.1923, 'learning_rate': 2.9647e-06, 'epoch': 1.33} + +[INFO|2024-11-25 11:30:24] logging.py:157 >> {'loss': 0.3373, 'learning_rate': 2.9592e-06, 'epoch': 1.33} + +[INFO|2024-11-25 11:30:44] logging.py:157 >> {'loss': 0.2003, 'learning_rate': 2.9537e-06, 'epoch': 1.34} + +[INFO|2024-11-25 11:31:06] logging.py:157 >> {'loss': 0.1736, 'learning_rate': 2.9482e-06, 'epoch': 1.34} + +[INFO|2024-11-25 11:31:26] logging.py:157 >> {'loss': 0.2854, 'learning_rate': 2.9427e-06, 'epoch': 1.34} + +[INFO|2024-11-25 11:31:47] logging.py:157 >> {'loss': 0.1429, 'learning_rate': 2.9372e-06, 'epoch': 1.34} + +[INFO|2024-11-25 11:32:08] logging.py:157 >> {'loss': 0.1374, 'learning_rate': 2.9317e-06, 'epoch': 1.35} + +[INFO|2024-11-25 11:32:28] logging.py:157 >> {'loss': 0.1429, 'learning_rate': 2.9262e-06, 'epoch': 1.35} + +[INFO|2024-11-25 11:32:49] logging.py:157 >> {'loss': 0.2211, 'learning_rate': 2.9206e-06, 'epoch': 1.35} + +[INFO|2024-11-25 11:33:11] logging.py:157 >> {'loss': 0.1726, 'learning_rate': 2.9151e-06, 'epoch': 1.35} + +[INFO|2024-11-25 11:33:33] logging.py:157 >> {'loss': 0.2319, 'learning_rate': 2.9096e-06, 'epoch': 1.35} + +[INFO|2024-11-25 11:33:55] logging.py:157 >> {'loss': 0.2942, 'learning_rate': 2.9041e-06, 'epoch': 1.36} + +[INFO|2024-11-25 11:34:17] logging.py:157 >> {'loss': 0.2206, 'learning_rate': 2.8985e-06, 'epoch': 1.36} + +[INFO|2024-11-25 11:34:36] logging.py:157 >> {'loss': 0.1729, 'learning_rate': 2.8930e-06, 'epoch': 1.36} + +[INFO|2024-11-25 11:34:58] logging.py:157 >> {'loss': 0.2600, 'learning_rate': 2.8875e-06, 'epoch': 1.36} + +[INFO|2024-11-25 11:35:20] logging.py:157 >> {'loss': 0.1996, 'learning_rate': 2.8820e-06, 'epoch': 1.36} + +[INFO|2024-11-25 11:35:42] logging.py:157 >> {'loss': 0.1706, 'learning_rate': 2.8764e-06, 'epoch': 1.37} + +[INFO|2024-11-25 11:36:02] logging.py:157 >> {'loss': 0.2089, 'learning_rate': 2.8709e-06, 'epoch': 1.37} + +[INFO|2024-11-25 11:36:22] logging.py:157 >> {'loss': 0.3736, 'learning_rate': 2.8654e-06, 'epoch': 1.37} + +[INFO|2024-11-25 11:36:42] logging.py:157 >> {'loss': 0.2904, 'learning_rate': 2.8598e-06, 'epoch': 1.37} + +[INFO|2024-11-25 11:37:04] logging.py:157 >> {'loss': 0.2265, 'learning_rate': 2.8543e-06, 'epoch': 1.37} + +[INFO|2024-11-25 11:37:25] logging.py:157 >> {'loss': 0.2266, 'learning_rate': 2.8487e-06, 'epoch': 1.38} + +[INFO|2024-11-25 11:37:46] logging.py:157 >> {'loss': 0.1478, 'learning_rate': 2.8432e-06, 'epoch': 1.38} + +[INFO|2024-11-25 11:38:07] logging.py:157 >> {'loss': 0.1831, 'learning_rate': 2.8376e-06, 'epoch': 1.38} + +[INFO|2024-11-25 11:38:29] logging.py:157 >> {'loss': 0.3069, 'learning_rate': 2.8321e-06, 'epoch': 1.38} + +[INFO|2024-11-25 11:38:50] logging.py:157 >> {'loss': 0.1158, 'learning_rate': 2.8265e-06, 'epoch': 1.39} + +[INFO|2024-11-25 11:39:11] logging.py:157 >> {'loss': 0.3263, 'learning_rate': 2.8210e-06, 'epoch': 1.39} + +[INFO|2024-11-25 11:39:31] logging.py:157 >> {'loss': 0.2294, 'learning_rate': 2.8154e-06, 'epoch': 1.39} + +[INFO|2024-11-25 11:39:51] logging.py:157 >> {'loss': 0.2063, 'learning_rate': 2.8099e-06, 'epoch': 1.39} + +[INFO|2024-11-25 11:40:12] logging.py:157 >> {'loss': 0.2116, 'learning_rate': 2.8043e-06, 'epoch': 1.39} + +[INFO|2024-11-25 11:40:32] logging.py:157 >> {'loss': 0.1887, 'learning_rate': 2.7988e-06, 'epoch': 1.40} + +[INFO|2024-11-25 11:40:54] logging.py:157 >> {'loss': 0.2322, 'learning_rate': 2.7932e-06, 'epoch': 1.40} + +[INFO|2024-11-25 11:41:14] logging.py:157 >> {'loss': 0.1766, 'learning_rate': 2.7877e-06, 'epoch': 1.40} + +[INFO|2024-11-25 11:41:35] logging.py:157 >> {'loss': 0.1912, 'learning_rate': 2.7821e-06, 'epoch': 1.40} + +[INFO|2024-11-25 11:41:56] logging.py:157 >> {'loss': 0.1987, 'learning_rate': 2.7765e-06, 'epoch': 1.40} + +[INFO|2024-11-25 11:42:17] logging.py:157 >> {'loss': 0.1324, 'learning_rate': 2.7710e-06, 'epoch': 1.41} + +[INFO|2024-11-25 11:42:37] logging.py:157 >> {'loss': 0.2485, 'learning_rate': 2.7654e-06, 'epoch': 1.41} + +[INFO|2024-11-25 11:42:59] logging.py:157 >> {'loss': 0.1730, 'learning_rate': 2.7598e-06, 'epoch': 1.41} + +[INFO|2024-11-25 11:43:19] logging.py:157 >> {'loss': 0.1933, 'learning_rate': 2.7543e-06, 'epoch': 1.41} + +[INFO|2024-11-25 11:43:40] logging.py:157 >> {'loss': 0.1837, 'learning_rate': 2.7487e-06, 'epoch': 1.42} + +[INFO|2024-11-25 11:44:02] logging.py:157 >> {'loss': 0.3647, 'learning_rate': 2.7431e-06, 'epoch': 1.42} + +[INFO|2024-11-25 11:44:22] logging.py:157 >> {'loss': 0.3015, 'learning_rate': 2.7376e-06, 'epoch': 1.42} + +[INFO|2024-11-25 11:44:45] logging.py:157 >> {'loss': 0.2581, 'learning_rate': 2.7320e-06, 'epoch': 1.42} + +[INFO|2024-11-25 11:45:06] logging.py:157 >> {'loss': 0.2046, 'learning_rate': 2.7264e-06, 'epoch': 1.42} + +[INFO|2024-11-25 11:45:26] logging.py:157 >> {'loss': 0.2459, 'learning_rate': 2.7208e-06, 'epoch': 1.43} + +[INFO|2024-11-25 11:45:46] logging.py:157 >> {'loss': 0.2656, 'learning_rate': 2.7153e-06, 'epoch': 1.43} + +[INFO|2024-11-25 11:46:07] logging.py:157 >> {'loss': 0.1731, 'learning_rate': 2.7097e-06, 'epoch': 1.43} + +[INFO|2024-11-25 11:46:29] logging.py:157 >> {'loss': 0.3142, 'learning_rate': 2.7041e-06, 'epoch': 1.43} + +[INFO|2024-11-25 11:46:49] logging.py:157 >> {'loss': 0.1379, 'learning_rate': 2.6985e-06, 'epoch': 1.43} + +[INFO|2024-11-25 11:47:10] logging.py:157 >> {'loss': 0.2351, 'learning_rate': 2.6929e-06, 'epoch': 1.44} + +[INFO|2024-11-25 11:47:32] logging.py:157 >> {'loss': 0.0984, 'learning_rate': 2.6874e-06, 'epoch': 1.44} + +[INFO|2024-11-25 11:47:52] logging.py:157 >> {'loss': 0.1528, 'learning_rate': 2.6818e-06, 'epoch': 1.44} + +[INFO|2024-11-25 11:48:13] logging.py:157 >> {'loss': 0.1678, 'learning_rate': 2.6762e-06, 'epoch': 1.44} + +[INFO|2024-11-25 11:48:34] logging.py:157 >> {'loss': 0.1700, 'learning_rate': 2.6706e-06, 'epoch': 1.44} + +[INFO|2024-11-25 11:48:54] logging.py:157 >> {'loss': 0.2781, 'learning_rate': 2.6650e-06, 'epoch': 1.45} + +[INFO|2024-11-25 11:49:14] logging.py:157 >> {'loss': 0.2947, 'learning_rate': 2.6594e-06, 'epoch': 1.45} + +[INFO|2024-11-25 11:49:34] logging.py:157 >> {'loss': 0.1783, 'learning_rate': 2.6538e-06, 'epoch': 1.45} + +[INFO|2024-11-25 11:49:55] logging.py:157 >> {'loss': 0.2216, 'learning_rate': 2.6483e-06, 'epoch': 1.45} + +[INFO|2024-11-25 11:50:17] logging.py:157 >> {'loss': 0.2853, 'learning_rate': 2.6427e-06, 'epoch': 1.46} + +[INFO|2024-11-25 11:50:37] logging.py:157 >> {'loss': 0.1873, 'learning_rate': 2.6371e-06, 'epoch': 1.46} + +[INFO|2024-11-25 11:50:59] logging.py:157 >> {'loss': 0.2065, 'learning_rate': 2.6315e-06, 'epoch': 1.46} + +[INFO|2024-11-25 11:51:20] logging.py:157 >> {'loss': 0.1938, 'learning_rate': 2.6259e-06, 'epoch': 1.46} + +[INFO|2024-11-25 11:51:40] logging.py:157 >> {'loss': 0.2258, 'learning_rate': 2.6203e-06, 'epoch': 1.46} + +[INFO|2024-11-25 11:52:00] logging.py:157 >> {'loss': 0.2049, 'learning_rate': 2.6147e-06, 'epoch': 1.47} + +[INFO|2024-11-25 11:52:21] logging.py:157 >> {'loss': 0.2649, 'learning_rate': 2.6091e-06, 'epoch': 1.47} + +[INFO|2024-11-25 11:52:42] logging.py:157 >> {'loss': 0.2249, 'learning_rate': 2.6035e-06, 'epoch': 1.47} + +[INFO|2024-11-25 11:53:03] logging.py:157 >> {'loss': 0.2629, 'learning_rate': 2.5979e-06, 'epoch': 1.47} + +[INFO|2024-11-25 11:53:24] logging.py:157 >> {'loss': 0.1787, 'learning_rate': 2.5923e-06, 'epoch': 1.47} + +[INFO|2024-11-25 11:53:46] logging.py:157 >> {'loss': 0.2431, 'learning_rate': 2.5868e-06, 'epoch': 1.48} + +[INFO|2024-11-25 11:54:06] logging.py:157 >> {'loss': 0.2282, 'learning_rate': 2.5812e-06, 'epoch': 1.48} + +[INFO|2024-11-25 11:54:28] logging.py:157 >> {'loss': 0.1392, 'learning_rate': 2.5756e-06, 'epoch': 1.48} + +[INFO|2024-11-25 11:54:49] logging.py:157 >> {'loss': 0.1325, 'learning_rate': 2.5700e-06, 'epoch': 1.48} + +[INFO|2024-11-25 11:55:10] logging.py:157 >> {'loss': 0.2908, 'learning_rate': 2.5644e-06, 'epoch': 1.49} + +[INFO|2024-11-25 11:55:31] logging.py:157 >> {'loss': 0.1575, 'learning_rate': 2.5588e-06, 'epoch': 1.49} + +[INFO|2024-11-25 11:55:52] logging.py:157 >> {'loss': 0.2134, 'learning_rate': 2.5532e-06, 'epoch': 1.49} + +[INFO|2024-11-25 11:56:15] logging.py:157 >> {'loss': 0.1237, 'learning_rate': 2.5476e-06, 'epoch': 1.49} + +[INFO|2024-11-25 11:56:36] logging.py:157 >> {'loss': 0.2685, 'learning_rate': 2.5420e-06, 'epoch': 1.49} + +[INFO|2024-11-25 11:56:57] logging.py:157 >> {'loss': 0.1412, 'learning_rate': 2.5364e-06, 'epoch': 1.50} + +[INFO|2024-11-25 11:57:19] logging.py:157 >> {'loss': 0.3377, 'learning_rate': 2.5308e-06, 'epoch': 1.50} + +[INFO|2024-11-25 11:57:40] logging.py:157 >> {'loss': 0.2192, 'learning_rate': 2.5252e-06, 'epoch': 1.50} + +[INFO|2024-11-25 11:58:01] logging.py:157 >> {'loss': 0.2958, 'learning_rate': 2.5196e-06, 'epoch': 1.50} + +[INFO|2024-11-25 11:58:22] logging.py:157 >> {'loss': 0.2331, 'learning_rate': 2.5140e-06, 'epoch': 1.50} + +[INFO|2024-11-25 11:58:44] logging.py:157 >> {'loss': 0.1968, 'learning_rate': 2.5084e-06, 'epoch': 1.51} + +[INFO|2024-11-25 11:59:04] logging.py:157 >> {'loss': 0.2898, 'learning_rate': 2.5028e-06, 'epoch': 1.51} + +[INFO|2024-11-25 11:59:24] logging.py:157 >> {'loss': 0.1849, 'learning_rate': 2.4972e-06, 'epoch': 1.51} + +[INFO|2024-11-25 11:59:45] logging.py:157 >> {'loss': 0.1244, 'learning_rate': 2.4916e-06, 'epoch': 1.51} + +[INFO|2024-11-25 12:00:06] logging.py:157 >> {'loss': 0.1860, 'learning_rate': 2.4860e-06, 'epoch': 1.51} + +[INFO|2024-11-25 12:00:26] logging.py:157 >> {'loss': 0.1995, 'learning_rate': 2.4804e-06, 'epoch': 1.52} + +[INFO|2024-11-25 12:00:46] logging.py:157 >> {'loss': 0.1875, 'learning_rate': 2.4748e-06, 'epoch': 1.52} + +[INFO|2024-11-25 12:01:08] logging.py:157 >> {'loss': 0.2135, 'learning_rate': 2.4692e-06, 'epoch': 1.52} + +[INFO|2024-11-25 12:01:29] logging.py:157 >> {'loss': 0.1819, 'learning_rate': 2.4636e-06, 'epoch': 1.52} + +[INFO|2024-11-25 12:01:48] logging.py:157 >> {'loss': 0.1927, 'learning_rate': 2.4580e-06, 'epoch': 1.53} + +[INFO|2024-11-25 12:02:08] logging.py:157 >> {'loss': 0.1666, 'learning_rate': 2.4524e-06, 'epoch': 1.53} + +[INFO|2024-11-25 12:02:29] logging.py:157 >> {'loss': 0.2549, 'learning_rate': 2.4468e-06, 'epoch': 1.53} + +[INFO|2024-11-25 12:02:51] logging.py:157 >> {'loss': 0.1705, 'learning_rate': 2.4412e-06, 'epoch': 1.53} + +[INFO|2024-11-25 12:03:11] logging.py:157 >> {'loss': 0.1925, 'learning_rate': 2.4356e-06, 'epoch': 1.53} + +[INFO|2024-11-25 12:03:31] logging.py:157 >> {'loss': 0.2595, 'learning_rate': 2.4300e-06, 'epoch': 1.54} + +[INFO|2024-11-25 12:03:52] logging.py:157 >> {'loss': 0.2232, 'learning_rate': 2.4244e-06, 'epoch': 1.54} + +[INFO|2024-11-25 12:04:13] logging.py:157 >> {'loss': 0.1417, 'learning_rate': 2.4188e-06, 'epoch': 1.54} + +[INFO|2024-11-25 12:04:35] logging.py:157 >> {'loss': 0.2102, 'learning_rate': 2.4132e-06, 'epoch': 1.54} + +[INFO|2024-11-25 12:04:55] logging.py:157 >> {'loss': 0.1773, 'learning_rate': 2.4077e-06, 'epoch': 1.54} + +[INFO|2024-11-25 12:05:16] logging.py:157 >> {'loss': 0.2415, 'learning_rate': 2.4021e-06, 'epoch': 1.55} + +[INFO|2024-11-25 12:05:37] logging.py:157 >> {'loss': 0.2973, 'learning_rate': 2.3965e-06, 'epoch': 1.55} + +[INFO|2024-11-25 12:05:57] logging.py:157 >> {'loss': 0.2207, 'learning_rate': 2.3909e-06, 'epoch': 1.55} + +[INFO|2024-11-25 12:06:18] logging.py:157 >> {'loss': 0.2319, 'learning_rate': 2.3853e-06, 'epoch': 1.55} + +[INFO|2024-11-25 12:06:39] logging.py:157 >> {'loss': 0.2266, 'learning_rate': 2.3797e-06, 'epoch': 1.55} + +[INFO|2024-11-25 12:07:00] logging.py:157 >> {'loss': 0.1672, 'learning_rate': 2.3741e-06, 'epoch': 1.56} + +[INFO|2024-11-25 12:07:20] logging.py:157 >> {'loss': 0.2455, 'learning_rate': 2.3685e-06, 'epoch': 1.56} + +[INFO|2024-11-25 12:07:42] logging.py:157 >> {'loss': 0.1731, 'learning_rate': 2.3629e-06, 'epoch': 1.56} + +[INFO|2024-11-25 12:08:04] logging.py:157 >> {'loss': 0.1820, 'learning_rate': 2.3573e-06, 'epoch': 1.56} + +[INFO|2024-11-25 12:08:25] logging.py:157 >> {'loss': 0.2215, 'learning_rate': 2.3517e-06, 'epoch': 1.57} + +[INFO|2024-11-25 12:08:47] logging.py:157 >> {'loss': 0.1727, 'learning_rate': 2.3462e-06, 'epoch': 1.57} + +[INFO|2024-11-25 12:09:07] logging.py:157 >> {'loss': 0.1117, 'learning_rate': 2.3406e-06, 'epoch': 1.57} + +[INFO|2024-11-25 12:09:27] logging.py:157 >> {'loss': 0.2172, 'learning_rate': 2.3350e-06, 'epoch': 1.57} + +[INFO|2024-11-25 12:09:48] logging.py:157 >> {'loss': 0.1758, 'learning_rate': 2.3294e-06, 'epoch': 1.57} + +[INFO|2024-11-25 12:10:10] logging.py:157 >> {'loss': 0.1564, 'learning_rate': 2.3238e-06, 'epoch': 1.58} + +[INFO|2024-11-25 12:10:31] logging.py:157 >> {'loss': 0.2507, 'learning_rate': 2.3182e-06, 'epoch': 1.58} + +[INFO|2024-11-25 12:10:52] logging.py:157 >> {'loss': 0.2025, 'learning_rate': 2.3126e-06, 'epoch': 1.58} + +[INFO|2024-11-25 12:11:13] logging.py:157 >> {'loss': 0.2627, 'learning_rate': 2.3071e-06, 'epoch': 1.58} + +[INFO|2024-11-25 12:11:34] logging.py:157 >> {'loss': 0.1475, 'learning_rate': 2.3015e-06, 'epoch': 1.58} + +[INFO|2024-11-25 12:11:55] logging.py:157 >> {'loss': 0.1478, 'learning_rate': 2.2959e-06, 'epoch': 1.59} + +[INFO|2024-11-25 12:12:16] logging.py:157 >> {'loss': 0.1690, 'learning_rate': 2.2903e-06, 'epoch': 1.59} + +[INFO|2024-11-25 12:12:37] logging.py:157 >> {'loss': 0.2719, 'learning_rate': 2.2847e-06, 'epoch': 1.59} + +[INFO|2024-11-25 12:12:58] logging.py:157 >> {'loss': 0.1815, 'learning_rate': 2.2792e-06, 'epoch': 1.59} + +[INFO|2024-11-25 12:13:20] logging.py:157 >> {'loss': 0.1354, 'learning_rate': 2.2736e-06, 'epoch': 1.60} + +[INFO|2024-11-25 12:13:41] logging.py:157 >> {'loss': 0.2361, 'learning_rate': 2.2680e-06, 'epoch': 1.60} + +[INFO|2024-11-25 12:14:03] logging.py:157 >> {'loss': 0.2273, 'learning_rate': 2.2624e-06, 'epoch': 1.60} + +[INFO|2024-11-25 12:14:24] logging.py:157 >> {'loss': 0.1695, 'learning_rate': 2.2569e-06, 'epoch': 1.60} + +[INFO|2024-11-25 12:14:45] logging.py:157 >> {'loss': 0.2105, 'learning_rate': 2.2513e-06, 'epoch': 1.60} + +[INFO|2024-11-25 12:15:06] logging.py:157 >> {'loss': 0.2822, 'learning_rate': 2.2457e-06, 'epoch': 1.61} + +[INFO|2024-11-25 12:15:28] logging.py:157 >> {'loss': 0.2802, 'learning_rate': 2.2402e-06, 'epoch': 1.61} + +[INFO|2024-11-25 12:15:49] logging.py:157 >> {'loss': 0.1117, 'learning_rate': 2.2346e-06, 'epoch': 1.61} + +[INFO|2024-11-25 12:16:11] logging.py:157 >> {'loss': 0.2573, 'learning_rate': 2.2290e-06, 'epoch': 1.61} + +[INFO|2024-11-25 12:16:33] logging.py:157 >> {'loss': 0.1806, 'learning_rate': 2.2235e-06, 'epoch': 1.61} + +[INFO|2024-11-25 12:16:54] logging.py:157 >> {'loss': 0.1327, 'learning_rate': 2.2179e-06, 'epoch': 1.62} + +[INFO|2024-11-25 12:17:15] logging.py:157 >> {'loss': 0.1819, 'learning_rate': 2.2123e-06, 'epoch': 1.62} + +[INFO|2024-11-25 12:17:36] logging.py:157 >> {'loss': 0.1626, 'learning_rate': 2.2068e-06, 'epoch': 1.62} + +[INFO|2024-11-25 12:17:58] logging.py:157 >> {'loss': 0.2006, 'learning_rate': 2.2012e-06, 'epoch': 1.62} + +[INFO|2024-11-25 12:18:20] logging.py:157 >> {'loss': 0.1135, 'learning_rate': 2.1957e-06, 'epoch': 1.62} + +[INFO|2024-11-25 12:18:42] logging.py:157 >> {'loss': 0.2926, 'learning_rate': 2.1901e-06, 'epoch': 1.63} + +[INFO|2024-11-25 12:19:03] logging.py:157 >> {'loss': 0.2127, 'learning_rate': 2.1846e-06, 'epoch': 1.63} + +[INFO|2024-11-25 12:19:24] logging.py:157 >> {'loss': 0.2560, 'learning_rate': 2.1790e-06, 'epoch': 1.63} + +[INFO|2024-11-25 12:19:46] logging.py:157 >> {'loss': 0.2511, 'learning_rate': 2.1735e-06, 'epoch': 1.63} + +[INFO|2024-11-25 12:20:06] logging.py:157 >> {'loss': 0.1786, 'learning_rate': 2.1679e-06, 'epoch': 1.64} + +[INFO|2024-11-25 12:20:28] logging.py:157 >> {'loss': 0.2015, 'learning_rate': 2.1624e-06, 'epoch': 1.64} + +[INFO|2024-11-25 12:20:49] logging.py:157 >> {'loss': 0.1488, 'learning_rate': 2.1568e-06, 'epoch': 1.64} + +[INFO|2024-11-25 12:21:10] logging.py:157 >> {'loss': 0.3628, 'learning_rate': 2.1513e-06, 'epoch': 1.64} + +[INFO|2024-11-25 12:21:31] logging.py:157 >> {'loss': 0.2429, 'learning_rate': 2.1457e-06, 'epoch': 1.64} + +[INFO|2024-11-25 12:21:51] logging.py:157 >> {'loss': 0.1817, 'learning_rate': 2.1402e-06, 'epoch': 1.65} + +[INFO|2024-11-25 12:22:12] logging.py:157 >> {'loss': 0.1804, 'learning_rate': 2.1346e-06, 'epoch': 1.65} + +[INFO|2024-11-25 12:22:33] logging.py:157 >> {'loss': 0.1714, 'learning_rate': 2.1291e-06, 'epoch': 1.65} + +[INFO|2024-11-25 12:22:54] logging.py:157 >> {'loss': 0.2376, 'learning_rate': 2.1236e-06, 'epoch': 1.65} + +[INFO|2024-11-25 12:23:15] logging.py:157 >> {'loss': 0.1878, 'learning_rate': 2.1180e-06, 'epoch': 1.65} + +[INFO|2024-11-25 12:23:37] logging.py:157 >> {'loss': 0.2489, 'learning_rate': 2.1125e-06, 'epoch': 1.66} + +[INFO|2024-11-25 12:23:57] logging.py:157 >> {'loss': 0.1492, 'learning_rate': 2.1070e-06, 'epoch': 1.66} + +[INFO|2024-11-25 12:24:17] logging.py:157 >> {'loss': 0.1525, 'learning_rate': 2.1015e-06, 'epoch': 1.66} + +[INFO|2024-11-25 12:24:38] logging.py:157 >> {'loss': 0.2749, 'learning_rate': 2.0959e-06, 'epoch': 1.66} + +[INFO|2024-11-25 12:25:00] logging.py:157 >> {'loss': 0.1183, 'learning_rate': 2.0904e-06, 'epoch': 1.67} + +[INFO|2024-11-25 12:25:21] logging.py:157 >> {'loss': 0.1484, 'learning_rate': 2.0849e-06, 'epoch': 1.67} + +[INFO|2024-11-25 12:25:42] logging.py:157 >> {'loss': 0.2783, 'learning_rate': 2.0794e-06, 'epoch': 1.67} + +[INFO|2024-11-25 12:26:04] logging.py:157 >> {'loss': 0.2064, 'learning_rate': 2.0738e-06, 'epoch': 1.67} + +[INFO|2024-11-25 12:26:26] logging.py:157 >> {'loss': 0.1742, 'learning_rate': 2.0683e-06, 'epoch': 1.67} + +[INFO|2024-11-25 12:26:47] logging.py:157 >> {'loss': 0.2273, 'learning_rate': 2.0628e-06, 'epoch': 1.68} + +[INFO|2024-11-25 12:27:09] logging.py:157 >> {'loss': 0.2515, 'learning_rate': 2.0573e-06, 'epoch': 1.68} + +[INFO|2024-11-25 12:27:31] logging.py:157 >> {'loss': 0.2791, 'learning_rate': 2.0518e-06, 'epoch': 1.68} + +[INFO|2024-11-25 12:27:52] logging.py:157 >> {'loss': 0.1838, 'learning_rate': 2.0463e-06, 'epoch': 1.68} + +[INFO|2024-11-25 12:28:12] logging.py:157 >> {'loss': 0.1880, 'learning_rate': 2.0408e-06, 'epoch': 1.68} + +[INFO|2024-11-25 12:28:33] logging.py:157 >> {'loss': 0.2529, 'learning_rate': 2.0353e-06, 'epoch': 1.69} + +[INFO|2024-11-25 12:28:55] logging.py:157 >> {'loss': 0.1882, 'learning_rate': 2.0298e-06, 'epoch': 1.69} + +[INFO|2024-11-25 12:29:16] logging.py:157 >> {'loss': 0.2542, 'learning_rate': 2.0243e-06, 'epoch': 1.69} + +[INFO|2024-11-25 12:29:37] logging.py:157 >> {'loss': 0.2018, 'learning_rate': 2.0188e-06, 'epoch': 1.69} + +[INFO|2024-11-25 12:29:59] logging.py:157 >> {'loss': 0.1885, 'learning_rate': 2.0133e-06, 'epoch': 1.69} + +[INFO|2024-11-25 12:30:19] logging.py:157 >> {'loss': 0.1909, 'learning_rate': 2.0078e-06, 'epoch': 1.70} + +[INFO|2024-11-25 12:30:40] logging.py:157 >> {'loss': 0.1939, 'learning_rate': 2.0023e-06, 'epoch': 1.70} + +[INFO|2024-11-25 12:31:03] logging.py:157 >> {'loss': 0.2151, 'learning_rate': 1.9968e-06, 'epoch': 1.70} + +[INFO|2024-11-25 12:31:23] logging.py:157 >> {'loss': 0.2121, 'learning_rate': 1.9914e-06, 'epoch': 1.70} + +[INFO|2024-11-25 12:31:45] logging.py:157 >> {'loss': 0.1356, 'learning_rate': 1.9859e-06, 'epoch': 1.71} + +[INFO|2024-11-25 12:32:06] logging.py:157 >> {'loss': 0.1723, 'learning_rate': 1.9804e-06, 'epoch': 1.71} + +[INFO|2024-11-25 12:32:27] logging.py:157 >> {'loss': 0.2443, 'learning_rate': 1.9749e-06, 'epoch': 1.71} + +[INFO|2024-11-25 12:32:48] logging.py:157 >> {'loss': 0.1573, 'learning_rate': 1.9695e-06, 'epoch': 1.71} + +[INFO|2024-11-25 12:33:08] logging.py:157 >> {'loss': 0.2239, 'learning_rate': 1.9640e-06, 'epoch': 1.71} + +[INFO|2024-11-25 12:33:29] logging.py:157 >> {'loss': 0.1589, 'learning_rate': 1.9585e-06, 'epoch': 1.72} + +[INFO|2024-11-25 12:33:51] logging.py:157 >> {'loss': 0.1738, 'learning_rate': 1.9531e-06, 'epoch': 1.72} + +[INFO|2024-11-25 12:34:12] logging.py:157 >> {'loss': 0.1698, 'learning_rate': 1.9476e-06, 'epoch': 1.72} + +[INFO|2024-11-25 12:34:34] logging.py:157 >> {'loss': 0.1406, 'learning_rate': 1.9421e-06, 'epoch': 1.72} + +[INFO|2024-11-25 12:34:55] logging.py:157 >> {'loss': 0.2140, 'learning_rate': 1.9367e-06, 'epoch': 1.72} + +[INFO|2024-11-25 12:35:16] logging.py:157 >> {'loss': 0.1675, 'learning_rate': 1.9312e-06, 'epoch': 1.73} + +[INFO|2024-11-25 12:35:37] logging.py:157 >> {'loss': 0.1727, 'learning_rate': 1.9258e-06, 'epoch': 1.73} + +[INFO|2024-11-25 12:35:57] logging.py:157 >> {'loss': 0.2671, 'learning_rate': 1.9203e-06, 'epoch': 1.73} + +[INFO|2024-11-25 12:36:18] logging.py:157 >> {'loss': 0.1879, 'learning_rate': 1.9149e-06, 'epoch': 1.73} + +[INFO|2024-11-25 12:36:39] logging.py:157 >> {'loss': 0.2305, 'learning_rate': 1.9094e-06, 'epoch': 1.74} + +[INFO|2024-11-25 12:36:59] logging.py:157 >> {'loss': 0.3013, 'learning_rate': 1.9040e-06, 'epoch': 1.74} + +[INFO|2024-11-25 12:37:20] logging.py:157 >> {'loss': 0.1450, 'learning_rate': 1.8986e-06, 'epoch': 1.74} + +[INFO|2024-11-25 12:37:41] logging.py:157 >> {'loss': 0.2027, 'learning_rate': 1.8931e-06, 'epoch': 1.74} + +[INFO|2024-11-25 12:38:01] logging.py:157 >> {'loss': 0.1941, 'learning_rate': 1.8877e-06, 'epoch': 1.74} + +[INFO|2024-11-25 12:38:23] logging.py:157 >> {'loss': 0.2453, 'learning_rate': 1.8823e-06, 'epoch': 1.75} + +[INFO|2024-11-25 12:38:43] logging.py:157 >> {'loss': 0.1622, 'learning_rate': 1.8769e-06, 'epoch': 1.75} + +[INFO|2024-11-25 12:39:05] logging.py:157 >> {'loss': 0.1394, 'learning_rate': 1.8714e-06, 'epoch': 1.75} + +[INFO|2024-11-25 12:39:27] logging.py:157 >> {'loss': 0.1650, 'learning_rate': 1.8660e-06, 'epoch': 1.75} + +[INFO|2024-11-25 12:39:49] logging.py:157 >> {'loss': 0.1421, 'learning_rate': 1.8606e-06, 'epoch': 1.75} + +[INFO|2024-11-25 12:40:10] logging.py:157 >> {'loss': 0.2401, 'learning_rate': 1.8552e-06, 'epoch': 1.76} + +[INFO|2024-11-25 12:40:31] logging.py:157 >> {'loss': 0.2401, 'learning_rate': 1.8498e-06, 'epoch': 1.76} + +[INFO|2024-11-25 12:40:52] logging.py:157 >> {'loss': 0.2251, 'learning_rate': 1.8444e-06, 'epoch': 1.76} + +[INFO|2024-11-25 12:41:13] logging.py:157 >> {'loss': 0.1130, 'learning_rate': 1.8390e-06, 'epoch': 1.76} + +[INFO|2024-11-25 12:41:33] logging.py:157 >> {'loss': 0.2415, 'learning_rate': 1.8336e-06, 'epoch': 1.76} + +[INFO|2024-11-25 12:41:55] logging.py:157 >> {'loss': 0.2079, 'learning_rate': 1.8282e-06, 'epoch': 1.77} + +[INFO|2024-11-25 12:42:16] logging.py:157 >> {'loss': 0.2262, 'learning_rate': 1.8228e-06, 'epoch': 1.77} + +[INFO|2024-11-25 12:42:36] logging.py:157 >> {'loss': 0.2094, 'learning_rate': 1.8174e-06, 'epoch': 1.77} + +[INFO|2024-11-25 12:42:56] logging.py:157 >> {'loss': 0.1674, 'learning_rate': 1.8120e-06, 'epoch': 1.77} + +[INFO|2024-11-25 12:43:16] logging.py:157 >> {'loss': 0.2550, 'learning_rate': 1.8067e-06, 'epoch': 1.78} + +[INFO|2024-11-25 12:43:37] logging.py:157 >> {'loss': 0.1705, 'learning_rate': 1.8013e-06, 'epoch': 1.78} + +[INFO|2024-11-25 12:43:58] logging.py:157 >> {'loss': 0.3657, 'learning_rate': 1.7959e-06, 'epoch': 1.78} + +[INFO|2024-11-25 12:44:18] logging.py:157 >> {'loss': 0.1641, 'learning_rate': 1.7905e-06, 'epoch': 1.78} + +[INFO|2024-11-25 12:44:39] logging.py:157 >> {'loss': 0.2821, 'learning_rate': 1.7852e-06, 'epoch': 1.78} + +[INFO|2024-11-25 12:45:00] logging.py:157 >> {'loss': 0.1800, 'learning_rate': 1.7798e-06, 'epoch': 1.79} + +[INFO|2024-11-25 12:45:20] logging.py:157 >> {'loss': 0.2798, 'learning_rate': 1.7745e-06, 'epoch': 1.79} + +[INFO|2024-11-25 12:45:40] logging.py:157 >> {'loss': 0.2194, 'learning_rate': 1.7691e-06, 'epoch': 1.79} + +[INFO|2024-11-25 12:46:01] logging.py:157 >> {'loss': 0.1493, 'learning_rate': 1.7637e-06, 'epoch': 1.79} + +[INFO|2024-11-25 12:46:22] logging.py:157 >> {'loss': 0.1907, 'learning_rate': 1.7584e-06, 'epoch': 1.79} + +[INFO|2024-11-25 12:46:44] logging.py:157 >> {'loss': 0.1661, 'learning_rate': 1.7531e-06, 'epoch': 1.80} + +[INFO|2024-11-25 12:47:04] logging.py:157 >> {'loss': 0.1454, 'learning_rate': 1.7477e-06, 'epoch': 1.80} + +[INFO|2024-11-25 12:47:25] logging.py:157 >> {'loss': 0.1912, 'learning_rate': 1.7424e-06, 'epoch': 1.80} + +[INFO|2024-11-25 12:47:48] logging.py:157 >> {'loss': 0.1125, 'learning_rate': 1.7370e-06, 'epoch': 1.80} + +[INFO|2024-11-25 12:48:07] logging.py:157 >> {'loss': 0.2471, 'learning_rate': 1.7317e-06, 'epoch': 1.81} + +[INFO|2024-11-25 12:48:28] logging.py:157 >> {'loss': 0.1341, 'learning_rate': 1.7264e-06, 'epoch': 1.81} + +[INFO|2024-11-25 12:48:49] logging.py:157 >> {'loss': 0.1579, 'learning_rate': 1.7211e-06, 'epoch': 1.81} + +[INFO|2024-11-25 12:49:10] logging.py:157 >> {'loss': 0.0722, 'learning_rate': 1.7158e-06, 'epoch': 1.81} + +[INFO|2024-11-25 12:49:30] logging.py:157 >> {'loss': 0.1729, 'learning_rate': 1.7104e-06, 'epoch': 1.81} + +[INFO|2024-11-25 12:49:51] logging.py:157 >> {'loss': 0.1131, 'learning_rate': 1.7051e-06, 'epoch': 1.82} + +[INFO|2024-11-25 12:50:12] logging.py:157 >> {'loss': 0.1515, 'learning_rate': 1.6998e-06, 'epoch': 1.82} + +[INFO|2024-11-25 12:50:33] logging.py:157 >> {'loss': 0.2163, 'learning_rate': 1.6945e-06, 'epoch': 1.82} + +[INFO|2024-11-25 12:50:54] logging.py:157 >> {'loss': 0.1602, 'learning_rate': 1.6892e-06, 'epoch': 1.82} + +[INFO|2024-11-25 12:51:15] logging.py:157 >> {'loss': 0.2203, 'learning_rate': 1.6839e-06, 'epoch': 1.82} + +[INFO|2024-11-25 12:51:38] logging.py:157 >> {'loss': 0.2015, 'learning_rate': 1.6786e-06, 'epoch': 1.83} + +[INFO|2024-11-25 12:51:59] logging.py:157 >> {'loss': 0.2026, 'learning_rate': 1.6734e-06, 'epoch': 1.83} + +[INFO|2024-11-25 12:52:20] logging.py:157 >> {'loss': 0.1659, 'learning_rate': 1.6681e-06, 'epoch': 1.83} + +[INFO|2024-11-25 12:52:40] logging.py:157 >> {'loss': 0.1280, 'learning_rate': 1.6628e-06, 'epoch': 1.83} + +[INFO|2024-11-25 12:53:01] logging.py:157 >> {'loss': 0.2637, 'learning_rate': 1.6575e-06, 'epoch': 1.83} + +[INFO|2024-11-25 12:53:21] logging.py:157 >> {'loss': 0.1259, 'learning_rate': 1.6523e-06, 'epoch': 1.84} + +[INFO|2024-11-25 12:53:42] logging.py:157 >> {'loss': 0.2048, 'learning_rate': 1.6470e-06, 'epoch': 1.84} + +[INFO|2024-11-25 12:54:03] logging.py:157 >> {'loss': 0.1192, 'learning_rate': 1.6417e-06, 'epoch': 1.84} + +[INFO|2024-11-25 12:54:24] logging.py:157 >> {'loss': 0.1157, 'learning_rate': 1.6365e-06, 'epoch': 1.84} + +[INFO|2024-11-25 12:54:44] logging.py:157 >> {'loss': 0.1635, 'learning_rate': 1.6312e-06, 'epoch': 1.85} + +[INFO|2024-11-25 12:55:05] logging.py:157 >> {'loss': 0.2340, 'learning_rate': 1.6260e-06, 'epoch': 1.85} + +[INFO|2024-11-25 12:55:25] logging.py:157 >> {'loss': 0.1229, 'learning_rate': 1.6207e-06, 'epoch': 1.85} + +[INFO|2024-11-25 12:55:45] logging.py:157 >> {'loss': 0.2016, 'learning_rate': 1.6155e-06, 'epoch': 1.85} + +[INFO|2024-11-25 12:56:07] logging.py:157 >> {'loss': 0.2195, 'learning_rate': 1.6103e-06, 'epoch': 1.85} + +[INFO|2024-11-25 12:56:28] logging.py:157 >> {'loss': 0.2128, 'learning_rate': 1.6050e-06, 'epoch': 1.86} + +[INFO|2024-11-25 12:56:49] logging.py:157 >> {'loss': 0.2381, 'learning_rate': 1.5998e-06, 'epoch': 1.86} + +[INFO|2024-11-25 12:57:09] logging.py:157 >> {'loss': 0.1580, 'learning_rate': 1.5946e-06, 'epoch': 1.86} + +[INFO|2024-11-25 12:57:30] logging.py:157 >> {'loss': 0.1924, 'learning_rate': 1.5894e-06, 'epoch': 1.86} + +[INFO|2024-11-25 12:57:51] logging.py:157 >> {'loss': 0.2010, 'learning_rate': 1.5842e-06, 'epoch': 1.86} + +[INFO|2024-11-25 12:58:12] logging.py:157 >> {'loss': 0.2340, 'learning_rate': 1.5790e-06, 'epoch': 1.87} + +[INFO|2024-11-25 12:58:33] logging.py:157 >> {'loss': 0.1891, 'learning_rate': 1.5738e-06, 'epoch': 1.87} + +[INFO|2024-11-25 12:58:54] logging.py:157 >> {'loss': 0.1912, 'learning_rate': 1.5686e-06, 'epoch': 1.87} + +[INFO|2024-11-25 12:59:14] logging.py:157 >> {'loss': 0.1075, 'learning_rate': 1.5634e-06, 'epoch': 1.87} + +[INFO|2024-11-25 12:59:35] logging.py:157 >> {'loss': 0.1945, 'learning_rate': 1.5582e-06, 'epoch': 1.88} + +[INFO|2024-11-25 12:59:57] logging.py:157 >> {'loss': 0.1465, 'learning_rate': 1.5530e-06, 'epoch': 1.88} + +[INFO|2024-11-25 13:00:17] logging.py:157 >> {'loss': 0.2768, 'learning_rate': 1.5478e-06, 'epoch': 1.88} + +[INFO|2024-11-25 13:00:39] logging.py:157 >> {'loss': 0.2076, 'learning_rate': 1.5426e-06, 'epoch': 1.88} + +[INFO|2024-11-25 13:00:59] logging.py:157 >> {'loss': 0.2828, 'learning_rate': 1.5375e-06, 'epoch': 1.88} + +[INFO|2024-11-25 13:01:20] logging.py:157 >> {'loss': 0.2031, 'learning_rate': 1.5323e-06, 'epoch': 1.89} + +[INFO|2024-11-25 13:01:41] logging.py:157 >> {'loss': 0.2678, 'learning_rate': 1.5272e-06, 'epoch': 1.89} + +[INFO|2024-11-25 13:02:01] logging.py:157 >> {'loss': 0.2210, 'learning_rate': 1.5220e-06, 'epoch': 1.89} + +[INFO|2024-11-25 13:02:21] logging.py:157 >> {'loss': 0.1595, 'learning_rate': 1.5168e-06, 'epoch': 1.89} + +[INFO|2024-11-25 13:02:42] logging.py:157 >> {'loss': 0.2665, 'learning_rate': 1.5117e-06, 'epoch': 1.89} + +[INFO|2024-11-25 13:03:02] logging.py:157 >> {'loss': 0.1806, 'learning_rate': 1.5066e-06, 'epoch': 1.90} + +[INFO|2024-11-25 13:03:23] logging.py:157 >> {'loss': 0.2988, 'learning_rate': 1.5014e-06, 'epoch': 1.90} + +[INFO|2024-11-25 13:03:45] logging.py:157 >> {'loss': 0.1248, 'learning_rate': 1.4963e-06, 'epoch': 1.90} + +[INFO|2024-11-25 13:04:06] logging.py:157 >> {'loss': 0.3798, 'learning_rate': 1.4912e-06, 'epoch': 1.90} + +[INFO|2024-11-25 13:04:27] logging.py:157 >> {'loss': 0.2455, 'learning_rate': 1.4861e-06, 'epoch': 1.90} + +[INFO|2024-11-25 13:04:47] logging.py:157 >> {'loss': 0.1762, 'learning_rate': 1.4809e-06, 'epoch': 1.91} + +[INFO|2024-11-25 13:05:08] logging.py:157 >> {'loss': 0.3043, 'learning_rate': 1.4758e-06, 'epoch': 1.91} + +[INFO|2024-11-25 13:05:29] logging.py:157 >> {'loss': 0.1608, 'learning_rate': 1.4707e-06, 'epoch': 1.91} + +[INFO|2024-11-25 13:05:50] logging.py:157 >> {'loss': 0.1494, 'learning_rate': 1.4656e-06, 'epoch': 1.91} + +[INFO|2024-11-25 13:06:12] logging.py:157 >> {'loss': 0.1819, 'learning_rate': 1.4605e-06, 'epoch': 1.92} + +[INFO|2024-11-25 13:06:33] logging.py:157 >> {'loss': 0.1381, 'learning_rate': 1.4554e-06, 'epoch': 1.92} + +[INFO|2024-11-25 13:06:55] logging.py:157 >> {'loss': 0.1973, 'learning_rate': 1.4504e-06, 'epoch': 1.92} + +[INFO|2024-11-25 13:07:17] logging.py:157 >> {'loss': 0.2893, 'learning_rate': 1.4453e-06, 'epoch': 1.92} + +[INFO|2024-11-25 13:07:39] logging.py:157 >> {'loss': 0.1968, 'learning_rate': 1.4402e-06, 'epoch': 1.92} + +[INFO|2024-11-25 13:08:00] logging.py:157 >> {'loss': 0.1978, 'learning_rate': 1.4351e-06, 'epoch': 1.93} + +[INFO|2024-11-25 13:08:21] logging.py:157 >> {'loss': 0.2572, 'learning_rate': 1.4301e-06, 'epoch': 1.93} + +[INFO|2024-11-25 13:08:43] logging.py:157 >> {'loss': 0.1473, 'learning_rate': 1.4250e-06, 'epoch': 1.93} + +[INFO|2024-11-25 13:09:03] logging.py:157 >> {'loss': 0.2889, 'learning_rate': 1.4200e-06, 'epoch': 1.93} + +[INFO|2024-11-25 13:09:23] logging.py:157 >> {'loss': 0.1495, 'learning_rate': 1.4149e-06, 'epoch': 1.93} + +[INFO|2024-11-25 13:09:43] logging.py:157 >> {'loss': 0.1174, 'learning_rate': 1.4099e-06, 'epoch': 1.94} + +[INFO|2024-11-25 13:10:04] logging.py:157 >> {'loss': 0.1357, 'learning_rate': 1.4049e-06, 'epoch': 1.94} + +[INFO|2024-11-25 13:10:25] logging.py:157 >> {'loss': 0.1929, 'learning_rate': 1.3998e-06, 'epoch': 1.94} + +[INFO|2024-11-25 13:10:46] logging.py:157 >> {'loss': 0.2133, 'learning_rate': 1.3948e-06, 'epoch': 1.94} + +[INFO|2024-11-25 13:11:06] logging.py:157 >> {'loss': 0.2032, 'learning_rate': 1.3898e-06, 'epoch': 1.95} + +[INFO|2024-11-25 13:11:27] logging.py:157 >> {'loss': 0.1907, 'learning_rate': 1.3848e-06, 'epoch': 1.95} + +[INFO|2024-11-25 13:11:48] logging.py:157 >> {'loss': 0.2204, 'learning_rate': 1.3798e-06, 'epoch': 1.95} + +[INFO|2024-11-25 13:12:09] logging.py:157 >> {'loss': 0.2518, 'learning_rate': 1.3748e-06, 'epoch': 1.95} + +[INFO|2024-11-25 13:12:30] logging.py:157 >> {'loss': 0.1671, 'learning_rate': 1.3698e-06, 'epoch': 1.95} + +[INFO|2024-11-25 13:12:50] logging.py:157 >> {'loss': 0.1723, 'learning_rate': 1.3648e-06, 'epoch': 1.96} + +[INFO|2024-11-25 13:13:12] logging.py:157 >> {'loss': 0.1485, 'learning_rate': 1.3598e-06, 'epoch': 1.96} + +[INFO|2024-11-25 13:13:33] logging.py:157 >> {'loss': 0.1481, 'learning_rate': 1.3548e-06, 'epoch': 1.96} + +[INFO|2024-11-25 13:13:54] logging.py:157 >> {'loss': 0.2583, 'learning_rate': 1.3498e-06, 'epoch': 1.96} + +[INFO|2024-11-25 13:14:16] logging.py:157 >> {'loss': 0.2165, 'learning_rate': 1.3449e-06, 'epoch': 1.96} + +[INFO|2024-11-25 13:14:37] logging.py:157 >> {'loss': 0.1807, 'learning_rate': 1.3399e-06, 'epoch': 1.97} + +[INFO|2024-11-25 13:14:58] logging.py:157 >> {'loss': 0.2490, 'learning_rate': 1.3350e-06, 'epoch': 1.97} + +[INFO|2024-11-25 13:15:19] logging.py:157 >> {'loss': 0.1337, 'learning_rate': 1.3300e-06, 'epoch': 1.97} + +[INFO|2024-11-25 13:15:40] logging.py:157 >> {'loss': 0.2563, 'learning_rate': 1.3251e-06, 'epoch': 1.97} + +[INFO|2024-11-25 13:16:01] logging.py:157 >> {'loss': 0.2068, 'learning_rate': 1.3201e-06, 'epoch': 1.97} + +[INFO|2024-11-25 13:16:22] logging.py:157 >> {'loss': 0.1813, 'learning_rate': 1.3152e-06, 'epoch': 1.98} + +[INFO|2024-11-25 13:16:42] logging.py:157 >> {'loss': 0.2077, 'learning_rate': 1.3103e-06, 'epoch': 1.98} + +[INFO|2024-11-25 13:17:03] logging.py:157 >> {'loss': 0.1782, 'learning_rate': 1.3053e-06, 'epoch': 1.98} + +[INFO|2024-11-25 13:17:25] logging.py:157 >> {'loss': 0.2884, 'learning_rate': 1.3004e-06, 'epoch': 1.98} + +[INFO|2024-11-25 13:17:46] logging.py:157 >> {'loss': 0.1920, 'learning_rate': 1.2955e-06, 'epoch': 1.99} + +[INFO|2024-11-25 13:18:07] logging.py:157 >> {'loss': 0.1134, 'learning_rate': 1.2906e-06, 'epoch': 1.99} + +[INFO|2024-11-25 13:18:29] logging.py:157 >> {'loss': 0.1924, 'learning_rate': 1.2857e-06, 'epoch': 1.99} + +[INFO|2024-11-25 13:18:49] logging.py:157 >> {'loss': 0.2068, 'learning_rate': 1.2808e-06, 'epoch': 1.99} + +[INFO|2024-11-25 13:19:11] logging.py:157 >> {'loss': 0.1122, 'learning_rate': 1.2759e-06, 'epoch': 1.99} + +[INFO|2024-11-25 13:19:32] logging.py:157 >> {'loss': 0.2615, 'learning_rate': 1.2711e-06, 'epoch': 2.00} + +[INFO|2024-11-25 13:19:53] logging.py:157 >> {'loss': 0.1196, 'learning_rate': 1.2662e-06, 'epoch': 2.00} + +[INFO|2024-11-25 13:20:14] logging.py:157 >> {'loss': 0.2324, 'learning_rate': 1.2613e-06, 'epoch': 2.00} + +[INFO|2024-11-25 13:20:35] logging.py:157 >> {'loss': 0.1671, 'learning_rate': 1.2565e-06, 'epoch': 2.00} + +[INFO|2024-11-25 13:20:55] logging.py:157 >> {'loss': 0.1219, 'learning_rate': 1.2516e-06, 'epoch': 2.01} + +[INFO|2024-11-25 13:21:17] logging.py:157 >> {'loss': 0.1258, 'learning_rate': 1.2468e-06, 'epoch': 2.01} + +[INFO|2024-11-25 13:21:39] logging.py:157 >> {'loss': 0.2731, 'learning_rate': 1.2419e-06, 'epoch': 2.01} + +[INFO|2024-11-25 13:21:59] logging.py:157 >> {'loss': 0.1510, 'learning_rate': 1.2371e-06, 'epoch': 2.01} + +[INFO|2024-11-25 13:22:20] logging.py:157 >> {'loss': 0.1870, 'learning_rate': 1.2323e-06, 'epoch': 2.01} + +[INFO|2024-11-25 13:22:41] logging.py:157 >> {'loss': 0.1094, 'learning_rate': 1.2274e-06, 'epoch': 2.02} + +[INFO|2024-11-25 13:23:02] logging.py:157 >> {'loss': 0.2884, 'learning_rate': 1.2226e-06, 'epoch': 2.02} + +[INFO|2024-11-25 13:23:22] logging.py:157 >> {'loss': 0.1166, 'learning_rate': 1.2178e-06, 'epoch': 2.02} + +[INFO|2024-11-25 13:23:43] logging.py:157 >> {'loss': 0.2639, 'learning_rate': 1.2130e-06, 'epoch': 2.02} + +[INFO|2024-11-25 13:24:04] logging.py:157 >> {'loss': 0.2392, 'learning_rate': 1.2082e-06, 'epoch': 2.02} + +[INFO|2024-11-25 13:24:23] logging.py:157 >> {'loss': 0.1054, 'learning_rate': 1.2034e-06, 'epoch': 2.03} + +[INFO|2024-11-25 13:24:44] logging.py:157 >> {'loss': 0.2579, 'learning_rate': 1.1986e-06, 'epoch': 2.03} + +[INFO|2024-11-25 13:25:05] logging.py:157 >> {'loss': 0.1962, 'learning_rate': 1.1939e-06, 'epoch': 2.03} + +[INFO|2024-11-25 13:25:25] logging.py:157 >> {'loss': 0.1390, 'learning_rate': 1.1891e-06, 'epoch': 2.03} + +[INFO|2024-11-25 13:25:46] logging.py:157 >> {'loss': 0.1442, 'learning_rate': 1.1843e-06, 'epoch': 2.03} + +[INFO|2024-11-25 13:26:08] logging.py:157 >> {'loss': 0.1862, 'learning_rate': 1.1796e-06, 'epoch': 2.04} + +[INFO|2024-11-25 13:26:28] logging.py:157 >> {'loss': 0.1870, 'learning_rate': 1.1748e-06, 'epoch': 2.04} + +[INFO|2024-11-25 13:26:48] logging.py:157 >> {'loss': 0.1043, 'learning_rate': 1.1701e-06, 'epoch': 2.04} + +[INFO|2024-11-25 13:27:10] logging.py:157 >> {'loss': 0.1359, 'learning_rate': 1.1654e-06, 'epoch': 2.04} + +[INFO|2024-11-25 13:27:30] logging.py:157 >> {'loss': 0.1808, 'learning_rate': 1.1606e-06, 'epoch': 2.05} + +[INFO|2024-11-25 13:27:51] logging.py:157 >> {'loss': 0.1454, 'learning_rate': 1.1559e-06, 'epoch': 2.05} + +[INFO|2024-11-25 13:28:11] logging.py:157 >> {'loss': 0.1273, 'learning_rate': 1.1512e-06, 'epoch': 2.05} + +[INFO|2024-11-25 13:28:32] logging.py:157 >> {'loss': 0.1516, 'learning_rate': 1.1465e-06, 'epoch': 2.05} + +[INFO|2024-11-25 13:28:54] logging.py:157 >> {'loss': 0.2406, 'learning_rate': 1.1418e-06, 'epoch': 2.05} + +[INFO|2024-11-25 13:29:14] logging.py:157 >> {'loss': 0.2046, 'learning_rate': 1.1371e-06, 'epoch': 2.06} + +[INFO|2024-11-25 13:29:34] logging.py:157 >> {'loss': 0.1645, 'learning_rate': 1.1324e-06, 'epoch': 2.06} + +[INFO|2024-11-25 13:29:54] logging.py:157 >> {'loss': 0.1562, 'learning_rate': 1.1277e-06, 'epoch': 2.06} + +[INFO|2024-11-25 13:30:15] logging.py:157 >> {'loss': 0.1089, 'learning_rate': 1.1230e-06, 'epoch': 2.06} + +[INFO|2024-11-25 13:30:37] logging.py:157 >> {'loss': 0.2160, 'learning_rate': 1.1184e-06, 'epoch': 2.06} + +[INFO|2024-11-25 13:30:57] logging.py:157 >> {'loss': 0.0965, 'learning_rate': 1.1137e-06, 'epoch': 2.07} + +[INFO|2024-11-25 13:31:18] logging.py:157 >> {'loss': 0.2348, 'learning_rate': 1.1090e-06, 'epoch': 2.07} + +[INFO|2024-11-25 13:31:39] logging.py:157 >> {'loss': 0.1252, 'learning_rate': 1.1044e-06, 'epoch': 2.07} + +[INFO|2024-11-25 13:32:00] logging.py:157 >> {'loss': 0.2280, 'learning_rate': 1.0997e-06, 'epoch': 2.07} + +[INFO|2024-11-25 13:32:20] logging.py:157 >> {'loss': 0.1241, 'learning_rate': 1.0951e-06, 'epoch': 2.08} + +[INFO|2024-11-25 13:32:42] logging.py:157 >> {'loss': 0.1477, 'learning_rate': 1.0905e-06, 'epoch': 2.08} + +[INFO|2024-11-25 13:33:03] logging.py:157 >> {'loss': 0.1195, 'learning_rate': 1.0859e-06, 'epoch': 2.08} + +[INFO|2024-11-25 13:33:24] logging.py:157 >> {'loss': 0.1273, 'learning_rate': 1.0813e-06, 'epoch': 2.08} + +[INFO|2024-11-25 13:33:46] logging.py:157 >> {'loss': 0.1584, 'learning_rate': 1.0767e-06, 'epoch': 2.08} + +[INFO|2024-11-25 13:34:07] logging.py:157 >> {'loss': 0.1586, 'learning_rate': 1.0721e-06, 'epoch': 2.09} + +[INFO|2024-11-25 13:34:27] logging.py:157 >> {'loss': 0.1341, 'learning_rate': 1.0675e-06, 'epoch': 2.09} + +[INFO|2024-11-25 13:34:48] logging.py:157 >> {'loss': 0.1727, 'learning_rate': 1.0629e-06, 'epoch': 2.09} + +[INFO|2024-11-25 13:35:08] logging.py:157 >> {'loss': 0.1506, 'learning_rate': 1.0583e-06, 'epoch': 2.09} + +[INFO|2024-11-25 13:35:30] logging.py:157 >> {'loss': 0.1112, 'learning_rate': 1.0537e-06, 'epoch': 2.09} + +[INFO|2024-11-25 13:35:50] logging.py:157 >> {'loss': 0.2002, 'learning_rate': 1.0492e-06, 'epoch': 2.10} + +[INFO|2024-11-25 13:36:11] logging.py:157 >> {'loss': 0.2054, 'learning_rate': 1.0446e-06, 'epoch': 2.10} + +[INFO|2024-11-25 13:36:32] logging.py:157 >> {'loss': 0.1530, 'learning_rate': 1.0401e-06, 'epoch': 2.10} + +[INFO|2024-11-25 13:36:52] logging.py:157 >> {'loss': 0.1552, 'learning_rate': 1.0355e-06, 'epoch': 2.10} + +[INFO|2024-11-25 13:37:13] logging.py:157 >> {'loss': 0.2001, 'learning_rate': 1.0310e-06, 'epoch': 2.10} + +[INFO|2024-11-25 13:37:34] logging.py:157 >> {'loss': 0.1307, 'learning_rate': 1.0265e-06, 'epoch': 2.11} + +[INFO|2024-11-25 13:37:54] logging.py:157 >> {'loss': 0.1668, 'learning_rate': 1.0219e-06, 'epoch': 2.11} + +[INFO|2024-11-25 13:38:15] logging.py:157 >> {'loss': 0.1635, 'learning_rate': 1.0174e-06, 'epoch': 2.11} + +[INFO|2024-11-25 13:38:37] logging.py:157 >> {'loss': 0.2443, 'learning_rate': 1.0129e-06, 'epoch': 2.11} + +[INFO|2024-11-25 13:38:58] logging.py:157 >> {'loss': 0.1109, 'learning_rate': 1.0084e-06, 'epoch': 2.12} + +[INFO|2024-11-25 13:39:18] logging.py:157 >> {'loss': 0.1842, 'learning_rate': 1.0039e-06, 'epoch': 2.12} + +[INFO|2024-11-25 13:39:39] logging.py:157 >> {'loss': 0.1828, 'learning_rate': 9.9946e-07, 'epoch': 2.12} + +[INFO|2024-11-25 13:40:00] logging.py:157 >> {'loss': 0.1531, 'learning_rate': 9.9499e-07, 'epoch': 2.12} + +[INFO|2024-11-25 13:40:08] trainer.py:3801 >> Saving model checkpoint to saves/Llama-3-8B-Instruct/full/train_2024-11-25-07-46-41/checkpoint-1000 + +[INFO|2024-11-25 13:40:08] configuration_utils.py:414 >> Configuration saved in saves/Llama-3-8B-Instruct/full/train_2024-11-25-07-46-41/checkpoint-1000/config.json + +[INFO|2024-11-25 13:40:08] configuration_utils.py:865 >> Configuration saved in saves/Llama-3-8B-Instruct/full/train_2024-11-25-07-46-41/checkpoint-1000/generation_config.json + +[INFO|2024-11-25 13:40:24] modeling_utils.py:3043 >> The model is bigger than the maximum size per checkpoint (5GB) and is going to be split in 4 checkpoint shards. You can find where each parameters has been saved in the index located at saves/Llama-3-8B-Instruct/full/train_2024-11-25-07-46-41/checkpoint-1000/model.safetensors.index.json. + +[INFO|2024-11-25 13:40:24] tokenization_utils_base.py:2646 >> tokenizer config file saved in saves/Llama-3-8B-Instruct/full/train_2024-11-25-07-46-41/checkpoint-1000/tokenizer_config.json + +[INFO|2024-11-25 13:40:24] tokenization_utils_base.py:2655 >> Special tokens file saved in saves/Llama-3-8B-Instruct/full/train_2024-11-25-07-46-41/checkpoint-1000/special_tokens_map.json + +[INFO|2024-11-25 13:41:52] logging.py:157 >> {'loss': 0.1289, 'learning_rate': 9.9052e-07, 'epoch': 2.12} + +[INFO|2024-11-25 13:42:14] logging.py:157 >> {'loss': 0.1114, 'learning_rate': 9.8607e-07, 'epoch': 2.13} + +[INFO|2024-11-25 13:42:35] logging.py:157 >> {'loss': 0.1902, 'learning_rate': 9.8161e-07, 'epoch': 2.13} + +[INFO|2024-11-25 13:42:56] logging.py:157 >> {'loss': 0.1395, 'learning_rate': 9.7717e-07, 'epoch': 2.13} + +[INFO|2024-11-25 13:43:17] logging.py:157 >> {'loss': 0.1410, 'learning_rate': 9.7274e-07, 'epoch': 2.13} + +[INFO|2024-11-25 13:43:38] logging.py:157 >> {'loss': 0.1943, 'learning_rate': 9.6831e-07, 'epoch': 2.13} + +[INFO|2024-11-25 13:43:57] logging.py:157 >> {'loss': 0.0903, 'learning_rate': 9.6389e-07, 'epoch': 2.14} + +[INFO|2024-11-25 13:44:18] logging.py:157 >> {'loss': 0.1862, 'learning_rate': 9.5947e-07, 'epoch': 2.14} + +[INFO|2024-11-25 13:44:40] logging.py:157 >> {'loss': 0.1140, 'learning_rate': 9.5507e-07, 'epoch': 2.14} + +[INFO|2024-11-25 13:45:02] logging.py:157 >> {'loss': 0.1046, 'learning_rate': 9.5067e-07, 'epoch': 2.14} + +[INFO|2024-11-25 13:45:24] logging.py:157 >> {'loss': 0.1864, 'learning_rate': 9.4628e-07, 'epoch': 2.15} + +[INFO|2024-11-25 13:45:46] logging.py:157 >> {'loss': 0.0640, 'learning_rate': 9.4190e-07, 'epoch': 2.15} + +[INFO|2024-11-25 13:46:05] logging.py:157 >> {'loss': 0.1237, 'learning_rate': 9.3753e-07, 'epoch': 2.15} + +[INFO|2024-11-25 13:46:26] logging.py:157 >> {'loss': 0.1576, 'learning_rate': 9.3316e-07, 'epoch': 2.15} + +[INFO|2024-11-25 13:46:46] logging.py:157 >> {'loss': 0.1716, 'learning_rate': 9.2880e-07, 'epoch': 2.15} + +[INFO|2024-11-25 13:47:07] logging.py:157 >> {'loss': 0.1497, 'learning_rate': 9.2445e-07, 'epoch': 2.16} + +[INFO|2024-11-25 13:47:28] logging.py:157 >> {'loss': 0.0957, 'learning_rate': 9.2011e-07, 'epoch': 2.16} + +[INFO|2024-11-25 13:47:49] logging.py:157 >> {'loss': 0.2541, 'learning_rate': 9.1578e-07, 'epoch': 2.16} + +[INFO|2024-11-25 13:48:09] logging.py:157 >> {'loss': 0.1664, 'learning_rate': 9.1145e-07, 'epoch': 2.16} + +[INFO|2024-11-25 13:48:29] logging.py:157 >> {'loss': 0.2169, 'learning_rate': 9.0713e-07, 'epoch': 2.16} + +[INFO|2024-11-25 13:48:51] logging.py:157 >> {'loss': 0.1863, 'learning_rate': 9.0282e-07, 'epoch': 2.17} + +[INFO|2024-11-25 13:49:12] logging.py:157 >> {'loss': 0.1827, 'learning_rate': 8.9852e-07, 'epoch': 2.17} + +[INFO|2024-11-25 13:49:32] logging.py:157 >> {'loss': 0.2556, 'learning_rate': 8.9422e-07, 'epoch': 2.17} + +[INFO|2024-11-25 13:49:53] logging.py:157 >> {'loss': 0.1713, 'learning_rate': 8.8994e-07, 'epoch': 2.17} + +[INFO|2024-11-25 13:50:12] logging.py:157 >> {'loss': 0.1403, 'learning_rate': 8.8566e-07, 'epoch': 2.17} + +[INFO|2024-11-25 13:50:35] logging.py:157 >> {'loss': 0.2385, 'learning_rate': 8.8139e-07, 'epoch': 2.18} + +[INFO|2024-11-25 13:50:55] logging.py:157 >> {'loss': 0.1823, 'learning_rate': 8.7712e-07, 'epoch': 2.18} + +[INFO|2024-11-25 13:51:16] logging.py:157 >> {'loss': 0.0917, 'learning_rate': 8.7287e-07, 'epoch': 2.18} + +[INFO|2024-11-25 13:51:37] logging.py:157 >> {'loss': 0.1308, 'learning_rate': 8.6862e-07, 'epoch': 2.18} + +[INFO|2024-11-25 13:51:57] logging.py:157 >> {'loss': 0.1810, 'learning_rate': 8.6439e-07, 'epoch': 2.19} + +[INFO|2024-11-25 13:52:17] logging.py:157 >> {'loss': 0.1376, 'learning_rate': 8.6016e-07, 'epoch': 2.19} + +[INFO|2024-11-25 13:52:38] logging.py:157 >> {'loss': 0.1826, 'learning_rate': 8.5594e-07, 'epoch': 2.19} + +[INFO|2024-11-25 13:52:58] logging.py:157 >> {'loss': 0.2169, 'learning_rate': 8.5172e-07, 'epoch': 2.19} + +[INFO|2024-11-25 13:53:20] logging.py:157 >> {'loss': 0.2092, 'learning_rate': 8.4752e-07, 'epoch': 2.19} + +[INFO|2024-11-25 13:53:39] logging.py:157 >> {'loss': 0.1093, 'learning_rate': 8.4332e-07, 'epoch': 2.20} + +[INFO|2024-11-25 13:53:59] logging.py:157 >> {'loss': 0.1931, 'learning_rate': 8.3913e-07, 'epoch': 2.20} + +[INFO|2024-11-25 13:54:20] logging.py:157 >> {'loss': 0.2260, 'learning_rate': 8.3495e-07, 'epoch': 2.20} + +[INFO|2024-11-25 13:54:40] logging.py:157 >> {'loss': 0.1644, 'learning_rate': 8.3078e-07, 'epoch': 2.20} + +[INFO|2024-11-25 13:55:02] logging.py:157 >> {'loss': 0.1338, 'learning_rate': 8.2662e-07, 'epoch': 2.20} + +[INFO|2024-11-25 13:55:22] logging.py:157 >> {'loss': 0.2425, 'learning_rate': 8.2246e-07, 'epoch': 2.21} + +[INFO|2024-11-25 13:55:43] logging.py:157 >> {'loss': 0.0995, 'learning_rate': 8.1832e-07, 'epoch': 2.21} + +[INFO|2024-11-25 13:56:03] logging.py:157 >> {'loss': 0.1023, 'learning_rate': 8.1418e-07, 'epoch': 2.21} + +[INFO|2024-11-25 13:56:24] logging.py:157 >> {'loss': 0.2438, 'learning_rate': 8.1005e-07, 'epoch': 2.21} + +[INFO|2024-11-25 13:56:46] logging.py:157 >> {'loss': 0.1800, 'learning_rate': 8.0593e-07, 'epoch': 2.22} + +[INFO|2024-11-25 13:57:07] logging.py:157 >> {'loss': 0.1664, 'learning_rate': 8.0182e-07, 'epoch': 2.22} + +[INFO|2024-11-25 13:57:28] logging.py:157 >> {'loss': 0.1453, 'learning_rate': 7.9771e-07, 'epoch': 2.22} + +[INFO|2024-11-25 13:57:49] logging.py:157 >> {'loss': 0.1826, 'learning_rate': 7.9362e-07, 'epoch': 2.22} + +[INFO|2024-11-25 13:58:10] logging.py:157 >> {'loss': 0.1264, 'learning_rate': 7.8953e-07, 'epoch': 2.22} + +[INFO|2024-11-25 13:58:32] logging.py:157 >> {'loss': 0.1218, 'learning_rate': 7.8545e-07, 'epoch': 2.23} + +[INFO|2024-11-25 13:58:53] logging.py:157 >> {'loss': 0.1772, 'learning_rate': 7.8138e-07, 'epoch': 2.23} + +[INFO|2024-11-25 13:59:14] logging.py:157 >> {'loss': 0.2343, 'learning_rate': 7.7732e-07, 'epoch': 2.23} + +[INFO|2024-11-25 13:59:34] logging.py:157 >> {'loss': 0.1654, 'learning_rate': 7.7327e-07, 'epoch': 2.23} + +[INFO|2024-11-25 13:59:55] logging.py:157 >> {'loss': 0.1807, 'learning_rate': 7.6922e-07, 'epoch': 2.23} + +[INFO|2024-11-25 14:00:16] logging.py:157 >> {'loss': 0.1645, 'learning_rate': 7.6519e-07, 'epoch': 2.24} + +[INFO|2024-11-25 14:00:37] logging.py:157 >> {'loss': 0.1378, 'learning_rate': 7.6116e-07, 'epoch': 2.24} + +[INFO|2024-11-25 14:00:57] logging.py:157 >> {'loss': 0.2183, 'learning_rate': 7.5715e-07, 'epoch': 2.24} + +[INFO|2024-11-25 14:01:18] logging.py:157 >> {'loss': 0.1840, 'learning_rate': 7.5314e-07, 'epoch': 2.24} + +[INFO|2024-11-25 14:01:39] logging.py:157 >> {'loss': 0.1685, 'learning_rate': 7.4914e-07, 'epoch': 2.24} + +[INFO|2024-11-25 14:01:59] logging.py:157 >> {'loss': 0.1379, 'learning_rate': 7.4514e-07, 'epoch': 2.25} + +[INFO|2024-11-25 14:02:19] logging.py:157 >> {'loss': 0.1665, 'learning_rate': 7.4116e-07, 'epoch': 2.25} + +[INFO|2024-11-25 14:02:40] logging.py:157 >> {'loss': 0.1337, 'learning_rate': 7.3719e-07, 'epoch': 2.25} + +[INFO|2024-11-25 14:03:02] logging.py:157 >> {'loss': 0.3001, 'learning_rate': 7.3322e-07, 'epoch': 2.25} + +[INFO|2024-11-25 14:03:24] logging.py:157 >> {'loss': 0.1673, 'learning_rate': 7.2927e-07, 'epoch': 2.26} + +[INFO|2024-11-25 14:03:45] logging.py:157 >> {'loss': 0.1727, 'learning_rate': 7.2532e-07, 'epoch': 2.26} + +[INFO|2024-11-25 14:04:05] logging.py:157 >> {'loss': 0.1634, 'learning_rate': 7.2138e-07, 'epoch': 2.26} + +[INFO|2024-11-25 14:04:26] logging.py:157 >> {'loss': 0.2101, 'learning_rate': 7.1745e-07, 'epoch': 2.26} + +[INFO|2024-11-25 14:04:46] logging.py:157 >> {'loss': 0.2167, 'learning_rate': 7.1353e-07, 'epoch': 2.26} + +[INFO|2024-11-25 14:05:08] logging.py:157 >> {'loss': 0.1175, 'learning_rate': 7.0962e-07, 'epoch': 2.27} + +[INFO|2024-11-25 14:05:29] logging.py:157 >> {'loss': 0.1834, 'learning_rate': 7.0572e-07, 'epoch': 2.27} + +[INFO|2024-11-25 14:05:49] logging.py:157 >> {'loss': 0.0926, 'learning_rate': 7.0182e-07, 'epoch': 2.27} + +[INFO|2024-11-25 14:06:10] logging.py:157 >> {'loss': 0.1592, 'learning_rate': 6.9794e-07, 'epoch': 2.27} + +[INFO|2024-11-25 14:06:31] logging.py:157 >> {'loss': 0.1927, 'learning_rate': 6.9406e-07, 'epoch': 2.27} + +[INFO|2024-11-25 14:06:53] logging.py:157 >> {'loss': 0.2078, 'learning_rate': 6.9020e-07, 'epoch': 2.28} + +[INFO|2024-11-25 14:07:14] logging.py:157 >> {'loss': 0.1582, 'learning_rate': 6.8634e-07, 'epoch': 2.28} + +[INFO|2024-11-25 14:07:35] logging.py:157 >> {'loss': 0.1972, 'learning_rate': 6.8249e-07, 'epoch': 2.28} + +[INFO|2024-11-25 14:07:55] logging.py:157 >> {'loss': 0.1635, 'learning_rate': 6.7865e-07, 'epoch': 2.28} + +[INFO|2024-11-25 14:08:15] logging.py:157 >> {'loss': 0.1746, 'learning_rate': 6.7482e-07, 'epoch': 2.29} + +[INFO|2024-11-25 14:08:36] logging.py:157 >> {'loss': 0.1611, 'learning_rate': 6.7100e-07, 'epoch': 2.29} + +[INFO|2024-11-25 14:08:58] logging.py:157 >> {'loss': 0.1905, 'learning_rate': 6.6719e-07, 'epoch': 2.29} + +[INFO|2024-11-25 14:09:19] logging.py:157 >> {'loss': 0.1512, 'learning_rate': 6.6339e-07, 'epoch': 2.29} + +[INFO|2024-11-25 14:09:40] logging.py:157 >> {'loss': 0.1088, 'learning_rate': 6.5959e-07, 'epoch': 2.29} + +[INFO|2024-11-25 14:10:00] logging.py:157 >> {'loss': 0.1399, 'learning_rate': 6.5581e-07, 'epoch': 2.30} + +[INFO|2024-11-25 14:10:22] logging.py:157 >> {'loss': 0.2310, 'learning_rate': 6.5203e-07, 'epoch': 2.30} + +[INFO|2024-11-25 14:10:42] logging.py:157 >> {'loss': 0.1828, 'learning_rate': 6.4827e-07, 'epoch': 2.30} + +[INFO|2024-11-25 14:11:02] logging.py:157 >> {'loss': 0.1228, 'learning_rate': 6.4451e-07, 'epoch': 2.30} + +[INFO|2024-11-25 14:11:23] logging.py:157 >> {'loss': 0.1959, 'learning_rate': 6.4077e-07, 'epoch': 2.30} + +[INFO|2024-11-25 14:11:44] logging.py:157 >> {'loss': 0.1723, 'learning_rate': 6.3703e-07, 'epoch': 2.31} + +[INFO|2024-11-25 14:12:04] logging.py:157 >> {'loss': 0.1399, 'learning_rate': 6.3330e-07, 'epoch': 2.31} + +[INFO|2024-11-25 14:12:25] logging.py:157 >> {'loss': 0.1240, 'learning_rate': 6.2958e-07, 'epoch': 2.31} + +[INFO|2024-11-25 14:12:45] logging.py:157 >> {'loss': 0.2000, 'learning_rate': 6.2587e-07, 'epoch': 2.31} + +[INFO|2024-11-25 14:13:07] logging.py:157 >> {'loss': 0.2478, 'learning_rate': 6.2217e-07, 'epoch': 2.31} + +[INFO|2024-11-25 14:13:27] logging.py:157 >> {'loss': 0.2235, 'learning_rate': 6.1848e-07, 'epoch': 2.32} + +[INFO|2024-11-25 14:13:48] logging.py:157 >> {'loss': 0.2590, 'learning_rate': 6.1480e-07, 'epoch': 2.32} + +[INFO|2024-11-25 14:14:08] logging.py:157 >> {'loss': 0.1029, 'learning_rate': 6.1113e-07, 'epoch': 2.32} + +[INFO|2024-11-25 14:14:30] logging.py:157 >> {'loss': 0.2121, 'learning_rate': 6.0746e-07, 'epoch': 2.32} + +[INFO|2024-11-25 14:14:51] logging.py:157 >> {'loss': 0.1593, 'learning_rate': 6.0381e-07, 'epoch': 2.33} + +[INFO|2024-11-25 14:15:11] logging.py:157 >> {'loss': 0.2646, 'learning_rate': 6.0017e-07, 'epoch': 2.33} + +[INFO|2024-11-25 14:15:32] logging.py:157 >> {'loss': 0.0587, 'learning_rate': 5.9653e-07, 'epoch': 2.33} + +[INFO|2024-11-25 14:15:54] logging.py:157 >> {'loss': 0.2278, 'learning_rate': 5.9291e-07, 'epoch': 2.33} + +[INFO|2024-11-25 14:16:13] logging.py:157 >> {'loss': 0.2335, 'learning_rate': 5.8929e-07, 'epoch': 2.33} + +[INFO|2024-11-25 14:16:35] logging.py:157 >> {'loss': 0.1164, 'learning_rate': 5.8569e-07, 'epoch': 2.34} + +[INFO|2024-11-25 14:16:56] logging.py:157 >> {'loss': 0.1564, 'learning_rate': 5.8209e-07, 'epoch': 2.34} + +[INFO|2024-11-25 14:17:17] logging.py:157 >> {'loss': 0.1035, 'learning_rate': 5.7851e-07, 'epoch': 2.34} + +[INFO|2024-11-25 14:17:37] logging.py:157 >> {'loss': 0.1593, 'learning_rate': 5.7493e-07, 'epoch': 2.34} + +[INFO|2024-11-25 14:17:59] logging.py:157 >> {'loss': 0.2125, 'learning_rate': 5.7136e-07, 'epoch': 2.34} + +[INFO|2024-11-25 14:18:21] logging.py:157 >> {'loss': 0.2044, 'learning_rate': 5.6781e-07, 'epoch': 2.35} + +[INFO|2024-11-25 14:18:42] logging.py:157 >> {'loss': 0.1786, 'learning_rate': 5.6426e-07, 'epoch': 2.35} + +[INFO|2024-11-25 14:19:04] logging.py:157 >> {'loss': 0.2013, 'learning_rate': 5.6072e-07, 'epoch': 2.35} + +[INFO|2024-11-25 14:19:24] logging.py:157 >> {'loss': 0.0689, 'learning_rate': 5.5719e-07, 'epoch': 2.35} + +[INFO|2024-11-25 14:19:45] logging.py:157 >> {'loss': 0.1401, 'learning_rate': 5.5368e-07, 'epoch': 2.36} + +[INFO|2024-11-25 14:20:06] logging.py:157 >> {'loss': 0.1351, 'learning_rate': 5.5017e-07, 'epoch': 2.36} + +[INFO|2024-11-25 14:20:26] logging.py:157 >> {'loss': 0.1929, 'learning_rate': 5.4667e-07, 'epoch': 2.36} + +[INFO|2024-11-25 14:20:47] logging.py:157 >> {'loss': 0.1553, 'learning_rate': 5.4318e-07, 'epoch': 2.36} + +[INFO|2024-11-25 14:21:07] logging.py:157 >> {'loss': 0.1258, 'learning_rate': 5.3970e-07, 'epoch': 2.36} + +[INFO|2024-11-25 14:21:28] logging.py:157 >> {'loss': 0.1353, 'learning_rate': 5.3623e-07, 'epoch': 2.37} + +[INFO|2024-11-25 14:21:48] logging.py:157 >> {'loss': 0.2128, 'learning_rate': 5.3277e-07, 'epoch': 2.37} + +[INFO|2024-11-25 14:22:08] logging.py:157 >> {'loss': 0.0749, 'learning_rate': 5.2932e-07, 'epoch': 2.37} + +[INFO|2024-11-25 14:22:30] logging.py:157 >> {'loss': 0.2372, 'learning_rate': 5.2588e-07, 'epoch': 2.37} + +[INFO|2024-11-25 14:22:50] logging.py:157 >> {'loss': 0.1649, 'learning_rate': 5.2245e-07, 'epoch': 2.37} + +[INFO|2024-11-25 14:23:10] logging.py:157 >> {'loss': 0.1553, 'learning_rate': 5.1903e-07, 'epoch': 2.38} + +[INFO|2024-11-25 14:23:30] logging.py:157 >> {'loss': 0.1436, 'learning_rate': 5.1562e-07, 'epoch': 2.38} + +[INFO|2024-11-25 14:23:51] logging.py:157 >> {'loss': 0.1716, 'learning_rate': 5.1222e-07, 'epoch': 2.38} + +[INFO|2024-11-25 14:24:12] logging.py:157 >> {'loss': 0.1668, 'learning_rate': 5.0883e-07, 'epoch': 2.38} + +[INFO|2024-11-25 14:24:32] logging.py:157 >> {'loss': 0.1036, 'learning_rate': 5.0545e-07, 'epoch': 2.38} + +[INFO|2024-11-25 14:24:52] logging.py:157 >> {'loss': 0.1721, 'learning_rate': 5.0208e-07, 'epoch': 2.39} + +[INFO|2024-11-25 14:25:13] logging.py:157 >> {'loss': 0.0804, 'learning_rate': 4.9872e-07, 'epoch': 2.39} + +[INFO|2024-11-25 14:25:33] logging.py:157 >> {'loss': 0.1742, 'learning_rate': 4.9537e-07, 'epoch': 2.39} + +[INFO|2024-11-25 14:25:55] logging.py:157 >> {'loss': 0.2472, 'learning_rate': 4.9203e-07, 'epoch': 2.39} + +[INFO|2024-11-25 14:26:15] logging.py:157 >> {'loss': 0.1866, 'learning_rate': 4.8870e-07, 'epoch': 2.40} + +[INFO|2024-11-25 14:26:35] logging.py:157 >> {'loss': 0.0903, 'learning_rate': 4.8538e-07, 'epoch': 2.40} + +[INFO|2024-11-25 14:26:55] logging.py:157 >> {'loss': 0.1345, 'learning_rate': 4.8207e-07, 'epoch': 2.40} + +[INFO|2024-11-25 14:27:16] logging.py:157 >> {'loss': 0.1936, 'learning_rate': 4.7877e-07, 'epoch': 2.40} + +[INFO|2024-11-25 14:27:37] logging.py:157 >> {'loss': 0.1536, 'learning_rate': 4.7549e-07, 'epoch': 2.40} + +[INFO|2024-11-25 14:27:59] logging.py:157 >> {'loss': 0.1719, 'learning_rate': 4.7221e-07, 'epoch': 2.41} + +[INFO|2024-11-25 14:28:20] logging.py:157 >> {'loss': 0.1753, 'learning_rate': 4.6894e-07, 'epoch': 2.41} + +[INFO|2024-11-25 14:28:41] logging.py:157 >> {'loss': 0.1237, 'learning_rate': 4.6568e-07, 'epoch': 2.41} + +[INFO|2024-11-25 14:29:03] logging.py:157 >> {'loss': 0.1424, 'learning_rate': 4.6243e-07, 'epoch': 2.41} + +[INFO|2024-11-25 14:29:23] logging.py:157 >> {'loss': 0.1932, 'learning_rate': 4.5919e-07, 'epoch': 2.41} + +[INFO|2024-11-25 14:29:45] logging.py:157 >> {'loss': 0.1664, 'learning_rate': 4.5596e-07, 'epoch': 2.42} + +[INFO|2024-11-25 14:30:06] logging.py:157 >> {'loss': 0.2251, 'learning_rate': 4.5274e-07, 'epoch': 2.42} + +[INFO|2024-11-25 14:30:26] logging.py:157 >> {'loss': 0.1409, 'learning_rate': 4.4954e-07, 'epoch': 2.42} + +[INFO|2024-11-25 14:30:47] logging.py:157 >> {'loss': 0.1910, 'learning_rate': 4.4634e-07, 'epoch': 2.42} + +[INFO|2024-11-25 14:31:08] logging.py:157 >> {'loss': 0.2368, 'learning_rate': 4.4315e-07, 'epoch': 2.43} + +[INFO|2024-11-25 14:31:29] logging.py:157 >> {'loss': 0.1493, 'learning_rate': 4.3998e-07, 'epoch': 2.43} + +[INFO|2024-11-25 14:31:49] logging.py:157 >> {'loss': 0.1692, 'learning_rate': 4.3681e-07, 'epoch': 2.43} + +[INFO|2024-11-25 14:32:10] logging.py:157 >> {'loss': 0.1777, 'learning_rate': 4.3365e-07, 'epoch': 2.43} + +[INFO|2024-11-25 14:32:30] logging.py:157 >> {'loss': 0.1687, 'learning_rate': 4.3051e-07, 'epoch': 2.43} + +[INFO|2024-11-25 14:32:50] logging.py:157 >> {'loss': 0.1453, 'learning_rate': 4.2737e-07, 'epoch': 2.44} + +[INFO|2024-11-25 14:33:12] logging.py:157 >> {'loss': 0.1837, 'learning_rate': 4.2425e-07, 'epoch': 2.44} + +[INFO|2024-11-25 14:33:32] logging.py:157 >> {'loss': 0.1461, 'learning_rate': 4.2113e-07, 'epoch': 2.44} + +[INFO|2024-11-25 14:33:52] logging.py:157 >> {'loss': 0.1405, 'learning_rate': 4.1803e-07, 'epoch': 2.44} + +[INFO|2024-11-25 14:34:13] logging.py:157 >> {'loss': 0.1662, 'learning_rate': 4.1493e-07, 'epoch': 2.44} + +[INFO|2024-11-25 14:34:34] logging.py:157 >> {'loss': 0.1365, 'learning_rate': 4.1185e-07, 'epoch': 2.45} + +[INFO|2024-11-25 14:34:54] logging.py:157 >> {'loss': 0.1012, 'learning_rate': 4.0878e-07, 'epoch': 2.45} + +[INFO|2024-11-25 14:35:16] logging.py:157 >> {'loss': 0.1600, 'learning_rate': 4.0572e-07, 'epoch': 2.45} + +[INFO|2024-11-25 14:35:37] logging.py:157 >> {'loss': 0.1339, 'learning_rate': 4.0266e-07, 'epoch': 2.45} + +[INFO|2024-11-25 14:35:56] logging.py:157 >> {'loss': 0.1725, 'learning_rate': 3.9962e-07, 'epoch': 2.45} + +[INFO|2024-11-25 14:36:18] logging.py:157 >> {'loss': 0.1981, 'learning_rate': 3.9659e-07, 'epoch': 2.46} + +[INFO|2024-11-25 14:36:40] logging.py:157 >> {'loss': 0.1306, 'learning_rate': 3.9357e-07, 'epoch': 2.46} + +[INFO|2024-11-25 14:37:00] logging.py:157 >> {'loss': 0.1381, 'learning_rate': 3.9056e-07, 'epoch': 2.46} + +[INFO|2024-11-25 14:37:22] logging.py:157 >> {'loss': 0.1665, 'learning_rate': 3.8756e-07, 'epoch': 2.46} + +[INFO|2024-11-25 14:37:42] logging.py:157 >> {'loss': 0.1530, 'learning_rate': 3.8457e-07, 'epoch': 2.47} + +[INFO|2024-11-25 14:38:03] logging.py:157 >> {'loss': 0.2096, 'learning_rate': 3.8160e-07, 'epoch': 2.47} + +[INFO|2024-11-25 14:38:25] logging.py:157 >> {'loss': 0.1243, 'learning_rate': 3.7863e-07, 'epoch': 2.47} + +[INFO|2024-11-25 14:38:45] logging.py:157 >> {'loss': 0.1478, 'learning_rate': 3.7567e-07, 'epoch': 2.47} + +[INFO|2024-11-25 14:39:06] logging.py:157 >> {'loss': 0.1344, 'learning_rate': 3.7273e-07, 'epoch': 2.47} + +[INFO|2024-11-25 14:39:26] logging.py:157 >> {'loss': 0.1596, 'learning_rate': 3.6979e-07, 'epoch': 2.48} + +[INFO|2024-11-25 14:39:47] logging.py:157 >> {'loss': 0.1897, 'learning_rate': 3.6687e-07, 'epoch': 2.48} + +[INFO|2024-11-25 14:40:09] logging.py:157 >> {'loss': 0.1230, 'learning_rate': 3.6395e-07, 'epoch': 2.48} + +[INFO|2024-11-25 14:40:30] logging.py:157 >> {'loss': 0.1602, 'learning_rate': 3.6105e-07, 'epoch': 2.48} + +[INFO|2024-11-25 14:40:54] logging.py:157 >> {'loss': 0.1281, 'learning_rate': 3.5816e-07, 'epoch': 2.48} + +[INFO|2024-11-25 14:41:16] logging.py:157 >> {'loss': 0.2761, 'learning_rate': 3.5527e-07, 'epoch': 2.49} + +[INFO|2024-11-25 14:41:37] logging.py:157 >> {'loss': 0.1354, 'learning_rate': 3.5240e-07, 'epoch': 2.49} + +[INFO|2024-11-25 14:41:57] logging.py:157 >> {'loss': 0.2041, 'learning_rate': 3.4954e-07, 'epoch': 2.49} + +[INFO|2024-11-25 14:42:18] logging.py:157 >> {'loss': 0.1717, 'learning_rate': 3.4669e-07, 'epoch': 2.49} + +[INFO|2024-11-25 14:42:39] logging.py:157 >> {'loss': 0.2393, 'learning_rate': 3.4385e-07, 'epoch': 2.50} + +[INFO|2024-11-25 14:42:59] logging.py:157 >> {'loss': 0.2275, 'learning_rate': 3.4103e-07, 'epoch': 2.50} + +[INFO|2024-11-25 14:43:21] logging.py:157 >> {'loss': 0.1546, 'learning_rate': 3.3821e-07, 'epoch': 2.50} + +[INFO|2024-11-25 14:43:41] logging.py:157 >> {'loss': 0.1479, 'learning_rate': 3.3540e-07, 'epoch': 2.50} + +[INFO|2024-11-25 14:44:03] logging.py:157 >> {'loss': 0.1361, 'learning_rate': 3.3261e-07, 'epoch': 2.50} + +[INFO|2024-11-25 14:44:24] logging.py:157 >> {'loss': 0.1951, 'learning_rate': 3.2982e-07, 'epoch': 2.51} + +[INFO|2024-11-25 14:44:44] logging.py:157 >> {'loss': 0.0913, 'learning_rate': 3.2705e-07, 'epoch': 2.51} + +[INFO|2024-11-25 14:45:05] logging.py:157 >> {'loss': 0.1820, 'learning_rate': 3.2429e-07, 'epoch': 2.51} + +[INFO|2024-11-25 14:45:28] logging.py:157 >> {'loss': 0.1474, 'learning_rate': 3.2154e-07, 'epoch': 2.51} + +[INFO|2024-11-25 14:45:48] logging.py:157 >> {'loss': 0.2535, 'learning_rate': 3.1879e-07, 'epoch': 2.51} + +[INFO|2024-11-25 14:46:09] logging.py:157 >> {'loss': 0.0681, 'learning_rate': 3.1606e-07, 'epoch': 2.52} + +[INFO|2024-11-25 14:46:30] logging.py:157 >> {'loss': 0.1279, 'learning_rate': 3.1335e-07, 'epoch': 2.52} + +[INFO|2024-11-25 14:46:50] logging.py:157 >> {'loss': 0.1971, 'learning_rate': 3.1064e-07, 'epoch': 2.52} + +[INFO|2024-11-25 14:47:12] logging.py:157 >> {'loss': 0.2494, 'learning_rate': 3.0794e-07, 'epoch': 2.52} + +[INFO|2024-11-25 14:47:34] logging.py:157 >> {'loss': 0.1830, 'learning_rate': 3.0525e-07, 'epoch': 2.52} + +[INFO|2024-11-25 14:47:54] logging.py:157 >> {'loss': 0.1433, 'learning_rate': 3.0258e-07, 'epoch': 2.53} + +[INFO|2024-11-25 14:48:15] logging.py:157 >> {'loss': 0.2281, 'learning_rate': 2.9991e-07, 'epoch': 2.53} + +[INFO|2024-11-25 14:48:36] logging.py:157 >> {'loss': 0.1830, 'learning_rate': 2.9726e-07, 'epoch': 2.53} + +[INFO|2024-11-25 14:48:58] logging.py:157 >> {'loss': 0.1823, 'learning_rate': 2.9462e-07, 'epoch': 2.53} + +[INFO|2024-11-25 14:49:19] logging.py:157 >> {'loss': 0.1234, 'learning_rate': 2.9199e-07, 'epoch': 2.54} + +[INFO|2024-11-25 14:49:40] logging.py:157 >> {'loss': 0.2472, 'learning_rate': 2.8937e-07, 'epoch': 2.54} + +[INFO|2024-11-25 14:50:01] logging.py:157 >> {'loss': 0.1547, 'learning_rate': 2.8676e-07, 'epoch': 2.54} + +[INFO|2024-11-25 14:50:21] logging.py:157 >> {'loss': 0.1421, 'learning_rate': 2.8416e-07, 'epoch': 2.54} + +[INFO|2024-11-25 14:50:42] logging.py:157 >> {'loss': 0.0918, 'learning_rate': 2.8158e-07, 'epoch': 2.54} + +[INFO|2024-11-25 14:51:03] logging.py:157 >> {'loss': 0.1396, 'learning_rate': 2.7900e-07, 'epoch': 2.55} + +[INFO|2024-11-25 14:51:23] logging.py:157 >> {'loss': 0.1228, 'learning_rate': 2.7644e-07, 'epoch': 2.55} + +[INFO|2024-11-25 14:51:45] logging.py:157 >> {'loss': 0.1093, 'learning_rate': 2.7388e-07, 'epoch': 2.55} + +[INFO|2024-11-25 14:52:06] logging.py:157 >> {'loss': 0.1161, 'learning_rate': 2.7134e-07, 'epoch': 2.55} + +[INFO|2024-11-25 14:52:27] logging.py:157 >> {'loss': 0.0870, 'learning_rate': 2.6881e-07, 'epoch': 2.55} + +[INFO|2024-11-25 14:52:49] logging.py:157 >> {'loss': 0.1630, 'learning_rate': 2.6629e-07, 'epoch': 2.56} + +[INFO|2024-11-25 14:53:11] logging.py:157 >> {'loss': 0.2213, 'learning_rate': 2.6378e-07, 'epoch': 2.56} + +[INFO|2024-11-25 14:53:33] logging.py:157 >> {'loss': 0.1643, 'learning_rate': 2.6129e-07, 'epoch': 2.56} + +[INFO|2024-11-25 14:53:53] logging.py:157 >> {'loss': 0.1321, 'learning_rate': 2.5880e-07, 'epoch': 2.56} + +[INFO|2024-11-25 14:54:14] logging.py:157 >> {'loss': 0.1203, 'learning_rate': 2.5632e-07, 'epoch': 2.57} + +[INFO|2024-11-25 14:54:35] logging.py:157 >> {'loss': 0.1767, 'learning_rate': 2.5386e-07, 'epoch': 2.57} + +[INFO|2024-11-25 14:54:56] logging.py:157 >> {'loss': 0.1699, 'learning_rate': 2.5141e-07, 'epoch': 2.57} + +[INFO|2024-11-25 14:55:17] logging.py:157 >> {'loss': 0.1116, 'learning_rate': 2.4897e-07, 'epoch': 2.57} + +[INFO|2024-11-25 14:55:39] logging.py:157 >> {'loss': 0.1551, 'learning_rate': 2.4654e-07, 'epoch': 2.57} + +[INFO|2024-11-25 14:56:00] logging.py:157 >> {'loss': 0.1659, 'learning_rate': 2.4412e-07, 'epoch': 2.58} + +[INFO|2024-11-25 14:56:21] logging.py:157 >> {'loss': 0.1267, 'learning_rate': 2.4171e-07, 'epoch': 2.58} + +[INFO|2024-11-25 14:56:41] logging.py:157 >> {'loss': 0.2032, 'learning_rate': 2.3932e-07, 'epoch': 2.58} + +[INFO|2024-11-25 14:57:02] logging.py:157 >> {'loss': 0.1342, 'learning_rate': 2.3693e-07, 'epoch': 2.58} + +[INFO|2024-11-25 14:57:23] logging.py:157 >> {'loss': 0.2205, 'learning_rate': 2.3456e-07, 'epoch': 2.58} + +[INFO|2024-11-25 14:57:43] logging.py:157 >> {'loss': 0.1616, 'learning_rate': 2.3220e-07, 'epoch': 2.59} + +[INFO|2024-11-25 14:58:05] logging.py:157 >> {'loss': 0.0837, 'learning_rate': 2.2985e-07, 'epoch': 2.59} + +[INFO|2024-11-25 14:58:25] logging.py:157 >> {'loss': 0.1858, 'learning_rate': 2.2751e-07, 'epoch': 2.59} + +[INFO|2024-11-25 14:58:46] logging.py:157 >> {'loss': 0.1615, 'learning_rate': 2.2518e-07, 'epoch': 2.59} + +[INFO|2024-11-25 14:59:07] logging.py:157 >> {'loss': 0.1641, 'learning_rate': 2.2286e-07, 'epoch': 2.59} + +[INFO|2024-11-25 14:59:29] logging.py:157 >> {'loss': 0.1021, 'learning_rate': 2.2056e-07, 'epoch': 2.60} + +[INFO|2024-11-25 14:59:51] logging.py:157 >> {'loss': 0.1784, 'learning_rate': 2.1827e-07, 'epoch': 2.60} + +[INFO|2024-11-25 15:00:12] logging.py:157 >> {'loss': 0.0990, 'learning_rate': 2.1598e-07, 'epoch': 2.60} + +[INFO|2024-11-25 15:00:33] logging.py:157 >> {'loss': 0.1403, 'learning_rate': 2.1371e-07, 'epoch': 2.60} + +[INFO|2024-11-25 15:00:53] logging.py:157 >> {'loss': 0.0802, 'learning_rate': 2.1146e-07, 'epoch': 2.61} + +[INFO|2024-11-25 15:01:14] logging.py:157 >> {'loss': 0.2204, 'learning_rate': 2.0921e-07, 'epoch': 2.61} + +[INFO|2024-11-25 15:01:35] logging.py:157 >> {'loss': 0.2012, 'learning_rate': 2.0697e-07, 'epoch': 2.61} + +[INFO|2024-11-25 15:01:56] logging.py:157 >> {'loss': 0.1189, 'learning_rate': 2.0475e-07, 'epoch': 2.61} + +[INFO|2024-11-25 15:02:17] logging.py:157 >> {'loss': 0.1462, 'learning_rate': 2.0253e-07, 'epoch': 2.61} + +[INFO|2024-11-25 15:02:37] logging.py:157 >> {'loss': 0.1963, 'learning_rate': 2.0033e-07, 'epoch': 2.62} + +[INFO|2024-11-25 15:02:59] logging.py:157 >> {'loss': 0.1338, 'learning_rate': 1.9814e-07, 'epoch': 2.62} + +[INFO|2024-11-25 15:03:19] logging.py:157 >> {'loss': 0.1657, 'learning_rate': 1.9596e-07, 'epoch': 2.62} + +[INFO|2024-11-25 15:03:40] logging.py:157 >> {'loss': 0.1489, 'learning_rate': 1.9380e-07, 'epoch': 2.62} + +[INFO|2024-11-25 15:04:02] logging.py:157 >> {'loss': 0.1600, 'learning_rate': 1.9164e-07, 'epoch': 2.62} + +[INFO|2024-11-25 15:04:23] logging.py:157 >> {'loss': 0.1490, 'learning_rate': 1.8950e-07, 'epoch': 2.63} + +[INFO|2024-11-25 15:04:44] logging.py:157 >> {'loss': 0.1035, 'learning_rate': 1.8737e-07, 'epoch': 2.63} + +[INFO|2024-11-25 15:05:05] logging.py:157 >> {'loss': 0.1697, 'learning_rate': 1.8525e-07, 'epoch': 2.63} + +[INFO|2024-11-25 15:05:24] logging.py:157 >> {'loss': 0.1162, 'learning_rate': 1.8314e-07, 'epoch': 2.63} + +[INFO|2024-11-25 15:05:45] logging.py:157 >> {'loss': 0.1021, 'learning_rate': 1.8104e-07, 'epoch': 2.64} + +[INFO|2024-11-25 15:06:06] logging.py:157 >> {'loss': 0.1861, 'learning_rate': 1.7895e-07, 'epoch': 2.64} + +[INFO|2024-11-25 15:06:27] logging.py:157 >> {'loss': 0.1493, 'learning_rate': 1.7688e-07, 'epoch': 2.64} + +[INFO|2024-11-25 15:06:47] logging.py:157 >> {'loss': 0.1817, 'learning_rate': 1.7482e-07, 'epoch': 2.64} + +[INFO|2024-11-25 15:07:08] logging.py:157 >> {'loss': 0.1297, 'learning_rate': 1.7277e-07, 'epoch': 2.64} + +[INFO|2024-11-25 15:07:28] logging.py:157 >> {'loss': 0.1710, 'learning_rate': 1.7073e-07, 'epoch': 2.65} + +[INFO|2024-11-25 15:07:48] logging.py:157 >> {'loss': 0.2401, 'learning_rate': 1.6870e-07, 'epoch': 2.65} + +[INFO|2024-11-25 15:08:09] logging.py:157 >> {'loss': 0.1526, 'learning_rate': 1.6668e-07, 'epoch': 2.65} + +[INFO|2024-11-25 15:08:29] logging.py:157 >> {'loss': 0.1687, 'learning_rate': 1.6468e-07, 'epoch': 2.65} + +[INFO|2024-11-25 15:08:49] logging.py:157 >> {'loss': 0.1425, 'learning_rate': 1.6269e-07, 'epoch': 2.65} + +[INFO|2024-11-25 15:09:10] logging.py:157 >> {'loss': 0.1047, 'learning_rate': 1.6071e-07, 'epoch': 2.66} + +[INFO|2024-11-25 15:09:30] logging.py:157 >> {'loss': 0.0906, 'learning_rate': 1.5874e-07, 'epoch': 2.66} + +[INFO|2024-11-25 15:09:51] logging.py:157 >> {'loss': 0.2841, 'learning_rate': 1.5678e-07, 'epoch': 2.66} + +[INFO|2024-11-25 15:10:12] logging.py:157 >> {'loss': 0.1890, 'learning_rate': 1.5484e-07, 'epoch': 2.66} + +[INFO|2024-11-25 15:10:32] logging.py:157 >> {'loss': 0.1188, 'learning_rate': 1.5290e-07, 'epoch': 2.66} + +[INFO|2024-11-25 15:10:52] logging.py:157 >> {'loss': 0.1719, 'learning_rate': 1.5098e-07, 'epoch': 2.67} + +[INFO|2024-11-25 15:11:13] logging.py:157 >> {'loss': 0.1993, 'learning_rate': 1.4907e-07, 'epoch': 2.67} + +[INFO|2024-11-25 15:11:33] logging.py:157 >> {'loss': 0.0885, 'learning_rate': 1.4717e-07, 'epoch': 2.67} + +[INFO|2024-11-25 15:11:54] logging.py:157 >> {'loss': 0.1655, 'learning_rate': 1.4529e-07, 'epoch': 2.67} + +[INFO|2024-11-25 15:12:15] logging.py:157 >> {'loss': 0.1801, 'learning_rate': 1.4341e-07, 'epoch': 2.68} + +[INFO|2024-11-25 15:12:36] logging.py:157 >> {'loss': 0.0940, 'learning_rate': 1.4155e-07, 'epoch': 2.68} + +[INFO|2024-11-25 15:12:56] logging.py:157 >> {'loss': 0.1391, 'learning_rate': 1.3970e-07, 'epoch': 2.68} + +[INFO|2024-11-25 15:13:17] logging.py:157 >> {'loss': 0.1501, 'learning_rate': 1.3786e-07, 'epoch': 2.68} + +[INFO|2024-11-25 15:13:39] logging.py:157 >> {'loss': 0.1566, 'learning_rate': 1.3603e-07, 'epoch': 2.68} + +[INFO|2024-11-25 15:14:00] logging.py:157 >> {'loss': 0.2451, 'learning_rate': 1.3422e-07, 'epoch': 2.69} + +[INFO|2024-11-25 15:14:21] logging.py:157 >> {'loss': 0.1454, 'learning_rate': 1.3241e-07, 'epoch': 2.69} + +[INFO|2024-11-25 15:14:42] logging.py:157 >> {'loss': 0.1908, 'learning_rate': 1.3062e-07, 'epoch': 2.69} + +[INFO|2024-11-25 15:15:02] logging.py:157 >> {'loss': 0.1143, 'learning_rate': 1.2884e-07, 'epoch': 2.69} + +[INFO|2024-11-25 15:15:23] logging.py:157 >> {'loss': 0.1197, 'learning_rate': 1.2707e-07, 'epoch': 2.69} + +[INFO|2024-11-25 15:15:43] logging.py:157 >> {'loss': 0.1989, 'learning_rate': 1.2532e-07, 'epoch': 2.70} + +[INFO|2024-11-25 15:16:03] logging.py:157 >> {'loss': 0.1403, 'learning_rate': 1.2357e-07, 'epoch': 2.70} + +[INFO|2024-11-25 15:16:24] logging.py:157 >> {'loss': 0.2304, 'learning_rate': 1.2184e-07, 'epoch': 2.70} + +[INFO|2024-11-25 15:16:44] logging.py:157 >> {'loss': 0.1451, 'learning_rate': 1.2012e-07, 'epoch': 2.70} + +[INFO|2024-11-25 15:17:05] logging.py:157 >> {'loss': 0.0898, 'learning_rate': 1.1841e-07, 'epoch': 2.71} + +[INFO|2024-11-25 15:17:26] logging.py:157 >> {'loss': 0.1182, 'learning_rate': 1.1672e-07, 'epoch': 2.71} + +[INFO|2024-11-25 15:17:46] logging.py:157 >> {'loss': 0.1747, 'learning_rate': 1.1503e-07, 'epoch': 2.71} + +[INFO|2024-11-25 15:18:07] logging.py:157 >> {'loss': 0.1696, 'learning_rate': 1.1336e-07, 'epoch': 2.71} + +[INFO|2024-11-25 15:18:29] logging.py:157 >> {'loss': 0.1617, 'learning_rate': 1.1170e-07, 'epoch': 2.71} + +[INFO|2024-11-25 15:18:49] logging.py:157 >> {'loss': 0.1001, 'learning_rate': 1.1005e-07, 'epoch': 2.72} + +[INFO|2024-11-25 15:19:09] logging.py:157 >> {'loss': 0.1711, 'learning_rate': 1.0841e-07, 'epoch': 2.72} + +[INFO|2024-11-25 15:19:31] logging.py:157 >> {'loss': 0.0921, 'learning_rate': 1.0679e-07, 'epoch': 2.72} + +[INFO|2024-11-25 15:19:53] logging.py:157 >> {'loss': 0.1551, 'learning_rate': 1.0517e-07, 'epoch': 2.72} + +[INFO|2024-11-25 15:20:14] logging.py:157 >> {'loss': 0.1658, 'learning_rate': 1.0357e-07, 'epoch': 2.72} + +[INFO|2024-11-25 15:20:34] logging.py:157 >> {'loss': 0.1094, 'learning_rate': 1.0199e-07, 'epoch': 2.73} + +[INFO|2024-11-25 15:20:55] logging.py:157 >> {'loss': 0.2643, 'learning_rate': 1.0041e-07, 'epoch': 2.73} + +[INFO|2024-11-25 15:21:16] logging.py:157 >> {'loss': 0.0869, 'learning_rate': 9.8845e-08, 'epoch': 2.73} + +[INFO|2024-11-25 15:21:36] logging.py:157 >> {'loss': 0.1214, 'learning_rate': 9.7292e-08, 'epoch': 2.73} + +[INFO|2024-11-25 15:21:58] logging.py:157 >> {'loss': 0.2651, 'learning_rate': 9.5752e-08, 'epoch': 2.73} + +[INFO|2024-11-25 15:22:19] logging.py:157 >> {'loss': 0.0823, 'learning_rate': 9.4223e-08, 'epoch': 2.74} + +[INFO|2024-11-25 15:22:39] logging.py:157 >> {'loss': 0.1873, 'learning_rate': 9.2707e-08, 'epoch': 2.74} + +[INFO|2024-11-25 15:23:01] logging.py:157 >> {'loss': 0.2122, 'learning_rate': 9.1202e-08, 'epoch': 2.74} + +[INFO|2024-11-25 15:23:24] logging.py:157 >> {'loss': 0.1604, 'learning_rate': 8.9710e-08, 'epoch': 2.74} + +[INFO|2024-11-25 15:23:44] logging.py:157 >> {'loss': 0.1293, 'learning_rate': 8.8230e-08, 'epoch': 2.75} + +[INFO|2024-11-25 15:24:04] logging.py:157 >> {'loss': 0.1202, 'learning_rate': 8.6762e-08, 'epoch': 2.75} + +[INFO|2024-11-25 15:24:25] logging.py:157 >> {'loss': 0.1630, 'learning_rate': 8.5306e-08, 'epoch': 2.75} + +[INFO|2024-11-25 15:24:45] logging.py:157 >> {'loss': 0.1314, 'learning_rate': 8.3862e-08, 'epoch': 2.75} + +[INFO|2024-11-25 15:25:07] logging.py:157 >> {'loss': 0.1117, 'learning_rate': 8.2431e-08, 'epoch': 2.75} + +[INFO|2024-11-25 15:25:28] logging.py:157 >> {'loss': 0.2353, 'learning_rate': 8.1011e-08, 'epoch': 2.76} + +[INFO|2024-11-25 15:25:50] logging.py:157 >> {'loss': 0.1271, 'learning_rate': 7.9604e-08, 'epoch': 2.76} + +[INFO|2024-11-25 15:26:10] logging.py:157 >> {'loss': 0.1141, 'learning_rate': 7.8208e-08, 'epoch': 2.76} + +[INFO|2024-11-25 15:26:31] logging.py:157 >> {'loss': 0.1758, 'learning_rate': 7.6825e-08, 'epoch': 2.76} + +[INFO|2024-11-25 15:26:53] logging.py:157 >> {'loss': 0.0946, 'learning_rate': 7.5454e-08, 'epoch': 2.76} + +[INFO|2024-11-25 15:27:14] logging.py:157 >> {'loss': 0.1267, 'learning_rate': 7.4095e-08, 'epoch': 2.77} + +[INFO|2024-11-25 15:27:36] logging.py:157 >> {'loss': 0.1801, 'learning_rate': 7.2749e-08, 'epoch': 2.77} + +[INFO|2024-11-25 15:27:56] logging.py:157 >> {'loss': 0.1650, 'learning_rate': 7.1414e-08, 'epoch': 2.77} + +[INFO|2024-11-25 15:28:17] logging.py:157 >> {'loss': 0.1933, 'learning_rate': 7.0092e-08, 'epoch': 2.77} + +[INFO|2024-11-25 15:28:39] logging.py:157 >> {'loss': 0.1828, 'learning_rate': 6.8781e-08, 'epoch': 2.77} + +[INFO|2024-11-25 15:29:00] logging.py:157 >> {'loss': 0.1831, 'learning_rate': 6.7483e-08, 'epoch': 2.78} + +[INFO|2024-11-25 15:29:20] logging.py:157 >> {'loss': 0.2365, 'learning_rate': 6.6198e-08, 'epoch': 2.78} + +[INFO|2024-11-25 15:29:41] logging.py:157 >> {'loss': 0.1281, 'learning_rate': 6.4924e-08, 'epoch': 2.78} + +[INFO|2024-11-25 15:30:01] logging.py:157 >> {'loss': 0.1193, 'learning_rate': 6.3663e-08, 'epoch': 2.78} + +[INFO|2024-11-25 15:30:21] logging.py:157 >> {'loss': 0.0859, 'learning_rate': 6.2414e-08, 'epoch': 2.79} + +[INFO|2024-11-25 15:30:42] logging.py:157 >> {'loss': 0.1035, 'learning_rate': 6.1177e-08, 'epoch': 2.79} + +[INFO|2024-11-25 15:31:02] logging.py:157 >> {'loss': 0.1114, 'learning_rate': 5.9952e-08, 'epoch': 2.79} + +[INFO|2024-11-25 15:31:24] logging.py:157 >> {'loss': 0.0927, 'learning_rate': 5.8739e-08, 'epoch': 2.79} + +[INFO|2024-11-25 15:31:45] logging.py:157 >> {'loss': 0.1889, 'learning_rate': 5.7539e-08, 'epoch': 2.79} + +[INFO|2024-11-25 15:32:06] logging.py:157 >> {'loss': 0.2010, 'learning_rate': 5.6351e-08, 'epoch': 2.80} + +[INFO|2024-11-25 15:32:26] logging.py:157 >> {'loss': 0.1615, 'learning_rate': 5.5175e-08, 'epoch': 2.80} + +[INFO|2024-11-25 15:32:47] logging.py:157 >> {'loss': 0.1195, 'learning_rate': 5.4012e-08, 'epoch': 2.80} + +[INFO|2024-11-25 15:33:09] logging.py:157 >> {'loss': 0.1593, 'learning_rate': 5.2861e-08, 'epoch': 2.80} + +[INFO|2024-11-25 15:33:29] logging.py:157 >> {'loss': 0.0893, 'learning_rate': 5.1722e-08, 'epoch': 2.80} + +[INFO|2024-11-25 15:33:49] logging.py:157 >> {'loss': 0.2956, 'learning_rate': 5.0595e-08, 'epoch': 2.81} + +[INFO|2024-11-25 15:34:11] logging.py:157 >> {'loss': 0.1717, 'learning_rate': 4.9481e-08, 'epoch': 2.81} + +[INFO|2024-11-25 15:34:32] logging.py:157 >> {'loss': 0.0977, 'learning_rate': 4.8379e-08, 'epoch': 2.81} + +[INFO|2024-11-25 15:34:52] logging.py:157 >> {'loss': 0.1553, 'learning_rate': 4.7289e-08, 'epoch': 2.81} + +[INFO|2024-11-25 15:35:12] logging.py:157 >> {'loss': 0.1686, 'learning_rate': 4.6211e-08, 'epoch': 2.82} + +[INFO|2024-11-25 15:35:33] logging.py:157 >> {'loss': 0.1846, 'learning_rate': 4.5146e-08, 'epoch': 2.82} + +[INFO|2024-11-25 15:35:54] logging.py:157 >> {'loss': 0.1363, 'learning_rate': 4.4093e-08, 'epoch': 2.82} + +[INFO|2024-11-25 15:36:14] logging.py:157 >> {'loss': 0.1339, 'learning_rate': 4.3053e-08, 'epoch': 2.82} + +[INFO|2024-11-25 15:36:36] logging.py:157 >> {'loss': 0.1288, 'learning_rate': 4.2024e-08, 'epoch': 2.82} + +[INFO|2024-11-25 15:36:58] logging.py:157 >> {'loss': 0.1397, 'learning_rate': 4.1008e-08, 'epoch': 2.83} + +[INFO|2024-11-25 15:37:18] logging.py:157 >> {'loss': 0.1248, 'learning_rate': 4.0005e-08, 'epoch': 2.83} + +[INFO|2024-11-25 15:37:39] logging.py:157 >> {'loss': 0.1981, 'learning_rate': 3.9014e-08, 'epoch': 2.83} + +[INFO|2024-11-25 15:38:00] logging.py:157 >> {'loss': 0.1387, 'learning_rate': 3.8035e-08, 'epoch': 2.83} + +[INFO|2024-11-25 15:38:20] logging.py:157 >> {'loss': 0.1013, 'learning_rate': 3.7068e-08, 'epoch': 2.83} + +[INFO|2024-11-25 15:38:40] logging.py:157 >> {'loss': 0.2936, 'learning_rate': 3.6114e-08, 'epoch': 2.84} + +[INFO|2024-11-25 15:39:03] logging.py:157 >> {'loss': 0.1551, 'learning_rate': 3.5172e-08, 'epoch': 2.84} + +[INFO|2024-11-25 15:39:24] logging.py:157 >> {'loss': 0.1314, 'learning_rate': 3.4242e-08, 'epoch': 2.84} + +[INFO|2024-11-25 15:39:43] logging.py:157 >> {'loss': 0.1936, 'learning_rate': 3.3325e-08, 'epoch': 2.84} + +[INFO|2024-11-25 15:40:04] logging.py:157 >> {'loss': 0.1696, 'learning_rate': 3.2420e-08, 'epoch': 2.84} + +[INFO|2024-11-25 15:40:24] logging.py:157 >> {'loss': 0.0762, 'learning_rate': 3.1528e-08, 'epoch': 2.85} + +[INFO|2024-11-25 15:40:46] logging.py:157 >> {'loss': 0.1341, 'learning_rate': 3.0648e-08, 'epoch': 2.85} + +[INFO|2024-11-25 15:41:06] logging.py:157 >> {'loss': 0.1482, 'learning_rate': 2.9780e-08, 'epoch': 2.85} + +[INFO|2024-11-25 15:41:27] logging.py:157 >> {'loss': 0.1360, 'learning_rate': 2.8925e-08, 'epoch': 2.85} + +[INFO|2024-11-25 15:41:48] logging.py:157 >> {'loss': 0.1296, 'learning_rate': 2.8082e-08, 'epoch': 2.86} + +[INFO|2024-11-25 15:42:08] logging.py:157 >> {'loss': 0.1119, 'learning_rate': 2.7252e-08, 'epoch': 2.86} + +[INFO|2024-11-25 15:42:28] logging.py:157 >> {'loss': 0.1892, 'learning_rate': 2.6433e-08, 'epoch': 2.86} + +[INFO|2024-11-25 15:42:50] logging.py:157 >> {'loss': 0.1666, 'learning_rate': 2.5628e-08, 'epoch': 2.86} + +[INFO|2024-11-25 15:43:10] logging.py:157 >> {'loss': 0.1364, 'learning_rate': 2.4834e-08, 'epoch': 2.86} + +[INFO|2024-11-25 15:43:31] logging.py:157 >> {'loss': 0.1658, 'learning_rate': 2.4054e-08, 'epoch': 2.87} + +[INFO|2024-11-25 15:43:52] logging.py:157 >> {'loss': 0.1677, 'learning_rate': 2.3285e-08, 'epoch': 2.87} + +[INFO|2024-11-25 15:44:14] logging.py:157 >> {'loss': 0.1026, 'learning_rate': 2.2529e-08, 'epoch': 2.87} + +[INFO|2024-11-25 15:44:35] logging.py:157 >> {'loss': 0.1761, 'learning_rate': 2.1785e-08, 'epoch': 2.87} + +[INFO|2024-11-25 15:44:56] logging.py:157 >> {'loss': 0.2169, 'learning_rate': 2.1054e-08, 'epoch': 2.87} + +[INFO|2024-11-25 15:45:18] logging.py:157 >> {'loss': 0.1990, 'learning_rate': 2.0335e-08, 'epoch': 2.88} + +[INFO|2024-11-25 15:45:39] logging.py:157 >> {'loss': 0.1348, 'learning_rate': 1.9629e-08, 'epoch': 2.88} + +[INFO|2024-11-25 15:46:00] logging.py:157 >> {'loss': 0.0994, 'learning_rate': 1.8935e-08, 'epoch': 2.88} + +[INFO|2024-11-25 15:46:21] logging.py:157 >> {'loss': 0.1815, 'learning_rate': 1.8254e-08, 'epoch': 2.88} + +[INFO|2024-11-25 15:46:42] logging.py:157 >> {'loss': 0.1956, 'learning_rate': 1.7585e-08, 'epoch': 2.89} + +[INFO|2024-11-25 15:47:03] logging.py:157 >> {'loss': 0.1832, 'learning_rate': 1.6928e-08, 'epoch': 2.89} + +[INFO|2024-11-25 15:47:23] logging.py:157 >> {'loss': 0.2045, 'learning_rate': 1.6284e-08, 'epoch': 2.89} + +[INFO|2024-11-25 15:47:44] logging.py:157 >> {'loss': 0.1563, 'learning_rate': 1.5652e-08, 'epoch': 2.89} + +[INFO|2024-11-25 15:48:04] logging.py:157 >> {'loss': 0.1395, 'learning_rate': 1.5033e-08, 'epoch': 2.89} + +[INFO|2024-11-25 15:48:26] logging.py:157 >> {'loss': 0.1354, 'learning_rate': 1.4426e-08, 'epoch': 2.90} + +[INFO|2024-11-25 15:48:47] logging.py:157 >> {'loss': 0.1807, 'learning_rate': 1.3832e-08, 'epoch': 2.90} + +[INFO|2024-11-25 15:49:08] logging.py:157 >> {'loss': 0.2193, 'learning_rate': 1.3250e-08, 'epoch': 2.90} + +[INFO|2024-11-25 15:49:29] logging.py:157 >> {'loss': 0.1427, 'learning_rate': 1.2681e-08, 'epoch': 2.90} + +[INFO|2024-11-25 15:49:49] logging.py:157 >> {'loss': 0.1666, 'learning_rate': 1.2124e-08, 'epoch': 2.90} + +[INFO|2024-11-25 15:50:10] logging.py:157 >> {'loss': 0.1087, 'learning_rate': 1.1580e-08, 'epoch': 2.91} + +[INFO|2024-11-25 15:50:31] logging.py:157 >> {'loss': 0.1042, 'learning_rate': 1.1048e-08, 'epoch': 2.91} + +[INFO|2024-11-25 15:50:51] logging.py:157 >> {'loss': 0.1230, 'learning_rate': 1.0528e-08, 'epoch': 2.91} + +[INFO|2024-11-25 15:51:13] logging.py:157 >> {'loss': 0.2518, 'learning_rate': 1.0021e-08, 'epoch': 2.91} + +[INFO|2024-11-25 15:51:35] logging.py:157 >> {'loss': 0.1938, 'learning_rate': 9.5268e-09, 'epoch': 2.91} + +[INFO|2024-11-25 15:51:55] logging.py:157 >> {'loss': 0.1524, 'learning_rate': 9.0448e-09, 'epoch': 2.92} + +[INFO|2024-11-25 15:52:17] logging.py:157 >> {'loss': 0.0865, 'learning_rate': 8.5753e-09, 'epoch': 2.92} + +[INFO|2024-11-25 15:52:38] logging.py:157 >> {'loss': 0.1245, 'learning_rate': 8.1183e-09, 'epoch': 2.92} + +[INFO|2024-11-25 15:52:58] logging.py:157 >> {'loss': 0.1392, 'learning_rate': 7.6738e-09, 'epoch': 2.92} + +[INFO|2024-11-25 15:53:20] logging.py:157 >> {'loss': 0.1392, 'learning_rate': 7.2417e-09, 'epoch': 2.93} + +[INFO|2024-11-25 15:53:40] logging.py:157 >> {'loss': 0.1728, 'learning_rate': 6.8222e-09, 'epoch': 2.93} + +[INFO|2024-11-25 15:54:01] logging.py:157 >> {'loss': 0.1577, 'learning_rate': 6.4152e-09, 'epoch': 2.93} + +[INFO|2024-11-25 15:54:22] logging.py:157 >> {'loss': 0.1659, 'learning_rate': 6.0207e-09, 'epoch': 2.93} + +[INFO|2024-11-25 15:54:42] logging.py:157 >> {'loss': 0.1507, 'learning_rate': 5.6386e-09, 'epoch': 2.93} + +[INFO|2024-11-25 15:55:03] logging.py:157 >> {'loss': 0.1365, 'learning_rate': 5.2691e-09, 'epoch': 2.94} + +[INFO|2024-11-25 15:55:24] logging.py:157 >> {'loss': 0.1626, 'learning_rate': 4.9121e-09, 'epoch': 2.94} + +[INFO|2024-11-25 15:55:45] logging.py:157 >> {'loss': 0.1482, 'learning_rate': 4.5676e-09, 'epoch': 2.94} + +[INFO|2024-11-25 15:56:09] logging.py:157 >> {'loss': 0.1666, 'learning_rate': 4.2356e-09, 'epoch': 2.94} + +[INFO|2024-11-25 15:56:32] logging.py:157 >> {'loss': 0.1035, 'learning_rate': 3.9162e-09, 'epoch': 2.94} + +[INFO|2024-11-25 15:56:53] logging.py:157 >> {'loss': 0.1345, 'learning_rate': 3.6092e-09, 'epoch': 2.95} + +[INFO|2024-11-25 15:57:13] logging.py:157 >> {'loss': 0.1287, 'learning_rate': 3.3148e-09, 'epoch': 2.95} + +[INFO|2024-11-25 15:57:34] logging.py:157 >> {'loss': 0.1304, 'learning_rate': 3.0329e-09, 'epoch': 2.95} + +[INFO|2024-11-25 15:57:55] logging.py:157 >> {'loss': 0.1966, 'learning_rate': 2.7635e-09, 'epoch': 2.95} + +[INFO|2024-11-25 15:58:16] logging.py:157 >> {'loss': 0.1600, 'learning_rate': 2.5066e-09, 'epoch': 2.96} + +[INFO|2024-11-25 15:58:39] logging.py:157 >> {'loss': 0.2442, 'learning_rate': 2.2622e-09, 'epoch': 2.96} + +[INFO|2024-11-25 15:58:59] logging.py:157 >> {'loss': 0.1084, 'learning_rate': 2.0304e-09, 'epoch': 2.96} + +[INFO|2024-11-25 15:59:20] logging.py:157 >> {'loss': 0.1805, 'learning_rate': 1.8111e-09, 'epoch': 2.96} + +[INFO|2024-11-25 15:59:40] logging.py:157 >> {'loss': 0.1576, 'learning_rate': 1.6043e-09, 'epoch': 2.96} + +[INFO|2024-11-25 16:00:02] logging.py:157 >> {'loss': 0.1739, 'learning_rate': 1.4101e-09, 'epoch': 2.97} + +[INFO|2024-11-25 16:00:23] logging.py:157 >> {'loss': 0.1755, 'learning_rate': 1.2283e-09, 'epoch': 2.97} + +[INFO|2024-11-25 16:00:43] logging.py:157 >> {'loss': 0.1123, 'learning_rate': 1.0591e-09, 'epoch': 2.97} + +[INFO|2024-11-25 16:01:05] logging.py:157 >> {'loss': 0.1952, 'learning_rate': 9.0247e-10, 'epoch': 2.97} + +[INFO|2024-11-25 16:01:26] logging.py:157 >> {'loss': 0.1802, 'learning_rate': 7.5833e-10, 'epoch': 2.97} + +[INFO|2024-11-25 16:01:46] logging.py:157 >> {'loss': 0.1862, 'learning_rate': 6.2672e-10, 'epoch': 2.98} + +[INFO|2024-11-25 16:02:07] logging.py:157 >> {'loss': 0.1186, 'learning_rate': 5.0765e-10, 'epoch': 2.98} + +[INFO|2024-11-25 16:02:28] logging.py:157 >> {'loss': 0.2020, 'learning_rate': 4.0111e-10, 'epoch': 2.98} + +[INFO|2024-11-25 16:02:48] logging.py:157 >> {'loss': 0.1106, 'learning_rate': 3.0710e-10, 'epoch': 2.98} + +[INFO|2024-11-25 16:03:09] logging.py:157 >> {'loss': 0.2274, 'learning_rate': 2.2563e-10, 'epoch': 2.98} + +[INFO|2024-11-25 16:03:29] logging.py:157 >> {'loss': 0.0980, 'learning_rate': 1.5669e-10, 'epoch': 2.99} + +[INFO|2024-11-25 16:03:49] logging.py:157 >> {'loss': 0.1817, 'learning_rate': 1.0028e-10, 'epoch': 2.99} + +[INFO|2024-11-25 16:04:11] logging.py:157 >> {'loss': 0.1669, 'learning_rate': 5.6407e-11, 'epoch': 2.99} + +[INFO|2024-11-25 16:04:30] logging.py:157 >> {'loss': 0.1413, 'learning_rate': 2.5070e-11, 'epoch': 2.99} + +[INFO|2024-11-25 16:04:50] logging.py:157 >> {'loss': 0.3418, 'learning_rate': 6.2675e-12, 'epoch': 3.00} + +[INFO|2024-11-25 16:05:11] logging.py:157 >> {'loss': 0.1737, 'learning_rate': 0.0000e+00, 'epoch': 3.00} + +[INFO|2024-11-25 16:05:19] trainer.py:3801 >> Saving model checkpoint to saves/Llama-3-8B-Instruct/full/train_2024-11-25-07-46-41/checkpoint-1413 + +[INFO|2024-11-25 16:05:19] configuration_utils.py:414 >> Configuration saved in saves/Llama-3-8B-Instruct/full/train_2024-11-25-07-46-41/checkpoint-1413/config.json + +[INFO|2024-11-25 16:05:19] configuration_utils.py:865 >> Configuration saved in saves/Llama-3-8B-Instruct/full/train_2024-11-25-07-46-41/checkpoint-1413/generation_config.json + +[INFO|2024-11-25 16:05:38] modeling_utils.py:3043 >> The model is bigger than the maximum size per checkpoint (5GB) and is going to be split in 4 checkpoint shards. You can find where each parameters has been saved in the index located at saves/Llama-3-8B-Instruct/full/train_2024-11-25-07-46-41/checkpoint-1413/model.safetensors.index.json. + +[INFO|2024-11-25 16:05:38] tokenization_utils_base.py:2646 >> tokenizer config file saved in saves/Llama-3-8B-Instruct/full/train_2024-11-25-07-46-41/checkpoint-1413/tokenizer_config.json + +[INFO|2024-11-25 16:05:38] tokenization_utils_base.py:2655 >> Special tokens file saved in saves/Llama-3-8B-Instruct/full/train_2024-11-25-07-46-41/checkpoint-1413/special_tokens_map.json + +[INFO|2024-11-25 16:06:37] trainer.py:2584 >> + +Training completed. Do not forget to share your model on huggingface.co/models =) + + + +[INFO|2024-11-25 16:06:45] trainer.py:3801 >> Saving model checkpoint to saves/Llama-3-8B-Instruct/full/train_2024-11-25-07-46-41 + +[INFO|2024-11-25 16:06:45] configuration_utils.py:414 >> Configuration saved in saves/Llama-3-8B-Instruct/full/train_2024-11-25-07-46-41/config.json + +[INFO|2024-11-25 16:06:45] configuration_utils.py:865 >> Configuration saved in saves/Llama-3-8B-Instruct/full/train_2024-11-25-07-46-41/generation_config.json + +[INFO|2024-11-25 16:07:17] modeling_utils.py:3043 >> The model is bigger than the maximum size per checkpoint (5GB) and is going to be split in 4 checkpoint shards. You can find where each parameters has been saved in the index located at saves/Llama-3-8B-Instruct/full/train_2024-11-25-07-46-41/model.safetensors.index.json. + +[INFO|2024-11-25 16:07:17] tokenization_utils_base.py:2646 >> tokenizer config file saved in saves/Llama-3-8B-Instruct/full/train_2024-11-25-07-46-41/tokenizer_config.json + +[INFO|2024-11-25 16:07:17] tokenization_utils_base.py:2655 >> Special tokens file saved in saves/Llama-3-8B-Instruct/full/train_2024-11-25-07-46-41/special_tokens_map.json + +[WARNING|2024-11-25 16:07:18] logging.py:162 >> No metric eval_loss to plot. + +[WARNING|2024-11-25 16:07:18] logging.py:162 >> No metric eval_accuracy to plot. + +[INFO|2024-11-25 16:07:18] modelcard.py:449 >> Dropping the following result as it does not have all the necessary fields: +{'task': {'name': 'Causal Language Modeling', 'type': 'text-generation'}} + diff --git a/rag_truth_hal_detection_model/special_tokens_map.json b/rag_truth_hal_detection_model/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..b43be96621d147110fb8a18b5776ec6e38516127 --- /dev/null +++ b/rag_truth_hal_detection_model/special_tokens_map.json @@ -0,0 +1,17 @@ +{ + "bos_token": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "<|eot_id|>" +} diff --git a/rag_truth_hal_detection_model/tokenizer.json b/rag_truth_hal_detection_model/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..86a33946b0c77216d2cce91bb28c8fada4a5e80b --- /dev/null +++ b/rag_truth_hal_detection_model/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c5cf44023714fb39b05e71e425f8d7b92805ff73f7988b083b8c87f0bf87393 +size 17209961 diff --git a/rag_truth_hal_detection_model/tokenizer_config.json b/rag_truth_hal_detection_model/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..82b337616471d4177c3b572a92a182f302f28430 --- /dev/null +++ b/rag_truth_hal_detection_model/tokenizer_config.json @@ -0,0 +1,2065 @@ +{ + "added_tokens_decoder": { + "128000": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128001": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128002": { + "content": "<|reserved_special_token_0|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128003": { + "content": "<|reserved_special_token_1|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128004": { + "content": "<|reserved_special_token_2|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128005": { + "content": "<|reserved_special_token_3|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128006": { + "content": "<|start_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128007": { + "content": "<|end_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128008": { + "content": "<|reserved_special_token_4|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128009": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128010": { + "content": "<|reserved_special_token_5|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128011": { + "content": "<|reserved_special_token_6|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128012": { + "content": "<|reserved_special_token_7|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128013": { + "content": "<|reserved_special_token_8|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128014": { + "content": "<|reserved_special_token_9|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128015": { + "content": "<|reserved_special_token_10|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128016": { + "content": "<|reserved_special_token_11|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128017": { + "content": "<|reserved_special_token_12|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128018": { + "content": "<|reserved_special_token_13|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128019": { + "content": "<|reserved_special_token_14|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128020": { + "content": "<|reserved_special_token_15|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128021": { + "content": "<|reserved_special_token_16|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128022": { + "content": "<|reserved_special_token_17|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128023": { + "content": "<|reserved_special_token_18|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128024": { + "content": "<|reserved_special_token_19|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128025": { + "content": "<|reserved_special_token_20|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128026": { + "content": "<|reserved_special_token_21|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128027": { + "content": "<|reserved_special_token_22|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128028": { + "content": "<|reserved_special_token_23|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128029": { + "content": "<|reserved_special_token_24|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128030": { + "content": "<|reserved_special_token_25|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128031": { + "content": "<|reserved_special_token_26|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128032": { + "content": "<|reserved_special_token_27|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128033": { + "content": "<|reserved_special_token_28|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128034": { + "content": "<|reserved_special_token_29|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128035": { + "content": "<|reserved_special_token_30|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128036": { + "content": "<|reserved_special_token_31|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128037": { + "content": "<|reserved_special_token_32|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128038": { + "content": "<|reserved_special_token_33|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128039": { + "content": "<|reserved_special_token_34|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128040": { + "content": "<|reserved_special_token_35|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128041": { + "content": "<|reserved_special_token_36|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128042": { + "content": "<|reserved_special_token_37|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128043": { + "content": "<|reserved_special_token_38|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128044": { + "content": "<|reserved_special_token_39|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128045": { + "content": "<|reserved_special_token_40|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128046": { + "content": "<|reserved_special_token_41|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128047": { + "content": "<|reserved_special_token_42|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128048": { + "content": "<|reserved_special_token_43|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128049": { + "content": "<|reserved_special_token_44|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128050": { + "content": "<|reserved_special_token_45|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128051": { + "content": "<|reserved_special_token_46|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128052": { + "content": "<|reserved_special_token_47|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128053": { + "content": "<|reserved_special_token_48|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128054": { + "content": "<|reserved_special_token_49|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128055": { + "content": "<|reserved_special_token_50|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128056": { + "content": "<|reserved_special_token_51|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128057": { + "content": "<|reserved_special_token_52|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128058": { + "content": "<|reserved_special_token_53|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128059": { + "content": "<|reserved_special_token_54|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128060": { + "content": "<|reserved_special_token_55|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128061": { + "content": "<|reserved_special_token_56|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128062": { + "content": "<|reserved_special_token_57|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128063": { + "content": "<|reserved_special_token_58|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128064": { + "content": "<|reserved_special_token_59|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128065": { + "content": "<|reserved_special_token_60|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128066": { + "content": "<|reserved_special_token_61|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128067": { + "content": "<|reserved_special_token_62|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128068": { + "content": "<|reserved_special_token_63|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128069": { + "content": "<|reserved_special_token_64|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128070": { + "content": "<|reserved_special_token_65|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128071": { + "content": "<|reserved_special_token_66|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128072": { + "content": "<|reserved_special_token_67|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128073": { + "content": "<|reserved_special_token_68|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128074": { + "content": "<|reserved_special_token_69|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128075": { + "content": "<|reserved_special_token_70|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128076": { + "content": "<|reserved_special_token_71|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128077": { + "content": "<|reserved_special_token_72|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128078": { + "content": "<|reserved_special_token_73|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128079": { + "content": "<|reserved_special_token_74|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128080": { + "content": "<|reserved_special_token_75|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128081": { + "content": "<|reserved_special_token_76|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128082": { + "content": "<|reserved_special_token_77|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128083": { + "content": "<|reserved_special_token_78|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128084": { + "content": "<|reserved_special_token_79|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128085": { + "content": "<|reserved_special_token_80|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128086": { + "content": "<|reserved_special_token_81|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128087": { + "content": "<|reserved_special_token_82|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128088": { + "content": "<|reserved_special_token_83|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128089": { + "content": "<|reserved_special_token_84|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128090": { + "content": "<|reserved_special_token_85|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128091": { + "content": "<|reserved_special_token_86|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128092": { + "content": "<|reserved_special_token_87|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128093": { + "content": "<|reserved_special_token_88|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128094": { + "content": "<|reserved_special_token_89|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128095": { + "content": "<|reserved_special_token_90|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128096": { + "content": "<|reserved_special_token_91|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128097": { + "content": "<|reserved_special_token_92|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128098": { + "content": "<|reserved_special_token_93|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128099": { + "content": "<|reserved_special_token_94|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128100": { + "content": "<|reserved_special_token_95|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128101": { + "content": "<|reserved_special_token_96|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128102": { + "content": "<|reserved_special_token_97|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128103": { + "content": "<|reserved_special_token_98|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128104": { + "content": "<|reserved_special_token_99|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128105": { + "content": "<|reserved_special_token_100|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128106": { + "content": "<|reserved_special_token_101|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128107": { + "content": "<|reserved_special_token_102|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128108": { + "content": "<|reserved_special_token_103|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128109": { + "content": "<|reserved_special_token_104|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128110": { + "content": "<|reserved_special_token_105|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128111": { + "content": "<|reserved_special_token_106|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128112": { + "content": "<|reserved_special_token_107|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128113": { + "content": "<|reserved_special_token_108|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128114": { + "content": "<|reserved_special_token_109|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128115": { + "content": "<|reserved_special_token_110|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128116": { + "content": "<|reserved_special_token_111|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128117": { + "content": "<|reserved_special_token_112|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128118": { + "content": "<|reserved_special_token_113|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128119": { + "content": "<|reserved_special_token_114|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128120": { + "content": "<|reserved_special_token_115|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128121": { + "content": "<|reserved_special_token_116|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128122": { + "content": "<|reserved_special_token_117|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128123": { + "content": "<|reserved_special_token_118|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128124": { + "content": "<|reserved_special_token_119|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128125": { + "content": "<|reserved_special_token_120|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128126": { + "content": "<|reserved_special_token_121|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128127": { + "content": "<|reserved_special_token_122|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128128": { + "content": "<|reserved_special_token_123|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128129": { + "content": "<|reserved_special_token_124|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128130": { + "content": "<|reserved_special_token_125|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128131": { + "content": "<|reserved_special_token_126|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128132": { + "content": "<|reserved_special_token_127|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128133": { + "content": "<|reserved_special_token_128|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128134": { + "content": "<|reserved_special_token_129|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128135": { + "content": "<|reserved_special_token_130|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128136": { + "content": "<|reserved_special_token_131|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128137": { + "content": "<|reserved_special_token_132|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128138": { + "content": "<|reserved_special_token_133|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128139": { + "content": "<|reserved_special_token_134|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128140": { + "content": "<|reserved_special_token_135|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128141": { + "content": "<|reserved_special_token_136|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128142": { + "content": "<|reserved_special_token_137|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128143": { + "content": "<|reserved_special_token_138|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128144": { + "content": "<|reserved_special_token_139|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128145": { + "content": "<|reserved_special_token_140|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128146": { + "content": "<|reserved_special_token_141|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128147": { + "content": "<|reserved_special_token_142|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128148": { + "content": "<|reserved_special_token_143|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128149": { + "content": "<|reserved_special_token_144|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128150": { + "content": "<|reserved_special_token_145|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128151": { + "content": "<|reserved_special_token_146|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128152": { + "content": "<|reserved_special_token_147|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128153": { + "content": "<|reserved_special_token_148|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128154": { + "content": "<|reserved_special_token_149|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128155": { + "content": "<|reserved_special_token_150|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128156": { + "content": "<|reserved_special_token_151|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128157": { + "content": "<|reserved_special_token_152|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128158": { + "content": "<|reserved_special_token_153|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128159": { + "content": "<|reserved_special_token_154|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128160": { + "content": "<|reserved_special_token_155|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128161": { + "content": "<|reserved_special_token_156|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128162": { + "content": "<|reserved_special_token_157|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128163": { + "content": "<|reserved_special_token_158|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128164": { + "content": "<|reserved_special_token_159|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128165": { + "content": "<|reserved_special_token_160|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128166": { + "content": "<|reserved_special_token_161|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128167": { + "content": "<|reserved_special_token_162|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128168": { + "content": "<|reserved_special_token_163|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128169": { + "content": "<|reserved_special_token_164|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128170": { + "content": "<|reserved_special_token_165|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128171": { + "content": "<|reserved_special_token_166|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128172": { + "content": "<|reserved_special_token_167|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128173": { + "content": "<|reserved_special_token_168|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128174": { + "content": "<|reserved_special_token_169|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128175": { + "content": "<|reserved_special_token_170|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128176": { + "content": "<|reserved_special_token_171|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128177": { + "content": "<|reserved_special_token_172|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128178": { + "content": "<|reserved_special_token_173|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128179": { + "content": "<|reserved_special_token_174|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128180": { + "content": "<|reserved_special_token_175|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128181": { + "content": "<|reserved_special_token_176|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128182": { + "content": "<|reserved_special_token_177|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128183": { + "content": "<|reserved_special_token_178|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128184": { + "content": "<|reserved_special_token_179|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128185": { + "content": "<|reserved_special_token_180|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128186": { + "content": "<|reserved_special_token_181|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128187": { + "content": "<|reserved_special_token_182|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128188": { + "content": "<|reserved_special_token_183|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128189": { + "content": "<|reserved_special_token_184|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128190": { + "content": "<|reserved_special_token_185|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128191": { + "content": "<|reserved_special_token_186|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128192": { + "content": "<|reserved_special_token_187|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128193": { + "content": "<|reserved_special_token_188|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128194": { + "content": "<|reserved_special_token_189|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128195": { + "content": "<|reserved_special_token_190|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128196": { + "content": "<|reserved_special_token_191|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128197": { + "content": "<|reserved_special_token_192|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128198": { + "content": "<|reserved_special_token_193|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128199": { + "content": "<|reserved_special_token_194|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128200": { + "content": "<|reserved_special_token_195|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128201": { + "content": "<|reserved_special_token_196|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128202": { + "content": "<|reserved_special_token_197|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128203": { + "content": "<|reserved_special_token_198|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128204": { + "content": "<|reserved_special_token_199|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128205": { + "content": "<|reserved_special_token_200|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128206": { + "content": "<|reserved_special_token_201|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128207": { + "content": "<|reserved_special_token_202|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128208": { + "content": "<|reserved_special_token_203|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128209": { + "content": "<|reserved_special_token_204|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128210": { + "content": "<|reserved_special_token_205|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128211": { + "content": "<|reserved_special_token_206|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128212": { + "content": "<|reserved_special_token_207|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128213": { + "content": "<|reserved_special_token_208|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128214": { + "content": "<|reserved_special_token_209|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128215": { + "content": "<|reserved_special_token_210|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128216": { + "content": "<|reserved_special_token_211|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128217": { + "content": "<|reserved_special_token_212|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128218": { + "content": "<|reserved_special_token_213|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128219": { + "content": "<|reserved_special_token_214|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128220": { + "content": "<|reserved_special_token_215|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128221": { + "content": "<|reserved_special_token_216|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128222": { + "content": "<|reserved_special_token_217|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128223": { + "content": "<|reserved_special_token_218|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128224": { + "content": "<|reserved_special_token_219|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128225": { + "content": "<|reserved_special_token_220|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128226": { + "content": "<|reserved_special_token_221|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128227": { + "content": "<|reserved_special_token_222|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128228": { + "content": "<|reserved_special_token_223|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128229": { + "content": "<|reserved_special_token_224|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128230": { + "content": "<|reserved_special_token_225|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128231": { + "content": "<|reserved_special_token_226|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128232": { + "content": "<|reserved_special_token_227|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128233": { + "content": "<|reserved_special_token_228|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128234": { + "content": "<|reserved_special_token_229|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128235": { + "content": "<|reserved_special_token_230|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128236": { + "content": "<|reserved_special_token_231|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128237": { + "content": "<|reserved_special_token_232|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128238": { + "content": "<|reserved_special_token_233|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128239": { + "content": "<|reserved_special_token_234|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128240": { + "content": "<|reserved_special_token_235|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128241": { + "content": "<|reserved_special_token_236|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128242": { + "content": "<|reserved_special_token_237|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128243": { + "content": "<|reserved_special_token_238|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128244": { + "content": "<|reserved_special_token_239|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128245": { + "content": "<|reserved_special_token_240|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128246": { + "content": "<|reserved_special_token_241|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128247": { + "content": "<|reserved_special_token_242|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128248": { + "content": "<|reserved_special_token_243|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128249": { + "content": "<|reserved_special_token_244|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128250": { + "content": "<|reserved_special_token_245|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128251": { + "content": "<|reserved_special_token_246|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128252": { + "content": "<|reserved_special_token_247|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128253": { + "content": "<|reserved_special_token_248|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128254": { + "content": "<|reserved_special_token_249|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128255": { + "content": "<|reserved_special_token_250|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "<|begin_of_text|>", + "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}", + "clean_up_tokenization_spaces": true, + "eos_token": "<|eot_id|>", + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 1000000000000000019884624838656, + "pad_token": "<|eot_id|>", + "padding_side": "right", + "split_special_tokens": false, + "tokenizer_class": "PreTrainedTokenizerFast" +} diff --git a/rag_truth_hal_detection_model/train_results.json b/rag_truth_hal_detection_model/train_results.json new file mode 100644 index 0000000000000000000000000000000000000000..685d6db0c045936cb9613c32540ca67f045ff161 --- /dev/null +++ b/rag_truth_hal_detection_model/train_results.json @@ -0,0 +1,8 @@ +{ + "epoch": 2.9976146302676914, + "total_flos": 1.9412022010031636e+18, + "train_loss": 0.22161940554313767, + "train_runtime": 29847.081, + "train_samples_per_second": 1.517, + "train_steps_per_second": 0.047 +} \ No newline at end of file diff --git a/rag_truth_hal_detection_model/trainer_log.jsonl b/rag_truth_hal_detection_model/trainer_log.jsonl new file mode 100644 index 0000000000000000000000000000000000000000..80e06b368ea8406f8c714ac183ece06e922a17c9 --- /dev/null +++ b/rag_truth_hal_detection_model/trainer_log.jsonl @@ -0,0 +1,1414 @@ +{"current_steps": 1, "total_steps": 1413, "loss": 1.2577, "lr": 5.000000000000001e-07, "epoch": 0.0021203286509408957, "percentage": 0.07, "elapsed_time": "0:00:29", "remaining_time": "11:31:57"} +{"current_steps": 2, "total_steps": 1413, "loss": 1.1764, "lr": 1.0000000000000002e-06, "epoch": 0.004240657301881791, "percentage": 0.14, "elapsed_time": "0:00:49", "remaining_time": "9:44:04"} +{"current_steps": 3, "total_steps": 1413, "loss": 1.1581, "lr": 1.5e-06, "epoch": 0.0063609859528226875, "percentage": 0.21, "elapsed_time": "0:01:10", "remaining_time": "9:12:47"} +{"current_steps": 4, "total_steps": 1413, "loss": 0.9151, "lr": 2.0000000000000003e-06, "epoch": 0.008481314603763583, "percentage": 0.28, "elapsed_time": "0:01:31", "remaining_time": "8:57:30"} +{"current_steps": 5, "total_steps": 1413, "loss": 0.5946, "lr": 2.5e-06, "epoch": 0.010601643254704479, "percentage": 0.35, "elapsed_time": "0:01:53", "remaining_time": "8:50:29"} +{"current_steps": 6, "total_steps": 1413, "loss": 0.514, "lr": 3e-06, "epoch": 0.012721971905645375, "percentage": 0.42, "elapsed_time": "0:02:13", "remaining_time": "8:41:35"} +{"current_steps": 7, "total_steps": 1413, "loss": 0.3226, "lr": 3.5e-06, "epoch": 0.014842300556586271, "percentage": 0.5, "elapsed_time": "0:02:35", "remaining_time": "8:41:31"} +{"current_steps": 8, "total_steps": 1413, "loss": 0.3853, "lr": 4.000000000000001e-06, "epoch": 0.016962629207527165, "percentage": 0.57, "elapsed_time": "0:02:56", "remaining_time": "8:36:58"} +{"current_steps": 9, "total_steps": 1413, "loss": 0.2983, "lr": 4.5e-06, "epoch": 0.01908295785846806, "percentage": 0.64, "elapsed_time": "0:03:17", "remaining_time": "8:34:07"} +{"current_steps": 10, "total_steps": 1413, "loss": 0.4318, "lr": 5e-06, "epoch": 0.021203286509408958, "percentage": 0.71, "elapsed_time": "0:03:39", "remaining_time": "8:32:18"} +{"current_steps": 11, "total_steps": 1413, "loss": 0.4925, "lr": 4.9999937325015554e-06, "epoch": 0.023323615160349854, "percentage": 0.78, "elapsed_time": "0:03:59", "remaining_time": "8:29:10"} +{"current_steps": 12, "total_steps": 1413, "loss": 0.4128, "lr": 4.999974930037645e-06, "epoch": 0.02544394381129075, "percentage": 0.85, "elapsed_time": "0:04:20", "remaining_time": "8:27:05"} +{"current_steps": 13, "total_steps": 1413, "loss": 0.3941, "lr": 4.999943592702547e-06, "epoch": 0.027564272462231646, "percentage": 0.92, "elapsed_time": "0:04:41", "remaining_time": "8:25:26"} +{"current_steps": 14, "total_steps": 1413, "loss": 0.527, "lr": 4.999899720653384e-06, "epoch": 0.029684601113172542, "percentage": 0.99, "elapsed_time": "0:05:02", "remaining_time": "8:24:04"} +{"current_steps": 15, "total_steps": 1413, "loss": 0.5217, "lr": 4.999843314110132e-06, "epoch": 0.031804929764113435, "percentage": 1.06, "elapsed_time": "0:05:25", "remaining_time": "8:25:31"} +{"current_steps": 16, "total_steps": 1413, "loss": 0.262, "lr": 4.999774373355613e-06, "epoch": 0.03392525841505433, "percentage": 1.13, "elapsed_time": "0:05:45", "remaining_time": "8:23:29"} +{"current_steps": 17, "total_steps": 1413, "loss": 0.5101, "lr": 4.999692898735496e-06, "epoch": 0.03604558706599523, "percentage": 1.2, "elapsed_time": "0:06:08", "remaining_time": "8:23:50"} +{"current_steps": 18, "total_steps": 1413, "loss": 0.376, "lr": 4.999598890658294e-06, "epoch": 0.03816591571693612, "percentage": 1.27, "elapsed_time": "0:06:29", "remaining_time": "8:22:49"} +{"current_steps": 19, "total_steps": 1413, "loss": 0.3747, "lr": 4.999492349595364e-06, "epoch": 0.04028624436787702, "percentage": 1.34, "elapsed_time": "0:06:49", "remaining_time": "8:21:12"} +{"current_steps": 20, "total_steps": 1413, "loss": 0.3933, "lr": 4.999373276080902e-06, "epoch": 0.042406573018817915, "percentage": 1.42, "elapsed_time": "0:07:10", "remaining_time": "8:19:35"} +{"current_steps": 21, "total_steps": 1413, "loss": 0.3696, "lr": 4.999241670711944e-06, "epoch": 0.04452690166975881, "percentage": 1.49, "elapsed_time": "0:07:34", "remaining_time": "8:21:54"} +{"current_steps": 22, "total_steps": 1413, "loss": 0.3125, "lr": 4.999097534148358e-06, "epoch": 0.04664723032069971, "percentage": 1.56, "elapsed_time": "0:07:55", "remaining_time": "8:21:03"} +{"current_steps": 23, "total_steps": 1413, "loss": 0.4218, "lr": 4.998940867112844e-06, "epoch": 0.048767558971640604, "percentage": 1.63, "elapsed_time": "0:08:16", "remaining_time": "8:19:55"} +{"current_steps": 24, "total_steps": 1413, "loss": 0.3827, "lr": 4.998771670390931e-06, "epoch": 0.0508878876225815, "percentage": 1.7, "elapsed_time": "0:08:37", "remaining_time": "8:19:13"} +{"current_steps": 25, "total_steps": 1413, "loss": 0.4637, "lr": 4.998589944830973e-06, "epoch": 0.053008216273522396, "percentage": 1.77, "elapsed_time": "0:08:58", "remaining_time": "8:18:15"} +{"current_steps": 26, "total_steps": 1413, "loss": 0.3562, "lr": 4.998395691344138e-06, "epoch": 0.05512854492446329, "percentage": 1.84, "elapsed_time": "0:09:18", "remaining_time": "8:16:39"} +{"current_steps": 27, "total_steps": 1413, "loss": 0.3842, "lr": 4.998188910904416e-06, "epoch": 0.05724887357540419, "percentage": 1.91, "elapsed_time": "0:09:40", "remaining_time": "8:16:33"} +{"current_steps": 28, "total_steps": 1413, "loss": 0.3048, "lr": 4.997969604548602e-06, "epoch": 0.059369202226345084, "percentage": 1.98, "elapsed_time": "0:10:01", "remaining_time": "8:16:09"} +{"current_steps": 29, "total_steps": 1413, "loss": 0.3621, "lr": 4.997737773376298e-06, "epoch": 0.06148953087728598, "percentage": 2.05, "elapsed_time": "0:10:23", "remaining_time": "8:16:09"} +{"current_steps": 30, "total_steps": 1413, "loss": 0.2974, "lr": 4.997493418549905e-06, "epoch": 0.06360985952822687, "percentage": 2.12, "elapsed_time": "0:10:44", "remaining_time": "8:14:52"} +{"current_steps": 31, "total_steps": 1413, "loss": 0.445, "lr": 4.99723654129462e-06, "epoch": 0.06573018817916777, "percentage": 2.19, "elapsed_time": "0:11:05", "remaining_time": "8:14:20"} +{"current_steps": 32, "total_steps": 1413, "loss": 0.3759, "lr": 4.996967142898423e-06, "epoch": 0.06785051683010866, "percentage": 2.26, "elapsed_time": "0:11:26", "remaining_time": "8:14:05"} +{"current_steps": 33, "total_steps": 1413, "loss": 0.3232, "lr": 4.996685224712077e-06, "epoch": 0.06997084548104957, "percentage": 2.34, "elapsed_time": "0:11:47", "remaining_time": "8:12:51"} +{"current_steps": 34, "total_steps": 1413, "loss": 0.4248, "lr": 4.99639078814912e-06, "epoch": 0.07209117413199045, "percentage": 2.41, "elapsed_time": "0:12:08", "remaining_time": "8:12:13"} +{"current_steps": 35, "total_steps": 1413, "loss": 0.2229, "lr": 4.996083834685858e-06, "epoch": 0.07421150278293136, "percentage": 2.48, "elapsed_time": "0:12:28", "remaining_time": "8:11:15"} +{"current_steps": 36, "total_steps": 1413, "loss": 0.316, "lr": 4.995764365861354e-06, "epoch": 0.07633183143387225, "percentage": 2.55, "elapsed_time": "0:12:49", "remaining_time": "8:10:21"} +{"current_steps": 37, "total_steps": 1413, "loss": 0.3061, "lr": 4.9954323832774235e-06, "epoch": 0.07845216008481315, "percentage": 2.62, "elapsed_time": "0:13:09", "remaining_time": "8:09:26"} +{"current_steps": 38, "total_steps": 1413, "loss": 0.3889, "lr": 4.995087888598629e-06, "epoch": 0.08057248873575404, "percentage": 2.69, "elapsed_time": "0:13:30", "remaining_time": "8:08:58"} +{"current_steps": 39, "total_steps": 1413, "loss": 0.3944, "lr": 4.994730883552263e-06, "epoch": 0.08269281738669494, "percentage": 2.76, "elapsed_time": "0:13:51", "remaining_time": "8:08:22"} +{"current_steps": 40, "total_steps": 1413, "loss": 0.5437, "lr": 4.994361369928352e-06, "epoch": 0.08481314603763583, "percentage": 2.83, "elapsed_time": "0:14:12", "remaining_time": "8:07:30"} +{"current_steps": 41, "total_steps": 1413, "loss": 0.357, "lr": 4.993979349579635e-06, "epoch": 0.08693347468857673, "percentage": 2.9, "elapsed_time": "0:14:33", "remaining_time": "8:06:55"} +{"current_steps": 42, "total_steps": 1413, "loss": 0.3081, "lr": 4.9935848244215615e-06, "epoch": 0.08905380333951762, "percentage": 2.97, "elapsed_time": "0:14:53", "remaining_time": "8:06:00"} +{"current_steps": 43, "total_steps": 1413, "loss": 0.3468, "lr": 4.993177796432281e-06, "epoch": 0.09117413199045853, "percentage": 3.04, "elapsed_time": "0:15:14", "remaining_time": "8:05:47"} +{"current_steps": 44, "total_steps": 1413, "loss": 0.3266, "lr": 4.99275826765263e-06, "epoch": 0.09329446064139942, "percentage": 3.11, "elapsed_time": "0:15:35", "remaining_time": "8:05:20"} +{"current_steps": 45, "total_steps": 1413, "loss": 0.3799, "lr": 4.992326240186127e-06, "epoch": 0.09541478929234032, "percentage": 3.18, "elapsed_time": "0:15:57", "remaining_time": "8:04:57"} +{"current_steps": 46, "total_steps": 1413, "loss": 0.3149, "lr": 4.991881716198955e-06, "epoch": 0.09753511794328121, "percentage": 3.26, "elapsed_time": "0:16:19", "remaining_time": "8:05:22"} +{"current_steps": 47, "total_steps": 1413, "loss": 0.2163, "lr": 4.9914246979199586e-06, "epoch": 0.09965544659422211, "percentage": 3.33, "elapsed_time": "0:16:41", "remaining_time": "8:05:03"} +{"current_steps": 48, "total_steps": 1413, "loss": 0.4008, "lr": 4.990955187640627e-06, "epoch": 0.101775775245163, "percentage": 3.4, "elapsed_time": "0:17:02", "remaining_time": "8:04:25"} +{"current_steps": 49, "total_steps": 1413, "loss": 0.3937, "lr": 4.990473187715082e-06, "epoch": 0.1038961038961039, "percentage": 3.47, "elapsed_time": "0:17:22", "remaining_time": "8:03:40"} +{"current_steps": 50, "total_steps": 1413, "loss": 0.381, "lr": 4.989978700560073e-06, "epoch": 0.10601643254704479, "percentage": 3.54, "elapsed_time": "0:17:43", "remaining_time": "8:03:11"} +{"current_steps": 51, "total_steps": 1413, "loss": 0.2995, "lr": 4.9894717286549566e-06, "epoch": 0.10813676119798568, "percentage": 3.61, "elapsed_time": "0:18:03", "remaining_time": "8:02:16"} +{"current_steps": 52, "total_steps": 1413, "loss": 0.2401, "lr": 4.98895227454169e-06, "epoch": 0.11025708984892658, "percentage": 3.68, "elapsed_time": "0:18:24", "remaining_time": "8:01:52"} +{"current_steps": 53, "total_steps": 1413, "loss": 0.3294, "lr": 4.9884203408248145e-06, "epoch": 0.11237741849986747, "percentage": 3.75, "elapsed_time": "0:18:45", "remaining_time": "8:01:33"} +{"current_steps": 54, "total_steps": 1413, "loss": 0.4972, "lr": 4.987875930171446e-06, "epoch": 0.11449774715080838, "percentage": 3.82, "elapsed_time": "0:19:06", "remaining_time": "8:00:51"} +{"current_steps": 55, "total_steps": 1413, "loss": 0.4146, "lr": 4.987319045311259e-06, "epoch": 0.11661807580174927, "percentage": 3.89, "elapsed_time": "0:19:26", "remaining_time": "8:00:10"} +{"current_steps": 56, "total_steps": 1413, "loss": 0.3277, "lr": 4.9867496890364734e-06, "epoch": 0.11873840445269017, "percentage": 3.96, "elapsed_time": "0:19:48", "remaining_time": "7:59:59"} +{"current_steps": 57, "total_steps": 1413, "loss": 0.2963, "lr": 4.98616786420184e-06, "epoch": 0.12085873310363106, "percentage": 4.03, "elapsed_time": "0:20:09", "remaining_time": "7:59:33"} +{"current_steps": 58, "total_steps": 1413, "loss": 0.2798, "lr": 4.985573573724628e-06, "epoch": 0.12297906175457196, "percentage": 4.1, "elapsed_time": "0:20:31", "remaining_time": "7:59:25"} +{"current_steps": 59, "total_steps": 1413, "loss": 0.3764, "lr": 4.98496682058461e-06, "epoch": 0.12509939040551285, "percentage": 4.18, "elapsed_time": "0:20:52", "remaining_time": "7:58:52"} +{"current_steps": 60, "total_steps": 1413, "loss": 0.2544, "lr": 4.984347607824045e-06, "epoch": 0.12721971905645374, "percentage": 4.25, "elapsed_time": "0:21:14", "remaining_time": "7:59:10"} +{"current_steps": 61, "total_steps": 1413, "loss": 0.3421, "lr": 4.9837159385476655e-06, "epoch": 0.12934004770739466, "percentage": 4.32, "elapsed_time": "0:21:36", "remaining_time": "7:59:00"} +{"current_steps": 62, "total_steps": 1413, "loss": 0.4167, "lr": 4.983071815922659e-06, "epoch": 0.13146037635833555, "percentage": 4.39, "elapsed_time": "0:21:57", "remaining_time": "7:58:38"} +{"current_steps": 63, "total_steps": 1413, "loss": 0.1973, "lr": 4.9824152431786565e-06, "epoch": 0.13358070500927643, "percentage": 4.46, "elapsed_time": "0:22:18", "remaining_time": "7:58:04"} +{"current_steps": 64, "total_steps": 1413, "loss": 0.3211, "lr": 4.981746223607713e-06, "epoch": 0.13570103366021732, "percentage": 4.53, "elapsed_time": "0:22:39", "remaining_time": "7:57:28"} +{"current_steps": 65, "total_steps": 1413, "loss": 0.2813, "lr": 4.981064760564292e-06, "epoch": 0.13782136231115824, "percentage": 4.6, "elapsed_time": "0:22:59", "remaining_time": "7:56:48"} +{"current_steps": 66, "total_steps": 1413, "loss": 0.2489, "lr": 4.9803708574652475e-06, "epoch": 0.13994169096209913, "percentage": 4.67, "elapsed_time": "0:23:20", "remaining_time": "7:56:19"} +{"current_steps": 67, "total_steps": 1413, "loss": 0.3817, "lr": 4.979664517789811e-06, "epoch": 0.14206201961304002, "percentage": 4.74, "elapsed_time": "0:23:41", "remaining_time": "7:55:59"} +{"current_steps": 68, "total_steps": 1413, "loss": 0.2673, "lr": 4.978945745079565e-06, "epoch": 0.1441823482639809, "percentage": 4.81, "elapsed_time": "0:24:01", "remaining_time": "7:55:18"} +{"current_steps": 69, "total_steps": 1413, "loss": 0.2844, "lr": 4.978214542938438e-06, "epoch": 0.14630267691492183, "percentage": 4.88, "elapsed_time": "0:24:22", "remaining_time": "7:54:51"} +{"current_steps": 70, "total_steps": 1413, "loss": 0.2262, "lr": 4.977470915032676e-06, "epoch": 0.14842300556586271, "percentage": 4.95, "elapsed_time": "0:24:42", "remaining_time": "7:54:10"} +{"current_steps": 71, "total_steps": 1413, "loss": 0.265, "lr": 4.976714865090827e-06, "epoch": 0.1505433342168036, "percentage": 5.02, "elapsed_time": "0:25:02", "remaining_time": "7:53:24"} +{"current_steps": 72, "total_steps": 1413, "loss": 0.3004, "lr": 4.975946396903727e-06, "epoch": 0.1526636628677445, "percentage": 5.1, "elapsed_time": "0:25:23", "remaining_time": "7:52:59"} +{"current_steps": 73, "total_steps": 1413, "loss": 0.3076, "lr": 4.9751655143244715e-06, "epoch": 0.1547839915186854, "percentage": 5.17, "elapsed_time": "0:25:44", "remaining_time": "7:52:34"} +{"current_steps": 74, "total_steps": 1413, "loss": 0.237, "lr": 4.974372221268408e-06, "epoch": 0.1569043201696263, "percentage": 5.24, "elapsed_time": "0:26:05", "remaining_time": "7:51:59"} +{"current_steps": 75, "total_steps": 1413, "loss": 0.3886, "lr": 4.973566521713104e-06, "epoch": 0.1590246488205672, "percentage": 5.31, "elapsed_time": "0:26:26", "remaining_time": "7:51:38"} +{"current_steps": 76, "total_steps": 1413, "loss": 0.4216, "lr": 4.972748419698337e-06, "epoch": 0.16114497747150808, "percentage": 5.38, "elapsed_time": "0:26:46", "remaining_time": "7:51:06"} +{"current_steps": 77, "total_steps": 1413, "loss": 0.2869, "lr": 4.971917919326071e-06, "epoch": 0.16326530612244897, "percentage": 5.45, "elapsed_time": "0:27:07", "remaining_time": "7:50:36"} +{"current_steps": 78, "total_steps": 1413, "loss": 0.2688, "lr": 4.971075024760432e-06, "epoch": 0.16538563477338988, "percentage": 5.52, "elapsed_time": "0:27:29", "remaining_time": "7:50:38"} +{"current_steps": 79, "total_steps": 1413, "loss": 0.3894, "lr": 4.970219740227693e-06, "epoch": 0.16750596342433077, "percentage": 5.59, "elapsed_time": "0:27:50", "remaining_time": "7:50:16"} +{"current_steps": 80, "total_steps": 1413, "loss": 0.3129, "lr": 4.96935207001625e-06, "epoch": 0.16962629207527166, "percentage": 5.66, "elapsed_time": "0:28:12", "remaining_time": "7:49:53"} +{"current_steps": 81, "total_steps": 1413, "loss": 0.322, "lr": 4.968472018476599e-06, "epoch": 0.17174662072621255, "percentage": 5.73, "elapsed_time": "0:28:32", "remaining_time": "7:49:24"} +{"current_steps": 82, "total_steps": 1413, "loss": 0.3069, "lr": 4.967579590021319e-06, "epoch": 0.17386694937715347, "percentage": 5.8, "elapsed_time": "0:28:53", "remaining_time": "7:48:51"} +{"current_steps": 83, "total_steps": 1413, "loss": 0.3893, "lr": 4.966674789125044e-06, "epoch": 0.17598727802809436, "percentage": 5.87, "elapsed_time": "0:29:16", "remaining_time": "7:49:00"} +{"current_steps": 84, "total_steps": 1413, "loss": 0.3198, "lr": 4.965757620324445e-06, "epoch": 0.17810760667903525, "percentage": 5.94, "elapsed_time": "0:29:36", "remaining_time": "7:48:23"} +{"current_steps": 85, "total_steps": 1413, "loss": 0.3547, "lr": 4.9648280882182056e-06, "epoch": 0.18022793532997614, "percentage": 6.02, "elapsed_time": "0:29:56", "remaining_time": "7:47:44"} +{"current_steps": 86, "total_steps": 1413, "loss": 0.2338, "lr": 4.963886197466998e-06, "epoch": 0.18234826398091705, "percentage": 6.09, "elapsed_time": "0:30:17", "remaining_time": "7:47:17"} +{"current_steps": 87, "total_steps": 1413, "loss": 0.3118, "lr": 4.962931952793461e-06, "epoch": 0.18446859263185794, "percentage": 6.16, "elapsed_time": "0:30:38", "remaining_time": "7:46:57"} +{"current_steps": 88, "total_steps": 1413, "loss": 0.2744, "lr": 4.961965358982177e-06, "epoch": 0.18658892128279883, "percentage": 6.23, "elapsed_time": "0:30:58", "remaining_time": "7:46:30"} +{"current_steps": 89, "total_steps": 1413, "loss": 0.3339, "lr": 4.960986420879645e-06, "epoch": 0.18870924993373972, "percentage": 6.3, "elapsed_time": "0:31:20", "remaining_time": "7:46:12"} +{"current_steps": 90, "total_steps": 1413, "loss": 0.2318, "lr": 4.9599951433942614e-06, "epoch": 0.19082957858468064, "percentage": 6.37, "elapsed_time": "0:31:42", "remaining_time": "7:46:01"} +{"current_steps": 91, "total_steps": 1413, "loss": 0.3198, "lr": 4.958991531496289e-06, "epoch": 0.19294990723562153, "percentage": 6.44, "elapsed_time": "0:32:03", "remaining_time": "7:45:49"} +{"current_steps": 92, "total_steps": 1413, "loss": 0.2254, "lr": 4.957975590217836e-06, "epoch": 0.19507023588656242, "percentage": 6.51, "elapsed_time": "0:32:24", "remaining_time": "7:45:27"} +{"current_steps": 93, "total_steps": 1413, "loss": 0.277, "lr": 4.956947324652832e-06, "epoch": 0.1971905645375033, "percentage": 6.58, "elapsed_time": "0:32:46", "remaining_time": "7:45:17"} +{"current_steps": 94, "total_steps": 1413, "loss": 0.3462, "lr": 4.955906739956999e-06, "epoch": 0.19931089318844422, "percentage": 6.65, "elapsed_time": "0:33:08", "remaining_time": "7:44:59"} +{"current_steps": 95, "total_steps": 1413, "loss": 0.2103, "lr": 4.954853841347827e-06, "epoch": 0.2014312218393851, "percentage": 6.72, "elapsed_time": "0:33:29", "remaining_time": "7:44:36"} +{"current_steps": 96, "total_steps": 1413, "loss": 0.246, "lr": 4.9537886341045475e-06, "epoch": 0.203551550490326, "percentage": 6.79, "elapsed_time": "0:33:50", "remaining_time": "7:44:19"} +{"current_steps": 97, "total_steps": 1413, "loss": 0.3306, "lr": 4.95271112356811e-06, "epoch": 0.2056718791412669, "percentage": 6.86, "elapsed_time": "0:34:11", "remaining_time": "7:43:55"} +{"current_steps": 98, "total_steps": 1413, "loss": 0.37, "lr": 4.951621315141149e-06, "epoch": 0.2077922077922078, "percentage": 6.94, "elapsed_time": "0:34:31", "remaining_time": "7:43:17"} +{"current_steps": 99, "total_steps": 1413, "loss": 0.3687, "lr": 4.950519214287966e-06, "epoch": 0.2099125364431487, "percentage": 7.01, "elapsed_time": "0:34:52", "remaining_time": "7:42:47"} +{"current_steps": 100, "total_steps": 1413, "loss": 0.4234, "lr": 4.9494048265344896e-06, "epoch": 0.21203286509408958, "percentage": 7.08, "elapsed_time": "0:35:13", "remaining_time": "7:42:26"} +{"current_steps": 101, "total_steps": 1413, "loss": 0.3633, "lr": 4.94827815746826e-06, "epoch": 0.21415319374503047, "percentage": 7.15, "elapsed_time": "0:35:34", "remaining_time": "7:42:05"} +{"current_steps": 102, "total_steps": 1413, "loss": 0.3335, "lr": 4.947139212738395e-06, "epoch": 0.21627352239597136, "percentage": 7.22, "elapsed_time": "0:35:55", "remaining_time": "7:41:45"} +{"current_steps": 103, "total_steps": 1413, "loss": 0.186, "lr": 4.945987998055562e-06, "epoch": 0.21839385104691228, "percentage": 7.29, "elapsed_time": "0:36:16", "remaining_time": "7:41:26"} +{"current_steps": 104, "total_steps": 1413, "loss": 0.2399, "lr": 4.944824519191949e-06, "epoch": 0.22051417969785317, "percentage": 7.36, "elapsed_time": "0:36:38", "remaining_time": "7:41:13"} +{"current_steps": 105, "total_steps": 1413, "loss": 0.2794, "lr": 4.943648781981239e-06, "epoch": 0.22263450834879406, "percentage": 7.43, "elapsed_time": "0:36:58", "remaining_time": "7:40:40"} +{"current_steps": 106, "total_steps": 1413, "loss": 0.2431, "lr": 4.942460792318575e-06, "epoch": 0.22475483699973495, "percentage": 7.5, "elapsed_time": "0:37:19", "remaining_time": "7:40:19"} +{"current_steps": 107, "total_steps": 1413, "loss": 0.258, "lr": 4.9412605561605365e-06, "epoch": 0.22687516565067586, "percentage": 7.57, "elapsed_time": "0:37:40", "remaining_time": "7:39:53"} +{"current_steps": 108, "total_steps": 1413, "loss": 0.3056, "lr": 4.940048079525108e-06, "epoch": 0.22899549430161675, "percentage": 7.64, "elapsed_time": "0:38:00", "remaining_time": "7:39:21"} +{"current_steps": 109, "total_steps": 1413, "loss": 0.3374, "lr": 4.9388233684916434e-06, "epoch": 0.23111582295255764, "percentage": 7.71, "elapsed_time": "0:38:21", "remaining_time": "7:38:56"} +{"current_steps": 110, "total_steps": 1413, "loss": 0.1877, "lr": 4.937586429200842e-06, "epoch": 0.23323615160349853, "percentage": 7.78, "elapsed_time": "0:38:43", "remaining_time": "7:38:45"} +{"current_steps": 111, "total_steps": 1413, "loss": 0.319, "lr": 4.936337267854719e-06, "epoch": 0.23535648025443945, "percentage": 7.86, "elapsed_time": "0:39:05", "remaining_time": "7:38:37"} +{"current_steps": 112, "total_steps": 1413, "loss": 0.2615, "lr": 4.935075890716565e-06, "epoch": 0.23747680890538034, "percentage": 7.93, "elapsed_time": "0:39:26", "remaining_time": "7:38:06"} +{"current_steps": 113, "total_steps": 1413, "loss": 0.2038, "lr": 4.933802304110925e-06, "epoch": 0.23959713755632123, "percentage": 8.0, "elapsed_time": "0:39:46", "remaining_time": "7:37:37"} +{"current_steps": 114, "total_steps": 1413, "loss": 0.2945, "lr": 4.932516514423559e-06, "epoch": 0.24171746620726212, "percentage": 8.07, "elapsed_time": "0:40:07", "remaining_time": "7:37:14"} +{"current_steps": 115, "total_steps": 1413, "loss": 0.2102, "lr": 4.931218528101416e-06, "epoch": 0.24383779485820303, "percentage": 8.14, "elapsed_time": "0:40:28", "remaining_time": "7:36:53"} +{"current_steps": 116, "total_steps": 1413, "loss": 0.3449, "lr": 4.929908351652598e-06, "epoch": 0.24595812350914392, "percentage": 8.21, "elapsed_time": "0:40:50", "remaining_time": "7:36:38"} +{"current_steps": 117, "total_steps": 1413, "loss": 0.3072, "lr": 4.928585991646327e-06, "epoch": 0.2480784521600848, "percentage": 8.28, "elapsed_time": "0:41:13", "remaining_time": "7:36:41"} +{"current_steps": 118, "total_steps": 1413, "loss": 0.3457, "lr": 4.927251454712915e-06, "epoch": 0.2501987808110257, "percentage": 8.35, "elapsed_time": "0:41:34", "remaining_time": "7:36:15"} +{"current_steps": 119, "total_steps": 1413, "loss": 0.3305, "lr": 4.925904747543729e-06, "epoch": 0.2523191094619666, "percentage": 8.42, "elapsed_time": "0:41:55", "remaining_time": "7:35:52"} +{"current_steps": 120, "total_steps": 1413, "loss": 0.4029, "lr": 4.924545876891157e-06, "epoch": 0.2544394381129075, "percentage": 8.49, "elapsed_time": "0:42:15", "remaining_time": "7:35:24"} +{"current_steps": 121, "total_steps": 1413, "loss": 0.3313, "lr": 4.9231748495685745e-06, "epoch": 0.2565597667638484, "percentage": 8.56, "elapsed_time": "0:42:36", "remaining_time": "7:34:57"} +{"current_steps": 122, "total_steps": 1413, "loss": 0.263, "lr": 4.921791672450311e-06, "epoch": 0.2586800954147893, "percentage": 8.63, "elapsed_time": "0:42:56", "remaining_time": "7:34:29"} +{"current_steps": 123, "total_steps": 1413, "loss": 0.4046, "lr": 4.920396352471613e-06, "epoch": 0.2608004240657302, "percentage": 8.7, "elapsed_time": "0:43:18", "remaining_time": "7:34:10"} +{"current_steps": 124, "total_steps": 1413, "loss": 0.2562, "lr": 4.918988896628617e-06, "epoch": 0.2629207527166711, "percentage": 8.78, "elapsed_time": "0:43:39", "remaining_time": "7:33:47"} +{"current_steps": 125, "total_steps": 1413, "loss": 0.2157, "lr": 4.917569311978301e-06, "epoch": 0.26504108136761195, "percentage": 8.85, "elapsed_time": "0:44:00", "remaining_time": "7:33:24"} +{"current_steps": 126, "total_steps": 1413, "loss": 0.2177, "lr": 4.916137605638463e-06, "epoch": 0.26716141001855287, "percentage": 8.92, "elapsed_time": "0:44:20", "remaining_time": "7:32:59"} +{"current_steps": 127, "total_steps": 1413, "loss": 0.2717, "lr": 4.914693784787676e-06, "epoch": 0.2692817386694938, "percentage": 8.99, "elapsed_time": "0:44:42", "remaining_time": "7:32:38"} +{"current_steps": 128, "total_steps": 1413, "loss": 0.2845, "lr": 4.913237856665256e-06, "epoch": 0.27140206732043465, "percentage": 9.06, "elapsed_time": "0:45:02", "remaining_time": "7:32:10"} +{"current_steps": 129, "total_steps": 1413, "loss": 0.2839, "lr": 4.911769828571224e-06, "epoch": 0.27352239597137556, "percentage": 9.13, "elapsed_time": "0:45:22", "remaining_time": "7:31:38"} +{"current_steps": 130, "total_steps": 1413, "loss": 0.3791, "lr": 4.910289707866273e-06, "epoch": 0.2756427246223165, "percentage": 9.2, "elapsed_time": "0:45:43", "remaining_time": "7:31:19"} +{"current_steps": 131, "total_steps": 1413, "loss": 0.3046, "lr": 4.908797501971725e-06, "epoch": 0.27776305327325734, "percentage": 9.27, "elapsed_time": "0:46:04", "remaining_time": "7:30:52"} +{"current_steps": 132, "total_steps": 1413, "loss": 0.2242, "lr": 4.907293218369499e-06, "epoch": 0.27988338192419826, "percentage": 9.34, "elapsed_time": "0:46:25", "remaining_time": "7:30:34"} +{"current_steps": 133, "total_steps": 1413, "loss": 0.2657, "lr": 4.90577686460207e-06, "epoch": 0.2820037105751391, "percentage": 9.41, "elapsed_time": "0:46:47", "remaining_time": "7:30:18"} +{"current_steps": 134, "total_steps": 1413, "loss": 0.2321, "lr": 4.904248448272435e-06, "epoch": 0.28412403922608004, "percentage": 9.48, "elapsed_time": "0:47:08", "remaining_time": "7:29:58"} +{"current_steps": 135, "total_steps": 1413, "loss": 0.2339, "lr": 4.902707977044071e-06, "epoch": 0.28624436787702096, "percentage": 9.55, "elapsed_time": "0:47:29", "remaining_time": "7:29:37"} +{"current_steps": 136, "total_steps": 1413, "loss": 0.2703, "lr": 4.9011554586409005e-06, "epoch": 0.2883646965279618, "percentage": 9.62, "elapsed_time": "0:47:51", "remaining_time": "7:29:22"} +{"current_steps": 137, "total_steps": 1413, "loss": 0.3249, "lr": 4.8995909008472465e-06, "epoch": 0.29048502517890273, "percentage": 9.7, "elapsed_time": "0:48:11", "remaining_time": "7:28:47"} +{"current_steps": 138, "total_steps": 1413, "loss": 0.229, "lr": 4.898014311507801e-06, "epoch": 0.29260535382984365, "percentage": 9.77, "elapsed_time": "0:48:32", "remaining_time": "7:28:24"} +{"current_steps": 139, "total_steps": 1413, "loss": 0.2925, "lr": 4.8964256985275805e-06, "epoch": 0.2947256824807845, "percentage": 9.84, "elapsed_time": "0:48:52", "remaining_time": "7:28:01"} +{"current_steps": 140, "total_steps": 1413, "loss": 0.2349, "lr": 4.8948250698718895e-06, "epoch": 0.29684601113172543, "percentage": 9.91, "elapsed_time": "0:49:12", "remaining_time": "7:27:27"} +{"current_steps": 141, "total_steps": 1413, "loss": 0.3615, "lr": 4.893212433566277e-06, "epoch": 0.2989663397826663, "percentage": 9.98, "elapsed_time": "0:49:34", "remaining_time": "7:27:17"} +{"current_steps": 142, "total_steps": 1413, "loss": 0.4128, "lr": 4.8915877976964995e-06, "epoch": 0.3010866684336072, "percentage": 10.05, "elapsed_time": "0:49:55", "remaining_time": "7:26:55"} +{"current_steps": 143, "total_steps": 1413, "loss": 0.2398, "lr": 4.889951170408479e-06, "epoch": 0.3032069970845481, "percentage": 10.12, "elapsed_time": "0:50:16", "remaining_time": "7:26:27"} +{"current_steps": 144, "total_steps": 1413, "loss": 0.3333, "lr": 4.888302559908265e-06, "epoch": 0.305327325735489, "percentage": 10.19, "elapsed_time": "0:50:36", "remaining_time": "7:26:01"} +{"current_steps": 145, "total_steps": 1413, "loss": 0.2091, "lr": 4.886641974461985e-06, "epoch": 0.3074476543864299, "percentage": 10.26, "elapsed_time": "0:50:59", "remaining_time": "7:25:50"} +{"current_steps": 146, "total_steps": 1413, "loss": 0.2042, "lr": 4.884969422395815e-06, "epoch": 0.3095679830373708, "percentage": 10.33, "elapsed_time": "0:51:19", "remaining_time": "7:25:22"} +{"current_steps": 147, "total_steps": 1413, "loss": 0.3742, "lr": 4.883284912095928e-06, "epoch": 0.3116883116883117, "percentage": 10.4, "elapsed_time": "0:51:40", "remaining_time": "7:25:03"} +{"current_steps": 148, "total_steps": 1413, "loss": 0.3228, "lr": 4.881588452008457e-06, "epoch": 0.3138086403392526, "percentage": 10.47, "elapsed_time": "0:52:01", "remaining_time": "7:24:38"} +{"current_steps": 149, "total_steps": 1413, "loss": 0.452, "lr": 4.87988005063945e-06, "epoch": 0.31592896899019346, "percentage": 10.54, "elapsed_time": "0:52:21", "remaining_time": "7:24:12"} +{"current_steps": 150, "total_steps": 1413, "loss": 0.3467, "lr": 4.87815971655483e-06, "epoch": 0.3180492976411344, "percentage": 10.62, "elapsed_time": "0:52:43", "remaining_time": "7:23:54"} +{"current_steps": 151, "total_steps": 1413, "loss": 0.3558, "lr": 4.876427458380349e-06, "epoch": 0.3201696262920753, "percentage": 10.69, "elapsed_time": "0:53:03", "remaining_time": "7:23:30"} +{"current_steps": 152, "total_steps": 1413, "loss": 0.2739, "lr": 4.874683284801548e-06, "epoch": 0.32228995494301615, "percentage": 10.76, "elapsed_time": "0:53:25", "remaining_time": "7:23:12"} +{"current_steps": 153, "total_steps": 1413, "loss": 0.2131, "lr": 4.872927204563712e-06, "epoch": 0.32441028359395707, "percentage": 10.83, "elapsed_time": "0:53:46", "remaining_time": "7:22:49"} +{"current_steps": 154, "total_steps": 1413, "loss": 0.329, "lr": 4.871159226471825e-06, "epoch": 0.32653061224489793, "percentage": 10.9, "elapsed_time": "0:54:07", "remaining_time": "7:22:25"} +{"current_steps": 155, "total_steps": 1413, "loss": 0.2388, "lr": 4.869379359390524e-06, "epoch": 0.32865094089583885, "percentage": 10.97, "elapsed_time": "0:54:29", "remaining_time": "7:22:13"} +{"current_steps": 156, "total_steps": 1413, "loss": 0.3476, "lr": 4.867587612244064e-06, "epoch": 0.33077126954677977, "percentage": 11.04, "elapsed_time": "0:54:50", "remaining_time": "7:21:55"} +{"current_steps": 157, "total_steps": 1413, "loss": 0.3471, "lr": 4.865783994016261e-06, "epoch": 0.33289159819772063, "percentage": 11.11, "elapsed_time": "0:55:12", "remaining_time": "7:21:36"} +{"current_steps": 158, "total_steps": 1413, "loss": 0.3026, "lr": 4.863968513750456e-06, "epoch": 0.33501192684866155, "percentage": 11.18, "elapsed_time": "0:55:32", "remaining_time": "7:21:13"} +{"current_steps": 159, "total_steps": 1413, "loss": 0.3127, "lr": 4.862141180549464e-06, "epoch": 0.33713225549960246, "percentage": 11.25, "elapsed_time": "0:55:54", "remaining_time": "7:20:54"} +{"current_steps": 160, "total_steps": 1413, "loss": 0.2059, "lr": 4.86030200357553e-06, "epoch": 0.3392525841505433, "percentage": 11.32, "elapsed_time": "0:56:15", "remaining_time": "7:20:31"} +{"current_steps": 161, "total_steps": 1413, "loss": 0.2706, "lr": 4.858450992050287e-06, "epoch": 0.34137291280148424, "percentage": 11.39, "elapsed_time": "0:56:36", "remaining_time": "7:20:12"} +{"current_steps": 162, "total_steps": 1413, "loss": 0.2539, "lr": 4.856588155254704e-06, "epoch": 0.3434932414524251, "percentage": 11.46, "elapsed_time": "0:56:57", "remaining_time": "7:19:47"} +{"current_steps": 163, "total_steps": 1413, "loss": 0.2923, "lr": 4.854713502529042e-06, "epoch": 0.345613570103366, "percentage": 11.54, "elapsed_time": "0:57:18", "remaining_time": "7:19:32"} +{"current_steps": 164, "total_steps": 1413, "loss": 0.2357, "lr": 4.852827043272808e-06, "epoch": 0.34773389875430694, "percentage": 11.61, "elapsed_time": "0:57:40", "remaining_time": "7:19:12"} +{"current_steps": 165, "total_steps": 1413, "loss": 0.2745, "lr": 4.850928786944706e-06, "epoch": 0.3498542274052478, "percentage": 11.68, "elapsed_time": "0:58:00", "remaining_time": "7:18:47"} +{"current_steps": 166, "total_steps": 1413, "loss": 0.2503, "lr": 4.84901874306259e-06, "epoch": 0.3519745560561887, "percentage": 11.75, "elapsed_time": "0:58:21", "remaining_time": "7:18:24"} +{"current_steps": 167, "total_steps": 1413, "loss": 0.3615, "lr": 4.847096921203419e-06, "epoch": 0.35409488470712963, "percentage": 11.82, "elapsed_time": "0:58:43", "remaining_time": "7:18:10"} +{"current_steps": 168, "total_steps": 1413, "loss": 0.187, "lr": 4.845163331003205e-06, "epoch": 0.3562152133580705, "percentage": 11.89, "elapsed_time": "0:59:05", "remaining_time": "7:17:54"} +{"current_steps": 169, "total_steps": 1413, "loss": 0.2641, "lr": 4.843217982156968e-06, "epoch": 0.3583355420090114, "percentage": 11.96, "elapsed_time": "0:59:26", "remaining_time": "7:17:33"} +{"current_steps": 170, "total_steps": 1413, "loss": 0.2323, "lr": 4.841260884418682e-06, "epoch": 0.36045587065995227, "percentage": 12.03, "elapsed_time": "0:59:47", "remaining_time": "7:17:07"} +{"current_steps": 171, "total_steps": 1413, "loss": 0.3339, "lr": 4.839292047601234e-06, "epoch": 0.3625761993108932, "percentage": 12.1, "elapsed_time": "1:00:09", "remaining_time": "7:16:54"} +{"current_steps": 172, "total_steps": 1413, "loss": 0.2844, "lr": 4.83731148157637e-06, "epoch": 0.3646965279618341, "percentage": 12.17, "elapsed_time": "1:00:30", "remaining_time": "7:16:31"} +{"current_steps": 173, "total_steps": 1413, "loss": 0.3137, "lr": 4.835319196274646e-06, "epoch": 0.36681685661277497, "percentage": 12.24, "elapsed_time": "1:00:50", "remaining_time": "7:16:05"} +{"current_steps": 174, "total_steps": 1413, "loss": 0.2336, "lr": 4.833315201685375e-06, "epoch": 0.3689371852637159, "percentage": 12.31, "elapsed_time": "1:01:10", "remaining_time": "7:15:37"} +{"current_steps": 175, "total_steps": 1413, "loss": 0.2312, "lr": 4.831299507856587e-06, "epoch": 0.37105751391465674, "percentage": 12.38, "elapsed_time": "1:01:31", "remaining_time": "7:15:16"} +{"current_steps": 176, "total_steps": 1413, "loss": 0.3141, "lr": 4.829272124894967e-06, "epoch": 0.37317784256559766, "percentage": 12.46, "elapsed_time": "1:01:53", "remaining_time": "7:14:57"} +{"current_steps": 177, "total_steps": 1413, "loss": 0.259, "lr": 4.827233062965811e-06, "epoch": 0.3752981712165386, "percentage": 12.53, "elapsed_time": "1:02:14", "remaining_time": "7:14:36"} +{"current_steps": 178, "total_steps": 1413, "loss": 0.23, "lr": 4.82518233229297e-06, "epoch": 0.37741849986747944, "percentage": 12.6, "elapsed_time": "1:02:36", "remaining_time": "7:14:20"} +{"current_steps": 179, "total_steps": 1413, "loss": 0.2643, "lr": 4.823119943158809e-06, "epoch": 0.37953882851842036, "percentage": 12.67, "elapsed_time": "1:02:57", "remaining_time": "7:14:03"} +{"current_steps": 180, "total_steps": 1413, "loss": 0.2215, "lr": 4.821045905904143e-06, "epoch": 0.3816591571693613, "percentage": 12.74, "elapsed_time": "1:03:18", "remaining_time": "7:13:40"} +{"current_steps": 181, "total_steps": 1413, "loss": 0.2168, "lr": 4.818960230928192e-06, "epoch": 0.38377948582030214, "percentage": 12.81, "elapsed_time": "1:03:39", "remaining_time": "7:13:18"} +{"current_steps": 182, "total_steps": 1413, "loss": 0.2618, "lr": 4.816862928688528e-06, "epoch": 0.38589981447124305, "percentage": 12.88, "elapsed_time": "1:04:00", "remaining_time": "7:12:57"} +{"current_steps": 183, "total_steps": 1413, "loss": 0.3713, "lr": 4.814754009701023e-06, "epoch": 0.3880201431221839, "percentage": 12.95, "elapsed_time": "1:04:22", "remaining_time": "7:12:38"} +{"current_steps": 184, "total_steps": 1413, "loss": 0.3274, "lr": 4.8126334845397914e-06, "epoch": 0.39014047177312483, "percentage": 13.02, "elapsed_time": "1:04:43", "remaining_time": "7:12:17"} +{"current_steps": 185, "total_steps": 1413, "loss": 0.231, "lr": 4.8105013638371454e-06, "epoch": 0.39226080042406575, "percentage": 13.09, "elapsed_time": "1:05:02", "remaining_time": "7:11:47"} +{"current_steps": 186, "total_steps": 1413, "loss": 0.3412, "lr": 4.8083576582835366e-06, "epoch": 0.3943811290750066, "percentage": 13.16, "elapsed_time": "1:05:24", "remaining_time": "7:11:28"} +{"current_steps": 187, "total_steps": 1413, "loss": 0.247, "lr": 4.8062023786274996e-06, "epoch": 0.3965014577259475, "percentage": 13.23, "elapsed_time": "1:05:45", "remaining_time": "7:11:06"} +{"current_steps": 188, "total_steps": 1413, "loss": 0.2412, "lr": 4.804035535675606e-06, "epoch": 0.39862178637688844, "percentage": 13.31, "elapsed_time": "1:06:05", "remaining_time": "7:10:39"} +{"current_steps": 189, "total_steps": 1413, "loss": 0.2943, "lr": 4.801857140292402e-06, "epoch": 0.4007421150278293, "percentage": 13.38, "elapsed_time": "1:06:27", "remaining_time": "7:10:22"} +{"current_steps": 190, "total_steps": 1413, "loss": 0.274, "lr": 4.799667203400361e-06, "epoch": 0.4028624436787702, "percentage": 13.45, "elapsed_time": "1:06:47", "remaining_time": "7:09:55"} +{"current_steps": 191, "total_steps": 1413, "loss": 0.245, "lr": 4.7974657359798224e-06, "epoch": 0.4049827723297111, "percentage": 13.52, "elapsed_time": "1:07:07", "remaining_time": "7:09:27"} +{"current_steps": 192, "total_steps": 1413, "loss": 0.3203, "lr": 4.795252749068942e-06, "epoch": 0.407103100980652, "percentage": 13.59, "elapsed_time": "1:07:28", "remaining_time": "7:09:07"} +{"current_steps": 193, "total_steps": 1413, "loss": 0.3274, "lr": 4.793028253763633e-06, "epoch": 0.4092234296315929, "percentage": 13.66, "elapsed_time": "1:07:49", "remaining_time": "7:08:46"} +{"current_steps": 194, "total_steps": 1413, "loss": 0.3502, "lr": 4.790792261217513e-06, "epoch": 0.4113437582825338, "percentage": 13.73, "elapsed_time": "1:08:10", "remaining_time": "7:08:24"} +{"current_steps": 195, "total_steps": 1413, "loss": 0.4093, "lr": 4.7885447826418435e-06, "epoch": 0.4134640869334747, "percentage": 13.8, "elapsed_time": "1:08:32", "remaining_time": "7:08:05"} +{"current_steps": 196, "total_steps": 1413, "loss": 0.3394, "lr": 4.786285829305481e-06, "epoch": 0.4155844155844156, "percentage": 13.87, "elapsed_time": "1:08:52", "remaining_time": "7:07:40"} +{"current_steps": 197, "total_steps": 1413, "loss": 0.2579, "lr": 4.784015412534816e-06, "epoch": 0.4177047442353565, "percentage": 13.94, "elapsed_time": "1:09:13", "remaining_time": "7:07:20"} +{"current_steps": 198, "total_steps": 1413, "loss": 0.3256, "lr": 4.781733543713714e-06, "epoch": 0.4198250728862974, "percentage": 14.01, "elapsed_time": "1:09:34", "remaining_time": "7:06:58"} +{"current_steps": 199, "total_steps": 1413, "loss": 0.2552, "lr": 4.779440234283461e-06, "epoch": 0.42194540153723825, "percentage": 14.08, "elapsed_time": "1:09:55", "remaining_time": "7:06:36"} +{"current_steps": 200, "total_steps": 1413, "loss": 0.345, "lr": 4.77713549574271e-06, "epoch": 0.42406573018817917, "percentage": 14.15, "elapsed_time": "1:10:16", "remaining_time": "7:06:14"} +{"current_steps": 201, "total_steps": 1413, "loss": 0.3555, "lr": 4.774819339647415e-06, "epoch": 0.4261860588391201, "percentage": 14.23, "elapsed_time": "1:10:38", "remaining_time": "7:05:58"} +{"current_steps": 202, "total_steps": 1413, "loss": 0.3845, "lr": 4.772491777610782e-06, "epoch": 0.42830638749006095, "percentage": 14.3, "elapsed_time": "1:10:59", "remaining_time": "7:05:38"} +{"current_steps": 203, "total_steps": 1413, "loss": 0.226, "lr": 4.770152821303203e-06, "epoch": 0.43042671614100186, "percentage": 14.37, "elapsed_time": "1:11:21", "remaining_time": "7:05:19"} +{"current_steps": 204, "total_steps": 1413, "loss": 0.2998, "lr": 4.767802482452202e-06, "epoch": 0.4325470447919427, "percentage": 14.44, "elapsed_time": "1:11:42", "remaining_time": "7:05:00"} +{"current_steps": 205, "total_steps": 1413, "loss": 0.2627, "lr": 4.7654407728423745e-06, "epoch": 0.43466737344288364, "percentage": 14.51, "elapsed_time": "1:12:03", "remaining_time": "7:04:38"} +{"current_steps": 206, "total_steps": 1413, "loss": 0.3959, "lr": 4.763067704315331e-06, "epoch": 0.43678770209382456, "percentage": 14.58, "elapsed_time": "1:12:24", "remaining_time": "7:04:13"} +{"current_steps": 207, "total_steps": 1413, "loss": 0.3076, "lr": 4.760683288769634e-06, "epoch": 0.4389080307447654, "percentage": 14.65, "elapsed_time": "1:12:44", "remaining_time": "7:03:48"} +{"current_steps": 208, "total_steps": 1413, "loss": 0.2894, "lr": 4.758287538160738e-06, "epoch": 0.44102835939570634, "percentage": 14.72, "elapsed_time": "1:13:06", "remaining_time": "7:03:30"} +{"current_steps": 209, "total_steps": 1413, "loss": 0.289, "lr": 4.755880464500936e-06, "epoch": 0.44314868804664725, "percentage": 14.79, "elapsed_time": "1:13:26", "remaining_time": "7:03:04"} +{"current_steps": 210, "total_steps": 1413, "loss": 0.2759, "lr": 4.753462079859291e-06, "epoch": 0.4452690166975881, "percentage": 14.86, "elapsed_time": "1:13:47", "remaining_time": "7:02:46"} +{"current_steps": 211, "total_steps": 1413, "loss": 0.2892, "lr": 4.7510323963615815e-06, "epoch": 0.44738934534852903, "percentage": 14.93, "elapsed_time": "1:14:08", "remaining_time": "7:02:21"} +{"current_steps": 212, "total_steps": 1413, "loss": 0.2232, "lr": 4.748591426190237e-06, "epoch": 0.4495096739994699, "percentage": 15.0, "elapsed_time": "1:14:29", "remaining_time": "7:02:02"} +{"current_steps": 213, "total_steps": 1413, "loss": 0.2904, "lr": 4.746139181584278e-06, "epoch": 0.4516300026504108, "percentage": 15.07, "elapsed_time": "1:14:51", "remaining_time": "7:01:41"} +{"current_steps": 214, "total_steps": 1413, "loss": 0.3108, "lr": 4.743675674839258e-06, "epoch": 0.45375033130135173, "percentage": 15.15, "elapsed_time": "1:15:12", "remaining_time": "7:01:22"} +{"current_steps": 215, "total_steps": 1413, "loss": 0.3254, "lr": 4.741200918307194e-06, "epoch": 0.4558706599522926, "percentage": 15.22, "elapsed_time": "1:15:33", "remaining_time": "7:01:00"} +{"current_steps": 216, "total_steps": 1413, "loss": 0.3318, "lr": 4.738714924396514e-06, "epoch": 0.4579909886032335, "percentage": 15.29, "elapsed_time": "1:15:54", "remaining_time": "7:00:37"} +{"current_steps": 217, "total_steps": 1413, "loss": 0.2817, "lr": 4.736217705571989e-06, "epoch": 0.4601113172541744, "percentage": 15.36, "elapsed_time": "1:16:15", "remaining_time": "7:00:17"} +{"current_steps": 218, "total_steps": 1413, "loss": 0.3168, "lr": 4.73370927435467e-06, "epoch": 0.4622316459051153, "percentage": 15.43, "elapsed_time": "1:16:36", "remaining_time": "6:59:54"} +{"current_steps": 219, "total_steps": 1413, "loss": 0.263, "lr": 4.731189643321829e-06, "epoch": 0.4643519745560562, "percentage": 15.5, "elapsed_time": "1:16:58", "remaining_time": "6:59:37"} +{"current_steps": 220, "total_steps": 1413, "loss": 0.237, "lr": 4.728658825106891e-06, "epoch": 0.46647230320699706, "percentage": 15.57, "elapsed_time": "1:17:18", "remaining_time": "6:59:14"} +{"current_steps": 221, "total_steps": 1413, "loss": 0.1574, "lr": 4.726116832399376e-06, "epoch": 0.468592631857938, "percentage": 15.64, "elapsed_time": "1:17:40", "remaining_time": "6:58:59"} +{"current_steps": 222, "total_steps": 1413, "loss": 0.287, "lr": 4.723563677944833e-06, "epoch": 0.4707129605088789, "percentage": 15.71, "elapsed_time": "1:18:01", "remaining_time": "6:58:35"} +{"current_steps": 223, "total_steps": 1413, "loss": 0.2368, "lr": 4.720999374544776e-06, "epoch": 0.47283328915981976, "percentage": 15.78, "elapsed_time": "1:18:22", "remaining_time": "6:58:16"} +{"current_steps": 224, "total_steps": 1413, "loss": 0.3074, "lr": 4.718423935056617e-06, "epoch": 0.4749536178107607, "percentage": 15.85, "elapsed_time": "1:18:44", "remaining_time": "6:58:00"} +{"current_steps": 225, "total_steps": 1413, "loss": 0.2073, "lr": 4.715837372393607e-06, "epoch": 0.47707394646170154, "percentage": 15.92, "elapsed_time": "1:19:05", "remaining_time": "6:57:36"} +{"current_steps": 226, "total_steps": 1413, "loss": 0.2204, "lr": 4.71323969952477e-06, "epoch": 0.47919427511264245, "percentage": 15.99, "elapsed_time": "1:19:26", "remaining_time": "6:57:12"} +{"current_steps": 227, "total_steps": 1413, "loss": 0.378, "lr": 4.7106309294748315e-06, "epoch": 0.48131460376358337, "percentage": 16.07, "elapsed_time": "1:19:47", "remaining_time": "6:56:52"} +{"current_steps": 228, "total_steps": 1413, "loss": 0.2746, "lr": 4.708011075324163e-06, "epoch": 0.48343493241452423, "percentage": 16.14, "elapsed_time": "1:20:07", "remaining_time": "6:56:25"} +{"current_steps": 229, "total_steps": 1413, "loss": 0.3171, "lr": 4.70538015020871e-06, "epoch": 0.48555526106546515, "percentage": 16.21, "elapsed_time": "1:20:28", "remaining_time": "6:56:07"} +{"current_steps": 230, "total_steps": 1413, "loss": 0.3478, "lr": 4.702738167319927e-06, "epoch": 0.48767558971640607, "percentage": 16.28, "elapsed_time": "1:20:49", "remaining_time": "6:55:43"} +{"current_steps": 231, "total_steps": 1413, "loss": 0.1753, "lr": 4.700085139904714e-06, "epoch": 0.4897959183673469, "percentage": 16.35, "elapsed_time": "1:21:09", "remaining_time": "6:55:14"} +{"current_steps": 232, "total_steps": 1413, "loss": 0.2202, "lr": 4.697421081265346e-06, "epoch": 0.49191624701828784, "percentage": 16.42, "elapsed_time": "1:21:31", "remaining_time": "6:55:01"} +{"current_steps": 233, "total_steps": 1413, "loss": 0.2557, "lr": 4.6947460047594105e-06, "epoch": 0.4940365756692287, "percentage": 16.49, "elapsed_time": "1:21:51", "remaining_time": "6:54:35"} +{"current_steps": 234, "total_steps": 1413, "loss": 0.3656, "lr": 4.692059923799736e-06, "epoch": 0.4961569043201696, "percentage": 16.56, "elapsed_time": "1:22:12", "remaining_time": "6:54:13"} +{"current_steps": 235, "total_steps": 1413, "loss": 0.3637, "lr": 4.689362851854333e-06, "epoch": 0.49827723297111054, "percentage": 16.63, "elapsed_time": "1:22:33", "remaining_time": "6:53:50"} +{"current_steps": 236, "total_steps": 1413, "loss": 0.2433, "lr": 4.686654802446313e-06, "epoch": 0.5003975616220514, "percentage": 16.7, "elapsed_time": "1:22:54", "remaining_time": "6:53:27"} +{"current_steps": 237, "total_steps": 1413, "loss": 0.3574, "lr": 4.683935789153834e-06, "epoch": 0.5025178902729923, "percentage": 16.77, "elapsed_time": "1:23:15", "remaining_time": "6:53:07"} +{"current_steps": 238, "total_steps": 1413, "loss": 0.3007, "lr": 4.681205825610025e-06, "epoch": 0.5046382189239332, "percentage": 16.84, "elapsed_time": "1:23:36", "remaining_time": "6:52:47"} +{"current_steps": 239, "total_steps": 1413, "loss": 0.2679, "lr": 4.67846492550292e-06, "epoch": 0.5067585475748742, "percentage": 16.91, "elapsed_time": "1:23:57", "remaining_time": "6:52:23"} +{"current_steps": 240, "total_steps": 1413, "loss": 0.423, "lr": 4.675713102575389e-06, "epoch": 0.508878876225815, "percentage": 16.99, "elapsed_time": "1:24:17", "remaining_time": "6:51:58"} +{"current_steps": 241, "total_steps": 1413, "loss": 0.2192, "lr": 4.672950370625067e-06, "epoch": 0.5109992048767559, "percentage": 17.06, "elapsed_time": "1:24:37", "remaining_time": "6:51:32"} +{"current_steps": 242, "total_steps": 1413, "loss": 0.3557, "lr": 4.670176743504291e-06, "epoch": 0.5131195335276968, "percentage": 17.13, "elapsed_time": "1:24:58", "remaining_time": "6:51:08"} +{"current_steps": 243, "total_steps": 1413, "loss": 0.2169, "lr": 4.667392235120023e-06, "epoch": 0.5152398621786377, "percentage": 17.2, "elapsed_time": "1:25:19", "remaining_time": "6:50:48"} +{"current_steps": 244, "total_steps": 1413, "loss": 0.2279, "lr": 4.664596859433784e-06, "epoch": 0.5173601908295786, "percentage": 17.27, "elapsed_time": "1:25:40", "remaining_time": "6:50:27"} +{"current_steps": 245, "total_steps": 1413, "loss": 0.235, "lr": 4.661790630461585e-06, "epoch": 0.5194805194805194, "percentage": 17.34, "elapsed_time": "1:26:01", "remaining_time": "6:50:08"} +{"current_steps": 246, "total_steps": 1413, "loss": 0.2745, "lr": 4.658973562273853e-06, "epoch": 0.5216008481314603, "percentage": 17.41, "elapsed_time": "1:26:22", "remaining_time": "6:49:44"} +{"current_steps": 247, "total_steps": 1413, "loss": 0.2579, "lr": 4.6561456689953665e-06, "epoch": 0.5237211767824013, "percentage": 17.48, "elapsed_time": "1:26:43", "remaining_time": "6:49:22"} +{"current_steps": 248, "total_steps": 1413, "loss": 0.3445, "lr": 4.653306964805178e-06, "epoch": 0.5258415054333422, "percentage": 17.55, "elapsed_time": "1:27:04", "remaining_time": "6:49:01"} +{"current_steps": 249, "total_steps": 1413, "loss": 0.2752, "lr": 4.650457463936547e-06, "epoch": 0.5279618340842831, "percentage": 17.62, "elapsed_time": "1:27:26", "remaining_time": "6:48:46"} +{"current_steps": 250, "total_steps": 1413, "loss": 0.2539, "lr": 4.647597180676866e-06, "epoch": 0.5300821627352239, "percentage": 17.69, "elapsed_time": "1:27:46", "remaining_time": "6:48:20"} +{"current_steps": 251, "total_steps": 1413, "loss": 0.2548, "lr": 4.644726129367594e-06, "epoch": 0.5322024913861648, "percentage": 17.76, "elapsed_time": "1:28:07", "remaining_time": "6:47:59"} +{"current_steps": 252, "total_steps": 1413, "loss": 0.2473, "lr": 4.6418443244041775e-06, "epoch": 0.5343228200371057, "percentage": 17.83, "elapsed_time": "1:28:28", "remaining_time": "6:47:37"} +{"current_steps": 253, "total_steps": 1413, "loss": 0.2633, "lr": 4.638951780235982e-06, "epoch": 0.5364431486880467, "percentage": 17.91, "elapsed_time": "1:28:48", "remaining_time": "6:47:13"} +{"current_steps": 254, "total_steps": 1413, "loss": 0.2015, "lr": 4.636048511366222e-06, "epoch": 0.5385634773389876, "percentage": 17.98, "elapsed_time": "1:29:09", "remaining_time": "6:46:51"} +{"current_steps": 255, "total_steps": 1413, "loss": 0.242, "lr": 4.633134532351883e-06, "epoch": 0.5406838059899285, "percentage": 18.05, "elapsed_time": "1:29:30", "remaining_time": "6:46:28"} +{"current_steps": 256, "total_steps": 1413, "loss": 0.1624, "lr": 4.630209857803653e-06, "epoch": 0.5428041346408693, "percentage": 18.12, "elapsed_time": "1:29:51", "remaining_time": "6:46:07"} +{"current_steps": 257, "total_steps": 1413, "loss": 0.266, "lr": 4.6272745023858445e-06, "epoch": 0.5449244632918102, "percentage": 18.19, "elapsed_time": "1:30:13", "remaining_time": "6:45:51"} +{"current_steps": 258, "total_steps": 1413, "loss": 0.2686, "lr": 4.624328480816329e-06, "epoch": 0.5470447919427511, "percentage": 18.26, "elapsed_time": "1:30:34", "remaining_time": "6:45:28"} +{"current_steps": 259, "total_steps": 1413, "loss": 0.2292, "lr": 4.621371807866452e-06, "epoch": 0.549165120593692, "percentage": 18.33, "elapsed_time": "1:30:55", "remaining_time": "6:45:07"} +{"current_steps": 260, "total_steps": 1413, "loss": 0.1938, "lr": 4.618404498360971e-06, "epoch": 0.551285449244633, "percentage": 18.4, "elapsed_time": "1:31:17", "remaining_time": "6:44:51"} +{"current_steps": 261, "total_steps": 1413, "loss": 0.2923, "lr": 4.6154265671779695e-06, "epoch": 0.5534057778955738, "percentage": 18.47, "elapsed_time": "1:31:39", "remaining_time": "6:44:31"} +{"current_steps": 262, "total_steps": 1413, "loss": 0.2513, "lr": 4.612438029248792e-06, "epoch": 0.5555261065465147, "percentage": 18.54, "elapsed_time": "1:32:01", "remaining_time": "6:44:14"} +{"current_steps": 263, "total_steps": 1413, "loss": 0.1831, "lr": 4.609438899557964e-06, "epoch": 0.5576464351974556, "percentage": 18.61, "elapsed_time": "1:32:21", "remaining_time": "6:43:52"} +{"current_steps": 264, "total_steps": 1413, "loss": 0.3138, "lr": 4.606429193143118e-06, "epoch": 0.5597667638483965, "percentage": 18.68, "elapsed_time": "1:32:42", "remaining_time": "6:43:30"} +{"current_steps": 265, "total_steps": 1413, "loss": 0.2822, "lr": 4.6034089250949184e-06, "epoch": 0.5618870924993374, "percentage": 18.75, "elapsed_time": "1:33:03", "remaining_time": "6:43:07"} +{"current_steps": 266, "total_steps": 1413, "loss": 0.3735, "lr": 4.600378110556985e-06, "epoch": 0.5640074211502782, "percentage": 18.83, "elapsed_time": "1:33:24", "remaining_time": "6:42:45"} +{"current_steps": 267, "total_steps": 1413, "loss": 0.2993, "lr": 4.597336764725817e-06, "epoch": 0.5661277498012192, "percentage": 18.9, "elapsed_time": "1:33:45", "remaining_time": "6:42:24"} +{"current_steps": 268, "total_steps": 1413, "loss": 0.2737, "lr": 4.594284902850721e-06, "epoch": 0.5682480784521601, "percentage": 18.97, "elapsed_time": "1:34:05", "remaining_time": "6:41:58"} +{"current_steps": 269, "total_steps": 1413, "loss": 0.2369, "lr": 4.591222540233726e-06, "epoch": 0.570368407103101, "percentage": 19.04, "elapsed_time": "1:34:27", "remaining_time": "6:41:40"} +{"current_steps": 270, "total_steps": 1413, "loss": 0.2901, "lr": 4.5881496922295176e-06, "epoch": 0.5724887357540419, "percentage": 19.11, "elapsed_time": "1:34:49", "remaining_time": "6:41:24"} +{"current_steps": 271, "total_steps": 1413, "loss": 0.2711, "lr": 4.585066374245349e-06, "epoch": 0.5746090644049828, "percentage": 19.18, "elapsed_time": "1:35:10", "remaining_time": "6:41:03"} +{"current_steps": 272, "total_steps": 1413, "loss": 0.202, "lr": 4.581972601740974e-06, "epoch": 0.5767293930559236, "percentage": 19.25, "elapsed_time": "1:35:30", "remaining_time": "6:40:38"} +{"current_steps": 273, "total_steps": 1413, "loss": 0.2347, "lr": 4.5788683902285644e-06, "epoch": 0.5788497217068646, "percentage": 19.32, "elapsed_time": "1:35:51", "remaining_time": "6:40:17"} +{"current_steps": 274, "total_steps": 1413, "loss": 0.2795, "lr": 4.5757537552726315e-06, "epoch": 0.5809700503578055, "percentage": 19.39, "elapsed_time": "1:36:13", "remaining_time": "6:40:00"} +{"current_steps": 275, "total_steps": 1413, "loss": 0.3109, "lr": 4.572628712489953e-06, "epoch": 0.5830903790087464, "percentage": 19.46, "elapsed_time": "1:36:33", "remaining_time": "6:39:36"} +{"current_steps": 276, "total_steps": 1413, "loss": 0.2391, "lr": 4.569493277549487e-06, "epoch": 0.5852107076596873, "percentage": 19.53, "elapsed_time": "1:36:54", "remaining_time": "6:39:13"} +{"current_steps": 277, "total_steps": 1413, "loss": 0.1732, "lr": 4.566347466172303e-06, "epoch": 0.5873310363106281, "percentage": 19.6, "elapsed_time": "1:37:15", "remaining_time": "6:38:53"} +{"current_steps": 278, "total_steps": 1413, "loss": 0.2278, "lr": 4.563191294131494e-06, "epoch": 0.589451364961569, "percentage": 19.67, "elapsed_time": "1:37:36", "remaining_time": "6:38:31"} +{"current_steps": 279, "total_steps": 1413, "loss": 0.2911, "lr": 4.560024777252103e-06, "epoch": 0.5915716936125099, "percentage": 19.75, "elapsed_time": "1:37:58", "remaining_time": "6:38:13"} +{"current_steps": 280, "total_steps": 1413, "loss": 0.327, "lr": 4.556847931411042e-06, "epoch": 0.5936920222634509, "percentage": 19.82, "elapsed_time": "1:38:19", "remaining_time": "6:37:52"} +{"current_steps": 281, "total_steps": 1413, "loss": 0.2883, "lr": 4.553660772537011e-06, "epoch": 0.5958123509143918, "percentage": 19.89, "elapsed_time": "1:38:41", "remaining_time": "6:37:35"} +{"current_steps": 282, "total_steps": 1413, "loss": 0.2981, "lr": 4.550463316610422e-06, "epoch": 0.5979326795653326, "percentage": 19.96, "elapsed_time": "1:39:03", "remaining_time": "6:37:16"} +{"current_steps": 283, "total_steps": 1413, "loss": 0.3031, "lr": 4.547255579663314e-06, "epoch": 0.6000530082162735, "percentage": 20.03, "elapsed_time": "1:39:24", "remaining_time": "6:36:53"} +{"current_steps": 284, "total_steps": 1413, "loss": 0.3123, "lr": 4.544037577779276e-06, "epoch": 0.6021733368672144, "percentage": 20.1, "elapsed_time": "1:39:44", "remaining_time": "6:36:31"} +{"current_steps": 285, "total_steps": 1413, "loss": 0.2838, "lr": 4.540809327093366e-06, "epoch": 0.6042936655181553, "percentage": 20.17, "elapsed_time": "1:40:06", "remaining_time": "6:36:11"} +{"current_steps": 286, "total_steps": 1413, "loss": 0.3393, "lr": 4.537570843792028e-06, "epoch": 0.6064139941690962, "percentage": 20.24, "elapsed_time": "1:40:27", "remaining_time": "6:35:53"} +{"current_steps": 287, "total_steps": 1413, "loss": 0.2278, "lr": 4.534322144113016e-06, "epoch": 0.608534322820037, "percentage": 20.31, "elapsed_time": "1:40:48", "remaining_time": "6:35:31"} +{"current_steps": 288, "total_steps": 1413, "loss": 0.2498, "lr": 4.531063244345303e-06, "epoch": 0.610654651470978, "percentage": 20.38, "elapsed_time": "1:41:09", "remaining_time": "6:35:09"} +{"current_steps": 289, "total_steps": 1413, "loss": 0.2269, "lr": 4.52779416082901e-06, "epoch": 0.6127749801219189, "percentage": 20.45, "elapsed_time": "1:41:31", "remaining_time": "6:34:50"} +{"current_steps": 290, "total_steps": 1413, "loss": 0.3268, "lr": 4.524514909955316e-06, "epoch": 0.6148953087728598, "percentage": 20.52, "elapsed_time": "1:41:52", "remaining_time": "6:34:30"} +{"current_steps": 291, "total_steps": 1413, "loss": 0.3014, "lr": 4.521225508166383e-06, "epoch": 0.6170156374238007, "percentage": 20.59, "elapsed_time": "1:42:13", "remaining_time": "6:34:08"} +{"current_steps": 292, "total_steps": 1413, "loss": 0.2863, "lr": 4.517925971955267e-06, "epoch": 0.6191359660747416, "percentage": 20.67, "elapsed_time": "1:42:33", "remaining_time": "6:33:44"} +{"current_steps": 293, "total_steps": 1413, "loss": 0.3096, "lr": 4.514616317865838e-06, "epoch": 0.6212562947256824, "percentage": 20.74, "elapsed_time": "1:42:54", "remaining_time": "6:33:23"} +{"current_steps": 294, "total_steps": 1413, "loss": 0.284, "lr": 4.5112965624926965e-06, "epoch": 0.6233766233766234, "percentage": 20.81, "elapsed_time": "1:43:17", "remaining_time": "6:33:06"} +{"current_steps": 295, "total_steps": 1413, "loss": 0.3541, "lr": 4.507966722481093e-06, "epoch": 0.6254969520275643, "percentage": 20.88, "elapsed_time": "1:43:37", "remaining_time": "6:32:43"} +{"current_steps": 296, "total_steps": 1413, "loss": 0.287, "lr": 4.504626814526841e-06, "epoch": 0.6276172806785052, "percentage": 20.95, "elapsed_time": "1:43:57", "remaining_time": "6:32:19"} +{"current_steps": 297, "total_steps": 1413, "loss": 0.266, "lr": 4.501276855376235e-06, "epoch": 0.6297376093294461, "percentage": 21.02, "elapsed_time": "1:44:19", "remaining_time": "6:31:59"} +{"current_steps": 298, "total_steps": 1413, "loss": 0.3637, "lr": 4.497916861825966e-06, "epoch": 0.6318579379803869, "percentage": 21.09, "elapsed_time": "1:44:40", "remaining_time": "6:31:38"} +{"current_steps": 299, "total_steps": 1413, "loss": 0.2331, "lr": 4.494546850723037e-06, "epoch": 0.6339782666313278, "percentage": 21.16, "elapsed_time": "1:45:00", "remaining_time": "6:31:15"} +{"current_steps": 300, "total_steps": 1413, "loss": 0.2661, "lr": 4.4911668389646795e-06, "epoch": 0.6360985952822688, "percentage": 21.23, "elapsed_time": "1:45:21", "remaining_time": "6:30:53"} +{"current_steps": 301, "total_steps": 1413, "loss": 0.2305, "lr": 4.487776843498268e-06, "epoch": 0.6382189239332097, "percentage": 21.3, "elapsed_time": "1:45:43", "remaining_time": "6:30:33"} +{"current_steps": 302, "total_steps": 1413, "loss": 0.3038, "lr": 4.484376881321237e-06, "epoch": 0.6403392525841506, "percentage": 21.37, "elapsed_time": "1:46:05", "remaining_time": "6:30:16"} +{"current_steps": 303, "total_steps": 1413, "loss": 0.1923, "lr": 4.480966969480992e-06, "epoch": 0.6424595812350914, "percentage": 21.44, "elapsed_time": "1:46:26", "remaining_time": "6:29:55"} +{"current_steps": 304, "total_steps": 1413, "loss": 0.2522, "lr": 4.477547125074826e-06, "epoch": 0.6445799098860323, "percentage": 21.51, "elapsed_time": "1:46:47", "remaining_time": "6:29:34"} +{"current_steps": 305, "total_steps": 1413, "loss": 0.3941, "lr": 4.474117365249835e-06, "epoch": 0.6467002385369732, "percentage": 21.59, "elapsed_time": "1:47:08", "remaining_time": "6:29:13"} +{"current_steps": 306, "total_steps": 1413, "loss": 0.2683, "lr": 4.4706777072028305e-06, "epoch": 0.6488205671879141, "percentage": 21.66, "elapsed_time": "1:47:29", "remaining_time": "6:28:53"} +{"current_steps": 307, "total_steps": 1413, "loss": 0.4248, "lr": 4.4672281681802536e-06, "epoch": 0.6509408958388551, "percentage": 21.73, "elapsed_time": "1:47:50", "remaining_time": "6:28:29"} +{"current_steps": 308, "total_steps": 1413, "loss": 0.3615, "lr": 4.463768765478088e-06, "epoch": 0.6530612244897959, "percentage": 21.8, "elapsed_time": "1:48:11", "remaining_time": "6:28:07"} +{"current_steps": 309, "total_steps": 1413, "loss": 0.1891, "lr": 4.460299516441777e-06, "epoch": 0.6551815531407368, "percentage": 21.87, "elapsed_time": "1:48:32", "remaining_time": "6:27:47"} +{"current_steps": 310, "total_steps": 1413, "loss": 0.3321, "lr": 4.456820438466127e-06, "epoch": 0.6573018817916777, "percentage": 21.94, "elapsed_time": "1:48:55", "remaining_time": "6:27:33"} +{"current_steps": 311, "total_steps": 1413, "loss": 0.1842, "lr": 4.453331548995235e-06, "epoch": 0.6594222104426186, "percentage": 22.01, "elapsed_time": "1:49:16", "remaining_time": "6:27:10"} +{"current_steps": 312, "total_steps": 1413, "loss": 0.2623, "lr": 4.449832865522386e-06, "epoch": 0.6615425390935595, "percentage": 22.08, "elapsed_time": "1:49:36", "remaining_time": "6:26:46"} +{"current_steps": 313, "total_steps": 1413, "loss": 0.2996, "lr": 4.446324405589973e-06, "epoch": 0.6636628677445005, "percentage": 22.15, "elapsed_time": "1:49:56", "remaining_time": "6:26:23"} +{"current_steps": 314, "total_steps": 1413, "loss": 0.292, "lr": 4.442806186789414e-06, "epoch": 0.6657831963954413, "percentage": 22.22, "elapsed_time": "1:50:19", "remaining_time": "6:26:06"} +{"current_steps": 315, "total_steps": 1413, "loss": 0.3205, "lr": 4.43927822676105e-06, "epoch": 0.6679035250463822, "percentage": 22.29, "elapsed_time": "1:50:38", "remaining_time": "6:25:41"} +{"current_steps": 316, "total_steps": 1413, "loss": 0.3059, "lr": 4.43574054319407e-06, "epoch": 0.6700238536973231, "percentage": 22.36, "elapsed_time": "1:50:59", "remaining_time": "6:25:19"} +{"current_steps": 317, "total_steps": 1413, "loss": 0.1772, "lr": 4.432193153826414e-06, "epoch": 0.672144182348264, "percentage": 22.43, "elapsed_time": "1:51:21", "remaining_time": "6:25:01"} +{"current_steps": 318, "total_steps": 1413, "loss": 0.2689, "lr": 4.428636076444689e-06, "epoch": 0.6742645109992049, "percentage": 22.51, "elapsed_time": "1:51:42", "remaining_time": "6:24:38"} +{"current_steps": 319, "total_steps": 1413, "loss": 0.3262, "lr": 4.425069328884076e-06, "epoch": 0.6763848396501457, "percentage": 22.58, "elapsed_time": "1:52:03", "remaining_time": "6:24:17"} +{"current_steps": 320, "total_steps": 1413, "loss": 0.2938, "lr": 4.421492929028243e-06, "epoch": 0.6785051683010866, "percentage": 22.65, "elapsed_time": "1:52:23", "remaining_time": "6:23:52"} +{"current_steps": 321, "total_steps": 1413, "loss": 0.287, "lr": 4.417906894809254e-06, "epoch": 0.6806254969520276, "percentage": 22.72, "elapsed_time": "1:52:44", "remaining_time": "6:23:32"} +{"current_steps": 322, "total_steps": 1413, "loss": 0.2534, "lr": 4.41431124420748e-06, "epoch": 0.6827458256029685, "percentage": 22.79, "elapsed_time": "1:53:06", "remaining_time": "6:23:13"} +{"current_steps": 323, "total_steps": 1413, "loss": 0.2202, "lr": 4.410705995251509e-06, "epoch": 0.6848661542539094, "percentage": 22.86, "elapsed_time": "1:53:26", "remaining_time": "6:22:49"} +{"current_steps": 324, "total_steps": 1413, "loss": 0.2868, "lr": 4.4070911660180546e-06, "epoch": 0.6869864829048502, "percentage": 22.93, "elapsed_time": "1:53:46", "remaining_time": "6:22:24"} +{"current_steps": 325, "total_steps": 1413, "loss": 0.1661, "lr": 4.403466774631867e-06, "epoch": 0.6891068115557911, "percentage": 23.0, "elapsed_time": "1:54:07", "remaining_time": "6:22:04"} +{"current_steps": 326, "total_steps": 1413, "loss": 0.2195, "lr": 4.39983283926564e-06, "epoch": 0.691227140206732, "percentage": 23.07, "elapsed_time": "1:54:28", "remaining_time": "6:21:40"} +{"current_steps": 327, "total_steps": 1413, "loss": 0.2696, "lr": 4.3961893781399186e-06, "epoch": 0.693347468857673, "percentage": 23.14, "elapsed_time": "1:54:48", "remaining_time": "6:21:17"} +{"current_steps": 328, "total_steps": 1413, "loss": 0.3592, "lr": 4.392536409523015e-06, "epoch": 0.6954677975086139, "percentage": 23.21, "elapsed_time": "1:55:08", "remaining_time": "6:20:54"} +{"current_steps": 329, "total_steps": 1413, "loss": 0.2301, "lr": 4.388873951730909e-06, "epoch": 0.6975881261595547, "percentage": 23.28, "elapsed_time": "1:55:29", "remaining_time": "6:20:30"} +{"current_steps": 330, "total_steps": 1413, "loss": 0.2445, "lr": 4.385202023127158e-06, "epoch": 0.6997084548104956, "percentage": 23.35, "elapsed_time": "1:55:49", "remaining_time": "6:20:06"} +{"current_steps": 331, "total_steps": 1413, "loss": 0.283, "lr": 4.381520642122808e-06, "epoch": 0.7018287834614365, "percentage": 23.43, "elapsed_time": "1:56:10", "remaining_time": "6:19:44"} +{"current_steps": 332, "total_steps": 1413, "loss": 0.423, "lr": 4.3778298271762995e-06, "epoch": 0.7039491121123774, "percentage": 23.5, "elapsed_time": "1:56:31", "remaining_time": "6:19:24"} +{"current_steps": 333, "total_steps": 1413, "loss": 0.3269, "lr": 4.374129596793375e-06, "epoch": 0.7060694407633183, "percentage": 23.57, "elapsed_time": "1:56:52", "remaining_time": "6:19:02"} +{"current_steps": 334, "total_steps": 1413, "loss": 0.2774, "lr": 4.370419969526982e-06, "epoch": 0.7081897694142593, "percentage": 23.64, "elapsed_time": "1:57:13", "remaining_time": "6:18:41"} +{"current_steps": 335, "total_steps": 1413, "loss": 0.2744, "lr": 4.366700963977188e-06, "epoch": 0.7103100980652001, "percentage": 23.71, "elapsed_time": "1:57:35", "remaining_time": "6:18:25"} +{"current_steps": 336, "total_steps": 1413, "loss": 0.3201, "lr": 4.362972598791085e-06, "epoch": 0.712430426716141, "percentage": 23.78, "elapsed_time": "1:57:57", "remaining_time": "6:18:04"} +{"current_steps": 337, "total_steps": 1413, "loss": 0.1742, "lr": 4.3592348926626886e-06, "epoch": 0.7145507553670819, "percentage": 23.85, "elapsed_time": "1:58:19", "remaining_time": "6:17:46"} +{"current_steps": 338, "total_steps": 1413, "loss": 0.3311, "lr": 4.355487864332853e-06, "epoch": 0.7166710840180228, "percentage": 23.92, "elapsed_time": "1:58:40", "remaining_time": "6:17:26"} +{"current_steps": 339, "total_steps": 1413, "loss": 0.2022, "lr": 4.351731532589173e-06, "epoch": 0.7187914126689637, "percentage": 23.99, "elapsed_time": "1:59:02", "remaining_time": "6:17:06"} +{"current_steps": 340, "total_steps": 1413, "loss": 0.3076, "lr": 4.347965916265893e-06, "epoch": 0.7209117413199045, "percentage": 24.06, "elapsed_time": "1:59:22", "remaining_time": "6:16:45"} +{"current_steps": 341, "total_steps": 1413, "loss": 0.2187, "lr": 4.3441910342438076e-06, "epoch": 0.7230320699708455, "percentage": 24.13, "elapsed_time": "1:59:43", "remaining_time": "6:16:22"} +{"current_steps": 342, "total_steps": 1413, "loss": 0.282, "lr": 4.340406905450171e-06, "epoch": 0.7251523986217864, "percentage": 24.2, "elapsed_time": "2:00:04", "remaining_time": "6:16:02"} +{"current_steps": 343, "total_steps": 1413, "loss": 0.2898, "lr": 4.3366135488586e-06, "epoch": 0.7272727272727273, "percentage": 24.27, "elapsed_time": "2:00:25", "remaining_time": "6:15:38"} +{"current_steps": 344, "total_steps": 1413, "loss": 0.2422, "lr": 4.332810983488979e-06, "epoch": 0.7293930559236682, "percentage": 24.35, "elapsed_time": "2:00:46", "remaining_time": "6:15:18"} +{"current_steps": 345, "total_steps": 1413, "loss": 0.2781, "lr": 4.3289992284073675e-06, "epoch": 0.731513384574609, "percentage": 24.42, "elapsed_time": "2:01:07", "remaining_time": "6:14:56"} +{"current_steps": 346, "total_steps": 1413, "loss": 0.1749, "lr": 4.325178302725901e-06, "epoch": 0.7336337132255499, "percentage": 24.49, "elapsed_time": "2:01:28", "remaining_time": "6:14:36"} +{"current_steps": 347, "total_steps": 1413, "loss": 0.287, "lr": 4.321348225602694e-06, "epoch": 0.7357540418764908, "percentage": 24.56, "elapsed_time": "2:01:48", "remaining_time": "6:14:13"} +{"current_steps": 348, "total_steps": 1413, "loss": 0.2698, "lr": 4.31750901624175e-06, "epoch": 0.7378743705274318, "percentage": 24.63, "elapsed_time": "2:02:10", "remaining_time": "6:13:53"} +{"current_steps": 349, "total_steps": 1413, "loss": 0.2312, "lr": 4.31366069389286e-06, "epoch": 0.7399946991783727, "percentage": 24.7, "elapsed_time": "2:02:31", "remaining_time": "6:13:34"} +{"current_steps": 350, "total_steps": 1413, "loss": 0.2886, "lr": 4.309803277851507e-06, "epoch": 0.7421150278293135, "percentage": 24.77, "elapsed_time": "2:02:53", "remaining_time": "6:13:15"} +{"current_steps": 351, "total_steps": 1413, "loss": 0.2501, "lr": 4.305936787458769e-06, "epoch": 0.7442353564802544, "percentage": 24.84, "elapsed_time": "2:03:15", "remaining_time": "6:12:57"} +{"current_steps": 352, "total_steps": 1413, "loss": 0.1851, "lr": 4.302061242101226e-06, "epoch": 0.7463556851311953, "percentage": 24.91, "elapsed_time": "2:03:36", "remaining_time": "6:12:34"} +{"current_steps": 353, "total_steps": 1413, "loss": 0.2419, "lr": 4.2981766612108576e-06, "epoch": 0.7484760137821362, "percentage": 24.98, "elapsed_time": "2:03:56", "remaining_time": "6:12:11"} +{"current_steps": 354, "total_steps": 1413, "loss": 0.2165, "lr": 4.294283064264947e-06, "epoch": 0.7505963424330772, "percentage": 25.05, "elapsed_time": "2:04:16", "remaining_time": "6:11:47"} +{"current_steps": 355, "total_steps": 1413, "loss": 0.2562, "lr": 4.290380470785984e-06, "epoch": 0.7527166710840181, "percentage": 25.12, "elapsed_time": "2:04:37", "remaining_time": "6:11:25"} +{"current_steps": 356, "total_steps": 1413, "loss": 0.318, "lr": 4.2864689003415675e-06, "epoch": 0.7548369997349589, "percentage": 25.19, "elapsed_time": "2:04:58", "remaining_time": "6:11:02"} +{"current_steps": 357, "total_steps": 1413, "loss": 0.2193, "lr": 4.282548372544307e-06, "epoch": 0.7569573283858998, "percentage": 25.27, "elapsed_time": "2:05:19", "remaining_time": "6:10:43"} +{"current_steps": 358, "total_steps": 1413, "loss": 0.2466, "lr": 4.278618907051724e-06, "epoch": 0.7590776570368407, "percentage": 25.34, "elapsed_time": "2:05:40", "remaining_time": "6:10:22"} +{"current_steps": 359, "total_steps": 1413, "loss": 0.2749, "lr": 4.274680523566154e-06, "epoch": 0.7611979856877816, "percentage": 25.41, "elapsed_time": "2:06:00", "remaining_time": "6:09:58"} +{"current_steps": 360, "total_steps": 1413, "loss": 0.3133, "lr": 4.270733241834647e-06, "epoch": 0.7633183143387225, "percentage": 25.48, "elapsed_time": "2:06:21", "remaining_time": "6:09:36"} +{"current_steps": 361, "total_steps": 1413, "loss": 0.3188, "lr": 4.266777081648868e-06, "epoch": 0.7654386429896634, "percentage": 25.55, "elapsed_time": "2:06:41", "remaining_time": "6:09:12"} +{"current_steps": 362, "total_steps": 1413, "loss": 0.3409, "lr": 4.262812062844999e-06, "epoch": 0.7675589716406043, "percentage": 25.62, "elapsed_time": "2:07:03", "remaining_time": "6:08:54"} +{"current_steps": 363, "total_steps": 1413, "loss": 0.2538, "lr": 4.25883820530364e-06, "epoch": 0.7696793002915452, "percentage": 25.69, "elapsed_time": "2:07:24", "remaining_time": "6:08:32"} +{"current_steps": 364, "total_steps": 1413, "loss": 0.2741, "lr": 4.254855528949709e-06, "epoch": 0.7717996289424861, "percentage": 25.76, "elapsed_time": "2:07:46", "remaining_time": "6:08:14"} +{"current_steps": 365, "total_steps": 1413, "loss": 0.2353, "lr": 4.250864053752337e-06, "epoch": 0.773919957593427, "percentage": 25.83, "elapsed_time": "2:08:07", "remaining_time": "6:07:52"} +{"current_steps": 366, "total_steps": 1413, "loss": 0.2585, "lr": 4.2468637997247794e-06, "epoch": 0.7760402862443678, "percentage": 25.9, "elapsed_time": "2:08:28", "remaining_time": "6:07:31"} +{"current_steps": 367, "total_steps": 1413, "loss": 0.2143, "lr": 4.242854786924302e-06, "epoch": 0.7781606148953087, "percentage": 25.97, "elapsed_time": "2:08:50", "remaining_time": "6:07:12"} +{"current_steps": 368, "total_steps": 1413, "loss": 0.1835, "lr": 4.238837035452092e-06, "epoch": 0.7802809435462497, "percentage": 26.04, "elapsed_time": "2:09:12", "remaining_time": "6:06:53"} +{"current_steps": 369, "total_steps": 1413, "loss": 0.2107, "lr": 4.234810565453148e-06, "epoch": 0.7824012721971906, "percentage": 26.11, "elapsed_time": "2:09:33", "remaining_time": "6:06:33"} +{"current_steps": 370, "total_steps": 1413, "loss": 0.2497, "lr": 4.230775397116188e-06, "epoch": 0.7845216008481315, "percentage": 26.19, "elapsed_time": "2:09:55", "remaining_time": "6:06:13"} +{"current_steps": 371, "total_steps": 1413, "loss": 0.2577, "lr": 4.2267315506735394e-06, "epoch": 0.7866419294990723, "percentage": 26.26, "elapsed_time": "2:10:15", "remaining_time": "6:05:52"} +{"current_steps": 372, "total_steps": 1413, "loss": 0.1978, "lr": 4.2226790464010445e-06, "epoch": 0.7887622581500132, "percentage": 26.33, "elapsed_time": "2:10:37", "remaining_time": "6:05:33"} +{"current_steps": 373, "total_steps": 1413, "loss": 0.2462, "lr": 4.218617904617953e-06, "epoch": 0.7908825868009541, "percentage": 26.4, "elapsed_time": "2:10:59", "remaining_time": "6:05:13"} +{"current_steps": 374, "total_steps": 1413, "loss": 0.274, "lr": 4.2145481456868265e-06, "epoch": 0.793002915451895, "percentage": 26.47, "elapsed_time": "2:11:21", "remaining_time": "6:04:56"} +{"current_steps": 375, "total_steps": 1413, "loss": 0.3099, "lr": 4.210469790013431e-06, "epoch": 0.795123244102836, "percentage": 26.54, "elapsed_time": "2:11:42", "remaining_time": "6:04:35"} +{"current_steps": 376, "total_steps": 1413, "loss": 0.4174, "lr": 4.206382858046636e-06, "epoch": 0.7972435727537769, "percentage": 26.61, "elapsed_time": "2:12:03", "remaining_time": "6:04:13"} +{"current_steps": 377, "total_steps": 1413, "loss": 0.2273, "lr": 4.202287370278313e-06, "epoch": 0.7993639014047177, "percentage": 26.68, "elapsed_time": "2:12:25", "remaining_time": "6:03:53"} +{"current_steps": 378, "total_steps": 1413, "loss": 0.1472, "lr": 4.198183347243233e-06, "epoch": 0.8014842300556586, "percentage": 26.75, "elapsed_time": "2:12:47", "remaining_time": "6:03:35"} +{"current_steps": 379, "total_steps": 1413, "loss": 0.3014, "lr": 4.194070809518963e-06, "epoch": 0.8036045587065995, "percentage": 26.82, "elapsed_time": "2:13:08", "remaining_time": "6:03:15"} +{"current_steps": 380, "total_steps": 1413, "loss": 0.2107, "lr": 4.1899497777257615e-06, "epoch": 0.8057248873575404, "percentage": 26.89, "elapsed_time": "2:13:29", "remaining_time": "6:02:52"} +{"current_steps": 381, "total_steps": 1413, "loss": 0.2336, "lr": 4.185820272526477e-06, "epoch": 0.8078452160084814, "percentage": 26.96, "elapsed_time": "2:13:50", "remaining_time": "6:02:30"} +{"current_steps": 382, "total_steps": 1413, "loss": 0.3076, "lr": 4.181682314626443e-06, "epoch": 0.8099655446594222, "percentage": 27.03, "elapsed_time": "2:14:11", "remaining_time": "6:02:10"} +{"current_steps": 383, "total_steps": 1413, "loss": 0.2436, "lr": 4.177535924773375e-06, "epoch": 0.8120858733103631, "percentage": 27.11, "elapsed_time": "2:14:31", "remaining_time": "6:01:47"} +{"current_steps": 384, "total_steps": 1413, "loss": 0.3278, "lr": 4.173381123757268e-06, "epoch": 0.814206201961304, "percentage": 27.18, "elapsed_time": "2:14:53", "remaining_time": "6:01:27"} +{"current_steps": 385, "total_steps": 1413, "loss": 0.3002, "lr": 4.169217932410288e-06, "epoch": 0.8163265306122449, "percentage": 27.25, "elapsed_time": "2:15:14", "remaining_time": "6:01:07"} +{"current_steps": 386, "total_steps": 1413, "loss": 0.2263, "lr": 4.165046371606671e-06, "epoch": 0.8184468592631858, "percentage": 27.32, "elapsed_time": "2:15:35", "remaining_time": "6:00:44"} +{"current_steps": 387, "total_steps": 1413, "loss": 0.2967, "lr": 4.160866462262618e-06, "epoch": 0.8205671879141266, "percentage": 27.39, "elapsed_time": "2:15:56", "remaining_time": "6:00:22"} +{"current_steps": 388, "total_steps": 1413, "loss": 0.2266, "lr": 4.15667822533619e-06, "epoch": 0.8226875165650676, "percentage": 27.46, "elapsed_time": "2:16:17", "remaining_time": "6:00:01"} +{"current_steps": 389, "total_steps": 1413, "loss": 0.3302, "lr": 4.152481681827201e-06, "epoch": 0.8248078452160085, "percentage": 27.53, "elapsed_time": "2:16:37", "remaining_time": "5:59:40"} +{"current_steps": 390, "total_steps": 1413, "loss": 0.2646, "lr": 4.1482768527771155e-06, "epoch": 0.8269281738669494, "percentage": 27.6, "elapsed_time": "2:16:58", "remaining_time": "5:59:17"} +{"current_steps": 391, "total_steps": 1413, "loss": 0.3638, "lr": 4.14406375926894e-06, "epoch": 0.8290485025178903, "percentage": 27.67, "elapsed_time": "2:17:20", "remaining_time": "5:58:58"} +{"current_steps": 392, "total_steps": 1413, "loss": 0.1704, "lr": 4.13984242242712e-06, "epoch": 0.8311688311688312, "percentage": 27.74, "elapsed_time": "2:17:40", "remaining_time": "5:58:35"} +{"current_steps": 393, "total_steps": 1413, "loss": 0.2594, "lr": 4.135612863417435e-06, "epoch": 0.833289159819772, "percentage": 27.81, "elapsed_time": "2:18:01", "remaining_time": "5:58:13"} +{"current_steps": 394, "total_steps": 1413, "loss": 0.2068, "lr": 4.131375103446889e-06, "epoch": 0.835409488470713, "percentage": 27.88, "elapsed_time": "2:18:22", "remaining_time": "5:57:52"} +{"current_steps": 395, "total_steps": 1413, "loss": 0.1623, "lr": 4.127129163763601e-06, "epoch": 0.8375298171216539, "percentage": 27.95, "elapsed_time": "2:18:42", "remaining_time": "5:57:29"} +{"current_steps": 396, "total_steps": 1413, "loss": 0.1622, "lr": 4.122875065656712e-06, "epoch": 0.8396501457725948, "percentage": 28.03, "elapsed_time": "2:19:03", "remaining_time": "5:57:07"} +{"current_steps": 397, "total_steps": 1413, "loss": 0.3365, "lr": 4.118612830456262e-06, "epoch": 0.8417704744235357, "percentage": 28.1, "elapsed_time": "2:19:25", "remaining_time": "5:56:47"} +{"current_steps": 398, "total_steps": 1413, "loss": 0.2857, "lr": 4.114342479533094e-06, "epoch": 0.8438908030744765, "percentage": 28.17, "elapsed_time": "2:19:44", "remaining_time": "5:56:23"} +{"current_steps": 399, "total_steps": 1413, "loss": 0.2944, "lr": 4.110064034298741e-06, "epoch": 0.8460111317254174, "percentage": 28.24, "elapsed_time": "2:20:05", "remaining_time": "5:56:02"} +{"current_steps": 400, "total_steps": 1413, "loss": 0.2156, "lr": 4.105777516205324e-06, "epoch": 0.8481314603763583, "percentage": 28.31, "elapsed_time": "2:20:26", "remaining_time": "5:55:40"} +{"current_steps": 401, "total_steps": 1413, "loss": 0.2235, "lr": 4.101482946745438e-06, "epoch": 0.8502517890272993, "percentage": 28.38, "elapsed_time": "2:20:46", "remaining_time": "5:55:16"} +{"current_steps": 402, "total_steps": 1413, "loss": 0.1273, "lr": 4.09718034745205e-06, "epoch": 0.8523721176782402, "percentage": 28.45, "elapsed_time": "2:21:08", "remaining_time": "5:54:56"} +{"current_steps": 403, "total_steps": 1413, "loss": 0.3338, "lr": 4.092869739898386e-06, "epoch": 0.854492446329181, "percentage": 28.52, "elapsed_time": "2:21:30", "remaining_time": "5:54:38"} +{"current_steps": 404, "total_steps": 1413, "loss": 0.2359, "lr": 4.0885511456978275e-06, "epoch": 0.8566127749801219, "percentage": 28.59, "elapsed_time": "2:21:50", "remaining_time": "5:54:15"} +{"current_steps": 405, "total_steps": 1413, "loss": 0.2267, "lr": 4.084224586503801e-06, "epoch": 0.8587331036310628, "percentage": 28.66, "elapsed_time": "2:22:11", "remaining_time": "5:53:52"} +{"current_steps": 406, "total_steps": 1413, "loss": 0.1329, "lr": 4.0798900840096694e-06, "epoch": 0.8608534322820037, "percentage": 28.73, "elapsed_time": "2:22:32", "remaining_time": "5:53:33"} +{"current_steps": 407, "total_steps": 1413, "loss": 0.2221, "lr": 4.075547659948621e-06, "epoch": 0.8629737609329446, "percentage": 28.8, "elapsed_time": "2:22:54", "remaining_time": "5:53:12"} +{"current_steps": 408, "total_steps": 1413, "loss": 0.3571, "lr": 4.071197336093566e-06, "epoch": 0.8650940895838855, "percentage": 28.87, "elapsed_time": "2:23:15", "remaining_time": "5:52:51"} +{"current_steps": 409, "total_steps": 1413, "loss": 0.247, "lr": 4.0668391342570225e-06, "epoch": 0.8672144182348264, "percentage": 28.95, "elapsed_time": "2:23:36", "remaining_time": "5:52:31"} +{"current_steps": 410, "total_steps": 1413, "loss": 0.2483, "lr": 4.062473076291009e-06, "epoch": 0.8693347468857673, "percentage": 29.02, "elapsed_time": "2:23:57", "remaining_time": "5:52:09"} +{"current_steps": 411, "total_steps": 1413, "loss": 0.2748, "lr": 4.058099184086934e-06, "epoch": 0.8714550755367082, "percentage": 29.09, "elapsed_time": "2:24:17", "remaining_time": "5:51:46"} +{"current_steps": 412, "total_steps": 1413, "loss": 0.1534, "lr": 4.05371747957549e-06, "epoch": 0.8735754041876491, "percentage": 29.16, "elapsed_time": "2:24:38", "remaining_time": "5:51:26"} +{"current_steps": 413, "total_steps": 1413, "loss": 0.3573, "lr": 4.049327984726535e-06, "epoch": 0.87569573283859, "percentage": 29.23, "elapsed_time": "2:24:59", "remaining_time": "5:51:03"} +{"current_steps": 414, "total_steps": 1413, "loss": 0.3242, "lr": 4.044930721548992e-06, "epoch": 0.8778160614895308, "percentage": 29.3, "elapsed_time": "2:25:19", "remaining_time": "5:50:41"} +{"current_steps": 415, "total_steps": 1413, "loss": 0.2101, "lr": 4.040525712090733e-06, "epoch": 0.8799363901404718, "percentage": 29.37, "elapsed_time": "2:25:40", "remaining_time": "5:50:19"} +{"current_steps": 416, "total_steps": 1413, "loss": 0.2115, "lr": 4.0361129784384705e-06, "epoch": 0.8820567187914127, "percentage": 29.44, "elapsed_time": "2:26:02", "remaining_time": "5:49:59"} +{"current_steps": 417, "total_steps": 1413, "loss": 0.274, "lr": 4.031692542717645e-06, "epoch": 0.8841770474423536, "percentage": 29.51, "elapsed_time": "2:26:24", "remaining_time": "5:49:41"} +{"current_steps": 418, "total_steps": 1413, "loss": 0.4542, "lr": 4.027264427092316e-06, "epoch": 0.8862973760932945, "percentage": 29.58, "elapsed_time": "2:26:44", "remaining_time": "5:49:18"} +{"current_steps": 419, "total_steps": 1413, "loss": 0.2008, "lr": 4.022828653765049e-06, "epoch": 0.8884177047442353, "percentage": 29.65, "elapsed_time": "2:27:07", "remaining_time": "5:49:01"} +{"current_steps": 420, "total_steps": 1413, "loss": 0.2777, "lr": 4.018385244976807e-06, "epoch": 0.8905380333951762, "percentage": 29.72, "elapsed_time": "2:27:28", "remaining_time": "5:48:39"} +{"current_steps": 421, "total_steps": 1413, "loss": 0.2378, "lr": 4.0139342230068355e-06, "epoch": 0.8926583620461171, "percentage": 29.79, "elapsed_time": "2:27:48", "remaining_time": "5:48:17"} +{"current_steps": 422, "total_steps": 1413, "loss": 0.2469, "lr": 4.009475610172553e-06, "epoch": 0.8947786906970581, "percentage": 29.87, "elapsed_time": "2:28:10", "remaining_time": "5:47:57"} +{"current_steps": 423, "total_steps": 1413, "loss": 0.2247, "lr": 4.005009428829439e-06, "epoch": 0.896899019347999, "percentage": 29.94, "elapsed_time": "2:28:30", "remaining_time": "5:47:34"} +{"current_steps": 424, "total_steps": 1413, "loss": 0.2117, "lr": 4.0005357013709215e-06, "epoch": 0.8990193479989398, "percentage": 30.01, "elapsed_time": "2:28:50", "remaining_time": "5:47:11"} +{"current_steps": 425, "total_steps": 1413, "loss": 0.2591, "lr": 3.996054450228263e-06, "epoch": 0.9011396766498807, "percentage": 30.08, "elapsed_time": "2:29:11", "remaining_time": "5:46:50"} +{"current_steps": 426, "total_steps": 1413, "loss": 0.2905, "lr": 3.991565697870453e-06, "epoch": 0.9032600053008216, "percentage": 30.15, "elapsed_time": "2:29:31", "remaining_time": "5:46:26"} +{"current_steps": 427, "total_steps": 1413, "loss": 0.298, "lr": 3.987069466804089e-06, "epoch": 0.9053803339517625, "percentage": 30.22, "elapsed_time": "2:29:52", "remaining_time": "5:46:04"} +{"current_steps": 428, "total_steps": 1413, "loss": 0.4034, "lr": 3.982565779573269e-06, "epoch": 0.9075006626027035, "percentage": 30.29, "elapsed_time": "2:30:14", "remaining_time": "5:45:45"} +{"current_steps": 429, "total_steps": 1413, "loss": 0.2176, "lr": 3.978054658759474e-06, "epoch": 0.9096209912536443, "percentage": 30.36, "elapsed_time": "2:30:36", "remaining_time": "5:45:26"} +{"current_steps": 430, "total_steps": 1413, "loss": 0.2228, "lr": 3.973536126981459e-06, "epoch": 0.9117413199045852, "percentage": 30.43, "elapsed_time": "2:30:58", "remaining_time": "5:45:07"} +{"current_steps": 431, "total_steps": 1413, "loss": 0.2471, "lr": 3.969010206895136e-06, "epoch": 0.9138616485555261, "percentage": 30.5, "elapsed_time": "2:31:18", "remaining_time": "5:44:44"} +{"current_steps": 432, "total_steps": 1413, "loss": 0.1858, "lr": 3.964476921193464e-06, "epoch": 0.915981977206467, "percentage": 30.57, "elapsed_time": "2:31:39", "remaining_time": "5:44:22"} +{"current_steps": 433, "total_steps": 1413, "loss": 0.2178, "lr": 3.9599362926063315e-06, "epoch": 0.9181023058574079, "percentage": 30.64, "elapsed_time": "2:32:00", "remaining_time": "5:44:02"} +{"current_steps": 434, "total_steps": 1413, "loss": 0.2695, "lr": 3.955388343900443e-06, "epoch": 0.9202226345083488, "percentage": 30.71, "elapsed_time": "2:32:21", "remaining_time": "5:43:41"} +{"current_steps": 435, "total_steps": 1413, "loss": 0.2193, "lr": 3.950833097879208e-06, "epoch": 0.9223429631592897, "percentage": 30.79, "elapsed_time": "2:32:42", "remaining_time": "5:43:20"} +{"current_steps": 436, "total_steps": 1413, "loss": 0.2479, "lr": 3.946270577382626e-06, "epoch": 0.9244632918102306, "percentage": 30.86, "elapsed_time": "2:33:04", "remaining_time": "5:43:00"} +{"current_steps": 437, "total_steps": 1413, "loss": 0.3304, "lr": 3.941700805287169e-06, "epoch": 0.9265836204611715, "percentage": 30.93, "elapsed_time": "2:33:25", "remaining_time": "5:42:40"} +{"current_steps": 438, "total_steps": 1413, "loss": 0.2871, "lr": 3.937123804505666e-06, "epoch": 0.9287039491121124, "percentage": 31.0, "elapsed_time": "2:33:46", "remaining_time": "5:42:18"} +{"current_steps": 439, "total_steps": 1413, "loss": 0.2042, "lr": 3.932539597987196e-06, "epoch": 0.9308242777630533, "percentage": 31.07, "elapsed_time": "2:34:07", "remaining_time": "5:41:57"} +{"current_steps": 440, "total_steps": 1413, "loss": 0.25, "lr": 3.927948208716964e-06, "epoch": 0.9329446064139941, "percentage": 31.14, "elapsed_time": "2:34:29", "remaining_time": "5:41:38"} +{"current_steps": 441, "total_steps": 1413, "loss": 0.2686, "lr": 3.92334965971619e-06, "epoch": 0.935064935064935, "percentage": 31.21, "elapsed_time": "2:34:50", "remaining_time": "5:41:17"} +{"current_steps": 442, "total_steps": 1413, "loss": 0.2693, "lr": 3.918743974041992e-06, "epoch": 0.937185263715876, "percentage": 31.28, "elapsed_time": "2:35:12", "remaining_time": "5:40:59"} +{"current_steps": 443, "total_steps": 1413, "loss": 0.2578, "lr": 3.914131174787274e-06, "epoch": 0.9393055923668169, "percentage": 31.35, "elapsed_time": "2:35:36", "remaining_time": "5:40:43"} +{"current_steps": 444, "total_steps": 1413, "loss": 0.278, "lr": 3.909511285080605e-06, "epoch": 0.9414259210177578, "percentage": 31.42, "elapsed_time": "2:35:57", "remaining_time": "5:40:22"} +{"current_steps": 445, "total_steps": 1413, "loss": 0.2269, "lr": 3.9048843280861055e-06, "epoch": 0.9435462496686986, "percentage": 31.49, "elapsed_time": "2:36:18", "remaining_time": "5:40:00"} +{"current_steps": 446, "total_steps": 1413, "loss": 0.2526, "lr": 3.900250327003333e-06, "epoch": 0.9456665783196395, "percentage": 31.56, "elapsed_time": "2:36:39", "remaining_time": "5:39:38"} +{"current_steps": 447, "total_steps": 1413, "loss": 0.2397, "lr": 3.895609305067162e-06, "epoch": 0.9477869069705804, "percentage": 31.63, "elapsed_time": "2:36:59", "remaining_time": "5:39:16"} +{"current_steps": 448, "total_steps": 1413, "loss": 0.2516, "lr": 3.890961285547672e-06, "epoch": 0.9499072356215214, "percentage": 31.71, "elapsed_time": "2:37:19", "remaining_time": "5:38:53"} +{"current_steps": 449, "total_steps": 1413, "loss": 0.2889, "lr": 3.886306291750028e-06, "epoch": 0.9520275642724623, "percentage": 31.78, "elapsed_time": "2:37:41", "remaining_time": "5:38:33"} +{"current_steps": 450, "total_steps": 1413, "loss": 0.3136, "lr": 3.881644347014361e-06, "epoch": 0.9541478929234031, "percentage": 31.85, "elapsed_time": "2:38:02", "remaining_time": "5:38:12"} +{"current_steps": 451, "total_steps": 1413, "loss": 0.2424, "lr": 3.876975474715656e-06, "epoch": 0.956268221574344, "percentage": 31.92, "elapsed_time": "2:38:23", "remaining_time": "5:37:50"} +{"current_steps": 452, "total_steps": 1413, "loss": 0.2841, "lr": 3.872299698263634e-06, "epoch": 0.9583885502252849, "percentage": 31.99, "elapsed_time": "2:38:46", "remaining_time": "5:37:33"} +{"current_steps": 453, "total_steps": 1413, "loss": 0.2141, "lr": 3.867617041102633e-06, "epoch": 0.9605088788762258, "percentage": 32.06, "elapsed_time": "2:39:06", "remaining_time": "5:37:11"} +{"current_steps": 454, "total_steps": 1413, "loss": 0.2419, "lr": 3.862927526711488e-06, "epoch": 0.9626292075271667, "percentage": 32.13, "elapsed_time": "2:39:28", "remaining_time": "5:36:52"} +{"current_steps": 455, "total_steps": 1413, "loss": 0.2179, "lr": 3.858231178603421e-06, "epoch": 0.9647495361781077, "percentage": 32.2, "elapsed_time": "2:39:52", "remaining_time": "5:36:36"} +{"current_steps": 456, "total_steps": 1413, "loss": 0.2963, "lr": 3.853528020325913e-06, "epoch": 0.9668698648290485, "percentage": 32.27, "elapsed_time": "2:40:16", "remaining_time": "5:36:20"} +{"current_steps": 457, "total_steps": 1413, "loss": 0.2386, "lr": 3.848818075460595e-06, "epoch": 0.9689901934799894, "percentage": 32.34, "elapsed_time": "2:40:38", "remaining_time": "5:36:02"} +{"current_steps": 458, "total_steps": 1413, "loss": 0.1932, "lr": 3.8441013676231255e-06, "epoch": 0.9711105221309303, "percentage": 32.41, "elapsed_time": "2:41:01", "remaining_time": "5:35:44"} +{"current_steps": 459, "total_steps": 1413, "loss": 0.2455, "lr": 3.83937792046307e-06, "epoch": 0.9732308507818712, "percentage": 32.48, "elapsed_time": "2:41:22", "remaining_time": "5:35:24"} +{"current_steps": 460, "total_steps": 1413, "loss": 0.2605, "lr": 3.834647757663788e-06, "epoch": 0.9753511794328121, "percentage": 32.55, "elapsed_time": "2:41:44", "remaining_time": "5:35:06"} +{"current_steps": 461, "total_steps": 1413, "loss": 0.26, "lr": 3.829910902942309e-06, "epoch": 0.9774715080837529, "percentage": 32.63, "elapsed_time": "2:42:06", "remaining_time": "5:34:44"} +{"current_steps": 462, "total_steps": 1413, "loss": 0.2549, "lr": 3.825167380049218e-06, "epoch": 0.9795918367346939, "percentage": 32.7, "elapsed_time": "2:42:26", "remaining_time": "5:34:22"} +{"current_steps": 463, "total_steps": 1413, "loss": 0.1391, "lr": 3.820417212768531e-06, "epoch": 0.9817121653856348, "percentage": 32.77, "elapsed_time": "2:42:47", "remaining_time": "5:34:01"} +{"current_steps": 464, "total_steps": 1413, "loss": 0.305, "lr": 3.8156604249175825e-06, "epoch": 0.9838324940365757, "percentage": 32.84, "elapsed_time": "2:43:09", "remaining_time": "5:33:42"} +{"current_steps": 465, "total_steps": 1413, "loss": 0.3457, "lr": 3.810897040346899e-06, "epoch": 0.9859528226875166, "percentage": 32.91, "elapsed_time": "2:43:29", "remaining_time": "5:33:19"} +{"current_steps": 466, "total_steps": 1413, "loss": 0.2261, "lr": 3.8061270829400876e-06, "epoch": 0.9880731513384574, "percentage": 32.98, "elapsed_time": "2:43:49", "remaining_time": "5:32:55"} +{"current_steps": 467, "total_steps": 1413, "loss": 0.2855, "lr": 3.801350576613706e-06, "epoch": 0.9901934799893983, "percentage": 33.05, "elapsed_time": "2:44:11", "remaining_time": "5:32:35"} +{"current_steps": 468, "total_steps": 1413, "loss": 0.1904, "lr": 3.796567545317153e-06, "epoch": 0.9923138086403392, "percentage": 33.12, "elapsed_time": "2:44:31", "remaining_time": "5:32:12"} +{"current_steps": 469, "total_steps": 1413, "loss": 0.2144, "lr": 3.79177801303254e-06, "epoch": 0.9944341372912802, "percentage": 33.19, "elapsed_time": "2:44:54", "remaining_time": "5:31:55"} +{"current_steps": 470, "total_steps": 1413, "loss": 0.1962, "lr": 3.7869820037745773e-06, "epoch": 0.9965544659422211, "percentage": 33.26, "elapsed_time": "2:45:15", "remaining_time": "5:31:33"} +{"current_steps": 471, "total_steps": 1413, "loss": 0.2887, "lr": 3.7821795415904482e-06, "epoch": 0.9986747945931619, "percentage": 33.33, "elapsed_time": "2:45:36", "remaining_time": "5:31:13"} +{"current_steps": 472, "total_steps": 1413, "loss": 0.2933, "lr": 3.777370650559693e-06, "epoch": 1.0015902464882056, "percentage": 33.4, "elapsed_time": "2:45:57", "remaining_time": "5:30:52"} +{"current_steps": 473, "total_steps": 1413, "loss": 0.2159, "lr": 3.772555354794085e-06, "epoch": 1.0037105751391466, "percentage": 33.47, "elapsed_time": "2:46:17", "remaining_time": "5:30:29"} +{"current_steps": 474, "total_steps": 1413, "loss": 0.3206, "lr": 3.7677336784375107e-06, "epoch": 1.0058309037900874, "percentage": 33.55, "elapsed_time": "2:46:39", "remaining_time": "5:30:09"} +{"current_steps": 475, "total_steps": 1413, "loss": 0.2397, "lr": 3.76290564566585e-06, "epoch": 1.0079512324410285, "percentage": 33.62, "elapsed_time": "2:47:00", "remaining_time": "5:29:47"} +{"current_steps": 476, "total_steps": 1413, "loss": 0.2207, "lr": 3.7580712806868536e-06, "epoch": 1.0100715610919693, "percentage": 33.69, "elapsed_time": "2:47:22", "remaining_time": "5:29:27"} +{"current_steps": 477, "total_steps": 1413, "loss": 0.2817, "lr": 3.7532306077400206e-06, "epoch": 1.01219188974291, "percentage": 33.76, "elapsed_time": "2:47:43", "remaining_time": "5:29:08"} +{"current_steps": 478, "total_steps": 1413, "loss": 0.2123, "lr": 3.7483836510964792e-06, "epoch": 1.014312218393851, "percentage": 33.83, "elapsed_time": "2:48:05", "remaining_time": "5:28:48"} +{"current_steps": 479, "total_steps": 1413, "loss": 0.2889, "lr": 3.7435304350588643e-06, "epoch": 1.016432547044792, "percentage": 33.9, "elapsed_time": "2:48:27", "remaining_time": "5:28:27"} +{"current_steps": 480, "total_steps": 1413, "loss": 0.2517, "lr": 3.738670983961195e-06, "epoch": 1.018552875695733, "percentage": 33.97, "elapsed_time": "2:48:48", "remaining_time": "5:28:07"} +{"current_steps": 481, "total_steps": 1413, "loss": 0.2451, "lr": 3.7338053221687533e-06, "epoch": 1.0206732043466737, "percentage": 34.04, "elapsed_time": "2:49:10", "remaining_time": "5:27:47"} +{"current_steps": 482, "total_steps": 1413, "loss": 0.2594, "lr": 3.728933474077961e-06, "epoch": 1.0227935329976146, "percentage": 34.11, "elapsed_time": "2:49:30", "remaining_time": "5:27:24"} +{"current_steps": 483, "total_steps": 1413, "loss": 0.2706, "lr": 3.7240554641162585e-06, "epoch": 1.0249138616485556, "percentage": 34.18, "elapsed_time": "2:49:51", "remaining_time": "5:27:03"} +{"current_steps": 484, "total_steps": 1413, "loss": 0.2099, "lr": 3.7191713167419814e-06, "epoch": 1.0270341902994964, "percentage": 34.25, "elapsed_time": "2:50:13", "remaining_time": "5:26:43"} +{"current_steps": 485, "total_steps": 1413, "loss": 0.3406, "lr": 3.7142810564442388e-06, "epoch": 1.0291545189504374, "percentage": 34.32, "elapsed_time": "2:50:33", "remaining_time": "5:26:21"} +{"current_steps": 486, "total_steps": 1413, "loss": 0.2251, "lr": 3.7093847077427904e-06, "epoch": 1.0312748476013782, "percentage": 34.39, "elapsed_time": "2:50:55", "remaining_time": "5:26:00"} +{"current_steps": 487, "total_steps": 1413, "loss": 0.1466, "lr": 3.7044822951879224e-06, "epoch": 1.033395176252319, "percentage": 34.47, "elapsed_time": "2:51:16", "remaining_time": "5:25:40"} +{"current_steps": 488, "total_steps": 1413, "loss": 0.3749, "lr": 3.6995738433603234e-06, "epoch": 1.03551550490326, "percentage": 34.54, "elapsed_time": "2:51:37", "remaining_time": "5:25:18"} +{"current_steps": 489, "total_steps": 1413, "loss": 0.2145, "lr": 3.6946593768709667e-06, "epoch": 1.0376358335542009, "percentage": 34.61, "elapsed_time": "2:51:58", "remaining_time": "5:24:57"} +{"current_steps": 490, "total_steps": 1413, "loss": 0.1499, "lr": 3.68973892036098e-06, "epoch": 1.0397561622051419, "percentage": 34.68, "elapsed_time": "2:52:18", "remaining_time": "5:24:34"} +{"current_steps": 491, "total_steps": 1413, "loss": 0.2445, "lr": 3.684812498501528e-06, "epoch": 1.0418764908560827, "percentage": 34.75, "elapsed_time": "2:52:39", "remaining_time": "5:24:13"} +{"current_steps": 492, "total_steps": 1413, "loss": 0.2568, "lr": 3.6798801359936808e-06, "epoch": 1.0439968195070235, "percentage": 34.82, "elapsed_time": "2:53:00", "remaining_time": "5:23:51"} +{"current_steps": 493, "total_steps": 1413, "loss": 0.1574, "lr": 3.6749418575683005e-06, "epoch": 1.0461171481579645, "percentage": 34.89, "elapsed_time": "2:53:23", "remaining_time": "5:23:34"} +{"current_steps": 494, "total_steps": 1413, "loss": 0.2175, "lr": 3.669997687985908e-06, "epoch": 1.0482374768089053, "percentage": 34.96, "elapsed_time": "2:53:44", "remaining_time": "5:23:12"} +{"current_steps": 495, "total_steps": 1413, "loss": 0.2276, "lr": 3.665047652036563e-06, "epoch": 1.0503578054598464, "percentage": 35.03, "elapsed_time": "2:54:04", "remaining_time": "5:22:50"} +{"current_steps": 496, "total_steps": 1413, "loss": 0.1829, "lr": 3.6600917745397403e-06, "epoch": 1.0524781341107872, "percentage": 35.1, "elapsed_time": "2:54:25", "remaining_time": "5:22:28"} +{"current_steps": 497, "total_steps": 1413, "loss": 0.1972, "lr": 3.6551300803442035e-06, "epoch": 1.054598462761728, "percentage": 35.17, "elapsed_time": "2:54:47", "remaining_time": "5:22:09"} +{"current_steps": 498, "total_steps": 1413, "loss": 0.1839, "lr": 3.650162594327881e-06, "epoch": 1.056718791412669, "percentage": 35.24, "elapsed_time": "2:55:08", "remaining_time": "5:21:47"} +{"current_steps": 499, "total_steps": 1413, "loss": 0.2619, "lr": 3.6451893413977413e-06, "epoch": 1.0588391200636098, "percentage": 35.31, "elapsed_time": "2:55:29", "remaining_time": "5:21:26"} +{"current_steps": 500, "total_steps": 1413, "loss": 0.2554, "lr": 3.6402103464896676e-06, "epoch": 1.0609594487145508, "percentage": 35.39, "elapsed_time": "2:55:51", "remaining_time": "5:21:06"} +{"current_steps": 501, "total_steps": 1413, "loss": 0.2435, "lr": 3.6352256345683358e-06, "epoch": 1.0630797773654916, "percentage": 35.46, "elapsed_time": "2:56:11", "remaining_time": "5:20:44"} +{"current_steps": 502, "total_steps": 1413, "loss": 0.2017, "lr": 3.630235230627085e-06, "epoch": 1.0652001060164324, "percentage": 35.53, "elapsed_time": "2:56:33", "remaining_time": "5:20:24"} +{"current_steps": 503, "total_steps": 1413, "loss": 0.2504, "lr": 3.6252391596877923e-06, "epoch": 1.0673204346673735, "percentage": 35.6, "elapsed_time": "2:56:52", "remaining_time": "5:20:00"} +{"current_steps": 504, "total_steps": 1413, "loss": 0.2066, "lr": 3.620237446800754e-06, "epoch": 1.0694407633183143, "percentage": 35.67, "elapsed_time": "2:57:13", "remaining_time": "5:19:38"} +{"current_steps": 505, "total_steps": 1413, "loss": 0.3272, "lr": 3.615230117044551e-06, "epoch": 1.0715610919692553, "percentage": 35.74, "elapsed_time": "2:57:33", "remaining_time": "5:19:15"} +{"current_steps": 506, "total_steps": 1413, "loss": 0.1846, "lr": 3.610217195525928e-06, "epoch": 1.0736814206201961, "percentage": 35.81, "elapsed_time": "2:57:54", "remaining_time": "5:18:54"} +{"current_steps": 507, "total_steps": 1413, "loss": 0.1817, "lr": 3.6051987073796684e-06, "epoch": 1.075801749271137, "percentage": 35.88, "elapsed_time": "2:58:16", "remaining_time": "5:18:34"} +{"current_steps": 508, "total_steps": 1413, "loss": 0.1909, "lr": 3.600174677768465e-06, "epoch": 1.077922077922078, "percentage": 35.95, "elapsed_time": "2:58:38", "remaining_time": "5:18:14"} +{"current_steps": 509, "total_steps": 1413, "loss": 0.2923, "lr": 3.595145131882795e-06, "epoch": 1.0800424065730188, "percentage": 36.02, "elapsed_time": "2:58:58", "remaining_time": "5:17:51"} +{"current_steps": 510, "total_steps": 1413, "loss": 0.1405, "lr": 3.5901100949407967e-06, "epoch": 1.0821627352239598, "percentage": 36.09, "elapsed_time": "2:59:19", "remaining_time": "5:17:29"} +{"current_steps": 511, "total_steps": 1413, "loss": 0.1853, "lr": 3.5850695921881383e-06, "epoch": 1.0842830638749006, "percentage": 36.16, "elapsed_time": "2:59:39", "remaining_time": "5:17:08"} +{"current_steps": 512, "total_steps": 1413, "loss": 0.1181, "lr": 3.5800236488978946e-06, "epoch": 1.0864033925258414, "percentage": 36.23, "elapsed_time": "2:59:59", "remaining_time": "5:16:45"} +{"current_steps": 513, "total_steps": 1413, "loss": 0.2086, "lr": 3.574972290370419e-06, "epoch": 1.0885237211767824, "percentage": 36.31, "elapsed_time": "3:00:20", "remaining_time": "5:16:23"} +{"current_steps": 514, "total_steps": 1413, "loss": 0.202, "lr": 3.569915541933217e-06, "epoch": 1.0906440498277232, "percentage": 36.38, "elapsed_time": "3:00:43", "remaining_time": "5:16:05"} +{"current_steps": 515, "total_steps": 1413, "loss": 0.1522, "lr": 3.564853428940819e-06, "epoch": 1.0927643784786643, "percentage": 36.45, "elapsed_time": "3:01:04", "remaining_time": "5:15:44"} +{"current_steps": 516, "total_steps": 1413, "loss": 0.1442, "lr": 3.5597859767746524e-06, "epoch": 1.094884707129605, "percentage": 36.52, "elapsed_time": "3:01:26", "remaining_time": "5:15:24"} +{"current_steps": 517, "total_steps": 1413, "loss": 0.2109, "lr": 3.5547132108429163e-06, "epoch": 1.0970050357805459, "percentage": 36.59, "elapsed_time": "3:01:47", "remaining_time": "5:15:03"} +{"current_steps": 518, "total_steps": 1413, "loss": 0.2269, "lr": 3.5496351565804542e-06, "epoch": 1.099125364431487, "percentage": 36.66, "elapsed_time": "3:02:09", "remaining_time": "5:14:44"} +{"current_steps": 519, "total_steps": 1413, "loss": 0.2547, "lr": 3.5445518394486215e-06, "epoch": 1.1012456930824277, "percentage": 36.73, "elapsed_time": "3:02:31", "remaining_time": "5:14:24"} +{"current_steps": 520, "total_steps": 1413, "loss": 0.1796, "lr": 3.5394632849351663e-06, "epoch": 1.1033660217333687, "percentage": 36.8, "elapsed_time": "3:02:53", "remaining_time": "5:14:04"} +{"current_steps": 521, "total_steps": 1413, "loss": 0.1957, "lr": 3.5343695185540927e-06, "epoch": 1.1054863503843095, "percentage": 36.87, "elapsed_time": "3:03:14", "remaining_time": "5:13:43"} +{"current_steps": 522, "total_steps": 1413, "loss": 0.2102, "lr": 3.5292705658455406e-06, "epoch": 1.1076066790352506, "percentage": 36.94, "elapsed_time": "3:03:35", "remaining_time": "5:13:22"} +{"current_steps": 523, "total_steps": 1413, "loss": 0.1964, "lr": 3.524166452375652e-06, "epoch": 1.1097270076861914, "percentage": 37.01, "elapsed_time": "3:03:56", "remaining_time": "5:13:00"} +{"current_steps": 524, "total_steps": 1413, "loss": 0.2761, "lr": 3.5190572037364445e-06, "epoch": 1.1118473363371322, "percentage": 37.08, "elapsed_time": "3:04:17", "remaining_time": "5:12:39"} +{"current_steps": 525, "total_steps": 1413, "loss": 0.1444, "lr": 3.513942845545686e-06, "epoch": 1.1139676649880732, "percentage": 37.15, "elapsed_time": "3:04:37", "remaining_time": "5:12:17"} +{"current_steps": 526, "total_steps": 1413, "loss": 0.2643, "lr": 3.5088234034467604e-06, "epoch": 1.116087993639014, "percentage": 37.23, "elapsed_time": "3:04:59", "remaining_time": "5:11:58"} +{"current_steps": 527, "total_steps": 1413, "loss": 0.1631, "lr": 3.5036989031085455e-06, "epoch": 1.118208322289955, "percentage": 37.3, "elapsed_time": "3:05:20", "remaining_time": "5:11:35"} +{"current_steps": 528, "total_steps": 1413, "loss": 0.2681, "lr": 3.498569370225279e-06, "epoch": 1.1203286509408958, "percentage": 37.37, "elapsed_time": "3:05:40", "remaining_time": "5:11:13"} +{"current_steps": 529, "total_steps": 1413, "loss": 0.2678, "lr": 3.4934348305164324e-06, "epoch": 1.1224489795918366, "percentage": 37.44, "elapsed_time": "3:06:01", "remaining_time": "5:10:51"} +{"current_steps": 530, "total_steps": 1413, "loss": 0.207, "lr": 3.4882953097265814e-06, "epoch": 1.1245693082427777, "percentage": 37.51, "elapsed_time": "3:06:22", "remaining_time": "5:10:31"} +{"current_steps": 531, "total_steps": 1413, "loss": 0.205, "lr": 3.4831508336252766e-06, "epoch": 1.1266896368937185, "percentage": 37.58, "elapsed_time": "3:06:43", "remaining_time": "5:10:09"} +{"current_steps": 532, "total_steps": 1413, "loss": 0.1029, "lr": 3.4780014280069153e-06, "epoch": 1.1288099655446595, "percentage": 37.65, "elapsed_time": "3:07:05", "remaining_time": "5:09:50"} +{"current_steps": 533, "total_steps": 1413, "loss": 0.2622, "lr": 3.472847118690611e-06, "epoch": 1.1309302941956003, "percentage": 37.72, "elapsed_time": "3:07:26", "remaining_time": "5:09:27"} +{"current_steps": 534, "total_steps": 1413, "loss": 0.1952, "lr": 3.467687931520064e-06, "epoch": 1.1330506228465411, "percentage": 37.79, "elapsed_time": "3:07:47", "remaining_time": "5:09:07"} +{"current_steps": 535, "total_steps": 1413, "loss": 0.1626, "lr": 3.462523892363432e-06, "epoch": 1.1351709514974822, "percentage": 37.86, "elapsed_time": "3:08:09", "remaining_time": "5:08:46"} +{"current_steps": 536, "total_steps": 1413, "loss": 0.2611, "lr": 3.4573550271132e-06, "epoch": 1.137291280148423, "percentage": 37.93, "elapsed_time": "3:08:30", "remaining_time": "5:08:26"} +{"current_steps": 537, "total_steps": 1413, "loss": 0.1755, "lr": 3.4521813616860545e-06, "epoch": 1.139411608799364, "percentage": 38.0, "elapsed_time": "3:08:51", "remaining_time": "5:08:04"} +{"current_steps": 538, "total_steps": 1413, "loss": 0.299, "lr": 3.4470029220227445e-06, "epoch": 1.1415319374503048, "percentage": 38.08, "elapsed_time": "3:09:12", "remaining_time": "5:07:44"} +{"current_steps": 539, "total_steps": 1413, "loss": 0.1295, "lr": 3.441819734087963e-06, "epoch": 1.1436522661012458, "percentage": 38.15, "elapsed_time": "3:09:32", "remaining_time": "5:07:21"} +{"current_steps": 540, "total_steps": 1413, "loss": 0.1765, "lr": 3.4366318238702063e-06, "epoch": 1.1457725947521866, "percentage": 38.22, "elapsed_time": "3:09:55", "remaining_time": "5:07:02"} +{"current_steps": 541, "total_steps": 1413, "loss": 0.1285, "lr": 3.4314392173816495e-06, "epoch": 1.1478929234031274, "percentage": 38.29, "elapsed_time": "3:10:15", "remaining_time": "5:06:39"} +{"current_steps": 542, "total_steps": 1413, "loss": 0.3035, "lr": 3.426241940658015e-06, "epoch": 1.1500132520540685, "percentage": 38.36, "elapsed_time": "3:10:34", "remaining_time": "5:06:15"} +{"current_steps": 543, "total_steps": 1413, "loss": 0.2073, "lr": 3.421040019758443e-06, "epoch": 1.1521335807050093, "percentage": 38.43, "elapsed_time": "3:10:57", "remaining_time": "5:05:56"} +{"current_steps": 544, "total_steps": 1413, "loss": 0.1855, "lr": 3.4158334807653577e-06, "epoch": 1.1542539093559503, "percentage": 38.5, "elapsed_time": "3:11:17", "remaining_time": "5:05:34"} +{"current_steps": 545, "total_steps": 1413, "loss": 0.2083, "lr": 3.4106223497843395e-06, "epoch": 1.156374238006891, "percentage": 38.57, "elapsed_time": "3:11:37", "remaining_time": "5:05:12"} +{"current_steps": 546, "total_steps": 1413, "loss": 0.2057, "lr": 3.4054066529439916e-06, "epoch": 1.158494566657832, "percentage": 38.64, "elapsed_time": "3:11:58", "remaining_time": "5:04:51"} +{"current_steps": 547, "total_steps": 1413, "loss": 0.2622, "lr": 3.4001864163958125e-06, "epoch": 1.160614895308773, "percentage": 38.71, "elapsed_time": "3:12:21", "remaining_time": "5:04:32"} +{"current_steps": 548, "total_steps": 1413, "loss": 0.2356, "lr": 3.394961666314061e-06, "epoch": 1.1627352239597137, "percentage": 38.78, "elapsed_time": "3:12:43", "remaining_time": "5:04:12"} +{"current_steps": 549, "total_steps": 1413, "loss": 0.2543, "lr": 3.389732428895629e-06, "epoch": 1.1648555526106548, "percentage": 38.85, "elapsed_time": "3:13:04", "remaining_time": "5:03:51"} +{"current_steps": 550, "total_steps": 1413, "loss": 0.1877, "lr": 3.384498730359905e-06, "epoch": 1.1669758812615956, "percentage": 38.92, "elapsed_time": "3:13:25", "remaining_time": "5:03:29"} +{"current_steps": 551, "total_steps": 1413, "loss": 0.2394, "lr": 3.379260596948646e-06, "epoch": 1.1690962099125364, "percentage": 39.0, "elapsed_time": "3:13:47", "remaining_time": "5:03:10"} +{"current_steps": 552, "total_steps": 1413, "loss": 0.251, "lr": 3.3740180549258496e-06, "epoch": 1.1712165385634774, "percentage": 39.07, "elapsed_time": "3:14:09", "remaining_time": "5:02:49"} +{"current_steps": 553, "total_steps": 1413, "loss": 0.1074, "lr": 3.368771130577613e-06, "epoch": 1.1733368672144182, "percentage": 39.14, "elapsed_time": "3:14:31", "remaining_time": "5:02:30"} +{"current_steps": 554, "total_steps": 1413, "loss": 0.1926, "lr": 3.363519850212007e-06, "epoch": 1.1754571958653592, "percentage": 39.21, "elapsed_time": "3:14:53", "remaining_time": "5:02:11"} +{"current_steps": 555, "total_steps": 1413, "loss": 0.1456, "lr": 3.358264240158947e-06, "epoch": 1.1775775245163, "percentage": 39.28, "elapsed_time": "3:15:14", "remaining_time": "5:01:49"} +{"current_steps": 556, "total_steps": 1413, "loss": 0.2445, "lr": 3.353004326770055e-06, "epoch": 1.1796978531672409, "percentage": 39.35, "elapsed_time": "3:15:35", "remaining_time": "5:01:29"} +{"current_steps": 557, "total_steps": 1413, "loss": 0.2098, "lr": 3.347740136418529e-06, "epoch": 1.1818181818181819, "percentage": 39.42, "elapsed_time": "3:15:56", "remaining_time": "5:01:07"} +{"current_steps": 558, "total_steps": 1413, "loss": 0.2096, "lr": 3.342471695499014e-06, "epoch": 1.1839385104691227, "percentage": 39.49, "elapsed_time": "3:16:17", "remaining_time": "5:00:46"} +{"current_steps": 559, "total_steps": 1413, "loss": 0.2537, "lr": 3.3371990304274654e-06, "epoch": 1.1860588391200637, "percentage": 39.56, "elapsed_time": "3:16:39", "remaining_time": "5:00:26"} +{"current_steps": 560, "total_steps": 1413, "loss": 0.1266, "lr": 3.33192216764102e-06, "epoch": 1.1881791677710045, "percentage": 39.63, "elapsed_time": "3:17:01", "remaining_time": "5:00:05"} +{"current_steps": 561, "total_steps": 1413, "loss": 0.2436, "lr": 3.3266411335978618e-06, "epoch": 1.1902994964219453, "percentage": 39.7, "elapsed_time": "3:17:22", "remaining_time": "4:59:45"} +{"current_steps": 562, "total_steps": 1413, "loss": 0.272, "lr": 3.3213559547770873e-06, "epoch": 1.1924198250728864, "percentage": 39.77, "elapsed_time": "3:17:43", "remaining_time": "4:59:24"} +{"current_steps": 563, "total_steps": 1413, "loss": 0.1754, "lr": 3.316066657678577e-06, "epoch": 1.1945401537238272, "percentage": 39.84, "elapsed_time": "3:18:04", "remaining_time": "4:59:03"} +{"current_steps": 564, "total_steps": 1413, "loss": 0.2089, "lr": 3.310773268822861e-06, "epoch": 1.1966604823747682, "percentage": 39.92, "elapsed_time": "3:18:26", "remaining_time": "4:58:43"} +{"current_steps": 565, "total_steps": 1413, "loss": 0.1492, "lr": 3.3054758147509837e-06, "epoch": 1.198780811025709, "percentage": 39.99, "elapsed_time": "3:18:46", "remaining_time": "4:58:20"} +{"current_steps": 566, "total_steps": 1413, "loss": 0.1841, "lr": 3.300174322024373e-06, "epoch": 1.2009011396766498, "percentage": 40.06, "elapsed_time": "3:19:07", "remaining_time": "4:57:59"} +{"current_steps": 567, "total_steps": 1413, "loss": 0.1904, "lr": 3.294868817224707e-06, "epoch": 1.2030214683275908, "percentage": 40.13, "elapsed_time": "3:19:29", "remaining_time": "4:57:39"} +{"current_steps": 568, "total_steps": 1413, "loss": 0.2079, "lr": 3.2895593269537806e-06, "epoch": 1.2051417969785316, "percentage": 40.2, "elapsed_time": "3:19:51", "remaining_time": "4:57:19"} +{"current_steps": 569, "total_steps": 1413, "loss": 0.2065, "lr": 3.284245877833371e-06, "epoch": 1.2072621256294727, "percentage": 40.27, "elapsed_time": "3:20:12", "remaining_time": "4:56:57"} +{"current_steps": 570, "total_steps": 1413, "loss": 0.1667, "lr": 3.2789284965051053e-06, "epoch": 1.2093824542804135, "percentage": 40.34, "elapsed_time": "3:20:33", "remaining_time": "4:56:36"} +{"current_steps": 571, "total_steps": 1413, "loss": 0.1957, "lr": 3.2736072096303277e-06, "epoch": 1.2115027829313543, "percentage": 40.41, "elapsed_time": "3:20:54", "remaining_time": "4:56:16"} +{"current_steps": 572, "total_steps": 1413, "loss": 0.1717, "lr": 3.268282043889963e-06, "epoch": 1.2136231115822953, "percentage": 40.48, "elapsed_time": "3:21:16", "remaining_time": "4:55:55"} +{"current_steps": 573, "total_steps": 1413, "loss": 0.2692, "lr": 3.2629530259843862e-06, "epoch": 1.215743440233236, "percentage": 40.55, "elapsed_time": "3:21:37", "remaining_time": "4:55:33"} +{"current_steps": 574, "total_steps": 1413, "loss": 0.223, "lr": 3.2576201826332864e-06, "epoch": 1.2178637688841771, "percentage": 40.62, "elapsed_time": "3:21:57", "remaining_time": "4:55:12"} +{"current_steps": 575, "total_steps": 1413, "loss": 0.2378, "lr": 3.252283540575533e-06, "epoch": 1.219984097535118, "percentage": 40.69, "elapsed_time": "3:22:17", "remaining_time": "4:54:49"} +{"current_steps": 576, "total_steps": 1413, "loss": 0.3113, "lr": 3.2469431265690432e-06, "epoch": 1.2221044261860587, "percentage": 40.76, "elapsed_time": "3:22:40", "remaining_time": "4:54:30"} +{"current_steps": 577, "total_steps": 1413, "loss": 0.2094, "lr": 3.2415989673906454e-06, "epoch": 1.2242247548369998, "percentage": 40.84, "elapsed_time": "3:23:00", "remaining_time": "4:54:08"} +{"current_steps": 578, "total_steps": 1413, "loss": 0.286, "lr": 3.2362510898359484e-06, "epoch": 1.2263450834879406, "percentage": 40.91, "elapsed_time": "3:23:20", "remaining_time": "4:53:46"} +{"current_steps": 579, "total_steps": 1413, "loss": 0.1752, "lr": 3.2308995207192028e-06, "epoch": 1.2284654121388816, "percentage": 40.98, "elapsed_time": "3:23:43", "remaining_time": "4:53:27"} +{"current_steps": 580, "total_steps": 1413, "loss": 0.2184, "lr": 3.225544286873169e-06, "epoch": 1.2305857407898224, "percentage": 41.05, "elapsed_time": "3:24:03", "remaining_time": "4:53:04"} +{"current_steps": 581, "total_steps": 1413, "loss": 0.2721, "lr": 3.220185415148984e-06, "epoch": 1.2327060694407632, "percentage": 41.12, "elapsed_time": "3:24:23", "remaining_time": "4:52:41"} +{"current_steps": 582, "total_steps": 1413, "loss": 0.3589, "lr": 3.2148229324160235e-06, "epoch": 1.2348263980917042, "percentage": 41.19, "elapsed_time": "3:24:44", "remaining_time": "4:52:20"} +{"current_steps": 583, "total_steps": 1413, "loss": 0.2667, "lr": 3.2094568655617692e-06, "epoch": 1.236946726742645, "percentage": 41.26, "elapsed_time": "3:25:05", "remaining_time": "4:51:59"} +{"current_steps": 584, "total_steps": 1413, "loss": 0.2865, "lr": 3.204087241491673e-06, "epoch": 1.239067055393586, "percentage": 41.33, "elapsed_time": "3:25:26", "remaining_time": "4:51:37"} +{"current_steps": 585, "total_steps": 1413, "loss": 0.2693, "lr": 3.198714087129024e-06, "epoch": 1.2411873840445269, "percentage": 41.4, "elapsed_time": "3:25:47", "remaining_time": "4:51:16"} +{"current_steps": 586, "total_steps": 1413, "loss": 0.1966, "lr": 3.1933374294148112e-06, "epoch": 1.2433077126954677, "percentage": 41.47, "elapsed_time": "3:26:08", "remaining_time": "4:50:54"} +{"current_steps": 587, "total_steps": 1413, "loss": 0.1645, "lr": 3.187957295307591e-06, "epoch": 1.2454280413464087, "percentage": 41.54, "elapsed_time": "3:26:29", "remaining_time": "4:50:33"} +{"current_steps": 588, "total_steps": 1413, "loss": 0.2136, "lr": 3.1825737117833465e-06, "epoch": 1.2475483699973495, "percentage": 41.61, "elapsed_time": "3:26:50", "remaining_time": "4:50:12"} +{"current_steps": 589, "total_steps": 1413, "loss": 0.1812, "lr": 3.177186705835361e-06, "epoch": 1.2496686986482906, "percentage": 41.68, "elapsed_time": "3:27:11", "remaining_time": "4:49:51"} +{"current_steps": 590, "total_steps": 1413, "loss": 0.1438, "lr": 3.171796304474074e-06, "epoch": 1.2517890272992314, "percentage": 41.76, "elapsed_time": "3:27:32", "remaining_time": "4:49:30"} +{"current_steps": 591, "total_steps": 1413, "loss": 0.224, "lr": 3.1664025347269533e-06, "epoch": 1.2539093559501722, "percentage": 41.83, "elapsed_time": "3:27:53", "remaining_time": "4:49:09"} +{"current_steps": 592, "total_steps": 1413, "loss": 0.1427, "lr": 3.1610054236383526e-06, "epoch": 1.2560296846011132, "percentage": 41.9, "elapsed_time": "3:28:13", "remaining_time": "4:48:46"} +{"current_steps": 593, "total_steps": 1413, "loss": 0.3275, "lr": 3.1556049982693794e-06, "epoch": 1.258150013252054, "percentage": 41.97, "elapsed_time": "3:28:35", "remaining_time": "4:48:25"} +{"current_steps": 594, "total_steps": 1413, "loss": 0.228, "lr": 3.1502012856977606e-06, "epoch": 1.260270341902995, "percentage": 42.04, "elapsed_time": "3:28:56", "remaining_time": "4:48:05"} +{"current_steps": 595, "total_steps": 1413, "loss": 0.1597, "lr": 3.144794313017704e-06, "epoch": 1.2623906705539358, "percentage": 42.11, "elapsed_time": "3:29:17", "remaining_time": "4:47:43"} +{"current_steps": 596, "total_steps": 1413, "loss": 0.2749, "lr": 3.1393841073397636e-06, "epoch": 1.2645109992048766, "percentage": 42.18, "elapsed_time": "3:29:37", "remaining_time": "4:47:20"} +{"current_steps": 597, "total_steps": 1413, "loss": 0.2947, "lr": 3.1339706957907058e-06, "epoch": 1.2666313278558177, "percentage": 42.25, "elapsed_time": "3:29:58", "remaining_time": "4:46:59"} +{"current_steps": 598, "total_steps": 1413, "loss": 0.2116, "lr": 3.128554105513367e-06, "epoch": 1.2687516565067585, "percentage": 42.32, "elapsed_time": "3:30:20", "remaining_time": "4:46:39"} +{"current_steps": 599, "total_steps": 1413, "loss": 0.3044, "lr": 3.123134363666525e-06, "epoch": 1.2708719851576995, "percentage": 42.39, "elapsed_time": "3:30:41", "remaining_time": "4:46:18"} +{"current_steps": 600, "total_steps": 1413, "loss": 0.2365, "lr": 3.117711497424759e-06, "epoch": 1.2729923138086403, "percentage": 42.46, "elapsed_time": "3:31:02", "remaining_time": "4:45:57"} +{"current_steps": 601, "total_steps": 1413, "loss": 0.2351, "lr": 3.1122855339783135e-06, "epoch": 1.2751126424595811, "percentage": 42.53, "elapsed_time": "3:31:23", "remaining_time": "4:45:37"} +{"current_steps": 602, "total_steps": 1413, "loss": 0.2982, "lr": 3.106856500532962e-06, "epoch": 1.2772329711105221, "percentage": 42.6, "elapsed_time": "3:31:44", "remaining_time": "4:45:15"} +{"current_steps": 603, "total_steps": 1413, "loss": 0.2545, "lr": 3.1014244243098723e-06, "epoch": 1.279353299761463, "percentage": 42.68, "elapsed_time": "3:32:05", "remaining_time": "4:44:53"} +{"current_steps": 604, "total_steps": 1413, "loss": 0.2081, "lr": 3.0959893325454675e-06, "epoch": 1.281473628412404, "percentage": 42.75, "elapsed_time": "3:32:25", "remaining_time": "4:44:31"} +{"current_steps": 605, "total_steps": 1413, "loss": 0.2386, "lr": 3.09055125249129e-06, "epoch": 1.2835939570633448, "percentage": 42.82, "elapsed_time": "3:32:47", "remaining_time": "4:44:11"} +{"current_steps": 606, "total_steps": 1413, "loss": 0.123, "lr": 3.0851102114138677e-06, "epoch": 1.2857142857142856, "percentage": 42.89, "elapsed_time": "3:33:12", "remaining_time": "4:43:55"} +{"current_steps": 607, "total_steps": 1413, "loss": 0.2888, "lr": 3.079666236594573e-06, "epoch": 1.2878346143652266, "percentage": 42.96, "elapsed_time": "3:33:33", "remaining_time": "4:43:34"} +{"current_steps": 608, "total_steps": 1413, "loss": 0.4641, "lr": 3.0742193553294896e-06, "epoch": 1.2899549430161676, "percentage": 43.03, "elapsed_time": "3:33:57", "remaining_time": "4:43:17"} +{"current_steps": 609, "total_steps": 1413, "loss": 0.1544, "lr": 3.0687695949292724e-06, "epoch": 1.2920752716671084, "percentage": 43.1, "elapsed_time": "3:34:19", "remaining_time": "4:42:56"} +{"current_steps": 610, "total_steps": 1413, "loss": 0.2008, "lr": 3.063316982719014e-06, "epoch": 1.2941956003180493, "percentage": 43.17, "elapsed_time": "3:34:40", "remaining_time": "4:42:36"} +{"current_steps": 611, "total_steps": 1413, "loss": 0.1276, "lr": 3.0578615460381047e-06, "epoch": 1.29631592896899, "percentage": 43.24, "elapsed_time": "3:35:01", "remaining_time": "4:42:14"} +{"current_steps": 612, "total_steps": 1413, "loss": 0.256, "lr": 3.0524033122400974e-06, "epoch": 1.298436257619931, "percentage": 43.31, "elapsed_time": "3:35:23", "remaining_time": "4:41:54"} +{"current_steps": 613, "total_steps": 1413, "loss": 0.2078, "lr": 3.04694230869257e-06, "epoch": 1.3005565862708721, "percentage": 43.38, "elapsed_time": "3:35:43", "remaining_time": "4:41:32"} +{"current_steps": 614, "total_steps": 1413, "loss": 0.2638, "lr": 3.0414785627769884e-06, "epoch": 1.302676914921813, "percentage": 43.45, "elapsed_time": "3:36:04", "remaining_time": "4:41:10"} +{"current_steps": 615, "total_steps": 1413, "loss": 0.1654, "lr": 3.036012101888565e-06, "epoch": 1.3047972435727537, "percentage": 43.52, "elapsed_time": "3:36:24", "remaining_time": "4:40:48"} +{"current_steps": 616, "total_steps": 1413, "loss": 0.1348, "lr": 3.0305429534361304e-06, "epoch": 1.3069175722236945, "percentage": 43.6, "elapsed_time": "3:36:45", "remaining_time": "4:40:26"} +{"current_steps": 617, "total_steps": 1413, "loss": 0.1318, "lr": 3.0250711448419867e-06, "epoch": 1.3090379008746356, "percentage": 43.67, "elapsed_time": "3:37:06", "remaining_time": "4:40:05"} +{"current_steps": 618, "total_steps": 1413, "loss": 0.2081, "lr": 3.0195967035417765e-06, "epoch": 1.3111582295255766, "percentage": 43.74, "elapsed_time": "3:37:27", "remaining_time": "4:39:44"} +{"current_steps": 619, "total_steps": 1413, "loss": 0.1596, "lr": 3.014119656984341e-06, "epoch": 1.3132785581765174, "percentage": 43.81, "elapsed_time": "3:37:47", "remaining_time": "4:39:22"} +{"current_steps": 620, "total_steps": 1413, "loss": 0.2253, "lr": 3.0086400326315853e-06, "epoch": 1.3153988868274582, "percentage": 43.88, "elapsed_time": "3:38:07", "remaining_time": "4:38:59"} +{"current_steps": 621, "total_steps": 1413, "loss": 0.2683, "lr": 3.0031578579583375e-06, "epoch": 1.3175192154783992, "percentage": 43.95, "elapsed_time": "3:38:28", "remaining_time": "4:38:37"} +{"current_steps": 622, "total_steps": 1413, "loss": 0.1977, "lr": 2.9976731604522175e-06, "epoch": 1.31963954412934, "percentage": 44.02, "elapsed_time": "3:38:49", "remaining_time": "4:38:17"} +{"current_steps": 623, "total_steps": 1413, "loss": 0.171, "lr": 2.992185967613489e-06, "epoch": 1.321759872780281, "percentage": 44.09, "elapsed_time": "3:39:10", "remaining_time": "4:37:55"} +{"current_steps": 624, "total_steps": 1413, "loss": 0.2047, "lr": 2.9866963069549315e-06, "epoch": 1.3238802014312219, "percentage": 44.16, "elapsed_time": "3:39:30", "remaining_time": "4:37:33"} +{"current_steps": 625, "total_steps": 1413, "loss": 0.1553, "lr": 2.9812042060016968e-06, "epoch": 1.3260005300821627, "percentage": 44.23, "elapsed_time": "3:39:51", "remaining_time": "4:37:12"} +{"current_steps": 626, "total_steps": 1413, "loss": 0.1797, "lr": 2.975709692291171e-06, "epoch": 1.3281208587331037, "percentage": 44.3, "elapsed_time": "3:40:12", "remaining_time": "4:36:50"} +{"current_steps": 627, "total_steps": 1413, "loss": 0.16, "lr": 2.9702127933728403e-06, "epoch": 1.3302411873840445, "percentage": 44.37, "elapsed_time": "3:40:32", "remaining_time": "4:36:27"} +{"current_steps": 628, "total_steps": 1413, "loss": 0.1923, "lr": 2.9647135368081488e-06, "epoch": 1.3323615160349855, "percentage": 44.44, "elapsed_time": "3:40:53", "remaining_time": "4:36:06"} +{"current_steps": 629, "total_steps": 1413, "loss": 0.3373, "lr": 2.9592119501703607e-06, "epoch": 1.3344818446859263, "percentage": 44.52, "elapsed_time": "3:41:14", "remaining_time": "4:35:45"} +{"current_steps": 630, "total_steps": 1413, "loss": 0.2003, "lr": 2.9537080610444274e-06, "epoch": 1.3366021733368671, "percentage": 44.59, "elapsed_time": "3:41:34", "remaining_time": "4:35:22"} +{"current_steps": 631, "total_steps": 1413, "loss": 0.1736, "lr": 2.9482018970268395e-06, "epoch": 1.3387225019878082, "percentage": 44.66, "elapsed_time": "3:41:55", "remaining_time": "4:35:02"} +{"current_steps": 632, "total_steps": 1413, "loss": 0.2854, "lr": 2.9426934857254975e-06, "epoch": 1.340842830638749, "percentage": 44.73, "elapsed_time": "3:42:16", "remaining_time": "4:34:40"} +{"current_steps": 633, "total_steps": 1413, "loss": 0.1429, "lr": 2.9371828547595695e-06, "epoch": 1.34296315928969, "percentage": 44.8, "elapsed_time": "3:42:36", "remaining_time": "4:34:18"} +{"current_steps": 634, "total_steps": 1413, "loss": 0.1374, "lr": 2.9316700317593507e-06, "epoch": 1.3450834879406308, "percentage": 44.87, "elapsed_time": "3:42:57", "remaining_time": "4:33:57"} +{"current_steps": 635, "total_steps": 1413, "loss": 0.1429, "lr": 2.92615504436613e-06, "epoch": 1.3472038165915716, "percentage": 44.94, "elapsed_time": "3:43:18", "remaining_time": "4:33:35"} +{"current_steps": 636, "total_steps": 1413, "loss": 0.2211, "lr": 2.920637920232047e-06, "epoch": 1.3493241452425127, "percentage": 45.01, "elapsed_time": "3:43:39", "remaining_time": "4:33:14"} +{"current_steps": 637, "total_steps": 1413, "loss": 0.1726, "lr": 2.9151186870199556e-06, "epoch": 1.3514444738934535, "percentage": 45.08, "elapsed_time": "3:44:00", "remaining_time": "4:32:53"} +{"current_steps": 638, "total_steps": 1413, "loss": 0.2319, "lr": 2.9095973724032832e-06, "epoch": 1.3535648025443945, "percentage": 45.15, "elapsed_time": "3:44:23", "remaining_time": "4:32:34"} +{"current_steps": 639, "total_steps": 1413, "loss": 0.2942, "lr": 2.9040740040658954e-06, "epoch": 1.3556851311953353, "percentage": 45.22, "elapsed_time": "3:44:44", "remaining_time": "4:32:13"} +{"current_steps": 640, "total_steps": 1413, "loss": 0.2206, "lr": 2.8985486097019543e-06, "epoch": 1.357805459846276, "percentage": 45.29, "elapsed_time": "3:45:06", "remaining_time": "4:31:53"} +{"current_steps": 641, "total_steps": 1413, "loss": 0.1729, "lr": 2.89302121701578e-06, "epoch": 1.3599257884972171, "percentage": 45.36, "elapsed_time": "3:45:26", "remaining_time": "4:31:30"} +{"current_steps": 642, "total_steps": 1413, "loss": 0.26, "lr": 2.8874918537217118e-06, "epoch": 1.362046117148158, "percentage": 45.44, "elapsed_time": "3:45:47", "remaining_time": "4:31:09"} +{"current_steps": 643, "total_steps": 1413, "loss": 0.1996, "lr": 2.8819605475439716e-06, "epoch": 1.364166445799099, "percentage": 45.51, "elapsed_time": "3:46:09", "remaining_time": "4:30:49"} +{"current_steps": 644, "total_steps": 1413, "loss": 0.1706, "lr": 2.876427326216521e-06, "epoch": 1.3662867744500398, "percentage": 45.58, "elapsed_time": "3:46:31", "remaining_time": "4:30:29"} +{"current_steps": 645, "total_steps": 1413, "loss": 0.2089, "lr": 2.870892217482925e-06, "epoch": 1.3684071031009806, "percentage": 45.65, "elapsed_time": "3:46:51", "remaining_time": "4:30:07"} +{"current_steps": 646, "total_steps": 1413, "loss": 0.3736, "lr": 2.8653552490962122e-06, "epoch": 1.3705274317519216, "percentage": 45.72, "elapsed_time": "3:47:12", "remaining_time": "4:29:45"} +{"current_steps": 647, "total_steps": 1413, "loss": 0.2904, "lr": 2.8598164488187354e-06, "epoch": 1.3726477604028624, "percentage": 45.79, "elapsed_time": "3:47:32", "remaining_time": "4:29:22"} +{"current_steps": 648, "total_steps": 1413, "loss": 0.2265, "lr": 2.8542758444220303e-06, "epoch": 1.3747680890538034, "percentage": 45.86, "elapsed_time": "3:47:53", "remaining_time": "4:29:02"} +{"current_steps": 649, "total_steps": 1413, "loss": 0.2266, "lr": 2.848733463686683e-06, "epoch": 1.3768884177047442, "percentage": 45.93, "elapsed_time": "3:48:15", "remaining_time": "4:28:42"} +{"current_steps": 650, "total_steps": 1413, "loss": 0.1478, "lr": 2.843189334402183e-06, "epoch": 1.379008746355685, "percentage": 46.0, "elapsed_time": "3:48:36", "remaining_time": "4:28:20"} +{"current_steps": 651, "total_steps": 1413, "loss": 0.1831, "lr": 2.837643484366787e-06, "epoch": 1.381129075006626, "percentage": 46.07, "elapsed_time": "3:48:57", "remaining_time": "4:27:59"} +{"current_steps": 652, "total_steps": 1413, "loss": 0.3069, "lr": 2.83209594138738e-06, "epoch": 1.3832494036575669, "percentage": 46.14, "elapsed_time": "3:49:18", "remaining_time": "4:27:38"} +{"current_steps": 653, "total_steps": 1413, "loss": 0.1158, "lr": 2.8265467332793358e-06, "epoch": 1.385369732308508, "percentage": 46.21, "elapsed_time": "3:49:39", "remaining_time": "4:27:17"} +{"current_steps": 654, "total_steps": 1413, "loss": 0.3263, "lr": 2.820995887866378e-06, "epoch": 1.3874900609594487, "percentage": 46.28, "elapsed_time": "3:50:00", "remaining_time": "4:26:56"} +{"current_steps": 655, "total_steps": 1413, "loss": 0.2294, "lr": 2.8154434329804366e-06, "epoch": 1.3896103896103895, "percentage": 46.36, "elapsed_time": "3:50:20", "remaining_time": "4:26:33"} +{"current_steps": 656, "total_steps": 1413, "loss": 0.2063, "lr": 2.8098893964615165e-06, "epoch": 1.3917307182613305, "percentage": 46.43, "elapsed_time": "3:50:40", "remaining_time": "4:26:11"} +{"current_steps": 657, "total_steps": 1413, "loss": 0.2116, "lr": 2.8043338061575464e-06, "epoch": 1.3938510469122714, "percentage": 46.5, "elapsed_time": "3:51:01", "remaining_time": "4:25:50"} +{"current_steps": 658, "total_steps": 1413, "loss": 0.1887, "lr": 2.7987766899242513e-06, "epoch": 1.3959713755632124, "percentage": 46.57, "elapsed_time": "3:51:22", "remaining_time": "4:25:28"} +{"current_steps": 659, "total_steps": 1413, "loss": 0.2322, "lr": 2.7932180756250042e-06, "epoch": 1.3980917042141532, "percentage": 46.64, "elapsed_time": "3:51:43", "remaining_time": "4:25:07"} +{"current_steps": 660, "total_steps": 1413, "loss": 0.1766, "lr": 2.787657991130692e-06, "epoch": 1.400212032865094, "percentage": 46.71, "elapsed_time": "3:52:03", "remaining_time": "4:24:45"} +{"current_steps": 661, "total_steps": 1413, "loss": 0.1912, "lr": 2.7820964643195685e-06, "epoch": 1.402332361516035, "percentage": 46.78, "elapsed_time": "3:52:25", "remaining_time": "4:24:25"} +{"current_steps": 662, "total_steps": 1413, "loss": 0.1987, "lr": 2.7765335230771255e-06, "epoch": 1.4044526901669758, "percentage": 46.85, "elapsed_time": "3:52:46", "remaining_time": "4:24:03"} +{"current_steps": 663, "total_steps": 1413, "loss": 0.1324, "lr": 2.7709691952959406e-06, "epoch": 1.4065730188179169, "percentage": 46.92, "elapsed_time": "3:53:06", "remaining_time": "4:23:41"} +{"current_steps": 664, "total_steps": 1413, "loss": 0.2485, "lr": 2.765403508875548e-06, "epoch": 1.4086933474688577, "percentage": 46.99, "elapsed_time": "3:53:27", "remaining_time": "4:23:20"} +{"current_steps": 665, "total_steps": 1413, "loss": 0.173, "lr": 2.759836491722292e-06, "epoch": 1.4108136761197985, "percentage": 47.06, "elapsed_time": "3:53:48", "remaining_time": "4:22:59"} +{"current_steps": 666, "total_steps": 1413, "loss": 0.1933, "lr": 2.75426817174919e-06, "epoch": 1.4129340047707395, "percentage": 47.13, "elapsed_time": "3:54:09", "remaining_time": "4:22:38"} +{"current_steps": 667, "total_steps": 1413, "loss": 0.1837, "lr": 2.7486985768757905e-06, "epoch": 1.4150543334216803, "percentage": 47.2, "elapsed_time": "3:54:30", "remaining_time": "4:22:16"} +{"current_steps": 668, "total_steps": 1413, "loss": 0.3647, "lr": 2.743127735028037e-06, "epoch": 1.4171746620726213, "percentage": 47.28, "elapsed_time": "3:54:51", "remaining_time": "4:21:55"} +{"current_steps": 669, "total_steps": 1413, "loss": 0.3015, "lr": 2.7375556741381216e-06, "epoch": 1.4192949907235621, "percentage": 47.35, "elapsed_time": "3:55:11", "remaining_time": "4:21:33"} +{"current_steps": 670, "total_steps": 1413, "loss": 0.2581, "lr": 2.731982422144352e-06, "epoch": 1.421415319374503, "percentage": 47.42, "elapsed_time": "3:55:34", "remaining_time": "4:21:14"} +{"current_steps": 671, "total_steps": 1413, "loss": 0.2046, "lr": 2.726408006991006e-06, "epoch": 1.423535648025444, "percentage": 47.49, "elapsed_time": "3:55:55", "remaining_time": "4:20:53"} +{"current_steps": 672, "total_steps": 1413, "loss": 0.2459, "lr": 2.7208324566281946e-06, "epoch": 1.4256559766763848, "percentage": 47.56, "elapsed_time": "3:56:15", "remaining_time": "4:20:31"} +{"current_steps": 673, "total_steps": 1413, "loss": 0.2656, "lr": 2.715255799011721e-06, "epoch": 1.4277763053273258, "percentage": 47.63, "elapsed_time": "3:56:36", "remaining_time": "4:20:09"} +{"current_steps": 674, "total_steps": 1413, "loss": 0.1731, "lr": 2.7096780621029386e-06, "epoch": 1.4298966339782666, "percentage": 47.7, "elapsed_time": "3:56:57", "remaining_time": "4:19:48"} +{"current_steps": 675, "total_steps": 1413, "loss": 0.3142, "lr": 2.7040992738686135e-06, "epoch": 1.4320169626292074, "percentage": 47.77, "elapsed_time": "3:57:18", "remaining_time": "4:19:27"} +{"current_steps": 676, "total_steps": 1413, "loss": 0.1379, "lr": 2.6985194622807835e-06, "epoch": 1.4341372912801484, "percentage": 47.84, "elapsed_time": "3:57:39", "remaining_time": "4:19:05"} +{"current_steps": 677, "total_steps": 1413, "loss": 0.2351, "lr": 2.6929386553166165e-06, "epoch": 1.4362576199310892, "percentage": 47.91, "elapsed_time": "3:58:00", "remaining_time": "4:18:44"} +{"current_steps": 678, "total_steps": 1413, "loss": 0.0984, "lr": 2.687356880958271e-06, "epoch": 1.4383779485820303, "percentage": 47.98, "elapsed_time": "3:58:21", "remaining_time": "4:18:24"} +{"current_steps": 679, "total_steps": 1413, "loss": 0.1528, "lr": 2.6817741671927587e-06, "epoch": 1.440498277232971, "percentage": 48.05, "elapsed_time": "3:58:42", "remaining_time": "4:18:02"} +{"current_steps": 680, "total_steps": 1413, "loss": 0.1678, "lr": 2.676190542011797e-06, "epoch": 1.4426186058839119, "percentage": 48.12, "elapsed_time": "3:59:02", "remaining_time": "4:17:40"} +{"current_steps": 681, "total_steps": 1413, "loss": 0.17, "lr": 2.670606033411678e-06, "epoch": 1.444738934534853, "percentage": 48.2, "elapsed_time": "3:59:24", "remaining_time": "4:17:19"} +{"current_steps": 682, "total_steps": 1413, "loss": 0.2781, "lr": 2.6650206693931184e-06, "epoch": 1.4468592631857937, "percentage": 48.27, "elapsed_time": "3:59:43", "remaining_time": "4:16:57"} +{"current_steps": 683, "total_steps": 1413, "loss": 0.2947, "lr": 2.659434477961129e-06, "epoch": 1.4489795918367347, "percentage": 48.34, "elapsed_time": "4:00:04", "remaining_time": "4:16:35"} +{"current_steps": 684, "total_steps": 1413, "loss": 0.1783, "lr": 2.653847487124865e-06, "epoch": 1.4510999204876756, "percentage": 48.41, "elapsed_time": "4:00:24", "remaining_time": "4:16:13"} +{"current_steps": 685, "total_steps": 1413, "loss": 0.2216, "lr": 2.648259724897492e-06, "epoch": 1.4532202491386164, "percentage": 48.48, "elapsed_time": "4:00:44", "remaining_time": "4:15:51"} +{"current_steps": 686, "total_steps": 1413, "loss": 0.2853, "lr": 2.6426712192960423e-06, "epoch": 1.4553405777895574, "percentage": 48.55, "elapsed_time": "4:01:06", "remaining_time": "4:15:31"} +{"current_steps": 687, "total_steps": 1413, "loss": 0.1873, "lr": 2.637081998341277e-06, "epoch": 1.4574609064404984, "percentage": 48.62, "elapsed_time": "4:01:27", "remaining_time": "4:15:09"} +{"current_steps": 688, "total_steps": 1413, "loss": 0.2065, "lr": 2.631492090057543e-06, "epoch": 1.4595812350914392, "percentage": 48.69, "elapsed_time": "4:01:48", "remaining_time": "4:14:49"} +{"current_steps": 689, "total_steps": 1413, "loss": 0.1938, "lr": 2.6259015224726325e-06, "epoch": 1.46170156374238, "percentage": 48.76, "elapsed_time": "4:02:09", "remaining_time": "4:14:27"} +{"current_steps": 690, "total_steps": 1413, "loss": 0.2258, "lr": 2.6203103236176446e-06, "epoch": 1.4638218923933208, "percentage": 48.83, "elapsed_time": "4:02:29", "remaining_time": "4:14:05"} +{"current_steps": 691, "total_steps": 1413, "loss": 0.2049, "lr": 2.6147185215268446e-06, "epoch": 1.4659422210442619, "percentage": 48.9, "elapsed_time": "4:02:49", "remaining_time": "4:13:43"} +{"current_steps": 692, "total_steps": 1413, "loss": 0.2649, "lr": 2.609126144237519e-06, "epoch": 1.468062549695203, "percentage": 48.97, "elapsed_time": "4:03:11", "remaining_time": "4:13:22"} +{"current_steps": 693, "total_steps": 1413, "loss": 0.2249, "lr": 2.603533219789844e-06, "epoch": 1.4701828783461437, "percentage": 49.04, "elapsed_time": "4:03:31", "remaining_time": "4:13:00"} +{"current_steps": 694, "total_steps": 1413, "loss": 0.2629, "lr": 2.597939776226732e-06, "epoch": 1.4723032069970845, "percentage": 49.12, "elapsed_time": "4:03:52", "remaining_time": "4:12:39"} +{"current_steps": 695, "total_steps": 1413, "loss": 0.1787, "lr": 2.5923458415937048e-06, "epoch": 1.4744235356480253, "percentage": 49.19, "elapsed_time": "4:04:13", "remaining_time": "4:12:18"} +{"current_steps": 696, "total_steps": 1413, "loss": 0.2431, "lr": 2.586751443938742e-06, "epoch": 1.4765438642989663, "percentage": 49.26, "elapsed_time": "4:04:35", "remaining_time": "4:11:58"} +{"current_steps": 697, "total_steps": 1413, "loss": 0.2282, "lr": 2.581156611312148e-06, "epoch": 1.4786641929499074, "percentage": 49.33, "elapsed_time": "4:04:55", "remaining_time": "4:11:36"} +{"current_steps": 698, "total_steps": 1413, "loss": 0.1392, "lr": 2.5755613717664053e-06, "epoch": 1.4807845216008482, "percentage": 49.4, "elapsed_time": "4:05:17", "remaining_time": "4:11:16"} +{"current_steps": 699, "total_steps": 1413, "loss": 0.1325, "lr": 2.5699657533560386e-06, "epoch": 1.482904850251789, "percentage": 49.47, "elapsed_time": "4:05:38", "remaining_time": "4:10:55"} +{"current_steps": 700, "total_steps": 1413, "loss": 0.2908, "lr": 2.5643697841374722e-06, "epoch": 1.48502517890273, "percentage": 49.54, "elapsed_time": "4:05:59", "remaining_time": "4:10:33"} +{"current_steps": 701, "total_steps": 1413, "loss": 0.1575, "lr": 2.5587734921688873e-06, "epoch": 1.4871455075536708, "percentage": 49.61, "elapsed_time": "4:06:20", "remaining_time": "4:10:12"} +{"current_steps": 702, "total_steps": 1413, "loss": 0.2134, "lr": 2.553176905510086e-06, "epoch": 1.4892658362046118, "percentage": 49.68, "elapsed_time": "4:06:41", "remaining_time": "4:09:51"} +{"current_steps": 703, "total_steps": 1413, "loss": 0.1237, "lr": 2.547580052222347e-06, "epoch": 1.4913861648555526, "percentage": 49.75, "elapsed_time": "4:07:04", "remaining_time": "4:09:32"} +{"current_steps": 704, "total_steps": 1413, "loss": 0.2685, "lr": 2.5419829603682857e-06, "epoch": 1.4935064935064934, "percentage": 49.82, "elapsed_time": "4:07:25", "remaining_time": "4:09:11"} +{"current_steps": 705, "total_steps": 1413, "loss": 0.1412, "lr": 2.5363856580117126e-06, "epoch": 1.4956268221574345, "percentage": 49.89, "elapsed_time": "4:07:47", "remaining_time": "4:08:50"} +{"current_steps": 706, "total_steps": 1413, "loss": 0.3377, "lr": 2.5307881732174954e-06, "epoch": 1.4977471508083753, "percentage": 49.96, "elapsed_time": "4:08:08", "remaining_time": "4:08:29"} +{"current_steps": 707, "total_steps": 1413, "loss": 0.2192, "lr": 2.525190534051416e-06, "epoch": 1.4998674794593163, "percentage": 50.04, "elapsed_time": "4:08:29", "remaining_time": "4:08:08"} +{"current_steps": 708, "total_steps": 1413, "loss": 0.2958, "lr": 2.519592768580031e-06, "epoch": 1.5019878081102571, "percentage": 50.11, "elapsed_time": "4:08:50", "remaining_time": "4:07:47"} +{"current_steps": 709, "total_steps": 1413, "loss": 0.2331, "lr": 2.513994904870528e-06, "epoch": 1.504108136761198, "percentage": 50.18, "elapsed_time": "4:09:11", "remaining_time": "4:07:26"} +{"current_steps": 710, "total_steps": 1413, "loss": 0.1968, "lr": 2.5083969709905904e-06, "epoch": 1.5062284654121387, "percentage": 50.25, "elapsed_time": "4:09:34", "remaining_time": "4:07:06"} +{"current_steps": 711, "total_steps": 1413, "loss": 0.2898, "lr": 2.502798995008249e-06, "epoch": 1.5083487940630798, "percentage": 50.32, "elapsed_time": "4:09:54", "remaining_time": "4:06:44"} +{"current_steps": 712, "total_steps": 1413, "loss": 0.1849, "lr": 2.4972010049917513e-06, "epoch": 1.5104691227140208, "percentage": 50.39, "elapsed_time": "4:10:14", "remaining_time": "4:06:22"} +{"current_steps": 713, "total_steps": 1413, "loss": 0.1244, "lr": 2.491603029009411e-06, "epoch": 1.5125894513649616, "percentage": 50.46, "elapsed_time": "4:10:34", "remaining_time": "4:06:00"} +{"current_steps": 714, "total_steps": 1413, "loss": 0.186, "lr": 2.4860050951294723e-06, "epoch": 1.5147097800159024, "percentage": 50.53, "elapsed_time": "4:10:55", "remaining_time": "4:05:39"} +{"current_steps": 715, "total_steps": 1413, "loss": 0.1995, "lr": 2.480407231419969e-06, "epoch": 1.5168301086668432, "percentage": 50.6, "elapsed_time": "4:11:15", "remaining_time": "4:05:17"} +{"current_steps": 716, "total_steps": 1413, "loss": 0.1875, "lr": 2.474809465948584e-06, "epoch": 1.5189504373177842, "percentage": 50.67, "elapsed_time": "4:11:35", "remaining_time": "4:04:55"} +{"current_steps": 717, "total_steps": 1413, "loss": 0.2135, "lr": 2.469211826782506e-06, "epoch": 1.5210707659687253, "percentage": 50.74, "elapsed_time": "4:11:58", "remaining_time": "4:04:35"} +{"current_steps": 718, "total_steps": 1413, "loss": 0.1819, "lr": 2.4636143419882887e-06, "epoch": 1.523191094619666, "percentage": 50.81, "elapsed_time": "4:12:18", "remaining_time": "4:04:13"} +{"current_steps": 719, "total_steps": 1413, "loss": 0.1927, "lr": 2.4580170396317156e-06, "epoch": 1.5253114232706069, "percentage": 50.88, "elapsed_time": "4:12:38", "remaining_time": "4:03:51"} +{"current_steps": 720, "total_steps": 1413, "loss": 0.1666, "lr": 2.452419947777654e-06, "epoch": 1.5274317519215477, "percentage": 50.96, "elapsed_time": "4:12:58", "remaining_time": "4:03:29"} +{"current_steps": 721, "total_steps": 1413, "loss": 0.2549, "lr": 2.4468230944899147e-06, "epoch": 1.5295520805724887, "percentage": 51.03, "elapsed_time": "4:13:19", "remaining_time": "4:03:07"} +{"current_steps": 722, "total_steps": 1413, "loss": 0.1705, "lr": 2.4412265078311135e-06, "epoch": 1.5316724092234297, "percentage": 51.1, "elapsed_time": "4:13:40", "remaining_time": "4:02:47"} +{"current_steps": 723, "total_steps": 1413, "loss": 0.1925, "lr": 2.435630215862529e-06, "epoch": 1.5337927378743705, "percentage": 51.17, "elapsed_time": "4:14:01", "remaining_time": "4:02:25"} +{"current_steps": 724, "total_steps": 1413, "loss": 0.2595, "lr": 2.4300342466439623e-06, "epoch": 1.5359130665253113, "percentage": 51.24, "elapsed_time": "4:14:20", "remaining_time": "4:02:03"} +{"current_steps": 725, "total_steps": 1413, "loss": 0.2232, "lr": 2.424438628233595e-06, "epoch": 1.5380333951762524, "percentage": 51.31, "elapsed_time": "4:14:42", "remaining_time": "4:01:42"} +{"current_steps": 726, "total_steps": 1413, "loss": 0.1417, "lr": 2.418843388687853e-06, "epoch": 1.5401537238271932, "percentage": 51.38, "elapsed_time": "4:15:03", "remaining_time": "4:01:21"} +{"current_steps": 727, "total_steps": 1413, "loss": 0.2102, "lr": 2.4132485560612583e-06, "epoch": 1.5422740524781342, "percentage": 51.45, "elapsed_time": "4:15:24", "remaining_time": "4:01:00"} +{"current_steps": 728, "total_steps": 1413, "loss": 0.1773, "lr": 2.4076541584062965e-06, "epoch": 1.544394381129075, "percentage": 51.52, "elapsed_time": "4:15:45", "remaining_time": "4:00:39"} +{"current_steps": 729, "total_steps": 1413, "loss": 0.2415, "lr": 2.402060223773269e-06, "epoch": 1.5465147097800158, "percentage": 51.59, "elapsed_time": "4:16:06", "remaining_time": "4:00:17"} +{"current_steps": 730, "total_steps": 1413, "loss": 0.2973, "lr": 2.3964667802101574e-06, "epoch": 1.5486350384309568, "percentage": 51.66, "elapsed_time": "4:16:26", "remaining_time": "3:59:55"} +{"current_steps": 731, "total_steps": 1413, "loss": 0.2207, "lr": 2.3908738557624812e-06, "epoch": 1.5507553670818977, "percentage": 51.73, "elapsed_time": "4:16:46", "remaining_time": "3:59:33"} +{"current_steps": 732, "total_steps": 1413, "loss": 0.2319, "lr": 2.385281478473156e-06, "epoch": 1.5528756957328387, "percentage": 51.8, "elapsed_time": "4:17:07", "remaining_time": "3:59:12"} +{"current_steps": 733, "total_steps": 1413, "loss": 0.2266, "lr": 2.379689676382356e-06, "epoch": 1.5549960243837795, "percentage": 51.88, "elapsed_time": "4:17:28", "remaining_time": "3:58:51"} +{"current_steps": 734, "total_steps": 1413, "loss": 0.1672, "lr": 2.3740984775273684e-06, "epoch": 1.5571163530347203, "percentage": 51.95, "elapsed_time": "4:17:50", "remaining_time": "3:58:30"} +{"current_steps": 735, "total_steps": 1413, "loss": 0.2455, "lr": 2.368507909942458e-06, "epoch": 1.5592366816856613, "percentage": 52.02, "elapsed_time": "4:18:10", "remaining_time": "3:58:09"} +{"current_steps": 736, "total_steps": 1413, "loss": 0.1731, "lr": 2.362918001658723e-06, "epoch": 1.5613570103366021, "percentage": 52.09, "elapsed_time": "4:18:31", "remaining_time": "3:57:48"} +{"current_steps": 737, "total_steps": 1413, "loss": 0.182, "lr": 2.3573287807039577e-06, "epoch": 1.5634773389875432, "percentage": 52.16, "elapsed_time": "4:18:54", "remaining_time": "3:57:28"} +{"current_steps": 738, "total_steps": 1413, "loss": 0.2215, "lr": 2.3517402751025083e-06, "epoch": 1.565597667638484, "percentage": 52.23, "elapsed_time": "4:19:14", "remaining_time": "3:57:06"} +{"current_steps": 739, "total_steps": 1413, "loss": 0.1727, "lr": 2.3461525128751364e-06, "epoch": 1.5677179962894248, "percentage": 52.3, "elapsed_time": "4:19:37", "remaining_time": "3:56:47"} +{"current_steps": 740, "total_steps": 1413, "loss": 0.1117, "lr": 2.3405655220388718e-06, "epoch": 1.5698383249403658, "percentage": 52.37, "elapsed_time": "4:19:56", "remaining_time": "3:56:24"} +{"current_steps": 741, "total_steps": 1413, "loss": 0.2172, "lr": 2.334979330606882e-06, "epoch": 1.5719586535913066, "percentage": 52.44, "elapsed_time": "4:20:16", "remaining_time": "3:56:02"} +{"current_steps": 742, "total_steps": 1413, "loss": 0.1758, "lr": 2.3293939665883233e-06, "epoch": 1.5740789822422476, "percentage": 52.51, "elapsed_time": "4:20:38", "remaining_time": "3:55:41"} +{"current_steps": 743, "total_steps": 1413, "loss": 0.1564, "lr": 2.3238094579882037e-06, "epoch": 1.5761993108931884, "percentage": 52.58, "elapsed_time": "4:20:59", "remaining_time": "3:55:21"} +{"current_steps": 744, "total_steps": 1413, "loss": 0.2507, "lr": 2.318225832807242e-06, "epoch": 1.5783196395441292, "percentage": 52.65, "elapsed_time": "4:21:21", "remaining_time": "3:55:00"} +{"current_steps": 745, "total_steps": 1413, "loss": 0.2025, "lr": 2.3126431190417294e-06, "epoch": 1.5804399681950703, "percentage": 52.72, "elapsed_time": "4:21:41", "remaining_time": "3:54:38"} +{"current_steps": 746, "total_steps": 1413, "loss": 0.2627, "lr": 2.3070613446833843e-06, "epoch": 1.5825602968460113, "percentage": 52.8, "elapsed_time": "4:22:02", "remaining_time": "3:54:17"} +{"current_steps": 747, "total_steps": 1413, "loss": 0.1475, "lr": 2.3014805377192173e-06, "epoch": 1.584680625496952, "percentage": 52.87, "elapsed_time": "4:22:23", "remaining_time": "3:53:56"} +{"current_steps": 748, "total_steps": 1413, "loss": 0.1478, "lr": 2.2959007261313865e-06, "epoch": 1.586800954147893, "percentage": 52.94, "elapsed_time": "4:22:45", "remaining_time": "3:53:36"} +{"current_steps": 749, "total_steps": 1413, "loss": 0.169, "lr": 2.2903219378970623e-06, "epoch": 1.5889212827988337, "percentage": 53.01, "elapsed_time": "4:23:06", "remaining_time": "3:53:14"} +{"current_steps": 750, "total_steps": 1413, "loss": 0.2719, "lr": 2.2847442009882805e-06, "epoch": 1.5910416114497747, "percentage": 53.08, "elapsed_time": "4:23:26", "remaining_time": "3:52:53"} +{"current_steps": 751, "total_steps": 1413, "loss": 0.1815, "lr": 2.2791675433718058e-06, "epoch": 1.5931619401007158, "percentage": 53.15, "elapsed_time": "4:23:47", "remaining_time": "3:52:32"} +{"current_steps": 752, "total_steps": 1413, "loss": 0.1354, "lr": 2.273591993008995e-06, "epoch": 1.5952822687516566, "percentage": 53.22, "elapsed_time": "4:24:09", "remaining_time": "3:52:11"} +{"current_steps": 753, "total_steps": 1413, "loss": 0.2361, "lr": 2.268017577855649e-06, "epoch": 1.5974025974025974, "percentage": 53.29, "elapsed_time": "4:24:30", "remaining_time": "3:51:50"} +{"current_steps": 754, "total_steps": 1413, "loss": 0.2273, "lr": 2.262444325861879e-06, "epoch": 1.5995229260535382, "percentage": 53.36, "elapsed_time": "4:24:52", "remaining_time": "3:51:30"} +{"current_steps": 755, "total_steps": 1413, "loss": 0.1695, "lr": 2.2568722649719637e-06, "epoch": 1.6016432547044792, "percentage": 53.43, "elapsed_time": "4:25:13", "remaining_time": "3:51:09"} +{"current_steps": 756, "total_steps": 1413, "loss": 0.2105, "lr": 2.25130142312421e-06, "epoch": 1.6037635833554202, "percentage": 53.5, "elapsed_time": "4:25:34", "remaining_time": "3:50:47"} +{"current_steps": 757, "total_steps": 1413, "loss": 0.2822, "lr": 2.2457318282508105e-06, "epoch": 1.605883912006361, "percentage": 53.57, "elapsed_time": "4:25:55", "remaining_time": "3:50:26"} +{"current_steps": 758, "total_steps": 1413, "loss": 0.2802, "lr": 2.2401635082777086e-06, "epoch": 1.6080042406573019, "percentage": 53.64, "elapsed_time": "4:26:18", "remaining_time": "3:50:06"} +{"current_steps": 759, "total_steps": 1413, "loss": 0.1117, "lr": 2.234596491124452e-06, "epoch": 1.6101245693082427, "percentage": 53.72, "elapsed_time": "4:26:39", "remaining_time": "3:49:45"} +{"current_steps": 760, "total_steps": 1413, "loss": 0.2573, "lr": 2.2290308047040607e-06, "epoch": 1.6122448979591837, "percentage": 53.79, "elapsed_time": "4:27:01", "remaining_time": "3:49:25"} +{"current_steps": 761, "total_steps": 1413, "loss": 0.1806, "lr": 2.2234664769228758e-06, "epoch": 1.6143652266101247, "percentage": 53.86, "elapsed_time": "4:27:23", "remaining_time": "3:49:05"} +{"current_steps": 762, "total_steps": 1413, "loss": 0.1327, "lr": 2.217903535680432e-06, "epoch": 1.6164855552610655, "percentage": 53.93, "elapsed_time": "4:27:43", "remaining_time": "3:48:43"} +{"current_steps": 763, "total_steps": 1413, "loss": 0.1819, "lr": 2.212342008869309e-06, "epoch": 1.6186058839120063, "percentage": 54.0, "elapsed_time": "4:28:04", "remaining_time": "3:48:22"} +{"current_steps": 764, "total_steps": 1413, "loss": 0.1626, "lr": 2.206781924374996e-06, "epoch": 1.6207262125629471, "percentage": 54.07, "elapsed_time": "4:28:25", "remaining_time": "3:48:01"} +{"current_steps": 765, "total_steps": 1413, "loss": 0.2006, "lr": 2.201223310075749e-06, "epoch": 1.6228465412138882, "percentage": 54.14, "elapsed_time": "4:28:48", "remaining_time": "3:47:41"} +{"current_steps": 766, "total_steps": 1413, "loss": 0.1135, "lr": 2.1956661938424544e-06, "epoch": 1.6249668698648292, "percentage": 54.21, "elapsed_time": "4:29:09", "remaining_time": "3:47:20"} +{"current_steps": 767, "total_steps": 1413, "loss": 0.2926, "lr": 2.1901106035384843e-06, "epoch": 1.62708719851577, "percentage": 54.28, "elapsed_time": "4:29:32", "remaining_time": "3:47:00"} +{"current_steps": 768, "total_steps": 1413, "loss": 0.2127, "lr": 2.1845565670195634e-06, "epoch": 1.6292075271667108, "percentage": 54.35, "elapsed_time": "4:29:52", "remaining_time": "3:46:39"} +{"current_steps": 769, "total_steps": 1413, "loss": 0.256, "lr": 2.1790041121336223e-06, "epoch": 1.6313278558176516, "percentage": 54.42, "elapsed_time": "4:30:14", "remaining_time": "3:46:18"} +{"current_steps": 770, "total_steps": 1413, "loss": 0.2511, "lr": 2.173453266720665e-06, "epoch": 1.6334481844685926, "percentage": 54.49, "elapsed_time": "4:30:36", "remaining_time": "3:45:58"} +{"current_steps": 771, "total_steps": 1413, "loss": 0.1786, "lr": 2.1679040586126214e-06, "epoch": 1.6355685131195337, "percentage": 54.56, "elapsed_time": "4:30:56", "remaining_time": "3:45:36"} +{"current_steps": 772, "total_steps": 1413, "loss": 0.2015, "lr": 2.1623565156332145e-06, "epoch": 1.6376888417704745, "percentage": 54.64, "elapsed_time": "4:31:17", "remaining_time": "3:45:15"} +{"current_steps": 773, "total_steps": 1413, "loss": 0.1488, "lr": 2.1568106655978184e-06, "epoch": 1.6398091704214153, "percentage": 54.71, "elapsed_time": "4:31:39", "remaining_time": "3:44:54"} +{"current_steps": 774, "total_steps": 1413, "loss": 0.3628, "lr": 2.1512665363133173e-06, "epoch": 1.641929499072356, "percentage": 54.78, "elapsed_time": "4:32:00", "remaining_time": "3:44:33"} +{"current_steps": 775, "total_steps": 1413, "loss": 0.2429, "lr": 2.14572415557797e-06, "epoch": 1.644049827723297, "percentage": 54.85, "elapsed_time": "4:32:21", "remaining_time": "3:44:12"} +{"current_steps": 776, "total_steps": 1413, "loss": 0.1817, "lr": 2.140183551181266e-06, "epoch": 1.6461701563742381, "percentage": 54.92, "elapsed_time": "4:32:41", "remaining_time": "3:43:50"} +{"current_steps": 777, "total_steps": 1413, "loss": 0.1804, "lr": 2.1346447509037886e-06, "epoch": 1.648290485025179, "percentage": 54.99, "elapsed_time": "4:33:01", "remaining_time": "3:43:29"} +{"current_steps": 778, "total_steps": 1413, "loss": 0.1714, "lr": 2.1291077825170756e-06, "epoch": 1.6504108136761197, "percentage": 55.06, "elapsed_time": "4:33:23", "remaining_time": "3:43:08"} +{"current_steps": 779, "total_steps": 1413, "loss": 0.2376, "lr": 2.1235726737834794e-06, "epoch": 1.6525311423270606, "percentage": 55.13, "elapsed_time": "4:33:44", "remaining_time": "3:42:47"} +{"current_steps": 780, "total_steps": 1413, "loss": 0.1878, "lr": 2.118039452456029e-06, "epoch": 1.6546514709780016, "percentage": 55.2, "elapsed_time": "4:34:05", "remaining_time": "3:42:25"} +{"current_steps": 781, "total_steps": 1413, "loss": 0.2489, "lr": 2.112508146278289e-06, "epoch": 1.6567717996289426, "percentage": 55.27, "elapsed_time": "4:34:26", "remaining_time": "3:42:05"} +{"current_steps": 782, "total_steps": 1413, "loss": 0.1492, "lr": 2.106978782984221e-06, "epoch": 1.6588921282798834, "percentage": 55.34, "elapsed_time": "4:34:46", "remaining_time": "3:41:43"} +{"current_steps": 783, "total_steps": 1413, "loss": 0.1525, "lr": 2.101451390298047e-06, "epoch": 1.6610124569308242, "percentage": 55.41, "elapsed_time": "4:35:07", "remaining_time": "3:41:21"} +{"current_steps": 784, "total_steps": 1413, "loss": 0.2749, "lr": 2.095925995934105e-06, "epoch": 1.663132785581765, "percentage": 55.48, "elapsed_time": "4:35:28", "remaining_time": "3:41:00"} +{"current_steps": 785, "total_steps": 1413, "loss": 0.1183, "lr": 2.0904026275967176e-06, "epoch": 1.665253114232706, "percentage": 55.56, "elapsed_time": "4:35:49", "remaining_time": "3:40:39"} +{"current_steps": 786, "total_steps": 1413, "loss": 0.1484, "lr": 2.084881312980045e-06, "epoch": 1.667373442883647, "percentage": 55.63, "elapsed_time": "4:36:11", "remaining_time": "3:40:19"} +{"current_steps": 787, "total_steps": 1413, "loss": 0.2783, "lr": 2.0793620797679537e-06, "epoch": 1.669493771534588, "percentage": 55.7, "elapsed_time": "4:36:31", "remaining_time": "3:39:57"} +{"current_steps": 788, "total_steps": 1413, "loss": 0.2064, "lr": 2.0738449556338704e-06, "epoch": 1.6716141001855287, "percentage": 55.77, "elapsed_time": "4:36:54", "remaining_time": "3:39:37"} +{"current_steps": 789, "total_steps": 1413, "loss": 0.1742, "lr": 2.0683299682406497e-06, "epoch": 1.6737344288364695, "percentage": 55.84, "elapsed_time": "4:37:15", "remaining_time": "3:39:16"} +{"current_steps": 790, "total_steps": 1413, "loss": 0.2273, "lr": 2.062817145240431e-06, "epoch": 1.6758547574874105, "percentage": 55.91, "elapsed_time": "4:37:37", "remaining_time": "3:38:55"} +{"current_steps": 791, "total_steps": 1413, "loss": 0.2515, "lr": 2.057306514274503e-06, "epoch": 1.6779750861383516, "percentage": 55.98, "elapsed_time": "4:37:58", "remaining_time": "3:38:35"} +{"current_steps": 792, "total_steps": 1413, "loss": 0.2791, "lr": 2.0517981029731613e-06, "epoch": 1.6800954147892924, "percentage": 56.05, "elapsed_time": "4:38:21", "remaining_time": "3:38:15"} +{"current_steps": 793, "total_steps": 1413, "loss": 0.1838, "lr": 2.0462919389555734e-06, "epoch": 1.6822157434402332, "percentage": 56.12, "elapsed_time": "4:38:42", "remaining_time": "3:37:53"} +{"current_steps": 794, "total_steps": 1413, "loss": 0.188, "lr": 2.0407880498296397e-06, "epoch": 1.684336072091174, "percentage": 56.19, "elapsed_time": "4:39:01", "remaining_time": "3:37:31"} +{"current_steps": 795, "total_steps": 1413, "loss": 0.2529, "lr": 2.035286463191852e-06, "epoch": 1.686456400742115, "percentage": 56.26, "elapsed_time": "4:39:22", "remaining_time": "3:37:10"} +{"current_steps": 796, "total_steps": 1413, "loss": 0.1882, "lr": 2.0297872066271606e-06, "epoch": 1.688576729393056, "percentage": 56.33, "elapsed_time": "4:39:44", "remaining_time": "3:36:50"} +{"current_steps": 797, "total_steps": 1413, "loss": 0.2542, "lr": 2.02429030770883e-06, "epoch": 1.6906970580439968, "percentage": 56.4, "elapsed_time": "4:40:06", "remaining_time": "3:36:29"} +{"current_steps": 798, "total_steps": 1413, "loss": 0.2018, "lr": 2.0187957939983045e-06, "epoch": 1.6928173866949376, "percentage": 56.48, "elapsed_time": "4:40:27", "remaining_time": "3:36:08"} +{"current_steps": 799, "total_steps": 1413, "loss": 0.1885, "lr": 2.0133036930450694e-06, "epoch": 1.6949377153458784, "percentage": 56.55, "elapsed_time": "4:40:48", "remaining_time": "3:35:47"} +{"current_steps": 800, "total_steps": 1413, "loss": 0.1909, "lr": 2.0078140323865114e-06, "epoch": 1.6970580439968195, "percentage": 56.62, "elapsed_time": "4:41:09", "remaining_time": "3:35:26"} +{"current_steps": 801, "total_steps": 1413, "loss": 0.1939, "lr": 2.0023268395477833e-06, "epoch": 1.6991783726477605, "percentage": 56.69, "elapsed_time": "4:41:30", "remaining_time": "3:35:04"} +{"current_steps": 802, "total_steps": 1413, "loss": 0.2151, "lr": 1.9968421420416633e-06, "epoch": 1.7012987012987013, "percentage": 56.76, "elapsed_time": "4:41:52", "remaining_time": "3:34:44"} +{"current_steps": 803, "total_steps": 1413, "loss": 0.2121, "lr": 1.991359967368416e-06, "epoch": 1.7034190299496421, "percentage": 56.83, "elapsed_time": "4:42:13", "remaining_time": "3:34:23"} +{"current_steps": 804, "total_steps": 1413, "loss": 0.1356, "lr": 1.9858803430156602e-06, "epoch": 1.7055393586005831, "percentage": 56.9, "elapsed_time": "4:42:34", "remaining_time": "3:34:02"} +{"current_steps": 805, "total_steps": 1413, "loss": 0.1723, "lr": 1.9804032964582243e-06, "epoch": 1.707659687251524, "percentage": 56.97, "elapsed_time": "4:42:56", "remaining_time": "3:33:41"} +{"current_steps": 806, "total_steps": 1413, "loss": 0.2443, "lr": 1.974928855158014e-06, "epoch": 1.709780015902465, "percentage": 57.04, "elapsed_time": "4:43:16", "remaining_time": "3:33:20"} +{"current_steps": 807, "total_steps": 1413, "loss": 0.1573, "lr": 1.96945704656387e-06, "epoch": 1.7119003445534058, "percentage": 57.11, "elapsed_time": "4:43:37", "remaining_time": "3:32:58"} +{"current_steps": 808, "total_steps": 1413, "loss": 0.2239, "lr": 1.9639878981114358e-06, "epoch": 1.7140206732043466, "percentage": 57.18, "elapsed_time": "4:43:58", "remaining_time": "3:32:37"} +{"current_steps": 809, "total_steps": 1413, "loss": 0.1589, "lr": 1.958521437223013e-06, "epoch": 1.7161410018552876, "percentage": 57.25, "elapsed_time": "4:44:18", "remaining_time": "3:32:16"} +{"current_steps": 810, "total_steps": 1413, "loss": 0.1738, "lr": 1.95305769130743e-06, "epoch": 1.7182613305062284, "percentage": 57.32, "elapsed_time": "4:44:40", "remaining_time": "3:31:55"} +{"current_steps": 811, "total_steps": 1413, "loss": 0.1698, "lr": 1.947596687759902e-06, "epoch": 1.7203816591571695, "percentage": 57.4, "elapsed_time": "4:45:02", "remaining_time": "3:31:34"} +{"current_steps": 812, "total_steps": 1413, "loss": 0.1406, "lr": 1.9421384539618957e-06, "epoch": 1.7225019878081103, "percentage": 57.47, "elapsed_time": "4:45:23", "remaining_time": "3:31:14"} +{"current_steps": 813, "total_steps": 1413, "loss": 0.214, "lr": 1.9366830172809877e-06, "epoch": 1.724622316459051, "percentage": 57.54, "elapsed_time": "4:45:44", "remaining_time": "3:30:52"} +{"current_steps": 814, "total_steps": 1413, "loss": 0.1675, "lr": 1.9312304050707293e-06, "epoch": 1.726742645109992, "percentage": 57.61, "elapsed_time": "4:46:05", "remaining_time": "3:30:31"} +{"current_steps": 815, "total_steps": 1413, "loss": 0.1727, "lr": 1.9257806446705116e-06, "epoch": 1.728862973760933, "percentage": 57.68, "elapsed_time": "4:46:26", "remaining_time": "3:30:10"} +{"current_steps": 816, "total_steps": 1413, "loss": 0.2671, "lr": 1.920333763405428e-06, "epoch": 1.730983302411874, "percentage": 57.75, "elapsed_time": "4:46:46", "remaining_time": "3:29:48"} +{"current_steps": 817, "total_steps": 1413, "loss": 0.1879, "lr": 1.914889788586133e-06, "epoch": 1.7331036310628147, "percentage": 57.82, "elapsed_time": "4:47:07", "remaining_time": "3:29:27"} +{"current_steps": 818, "total_steps": 1413, "loss": 0.2305, "lr": 1.909448747508711e-06, "epoch": 1.7352239597137555, "percentage": 57.89, "elapsed_time": "4:47:28", "remaining_time": "3:29:06"} +{"current_steps": 819, "total_steps": 1413, "loss": 0.3013, "lr": 1.9040106674545333e-06, "epoch": 1.7373442883646966, "percentage": 57.96, "elapsed_time": "4:47:49", "remaining_time": "3:28:44"} +{"current_steps": 820, "total_steps": 1413, "loss": 0.145, "lr": 1.898575575690128e-06, "epoch": 1.7394646170156374, "percentage": 58.03, "elapsed_time": "4:48:09", "remaining_time": "3:28:23"} +{"current_steps": 821, "total_steps": 1413, "loss": 0.2027, "lr": 1.8931434994670377e-06, "epoch": 1.7415849456665784, "percentage": 58.1, "elapsed_time": "4:48:30", "remaining_time": "3:28:02"} +{"current_steps": 822, "total_steps": 1413, "loss": 0.1941, "lr": 1.8877144660216867e-06, "epoch": 1.7437052743175192, "percentage": 58.17, "elapsed_time": "4:48:50", "remaining_time": "3:27:40"} +{"current_steps": 823, "total_steps": 1413, "loss": 0.2453, "lr": 1.8822885025752408e-06, "epoch": 1.74582560296846, "percentage": 58.24, "elapsed_time": "4:49:12", "remaining_time": "3:27:20"} +{"current_steps": 824, "total_steps": 1413, "loss": 0.1622, "lr": 1.8768656363334759e-06, "epoch": 1.747945931619401, "percentage": 58.32, "elapsed_time": "4:49:32", "remaining_time": "3:26:58"} +{"current_steps": 825, "total_steps": 1413, "loss": 0.1394, "lr": 1.8714458944866342e-06, "epoch": 1.750066260270342, "percentage": 58.39, "elapsed_time": "4:49:54", "remaining_time": "3:26:37"} +{"current_steps": 826, "total_steps": 1413, "loss": 0.165, "lr": 1.8660293042092953e-06, "epoch": 1.7521865889212829, "percentage": 58.46, "elapsed_time": "4:50:16", "remaining_time": "3:26:17"} +{"current_steps": 827, "total_steps": 1413, "loss": 0.1421, "lr": 1.8606158926602368e-06, "epoch": 1.7543069175722237, "percentage": 58.53, "elapsed_time": "4:50:38", "remaining_time": "3:25:56"} +{"current_steps": 828, "total_steps": 1413, "loss": 0.2401, "lr": 1.8552056869822968e-06, "epoch": 1.7564272462231645, "percentage": 58.6, "elapsed_time": "4:51:00", "remaining_time": "3:25:36"} +{"current_steps": 829, "total_steps": 1413, "loss": 0.2401, "lr": 1.8497987143022405e-06, "epoch": 1.7585475748741055, "percentage": 58.67, "elapsed_time": "4:51:20", "remaining_time": "3:25:14"} +{"current_steps": 830, "total_steps": 1413, "loss": 0.2251, "lr": 1.8443950017306214e-06, "epoch": 1.7606679035250465, "percentage": 58.74, "elapsed_time": "4:51:41", "remaining_time": "3:24:53"} +{"current_steps": 831, "total_steps": 1413, "loss": 0.113, "lr": 1.8389945763616485e-06, "epoch": 1.7627882321759873, "percentage": 58.81, "elapsed_time": "4:52:02", "remaining_time": "3:24:32"} +{"current_steps": 832, "total_steps": 1413, "loss": 0.2415, "lr": 1.8335974652730467e-06, "epoch": 1.7649085608269282, "percentage": 58.88, "elapsed_time": "4:52:23", "remaining_time": "3:24:10"} +{"current_steps": 833, "total_steps": 1413, "loss": 0.2079, "lr": 1.8282036955259258e-06, "epoch": 1.767028889477869, "percentage": 58.95, "elapsed_time": "4:52:44", "remaining_time": "3:23:50"} +{"current_steps": 834, "total_steps": 1413, "loss": 0.2262, "lr": 1.8228132941646404e-06, "epoch": 1.76914921812881, "percentage": 59.02, "elapsed_time": "4:53:05", "remaining_time": "3:23:28"} +{"current_steps": 835, "total_steps": 1413, "loss": 0.2094, "lr": 1.817426288216655e-06, "epoch": 1.771269546779751, "percentage": 59.09, "elapsed_time": "4:53:25", "remaining_time": "3:23:07"} +{"current_steps": 836, "total_steps": 1413, "loss": 0.1674, "lr": 1.8120427046924106e-06, "epoch": 1.7733898754306918, "percentage": 59.16, "elapsed_time": "4:53:46", "remaining_time": "3:22:45"} +{"current_steps": 837, "total_steps": 1413, "loss": 0.255, "lr": 1.8066625705851896e-06, "epoch": 1.7755102040816326, "percentage": 59.24, "elapsed_time": "4:54:05", "remaining_time": "3:22:23"} +{"current_steps": 838, "total_steps": 1413, "loss": 0.1705, "lr": 1.8012859128709766e-06, "epoch": 1.7776305327325734, "percentage": 59.31, "elapsed_time": "4:54:26", "remaining_time": "3:22:02"} +{"current_steps": 839, "total_steps": 1413, "loss": 0.3657, "lr": 1.7959127585083281e-06, "epoch": 1.7797508613835145, "percentage": 59.38, "elapsed_time": "4:54:47", "remaining_time": "3:21:41"} +{"current_steps": 840, "total_steps": 1413, "loss": 0.1641, "lr": 1.7905431344382318e-06, "epoch": 1.7818711900344555, "percentage": 59.45, "elapsed_time": "4:55:08", "remaining_time": "3:21:19"} +{"current_steps": 841, "total_steps": 1413, "loss": 0.2821, "lr": 1.7851770675839771e-06, "epoch": 1.7839915186853963, "percentage": 59.52, "elapsed_time": "4:55:28", "remaining_time": "3:20:58"} +{"current_steps": 842, "total_steps": 1413, "loss": 0.18, "lr": 1.7798145848510162e-06, "epoch": 1.786111847336337, "percentage": 59.59, "elapsed_time": "4:55:49", "remaining_time": "3:20:36"} +{"current_steps": 843, "total_steps": 1413, "loss": 0.2798, "lr": 1.7744557131268312e-06, "epoch": 1.788232175987278, "percentage": 59.66, "elapsed_time": "4:56:09", "remaining_time": "3:20:15"} +{"current_steps": 844, "total_steps": 1413, "loss": 0.2194, "lr": 1.7691004792807976e-06, "epoch": 1.790352504638219, "percentage": 59.73, "elapsed_time": "4:56:30", "remaining_time": "3:19:53"} +{"current_steps": 845, "total_steps": 1413, "loss": 0.1493, "lr": 1.7637489101640526e-06, "epoch": 1.79247283328916, "percentage": 59.8, "elapsed_time": "4:56:51", "remaining_time": "3:19:32"} +{"current_steps": 846, "total_steps": 1413, "loss": 0.1907, "lr": 1.7584010326093554e-06, "epoch": 1.7945931619401008, "percentage": 59.87, "elapsed_time": "4:57:11", "remaining_time": "3:19:11"} +{"current_steps": 847, "total_steps": 1413, "loss": 0.1661, "lr": 1.7530568734309578e-06, "epoch": 1.7967134905910416, "percentage": 59.94, "elapsed_time": "4:57:34", "remaining_time": "3:18:50"} +{"current_steps": 848, "total_steps": 1413, "loss": 0.1454, "lr": 1.747716459424468e-06, "epoch": 1.7988338192419824, "percentage": 60.01, "elapsed_time": "4:57:54", "remaining_time": "3:18:29"} +{"current_steps": 849, "total_steps": 1413, "loss": 0.1912, "lr": 1.7423798173667144e-06, "epoch": 1.8009541478929234, "percentage": 60.08, "elapsed_time": "4:58:15", "remaining_time": "3:18:07"} +{"current_steps": 850, "total_steps": 1413, "loss": 0.1125, "lr": 1.7370469740156146e-06, "epoch": 1.8030744765438644, "percentage": 60.16, "elapsed_time": "4:58:37", "remaining_time": "3:17:47"} +{"current_steps": 851, "total_steps": 1413, "loss": 0.2471, "lr": 1.7317179561100372e-06, "epoch": 1.8051948051948052, "percentage": 60.23, "elapsed_time": "4:58:57", "remaining_time": "3:17:25"} +{"current_steps": 852, "total_steps": 1413, "loss": 0.1341, "lr": 1.726392790369673e-06, "epoch": 1.807315133845746, "percentage": 60.3, "elapsed_time": "4:59:17", "remaining_time": "3:17:04"} +{"current_steps": 853, "total_steps": 1413, "loss": 0.1579, "lr": 1.7210715034948949e-06, "epoch": 1.8094354624966869, "percentage": 60.37, "elapsed_time": "4:59:38", "remaining_time": "3:16:43"} +{"current_steps": 854, "total_steps": 1413, "loss": 0.0722, "lr": 1.7157541221666291e-06, "epoch": 1.8115557911476279, "percentage": 60.44, "elapsed_time": "4:59:59", "remaining_time": "3:16:21"} +{"current_steps": 855, "total_steps": 1413, "loss": 0.1729, "lr": 1.7104406730462203e-06, "epoch": 1.813676119798569, "percentage": 60.51, "elapsed_time": "5:00:19", "remaining_time": "3:16:00"} +{"current_steps": 856, "total_steps": 1413, "loss": 0.1131, "lr": 1.705131182775294e-06, "epoch": 1.8157964484495097, "percentage": 60.58, "elapsed_time": "5:00:40", "remaining_time": "3:15:39"} +{"current_steps": 857, "total_steps": 1413, "loss": 0.1515, "lr": 1.6998256779756279e-06, "epoch": 1.8179167771004505, "percentage": 60.65, "elapsed_time": "5:01:01", "remaining_time": "3:15:17"} +{"current_steps": 858, "total_steps": 1413, "loss": 0.2163, "lr": 1.6945241852490173e-06, "epoch": 1.8200371057513913, "percentage": 60.72, "elapsed_time": "5:01:23", "remaining_time": "3:14:57"} +{"current_steps": 859, "total_steps": 1413, "loss": 0.1602, "lr": 1.6892267311771395e-06, "epoch": 1.8221574344023324, "percentage": 60.79, "elapsed_time": "5:01:43", "remaining_time": "3:14:35"} +{"current_steps": 860, "total_steps": 1413, "loss": 0.2203, "lr": 1.6839333423214235e-06, "epoch": 1.8242777630532734, "percentage": 60.86, "elapsed_time": "5:02:04", "remaining_time": "3:14:14"} +{"current_steps": 861, "total_steps": 1413, "loss": 0.2015, "lr": 1.6786440452229134e-06, "epoch": 1.8263980917042142, "percentage": 60.93, "elapsed_time": "5:02:27", "remaining_time": "3:13:54"} +{"current_steps": 862, "total_steps": 1413, "loss": 0.2026, "lr": 1.673358866402139e-06, "epoch": 1.828518420355155, "percentage": 61.0, "elapsed_time": "5:02:48", "remaining_time": "3:13:33"} +{"current_steps": 863, "total_steps": 1413, "loss": 0.1659, "lr": 1.6680778323589798e-06, "epoch": 1.8306387490060958, "percentage": 61.08, "elapsed_time": "5:03:09", "remaining_time": "3:13:12"} +{"current_steps": 864, "total_steps": 1413, "loss": 0.128, "lr": 1.6628009695725348e-06, "epoch": 1.8327590776570368, "percentage": 61.15, "elapsed_time": "5:03:30", "remaining_time": "3:12:51"} +{"current_steps": 865, "total_steps": 1413, "loss": 0.2637, "lr": 1.657528304500986e-06, "epoch": 1.8348794063079779, "percentage": 61.22, "elapsed_time": "5:03:51", "remaining_time": "3:12:29"} +{"current_steps": 866, "total_steps": 1413, "loss": 0.1259, "lr": 1.6522598635814718e-06, "epoch": 1.8369997349589187, "percentage": 61.29, "elapsed_time": "5:04:11", "remaining_time": "3:12:08"} +{"current_steps": 867, "total_steps": 1413, "loss": 0.2048, "lr": 1.6469956732299463e-06, "epoch": 1.8391200636098595, "percentage": 61.36, "elapsed_time": "5:04:32", "remaining_time": "3:11:47"} +{"current_steps": 868, "total_steps": 1413, "loss": 0.1192, "lr": 1.6417357598410539e-06, "epoch": 1.8412403922608003, "percentage": 61.43, "elapsed_time": "5:04:52", "remaining_time": "3:11:25"} +{"current_steps": 869, "total_steps": 1413, "loss": 0.1157, "lr": 1.636480149787994e-06, "epoch": 1.8433607209117413, "percentage": 61.5, "elapsed_time": "5:05:13", "remaining_time": "3:11:04"} +{"current_steps": 870, "total_steps": 1413, "loss": 0.1635, "lr": 1.6312288694223882e-06, "epoch": 1.8454810495626823, "percentage": 61.57, "elapsed_time": "5:05:34", "remaining_time": "3:10:43"} +{"current_steps": 871, "total_steps": 1413, "loss": 0.234, "lr": 1.6259819450741512e-06, "epoch": 1.8476013782136231, "percentage": 61.64, "elapsed_time": "5:05:54", "remaining_time": "3:10:21"} +{"current_steps": 872, "total_steps": 1413, "loss": 0.1229, "lr": 1.620739403051354e-06, "epoch": 1.849721706864564, "percentage": 61.71, "elapsed_time": "5:06:14", "remaining_time": "3:09:59"} +{"current_steps": 873, "total_steps": 1413, "loss": 0.2016, "lr": 1.6155012696400959e-06, "epoch": 1.8518420355155047, "percentage": 61.78, "elapsed_time": "5:06:35", "remaining_time": "3:09:38"} +{"current_steps": 874, "total_steps": 1413, "loss": 0.2195, "lr": 1.6102675711043719e-06, "epoch": 1.8539623641664458, "percentage": 61.85, "elapsed_time": "5:06:57", "remaining_time": "3:09:17"} +{"current_steps": 875, "total_steps": 1413, "loss": 0.2128, "lr": 1.6050383336859388e-06, "epoch": 1.8560826928173868, "percentage": 61.92, "elapsed_time": "5:07:17", "remaining_time": "3:08:56"} +{"current_steps": 876, "total_steps": 1413, "loss": 0.2381, "lr": 1.599813583604188e-06, "epoch": 1.8582030214683276, "percentage": 62.0, "elapsed_time": "5:07:38", "remaining_time": "3:08:35"} +{"current_steps": 877, "total_steps": 1413, "loss": 0.158, "lr": 1.5945933470560097e-06, "epoch": 1.8603233501192684, "percentage": 62.07, "elapsed_time": "5:07:59", "remaining_time": "3:08:14"} +{"current_steps": 878, "total_steps": 1413, "loss": 0.1924, "lr": 1.5893776502156616e-06, "epoch": 1.8624436787702092, "percentage": 62.14, "elapsed_time": "5:08:19", "remaining_time": "3:07:52"} +{"current_steps": 879, "total_steps": 1413, "loss": 0.201, "lr": 1.5841665192346432e-06, "epoch": 1.8645640074211502, "percentage": 62.21, "elapsed_time": "5:08:40", "remaining_time": "3:07:31"} +{"current_steps": 880, "total_steps": 1413, "loss": 0.234, "lr": 1.5789599802415572e-06, "epoch": 1.8666843360720913, "percentage": 62.28, "elapsed_time": "5:09:02", "remaining_time": "3:07:10"} +{"current_steps": 881, "total_steps": 1413, "loss": 0.1891, "lr": 1.5737580593419854e-06, "epoch": 1.868804664723032, "percentage": 62.35, "elapsed_time": "5:09:22", "remaining_time": "3:06:49"} +{"current_steps": 882, "total_steps": 1413, "loss": 0.1912, "lr": 1.5685607826183514e-06, "epoch": 1.8709249933739729, "percentage": 62.42, "elapsed_time": "5:09:44", "remaining_time": "3:06:28"} +{"current_steps": 883, "total_steps": 1413, "loss": 0.1075, "lr": 1.5633681761297948e-06, "epoch": 1.873045322024914, "percentage": 62.49, "elapsed_time": "5:10:04", "remaining_time": "3:06:06"} +{"current_steps": 884, "total_steps": 1413, "loss": 0.1945, "lr": 1.558180265912037e-06, "epoch": 1.8751656506758547, "percentage": 62.56, "elapsed_time": "5:10:25", "remaining_time": "3:05:45"} +{"current_steps": 885, "total_steps": 1413, "loss": 0.1465, "lr": 1.5529970779772552e-06, "epoch": 1.8772859793267958, "percentage": 62.63, "elapsed_time": "5:10:46", "remaining_time": "3:05:24"} +{"current_steps": 886, "total_steps": 1413, "loss": 0.2768, "lr": 1.5478186383139459e-06, "epoch": 1.8794063079777366, "percentage": 62.7, "elapsed_time": "5:11:07", "remaining_time": "3:05:03"} +{"current_steps": 887, "total_steps": 1413, "loss": 0.2076, "lr": 1.5426449728868004e-06, "epoch": 1.8815266366286774, "percentage": 62.77, "elapsed_time": "5:11:28", "remaining_time": "3:04:42"} +{"current_steps": 888, "total_steps": 1413, "loss": 0.2828, "lr": 1.5374761076365695e-06, "epoch": 1.8836469652796184, "percentage": 62.85, "elapsed_time": "5:11:49", "remaining_time": "3:04:21"} +{"current_steps": 889, "total_steps": 1413, "loss": 0.2031, "lr": 1.5323120684799374e-06, "epoch": 1.8857672939305592, "percentage": 62.92, "elapsed_time": "5:12:09", "remaining_time": "3:03:59"} +{"current_steps": 890, "total_steps": 1413, "loss": 0.2678, "lr": 1.5271528813093896e-06, "epoch": 1.8878876225815002, "percentage": 62.99, "elapsed_time": "5:12:30", "remaining_time": "3:03:38"} +{"current_steps": 891, "total_steps": 1413, "loss": 0.221, "lr": 1.5219985719930851e-06, "epoch": 1.890007951232441, "percentage": 63.06, "elapsed_time": "5:12:50", "remaining_time": "3:03:16"} +{"current_steps": 892, "total_steps": 1413, "loss": 0.1595, "lr": 1.5168491663747236e-06, "epoch": 1.8921282798833818, "percentage": 63.13, "elapsed_time": "5:13:11", "remaining_time": "3:02:55"} +{"current_steps": 893, "total_steps": 1413, "loss": 0.2665, "lr": 1.5117046902734194e-06, "epoch": 1.8942486085343229, "percentage": 63.2, "elapsed_time": "5:13:32", "remaining_time": "3:02:34"} +{"current_steps": 894, "total_steps": 1413, "loss": 0.1806, "lr": 1.5065651694835682e-06, "epoch": 1.8963689371852637, "percentage": 63.27, "elapsed_time": "5:13:52", "remaining_time": "3:02:12"} +{"current_steps": 895, "total_steps": 1413, "loss": 0.2988, "lr": 1.5014306297747217e-06, "epoch": 1.8984892658362047, "percentage": 63.34, "elapsed_time": "5:14:13", "remaining_time": "3:01:51"} +{"current_steps": 896, "total_steps": 1413, "loss": 0.1248, "lr": 1.4963010968914549e-06, "epoch": 1.9006095944871455, "percentage": 63.41, "elapsed_time": "5:14:34", "remaining_time": "3:01:30"} +{"current_steps": 897, "total_steps": 1413, "loss": 0.3798, "lr": 1.4911765965532398e-06, "epoch": 1.9027299231380863, "percentage": 63.48, "elapsed_time": "5:14:55", "remaining_time": "3:01:09"} +{"current_steps": 898, "total_steps": 1413, "loss": 0.2455, "lr": 1.4860571544543157e-06, "epoch": 1.9048502517890273, "percentage": 63.55, "elapsed_time": "5:15:17", "remaining_time": "3:00:48"} +{"current_steps": 899, "total_steps": 1413, "loss": 0.1762, "lr": 1.480942796263556e-06, "epoch": 1.9069705804399681, "percentage": 63.62, "elapsed_time": "5:15:37", "remaining_time": "3:00:27"} +{"current_steps": 900, "total_steps": 1413, "loss": 0.3043, "lr": 1.475833547624349e-06, "epoch": 1.9090909090909092, "percentage": 63.69, "elapsed_time": "5:15:58", "remaining_time": "3:00:06"} +{"current_steps": 901, "total_steps": 1413, "loss": 0.1608, "lr": 1.4707294341544598e-06, "epoch": 1.91121123774185, "percentage": 63.77, "elapsed_time": "5:16:19", "remaining_time": "2:59:45"} +{"current_steps": 902, "total_steps": 1413, "loss": 0.1494, "lr": 1.4656304814459077e-06, "epoch": 1.9133315663927908, "percentage": 63.84, "elapsed_time": "5:16:40", "remaining_time": "2:59:24"} +{"current_steps": 903, "total_steps": 1413, "loss": 0.1819, "lr": 1.4605367150648341e-06, "epoch": 1.9154518950437318, "percentage": 63.91, "elapsed_time": "5:17:02", "remaining_time": "2:59:03"} +{"current_steps": 904, "total_steps": 1413, "loss": 0.1381, "lr": 1.455448160551378e-06, "epoch": 1.9175722236946728, "percentage": 63.98, "elapsed_time": "5:17:23", "remaining_time": "2:58:42"} +{"current_steps": 905, "total_steps": 1413, "loss": 0.1973, "lr": 1.4503648434195466e-06, "epoch": 1.9196925523456136, "percentage": 64.05, "elapsed_time": "5:17:44", "remaining_time": "2:58:21"} +{"current_steps": 906, "total_steps": 1413, "loss": 0.2893, "lr": 1.445286789157084e-06, "epoch": 1.9218128809965545, "percentage": 64.12, "elapsed_time": "5:18:06", "remaining_time": "2:58:01"} +{"current_steps": 907, "total_steps": 1413, "loss": 0.1968, "lr": 1.4402140232253486e-06, "epoch": 1.9239332096474953, "percentage": 64.19, "elapsed_time": "5:18:29", "remaining_time": "2:57:40"} +{"current_steps": 908, "total_steps": 1413, "loss": 0.1978, "lr": 1.435146571059181e-06, "epoch": 1.9260535382984363, "percentage": 64.26, "elapsed_time": "5:18:49", "remaining_time": "2:57:19"} +{"current_steps": 909, "total_steps": 1413, "loss": 0.2572, "lr": 1.430084458066784e-06, "epoch": 1.9281738669493773, "percentage": 64.33, "elapsed_time": "5:19:10", "remaining_time": "2:56:58"} +{"current_steps": 910, "total_steps": 1413, "loss": 0.1473, "lr": 1.4250277096295817e-06, "epoch": 1.9302941956003181, "percentage": 64.4, "elapsed_time": "5:19:32", "remaining_time": "2:56:37"} +{"current_steps": 911, "total_steps": 1413, "loss": 0.2889, "lr": 1.4199763511021065e-06, "epoch": 1.932414524251259, "percentage": 64.47, "elapsed_time": "5:19:52", "remaining_time": "2:56:16"} +{"current_steps": 912, "total_steps": 1413, "loss": 0.1495, "lr": 1.4149304078118619e-06, "epoch": 1.9345348529021997, "percentage": 64.54, "elapsed_time": "5:20:12", "remaining_time": "2:55:54"} +{"current_steps": 913, "total_steps": 1413, "loss": 0.1174, "lr": 1.4098899050592037e-06, "epoch": 1.9366551815531408, "percentage": 64.61, "elapsed_time": "5:20:33", "remaining_time": "2:55:33"} +{"current_steps": 914, "total_steps": 1413, "loss": 0.1357, "lr": 1.404854868117206e-06, "epoch": 1.9387755102040818, "percentage": 64.69, "elapsed_time": "5:20:53", "remaining_time": "2:55:11"} +{"current_steps": 915, "total_steps": 1413, "loss": 0.1929, "lr": 1.3998253222315363e-06, "epoch": 1.9408958388550226, "percentage": 64.76, "elapsed_time": "5:21:15", "remaining_time": "2:54:50"} +{"current_steps": 916, "total_steps": 1413, "loss": 0.2133, "lr": 1.394801292620332e-06, "epoch": 1.9430161675059634, "percentage": 64.83, "elapsed_time": "5:21:36", "remaining_time": "2:54:29"} +{"current_steps": 917, "total_steps": 1413, "loss": 0.2032, "lr": 1.389782804474072e-06, "epoch": 1.9451364961569042, "percentage": 64.9, "elapsed_time": "5:21:56", "remaining_time": "2:54:08"} +{"current_steps": 918, "total_steps": 1413, "loss": 0.1907, "lr": 1.3847698829554496e-06, "epoch": 1.9472568248078452, "percentage": 64.97, "elapsed_time": "5:22:16", "remaining_time": "2:53:46"} +{"current_steps": 919, "total_steps": 1413, "loss": 0.2204, "lr": 1.3797625531992464e-06, "epoch": 1.9493771534587863, "percentage": 65.04, "elapsed_time": "5:22:37", "remaining_time": "2:53:25"} +{"current_steps": 920, "total_steps": 1413, "loss": 0.2518, "lr": 1.374760840312208e-06, "epoch": 1.951497482109727, "percentage": 65.11, "elapsed_time": "5:22:58", "remaining_time": "2:53:04"} +{"current_steps": 921, "total_steps": 1413, "loss": 0.1671, "lr": 1.3697647693729166e-06, "epoch": 1.9536178107606679, "percentage": 65.18, "elapsed_time": "5:23:19", "remaining_time": "2:52:43"} +{"current_steps": 922, "total_steps": 1413, "loss": 0.1723, "lr": 1.3647743654316653e-06, "epoch": 1.9557381394116087, "percentage": 65.25, "elapsed_time": "5:23:40", "remaining_time": "2:52:21"} +{"current_steps": 923, "total_steps": 1413, "loss": 0.1485, "lr": 1.3597896535103328e-06, "epoch": 1.9578584680625497, "percentage": 65.32, "elapsed_time": "5:24:01", "remaining_time": "2:52:01"} +{"current_steps": 924, "total_steps": 1413, "loss": 0.1481, "lr": 1.3548106586022597e-06, "epoch": 1.9599787967134907, "percentage": 65.39, "elapsed_time": "5:24:23", "remaining_time": "2:51:40"} +{"current_steps": 925, "total_steps": 1413, "loss": 0.2583, "lr": 1.3498374056721198e-06, "epoch": 1.9620991253644315, "percentage": 65.46, "elapsed_time": "5:24:43", "remaining_time": "2:51:19"} +{"current_steps": 926, "total_steps": 1413, "loss": 0.2165, "lr": 1.3448699196557973e-06, "epoch": 1.9642194540153723, "percentage": 65.53, "elapsed_time": "5:25:05", "remaining_time": "2:50:58"} +{"current_steps": 927, "total_steps": 1413, "loss": 0.1807, "lr": 1.3399082254602594e-06, "epoch": 1.9663397826663132, "percentage": 65.61, "elapsed_time": "5:25:26", "remaining_time": "2:50:37"} +{"current_steps": 928, "total_steps": 1413, "loss": 0.249, "lr": 1.3349523479634368e-06, "epoch": 1.9684601113172542, "percentage": 65.68, "elapsed_time": "5:25:48", "remaining_time": "2:50:16"} +{"current_steps": 929, "total_steps": 1413, "loss": 0.1337, "lr": 1.3300023120140926e-06, "epoch": 1.9705804399681952, "percentage": 65.75, "elapsed_time": "5:26:08", "remaining_time": "2:49:55"} +{"current_steps": 930, "total_steps": 1413, "loss": 0.2563, "lr": 1.3250581424317012e-06, "epoch": 1.972700768619136, "percentage": 65.82, "elapsed_time": "5:26:29", "remaining_time": "2:49:33"} +{"current_steps": 931, "total_steps": 1413, "loss": 0.2068, "lr": 1.3201198640063196e-06, "epoch": 1.9748210972700768, "percentage": 65.89, "elapsed_time": "5:26:50", "remaining_time": "2:49:13"} +{"current_steps": 932, "total_steps": 1413, "loss": 0.1813, "lr": 1.3151875014984734e-06, "epoch": 1.9769414259210176, "percentage": 65.96, "elapsed_time": "5:27:11", "remaining_time": "2:48:51"} +{"current_steps": 933, "total_steps": 1413, "loss": 0.2077, "lr": 1.3102610796390209e-06, "epoch": 1.9790617545719587, "percentage": 66.03, "elapsed_time": "5:27:32", "remaining_time": "2:48:30"} +{"current_steps": 934, "total_steps": 1413, "loss": 0.1782, "lr": 1.3053406231290348e-06, "epoch": 1.9811820832228997, "percentage": 66.1, "elapsed_time": "5:27:52", "remaining_time": "2:48:09"} +{"current_steps": 935, "total_steps": 1413, "loss": 0.2884, "lr": 1.300426156639677e-06, "epoch": 1.9833024118738405, "percentage": 66.17, "elapsed_time": "5:28:15", "remaining_time": "2:47:48"} +{"current_steps": 936, "total_steps": 1413, "loss": 0.192, "lr": 1.2955177048120786e-06, "epoch": 1.9854227405247813, "percentage": 66.24, "elapsed_time": "5:28:36", "remaining_time": "2:47:27"} +{"current_steps": 937, "total_steps": 1413, "loss": 0.1134, "lr": 1.2906152922572102e-06, "epoch": 1.987543069175722, "percentage": 66.31, "elapsed_time": "5:28:57", "remaining_time": "2:47:06"} +{"current_steps": 938, "total_steps": 1413, "loss": 0.1924, "lr": 1.2857189435557616e-06, "epoch": 1.9896633978266631, "percentage": 66.38, "elapsed_time": "5:29:18", "remaining_time": "2:46:45"} +{"current_steps": 939, "total_steps": 1413, "loss": 0.2068, "lr": 1.2808286832580186e-06, "epoch": 1.9917837264776042, "percentage": 66.45, "elapsed_time": "5:29:39", "remaining_time": "2:46:24"} +{"current_steps": 940, "total_steps": 1413, "loss": 0.1122, "lr": 1.2759445358837419e-06, "epoch": 1.993904055128545, "percentage": 66.53, "elapsed_time": "5:30:00", "remaining_time": "2:46:03"} +{"current_steps": 941, "total_steps": 1413, "loss": 0.2615, "lr": 1.2710665259220403e-06, "epoch": 1.9960243837794858, "percentage": 66.6, "elapsed_time": "5:30:21", "remaining_time": "2:45:42"} +{"current_steps": 942, "total_steps": 1413, "loss": 0.1196, "lr": 1.2661946778312473e-06, "epoch": 1.9981447124304266, "percentage": 66.67, "elapsed_time": "5:30:42", "remaining_time": "2:45:21"} +{"current_steps": 943, "total_steps": 1413, "loss": 0.2324, "lr": 1.2613290160388052e-06, "epoch": 2.0010601643254704, "percentage": 66.74, "elapsed_time": "5:31:04", "remaining_time": "2:45:00"} +{"current_steps": 944, "total_steps": 1413, "loss": 0.1671, "lr": 1.2564695649411363e-06, "epoch": 2.003180492976411, "percentage": 66.81, "elapsed_time": "5:31:24", "remaining_time": "2:44:39"} +{"current_steps": 945, "total_steps": 1413, "loss": 0.1219, "lr": 1.2516163489035216e-06, "epoch": 2.0053008216273525, "percentage": 66.88, "elapsed_time": "5:31:45", "remaining_time": "2:44:17"} +{"current_steps": 946, "total_steps": 1413, "loss": 0.1258, "lr": 1.2467693922599805e-06, "epoch": 2.0074211502782933, "percentage": 66.95, "elapsed_time": "5:32:06", "remaining_time": "2:43:57"} +{"current_steps": 947, "total_steps": 1413, "loss": 0.2731, "lr": 1.2419287193131468e-06, "epoch": 2.009541478929234, "percentage": 67.02, "elapsed_time": "5:32:28", "remaining_time": "2:43:36"} +{"current_steps": 948, "total_steps": 1413, "loss": 0.151, "lr": 1.23709435433415e-06, "epoch": 2.011661807580175, "percentage": 67.09, "elapsed_time": "5:32:48", "remaining_time": "2:43:14"} +{"current_steps": 949, "total_steps": 1413, "loss": 0.187, "lr": 1.2322663215624898e-06, "epoch": 2.0137821362311157, "percentage": 67.16, "elapsed_time": "5:33:10", "remaining_time": "2:42:53"} +{"current_steps": 950, "total_steps": 1413, "loss": 0.1094, "lr": 1.2274446452059158e-06, "epoch": 2.015902464882057, "percentage": 67.23, "elapsed_time": "5:33:31", "remaining_time": "2:42:32"} +{"current_steps": 951, "total_steps": 1413, "loss": 0.2884, "lr": 1.222629349440308e-06, "epoch": 2.0180227935329977, "percentage": 67.3, "elapsed_time": "5:33:51", "remaining_time": "2:42:11"} +{"current_steps": 952, "total_steps": 1413, "loss": 0.1166, "lr": 1.2178204584095526e-06, "epoch": 2.0201431221839385, "percentage": 67.37, "elapsed_time": "5:34:12", "remaining_time": "2:41:50"} +{"current_steps": 953, "total_steps": 1413, "loss": 0.2639, "lr": 1.213017996225424e-06, "epoch": 2.0222634508348794, "percentage": 67.45, "elapsed_time": "5:34:32", "remaining_time": "2:41:28"} +{"current_steps": 954, "total_steps": 1413, "loss": 0.2392, "lr": 1.2082219869674603e-06, "epoch": 2.02438377948582, "percentage": 67.52, "elapsed_time": "5:34:53", "remaining_time": "2:41:07"} +{"current_steps": 955, "total_steps": 1413, "loss": 0.1054, "lr": 1.2034324546828477e-06, "epoch": 2.0265041081367614, "percentage": 67.59, "elapsed_time": "5:35:13", "remaining_time": "2:40:45"} +{"current_steps": 956, "total_steps": 1413, "loss": 0.2579, "lr": 1.1986494233862948e-06, "epoch": 2.028624436787702, "percentage": 67.66, "elapsed_time": "5:35:33", "remaining_time": "2:40:24"} +{"current_steps": 957, "total_steps": 1413, "loss": 0.1962, "lr": 1.1938729170599136e-06, "epoch": 2.030744765438643, "percentage": 67.73, "elapsed_time": "5:35:55", "remaining_time": "2:40:03"} +{"current_steps": 958, "total_steps": 1413, "loss": 0.139, "lr": 1.1891029596531005e-06, "epoch": 2.032865094089584, "percentage": 67.8, "elapsed_time": "5:36:15", "remaining_time": "2:39:42"} +{"current_steps": 959, "total_steps": 1413, "loss": 0.1442, "lr": 1.1843395750824183e-06, "epoch": 2.0349854227405246, "percentage": 67.87, "elapsed_time": "5:36:36", "remaining_time": "2:39:21"} +{"current_steps": 960, "total_steps": 1413, "loss": 0.1862, "lr": 1.1795827872314694e-06, "epoch": 2.037105751391466, "percentage": 67.94, "elapsed_time": "5:36:58", "remaining_time": "2:39:00"} +{"current_steps": 961, "total_steps": 1413, "loss": 0.187, "lr": 1.1748326199507829e-06, "epoch": 2.0392260800424067, "percentage": 68.01, "elapsed_time": "5:37:17", "remaining_time": "2:38:38"} +{"current_steps": 962, "total_steps": 1413, "loss": 0.1043, "lr": 1.1700890970576914e-06, "epoch": 2.0413464086933475, "percentage": 68.08, "elapsed_time": "5:37:38", "remaining_time": "2:38:17"} +{"current_steps": 963, "total_steps": 1413, "loss": 0.1359, "lr": 1.1653522423362129e-06, "epoch": 2.0434667373442883, "percentage": 68.15, "elapsed_time": "5:37:59", "remaining_time": "2:37:56"} +{"current_steps": 964, "total_steps": 1413, "loss": 0.1808, "lr": 1.1606220795369307e-06, "epoch": 2.045587065995229, "percentage": 68.22, "elapsed_time": "5:38:20", "remaining_time": "2:37:35"} +{"current_steps": 965, "total_steps": 1413, "loss": 0.1454, "lr": 1.1558986323768758e-06, "epoch": 2.0477073946461704, "percentage": 68.29, "elapsed_time": "5:38:41", "remaining_time": "2:37:14"} +{"current_steps": 966, "total_steps": 1413, "loss": 0.1273, "lr": 1.1511819245394051e-06, "epoch": 2.049827723297111, "percentage": 68.37, "elapsed_time": "5:39:01", "remaining_time": "2:36:52"} +{"current_steps": 967, "total_steps": 1413, "loss": 0.1516, "lr": 1.1464719796740875e-06, "epoch": 2.051948051948052, "percentage": 68.44, "elapsed_time": "5:39:22", "remaining_time": "2:36:31"} +{"current_steps": 968, "total_steps": 1413, "loss": 0.2406, "lr": 1.1417688213965803e-06, "epoch": 2.0540683805989928, "percentage": 68.51, "elapsed_time": "5:39:44", "remaining_time": "2:36:10"} +{"current_steps": 969, "total_steps": 1413, "loss": 0.2046, "lr": 1.1370724732885126e-06, "epoch": 2.0561887092499336, "percentage": 68.58, "elapsed_time": "5:40:04", "remaining_time": "2:35:49"} +{"current_steps": 970, "total_steps": 1413, "loss": 0.1645, "lr": 1.1323829588973676e-06, "epoch": 2.058309037900875, "percentage": 68.65, "elapsed_time": "5:40:24", "remaining_time": "2:35:27"} +{"current_steps": 971, "total_steps": 1413, "loss": 0.1562, "lr": 1.1277003017363661e-06, "epoch": 2.0604293665518156, "percentage": 68.72, "elapsed_time": "5:40:44", "remaining_time": "2:35:06"} +{"current_steps": 972, "total_steps": 1413, "loss": 0.1089, "lr": 1.1230245252843456e-06, "epoch": 2.0625496952027564, "percentage": 68.79, "elapsed_time": "5:41:05", "remaining_time": "2:34:45"} +{"current_steps": 973, "total_steps": 1413, "loss": 0.216, "lr": 1.1183556529856404e-06, "epoch": 2.0646700238536972, "percentage": 68.86, "elapsed_time": "5:41:26", "remaining_time": "2:34:24"} +{"current_steps": 974, "total_steps": 1413, "loss": 0.0965, "lr": 1.1136937082499733e-06, "epoch": 2.066790352504638, "percentage": 68.93, "elapsed_time": "5:41:46", "remaining_time": "2:34:02"} +{"current_steps": 975, "total_steps": 1413, "loss": 0.2348, "lr": 1.1090387144523284e-06, "epoch": 2.0689106811555793, "percentage": 69.0, "elapsed_time": "5:42:07", "remaining_time": "2:33:41"} +{"current_steps": 976, "total_steps": 1413, "loss": 0.1252, "lr": 1.1043906949328387e-06, "epoch": 2.07103100980652, "percentage": 69.07, "elapsed_time": "5:42:29", "remaining_time": "2:33:20"} +{"current_steps": 977, "total_steps": 1413, "loss": 0.228, "lr": 1.0997496729966679e-06, "epoch": 2.073151338457461, "percentage": 69.14, "elapsed_time": "5:42:50", "remaining_time": "2:32:59"} +{"current_steps": 978, "total_steps": 1413, "loss": 0.1241, "lr": 1.0951156719138953e-06, "epoch": 2.0752716671084017, "percentage": 69.21, "elapsed_time": "5:43:09", "remaining_time": "2:32:38"} +{"current_steps": 979, "total_steps": 1413, "loss": 0.1477, "lr": 1.090488714919396e-06, "epoch": 2.0773919957593425, "percentage": 69.29, "elapsed_time": "5:43:32", "remaining_time": "2:32:17"} +{"current_steps": 980, "total_steps": 1413, "loss": 0.1195, "lr": 1.0858688252127268e-06, "epoch": 2.0795123244102838, "percentage": 69.36, "elapsed_time": "5:43:53", "remaining_time": "2:31:56"} +{"current_steps": 981, "total_steps": 1413, "loss": 0.1273, "lr": 1.0812560259580076e-06, "epoch": 2.0816326530612246, "percentage": 69.43, "elapsed_time": "5:44:14", "remaining_time": "2:31:35"} +{"current_steps": 982, "total_steps": 1413, "loss": 0.1584, "lr": 1.0766503402838103e-06, "epoch": 2.0837529817121654, "percentage": 69.5, "elapsed_time": "5:44:35", "remaining_time": "2:31:14"} +{"current_steps": 983, "total_steps": 1413, "loss": 0.1586, "lr": 1.0720517912830371e-06, "epoch": 2.085873310363106, "percentage": 69.57, "elapsed_time": "5:44:56", "remaining_time": "2:30:53"} +{"current_steps": 984, "total_steps": 1413, "loss": 0.1341, "lr": 1.0674604020128051e-06, "epoch": 2.087993639014047, "percentage": 69.64, "elapsed_time": "5:45:16", "remaining_time": "2:30:31"} +{"current_steps": 985, "total_steps": 1413, "loss": 0.1727, "lr": 1.0628761954943343e-06, "epoch": 2.0901139676649882, "percentage": 69.71, "elapsed_time": "5:45:37", "remaining_time": "2:30:10"} +{"current_steps": 986, "total_steps": 1413, "loss": 0.1506, "lr": 1.0582991947128324e-06, "epoch": 2.092234296315929, "percentage": 69.78, "elapsed_time": "5:45:57", "remaining_time": "2:29:49"} +{"current_steps": 987, "total_steps": 1413, "loss": 0.1112, "lr": 1.0537294226173748e-06, "epoch": 2.09435462496687, "percentage": 69.85, "elapsed_time": "5:46:19", "remaining_time": "2:29:28"} +{"current_steps": 988, "total_steps": 1413, "loss": 0.2002, "lr": 1.0491669021207929e-06, "epoch": 2.0964749536178107, "percentage": 69.92, "elapsed_time": "5:46:40", "remaining_time": "2:29:07"} +{"current_steps": 989, "total_steps": 1413, "loss": 0.2054, "lr": 1.0446116560995582e-06, "epoch": 2.0985952822687515, "percentage": 69.99, "elapsed_time": "5:47:01", "remaining_time": "2:28:46"} +{"current_steps": 990, "total_steps": 1413, "loss": 0.153, "lr": 1.0400637073936697e-06, "epoch": 2.1007156109196927, "percentage": 70.06, "elapsed_time": "5:47:22", "remaining_time": "2:28:25"} +{"current_steps": 991, "total_steps": 1413, "loss": 0.1552, "lr": 1.0355230788065365e-06, "epoch": 2.1028359395706335, "percentage": 70.13, "elapsed_time": "5:47:42", "remaining_time": "2:28:03"} +{"current_steps": 992, "total_steps": 1413, "loss": 0.2001, "lr": 1.030989793104864e-06, "epoch": 2.1049562682215743, "percentage": 70.21, "elapsed_time": "5:48:03", "remaining_time": "2:27:42"} +{"current_steps": 993, "total_steps": 1413, "loss": 0.1307, "lr": 1.0264638730185409e-06, "epoch": 2.107076596872515, "percentage": 70.28, "elapsed_time": "5:48:24", "remaining_time": "2:27:21"} +{"current_steps": 994, "total_steps": 1413, "loss": 0.1668, "lr": 1.021945341240527e-06, "epoch": 2.109196925523456, "percentage": 70.35, "elapsed_time": "5:48:44", "remaining_time": "2:27:00"} +{"current_steps": 995, "total_steps": 1413, "loss": 0.1635, "lr": 1.0174342204267323e-06, "epoch": 2.111317254174397, "percentage": 70.42, "elapsed_time": "5:49:04", "remaining_time": "2:26:38"} +{"current_steps": 996, "total_steps": 1413, "loss": 0.2443, "lr": 1.012930533195911e-06, "epoch": 2.113437582825338, "percentage": 70.49, "elapsed_time": "5:49:26", "remaining_time": "2:26:18"} +{"current_steps": 997, "total_steps": 1413, "loss": 0.1109, "lr": 1.0084343021295476e-06, "epoch": 2.115557911476279, "percentage": 70.56, "elapsed_time": "5:49:47", "remaining_time": "2:25:57"} +{"current_steps": 998, "total_steps": 1413, "loss": 0.1842, "lr": 1.0039455497717376e-06, "epoch": 2.1176782401272196, "percentage": 70.63, "elapsed_time": "5:50:08", "remaining_time": "2:25:35"} +{"current_steps": 999, "total_steps": 1413, "loss": 0.1828, "lr": 9.994642986290797e-07, "epoch": 2.1197985687781604, "percentage": 70.7, "elapsed_time": "5:50:29", "remaining_time": "2:25:14"} +{"current_steps": 1000, "total_steps": 1413, "loss": 0.1531, "lr": 9.949905711705613e-07, "epoch": 2.1219188974291017, "percentage": 70.77, "elapsed_time": "5:50:49", "remaining_time": "2:24:53"} +{"current_steps": 1001, "total_steps": 1413, "loss": 0.1289, "lr": 9.905243898274476e-07, "epoch": 2.1240392260800425, "percentage": 70.84, "elapsed_time": "5:52:42", "remaining_time": "2:25:10"} +{"current_steps": 1002, "total_steps": 1413, "loss": 0.1114, "lr": 9.86065776993165e-07, "epoch": 2.1261595547309833, "percentage": 70.91, "elapsed_time": "5:53:04", "remaining_time": "2:24:49"} +{"current_steps": 1003, "total_steps": 1413, "loss": 0.1902, "lr": 9.816147550231936e-07, "epoch": 2.128279883381924, "percentage": 70.98, "elapsed_time": "5:53:24", "remaining_time": "2:24:27"} +{"current_steps": 1004, "total_steps": 1413, "loss": 0.1395, "lr": 9.771713462349517e-07, "epoch": 2.130400212032865, "percentage": 71.05, "elapsed_time": "5:53:45", "remaining_time": "2:24:06"} +{"current_steps": 1005, "total_steps": 1413, "loss": 0.141, "lr": 9.727355729076848e-07, "epoch": 2.132520540683806, "percentage": 71.13, "elapsed_time": "5:54:06", "remaining_time": "2:23:45"} +{"current_steps": 1006, "total_steps": 1413, "loss": 0.1943, "lr": 9.683074572823558e-07, "epoch": 2.134640869334747, "percentage": 71.2, "elapsed_time": "5:54:27", "remaining_time": "2:23:24"} +{"current_steps": 1007, "total_steps": 1413, "loss": 0.0903, "lr": 9.638870215615304e-07, "epoch": 2.1367611979856878, "percentage": 71.27, "elapsed_time": "5:54:46", "remaining_time": "2:23:02"} +{"current_steps": 1008, "total_steps": 1413, "loss": 0.1862, "lr": 9.594742879092673e-07, "epoch": 2.1388815266366286, "percentage": 71.34, "elapsed_time": "5:55:07", "remaining_time": "2:22:41"} +{"current_steps": 1009, "total_steps": 1413, "loss": 0.114, "lr": 9.550692784510085e-07, "epoch": 2.1410018552875694, "percentage": 71.41, "elapsed_time": "5:55:30", "remaining_time": "2:22:20"} +{"current_steps": 1010, "total_steps": 1413, "loss": 0.1046, "lr": 9.50672015273466e-07, "epoch": 2.1431221839385106, "percentage": 71.48, "elapsed_time": "5:55:51", "remaining_time": "2:21:59"} +{"current_steps": 1011, "total_steps": 1413, "loss": 0.1864, "lr": 9.462825204245113e-07, "epoch": 2.1452425125894514, "percentage": 71.55, "elapsed_time": "5:56:13", "remaining_time": "2:21:38"} +{"current_steps": 1012, "total_steps": 1413, "loss": 0.064, "lr": 9.419008159130658e-07, "epoch": 2.1473628412403922, "percentage": 71.62, "elapsed_time": "5:56:35", "remaining_time": "2:21:17"} +{"current_steps": 1013, "total_steps": 1413, "loss": 0.1237, "lr": 9.375269237089915e-07, "epoch": 2.149483169891333, "percentage": 71.69, "elapsed_time": "5:56:55", "remaining_time": "2:20:56"} +{"current_steps": 1014, "total_steps": 1413, "loss": 0.1576, "lr": 9.331608657429781e-07, "epoch": 2.151603498542274, "percentage": 71.76, "elapsed_time": "5:57:15", "remaining_time": "2:20:34"} +{"current_steps": 1015, "total_steps": 1413, "loss": 0.1716, "lr": 9.288026639064346e-07, "epoch": 2.153723827193215, "percentage": 71.83, "elapsed_time": "5:57:36", "remaining_time": "2:20:13"} +{"current_steps": 1016, "total_steps": 1413, "loss": 0.1497, "lr": 9.244523400513797e-07, "epoch": 2.155844155844156, "percentage": 71.9, "elapsed_time": "5:57:56", "remaining_time": "2:19:52"} +{"current_steps": 1017, "total_steps": 1413, "loss": 0.0957, "lr": 9.201099159903318e-07, "epoch": 2.1579644844950967, "percentage": 71.97, "elapsed_time": "5:58:17", "remaining_time": "2:19:30"} +{"current_steps": 1018, "total_steps": 1413, "loss": 0.2541, "lr": 9.157754134961997e-07, "epoch": 2.1600848131460375, "percentage": 72.05, "elapsed_time": "5:58:38", "remaining_time": "2:19:09"} +{"current_steps": 1019, "total_steps": 1413, "loss": 0.1664, "lr": 9.114488543021724e-07, "epoch": 2.1622051417969788, "percentage": 72.12, "elapsed_time": "5:58:58", "remaining_time": "2:18:48"} +{"current_steps": 1020, "total_steps": 1413, "loss": 0.2169, "lr": 9.071302601016147e-07, "epoch": 2.1643254704479196, "percentage": 72.19, "elapsed_time": "5:59:19", "remaining_time": "2:18:26"} +{"current_steps": 1021, "total_steps": 1413, "loss": 0.1863, "lr": 9.02819652547951e-07, "epoch": 2.1664457990988604, "percentage": 72.26, "elapsed_time": "5:59:40", "remaining_time": "2:18:05"} +{"current_steps": 1022, "total_steps": 1413, "loss": 0.1827, "lr": 8.985170532545623e-07, "epoch": 2.168566127749801, "percentage": 72.33, "elapsed_time": "6:00:01", "remaining_time": "2:17:44"} +{"current_steps": 1023, "total_steps": 1413, "loss": 0.2556, "lr": 8.942224837946767e-07, "epoch": 2.170686456400742, "percentage": 72.4, "elapsed_time": "6:00:22", "remaining_time": "2:17:23"} +{"current_steps": 1024, "total_steps": 1413, "loss": 0.1713, "lr": 8.899359657012585e-07, "epoch": 2.172806785051683, "percentage": 72.47, "elapsed_time": "6:00:42", "remaining_time": "2:17:01"} +{"current_steps": 1025, "total_steps": 1413, "loss": 0.1403, "lr": 8.856575204669066e-07, "epoch": 2.174927113702624, "percentage": 72.54, "elapsed_time": "6:01:02", "remaining_time": "2:16:40"} +{"current_steps": 1026, "total_steps": 1413, "loss": 0.2385, "lr": 8.813871695437392e-07, "epoch": 2.177047442353565, "percentage": 72.61, "elapsed_time": "6:01:24", "remaining_time": "2:16:19"} +{"current_steps": 1027, "total_steps": 1413, "loss": 0.1823, "lr": 8.771249343432886e-07, "epoch": 2.1791677710045056, "percentage": 72.68, "elapsed_time": "6:01:44", "remaining_time": "2:15:57"} +{"current_steps": 1028, "total_steps": 1413, "loss": 0.0917, "lr": 8.728708362363991e-07, "epoch": 2.1812880996554465, "percentage": 72.75, "elapsed_time": "6:02:06", "remaining_time": "2:15:36"} +{"current_steps": 1029, "total_steps": 1413, "loss": 0.1308, "lr": 8.686248965531124e-07, "epoch": 2.1834084283063877, "percentage": 72.82, "elapsed_time": "6:02:26", "remaining_time": "2:15:15"} +{"current_steps": 1030, "total_steps": 1413, "loss": 0.181, "lr": 8.643871365825651e-07, "epoch": 2.1855287569573285, "percentage": 72.89, "elapsed_time": "6:02:46", "remaining_time": "2:14:53"} +{"current_steps": 1031, "total_steps": 1413, "loss": 0.1376, "lr": 8.601575775728793e-07, "epoch": 2.1876490856082693, "percentage": 72.97, "elapsed_time": "6:03:07", "remaining_time": "2:14:32"} +{"current_steps": 1032, "total_steps": 1413, "loss": 0.1826, "lr": 8.559362407310607e-07, "epoch": 2.18976941425921, "percentage": 73.04, "elapsed_time": "6:03:28", "remaining_time": "2:14:11"} +{"current_steps": 1033, "total_steps": 1413, "loss": 0.2169, "lr": 8.517231472228854e-07, "epoch": 2.191889742910151, "percentage": 73.11, "elapsed_time": "6:03:48", "remaining_time": "2:13:49"} +{"current_steps": 1034, "total_steps": 1413, "loss": 0.2092, "lr": 8.475183181727995e-07, "epoch": 2.1940100715610917, "percentage": 73.18, "elapsed_time": "6:04:09", "remaining_time": "2:13:28"} +{"current_steps": 1035, "total_steps": 1413, "loss": 0.1093, "lr": 8.433217746638098e-07, "epoch": 2.196130400212033, "percentage": 73.25, "elapsed_time": "6:04:29", "remaining_time": "2:13:07"} +{"current_steps": 1036, "total_steps": 1413, "loss": 0.1931, "lr": 8.391335377373825e-07, "epoch": 2.198250728862974, "percentage": 73.32, "elapsed_time": "6:04:49", "remaining_time": "2:12:45"} +{"current_steps": 1037, "total_steps": 1413, "loss": 0.226, "lr": 8.349536283933302e-07, "epoch": 2.2003710575139146, "percentage": 73.39, "elapsed_time": "6:05:10", "remaining_time": "2:12:24"} +{"current_steps": 1038, "total_steps": 1413, "loss": 0.1644, "lr": 8.307820675897127e-07, "epoch": 2.2024913861648554, "percentage": 73.46, "elapsed_time": "6:05:29", "remaining_time": "2:12:02"} +{"current_steps": 1039, "total_steps": 1413, "loss": 0.1338, "lr": 8.266188762427327e-07, "epoch": 2.2046117148157967, "percentage": 73.53, "elapsed_time": "6:05:51", "remaining_time": "2:11:41"} +{"current_steps": 1040, "total_steps": 1413, "loss": 0.2425, "lr": 8.224640752266256e-07, "epoch": 2.2067320434667375, "percentage": 73.6, "elapsed_time": "6:06:12", "remaining_time": "2:11:20"} +{"current_steps": 1041, "total_steps": 1413, "loss": 0.0995, "lr": 8.18317685373558e-07, "epoch": 2.2088523721176783, "percentage": 73.67, "elapsed_time": "6:06:32", "remaining_time": "2:10:59"} +{"current_steps": 1042, "total_steps": 1413, "loss": 0.1023, "lr": 8.141797274735242e-07, "epoch": 2.210972700768619, "percentage": 73.74, "elapsed_time": "6:06:53", "remaining_time": "2:10:37"} +{"current_steps": 1043, "total_steps": 1413, "loss": 0.2438, "lr": 8.100502222742387e-07, "epoch": 2.21309302941956, "percentage": 73.81, "elapsed_time": "6:07:14", "remaining_time": "2:10:16"} +{"current_steps": 1044, "total_steps": 1413, "loss": 0.18, "lr": 8.059291904810373e-07, "epoch": 2.215213358070501, "percentage": 73.89, "elapsed_time": "6:07:35", "remaining_time": "2:09:55"} +{"current_steps": 1045, "total_steps": 1413, "loss": 0.1664, "lr": 8.018166527567672e-07, "epoch": 2.217333686721442, "percentage": 73.96, "elapsed_time": "6:07:57", "remaining_time": "2:09:34"} +{"current_steps": 1046, "total_steps": 1413, "loss": 0.1453, "lr": 7.977126297216878e-07, "epoch": 2.2194540153723827, "percentage": 74.03, "elapsed_time": "6:08:18", "remaining_time": "2:09:13"} +{"current_steps": 1047, "total_steps": 1413, "loss": 0.1826, "lr": 7.936171419533653e-07, "epoch": 2.2215743440233235, "percentage": 74.1, "elapsed_time": "6:08:38", "remaining_time": "2:08:52"} +{"current_steps": 1048, "total_steps": 1413, "loss": 0.1264, "lr": 7.895302099865701e-07, "epoch": 2.2236946726742643, "percentage": 74.17, "elapsed_time": "6:08:59", "remaining_time": "2:08:30"} +{"current_steps": 1049, "total_steps": 1413, "loss": 0.1218, "lr": 7.854518543131742e-07, "epoch": 2.2258150013252056, "percentage": 74.24, "elapsed_time": "6:09:21", "remaining_time": "2:08:10"} +{"current_steps": 1050, "total_steps": 1413, "loss": 0.1772, "lr": 7.813820953820469e-07, "epoch": 2.2279353299761464, "percentage": 74.31, "elapsed_time": "6:09:42", "remaining_time": "2:07:48"} +{"current_steps": 1051, "total_steps": 1413, "loss": 0.2343, "lr": 7.773209535989562e-07, "epoch": 2.230055658627087, "percentage": 74.38, "elapsed_time": "6:10:04", "remaining_time": "2:07:27"} +{"current_steps": 1052, "total_steps": 1413, "loss": 0.1654, "lr": 7.732684493264611e-07, "epoch": 2.232175987278028, "percentage": 74.45, "elapsed_time": "6:10:24", "remaining_time": "2:07:06"} +{"current_steps": 1053, "total_steps": 1413, "loss": 0.1807, "lr": 7.69224602883813e-07, "epoch": 2.234296315928969, "percentage": 74.52, "elapsed_time": "6:10:44", "remaining_time": "2:06:45"} +{"current_steps": 1054, "total_steps": 1413, "loss": 0.1645, "lr": 7.651894345468522e-07, "epoch": 2.23641664457991, "percentage": 74.59, "elapsed_time": "6:11:05", "remaining_time": "2:06:23"} +{"current_steps": 1055, "total_steps": 1413, "loss": 0.1378, "lr": 7.61162964547909e-07, "epoch": 2.238536973230851, "percentage": 74.66, "elapsed_time": "6:11:26", "remaining_time": "2:06:02"} +{"current_steps": 1056, "total_steps": 1413, "loss": 0.2183, "lr": 7.571452130756984e-07, "epoch": 2.2406573018817917, "percentage": 74.73, "elapsed_time": "6:11:47", "remaining_time": "2:05:41"} +{"current_steps": 1057, "total_steps": 1413, "loss": 0.184, "lr": 7.531362002752224e-07, "epoch": 2.2427776305327325, "percentage": 74.81, "elapsed_time": "6:12:07", "remaining_time": "2:05:19"} +{"current_steps": 1058, "total_steps": 1413, "loss": 0.1685, "lr": 7.491359462476632e-07, "epoch": 2.2448979591836733, "percentage": 74.88, "elapsed_time": "6:12:28", "remaining_time": "2:04:58"} +{"current_steps": 1059, "total_steps": 1413, "loss": 0.1379, "lr": 7.451444710502923e-07, "epoch": 2.2470182878346145, "percentage": 74.95, "elapsed_time": "6:12:48", "remaining_time": "2:04:37"} +{"current_steps": 1060, "total_steps": 1413, "loss": 0.1665, "lr": 7.411617946963604e-07, "epoch": 2.2491386164855554, "percentage": 75.02, "elapsed_time": "6:13:09", "remaining_time": "2:04:15"} +{"current_steps": 1061, "total_steps": 1413, "loss": 0.1337, "lr": 7.371879371550017e-07, "epoch": 2.251258945136496, "percentage": 75.09, "elapsed_time": "6:13:29", "remaining_time": "2:03:54"} +{"current_steps": 1062, "total_steps": 1413, "loss": 0.3001, "lr": 7.332229183511325e-07, "epoch": 2.253379273787437, "percentage": 75.16, "elapsed_time": "6:13:52", "remaining_time": "2:03:34"} +{"current_steps": 1063, "total_steps": 1413, "loss": 0.1673, "lr": 7.292667581653537e-07, "epoch": 2.2554996024383778, "percentage": 75.23, "elapsed_time": "6:14:13", "remaining_time": "2:03:13"} +{"current_steps": 1064, "total_steps": 1413, "loss": 0.1727, "lr": 7.253194764338465e-07, "epoch": 2.257619931089319, "percentage": 75.3, "elapsed_time": "6:14:34", "remaining_time": "2:02:51"} +{"current_steps": 1065, "total_steps": 1413, "loss": 0.1634, "lr": 7.213810929482765e-07, "epoch": 2.25974025974026, "percentage": 75.37, "elapsed_time": "6:14:55", "remaining_time": "2:02:30"} +{"current_steps": 1066, "total_steps": 1413, "loss": 0.2101, "lr": 7.174516274556931e-07, "epoch": 2.2618605883912006, "percentage": 75.44, "elapsed_time": "6:15:15", "remaining_time": "2:02:09"} +{"current_steps": 1067, "total_steps": 1413, "loss": 0.2167, "lr": 7.13531099658433e-07, "epoch": 2.2639809170421414, "percentage": 75.51, "elapsed_time": "6:15:36", "remaining_time": "2:01:47"} +{"current_steps": 1068, "total_steps": 1413, "loss": 0.1175, "lr": 7.096195292140173e-07, "epoch": 2.2661012456930822, "percentage": 75.58, "elapsed_time": "6:15:57", "remaining_time": "2:01:26"} +{"current_steps": 1069, "total_steps": 1413, "loss": 0.1834, "lr": 7.057169357350535e-07, "epoch": 2.2682215743440235, "percentage": 75.65, "elapsed_time": "6:16:19", "remaining_time": "2:01:05"} +{"current_steps": 1070, "total_steps": 1413, "loss": 0.0926, "lr": 7.018233387891426e-07, "epoch": 2.2703419029949643, "percentage": 75.73, "elapsed_time": "6:16:39", "remaining_time": "2:00:44"} +{"current_steps": 1071, "total_steps": 1413, "loss": 0.1592, "lr": 6.97938757898774e-07, "epoch": 2.272462231645905, "percentage": 75.8, "elapsed_time": "6:16:59", "remaining_time": "2:00:23"} +{"current_steps": 1072, "total_steps": 1413, "loss": 0.1927, "lr": 6.940632125412314e-07, "epoch": 2.274582560296846, "percentage": 75.87, "elapsed_time": "6:17:20", "remaining_time": "2:00:01"} +{"current_steps": 1073, "total_steps": 1413, "loss": 0.2078, "lr": 6.901967221484937e-07, "epoch": 2.2767028889477867, "percentage": 75.94, "elapsed_time": "6:17:42", "remaining_time": "1:59:41"} +{"current_steps": 1074, "total_steps": 1413, "loss": 0.1582, "lr": 6.863393061071407e-07, "epoch": 2.278823217598728, "percentage": 76.01, "elapsed_time": "6:18:03", "remaining_time": "1:59:19"} +{"current_steps": 1075, "total_steps": 1413, "loss": 0.1972, "lr": 6.824909837582505e-07, "epoch": 2.2809435462496688, "percentage": 76.08, "elapsed_time": "6:18:24", "remaining_time": "1:58:58"} +{"current_steps": 1076, "total_steps": 1413, "loss": 0.1635, "lr": 6.786517743973065e-07, "epoch": 2.2830638749006096, "percentage": 76.15, "elapsed_time": "6:18:45", "remaining_time": "1:58:37"} +{"current_steps": 1077, "total_steps": 1413, "loss": 0.1746, "lr": 6.748216972740992e-07, "epoch": 2.2851842035515504, "percentage": 76.22, "elapsed_time": "6:19:04", "remaining_time": "1:58:15"} +{"current_steps": 1078, "total_steps": 1413, "loss": 0.1611, "lr": 6.71000771592632e-07, "epoch": 2.2873045322024916, "percentage": 76.29, "elapsed_time": "6:19:26", "remaining_time": "1:57:54"} +{"current_steps": 1079, "total_steps": 1413, "loss": 0.1905, "lr": 6.671890165110214e-07, "epoch": 2.2894248608534324, "percentage": 76.36, "elapsed_time": "6:19:47", "remaining_time": "1:57:33"} +{"current_steps": 1080, "total_steps": 1413, "loss": 0.1512, "lr": 6.633864511414015e-07, "epoch": 2.2915451895043732, "percentage": 76.43, "elapsed_time": "6:20:09", "remaining_time": "1:57:12"} +{"current_steps": 1081, "total_steps": 1413, "loss": 0.1088, "lr": 6.595930945498297e-07, "epoch": 2.293665518155314, "percentage": 76.5, "elapsed_time": "6:20:29", "remaining_time": "1:56:51"} +{"current_steps": 1082, "total_steps": 1413, "loss": 0.1399, "lr": 6.558089657561931e-07, "epoch": 2.295785846806255, "percentage": 76.57, "elapsed_time": "6:20:49", "remaining_time": "1:56:30"} +{"current_steps": 1083, "total_steps": 1413, "loss": 0.231, "lr": 6.520340837341079e-07, "epoch": 2.2979061754571957, "percentage": 76.65, "elapsed_time": "6:21:11", "remaining_time": "1:56:09"} +{"current_steps": 1084, "total_steps": 1413, "loss": 0.1828, "lr": 6.482684674108281e-07, "epoch": 2.300026504108137, "percentage": 76.72, "elapsed_time": "6:21:32", "remaining_time": "1:55:47"} +{"current_steps": 1085, "total_steps": 1413, "loss": 0.1228, "lr": 6.445121356671483e-07, "epoch": 2.3021468327590777, "percentage": 76.79, "elapsed_time": "6:21:52", "remaining_time": "1:55:26"} +{"current_steps": 1086, "total_steps": 1413, "loss": 0.1959, "lr": 6.407651073373125e-07, "epoch": 2.3042671614100185, "percentage": 76.86, "elapsed_time": "6:22:13", "remaining_time": "1:55:05"} +{"current_steps": 1087, "total_steps": 1413, "loss": 0.1723, "lr": 6.370274012089159e-07, "epoch": 2.3063874900609593, "percentage": 76.93, "elapsed_time": "6:22:33", "remaining_time": "1:54:44"} +{"current_steps": 1088, "total_steps": 1413, "loss": 0.1399, "lr": 6.332990360228119e-07, "epoch": 2.3085078187119006, "percentage": 77.0, "elapsed_time": "6:22:54", "remaining_time": "1:54:22"} +{"current_steps": 1089, "total_steps": 1413, "loss": 0.124, "lr": 6.29580030473019e-07, "epoch": 2.3106281473628414, "percentage": 77.07, "elapsed_time": "6:23:14", "remaining_time": "1:54:01"} +{"current_steps": 1090, "total_steps": 1413, "loss": 0.2, "lr": 6.258704032066265e-07, "epoch": 2.312748476013782, "percentage": 77.14, "elapsed_time": "6:23:35", "remaining_time": "1:53:40"} +{"current_steps": 1091, "total_steps": 1413, "loss": 0.2478, "lr": 6.221701728237008e-07, "epoch": 2.314868804664723, "percentage": 77.21, "elapsed_time": "6:23:56", "remaining_time": "1:53:19"} +{"current_steps": 1092, "total_steps": 1413, "loss": 0.2235, "lr": 6.184793578771919e-07, "epoch": 2.316989133315664, "percentage": 77.28, "elapsed_time": "6:24:17", "remaining_time": "1:52:57"} +{"current_steps": 1093, "total_steps": 1413, "loss": 0.259, "lr": 6.147979768728427e-07, "epoch": 2.3191094619666046, "percentage": 77.35, "elapsed_time": "6:24:37", "remaining_time": "1:52:36"} +{"current_steps": 1094, "total_steps": 1413, "loss": 0.1029, "lr": 6.11126048269092e-07, "epoch": 2.321229790617546, "percentage": 77.42, "elapsed_time": "6:24:58", "remaining_time": "1:52:15"} +{"current_steps": 1095, "total_steps": 1413, "loss": 0.2121, "lr": 6.074635904769855e-07, "epoch": 2.3233501192684867, "percentage": 77.49, "elapsed_time": "6:25:19", "remaining_time": "1:51:54"} +{"current_steps": 1096, "total_steps": 1413, "loss": 0.1593, "lr": 6.03810621860082e-07, "epoch": 2.3254704479194275, "percentage": 77.57, "elapsed_time": "6:25:40", "remaining_time": "1:51:33"} +{"current_steps": 1097, "total_steps": 1413, "loss": 0.2646, "lr": 6.001671607343609e-07, "epoch": 2.3275907765703683, "percentage": 77.64, "elapsed_time": "6:26:00", "remaining_time": "1:51:11"} +{"current_steps": 1098, "total_steps": 1413, "loss": 0.0587, "lr": 5.96533225368133e-07, "epoch": 2.3297111052213095, "percentage": 77.71, "elapsed_time": "6:26:21", "remaining_time": "1:50:50"} +{"current_steps": 1099, "total_steps": 1413, "loss": 0.2278, "lr": 5.929088339819452e-07, "epoch": 2.3318314338722503, "percentage": 77.78, "elapsed_time": "6:26:43", "remaining_time": "1:50:29"} +{"current_steps": 1100, "total_steps": 1413, "loss": 0.2335, "lr": 5.892940047484915e-07, "epoch": 2.333951762523191, "percentage": 77.85, "elapsed_time": "6:27:03", "remaining_time": "1:50:08"} +{"current_steps": 1101, "total_steps": 1413, "loss": 0.1164, "lr": 5.856887557925209e-07, "epoch": 2.336072091174132, "percentage": 77.92, "elapsed_time": "6:27:25", "remaining_time": "1:49:47"} +{"current_steps": 1102, "total_steps": 1413, "loss": 0.1564, "lr": 5.820931051907471e-07, "epoch": 2.3381924198250728, "percentage": 77.99, "elapsed_time": "6:27:45", "remaining_time": "1:49:25"} +{"current_steps": 1103, "total_steps": 1413, "loss": 0.1035, "lr": 5.785070709717583e-07, "epoch": 2.3403127484760136, "percentage": 78.06, "elapsed_time": "6:28:06", "remaining_time": "1:49:04"} +{"current_steps": 1104, "total_steps": 1413, "loss": 0.1593, "lr": 5.749306711159245e-07, "epoch": 2.342433077126955, "percentage": 78.13, "elapsed_time": "6:28:27", "remaining_time": "1:48:43"} +{"current_steps": 1105, "total_steps": 1413, "loss": 0.2125, "lr": 5.713639235553115e-07, "epoch": 2.3445534057778956, "percentage": 78.2, "elapsed_time": "6:28:48", "remaining_time": "1:48:22"} +{"current_steps": 1106, "total_steps": 1413, "loss": 0.2044, "lr": 5.678068461735864e-07, "epoch": 2.3466737344288364, "percentage": 78.27, "elapsed_time": "6:29:10", "remaining_time": "1:48:01"} +{"current_steps": 1107, "total_steps": 1413, "loss": 0.1786, "lr": 5.642594568059309e-07, "epoch": 2.3487940630797772, "percentage": 78.34, "elapsed_time": "6:29:32", "remaining_time": "1:47:40"} +{"current_steps": 1108, "total_steps": 1413, "loss": 0.2013, "lr": 5.607217732389503e-07, "epoch": 2.3509143917307185, "percentage": 78.41, "elapsed_time": "6:29:53", "remaining_time": "1:47:19"} +{"current_steps": 1109, "total_steps": 1413, "loss": 0.0689, "lr": 5.571938132105867e-07, "epoch": 2.3530347203816593, "percentage": 78.49, "elapsed_time": "6:30:13", "remaining_time": "1:46:58"} +{"current_steps": 1110, "total_steps": 1413, "loss": 0.1401, "lr": 5.536755944100269e-07, "epoch": 2.3551550490326, "percentage": 78.56, "elapsed_time": "6:30:35", "remaining_time": "1:46:37"} +{"current_steps": 1111, "total_steps": 1413, "loss": 0.1351, "lr": 5.501671344776152e-07, "epoch": 2.357275377683541, "percentage": 78.63, "elapsed_time": "6:30:56", "remaining_time": "1:46:16"} +{"current_steps": 1112, "total_steps": 1413, "loss": 0.1929, "lr": 5.466684510047659e-07, "epoch": 2.3593957063344817, "percentage": 78.7, "elapsed_time": "6:31:16", "remaining_time": "1:45:54"} +{"current_steps": 1113, "total_steps": 1413, "loss": 0.1553, "lr": 5.43179561533873e-07, "epoch": 2.3615160349854225, "percentage": 78.77, "elapsed_time": "6:31:36", "remaining_time": "1:45:33"} +{"current_steps": 1114, "total_steps": 1413, "loss": 0.1258, "lr": 5.397004835582242e-07, "epoch": 2.3636363636363638, "percentage": 78.84, "elapsed_time": "6:31:56", "remaining_time": "1:45:11"} +{"current_steps": 1115, "total_steps": 1413, "loss": 0.1353, "lr": 5.362312345219125e-07, "epoch": 2.3657566922873046, "percentage": 78.91, "elapsed_time": "6:32:17", "remaining_time": "1:44:50"} +{"current_steps": 1116, "total_steps": 1413, "loss": 0.2128, "lr": 5.327718318197469e-07, "epoch": 2.3678770209382454, "percentage": 78.98, "elapsed_time": "6:32:37", "remaining_time": "1:44:29"} +{"current_steps": 1117, "total_steps": 1413, "loss": 0.0749, "lr": 5.293222927971703e-07, "epoch": 2.369997349589186, "percentage": 79.05, "elapsed_time": "6:32:58", "remaining_time": "1:44:08"} +{"current_steps": 1118, "total_steps": 1413, "loss": 0.2372, "lr": 5.258826347501655e-07, "epoch": 2.3721176782401274, "percentage": 79.12, "elapsed_time": "6:33:20", "remaining_time": "1:43:47"} +{"current_steps": 1119, "total_steps": 1413, "loss": 0.1649, "lr": 5.224528749251747e-07, "epoch": 2.3742380068910682, "percentage": 79.19, "elapsed_time": "6:33:40", "remaining_time": "1:43:25"} +{"current_steps": 1120, "total_steps": 1413, "loss": 0.1553, "lr": 5.190330305190081e-07, "epoch": 2.376358335542009, "percentage": 79.26, "elapsed_time": "6:33:59", "remaining_time": "1:43:04"} +{"current_steps": 1121, "total_steps": 1413, "loss": 0.1436, "lr": 5.156231186787633e-07, "epoch": 2.37847866419295, "percentage": 79.33, "elapsed_time": "6:34:20", "remaining_time": "1:42:43"} +{"current_steps": 1122, "total_steps": 1413, "loss": 0.1716, "lr": 5.122231565017321e-07, "epoch": 2.3805989928438906, "percentage": 79.41, "elapsed_time": "6:34:41", "remaining_time": "1:42:21"} +{"current_steps": 1123, "total_steps": 1413, "loss": 0.1668, "lr": 5.088331610353209e-07, "epoch": 2.3827193214948315, "percentage": 79.48, "elapsed_time": "6:35:01", "remaining_time": "1:42:00"} +{"current_steps": 1124, "total_steps": 1413, "loss": 0.1036, "lr": 5.054531492769637e-07, "epoch": 2.3848396501457727, "percentage": 79.55, "elapsed_time": "6:35:21", "remaining_time": "1:41:39"} +{"current_steps": 1125, "total_steps": 1413, "loss": 0.1721, "lr": 5.020831381740348e-07, "epoch": 2.3869599787967135, "percentage": 79.62, "elapsed_time": "6:35:41", "remaining_time": "1:41:17"} +{"current_steps": 1126, "total_steps": 1413, "loss": 0.0804, "lr": 4.987231446237656e-07, "epoch": 2.3890803074476543, "percentage": 79.69, "elapsed_time": "6:36:03", "remaining_time": "1:40:56"} +{"current_steps": 1127, "total_steps": 1413, "loss": 0.1742, "lr": 4.953731854731591e-07, "epoch": 2.391200636098595, "percentage": 79.76, "elapsed_time": "6:36:23", "remaining_time": "1:40:35"} +{"current_steps": 1128, "total_steps": 1413, "loss": 0.2472, "lr": 4.920332775189074e-07, "epoch": 2.3933209647495364, "percentage": 79.83, "elapsed_time": "6:36:44", "remaining_time": "1:40:14"} +{"current_steps": 1129, "total_steps": 1413, "loss": 0.1866, "lr": 4.887034375073041e-07, "epoch": 2.395441293400477, "percentage": 79.9, "elapsed_time": "6:37:05", "remaining_time": "1:39:53"} +{"current_steps": 1130, "total_steps": 1413, "loss": 0.0903, "lr": 4.853836821341632e-07, "epoch": 2.397561622051418, "percentage": 79.97, "elapsed_time": "6:37:24", "remaining_time": "1:39:31"} +{"current_steps": 1131, "total_steps": 1413, "loss": 0.1345, "lr": 4.820740280447331e-07, "epoch": 2.399681950702359, "percentage": 80.04, "elapsed_time": "6:37:44", "remaining_time": "1:39:10"} +{"current_steps": 1132, "total_steps": 1413, "loss": 0.1936, "lr": 4.787744918336173e-07, "epoch": 2.4018022793532996, "percentage": 80.11, "elapsed_time": "6:38:06", "remaining_time": "1:38:49"} +{"current_steps": 1133, "total_steps": 1413, "loss": 0.1536, "lr": 4.7548509004468444e-07, "epoch": 2.403922608004241, "percentage": 80.18, "elapsed_time": "6:38:26", "remaining_time": "1:38:28"} +{"current_steps": 1134, "total_steps": 1413, "loss": 0.1719, "lr": 4.7220583917099135e-07, "epoch": 2.4060429366551817, "percentage": 80.25, "elapsed_time": "6:38:48", "remaining_time": "1:38:07"} +{"current_steps": 1135, "total_steps": 1413, "loss": 0.1753, "lr": 4.6893675565469754e-07, "epoch": 2.4081632653061225, "percentage": 80.33, "elapsed_time": "6:39:10", "remaining_time": "1:37:46"} +{"current_steps": 1136, "total_steps": 1413, "loss": 0.1237, "lr": 4.656778558869848e-07, "epoch": 2.4102835939570633, "percentage": 80.4, "elapsed_time": "6:39:30", "remaining_time": "1:37:24"} +{"current_steps": 1137, "total_steps": 1413, "loss": 0.1424, "lr": 4.624291562079719e-07, "epoch": 2.412403922608004, "percentage": 80.47, "elapsed_time": "6:39:52", "remaining_time": "1:37:04"} +{"current_steps": 1138, "total_steps": 1413, "loss": 0.1932, "lr": 4.5919067290663503e-07, "epoch": 2.4145242512589453, "percentage": 80.54, "elapsed_time": "6:40:12", "remaining_time": "1:36:42"} +{"current_steps": 1139, "total_steps": 1413, "loss": 0.1664, "lr": 4.5596242222072457e-07, "epoch": 2.416644579909886, "percentage": 80.61, "elapsed_time": "6:40:34", "remaining_time": "1:36:21"} +{"current_steps": 1140, "total_steps": 1413, "loss": 0.2251, "lr": 4.527444203366868e-07, "epoch": 2.418764908560827, "percentage": 80.68, "elapsed_time": "6:40:55", "remaining_time": "1:36:00"} +{"current_steps": 1141, "total_steps": 1413, "loss": 0.1409, "lr": 4.4953668338957896e-07, "epoch": 2.4208852372117677, "percentage": 80.75, "elapsed_time": "6:41:16", "remaining_time": "1:35:39"} +{"current_steps": 1142, "total_steps": 1413, "loss": 0.191, "lr": 4.4633922746298965e-07, "epoch": 2.4230055658627085, "percentage": 80.82, "elapsed_time": "6:41:36", "remaining_time": "1:35:18"} +{"current_steps": 1143, "total_steps": 1413, "loss": 0.2368, "lr": 4.431520685889587e-07, "epoch": 2.42512589451365, "percentage": 80.89, "elapsed_time": "6:41:58", "remaining_time": "1:34:57"} +{"current_steps": 1144, "total_steps": 1413, "loss": 0.1493, "lr": 4.3997522274789735e-07, "epoch": 2.4272462231645906, "percentage": 80.96, "elapsed_time": "6:42:19", "remaining_time": "1:34:36"} +{"current_steps": 1145, "total_steps": 1413, "loss": 0.1692, "lr": 4.3680870586850636e-07, "epoch": 2.4293665518155314, "percentage": 81.03, "elapsed_time": "6:42:39", "remaining_time": "1:34:14"} +{"current_steps": 1146, "total_steps": 1413, "loss": 0.1777, "lr": 4.33652533827697e-07, "epoch": 2.431486880466472, "percentage": 81.1, "elapsed_time": "6:42:59", "remaining_time": "1:33:53"} +{"current_steps": 1147, "total_steps": 1413, "loss": 0.1687, "lr": 4.30506722450513e-07, "epoch": 2.433607209117413, "percentage": 81.17, "elapsed_time": "6:43:20", "remaining_time": "1:33:32"} +{"current_steps": 1148, "total_steps": 1413, "loss": 0.1453, "lr": 4.2737128751004804e-07, "epoch": 2.4357275377683543, "percentage": 81.25, "elapsed_time": "6:43:40", "remaining_time": "1:33:10"} +{"current_steps": 1149, "total_steps": 1413, "loss": 0.1837, "lr": 4.2424624472736904e-07, "epoch": 2.437847866419295, "percentage": 81.32, "elapsed_time": "6:44:01", "remaining_time": "1:32:49"} +{"current_steps": 1150, "total_steps": 1413, "loss": 0.1461, "lr": 4.21131609771436e-07, "epoch": 2.439968195070236, "percentage": 81.39, "elapsed_time": "6:44:21", "remaining_time": "1:32:28"} +{"current_steps": 1151, "total_steps": 1413, "loss": 0.1405, "lr": 4.1802739825902604e-07, "epoch": 2.4420885237211767, "percentage": 81.46, "elapsed_time": "6:44:41", "remaining_time": "1:32:07"} +{"current_steps": 1152, "total_steps": 1413, "loss": 0.1662, "lr": 4.149336257546513e-07, "epoch": 2.4442088523721175, "percentage": 81.53, "elapsed_time": "6:45:02", "remaining_time": "1:31:46"} +{"current_steps": 1153, "total_steps": 1413, "loss": 0.1365, "lr": 4.1185030777048385e-07, "epoch": 2.4463291810230587, "percentage": 81.6, "elapsed_time": "6:45:23", "remaining_time": "1:31:24"} +{"current_steps": 1154, "total_steps": 1413, "loss": 0.1012, "lr": 4.0877745976627416e-07, "epoch": 2.4484495096739995, "percentage": 81.67, "elapsed_time": "6:45:43", "remaining_time": "1:31:03"} +{"current_steps": 1155, "total_steps": 1413, "loss": 0.16, "lr": 4.0571509714928015e-07, "epoch": 2.4505698383249404, "percentage": 81.74, "elapsed_time": "6:46:05", "remaining_time": "1:30:42"} +{"current_steps": 1156, "total_steps": 1413, "loss": 0.1339, "lr": 4.0266323527418384e-07, "epoch": 2.452690166975881, "percentage": 81.81, "elapsed_time": "6:46:26", "remaining_time": "1:30:21"} +{"current_steps": 1157, "total_steps": 1413, "loss": 0.1725, "lr": 3.996218894430165e-07, "epoch": 2.454810495626822, "percentage": 81.88, "elapsed_time": "6:46:46", "remaining_time": "1:30:00"} +{"current_steps": 1158, "total_steps": 1413, "loss": 0.1981, "lr": 3.965910749050822e-07, "epoch": 2.456930824277763, "percentage": 81.95, "elapsed_time": "6:47:07", "remaining_time": "1:29:39"} +{"current_steps": 1159, "total_steps": 1413, "loss": 0.1306, "lr": 3.935708068568822e-07, "epoch": 2.459051152928704, "percentage": 82.02, "elapsed_time": "6:47:29", "remaining_time": "1:29:18"} +{"current_steps": 1160, "total_steps": 1413, "loss": 0.1381, "lr": 3.9056110044203594e-07, "epoch": 2.461171481579645, "percentage": 82.09, "elapsed_time": "6:47:50", "remaining_time": "1:28:57"} +{"current_steps": 1161, "total_steps": 1413, "loss": 0.1665, "lr": 3.875619707512082e-07, "epoch": 2.4632918102305856, "percentage": 82.17, "elapsed_time": "6:48:11", "remaining_time": "1:28:36"} +{"current_steps": 1162, "total_steps": 1413, "loss": 0.153, "lr": 3.845734328220302e-07, "epoch": 2.4654121388815264, "percentage": 82.24, "elapsed_time": "6:48:32", "remaining_time": "1:28:14"} +{"current_steps": 1163, "total_steps": 1413, "loss": 0.2096, "lr": 3.8159550163902936e-07, "epoch": 2.4675324675324677, "percentage": 82.31, "elapsed_time": "6:48:53", "remaining_time": "1:27:53"} +{"current_steps": 1164, "total_steps": 1413, "loss": 0.1243, "lr": 3.786281921335483e-07, "epoch": 2.4696527961834085, "percentage": 82.38, "elapsed_time": "6:49:14", "remaining_time": "1:27:32"} +{"current_steps": 1165, "total_steps": 1413, "loss": 0.1478, "lr": 3.7567151918367156e-07, "epoch": 2.4717731248343493, "percentage": 82.45, "elapsed_time": "6:49:34", "remaining_time": "1:27:11"} +{"current_steps": 1166, "total_steps": 1413, "loss": 0.1344, "lr": 3.727254976141556e-07, "epoch": 2.47389345348529, "percentage": 82.52, "elapsed_time": "6:49:55", "remaining_time": "1:26:50"} +{"current_steps": 1167, "total_steps": 1413, "loss": 0.1596, "lr": 3.697901421963482e-07, "epoch": 2.4760137821362314, "percentage": 82.59, "elapsed_time": "6:50:16", "remaining_time": "1:26:29"} +{"current_steps": 1168, "total_steps": 1413, "loss": 0.1897, "lr": 3.6686546764811787e-07, "epoch": 2.478134110787172, "percentage": 82.66, "elapsed_time": "6:50:37", "remaining_time": "1:26:07"} +{"current_steps": 1169, "total_steps": 1413, "loss": 0.123, "lr": 3.639514886337786e-07, "epoch": 2.480254439438113, "percentage": 82.73, "elapsed_time": "6:50:59", "remaining_time": "1:25:46"} +{"current_steps": 1170, "total_steps": 1413, "loss": 0.1602, "lr": 3.6104821976401834e-07, "epoch": 2.4823747680890538, "percentage": 82.8, "elapsed_time": "6:51:20", "remaining_time": "1:25:25"} +{"current_steps": 1171, "total_steps": 1413, "loss": 0.1281, "lr": 3.581556755958232e-07, "epoch": 2.4844950967399946, "percentage": 82.87, "elapsed_time": "6:51:44", "remaining_time": "1:25:05"} +{"current_steps": 1172, "total_steps": 1413, "loss": 0.2761, "lr": 3.552738706324063e-07, "epoch": 2.4866154253909354, "percentage": 82.94, "elapsed_time": "6:52:05", "remaining_time": "1:24:44"} +{"current_steps": 1173, "total_steps": 1413, "loss": 0.1354, "lr": 3.524028193231338e-07, "epoch": 2.4887357540418766, "percentage": 83.01, "elapsed_time": "6:52:27", "remaining_time": "1:24:23"} +{"current_steps": 1174, "total_steps": 1413, "loss": 0.2041, "lr": 3.4954253606345386e-07, "epoch": 2.4908560826928174, "percentage": 83.09, "elapsed_time": "6:52:47", "remaining_time": "1:24:02"} +{"current_steps": 1175, "total_steps": 1413, "loss": 0.1717, "lr": 3.466930351948225e-07, "epoch": 2.4929764113437582, "percentage": 83.16, "elapsed_time": "6:53:08", "remaining_time": "1:23:40"} +{"current_steps": 1176, "total_steps": 1413, "loss": 0.2393, "lr": 3.438543310046341e-07, "epoch": 2.495096739994699, "percentage": 83.23, "elapsed_time": "6:53:28", "remaining_time": "1:23:19"} +{"current_steps": 1177, "total_steps": 1413, "loss": 0.2275, "lr": 3.4102643772614713e-07, "epoch": 2.4972170686456403, "percentage": 83.3, "elapsed_time": "6:53:49", "remaining_time": "1:22:58"} +{"current_steps": 1178, "total_steps": 1413, "loss": 0.1546, "lr": 3.3820936953841585e-07, "epoch": 2.499337397296581, "percentage": 83.37, "elapsed_time": "6:54:10", "remaining_time": "1:22:37"} +{"current_steps": 1179, "total_steps": 1413, "loss": 0.1479, "lr": 3.354031405662167e-07, "epoch": 2.501457725947522, "percentage": 83.44, "elapsed_time": "6:54:31", "remaining_time": "1:22:16"} +{"current_steps": 1180, "total_steps": 1413, "loss": 0.1361, "lr": 3.3260776487997803e-07, "epoch": 2.5035780545984627, "percentage": 83.51, "elapsed_time": "6:54:52", "remaining_time": "1:21:55"} +{"current_steps": 1181, "total_steps": 1413, "loss": 0.1951, "lr": 3.2982325649570907e-07, "epoch": 2.5056983832494035, "percentage": 83.58, "elapsed_time": "6:55:13", "remaining_time": "1:21:34"} +{"current_steps": 1182, "total_steps": 1413, "loss": 0.0913, "lr": 3.2704962937493314e-07, "epoch": 2.5078187119003443, "percentage": 83.65, "elapsed_time": "6:55:34", "remaining_time": "1:21:12"} +{"current_steps": 1183, "total_steps": 1413, "loss": 0.182, "lr": 3.2428689742461187e-07, "epoch": 2.5099390405512856, "percentage": 83.72, "elapsed_time": "6:55:55", "remaining_time": "1:20:51"} +{"current_steps": 1184, "total_steps": 1413, "loss": 0.1474, "lr": 3.215350744970808e-07, "epoch": 2.5120593692022264, "percentage": 83.79, "elapsed_time": "6:56:17", "remaining_time": "1:20:30"} +{"current_steps": 1185, "total_steps": 1413, "loss": 0.2535, "lr": 3.1879417438997583e-07, "epoch": 2.514179697853167, "percentage": 83.86, "elapsed_time": "6:56:38", "remaining_time": "1:20:09"} +{"current_steps": 1186, "total_steps": 1413, "loss": 0.0681, "lr": 3.16064210846167e-07, "epoch": 2.516300026504108, "percentage": 83.93, "elapsed_time": "6:56:59", "remaining_time": "1:19:48"} +{"current_steps": 1187, "total_steps": 1413, "loss": 0.1279, "lr": 3.1334519755368805e-07, "epoch": 2.5184203551550493, "percentage": 84.01, "elapsed_time": "6:57:19", "remaining_time": "1:19:27"} +{"current_steps": 1188, "total_steps": 1413, "loss": 0.1971, "lr": 3.106371481456677e-07, "epoch": 2.52054068380599, "percentage": 84.08, "elapsed_time": "6:57:40", "remaining_time": "1:19:06"} +{"current_steps": 1189, "total_steps": 1413, "loss": 0.2494, "lr": 3.079400762002635e-07, "epoch": 2.522661012456931, "percentage": 84.15, "elapsed_time": "6:58:02", "remaining_time": "1:18:45"} +{"current_steps": 1190, "total_steps": 1413, "loss": 0.183, "lr": 3.0525399524059055e-07, "epoch": 2.5247813411078717, "percentage": 84.22, "elapsed_time": "6:58:23", "remaining_time": "1:18:24"} +{"current_steps": 1191, "total_steps": 1413, "loss": 0.1433, "lr": 3.025789187346548e-07, "epoch": 2.5269016697588125, "percentage": 84.29, "elapsed_time": "6:58:44", "remaining_time": "1:18:03"} +{"current_steps": 1192, "total_steps": 1413, "loss": 0.2281, "lr": 2.9991486009528696e-07, "epoch": 2.5290219984097533, "percentage": 84.36, "elapsed_time": "6:59:05", "remaining_time": "1:17:41"} +{"current_steps": 1193, "total_steps": 1413, "loss": 0.183, "lr": 2.9726183268007304e-07, "epoch": 2.5311423270606945, "percentage": 84.43, "elapsed_time": "6:59:26", "remaining_time": "1:17:20"} +{"current_steps": 1194, "total_steps": 1413, "loss": 0.1823, "lr": 2.9461984979129056e-07, "epoch": 2.5332626557116353, "percentage": 84.5, "elapsed_time": "6:59:48", "remaining_time": "1:16:59"} +{"current_steps": 1195, "total_steps": 1413, "loss": 0.1234, "lr": 2.919889246758373e-07, "epoch": 2.535382984362576, "percentage": 84.57, "elapsed_time": "7:00:09", "remaining_time": "1:16:38"} +{"current_steps": 1196, "total_steps": 1413, "loss": 0.2472, "lr": 2.8936907052516923e-07, "epoch": 2.537503313013517, "percentage": 84.64, "elapsed_time": "7:00:30", "remaining_time": "1:16:17"} +{"current_steps": 1197, "total_steps": 1413, "loss": 0.1547, "lr": 2.8676030047523115e-07, "epoch": 2.539623641664458, "percentage": 84.71, "elapsed_time": "7:00:50", "remaining_time": "1:15:56"} +{"current_steps": 1198, "total_steps": 1413, "loss": 0.1421, "lr": 2.841626276063933e-07, "epoch": 2.541743970315399, "percentage": 84.78, "elapsed_time": "7:01:11", "remaining_time": "1:15:35"} +{"current_steps": 1199, "total_steps": 1413, "loss": 0.0918, "lr": 2.815760649433841e-07, "epoch": 2.54386429896634, "percentage": 84.85, "elapsed_time": "7:01:32", "remaining_time": "1:15:14"} +{"current_steps": 1200, "total_steps": 1413, "loss": 0.1396, "lr": 2.7900062545522493e-07, "epoch": 2.5459846276172806, "percentage": 84.93, "elapsed_time": "7:01:52", "remaining_time": "1:14:53"} +{"current_steps": 1201, "total_steps": 1413, "loss": 0.1228, "lr": 2.764363220551672e-07, "epoch": 2.5481049562682214, "percentage": 85.0, "elapsed_time": "7:02:12", "remaining_time": "1:14:31"} +{"current_steps": 1202, "total_steps": 1413, "loss": 0.1093, "lr": 2.7388316760062457e-07, "epoch": 2.5502252849191622, "percentage": 85.07, "elapsed_time": "7:02:34", "remaining_time": "1:14:10"} +{"current_steps": 1203, "total_steps": 1413, "loss": 0.1161, "lr": 2.7134117489311023e-07, "epoch": 2.5523456135701035, "percentage": 85.14, "elapsed_time": "7:02:56", "remaining_time": "1:13:49"} +{"current_steps": 1204, "total_steps": 1413, "loss": 0.087, "lr": 2.688103566781719e-07, "epoch": 2.5544659422210443, "percentage": 85.21, "elapsed_time": "7:03:16", "remaining_time": "1:13:28"} +{"current_steps": 1205, "total_steps": 1413, "loss": 0.163, "lr": 2.6629072564533007e-07, "epoch": 2.556586270871985, "percentage": 85.28, "elapsed_time": "7:03:39", "remaining_time": "1:13:07"} +{"current_steps": 1206, "total_steps": 1413, "loss": 0.2213, "lr": 2.6378229442801163e-07, "epoch": 2.558706599522926, "percentage": 85.35, "elapsed_time": "7:04:01", "remaining_time": "1:12:46"} +{"current_steps": 1207, "total_steps": 1413, "loss": 0.1643, "lr": 2.6128507560348626e-07, "epoch": 2.560826928173867, "percentage": 85.42, "elapsed_time": "7:04:23", "remaining_time": "1:12:25"} +{"current_steps": 1208, "total_steps": 1413, "loss": 0.1321, "lr": 2.5879908169280653e-07, "epoch": 2.562947256824808, "percentage": 85.49, "elapsed_time": "7:04:43", "remaining_time": "1:12:04"} +{"current_steps": 1209, "total_steps": 1413, "loss": 0.1203, "lr": 2.563243251607433e-07, "epoch": 2.5650675854757488, "percentage": 85.56, "elapsed_time": "7:05:04", "remaining_time": "1:11:43"} +{"current_steps": 1210, "total_steps": 1413, "loss": 0.1767, "lr": 2.538608184157229e-07, "epoch": 2.5671879141266896, "percentage": 85.63, "elapsed_time": "7:05:25", "remaining_time": "1:11:22"} +{"current_steps": 1211, "total_steps": 1413, "loss": 0.1699, "lr": 2.5140857380976436e-07, "epoch": 2.5693082427776304, "percentage": 85.7, "elapsed_time": "7:05:45", "remaining_time": "1:11:01"} +{"current_steps": 1212, "total_steps": 1413, "loss": 0.1116, "lr": 2.489676036384192e-07, "epoch": 2.571428571428571, "percentage": 85.77, "elapsed_time": "7:06:06", "remaining_time": "1:10:40"} +{"current_steps": 1213, "total_steps": 1413, "loss": 0.1551, "lr": 2.4653792014070923e-07, "epoch": 2.5735489000795124, "percentage": 85.85, "elapsed_time": "7:06:28", "remaining_time": "1:10:19"} +{"current_steps": 1214, "total_steps": 1413, "loss": 0.1659, "lr": 2.441195354990644e-07, "epoch": 2.5756692287304532, "percentage": 85.92, "elapsed_time": "7:06:50", "remaining_time": "1:09:58"} +{"current_steps": 1215, "total_steps": 1413, "loss": 0.1267, "lr": 2.4171246183926247e-07, "epoch": 2.577789557381394, "percentage": 85.99, "elapsed_time": "7:07:10", "remaining_time": "1:09:36"} +{"current_steps": 1216, "total_steps": 1413, "loss": 0.2032, "lr": 2.393167112303668e-07, "epoch": 2.5799098860323353, "percentage": 86.06, "elapsed_time": "7:07:30", "remaining_time": "1:09:15"} +{"current_steps": 1217, "total_steps": 1413, "loss": 0.1342, "lr": 2.3693229568466952e-07, "epoch": 2.582030214683276, "percentage": 86.13, "elapsed_time": "7:07:52", "remaining_time": "1:08:54"} +{"current_steps": 1218, "total_steps": 1413, "loss": 0.2205, "lr": 2.345592271576261e-07, "epoch": 2.584150543334217, "percentage": 86.2, "elapsed_time": "7:08:13", "remaining_time": "1:08:33"} +{"current_steps": 1219, "total_steps": 1413, "loss": 0.1616, "lr": 2.3219751754779862e-07, "epoch": 2.5862708719851577, "percentage": 86.27, "elapsed_time": "7:08:33", "remaining_time": "1:08:12"} +{"current_steps": 1220, "total_steps": 1413, "loss": 0.0837, "lr": 2.2984717869679762e-07, "epoch": 2.5883912006360985, "percentage": 86.34, "elapsed_time": "7:08:54", "remaining_time": "1:07:51"} +{"current_steps": 1221, "total_steps": 1413, "loss": 0.1858, "lr": 2.2750822238921861e-07, "epoch": 2.5905115292870393, "percentage": 86.41, "elapsed_time": "7:09:14", "remaining_time": "1:07:29"} +{"current_steps": 1222, "total_steps": 1413, "loss": 0.1615, "lr": 2.251806603525855e-07, "epoch": 2.59263185793798, "percentage": 86.48, "elapsed_time": "7:09:35", "remaining_time": "1:07:08"} +{"current_steps": 1223, "total_steps": 1413, "loss": 0.1641, "lr": 2.228645042572908e-07, "epoch": 2.5947521865889214, "percentage": 86.55, "elapsed_time": "7:09:57", "remaining_time": "1:06:47"} +{"current_steps": 1224, "total_steps": 1413, "loss": 0.1021, "lr": 2.2055976571653953e-07, "epoch": 2.596872515239862, "percentage": 86.62, "elapsed_time": "7:10:18", "remaining_time": "1:06:26"} +{"current_steps": 1225, "total_steps": 1413, "loss": 0.1784, "lr": 2.1826645628628712e-07, "epoch": 2.598992843890803, "percentage": 86.69, "elapsed_time": "7:10:40", "remaining_time": "1:06:05"} +{"current_steps": 1226, "total_steps": 1413, "loss": 0.099, "lr": 2.1598458746518448e-07, "epoch": 2.6011131725417442, "percentage": 86.77, "elapsed_time": "7:11:02", "remaining_time": "1:05:44"} +{"current_steps": 1227, "total_steps": 1413, "loss": 0.1403, "lr": 2.1371417069451867e-07, "epoch": 2.603233501192685, "percentage": 86.84, "elapsed_time": "7:11:22", "remaining_time": "1:05:23"} +{"current_steps": 1228, "total_steps": 1413, "loss": 0.0802, "lr": 2.1145521735815716e-07, "epoch": 2.605353829843626, "percentage": 86.91, "elapsed_time": "7:11:43", "remaining_time": "1:05:02"} +{"current_steps": 1229, "total_steps": 1413, "loss": 0.2204, "lr": 2.092077387824884e-07, "epoch": 2.6074741584945667, "percentage": 86.98, "elapsed_time": "7:12:04", "remaining_time": "1:04:41"} +{"current_steps": 1230, "total_steps": 1413, "loss": 0.2012, "lr": 2.0697174623636795e-07, "epoch": 2.6095944871455075, "percentage": 87.05, "elapsed_time": "7:12:24", "remaining_time": "1:04:20"} +{"current_steps": 1231, "total_steps": 1413, "loss": 0.1189, "lr": 2.0474725093105857e-07, "epoch": 2.6117148157964483, "percentage": 87.12, "elapsed_time": "7:12:46", "remaining_time": "1:03:59"} +{"current_steps": 1232, "total_steps": 1413, "loss": 0.1462, "lr": 2.025342640201783e-07, "epoch": 2.613835144447389, "percentage": 87.19, "elapsed_time": "7:13:06", "remaining_time": "1:03:37"} +{"current_steps": 1233, "total_steps": 1413, "loss": 0.1963, "lr": 2.003327965996399e-07, "epoch": 2.6159554730983303, "percentage": 87.26, "elapsed_time": "7:13:27", "remaining_time": "1:03:16"} +{"current_steps": 1234, "total_steps": 1413, "loss": 0.1338, "lr": 1.981428597075985e-07, "epoch": 2.618075801749271, "percentage": 87.33, "elapsed_time": "7:13:49", "remaining_time": "1:02:55"} +{"current_steps": 1235, "total_steps": 1413, "loss": 0.1657, "lr": 1.9596446432439465e-07, "epoch": 2.620196130400212, "percentage": 87.4, "elapsed_time": "7:14:09", "remaining_time": "1:02:34"} +{"current_steps": 1236, "total_steps": 1413, "loss": 0.1489, "lr": 1.9379762137250069e-07, "epoch": 2.622316459051153, "percentage": 87.47, "elapsed_time": "7:14:29", "remaining_time": "1:02:13"} +{"current_steps": 1237, "total_steps": 1413, "loss": 0.16, "lr": 1.9164234171646423e-07, "epoch": 2.624436787702094, "percentage": 87.54, "elapsed_time": "7:14:51", "remaining_time": "1:01:52"} +{"current_steps": 1238, "total_steps": 1413, "loss": 0.149, "lr": 1.894986361628548e-07, "epoch": 2.626557116353035, "percentage": 87.62, "elapsed_time": "7:15:12", "remaining_time": "1:01:31"} +{"current_steps": 1239, "total_steps": 1413, "loss": 0.1035, "lr": 1.8736651546020946e-07, "epoch": 2.6286774450039756, "percentage": 87.69, "elapsed_time": "7:15:33", "remaining_time": "1:01:10"} +{"current_steps": 1240, "total_steps": 1413, "loss": 0.1697, "lr": 1.852459902989784e-07, "epoch": 2.6307977736549164, "percentage": 87.76, "elapsed_time": "7:15:54", "remaining_time": "1:00:48"} +{"current_steps": 1241, "total_steps": 1413, "loss": 0.1162, "lr": 1.8313707131147217e-07, "epoch": 2.632918102305857, "percentage": 87.83, "elapsed_time": "7:16:14", "remaining_time": "1:00:27"} +{"current_steps": 1242, "total_steps": 1413, "loss": 0.1021, "lr": 1.8103976907180798e-07, "epoch": 2.6350384309567985, "percentage": 87.9, "elapsed_time": "7:16:35", "remaining_time": "1:00:06"} +{"current_steps": 1243, "total_steps": 1413, "loss": 0.1861, "lr": 1.789540940958573e-07, "epoch": 2.6371587596077393, "percentage": 87.97, "elapsed_time": "7:16:56", "remaining_time": "0:59:45"} +{"current_steps": 1244, "total_steps": 1413, "loss": 0.1493, "lr": 1.768800568411913e-07, "epoch": 2.63927908825868, "percentage": 88.04, "elapsed_time": "7:17:16", "remaining_time": "0:59:24"} +{"current_steps": 1245, "total_steps": 1413, "loss": 0.1817, "lr": 1.7481766770703013e-07, "epoch": 2.641399416909621, "percentage": 88.11, "elapsed_time": "7:17:37", "remaining_time": "0:59:03"} +{"current_steps": 1246, "total_steps": 1413, "loss": 0.1297, "lr": 1.7276693703419058e-07, "epoch": 2.643519745560562, "percentage": 88.18, "elapsed_time": "7:17:57", "remaining_time": "0:58:41"} +{"current_steps": 1247, "total_steps": 1413, "loss": 0.171, "lr": 1.7072787510503313e-07, "epoch": 2.645640074211503, "percentage": 88.25, "elapsed_time": "7:18:17", "remaining_time": "0:58:20"} +{"current_steps": 1248, "total_steps": 1413, "loss": 0.2401, "lr": 1.6870049214341266e-07, "epoch": 2.6477604028624437, "percentage": 88.32, "elapsed_time": "7:18:38", "remaining_time": "0:57:59"} +{"current_steps": 1249, "total_steps": 1413, "loss": 0.1526, "lr": 1.6668479831462498e-07, "epoch": 2.6498807315133845, "percentage": 88.39, "elapsed_time": "7:18:59", "remaining_time": "0:57:38"} +{"current_steps": 1250, "total_steps": 1413, "loss": 0.1687, "lr": 1.6468080372535472e-07, "epoch": 2.6520010601643254, "percentage": 88.46, "elapsed_time": "7:19:18", "remaining_time": "0:57:17"} +{"current_steps": 1251, "total_steps": 1413, "loss": 0.1425, "lr": 1.6268851842362988e-07, "epoch": 2.654121388815266, "percentage": 88.54, "elapsed_time": "7:19:39", "remaining_time": "0:56:56"} +{"current_steps": 1252, "total_steps": 1413, "loss": 0.1047, "lr": 1.607079523987662e-07, "epoch": 2.6562417174662074, "percentage": 88.61, "elapsed_time": "7:19:59", "remaining_time": "0:56:34"} +{"current_steps": 1253, "total_steps": 1413, "loss": 0.0906, "lr": 1.5873911558131866e-07, "epoch": 2.658362046117148, "percentage": 88.68, "elapsed_time": "7:20:19", "remaining_time": "0:56:13"} +{"current_steps": 1254, "total_steps": 1413, "loss": 0.2841, "lr": 1.5678201784303293e-07, "epoch": 2.660482374768089, "percentage": 88.75, "elapsed_time": "7:20:40", "remaining_time": "0:55:52"} +{"current_steps": 1255, "total_steps": 1413, "loss": 0.189, "lr": 1.548366689967948e-07, "epoch": 2.66260270341903, "percentage": 88.82, "elapsed_time": "7:21:01", "remaining_time": "0:55:31"} +{"current_steps": 1256, "total_steps": 1413, "loss": 0.1188, "lr": 1.52903078796581e-07, "epoch": 2.664723032069971, "percentage": 88.89, "elapsed_time": "7:21:21", "remaining_time": "0:55:10"} +{"current_steps": 1257, "total_steps": 1413, "loss": 0.1719, "lr": 1.5098125693741027e-07, "epoch": 2.666843360720912, "percentage": 88.96, "elapsed_time": "7:21:42", "remaining_time": "0:54:49"} +{"current_steps": 1258, "total_steps": 1413, "loss": 0.1993, "lr": 1.490712130552946e-07, "epoch": 2.6689636893718527, "percentage": 89.03, "elapsed_time": "7:22:02", "remaining_time": "0:54:27"} +{"current_steps": 1259, "total_steps": 1413, "loss": 0.0885, "lr": 1.471729567271929e-07, "epoch": 2.6710840180227935, "percentage": 89.1, "elapsed_time": "7:22:22", "remaining_time": "0:54:06"} +{"current_steps": 1260, "total_steps": 1413, "loss": 0.1655, "lr": 1.4528649747095863e-07, "epoch": 2.6732043466737343, "percentage": 89.17, "elapsed_time": "7:22:43", "remaining_time": "0:53:45"} +{"current_steps": 1261, "total_steps": 1413, "loss": 0.1801, "lr": 1.4341184474529646e-07, "epoch": 2.675324675324675, "percentage": 89.24, "elapsed_time": "7:23:05", "remaining_time": "0:53:24"} +{"current_steps": 1262, "total_steps": 1413, "loss": 0.094, "lr": 1.4154900794971337e-07, "epoch": 2.6774450039756164, "percentage": 89.31, "elapsed_time": "7:23:25", "remaining_time": "0:53:03"} +{"current_steps": 1263, "total_steps": 1413, "loss": 0.1391, "lr": 1.3969799642447047e-07, "epoch": 2.679565332626557, "percentage": 89.38, "elapsed_time": "7:23:45", "remaining_time": "0:52:42"} +{"current_steps": 1264, "total_steps": 1413, "loss": 0.1501, "lr": 1.378588194505373e-07, "epoch": 2.681685661277498, "percentage": 89.46, "elapsed_time": "7:24:07", "remaining_time": "0:52:21"} +{"current_steps": 1265, "total_steps": 1413, "loss": 0.1566, "lr": 1.3603148624954488e-07, "epoch": 2.6838059899284388, "percentage": 89.53, "elapsed_time": "7:24:28", "remaining_time": "0:52:00"} +{"current_steps": 1266, "total_steps": 1413, "loss": 0.2451, "lr": 1.3421600598373886e-07, "epoch": 2.68592631857938, "percentage": 89.6, "elapsed_time": "7:24:50", "remaining_time": "0:51:39"} +{"current_steps": 1267, "total_steps": 1413, "loss": 0.1454, "lr": 1.3241238775593634e-07, "epoch": 2.688046647230321, "percentage": 89.67, "elapsed_time": "7:25:11", "remaining_time": "0:51:17"} +{"current_steps": 1268, "total_steps": 1413, "loss": 0.1908, "lr": 1.306206406094762e-07, "epoch": 2.6901669758812616, "percentage": 89.74, "elapsed_time": "7:25:31", "remaining_time": "0:50:56"} +{"current_steps": 1269, "total_steps": 1413, "loss": 0.1143, "lr": 1.2884077352817659e-07, "epoch": 2.6922873045322024, "percentage": 89.81, "elapsed_time": "7:25:52", "remaining_time": "0:50:35"} +{"current_steps": 1270, "total_steps": 1413, "loss": 0.1197, "lr": 1.2707279543628853e-07, "epoch": 2.6944076331831432, "percentage": 89.88, "elapsed_time": "7:26:12", "remaining_time": "0:50:14"} +{"current_steps": 1271, "total_steps": 1413, "loss": 0.1989, "lr": 1.2531671519845218e-07, "epoch": 2.696527961834084, "percentage": 89.95, "elapsed_time": "7:26:33", "remaining_time": "0:49:53"} +{"current_steps": 1272, "total_steps": 1413, "loss": 0.1403, "lr": 1.2357254161965176e-07, "epoch": 2.6986482904850253, "percentage": 90.02, "elapsed_time": "7:26:53", "remaining_time": "0:49:32"} +{"current_steps": 1273, "total_steps": 1413, "loss": 0.2304, "lr": 1.2184028344517096e-07, "epoch": 2.700768619135966, "percentage": 90.09, "elapsed_time": "7:27:13", "remaining_time": "0:49:11"} +{"current_steps": 1274, "total_steps": 1413, "loss": 0.1451, "lr": 1.2011994936055066e-07, "epoch": 2.702888947786907, "percentage": 90.16, "elapsed_time": "7:27:34", "remaining_time": "0:48:49"} +{"current_steps": 1275, "total_steps": 1413, "loss": 0.0898, "lr": 1.1841154799154376e-07, "epoch": 2.7050092764378477, "percentage": 90.23, "elapsed_time": "7:27:54", "remaining_time": "0:48:28"} +{"current_steps": 1276, "total_steps": 1413, "loss": 0.1182, "lr": 1.1671508790407238e-07, "epoch": 2.707129605088789, "percentage": 90.3, "elapsed_time": "7:28:15", "remaining_time": "0:48:07"} +{"current_steps": 1277, "total_steps": 1413, "loss": 0.1747, "lr": 1.1503057760418518e-07, "epoch": 2.7092499337397298, "percentage": 90.38, "elapsed_time": "7:28:36", "remaining_time": "0:47:46"} +{"current_steps": 1278, "total_steps": 1413, "loss": 0.1696, "lr": 1.1335802553801512e-07, "epoch": 2.7113702623906706, "percentage": 90.45, "elapsed_time": "7:28:56", "remaining_time": "0:47:25"} +{"current_steps": 1279, "total_steps": 1413, "loss": 0.1617, "lr": 1.1169744009173588e-07, "epoch": 2.7134905910416114, "percentage": 90.52, "elapsed_time": "7:29:18", "remaining_time": "0:47:04"} +{"current_steps": 1280, "total_steps": 1413, "loss": 0.1001, "lr": 1.1004882959152085e-07, "epoch": 2.715610919692552, "percentage": 90.59, "elapsed_time": "7:29:38", "remaining_time": "0:46:43"} +{"current_steps": 1281, "total_steps": 1413, "loss": 0.1711, "lr": 1.0841220230350142e-07, "epoch": 2.717731248343493, "percentage": 90.66, "elapsed_time": "7:29:59", "remaining_time": "0:46:22"} +{"current_steps": 1282, "total_steps": 1413, "loss": 0.0921, "lr": 1.0678756643372423e-07, "epoch": 2.7198515769944343, "percentage": 90.73, "elapsed_time": "7:30:21", "remaining_time": "0:46:01"} +{"current_steps": 1283, "total_steps": 1413, "loss": 0.1551, "lr": 1.0517493012811159e-07, "epoch": 2.721971905645375, "percentage": 90.8, "elapsed_time": "7:30:43", "remaining_time": "0:45:40"} +{"current_steps": 1284, "total_steps": 1413, "loss": 0.1658, "lr": 1.0357430147242026e-07, "epoch": 2.724092234296316, "percentage": 90.87, "elapsed_time": "7:31:03", "remaining_time": "0:45:19"} +{"current_steps": 1285, "total_steps": 1413, "loss": 0.1094, "lr": 1.0198568849219964e-07, "epoch": 2.7262125629472567, "percentage": 90.94, "elapsed_time": "7:31:24", "remaining_time": "0:44:57"} +{"current_steps": 1286, "total_steps": 1413, "loss": 0.2643, "lr": 1.0040909915275399e-07, "epoch": 2.728332891598198, "percentage": 91.01, "elapsed_time": "7:31:45", "remaining_time": "0:44:36"} +{"current_steps": 1287, "total_steps": 1413, "loss": 0.0869, "lr": 9.884454135910021e-08, "epoch": 2.7304532202491387, "percentage": 91.08, "elapsed_time": "7:32:06", "remaining_time": "0:44:15"} +{"current_steps": 1288, "total_steps": 1413, "loss": 0.1214, "lr": 9.729202295592877e-08, "epoch": 2.7325735489000795, "percentage": 91.15, "elapsed_time": "7:32:26", "remaining_time": "0:43:54"} +{"current_steps": 1289, "total_steps": 1413, "loss": 0.2651, "lr": 9.575155172756506e-08, "epoch": 2.7346938775510203, "percentage": 91.22, "elapsed_time": "7:32:47", "remaining_time": "0:43:33"} +{"current_steps": 1290, "total_steps": 1413, "loss": 0.0823, "lr": 9.422313539793032e-08, "epoch": 2.736814206201961, "percentage": 91.3, "elapsed_time": "7:33:09", "remaining_time": "0:43:12"} +{"current_steps": 1291, "total_steps": 1413, "loss": 0.1873, "lr": 9.270678163050218e-08, "epoch": 2.738934534852902, "percentage": 91.37, "elapsed_time": "7:33:28", "remaining_time": "0:42:51"} +{"current_steps": 1292, "total_steps": 1413, "loss": 0.2122, "lr": 9.120249802827525e-08, "epoch": 2.741054863503843, "percentage": 91.44, "elapsed_time": "7:33:51", "remaining_time": "0:42:30"} +{"current_steps": 1293, "total_steps": 1413, "loss": 0.1604, "lr": 8.971029213372729e-08, "epoch": 2.743175192154784, "percentage": 91.51, "elapsed_time": "7:34:13", "remaining_time": "0:42:09"} +{"current_steps": 1294, "total_steps": 1413, "loss": 0.1293, "lr": 8.823017142877587e-08, "epoch": 2.745295520805725, "percentage": 91.58, "elapsed_time": "7:34:33", "remaining_time": "0:41:48"} +{"current_steps": 1295, "total_steps": 1413, "loss": 0.1202, "lr": 8.676214333474458e-08, "epoch": 2.747415849456666, "percentage": 91.65, "elapsed_time": "7:34:53", "remaining_time": "0:41:27"} +{"current_steps": 1296, "total_steps": 1413, "loss": 0.163, "lr": 8.530621521232435e-08, "epoch": 2.749536178107607, "percentage": 91.72, "elapsed_time": "7:35:14", "remaining_time": "0:41:05"} +{"current_steps": 1297, "total_steps": 1413, "loss": 0.1314, "lr": 8.386239436153742e-08, "epoch": 2.7516565067585477, "percentage": 91.79, "elapsed_time": "7:35:35", "remaining_time": "0:40:44"} +{"current_steps": 1298, "total_steps": 1413, "loss": 0.1117, "lr": 8.243068802169906e-08, "epoch": 2.7537768354094885, "percentage": 91.86, "elapsed_time": "7:35:56", "remaining_time": "0:40:23"} +{"current_steps": 1299, "total_steps": 1413, "loss": 0.2353, "lr": 8.101110337138369e-08, "epoch": 2.7558971640604293, "percentage": 91.93, "elapsed_time": "7:36:18", "remaining_time": "0:40:02"} +{"current_steps": 1300, "total_steps": 1413, "loss": 0.1271, "lr": 7.96036475283865e-08, "epoch": 2.75801749271137, "percentage": 92.0, "elapsed_time": "7:36:39", "remaining_time": "0:39:41"} +{"current_steps": 1301, "total_steps": 1413, "loss": 0.1141, "lr": 7.820832754968976e-08, "epoch": 2.760137821362311, "percentage": 92.07, "elapsed_time": "7:37:00", "remaining_time": "0:39:20"} +{"current_steps": 1302, "total_steps": 1413, "loss": 0.1758, "lr": 7.682515043142602e-08, "epoch": 2.762258150013252, "percentage": 92.14, "elapsed_time": "7:37:20", "remaining_time": "0:38:59"} +{"current_steps": 1303, "total_steps": 1413, "loss": 0.0946, "lr": 7.545412310884347e-08, "epoch": 2.764378478664193, "percentage": 92.22, "elapsed_time": "7:37:42", "remaining_time": "0:38:38"} +{"current_steps": 1304, "total_steps": 1413, "loss": 0.1267, "lr": 7.409525245627103e-08, "epoch": 2.7664988073151338, "percentage": 92.29, "elapsed_time": "7:38:03", "remaining_time": "0:38:17"} +{"current_steps": 1305, "total_steps": 1413, "loss": 0.1801, "lr": 7.27485452870852e-08, "epoch": 2.768619135966075, "percentage": 92.36, "elapsed_time": "7:38:25", "remaining_time": "0:37:56"} +{"current_steps": 1306, "total_steps": 1413, "loss": 0.165, "lr": 7.141400835367379e-08, "epoch": 2.770739464617016, "percentage": 92.43, "elapsed_time": "7:38:45", "remaining_time": "0:37:35"} +{"current_steps": 1307, "total_steps": 1413, "loss": 0.1933, "lr": 7.009164834740318e-08, "epoch": 2.7728597932679566, "percentage": 92.5, "elapsed_time": "7:39:06", "remaining_time": "0:37:14"} +{"current_steps": 1308, "total_steps": 1413, "loss": 0.1828, "lr": 6.878147189858464e-08, "epoch": 2.7749801219188974, "percentage": 92.57, "elapsed_time": "7:39:29", "remaining_time": "0:36:53"} +{"current_steps": 1309, "total_steps": 1413, "loss": 0.1831, "lr": 6.748348557644169e-08, "epoch": 2.7771004505698382, "percentage": 92.64, "elapsed_time": "7:39:49", "remaining_time": "0:36:32"} +{"current_steps": 1310, "total_steps": 1413, "loss": 0.2365, "lr": 6.619769588907588e-08, "epoch": 2.779220779220779, "percentage": 92.71, "elapsed_time": "7:40:10", "remaining_time": "0:36:10"} +{"current_steps": 1311, "total_steps": 1413, "loss": 0.1281, "lr": 6.492410928343545e-08, "epoch": 2.78134110787172, "percentage": 92.78, "elapsed_time": "7:40:30", "remaining_time": "0:35:49"} +{"current_steps": 1312, "total_steps": 1413, "loss": 0.1193, "lr": 6.366273214528124e-08, "epoch": 2.783461436522661, "percentage": 92.85, "elapsed_time": "7:40:50", "remaining_time": "0:35:28"} +{"current_steps": 1313, "total_steps": 1413, "loss": 0.0859, "lr": 6.241357079915771e-08, "epoch": 2.785581765173602, "percentage": 92.92, "elapsed_time": "7:41:11", "remaining_time": "0:35:07"} +{"current_steps": 1314, "total_steps": 1413, "loss": 0.1035, "lr": 6.117663150835756e-08, "epoch": 2.7877020938245427, "percentage": 92.99, "elapsed_time": "7:41:31", "remaining_time": "0:34:46"} +{"current_steps": 1315, "total_steps": 1413, "loss": 0.1114, "lr": 5.995192047489301e-08, "epoch": 2.789822422475484, "percentage": 93.06, "elapsed_time": "7:41:51", "remaining_time": "0:34:25"} +{"current_steps": 1316, "total_steps": 1413, "loss": 0.0927, "lr": 5.8739443839463675e-08, "epoch": 2.7919427511264248, "percentage": 93.14, "elapsed_time": "7:42:13", "remaining_time": "0:34:04"} +{"current_steps": 1317, "total_steps": 1413, "loss": 0.1889, "lr": 5.7539207681426015e-08, "epoch": 2.7940630797773656, "percentage": 93.21, "elapsed_time": "7:42:35", "remaining_time": "0:33:43"} +{"current_steps": 1318, "total_steps": 1413, "loss": 0.201, "lr": 5.635121801876253e-08, "epoch": 2.7961834084283064, "percentage": 93.28, "elapsed_time": "7:42:56", "remaining_time": "0:33:22"} +{"current_steps": 1319, "total_steps": 1413, "loss": 0.1615, "lr": 5.5175480808051515e-08, "epoch": 2.798303737079247, "percentage": 93.35, "elapsed_time": "7:43:16", "remaining_time": "0:33:00"} +{"current_steps": 1320, "total_steps": 1413, "loss": 0.1195, "lr": 5.401200194443873e-08, "epoch": 2.800424065730188, "percentage": 93.42, "elapsed_time": "7:43:37", "remaining_time": "0:32:39"} +{"current_steps": 1321, "total_steps": 1413, "loss": 0.1593, "lr": 5.2860787261605485e-08, "epoch": 2.8025443943811292, "percentage": 93.49, "elapsed_time": "7:43:58", "remaining_time": "0:32:18"} +{"current_steps": 1322, "total_steps": 1413, "loss": 0.0893, "lr": 5.172184253174034e-08, "epoch": 2.80466472303207, "percentage": 93.56, "elapsed_time": "7:44:18", "remaining_time": "0:31:57"} +{"current_steps": 1323, "total_steps": 1413, "loss": 0.2956, "lr": 5.059517346551107e-08, "epoch": 2.806785051683011, "percentage": 93.63, "elapsed_time": "7:44:39", "remaining_time": "0:31:36"} +{"current_steps": 1324, "total_steps": 1413, "loss": 0.1717, "lr": 4.948078571203496e-08, "epoch": 2.8089053803339517, "percentage": 93.7, "elapsed_time": "7:45:00", "remaining_time": "0:31:15"} +{"current_steps": 1325, "total_steps": 1413, "loss": 0.0977, "lr": 4.83786848588505e-08, "epoch": 2.811025708984893, "percentage": 93.77, "elapsed_time": "7:45:22", "remaining_time": "0:30:54"} +{"current_steps": 1326, "total_steps": 1413, "loss": 0.1553, "lr": 4.728887643189073e-08, "epoch": 2.8131460376358337, "percentage": 93.84, "elapsed_time": "7:45:41", "remaining_time": "0:30:33"} +{"current_steps": 1327, "total_steps": 1413, "loss": 0.1686, "lr": 4.621136589545272e-08, "epoch": 2.8152663662867745, "percentage": 93.91, "elapsed_time": "7:46:01", "remaining_time": "0:30:12"} +{"current_steps": 1328, "total_steps": 1413, "loss": 0.1846, "lr": 4.5146158652173696e-08, "epoch": 2.8173866949377153, "percentage": 93.98, "elapsed_time": "7:46:23", "remaining_time": "0:29:51"} +{"current_steps": 1329, "total_steps": 1413, "loss": 0.1363, "lr": 4.4093260043001626e-08, "epoch": 2.819507023588656, "percentage": 94.06, "elapsed_time": "7:46:44", "remaining_time": "0:29:30"} +{"current_steps": 1330, "total_steps": 1413, "loss": 0.1339, "lr": 4.305267534716828e-08, "epoch": 2.821627352239597, "percentage": 94.13, "elapsed_time": "7:47:04", "remaining_time": "0:29:08"} +{"current_steps": 1331, "total_steps": 1413, "loss": 0.1288, "lr": 4.202440978216399e-08, "epoch": 2.823747680890538, "percentage": 94.2, "elapsed_time": "7:47:25", "remaining_time": "0:28:47"} +{"current_steps": 1332, "total_steps": 1413, "loss": 0.1397, "lr": 4.1008468503711266e-08, "epoch": 2.825868009541479, "percentage": 94.27, "elapsed_time": "7:47:48", "remaining_time": "0:28:26"} +{"current_steps": 1333, "total_steps": 1413, "loss": 0.1248, "lr": 4.000485660573872e-08, "epoch": 2.82798833819242, "percentage": 94.34, "elapsed_time": "7:48:07", "remaining_time": "0:28:05"} +{"current_steps": 1334, "total_steps": 1413, "loss": 0.1981, "lr": 3.9013579120354696e-08, "epoch": 2.8301086668433606, "percentage": 94.41, "elapsed_time": "7:48:28", "remaining_time": "0:27:44"} +{"current_steps": 1335, "total_steps": 1413, "loss": 0.1387, "lr": 3.803464101782367e-08, "epoch": 2.832228995494302, "percentage": 94.48, "elapsed_time": "7:48:49", "remaining_time": "0:27:23"} +{"current_steps": 1336, "total_steps": 1413, "loss": 0.1013, "lr": 3.706804720653962e-08, "epoch": 2.8343493241452427, "percentage": 94.55, "elapsed_time": "7:49:09", "remaining_time": "0:27:02"} +{"current_steps": 1337, "total_steps": 1413, "loss": 0.2936, "lr": 3.611380253300267e-08, "epoch": 2.8364696527961835, "percentage": 94.62, "elapsed_time": "7:49:30", "remaining_time": "0:26:41"} +{"current_steps": 1338, "total_steps": 1413, "loss": 0.1551, "lr": 3.517191178179474e-08, "epoch": 2.8385899814471243, "percentage": 94.69, "elapsed_time": "7:49:52", "remaining_time": "0:26:20"} +{"current_steps": 1339, "total_steps": 1413, "loss": 0.1314, "lr": 3.4242379675555046e-08, "epoch": 2.840710310098065, "percentage": 94.76, "elapsed_time": "7:50:13", "remaining_time": "0:25:59"} +{"current_steps": 1340, "total_steps": 1413, "loss": 0.1936, "lr": 3.332521087495627e-08, "epoch": 2.842830638749006, "percentage": 94.83, "elapsed_time": "7:50:33", "remaining_time": "0:25:38"} +{"current_steps": 1341, "total_steps": 1413, "loss": 0.1696, "lr": 3.242040997868123e-08, "epoch": 2.844950967399947, "percentage": 94.9, "elapsed_time": "7:50:53", "remaining_time": "0:25:16"} +{"current_steps": 1342, "total_steps": 1413, "loss": 0.0762, "lr": 3.1527981523400974e-08, "epoch": 2.847071296050888, "percentage": 94.98, "elapsed_time": "7:51:14", "remaining_time": "0:24:55"} +{"current_steps": 1343, "total_steps": 1413, "loss": 0.1341, "lr": 3.064792998375032e-08, "epoch": 2.8491916247018287, "percentage": 95.05, "elapsed_time": "7:51:35", "remaining_time": "0:24:34"} +{"current_steps": 1344, "total_steps": 1413, "loss": 0.1482, "lr": 2.9780259772307362e-08, "epoch": 2.8513119533527695, "percentage": 95.12, "elapsed_time": "7:51:56", "remaining_time": "0:24:13"} +{"current_steps": 1345, "total_steps": 1413, "loss": 0.136, "lr": 2.8924975239568444e-08, "epoch": 2.853432282003711, "percentage": 95.19, "elapsed_time": "7:52:16", "remaining_time": "0:23:52"} +{"current_steps": 1346, "total_steps": 1413, "loss": 0.1296, "lr": 2.8082080673929312e-08, "epoch": 2.8555526106546516, "percentage": 95.26, "elapsed_time": "7:52:37", "remaining_time": "0:23:31"} +{"current_steps": 1347, "total_steps": 1413, "loss": 0.1119, "lr": 2.7251580301662916e-08, "epoch": 2.8576729393055924, "percentage": 95.33, "elapsed_time": "7:52:58", "remaining_time": "0:23:10"} +{"current_steps": 1348, "total_steps": 1413, "loss": 0.1892, "lr": 2.643347828689663e-08, "epoch": 2.859793267956533, "percentage": 95.4, "elapsed_time": "7:53:18", "remaining_time": "0:22:49"} +{"current_steps": 1349, "total_steps": 1413, "loss": 0.1666, "lr": 2.562777873159311e-08, "epoch": 2.861913596607474, "percentage": 95.47, "elapsed_time": "7:53:39", "remaining_time": "0:22:28"} +{"current_steps": 1350, "total_steps": 1413, "loss": 0.1364, "lr": 2.4834485675528653e-08, "epoch": 2.864033925258415, "percentage": 95.54, "elapsed_time": "7:54:00", "remaining_time": "0:22:07"} +{"current_steps": 1351, "total_steps": 1413, "loss": 0.1658, "lr": 2.4053603096274027e-08, "epoch": 2.866154253909356, "percentage": 95.61, "elapsed_time": "7:54:21", "remaining_time": "0:21:46"} +{"current_steps": 1352, "total_steps": 1413, "loss": 0.1677, "lr": 2.3285134909173113e-08, "epoch": 2.868274582560297, "percentage": 95.68, "elapsed_time": "7:54:41", "remaining_time": "0:21:25"} +{"current_steps": 1353, "total_steps": 1413, "loss": 0.1026, "lr": 2.2529084967324867e-08, "epoch": 2.8703949112112377, "percentage": 95.75, "elapsed_time": "7:55:04", "remaining_time": "0:21:04"} +{"current_steps": 1354, "total_steps": 1413, "loss": 0.1761, "lr": 2.178545706156221e-08, "epoch": 2.8725152398621785, "percentage": 95.82, "elapsed_time": "7:55:25", "remaining_time": "0:20:42"} +{"current_steps": 1355, "total_steps": 1413, "loss": 0.2169, "lr": 2.105425492043539e-08, "epoch": 2.8746355685131197, "percentage": 95.9, "elapsed_time": "7:55:46", "remaining_time": "0:20:21"} +{"current_steps": 1356, "total_steps": 1413, "loss": 0.199, "lr": 2.0335482210190327e-08, "epoch": 2.8767558971640605, "percentage": 95.97, "elapsed_time": "7:56:07", "remaining_time": "0:20:00"} +{"current_steps": 1357, "total_steps": 1413, "loss": 0.1348, "lr": 1.962914253475251e-08, "epoch": 2.8788762258150014, "percentage": 96.04, "elapsed_time": "7:56:29", "remaining_time": "0:19:39"} +{"current_steps": 1358, "total_steps": 1413, "loss": 0.0994, "lr": 1.893523943570841e-08, "epoch": 2.880996554465942, "percentage": 96.11, "elapsed_time": "7:56:49", "remaining_time": "0:19:18"} +{"current_steps": 1359, "total_steps": 1413, "loss": 0.1815, "lr": 1.8253776392287147e-08, "epoch": 2.883116883116883, "percentage": 96.18, "elapsed_time": "7:57:11", "remaining_time": "0:18:57"} +{"current_steps": 1360, "total_steps": 1413, "loss": 0.1956, "lr": 1.7584756821343864e-08, "epoch": 2.8852372117678238, "percentage": 96.25, "elapsed_time": "7:57:32", "remaining_time": "0:18:36"} +{"current_steps": 1361, "total_steps": 1413, "loss": 0.1832, "lr": 1.692818407734165e-08, "epoch": 2.887357540418765, "percentage": 96.32, "elapsed_time": "7:57:52", "remaining_time": "0:18:15"} +{"current_steps": 1362, "total_steps": 1413, "loss": 0.2045, "lr": 1.6284061452335464e-08, "epoch": 2.889477869069706, "percentage": 96.39, "elapsed_time": "7:58:12", "remaining_time": "0:17:54"} +{"current_steps": 1363, "total_steps": 1413, "loss": 0.1563, "lr": 1.565239217595549e-08, "epoch": 2.8915981977206466, "percentage": 96.46, "elapsed_time": "7:58:34", "remaining_time": "0:17:33"} +{"current_steps": 1364, "total_steps": 1413, "loss": 0.1395, "lr": 1.5033179415390176e-08, "epoch": 2.8937185263715874, "percentage": 96.53, "elapsed_time": "7:58:54", "remaining_time": "0:17:12"} +{"current_steps": 1365, "total_steps": 1413, "loss": 0.1354, "lr": 1.4426426275372385e-08, "epoch": 2.8958388550225287, "percentage": 96.6, "elapsed_time": "7:59:16", "remaining_time": "0:16:51"} +{"current_steps": 1366, "total_steps": 1413, "loss": 0.1807, "lr": 1.3832135798160783e-08, "epoch": 2.8979591836734695, "percentage": 96.67, "elapsed_time": "7:59:36", "remaining_time": "0:16:30"} +{"current_steps": 1367, "total_steps": 1413, "loss": 0.2193, "lr": 1.3250310963527358e-08, "epoch": 2.9000795123244103, "percentage": 96.74, "elapsed_time": "7:59:57", "remaining_time": "0:16:09"} +{"current_steps": 1368, "total_steps": 1413, "loss": 0.1427, "lr": 1.268095468874131e-08, "epoch": 2.902199840975351, "percentage": 96.82, "elapsed_time": "8:00:18", "remaining_time": "0:15:47"} +{"current_steps": 1369, "total_steps": 1413, "loss": 0.1666, "lr": 1.2124069828554075e-08, "epoch": 2.904320169626292, "percentage": 96.89, "elapsed_time": "8:00:39", "remaining_time": "0:15:26"} +{"current_steps": 1370, "total_steps": 1413, "loss": 0.1087, "lr": 1.1579659175185998e-08, "epoch": 2.9064404982772327, "percentage": 96.96, "elapsed_time": "8:01:00", "remaining_time": "0:15:05"} +{"current_steps": 1371, "total_steps": 1413, "loss": 0.1042, "lr": 1.1047725458310788e-08, "epoch": 2.908560826928174, "percentage": 97.03, "elapsed_time": "8:01:21", "remaining_time": "0:14:44"} +{"current_steps": 1372, "total_steps": 1413, "loss": 0.123, "lr": 1.0528271345044139e-08, "epoch": 2.9106811555791148, "percentage": 97.1, "elapsed_time": "8:01:41", "remaining_time": "0:14:23"} +{"current_steps": 1373, "total_steps": 1413, "loss": 0.2518, "lr": 1.0021299439927635e-08, "epoch": 2.9128014842300556, "percentage": 97.17, "elapsed_time": "8:02:02", "remaining_time": "0:14:02"} +{"current_steps": 1374, "total_steps": 1413, "loss": 0.1938, "lr": 9.526812284918196e-09, "epoch": 2.914921812880997, "percentage": 97.24, "elapsed_time": "8:02:24", "remaining_time": "0:13:41"} +{"current_steps": 1375, "total_steps": 1413, "loss": 0.1524, "lr": 9.044812359373933e-09, "epoch": 2.9170421415319376, "percentage": 97.31, "elapsed_time": "8:02:45", "remaining_time": "0:13:20"} +{"current_steps": 1376, "total_steps": 1413, "loss": 0.0865, "lr": 8.575302080041648e-09, "epoch": 2.9191624701828784, "percentage": 97.38, "elapsed_time": "8:03:07", "remaining_time": "0:12:59"} +{"current_steps": 1377, "total_steps": 1413, "loss": 0.1245, "lr": 8.118283801045179e-09, "epoch": 2.9212827988338192, "percentage": 97.45, "elapsed_time": "8:03:27", "remaining_time": "0:12:38"} +{"current_steps": 1378, "total_steps": 1413, "loss": 0.1392, "lr": 7.673759813873749e-09, "epoch": 2.92340312748476, "percentage": 97.52, "elapsed_time": "8:03:48", "remaining_time": "0:12:17"} +{"current_steps": 1379, "total_steps": 1413, "loss": 0.1392, "lr": 7.2417323473703005e-09, "epoch": 2.925523456135701, "percentage": 97.59, "elapsed_time": "8:04:09", "remaining_time": "0:11:56"} +{"current_steps": 1380, "total_steps": 1413, "loss": 0.1728, "lr": 6.8222035677195655e-09, "epoch": 2.9276437847866417, "percentage": 97.66, "elapsed_time": "8:04:30", "remaining_time": "0:11:35"} +{"current_steps": 1381, "total_steps": 1413, "loss": 0.1577, "lr": 6.415175578438626e-09, "epoch": 2.929764113437583, "percentage": 97.74, "elapsed_time": "8:04:50", "remaining_time": "0:11:14"} +{"current_steps": 1382, "total_steps": 1413, "loss": 0.1659, "lr": 6.0206504203652595e-09, "epoch": 2.9318844420885237, "percentage": 97.81, "elapsed_time": "8:05:11", "remaining_time": "0:10:53"} +{"current_steps": 1383, "total_steps": 1413, "loss": 0.1507, "lr": 5.638630071648221e-09, "epoch": 2.9340047707394645, "percentage": 97.88, "elapsed_time": "8:05:31", "remaining_time": "0:10:31"} +{"current_steps": 1384, "total_steps": 1413, "loss": 0.1365, "lr": 5.2691164477367e-09, "epoch": 2.936125099390406, "percentage": 97.95, "elapsed_time": "8:05:53", "remaining_time": "0:10:10"} +{"current_steps": 1385, "total_steps": 1413, "loss": 0.1626, "lr": 4.9121114013719886e-09, "epoch": 2.9382454280413466, "percentage": 98.02, "elapsed_time": "8:06:13", "remaining_time": "0:09:49"} +{"current_steps": 1386, "total_steps": 1413, "loss": 0.1482, "lr": 4.5676167225766625e-09, "epoch": 2.9403657566922874, "percentage": 98.09, "elapsed_time": "8:06:35", "remaining_time": "0:09:28"} +{"current_steps": 1387, "total_steps": 1413, "loss": 0.1666, "lr": 4.2356341386468045e-09, "epoch": 2.942486085343228, "percentage": 98.16, "elapsed_time": "8:06:58", "remaining_time": "0:09:07"} +{"current_steps": 1388, "total_steps": 1413, "loss": 0.1035, "lr": 3.916165314142295e-09, "epoch": 2.944606413994169, "percentage": 98.23, "elapsed_time": "8:07:22", "remaining_time": "0:08:46"} +{"current_steps": 1389, "total_steps": 1413, "loss": 0.1345, "lr": 3.609211850879868e-09, "epoch": 2.94672674264511, "percentage": 98.3, "elapsed_time": "8:07:42", "remaining_time": "0:08:25"} +{"current_steps": 1390, "total_steps": 1413, "loss": 0.1287, "lr": 3.3147752879236773e-09, "epoch": 2.9488470712960506, "percentage": 98.37, "elapsed_time": "8:08:03", "remaining_time": "0:08:04"} +{"current_steps": 1391, "total_steps": 1413, "loss": 0.1304, "lr": 3.032857101578357e-09, "epoch": 2.950967399946992, "percentage": 98.44, "elapsed_time": "8:08:24", "remaining_time": "0:07:43"} +{"current_steps": 1392, "total_steps": 1413, "loss": 0.1966, "lr": 2.7634587053809723e-09, "epoch": 2.9530877285979327, "percentage": 98.51, "elapsed_time": "8:08:45", "remaining_time": "0:07:22"} +{"current_steps": 1393, "total_steps": 1413, "loss": 0.16, "lr": 2.5065814500951914e-09, "epoch": 2.9552080572488735, "percentage": 98.58, "elapsed_time": "8:09:06", "remaining_time": "0:07:01"} +{"current_steps": 1394, "total_steps": 1413, "loss": 0.2442, "lr": 2.2622266237029565e-09, "epoch": 2.9573283858998147, "percentage": 98.66, "elapsed_time": "8:09:28", "remaining_time": "0:06:40"} +{"current_steps": 1395, "total_steps": 1413, "loss": 0.1084, "lr": 2.030395451399214e-09, "epoch": 2.9594487145507555, "percentage": 98.73, "elapsed_time": "8:09:48", "remaining_time": "0:06:19"} +{"current_steps": 1396, "total_steps": 1413, "loss": 0.1805, "lr": 1.8110890955849724e-09, "epoch": 2.9615690432016963, "percentage": 98.8, "elapsed_time": "8:10:09", "remaining_time": "0:05:58"} +{"current_steps": 1397, "total_steps": 1413, "loss": 0.1576, "lr": 1.6043086558623078e-09, "epoch": 2.963689371852637, "percentage": 98.87, "elapsed_time": "8:10:30", "remaining_time": "0:05:37"} +{"current_steps": 1398, "total_steps": 1413, "loss": 0.1739, "lr": 1.4100551690279796e-09, "epoch": 2.965809700503578, "percentage": 98.94, "elapsed_time": "8:10:51", "remaining_time": "0:05:16"} +{"current_steps": 1399, "total_steps": 1413, "loss": 0.1755, "lr": 1.2283296090687125e-09, "epoch": 2.9679300291545188, "percentage": 99.01, "elapsed_time": "8:11:13", "remaining_time": "0:04:54"} +{"current_steps": 1400, "total_steps": 1413, "loss": 0.1123, "lr": 1.0591328871562e-09, "epoch": 2.97005035780546, "percentage": 99.08, "elapsed_time": "8:11:33", "remaining_time": "0:04:33"} +{"current_steps": 1401, "total_steps": 1413, "loss": 0.1952, "lr": 9.024658516426643e-10, "epoch": 2.972170686456401, "percentage": 99.15, "elapsed_time": "8:11:55", "remaining_time": "0:04:12"} +{"current_steps": 1402, "total_steps": 1413, "loss": 0.1802, "lr": 7.583292880564142e-10, "epoch": 2.9742910151073416, "percentage": 99.22, "elapsed_time": "8:12:16", "remaining_time": "0:03:51"} +{"current_steps": 1403, "total_steps": 1413, "loss": 0.1862, "lr": 6.267239190979601e-10, "epoch": 2.9764113437582824, "percentage": 99.29, "elapsed_time": "8:12:36", "remaining_time": "0:03:30"} +{"current_steps": 1404, "total_steps": 1413, "loss": 0.1186, "lr": 5.076504046364061e-10, "epoch": 2.9785316724092237, "percentage": 99.36, "elapsed_time": "8:12:57", "remaining_time": "0:03:09"} +{"current_steps": 1405, "total_steps": 1413, "loss": 0.202, "lr": 4.0110934170639603e-10, "epoch": 2.9806520010601645, "percentage": 99.43, "elapsed_time": "8:13:17", "remaining_time": "0:02:48"} +{"current_steps": 1406, "total_steps": 1413, "loss": 0.1106, "lr": 3.0710126450450574e-10, "epoch": 2.9827723297111053, "percentage": 99.5, "elapsed_time": "8:13:37", "remaining_time": "0:02:27"} +{"current_steps": 1407, "total_steps": 1413, "loss": 0.2274, "lr": 2.2562664438730008e-10, "epoch": 2.984892658362046, "percentage": 99.58, "elapsed_time": "8:13:58", "remaining_time": "0:02:06"} +{"current_steps": 1408, "total_steps": 1413, "loss": 0.098, "lr": 1.5668588986800237e-10, "epoch": 2.987012987012987, "percentage": 99.65, "elapsed_time": "8:14:18", "remaining_time": "0:01:45"} +{"current_steps": 1409, "total_steps": 1413, "loss": 0.1817, "lr": 1.0027934661593908e-10, "epoch": 2.9891333156639277, "percentage": 99.72, "elapsed_time": "8:14:39", "remaining_time": "0:01:24"} +{"current_steps": 1410, "total_steps": 1413, "loss": 0.1669, "lr": 5.640729745348683e-11, "epoch": 2.991253644314869, "percentage": 99.79, "elapsed_time": "8:15:00", "remaining_time": "0:01:03"} +{"current_steps": 1411, "total_steps": 1413, "loss": 0.1413, "lr": 2.5069962354684618e-11, "epoch": 2.9933739729658098, "percentage": 99.86, "elapsed_time": "8:15:20", "remaining_time": "0:00:42"} +{"current_steps": 1412, "total_steps": 1413, "loss": 0.3418, "lr": 6.267498444956222e-12, "epoch": 2.9954943016167506, "percentage": 99.93, "elapsed_time": "8:15:39", "remaining_time": "0:00:21"} +{"current_steps": 1413, "total_steps": 1413, "loss": 0.1737, "lr": 0.0, "epoch": 2.9976146302676914, "percentage": 100.0, "elapsed_time": "8:16:00", "remaining_time": "0:00:00"} +{"current_steps": 1413, "total_steps": 1413, "epoch": 2.9976146302676914, "percentage": 100.0, "elapsed_time": "8:17:27", "remaining_time": "0:00:00"} diff --git a/rag_truth_hal_detection_model/trainer_state.json b/rag_truth_hal_detection_model/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..b63a6fde6d0f5c3fd63432aa5d8a95d2a01809c8 --- /dev/null +++ b/rag_truth_hal_detection_model/trainer_state.json @@ -0,0 +1,9933 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 2.9976146302676914, + "eval_steps": 500, + "global_step": 1413, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0021203286509408957, + "grad_norm": 25.949520111083984, + "learning_rate": 5.000000000000001e-07, + "loss": 1.2577, + "step": 1 + }, + { + "epoch": 0.004240657301881791, + "grad_norm": 27.748842239379883, + "learning_rate": 1.0000000000000002e-06, + "loss": 1.1764, + "step": 2 + }, + { + "epoch": 0.0063609859528226875, + "grad_norm": 25.2868595123291, + "learning_rate": 1.5e-06, + "loss": 1.1581, + "step": 3 + }, + { + "epoch": 0.008481314603763583, + "grad_norm": 26.029958724975586, + "learning_rate": 2.0000000000000003e-06, + "loss": 0.9151, + "step": 4 + }, + { + "epoch": 0.010601643254704479, + "grad_norm": 15.586308479309082, + "learning_rate": 2.5e-06, + "loss": 0.5946, + "step": 5 + }, + { + "epoch": 0.012721971905645375, + "grad_norm": 24.38088607788086, + "learning_rate": 3e-06, + "loss": 0.514, + "step": 6 + }, + { + "epoch": 0.014842300556586271, + "grad_norm": 15.221429824829102, + "learning_rate": 3.5e-06, + "loss": 0.3226, + "step": 7 + }, + { + "epoch": 0.016962629207527165, + "grad_norm": 12.0006742477417, + "learning_rate": 4.000000000000001e-06, + "loss": 0.3853, + "step": 8 + }, + { + "epoch": 0.01908295785846806, + "grad_norm": 4.748922348022461, + "learning_rate": 4.5e-06, + "loss": 0.2983, + "step": 9 + }, + { + "epoch": 0.021203286509408958, + "grad_norm": 2.3620359897613525, + "learning_rate": 5e-06, + "loss": 0.4318, + "step": 10 + }, + { + "epoch": 0.023323615160349854, + "grad_norm": 8.839906692504883, + "learning_rate": 4.9999937325015554e-06, + "loss": 0.4925, + "step": 11 + }, + { + "epoch": 0.02544394381129075, + "grad_norm": 4.359335422515869, + "learning_rate": 4.999974930037645e-06, + "loss": 0.4128, + "step": 12 + }, + { + "epoch": 0.027564272462231646, + "grad_norm": 2.051809310913086, + "learning_rate": 4.999943592702547e-06, + "loss": 0.3941, + "step": 13 + }, + { + "epoch": 0.029684601113172542, + "grad_norm": 4.041887283325195, + "learning_rate": 4.999899720653384e-06, + "loss": 0.527, + "step": 14 + }, + { + "epoch": 0.031804929764113435, + "grad_norm": 4.354254245758057, + "learning_rate": 4.999843314110132e-06, + "loss": 0.5217, + "step": 15 + }, + { + "epoch": 0.03392525841505433, + "grad_norm": 4.818948268890381, + "learning_rate": 4.999774373355613e-06, + "loss": 0.262, + "step": 16 + }, + { + "epoch": 0.03604558706599523, + "grad_norm": 4.6067585945129395, + "learning_rate": 4.999692898735496e-06, + "loss": 0.5101, + "step": 17 + }, + { + "epoch": 0.03816591571693612, + "grad_norm": 4.296671390533447, + "learning_rate": 4.999598890658294e-06, + "loss": 0.376, + "step": 18 + }, + { + "epoch": 0.04028624436787702, + "grad_norm": 5.08732795715332, + "learning_rate": 4.999492349595364e-06, + "loss": 0.3747, + "step": 19 + }, + { + "epoch": 0.042406573018817915, + "grad_norm": 4.986461639404297, + "learning_rate": 4.999373276080902e-06, + "loss": 0.3933, + "step": 20 + }, + { + "epoch": 0.04452690166975881, + "grad_norm": 3.174241781234741, + "learning_rate": 4.999241670711944e-06, + "loss": 0.3696, + "step": 21 + }, + { + "epoch": 0.04664723032069971, + "grad_norm": 2.13350510597229, + "learning_rate": 4.999097534148358e-06, + "loss": 0.3125, + "step": 22 + }, + { + "epoch": 0.048767558971640604, + "grad_norm": 15.487786293029785, + "learning_rate": 4.998940867112844e-06, + "loss": 0.4218, + "step": 23 + }, + { + "epoch": 0.0508878876225815, + "grad_norm": 4.8160552978515625, + "learning_rate": 4.998771670390931e-06, + "loss": 0.3827, + "step": 24 + }, + { + "epoch": 0.053008216273522396, + "grad_norm": 3.281799077987671, + "learning_rate": 4.998589944830973e-06, + "loss": 0.4637, + "step": 25 + }, + { + "epoch": 0.05512854492446329, + "grad_norm": 3.690784454345703, + "learning_rate": 4.998395691344138e-06, + "loss": 0.3562, + "step": 26 + }, + { + "epoch": 0.05724887357540419, + "grad_norm": 3.4011573791503906, + "learning_rate": 4.998188910904416e-06, + "loss": 0.3842, + "step": 27 + }, + { + "epoch": 0.059369202226345084, + "grad_norm": 4.38139533996582, + "learning_rate": 4.997969604548602e-06, + "loss": 0.3048, + "step": 28 + }, + { + "epoch": 0.06148953087728598, + "grad_norm": 2.751617908477783, + "learning_rate": 4.997737773376298e-06, + "loss": 0.3621, + "step": 29 + }, + { + "epoch": 0.06360985952822687, + "grad_norm": 4.899576187133789, + "learning_rate": 4.997493418549905e-06, + "loss": 0.2974, + "step": 30 + }, + { + "epoch": 0.06573018817916777, + "grad_norm": 1.5958459377288818, + "learning_rate": 4.99723654129462e-06, + "loss": 0.445, + "step": 31 + }, + { + "epoch": 0.06785051683010866, + "grad_norm": 4.093502521514893, + "learning_rate": 4.996967142898423e-06, + "loss": 0.3759, + "step": 32 + }, + { + "epoch": 0.06997084548104957, + "grad_norm": 0.6687224507331848, + "learning_rate": 4.996685224712077e-06, + "loss": 0.3232, + "step": 33 + }, + { + "epoch": 0.07209117413199045, + "grad_norm": 3.0124692916870117, + "learning_rate": 4.99639078814912e-06, + "loss": 0.4248, + "step": 34 + }, + { + "epoch": 0.07421150278293136, + "grad_norm": 2.5640933513641357, + "learning_rate": 4.996083834685858e-06, + "loss": 0.2229, + "step": 35 + }, + { + "epoch": 0.07633183143387225, + "grad_norm": 6.7540812492370605, + "learning_rate": 4.995764365861354e-06, + "loss": 0.316, + "step": 36 + }, + { + "epoch": 0.07845216008481315, + "grad_norm": 4.984259605407715, + "learning_rate": 4.9954323832774235e-06, + "loss": 0.3061, + "step": 37 + }, + { + "epoch": 0.08057248873575404, + "grad_norm": 2.3390185832977295, + "learning_rate": 4.995087888598629e-06, + "loss": 0.3889, + "step": 38 + }, + { + "epoch": 0.08269281738669494, + "grad_norm": 3.226795196533203, + "learning_rate": 4.994730883552263e-06, + "loss": 0.3944, + "step": 39 + }, + { + "epoch": 0.08481314603763583, + "grad_norm": 3.2235963344573975, + "learning_rate": 4.994361369928352e-06, + "loss": 0.5437, + "step": 40 + }, + { + "epoch": 0.08693347468857673, + "grad_norm": 5.956916809082031, + "learning_rate": 4.993979349579635e-06, + "loss": 0.357, + "step": 41 + }, + { + "epoch": 0.08905380333951762, + "grad_norm": 5.488076210021973, + "learning_rate": 4.9935848244215615e-06, + "loss": 0.3081, + "step": 42 + }, + { + "epoch": 0.09117413199045853, + "grad_norm": 2.534620761871338, + "learning_rate": 4.993177796432281e-06, + "loss": 0.3468, + "step": 43 + }, + { + "epoch": 0.09329446064139942, + "grad_norm": 3.6338629722595215, + "learning_rate": 4.99275826765263e-06, + "loss": 0.3266, + "step": 44 + }, + { + "epoch": 0.09541478929234032, + "grad_norm": 3.6629638671875, + "learning_rate": 4.992326240186127e-06, + "loss": 0.3799, + "step": 45 + }, + { + "epoch": 0.09753511794328121, + "grad_norm": 3.4478704929351807, + "learning_rate": 4.991881716198955e-06, + "loss": 0.3149, + "step": 46 + }, + { + "epoch": 0.09965544659422211, + "grad_norm": 1.566508412361145, + "learning_rate": 4.9914246979199586e-06, + "loss": 0.2163, + "step": 47 + }, + { + "epoch": 0.101775775245163, + "grad_norm": 2.76956844329834, + "learning_rate": 4.990955187640627e-06, + "loss": 0.4008, + "step": 48 + }, + { + "epoch": 0.1038961038961039, + "grad_norm": 3.9344685077667236, + "learning_rate": 4.990473187715082e-06, + "loss": 0.3937, + "step": 49 + }, + { + "epoch": 0.10601643254704479, + "grad_norm": 2.5321309566497803, + "learning_rate": 4.989978700560073e-06, + "loss": 0.381, + "step": 50 + }, + { + "epoch": 0.10813676119798568, + "grad_norm": 3.8619720935821533, + "learning_rate": 4.9894717286549566e-06, + "loss": 0.2995, + "step": 51 + }, + { + "epoch": 0.11025708984892658, + "grad_norm": 8.722846031188965, + "learning_rate": 4.98895227454169e-06, + "loss": 0.2401, + "step": 52 + }, + { + "epoch": 0.11237741849986747, + "grad_norm": 1.9420874118804932, + "learning_rate": 4.9884203408248145e-06, + "loss": 0.3294, + "step": 53 + }, + { + "epoch": 0.11449774715080838, + "grad_norm": 2.523827314376831, + "learning_rate": 4.987875930171446e-06, + "loss": 0.4972, + "step": 54 + }, + { + "epoch": 0.11661807580174927, + "grad_norm": 3.6966936588287354, + "learning_rate": 4.987319045311259e-06, + "loss": 0.4146, + "step": 55 + }, + { + "epoch": 0.11873840445269017, + "grad_norm": 2.447277069091797, + "learning_rate": 4.9867496890364734e-06, + "loss": 0.3277, + "step": 56 + }, + { + "epoch": 0.12085873310363106, + "grad_norm": 2.2751476764678955, + "learning_rate": 4.98616786420184e-06, + "loss": 0.2963, + "step": 57 + }, + { + "epoch": 0.12297906175457196, + "grad_norm": 1.655998706817627, + "learning_rate": 4.985573573724628e-06, + "loss": 0.2798, + "step": 58 + }, + { + "epoch": 0.12509939040551285, + "grad_norm": 5.7478837966918945, + "learning_rate": 4.98496682058461e-06, + "loss": 0.3764, + "step": 59 + }, + { + "epoch": 0.12721971905645374, + "grad_norm": 1.5899176597595215, + "learning_rate": 4.984347607824045e-06, + "loss": 0.2544, + "step": 60 + }, + { + "epoch": 0.12934004770739466, + "grad_norm": 2.066739082336426, + "learning_rate": 4.9837159385476655e-06, + "loss": 0.3421, + "step": 61 + }, + { + "epoch": 0.13146037635833555, + "grad_norm": 4.85571813583374, + "learning_rate": 4.983071815922659e-06, + "loss": 0.4167, + "step": 62 + }, + { + "epoch": 0.13358070500927643, + "grad_norm": 4.446200370788574, + "learning_rate": 4.9824152431786565e-06, + "loss": 0.1973, + "step": 63 + }, + { + "epoch": 0.13570103366021732, + "grad_norm": 2.905205011367798, + "learning_rate": 4.981746223607713e-06, + "loss": 0.3211, + "step": 64 + }, + { + "epoch": 0.13782136231115824, + "grad_norm": 1.2360762357711792, + "learning_rate": 4.981064760564292e-06, + "loss": 0.2813, + "step": 65 + }, + { + "epoch": 0.13994169096209913, + "grad_norm": 2.0999205112457275, + "learning_rate": 4.9803708574652475e-06, + "loss": 0.2489, + "step": 66 + }, + { + "epoch": 0.14206201961304002, + "grad_norm": 4.240612030029297, + "learning_rate": 4.979664517789811e-06, + "loss": 0.3817, + "step": 67 + }, + { + "epoch": 0.1441823482639809, + "grad_norm": 2.3623316287994385, + "learning_rate": 4.978945745079565e-06, + "loss": 0.2673, + "step": 68 + }, + { + "epoch": 0.14630267691492183, + "grad_norm": 3.3251216411590576, + "learning_rate": 4.978214542938438e-06, + "loss": 0.2844, + "step": 69 + }, + { + "epoch": 0.14842300556586271, + "grad_norm": 1.5501821041107178, + "learning_rate": 4.977470915032676e-06, + "loss": 0.2262, + "step": 70 + }, + { + "epoch": 0.1505433342168036, + "grad_norm": 2.6850452423095703, + "learning_rate": 4.976714865090827e-06, + "loss": 0.265, + "step": 71 + }, + { + "epoch": 0.1526636628677445, + "grad_norm": 3.2187998294830322, + "learning_rate": 4.975946396903727e-06, + "loss": 0.3004, + "step": 72 + }, + { + "epoch": 0.1547839915186854, + "grad_norm": 2.397681951522827, + "learning_rate": 4.9751655143244715e-06, + "loss": 0.3076, + "step": 73 + }, + { + "epoch": 0.1569043201696263, + "grad_norm": 4.3145952224731445, + "learning_rate": 4.974372221268408e-06, + "loss": 0.237, + "step": 74 + }, + { + "epoch": 0.1590246488205672, + "grad_norm": 1.271013617515564, + "learning_rate": 4.973566521713104e-06, + "loss": 0.3886, + "step": 75 + }, + { + "epoch": 0.16114497747150808, + "grad_norm": 3.8556087017059326, + "learning_rate": 4.972748419698337e-06, + "loss": 0.4216, + "step": 76 + }, + { + "epoch": 0.16326530612244897, + "grad_norm": 2.6716325283050537, + "learning_rate": 4.971917919326071e-06, + "loss": 0.2869, + "step": 77 + }, + { + "epoch": 0.16538563477338988, + "grad_norm": 3.054572820663452, + "learning_rate": 4.971075024760432e-06, + "loss": 0.2688, + "step": 78 + }, + { + "epoch": 0.16750596342433077, + "grad_norm": 2.3528730869293213, + "learning_rate": 4.970219740227693e-06, + "loss": 0.3894, + "step": 79 + }, + { + "epoch": 0.16962629207527166, + "grad_norm": 2.507408857345581, + "learning_rate": 4.96935207001625e-06, + "loss": 0.3129, + "step": 80 + }, + { + "epoch": 0.17174662072621255, + "grad_norm": 3.135934829711914, + "learning_rate": 4.968472018476599e-06, + "loss": 0.322, + "step": 81 + }, + { + "epoch": 0.17386694937715347, + "grad_norm": 2.3163411617279053, + "learning_rate": 4.967579590021319e-06, + "loss": 0.3069, + "step": 82 + }, + { + "epoch": 0.17598727802809436, + "grad_norm": 4.409370422363281, + "learning_rate": 4.966674789125044e-06, + "loss": 0.3893, + "step": 83 + }, + { + "epoch": 0.17810760667903525, + "grad_norm": 3.5317368507385254, + "learning_rate": 4.965757620324445e-06, + "loss": 0.3198, + "step": 84 + }, + { + "epoch": 0.18022793532997614, + "grad_norm": 2.794269561767578, + "learning_rate": 4.9648280882182056e-06, + "loss": 0.3547, + "step": 85 + }, + { + "epoch": 0.18234826398091705, + "grad_norm": 1.2279053926467896, + "learning_rate": 4.963886197466998e-06, + "loss": 0.2338, + "step": 86 + }, + { + "epoch": 0.18446859263185794, + "grad_norm": 3.633697509765625, + "learning_rate": 4.962931952793461e-06, + "loss": 0.3118, + "step": 87 + }, + { + "epoch": 0.18658892128279883, + "grad_norm": 1.3397223949432373, + "learning_rate": 4.961965358982177e-06, + "loss": 0.2744, + "step": 88 + }, + { + "epoch": 0.18870924993373972, + "grad_norm": 2.2551627159118652, + "learning_rate": 4.960986420879645e-06, + "loss": 0.3339, + "step": 89 + }, + { + "epoch": 0.19082957858468064, + "grad_norm": 2.727034330368042, + "learning_rate": 4.9599951433942614e-06, + "loss": 0.2318, + "step": 90 + }, + { + "epoch": 0.19294990723562153, + "grad_norm": 2.2735791206359863, + "learning_rate": 4.958991531496289e-06, + "loss": 0.3198, + "step": 91 + }, + { + "epoch": 0.19507023588656242, + "grad_norm": 3.066884756088257, + "learning_rate": 4.957975590217836e-06, + "loss": 0.2254, + "step": 92 + }, + { + "epoch": 0.1971905645375033, + "grad_norm": 2.4200687408447266, + "learning_rate": 4.956947324652832e-06, + "loss": 0.277, + "step": 93 + }, + { + "epoch": 0.19931089318844422, + "grad_norm": 3.770292043685913, + "learning_rate": 4.955906739956999e-06, + "loss": 0.3462, + "step": 94 + }, + { + "epoch": 0.2014312218393851, + "grad_norm": 2.9880192279815674, + "learning_rate": 4.954853841347827e-06, + "loss": 0.2103, + "step": 95 + }, + { + "epoch": 0.203551550490326, + "grad_norm": 2.8914637565612793, + "learning_rate": 4.9537886341045475e-06, + "loss": 0.246, + "step": 96 + }, + { + "epoch": 0.2056718791412669, + "grad_norm": 4.304288864135742, + "learning_rate": 4.95271112356811e-06, + "loss": 0.3306, + "step": 97 + }, + { + "epoch": 0.2077922077922078, + "grad_norm": 6.69378662109375, + "learning_rate": 4.951621315141149e-06, + "loss": 0.37, + "step": 98 + }, + { + "epoch": 0.2099125364431487, + "grad_norm": 4.184510231018066, + "learning_rate": 4.950519214287966e-06, + "loss": 0.3687, + "step": 99 + }, + { + "epoch": 0.21203286509408958, + "grad_norm": 3.177889585494995, + "learning_rate": 4.9494048265344896e-06, + "loss": 0.4234, + "step": 100 + }, + { + "epoch": 0.21415319374503047, + "grad_norm": 1.1268483400344849, + "learning_rate": 4.94827815746826e-06, + "loss": 0.3633, + "step": 101 + }, + { + "epoch": 0.21627352239597136, + "grad_norm": 3.196904420852661, + "learning_rate": 4.947139212738395e-06, + "loss": 0.3335, + "step": 102 + }, + { + "epoch": 0.21839385104691228, + "grad_norm": 3.6721370220184326, + "learning_rate": 4.945987998055562e-06, + "loss": 0.186, + "step": 103 + }, + { + "epoch": 0.22051417969785317, + "grad_norm": 2.374629497528076, + "learning_rate": 4.944824519191949e-06, + "loss": 0.2399, + "step": 104 + }, + { + "epoch": 0.22263450834879406, + "grad_norm": 3.0888235569000244, + "learning_rate": 4.943648781981239e-06, + "loss": 0.2794, + "step": 105 + }, + { + "epoch": 0.22475483699973495, + "grad_norm": 2.1860692501068115, + "learning_rate": 4.942460792318575e-06, + "loss": 0.2431, + "step": 106 + }, + { + "epoch": 0.22687516565067586, + "grad_norm": 2.057961940765381, + "learning_rate": 4.9412605561605365e-06, + "loss": 0.258, + "step": 107 + }, + { + "epoch": 0.22899549430161675, + "grad_norm": 2.826047420501709, + "learning_rate": 4.940048079525108e-06, + "loss": 0.3056, + "step": 108 + }, + { + "epoch": 0.23111582295255764, + "grad_norm": 1.93588125705719, + "learning_rate": 4.9388233684916434e-06, + "loss": 0.3374, + "step": 109 + }, + { + "epoch": 0.23323615160349853, + "grad_norm": 1.4116945266723633, + "learning_rate": 4.937586429200842e-06, + "loss": 0.1877, + "step": 110 + }, + { + "epoch": 0.23535648025443945, + "grad_norm": 3.5607080459594727, + "learning_rate": 4.936337267854719e-06, + "loss": 0.319, + "step": 111 + }, + { + "epoch": 0.23747680890538034, + "grad_norm": 1.9677248001098633, + "learning_rate": 4.935075890716565e-06, + "loss": 0.2615, + "step": 112 + }, + { + "epoch": 0.23959713755632123, + "grad_norm": 1.2864681482315063, + "learning_rate": 4.933802304110925e-06, + "loss": 0.2038, + "step": 113 + }, + { + "epoch": 0.24171746620726212, + "grad_norm": 3.6011598110198975, + "learning_rate": 4.932516514423559e-06, + "loss": 0.2945, + "step": 114 + }, + { + "epoch": 0.24383779485820303, + "grad_norm": 0.8037973642349243, + "learning_rate": 4.931218528101416e-06, + "loss": 0.2102, + "step": 115 + }, + { + "epoch": 0.24595812350914392, + "grad_norm": 5.048084259033203, + "learning_rate": 4.929908351652598e-06, + "loss": 0.3449, + "step": 116 + }, + { + "epoch": 0.2480784521600848, + "grad_norm": 3.8754634857177734, + "learning_rate": 4.928585991646327e-06, + "loss": 0.3072, + "step": 117 + }, + { + "epoch": 0.2501987808110257, + "grad_norm": 3.335463523864746, + "learning_rate": 4.927251454712915e-06, + "loss": 0.3457, + "step": 118 + }, + { + "epoch": 0.2523191094619666, + "grad_norm": 2.5155117511749268, + "learning_rate": 4.925904747543729e-06, + "loss": 0.3305, + "step": 119 + }, + { + "epoch": 0.2544394381129075, + "grad_norm": 3.2518768310546875, + "learning_rate": 4.924545876891157e-06, + "loss": 0.4029, + "step": 120 + }, + { + "epoch": 0.2565597667638484, + "grad_norm": 3.0308430194854736, + "learning_rate": 4.9231748495685745e-06, + "loss": 0.3313, + "step": 121 + }, + { + "epoch": 0.2586800954147893, + "grad_norm": 4.494399070739746, + "learning_rate": 4.921791672450311e-06, + "loss": 0.263, + "step": 122 + }, + { + "epoch": 0.2608004240657302, + "grad_norm": 3.257610321044922, + "learning_rate": 4.920396352471613e-06, + "loss": 0.4046, + "step": 123 + }, + { + "epoch": 0.2629207527166711, + "grad_norm": 2.162080764770508, + "learning_rate": 4.918988896628617e-06, + "loss": 0.2562, + "step": 124 + }, + { + "epoch": 0.26504108136761195, + "grad_norm": 1.7331904172897339, + "learning_rate": 4.917569311978301e-06, + "loss": 0.2157, + "step": 125 + }, + { + "epoch": 0.26716141001855287, + "grad_norm": 2.089783191680908, + "learning_rate": 4.916137605638463e-06, + "loss": 0.2177, + "step": 126 + }, + { + "epoch": 0.2692817386694938, + "grad_norm": 2.637751817703247, + "learning_rate": 4.914693784787676e-06, + "loss": 0.2717, + "step": 127 + }, + { + "epoch": 0.27140206732043465, + "grad_norm": 1.1012979745864868, + "learning_rate": 4.913237856665256e-06, + "loss": 0.2845, + "step": 128 + }, + { + "epoch": 0.27352239597137556, + "grad_norm": 2.7496721744537354, + "learning_rate": 4.911769828571224e-06, + "loss": 0.2839, + "step": 129 + }, + { + "epoch": 0.2756427246223165, + "grad_norm": 3.16662335395813, + "learning_rate": 4.910289707866273e-06, + "loss": 0.3791, + "step": 130 + }, + { + "epoch": 0.27776305327325734, + "grad_norm": 3.3091320991516113, + "learning_rate": 4.908797501971725e-06, + "loss": 0.3046, + "step": 131 + }, + { + "epoch": 0.27988338192419826, + "grad_norm": 2.08532452583313, + "learning_rate": 4.907293218369499e-06, + "loss": 0.2242, + "step": 132 + }, + { + "epoch": 0.2820037105751391, + "grad_norm": 1.4009634256362915, + "learning_rate": 4.90577686460207e-06, + "loss": 0.2657, + "step": 133 + }, + { + "epoch": 0.28412403922608004, + "grad_norm": 2.2569682598114014, + "learning_rate": 4.904248448272435e-06, + "loss": 0.2321, + "step": 134 + }, + { + "epoch": 0.28624436787702096, + "grad_norm": 2.43658709526062, + "learning_rate": 4.902707977044071e-06, + "loss": 0.2339, + "step": 135 + }, + { + "epoch": 0.2883646965279618, + "grad_norm": 1.7777557373046875, + "learning_rate": 4.9011554586409005e-06, + "loss": 0.2703, + "step": 136 + }, + { + "epoch": 0.29048502517890273, + "grad_norm": 4.1074347496032715, + "learning_rate": 4.8995909008472465e-06, + "loss": 0.3249, + "step": 137 + }, + { + "epoch": 0.29260535382984365, + "grad_norm": 2.1729867458343506, + "learning_rate": 4.898014311507801e-06, + "loss": 0.229, + "step": 138 + }, + { + "epoch": 0.2947256824807845, + "grad_norm": 3.032817840576172, + "learning_rate": 4.8964256985275805e-06, + "loss": 0.2925, + "step": 139 + }, + { + "epoch": 0.29684601113172543, + "grad_norm": 1.834567904472351, + "learning_rate": 4.8948250698718895e-06, + "loss": 0.2349, + "step": 140 + }, + { + "epoch": 0.2989663397826663, + "grad_norm": 3.393310785293579, + "learning_rate": 4.893212433566277e-06, + "loss": 0.3615, + "step": 141 + }, + { + "epoch": 0.3010866684336072, + "grad_norm": 4.021195888519287, + "learning_rate": 4.8915877976964995e-06, + "loss": 0.4128, + "step": 142 + }, + { + "epoch": 0.3032069970845481, + "grad_norm": 1.6174540519714355, + "learning_rate": 4.889951170408479e-06, + "loss": 0.2398, + "step": 143 + }, + { + "epoch": 0.305327325735489, + "grad_norm": 2.0691730976104736, + "learning_rate": 4.888302559908265e-06, + "loss": 0.3333, + "step": 144 + }, + { + "epoch": 0.3074476543864299, + "grad_norm": 0.9198992848396301, + "learning_rate": 4.886641974461985e-06, + "loss": 0.2091, + "step": 145 + }, + { + "epoch": 0.3095679830373708, + "grad_norm": 2.2674360275268555, + "learning_rate": 4.884969422395815e-06, + "loss": 0.2042, + "step": 146 + }, + { + "epoch": 0.3116883116883117, + "grad_norm": 2.365835428237915, + "learning_rate": 4.883284912095928e-06, + "loss": 0.3742, + "step": 147 + }, + { + "epoch": 0.3138086403392526, + "grad_norm": 3.322329521179199, + "learning_rate": 4.881588452008457e-06, + "loss": 0.3228, + "step": 148 + }, + { + "epoch": 0.31592896899019346, + "grad_norm": 6.298361301422119, + "learning_rate": 4.87988005063945e-06, + "loss": 0.452, + "step": 149 + }, + { + "epoch": 0.3180492976411344, + "grad_norm": 3.925762414932251, + "learning_rate": 4.87815971655483e-06, + "loss": 0.3467, + "step": 150 + }, + { + "epoch": 0.3201696262920753, + "grad_norm": 4.023056507110596, + "learning_rate": 4.876427458380349e-06, + "loss": 0.3558, + "step": 151 + }, + { + "epoch": 0.32228995494301615, + "grad_norm": 3.4093480110168457, + "learning_rate": 4.874683284801548e-06, + "loss": 0.2739, + "step": 152 + }, + { + "epoch": 0.32441028359395707, + "grad_norm": 0.9935247302055359, + "learning_rate": 4.872927204563712e-06, + "loss": 0.2131, + "step": 153 + }, + { + "epoch": 0.32653061224489793, + "grad_norm": 1.8300209045410156, + "learning_rate": 4.871159226471825e-06, + "loss": 0.329, + "step": 154 + }, + { + "epoch": 0.32865094089583885, + "grad_norm": 2.8266682624816895, + "learning_rate": 4.869379359390524e-06, + "loss": 0.2388, + "step": 155 + }, + { + "epoch": 0.33077126954677977, + "grad_norm": 3.9147934913635254, + "learning_rate": 4.867587612244064e-06, + "loss": 0.3476, + "step": 156 + }, + { + "epoch": 0.33289159819772063, + "grad_norm": 2.4226462841033936, + "learning_rate": 4.865783994016261e-06, + "loss": 0.3471, + "step": 157 + }, + { + "epoch": 0.33501192684866155, + "grad_norm": 2.4413650035858154, + "learning_rate": 4.863968513750456e-06, + "loss": 0.3026, + "step": 158 + }, + { + "epoch": 0.33713225549960246, + "grad_norm": 2.6878299713134766, + "learning_rate": 4.862141180549464e-06, + "loss": 0.3127, + "step": 159 + }, + { + "epoch": 0.3392525841505433, + "grad_norm": 2.855107545852661, + "learning_rate": 4.86030200357553e-06, + "loss": 0.2059, + "step": 160 + }, + { + "epoch": 0.34137291280148424, + "grad_norm": 2.976635217666626, + "learning_rate": 4.858450992050287e-06, + "loss": 0.2706, + "step": 161 + }, + { + "epoch": 0.3434932414524251, + "grad_norm": 4.121407508850098, + "learning_rate": 4.856588155254704e-06, + "loss": 0.2539, + "step": 162 + }, + { + "epoch": 0.345613570103366, + "grad_norm": 0.857638955116272, + "learning_rate": 4.854713502529042e-06, + "loss": 0.2923, + "step": 163 + }, + { + "epoch": 0.34773389875430694, + "grad_norm": 1.6652028560638428, + "learning_rate": 4.852827043272808e-06, + "loss": 0.2357, + "step": 164 + }, + { + "epoch": 0.3498542274052478, + "grad_norm": 3.286330223083496, + "learning_rate": 4.850928786944706e-06, + "loss": 0.2745, + "step": 165 + }, + { + "epoch": 0.3519745560561887, + "grad_norm": 3.9806864261627197, + "learning_rate": 4.84901874306259e-06, + "loss": 0.2503, + "step": 166 + }, + { + "epoch": 0.35409488470712963, + "grad_norm": 2.8622264862060547, + "learning_rate": 4.847096921203419e-06, + "loss": 0.3615, + "step": 167 + }, + { + "epoch": 0.3562152133580705, + "grad_norm": 3.0431885719299316, + "learning_rate": 4.845163331003205e-06, + "loss": 0.187, + "step": 168 + }, + { + "epoch": 0.3583355420090114, + "grad_norm": 1.8177791833877563, + "learning_rate": 4.843217982156968e-06, + "loss": 0.2641, + "step": 169 + }, + { + "epoch": 0.36045587065995227, + "grad_norm": 0.6192033290863037, + "learning_rate": 4.841260884418682e-06, + "loss": 0.2323, + "step": 170 + }, + { + "epoch": 0.3625761993108932, + "grad_norm": 4.052712917327881, + "learning_rate": 4.839292047601234e-06, + "loss": 0.3339, + "step": 171 + }, + { + "epoch": 0.3646965279618341, + "grad_norm": 1.8390997648239136, + "learning_rate": 4.83731148157637e-06, + "loss": 0.2844, + "step": 172 + }, + { + "epoch": 0.36681685661277497, + "grad_norm": 1.4040610790252686, + "learning_rate": 4.835319196274646e-06, + "loss": 0.3137, + "step": 173 + }, + { + "epoch": 0.3689371852637159, + "grad_norm": 3.0023269653320312, + "learning_rate": 4.833315201685375e-06, + "loss": 0.2336, + "step": 174 + }, + { + "epoch": 0.37105751391465674, + "grad_norm": 1.7594302892684937, + "learning_rate": 4.831299507856587e-06, + "loss": 0.2312, + "step": 175 + }, + { + "epoch": 0.37317784256559766, + "grad_norm": 1.7524633407592773, + "learning_rate": 4.829272124894967e-06, + "loss": 0.3141, + "step": 176 + }, + { + "epoch": 0.3752981712165386, + "grad_norm": 9.093369483947754, + "learning_rate": 4.827233062965811e-06, + "loss": 0.259, + "step": 177 + }, + { + "epoch": 0.37741849986747944, + "grad_norm": 2.2024335861206055, + "learning_rate": 4.82518233229297e-06, + "loss": 0.23, + "step": 178 + }, + { + "epoch": 0.37953882851842036, + "grad_norm": 0.7254531979560852, + "learning_rate": 4.823119943158809e-06, + "loss": 0.2643, + "step": 179 + }, + { + "epoch": 0.3816591571693613, + "grad_norm": 2.181795120239258, + "learning_rate": 4.821045905904143e-06, + "loss": 0.2215, + "step": 180 + }, + { + "epoch": 0.38377948582030214, + "grad_norm": 1.5816072225570679, + "learning_rate": 4.818960230928192e-06, + "loss": 0.2168, + "step": 181 + }, + { + "epoch": 0.38589981447124305, + "grad_norm": 2.4816792011260986, + "learning_rate": 4.816862928688528e-06, + "loss": 0.2618, + "step": 182 + }, + { + "epoch": 0.3880201431221839, + "grad_norm": 2.069082260131836, + "learning_rate": 4.814754009701023e-06, + "loss": 0.3713, + "step": 183 + }, + { + "epoch": 0.39014047177312483, + "grad_norm": 2.61807918548584, + "learning_rate": 4.8126334845397914e-06, + "loss": 0.3274, + "step": 184 + }, + { + "epoch": 0.39226080042406575, + "grad_norm": 2.7736072540283203, + "learning_rate": 4.8105013638371454e-06, + "loss": 0.231, + "step": 185 + }, + { + "epoch": 0.3943811290750066, + "grad_norm": 3.6297597885131836, + "learning_rate": 4.8083576582835366e-06, + "loss": 0.3412, + "step": 186 + }, + { + "epoch": 0.3965014577259475, + "grad_norm": 2.2494869232177734, + "learning_rate": 4.8062023786274996e-06, + "loss": 0.247, + "step": 187 + }, + { + "epoch": 0.39862178637688844, + "grad_norm": 1.3295131921768188, + "learning_rate": 4.804035535675606e-06, + "loss": 0.2412, + "step": 188 + }, + { + "epoch": 0.4007421150278293, + "grad_norm": 2.058772325515747, + "learning_rate": 4.801857140292402e-06, + "loss": 0.2943, + "step": 189 + }, + { + "epoch": 0.4028624436787702, + "grad_norm": 1.5720592737197876, + "learning_rate": 4.799667203400361e-06, + "loss": 0.274, + "step": 190 + }, + { + "epoch": 0.4049827723297111, + "grad_norm": 2.5041348934173584, + "learning_rate": 4.7974657359798224e-06, + "loss": 0.245, + "step": 191 + }, + { + "epoch": 0.407103100980652, + "grad_norm": 1.9566255807876587, + "learning_rate": 4.795252749068942e-06, + "loss": 0.3203, + "step": 192 + }, + { + "epoch": 0.4092234296315929, + "grad_norm": 4.478713035583496, + "learning_rate": 4.793028253763633e-06, + "loss": 0.3274, + "step": 193 + }, + { + "epoch": 0.4113437582825338, + "grad_norm": 3.3313329219818115, + "learning_rate": 4.790792261217513e-06, + "loss": 0.3502, + "step": 194 + }, + { + "epoch": 0.4134640869334747, + "grad_norm": 2.875757932662964, + "learning_rate": 4.7885447826418435e-06, + "loss": 0.4093, + "step": 195 + }, + { + "epoch": 0.4155844155844156, + "grad_norm": 2.094299793243408, + "learning_rate": 4.786285829305481e-06, + "loss": 0.3394, + "step": 196 + }, + { + "epoch": 0.4177047442353565, + "grad_norm": 3.40802264213562, + "learning_rate": 4.784015412534816e-06, + "loss": 0.2579, + "step": 197 + }, + { + "epoch": 0.4198250728862974, + "grad_norm": 2.5901896953582764, + "learning_rate": 4.781733543713714e-06, + "loss": 0.3256, + "step": 198 + }, + { + "epoch": 0.42194540153723825, + "grad_norm": 2.649927854537964, + "learning_rate": 4.779440234283461e-06, + "loss": 0.2552, + "step": 199 + }, + { + "epoch": 0.42406573018817917, + "grad_norm": 2.827615261077881, + "learning_rate": 4.77713549574271e-06, + "loss": 0.345, + "step": 200 + }, + { + "epoch": 0.4261860588391201, + "grad_norm": 2.3520429134368896, + "learning_rate": 4.774819339647415e-06, + "loss": 0.3555, + "step": 201 + }, + { + "epoch": 0.42830638749006095, + "grad_norm": 2.04105281829834, + "learning_rate": 4.772491777610782e-06, + "loss": 0.3845, + "step": 202 + }, + { + "epoch": 0.43042671614100186, + "grad_norm": 2.4335427284240723, + "learning_rate": 4.770152821303203e-06, + "loss": 0.226, + "step": 203 + }, + { + "epoch": 0.4325470447919427, + "grad_norm": 3.064467191696167, + "learning_rate": 4.767802482452202e-06, + "loss": 0.2998, + "step": 204 + }, + { + "epoch": 0.43466737344288364, + "grad_norm": 1.1668577194213867, + "learning_rate": 4.7654407728423745e-06, + "loss": 0.2627, + "step": 205 + }, + { + "epoch": 0.43678770209382456, + "grad_norm": 1.9054539203643799, + "learning_rate": 4.763067704315331e-06, + "loss": 0.3959, + "step": 206 + }, + { + "epoch": 0.4389080307447654, + "grad_norm": 2.3456785678863525, + "learning_rate": 4.760683288769634e-06, + "loss": 0.3076, + "step": 207 + }, + { + "epoch": 0.44102835939570634, + "grad_norm": 3.0187900066375732, + "learning_rate": 4.758287538160738e-06, + "loss": 0.2894, + "step": 208 + }, + { + "epoch": 0.44314868804664725, + "grad_norm": 2.9057319164276123, + "learning_rate": 4.755880464500936e-06, + "loss": 0.289, + "step": 209 + }, + { + "epoch": 0.4452690166975881, + "grad_norm": 2.7487642765045166, + "learning_rate": 4.753462079859291e-06, + "loss": 0.2759, + "step": 210 + }, + { + "epoch": 0.44738934534852903, + "grad_norm": 1.8765803575515747, + "learning_rate": 4.7510323963615815e-06, + "loss": 0.2892, + "step": 211 + }, + { + "epoch": 0.4495096739994699, + "grad_norm": 1.8452672958374023, + "learning_rate": 4.748591426190237e-06, + "loss": 0.2232, + "step": 212 + }, + { + "epoch": 0.4516300026504108, + "grad_norm": 3.8514230251312256, + "learning_rate": 4.746139181584278e-06, + "loss": 0.2904, + "step": 213 + }, + { + "epoch": 0.45375033130135173, + "grad_norm": 1.5355229377746582, + "learning_rate": 4.743675674839258e-06, + "loss": 0.3108, + "step": 214 + }, + { + "epoch": 0.4558706599522926, + "grad_norm": 2.429868698120117, + "learning_rate": 4.741200918307194e-06, + "loss": 0.3254, + "step": 215 + }, + { + "epoch": 0.4579909886032335, + "grad_norm": 1.8861596584320068, + "learning_rate": 4.738714924396514e-06, + "loss": 0.3318, + "step": 216 + }, + { + "epoch": 0.4601113172541744, + "grad_norm": 2.709230661392212, + "learning_rate": 4.736217705571989e-06, + "loss": 0.2817, + "step": 217 + }, + { + "epoch": 0.4622316459051153, + "grad_norm": 1.2253323793411255, + "learning_rate": 4.73370927435467e-06, + "loss": 0.3168, + "step": 218 + }, + { + "epoch": 0.4643519745560562, + "grad_norm": 2.5226621627807617, + "learning_rate": 4.731189643321829e-06, + "loss": 0.263, + "step": 219 + }, + { + "epoch": 0.46647230320699706, + "grad_norm": 3.8697330951690674, + "learning_rate": 4.728658825106891e-06, + "loss": 0.237, + "step": 220 + }, + { + "epoch": 0.468592631857938, + "grad_norm": 1.7124079465866089, + "learning_rate": 4.726116832399376e-06, + "loss": 0.1574, + "step": 221 + }, + { + "epoch": 0.4707129605088789, + "grad_norm": 1.372372031211853, + "learning_rate": 4.723563677944833e-06, + "loss": 0.287, + "step": 222 + }, + { + "epoch": 0.47283328915981976, + "grad_norm": 1.5783618688583374, + "learning_rate": 4.720999374544776e-06, + "loss": 0.2368, + "step": 223 + }, + { + "epoch": 0.4749536178107607, + "grad_norm": 2.918891191482544, + "learning_rate": 4.718423935056617e-06, + "loss": 0.3074, + "step": 224 + }, + { + "epoch": 0.47707394646170154, + "grad_norm": 2.4617486000061035, + "learning_rate": 4.715837372393607e-06, + "loss": 0.2073, + "step": 225 + }, + { + "epoch": 0.47919427511264245, + "grad_norm": 2.3654730319976807, + "learning_rate": 4.71323969952477e-06, + "loss": 0.2204, + "step": 226 + }, + { + "epoch": 0.48131460376358337, + "grad_norm": 2.3249452114105225, + "learning_rate": 4.7106309294748315e-06, + "loss": 0.378, + "step": 227 + }, + { + "epoch": 0.48343493241452423, + "grad_norm": 5.216866493225098, + "learning_rate": 4.708011075324163e-06, + "loss": 0.2746, + "step": 228 + }, + { + "epoch": 0.48555526106546515, + "grad_norm": 2.4934608936309814, + "learning_rate": 4.70538015020871e-06, + "loss": 0.3171, + "step": 229 + }, + { + "epoch": 0.48767558971640607, + "grad_norm": 3.2651522159576416, + "learning_rate": 4.702738167319927e-06, + "loss": 0.3478, + "step": 230 + }, + { + "epoch": 0.4897959183673469, + "grad_norm": 2.3438186645507812, + "learning_rate": 4.700085139904714e-06, + "loss": 0.1753, + "step": 231 + }, + { + "epoch": 0.49191624701828784, + "grad_norm": 3.3518893718719482, + "learning_rate": 4.697421081265346e-06, + "loss": 0.2202, + "step": 232 + }, + { + "epoch": 0.4940365756692287, + "grad_norm": 5.121367931365967, + "learning_rate": 4.6947460047594105e-06, + "loss": 0.2557, + "step": 233 + }, + { + "epoch": 0.4961569043201696, + "grad_norm": 2.5385594367980957, + "learning_rate": 4.692059923799736e-06, + "loss": 0.3656, + "step": 234 + }, + { + "epoch": 0.49827723297111054, + "grad_norm": 2.5510666370391846, + "learning_rate": 4.689362851854333e-06, + "loss": 0.3637, + "step": 235 + }, + { + "epoch": 0.5003975616220514, + "grad_norm": 2.288750171661377, + "learning_rate": 4.686654802446313e-06, + "loss": 0.2433, + "step": 236 + }, + { + "epoch": 0.5025178902729923, + "grad_norm": 2.547922372817993, + "learning_rate": 4.683935789153834e-06, + "loss": 0.3574, + "step": 237 + }, + { + "epoch": 0.5046382189239332, + "grad_norm": 1.7912276983261108, + "learning_rate": 4.681205825610025e-06, + "loss": 0.3007, + "step": 238 + }, + { + "epoch": 0.5067585475748742, + "grad_norm": 1.9286338090896606, + "learning_rate": 4.67846492550292e-06, + "loss": 0.2679, + "step": 239 + }, + { + "epoch": 0.508878876225815, + "grad_norm": 2.0864994525909424, + "learning_rate": 4.675713102575389e-06, + "loss": 0.423, + "step": 240 + }, + { + "epoch": 0.5109992048767559, + "grad_norm": 1.037505030632019, + "learning_rate": 4.672950370625067e-06, + "loss": 0.2192, + "step": 241 + }, + { + "epoch": 0.5131195335276968, + "grad_norm": 1.936712384223938, + "learning_rate": 4.670176743504291e-06, + "loss": 0.3557, + "step": 242 + }, + { + "epoch": 0.5152398621786377, + "grad_norm": 2.4721193313598633, + "learning_rate": 4.667392235120023e-06, + "loss": 0.2169, + "step": 243 + }, + { + "epoch": 0.5173601908295786, + "grad_norm": 2.0251030921936035, + "learning_rate": 4.664596859433784e-06, + "loss": 0.2279, + "step": 244 + }, + { + "epoch": 0.5194805194805194, + "grad_norm": 2.416062593460083, + "learning_rate": 4.661790630461585e-06, + "loss": 0.235, + "step": 245 + }, + { + "epoch": 0.5216008481314603, + "grad_norm": 2.3397867679595947, + "learning_rate": 4.658973562273853e-06, + "loss": 0.2745, + "step": 246 + }, + { + "epoch": 0.5237211767824013, + "grad_norm": 3.574948787689209, + "learning_rate": 4.6561456689953665e-06, + "loss": 0.2579, + "step": 247 + }, + { + "epoch": 0.5258415054333422, + "grad_norm": 2.3914096355438232, + "learning_rate": 4.653306964805178e-06, + "loss": 0.3445, + "step": 248 + }, + { + "epoch": 0.5279618340842831, + "grad_norm": 1.807157278060913, + "learning_rate": 4.650457463936547e-06, + "loss": 0.2752, + "step": 249 + }, + { + "epoch": 0.5300821627352239, + "grad_norm": 1.997169017791748, + "learning_rate": 4.647597180676866e-06, + "loss": 0.2539, + "step": 250 + }, + { + "epoch": 0.5322024913861648, + "grad_norm": 2.018228530883789, + "learning_rate": 4.644726129367594e-06, + "loss": 0.2548, + "step": 251 + }, + { + "epoch": 0.5343228200371057, + "grad_norm": 1.5280331373214722, + "learning_rate": 4.6418443244041775e-06, + "loss": 0.2473, + "step": 252 + }, + { + "epoch": 0.5364431486880467, + "grad_norm": 2.8328475952148438, + "learning_rate": 4.638951780235982e-06, + "loss": 0.2633, + "step": 253 + }, + { + "epoch": 0.5385634773389876, + "grad_norm": 1.2343734502792358, + "learning_rate": 4.636048511366222e-06, + "loss": 0.2015, + "step": 254 + }, + { + "epoch": 0.5406838059899285, + "grad_norm": 2.285114049911499, + "learning_rate": 4.633134532351883e-06, + "loss": 0.242, + "step": 255 + }, + { + "epoch": 0.5428041346408693, + "grad_norm": 1.9822317361831665, + "learning_rate": 4.630209857803653e-06, + "loss": 0.1624, + "step": 256 + }, + { + "epoch": 0.5449244632918102, + "grad_norm": 1.7463964223861694, + "learning_rate": 4.6272745023858445e-06, + "loss": 0.266, + "step": 257 + }, + { + "epoch": 0.5470447919427511, + "grad_norm": 1.835262656211853, + "learning_rate": 4.624328480816329e-06, + "loss": 0.2686, + "step": 258 + }, + { + "epoch": 0.549165120593692, + "grad_norm": 3.0902907848358154, + "learning_rate": 4.621371807866452e-06, + "loss": 0.2292, + "step": 259 + }, + { + "epoch": 0.551285449244633, + "grad_norm": 1.0292060375213623, + "learning_rate": 4.618404498360971e-06, + "loss": 0.1938, + "step": 260 + }, + { + "epoch": 0.5534057778955738, + "grad_norm": 1.2217211723327637, + "learning_rate": 4.6154265671779695e-06, + "loss": 0.2923, + "step": 261 + }, + { + "epoch": 0.5555261065465147, + "grad_norm": 0.7709723711013794, + "learning_rate": 4.612438029248792e-06, + "loss": 0.2513, + "step": 262 + }, + { + "epoch": 0.5576464351974556, + "grad_norm": 1.7595287561416626, + "learning_rate": 4.609438899557964e-06, + "loss": 0.1831, + "step": 263 + }, + { + "epoch": 0.5597667638483965, + "grad_norm": 1.169548749923706, + "learning_rate": 4.606429193143118e-06, + "loss": 0.3138, + "step": 264 + }, + { + "epoch": 0.5618870924993374, + "grad_norm": 3.089507579803467, + "learning_rate": 4.6034089250949184e-06, + "loss": 0.2822, + "step": 265 + }, + { + "epoch": 0.5640074211502782, + "grad_norm": 4.917386531829834, + "learning_rate": 4.600378110556985e-06, + "loss": 0.3735, + "step": 266 + }, + { + "epoch": 0.5661277498012192, + "grad_norm": 1.7424579858779907, + "learning_rate": 4.597336764725817e-06, + "loss": 0.2993, + "step": 267 + }, + { + "epoch": 0.5682480784521601, + "grad_norm": 3.4557604789733887, + "learning_rate": 4.594284902850721e-06, + "loss": 0.2737, + "step": 268 + }, + { + "epoch": 0.570368407103101, + "grad_norm": 1.8935794830322266, + "learning_rate": 4.591222540233726e-06, + "loss": 0.2369, + "step": 269 + }, + { + "epoch": 0.5724887357540419, + "grad_norm": 3.673444986343384, + "learning_rate": 4.5881496922295176e-06, + "loss": 0.2901, + "step": 270 + }, + { + "epoch": 0.5746090644049828, + "grad_norm": 2.3238632678985596, + "learning_rate": 4.585066374245349e-06, + "loss": 0.2711, + "step": 271 + }, + { + "epoch": 0.5767293930559236, + "grad_norm": 3.2917137145996094, + "learning_rate": 4.581972601740974e-06, + "loss": 0.202, + "step": 272 + }, + { + "epoch": 0.5788497217068646, + "grad_norm": 2.7594401836395264, + "learning_rate": 4.5788683902285644e-06, + "loss": 0.2347, + "step": 273 + }, + { + "epoch": 0.5809700503578055, + "grad_norm": 2.7743582725524902, + "learning_rate": 4.5757537552726315e-06, + "loss": 0.2795, + "step": 274 + }, + { + "epoch": 0.5830903790087464, + "grad_norm": 2.2841763496398926, + "learning_rate": 4.572628712489953e-06, + "loss": 0.3109, + "step": 275 + }, + { + "epoch": 0.5852107076596873, + "grad_norm": 2.3819563388824463, + "learning_rate": 4.569493277549487e-06, + "loss": 0.2391, + "step": 276 + }, + { + "epoch": 0.5873310363106281, + "grad_norm": 1.7411075830459595, + "learning_rate": 4.566347466172303e-06, + "loss": 0.1732, + "step": 277 + }, + { + "epoch": 0.589451364961569, + "grad_norm": 0.9455245733261108, + "learning_rate": 4.563191294131494e-06, + "loss": 0.2278, + "step": 278 + }, + { + "epoch": 0.5915716936125099, + "grad_norm": 1.5805822610855103, + "learning_rate": 4.560024777252103e-06, + "loss": 0.2911, + "step": 279 + }, + { + "epoch": 0.5936920222634509, + "grad_norm": 2.25376033782959, + "learning_rate": 4.556847931411042e-06, + "loss": 0.327, + "step": 280 + }, + { + "epoch": 0.5958123509143918, + "grad_norm": 3.1903650760650635, + "learning_rate": 4.553660772537011e-06, + "loss": 0.2883, + "step": 281 + }, + { + "epoch": 0.5979326795653326, + "grad_norm": 0.6892781853675842, + "learning_rate": 4.550463316610422e-06, + "loss": 0.2981, + "step": 282 + }, + { + "epoch": 0.6000530082162735, + "grad_norm": 3.3684580326080322, + "learning_rate": 4.547255579663314e-06, + "loss": 0.3031, + "step": 283 + }, + { + "epoch": 0.6021733368672144, + "grad_norm": 1.6963587999343872, + "learning_rate": 4.544037577779276e-06, + "loss": 0.3123, + "step": 284 + }, + { + "epoch": 0.6042936655181553, + "grad_norm": 2.595681667327881, + "learning_rate": 4.540809327093366e-06, + "loss": 0.2838, + "step": 285 + }, + { + "epoch": 0.6064139941690962, + "grad_norm": 3.383328437805176, + "learning_rate": 4.537570843792028e-06, + "loss": 0.3393, + "step": 286 + }, + { + "epoch": 0.608534322820037, + "grad_norm": 2.2130298614501953, + "learning_rate": 4.534322144113016e-06, + "loss": 0.2278, + "step": 287 + }, + { + "epoch": 0.610654651470978, + "grad_norm": 1.0078691244125366, + "learning_rate": 4.531063244345303e-06, + "loss": 0.2498, + "step": 288 + }, + { + "epoch": 0.6127749801219189, + "grad_norm": 0.9451133608818054, + "learning_rate": 4.52779416082901e-06, + "loss": 0.2269, + "step": 289 + }, + { + "epoch": 0.6148953087728598, + "grad_norm": 1.5240414142608643, + "learning_rate": 4.524514909955316e-06, + "loss": 0.3268, + "step": 290 + }, + { + "epoch": 0.6170156374238007, + "grad_norm": 1.5782700777053833, + "learning_rate": 4.521225508166383e-06, + "loss": 0.3014, + "step": 291 + }, + { + "epoch": 0.6191359660747416, + "grad_norm": 1.9916071891784668, + "learning_rate": 4.517925971955267e-06, + "loss": 0.2863, + "step": 292 + }, + { + "epoch": 0.6212562947256824, + "grad_norm": 1.9299273490905762, + "learning_rate": 4.514616317865838e-06, + "loss": 0.3096, + "step": 293 + }, + { + "epoch": 0.6233766233766234, + "grad_norm": 1.721146583557129, + "learning_rate": 4.5112965624926965e-06, + "loss": 0.284, + "step": 294 + }, + { + "epoch": 0.6254969520275643, + "grad_norm": 2.213865280151367, + "learning_rate": 4.507966722481093e-06, + "loss": 0.3541, + "step": 295 + }, + { + "epoch": 0.6276172806785052, + "grad_norm": 5.646588325500488, + "learning_rate": 4.504626814526841e-06, + "loss": 0.287, + "step": 296 + }, + { + "epoch": 0.6297376093294461, + "grad_norm": 1.9379154443740845, + "learning_rate": 4.501276855376235e-06, + "loss": 0.266, + "step": 297 + }, + { + "epoch": 0.6318579379803869, + "grad_norm": 4.37392520904541, + "learning_rate": 4.497916861825966e-06, + "loss": 0.3637, + "step": 298 + }, + { + "epoch": 0.6339782666313278, + "grad_norm": 1.6309797763824463, + "learning_rate": 4.494546850723037e-06, + "loss": 0.2331, + "step": 299 + }, + { + "epoch": 0.6360985952822688, + "grad_norm": 1.2552251815795898, + "learning_rate": 4.4911668389646795e-06, + "loss": 0.2661, + "step": 300 + }, + { + "epoch": 0.6382189239332097, + "grad_norm": 2.0839784145355225, + "learning_rate": 4.487776843498268e-06, + "loss": 0.2305, + "step": 301 + }, + { + "epoch": 0.6403392525841506, + "grad_norm": 2.6097898483276367, + "learning_rate": 4.484376881321237e-06, + "loss": 0.3038, + "step": 302 + }, + { + "epoch": 0.6424595812350914, + "grad_norm": 1.4699310064315796, + "learning_rate": 4.480966969480992e-06, + "loss": 0.1923, + "step": 303 + }, + { + "epoch": 0.6445799098860323, + "grad_norm": 1.1542787551879883, + "learning_rate": 4.477547125074826e-06, + "loss": 0.2522, + "step": 304 + }, + { + "epoch": 0.6467002385369732, + "grad_norm": 3.114525556564331, + "learning_rate": 4.474117365249835e-06, + "loss": 0.3941, + "step": 305 + }, + { + "epoch": 0.6488205671879141, + "grad_norm": 3.131681442260742, + "learning_rate": 4.4706777072028305e-06, + "loss": 0.2683, + "step": 306 + }, + { + "epoch": 0.6509408958388551, + "grad_norm": 2.522207021713257, + "learning_rate": 4.4672281681802536e-06, + "loss": 0.4248, + "step": 307 + }, + { + "epoch": 0.6530612244897959, + "grad_norm": 2.6396241188049316, + "learning_rate": 4.463768765478088e-06, + "loss": 0.3615, + "step": 308 + }, + { + "epoch": 0.6551815531407368, + "grad_norm": 1.8852202892303467, + "learning_rate": 4.460299516441777e-06, + "loss": 0.1891, + "step": 309 + }, + { + "epoch": 0.6573018817916777, + "grad_norm": 1.5633989572525024, + "learning_rate": 4.456820438466127e-06, + "loss": 0.3321, + "step": 310 + }, + { + "epoch": 0.6594222104426186, + "grad_norm": 0.9212223291397095, + "learning_rate": 4.453331548995235e-06, + "loss": 0.1842, + "step": 311 + }, + { + "epoch": 0.6615425390935595, + "grad_norm": 0.9008169174194336, + "learning_rate": 4.449832865522386e-06, + "loss": 0.2623, + "step": 312 + }, + { + "epoch": 0.6636628677445005, + "grad_norm": 2.3239521980285645, + "learning_rate": 4.446324405589973e-06, + "loss": 0.2996, + "step": 313 + }, + { + "epoch": 0.6657831963954413, + "grad_norm": 1.245194911956787, + "learning_rate": 4.442806186789414e-06, + "loss": 0.292, + "step": 314 + }, + { + "epoch": 0.6679035250463822, + "grad_norm": 1.7970019578933716, + "learning_rate": 4.43927822676105e-06, + "loss": 0.3205, + "step": 315 + }, + { + "epoch": 0.6700238536973231, + "grad_norm": 2.037053346633911, + "learning_rate": 4.43574054319407e-06, + "loss": 0.3059, + "step": 316 + }, + { + "epoch": 0.672144182348264, + "grad_norm": 2.7384984493255615, + "learning_rate": 4.432193153826414e-06, + "loss": 0.1772, + "step": 317 + }, + { + "epoch": 0.6742645109992049, + "grad_norm": 2.5001444816589355, + "learning_rate": 4.428636076444689e-06, + "loss": 0.2689, + "step": 318 + }, + { + "epoch": 0.6763848396501457, + "grad_norm": 2.1559765338897705, + "learning_rate": 4.425069328884076e-06, + "loss": 0.3262, + "step": 319 + }, + { + "epoch": 0.6785051683010866, + "grad_norm": 2.2558753490448, + "learning_rate": 4.421492929028243e-06, + "loss": 0.2938, + "step": 320 + }, + { + "epoch": 0.6806254969520276, + "grad_norm": 2.5780105590820312, + "learning_rate": 4.417906894809254e-06, + "loss": 0.287, + "step": 321 + }, + { + "epoch": 0.6827458256029685, + "grad_norm": 1.2815518379211426, + "learning_rate": 4.41431124420748e-06, + "loss": 0.2534, + "step": 322 + }, + { + "epoch": 0.6848661542539094, + "grad_norm": 1.6378668546676636, + "learning_rate": 4.410705995251509e-06, + "loss": 0.2202, + "step": 323 + }, + { + "epoch": 0.6869864829048502, + "grad_norm": 1.0137518644332886, + "learning_rate": 4.4070911660180546e-06, + "loss": 0.2868, + "step": 324 + }, + { + "epoch": 0.6891068115557911, + "grad_norm": 1.8886064291000366, + "learning_rate": 4.403466774631867e-06, + "loss": 0.1661, + "step": 325 + }, + { + "epoch": 0.691227140206732, + "grad_norm": 1.7047724723815918, + "learning_rate": 4.39983283926564e-06, + "loss": 0.2195, + "step": 326 + }, + { + "epoch": 0.693347468857673, + "grad_norm": 3.3912291526794434, + "learning_rate": 4.3961893781399186e-06, + "loss": 0.2696, + "step": 327 + }, + { + "epoch": 0.6954677975086139, + "grad_norm": 1.9746174812316895, + "learning_rate": 4.392536409523015e-06, + "loss": 0.3592, + "step": 328 + }, + { + "epoch": 0.6975881261595547, + "grad_norm": 5.287510395050049, + "learning_rate": 4.388873951730909e-06, + "loss": 0.2301, + "step": 329 + }, + { + "epoch": 0.6997084548104956, + "grad_norm": 3.351943254470825, + "learning_rate": 4.385202023127158e-06, + "loss": 0.2445, + "step": 330 + }, + { + "epoch": 0.7018287834614365, + "grad_norm": 1.951226830482483, + "learning_rate": 4.381520642122808e-06, + "loss": 0.283, + "step": 331 + }, + { + "epoch": 0.7039491121123774, + "grad_norm": 2.763387441635132, + "learning_rate": 4.3778298271762995e-06, + "loss": 0.423, + "step": 332 + }, + { + "epoch": 0.7060694407633183, + "grad_norm": 5.014280796051025, + "learning_rate": 4.374129596793375e-06, + "loss": 0.3269, + "step": 333 + }, + { + "epoch": 0.7081897694142593, + "grad_norm": 1.114488124847412, + "learning_rate": 4.370419969526982e-06, + "loss": 0.2774, + "step": 334 + }, + { + "epoch": 0.7103100980652001, + "grad_norm": 2.432865619659424, + "learning_rate": 4.366700963977188e-06, + "loss": 0.2744, + "step": 335 + }, + { + "epoch": 0.712430426716141, + "grad_norm": 1.1525187492370605, + "learning_rate": 4.362972598791085e-06, + "loss": 0.3201, + "step": 336 + }, + { + "epoch": 0.7145507553670819, + "grad_norm": 2.6614933013916016, + "learning_rate": 4.3592348926626886e-06, + "loss": 0.1742, + "step": 337 + }, + { + "epoch": 0.7166710840180228, + "grad_norm": 3.2576396465301514, + "learning_rate": 4.355487864332853e-06, + "loss": 0.3311, + "step": 338 + }, + { + "epoch": 0.7187914126689637, + "grad_norm": 2.1801483631134033, + "learning_rate": 4.351731532589173e-06, + "loss": 0.2022, + "step": 339 + }, + { + "epoch": 0.7209117413199045, + "grad_norm": 2.8371381759643555, + "learning_rate": 4.347965916265893e-06, + "loss": 0.3076, + "step": 340 + }, + { + "epoch": 0.7230320699708455, + "grad_norm": 2.4353699684143066, + "learning_rate": 4.3441910342438076e-06, + "loss": 0.2187, + "step": 341 + }, + { + "epoch": 0.7251523986217864, + "grad_norm": 0.7535296678543091, + "learning_rate": 4.340406905450171e-06, + "loss": 0.282, + "step": 342 + }, + { + "epoch": 0.7272727272727273, + "grad_norm": 1.656532883644104, + "learning_rate": 4.3366135488586e-06, + "loss": 0.2898, + "step": 343 + }, + { + "epoch": 0.7293930559236682, + "grad_norm": 1.5099116563796997, + "learning_rate": 4.332810983488979e-06, + "loss": 0.2422, + "step": 344 + }, + { + "epoch": 0.731513384574609, + "grad_norm": 1.4573249816894531, + "learning_rate": 4.3289992284073675e-06, + "loss": 0.2781, + "step": 345 + }, + { + "epoch": 0.7336337132255499, + "grad_norm": 1.6948301792144775, + "learning_rate": 4.325178302725901e-06, + "loss": 0.1749, + "step": 346 + }, + { + "epoch": 0.7357540418764908, + "grad_norm": 2.298999547958374, + "learning_rate": 4.321348225602694e-06, + "loss": 0.287, + "step": 347 + }, + { + "epoch": 0.7378743705274318, + "grad_norm": 1.248860239982605, + "learning_rate": 4.31750901624175e-06, + "loss": 0.2698, + "step": 348 + }, + { + "epoch": 0.7399946991783727, + "grad_norm": 1.6918904781341553, + "learning_rate": 4.31366069389286e-06, + "loss": 0.2312, + "step": 349 + }, + { + "epoch": 0.7421150278293135, + "grad_norm": 3.1004738807678223, + "learning_rate": 4.309803277851507e-06, + "loss": 0.2886, + "step": 350 + }, + { + "epoch": 0.7442353564802544, + "grad_norm": 2.718191623687744, + "learning_rate": 4.305936787458769e-06, + "loss": 0.2501, + "step": 351 + }, + { + "epoch": 0.7463556851311953, + "grad_norm": 1.4747895002365112, + "learning_rate": 4.302061242101226e-06, + "loss": 0.1851, + "step": 352 + }, + { + "epoch": 0.7484760137821362, + "grad_norm": 1.5939568281173706, + "learning_rate": 4.2981766612108576e-06, + "loss": 0.2419, + "step": 353 + }, + { + "epoch": 0.7505963424330772, + "grad_norm": 1.2325273752212524, + "learning_rate": 4.294283064264947e-06, + "loss": 0.2165, + "step": 354 + }, + { + "epoch": 0.7527166710840181, + "grad_norm": 5.181772232055664, + "learning_rate": 4.290380470785984e-06, + "loss": 0.2562, + "step": 355 + }, + { + "epoch": 0.7548369997349589, + "grad_norm": 1.3235808610916138, + "learning_rate": 4.2864689003415675e-06, + "loss": 0.318, + "step": 356 + }, + { + "epoch": 0.7569573283858998, + "grad_norm": 2.194802761077881, + "learning_rate": 4.282548372544307e-06, + "loss": 0.2193, + "step": 357 + }, + { + "epoch": 0.7590776570368407, + "grad_norm": 2.330679178237915, + "learning_rate": 4.278618907051724e-06, + "loss": 0.2466, + "step": 358 + }, + { + "epoch": 0.7611979856877816, + "grad_norm": 2.1647789478302, + "learning_rate": 4.274680523566154e-06, + "loss": 0.2749, + "step": 359 + }, + { + "epoch": 0.7633183143387225, + "grad_norm": 1.5459215641021729, + "learning_rate": 4.270733241834647e-06, + "loss": 0.3133, + "step": 360 + }, + { + "epoch": 0.7654386429896634, + "grad_norm": 0.6741765141487122, + "learning_rate": 4.266777081648868e-06, + "loss": 0.3188, + "step": 361 + }, + { + "epoch": 0.7675589716406043, + "grad_norm": 2.7495875358581543, + "learning_rate": 4.262812062844999e-06, + "loss": 0.3409, + "step": 362 + }, + { + "epoch": 0.7696793002915452, + "grad_norm": 4.160212993621826, + "learning_rate": 4.25883820530364e-06, + "loss": 0.2538, + "step": 363 + }, + { + "epoch": 0.7717996289424861, + "grad_norm": 2.0317301750183105, + "learning_rate": 4.254855528949709e-06, + "loss": 0.2741, + "step": 364 + }, + { + "epoch": 0.773919957593427, + "grad_norm": 2.1977953910827637, + "learning_rate": 4.250864053752337e-06, + "loss": 0.2353, + "step": 365 + }, + { + "epoch": 0.7760402862443678, + "grad_norm": 3.028444290161133, + "learning_rate": 4.2468637997247794e-06, + "loss": 0.2585, + "step": 366 + }, + { + "epoch": 0.7781606148953087, + "grad_norm": 1.4199281930923462, + "learning_rate": 4.242854786924302e-06, + "loss": 0.2143, + "step": 367 + }, + { + "epoch": 0.7802809435462497, + "grad_norm": 1.7088114023208618, + "learning_rate": 4.238837035452092e-06, + "loss": 0.1835, + "step": 368 + }, + { + "epoch": 0.7824012721971906, + "grad_norm": 1.4326963424682617, + "learning_rate": 4.234810565453148e-06, + "loss": 0.2107, + "step": 369 + }, + { + "epoch": 0.7845216008481315, + "grad_norm": 1.337410569190979, + "learning_rate": 4.230775397116188e-06, + "loss": 0.2497, + "step": 370 + }, + { + "epoch": 0.7866419294990723, + "grad_norm": 1.4517322778701782, + "learning_rate": 4.2267315506735394e-06, + "loss": 0.2577, + "step": 371 + }, + { + "epoch": 0.7887622581500132, + "grad_norm": 0.9060394167900085, + "learning_rate": 4.2226790464010445e-06, + "loss": 0.1978, + "step": 372 + }, + { + "epoch": 0.7908825868009541, + "grad_norm": 2.3969204425811768, + "learning_rate": 4.218617904617953e-06, + "loss": 0.2462, + "step": 373 + }, + { + "epoch": 0.793002915451895, + "grad_norm": 2.8702633380889893, + "learning_rate": 4.2145481456868265e-06, + "loss": 0.274, + "step": 374 + }, + { + "epoch": 0.795123244102836, + "grad_norm": 1.4537705183029175, + "learning_rate": 4.210469790013431e-06, + "loss": 0.3099, + "step": 375 + }, + { + "epoch": 0.7972435727537769, + "grad_norm": 2.5505456924438477, + "learning_rate": 4.206382858046636e-06, + "loss": 0.4174, + "step": 376 + }, + { + "epoch": 0.7993639014047177, + "grad_norm": 0.903439462184906, + "learning_rate": 4.202287370278313e-06, + "loss": 0.2273, + "step": 377 + }, + { + "epoch": 0.8014842300556586, + "grad_norm": 2.118838310241699, + "learning_rate": 4.198183347243233e-06, + "loss": 0.1472, + "step": 378 + }, + { + "epoch": 0.8036045587065995, + "grad_norm": 1.7555965185165405, + "learning_rate": 4.194070809518963e-06, + "loss": 0.3014, + "step": 379 + }, + { + "epoch": 0.8057248873575404, + "grad_norm": 1.575334072113037, + "learning_rate": 4.1899497777257615e-06, + "loss": 0.2107, + "step": 380 + }, + { + "epoch": 0.8078452160084814, + "grad_norm": 1.020128607749939, + "learning_rate": 4.185820272526477e-06, + "loss": 0.2336, + "step": 381 + }, + { + "epoch": 0.8099655446594222, + "grad_norm": 2.3840348720550537, + "learning_rate": 4.181682314626443e-06, + "loss": 0.3076, + "step": 382 + }, + { + "epoch": 0.8120858733103631, + "grad_norm": 0.7766013741493225, + "learning_rate": 4.177535924773375e-06, + "loss": 0.2436, + "step": 383 + }, + { + "epoch": 0.814206201961304, + "grad_norm": 2.136934757232666, + "learning_rate": 4.173381123757268e-06, + "loss": 0.3278, + "step": 384 + }, + { + "epoch": 0.8163265306122449, + "grad_norm": 2.10295033454895, + "learning_rate": 4.169217932410288e-06, + "loss": 0.3002, + "step": 385 + }, + { + "epoch": 0.8184468592631858, + "grad_norm": 2.8707754611968994, + "learning_rate": 4.165046371606671e-06, + "loss": 0.2263, + "step": 386 + }, + { + "epoch": 0.8205671879141266, + "grad_norm": 2.254936933517456, + "learning_rate": 4.160866462262618e-06, + "loss": 0.2967, + "step": 387 + }, + { + "epoch": 0.8226875165650676, + "grad_norm": 1.71103036403656, + "learning_rate": 4.15667822533619e-06, + "loss": 0.2266, + "step": 388 + }, + { + "epoch": 0.8248078452160085, + "grad_norm": 3.3162853717803955, + "learning_rate": 4.152481681827201e-06, + "loss": 0.3302, + "step": 389 + }, + { + "epoch": 0.8269281738669494, + "grad_norm": 2.03659987449646, + "learning_rate": 4.1482768527771155e-06, + "loss": 0.2646, + "step": 390 + }, + { + "epoch": 0.8290485025178903, + "grad_norm": 3.0324466228485107, + "learning_rate": 4.14406375926894e-06, + "loss": 0.3638, + "step": 391 + }, + { + "epoch": 0.8311688311688312, + "grad_norm": 1.9642225503921509, + "learning_rate": 4.13984242242712e-06, + "loss": 0.1704, + "step": 392 + }, + { + "epoch": 0.833289159819772, + "grad_norm": 1.727362036705017, + "learning_rate": 4.135612863417435e-06, + "loss": 0.2594, + "step": 393 + }, + { + "epoch": 0.835409488470713, + "grad_norm": 1.6325123310089111, + "learning_rate": 4.131375103446889e-06, + "loss": 0.2068, + "step": 394 + }, + { + "epoch": 0.8375298171216539, + "grad_norm": 1.1266484260559082, + "learning_rate": 4.127129163763601e-06, + "loss": 0.1623, + "step": 395 + }, + { + "epoch": 0.8396501457725948, + "grad_norm": 0.7224255800247192, + "learning_rate": 4.122875065656712e-06, + "loss": 0.1622, + "step": 396 + }, + { + "epoch": 0.8417704744235357, + "grad_norm": 2.530782699584961, + "learning_rate": 4.118612830456262e-06, + "loss": 0.3365, + "step": 397 + }, + { + "epoch": 0.8438908030744765, + "grad_norm": 2.0396225452423096, + "learning_rate": 4.114342479533094e-06, + "loss": 0.2857, + "step": 398 + }, + { + "epoch": 0.8460111317254174, + "grad_norm": 1.927078127861023, + "learning_rate": 4.110064034298741e-06, + "loss": 0.2944, + "step": 399 + }, + { + "epoch": 0.8481314603763583, + "grad_norm": 3.6908702850341797, + "learning_rate": 4.105777516205324e-06, + "loss": 0.2156, + "step": 400 + }, + { + "epoch": 0.8502517890272993, + "grad_norm": 0.6398283243179321, + "learning_rate": 4.101482946745438e-06, + "loss": 0.2235, + "step": 401 + }, + { + "epoch": 0.8523721176782402, + "grad_norm": 1.541572093963623, + "learning_rate": 4.09718034745205e-06, + "loss": 0.1273, + "step": 402 + }, + { + "epoch": 0.854492446329181, + "grad_norm": 3.8959381580352783, + "learning_rate": 4.092869739898386e-06, + "loss": 0.3338, + "step": 403 + }, + { + "epoch": 0.8566127749801219, + "grad_norm": 1.9765669107437134, + "learning_rate": 4.0885511456978275e-06, + "loss": 0.2359, + "step": 404 + }, + { + "epoch": 0.8587331036310628, + "grad_norm": 2.276289939880371, + "learning_rate": 4.084224586503801e-06, + "loss": 0.2267, + "step": 405 + }, + { + "epoch": 0.8608534322820037, + "grad_norm": 0.6204816102981567, + "learning_rate": 4.0798900840096694e-06, + "loss": 0.1329, + "step": 406 + }, + { + "epoch": 0.8629737609329446, + "grad_norm": 1.452314853668213, + "learning_rate": 4.075547659948621e-06, + "loss": 0.2221, + "step": 407 + }, + { + "epoch": 0.8650940895838855, + "grad_norm": 1.0840950012207031, + "learning_rate": 4.071197336093566e-06, + "loss": 0.3571, + "step": 408 + }, + { + "epoch": 0.8672144182348264, + "grad_norm": 3.603943347930908, + "learning_rate": 4.0668391342570225e-06, + "loss": 0.247, + "step": 409 + }, + { + "epoch": 0.8693347468857673, + "grad_norm": 1.4998263120651245, + "learning_rate": 4.062473076291009e-06, + "loss": 0.2483, + "step": 410 + }, + { + "epoch": 0.8714550755367082, + "grad_norm": 1.4034696817398071, + "learning_rate": 4.058099184086934e-06, + "loss": 0.2748, + "step": 411 + }, + { + "epoch": 0.8735754041876491, + "grad_norm": 1.1534749269485474, + "learning_rate": 4.05371747957549e-06, + "loss": 0.1534, + "step": 412 + }, + { + "epoch": 0.87569573283859, + "grad_norm": 1.709837555885315, + "learning_rate": 4.049327984726535e-06, + "loss": 0.3573, + "step": 413 + }, + { + "epoch": 0.8778160614895308, + "grad_norm": 1.9228962659835815, + "learning_rate": 4.044930721548992e-06, + "loss": 0.3242, + "step": 414 + }, + { + "epoch": 0.8799363901404718, + "grad_norm": 2.2846219539642334, + "learning_rate": 4.040525712090733e-06, + "loss": 0.2101, + "step": 415 + }, + { + "epoch": 0.8820567187914127, + "grad_norm": 2.0104122161865234, + "learning_rate": 4.0361129784384705e-06, + "loss": 0.2115, + "step": 416 + }, + { + "epoch": 0.8841770474423536, + "grad_norm": 2.7587649822235107, + "learning_rate": 4.031692542717645e-06, + "loss": 0.274, + "step": 417 + }, + { + "epoch": 0.8862973760932945, + "grad_norm": 4.8226542472839355, + "learning_rate": 4.027264427092316e-06, + "loss": 0.4542, + "step": 418 + }, + { + "epoch": 0.8884177047442353, + "grad_norm": 2.651845693588257, + "learning_rate": 4.022828653765049e-06, + "loss": 0.2008, + "step": 419 + }, + { + "epoch": 0.8905380333951762, + "grad_norm": 1.5795021057128906, + "learning_rate": 4.018385244976807e-06, + "loss": 0.2777, + "step": 420 + }, + { + "epoch": 0.8926583620461171, + "grad_norm": 1.470374584197998, + "learning_rate": 4.0139342230068355e-06, + "loss": 0.2378, + "step": 421 + }, + { + "epoch": 0.8947786906970581, + "grad_norm": 2.2073006629943848, + "learning_rate": 4.009475610172553e-06, + "loss": 0.2469, + "step": 422 + }, + { + "epoch": 0.896899019347999, + "grad_norm": 3.0384535789489746, + "learning_rate": 4.005009428829439e-06, + "loss": 0.2247, + "step": 423 + }, + { + "epoch": 0.8990193479989398, + "grad_norm": 1.5634294748306274, + "learning_rate": 4.0005357013709215e-06, + "loss": 0.2117, + "step": 424 + }, + { + "epoch": 0.9011396766498807, + "grad_norm": 0.9764052033424377, + "learning_rate": 3.996054450228263e-06, + "loss": 0.2591, + "step": 425 + }, + { + "epoch": 0.9032600053008216, + "grad_norm": 1.669441819190979, + "learning_rate": 3.991565697870453e-06, + "loss": 0.2905, + "step": 426 + }, + { + "epoch": 0.9053803339517625, + "grad_norm": 2.682272434234619, + "learning_rate": 3.987069466804089e-06, + "loss": 0.298, + "step": 427 + }, + { + "epoch": 0.9075006626027035, + "grad_norm": 0.5667883157730103, + "learning_rate": 3.982565779573269e-06, + "loss": 0.4034, + "step": 428 + }, + { + "epoch": 0.9096209912536443, + "grad_norm": 2.6494028568267822, + "learning_rate": 3.978054658759474e-06, + "loss": 0.2176, + "step": 429 + }, + { + "epoch": 0.9117413199045852, + "grad_norm": 1.3368819952011108, + "learning_rate": 3.973536126981459e-06, + "loss": 0.2228, + "step": 430 + }, + { + "epoch": 0.9138616485555261, + "grad_norm": 2.0899736881256104, + "learning_rate": 3.969010206895136e-06, + "loss": 0.2471, + "step": 431 + }, + { + "epoch": 0.915981977206467, + "grad_norm": 0.29745158553123474, + "learning_rate": 3.964476921193464e-06, + "loss": 0.1858, + "step": 432 + }, + { + "epoch": 0.9181023058574079, + "grad_norm": 2.4237589836120605, + "learning_rate": 3.9599362926063315e-06, + "loss": 0.2178, + "step": 433 + }, + { + "epoch": 0.9202226345083488, + "grad_norm": 2.9499125480651855, + "learning_rate": 3.955388343900443e-06, + "loss": 0.2695, + "step": 434 + }, + { + "epoch": 0.9223429631592897, + "grad_norm": 1.6062681674957275, + "learning_rate": 3.950833097879208e-06, + "loss": 0.2193, + "step": 435 + }, + { + "epoch": 0.9244632918102306, + "grad_norm": 3.3054378032684326, + "learning_rate": 3.946270577382626e-06, + "loss": 0.2479, + "step": 436 + }, + { + "epoch": 0.9265836204611715, + "grad_norm": 1.836806058883667, + "learning_rate": 3.941700805287169e-06, + "loss": 0.3304, + "step": 437 + }, + { + "epoch": 0.9287039491121124, + "grad_norm": 2.154625654220581, + "learning_rate": 3.937123804505666e-06, + "loss": 0.2871, + "step": 438 + }, + { + "epoch": 0.9308242777630533, + "grad_norm": 1.1884167194366455, + "learning_rate": 3.932539597987196e-06, + "loss": 0.2042, + "step": 439 + }, + { + "epoch": 0.9329446064139941, + "grad_norm": 1.345928430557251, + "learning_rate": 3.927948208716964e-06, + "loss": 0.25, + "step": 440 + }, + { + "epoch": 0.935064935064935, + "grad_norm": 1.952118992805481, + "learning_rate": 3.92334965971619e-06, + "loss": 0.2686, + "step": 441 + }, + { + "epoch": 0.937185263715876, + "grad_norm": 2.034341335296631, + "learning_rate": 3.918743974041992e-06, + "loss": 0.2693, + "step": 442 + }, + { + "epoch": 0.9393055923668169, + "grad_norm": 1.5500835180282593, + "learning_rate": 3.914131174787274e-06, + "loss": 0.2578, + "step": 443 + }, + { + "epoch": 0.9414259210177578, + "grad_norm": 1.8623617887496948, + "learning_rate": 3.909511285080605e-06, + "loss": 0.278, + "step": 444 + }, + { + "epoch": 0.9435462496686986, + "grad_norm": 3.387428045272827, + "learning_rate": 3.9048843280861055e-06, + "loss": 0.2269, + "step": 445 + }, + { + "epoch": 0.9456665783196395, + "grad_norm": 3.092822551727295, + "learning_rate": 3.900250327003333e-06, + "loss": 0.2526, + "step": 446 + }, + { + "epoch": 0.9477869069705804, + "grad_norm": 2.328296422958374, + "learning_rate": 3.895609305067162e-06, + "loss": 0.2397, + "step": 447 + }, + { + "epoch": 0.9499072356215214, + "grad_norm": 1.579817533493042, + "learning_rate": 3.890961285547672e-06, + "loss": 0.2516, + "step": 448 + }, + { + "epoch": 0.9520275642724623, + "grad_norm": 1.765915870666504, + "learning_rate": 3.886306291750028e-06, + "loss": 0.2889, + "step": 449 + }, + { + "epoch": 0.9541478929234031, + "grad_norm": 2.5610663890838623, + "learning_rate": 3.881644347014361e-06, + "loss": 0.3136, + "step": 450 + }, + { + "epoch": 0.956268221574344, + "grad_norm": 1.9422125816345215, + "learning_rate": 3.876975474715656e-06, + "loss": 0.2424, + "step": 451 + }, + { + "epoch": 0.9583885502252849, + "grad_norm": 2.0714170932769775, + "learning_rate": 3.872299698263634e-06, + "loss": 0.2841, + "step": 452 + }, + { + "epoch": 0.9605088788762258, + "grad_norm": 1.0616906881332397, + "learning_rate": 3.867617041102633e-06, + "loss": 0.2141, + "step": 453 + }, + { + "epoch": 0.9626292075271667, + "grad_norm": 1.4508030414581299, + "learning_rate": 3.862927526711488e-06, + "loss": 0.2419, + "step": 454 + }, + { + "epoch": 0.9647495361781077, + "grad_norm": 1.6528363227844238, + "learning_rate": 3.858231178603421e-06, + "loss": 0.2179, + "step": 455 + }, + { + "epoch": 0.9668698648290485, + "grad_norm": 2.853685140609741, + "learning_rate": 3.853528020325913e-06, + "loss": 0.2963, + "step": 456 + }, + { + "epoch": 0.9689901934799894, + "grad_norm": 1.16892671585083, + "learning_rate": 3.848818075460595e-06, + "loss": 0.2386, + "step": 457 + }, + { + "epoch": 0.9711105221309303, + "grad_norm": 1.986411452293396, + "learning_rate": 3.8441013676231255e-06, + "loss": 0.1932, + "step": 458 + }, + { + "epoch": 0.9732308507818712, + "grad_norm": 1.9140475988388062, + "learning_rate": 3.83937792046307e-06, + "loss": 0.2455, + "step": 459 + }, + { + "epoch": 0.9753511794328121, + "grad_norm": 1.5750322341918945, + "learning_rate": 3.834647757663788e-06, + "loss": 0.2605, + "step": 460 + }, + { + "epoch": 0.9774715080837529, + "grad_norm": 1.1858994960784912, + "learning_rate": 3.829910902942309e-06, + "loss": 0.26, + "step": 461 + }, + { + "epoch": 0.9795918367346939, + "grad_norm": 3.8463196754455566, + "learning_rate": 3.825167380049218e-06, + "loss": 0.2549, + "step": 462 + }, + { + "epoch": 0.9817121653856348, + "grad_norm": 2.046649217605591, + "learning_rate": 3.820417212768531e-06, + "loss": 0.1391, + "step": 463 + }, + { + "epoch": 0.9838324940365757, + "grad_norm": 1.923967957496643, + "learning_rate": 3.8156604249175825e-06, + "loss": 0.305, + "step": 464 + }, + { + "epoch": 0.9859528226875166, + "grad_norm": 3.389587879180908, + "learning_rate": 3.810897040346899e-06, + "loss": 0.3457, + "step": 465 + }, + { + "epoch": 0.9880731513384574, + "grad_norm": 1.8285034894943237, + "learning_rate": 3.8061270829400876e-06, + "loss": 0.2261, + "step": 466 + }, + { + "epoch": 0.9901934799893983, + "grad_norm": 2.468703031539917, + "learning_rate": 3.801350576613706e-06, + "loss": 0.2855, + "step": 467 + }, + { + "epoch": 0.9923138086403392, + "grad_norm": 2.497868776321411, + "learning_rate": 3.796567545317153e-06, + "loss": 0.1904, + "step": 468 + }, + { + "epoch": 0.9944341372912802, + "grad_norm": 1.1878782510757446, + "learning_rate": 3.79177801303254e-06, + "loss": 0.2144, + "step": 469 + }, + { + "epoch": 0.9965544659422211, + "grad_norm": 1.0926648378372192, + "learning_rate": 3.7869820037745773e-06, + "loss": 0.1962, + "step": 470 + }, + { + "epoch": 0.9986747945931619, + "grad_norm": 1.597976803779602, + "learning_rate": 3.7821795415904482e-06, + "loss": 0.2887, + "step": 471 + }, + { + "epoch": 1.0015902464882056, + "grad_norm": 1.37874174118042, + "learning_rate": 3.777370650559693e-06, + "loss": 0.2933, + "step": 472 + }, + { + "epoch": 1.0037105751391466, + "grad_norm": 1.9284913539886475, + "learning_rate": 3.772555354794085e-06, + "loss": 0.2159, + "step": 473 + }, + { + "epoch": 1.0058309037900874, + "grad_norm": 3.890476942062378, + "learning_rate": 3.7677336784375107e-06, + "loss": 0.3206, + "step": 474 + }, + { + "epoch": 1.0079512324410285, + "grad_norm": 2.379439353942871, + "learning_rate": 3.76290564566585e-06, + "loss": 0.2397, + "step": 475 + }, + { + "epoch": 1.0100715610919693, + "grad_norm": 1.771033525466919, + "learning_rate": 3.7580712806868536e-06, + "loss": 0.2207, + "step": 476 + }, + { + "epoch": 1.01219188974291, + "grad_norm": 1.5666189193725586, + "learning_rate": 3.7532306077400206e-06, + "loss": 0.2817, + "step": 477 + }, + { + "epoch": 1.014312218393851, + "grad_norm": 0.6713786125183105, + "learning_rate": 3.7483836510964792e-06, + "loss": 0.2123, + "step": 478 + }, + { + "epoch": 1.016432547044792, + "grad_norm": 1.3699878454208374, + "learning_rate": 3.7435304350588643e-06, + "loss": 0.2889, + "step": 479 + }, + { + "epoch": 1.018552875695733, + "grad_norm": 1.747329592704773, + "learning_rate": 3.738670983961195e-06, + "loss": 0.2517, + "step": 480 + }, + { + "epoch": 1.0206732043466737, + "grad_norm": 2.277524471282959, + "learning_rate": 3.7338053221687533e-06, + "loss": 0.2451, + "step": 481 + }, + { + "epoch": 1.0227935329976146, + "grad_norm": 2.4319913387298584, + "learning_rate": 3.728933474077961e-06, + "loss": 0.2594, + "step": 482 + }, + { + "epoch": 1.0249138616485556, + "grad_norm": 1.2065045833587646, + "learning_rate": 3.7240554641162585e-06, + "loss": 0.2706, + "step": 483 + }, + { + "epoch": 1.0270341902994964, + "grad_norm": 1.6133732795715332, + "learning_rate": 3.7191713167419814e-06, + "loss": 0.2099, + "step": 484 + }, + { + "epoch": 1.0291545189504374, + "grad_norm": 2.497514486312866, + "learning_rate": 3.7142810564442388e-06, + "loss": 0.3406, + "step": 485 + }, + { + "epoch": 1.0312748476013782, + "grad_norm": 2.1485133171081543, + "learning_rate": 3.7093847077427904e-06, + "loss": 0.2251, + "step": 486 + }, + { + "epoch": 1.033395176252319, + "grad_norm": 2.118579149246216, + "learning_rate": 3.7044822951879224e-06, + "loss": 0.1466, + "step": 487 + }, + { + "epoch": 1.03551550490326, + "grad_norm": 1.457202672958374, + "learning_rate": 3.6995738433603234e-06, + "loss": 0.3749, + "step": 488 + }, + { + "epoch": 1.0376358335542009, + "grad_norm": 1.4717838764190674, + "learning_rate": 3.6946593768709667e-06, + "loss": 0.2145, + "step": 489 + }, + { + "epoch": 1.0397561622051419, + "grad_norm": 1.1702837944030762, + "learning_rate": 3.68973892036098e-06, + "loss": 0.1499, + "step": 490 + }, + { + "epoch": 1.0418764908560827, + "grad_norm": 1.9794777631759644, + "learning_rate": 3.684812498501528e-06, + "loss": 0.2445, + "step": 491 + }, + { + "epoch": 1.0439968195070235, + "grad_norm": 5.563566207885742, + "learning_rate": 3.6798801359936808e-06, + "loss": 0.2568, + "step": 492 + }, + { + "epoch": 1.0461171481579645, + "grad_norm": 1.5425770282745361, + "learning_rate": 3.6749418575683005e-06, + "loss": 0.1574, + "step": 493 + }, + { + "epoch": 1.0482374768089053, + "grad_norm": 2.789044141769409, + "learning_rate": 3.669997687985908e-06, + "loss": 0.2175, + "step": 494 + }, + { + "epoch": 1.0503578054598464, + "grad_norm": 2.0900280475616455, + "learning_rate": 3.665047652036563e-06, + "loss": 0.2276, + "step": 495 + }, + { + "epoch": 1.0524781341107872, + "grad_norm": 1.0383256673812866, + "learning_rate": 3.6600917745397403e-06, + "loss": 0.1829, + "step": 496 + }, + { + "epoch": 1.054598462761728, + "grad_norm": 1.5721336603164673, + "learning_rate": 3.6551300803442035e-06, + "loss": 0.1972, + "step": 497 + }, + { + "epoch": 1.056718791412669, + "grad_norm": 0.5374338030815125, + "learning_rate": 3.650162594327881e-06, + "loss": 0.1839, + "step": 498 + }, + { + "epoch": 1.0588391200636098, + "grad_norm": 2.335890054702759, + "learning_rate": 3.6451893413977413e-06, + "loss": 0.2619, + "step": 499 + }, + { + "epoch": 1.0609594487145508, + "grad_norm": 2.4904046058654785, + "learning_rate": 3.6402103464896676e-06, + "loss": 0.2554, + "step": 500 + }, + { + "epoch": 1.0630797773654916, + "grad_norm": 2.201873540878296, + "learning_rate": 3.6352256345683358e-06, + "loss": 0.2435, + "step": 501 + }, + { + "epoch": 1.0652001060164324, + "grad_norm": 1.2125855684280396, + "learning_rate": 3.630235230627085e-06, + "loss": 0.2017, + "step": 502 + }, + { + "epoch": 1.0673204346673735, + "grad_norm": 1.4849168062210083, + "learning_rate": 3.6252391596877923e-06, + "loss": 0.2504, + "step": 503 + }, + { + "epoch": 1.0694407633183143, + "grad_norm": 1.445149302482605, + "learning_rate": 3.620237446800754e-06, + "loss": 0.2066, + "step": 504 + }, + { + "epoch": 1.0715610919692553, + "grad_norm": 2.7715039253234863, + "learning_rate": 3.615230117044551e-06, + "loss": 0.3272, + "step": 505 + }, + { + "epoch": 1.0736814206201961, + "grad_norm": 1.57020902633667, + "learning_rate": 3.610217195525928e-06, + "loss": 0.1846, + "step": 506 + }, + { + "epoch": 1.075801749271137, + "grad_norm": 1.8669289350509644, + "learning_rate": 3.6051987073796684e-06, + "loss": 0.1817, + "step": 507 + }, + { + "epoch": 1.077922077922078, + "grad_norm": 1.7587169408798218, + "learning_rate": 3.600174677768465e-06, + "loss": 0.1909, + "step": 508 + }, + { + "epoch": 1.0800424065730188, + "grad_norm": 2.2706751823425293, + "learning_rate": 3.595145131882795e-06, + "loss": 0.2923, + "step": 509 + }, + { + "epoch": 1.0821627352239598, + "grad_norm": 1.3291329145431519, + "learning_rate": 3.5901100949407967e-06, + "loss": 0.1405, + "step": 510 + }, + { + "epoch": 1.0842830638749006, + "grad_norm": 1.3454506397247314, + "learning_rate": 3.5850695921881383e-06, + "loss": 0.1853, + "step": 511 + }, + { + "epoch": 1.0864033925258414, + "grad_norm": 1.4152384996414185, + "learning_rate": 3.5800236488978946e-06, + "loss": 0.1181, + "step": 512 + }, + { + "epoch": 1.0885237211767824, + "grad_norm": 3.2865519523620605, + "learning_rate": 3.574972290370419e-06, + "loss": 0.2086, + "step": 513 + }, + { + "epoch": 1.0906440498277232, + "grad_norm": 1.90707528591156, + "learning_rate": 3.569915541933217e-06, + "loss": 0.202, + "step": 514 + }, + { + "epoch": 1.0927643784786643, + "grad_norm": 1.0512449741363525, + "learning_rate": 3.564853428940819e-06, + "loss": 0.1522, + "step": 515 + }, + { + "epoch": 1.094884707129605, + "grad_norm": 1.8712276220321655, + "learning_rate": 3.5597859767746524e-06, + "loss": 0.1442, + "step": 516 + }, + { + "epoch": 1.0970050357805459, + "grad_norm": 0.539580225944519, + "learning_rate": 3.5547132108429163e-06, + "loss": 0.2109, + "step": 517 + }, + { + "epoch": 1.099125364431487, + "grad_norm": 0.8322845101356506, + "learning_rate": 3.5496351565804542e-06, + "loss": 0.2269, + "step": 518 + }, + { + "epoch": 1.1012456930824277, + "grad_norm": 3.7564239501953125, + "learning_rate": 3.5445518394486215e-06, + "loss": 0.2547, + "step": 519 + }, + { + "epoch": 1.1033660217333687, + "grad_norm": 1.5247739553451538, + "learning_rate": 3.5394632849351663e-06, + "loss": 0.1796, + "step": 520 + }, + { + "epoch": 1.1054863503843095, + "grad_norm": 2.528141498565674, + "learning_rate": 3.5343695185540927e-06, + "loss": 0.1957, + "step": 521 + }, + { + "epoch": 1.1076066790352506, + "grad_norm": 1.748477578163147, + "learning_rate": 3.5292705658455406e-06, + "loss": 0.2102, + "step": 522 + }, + { + "epoch": 1.1097270076861914, + "grad_norm": 2.315608024597168, + "learning_rate": 3.524166452375652e-06, + "loss": 0.1964, + "step": 523 + }, + { + "epoch": 1.1118473363371322, + "grad_norm": 3.3954997062683105, + "learning_rate": 3.5190572037364445e-06, + "loss": 0.2761, + "step": 524 + }, + { + "epoch": 1.1139676649880732, + "grad_norm": 2.1260130405426025, + "learning_rate": 3.513942845545686e-06, + "loss": 0.1444, + "step": 525 + }, + { + "epoch": 1.116087993639014, + "grad_norm": 3.0516886711120605, + "learning_rate": 3.5088234034467604e-06, + "loss": 0.2643, + "step": 526 + }, + { + "epoch": 1.118208322289955, + "grad_norm": 1.948144555091858, + "learning_rate": 3.5036989031085455e-06, + "loss": 0.1631, + "step": 527 + }, + { + "epoch": 1.1203286509408958, + "grad_norm": 3.5732581615448, + "learning_rate": 3.498569370225279e-06, + "loss": 0.2681, + "step": 528 + }, + { + "epoch": 1.1224489795918366, + "grad_norm": 2.172426462173462, + "learning_rate": 3.4934348305164324e-06, + "loss": 0.2678, + "step": 529 + }, + { + "epoch": 1.1245693082427777, + "grad_norm": 1.3486807346343994, + "learning_rate": 3.4882953097265814e-06, + "loss": 0.207, + "step": 530 + }, + { + "epoch": 1.1266896368937185, + "grad_norm": 0.8123583793640137, + "learning_rate": 3.4831508336252766e-06, + "loss": 0.205, + "step": 531 + }, + { + "epoch": 1.1288099655446595, + "grad_norm": 1.3351538181304932, + "learning_rate": 3.4780014280069153e-06, + "loss": 0.1029, + "step": 532 + }, + { + "epoch": 1.1309302941956003, + "grad_norm": 1.3779995441436768, + "learning_rate": 3.472847118690611e-06, + "loss": 0.2622, + "step": 533 + }, + { + "epoch": 1.1330506228465411, + "grad_norm": 1.0775947570800781, + "learning_rate": 3.467687931520064e-06, + "loss": 0.1952, + "step": 534 + }, + { + "epoch": 1.1351709514974822, + "grad_norm": 2.4154770374298096, + "learning_rate": 3.462523892363432e-06, + "loss": 0.1626, + "step": 535 + }, + { + "epoch": 1.137291280148423, + "grad_norm": 2.120819091796875, + "learning_rate": 3.4573550271132e-06, + "loss": 0.2611, + "step": 536 + }, + { + "epoch": 1.139411608799364, + "grad_norm": 1.0421452522277832, + "learning_rate": 3.4521813616860545e-06, + "loss": 0.1755, + "step": 537 + }, + { + "epoch": 1.1415319374503048, + "grad_norm": 2.1693243980407715, + "learning_rate": 3.4470029220227445e-06, + "loss": 0.299, + "step": 538 + }, + { + "epoch": 1.1436522661012458, + "grad_norm": 1.831677794456482, + "learning_rate": 3.441819734087963e-06, + "loss": 0.1295, + "step": 539 + }, + { + "epoch": 1.1457725947521866, + "grad_norm": 1.4600670337677002, + "learning_rate": 3.4366318238702063e-06, + "loss": 0.1765, + "step": 540 + }, + { + "epoch": 1.1478929234031274, + "grad_norm": 1.2835088968276978, + "learning_rate": 3.4314392173816495e-06, + "loss": 0.1285, + "step": 541 + }, + { + "epoch": 1.1500132520540685, + "grad_norm": 2.4741337299346924, + "learning_rate": 3.426241940658015e-06, + "loss": 0.3035, + "step": 542 + }, + { + "epoch": 1.1521335807050093, + "grad_norm": 1.5897051095962524, + "learning_rate": 3.421040019758443e-06, + "loss": 0.2073, + "step": 543 + }, + { + "epoch": 1.1542539093559503, + "grad_norm": 1.9757038354873657, + "learning_rate": 3.4158334807653577e-06, + "loss": 0.1855, + "step": 544 + }, + { + "epoch": 1.156374238006891, + "grad_norm": 2.5434279441833496, + "learning_rate": 3.4106223497843395e-06, + "loss": 0.2083, + "step": 545 + }, + { + "epoch": 1.158494566657832, + "grad_norm": 1.7457334995269775, + "learning_rate": 3.4054066529439916e-06, + "loss": 0.2057, + "step": 546 + }, + { + "epoch": 1.160614895308773, + "grad_norm": 2.125014305114746, + "learning_rate": 3.4001864163958125e-06, + "loss": 0.2622, + "step": 547 + }, + { + "epoch": 1.1627352239597137, + "grad_norm": 1.9452868700027466, + "learning_rate": 3.394961666314061e-06, + "loss": 0.2356, + "step": 548 + }, + { + "epoch": 1.1648555526106548, + "grad_norm": 1.8804444074630737, + "learning_rate": 3.389732428895629e-06, + "loss": 0.2543, + "step": 549 + }, + { + "epoch": 1.1669758812615956, + "grad_norm": 1.7958191633224487, + "learning_rate": 3.384498730359905e-06, + "loss": 0.1877, + "step": 550 + }, + { + "epoch": 1.1690962099125364, + "grad_norm": 2.4635379314422607, + "learning_rate": 3.379260596948646e-06, + "loss": 0.2394, + "step": 551 + }, + { + "epoch": 1.1712165385634774, + "grad_norm": 1.7975070476531982, + "learning_rate": 3.3740180549258496e-06, + "loss": 0.251, + "step": 552 + }, + { + "epoch": 1.1733368672144182, + "grad_norm": 1.1541494131088257, + "learning_rate": 3.368771130577613e-06, + "loss": 0.1074, + "step": 553 + }, + { + "epoch": 1.1754571958653592, + "grad_norm": 1.4837067127227783, + "learning_rate": 3.363519850212007e-06, + "loss": 0.1926, + "step": 554 + }, + { + "epoch": 1.1775775245163, + "grad_norm": 3.1769111156463623, + "learning_rate": 3.358264240158947e-06, + "loss": 0.1456, + "step": 555 + }, + { + "epoch": 1.1796978531672409, + "grad_norm": 1.6445987224578857, + "learning_rate": 3.353004326770055e-06, + "loss": 0.2445, + "step": 556 + }, + { + "epoch": 1.1818181818181819, + "grad_norm": 0.7336058020591736, + "learning_rate": 3.347740136418529e-06, + "loss": 0.2098, + "step": 557 + }, + { + "epoch": 1.1839385104691227, + "grad_norm": 0.853908121585846, + "learning_rate": 3.342471695499014e-06, + "loss": 0.2096, + "step": 558 + }, + { + "epoch": 1.1860588391200637, + "grad_norm": 0.5674437880516052, + "learning_rate": 3.3371990304274654e-06, + "loss": 0.2537, + "step": 559 + }, + { + "epoch": 1.1881791677710045, + "grad_norm": 1.4246636629104614, + "learning_rate": 3.33192216764102e-06, + "loss": 0.1266, + "step": 560 + }, + { + "epoch": 1.1902994964219453, + "grad_norm": 0.6851096153259277, + "learning_rate": 3.3266411335978618e-06, + "loss": 0.2436, + "step": 561 + }, + { + "epoch": 1.1924198250728864, + "grad_norm": 2.390455722808838, + "learning_rate": 3.3213559547770873e-06, + "loss": 0.272, + "step": 562 + }, + { + "epoch": 1.1945401537238272, + "grad_norm": 0.6653962731361389, + "learning_rate": 3.316066657678577e-06, + "loss": 0.1754, + "step": 563 + }, + { + "epoch": 1.1966604823747682, + "grad_norm": 3.227832555770874, + "learning_rate": 3.310773268822861e-06, + "loss": 0.2089, + "step": 564 + }, + { + "epoch": 1.198780811025709, + "grad_norm": 1.3733195066452026, + "learning_rate": 3.3054758147509837e-06, + "loss": 0.1492, + "step": 565 + }, + { + "epoch": 1.2009011396766498, + "grad_norm": 2.4527945518493652, + "learning_rate": 3.300174322024373e-06, + "loss": 0.1841, + "step": 566 + }, + { + "epoch": 1.2030214683275908, + "grad_norm": 1.4190953969955444, + "learning_rate": 3.294868817224707e-06, + "loss": 0.1904, + "step": 567 + }, + { + "epoch": 1.2051417969785316, + "grad_norm": 1.0891777276992798, + "learning_rate": 3.2895593269537806e-06, + "loss": 0.2079, + "step": 568 + }, + { + "epoch": 1.2072621256294727, + "grad_norm": 3.3715262413024902, + "learning_rate": 3.284245877833371e-06, + "loss": 0.2065, + "step": 569 + }, + { + "epoch": 1.2093824542804135, + "grad_norm": 1.8128390312194824, + "learning_rate": 3.2789284965051053e-06, + "loss": 0.1667, + "step": 570 + }, + { + "epoch": 1.2115027829313543, + "grad_norm": 2.6780452728271484, + "learning_rate": 3.2736072096303277e-06, + "loss": 0.1957, + "step": 571 + }, + { + "epoch": 1.2136231115822953, + "grad_norm": 1.6943888664245605, + "learning_rate": 3.268282043889963e-06, + "loss": 0.1717, + "step": 572 + }, + { + "epoch": 1.215743440233236, + "grad_norm": 2.704658269882202, + "learning_rate": 3.2629530259843862e-06, + "loss": 0.2692, + "step": 573 + }, + { + "epoch": 1.2178637688841771, + "grad_norm": 2.5095183849334717, + "learning_rate": 3.2576201826332864e-06, + "loss": 0.223, + "step": 574 + }, + { + "epoch": 1.219984097535118, + "grad_norm": 0.9887157678604126, + "learning_rate": 3.252283540575533e-06, + "loss": 0.2378, + "step": 575 + }, + { + "epoch": 1.2221044261860587, + "grad_norm": 1.8679485321044922, + "learning_rate": 3.2469431265690432e-06, + "loss": 0.3113, + "step": 576 + }, + { + "epoch": 1.2242247548369998, + "grad_norm": 2.1015641689300537, + "learning_rate": 3.2415989673906454e-06, + "loss": 0.2094, + "step": 577 + }, + { + "epoch": 1.2263450834879406, + "grad_norm": 3.247260808944702, + "learning_rate": 3.2362510898359484e-06, + "loss": 0.286, + "step": 578 + }, + { + "epoch": 1.2284654121388816, + "grad_norm": 2.1203606128692627, + "learning_rate": 3.2308995207192028e-06, + "loss": 0.1752, + "step": 579 + }, + { + "epoch": 1.2305857407898224, + "grad_norm": 3.4415900707244873, + "learning_rate": 3.225544286873169e-06, + "loss": 0.2184, + "step": 580 + }, + { + "epoch": 1.2327060694407632, + "grad_norm": 4.078723430633545, + "learning_rate": 3.220185415148984e-06, + "loss": 0.2721, + "step": 581 + }, + { + "epoch": 1.2348263980917042, + "grad_norm": 2.06363844871521, + "learning_rate": 3.2148229324160235e-06, + "loss": 0.3589, + "step": 582 + }, + { + "epoch": 1.236946726742645, + "grad_norm": 1.6750868558883667, + "learning_rate": 3.2094568655617692e-06, + "loss": 0.2667, + "step": 583 + }, + { + "epoch": 1.239067055393586, + "grad_norm": 2.284876823425293, + "learning_rate": 3.204087241491673e-06, + "loss": 0.2865, + "step": 584 + }, + { + "epoch": 1.2411873840445269, + "grad_norm": 1.0437135696411133, + "learning_rate": 3.198714087129024e-06, + "loss": 0.2693, + "step": 585 + }, + { + "epoch": 1.2433077126954677, + "grad_norm": 1.643754005432129, + "learning_rate": 3.1933374294148112e-06, + "loss": 0.1966, + "step": 586 + }, + { + "epoch": 1.2454280413464087, + "grad_norm": 0.8333995342254639, + "learning_rate": 3.187957295307591e-06, + "loss": 0.1645, + "step": 587 + }, + { + "epoch": 1.2475483699973495, + "grad_norm": 0.7705175280570984, + "learning_rate": 3.1825737117833465e-06, + "loss": 0.2136, + "step": 588 + }, + { + "epoch": 1.2496686986482906, + "grad_norm": 1.509788155555725, + "learning_rate": 3.177186705835361e-06, + "loss": 0.1812, + "step": 589 + }, + { + "epoch": 1.2517890272992314, + "grad_norm": 0.5960215926170349, + "learning_rate": 3.171796304474074e-06, + "loss": 0.1438, + "step": 590 + }, + { + "epoch": 1.2539093559501722, + "grad_norm": 2.9289567470550537, + "learning_rate": 3.1664025347269533e-06, + "loss": 0.224, + "step": 591 + }, + { + "epoch": 1.2560296846011132, + "grad_norm": 1.6071057319641113, + "learning_rate": 3.1610054236383526e-06, + "loss": 0.1427, + "step": 592 + }, + { + "epoch": 1.258150013252054, + "grad_norm": 2.266662359237671, + "learning_rate": 3.1556049982693794e-06, + "loss": 0.3275, + "step": 593 + }, + { + "epoch": 1.260270341902995, + "grad_norm": 0.8570841550827026, + "learning_rate": 3.1502012856977606e-06, + "loss": 0.228, + "step": 594 + }, + { + "epoch": 1.2623906705539358, + "grad_norm": 2.0917248725891113, + "learning_rate": 3.144794313017704e-06, + "loss": 0.1597, + "step": 595 + }, + { + "epoch": 1.2645109992048766, + "grad_norm": 2.6728296279907227, + "learning_rate": 3.1393841073397636e-06, + "loss": 0.2749, + "step": 596 + }, + { + "epoch": 1.2666313278558177, + "grad_norm": 0.8114733695983887, + "learning_rate": 3.1339706957907058e-06, + "loss": 0.2947, + "step": 597 + }, + { + "epoch": 1.2687516565067585, + "grad_norm": 3.9571282863616943, + "learning_rate": 3.128554105513367e-06, + "loss": 0.2116, + "step": 598 + }, + { + "epoch": 1.2708719851576995, + "grad_norm": 1.4085323810577393, + "learning_rate": 3.123134363666525e-06, + "loss": 0.3044, + "step": 599 + }, + { + "epoch": 1.2729923138086403, + "grad_norm": 1.3042069673538208, + "learning_rate": 3.117711497424759e-06, + "loss": 0.2365, + "step": 600 + }, + { + "epoch": 1.2751126424595811, + "grad_norm": 9.497270584106445, + "learning_rate": 3.1122855339783135e-06, + "loss": 0.2351, + "step": 601 + }, + { + "epoch": 1.2772329711105221, + "grad_norm": 2.055746078491211, + "learning_rate": 3.106856500532962e-06, + "loss": 0.2982, + "step": 602 + }, + { + "epoch": 1.279353299761463, + "grad_norm": 1.661730408668518, + "learning_rate": 3.1014244243098723e-06, + "loss": 0.2545, + "step": 603 + }, + { + "epoch": 1.281473628412404, + "grad_norm": 2.3598806858062744, + "learning_rate": 3.0959893325454675e-06, + "loss": 0.2081, + "step": 604 + }, + { + "epoch": 1.2835939570633448, + "grad_norm": 2.3903353214263916, + "learning_rate": 3.09055125249129e-06, + "loss": 0.2386, + "step": 605 + }, + { + "epoch": 1.2857142857142856, + "grad_norm": 2.1055004596710205, + "learning_rate": 3.0851102114138677e-06, + "loss": 0.123, + "step": 606 + }, + { + "epoch": 1.2878346143652266, + "grad_norm": 2.7721481323242188, + "learning_rate": 3.079666236594573e-06, + "loss": 0.2888, + "step": 607 + }, + { + "epoch": 1.2899549430161676, + "grad_norm": 1.0820283889770508, + "learning_rate": 3.0742193553294896e-06, + "loss": 0.4641, + "step": 608 + }, + { + "epoch": 1.2920752716671084, + "grad_norm": 1.0403881072998047, + "learning_rate": 3.0687695949292724e-06, + "loss": 0.1544, + "step": 609 + }, + { + "epoch": 1.2941956003180493, + "grad_norm": 1.1737229824066162, + "learning_rate": 3.063316982719014e-06, + "loss": 0.2008, + "step": 610 + }, + { + "epoch": 1.29631592896899, + "grad_norm": 1.0275263786315918, + "learning_rate": 3.0578615460381047e-06, + "loss": 0.1276, + "step": 611 + }, + { + "epoch": 1.298436257619931, + "grad_norm": 1.435745120048523, + "learning_rate": 3.0524033122400974e-06, + "loss": 0.256, + "step": 612 + }, + { + "epoch": 1.3005565862708721, + "grad_norm": 1.1113966703414917, + "learning_rate": 3.04694230869257e-06, + "loss": 0.2078, + "step": 613 + }, + { + "epoch": 1.302676914921813, + "grad_norm": 0.7453861236572266, + "learning_rate": 3.0414785627769884e-06, + "loss": 0.2638, + "step": 614 + }, + { + "epoch": 1.3047972435727537, + "grad_norm": 2.004967212677002, + "learning_rate": 3.036012101888565e-06, + "loss": 0.1654, + "step": 615 + }, + { + "epoch": 1.3069175722236945, + "grad_norm": 1.6051661968231201, + "learning_rate": 3.0305429534361304e-06, + "loss": 0.1348, + "step": 616 + }, + { + "epoch": 1.3090379008746356, + "grad_norm": 2.3148880004882812, + "learning_rate": 3.0250711448419867e-06, + "loss": 0.1318, + "step": 617 + }, + { + "epoch": 1.3111582295255766, + "grad_norm": 1.5317455530166626, + "learning_rate": 3.0195967035417765e-06, + "loss": 0.2081, + "step": 618 + }, + { + "epoch": 1.3132785581765174, + "grad_norm": 2.321281671524048, + "learning_rate": 3.014119656984341e-06, + "loss": 0.1596, + "step": 619 + }, + { + "epoch": 1.3153988868274582, + "grad_norm": 2.7379441261291504, + "learning_rate": 3.0086400326315853e-06, + "loss": 0.2253, + "step": 620 + }, + { + "epoch": 1.3175192154783992, + "grad_norm": 1.8512643575668335, + "learning_rate": 3.0031578579583375e-06, + "loss": 0.2683, + "step": 621 + }, + { + "epoch": 1.31963954412934, + "grad_norm": 3.2570621967315674, + "learning_rate": 2.9976731604522175e-06, + "loss": 0.1977, + "step": 622 + }, + { + "epoch": 1.321759872780281, + "grad_norm": 1.7534589767456055, + "learning_rate": 2.992185967613489e-06, + "loss": 0.171, + "step": 623 + }, + { + "epoch": 1.3238802014312219, + "grad_norm": 0.5050146579742432, + "learning_rate": 2.9866963069549315e-06, + "loss": 0.2047, + "step": 624 + }, + { + "epoch": 1.3260005300821627, + "grad_norm": 1.552862524986267, + "learning_rate": 2.9812042060016968e-06, + "loss": 0.1553, + "step": 625 + }, + { + "epoch": 1.3281208587331037, + "grad_norm": 1.942893385887146, + "learning_rate": 2.975709692291171e-06, + "loss": 0.1797, + "step": 626 + }, + { + "epoch": 1.3302411873840445, + "grad_norm": 1.2831542491912842, + "learning_rate": 2.9702127933728403e-06, + "loss": 0.16, + "step": 627 + }, + { + "epoch": 1.3323615160349855, + "grad_norm": 1.4484132528305054, + "learning_rate": 2.9647135368081488e-06, + "loss": 0.1923, + "step": 628 + }, + { + "epoch": 1.3344818446859263, + "grad_norm": 3.5186307430267334, + "learning_rate": 2.9592119501703607e-06, + "loss": 0.3373, + "step": 629 + }, + { + "epoch": 1.3366021733368671, + "grad_norm": 1.9385162591934204, + "learning_rate": 2.9537080610444274e-06, + "loss": 0.2003, + "step": 630 + }, + { + "epoch": 1.3387225019878082, + "grad_norm": 1.2267210483551025, + "learning_rate": 2.9482018970268395e-06, + "loss": 0.1736, + "step": 631 + }, + { + "epoch": 1.340842830638749, + "grad_norm": 0.9191475510597229, + "learning_rate": 2.9426934857254975e-06, + "loss": 0.2854, + "step": 632 + }, + { + "epoch": 1.34296315928969, + "grad_norm": 1.7922972440719604, + "learning_rate": 2.9371828547595695e-06, + "loss": 0.1429, + "step": 633 + }, + { + "epoch": 1.3450834879406308, + "grad_norm": 1.5351743698120117, + "learning_rate": 2.9316700317593507e-06, + "loss": 0.1374, + "step": 634 + }, + { + "epoch": 1.3472038165915716, + "grad_norm": 1.2162325382232666, + "learning_rate": 2.92615504436613e-06, + "loss": 0.1429, + "step": 635 + }, + { + "epoch": 1.3493241452425127, + "grad_norm": 1.7114899158477783, + "learning_rate": 2.920637920232047e-06, + "loss": 0.2211, + "step": 636 + }, + { + "epoch": 1.3514444738934535, + "grad_norm": 1.5543713569641113, + "learning_rate": 2.9151186870199556e-06, + "loss": 0.1726, + "step": 637 + }, + { + "epoch": 1.3535648025443945, + "grad_norm": 2.1046950817108154, + "learning_rate": 2.9095973724032832e-06, + "loss": 0.2319, + "step": 638 + }, + { + "epoch": 1.3556851311953353, + "grad_norm": 2.058473587036133, + "learning_rate": 2.9040740040658954e-06, + "loss": 0.2942, + "step": 639 + }, + { + "epoch": 1.357805459846276, + "grad_norm": 1.5705662965774536, + "learning_rate": 2.8985486097019543e-06, + "loss": 0.2206, + "step": 640 + }, + { + "epoch": 1.3599257884972171, + "grad_norm": 2.0310404300689697, + "learning_rate": 2.89302121701578e-06, + "loss": 0.1729, + "step": 641 + }, + { + "epoch": 1.362046117148158, + "grad_norm": 1.455135703086853, + "learning_rate": 2.8874918537217118e-06, + "loss": 0.26, + "step": 642 + }, + { + "epoch": 1.364166445799099, + "grad_norm": 2.1307947635650635, + "learning_rate": 2.8819605475439716e-06, + "loss": 0.1996, + "step": 643 + }, + { + "epoch": 1.3662867744500398, + "grad_norm": 1.6828829050064087, + "learning_rate": 2.876427326216521e-06, + "loss": 0.1706, + "step": 644 + }, + { + "epoch": 1.3684071031009806, + "grad_norm": 2.5645523071289062, + "learning_rate": 2.870892217482925e-06, + "loss": 0.2089, + "step": 645 + }, + { + "epoch": 1.3705274317519216, + "grad_norm": 3.5876777172088623, + "learning_rate": 2.8653552490962122e-06, + "loss": 0.3736, + "step": 646 + }, + { + "epoch": 1.3726477604028624, + "grad_norm": 1.182286262512207, + "learning_rate": 2.8598164488187354e-06, + "loss": 0.2904, + "step": 647 + }, + { + "epoch": 1.3747680890538034, + "grad_norm": 1.9589124917984009, + "learning_rate": 2.8542758444220303e-06, + "loss": 0.2265, + "step": 648 + }, + { + "epoch": 1.3768884177047442, + "grad_norm": 0.8725947737693787, + "learning_rate": 2.848733463686683e-06, + "loss": 0.2266, + "step": 649 + }, + { + "epoch": 1.379008746355685, + "grad_norm": 2.0674960613250732, + "learning_rate": 2.843189334402183e-06, + "loss": 0.1478, + "step": 650 + }, + { + "epoch": 1.381129075006626, + "grad_norm": 0.9025703072547913, + "learning_rate": 2.837643484366787e-06, + "loss": 0.1831, + "step": 651 + }, + { + "epoch": 1.3832494036575669, + "grad_norm": 2.652928352355957, + "learning_rate": 2.83209594138738e-06, + "loss": 0.3069, + "step": 652 + }, + { + "epoch": 1.385369732308508, + "grad_norm": 0.8679104447364807, + "learning_rate": 2.8265467332793358e-06, + "loss": 0.1158, + "step": 653 + }, + { + "epoch": 1.3874900609594487, + "grad_norm": 2.065187692642212, + "learning_rate": 2.820995887866378e-06, + "loss": 0.3263, + "step": 654 + }, + { + "epoch": 1.3896103896103895, + "grad_norm": 1.9065489768981934, + "learning_rate": 2.8154434329804366e-06, + "loss": 0.2294, + "step": 655 + }, + { + "epoch": 1.3917307182613305, + "grad_norm": 2.2654645442962646, + "learning_rate": 2.8098893964615165e-06, + "loss": 0.2063, + "step": 656 + }, + { + "epoch": 1.3938510469122714, + "grad_norm": 1.9993574619293213, + "learning_rate": 2.8043338061575464e-06, + "loss": 0.2116, + "step": 657 + }, + { + "epoch": 1.3959713755632124, + "grad_norm": 1.850152850151062, + "learning_rate": 2.7987766899242513e-06, + "loss": 0.1887, + "step": 658 + }, + { + "epoch": 1.3980917042141532, + "grad_norm": 0.9010924696922302, + "learning_rate": 2.7932180756250042e-06, + "loss": 0.2322, + "step": 659 + }, + { + "epoch": 1.400212032865094, + "grad_norm": 1.3110419511795044, + "learning_rate": 2.787657991130692e-06, + "loss": 0.1766, + "step": 660 + }, + { + "epoch": 1.402332361516035, + "grad_norm": 0.9936445951461792, + "learning_rate": 2.7820964643195685e-06, + "loss": 0.1912, + "step": 661 + }, + { + "epoch": 1.4044526901669758, + "grad_norm": 1.7485136985778809, + "learning_rate": 2.7765335230771255e-06, + "loss": 0.1987, + "step": 662 + }, + { + "epoch": 1.4065730188179169, + "grad_norm": 1.2912129163742065, + "learning_rate": 2.7709691952959406e-06, + "loss": 0.1324, + "step": 663 + }, + { + "epoch": 1.4086933474688577, + "grad_norm": 2.263025999069214, + "learning_rate": 2.765403508875548e-06, + "loss": 0.2485, + "step": 664 + }, + { + "epoch": 1.4108136761197985, + "grad_norm": 1.1566165685653687, + "learning_rate": 2.759836491722292e-06, + "loss": 0.173, + "step": 665 + }, + { + "epoch": 1.4129340047707395, + "grad_norm": 1.7113949060440063, + "learning_rate": 2.75426817174919e-06, + "loss": 0.1933, + "step": 666 + }, + { + "epoch": 1.4150543334216803, + "grad_norm": 2.519707679748535, + "learning_rate": 2.7486985768757905e-06, + "loss": 0.1837, + "step": 667 + }, + { + "epoch": 1.4171746620726213, + "grad_norm": 2.177272319793701, + "learning_rate": 2.743127735028037e-06, + "loss": 0.3647, + "step": 668 + }, + { + "epoch": 1.4192949907235621, + "grad_norm": 2.8958051204681396, + "learning_rate": 2.7375556741381216e-06, + "loss": 0.3015, + "step": 669 + }, + { + "epoch": 1.421415319374503, + "grad_norm": 1.972503662109375, + "learning_rate": 2.731982422144352e-06, + "loss": 0.2581, + "step": 670 + }, + { + "epoch": 1.423535648025444, + "grad_norm": 0.32309406995773315, + "learning_rate": 2.726408006991006e-06, + "loss": 0.2046, + "step": 671 + }, + { + "epoch": 1.4256559766763848, + "grad_norm": 0.9400335550308228, + "learning_rate": 2.7208324566281946e-06, + "loss": 0.2459, + "step": 672 + }, + { + "epoch": 1.4277763053273258, + "grad_norm": 2.608882188796997, + "learning_rate": 2.715255799011721e-06, + "loss": 0.2656, + "step": 673 + }, + { + "epoch": 1.4298966339782666, + "grad_norm": 1.6778721809387207, + "learning_rate": 2.7096780621029386e-06, + "loss": 0.1731, + "step": 674 + }, + { + "epoch": 1.4320169626292074, + "grad_norm": 1.2319176197052002, + "learning_rate": 2.7040992738686135e-06, + "loss": 0.3142, + "step": 675 + }, + { + "epoch": 1.4341372912801484, + "grad_norm": 2.1388039588928223, + "learning_rate": 2.6985194622807835e-06, + "loss": 0.1379, + "step": 676 + }, + { + "epoch": 1.4362576199310892, + "grad_norm": 2.897584915161133, + "learning_rate": 2.6929386553166165e-06, + "loss": 0.2351, + "step": 677 + }, + { + "epoch": 1.4383779485820303, + "grad_norm": 1.4169594049453735, + "learning_rate": 2.687356880958271e-06, + "loss": 0.0984, + "step": 678 + }, + { + "epoch": 1.440498277232971, + "grad_norm": 1.3336187601089478, + "learning_rate": 2.6817741671927587e-06, + "loss": 0.1528, + "step": 679 + }, + { + "epoch": 1.4426186058839119, + "grad_norm": 1.822395920753479, + "learning_rate": 2.676190542011797e-06, + "loss": 0.1678, + "step": 680 + }, + { + "epoch": 1.444738934534853, + "grad_norm": 1.3622679710388184, + "learning_rate": 2.670606033411678e-06, + "loss": 0.17, + "step": 681 + }, + { + "epoch": 1.4468592631857937, + "grad_norm": 2.184080123901367, + "learning_rate": 2.6650206693931184e-06, + "loss": 0.2781, + "step": 682 + }, + { + "epoch": 1.4489795918367347, + "grad_norm": 1.511780858039856, + "learning_rate": 2.659434477961129e-06, + "loss": 0.2947, + "step": 683 + }, + { + "epoch": 1.4510999204876756, + "grad_norm": 1.5842374563217163, + "learning_rate": 2.653847487124865e-06, + "loss": 0.1783, + "step": 684 + }, + { + "epoch": 1.4532202491386164, + "grad_norm": 1.9350712299346924, + "learning_rate": 2.648259724897492e-06, + "loss": 0.2216, + "step": 685 + }, + { + "epoch": 1.4553405777895574, + "grad_norm": 2.5653059482574463, + "learning_rate": 2.6426712192960423e-06, + "loss": 0.2853, + "step": 686 + }, + { + "epoch": 1.4574609064404984, + "grad_norm": 3.479128837585449, + "learning_rate": 2.637081998341277e-06, + "loss": 0.1873, + "step": 687 + }, + { + "epoch": 1.4595812350914392, + "grad_norm": 2.4509148597717285, + "learning_rate": 2.631492090057543e-06, + "loss": 0.2065, + "step": 688 + }, + { + "epoch": 1.46170156374238, + "grad_norm": 1.770412564277649, + "learning_rate": 2.6259015224726325e-06, + "loss": 0.1938, + "step": 689 + }, + { + "epoch": 1.4638218923933208, + "grad_norm": 1.4200644493103027, + "learning_rate": 2.6203103236176446e-06, + "loss": 0.2258, + "step": 690 + }, + { + "epoch": 1.4659422210442619, + "grad_norm": 2.0753350257873535, + "learning_rate": 2.6147185215268446e-06, + "loss": 0.2049, + "step": 691 + }, + { + "epoch": 1.468062549695203, + "grad_norm": 1.6016238927841187, + "learning_rate": 2.609126144237519e-06, + "loss": 0.2649, + "step": 692 + }, + { + "epoch": 1.4701828783461437, + "grad_norm": 1.9330469369888306, + "learning_rate": 2.603533219789844e-06, + "loss": 0.2249, + "step": 693 + }, + { + "epoch": 1.4723032069970845, + "grad_norm": 2.1735124588012695, + "learning_rate": 2.597939776226732e-06, + "loss": 0.2629, + "step": 694 + }, + { + "epoch": 1.4744235356480253, + "grad_norm": 1.841036319732666, + "learning_rate": 2.5923458415937048e-06, + "loss": 0.1787, + "step": 695 + }, + { + "epoch": 1.4765438642989663, + "grad_norm": 2.6332991123199463, + "learning_rate": 2.586751443938742e-06, + "loss": 0.2431, + "step": 696 + }, + { + "epoch": 1.4786641929499074, + "grad_norm": 1.6684833765029907, + "learning_rate": 2.581156611312148e-06, + "loss": 0.2282, + "step": 697 + }, + { + "epoch": 1.4807845216008482, + "grad_norm": 0.7805116772651672, + "learning_rate": 2.5755613717664053e-06, + "loss": 0.1392, + "step": 698 + }, + { + "epoch": 1.482904850251789, + "grad_norm": 0.9408957958221436, + "learning_rate": 2.5699657533560386e-06, + "loss": 0.1325, + "step": 699 + }, + { + "epoch": 1.48502517890273, + "grad_norm": 2.233403444290161, + "learning_rate": 2.5643697841374722e-06, + "loss": 0.2908, + "step": 700 + }, + { + "epoch": 1.4871455075536708, + "grad_norm": 0.5273526310920715, + "learning_rate": 2.5587734921688873e-06, + "loss": 0.1575, + "step": 701 + }, + { + "epoch": 1.4892658362046118, + "grad_norm": 1.2741076946258545, + "learning_rate": 2.553176905510086e-06, + "loss": 0.2134, + "step": 702 + }, + { + "epoch": 1.4913861648555526, + "grad_norm": 1.4551169872283936, + "learning_rate": 2.547580052222347e-06, + "loss": 0.1237, + "step": 703 + }, + { + "epoch": 1.4935064935064934, + "grad_norm": 2.193265914916992, + "learning_rate": 2.5419829603682857e-06, + "loss": 0.2685, + "step": 704 + }, + { + "epoch": 1.4956268221574345, + "grad_norm": 1.1736443042755127, + "learning_rate": 2.5363856580117126e-06, + "loss": 0.1412, + "step": 705 + }, + { + "epoch": 1.4977471508083753, + "grad_norm": 2.0331931114196777, + "learning_rate": 2.5307881732174954e-06, + "loss": 0.3377, + "step": 706 + }, + { + "epoch": 1.4998674794593163, + "grad_norm": 1.456709861755371, + "learning_rate": 2.525190534051416e-06, + "loss": 0.2192, + "step": 707 + }, + { + "epoch": 1.5019878081102571, + "grad_norm": 3.0361955165863037, + "learning_rate": 2.519592768580031e-06, + "loss": 0.2958, + "step": 708 + }, + { + "epoch": 1.504108136761198, + "grad_norm": 1.2546547651290894, + "learning_rate": 2.513994904870528e-06, + "loss": 0.2331, + "step": 709 + }, + { + "epoch": 1.5062284654121387, + "grad_norm": 1.4712584018707275, + "learning_rate": 2.5083969709905904e-06, + "loss": 0.1968, + "step": 710 + }, + { + "epoch": 1.5083487940630798, + "grad_norm": 1.318629264831543, + "learning_rate": 2.502798995008249e-06, + "loss": 0.2898, + "step": 711 + }, + { + "epoch": 1.5104691227140208, + "grad_norm": 3.635026693344116, + "learning_rate": 2.4972010049917513e-06, + "loss": 0.1849, + "step": 712 + }, + { + "epoch": 1.5125894513649616, + "grad_norm": 1.7475965023040771, + "learning_rate": 2.491603029009411e-06, + "loss": 0.1244, + "step": 713 + }, + { + "epoch": 1.5147097800159024, + "grad_norm": 2.1681947708129883, + "learning_rate": 2.4860050951294723e-06, + "loss": 0.186, + "step": 714 + }, + { + "epoch": 1.5168301086668432, + "grad_norm": 1.8500131368637085, + "learning_rate": 2.480407231419969e-06, + "loss": 0.1995, + "step": 715 + }, + { + "epoch": 1.5189504373177842, + "grad_norm": 1.4108548164367676, + "learning_rate": 2.474809465948584e-06, + "loss": 0.1875, + "step": 716 + }, + { + "epoch": 1.5210707659687253, + "grad_norm": 1.5259912014007568, + "learning_rate": 2.469211826782506e-06, + "loss": 0.2135, + "step": 717 + }, + { + "epoch": 1.523191094619666, + "grad_norm": 1.7771860361099243, + "learning_rate": 2.4636143419882887e-06, + "loss": 0.1819, + "step": 718 + }, + { + "epoch": 1.5253114232706069, + "grad_norm": 1.3263814449310303, + "learning_rate": 2.4580170396317156e-06, + "loss": 0.1927, + "step": 719 + }, + { + "epoch": 1.5274317519215477, + "grad_norm": 3.3468446731567383, + "learning_rate": 2.452419947777654e-06, + "loss": 0.1666, + "step": 720 + }, + { + "epoch": 1.5295520805724887, + "grad_norm": 1.9386024475097656, + "learning_rate": 2.4468230944899147e-06, + "loss": 0.2549, + "step": 721 + }, + { + "epoch": 1.5316724092234297, + "grad_norm": 0.590383768081665, + "learning_rate": 2.4412265078311135e-06, + "loss": 0.1705, + "step": 722 + }, + { + "epoch": 1.5337927378743705, + "grad_norm": 1.4284600019454956, + "learning_rate": 2.435630215862529e-06, + "loss": 0.1925, + "step": 723 + }, + { + "epoch": 1.5359130665253113, + "grad_norm": 1.2749354839324951, + "learning_rate": 2.4300342466439623e-06, + "loss": 0.2595, + "step": 724 + }, + { + "epoch": 1.5380333951762524, + "grad_norm": 1.1233924627304077, + "learning_rate": 2.424438628233595e-06, + "loss": 0.2232, + "step": 725 + }, + { + "epoch": 1.5401537238271932, + "grad_norm": 1.092596173286438, + "learning_rate": 2.418843388687853e-06, + "loss": 0.1417, + "step": 726 + }, + { + "epoch": 1.5422740524781342, + "grad_norm": 2.1619231700897217, + "learning_rate": 2.4132485560612583e-06, + "loss": 0.2102, + "step": 727 + }, + { + "epoch": 1.544394381129075, + "grad_norm": 1.9228898286819458, + "learning_rate": 2.4076541584062965e-06, + "loss": 0.1773, + "step": 728 + }, + { + "epoch": 1.5465147097800158, + "grad_norm": 2.4524118900299072, + "learning_rate": 2.402060223773269e-06, + "loss": 0.2415, + "step": 729 + }, + { + "epoch": 1.5486350384309568, + "grad_norm": 1.9279297590255737, + "learning_rate": 2.3964667802101574e-06, + "loss": 0.2973, + "step": 730 + }, + { + "epoch": 1.5507553670818977, + "grad_norm": 1.126503348350525, + "learning_rate": 2.3908738557624812e-06, + "loss": 0.2207, + "step": 731 + }, + { + "epoch": 1.5528756957328387, + "grad_norm": 1.8187668323516846, + "learning_rate": 2.385281478473156e-06, + "loss": 0.2319, + "step": 732 + }, + { + "epoch": 1.5549960243837795, + "grad_norm": 1.953602910041809, + "learning_rate": 2.379689676382356e-06, + "loss": 0.2266, + "step": 733 + }, + { + "epoch": 1.5571163530347203, + "grad_norm": 1.342537522315979, + "learning_rate": 2.3740984775273684e-06, + "loss": 0.1672, + "step": 734 + }, + { + "epoch": 1.5592366816856613, + "grad_norm": 3.2077980041503906, + "learning_rate": 2.368507909942458e-06, + "loss": 0.2455, + "step": 735 + }, + { + "epoch": 1.5613570103366021, + "grad_norm": 1.859153151512146, + "learning_rate": 2.362918001658723e-06, + "loss": 0.1731, + "step": 736 + }, + { + "epoch": 1.5634773389875432, + "grad_norm": 2.042102813720703, + "learning_rate": 2.3573287807039577e-06, + "loss": 0.182, + "step": 737 + }, + { + "epoch": 1.565597667638484, + "grad_norm": 2.096276044845581, + "learning_rate": 2.3517402751025083e-06, + "loss": 0.2215, + "step": 738 + }, + { + "epoch": 1.5677179962894248, + "grad_norm": 0.925915002822876, + "learning_rate": 2.3461525128751364e-06, + "loss": 0.1727, + "step": 739 + }, + { + "epoch": 1.5698383249403658, + "grad_norm": 1.1790268421173096, + "learning_rate": 2.3405655220388718e-06, + "loss": 0.1117, + "step": 740 + }, + { + "epoch": 1.5719586535913066, + "grad_norm": 6.514387607574463, + "learning_rate": 2.334979330606882e-06, + "loss": 0.2172, + "step": 741 + }, + { + "epoch": 1.5740789822422476, + "grad_norm": 2.039428949356079, + "learning_rate": 2.3293939665883233e-06, + "loss": 0.1758, + "step": 742 + }, + { + "epoch": 1.5761993108931884, + "grad_norm": 2.0858302116394043, + "learning_rate": 2.3238094579882037e-06, + "loss": 0.1564, + "step": 743 + }, + { + "epoch": 1.5783196395441292, + "grad_norm": 2.3777787685394287, + "learning_rate": 2.318225832807242e-06, + "loss": 0.2507, + "step": 744 + }, + { + "epoch": 1.5804399681950703, + "grad_norm": 1.0911935567855835, + "learning_rate": 2.3126431190417294e-06, + "loss": 0.2025, + "step": 745 + }, + { + "epoch": 1.5825602968460113, + "grad_norm": 1.207847237586975, + "learning_rate": 2.3070613446833843e-06, + "loss": 0.2627, + "step": 746 + }, + { + "epoch": 1.584680625496952, + "grad_norm": 1.059277892112732, + "learning_rate": 2.3014805377192173e-06, + "loss": 0.1475, + "step": 747 + }, + { + "epoch": 1.586800954147893, + "grad_norm": 1.6303125619888306, + "learning_rate": 2.2959007261313865e-06, + "loss": 0.1478, + "step": 748 + }, + { + "epoch": 1.5889212827988337, + "grad_norm": 0.9721236824989319, + "learning_rate": 2.2903219378970623e-06, + "loss": 0.169, + "step": 749 + }, + { + "epoch": 1.5910416114497747, + "grad_norm": 2.5028750896453857, + "learning_rate": 2.2847442009882805e-06, + "loss": 0.2719, + "step": 750 + }, + { + "epoch": 1.5931619401007158, + "grad_norm": 1.3091676235198975, + "learning_rate": 2.2791675433718058e-06, + "loss": 0.1815, + "step": 751 + }, + { + "epoch": 1.5952822687516566, + "grad_norm": 1.014621615409851, + "learning_rate": 2.273591993008995e-06, + "loss": 0.1354, + "step": 752 + }, + { + "epoch": 1.5974025974025974, + "grad_norm": 1.3206697702407837, + "learning_rate": 2.268017577855649e-06, + "loss": 0.2361, + "step": 753 + }, + { + "epoch": 1.5995229260535382, + "grad_norm": 1.9211969375610352, + "learning_rate": 2.262444325861879e-06, + "loss": 0.2273, + "step": 754 + }, + { + "epoch": 1.6016432547044792, + "grad_norm": 0.9052472710609436, + "learning_rate": 2.2568722649719637e-06, + "loss": 0.1695, + "step": 755 + }, + { + "epoch": 1.6037635833554202, + "grad_norm": 0.7492967844009399, + "learning_rate": 2.25130142312421e-06, + "loss": 0.2105, + "step": 756 + }, + { + "epoch": 1.605883912006361, + "grad_norm": 1.8103669881820679, + "learning_rate": 2.2457318282508105e-06, + "loss": 0.2822, + "step": 757 + }, + { + "epoch": 1.6080042406573019, + "grad_norm": 1.9676963090896606, + "learning_rate": 2.2401635082777086e-06, + "loss": 0.2802, + "step": 758 + }, + { + "epoch": 1.6101245693082427, + "grad_norm": 1.3851075172424316, + "learning_rate": 2.234596491124452e-06, + "loss": 0.1117, + "step": 759 + }, + { + "epoch": 1.6122448979591837, + "grad_norm": 0.9123232960700989, + "learning_rate": 2.2290308047040607e-06, + "loss": 0.2573, + "step": 760 + }, + { + "epoch": 1.6143652266101247, + "grad_norm": 1.3736172914505005, + "learning_rate": 2.2234664769228758e-06, + "loss": 0.1806, + "step": 761 + }, + { + "epoch": 1.6164855552610655, + "grad_norm": 0.8288306593894958, + "learning_rate": 2.217903535680432e-06, + "loss": 0.1327, + "step": 762 + }, + { + "epoch": 1.6186058839120063, + "grad_norm": 0.9833022952079773, + "learning_rate": 2.212342008869309e-06, + "loss": 0.1819, + "step": 763 + }, + { + "epoch": 1.6207262125629471, + "grad_norm": 1.44596266746521, + "learning_rate": 2.206781924374996e-06, + "loss": 0.1626, + "step": 764 + }, + { + "epoch": 1.6228465412138882, + "grad_norm": 2.6636288166046143, + "learning_rate": 2.201223310075749e-06, + "loss": 0.2006, + "step": 765 + }, + { + "epoch": 1.6249668698648292, + "grad_norm": 1.4887255430221558, + "learning_rate": 2.1956661938424544e-06, + "loss": 0.1135, + "step": 766 + }, + { + "epoch": 1.62708719851577, + "grad_norm": 2.366757392883301, + "learning_rate": 2.1901106035384843e-06, + "loss": 0.2926, + "step": 767 + }, + { + "epoch": 1.6292075271667108, + "grad_norm": 1.6054885387420654, + "learning_rate": 2.1845565670195634e-06, + "loss": 0.2127, + "step": 768 + }, + { + "epoch": 1.6313278558176516, + "grad_norm": 1.424625277519226, + "learning_rate": 2.1790041121336223e-06, + "loss": 0.256, + "step": 769 + }, + { + "epoch": 1.6334481844685926, + "grad_norm": 1.324894905090332, + "learning_rate": 2.173453266720665e-06, + "loss": 0.2511, + "step": 770 + }, + { + "epoch": 1.6355685131195337, + "grad_norm": 1.541780710220337, + "learning_rate": 2.1679040586126214e-06, + "loss": 0.1786, + "step": 771 + }, + { + "epoch": 1.6376888417704745, + "grad_norm": 1.0855908393859863, + "learning_rate": 2.1623565156332145e-06, + "loss": 0.2015, + "step": 772 + }, + { + "epoch": 1.6398091704214153, + "grad_norm": 1.2004632949829102, + "learning_rate": 2.1568106655978184e-06, + "loss": 0.1488, + "step": 773 + }, + { + "epoch": 1.641929499072356, + "grad_norm": 2.120727300643921, + "learning_rate": 2.1512665363133173e-06, + "loss": 0.3628, + "step": 774 + }, + { + "epoch": 1.644049827723297, + "grad_norm": 1.992598056793213, + "learning_rate": 2.14572415557797e-06, + "loss": 0.2429, + "step": 775 + }, + { + "epoch": 1.6461701563742381, + "grad_norm": 1.2479114532470703, + "learning_rate": 2.140183551181266e-06, + "loss": 0.1817, + "step": 776 + }, + { + "epoch": 1.648290485025179, + "grad_norm": 1.3581926822662354, + "learning_rate": 2.1346447509037886e-06, + "loss": 0.1804, + "step": 777 + }, + { + "epoch": 1.6504108136761197, + "grad_norm": 1.578666090965271, + "learning_rate": 2.1291077825170756e-06, + "loss": 0.1714, + "step": 778 + }, + { + "epoch": 1.6525311423270606, + "grad_norm": 1.6858261823654175, + "learning_rate": 2.1235726737834794e-06, + "loss": 0.2376, + "step": 779 + }, + { + "epoch": 1.6546514709780016, + "grad_norm": 1.8544155359268188, + "learning_rate": 2.118039452456029e-06, + "loss": 0.1878, + "step": 780 + }, + { + "epoch": 1.6567717996289426, + "grad_norm": 1.179569959640503, + "learning_rate": 2.112508146278289e-06, + "loss": 0.2489, + "step": 781 + }, + { + "epoch": 1.6588921282798834, + "grad_norm": 1.2655270099639893, + "learning_rate": 2.106978782984221e-06, + "loss": 0.1492, + "step": 782 + }, + { + "epoch": 1.6610124569308242, + "grad_norm": 0.9758352041244507, + "learning_rate": 2.101451390298047e-06, + "loss": 0.1525, + "step": 783 + }, + { + "epoch": 1.663132785581765, + "grad_norm": 1.285880208015442, + "learning_rate": 2.095925995934105e-06, + "loss": 0.2749, + "step": 784 + }, + { + "epoch": 1.665253114232706, + "grad_norm": 0.683684766292572, + "learning_rate": 2.0904026275967176e-06, + "loss": 0.1183, + "step": 785 + }, + { + "epoch": 1.667373442883647, + "grad_norm": 1.4306302070617676, + "learning_rate": 2.084881312980045e-06, + "loss": 0.1484, + "step": 786 + }, + { + "epoch": 1.669493771534588, + "grad_norm": 1.3516453504562378, + "learning_rate": 2.0793620797679537e-06, + "loss": 0.2783, + "step": 787 + }, + { + "epoch": 1.6716141001855287, + "grad_norm": 1.849977731704712, + "learning_rate": 2.0738449556338704e-06, + "loss": 0.2064, + "step": 788 + }, + { + "epoch": 1.6737344288364695, + "grad_norm": 2.6501619815826416, + "learning_rate": 2.0683299682406497e-06, + "loss": 0.1742, + "step": 789 + }, + { + "epoch": 1.6758547574874105, + "grad_norm": 1.9885671138763428, + "learning_rate": 2.062817145240431e-06, + "loss": 0.2273, + "step": 790 + }, + { + "epoch": 1.6779750861383516, + "grad_norm": 1.9040833711624146, + "learning_rate": 2.057306514274503e-06, + "loss": 0.2515, + "step": 791 + }, + { + "epoch": 1.6800954147892924, + "grad_norm": 1.9295481443405151, + "learning_rate": 2.0517981029731613e-06, + "loss": 0.2791, + "step": 792 + }, + { + "epoch": 1.6822157434402332, + "grad_norm": 1.2951781749725342, + "learning_rate": 2.0462919389555734e-06, + "loss": 0.1838, + "step": 793 + }, + { + "epoch": 1.684336072091174, + "grad_norm": 1.2169189453125, + "learning_rate": 2.0407880498296397e-06, + "loss": 0.188, + "step": 794 + }, + { + "epoch": 1.686456400742115, + "grad_norm": 1.4646093845367432, + "learning_rate": 2.035286463191852e-06, + "loss": 0.2529, + "step": 795 + }, + { + "epoch": 1.688576729393056, + "grad_norm": 1.2175997495651245, + "learning_rate": 2.0297872066271606e-06, + "loss": 0.1882, + "step": 796 + }, + { + "epoch": 1.6906970580439968, + "grad_norm": 1.482407808303833, + "learning_rate": 2.02429030770883e-06, + "loss": 0.2542, + "step": 797 + }, + { + "epoch": 1.6928173866949376, + "grad_norm": 1.4033699035644531, + "learning_rate": 2.0187957939983045e-06, + "loss": 0.2018, + "step": 798 + }, + { + "epoch": 1.6949377153458784, + "grad_norm": 2.2561542987823486, + "learning_rate": 2.0133036930450694e-06, + "loss": 0.1885, + "step": 799 + }, + { + "epoch": 1.6970580439968195, + "grad_norm": 1.9615060091018677, + "learning_rate": 2.0078140323865114e-06, + "loss": 0.1909, + "step": 800 + }, + { + "epoch": 1.6991783726477605, + "grad_norm": 1.5575997829437256, + "learning_rate": 2.0023268395477833e-06, + "loss": 0.1939, + "step": 801 + }, + { + "epoch": 1.7012987012987013, + "grad_norm": 1.2603005170822144, + "learning_rate": 1.9968421420416633e-06, + "loss": 0.2151, + "step": 802 + }, + { + "epoch": 1.7034190299496421, + "grad_norm": 1.56342613697052, + "learning_rate": 1.991359967368416e-06, + "loss": 0.2121, + "step": 803 + }, + { + "epoch": 1.7055393586005831, + "grad_norm": 0.8418555855751038, + "learning_rate": 1.9858803430156602e-06, + "loss": 0.1356, + "step": 804 + }, + { + "epoch": 1.707659687251524, + "grad_norm": 2.612060308456421, + "learning_rate": 1.9804032964582243e-06, + "loss": 0.1723, + "step": 805 + }, + { + "epoch": 1.709780015902465, + "grad_norm": 1.789333462715149, + "learning_rate": 1.974928855158014e-06, + "loss": 0.2443, + "step": 806 + }, + { + "epoch": 1.7119003445534058, + "grad_norm": 2.306417226791382, + "learning_rate": 1.96945704656387e-06, + "loss": 0.1573, + "step": 807 + }, + { + "epoch": 1.7140206732043466, + "grad_norm": 1.3851442337036133, + "learning_rate": 1.9639878981114358e-06, + "loss": 0.2239, + "step": 808 + }, + { + "epoch": 1.7161410018552876, + "grad_norm": 1.9788298606872559, + "learning_rate": 1.958521437223013e-06, + "loss": 0.1589, + "step": 809 + }, + { + "epoch": 1.7182613305062284, + "grad_norm": 1.2567238807678223, + "learning_rate": 1.95305769130743e-06, + "loss": 0.1738, + "step": 810 + }, + { + "epoch": 1.7203816591571695, + "grad_norm": 1.2289453744888306, + "learning_rate": 1.947596687759902e-06, + "loss": 0.1698, + "step": 811 + }, + { + "epoch": 1.7225019878081103, + "grad_norm": 1.1884444952011108, + "learning_rate": 1.9421384539618957e-06, + "loss": 0.1406, + "step": 812 + }, + { + "epoch": 1.724622316459051, + "grad_norm": 2.408679485321045, + "learning_rate": 1.9366830172809877e-06, + "loss": 0.214, + "step": 813 + }, + { + "epoch": 1.726742645109992, + "grad_norm": 1.555776596069336, + "learning_rate": 1.9312304050707293e-06, + "loss": 0.1675, + "step": 814 + }, + { + "epoch": 1.728862973760933, + "grad_norm": 1.8956245183944702, + "learning_rate": 1.9257806446705116e-06, + "loss": 0.1727, + "step": 815 + }, + { + "epoch": 1.730983302411874, + "grad_norm": 2.6797003746032715, + "learning_rate": 1.920333763405428e-06, + "loss": 0.2671, + "step": 816 + }, + { + "epoch": 1.7331036310628147, + "grad_norm": 5.029034614562988, + "learning_rate": 1.914889788586133e-06, + "loss": 0.1879, + "step": 817 + }, + { + "epoch": 1.7352239597137555, + "grad_norm": 1.3859666585922241, + "learning_rate": 1.909448747508711e-06, + "loss": 0.2305, + "step": 818 + }, + { + "epoch": 1.7373442883646966, + "grad_norm": 1.9923025369644165, + "learning_rate": 1.9040106674545333e-06, + "loss": 0.3013, + "step": 819 + }, + { + "epoch": 1.7394646170156374, + "grad_norm": 2.2539119720458984, + "learning_rate": 1.898575575690128e-06, + "loss": 0.145, + "step": 820 + }, + { + "epoch": 1.7415849456665784, + "grad_norm": 1.2624527215957642, + "learning_rate": 1.8931434994670377e-06, + "loss": 0.2027, + "step": 821 + }, + { + "epoch": 1.7437052743175192, + "grad_norm": 1.10843825340271, + "learning_rate": 1.8877144660216867e-06, + "loss": 0.1941, + "step": 822 + }, + { + "epoch": 1.74582560296846, + "grad_norm": 1.4225454330444336, + "learning_rate": 1.8822885025752408e-06, + "loss": 0.2453, + "step": 823 + }, + { + "epoch": 1.747945931619401, + "grad_norm": 0.7526883482933044, + "learning_rate": 1.8768656363334759e-06, + "loss": 0.1622, + "step": 824 + }, + { + "epoch": 1.750066260270342, + "grad_norm": 0.6890954375267029, + "learning_rate": 1.8714458944866342e-06, + "loss": 0.1394, + "step": 825 + }, + { + "epoch": 1.7521865889212829, + "grad_norm": 1.9675222635269165, + "learning_rate": 1.8660293042092953e-06, + "loss": 0.165, + "step": 826 + }, + { + "epoch": 1.7543069175722237, + "grad_norm": 1.5908443927764893, + "learning_rate": 1.8606158926602368e-06, + "loss": 0.1421, + "step": 827 + }, + { + "epoch": 1.7564272462231645, + "grad_norm": 2.1363799571990967, + "learning_rate": 1.8552056869822968e-06, + "loss": 0.2401, + "step": 828 + }, + { + "epoch": 1.7585475748741055, + "grad_norm": 1.3258087635040283, + "learning_rate": 1.8497987143022405e-06, + "loss": 0.2401, + "step": 829 + }, + { + "epoch": 1.7606679035250465, + "grad_norm": 2.014814615249634, + "learning_rate": 1.8443950017306214e-06, + "loss": 0.2251, + "step": 830 + }, + { + "epoch": 1.7627882321759873, + "grad_norm": 0.8224743604660034, + "learning_rate": 1.8389945763616485e-06, + "loss": 0.113, + "step": 831 + }, + { + "epoch": 1.7649085608269282, + "grad_norm": 1.5032809972763062, + "learning_rate": 1.8335974652730467e-06, + "loss": 0.2415, + "step": 832 + }, + { + "epoch": 1.767028889477869, + "grad_norm": 2.1641783714294434, + "learning_rate": 1.8282036955259258e-06, + "loss": 0.2079, + "step": 833 + }, + { + "epoch": 1.76914921812881, + "grad_norm": 1.787461519241333, + "learning_rate": 1.8228132941646404e-06, + "loss": 0.2262, + "step": 834 + }, + { + "epoch": 1.771269546779751, + "grad_norm": 0.7867398858070374, + "learning_rate": 1.817426288216655e-06, + "loss": 0.2094, + "step": 835 + }, + { + "epoch": 1.7733898754306918, + "grad_norm": 1.3670313358306885, + "learning_rate": 1.8120427046924106e-06, + "loss": 0.1674, + "step": 836 + }, + { + "epoch": 1.7755102040816326, + "grad_norm": 1.9899623394012451, + "learning_rate": 1.8066625705851896e-06, + "loss": 0.255, + "step": 837 + }, + { + "epoch": 1.7776305327325734, + "grad_norm": 1.7844711542129517, + "learning_rate": 1.8012859128709766e-06, + "loss": 0.1705, + "step": 838 + }, + { + "epoch": 1.7797508613835145, + "grad_norm": 2.2082679271698, + "learning_rate": 1.7959127585083281e-06, + "loss": 0.3657, + "step": 839 + }, + { + "epoch": 1.7818711900344555, + "grad_norm": 3.0161192417144775, + "learning_rate": 1.7905431344382318e-06, + "loss": 0.1641, + "step": 840 + }, + { + "epoch": 1.7839915186853963, + "grad_norm": 2.1656365394592285, + "learning_rate": 1.7851770675839771e-06, + "loss": 0.2821, + "step": 841 + }, + { + "epoch": 1.786111847336337, + "grad_norm": 1.0514625310897827, + "learning_rate": 1.7798145848510162e-06, + "loss": 0.18, + "step": 842 + }, + { + "epoch": 1.788232175987278, + "grad_norm": 1.528306245803833, + "learning_rate": 1.7744557131268312e-06, + "loss": 0.2798, + "step": 843 + }, + { + "epoch": 1.790352504638219, + "grad_norm": 1.0451114177703857, + "learning_rate": 1.7691004792807976e-06, + "loss": 0.2194, + "step": 844 + }, + { + "epoch": 1.79247283328916, + "grad_norm": 1.3756572008132935, + "learning_rate": 1.7637489101640526e-06, + "loss": 0.1493, + "step": 845 + }, + { + "epoch": 1.7945931619401008, + "grad_norm": 2.324673652648926, + "learning_rate": 1.7584010326093554e-06, + "loss": 0.1907, + "step": 846 + }, + { + "epoch": 1.7967134905910416, + "grad_norm": 1.8477604389190674, + "learning_rate": 1.7530568734309578e-06, + "loss": 0.1661, + "step": 847 + }, + { + "epoch": 1.7988338192419824, + "grad_norm": 1.0166375637054443, + "learning_rate": 1.747716459424468e-06, + "loss": 0.1454, + "step": 848 + }, + { + "epoch": 1.8009541478929234, + "grad_norm": 1.7437880039215088, + "learning_rate": 1.7423798173667144e-06, + "loss": 0.1912, + "step": 849 + }, + { + "epoch": 1.8030744765438644, + "grad_norm": 0.8157974481582642, + "learning_rate": 1.7370469740156146e-06, + "loss": 0.1125, + "step": 850 + }, + { + "epoch": 1.8051948051948052, + "grad_norm": 1.758787989616394, + "learning_rate": 1.7317179561100372e-06, + "loss": 0.2471, + "step": 851 + }, + { + "epoch": 1.807315133845746, + "grad_norm": 1.253186821937561, + "learning_rate": 1.726392790369673e-06, + "loss": 0.1341, + "step": 852 + }, + { + "epoch": 1.8094354624966869, + "grad_norm": 0.8312148451805115, + "learning_rate": 1.7210715034948949e-06, + "loss": 0.1579, + "step": 853 + }, + { + "epoch": 1.8115557911476279, + "grad_norm": 0.9796281456947327, + "learning_rate": 1.7157541221666291e-06, + "loss": 0.0722, + "step": 854 + }, + { + "epoch": 1.813676119798569, + "grad_norm": 1.192187786102295, + "learning_rate": 1.7104406730462203e-06, + "loss": 0.1729, + "step": 855 + }, + { + "epoch": 1.8157964484495097, + "grad_norm": 1.2145785093307495, + "learning_rate": 1.705131182775294e-06, + "loss": 0.1131, + "step": 856 + }, + { + "epoch": 1.8179167771004505, + "grad_norm": 1.1818413734436035, + "learning_rate": 1.6998256779756279e-06, + "loss": 0.1515, + "step": 857 + }, + { + "epoch": 1.8200371057513913, + "grad_norm": 1.1990983486175537, + "learning_rate": 1.6945241852490173e-06, + "loss": 0.2163, + "step": 858 + }, + { + "epoch": 1.8221574344023324, + "grad_norm": 3.079540491104126, + "learning_rate": 1.6892267311771395e-06, + "loss": 0.1602, + "step": 859 + }, + { + "epoch": 1.8242777630532734, + "grad_norm": 1.5485817193984985, + "learning_rate": 1.6839333423214235e-06, + "loss": 0.2203, + "step": 860 + }, + { + "epoch": 1.8263980917042142, + "grad_norm": 2.226602554321289, + "learning_rate": 1.6786440452229134e-06, + "loss": 0.2015, + "step": 861 + }, + { + "epoch": 1.828518420355155, + "grad_norm": 1.1683058738708496, + "learning_rate": 1.673358866402139e-06, + "loss": 0.2026, + "step": 862 + }, + { + "epoch": 1.8306387490060958, + "grad_norm": 1.8131059408187866, + "learning_rate": 1.6680778323589798e-06, + "loss": 0.1659, + "step": 863 + }, + { + "epoch": 1.8327590776570368, + "grad_norm": 1.0971344709396362, + "learning_rate": 1.6628009695725348e-06, + "loss": 0.128, + "step": 864 + }, + { + "epoch": 1.8348794063079779, + "grad_norm": 2.1698126792907715, + "learning_rate": 1.657528304500986e-06, + "loss": 0.2637, + "step": 865 + }, + { + "epoch": 1.8369997349589187, + "grad_norm": 1.535143494606018, + "learning_rate": 1.6522598635814718e-06, + "loss": 0.1259, + "step": 866 + }, + { + "epoch": 1.8391200636098595, + "grad_norm": 1.4739115238189697, + "learning_rate": 1.6469956732299463e-06, + "loss": 0.2048, + "step": 867 + }, + { + "epoch": 1.8412403922608003, + "grad_norm": 0.9692105054855347, + "learning_rate": 1.6417357598410539e-06, + "loss": 0.1192, + "step": 868 + }, + { + "epoch": 1.8433607209117413, + "grad_norm": 1.028839349746704, + "learning_rate": 1.636480149787994e-06, + "loss": 0.1157, + "step": 869 + }, + { + "epoch": 1.8454810495626823, + "grad_norm": 1.9451359510421753, + "learning_rate": 1.6312288694223882e-06, + "loss": 0.1635, + "step": 870 + }, + { + "epoch": 1.8476013782136231, + "grad_norm": 1.6668827533721924, + "learning_rate": 1.6259819450741512e-06, + "loss": 0.234, + "step": 871 + }, + { + "epoch": 1.849721706864564, + "grad_norm": 0.971024751663208, + "learning_rate": 1.620739403051354e-06, + "loss": 0.1229, + "step": 872 + }, + { + "epoch": 1.8518420355155047, + "grad_norm": 2.122507095336914, + "learning_rate": 1.6155012696400959e-06, + "loss": 0.2016, + "step": 873 + }, + { + "epoch": 1.8539623641664458, + "grad_norm": 2.7607994079589844, + "learning_rate": 1.6102675711043719e-06, + "loss": 0.2195, + "step": 874 + }, + { + "epoch": 1.8560826928173868, + "grad_norm": 1.627505898475647, + "learning_rate": 1.6050383336859388e-06, + "loss": 0.2128, + "step": 875 + }, + { + "epoch": 1.8582030214683276, + "grad_norm": 2.6249325275421143, + "learning_rate": 1.599813583604188e-06, + "loss": 0.2381, + "step": 876 + }, + { + "epoch": 1.8603233501192684, + "grad_norm": 1.4043858051300049, + "learning_rate": 1.5945933470560097e-06, + "loss": 0.158, + "step": 877 + }, + { + "epoch": 1.8624436787702092, + "grad_norm": 2.1411776542663574, + "learning_rate": 1.5893776502156616e-06, + "loss": 0.1924, + "step": 878 + }, + { + "epoch": 1.8645640074211502, + "grad_norm": 0.7305095195770264, + "learning_rate": 1.5841665192346432e-06, + "loss": 0.201, + "step": 879 + }, + { + "epoch": 1.8666843360720913, + "grad_norm": 3.2844574451446533, + "learning_rate": 1.5789599802415572e-06, + "loss": 0.234, + "step": 880 + }, + { + "epoch": 1.868804664723032, + "grad_norm": 1.5105334520339966, + "learning_rate": 1.5737580593419854e-06, + "loss": 0.1891, + "step": 881 + }, + { + "epoch": 1.8709249933739729, + "grad_norm": 3.2038848400115967, + "learning_rate": 1.5685607826183514e-06, + "loss": 0.1912, + "step": 882 + }, + { + "epoch": 1.873045322024914, + "grad_norm": 1.120902180671692, + "learning_rate": 1.5633681761297948e-06, + "loss": 0.1075, + "step": 883 + }, + { + "epoch": 1.8751656506758547, + "grad_norm": 2.2855780124664307, + "learning_rate": 1.558180265912037e-06, + "loss": 0.1945, + "step": 884 + }, + { + "epoch": 1.8772859793267958, + "grad_norm": 1.1479313373565674, + "learning_rate": 1.5529970779772552e-06, + "loss": 0.1465, + "step": 885 + }, + { + "epoch": 1.8794063079777366, + "grad_norm": 1.4228770732879639, + "learning_rate": 1.5478186383139459e-06, + "loss": 0.2768, + "step": 886 + }, + { + "epoch": 1.8815266366286774, + "grad_norm": 1.2616146802902222, + "learning_rate": 1.5426449728868004e-06, + "loss": 0.2076, + "step": 887 + }, + { + "epoch": 1.8836469652796184, + "grad_norm": 2.149235248565674, + "learning_rate": 1.5374761076365695e-06, + "loss": 0.2828, + "step": 888 + }, + { + "epoch": 1.8857672939305592, + "grad_norm": 1.1656577587127686, + "learning_rate": 1.5323120684799374e-06, + "loss": 0.2031, + "step": 889 + }, + { + "epoch": 1.8878876225815002, + "grad_norm": 1.62466299533844, + "learning_rate": 1.5271528813093896e-06, + "loss": 0.2678, + "step": 890 + }, + { + "epoch": 1.890007951232441, + "grad_norm": 0.9776110053062439, + "learning_rate": 1.5219985719930851e-06, + "loss": 0.221, + "step": 891 + }, + { + "epoch": 1.8921282798833818, + "grad_norm": 0.5721087455749512, + "learning_rate": 1.5168491663747236e-06, + "loss": 0.1595, + "step": 892 + }, + { + "epoch": 1.8942486085343229, + "grad_norm": 1.2385927438735962, + "learning_rate": 1.5117046902734194e-06, + "loss": 0.2665, + "step": 893 + }, + { + "epoch": 1.8963689371852637, + "grad_norm": 1.5480061769485474, + "learning_rate": 1.5065651694835682e-06, + "loss": 0.1806, + "step": 894 + }, + { + "epoch": 1.8984892658362047, + "grad_norm": 1.9919331073760986, + "learning_rate": 1.5014306297747217e-06, + "loss": 0.2988, + "step": 895 + }, + { + "epoch": 1.9006095944871455, + "grad_norm": 0.4841969311237335, + "learning_rate": 1.4963010968914549e-06, + "loss": 0.1248, + "step": 896 + }, + { + "epoch": 1.9027299231380863, + "grad_norm": 2.00504994392395, + "learning_rate": 1.4911765965532398e-06, + "loss": 0.3798, + "step": 897 + }, + { + "epoch": 1.9048502517890273, + "grad_norm": 0.846325695514679, + "learning_rate": 1.4860571544543157e-06, + "loss": 0.2455, + "step": 898 + }, + { + "epoch": 1.9069705804399681, + "grad_norm": 1.6753747463226318, + "learning_rate": 1.480942796263556e-06, + "loss": 0.1762, + "step": 899 + }, + { + "epoch": 1.9090909090909092, + "grad_norm": 1.3008391857147217, + "learning_rate": 1.475833547624349e-06, + "loss": 0.3043, + "step": 900 + }, + { + "epoch": 1.91121123774185, + "grad_norm": 0.8818872570991516, + "learning_rate": 1.4707294341544598e-06, + "loss": 0.1608, + "step": 901 + }, + { + "epoch": 1.9133315663927908, + "grad_norm": 0.6332581639289856, + "learning_rate": 1.4656304814459077e-06, + "loss": 0.1494, + "step": 902 + }, + { + "epoch": 1.9154518950437318, + "grad_norm": 1.6962636709213257, + "learning_rate": 1.4605367150648341e-06, + "loss": 0.1819, + "step": 903 + }, + { + "epoch": 1.9175722236946728, + "grad_norm": 0.4807201623916626, + "learning_rate": 1.455448160551378e-06, + "loss": 0.1381, + "step": 904 + }, + { + "epoch": 1.9196925523456136, + "grad_norm": 1.2451565265655518, + "learning_rate": 1.4503648434195466e-06, + "loss": 0.1973, + "step": 905 + }, + { + "epoch": 1.9218128809965545, + "grad_norm": 1.3982090950012207, + "learning_rate": 1.445286789157084e-06, + "loss": 0.2893, + "step": 906 + }, + { + "epoch": 1.9239332096474953, + "grad_norm": 1.4739251136779785, + "learning_rate": 1.4402140232253486e-06, + "loss": 0.1968, + "step": 907 + }, + { + "epoch": 1.9260535382984363, + "grad_norm": 2.5440287590026855, + "learning_rate": 1.435146571059181e-06, + "loss": 0.1978, + "step": 908 + }, + { + "epoch": 1.9281738669493773, + "grad_norm": 3.4602210521698, + "learning_rate": 1.430084458066784e-06, + "loss": 0.2572, + "step": 909 + }, + { + "epoch": 1.9302941956003181, + "grad_norm": 0.7656342387199402, + "learning_rate": 1.4250277096295817e-06, + "loss": 0.1473, + "step": 910 + }, + { + "epoch": 1.932414524251259, + "grad_norm": 4.068082332611084, + "learning_rate": 1.4199763511021065e-06, + "loss": 0.2889, + "step": 911 + }, + { + "epoch": 1.9345348529021997, + "grad_norm": 0.7085794806480408, + "learning_rate": 1.4149304078118619e-06, + "loss": 0.1495, + "step": 912 + }, + { + "epoch": 1.9366551815531408, + "grad_norm": 0.3622530996799469, + "learning_rate": 1.4098899050592037e-06, + "loss": 0.1174, + "step": 913 + }, + { + "epoch": 1.9387755102040818, + "grad_norm": 1.3513684272766113, + "learning_rate": 1.404854868117206e-06, + "loss": 0.1357, + "step": 914 + }, + { + "epoch": 1.9408958388550226, + "grad_norm": 1.4065253734588623, + "learning_rate": 1.3998253222315363e-06, + "loss": 0.1929, + "step": 915 + }, + { + "epoch": 1.9430161675059634, + "grad_norm": 1.104533076286316, + "learning_rate": 1.394801292620332e-06, + "loss": 0.2133, + "step": 916 + }, + { + "epoch": 1.9451364961569042, + "grad_norm": 1.756828784942627, + "learning_rate": 1.389782804474072e-06, + "loss": 0.2032, + "step": 917 + }, + { + "epoch": 1.9472568248078452, + "grad_norm": 1.4066181182861328, + "learning_rate": 1.3847698829554496e-06, + "loss": 0.1907, + "step": 918 + }, + { + "epoch": 1.9493771534587863, + "grad_norm": 2.111950397491455, + "learning_rate": 1.3797625531992464e-06, + "loss": 0.2204, + "step": 919 + }, + { + "epoch": 1.951497482109727, + "grad_norm": 1.4993287324905396, + "learning_rate": 1.374760840312208e-06, + "loss": 0.2518, + "step": 920 + }, + { + "epoch": 1.9536178107606679, + "grad_norm": 0.8992859125137329, + "learning_rate": 1.3697647693729166e-06, + "loss": 0.1671, + "step": 921 + }, + { + "epoch": 1.9557381394116087, + "grad_norm": 0.6463199853897095, + "learning_rate": 1.3647743654316653e-06, + "loss": 0.1723, + "step": 922 + }, + { + "epoch": 1.9578584680625497, + "grad_norm": 0.7732374668121338, + "learning_rate": 1.3597896535103328e-06, + "loss": 0.1485, + "step": 923 + }, + { + "epoch": 1.9599787967134907, + "grad_norm": 1.8219809532165527, + "learning_rate": 1.3548106586022597e-06, + "loss": 0.1481, + "step": 924 + }, + { + "epoch": 1.9620991253644315, + "grad_norm": 2.0674850940704346, + "learning_rate": 1.3498374056721198e-06, + "loss": 0.2583, + "step": 925 + }, + { + "epoch": 1.9642194540153723, + "grad_norm": 2.160161256790161, + "learning_rate": 1.3448699196557973e-06, + "loss": 0.2165, + "step": 926 + }, + { + "epoch": 1.9663397826663132, + "grad_norm": 1.0526455640792847, + "learning_rate": 1.3399082254602594e-06, + "loss": 0.1807, + "step": 927 + }, + { + "epoch": 1.9684601113172542, + "grad_norm": 2.217966079711914, + "learning_rate": 1.3349523479634368e-06, + "loss": 0.249, + "step": 928 + }, + { + "epoch": 1.9705804399681952, + "grad_norm": 1.8820593357086182, + "learning_rate": 1.3300023120140926e-06, + "loss": 0.1337, + "step": 929 + }, + { + "epoch": 1.972700768619136, + "grad_norm": 2.38179349899292, + "learning_rate": 1.3250581424317012e-06, + "loss": 0.2563, + "step": 930 + }, + { + "epoch": 1.9748210972700768, + "grad_norm": 1.0373716354370117, + "learning_rate": 1.3201198640063196e-06, + "loss": 0.2068, + "step": 931 + }, + { + "epoch": 1.9769414259210176, + "grad_norm": 2.2542104721069336, + "learning_rate": 1.3151875014984734e-06, + "loss": 0.1813, + "step": 932 + }, + { + "epoch": 1.9790617545719587, + "grad_norm": 0.9453467130661011, + "learning_rate": 1.3102610796390209e-06, + "loss": 0.2077, + "step": 933 + }, + { + "epoch": 1.9811820832228997, + "grad_norm": 2.0382044315338135, + "learning_rate": 1.3053406231290348e-06, + "loss": 0.1782, + "step": 934 + }, + { + "epoch": 1.9833024118738405, + "grad_norm": 1.4644185304641724, + "learning_rate": 1.300426156639677e-06, + "loss": 0.2884, + "step": 935 + }, + { + "epoch": 1.9854227405247813, + "grad_norm": 1.245954990386963, + "learning_rate": 1.2955177048120786e-06, + "loss": 0.192, + "step": 936 + }, + { + "epoch": 1.987543069175722, + "grad_norm": 0.672512412071228, + "learning_rate": 1.2906152922572102e-06, + "loss": 0.1134, + "step": 937 + }, + { + "epoch": 1.9896633978266631, + "grad_norm": 1.7579939365386963, + "learning_rate": 1.2857189435557616e-06, + "loss": 0.1924, + "step": 938 + }, + { + "epoch": 1.9917837264776042, + "grad_norm": 1.3811734914779663, + "learning_rate": 1.2808286832580186e-06, + "loss": 0.2068, + "step": 939 + }, + { + "epoch": 1.993904055128545, + "grad_norm": 2.4520797729492188, + "learning_rate": 1.2759445358837419e-06, + "loss": 0.1122, + "step": 940 + }, + { + "epoch": 1.9960243837794858, + "grad_norm": 1.866734266281128, + "learning_rate": 1.2710665259220403e-06, + "loss": 0.2615, + "step": 941 + }, + { + "epoch": 1.9981447124304266, + "grad_norm": 1.1177961826324463, + "learning_rate": 1.2661946778312473e-06, + "loss": 0.1196, + "step": 942 + }, + { + "epoch": 2.0010601643254704, + "grad_norm": 1.9562182426452637, + "learning_rate": 1.2613290160388052e-06, + "loss": 0.2324, + "step": 943 + }, + { + "epoch": 2.003180492976411, + "grad_norm": 1.1798341274261475, + "learning_rate": 1.2564695649411363e-06, + "loss": 0.1671, + "step": 944 + }, + { + "epoch": 2.0053008216273525, + "grad_norm": 1.4037326574325562, + "learning_rate": 1.2516163489035216e-06, + "loss": 0.1219, + "step": 945 + }, + { + "epoch": 2.0074211502782933, + "grad_norm": 1.7019480466842651, + "learning_rate": 1.2467693922599805e-06, + "loss": 0.1258, + "step": 946 + }, + { + "epoch": 2.009541478929234, + "grad_norm": 1.0615661144256592, + "learning_rate": 1.2419287193131468e-06, + "loss": 0.2731, + "step": 947 + }, + { + "epoch": 2.011661807580175, + "grad_norm": 1.3318649530410767, + "learning_rate": 1.23709435433415e-06, + "loss": 0.151, + "step": 948 + }, + { + "epoch": 2.0137821362311157, + "grad_norm": 1.8564578294754028, + "learning_rate": 1.2322663215624898e-06, + "loss": 0.187, + "step": 949 + }, + { + "epoch": 2.015902464882057, + "grad_norm": 1.6483088731765747, + "learning_rate": 1.2274446452059158e-06, + "loss": 0.1094, + "step": 950 + }, + { + "epoch": 2.0180227935329977, + "grad_norm": 1.7207893133163452, + "learning_rate": 1.222629349440308e-06, + "loss": 0.2884, + "step": 951 + }, + { + "epoch": 2.0201431221839385, + "grad_norm": 1.4903310537338257, + "learning_rate": 1.2178204584095526e-06, + "loss": 0.1166, + "step": 952 + }, + { + "epoch": 2.0222634508348794, + "grad_norm": 2.676420211791992, + "learning_rate": 1.213017996225424e-06, + "loss": 0.2639, + "step": 953 + }, + { + "epoch": 2.02438377948582, + "grad_norm": 1.2780916690826416, + "learning_rate": 1.2082219869674603e-06, + "loss": 0.2392, + "step": 954 + }, + { + "epoch": 2.0265041081367614, + "grad_norm": 0.6168650984764099, + "learning_rate": 1.2034324546828477e-06, + "loss": 0.1054, + "step": 955 + }, + { + "epoch": 2.028624436787702, + "grad_norm": 1.404857873916626, + "learning_rate": 1.1986494233862948e-06, + "loss": 0.2579, + "step": 956 + }, + { + "epoch": 2.030744765438643, + "grad_norm": 2.3824305534362793, + "learning_rate": 1.1938729170599136e-06, + "loss": 0.1962, + "step": 957 + }, + { + "epoch": 2.032865094089584, + "grad_norm": 0.960718035697937, + "learning_rate": 1.1891029596531005e-06, + "loss": 0.139, + "step": 958 + }, + { + "epoch": 2.0349854227405246, + "grad_norm": 1.5871549844741821, + "learning_rate": 1.1843395750824183e-06, + "loss": 0.1442, + "step": 959 + }, + { + "epoch": 2.037105751391466, + "grad_norm": 1.264162540435791, + "learning_rate": 1.1795827872314694e-06, + "loss": 0.1862, + "step": 960 + }, + { + "epoch": 2.0392260800424067, + "grad_norm": 0.9427124261856079, + "learning_rate": 1.1748326199507829e-06, + "loss": 0.187, + "step": 961 + }, + { + "epoch": 2.0413464086933475, + "grad_norm": 1.307521939277649, + "learning_rate": 1.1700890970576914e-06, + "loss": 0.1043, + "step": 962 + }, + { + "epoch": 2.0434667373442883, + "grad_norm": 0.6865214109420776, + "learning_rate": 1.1653522423362129e-06, + "loss": 0.1359, + "step": 963 + }, + { + "epoch": 2.045587065995229, + "grad_norm": 1.6144641637802124, + "learning_rate": 1.1606220795369307e-06, + "loss": 0.1808, + "step": 964 + }, + { + "epoch": 2.0477073946461704, + "grad_norm": 0.6050888299942017, + "learning_rate": 1.1558986323768758e-06, + "loss": 0.1454, + "step": 965 + }, + { + "epoch": 2.049827723297111, + "grad_norm": 1.202744483947754, + "learning_rate": 1.1511819245394051e-06, + "loss": 0.1273, + "step": 966 + }, + { + "epoch": 2.051948051948052, + "grad_norm": 0.35640886425971985, + "learning_rate": 1.1464719796740875e-06, + "loss": 0.1516, + "step": 967 + }, + { + "epoch": 2.0540683805989928, + "grad_norm": 2.3331637382507324, + "learning_rate": 1.1417688213965803e-06, + "loss": 0.2406, + "step": 968 + }, + { + "epoch": 2.0561887092499336, + "grad_norm": 1.4808611869812012, + "learning_rate": 1.1370724732885126e-06, + "loss": 0.2046, + "step": 969 + }, + { + "epoch": 2.058309037900875, + "grad_norm": 0.8104944229125977, + "learning_rate": 1.1323829588973676e-06, + "loss": 0.1645, + "step": 970 + }, + { + "epoch": 2.0604293665518156, + "grad_norm": 1.5165859460830688, + "learning_rate": 1.1277003017363661e-06, + "loss": 0.1562, + "step": 971 + }, + { + "epoch": 2.0625496952027564, + "grad_norm": 1.645854115486145, + "learning_rate": 1.1230245252843456e-06, + "loss": 0.1089, + "step": 972 + }, + { + "epoch": 2.0646700238536972, + "grad_norm": 1.7471455335617065, + "learning_rate": 1.1183556529856404e-06, + "loss": 0.216, + "step": 973 + }, + { + "epoch": 2.066790352504638, + "grad_norm": 1.2812058925628662, + "learning_rate": 1.1136937082499733e-06, + "loss": 0.0965, + "step": 974 + }, + { + "epoch": 2.0689106811555793, + "grad_norm": 1.1503514051437378, + "learning_rate": 1.1090387144523284e-06, + "loss": 0.2348, + "step": 975 + }, + { + "epoch": 2.07103100980652, + "grad_norm": 1.0059962272644043, + "learning_rate": 1.1043906949328387e-06, + "loss": 0.1252, + "step": 976 + }, + { + "epoch": 2.073151338457461, + "grad_norm": 1.8063433170318604, + "learning_rate": 1.0997496729966679e-06, + "loss": 0.228, + "step": 977 + }, + { + "epoch": 2.0752716671084017, + "grad_norm": 1.0282273292541504, + "learning_rate": 1.0951156719138953e-06, + "loss": 0.1241, + "step": 978 + }, + { + "epoch": 2.0773919957593425, + "grad_norm": 1.623639464378357, + "learning_rate": 1.090488714919396e-06, + "loss": 0.1477, + "step": 979 + }, + { + "epoch": 2.0795123244102838, + "grad_norm": 1.7182891368865967, + "learning_rate": 1.0858688252127268e-06, + "loss": 0.1195, + "step": 980 + }, + { + "epoch": 2.0816326530612246, + "grad_norm": 1.336841344833374, + "learning_rate": 1.0812560259580076e-06, + "loss": 0.1273, + "step": 981 + }, + { + "epoch": 2.0837529817121654, + "grad_norm": 1.0584746599197388, + "learning_rate": 1.0766503402838103e-06, + "loss": 0.1584, + "step": 982 + }, + { + "epoch": 2.085873310363106, + "grad_norm": 2.303407669067383, + "learning_rate": 1.0720517912830371e-06, + "loss": 0.1586, + "step": 983 + }, + { + "epoch": 2.087993639014047, + "grad_norm": 1.6193451881408691, + "learning_rate": 1.0674604020128051e-06, + "loss": 0.1341, + "step": 984 + }, + { + "epoch": 2.0901139676649882, + "grad_norm": 1.0736302137374878, + "learning_rate": 1.0628761954943343e-06, + "loss": 0.1727, + "step": 985 + }, + { + "epoch": 2.092234296315929, + "grad_norm": 0.9856461882591248, + "learning_rate": 1.0582991947128324e-06, + "loss": 0.1506, + "step": 986 + }, + { + "epoch": 2.09435462496687, + "grad_norm": 0.495143324136734, + "learning_rate": 1.0537294226173748e-06, + "loss": 0.1112, + "step": 987 + }, + { + "epoch": 2.0964749536178107, + "grad_norm": 1.2475007772445679, + "learning_rate": 1.0491669021207929e-06, + "loss": 0.2002, + "step": 988 + }, + { + "epoch": 2.0985952822687515, + "grad_norm": 1.5196057558059692, + "learning_rate": 1.0446116560995582e-06, + "loss": 0.2054, + "step": 989 + }, + { + "epoch": 2.1007156109196927, + "grad_norm": 0.9226682186126709, + "learning_rate": 1.0400637073936697e-06, + "loss": 0.153, + "step": 990 + }, + { + "epoch": 2.1028359395706335, + "grad_norm": 0.7360610961914062, + "learning_rate": 1.0355230788065365e-06, + "loss": 0.1552, + "step": 991 + }, + { + "epoch": 2.1049562682215743, + "grad_norm": 0.5949102640151978, + "learning_rate": 1.030989793104864e-06, + "loss": 0.2001, + "step": 992 + }, + { + "epoch": 2.107076596872515, + "grad_norm": 0.2589457929134369, + "learning_rate": 1.0264638730185409e-06, + "loss": 0.1307, + "step": 993 + }, + { + "epoch": 2.109196925523456, + "grad_norm": 0.5593380928039551, + "learning_rate": 1.021945341240527e-06, + "loss": 0.1668, + "step": 994 + }, + { + "epoch": 2.111317254174397, + "grad_norm": 0.8510894775390625, + "learning_rate": 1.0174342204267323e-06, + "loss": 0.1635, + "step": 995 + }, + { + "epoch": 2.113437582825338, + "grad_norm": 2.4190611839294434, + "learning_rate": 1.012930533195911e-06, + "loss": 0.2443, + "step": 996 + }, + { + "epoch": 2.115557911476279, + "grad_norm": 1.0228517055511475, + "learning_rate": 1.0084343021295476e-06, + "loss": 0.1109, + "step": 997 + }, + { + "epoch": 2.1176782401272196, + "grad_norm": 1.9541192054748535, + "learning_rate": 1.0039455497717376e-06, + "loss": 0.1842, + "step": 998 + }, + { + "epoch": 2.1197985687781604, + "grad_norm": 1.7048015594482422, + "learning_rate": 9.994642986290797e-07, + "loss": 0.1828, + "step": 999 + }, + { + "epoch": 2.1219188974291017, + "grad_norm": 1.2028521299362183, + "learning_rate": 9.949905711705613e-07, + "loss": 0.1531, + "step": 1000 + }, + { + "epoch": 2.1240392260800425, + "grad_norm": 0.7890755534172058, + "learning_rate": 9.905243898274476e-07, + "loss": 0.1289, + "step": 1001 + }, + { + "epoch": 2.1261595547309833, + "grad_norm": 1.3331317901611328, + "learning_rate": 9.86065776993165e-07, + "loss": 0.1114, + "step": 1002 + }, + { + "epoch": 2.128279883381924, + "grad_norm": 1.6627100706100464, + "learning_rate": 9.816147550231936e-07, + "loss": 0.1902, + "step": 1003 + }, + { + "epoch": 2.130400212032865, + "grad_norm": 1.721989393234253, + "learning_rate": 9.771713462349517e-07, + "loss": 0.1395, + "step": 1004 + }, + { + "epoch": 2.132520540683806, + "grad_norm": 2.435530662536621, + "learning_rate": 9.727355729076848e-07, + "loss": 0.141, + "step": 1005 + }, + { + "epoch": 2.134640869334747, + "grad_norm": 1.3753666877746582, + "learning_rate": 9.683074572823558e-07, + "loss": 0.1943, + "step": 1006 + }, + { + "epoch": 2.1367611979856878, + "grad_norm": 0.669357419013977, + "learning_rate": 9.638870215615304e-07, + "loss": 0.0903, + "step": 1007 + }, + { + "epoch": 2.1388815266366286, + "grad_norm": 1.5727747678756714, + "learning_rate": 9.594742879092673e-07, + "loss": 0.1862, + "step": 1008 + }, + { + "epoch": 2.1410018552875694, + "grad_norm": 1.037684440612793, + "learning_rate": 9.550692784510085e-07, + "loss": 0.114, + "step": 1009 + }, + { + "epoch": 2.1431221839385106, + "grad_norm": 1.0889723300933838, + "learning_rate": 9.50672015273466e-07, + "loss": 0.1046, + "step": 1010 + }, + { + "epoch": 2.1452425125894514, + "grad_norm": 2.344956398010254, + "learning_rate": 9.462825204245113e-07, + "loss": 0.1864, + "step": 1011 + }, + { + "epoch": 2.1473628412403922, + "grad_norm": 0.6746013760566711, + "learning_rate": 9.419008159130658e-07, + "loss": 0.064, + "step": 1012 + }, + { + "epoch": 2.149483169891333, + "grad_norm": 1.1768742799758911, + "learning_rate": 9.375269237089915e-07, + "loss": 0.1237, + "step": 1013 + }, + { + "epoch": 2.151603498542274, + "grad_norm": 1.0476148128509521, + "learning_rate": 9.331608657429781e-07, + "loss": 0.1576, + "step": 1014 + }, + { + "epoch": 2.153723827193215, + "grad_norm": 1.505977749824524, + "learning_rate": 9.288026639064346e-07, + "loss": 0.1716, + "step": 1015 + }, + { + "epoch": 2.155844155844156, + "grad_norm": 1.6064363718032837, + "learning_rate": 9.244523400513797e-07, + "loss": 0.1497, + "step": 1016 + }, + { + "epoch": 2.1579644844950967, + "grad_norm": 0.21721459925174713, + "learning_rate": 9.201099159903318e-07, + "loss": 0.0957, + "step": 1017 + }, + { + "epoch": 2.1600848131460375, + "grad_norm": 1.4369566440582275, + "learning_rate": 9.157754134961997e-07, + "loss": 0.2541, + "step": 1018 + }, + { + "epoch": 2.1622051417969788, + "grad_norm": 2.7585020065307617, + "learning_rate": 9.114488543021724e-07, + "loss": 0.1664, + "step": 1019 + }, + { + "epoch": 2.1643254704479196, + "grad_norm": 2.044339179992676, + "learning_rate": 9.071302601016147e-07, + "loss": 0.2169, + "step": 1020 + }, + { + "epoch": 2.1664457990988604, + "grad_norm": 1.5984207391738892, + "learning_rate": 9.02819652547951e-07, + "loss": 0.1863, + "step": 1021 + }, + { + "epoch": 2.168566127749801, + "grad_norm": 0.9591246247291565, + "learning_rate": 8.985170532545623e-07, + "loss": 0.1827, + "step": 1022 + }, + { + "epoch": 2.170686456400742, + "grad_norm": 2.260664939880371, + "learning_rate": 8.942224837946767e-07, + "loss": 0.2556, + "step": 1023 + }, + { + "epoch": 2.172806785051683, + "grad_norm": 1.4247132539749146, + "learning_rate": 8.899359657012585e-07, + "loss": 0.1713, + "step": 1024 + }, + { + "epoch": 2.174927113702624, + "grad_norm": 0.177411288022995, + "learning_rate": 8.856575204669066e-07, + "loss": 0.1403, + "step": 1025 + }, + { + "epoch": 2.177047442353565, + "grad_norm": 1.4643137454986572, + "learning_rate": 8.813871695437392e-07, + "loss": 0.2385, + "step": 1026 + }, + { + "epoch": 2.1791677710045056, + "grad_norm": 0.7702186107635498, + "learning_rate": 8.771249343432886e-07, + "loss": 0.1823, + "step": 1027 + }, + { + "epoch": 2.1812880996554465, + "grad_norm": 1.4628134965896606, + "learning_rate": 8.728708362363991e-07, + "loss": 0.0917, + "step": 1028 + }, + { + "epoch": 2.1834084283063877, + "grad_norm": 1.2553027868270874, + "learning_rate": 8.686248965531124e-07, + "loss": 0.1308, + "step": 1029 + }, + { + "epoch": 2.1855287569573285, + "grad_norm": 1.879456639289856, + "learning_rate": 8.643871365825651e-07, + "loss": 0.181, + "step": 1030 + }, + { + "epoch": 2.1876490856082693, + "grad_norm": 0.45591041445732117, + "learning_rate": 8.601575775728793e-07, + "loss": 0.1376, + "step": 1031 + }, + { + "epoch": 2.18976941425921, + "grad_norm": 2.5236010551452637, + "learning_rate": 8.559362407310607e-07, + "loss": 0.1826, + "step": 1032 + }, + { + "epoch": 2.191889742910151, + "grad_norm": 1.757652997970581, + "learning_rate": 8.517231472228854e-07, + "loss": 0.2169, + "step": 1033 + }, + { + "epoch": 2.1940100715610917, + "grad_norm": 1.7674883604049683, + "learning_rate": 8.475183181727995e-07, + "loss": 0.2092, + "step": 1034 + }, + { + "epoch": 2.196130400212033, + "grad_norm": 1.4368592500686646, + "learning_rate": 8.433217746638098e-07, + "loss": 0.1093, + "step": 1035 + }, + { + "epoch": 2.198250728862974, + "grad_norm": 3.643383264541626, + "learning_rate": 8.391335377373825e-07, + "loss": 0.1931, + "step": 1036 + }, + { + "epoch": 2.2003710575139146, + "grad_norm": 1.120516300201416, + "learning_rate": 8.349536283933302e-07, + "loss": 0.226, + "step": 1037 + }, + { + "epoch": 2.2024913861648554, + "grad_norm": 1.6171327829360962, + "learning_rate": 8.307820675897127e-07, + "loss": 0.1644, + "step": 1038 + }, + { + "epoch": 2.2046117148157967, + "grad_norm": 0.962647557258606, + "learning_rate": 8.266188762427327e-07, + "loss": 0.1338, + "step": 1039 + }, + { + "epoch": 2.2067320434667375, + "grad_norm": 2.5459415912628174, + "learning_rate": 8.224640752266256e-07, + "loss": 0.2425, + "step": 1040 + }, + { + "epoch": 2.2088523721176783, + "grad_norm": 1.1007134914398193, + "learning_rate": 8.18317685373558e-07, + "loss": 0.0995, + "step": 1041 + }, + { + "epoch": 2.210972700768619, + "grad_norm": 1.3371065855026245, + "learning_rate": 8.141797274735242e-07, + "loss": 0.1023, + "step": 1042 + }, + { + "epoch": 2.21309302941956, + "grad_norm": 1.4020932912826538, + "learning_rate": 8.100502222742387e-07, + "loss": 0.2438, + "step": 1043 + }, + { + "epoch": 2.215213358070501, + "grad_norm": 0.8787581324577332, + "learning_rate": 8.059291904810373e-07, + "loss": 0.18, + "step": 1044 + }, + { + "epoch": 2.217333686721442, + "grad_norm": 2.061732292175293, + "learning_rate": 8.018166527567672e-07, + "loss": 0.1664, + "step": 1045 + }, + { + "epoch": 2.2194540153723827, + "grad_norm": 1.4549061059951782, + "learning_rate": 7.977126297216878e-07, + "loss": 0.1453, + "step": 1046 + }, + { + "epoch": 2.2215743440233235, + "grad_norm": 1.787046194076538, + "learning_rate": 7.936171419533653e-07, + "loss": 0.1826, + "step": 1047 + }, + { + "epoch": 2.2236946726742643, + "grad_norm": 1.2680433988571167, + "learning_rate": 7.895302099865701e-07, + "loss": 0.1264, + "step": 1048 + }, + { + "epoch": 2.2258150013252056, + "grad_norm": 1.716055989265442, + "learning_rate": 7.854518543131742e-07, + "loss": 0.1218, + "step": 1049 + }, + { + "epoch": 2.2279353299761464, + "grad_norm": 1.614372730255127, + "learning_rate": 7.813820953820469e-07, + "loss": 0.1772, + "step": 1050 + }, + { + "epoch": 2.230055658627087, + "grad_norm": 1.2348659038543701, + "learning_rate": 7.773209535989562e-07, + "loss": 0.2343, + "step": 1051 + }, + { + "epoch": 2.232175987278028, + "grad_norm": 0.6399396657943726, + "learning_rate": 7.732684493264611e-07, + "loss": 0.1654, + "step": 1052 + }, + { + "epoch": 2.234296315928969, + "grad_norm": 0.7470250129699707, + "learning_rate": 7.69224602883813e-07, + "loss": 0.1807, + "step": 1053 + }, + { + "epoch": 2.23641664457991, + "grad_norm": 1.0854237079620361, + "learning_rate": 7.651894345468522e-07, + "loss": 0.1645, + "step": 1054 + }, + { + "epoch": 2.238536973230851, + "grad_norm": 1.6901220083236694, + "learning_rate": 7.61162964547909e-07, + "loss": 0.1378, + "step": 1055 + }, + { + "epoch": 2.2406573018817917, + "grad_norm": 1.3711787462234497, + "learning_rate": 7.571452130756984e-07, + "loss": 0.2183, + "step": 1056 + }, + { + "epoch": 2.2427776305327325, + "grad_norm": 2.0862414836883545, + "learning_rate": 7.531362002752224e-07, + "loss": 0.184, + "step": 1057 + }, + { + "epoch": 2.2448979591836733, + "grad_norm": 1.5051991939544678, + "learning_rate": 7.491359462476632e-07, + "loss": 0.1685, + "step": 1058 + }, + { + "epoch": 2.2470182878346145, + "grad_norm": 1.7202171087265015, + "learning_rate": 7.451444710502923e-07, + "loss": 0.1379, + "step": 1059 + }, + { + "epoch": 2.2491386164855554, + "grad_norm": 1.7147220373153687, + "learning_rate": 7.411617946963604e-07, + "loss": 0.1665, + "step": 1060 + }, + { + "epoch": 2.251258945136496, + "grad_norm": 2.444573402404785, + "learning_rate": 7.371879371550017e-07, + "loss": 0.1337, + "step": 1061 + }, + { + "epoch": 2.253379273787437, + "grad_norm": 0.8904200792312622, + "learning_rate": 7.332229183511325e-07, + "loss": 0.3001, + "step": 1062 + }, + { + "epoch": 2.2554996024383778, + "grad_norm": 2.107675075531006, + "learning_rate": 7.292667581653537e-07, + "loss": 0.1673, + "step": 1063 + }, + { + "epoch": 2.257619931089319, + "grad_norm": 1.31276273727417, + "learning_rate": 7.253194764338465e-07, + "loss": 0.1727, + "step": 1064 + }, + { + "epoch": 2.25974025974026, + "grad_norm": 1.6621828079223633, + "learning_rate": 7.213810929482765e-07, + "loss": 0.1634, + "step": 1065 + }, + { + "epoch": 2.2618605883912006, + "grad_norm": 1.0999544858932495, + "learning_rate": 7.174516274556931e-07, + "loss": 0.2101, + "step": 1066 + }, + { + "epoch": 2.2639809170421414, + "grad_norm": 1.487066626548767, + "learning_rate": 7.13531099658433e-07, + "loss": 0.2167, + "step": 1067 + }, + { + "epoch": 2.2661012456930822, + "grad_norm": 1.1154425144195557, + "learning_rate": 7.096195292140173e-07, + "loss": 0.1175, + "step": 1068 + }, + { + "epoch": 2.2682215743440235, + "grad_norm": 1.7825549840927124, + "learning_rate": 7.057169357350535e-07, + "loss": 0.1834, + "step": 1069 + }, + { + "epoch": 2.2703419029949643, + "grad_norm": 2.048605442047119, + "learning_rate": 7.018233387891426e-07, + "loss": 0.0926, + "step": 1070 + }, + { + "epoch": 2.272462231645905, + "grad_norm": 1.7023017406463623, + "learning_rate": 6.97938757898774e-07, + "loss": 0.1592, + "step": 1071 + }, + { + "epoch": 2.274582560296846, + "grad_norm": 2.4371001720428467, + "learning_rate": 6.940632125412314e-07, + "loss": 0.1927, + "step": 1072 + }, + { + "epoch": 2.2767028889477867, + "grad_norm": 1.6496391296386719, + "learning_rate": 6.901967221484937e-07, + "loss": 0.2078, + "step": 1073 + }, + { + "epoch": 2.278823217598728, + "grad_norm": 0.7623432278633118, + "learning_rate": 6.863393061071407e-07, + "loss": 0.1582, + "step": 1074 + }, + { + "epoch": 2.2809435462496688, + "grad_norm": 1.767440915107727, + "learning_rate": 6.824909837582505e-07, + "loss": 0.1972, + "step": 1075 + }, + { + "epoch": 2.2830638749006096, + "grad_norm": 1.3551329374313354, + "learning_rate": 6.786517743973065e-07, + "loss": 0.1635, + "step": 1076 + }, + { + "epoch": 2.2851842035515504, + "grad_norm": 1.824154019355774, + "learning_rate": 6.748216972740992e-07, + "loss": 0.1746, + "step": 1077 + }, + { + "epoch": 2.2873045322024916, + "grad_norm": 1.9137120246887207, + "learning_rate": 6.71000771592632e-07, + "loss": 0.1611, + "step": 1078 + }, + { + "epoch": 2.2894248608534324, + "grad_norm": 1.8039703369140625, + "learning_rate": 6.671890165110214e-07, + "loss": 0.1905, + "step": 1079 + }, + { + "epoch": 2.2915451895043732, + "grad_norm": 1.7576533555984497, + "learning_rate": 6.633864511414015e-07, + "loss": 0.1512, + "step": 1080 + }, + { + "epoch": 2.293665518155314, + "grad_norm": 0.6087268590927124, + "learning_rate": 6.595930945498297e-07, + "loss": 0.1088, + "step": 1081 + }, + { + "epoch": 2.295785846806255, + "grad_norm": 0.9811050891876221, + "learning_rate": 6.558089657561931e-07, + "loss": 0.1399, + "step": 1082 + }, + { + "epoch": 2.2979061754571957, + "grad_norm": 2.133836507797241, + "learning_rate": 6.520340837341079e-07, + "loss": 0.231, + "step": 1083 + }, + { + "epoch": 2.300026504108137, + "grad_norm": 1.9858092069625854, + "learning_rate": 6.482684674108281e-07, + "loss": 0.1828, + "step": 1084 + }, + { + "epoch": 2.3021468327590777, + "grad_norm": 1.1744147539138794, + "learning_rate": 6.445121356671483e-07, + "loss": 0.1228, + "step": 1085 + }, + { + "epoch": 2.3042671614100185, + "grad_norm": 1.6011583805084229, + "learning_rate": 6.407651073373125e-07, + "loss": 0.1959, + "step": 1086 + }, + { + "epoch": 2.3063874900609593, + "grad_norm": 1.8023475408554077, + "learning_rate": 6.370274012089159e-07, + "loss": 0.1723, + "step": 1087 + }, + { + "epoch": 2.3085078187119006, + "grad_norm": 0.8929461240768433, + "learning_rate": 6.332990360228119e-07, + "loss": 0.1399, + "step": 1088 + }, + { + "epoch": 2.3106281473628414, + "grad_norm": 1.1111611127853394, + "learning_rate": 6.29580030473019e-07, + "loss": 0.124, + "step": 1089 + }, + { + "epoch": 2.312748476013782, + "grad_norm": 2.0618672370910645, + "learning_rate": 6.258704032066265e-07, + "loss": 0.2, + "step": 1090 + }, + { + "epoch": 2.314868804664723, + "grad_norm": 1.5747716426849365, + "learning_rate": 6.221701728237008e-07, + "loss": 0.2478, + "step": 1091 + }, + { + "epoch": 2.316989133315664, + "grad_norm": 1.6358662843704224, + "learning_rate": 6.184793578771919e-07, + "loss": 0.2235, + "step": 1092 + }, + { + "epoch": 2.3191094619666046, + "grad_norm": 1.1135793924331665, + "learning_rate": 6.147979768728427e-07, + "loss": 0.259, + "step": 1093 + }, + { + "epoch": 2.321229790617546, + "grad_norm": 1.4510762691497803, + "learning_rate": 6.11126048269092e-07, + "loss": 0.1029, + "step": 1094 + }, + { + "epoch": 2.3233501192684867, + "grad_norm": 1.924076795578003, + "learning_rate": 6.074635904769855e-07, + "loss": 0.2121, + "step": 1095 + }, + { + "epoch": 2.3254704479194275, + "grad_norm": 2.4901790618896484, + "learning_rate": 6.03810621860082e-07, + "loss": 0.1593, + "step": 1096 + }, + { + "epoch": 2.3275907765703683, + "grad_norm": 2.7300894260406494, + "learning_rate": 6.001671607343609e-07, + "loss": 0.2646, + "step": 1097 + }, + { + "epoch": 2.3297111052213095, + "grad_norm": 0.29893285036087036, + "learning_rate": 5.96533225368133e-07, + "loss": 0.0587, + "step": 1098 + }, + { + "epoch": 2.3318314338722503, + "grad_norm": 2.7989368438720703, + "learning_rate": 5.929088339819452e-07, + "loss": 0.2278, + "step": 1099 + }, + { + "epoch": 2.333951762523191, + "grad_norm": 1.3706281185150146, + "learning_rate": 5.892940047484915e-07, + "loss": 0.2335, + "step": 1100 + }, + { + "epoch": 2.336072091174132, + "grad_norm": 0.9056196808815002, + "learning_rate": 5.856887557925209e-07, + "loss": 0.1164, + "step": 1101 + }, + { + "epoch": 2.3381924198250728, + "grad_norm": 0.811579167842865, + "learning_rate": 5.820931051907471e-07, + "loss": 0.1564, + "step": 1102 + }, + { + "epoch": 2.3403127484760136, + "grad_norm": 1.3035115003585815, + "learning_rate": 5.785070709717583e-07, + "loss": 0.1035, + "step": 1103 + }, + { + "epoch": 2.342433077126955, + "grad_norm": 1.7552999258041382, + "learning_rate": 5.749306711159245e-07, + "loss": 0.1593, + "step": 1104 + }, + { + "epoch": 2.3445534057778956, + "grad_norm": 1.4544363021850586, + "learning_rate": 5.713639235553115e-07, + "loss": 0.2125, + "step": 1105 + }, + { + "epoch": 2.3466737344288364, + "grad_norm": 1.2122842073440552, + "learning_rate": 5.678068461735864e-07, + "loss": 0.2044, + "step": 1106 + }, + { + "epoch": 2.3487940630797772, + "grad_norm": 3.637741804122925, + "learning_rate": 5.642594568059309e-07, + "loss": 0.1786, + "step": 1107 + }, + { + "epoch": 2.3509143917307185, + "grad_norm": 1.0546187162399292, + "learning_rate": 5.607217732389503e-07, + "loss": 0.2013, + "step": 1108 + }, + { + "epoch": 2.3530347203816593, + "grad_norm": 0.7517843246459961, + "learning_rate": 5.571938132105867e-07, + "loss": 0.0689, + "step": 1109 + }, + { + "epoch": 2.3551550490326, + "grad_norm": 1.7113940715789795, + "learning_rate": 5.536755944100269e-07, + "loss": 0.1401, + "step": 1110 + }, + { + "epoch": 2.357275377683541, + "grad_norm": 0.45268720388412476, + "learning_rate": 5.501671344776152e-07, + "loss": 0.1351, + "step": 1111 + }, + { + "epoch": 2.3593957063344817, + "grad_norm": 1.2750608921051025, + "learning_rate": 5.466684510047659e-07, + "loss": 0.1929, + "step": 1112 + }, + { + "epoch": 2.3615160349854225, + "grad_norm": 1.2814080715179443, + "learning_rate": 5.43179561533873e-07, + "loss": 0.1553, + "step": 1113 + }, + { + "epoch": 2.3636363636363638, + "grad_norm": 0.29188236594200134, + "learning_rate": 5.397004835582242e-07, + "loss": 0.1258, + "step": 1114 + }, + { + "epoch": 2.3657566922873046, + "grad_norm": 1.2712785005569458, + "learning_rate": 5.362312345219125e-07, + "loss": 0.1353, + "step": 1115 + }, + { + "epoch": 2.3678770209382454, + "grad_norm": 1.9240132570266724, + "learning_rate": 5.327718318197469e-07, + "loss": 0.2128, + "step": 1116 + }, + { + "epoch": 2.369997349589186, + "grad_norm": 0.3361606299877167, + "learning_rate": 5.293222927971703e-07, + "loss": 0.0749, + "step": 1117 + }, + { + "epoch": 2.3721176782401274, + "grad_norm": 0.9936760663986206, + "learning_rate": 5.258826347501655e-07, + "loss": 0.2372, + "step": 1118 + }, + { + "epoch": 2.3742380068910682, + "grad_norm": 1.9898719787597656, + "learning_rate": 5.224528749251747e-07, + "loss": 0.1649, + "step": 1119 + }, + { + "epoch": 2.376358335542009, + "grad_norm": 2.3979244232177734, + "learning_rate": 5.190330305190081e-07, + "loss": 0.1553, + "step": 1120 + }, + { + "epoch": 2.37847866419295, + "grad_norm": 1.371147632598877, + "learning_rate": 5.156231186787633e-07, + "loss": 0.1436, + "step": 1121 + }, + { + "epoch": 2.3805989928438906, + "grad_norm": 2.101191759109497, + "learning_rate": 5.122231565017321e-07, + "loss": 0.1716, + "step": 1122 + }, + { + "epoch": 2.3827193214948315, + "grad_norm": 3.039147138595581, + "learning_rate": 5.088331610353209e-07, + "loss": 0.1668, + "step": 1123 + }, + { + "epoch": 2.3848396501457727, + "grad_norm": 1.054470181465149, + "learning_rate": 5.054531492769637e-07, + "loss": 0.1036, + "step": 1124 + }, + { + "epoch": 2.3869599787967135, + "grad_norm": 2.9882962703704834, + "learning_rate": 5.020831381740348e-07, + "loss": 0.1721, + "step": 1125 + }, + { + "epoch": 2.3890803074476543, + "grad_norm": 0.9891959428787231, + "learning_rate": 4.987231446237656e-07, + "loss": 0.0804, + "step": 1126 + }, + { + "epoch": 2.391200636098595, + "grad_norm": 1.865025520324707, + "learning_rate": 4.953731854731591e-07, + "loss": 0.1742, + "step": 1127 + }, + { + "epoch": 2.3933209647495364, + "grad_norm": 1.979583740234375, + "learning_rate": 4.920332775189074e-07, + "loss": 0.2472, + "step": 1128 + }, + { + "epoch": 2.395441293400477, + "grad_norm": 1.5632679462432861, + "learning_rate": 4.887034375073041e-07, + "loss": 0.1866, + "step": 1129 + }, + { + "epoch": 2.397561622051418, + "grad_norm": 0.98792564868927, + "learning_rate": 4.853836821341632e-07, + "loss": 0.0903, + "step": 1130 + }, + { + "epoch": 2.399681950702359, + "grad_norm": 1.7451393604278564, + "learning_rate": 4.820740280447331e-07, + "loss": 0.1345, + "step": 1131 + }, + { + "epoch": 2.4018022793532996, + "grad_norm": 1.910881757736206, + "learning_rate": 4.787744918336173e-07, + "loss": 0.1936, + "step": 1132 + }, + { + "epoch": 2.403922608004241, + "grad_norm": 1.0377843379974365, + "learning_rate": 4.7548509004468444e-07, + "loss": 0.1536, + "step": 1133 + }, + { + "epoch": 2.4060429366551817, + "grad_norm": 1.5963490009307861, + "learning_rate": 4.7220583917099135e-07, + "loss": 0.1719, + "step": 1134 + }, + { + "epoch": 2.4081632653061225, + "grad_norm": 1.8249528408050537, + "learning_rate": 4.6893675565469754e-07, + "loss": 0.1753, + "step": 1135 + }, + { + "epoch": 2.4102835939570633, + "grad_norm": 1.2173981666564941, + "learning_rate": 4.656778558869848e-07, + "loss": 0.1237, + "step": 1136 + }, + { + "epoch": 2.412403922608004, + "grad_norm": 2.324706554412842, + "learning_rate": 4.624291562079719e-07, + "loss": 0.1424, + "step": 1137 + }, + { + "epoch": 2.4145242512589453, + "grad_norm": 0.6716301441192627, + "learning_rate": 4.5919067290663503e-07, + "loss": 0.1932, + "step": 1138 + }, + { + "epoch": 2.416644579909886, + "grad_norm": 0.7555845379829407, + "learning_rate": 4.5596242222072457e-07, + "loss": 0.1664, + "step": 1139 + }, + { + "epoch": 2.418764908560827, + "grad_norm": 1.272320032119751, + "learning_rate": 4.527444203366868e-07, + "loss": 0.2251, + "step": 1140 + }, + { + "epoch": 2.4208852372117677, + "grad_norm": 1.8669896125793457, + "learning_rate": 4.4953668338957896e-07, + "loss": 0.1409, + "step": 1141 + }, + { + "epoch": 2.4230055658627085, + "grad_norm": 1.2830485105514526, + "learning_rate": 4.4633922746298965e-07, + "loss": 0.191, + "step": 1142 + }, + { + "epoch": 2.42512589451365, + "grad_norm": 1.8277826309204102, + "learning_rate": 4.431520685889587e-07, + "loss": 0.2368, + "step": 1143 + }, + { + "epoch": 2.4272462231645906, + "grad_norm": 0.8286747336387634, + "learning_rate": 4.3997522274789735e-07, + "loss": 0.1493, + "step": 1144 + }, + { + "epoch": 2.4293665518155314, + "grad_norm": 1.1364187002182007, + "learning_rate": 4.3680870586850636e-07, + "loss": 0.1692, + "step": 1145 + }, + { + "epoch": 2.431486880466472, + "grad_norm": 1.0993447303771973, + "learning_rate": 4.33652533827697e-07, + "loss": 0.1777, + "step": 1146 + }, + { + "epoch": 2.433607209117413, + "grad_norm": 1.555851697921753, + "learning_rate": 4.30506722450513e-07, + "loss": 0.1687, + "step": 1147 + }, + { + "epoch": 2.4357275377683543, + "grad_norm": 1.4744566679000854, + "learning_rate": 4.2737128751004804e-07, + "loss": 0.1453, + "step": 1148 + }, + { + "epoch": 2.437847866419295, + "grad_norm": 1.0803353786468506, + "learning_rate": 4.2424624472736904e-07, + "loss": 0.1837, + "step": 1149 + }, + { + "epoch": 2.439968195070236, + "grad_norm": 2.3968465328216553, + "learning_rate": 4.21131609771436e-07, + "loss": 0.1461, + "step": 1150 + }, + { + "epoch": 2.4420885237211767, + "grad_norm": 0.953355610370636, + "learning_rate": 4.1802739825902604e-07, + "loss": 0.1405, + "step": 1151 + }, + { + "epoch": 2.4442088523721175, + "grad_norm": 1.5285724401474, + "learning_rate": 4.149336257546513e-07, + "loss": 0.1662, + "step": 1152 + }, + { + "epoch": 2.4463291810230587, + "grad_norm": 1.5645101070404053, + "learning_rate": 4.1185030777048385e-07, + "loss": 0.1365, + "step": 1153 + }, + { + "epoch": 2.4484495096739995, + "grad_norm": 1.1964720487594604, + "learning_rate": 4.0877745976627416e-07, + "loss": 0.1012, + "step": 1154 + }, + { + "epoch": 2.4505698383249404, + "grad_norm": 0.9920772314071655, + "learning_rate": 4.0571509714928015e-07, + "loss": 0.16, + "step": 1155 + }, + { + "epoch": 2.452690166975881, + "grad_norm": 1.2442920207977295, + "learning_rate": 4.0266323527418384e-07, + "loss": 0.1339, + "step": 1156 + }, + { + "epoch": 2.454810495626822, + "grad_norm": 2.105613946914673, + "learning_rate": 3.996218894430165e-07, + "loss": 0.1725, + "step": 1157 + }, + { + "epoch": 2.456930824277763, + "grad_norm": 2.082643985748291, + "learning_rate": 3.965910749050822e-07, + "loss": 0.1981, + "step": 1158 + }, + { + "epoch": 2.459051152928704, + "grad_norm": 1.1390914916992188, + "learning_rate": 3.935708068568822e-07, + "loss": 0.1306, + "step": 1159 + }, + { + "epoch": 2.461171481579645, + "grad_norm": 2.3896877765655518, + "learning_rate": 3.9056110044203594e-07, + "loss": 0.1381, + "step": 1160 + }, + { + "epoch": 2.4632918102305856, + "grad_norm": 2.7147066593170166, + "learning_rate": 3.875619707512082e-07, + "loss": 0.1665, + "step": 1161 + }, + { + "epoch": 2.4654121388815264, + "grad_norm": 1.8762184381484985, + "learning_rate": 3.845734328220302e-07, + "loss": 0.153, + "step": 1162 + }, + { + "epoch": 2.4675324675324677, + "grad_norm": 1.4341996908187866, + "learning_rate": 3.8159550163902936e-07, + "loss": 0.2096, + "step": 1163 + }, + { + "epoch": 2.4696527961834085, + "grad_norm": 0.6933192014694214, + "learning_rate": 3.786281921335483e-07, + "loss": 0.1243, + "step": 1164 + }, + { + "epoch": 2.4717731248343493, + "grad_norm": 1.4996116161346436, + "learning_rate": 3.7567151918367156e-07, + "loss": 0.1478, + "step": 1165 + }, + { + "epoch": 2.47389345348529, + "grad_norm": 1.3368818759918213, + "learning_rate": 3.727254976141556e-07, + "loss": 0.1344, + "step": 1166 + }, + { + "epoch": 2.4760137821362314, + "grad_norm": 1.774940013885498, + "learning_rate": 3.697901421963482e-07, + "loss": 0.1596, + "step": 1167 + }, + { + "epoch": 2.478134110787172, + "grad_norm": 1.6905888319015503, + "learning_rate": 3.6686546764811787e-07, + "loss": 0.1897, + "step": 1168 + }, + { + "epoch": 2.480254439438113, + "grad_norm": 1.100188136100769, + "learning_rate": 3.639514886337786e-07, + "loss": 0.123, + "step": 1169 + }, + { + "epoch": 2.4823747680890538, + "grad_norm": 1.1606425046920776, + "learning_rate": 3.6104821976401834e-07, + "loss": 0.1602, + "step": 1170 + }, + { + "epoch": 2.4844950967399946, + "grad_norm": 0.8431051969528198, + "learning_rate": 3.581556755958232e-07, + "loss": 0.1281, + "step": 1171 + }, + { + "epoch": 2.4866154253909354, + "grad_norm": 3.2979464530944824, + "learning_rate": 3.552738706324063e-07, + "loss": 0.2761, + "step": 1172 + }, + { + "epoch": 2.4887357540418766, + "grad_norm": 1.7223345041275024, + "learning_rate": 3.524028193231338e-07, + "loss": 0.1354, + "step": 1173 + }, + { + "epoch": 2.4908560826928174, + "grad_norm": 0.983549952507019, + "learning_rate": 3.4954253606345386e-07, + "loss": 0.2041, + "step": 1174 + }, + { + "epoch": 2.4929764113437582, + "grad_norm": 3.322826385498047, + "learning_rate": 3.466930351948225e-07, + "loss": 0.1717, + "step": 1175 + }, + { + "epoch": 2.495096739994699, + "grad_norm": 1.789494514465332, + "learning_rate": 3.438543310046341e-07, + "loss": 0.2393, + "step": 1176 + }, + { + "epoch": 2.4972170686456403, + "grad_norm": 2.312497138977051, + "learning_rate": 3.4102643772614713e-07, + "loss": 0.2275, + "step": 1177 + }, + { + "epoch": 2.499337397296581, + "grad_norm": 1.2368191480636597, + "learning_rate": 3.3820936953841585e-07, + "loss": 0.1546, + "step": 1178 + }, + { + "epoch": 2.501457725947522, + "grad_norm": 1.659166932106018, + "learning_rate": 3.354031405662167e-07, + "loss": 0.1479, + "step": 1179 + }, + { + "epoch": 2.5035780545984627, + "grad_norm": 0.9831505417823792, + "learning_rate": 3.3260776487997803e-07, + "loss": 0.1361, + "step": 1180 + }, + { + "epoch": 2.5056983832494035, + "grad_norm": 2.298849105834961, + "learning_rate": 3.2982325649570907e-07, + "loss": 0.1951, + "step": 1181 + }, + { + "epoch": 2.5078187119003443, + "grad_norm": 0.6283709406852722, + "learning_rate": 3.2704962937493314e-07, + "loss": 0.0913, + "step": 1182 + }, + { + "epoch": 2.5099390405512856, + "grad_norm": 1.612980604171753, + "learning_rate": 3.2428689742461187e-07, + "loss": 0.182, + "step": 1183 + }, + { + "epoch": 2.5120593692022264, + "grad_norm": 0.8001376390457153, + "learning_rate": 3.215350744970808e-07, + "loss": 0.1474, + "step": 1184 + }, + { + "epoch": 2.514179697853167, + "grad_norm": 1.5370627641677856, + "learning_rate": 3.1879417438997583e-07, + "loss": 0.2535, + "step": 1185 + }, + { + "epoch": 2.516300026504108, + "grad_norm": 0.8482860922813416, + "learning_rate": 3.16064210846167e-07, + "loss": 0.0681, + "step": 1186 + }, + { + "epoch": 2.5184203551550493, + "grad_norm": 0.5224332213401794, + "learning_rate": 3.1334519755368805e-07, + "loss": 0.1279, + "step": 1187 + }, + { + "epoch": 2.52054068380599, + "grad_norm": 0.6476213932037354, + "learning_rate": 3.106371481456677e-07, + "loss": 0.1971, + "step": 1188 + }, + { + "epoch": 2.522661012456931, + "grad_norm": 2.0311484336853027, + "learning_rate": 3.079400762002635e-07, + "loss": 0.2494, + "step": 1189 + }, + { + "epoch": 2.5247813411078717, + "grad_norm": 1.1243444681167603, + "learning_rate": 3.0525399524059055e-07, + "loss": 0.183, + "step": 1190 + }, + { + "epoch": 2.5269016697588125, + "grad_norm": 0.8074027895927429, + "learning_rate": 3.025789187346548e-07, + "loss": 0.1433, + "step": 1191 + }, + { + "epoch": 2.5290219984097533, + "grad_norm": 2.325946092605591, + "learning_rate": 2.9991486009528696e-07, + "loss": 0.2281, + "step": 1192 + }, + { + "epoch": 2.5311423270606945, + "grad_norm": 1.595554232597351, + "learning_rate": 2.9726183268007304e-07, + "loss": 0.183, + "step": 1193 + }, + { + "epoch": 2.5332626557116353, + "grad_norm": 1.5321136713027954, + "learning_rate": 2.9461984979129056e-07, + "loss": 0.1823, + "step": 1194 + }, + { + "epoch": 2.535382984362576, + "grad_norm": 1.1611591577529907, + "learning_rate": 2.919889246758373e-07, + "loss": 0.1234, + "step": 1195 + }, + { + "epoch": 2.537503313013517, + "grad_norm": 2.7219529151916504, + "learning_rate": 2.8936907052516923e-07, + "loss": 0.2472, + "step": 1196 + }, + { + "epoch": 2.539623641664458, + "grad_norm": 1.3693172931671143, + "learning_rate": 2.8676030047523115e-07, + "loss": 0.1547, + "step": 1197 + }, + { + "epoch": 2.541743970315399, + "grad_norm": 0.7124255895614624, + "learning_rate": 2.841626276063933e-07, + "loss": 0.1421, + "step": 1198 + }, + { + "epoch": 2.54386429896634, + "grad_norm": 0.7943392992019653, + "learning_rate": 2.815760649433841e-07, + "loss": 0.0918, + "step": 1199 + }, + { + "epoch": 2.5459846276172806, + "grad_norm": 2.9632608890533447, + "learning_rate": 2.7900062545522493e-07, + "loss": 0.1396, + "step": 1200 + }, + { + "epoch": 2.5481049562682214, + "grad_norm": 0.6642888188362122, + "learning_rate": 2.764363220551672e-07, + "loss": 0.1228, + "step": 1201 + }, + { + "epoch": 2.5502252849191622, + "grad_norm": 1.34070885181427, + "learning_rate": 2.7388316760062457e-07, + "loss": 0.1093, + "step": 1202 + }, + { + "epoch": 2.5523456135701035, + "grad_norm": 1.1793408393859863, + "learning_rate": 2.7134117489311023e-07, + "loss": 0.1161, + "step": 1203 + }, + { + "epoch": 2.5544659422210443, + "grad_norm": 0.8148817420005798, + "learning_rate": 2.688103566781719e-07, + "loss": 0.087, + "step": 1204 + }, + { + "epoch": 2.556586270871985, + "grad_norm": 1.3565353155136108, + "learning_rate": 2.6629072564533007e-07, + "loss": 0.163, + "step": 1205 + }, + { + "epoch": 2.558706599522926, + "grad_norm": 0.799563467502594, + "learning_rate": 2.6378229442801163e-07, + "loss": 0.2213, + "step": 1206 + }, + { + "epoch": 2.560826928173867, + "grad_norm": 2.457230806350708, + "learning_rate": 2.6128507560348626e-07, + "loss": 0.1643, + "step": 1207 + }, + { + "epoch": 2.562947256824808, + "grad_norm": 1.6923904418945312, + "learning_rate": 2.5879908169280653e-07, + "loss": 0.1321, + "step": 1208 + }, + { + "epoch": 2.5650675854757488, + "grad_norm": 0.8046866655349731, + "learning_rate": 2.563243251607433e-07, + "loss": 0.1203, + "step": 1209 + }, + { + "epoch": 2.5671879141266896, + "grad_norm": 1.798595905303955, + "learning_rate": 2.538608184157229e-07, + "loss": 0.1767, + "step": 1210 + }, + { + "epoch": 2.5693082427776304, + "grad_norm": 0.4894849359989166, + "learning_rate": 2.5140857380976436e-07, + "loss": 0.1699, + "step": 1211 + }, + { + "epoch": 2.571428571428571, + "grad_norm": 0.8975478410720825, + "learning_rate": 2.489676036384192e-07, + "loss": 0.1116, + "step": 1212 + }, + { + "epoch": 2.5735489000795124, + "grad_norm": 0.9097894430160522, + "learning_rate": 2.4653792014070923e-07, + "loss": 0.1551, + "step": 1213 + }, + { + "epoch": 2.5756692287304532, + "grad_norm": 1.2728402614593506, + "learning_rate": 2.441195354990644e-07, + "loss": 0.1659, + "step": 1214 + }, + { + "epoch": 2.577789557381394, + "grad_norm": 0.8073611259460449, + "learning_rate": 2.4171246183926247e-07, + "loss": 0.1267, + "step": 1215 + }, + { + "epoch": 2.5799098860323353, + "grad_norm": 1.5247647762298584, + "learning_rate": 2.393167112303668e-07, + "loss": 0.2032, + "step": 1216 + }, + { + "epoch": 2.582030214683276, + "grad_norm": 1.960932970046997, + "learning_rate": 2.3693229568466952e-07, + "loss": 0.1342, + "step": 1217 + }, + { + "epoch": 2.584150543334217, + "grad_norm": 1.18437659740448, + "learning_rate": 2.345592271576261e-07, + "loss": 0.2205, + "step": 1218 + }, + { + "epoch": 2.5862708719851577, + "grad_norm": 1.630253791809082, + "learning_rate": 2.3219751754779862e-07, + "loss": 0.1616, + "step": 1219 + }, + { + "epoch": 2.5883912006360985, + "grad_norm": 1.5184342861175537, + "learning_rate": 2.2984717869679762e-07, + "loss": 0.0837, + "step": 1220 + }, + { + "epoch": 2.5905115292870393, + "grad_norm": 1.1323899030685425, + "learning_rate": 2.2750822238921861e-07, + "loss": 0.1858, + "step": 1221 + }, + { + "epoch": 2.59263185793798, + "grad_norm": 1.345180869102478, + "learning_rate": 2.251806603525855e-07, + "loss": 0.1615, + "step": 1222 + }, + { + "epoch": 2.5947521865889214, + "grad_norm": 2.1184494495391846, + "learning_rate": 2.228645042572908e-07, + "loss": 0.1641, + "step": 1223 + }, + { + "epoch": 2.596872515239862, + "grad_norm": 1.658331274986267, + "learning_rate": 2.2055976571653953e-07, + "loss": 0.1021, + "step": 1224 + }, + { + "epoch": 2.598992843890803, + "grad_norm": 1.2527090311050415, + "learning_rate": 2.1826645628628712e-07, + "loss": 0.1784, + "step": 1225 + }, + { + "epoch": 2.6011131725417442, + "grad_norm": 1.1310408115386963, + "learning_rate": 2.1598458746518448e-07, + "loss": 0.099, + "step": 1226 + }, + { + "epoch": 2.603233501192685, + "grad_norm": 1.2051087617874146, + "learning_rate": 2.1371417069451867e-07, + "loss": 0.1403, + "step": 1227 + }, + { + "epoch": 2.605353829843626, + "grad_norm": 1.2487993240356445, + "learning_rate": 2.1145521735815716e-07, + "loss": 0.0802, + "step": 1228 + }, + { + "epoch": 2.6074741584945667, + "grad_norm": 1.7651934623718262, + "learning_rate": 2.092077387824884e-07, + "loss": 0.2204, + "step": 1229 + }, + { + "epoch": 2.6095944871455075, + "grad_norm": 1.2847148180007935, + "learning_rate": 2.0697174623636795e-07, + "loss": 0.2012, + "step": 1230 + }, + { + "epoch": 2.6117148157964483, + "grad_norm": 1.5150816440582275, + "learning_rate": 2.0474725093105857e-07, + "loss": 0.1189, + "step": 1231 + }, + { + "epoch": 2.613835144447389, + "grad_norm": 2.1295809745788574, + "learning_rate": 2.025342640201783e-07, + "loss": 0.1462, + "step": 1232 + }, + { + "epoch": 2.6159554730983303, + "grad_norm": 2.1882126331329346, + "learning_rate": 2.003327965996399e-07, + "loss": 0.1963, + "step": 1233 + }, + { + "epoch": 2.618075801749271, + "grad_norm": 0.8546215891838074, + "learning_rate": 1.981428597075985e-07, + "loss": 0.1338, + "step": 1234 + }, + { + "epoch": 2.620196130400212, + "grad_norm": 2.6739611625671387, + "learning_rate": 1.9596446432439465e-07, + "loss": 0.1657, + "step": 1235 + }, + { + "epoch": 2.622316459051153, + "grad_norm": 1.686671495437622, + "learning_rate": 1.9379762137250069e-07, + "loss": 0.1489, + "step": 1236 + }, + { + "epoch": 2.624436787702094, + "grad_norm": 1.1274560689926147, + "learning_rate": 1.9164234171646423e-07, + "loss": 0.16, + "step": 1237 + }, + { + "epoch": 2.626557116353035, + "grad_norm": 1.799912691116333, + "learning_rate": 1.894986361628548e-07, + "loss": 0.149, + "step": 1238 + }, + { + "epoch": 2.6286774450039756, + "grad_norm": 0.9930972456932068, + "learning_rate": 1.8736651546020946e-07, + "loss": 0.1035, + "step": 1239 + }, + { + "epoch": 2.6307977736549164, + "grad_norm": 2.4395933151245117, + "learning_rate": 1.852459902989784e-07, + "loss": 0.1697, + "step": 1240 + }, + { + "epoch": 2.632918102305857, + "grad_norm": 1.3282368183135986, + "learning_rate": 1.8313707131147217e-07, + "loss": 0.1162, + "step": 1241 + }, + { + "epoch": 2.6350384309567985, + "grad_norm": 0.9472673535346985, + "learning_rate": 1.8103976907180798e-07, + "loss": 0.1021, + "step": 1242 + }, + { + "epoch": 2.6371587596077393, + "grad_norm": 1.8185752630233765, + "learning_rate": 1.789540940958573e-07, + "loss": 0.1861, + "step": 1243 + }, + { + "epoch": 2.63927908825868, + "grad_norm": 3.4913649559020996, + "learning_rate": 1.768800568411913e-07, + "loss": 0.1493, + "step": 1244 + }, + { + "epoch": 2.641399416909621, + "grad_norm": 1.3419857025146484, + "learning_rate": 1.7481766770703013e-07, + "loss": 0.1817, + "step": 1245 + }, + { + "epoch": 2.643519745560562, + "grad_norm": 1.4055255651474, + "learning_rate": 1.7276693703419058e-07, + "loss": 0.1297, + "step": 1246 + }, + { + "epoch": 2.645640074211503, + "grad_norm": 0.5878762006759644, + "learning_rate": 1.7072787510503313e-07, + "loss": 0.171, + "step": 1247 + }, + { + "epoch": 2.6477604028624437, + "grad_norm": 1.682094931602478, + "learning_rate": 1.6870049214341266e-07, + "loss": 0.2401, + "step": 1248 + }, + { + "epoch": 2.6498807315133845, + "grad_norm": 1.5442759990692139, + "learning_rate": 1.6668479831462498e-07, + "loss": 0.1526, + "step": 1249 + }, + { + "epoch": 2.6520010601643254, + "grad_norm": 2.29052734375, + "learning_rate": 1.6468080372535472e-07, + "loss": 0.1687, + "step": 1250 + }, + { + "epoch": 2.654121388815266, + "grad_norm": 1.219740390777588, + "learning_rate": 1.6268851842362988e-07, + "loss": 0.1425, + "step": 1251 + }, + { + "epoch": 2.6562417174662074, + "grad_norm": 0.8430941700935364, + "learning_rate": 1.607079523987662e-07, + "loss": 0.1047, + "step": 1252 + }, + { + "epoch": 2.658362046117148, + "grad_norm": 0.7257691621780396, + "learning_rate": 1.5873911558131866e-07, + "loss": 0.0906, + "step": 1253 + }, + { + "epoch": 2.660482374768089, + "grad_norm": 2.1663389205932617, + "learning_rate": 1.5678201784303293e-07, + "loss": 0.2841, + "step": 1254 + }, + { + "epoch": 2.66260270341903, + "grad_norm": 3.093027114868164, + "learning_rate": 1.548366689967948e-07, + "loss": 0.189, + "step": 1255 + }, + { + "epoch": 2.664723032069971, + "grad_norm": 1.9395819902420044, + "learning_rate": 1.52903078796581e-07, + "loss": 0.1188, + "step": 1256 + }, + { + "epoch": 2.666843360720912, + "grad_norm": 2.172022819519043, + "learning_rate": 1.5098125693741027e-07, + "loss": 0.1719, + "step": 1257 + }, + { + "epoch": 2.6689636893718527, + "grad_norm": 1.5533020496368408, + "learning_rate": 1.490712130552946e-07, + "loss": 0.1993, + "step": 1258 + }, + { + "epoch": 2.6710840180227935, + "grad_norm": 1.4032930135726929, + "learning_rate": 1.471729567271929e-07, + "loss": 0.0885, + "step": 1259 + }, + { + "epoch": 2.6732043466737343, + "grad_norm": 1.226884365081787, + "learning_rate": 1.4528649747095863e-07, + "loss": 0.1655, + "step": 1260 + }, + { + "epoch": 2.675324675324675, + "grad_norm": 0.9834424257278442, + "learning_rate": 1.4341184474529646e-07, + "loss": 0.1801, + "step": 1261 + }, + { + "epoch": 2.6774450039756164, + "grad_norm": 0.732979416847229, + "learning_rate": 1.4154900794971337e-07, + "loss": 0.094, + "step": 1262 + }, + { + "epoch": 2.679565332626557, + "grad_norm": 1.6163511276245117, + "learning_rate": 1.3969799642447047e-07, + "loss": 0.1391, + "step": 1263 + }, + { + "epoch": 2.681685661277498, + "grad_norm": 2.8434619903564453, + "learning_rate": 1.378588194505373e-07, + "loss": 0.1501, + "step": 1264 + }, + { + "epoch": 2.6838059899284388, + "grad_norm": 1.1843012571334839, + "learning_rate": 1.3603148624954488e-07, + "loss": 0.1566, + "step": 1265 + }, + { + "epoch": 2.68592631857938, + "grad_norm": 2.1769988536834717, + "learning_rate": 1.3421600598373886e-07, + "loss": 0.2451, + "step": 1266 + }, + { + "epoch": 2.688046647230321, + "grad_norm": 1.3834940195083618, + "learning_rate": 1.3241238775593634e-07, + "loss": 0.1454, + "step": 1267 + }, + { + "epoch": 2.6901669758812616, + "grad_norm": 1.287031650543213, + "learning_rate": 1.306206406094762e-07, + "loss": 0.1908, + "step": 1268 + }, + { + "epoch": 2.6922873045322024, + "grad_norm": 0.7013579607009888, + "learning_rate": 1.2884077352817659e-07, + "loss": 0.1143, + "step": 1269 + }, + { + "epoch": 2.6944076331831432, + "grad_norm": 2.7400264739990234, + "learning_rate": 1.2707279543628853e-07, + "loss": 0.1197, + "step": 1270 + }, + { + "epoch": 2.696527961834084, + "grad_norm": 0.6707156300544739, + "learning_rate": 1.2531671519845218e-07, + "loss": 0.1989, + "step": 1271 + }, + { + "epoch": 2.6986482904850253, + "grad_norm": 1.2751717567443848, + "learning_rate": 1.2357254161965176e-07, + "loss": 0.1403, + "step": 1272 + }, + { + "epoch": 2.700768619135966, + "grad_norm": 2.0241830348968506, + "learning_rate": 1.2184028344517096e-07, + "loss": 0.2304, + "step": 1273 + }, + { + "epoch": 2.702888947786907, + "grad_norm": 1.743528127670288, + "learning_rate": 1.2011994936055066e-07, + "loss": 0.1451, + "step": 1274 + }, + { + "epoch": 2.7050092764378477, + "grad_norm": 0.3977453410625458, + "learning_rate": 1.1841154799154376e-07, + "loss": 0.0898, + "step": 1275 + }, + { + "epoch": 2.707129605088789, + "grad_norm": 2.3948724269866943, + "learning_rate": 1.1671508790407238e-07, + "loss": 0.1182, + "step": 1276 + }, + { + "epoch": 2.7092499337397298, + "grad_norm": 1.9363933801651, + "learning_rate": 1.1503057760418518e-07, + "loss": 0.1747, + "step": 1277 + }, + { + "epoch": 2.7113702623906706, + "grad_norm": 2.442246198654175, + "learning_rate": 1.1335802553801512e-07, + "loss": 0.1696, + "step": 1278 + }, + { + "epoch": 2.7134905910416114, + "grad_norm": 1.0210362672805786, + "learning_rate": 1.1169744009173588e-07, + "loss": 0.1617, + "step": 1279 + }, + { + "epoch": 2.715610919692552, + "grad_norm": 1.444462776184082, + "learning_rate": 1.1004882959152085e-07, + "loss": 0.1001, + "step": 1280 + }, + { + "epoch": 2.717731248343493, + "grad_norm": 1.7707880735397339, + "learning_rate": 1.0841220230350142e-07, + "loss": 0.1711, + "step": 1281 + }, + { + "epoch": 2.7198515769944343, + "grad_norm": 1.8543199300765991, + "learning_rate": 1.0678756643372423e-07, + "loss": 0.0921, + "step": 1282 + }, + { + "epoch": 2.721971905645375, + "grad_norm": 1.4447288513183594, + "learning_rate": 1.0517493012811159e-07, + "loss": 0.1551, + "step": 1283 + }, + { + "epoch": 2.724092234296316, + "grad_norm": 1.2040534019470215, + "learning_rate": 1.0357430147242026e-07, + "loss": 0.1658, + "step": 1284 + }, + { + "epoch": 2.7262125629472567, + "grad_norm": 1.268929123878479, + "learning_rate": 1.0198568849219964e-07, + "loss": 0.1094, + "step": 1285 + }, + { + "epoch": 2.728332891598198, + "grad_norm": 1.3716996908187866, + "learning_rate": 1.0040909915275399e-07, + "loss": 0.2643, + "step": 1286 + }, + { + "epoch": 2.7304532202491387, + "grad_norm": 1.3784637451171875, + "learning_rate": 9.884454135910021e-08, + "loss": 0.0869, + "step": 1287 + }, + { + "epoch": 2.7325735489000795, + "grad_norm": 0.7445333003997803, + "learning_rate": 9.729202295592877e-08, + "loss": 0.1214, + "step": 1288 + }, + { + "epoch": 2.7346938775510203, + "grad_norm": 1.653314232826233, + "learning_rate": 9.575155172756506e-08, + "loss": 0.2651, + "step": 1289 + }, + { + "epoch": 2.736814206201961, + "grad_norm": 1.1880884170532227, + "learning_rate": 9.422313539793032e-08, + "loss": 0.0823, + "step": 1290 + }, + { + "epoch": 2.738934534852902, + "grad_norm": 1.2698768377304077, + "learning_rate": 9.270678163050218e-08, + "loss": 0.1873, + "step": 1291 + }, + { + "epoch": 2.741054863503843, + "grad_norm": 1.7306122779846191, + "learning_rate": 9.120249802827525e-08, + "loss": 0.2122, + "step": 1292 + }, + { + "epoch": 2.743175192154784, + "grad_norm": 1.6289342641830444, + "learning_rate": 8.971029213372729e-08, + "loss": 0.1604, + "step": 1293 + }, + { + "epoch": 2.745295520805725, + "grad_norm": 1.374562382698059, + "learning_rate": 8.823017142877587e-08, + "loss": 0.1293, + "step": 1294 + }, + { + "epoch": 2.747415849456666, + "grad_norm": 1.2182096242904663, + "learning_rate": 8.676214333474458e-08, + "loss": 0.1202, + "step": 1295 + }, + { + "epoch": 2.749536178107607, + "grad_norm": 0.7654268741607666, + "learning_rate": 8.530621521232435e-08, + "loss": 0.163, + "step": 1296 + }, + { + "epoch": 2.7516565067585477, + "grad_norm": 1.4261541366577148, + "learning_rate": 8.386239436153742e-08, + "loss": 0.1314, + "step": 1297 + }, + { + "epoch": 2.7537768354094885, + "grad_norm": 0.9270122647285461, + "learning_rate": 8.243068802169906e-08, + "loss": 0.1117, + "step": 1298 + }, + { + "epoch": 2.7558971640604293, + "grad_norm": 1.9634398221969604, + "learning_rate": 8.101110337138369e-08, + "loss": 0.2353, + "step": 1299 + }, + { + "epoch": 2.75801749271137, + "grad_norm": 1.8488718271255493, + "learning_rate": 7.96036475283865e-08, + "loss": 0.1271, + "step": 1300 + }, + { + "epoch": 2.760137821362311, + "grad_norm": 0.47494515776634216, + "learning_rate": 7.820832754968976e-08, + "loss": 0.1141, + "step": 1301 + }, + { + "epoch": 2.762258150013252, + "grad_norm": 1.7033765316009521, + "learning_rate": 7.682515043142602e-08, + "loss": 0.1758, + "step": 1302 + }, + { + "epoch": 2.764378478664193, + "grad_norm": 1.3400825262069702, + "learning_rate": 7.545412310884347e-08, + "loss": 0.0946, + "step": 1303 + }, + { + "epoch": 2.7664988073151338, + "grad_norm": 1.8070900440216064, + "learning_rate": 7.409525245627103e-08, + "loss": 0.1267, + "step": 1304 + }, + { + "epoch": 2.768619135966075, + "grad_norm": 1.3982330560684204, + "learning_rate": 7.27485452870852e-08, + "loss": 0.1801, + "step": 1305 + }, + { + "epoch": 2.770739464617016, + "grad_norm": 1.0061707496643066, + "learning_rate": 7.141400835367379e-08, + "loss": 0.165, + "step": 1306 + }, + { + "epoch": 2.7728597932679566, + "grad_norm": 0.810421884059906, + "learning_rate": 7.009164834740318e-08, + "loss": 0.1933, + "step": 1307 + }, + { + "epoch": 2.7749801219188974, + "grad_norm": 4.0556535720825195, + "learning_rate": 6.878147189858464e-08, + "loss": 0.1828, + "step": 1308 + }, + { + "epoch": 2.7771004505698382, + "grad_norm": 1.9069404602050781, + "learning_rate": 6.748348557644169e-08, + "loss": 0.1831, + "step": 1309 + }, + { + "epoch": 2.779220779220779, + "grad_norm": 1.4549925327301025, + "learning_rate": 6.619769588907588e-08, + "loss": 0.2365, + "step": 1310 + }, + { + "epoch": 2.78134110787172, + "grad_norm": 1.3765535354614258, + "learning_rate": 6.492410928343545e-08, + "loss": 0.1281, + "step": 1311 + }, + { + "epoch": 2.783461436522661, + "grad_norm": 1.1901353597640991, + "learning_rate": 6.366273214528124e-08, + "loss": 0.1193, + "step": 1312 + }, + { + "epoch": 2.785581765173602, + "grad_norm": 0.7537523508071899, + "learning_rate": 6.241357079915771e-08, + "loss": 0.0859, + "step": 1313 + }, + { + "epoch": 2.7877020938245427, + "grad_norm": 2.4557838439941406, + "learning_rate": 6.117663150835756e-08, + "loss": 0.1035, + "step": 1314 + }, + { + "epoch": 2.789822422475484, + "grad_norm": 1.539157509803772, + "learning_rate": 5.995192047489301e-08, + "loss": 0.1114, + "step": 1315 + }, + { + "epoch": 2.7919427511264248, + "grad_norm": 0.7973776459693909, + "learning_rate": 5.8739443839463675e-08, + "loss": 0.0927, + "step": 1316 + }, + { + "epoch": 2.7940630797773656, + "grad_norm": 1.1481491327285767, + "learning_rate": 5.7539207681426015e-08, + "loss": 0.1889, + "step": 1317 + }, + { + "epoch": 2.7961834084283064, + "grad_norm": 1.7523208856582642, + "learning_rate": 5.635121801876253e-08, + "loss": 0.201, + "step": 1318 + }, + { + "epoch": 2.798303737079247, + "grad_norm": 0.6877788305282593, + "learning_rate": 5.5175480808051515e-08, + "loss": 0.1615, + "step": 1319 + }, + { + "epoch": 2.800424065730188, + "grad_norm": 7.792228698730469, + "learning_rate": 5.401200194443873e-08, + "loss": 0.1195, + "step": 1320 + }, + { + "epoch": 2.8025443943811292, + "grad_norm": 1.1625345945358276, + "learning_rate": 5.2860787261605485e-08, + "loss": 0.1593, + "step": 1321 + }, + { + "epoch": 2.80466472303207, + "grad_norm": 1.4142205715179443, + "learning_rate": 5.172184253174034e-08, + "loss": 0.0893, + "step": 1322 + }, + { + "epoch": 2.806785051683011, + "grad_norm": 2.7474701404571533, + "learning_rate": 5.059517346551107e-08, + "loss": 0.2956, + "step": 1323 + }, + { + "epoch": 2.8089053803339517, + "grad_norm": 2.946167469024658, + "learning_rate": 4.948078571203496e-08, + "loss": 0.1717, + "step": 1324 + }, + { + "epoch": 2.811025708984893, + "grad_norm": 1.3838998079299927, + "learning_rate": 4.83786848588505e-08, + "loss": 0.0977, + "step": 1325 + }, + { + "epoch": 2.8131460376358337, + "grad_norm": 1.9812895059585571, + "learning_rate": 4.728887643189073e-08, + "loss": 0.1553, + "step": 1326 + }, + { + "epoch": 2.8152663662867745, + "grad_norm": 2.396117687225342, + "learning_rate": 4.621136589545272e-08, + "loss": 0.1686, + "step": 1327 + }, + { + "epoch": 2.8173866949377153, + "grad_norm": 1.9404491186141968, + "learning_rate": 4.5146158652173696e-08, + "loss": 0.1846, + "step": 1328 + }, + { + "epoch": 2.819507023588656, + "grad_norm": 0.7136148810386658, + "learning_rate": 4.4093260043001626e-08, + "loss": 0.1363, + "step": 1329 + }, + { + "epoch": 2.821627352239597, + "grad_norm": 1.5374301671981812, + "learning_rate": 4.305267534716828e-08, + "loss": 0.1339, + "step": 1330 + }, + { + "epoch": 2.823747680890538, + "grad_norm": 1.3492411375045776, + "learning_rate": 4.202440978216399e-08, + "loss": 0.1288, + "step": 1331 + }, + { + "epoch": 2.825868009541479, + "grad_norm": 1.5458908081054688, + "learning_rate": 4.1008468503711266e-08, + "loss": 0.1397, + "step": 1332 + }, + { + "epoch": 2.82798833819242, + "grad_norm": 0.7465994358062744, + "learning_rate": 4.000485660573872e-08, + "loss": 0.1248, + "step": 1333 + }, + { + "epoch": 2.8301086668433606, + "grad_norm": 1.4333218336105347, + "learning_rate": 3.9013579120354696e-08, + "loss": 0.1981, + "step": 1334 + }, + { + "epoch": 2.832228995494302, + "grad_norm": 1.3847651481628418, + "learning_rate": 3.803464101782367e-08, + "loss": 0.1387, + "step": 1335 + }, + { + "epoch": 2.8343493241452427, + "grad_norm": 1.7092586755752563, + "learning_rate": 3.706804720653962e-08, + "loss": 0.1013, + "step": 1336 + }, + { + "epoch": 2.8364696527961835, + "grad_norm": 0.910914957523346, + "learning_rate": 3.611380253300267e-08, + "loss": 0.2936, + "step": 1337 + }, + { + "epoch": 2.8385899814471243, + "grad_norm": 0.823289692401886, + "learning_rate": 3.517191178179474e-08, + "loss": 0.1551, + "step": 1338 + }, + { + "epoch": 2.840710310098065, + "grad_norm": 1.4775550365447998, + "learning_rate": 3.4242379675555046e-08, + "loss": 0.1314, + "step": 1339 + }, + { + "epoch": 2.842830638749006, + "grad_norm": 1.5959218740463257, + "learning_rate": 3.332521087495627e-08, + "loss": 0.1936, + "step": 1340 + }, + { + "epoch": 2.844950967399947, + "grad_norm": 1.1180788278579712, + "learning_rate": 3.242040997868123e-08, + "loss": 0.1696, + "step": 1341 + }, + { + "epoch": 2.847071296050888, + "grad_norm": 1.3411235809326172, + "learning_rate": 3.1527981523400974e-08, + "loss": 0.0762, + "step": 1342 + }, + { + "epoch": 2.8491916247018287, + "grad_norm": 1.4830942153930664, + "learning_rate": 3.064792998375032e-08, + "loss": 0.1341, + "step": 1343 + }, + { + "epoch": 2.8513119533527695, + "grad_norm": 1.154703140258789, + "learning_rate": 2.9780259772307362e-08, + "loss": 0.1482, + "step": 1344 + }, + { + "epoch": 2.853432282003711, + "grad_norm": 2.1193814277648926, + "learning_rate": 2.8924975239568444e-08, + "loss": 0.136, + "step": 1345 + }, + { + "epoch": 2.8555526106546516, + "grad_norm": 1.6052285432815552, + "learning_rate": 2.8082080673929312e-08, + "loss": 0.1296, + "step": 1346 + }, + { + "epoch": 2.8576729393055924, + "grad_norm": 1.887386441230774, + "learning_rate": 2.7251580301662916e-08, + "loss": 0.1119, + "step": 1347 + }, + { + "epoch": 2.859793267956533, + "grad_norm": 2.486104726791382, + "learning_rate": 2.643347828689663e-08, + "loss": 0.1892, + "step": 1348 + }, + { + "epoch": 2.861913596607474, + "grad_norm": 1.018723726272583, + "learning_rate": 2.562777873159311e-08, + "loss": 0.1666, + "step": 1349 + }, + { + "epoch": 2.864033925258415, + "grad_norm": 1.8284214735031128, + "learning_rate": 2.4834485675528653e-08, + "loss": 0.1364, + "step": 1350 + }, + { + "epoch": 2.866154253909356, + "grad_norm": 1.6964608430862427, + "learning_rate": 2.4053603096274027e-08, + "loss": 0.1658, + "step": 1351 + }, + { + "epoch": 2.868274582560297, + "grad_norm": 2.2789952754974365, + "learning_rate": 2.3285134909173113e-08, + "loss": 0.1677, + "step": 1352 + }, + { + "epoch": 2.8703949112112377, + "grad_norm": 1.1281884908676147, + "learning_rate": 2.2529084967324867e-08, + "loss": 0.1026, + "step": 1353 + }, + { + "epoch": 2.8725152398621785, + "grad_norm": 1.7842395305633545, + "learning_rate": 2.178545706156221e-08, + "loss": 0.1761, + "step": 1354 + }, + { + "epoch": 2.8746355685131197, + "grad_norm": 4.740082263946533, + "learning_rate": 2.105425492043539e-08, + "loss": 0.2169, + "step": 1355 + }, + { + "epoch": 2.8767558971640605, + "grad_norm": 1.7496134042739868, + "learning_rate": 2.0335482210190327e-08, + "loss": 0.199, + "step": 1356 + }, + { + "epoch": 2.8788762258150014, + "grad_norm": 1.1270558834075928, + "learning_rate": 1.962914253475251e-08, + "loss": 0.1348, + "step": 1357 + }, + { + "epoch": 2.880996554465942, + "grad_norm": 1.2198997735977173, + "learning_rate": 1.893523943570841e-08, + "loss": 0.0994, + "step": 1358 + }, + { + "epoch": 2.883116883116883, + "grad_norm": 1.9801288843154907, + "learning_rate": 1.8253776392287147e-08, + "loss": 0.1815, + "step": 1359 + }, + { + "epoch": 2.8852372117678238, + "grad_norm": 1.704171061515808, + "learning_rate": 1.7584756821343864e-08, + "loss": 0.1956, + "step": 1360 + }, + { + "epoch": 2.887357540418765, + "grad_norm": 1.9090226888656616, + "learning_rate": 1.692818407734165e-08, + "loss": 0.1832, + "step": 1361 + }, + { + "epoch": 2.889477869069706, + "grad_norm": 1.2632900476455688, + "learning_rate": 1.6284061452335464e-08, + "loss": 0.2045, + "step": 1362 + }, + { + "epoch": 2.8915981977206466, + "grad_norm": 1.6799594163894653, + "learning_rate": 1.565239217595549e-08, + "loss": 0.1563, + "step": 1363 + }, + { + "epoch": 2.8937185263715874, + "grad_norm": 0.9902015924453735, + "learning_rate": 1.5033179415390176e-08, + "loss": 0.1395, + "step": 1364 + }, + { + "epoch": 2.8958388550225287, + "grad_norm": 1.852407455444336, + "learning_rate": 1.4426426275372385e-08, + "loss": 0.1354, + "step": 1365 + }, + { + "epoch": 2.8979591836734695, + "grad_norm": 1.5521894693374634, + "learning_rate": 1.3832135798160783e-08, + "loss": 0.1807, + "step": 1366 + }, + { + "epoch": 2.9000795123244103, + "grad_norm": 4.004573822021484, + "learning_rate": 1.3250310963527358e-08, + "loss": 0.2193, + "step": 1367 + }, + { + "epoch": 2.902199840975351, + "grad_norm": 1.0895882844924927, + "learning_rate": 1.268095468874131e-08, + "loss": 0.1427, + "step": 1368 + }, + { + "epoch": 2.904320169626292, + "grad_norm": 1.187664270401001, + "learning_rate": 1.2124069828554075e-08, + "loss": 0.1666, + "step": 1369 + }, + { + "epoch": 2.9064404982772327, + "grad_norm": 1.6270695924758911, + "learning_rate": 1.1579659175185998e-08, + "loss": 0.1087, + "step": 1370 + }, + { + "epoch": 2.908560826928174, + "grad_norm": 1.6206939220428467, + "learning_rate": 1.1047725458310788e-08, + "loss": 0.1042, + "step": 1371 + }, + { + "epoch": 2.9106811555791148, + "grad_norm": 0.5481939315795898, + "learning_rate": 1.0528271345044139e-08, + "loss": 0.123, + "step": 1372 + }, + { + "epoch": 2.9128014842300556, + "grad_norm": 1.871779441833496, + "learning_rate": 1.0021299439927635e-08, + "loss": 0.2518, + "step": 1373 + }, + { + "epoch": 2.914921812880997, + "grad_norm": 1.5158265829086304, + "learning_rate": 9.526812284918196e-09, + "loss": 0.1938, + "step": 1374 + }, + { + "epoch": 2.9170421415319376, + "grad_norm": 1.6060808897018433, + "learning_rate": 9.044812359373933e-09, + "loss": 0.1524, + "step": 1375 + }, + { + "epoch": 2.9191624701828784, + "grad_norm": 1.282213807106018, + "learning_rate": 8.575302080041648e-09, + "loss": 0.0865, + "step": 1376 + }, + { + "epoch": 2.9212827988338192, + "grad_norm": 1.064220666885376, + "learning_rate": 8.118283801045179e-09, + "loss": 0.1245, + "step": 1377 + }, + { + "epoch": 2.92340312748476, + "grad_norm": 1.623093605041504, + "learning_rate": 7.673759813873749e-09, + "loss": 0.1392, + "step": 1378 + }, + { + "epoch": 2.925523456135701, + "grad_norm": 1.3206197023391724, + "learning_rate": 7.2417323473703005e-09, + "loss": 0.1392, + "step": 1379 + }, + { + "epoch": 2.9276437847866417, + "grad_norm": 1.0642672777175903, + "learning_rate": 6.8222035677195655e-09, + "loss": 0.1728, + "step": 1380 + }, + { + "epoch": 2.929764113437583, + "grad_norm": 1.2734618186950684, + "learning_rate": 6.415175578438626e-09, + "loss": 0.1577, + "step": 1381 + }, + { + "epoch": 2.9318844420885237, + "grad_norm": 1.2089275121688843, + "learning_rate": 6.0206504203652595e-09, + "loss": 0.1659, + "step": 1382 + }, + { + "epoch": 2.9340047707394645, + "grad_norm": 1.001374363899231, + "learning_rate": 5.638630071648221e-09, + "loss": 0.1507, + "step": 1383 + }, + { + "epoch": 2.936125099390406, + "grad_norm": 2.069044589996338, + "learning_rate": 5.2691164477367e-09, + "loss": 0.1365, + "step": 1384 + }, + { + "epoch": 2.9382454280413466, + "grad_norm": 1.3570106029510498, + "learning_rate": 4.9121114013719886e-09, + "loss": 0.1626, + "step": 1385 + }, + { + "epoch": 2.9403657566922874, + "grad_norm": 0.8516995906829834, + "learning_rate": 4.5676167225766625e-09, + "loss": 0.1482, + "step": 1386 + }, + { + "epoch": 2.942486085343228, + "grad_norm": 2.186077117919922, + "learning_rate": 4.2356341386468045e-09, + "loss": 0.1666, + "step": 1387 + }, + { + "epoch": 2.944606413994169, + "grad_norm": 1.2149814367294312, + "learning_rate": 3.916165314142295e-09, + "loss": 0.1035, + "step": 1388 + }, + { + "epoch": 2.94672674264511, + "grad_norm": 1.4955745935440063, + "learning_rate": 3.609211850879868e-09, + "loss": 0.1345, + "step": 1389 + }, + { + "epoch": 2.9488470712960506, + "grad_norm": 0.9449958801269531, + "learning_rate": 3.3147752879236773e-09, + "loss": 0.1287, + "step": 1390 + }, + { + "epoch": 2.950967399946992, + "grad_norm": 1.2510886192321777, + "learning_rate": 3.032857101578357e-09, + "loss": 0.1304, + "step": 1391 + }, + { + "epoch": 2.9530877285979327, + "grad_norm": 2.1328423023223877, + "learning_rate": 2.7634587053809723e-09, + "loss": 0.1966, + "step": 1392 + }, + { + "epoch": 2.9552080572488735, + "grad_norm": 2.7924039363861084, + "learning_rate": 2.5065814500951914e-09, + "loss": 0.16, + "step": 1393 + }, + { + "epoch": 2.9573283858998147, + "grad_norm": 2.112011671066284, + "learning_rate": 2.2622266237029565e-09, + "loss": 0.2442, + "step": 1394 + }, + { + "epoch": 2.9594487145507555, + "grad_norm": 1.9325287342071533, + "learning_rate": 2.030395451399214e-09, + "loss": 0.1084, + "step": 1395 + }, + { + "epoch": 2.9615690432016963, + "grad_norm": 1.0809413194656372, + "learning_rate": 1.8110890955849724e-09, + "loss": 0.1805, + "step": 1396 + }, + { + "epoch": 2.963689371852637, + "grad_norm": 1.6688867807388306, + "learning_rate": 1.6043086558623078e-09, + "loss": 0.1576, + "step": 1397 + }, + { + "epoch": 2.965809700503578, + "grad_norm": 1.1752701997756958, + "learning_rate": 1.4100551690279796e-09, + "loss": 0.1739, + "step": 1398 + }, + { + "epoch": 2.9679300291545188, + "grad_norm": 2.4213781356811523, + "learning_rate": 1.2283296090687125e-09, + "loss": 0.1755, + "step": 1399 + }, + { + "epoch": 2.97005035780546, + "grad_norm": 0.7826443314552307, + "learning_rate": 1.0591328871562e-09, + "loss": 0.1123, + "step": 1400 + }, + { + "epoch": 2.972170686456401, + "grad_norm": 1.7806673049926758, + "learning_rate": 9.024658516426643e-10, + "loss": 0.1952, + "step": 1401 + }, + { + "epoch": 2.9742910151073416, + "grad_norm": 1.3985880613327026, + "learning_rate": 7.583292880564142e-10, + "loss": 0.1802, + "step": 1402 + }, + { + "epoch": 2.9764113437582824, + "grad_norm": 0.9030689001083374, + "learning_rate": 6.267239190979601e-10, + "loss": 0.1862, + "step": 1403 + }, + { + "epoch": 2.9785316724092237, + "grad_norm": 1.05217707157135, + "learning_rate": 5.076504046364061e-10, + "loss": 0.1186, + "step": 1404 + }, + { + "epoch": 2.9806520010601645, + "grad_norm": 2.4997191429138184, + "learning_rate": 4.0110934170639603e-10, + "loss": 0.202, + "step": 1405 + }, + { + "epoch": 2.9827723297111053, + "grad_norm": 0.7951033711433411, + "learning_rate": 3.0710126450450574e-10, + "loss": 0.1106, + "step": 1406 + }, + { + "epoch": 2.984892658362046, + "grad_norm": 1.5203306674957275, + "learning_rate": 2.2562664438730008e-10, + "loss": 0.2274, + "step": 1407 + }, + { + "epoch": 2.987012987012987, + "grad_norm": 1.2033835649490356, + "learning_rate": 1.5668588986800237e-10, + "loss": 0.098, + "step": 1408 + }, + { + "epoch": 2.9891333156639277, + "grad_norm": 2.494394063949585, + "learning_rate": 1.0027934661593908e-10, + "loss": 0.1817, + "step": 1409 + }, + { + "epoch": 2.991253644314869, + "grad_norm": 1.0664846897125244, + "learning_rate": 5.640729745348683e-11, + "loss": 0.1669, + "step": 1410 + }, + { + "epoch": 2.9933739729658098, + "grad_norm": 0.9831266403198242, + "learning_rate": 2.5069962354684618e-11, + "loss": 0.1413, + "step": 1411 + }, + { + "epoch": 2.9954943016167506, + "grad_norm": 17.356966018676758, + "learning_rate": 6.267498444956222e-12, + "loss": 0.3418, + "step": 1412 + }, + { + "epoch": 2.9976146302676914, + "grad_norm": 1.7750447988510132, + "learning_rate": 0.0, + "loss": 0.1737, + "step": 1413 + }, + { + "epoch": 2.9976146302676914, + "step": 1413, + "total_flos": 1.9412022010031636e+18, + "train_loss": 0.22161940554313767, + "train_runtime": 29847.081, + "train_samples_per_second": 1.517, + "train_steps_per_second": 0.047 + } + ], + "logging_steps": 1, + "max_steps": 1413, + "num_input_tokens_seen": 0, + "num_train_epochs": 3, + "save_steps": 1000, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": true + }, + "attributes": {} + } + }, + "total_flos": 1.9412022010031636e+18, + "train_batch_size": 1, + "trial_name": null, + "trial_params": null +} diff --git a/rag_truth_hal_detection_model/training_args.bin b/rag_truth_hal_detection_model/training_args.bin new file mode 100644 index 0000000000000000000000000000000000000000..7c2f22d4d5100bea19a9b524d6fe22f4b61ba2b8 --- /dev/null +++ b/rag_truth_hal_detection_model/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8cba5214263bc92d48c42393a60c4f497265c69e8a26b939f349b78bea897898 +size 7160 diff --git a/rag_truth_hal_detection_model/training_args.yaml b/rag_truth_hal_detection_model/training_args.yaml new file mode 100644 index 0000000000000000000000000000000000000000..4467ff2cf9ddac639b7cc5262421bd32e1c3e112 --- /dev/null +++ b/rag_truth_hal_detection_model/training_args.yaml @@ -0,0 +1,28 @@ +bf16: true +cutoff_len: 4096 +dataset: train_hal_detection_1125 +dataset_dir: data +ddp_timeout: 180000000 +deepspeed: cache/ds_z2_offload_config.json +do_train: true +finetuning_type: full +flash_attn: auto +gradient_accumulation_steps: 8 +learning_rate: 5.0e-06 +logging_steps: 1 +lr_scheduler_type: cosine +max_grad_norm: 1.0 +max_samples: 100000 +model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct +num_train_epochs: 3.0 +optim: adamw_torch +output_dir: saves/Llama-3-8B-Instruct/full/train_2024-11-25-07-46-41 +packing: false +per_device_train_batch_size: 1 +plot_loss: true +preprocessing_num_workers: 16 +report_to: none +save_steps: 1000 +stage: sft +template: llama3 +warmup_steps: 10 diff --git a/rag_truth_hal_detection_model/training_loss.png b/rag_truth_hal_detection_model/training_loss.png new file mode 100644 index 0000000000000000000000000000000000000000..980c94e60e475dc03ad2d5bfc3f9b836f11518fe Binary files /dev/null and b/rag_truth_hal_detection_model/training_loss.png differ