commit ce71455f6d2adbeb548b97cf8d0c23ce74ffc19d Author: ModelHub XC Date: Wed Jun 3 05:20:12 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mlfoundations-dev/b2_code_random Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..caba244 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,56 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text + + +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text + +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.gguf* filter=lfs diff=lfs merge=lfs -text +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text + +merges.txt filter=lfs diff=lfs merge=lfs -text +model-00001-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text +vocab.json filter=lfs diff=lfs merge=lfs -text +training_args.bin filter=lfs diff=lfs merge=lfs -text +model-00004-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +model-00003-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +model-00002-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..42517bf --- /dev/null +++ b/README.md @@ -0,0 +1,61 @@ +--- +library_name: transformers +license: apache-2.0 +base_model: Qwen/Qwen2.5-7B-Instruct +tags: +- llama-factory +- full +- generated_from_trainer +model-index: +- name: b2_code_random + results: [] +--- + + + +# b2_code_random + +This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the mlfoundations-dev/b2_code_random 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: 4e-05 +- train_batch_size: 1 +- eval_batch_size: 8 +- seed: 42 +- distributed_type: multi-GPU +- num_devices: 32 +- gradient_accumulation_steps: 4 +- total_train_batch_size: 128 +- total_eval_batch_size: 256 +- optimizer: Use OptimizerNames.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_ratio: 0.1 +- num_epochs: 5.0 + +### Training results + + + +### Framework versions + +- Transformers 4.46.1 +- Pytorch 2.5.1 +- Datasets 3.0.2 +- Tokenizers 0.20.3 diff --git a/added_tokens.json b/added_tokens.json new file mode 100644 index 0000000..482ced4 --- /dev/null +++ b/added_tokens.json @@ -0,0 +1,24 @@ +{ + "": 151658, + "": 151657, + "<|box_end|>": 151649, + "<|box_start|>": 151648, + "<|endoftext|>": 151643, + "<|file_sep|>": 151664, + "<|fim_middle|>": 151660, + "<|fim_pad|>": 151662, + "<|fim_prefix|>": 151659, + "<|fim_suffix|>": 151661, + "<|im_end|>": 151645, + "<|im_start|>": 151644, + "<|image_pad|>": 151655, + "<|object_ref_end|>": 151647, + "<|object_ref_start|>": 151646, + "<|quad_end|>": 151651, + "<|quad_start|>": 151650, + "<|repo_name|>": 151663, + "<|video_pad|>": 151656, + "<|vision_end|>": 151653, + "<|vision_pad|>": 151654, + "<|vision_start|>": 151652 +} diff --git a/all_results.json b/all_results.json new file mode 100644 index 0000000..0525d63 --- /dev/null +++ b/all_results.json @@ -0,0 +1,8 @@ +{ + "epoch": 5.0, + "total_flos": 4.3365838011792097e+18, + "train_loss": 0.4892277446353001, + "train_runtime": 29008.2393, + "train_samples_per_second": 5.447, + "train_steps_per_second": 0.043 +} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..6c52571 --- /dev/null +++ b/config.json @@ -0,0 +1,29 @@ +{ + "_name_or_path": "Qwen/Qwen2.5-7B-Instruct", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 151643, + "eos_token_id": 151645, + "hidden_act": "silu", + "hidden_size": 3584, + "initializer_range": 0.02, + "intermediate_size": 18944, + "max_position_embeddings": 32768, + "max_window_layers": 28, + "model_type": "qwen2", + "num_attention_heads": 28, + "num_hidden_layers": 28, + "num_key_value_heads": 4, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000.0, + "sliding_window": null, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.46.1", + "use_cache": false, + "use_sliding_window": false, + "vocab_size": 152064 +} diff --git a/configs.yaml b/configs.yaml new file mode 100644 index 0000000..4931071 --- /dev/null +++ b/configs.yaml @@ -0,0 +1,37 @@ +assistant_tag: gpt +bf16: true +content_tag: value +cutoff_len: 16384 +dataloader_num_workers: 4 +dataloader_persistent_workers: true +dataloader_pin_memory: true +dataset: mlfoundations-dev/b2_code_random +dataset_dir: ONLINE +ddp_timeout: 180000000 +deepspeed: dcft/train/zero3.json +do_train: true +enable_liger_kernel: true +finetuning_type: full +global_batch_size: 128 +gradient_accumulation_steps: 4 +hub_model_id: mlfoundations-dev/b2_code_random +learning_rate: 4.0e-05 +logging_steps: 1 +lr_scheduler_type: cosine +messages: conversations +model_name_or_path: Qwen/Qwen2.5-7B-Instruct +num_train_epochs: 5.0 +output_dir: /scratch/10159/rmarten/checkpoints/b2_code_random +overwrite_cache: true +per_device_train_batch_size: 1 +plot_loss: true +preprocessing_num_workers: 16 +push_to_db: true +push_to_hub: true +report_to: wandb +role_tag: from +save_strategy: epoch +stage: sft +template: qwen25 +user_tag: human +warmup_ratio: 0.1 diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..a753841 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,14 @@ +{ + "bos_token_id": 151643, + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "repetition_penalty": 1.05, + "temperature": 0.7, + "top_k": 20, + "top_p": 0.8, + "transformers_version": "4.46.1" +} diff --git a/merges.txt b/merges.txt new file mode 100644 index 0000000..80c1a19 --- /dev/null +++ b/merges.txt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5 +size 1671853 diff --git a/model-00001-of-00004.safetensors b/model-00001-of-00004.safetensors new file mode 100644 index 0000000..2b7e5dc --- /dev/null +++ b/model-00001-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bdcc792ea78d46f34bf183c51fdcc37f7203f673f3eece498b471f13992446d +size 4877660776 diff --git a/model-00002-of-00004.safetensors b/model-00002-of-00004.safetensors new file mode 100644 index 0000000..520218c --- /dev/null +++ b/model-00002-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1c24c0e5b54a60b519a6d3da2b55644129ea3f14d0be685dd7356ab6f61c13b +size 4932751008 diff --git a/model-00003-of-00004.safetensors b/model-00003-of-00004.safetensors new file mode 100644 index 0000000..4e93dee --- /dev/null +++ b/model-00003-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ccb4f06ac71e0ca6a1c79ac5b0f5857ee1ff08efe6f86b8351eedb271f8aa62 +size 4330865200 diff --git a/model-00004-of-00004.safetensors b/model-00004-of-00004.safetensors new file mode 100644 index 0000000..c87f328 --- /dev/null +++ b/model-00004-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9a5c1bae1b59de61a3ee62fcd13cc26e04af2aa35d0302fbadf7075191b564b +size 1089994880 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..6ca5084 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,346 @@ +{ + "metadata": { + "total_size": 15231233024 + }, + "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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-00003-of-00004.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00003-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-00003-of-00004.safetensors", + "model.layers.18.self_attn.k_proj.bias": "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.bias": "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.bias": "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-00003-of-00004.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00003-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.bias": "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.bias": "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.bias": "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-00003-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.bias": "model-00003-of-00004.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00003-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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "model-00003-of-00004.safetensors", + "model.layers.27.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.bias": "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.bias": "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.bias": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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-00002-of-00004.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.8.self_attn.k_proj.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.norm.weight": "model-00003-of-00004.safetensors" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..17305b3 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,31 @@ +{ + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "eos_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..51ebb3b --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa +size 11421896 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..b84f53a --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,208 @@ +{ + "add_bos_token": false, + "add_prefix_space": false, + "added_tokens_decoder": { + "151643": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151644": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151645": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151646": { + "content": "<|object_ref_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151647": { + "content": "<|object_ref_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151648": { + "content": "<|box_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151649": { + "content": "<|box_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151650": { + "content": "<|quad_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151657": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151658": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "bos_token": null, + "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within XML tags:\\n\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n\\n\\nFor each function call, return a json object with function name and arguments within XML tags:\\n\\n{\\\"name\\\": , \\\"arguments\\\": }\\n<|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n\\n' }}\n {{- message.content }}\n {{- '\\n' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n", + "clean_up_tokenization_spaces": false, + "eos_token": "<|endoftext|>", + "errors": "replace", + "model_max_length": 131072, + "pad_token": "<|endoftext|>", + "padding_side": "right", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +} diff --git a/train_results.json b/train_results.json new file mode 100644 index 0000000..0525d63 --- /dev/null +++ b/train_results.json @@ -0,0 +1,8 @@ +{ + "epoch": 5.0, + "total_flos": 4.3365838011792097e+18, + "train_loss": 0.4892277446353001, + "train_runtime": 29008.2393, + "train_samples_per_second": 5.447, + "train_steps_per_second": 0.043 +} \ No newline at end of file diff --git a/trainer_log.jsonl b/trainer_log.jsonl new file mode 100644 index 0000000..9951a01 --- /dev/null +++ b/trainer_log.jsonl @@ -0,0 +1,1236 @@ +{"current_steps": 1, "total_steps": 1235, "loss": 1.0591, "lr": 3.2258064516129035e-07, "epoch": 0.004048582995951417, "percentage": 0.08, "elapsed_time": "0:00:26", "remaining_time": "8:58:51"} +{"current_steps": 2, "total_steps": 1235, "loss": 1.0685, "lr": 6.451612903225807e-07, "epoch": 0.008097165991902834, "percentage": 0.16, "elapsed_time": "0:00:49", "remaining_time": "8:27:05"} +{"current_steps": 3, "total_steps": 1235, "loss": 1.0446, "lr": 9.67741935483871e-07, "epoch": 0.012145748987854251, "percentage": 0.24, "elapsed_time": "0:01:12", "remaining_time": "8:17:59"} +{"current_steps": 4, "total_steps": 1235, "loss": 1.0575, "lr": 1.2903225806451614e-06, "epoch": 0.016194331983805668, "percentage": 0.32, "elapsed_time": "0:01:36", "remaining_time": "8:12:47"} +{"current_steps": 5, "total_steps": 1235, "loss": 1.0547, "lr": 1.6129032258064516e-06, "epoch": 0.020242914979757085, "percentage": 0.4, "elapsed_time": "0:01:57", "remaining_time": "8:03:45"} +{"current_steps": 6, "total_steps": 1235, "loss": 1.0443, "lr": 1.935483870967742e-06, "epoch": 0.024291497975708502, "percentage": 0.49, "elapsed_time": "0:02:20", "remaining_time": "7:59:41"} +{"current_steps": 7, "total_steps": 1235, "loss": 1.0039, "lr": 2.2580645161290324e-06, "epoch": 0.02834008097165992, "percentage": 0.57, "elapsed_time": "0:02:42", "remaining_time": "7:55:32"} +{"current_steps": 8, "total_steps": 1235, "loss": 1.004, "lr": 2.580645161290323e-06, "epoch": 0.032388663967611336, "percentage": 0.65, "elapsed_time": "0:03:05", "remaining_time": "7:54:44"} +{"current_steps": 9, "total_steps": 1235, "loss": 0.9558, "lr": 2.903225806451613e-06, "epoch": 0.03643724696356275, "percentage": 0.73, "elapsed_time": "0:03:28", "remaining_time": "7:54:09"} +{"current_steps": 10, "total_steps": 1235, "loss": 0.9629, "lr": 3.225806451612903e-06, "epoch": 0.04048582995951417, "percentage": 0.81, "elapsed_time": "0:03:52", "remaining_time": "7:54:34"} +{"current_steps": 11, "total_steps": 1235, "loss": 0.9542, "lr": 3.548387096774194e-06, "epoch": 0.044534412955465584, "percentage": 0.89, "elapsed_time": "0:04:16", "remaining_time": "7:54:55"} +{"current_steps": 12, "total_steps": 1235, "loss": 0.94, "lr": 3.870967741935484e-06, "epoch": 0.048582995951417005, "percentage": 0.97, "elapsed_time": "0:04:38", "remaining_time": "7:53:36"} +{"current_steps": 13, "total_steps": 1235, "loss": 0.9349, "lr": 4.193548387096774e-06, "epoch": 0.05263157894736842, "percentage": 1.05, "elapsed_time": "0:05:01", "remaining_time": "7:52:52"} +{"current_steps": 14, "total_steps": 1235, "loss": 0.9312, "lr": 4.516129032258065e-06, "epoch": 0.05668016194331984, "percentage": 1.13, "elapsed_time": "0:05:24", "remaining_time": "7:52:16"} +{"current_steps": 15, "total_steps": 1235, "loss": 0.9129, "lr": 4.838709677419355e-06, "epoch": 0.06072874493927125, "percentage": 1.21, "elapsed_time": "0:05:47", "remaining_time": "7:51:38"} +{"current_steps": 16, "total_steps": 1235, "loss": 0.8783, "lr": 5.161290322580646e-06, "epoch": 0.06477732793522267, "percentage": 1.3, "elapsed_time": "0:06:10", "remaining_time": "7:50:56"} +{"current_steps": 17, "total_steps": 1235, "loss": 0.8682, "lr": 5.483870967741935e-06, "epoch": 0.06882591093117409, "percentage": 1.38, "elapsed_time": "0:06:33", "remaining_time": "7:49:27"} +{"current_steps": 18, "total_steps": 1235, "loss": 0.8575, "lr": 5.806451612903226e-06, "epoch": 0.0728744939271255, "percentage": 1.46, "elapsed_time": "0:06:56", "remaining_time": "7:49:36"} +{"current_steps": 19, "total_steps": 1235, "loss": 0.8403, "lr": 6.129032258064517e-06, "epoch": 0.07692307692307693, "percentage": 1.54, "elapsed_time": "0:07:20", "remaining_time": "7:49:51"} +{"current_steps": 20, "total_steps": 1235, "loss": 0.795, "lr": 6.451612903225806e-06, "epoch": 0.08097165991902834, "percentage": 1.62, "elapsed_time": "0:07:43", "remaining_time": "7:49:21"} +{"current_steps": 21, "total_steps": 1235, "loss": 0.8068, "lr": 6.774193548387097e-06, "epoch": 0.08502024291497975, "percentage": 1.7, "elapsed_time": "0:08:07", "remaining_time": "7:49:20"} +{"current_steps": 22, "total_steps": 1235, "loss": 0.8264, "lr": 7.096774193548388e-06, "epoch": 0.08906882591093117, "percentage": 1.78, "elapsed_time": "0:08:28", "remaining_time": "7:47:04"} +{"current_steps": 23, "total_steps": 1235, "loss": 0.7984, "lr": 7.4193548387096784e-06, "epoch": 0.0931174089068826, "percentage": 1.86, "elapsed_time": "0:08:51", "remaining_time": "7:46:33"} +{"current_steps": 24, "total_steps": 1235, "loss": 0.7919, "lr": 7.741935483870968e-06, "epoch": 0.09716599190283401, "percentage": 1.94, "elapsed_time": "0:09:14", "remaining_time": "7:46:19"} +{"current_steps": 25, "total_steps": 1235, "loss": 0.7575, "lr": 8.064516129032258e-06, "epoch": 0.10121457489878542, "percentage": 2.02, "elapsed_time": "0:09:37", "remaining_time": "7:46:08"} +{"current_steps": 26, "total_steps": 1235, "loss": 0.7722, "lr": 8.387096774193549e-06, "epoch": 0.10526315789473684, "percentage": 2.11, "elapsed_time": "0:09:59", "remaining_time": "7:44:31"} +{"current_steps": 27, "total_steps": 1235, "loss": 0.7682, "lr": 8.70967741935484e-06, "epoch": 0.10931174089068826, "percentage": 2.19, "elapsed_time": "0:10:21", "remaining_time": "7:43:31"} +{"current_steps": 28, "total_steps": 1235, "loss": 0.7439, "lr": 9.03225806451613e-06, "epoch": 0.11336032388663968, "percentage": 2.27, "elapsed_time": "0:10:44", "remaining_time": "7:43:08"} +{"current_steps": 29, "total_steps": 1235, "loss": 0.7359, "lr": 9.35483870967742e-06, "epoch": 0.11740890688259109, "percentage": 2.35, "elapsed_time": "0:11:07", "remaining_time": "7:42:54"} +{"current_steps": 30, "total_steps": 1235, "loss": 0.7288, "lr": 9.67741935483871e-06, "epoch": 0.1214574898785425, "percentage": 2.43, "elapsed_time": "0:11:31", "remaining_time": "7:43:13"} +{"current_steps": 31, "total_steps": 1235, "loss": 0.7433, "lr": 1e-05, "epoch": 0.12550607287449392, "percentage": 2.51, "elapsed_time": "0:11:54", "remaining_time": "7:42:40"} +{"current_steps": 32, "total_steps": 1235, "loss": 0.715, "lr": 1.0322580645161291e-05, "epoch": 0.12955465587044535, "percentage": 2.59, "elapsed_time": "0:12:18", "remaining_time": "7:42:29"} +{"current_steps": 33, "total_steps": 1235, "loss": 0.7312, "lr": 1.0645161290322582e-05, "epoch": 0.13360323886639677, "percentage": 2.67, "elapsed_time": "0:12:41", "remaining_time": "7:42:34"} +{"current_steps": 34, "total_steps": 1235, "loss": 0.7278, "lr": 1.096774193548387e-05, "epoch": 0.13765182186234817, "percentage": 2.75, "elapsed_time": "0:13:05", "remaining_time": "7:42:17"} +{"current_steps": 35, "total_steps": 1235, "loss": 0.7237, "lr": 1.1290322580645164e-05, "epoch": 0.1417004048582996, "percentage": 2.83, "elapsed_time": "0:13:28", "remaining_time": "7:42:08"} +{"current_steps": 36, "total_steps": 1235, "loss": 0.7165, "lr": 1.1612903225806453e-05, "epoch": 0.145748987854251, "percentage": 2.91, "elapsed_time": "0:13:52", "remaining_time": "7:42:14"} +{"current_steps": 37, "total_steps": 1235, "loss": 0.6971, "lr": 1.1935483870967743e-05, "epoch": 0.14979757085020243, "percentage": 3.0, "elapsed_time": "0:14:15", "remaining_time": "7:41:37"} +{"current_steps": 38, "total_steps": 1235, "loss": 0.7136, "lr": 1.2258064516129034e-05, "epoch": 0.15384615384615385, "percentage": 3.08, "elapsed_time": "0:14:38", "remaining_time": "7:40:59"} +{"current_steps": 39, "total_steps": 1235, "loss": 0.7263, "lr": 1.2580645161290324e-05, "epoch": 0.15789473684210525, "percentage": 3.16, "elapsed_time": "0:14:59", "remaining_time": "7:39:52"} +{"current_steps": 40, "total_steps": 1235, "loss": 0.7265, "lr": 1.2903225806451613e-05, "epoch": 0.16194331983805668, "percentage": 3.24, "elapsed_time": "0:15:22", "remaining_time": "7:39:23"} +{"current_steps": 41, "total_steps": 1235, "loss": 0.7021, "lr": 1.3225806451612903e-05, "epoch": 0.1659919028340081, "percentage": 3.32, "elapsed_time": "0:15:45", "remaining_time": "7:39:01"} +{"current_steps": 42, "total_steps": 1235, "loss": 0.7127, "lr": 1.3548387096774194e-05, "epoch": 0.1700404858299595, "percentage": 3.4, "elapsed_time": "0:16:09", "remaining_time": "7:39:00"} +{"current_steps": 43, "total_steps": 1235, "loss": 0.6885, "lr": 1.3870967741935486e-05, "epoch": 0.17408906882591094, "percentage": 3.48, "elapsed_time": "0:16:33", "remaining_time": "7:38:54"} +{"current_steps": 44, "total_steps": 1235, "loss": 0.6976, "lr": 1.4193548387096776e-05, "epoch": 0.17813765182186234, "percentage": 3.56, "elapsed_time": "0:16:55", "remaining_time": "7:38:16"} +{"current_steps": 45, "total_steps": 1235, "loss": 0.6799, "lr": 1.4516129032258066e-05, "epoch": 0.18218623481781376, "percentage": 3.64, "elapsed_time": "0:17:19", "remaining_time": "7:37:59"} +{"current_steps": 46, "total_steps": 1235, "loss": 0.6994, "lr": 1.4838709677419357e-05, "epoch": 0.1862348178137652, "percentage": 3.72, "elapsed_time": "0:17:42", "remaining_time": "7:37:46"} +{"current_steps": 47, "total_steps": 1235, "loss": 0.6885, "lr": 1.5161290322580646e-05, "epoch": 0.1902834008097166, "percentage": 3.81, "elapsed_time": "0:18:06", "remaining_time": "7:37:37"} +{"current_steps": 48, "total_steps": 1235, "loss": 0.6747, "lr": 1.5483870967741936e-05, "epoch": 0.19433198380566802, "percentage": 3.89, "elapsed_time": "0:18:29", "remaining_time": "7:37:20"} +{"current_steps": 49, "total_steps": 1235, "loss": 0.6864, "lr": 1.5806451612903226e-05, "epoch": 0.19838056680161945, "percentage": 3.97, "elapsed_time": "0:18:51", "remaining_time": "7:36:25"} +{"current_steps": 50, "total_steps": 1235, "loss": 0.6924, "lr": 1.6129032258064517e-05, "epoch": 0.20242914979757085, "percentage": 4.05, "elapsed_time": "0:19:13", "remaining_time": "7:35:35"} +{"current_steps": 51, "total_steps": 1235, "loss": 0.7048, "lr": 1.6451612903225807e-05, "epoch": 0.20647773279352227, "percentage": 4.13, "elapsed_time": "0:19:36", "remaining_time": "7:35:17"} +{"current_steps": 52, "total_steps": 1235, "loss": 0.6775, "lr": 1.6774193548387098e-05, "epoch": 0.21052631578947367, "percentage": 4.21, "elapsed_time": "0:20:00", "remaining_time": "7:35:00"} +{"current_steps": 53, "total_steps": 1235, "loss": 0.6836, "lr": 1.7096774193548388e-05, "epoch": 0.2145748987854251, "percentage": 4.29, "elapsed_time": "0:20:22", "remaining_time": "7:34:33"} +{"current_steps": 54, "total_steps": 1235, "loss": 0.6806, "lr": 1.741935483870968e-05, "epoch": 0.21862348178137653, "percentage": 4.37, "elapsed_time": "0:20:45", "remaining_time": "7:34:03"} +{"current_steps": 55, "total_steps": 1235, "loss": 0.6801, "lr": 1.774193548387097e-05, "epoch": 0.22267206477732793, "percentage": 4.45, "elapsed_time": "0:21:08", "remaining_time": "7:33:45"} +{"current_steps": 56, "total_steps": 1235, "loss": 0.6763, "lr": 1.806451612903226e-05, "epoch": 0.22672064777327935, "percentage": 4.53, "elapsed_time": "0:21:31", "remaining_time": "7:33:14"} +{"current_steps": 57, "total_steps": 1235, "loss": 0.6671, "lr": 1.838709677419355e-05, "epoch": 0.23076923076923078, "percentage": 4.62, "elapsed_time": "0:21:55", "remaining_time": "7:33:03"} +{"current_steps": 58, "total_steps": 1235, "loss": 0.6653, "lr": 1.870967741935484e-05, "epoch": 0.23481781376518218, "percentage": 4.7, "elapsed_time": "0:22:18", "remaining_time": "7:32:45"} +{"current_steps": 59, "total_steps": 1235, "loss": 0.6728, "lr": 1.903225806451613e-05, "epoch": 0.2388663967611336, "percentage": 4.78, "elapsed_time": "0:22:41", "remaining_time": "7:32:20"} +{"current_steps": 60, "total_steps": 1235, "loss": 0.6864, "lr": 1.935483870967742e-05, "epoch": 0.242914979757085, "percentage": 4.86, "elapsed_time": "0:23:04", "remaining_time": "7:31:54"} +{"current_steps": 61, "total_steps": 1235, "loss": 0.6658, "lr": 1.967741935483871e-05, "epoch": 0.24696356275303644, "percentage": 4.94, "elapsed_time": "0:23:28", "remaining_time": "7:31:40"} +{"current_steps": 62, "total_steps": 1235, "loss": 0.6849, "lr": 2e-05, "epoch": 0.25101214574898784, "percentage": 5.02, "elapsed_time": "0:23:51", "remaining_time": "7:31:17"} +{"current_steps": 63, "total_steps": 1235, "loss": 0.6655, "lr": 2.0322580645161292e-05, "epoch": 0.2550607287449393, "percentage": 5.1, "elapsed_time": "0:24:14", "remaining_time": "7:31:01"} +{"current_steps": 64, "total_steps": 1235, "loss": 0.6771, "lr": 2.0645161290322582e-05, "epoch": 0.2591093117408907, "percentage": 5.18, "elapsed_time": "0:24:37", "remaining_time": "7:30:28"} +{"current_steps": 65, "total_steps": 1235, "loss": 0.6453, "lr": 2.0967741935483873e-05, "epoch": 0.2631578947368421, "percentage": 5.26, "elapsed_time": "0:24:58", "remaining_time": "7:29:35"} +{"current_steps": 66, "total_steps": 1235, "loss": 0.6723, "lr": 2.1290322580645163e-05, "epoch": 0.26720647773279355, "percentage": 5.34, "elapsed_time": "0:25:21", "remaining_time": "7:29:14"} +{"current_steps": 67, "total_steps": 1235, "loss": 0.6622, "lr": 2.161290322580645e-05, "epoch": 0.27125506072874495, "percentage": 5.43, "elapsed_time": "0:25:44", "remaining_time": "7:28:40"} +{"current_steps": 68, "total_steps": 1235, "loss": 0.6652, "lr": 2.193548387096774e-05, "epoch": 0.27530364372469635, "percentage": 5.51, "elapsed_time": "0:26:07", "remaining_time": "7:28:27"} +{"current_steps": 69, "total_steps": 1235, "loss": 0.6665, "lr": 2.225806451612903e-05, "epoch": 0.2793522267206478, "percentage": 5.59, "elapsed_time": "0:26:30", "remaining_time": "7:28:03"} +{"current_steps": 70, "total_steps": 1235, "loss": 0.6716, "lr": 2.2580645161290328e-05, "epoch": 0.2834008097165992, "percentage": 5.67, "elapsed_time": "0:26:53", "remaining_time": "7:27:40"} +{"current_steps": 71, "total_steps": 1235, "loss": 0.6728, "lr": 2.2903225806451615e-05, "epoch": 0.2874493927125506, "percentage": 5.75, "elapsed_time": "0:27:17", "remaining_time": "7:27:26"} +{"current_steps": 72, "total_steps": 1235, "loss": 0.6559, "lr": 2.3225806451612906e-05, "epoch": 0.291497975708502, "percentage": 5.83, "elapsed_time": "0:27:40", "remaining_time": "7:27:04"} +{"current_steps": 73, "total_steps": 1235, "loss": 0.6538, "lr": 2.3548387096774196e-05, "epoch": 0.29554655870445345, "percentage": 5.91, "elapsed_time": "0:28:03", "remaining_time": "7:26:38"} +{"current_steps": 74, "total_steps": 1235, "loss": 0.6485, "lr": 2.3870967741935486e-05, "epoch": 0.29959514170040485, "percentage": 5.99, "elapsed_time": "0:28:27", "remaining_time": "7:26:23"} +{"current_steps": 75, "total_steps": 1235, "loss": 0.6642, "lr": 2.4193548387096777e-05, "epoch": 0.30364372469635625, "percentage": 6.07, "elapsed_time": "0:28:49", "remaining_time": "7:25:55"} +{"current_steps": 76, "total_steps": 1235, "loss": 0.6621, "lr": 2.4516129032258067e-05, "epoch": 0.3076923076923077, "percentage": 6.15, "elapsed_time": "0:29:13", "remaining_time": "7:25:34"} +{"current_steps": 77, "total_steps": 1235, "loss": 0.6592, "lr": 2.4838709677419358e-05, "epoch": 0.3117408906882591, "percentage": 6.23, "elapsed_time": "0:29:35", "remaining_time": "7:24:59"} +{"current_steps": 78, "total_steps": 1235, "loss": 0.6716, "lr": 2.5161290322580648e-05, "epoch": 0.3157894736842105, "percentage": 6.32, "elapsed_time": "0:29:57", "remaining_time": "7:24:24"} +{"current_steps": 79, "total_steps": 1235, "loss": 0.6612, "lr": 2.548387096774194e-05, "epoch": 0.31983805668016196, "percentage": 6.4, "elapsed_time": "0:30:21", "remaining_time": "7:24:10"} +{"current_steps": 80, "total_steps": 1235, "loss": 0.661, "lr": 2.5806451612903226e-05, "epoch": 0.32388663967611336, "percentage": 6.48, "elapsed_time": "0:30:44", "remaining_time": "7:23:51"} +{"current_steps": 81, "total_steps": 1235, "loss": 0.6682, "lr": 2.6129032258064516e-05, "epoch": 0.32793522267206476, "percentage": 6.56, "elapsed_time": "0:31:08", "remaining_time": "7:23:36"} +{"current_steps": 82, "total_steps": 1235, "loss": 0.6401, "lr": 2.6451612903225806e-05, "epoch": 0.3319838056680162, "percentage": 6.64, "elapsed_time": "0:31:31", "remaining_time": "7:23:20"} +{"current_steps": 83, "total_steps": 1235, "loss": 0.6528, "lr": 2.6774193548387097e-05, "epoch": 0.3360323886639676, "percentage": 6.72, "elapsed_time": "0:31:54", "remaining_time": "7:22:57"} +{"current_steps": 84, "total_steps": 1235, "loss": 0.6716, "lr": 2.7096774193548387e-05, "epoch": 0.340080971659919, "percentage": 6.8, "elapsed_time": "0:32:18", "remaining_time": "7:22:39"} +{"current_steps": 85, "total_steps": 1235, "loss": 0.6498, "lr": 2.7419354838709678e-05, "epoch": 0.3441295546558704, "percentage": 6.88, "elapsed_time": "0:32:41", "remaining_time": "7:22:13"} +{"current_steps": 86, "total_steps": 1235, "loss": 0.6483, "lr": 2.774193548387097e-05, "epoch": 0.3481781376518219, "percentage": 6.96, "elapsed_time": "0:33:04", "remaining_time": "7:21:59"} +{"current_steps": 87, "total_steps": 1235, "loss": 0.6478, "lr": 2.8064516129032262e-05, "epoch": 0.3522267206477733, "percentage": 7.04, "elapsed_time": "0:33:27", "remaining_time": "7:21:28"} +{"current_steps": 88, "total_steps": 1235, "loss": 0.6637, "lr": 2.8387096774193552e-05, "epoch": 0.3562753036437247, "percentage": 7.13, "elapsed_time": "0:33:49", "remaining_time": "7:20:46"} +{"current_steps": 89, "total_steps": 1235, "loss": 0.6422, "lr": 2.8709677419354843e-05, "epoch": 0.3603238866396761, "percentage": 7.21, "elapsed_time": "0:34:12", "remaining_time": "7:20:25"} +{"current_steps": 90, "total_steps": 1235, "loss": 0.6543, "lr": 2.9032258064516133e-05, "epoch": 0.3643724696356275, "percentage": 7.29, "elapsed_time": "0:34:35", "remaining_time": "7:20:03"} +{"current_steps": 91, "total_steps": 1235, "loss": 0.6482, "lr": 2.9354838709677423e-05, "epoch": 0.3684210526315789, "percentage": 7.37, "elapsed_time": "0:34:58", "remaining_time": "7:19:45"} +{"current_steps": 92, "total_steps": 1235, "loss": 0.6501, "lr": 2.9677419354838714e-05, "epoch": 0.3724696356275304, "percentage": 7.45, "elapsed_time": "0:35:20", "remaining_time": "7:19:05"} +{"current_steps": 93, "total_steps": 1235, "loss": 0.6552, "lr": 3.0000000000000004e-05, "epoch": 0.3765182186234818, "percentage": 7.53, "elapsed_time": "0:35:43", "remaining_time": "7:18:43"} +{"current_steps": 94, "total_steps": 1235, "loss": 0.6581, "lr": 3.032258064516129e-05, "epoch": 0.3805668016194332, "percentage": 7.61, "elapsed_time": "0:36:07", "remaining_time": "7:18:29"} +{"current_steps": 95, "total_steps": 1235, "loss": 0.6574, "lr": 3.0645161290322585e-05, "epoch": 0.38461538461538464, "percentage": 7.69, "elapsed_time": "0:36:29", "remaining_time": "7:17:56"} +{"current_steps": 96, "total_steps": 1235, "loss": 0.6683, "lr": 3.096774193548387e-05, "epoch": 0.38866396761133604, "percentage": 7.77, "elapsed_time": "0:36:52", "remaining_time": "7:17:29"} +{"current_steps": 97, "total_steps": 1235, "loss": 0.6435, "lr": 3.1290322580645166e-05, "epoch": 0.39271255060728744, "percentage": 7.85, "elapsed_time": "0:37:15", "remaining_time": "7:17:11"} +{"current_steps": 98, "total_steps": 1235, "loss": 0.6502, "lr": 3.161290322580645e-05, "epoch": 0.3967611336032389, "percentage": 7.94, "elapsed_time": "0:37:38", "remaining_time": "7:16:48"} +{"current_steps": 99, "total_steps": 1235, "loss": 0.6579, "lr": 3.193548387096774e-05, "epoch": 0.4008097165991903, "percentage": 8.02, "elapsed_time": "0:38:02", "remaining_time": "7:16:25"} +{"current_steps": 100, "total_steps": 1235, "loss": 0.6422, "lr": 3.2258064516129034e-05, "epoch": 0.4048582995951417, "percentage": 8.1, "elapsed_time": "0:38:26", "remaining_time": "7:16:14"} +{"current_steps": 101, "total_steps": 1235, "loss": 0.6481, "lr": 3.258064516129033e-05, "epoch": 0.4089068825910931, "percentage": 8.18, "elapsed_time": "0:38:49", "remaining_time": "7:15:57"} +{"current_steps": 102, "total_steps": 1235, "loss": 0.6518, "lr": 3.2903225806451614e-05, "epoch": 0.41295546558704455, "percentage": 8.26, "elapsed_time": "0:39:13", "remaining_time": "7:15:44"} +{"current_steps": 103, "total_steps": 1235, "loss": 0.6502, "lr": 3.322580645161291e-05, "epoch": 0.41700404858299595, "percentage": 8.34, "elapsed_time": "0:39:35", "remaining_time": "7:15:11"} +{"current_steps": 104, "total_steps": 1235, "loss": 0.6305, "lr": 3.3548387096774195e-05, "epoch": 0.42105263157894735, "percentage": 8.42, "elapsed_time": "0:39:58", "remaining_time": "7:14:46"} +{"current_steps": 105, "total_steps": 1235, "loss": 0.6524, "lr": 3.387096774193549e-05, "epoch": 0.4251012145748988, "percentage": 8.5, "elapsed_time": "0:40:21", "remaining_time": "7:14:21"} +{"current_steps": 106, "total_steps": 1235, "loss": 0.6257, "lr": 3.4193548387096776e-05, "epoch": 0.4291497975708502, "percentage": 8.58, "elapsed_time": "0:40:44", "remaining_time": "7:13:52"} +{"current_steps": 107, "total_steps": 1235, "loss": 0.6413, "lr": 3.451612903225807e-05, "epoch": 0.4331983805668016, "percentage": 8.66, "elapsed_time": "0:41:08", "remaining_time": "7:13:39"} +{"current_steps": 108, "total_steps": 1235, "loss": 0.6672, "lr": 3.483870967741936e-05, "epoch": 0.43724696356275305, "percentage": 8.74, "elapsed_time": "0:41:31", "remaining_time": "7:13:18"} +{"current_steps": 109, "total_steps": 1235, "loss": 0.6421, "lr": 3.516129032258065e-05, "epoch": 0.44129554655870445, "percentage": 8.83, "elapsed_time": "0:41:53", "remaining_time": "7:12:44"} +{"current_steps": 110, "total_steps": 1235, "loss": 0.635, "lr": 3.548387096774194e-05, "epoch": 0.44534412955465585, "percentage": 8.91, "elapsed_time": "0:42:15", "remaining_time": "7:12:14"} +{"current_steps": 111, "total_steps": 1235, "loss": 0.6354, "lr": 3.5806451612903225e-05, "epoch": 0.4493927125506073, "percentage": 8.99, "elapsed_time": "0:42:39", "remaining_time": "7:11:55"} +{"current_steps": 112, "total_steps": 1235, "loss": 0.6434, "lr": 3.612903225806452e-05, "epoch": 0.4534412955465587, "percentage": 9.07, "elapsed_time": "0:43:01", "remaining_time": "7:11:24"} +{"current_steps": 113, "total_steps": 1235, "loss": 0.6371, "lr": 3.6451612903225805e-05, "epoch": 0.4574898785425101, "percentage": 9.15, "elapsed_time": "0:43:23", "remaining_time": "7:10:54"} +{"current_steps": 114, "total_steps": 1235, "loss": 0.6251, "lr": 3.67741935483871e-05, "epoch": 0.46153846153846156, "percentage": 9.23, "elapsed_time": "0:43:47", "remaining_time": "7:10:33"} +{"current_steps": 115, "total_steps": 1235, "loss": 0.6353, "lr": 3.7096774193548386e-05, "epoch": 0.46558704453441296, "percentage": 9.31, "elapsed_time": "0:44:10", "remaining_time": "7:10:13"} +{"current_steps": 116, "total_steps": 1235, "loss": 0.644, "lr": 3.741935483870968e-05, "epoch": 0.46963562753036436, "percentage": 9.39, "elapsed_time": "0:44:34", "remaining_time": "7:09:55"} +{"current_steps": 117, "total_steps": 1235, "loss": 0.6488, "lr": 3.7741935483870974e-05, "epoch": 0.47368421052631576, "percentage": 9.47, "elapsed_time": "0:44:56", "remaining_time": "7:09:31"} +{"current_steps": 118, "total_steps": 1235, "loss": 0.6593, "lr": 3.806451612903226e-05, "epoch": 0.4777327935222672, "percentage": 9.55, "elapsed_time": "0:45:20", "remaining_time": "7:09:10"} +{"current_steps": 119, "total_steps": 1235, "loss": 0.6397, "lr": 3.8387096774193555e-05, "epoch": 0.4817813765182186, "percentage": 9.64, "elapsed_time": "0:45:43", "remaining_time": "7:08:50"} +{"current_steps": 120, "total_steps": 1235, "loss": 0.6481, "lr": 3.870967741935484e-05, "epoch": 0.48582995951417, "percentage": 9.72, "elapsed_time": "0:46:06", "remaining_time": "7:08:25"} +{"current_steps": 121, "total_steps": 1235, "loss": 0.6309, "lr": 3.9032258064516135e-05, "epoch": 0.4898785425101215, "percentage": 9.8, "elapsed_time": "0:46:29", "remaining_time": "7:08:06"} +{"current_steps": 122, "total_steps": 1235, "loss": 0.6389, "lr": 3.935483870967742e-05, "epoch": 0.4939271255060729, "percentage": 9.88, "elapsed_time": "0:46:52", "remaining_time": "7:07:37"} +{"current_steps": 123, "total_steps": 1235, "loss": 0.6432, "lr": 3.9677419354838716e-05, "epoch": 0.4979757085020243, "percentage": 9.96, "elapsed_time": "0:47:15", "remaining_time": "7:07:15"} +{"current_steps": 124, "total_steps": 1235, "loss": 0.6348, "lr": 4e-05, "epoch": 0.5020242914979757, "percentage": 10.04, "elapsed_time": "0:47:38", "remaining_time": "7:06:52"} +{"current_steps": 125, "total_steps": 1235, "loss": 0.638, "lr": 3.9999920040266474e-05, "epoch": 0.5060728744939271, "percentage": 10.12, "elapsed_time": "0:48:00", "remaining_time": "7:06:20"} +{"current_steps": 126, "total_steps": 1235, "loss": 0.6616, "lr": 3.999968016170525e-05, "epoch": 0.5101214574898786, "percentage": 10.2, "elapsed_time": "0:48:24", "remaining_time": "7:06:03"} +{"current_steps": 127, "total_steps": 1235, "loss": 0.6304, "lr": 3.9999280366234394e-05, "epoch": 0.5141700404858299, "percentage": 10.28, "elapsed_time": "0:48:46", "remaining_time": "7:05:34"} +{"current_steps": 128, "total_steps": 1235, "loss": 0.6288, "lr": 3.999872065705065e-05, "epoch": 0.5182186234817814, "percentage": 10.36, "elapsed_time": "0:49:08", "remaining_time": "7:04:57"} +{"current_steps": 129, "total_steps": 1235, "loss": 0.6365, "lr": 3.999800103862945e-05, "epoch": 0.5222672064777328, "percentage": 10.45, "elapsed_time": "0:49:30", "remaining_time": "7:04:29"} +{"current_steps": 130, "total_steps": 1235, "loss": 0.6314, "lr": 3.9997121516724834e-05, "epoch": 0.5263157894736842, "percentage": 10.53, "elapsed_time": "0:49:53", "remaining_time": "7:04:05"} +{"current_steps": 131, "total_steps": 1235, "loss": 0.6323, "lr": 3.999608209836944e-05, "epoch": 0.5303643724696356, "percentage": 10.61, "elapsed_time": "0:50:16", "remaining_time": "7:03:38"} +{"current_steps": 132, "total_steps": 1235, "loss": 0.6424, "lr": 3.999488279187443e-05, "epoch": 0.5344129554655871, "percentage": 10.69, "elapsed_time": "0:50:39", "remaining_time": "7:03:14"} +{"current_steps": 133, "total_steps": 1235, "loss": 0.6364, "lr": 3.9993523606829425e-05, "epoch": 0.5384615384615384, "percentage": 10.77, "elapsed_time": "0:51:02", "remaining_time": "7:02:57"} +{"current_steps": 134, "total_steps": 1235, "loss": 0.6324, "lr": 3.9992004554102435e-05, "epoch": 0.5425101214574899, "percentage": 10.85, "elapsed_time": "0:51:26", "remaining_time": "7:02:42"} +{"current_steps": 135, "total_steps": 1235, "loss": 0.6321, "lr": 3.999032564583976e-05, "epoch": 0.5465587044534413, "percentage": 10.93, "elapsed_time": "0:51:48", "remaining_time": "7:02:11"} +{"current_steps": 136, "total_steps": 1235, "loss": 0.6235, "lr": 3.998848689546591e-05, "epoch": 0.5506072874493927, "percentage": 11.01, "elapsed_time": "0:52:11", "remaining_time": "7:01:44"} +{"current_steps": 137, "total_steps": 1235, "loss": 0.6497, "lr": 3.9986488317683496e-05, "epoch": 0.5546558704453441, "percentage": 11.09, "elapsed_time": "0:52:34", "remaining_time": "7:01:19"} +{"current_steps": 138, "total_steps": 1235, "loss": 0.6413, "lr": 3.9984329928473067e-05, "epoch": 0.5587044534412956, "percentage": 11.17, "elapsed_time": "0:52:58", "remaining_time": "7:01:02"} +{"current_steps": 139, "total_steps": 1235, "loss": 0.6367, "lr": 3.998201174509306e-05, "epoch": 0.562753036437247, "percentage": 11.26, "elapsed_time": "0:53:20", "remaining_time": "7:00:38"} +{"current_steps": 140, "total_steps": 1235, "loss": 0.646, "lr": 3.997953378607961e-05, "epoch": 0.5668016194331984, "percentage": 11.34, "elapsed_time": "0:53:43", "remaining_time": "7:00:10"} +{"current_steps": 141, "total_steps": 1235, "loss": 0.6422, "lr": 3.9976896071246403e-05, "epoch": 0.5708502024291497, "percentage": 11.42, "elapsed_time": "0:54:05", "remaining_time": "6:59:45"} +{"current_steps": 142, "total_steps": 1235, "loss": 0.6372, "lr": 3.997409862168454e-05, "epoch": 0.5748987854251012, "percentage": 11.5, "elapsed_time": "0:54:29", "remaining_time": "6:59:24"} +{"current_steps": 143, "total_steps": 1235, "loss": 0.6338, "lr": 3.997114145976237e-05, "epoch": 0.5789473684210527, "percentage": 11.58, "elapsed_time": "0:54:52", "remaining_time": "6:59:00"} +{"current_steps": 144, "total_steps": 1235, "loss": 0.6401, "lr": 3.9968024609125245e-05, "epoch": 0.582995951417004, "percentage": 11.66, "elapsed_time": "0:55:16", "remaining_time": "6:58:44"} +{"current_steps": 145, "total_steps": 1235, "loss": 0.6324, "lr": 3.996474809469545e-05, "epoch": 0.5870445344129555, "percentage": 11.74, "elapsed_time": "0:55:38", "remaining_time": "6:58:19"} +{"current_steps": 146, "total_steps": 1235, "loss": 0.638, "lr": 3.996131194267189e-05, "epoch": 0.5910931174089069, "percentage": 11.82, "elapsed_time": "0:56:02", "remaining_time": "6:57:58"} +{"current_steps": 147, "total_steps": 1235, "loss": 0.6395, "lr": 3.995771618052995e-05, "epoch": 0.5951417004048583, "percentage": 11.9, "elapsed_time": "0:56:24", "remaining_time": "6:57:27"} +{"current_steps": 148, "total_steps": 1235, "loss": 0.6326, "lr": 3.9953960837021256e-05, "epoch": 0.5991902834008097, "percentage": 11.98, "elapsed_time": "0:56:47", "remaining_time": "6:57:07"} +{"current_steps": 149, "total_steps": 1235, "loss": 0.6211, "lr": 3.995004594217343e-05, "epoch": 0.6032388663967612, "percentage": 12.06, "elapsed_time": "0:57:11", "remaining_time": "6:56:47"} +{"current_steps": 150, "total_steps": 1235, "loss": 0.6295, "lr": 3.994597152728987e-05, "epoch": 0.6072874493927125, "percentage": 12.15, "elapsed_time": "0:57:34", "remaining_time": "6:56:27"} +{"current_steps": 151, "total_steps": 1235, "loss": 0.6443, "lr": 3.994173762494947e-05, "epoch": 0.611336032388664, "percentage": 12.23, "elapsed_time": "0:57:57", "remaining_time": "6:56:06"} +{"current_steps": 152, "total_steps": 1235, "loss": 0.6322, "lr": 3.9937344269006424e-05, "epoch": 0.6153846153846154, "percentage": 12.31, "elapsed_time": "0:58:21", "remaining_time": "6:55:45"} +{"current_steps": 153, "total_steps": 1235, "loss": 0.6451, "lr": 3.993279149458988e-05, "epoch": 0.6194331983805668, "percentage": 12.39, "elapsed_time": "0:58:44", "remaining_time": "6:55:25"} +{"current_steps": 154, "total_steps": 1235, "loss": 0.6351, "lr": 3.9928079338103695e-05, "epoch": 0.6234817813765182, "percentage": 12.47, "elapsed_time": "0:59:08", "remaining_time": "6:55:07"} +{"current_steps": 155, "total_steps": 1235, "loss": 0.6286, "lr": 3.992320783722616e-05, "epoch": 0.6275303643724697, "percentage": 12.55, "elapsed_time": "0:59:32", "remaining_time": "6:54:49"} +{"current_steps": 156, "total_steps": 1235, "loss": 0.6463, "lr": 3.991817703090965e-05, "epoch": 0.631578947368421, "percentage": 12.63, "elapsed_time": "0:59:55", "remaining_time": "6:54:25"} +{"current_steps": 157, "total_steps": 1235, "loss": 0.6305, "lr": 3.991298695938038e-05, "epoch": 0.6356275303643725, "percentage": 12.71, "elapsed_time": "1:00:18", "remaining_time": "6:54:04"} +{"current_steps": 158, "total_steps": 1235, "loss": 0.6347, "lr": 3.9907637664138e-05, "epoch": 0.6396761133603239, "percentage": 12.79, "elapsed_time": "1:00:41", "remaining_time": "6:53:39"} +{"current_steps": 159, "total_steps": 1235, "loss": 0.6328, "lr": 3.990212918795534e-05, "epoch": 0.6437246963562753, "percentage": 12.87, "elapsed_time": "1:01:03", "remaining_time": "6:53:14"} +{"current_steps": 160, "total_steps": 1235, "loss": 0.6487, "lr": 3.9896461574878036e-05, "epoch": 0.6477732793522267, "percentage": 12.96, "elapsed_time": "1:01:26", "remaining_time": "6:52:49"} +{"current_steps": 161, "total_steps": 1235, "loss": 0.6371, "lr": 3.989063487022416e-05, "epoch": 0.6518218623481782, "percentage": 13.04, "elapsed_time": "1:01:49", "remaining_time": "6:52:22"} +{"current_steps": 162, "total_steps": 1235, "loss": 0.6339, "lr": 3.9884649120583903e-05, "epoch": 0.6558704453441295, "percentage": 13.12, "elapsed_time": "1:02:11", "remaining_time": "6:51:57"} +{"current_steps": 163, "total_steps": 1235, "loss": 0.6167, "lr": 3.987850437381915e-05, "epoch": 0.659919028340081, "percentage": 13.2, "elapsed_time": "1:02:35", "remaining_time": "6:51:35"} +{"current_steps": 164, "total_steps": 1235, "loss": 0.6282, "lr": 3.987220067906313e-05, "epoch": 0.6639676113360324, "percentage": 13.28, "elapsed_time": "1:02:59", "remaining_time": "6:51:19"} +{"current_steps": 165, "total_steps": 1235, "loss": 0.6395, "lr": 3.986573808672002e-05, "epoch": 0.6680161943319838, "percentage": 13.36, "elapsed_time": "1:03:22", "remaining_time": "6:50:58"} +{"current_steps": 166, "total_steps": 1235, "loss": 0.6232, "lr": 3.9859116648464534e-05, "epoch": 0.6720647773279352, "percentage": 13.44, "elapsed_time": "1:03:45", "remaining_time": "6:50:32"} +{"current_steps": 167, "total_steps": 1235, "loss": 0.6275, "lr": 3.985233641724152e-05, "epoch": 0.6761133603238867, "percentage": 13.52, "elapsed_time": "1:04:08", "remaining_time": "6:50:09"} +{"current_steps": 168, "total_steps": 1235, "loss": 0.6373, "lr": 3.984539744726554e-05, "epoch": 0.680161943319838, "percentage": 13.6, "elapsed_time": "1:04:31", "remaining_time": "6:49:47"} +{"current_steps": 169, "total_steps": 1235, "loss": 0.6088, "lr": 3.983829979402038e-05, "epoch": 0.6842105263157895, "percentage": 13.68, "elapsed_time": "1:04:52", "remaining_time": "6:49:15"} +{"current_steps": 170, "total_steps": 1235, "loss": 0.6277, "lr": 3.983104351425871e-05, "epoch": 0.6882591093117408, "percentage": 13.77, "elapsed_time": "1:05:16", "remaining_time": "6:48:54"} +{"current_steps": 171, "total_steps": 1235, "loss": 0.6312, "lr": 3.982362866600154e-05, "epoch": 0.6923076923076923, "percentage": 13.85, "elapsed_time": "1:05:39", "remaining_time": "6:48:33"} +{"current_steps": 172, "total_steps": 1235, "loss": 0.6408, "lr": 3.9816055308537806e-05, "epoch": 0.6963562753036437, "percentage": 13.93, "elapsed_time": "1:06:03", "remaining_time": "6:48:14"} +{"current_steps": 173, "total_steps": 1235, "loss": 0.6228, "lr": 3.980832350242388e-05, "epoch": 0.7004048582995951, "percentage": 14.01, "elapsed_time": "1:06:26", "remaining_time": "6:47:50"} +{"current_steps": 174, "total_steps": 1235, "loss": 0.6116, "lr": 3.980043330948306e-05, "epoch": 0.7044534412955465, "percentage": 14.09, "elapsed_time": "1:06:47", "remaining_time": "6:47:14"} +{"current_steps": 175, "total_steps": 1235, "loss": 0.6232, "lr": 3.9792384792805124e-05, "epoch": 0.708502024291498, "percentage": 14.17, "elapsed_time": "1:07:09", "remaining_time": "6:46:47"} +{"current_steps": 176, "total_steps": 1235, "loss": 0.6192, "lr": 3.978417801674579e-05, "epoch": 0.7125506072874493, "percentage": 14.25, "elapsed_time": "1:07:32", "remaining_time": "6:46:21"} +{"current_steps": 177, "total_steps": 1235, "loss": 0.6183, "lr": 3.9775813046926244e-05, "epoch": 0.7165991902834008, "percentage": 14.33, "elapsed_time": "1:07:54", "remaining_time": "6:45:57"} +{"current_steps": 178, "total_steps": 1235, "loss": 0.6072, "lr": 3.976728995023254e-05, "epoch": 0.7206477732793523, "percentage": 14.41, "elapsed_time": "1:08:18", "remaining_time": "6:45:37"} +{"current_steps": 179, "total_steps": 1235, "loss": 0.6153, "lr": 3.975860879481514e-05, "epoch": 0.7246963562753036, "percentage": 14.49, "elapsed_time": "1:08:40", "remaining_time": "6:45:06"} +{"current_steps": 180, "total_steps": 1235, "loss": 0.6368, "lr": 3.974976965008833e-05, "epoch": 0.728744939271255, "percentage": 14.57, "elapsed_time": "1:09:03", "remaining_time": "6:44:44"} +{"current_steps": 181, "total_steps": 1235, "loss": 0.6107, "lr": 3.9740772586729674e-05, "epoch": 0.7327935222672065, "percentage": 14.66, "elapsed_time": "1:09:25", "remaining_time": "6:44:18"} +{"current_steps": 182, "total_steps": 1235, "loss": 0.6216, "lr": 3.973161767667946e-05, "epoch": 0.7368421052631579, "percentage": 14.74, "elapsed_time": "1:09:49", "remaining_time": "6:43:58"} +{"current_steps": 183, "total_steps": 1235, "loss": 0.6309, "lr": 3.972230499314009e-05, "epoch": 0.7408906882591093, "percentage": 14.82, "elapsed_time": "1:10:12", "remaining_time": "6:43:33"} +{"current_steps": 184, "total_steps": 1235, "loss": 0.6123, "lr": 3.9712834610575545e-05, "epoch": 0.7449392712550608, "percentage": 14.9, "elapsed_time": "1:10:35", "remaining_time": "6:43:11"} +{"current_steps": 185, "total_steps": 1235, "loss": 0.6106, "lr": 3.9703206604710746e-05, "epoch": 0.7489878542510121, "percentage": 14.98, "elapsed_time": "1:10:57", "remaining_time": "6:42:45"} +{"current_steps": 186, "total_steps": 1235, "loss": 0.6229, "lr": 3.969342105253098e-05, "epoch": 0.7530364372469636, "percentage": 15.06, "elapsed_time": "1:11:18", "remaining_time": "6:42:12"} +{"current_steps": 187, "total_steps": 1235, "loss": 0.6015, "lr": 3.9683478032281246e-05, "epoch": 0.757085020242915, "percentage": 15.14, "elapsed_time": "1:11:40", "remaining_time": "6:41:42"} +{"current_steps": 188, "total_steps": 1235, "loss": 0.6124, "lr": 3.967337762346568e-05, "epoch": 0.7611336032388664, "percentage": 15.22, "elapsed_time": "1:12:04", "remaining_time": "6:41:21"} +{"current_steps": 189, "total_steps": 1235, "loss": 0.6182, "lr": 3.9663119906846885e-05, "epoch": 0.7651821862348178, "percentage": 15.3, "elapsed_time": "1:12:27", "remaining_time": "6:40:59"} +{"current_steps": 190, "total_steps": 1235, "loss": 0.6229, "lr": 3.965270496444528e-05, "epoch": 0.7692307692307693, "percentage": 15.38, "elapsed_time": "1:12:50", "remaining_time": "6:40:37"} +{"current_steps": 191, "total_steps": 1235, "loss": 0.6182, "lr": 3.9642132879538465e-05, "epoch": 0.7732793522267206, "percentage": 15.47, "elapsed_time": "1:13:12", "remaining_time": "6:40:10"} +{"current_steps": 192, "total_steps": 1235, "loss": 0.6093, "lr": 3.9631403736660566e-05, "epoch": 0.7773279352226721, "percentage": 15.55, "elapsed_time": "1:13:35", "remaining_time": "6:39:48"} +{"current_steps": 193, "total_steps": 1235, "loss": 0.6153, "lr": 3.962051762160151e-05, "epoch": 0.7813765182186235, "percentage": 15.63, "elapsed_time": "1:13:59", "remaining_time": "6:39:28"} +{"current_steps": 194, "total_steps": 1235, "loss": 0.6135, "lr": 3.960947462140638e-05, "epoch": 0.7854251012145749, "percentage": 15.71, "elapsed_time": "1:14:22", "remaining_time": "6:39:07"} +{"current_steps": 195, "total_steps": 1235, "loss": 0.616, "lr": 3.959827482437472e-05, "epoch": 0.7894736842105263, "percentage": 15.79, "elapsed_time": "1:14:44", "remaining_time": "6:38:36"} +{"current_steps": 196, "total_steps": 1235, "loss": 0.6284, "lr": 3.958691832005981e-05, "epoch": 0.7935222672064778, "percentage": 15.87, "elapsed_time": "1:15:07", "remaining_time": "6:38:14"} +{"current_steps": 197, "total_steps": 1235, "loss": 0.6242, "lr": 3.9575405199267944e-05, "epoch": 0.7975708502024291, "percentage": 15.95, "elapsed_time": "1:15:31", "remaining_time": "6:37:54"} +{"current_steps": 198, "total_steps": 1235, "loss": 0.617, "lr": 3.956373555405774e-05, "epoch": 0.8016194331983806, "percentage": 16.03, "elapsed_time": "1:15:53", "remaining_time": "6:37:27"} +{"current_steps": 199, "total_steps": 1235, "loss": 0.6241, "lr": 3.955190947773937e-05, "epoch": 0.805668016194332, "percentage": 16.11, "elapsed_time": "1:16:16", "remaining_time": "6:37:06"} +{"current_steps": 200, "total_steps": 1235, "loss": 0.6196, "lr": 3.9539927064873824e-05, "epoch": 0.8097165991902834, "percentage": 16.19, "elapsed_time": "1:16:39", "remaining_time": "6:36:44"} +{"current_steps": 201, "total_steps": 1235, "loss": 0.6354, "lr": 3.952778841127214e-05, "epoch": 0.8137651821862348, "percentage": 16.28, "elapsed_time": "1:17:03", "remaining_time": "6:36:26"} +{"current_steps": 202, "total_steps": 1235, "loss": 0.6195, "lr": 3.95154936139947e-05, "epoch": 0.8178137651821862, "percentage": 16.36, "elapsed_time": "1:17:27", "remaining_time": "6:36:09"} +{"current_steps": 203, "total_steps": 1235, "loss": 0.6086, "lr": 3.950304277135034e-05, "epoch": 0.8218623481781376, "percentage": 16.44, "elapsed_time": "1:17:51", "remaining_time": "6:35:47"} +{"current_steps": 204, "total_steps": 1235, "loss": 0.6229, "lr": 3.94904359828957e-05, "epoch": 0.8259109311740891, "percentage": 16.52, "elapsed_time": "1:18:14", "remaining_time": "6:35:27"} +{"current_steps": 205, "total_steps": 1235, "loss": 0.6165, "lr": 3.94776733494343e-05, "epoch": 0.8299595141700404, "percentage": 16.6, "elapsed_time": "1:18:38", "remaining_time": "6:35:07"} +{"current_steps": 206, "total_steps": 1235, "loss": 0.6148, "lr": 3.9464754973015826e-05, "epoch": 0.8340080971659919, "percentage": 16.68, "elapsed_time": "1:19:02", "remaining_time": "6:34:49"} +{"current_steps": 207, "total_steps": 1235, "loss": 0.6282, "lr": 3.9451680956935275e-05, "epoch": 0.8380566801619433, "percentage": 16.76, "elapsed_time": "1:19:24", "remaining_time": "6:34:22"} +{"current_steps": 208, "total_steps": 1235, "loss": 0.6183, "lr": 3.943845140573213e-05, "epoch": 0.8421052631578947, "percentage": 16.84, "elapsed_time": "1:19:48", "remaining_time": "6:34:01"} +{"current_steps": 209, "total_steps": 1235, "loss": 0.6182, "lr": 3.942506642518952e-05, "epoch": 0.8461538461538461, "percentage": 16.92, "elapsed_time": "1:20:11", "remaining_time": "6:33:39"} +{"current_steps": 210, "total_steps": 1235, "loss": 0.6043, "lr": 3.9411526122333396e-05, "epoch": 0.8502024291497976, "percentage": 17.0, "elapsed_time": "1:20:34", "remaining_time": "6:33:19"} +{"current_steps": 211, "total_steps": 1235, "loss": 0.6301, "lr": 3.939783060543167e-05, "epoch": 0.854251012145749, "percentage": 17.09, "elapsed_time": "1:20:57", "remaining_time": "6:32:56"} +{"current_steps": 212, "total_steps": 1235, "loss": 0.6092, "lr": 3.938397998399333e-05, "epoch": 0.8582995951417004, "percentage": 17.17, "elapsed_time": "1:21:20", "remaining_time": "6:32:32"} +{"current_steps": 213, "total_steps": 1235, "loss": 0.609, "lr": 3.936997436876756e-05, "epoch": 0.8623481781376519, "percentage": 17.25, "elapsed_time": "1:21:43", "remaining_time": "6:32:06"} +{"current_steps": 214, "total_steps": 1235, "loss": 0.6085, "lr": 3.935581387174289e-05, "epoch": 0.8663967611336032, "percentage": 17.33, "elapsed_time": "1:22:06", "remaining_time": "6:31:43"} +{"current_steps": 215, "total_steps": 1235, "loss": 0.6242, "lr": 3.9341498606146295e-05, "epoch": 0.8704453441295547, "percentage": 17.41, "elapsed_time": "1:22:28", "remaining_time": "6:31:17"} +{"current_steps": 216, "total_steps": 1235, "loss": 0.6042, "lr": 3.932702868644224e-05, "epoch": 0.8744939271255061, "percentage": 17.49, "elapsed_time": "1:22:50", "remaining_time": "6:30:49"} +{"current_steps": 217, "total_steps": 1235, "loss": 0.6344, "lr": 3.931240422833181e-05, "epoch": 0.8785425101214575, "percentage": 17.57, "elapsed_time": "1:23:14", "remaining_time": "6:30:28"} +{"current_steps": 218, "total_steps": 1235, "loss": 0.6313, "lr": 3.9297625348751806e-05, "epoch": 0.8825910931174089, "percentage": 17.65, "elapsed_time": "1:23:36", "remaining_time": "6:30:04"} +{"current_steps": 219, "total_steps": 1235, "loss": 0.6287, "lr": 3.9282692165873744e-05, "epoch": 0.8866396761133604, "percentage": 17.73, "elapsed_time": "1:23:59", "remaining_time": "6:29:39"} +{"current_steps": 220, "total_steps": 1235, "loss": 0.62, "lr": 3.9267604799102945e-05, "epoch": 0.8906882591093117, "percentage": 17.81, "elapsed_time": "1:24:22", "remaining_time": "6:29:16"} +{"current_steps": 221, "total_steps": 1235, "loss": 0.6062, "lr": 3.9252363369077615e-05, "epoch": 0.8947368421052632, "percentage": 17.89, "elapsed_time": "1:24:45", "remaining_time": "6:28:53"} +{"current_steps": 222, "total_steps": 1235, "loss": 0.6211, "lr": 3.9236967997667796e-05, "epoch": 0.8987854251012146, "percentage": 17.98, "elapsed_time": "1:25:08", "remaining_time": "6:28:31"} +{"current_steps": 223, "total_steps": 1235, "loss": 0.6253, "lr": 3.9221418807974496e-05, "epoch": 0.902834008097166, "percentage": 18.06, "elapsed_time": "1:25:32", "remaining_time": "6:28:09"} +{"current_steps": 224, "total_steps": 1235, "loss": 0.5996, "lr": 3.92057159243286e-05, "epoch": 0.9068825910931174, "percentage": 18.14, "elapsed_time": "1:25:55", "remaining_time": "6:27:48"} +{"current_steps": 225, "total_steps": 1235, "loss": 0.615, "lr": 3.9189859472289956e-05, "epoch": 0.9109311740890689, "percentage": 18.22, "elapsed_time": "1:26:18", "remaining_time": "6:27:26"} +{"current_steps": 226, "total_steps": 1235, "loss": 0.6171, "lr": 3.9173849578646324e-05, "epoch": 0.9149797570850202, "percentage": 18.3, "elapsed_time": "1:26:41", "remaining_time": "6:27:03"} +{"current_steps": 227, "total_steps": 1235, "loss": 0.6078, "lr": 3.9157686371412395e-05, "epoch": 0.9190283400809717, "percentage": 18.38, "elapsed_time": "1:27:04", "remaining_time": "6:26:41"} +{"current_steps": 228, "total_steps": 1235, "loss": 0.5878, "lr": 3.914136997982874e-05, "epoch": 0.9230769230769231, "percentage": 18.46, "elapsed_time": "1:27:27", "remaining_time": "6:26:18"} +{"current_steps": 229, "total_steps": 1235, "loss": 0.6049, "lr": 3.912490053436079e-05, "epoch": 0.9271255060728745, "percentage": 18.54, "elapsed_time": "1:27:51", "remaining_time": "6:25:56"} +{"current_steps": 230, "total_steps": 1235, "loss": 0.6119, "lr": 3.9108278166697805e-05, "epoch": 0.9311740890688259, "percentage": 18.62, "elapsed_time": "1:28:14", "remaining_time": "6:25:33"} +{"current_steps": 231, "total_steps": 1235, "loss": 0.5956, "lr": 3.909150300975178e-05, "epoch": 0.9352226720647774, "percentage": 18.7, "elapsed_time": "1:28:36", "remaining_time": "6:25:06"} +{"current_steps": 232, "total_steps": 1235, "loss": 0.6237, "lr": 3.907457519765642e-05, "epoch": 0.9392712550607287, "percentage": 18.79, "elapsed_time": "1:28:57", "remaining_time": "6:24:37"} +{"current_steps": 233, "total_steps": 1235, "loss": 0.6038, "lr": 3.905749486576607e-05, "epoch": 0.9433198380566802, "percentage": 18.87, "elapsed_time": "1:29:20", "remaining_time": "6:24:13"} +{"current_steps": 234, "total_steps": 1235, "loss": 0.6098, "lr": 3.90402621506546e-05, "epoch": 0.9473684210526315, "percentage": 18.95, "elapsed_time": "1:29:43", "remaining_time": "6:23:48"} +{"current_steps": 235, "total_steps": 1235, "loss": 0.6132, "lr": 3.902287719011435e-05, "epoch": 0.951417004048583, "percentage": 19.03, "elapsed_time": "1:30:06", "remaining_time": "6:23:28"} +{"current_steps": 236, "total_steps": 1235, "loss": 0.6143, "lr": 3.900534012315499e-05, "epoch": 0.9554655870445344, "percentage": 19.11, "elapsed_time": "1:30:30", "remaining_time": "6:23:08"} +{"current_steps": 237, "total_steps": 1235, "loss": 0.6078, "lr": 3.8987651090002454e-05, "epoch": 0.9595141700404858, "percentage": 19.19, "elapsed_time": "1:30:54", "remaining_time": "6:22:46"} +{"current_steps": 238, "total_steps": 1235, "loss": 0.626, "lr": 3.896981023209777e-05, "epoch": 0.9635627530364372, "percentage": 19.27, "elapsed_time": "1:31:16", "remaining_time": "6:22:20"} +{"current_steps": 239, "total_steps": 1235, "loss": 0.6116, "lr": 3.8951817692095966e-05, "epoch": 0.9676113360323887, "percentage": 19.35, "elapsed_time": "1:31:39", "remaining_time": "6:21:59"} +{"current_steps": 240, "total_steps": 1235, "loss": 0.6156, "lr": 3.893367361386491e-05, "epoch": 0.97165991902834, "percentage": 19.43, "elapsed_time": "1:32:03", "remaining_time": "6:21:38"} +{"current_steps": 241, "total_steps": 1235, "loss": 0.6068, "lr": 3.891537814248417e-05, "epoch": 0.9757085020242915, "percentage": 19.51, "elapsed_time": "1:32:26", "remaining_time": "6:21:18"} +{"current_steps": 242, "total_steps": 1235, "loss": 0.6081, "lr": 3.889693142424384e-05, "epoch": 0.979757085020243, "percentage": 19.6, "elapsed_time": "1:32:51", "remaining_time": "6:20:59"} +{"current_steps": 243, "total_steps": 1235, "loss": 0.6124, "lr": 3.8878333606643405e-05, "epoch": 0.9838056680161943, "percentage": 19.68, "elapsed_time": "1:33:14", "remaining_time": "6:20:39"} +{"current_steps": 244, "total_steps": 1235, "loss": 0.6111, "lr": 3.885958483839049e-05, "epoch": 0.9878542510121457, "percentage": 19.76, "elapsed_time": "1:33:38", "remaining_time": "6:20:19"} +{"current_steps": 245, "total_steps": 1235, "loss": 0.6314, "lr": 3.8840685269399786e-05, "epoch": 0.9919028340080972, "percentage": 19.84, "elapsed_time": "1:34:00", "remaining_time": "6:19:52"} +{"current_steps": 246, "total_steps": 1235, "loss": 0.6119, "lr": 3.882163505079171e-05, "epoch": 0.9959514170040485, "percentage": 19.92, "elapsed_time": "1:34:24", "remaining_time": "6:19:34"} +{"current_steps": 247, "total_steps": 1235, "loss": 0.5973, "lr": 3.880243433489132e-05, "epoch": 1.0, "percentage": 20.0, "elapsed_time": "1:34:48", "remaining_time": "6:19:12"} +{"current_steps": 248, "total_steps": 1235, "loss": 0.5576, "lr": 3.878308327522702e-05, "epoch": 1.0040485829959513, "percentage": 20.08, "elapsed_time": "1:36:56", "remaining_time": "6:25:49"} +{"current_steps": 249, "total_steps": 1235, "loss": 0.5447, "lr": 3.876358202652936e-05, "epoch": 1.008097165991903, "percentage": 20.16, "elapsed_time": "1:37:20", "remaining_time": "6:25:25"} +{"current_steps": 250, "total_steps": 1235, "loss": 0.5751, "lr": 3.8743930744729835e-05, "epoch": 1.0121457489878543, "percentage": 20.24, "elapsed_time": "1:37:43", "remaining_time": "6:25:01"} +{"current_steps": 251, "total_steps": 1235, "loss": 0.5575, "lr": 3.8724129586959535e-05, "epoch": 1.0161943319838056, "percentage": 20.32, "elapsed_time": "1:38:07", "remaining_time": "6:24:38"} +{"current_steps": 252, "total_steps": 1235, "loss": 0.549, "lr": 3.870417871154801e-05, "epoch": 1.0202429149797572, "percentage": 20.4, "elapsed_time": "1:38:30", "remaining_time": "6:24:16"} +{"current_steps": 253, "total_steps": 1235, "loss": 0.5483, "lr": 3.868407827802192e-05, "epoch": 1.0242914979757085, "percentage": 20.49, "elapsed_time": "1:38:54", "remaining_time": "6:23:54"} +{"current_steps": 254, "total_steps": 1235, "loss": 0.5558, "lr": 3.8663828447103804e-05, "epoch": 1.0283400809716599, "percentage": 20.57, "elapsed_time": "1:39:16", "remaining_time": "6:23:25"} +{"current_steps": 255, "total_steps": 1235, "loss": 0.5571, "lr": 3.8643429380710765e-05, "epoch": 1.0323886639676114, "percentage": 20.65, "elapsed_time": "1:39:39", "remaining_time": "6:22:59"} +{"current_steps": 256, "total_steps": 1235, "loss": 0.5507, "lr": 3.862288124195319e-05, "epoch": 1.0364372469635628, "percentage": 20.73, "elapsed_time": "1:40:01", "remaining_time": "6:22:32"} +{"current_steps": 257, "total_steps": 1235, "loss": 0.56, "lr": 3.8602184195133464e-05, "epoch": 1.040485829959514, "percentage": 20.81, "elapsed_time": "1:40:24", "remaining_time": "6:22:05"} +{"current_steps": 258, "total_steps": 1235, "loss": 0.5328, "lr": 3.8581338405744604e-05, "epoch": 1.0445344129554657, "percentage": 20.89, "elapsed_time": "1:40:46", "remaining_time": "6:21:38"} +{"current_steps": 259, "total_steps": 1235, "loss": 0.5478, "lr": 3.8560344040468996e-05, "epoch": 1.048582995951417, "percentage": 20.97, "elapsed_time": "1:41:10", "remaining_time": "6:21:15"} +{"current_steps": 260, "total_steps": 1235, "loss": 0.5457, "lr": 3.853920126717703e-05, "epoch": 1.0526315789473684, "percentage": 21.05, "elapsed_time": "1:41:32", "remaining_time": "6:20:47"} +{"current_steps": 261, "total_steps": 1235, "loss": 0.5674, "lr": 3.851791025492574e-05, "epoch": 1.05668016194332, "percentage": 21.13, "elapsed_time": "1:41:55", "remaining_time": "6:20:22"} +{"current_steps": 262, "total_steps": 1235, "loss": 0.5565, "lr": 3.8496471173957515e-05, "epoch": 1.0607287449392713, "percentage": 21.21, "elapsed_time": "1:42:18", "remaining_time": "6:19:56"} +{"current_steps": 263, "total_steps": 1235, "loss": 0.5518, "lr": 3.847488419569866e-05, "epoch": 1.0647773279352226, "percentage": 21.3, "elapsed_time": "1:42:40", "remaining_time": "6:19:29"} +{"current_steps": 264, "total_steps": 1235, "loss": 0.5296, "lr": 3.8453149492758077e-05, "epoch": 1.0688259109311742, "percentage": 21.38, "elapsed_time": "1:43:04", "remaining_time": "6:19:06"} +{"current_steps": 265, "total_steps": 1235, "loss": 0.553, "lr": 3.8431267238925886e-05, "epoch": 1.0728744939271255, "percentage": 21.46, "elapsed_time": "1:43:27", "remaining_time": "6:18:41"} +{"current_steps": 266, "total_steps": 1235, "loss": 0.546, "lr": 3.840923760917199e-05, "epoch": 1.0769230769230769, "percentage": 21.54, "elapsed_time": "1:43:49", "remaining_time": "6:18:13"} +{"current_steps": 267, "total_steps": 1235, "loss": 0.5558, "lr": 3.838706077964473e-05, "epoch": 1.0809716599190284, "percentage": 21.62, "elapsed_time": "1:44:12", "remaining_time": "6:17:48"} +{"current_steps": 268, "total_steps": 1235, "loss": 0.5435, "lr": 3.836473692766944e-05, "epoch": 1.0850202429149798, "percentage": 21.7, "elapsed_time": "1:44:34", "remaining_time": "6:17:20"} +{"current_steps": 269, "total_steps": 1235, "loss": 0.5594, "lr": 3.834226623174705e-05, "epoch": 1.0890688259109311, "percentage": 21.78, "elapsed_time": "1:44:57", "remaining_time": "6:16:55"} +{"current_steps": 270, "total_steps": 1235, "loss": 0.55, "lr": 3.831964887155264e-05, "epoch": 1.0931174089068827, "percentage": 21.86, "elapsed_time": "1:45:20", "remaining_time": "6:16:31"} +{"current_steps": 271, "total_steps": 1235, "loss": 0.5395, "lr": 3.829688502793403e-05, "epoch": 1.097165991902834, "percentage": 21.94, "elapsed_time": "1:45:44", "remaining_time": "6:16:08"} +{"current_steps": 272, "total_steps": 1235, "loss": 0.5651, "lr": 3.827397488291029e-05, "epoch": 1.1012145748987854, "percentage": 22.02, "elapsed_time": "1:46:08", "remaining_time": "6:15:46"} +{"current_steps": 273, "total_steps": 1235, "loss": 0.5547, "lr": 3.8250918619670343e-05, "epoch": 1.1052631578947367, "percentage": 22.11, "elapsed_time": "1:46:31", "remaining_time": "6:15:23"} +{"current_steps": 274, "total_steps": 1235, "loss": 0.5585, "lr": 3.822771642257145e-05, "epoch": 1.1093117408906883, "percentage": 22.19, "elapsed_time": "1:46:54", "remaining_time": "6:14:57"} +{"current_steps": 275, "total_steps": 1235, "loss": 0.5588, "lr": 3.820436847713776e-05, "epoch": 1.1133603238866396, "percentage": 22.27, "elapsed_time": "1:47:18", "remaining_time": "6:14:34"} +{"current_steps": 276, "total_steps": 1235, "loss": 0.5429, "lr": 3.8180874970058826e-05, "epoch": 1.117408906882591, "percentage": 22.35, "elapsed_time": "1:47:42", "remaining_time": "6:14:13"} +{"current_steps": 277, "total_steps": 1235, "loss": 0.5617, "lr": 3.8157236089188103e-05, "epoch": 1.1214574898785425, "percentage": 22.43, "elapsed_time": "1:48:05", "remaining_time": "6:13:50"} +{"current_steps": 278, "total_steps": 1235, "loss": 0.5435, "lr": 3.813345202354145e-05, "epoch": 1.125506072874494, "percentage": 22.51, "elapsed_time": "1:48:28", "remaining_time": "6:13:26"} +{"current_steps": 279, "total_steps": 1235, "loss": 0.5556, "lr": 3.810952296329563e-05, "epoch": 1.1295546558704452, "percentage": 22.59, "elapsed_time": "1:48:50", "remaining_time": "6:12:55"} +{"current_steps": 280, "total_steps": 1235, "loss": 0.5508, "lr": 3.808544909978676e-05, "epoch": 1.1336032388663968, "percentage": 22.67, "elapsed_time": "1:49:12", "remaining_time": "6:12:28"} +{"current_steps": 281, "total_steps": 1235, "loss": 0.5498, "lr": 3.806123062550882e-05, "epoch": 1.1376518218623481, "percentage": 22.75, "elapsed_time": "1:49:35", "remaining_time": "6:12:04"} +{"current_steps": 282, "total_steps": 1235, "loss": 0.5475, "lr": 3.803686773411208e-05, "epoch": 1.1417004048582995, "percentage": 22.83, "elapsed_time": "1:49:59", "remaining_time": "6:11:42"} +{"current_steps": 283, "total_steps": 1235, "loss": 0.5521, "lr": 3.801236062040158e-05, "epoch": 1.145748987854251, "percentage": 22.91, "elapsed_time": "1:50:23", "remaining_time": "6:11:20"} +{"current_steps": 284, "total_steps": 1235, "loss": 0.5354, "lr": 3.798770948033553e-05, "epoch": 1.1497975708502024, "percentage": 23.0, "elapsed_time": "1:50:46", "remaining_time": "6:10:56"} +{"current_steps": 285, "total_steps": 1235, "loss": 0.5496, "lr": 3.796291451102381e-05, "epoch": 1.1538461538461537, "percentage": 23.08, "elapsed_time": "1:51:09", "remaining_time": "6:10:32"} +{"current_steps": 286, "total_steps": 1235, "loss": 0.5485, "lr": 3.793797591072631e-05, "epoch": 1.1578947368421053, "percentage": 23.16, "elapsed_time": "1:51:33", "remaining_time": "6:10:10"} +{"current_steps": 287, "total_steps": 1235, "loss": 0.5614, "lr": 3.791289387885144e-05, "epoch": 1.1619433198380567, "percentage": 23.24, "elapsed_time": "1:51:55", "remaining_time": "6:09:43"} +{"current_steps": 288, "total_steps": 1235, "loss": 0.5398, "lr": 3.788766861595443e-05, "epoch": 1.165991902834008, "percentage": 23.32, "elapsed_time": "1:52:17", "remaining_time": "6:09:14"} +{"current_steps": 289, "total_steps": 1235, "loss": 0.5482, "lr": 3.7862300323735835e-05, "epoch": 1.1700404858299596, "percentage": 23.4, "elapsed_time": "1:52:39", "remaining_time": "6:08:45"} +{"current_steps": 290, "total_steps": 1235, "loss": 0.5643, "lr": 3.783678920503983e-05, "epoch": 1.174089068825911, "percentage": 23.48, "elapsed_time": "1:53:02", "remaining_time": "6:08:21"} +{"current_steps": 291, "total_steps": 1235, "loss": 0.5786, "lr": 3.781113546385265e-05, "epoch": 1.1781376518218623, "percentage": 23.56, "elapsed_time": "1:53:25", "remaining_time": "6:07:57"} +{"current_steps": 292, "total_steps": 1235, "loss": 0.5533, "lr": 3.7785339305300916e-05, "epoch": 1.1821862348178138, "percentage": 23.64, "elapsed_time": "1:53:49", "remaining_time": "6:07:33"} +{"current_steps": 293, "total_steps": 1235, "loss": 0.553, "lr": 3.7759400935650025e-05, "epoch": 1.1862348178137652, "percentage": 23.72, "elapsed_time": "1:54:12", "remaining_time": "6:07:09"} +{"current_steps": 294, "total_steps": 1235, "loss": 0.5337, "lr": 3.77333205623025e-05, "epoch": 1.1902834008097165, "percentage": 23.81, "elapsed_time": "1:54:34", "remaining_time": "6:06:44"} +{"current_steps": 295, "total_steps": 1235, "loss": 0.5469, "lr": 3.7707098393796295e-05, "epoch": 1.194331983805668, "percentage": 23.89, "elapsed_time": "1:54:57", "remaining_time": "6:06:19"} +{"current_steps": 296, "total_steps": 1235, "loss": 0.5497, "lr": 3.7680734639803185e-05, "epoch": 1.1983805668016194, "percentage": 23.97, "elapsed_time": "1:55:20", "remaining_time": "6:05:53"} +{"current_steps": 297, "total_steps": 1235, "loss": 0.5628, "lr": 3.765422951112704e-05, "epoch": 1.2024291497975708, "percentage": 24.05, "elapsed_time": "1:55:43", "remaining_time": "6:05:30"} +{"current_steps": 298, "total_steps": 1235, "loss": 0.5549, "lr": 3.762758321970216e-05, "epoch": 1.2064777327935223, "percentage": 24.13, "elapsed_time": "1:56:05", "remaining_time": "6:05:02"} +{"current_steps": 299, "total_steps": 1235, "loss": 0.5493, "lr": 3.7600795978591584e-05, "epoch": 1.2105263157894737, "percentage": 24.21, "elapsed_time": "1:56:28", "remaining_time": "6:04:37"} +{"current_steps": 300, "total_steps": 1235, "loss": 0.562, "lr": 3.757386800198538e-05, "epoch": 1.214574898785425, "percentage": 24.29, "elapsed_time": "1:56:51", "remaining_time": "6:04:13"} +{"current_steps": 301, "total_steps": 1235, "loss": 0.5597, "lr": 3.7546799505198925e-05, "epoch": 1.2186234817813766, "percentage": 24.37, "elapsed_time": "1:57:14", "remaining_time": "6:03:48"} +{"current_steps": 302, "total_steps": 1235, "loss": 0.5524, "lr": 3.7519590704671197e-05, "epoch": 1.222672064777328, "percentage": 24.45, "elapsed_time": "1:57:37", "remaining_time": "6:03:22"} +{"current_steps": 303, "total_steps": 1235, "loss": 0.5554, "lr": 3.749224181796305e-05, "epoch": 1.2267206477732793, "percentage": 24.53, "elapsed_time": "1:57:59", "remaining_time": "6:02:55"} +{"current_steps": 304, "total_steps": 1235, "loss": 0.562, "lr": 3.746475306375545e-05, "epoch": 1.2307692307692308, "percentage": 24.62, "elapsed_time": "1:58:22", "remaining_time": "6:02:30"} +{"current_steps": 305, "total_steps": 1235, "loss": 0.5567, "lr": 3.743712466184774e-05, "epoch": 1.2348178137651822, "percentage": 24.7, "elapsed_time": "1:58:45", "remaining_time": "6:02:05"} +{"current_steps": 306, "total_steps": 1235, "loss": 0.5658, "lr": 3.7409356833155885e-05, "epoch": 1.2388663967611335, "percentage": 24.78, "elapsed_time": "1:59:08", "remaining_time": "6:01:41"} +{"current_steps": 307, "total_steps": 1235, "loss": 0.5548, "lr": 3.73814497997107e-05, "epoch": 1.242914979757085, "percentage": 24.86, "elapsed_time": "1:59:31", "remaining_time": "6:01:17"} +{"current_steps": 308, "total_steps": 1235, "loss": 0.5536, "lr": 3.7353403784656095e-05, "epoch": 1.2469635627530364, "percentage": 24.94, "elapsed_time": "1:59:54", "remaining_time": "6:00:53"} +{"current_steps": 309, "total_steps": 1235, "loss": 0.549, "lr": 3.732521901224724e-05, "epoch": 1.2510121457489878, "percentage": 25.02, "elapsed_time": "2:00:18", "remaining_time": "6:00:31"} +{"current_steps": 310, "total_steps": 1235, "loss": 0.5731, "lr": 3.7296895707848844e-05, "epoch": 1.2550607287449393, "percentage": 25.1, "elapsed_time": "2:00:41", "remaining_time": "6:00:06"} +{"current_steps": 311, "total_steps": 1235, "loss": 0.546, "lr": 3.7268434097933275e-05, "epoch": 1.2591093117408907, "percentage": 25.18, "elapsed_time": "2:01:02", "remaining_time": "5:59:36"} +{"current_steps": 312, "total_steps": 1235, "loss": 0.5437, "lr": 3.723983441007882e-05, "epoch": 1.263157894736842, "percentage": 25.26, "elapsed_time": "2:01:25", "remaining_time": "5:59:13"} +{"current_steps": 313, "total_steps": 1235, "loss": 0.5522, "lr": 3.721109687296781e-05, "epoch": 1.2672064777327936, "percentage": 25.34, "elapsed_time": "2:01:48", "remaining_time": "5:58:49"} +{"current_steps": 314, "total_steps": 1235, "loss": 0.5627, "lr": 3.718222171638484e-05, "epoch": 1.271255060728745, "percentage": 25.43, "elapsed_time": "2:02:12", "remaining_time": "5:58:27"} +{"current_steps": 315, "total_steps": 1235, "loss": 0.5508, "lr": 3.715320917121488e-05, "epoch": 1.2753036437246963, "percentage": 25.51, "elapsed_time": "2:02:36", "remaining_time": "5:58:04"} +{"current_steps": 316, "total_steps": 1235, "loss": 0.5627, "lr": 3.712405946944149e-05, "epoch": 1.2793522267206479, "percentage": 25.59, "elapsed_time": "2:02:59", "remaining_time": "5:57:40"} +{"current_steps": 317, "total_steps": 1235, "loss": 0.5493, "lr": 3.709477284414488e-05, "epoch": 1.2834008097165992, "percentage": 25.67, "elapsed_time": "2:03:21", "remaining_time": "5:57:14"} +{"current_steps": 318, "total_steps": 1235, "loss": 0.5511, "lr": 3.7065349529500136e-05, "epoch": 1.2874493927125505, "percentage": 25.75, "elapsed_time": "2:03:44", "remaining_time": "5:56:50"} +{"current_steps": 319, "total_steps": 1235, "loss": 0.5548, "lr": 3.7035789760775305e-05, "epoch": 1.291497975708502, "percentage": 25.83, "elapsed_time": "2:04:07", "remaining_time": "5:56:24"} +{"current_steps": 320, "total_steps": 1235, "loss": 0.5613, "lr": 3.70060937743295e-05, "epoch": 1.2955465587044535, "percentage": 25.91, "elapsed_time": "2:04:31", "remaining_time": "5:56:03"} +{"current_steps": 321, "total_steps": 1235, "loss": 0.5589, "lr": 3.6976261807611045e-05, "epoch": 1.2995951417004048, "percentage": 25.99, "elapsed_time": "2:04:53", "remaining_time": "5:55:36"} +{"current_steps": 322, "total_steps": 1235, "loss": 0.5485, "lr": 3.694629409915555e-05, "epoch": 1.3036437246963564, "percentage": 26.07, "elapsed_time": "2:05:16", "remaining_time": "5:55:12"} +{"current_steps": 323, "total_steps": 1235, "loss": 0.5454, "lr": 3.691619088858401e-05, "epoch": 1.3076923076923077, "percentage": 26.15, "elapsed_time": "2:05:40", "remaining_time": "5:54:50"} +{"current_steps": 324, "total_steps": 1235, "loss": 0.5529, "lr": 3.68859524166009e-05, "epoch": 1.311740890688259, "percentage": 26.23, "elapsed_time": "2:06:03", "remaining_time": "5:54:26"} +{"current_steps": 325, "total_steps": 1235, "loss": 0.5475, "lr": 3.6855578924992226e-05, "epoch": 1.3157894736842106, "percentage": 26.32, "elapsed_time": "2:06:27", "remaining_time": "5:54:04"} +{"current_steps": 326, "total_steps": 1235, "loss": 0.5486, "lr": 3.6825070656623626e-05, "epoch": 1.319838056680162, "percentage": 26.4, "elapsed_time": "2:06:49", "remaining_time": "5:53:38"} +{"current_steps": 327, "total_steps": 1235, "loss": 0.5589, "lr": 3.67944278554384e-05, "epoch": 1.3238866396761133, "percentage": 26.48, "elapsed_time": "2:07:13", "remaining_time": "5:53:16"} +{"current_steps": 328, "total_steps": 1235, "loss": 0.5496, "lr": 3.676365076645557e-05, "epoch": 1.3279352226720649, "percentage": 26.56, "elapsed_time": "2:07:36", "remaining_time": "5:52:52"} +{"current_steps": 329, "total_steps": 1235, "loss": 0.5515, "lr": 3.673273963576791e-05, "epoch": 1.3319838056680162, "percentage": 26.64, "elapsed_time": "2:07:59", "remaining_time": "5:52:29"} +{"current_steps": 330, "total_steps": 1235, "loss": 0.5575, "lr": 3.670169471054001e-05, "epoch": 1.3360323886639676, "percentage": 26.72, "elapsed_time": "2:08:23", "remaining_time": "5:52:06"} +{"current_steps": 331, "total_steps": 1235, "loss": 0.5674, "lr": 3.6670516239006254e-05, "epoch": 1.3400809716599191, "percentage": 26.8, "elapsed_time": "2:08:46", "remaining_time": "5:51:42"} +{"current_steps": 332, "total_steps": 1235, "loss": 0.5472, "lr": 3.663920447046888e-05, "epoch": 1.3441295546558705, "percentage": 26.88, "elapsed_time": "2:09:09", "remaining_time": "5:51:16"} +{"current_steps": 333, "total_steps": 1235, "loss": 0.5639, "lr": 3.6607759655295954e-05, "epoch": 1.3481781376518218, "percentage": 26.96, "elapsed_time": "2:09:32", "remaining_time": "5:50:52"} +{"current_steps": 334, "total_steps": 1235, "loss": 0.5476, "lr": 3.657618204491937e-05, "epoch": 1.3522267206477734, "percentage": 27.04, "elapsed_time": "2:09:55", "remaining_time": "5:50:28"} +{"current_steps": 335, "total_steps": 1235, "loss": 0.5648, "lr": 3.6544471891832875e-05, "epoch": 1.3562753036437247, "percentage": 27.13, "elapsed_time": "2:10:18", "remaining_time": "5:50:03"} +{"current_steps": 336, "total_steps": 1235, "loss": 0.5646, "lr": 3.6512629449589983e-05, "epoch": 1.360323886639676, "percentage": 27.21, "elapsed_time": "2:10:42", "remaining_time": "5:49:42"} +{"current_steps": 337, "total_steps": 1235, "loss": 0.5732, "lr": 3.6480654972802045e-05, "epoch": 1.3643724696356276, "percentage": 27.29, "elapsed_time": "2:11:04", "remaining_time": "5:49:16"} +{"current_steps": 338, "total_steps": 1235, "loss": 0.5765, "lr": 3.644854871713611e-05, "epoch": 1.368421052631579, "percentage": 27.37, "elapsed_time": "2:11:27", "remaining_time": "5:48:53"} +{"current_steps": 339, "total_steps": 1235, "loss": 0.5645, "lr": 3.6416310939312924e-05, "epoch": 1.3724696356275303, "percentage": 27.45, "elapsed_time": "2:11:50", "remaining_time": "5:48:27"} +{"current_steps": 340, "total_steps": 1235, "loss": 0.552, "lr": 3.638394189710493e-05, "epoch": 1.376518218623482, "percentage": 27.53, "elapsed_time": "2:12:13", "remaining_time": "5:48:03"} +{"current_steps": 341, "total_steps": 1235, "loss": 0.5495, "lr": 3.635144184933412e-05, "epoch": 1.3805668016194332, "percentage": 27.61, "elapsed_time": "2:12:36", "remaining_time": "5:47:39"} +{"current_steps": 342, "total_steps": 1235, "loss": 0.5488, "lr": 3.6318811055869994e-05, "epoch": 1.3846153846153846, "percentage": 27.69, "elapsed_time": "2:13:00", "remaining_time": "5:47:16"} +{"current_steps": 343, "total_steps": 1235, "loss": 0.5688, "lr": 3.628604977762752e-05, "epoch": 1.3886639676113361, "percentage": 27.77, "elapsed_time": "2:13:23", "remaining_time": "5:46:53"} +{"current_steps": 344, "total_steps": 1235, "loss": 0.5455, "lr": 3.6253158276565004e-05, "epoch": 1.3927125506072875, "percentage": 27.85, "elapsed_time": "2:13:46", "remaining_time": "5:46:29"} +{"current_steps": 345, "total_steps": 1235, "loss": 0.5696, "lr": 3.6220136815682016e-05, "epoch": 1.3967611336032388, "percentage": 27.94, "elapsed_time": "2:14:08", "remaining_time": "5:46:03"} +{"current_steps": 346, "total_steps": 1235, "loss": 0.5619, "lr": 3.618698565901727e-05, "epoch": 1.4008097165991904, "percentage": 28.02, "elapsed_time": "2:14:32", "remaining_time": "5:45:40"} +{"current_steps": 347, "total_steps": 1235, "loss": 0.5493, "lr": 3.615370507164654e-05, "epoch": 1.4048582995951417, "percentage": 28.1, "elapsed_time": "2:14:53", "remaining_time": "5:45:13"} +{"current_steps": 348, "total_steps": 1235, "loss": 0.5515, "lr": 3.61202953196805e-05, "epoch": 1.408906882591093, "percentage": 28.18, "elapsed_time": "2:15:17", "remaining_time": "5:44:49"} +{"current_steps": 349, "total_steps": 1235, "loss": 0.5461, "lr": 3.6086756670262654e-05, "epoch": 1.4129554655870447, "percentage": 28.26, "elapsed_time": "2:15:40", "remaining_time": "5:44:24"} +{"current_steps": 350, "total_steps": 1235, "loss": 0.5476, "lr": 3.6053089391567135e-05, "epoch": 1.417004048582996, "percentage": 28.34, "elapsed_time": "2:16:03", "remaining_time": "5:44:02"} +{"current_steps": 351, "total_steps": 1235, "loss": 0.559, "lr": 3.601929375279662e-05, "epoch": 1.4210526315789473, "percentage": 28.42, "elapsed_time": "2:16:27", "remaining_time": "5:43:41"} +{"current_steps": 352, "total_steps": 1235, "loss": 0.5369, "lr": 3.598537002418012e-05, "epoch": 1.425101214574899, "percentage": 28.5, "elapsed_time": "2:16:51", "remaining_time": "5:43:18"} +{"current_steps": 353, "total_steps": 1235, "loss": 0.546, "lr": 3.5951318476970885e-05, "epoch": 1.4291497975708503, "percentage": 28.58, "elapsed_time": "2:17:14", "remaining_time": "5:42:55"} +{"current_steps": 354, "total_steps": 1235, "loss": 0.5291, "lr": 3.591713938344416e-05, "epoch": 1.4331983805668016, "percentage": 28.66, "elapsed_time": "2:17:38", "remaining_time": "5:42:32"} +{"current_steps": 355, "total_steps": 1235, "loss": 0.5495, "lr": 3.588283301689507e-05, "epoch": 1.4372469635627532, "percentage": 28.74, "elapsed_time": "2:18:01", "remaining_time": "5:42:09"} +{"current_steps": 356, "total_steps": 1235, "loss": 0.5442, "lr": 3.5848399651636424e-05, "epoch": 1.4412955465587045, "percentage": 28.83, "elapsed_time": "2:18:25", "remaining_time": "5:41:47"} +{"current_steps": 357, "total_steps": 1235, "loss": 0.545, "lr": 3.5813839562996473e-05, "epoch": 1.4453441295546559, "percentage": 28.91, "elapsed_time": "2:18:48", "remaining_time": "5:41:23"} +{"current_steps": 358, "total_steps": 1235, "loss": 0.5459, "lr": 3.5779153027316775e-05, "epoch": 1.4493927125506074, "percentage": 28.99, "elapsed_time": "2:19:11", "remaining_time": "5:40:59"} +{"current_steps": 359, "total_steps": 1235, "loss": 0.5578, "lr": 3.574434032194994e-05, "epoch": 1.4534412955465588, "percentage": 29.07, "elapsed_time": "2:19:33", "remaining_time": "5:40:33"} +{"current_steps": 360, "total_steps": 1235, "loss": 0.5578, "lr": 3.5709401725257436e-05, "epoch": 1.45748987854251, "percentage": 29.15, "elapsed_time": "2:19:57", "remaining_time": "5:40:10"} +{"current_steps": 361, "total_steps": 1235, "loss": 0.5506, "lr": 3.5674337516607346e-05, "epoch": 1.4615384615384617, "percentage": 29.23, "elapsed_time": "2:20:21", "remaining_time": "5:39:48"} +{"current_steps": 362, "total_steps": 1235, "loss": 0.5545, "lr": 3.563914797637216e-05, "epoch": 1.465587044534413, "percentage": 29.31, "elapsed_time": "2:20:44", "remaining_time": "5:39:24"} +{"current_steps": 363, "total_steps": 1235, "loss": 0.5516, "lr": 3.560383338592649e-05, "epoch": 1.4696356275303644, "percentage": 29.39, "elapsed_time": "2:21:07", "remaining_time": "5:39:00"} +{"current_steps": 364, "total_steps": 1235, "loss": 0.5618, "lr": 3.556839402764487e-05, "epoch": 1.4736842105263157, "percentage": 29.47, "elapsed_time": "2:21:30", "remaining_time": "5:38:37"} +{"current_steps": 365, "total_steps": 1235, "loss": 0.5426, "lr": 3.553283018489946e-05, "epoch": 1.4777327935222673, "percentage": 29.55, "elapsed_time": "2:21:52", "remaining_time": "5:38:09"} +{"current_steps": 366, "total_steps": 1235, "loss": 0.5292, "lr": 3.54971421420578e-05, "epoch": 1.4817813765182186, "percentage": 29.64, "elapsed_time": "2:22:15", "remaining_time": "5:37:45"} +{"current_steps": 367, "total_steps": 1235, "loss": 0.5586, "lr": 3.5461330184480524e-05, "epoch": 1.48582995951417, "percentage": 29.72, "elapsed_time": "2:22:37", "remaining_time": "5:37:19"} +{"current_steps": 368, "total_steps": 1235, "loss": 0.5403, "lr": 3.54253945985191e-05, "epoch": 1.4898785425101215, "percentage": 29.8, "elapsed_time": "2:23:00", "remaining_time": "5:36:55"} +{"current_steps": 369, "total_steps": 1235, "loss": 0.538, "lr": 3.5389335671513524e-05, "epoch": 1.4939271255060729, "percentage": 29.88, "elapsed_time": "2:23:24", "remaining_time": "5:36:32"} +{"current_steps": 370, "total_steps": 1235, "loss": 0.5517, "lr": 3.5353153691789986e-05, "epoch": 1.4979757085020242, "percentage": 29.96, "elapsed_time": "2:23:47", "remaining_time": "5:36:08"} +{"current_steps": 371, "total_steps": 1235, "loss": 0.5541, "lr": 3.531684894865866e-05, "epoch": 1.5020242914979756, "percentage": 30.04, "elapsed_time": "2:24:10", "remaining_time": "5:35:46"} +{"current_steps": 372, "total_steps": 1235, "loss": 0.5421, "lr": 3.528042173241128e-05, "epoch": 1.5060728744939271, "percentage": 30.12, "elapsed_time": "2:24:33", "remaining_time": "5:35:22"} +{"current_steps": 373, "total_steps": 1235, "loss": 0.5417, "lr": 3.524387233431892e-05, "epoch": 1.5101214574898787, "percentage": 30.2, "elapsed_time": "2:24:55", "remaining_time": "5:34:55"} +{"current_steps": 374, "total_steps": 1235, "loss": 0.567, "lr": 3.520720104662958e-05, "epoch": 1.5141700404858298, "percentage": 30.28, "elapsed_time": "2:25:18", "remaining_time": "5:34:30"} +{"current_steps": 375, "total_steps": 1235, "loss": 0.5522, "lr": 3.5170408162565904e-05, "epoch": 1.5182186234817814, "percentage": 30.36, "elapsed_time": "2:25:41", "remaining_time": "5:34:07"} +{"current_steps": 376, "total_steps": 1235, "loss": 0.5414, "lr": 3.513349397632281e-05, "epoch": 1.522267206477733, "percentage": 30.45, "elapsed_time": "2:26:04", "remaining_time": "5:33:42"} +{"current_steps": 377, "total_steps": 1235, "loss": 0.5602, "lr": 3.5096458783065145e-05, "epoch": 1.526315789473684, "percentage": 30.53, "elapsed_time": "2:26:28", "remaining_time": "5:33:20"} +{"current_steps": 378, "total_steps": 1235, "loss": 0.5548, "lr": 3.505930287892533e-05, "epoch": 1.5303643724696356, "percentage": 30.61, "elapsed_time": "2:26:51", "remaining_time": "5:32:56"} +{"current_steps": 379, "total_steps": 1235, "loss": 0.5603, "lr": 3.502202656100099e-05, "epoch": 1.5344129554655872, "percentage": 30.69, "elapsed_time": "2:27:14", "remaining_time": "5:32:34"} +{"current_steps": 380, "total_steps": 1235, "loss": 0.5569, "lr": 3.498463012735256e-05, "epoch": 1.5384615384615383, "percentage": 30.77, "elapsed_time": "2:27:38", "remaining_time": "5:32:11"} +{"current_steps": 381, "total_steps": 1235, "loss": 0.5544, "lr": 3.494711387700094e-05, "epoch": 1.54251012145749, "percentage": 30.85, "elapsed_time": "2:28:01", "remaining_time": "5:31:46"} +{"current_steps": 382, "total_steps": 1235, "loss": 0.552, "lr": 3.490947810992505e-05, "epoch": 1.5465587044534415, "percentage": 30.93, "elapsed_time": "2:28:24", "remaining_time": "5:31:24"} +{"current_steps": 383, "total_steps": 1235, "loss": 0.5527, "lr": 3.48717231270595e-05, "epoch": 1.5506072874493926, "percentage": 31.01, "elapsed_time": "2:28:48", "remaining_time": "5:31:01"} +{"current_steps": 384, "total_steps": 1235, "loss": 0.5484, "lr": 3.483384923029211e-05, "epoch": 1.5546558704453441, "percentage": 31.09, "elapsed_time": "2:29:11", "remaining_time": "5:30:38"} +{"current_steps": 385, "total_steps": 1235, "loss": 0.558, "lr": 3.479585672246156e-05, "epoch": 1.5587044534412957, "percentage": 31.17, "elapsed_time": "2:29:35", "remaining_time": "5:30:15"} +{"current_steps": 386, "total_steps": 1235, "loss": 0.5536, "lr": 3.4757745907354924e-05, "epoch": 1.5627530364372468, "percentage": 31.26, "elapsed_time": "2:29:57", "remaining_time": "5:29:50"} +{"current_steps": 387, "total_steps": 1235, "loss": 0.5368, "lr": 3.471951708970527e-05, "epoch": 1.5668016194331984, "percentage": 31.34, "elapsed_time": "2:30:19", "remaining_time": "5:29:23"} +{"current_steps": 388, "total_steps": 1235, "loss": 0.5569, "lr": 3.468117057518921e-05, "epoch": 1.5708502024291497, "percentage": 31.42, "elapsed_time": "2:30:42", "remaining_time": "5:28:59"} +{"current_steps": 389, "total_steps": 1235, "loss": 0.5497, "lr": 3.4642706670424426e-05, "epoch": 1.574898785425101, "percentage": 31.5, "elapsed_time": "2:31:04", "remaining_time": "5:28:33"} +{"current_steps": 390, "total_steps": 1235, "loss": 0.5443, "lr": 3.460412568296731e-05, "epoch": 1.5789473684210527, "percentage": 31.58, "elapsed_time": "2:31:27", "remaining_time": "5:28:08"} +{"current_steps": 391, "total_steps": 1235, "loss": 0.5487, "lr": 3.456542792131039e-05, "epoch": 1.582995951417004, "percentage": 31.66, "elapsed_time": "2:31:50", "remaining_time": "5:27:45"} +{"current_steps": 392, "total_steps": 1235, "loss": 0.5608, "lr": 3.4526613694879936e-05, "epoch": 1.5870445344129553, "percentage": 31.74, "elapsed_time": "2:32:13", "remaining_time": "5:27:21"} +{"current_steps": 393, "total_steps": 1235, "loss": 0.5494, "lr": 3.448768331403348e-05, "epoch": 1.591093117408907, "percentage": 31.82, "elapsed_time": "2:32:37", "remaining_time": "5:26:59"} +{"current_steps": 394, "total_steps": 1235, "loss": 0.5649, "lr": 3.44486370900573e-05, "epoch": 1.5951417004048583, "percentage": 31.9, "elapsed_time": "2:32:59", "remaining_time": "5:26:34"} +{"current_steps": 395, "total_steps": 1235, "loss": 0.5433, "lr": 3.440947533516396e-05, "epoch": 1.5991902834008096, "percentage": 31.98, "elapsed_time": "2:33:23", "remaining_time": "5:26:11"} +{"current_steps": 396, "total_steps": 1235, "loss": 0.5626, "lr": 3.4370198362489816e-05, "epoch": 1.6032388663967612, "percentage": 32.06, "elapsed_time": "2:33:45", "remaining_time": "5:25:46"} +{"current_steps": 397, "total_steps": 1235, "loss": 0.5435, "lr": 3.43308064860925e-05, "epoch": 1.6072874493927125, "percentage": 32.15, "elapsed_time": "2:34:09", "remaining_time": "5:25:24"} +{"current_steps": 398, "total_steps": 1235, "loss": 0.564, "lr": 3.4291300020948393e-05, "epoch": 1.6113360323886639, "percentage": 32.23, "elapsed_time": "2:34:32", "remaining_time": "5:24:59"} +{"current_steps": 399, "total_steps": 1235, "loss": 0.5558, "lr": 3.425167928295015e-05, "epoch": 1.6153846153846154, "percentage": 32.31, "elapsed_time": "2:34:54", "remaining_time": "5:24:34"} +{"current_steps": 400, "total_steps": 1235, "loss": 0.539, "lr": 3.421194458890411e-05, "epoch": 1.6194331983805668, "percentage": 32.39, "elapsed_time": "2:35:16", "remaining_time": "5:24:09"} +{"current_steps": 401, "total_steps": 1235, "loss": 0.5512, "lr": 3.4172096256527865e-05, "epoch": 1.623481781376518, "percentage": 32.47, "elapsed_time": "2:35:40", "remaining_time": "5:23:46"} +{"current_steps": 402, "total_steps": 1235, "loss": 0.5498, "lr": 3.4132134604447595e-05, "epoch": 1.6275303643724697, "percentage": 32.55, "elapsed_time": "2:36:03", "remaining_time": "5:23:22"} +{"current_steps": 403, "total_steps": 1235, "loss": 0.5461, "lr": 3.409205995219561e-05, "epoch": 1.631578947368421, "percentage": 32.63, "elapsed_time": "2:36:27", "remaining_time": "5:23:00"} +{"current_steps": 404, "total_steps": 1235, "loss": 0.5257, "lr": 3.4051872620207765e-05, "epoch": 1.6356275303643724, "percentage": 32.71, "elapsed_time": "2:36:49", "remaining_time": "5:22:34"} +{"current_steps": 405, "total_steps": 1235, "loss": 0.575, "lr": 3.40115729298209e-05, "epoch": 1.639676113360324, "percentage": 32.79, "elapsed_time": "2:37:13", "remaining_time": "5:22:13"} +{"current_steps": 406, "total_steps": 1235, "loss": 0.5518, "lr": 3.397116120327025e-05, "epoch": 1.6437246963562753, "percentage": 32.87, "elapsed_time": "2:37:37", "remaining_time": "5:21:50"} +{"current_steps": 407, "total_steps": 1235, "loss": 0.5393, "lr": 3.3930637763686916e-05, "epoch": 1.6477732793522266, "percentage": 32.96, "elapsed_time": "2:38:00", "remaining_time": "5:21:27"} +{"current_steps": 408, "total_steps": 1235, "loss": 0.5477, "lr": 3.389000293509524e-05, "epoch": 1.6518218623481782, "percentage": 33.04, "elapsed_time": "2:38:23", "remaining_time": "5:21:02"} +{"current_steps": 409, "total_steps": 1235, "loss": 0.5478, "lr": 3.3849257042410225e-05, "epoch": 1.6558704453441295, "percentage": 33.12, "elapsed_time": "2:38:46", "remaining_time": "5:20:39"} +{"current_steps": 410, "total_steps": 1235, "loss": 0.5555, "lr": 3.380840041143494e-05, "epoch": 1.6599190283400809, "percentage": 33.2, "elapsed_time": "2:39:08", "remaining_time": "5:20:13"} +{"current_steps": 411, "total_steps": 1235, "loss": 0.5512, "lr": 3.376743336885792e-05, "epoch": 1.6639676113360324, "percentage": 33.28, "elapsed_time": "2:39:32", "remaining_time": "5:19:51"} +{"current_steps": 412, "total_steps": 1235, "loss": 0.5569, "lr": 3.372635624225055e-05, "epoch": 1.6680161943319838, "percentage": 33.36, "elapsed_time": "2:39:54", "remaining_time": "5:19:26"} +{"current_steps": 413, "total_steps": 1235, "loss": 0.5653, "lr": 3.3685169360064445e-05, "epoch": 1.6720647773279351, "percentage": 33.44, "elapsed_time": "2:40:17", "remaining_time": "5:19:02"} +{"current_steps": 414, "total_steps": 1235, "loss": 0.5608, "lr": 3.3643873051628804e-05, "epoch": 1.6761133603238867, "percentage": 33.52, "elapsed_time": "2:40:41", "remaining_time": "5:18:39"} +{"current_steps": 415, "total_steps": 1235, "loss": 0.5735, "lr": 3.3602467647147814e-05, "epoch": 1.680161943319838, "percentage": 33.6, "elapsed_time": "2:41:04", "remaining_time": "5:18:16"} +{"current_steps": 416, "total_steps": 1235, "loss": 0.5481, "lr": 3.356095347769799e-05, "epoch": 1.6842105263157894, "percentage": 33.68, "elapsed_time": "2:41:26", "remaining_time": "5:17:50"} +{"current_steps": 417, "total_steps": 1235, "loss": 0.5545, "lr": 3.351933087522552e-05, "epoch": 1.688259109311741, "percentage": 33.77, "elapsed_time": "2:41:50", "remaining_time": "5:17:27"} +{"current_steps": 418, "total_steps": 1235, "loss": 0.5493, "lr": 3.3477600172543626e-05, "epoch": 1.6923076923076923, "percentage": 33.85, "elapsed_time": "2:42:13", "remaining_time": "5:17:03"} +{"current_steps": 419, "total_steps": 1235, "loss": 0.5587, "lr": 3.3435761703329894e-05, "epoch": 1.6963562753036436, "percentage": 33.93, "elapsed_time": "2:42:36", "remaining_time": "5:16:39"} +{"current_steps": 420, "total_steps": 1235, "loss": 0.5395, "lr": 3.3393815802123606e-05, "epoch": 1.7004048582995952, "percentage": 34.01, "elapsed_time": "2:42:59", "remaining_time": "5:16:16"} +{"current_steps": 421, "total_steps": 1235, "loss": 0.5428, "lr": 3.335176280432308e-05, "epoch": 1.7044534412955465, "percentage": 34.09, "elapsed_time": "2:43:21", "remaining_time": "5:15:50"} +{"current_steps": 422, "total_steps": 1235, "loss": 0.5381, "lr": 3.330960304618295e-05, "epoch": 1.708502024291498, "percentage": 34.17, "elapsed_time": "2:43:44", "remaining_time": "5:15:27"} +{"current_steps": 423, "total_steps": 1235, "loss": 0.5408, "lr": 3.326733686481153e-05, "epoch": 1.7125506072874495, "percentage": 34.25, "elapsed_time": "2:44:05", "remaining_time": "5:15:00"} +{"current_steps": 424, "total_steps": 1235, "loss": 0.5589, "lr": 3.3224964598168084e-05, "epoch": 1.7165991902834008, "percentage": 34.33, "elapsed_time": "2:44:29", "remaining_time": "5:14:36"} +{"current_steps": 425, "total_steps": 1235, "loss": 0.5524, "lr": 3.318248658506012e-05, "epoch": 1.7206477732793521, "percentage": 34.41, "elapsed_time": "2:44:52", "remaining_time": "5:14:13"} +{"current_steps": 426, "total_steps": 1235, "loss": 0.5608, "lr": 3.313990316514069e-05, "epoch": 1.7246963562753037, "percentage": 34.49, "elapsed_time": "2:45:15", "remaining_time": "5:13:49"} +{"current_steps": 427, "total_steps": 1235, "loss": 0.5456, "lr": 3.309721467890571e-05, "epoch": 1.728744939271255, "percentage": 34.57, "elapsed_time": "2:45:37", "remaining_time": "5:13:23"} +{"current_steps": 428, "total_steps": 1235, "loss": 0.554, "lr": 3.305442146769115e-05, "epoch": 1.7327935222672064, "percentage": 34.66, "elapsed_time": "2:45:58", "remaining_time": "5:12:57"} +{"current_steps": 429, "total_steps": 1235, "loss": 0.5607, "lr": 3.30115238736704e-05, "epoch": 1.736842105263158, "percentage": 34.74, "elapsed_time": "2:46:21", "remaining_time": "5:12:33"} +{"current_steps": 430, "total_steps": 1235, "loss": 0.5324, "lr": 3.296852223985148e-05, "epoch": 1.7408906882591093, "percentage": 34.82, "elapsed_time": "2:46:45", "remaining_time": "5:12:10"} +{"current_steps": 431, "total_steps": 1235, "loss": 0.5477, "lr": 3.2925416910074315e-05, "epoch": 1.7449392712550607, "percentage": 34.9, "elapsed_time": "2:47:06", "remaining_time": "5:11:42"} +{"current_steps": 432, "total_steps": 1235, "loss": 0.5404, "lr": 3.288220822900796e-05, "epoch": 1.7489878542510122, "percentage": 34.98, "elapsed_time": "2:47:28", "remaining_time": "5:11:17"} +{"current_steps": 433, "total_steps": 1235, "loss": 0.5311, "lr": 3.283889654214788e-05, "epoch": 1.7530364372469636, "percentage": 35.06, "elapsed_time": "2:47:51", "remaining_time": "5:10:54"} +{"current_steps": 434, "total_steps": 1235, "loss": 0.5457, "lr": 3.279548219581317e-05, "epoch": 1.757085020242915, "percentage": 35.14, "elapsed_time": "2:48:14", "remaining_time": "5:10:30"} +{"current_steps": 435, "total_steps": 1235, "loss": 0.5512, "lr": 3.275196553714379e-05, "epoch": 1.7611336032388665, "percentage": 35.22, "elapsed_time": "2:48:36", "remaining_time": "5:10:05"} +{"current_steps": 436, "total_steps": 1235, "loss": 0.5433, "lr": 3.270834691409778e-05, "epoch": 1.7651821862348178, "percentage": 35.3, "elapsed_time": "2:49:00", "remaining_time": "5:09:43"} +{"current_steps": 437, "total_steps": 1235, "loss": 0.5473, "lr": 3.266462667544849e-05, "epoch": 1.7692307692307692, "percentage": 35.38, "elapsed_time": "2:49:23", "remaining_time": "5:09:19"} +{"current_steps": 438, "total_steps": 1235, "loss": 0.5556, "lr": 3.262080517078178e-05, "epoch": 1.7732793522267207, "percentage": 35.47, "elapsed_time": "2:49:46", "remaining_time": "5:08:56"} +{"current_steps": 439, "total_steps": 1235, "loss": 0.5466, "lr": 3.257688275049323e-05, "epoch": 1.777327935222672, "percentage": 35.55, "elapsed_time": "2:50:09", "remaining_time": "5:08:31"} +{"current_steps": 440, "total_steps": 1235, "loss": 0.5443, "lr": 3.253285976578535e-05, "epoch": 1.7813765182186234, "percentage": 35.63, "elapsed_time": "2:50:32", "remaining_time": "5:08:08"} +{"current_steps": 441, "total_steps": 1235, "loss": 0.5436, "lr": 3.2488736568664756e-05, "epoch": 1.785425101214575, "percentage": 35.71, "elapsed_time": "2:50:55", "remaining_time": "5:07:44"} +{"current_steps": 442, "total_steps": 1235, "loss": 0.5475, "lr": 3.244451351193935e-05, "epoch": 1.7894736842105263, "percentage": 35.79, "elapsed_time": "2:51:18", "remaining_time": "5:07:20"} +{"current_steps": 443, "total_steps": 1235, "loss": 0.5509, "lr": 3.240019094921551e-05, "epoch": 1.7935222672064777, "percentage": 35.87, "elapsed_time": "2:51:41", "remaining_time": "5:06:56"} +{"current_steps": 444, "total_steps": 1235, "loss": 0.5535, "lr": 3.235576923489527e-05, "epoch": 1.7975708502024292, "percentage": 35.95, "elapsed_time": "2:52:04", "remaining_time": "5:06:33"} +{"current_steps": 445, "total_steps": 1235, "loss": 0.5468, "lr": 3.2311248724173476e-05, "epoch": 1.8016194331983806, "percentage": 36.03, "elapsed_time": "2:52:28", "remaining_time": "5:06:10"} +{"current_steps": 446, "total_steps": 1235, "loss": 0.5594, "lr": 3.226662977303494e-05, "epoch": 1.805668016194332, "percentage": 36.11, "elapsed_time": "2:52:50", "remaining_time": "5:05:46"} +{"current_steps": 447, "total_steps": 1235, "loss": 0.5506, "lr": 3.2221912738251626e-05, "epoch": 1.8097165991902835, "percentage": 36.19, "elapsed_time": "2:53:13", "remaining_time": "5:05:23"} +{"current_steps": 448, "total_steps": 1235, "loss": 0.5301, "lr": 3.2177097977379736e-05, "epoch": 1.8137651821862348, "percentage": 36.28, "elapsed_time": "2:53:36", "remaining_time": "5:04:58"} +{"current_steps": 449, "total_steps": 1235, "loss": 0.5551, "lr": 3.21321858487569e-05, "epoch": 1.8178137651821862, "percentage": 36.36, "elapsed_time": "2:53:59", "remaining_time": "5:04:35"} +{"current_steps": 450, "total_steps": 1235, "loss": 0.5506, "lr": 3.208717671149931e-05, "epoch": 1.8218623481781377, "percentage": 36.44, "elapsed_time": "2:54:22", "remaining_time": "5:04:10"} +{"current_steps": 451, "total_steps": 1235, "loss": 0.5404, "lr": 3.204207092549882e-05, "epoch": 1.825910931174089, "percentage": 36.52, "elapsed_time": "2:54:43", "remaining_time": "5:03:43"} +{"current_steps": 452, "total_steps": 1235, "loss": 0.5473, "lr": 3.19968688514201e-05, "epoch": 1.8299595141700404, "percentage": 36.6, "elapsed_time": "2:55:05", "remaining_time": "5:03:19"} +{"current_steps": 453, "total_steps": 1235, "loss": 0.5478, "lr": 3.195157085069774e-05, "epoch": 1.834008097165992, "percentage": 36.68, "elapsed_time": "2:55:28", "remaining_time": "5:02:55"} +{"current_steps": 454, "total_steps": 1235, "loss": 0.5648, "lr": 3.190617728553332e-05, "epoch": 1.8380566801619433, "percentage": 36.76, "elapsed_time": "2:55:51", "remaining_time": "5:02:31"} +{"current_steps": 455, "total_steps": 1235, "loss": 0.5631, "lr": 3.1860688518892606e-05, "epoch": 1.8421052631578947, "percentage": 36.84, "elapsed_time": "2:56:14", "remaining_time": "5:02:07"} +{"current_steps": 456, "total_steps": 1235, "loss": 0.554, "lr": 3.181510491450254e-05, "epoch": 1.8461538461538463, "percentage": 36.92, "elapsed_time": "2:56:37", "remaining_time": "5:01:44"} +{"current_steps": 457, "total_steps": 1235, "loss": 0.5436, "lr": 3.176942683684842e-05, "epoch": 1.8502024291497976, "percentage": 37.0, "elapsed_time": "2:57:01", "remaining_time": "5:01:22"} +{"current_steps": 458, "total_steps": 1235, "loss": 0.5485, "lr": 3.1723654651170934e-05, "epoch": 1.854251012145749, "percentage": 37.09, "elapsed_time": "2:57:25", "remaining_time": "5:00:59"} +{"current_steps": 459, "total_steps": 1235, "loss": 0.5261, "lr": 3.167778872346327e-05, "epoch": 1.8582995951417005, "percentage": 37.17, "elapsed_time": "2:57:48", "remaining_time": "5:00:36"} +{"current_steps": 460, "total_steps": 1235, "loss": 0.5611, "lr": 3.163182942046815e-05, "epoch": 1.8623481781376519, "percentage": 37.25, "elapsed_time": "2:58:12", "remaining_time": "5:00:14"} +{"current_steps": 461, "total_steps": 1235, "loss": 0.5492, "lr": 3.158577710967494e-05, "epoch": 1.8663967611336032, "percentage": 37.33, "elapsed_time": "2:58:36", "remaining_time": "4:59:52"} +{"current_steps": 462, "total_steps": 1235, "loss": 0.542, "lr": 3.153963215931669e-05, "epoch": 1.8704453441295548, "percentage": 37.41, "elapsed_time": "2:58:59", "remaining_time": "4:59:28"} +{"current_steps": 463, "total_steps": 1235, "loss": 0.5456, "lr": 3.14933949383672e-05, "epoch": 1.874493927125506, "percentage": 37.49, "elapsed_time": "2:59:22", "remaining_time": "4:59:04"} +{"current_steps": 464, "total_steps": 1235, "loss": 0.5541, "lr": 3.144706581653805e-05, "epoch": 1.8785425101214575, "percentage": 37.57, "elapsed_time": "2:59:45", "remaining_time": "4:58:41"} +{"current_steps": 465, "total_steps": 1235, "loss": 0.5531, "lr": 3.140064516427566e-05, "epoch": 1.882591093117409, "percentage": 37.65, "elapsed_time": "3:00:08", "remaining_time": "4:58:18"} +{"current_steps": 466, "total_steps": 1235, "loss": 0.5567, "lr": 3.135413335275833e-05, "epoch": 1.8866396761133604, "percentage": 37.73, "elapsed_time": "3:00:32", "remaining_time": "4:57:55"} +{"current_steps": 467, "total_steps": 1235, "loss": 0.531, "lr": 3.130753075389327e-05, "epoch": 1.8906882591093117, "percentage": 37.81, "elapsed_time": "3:00:54", "remaining_time": "4:57:31"} +{"current_steps": 468, "total_steps": 1235, "loss": 0.5476, "lr": 3.1260837740313625e-05, "epoch": 1.8947368421052633, "percentage": 37.89, "elapsed_time": "3:01:16", "remaining_time": "4:57:05"} +{"current_steps": 469, "total_steps": 1235, "loss": 0.553, "lr": 3.121405468537547e-05, "epoch": 1.8987854251012146, "percentage": 37.98, "elapsed_time": "3:01:40", "remaining_time": "4:56:43"} +{"current_steps": 470, "total_steps": 1235, "loss": 0.5376, "lr": 3.116718196315488e-05, "epoch": 1.902834008097166, "percentage": 38.06, "elapsed_time": "3:02:03", "remaining_time": "4:56:19"} +{"current_steps": 471, "total_steps": 1235, "loss": 0.5449, "lr": 3.1120219948444894e-05, "epoch": 1.9068825910931175, "percentage": 38.14, "elapsed_time": "3:02:25", "remaining_time": "4:55:54"} +{"current_steps": 472, "total_steps": 1235, "loss": 0.5446, "lr": 3.107316901675252e-05, "epoch": 1.9109311740890689, "percentage": 38.22, "elapsed_time": "3:02:48", "remaining_time": "4:55:31"} +{"current_steps": 473, "total_steps": 1235, "loss": 0.538, "lr": 3.1026029544295745e-05, "epoch": 1.9149797570850202, "percentage": 38.3, "elapsed_time": "3:03:11", "remaining_time": "4:55:07"} +{"current_steps": 474, "total_steps": 1235, "loss": 0.5458, "lr": 3.097880190800057e-05, "epoch": 1.9190283400809718, "percentage": 38.38, "elapsed_time": "3:03:32", "remaining_time": "4:54:40"} +{"current_steps": 475, "total_steps": 1235, "loss": 0.5444, "lr": 3.093148648549788e-05, "epoch": 1.9230769230769231, "percentage": 38.46, "elapsed_time": "3:03:54", "remaining_time": "4:54:15"} +{"current_steps": 476, "total_steps": 1235, "loss": 0.5352, "lr": 3.088408365512055e-05, "epoch": 1.9271255060728745, "percentage": 38.54, "elapsed_time": "3:04:16", "remaining_time": "4:53:50"} +{"current_steps": 477, "total_steps": 1235, "loss": 0.5555, "lr": 3.083659379590034e-05, "epoch": 1.931174089068826, "percentage": 38.62, "elapsed_time": "3:04:40", "remaining_time": "4:53:27"} +{"current_steps": 478, "total_steps": 1235, "loss": 0.5389, "lr": 3.0789017287564913e-05, "epoch": 1.9352226720647774, "percentage": 38.7, "elapsed_time": "3:05:03", "remaining_time": "4:53:04"} +{"current_steps": 479, "total_steps": 1235, "loss": 0.5506, "lr": 3.074135451053475e-05, "epoch": 1.9392712550607287, "percentage": 38.79, "elapsed_time": "3:05:25", "remaining_time": "4:52:40"} +{"current_steps": 480, "total_steps": 1235, "loss": 0.5471, "lr": 3.069360584592015e-05, "epoch": 1.9433198380566803, "percentage": 38.87, "elapsed_time": "3:05:48", "remaining_time": "4:52:15"} +{"current_steps": 481, "total_steps": 1235, "loss": 0.5418, "lr": 3.064577167551816e-05, "epoch": 1.9473684210526314, "percentage": 38.95, "elapsed_time": "3:06:11", "remaining_time": "4:51:52"} +{"current_steps": 482, "total_steps": 1235, "loss": 0.5464, "lr": 3.059785238180953e-05, "epoch": 1.951417004048583, "percentage": 39.03, "elapsed_time": "3:06:35", "remaining_time": "4:51:29"} +{"current_steps": 483, "total_steps": 1235, "loss": 0.5498, "lr": 3.054984834795566e-05, "epoch": 1.9554655870445345, "percentage": 39.11, "elapsed_time": "3:06:58", "remaining_time": "4:51:06"} +{"current_steps": 484, "total_steps": 1235, "loss": 0.5363, "lr": 3.0501759957795537e-05, "epoch": 1.9595141700404857, "percentage": 39.19, "elapsed_time": "3:07:20", "remaining_time": "4:50:41"} +{"current_steps": 485, "total_steps": 1235, "loss": 0.5439, "lr": 3.0453587595842627e-05, "epoch": 1.9635627530364372, "percentage": 39.27, "elapsed_time": "3:07:41", "remaining_time": "4:50:14"} +{"current_steps": 486, "total_steps": 1235, "loss": 0.5575, "lr": 3.0405331647281856e-05, "epoch": 1.9676113360323888, "percentage": 39.35, "elapsed_time": "3:08:03", "remaining_time": "4:49:49"} +{"current_steps": 487, "total_steps": 1235, "loss": 0.5299, "lr": 3.0356992497966508e-05, "epoch": 1.97165991902834, "percentage": 39.43, "elapsed_time": "3:08:25", "remaining_time": "4:49:25"} +{"current_steps": 488, "total_steps": 1235, "loss": 0.5448, "lr": 3.0308570534415137e-05, "epoch": 1.9757085020242915, "percentage": 39.51, "elapsed_time": "3:08:49", "remaining_time": "4:49:02"} +{"current_steps": 489, "total_steps": 1235, "loss": 0.5359, "lr": 3.0260066143808467e-05, "epoch": 1.979757085020243, "percentage": 39.6, "elapsed_time": "3:09:11", "remaining_time": "4:48:38"} +{"current_steps": 490, "total_steps": 1235, "loss": 0.5584, "lr": 3.021147971398632e-05, "epoch": 1.9838056680161942, "percentage": 39.68, "elapsed_time": "3:09:35", "remaining_time": "4:48:15"} +{"current_steps": 491, "total_steps": 1235, "loss": 0.5409, "lr": 3.0162811633444478e-05, "epoch": 1.9878542510121457, "percentage": 39.76, "elapsed_time": "3:09:59", "remaining_time": "4:47:53"} +{"current_steps": 492, "total_steps": 1235, "loss": 0.5546, "lr": 3.0114062291331635e-05, "epoch": 1.9919028340080973, "percentage": 39.84, "elapsed_time": "3:10:21", "remaining_time": "4:47:28"} +{"current_steps": 493, "total_steps": 1235, "loss": 0.5449, "lr": 3.0065232077446217e-05, "epoch": 1.9959514170040484, "percentage": 39.92, "elapsed_time": "3:10:44", "remaining_time": "4:47:04"} +{"current_steps": 494, "total_steps": 1235, "loss": 0.5235, "lr": 3.001632138223332e-05, "epoch": 2.0, "percentage": 40.0, "elapsed_time": "3:11:07", "remaining_time": "4:46:41"} +{"current_steps": 495, "total_steps": 1235, "loss": 0.4834, "lr": 2.9967330596781565e-05, "epoch": 2.0040485829959516, "percentage": 40.08, "elapsed_time": "3:13:14", "remaining_time": "4:48:52"} +{"current_steps": 496, "total_steps": 1235, "loss": 0.4836, "lr": 2.9918260112819952e-05, "epoch": 2.0080971659919027, "percentage": 40.16, "elapsed_time": "3:13:36", "remaining_time": "4:48:27"} +{"current_steps": 497, "total_steps": 1235, "loss": 0.4674, "lr": 2.9869110322714778e-05, "epoch": 2.0121457489878543, "percentage": 40.24, "elapsed_time": "3:14:00", "remaining_time": "4:48:04"} +{"current_steps": 498, "total_steps": 1235, "loss": 0.4882, "lr": 2.9819881619466447e-05, "epoch": 2.016194331983806, "percentage": 40.32, "elapsed_time": "3:14:23", "remaining_time": "4:47:41"} +{"current_steps": 499, "total_steps": 1235, "loss": 0.4661, "lr": 2.9770574396706364e-05, "epoch": 2.020242914979757, "percentage": 40.4, "elapsed_time": "3:14:47", "remaining_time": "4:47:18"} +{"current_steps": 500, "total_steps": 1235, "loss": 0.4593, "lr": 2.972118904869376e-05, "epoch": 2.0242914979757085, "percentage": 40.49, "elapsed_time": "3:15:10", "remaining_time": "4:46:53"} +{"current_steps": 501, "total_steps": 1235, "loss": 0.4656, "lr": 2.9671725970312563e-05, "epoch": 2.02834008097166, "percentage": 40.57, "elapsed_time": "3:15:32", "remaining_time": "4:46:28"} +{"current_steps": 502, "total_steps": 1235, "loss": 0.471, "lr": 2.9622185557068238e-05, "epoch": 2.032388663967611, "percentage": 40.65, "elapsed_time": "3:15:55", "remaining_time": "4:46:05"} +{"current_steps": 503, "total_steps": 1235, "loss": 0.4839, "lr": 2.95725682050846e-05, "epoch": 2.0364372469635628, "percentage": 40.73, "elapsed_time": "3:16:19", "remaining_time": "4:45:41"} +{"current_steps": 504, "total_steps": 1235, "loss": 0.4726, "lr": 2.9522874311100684e-05, "epoch": 2.0404858299595143, "percentage": 40.81, "elapsed_time": "3:16:42", "remaining_time": "4:45:18"} +{"current_steps": 505, "total_steps": 1235, "loss": 0.4942, "lr": 2.9473104272467526e-05, "epoch": 2.0445344129554655, "percentage": 40.89, "elapsed_time": "3:17:05", "remaining_time": "4:44:53"} +{"current_steps": 506, "total_steps": 1235, "loss": 0.4567, "lr": 2.942325848714505e-05, "epoch": 2.048582995951417, "percentage": 40.97, "elapsed_time": "3:17:27", "remaining_time": "4:44:28"} +{"current_steps": 507, "total_steps": 1235, "loss": 0.4957, "lr": 2.9373337353698804e-05, "epoch": 2.0526315789473686, "percentage": 41.05, "elapsed_time": "3:17:50", "remaining_time": "4:44:04"} +{"current_steps": 508, "total_steps": 1235, "loss": 0.4727, "lr": 2.932334127129686e-05, "epoch": 2.0566801619433197, "percentage": 41.13, "elapsed_time": "3:18:13", "remaining_time": "4:43:41"} +{"current_steps": 509, "total_steps": 1235, "loss": 0.456, "lr": 2.9273270639706547e-05, "epoch": 2.0607287449392713, "percentage": 41.21, "elapsed_time": "3:18:35", "remaining_time": "4:43:15"} +{"current_steps": 510, "total_steps": 1235, "loss": 0.4702, "lr": 2.922312585929131e-05, "epoch": 2.064777327935223, "percentage": 41.3, "elapsed_time": "3:18:58", "remaining_time": "4:42:50"} +{"current_steps": 511, "total_steps": 1235, "loss": 0.4899, "lr": 2.9172907331007478e-05, "epoch": 2.068825910931174, "percentage": 41.38, "elapsed_time": "3:19:21", "remaining_time": "4:42:27"} +{"current_steps": 512, "total_steps": 1235, "loss": 0.4654, "lr": 2.9122615456401053e-05, "epoch": 2.0728744939271255, "percentage": 41.46, "elapsed_time": "3:19:44", "remaining_time": "4:42:03"} +{"current_steps": 513, "total_steps": 1235, "loss": 0.4571, "lr": 2.9072250637604535e-05, "epoch": 2.076923076923077, "percentage": 41.54, "elapsed_time": "3:20:07", "remaining_time": "4:41:39"} +{"current_steps": 514, "total_steps": 1235, "loss": 0.4686, "lr": 2.9021813277333667e-05, "epoch": 2.080971659919028, "percentage": 41.62, "elapsed_time": "3:20:32", "remaining_time": "4:41:17"} +{"current_steps": 515, "total_steps": 1235, "loss": 0.466, "lr": 2.8971303778884244e-05, "epoch": 2.08502024291498, "percentage": 41.7, "elapsed_time": "3:20:54", "remaining_time": "4:40:52"} +{"current_steps": 516, "total_steps": 1235, "loss": 0.4848, "lr": 2.8920722546128863e-05, "epoch": 2.0890688259109313, "percentage": 41.78, "elapsed_time": "3:21:18", "remaining_time": "4:40:29"} +{"current_steps": 517, "total_steps": 1235, "loss": 0.4658, "lr": 2.887006998351372e-05, "epoch": 2.0931174089068825, "percentage": 41.86, "elapsed_time": "3:21:41", "remaining_time": "4:40:05"} +{"current_steps": 518, "total_steps": 1235, "loss": 0.4925, "lr": 2.881934649605535e-05, "epoch": 2.097165991902834, "percentage": 41.94, "elapsed_time": "3:22:04", "remaining_time": "4:39:42"} +{"current_steps": 519, "total_steps": 1235, "loss": 0.4711, "lr": 2.8768552489337408e-05, "epoch": 2.1012145748987856, "percentage": 42.02, "elapsed_time": "3:22:26", "remaining_time": "4:39:17"} +{"current_steps": 520, "total_steps": 1235, "loss": 0.4843, "lr": 2.8717688369507425e-05, "epoch": 2.1052631578947367, "percentage": 42.11, "elapsed_time": "3:22:50", "remaining_time": "4:38:53"} +{"current_steps": 521, "total_steps": 1235, "loss": 0.4474, "lr": 2.8666754543273535e-05, "epoch": 2.1093117408906883, "percentage": 42.19, "elapsed_time": "3:23:12", "remaining_time": "4:38:29"} +{"current_steps": 522, "total_steps": 1235, "loss": 0.4555, "lr": 2.8615751417901273e-05, "epoch": 2.11336032388664, "percentage": 42.27, "elapsed_time": "3:23:36", "remaining_time": "4:38:06"} +{"current_steps": 523, "total_steps": 1235, "loss": 0.4807, "lr": 2.856467940121025e-05, "epoch": 2.117408906882591, "percentage": 42.35, "elapsed_time": "3:23:59", "remaining_time": "4:37:42"} +{"current_steps": 524, "total_steps": 1235, "loss": 0.464, "lr": 2.8513538901570964e-05, "epoch": 2.1214574898785425, "percentage": 42.43, "elapsed_time": "3:24:23", "remaining_time": "4:37:19"} +{"current_steps": 525, "total_steps": 1235, "loss": 0.4636, "lr": 2.846233032790149e-05, "epoch": 2.125506072874494, "percentage": 42.51, "elapsed_time": "3:24:47", "remaining_time": "4:36:56"} +{"current_steps": 526, "total_steps": 1235, "loss": 0.4676, "lr": 2.84110540896642e-05, "epoch": 2.1295546558704452, "percentage": 42.59, "elapsed_time": "3:25:09", "remaining_time": "4:36:31"} +{"current_steps": 527, "total_steps": 1235, "loss": 0.4615, "lr": 2.8359710596862555e-05, "epoch": 2.133603238866397, "percentage": 42.67, "elapsed_time": "3:25:31", "remaining_time": "4:36:07"} +{"current_steps": 528, "total_steps": 1235, "loss": 0.4578, "lr": 2.8308300260037734e-05, "epoch": 2.1376518218623484, "percentage": 42.75, "elapsed_time": "3:25:53", "remaining_time": "4:35:42"} +{"current_steps": 529, "total_steps": 1235, "loss": 0.4675, "lr": 2.8256823490265424e-05, "epoch": 2.1417004048582995, "percentage": 42.83, "elapsed_time": "3:26:16", "remaining_time": "4:35:17"} +{"current_steps": 530, "total_steps": 1235, "loss": 0.4745, "lr": 2.8205280699152515e-05, "epoch": 2.145748987854251, "percentage": 42.91, "elapsed_time": "3:26:40", "remaining_time": "4:34:54"} +{"current_steps": 531, "total_steps": 1235, "loss": 0.4628, "lr": 2.8153672298833777e-05, "epoch": 2.1497975708502026, "percentage": 43.0, "elapsed_time": "3:27:03", "remaining_time": "4:34:30"} +{"current_steps": 532, "total_steps": 1235, "loss": 0.485, "lr": 2.8101998701968615e-05, "epoch": 2.1538461538461537, "percentage": 43.08, "elapsed_time": "3:27:26", "remaining_time": "4:34:07"} +{"current_steps": 533, "total_steps": 1235, "loss": 0.4815, "lr": 2.805026032173773e-05, "epoch": 2.1578947368421053, "percentage": 43.16, "elapsed_time": "3:27:50", "remaining_time": "4:33:43"} +{"current_steps": 534, "total_steps": 1235, "loss": 0.4746, "lr": 2.7998457571839832e-05, "epoch": 2.161943319838057, "percentage": 43.24, "elapsed_time": "3:28:13", "remaining_time": "4:33:20"} +{"current_steps": 535, "total_steps": 1235, "loss": 0.4696, "lr": 2.7946590866488322e-05, "epoch": 2.165991902834008, "percentage": 43.32, "elapsed_time": "3:28:36", "remaining_time": "4:32:56"} +{"current_steps": 536, "total_steps": 1235, "loss": 0.459, "lr": 2.7894660620408e-05, "epoch": 2.1700404858299596, "percentage": 43.4, "elapsed_time": "3:28:58", "remaining_time": "4:32:32"} +{"current_steps": 537, "total_steps": 1235, "loss": 0.4947, "lr": 2.784266724883173e-05, "epoch": 2.174089068825911, "percentage": 43.48, "elapsed_time": "3:29:22", "remaining_time": "4:32:08"} +{"current_steps": 538, "total_steps": 1235, "loss": 0.4789, "lr": 2.7790611167497128e-05, "epoch": 2.1781376518218623, "percentage": 43.56, "elapsed_time": "3:29:46", "remaining_time": "4:31:45"} +{"current_steps": 539, "total_steps": 1235, "loss": 0.4792, "lr": 2.7738492792643224e-05, "epoch": 2.182186234817814, "percentage": 43.64, "elapsed_time": "3:30:07", "remaining_time": "4:31:20"} +{"current_steps": 540, "total_steps": 1235, "loss": 0.4493, "lr": 2.768631254100716e-05, "epoch": 2.1862348178137654, "percentage": 43.72, "elapsed_time": "3:30:31", "remaining_time": "4:30:56"} +{"current_steps": 541, "total_steps": 1235, "loss": 0.4643, "lr": 2.7634070829820836e-05, "epoch": 2.1902834008097165, "percentage": 43.81, "elapsed_time": "3:30:54", "remaining_time": "4:30:33"} +{"current_steps": 542, "total_steps": 1235, "loss": 0.4636, "lr": 2.7581768076807592e-05, "epoch": 2.194331983805668, "percentage": 43.89, "elapsed_time": "3:31:17", "remaining_time": "4:30:09"} +{"current_steps": 543, "total_steps": 1235, "loss": 0.4663, "lr": 2.7529404700178832e-05, "epoch": 2.1983805668016196, "percentage": 43.97, "elapsed_time": "3:31:39", "remaining_time": "4:29:44"} +{"current_steps": 544, "total_steps": 1235, "loss": 0.4647, "lr": 2.7476981118630735e-05, "epoch": 2.2024291497975708, "percentage": 44.05, "elapsed_time": "3:32:02", "remaining_time": "4:29:20"} +{"current_steps": 545, "total_steps": 1235, "loss": 0.4744, "lr": 2.742449775134085e-05, "epoch": 2.2064777327935223, "percentage": 44.13, "elapsed_time": "3:32:25", "remaining_time": "4:28:56"} +{"current_steps": 546, "total_steps": 1235, "loss": 0.4667, "lr": 2.7371955017964788e-05, "epoch": 2.2105263157894735, "percentage": 44.21, "elapsed_time": "3:32:48", "remaining_time": "4:28:32"} +{"current_steps": 547, "total_steps": 1235, "loss": 0.4729, "lr": 2.7319353338632845e-05, "epoch": 2.214574898785425, "percentage": 44.29, "elapsed_time": "3:33:10", "remaining_time": "4:28:07"} +{"current_steps": 548, "total_steps": 1235, "loss": 0.4784, "lr": 2.7266693133946645e-05, "epoch": 2.2186234817813766, "percentage": 44.37, "elapsed_time": "3:33:34", "remaining_time": "4:27:44"} +{"current_steps": 549, "total_steps": 1235, "loss": 0.4648, "lr": 2.7213974824975785e-05, "epoch": 2.2226720647773277, "percentage": 44.45, "elapsed_time": "3:33:57", "remaining_time": "4:27:21"} +{"current_steps": 550, "total_steps": 1235, "loss": 0.4748, "lr": 2.7161198833254464e-05, "epoch": 2.2267206477732793, "percentage": 44.53, "elapsed_time": "3:34:20", "remaining_time": "4:26:57"} +{"current_steps": 551, "total_steps": 1235, "loss": 0.4786, "lr": 2.7108365580778095e-05, "epoch": 2.230769230769231, "percentage": 44.62, "elapsed_time": "3:34:43", "remaining_time": "4:26:33"} +{"current_steps": 552, "total_steps": 1235, "loss": 0.4814, "lr": 2.705547548999996e-05, "epoch": 2.234817813765182, "percentage": 44.7, "elapsed_time": "3:35:07", "remaining_time": "4:26:10"} +{"current_steps": 553, "total_steps": 1235, "loss": 0.4652, "lr": 2.7002528983827817e-05, "epoch": 2.2388663967611335, "percentage": 44.78, "elapsed_time": "3:35:29", "remaining_time": "4:25:45"} +{"current_steps": 554, "total_steps": 1235, "loss": 0.4698, "lr": 2.6949526485620517e-05, "epoch": 2.242914979757085, "percentage": 44.86, "elapsed_time": "3:35:53", "remaining_time": "4:25:22"} +{"current_steps": 555, "total_steps": 1235, "loss": 0.4774, "lr": 2.6896468419184623e-05, "epoch": 2.246963562753036, "percentage": 44.94, "elapsed_time": "3:36:16", "remaining_time": "4:24:58"} +{"current_steps": 556, "total_steps": 1235, "loss": 0.4769, "lr": 2.6843355208771024e-05, "epoch": 2.251012145748988, "percentage": 45.02, "elapsed_time": "3:36:39", "remaining_time": "4:24:35"} +{"current_steps": 557, "total_steps": 1235, "loss": 0.474, "lr": 2.6790187279071536e-05, "epoch": 2.2550607287449393, "percentage": 45.1, "elapsed_time": "3:37:02", "remaining_time": "4:24:11"} +{"current_steps": 558, "total_steps": 1235, "loss": 0.475, "lr": 2.67369650552155e-05, "epoch": 2.2591093117408905, "percentage": 45.18, "elapsed_time": "3:37:25", "remaining_time": "4:23:47"} +{"current_steps": 559, "total_steps": 1235, "loss": 0.4613, "lr": 2.6683688962766407e-05, "epoch": 2.263157894736842, "percentage": 45.26, "elapsed_time": "3:37:47", "remaining_time": "4:23:23"} +{"current_steps": 560, "total_steps": 1235, "loss": 0.4667, "lr": 2.6630359427718468e-05, "epoch": 2.2672064777327936, "percentage": 45.34, "elapsed_time": "3:38:11", "remaining_time": "4:23:00"} +{"current_steps": 561, "total_steps": 1235, "loss": 0.4689, "lr": 2.6576976876493225e-05, "epoch": 2.2712550607287447, "percentage": 45.43, "elapsed_time": "3:38:34", "remaining_time": "4:22:36"} +{"current_steps": 562, "total_steps": 1235, "loss": 0.4797, "lr": 2.652354173593614e-05, "epoch": 2.2753036437246963, "percentage": 45.51, "elapsed_time": "3:38:57", "remaining_time": "4:22:12"} +{"current_steps": 563, "total_steps": 1235, "loss": 0.4563, "lr": 2.647005443331317e-05, "epoch": 2.279352226720648, "percentage": 45.59, "elapsed_time": "3:39:19", "remaining_time": "4:21:46"} +{"current_steps": 564, "total_steps": 1235, "loss": 0.4742, "lr": 2.6416515396307354e-05, "epoch": 2.283400809716599, "percentage": 45.67, "elapsed_time": "3:39:42", "remaining_time": "4:21:23"} +{"current_steps": 565, "total_steps": 1235, "loss": 0.4898, "lr": 2.636292505301542e-05, "epoch": 2.2874493927125505, "percentage": 45.75, "elapsed_time": "3:40:06", "remaining_time": "4:21:00"} +{"current_steps": 566, "total_steps": 1235, "loss": 0.4562, "lr": 2.630928383194431e-05, "epoch": 2.291497975708502, "percentage": 45.83, "elapsed_time": "3:40:29", "remaining_time": "4:20:37"} +{"current_steps": 567, "total_steps": 1235, "loss": 0.4753, "lr": 2.625559216200781e-05, "epoch": 2.2955465587044532, "percentage": 45.91, "elapsed_time": "3:40:52", "remaining_time": "4:20:13"} +{"current_steps": 568, "total_steps": 1235, "loss": 0.4859, "lr": 2.620185047252308e-05, "epoch": 2.299595141700405, "percentage": 45.99, "elapsed_time": "3:41:15", "remaining_time": "4:19:48"} +{"current_steps": 569, "total_steps": 1235, "loss": 0.485, "lr": 2.614805919320723e-05, "epoch": 2.3036437246963564, "percentage": 46.07, "elapsed_time": "3:41:37", "remaining_time": "4:19:24"} +{"current_steps": 570, "total_steps": 1235, "loss": 0.4859, "lr": 2.6094218754173895e-05, "epoch": 2.3076923076923075, "percentage": 46.15, "elapsed_time": "3:42:01", "remaining_time": "4:19:01"} +{"current_steps": 571, "total_steps": 1235, "loss": 0.4669, "lr": 2.60403295859298e-05, "epoch": 2.311740890688259, "percentage": 46.23, "elapsed_time": "3:42:25", "remaining_time": "4:18:38"} +{"current_steps": 572, "total_steps": 1235, "loss": 0.4648, "lr": 2.5986392119371297e-05, "epoch": 2.3157894736842106, "percentage": 46.32, "elapsed_time": "3:42:47", "remaining_time": "4:18:14"} +{"current_steps": 573, "total_steps": 1235, "loss": 0.4579, "lr": 2.5932406785780928e-05, "epoch": 2.3198380566801617, "percentage": 46.4, "elapsed_time": "3:43:10", "remaining_time": "4:17:50"} +{"current_steps": 574, "total_steps": 1235, "loss": 0.4579, "lr": 2.5878374016823987e-05, "epoch": 2.3238866396761133, "percentage": 46.48, "elapsed_time": "3:43:32", "remaining_time": "4:17:25"} +{"current_steps": 575, "total_steps": 1235, "loss": 0.485, "lr": 2.5824294244545045e-05, "epoch": 2.327935222672065, "percentage": 46.56, "elapsed_time": "3:43:55", "remaining_time": "4:17:02"} +{"current_steps": 576, "total_steps": 1235, "loss": 0.4831, "lr": 2.577016790136453e-05, "epoch": 2.331983805668016, "percentage": 46.64, "elapsed_time": "3:44:19", "remaining_time": "4:16:38"} +{"current_steps": 577, "total_steps": 1235, "loss": 0.4766, "lr": 2.5715995420075225e-05, "epoch": 2.3360323886639676, "percentage": 46.72, "elapsed_time": "3:44:42", "remaining_time": "4:16:15"} +{"current_steps": 578, "total_steps": 1235, "loss": 0.4603, "lr": 2.5661777233838864e-05, "epoch": 2.340080971659919, "percentage": 46.8, "elapsed_time": "3:45:05", "remaining_time": "4:15:51"} +{"current_steps": 579, "total_steps": 1235, "loss": 0.4538, "lr": 2.5607513776182616e-05, "epoch": 2.3441295546558703, "percentage": 46.88, "elapsed_time": "3:45:29", "remaining_time": "4:15:28"} +{"current_steps": 580, "total_steps": 1235, "loss": 0.4641, "lr": 2.5553205480995633e-05, "epoch": 2.348178137651822, "percentage": 46.96, "elapsed_time": "3:45:52", "remaining_time": "4:15:05"} +{"current_steps": 581, "total_steps": 1235, "loss": 0.4634, "lr": 2.5498852782525604e-05, "epoch": 2.3522267206477734, "percentage": 47.04, "elapsed_time": "3:46:15", "remaining_time": "4:14:41"} +{"current_steps": 582, "total_steps": 1235, "loss": 0.4497, "lr": 2.5444456115375252e-05, "epoch": 2.3562753036437245, "percentage": 47.13, "elapsed_time": "3:46:38", "remaining_time": "4:14:17"} +{"current_steps": 583, "total_steps": 1235, "loss": 0.4553, "lr": 2.539001591449889e-05, "epoch": 2.360323886639676, "percentage": 47.21, "elapsed_time": "3:47:00", "remaining_time": "4:13:53"} +{"current_steps": 584, "total_steps": 1235, "loss": 0.4776, "lr": 2.53355326151989e-05, "epoch": 2.3643724696356276, "percentage": 47.29, "elapsed_time": "3:47:23", "remaining_time": "4:13:29"} +{"current_steps": 585, "total_steps": 1235, "loss": 0.4677, "lr": 2.5281006653122288e-05, "epoch": 2.3684210526315788, "percentage": 47.37, "elapsed_time": "3:47:47", "remaining_time": "4:13:05"} +{"current_steps": 586, "total_steps": 1235, "loss": 0.4601, "lr": 2.5226438464257217e-05, "epoch": 2.3724696356275303, "percentage": 47.45, "elapsed_time": "3:48:09", "remaining_time": "4:12:41"} +{"current_steps": 587, "total_steps": 1235, "loss": 0.4839, "lr": 2.5171828484929447e-05, "epoch": 2.376518218623482, "percentage": 47.53, "elapsed_time": "3:48:31", "remaining_time": "4:12:16"} +{"current_steps": 588, "total_steps": 1235, "loss": 0.4591, "lr": 2.5117177151798934e-05, "epoch": 2.380566801619433, "percentage": 47.61, "elapsed_time": "3:48:55", "remaining_time": "4:11:53"} +{"current_steps": 589, "total_steps": 1235, "loss": 0.4802, "lr": 2.506248490185627e-05, "epoch": 2.3846153846153846, "percentage": 47.69, "elapsed_time": "3:49:18", "remaining_time": "4:11:29"} +{"current_steps": 590, "total_steps": 1235, "loss": 0.4739, "lr": 2.500775217241923e-05, "epoch": 2.388663967611336, "percentage": 47.77, "elapsed_time": "3:49:41", "remaining_time": "4:11:06"} +{"current_steps": 591, "total_steps": 1235, "loss": 0.4779, "lr": 2.4952979401129266e-05, "epoch": 2.3927125506072873, "percentage": 47.85, "elapsed_time": "3:50:04", "remaining_time": "4:10:42"} +{"current_steps": 592, "total_steps": 1235, "loss": 0.4512, "lr": 2.4898167025948e-05, "epoch": 2.396761133603239, "percentage": 47.94, "elapsed_time": "3:50:27", "remaining_time": "4:10:18"} +{"current_steps": 593, "total_steps": 1235, "loss": 0.476, "lr": 2.4843315485153703e-05, "epoch": 2.4008097165991904, "percentage": 48.02, "elapsed_time": "3:50:50", "remaining_time": "4:09:55"} +{"current_steps": 594, "total_steps": 1235, "loss": 0.4807, "lr": 2.4788425217337856e-05, "epoch": 2.4048582995951415, "percentage": 48.1, "elapsed_time": "3:51:13", "remaining_time": "4:09:31"} +{"current_steps": 595, "total_steps": 1235, "loss": 0.4709, "lr": 2.4733496661401572e-05, "epoch": 2.408906882591093, "percentage": 48.18, "elapsed_time": "3:51:36", "remaining_time": "4:09:07"} +{"current_steps": 596, "total_steps": 1235, "loss": 0.4894, "lr": 2.4678530256552114e-05, "epoch": 2.4129554655870447, "percentage": 48.26, "elapsed_time": "3:51:59", "remaining_time": "4:08:43"} +{"current_steps": 597, "total_steps": 1235, "loss": 0.4649, "lr": 2.46235264422994e-05, "epoch": 2.417004048582996, "percentage": 48.34, "elapsed_time": "3:52:23", "remaining_time": "4:08:21"} +{"current_steps": 598, "total_steps": 1235, "loss": 0.4714, "lr": 2.4568485658452452e-05, "epoch": 2.4210526315789473, "percentage": 48.42, "elapsed_time": "3:52:46", "remaining_time": "4:07:57"} +{"current_steps": 599, "total_steps": 1235, "loss": 0.4692, "lr": 2.451340834511592e-05, "epoch": 2.425101214574899, "percentage": 48.5, "elapsed_time": "3:53:09", "remaining_time": "4:07:33"} +{"current_steps": 600, "total_steps": 1235, "loss": 0.4698, "lr": 2.4458294942686528e-05, "epoch": 2.42914979757085, "percentage": 48.58, "elapsed_time": "3:53:33", "remaining_time": "4:07:10"} +{"current_steps": 601, "total_steps": 1235, "loss": 0.4784, "lr": 2.440314589184958e-05, "epoch": 2.4331983805668016, "percentage": 48.66, "elapsed_time": "3:53:57", "remaining_time": "4:06:47"} +{"current_steps": 602, "total_steps": 1235, "loss": 0.4841, "lr": 2.434796163357541e-05, "epoch": 2.437246963562753, "percentage": 48.74, "elapsed_time": "3:54:20", "remaining_time": "4:06:24"} +{"current_steps": 603, "total_steps": 1235, "loss": 0.4631, "lr": 2.429274260911588e-05, "epoch": 2.4412955465587043, "percentage": 48.83, "elapsed_time": "3:54:42", "remaining_time": "4:05:59"} +{"current_steps": 604, "total_steps": 1235, "loss": 0.4458, "lr": 2.423748926000084e-05, "epoch": 2.445344129554656, "percentage": 48.91, "elapsed_time": "3:55:03", "remaining_time": "4:05:34"} +{"current_steps": 605, "total_steps": 1235, "loss": 0.4796, "lr": 2.418220202803459e-05, "epoch": 2.4493927125506074, "percentage": 48.99, "elapsed_time": "3:55:26", "remaining_time": "4:05:10"} +{"current_steps": 606, "total_steps": 1235, "loss": 0.471, "lr": 2.412688135529237e-05, "epoch": 2.4534412955465585, "percentage": 49.07, "elapsed_time": "3:55:49", "remaining_time": "4:04:46"} +{"current_steps": 607, "total_steps": 1235, "loss": 0.4792, "lr": 2.4071527684116807e-05, "epoch": 2.45748987854251, "percentage": 49.15, "elapsed_time": "3:56:11", "remaining_time": "4:04:21"} +{"current_steps": 608, "total_steps": 1235, "loss": 0.479, "lr": 2.4016141457114372e-05, "epoch": 2.4615384615384617, "percentage": 49.23, "elapsed_time": "3:56:33", "remaining_time": "4:03:57"} +{"current_steps": 609, "total_steps": 1235, "loss": 0.4681, "lr": 2.396072311715187e-05, "epoch": 2.465587044534413, "percentage": 49.31, "elapsed_time": "3:56:56", "remaining_time": "4:03:33"} +{"current_steps": 610, "total_steps": 1235, "loss": 0.4639, "lr": 2.3905273107352863e-05, "epoch": 2.4696356275303644, "percentage": 49.39, "elapsed_time": "3:57:19", "remaining_time": "4:03:09"} +{"current_steps": 611, "total_steps": 1235, "loss": 0.4759, "lr": 2.3849791871094157e-05, "epoch": 2.473684210526316, "percentage": 49.47, "elapsed_time": "3:57:42", "remaining_time": "4:02:46"} +{"current_steps": 612, "total_steps": 1235, "loss": 0.494, "lr": 2.379427985200223e-05, "epoch": 2.477732793522267, "percentage": 49.55, "elapsed_time": "3:58:06", "remaining_time": "4:02:22"} +{"current_steps": 613, "total_steps": 1235, "loss": 0.4719, "lr": 2.373873749394972e-05, "epoch": 2.4817813765182186, "percentage": 49.64, "elapsed_time": "3:58:30", "remaining_time": "4:02:00"} +{"current_steps": 614, "total_steps": 1235, "loss": 0.48, "lr": 2.3683165241051836e-05, "epoch": 2.48582995951417, "percentage": 49.72, "elapsed_time": "3:58:53", "remaining_time": "4:01:37"} +{"current_steps": 615, "total_steps": 1235, "loss": 0.47, "lr": 2.3627563537662823e-05, "epoch": 2.4898785425101213, "percentage": 49.8, "elapsed_time": "3:59:16", "remaining_time": "4:01:12"} +{"current_steps": 616, "total_steps": 1235, "loss": 0.4701, "lr": 2.3571932828372433e-05, "epoch": 2.493927125506073, "percentage": 49.88, "elapsed_time": "3:59:38", "remaining_time": "4:00:48"} +{"current_steps": 617, "total_steps": 1235, "loss": 0.4578, "lr": 2.351627355800233e-05, "epoch": 2.4979757085020244, "percentage": 49.96, "elapsed_time": "4:00:01", "remaining_time": "4:00:24"} +{"current_steps": 618, "total_steps": 1235, "loss": 0.4724, "lr": 2.346058617160256e-05, "epoch": 2.5020242914979756, "percentage": 50.04, "elapsed_time": "4:00:25", "remaining_time": "4:00:01"} +{"current_steps": 619, "total_steps": 1235, "loss": 0.4675, "lr": 2.3404871114447976e-05, "epoch": 2.506072874493927, "percentage": 50.12, "elapsed_time": "4:00:48", "remaining_time": "3:59:38"} +{"current_steps": 620, "total_steps": 1235, "loss": 0.4691, "lr": 2.334912883203469e-05, "epoch": 2.5101214574898787, "percentage": 50.2, "elapsed_time": "4:01:11", "remaining_time": "3:59:14"} +{"current_steps": 621, "total_steps": 1235, "loss": 0.4735, "lr": 2.3293359770076505e-05, "epoch": 2.51417004048583, "percentage": 50.28, "elapsed_time": "4:01:34", "remaining_time": "3:58:51"} +{"current_steps": 622, "total_steps": 1235, "loss": 0.4864, "lr": 2.323756437450136e-05, "epoch": 2.5182186234817814, "percentage": 50.36, "elapsed_time": "4:01:58", "remaining_time": "3:58:28"} +{"current_steps": 623, "total_steps": 1235, "loss": 0.4577, "lr": 2.3181743091447754e-05, "epoch": 2.522267206477733, "percentage": 50.45, "elapsed_time": "4:02:21", "remaining_time": "3:58:05"} +{"current_steps": 624, "total_steps": 1235, "loss": 0.4764, "lr": 2.3125896367261164e-05, "epoch": 2.526315789473684, "percentage": 50.53, "elapsed_time": "4:02:45", "remaining_time": "3:57:41"} +{"current_steps": 625, "total_steps": 1235, "loss": 0.4718, "lr": 2.307002464849052e-05, "epoch": 2.5303643724696356, "percentage": 50.61, "elapsed_time": "4:03:07", "remaining_time": "3:57:17"} +{"current_steps": 626, "total_steps": 1235, "loss": 0.4489, "lr": 2.30141283818846e-05, "epoch": 2.534412955465587, "percentage": 50.69, "elapsed_time": "4:03:31", "remaining_time": "3:56:54"} +{"current_steps": 627, "total_steps": 1235, "loss": 0.4603, "lr": 2.2958208014388462e-05, "epoch": 2.5384615384615383, "percentage": 50.77, "elapsed_time": "4:03:55", "remaining_time": "3:56:31"} +{"current_steps": 628, "total_steps": 1235, "loss": 0.4811, "lr": 2.2902263993139857e-05, "epoch": 2.54251012145749, "percentage": 50.85, "elapsed_time": "4:04:18", "remaining_time": "3:56:08"} +{"current_steps": 629, "total_steps": 1235, "loss": 0.4679, "lr": 2.2846296765465708e-05, "epoch": 2.5465587044534415, "percentage": 50.93, "elapsed_time": "4:04:41", "remaining_time": "3:55:44"} +{"current_steps": 630, "total_steps": 1235, "loss": 0.4698, "lr": 2.2790306778878465e-05, "epoch": 2.5506072874493926, "percentage": 51.01, "elapsed_time": "4:05:04", "remaining_time": "3:55:21"} +{"current_steps": 631, "total_steps": 1235, "loss": 0.4813, "lr": 2.273429448107257e-05, "epoch": 2.554655870445344, "percentage": 51.09, "elapsed_time": "4:05:27", "remaining_time": "3:54:57"} +{"current_steps": 632, "total_steps": 1235, "loss": 0.4629, "lr": 2.2678260319920868e-05, "epoch": 2.5587044534412957, "percentage": 51.17, "elapsed_time": "4:05:50", "remaining_time": "3:54:33"} +{"current_steps": 633, "total_steps": 1235, "loss": 0.4585, "lr": 2.262220474347102e-05, "epoch": 2.562753036437247, "percentage": 51.26, "elapsed_time": "4:06:12", "remaining_time": "3:54:09"} +{"current_steps": 634, "total_steps": 1235, "loss": 0.4712, "lr": 2.2566128199941918e-05, "epoch": 2.5668016194331984, "percentage": 51.34, "elapsed_time": "4:06:36", "remaining_time": "3:53:46"} +{"current_steps": 635, "total_steps": 1235, "loss": 0.4598, "lr": 2.2510031137720104e-05, "epoch": 2.57085020242915, "percentage": 51.42, "elapsed_time": "4:06:58", "remaining_time": "3:53:21"} +{"current_steps": 636, "total_steps": 1235, "loss": 0.5082, "lr": 2.2453914005356206e-05, "epoch": 2.574898785425101, "percentage": 51.5, "elapsed_time": "4:07:21", "remaining_time": "3:52:57"} +{"current_steps": 637, "total_steps": 1235, "loss": 0.4797, "lr": 2.2397777251561302e-05, "epoch": 2.5789473684210527, "percentage": 51.58, "elapsed_time": "4:07:44", "remaining_time": "3:52:34"} +{"current_steps": 638, "total_steps": 1235, "loss": 0.4907, "lr": 2.2341621325203393e-05, "epoch": 2.582995951417004, "percentage": 51.66, "elapsed_time": "4:08:06", "remaining_time": "3:52:09"} +{"current_steps": 639, "total_steps": 1235, "loss": 0.471, "lr": 2.2285446675303764e-05, "epoch": 2.5870445344129553, "percentage": 51.74, "elapsed_time": "4:08:30", "remaining_time": "3:51:46"} +{"current_steps": 640, "total_steps": 1235, "loss": 0.4732, "lr": 2.2229253751033423e-05, "epoch": 2.591093117408907, "percentage": 51.82, "elapsed_time": "4:08:52", "remaining_time": "3:51:22"} +{"current_steps": 641, "total_steps": 1235, "loss": 0.478, "lr": 2.2173043001709492e-05, "epoch": 2.5951417004048585, "percentage": 51.9, "elapsed_time": "4:09:15", "remaining_time": "3:50:58"} +{"current_steps": 642, "total_steps": 1235, "loss": 0.467, "lr": 2.2116814876791627e-05, "epoch": 2.5991902834008096, "percentage": 51.98, "elapsed_time": "4:09:38", "remaining_time": "3:50:35"} +{"current_steps": 643, "total_steps": 1235, "loss": 0.464, "lr": 2.2060569825878413e-05, "epoch": 2.603238866396761, "percentage": 52.06, "elapsed_time": "4:10:00", "remaining_time": "3:50:11"} +{"current_steps": 644, "total_steps": 1235, "loss": 0.4876, "lr": 2.2004308298703777e-05, "epoch": 2.6072874493927127, "percentage": 52.15, "elapsed_time": "4:10:24", "remaining_time": "3:49:47"} +{"current_steps": 645, "total_steps": 1235, "loss": 0.4706, "lr": 2.1948030745133396e-05, "epoch": 2.611336032388664, "percentage": 52.23, "elapsed_time": "4:10:47", "remaining_time": "3:49:24"} +{"current_steps": 646, "total_steps": 1235, "loss": 0.4626, "lr": 2.1891737615161083e-05, "epoch": 2.6153846153846154, "percentage": 52.31, "elapsed_time": "4:11:10", "remaining_time": "3:49:00"} +{"current_steps": 647, "total_steps": 1235, "loss": 0.4672, "lr": 2.1835429358905218e-05, "epoch": 2.619433198380567, "percentage": 52.39, "elapsed_time": "4:11:33", "remaining_time": "3:48:37"} +{"current_steps": 648, "total_steps": 1235, "loss": 0.4645, "lr": 2.17791064266051e-05, "epoch": 2.623481781376518, "percentage": 52.47, "elapsed_time": "4:11:58", "remaining_time": "3:48:14"} +{"current_steps": 649, "total_steps": 1235, "loss": 0.4743, "lr": 2.172276926861741e-05, "epoch": 2.6275303643724697, "percentage": 52.55, "elapsed_time": "4:12:21", "remaining_time": "3:47:51"} +{"current_steps": 650, "total_steps": 1235, "loss": 0.468, "lr": 2.166641833541255e-05, "epoch": 2.6315789473684212, "percentage": 52.63, "elapsed_time": "4:12:44", "remaining_time": "3:47:27"} +{"current_steps": 651, "total_steps": 1235, "loss": 0.4532, "lr": 2.161005407757109e-05, "epoch": 2.6356275303643724, "percentage": 52.71, "elapsed_time": "4:13:07", "remaining_time": "3:47:04"} +{"current_steps": 652, "total_steps": 1235, "loss": 0.4819, "lr": 2.155367694578013e-05, "epoch": 2.639676113360324, "percentage": 52.79, "elapsed_time": "4:13:31", "remaining_time": "3:46:41"} +{"current_steps": 653, "total_steps": 1235, "loss": 0.477, "lr": 2.1497287390829712e-05, "epoch": 2.6437246963562755, "percentage": 52.87, "elapsed_time": "4:13:53", "remaining_time": "3:46:16"} +{"current_steps": 654, "total_steps": 1235, "loss": 0.4803, "lr": 2.1440885863609208e-05, "epoch": 2.6477732793522266, "percentage": 52.96, "elapsed_time": "4:14:16", "remaining_time": "3:45:53"} +{"current_steps": 655, "total_steps": 1235, "loss": 0.458, "lr": 2.1384472815103737e-05, "epoch": 2.651821862348178, "percentage": 53.04, "elapsed_time": "4:14:40", "remaining_time": "3:45:30"} +{"current_steps": 656, "total_steps": 1235, "loss": 0.4815, "lr": 2.1328048696390534e-05, "epoch": 2.6558704453441297, "percentage": 53.12, "elapsed_time": "4:15:02", "remaining_time": "3:45:06"} +{"current_steps": 657, "total_steps": 1235, "loss": 0.4867, "lr": 2.1271613958635342e-05, "epoch": 2.659919028340081, "percentage": 53.2, "elapsed_time": "4:15:25", "remaining_time": "3:44:42"} +{"current_steps": 658, "total_steps": 1235, "loss": 0.4569, "lr": 2.1215169053088825e-05, "epoch": 2.6639676113360324, "percentage": 53.28, "elapsed_time": "4:15:49", "remaining_time": "3:44:19"} +{"current_steps": 659, "total_steps": 1235, "loss": 0.4758, "lr": 2.1158714431082937e-05, "epoch": 2.668016194331984, "percentage": 53.36, "elapsed_time": "4:16:12", "remaining_time": "3:43:56"} +{"current_steps": 660, "total_steps": 1235, "loss": 0.4712, "lr": 2.110225054402733e-05, "epoch": 2.672064777327935, "percentage": 53.44, "elapsed_time": "4:16:35", "remaining_time": "3:43:33"} +{"current_steps": 661, "total_steps": 1235, "loss": 0.4875, "lr": 2.1045777843405747e-05, "epoch": 2.6761133603238867, "percentage": 53.52, "elapsed_time": "4:16:58", "remaining_time": "3:43:09"} +{"current_steps": 662, "total_steps": 1235, "loss": 0.4761, "lr": 2.09892967807724e-05, "epoch": 2.6801619433198383, "percentage": 53.6, "elapsed_time": "4:17:21", "remaining_time": "3:42:45"} +{"current_steps": 663, "total_steps": 1235, "loss": 0.4768, "lr": 2.093280780774835e-05, "epoch": 2.6842105263157894, "percentage": 53.68, "elapsed_time": "4:17:44", "remaining_time": "3:42:22"} +{"current_steps": 664, "total_steps": 1235, "loss": 0.4754, "lr": 2.087631137601793e-05, "epoch": 2.688259109311741, "percentage": 53.77, "elapsed_time": "4:18:08", "remaining_time": "3:41:59"} +{"current_steps": 665, "total_steps": 1235, "loss": 0.464, "lr": 2.0819807937325104e-05, "epoch": 2.6923076923076925, "percentage": 53.85, "elapsed_time": "4:18:31", "remaining_time": "3:41:35"} +{"current_steps": 666, "total_steps": 1235, "loss": 0.4704, "lr": 2.0763297943469847e-05, "epoch": 2.6963562753036436, "percentage": 53.93, "elapsed_time": "4:18:55", "remaining_time": "3:41:12"} +{"current_steps": 667, "total_steps": 1235, "loss": 0.4587, "lr": 2.070678184630458e-05, "epoch": 2.700404858299595, "percentage": 54.01, "elapsed_time": "4:19:18", "remaining_time": "3:40:49"} +{"current_steps": 668, "total_steps": 1235, "loss": 0.4677, "lr": 2.06502600977305e-05, "epoch": 2.7044534412955468, "percentage": 54.09, "elapsed_time": "4:19:41", "remaining_time": "3:40:25"} +{"current_steps": 669, "total_steps": 1235, "loss": 0.4618, "lr": 2.0593733149694008e-05, "epoch": 2.708502024291498, "percentage": 54.17, "elapsed_time": "4:20:04", "remaining_time": "3:40:01"} +{"current_steps": 670, "total_steps": 1235, "loss": 0.4563, "lr": 2.0537201454183074e-05, "epoch": 2.7125506072874495, "percentage": 54.25, "elapsed_time": "4:20:25", "remaining_time": "3:39:36"} +{"current_steps": 671, "total_steps": 1235, "loss": 0.4869, "lr": 2.0480665463223626e-05, "epoch": 2.716599190283401, "percentage": 54.33, "elapsed_time": "4:20:48", "remaining_time": "3:39:13"} +{"current_steps": 672, "total_steps": 1235, "loss": 0.4728, "lr": 2.042412562887594e-05, "epoch": 2.720647773279352, "percentage": 54.41, "elapsed_time": "4:21:11", "remaining_time": "3:38:49"} +{"current_steps": 673, "total_steps": 1235, "loss": 0.4723, "lr": 2.0367582403231033e-05, "epoch": 2.7246963562753037, "percentage": 54.49, "elapsed_time": "4:21:34", "remaining_time": "3:38:25"} +{"current_steps": 674, "total_steps": 1235, "loss": 0.4609, "lr": 2.0311036238407023e-05, "epoch": 2.7287449392712553, "percentage": 54.57, "elapsed_time": "4:21:57", "remaining_time": "3:38:02"} +{"current_steps": 675, "total_steps": 1235, "loss": 0.4887, "lr": 2.0254487586545534e-05, "epoch": 2.7327935222672064, "percentage": 54.66, "elapsed_time": "4:22:19", "remaining_time": "3:37:37"} +{"current_steps": 676, "total_steps": 1235, "loss": 0.4528, "lr": 2.0197936899808088e-05, "epoch": 2.736842105263158, "percentage": 54.74, "elapsed_time": "4:22:42", "remaining_time": "3:37:14"} +{"current_steps": 677, "total_steps": 1235, "loss": 0.4748, "lr": 2.0141384630372466e-05, "epoch": 2.7408906882591095, "percentage": 54.82, "elapsed_time": "4:23:05", "remaining_time": "3:36:50"} +{"current_steps": 678, "total_steps": 1235, "loss": 0.4779, "lr": 2.0084831230429106e-05, "epoch": 2.7449392712550607, "percentage": 54.9, "elapsed_time": "4:23:27", "remaining_time": "3:36:26"} +{"current_steps": 679, "total_steps": 1235, "loss": 0.4965, "lr": 2.0028277152177492e-05, "epoch": 2.748987854251012, "percentage": 54.98, "elapsed_time": "4:23:49", "remaining_time": "3:36:02"} +{"current_steps": 680, "total_steps": 1235, "loss": 0.4667, "lr": 1.9971722847822518e-05, "epoch": 2.753036437246964, "percentage": 55.06, "elapsed_time": "4:24:12", "remaining_time": "3:35:38"} +{"current_steps": 681, "total_steps": 1235, "loss": 0.4688, "lr": 1.99151687695709e-05, "epoch": 2.757085020242915, "percentage": 55.14, "elapsed_time": "4:24:35", "remaining_time": "3:35:14"} +{"current_steps": 682, "total_steps": 1235, "loss": 0.4756, "lr": 1.9858615369627537e-05, "epoch": 2.7611336032388665, "percentage": 55.22, "elapsed_time": "4:24:58", "remaining_time": "3:34:51"} +{"current_steps": 683, "total_steps": 1235, "loss": 0.4567, "lr": 1.9802063100191916e-05, "epoch": 2.765182186234818, "percentage": 55.3, "elapsed_time": "4:25:20", "remaining_time": "3:34:26"} +{"current_steps": 684, "total_steps": 1235, "loss": 0.4661, "lr": 1.974551241345447e-05, "epoch": 2.769230769230769, "percentage": 55.38, "elapsed_time": "4:25:42", "remaining_time": "3:34:02"} +{"current_steps": 685, "total_steps": 1235, "loss": 0.4504, "lr": 1.9688963761592984e-05, "epoch": 2.7732793522267207, "percentage": 55.47, "elapsed_time": "4:26:06", "remaining_time": "3:33:39"} +{"current_steps": 686, "total_steps": 1235, "loss": 0.4732, "lr": 1.963241759676897e-05, "epoch": 2.7773279352226723, "percentage": 55.55, "elapsed_time": "4:26:29", "remaining_time": "3:33:16"} +{"current_steps": 687, "total_steps": 1235, "loss": 0.4799, "lr": 1.9575874371124066e-05, "epoch": 2.7813765182186234, "percentage": 55.63, "elapsed_time": "4:26:53", "remaining_time": "3:32:53"} +{"current_steps": 688, "total_steps": 1235, "loss": 0.4805, "lr": 1.951933453677638e-05, "epoch": 2.785425101214575, "percentage": 55.71, "elapsed_time": "4:27:16", "remaining_time": "3:32:30"} +{"current_steps": 689, "total_steps": 1235, "loss": 0.454, "lr": 1.9462798545816932e-05, "epoch": 2.7894736842105265, "percentage": 55.79, "elapsed_time": "4:27:39", "remaining_time": "3:32:06"} +{"current_steps": 690, "total_steps": 1235, "loss": 0.4596, "lr": 1.9406266850305996e-05, "epoch": 2.7935222672064777, "percentage": 55.87, "elapsed_time": "4:28:03", "remaining_time": "3:31:43"} +{"current_steps": 691, "total_steps": 1235, "loss": 0.481, "lr": 1.9349739902269503e-05, "epoch": 2.7975708502024292, "percentage": 55.95, "elapsed_time": "4:28:26", "remaining_time": "3:31:20"} +{"current_steps": 692, "total_steps": 1235, "loss": 0.4643, "lr": 1.9293218153695425e-05, "epoch": 2.801619433198381, "percentage": 56.03, "elapsed_time": "4:28:48", "remaining_time": "3:30:56"} +{"current_steps": 693, "total_steps": 1235, "loss": 0.4778, "lr": 1.9236702056530153e-05, "epoch": 2.805668016194332, "percentage": 56.11, "elapsed_time": "4:29:12", "remaining_time": "3:30:32"} +{"current_steps": 694, "total_steps": 1235, "loss": 0.4853, "lr": 1.9180192062674907e-05, "epoch": 2.8097165991902835, "percentage": 56.19, "elapsed_time": "4:29:34", "remaining_time": "3:30:08"} +{"current_steps": 695, "total_steps": 1235, "loss": 0.4704, "lr": 1.9123688623982076e-05, "epoch": 2.813765182186235, "percentage": 56.28, "elapsed_time": "4:29:57", "remaining_time": "3:29:45"} +{"current_steps": 696, "total_steps": 1235, "loss": 0.4758, "lr": 1.906719219225165e-05, "epoch": 2.817813765182186, "percentage": 56.36, "elapsed_time": "4:30:20", "remaining_time": "3:29:21"} +{"current_steps": 697, "total_steps": 1235, "loss": 0.4697, "lr": 1.9010703219227603e-05, "epoch": 2.8218623481781377, "percentage": 56.44, "elapsed_time": "4:30:43", "remaining_time": "3:28:57"} +{"current_steps": 698, "total_steps": 1235, "loss": 0.4752, "lr": 1.8954222156594256e-05, "epoch": 2.8259109311740893, "percentage": 56.52, "elapsed_time": "4:31:06", "remaining_time": "3:28:34"} +{"current_steps": 699, "total_steps": 1235, "loss": 0.4657, "lr": 1.8897749455972673e-05, "epoch": 2.8299595141700404, "percentage": 56.6, "elapsed_time": "4:31:29", "remaining_time": "3:28:10"} +{"current_steps": 700, "total_steps": 1235, "loss": 0.4658, "lr": 1.884128556891707e-05, "epoch": 2.834008097165992, "percentage": 56.68, "elapsed_time": "4:31:52", "remaining_time": "3:27:47"} +{"current_steps": 701, "total_steps": 1235, "loss": 0.476, "lr": 1.878483094691119e-05, "epoch": 2.8380566801619436, "percentage": 56.76, "elapsed_time": "4:32:16", "remaining_time": "3:27:24"} +{"current_steps": 702, "total_steps": 1235, "loss": 0.4692, "lr": 1.8728386041364664e-05, "epoch": 2.8421052631578947, "percentage": 56.84, "elapsed_time": "4:32:39", "remaining_time": "3:27:01"} +{"current_steps": 703, "total_steps": 1235, "loss": 0.466, "lr": 1.867195130360947e-05, "epoch": 2.8461538461538463, "percentage": 56.92, "elapsed_time": "4:33:01", "remaining_time": "3:26:37"} +{"current_steps": 704, "total_steps": 1235, "loss": 0.4747, "lr": 1.8615527184896263e-05, "epoch": 2.850202429149798, "percentage": 57.0, "elapsed_time": "4:33:23", "remaining_time": "3:26:12"} +{"current_steps": 705, "total_steps": 1235, "loss": 0.4866, "lr": 1.8559114136390795e-05, "epoch": 2.854251012145749, "percentage": 57.09, "elapsed_time": "4:33:46", "remaining_time": "3:25:49"} +{"current_steps": 706, "total_steps": 1235, "loss": 0.4789, "lr": 1.8502712609170298e-05, "epoch": 2.8582995951417005, "percentage": 57.17, "elapsed_time": "4:34:09", "remaining_time": "3:25:25"} +{"current_steps": 707, "total_steps": 1235, "loss": 0.4855, "lr": 1.8446323054219876e-05, "epoch": 2.862348178137652, "percentage": 57.25, "elapsed_time": "4:34:33", "remaining_time": "3:25:02"} +{"current_steps": 708, "total_steps": 1235, "loss": 0.4663, "lr": 1.838994592242891e-05, "epoch": 2.866396761133603, "percentage": 57.33, "elapsed_time": "4:34:57", "remaining_time": "3:24:39"} +{"current_steps": 709, "total_steps": 1235, "loss": 0.4395, "lr": 1.8333581664587453e-05, "epoch": 2.8704453441295548, "percentage": 57.41, "elapsed_time": "4:35:19", "remaining_time": "3:24:15"} +{"current_steps": 710, "total_steps": 1235, "loss": 0.4738, "lr": 1.8277230731382593e-05, "epoch": 2.8744939271255063, "percentage": 57.49, "elapsed_time": "4:35:42", "remaining_time": "3:23:51"} +{"current_steps": 711, "total_steps": 1235, "loss": 0.4846, "lr": 1.82208935733949e-05, "epoch": 2.8785425101214575, "percentage": 57.57, "elapsed_time": "4:36:05", "remaining_time": "3:23:28"} +{"current_steps": 712, "total_steps": 1235, "loss": 0.5128, "lr": 1.8164570641094793e-05, "epoch": 2.882591093117409, "percentage": 57.65, "elapsed_time": "4:36:27", "remaining_time": "3:23:04"} +{"current_steps": 713, "total_steps": 1235, "loss": 0.4742, "lr": 1.810826238483892e-05, "epoch": 2.8866396761133606, "percentage": 57.73, "elapsed_time": "4:36:51", "remaining_time": "3:22:41"} +{"current_steps": 714, "total_steps": 1235, "loss": 0.4818, "lr": 1.8051969254866608e-05, "epoch": 2.8906882591093117, "percentage": 57.81, "elapsed_time": "4:37:15", "remaining_time": "3:22:18"} +{"current_steps": 715, "total_steps": 1235, "loss": 0.4446, "lr": 1.7995691701296226e-05, "epoch": 2.8947368421052633, "percentage": 57.89, "elapsed_time": "4:37:38", "remaining_time": "3:21:55"} +{"current_steps": 716, "total_steps": 1235, "loss": 0.4532, "lr": 1.7939430174121593e-05, "epoch": 2.898785425101215, "percentage": 57.98, "elapsed_time": "4:38:01", "remaining_time": "3:21:32"} +{"current_steps": 717, "total_steps": 1235, "loss": 0.4508, "lr": 1.788318512320838e-05, "epoch": 2.902834008097166, "percentage": 58.06, "elapsed_time": "4:38:24", "remaining_time": "3:21:08"} +{"current_steps": 718, "total_steps": 1235, "loss": 0.4843, "lr": 1.782695699829051e-05, "epoch": 2.9068825910931175, "percentage": 58.14, "elapsed_time": "4:38:48", "remaining_time": "3:20:45"} +{"current_steps": 719, "total_steps": 1235, "loss": 0.4582, "lr": 1.7770746248966587e-05, "epoch": 2.910931174089069, "percentage": 58.22, "elapsed_time": "4:39:11", "remaining_time": "3:20:22"} +{"current_steps": 720, "total_steps": 1235, "loss": 0.475, "lr": 1.7714553324696243e-05, "epoch": 2.91497975708502, "percentage": 58.3, "elapsed_time": "4:39:35", "remaining_time": "3:19:58"} +{"current_steps": 721, "total_steps": 1235, "loss": 0.469, "lr": 1.7658378674796614e-05, "epoch": 2.919028340080972, "percentage": 58.38, "elapsed_time": "4:39:58", "remaining_time": "3:19:35"} +{"current_steps": 722, "total_steps": 1235, "loss": 0.4875, "lr": 1.76022227484387e-05, "epoch": 2.9230769230769234, "percentage": 58.46, "elapsed_time": "4:40:22", "remaining_time": "3:19:12"} +{"current_steps": 723, "total_steps": 1235, "loss": 0.4628, "lr": 1.7546085994643807e-05, "epoch": 2.9271255060728745, "percentage": 58.54, "elapsed_time": "4:40:44", "remaining_time": "3:18:48"} +{"current_steps": 724, "total_steps": 1235, "loss": 0.4773, "lr": 1.7489968862279902e-05, "epoch": 2.931174089068826, "percentage": 58.62, "elapsed_time": "4:41:07", "remaining_time": "3:18:25"} +{"current_steps": 725, "total_steps": 1235, "loss": 0.4726, "lr": 1.743387180005809e-05, "epoch": 2.9352226720647776, "percentage": 58.7, "elapsed_time": "4:41:31", "remaining_time": "3:18:02"} +{"current_steps": 726, "total_steps": 1235, "loss": 0.4672, "lr": 1.737779525652899e-05, "epoch": 2.9392712550607287, "percentage": 58.79, "elapsed_time": "4:41:55", "remaining_time": "3:17:39"} +{"current_steps": 727, "total_steps": 1235, "loss": 0.4683, "lr": 1.732173968007914e-05, "epoch": 2.9433198380566803, "percentage": 58.87, "elapsed_time": "4:42:17", "remaining_time": "3:17:15"} +{"current_steps": 728, "total_steps": 1235, "loss": 0.4802, "lr": 1.7265705518927437e-05, "epoch": 2.9473684210526314, "percentage": 58.95, "elapsed_time": "4:42:39", "remaining_time": "3:16:51"} +{"current_steps": 729, "total_steps": 1235, "loss": 0.4601, "lr": 1.7209693221121542e-05, "epoch": 2.951417004048583, "percentage": 59.03, "elapsed_time": "4:43:02", "remaining_time": "3:16:27"} +{"current_steps": 730, "total_steps": 1235, "loss": 0.4719, "lr": 1.7153703234534302e-05, "epoch": 2.9554655870445345, "percentage": 59.11, "elapsed_time": "4:43:26", "remaining_time": "3:16:04"} +{"current_steps": 731, "total_steps": 1235, "loss": 0.4903, "lr": 1.709773600686015e-05, "epoch": 2.9595141700404857, "percentage": 59.19, "elapsed_time": "4:43:48", "remaining_time": "3:15:40"} +{"current_steps": 732, "total_steps": 1235, "loss": 0.4584, "lr": 1.7041791985611548e-05, "epoch": 2.9635627530364372, "percentage": 59.27, "elapsed_time": "4:44:11", "remaining_time": "3:15:17"} +{"current_steps": 733, "total_steps": 1235, "loss": 0.4544, "lr": 1.69858716181154e-05, "epoch": 2.967611336032389, "percentage": 59.35, "elapsed_time": "4:44:35", "remaining_time": "3:14:54"} +{"current_steps": 734, "total_steps": 1235, "loss": 0.4801, "lr": 1.692997535150948e-05, "epoch": 2.97165991902834, "percentage": 59.43, "elapsed_time": "4:44:57", "remaining_time": "3:14:30"} +{"current_steps": 735, "total_steps": 1235, "loss": 0.4801, "lr": 1.687410363273884e-05, "epoch": 2.9757085020242915, "percentage": 59.51, "elapsed_time": "4:45:20", "remaining_time": "3:14:06"} +{"current_steps": 736, "total_steps": 1235, "loss": 0.4516, "lr": 1.6818256908552257e-05, "epoch": 2.979757085020243, "percentage": 59.6, "elapsed_time": "4:45:42", "remaining_time": "3:13:42"} +{"current_steps": 737, "total_steps": 1235, "loss": 0.4433, "lr": 1.6762435625498646e-05, "epoch": 2.983805668016194, "percentage": 59.68, "elapsed_time": "4:46:05", "remaining_time": "3:13:19"} +{"current_steps": 738, "total_steps": 1235, "loss": 0.4622, "lr": 1.67066402299235e-05, "epoch": 2.9878542510121457, "percentage": 59.76, "elapsed_time": "4:46:27", "remaining_time": "3:12:54"} +{"current_steps": 739, "total_steps": 1235, "loss": 0.4532, "lr": 1.6650871167965313e-05, "epoch": 2.9919028340080973, "percentage": 59.84, "elapsed_time": "4:46:48", "remaining_time": "3:12:30"} +{"current_steps": 740, "total_steps": 1235, "loss": 0.4704, "lr": 1.6595128885552028e-05, "epoch": 2.9959514170040484, "percentage": 59.92, "elapsed_time": "4:47:12", "remaining_time": "3:12:07"} +{"current_steps": 741, "total_steps": 1235, "loss": 0.4558, "lr": 1.653941382839745e-05, "epoch": 3.0, "percentage": 60.0, "elapsed_time": "4:47:35", "remaining_time": "3:11:43"} +{"current_steps": 742, "total_steps": 1235, "loss": 0.4145, "lr": 1.6483726441997673e-05, "epoch": 3.0040485829959516, "percentage": 60.08, "elapsed_time": "4:49:41", "remaining_time": "3:12:28"} +{"current_steps": 743, "total_steps": 1235, "loss": 0.3894, "lr": 1.642806717162757e-05, "epoch": 3.0080971659919027, "percentage": 60.16, "elapsed_time": "4:50:04", "remaining_time": "3:12:04"} +{"current_steps": 744, "total_steps": 1235, "loss": 0.3944, "lr": 1.637243646233718e-05, "epoch": 3.0121457489878543, "percentage": 60.24, "elapsed_time": "4:50:27", "remaining_time": "3:11:40"} +{"current_steps": 745, "total_steps": 1235, "loss": 0.4361, "lr": 1.6316834758948174e-05, "epoch": 3.016194331983806, "percentage": 60.32, "elapsed_time": "4:50:50", "remaining_time": "3:11:17"} +{"current_steps": 746, "total_steps": 1235, "loss": 0.4121, "lr": 1.6261262506050282e-05, "epoch": 3.020242914979757, "percentage": 60.4, "elapsed_time": "4:51:13", "remaining_time": "3:10:54"} +{"current_steps": 747, "total_steps": 1235, "loss": 0.4079, "lr": 1.620572014799777e-05, "epoch": 3.0242914979757085, "percentage": 60.49, "elapsed_time": "4:51:37", "remaining_time": "3:10:30"} +{"current_steps": 748, "total_steps": 1235, "loss": 0.409, "lr": 1.6150208128905857e-05, "epoch": 3.02834008097166, "percentage": 60.57, "elapsed_time": "4:51:59", "remaining_time": "3:10:06"} +{"current_steps": 749, "total_steps": 1235, "loss": 0.3952, "lr": 1.6094726892647147e-05, "epoch": 3.032388663967611, "percentage": 60.65, "elapsed_time": "4:52:22", "remaining_time": "3:09:42"} +{"current_steps": 750, "total_steps": 1235, "loss": 0.3916, "lr": 1.6039276882848135e-05, "epoch": 3.0364372469635628, "percentage": 60.73, "elapsed_time": "4:52:45", "remaining_time": "3:09:19"} +{"current_steps": 751, "total_steps": 1235, "loss": 0.3825, "lr": 1.5983858542885635e-05, "epoch": 3.0404858299595143, "percentage": 60.81, "elapsed_time": "4:53:08", "remaining_time": "3:08:55"} +{"current_steps": 752, "total_steps": 1235, "loss": 0.4021, "lr": 1.5928472315883203e-05, "epoch": 3.0445344129554655, "percentage": 60.89, "elapsed_time": "4:53:32", "remaining_time": "3:08:32"} +{"current_steps": 753, "total_steps": 1235, "loss": 0.4034, "lr": 1.5873118644707633e-05, "epoch": 3.048582995951417, "percentage": 60.97, "elapsed_time": "4:53:55", "remaining_time": "3:08:08"} +{"current_steps": 754, "total_steps": 1235, "loss": 0.3802, "lr": 1.5817797971965413e-05, "epoch": 3.0526315789473686, "percentage": 61.05, "elapsed_time": "4:54:18", "remaining_time": "3:07:44"} +{"current_steps": 755, "total_steps": 1235, "loss": 0.3992, "lr": 1.576251073999917e-05, "epoch": 3.0566801619433197, "percentage": 61.13, "elapsed_time": "4:54:41", "remaining_time": "3:07:21"} +{"current_steps": 756, "total_steps": 1235, "loss": 0.3819, "lr": 1.5707257390884126e-05, "epoch": 3.0607287449392713, "percentage": 61.21, "elapsed_time": "4:55:04", "remaining_time": "3:06:57"} +{"current_steps": 757, "total_steps": 1235, "loss": 0.3835, "lr": 1.5652038366424595e-05, "epoch": 3.064777327935223, "percentage": 61.3, "elapsed_time": "4:55:27", "remaining_time": "3:06:34"} +{"current_steps": 758, "total_steps": 1235, "loss": 0.3882, "lr": 1.5596854108150424e-05, "epoch": 3.068825910931174, "percentage": 61.38, "elapsed_time": "4:55:50", "remaining_time": "3:06:10"} +{"current_steps": 759, "total_steps": 1235, "loss": 0.4071, "lr": 1.5541705057313476e-05, "epoch": 3.0728744939271255, "percentage": 61.46, "elapsed_time": "4:56:14", "remaining_time": "3:05:47"} +{"current_steps": 760, "total_steps": 1235, "loss": 0.4138, "lr": 1.5486591654884086e-05, "epoch": 3.076923076923077, "percentage": 61.54, "elapsed_time": "4:56:36", "remaining_time": "3:05:23"} +{"current_steps": 761, "total_steps": 1235, "loss": 0.4037, "lr": 1.543151434154755e-05, "epoch": 3.080971659919028, "percentage": 61.62, "elapsed_time": "4:56:59", "remaining_time": "3:04:59"} +{"current_steps": 762, "total_steps": 1235, "loss": 0.4006, "lr": 1.5376473557700615e-05, "epoch": 3.08502024291498, "percentage": 61.7, "elapsed_time": "4:57:22", "remaining_time": "3:04:35"} +{"current_steps": 763, "total_steps": 1235, "loss": 0.3926, "lr": 1.5321469743447893e-05, "epoch": 3.0890688259109313, "percentage": 61.78, "elapsed_time": "4:57:45", "remaining_time": "3:04:11"} +{"current_steps": 764, "total_steps": 1235, "loss": 0.4211, "lr": 1.5266503338598434e-05, "epoch": 3.0931174089068825, "percentage": 61.86, "elapsed_time": "4:58:08", "remaining_time": "3:03:48"} +{"current_steps": 765, "total_steps": 1235, "loss": 0.4107, "lr": 1.5211574782662149e-05, "epoch": 3.097165991902834, "percentage": 61.94, "elapsed_time": "4:58:31", "remaining_time": "3:03:24"} +{"current_steps": 766, "total_steps": 1235, "loss": 0.3854, "lr": 1.5156684514846307e-05, "epoch": 3.1012145748987856, "percentage": 62.02, "elapsed_time": "4:58:53", "remaining_time": "3:03:00"} +{"current_steps": 767, "total_steps": 1235, "loss": 0.4037, "lr": 1.5101832974052012e-05, "epoch": 3.1052631578947367, "percentage": 62.11, "elapsed_time": "4:59:17", "remaining_time": "3:02:37"} +{"current_steps": 768, "total_steps": 1235, "loss": 0.3925, "lr": 1.5047020598870737e-05, "epoch": 3.1093117408906883, "percentage": 62.19, "elapsed_time": "4:59:41", "remaining_time": "3:02:14"} +{"current_steps": 769, "total_steps": 1235, "loss": 0.3882, "lr": 1.4992247827580778e-05, "epoch": 3.11336032388664, "percentage": 62.27, "elapsed_time": "5:00:04", "remaining_time": "3:01:50"} +{"current_steps": 770, "total_steps": 1235, "loss": 0.4064, "lr": 1.493751509814374e-05, "epoch": 3.117408906882591, "percentage": 62.35, "elapsed_time": "5:00:27", "remaining_time": "3:01:26"} +{"current_steps": 771, "total_steps": 1235, "loss": 0.4025, "lr": 1.4882822848201073e-05, "epoch": 3.1214574898785425, "percentage": 62.43, "elapsed_time": "5:00:49", "remaining_time": "3:01:02"} +{"current_steps": 772, "total_steps": 1235, "loss": 0.4315, "lr": 1.4828171515070553e-05, "epoch": 3.125506072874494, "percentage": 62.51, "elapsed_time": "5:01:13", "remaining_time": "3:00:39"} +{"current_steps": 773, "total_steps": 1235, "loss": 0.3868, "lr": 1.4773561535742793e-05, "epoch": 3.1295546558704452, "percentage": 62.59, "elapsed_time": "5:01:36", "remaining_time": "3:00:15"} +{"current_steps": 774, "total_steps": 1235, "loss": 0.3979, "lr": 1.4718993346877715e-05, "epoch": 3.133603238866397, "percentage": 62.67, "elapsed_time": "5:01:59", "remaining_time": "2:59:52"} +{"current_steps": 775, "total_steps": 1235, "loss": 0.4104, "lr": 1.466446738480111e-05, "epoch": 3.1376518218623484, "percentage": 62.75, "elapsed_time": "5:02:21", "remaining_time": "2:59:27"} +{"current_steps": 776, "total_steps": 1235, "loss": 0.3934, "lr": 1.460998408550112e-05, "epoch": 3.1417004048582995, "percentage": 62.83, "elapsed_time": "5:02:44", "remaining_time": "2:59:04"} +{"current_steps": 777, "total_steps": 1235, "loss": 0.4024, "lr": 1.4555543884624751e-05, "epoch": 3.145748987854251, "percentage": 62.91, "elapsed_time": "5:03:07", "remaining_time": "2:58:40"} +{"current_steps": 778, "total_steps": 1235, "loss": 0.4004, "lr": 1.4501147217474402e-05, "epoch": 3.1497975708502026, "percentage": 63.0, "elapsed_time": "5:03:31", "remaining_time": "2:58:17"} +{"current_steps": 779, "total_steps": 1235, "loss": 0.4176, "lr": 1.444679451900437e-05, "epoch": 3.1538461538461537, "percentage": 63.08, "elapsed_time": "5:03:55", "remaining_time": "2:57:54"} +{"current_steps": 780, "total_steps": 1235, "loss": 0.3982, "lr": 1.4392486223817397e-05, "epoch": 3.1578947368421053, "percentage": 63.16, "elapsed_time": "5:04:17", "remaining_time": "2:57:30"} +{"current_steps": 781, "total_steps": 1235, "loss": 0.3952, "lr": 1.4338222766161143e-05, "epoch": 3.161943319838057, "percentage": 63.24, "elapsed_time": "5:04:41", "remaining_time": "2:57:07"} +{"current_steps": 782, "total_steps": 1235, "loss": 0.3992, "lr": 1.4284004579924777e-05, "epoch": 3.165991902834008, "percentage": 63.32, "elapsed_time": "5:05:05", "remaining_time": "2:56:43"} +{"current_steps": 783, "total_steps": 1235, "loss": 0.402, "lr": 1.4229832098635479e-05, "epoch": 3.1700404858299596, "percentage": 63.4, "elapsed_time": "5:05:28", "remaining_time": "2:56:20"} +{"current_steps": 784, "total_steps": 1235, "loss": 0.4207, "lr": 1.4175705755454963e-05, "epoch": 3.174089068825911, "percentage": 63.48, "elapsed_time": "5:05:52", "remaining_time": "2:55:57"} +{"current_steps": 785, "total_steps": 1235, "loss": 0.3993, "lr": 1.412162598317602e-05, "epoch": 3.1781376518218623, "percentage": 63.56, "elapsed_time": "5:06:15", "remaining_time": "2:55:33"} +{"current_steps": 786, "total_steps": 1235, "loss": 0.3799, "lr": 1.406759321421907e-05, "epoch": 3.182186234817814, "percentage": 63.64, "elapsed_time": "5:06:38", "remaining_time": "2:55:10"} +{"current_steps": 787, "total_steps": 1235, "loss": 0.3924, "lr": 1.401360788062871e-05, "epoch": 3.1862348178137654, "percentage": 63.72, "elapsed_time": "5:07:01", "remaining_time": "2:54:46"} +{"current_steps": 788, "total_steps": 1235, "loss": 0.3947, "lr": 1.3959670414070204e-05, "epoch": 3.1902834008097165, "percentage": 63.81, "elapsed_time": "5:07:24", "remaining_time": "2:54:22"} +{"current_steps": 789, "total_steps": 1235, "loss": 0.3833, "lr": 1.3905781245826108e-05, "epoch": 3.194331983805668, "percentage": 63.89, "elapsed_time": "5:07:46", "remaining_time": "2:53:58"} +{"current_steps": 790, "total_steps": 1235, "loss": 0.4058, "lr": 1.3851940806792778e-05, "epoch": 3.1983805668016196, "percentage": 63.97, "elapsed_time": "5:08:10", "remaining_time": "2:53:35"} +{"current_steps": 791, "total_steps": 1235, "loss": 0.3767, "lr": 1.379814952747693e-05, "epoch": 3.2024291497975708, "percentage": 64.05, "elapsed_time": "5:08:33", "remaining_time": "2:53:11"} +{"current_steps": 792, "total_steps": 1235, "loss": 0.4097, "lr": 1.3744407837992193e-05, "epoch": 3.2064777327935223, "percentage": 64.13, "elapsed_time": "5:08:57", "remaining_time": "2:52:48"} +{"current_steps": 793, "total_steps": 1235, "loss": 0.4014, "lr": 1.3690716168055692e-05, "epoch": 3.2105263157894735, "percentage": 64.21, "elapsed_time": "5:09:19", "remaining_time": "2:52:24"} +{"current_steps": 794, "total_steps": 1235, "loss": 0.3754, "lr": 1.363707494698459e-05, "epoch": 3.214574898785425, "percentage": 64.29, "elapsed_time": "5:09:42", "remaining_time": "2:52:00"} +{"current_steps": 795, "total_steps": 1235, "loss": 0.4053, "lr": 1.358348460369265e-05, "epoch": 3.2186234817813766, "percentage": 64.37, "elapsed_time": "5:10:04", "remaining_time": "2:51:36"} +{"current_steps": 796, "total_steps": 1235, "loss": 0.3932, "lr": 1.352994556668684e-05, "epoch": 3.2226720647773277, "percentage": 64.45, "elapsed_time": "5:10:28", "remaining_time": "2:51:13"} +{"current_steps": 797, "total_steps": 1235, "loss": 0.3993, "lr": 1.3476458264063865e-05, "epoch": 3.2267206477732793, "percentage": 64.53, "elapsed_time": "5:10:51", "remaining_time": "2:50:50"} +{"current_steps": 798, "total_steps": 1235, "loss": 0.4102, "lr": 1.342302312350678e-05, "epoch": 3.230769230769231, "percentage": 64.62, "elapsed_time": "5:11:15", "remaining_time": "2:50:27"} +{"current_steps": 799, "total_steps": 1235, "loss": 0.4061, "lr": 1.3369640572281537e-05, "epoch": 3.234817813765182, "percentage": 64.7, "elapsed_time": "5:11:38", "remaining_time": "2:50:03"} +{"current_steps": 800, "total_steps": 1235, "loss": 0.4124, "lr": 1.3316311037233596e-05, "epoch": 3.2388663967611335, "percentage": 64.78, "elapsed_time": "5:12:00", "remaining_time": "2:49:39"} +{"current_steps": 801, "total_steps": 1235, "loss": 0.4187, "lr": 1.326303494478451e-05, "epoch": 3.242914979757085, "percentage": 64.86, "elapsed_time": "5:12:23", "remaining_time": "2:49:15"} +{"current_steps": 802, "total_steps": 1235, "loss": 0.4038, "lr": 1.3209812720928472e-05, "epoch": 3.246963562753036, "percentage": 64.94, "elapsed_time": "5:12:46", "remaining_time": "2:48:52"} +{"current_steps": 803, "total_steps": 1235, "loss": 0.4036, "lr": 1.315664479122898e-05, "epoch": 3.251012145748988, "percentage": 65.02, "elapsed_time": "5:13:10", "remaining_time": "2:48:29"} +{"current_steps": 804, "total_steps": 1235, "loss": 0.3836, "lr": 1.3103531580815378e-05, "epoch": 3.2550607287449393, "percentage": 65.1, "elapsed_time": "5:13:34", "remaining_time": "2:48:05"} +{"current_steps": 805, "total_steps": 1235, "loss": 0.3911, "lr": 1.3050473514379488e-05, "epoch": 3.2591093117408905, "percentage": 65.18, "elapsed_time": "5:13:57", "remaining_time": "2:47:42"} +{"current_steps": 806, "total_steps": 1235, "loss": 0.3971, "lr": 1.2997471016172188e-05, "epoch": 3.263157894736842, "percentage": 65.26, "elapsed_time": "5:14:20", "remaining_time": "2:47:18"} +{"current_steps": 807, "total_steps": 1235, "loss": 0.3678, "lr": 1.2944524510000042e-05, "epoch": 3.2672064777327936, "percentage": 65.34, "elapsed_time": "5:14:43", "remaining_time": "2:46:54"} +{"current_steps": 808, "total_steps": 1235, "loss": 0.3799, "lr": 1.2891634419221908e-05, "epoch": 3.2712550607287447, "percentage": 65.43, "elapsed_time": "5:15:05", "remaining_time": "2:46:30"} +{"current_steps": 809, "total_steps": 1235, "loss": 0.3976, "lr": 1.2838801166745545e-05, "epoch": 3.2753036437246963, "percentage": 65.51, "elapsed_time": "5:15:27", "remaining_time": "2:46:06"} +{"current_steps": 810, "total_steps": 1235, "loss": 0.4159, "lr": 1.2786025175024216e-05, "epoch": 3.279352226720648, "percentage": 65.59, "elapsed_time": "5:15:50", "remaining_time": "2:45:43"} +{"current_steps": 811, "total_steps": 1235, "loss": 0.3765, "lr": 1.2733306866053357e-05, "epoch": 3.283400809716599, "percentage": 65.67, "elapsed_time": "5:16:13", "remaining_time": "2:45:19"} +{"current_steps": 812, "total_steps": 1235, "loss": 0.4107, "lr": 1.2680646661367163e-05, "epoch": 3.2874493927125505, "percentage": 65.75, "elapsed_time": "5:16:36", "remaining_time": "2:44:55"} +{"current_steps": 813, "total_steps": 1235, "loss": 0.3982, "lr": 1.2628044982035219e-05, "epoch": 3.291497975708502, "percentage": 65.83, "elapsed_time": "5:16:59", "remaining_time": "2:44:32"} +{"current_steps": 814, "total_steps": 1235, "loss": 0.3932, "lr": 1.2575502248659155e-05, "epoch": 3.2955465587044532, "percentage": 65.91, "elapsed_time": "5:17:22", "remaining_time": "2:44:08"} +{"current_steps": 815, "total_steps": 1235, "loss": 0.4075, "lr": 1.2523018881369269e-05, "epoch": 3.299595141700405, "percentage": 65.99, "elapsed_time": "5:17:44", "remaining_time": "2:43:44"} +{"current_steps": 816, "total_steps": 1235, "loss": 0.4075, "lr": 1.2470595299821176e-05, "epoch": 3.3036437246963564, "percentage": 66.07, "elapsed_time": "5:18:06", "remaining_time": "2:43:20"} +{"current_steps": 817, "total_steps": 1235, "loss": 0.374, "lr": 1.2418231923192416e-05, "epoch": 3.3076923076923075, "percentage": 66.15, "elapsed_time": "5:18:29", "remaining_time": "2:42:56"} +{"current_steps": 818, "total_steps": 1235, "loss": 0.4074, "lr": 1.2365929170179165e-05, "epoch": 3.311740890688259, "percentage": 66.23, "elapsed_time": "5:18:52", "remaining_time": "2:42:33"} +{"current_steps": 819, "total_steps": 1235, "loss": 0.3898, "lr": 1.2313687458992848e-05, "epoch": 3.3157894736842106, "percentage": 66.32, "elapsed_time": "5:19:15", "remaining_time": "2:42:09"} +{"current_steps": 820, "total_steps": 1235, "loss": 0.4019, "lr": 1.2261507207356785e-05, "epoch": 3.3198380566801617, "percentage": 66.4, "elapsed_time": "5:19:38", "remaining_time": "2:41:46"} +{"current_steps": 821, "total_steps": 1235, "loss": 0.4107, "lr": 1.220938883250288e-05, "epoch": 3.3238866396761133, "percentage": 66.48, "elapsed_time": "5:20:01", "remaining_time": "2:41:22"} +{"current_steps": 822, "total_steps": 1235, "loss": 0.4021, "lr": 1.215733275116827e-05, "epoch": 3.327935222672065, "percentage": 66.56, "elapsed_time": "5:20:24", "remaining_time": "2:40:59"} +{"current_steps": 823, "total_steps": 1235, "loss": 0.4037, "lr": 1.2105339379592005e-05, "epoch": 3.331983805668016, "percentage": 66.64, "elapsed_time": "5:20:47", "remaining_time": "2:40:35"} +{"current_steps": 824, "total_steps": 1235, "loss": 0.3831, "lr": 1.2053409133511681e-05, "epoch": 3.3360323886639676, "percentage": 66.72, "elapsed_time": "5:21:10", "remaining_time": "2:40:11"} +{"current_steps": 825, "total_steps": 1235, "loss": 0.412, "lr": 1.2001542428160173e-05, "epoch": 3.340080971659919, "percentage": 66.8, "elapsed_time": "5:21:34", "remaining_time": "2:39:48"} +{"current_steps": 826, "total_steps": 1235, "loss": 0.3993, "lr": 1.1949739678262278e-05, "epoch": 3.3441295546558703, "percentage": 66.88, "elapsed_time": "5:21:57", "remaining_time": "2:39:25"} +{"current_steps": 827, "total_steps": 1235, "loss": 0.4167, "lr": 1.189800129803139e-05, "epoch": 3.348178137651822, "percentage": 66.96, "elapsed_time": "5:22:21", "remaining_time": "2:39:01"} +{"current_steps": 828, "total_steps": 1235, "loss": 0.3948, "lr": 1.1846327701166228e-05, "epoch": 3.3522267206477734, "percentage": 67.04, "elapsed_time": "5:22:43", "remaining_time": "2:38:38"} +{"current_steps": 829, "total_steps": 1235, "loss": 0.3961, "lr": 1.1794719300847493e-05, "epoch": 3.3562753036437245, "percentage": 67.13, "elapsed_time": "5:23:06", "remaining_time": "2:38:14"} +{"current_steps": 830, "total_steps": 1235, "loss": 0.4062, "lr": 1.1743176509734582e-05, "epoch": 3.360323886639676, "percentage": 67.21, "elapsed_time": "5:23:30", "remaining_time": "2:37:51"} +{"current_steps": 831, "total_steps": 1235, "loss": 0.41, "lr": 1.1691699739962275e-05, "epoch": 3.3643724696356276, "percentage": 67.29, "elapsed_time": "5:23:54", "remaining_time": "2:37:28"} +{"current_steps": 832, "total_steps": 1235, "loss": 0.3984, "lr": 1.1640289403137456e-05, "epoch": 3.3684210526315788, "percentage": 67.37, "elapsed_time": "5:24:16", "remaining_time": "2:37:04"} +{"current_steps": 833, "total_steps": 1235, "loss": 0.4019, "lr": 1.1588945910335802e-05, "epoch": 3.3724696356275303, "percentage": 67.45, "elapsed_time": "5:24:39", "remaining_time": "2:36:40"} +{"current_steps": 834, "total_steps": 1235, "loss": 0.3922, "lr": 1.1537669672098517e-05, "epoch": 3.376518218623482, "percentage": 67.53, "elapsed_time": "5:25:03", "remaining_time": "2:36:17"} +{"current_steps": 835, "total_steps": 1235, "loss": 0.4198, "lr": 1.1486461098429036e-05, "epoch": 3.380566801619433, "percentage": 67.61, "elapsed_time": "5:25:26", "remaining_time": "2:35:53"} +{"current_steps": 836, "total_steps": 1235, "loss": 0.4096, "lr": 1.1435320598789747e-05, "epoch": 3.3846153846153846, "percentage": 67.69, "elapsed_time": "5:25:50", "remaining_time": "2:35:30"} +{"current_steps": 837, "total_steps": 1235, "loss": 0.403, "lr": 1.1384248582098736e-05, "epoch": 3.388663967611336, "percentage": 67.77, "elapsed_time": "5:26:14", "remaining_time": "2:35:07"} +{"current_steps": 838, "total_steps": 1235, "loss": 0.4015, "lr": 1.1333245456726467e-05, "epoch": 3.3927125506072873, "percentage": 67.85, "elapsed_time": "5:26:37", "remaining_time": "2:34:44"} +{"current_steps": 839, "total_steps": 1235, "loss": 0.3957, "lr": 1.128231163049258e-05, "epoch": 3.396761133603239, "percentage": 67.94, "elapsed_time": "5:27:00", "remaining_time": "2:34:20"} +{"current_steps": 840, "total_steps": 1235, "loss": 0.4027, "lr": 1.123144751066259e-05, "epoch": 3.4008097165991904, "percentage": 68.02, "elapsed_time": "5:27:23", "remaining_time": "2:33:57"} +{"current_steps": 841, "total_steps": 1235, "loss": 0.3793, "lr": 1.1180653503944657e-05, "epoch": 3.4048582995951415, "percentage": 68.1, "elapsed_time": "5:27:46", "remaining_time": "2:33:33"} +{"current_steps": 842, "total_steps": 1235, "loss": 0.397, "lr": 1.1129930016486287e-05, "epoch": 3.408906882591093, "percentage": 68.18, "elapsed_time": "5:28:08", "remaining_time": "2:33:09"} +{"current_steps": 843, "total_steps": 1235, "loss": 0.4009, "lr": 1.107927745387114e-05, "epoch": 3.4129554655870447, "percentage": 68.26, "elapsed_time": "5:28:31", "remaining_time": "2:32:46"} +{"current_steps": 844, "total_steps": 1235, "loss": 0.3693, "lr": 1.1028696221115766e-05, "epoch": 3.417004048582996, "percentage": 68.34, "elapsed_time": "5:28:53", "remaining_time": "2:32:22"} +{"current_steps": 845, "total_steps": 1235, "loss": 0.397, "lr": 1.0978186722666341e-05, "epoch": 3.4210526315789473, "percentage": 68.42, "elapsed_time": "5:29:17", "remaining_time": "2:31:58"} +{"current_steps": 846, "total_steps": 1235, "loss": 0.4073, "lr": 1.0927749362395475e-05, "epoch": 3.425101214574899, "percentage": 68.5, "elapsed_time": "5:29:39", "remaining_time": "2:31:34"} +{"current_steps": 847, "total_steps": 1235, "loss": 0.4185, "lr": 1.0877384543598954e-05, "epoch": 3.42914979757085, "percentage": 68.58, "elapsed_time": "5:30:02", "remaining_time": "2:31:11"} +{"current_steps": 848, "total_steps": 1235, "loss": 0.414, "lr": 1.0827092668992529e-05, "epoch": 3.4331983805668016, "percentage": 68.66, "elapsed_time": "5:30:25", "remaining_time": "2:30:47"} +{"current_steps": 849, "total_steps": 1235, "loss": 0.3893, "lr": 1.077687414070869e-05, "epoch": 3.437246963562753, "percentage": 68.74, "elapsed_time": "5:30:45", "remaining_time": "2:30:22"} +{"current_steps": 850, "total_steps": 1235, "loss": 0.3827, "lr": 1.0726729360293451e-05, "epoch": 3.4412955465587043, "percentage": 68.83, "elapsed_time": "5:31:08", "remaining_time": "2:29:59"} +{"current_steps": 851, "total_steps": 1235, "loss": 0.4035, "lr": 1.0676658728703147e-05, "epoch": 3.445344129554656, "percentage": 68.91, "elapsed_time": "5:31:32", "remaining_time": "2:29:36"} +{"current_steps": 852, "total_steps": 1235, "loss": 0.3918, "lr": 1.0626662646301198e-05, "epoch": 3.4493927125506074, "percentage": 68.99, "elapsed_time": "5:31:55", "remaining_time": "2:29:12"} +{"current_steps": 853, "total_steps": 1235, "loss": 0.4099, "lr": 1.0576741512854958e-05, "epoch": 3.4534412955465585, "percentage": 69.07, "elapsed_time": "5:32:18", "remaining_time": "2:28:49"} +{"current_steps": 854, "total_steps": 1235, "loss": 0.4111, "lr": 1.052689572753247e-05, "epoch": 3.45748987854251, "percentage": 69.15, "elapsed_time": "5:32:42", "remaining_time": "2:28:25"} +{"current_steps": 855, "total_steps": 1235, "loss": 0.3946, "lr": 1.0477125688899328e-05, "epoch": 3.4615384615384617, "percentage": 69.23, "elapsed_time": "5:33:06", "remaining_time": "2:28:02"} +{"current_steps": 856, "total_steps": 1235, "loss": 0.4205, "lr": 1.0427431794915406e-05, "epoch": 3.465587044534413, "percentage": 69.31, "elapsed_time": "5:33:28", "remaining_time": "2:27:38"} +{"current_steps": 857, "total_steps": 1235, "loss": 0.4037, "lr": 1.0377814442931769e-05, "epoch": 3.4696356275303644, "percentage": 69.39, "elapsed_time": "5:33:51", "remaining_time": "2:27:15"} +{"current_steps": 858, "total_steps": 1235, "loss": 0.3926, "lr": 1.0328274029687439e-05, "epoch": 3.473684210526316, "percentage": 69.47, "elapsed_time": "5:34:14", "remaining_time": "2:26:51"} +{"current_steps": 859, "total_steps": 1235, "loss": 0.3938, "lr": 1.0278810951306253e-05, "epoch": 3.477732793522267, "percentage": 69.55, "elapsed_time": "5:34:36", "remaining_time": "2:26:27"} +{"current_steps": 860, "total_steps": 1235, "loss": 0.399, "lr": 1.0229425603293647e-05, "epoch": 3.4817813765182186, "percentage": 69.64, "elapsed_time": "5:34:59", "remaining_time": "2:26:04"} +{"current_steps": 861, "total_steps": 1235, "loss": 0.3991, "lr": 1.0180118380533558e-05, "epoch": 3.48582995951417, "percentage": 69.72, "elapsed_time": "5:35:21", "remaining_time": "2:25:40"} +{"current_steps": 862, "total_steps": 1235, "loss": 0.4139, "lr": 1.0130889677285225e-05, "epoch": 3.4898785425101213, "percentage": 69.8, "elapsed_time": "5:35:44", "remaining_time": "2:25:17"} +{"current_steps": 863, "total_steps": 1235, "loss": 0.39, "lr": 1.008173988718005e-05, "epoch": 3.493927125506073, "percentage": 69.88, "elapsed_time": "5:36:06", "remaining_time": "2:24:53"} +{"current_steps": 864, "total_steps": 1235, "loss": 0.4028, "lr": 1.0032669403218439e-05, "epoch": 3.4979757085020244, "percentage": 69.96, "elapsed_time": "5:36:30", "remaining_time": "2:24:29"} +{"current_steps": 865, "total_steps": 1235, "loss": 0.3973, "lr": 9.983678617766677e-06, "epoch": 3.5020242914979756, "percentage": 70.04, "elapsed_time": "5:36:52", "remaining_time": "2:24:05"} +{"current_steps": 866, "total_steps": 1235, "loss": 0.3919, "lr": 9.934767922553788e-06, "epoch": 3.506072874493927, "percentage": 70.12, "elapsed_time": "5:37:15", "remaining_time": "2:23:42"} +{"current_steps": 867, "total_steps": 1235, "loss": 0.3756, "lr": 9.885937708668371e-06, "epoch": 3.5101214574898787, "percentage": 70.2, "elapsed_time": "5:37:39", "remaining_time": "2:23:19"} +{"current_steps": 868, "total_steps": 1235, "loss": 0.3939, "lr": 9.837188366555524e-06, "epoch": 3.51417004048583, "percentage": 70.28, "elapsed_time": "5:38:02", "remaining_time": "2:22:55"} +{"current_steps": 869, "total_steps": 1235, "loss": 0.3843, "lr": 9.788520286013691e-06, "epoch": 3.5182186234817814, "percentage": 70.36, "elapsed_time": "5:38:24", "remaining_time": "2:22:31"} +{"current_steps": 870, "total_steps": 1235, "loss": 0.3877, "lr": 9.739933856191537e-06, "epoch": 3.522267206477733, "percentage": 70.45, "elapsed_time": "5:38:48", "remaining_time": "2:22:08"} +{"current_steps": 871, "total_steps": 1235, "loss": 0.4062, "lr": 9.691429465584866e-06, "epoch": 3.526315789473684, "percentage": 70.53, "elapsed_time": "5:39:11", "remaining_time": "2:21:45"} +{"current_steps": 872, "total_steps": 1235, "loss": 0.3972, "lr": 9.643007502033492e-06, "epoch": 3.5303643724696356, "percentage": 70.61, "elapsed_time": "5:39:34", "remaining_time": "2:21:21"} +{"current_steps": 873, "total_steps": 1235, "loss": 0.4287, "lr": 9.594668352718152e-06, "epoch": 3.534412955465587, "percentage": 70.69, "elapsed_time": "5:39:57", "remaining_time": "2:20:58"} +{"current_steps": 874, "total_steps": 1235, "loss": 0.3883, "lr": 9.546412404157383e-06, "epoch": 3.5384615384615383, "percentage": 70.77, "elapsed_time": "5:40:20", "remaining_time": "2:20:34"} +{"current_steps": 875, "total_steps": 1235, "loss": 0.4031, "lr": 9.498240042204471e-06, "epoch": 3.54251012145749, "percentage": 70.85, "elapsed_time": "5:40:43", "remaining_time": "2:20:11"} +{"current_steps": 876, "total_steps": 1235, "loss": 0.4046, "lr": 9.450151652044339e-06, "epoch": 3.5465587044534415, "percentage": 70.93, "elapsed_time": "5:41:06", "remaining_time": "2:19:47"} +{"current_steps": 877, "total_steps": 1235, "loss": 0.4092, "lr": 9.402147618190472e-06, "epoch": 3.5506072874493926, "percentage": 71.01, "elapsed_time": "5:41:29", "remaining_time": "2:19:24"} +{"current_steps": 878, "total_steps": 1235, "loss": 0.4164, "lr": 9.354228324481841e-06, "epoch": 3.554655870445344, "percentage": 71.09, "elapsed_time": "5:41:52", "remaining_time": "2:19:00"} +{"current_steps": 879, "total_steps": 1235, "loss": 0.3979, "lr": 9.306394154079852e-06, "epoch": 3.5587044534412957, "percentage": 71.17, "elapsed_time": "5:42:16", "remaining_time": "2:18:37"} +{"current_steps": 880, "total_steps": 1235, "loss": 0.4112, "lr": 9.258645489465254e-06, "epoch": 3.562753036437247, "percentage": 71.26, "elapsed_time": "5:42:38", "remaining_time": "2:18:13"} +{"current_steps": 881, "total_steps": 1235, "loss": 0.3858, "lr": 9.21098271243509e-06, "epoch": 3.5668016194331984, "percentage": 71.34, "elapsed_time": "5:43:01", "remaining_time": "2:17:49"} +{"current_steps": 882, "total_steps": 1235, "loss": 0.3978, "lr": 9.163406204099659e-06, "epoch": 3.57085020242915, "percentage": 71.42, "elapsed_time": "5:43:23", "remaining_time": "2:17:26"} +{"current_steps": 883, "total_steps": 1235, "loss": 0.3915, "lr": 9.115916344879452e-06, "epoch": 3.574898785425101, "percentage": 71.5, "elapsed_time": "5:43:45", "remaining_time": "2:17:02"} +{"current_steps": 884, "total_steps": 1235, "loss": 0.4132, "lr": 9.068513514502126e-06, "epoch": 3.5789473684210527, "percentage": 71.58, "elapsed_time": "5:44:08", "remaining_time": "2:16:38"} +{"current_steps": 885, "total_steps": 1235, "loss": 0.4039, "lr": 9.021198091999439e-06, "epoch": 3.582995951417004, "percentage": 71.66, "elapsed_time": "5:44:30", "remaining_time": "2:16:14"} +{"current_steps": 886, "total_steps": 1235, "loss": 0.3799, "lr": 8.973970455704251e-06, "epoch": 3.5870445344129553, "percentage": 71.74, "elapsed_time": "5:44:53", "remaining_time": "2:15:51"} +{"current_steps": 887, "total_steps": 1235, "loss": 0.3963, "lr": 8.926830983247495e-06, "epoch": 3.591093117408907, "percentage": 71.82, "elapsed_time": "5:45:16", "remaining_time": "2:15:27"} +{"current_steps": 888, "total_steps": 1235, "loss": 0.4025, "lr": 8.879780051555116e-06, "epoch": 3.5951417004048585, "percentage": 71.9, "elapsed_time": "5:45:39", "remaining_time": "2:15:04"} +{"current_steps": 889, "total_steps": 1235, "loss": 0.3938, "lr": 8.83281803684512e-06, "epoch": 3.5991902834008096, "percentage": 71.98, "elapsed_time": "5:46:02", "remaining_time": "2:14:40"} +{"current_steps": 890, "total_steps": 1235, "loss": 0.403, "lr": 8.785945314624532e-06, "epoch": 3.603238866396761, "percentage": 72.06, "elapsed_time": "5:46:26", "remaining_time": "2:14:17"} +{"current_steps": 891, "total_steps": 1235, "loss": 0.3839, "lr": 8.739162259686385e-06, "epoch": 3.6072874493927127, "percentage": 72.15, "elapsed_time": "5:46:49", "remaining_time": "2:13:54"} +{"current_steps": 892, "total_steps": 1235, "loss": 0.4109, "lr": 8.692469246106734e-06, "epoch": 3.611336032388664, "percentage": 72.23, "elapsed_time": "5:47:11", "remaining_time": "2:13:30"} +{"current_steps": 893, "total_steps": 1235, "loss": 0.4004, "lr": 8.645866647241677e-06, "epoch": 3.6153846153846154, "percentage": 72.31, "elapsed_time": "5:47:35", "remaining_time": "2:13:07"} +{"current_steps": 894, "total_steps": 1235, "loss": 0.3782, "lr": 8.599354835724348e-06, "epoch": 3.619433198380567, "percentage": 72.39, "elapsed_time": "5:47:57", "remaining_time": "2:12:43"} +{"current_steps": 895, "total_steps": 1235, "loss": 0.4162, "lr": 8.552934183461958e-06, "epoch": 3.623481781376518, "percentage": 72.47, "elapsed_time": "5:48:20", "remaining_time": "2:12:19"} +{"current_steps": 896, "total_steps": 1235, "loss": 0.4129, "lr": 8.506605061632805e-06, "epoch": 3.6275303643724697, "percentage": 72.55, "elapsed_time": "5:48:43", "remaining_time": "2:11:56"} +{"current_steps": 897, "total_steps": 1235, "loss": 0.4011, "lr": 8.460367840683308e-06, "epoch": 3.6315789473684212, "percentage": 72.63, "elapsed_time": "5:49:06", "remaining_time": "2:11:32"} +{"current_steps": 898, "total_steps": 1235, "loss": 0.421, "lr": 8.414222890325065e-06, "epoch": 3.6356275303643724, "percentage": 72.71, "elapsed_time": "5:49:29", "remaining_time": "2:11:09"} +{"current_steps": 899, "total_steps": 1235, "loss": 0.4003, "lr": 8.368170579531855e-06, "epoch": 3.639676113360324, "percentage": 72.79, "elapsed_time": "5:49:52", "remaining_time": "2:10:45"} +{"current_steps": 900, "total_steps": 1235, "loss": 0.3927, "lr": 8.322211276536733e-06, "epoch": 3.6437246963562755, "percentage": 72.87, "elapsed_time": "5:50:15", "remaining_time": "2:10:22"} +{"current_steps": 901, "total_steps": 1235, "loss": 0.3905, "lr": 8.27634534882907e-06, "epoch": 3.6477732793522266, "percentage": 72.96, "elapsed_time": "5:50:39", "remaining_time": "2:09:59"} +{"current_steps": 902, "total_steps": 1235, "loss": 0.3978, "lr": 8.230573163151585e-06, "epoch": 3.651821862348178, "percentage": 73.04, "elapsed_time": "5:51:02", "remaining_time": "2:09:35"} +{"current_steps": 903, "total_steps": 1235, "loss": 0.4108, "lr": 8.184895085497466e-06, "epoch": 3.6558704453441297, "percentage": 73.12, "elapsed_time": "5:51:25", "remaining_time": "2:09:12"} +{"current_steps": 904, "total_steps": 1235, "loss": 0.3974, "lr": 8.139311481107401e-06, "epoch": 3.659919028340081, "percentage": 73.2, "elapsed_time": "5:51:48", "remaining_time": "2:08:48"} +{"current_steps": 905, "total_steps": 1235, "loss": 0.4153, "lr": 8.093822714466686e-06, "epoch": 3.6639676113360324, "percentage": 73.28, "elapsed_time": "5:52:12", "remaining_time": "2:08:25"} +{"current_steps": 906, "total_steps": 1235, "loss": 0.4007, "lr": 8.048429149302271e-06, "epoch": 3.668016194331984, "percentage": 73.36, "elapsed_time": "5:52:33", "remaining_time": "2:08:01"} +{"current_steps": 907, "total_steps": 1235, "loss": 0.4388, "lr": 8.003131148579902e-06, "epoch": 3.672064777327935, "percentage": 73.44, "elapsed_time": "5:52:57", "remaining_time": "2:07:38"} +{"current_steps": 908, "total_steps": 1235, "loss": 0.3878, "lr": 7.957929074501182e-06, "epoch": 3.6761133603238867, "percentage": 73.52, "elapsed_time": "5:53:19", "remaining_time": "2:07:14"} +{"current_steps": 909, "total_steps": 1235, "loss": 0.398, "lr": 7.912823288500695e-06, "epoch": 3.6801619433198383, "percentage": 73.6, "elapsed_time": "5:53:42", "remaining_time": "2:06:51"} +{"current_steps": 910, "total_steps": 1235, "loss": 0.3911, "lr": 7.867814151243102e-06, "epoch": 3.6842105263157894, "percentage": 73.68, "elapsed_time": "5:54:04", "remaining_time": "2:06:27"} +{"current_steps": 911, "total_steps": 1235, "loss": 0.4054, "lr": 7.822902022620267e-06, "epoch": 3.688259109311741, "percentage": 73.77, "elapsed_time": "5:54:27", "remaining_time": "2:06:03"} +{"current_steps": 912, "total_steps": 1235, "loss": 0.4013, "lr": 7.778087261748377e-06, "epoch": 3.6923076923076925, "percentage": 73.85, "elapsed_time": "5:54:50", "remaining_time": "2:05:40"} +{"current_steps": 913, "total_steps": 1235, "loss": 0.3852, "lr": 7.733370226965056e-06, "epoch": 3.6963562753036436, "percentage": 73.93, "elapsed_time": "5:55:14", "remaining_time": "2:05:17"} +{"current_steps": 914, "total_steps": 1235, "loss": 0.4235, "lr": 7.688751275826527e-06, "epoch": 3.700404858299595, "percentage": 74.01, "elapsed_time": "5:55:36", "remaining_time": "2:04:53"} +{"current_steps": 915, "total_steps": 1235, "loss": 0.3952, "lr": 7.644230765104735e-06, "epoch": 3.7044534412955468, "percentage": 74.09, "elapsed_time": "5:56:00", "remaining_time": "2:04:30"} +{"current_steps": 916, "total_steps": 1235, "loss": 0.3686, "lr": 7.599809050784502e-06, "epoch": 3.708502024291498, "percentage": 74.17, "elapsed_time": "5:56:22", "remaining_time": "2:04:06"} +{"current_steps": 917, "total_steps": 1235, "loss": 0.3891, "lr": 7.555486488060661e-06, "epoch": 3.7125506072874495, "percentage": 74.25, "elapsed_time": "5:56:46", "remaining_time": "2:03:43"} +{"current_steps": 918, "total_steps": 1235, "loss": 0.3934, "lr": 7.511263431335249e-06, "epoch": 3.716599190283401, "percentage": 74.33, "elapsed_time": "5:57:09", "remaining_time": "2:03:20"} +{"current_steps": 919, "total_steps": 1235, "loss": 0.3993, "lr": 7.467140234214656e-06, "epoch": 3.720647773279352, "percentage": 74.41, "elapsed_time": "5:57:33", "remaining_time": "2:02:56"} +{"current_steps": 920, "total_steps": 1235, "loss": 0.405, "lr": 7.423117249506777e-06, "epoch": 3.7246963562753037, "percentage": 74.49, "elapsed_time": "5:57:56", "remaining_time": "2:02:33"} +{"current_steps": 921, "total_steps": 1235, "loss": 0.4003, "lr": 7.379194829218231e-06, "epoch": 3.7287449392712553, "percentage": 74.57, "elapsed_time": "5:58:19", "remaining_time": "2:02:09"} +{"current_steps": 922, "total_steps": 1235, "loss": 0.4023, "lr": 7.335373324551518e-06, "epoch": 3.7327935222672064, "percentage": 74.66, "elapsed_time": "5:58:42", "remaining_time": "2:01:46"} +{"current_steps": 923, "total_steps": 1235, "loss": 0.3999, "lr": 7.291653085902224e-06, "epoch": 3.736842105263158, "percentage": 74.74, "elapsed_time": "5:59:05", "remaining_time": "2:01:23"} +{"current_steps": 924, "total_steps": 1235, "loss": 0.397, "lr": 7.248034462856213e-06, "epoch": 3.7408906882591095, "percentage": 74.82, "elapsed_time": "5:59:28", "remaining_time": "2:00:59"} +{"current_steps": 925, "total_steps": 1235, "loss": 0.3836, "lr": 7.20451780418683e-06, "epoch": 3.7449392712550607, "percentage": 74.9, "elapsed_time": "5:59:52", "remaining_time": "2:00:36"} +{"current_steps": 926, "total_steps": 1235, "loss": 0.4147, "lr": 7.161103457852128e-06, "epoch": 3.748987854251012, "percentage": 74.98, "elapsed_time": "6:00:14", "remaining_time": "2:00:12"} +{"current_steps": 927, "total_steps": 1235, "loss": 0.4041, "lr": 7.117791770992046e-06, "epoch": 3.753036437246964, "percentage": 75.06, "elapsed_time": "6:00:38", "remaining_time": "1:59:49"} +{"current_steps": 928, "total_steps": 1235, "loss": 0.4059, "lr": 7.074583089925688e-06, "epoch": 3.757085020242915, "percentage": 75.14, "elapsed_time": "6:01:02", "remaining_time": "1:59:26"} +{"current_steps": 929, "total_steps": 1235, "loss": 0.3856, "lr": 7.0314777601485155e-06, "epoch": 3.7611336032388665, "percentage": 75.22, "elapsed_time": "6:01:25", "remaining_time": "1:59:02"} +{"current_steps": 930, "total_steps": 1235, "loss": 0.3942, "lr": 6.988476126329604e-06, "epoch": 3.765182186234818, "percentage": 75.3, "elapsed_time": "6:01:48", "remaining_time": "1:58:39"} +{"current_steps": 931, "total_steps": 1235, "loss": 0.383, "lr": 6.945578532308857e-06, "epoch": 3.769230769230769, "percentage": 75.38, "elapsed_time": "6:02:11", "remaining_time": "1:58:15"} +{"current_steps": 932, "total_steps": 1235, "loss": 0.4194, "lr": 6.902785321094301e-06, "epoch": 3.7732793522267207, "percentage": 75.47, "elapsed_time": "6:02:33", "remaining_time": "1:57:52"} +{"current_steps": 933, "total_steps": 1235, "loss": 0.4156, "lr": 6.8600968348593115e-06, "epoch": 3.7773279352226723, "percentage": 75.55, "elapsed_time": "6:02:57", "remaining_time": "1:57:29"} +{"current_steps": 934, "total_steps": 1235, "loss": 0.3837, "lr": 6.817513414939892e-06, "epoch": 3.7813765182186234, "percentage": 75.63, "elapsed_time": "6:03:21", "remaining_time": "1:57:05"} +{"current_steps": 935, "total_steps": 1235, "loss": 0.3952, "lr": 6.775035401831924e-06, "epoch": 3.785425101214575, "percentage": 75.71, "elapsed_time": "6:03:44", "remaining_time": "1:56:42"} +{"current_steps": 936, "total_steps": 1235, "loss": 0.4004, "lr": 6.732663135188473e-06, "epoch": 3.7894736842105265, "percentage": 75.79, "elapsed_time": "6:04:06", "remaining_time": "1:56:18"} +{"current_steps": 937, "total_steps": 1235, "loss": 0.3757, "lr": 6.690396953817055e-06, "epoch": 3.7935222672064777, "percentage": 75.87, "elapsed_time": "6:04:28", "remaining_time": "1:55:54"} +{"current_steps": 938, "total_steps": 1235, "loss": 0.4105, "lr": 6.648237195676927e-06, "epoch": 3.7975708502024292, "percentage": 75.95, "elapsed_time": "6:04:51", "remaining_time": "1:55:31"} +{"current_steps": 939, "total_steps": 1235, "loss": 0.3982, "lr": 6.606184197876395e-06, "epoch": 3.801619433198381, "percentage": 76.03, "elapsed_time": "6:05:14", "remaining_time": "1:55:08"} +{"current_steps": 940, "total_steps": 1235, "loss": 0.4053, "lr": 6.564238296670109e-06, "epoch": 3.805668016194332, "percentage": 76.11, "elapsed_time": "6:05:37", "remaining_time": "1:54:44"} +{"current_steps": 941, "total_steps": 1235, "loss": 0.3795, "lr": 6.52239982745638e-06, "epoch": 3.8097165991902835, "percentage": 76.19, "elapsed_time": "6:06:01", "remaining_time": "1:54:21"} +{"current_steps": 942, "total_steps": 1235, "loss": 0.4261, "lr": 6.480669124774484e-06, "epoch": 3.813765182186235, "percentage": 76.28, "elapsed_time": "6:06:23", "remaining_time": "1:53:57"} +{"current_steps": 943, "total_steps": 1235, "loss": 0.3982, "lr": 6.439046522302013e-06, "epoch": 3.817813765182186, "percentage": 76.36, "elapsed_time": "6:06:47", "remaining_time": "1:53:34"} +{"current_steps": 944, "total_steps": 1235, "loss": 0.3849, "lr": 6.397532352852191e-06, "epoch": 3.8218623481781377, "percentage": 76.44, "elapsed_time": "6:07:10", "remaining_time": "1:53:11"} +{"current_steps": 945, "total_steps": 1235, "loss": 0.3915, "lr": 6.356126948371202e-06, "epoch": 3.8259109311740893, "percentage": 76.52, "elapsed_time": "6:07:32", "remaining_time": "1:52:47"} +{"current_steps": 946, "total_steps": 1235, "loss": 0.3829, "lr": 6.314830639935559e-06, "epoch": 3.8299595141700404, "percentage": 76.6, "elapsed_time": "6:07:55", "remaining_time": "1:52:24"} +{"current_steps": 947, "total_steps": 1235, "loss": 0.4, "lr": 6.273643757749448e-06, "epoch": 3.834008097165992, "percentage": 76.68, "elapsed_time": "6:08:18", "remaining_time": "1:52:00"} +{"current_steps": 948, "total_steps": 1235, "loss": 0.4108, "lr": 6.2325666311420856e-06, "epoch": 3.8380566801619436, "percentage": 76.76, "elapsed_time": "6:08:42", "remaining_time": "1:51:37"} +{"current_steps": 949, "total_steps": 1235, "loss": 0.4187, "lr": 6.1915995885650675e-06, "epoch": 3.8421052631578947, "percentage": 76.84, "elapsed_time": "6:09:06", "remaining_time": "1:51:14"} +{"current_steps": 950, "total_steps": 1235, "loss": 0.3939, "lr": 6.150742957589784e-06, "epoch": 3.8461538461538463, "percentage": 76.92, "elapsed_time": "6:09:28", "remaining_time": "1:50:50"} +{"current_steps": 951, "total_steps": 1235, "loss": 0.3945, "lr": 6.109997064904774e-06, "epoch": 3.850202429149798, "percentage": 77.0, "elapsed_time": "6:09:51", "remaining_time": "1:50:27"} +{"current_steps": 952, "total_steps": 1235, "loss": 0.3969, "lr": 6.069362236313092e-06, "epoch": 3.854251012145749, "percentage": 77.09, "elapsed_time": "6:10:15", "remaining_time": "1:50:03"} +{"current_steps": 953, "total_steps": 1235, "loss": 0.3967, "lr": 6.0288387967297565e-06, "epoch": 3.8582995951417005, "percentage": 77.17, "elapsed_time": "6:10:38", "remaining_time": "1:49:40"} +{"current_steps": 954, "total_steps": 1235, "loss": 0.3933, "lr": 5.988427070179108e-06, "epoch": 3.862348178137652, "percentage": 77.25, "elapsed_time": "6:11:01", "remaining_time": "1:49:17"} +{"current_steps": 955, "total_steps": 1235, "loss": 0.3855, "lr": 5.948127379792234e-06, "epoch": 3.866396761133603, "percentage": 77.33, "elapsed_time": "6:11:24", "remaining_time": "1:48:53"} +{"current_steps": 956, "total_steps": 1235, "loss": 0.428, "lr": 5.90794004780439e-06, "epoch": 3.8704453441295548, "percentage": 77.41, "elapsed_time": "6:11:47", "remaining_time": "1:48:30"} +{"current_steps": 957, "total_steps": 1235, "loss": 0.4099, "lr": 5.867865395552405e-06, "epoch": 3.8744939271255063, "percentage": 77.49, "elapsed_time": "6:12:10", "remaining_time": "1:48:06"} +{"current_steps": 958, "total_steps": 1235, "loss": 0.4091, "lr": 5.8279037434721364e-06, "epoch": 3.8785425101214575, "percentage": 77.57, "elapsed_time": "6:12:31", "remaining_time": "1:47:42"} +{"current_steps": 959, "total_steps": 1235, "loss": 0.3972, "lr": 5.788055411095892e-06, "epoch": 3.882591093117409, "percentage": 77.65, "elapsed_time": "6:12:54", "remaining_time": "1:47:19"} +{"current_steps": 960, "total_steps": 1235, "loss": 0.3765, "lr": 5.7483207170498625e-06, "epoch": 3.8866396761133606, "percentage": 77.73, "elapsed_time": "6:13:17", "remaining_time": "1:46:56"} +{"current_steps": 961, "total_steps": 1235, "loss": 0.393, "lr": 5.708699979051613e-06, "epoch": 3.8906882591093117, "percentage": 77.81, "elapsed_time": "6:13:40", "remaining_time": "1:46:32"} +{"current_steps": 962, "total_steps": 1235, "loss": 0.3911, "lr": 5.66919351390751e-06, "epoch": 3.8947368421052633, "percentage": 77.89, "elapsed_time": "6:14:03", "remaining_time": "1:46:09"} +{"current_steps": 963, "total_steps": 1235, "loss": 0.3941, "lr": 5.629801637510188e-06, "epoch": 3.898785425101215, "percentage": 77.98, "elapsed_time": "6:14:26", "remaining_time": "1:45:45"} +{"current_steps": 964, "total_steps": 1235, "loss": 0.3802, "lr": 5.590524664836043e-06, "epoch": 3.902834008097166, "percentage": 78.06, "elapsed_time": "6:14:48", "remaining_time": "1:45:22"} +{"current_steps": 965, "total_steps": 1235, "loss": 0.4009, "lr": 5.551362909942708e-06, "epoch": 3.9068825910931175, "percentage": 78.14, "elapsed_time": "6:15:11", "remaining_time": "1:44:58"} +{"current_steps": 966, "total_steps": 1235, "loss": 0.3877, "lr": 5.51231668596653e-06, "epoch": 3.910931174089069, "percentage": 78.22, "elapsed_time": "6:15:34", "remaining_time": "1:44:34"} +{"current_steps": 967, "total_steps": 1235, "loss": 0.4022, "lr": 5.47338630512007e-06, "epoch": 3.91497975708502, "percentage": 78.3, "elapsed_time": "6:15:57", "remaining_time": "1:44:11"} +{"current_steps": 968, "total_steps": 1235, "loss": 0.4164, "lr": 5.434572078689617e-06, "epoch": 3.919028340080972, "percentage": 78.38, "elapsed_time": "6:16:21", "remaining_time": "1:43:48"} +{"current_steps": 969, "total_steps": 1235, "loss": 0.387, "lr": 5.395874317032694e-06, "epoch": 3.9230769230769234, "percentage": 78.46, "elapsed_time": "6:16:44", "remaining_time": "1:43:25"} +{"current_steps": 970, "total_steps": 1235, "loss": 0.3783, "lr": 5.357293329575573e-06, "epoch": 3.9271255060728745, "percentage": 78.54, "elapsed_time": "6:17:06", "remaining_time": "1:43:01"} +{"current_steps": 971, "total_steps": 1235, "loss": 0.4327, "lr": 5.318829424810797e-06, "epoch": 3.931174089068826, "percentage": 78.62, "elapsed_time": "6:17:28", "remaining_time": "1:42:37"} +{"current_steps": 972, "total_steps": 1235, "loss": 0.3859, "lr": 5.280482910294728e-06, "epoch": 3.9352226720647776, "percentage": 78.7, "elapsed_time": "6:17:51", "remaining_time": "1:42:14"} +{"current_steps": 973, "total_steps": 1235, "loss": 0.3954, "lr": 5.242254092645078e-06, "epoch": 3.9392712550607287, "percentage": 78.79, "elapsed_time": "6:18:14", "remaining_time": "1:41:51"} +{"current_steps": 974, "total_steps": 1235, "loss": 0.3981, "lr": 5.2041432775384445e-06, "epoch": 3.9433198380566803, "percentage": 78.87, "elapsed_time": "6:18:37", "remaining_time": "1:41:27"} +{"current_steps": 975, "total_steps": 1235, "loss": 0.396, "lr": 5.166150769707892e-06, "epoch": 3.9473684210526314, "percentage": 78.95, "elapsed_time": "6:19:01", "remaining_time": "1:41:04"} +{"current_steps": 976, "total_steps": 1235, "loss": 0.3953, "lr": 5.128276872940503e-06, "epoch": 3.951417004048583, "percentage": 79.03, "elapsed_time": "6:19:25", "remaining_time": "1:40:41"} +{"current_steps": 977, "total_steps": 1235, "loss": 0.4082, "lr": 5.090521890074953e-06, "epoch": 3.9554655870445345, "percentage": 79.11, "elapsed_time": "6:19:47", "remaining_time": "1:40:17"} +{"current_steps": 978, "total_steps": 1235, "loss": 0.3768, "lr": 5.0528861229990675e-06, "epoch": 3.9595141700404857, "percentage": 79.19, "elapsed_time": "6:20:09", "remaining_time": "1:39:53"} +{"current_steps": 979, "total_steps": 1235, "loss": 0.4261, "lr": 5.015369872647442e-06, "epoch": 3.9635627530364372, "percentage": 79.27, "elapsed_time": "6:20:32", "remaining_time": "1:39:30"} +{"current_steps": 980, "total_steps": 1235, "loss": 0.4064, "lr": 4.9779734389990195e-06, "epoch": 3.967611336032389, "percentage": 79.35, "elapsed_time": "6:20:55", "remaining_time": "1:39:07"} +{"current_steps": 981, "total_steps": 1235, "loss": 0.417, "lr": 4.940697121074675e-06, "epoch": 3.97165991902834, "percentage": 79.43, "elapsed_time": "6:21:18", "remaining_time": "1:38:43"} +{"current_steps": 982, "total_steps": 1235, "loss": 0.407, "lr": 4.903541216934864e-06, "epoch": 3.9757085020242915, "percentage": 79.51, "elapsed_time": "6:21:40", "remaining_time": "1:38:20"} +{"current_steps": 983, "total_steps": 1235, "loss": 0.4032, "lr": 4.8665060236772e-06, "epoch": 3.979757085020243, "percentage": 79.6, "elapsed_time": "6:22:03", "remaining_time": "1:37:56"} +{"current_steps": 984, "total_steps": 1235, "loss": 0.3942, "lr": 4.829591837434102e-06, "epoch": 3.983805668016194, "percentage": 79.68, "elapsed_time": "6:22:25", "remaining_time": "1:37:33"} +{"current_steps": 985, "total_steps": 1235, "loss": 0.4004, "lr": 4.792798953370424e-06, "epoch": 3.9878542510121457, "percentage": 79.76, "elapsed_time": "6:22:49", "remaining_time": "1:37:09"} +{"current_steps": 986, "total_steps": 1235, "loss": 0.3799, "lr": 4.756127665681083e-06, "epoch": 3.9919028340080973, "percentage": 79.84, "elapsed_time": "6:23:12", "remaining_time": "1:36:46"} +{"current_steps": 987, "total_steps": 1235, "loss": 0.4183, "lr": 4.719578267588725e-06, "epoch": 3.9959514170040484, "percentage": 79.92, "elapsed_time": "6:23:36", "remaining_time": "1:36:23"} +{"current_steps": 988, "total_steps": 1235, "loss": 0.3991, "lr": 4.6831510513413525e-06, "epoch": 4.0, "percentage": 80.0, "elapsed_time": "6:23:59", "remaining_time": "1:35:59"} +{"current_steps": 989, "total_steps": 1235, "loss": 0.386, "lr": 4.6468463082100176e-06, "epoch": 4.004048582995951, "percentage": 80.08, "elapsed_time": "6:26:08", "remaining_time": "1:36:02"} +{"current_steps": 990, "total_steps": 1235, "loss": 0.3684, "lr": 4.610664328486485e-06, "epoch": 4.008097165991903, "percentage": 80.16, "elapsed_time": "6:26:32", "remaining_time": "1:35:39"} +{"current_steps": 991, "total_steps": 1235, "loss": 0.3463, "lr": 4.5746054014809e-06, "epoch": 4.012145748987854, "percentage": 80.24, "elapsed_time": "6:26:55", "remaining_time": "1:35:15"} +{"current_steps": 992, "total_steps": 1235, "loss": 0.3548, "lr": 4.5386698155194766e-06, "epoch": 4.016194331983805, "percentage": 80.32, "elapsed_time": "6:27:18", "remaining_time": "1:34:52"} +{"current_steps": 993, "total_steps": 1235, "loss": 0.3403, "lr": 4.502857857942204e-06, "epoch": 4.020242914979757, "percentage": 80.4, "elapsed_time": "6:27:40", "remaining_time": "1:34:28"} +{"current_steps": 994, "total_steps": 1235, "loss": 0.3397, "lr": 4.467169815100549e-06, "epoch": 4.0242914979757085, "percentage": 80.49, "elapsed_time": "6:28:03", "remaining_time": "1:34:05"} +{"current_steps": 995, "total_steps": 1235, "loss": 0.3676, "lr": 4.431605972355137e-06, "epoch": 4.02834008097166, "percentage": 80.57, "elapsed_time": "6:28:27", "remaining_time": "1:33:41"} +{"current_steps": 996, "total_steps": 1235, "loss": 0.357, "lr": 4.396166614073516e-06, "epoch": 4.032388663967612, "percentage": 80.65, "elapsed_time": "6:28:49", "remaining_time": "1:33:18"} +{"current_steps": 997, "total_steps": 1235, "loss": 0.3532, "lr": 4.360852023627846e-06, "epoch": 4.036437246963563, "percentage": 80.73, "elapsed_time": "6:29:12", "remaining_time": "1:32:54"} +{"current_steps": 998, "total_steps": 1235, "loss": 0.3813, "lr": 4.325662483392656e-06, "epoch": 4.040485829959514, "percentage": 80.81, "elapsed_time": "6:29:36", "remaining_time": "1:32:31"} +{"current_steps": 999, "total_steps": 1235, "loss": 0.3411, "lr": 4.29059827474257e-06, "epoch": 4.044534412955466, "percentage": 80.89, "elapsed_time": "6:30:00", "remaining_time": "1:32:08"} +{"current_steps": 1000, "total_steps": 1235, "loss": 0.351, "lr": 4.255659678050063e-06, "epoch": 4.048582995951417, "percentage": 80.97, "elapsed_time": "6:30:24", "remaining_time": "1:31:44"} +{"current_steps": 1001, "total_steps": 1235, "loss": 0.3461, "lr": 4.22084697268323e-06, "epoch": 4.052631578947368, "percentage": 81.05, "elapsed_time": "6:30:47", "remaining_time": "1:31:21"} +{"current_steps": 1002, "total_steps": 1235, "loss": 0.3639, "lr": 4.186160437003535e-06, "epoch": 4.05668016194332, "percentage": 81.13, "elapsed_time": "6:31:09", "remaining_time": "1:30:57"} +{"current_steps": 1003, "total_steps": 1235, "loss": 0.337, "lr": 4.151600348363582e-06, "epoch": 4.060728744939271, "percentage": 81.21, "elapsed_time": "6:31:32", "remaining_time": "1:30:34"} +{"current_steps": 1004, "total_steps": 1235, "loss": 0.3564, "lr": 4.11716698310493e-06, "epoch": 4.064777327935222, "percentage": 81.3, "elapsed_time": "6:31:56", "remaining_time": "1:30:10"} +{"current_steps": 1005, "total_steps": 1235, "loss": 0.357, "lr": 4.082860616555848e-06, "epoch": 4.068825910931174, "percentage": 81.38, "elapsed_time": "6:32:19", "remaining_time": "1:29:47"} +{"current_steps": 1006, "total_steps": 1235, "loss": 0.3405, "lr": 4.048681523029125e-06, "epoch": 4.0728744939271255, "percentage": 81.46, "elapsed_time": "6:32:42", "remaining_time": "1:29:23"} +{"current_steps": 1007, "total_steps": 1235, "loss": 0.3497, "lr": 4.014629975819882e-06, "epoch": 4.076923076923077, "percentage": 81.54, "elapsed_time": "6:33:05", "remaining_time": "1:29:00"} +{"current_steps": 1008, "total_steps": 1235, "loss": 0.3546, "lr": 3.9807062472033855e-06, "epoch": 4.080971659919029, "percentage": 81.62, "elapsed_time": "6:33:28", "remaining_time": "1:28:36"} +{"current_steps": 1009, "total_steps": 1235, "loss": 0.3603, "lr": 3.94691060843287e-06, "epoch": 4.08502024291498, "percentage": 81.7, "elapsed_time": "6:33:50", "remaining_time": "1:28:12"} +{"current_steps": 1010, "total_steps": 1235, "loss": 0.3562, "lr": 3.913243329737353e-06, "epoch": 4.089068825910931, "percentage": 81.78, "elapsed_time": "6:34:13", "remaining_time": "1:27:49"} +{"current_steps": 1011, "total_steps": 1235, "loss": 0.3466, "lr": 3.879704680319503e-06, "epoch": 4.093117408906883, "percentage": 81.86, "elapsed_time": "6:34:36", "remaining_time": "1:27:25"} +{"current_steps": 1012, "total_steps": 1235, "loss": 0.3757, "lr": 3.846294928353471e-06, "epoch": 4.097165991902834, "percentage": 81.94, "elapsed_time": "6:34:58", "remaining_time": "1:27:02"} +{"current_steps": 1013, "total_steps": 1235, "loss": 0.3579, "lr": 3.8130143409827345e-06, "epoch": 4.101214574898785, "percentage": 82.02, "elapsed_time": "6:35:19", "remaining_time": "1:26:38"} +{"current_steps": 1014, "total_steps": 1235, "loss": 0.3425, "lr": 3.7798631843179887e-06, "epoch": 4.105263157894737, "percentage": 82.11, "elapsed_time": "6:35:42", "remaining_time": "1:26:14"} +{"current_steps": 1015, "total_steps": 1235, "loss": 0.3546, "lr": 3.7468417234349973e-06, "epoch": 4.109311740890688, "percentage": 82.19, "elapsed_time": "6:36:06", "remaining_time": "1:25:51"} +{"current_steps": 1016, "total_steps": 1235, "loss": 0.3359, "lr": 3.7139502223724823e-06, "epoch": 4.113360323886639, "percentage": 82.27, "elapsed_time": "6:36:29", "remaining_time": "1:25:27"} +{"current_steps": 1017, "total_steps": 1235, "loss": 0.3499, "lr": 3.6811889441300095e-06, "epoch": 4.117408906882591, "percentage": 82.35, "elapsed_time": "6:36:52", "remaining_time": "1:25:04"} +{"current_steps": 1018, "total_steps": 1235, "loss": 0.3553, "lr": 3.648558150665886e-06, "epoch": 4.1214574898785425, "percentage": 82.43, "elapsed_time": "6:37:15", "remaining_time": "1:24:40"} +{"current_steps": 1019, "total_steps": 1235, "loss": 0.3594, "lr": 3.616058102895075e-06, "epoch": 4.125506072874494, "percentage": 82.51, "elapsed_time": "6:37:38", "remaining_time": "1:24:17"} +{"current_steps": 1020, "total_steps": 1235, "loss": 0.3403, "lr": 3.583689060687079e-06, "epoch": 4.129554655870446, "percentage": 82.59, "elapsed_time": "6:38:01", "remaining_time": "1:23:53"} +{"current_steps": 1021, "total_steps": 1235, "loss": 0.3364, "lr": 3.5514512828639023e-06, "epoch": 4.133603238866397, "percentage": 82.67, "elapsed_time": "6:38:23", "remaining_time": "1:23:30"} +{"current_steps": 1022, "total_steps": 1235, "loss": 0.361, "lr": 3.51934502719796e-06, "epoch": 4.137651821862348, "percentage": 82.75, "elapsed_time": "6:38:47", "remaining_time": "1:23:06"} +{"current_steps": 1023, "total_steps": 1235, "loss": 0.3537, "lr": 3.4873705504100185e-06, "epoch": 4.1417004048583, "percentage": 82.83, "elapsed_time": "6:39:10", "remaining_time": "1:22:43"} +{"current_steps": 1024, "total_steps": 1235, "loss": 0.3481, "lr": 3.4555281081671345e-06, "epoch": 4.145748987854251, "percentage": 82.91, "elapsed_time": "6:39:32", "remaining_time": "1:22:19"} +{"current_steps": 1025, "total_steps": 1235, "loss": 0.3388, "lr": 3.4238179550806326e-06, "epoch": 4.149797570850202, "percentage": 83.0, "elapsed_time": "6:39:56", "remaining_time": "1:21:56"} +{"current_steps": 1026, "total_steps": 1235, "loss": 0.3457, "lr": 3.3922403447040497e-06, "epoch": 4.153846153846154, "percentage": 83.08, "elapsed_time": "6:40:18", "remaining_time": "1:21:32"} +{"current_steps": 1027, "total_steps": 1235, "loss": 0.3272, "lr": 3.3607955295311247e-06, "epoch": 4.157894736842105, "percentage": 83.16, "elapsed_time": "6:40:39", "remaining_time": "1:21:08"} +{"current_steps": 1028, "total_steps": 1235, "loss": 0.3372, "lr": 3.32948376099375e-06, "epoch": 4.161943319838056, "percentage": 83.24, "elapsed_time": "6:41:02", "remaining_time": "1:20:45"} +{"current_steps": 1029, "total_steps": 1235, "loss": 0.37, "lr": 3.2983052894599976e-06, "epoch": 4.165991902834008, "percentage": 83.32, "elapsed_time": "6:41:23", "remaining_time": "1:20:21"} +{"current_steps": 1030, "total_steps": 1235, "loss": 0.3546, "lr": 3.2672603642320945e-06, "epoch": 4.17004048582996, "percentage": 83.4, "elapsed_time": "6:41:46", "remaining_time": "1:19:57"} +{"current_steps": 1031, "total_steps": 1235, "loss": 0.3274, "lr": 3.236349233544438e-06, "epoch": 4.174089068825911, "percentage": 83.48, "elapsed_time": "6:42:08", "remaining_time": "1:19:34"} +{"current_steps": 1032, "total_steps": 1235, "loss": 0.3485, "lr": 3.205572144561604e-06, "epoch": 4.178137651821863, "percentage": 83.56, "elapsed_time": "6:42:30", "remaining_time": "1:19:10"} +{"current_steps": 1033, "total_steps": 1235, "loss": 0.3531, "lr": 3.174929343376374e-06, "epoch": 4.182186234817814, "percentage": 83.64, "elapsed_time": "6:42:54", "remaining_time": "1:18:47"} +{"current_steps": 1034, "total_steps": 1235, "loss": 0.3692, "lr": 3.1444210750077777e-06, "epoch": 4.186234817813765, "percentage": 83.72, "elapsed_time": "6:43:18", "remaining_time": "1:18:23"} +{"current_steps": 1035, "total_steps": 1235, "loss": 0.3571, "lr": 3.1140475833991046e-06, "epoch": 4.190283400809717, "percentage": 83.81, "elapsed_time": "6:43:40", "remaining_time": "1:18:00"} +{"current_steps": 1036, "total_steps": 1235, "loss": 0.3634, "lr": 3.0838091114159895e-06, "epoch": 4.194331983805668, "percentage": 83.89, "elapsed_time": "6:44:03", "remaining_time": "1:17:36"} +{"current_steps": 1037, "total_steps": 1235, "loss": 0.3511, "lr": 3.0537059008444524e-06, "epoch": 4.198380566801619, "percentage": 83.97, "elapsed_time": "6:44:26", "remaining_time": "1:17:13"} +{"current_steps": 1038, "total_steps": 1235, "loss": 0.3504, "lr": 3.0237381923889563e-06, "epoch": 4.202429149797571, "percentage": 84.05, "elapsed_time": "6:44:48", "remaining_time": "1:16:49"} +{"current_steps": 1039, "total_steps": 1235, "loss": 0.3726, "lr": 2.9939062256704997e-06, "epoch": 4.206477732793522, "percentage": 84.13, "elapsed_time": "6:45:12", "remaining_time": "1:16:26"} +{"current_steps": 1040, "total_steps": 1235, "loss": 0.3604, "lr": 2.964210239224696e-06, "epoch": 4.2105263157894735, "percentage": 84.21, "elapsed_time": "6:45:35", "remaining_time": "1:16:02"} +{"current_steps": 1041, "total_steps": 1235, "loss": 0.3536, "lr": 2.934650470499869e-06, "epoch": 4.2145748987854255, "percentage": 84.29, "elapsed_time": "6:45:58", "remaining_time": "1:15:39"} +{"current_steps": 1042, "total_steps": 1235, "loss": 0.3367, "lr": 2.905227155855128e-06, "epoch": 4.218623481781377, "percentage": 84.37, "elapsed_time": "6:46:21", "remaining_time": "1:15:16"} +{"current_steps": 1043, "total_steps": 1235, "loss": 0.3674, "lr": 2.875940530558519e-06, "epoch": 4.222672064777328, "percentage": 84.45, "elapsed_time": "6:46:45", "remaining_time": "1:14:52"} +{"current_steps": 1044, "total_steps": 1235, "loss": 0.3434, "lr": 2.8467908287851154e-06, "epoch": 4.22672064777328, "percentage": 84.53, "elapsed_time": "6:47:08", "remaining_time": "1:14:29"} +{"current_steps": 1045, "total_steps": 1235, "loss": 0.3593, "lr": 2.8177782836151603e-06, "epoch": 4.230769230769231, "percentage": 84.62, "elapsed_time": "6:47:31", "remaining_time": "1:14:05"} +{"current_steps": 1046, "total_steps": 1235, "loss": 0.3576, "lr": 2.7889031270321874e-06, "epoch": 4.234817813765182, "percentage": 84.7, "elapsed_time": "6:47:53", "remaining_time": "1:13:42"} +{"current_steps": 1047, "total_steps": 1235, "loss": 0.3566, "lr": 2.760165589921184e-06, "epoch": 4.238866396761134, "percentage": 84.78, "elapsed_time": "6:48:17", "remaining_time": "1:13:18"} +{"current_steps": 1048, "total_steps": 1235, "loss": 0.3727, "lr": 2.7315659020667305e-06, "epoch": 4.242914979757085, "percentage": 84.86, "elapsed_time": "6:48:40", "remaining_time": "1:12:55"} +{"current_steps": 1049, "total_steps": 1235, "loss": 0.3703, "lr": 2.703104292151164e-06, "epoch": 4.246963562753036, "percentage": 84.94, "elapsed_time": "6:49:03", "remaining_time": "1:12:31"} +{"current_steps": 1050, "total_steps": 1235, "loss": 0.3641, "lr": 2.6747809877527607e-06, "epoch": 4.251012145748988, "percentage": 85.02, "elapsed_time": "6:49:25", "remaining_time": "1:12:08"} +{"current_steps": 1051, "total_steps": 1235, "loss": 0.3594, "lr": 2.6465962153439082e-06, "epoch": 4.255060728744939, "percentage": 85.1, "elapsed_time": "6:49:47", "remaining_time": "1:11:44"} +{"current_steps": 1052, "total_steps": 1235, "loss": 0.3354, "lr": 2.618550200289303e-06, "epoch": 4.2591093117408905, "percentage": 85.18, "elapsed_time": "6:50:10", "remaining_time": "1:11:21"} +{"current_steps": 1053, "total_steps": 1235, "loss": 0.3605, "lr": 2.59064316684412e-06, "epoch": 4.2631578947368425, "percentage": 85.26, "elapsed_time": "6:50:33", "remaining_time": "1:10:57"} +{"current_steps": 1054, "total_steps": 1235, "loss": 0.3465, "lr": 2.562875338152264e-06, "epoch": 4.267206477732794, "percentage": 85.34, "elapsed_time": "6:50:56", "remaining_time": "1:10:34"} +{"current_steps": 1055, "total_steps": 1235, "loss": 0.3517, "lr": 2.5352469362445552e-06, "epoch": 4.271255060728745, "percentage": 85.43, "elapsed_time": "6:51:18", "remaining_time": "1:10:10"} +{"current_steps": 1056, "total_steps": 1235, "loss": 0.3481, "lr": 2.5077581820369523e-06, "epoch": 4.275303643724697, "percentage": 85.51, "elapsed_time": "6:51:41", "remaining_time": "1:09:47"} +{"current_steps": 1057, "total_steps": 1235, "loss": 0.3536, "lr": 2.480409295328803e-06, "epoch": 4.279352226720648, "percentage": 85.59, "elapsed_time": "6:52:05", "remaining_time": "1:09:23"} +{"current_steps": 1058, "total_steps": 1235, "loss": 0.3499, "lr": 2.45320049480108e-06, "epoch": 4.283400809716599, "percentage": 85.67, "elapsed_time": "6:52:28", "remaining_time": "1:09:00"} +{"current_steps": 1059, "total_steps": 1235, "loss": 0.3467, "lr": 2.4261319980146293e-06, "epoch": 4.287449392712551, "percentage": 85.75, "elapsed_time": "6:52:49", "remaining_time": "1:08:36"} +{"current_steps": 1060, "total_steps": 1235, "loss": 0.3431, "lr": 2.399204021408421e-06, "epoch": 4.291497975708502, "percentage": 85.83, "elapsed_time": "6:53:12", "remaining_time": "1:08:13"} +{"current_steps": 1061, "total_steps": 1235, "loss": 0.3501, "lr": 2.3724167802978395e-06, "epoch": 4.295546558704453, "percentage": 85.91, "elapsed_time": "6:53:35", "remaining_time": "1:07:49"} +{"current_steps": 1062, "total_steps": 1235, "loss": 0.357, "lr": 2.3457704888729625e-06, "epoch": 4.299595141700405, "percentage": 85.99, "elapsed_time": "6:53:58", "remaining_time": "1:07:26"} +{"current_steps": 1063, "total_steps": 1235, "loss": 0.3697, "lr": 2.3192653601968162e-06, "epoch": 4.303643724696356, "percentage": 86.07, "elapsed_time": "6:54:21", "remaining_time": "1:07:02"} +{"current_steps": 1064, "total_steps": 1235, "loss": 0.3385, "lr": 2.2929016062037057e-06, "epoch": 4.3076923076923075, "percentage": 86.15, "elapsed_time": "6:54:45", "remaining_time": "1:06:39"} +{"current_steps": 1065, "total_steps": 1235, "loss": 0.3465, "lr": 2.2666794376975055e-06, "epoch": 4.3117408906882595, "percentage": 86.23, "elapsed_time": "6:55:07", "remaining_time": "1:06:15"} +{"current_steps": 1066, "total_steps": 1235, "loss": 0.3246, "lr": 2.24059906434998e-06, "epoch": 4.315789473684211, "percentage": 86.32, "elapsed_time": "6:55:30", "remaining_time": "1:05:52"} +{"current_steps": 1067, "total_steps": 1235, "loss": 0.3411, "lr": 2.214660694699091e-06, "epoch": 4.319838056680162, "percentage": 86.4, "elapsed_time": "6:55:54", "remaining_time": "1:05:29"} +{"current_steps": 1068, "total_steps": 1235, "loss": 0.3483, "lr": 2.188864536147355e-06, "epoch": 4.323886639676114, "percentage": 86.48, "elapsed_time": "6:56:17", "remaining_time": "1:05:05"} +{"current_steps": 1069, "total_steps": 1235, "loss": 0.3605, "lr": 2.1632107949601757e-06, "epoch": 4.327935222672065, "percentage": 86.56, "elapsed_time": "6:56:41", "remaining_time": "1:04:42"} +{"current_steps": 1070, "total_steps": 1235, "loss": 0.3446, "lr": 2.137699676264171e-06, "epoch": 4.331983805668016, "percentage": 86.64, "elapsed_time": "6:57:05", "remaining_time": "1:04:19"} +{"current_steps": 1071, "total_steps": 1235, "loss": 0.3472, "lr": 2.1123313840455738e-06, "epoch": 4.336032388663968, "percentage": 86.72, "elapsed_time": "6:57:28", "remaining_time": "1:03:55"} +{"current_steps": 1072, "total_steps": 1235, "loss": 0.3602, "lr": 2.08710612114857e-06, "epoch": 4.340080971659919, "percentage": 86.8, "elapsed_time": "6:57:51", "remaining_time": "1:03:32"} +{"current_steps": 1073, "total_steps": 1235, "loss": 0.363, "lr": 2.0620240892736953e-06, "epoch": 4.34412955465587, "percentage": 86.88, "elapsed_time": "6:58:15", "remaining_time": "1:03:08"} +{"current_steps": 1074, "total_steps": 1235, "loss": 0.3698, "lr": 2.0370854889762e-06, "epoch": 4.348178137651822, "percentage": 86.96, "elapsed_time": "6:58:38", "remaining_time": "1:02:45"} +{"current_steps": 1075, "total_steps": 1235, "loss": 0.3388, "lr": 2.0122905196644726e-06, "epoch": 4.352226720647773, "percentage": 87.04, "elapsed_time": "6:59:02", "remaining_time": "1:02:22"} +{"current_steps": 1076, "total_steps": 1235, "loss": 0.344, "lr": 1.987639379598427e-06, "epoch": 4.3562753036437245, "percentage": 87.13, "elapsed_time": "6:59:24", "remaining_time": "1:01:58"} +{"current_steps": 1077, "total_steps": 1235, "loss": 0.3593, "lr": 1.963132265887919e-06, "epoch": 4.3603238866396765, "percentage": 87.21, "elapsed_time": "6:59:48", "remaining_time": "1:01:35"} +{"current_steps": 1078, "total_steps": 1235, "loss": 0.3598, "lr": 1.9387693744911784e-06, "epoch": 4.364372469635628, "percentage": 87.29, "elapsed_time": "7:00:12", "remaining_time": "1:01:11"} +{"current_steps": 1079, "total_steps": 1235, "loss": 0.3545, "lr": 1.9145509002132368e-06, "epoch": 4.368421052631579, "percentage": 87.37, "elapsed_time": "7:00:34", "remaining_time": "1:00:48"} +{"current_steps": 1080, "total_steps": 1235, "loss": 0.3551, "lr": 1.8904770367043723e-06, "epoch": 4.372469635627531, "percentage": 87.45, "elapsed_time": "7:00:57", "remaining_time": "1:00:24"} +{"current_steps": 1081, "total_steps": 1235, "loss": 0.3682, "lr": 1.8665479764585504e-06, "epoch": 4.376518218623482, "percentage": 87.53, "elapsed_time": "7:01:19", "remaining_time": "1:00:01"} +{"current_steps": 1082, "total_steps": 1235, "loss": 0.3403, "lr": 1.8427639108118977e-06, "epoch": 4.380566801619433, "percentage": 87.61, "elapsed_time": "7:01:42", "remaining_time": "0:59:37"} +{"current_steps": 1083, "total_steps": 1235, "loss": 0.374, "lr": 1.8191250299411755e-06, "epoch": 4.384615384615385, "percentage": 87.69, "elapsed_time": "7:02:05", "remaining_time": "0:59:14"} +{"current_steps": 1084, "total_steps": 1235, "loss": 0.345, "lr": 1.7956315228622446e-06, "epoch": 4.388663967611336, "percentage": 87.77, "elapsed_time": "7:02:27", "remaining_time": "0:58:50"} +{"current_steps": 1085, "total_steps": 1235, "loss": 0.3364, "lr": 1.7722835774285553e-06, "epoch": 4.392712550607287, "percentage": 87.85, "elapsed_time": "7:02:50", "remaining_time": "0:58:27"} +{"current_steps": 1086, "total_steps": 1235, "loss": 0.3504, "lr": 1.7490813803296624e-06, "epoch": 4.396761133603239, "percentage": 87.94, "elapsed_time": "7:03:14", "remaining_time": "0:58:04"} +{"current_steps": 1087, "total_steps": 1235, "loss": 0.3249, "lr": 1.726025117089718e-06, "epoch": 4.40080971659919, "percentage": 88.02, "elapsed_time": "7:03:36", "remaining_time": "0:57:40"} +{"current_steps": 1088, "total_steps": 1235, "loss": 0.3504, "lr": 1.70311497206598e-06, "epoch": 4.4048582995951415, "percentage": 88.1, "elapsed_time": "7:03:59", "remaining_time": "0:57:17"} +{"current_steps": 1089, "total_steps": 1235, "loss": 0.3477, "lr": 1.6803511284473638e-06, "epoch": 4.4089068825910935, "percentage": 88.18, "elapsed_time": "7:04:22", "remaining_time": "0:56:53"} +{"current_steps": 1090, "total_steps": 1235, "loss": 0.3423, "lr": 1.6577337682529538e-06, "epoch": 4.412955465587045, "percentage": 88.26, "elapsed_time": "7:04:45", "remaining_time": "0:56:30"} +{"current_steps": 1091, "total_steps": 1235, "loss": 0.354, "lr": 1.6352630723305617e-06, "epoch": 4.417004048582996, "percentage": 88.34, "elapsed_time": "7:05:08", "remaining_time": "0:56:06"} +{"current_steps": 1092, "total_steps": 1235, "loss": 0.3385, "lr": 1.612939220355272e-06, "epoch": 4.421052631578947, "percentage": 88.42, "elapsed_time": "7:05:31", "remaining_time": "0:55:43"} +{"current_steps": 1093, "total_steps": 1235, "loss": 0.3481, "lr": 1.5907623908280112e-06, "epoch": 4.425101214574899, "percentage": 88.5, "elapsed_time": "7:05:54", "remaining_time": "0:55:20"} +{"current_steps": 1094, "total_steps": 1235, "loss": 0.3385, "lr": 1.568732761074121e-06, "epoch": 4.42914979757085, "percentage": 88.58, "elapsed_time": "7:06:18", "remaining_time": "0:54:56"} +{"current_steps": 1095, "total_steps": 1235, "loss": 0.3517, "lr": 1.5468505072419237e-06, "epoch": 4.433198380566802, "percentage": 88.66, "elapsed_time": "7:06:42", "remaining_time": "0:54:33"} +{"current_steps": 1096, "total_steps": 1235, "loss": 0.3399, "lr": 1.5251158043013448e-06, "epoch": 4.437246963562753, "percentage": 88.74, "elapsed_time": "7:07:05", "remaining_time": "0:54:09"} +{"current_steps": 1097, "total_steps": 1235, "loss": 0.3448, "lr": 1.5035288260424885e-06, "epoch": 4.441295546558704, "percentage": 88.83, "elapsed_time": "7:07:28", "remaining_time": "0:53:46"} +{"current_steps": 1098, "total_steps": 1235, "loss": 0.356, "lr": 1.4820897450742623e-06, "epoch": 4.445344129554655, "percentage": 88.91, "elapsed_time": "7:07:51", "remaining_time": "0:53:23"} +{"current_steps": 1099, "total_steps": 1235, "loss": 0.3598, "lr": 1.4607987328229767e-06, "epoch": 4.449392712550607, "percentage": 88.99, "elapsed_time": "7:08:14", "remaining_time": "0:52:59"} +{"current_steps": 1100, "total_steps": 1235, "loss": 0.3336, "lr": 1.4396559595310056e-06, "epoch": 4.4534412955465585, "percentage": 89.07, "elapsed_time": "7:08:38", "remaining_time": "0:52:36"} +{"current_steps": 1101, "total_steps": 1235, "loss": 0.369, "lr": 1.4186615942553973e-06, "epoch": 4.4574898785425106, "percentage": 89.15, "elapsed_time": "7:09:00", "remaining_time": "0:52:12"} +{"current_steps": 1102, "total_steps": 1235, "loss": 0.3327, "lr": 1.3978158048665424e-06, "epoch": 4.461538461538462, "percentage": 89.23, "elapsed_time": "7:09:22", "remaining_time": "0:51:49"} +{"current_steps": 1103, "total_steps": 1235, "loss": 0.3584, "lr": 1.3771187580468115e-06, "epoch": 4.465587044534413, "percentage": 89.31, "elapsed_time": "7:09:46", "remaining_time": "0:51:25"} +{"current_steps": 1104, "total_steps": 1235, "loss": 0.3695, "lr": 1.3565706192892392e-06, "epoch": 4.469635627530364, "percentage": 89.39, "elapsed_time": "7:10:09", "remaining_time": "0:51:02"} +{"current_steps": 1105, "total_steps": 1235, "loss": 0.3375, "lr": 1.3361715528961993e-06, "epoch": 4.473684210526316, "percentage": 89.47, "elapsed_time": "7:10:32", "remaining_time": "0:50:39"} +{"current_steps": 1106, "total_steps": 1235, "loss": 0.3629, "lr": 1.3159217219780817e-06, "epoch": 4.477732793522267, "percentage": 89.55, "elapsed_time": "7:10:54", "remaining_time": "0:50:15"} +{"current_steps": 1107, "total_steps": 1235, "loss": 0.3595, "lr": 1.2958212884519949e-06, "epoch": 4.481781376518219, "percentage": 89.64, "elapsed_time": "7:11:16", "remaining_time": "0:49:52"} +{"current_steps": 1108, "total_steps": 1235, "loss": 0.3682, "lr": 1.2758704130404675e-06, "epoch": 4.48582995951417, "percentage": 89.72, "elapsed_time": "7:11:39", "remaining_time": "0:49:28"} +{"current_steps": 1109, "total_steps": 1235, "loss": 0.362, "lr": 1.2560692552701738e-06, "epoch": 4.489878542510121, "percentage": 89.8, "elapsed_time": "7:12:03", "remaining_time": "0:49:05"} +{"current_steps": 1110, "total_steps": 1235, "loss": 0.3706, "lr": 1.2364179734706382e-06, "epoch": 4.493927125506072, "percentage": 89.88, "elapsed_time": "7:12:27", "remaining_time": "0:48:41"} +{"current_steps": 1111, "total_steps": 1235, "loss": 0.3552, "lr": 1.2169167247729852e-06, "epoch": 4.497975708502024, "percentage": 89.96, "elapsed_time": "7:12:50", "remaining_time": "0:48:18"} +{"current_steps": 1112, "total_steps": 1235, "loss": 0.3568, "lr": 1.1975656651086864e-06, "epoch": 4.502024291497976, "percentage": 90.04, "elapsed_time": "7:13:13", "remaining_time": "0:47:55"} +{"current_steps": 1113, "total_steps": 1235, "loss": 0.3458, "lr": 1.1783649492082926e-06, "epoch": 4.506072874493928, "percentage": 90.12, "elapsed_time": "7:13:36", "remaining_time": "0:47:31"} +{"current_steps": 1114, "total_steps": 1235, "loss": 0.3475, "lr": 1.1593147306002183e-06, "epoch": 4.510121457489879, "percentage": 90.2, "elapsed_time": "7:13:59", "remaining_time": "0:47:08"} +{"current_steps": 1115, "total_steps": 1235, "loss": 0.3566, "lr": 1.140415161609505e-06, "epoch": 4.51417004048583, "percentage": 90.28, "elapsed_time": "7:14:23", "remaining_time": "0:46:45"} +{"current_steps": 1116, "total_steps": 1235, "loss": 0.3708, "lr": 1.121666393356604e-06, "epoch": 4.518218623481781, "percentage": 90.36, "elapsed_time": "7:14:46", "remaining_time": "0:46:21"} +{"current_steps": 1117, "total_steps": 1235, "loss": 0.3359, "lr": 1.1030685757561632e-06, "epoch": 4.522267206477733, "percentage": 90.45, "elapsed_time": "7:15:09", "remaining_time": "0:45:58"} +{"current_steps": 1118, "total_steps": 1235, "loss": 0.3365, "lr": 1.0846218575158373e-06, "epoch": 4.526315789473684, "percentage": 90.53, "elapsed_time": "7:15:33", "remaining_time": "0:45:34"} +{"current_steps": 1119, "total_steps": 1235, "loss": 0.3318, "lr": 1.066326386135097e-06, "epoch": 4.530364372469636, "percentage": 90.61, "elapsed_time": "7:15:56", "remaining_time": "0:45:11"} +{"current_steps": 1120, "total_steps": 1235, "loss": 0.3576, "lr": 1.0481823079040398e-06, "epoch": 4.534412955465587, "percentage": 90.69, "elapsed_time": "7:16:19", "remaining_time": "0:44:48"} +{"current_steps": 1121, "total_steps": 1235, "loss": 0.3634, "lr": 1.0301897679022344e-06, "epoch": 4.538461538461538, "percentage": 90.77, "elapsed_time": "7:16:43", "remaining_time": "0:44:24"} +{"current_steps": 1122, "total_steps": 1235, "loss": 0.3519, "lr": 1.0123489099975491e-06, "epoch": 4.5425101214574894, "percentage": 90.85, "elapsed_time": "7:17:07", "remaining_time": "0:44:01"} +{"current_steps": 1123, "total_steps": 1235, "loss": 0.3576, "lr": 9.9465987684501e-07, "epoch": 4.5465587044534415, "percentage": 90.93, "elapsed_time": "7:17:30", "remaining_time": "0:43:38"} +{"current_steps": 1124, "total_steps": 1235, "loss": 0.3366, "lr": 9.771228098856534e-07, "epoch": 4.550607287449393, "percentage": 91.01, "elapsed_time": "7:17:51", "remaining_time": "0:43:14"} +{"current_steps": 1125, "total_steps": 1235, "loss": 0.3446, "lr": 9.597378493454013e-07, "epoch": 4.554655870445345, "percentage": 91.09, "elapsed_time": "7:18:15", "remaining_time": "0:42:51"} +{"current_steps": 1126, "total_steps": 1235, "loss": 0.3161, "lr": 9.425051342339353e-07, "epoch": 4.558704453441296, "percentage": 91.17, "elapsed_time": "7:18:35", "remaining_time": "0:42:27"} +{"current_steps": 1127, "total_steps": 1235, "loss": 0.3387, "lr": 9.254248023435864e-07, "epoch": 4.562753036437247, "percentage": 91.26, "elapsed_time": "7:18:57", "remaining_time": "0:42:03"} +{"current_steps": 1128, "total_steps": 1235, "loss": 0.3541, "lr": 9.084969902482288e-07, "epoch": 4.566801619433198, "percentage": 91.34, "elapsed_time": "7:19:20", "remaining_time": "0:41:40"} +{"current_steps": 1129, "total_steps": 1235, "loss": 0.358, "lr": 8.917218333021993e-07, "epoch": 4.57085020242915, "percentage": 91.42, "elapsed_time": "7:19:44", "remaining_time": "0:41:17"} +{"current_steps": 1130, "total_steps": 1235, "loss": 0.3697, "lr": 8.750994656392109e-07, "epoch": 4.574898785425101, "percentage": 91.5, "elapsed_time": "7:20:07", "remaining_time": "0:40:53"} +{"current_steps": 1131, "total_steps": 1235, "loss": 0.3578, "lr": 8.58630020171265e-07, "epoch": 4.578947368421053, "percentage": 91.58, "elapsed_time": "7:20:31", "remaining_time": "0:40:30"} +{"current_steps": 1132, "total_steps": 1235, "loss": 0.3368, "lr": 8.423136285876099e-07, "epoch": 4.582995951417004, "percentage": 91.66, "elapsed_time": "7:20:54", "remaining_time": "0:40:07"} +{"current_steps": 1133, "total_steps": 1235, "loss": 0.3507, "lr": 8.26150421353682e-07, "epoch": 4.587044534412955, "percentage": 91.74, "elapsed_time": "7:21:18", "remaining_time": "0:39:43"} +{"current_steps": 1134, "total_steps": 1235, "loss": 0.3232, "lr": 8.101405277100549e-07, "epoch": 4.5910931174089065, "percentage": 91.82, "elapsed_time": "7:21:40", "remaining_time": "0:39:20"} +{"current_steps": 1135, "total_steps": 1235, "loss": 0.3439, "lr": 7.942840756714077e-07, "epoch": 4.5951417004048585, "percentage": 91.9, "elapsed_time": "7:22:04", "remaining_time": "0:38:56"} +{"current_steps": 1136, "total_steps": 1235, "loss": 0.3239, "lr": 7.785811920255093e-07, "epoch": 4.59919028340081, "percentage": 91.98, "elapsed_time": "7:22:27", "remaining_time": "0:38:33"} +{"current_steps": 1137, "total_steps": 1235, "loss": 0.3432, "lr": 7.630320023322024e-07, "epoch": 4.603238866396762, "percentage": 92.06, "elapsed_time": "7:22:50", "remaining_time": "0:38:10"} +{"current_steps": 1138, "total_steps": 1235, "loss": 0.3548, "lr": 7.476366309223903e-07, "epoch": 4.607287449392713, "percentage": 92.15, "elapsed_time": "7:23:14", "remaining_time": "0:37:46"} +{"current_steps": 1139, "total_steps": 1235, "loss": 0.3457, "lr": 7.323952008970537e-07, "epoch": 4.611336032388664, "percentage": 92.23, "elapsed_time": "7:23:37", "remaining_time": "0:37:23"} +{"current_steps": 1140, "total_steps": 1235, "loss": 0.3455, "lr": 7.173078341262618e-07, "epoch": 4.615384615384615, "percentage": 92.31, "elapsed_time": "7:24:01", "remaining_time": "0:37:00"} +{"current_steps": 1141, "total_steps": 1235, "loss": 0.355, "lr": 7.023746512481989e-07, "epoch": 4.619433198380567, "percentage": 92.39, "elapsed_time": "7:24:23", "remaining_time": "0:36:36"} +{"current_steps": 1142, "total_steps": 1235, "loss": 0.3422, "lr": 6.875957716681902e-07, "epoch": 4.623481781376518, "percentage": 92.47, "elapsed_time": "7:24:46", "remaining_time": "0:36:13"} +{"current_steps": 1143, "total_steps": 1235, "loss": 0.347, "lr": 6.729713135577687e-07, "epoch": 4.62753036437247, "percentage": 92.55, "elapsed_time": "7:25:09", "remaining_time": "0:35:49"} +{"current_steps": 1144, "total_steps": 1235, "loss": 0.3612, "lr": 6.585013938537143e-07, "epoch": 4.631578947368421, "percentage": 92.63, "elapsed_time": "7:25:33", "remaining_time": "0:35:26"} +{"current_steps": 1145, "total_steps": 1235, "loss": 0.3432, "lr": 6.441861282571115e-07, "epoch": 4.635627530364372, "percentage": 92.71, "elapsed_time": "7:25:56", "remaining_time": "0:35:03"} +{"current_steps": 1146, "total_steps": 1235, "loss": 0.3543, "lr": 6.300256312324471e-07, "epoch": 4.6396761133603235, "percentage": 92.79, "elapsed_time": "7:26:20", "remaining_time": "0:34:39"} +{"current_steps": 1147, "total_steps": 1235, "loss": 0.358, "lr": 6.160200160066776e-07, "epoch": 4.6437246963562755, "percentage": 92.87, "elapsed_time": "7:26:42", "remaining_time": "0:34:16"} +{"current_steps": 1148, "total_steps": 1235, "loss": 0.335, "lr": 6.021693945683327e-07, "epoch": 4.647773279352227, "percentage": 92.96, "elapsed_time": "7:27:05", "remaining_time": "0:33:52"} +{"current_steps": 1149, "total_steps": 1235, "loss": 0.351, "lr": 5.884738776666044e-07, "epoch": 4.651821862348179, "percentage": 93.04, "elapsed_time": "7:27:28", "remaining_time": "0:33:29"} +{"current_steps": 1150, "total_steps": 1235, "loss": 0.3494, "lr": 5.749335748104878e-07, "epoch": 4.65587044534413, "percentage": 93.12, "elapsed_time": "7:27:51", "remaining_time": "0:33:06"} +{"current_steps": 1151, "total_steps": 1235, "loss": 0.3417, "lr": 5.615485942678778e-07, "epoch": 4.659919028340081, "percentage": 93.2, "elapsed_time": "7:28:14", "remaining_time": "0:32:42"} +{"current_steps": 1152, "total_steps": 1235, "loss": 0.3303, "lr": 5.483190430647289e-07, "epoch": 4.663967611336032, "percentage": 93.28, "elapsed_time": "7:28:37", "remaining_time": "0:32:19"} +{"current_steps": 1153, "total_steps": 1235, "loss": 0.3532, "lr": 5.352450269841747e-07, "epoch": 4.668016194331984, "percentage": 93.36, "elapsed_time": "7:29:01", "remaining_time": "0:31:56"} +{"current_steps": 1154, "total_steps": 1235, "loss": 0.3392, "lr": 5.22326650565701e-07, "epoch": 4.672064777327935, "percentage": 93.44, "elapsed_time": "7:29:24", "remaining_time": "0:31:32"} +{"current_steps": 1155, "total_steps": 1235, "loss": 0.3481, "lr": 5.095640171043048e-07, "epoch": 4.676113360323887, "percentage": 93.52, "elapsed_time": "7:29:46", "remaining_time": "0:31:09"} +{"current_steps": 1156, "total_steps": 1235, "loss": 0.3448, "lr": 4.969572286496594e-07, "epoch": 4.680161943319838, "percentage": 93.6, "elapsed_time": "7:30:09", "remaining_time": "0:30:45"} +{"current_steps": 1157, "total_steps": 1235, "loss": 0.3514, "lr": 4.845063860053079e-07, "epoch": 4.684210526315789, "percentage": 93.68, "elapsed_time": "7:30:31", "remaining_time": "0:30:22"} +{"current_steps": 1158, "total_steps": 1235, "loss": 0.3413, "lr": 4.7221158872785997e-07, "epoch": 4.6882591093117405, "percentage": 93.77, "elapsed_time": "7:30:55", "remaining_time": "0:29:59"} +{"current_steps": 1159, "total_steps": 1235, "loss": 0.3631, "lr": 4.600729351261857e-07, "epoch": 4.6923076923076925, "percentage": 93.85, "elapsed_time": "7:31:18", "remaining_time": "0:29:35"} +{"current_steps": 1160, "total_steps": 1235, "loss": 0.3216, "lr": 4.4809052226063355e-07, "epoch": 4.696356275303644, "percentage": 93.93, "elapsed_time": "7:31:40", "remaining_time": "0:29:12"} +{"current_steps": 1161, "total_steps": 1235, "loss": 0.3254, "lr": 4.3626444594226046e-07, "epoch": 4.700404858299595, "percentage": 94.01, "elapsed_time": "7:32:02", "remaining_time": "0:28:48"} +{"current_steps": 1162, "total_steps": 1235, "loss": 0.3673, "lr": 4.245948007320588e-07, "epoch": 4.704453441295547, "percentage": 94.09, "elapsed_time": "7:32:26", "remaining_time": "0:28:25"} +{"current_steps": 1163, "total_steps": 1235, "loss": 0.3494, "lr": 4.130816799401971e-07, "epoch": 4.708502024291498, "percentage": 94.17, "elapsed_time": "7:32:49", "remaining_time": "0:28:02"} +{"current_steps": 1164, "total_steps": 1235, "loss": 0.3398, "lr": 4.017251756252827e-07, "epoch": 4.712550607287449, "percentage": 94.25, "elapsed_time": "7:33:13", "remaining_time": "0:27:38"} +{"current_steps": 1165, "total_steps": 1235, "loss": 0.3586, "lr": 3.9052537859362473e-07, "epoch": 4.716599190283401, "percentage": 94.33, "elapsed_time": "7:33:39", "remaining_time": "0:27:15"} +{"current_steps": 1166, "total_steps": 1235, "loss": 0.3664, "lr": 3.7948237839849687e-07, "epoch": 4.720647773279352, "percentage": 94.41, "elapsed_time": "7:34:03", "remaining_time": "0:26:52"} +{"current_steps": 1167, "total_steps": 1235, "loss": 0.3402, "lr": 3.6859626333943797e-07, "epoch": 4.724696356275303, "percentage": 94.49, "elapsed_time": "7:34:25", "remaining_time": "0:26:28"} +{"current_steps": 1168, "total_steps": 1235, "loss": 0.3482, "lr": 3.578671204615347e-07, "epoch": 4.728744939271255, "percentage": 94.57, "elapsed_time": "7:34:49", "remaining_time": "0:26:05"} +{"current_steps": 1169, "total_steps": 1235, "loss": 0.3568, "lr": 3.472950355547267e-07, "epoch": 4.732793522267206, "percentage": 94.66, "elapsed_time": "7:35:13", "remaining_time": "0:25:42"} +{"current_steps": 1170, "total_steps": 1235, "loss": 0.3436, "lr": 3.3688009315312244e-07, "epoch": 4.7368421052631575, "percentage": 94.74, "elapsed_time": "7:35:36", "remaining_time": "0:25:18"} +{"current_steps": 1171, "total_steps": 1235, "loss": 0.3639, "lr": 3.266223765343224e-07, "epoch": 4.7408906882591095, "percentage": 94.82, "elapsed_time": "7:36:00", "remaining_time": "0:24:55"} +{"current_steps": 1172, "total_steps": 1235, "loss": 0.3534, "lr": 3.16521967718757e-07, "epoch": 4.744939271255061, "percentage": 94.9, "elapsed_time": "7:36:25", "remaining_time": "0:24:32"} +{"current_steps": 1173, "total_steps": 1235, "loss": 0.3737, "lr": 3.0657894746902726e-07, "epoch": 4.748987854251012, "percentage": 94.98, "elapsed_time": "7:36:47", "remaining_time": "0:24:08"} +{"current_steps": 1174, "total_steps": 1235, "loss": 0.3611, "lr": 2.9679339528925654e-07, "epoch": 4.753036437246964, "percentage": 95.06, "elapsed_time": "7:37:10", "remaining_time": "0:23:45"} +{"current_steps": 1175, "total_steps": 1235, "loss": 0.3651, "lr": 2.871653894244597e-07, "epoch": 4.757085020242915, "percentage": 95.14, "elapsed_time": "7:37:32", "remaining_time": "0:23:21"} +{"current_steps": 1176, "total_steps": 1235, "loss": 0.3586, "lr": 2.7769500685991266e-07, "epoch": 4.761133603238866, "percentage": 95.22, "elapsed_time": "7:37:53", "remaining_time": "0:22:58"} +{"current_steps": 1177, "total_steps": 1235, "loss": 0.3795, "lr": 2.683823233205485e-07, "epoch": 4.765182186234818, "percentage": 95.3, "elapsed_time": "7:38:16", "remaining_time": "0:22:34"} +{"current_steps": 1178, "total_steps": 1235, "loss": 0.3367, "lr": 2.592274132703287e-07, "epoch": 4.769230769230769, "percentage": 95.38, "elapsed_time": "7:38:39", "remaining_time": "0:22:11"} +{"current_steps": 1179, "total_steps": 1235, "loss": 0.3455, "lr": 2.502303499116754e-07, "epoch": 4.77327935222672, "percentage": 95.47, "elapsed_time": "7:39:02", "remaining_time": "0:21:48"} +{"current_steps": 1180, "total_steps": 1235, "loss": 0.352, "lr": 2.413912051848666e-07, "epoch": 4.777327935222672, "percentage": 95.55, "elapsed_time": "7:39:26", "remaining_time": "0:21:24"} +{"current_steps": 1181, "total_steps": 1235, "loss": 0.3502, "lr": 2.3271004976746613e-07, "epoch": 4.781376518218623, "percentage": 95.63, "elapsed_time": "7:39:49", "remaining_time": "0:21:01"} +{"current_steps": 1182, "total_steps": 1235, "loss": 0.356, "lr": 2.2418695307376393e-07, "epoch": 4.7854251012145745, "percentage": 95.71, "elapsed_time": "7:40:12", "remaining_time": "0:20:38"} +{"current_steps": 1183, "total_steps": 1235, "loss": 0.3387, "lr": 2.1582198325420968e-07, "epoch": 4.7894736842105265, "percentage": 95.79, "elapsed_time": "7:40:35", "remaining_time": "0:20:14"} +{"current_steps": 1184, "total_steps": 1235, "loss": 0.3368, "lr": 2.0761520719488447e-07, "epoch": 4.793522267206478, "percentage": 95.87, "elapsed_time": "7:40:59", "remaining_time": "0:19:51"} +{"current_steps": 1185, "total_steps": 1235, "loss": 0.3521, "lr": 1.9956669051694798e-07, "epoch": 4.797570850202429, "percentage": 95.95, "elapsed_time": "7:41:22", "remaining_time": "0:19:28"} +{"current_steps": 1186, "total_steps": 1235, "loss": 0.3668, "lr": 1.916764975761254e-07, "epoch": 4.801619433198381, "percentage": 96.03, "elapsed_time": "7:41:43", "remaining_time": "0:19:04"} +{"current_steps": 1187, "total_steps": 1235, "loss": 0.3409, "lr": 1.839446914621923e-07, "epoch": 4.805668016194332, "percentage": 96.11, "elapsed_time": "7:42:07", "remaining_time": "0:18:41"} +{"current_steps": 1188, "total_steps": 1235, "loss": 0.3339, "lr": 1.7637133399845962e-07, "epoch": 4.809716599190283, "percentage": 96.19, "elapsed_time": "7:42:31", "remaining_time": "0:18:17"} +{"current_steps": 1189, "total_steps": 1235, "loss": 0.3363, "lr": 1.6895648574129397e-07, "epoch": 4.813765182186235, "percentage": 96.28, "elapsed_time": "7:42:53", "remaining_time": "0:17:54"} +{"current_steps": 1190, "total_steps": 1235, "loss": 0.3255, "lr": 1.6170020597962465e-07, "epoch": 4.817813765182186, "percentage": 96.36, "elapsed_time": "7:43:16", "remaining_time": "0:17:31"} +{"current_steps": 1191, "total_steps": 1235, "loss": 0.3619, "lr": 1.5460255273447078e-07, "epoch": 4.821862348178137, "percentage": 96.44, "elapsed_time": "7:43:39", "remaining_time": "0:17:07"} +{"current_steps": 1192, "total_steps": 1235, "loss": 0.3486, "lr": 1.4766358275847715e-07, "epoch": 4.825910931174089, "percentage": 96.52, "elapsed_time": "7:44:02", "remaining_time": "0:16:44"} +{"current_steps": 1193, "total_steps": 1235, "loss": 0.345, "lr": 1.4088335153546573e-07, "epoch": 4.82995951417004, "percentage": 96.6, "elapsed_time": "7:44:25", "remaining_time": "0:16:21"} +{"current_steps": 1194, "total_steps": 1235, "loss": 0.3633, "lr": 1.3426191327998496e-07, "epoch": 4.834008097165992, "percentage": 96.68, "elapsed_time": "7:44:47", "remaining_time": "0:15:57"} +{"current_steps": 1195, "total_steps": 1235, "loss": 0.3644, "lr": 1.277993209368744e-07, "epoch": 4.838056680161944, "percentage": 96.76, "elapsed_time": "7:45:11", "remaining_time": "0:15:34"} +{"current_steps": 1196, "total_steps": 1235, "loss": 0.3364, "lr": 1.214956261808542e-07, "epoch": 4.842105263157895, "percentage": 96.84, "elapsed_time": "7:45:33", "remaining_time": "0:15:10"} +{"current_steps": 1197, "total_steps": 1235, "loss": 0.3688, "lr": 1.1535087941609846e-07, "epoch": 4.846153846153846, "percentage": 96.92, "elapsed_time": "7:45:56", "remaining_time": "0:14:47"} +{"current_steps": 1198, "total_steps": 1235, "loss": 0.3601, "lr": 1.0936512977583802e-07, "epoch": 4.850202429149798, "percentage": 97.0, "elapsed_time": "7:46:19", "remaining_time": "0:14:24"} +{"current_steps": 1199, "total_steps": 1235, "loss": 0.359, "lr": 1.0353842512196732e-07, "epoch": 4.854251012145749, "percentage": 97.09, "elapsed_time": "7:46:42", "remaining_time": "0:14:00"} +{"current_steps": 1200, "total_steps": 1235, "loss": 0.352, "lr": 9.787081204466253e-08, "epoch": 4.8582995951417, "percentage": 97.17, "elapsed_time": "7:47:05", "remaining_time": "0:13:37"} +{"current_steps": 1201, "total_steps": 1235, "loss": 0.3567, "lr": 9.236233586200627e-08, "epoch": 4.862348178137652, "percentage": 97.25, "elapsed_time": "7:47:27", "remaining_time": "0:13:14"} +{"current_steps": 1202, "total_steps": 1235, "loss": 0.3563, "lr": 8.70130406196279e-08, "epoch": 4.866396761133603, "percentage": 97.33, "elapsed_time": "7:47:51", "remaining_time": "0:12:50"} +{"current_steps": 1203, "total_steps": 1235, "loss": 0.3413, "lr": 8.182296909035047e-08, "epoch": 4.870445344129554, "percentage": 97.41, "elapsed_time": "7:48:13", "remaining_time": "0:12:27"} +{"current_steps": 1204, "total_steps": 1235, "loss": 0.3573, "lr": 7.679216277384439e-08, "epoch": 4.874493927125506, "percentage": 97.49, "elapsed_time": "7:48:36", "remaining_time": "0:12:03"} +{"current_steps": 1205, "total_steps": 1235, "loss": 0.3393, "lr": 7.19206618963053e-08, "epoch": 4.8785425101214575, "percentage": 97.57, "elapsed_time": "7:48:59", "remaining_time": "0:11:40"} +{"current_steps": 1206, "total_steps": 1235, "loss": 0.3631, "lr": 6.720850541012347e-08, "epoch": 4.882591093117409, "percentage": 97.65, "elapsed_time": "7:49:21", "remaining_time": "0:11:17"} +{"current_steps": 1207, "total_steps": 1235, "loss": 0.3473, "lr": 6.265573099357714e-08, "epoch": 4.886639676113361, "percentage": 97.73, "elapsed_time": "7:49:45", "remaining_time": "0:10:53"} +{"current_steps": 1208, "total_steps": 1235, "loss": 0.3424, "lr": 5.826237505053067e-08, "epoch": 4.890688259109312, "percentage": 97.81, "elapsed_time": "7:50:07", "remaining_time": "0:10:30"} +{"current_steps": 1209, "total_steps": 1235, "loss": 0.3413, "lr": 5.4028472710137e-08, "epoch": 4.894736842105263, "percentage": 97.89, "elapsed_time": "7:50:31", "remaining_time": "0:10:07"} +{"current_steps": 1210, "total_steps": 1235, "loss": 0.3464, "lr": 4.9954057826571146e-08, "epoch": 4.898785425101215, "percentage": 97.98, "elapsed_time": "7:50:53", "remaining_time": "0:09:43"} +{"current_steps": 1211, "total_steps": 1235, "loss": 0.3451, "lr": 4.6039162978743776e-08, "epoch": 4.902834008097166, "percentage": 98.06, "elapsed_time": "7:51:17", "remaining_time": "0:09:20"} +{"current_steps": 1212, "total_steps": 1235, "loss": 0.3551, "lr": 4.228381947004812e-08, "epoch": 4.906882591093117, "percentage": 98.14, "elapsed_time": "7:51:40", "remaining_time": "0:08:57"} +{"current_steps": 1213, "total_steps": 1235, "loss": 0.3666, "lr": 3.868805732811343e-08, "epoch": 4.910931174089069, "percentage": 98.22, "elapsed_time": "7:52:04", "remaining_time": "0:08:33"} +{"current_steps": 1214, "total_steps": 1235, "loss": 0.3675, "lr": 3.525190530455636e-08, "epoch": 4.91497975708502, "percentage": 98.3, "elapsed_time": "7:52:27", "remaining_time": "0:08:10"} +{"current_steps": 1215, "total_steps": 1235, "loss": 0.3519, "lr": 3.197539087475887e-08, "epoch": 4.919028340080971, "percentage": 98.38, "elapsed_time": "7:52:49", "remaining_time": "0:07:46"} +{"current_steps": 1216, "total_steps": 1235, "loss": 0.3569, "lr": 2.8858540237641786e-08, "epoch": 4.923076923076923, "percentage": 98.46, "elapsed_time": "7:53:13", "remaining_time": "0:07:23"} +{"current_steps": 1217, "total_steps": 1235, "loss": 0.3439, "lr": 2.5901378315458247e-08, "epoch": 4.9271255060728745, "percentage": 98.54, "elapsed_time": "7:53:36", "remaining_time": "0:07:00"} +{"current_steps": 1218, "total_steps": 1235, "loss": 0.369, "lr": 2.3103928753598347e-08, "epoch": 4.931174089068826, "percentage": 98.62, "elapsed_time": "7:53:59", "remaining_time": "0:06:36"} +{"current_steps": 1219, "total_steps": 1235, "loss": 0.3478, "lr": 2.0466213920393718e-08, "epoch": 4.935222672064778, "percentage": 98.7, "elapsed_time": "7:54:21", "remaining_time": "0:06:13"} +{"current_steps": 1220, "total_steps": 1235, "loss": 0.3645, "lr": 1.7988254906942115e-08, "epoch": 4.939271255060729, "percentage": 98.79, "elapsed_time": "7:54:45", "remaining_time": "0:05:50"} +{"current_steps": 1221, "total_steps": 1235, "loss": 0.3702, "lr": 1.5670071526936447e-08, "epoch": 4.94331983805668, "percentage": 98.87, "elapsed_time": "7:55:08", "remaining_time": "0:05:26"} +{"current_steps": 1222, "total_steps": 1235, "loss": 0.3617, "lr": 1.3511682316509344e-08, "epoch": 4.947368421052632, "percentage": 98.95, "elapsed_time": "7:55:31", "remaining_time": "0:05:03"} +{"current_steps": 1223, "total_steps": 1235, "loss": 0.3642, "lr": 1.1513104534086605e-08, "epoch": 4.951417004048583, "percentage": 99.03, "elapsed_time": "7:55:53", "remaining_time": "0:04:40"} +{"current_steps": 1224, "total_steps": 1235, "loss": 0.3345, "lr": 9.67435416023843e-09, "epoch": 4.955465587044534, "percentage": 99.11, "elapsed_time": "7:56:16", "remaining_time": "0:04:16"} +{"current_steps": 1225, "total_steps": 1235, "loss": 0.3534, "lr": 7.995445897566178e-09, "epoch": 4.959514170040486, "percentage": 99.19, "elapsed_time": "7:56:38", "remaining_time": "0:03:53"} +{"current_steps": 1226, "total_steps": 1235, "loss": 0.3538, "lr": 6.476393170578021e-09, "epoch": 4.963562753036437, "percentage": 99.27, "elapsed_time": "7:57:02", "remaining_time": "0:03:30"} +{"current_steps": 1227, "total_steps": 1235, "loss": 0.383, "lr": 5.11720812557348e-09, "epoch": 4.967611336032388, "percentage": 99.35, "elapsed_time": "7:57:25", "remaining_time": "0:03:06"} +{"current_steps": 1228, "total_steps": 1235, "loss": 0.3391, "lr": 3.917901630563492e-09, "epoch": 4.97165991902834, "percentage": 99.43, "elapsed_time": "7:57:49", "remaining_time": "0:02:43"} +{"current_steps": 1229, "total_steps": 1235, "loss": 0.3758, "lr": 2.878483275170485e-09, "epoch": 4.9757085020242915, "percentage": 99.51, "elapsed_time": "7:58:12", "remaining_time": "0:02:20"} +{"current_steps": 1230, "total_steps": 1235, "loss": 0.3351, "lr": 1.998961370555108e-09, "epoch": 4.979757085020243, "percentage": 99.6, "elapsed_time": "7:58:35", "remaining_time": "0:01:56"} +{"current_steps": 1231, "total_steps": 1235, "loss": 0.3562, "lr": 1.2793429493518361e-09, "epoch": 4.983805668016195, "percentage": 99.68, "elapsed_time": "7:58:59", "remaining_time": "0:01:33"} +{"current_steps": 1232, "total_steps": 1235, "loss": 0.3503, "lr": 7.196337656112384e-10, "epoch": 4.987854251012146, "percentage": 99.76, "elapsed_time": "7:59:23", "remaining_time": "0:01:10"} +{"current_steps": 1233, "total_steps": 1235, "loss": 0.3646, "lr": 3.198382947511292e-10, "epoch": 4.991902834008097, "percentage": 99.84, "elapsed_time": "7:59:46", "remaining_time": "0:00:46"} +{"current_steps": 1234, "total_steps": 1235, "loss": 0.3765, "lr": 7.995973352770137e-11, "epoch": 4.995951417004049, "percentage": 99.92, "elapsed_time": "8:00:10", "remaining_time": "0:00:23"} +{"current_steps": 1235, "total_steps": 1235, "loss": 0.3403, "lr": 0.0, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "8:00:34", "remaining_time": "0:00:00"} +{"current_steps": 1235, "total_steps": 1235, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "8:03:26", "remaining_time": "0:00:00"} diff --git a/trainer_state.json b/trainer_state.json new file mode 100644 index 0000000..fe59a38 --- /dev/null +++ b/trainer_state.json @@ -0,0 +1,8687 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 5.0, + "eval_steps": 500, + "global_step": 1235, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.004048582995951417, + "grad_norm": 6.529969639004119, + "learning_rate": 3.2258064516129035e-07, + "loss": 1.0591, + "step": 1 + }, + { + "epoch": 0.008097165991902834, + "grad_norm": 6.6200958359971525, + "learning_rate": 6.451612903225807e-07, + "loss": 1.0685, + "step": 2 + }, + { + "epoch": 0.012145748987854251, + "grad_norm": 6.5053460954628495, + "learning_rate": 9.67741935483871e-07, + "loss": 1.0446, + "step": 3 + }, + { + "epoch": 0.016194331983805668, + "grad_norm": 6.38964653410593, + "learning_rate": 1.2903225806451614e-06, + "loss": 1.0575, + "step": 4 + }, + { + "epoch": 0.020242914979757085, + "grad_norm": 6.256048954955403, + "learning_rate": 1.6129032258064516e-06, + "loss": 1.0547, + "step": 5 + }, + { + "epoch": 0.024291497975708502, + "grad_norm": 5.906526094468779, + "learning_rate": 1.935483870967742e-06, + "loss": 1.0443, + "step": 6 + }, + { + "epoch": 0.02834008097165992, + "grad_norm": 4.720924779310831, + "learning_rate": 2.2580645161290324e-06, + "loss": 1.0039, + "step": 7 + }, + { + "epoch": 0.032388663967611336, + "grad_norm": 4.3557410458205155, + "learning_rate": 2.580645161290323e-06, + "loss": 1.004, + "step": 8 + }, + { + "epoch": 0.03643724696356275, + "grad_norm": 2.8932334090195897, + "learning_rate": 2.903225806451613e-06, + "loss": 0.9558, + "step": 9 + }, + { + "epoch": 0.04048582995951417, + "grad_norm": 2.652247270259386, + "learning_rate": 3.225806451612903e-06, + "loss": 0.9629, + "step": 10 + }, + { + "epoch": 0.044534412955465584, + "grad_norm": 2.545365253066352, + "learning_rate": 3.548387096774194e-06, + "loss": 0.9542, + "step": 11 + }, + { + "epoch": 0.048582995951417005, + "grad_norm": 3.9315528894192817, + "learning_rate": 3.870967741935484e-06, + "loss": 0.94, + "step": 12 + }, + { + "epoch": 0.05263157894736842, + "grad_norm": 4.137544437321004, + "learning_rate": 4.193548387096774e-06, + "loss": 0.9349, + "step": 13 + }, + { + "epoch": 0.05668016194331984, + "grad_norm": 3.9465378672538676, + "learning_rate": 4.516129032258065e-06, + "loss": 0.9312, + "step": 14 + }, + { + "epoch": 0.06072874493927125, + "grad_norm": 3.595489793720538, + "learning_rate": 4.838709677419355e-06, + "loss": 0.9129, + "step": 15 + }, + { + "epoch": 0.06477732793522267, + "grad_norm": 2.6397721210601084, + "learning_rate": 5.161290322580646e-06, + "loss": 0.8783, + "step": 16 + }, + { + "epoch": 0.06882591093117409, + "grad_norm": 2.4240178771196343, + "learning_rate": 5.483870967741935e-06, + "loss": 0.8682, + "step": 17 + }, + { + "epoch": 0.0728744939271255, + "grad_norm": 2.00999422861566, + "learning_rate": 5.806451612903226e-06, + "loss": 0.8575, + "step": 18 + }, + { + "epoch": 0.07692307692307693, + "grad_norm": 1.5223510919211352, + "learning_rate": 6.129032258064517e-06, + "loss": 0.8403, + "step": 19 + }, + { + "epoch": 0.08097165991902834, + "grad_norm": 1.189574399590261, + "learning_rate": 6.451612903225806e-06, + "loss": 0.795, + "step": 20 + }, + { + "epoch": 0.08502024291497975, + "grad_norm": 1.124160330311177, + "learning_rate": 6.774193548387097e-06, + "loss": 0.8068, + "step": 21 + }, + { + "epoch": 0.08906882591093117, + "grad_norm": 1.2321755393793086, + "learning_rate": 7.096774193548388e-06, + "loss": 0.8264, + "step": 22 + }, + { + "epoch": 0.0931174089068826, + "grad_norm": 1.1157221564859934, + "learning_rate": 7.4193548387096784e-06, + "loss": 0.7984, + "step": 23 + }, + { + "epoch": 0.09716599190283401, + "grad_norm": 0.9234055073791403, + "learning_rate": 7.741935483870968e-06, + "loss": 0.7919, + "step": 24 + }, + { + "epoch": 0.10121457489878542, + "grad_norm": 0.8824709909470099, + "learning_rate": 8.064516129032258e-06, + "loss": 0.7575, + "step": 25 + }, + { + "epoch": 0.10526315789473684, + "grad_norm": 0.8927990673095986, + "learning_rate": 8.387096774193549e-06, + "loss": 0.7722, + "step": 26 + }, + { + "epoch": 0.10931174089068826, + "grad_norm": 0.7904767128873359, + "learning_rate": 8.70967741935484e-06, + "loss": 0.7682, + "step": 27 + }, + { + "epoch": 0.11336032388663968, + "grad_norm": 0.7835737436161865, + "learning_rate": 9.03225806451613e-06, + "loss": 0.7439, + "step": 28 + }, + { + "epoch": 0.11740890688259109, + "grad_norm": 0.7039714072286063, + "learning_rate": 9.35483870967742e-06, + "loss": 0.7359, + "step": 29 + }, + { + "epoch": 0.1214574898785425, + "grad_norm": 0.742602582354179, + "learning_rate": 9.67741935483871e-06, + "loss": 0.7288, + "step": 30 + }, + { + "epoch": 0.12550607287449392, + "grad_norm": 0.6895474616730898, + "learning_rate": 1e-05, + "loss": 0.7433, + "step": 31 + }, + { + "epoch": 0.12955465587044535, + "grad_norm": 0.67546853744356, + "learning_rate": 1.0322580645161291e-05, + "loss": 0.715, + "step": 32 + }, + { + "epoch": 0.13360323886639677, + "grad_norm": 0.6837612229305043, + "learning_rate": 1.0645161290322582e-05, + "loss": 0.7312, + "step": 33 + }, + { + "epoch": 0.13765182186234817, + "grad_norm": 0.6563589423404679, + "learning_rate": 1.096774193548387e-05, + "loss": 0.7278, + "step": 34 + }, + { + "epoch": 0.1417004048582996, + "grad_norm": 0.6861089450244338, + "learning_rate": 1.1290322580645164e-05, + "loss": 0.7237, + "step": 35 + }, + { + "epoch": 0.145748987854251, + "grad_norm": 0.64416899060065, + "learning_rate": 1.1612903225806453e-05, + "loss": 0.7165, + "step": 36 + }, + { + "epoch": 0.14979757085020243, + "grad_norm": 0.6726397275319622, + "learning_rate": 1.1935483870967743e-05, + "loss": 0.6971, + "step": 37 + }, + { + "epoch": 0.15384615384615385, + "grad_norm": 0.6120205136061637, + "learning_rate": 1.2258064516129034e-05, + "loss": 0.7136, + "step": 38 + }, + { + "epoch": 0.15789473684210525, + "grad_norm": 0.5842112714653325, + "learning_rate": 1.2580645161290324e-05, + "loss": 0.7263, + "step": 39 + }, + { + "epoch": 0.16194331983805668, + "grad_norm": 0.5985131754938803, + "learning_rate": 1.2903225806451613e-05, + "loss": 0.7265, + "step": 40 + }, + { + "epoch": 0.1659919028340081, + "grad_norm": 0.5421734335942299, + "learning_rate": 1.3225806451612903e-05, + "loss": 0.7021, + "step": 41 + }, + { + "epoch": 0.1700404858299595, + "grad_norm": 0.5439477578841015, + "learning_rate": 1.3548387096774194e-05, + "loss": 0.7127, + "step": 42 + }, + { + "epoch": 0.17408906882591094, + "grad_norm": 0.548772122979161, + "learning_rate": 1.3870967741935486e-05, + "loss": 0.6885, + "step": 43 + }, + { + "epoch": 0.17813765182186234, + "grad_norm": 0.5438852285801518, + "learning_rate": 1.4193548387096776e-05, + "loss": 0.6976, + "step": 44 + }, + { + "epoch": 0.18218623481781376, + "grad_norm": 0.703789779018483, + "learning_rate": 1.4516129032258066e-05, + "loss": 0.6799, + "step": 45 + }, + { + "epoch": 0.1862348178137652, + "grad_norm": 0.5839323106634435, + "learning_rate": 1.4838709677419357e-05, + "loss": 0.6994, + "step": 46 + }, + { + "epoch": 0.1902834008097166, + "grad_norm": 0.5047233313587509, + "learning_rate": 1.5161290322580646e-05, + "loss": 0.6885, + "step": 47 + }, + { + "epoch": 0.19433198380566802, + "grad_norm": 0.5466473189578837, + "learning_rate": 1.5483870967741936e-05, + "loss": 0.6747, + "step": 48 + }, + { + "epoch": 0.19838056680161945, + "grad_norm": 0.5003352871369224, + "learning_rate": 1.5806451612903226e-05, + "loss": 0.6864, + "step": 49 + }, + { + "epoch": 0.20242914979757085, + "grad_norm": 0.6332807756583119, + "learning_rate": 1.6129032258064517e-05, + "loss": 0.6924, + "step": 50 + }, + { + "epoch": 0.20647773279352227, + "grad_norm": 0.6354224122058385, + "learning_rate": 1.6451612903225807e-05, + "loss": 0.7048, + "step": 51 + }, + { + "epoch": 0.21052631578947367, + "grad_norm": 0.6383184074404532, + "learning_rate": 1.6774193548387098e-05, + "loss": 0.6775, + "step": 52 + }, + { + "epoch": 0.2145748987854251, + "grad_norm": 0.6105784591765013, + "learning_rate": 1.7096774193548388e-05, + "loss": 0.6836, + "step": 53 + }, + { + "epoch": 0.21862348178137653, + "grad_norm": 0.7397161991819674, + "learning_rate": 1.741935483870968e-05, + "loss": 0.6806, + "step": 54 + }, + { + "epoch": 0.22267206477732793, + "grad_norm": 0.6293965991496899, + "learning_rate": 1.774193548387097e-05, + "loss": 0.6801, + "step": 55 + }, + { + "epoch": 0.22672064777327935, + "grad_norm": 0.6033220591385403, + "learning_rate": 1.806451612903226e-05, + "loss": 0.6763, + "step": 56 + }, + { + "epoch": 0.23076923076923078, + "grad_norm": 0.6757597984809728, + "learning_rate": 1.838709677419355e-05, + "loss": 0.6671, + "step": 57 + }, + { + "epoch": 0.23481781376518218, + "grad_norm": 0.6453830325096583, + "learning_rate": 1.870967741935484e-05, + "loss": 0.6653, + "step": 58 + }, + { + "epoch": 0.2388663967611336, + "grad_norm": 0.6320988356582008, + "learning_rate": 1.903225806451613e-05, + "loss": 0.6728, + "step": 59 + }, + { + "epoch": 0.242914979757085, + "grad_norm": 0.7455217279066642, + "learning_rate": 1.935483870967742e-05, + "loss": 0.6864, + "step": 60 + }, + { + "epoch": 0.24696356275303644, + "grad_norm": 0.6021375449643891, + "learning_rate": 1.967741935483871e-05, + "loss": 0.6658, + "step": 61 + }, + { + "epoch": 0.25101214574898784, + "grad_norm": 0.6516520040260566, + "learning_rate": 2e-05, + "loss": 0.6849, + "step": 62 + }, + { + "epoch": 0.2550607287449393, + "grad_norm": 0.7753318890823696, + "learning_rate": 2.0322580645161292e-05, + "loss": 0.6655, + "step": 63 + }, + { + "epoch": 0.2591093117408907, + "grad_norm": 0.866848128282218, + "learning_rate": 2.0645161290322582e-05, + "loss": 0.6771, + "step": 64 + }, + { + "epoch": 0.2631578947368421, + "grad_norm": 0.5729195151500129, + "learning_rate": 2.0967741935483873e-05, + "loss": 0.6453, + "step": 65 + }, + { + "epoch": 0.26720647773279355, + "grad_norm": 0.7500011761258638, + "learning_rate": 2.1290322580645163e-05, + "loss": 0.6723, + "step": 66 + }, + { + "epoch": 0.27125506072874495, + "grad_norm": 0.7930700971827921, + "learning_rate": 2.161290322580645e-05, + "loss": 0.6622, + "step": 67 + }, + { + "epoch": 0.27530364372469635, + "grad_norm": 0.7044288300845005, + "learning_rate": 2.193548387096774e-05, + "loss": 0.6652, + "step": 68 + }, + { + "epoch": 0.2793522267206478, + "grad_norm": 0.7470327200358218, + "learning_rate": 2.225806451612903e-05, + "loss": 0.6665, + "step": 69 + }, + { + "epoch": 0.2834008097165992, + "grad_norm": 0.8061535159957012, + "learning_rate": 2.2580645161290328e-05, + "loss": 0.6716, + "step": 70 + }, + { + "epoch": 0.2874493927125506, + "grad_norm": 0.7038774097264121, + "learning_rate": 2.2903225806451615e-05, + "loss": 0.6728, + "step": 71 + }, + { + "epoch": 0.291497975708502, + "grad_norm": 0.7066161590002146, + "learning_rate": 2.3225806451612906e-05, + "loss": 0.6559, + "step": 72 + }, + { + "epoch": 0.29554655870445345, + "grad_norm": 0.6054155989171657, + "learning_rate": 2.3548387096774196e-05, + "loss": 0.6538, + "step": 73 + }, + { + "epoch": 0.29959514170040485, + "grad_norm": 0.6915675088727053, + "learning_rate": 2.3870967741935486e-05, + "loss": 0.6485, + "step": 74 + }, + { + "epoch": 0.30364372469635625, + "grad_norm": 0.8360497101963237, + "learning_rate": 2.4193548387096777e-05, + "loss": 0.6642, + "step": 75 + }, + { + "epoch": 0.3076923076923077, + "grad_norm": 0.8600219267094722, + "learning_rate": 2.4516129032258067e-05, + "loss": 0.6621, + "step": 76 + }, + { + "epoch": 0.3117408906882591, + "grad_norm": 0.8595703863626754, + "learning_rate": 2.4838709677419358e-05, + "loss": 0.6592, + "step": 77 + }, + { + "epoch": 0.3157894736842105, + "grad_norm": 1.1595341999461948, + "learning_rate": 2.5161290322580648e-05, + "loss": 0.6716, + "step": 78 + }, + { + "epoch": 0.31983805668016196, + "grad_norm": 1.0409445503540686, + "learning_rate": 2.548387096774194e-05, + "loss": 0.6612, + "step": 79 + }, + { + "epoch": 0.32388663967611336, + "grad_norm": 1.2267989679211295, + "learning_rate": 2.5806451612903226e-05, + "loss": 0.661, + "step": 80 + }, + { + "epoch": 0.32793522267206476, + "grad_norm": 0.7779818541728512, + "learning_rate": 2.6129032258064516e-05, + "loss": 0.6682, + "step": 81 + }, + { + "epoch": 0.3319838056680162, + "grad_norm": 0.6786494700253207, + "learning_rate": 2.6451612903225806e-05, + "loss": 0.6401, + "step": 82 + }, + { + "epoch": 0.3360323886639676, + "grad_norm": 0.9364366485836457, + "learning_rate": 2.6774193548387097e-05, + "loss": 0.6528, + "step": 83 + }, + { + "epoch": 0.340080971659919, + "grad_norm": 0.9358927507972675, + "learning_rate": 2.7096774193548387e-05, + "loss": 0.6716, + "step": 84 + }, + { + "epoch": 0.3441295546558704, + "grad_norm": 1.186303936950258, + "learning_rate": 2.7419354838709678e-05, + "loss": 0.6498, + "step": 85 + }, + { + "epoch": 0.3481781376518219, + "grad_norm": 1.0176956447006573, + "learning_rate": 2.774193548387097e-05, + "loss": 0.6483, + "step": 86 + }, + { + "epoch": 0.3522267206477733, + "grad_norm": 0.763434015594322, + "learning_rate": 2.8064516129032262e-05, + "loss": 0.6478, + "step": 87 + }, + { + "epoch": 0.3562753036437247, + "grad_norm": 0.8412683277547806, + "learning_rate": 2.8387096774193552e-05, + "loss": 0.6637, + "step": 88 + }, + { + "epoch": 0.3603238866396761, + "grad_norm": 1.1471166103609722, + "learning_rate": 2.8709677419354843e-05, + "loss": 0.6422, + "step": 89 + }, + { + "epoch": 0.3643724696356275, + "grad_norm": 1.02560876253542, + "learning_rate": 2.9032258064516133e-05, + "loss": 0.6543, + "step": 90 + }, + { + "epoch": 0.3684210526315789, + "grad_norm": 1.0261130982502162, + "learning_rate": 2.9354838709677423e-05, + "loss": 0.6482, + "step": 91 + }, + { + "epoch": 0.3724696356275304, + "grad_norm": 0.9985680238163215, + "learning_rate": 2.9677419354838714e-05, + "loss": 0.6501, + "step": 92 + }, + { + "epoch": 0.3765182186234818, + "grad_norm": 0.822642203018212, + "learning_rate": 3.0000000000000004e-05, + "loss": 0.6552, + "step": 93 + }, + { + "epoch": 0.3805668016194332, + "grad_norm": 1.3385269411223348, + "learning_rate": 3.032258064516129e-05, + "loss": 0.6581, + "step": 94 + }, + { + "epoch": 0.38461538461538464, + "grad_norm": 1.0104061576274967, + "learning_rate": 3.0645161290322585e-05, + "loss": 0.6574, + "step": 95 + }, + { + "epoch": 0.38866396761133604, + "grad_norm": 1.395722260369119, + "learning_rate": 3.096774193548387e-05, + "loss": 0.6683, + "step": 96 + }, + { + "epoch": 0.39271255060728744, + "grad_norm": 0.7630998511082215, + "learning_rate": 3.1290322580645166e-05, + "loss": 0.6435, + "step": 97 + }, + { + "epoch": 0.3967611336032389, + "grad_norm": 0.9598538021255822, + "learning_rate": 3.161290322580645e-05, + "loss": 0.6502, + "step": 98 + }, + { + "epoch": 0.4008097165991903, + "grad_norm": 1.2624432100322756, + "learning_rate": 3.193548387096774e-05, + "loss": 0.6579, + "step": 99 + }, + { + "epoch": 0.4048582995951417, + "grad_norm": 1.3947492509385464, + "learning_rate": 3.2258064516129034e-05, + "loss": 0.6422, + "step": 100 + }, + { + "epoch": 0.4089068825910931, + "grad_norm": 0.7815112312968828, + "learning_rate": 3.258064516129033e-05, + "loss": 0.6481, + "step": 101 + }, + { + "epoch": 0.41295546558704455, + "grad_norm": 1.376172482674097, + "learning_rate": 3.2903225806451614e-05, + "loss": 0.6518, + "step": 102 + }, + { + "epoch": 0.41700404858299595, + "grad_norm": 0.9860394802734346, + "learning_rate": 3.322580645161291e-05, + "loss": 0.6502, + "step": 103 + }, + { + "epoch": 0.42105263157894735, + "grad_norm": 0.9483153291680856, + "learning_rate": 3.3548387096774195e-05, + "loss": 0.6305, + "step": 104 + }, + { + "epoch": 0.4251012145748988, + "grad_norm": 0.8395001349312757, + "learning_rate": 3.387096774193549e-05, + "loss": 0.6524, + "step": 105 + }, + { + "epoch": 0.4291497975708502, + "grad_norm": 1.217875542596544, + "learning_rate": 3.4193548387096776e-05, + "loss": 0.6257, + "step": 106 + }, + { + "epoch": 0.4331983805668016, + "grad_norm": 0.8987334812224276, + "learning_rate": 3.451612903225807e-05, + "loss": 0.6413, + "step": 107 + }, + { + "epoch": 0.43724696356275305, + "grad_norm": 0.9749608839246254, + "learning_rate": 3.483870967741936e-05, + "loss": 0.6672, + "step": 108 + }, + { + "epoch": 0.44129554655870445, + "grad_norm": 1.1130462256658686, + "learning_rate": 3.516129032258065e-05, + "loss": 0.6421, + "step": 109 + }, + { + "epoch": 0.44534412955465585, + "grad_norm": 1.0313733954709317, + "learning_rate": 3.548387096774194e-05, + "loss": 0.635, + "step": 110 + }, + { + "epoch": 0.4493927125506073, + "grad_norm": 1.3343313614801513, + "learning_rate": 3.5806451612903225e-05, + "loss": 0.6354, + "step": 111 + }, + { + "epoch": 0.4534412955465587, + "grad_norm": 0.9136566659216148, + "learning_rate": 3.612903225806452e-05, + "loss": 0.6434, + "step": 112 + }, + { + "epoch": 0.4574898785425101, + "grad_norm": 0.8559261120779332, + "learning_rate": 3.6451612903225805e-05, + "loss": 0.6371, + "step": 113 + }, + { + "epoch": 0.46153846153846156, + "grad_norm": 1.1620663232974304, + "learning_rate": 3.67741935483871e-05, + "loss": 0.6251, + "step": 114 + }, + { + "epoch": 0.46558704453441296, + "grad_norm": 0.9172092098695629, + "learning_rate": 3.7096774193548386e-05, + "loss": 0.6353, + "step": 115 + }, + { + "epoch": 0.46963562753036436, + "grad_norm": 0.817297456923834, + "learning_rate": 3.741935483870968e-05, + "loss": 0.644, + "step": 116 + }, + { + "epoch": 0.47368421052631576, + "grad_norm": 0.7972250031264954, + "learning_rate": 3.7741935483870974e-05, + "loss": 0.6488, + "step": 117 + }, + { + "epoch": 0.4777327935222672, + "grad_norm": 1.1227209164357583, + "learning_rate": 3.806451612903226e-05, + "loss": 0.6593, + "step": 118 + }, + { + "epoch": 0.4817813765182186, + "grad_norm": 0.9952477658398028, + "learning_rate": 3.8387096774193555e-05, + "loss": 0.6397, + "step": 119 + }, + { + "epoch": 0.48582995951417, + "grad_norm": 1.1809215504883686, + "learning_rate": 3.870967741935484e-05, + "loss": 0.6481, + "step": 120 + }, + { + "epoch": 0.4898785425101215, + "grad_norm": 1.438907188392669, + "learning_rate": 3.9032258064516135e-05, + "loss": 0.6309, + "step": 121 + }, + { + "epoch": 0.4939271255060729, + "grad_norm": 0.7663114723438924, + "learning_rate": 3.935483870967742e-05, + "loss": 0.6389, + "step": 122 + }, + { + "epoch": 0.4979757085020243, + "grad_norm": 1.5680395279138002, + "learning_rate": 3.9677419354838716e-05, + "loss": 0.6432, + "step": 123 + }, + { + "epoch": 0.5020242914979757, + "grad_norm": 1.0327193880827006, + "learning_rate": 4e-05, + "loss": 0.6348, + "step": 124 + }, + { + "epoch": 0.5060728744939271, + "grad_norm": 1.1687309323783, + "learning_rate": 3.9999920040266474e-05, + "loss": 0.638, + "step": 125 + }, + { + "epoch": 0.5101214574898786, + "grad_norm": 1.0910714606480205, + "learning_rate": 3.999968016170525e-05, + "loss": 0.6616, + "step": 126 + }, + { + "epoch": 0.5141700404858299, + "grad_norm": 1.1076017858087872, + "learning_rate": 3.9999280366234394e-05, + "loss": 0.6304, + "step": 127 + }, + { + "epoch": 0.5182186234817814, + "grad_norm": 0.9923133005646836, + "learning_rate": 3.999872065705065e-05, + "loss": 0.6288, + "step": 128 + }, + { + "epoch": 0.5222672064777328, + "grad_norm": 1.0804508855939996, + "learning_rate": 3.999800103862945e-05, + "loss": 0.6365, + "step": 129 + }, + { + "epoch": 0.5263157894736842, + "grad_norm": 0.817665032911421, + "learning_rate": 3.9997121516724834e-05, + "loss": 0.6314, + "step": 130 + }, + { + "epoch": 0.5303643724696356, + "grad_norm": 0.9352471916864006, + "learning_rate": 3.999608209836944e-05, + "loss": 0.6323, + "step": 131 + }, + { + "epoch": 0.5344129554655871, + "grad_norm": 0.8817695822294224, + "learning_rate": 3.999488279187443e-05, + "loss": 0.6424, + "step": 132 + }, + { + "epoch": 0.5384615384615384, + "grad_norm": 0.8755749602851766, + "learning_rate": 3.9993523606829425e-05, + "loss": 0.6364, + "step": 133 + }, + { + "epoch": 0.5425101214574899, + "grad_norm": 0.8934221664965026, + "learning_rate": 3.9992004554102435e-05, + "loss": 0.6324, + "step": 134 + }, + { + "epoch": 0.5465587044534413, + "grad_norm": 1.0782795203324302, + "learning_rate": 3.999032564583976e-05, + "loss": 0.6321, + "step": 135 + }, + { + "epoch": 0.5506072874493927, + "grad_norm": 1.1322382934999973, + "learning_rate": 3.998848689546591e-05, + "loss": 0.6235, + "step": 136 + }, + { + "epoch": 0.5546558704453441, + "grad_norm": 0.8422117252027796, + "learning_rate": 3.9986488317683496e-05, + "loss": 0.6497, + "step": 137 + }, + { + "epoch": 0.5587044534412956, + "grad_norm": 0.832426124213949, + "learning_rate": 3.9984329928473067e-05, + "loss": 0.6413, + "step": 138 + }, + { + "epoch": 0.562753036437247, + "grad_norm": 1.0340569952005274, + "learning_rate": 3.998201174509306e-05, + "loss": 0.6367, + "step": 139 + }, + { + "epoch": 0.5668016194331984, + "grad_norm": 0.8527185628226626, + "learning_rate": 3.997953378607961e-05, + "loss": 0.646, + "step": 140 + }, + { + "epoch": 0.5708502024291497, + "grad_norm": 0.9958832726645142, + "learning_rate": 3.9976896071246403e-05, + "loss": 0.6422, + "step": 141 + }, + { + "epoch": 0.5748987854251012, + "grad_norm": 1.2128829428930699, + "learning_rate": 3.997409862168454e-05, + "loss": 0.6372, + "step": 142 + }, + { + "epoch": 0.5789473684210527, + "grad_norm": 0.689582620288129, + "learning_rate": 3.997114145976237e-05, + "loss": 0.6338, + "step": 143 + }, + { + "epoch": 0.582995951417004, + "grad_norm": 1.062778190567828, + "learning_rate": 3.9968024609125245e-05, + "loss": 0.6401, + "step": 144 + }, + { + "epoch": 0.5870445344129555, + "grad_norm": 0.90248862633625, + "learning_rate": 3.996474809469545e-05, + "loss": 0.6324, + "step": 145 + }, + { + "epoch": 0.5910931174089069, + "grad_norm": 1.043632473165674, + "learning_rate": 3.996131194267189e-05, + "loss": 0.638, + "step": 146 + }, + { + "epoch": 0.5951417004048583, + "grad_norm": 0.7850950492848126, + "learning_rate": 3.995771618052995e-05, + "loss": 0.6395, + "step": 147 + }, + { + "epoch": 0.5991902834008097, + "grad_norm": 0.7894320986198138, + "learning_rate": 3.9953960837021256e-05, + "loss": 0.6326, + "step": 148 + }, + { + "epoch": 0.6032388663967612, + "grad_norm": 0.803501288869217, + "learning_rate": 3.995004594217343e-05, + "loss": 0.6211, + "step": 149 + }, + { + "epoch": 0.6072874493927125, + "grad_norm": 0.9247824586670753, + "learning_rate": 3.994597152728987e-05, + "loss": 0.6295, + "step": 150 + }, + { + "epoch": 0.611336032388664, + "grad_norm": 0.8989681645653814, + "learning_rate": 3.994173762494947e-05, + "loss": 0.6443, + "step": 151 + }, + { + "epoch": 0.6153846153846154, + "grad_norm": 0.722741778431614, + "learning_rate": 3.9937344269006424e-05, + "loss": 0.6322, + "step": 152 + }, + { + "epoch": 0.6194331983805668, + "grad_norm": 0.7436875364196052, + "learning_rate": 3.993279149458988e-05, + "loss": 0.6451, + "step": 153 + }, + { + "epoch": 0.6234817813765182, + "grad_norm": 0.7578110975199271, + "learning_rate": 3.9928079338103695e-05, + "loss": 0.6351, + "step": 154 + }, + { + "epoch": 0.6275303643724697, + "grad_norm": 0.7050694314401702, + "learning_rate": 3.992320783722616e-05, + "loss": 0.6286, + "step": 155 + }, + { + "epoch": 0.631578947368421, + "grad_norm": 0.7067647872750286, + "learning_rate": 3.991817703090965e-05, + "loss": 0.6463, + "step": 156 + }, + { + "epoch": 0.6356275303643725, + "grad_norm": 0.983934515966914, + "learning_rate": 3.991298695938038e-05, + "loss": 0.6305, + "step": 157 + }, + { + "epoch": 0.6396761133603239, + "grad_norm": 0.7954101351871492, + "learning_rate": 3.9907637664138e-05, + "loss": 0.6347, + "step": 158 + }, + { + "epoch": 0.6437246963562753, + "grad_norm": 0.775081487114188, + "learning_rate": 3.990212918795534e-05, + "loss": 0.6328, + "step": 159 + }, + { + "epoch": 0.6477732793522267, + "grad_norm": 1.5872758288659552, + "learning_rate": 3.9896461574878036e-05, + "loss": 0.6487, + "step": 160 + }, + { + "epoch": 0.6518218623481782, + "grad_norm": 0.7168847242793819, + "learning_rate": 3.989063487022416e-05, + "loss": 0.6371, + "step": 161 + }, + { + "epoch": 0.6558704453441295, + "grad_norm": 1.6134037960682746, + "learning_rate": 3.9884649120583903e-05, + "loss": 0.6339, + "step": 162 + }, + { + "epoch": 0.659919028340081, + "grad_norm": 0.9904786856875362, + "learning_rate": 3.987850437381915e-05, + "loss": 0.6167, + "step": 163 + }, + { + "epoch": 0.6639676113360324, + "grad_norm": 1.8512232041435623, + "learning_rate": 3.987220067906313e-05, + "loss": 0.6282, + "step": 164 + }, + { + "epoch": 0.6680161943319838, + "grad_norm": 1.8384581741287656, + "learning_rate": 3.986573808672002e-05, + "loss": 0.6395, + "step": 165 + }, + { + "epoch": 0.6720647773279352, + "grad_norm": 0.8481826015397634, + "learning_rate": 3.9859116648464534e-05, + "loss": 0.6232, + "step": 166 + }, + { + "epoch": 0.6761133603238867, + "grad_norm": 1.0936447673758132, + "learning_rate": 3.985233641724152e-05, + "loss": 0.6275, + "step": 167 + }, + { + "epoch": 0.680161943319838, + "grad_norm": 0.7977314365370172, + "learning_rate": 3.984539744726554e-05, + "loss": 0.6373, + "step": 168 + }, + { + "epoch": 0.6842105263157895, + "grad_norm": 0.9136182673626502, + "learning_rate": 3.983829979402038e-05, + "loss": 0.6088, + "step": 169 + }, + { + "epoch": 0.6882591093117408, + "grad_norm": 0.8314997365759503, + "learning_rate": 3.983104351425871e-05, + "loss": 0.6277, + "step": 170 + }, + { + "epoch": 0.6923076923076923, + "grad_norm": 1.044219320494823, + "learning_rate": 3.982362866600154e-05, + "loss": 0.6312, + "step": 171 + }, + { + "epoch": 0.6963562753036437, + "grad_norm": 0.700018469077164, + "learning_rate": 3.9816055308537806e-05, + "loss": 0.6408, + "step": 172 + }, + { + "epoch": 0.7004048582995951, + "grad_norm": 1.1693680118216576, + "learning_rate": 3.980832350242388e-05, + "loss": 0.6228, + "step": 173 + }, + { + "epoch": 0.7044534412955465, + "grad_norm": 0.6002979966906169, + "learning_rate": 3.980043330948306e-05, + "loss": 0.6116, + "step": 174 + }, + { + "epoch": 0.708502024291498, + "grad_norm": 1.0373869288521915, + "learning_rate": 3.9792384792805124e-05, + "loss": 0.6232, + "step": 175 + }, + { + "epoch": 0.7125506072874493, + "grad_norm": 0.6923956546670341, + "learning_rate": 3.978417801674579e-05, + "loss": 0.6192, + "step": 176 + }, + { + "epoch": 0.7165991902834008, + "grad_norm": 0.7859532332776078, + "learning_rate": 3.9775813046926244e-05, + "loss": 0.6183, + "step": 177 + }, + { + "epoch": 0.7206477732793523, + "grad_norm": 0.707810864869097, + "learning_rate": 3.976728995023254e-05, + "loss": 0.6072, + "step": 178 + }, + { + "epoch": 0.7246963562753036, + "grad_norm": 0.620891261793413, + "learning_rate": 3.975860879481514e-05, + "loss": 0.6153, + "step": 179 + }, + { + "epoch": 0.728744939271255, + "grad_norm": 0.651372927484864, + "learning_rate": 3.974976965008833e-05, + "loss": 0.6368, + "step": 180 + }, + { + "epoch": 0.7327935222672065, + "grad_norm": 0.47855093913379376, + "learning_rate": 3.9740772586729674e-05, + "loss": 0.6107, + "step": 181 + }, + { + "epoch": 0.7368421052631579, + "grad_norm": 0.731646773128479, + "learning_rate": 3.973161767667946e-05, + "loss": 0.6216, + "step": 182 + }, + { + "epoch": 0.7408906882591093, + "grad_norm": 0.5982659171536929, + "learning_rate": 3.972230499314009e-05, + "loss": 0.6309, + "step": 183 + }, + { + "epoch": 0.7449392712550608, + "grad_norm": 0.5151942725007864, + "learning_rate": 3.9712834610575545e-05, + "loss": 0.6123, + "step": 184 + }, + { + "epoch": 0.7489878542510121, + "grad_norm": 0.5892170734133515, + "learning_rate": 3.9703206604710746e-05, + "loss": 0.6106, + "step": 185 + }, + { + "epoch": 0.7530364372469636, + "grad_norm": 0.4537942669553407, + "learning_rate": 3.969342105253098e-05, + "loss": 0.6229, + "step": 186 + }, + { + "epoch": 0.757085020242915, + "grad_norm": 0.5616845843720286, + "learning_rate": 3.9683478032281246e-05, + "loss": 0.6015, + "step": 187 + }, + { + "epoch": 0.7611336032388664, + "grad_norm": 0.4466693217963082, + "learning_rate": 3.967337762346568e-05, + "loss": 0.6124, + "step": 188 + }, + { + "epoch": 0.7651821862348178, + "grad_norm": 0.5419606067309186, + "learning_rate": 3.9663119906846885e-05, + "loss": 0.6182, + "step": 189 + }, + { + "epoch": 0.7692307692307693, + "grad_norm": 0.516175412259924, + "learning_rate": 3.965270496444528e-05, + "loss": 0.6229, + "step": 190 + }, + { + "epoch": 0.7732793522267206, + "grad_norm": 0.4996499636275476, + "learning_rate": 3.9642132879538465e-05, + "loss": 0.6182, + "step": 191 + }, + { + "epoch": 0.7773279352226721, + "grad_norm": 0.46417953170161513, + "learning_rate": 3.9631403736660566e-05, + "loss": 0.6093, + "step": 192 + }, + { + "epoch": 0.7813765182186235, + "grad_norm": 0.5342907677014899, + "learning_rate": 3.962051762160151e-05, + "loss": 0.6153, + "step": 193 + }, + { + "epoch": 0.7854251012145749, + "grad_norm": 0.5001495397084043, + "learning_rate": 3.960947462140638e-05, + "loss": 0.6135, + "step": 194 + }, + { + "epoch": 0.7894736842105263, + "grad_norm": 0.5729588664989923, + "learning_rate": 3.959827482437472e-05, + "loss": 0.616, + "step": 195 + }, + { + "epoch": 0.7935222672064778, + "grad_norm": 0.4419488962650638, + "learning_rate": 3.958691832005981e-05, + "loss": 0.6284, + "step": 196 + }, + { + "epoch": 0.7975708502024291, + "grad_norm": 0.4486218672121873, + "learning_rate": 3.9575405199267944e-05, + "loss": 0.6242, + "step": 197 + }, + { + "epoch": 0.8016194331983806, + "grad_norm": 0.43348975514551746, + "learning_rate": 3.956373555405774e-05, + "loss": 0.617, + "step": 198 + }, + { + "epoch": 0.805668016194332, + "grad_norm": 0.48273858803181113, + "learning_rate": 3.955190947773937e-05, + "loss": 0.6241, + "step": 199 + }, + { + "epoch": 0.8097165991902834, + "grad_norm": 0.4424487924793021, + "learning_rate": 3.9539927064873824e-05, + "loss": 0.6196, + "step": 200 + }, + { + "epoch": 0.8137651821862348, + "grad_norm": 0.5422773138347089, + "learning_rate": 3.952778841127214e-05, + "loss": 0.6354, + "step": 201 + }, + { + "epoch": 0.8178137651821862, + "grad_norm": 0.42729713498861527, + "learning_rate": 3.95154936139947e-05, + "loss": 0.6195, + "step": 202 + }, + { + "epoch": 0.8218623481781376, + "grad_norm": 0.5091026290897528, + "learning_rate": 3.950304277135034e-05, + "loss": 0.6086, + "step": 203 + }, + { + "epoch": 0.8259109311740891, + "grad_norm": 0.48614170839755616, + "learning_rate": 3.94904359828957e-05, + "loss": 0.6229, + "step": 204 + }, + { + "epoch": 0.8299595141700404, + "grad_norm": 0.42978490241726597, + "learning_rate": 3.94776733494343e-05, + "loss": 0.6165, + "step": 205 + }, + { + "epoch": 0.8340080971659919, + "grad_norm": 0.4414966377823553, + "learning_rate": 3.9464754973015826e-05, + "loss": 0.6148, + "step": 206 + }, + { + "epoch": 0.8380566801619433, + "grad_norm": 0.42144526997964776, + "learning_rate": 3.9451680956935275e-05, + "loss": 0.6282, + "step": 207 + }, + { + "epoch": 0.8421052631578947, + "grad_norm": 0.4971978379430151, + "learning_rate": 3.943845140573213e-05, + "loss": 0.6183, + "step": 208 + }, + { + "epoch": 0.8461538461538461, + "grad_norm": 0.4397336850109413, + "learning_rate": 3.942506642518952e-05, + "loss": 0.6182, + "step": 209 + }, + { + "epoch": 0.8502024291497976, + "grad_norm": 0.4259875817327147, + "learning_rate": 3.9411526122333396e-05, + "loss": 0.6043, + "step": 210 + }, + { + "epoch": 0.854251012145749, + "grad_norm": 0.5635474056854293, + "learning_rate": 3.939783060543167e-05, + "loss": 0.6301, + "step": 211 + }, + { + "epoch": 0.8582995951417004, + "grad_norm": 0.5603256300857928, + "learning_rate": 3.938397998399333e-05, + "loss": 0.6092, + "step": 212 + }, + { + "epoch": 0.8623481781376519, + "grad_norm": 0.44306757287931325, + "learning_rate": 3.936997436876756e-05, + "loss": 0.609, + "step": 213 + }, + { + "epoch": 0.8663967611336032, + "grad_norm": 0.4364476799153564, + "learning_rate": 3.935581387174289e-05, + "loss": 0.6085, + "step": 214 + }, + { + "epoch": 0.8704453441295547, + "grad_norm": 0.5045660091969703, + "learning_rate": 3.9341498606146295e-05, + "loss": 0.6242, + "step": 215 + }, + { + "epoch": 0.8744939271255061, + "grad_norm": 0.5647741955357021, + "learning_rate": 3.932702868644224e-05, + "loss": 0.6042, + "step": 216 + }, + { + "epoch": 0.8785425101214575, + "grad_norm": 0.4570840163078956, + "learning_rate": 3.931240422833181e-05, + "loss": 0.6344, + "step": 217 + }, + { + "epoch": 0.8825910931174089, + "grad_norm": 0.5370484336906498, + "learning_rate": 3.9297625348751806e-05, + "loss": 0.6313, + "step": 218 + }, + { + "epoch": 0.8866396761133604, + "grad_norm": 0.713468321749162, + "learning_rate": 3.9282692165873744e-05, + "loss": 0.6287, + "step": 219 + }, + { + "epoch": 0.8906882591093117, + "grad_norm": 0.7233019925145787, + "learning_rate": 3.9267604799102945e-05, + "loss": 0.62, + "step": 220 + }, + { + "epoch": 0.8947368421052632, + "grad_norm": 0.5684226820308063, + "learning_rate": 3.9252363369077615e-05, + "loss": 0.6062, + "step": 221 + }, + { + "epoch": 0.8987854251012146, + "grad_norm": 0.47880428862025937, + "learning_rate": 3.9236967997667796e-05, + "loss": 0.6211, + "step": 222 + }, + { + "epoch": 0.902834008097166, + "grad_norm": 0.7613900856575858, + "learning_rate": 3.9221418807974496e-05, + "loss": 0.6253, + "step": 223 + }, + { + "epoch": 0.9068825910931174, + "grad_norm": 0.8939981732774428, + "learning_rate": 3.92057159243286e-05, + "loss": 0.5996, + "step": 224 + }, + { + "epoch": 0.9109311740890689, + "grad_norm": 0.6481498236160634, + "learning_rate": 3.9189859472289956e-05, + "loss": 0.615, + "step": 225 + }, + { + "epoch": 0.9149797570850202, + "grad_norm": 0.4572178581636744, + "learning_rate": 3.9173849578646324e-05, + "loss": 0.6171, + "step": 226 + }, + { + "epoch": 0.9190283400809717, + "grad_norm": 0.6300277681213433, + "learning_rate": 3.9157686371412395e-05, + "loss": 0.6078, + "step": 227 + }, + { + "epoch": 0.9230769230769231, + "grad_norm": 0.5861102168625972, + "learning_rate": 3.914136997982874e-05, + "loss": 0.5878, + "step": 228 + }, + { + "epoch": 0.9271255060728745, + "grad_norm": 0.6130034914826623, + "learning_rate": 3.912490053436079e-05, + "loss": 0.6049, + "step": 229 + }, + { + "epoch": 0.9311740890688259, + "grad_norm": 0.49515242299378187, + "learning_rate": 3.9108278166697805e-05, + "loss": 0.6119, + "step": 230 + }, + { + "epoch": 0.9352226720647774, + "grad_norm": 0.597966386055594, + "learning_rate": 3.909150300975178e-05, + "loss": 0.5956, + "step": 231 + }, + { + "epoch": 0.9392712550607287, + "grad_norm": 0.55660854181991, + "learning_rate": 3.907457519765642e-05, + "loss": 0.6237, + "step": 232 + }, + { + "epoch": 0.9433198380566802, + "grad_norm": 0.5553598038284859, + "learning_rate": 3.905749486576607e-05, + "loss": 0.6038, + "step": 233 + }, + { + "epoch": 0.9473684210526315, + "grad_norm": 0.5471646390468593, + "learning_rate": 3.90402621506546e-05, + "loss": 0.6098, + "step": 234 + }, + { + "epoch": 0.951417004048583, + "grad_norm": 0.5513647965488957, + "learning_rate": 3.902287719011435e-05, + "loss": 0.6132, + "step": 235 + }, + { + "epoch": 0.9554655870445344, + "grad_norm": 0.5875164911765222, + "learning_rate": 3.900534012315499e-05, + "loss": 0.6143, + "step": 236 + }, + { + "epoch": 0.9595141700404858, + "grad_norm": 0.6352542152027957, + "learning_rate": 3.8987651090002454e-05, + "loss": 0.6078, + "step": 237 + }, + { + "epoch": 0.9635627530364372, + "grad_norm": 0.5679110920722806, + "learning_rate": 3.896981023209777e-05, + "loss": 0.626, + "step": 238 + }, + { + "epoch": 0.9676113360323887, + "grad_norm": 0.7078123352220793, + "learning_rate": 3.8951817692095966e-05, + "loss": 0.6116, + "step": 239 + }, + { + "epoch": 0.97165991902834, + "grad_norm": 0.481187098076771, + "learning_rate": 3.893367361386491e-05, + "loss": 0.6156, + "step": 240 + }, + { + "epoch": 0.9757085020242915, + "grad_norm": 0.5952843121024332, + "learning_rate": 3.891537814248417e-05, + "loss": 0.6068, + "step": 241 + }, + { + "epoch": 0.979757085020243, + "grad_norm": 0.5998410954147507, + "learning_rate": 3.889693142424384e-05, + "loss": 0.6081, + "step": 242 + }, + { + "epoch": 0.9838056680161943, + "grad_norm": 0.5469912261406582, + "learning_rate": 3.8878333606643405e-05, + "loss": 0.6124, + "step": 243 + }, + { + "epoch": 0.9878542510121457, + "grad_norm": 0.4684319128726047, + "learning_rate": 3.885958483839049e-05, + "loss": 0.6111, + "step": 244 + }, + { + "epoch": 0.9919028340080972, + "grad_norm": 0.455722128318724, + "learning_rate": 3.8840685269399786e-05, + "loss": 0.6314, + "step": 245 + }, + { + "epoch": 0.9959514170040485, + "grad_norm": 0.5133103364417629, + "learning_rate": 3.882163505079171e-05, + "loss": 0.6119, + "step": 246 + }, + { + "epoch": 1.0, + "grad_norm": 0.5734870359919972, + "learning_rate": 3.880243433489132e-05, + "loss": 0.5973, + "step": 247 + }, + { + "epoch": 1.0040485829959513, + "grad_norm": 0.540210858366143, + "learning_rate": 3.878308327522702e-05, + "loss": 0.5576, + "step": 248 + }, + { + "epoch": 1.008097165991903, + "grad_norm": 0.5227357169726952, + "learning_rate": 3.876358202652936e-05, + "loss": 0.5447, + "step": 249 + }, + { + "epoch": 1.0121457489878543, + "grad_norm": 0.7520944057826915, + "learning_rate": 3.8743930744729835e-05, + "loss": 0.5751, + "step": 250 + }, + { + "epoch": 1.0161943319838056, + "grad_norm": 0.540377666500093, + "learning_rate": 3.8724129586959535e-05, + "loss": 0.5575, + "step": 251 + }, + { + "epoch": 1.0202429149797572, + "grad_norm": 0.607476450642687, + "learning_rate": 3.870417871154801e-05, + "loss": 0.549, + "step": 252 + }, + { + "epoch": 1.0242914979757085, + "grad_norm": 0.5392363836243653, + "learning_rate": 3.868407827802192e-05, + "loss": 0.5483, + "step": 253 + }, + { + "epoch": 1.0283400809716599, + "grad_norm": 0.5395653224036908, + "learning_rate": 3.8663828447103804e-05, + "loss": 0.5558, + "step": 254 + }, + { + "epoch": 1.0323886639676114, + "grad_norm": 0.6204120058255576, + "learning_rate": 3.8643429380710765e-05, + "loss": 0.5571, + "step": 255 + }, + { + "epoch": 1.0364372469635628, + "grad_norm": 0.48328284319753095, + "learning_rate": 3.862288124195319e-05, + "loss": 0.5507, + "step": 256 + }, + { + "epoch": 1.040485829959514, + "grad_norm": 0.5189758746634813, + "learning_rate": 3.8602184195133464e-05, + "loss": 0.56, + "step": 257 + }, + { + "epoch": 1.0445344129554657, + "grad_norm": 0.5111870246043166, + "learning_rate": 3.8581338405744604e-05, + "loss": 0.5328, + "step": 258 + }, + { + "epoch": 1.048582995951417, + "grad_norm": 0.5080575325509256, + "learning_rate": 3.8560344040468996e-05, + "loss": 0.5478, + "step": 259 + }, + { + "epoch": 1.0526315789473684, + "grad_norm": 0.5095334983196335, + "learning_rate": 3.853920126717703e-05, + "loss": 0.5457, + "step": 260 + }, + { + "epoch": 1.05668016194332, + "grad_norm": 0.507676212117483, + "learning_rate": 3.851791025492574e-05, + "loss": 0.5674, + "step": 261 + }, + { + "epoch": 1.0607287449392713, + "grad_norm": 0.5191765008859061, + "learning_rate": 3.8496471173957515e-05, + "loss": 0.5565, + "step": 262 + }, + { + "epoch": 1.0647773279352226, + "grad_norm": 0.4282035210013262, + "learning_rate": 3.847488419569866e-05, + "loss": 0.5518, + "step": 263 + }, + { + "epoch": 1.0688259109311742, + "grad_norm": 0.4889287480748198, + "learning_rate": 3.8453149492758077e-05, + "loss": 0.5296, + "step": 264 + }, + { + "epoch": 1.0728744939271255, + "grad_norm": 0.47003278405863397, + "learning_rate": 3.8431267238925886e-05, + "loss": 0.553, + "step": 265 + }, + { + "epoch": 1.0769230769230769, + "grad_norm": 0.5036742644253677, + "learning_rate": 3.840923760917199e-05, + "loss": 0.546, + "step": 266 + }, + { + "epoch": 1.0809716599190284, + "grad_norm": 0.6419475051987283, + "learning_rate": 3.838706077964473e-05, + "loss": 0.5558, + "step": 267 + }, + { + "epoch": 1.0850202429149798, + "grad_norm": 0.4399528869308145, + "learning_rate": 3.836473692766944e-05, + "loss": 0.5435, + "step": 268 + }, + { + "epoch": 1.0890688259109311, + "grad_norm": 0.4231051807662026, + "learning_rate": 3.834226623174705e-05, + "loss": 0.5594, + "step": 269 + }, + { + "epoch": 1.0931174089068827, + "grad_norm": 0.5069959107564458, + "learning_rate": 3.831964887155264e-05, + "loss": 0.55, + "step": 270 + }, + { + "epoch": 1.097165991902834, + "grad_norm": 0.4453717423833374, + "learning_rate": 3.829688502793403e-05, + "loss": 0.5395, + "step": 271 + }, + { + "epoch": 1.1012145748987854, + "grad_norm": 0.6655348812599078, + "learning_rate": 3.827397488291029e-05, + "loss": 0.5651, + "step": 272 + }, + { + "epoch": 1.1052631578947367, + "grad_norm": 0.5010083669051043, + "learning_rate": 3.8250918619670343e-05, + "loss": 0.5547, + "step": 273 + }, + { + "epoch": 1.1093117408906883, + "grad_norm": 0.519276120776747, + "learning_rate": 3.822771642257145e-05, + "loss": 0.5585, + "step": 274 + }, + { + "epoch": 1.1133603238866396, + "grad_norm": 0.5029795532137715, + "learning_rate": 3.820436847713776e-05, + "loss": 0.5588, + "step": 275 + }, + { + "epoch": 1.117408906882591, + "grad_norm": 0.5002262377924468, + "learning_rate": 3.8180874970058826e-05, + "loss": 0.5429, + "step": 276 + }, + { + "epoch": 1.1214574898785425, + "grad_norm": 0.5680291049643177, + "learning_rate": 3.8157236089188103e-05, + "loss": 0.5617, + "step": 277 + }, + { + "epoch": 1.125506072874494, + "grad_norm": 0.4702917372790098, + "learning_rate": 3.813345202354145e-05, + "loss": 0.5435, + "step": 278 + }, + { + "epoch": 1.1295546558704452, + "grad_norm": 0.5847386721530332, + "learning_rate": 3.810952296329563e-05, + "loss": 0.5556, + "step": 279 + }, + { + "epoch": 1.1336032388663968, + "grad_norm": 0.4393713600650091, + "learning_rate": 3.808544909978676e-05, + "loss": 0.5508, + "step": 280 + }, + { + "epoch": 1.1376518218623481, + "grad_norm": 0.5808942464909159, + "learning_rate": 3.806123062550882e-05, + "loss": 0.5498, + "step": 281 + }, + { + "epoch": 1.1417004048582995, + "grad_norm": 0.4993187940081679, + "learning_rate": 3.803686773411208e-05, + "loss": 0.5475, + "step": 282 + }, + { + "epoch": 1.145748987854251, + "grad_norm": 0.5509555642971127, + "learning_rate": 3.801236062040158e-05, + "loss": 0.5521, + "step": 283 + }, + { + "epoch": 1.1497975708502024, + "grad_norm": 0.6525608738472736, + "learning_rate": 3.798770948033553e-05, + "loss": 0.5354, + "step": 284 + }, + { + "epoch": 1.1538461538461537, + "grad_norm": 0.5127217866220706, + "learning_rate": 3.796291451102381e-05, + "loss": 0.5496, + "step": 285 + }, + { + "epoch": 1.1578947368421053, + "grad_norm": 0.45509269290060966, + "learning_rate": 3.793797591072631e-05, + "loss": 0.5485, + "step": 286 + }, + { + "epoch": 1.1619433198380567, + "grad_norm": 0.4826078903938804, + "learning_rate": 3.791289387885144e-05, + "loss": 0.5614, + "step": 287 + }, + { + "epoch": 1.165991902834008, + "grad_norm": 0.6419715492761251, + "learning_rate": 3.788766861595443e-05, + "loss": 0.5398, + "step": 288 + }, + { + "epoch": 1.1700404858299596, + "grad_norm": 0.6379950497762314, + "learning_rate": 3.7862300323735835e-05, + "loss": 0.5482, + "step": 289 + }, + { + "epoch": 1.174089068825911, + "grad_norm": 0.5062083950047841, + "learning_rate": 3.783678920503983e-05, + "loss": 0.5643, + "step": 290 + }, + { + "epoch": 1.1781376518218623, + "grad_norm": 0.6625968553598032, + "learning_rate": 3.781113546385265e-05, + "loss": 0.5786, + "step": 291 + }, + { + "epoch": 1.1821862348178138, + "grad_norm": 0.4994277022519586, + "learning_rate": 3.7785339305300916e-05, + "loss": 0.5533, + "step": 292 + }, + { + "epoch": 1.1862348178137652, + "grad_norm": 0.4819023491870224, + "learning_rate": 3.7759400935650025e-05, + "loss": 0.553, + "step": 293 + }, + { + "epoch": 1.1902834008097165, + "grad_norm": 0.5441594571533597, + "learning_rate": 3.77333205623025e-05, + "loss": 0.5337, + "step": 294 + }, + { + "epoch": 1.194331983805668, + "grad_norm": 0.4895437341365659, + "learning_rate": 3.7707098393796295e-05, + "loss": 0.5469, + "step": 295 + }, + { + "epoch": 1.1983805668016194, + "grad_norm": 0.4865308090361683, + "learning_rate": 3.7680734639803185e-05, + "loss": 0.5497, + "step": 296 + }, + { + "epoch": 1.2024291497975708, + "grad_norm": 0.5864893603557435, + "learning_rate": 3.765422951112704e-05, + "loss": 0.5628, + "step": 297 + }, + { + "epoch": 1.2064777327935223, + "grad_norm": 0.591303872390734, + "learning_rate": 3.762758321970216e-05, + "loss": 0.5549, + "step": 298 + }, + { + "epoch": 1.2105263157894737, + "grad_norm": 0.53310021325941, + "learning_rate": 3.7600795978591584e-05, + "loss": 0.5493, + "step": 299 + }, + { + "epoch": 1.214574898785425, + "grad_norm": 0.5224984563250727, + "learning_rate": 3.757386800198538e-05, + "loss": 0.562, + "step": 300 + }, + { + "epoch": 1.2186234817813766, + "grad_norm": 0.5507639513338117, + "learning_rate": 3.7546799505198925e-05, + "loss": 0.5597, + "step": 301 + }, + { + "epoch": 1.222672064777328, + "grad_norm": 0.4517072122304285, + "learning_rate": 3.7519590704671197e-05, + "loss": 0.5524, + "step": 302 + }, + { + "epoch": 1.2267206477732793, + "grad_norm": 0.5586001959862958, + "learning_rate": 3.749224181796305e-05, + "loss": 0.5554, + "step": 303 + }, + { + "epoch": 1.2307692307692308, + "grad_norm": 0.5335778652193891, + "learning_rate": 3.746475306375545e-05, + "loss": 0.562, + "step": 304 + }, + { + "epoch": 1.2348178137651822, + "grad_norm": 0.611563231236552, + "learning_rate": 3.743712466184774e-05, + "loss": 0.5567, + "step": 305 + }, + { + "epoch": 1.2388663967611335, + "grad_norm": 0.44935695850558155, + "learning_rate": 3.7409356833155885e-05, + "loss": 0.5658, + "step": 306 + }, + { + "epoch": 1.242914979757085, + "grad_norm": 0.6270737796700282, + "learning_rate": 3.73814497997107e-05, + "loss": 0.5548, + "step": 307 + }, + { + "epoch": 1.2469635627530364, + "grad_norm": 0.7223834929063898, + "learning_rate": 3.7353403784656095e-05, + "loss": 0.5536, + "step": 308 + }, + { + "epoch": 1.2510121457489878, + "grad_norm": 0.6307477544218978, + "learning_rate": 3.732521901224724e-05, + "loss": 0.549, + "step": 309 + }, + { + "epoch": 1.2550607287449393, + "grad_norm": 0.721289777737997, + "learning_rate": 3.7296895707848844e-05, + "loss": 0.5731, + "step": 310 + }, + { + "epoch": 1.2591093117408907, + "grad_norm": 0.5434580430976932, + "learning_rate": 3.7268434097933275e-05, + "loss": 0.546, + "step": 311 + }, + { + "epoch": 1.263157894736842, + "grad_norm": 0.5682339502589898, + "learning_rate": 3.723983441007882e-05, + "loss": 0.5437, + "step": 312 + }, + { + "epoch": 1.2672064777327936, + "grad_norm": 0.49879264820585584, + "learning_rate": 3.721109687296781e-05, + "loss": 0.5522, + "step": 313 + }, + { + "epoch": 1.271255060728745, + "grad_norm": 0.42957942474280564, + "learning_rate": 3.718222171638484e-05, + "loss": 0.5627, + "step": 314 + }, + { + "epoch": 1.2753036437246963, + "grad_norm": 0.43551789799851554, + "learning_rate": 3.715320917121488e-05, + "loss": 0.5508, + "step": 315 + }, + { + "epoch": 1.2793522267206479, + "grad_norm": 0.4169534808214485, + "learning_rate": 3.712405946944149e-05, + "loss": 0.5627, + "step": 316 + }, + { + "epoch": 1.2834008097165992, + "grad_norm": 0.5227318569046997, + "learning_rate": 3.709477284414488e-05, + "loss": 0.5493, + "step": 317 + }, + { + "epoch": 1.2874493927125505, + "grad_norm": 0.4375006421267927, + "learning_rate": 3.7065349529500136e-05, + "loss": 0.5511, + "step": 318 + }, + { + "epoch": 1.291497975708502, + "grad_norm": 0.5327518828699664, + "learning_rate": 3.7035789760775305e-05, + "loss": 0.5548, + "step": 319 + }, + { + "epoch": 1.2955465587044535, + "grad_norm": 0.4793560806529308, + "learning_rate": 3.70060937743295e-05, + "loss": 0.5613, + "step": 320 + }, + { + "epoch": 1.2995951417004048, + "grad_norm": 0.4422973110007042, + "learning_rate": 3.6976261807611045e-05, + "loss": 0.5589, + "step": 321 + }, + { + "epoch": 1.3036437246963564, + "grad_norm": 0.5255791899941813, + "learning_rate": 3.694629409915555e-05, + "loss": 0.5485, + "step": 322 + }, + { + "epoch": 1.3076923076923077, + "grad_norm": 0.47677190019246984, + "learning_rate": 3.691619088858401e-05, + "loss": 0.5454, + "step": 323 + }, + { + "epoch": 1.311740890688259, + "grad_norm": 0.44723231231376087, + "learning_rate": 3.68859524166009e-05, + "loss": 0.5529, + "step": 324 + }, + { + "epoch": 1.3157894736842106, + "grad_norm": 0.5169572952108423, + "learning_rate": 3.6855578924992226e-05, + "loss": 0.5475, + "step": 325 + }, + { + "epoch": 1.319838056680162, + "grad_norm": 0.6009692364899125, + "learning_rate": 3.6825070656623626e-05, + "loss": 0.5486, + "step": 326 + }, + { + "epoch": 1.3238866396761133, + "grad_norm": 0.42519216712380825, + "learning_rate": 3.67944278554384e-05, + "loss": 0.5589, + "step": 327 + }, + { + "epoch": 1.3279352226720649, + "grad_norm": 0.4811007271686678, + "learning_rate": 3.676365076645557e-05, + "loss": 0.5496, + "step": 328 + }, + { + "epoch": 1.3319838056680162, + "grad_norm": 0.6209529255724376, + "learning_rate": 3.673273963576791e-05, + "loss": 0.5515, + "step": 329 + }, + { + "epoch": 1.3360323886639676, + "grad_norm": 0.4700061665762509, + "learning_rate": 3.670169471054001e-05, + "loss": 0.5575, + "step": 330 + }, + { + "epoch": 1.3400809716599191, + "grad_norm": 0.5037104146644436, + "learning_rate": 3.6670516239006254e-05, + "loss": 0.5674, + "step": 331 + }, + { + "epoch": 1.3441295546558705, + "grad_norm": 0.6790236698248087, + "learning_rate": 3.663920447046888e-05, + "loss": 0.5472, + "step": 332 + }, + { + "epoch": 1.3481781376518218, + "grad_norm": 0.5424416726637894, + "learning_rate": 3.6607759655295954e-05, + "loss": 0.5639, + "step": 333 + }, + { + "epoch": 1.3522267206477734, + "grad_norm": 0.6090700756392909, + "learning_rate": 3.657618204491937e-05, + "loss": 0.5476, + "step": 334 + }, + { + "epoch": 1.3562753036437247, + "grad_norm": 0.5451550927564242, + "learning_rate": 3.6544471891832875e-05, + "loss": 0.5648, + "step": 335 + }, + { + "epoch": 1.360323886639676, + "grad_norm": 0.48567533213127456, + "learning_rate": 3.6512629449589983e-05, + "loss": 0.5646, + "step": 336 + }, + { + "epoch": 1.3643724696356276, + "grad_norm": 0.43598024622999454, + "learning_rate": 3.6480654972802045e-05, + "loss": 0.5732, + "step": 337 + }, + { + "epoch": 1.368421052631579, + "grad_norm": 0.5054750326986709, + "learning_rate": 3.644854871713611e-05, + "loss": 0.5765, + "step": 338 + }, + { + "epoch": 1.3724696356275303, + "grad_norm": 0.42163280134862907, + "learning_rate": 3.6416310939312924e-05, + "loss": 0.5645, + "step": 339 + }, + { + "epoch": 1.376518218623482, + "grad_norm": 0.47045530112085526, + "learning_rate": 3.638394189710493e-05, + "loss": 0.552, + "step": 340 + }, + { + "epoch": 1.3805668016194332, + "grad_norm": 0.5550586320534833, + "learning_rate": 3.635144184933412e-05, + "loss": 0.5495, + "step": 341 + }, + { + "epoch": 1.3846153846153846, + "grad_norm": 0.5780287615962894, + "learning_rate": 3.6318811055869994e-05, + "loss": 0.5488, + "step": 342 + }, + { + "epoch": 1.3886639676113361, + "grad_norm": 0.4774294949658317, + "learning_rate": 3.628604977762752e-05, + "loss": 0.5688, + "step": 343 + }, + { + "epoch": 1.3927125506072875, + "grad_norm": 0.41444601369997114, + "learning_rate": 3.6253158276565004e-05, + "loss": 0.5455, + "step": 344 + }, + { + "epoch": 1.3967611336032388, + "grad_norm": 0.5013850214901393, + "learning_rate": 3.6220136815682016e-05, + "loss": 0.5696, + "step": 345 + }, + { + "epoch": 1.4008097165991904, + "grad_norm": 0.3679283745536597, + "learning_rate": 3.618698565901727e-05, + "loss": 0.5619, + "step": 346 + }, + { + "epoch": 1.4048582995951417, + "grad_norm": 0.3897272243538813, + "learning_rate": 3.615370507164654e-05, + "loss": 0.5493, + "step": 347 + }, + { + "epoch": 1.408906882591093, + "grad_norm": 0.3832925323325651, + "learning_rate": 3.61202953196805e-05, + "loss": 0.5515, + "step": 348 + }, + { + "epoch": 1.4129554655870447, + "grad_norm": 0.46367799002036797, + "learning_rate": 3.6086756670262654e-05, + "loss": 0.5461, + "step": 349 + }, + { + "epoch": 1.417004048582996, + "grad_norm": 0.39284924559677564, + "learning_rate": 3.6053089391567135e-05, + "loss": 0.5476, + "step": 350 + }, + { + "epoch": 1.4210526315789473, + "grad_norm": 0.4952992287311946, + "learning_rate": 3.601929375279662e-05, + "loss": 0.559, + "step": 351 + }, + { + "epoch": 1.425101214574899, + "grad_norm": 0.4610452474949315, + "learning_rate": 3.598537002418012e-05, + "loss": 0.5369, + "step": 352 + }, + { + "epoch": 1.4291497975708503, + "grad_norm": 0.46389667312705835, + "learning_rate": 3.5951318476970885e-05, + "loss": 0.546, + "step": 353 + }, + { + "epoch": 1.4331983805668016, + "grad_norm": 0.4431678938980406, + "learning_rate": 3.591713938344416e-05, + "loss": 0.5291, + "step": 354 + }, + { + "epoch": 1.4372469635627532, + "grad_norm": 0.4831802326494412, + "learning_rate": 3.588283301689507e-05, + "loss": 0.5495, + "step": 355 + }, + { + "epoch": 1.4412955465587045, + "grad_norm": 0.5268832881017466, + "learning_rate": 3.5848399651636424e-05, + "loss": 0.5442, + "step": 356 + }, + { + "epoch": 1.4453441295546559, + "grad_norm": 0.38585200877783915, + "learning_rate": 3.5813839562996473e-05, + "loss": 0.545, + "step": 357 + }, + { + "epoch": 1.4493927125506074, + "grad_norm": 0.46686962852077835, + "learning_rate": 3.5779153027316775e-05, + "loss": 0.5459, + "step": 358 + }, + { + "epoch": 1.4534412955465588, + "grad_norm": 0.5341180163010323, + "learning_rate": 3.574434032194994e-05, + "loss": 0.5578, + "step": 359 + }, + { + "epoch": 1.45748987854251, + "grad_norm": 0.4801419466950967, + "learning_rate": 3.5709401725257436e-05, + "loss": 0.5578, + "step": 360 + }, + { + "epoch": 1.4615384615384617, + "grad_norm": 0.49864545695542234, + "learning_rate": 3.5674337516607346e-05, + "loss": 0.5506, + "step": 361 + }, + { + "epoch": 1.465587044534413, + "grad_norm": 0.48229097959718886, + "learning_rate": 3.563914797637216e-05, + "loss": 0.5545, + "step": 362 + }, + { + "epoch": 1.4696356275303644, + "grad_norm": 0.590027701630367, + "learning_rate": 3.560383338592649e-05, + "loss": 0.5516, + "step": 363 + }, + { + "epoch": 1.4736842105263157, + "grad_norm": 0.3973589361909056, + "learning_rate": 3.556839402764487e-05, + "loss": 0.5618, + "step": 364 + }, + { + "epoch": 1.4777327935222673, + "grad_norm": 0.5573343027370713, + "learning_rate": 3.553283018489946e-05, + "loss": 0.5426, + "step": 365 + }, + { + "epoch": 1.4817813765182186, + "grad_norm": 0.413026150092314, + "learning_rate": 3.54971421420578e-05, + "loss": 0.5292, + "step": 366 + }, + { + "epoch": 1.48582995951417, + "grad_norm": 0.4307883449695307, + "learning_rate": 3.5461330184480524e-05, + "loss": 0.5586, + "step": 367 + }, + { + "epoch": 1.4898785425101215, + "grad_norm": 0.4400574114423602, + "learning_rate": 3.54253945985191e-05, + "loss": 0.5403, + "step": 368 + }, + { + "epoch": 1.4939271255060729, + "grad_norm": 0.39465493810840213, + "learning_rate": 3.5389335671513524e-05, + "loss": 0.538, + "step": 369 + }, + { + "epoch": 1.4979757085020242, + "grad_norm": 0.4874948301856071, + "learning_rate": 3.5353153691789986e-05, + "loss": 0.5517, + "step": 370 + }, + { + "epoch": 1.5020242914979756, + "grad_norm": 0.39455894043145295, + "learning_rate": 3.531684894865866e-05, + "loss": 0.5541, + "step": 371 + }, + { + "epoch": 1.5060728744939271, + "grad_norm": 0.46882120257103344, + "learning_rate": 3.528042173241128e-05, + "loss": 0.5421, + "step": 372 + }, + { + "epoch": 1.5101214574898787, + "grad_norm": 0.45718890645236365, + "learning_rate": 3.524387233431892e-05, + "loss": 0.5417, + "step": 373 + }, + { + "epoch": 1.5141700404858298, + "grad_norm": 0.4803488825701153, + "learning_rate": 3.520720104662958e-05, + "loss": 0.567, + "step": 374 + }, + { + "epoch": 1.5182186234817814, + "grad_norm": 0.4467902505737919, + "learning_rate": 3.5170408162565904e-05, + "loss": 0.5522, + "step": 375 + }, + { + "epoch": 1.522267206477733, + "grad_norm": 0.4170937118219365, + "learning_rate": 3.513349397632281e-05, + "loss": 0.5414, + "step": 376 + }, + { + "epoch": 1.526315789473684, + "grad_norm": 0.42477100779857063, + "learning_rate": 3.5096458783065145e-05, + "loss": 0.5602, + "step": 377 + }, + { + "epoch": 1.5303643724696356, + "grad_norm": 0.4241683836722998, + "learning_rate": 3.505930287892533e-05, + "loss": 0.5548, + "step": 378 + }, + { + "epoch": 1.5344129554655872, + "grad_norm": 0.38051661807760684, + "learning_rate": 3.502202656100099e-05, + "loss": 0.5603, + "step": 379 + }, + { + "epoch": 1.5384615384615383, + "grad_norm": 0.5357352899755009, + "learning_rate": 3.498463012735256e-05, + "loss": 0.5569, + "step": 380 + }, + { + "epoch": 1.54251012145749, + "grad_norm": 0.482019382832418, + "learning_rate": 3.494711387700094e-05, + "loss": 0.5544, + "step": 381 + }, + { + "epoch": 1.5465587044534415, + "grad_norm": 0.3938424753573089, + "learning_rate": 3.490947810992505e-05, + "loss": 0.552, + "step": 382 + }, + { + "epoch": 1.5506072874493926, + "grad_norm": 0.5174118429863914, + "learning_rate": 3.48717231270595e-05, + "loss": 0.5527, + "step": 383 + }, + { + "epoch": 1.5546558704453441, + "grad_norm": 0.5394486595950968, + "learning_rate": 3.483384923029211e-05, + "loss": 0.5484, + "step": 384 + }, + { + "epoch": 1.5587044534412957, + "grad_norm": 0.41399024778091725, + "learning_rate": 3.479585672246156e-05, + "loss": 0.558, + "step": 385 + }, + { + "epoch": 1.5627530364372468, + "grad_norm": 0.542223157798853, + "learning_rate": 3.4757745907354924e-05, + "loss": 0.5536, + "step": 386 + }, + { + "epoch": 1.5668016194331984, + "grad_norm": 0.5654299434172781, + "learning_rate": 3.471951708970527e-05, + "loss": 0.5368, + "step": 387 + }, + { + "epoch": 1.5708502024291497, + "grad_norm": 0.6319379175885185, + "learning_rate": 3.468117057518921e-05, + "loss": 0.5569, + "step": 388 + }, + { + "epoch": 1.574898785425101, + "grad_norm": 0.6374862750444101, + "learning_rate": 3.4642706670424426e-05, + "loss": 0.5497, + "step": 389 + }, + { + "epoch": 1.5789473684210527, + "grad_norm": 0.6211163536487391, + "learning_rate": 3.460412568296731e-05, + "loss": 0.5443, + "step": 390 + }, + { + "epoch": 1.582995951417004, + "grad_norm": 0.5075433409846783, + "learning_rate": 3.456542792131039e-05, + "loss": 0.5487, + "step": 391 + }, + { + "epoch": 1.5870445344129553, + "grad_norm": 0.4881890963846757, + "learning_rate": 3.4526613694879936e-05, + "loss": 0.5608, + "step": 392 + }, + { + "epoch": 1.591093117408907, + "grad_norm": 0.5134647230223943, + "learning_rate": 3.448768331403348e-05, + "loss": 0.5494, + "step": 393 + }, + { + "epoch": 1.5951417004048583, + "grad_norm": 0.4850033851457585, + "learning_rate": 3.44486370900573e-05, + "loss": 0.5649, + "step": 394 + }, + { + "epoch": 1.5991902834008096, + "grad_norm": 0.4366799252060436, + "learning_rate": 3.440947533516396e-05, + "loss": 0.5433, + "step": 395 + }, + { + "epoch": 1.6032388663967612, + "grad_norm": 0.4915409095825524, + "learning_rate": 3.4370198362489816e-05, + "loss": 0.5626, + "step": 396 + }, + { + "epoch": 1.6072874493927125, + "grad_norm": 0.45940535841031205, + "learning_rate": 3.43308064860925e-05, + "loss": 0.5435, + "step": 397 + }, + { + "epoch": 1.6113360323886639, + "grad_norm": 0.37867939112393256, + "learning_rate": 3.4291300020948393e-05, + "loss": 0.564, + "step": 398 + }, + { + "epoch": 1.6153846153846154, + "grad_norm": 0.46982559972310506, + "learning_rate": 3.425167928295015e-05, + "loss": 0.5558, + "step": 399 + }, + { + "epoch": 1.6194331983805668, + "grad_norm": 0.3447582771059348, + "learning_rate": 3.421194458890411e-05, + "loss": 0.539, + "step": 400 + }, + { + "epoch": 1.623481781376518, + "grad_norm": 0.4739530629561756, + "learning_rate": 3.4172096256527865e-05, + "loss": 0.5512, + "step": 401 + }, + { + "epoch": 1.6275303643724697, + "grad_norm": 0.35737477422788033, + "learning_rate": 3.4132134604447595e-05, + "loss": 0.5498, + "step": 402 + }, + { + "epoch": 1.631578947368421, + "grad_norm": 0.37833474400556966, + "learning_rate": 3.409205995219561e-05, + "loss": 0.5461, + "step": 403 + }, + { + "epoch": 1.6356275303643724, + "grad_norm": 0.42136837893130685, + "learning_rate": 3.4051872620207765e-05, + "loss": 0.5257, + "step": 404 + }, + { + "epoch": 1.639676113360324, + "grad_norm": 0.47416360503414695, + "learning_rate": 3.40115729298209e-05, + "loss": 0.575, + "step": 405 + }, + { + "epoch": 1.6437246963562753, + "grad_norm": 0.41500293083067213, + "learning_rate": 3.397116120327025e-05, + "loss": 0.5518, + "step": 406 + }, + { + "epoch": 1.6477732793522266, + "grad_norm": 0.5123692778577028, + "learning_rate": 3.3930637763686916e-05, + "loss": 0.5393, + "step": 407 + }, + { + "epoch": 1.6518218623481782, + "grad_norm": 0.4512501757856307, + "learning_rate": 3.389000293509524e-05, + "loss": 0.5477, + "step": 408 + }, + { + "epoch": 1.6558704453441295, + "grad_norm": 0.3927144558433259, + "learning_rate": 3.3849257042410225e-05, + "loss": 0.5478, + "step": 409 + }, + { + "epoch": 1.6599190283400809, + "grad_norm": 0.45171782322140364, + "learning_rate": 3.380840041143494e-05, + "loss": 0.5555, + "step": 410 + }, + { + "epoch": 1.6639676113360324, + "grad_norm": 0.38609462614884377, + "learning_rate": 3.376743336885792e-05, + "loss": 0.5512, + "step": 411 + }, + { + "epoch": 1.6680161943319838, + "grad_norm": 0.3855332775234726, + "learning_rate": 3.372635624225055e-05, + "loss": 0.5569, + "step": 412 + }, + { + "epoch": 1.6720647773279351, + "grad_norm": 0.5152862683549998, + "learning_rate": 3.3685169360064445e-05, + "loss": 0.5653, + "step": 413 + }, + { + "epoch": 1.6761133603238867, + "grad_norm": 0.532655027125735, + "learning_rate": 3.3643873051628804e-05, + "loss": 0.5608, + "step": 414 + }, + { + "epoch": 1.680161943319838, + "grad_norm": 0.6108427499529075, + "learning_rate": 3.3602467647147814e-05, + "loss": 0.5735, + "step": 415 + }, + { + "epoch": 1.6842105263157894, + "grad_norm": 0.5015537247732341, + "learning_rate": 3.356095347769799e-05, + "loss": 0.5481, + "step": 416 + }, + { + "epoch": 1.688259109311741, + "grad_norm": 0.5348150300321532, + "learning_rate": 3.351933087522552e-05, + "loss": 0.5545, + "step": 417 + }, + { + "epoch": 1.6923076923076923, + "grad_norm": 0.41510643025274463, + "learning_rate": 3.3477600172543626e-05, + "loss": 0.5493, + "step": 418 + }, + { + "epoch": 1.6963562753036436, + "grad_norm": 0.5123200661215432, + "learning_rate": 3.3435761703329894e-05, + "loss": 0.5587, + "step": 419 + }, + { + "epoch": 1.7004048582995952, + "grad_norm": 0.3938895165544414, + "learning_rate": 3.3393815802123606e-05, + "loss": 0.5395, + "step": 420 + }, + { + "epoch": 1.7044534412955465, + "grad_norm": 0.48836833526973966, + "learning_rate": 3.335176280432308e-05, + "loss": 0.5428, + "step": 421 + }, + { + "epoch": 1.708502024291498, + "grad_norm": 0.41700771118523683, + "learning_rate": 3.330960304618295e-05, + "loss": 0.5381, + "step": 422 + }, + { + "epoch": 1.7125506072874495, + "grad_norm": 0.42392661138671284, + "learning_rate": 3.326733686481153e-05, + "loss": 0.5408, + "step": 423 + }, + { + "epoch": 1.7165991902834008, + "grad_norm": 0.4498850780548398, + "learning_rate": 3.3224964598168084e-05, + "loss": 0.5589, + "step": 424 + }, + { + "epoch": 1.7206477732793521, + "grad_norm": 0.4389911378602445, + "learning_rate": 3.318248658506012e-05, + "loss": 0.5524, + "step": 425 + }, + { + "epoch": 1.7246963562753037, + "grad_norm": 0.45545630188421915, + "learning_rate": 3.313990316514069e-05, + "loss": 0.5608, + "step": 426 + }, + { + "epoch": 1.728744939271255, + "grad_norm": 0.3724498302675261, + "learning_rate": 3.309721467890571e-05, + "loss": 0.5456, + "step": 427 + }, + { + "epoch": 1.7327935222672064, + "grad_norm": 0.4433652919655176, + "learning_rate": 3.305442146769115e-05, + "loss": 0.554, + "step": 428 + }, + { + "epoch": 1.736842105263158, + "grad_norm": 0.3882061134747794, + "learning_rate": 3.30115238736704e-05, + "loss": 0.5607, + "step": 429 + }, + { + "epoch": 1.7408906882591093, + "grad_norm": 0.4120555730353867, + "learning_rate": 3.296852223985148e-05, + "loss": 0.5324, + "step": 430 + }, + { + "epoch": 1.7449392712550607, + "grad_norm": 0.36729827490763023, + "learning_rate": 3.2925416910074315e-05, + "loss": 0.5477, + "step": 431 + }, + { + "epoch": 1.7489878542510122, + "grad_norm": 0.45722175229791023, + "learning_rate": 3.288220822900796e-05, + "loss": 0.5404, + "step": 432 + }, + { + "epoch": 1.7530364372469636, + "grad_norm": 0.3776632127113273, + "learning_rate": 3.283889654214788e-05, + "loss": 0.5311, + "step": 433 + }, + { + "epoch": 1.757085020242915, + "grad_norm": 0.4056120433513921, + "learning_rate": 3.279548219581317e-05, + "loss": 0.5457, + "step": 434 + }, + { + "epoch": 1.7611336032388665, + "grad_norm": 0.4105112997028296, + "learning_rate": 3.275196553714379e-05, + "loss": 0.5512, + "step": 435 + }, + { + "epoch": 1.7651821862348178, + "grad_norm": 0.3680625477691142, + "learning_rate": 3.270834691409778e-05, + "loss": 0.5433, + "step": 436 + }, + { + "epoch": 1.7692307692307692, + "grad_norm": 0.45468805123926964, + "learning_rate": 3.266462667544849e-05, + "loss": 0.5473, + "step": 437 + }, + { + "epoch": 1.7732793522267207, + "grad_norm": 0.3546369201109977, + "learning_rate": 3.262080517078178e-05, + "loss": 0.5556, + "step": 438 + }, + { + "epoch": 1.777327935222672, + "grad_norm": 0.4720267497109987, + "learning_rate": 3.257688275049323e-05, + "loss": 0.5466, + "step": 439 + }, + { + "epoch": 1.7813765182186234, + "grad_norm": 0.34544705728811137, + "learning_rate": 3.253285976578535e-05, + "loss": 0.5443, + "step": 440 + }, + { + "epoch": 1.785425101214575, + "grad_norm": 0.45228105252286954, + "learning_rate": 3.2488736568664756e-05, + "loss": 0.5436, + "step": 441 + }, + { + "epoch": 1.7894736842105263, + "grad_norm": 0.41616520171122157, + "learning_rate": 3.244451351193935e-05, + "loss": 0.5475, + "step": 442 + }, + { + "epoch": 1.7935222672064777, + "grad_norm": 0.4657120830205619, + "learning_rate": 3.240019094921551e-05, + "loss": 0.5509, + "step": 443 + }, + { + "epoch": 1.7975708502024292, + "grad_norm": 0.35807530886934, + "learning_rate": 3.235576923489527e-05, + "loss": 0.5535, + "step": 444 + }, + { + "epoch": 1.8016194331983806, + "grad_norm": 0.42910499118022677, + "learning_rate": 3.2311248724173476e-05, + "loss": 0.5468, + "step": 445 + }, + { + "epoch": 1.805668016194332, + "grad_norm": 0.4138754244853176, + "learning_rate": 3.226662977303494e-05, + "loss": 0.5594, + "step": 446 + }, + { + "epoch": 1.8097165991902835, + "grad_norm": 0.36266840152979907, + "learning_rate": 3.2221912738251626e-05, + "loss": 0.5506, + "step": 447 + }, + { + "epoch": 1.8137651821862348, + "grad_norm": 0.4526986373398701, + "learning_rate": 3.2177097977379736e-05, + "loss": 0.5301, + "step": 448 + }, + { + "epoch": 1.8178137651821862, + "grad_norm": 0.3585237262414563, + "learning_rate": 3.21321858487569e-05, + "loss": 0.5551, + "step": 449 + }, + { + "epoch": 1.8218623481781377, + "grad_norm": 0.47654069174534053, + "learning_rate": 3.208717671149931e-05, + "loss": 0.5506, + "step": 450 + }, + { + "epoch": 1.825910931174089, + "grad_norm": 0.40839194924916145, + "learning_rate": 3.204207092549882e-05, + "loss": 0.5404, + "step": 451 + }, + { + "epoch": 1.8299595141700404, + "grad_norm": 0.3998278469136544, + "learning_rate": 3.19968688514201e-05, + "loss": 0.5473, + "step": 452 + }, + { + "epoch": 1.834008097165992, + "grad_norm": 0.44899481722834267, + "learning_rate": 3.195157085069774e-05, + "loss": 0.5478, + "step": 453 + }, + { + "epoch": 1.8380566801619433, + "grad_norm": 0.4075145680490999, + "learning_rate": 3.190617728553332e-05, + "loss": 0.5648, + "step": 454 + }, + { + "epoch": 1.8421052631578947, + "grad_norm": 0.39224400573681795, + "learning_rate": 3.1860688518892606e-05, + "loss": 0.5631, + "step": 455 + }, + { + "epoch": 1.8461538461538463, + "grad_norm": 0.35881012324622164, + "learning_rate": 3.181510491450254e-05, + "loss": 0.554, + "step": 456 + }, + { + "epoch": 1.8502024291497976, + "grad_norm": 0.4070925198407618, + "learning_rate": 3.176942683684842e-05, + "loss": 0.5436, + "step": 457 + }, + { + "epoch": 1.854251012145749, + "grad_norm": 0.3995158115344002, + "learning_rate": 3.1723654651170934e-05, + "loss": 0.5485, + "step": 458 + }, + { + "epoch": 1.8582995951417005, + "grad_norm": 0.46543775323672254, + "learning_rate": 3.167778872346327e-05, + "loss": 0.5261, + "step": 459 + }, + { + "epoch": 1.8623481781376519, + "grad_norm": 0.4314581370809254, + "learning_rate": 3.163182942046815e-05, + "loss": 0.5611, + "step": 460 + }, + { + "epoch": 1.8663967611336032, + "grad_norm": 0.3423538756451831, + "learning_rate": 3.158577710967494e-05, + "loss": 0.5492, + "step": 461 + }, + { + "epoch": 1.8704453441295548, + "grad_norm": 0.48678469136820907, + "learning_rate": 3.153963215931669e-05, + "loss": 0.542, + "step": 462 + }, + { + "epoch": 1.874493927125506, + "grad_norm": 0.3394810968245217, + "learning_rate": 3.14933949383672e-05, + "loss": 0.5456, + "step": 463 + }, + { + "epoch": 1.8785425101214575, + "grad_norm": 0.3937261361856436, + "learning_rate": 3.144706581653805e-05, + "loss": 0.5541, + "step": 464 + }, + { + "epoch": 1.882591093117409, + "grad_norm": 0.3592123099391868, + "learning_rate": 3.140064516427566e-05, + "loss": 0.5531, + "step": 465 + }, + { + "epoch": 1.8866396761133604, + "grad_norm": 0.4167953601339203, + "learning_rate": 3.135413335275833e-05, + "loss": 0.5567, + "step": 466 + }, + { + "epoch": 1.8906882591093117, + "grad_norm": 0.35623651252377, + "learning_rate": 3.130753075389327e-05, + "loss": 0.531, + "step": 467 + }, + { + "epoch": 1.8947368421052633, + "grad_norm": 0.5205198585236963, + "learning_rate": 3.1260837740313625e-05, + "loss": 0.5476, + "step": 468 + }, + { + "epoch": 1.8987854251012146, + "grad_norm": 0.40651845114732427, + "learning_rate": 3.121405468537547e-05, + "loss": 0.553, + "step": 469 + }, + { + "epoch": 1.902834008097166, + "grad_norm": 0.41841636366429635, + "learning_rate": 3.116718196315488e-05, + "loss": 0.5376, + "step": 470 + }, + { + "epoch": 1.9068825910931175, + "grad_norm": 0.37450354897551613, + "learning_rate": 3.1120219948444894e-05, + "loss": 0.5449, + "step": 471 + }, + { + "epoch": 1.9109311740890689, + "grad_norm": 0.478571281268759, + "learning_rate": 3.107316901675252e-05, + "loss": 0.5446, + "step": 472 + }, + { + "epoch": 1.9149797570850202, + "grad_norm": 0.3431961573217063, + "learning_rate": 3.1026029544295745e-05, + "loss": 0.538, + "step": 473 + }, + { + "epoch": 1.9190283400809718, + "grad_norm": 0.4569109066299344, + "learning_rate": 3.097880190800057e-05, + "loss": 0.5458, + "step": 474 + }, + { + "epoch": 1.9230769230769231, + "grad_norm": 0.3797637854649633, + "learning_rate": 3.093148648549788e-05, + "loss": 0.5444, + "step": 475 + }, + { + "epoch": 1.9271255060728745, + "grad_norm": 0.4850407895914578, + "learning_rate": 3.088408365512055e-05, + "loss": 0.5352, + "step": 476 + }, + { + "epoch": 1.931174089068826, + "grad_norm": 0.39154724201976876, + "learning_rate": 3.083659379590034e-05, + "loss": 0.5555, + "step": 477 + }, + { + "epoch": 1.9352226720647774, + "grad_norm": 0.4059931816105655, + "learning_rate": 3.0789017287564913e-05, + "loss": 0.5389, + "step": 478 + }, + { + "epoch": 1.9392712550607287, + "grad_norm": 0.39198406824890436, + "learning_rate": 3.074135451053475e-05, + "loss": 0.5506, + "step": 479 + }, + { + "epoch": 1.9433198380566803, + "grad_norm": 0.4309495555395892, + "learning_rate": 3.069360584592015e-05, + "loss": 0.5471, + "step": 480 + }, + { + "epoch": 1.9473684210526314, + "grad_norm": 0.36268280729713287, + "learning_rate": 3.064577167551816e-05, + "loss": 0.5418, + "step": 481 + }, + { + "epoch": 1.951417004048583, + "grad_norm": 0.5410017886574541, + "learning_rate": 3.059785238180953e-05, + "loss": 0.5464, + "step": 482 + }, + { + "epoch": 1.9554655870445345, + "grad_norm": 0.38013406316511567, + "learning_rate": 3.054984834795566e-05, + "loss": 0.5498, + "step": 483 + }, + { + "epoch": 1.9595141700404857, + "grad_norm": 0.3926074445531767, + "learning_rate": 3.0501759957795537e-05, + "loss": 0.5363, + "step": 484 + }, + { + "epoch": 1.9635627530364372, + "grad_norm": 0.474164894760192, + "learning_rate": 3.0453587595842627e-05, + "loss": 0.5439, + "step": 485 + }, + { + "epoch": 1.9676113360323888, + "grad_norm": 0.4137540319481608, + "learning_rate": 3.0405331647281856e-05, + "loss": 0.5575, + "step": 486 + }, + { + "epoch": 1.97165991902834, + "grad_norm": 0.3592404831855967, + "learning_rate": 3.0356992497966508e-05, + "loss": 0.5299, + "step": 487 + }, + { + "epoch": 1.9757085020242915, + "grad_norm": 0.43995117174321957, + "learning_rate": 3.0308570534415137e-05, + "loss": 0.5448, + "step": 488 + }, + { + "epoch": 1.979757085020243, + "grad_norm": 0.3846267866467673, + "learning_rate": 3.0260066143808467e-05, + "loss": 0.5359, + "step": 489 + }, + { + "epoch": 1.9838056680161942, + "grad_norm": 0.3822557457112387, + "learning_rate": 3.021147971398632e-05, + "loss": 0.5584, + "step": 490 + }, + { + "epoch": 1.9878542510121457, + "grad_norm": 0.43765737969487994, + "learning_rate": 3.0162811633444478e-05, + "loss": 0.5409, + "step": 491 + }, + { + "epoch": 1.9919028340080973, + "grad_norm": 0.4185551888312873, + "learning_rate": 3.0114062291331635e-05, + "loss": 0.5546, + "step": 492 + }, + { + "epoch": 1.9959514170040484, + "grad_norm": 0.4504733570689978, + "learning_rate": 3.0065232077446217e-05, + "loss": 0.5449, + "step": 493 + }, + { + "epoch": 2.0, + "grad_norm": 0.3380077122309689, + "learning_rate": 3.001632138223332e-05, + "loss": 0.5235, + "step": 494 + }, + { + "epoch": 2.0040485829959516, + "grad_norm": 0.5289131107391366, + "learning_rate": 2.9967330596781565e-05, + "loss": 0.4834, + "step": 495 + }, + { + "epoch": 2.0080971659919027, + "grad_norm": 0.6022235810466267, + "learning_rate": 2.9918260112819952e-05, + "loss": 0.4836, + "step": 496 + }, + { + "epoch": 2.0121457489878543, + "grad_norm": 0.4400790952976979, + "learning_rate": 2.9869110322714778e-05, + "loss": 0.4674, + "step": 497 + }, + { + "epoch": 2.016194331983806, + "grad_norm": 0.545815817391453, + "learning_rate": 2.9819881619466447e-05, + "loss": 0.4882, + "step": 498 + }, + { + "epoch": 2.020242914979757, + "grad_norm": 0.496900921892097, + "learning_rate": 2.9770574396706364e-05, + "loss": 0.4661, + "step": 499 + }, + { + "epoch": 2.0242914979757085, + "grad_norm": 0.456382911999509, + "learning_rate": 2.972118904869376e-05, + "loss": 0.4593, + "step": 500 + }, + { + "epoch": 2.02834008097166, + "grad_norm": 0.5263819962981636, + "learning_rate": 2.9671725970312563e-05, + "loss": 0.4656, + "step": 501 + }, + { + "epoch": 2.032388663967611, + "grad_norm": 0.4230056736391131, + "learning_rate": 2.9622185557068238e-05, + "loss": 0.471, + "step": 502 + }, + { + "epoch": 2.0364372469635628, + "grad_norm": 0.46179584479083574, + "learning_rate": 2.95725682050846e-05, + "loss": 0.4839, + "step": 503 + }, + { + "epoch": 2.0404858299595143, + "grad_norm": 0.48439366788063903, + "learning_rate": 2.9522874311100684e-05, + "loss": 0.4726, + "step": 504 + }, + { + "epoch": 2.0445344129554655, + "grad_norm": 0.41547617409636994, + "learning_rate": 2.9473104272467526e-05, + "loss": 0.4942, + "step": 505 + }, + { + "epoch": 2.048582995951417, + "grad_norm": 0.594966581072272, + "learning_rate": 2.942325848714505e-05, + "loss": 0.4567, + "step": 506 + }, + { + "epoch": 2.0526315789473686, + "grad_norm": 0.4294633248047652, + "learning_rate": 2.9373337353698804e-05, + "loss": 0.4957, + "step": 507 + }, + { + "epoch": 2.0566801619433197, + "grad_norm": 0.526729042254394, + "learning_rate": 2.932334127129686e-05, + "loss": 0.4727, + "step": 508 + }, + { + "epoch": 2.0607287449392713, + "grad_norm": 0.45056322101181373, + "learning_rate": 2.9273270639706547e-05, + "loss": 0.456, + "step": 509 + }, + { + "epoch": 2.064777327935223, + "grad_norm": 0.39405012393372085, + "learning_rate": 2.922312585929131e-05, + "loss": 0.4702, + "step": 510 + }, + { + "epoch": 2.068825910931174, + "grad_norm": 0.4204333811534276, + "learning_rate": 2.9172907331007478e-05, + "loss": 0.4899, + "step": 511 + }, + { + "epoch": 2.0728744939271255, + "grad_norm": 0.3887012620747415, + "learning_rate": 2.9122615456401053e-05, + "loss": 0.4654, + "step": 512 + }, + { + "epoch": 2.076923076923077, + "grad_norm": 0.35990481638091615, + "learning_rate": 2.9072250637604535e-05, + "loss": 0.4571, + "step": 513 + }, + { + "epoch": 2.080971659919028, + "grad_norm": 0.4002959330102329, + "learning_rate": 2.9021813277333667e-05, + "loss": 0.4686, + "step": 514 + }, + { + "epoch": 2.08502024291498, + "grad_norm": 0.39423234242883837, + "learning_rate": 2.8971303778884244e-05, + "loss": 0.466, + "step": 515 + }, + { + "epoch": 2.0890688259109313, + "grad_norm": 0.3681086322766949, + "learning_rate": 2.8920722546128863e-05, + "loss": 0.4848, + "step": 516 + }, + { + "epoch": 2.0931174089068825, + "grad_norm": 0.38978246302612757, + "learning_rate": 2.887006998351372e-05, + "loss": 0.4658, + "step": 517 + }, + { + "epoch": 2.097165991902834, + "grad_norm": 0.3532291335669879, + "learning_rate": 2.881934649605535e-05, + "loss": 0.4925, + "step": 518 + }, + { + "epoch": 2.1012145748987856, + "grad_norm": 0.38186745331201294, + "learning_rate": 2.8768552489337408e-05, + "loss": 0.4711, + "step": 519 + }, + { + "epoch": 2.1052631578947367, + "grad_norm": 0.36906415232922274, + "learning_rate": 2.8717688369507425e-05, + "loss": 0.4843, + "step": 520 + }, + { + "epoch": 2.1093117408906883, + "grad_norm": 0.36645053349597984, + "learning_rate": 2.8666754543273535e-05, + "loss": 0.4474, + "step": 521 + }, + { + "epoch": 2.11336032388664, + "grad_norm": 0.37114722122388955, + "learning_rate": 2.8615751417901273e-05, + "loss": 0.4555, + "step": 522 + }, + { + "epoch": 2.117408906882591, + "grad_norm": 0.372911001636862, + "learning_rate": 2.856467940121025e-05, + "loss": 0.4807, + "step": 523 + }, + { + "epoch": 2.1214574898785425, + "grad_norm": 0.4071572798214776, + "learning_rate": 2.8513538901570964e-05, + "loss": 0.464, + "step": 524 + }, + { + "epoch": 2.125506072874494, + "grad_norm": 0.35632640658907105, + "learning_rate": 2.846233032790149e-05, + "loss": 0.4636, + "step": 525 + }, + { + "epoch": 2.1295546558704452, + "grad_norm": 0.407421736752148, + "learning_rate": 2.84110540896642e-05, + "loss": 0.4676, + "step": 526 + }, + { + "epoch": 2.133603238866397, + "grad_norm": 0.3600858946924453, + "learning_rate": 2.8359710596862555e-05, + "loss": 0.4615, + "step": 527 + }, + { + "epoch": 2.1376518218623484, + "grad_norm": 0.3887966984904334, + "learning_rate": 2.8308300260037734e-05, + "loss": 0.4578, + "step": 528 + }, + { + "epoch": 2.1417004048582995, + "grad_norm": 0.42801194935906345, + "learning_rate": 2.8256823490265424e-05, + "loss": 0.4675, + "step": 529 + }, + { + "epoch": 2.145748987854251, + "grad_norm": 0.3950771679844169, + "learning_rate": 2.8205280699152515e-05, + "loss": 0.4745, + "step": 530 + }, + { + "epoch": 2.1497975708502026, + "grad_norm": 0.3585003723819789, + "learning_rate": 2.8153672298833777e-05, + "loss": 0.4628, + "step": 531 + }, + { + "epoch": 2.1538461538461537, + "grad_norm": 0.41410722244982173, + "learning_rate": 2.8101998701968615e-05, + "loss": 0.485, + "step": 532 + }, + { + "epoch": 2.1578947368421053, + "grad_norm": 0.3434360443862549, + "learning_rate": 2.805026032173773e-05, + "loss": 0.4815, + "step": 533 + }, + { + "epoch": 2.161943319838057, + "grad_norm": 0.39743634784732035, + "learning_rate": 2.7998457571839832e-05, + "loss": 0.4746, + "step": 534 + }, + { + "epoch": 2.165991902834008, + "grad_norm": 0.3813098043806024, + "learning_rate": 2.7946590866488322e-05, + "loss": 0.4696, + "step": 535 + }, + { + "epoch": 2.1700404858299596, + "grad_norm": 0.3983542399307604, + "learning_rate": 2.7894660620408e-05, + "loss": 0.459, + "step": 536 + }, + { + "epoch": 2.174089068825911, + "grad_norm": 0.41987785835931407, + "learning_rate": 2.784266724883173e-05, + "loss": 0.4947, + "step": 537 + }, + { + "epoch": 2.1781376518218623, + "grad_norm": 0.40241111496012827, + "learning_rate": 2.7790611167497128e-05, + "loss": 0.4789, + "step": 538 + }, + { + "epoch": 2.182186234817814, + "grad_norm": 0.39023673319231317, + "learning_rate": 2.7738492792643224e-05, + "loss": 0.4792, + "step": 539 + }, + { + "epoch": 2.1862348178137654, + "grad_norm": 0.3793270718490223, + "learning_rate": 2.768631254100716e-05, + "loss": 0.4493, + "step": 540 + }, + { + "epoch": 2.1902834008097165, + "grad_norm": 0.37919787964995894, + "learning_rate": 2.7634070829820836e-05, + "loss": 0.4643, + "step": 541 + }, + { + "epoch": 2.194331983805668, + "grad_norm": 0.464876555099051, + "learning_rate": 2.7581768076807592e-05, + "loss": 0.4636, + "step": 542 + }, + { + "epoch": 2.1983805668016196, + "grad_norm": 0.34831664505059756, + "learning_rate": 2.7529404700178832e-05, + "loss": 0.4663, + "step": 543 + }, + { + "epoch": 2.2024291497975708, + "grad_norm": 0.473538749300893, + "learning_rate": 2.7476981118630735e-05, + "loss": 0.4647, + "step": 544 + }, + { + "epoch": 2.2064777327935223, + "grad_norm": 0.41532908723824047, + "learning_rate": 2.742449775134085e-05, + "loss": 0.4744, + "step": 545 + }, + { + "epoch": 2.2105263157894735, + "grad_norm": 0.4325420713415665, + "learning_rate": 2.7371955017964788e-05, + "loss": 0.4667, + "step": 546 + }, + { + "epoch": 2.214574898785425, + "grad_norm": 0.3712572618100617, + "learning_rate": 2.7319353338632845e-05, + "loss": 0.4729, + "step": 547 + }, + { + "epoch": 2.2186234817813766, + "grad_norm": 0.4192323550670153, + "learning_rate": 2.7266693133946645e-05, + "loss": 0.4784, + "step": 548 + }, + { + "epoch": 2.2226720647773277, + "grad_norm": 0.3760390778470649, + "learning_rate": 2.7213974824975785e-05, + "loss": 0.4648, + "step": 549 + }, + { + "epoch": 2.2267206477732793, + "grad_norm": 0.4085235609646252, + "learning_rate": 2.7161198833254464e-05, + "loss": 0.4748, + "step": 550 + }, + { + "epoch": 2.230769230769231, + "grad_norm": 0.36440628001217223, + "learning_rate": 2.7108365580778095e-05, + "loss": 0.4786, + "step": 551 + }, + { + "epoch": 2.234817813765182, + "grad_norm": 0.36064660679079313, + "learning_rate": 2.705547548999996e-05, + "loss": 0.4814, + "step": 552 + }, + { + "epoch": 2.2388663967611335, + "grad_norm": 0.34405519777520305, + "learning_rate": 2.7002528983827817e-05, + "loss": 0.4652, + "step": 553 + }, + { + "epoch": 2.242914979757085, + "grad_norm": 0.3561085501893368, + "learning_rate": 2.6949526485620517e-05, + "loss": 0.4698, + "step": 554 + }, + { + "epoch": 2.246963562753036, + "grad_norm": 0.33308767185517657, + "learning_rate": 2.6896468419184623e-05, + "loss": 0.4774, + "step": 555 + }, + { + "epoch": 2.251012145748988, + "grad_norm": 0.35670569942609115, + "learning_rate": 2.6843355208771024e-05, + "loss": 0.4769, + "step": 556 + }, + { + "epoch": 2.2550607287449393, + "grad_norm": 0.33158505889937534, + "learning_rate": 2.6790187279071536e-05, + "loss": 0.474, + "step": 557 + }, + { + "epoch": 2.2591093117408905, + "grad_norm": 0.38381653261218773, + "learning_rate": 2.67369650552155e-05, + "loss": 0.475, + "step": 558 + }, + { + "epoch": 2.263157894736842, + "grad_norm": 0.3422734312753868, + "learning_rate": 2.6683688962766407e-05, + "loss": 0.4613, + "step": 559 + }, + { + "epoch": 2.2672064777327936, + "grad_norm": 0.38188805603816467, + "learning_rate": 2.6630359427718468e-05, + "loss": 0.4667, + "step": 560 + }, + { + "epoch": 2.2712550607287447, + "grad_norm": 0.46925988661233364, + "learning_rate": 2.6576976876493225e-05, + "loss": 0.4689, + "step": 561 + }, + { + "epoch": 2.2753036437246963, + "grad_norm": 0.37793021251002573, + "learning_rate": 2.652354173593614e-05, + "loss": 0.4797, + "step": 562 + }, + { + "epoch": 2.279352226720648, + "grad_norm": 0.4605648510080909, + "learning_rate": 2.647005443331317e-05, + "loss": 0.4563, + "step": 563 + }, + { + "epoch": 2.283400809716599, + "grad_norm": 0.43125599069077186, + "learning_rate": 2.6416515396307354e-05, + "loss": 0.4742, + "step": 564 + }, + { + "epoch": 2.2874493927125505, + "grad_norm": 0.46432052133395, + "learning_rate": 2.636292505301542e-05, + "loss": 0.4898, + "step": 565 + }, + { + "epoch": 2.291497975708502, + "grad_norm": 0.44733140224716633, + "learning_rate": 2.630928383194431e-05, + "loss": 0.4562, + "step": 566 + }, + { + "epoch": 2.2955465587044532, + "grad_norm": 0.48860470102474335, + "learning_rate": 2.625559216200781e-05, + "loss": 0.4753, + "step": 567 + }, + { + "epoch": 2.299595141700405, + "grad_norm": 0.36079111143282705, + "learning_rate": 2.620185047252308e-05, + "loss": 0.4859, + "step": 568 + }, + { + "epoch": 2.3036437246963564, + "grad_norm": 0.3702166687096711, + "learning_rate": 2.614805919320723e-05, + "loss": 0.485, + "step": 569 + }, + { + "epoch": 2.3076923076923075, + "grad_norm": 0.35874775260123865, + "learning_rate": 2.6094218754173895e-05, + "loss": 0.4859, + "step": 570 + }, + { + "epoch": 2.311740890688259, + "grad_norm": 0.42129381075605, + "learning_rate": 2.60403295859298e-05, + "loss": 0.4669, + "step": 571 + }, + { + "epoch": 2.3157894736842106, + "grad_norm": 0.38504775067315683, + "learning_rate": 2.5986392119371297e-05, + "loss": 0.4648, + "step": 572 + }, + { + "epoch": 2.3198380566801617, + "grad_norm": 0.3891173682528562, + "learning_rate": 2.5932406785780928e-05, + "loss": 0.4579, + "step": 573 + }, + { + "epoch": 2.3238866396761133, + "grad_norm": 0.3426575406941934, + "learning_rate": 2.5878374016823987e-05, + "loss": 0.4579, + "step": 574 + }, + { + "epoch": 2.327935222672065, + "grad_norm": 0.4511644725966341, + "learning_rate": 2.5824294244545045e-05, + "loss": 0.485, + "step": 575 + }, + { + "epoch": 2.331983805668016, + "grad_norm": 0.29572287582732354, + "learning_rate": 2.577016790136453e-05, + "loss": 0.4831, + "step": 576 + }, + { + "epoch": 2.3360323886639676, + "grad_norm": 0.3313896962120594, + "learning_rate": 2.5715995420075225e-05, + "loss": 0.4766, + "step": 577 + }, + { + "epoch": 2.340080971659919, + "grad_norm": 0.3315563690434995, + "learning_rate": 2.5661777233838864e-05, + "loss": 0.4603, + "step": 578 + }, + { + "epoch": 2.3441295546558703, + "grad_norm": 0.3373110078275791, + "learning_rate": 2.5607513776182616e-05, + "loss": 0.4538, + "step": 579 + }, + { + "epoch": 2.348178137651822, + "grad_norm": 0.3477669631255805, + "learning_rate": 2.5553205480995633e-05, + "loss": 0.4641, + "step": 580 + }, + { + "epoch": 2.3522267206477734, + "grad_norm": 0.3440817599220889, + "learning_rate": 2.5498852782525604e-05, + "loss": 0.4634, + "step": 581 + }, + { + "epoch": 2.3562753036437245, + "grad_norm": 0.37659900133153484, + "learning_rate": 2.5444456115375252e-05, + "loss": 0.4497, + "step": 582 + }, + { + "epoch": 2.360323886639676, + "grad_norm": 0.3602350626809477, + "learning_rate": 2.539001591449889e-05, + "loss": 0.4553, + "step": 583 + }, + { + "epoch": 2.3643724696356276, + "grad_norm": 0.39741638228239157, + "learning_rate": 2.53355326151989e-05, + "loss": 0.4776, + "step": 584 + }, + { + "epoch": 2.3684210526315788, + "grad_norm": 0.32748728437779256, + "learning_rate": 2.5281006653122288e-05, + "loss": 0.4677, + "step": 585 + }, + { + "epoch": 2.3724696356275303, + "grad_norm": 0.3861007820195246, + "learning_rate": 2.5226438464257217e-05, + "loss": 0.4601, + "step": 586 + }, + { + "epoch": 2.376518218623482, + "grad_norm": 0.36997494102133976, + "learning_rate": 2.5171828484929447e-05, + "loss": 0.4839, + "step": 587 + }, + { + "epoch": 2.380566801619433, + "grad_norm": 0.37491367405944975, + "learning_rate": 2.5117177151798934e-05, + "loss": 0.4591, + "step": 588 + }, + { + "epoch": 2.3846153846153846, + "grad_norm": 0.3233274364368284, + "learning_rate": 2.506248490185627e-05, + "loss": 0.4802, + "step": 589 + }, + { + "epoch": 2.388663967611336, + "grad_norm": 0.35083045483335773, + "learning_rate": 2.500775217241923e-05, + "loss": 0.4739, + "step": 590 + }, + { + "epoch": 2.3927125506072873, + "grad_norm": 0.326044765223085, + "learning_rate": 2.4952979401129266e-05, + "loss": 0.4779, + "step": 591 + }, + { + "epoch": 2.396761133603239, + "grad_norm": 0.34841866611269434, + "learning_rate": 2.4898167025948e-05, + "loss": 0.4512, + "step": 592 + }, + { + "epoch": 2.4008097165991904, + "grad_norm": 0.31477475403259236, + "learning_rate": 2.4843315485153703e-05, + "loss": 0.476, + "step": 593 + }, + { + "epoch": 2.4048582995951415, + "grad_norm": 0.3482626468712851, + "learning_rate": 2.4788425217337856e-05, + "loss": 0.4807, + "step": 594 + }, + { + "epoch": 2.408906882591093, + "grad_norm": 0.32164393241425837, + "learning_rate": 2.4733496661401572e-05, + "loss": 0.4709, + "step": 595 + }, + { + "epoch": 2.4129554655870447, + "grad_norm": 0.3970875387432804, + "learning_rate": 2.4678530256552114e-05, + "loss": 0.4894, + "step": 596 + }, + { + "epoch": 2.417004048582996, + "grad_norm": 0.34086951114197794, + "learning_rate": 2.46235264422994e-05, + "loss": 0.4649, + "step": 597 + }, + { + "epoch": 2.4210526315789473, + "grad_norm": 0.35673013344339477, + "learning_rate": 2.4568485658452452e-05, + "loss": 0.4714, + "step": 598 + }, + { + "epoch": 2.425101214574899, + "grad_norm": 0.3323238295952803, + "learning_rate": 2.451340834511592e-05, + "loss": 0.4692, + "step": 599 + }, + { + "epoch": 2.42914979757085, + "grad_norm": 0.39056065594393535, + "learning_rate": 2.4458294942686528e-05, + "loss": 0.4698, + "step": 600 + }, + { + "epoch": 2.4331983805668016, + "grad_norm": 0.303973712665435, + "learning_rate": 2.440314589184958e-05, + "loss": 0.4784, + "step": 601 + }, + { + "epoch": 2.437246963562753, + "grad_norm": 0.38368627274800393, + "learning_rate": 2.434796163357541e-05, + "loss": 0.4841, + "step": 602 + }, + { + "epoch": 2.4412955465587043, + "grad_norm": 0.35763831536025387, + "learning_rate": 2.429274260911588e-05, + "loss": 0.4631, + "step": 603 + }, + { + "epoch": 2.445344129554656, + "grad_norm": 0.37175290371079334, + "learning_rate": 2.423748926000084e-05, + "loss": 0.4458, + "step": 604 + }, + { + "epoch": 2.4493927125506074, + "grad_norm": 0.3585467420104883, + "learning_rate": 2.418220202803459e-05, + "loss": 0.4796, + "step": 605 + }, + { + "epoch": 2.4534412955465585, + "grad_norm": 0.3655276274995093, + "learning_rate": 2.412688135529237e-05, + "loss": 0.471, + "step": 606 + }, + { + "epoch": 2.45748987854251, + "grad_norm": 0.4176348120637941, + "learning_rate": 2.4071527684116807e-05, + "loss": 0.4792, + "step": 607 + }, + { + "epoch": 2.4615384615384617, + "grad_norm": 0.3582853844595898, + "learning_rate": 2.4016141457114372e-05, + "loss": 0.479, + "step": 608 + }, + { + "epoch": 2.465587044534413, + "grad_norm": 0.36586477669709805, + "learning_rate": 2.396072311715187e-05, + "loss": 0.4681, + "step": 609 + }, + { + "epoch": 2.4696356275303644, + "grad_norm": 0.36553198190210434, + "learning_rate": 2.3905273107352863e-05, + "loss": 0.4639, + "step": 610 + }, + { + "epoch": 2.473684210526316, + "grad_norm": 0.31806306388717664, + "learning_rate": 2.3849791871094157e-05, + "loss": 0.4759, + "step": 611 + }, + { + "epoch": 2.477732793522267, + "grad_norm": 0.3343846510914838, + "learning_rate": 2.379427985200223e-05, + "loss": 0.494, + "step": 612 + }, + { + "epoch": 2.4817813765182186, + "grad_norm": 0.3509763594646804, + "learning_rate": 2.373873749394972e-05, + "loss": 0.4719, + "step": 613 + }, + { + "epoch": 2.48582995951417, + "grad_norm": 0.38163474874396014, + "learning_rate": 2.3683165241051836e-05, + "loss": 0.48, + "step": 614 + }, + { + "epoch": 2.4898785425101213, + "grad_norm": 0.34888297907860066, + "learning_rate": 2.3627563537662823e-05, + "loss": 0.47, + "step": 615 + }, + { + "epoch": 2.493927125506073, + "grad_norm": 0.5043817163040952, + "learning_rate": 2.3571932828372433e-05, + "loss": 0.4701, + "step": 616 + }, + { + "epoch": 2.4979757085020244, + "grad_norm": 0.31986595378205324, + "learning_rate": 2.351627355800233e-05, + "loss": 0.4578, + "step": 617 + }, + { + "epoch": 2.5020242914979756, + "grad_norm": 0.44809394604156066, + "learning_rate": 2.346058617160256e-05, + "loss": 0.4724, + "step": 618 + }, + { + "epoch": 2.506072874493927, + "grad_norm": 0.3803406268645901, + "learning_rate": 2.3404871114447976e-05, + "loss": 0.4675, + "step": 619 + }, + { + "epoch": 2.5101214574898787, + "grad_norm": 0.38727070679134573, + "learning_rate": 2.334912883203469e-05, + "loss": 0.4691, + "step": 620 + }, + { + "epoch": 2.51417004048583, + "grad_norm": 0.4085269350736793, + "learning_rate": 2.3293359770076505e-05, + "loss": 0.4735, + "step": 621 + }, + { + "epoch": 2.5182186234817814, + "grad_norm": 0.30185259471088327, + "learning_rate": 2.323756437450136e-05, + "loss": 0.4864, + "step": 622 + }, + { + "epoch": 2.522267206477733, + "grad_norm": 0.3894773932462322, + "learning_rate": 2.3181743091447754e-05, + "loss": 0.4577, + "step": 623 + }, + { + "epoch": 2.526315789473684, + "grad_norm": 0.32351716330654307, + "learning_rate": 2.3125896367261164e-05, + "loss": 0.4764, + "step": 624 + }, + { + "epoch": 2.5303643724696356, + "grad_norm": 0.34173411462586567, + "learning_rate": 2.307002464849052e-05, + "loss": 0.4718, + "step": 625 + }, + { + "epoch": 2.534412955465587, + "grad_norm": 0.3516830125710817, + "learning_rate": 2.30141283818846e-05, + "loss": 0.4489, + "step": 626 + }, + { + "epoch": 2.5384615384615383, + "grad_norm": 0.3289270653436247, + "learning_rate": 2.2958208014388462e-05, + "loss": 0.4603, + "step": 627 + }, + { + "epoch": 2.54251012145749, + "grad_norm": 0.3359630658424367, + "learning_rate": 2.2902263993139857e-05, + "loss": 0.4811, + "step": 628 + }, + { + "epoch": 2.5465587044534415, + "grad_norm": 0.34174714321643945, + "learning_rate": 2.2846296765465708e-05, + "loss": 0.4679, + "step": 629 + }, + { + "epoch": 2.5506072874493926, + "grad_norm": 0.30507686335405604, + "learning_rate": 2.2790306778878465e-05, + "loss": 0.4698, + "step": 630 + }, + { + "epoch": 2.554655870445344, + "grad_norm": 0.3136405593559288, + "learning_rate": 2.273429448107257e-05, + "loss": 0.4813, + "step": 631 + }, + { + "epoch": 2.5587044534412957, + "grad_norm": 0.332931904968984, + "learning_rate": 2.2678260319920868e-05, + "loss": 0.4629, + "step": 632 + }, + { + "epoch": 2.562753036437247, + "grad_norm": 0.311658805962014, + "learning_rate": 2.262220474347102e-05, + "loss": 0.4585, + "step": 633 + }, + { + "epoch": 2.5668016194331984, + "grad_norm": 0.3117286819046009, + "learning_rate": 2.2566128199941918e-05, + "loss": 0.4712, + "step": 634 + }, + { + "epoch": 2.57085020242915, + "grad_norm": 0.36469265045480437, + "learning_rate": 2.2510031137720104e-05, + "loss": 0.4598, + "step": 635 + }, + { + "epoch": 2.574898785425101, + "grad_norm": 0.2839508147983164, + "learning_rate": 2.2453914005356206e-05, + "loss": 0.5082, + "step": 636 + }, + { + "epoch": 2.5789473684210527, + "grad_norm": 0.3621309008665885, + "learning_rate": 2.2397777251561302e-05, + "loss": 0.4797, + "step": 637 + }, + { + "epoch": 2.582995951417004, + "grad_norm": 0.3233280989264786, + "learning_rate": 2.2341621325203393e-05, + "loss": 0.4907, + "step": 638 + }, + { + "epoch": 2.5870445344129553, + "grad_norm": 0.32922250296269107, + "learning_rate": 2.2285446675303764e-05, + "loss": 0.471, + "step": 639 + }, + { + "epoch": 2.591093117408907, + "grad_norm": 0.3046512033855943, + "learning_rate": 2.2229253751033423e-05, + "loss": 0.4732, + "step": 640 + }, + { + "epoch": 2.5951417004048585, + "grad_norm": 0.2831733484243294, + "learning_rate": 2.2173043001709492e-05, + "loss": 0.478, + "step": 641 + }, + { + "epoch": 2.5991902834008096, + "grad_norm": 0.3504749377354086, + "learning_rate": 2.2116814876791627e-05, + "loss": 0.467, + "step": 642 + }, + { + "epoch": 2.603238866396761, + "grad_norm": 0.29875773004011347, + "learning_rate": 2.2060569825878413e-05, + "loss": 0.464, + "step": 643 + }, + { + "epoch": 2.6072874493927127, + "grad_norm": 0.32165733067425256, + "learning_rate": 2.2004308298703777e-05, + "loss": 0.4876, + "step": 644 + }, + { + "epoch": 2.611336032388664, + "grad_norm": 0.3007203918461871, + "learning_rate": 2.1948030745133396e-05, + "loss": 0.4706, + "step": 645 + }, + { + "epoch": 2.6153846153846154, + "grad_norm": 0.3135960643322974, + "learning_rate": 2.1891737615161083e-05, + "loss": 0.4626, + "step": 646 + }, + { + "epoch": 2.619433198380567, + "grad_norm": 0.32427753547893956, + "learning_rate": 2.1835429358905218e-05, + "loss": 0.4672, + "step": 647 + }, + { + "epoch": 2.623481781376518, + "grad_norm": 0.33476942408537713, + "learning_rate": 2.17791064266051e-05, + "loss": 0.4645, + "step": 648 + }, + { + "epoch": 2.6275303643724697, + "grad_norm": 0.31649300179640893, + "learning_rate": 2.172276926861741e-05, + "loss": 0.4743, + "step": 649 + }, + { + "epoch": 2.6315789473684212, + "grad_norm": 0.31768589472707026, + "learning_rate": 2.166641833541255e-05, + "loss": 0.468, + "step": 650 + }, + { + "epoch": 2.6356275303643724, + "grad_norm": 0.33028944430403434, + "learning_rate": 2.161005407757109e-05, + "loss": 0.4532, + "step": 651 + }, + { + "epoch": 2.639676113360324, + "grad_norm": 0.302483299095317, + "learning_rate": 2.155367694578013e-05, + "loss": 0.4819, + "step": 652 + }, + { + "epoch": 2.6437246963562755, + "grad_norm": 0.3536366573491848, + "learning_rate": 2.1497287390829712e-05, + "loss": 0.477, + "step": 653 + }, + { + "epoch": 2.6477732793522266, + "grad_norm": 0.30598265942096503, + "learning_rate": 2.1440885863609208e-05, + "loss": 0.4803, + "step": 654 + }, + { + "epoch": 2.651821862348178, + "grad_norm": 0.30999528367794305, + "learning_rate": 2.1384472815103737e-05, + "loss": 0.458, + "step": 655 + }, + { + "epoch": 2.6558704453441297, + "grad_norm": 0.350195897974722, + "learning_rate": 2.1328048696390534e-05, + "loss": 0.4815, + "step": 656 + }, + { + "epoch": 2.659919028340081, + "grad_norm": 0.37060919417675453, + "learning_rate": 2.1271613958635342e-05, + "loss": 0.4867, + "step": 657 + }, + { + "epoch": 2.6639676113360324, + "grad_norm": 0.36560319023462984, + "learning_rate": 2.1215169053088825e-05, + "loss": 0.4569, + "step": 658 + }, + { + "epoch": 2.668016194331984, + "grad_norm": 0.3314019334883962, + "learning_rate": 2.1158714431082937e-05, + "loss": 0.4758, + "step": 659 + }, + { + "epoch": 2.672064777327935, + "grad_norm": 0.46988782171655563, + "learning_rate": 2.110225054402733e-05, + "loss": 0.4712, + "step": 660 + }, + { + "epoch": 2.6761133603238867, + "grad_norm": 0.3410482456079, + "learning_rate": 2.1045777843405747e-05, + "loss": 0.4875, + "step": 661 + }, + { + "epoch": 2.6801619433198383, + "grad_norm": 0.34162144130301464, + "learning_rate": 2.09892967807724e-05, + "loss": 0.4761, + "step": 662 + }, + { + "epoch": 2.6842105263157894, + "grad_norm": 0.298288139149004, + "learning_rate": 2.093280780774835e-05, + "loss": 0.4768, + "step": 663 + }, + { + "epoch": 2.688259109311741, + "grad_norm": 0.3385298260242562, + "learning_rate": 2.087631137601793e-05, + "loss": 0.4754, + "step": 664 + }, + { + "epoch": 2.6923076923076925, + "grad_norm": 0.2888870921061015, + "learning_rate": 2.0819807937325104e-05, + "loss": 0.464, + "step": 665 + }, + { + "epoch": 2.6963562753036436, + "grad_norm": 0.34346896754454553, + "learning_rate": 2.0763297943469847e-05, + "loss": 0.4704, + "step": 666 + }, + { + "epoch": 2.700404858299595, + "grad_norm": 0.3038289102570644, + "learning_rate": 2.070678184630458e-05, + "loss": 0.4587, + "step": 667 + }, + { + "epoch": 2.7044534412955468, + "grad_norm": 0.34339827099837295, + "learning_rate": 2.06502600977305e-05, + "loss": 0.4677, + "step": 668 + }, + { + "epoch": 2.708502024291498, + "grad_norm": 0.32201713444714464, + "learning_rate": 2.0593733149694008e-05, + "loss": 0.4618, + "step": 669 + }, + { + "epoch": 2.7125506072874495, + "grad_norm": 0.36296637557038713, + "learning_rate": 2.0537201454183074e-05, + "loss": 0.4563, + "step": 670 + }, + { + "epoch": 2.716599190283401, + "grad_norm": 0.3456821093327759, + "learning_rate": 2.0480665463223626e-05, + "loss": 0.4869, + "step": 671 + }, + { + "epoch": 2.720647773279352, + "grad_norm": 0.3272477673973111, + "learning_rate": 2.042412562887594e-05, + "loss": 0.4728, + "step": 672 + }, + { + "epoch": 2.7246963562753037, + "grad_norm": 0.3866003204906215, + "learning_rate": 2.0367582403231033e-05, + "loss": 0.4723, + "step": 673 + }, + { + "epoch": 2.7287449392712553, + "grad_norm": 0.3073713438860689, + "learning_rate": 2.0311036238407023e-05, + "loss": 0.4609, + "step": 674 + }, + { + "epoch": 2.7327935222672064, + "grad_norm": 0.3922461608910711, + "learning_rate": 2.0254487586545534e-05, + "loss": 0.4887, + "step": 675 + }, + { + "epoch": 2.736842105263158, + "grad_norm": 0.27893091137961484, + "learning_rate": 2.0197936899808088e-05, + "loss": 0.4528, + "step": 676 + }, + { + "epoch": 2.7408906882591095, + "grad_norm": 0.3678379085622595, + "learning_rate": 2.0141384630372466e-05, + "loss": 0.4748, + "step": 677 + }, + { + "epoch": 2.7449392712550607, + "grad_norm": 0.3057727233857769, + "learning_rate": 2.0084831230429106e-05, + "loss": 0.4779, + "step": 678 + }, + { + "epoch": 2.748987854251012, + "grad_norm": 0.36732655096292677, + "learning_rate": 2.0028277152177492e-05, + "loss": 0.4965, + "step": 679 + }, + { + "epoch": 2.753036437246964, + "grad_norm": 0.33240567014777495, + "learning_rate": 1.9971722847822518e-05, + "loss": 0.4667, + "step": 680 + }, + { + "epoch": 2.757085020242915, + "grad_norm": 0.3303802378860808, + "learning_rate": 1.99151687695709e-05, + "loss": 0.4688, + "step": 681 + }, + { + "epoch": 2.7611336032388665, + "grad_norm": 0.37329682185170615, + "learning_rate": 1.9858615369627537e-05, + "loss": 0.4756, + "step": 682 + }, + { + "epoch": 2.765182186234818, + "grad_norm": 0.3850595273440119, + "learning_rate": 1.9802063100191916e-05, + "loss": 0.4567, + "step": 683 + }, + { + "epoch": 2.769230769230769, + "grad_norm": 0.3663096864871412, + "learning_rate": 1.974551241345447e-05, + "loss": 0.4661, + "step": 684 + }, + { + "epoch": 2.7732793522267207, + "grad_norm": 0.3599165352209678, + "learning_rate": 1.9688963761592984e-05, + "loss": 0.4504, + "step": 685 + }, + { + "epoch": 2.7773279352226723, + "grad_norm": 0.38821124338314106, + "learning_rate": 1.963241759676897e-05, + "loss": 0.4732, + "step": 686 + }, + { + "epoch": 2.7813765182186234, + "grad_norm": 0.358350604687425, + "learning_rate": 1.9575874371124066e-05, + "loss": 0.4799, + "step": 687 + }, + { + "epoch": 2.785425101214575, + "grad_norm": 0.40827396803548827, + "learning_rate": 1.951933453677638e-05, + "loss": 0.4805, + "step": 688 + }, + { + "epoch": 2.7894736842105265, + "grad_norm": 0.35373790989653736, + "learning_rate": 1.9462798545816932e-05, + "loss": 0.454, + "step": 689 + }, + { + "epoch": 2.7935222672064777, + "grad_norm": 0.363751919325277, + "learning_rate": 1.9406266850305996e-05, + "loss": 0.4596, + "step": 690 + }, + { + "epoch": 2.7975708502024292, + "grad_norm": 0.33994129204769535, + "learning_rate": 1.9349739902269503e-05, + "loss": 0.481, + "step": 691 + }, + { + "epoch": 2.801619433198381, + "grad_norm": 0.34565772212921586, + "learning_rate": 1.9293218153695425e-05, + "loss": 0.4643, + "step": 692 + }, + { + "epoch": 2.805668016194332, + "grad_norm": 0.3109370153332686, + "learning_rate": 1.9236702056530153e-05, + "loss": 0.4778, + "step": 693 + }, + { + "epoch": 2.8097165991902835, + "grad_norm": 0.3357299663575633, + "learning_rate": 1.9180192062674907e-05, + "loss": 0.4853, + "step": 694 + }, + { + "epoch": 2.813765182186235, + "grad_norm": 0.29742860144277455, + "learning_rate": 1.9123688623982076e-05, + "loss": 0.4704, + "step": 695 + }, + { + "epoch": 2.817813765182186, + "grad_norm": 0.35922528314987906, + "learning_rate": 1.906719219225165e-05, + "loss": 0.4758, + "step": 696 + }, + { + "epoch": 2.8218623481781377, + "grad_norm": 0.32391005534615974, + "learning_rate": 1.9010703219227603e-05, + "loss": 0.4697, + "step": 697 + }, + { + "epoch": 2.8259109311740893, + "grad_norm": 0.33210164499127826, + "learning_rate": 1.8954222156594256e-05, + "loss": 0.4752, + "step": 698 + }, + { + "epoch": 2.8299595141700404, + "grad_norm": 0.31726860344691454, + "learning_rate": 1.8897749455972673e-05, + "loss": 0.4657, + "step": 699 + }, + { + "epoch": 2.834008097165992, + "grad_norm": 0.3306097933209381, + "learning_rate": 1.884128556891707e-05, + "loss": 0.4658, + "step": 700 + }, + { + "epoch": 2.8380566801619436, + "grad_norm": 0.3424920513114646, + "learning_rate": 1.878483094691119e-05, + "loss": 0.476, + "step": 701 + }, + { + "epoch": 2.8421052631578947, + "grad_norm": 0.28904704909201984, + "learning_rate": 1.8728386041364664e-05, + "loss": 0.4692, + "step": 702 + }, + { + "epoch": 2.8461538461538463, + "grad_norm": 0.3595502806011488, + "learning_rate": 1.867195130360947e-05, + "loss": 0.466, + "step": 703 + }, + { + "epoch": 2.850202429149798, + "grad_norm": 0.2730135535030052, + "learning_rate": 1.8615527184896263e-05, + "loss": 0.4747, + "step": 704 + }, + { + "epoch": 2.854251012145749, + "grad_norm": 0.33496161092061855, + "learning_rate": 1.8559114136390795e-05, + "loss": 0.4866, + "step": 705 + }, + { + "epoch": 2.8582995951417005, + "grad_norm": 0.2877227589279155, + "learning_rate": 1.8502712609170298e-05, + "loss": 0.4789, + "step": 706 + }, + { + "epoch": 2.862348178137652, + "grad_norm": 0.29099491510428, + "learning_rate": 1.8446323054219876e-05, + "loss": 0.4855, + "step": 707 + }, + { + "epoch": 2.866396761133603, + "grad_norm": 0.29740243907780906, + "learning_rate": 1.838994592242891e-05, + "loss": 0.4663, + "step": 708 + }, + { + "epoch": 2.8704453441295548, + "grad_norm": 0.29543102669769844, + "learning_rate": 1.8333581664587453e-05, + "loss": 0.4395, + "step": 709 + }, + { + "epoch": 2.8744939271255063, + "grad_norm": 0.3204411434370082, + "learning_rate": 1.8277230731382593e-05, + "loss": 0.4738, + "step": 710 + }, + { + "epoch": 2.8785425101214575, + "grad_norm": 0.28886011765893554, + "learning_rate": 1.82208935733949e-05, + "loss": 0.4846, + "step": 711 + }, + { + "epoch": 2.882591093117409, + "grad_norm": 0.9417814970165729, + "learning_rate": 1.8164570641094793e-05, + "loss": 0.5128, + "step": 712 + }, + { + "epoch": 2.8866396761133606, + "grad_norm": 0.27661003241316195, + "learning_rate": 1.810826238483892e-05, + "loss": 0.4742, + "step": 713 + }, + { + "epoch": 2.8906882591093117, + "grad_norm": 0.3086585071380245, + "learning_rate": 1.8051969254866608e-05, + "loss": 0.4818, + "step": 714 + }, + { + "epoch": 2.8947368421052633, + "grad_norm": 0.30078715055061295, + "learning_rate": 1.7995691701296226e-05, + "loss": 0.4446, + "step": 715 + }, + { + "epoch": 2.898785425101215, + "grad_norm": 0.2871803436954661, + "learning_rate": 1.7939430174121593e-05, + "loss": 0.4532, + "step": 716 + }, + { + "epoch": 2.902834008097166, + "grad_norm": 0.3138947010184722, + "learning_rate": 1.788318512320838e-05, + "loss": 0.4508, + "step": 717 + }, + { + "epoch": 2.9068825910931175, + "grad_norm": 0.30361044615173394, + "learning_rate": 1.782695699829051e-05, + "loss": 0.4843, + "step": 718 + }, + { + "epoch": 2.910931174089069, + "grad_norm": 0.2808852401394827, + "learning_rate": 1.7770746248966587e-05, + "loss": 0.4582, + "step": 719 + }, + { + "epoch": 2.91497975708502, + "grad_norm": 0.3083753302687146, + "learning_rate": 1.7714553324696243e-05, + "loss": 0.475, + "step": 720 + }, + { + "epoch": 2.919028340080972, + "grad_norm": 0.3132897444909797, + "learning_rate": 1.7658378674796614e-05, + "loss": 0.469, + "step": 721 + }, + { + "epoch": 2.9230769230769234, + "grad_norm": 0.36205543815132457, + "learning_rate": 1.76022227484387e-05, + "loss": 0.4875, + "step": 722 + }, + { + "epoch": 2.9271255060728745, + "grad_norm": 0.31189433187662546, + "learning_rate": 1.7546085994643807e-05, + "loss": 0.4628, + "step": 723 + }, + { + "epoch": 2.931174089068826, + "grad_norm": 0.2874349653410532, + "learning_rate": 1.7489968862279902e-05, + "loss": 0.4773, + "step": 724 + }, + { + "epoch": 2.9352226720647776, + "grad_norm": 0.29349611573681844, + "learning_rate": 1.743387180005809e-05, + "loss": 0.4726, + "step": 725 + }, + { + "epoch": 2.9392712550607287, + "grad_norm": 0.29408824436113395, + "learning_rate": 1.737779525652899e-05, + "loss": 0.4672, + "step": 726 + }, + { + "epoch": 2.9433198380566803, + "grad_norm": 0.35048544272501203, + "learning_rate": 1.732173968007914e-05, + "loss": 0.4683, + "step": 727 + }, + { + "epoch": 2.9473684210526314, + "grad_norm": 0.29914971824174563, + "learning_rate": 1.7265705518927437e-05, + "loss": 0.4802, + "step": 728 + }, + { + "epoch": 2.951417004048583, + "grad_norm": 0.3410707511238311, + "learning_rate": 1.7209693221121542e-05, + "loss": 0.4601, + "step": 729 + }, + { + "epoch": 2.9554655870445345, + "grad_norm": 0.33866593860371036, + "learning_rate": 1.7153703234534302e-05, + "loss": 0.4719, + "step": 730 + }, + { + "epoch": 2.9595141700404857, + "grad_norm": 0.31519873092215756, + "learning_rate": 1.709773600686015e-05, + "loss": 0.4903, + "step": 731 + }, + { + "epoch": 2.9635627530364372, + "grad_norm": 0.3119387947740441, + "learning_rate": 1.7041791985611548e-05, + "loss": 0.4584, + "step": 732 + }, + { + "epoch": 2.967611336032389, + "grad_norm": 0.344297030115303, + "learning_rate": 1.69858716181154e-05, + "loss": 0.4544, + "step": 733 + }, + { + "epoch": 2.97165991902834, + "grad_norm": 0.27305573370869207, + "learning_rate": 1.692997535150948e-05, + "loss": 0.4801, + "step": 734 + }, + { + "epoch": 2.9757085020242915, + "grad_norm": 0.30897170847665006, + "learning_rate": 1.687410363273884e-05, + "loss": 0.4801, + "step": 735 + }, + { + "epoch": 2.979757085020243, + "grad_norm": 0.3323742547274772, + "learning_rate": 1.6818256908552257e-05, + "loss": 0.4516, + "step": 736 + }, + { + "epoch": 2.983805668016194, + "grad_norm": 0.2855963734008308, + "learning_rate": 1.6762435625498646e-05, + "loss": 0.4433, + "step": 737 + }, + { + "epoch": 2.9878542510121457, + "grad_norm": 0.2742376352429609, + "learning_rate": 1.67066402299235e-05, + "loss": 0.4622, + "step": 738 + }, + { + "epoch": 2.9919028340080973, + "grad_norm": 0.32590838548268597, + "learning_rate": 1.6650871167965313e-05, + "loss": 0.4532, + "step": 739 + }, + { + "epoch": 2.9959514170040484, + "grad_norm": 0.29238168793636055, + "learning_rate": 1.6595128885552028e-05, + "loss": 0.4704, + "step": 740 + }, + { + "epoch": 3.0, + "grad_norm": 0.3063776998072053, + "learning_rate": 1.653941382839745e-05, + "loss": 0.4558, + "step": 741 + }, + { + "epoch": 3.0040485829959516, + "grad_norm": 0.47020268979759683, + "learning_rate": 1.6483726441997673e-05, + "loss": 0.4145, + "step": 742 + }, + { + "epoch": 3.0080971659919027, + "grad_norm": 0.35013469844452316, + "learning_rate": 1.642806717162757e-05, + "loss": 0.3894, + "step": 743 + }, + { + "epoch": 3.0121457489878543, + "grad_norm": 0.6038473772462262, + "learning_rate": 1.637243646233718e-05, + "loss": 0.3944, + "step": 744 + }, + { + "epoch": 3.016194331983806, + "grad_norm": 0.5928692805303908, + "learning_rate": 1.6316834758948174e-05, + "loss": 0.4361, + "step": 745 + }, + { + "epoch": 3.020242914979757, + "grad_norm": 0.467563311823661, + "learning_rate": 1.6261262506050282e-05, + "loss": 0.4121, + "step": 746 + }, + { + "epoch": 3.0242914979757085, + "grad_norm": 0.35909206816783784, + "learning_rate": 1.620572014799777e-05, + "loss": 0.4079, + "step": 747 + }, + { + "epoch": 3.02834008097166, + "grad_norm": 0.4176368143252143, + "learning_rate": 1.6150208128905857e-05, + "loss": 0.409, + "step": 748 + }, + { + "epoch": 3.032388663967611, + "grad_norm": 0.4340286108130099, + "learning_rate": 1.6094726892647147e-05, + "loss": 0.3952, + "step": 749 + }, + { + "epoch": 3.0364372469635628, + "grad_norm": 0.39798184382786383, + "learning_rate": 1.6039276882848135e-05, + "loss": 0.3916, + "step": 750 + }, + { + "epoch": 3.0404858299595143, + "grad_norm": 0.4211512391371717, + "learning_rate": 1.5983858542885635e-05, + "loss": 0.3825, + "step": 751 + }, + { + "epoch": 3.0445344129554655, + "grad_norm": 0.36513888965892505, + "learning_rate": 1.5928472315883203e-05, + "loss": 0.4021, + "step": 752 + }, + { + "epoch": 3.048582995951417, + "grad_norm": 0.3828145516699195, + "learning_rate": 1.5873118644707633e-05, + "loss": 0.4034, + "step": 753 + }, + { + "epoch": 3.0526315789473686, + "grad_norm": 0.3625023427209613, + "learning_rate": 1.5817797971965413e-05, + "loss": 0.3802, + "step": 754 + }, + { + "epoch": 3.0566801619433197, + "grad_norm": 0.3307646942092969, + "learning_rate": 1.576251073999917e-05, + "loss": 0.3992, + "step": 755 + }, + { + "epoch": 3.0607287449392713, + "grad_norm": 0.3764630940923384, + "learning_rate": 1.5707257390884126e-05, + "loss": 0.3819, + "step": 756 + }, + { + "epoch": 3.064777327935223, + "grad_norm": 0.3536487231964897, + "learning_rate": 1.5652038366424595e-05, + "loss": 0.3835, + "step": 757 + }, + { + "epoch": 3.068825910931174, + "grad_norm": 0.341091257672784, + "learning_rate": 1.5596854108150424e-05, + "loss": 0.3882, + "step": 758 + }, + { + "epoch": 3.0728744939271255, + "grad_norm": 0.4418188726507605, + "learning_rate": 1.5541705057313476e-05, + "loss": 0.4071, + "step": 759 + }, + { + "epoch": 3.076923076923077, + "grad_norm": 0.33226439855907913, + "learning_rate": 1.5486591654884086e-05, + "loss": 0.4138, + "step": 760 + }, + { + "epoch": 3.080971659919028, + "grad_norm": 0.34958945516212986, + "learning_rate": 1.543151434154755e-05, + "loss": 0.4037, + "step": 761 + }, + { + "epoch": 3.08502024291498, + "grad_norm": 0.3316440411170271, + "learning_rate": 1.5376473557700615e-05, + "loss": 0.4006, + "step": 762 + }, + { + "epoch": 3.0890688259109313, + "grad_norm": 0.32339105456377293, + "learning_rate": 1.5321469743447893e-05, + "loss": 0.3926, + "step": 763 + }, + { + "epoch": 3.0931174089068825, + "grad_norm": 0.2965961077665869, + "learning_rate": 1.5266503338598434e-05, + "loss": 0.4211, + "step": 764 + }, + { + "epoch": 3.097165991902834, + "grad_norm": 0.2934465581260307, + "learning_rate": 1.5211574782662149e-05, + "loss": 0.4107, + "step": 765 + }, + { + "epoch": 3.1012145748987856, + "grad_norm": 0.30748642889930955, + "learning_rate": 1.5156684514846307e-05, + "loss": 0.3854, + "step": 766 + }, + { + "epoch": 3.1052631578947367, + "grad_norm": 0.2857971484072039, + "learning_rate": 1.5101832974052012e-05, + "loss": 0.4037, + "step": 767 + }, + { + "epoch": 3.1093117408906883, + "grad_norm": 0.3036256448093267, + "learning_rate": 1.5047020598870737e-05, + "loss": 0.3925, + "step": 768 + }, + { + "epoch": 3.11336032388664, + "grad_norm": 0.3044484387216606, + "learning_rate": 1.4992247827580778e-05, + "loss": 0.3882, + "step": 769 + }, + { + "epoch": 3.117408906882591, + "grad_norm": 0.2820156848268788, + "learning_rate": 1.493751509814374e-05, + "loss": 0.4064, + "step": 770 + }, + { + "epoch": 3.1214574898785425, + "grad_norm": 0.2964875179324039, + "learning_rate": 1.4882822848201073e-05, + "loss": 0.4025, + "step": 771 + }, + { + "epoch": 3.125506072874494, + "grad_norm": 0.2639983591779373, + "learning_rate": 1.4828171515070553e-05, + "loss": 0.4315, + "step": 772 + }, + { + "epoch": 3.1295546558704452, + "grad_norm": 0.2737789307748836, + "learning_rate": 1.4773561535742793e-05, + "loss": 0.3868, + "step": 773 + }, + { + "epoch": 3.133603238866397, + "grad_norm": 0.2895731291526676, + "learning_rate": 1.4718993346877715e-05, + "loss": 0.3979, + "step": 774 + }, + { + "epoch": 3.1376518218623484, + "grad_norm": 0.26142750104972096, + "learning_rate": 1.466446738480111e-05, + "loss": 0.4104, + "step": 775 + }, + { + "epoch": 3.1417004048582995, + "grad_norm": 0.26481475798300586, + "learning_rate": 1.460998408550112e-05, + "loss": 0.3934, + "step": 776 + }, + { + "epoch": 3.145748987854251, + "grad_norm": 0.2547449336718836, + "learning_rate": 1.4555543884624751e-05, + "loss": 0.4024, + "step": 777 + }, + { + "epoch": 3.1497975708502026, + "grad_norm": 0.2906738492510942, + "learning_rate": 1.4501147217474402e-05, + "loss": 0.4004, + "step": 778 + }, + { + "epoch": 3.1538461538461537, + "grad_norm": 0.2694246620778903, + "learning_rate": 1.444679451900437e-05, + "loss": 0.4176, + "step": 779 + }, + { + "epoch": 3.1578947368421053, + "grad_norm": 0.2714479652863721, + "learning_rate": 1.4392486223817397e-05, + "loss": 0.3982, + "step": 780 + }, + { + "epoch": 3.161943319838057, + "grad_norm": 0.28778595555389214, + "learning_rate": 1.4338222766161143e-05, + "loss": 0.3952, + "step": 781 + }, + { + "epoch": 3.165991902834008, + "grad_norm": 0.2691997521461367, + "learning_rate": 1.4284004579924777e-05, + "loss": 0.3992, + "step": 782 + }, + { + "epoch": 3.1700404858299596, + "grad_norm": 0.2559117840207078, + "learning_rate": 1.4229832098635479e-05, + "loss": 0.402, + "step": 783 + }, + { + "epoch": 3.174089068825911, + "grad_norm": 0.28294512331136434, + "learning_rate": 1.4175705755454963e-05, + "loss": 0.4207, + "step": 784 + }, + { + "epoch": 3.1781376518218623, + "grad_norm": 0.28035673170635383, + "learning_rate": 1.412162598317602e-05, + "loss": 0.3993, + "step": 785 + }, + { + "epoch": 3.182186234817814, + "grad_norm": 0.27910519069089856, + "learning_rate": 1.406759321421907e-05, + "loss": 0.3799, + "step": 786 + }, + { + "epoch": 3.1862348178137654, + "grad_norm": 0.2673901381311783, + "learning_rate": 1.401360788062871e-05, + "loss": 0.3924, + "step": 787 + }, + { + "epoch": 3.1902834008097165, + "grad_norm": 0.2884832420537452, + "learning_rate": 1.3959670414070204e-05, + "loss": 0.3947, + "step": 788 + }, + { + "epoch": 3.194331983805668, + "grad_norm": 0.2788663496080745, + "learning_rate": 1.3905781245826108e-05, + "loss": 0.3833, + "step": 789 + }, + { + "epoch": 3.1983805668016196, + "grad_norm": 0.35329624051570796, + "learning_rate": 1.3851940806792778e-05, + "loss": 0.4058, + "step": 790 + }, + { + "epoch": 3.2024291497975708, + "grad_norm": 0.2882563916985464, + "learning_rate": 1.379814952747693e-05, + "loss": 0.3767, + "step": 791 + }, + { + "epoch": 3.2064777327935223, + "grad_norm": 0.2856549012844441, + "learning_rate": 1.3744407837992193e-05, + "loss": 0.4097, + "step": 792 + }, + { + "epoch": 3.2105263157894735, + "grad_norm": 0.26966913831050154, + "learning_rate": 1.3690716168055692e-05, + "loss": 0.4014, + "step": 793 + }, + { + "epoch": 3.214574898785425, + "grad_norm": 0.31155437315143175, + "learning_rate": 1.363707494698459e-05, + "loss": 0.3754, + "step": 794 + }, + { + "epoch": 3.2186234817813766, + "grad_norm": 0.27011940396193224, + "learning_rate": 1.358348460369265e-05, + "loss": 0.4053, + "step": 795 + }, + { + "epoch": 3.2226720647773277, + "grad_norm": 0.2864982194889137, + "learning_rate": 1.352994556668684e-05, + "loss": 0.3932, + "step": 796 + }, + { + "epoch": 3.2267206477732793, + "grad_norm": 0.25478520159468765, + "learning_rate": 1.3476458264063865e-05, + "loss": 0.3993, + "step": 797 + }, + { + "epoch": 3.230769230769231, + "grad_norm": 0.26975633302096436, + "learning_rate": 1.342302312350678e-05, + "loss": 0.4102, + "step": 798 + }, + { + "epoch": 3.234817813765182, + "grad_norm": 0.26810245424854356, + "learning_rate": 1.3369640572281537e-05, + "loss": 0.4061, + "step": 799 + }, + { + "epoch": 3.2388663967611335, + "grad_norm": 0.2640966133451815, + "learning_rate": 1.3316311037233596e-05, + "loss": 0.4124, + "step": 800 + }, + { + "epoch": 3.242914979757085, + "grad_norm": 0.27329588045000036, + "learning_rate": 1.326303494478451e-05, + "loss": 0.4187, + "step": 801 + }, + { + "epoch": 3.246963562753036, + "grad_norm": 0.270120015801755, + "learning_rate": 1.3209812720928472e-05, + "loss": 0.4038, + "step": 802 + }, + { + "epoch": 3.251012145748988, + "grad_norm": 0.25361627090680017, + "learning_rate": 1.315664479122898e-05, + "loss": 0.4036, + "step": 803 + }, + { + "epoch": 3.2550607287449393, + "grad_norm": 0.27696163182826794, + "learning_rate": 1.3103531580815378e-05, + "loss": 0.3836, + "step": 804 + }, + { + "epoch": 3.2591093117408905, + "grad_norm": 0.2741932454538595, + "learning_rate": 1.3050473514379488e-05, + "loss": 0.3911, + "step": 805 + }, + { + "epoch": 3.263157894736842, + "grad_norm": 0.2940740189934853, + "learning_rate": 1.2997471016172188e-05, + "loss": 0.3971, + "step": 806 + }, + { + "epoch": 3.2672064777327936, + "grad_norm": 0.2806074580169743, + "learning_rate": 1.2944524510000042e-05, + "loss": 0.3678, + "step": 807 + }, + { + "epoch": 3.2712550607287447, + "grad_norm": 0.29640537891218965, + "learning_rate": 1.2891634419221908e-05, + "loss": 0.3799, + "step": 808 + }, + { + "epoch": 3.2753036437246963, + "grad_norm": 0.2872446355915579, + "learning_rate": 1.2838801166745545e-05, + "loss": 0.3976, + "step": 809 + }, + { + "epoch": 3.279352226720648, + "grad_norm": 0.29459332147371187, + "learning_rate": 1.2786025175024216e-05, + "loss": 0.4159, + "step": 810 + }, + { + "epoch": 3.283400809716599, + "grad_norm": 0.30407622562278297, + "learning_rate": 1.2733306866053357e-05, + "loss": 0.3765, + "step": 811 + }, + { + "epoch": 3.2874493927125505, + "grad_norm": 0.2848231519218241, + "learning_rate": 1.2680646661367163e-05, + "loss": 0.4107, + "step": 812 + }, + { + "epoch": 3.291497975708502, + "grad_norm": 0.2997670595564209, + "learning_rate": 1.2628044982035219e-05, + "loss": 0.3982, + "step": 813 + }, + { + "epoch": 3.2955465587044532, + "grad_norm": 0.28633408701217816, + "learning_rate": 1.2575502248659155e-05, + "loss": 0.3932, + "step": 814 + }, + { + "epoch": 3.299595141700405, + "grad_norm": 0.2813981315800815, + "learning_rate": 1.2523018881369269e-05, + "loss": 0.4075, + "step": 815 + }, + { + "epoch": 3.3036437246963564, + "grad_norm": 0.2881658757982672, + "learning_rate": 1.2470595299821176e-05, + "loss": 0.4075, + "step": 816 + }, + { + "epoch": 3.3076923076923075, + "grad_norm": 0.27549271302449885, + "learning_rate": 1.2418231923192416e-05, + "loss": 0.374, + "step": 817 + }, + { + "epoch": 3.311740890688259, + "grad_norm": 0.2995541806438367, + "learning_rate": 1.2365929170179165e-05, + "loss": 0.4074, + "step": 818 + }, + { + "epoch": 3.3157894736842106, + "grad_norm": 0.2710618269456132, + "learning_rate": 1.2313687458992848e-05, + "loss": 0.3898, + "step": 819 + }, + { + "epoch": 3.3198380566801617, + "grad_norm": 0.2903411492108107, + "learning_rate": 1.2261507207356785e-05, + "loss": 0.4019, + "step": 820 + }, + { + "epoch": 3.3238866396761133, + "grad_norm": 0.27852378785558235, + "learning_rate": 1.220938883250288e-05, + "loss": 0.4107, + "step": 821 + }, + { + "epoch": 3.327935222672065, + "grad_norm": 0.273773599420098, + "learning_rate": 1.215733275116827e-05, + "loss": 0.4021, + "step": 822 + }, + { + "epoch": 3.331983805668016, + "grad_norm": 0.2775478592107353, + "learning_rate": 1.2105339379592005e-05, + "loss": 0.4037, + "step": 823 + }, + { + "epoch": 3.3360323886639676, + "grad_norm": 0.2589429630173823, + "learning_rate": 1.2053409133511681e-05, + "loss": 0.3831, + "step": 824 + }, + { + "epoch": 3.340080971659919, + "grad_norm": 0.2765149231633141, + "learning_rate": 1.2001542428160173e-05, + "loss": 0.412, + "step": 825 + }, + { + "epoch": 3.3441295546558703, + "grad_norm": 0.28328996539229645, + "learning_rate": 1.1949739678262278e-05, + "loss": 0.3993, + "step": 826 + }, + { + "epoch": 3.348178137651822, + "grad_norm": 0.26801889221001546, + "learning_rate": 1.189800129803139e-05, + "loss": 0.4167, + "step": 827 + }, + { + "epoch": 3.3522267206477734, + "grad_norm": 0.2781858550205906, + "learning_rate": 1.1846327701166228e-05, + "loss": 0.3948, + "step": 828 + }, + { + "epoch": 3.3562753036437245, + "grad_norm": 0.2819650988515181, + "learning_rate": 1.1794719300847493e-05, + "loss": 0.3961, + "step": 829 + }, + { + "epoch": 3.360323886639676, + "grad_norm": 0.2691519302094065, + "learning_rate": 1.1743176509734582e-05, + "loss": 0.4062, + "step": 830 + }, + { + "epoch": 3.3643724696356276, + "grad_norm": 0.29610933766207376, + "learning_rate": 1.1691699739962275e-05, + "loss": 0.41, + "step": 831 + }, + { + "epoch": 3.3684210526315788, + "grad_norm": 0.276292334108597, + "learning_rate": 1.1640289403137456e-05, + "loss": 0.3984, + "step": 832 + }, + { + "epoch": 3.3724696356275303, + "grad_norm": 0.27321465201751177, + "learning_rate": 1.1588945910335802e-05, + "loss": 0.4019, + "step": 833 + }, + { + "epoch": 3.376518218623482, + "grad_norm": 0.29173995779685047, + "learning_rate": 1.1537669672098517e-05, + "loss": 0.3922, + "step": 834 + }, + { + "epoch": 3.380566801619433, + "grad_norm": 0.2563678019392041, + "learning_rate": 1.1486461098429036e-05, + "loss": 0.4198, + "step": 835 + }, + { + "epoch": 3.3846153846153846, + "grad_norm": 0.2603386173751867, + "learning_rate": 1.1435320598789747e-05, + "loss": 0.4096, + "step": 836 + }, + { + "epoch": 3.388663967611336, + "grad_norm": 0.29885623995862615, + "learning_rate": 1.1384248582098736e-05, + "loss": 0.403, + "step": 837 + }, + { + "epoch": 3.3927125506072873, + "grad_norm": 0.26228948582261363, + "learning_rate": 1.1333245456726467e-05, + "loss": 0.4015, + "step": 838 + }, + { + "epoch": 3.396761133603239, + "grad_norm": 0.2707014181849456, + "learning_rate": 1.128231163049258e-05, + "loss": 0.3957, + "step": 839 + }, + { + "epoch": 3.4008097165991904, + "grad_norm": 0.28603557246858824, + "learning_rate": 1.123144751066259e-05, + "loss": 0.4027, + "step": 840 + }, + { + "epoch": 3.4048582995951415, + "grad_norm": 0.267053574727869, + "learning_rate": 1.1180653503944657e-05, + "loss": 0.3793, + "step": 841 + }, + { + "epoch": 3.408906882591093, + "grad_norm": 0.26974157313035957, + "learning_rate": 1.1129930016486287e-05, + "loss": 0.397, + "step": 842 + }, + { + "epoch": 3.4129554655870447, + "grad_norm": 0.2697248631250802, + "learning_rate": 1.107927745387114e-05, + "loss": 0.4009, + "step": 843 + }, + { + "epoch": 3.417004048582996, + "grad_norm": 0.2773343238615587, + "learning_rate": 1.1028696221115766e-05, + "loss": 0.3693, + "step": 844 + }, + { + "epoch": 3.4210526315789473, + "grad_norm": 0.2702112505643063, + "learning_rate": 1.0978186722666341e-05, + "loss": 0.397, + "step": 845 + }, + { + "epoch": 3.425101214574899, + "grad_norm": 0.2679778046710898, + "learning_rate": 1.0927749362395475e-05, + "loss": 0.4073, + "step": 846 + }, + { + "epoch": 3.42914979757085, + "grad_norm": 0.28056735226034046, + "learning_rate": 1.0877384543598954e-05, + "loss": 0.4185, + "step": 847 + }, + { + "epoch": 3.4331983805668016, + "grad_norm": 0.25814114028190616, + "learning_rate": 1.0827092668992529e-05, + "loss": 0.414, + "step": 848 + }, + { + "epoch": 3.437246963562753, + "grad_norm": 0.2701765872611739, + "learning_rate": 1.077687414070869e-05, + "loss": 0.3893, + "step": 849 + }, + { + "epoch": 3.4412955465587043, + "grad_norm": 0.2587460379987047, + "learning_rate": 1.0726729360293451e-05, + "loss": 0.3827, + "step": 850 + }, + { + "epoch": 3.445344129554656, + "grad_norm": 0.2588484943755391, + "learning_rate": 1.0676658728703147e-05, + "loss": 0.4035, + "step": 851 + }, + { + "epoch": 3.4493927125506074, + "grad_norm": 0.2846609630093237, + "learning_rate": 1.0626662646301198e-05, + "loss": 0.3918, + "step": 852 + }, + { + "epoch": 3.4534412955465585, + "grad_norm": 0.24811677295859325, + "learning_rate": 1.0576741512854958e-05, + "loss": 0.4099, + "step": 853 + }, + { + "epoch": 3.45748987854251, + "grad_norm": 0.27466256426218233, + "learning_rate": 1.052689572753247e-05, + "loss": 0.4111, + "step": 854 + }, + { + "epoch": 3.4615384615384617, + "grad_norm": 0.2888514039023773, + "learning_rate": 1.0477125688899328e-05, + "loss": 0.3946, + "step": 855 + }, + { + "epoch": 3.465587044534413, + "grad_norm": 0.2850114987091914, + "learning_rate": 1.0427431794915406e-05, + "loss": 0.4205, + "step": 856 + }, + { + "epoch": 3.4696356275303644, + "grad_norm": 0.2764173276711337, + "learning_rate": 1.0377814442931769e-05, + "loss": 0.4037, + "step": 857 + }, + { + "epoch": 3.473684210526316, + "grad_norm": 0.25564512891009095, + "learning_rate": 1.0328274029687439e-05, + "loss": 0.3926, + "step": 858 + }, + { + "epoch": 3.477732793522267, + "grad_norm": 0.2626487150494378, + "learning_rate": 1.0278810951306253e-05, + "loss": 0.3938, + "step": 859 + }, + { + "epoch": 3.4817813765182186, + "grad_norm": 0.2638548708002062, + "learning_rate": 1.0229425603293647e-05, + "loss": 0.399, + "step": 860 + }, + { + "epoch": 3.48582995951417, + "grad_norm": 0.26785696189459274, + "learning_rate": 1.0180118380533558e-05, + "loss": 0.3991, + "step": 861 + }, + { + "epoch": 3.4898785425101213, + "grad_norm": 0.24716388565742417, + "learning_rate": 1.0130889677285225e-05, + "loss": 0.4139, + "step": 862 + }, + { + "epoch": 3.493927125506073, + "grad_norm": 0.264117042678668, + "learning_rate": 1.008173988718005e-05, + "loss": 0.39, + "step": 863 + }, + { + "epoch": 3.4979757085020244, + "grad_norm": 0.28146011721560793, + "learning_rate": 1.0032669403218439e-05, + "loss": 0.4028, + "step": 864 + }, + { + "epoch": 3.5020242914979756, + "grad_norm": 0.25381746306604436, + "learning_rate": 9.983678617766677e-06, + "loss": 0.3973, + "step": 865 + }, + { + "epoch": 3.506072874493927, + "grad_norm": 0.248414384918097, + "learning_rate": 9.934767922553788e-06, + "loss": 0.3919, + "step": 866 + }, + { + "epoch": 3.5101214574898787, + "grad_norm": 0.261041913037476, + "learning_rate": 9.885937708668371e-06, + "loss": 0.3756, + "step": 867 + }, + { + "epoch": 3.51417004048583, + "grad_norm": 0.2521268466552633, + "learning_rate": 9.837188366555524e-06, + "loss": 0.3939, + "step": 868 + }, + { + "epoch": 3.5182186234817814, + "grad_norm": 0.2544659403691464, + "learning_rate": 9.788520286013691e-06, + "loss": 0.3843, + "step": 869 + }, + { + "epoch": 3.522267206477733, + "grad_norm": 0.2519326730914753, + "learning_rate": 9.739933856191537e-06, + "loss": 0.3877, + "step": 870 + }, + { + "epoch": 3.526315789473684, + "grad_norm": 0.2601352550985588, + "learning_rate": 9.691429465584866e-06, + "loss": 0.4062, + "step": 871 + }, + { + "epoch": 3.5303643724696356, + "grad_norm": 0.2452523864712829, + "learning_rate": 9.643007502033492e-06, + "loss": 0.3972, + "step": 872 + }, + { + "epoch": 3.534412955465587, + "grad_norm": 0.2580080844174789, + "learning_rate": 9.594668352718152e-06, + "loss": 0.4287, + "step": 873 + }, + { + "epoch": 3.5384615384615383, + "grad_norm": 0.2774683350412787, + "learning_rate": 9.546412404157383e-06, + "loss": 0.3883, + "step": 874 + }, + { + "epoch": 3.54251012145749, + "grad_norm": 0.26582335181234895, + "learning_rate": 9.498240042204471e-06, + "loss": 0.4031, + "step": 875 + }, + { + "epoch": 3.5465587044534415, + "grad_norm": 0.27102193629605836, + "learning_rate": 9.450151652044339e-06, + "loss": 0.4046, + "step": 876 + }, + { + "epoch": 3.5506072874493926, + "grad_norm": 0.2621535176741002, + "learning_rate": 9.402147618190472e-06, + "loss": 0.4092, + "step": 877 + }, + { + "epoch": 3.554655870445344, + "grad_norm": 0.25287360382794427, + "learning_rate": 9.354228324481841e-06, + "loss": 0.4164, + "step": 878 + }, + { + "epoch": 3.5587044534412957, + "grad_norm": 0.25996917355505217, + "learning_rate": 9.306394154079852e-06, + "loss": 0.3979, + "step": 879 + }, + { + "epoch": 3.562753036437247, + "grad_norm": 0.257356902067772, + "learning_rate": 9.258645489465254e-06, + "loss": 0.4112, + "step": 880 + }, + { + "epoch": 3.5668016194331984, + "grad_norm": 0.2625344106358796, + "learning_rate": 9.21098271243509e-06, + "loss": 0.3858, + "step": 881 + }, + { + "epoch": 3.57085020242915, + "grad_norm": 0.2718294980979648, + "learning_rate": 9.163406204099659e-06, + "loss": 0.3978, + "step": 882 + }, + { + "epoch": 3.574898785425101, + "grad_norm": 0.27805947441109446, + "learning_rate": 9.115916344879452e-06, + "loss": 0.3915, + "step": 883 + }, + { + "epoch": 3.5789473684210527, + "grad_norm": 0.2605246498114428, + "learning_rate": 9.068513514502126e-06, + "loss": 0.4132, + "step": 884 + }, + { + "epoch": 3.582995951417004, + "grad_norm": 0.2636106593688388, + "learning_rate": 9.021198091999439e-06, + "loss": 0.4039, + "step": 885 + }, + { + "epoch": 3.5870445344129553, + "grad_norm": 0.25161807643977996, + "learning_rate": 8.973970455704251e-06, + "loss": 0.3799, + "step": 886 + }, + { + "epoch": 3.591093117408907, + "grad_norm": 0.2525315152985144, + "learning_rate": 8.926830983247495e-06, + "loss": 0.3963, + "step": 887 + }, + { + "epoch": 3.5951417004048585, + "grad_norm": 0.26246867649983074, + "learning_rate": 8.879780051555116e-06, + "loss": 0.4025, + "step": 888 + }, + { + "epoch": 3.5991902834008096, + "grad_norm": 0.24695841781571237, + "learning_rate": 8.83281803684512e-06, + "loss": 0.3938, + "step": 889 + }, + { + "epoch": 3.603238866396761, + "grad_norm": 0.24609400849220273, + "learning_rate": 8.785945314624532e-06, + "loss": 0.403, + "step": 890 + }, + { + "epoch": 3.6072874493927127, + "grad_norm": 0.2581802374962549, + "learning_rate": 8.739162259686385e-06, + "loss": 0.3839, + "step": 891 + }, + { + "epoch": 3.611336032388664, + "grad_norm": 0.25075357340334853, + "learning_rate": 8.692469246106734e-06, + "loss": 0.4109, + "step": 892 + }, + { + "epoch": 3.6153846153846154, + "grad_norm": 0.26237016496273113, + "learning_rate": 8.645866647241677e-06, + "loss": 0.4004, + "step": 893 + }, + { + "epoch": 3.619433198380567, + "grad_norm": 0.2882246362187001, + "learning_rate": 8.599354835724348e-06, + "loss": 0.3782, + "step": 894 + }, + { + "epoch": 3.623481781376518, + "grad_norm": 0.25659285881051, + "learning_rate": 8.552934183461958e-06, + "loss": 0.4162, + "step": 895 + }, + { + "epoch": 3.6275303643724697, + "grad_norm": 0.26088902735066194, + "learning_rate": 8.506605061632805e-06, + "loss": 0.4129, + "step": 896 + }, + { + "epoch": 3.6315789473684212, + "grad_norm": 0.26965931170838897, + "learning_rate": 8.460367840683308e-06, + "loss": 0.4011, + "step": 897 + }, + { + "epoch": 3.6356275303643724, + "grad_norm": 0.26530896527002007, + "learning_rate": 8.414222890325065e-06, + "loss": 0.421, + "step": 898 + }, + { + "epoch": 3.639676113360324, + "grad_norm": 0.24627037772337812, + "learning_rate": 8.368170579531855e-06, + "loss": 0.4003, + "step": 899 + }, + { + "epoch": 3.6437246963562755, + "grad_norm": 0.2808326149734353, + "learning_rate": 8.322211276536733e-06, + "loss": 0.3927, + "step": 900 + }, + { + "epoch": 3.6477732793522266, + "grad_norm": 0.2810110062329657, + "learning_rate": 8.27634534882907e-06, + "loss": 0.3905, + "step": 901 + }, + { + "epoch": 3.651821862348178, + "grad_norm": 0.2846287059994868, + "learning_rate": 8.230573163151585e-06, + "loss": 0.3978, + "step": 902 + }, + { + "epoch": 3.6558704453441297, + "grad_norm": 0.2776981963791679, + "learning_rate": 8.184895085497466e-06, + "loss": 0.4108, + "step": 903 + }, + { + "epoch": 3.659919028340081, + "grad_norm": 0.25479335375747225, + "learning_rate": 8.139311481107401e-06, + "loss": 0.3974, + "step": 904 + }, + { + "epoch": 3.6639676113360324, + "grad_norm": 0.26138374170115236, + "learning_rate": 8.093822714466686e-06, + "loss": 0.4153, + "step": 905 + }, + { + "epoch": 3.668016194331984, + "grad_norm": 0.25970177380514753, + "learning_rate": 8.048429149302271e-06, + "loss": 0.4007, + "step": 906 + }, + { + "epoch": 3.672064777327935, + "grad_norm": 0.26833712196057713, + "learning_rate": 8.003131148579902e-06, + "loss": 0.4388, + "step": 907 + }, + { + "epoch": 3.6761133603238867, + "grad_norm": 0.26967763660794486, + "learning_rate": 7.957929074501182e-06, + "loss": 0.3878, + "step": 908 + }, + { + "epoch": 3.6801619433198383, + "grad_norm": 0.24779583699298474, + "learning_rate": 7.912823288500695e-06, + "loss": 0.398, + "step": 909 + }, + { + "epoch": 3.6842105263157894, + "grad_norm": 0.25156114361962584, + "learning_rate": 7.867814151243102e-06, + "loss": 0.3911, + "step": 910 + }, + { + "epoch": 3.688259109311741, + "grad_norm": 0.26425518726978486, + "learning_rate": 7.822902022620267e-06, + "loss": 0.4054, + "step": 911 + }, + { + "epoch": 3.6923076923076925, + "grad_norm": 0.2730049375494375, + "learning_rate": 7.778087261748377e-06, + "loss": 0.4013, + "step": 912 + }, + { + "epoch": 3.6963562753036436, + "grad_norm": 0.24850133788333098, + "learning_rate": 7.733370226965056e-06, + "loss": 0.3852, + "step": 913 + }, + { + "epoch": 3.700404858299595, + "grad_norm": 0.2892570968437071, + "learning_rate": 7.688751275826527e-06, + "loss": 0.4235, + "step": 914 + }, + { + "epoch": 3.7044534412955468, + "grad_norm": 0.2608505844113899, + "learning_rate": 7.644230765104735e-06, + "loss": 0.3952, + "step": 915 + }, + { + "epoch": 3.708502024291498, + "grad_norm": 0.25553764028268006, + "learning_rate": 7.599809050784502e-06, + "loss": 0.3686, + "step": 916 + }, + { + "epoch": 3.7125506072874495, + "grad_norm": 0.25154241452219767, + "learning_rate": 7.555486488060661e-06, + "loss": 0.3891, + "step": 917 + }, + { + "epoch": 3.716599190283401, + "grad_norm": 0.27048754388083324, + "learning_rate": 7.511263431335249e-06, + "loss": 0.3934, + "step": 918 + }, + { + "epoch": 3.720647773279352, + "grad_norm": 0.2579563080100022, + "learning_rate": 7.467140234214656e-06, + "loss": 0.3993, + "step": 919 + }, + { + "epoch": 3.7246963562753037, + "grad_norm": 0.2458306996708746, + "learning_rate": 7.423117249506777e-06, + "loss": 0.405, + "step": 920 + }, + { + "epoch": 3.7287449392712553, + "grad_norm": 0.24330160175726903, + "learning_rate": 7.379194829218231e-06, + "loss": 0.4003, + "step": 921 + }, + { + "epoch": 3.7327935222672064, + "grad_norm": 0.2510017842896356, + "learning_rate": 7.335373324551518e-06, + "loss": 0.4023, + "step": 922 + }, + { + "epoch": 3.736842105263158, + "grad_norm": 0.2453276727063968, + "learning_rate": 7.291653085902224e-06, + "loss": 0.3999, + "step": 923 + }, + { + "epoch": 3.7408906882591095, + "grad_norm": 0.5212947883385897, + "learning_rate": 7.248034462856213e-06, + "loss": 0.397, + "step": 924 + }, + { + "epoch": 3.7449392712550607, + "grad_norm": 0.2467623662008714, + "learning_rate": 7.20451780418683e-06, + "loss": 0.3836, + "step": 925 + }, + { + "epoch": 3.748987854251012, + "grad_norm": 0.25487743709850136, + "learning_rate": 7.161103457852128e-06, + "loss": 0.4147, + "step": 926 + }, + { + "epoch": 3.753036437246964, + "grad_norm": 0.25464076806229746, + "learning_rate": 7.117791770992046e-06, + "loss": 0.4041, + "step": 927 + }, + { + "epoch": 3.757085020242915, + "grad_norm": 0.25167927177436367, + "learning_rate": 7.074583089925688e-06, + "loss": 0.4059, + "step": 928 + }, + { + "epoch": 3.7611336032388665, + "grad_norm": 0.2655923532043895, + "learning_rate": 7.0314777601485155e-06, + "loss": 0.3856, + "step": 929 + }, + { + "epoch": 3.765182186234818, + "grad_norm": 0.2576473066804947, + "learning_rate": 6.988476126329604e-06, + "loss": 0.3942, + "step": 930 + }, + { + "epoch": 3.769230769230769, + "grad_norm": 0.2501951106942732, + "learning_rate": 6.945578532308857e-06, + "loss": 0.383, + "step": 931 + }, + { + "epoch": 3.7732793522267207, + "grad_norm": 0.2356251784291764, + "learning_rate": 6.902785321094301e-06, + "loss": 0.4194, + "step": 932 + }, + { + "epoch": 3.7773279352226723, + "grad_norm": 0.25810031591063787, + "learning_rate": 6.8600968348593115e-06, + "loss": 0.4156, + "step": 933 + }, + { + "epoch": 3.7813765182186234, + "grad_norm": 0.2548572712801417, + "learning_rate": 6.817513414939892e-06, + "loss": 0.3837, + "step": 934 + }, + { + "epoch": 3.785425101214575, + "grad_norm": 0.24568361082556728, + "learning_rate": 6.775035401831924e-06, + "loss": 0.3952, + "step": 935 + }, + { + "epoch": 3.7894736842105265, + "grad_norm": 0.24790324486991364, + "learning_rate": 6.732663135188473e-06, + "loss": 0.4004, + "step": 936 + }, + { + "epoch": 3.7935222672064777, + "grad_norm": 0.2580268284209731, + "learning_rate": 6.690396953817055e-06, + "loss": 0.3757, + "step": 937 + }, + { + "epoch": 3.7975708502024292, + "grad_norm": 0.2661571470471815, + "learning_rate": 6.648237195676927e-06, + "loss": 0.4105, + "step": 938 + }, + { + "epoch": 3.801619433198381, + "grad_norm": 0.2540927957213218, + "learning_rate": 6.606184197876395e-06, + "loss": 0.3982, + "step": 939 + }, + { + "epoch": 3.805668016194332, + "grad_norm": 0.23852402240223206, + "learning_rate": 6.564238296670109e-06, + "loss": 0.4053, + "step": 940 + }, + { + "epoch": 3.8097165991902835, + "grad_norm": 0.24463113602140202, + "learning_rate": 6.52239982745638e-06, + "loss": 0.3795, + "step": 941 + }, + { + "epoch": 3.813765182186235, + "grad_norm": 0.26859166521212224, + "learning_rate": 6.480669124774484e-06, + "loss": 0.4261, + "step": 942 + }, + { + "epoch": 3.817813765182186, + "grad_norm": 0.2493362043402934, + "learning_rate": 6.439046522302013e-06, + "loss": 0.3982, + "step": 943 + }, + { + "epoch": 3.8218623481781377, + "grad_norm": 0.23372007207470108, + "learning_rate": 6.397532352852191e-06, + "loss": 0.3849, + "step": 944 + }, + { + "epoch": 3.8259109311740893, + "grad_norm": 0.2384052036329297, + "learning_rate": 6.356126948371202e-06, + "loss": 0.3915, + "step": 945 + }, + { + "epoch": 3.8299595141700404, + "grad_norm": 0.2660293047055337, + "learning_rate": 6.314830639935559e-06, + "loss": 0.3829, + "step": 946 + }, + { + "epoch": 3.834008097165992, + "grad_norm": 0.2426288318934874, + "learning_rate": 6.273643757749448e-06, + "loss": 0.4, + "step": 947 + }, + { + "epoch": 3.8380566801619436, + "grad_norm": 0.23072334367483865, + "learning_rate": 6.2325666311420856e-06, + "loss": 0.4108, + "step": 948 + }, + { + "epoch": 3.8421052631578947, + "grad_norm": 0.23566078085542072, + "learning_rate": 6.1915995885650675e-06, + "loss": 0.4187, + "step": 949 + }, + { + "epoch": 3.8461538461538463, + "grad_norm": 0.2533004766523023, + "learning_rate": 6.150742957589784e-06, + "loss": 0.3939, + "step": 950 + }, + { + "epoch": 3.850202429149798, + "grad_norm": 0.255026363909699, + "learning_rate": 6.109997064904774e-06, + "loss": 0.3945, + "step": 951 + }, + { + "epoch": 3.854251012145749, + "grad_norm": 0.2516959153765303, + "learning_rate": 6.069362236313092e-06, + "loss": 0.3969, + "step": 952 + }, + { + "epoch": 3.8582995951417005, + "grad_norm": 0.23944396762387107, + "learning_rate": 6.0288387967297565e-06, + "loss": 0.3967, + "step": 953 + }, + { + "epoch": 3.862348178137652, + "grad_norm": 0.2563244427632202, + "learning_rate": 5.988427070179108e-06, + "loss": 0.3933, + "step": 954 + }, + { + "epoch": 3.866396761133603, + "grad_norm": 0.24314778546685753, + "learning_rate": 5.948127379792234e-06, + "loss": 0.3855, + "step": 955 + }, + { + "epoch": 3.8704453441295548, + "grad_norm": 0.23067182066503353, + "learning_rate": 5.90794004780439e-06, + "loss": 0.428, + "step": 956 + }, + { + "epoch": 3.8744939271255063, + "grad_norm": 0.23327483579024305, + "learning_rate": 5.867865395552405e-06, + "loss": 0.4099, + "step": 957 + }, + { + "epoch": 3.8785425101214575, + "grad_norm": 0.2352275179837997, + "learning_rate": 5.8279037434721364e-06, + "loss": 0.4091, + "step": 958 + }, + { + "epoch": 3.882591093117409, + "grad_norm": 0.23797554785516736, + "learning_rate": 5.788055411095892e-06, + "loss": 0.3972, + "step": 959 + }, + { + "epoch": 3.8866396761133606, + "grad_norm": 0.240505128143109, + "learning_rate": 5.7483207170498625e-06, + "loss": 0.3765, + "step": 960 + }, + { + "epoch": 3.8906882591093117, + "grad_norm": 0.24245588301650184, + "learning_rate": 5.708699979051613e-06, + "loss": 0.393, + "step": 961 + }, + { + "epoch": 3.8947368421052633, + "grad_norm": 0.24322487305380647, + "learning_rate": 5.66919351390751e-06, + "loss": 0.3911, + "step": 962 + }, + { + "epoch": 3.898785425101215, + "grad_norm": 0.2632892867939988, + "learning_rate": 5.629801637510188e-06, + "loss": 0.3941, + "step": 963 + }, + { + "epoch": 3.902834008097166, + "grad_norm": 0.26557379365147565, + "learning_rate": 5.590524664836043e-06, + "loss": 0.3802, + "step": 964 + }, + { + "epoch": 3.9068825910931175, + "grad_norm": 0.2388672706173119, + "learning_rate": 5.551362909942708e-06, + "loss": 0.4009, + "step": 965 + }, + { + "epoch": 3.910931174089069, + "grad_norm": 0.24146410913985683, + "learning_rate": 5.51231668596653e-06, + "loss": 0.3877, + "step": 966 + }, + { + "epoch": 3.91497975708502, + "grad_norm": 0.23118435148167393, + "learning_rate": 5.47338630512007e-06, + "loss": 0.4022, + "step": 967 + }, + { + "epoch": 3.919028340080972, + "grad_norm": 0.22922462083807338, + "learning_rate": 5.434572078689617e-06, + "loss": 0.4164, + "step": 968 + }, + { + "epoch": 3.9230769230769234, + "grad_norm": 0.24877936048119406, + "learning_rate": 5.395874317032694e-06, + "loss": 0.387, + "step": 969 + }, + { + "epoch": 3.9271255060728745, + "grad_norm": 0.26055430526319345, + "learning_rate": 5.357293329575573e-06, + "loss": 0.3783, + "step": 970 + }, + { + "epoch": 3.931174089068826, + "grad_norm": 0.22105744471340408, + "learning_rate": 5.318829424810797e-06, + "loss": 0.4327, + "step": 971 + }, + { + "epoch": 3.9352226720647776, + "grad_norm": 0.2449757871570657, + "learning_rate": 5.280482910294728e-06, + "loss": 0.3859, + "step": 972 + }, + { + "epoch": 3.9392712550607287, + "grad_norm": 0.24018477802916766, + "learning_rate": 5.242254092645078e-06, + "loss": 0.3954, + "step": 973 + }, + { + "epoch": 3.9433198380566803, + "grad_norm": 0.54641945163986, + "learning_rate": 5.2041432775384445e-06, + "loss": 0.3981, + "step": 974 + }, + { + "epoch": 3.9473684210526314, + "grad_norm": 0.2443746903062744, + "learning_rate": 5.166150769707892e-06, + "loss": 0.396, + "step": 975 + }, + { + "epoch": 3.951417004048583, + "grad_norm": 0.2555352085521793, + "learning_rate": 5.128276872940503e-06, + "loss": 0.3953, + "step": 976 + }, + { + "epoch": 3.9554655870445345, + "grad_norm": 0.2391802374854783, + "learning_rate": 5.090521890074953e-06, + "loss": 0.4082, + "step": 977 + }, + { + "epoch": 3.9595141700404857, + "grad_norm": 0.2644542339847005, + "learning_rate": 5.0528861229990675e-06, + "loss": 0.3768, + "step": 978 + }, + { + "epoch": 3.9635627530364372, + "grad_norm": 0.24523603226311658, + "learning_rate": 5.015369872647442e-06, + "loss": 0.4261, + "step": 979 + }, + { + "epoch": 3.967611336032389, + "grad_norm": 0.23307816128507172, + "learning_rate": 4.9779734389990195e-06, + "loss": 0.4064, + "step": 980 + }, + { + "epoch": 3.97165991902834, + "grad_norm": 0.2434032550275147, + "learning_rate": 4.940697121074675e-06, + "loss": 0.417, + "step": 981 + }, + { + "epoch": 3.9757085020242915, + "grad_norm": 0.24908357483438634, + "learning_rate": 4.903541216934864e-06, + "loss": 0.407, + "step": 982 + }, + { + "epoch": 3.979757085020243, + "grad_norm": 0.2378276060516935, + "learning_rate": 4.8665060236772e-06, + "loss": 0.4032, + "step": 983 + }, + { + "epoch": 3.983805668016194, + "grad_norm": 0.2512193602980041, + "learning_rate": 4.829591837434102e-06, + "loss": 0.3942, + "step": 984 + }, + { + "epoch": 3.9878542510121457, + "grad_norm": 0.2369980926472287, + "learning_rate": 4.792798953370424e-06, + "loss": 0.4004, + "step": 985 + }, + { + "epoch": 3.9919028340080973, + "grad_norm": 0.23480574859245698, + "learning_rate": 4.756127665681083e-06, + "loss": 0.3799, + "step": 986 + }, + { + "epoch": 3.9959514170040484, + "grad_norm": 0.23241652156430984, + "learning_rate": 4.719578267588725e-06, + "loss": 0.4183, + "step": 987 + }, + { + "epoch": 4.0, + "grad_norm": 0.25062131131933907, + "learning_rate": 4.6831510513413525e-06, + "loss": 0.3991, + "step": 988 + }, + { + "epoch": 4.004048582995951, + "grad_norm": 0.3783650838000581, + "learning_rate": 4.6468463082100176e-06, + "loss": 0.386, + "step": 989 + }, + { + "epoch": 4.008097165991903, + "grad_norm": 0.2920697730941661, + "learning_rate": 4.610664328486485e-06, + "loss": 0.3684, + "step": 990 + }, + { + "epoch": 4.012145748987854, + "grad_norm": 0.22950016611971452, + "learning_rate": 4.5746054014809e-06, + "loss": 0.3463, + "step": 991 + }, + { + "epoch": 4.016194331983805, + "grad_norm": 0.43840434835816955, + "learning_rate": 4.5386698155194766e-06, + "loss": 0.3548, + "step": 992 + }, + { + "epoch": 4.020242914979757, + "grad_norm": 0.33888835470517975, + "learning_rate": 4.502857857942204e-06, + "loss": 0.3403, + "step": 993 + }, + { + "epoch": 4.0242914979757085, + "grad_norm": 0.26320838133436825, + "learning_rate": 4.467169815100549e-06, + "loss": 0.3397, + "step": 994 + }, + { + "epoch": 4.02834008097166, + "grad_norm": 0.27813571661970427, + "learning_rate": 4.431605972355137e-06, + "loss": 0.3676, + "step": 995 + }, + { + "epoch": 4.032388663967612, + "grad_norm": 0.3158905375825157, + "learning_rate": 4.396166614073516e-06, + "loss": 0.357, + "step": 996 + }, + { + "epoch": 4.036437246963563, + "grad_norm": 0.28364267632515516, + "learning_rate": 4.360852023627846e-06, + "loss": 0.3532, + "step": 997 + }, + { + "epoch": 4.040485829959514, + "grad_norm": 0.2543842301000708, + "learning_rate": 4.325662483392656e-06, + "loss": 0.3813, + "step": 998 + }, + { + "epoch": 4.044534412955466, + "grad_norm": 0.26105290830466216, + "learning_rate": 4.29059827474257e-06, + "loss": 0.3411, + "step": 999 + }, + { + "epoch": 4.048582995951417, + "grad_norm": 0.2868179658328338, + "learning_rate": 4.255659678050063e-06, + "loss": 0.351, + "step": 1000 + }, + { + "epoch": 4.052631578947368, + "grad_norm": 0.2675746084353129, + "learning_rate": 4.22084697268323e-06, + "loss": 0.3461, + "step": 1001 + }, + { + "epoch": 4.05668016194332, + "grad_norm": 0.2443820660376726, + "learning_rate": 4.186160437003535e-06, + "loss": 0.3639, + "step": 1002 + }, + { + "epoch": 4.060728744939271, + "grad_norm": 0.2616353649512723, + "learning_rate": 4.151600348363582e-06, + "loss": 0.337, + "step": 1003 + }, + { + "epoch": 4.064777327935222, + "grad_norm": 0.25914622000301085, + "learning_rate": 4.11716698310493e-06, + "loss": 0.3564, + "step": 1004 + }, + { + "epoch": 4.068825910931174, + "grad_norm": 0.2873524988949604, + "learning_rate": 4.082860616555848e-06, + "loss": 0.357, + "step": 1005 + }, + { + "epoch": 4.0728744939271255, + "grad_norm": 0.22891956962770094, + "learning_rate": 4.048681523029125e-06, + "loss": 0.3405, + "step": 1006 + }, + { + "epoch": 4.076923076923077, + "grad_norm": 0.24571382770822517, + "learning_rate": 4.014629975819882e-06, + "loss": 0.3497, + "step": 1007 + }, + { + "epoch": 4.080971659919029, + "grad_norm": 0.24843214042062728, + "learning_rate": 3.9807062472033855e-06, + "loss": 0.3546, + "step": 1008 + }, + { + "epoch": 4.08502024291498, + "grad_norm": 0.2465607959774885, + "learning_rate": 3.94691060843287e-06, + "loss": 0.3603, + "step": 1009 + }, + { + "epoch": 4.089068825910931, + "grad_norm": 0.2675122961627523, + "learning_rate": 3.913243329737353e-06, + "loss": 0.3562, + "step": 1010 + }, + { + "epoch": 4.093117408906883, + "grad_norm": 0.2424809729186539, + "learning_rate": 3.879704680319503e-06, + "loss": 0.3466, + "step": 1011 + }, + { + "epoch": 4.097165991902834, + "grad_norm": 0.23108768484925987, + "learning_rate": 3.846294928353471e-06, + "loss": 0.3757, + "step": 1012 + }, + { + "epoch": 4.101214574898785, + "grad_norm": 0.2303927276614939, + "learning_rate": 3.8130143409827345e-06, + "loss": 0.3579, + "step": 1013 + }, + { + "epoch": 4.105263157894737, + "grad_norm": 0.2503006712404116, + "learning_rate": 3.7798631843179887e-06, + "loss": 0.3425, + "step": 1014 + }, + { + "epoch": 4.109311740890688, + "grad_norm": 0.23587877517272107, + "learning_rate": 3.7468417234349973e-06, + "loss": 0.3546, + "step": 1015 + }, + { + "epoch": 4.113360323886639, + "grad_norm": 0.21503001494073443, + "learning_rate": 3.7139502223724823e-06, + "loss": 0.3359, + "step": 1016 + }, + { + "epoch": 4.117408906882591, + "grad_norm": 0.2289005650196009, + "learning_rate": 3.6811889441300095e-06, + "loss": 0.3499, + "step": 1017 + }, + { + "epoch": 4.1214574898785425, + "grad_norm": 0.23211782207857637, + "learning_rate": 3.648558150665886e-06, + "loss": 0.3553, + "step": 1018 + }, + { + "epoch": 4.125506072874494, + "grad_norm": 0.23029248826189908, + "learning_rate": 3.616058102895075e-06, + "loss": 0.3594, + "step": 1019 + }, + { + "epoch": 4.129554655870446, + "grad_norm": 0.2216727178175573, + "learning_rate": 3.583689060687079e-06, + "loss": 0.3403, + "step": 1020 + }, + { + "epoch": 4.133603238866397, + "grad_norm": 0.22664469690604203, + "learning_rate": 3.5514512828639023e-06, + "loss": 0.3364, + "step": 1021 + }, + { + "epoch": 4.137651821862348, + "grad_norm": 0.23222039032627587, + "learning_rate": 3.51934502719796e-06, + "loss": 0.361, + "step": 1022 + }, + { + "epoch": 4.1417004048583, + "grad_norm": 0.22928636739656733, + "learning_rate": 3.4873705504100185e-06, + "loss": 0.3537, + "step": 1023 + }, + { + "epoch": 4.145748987854251, + "grad_norm": 0.22560270439305877, + "learning_rate": 3.4555281081671345e-06, + "loss": 0.3481, + "step": 1024 + }, + { + "epoch": 4.149797570850202, + "grad_norm": 0.22532252455367618, + "learning_rate": 3.4238179550806326e-06, + "loss": 0.3388, + "step": 1025 + }, + { + "epoch": 4.153846153846154, + "grad_norm": 0.2258203766081333, + "learning_rate": 3.3922403447040497e-06, + "loss": 0.3457, + "step": 1026 + }, + { + "epoch": 4.157894736842105, + "grad_norm": 0.2457246908515629, + "learning_rate": 3.3607955295311247e-06, + "loss": 0.3272, + "step": 1027 + }, + { + "epoch": 4.161943319838056, + "grad_norm": 0.2195767860941197, + "learning_rate": 3.32948376099375e-06, + "loss": 0.3372, + "step": 1028 + }, + { + "epoch": 4.165991902834008, + "grad_norm": 0.21990430120043997, + "learning_rate": 3.2983052894599976e-06, + "loss": 0.37, + "step": 1029 + }, + { + "epoch": 4.17004048582996, + "grad_norm": 0.23571372424783638, + "learning_rate": 3.2672603642320945e-06, + "loss": 0.3546, + "step": 1030 + }, + { + "epoch": 4.174089068825911, + "grad_norm": 0.22263428561959228, + "learning_rate": 3.236349233544438e-06, + "loss": 0.3274, + "step": 1031 + }, + { + "epoch": 4.178137651821863, + "grad_norm": 0.2244410793184272, + "learning_rate": 3.205572144561604e-06, + "loss": 0.3485, + "step": 1032 + }, + { + "epoch": 4.182186234817814, + "grad_norm": 0.22446774577553197, + "learning_rate": 3.174929343376374e-06, + "loss": 0.3531, + "step": 1033 + }, + { + "epoch": 4.186234817813765, + "grad_norm": 0.23610655476947706, + "learning_rate": 3.1444210750077777e-06, + "loss": 0.3692, + "step": 1034 + }, + { + "epoch": 4.190283400809717, + "grad_norm": 0.23756303888407893, + "learning_rate": 3.1140475833991046e-06, + "loss": 0.3571, + "step": 1035 + }, + { + "epoch": 4.194331983805668, + "grad_norm": 0.22231894655105244, + "learning_rate": 3.0838091114159895e-06, + "loss": 0.3634, + "step": 1036 + }, + { + "epoch": 4.198380566801619, + "grad_norm": 0.22448325256959328, + "learning_rate": 3.0537059008444524e-06, + "loss": 0.3511, + "step": 1037 + }, + { + "epoch": 4.202429149797571, + "grad_norm": 0.2335532285443408, + "learning_rate": 3.0237381923889563e-06, + "loss": 0.3504, + "step": 1038 + }, + { + "epoch": 4.206477732793522, + "grad_norm": 0.5793528331954596, + "learning_rate": 2.9939062256704997e-06, + "loss": 0.3726, + "step": 1039 + }, + { + "epoch": 4.2105263157894735, + "grad_norm": 0.22423547369345884, + "learning_rate": 2.964210239224696e-06, + "loss": 0.3604, + "step": 1040 + }, + { + "epoch": 4.2145748987854255, + "grad_norm": 0.23161100538736404, + "learning_rate": 2.934650470499869e-06, + "loss": 0.3536, + "step": 1041 + }, + { + "epoch": 4.218623481781377, + "grad_norm": 0.2163494154930157, + "learning_rate": 2.905227155855128e-06, + "loss": 0.3367, + "step": 1042 + }, + { + "epoch": 4.222672064777328, + "grad_norm": 0.2205296998945866, + "learning_rate": 2.875940530558519e-06, + "loss": 0.3674, + "step": 1043 + }, + { + "epoch": 4.22672064777328, + "grad_norm": 0.23574239307053088, + "learning_rate": 2.8467908287851154e-06, + "loss": 0.3434, + "step": 1044 + }, + { + "epoch": 4.230769230769231, + "grad_norm": 0.2225426660179318, + "learning_rate": 2.8177782836151603e-06, + "loss": 0.3593, + "step": 1045 + }, + { + "epoch": 4.234817813765182, + "grad_norm": 0.21403984761568692, + "learning_rate": 2.7889031270321874e-06, + "loss": 0.3576, + "step": 1046 + }, + { + "epoch": 4.238866396761134, + "grad_norm": 0.23335424224168902, + "learning_rate": 2.760165589921184e-06, + "loss": 0.3566, + "step": 1047 + }, + { + "epoch": 4.242914979757085, + "grad_norm": 0.21839872353101586, + "learning_rate": 2.7315659020667305e-06, + "loss": 0.3727, + "step": 1048 + }, + { + "epoch": 4.246963562753036, + "grad_norm": 0.21536077129215667, + "learning_rate": 2.703104292151164e-06, + "loss": 0.3703, + "step": 1049 + }, + { + "epoch": 4.251012145748988, + "grad_norm": 0.21915686633686665, + "learning_rate": 2.6747809877527607e-06, + "loss": 0.3641, + "step": 1050 + }, + { + "epoch": 4.255060728744939, + "grad_norm": 0.23552742930679932, + "learning_rate": 2.6465962153439082e-06, + "loss": 0.3594, + "step": 1051 + }, + { + "epoch": 4.2591093117408905, + "grad_norm": 0.2296164934760995, + "learning_rate": 2.618550200289303e-06, + "loss": 0.3354, + "step": 1052 + }, + { + "epoch": 4.2631578947368425, + "grad_norm": 0.22687092005409798, + "learning_rate": 2.59064316684412e-06, + "loss": 0.3605, + "step": 1053 + }, + { + "epoch": 4.267206477732794, + "grad_norm": 0.21758148571738767, + "learning_rate": 2.562875338152264e-06, + "loss": 0.3465, + "step": 1054 + }, + { + "epoch": 4.271255060728745, + "grad_norm": 0.21873330025515378, + "learning_rate": 2.5352469362445552e-06, + "loss": 0.3517, + "step": 1055 + }, + { + "epoch": 4.275303643724697, + "grad_norm": 0.23071892573407807, + "learning_rate": 2.5077581820369523e-06, + "loss": 0.3481, + "step": 1056 + }, + { + "epoch": 4.279352226720648, + "grad_norm": 0.22942132465826762, + "learning_rate": 2.480409295328803e-06, + "loss": 0.3536, + "step": 1057 + }, + { + "epoch": 4.283400809716599, + "grad_norm": 0.22170699369129182, + "learning_rate": 2.45320049480108e-06, + "loss": 0.3499, + "step": 1058 + }, + { + "epoch": 4.287449392712551, + "grad_norm": 0.2295617065259299, + "learning_rate": 2.4261319980146293e-06, + "loss": 0.3467, + "step": 1059 + }, + { + "epoch": 4.291497975708502, + "grad_norm": 0.22497332961078273, + "learning_rate": 2.399204021408421e-06, + "loss": 0.3431, + "step": 1060 + }, + { + "epoch": 4.295546558704453, + "grad_norm": 0.2292723559038031, + "learning_rate": 2.3724167802978395e-06, + "loss": 0.3501, + "step": 1061 + }, + { + "epoch": 4.299595141700405, + "grad_norm": 0.21960199376120665, + "learning_rate": 2.3457704888729625e-06, + "loss": 0.357, + "step": 1062 + }, + { + "epoch": 4.303643724696356, + "grad_norm": 0.21196127660437591, + "learning_rate": 2.3192653601968162e-06, + "loss": 0.3697, + "step": 1063 + }, + { + "epoch": 4.3076923076923075, + "grad_norm": 0.23493728730326113, + "learning_rate": 2.2929016062037057e-06, + "loss": 0.3385, + "step": 1064 + }, + { + "epoch": 4.3117408906882595, + "grad_norm": 0.22362764822046213, + "learning_rate": 2.2666794376975055e-06, + "loss": 0.3465, + "step": 1065 + }, + { + "epoch": 4.315789473684211, + "grad_norm": 0.22643559066713614, + "learning_rate": 2.24059906434998e-06, + "loss": 0.3246, + "step": 1066 + }, + { + "epoch": 4.319838056680162, + "grad_norm": 0.21694790043613899, + "learning_rate": 2.214660694699091e-06, + "loss": 0.3411, + "step": 1067 + }, + { + "epoch": 4.323886639676114, + "grad_norm": 0.23120501051576178, + "learning_rate": 2.188864536147355e-06, + "loss": 0.3483, + "step": 1068 + }, + { + "epoch": 4.327935222672065, + "grad_norm": 0.22398304071067057, + "learning_rate": 2.1632107949601757e-06, + "loss": 0.3605, + "step": 1069 + }, + { + "epoch": 4.331983805668016, + "grad_norm": 0.2326243643738351, + "learning_rate": 2.137699676264171e-06, + "loss": 0.3446, + "step": 1070 + }, + { + "epoch": 4.336032388663968, + "grad_norm": 0.22215961851764462, + "learning_rate": 2.1123313840455738e-06, + "loss": 0.3472, + "step": 1071 + }, + { + "epoch": 4.340080971659919, + "grad_norm": 0.21620112433540514, + "learning_rate": 2.08710612114857e-06, + "loss": 0.3602, + "step": 1072 + }, + { + "epoch": 4.34412955465587, + "grad_norm": 0.22509800012653997, + "learning_rate": 2.0620240892736953e-06, + "loss": 0.363, + "step": 1073 + }, + { + "epoch": 4.348178137651822, + "grad_norm": 0.21705431774253145, + "learning_rate": 2.0370854889762e-06, + "loss": 0.3698, + "step": 1074 + }, + { + "epoch": 4.352226720647773, + "grad_norm": 0.22491323102615568, + "learning_rate": 2.0122905196644726e-06, + "loss": 0.3388, + "step": 1075 + }, + { + "epoch": 4.3562753036437245, + "grad_norm": 0.22184473402586508, + "learning_rate": 1.987639379598427e-06, + "loss": 0.344, + "step": 1076 + }, + { + "epoch": 4.3603238866396765, + "grad_norm": 0.21353558784278348, + "learning_rate": 1.963132265887919e-06, + "loss": 0.3593, + "step": 1077 + }, + { + "epoch": 4.364372469635628, + "grad_norm": 0.2123526897186212, + "learning_rate": 1.9387693744911784e-06, + "loss": 0.3598, + "step": 1078 + }, + { + "epoch": 4.368421052631579, + "grad_norm": 0.2160864041827765, + "learning_rate": 1.9145509002132368e-06, + "loss": 0.3545, + "step": 1079 + }, + { + "epoch": 4.372469635627531, + "grad_norm": 0.21291893043423948, + "learning_rate": 1.8904770367043723e-06, + "loss": 0.3551, + "step": 1080 + }, + { + "epoch": 4.376518218623482, + "grad_norm": 0.22510111085313814, + "learning_rate": 1.8665479764585504e-06, + "loss": 0.3682, + "step": 1081 + }, + { + "epoch": 4.380566801619433, + "grad_norm": 0.22336477231529045, + "learning_rate": 1.8427639108118977e-06, + "loss": 0.3403, + "step": 1082 + }, + { + "epoch": 4.384615384615385, + "grad_norm": 0.2137247678596304, + "learning_rate": 1.8191250299411755e-06, + "loss": 0.374, + "step": 1083 + }, + { + "epoch": 4.388663967611336, + "grad_norm": 0.2166068504125183, + "learning_rate": 1.7956315228622446e-06, + "loss": 0.345, + "step": 1084 + }, + { + "epoch": 4.392712550607287, + "grad_norm": 0.22511242742682394, + "learning_rate": 1.7722835774285553e-06, + "loss": 0.3364, + "step": 1085 + }, + { + "epoch": 4.396761133603239, + "grad_norm": 0.2214638720990216, + "learning_rate": 1.7490813803296624e-06, + "loss": 0.3504, + "step": 1086 + }, + { + "epoch": 4.40080971659919, + "grad_norm": 0.253537346844459, + "learning_rate": 1.726025117089718e-06, + "loss": 0.3249, + "step": 1087 + }, + { + "epoch": 4.4048582995951415, + "grad_norm": 0.2150184483673469, + "learning_rate": 1.70311497206598e-06, + "loss": 0.3504, + "step": 1088 + }, + { + "epoch": 4.4089068825910935, + "grad_norm": 0.2157399759446024, + "learning_rate": 1.6803511284473638e-06, + "loss": 0.3477, + "step": 1089 + }, + { + "epoch": 4.412955465587045, + "grad_norm": 0.22610928635292016, + "learning_rate": 1.6577337682529538e-06, + "loss": 0.3423, + "step": 1090 + }, + { + "epoch": 4.417004048582996, + "grad_norm": 0.21510373934092863, + "learning_rate": 1.6352630723305617e-06, + "loss": 0.354, + "step": 1091 + }, + { + "epoch": 4.421052631578947, + "grad_norm": 0.220831958681427, + "learning_rate": 1.612939220355272e-06, + "loss": 0.3385, + "step": 1092 + }, + { + "epoch": 4.425101214574899, + "grad_norm": 0.21331794750385474, + "learning_rate": 1.5907623908280112e-06, + "loss": 0.3481, + "step": 1093 + }, + { + "epoch": 4.42914979757085, + "grad_norm": 0.21965358589691067, + "learning_rate": 1.568732761074121e-06, + "loss": 0.3385, + "step": 1094 + }, + { + "epoch": 4.433198380566802, + "grad_norm": 0.21808252432907507, + "learning_rate": 1.5468505072419237e-06, + "loss": 0.3517, + "step": 1095 + }, + { + "epoch": 4.437246963562753, + "grad_norm": 0.219725370488758, + "learning_rate": 1.5251158043013448e-06, + "loss": 0.3399, + "step": 1096 + }, + { + "epoch": 4.441295546558704, + "grad_norm": 0.21447630744324067, + "learning_rate": 1.5035288260424885e-06, + "loss": 0.3448, + "step": 1097 + }, + { + "epoch": 4.445344129554655, + "grad_norm": 0.23811093204087833, + "learning_rate": 1.4820897450742623e-06, + "loss": 0.356, + "step": 1098 + }, + { + "epoch": 4.449392712550607, + "grad_norm": 0.2963749157288049, + "learning_rate": 1.4607987328229767e-06, + "loss": 0.3598, + "step": 1099 + }, + { + "epoch": 4.4534412955465585, + "grad_norm": 0.22526454186464548, + "learning_rate": 1.4396559595310056e-06, + "loss": 0.3336, + "step": 1100 + }, + { + "epoch": 4.4574898785425106, + "grad_norm": 0.21931253242822588, + "learning_rate": 1.4186615942553973e-06, + "loss": 0.369, + "step": 1101 + }, + { + "epoch": 4.461538461538462, + "grad_norm": 0.21424967558111693, + "learning_rate": 1.3978158048665424e-06, + "loss": 0.3327, + "step": 1102 + }, + { + "epoch": 4.465587044534413, + "grad_norm": 0.2174484158413736, + "learning_rate": 1.3771187580468115e-06, + "loss": 0.3584, + "step": 1103 + }, + { + "epoch": 4.469635627530364, + "grad_norm": 0.21771367345686166, + "learning_rate": 1.3565706192892392e-06, + "loss": 0.3695, + "step": 1104 + }, + { + "epoch": 4.473684210526316, + "grad_norm": 0.21968952269674819, + "learning_rate": 1.3361715528961993e-06, + "loss": 0.3375, + "step": 1105 + }, + { + "epoch": 4.477732793522267, + "grad_norm": 0.21393503845515646, + "learning_rate": 1.3159217219780817e-06, + "loss": 0.3629, + "step": 1106 + }, + { + "epoch": 4.481781376518219, + "grad_norm": 0.21907466640012907, + "learning_rate": 1.2958212884519949e-06, + "loss": 0.3595, + "step": 1107 + }, + { + "epoch": 4.48582995951417, + "grad_norm": 0.21248830945237449, + "learning_rate": 1.2758704130404675e-06, + "loss": 0.3682, + "step": 1108 + }, + { + "epoch": 4.489878542510121, + "grad_norm": 0.24613964059771007, + "learning_rate": 1.2560692552701738e-06, + "loss": 0.362, + "step": 1109 + }, + { + "epoch": 4.493927125506072, + "grad_norm": 0.21006573306691365, + "learning_rate": 1.2364179734706382e-06, + "loss": 0.3706, + "step": 1110 + }, + { + "epoch": 4.497975708502024, + "grad_norm": 0.21927485168668118, + "learning_rate": 1.2169167247729852e-06, + "loss": 0.3552, + "step": 1111 + }, + { + "epoch": 4.502024291497976, + "grad_norm": 0.22757958778961074, + "learning_rate": 1.1975656651086864e-06, + "loss": 0.3568, + "step": 1112 + }, + { + "epoch": 4.506072874493928, + "grad_norm": 0.2258873096014452, + "learning_rate": 1.1783649492082926e-06, + "loss": 0.3458, + "step": 1113 + }, + { + "epoch": 4.510121457489879, + "grad_norm": 0.21963859396377536, + "learning_rate": 1.1593147306002183e-06, + "loss": 0.3475, + "step": 1114 + }, + { + "epoch": 4.51417004048583, + "grad_norm": 0.21342866870982344, + "learning_rate": 1.140415161609505e-06, + "loss": 0.3566, + "step": 1115 + }, + { + "epoch": 4.518218623481781, + "grad_norm": 0.2164689381124055, + "learning_rate": 1.121666393356604e-06, + "loss": 0.3708, + "step": 1116 + }, + { + "epoch": 4.522267206477733, + "grad_norm": 0.22600934975751422, + "learning_rate": 1.1030685757561632e-06, + "loss": 0.3359, + "step": 1117 + }, + { + "epoch": 4.526315789473684, + "grad_norm": 0.23203643357959783, + "learning_rate": 1.0846218575158373e-06, + "loss": 0.3365, + "step": 1118 + }, + { + "epoch": 4.530364372469636, + "grad_norm": 0.2210541520003719, + "learning_rate": 1.066326386135097e-06, + "loss": 0.3318, + "step": 1119 + }, + { + "epoch": 4.534412955465587, + "grad_norm": 0.3468166668970051, + "learning_rate": 1.0481823079040398e-06, + "loss": 0.3576, + "step": 1120 + }, + { + "epoch": 4.538461538461538, + "grad_norm": 0.21424482433826317, + "learning_rate": 1.0301897679022344e-06, + "loss": 0.3634, + "step": 1121 + }, + { + "epoch": 4.5425101214574894, + "grad_norm": 0.22063064037182897, + "learning_rate": 1.0123489099975491e-06, + "loss": 0.3519, + "step": 1122 + }, + { + "epoch": 4.5465587044534415, + "grad_norm": 0.21828075641418282, + "learning_rate": 9.9465987684501e-07, + "loss": 0.3576, + "step": 1123 + }, + { + "epoch": 4.550607287449393, + "grad_norm": 0.21720568793672695, + "learning_rate": 9.771228098856534e-07, + "loss": 0.3366, + "step": 1124 + }, + { + "epoch": 4.554655870445345, + "grad_norm": 0.21237924750192497, + "learning_rate": 9.597378493454013e-07, + "loss": 0.3446, + "step": 1125 + }, + { + "epoch": 4.558704453441296, + "grad_norm": 0.21966762364519243, + "learning_rate": 9.425051342339353e-07, + "loss": 0.3161, + "step": 1126 + }, + { + "epoch": 4.562753036437247, + "grad_norm": 0.21776030085005246, + "learning_rate": 9.254248023435864e-07, + "loss": 0.3387, + "step": 1127 + }, + { + "epoch": 4.566801619433198, + "grad_norm": 0.2158183267551532, + "learning_rate": 9.084969902482288e-07, + "loss": 0.3541, + "step": 1128 + }, + { + "epoch": 4.57085020242915, + "grad_norm": 0.20854892839872805, + "learning_rate": 8.917218333021993e-07, + "loss": 0.358, + "step": 1129 + }, + { + "epoch": 4.574898785425101, + "grad_norm": 0.20522235613228879, + "learning_rate": 8.750994656392109e-07, + "loss": 0.3697, + "step": 1130 + }, + { + "epoch": 4.578947368421053, + "grad_norm": 0.7308803631927825, + "learning_rate": 8.58630020171265e-07, + "loss": 0.3578, + "step": 1131 + }, + { + "epoch": 4.582995951417004, + "grad_norm": 0.21438119122643884, + "learning_rate": 8.423136285876099e-07, + "loss": 0.3368, + "step": 1132 + }, + { + "epoch": 4.587044534412955, + "grad_norm": 0.21078722284785054, + "learning_rate": 8.26150421353682e-07, + "loss": 0.3507, + "step": 1133 + }, + { + "epoch": 4.5910931174089065, + "grad_norm": 0.2241967793900079, + "learning_rate": 8.101405277100549e-07, + "loss": 0.3232, + "step": 1134 + }, + { + "epoch": 4.5951417004048585, + "grad_norm": 0.24736717702231711, + "learning_rate": 7.942840756714077e-07, + "loss": 0.3439, + "step": 1135 + }, + { + "epoch": 4.59919028340081, + "grad_norm": 0.2256851105132317, + "learning_rate": 7.785811920255093e-07, + "loss": 0.3239, + "step": 1136 + }, + { + "epoch": 4.603238866396762, + "grad_norm": 0.21713672643091528, + "learning_rate": 7.630320023322024e-07, + "loss": 0.3432, + "step": 1137 + }, + { + "epoch": 4.607287449392713, + "grad_norm": 0.21469515378147339, + "learning_rate": 7.476366309223903e-07, + "loss": 0.3548, + "step": 1138 + }, + { + "epoch": 4.611336032388664, + "grad_norm": 0.20722760757546388, + "learning_rate": 7.323952008970537e-07, + "loss": 0.3457, + "step": 1139 + }, + { + "epoch": 4.615384615384615, + "grad_norm": 0.21059549574085148, + "learning_rate": 7.173078341262618e-07, + "loss": 0.3455, + "step": 1140 + }, + { + "epoch": 4.619433198380567, + "grad_norm": 0.2178516769467103, + "learning_rate": 7.023746512481989e-07, + "loss": 0.355, + "step": 1141 + }, + { + "epoch": 4.623481781376518, + "grad_norm": 0.22997604619876846, + "learning_rate": 6.875957716681902e-07, + "loss": 0.3422, + "step": 1142 + }, + { + "epoch": 4.62753036437247, + "grad_norm": 0.21809168795733133, + "learning_rate": 6.729713135577687e-07, + "loss": 0.347, + "step": 1143 + }, + { + "epoch": 4.631578947368421, + "grad_norm": 0.20557633917638404, + "learning_rate": 6.585013938537143e-07, + "loss": 0.3612, + "step": 1144 + }, + { + "epoch": 4.635627530364372, + "grad_norm": 0.2201300927637923, + "learning_rate": 6.441861282571115e-07, + "loss": 0.3432, + "step": 1145 + }, + { + "epoch": 4.6396761133603235, + "grad_norm": 0.20951324776043373, + "learning_rate": 6.300256312324471e-07, + "loss": 0.3543, + "step": 1146 + }, + { + "epoch": 4.6437246963562755, + "grad_norm": 0.2127126175388503, + "learning_rate": 6.160200160066776e-07, + "loss": 0.358, + "step": 1147 + }, + { + "epoch": 4.647773279352227, + "grad_norm": 0.21574183445888204, + "learning_rate": 6.021693945683327e-07, + "loss": 0.335, + "step": 1148 + }, + { + "epoch": 4.651821862348179, + "grad_norm": 0.22151779935166038, + "learning_rate": 5.884738776666044e-07, + "loss": 0.351, + "step": 1149 + }, + { + "epoch": 4.65587044534413, + "grad_norm": 0.21472485408796055, + "learning_rate": 5.749335748104878e-07, + "loss": 0.3494, + "step": 1150 + }, + { + "epoch": 4.659919028340081, + "grad_norm": 0.2274685289308812, + "learning_rate": 5.615485942678778e-07, + "loss": 0.3417, + "step": 1151 + }, + { + "epoch": 4.663967611336032, + "grad_norm": 0.2232214155589449, + "learning_rate": 5.483190430647289e-07, + "loss": 0.3303, + "step": 1152 + }, + { + "epoch": 4.668016194331984, + "grad_norm": 0.21684150531046809, + "learning_rate": 5.352450269841747e-07, + "loss": 0.3532, + "step": 1153 + }, + { + "epoch": 4.672064777327935, + "grad_norm": 0.2248154804634695, + "learning_rate": 5.22326650565701e-07, + "loss": 0.3392, + "step": 1154 + }, + { + "epoch": 4.676113360323887, + "grad_norm": 0.22466369098426495, + "learning_rate": 5.095640171043048e-07, + "loss": 0.3481, + "step": 1155 + }, + { + "epoch": 4.680161943319838, + "grad_norm": 0.20727811265249846, + "learning_rate": 4.969572286496594e-07, + "loss": 0.3448, + "step": 1156 + }, + { + "epoch": 4.684210526315789, + "grad_norm": 0.2112213551031676, + "learning_rate": 4.845063860053079e-07, + "loss": 0.3514, + "step": 1157 + }, + { + "epoch": 4.6882591093117405, + "grad_norm": 0.21480913344922994, + "learning_rate": 4.7221158872785997e-07, + "loss": 0.3413, + "step": 1158 + }, + { + "epoch": 4.6923076923076925, + "grad_norm": 0.21471149284077426, + "learning_rate": 4.600729351261857e-07, + "loss": 0.3631, + "step": 1159 + }, + { + "epoch": 4.696356275303644, + "grad_norm": 0.2153034048725801, + "learning_rate": 4.4809052226063355e-07, + "loss": 0.3216, + "step": 1160 + }, + { + "epoch": 4.700404858299595, + "grad_norm": 0.22747359845273807, + "learning_rate": 4.3626444594226046e-07, + "loss": 0.3254, + "step": 1161 + }, + { + "epoch": 4.704453441295547, + "grad_norm": 0.20540732174402357, + "learning_rate": 4.245948007320588e-07, + "loss": 0.3673, + "step": 1162 + }, + { + "epoch": 4.708502024291498, + "grad_norm": 0.2152998120592181, + "learning_rate": 4.130816799401971e-07, + "loss": 0.3494, + "step": 1163 + }, + { + "epoch": 4.712550607287449, + "grad_norm": 0.21346712908090132, + "learning_rate": 4.017251756252827e-07, + "loss": 0.3398, + "step": 1164 + }, + { + "epoch": 4.716599190283401, + "grad_norm": 0.21132438841224435, + "learning_rate": 3.9052537859362473e-07, + "loss": 0.3586, + "step": 1165 + }, + { + "epoch": 4.720647773279352, + "grad_norm": 0.2012849616835743, + "learning_rate": 3.7948237839849687e-07, + "loss": 0.3664, + "step": 1166 + }, + { + "epoch": 4.724696356275303, + "grad_norm": 0.21325554419180645, + "learning_rate": 3.6859626333943797e-07, + "loss": 0.3402, + "step": 1167 + }, + { + "epoch": 4.728744939271255, + "grad_norm": 0.22467465337471185, + "learning_rate": 3.578671204615347e-07, + "loss": 0.3482, + "step": 1168 + }, + { + "epoch": 4.732793522267206, + "grad_norm": 0.21957208624605082, + "learning_rate": 3.472950355547267e-07, + "loss": 0.3568, + "step": 1169 + }, + { + "epoch": 4.7368421052631575, + "grad_norm": 0.21790040803264907, + "learning_rate": 3.3688009315312244e-07, + "loss": 0.3436, + "step": 1170 + }, + { + "epoch": 4.7408906882591095, + "grad_norm": 0.21071110166407558, + "learning_rate": 3.266223765343224e-07, + "loss": 0.3639, + "step": 1171 + }, + { + "epoch": 4.744939271255061, + "grad_norm": 0.2173513694277339, + "learning_rate": 3.16521967718757e-07, + "loss": 0.3534, + "step": 1172 + }, + { + "epoch": 4.748987854251012, + "grad_norm": 0.20986188074936768, + "learning_rate": 3.0657894746902726e-07, + "loss": 0.3737, + "step": 1173 + }, + { + "epoch": 4.753036437246964, + "grad_norm": 0.2105350349001971, + "learning_rate": 2.9679339528925654e-07, + "loss": 0.3611, + "step": 1174 + }, + { + "epoch": 4.757085020242915, + "grad_norm": 0.20841721906603652, + "learning_rate": 2.871653894244597e-07, + "loss": 0.3651, + "step": 1175 + }, + { + "epoch": 4.761133603238866, + "grad_norm": 0.20946338290949917, + "learning_rate": 2.7769500685991266e-07, + "loss": 0.3586, + "step": 1176 + }, + { + "epoch": 4.765182186234818, + "grad_norm": 0.20818293808999547, + "learning_rate": 2.683823233205485e-07, + "loss": 0.3795, + "step": 1177 + }, + { + "epoch": 4.769230769230769, + "grad_norm": 0.21714903566281354, + "learning_rate": 2.592274132703287e-07, + "loss": 0.3367, + "step": 1178 + }, + { + "epoch": 4.77327935222672, + "grad_norm": 0.22896158253435145, + "learning_rate": 2.502303499116754e-07, + "loss": 0.3455, + "step": 1179 + }, + { + "epoch": 4.777327935222672, + "grad_norm": 0.21682902898881515, + "learning_rate": 2.413912051848666e-07, + "loss": 0.352, + "step": 1180 + }, + { + "epoch": 4.781376518218623, + "grad_norm": 0.21977143136584582, + "learning_rate": 2.3271004976746613e-07, + "loss": 0.3502, + "step": 1181 + }, + { + "epoch": 4.7854251012145745, + "grad_norm": 0.21766349727526496, + "learning_rate": 2.2418695307376393e-07, + "loss": 0.356, + "step": 1182 + }, + { + "epoch": 4.7894736842105265, + "grad_norm": 0.20907183893598175, + "learning_rate": 2.1582198325420968e-07, + "loss": 0.3387, + "step": 1183 + }, + { + "epoch": 4.793522267206478, + "grad_norm": 0.21138155191339106, + "learning_rate": 2.0761520719488447e-07, + "loss": 0.3368, + "step": 1184 + }, + { + "epoch": 4.797570850202429, + "grad_norm": 0.2124284279326404, + "learning_rate": 1.9956669051694798e-07, + "loss": 0.3521, + "step": 1185 + }, + { + "epoch": 4.801619433198381, + "grad_norm": 0.21694717104780725, + "learning_rate": 1.916764975761254e-07, + "loss": 0.3668, + "step": 1186 + }, + { + "epoch": 4.805668016194332, + "grad_norm": 0.2170397663825815, + "learning_rate": 1.839446914621923e-07, + "loss": 0.3409, + "step": 1187 + }, + { + "epoch": 4.809716599190283, + "grad_norm": 0.21748643805786635, + "learning_rate": 1.7637133399845962e-07, + "loss": 0.3339, + "step": 1188 + }, + { + "epoch": 4.813765182186235, + "grad_norm": 0.20707902210633883, + "learning_rate": 1.6895648574129397e-07, + "loss": 0.3363, + "step": 1189 + }, + { + "epoch": 4.817813765182186, + "grad_norm": 0.2194633874502687, + "learning_rate": 1.6170020597962465e-07, + "loss": 0.3255, + "step": 1190 + }, + { + "epoch": 4.821862348178137, + "grad_norm": 0.2087898244726411, + "learning_rate": 1.5460255273447078e-07, + "loss": 0.3619, + "step": 1191 + }, + { + "epoch": 4.825910931174089, + "grad_norm": 0.21490707710056509, + "learning_rate": 1.4766358275847715e-07, + "loss": 0.3486, + "step": 1192 + }, + { + "epoch": 4.82995951417004, + "grad_norm": 0.21347088097556302, + "learning_rate": 1.4088335153546573e-07, + "loss": 0.345, + "step": 1193 + }, + { + "epoch": 4.834008097165992, + "grad_norm": 0.2076237152665109, + "learning_rate": 1.3426191327998496e-07, + "loss": 0.3633, + "step": 1194 + }, + { + "epoch": 4.838056680161944, + "grad_norm": 0.2174825648484177, + "learning_rate": 1.277993209368744e-07, + "loss": 0.3644, + "step": 1195 + }, + { + "epoch": 4.842105263157895, + "grad_norm": 0.22262434135765247, + "learning_rate": 1.214956261808542e-07, + "loss": 0.3364, + "step": 1196 + }, + { + "epoch": 4.846153846153846, + "grad_norm": 0.20514308901313075, + "learning_rate": 1.1535087941609846e-07, + "loss": 0.3688, + "step": 1197 + }, + { + "epoch": 4.850202429149798, + "grad_norm": 0.20592342617789813, + "learning_rate": 1.0936512977583802e-07, + "loss": 0.3601, + "step": 1198 + }, + { + "epoch": 4.854251012145749, + "grad_norm": 0.22715270838435855, + "learning_rate": 1.0353842512196732e-07, + "loss": 0.359, + "step": 1199 + }, + { + "epoch": 4.8582995951417, + "grad_norm": 0.20917532052739576, + "learning_rate": 9.787081204466253e-08, + "loss": 0.352, + "step": 1200 + }, + { + "epoch": 4.862348178137652, + "grad_norm": 0.20905358860043996, + "learning_rate": 9.236233586200627e-08, + "loss": 0.3567, + "step": 1201 + }, + { + "epoch": 4.866396761133603, + "grad_norm": 0.21305061918848994, + "learning_rate": 8.70130406196279e-08, + "loss": 0.3563, + "step": 1202 + }, + { + "epoch": 4.870445344129554, + "grad_norm": 0.2065338874580827, + "learning_rate": 8.182296909035047e-08, + "loss": 0.3413, + "step": 1203 + }, + { + "epoch": 4.874493927125506, + "grad_norm": 0.21448653176165883, + "learning_rate": 7.679216277384439e-08, + "loss": 0.3573, + "step": 1204 + }, + { + "epoch": 4.8785425101214575, + "grad_norm": 0.22006429040638045, + "learning_rate": 7.19206618963053e-08, + "loss": 0.3393, + "step": 1205 + }, + { + "epoch": 4.882591093117409, + "grad_norm": 0.20715854975505488, + "learning_rate": 6.720850541012347e-08, + "loss": 0.3631, + "step": 1206 + }, + { + "epoch": 4.886639676113361, + "grad_norm": 0.21297644455013515, + "learning_rate": 6.265573099357714e-08, + "loss": 0.3473, + "step": 1207 + }, + { + "epoch": 4.890688259109312, + "grad_norm": 0.21646831391396468, + "learning_rate": 5.826237505053067e-08, + "loss": 0.3424, + "step": 1208 + }, + { + "epoch": 4.894736842105263, + "grad_norm": 0.21129211798763098, + "learning_rate": 5.4028472710137e-08, + "loss": 0.3413, + "step": 1209 + }, + { + "epoch": 4.898785425101215, + "grad_norm": 0.21609170971481384, + "learning_rate": 4.9954057826571146e-08, + "loss": 0.3464, + "step": 1210 + }, + { + "epoch": 4.902834008097166, + "grad_norm": 0.21080543543007416, + "learning_rate": 4.6039162978743776e-08, + "loss": 0.3451, + "step": 1211 + }, + { + "epoch": 4.906882591093117, + "grad_norm": 0.2069308289313909, + "learning_rate": 4.228381947004812e-08, + "loss": 0.3551, + "step": 1212 + }, + { + "epoch": 4.910931174089069, + "grad_norm": 0.20960865982845941, + "learning_rate": 3.868805732811343e-08, + "loss": 0.3666, + "step": 1213 + }, + { + "epoch": 4.91497975708502, + "grad_norm": 0.21861468388063918, + "learning_rate": 3.525190530455636e-08, + "loss": 0.3675, + "step": 1214 + }, + { + "epoch": 4.919028340080971, + "grad_norm": 0.21330046643890457, + "learning_rate": 3.197539087475887e-08, + "loss": 0.3519, + "step": 1215 + }, + { + "epoch": 4.923076923076923, + "grad_norm": 0.22121906183317566, + "learning_rate": 2.8858540237641786e-08, + "loss": 0.3569, + "step": 1216 + }, + { + "epoch": 4.9271255060728745, + "grad_norm": 0.21833650582428296, + "learning_rate": 2.5901378315458247e-08, + "loss": 0.3439, + "step": 1217 + }, + { + "epoch": 4.931174089068826, + "grad_norm": 0.19587236502502833, + "learning_rate": 2.3103928753598347e-08, + "loss": 0.369, + "step": 1218 + }, + { + "epoch": 4.935222672064778, + "grad_norm": 0.22091116653653184, + "learning_rate": 2.0466213920393718e-08, + "loss": 0.3478, + "step": 1219 + }, + { + "epoch": 4.939271255060729, + "grad_norm": 0.22495205921700442, + "learning_rate": 1.7988254906942115e-08, + "loss": 0.3645, + "step": 1220 + }, + { + "epoch": 4.94331983805668, + "grad_norm": 0.20674120912861857, + "learning_rate": 1.5670071526936447e-08, + "loss": 0.3702, + "step": 1221 + }, + { + "epoch": 4.947368421052632, + "grad_norm": 0.20410245486620435, + "learning_rate": 1.3511682316509344e-08, + "loss": 0.3617, + "step": 1222 + }, + { + "epoch": 4.951417004048583, + "grad_norm": 0.2099043633781449, + "learning_rate": 1.1513104534086605e-08, + "loss": 0.3642, + "step": 1223 + }, + { + "epoch": 4.955465587044534, + "grad_norm": 0.21209144325685536, + "learning_rate": 9.67435416023843e-09, + "loss": 0.3345, + "step": 1224 + }, + { + "epoch": 4.959514170040486, + "grad_norm": 0.20383189291337764, + "learning_rate": 7.995445897566178e-09, + "loss": 0.3534, + "step": 1225 + }, + { + "epoch": 4.963562753036437, + "grad_norm": 0.21166245571885528, + "learning_rate": 6.476393170578021e-09, + "loss": 0.3538, + "step": 1226 + }, + { + "epoch": 4.967611336032388, + "grad_norm": 0.21973251934476282, + "learning_rate": 5.11720812557348e-09, + "loss": 0.383, + "step": 1227 + }, + { + "epoch": 4.97165991902834, + "grad_norm": 0.21187157850872798, + "learning_rate": 3.917901630563492e-09, + "loss": 0.3391, + "step": 1228 + }, + { + "epoch": 4.9757085020242915, + "grad_norm": 0.20778380586964065, + "learning_rate": 2.878483275170485e-09, + "loss": 0.3758, + "step": 1229 + }, + { + "epoch": 4.979757085020243, + "grad_norm": 0.20770995650646387, + "learning_rate": 1.998961370555108e-09, + "loss": 0.3351, + "step": 1230 + }, + { + "epoch": 4.983805668016195, + "grad_norm": 0.21165800109265864, + "learning_rate": 1.2793429493518361e-09, + "loss": 0.3562, + "step": 1231 + }, + { + "epoch": 4.987854251012146, + "grad_norm": 0.20757703136943653, + "learning_rate": 7.196337656112384e-10, + "loss": 0.3503, + "step": 1232 + }, + { + "epoch": 4.991902834008097, + "grad_norm": 0.2051477933500928, + "learning_rate": 3.198382947511292e-10, + "loss": 0.3646, + "step": 1233 + }, + { + "epoch": 4.995951417004049, + "grad_norm": 0.2082728527602629, + "learning_rate": 7.995973352770137e-11, + "loss": 0.3765, + "step": 1234 + }, + { + "epoch": 5.0, + "grad_norm": 0.21010748134866428, + "learning_rate": 0.0, + "loss": 0.3403, + "step": 1235 + }, + { + "epoch": 5.0, + "step": 1235, + "total_flos": 4.3365838011792097e+18, + "train_loss": 0.4892277446353001, + "train_runtime": 29008.2393, + "train_samples_per_second": 5.447, + "train_steps_per_second": 0.043 + } + ], + "logging_steps": 1, + "max_steps": 1235, + "num_input_tokens_seen": 0, + "num_train_epochs": 5, + "save_steps": 500, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": true + }, + "attributes": {} + } + }, + "total_flos": 4.3365838011792097e+18, + "train_batch_size": 1, + "trial_name": null, + "trial_params": null +} diff --git a/training_args.bin b/training_args.bin new file mode 100644 index 0000000..89d2de9 --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac9b3907015013e66de4061013f404c63a88a9b7ad1f93b5baed13e328b3130d +size 7224 diff --git a/training_loss.png b/training_loss.png new file mode 100644 index 0000000..775119e Binary files /dev/null and b/training_loss.png differ diff --git a/vocab.json b/vocab.json new file mode 100644 index 0000000..6c49fc6 --- /dev/null +++ b/vocab.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910 +size 2776833