commit 2e88a7302785c2672db57942f510afce0bda5f16 Author: ModelHub XC Date: Fri May 8 15:59:25 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mlfoundations-dev/qwen2-5_code_ablate_duplications_3 Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b50ee21 --- /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 +training_args.bin filter=lfs diff=lfs merge=lfs -text +model-00002-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +vocab.json filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text +model-00004-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +model-00001-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +model-00003-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..b40c48a --- /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: qwen2-5_code_ablate_duplications_3 + results: [] +--- + + + +# qwen2-5_code_ablate_duplications_3 + +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/code_ablate_duplications_3 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: 1e-05 +- train_batch_size: 1 +- eval_batch_size: 8 +- seed: 42 +- distributed_type: multi-GPU +- num_devices: 32 +- gradient_accumulation_steps: 3 +- total_train_batch_size: 96 +- 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: 3.0 + +### 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..af936fe --- /dev/null +++ b/all_results.json @@ -0,0 +1,8 @@ +{ + "epoch": 2.994773519163763, + "total_flos": 520358168002560.0, + "train_loss": 0.6214590458553707, + "train_runtime": 8980.1589, + "train_samples_per_second": 6.133, + "train_steps_per_second": 0.064 +} \ 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..1f06281 --- /dev/null +++ b/configs.yaml @@ -0,0 +1,37 @@ +assistant_tag: gpt +bf16: true +content_tag: value +cutoff_len: 16384 +dataset: mlfoundations-dev/code_ablate_duplications_3 +dataset_dir: ONLINE +ddp_timeout: 180000000 +deepspeed: dcft/train/zero3.json +do_train: true +eval_strategy: 'no' +finetuning_type: full +formatting: sharegpt +global_batch_size: 96 +gradient_accumulation_steps: 3 +hub_model_id: mlfoundations-dev/qwen2-5_code_ablate_duplications_3 +include_hp: dcft/train/hp_settings/reasoning_old.yaml +learning_rate: 1.0e-05 +logging_steps: 1 +lr_scheduler_type: cosine +messages: conversations +model_name_or_path: Qwen/Qwen2.5-7B-Instruct +num_train_epochs: 3.0 +output_dir: /tmp/dcft_checkpoints/train/checkpoints/qwen2-5_code_ablate_duplications_3 +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 +run_name: qwen2-5_code_ablate_duplications_3 +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..a716666 --- /dev/null +++ b/model-00001-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73204e15758ce8a777588f7f532ec8d0195fb9a9dd142a678d1812764bb5d8cf +size 4877660776 diff --git a/model-00002-of-00004.safetensors b/model-00002-of-00004.safetensors new file mode 100644 index 0000000..f7c363e --- /dev/null +++ b/model-00002-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d88913f2aaede3f9711adc7f8f914e305821bfb40610faf4d173f09d64c0e94b +size 4932751008 diff --git a/model-00003-of-00004.safetensors b/model-00003-of-00004.safetensors new file mode 100644 index 0000000..fab10cb --- /dev/null +++ b/model-00003-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11615fd89fc1aaa1f1da4cd18972f52a5daae558ffa40d5215484b6a3f6b9e3e +size 4330865200 diff --git a/model-00004-of-00004.safetensors b/model-00004-of-00004.safetensors new file mode 100644 index 0000000..b871347 --- /dev/null +++ b/model-00004-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba213f8e3ebcdab24c60fa2721b2eeca4fec565d6065b5e9055bdace04dca318 +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..af936fe --- /dev/null +++ b/train_results.json @@ -0,0 +1,8 @@ +{ + "epoch": 2.994773519163763, + "total_flos": 520358168002560.0, + "train_loss": 0.6214590458553707, + "train_runtime": 8980.1589, + "train_samples_per_second": 6.133, + "train_steps_per_second": 0.064 +} \ No newline at end of file diff --git a/trainer_log.jsonl b/trainer_log.jsonl new file mode 100644 index 0000000..15116ac --- /dev/null +++ b/trainer_log.jsonl @@ -0,0 +1,574 @@ +{"current_steps": 1, "total_steps": 573, "loss": 1.0919, "lr": 1.7241379310344828e-07, "epoch": 0.005226480836236934, "percentage": 0.17, "elapsed_time": "0:00:17", "remaining_time": "2:48:06"} +{"current_steps": 2, "total_steps": 573, "loss": 1.1216, "lr": 3.4482758620689656e-07, "epoch": 0.010452961672473868, "percentage": 0.35, "elapsed_time": "0:00:34", "remaining_time": "2:46:27"} +{"current_steps": 3, "total_steps": 573, "loss": 1.0823, "lr": 5.172413793103449e-07, "epoch": 0.0156794425087108, "percentage": 0.52, "elapsed_time": "0:00:49", "remaining_time": "2:37:04"} +{"current_steps": 4, "total_steps": 573, "loss": 1.1163, "lr": 6.896551724137931e-07, "epoch": 0.020905923344947737, "percentage": 0.7, "elapsed_time": "0:01:04", "remaining_time": "2:33:03"} +{"current_steps": 5, "total_steps": 573, "loss": 1.0475, "lr": 8.620689655172415e-07, "epoch": 0.02613240418118467, "percentage": 0.87, "elapsed_time": "0:01:21", "remaining_time": "2:33:37"} +{"current_steps": 6, "total_steps": 573, "loss": 1.0632, "lr": 1.0344827586206898e-06, "epoch": 0.0313588850174216, "percentage": 1.05, "elapsed_time": "0:01:35", "remaining_time": "2:30:48"} +{"current_steps": 7, "total_steps": 573, "loss": 1.0867, "lr": 1.2068965517241381e-06, "epoch": 0.036585365853658534, "percentage": 1.22, "elapsed_time": "0:01:50", "remaining_time": "2:29:14"} +{"current_steps": 8, "total_steps": 573, "loss": 1.0679, "lr": 1.3793103448275862e-06, "epoch": 0.041811846689895474, "percentage": 1.4, "elapsed_time": "0:02:03", "remaining_time": "2:25:13"} +{"current_steps": 9, "total_steps": 573, "loss": 1.0599, "lr": 1.5517241379310346e-06, "epoch": 0.047038327526132406, "percentage": 1.57, "elapsed_time": "0:02:20", "remaining_time": "2:26:57"} +{"current_steps": 10, "total_steps": 573, "loss": 1.0377, "lr": 1.724137931034483e-06, "epoch": 0.05226480836236934, "percentage": 1.75, "elapsed_time": "0:02:36", "remaining_time": "2:27:12"} +{"current_steps": 11, "total_steps": 573, "loss": 0.9836, "lr": 1.896551724137931e-06, "epoch": 0.05749128919860627, "percentage": 1.92, "elapsed_time": "0:02:52", "remaining_time": "2:27:09"} +{"current_steps": 12, "total_steps": 573, "loss": 1.0003, "lr": 2.0689655172413796e-06, "epoch": 0.0627177700348432, "percentage": 2.09, "elapsed_time": "0:03:09", "remaining_time": "2:27:57"} +{"current_steps": 13, "total_steps": 573, "loss": 0.9805, "lr": 2.241379310344828e-06, "epoch": 0.06794425087108014, "percentage": 2.27, "elapsed_time": "0:03:24", "remaining_time": "2:27:07"} +{"current_steps": 14, "total_steps": 573, "loss": 0.9785, "lr": 2.4137931034482762e-06, "epoch": 0.07317073170731707, "percentage": 2.44, "elapsed_time": "0:03:39", "remaining_time": "2:25:46"} +{"current_steps": 15, "total_steps": 573, "loss": 0.9579, "lr": 2.5862068965517246e-06, "epoch": 0.078397212543554, "percentage": 2.62, "elapsed_time": "0:03:52", "remaining_time": "2:23:51"} +{"current_steps": 16, "total_steps": 573, "loss": 0.9266, "lr": 2.7586206896551725e-06, "epoch": 0.08362369337979095, "percentage": 2.79, "elapsed_time": "0:04:08", "remaining_time": "2:24:27"} +{"current_steps": 17, "total_steps": 573, "loss": 0.9496, "lr": 2.931034482758621e-06, "epoch": 0.08885017421602788, "percentage": 2.97, "elapsed_time": "0:04:25", "remaining_time": "2:24:43"} +{"current_steps": 18, "total_steps": 573, "loss": 0.9417, "lr": 3.103448275862069e-06, "epoch": 0.09407665505226481, "percentage": 3.14, "elapsed_time": "0:04:39", "remaining_time": "2:23:32"} +{"current_steps": 19, "total_steps": 573, "loss": 0.9133, "lr": 3.2758620689655175e-06, "epoch": 0.09930313588850175, "percentage": 3.32, "elapsed_time": "0:04:55", "remaining_time": "2:23:50"} +{"current_steps": 20, "total_steps": 573, "loss": 0.9181, "lr": 3.448275862068966e-06, "epoch": 0.10452961672473868, "percentage": 3.49, "elapsed_time": "0:05:08", "remaining_time": "2:22:06"} +{"current_steps": 21, "total_steps": 573, "loss": 0.8708, "lr": 3.620689655172414e-06, "epoch": 0.10975609756097561, "percentage": 3.66, "elapsed_time": "0:05:20", "remaining_time": "2:20:29"} +{"current_steps": 22, "total_steps": 573, "loss": 0.8532, "lr": 3.793103448275862e-06, "epoch": 0.11498257839721254, "percentage": 3.84, "elapsed_time": "0:05:38", "remaining_time": "2:21:06"} +{"current_steps": 23, "total_steps": 573, "loss": 0.867, "lr": 3.96551724137931e-06, "epoch": 0.12020905923344948, "percentage": 4.01, "elapsed_time": "0:05:51", "remaining_time": "2:19:56"} +{"current_steps": 24, "total_steps": 573, "loss": 0.8596, "lr": 4.137931034482759e-06, "epoch": 0.1254355400696864, "percentage": 4.19, "elapsed_time": "0:06:06", "remaining_time": "2:19:45"} +{"current_steps": 25, "total_steps": 573, "loss": 0.8119, "lr": 4.310344827586207e-06, "epoch": 0.13066202090592335, "percentage": 4.36, "elapsed_time": "0:06:21", "remaining_time": "2:19:15"} +{"current_steps": 26, "total_steps": 573, "loss": 0.8374, "lr": 4.482758620689656e-06, "epoch": 0.13588850174216027, "percentage": 4.54, "elapsed_time": "0:06:36", "remaining_time": "2:19:03"} +{"current_steps": 27, "total_steps": 573, "loss": 0.7917, "lr": 4.655172413793104e-06, "epoch": 0.14111498257839722, "percentage": 4.71, "elapsed_time": "0:06:53", "remaining_time": "2:19:28"} +{"current_steps": 28, "total_steps": 573, "loss": 0.8187, "lr": 4.8275862068965525e-06, "epoch": 0.14634146341463414, "percentage": 4.89, "elapsed_time": "0:07:08", "remaining_time": "2:19:05"} +{"current_steps": 29, "total_steps": 573, "loss": 0.8106, "lr": 5e-06, "epoch": 0.15156794425087108, "percentage": 5.06, "elapsed_time": "0:07:25", "remaining_time": "2:19:08"} +{"current_steps": 30, "total_steps": 573, "loss": 0.7807, "lr": 5.172413793103449e-06, "epoch": 0.156794425087108, "percentage": 5.24, "elapsed_time": "0:07:42", "remaining_time": "2:19:27"} +{"current_steps": 31, "total_steps": 573, "loss": 0.7987, "lr": 5.344827586206896e-06, "epoch": 0.16202090592334495, "percentage": 5.41, "elapsed_time": "0:07:57", "remaining_time": "2:19:13"} +{"current_steps": 32, "total_steps": 573, "loss": 0.7978, "lr": 5.517241379310345e-06, "epoch": 0.1672473867595819, "percentage": 5.58, "elapsed_time": "0:08:08", "remaining_time": "2:17:43"} +{"current_steps": 33, "total_steps": 573, "loss": 0.7872, "lr": 5.689655172413794e-06, "epoch": 0.17247386759581881, "percentage": 5.76, "elapsed_time": "0:08:23", "remaining_time": "2:17:16"} +{"current_steps": 34, "total_steps": 573, "loss": 0.7704, "lr": 5.862068965517242e-06, "epoch": 0.17770034843205576, "percentage": 5.93, "elapsed_time": "0:08:38", "remaining_time": "2:16:59"} +{"current_steps": 35, "total_steps": 573, "loss": 0.7581, "lr": 6.03448275862069e-06, "epoch": 0.18292682926829268, "percentage": 6.11, "elapsed_time": "0:08:51", "remaining_time": "2:16:05"} +{"current_steps": 36, "total_steps": 573, "loss": 0.7787, "lr": 6.206896551724138e-06, "epoch": 0.18815331010452963, "percentage": 6.28, "elapsed_time": "0:09:06", "remaining_time": "2:15:46"} +{"current_steps": 37, "total_steps": 573, "loss": 0.745, "lr": 6.379310344827587e-06, "epoch": 0.19337979094076654, "percentage": 6.46, "elapsed_time": "0:09:21", "remaining_time": "2:15:29"} +{"current_steps": 38, "total_steps": 573, "loss": 0.7604, "lr": 6.551724137931035e-06, "epoch": 0.1986062717770035, "percentage": 6.63, "elapsed_time": "0:09:36", "remaining_time": "2:15:11"} +{"current_steps": 39, "total_steps": 573, "loss": 0.7544, "lr": 6.724137931034484e-06, "epoch": 0.2038327526132404, "percentage": 6.81, "elapsed_time": "0:09:49", "remaining_time": "2:14:25"} +{"current_steps": 40, "total_steps": 573, "loss": 0.732, "lr": 6.896551724137932e-06, "epoch": 0.20905923344947736, "percentage": 6.98, "elapsed_time": "0:10:05", "remaining_time": "2:14:23"} +{"current_steps": 41, "total_steps": 573, "loss": 0.7297, "lr": 7.0689655172413796e-06, "epoch": 0.21428571428571427, "percentage": 7.16, "elapsed_time": "0:10:17", "remaining_time": "2:13:36"} +{"current_steps": 42, "total_steps": 573, "loss": 0.7383, "lr": 7.241379310344828e-06, "epoch": 0.21951219512195122, "percentage": 7.33, "elapsed_time": "0:10:31", "remaining_time": "2:12:59"} +{"current_steps": 43, "total_steps": 573, "loss": 0.7461, "lr": 7.413793103448277e-06, "epoch": 0.22473867595818817, "percentage": 7.5, "elapsed_time": "0:10:48", "remaining_time": "2:13:18"} +{"current_steps": 44, "total_steps": 573, "loss": 0.7343, "lr": 7.586206896551724e-06, "epoch": 0.22996515679442509, "percentage": 7.68, "elapsed_time": "0:11:04", "remaining_time": "2:13:06"} +{"current_steps": 45, "total_steps": 573, "loss": 0.7211, "lr": 7.758620689655173e-06, "epoch": 0.23519163763066203, "percentage": 7.85, "elapsed_time": "0:11:19", "remaining_time": "2:12:56"} +{"current_steps": 46, "total_steps": 573, "loss": 0.7307, "lr": 7.93103448275862e-06, "epoch": 0.24041811846689895, "percentage": 8.03, "elapsed_time": "0:11:36", "remaining_time": "2:12:54"} +{"current_steps": 47, "total_steps": 573, "loss": 0.7244, "lr": 8.103448275862069e-06, "epoch": 0.2456445993031359, "percentage": 8.2, "elapsed_time": "0:11:50", "remaining_time": "2:12:29"} +{"current_steps": 48, "total_steps": 573, "loss": 0.7222, "lr": 8.275862068965518e-06, "epoch": 0.2508710801393728, "percentage": 8.38, "elapsed_time": "0:12:04", "remaining_time": "2:12:07"} +{"current_steps": 49, "total_steps": 573, "loss": 0.7325, "lr": 8.448275862068966e-06, "epoch": 0.25609756097560976, "percentage": 8.55, "elapsed_time": "0:12:20", "remaining_time": "2:11:54"} +{"current_steps": 50, "total_steps": 573, "loss": 0.7166, "lr": 8.620689655172414e-06, "epoch": 0.2613240418118467, "percentage": 8.73, "elapsed_time": "0:12:35", "remaining_time": "2:11:43"} +{"current_steps": 51, "total_steps": 573, "loss": 0.7367, "lr": 8.793103448275862e-06, "epoch": 0.2665505226480836, "percentage": 8.9, "elapsed_time": "0:12:49", "remaining_time": "2:11:20"} +{"current_steps": 52, "total_steps": 573, "loss": 0.7104, "lr": 8.965517241379312e-06, "epoch": 0.27177700348432055, "percentage": 9.08, "elapsed_time": "0:13:02", "remaining_time": "2:10:44"} +{"current_steps": 53, "total_steps": 573, "loss": 0.7183, "lr": 9.13793103448276e-06, "epoch": 0.2770034843205575, "percentage": 9.25, "elapsed_time": "0:13:17", "remaining_time": "2:10:20"} +{"current_steps": 54, "total_steps": 573, "loss": 0.7153, "lr": 9.310344827586207e-06, "epoch": 0.28222996515679444, "percentage": 9.42, "elapsed_time": "0:13:31", "remaining_time": "2:10:02"} +{"current_steps": 55, "total_steps": 573, "loss": 0.7093, "lr": 9.482758620689655e-06, "epoch": 0.2874564459930314, "percentage": 9.6, "elapsed_time": "0:13:49", "remaining_time": "2:10:08"} +{"current_steps": 56, "total_steps": 573, "loss": 0.7176, "lr": 9.655172413793105e-06, "epoch": 0.2926829268292683, "percentage": 9.77, "elapsed_time": "0:14:03", "remaining_time": "2:09:50"} +{"current_steps": 57, "total_steps": 573, "loss": 0.7211, "lr": 9.827586206896553e-06, "epoch": 0.2979094076655052, "percentage": 9.95, "elapsed_time": "0:14:17", "remaining_time": "2:09:26"} +{"current_steps": 58, "total_steps": 573, "loss": 0.6993, "lr": 1e-05, "epoch": 0.30313588850174217, "percentage": 10.12, "elapsed_time": "0:14:30", "remaining_time": "2:08:46"} +{"current_steps": 59, "total_steps": 573, "loss": 0.6963, "lr": 9.999906969801156e-06, "epoch": 0.3083623693379791, "percentage": 10.3, "elapsed_time": "0:14:48", "remaining_time": "2:09:02"} +{"current_steps": 60, "total_steps": 573, "loss": 0.7151, "lr": 9.999627882666474e-06, "epoch": 0.313588850174216, "percentage": 10.47, "elapsed_time": "0:15:03", "remaining_time": "2:08:45"} +{"current_steps": 61, "total_steps": 573, "loss": 0.7049, "lr": 9.999162748981362e-06, "epoch": 0.31881533101045295, "percentage": 10.65, "elapsed_time": "0:15:19", "remaining_time": "2:08:39"} +{"current_steps": 62, "total_steps": 573, "loss": 0.7013, "lr": 9.998511586054415e-06, "epoch": 0.3240418118466899, "percentage": 10.82, "elapsed_time": "0:15:34", "remaining_time": "2:08:18"} +{"current_steps": 63, "total_steps": 573, "loss": 0.717, "lr": 9.997674418116759e-06, "epoch": 0.32926829268292684, "percentage": 10.99, "elapsed_time": "0:15:44", "remaining_time": "2:07:22"} +{"current_steps": 64, "total_steps": 573, "loss": 0.6952, "lr": 9.996651276321153e-06, "epoch": 0.3344947735191638, "percentage": 11.17, "elapsed_time": "0:16:02", "remaining_time": "2:07:32"} +{"current_steps": 65, "total_steps": 573, "loss": 0.701, "lr": 9.995442198740832e-06, "epoch": 0.3397212543554007, "percentage": 11.34, "elapsed_time": "0:16:16", "remaining_time": "2:07:11"} +{"current_steps": 66, "total_steps": 573, "loss": 0.7124, "lr": 9.994047230368087e-06, "epoch": 0.34494773519163763, "percentage": 11.52, "elapsed_time": "0:16:31", "remaining_time": "2:06:57"} +{"current_steps": 67, "total_steps": 573, "loss": 0.7041, "lr": 9.99246642311259e-06, "epoch": 0.3501742160278746, "percentage": 11.69, "elapsed_time": "0:16:46", "remaining_time": "2:06:43"} +{"current_steps": 68, "total_steps": 573, "loss": 0.6885, "lr": 9.99069983579947e-06, "epoch": 0.3554006968641115, "percentage": 11.87, "elapsed_time": "0:17:00", "remaining_time": "2:06:18"} +{"current_steps": 69, "total_steps": 573, "loss": 0.7179, "lr": 9.988747534167112e-06, "epoch": 0.3606271777003484, "percentage": 12.04, "elapsed_time": "0:17:16", "remaining_time": "2:06:09"} +{"current_steps": 70, "total_steps": 573, "loss": 0.6955, "lr": 9.98660959086472e-06, "epoch": 0.36585365853658536, "percentage": 12.22, "elapsed_time": "0:17:30", "remaining_time": "2:05:49"} +{"current_steps": 71, "total_steps": 573, "loss": 0.6903, "lr": 9.98428608544961e-06, "epoch": 0.3710801393728223, "percentage": 12.39, "elapsed_time": "0:17:44", "remaining_time": "2:05:28"} +{"current_steps": 72, "total_steps": 573, "loss": 0.7082, "lr": 9.981777104384251e-06, "epoch": 0.37630662020905925, "percentage": 12.57, "elapsed_time": "0:18:01", "remaining_time": "2:05:26"} +{"current_steps": 73, "total_steps": 573, "loss": 0.6768, "lr": 9.979082741033047e-06, "epoch": 0.38153310104529614, "percentage": 12.74, "elapsed_time": "0:18:18", "remaining_time": "2:05:25"} +{"current_steps": 74, "total_steps": 573, "loss": 0.6761, "lr": 9.976203095658859e-06, "epoch": 0.3867595818815331, "percentage": 12.91, "elapsed_time": "0:18:32", "remaining_time": "2:05:03"} +{"current_steps": 75, "total_steps": 573, "loss": 0.6934, "lr": 9.97313827541928e-06, "epoch": 0.39198606271777003, "percentage": 13.09, "elapsed_time": "0:18:48", "remaining_time": "2:04:55"} +{"current_steps": 76, "total_steps": 573, "loss": 0.7041, "lr": 9.969888394362648e-06, "epoch": 0.397212543554007, "percentage": 13.26, "elapsed_time": "0:19:02", "remaining_time": "2:04:33"} +{"current_steps": 77, "total_steps": 573, "loss": 0.6945, "lr": 9.96645357342379e-06, "epoch": 0.4024390243902439, "percentage": 13.44, "elapsed_time": "0:19:19", "remaining_time": "2:04:27"} +{"current_steps": 78, "total_steps": 573, "loss": 0.696, "lr": 9.96283394041954e-06, "epoch": 0.4076655052264808, "percentage": 13.61, "elapsed_time": "0:19:37", "remaining_time": "2:04:30"} +{"current_steps": 79, "total_steps": 573, "loss": 0.691, "lr": 9.959029630043969e-06, "epoch": 0.41289198606271776, "percentage": 13.79, "elapsed_time": "0:19:51", "remaining_time": "2:04:08"} +{"current_steps": 80, "total_steps": 573, "loss": 0.692, "lr": 9.955040783863373e-06, "epoch": 0.4181184668989547, "percentage": 13.96, "elapsed_time": "0:20:04", "remaining_time": "2:03:44"} +{"current_steps": 81, "total_steps": 573, "loss": 0.7196, "lr": 9.950867550311019e-06, "epoch": 0.42334494773519166, "percentage": 14.14, "elapsed_time": "0:20:19", "remaining_time": "2:03:25"} +{"current_steps": 82, "total_steps": 573, "loss": 0.6726, "lr": 9.946510084681602e-06, "epoch": 0.42857142857142855, "percentage": 14.31, "elapsed_time": "0:20:36", "remaining_time": "2:03:24"} +{"current_steps": 83, "total_steps": 573, "loss": 0.6897, "lr": 9.941968549125481e-06, "epoch": 0.4337979094076655, "percentage": 14.49, "elapsed_time": "0:20:52", "remaining_time": "2:03:12"} +{"current_steps": 84, "total_steps": 573, "loss": 0.6918, "lr": 9.937243112642639e-06, "epoch": 0.43902439024390244, "percentage": 14.66, "elapsed_time": "0:21:08", "remaining_time": "2:03:07"} +{"current_steps": 85, "total_steps": 573, "loss": 0.6766, "lr": 9.932333951076395e-06, "epoch": 0.4442508710801394, "percentage": 14.83, "elapsed_time": "0:21:24", "remaining_time": "2:02:56"} +{"current_steps": 86, "total_steps": 573, "loss": 0.695, "lr": 9.927241247106856e-06, "epoch": 0.44947735191637633, "percentage": 15.01, "elapsed_time": "0:21:37", "remaining_time": "2:02:26"} +{"current_steps": 87, "total_steps": 573, "loss": 0.6534, "lr": 9.921965190244129e-06, "epoch": 0.4547038327526132, "percentage": 15.18, "elapsed_time": "0:21:52", "remaining_time": "2:02:10"} +{"current_steps": 88, "total_steps": 573, "loss": 0.6964, "lr": 9.916505976821262e-06, "epoch": 0.45993031358885017, "percentage": 15.36, "elapsed_time": "0:22:07", "remaining_time": "2:01:54"} +{"current_steps": 89, "total_steps": 573, "loss": 0.6948, "lr": 9.910863809986942e-06, "epoch": 0.4651567944250871, "percentage": 15.53, "elapsed_time": "0:22:23", "remaining_time": "2:01:45"} +{"current_steps": 90, "total_steps": 573, "loss": 0.6748, "lr": 9.905038899697924e-06, "epoch": 0.47038327526132406, "percentage": 15.71, "elapsed_time": "0:22:37", "remaining_time": "2:01:27"} +{"current_steps": 91, "total_steps": 573, "loss": 0.698, "lr": 9.899031462711237e-06, "epoch": 0.47560975609756095, "percentage": 15.88, "elapsed_time": "0:22:51", "remaining_time": "2:01:05"} +{"current_steps": 92, "total_steps": 573, "loss": 0.6839, "lr": 9.892841722576103e-06, "epoch": 0.4808362369337979, "percentage": 16.06, "elapsed_time": "0:23:06", "remaining_time": "2:00:50"} +{"current_steps": 93, "total_steps": 573, "loss": 0.6865, "lr": 9.886469909625624e-06, "epoch": 0.48606271777003485, "percentage": 16.23, "elapsed_time": "0:23:22", "remaining_time": "2:00:39"} +{"current_steps": 94, "total_steps": 573, "loss": 0.6693, "lr": 9.879916260968212e-06, "epoch": 0.4912891986062718, "percentage": 16.4, "elapsed_time": "0:23:35", "remaining_time": "2:00:10"} +{"current_steps": 95, "total_steps": 573, "loss": 0.6812, "lr": 9.87318102047876e-06, "epoch": 0.4965156794425087, "percentage": 16.58, "elapsed_time": "0:23:49", "remaining_time": "1:59:51"} +{"current_steps": 96, "total_steps": 573, "loss": 0.686, "lr": 9.866264438789573e-06, "epoch": 0.5017421602787456, "percentage": 16.75, "elapsed_time": "0:24:01", "remaining_time": "1:59:20"} +{"current_steps": 97, "total_steps": 573, "loss": 0.7037, "lr": 9.85916677328104e-06, "epoch": 0.5069686411149826, "percentage": 16.93, "elapsed_time": "0:24:16", "remaining_time": "1:59:07"} +{"current_steps": 98, "total_steps": 573, "loss": 0.7037, "lr": 9.851888288072053e-06, "epoch": 0.5121951219512195, "percentage": 17.1, "elapsed_time": "0:24:31", "remaining_time": "1:58:52"} +{"current_steps": 99, "total_steps": 573, "loss": 0.6969, "lr": 9.844429254010184e-06, "epoch": 0.5174216027874564, "percentage": 17.28, "elapsed_time": "0:24:47", "remaining_time": "1:58:42"} +{"current_steps": 100, "total_steps": 573, "loss": 0.6879, "lr": 9.836789948661602e-06, "epoch": 0.5226480836236934, "percentage": 17.45, "elapsed_time": "0:25:02", "remaining_time": "1:58:27"} +{"current_steps": 101, "total_steps": 573, "loss": 0.6898, "lr": 9.828970656300743e-06, "epoch": 0.5278745644599303, "percentage": 17.63, "elapsed_time": "0:25:17", "remaining_time": "1:58:13"} +{"current_steps": 102, "total_steps": 573, "loss": 0.6778, "lr": 9.82097166789974e-06, "epoch": 0.5331010452961672, "percentage": 17.8, "elapsed_time": "0:25:34", "remaining_time": "1:58:04"} +{"current_steps": 103, "total_steps": 573, "loss": 0.6882, "lr": 9.81279328111758e-06, "epoch": 0.5383275261324042, "percentage": 17.98, "elapsed_time": "0:25:47", "remaining_time": "1:57:39"} +{"current_steps": 104, "total_steps": 573, "loss": 0.6893, "lr": 9.804435800289047e-06, "epoch": 0.5435540069686411, "percentage": 18.15, "elapsed_time": "0:26:02", "remaining_time": "1:57:27"} +{"current_steps": 105, "total_steps": 573, "loss": 0.663, "lr": 9.795899536413383e-06, "epoch": 0.5487804878048781, "percentage": 18.32, "elapsed_time": "0:26:18", "remaining_time": "1:57:13"} +{"current_steps": 106, "total_steps": 573, "loss": 0.6782, "lr": 9.787184807142713e-06, "epoch": 0.554006968641115, "percentage": 18.5, "elapsed_time": "0:26:35", "remaining_time": "1:57:08"} +{"current_steps": 107, "total_steps": 573, "loss": 0.6948, "lr": 9.778291936770241e-06, "epoch": 0.5592334494773519, "percentage": 18.67, "elapsed_time": "0:26:48", "remaining_time": "1:56:44"} +{"current_steps": 108, "total_steps": 573, "loss": 0.6855, "lr": 9.769221256218165e-06, "epoch": 0.5644599303135889, "percentage": 18.85, "elapsed_time": "0:27:04", "remaining_time": "1:56:33"} +{"current_steps": 109, "total_steps": 573, "loss": 0.6692, "lr": 9.759973103025369e-06, "epoch": 0.5696864111498258, "percentage": 19.02, "elapsed_time": "0:27:20", "remaining_time": "1:56:22"} +{"current_steps": 110, "total_steps": 573, "loss": 0.6881, "lr": 9.750547821334868e-06, "epoch": 0.5749128919860628, "percentage": 19.2, "elapsed_time": "0:27:36", "remaining_time": "1:56:11"} +{"current_steps": 111, "total_steps": 573, "loss": 0.6483, "lr": 9.740945761880993e-06, "epoch": 0.5801393728222997, "percentage": 19.37, "elapsed_time": "0:27:52", "remaining_time": "1:56:01"} +{"current_steps": 112, "total_steps": 573, "loss": 0.6573, "lr": 9.731167281976346e-06, "epoch": 0.5853658536585366, "percentage": 19.55, "elapsed_time": "0:28:10", "remaining_time": "1:55:59"} +{"current_steps": 113, "total_steps": 573, "loss": 0.6831, "lr": 9.721212745498493e-06, "epoch": 0.5905923344947736, "percentage": 19.72, "elapsed_time": "0:28:27", "remaining_time": "1:55:49"} +{"current_steps": 114, "total_steps": 573, "loss": 0.6883, "lr": 9.711082522876445e-06, "epoch": 0.5958188153310104, "percentage": 19.9, "elapsed_time": "0:28:42", "remaining_time": "1:55:36"} +{"current_steps": 115, "total_steps": 573, "loss": 0.6826, "lr": 9.700776991076846e-06, "epoch": 0.6010452961672473, "percentage": 20.07, "elapsed_time": "0:28:55", "remaining_time": "1:55:11"} +{"current_steps": 116, "total_steps": 573, "loss": 0.6669, "lr": 9.690296533589967e-06, "epoch": 0.6062717770034843, "percentage": 20.24, "elapsed_time": "0:29:07", "remaining_time": "1:54:45"} +{"current_steps": 117, "total_steps": 573, "loss": 0.6659, "lr": 9.679641540415428e-06, "epoch": 0.6114982578397212, "percentage": 20.42, "elapsed_time": "0:29:24", "remaining_time": "1:54:36"} +{"current_steps": 118, "total_steps": 573, "loss": 0.6597, "lr": 9.66881240804768e-06, "epoch": 0.6167247386759582, "percentage": 20.59, "elapsed_time": "0:29:39", "remaining_time": "1:54:20"} +{"current_steps": 119, "total_steps": 573, "loss": 0.6831, "lr": 9.657809539461256e-06, "epoch": 0.6219512195121951, "percentage": 20.77, "elapsed_time": "0:29:55", "remaining_time": "1:54:09"} +{"current_steps": 120, "total_steps": 573, "loss": 0.666, "lr": 9.64663334409578e-06, "epoch": 0.627177700348432, "percentage": 20.94, "elapsed_time": "0:30:05", "remaining_time": "1:53:36"} +{"current_steps": 121, "total_steps": 573, "loss": 0.6553, "lr": 9.635284237840721e-06, "epoch": 0.632404181184669, "percentage": 21.12, "elapsed_time": "0:30:18", "remaining_time": "1:53:14"} +{"current_steps": 122, "total_steps": 573, "loss": 0.6771, "lr": 9.623762643019927e-06, "epoch": 0.6376306620209059, "percentage": 21.29, "elapsed_time": "0:30:34", "remaining_time": "1:53:00"} +{"current_steps": 123, "total_steps": 573, "loss": 0.6715, "lr": 9.612068988375898e-06, "epoch": 0.6428571428571429, "percentage": 21.47, "elapsed_time": "0:30:47", "remaining_time": "1:52:40"} +{"current_steps": 124, "total_steps": 573, "loss": 0.6514, "lr": 9.60020370905384e-06, "epoch": 0.6480836236933798, "percentage": 21.64, "elapsed_time": "0:31:03", "remaining_time": "1:52:28"} +{"current_steps": 125, "total_steps": 573, "loss": 0.6459, "lr": 9.588167246585474e-06, "epoch": 0.6533101045296167, "percentage": 21.82, "elapsed_time": "0:31:19", "remaining_time": "1:52:14"} +{"current_steps": 126, "total_steps": 573, "loss": 0.6896, "lr": 9.575960048872595e-06, "epoch": 0.6585365853658537, "percentage": 21.99, "elapsed_time": "0:31:32", "remaining_time": "1:51:55"} +{"current_steps": 127, "total_steps": 573, "loss": 0.6613, "lr": 9.563582570170418e-06, "epoch": 0.6637630662020906, "percentage": 22.16, "elapsed_time": "0:31:48", "remaining_time": "1:51:41"} +{"current_steps": 128, "total_steps": 573, "loss": 0.6516, "lr": 9.551035271070665e-06, "epoch": 0.6689895470383276, "percentage": 22.34, "elapsed_time": "0:32:03", "remaining_time": "1:51:27"} +{"current_steps": 129, "total_steps": 573, "loss": 0.6618, "lr": 9.538318618484426e-06, "epoch": 0.6742160278745645, "percentage": 22.51, "elapsed_time": "0:32:17", "remaining_time": "1:51:09"} +{"current_steps": 130, "total_steps": 573, "loss": 0.6864, "lr": 9.52543308562479e-06, "epoch": 0.6794425087108014, "percentage": 22.69, "elapsed_time": "0:32:34", "remaining_time": "1:50:59"} +{"current_steps": 131, "total_steps": 573, "loss": 0.6784, "lr": 9.512379151989229e-06, "epoch": 0.6846689895470384, "percentage": 22.86, "elapsed_time": "0:32:51", "remaining_time": "1:50:50"} +{"current_steps": 132, "total_steps": 573, "loss": 0.6653, "lr": 9.499157303341761e-06, "epoch": 0.6898954703832753, "percentage": 23.04, "elapsed_time": "0:33:07", "remaining_time": "1:50:39"} +{"current_steps": 133, "total_steps": 573, "loss": 0.6731, "lr": 9.485768031694872e-06, "epoch": 0.6951219512195121, "percentage": 23.21, "elapsed_time": "0:33:21", "remaining_time": "1:50:23"} +{"current_steps": 134, "total_steps": 573, "loss": 0.6663, "lr": 9.4722118352912e-06, "epoch": 0.7003484320557491, "percentage": 23.39, "elapsed_time": "0:33:38", "remaining_time": "1:50:11"} +{"current_steps": 135, "total_steps": 573, "loss": 0.655, "lr": 9.458489218585003e-06, "epoch": 0.705574912891986, "percentage": 23.56, "elapsed_time": "0:33:54", "remaining_time": "1:50:00"} +{"current_steps": 136, "total_steps": 573, "loss": 0.6749, "lr": 9.44460069222339e-06, "epoch": 0.710801393728223, "percentage": 23.73, "elapsed_time": "0:34:08", "remaining_time": "1:49:42"} +{"current_steps": 137, "total_steps": 573, "loss": 0.6686, "lr": 9.430546773027302e-06, "epoch": 0.7160278745644599, "percentage": 23.91, "elapsed_time": "0:34:24", "remaining_time": "1:49:28"} +{"current_steps": 138, "total_steps": 573, "loss": 0.6594, "lr": 9.416327983972304e-06, "epoch": 0.7212543554006968, "percentage": 24.08, "elapsed_time": "0:34:37", "remaining_time": "1:49:08"} +{"current_steps": 139, "total_steps": 573, "loss": 0.6749, "lr": 9.401944854169103e-06, "epoch": 0.7264808362369338, "percentage": 24.26, "elapsed_time": "0:34:50", "remaining_time": "1:48:47"} +{"current_steps": 140, "total_steps": 573, "loss": 0.6579, "lr": 9.38739791884387e-06, "epoch": 0.7317073170731707, "percentage": 24.43, "elapsed_time": "0:35:01", "remaining_time": "1:48:20"} +{"current_steps": 141, "total_steps": 573, "loss": 0.681, "lr": 9.372687719318316e-06, "epoch": 0.7369337979094077, "percentage": 24.61, "elapsed_time": "0:35:13", "remaining_time": "1:47:55"} +{"current_steps": 142, "total_steps": 573, "loss": 0.6666, "lr": 9.35781480298956e-06, "epoch": 0.7421602787456446, "percentage": 24.78, "elapsed_time": "0:35:25", "remaining_time": "1:47:32"} +{"current_steps": 143, "total_steps": 573, "loss": 0.6238, "lr": 9.342779723309746e-06, "epoch": 0.7473867595818815, "percentage": 24.96, "elapsed_time": "0:35:42", "remaining_time": "1:47:22"} +{"current_steps": 144, "total_steps": 573, "loss": 0.6637, "lr": 9.327583039765453e-06, "epoch": 0.7526132404181185, "percentage": 25.13, "elapsed_time": "0:35:57", "remaining_time": "1:47:06"} +{"current_steps": 145, "total_steps": 573, "loss": 0.6523, "lr": 9.31222531785688e-06, "epoch": 0.7578397212543554, "percentage": 25.31, "elapsed_time": "0:36:12", "remaining_time": "1:46:52"} +{"current_steps": 146, "total_steps": 573, "loss": 0.6626, "lr": 9.296707129076794e-06, "epoch": 0.7630662020905923, "percentage": 25.48, "elapsed_time": "0:36:25", "remaining_time": "1:46:33"} +{"current_steps": 147, "total_steps": 573, "loss": 0.6786, "lr": 9.281029050889274e-06, "epoch": 0.7682926829268293, "percentage": 25.65, "elapsed_time": "0:36:40", "remaining_time": "1:46:17"} +{"current_steps": 148, "total_steps": 573, "loss": 0.6861, "lr": 9.26519166670821e-06, "epoch": 0.7735191637630662, "percentage": 25.83, "elapsed_time": "0:36:58", "remaining_time": "1:46:10"} +{"current_steps": 149, "total_steps": 573, "loss": 0.6591, "lr": 9.2491955658756e-06, "epoch": 0.7787456445993032, "percentage": 26.0, "elapsed_time": "0:37:13", "remaining_time": "1:45:55"} +{"current_steps": 150, "total_steps": 573, "loss": 0.6881, "lr": 9.233041343639623e-06, "epoch": 0.7839721254355401, "percentage": 26.18, "elapsed_time": "0:37:26", "remaining_time": "1:45:35"} +{"current_steps": 151, "total_steps": 573, "loss": 0.6702, "lr": 9.216729601132481e-06, "epoch": 0.789198606271777, "percentage": 26.35, "elapsed_time": "0:37:43", "remaining_time": "1:45:24"} +{"current_steps": 152, "total_steps": 573, "loss": 0.6652, "lr": 9.200260945348034e-06, "epoch": 0.794425087108014, "percentage": 26.53, "elapsed_time": "0:37:56", "remaining_time": "1:45:04"} +{"current_steps": 153, "total_steps": 573, "loss": 0.6569, "lr": 9.183635989119211e-06, "epoch": 0.7996515679442509, "percentage": 26.7, "elapsed_time": "0:38:13", "remaining_time": "1:44:54"} +{"current_steps": 154, "total_steps": 573, "loss": 0.6629, "lr": 9.166855351095205e-06, "epoch": 0.8048780487804879, "percentage": 26.88, "elapsed_time": "0:38:25", "remaining_time": "1:44:32"} +{"current_steps": 155, "total_steps": 573, "loss": 0.6615, "lr": 9.149919655718453e-06, "epoch": 0.8101045296167247, "percentage": 27.05, "elapsed_time": "0:38:37", "remaining_time": "1:44:10"} +{"current_steps": 156, "total_steps": 573, "loss": 0.6321, "lr": 9.132829533201397e-06, "epoch": 0.8153310104529616, "percentage": 27.23, "elapsed_time": "0:38:50", "remaining_time": "1:43:50"} +{"current_steps": 157, "total_steps": 573, "loss": 0.6471, "lr": 9.115585619503039e-06, "epoch": 0.8205574912891986, "percentage": 27.4, "elapsed_time": "0:39:02", "remaining_time": "1:43:27"} +{"current_steps": 158, "total_steps": 573, "loss": 0.6748, "lr": 9.098188556305262e-06, "epoch": 0.8257839721254355, "percentage": 27.57, "elapsed_time": "0:39:16", "remaining_time": "1:43:09"} +{"current_steps": 159, "total_steps": 573, "loss": 0.6564, "lr": 9.080638990988971e-06, "epoch": 0.8310104529616724, "percentage": 27.75, "elapsed_time": "0:39:26", "remaining_time": "1:42:43"} +{"current_steps": 160, "total_steps": 573, "loss": 0.654, "lr": 9.062937576609983e-06, "epoch": 0.8362369337979094, "percentage": 27.92, "elapsed_time": "0:39:38", "remaining_time": "1:42:20"} +{"current_steps": 161, "total_steps": 573, "loss": 0.6558, "lr": 9.045084971874738e-06, "epoch": 0.8414634146341463, "percentage": 28.1, "elapsed_time": "0:39:54", "remaining_time": "1:42:08"} +{"current_steps": 162, "total_steps": 573, "loss": 0.6663, "lr": 9.027081841115784e-06, "epoch": 0.8466898954703833, "percentage": 28.27, "elapsed_time": "0:40:12", "remaining_time": "1:41:59"} +{"current_steps": 163, "total_steps": 573, "loss": 0.6443, "lr": 9.008928854267054e-06, "epoch": 0.8519163763066202, "percentage": 28.45, "elapsed_time": "0:40:26", "remaining_time": "1:41:43"} +{"current_steps": 164, "total_steps": 573, "loss": 0.6536, "lr": 8.99062668683894e-06, "epoch": 0.8571428571428571, "percentage": 28.62, "elapsed_time": "0:40:40", "remaining_time": "1:41:27"} +{"current_steps": 165, "total_steps": 573, "loss": 0.6579, "lr": 8.97217601989315e-06, "epoch": 0.8623693379790941, "percentage": 28.8, "elapsed_time": "0:40:57", "remaining_time": "1:41:17"} +{"current_steps": 166, "total_steps": 573, "loss": 0.6713, "lr": 8.95357754001737e-06, "epoch": 0.867595818815331, "percentage": 28.97, "elapsed_time": "0:41:13", "remaining_time": "1:41:04"} +{"current_steps": 167, "total_steps": 573, "loss": 0.6696, "lr": 8.934831939299715e-06, "epoch": 0.872822299651568, "percentage": 29.14, "elapsed_time": "0:41:28", "remaining_time": "1:40:50"} +{"current_steps": 168, "total_steps": 573, "loss": 0.6584, "lr": 8.91593991530297e-06, "epoch": 0.8780487804878049, "percentage": 29.32, "elapsed_time": "0:41:47", "remaining_time": "1:40:44"} +{"current_steps": 169, "total_steps": 573, "loss": 0.6529, "lr": 8.896902171038629e-06, "epoch": 0.8832752613240418, "percentage": 29.49, "elapsed_time": "0:42:03", "remaining_time": "1:40:32"} +{"current_steps": 170, "total_steps": 573, "loss": 0.6816, "lr": 8.877719414940751e-06, "epoch": 0.8885017421602788, "percentage": 29.67, "elapsed_time": "0:42:13", "remaining_time": "1:40:06"} +{"current_steps": 171, "total_steps": 573, "loss": 0.6591, "lr": 8.85839236083958e-06, "epoch": 0.8937282229965157, "percentage": 29.84, "elapsed_time": "0:42:28", "remaining_time": "1:39:50"} +{"current_steps": 172, "total_steps": 573, "loss": 0.6725, "lr": 8.838921727934992e-06, "epoch": 0.8989547038327527, "percentage": 30.02, "elapsed_time": "0:42:39", "remaining_time": "1:39:26"} +{"current_steps": 173, "total_steps": 573, "loss": 0.663, "lr": 8.819308240769726e-06, "epoch": 0.9041811846689896, "percentage": 30.19, "elapsed_time": "0:42:56", "remaining_time": "1:39:16"} +{"current_steps": 174, "total_steps": 573, "loss": 0.6593, "lr": 8.799552629202424e-06, "epoch": 0.9094076655052264, "percentage": 30.37, "elapsed_time": "0:43:11", "remaining_time": "1:39:02"} +{"current_steps": 175, "total_steps": 573, "loss": 0.6366, "lr": 8.779655628380479e-06, "epoch": 0.9146341463414634, "percentage": 30.54, "elapsed_time": "0:43:27", "remaining_time": "1:38:49"} +{"current_steps": 176, "total_steps": 573, "loss": 0.6588, "lr": 8.759617978712667e-06, "epoch": 0.9198606271777003, "percentage": 30.72, "elapsed_time": "0:43:43", "remaining_time": "1:38:37"} +{"current_steps": 177, "total_steps": 573, "loss": 0.6708, "lr": 8.7394404258416e-06, "epoch": 0.9250871080139372, "percentage": 30.89, "elapsed_time": "0:43:56", "remaining_time": "1:38:19"} +{"current_steps": 178, "total_steps": 573, "loss": 0.6581, "lr": 8.71912372061598e-06, "epoch": 0.9303135888501742, "percentage": 31.06, "elapsed_time": "0:44:12", "remaining_time": "1:38:05"} +{"current_steps": 179, "total_steps": 573, "loss": 0.675, "lr": 8.69866861906266e-06, "epoch": 0.9355400696864111, "percentage": 31.24, "elapsed_time": "0:44:29", "remaining_time": "1:37:55"} +{"current_steps": 180, "total_steps": 573, "loss": 0.6315, "lr": 8.678075882358506e-06, "epoch": 0.9407665505226481, "percentage": 31.41, "elapsed_time": "0:44:44", "remaining_time": "1:37:40"} +{"current_steps": 181, "total_steps": 573, "loss": 0.6407, "lr": 8.657346276802071e-06, "epoch": 0.945993031358885, "percentage": 31.59, "elapsed_time": "0:44:58", "remaining_time": "1:37:23"} +{"current_steps": 182, "total_steps": 573, "loss": 0.6665, "lr": 8.636480573785089e-06, "epoch": 0.9512195121951219, "percentage": 31.76, "elapsed_time": "0:45:08", "remaining_time": "1:36:59"} +{"current_steps": 183, "total_steps": 573, "loss": 0.6618, "lr": 8.615479549763756e-06, "epoch": 0.9564459930313589, "percentage": 31.94, "elapsed_time": "0:45:22", "remaining_time": "1:36:42"} +{"current_steps": 184, "total_steps": 573, "loss": 0.6773, "lr": 8.594343986229854e-06, "epoch": 0.9616724738675958, "percentage": 32.11, "elapsed_time": "0:45:37", "remaining_time": "1:36:28"} +{"current_steps": 185, "total_steps": 573, "loss": 0.6429, "lr": 8.57307466968165e-06, "epoch": 0.9668989547038328, "percentage": 32.29, "elapsed_time": "0:45:52", "remaining_time": "1:36:13"} +{"current_steps": 186, "total_steps": 573, "loss": 0.6735, "lr": 8.551672391594646e-06, "epoch": 0.9721254355400697, "percentage": 32.46, "elapsed_time": "0:46:09", "remaining_time": "1:36:01"} +{"current_steps": 187, "total_steps": 573, "loss": 0.6614, "lr": 8.530137948392113e-06, "epoch": 0.9773519163763066, "percentage": 32.64, "elapsed_time": "0:46:27", "remaining_time": "1:35:53"} +{"current_steps": 188, "total_steps": 573, "loss": 0.6539, "lr": 8.508472141415468e-06, "epoch": 0.9825783972125436, "percentage": 32.81, "elapsed_time": "0:46:43", "remaining_time": "1:35:40"} +{"current_steps": 189, "total_steps": 573, "loss": 0.6346, "lr": 8.48667577689444e-06, "epoch": 0.9878048780487805, "percentage": 32.98, "elapsed_time": "0:46:57", "remaining_time": "1:35:25"} +{"current_steps": 190, "total_steps": 573, "loss": 0.6626, "lr": 8.46474966591708e-06, "epoch": 0.9930313588850174, "percentage": 33.16, "elapsed_time": "0:47:12", "remaining_time": "1:35:09"} +{"current_steps": 191, "total_steps": 573, "loss": 0.6604, "lr": 8.442694624399576e-06, "epoch": 0.9982578397212544, "percentage": 33.33, "elapsed_time": "0:47:27", "remaining_time": "1:34:54"} +{"current_steps": 192, "total_steps": 573, "loss": 1.0489, "lr": 8.420511473055887e-06, "epoch": 1.0034843205574913, "percentage": 33.51, "elapsed_time": "0:49:31", "remaining_time": "1:38:16"} +{"current_steps": 193, "total_steps": 573, "loss": 0.6419, "lr": 8.398201037367202e-06, "epoch": 1.0087108013937283, "percentage": 33.68, "elapsed_time": "0:49:46", "remaining_time": "1:38:00"} +{"current_steps": 194, "total_steps": 573, "loss": 0.6137, "lr": 8.37576414755123e-06, "epoch": 1.0139372822299653, "percentage": 33.86, "elapsed_time": "0:50:02", "remaining_time": "1:37:45"} +{"current_steps": 195, "total_steps": 573, "loss": 0.6243, "lr": 8.3532016385313e-06, "epoch": 1.019163763066202, "percentage": 34.03, "elapsed_time": "0:50:19", "remaining_time": "1:37:34"} +{"current_steps": 196, "total_steps": 573, "loss": 0.6368, "lr": 8.330514349905295e-06, "epoch": 1.024390243902439, "percentage": 34.21, "elapsed_time": "0:50:35", "remaining_time": "1:37:18"} +{"current_steps": 197, "total_steps": 573, "loss": 0.5435, "lr": 8.307703125914397e-06, "epoch": 1.029616724738676, "percentage": 34.38, "elapsed_time": "0:50:49", "remaining_time": "1:37:00"} +{"current_steps": 198, "total_steps": 573, "loss": 0.6031, "lr": 8.284768815411693e-06, "epoch": 1.0348432055749128, "percentage": 34.55, "elapsed_time": "0:51:06", "remaining_time": "1:36:47"} +{"current_steps": 199, "total_steps": 573, "loss": 0.5943, "lr": 8.261712271830564e-06, "epoch": 1.0400696864111498, "percentage": 34.73, "elapsed_time": "0:51:19", "remaining_time": "1:36:27"} +{"current_steps": 200, "total_steps": 573, "loss": 0.5491, "lr": 8.23853435315295e-06, "epoch": 1.0452961672473868, "percentage": 34.9, "elapsed_time": "0:51:32", "remaining_time": "1:36:07"} +{"current_steps": 201, "total_steps": 573, "loss": 0.5604, "lr": 8.215235921877403e-06, "epoch": 1.0505226480836236, "percentage": 35.08, "elapsed_time": "0:51:49", "remaining_time": "1:35:54"} +{"current_steps": 202, "total_steps": 573, "loss": 0.6434, "lr": 8.191817844986998e-06, "epoch": 1.0557491289198606, "percentage": 35.25, "elapsed_time": "0:52:01", "remaining_time": "1:35:33"} +{"current_steps": 203, "total_steps": 573, "loss": 0.5594, "lr": 8.168280993917078e-06, "epoch": 1.0609756097560976, "percentage": 35.43, "elapsed_time": "0:52:17", "remaining_time": "1:35:18"} +{"current_steps": 204, "total_steps": 573, "loss": 0.5686, "lr": 8.144626244522812e-06, "epoch": 1.0662020905923344, "percentage": 35.6, "elapsed_time": "0:52:31", "remaining_time": "1:34:59"} +{"current_steps": 205, "total_steps": 573, "loss": 0.6803, "lr": 8.120854477046621e-06, "epoch": 1.0714285714285714, "percentage": 35.78, "elapsed_time": "0:52:46", "remaining_time": "1:34:43"} +{"current_steps": 206, "total_steps": 573, "loss": 0.5824, "lr": 8.096966576085406e-06, "epoch": 1.0766550522648084, "percentage": 35.95, "elapsed_time": "0:52:59", "remaining_time": "1:34:24"} +{"current_steps": 207, "total_steps": 573, "loss": 0.6028, "lr": 8.072963430557636e-06, "epoch": 1.0818815331010452, "percentage": 36.13, "elapsed_time": "0:53:14", "remaining_time": "1:34:07"} +{"current_steps": 208, "total_steps": 573, "loss": 0.5777, "lr": 8.048845933670274e-06, "epoch": 1.0871080139372822, "percentage": 36.3, "elapsed_time": "0:53:29", "remaining_time": "1:33:52"} +{"current_steps": 209, "total_steps": 573, "loss": 0.5577, "lr": 8.024614982885527e-06, "epoch": 1.0923344947735192, "percentage": 36.47, "elapsed_time": "0:53:45", "remaining_time": "1:33:37"} +{"current_steps": 210, "total_steps": 573, "loss": 0.6143, "lr": 8.00027147988747e-06, "epoch": 1.0975609756097562, "percentage": 36.65, "elapsed_time": "0:53:59", "remaining_time": "1:33:19"} +{"current_steps": 211, "total_steps": 573, "loss": 0.596, "lr": 7.975816330548466e-06, "epoch": 1.102787456445993, "percentage": 36.82, "elapsed_time": "0:54:12", "remaining_time": "1:32:59"} +{"current_steps": 212, "total_steps": 573, "loss": 0.6494, "lr": 7.951250444895485e-06, "epoch": 1.10801393728223, "percentage": 37.0, "elapsed_time": "0:54:27", "remaining_time": "1:32:43"} +{"current_steps": 213, "total_steps": 573, "loss": 0.5217, "lr": 7.92657473707621e-06, "epoch": 1.113240418118467, "percentage": 37.17, "elapsed_time": "0:54:44", "remaining_time": "1:32:31"} +{"current_steps": 214, "total_steps": 573, "loss": 0.6941, "lr": 7.901790125325049e-06, "epoch": 1.1184668989547037, "percentage": 37.35, "elapsed_time": "0:55:01", "remaining_time": "1:32:19"} +{"current_steps": 215, "total_steps": 573, "loss": 0.6076, "lr": 7.876897531928943e-06, "epoch": 1.1236933797909407, "percentage": 37.52, "elapsed_time": "0:55:15", "remaining_time": "1:32:00"} +{"current_steps": 216, "total_steps": 573, "loss": 0.5852, "lr": 7.851897883193057e-06, "epoch": 1.1289198606271778, "percentage": 37.7, "elapsed_time": "0:55:30", "remaining_time": "1:31:44"} +{"current_steps": 217, "total_steps": 573, "loss": 0.6033, "lr": 7.82679210940631e-06, "epoch": 1.1341463414634148, "percentage": 37.87, "elapsed_time": "0:55:44", "remaining_time": "1:31:27"} +{"current_steps": 218, "total_steps": 573, "loss": 0.5587, "lr": 7.801581144806752e-06, "epoch": 1.1393728222996515, "percentage": 38.05, "elapsed_time": "0:55:59", "remaining_time": "1:31:10"} +{"current_steps": 219, "total_steps": 573, "loss": 0.618, "lr": 7.7762659275468e-06, "epoch": 1.1445993031358885, "percentage": 38.22, "elapsed_time": "0:56:17", "remaining_time": "1:30:58"} +{"current_steps": 220, "total_steps": 573, "loss": 0.6282, "lr": 7.750847399658336e-06, "epoch": 1.1498257839721253, "percentage": 38.39, "elapsed_time": "0:56:31", "remaining_time": "1:30:41"} +{"current_steps": 221, "total_steps": 573, "loss": 0.5451, "lr": 7.725326507017644e-06, "epoch": 1.1550522648083623, "percentage": 38.57, "elapsed_time": "0:56:44", "remaining_time": "1:30:22"} +{"current_steps": 222, "total_steps": 573, "loss": 0.5972, "lr": 7.699704199310204e-06, "epoch": 1.1602787456445993, "percentage": 38.74, "elapsed_time": "0:57:00", "remaining_time": "1:30:07"} +{"current_steps": 223, "total_steps": 573, "loss": 0.6114, "lr": 7.673981429995372e-06, "epoch": 1.1655052264808363, "percentage": 38.92, "elapsed_time": "0:57:11", "remaining_time": "1:29:46"} +{"current_steps": 224, "total_steps": 573, "loss": 0.6268, "lr": 7.648159156270884e-06, "epoch": 1.170731707317073, "percentage": 39.09, "elapsed_time": "0:57:28", "remaining_time": "1:29:33"} +{"current_steps": 225, "total_steps": 573, "loss": 0.6141, "lr": 7.622238339037248e-06, "epoch": 1.17595818815331, "percentage": 39.27, "elapsed_time": "0:57:43", "remaining_time": "1:29:17"} +{"current_steps": 226, "total_steps": 573, "loss": 0.5655, "lr": 7.596219942861971e-06, "epoch": 1.181184668989547, "percentage": 39.44, "elapsed_time": "0:57:55", "remaining_time": "1:28:55"} +{"current_steps": 227, "total_steps": 573, "loss": 0.5983, "lr": 7.570104935943685e-06, "epoch": 1.1864111498257839, "percentage": 39.62, "elapsed_time": "0:58:07", "remaining_time": "1:28:35"} +{"current_steps": 228, "total_steps": 573, "loss": 0.6072, "lr": 7.5438942900761035e-06, "epoch": 1.1916376306620209, "percentage": 39.79, "elapsed_time": "0:58:22", "remaining_time": "1:28:20"} +{"current_steps": 229, "total_steps": 573, "loss": 0.6306, "lr": 7.517588980611864e-06, "epoch": 1.1968641114982579, "percentage": 39.97, "elapsed_time": "0:58:36", "remaining_time": "1:28:02"} +{"current_steps": 230, "total_steps": 573, "loss": 0.523, "lr": 7.491189986426236e-06, "epoch": 1.202090592334495, "percentage": 40.14, "elapsed_time": "0:58:51", "remaining_time": "1:27:47"} +{"current_steps": 231, "total_steps": 573, "loss": 0.6248, "lr": 7.464698289880689e-06, "epoch": 1.2073170731707317, "percentage": 40.31, "elapsed_time": "0:59:04", "remaining_time": "1:27:28"} +{"current_steps": 232, "total_steps": 573, "loss": 0.5892, "lr": 7.438114876786344e-06, "epoch": 1.2125435540069687, "percentage": 40.49, "elapsed_time": "0:59:20", "remaining_time": "1:27:12"} +{"current_steps": 233, "total_steps": 573, "loss": 0.604, "lr": 7.411440736367281e-06, "epoch": 1.2177700348432055, "percentage": 40.66, "elapsed_time": "0:59:37", "remaining_time": "1:27:00"} +{"current_steps": 234, "total_steps": 573, "loss": 0.5938, "lr": 7.384676861223738e-06, "epoch": 1.2229965156794425, "percentage": 40.84, "elapsed_time": "0:59:50", "remaining_time": "1:26:41"} +{"current_steps": 235, "total_steps": 573, "loss": 0.5606, "lr": 7.3578242472951635e-06, "epoch": 1.2282229965156795, "percentage": 41.01, "elapsed_time": "1:00:06", "remaining_time": "1:26:26"} +{"current_steps": 236, "total_steps": 573, "loss": 0.6321, "lr": 7.330883893823164e-06, "epoch": 1.2334494773519165, "percentage": 41.19, "elapsed_time": "1:00:21", "remaining_time": "1:26:11"} +{"current_steps": 237, "total_steps": 573, "loss": 0.5772, "lr": 7.303856803314313e-06, "epoch": 1.2386759581881532, "percentage": 41.36, "elapsed_time": "1:00:36", "remaining_time": "1:25:55"} +{"current_steps": 238, "total_steps": 573, "loss": 0.6249, "lr": 7.276743981502856e-06, "epoch": 1.2439024390243902, "percentage": 41.54, "elapsed_time": "1:00:50", "remaining_time": "1:25:38"} +{"current_steps": 239, "total_steps": 573, "loss": 0.5742, "lr": 7.249546437313273e-06, "epoch": 1.2491289198606272, "percentage": 41.71, "elapsed_time": "1:01:04", "remaining_time": "1:25:21"} +{"current_steps": 240, "total_steps": 573, "loss": 0.5931, "lr": 7.22226518282274e-06, "epoch": 1.254355400696864, "percentage": 41.88, "elapsed_time": "1:01:21", "remaining_time": "1:25:07"} +{"current_steps": 241, "total_steps": 573, "loss": 0.6026, "lr": 7.194901233223471e-06, "epoch": 1.259581881533101, "percentage": 42.06, "elapsed_time": "1:01:37", "remaining_time": "1:24:52"} +{"current_steps": 242, "total_steps": 573, "loss": 0.5973, "lr": 7.167455606784936e-06, "epoch": 1.264808362369338, "percentage": 42.23, "elapsed_time": "1:01:47", "remaining_time": "1:24:31"} +{"current_steps": 243, "total_steps": 573, "loss": 0.639, "lr": 7.139929324815965e-06, "epoch": 1.270034843205575, "percentage": 42.41, "elapsed_time": "1:02:04", "remaining_time": "1:24:18"} +{"current_steps": 244, "total_steps": 573, "loss": 0.5975, "lr": 7.112323411626756e-06, "epoch": 1.2752613240418118, "percentage": 42.58, "elapsed_time": "1:02:19", "remaining_time": "1:24:02"} +{"current_steps": 245, "total_steps": 573, "loss": 0.5932, "lr": 7.084638894490744e-06, "epoch": 1.2804878048780488, "percentage": 42.76, "elapsed_time": "1:02:34", "remaining_time": "1:23:46"} +{"current_steps": 246, "total_steps": 573, "loss": 0.6211, "lr": 7.056876803606384e-06, "epoch": 1.2857142857142856, "percentage": 42.93, "elapsed_time": "1:02:47", "remaining_time": "1:23:28"} +{"current_steps": 247, "total_steps": 573, "loss": 0.5816, "lr": 7.029038172058809e-06, "epoch": 1.2909407665505226, "percentage": 43.11, "elapsed_time": "1:03:05", "remaining_time": "1:23:16"} +{"current_steps": 248, "total_steps": 573, "loss": 0.5793, "lr": 7.00112403578139e-06, "epoch": 1.2961672473867596, "percentage": 43.28, "elapsed_time": "1:03:24", "remaining_time": "1:23:05"} +{"current_steps": 249, "total_steps": 573, "loss": 0.5969, "lr": 6.9731354335171885e-06, "epoch": 1.3013937282229966, "percentage": 43.46, "elapsed_time": "1:03:38", "remaining_time": "1:22:48"} +{"current_steps": 250, "total_steps": 573, "loss": 0.6263, "lr": 6.945073406780296e-06, "epoch": 1.3066202090592334, "percentage": 43.63, "elapsed_time": "1:03:50", "remaining_time": "1:22:28"} +{"current_steps": 251, "total_steps": 573, "loss": 0.6258, "lr": 6.916938999817085e-06, "epoch": 1.3118466898954704, "percentage": 43.8, "elapsed_time": "1:04:05", "remaining_time": "1:22:13"} +{"current_steps": 252, "total_steps": 573, "loss": 0.5697, "lr": 6.888733259567343e-06, "epoch": 1.3170731707317074, "percentage": 43.98, "elapsed_time": "1:04:19", "remaining_time": "1:21:56"} +{"current_steps": 253, "total_steps": 573, "loss": 0.6192, "lr": 6.860457235625322e-06, "epoch": 1.3222996515679442, "percentage": 44.15, "elapsed_time": "1:04:35", "remaining_time": "1:21:41"} +{"current_steps": 254, "total_steps": 573, "loss": 0.5595, "lr": 6.832111980200672e-06, "epoch": 1.3275261324041812, "percentage": 44.33, "elapsed_time": "1:04:53", "remaining_time": "1:21:29"} +{"current_steps": 255, "total_steps": 573, "loss": 0.6001, "lr": 6.803698548079294e-06, "epoch": 1.3327526132404182, "percentage": 44.5, "elapsed_time": "1:05:08", "remaining_time": "1:21:14"} +{"current_steps": 256, "total_steps": 573, "loss": 0.5915, "lr": 6.775217996584082e-06, "epoch": 1.3379790940766552, "percentage": 44.68, "elapsed_time": "1:05:23", "remaining_time": "1:20:58"} +{"current_steps": 257, "total_steps": 573, "loss": 0.5953, "lr": 6.746671385535586e-06, "epoch": 1.343205574912892, "percentage": 44.85, "elapsed_time": "1:05:41", "remaining_time": "1:20:46"} +{"current_steps": 258, "total_steps": 573, "loss": 0.6388, "lr": 6.7180597772125665e-06, "epoch": 1.348432055749129, "percentage": 45.03, "elapsed_time": "1:05:57", "remaining_time": "1:20:31"} +{"current_steps": 259, "total_steps": 573, "loss": 0.5838, "lr": 6.689384236312465e-06, "epoch": 1.3536585365853657, "percentage": 45.2, "elapsed_time": "1:06:12", "remaining_time": "1:20:16"} +{"current_steps": 260, "total_steps": 573, "loss": 0.6318, "lr": 6.660645829911794e-06, "epoch": 1.3588850174216027, "percentage": 45.38, "elapsed_time": "1:06:30", "remaining_time": "1:20:03"} +{"current_steps": 261, "total_steps": 573, "loss": 0.5425, "lr": 6.631845627426418e-06, "epoch": 1.3641114982578397, "percentage": 45.55, "elapsed_time": "1:06:46", "remaining_time": "1:19:49"} +{"current_steps": 262, "total_steps": 573, "loss": 0.5305, "lr": 6.602984700571758e-06, "epoch": 1.3693379790940767, "percentage": 45.72, "elapsed_time": "1:07:01", "remaining_time": "1:19:33"} +{"current_steps": 263, "total_steps": 573, "loss": 0.6405, "lr": 6.574064123322925e-06, "epoch": 1.3745644599303135, "percentage": 45.9, "elapsed_time": "1:07:18", "remaining_time": "1:19:20"} +{"current_steps": 264, "total_steps": 573, "loss": 0.5802, "lr": 6.545084971874738e-06, "epoch": 1.3797909407665505, "percentage": 46.07, "elapsed_time": "1:07:36", "remaining_time": "1:19:07"} +{"current_steps": 265, "total_steps": 573, "loss": 0.6166, "lr": 6.516048324601685e-06, "epoch": 1.3850174216027875, "percentage": 46.25, "elapsed_time": "1:07:52", "remaining_time": "1:18:53"} +{"current_steps": 266, "total_steps": 573, "loss": 0.6049, "lr": 6.486955262017794e-06, "epoch": 1.3902439024390243, "percentage": 46.42, "elapsed_time": "1:08:07", "remaining_time": "1:18:37"} +{"current_steps": 267, "total_steps": 573, "loss": 0.615, "lr": 6.457806866736424e-06, "epoch": 1.3954703832752613, "percentage": 46.6, "elapsed_time": "1:08:21", "remaining_time": "1:18:20"} +{"current_steps": 268, "total_steps": 573, "loss": 0.522, "lr": 6.42860422342998e-06, "epoch": 1.4006968641114983, "percentage": 46.77, "elapsed_time": "1:08:30", "remaining_time": "1:17:58"} +{"current_steps": 269, "total_steps": 573, "loss": 0.6314, "lr": 6.399348418789545e-06, "epoch": 1.4059233449477353, "percentage": 46.95, "elapsed_time": "1:08:47", "remaining_time": "1:17:44"} +{"current_steps": 270, "total_steps": 573, "loss": 0.5822, "lr": 6.37004054148445e-06, "epoch": 1.411149825783972, "percentage": 47.12, "elapsed_time": "1:09:00", "remaining_time": "1:17:26"} +{"current_steps": 271, "total_steps": 573, "loss": 0.6093, "lr": 6.3406816821217554e-06, "epoch": 1.416376306620209, "percentage": 47.29, "elapsed_time": "1:09:16", "remaining_time": "1:17:12"} +{"current_steps": 272, "total_steps": 573, "loss": 0.5832, "lr": 6.311272933205672e-06, "epoch": 1.4216027874564459, "percentage": 47.47, "elapsed_time": "1:09:29", "remaining_time": "1:16:54"} +{"current_steps": 273, "total_steps": 573, "loss": 0.529, "lr": 6.281815389096903e-06, "epoch": 1.4268292682926829, "percentage": 47.64, "elapsed_time": "1:09:45", "remaining_time": "1:16:39"} +{"current_steps": 274, "total_steps": 573, "loss": 0.6526, "lr": 6.2523101459719204e-06, "epoch": 1.4320557491289199, "percentage": 47.82, "elapsed_time": "1:10:01", "remaining_time": "1:16:25"} +{"current_steps": 275, "total_steps": 573, "loss": 0.6282, "lr": 6.222758301782183e-06, "epoch": 1.4372822299651569, "percentage": 47.99, "elapsed_time": "1:10:17", "remaining_time": "1:16:09"} +{"current_steps": 276, "total_steps": 573, "loss": 0.5903, "lr": 6.193160956213262e-06, "epoch": 1.4425087108013936, "percentage": 48.17, "elapsed_time": "1:10:29", "remaining_time": "1:15:51"} +{"current_steps": 277, "total_steps": 573, "loss": 0.6083, "lr": 6.163519210643939e-06, "epoch": 1.4477351916376306, "percentage": 48.34, "elapsed_time": "1:10:42", "remaining_time": "1:15:33"} +{"current_steps": 278, "total_steps": 573, "loss": 0.5271, "lr": 6.133834168105206e-06, "epoch": 1.4529616724738676, "percentage": 48.52, "elapsed_time": "1:10:58", "remaining_time": "1:15:18"} +{"current_steps": 279, "total_steps": 573, "loss": 0.5636, "lr": 6.104106933239227e-06, "epoch": 1.4581881533101044, "percentage": 48.69, "elapsed_time": "1:11:12", "remaining_time": "1:15:02"} +{"current_steps": 280, "total_steps": 573, "loss": 0.6205, "lr": 6.07433861225823e-06, "epoch": 1.4634146341463414, "percentage": 48.87, "elapsed_time": "1:11:29", "remaining_time": "1:14:48"} +{"current_steps": 281, "total_steps": 573, "loss": 0.5794, "lr": 6.044530312903343e-06, "epoch": 1.4686411149825784, "percentage": 49.04, "elapsed_time": "1:11:42", "remaining_time": "1:14:31"} +{"current_steps": 282, "total_steps": 573, "loss": 0.6167, "lr": 6.014683144403375e-06, "epoch": 1.4738675958188154, "percentage": 49.21, "elapsed_time": "1:11:55", "remaining_time": "1:14:13"} +{"current_steps": 283, "total_steps": 573, "loss": 0.6008, "lr": 5.9847982174335314e-06, "epoch": 1.4790940766550522, "percentage": 49.39, "elapsed_time": "1:12:09", "remaining_time": "1:13:56"} +{"current_steps": 284, "total_steps": 573, "loss": 0.6057, "lr": 5.954876644074092e-06, "epoch": 1.4843205574912892, "percentage": 49.56, "elapsed_time": "1:12:26", "remaining_time": "1:13:42"} +{"current_steps": 285, "total_steps": 573, "loss": 0.5872, "lr": 5.924919537769025e-06, "epoch": 1.489547038327526, "percentage": 49.74, "elapsed_time": "1:12:40", "remaining_time": "1:13:26"} +{"current_steps": 286, "total_steps": 573, "loss": 0.549, "lr": 5.894928013284551e-06, "epoch": 1.494773519163763, "percentage": 49.91, "elapsed_time": "1:12:55", "remaining_time": "1:13:10"} +{"current_steps": 287, "total_steps": 573, "loss": 0.6325, "lr": 5.8649031866676685e-06, "epoch": 1.5, "percentage": 50.09, "elapsed_time": "1:13:11", "remaining_time": "1:12:56"} +{"current_steps": 288, "total_steps": 573, "loss": 0.5278, "lr": 5.834846175204612e-06, "epoch": 1.505226480836237, "percentage": 50.26, "elapsed_time": "1:13:26", "remaining_time": "1:12:40"} +{"current_steps": 289, "total_steps": 573, "loss": 0.6634, "lr": 5.804758097379281e-06, "epoch": 1.510452961672474, "percentage": 50.44, "elapsed_time": "1:13:43", "remaining_time": "1:12:26"} +{"current_steps": 290, "total_steps": 573, "loss": 0.5773, "lr": 5.774640072831622e-06, "epoch": 1.5156794425087108, "percentage": 50.61, "elapsed_time": "1:13:57", "remaining_time": "1:12:09"} +{"current_steps": 291, "total_steps": 573, "loss": 0.6216, "lr": 5.74449322231596e-06, "epoch": 1.5209059233449478, "percentage": 50.79, "elapsed_time": "1:14:11", "remaining_time": "1:11:54"} +{"current_steps": 292, "total_steps": 573, "loss": 0.5697, "lr": 5.714318667659295e-06, "epoch": 1.5261324041811846, "percentage": 50.96, "elapsed_time": "1:14:26", "remaining_time": "1:11:37"} +{"current_steps": 293, "total_steps": 573, "loss": 0.5902, "lr": 5.684117531719552e-06, "epoch": 1.5313588850174216, "percentage": 51.13, "elapsed_time": "1:14:38", "remaining_time": "1:11:20"} +{"current_steps": 294, "total_steps": 573, "loss": 0.6084, "lr": 5.653890938343806e-06, "epoch": 1.5365853658536586, "percentage": 51.31, "elapsed_time": "1:14:55", "remaining_time": "1:11:05"} +{"current_steps": 295, "total_steps": 573, "loss": 0.6074, "lr": 5.623640012326455e-06, "epoch": 1.5418118466898956, "percentage": 51.48, "elapsed_time": "1:15:11", "remaining_time": "1:10:51"} +{"current_steps": 296, "total_steps": 573, "loss": 0.559, "lr": 5.593365879367361e-06, "epoch": 1.5470383275261324, "percentage": 51.66, "elapsed_time": "1:15:25", "remaining_time": "1:10:34"} +{"current_steps": 297, "total_steps": 573, "loss": 0.6259, "lr": 5.56306966602997e-06, "epoch": 1.5522648083623694, "percentage": 51.83, "elapsed_time": "1:15:42", "remaining_time": "1:10:21"} +{"current_steps": 298, "total_steps": 573, "loss": 0.6274, "lr": 5.532752499699381e-06, "epoch": 1.5574912891986061, "percentage": 52.01, "elapsed_time": "1:15:57", "remaining_time": "1:10:05"} +{"current_steps": 299, "total_steps": 573, "loss": 0.5689, "lr": 5.502415508540401e-06, "epoch": 1.5627177700348431, "percentage": 52.18, "elapsed_time": "1:16:09", "remaining_time": "1:09:47"} +{"current_steps": 300, "total_steps": 573, "loss": 0.615, "lr": 5.472059821455554e-06, "epoch": 1.5679442508710801, "percentage": 52.36, "elapsed_time": "1:16:26", "remaining_time": "1:09:33"} +{"current_steps": 301, "total_steps": 573, "loss": 0.6209, "lr": 5.441686568043086e-06, "epoch": 1.5731707317073171, "percentage": 52.53, "elapsed_time": "1:16:42", "remaining_time": "1:09:18"} +{"current_steps": 302, "total_steps": 573, "loss": 0.5778, "lr": 5.411296878554918e-06, "epoch": 1.5783972125435541, "percentage": 52.71, "elapsed_time": "1:16:56", "remaining_time": "1:09:02"} +{"current_steps": 303, "total_steps": 573, "loss": 0.5891, "lr": 5.380891883854591e-06, "epoch": 1.583623693379791, "percentage": 52.88, "elapsed_time": "1:17:12", "remaining_time": "1:08:47"} +{"current_steps": 304, "total_steps": 573, "loss": 0.5781, "lr": 5.3504727153751865e-06, "epoch": 1.588850174216028, "percentage": 53.05, "elapsed_time": "1:17:24", "remaining_time": "1:08:30"} +{"current_steps": 305, "total_steps": 573, "loss": 0.6108, "lr": 5.320040505077222e-06, "epoch": 1.5940766550522647, "percentage": 53.23, "elapsed_time": "1:17:40", "remaining_time": "1:08:15"} +{"current_steps": 306, "total_steps": 573, "loss": 0.5925, "lr": 5.289596385406527e-06, "epoch": 1.5993031358885017, "percentage": 53.4, "elapsed_time": "1:17:57", "remaining_time": "1:08:01"} +{"current_steps": 307, "total_steps": 573, "loss": 0.5211, "lr": 5.259141489252104e-06, "epoch": 1.6045296167247387, "percentage": 53.58, "elapsed_time": "1:18:10", "remaining_time": "1:07:44"} +{"current_steps": 308, "total_steps": 573, "loss": 0.6835, "lr": 5.228676949903974e-06, "epoch": 1.6097560975609757, "percentage": 53.75, "elapsed_time": "1:18:27", "remaining_time": "1:07:30"} +{"current_steps": 309, "total_steps": 573, "loss": 0.5614, "lr": 5.198203901010993e-06, "epoch": 1.6149825783972127, "percentage": 53.93, "elapsed_time": "1:18:42", "remaining_time": "1:07:14"} +{"current_steps": 310, "total_steps": 573, "loss": 0.6063, "lr": 5.167723476538683e-06, "epoch": 1.6202090592334495, "percentage": 54.1, "elapsed_time": "1:18:56", "remaining_time": "1:06:58"} +{"current_steps": 311, "total_steps": 573, "loss": 0.5358, "lr": 5.137236810727025e-06, "epoch": 1.6254355400696863, "percentage": 54.28, "elapsed_time": "1:19:10", "remaining_time": "1:06:42"} +{"current_steps": 312, "total_steps": 573, "loss": 0.6031, "lr": 5.106745038048251e-06, "epoch": 1.6306620209059233, "percentage": 54.45, "elapsed_time": "1:19:19", "remaining_time": "1:06:21"} +{"current_steps": 313, "total_steps": 573, "loss": 0.5926, "lr": 5.07624929316463e-06, "epoch": 1.6358885017421603, "percentage": 54.62, "elapsed_time": "1:19:33", "remaining_time": "1:06:04"} +{"current_steps": 314, "total_steps": 573, "loss": 0.5909, "lr": 5.045750710886248e-06, "epoch": 1.6411149825783973, "percentage": 54.8, "elapsed_time": "1:19:50", "remaining_time": "1:05:51"} +{"current_steps": 315, "total_steps": 573, "loss": 0.5394, "lr": 5.015250426128772e-06, "epoch": 1.6463414634146343, "percentage": 54.97, "elapsed_time": "1:20:06", "remaining_time": "1:05:36"} +{"current_steps": 316, "total_steps": 573, "loss": 0.6349, "lr": 4.984749573871228e-06, "epoch": 1.651567944250871, "percentage": 55.15, "elapsed_time": "1:20:23", "remaining_time": "1:05:22"} +{"current_steps": 317, "total_steps": 573, "loss": 0.6271, "lr": 4.954249289113753e-06, "epoch": 1.656794425087108, "percentage": 55.32, "elapsed_time": "1:20:37", "remaining_time": "1:05:06"} +{"current_steps": 318, "total_steps": 573, "loss": 0.6067, "lr": 4.923750706835371e-06, "epoch": 1.6620209059233448, "percentage": 55.5, "elapsed_time": "1:20:53", "remaining_time": "1:04:52"} +{"current_steps": 319, "total_steps": 573, "loss": 0.5688, "lr": 4.8932549619517514e-06, "epoch": 1.6672473867595818, "percentage": 55.67, "elapsed_time": "1:21:10", "remaining_time": "1:04:37"} +{"current_steps": 320, "total_steps": 573, "loss": 0.5993, "lr": 4.862763189272976e-06, "epoch": 1.6724738675958188, "percentage": 55.85, "elapsed_time": "1:21:25", "remaining_time": "1:04:22"} +{"current_steps": 321, "total_steps": 573, "loss": 0.5251, "lr": 4.832276523461317e-06, "epoch": 1.6777003484320558, "percentage": 56.02, "elapsed_time": "1:21:38", "remaining_time": "1:04:05"} +{"current_steps": 322, "total_steps": 573, "loss": 0.6171, "lr": 4.801796098989009e-06, "epoch": 1.6829268292682928, "percentage": 56.2, "elapsed_time": "1:21:53", "remaining_time": "1:03:50"} +{"current_steps": 323, "total_steps": 573, "loss": 0.5868, "lr": 4.771323050096028e-06, "epoch": 1.6881533101045296, "percentage": 56.37, "elapsed_time": "1:22:07", "remaining_time": "1:03:34"} +{"current_steps": 324, "total_steps": 573, "loss": 0.6094, "lr": 4.740858510747897e-06, "epoch": 1.6933797909407664, "percentage": 56.54, "elapsed_time": "1:22:22", "remaining_time": "1:03:18"} +{"current_steps": 325, "total_steps": 573, "loss": 0.551, "lr": 4.710403614593475e-06, "epoch": 1.6986062717770034, "percentage": 56.72, "elapsed_time": "1:22:33", "remaining_time": "1:02:59"} +{"current_steps": 326, "total_steps": 573, "loss": 0.6207, "lr": 4.679959494922779e-06, "epoch": 1.7038327526132404, "percentage": 56.89, "elapsed_time": "1:22:48", "remaining_time": "1:02:44"} +{"current_steps": 327, "total_steps": 573, "loss": 0.5813, "lr": 4.649527284624814e-06, "epoch": 1.7090592334494774, "percentage": 57.07, "elapsed_time": "1:23:05", "remaining_time": "1:02:30"} +{"current_steps": 328, "total_steps": 573, "loss": 0.5997, "lr": 4.619108116145411e-06, "epoch": 1.7142857142857144, "percentage": 57.24, "elapsed_time": "1:23:21", "remaining_time": "1:02:16"} +{"current_steps": 329, "total_steps": 573, "loss": 0.6162, "lr": 4.588703121445084e-06, "epoch": 1.7195121951219512, "percentage": 57.42, "elapsed_time": "1:23:37", "remaining_time": "1:02:01"} +{"current_steps": 330, "total_steps": 573, "loss": 0.5616, "lr": 4.558313431956914e-06, "epoch": 1.7247386759581882, "percentage": 57.59, "elapsed_time": "1:23:53", "remaining_time": "1:01:46"} +{"current_steps": 331, "total_steps": 573, "loss": 0.6088, "lr": 4.527940178544446e-06, "epoch": 1.729965156794425, "percentage": 57.77, "elapsed_time": "1:24:08", "remaining_time": "1:01:31"} +{"current_steps": 332, "total_steps": 573, "loss": 0.5808, "lr": 4.4975844914596015e-06, "epoch": 1.735191637630662, "percentage": 57.94, "elapsed_time": "1:24:23", "remaining_time": "1:01:15"} +{"current_steps": 333, "total_steps": 573, "loss": 0.6187, "lr": 4.467247500300621e-06, "epoch": 1.740418118466899, "percentage": 58.12, "elapsed_time": "1:24:39", "remaining_time": "1:01:01"} +{"current_steps": 334, "total_steps": 573, "loss": 0.5532, "lr": 4.436930333970033e-06, "epoch": 1.745644599303136, "percentage": 58.29, "elapsed_time": "1:24:53", "remaining_time": "1:00:44"} +{"current_steps": 335, "total_steps": 573, "loss": 0.6331, "lr": 4.40663412063264e-06, "epoch": 1.750871080139373, "percentage": 58.46, "elapsed_time": "1:25:09", "remaining_time": "1:00:29"} +{"current_steps": 336, "total_steps": 573, "loss": 0.5759, "lr": 4.376359987673547e-06, "epoch": 1.7560975609756098, "percentage": 58.64, "elapsed_time": "1:25:22", "remaining_time": "1:00:13"} +{"current_steps": 337, "total_steps": 573, "loss": 0.5859, "lr": 4.346109061656196e-06, "epoch": 1.7613240418118465, "percentage": 58.81, "elapsed_time": "1:25:32", "remaining_time": "0:59:54"} +{"current_steps": 338, "total_steps": 573, "loss": 0.6084, "lr": 4.31588246828045e-06, "epoch": 1.7665505226480835, "percentage": 58.99, "elapsed_time": "1:25:47", "remaining_time": "0:59:38"} +{"current_steps": 339, "total_steps": 573, "loss": 0.5706, "lr": 4.285681332340708e-06, "epoch": 1.7717770034843205, "percentage": 59.16, "elapsed_time": "1:26:02", "remaining_time": "0:59:23"} +{"current_steps": 340, "total_steps": 573, "loss": 0.5904, "lr": 4.255506777684041e-06, "epoch": 1.7770034843205575, "percentage": 59.34, "elapsed_time": "1:26:15", "remaining_time": "0:59:06"} +{"current_steps": 341, "total_steps": 573, "loss": 0.5667, "lr": 4.225359927168379e-06, "epoch": 1.7822299651567945, "percentage": 59.51, "elapsed_time": "1:26:32", "remaining_time": "0:58:52"} +{"current_steps": 342, "total_steps": 573, "loss": 0.6049, "lr": 4.195241902620721e-06, "epoch": 1.7874564459930313, "percentage": 59.69, "elapsed_time": "1:26:48", "remaining_time": "0:58:37"} +{"current_steps": 343, "total_steps": 573, "loss": 0.6078, "lr": 4.165153824795391e-06, "epoch": 1.7926829268292683, "percentage": 59.86, "elapsed_time": "1:27:01", "remaining_time": "0:58:21"} +{"current_steps": 344, "total_steps": 573, "loss": 0.588, "lr": 4.135096813332333e-06, "epoch": 1.797909407665505, "percentage": 60.03, "elapsed_time": "1:27:13", "remaining_time": "0:58:03"} +{"current_steps": 345, "total_steps": 573, "loss": 0.6015, "lr": 4.105071986715449e-06, "epoch": 1.8031358885017421, "percentage": 60.21, "elapsed_time": "1:27:30", "remaining_time": "0:57:49"} +{"current_steps": 346, "total_steps": 573, "loss": 0.5697, "lr": 4.075080462230977e-06, "epoch": 1.8083623693379791, "percentage": 60.38, "elapsed_time": "1:27:46", "remaining_time": "0:57:35"} +{"current_steps": 347, "total_steps": 573, "loss": 0.5698, "lr": 4.04512335592591e-06, "epoch": 1.8135888501742161, "percentage": 60.56, "elapsed_time": "1:28:00", "remaining_time": "0:57:19"} +{"current_steps": 348, "total_steps": 573, "loss": 0.5787, "lr": 4.015201782566471e-06, "epoch": 1.8188153310104531, "percentage": 60.73, "elapsed_time": "1:28:15", "remaining_time": "0:57:03"} +{"current_steps": 349, "total_steps": 573, "loss": 0.6, "lr": 3.985316855596627e-06, "epoch": 1.82404181184669, "percentage": 60.91, "elapsed_time": "1:28:27", "remaining_time": "0:56:46"} +{"current_steps": 350, "total_steps": 573, "loss": 0.5759, "lr": 3.955469687096657e-06, "epoch": 1.8292682926829267, "percentage": 61.08, "elapsed_time": "1:28:43", "remaining_time": "0:56:31"} +{"current_steps": 351, "total_steps": 573, "loss": 0.6505, "lr": 3.9256613877417715e-06, "epoch": 1.8344947735191637, "percentage": 61.26, "elapsed_time": "1:28:59", "remaining_time": "0:56:16"} +{"current_steps": 352, "total_steps": 573, "loss": 0.5581, "lr": 3.895893066760774e-06, "epoch": 1.8397212543554007, "percentage": 61.43, "elapsed_time": "1:29:13", "remaining_time": "0:56:01"} +{"current_steps": 353, "total_steps": 573, "loss": 0.6126, "lr": 3.866165831894796e-06, "epoch": 1.8449477351916377, "percentage": 61.61, "elapsed_time": "1:29:31", "remaining_time": "0:55:47"} +{"current_steps": 354, "total_steps": 573, "loss": 0.6353, "lr": 3.836480789356063e-06, "epoch": 1.8501742160278747, "percentage": 61.78, "elapsed_time": "1:29:46", "remaining_time": "0:55:32"} +{"current_steps": 355, "total_steps": 573, "loss": 0.5625, "lr": 3.806839043786738e-06, "epoch": 1.8554006968641115, "percentage": 61.95, "elapsed_time": "1:30:01", "remaining_time": "0:55:16"} +{"current_steps": 356, "total_steps": 573, "loss": 0.5839, "lr": 3.777241698217819e-06, "epoch": 1.8606271777003485, "percentage": 62.13, "elapsed_time": "1:30:15", "remaining_time": "0:55:01"} +{"current_steps": 357, "total_steps": 573, "loss": 0.596, "lr": 3.747689854028081e-06, "epoch": 1.8658536585365852, "percentage": 62.3, "elapsed_time": "1:30:31", "remaining_time": "0:54:46"} +{"current_steps": 358, "total_steps": 573, "loss": 0.5786, "lr": 3.7181846109031007e-06, "epoch": 1.8710801393728222, "percentage": 62.48, "elapsed_time": "1:30:47", "remaining_time": "0:54:31"} +{"current_steps": 359, "total_steps": 573, "loss": 0.5763, "lr": 3.6887270667943285e-06, "epoch": 1.8763066202090593, "percentage": 62.65, "elapsed_time": "1:31:02", "remaining_time": "0:54:16"} +{"current_steps": 360, "total_steps": 573, "loss": 0.6022, "lr": 3.6593183178782454e-06, "epoch": 1.8815331010452963, "percentage": 62.83, "elapsed_time": "1:31:17", "remaining_time": "0:54:00"} +{"current_steps": 361, "total_steps": 573, "loss": 0.5949, "lr": 3.6299594585155513e-06, "epoch": 1.8867595818815333, "percentage": 63.0, "elapsed_time": "1:31:30", "remaining_time": "0:53:44"} +{"current_steps": 362, "total_steps": 573, "loss": 0.5868, "lr": 3.600651581210457e-06, "epoch": 1.89198606271777, "percentage": 63.18, "elapsed_time": "1:31:45", "remaining_time": "0:53:28"} +{"current_steps": 363, "total_steps": 573, "loss": 0.5522, "lr": 3.5713957765700224e-06, "epoch": 1.8972125435540068, "percentage": 63.35, "elapsed_time": "1:32:01", "remaining_time": "0:53:14"} +{"current_steps": 364, "total_steps": 573, "loss": 0.6013, "lr": 3.542193133263576e-06, "epoch": 1.9024390243902438, "percentage": 63.53, "elapsed_time": "1:32:18", "remaining_time": "0:52:59"} +{"current_steps": 365, "total_steps": 573, "loss": 0.5448, "lr": 3.5130447379822076e-06, "epoch": 1.9076655052264808, "percentage": 63.7, "elapsed_time": "1:32:33", "remaining_time": "0:52:44"} +{"current_steps": 366, "total_steps": 573, "loss": 0.6007, "lr": 3.483951675398316e-06, "epoch": 1.9128919860627178, "percentage": 63.87, "elapsed_time": "1:32:48", "remaining_time": "0:52:29"} +{"current_steps": 367, "total_steps": 573, "loss": 0.5685, "lr": 3.4549150281252635e-06, "epoch": 1.9181184668989548, "percentage": 64.05, "elapsed_time": "1:33:01", "remaining_time": "0:52:12"} +{"current_steps": 368, "total_steps": 573, "loss": 0.5857, "lr": 3.425935876677077e-06, "epoch": 1.9233449477351916, "percentage": 64.22, "elapsed_time": "1:33:09", "remaining_time": "0:51:53"} +{"current_steps": 369, "total_steps": 573, "loss": 0.5809, "lr": 3.397015299428242e-06, "epoch": 1.9285714285714286, "percentage": 64.4, "elapsed_time": "1:33:23", "remaining_time": "0:51:37"} +{"current_steps": 370, "total_steps": 573, "loss": 0.6067, "lr": 3.3681543725735843e-06, "epoch": 1.9337979094076654, "percentage": 64.57, "elapsed_time": "1:33:40", "remaining_time": "0:51:23"} +{"current_steps": 371, "total_steps": 573, "loss": 0.5398, "lr": 3.339354170088207e-06, "epoch": 1.9390243902439024, "percentage": 64.75, "elapsed_time": "1:33:51", "remaining_time": "0:51:06"} +{"current_steps": 372, "total_steps": 573, "loss": 0.5702, "lr": 3.3106157636875356e-06, "epoch": 1.9442508710801394, "percentage": 64.92, "elapsed_time": "1:34:08", "remaining_time": "0:50:51"} +{"current_steps": 373, "total_steps": 573, "loss": 0.5925, "lr": 3.2819402227874364e-06, "epoch": 1.9494773519163764, "percentage": 65.1, "elapsed_time": "1:34:22", "remaining_time": "0:50:36"} +{"current_steps": 374, "total_steps": 573, "loss": 0.6521, "lr": 3.253328614464414e-06, "epoch": 1.9547038327526134, "percentage": 65.27, "elapsed_time": "1:34:38", "remaining_time": "0:50:21"} +{"current_steps": 375, "total_steps": 573, "loss": 0.5637, "lr": 3.2247820034159182e-06, "epoch": 1.9599303135888502, "percentage": 65.45, "elapsed_time": "1:34:54", "remaining_time": "0:50:06"} +{"current_steps": 376, "total_steps": 573, "loss": 0.6078, "lr": 3.196301451920708e-06, "epoch": 1.965156794425087, "percentage": 65.62, "elapsed_time": "1:35:10", "remaining_time": "0:49:52"} +{"current_steps": 377, "total_steps": 573, "loss": 0.614, "lr": 3.16788801979933e-06, "epoch": 1.970383275261324, "percentage": 65.79, "elapsed_time": "1:35:28", "remaining_time": "0:49:38"} +{"current_steps": 378, "total_steps": 573, "loss": 0.5407, "lr": 3.1395427643746802e-06, "epoch": 1.975609756097561, "percentage": 65.97, "elapsed_time": "1:35:41", "remaining_time": "0:49:21"} +{"current_steps": 379, "total_steps": 573, "loss": 0.5792, "lr": 3.111266740432658e-06, "epoch": 1.980836236933798, "percentage": 66.14, "elapsed_time": "1:35:56", "remaining_time": "0:49:06"} +{"current_steps": 380, "total_steps": 573, "loss": 0.5552, "lr": 3.0830610001829173e-06, "epoch": 1.986062717770035, "percentage": 66.32, "elapsed_time": "1:36:11", "remaining_time": "0:48:51"} +{"current_steps": 381, "total_steps": 573, "loss": 0.5474, "lr": 3.0549265932197055e-06, "epoch": 1.9912891986062717, "percentage": 66.49, "elapsed_time": "1:36:28", "remaining_time": "0:48:36"} +{"current_steps": 382, "total_steps": 573, "loss": 0.5926, "lr": 3.026864566482813e-06, "epoch": 1.9965156794425087, "percentage": 66.67, "elapsed_time": "1:36:41", "remaining_time": "0:48:20"} +{"current_steps": 383, "total_steps": 573, "loss": 0.9583, "lr": 2.99887596421861e-06, "epoch": 2.0017421602787455, "percentage": 66.84, "elapsed_time": "1:38:44", "remaining_time": "0:48:59"} +{"current_steps": 384, "total_steps": 573, "loss": 0.4765, "lr": 2.9709618279411922e-06, "epoch": 2.0069686411149825, "percentage": 67.02, "elapsed_time": "1:38:57", "remaining_time": "0:48:42"} +{"current_steps": 385, "total_steps": 573, "loss": 0.5513, "lr": 2.9431231963936176e-06, "epoch": 2.0121951219512195, "percentage": 67.19, "elapsed_time": "1:39:13", "remaining_time": "0:48:27"} +{"current_steps": 386, "total_steps": 573, "loss": 0.5568, "lr": 2.9153611055092586e-06, "epoch": 2.0174216027874565, "percentage": 67.36, "elapsed_time": "1:39:28", "remaining_time": "0:48:11"} +{"current_steps": 387, "total_steps": 573, "loss": 0.5378, "lr": 2.8876765883732447e-06, "epoch": 2.0226480836236935, "percentage": 67.54, "elapsed_time": "1:39:45", "remaining_time": "0:47:56"} +{"current_steps": 388, "total_steps": 573, "loss": 0.5742, "lr": 2.860070675184036e-06, "epoch": 2.0278745644599305, "percentage": 67.71, "elapsed_time": "1:39:59", "remaining_time": "0:47:40"} +{"current_steps": 389, "total_steps": 573, "loss": 0.5343, "lr": 2.8325443932150646e-06, "epoch": 2.033101045296167, "percentage": 67.89, "elapsed_time": "1:40:14", "remaining_time": "0:47:24"} +{"current_steps": 390, "total_steps": 573, "loss": 0.5849, "lr": 2.805098766776529e-06, "epoch": 2.038327526132404, "percentage": 68.06, "elapsed_time": "1:40:29", "remaining_time": "0:47:09"} +{"current_steps": 391, "total_steps": 573, "loss": 0.5105, "lr": 2.7777348171772604e-06, "epoch": 2.043554006968641, "percentage": 68.24, "elapsed_time": "1:40:46", "remaining_time": "0:46:54"} +{"current_steps": 392, "total_steps": 573, "loss": 0.5143, "lr": 2.750453562686729e-06, "epoch": 2.048780487804878, "percentage": 68.41, "elapsed_time": "1:40:58", "remaining_time": "0:46:37"} +{"current_steps": 393, "total_steps": 573, "loss": 0.5839, "lr": 2.7232560184971437e-06, "epoch": 2.054006968641115, "percentage": 68.59, "elapsed_time": "1:41:15", "remaining_time": "0:46:22"} +{"current_steps": 394, "total_steps": 573, "loss": 0.5233, "lr": 2.6961431966856866e-06, "epoch": 2.059233449477352, "percentage": 68.76, "elapsed_time": "1:41:28", "remaining_time": "0:46:06"} +{"current_steps": 395, "total_steps": 573, "loss": 0.5494, "lr": 2.669116106176838e-06, "epoch": 2.0644599303135887, "percentage": 68.94, "elapsed_time": "1:41:44", "remaining_time": "0:45:51"} +{"current_steps": 396, "total_steps": 573, "loss": 0.5097, "lr": 2.6421757527048373e-06, "epoch": 2.0696864111498257, "percentage": 69.11, "elapsed_time": "1:42:00", "remaining_time": "0:45:35"} +{"current_steps": 397, "total_steps": 573, "loss": 0.5719, "lr": 2.615323138776264e-06, "epoch": 2.0749128919860627, "percentage": 69.28, "elapsed_time": "1:42:13", "remaining_time": "0:45:19"} +{"current_steps": 398, "total_steps": 573, "loss": 0.5265, "lr": 2.588559263632719e-06, "epoch": 2.0801393728222997, "percentage": 69.46, "elapsed_time": "1:42:26", "remaining_time": "0:45:02"} +{"current_steps": 399, "total_steps": 573, "loss": 0.5772, "lr": 2.5618851232136576e-06, "epoch": 2.0853658536585367, "percentage": 69.63, "elapsed_time": "1:42:41", "remaining_time": "0:44:47"} +{"current_steps": 400, "total_steps": 573, "loss": 0.4555, "lr": 2.5353017101193124e-06, "epoch": 2.0905923344947737, "percentage": 69.81, "elapsed_time": "1:42:57", "remaining_time": "0:44:31"} +{"current_steps": 401, "total_steps": 573, "loss": 0.5643, "lr": 2.508810013573767e-06, "epoch": 2.0958188153310107, "percentage": 69.98, "elapsed_time": "1:43:13", "remaining_time": "0:44:16"} +{"current_steps": 402, "total_steps": 573, "loss": 0.5065, "lr": 2.4824110193881384e-06, "epoch": 2.1010452961672472, "percentage": 70.16, "elapsed_time": "1:43:27", "remaining_time": "0:44:00"} +{"current_steps": 403, "total_steps": 573, "loss": 0.563, "lr": 2.4561057099238973e-06, "epoch": 2.1062717770034842, "percentage": 70.33, "elapsed_time": "1:43:44", "remaining_time": "0:43:45"} +{"current_steps": 404, "total_steps": 573, "loss": 0.5056, "lr": 2.4298950640563155e-06, "epoch": 2.1114982578397212, "percentage": 70.51, "elapsed_time": "1:43:58", "remaining_time": "0:43:29"} +{"current_steps": 405, "total_steps": 573, "loss": 0.5517, "lr": 2.4037800571380297e-06, "epoch": 2.1167247386759582, "percentage": 70.68, "elapsed_time": "1:44:13", "remaining_time": "0:43:14"} +{"current_steps": 406, "total_steps": 573, "loss": 0.5764, "lr": 2.377761660962754e-06, "epoch": 2.1219512195121952, "percentage": 70.86, "elapsed_time": "1:44:31", "remaining_time": "0:42:59"} +{"current_steps": 407, "total_steps": 573, "loss": 0.5357, "lr": 2.3518408437291155e-06, "epoch": 2.1271777003484322, "percentage": 71.03, "elapsed_time": "1:44:47", "remaining_time": "0:42:44"} +{"current_steps": 408, "total_steps": 573, "loss": 0.5321, "lr": 2.3260185700046295e-06, "epoch": 2.132404181184669, "percentage": 71.2, "elapsed_time": "1:45:01", "remaining_time": "0:42:28"} +{"current_steps": 409, "total_steps": 573, "loss": 0.5468, "lr": 2.3002958006897985e-06, "epoch": 2.137630662020906, "percentage": 71.38, "elapsed_time": "1:45:15", "remaining_time": "0:42:12"} +{"current_steps": 410, "total_steps": 573, "loss": 0.531, "lr": 2.2746734929823596e-06, "epoch": 2.142857142857143, "percentage": 71.55, "elapsed_time": "1:45:30", "remaining_time": "0:41:56"} +{"current_steps": 411, "total_steps": 573, "loss": 0.52, "lr": 2.249152600341665e-06, "epoch": 2.14808362369338, "percentage": 71.73, "elapsed_time": "1:45:47", "remaining_time": "0:41:42"} +{"current_steps": 412, "total_steps": 573, "loss": 0.6015, "lr": 2.2237340724532007e-06, "epoch": 2.153310104529617, "percentage": 71.9, "elapsed_time": "1:46:05", "remaining_time": "0:41:27"} +{"current_steps": 413, "total_steps": 573, "loss": 0.4911, "lr": 2.1984188551932513e-06, "epoch": 2.158536585365854, "percentage": 72.08, "elapsed_time": "1:46:17", "remaining_time": "0:41:10"} +{"current_steps": 414, "total_steps": 573, "loss": 0.5519, "lr": 2.173207890593693e-06, "epoch": 2.1637630662020904, "percentage": 72.25, "elapsed_time": "1:46:31", "remaining_time": "0:40:54"} +{"current_steps": 415, "total_steps": 573, "loss": 0.531, "lr": 2.148102116806944e-06, "epoch": 2.1689895470383274, "percentage": 72.43, "elapsed_time": "1:46:45", "remaining_time": "0:40:38"} +{"current_steps": 416, "total_steps": 573, "loss": 0.5249, "lr": 2.123102468071058e-06, "epoch": 2.1742160278745644, "percentage": 72.6, "elapsed_time": "1:46:59", "remaining_time": "0:40:22"} +{"current_steps": 417, "total_steps": 573, "loss": 0.5261, "lr": 2.0982098746749524e-06, "epoch": 2.1794425087108014, "percentage": 72.77, "elapsed_time": "1:47:16", "remaining_time": "0:40:07"} +{"current_steps": 418, "total_steps": 573, "loss": 0.609, "lr": 2.0734252629237892e-06, "epoch": 2.1846689895470384, "percentage": 72.95, "elapsed_time": "1:47:33", "remaining_time": "0:39:52"} +{"current_steps": 419, "total_steps": 573, "loss": 0.5314, "lr": 2.048749555104516e-06, "epoch": 2.1898954703832754, "percentage": 73.12, "elapsed_time": "1:47:48", "remaining_time": "0:39:37"} +{"current_steps": 420, "total_steps": 573, "loss": 0.54, "lr": 2.0241836694515338e-06, "epoch": 2.1951219512195124, "percentage": 73.3, "elapsed_time": "1:48:01", "remaining_time": "0:39:21"} +{"current_steps": 421, "total_steps": 573, "loss": 0.5182, "lr": 1.9997285201125328e-06, "epoch": 2.200348432055749, "percentage": 73.47, "elapsed_time": "1:48:16", "remaining_time": "0:39:05"} +{"current_steps": 422, "total_steps": 573, "loss": 0.5786, "lr": 1.975385017114473e-06, "epoch": 2.205574912891986, "percentage": 73.65, "elapsed_time": "1:48:32", "remaining_time": "0:38:50"} +{"current_steps": 423, "total_steps": 573, "loss": 0.5183, "lr": 1.9511540663297284e-06, "epoch": 2.210801393728223, "percentage": 73.82, "elapsed_time": "1:48:45", "remaining_time": "0:38:34"} +{"current_steps": 424, "total_steps": 573, "loss": 0.5159, "lr": 1.9270365694423654e-06, "epoch": 2.21602787456446, "percentage": 74.0, "elapsed_time": "1:48:57", "remaining_time": "0:38:17"} +{"current_steps": 425, "total_steps": 573, "loss": 0.5957, "lr": 1.903033423914596e-06, "epoch": 2.221254355400697, "percentage": 74.17, "elapsed_time": "1:49:12", "remaining_time": "0:38:01"} +{"current_steps": 426, "total_steps": 573, "loss": 0.4488, "lr": 1.8791455229533806e-06, "epoch": 2.226480836236934, "percentage": 74.35, "elapsed_time": "1:49:22", "remaining_time": "0:37:44"} +{"current_steps": 427, "total_steps": 573, "loss": 0.6349, "lr": 1.8553737554771883e-06, "epoch": 2.231707317073171, "percentage": 74.52, "elapsed_time": "1:49:36", "remaining_time": "0:37:28"} +{"current_steps": 428, "total_steps": 573, "loss": 0.5089, "lr": 1.8317190060829242e-06, "epoch": 2.2369337979094075, "percentage": 74.69, "elapsed_time": "1:49:52", "remaining_time": "0:37:13"} +{"current_steps": 429, "total_steps": 573, "loss": 0.4899, "lr": 1.808182155013003e-06, "epoch": 2.2421602787456445, "percentage": 74.87, "elapsed_time": "1:50:08", "remaining_time": "0:36:58"} +{"current_steps": 430, "total_steps": 573, "loss": 0.5486, "lr": 1.7847640781225982e-06, "epoch": 2.2473867595818815, "percentage": 75.04, "elapsed_time": "1:50:24", "remaining_time": "0:36:42"} +{"current_steps": 431, "total_steps": 573, "loss": 0.6217, "lr": 1.7614656468470508e-06, "epoch": 2.2526132404181185, "percentage": 75.22, "elapsed_time": "1:50:40", "remaining_time": "0:36:27"} +{"current_steps": 432, "total_steps": 573, "loss": 0.5065, "lr": 1.7382877281694355e-06, "epoch": 2.2578397212543555, "percentage": 75.39, "elapsed_time": "1:50:55", "remaining_time": "0:36:12"} +{"current_steps": 433, "total_steps": 573, "loss": 0.5339, "lr": 1.7152311845883096e-06, "epoch": 2.2630662020905925, "percentage": 75.57, "elapsed_time": "1:51:09", "remaining_time": "0:35:56"} +{"current_steps": 434, "total_steps": 573, "loss": 0.5833, "lr": 1.692296874085605e-06, "epoch": 2.2682926829268295, "percentage": 75.74, "elapsed_time": "1:51:24", "remaining_time": "0:35:40"} +{"current_steps": 435, "total_steps": 573, "loss": 0.5414, "lr": 1.6694856500947081e-06, "epoch": 2.273519163763066, "percentage": 75.92, "elapsed_time": "1:51:38", "remaining_time": "0:35:24"} +{"current_steps": 436, "total_steps": 573, "loss": 0.5291, "lr": 1.6467983614686995e-06, "epoch": 2.278745644599303, "percentage": 76.09, "elapsed_time": "1:51:51", "remaining_time": "0:35:08"} +{"current_steps": 437, "total_steps": 573, "loss": 0.5207, "lr": 1.62423585244877e-06, "epoch": 2.28397212543554, "percentage": 76.27, "elapsed_time": "1:52:06", "remaining_time": "0:34:53"} +{"current_steps": 438, "total_steps": 573, "loss": 0.5233, "lr": 1.601798962632799e-06, "epoch": 2.289198606271777, "percentage": 76.44, "elapsed_time": "1:52:20", "remaining_time": "0:34:37"} +{"current_steps": 439, "total_steps": 573, "loss": 0.5789, "lr": 1.5794885269441152e-06, "epoch": 2.294425087108014, "percentage": 76.61, "elapsed_time": "1:52:36", "remaining_time": "0:34:22"} +{"current_steps": 440, "total_steps": 573, "loss": 0.5447, "lr": 1.5573053756004253e-06, "epoch": 2.2996515679442506, "percentage": 76.79, "elapsed_time": "1:52:51", "remaining_time": "0:34:06"} +{"current_steps": 441, "total_steps": 573, "loss": 0.5522, "lr": 1.53525033408292e-06, "epoch": 2.3048780487804876, "percentage": 76.96, "elapsed_time": "1:53:08", "remaining_time": "0:33:51"} +{"current_steps": 442, "total_steps": 573, "loss": 0.52, "lr": 1.5133242231055622e-06, "epoch": 2.3101045296167246, "percentage": 77.14, "elapsed_time": "1:53:24", "remaining_time": "0:33:36"} +{"current_steps": 443, "total_steps": 573, "loss": 0.5629, "lr": 1.491527858584535e-06, "epoch": 2.3153310104529616, "percentage": 77.31, "elapsed_time": "1:53:39", "remaining_time": "0:33:21"} +{"current_steps": 444, "total_steps": 573, "loss": 0.5899, "lr": 1.4698620516078882e-06, "epoch": 2.3205574912891986, "percentage": 77.49, "elapsed_time": "1:53:54", "remaining_time": "0:33:05"} +{"current_steps": 445, "total_steps": 573, "loss": 0.514, "lr": 1.4483276084053567e-06, "epoch": 2.3257839721254356, "percentage": 77.66, "elapsed_time": "1:54:10", "remaining_time": "0:32:50"} +{"current_steps": 446, "total_steps": 573, "loss": 0.5766, "lr": 1.4269253303183516e-06, "epoch": 2.3310104529616726, "percentage": 77.84, "elapsed_time": "1:54:28", "remaining_time": "0:32:35"} +{"current_steps": 447, "total_steps": 573, "loss": 0.492, "lr": 1.4056560137701469e-06, "epoch": 2.3362369337979096, "percentage": 78.01, "elapsed_time": "1:54:42", "remaining_time": "0:32:20"} +{"current_steps": 448, "total_steps": 573, "loss": 0.5503, "lr": 1.3845204502362442e-06, "epoch": 2.341463414634146, "percentage": 78.18, "elapsed_time": "1:54:56", "remaining_time": "0:32:04"} +{"current_steps": 449, "total_steps": 573, "loss": 0.5173, "lr": 1.3635194262149131e-06, "epoch": 2.346689895470383, "percentage": 78.36, "elapsed_time": "1:55:08", "remaining_time": "0:31:48"} +{"current_steps": 450, "total_steps": 573, "loss": 0.5464, "lr": 1.3426537231979309e-06, "epoch": 2.35191637630662, "percentage": 78.53, "elapsed_time": "1:55:25", "remaining_time": "0:31:33"} +{"current_steps": 451, "total_steps": 573, "loss": 0.5341, "lr": 1.3219241176414948e-06, "epoch": 2.357142857142857, "percentage": 78.71, "elapsed_time": "1:55:37", "remaining_time": "0:31:16"} +{"current_steps": 452, "total_steps": 573, "loss": 0.5283, "lr": 1.3013313809373396e-06, "epoch": 2.362369337979094, "percentage": 78.88, "elapsed_time": "1:55:52", "remaining_time": "0:31:01"} +{"current_steps": 453, "total_steps": 573, "loss": 0.5103, "lr": 1.28087627938402e-06, "epoch": 2.3675958188153308, "percentage": 79.06, "elapsed_time": "1:56:06", "remaining_time": "0:30:45"} +{"current_steps": 454, "total_steps": 573, "loss": 0.5989, "lr": 1.2605595741584015e-06, "epoch": 2.3728222996515678, "percentage": 79.23, "elapsed_time": "1:56:22", "remaining_time": "0:30:30"} +{"current_steps": 455, "total_steps": 573, "loss": 0.5247, "lr": 1.2403820212873347e-06, "epoch": 2.3780487804878048, "percentage": 79.41, "elapsed_time": "1:56:36", "remaining_time": "0:30:14"} +{"current_steps": 456, "total_steps": 573, "loss": 0.547, "lr": 1.2203443716195213e-06, "epoch": 2.3832752613240418, "percentage": 79.58, "elapsed_time": "1:56:50", "remaining_time": "0:29:58"} +{"current_steps": 457, "total_steps": 573, "loss": 0.5319, "lr": 1.200447370797576e-06, "epoch": 2.3885017421602788, "percentage": 79.76, "elapsed_time": "1:57:02", "remaining_time": "0:29:42"} +{"current_steps": 458, "total_steps": 573, "loss": 0.5079, "lr": 1.1806917592302763e-06, "epoch": 2.3937282229965158, "percentage": 79.93, "elapsed_time": "1:57:16", "remaining_time": "0:29:26"} +{"current_steps": 459, "total_steps": 573, "loss": 0.528, "lr": 1.16107827206501e-06, "epoch": 2.3989547038327528, "percentage": 80.1, "elapsed_time": "1:57:31", "remaining_time": "0:29:11"} +{"current_steps": 460, "total_steps": 573, "loss": 0.5351, "lr": 1.1416076391604197e-06, "epoch": 2.40418118466899, "percentage": 80.28, "elapsed_time": "1:57:49", "remaining_time": "0:28:56"} +{"current_steps": 461, "total_steps": 573, "loss": 0.5459, "lr": 1.12228058505925e-06, "epoch": 2.4094076655052263, "percentage": 80.45, "elapsed_time": "1:58:05", "remaining_time": "0:28:41"} +{"current_steps": 462, "total_steps": 573, "loss": 0.5377, "lr": 1.1030978289613725e-06, "epoch": 2.4146341463414633, "percentage": 80.63, "elapsed_time": "1:58:20", "remaining_time": "0:28:25"} +{"current_steps": 463, "total_steps": 573, "loss": 0.5494, "lr": 1.0840600846970333e-06, "epoch": 2.4198606271777003, "percentage": 80.8, "elapsed_time": "1:58:33", "remaining_time": "0:28:10"} +{"current_steps": 464, "total_steps": 573, "loss": 0.5372, "lr": 1.0651680607002861e-06, "epoch": 2.4250871080139373, "percentage": 80.98, "elapsed_time": "1:58:49", "remaining_time": "0:27:54"} +{"current_steps": 465, "total_steps": 573, "loss": 0.5127, "lr": 1.0464224599826301e-06, "epoch": 2.4303135888501743, "percentage": 81.15, "elapsed_time": "1:59:03", "remaining_time": "0:27:39"} +{"current_steps": 466, "total_steps": 573, "loss": 0.5137, "lr": 1.0278239801068518e-06, "epoch": 2.435540069686411, "percentage": 81.33, "elapsed_time": "1:59:16", "remaining_time": "0:27:23"} +{"current_steps": 467, "total_steps": 573, "loss": 0.6034, "lr": 1.0093733131610621e-06, "epoch": 2.440766550522648, "percentage": 81.5, "elapsed_time": "1:59:33", "remaining_time": "0:27:08"} +{"current_steps": 468, "total_steps": 573, "loss": 0.5201, "lr": 9.91071145732948e-07, "epoch": 2.445993031358885, "percentage": 81.68, "elapsed_time": "1:59:46", "remaining_time": "0:26:52"} +{"current_steps": 469, "total_steps": 573, "loss": 0.4763, "lr": 9.729181588842184e-07, "epoch": 2.451219512195122, "percentage": 81.85, "elapsed_time": "2:00:02", "remaining_time": "0:26:37"} +{"current_steps": 470, "total_steps": 573, "loss": 0.5551, "lr": 9.549150281252633e-07, "epoch": 2.456445993031359, "percentage": 82.02, "elapsed_time": "2:00:17", "remaining_time": "0:26:21"} +{"current_steps": 471, "total_steps": 573, "loss": 0.509, "lr": 9.370624233900183e-07, "epoch": 2.461672473867596, "percentage": 82.2, "elapsed_time": "2:00:34", "remaining_time": "0:26:06"} +{"current_steps": 472, "total_steps": 573, "loss": 0.5605, "lr": 9.193610090110305e-07, "epoch": 2.466898954703833, "percentage": 82.37, "elapsed_time": "2:00:52", "remaining_time": "0:25:51"} +{"current_steps": 473, "total_steps": 573, "loss": 0.5394, "lr": 9.018114436947373e-07, "epoch": 2.47212543554007, "percentage": 82.55, "elapsed_time": "2:01:06", "remaining_time": "0:25:36"} +{"current_steps": 474, "total_steps": 573, "loss": 0.5614, "lr": 8.844143804969624e-07, "epoch": 2.4773519163763065, "percentage": 82.72, "elapsed_time": "2:01:18", "remaining_time": "0:25:20"} +{"current_steps": 475, "total_steps": 573, "loss": 0.495, "lr": 8.671704667986036e-07, "epoch": 2.4825783972125435, "percentage": 82.9, "elapsed_time": "2:01:31", "remaining_time": "0:25:04"} +{"current_steps": 476, "total_steps": 573, "loss": 0.5337, "lr": 8.500803442815475e-07, "epoch": 2.4878048780487805, "percentage": 83.07, "elapsed_time": "2:01:46", "remaining_time": "0:24:48"} +{"current_steps": 477, "total_steps": 573, "loss": 0.5432, "lr": 8.331446489047956e-07, "epoch": 2.4930313588850175, "percentage": 83.25, "elapsed_time": "2:02:01", "remaining_time": "0:24:33"} +{"current_steps": 478, "total_steps": 573, "loss": 0.5526, "lr": 8.163640108807897e-07, "epoch": 2.4982578397212545, "percentage": 83.42, "elapsed_time": "2:02:18", "remaining_time": "0:24:18"} +{"current_steps": 479, "total_steps": 573, "loss": 0.5274, "lr": 7.997390546519668e-07, "epoch": 2.503484320557491, "percentage": 83.6, "elapsed_time": "2:02:34", "remaining_time": "0:24:03"} +{"current_steps": 480, "total_steps": 573, "loss": 0.5498, "lr": 7.832703988675195e-07, "epoch": 2.508710801393728, "percentage": 83.77, "elapsed_time": "2:02:52", "remaining_time": "0:23:48"} +{"current_steps": 481, "total_steps": 573, "loss": 0.5531, "lr": 7.669586563603782e-07, "epoch": 2.513937282229965, "percentage": 83.94, "elapsed_time": "2:03:05", "remaining_time": "0:23:32"} +{"current_steps": 482, "total_steps": 573, "loss": 0.5914, "lr": 7.508044341244014e-07, "epoch": 2.519163763066202, "percentage": 84.12, "elapsed_time": "2:03:21", "remaining_time": "0:23:17"} +{"current_steps": 483, "total_steps": 573, "loss": 0.5302, "lr": 7.348083332917927e-07, "epoch": 2.524390243902439, "percentage": 84.29, "elapsed_time": "2:03:38", "remaining_time": "0:23:02"} +{"current_steps": 484, "total_steps": 573, "loss": 0.5103, "lr": 7.189709491107272e-07, "epoch": 2.529616724738676, "percentage": 84.47, "elapsed_time": "2:03:54", "remaining_time": "0:22:47"} +{"current_steps": 485, "total_steps": 573, "loss": 0.5131, "lr": 7.032928709232062e-07, "epoch": 2.534843205574913, "percentage": 84.64, "elapsed_time": "2:04:11", "remaining_time": "0:22:31"} +{"current_steps": 486, "total_steps": 573, "loss": 0.5406, "lr": 6.87774682143122e-07, "epoch": 2.54006968641115, "percentage": 84.82, "elapsed_time": "2:04:24", "remaining_time": "0:22:16"} +{"current_steps": 487, "total_steps": 573, "loss": 0.5524, "lr": 6.724169602345487e-07, "epoch": 2.5452961672473866, "percentage": 84.99, "elapsed_time": "2:04:40", "remaining_time": "0:22:00"} +{"current_steps": 488, "total_steps": 573, "loss": 0.5107, "lr": 6.572202766902569e-07, "epoch": 2.5505226480836236, "percentage": 85.17, "elapsed_time": "2:04:52", "remaining_time": "0:21:45"} +{"current_steps": 489, "total_steps": 573, "loss": 0.5465, "lr": 6.421851970104409e-07, "epoch": 2.5557491289198606, "percentage": 85.34, "elapsed_time": "2:05:07", "remaining_time": "0:21:29"} +{"current_steps": 490, "total_steps": 573, "loss": 0.5306, "lr": 6.273122806816845e-07, "epoch": 2.5609756097560976, "percentage": 85.51, "elapsed_time": "2:05:22", "remaining_time": "0:21:14"} +{"current_steps": 491, "total_steps": 573, "loss": 0.5881, "lr": 6.126020811561323e-07, "epoch": 2.5662020905923346, "percentage": 85.69, "elapsed_time": "2:05:37", "remaining_time": "0:20:58"} +{"current_steps": 492, "total_steps": 573, "loss": 0.4535, "lr": 5.980551458308981e-07, "epoch": 2.571428571428571, "percentage": 85.86, "elapsed_time": "2:05:52", "remaining_time": "0:20:43"} +{"current_steps": 493, "total_steps": 573, "loss": 0.5696, "lr": 5.836720160276971e-07, "epoch": 2.576655052264808, "percentage": 86.04, "elapsed_time": "2:06:08", "remaining_time": "0:20:28"} +{"current_steps": 494, "total_steps": 573, "loss": 0.5412, "lr": 5.694532269726977e-07, "epoch": 2.581881533101045, "percentage": 86.21, "elapsed_time": "2:06:24", "remaining_time": "0:20:12"} +{"current_steps": 495, "total_steps": 573, "loss": 0.5886, "lr": 5.553993077766124e-07, "epoch": 2.587108013937282, "percentage": 86.39, "elapsed_time": "2:06:39", "remaining_time": "0:19:57"} +{"current_steps": 496, "total_steps": 573, "loss": 0.519, "lr": 5.415107814149978e-07, "epoch": 2.592334494773519, "percentage": 86.56, "elapsed_time": "2:06:55", "remaining_time": "0:19:42"} +{"current_steps": 497, "total_steps": 573, "loss": 0.5866, "lr": 5.277881647088024e-07, "epoch": 2.597560975609756, "percentage": 86.74, "elapsed_time": "2:07:10", "remaining_time": "0:19:26"} +{"current_steps": 498, "total_steps": 573, "loss": 0.5824, "lr": 5.1423196830513e-07, "epoch": 2.602787456445993, "percentage": 86.91, "elapsed_time": "2:07:27", "remaining_time": "0:19:11"} +{"current_steps": 499, "total_steps": 573, "loss": 0.5086, "lr": 5.008426966582386e-07, "epoch": 2.60801393728223, "percentage": 87.09, "elapsed_time": "2:07:44", "remaining_time": "0:18:56"} +{"current_steps": 500, "total_steps": 573, "loss": 0.5853, "lr": 4.87620848010772e-07, "epoch": 2.6132404181184667, "percentage": 87.26, "elapsed_time": "2:08:00", "remaining_time": "0:18:41"} +{"current_steps": 501, "total_steps": 573, "loss": 0.4705, "lr": 4.7456691437521243e-07, "epoch": 2.6184668989547037, "percentage": 87.43, "elapsed_time": "2:08:14", "remaining_time": "0:18:25"} +{"current_steps": 502, "total_steps": 573, "loss": 0.6052, "lr": 4.6168138151557516e-07, "epoch": 2.6236933797909407, "percentage": 87.61, "elapsed_time": "2:08:33", "remaining_time": "0:18:10"} +{"current_steps": 503, "total_steps": 573, "loss": 0.5156, "lr": 4.4896472892933693e-07, "epoch": 2.6289198606271778, "percentage": 87.78, "elapsed_time": "2:08:46", "remaining_time": "0:17:55"} +{"current_steps": 504, "total_steps": 573, "loss": 0.5552, "lr": 4.3641742982958203e-07, "epoch": 2.6341463414634148, "percentage": 87.96, "elapsed_time": "2:09:00", "remaining_time": "0:17:39"} +{"current_steps": 505, "total_steps": 573, "loss": 0.4874, "lr": 4.240399511274057e-07, "epoch": 2.6393728222996513, "percentage": 88.13, "elapsed_time": "2:09:19", "remaining_time": "0:17:24"} +{"current_steps": 506, "total_steps": 573, "loss": 0.5473, "lr": 4.118327534145278e-07, "epoch": 2.6445993031358883, "percentage": 88.31, "elapsed_time": "2:09:36", "remaining_time": "0:17:09"} +{"current_steps": 507, "total_steps": 573, "loss": 0.5476, "lr": 3.997962909461611e-07, "epoch": 2.6498257839721253, "percentage": 88.48, "elapsed_time": "2:09:48", "remaining_time": "0:16:53"} +{"current_steps": 508, "total_steps": 573, "loss": 0.515, "lr": 3.8793101162410417e-07, "epoch": 2.6550522648083623, "percentage": 88.66, "elapsed_time": "2:10:05", "remaining_time": "0:16:38"} +{"current_steps": 509, "total_steps": 573, "loss": 0.5736, "lr": 3.762373569800737e-07, "epoch": 2.6602787456445993, "percentage": 88.83, "elapsed_time": "2:10:21", "remaining_time": "0:16:23"} +{"current_steps": 510, "total_steps": 573, "loss": 0.5301, "lr": 3.6471576215927897e-07, "epoch": 2.6655052264808363, "percentage": 89.01, "elapsed_time": "2:10:37", "remaining_time": "0:16:08"} +{"current_steps": 511, "total_steps": 573, "loss": 0.5274, "lr": 3.5336665590422147e-07, "epoch": 2.6707317073170733, "percentage": 89.18, "elapsed_time": "2:10:53", "remaining_time": "0:15:52"} +{"current_steps": 512, "total_steps": 573, "loss": 0.5453, "lr": 3.4219046053874604e-07, "epoch": 2.6759581881533103, "percentage": 89.35, "elapsed_time": "2:11:07", "remaining_time": "0:15:37"} +{"current_steps": 513, "total_steps": 573, "loss": 0.5573, "lr": 3.3118759195232273e-07, "epoch": 2.681184668989547, "percentage": 89.53, "elapsed_time": "2:11:23", "remaining_time": "0:15:22"} +{"current_steps": 514, "total_steps": 573, "loss": 0.5181, "lr": 3.2035845958457324e-07, "epoch": 2.686411149825784, "percentage": 89.7, "elapsed_time": "2:11:40", "remaining_time": "0:15:06"} +{"current_steps": 515, "total_steps": 573, "loss": 0.5436, "lr": 3.0970346641003346e-07, "epoch": 2.691637630662021, "percentage": 89.88, "elapsed_time": "2:11:51", "remaining_time": "0:14:51"} +{"current_steps": 516, "total_steps": 573, "loss": 0.5475, "lr": 2.9922300892315517e-07, "epoch": 2.696864111498258, "percentage": 90.05, "elapsed_time": "2:12:08", "remaining_time": "0:14:35"} +{"current_steps": 517, "total_steps": 573, "loss": 0.5559, "lr": 2.88917477123557e-07, "epoch": 2.702090592334495, "percentage": 90.23, "elapsed_time": "2:12:23", "remaining_time": "0:14:20"} +{"current_steps": 518, "total_steps": 573, "loss": 0.5059, "lr": 2.787872545015069e-07, "epoch": 2.7073170731707314, "percentage": 90.4, "elapsed_time": "2:12:36", "remaining_time": "0:14:04"} +{"current_steps": 519, "total_steps": 573, "loss": 0.5585, "lr": 2.6883271802365606e-07, "epoch": 2.7125435540069684, "percentage": 90.58, "elapsed_time": "2:12:51", "remaining_time": "0:13:49"} +{"current_steps": 520, "total_steps": 573, "loss": 0.5104, "lr": 2.5905423811900755e-07, "epoch": 2.7177700348432055, "percentage": 90.75, "elapsed_time": "2:13:06", "remaining_time": "0:13:34"} +{"current_steps": 521, "total_steps": 573, "loss": 0.5518, "lr": 2.4945217866513274e-07, "epoch": 2.7229965156794425, "percentage": 90.92, "elapsed_time": "2:13:22", "remaining_time": "0:13:18"} +{"current_steps": 522, "total_steps": 573, "loss": 0.5305, "lr": 2.4002689697463224e-07, "epoch": 2.7282229965156795, "percentage": 91.1, "elapsed_time": "2:13:36", "remaining_time": "0:13:03"} +{"current_steps": 523, "total_steps": 573, "loss": 0.5579, "lr": 2.307787437818365e-07, "epoch": 2.7334494773519165, "percentage": 91.27, "elapsed_time": "2:13:51", "remaining_time": "0:12:47"} +{"current_steps": 524, "total_steps": 573, "loss": 0.5133, "lr": 2.2170806322976023e-07, "epoch": 2.7386759581881535, "percentage": 91.45, "elapsed_time": "2:14:05", "remaining_time": "0:12:32"} +{"current_steps": 525, "total_steps": 573, "loss": 0.5837, "lr": 2.1281519285728803e-07, "epoch": 2.7439024390243905, "percentage": 91.62, "elapsed_time": "2:14:18", "remaining_time": "0:12:16"} +{"current_steps": 526, "total_steps": 573, "loss": 0.5105, "lr": 2.041004635866195e-07, "epoch": 2.749128919860627, "percentage": 91.8, "elapsed_time": "2:14:28", "remaining_time": "0:12:00"} +{"current_steps": 527, "total_steps": 573, "loss": 0.5319, "lr": 1.9556419971095363e-07, "epoch": 2.754355400696864, "percentage": 91.97, "elapsed_time": "2:14:42", "remaining_time": "0:11:45"} +{"current_steps": 528, "total_steps": 573, "loss": 0.4988, "lr": 1.8720671888242058e-07, "epoch": 2.759581881533101, "percentage": 92.15, "elapsed_time": "2:14:53", "remaining_time": "0:11:29"} +{"current_steps": 529, "total_steps": 573, "loss": 0.546, "lr": 1.7902833210026228e-07, "epoch": 2.764808362369338, "percentage": 92.32, "elapsed_time": "2:15:08", "remaining_time": "0:11:14"} +{"current_steps": 530, "total_steps": 573, "loss": 0.5696, "lr": 1.710293436992566e-07, "epoch": 2.770034843205575, "percentage": 92.5, "elapsed_time": "2:15:27", "remaining_time": "0:10:59"} +{"current_steps": 531, "total_steps": 573, "loss": 0.5316, "lr": 1.6321005133839884e-07, "epoch": 2.7752613240418116, "percentage": 92.67, "elapsed_time": "2:15:43", "remaining_time": "0:10:44"} +{"current_steps": 532, "total_steps": 573, "loss": 0.5301, "lr": 1.5557074598981593e-07, "epoch": 2.7804878048780486, "percentage": 92.84, "elapsed_time": "2:15:57", "remaining_time": "0:10:28"} +{"current_steps": 533, "total_steps": 573, "loss": 0.5697, "lr": 1.4811171192794628e-07, "epoch": 2.7857142857142856, "percentage": 93.02, "elapsed_time": "2:16:14", "remaining_time": "0:10:13"} +{"current_steps": 534, "total_steps": 573, "loss": 0.4895, "lr": 1.4083322671896048e-07, "epoch": 2.7909407665505226, "percentage": 93.19, "elapsed_time": "2:16:30", "remaining_time": "0:09:58"} +{"current_steps": 535, "total_steps": 573, "loss": 0.5793, "lr": 1.337355612104274e-07, "epoch": 2.7961672473867596, "percentage": 93.37, "elapsed_time": "2:16:45", "remaining_time": "0:09:42"} +{"current_steps": 536, "total_steps": 573, "loss": 0.5057, "lr": 1.2681897952124046e-07, "epoch": 2.8013937282229966, "percentage": 93.54, "elapsed_time": "2:17:01", "remaining_time": "0:09:27"} +{"current_steps": 537, "total_steps": 573, "loss": 0.5524, "lr": 1.2008373903178828e-07, "epoch": 2.8066202090592336, "percentage": 93.72, "elapsed_time": "2:17:15", "remaining_time": "0:09:12"} +{"current_steps": 538, "total_steps": 573, "loss": 0.4922, "lr": 1.1353009037437523e-07, "epoch": 2.8118466898954706, "percentage": 93.89, "elapsed_time": "2:17:29", "remaining_time": "0:08:56"} +{"current_steps": 539, "total_steps": 573, "loss": 0.5724, "lr": 1.0715827742389717e-07, "epoch": 2.817073170731707, "percentage": 94.07, "elapsed_time": "2:17:45", "remaining_time": "0:08:41"} +{"current_steps": 540, "total_steps": 573, "loss": 0.4959, "lr": 1.0096853728876365e-07, "epoch": 2.822299651567944, "percentage": 94.24, "elapsed_time": "2:18:02", "remaining_time": "0:08:26"} +{"current_steps": 541, "total_steps": 573, "loss": 0.5187, "lr": 9.496110030207673e-08, "epoch": 2.827526132404181, "percentage": 94.42, "elapsed_time": "2:18:17", "remaining_time": "0:08:10"} +{"current_steps": 542, "total_steps": 573, "loss": 0.5413, "lr": 8.913619001305995e-08, "epoch": 2.832752613240418, "percentage": 94.59, "elapsed_time": "2:18:33", "remaining_time": "0:07:55"} +{"current_steps": 543, "total_steps": 573, "loss": 0.5597, "lr": 8.34940231787379e-08, "epoch": 2.837979094076655, "percentage": 94.76, "elapsed_time": "2:18:48", "remaining_time": "0:07:40"} +{"current_steps": 544, "total_steps": 573, "loss": 0.542, "lr": 7.803480975587197e-08, "epoch": 2.8432055749128917, "percentage": 94.94, "elapsed_time": "2:19:05", "remaining_time": "0:07:24"} +{"current_steps": 545, "total_steps": 573, "loss": 0.5495, "lr": 7.275875289314616e-08, "epoch": 2.8484320557491287, "percentage": 95.11, "elapsed_time": "2:19:19", "remaining_time": "0:07:09"} +{"current_steps": 546, "total_steps": 573, "loss": 0.5724, "lr": 6.766604892360751e-08, "epoch": 2.8536585365853657, "percentage": 95.29, "elapsed_time": "2:19:35", "remaining_time": "0:06:54"} +{"current_steps": 547, "total_steps": 573, "loss": 0.5257, "lr": 6.275688735736141e-08, "epoch": 2.8588850174216027, "percentage": 95.46, "elapsed_time": "2:19:49", "remaining_time": "0:06:38"} +{"current_steps": 548, "total_steps": 573, "loss": 0.5131, "lr": 5.803145087451945e-08, "epoch": 2.8641114982578397, "percentage": 95.64, "elapsed_time": "2:20:06", "remaining_time": "0:06:23"} +{"current_steps": 549, "total_steps": 573, "loss": 0.5607, "lr": 5.348991531839875e-08, "epoch": 2.8693379790940767, "percentage": 95.81, "elapsed_time": "2:20:21", "remaining_time": "0:06:08"} +{"current_steps": 550, "total_steps": 573, "loss": 0.5056, "lr": 4.913244968898279e-08, "epoch": 2.8745644599303137, "percentage": 95.99, "elapsed_time": "2:20:36", "remaining_time": "0:05:52"} +{"current_steps": 551, "total_steps": 573, "loss": 0.5415, "lr": 4.495921613662746e-08, "epoch": 2.8797909407665507, "percentage": 96.16, "elapsed_time": "2:20:53", "remaining_time": "0:05:37"} +{"current_steps": 552, "total_steps": 573, "loss": 0.5205, "lr": 4.097036995603321e-08, "epoch": 2.8850174216027873, "percentage": 96.34, "elapsed_time": "2:21:09", "remaining_time": "0:05:22"} +{"current_steps": 553, "total_steps": 573, "loss": 0.5259, "lr": 3.716605958046071e-08, "epoch": 2.8902439024390243, "percentage": 96.51, "elapsed_time": "2:21:21", "remaining_time": "0:05:06"} +{"current_steps": 554, "total_steps": 573, "loss": 0.604, "lr": 3.354642657621032e-08, "epoch": 2.8954703832752613, "percentage": 96.68, "elapsed_time": "2:21:39", "remaining_time": "0:04:51"} +{"current_steps": 555, "total_steps": 573, "loss": 0.4883, "lr": 3.011160563735349e-08, "epoch": 2.9006968641114983, "percentage": 96.86, "elapsed_time": "2:21:51", "remaining_time": "0:04:36"} +{"current_steps": 556, "total_steps": 573, "loss": 0.5621, "lr": 2.6861724580719562e-08, "epoch": 2.9059233449477353, "percentage": 97.03, "elapsed_time": "2:22:07", "remaining_time": "0:04:20"} +{"current_steps": 557, "total_steps": 573, "loss": 0.5334, "lr": 2.3796904341141236e-08, "epoch": 2.911149825783972, "percentage": 97.21, "elapsed_time": "2:22:20", "remaining_time": "0:04:05"} +{"current_steps": 558, "total_steps": 573, "loss": 0.553, "lr": 2.0917258966953735e-08, "epoch": 2.916376306620209, "percentage": 97.38, "elapsed_time": "2:22:37", "remaining_time": "0:03:50"} +{"current_steps": 559, "total_steps": 573, "loss": 0.5358, "lr": 1.8222895615748748e-08, "epoch": 2.921602787456446, "percentage": 97.56, "elapsed_time": "2:22:53", "remaining_time": "0:03:34"} +{"current_steps": 560, "total_steps": 573, "loss": 0.5405, "lr": 1.5713914550389843e-08, "epoch": 2.926829268292683, "percentage": 97.73, "elapsed_time": "2:23:07", "remaining_time": "0:03:19"} +{"current_steps": 561, "total_steps": 573, "loss": 0.5513, "lr": 1.3390409135281001e-08, "epoch": 2.93205574912892, "percentage": 97.91, "elapsed_time": "2:23:21", "remaining_time": "0:03:03"} +{"current_steps": 562, "total_steps": 573, "loss": 0.5245, "lr": 1.125246583288886e-08, "epoch": 2.937282229965157, "percentage": 98.08, "elapsed_time": "2:23:36", "remaining_time": "0:02:48"} +{"current_steps": 563, "total_steps": 573, "loss": 0.5701, "lr": 9.300164200530815e-09, "epoch": 2.942508710801394, "percentage": 98.25, "elapsed_time": "2:23:50", "remaining_time": "0:02:33"} +{"current_steps": 564, "total_steps": 573, "loss": 0.4999, "lr": 7.533576887410188e-09, "epoch": 2.947735191637631, "percentage": 98.43, "elapsed_time": "2:24:02", "remaining_time": "0:02:17"} +{"current_steps": 565, "total_steps": 573, "loss": 0.5704, "lr": 5.95276963191449e-09, "epoch": 2.952961672473868, "percentage": 98.6, "elapsed_time": "2:24:20", "remaining_time": "0:02:02"} +{"current_steps": 566, "total_steps": 573, "loss": 0.4995, "lr": 4.557801259169048e-09, "epoch": 2.9581881533101044, "percentage": 98.78, "elapsed_time": "2:24:31", "remaining_time": "0:01:47"} +{"current_steps": 567, "total_steps": 573, "loss": 0.5569, "lr": 3.348723678847643e-09, "epoch": 2.9634146341463414, "percentage": 98.95, "elapsed_time": "2:24:47", "remaining_time": "0:01:31"} +{"current_steps": 568, "total_steps": 573, "loss": 0.5232, "lr": 2.3255818832423894e-09, "epoch": 2.9686411149825784, "percentage": 99.13, "elapsed_time": "2:25:04", "remaining_time": "0:01:16"} +{"current_steps": 569, "total_steps": 573, "loss": 0.5572, "lr": 1.4884139455861868e-09, "epoch": 2.9738675958188154, "percentage": 99.3, "elapsed_time": "2:25:21", "remaining_time": "0:01:01"} +{"current_steps": 570, "total_steps": 573, "loss": 0.5603, "lr": 8.372510186388516e-10, "epoch": 2.979094076655052, "percentage": 99.48, "elapsed_time": "2:25:38", "remaining_time": "0:00:45"} +{"current_steps": 571, "total_steps": 573, "loss": 0.4893, "lr": 3.7211733352748856e-10, "epoch": 2.984320557491289, "percentage": 99.65, "elapsed_time": "2:25:49", "remaining_time": "0:00:30"} +{"current_steps": 572, "total_steps": 573, "loss": 0.5622, "lr": 9.303019884387976e-11, "epoch": 2.989547038327526, "percentage": 99.83, "elapsed_time": "2:26:04", "remaining_time": "0:00:15"} +{"current_steps": 573, "total_steps": 573, "loss": 0.4927, "lr": 0.0, "epoch": 2.994773519163763, "percentage": 100.0, "elapsed_time": "2:26:17", "remaining_time": "0:00:00"} +{"current_steps": 573, "total_steps": 573, "epoch": 2.994773519163763, "percentage": 100.0, "elapsed_time": "2:29:34", "remaining_time": "0:00:00"} diff --git a/trainer_state.json b/trainer_state.json new file mode 100644 index 0000000..c32d0b6 --- /dev/null +++ b/trainer_state.json @@ -0,0 +1,4053 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 2.994773519163763, + "eval_steps": 500, + "global_step": 573, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.005226480836236934, + "grad_norm": 6.817761533477436, + "learning_rate": 1.7241379310344828e-07, + "loss": 1.0919, + "step": 1 + }, + { + "epoch": 0.010452961672473868, + "grad_norm": 7.115516920325354, + "learning_rate": 3.4482758620689656e-07, + "loss": 1.1216, + "step": 2 + }, + { + "epoch": 0.0156794425087108, + "grad_norm": 6.6059432881920035, + "learning_rate": 5.172413793103449e-07, + "loss": 1.0823, + "step": 3 + }, + { + "epoch": 0.020905923344947737, + "grad_norm": 7.040897553026814, + "learning_rate": 6.896551724137931e-07, + "loss": 1.1163, + "step": 4 + }, + { + "epoch": 0.02613240418118467, + "grad_norm": 6.283884644524741, + "learning_rate": 8.620689655172415e-07, + "loss": 1.0475, + "step": 5 + }, + { + "epoch": 0.0313588850174216, + "grad_norm": 6.519407744623921, + "learning_rate": 1.0344827586206898e-06, + "loss": 1.0632, + "step": 6 + }, + { + "epoch": 0.036585365853658534, + "grad_norm": 6.169268594264987, + "learning_rate": 1.2068965517241381e-06, + "loss": 1.0867, + "step": 7 + }, + { + "epoch": 0.041811846689895474, + "grad_norm": 6.0230600012209905, + "learning_rate": 1.3793103448275862e-06, + "loss": 1.0679, + "step": 8 + }, + { + "epoch": 0.047038327526132406, + "grad_norm": 4.974697996657908, + "learning_rate": 1.5517241379310346e-06, + "loss": 1.0599, + "step": 9 + }, + { + "epoch": 0.05226480836236934, + "grad_norm": 4.610162697639871, + "learning_rate": 1.724137931034483e-06, + "loss": 1.0377, + "step": 10 + }, + { + "epoch": 0.05749128919860627, + "grad_norm": 3.231983464184593, + "learning_rate": 1.896551724137931e-06, + "loss": 0.9836, + "step": 11 + }, + { + "epoch": 0.0627177700348432, + "grad_norm": 2.8094756280140682, + "learning_rate": 2.0689655172413796e-06, + "loss": 1.0003, + "step": 12 + }, + { + "epoch": 0.06794425087108014, + "grad_norm": 2.5493675085491594, + "learning_rate": 2.241379310344828e-06, + "loss": 0.9805, + "step": 13 + }, + { + "epoch": 0.07317073170731707, + "grad_norm": 2.5421388777679423, + "learning_rate": 2.4137931034482762e-06, + "loss": 0.9785, + "step": 14 + }, + { + "epoch": 0.078397212543554, + "grad_norm": 2.4038506323025564, + "learning_rate": 2.5862068965517246e-06, + "loss": 0.9579, + "step": 15 + }, + { + "epoch": 0.08362369337979095, + "grad_norm": 3.118376309649565, + "learning_rate": 2.7586206896551725e-06, + "loss": 0.9266, + "step": 16 + }, + { + "epoch": 0.08885017421602788, + "grad_norm": 3.256072028222514, + "learning_rate": 2.931034482758621e-06, + "loss": 0.9496, + "step": 17 + }, + { + "epoch": 0.09407665505226481, + "grad_norm": 3.0097390475425785, + "learning_rate": 3.103448275862069e-06, + "loss": 0.9417, + "step": 18 + }, + { + "epoch": 0.09930313588850175, + "grad_norm": 2.5804981571566685, + "learning_rate": 3.2758620689655175e-06, + "loss": 0.9133, + "step": 19 + }, + { + "epoch": 0.10452961672473868, + "grad_norm": 2.1253546888275614, + "learning_rate": 3.448275862068966e-06, + "loss": 0.9181, + "step": 20 + }, + { + "epoch": 0.10975609756097561, + "grad_norm": 1.4630576625319751, + "learning_rate": 3.620689655172414e-06, + "loss": 0.8708, + "step": 21 + }, + { + "epoch": 0.11498257839721254, + "grad_norm": 1.8224890188617031, + "learning_rate": 3.793103448275862e-06, + "loss": 0.8532, + "step": 22 + }, + { + "epoch": 0.12020905923344948, + "grad_norm": 1.947817512922658, + "learning_rate": 3.96551724137931e-06, + "loss": 0.867, + "step": 23 + }, + { + "epoch": 0.1254355400696864, + "grad_norm": 1.6741792992922881, + "learning_rate": 4.137931034482759e-06, + "loss": 0.8596, + "step": 24 + }, + { + "epoch": 0.13066202090592335, + "grad_norm": 1.1380185267106577, + "learning_rate": 4.310344827586207e-06, + "loss": 0.8119, + "step": 25 + }, + { + "epoch": 0.13588850174216027, + "grad_norm": 1.2049716071539038, + "learning_rate": 4.482758620689656e-06, + "loss": 0.8374, + "step": 26 + }, + { + "epoch": 0.14111498257839722, + "grad_norm": 1.1289607052380697, + "learning_rate": 4.655172413793104e-06, + "loss": 0.7917, + "step": 27 + }, + { + "epoch": 0.14634146341463414, + "grad_norm": 1.2662899307258315, + "learning_rate": 4.8275862068965525e-06, + "loss": 0.8187, + "step": 28 + }, + { + "epoch": 0.15156794425087108, + "grad_norm": 1.3017674903802239, + "learning_rate": 5e-06, + "loss": 0.8106, + "step": 29 + }, + { + "epoch": 0.156794425087108, + "grad_norm": 0.9437556124885579, + "learning_rate": 5.172413793103449e-06, + "loss": 0.7807, + "step": 30 + }, + { + "epoch": 0.16202090592334495, + "grad_norm": 0.9854643253704647, + "learning_rate": 5.344827586206896e-06, + "loss": 0.7987, + "step": 31 + }, + { + "epoch": 0.1672473867595819, + "grad_norm": 1.0216232146030035, + "learning_rate": 5.517241379310345e-06, + "loss": 0.7978, + "step": 32 + }, + { + "epoch": 0.17247386759581881, + "grad_norm": 0.8155263699639064, + "learning_rate": 5.689655172413794e-06, + "loss": 0.7872, + "step": 33 + }, + { + "epoch": 0.17770034843205576, + "grad_norm": 0.8283995090284338, + "learning_rate": 5.862068965517242e-06, + "loss": 0.7704, + "step": 34 + }, + { + "epoch": 0.18292682926829268, + "grad_norm": 0.7185821947364432, + "learning_rate": 6.03448275862069e-06, + "loss": 0.7581, + "step": 35 + }, + { + "epoch": 0.18815331010452963, + "grad_norm": 0.770352836030317, + "learning_rate": 6.206896551724138e-06, + "loss": 0.7787, + "step": 36 + }, + { + "epoch": 0.19337979094076654, + "grad_norm": 0.7388881984398195, + "learning_rate": 6.379310344827587e-06, + "loss": 0.745, + "step": 37 + }, + { + "epoch": 0.1986062717770035, + "grad_norm": 0.8358555735535642, + "learning_rate": 6.551724137931035e-06, + "loss": 0.7604, + "step": 38 + }, + { + "epoch": 0.2038327526132404, + "grad_norm": 0.793851198978272, + "learning_rate": 6.724137931034484e-06, + "loss": 0.7544, + "step": 39 + }, + { + "epoch": 0.20905923344947736, + "grad_norm": 0.7772514888903087, + "learning_rate": 6.896551724137932e-06, + "loss": 0.732, + "step": 40 + }, + { + "epoch": 0.21428571428571427, + "grad_norm": 0.8148652288090457, + "learning_rate": 7.0689655172413796e-06, + "loss": 0.7297, + "step": 41 + }, + { + "epoch": 0.21951219512195122, + "grad_norm": 0.8289759706310655, + "learning_rate": 7.241379310344828e-06, + "loss": 0.7383, + "step": 42 + }, + { + "epoch": 0.22473867595818817, + "grad_norm": 0.7140088762027519, + "learning_rate": 7.413793103448277e-06, + "loss": 0.7461, + "step": 43 + }, + { + "epoch": 0.22996515679442509, + "grad_norm": 0.6669906555709666, + "learning_rate": 7.586206896551724e-06, + "loss": 0.7343, + "step": 44 + }, + { + "epoch": 0.23519163763066203, + "grad_norm": 0.7425162700101843, + "learning_rate": 7.758620689655173e-06, + "loss": 0.7211, + "step": 45 + }, + { + "epoch": 0.24041811846689895, + "grad_norm": 0.7667317947005017, + "learning_rate": 7.93103448275862e-06, + "loss": 0.7307, + "step": 46 + }, + { + "epoch": 0.2456445993031359, + "grad_norm": 0.6701254662379068, + "learning_rate": 8.103448275862069e-06, + "loss": 0.7244, + "step": 47 + }, + { + "epoch": 0.2508710801393728, + "grad_norm": 0.6974840533976149, + "learning_rate": 8.275862068965518e-06, + "loss": 0.7222, + "step": 48 + }, + { + "epoch": 0.25609756097560976, + "grad_norm": 0.7601606441382056, + "learning_rate": 8.448275862068966e-06, + "loss": 0.7325, + "step": 49 + }, + { + "epoch": 0.2613240418118467, + "grad_norm": 0.6932741056532161, + "learning_rate": 8.620689655172414e-06, + "loss": 0.7166, + "step": 50 + }, + { + "epoch": 0.2665505226480836, + "grad_norm": 0.7185062343660426, + "learning_rate": 8.793103448275862e-06, + "loss": 0.7367, + "step": 51 + }, + { + "epoch": 0.27177700348432055, + "grad_norm": 0.6728422963531511, + "learning_rate": 8.965517241379312e-06, + "loss": 0.7104, + "step": 52 + }, + { + "epoch": 0.2770034843205575, + "grad_norm": 0.661725549134852, + "learning_rate": 9.13793103448276e-06, + "loss": 0.7183, + "step": 53 + }, + { + "epoch": 0.28222996515679444, + "grad_norm": 0.6362203257614645, + "learning_rate": 9.310344827586207e-06, + "loss": 0.7153, + "step": 54 + }, + { + "epoch": 0.2874564459930314, + "grad_norm": 0.5890508129443038, + "learning_rate": 9.482758620689655e-06, + "loss": 0.7093, + "step": 55 + }, + { + "epoch": 0.2926829268292683, + "grad_norm": 0.6116919862768194, + "learning_rate": 9.655172413793105e-06, + "loss": 0.7176, + "step": 56 + }, + { + "epoch": 0.2979094076655052, + "grad_norm": 0.7050152514142426, + "learning_rate": 9.827586206896553e-06, + "loss": 0.7211, + "step": 57 + }, + { + "epoch": 0.30313588850174217, + "grad_norm": 0.6296132679526024, + "learning_rate": 1e-05, + "loss": 0.6993, + "step": 58 + }, + { + "epoch": 0.3083623693379791, + "grad_norm": 0.6453523097142025, + "learning_rate": 9.999906969801156e-06, + "loss": 0.6963, + "step": 59 + }, + { + "epoch": 0.313588850174216, + "grad_norm": 0.6955516834757508, + "learning_rate": 9.999627882666474e-06, + "loss": 0.7151, + "step": 60 + }, + { + "epoch": 0.31881533101045295, + "grad_norm": 0.5580219589427374, + "learning_rate": 9.999162748981362e-06, + "loss": 0.7049, + "step": 61 + }, + { + "epoch": 0.3240418118466899, + "grad_norm": 0.5910429225441691, + "learning_rate": 9.998511586054415e-06, + "loss": 0.7013, + "step": 62 + }, + { + "epoch": 0.32926829268292684, + "grad_norm": 0.8120038822728922, + "learning_rate": 9.997674418116759e-06, + "loss": 0.717, + "step": 63 + }, + { + "epoch": 0.3344947735191638, + "grad_norm": 0.7517280345835676, + "learning_rate": 9.996651276321153e-06, + "loss": 0.6952, + "step": 64 + }, + { + "epoch": 0.3397212543554007, + "grad_norm": 0.6469274840068534, + "learning_rate": 9.995442198740832e-06, + "loss": 0.701, + "step": 65 + }, + { + "epoch": 0.34494773519163763, + "grad_norm": 0.9251247112850067, + "learning_rate": 9.994047230368087e-06, + "loss": 0.7124, + "step": 66 + }, + { + "epoch": 0.3501742160278746, + "grad_norm": 0.662124581217118, + "learning_rate": 9.99246642311259e-06, + "loss": 0.7041, + "step": 67 + }, + { + "epoch": 0.3554006968641115, + "grad_norm": 0.6490157119284249, + "learning_rate": 9.99069983579947e-06, + "loss": 0.6885, + "step": 68 + }, + { + "epoch": 0.3606271777003484, + "grad_norm": 0.8298745583053626, + "learning_rate": 9.988747534167112e-06, + "loss": 0.7179, + "step": 69 + }, + { + "epoch": 0.36585365853658536, + "grad_norm": 0.561322661520838, + "learning_rate": 9.98660959086472e-06, + "loss": 0.6955, + "step": 70 + }, + { + "epoch": 0.3710801393728223, + "grad_norm": 0.7057604500980034, + "learning_rate": 9.98428608544961e-06, + "loss": 0.6903, + "step": 71 + }, + { + "epoch": 0.37630662020905925, + "grad_norm": 0.6658460439147413, + "learning_rate": 9.981777104384251e-06, + "loss": 0.7082, + "step": 72 + }, + { + "epoch": 0.38153310104529614, + "grad_norm": 0.5943504077793226, + "learning_rate": 9.979082741033047e-06, + "loss": 0.6768, + "step": 73 + }, + { + "epoch": 0.3867595818815331, + "grad_norm": 0.6864915702650408, + "learning_rate": 9.976203095658859e-06, + "loss": 0.6761, + "step": 74 + }, + { + "epoch": 0.39198606271777003, + "grad_norm": 0.6390276002240977, + "learning_rate": 9.97313827541928e-06, + "loss": 0.6934, + "step": 75 + }, + { + "epoch": 0.397212543554007, + "grad_norm": 0.6038585831748531, + "learning_rate": 9.969888394362648e-06, + "loss": 0.7041, + "step": 76 + }, + { + "epoch": 0.4024390243902439, + "grad_norm": 0.6334231152676686, + "learning_rate": 9.96645357342379e-06, + "loss": 0.6945, + "step": 77 + }, + { + "epoch": 0.4076655052264808, + "grad_norm": 0.5462598060569209, + "learning_rate": 9.96283394041954e-06, + "loss": 0.696, + "step": 78 + }, + { + "epoch": 0.41289198606271776, + "grad_norm": 0.6338524439755173, + "learning_rate": 9.959029630043969e-06, + "loss": 0.691, + "step": 79 + }, + { + "epoch": 0.4181184668989547, + "grad_norm": 0.6411928123304964, + "learning_rate": 9.955040783863373e-06, + "loss": 0.692, + "step": 80 + }, + { + "epoch": 0.42334494773519166, + "grad_norm": 0.8030581042650948, + "learning_rate": 9.950867550311019e-06, + "loss": 0.7196, + "step": 81 + }, + { + "epoch": 0.42857142857142855, + "grad_norm": 0.6024953623866571, + "learning_rate": 9.946510084681602e-06, + "loss": 0.6726, + "step": 82 + }, + { + "epoch": 0.4337979094076655, + "grad_norm": 0.6074570740511613, + "learning_rate": 9.941968549125481e-06, + "loss": 0.6897, + "step": 83 + }, + { + "epoch": 0.43902439024390244, + "grad_norm": 0.7048846718482608, + "learning_rate": 9.937243112642639e-06, + "loss": 0.6918, + "step": 84 + }, + { + "epoch": 0.4442508710801394, + "grad_norm": 0.5918640923441442, + "learning_rate": 9.932333951076395e-06, + "loss": 0.6766, + "step": 85 + }, + { + "epoch": 0.44947735191637633, + "grad_norm": 0.5926297060359819, + "learning_rate": 9.927241247106856e-06, + "loss": 0.695, + "step": 86 + }, + { + "epoch": 0.4547038327526132, + "grad_norm": 0.553208274597187, + "learning_rate": 9.921965190244129e-06, + "loss": 0.6534, + "step": 87 + }, + { + "epoch": 0.45993031358885017, + "grad_norm": 0.7161403077582934, + "learning_rate": 9.916505976821262e-06, + "loss": 0.6964, + "step": 88 + }, + { + "epoch": 0.4651567944250871, + "grad_norm": 0.6949109145902641, + "learning_rate": 9.910863809986942e-06, + "loss": 0.6948, + "step": 89 + }, + { + "epoch": 0.47038327526132406, + "grad_norm": 0.669998554662786, + "learning_rate": 9.905038899697924e-06, + "loss": 0.6748, + "step": 90 + }, + { + "epoch": 0.47560975609756095, + "grad_norm": 0.812799215586504, + "learning_rate": 9.899031462711237e-06, + "loss": 0.698, + "step": 91 + }, + { + "epoch": 0.4808362369337979, + "grad_norm": 0.7765125728252844, + "learning_rate": 9.892841722576103e-06, + "loss": 0.6839, + "step": 92 + }, + { + "epoch": 0.48606271777003485, + "grad_norm": 0.7279630881961654, + "learning_rate": 9.886469909625624e-06, + "loss": 0.6865, + "step": 93 + }, + { + "epoch": 0.4912891986062718, + "grad_norm": 0.8884193887396585, + "learning_rate": 9.879916260968212e-06, + "loss": 0.6693, + "step": 94 + }, + { + "epoch": 0.4965156794425087, + "grad_norm": 0.607572845135145, + "learning_rate": 9.87318102047876e-06, + "loss": 0.6812, + "step": 95 + }, + { + "epoch": 0.5017421602787456, + "grad_norm": 0.7203962118826617, + "learning_rate": 9.866264438789573e-06, + "loss": 0.686, + "step": 96 + }, + { + "epoch": 0.5069686411149826, + "grad_norm": 0.6785442509634554, + "learning_rate": 9.85916677328104e-06, + "loss": 0.7037, + "step": 97 + }, + { + "epoch": 0.5121951219512195, + "grad_norm": 0.5917891054628419, + "learning_rate": 9.851888288072053e-06, + "loss": 0.7037, + "step": 98 + }, + { + "epoch": 0.5174216027874564, + "grad_norm": 0.7601539373800206, + "learning_rate": 9.844429254010184e-06, + "loss": 0.6969, + "step": 99 + }, + { + "epoch": 0.5226480836236934, + "grad_norm": 0.6020652320578571, + "learning_rate": 9.836789948661602e-06, + "loss": 0.6879, + "step": 100 + }, + { + "epoch": 0.5278745644599303, + "grad_norm": 0.6764576509816881, + "learning_rate": 9.828970656300743e-06, + "loss": 0.6898, + "step": 101 + }, + { + "epoch": 0.5331010452961672, + "grad_norm": 0.6666874805819255, + "learning_rate": 9.82097166789974e-06, + "loss": 0.6778, + "step": 102 + }, + { + "epoch": 0.5383275261324042, + "grad_norm": 0.7360464789092225, + "learning_rate": 9.81279328111758e-06, + "loss": 0.6882, + "step": 103 + }, + { + "epoch": 0.5435540069686411, + "grad_norm": 0.701626438763124, + "learning_rate": 9.804435800289047e-06, + "loss": 0.6893, + "step": 104 + }, + { + "epoch": 0.5487804878048781, + "grad_norm": 0.7646586589346112, + "learning_rate": 9.795899536413383e-06, + "loss": 0.663, + "step": 105 + }, + { + "epoch": 0.554006968641115, + "grad_norm": 0.7827135637222683, + "learning_rate": 9.787184807142713e-06, + "loss": 0.6782, + "step": 106 + }, + { + "epoch": 0.5592334494773519, + "grad_norm": 0.7963355955603488, + "learning_rate": 9.778291936770241e-06, + "loss": 0.6948, + "step": 107 + }, + { + "epoch": 0.5644599303135889, + "grad_norm": 0.9185384976633354, + "learning_rate": 9.769221256218165e-06, + "loss": 0.6855, + "step": 108 + }, + { + "epoch": 0.5696864111498258, + "grad_norm": 0.6715876776695767, + "learning_rate": 9.759973103025369e-06, + "loss": 0.6692, + "step": 109 + }, + { + "epoch": 0.5749128919860628, + "grad_norm": 1.2389220927650733, + "learning_rate": 9.750547821334868e-06, + "loss": 0.6881, + "step": 110 + }, + { + "epoch": 0.5801393728222997, + "grad_norm": 0.7818470562308032, + "learning_rate": 9.740945761880993e-06, + "loss": 0.6483, + "step": 111 + }, + { + "epoch": 0.5853658536585366, + "grad_norm": 0.8194633115862917, + "learning_rate": 9.731167281976346e-06, + "loss": 0.6573, + "step": 112 + }, + { + "epoch": 0.5905923344947736, + "grad_norm": 0.8554081467672775, + "learning_rate": 9.721212745498493e-06, + "loss": 0.6831, + "step": 113 + }, + { + "epoch": 0.5958188153310104, + "grad_norm": 0.6301357489652583, + "learning_rate": 9.711082522876445e-06, + "loss": 0.6883, + "step": 114 + }, + { + "epoch": 0.6010452961672473, + "grad_norm": 0.7320145359964577, + "learning_rate": 9.700776991076846e-06, + "loss": 0.6826, + "step": 115 + }, + { + "epoch": 0.6062717770034843, + "grad_norm": 0.7164618151118382, + "learning_rate": 9.690296533589967e-06, + "loss": 0.6669, + "step": 116 + }, + { + "epoch": 0.6114982578397212, + "grad_norm": 0.6788237892173536, + "learning_rate": 9.679641540415428e-06, + "loss": 0.6659, + "step": 117 + }, + { + "epoch": 0.6167247386759582, + "grad_norm": 0.6158473714288532, + "learning_rate": 9.66881240804768e-06, + "loss": 0.6597, + "step": 118 + }, + { + "epoch": 0.6219512195121951, + "grad_norm": 0.6555526405519565, + "learning_rate": 9.657809539461256e-06, + "loss": 0.6831, + "step": 119 + }, + { + "epoch": 0.627177700348432, + "grad_norm": 0.6887980438356484, + "learning_rate": 9.64663334409578e-06, + "loss": 0.666, + "step": 120 + }, + { + "epoch": 0.632404181184669, + "grad_norm": 0.5979509900819844, + "learning_rate": 9.635284237840721e-06, + "loss": 0.6553, + "step": 121 + }, + { + "epoch": 0.6376306620209059, + "grad_norm": 0.7294362846964269, + "learning_rate": 9.623762643019927e-06, + "loss": 0.6771, + "step": 122 + }, + { + "epoch": 0.6428571428571429, + "grad_norm": 0.7545085300162823, + "learning_rate": 9.612068988375898e-06, + "loss": 0.6715, + "step": 123 + }, + { + "epoch": 0.6480836236933798, + "grad_norm": 0.6749790083440244, + "learning_rate": 9.60020370905384e-06, + "loss": 0.6514, + "step": 124 + }, + { + "epoch": 0.6533101045296167, + "grad_norm": 0.804530126401735, + "learning_rate": 9.588167246585474e-06, + "loss": 0.6459, + "step": 125 + }, + { + "epoch": 0.6585365853658537, + "grad_norm": 0.6831220443498838, + "learning_rate": 9.575960048872595e-06, + "loss": 0.6896, + "step": 126 + }, + { + "epoch": 0.6637630662020906, + "grad_norm": 0.5810171537948514, + "learning_rate": 9.563582570170418e-06, + "loss": 0.6613, + "step": 127 + }, + { + "epoch": 0.6689895470383276, + "grad_norm": 0.7304494902535995, + "learning_rate": 9.551035271070665e-06, + "loss": 0.6516, + "step": 128 + }, + { + "epoch": 0.6742160278745645, + "grad_norm": 0.6119862390653155, + "learning_rate": 9.538318618484426e-06, + "loss": 0.6618, + "step": 129 + }, + { + "epoch": 0.6794425087108014, + "grad_norm": 0.6430165539813878, + "learning_rate": 9.52543308562479e-06, + "loss": 0.6864, + "step": 130 + }, + { + "epoch": 0.6846689895470384, + "grad_norm": 0.6194884070250605, + "learning_rate": 9.512379151989229e-06, + "loss": 0.6784, + "step": 131 + }, + { + "epoch": 0.6898954703832753, + "grad_norm": 0.5516355539801995, + "learning_rate": 9.499157303341761e-06, + "loss": 0.6653, + "step": 132 + }, + { + "epoch": 0.6951219512195121, + "grad_norm": 0.622640994125776, + "learning_rate": 9.485768031694872e-06, + "loss": 0.6731, + "step": 133 + }, + { + "epoch": 0.7003484320557491, + "grad_norm": 0.547286279646913, + "learning_rate": 9.4722118352912e-06, + "loss": 0.6663, + "step": 134 + }, + { + "epoch": 0.705574912891986, + "grad_norm": 0.6363064057591127, + "learning_rate": 9.458489218585003e-06, + "loss": 0.655, + "step": 135 + }, + { + "epoch": 0.710801393728223, + "grad_norm": 0.6134952050030124, + "learning_rate": 9.44460069222339e-06, + "loss": 0.6749, + "step": 136 + }, + { + "epoch": 0.7160278745644599, + "grad_norm": 0.5937836538107625, + "learning_rate": 9.430546773027302e-06, + "loss": 0.6686, + "step": 137 + }, + { + "epoch": 0.7212543554006968, + "grad_norm": 0.6644117521702412, + "learning_rate": 9.416327983972304e-06, + "loss": 0.6594, + "step": 138 + }, + { + "epoch": 0.7264808362369338, + "grad_norm": 0.6220644455779103, + "learning_rate": 9.401944854169103e-06, + "loss": 0.6749, + "step": 139 + }, + { + "epoch": 0.7317073170731707, + "grad_norm": 0.6547771063435059, + "learning_rate": 9.38739791884387e-06, + "loss": 0.6579, + "step": 140 + }, + { + "epoch": 0.7369337979094077, + "grad_norm": 0.561284464609663, + "learning_rate": 9.372687719318316e-06, + "loss": 0.681, + "step": 141 + }, + { + "epoch": 0.7421602787456446, + "grad_norm": 0.6038846576238117, + "learning_rate": 9.35781480298956e-06, + "loss": 0.6666, + "step": 142 + }, + { + "epoch": 0.7473867595818815, + "grad_norm": 0.572240770754845, + "learning_rate": 9.342779723309746e-06, + "loss": 0.6238, + "step": 143 + }, + { + "epoch": 0.7526132404181185, + "grad_norm": 0.5890147611510671, + "learning_rate": 9.327583039765453e-06, + "loss": 0.6637, + "step": 144 + }, + { + "epoch": 0.7578397212543554, + "grad_norm": 0.6636633864116531, + "learning_rate": 9.31222531785688e-06, + "loss": 0.6523, + "step": 145 + }, + { + "epoch": 0.7630662020905923, + "grad_norm": 0.6188433137259545, + "learning_rate": 9.296707129076794e-06, + "loss": 0.6626, + "step": 146 + }, + { + "epoch": 0.7682926829268293, + "grad_norm": 0.6163886375278169, + "learning_rate": 9.281029050889274e-06, + "loss": 0.6786, + "step": 147 + }, + { + "epoch": 0.7735191637630662, + "grad_norm": 0.7346550992330867, + "learning_rate": 9.26519166670821e-06, + "loss": 0.6861, + "step": 148 + }, + { + "epoch": 0.7787456445993032, + "grad_norm": 0.5852860888717738, + "learning_rate": 9.2491955658756e-06, + "loss": 0.6591, + "step": 149 + }, + { + "epoch": 0.7839721254355401, + "grad_norm": 0.7028963677577197, + "learning_rate": 9.233041343639623e-06, + "loss": 0.6881, + "step": 150 + }, + { + "epoch": 0.789198606271777, + "grad_norm": 0.8189320800786853, + "learning_rate": 9.216729601132481e-06, + "loss": 0.6702, + "step": 151 + }, + { + "epoch": 0.794425087108014, + "grad_norm": 0.5963261479645, + "learning_rate": 9.200260945348034e-06, + "loss": 0.6652, + "step": 152 + }, + { + "epoch": 0.7996515679442509, + "grad_norm": 0.6745799083758508, + "learning_rate": 9.183635989119211e-06, + "loss": 0.6569, + "step": 153 + }, + { + "epoch": 0.8048780487804879, + "grad_norm": 0.7674431433443214, + "learning_rate": 9.166855351095205e-06, + "loss": 0.6629, + "step": 154 + }, + { + "epoch": 0.8101045296167247, + "grad_norm": 0.5864935078587289, + "learning_rate": 9.149919655718453e-06, + "loss": 0.6615, + "step": 155 + }, + { + "epoch": 0.8153310104529616, + "grad_norm": 0.6569771197412858, + "learning_rate": 9.132829533201397e-06, + "loss": 0.6321, + "step": 156 + }, + { + "epoch": 0.8205574912891986, + "grad_norm": 0.6855458963431387, + "learning_rate": 9.115585619503039e-06, + "loss": 0.6471, + "step": 157 + }, + { + "epoch": 0.8257839721254355, + "grad_norm": 0.5765451182091219, + "learning_rate": 9.098188556305262e-06, + "loss": 0.6748, + "step": 158 + }, + { + "epoch": 0.8310104529616724, + "grad_norm": 0.6567732753183342, + "learning_rate": 9.080638990988971e-06, + "loss": 0.6564, + "step": 159 + }, + { + "epoch": 0.8362369337979094, + "grad_norm": 0.636552981471604, + "learning_rate": 9.062937576609983e-06, + "loss": 0.654, + "step": 160 + }, + { + "epoch": 0.8414634146341463, + "grad_norm": 0.5529034964515249, + "learning_rate": 9.045084971874738e-06, + "loss": 0.6558, + "step": 161 + }, + { + "epoch": 0.8466898954703833, + "grad_norm": 0.5893696671833625, + "learning_rate": 9.027081841115784e-06, + "loss": 0.6663, + "step": 162 + }, + { + "epoch": 0.8519163763066202, + "grad_norm": 0.5667170304864082, + "learning_rate": 9.008928854267054e-06, + "loss": 0.6443, + "step": 163 + }, + { + "epoch": 0.8571428571428571, + "grad_norm": 0.5725785658325226, + "learning_rate": 8.99062668683894e-06, + "loss": 0.6536, + "step": 164 + }, + { + "epoch": 0.8623693379790941, + "grad_norm": 0.6060232996236128, + "learning_rate": 8.97217601989315e-06, + "loss": 0.6579, + "step": 165 + }, + { + "epoch": 0.867595818815331, + "grad_norm": 0.5509869618020639, + "learning_rate": 8.95357754001737e-06, + "loss": 0.6713, + "step": 166 + }, + { + "epoch": 0.872822299651568, + "grad_norm": 0.6324223806192756, + "learning_rate": 8.934831939299715e-06, + "loss": 0.6696, + "step": 167 + }, + { + "epoch": 0.8780487804878049, + "grad_norm": 0.6405745054270299, + "learning_rate": 8.91593991530297e-06, + "loss": 0.6584, + "step": 168 + }, + { + "epoch": 0.8832752613240418, + "grad_norm": 0.6307439054892403, + "learning_rate": 8.896902171038629e-06, + "loss": 0.6529, + "step": 169 + }, + { + "epoch": 0.8885017421602788, + "grad_norm": 0.6611063399387049, + "learning_rate": 8.877719414940751e-06, + "loss": 0.6816, + "step": 170 + }, + { + "epoch": 0.8937282229965157, + "grad_norm": 0.5327557983597507, + "learning_rate": 8.85839236083958e-06, + "loss": 0.6591, + "step": 171 + }, + { + "epoch": 0.8989547038327527, + "grad_norm": 0.6306768954606544, + "learning_rate": 8.838921727934992e-06, + "loss": 0.6725, + "step": 172 + }, + { + "epoch": 0.9041811846689896, + "grad_norm": 0.5906681591023982, + "learning_rate": 8.819308240769726e-06, + "loss": 0.663, + "step": 173 + }, + { + "epoch": 0.9094076655052264, + "grad_norm": 0.6242722153083872, + "learning_rate": 8.799552629202424e-06, + "loss": 0.6593, + "step": 174 + }, + { + "epoch": 0.9146341463414634, + "grad_norm": 0.6206172349107745, + "learning_rate": 8.779655628380479e-06, + "loss": 0.6366, + "step": 175 + }, + { + "epoch": 0.9198606271777003, + "grad_norm": 0.6446754833762357, + "learning_rate": 8.759617978712667e-06, + "loss": 0.6588, + "step": 176 + }, + { + "epoch": 0.9250871080139372, + "grad_norm": 0.6524808843585924, + "learning_rate": 8.7394404258416e-06, + "loss": 0.6708, + "step": 177 + }, + { + "epoch": 0.9303135888501742, + "grad_norm": 0.5695275564016344, + "learning_rate": 8.71912372061598e-06, + "loss": 0.6581, + "step": 178 + }, + { + "epoch": 0.9355400696864111, + "grad_norm": 0.5524125516832253, + "learning_rate": 8.69866861906266e-06, + "loss": 0.675, + "step": 179 + }, + { + "epoch": 0.9407665505226481, + "grad_norm": 0.6301898047784469, + "learning_rate": 8.678075882358506e-06, + "loss": 0.6315, + "step": 180 + }, + { + "epoch": 0.945993031358885, + "grad_norm": 0.5726932230656162, + "learning_rate": 8.657346276802071e-06, + "loss": 0.6407, + "step": 181 + }, + { + "epoch": 0.9512195121951219, + "grad_norm": 0.6267676856772942, + "learning_rate": 8.636480573785089e-06, + "loss": 0.6665, + "step": 182 + }, + { + "epoch": 0.9564459930313589, + "grad_norm": 0.6244142776173546, + "learning_rate": 8.615479549763756e-06, + "loss": 0.6618, + "step": 183 + }, + { + "epoch": 0.9616724738675958, + "grad_norm": 0.6177405231356075, + "learning_rate": 8.594343986229854e-06, + "loss": 0.6773, + "step": 184 + }, + { + "epoch": 0.9668989547038328, + "grad_norm": 0.5988900835082392, + "learning_rate": 8.57307466968165e-06, + "loss": 0.6429, + "step": 185 + }, + { + "epoch": 0.9721254355400697, + "grad_norm": 0.6447854583228403, + "learning_rate": 8.551672391594646e-06, + "loss": 0.6735, + "step": 186 + }, + { + "epoch": 0.9773519163763066, + "grad_norm": 0.5761133455065623, + "learning_rate": 8.530137948392113e-06, + "loss": 0.6614, + "step": 187 + }, + { + "epoch": 0.9825783972125436, + "grad_norm": 0.5943974371608253, + "learning_rate": 8.508472141415468e-06, + "loss": 0.6539, + "step": 188 + }, + { + "epoch": 0.9878048780487805, + "grad_norm": 0.6718313091561632, + "learning_rate": 8.48667577689444e-06, + "loss": 0.6346, + "step": 189 + }, + { + "epoch": 0.9930313588850174, + "grad_norm": 0.5856014973725608, + "learning_rate": 8.46474966591708e-06, + "loss": 0.6626, + "step": 190 + }, + { + "epoch": 0.9982578397212544, + "grad_norm": 0.6113432602736558, + "learning_rate": 8.442694624399576e-06, + "loss": 0.6604, + "step": 191 + }, + { + "epoch": 1.0034843205574913, + "grad_norm": 1.1692152399954596, + "learning_rate": 8.420511473055887e-06, + "loss": 1.0489, + "step": 192 + }, + { + "epoch": 1.0087108013937283, + "grad_norm": 0.6145614135481637, + "learning_rate": 8.398201037367202e-06, + "loss": 0.6419, + "step": 193 + }, + { + "epoch": 1.0139372822299653, + "grad_norm": 0.6268987577515908, + "learning_rate": 8.37576414755123e-06, + "loss": 0.6137, + "step": 194 + }, + { + "epoch": 1.019163763066202, + "grad_norm": 0.6416953015407134, + "learning_rate": 8.3532016385313e-06, + "loss": 0.6243, + "step": 195 + }, + { + "epoch": 1.024390243902439, + "grad_norm": 0.5704666555598586, + "learning_rate": 8.330514349905295e-06, + "loss": 0.6368, + "step": 196 + }, + { + "epoch": 1.029616724738676, + "grad_norm": 0.503382880864932, + "learning_rate": 8.307703125914397e-06, + "loss": 0.5435, + "step": 197 + }, + { + "epoch": 1.0348432055749128, + "grad_norm": 0.5773976279224134, + "learning_rate": 8.284768815411693e-06, + "loss": 0.6031, + "step": 198 + }, + { + "epoch": 1.0400696864111498, + "grad_norm": 0.6463491533346394, + "learning_rate": 8.261712271830564e-06, + "loss": 0.5943, + "step": 199 + }, + { + "epoch": 1.0452961672473868, + "grad_norm": 0.6023840946052278, + "learning_rate": 8.23853435315295e-06, + "loss": 0.5491, + "step": 200 + }, + { + "epoch": 1.0505226480836236, + "grad_norm": 0.5738792581365361, + "learning_rate": 8.215235921877403e-06, + "loss": 0.5604, + "step": 201 + }, + { + "epoch": 1.0557491289198606, + "grad_norm": 0.6156147642415088, + "learning_rate": 8.191817844986998e-06, + "loss": 0.6434, + "step": 202 + }, + { + "epoch": 1.0609756097560976, + "grad_norm": 0.5569699792461741, + "learning_rate": 8.168280993917078e-06, + "loss": 0.5594, + "step": 203 + }, + { + "epoch": 1.0662020905923344, + "grad_norm": 0.5657310358177506, + "learning_rate": 8.144626244522812e-06, + "loss": 0.5686, + "step": 204 + }, + { + "epoch": 1.0714285714285714, + "grad_norm": 0.6672649446625757, + "learning_rate": 8.120854477046621e-06, + "loss": 0.6803, + "step": 205 + }, + { + "epoch": 1.0766550522648084, + "grad_norm": 0.5612168930959153, + "learning_rate": 8.096966576085406e-06, + "loss": 0.5824, + "step": 206 + }, + { + "epoch": 1.0818815331010452, + "grad_norm": 0.6579205469061564, + "learning_rate": 8.072963430557636e-06, + "loss": 0.6028, + "step": 207 + }, + { + "epoch": 1.0871080139372822, + "grad_norm": 0.5598751666256221, + "learning_rate": 8.048845933670274e-06, + "loss": 0.5777, + "step": 208 + }, + { + "epoch": 1.0923344947735192, + "grad_norm": 0.5843330235385993, + "learning_rate": 8.024614982885527e-06, + "loss": 0.5577, + "step": 209 + }, + { + "epoch": 1.0975609756097562, + "grad_norm": 0.601858208353747, + "learning_rate": 8.00027147988747e-06, + "loss": 0.6143, + "step": 210 + }, + { + "epoch": 1.102787456445993, + "grad_norm": 0.627628607597956, + "learning_rate": 7.975816330548466e-06, + "loss": 0.596, + "step": 211 + }, + { + "epoch": 1.10801393728223, + "grad_norm": 0.6241333668783621, + "learning_rate": 7.951250444895485e-06, + "loss": 0.6494, + "step": 212 + }, + { + "epoch": 1.113240418118467, + "grad_norm": 0.5382934099983673, + "learning_rate": 7.92657473707621e-06, + "loss": 0.5217, + "step": 213 + }, + { + "epoch": 1.1184668989547037, + "grad_norm": 0.6953324804344473, + "learning_rate": 7.901790125325049e-06, + "loss": 0.6941, + "step": 214 + }, + { + "epoch": 1.1236933797909407, + "grad_norm": 0.5453365037414081, + "learning_rate": 7.876897531928943e-06, + "loss": 0.6076, + "step": 215 + }, + { + "epoch": 1.1289198606271778, + "grad_norm": 0.5736100460893016, + "learning_rate": 7.851897883193057e-06, + "loss": 0.5852, + "step": 216 + }, + { + "epoch": 1.1341463414634148, + "grad_norm": 0.5648285470025594, + "learning_rate": 7.82679210940631e-06, + "loss": 0.6033, + "step": 217 + }, + { + "epoch": 1.1393728222996515, + "grad_norm": 0.5867845846947239, + "learning_rate": 7.801581144806752e-06, + "loss": 0.5587, + "step": 218 + }, + { + "epoch": 1.1445993031358885, + "grad_norm": 0.5513023482330085, + "learning_rate": 7.7762659275468e-06, + "loss": 0.618, + "step": 219 + }, + { + "epoch": 1.1498257839721253, + "grad_norm": 0.6153474010859067, + "learning_rate": 7.750847399658336e-06, + "loss": 0.6282, + "step": 220 + }, + { + "epoch": 1.1550522648083623, + "grad_norm": 0.4877966585426567, + "learning_rate": 7.725326507017644e-06, + "loss": 0.5451, + "step": 221 + }, + { + "epoch": 1.1602787456445993, + "grad_norm": 0.5463512600607151, + "learning_rate": 7.699704199310204e-06, + "loss": 0.5972, + "step": 222 + }, + { + "epoch": 1.1655052264808363, + "grad_norm": 0.6352304968816307, + "learning_rate": 7.673981429995372e-06, + "loss": 0.6114, + "step": 223 + }, + { + "epoch": 1.170731707317073, + "grad_norm": 0.510832677269982, + "learning_rate": 7.648159156270884e-06, + "loss": 0.6268, + "step": 224 + }, + { + "epoch": 1.17595818815331, + "grad_norm": 0.5814622275101878, + "learning_rate": 7.622238339037248e-06, + "loss": 0.6141, + "step": 225 + }, + { + "epoch": 1.181184668989547, + "grad_norm": 0.5818228914475463, + "learning_rate": 7.596219942861971e-06, + "loss": 0.5655, + "step": 226 + }, + { + "epoch": 1.1864111498257839, + "grad_norm": 0.5842183364885295, + "learning_rate": 7.570104935943685e-06, + "loss": 0.5983, + "step": 227 + }, + { + "epoch": 1.1916376306620209, + "grad_norm": 0.5752307733655048, + "learning_rate": 7.5438942900761035e-06, + "loss": 0.6072, + "step": 228 + }, + { + "epoch": 1.1968641114982579, + "grad_norm": 0.585743260967966, + "learning_rate": 7.517588980611864e-06, + "loss": 0.6306, + "step": 229 + }, + { + "epoch": 1.202090592334495, + "grad_norm": 0.48400699770777905, + "learning_rate": 7.491189986426236e-06, + "loss": 0.523, + "step": 230 + }, + { + "epoch": 1.2073170731707317, + "grad_norm": 0.6000420590770226, + "learning_rate": 7.464698289880689e-06, + "loss": 0.6248, + "step": 231 + }, + { + "epoch": 1.2125435540069687, + "grad_norm": 0.566825613388456, + "learning_rate": 7.438114876786344e-06, + "loss": 0.5892, + "step": 232 + }, + { + "epoch": 1.2177700348432055, + "grad_norm": 0.5942135634459118, + "learning_rate": 7.411440736367281e-06, + "loss": 0.604, + "step": 233 + }, + { + "epoch": 1.2229965156794425, + "grad_norm": 0.5308639194617243, + "learning_rate": 7.384676861223738e-06, + "loss": 0.5938, + "step": 234 + }, + { + "epoch": 1.2282229965156795, + "grad_norm": 0.5233297325602637, + "learning_rate": 7.3578242472951635e-06, + "loss": 0.5606, + "step": 235 + }, + { + "epoch": 1.2334494773519165, + "grad_norm": 0.5506498491313724, + "learning_rate": 7.330883893823164e-06, + "loss": 0.6321, + "step": 236 + }, + { + "epoch": 1.2386759581881532, + "grad_norm": 0.5032393653634389, + "learning_rate": 7.303856803314313e-06, + "loss": 0.5772, + "step": 237 + }, + { + "epoch": 1.2439024390243902, + "grad_norm": 0.5516215897044785, + "learning_rate": 7.276743981502856e-06, + "loss": 0.6249, + "step": 238 + }, + { + "epoch": 1.2491289198606272, + "grad_norm": 0.5922013934962067, + "learning_rate": 7.249546437313273e-06, + "loss": 0.5742, + "step": 239 + }, + { + "epoch": 1.254355400696864, + "grad_norm": 0.563594800466747, + "learning_rate": 7.22226518282274e-06, + "loss": 0.5931, + "step": 240 + }, + { + "epoch": 1.259581881533101, + "grad_norm": 0.5865049138488002, + "learning_rate": 7.194901233223471e-06, + "loss": 0.6026, + "step": 241 + }, + { + "epoch": 1.264808362369338, + "grad_norm": 0.6049741584214127, + "learning_rate": 7.167455606784936e-06, + "loss": 0.5973, + "step": 242 + }, + { + "epoch": 1.270034843205575, + "grad_norm": 0.600516789714151, + "learning_rate": 7.139929324815965e-06, + "loss": 0.639, + "step": 243 + }, + { + "epoch": 1.2752613240418118, + "grad_norm": 0.5799862799629144, + "learning_rate": 7.112323411626756e-06, + "loss": 0.5975, + "step": 244 + }, + { + "epoch": 1.2804878048780488, + "grad_norm": 0.608405822867294, + "learning_rate": 7.084638894490744e-06, + "loss": 0.5932, + "step": 245 + }, + { + "epoch": 1.2857142857142856, + "grad_norm": 0.6086512791994181, + "learning_rate": 7.056876803606384e-06, + "loss": 0.6211, + "step": 246 + }, + { + "epoch": 1.2909407665505226, + "grad_norm": 0.6114934942027832, + "learning_rate": 7.029038172058809e-06, + "loss": 0.5816, + "step": 247 + }, + { + "epoch": 1.2961672473867596, + "grad_norm": 0.5531245874896416, + "learning_rate": 7.00112403578139e-06, + "loss": 0.5793, + "step": 248 + }, + { + "epoch": 1.3013937282229966, + "grad_norm": 0.590859726592878, + "learning_rate": 6.9731354335171885e-06, + "loss": 0.5969, + "step": 249 + }, + { + "epoch": 1.3066202090592334, + "grad_norm": 0.6199140175680848, + "learning_rate": 6.945073406780296e-06, + "loss": 0.6263, + "step": 250 + }, + { + "epoch": 1.3118466898954704, + "grad_norm": 0.49378151455087976, + "learning_rate": 6.916938999817085e-06, + "loss": 0.6258, + "step": 251 + }, + { + "epoch": 1.3170731707317074, + "grad_norm": 0.5481220680272908, + "learning_rate": 6.888733259567343e-06, + "loss": 0.5697, + "step": 252 + }, + { + "epoch": 1.3222996515679442, + "grad_norm": 0.5601237104950061, + "learning_rate": 6.860457235625322e-06, + "loss": 0.6192, + "step": 253 + }, + { + "epoch": 1.3275261324041812, + "grad_norm": 0.5562695792344781, + "learning_rate": 6.832111980200672e-06, + "loss": 0.5595, + "step": 254 + }, + { + "epoch": 1.3327526132404182, + "grad_norm": 0.6375068604321416, + "learning_rate": 6.803698548079294e-06, + "loss": 0.6001, + "step": 255 + }, + { + "epoch": 1.3379790940766552, + "grad_norm": 0.5443785529911263, + "learning_rate": 6.775217996584082e-06, + "loss": 0.5915, + "step": 256 + }, + { + "epoch": 1.343205574912892, + "grad_norm": 0.5408122608427677, + "learning_rate": 6.746671385535586e-06, + "loss": 0.5953, + "step": 257 + }, + { + "epoch": 1.348432055749129, + "grad_norm": 0.5539163863396951, + "learning_rate": 6.7180597772125665e-06, + "loss": 0.6388, + "step": 258 + }, + { + "epoch": 1.3536585365853657, + "grad_norm": 0.5362462583433603, + "learning_rate": 6.689384236312465e-06, + "loss": 0.5838, + "step": 259 + }, + { + "epoch": 1.3588850174216027, + "grad_norm": 0.541689780691623, + "learning_rate": 6.660645829911794e-06, + "loss": 0.6318, + "step": 260 + }, + { + "epoch": 1.3641114982578397, + "grad_norm": 0.5106593953968394, + "learning_rate": 6.631845627426418e-06, + "loss": 0.5425, + "step": 261 + }, + { + "epoch": 1.3693379790940767, + "grad_norm": 0.49403851854670217, + "learning_rate": 6.602984700571758e-06, + "loss": 0.5305, + "step": 262 + }, + { + "epoch": 1.3745644599303135, + "grad_norm": 0.5967203227127262, + "learning_rate": 6.574064123322925e-06, + "loss": 0.6405, + "step": 263 + }, + { + "epoch": 1.3797909407665505, + "grad_norm": 0.5601246715123179, + "learning_rate": 6.545084971874738e-06, + "loss": 0.5802, + "step": 264 + }, + { + "epoch": 1.3850174216027875, + "grad_norm": 0.5342203081001657, + "learning_rate": 6.516048324601685e-06, + "loss": 0.6166, + "step": 265 + }, + { + "epoch": 1.3902439024390243, + "grad_norm": 0.5175415102386944, + "learning_rate": 6.486955262017794e-06, + "loss": 0.6049, + "step": 266 + }, + { + "epoch": 1.3954703832752613, + "grad_norm": 0.603808078724887, + "learning_rate": 6.457806866736424e-06, + "loss": 0.615, + "step": 267 + }, + { + "epoch": 1.4006968641114983, + "grad_norm": 0.5271092125681837, + "learning_rate": 6.42860422342998e-06, + "loss": 0.522, + "step": 268 + }, + { + "epoch": 1.4059233449477353, + "grad_norm": 0.5871002546738227, + "learning_rate": 6.399348418789545e-06, + "loss": 0.6314, + "step": 269 + }, + { + "epoch": 1.411149825783972, + "grad_norm": 0.5188920938550411, + "learning_rate": 6.37004054148445e-06, + "loss": 0.5822, + "step": 270 + }, + { + "epoch": 1.416376306620209, + "grad_norm": 0.5152138837098115, + "learning_rate": 6.3406816821217554e-06, + "loss": 0.6093, + "step": 271 + }, + { + "epoch": 1.4216027874564459, + "grad_norm": 0.513754045434498, + "learning_rate": 6.311272933205672e-06, + "loss": 0.5832, + "step": 272 + }, + { + "epoch": 1.4268292682926829, + "grad_norm": 0.4912944860658243, + "learning_rate": 6.281815389096903e-06, + "loss": 0.529, + "step": 273 + }, + { + "epoch": 1.4320557491289199, + "grad_norm": 0.5427353767757749, + "learning_rate": 6.2523101459719204e-06, + "loss": 0.6526, + "step": 274 + }, + { + "epoch": 1.4372822299651569, + "grad_norm": 0.5535697011306765, + "learning_rate": 6.222758301782183e-06, + "loss": 0.6282, + "step": 275 + }, + { + "epoch": 1.4425087108013936, + "grad_norm": 0.5162479310938117, + "learning_rate": 6.193160956213262e-06, + "loss": 0.5903, + "step": 276 + }, + { + "epoch": 1.4477351916376306, + "grad_norm": 0.5604814223022786, + "learning_rate": 6.163519210643939e-06, + "loss": 0.6083, + "step": 277 + }, + { + "epoch": 1.4529616724738676, + "grad_norm": 0.5139952218594641, + "learning_rate": 6.133834168105206e-06, + "loss": 0.5271, + "step": 278 + }, + { + "epoch": 1.4581881533101044, + "grad_norm": 0.6229450021349342, + "learning_rate": 6.104106933239227e-06, + "loss": 0.5636, + "step": 279 + }, + { + "epoch": 1.4634146341463414, + "grad_norm": 0.5408488715069601, + "learning_rate": 6.07433861225823e-06, + "loss": 0.6205, + "step": 280 + }, + { + "epoch": 1.4686411149825784, + "grad_norm": 0.49674309270840106, + "learning_rate": 6.044530312903343e-06, + "loss": 0.5794, + "step": 281 + }, + { + "epoch": 1.4738675958188154, + "grad_norm": 0.582431202829567, + "learning_rate": 6.014683144403375e-06, + "loss": 0.6167, + "step": 282 + }, + { + "epoch": 1.4790940766550522, + "grad_norm": 0.573524016791654, + "learning_rate": 5.9847982174335314e-06, + "loss": 0.6008, + "step": 283 + }, + { + "epoch": 1.4843205574912892, + "grad_norm": 0.5130183259716176, + "learning_rate": 5.954876644074092e-06, + "loss": 0.6057, + "step": 284 + }, + { + "epoch": 1.489547038327526, + "grad_norm": 0.547570250155865, + "learning_rate": 5.924919537769025e-06, + "loss": 0.5872, + "step": 285 + }, + { + "epoch": 1.494773519163763, + "grad_norm": 0.5786698298674792, + "learning_rate": 5.894928013284551e-06, + "loss": 0.549, + "step": 286 + }, + { + "epoch": 1.5, + "grad_norm": 0.5765527388977582, + "learning_rate": 5.8649031866676685e-06, + "loss": 0.6325, + "step": 287 + }, + { + "epoch": 1.505226480836237, + "grad_norm": 0.4800435309675829, + "learning_rate": 5.834846175204612e-06, + "loss": 0.5278, + "step": 288 + }, + { + "epoch": 1.510452961672474, + "grad_norm": 0.6218236849239587, + "learning_rate": 5.804758097379281e-06, + "loss": 0.6634, + "step": 289 + }, + { + "epoch": 1.5156794425087108, + "grad_norm": 0.5073235422648865, + "learning_rate": 5.774640072831622e-06, + "loss": 0.5773, + "step": 290 + }, + { + "epoch": 1.5209059233449478, + "grad_norm": 0.5687256206289278, + "learning_rate": 5.74449322231596e-06, + "loss": 0.6216, + "step": 291 + }, + { + "epoch": 1.5261324041811846, + "grad_norm": 0.495289281164082, + "learning_rate": 5.714318667659295e-06, + "loss": 0.5697, + "step": 292 + }, + { + "epoch": 1.5313588850174216, + "grad_norm": 0.5071599473157437, + "learning_rate": 5.684117531719552e-06, + "loss": 0.5902, + "step": 293 + }, + { + "epoch": 1.5365853658536586, + "grad_norm": 0.5465492422582399, + "learning_rate": 5.653890938343806e-06, + "loss": 0.6084, + "step": 294 + }, + { + "epoch": 1.5418118466898956, + "grad_norm": 0.5794183886322944, + "learning_rate": 5.623640012326455e-06, + "loss": 0.6074, + "step": 295 + }, + { + "epoch": 1.5470383275261324, + "grad_norm": 0.5077288815232027, + "learning_rate": 5.593365879367361e-06, + "loss": 0.559, + "step": 296 + }, + { + "epoch": 1.5522648083623694, + "grad_norm": 0.535785650486145, + "learning_rate": 5.56306966602997e-06, + "loss": 0.6259, + "step": 297 + }, + { + "epoch": 1.5574912891986061, + "grad_norm": 0.5574339114144872, + "learning_rate": 5.532752499699381e-06, + "loss": 0.6274, + "step": 298 + }, + { + "epoch": 1.5627177700348431, + "grad_norm": 0.4864171169075875, + "learning_rate": 5.502415508540401e-06, + "loss": 0.5689, + "step": 299 + }, + { + "epoch": 1.5679442508710801, + "grad_norm": 0.5395355580960868, + "learning_rate": 5.472059821455554e-06, + "loss": 0.615, + "step": 300 + }, + { + "epoch": 1.5731707317073171, + "grad_norm": 0.5367333644494985, + "learning_rate": 5.441686568043086e-06, + "loss": 0.6209, + "step": 301 + }, + { + "epoch": 1.5783972125435541, + "grad_norm": 0.5629949580706008, + "learning_rate": 5.411296878554918e-06, + "loss": 0.5778, + "step": 302 + }, + { + "epoch": 1.583623693379791, + "grad_norm": 0.5279025042856722, + "learning_rate": 5.380891883854591e-06, + "loss": 0.5891, + "step": 303 + }, + { + "epoch": 1.588850174216028, + "grad_norm": 0.529056626502548, + "learning_rate": 5.3504727153751865e-06, + "loss": 0.5781, + "step": 304 + }, + { + "epoch": 1.5940766550522647, + "grad_norm": 0.5143855575664987, + "learning_rate": 5.320040505077222e-06, + "loss": 0.6108, + "step": 305 + }, + { + "epoch": 1.5993031358885017, + "grad_norm": 0.5496043322415672, + "learning_rate": 5.289596385406527e-06, + "loss": 0.5925, + "step": 306 + }, + { + "epoch": 1.6045296167247387, + "grad_norm": 0.45788921944124966, + "learning_rate": 5.259141489252104e-06, + "loss": 0.5211, + "step": 307 + }, + { + "epoch": 1.6097560975609757, + "grad_norm": 0.5610785336406, + "learning_rate": 5.228676949903974e-06, + "loss": 0.6835, + "step": 308 + }, + { + "epoch": 1.6149825783972127, + "grad_norm": 0.5041137193985311, + "learning_rate": 5.198203901010993e-06, + "loss": 0.5614, + "step": 309 + }, + { + "epoch": 1.6202090592334495, + "grad_norm": 0.6140523018892134, + "learning_rate": 5.167723476538683e-06, + "loss": 0.6063, + "step": 310 + }, + { + "epoch": 1.6254355400696863, + "grad_norm": 0.47853290908855395, + "learning_rate": 5.137236810727025e-06, + "loss": 0.5358, + "step": 311 + }, + { + "epoch": 1.6306620209059233, + "grad_norm": 0.5819289571367962, + "learning_rate": 5.106745038048251e-06, + "loss": 0.6031, + "step": 312 + }, + { + "epoch": 1.6358885017421603, + "grad_norm": 0.5268059390545785, + "learning_rate": 5.07624929316463e-06, + "loss": 0.5926, + "step": 313 + }, + { + "epoch": 1.6411149825783973, + "grad_norm": 0.5158701213233892, + "learning_rate": 5.045750710886248e-06, + "loss": 0.5909, + "step": 314 + }, + { + "epoch": 1.6463414634146343, + "grad_norm": 0.5151166538253583, + "learning_rate": 5.015250426128772e-06, + "loss": 0.5394, + "step": 315 + }, + { + "epoch": 1.651567944250871, + "grad_norm": 0.5538710708429964, + "learning_rate": 4.984749573871228e-06, + "loss": 0.6349, + "step": 316 + }, + { + "epoch": 1.656794425087108, + "grad_norm": 0.5631924824167399, + "learning_rate": 4.954249289113753e-06, + "loss": 0.6271, + "step": 317 + }, + { + "epoch": 1.6620209059233448, + "grad_norm": 0.5557831986406585, + "learning_rate": 4.923750706835371e-06, + "loss": 0.6067, + "step": 318 + }, + { + "epoch": 1.6672473867595818, + "grad_norm": 0.5129556814943586, + "learning_rate": 4.8932549619517514e-06, + "loss": 0.5688, + "step": 319 + }, + { + "epoch": 1.6724738675958188, + "grad_norm": 0.510154514617586, + "learning_rate": 4.862763189272976e-06, + "loss": 0.5993, + "step": 320 + }, + { + "epoch": 1.6777003484320558, + "grad_norm": 0.5144230379042817, + "learning_rate": 4.832276523461317e-06, + "loss": 0.5251, + "step": 321 + }, + { + "epoch": 1.6829268292682928, + "grad_norm": 0.6787456643186844, + "learning_rate": 4.801796098989009e-06, + "loss": 0.6171, + "step": 322 + }, + { + "epoch": 1.6881533101045296, + "grad_norm": 0.5288392604393932, + "learning_rate": 4.771323050096028e-06, + "loss": 0.5868, + "step": 323 + }, + { + "epoch": 1.6933797909407664, + "grad_norm": 0.5337562030536104, + "learning_rate": 4.740858510747897e-06, + "loss": 0.6094, + "step": 324 + }, + { + "epoch": 1.6986062717770034, + "grad_norm": 0.5526357082902859, + "learning_rate": 4.710403614593475e-06, + "loss": 0.551, + "step": 325 + }, + { + "epoch": 1.7038327526132404, + "grad_norm": 0.5667609879832234, + "learning_rate": 4.679959494922779e-06, + "loss": 0.6207, + "step": 326 + }, + { + "epoch": 1.7090592334494774, + "grad_norm": 0.5052465715351889, + "learning_rate": 4.649527284624814e-06, + "loss": 0.5813, + "step": 327 + }, + { + "epoch": 1.7142857142857144, + "grad_norm": 0.6012385103563326, + "learning_rate": 4.619108116145411e-06, + "loss": 0.5997, + "step": 328 + }, + { + "epoch": 1.7195121951219512, + "grad_norm": 0.49875874383318625, + "learning_rate": 4.588703121445084e-06, + "loss": 0.6162, + "step": 329 + }, + { + "epoch": 1.7247386759581882, + "grad_norm": 0.5203036540095274, + "learning_rate": 4.558313431956914e-06, + "loss": 0.5616, + "step": 330 + }, + { + "epoch": 1.729965156794425, + "grad_norm": 0.6015714400165652, + "learning_rate": 4.527940178544446e-06, + "loss": 0.6088, + "step": 331 + }, + { + "epoch": 1.735191637630662, + "grad_norm": 0.4998018729629211, + "learning_rate": 4.4975844914596015e-06, + "loss": 0.5808, + "step": 332 + }, + { + "epoch": 1.740418118466899, + "grad_norm": 0.5755597332027752, + "learning_rate": 4.467247500300621e-06, + "loss": 0.6187, + "step": 333 + }, + { + "epoch": 1.745644599303136, + "grad_norm": 0.4930485861382567, + "learning_rate": 4.436930333970033e-06, + "loss": 0.5532, + "step": 334 + }, + { + "epoch": 1.750871080139373, + "grad_norm": 0.5496423220513306, + "learning_rate": 4.40663412063264e-06, + "loss": 0.6331, + "step": 335 + }, + { + "epoch": 1.7560975609756098, + "grad_norm": 0.5442491839702545, + "learning_rate": 4.376359987673547e-06, + "loss": 0.5759, + "step": 336 + }, + { + "epoch": 1.7613240418118465, + "grad_norm": 0.5248586938914367, + "learning_rate": 4.346109061656196e-06, + "loss": 0.5859, + "step": 337 + }, + { + "epoch": 1.7665505226480835, + "grad_norm": 0.5323054479309529, + "learning_rate": 4.31588246828045e-06, + "loss": 0.6084, + "step": 338 + }, + { + "epoch": 1.7717770034843205, + "grad_norm": 0.47627566350608475, + "learning_rate": 4.285681332340708e-06, + "loss": 0.5706, + "step": 339 + }, + { + "epoch": 1.7770034843205575, + "grad_norm": 0.5358815728520783, + "learning_rate": 4.255506777684041e-06, + "loss": 0.5904, + "step": 340 + }, + { + "epoch": 1.7822299651567945, + "grad_norm": 0.48425524407967563, + "learning_rate": 4.225359927168379e-06, + "loss": 0.5667, + "step": 341 + }, + { + "epoch": 1.7874564459930313, + "grad_norm": 0.5596432588171234, + "learning_rate": 4.195241902620721e-06, + "loss": 0.6049, + "step": 342 + }, + { + "epoch": 1.7926829268292683, + "grad_norm": 0.5440361119871323, + "learning_rate": 4.165153824795391e-06, + "loss": 0.6078, + "step": 343 + }, + { + "epoch": 1.797909407665505, + "grad_norm": 0.4826979180979176, + "learning_rate": 4.135096813332333e-06, + "loss": 0.588, + "step": 344 + }, + { + "epoch": 1.8031358885017421, + "grad_norm": 0.5397256499018573, + "learning_rate": 4.105071986715449e-06, + "loss": 0.6015, + "step": 345 + }, + { + "epoch": 1.8083623693379791, + "grad_norm": 0.4510163396115861, + "learning_rate": 4.075080462230977e-06, + "loss": 0.5697, + "step": 346 + }, + { + "epoch": 1.8135888501742161, + "grad_norm": 0.5218309859466103, + "learning_rate": 4.04512335592591e-06, + "loss": 0.5698, + "step": 347 + }, + { + "epoch": 1.8188153310104531, + "grad_norm": 0.5100313135625644, + "learning_rate": 4.015201782566471e-06, + "loss": 0.5787, + "step": 348 + }, + { + "epoch": 1.82404181184669, + "grad_norm": 0.498790862195705, + "learning_rate": 3.985316855596627e-06, + "loss": 0.6, + "step": 349 + }, + { + "epoch": 1.8292682926829267, + "grad_norm": 0.4754481818294577, + "learning_rate": 3.955469687096657e-06, + "loss": 0.5759, + "step": 350 + }, + { + "epoch": 1.8344947735191637, + "grad_norm": 0.5366460340127677, + "learning_rate": 3.9256613877417715e-06, + "loss": 0.6505, + "step": 351 + }, + { + "epoch": 1.8397212543554007, + "grad_norm": 0.48550128940070797, + "learning_rate": 3.895893066760774e-06, + "loss": 0.5581, + "step": 352 + }, + { + "epoch": 1.8449477351916377, + "grad_norm": 0.4645102288396099, + "learning_rate": 3.866165831894796e-06, + "loss": 0.6126, + "step": 353 + }, + { + "epoch": 1.8501742160278747, + "grad_norm": 0.5483359900678575, + "learning_rate": 3.836480789356063e-06, + "loss": 0.6353, + "step": 354 + }, + { + "epoch": 1.8554006968641115, + "grad_norm": 0.4726139182789402, + "learning_rate": 3.806839043786738e-06, + "loss": 0.5625, + "step": 355 + }, + { + "epoch": 1.8606271777003485, + "grad_norm": 0.46997478052113384, + "learning_rate": 3.777241698217819e-06, + "loss": 0.5839, + "step": 356 + }, + { + "epoch": 1.8658536585365852, + "grad_norm": 0.487480595451344, + "learning_rate": 3.747689854028081e-06, + "loss": 0.596, + "step": 357 + }, + { + "epoch": 1.8710801393728222, + "grad_norm": 0.4691428215776054, + "learning_rate": 3.7181846109031007e-06, + "loss": 0.5786, + "step": 358 + }, + { + "epoch": 1.8763066202090593, + "grad_norm": 0.49771800498221574, + "learning_rate": 3.6887270667943285e-06, + "loss": 0.5763, + "step": 359 + }, + { + "epoch": 1.8815331010452963, + "grad_norm": 0.48008730260324617, + "learning_rate": 3.6593183178782454e-06, + "loss": 0.6022, + "step": 360 + }, + { + "epoch": 1.8867595818815333, + "grad_norm": 0.49688177136494294, + "learning_rate": 3.6299594585155513e-06, + "loss": 0.5949, + "step": 361 + }, + { + "epoch": 1.89198606271777, + "grad_norm": 0.48272168297238965, + "learning_rate": 3.600651581210457e-06, + "loss": 0.5868, + "step": 362 + }, + { + "epoch": 1.8972125435540068, + "grad_norm": 0.4282471284231044, + "learning_rate": 3.5713957765700224e-06, + "loss": 0.5522, + "step": 363 + }, + { + "epoch": 1.9024390243902438, + "grad_norm": 0.49857423331197087, + "learning_rate": 3.542193133263576e-06, + "loss": 0.6013, + "step": 364 + }, + { + "epoch": 1.9076655052264808, + "grad_norm": 0.5051671065894443, + "learning_rate": 3.5130447379822076e-06, + "loss": 0.5448, + "step": 365 + }, + { + "epoch": 1.9128919860627178, + "grad_norm": 0.49126598359477613, + "learning_rate": 3.483951675398316e-06, + "loss": 0.6007, + "step": 366 + }, + { + "epoch": 1.9181184668989548, + "grad_norm": 0.5076571957591817, + "learning_rate": 3.4549150281252635e-06, + "loss": 0.5685, + "step": 367 + }, + { + "epoch": 1.9233449477351916, + "grad_norm": 0.512416353580941, + "learning_rate": 3.425935876677077e-06, + "loss": 0.5857, + "step": 368 + }, + { + "epoch": 1.9285714285714286, + "grad_norm": 0.5368818226681046, + "learning_rate": 3.397015299428242e-06, + "loss": 0.5809, + "step": 369 + }, + { + "epoch": 1.9337979094076654, + "grad_norm": 0.5120830184486495, + "learning_rate": 3.3681543725735843e-06, + "loss": 0.6067, + "step": 370 + }, + { + "epoch": 1.9390243902439024, + "grad_norm": 0.4785710907485341, + "learning_rate": 3.339354170088207e-06, + "loss": 0.5398, + "step": 371 + }, + { + "epoch": 1.9442508710801394, + "grad_norm": 0.45732087968552365, + "learning_rate": 3.3106157636875356e-06, + "loss": 0.5702, + "step": 372 + }, + { + "epoch": 1.9494773519163764, + "grad_norm": 0.49177652612113, + "learning_rate": 3.2819402227874364e-06, + "loss": 0.5925, + "step": 373 + }, + { + "epoch": 1.9547038327526134, + "grad_norm": 0.522898733840705, + "learning_rate": 3.253328614464414e-06, + "loss": 0.6521, + "step": 374 + }, + { + "epoch": 1.9599303135888502, + "grad_norm": 0.4962984913773303, + "learning_rate": 3.2247820034159182e-06, + "loss": 0.5637, + "step": 375 + }, + { + "epoch": 1.965156794425087, + "grad_norm": 0.48961258731018903, + "learning_rate": 3.196301451920708e-06, + "loss": 0.6078, + "step": 376 + }, + { + "epoch": 1.970383275261324, + "grad_norm": 0.516946862548738, + "learning_rate": 3.16788801979933e-06, + "loss": 0.614, + "step": 377 + }, + { + "epoch": 1.975609756097561, + "grad_norm": 0.49422567410473595, + "learning_rate": 3.1395427643746802e-06, + "loss": 0.5407, + "step": 378 + }, + { + "epoch": 1.980836236933798, + "grad_norm": 0.5096634642555786, + "learning_rate": 3.111266740432658e-06, + "loss": 0.5792, + "step": 379 + }, + { + "epoch": 1.986062717770035, + "grad_norm": 0.5002493838245908, + "learning_rate": 3.0830610001829173e-06, + "loss": 0.5552, + "step": 380 + }, + { + "epoch": 1.9912891986062717, + "grad_norm": 0.4634141103131062, + "learning_rate": 3.0549265932197055e-06, + "loss": 0.5474, + "step": 381 + }, + { + "epoch": 1.9965156794425087, + "grad_norm": 0.49968954452588915, + "learning_rate": 3.026864566482813e-06, + "loss": 0.5926, + "step": 382 + }, + { + "epoch": 2.0017421602787455, + "grad_norm": 0.9566301326202498, + "learning_rate": 2.99887596421861e-06, + "loss": 0.9583, + "step": 383 + }, + { + "epoch": 2.0069686411149825, + "grad_norm": 0.4819191529898956, + "learning_rate": 2.9709618279411922e-06, + "loss": 0.4765, + "step": 384 + }, + { + "epoch": 2.0121951219512195, + "grad_norm": 0.5177350268902499, + "learning_rate": 2.9431231963936176e-06, + "loss": 0.5513, + "step": 385 + }, + { + "epoch": 2.0174216027874565, + "grad_norm": 0.49571084166916257, + "learning_rate": 2.9153611055092586e-06, + "loss": 0.5568, + "step": 386 + }, + { + "epoch": 2.0226480836236935, + "grad_norm": 0.46758191028533336, + "learning_rate": 2.8876765883732447e-06, + "loss": 0.5378, + "step": 387 + }, + { + "epoch": 2.0278745644599305, + "grad_norm": 0.5062906288655116, + "learning_rate": 2.860070675184036e-06, + "loss": 0.5742, + "step": 388 + }, + { + "epoch": 2.033101045296167, + "grad_norm": 0.48782738802655556, + "learning_rate": 2.8325443932150646e-06, + "loss": 0.5343, + "step": 389 + }, + { + "epoch": 2.038327526132404, + "grad_norm": 0.5414387332438313, + "learning_rate": 2.805098766776529e-06, + "loss": 0.5849, + "step": 390 + }, + { + "epoch": 2.043554006968641, + "grad_norm": 0.4642400730103952, + "learning_rate": 2.7777348171772604e-06, + "loss": 0.5105, + "step": 391 + }, + { + "epoch": 2.048780487804878, + "grad_norm": 0.5304251807046266, + "learning_rate": 2.750453562686729e-06, + "loss": 0.5143, + "step": 392 + }, + { + "epoch": 2.054006968641115, + "grad_norm": 0.5576744024363436, + "learning_rate": 2.7232560184971437e-06, + "loss": 0.5839, + "step": 393 + }, + { + "epoch": 2.059233449477352, + "grad_norm": 0.45314772448223345, + "learning_rate": 2.6961431966856866e-06, + "loss": 0.5233, + "step": 394 + }, + { + "epoch": 2.0644599303135887, + "grad_norm": 0.4577070909297848, + "learning_rate": 2.669116106176838e-06, + "loss": 0.5494, + "step": 395 + }, + { + "epoch": 2.0696864111498257, + "grad_norm": 0.4395553331677893, + "learning_rate": 2.6421757527048373e-06, + "loss": 0.5097, + "step": 396 + }, + { + "epoch": 2.0749128919860627, + "grad_norm": 0.5287787777736306, + "learning_rate": 2.615323138776264e-06, + "loss": 0.5719, + "step": 397 + }, + { + "epoch": 2.0801393728222997, + "grad_norm": 0.5093454684767568, + "learning_rate": 2.588559263632719e-06, + "loss": 0.5265, + "step": 398 + }, + { + "epoch": 2.0853658536585367, + "grad_norm": 0.5080566318736497, + "learning_rate": 2.5618851232136576e-06, + "loss": 0.5772, + "step": 399 + }, + { + "epoch": 2.0905923344947737, + "grad_norm": 0.4499734335969841, + "learning_rate": 2.5353017101193124e-06, + "loss": 0.4555, + "step": 400 + }, + { + "epoch": 2.0958188153310107, + "grad_norm": 0.5291566057629548, + "learning_rate": 2.508810013573767e-06, + "loss": 0.5643, + "step": 401 + }, + { + "epoch": 2.1010452961672472, + "grad_norm": 0.46824151574429873, + "learning_rate": 2.4824110193881384e-06, + "loss": 0.5065, + "step": 402 + }, + { + "epoch": 2.1062717770034842, + "grad_norm": 0.4617359511491741, + "learning_rate": 2.4561057099238973e-06, + "loss": 0.563, + "step": 403 + }, + { + "epoch": 2.1114982578397212, + "grad_norm": 0.4697636992836946, + "learning_rate": 2.4298950640563155e-06, + "loss": 0.5056, + "step": 404 + }, + { + "epoch": 2.1167247386759582, + "grad_norm": 0.48460609918415953, + "learning_rate": 2.4037800571380297e-06, + "loss": 0.5517, + "step": 405 + }, + { + "epoch": 2.1219512195121952, + "grad_norm": 0.465322807158819, + "learning_rate": 2.377761660962754e-06, + "loss": 0.5764, + "step": 406 + }, + { + "epoch": 2.1271777003484322, + "grad_norm": 0.49593267777356703, + "learning_rate": 2.3518408437291155e-06, + "loss": 0.5357, + "step": 407 + }, + { + "epoch": 2.132404181184669, + "grad_norm": 0.48746378777099386, + "learning_rate": 2.3260185700046295e-06, + "loss": 0.5321, + "step": 408 + }, + { + "epoch": 2.137630662020906, + "grad_norm": 0.46071947103740635, + "learning_rate": 2.3002958006897985e-06, + "loss": 0.5468, + "step": 409 + }, + { + "epoch": 2.142857142857143, + "grad_norm": 0.440111968230906, + "learning_rate": 2.2746734929823596e-06, + "loss": 0.531, + "step": 410 + }, + { + "epoch": 2.14808362369338, + "grad_norm": 0.4575672027883791, + "learning_rate": 2.249152600341665e-06, + "loss": 0.52, + "step": 411 + }, + { + "epoch": 2.153310104529617, + "grad_norm": 0.5283338120770418, + "learning_rate": 2.2237340724532007e-06, + "loss": 0.6015, + "step": 412 + }, + { + "epoch": 2.158536585365854, + "grad_norm": 0.4532501199512347, + "learning_rate": 2.1984188551932513e-06, + "loss": 0.4911, + "step": 413 + }, + { + "epoch": 2.1637630662020904, + "grad_norm": 0.5151201704194432, + "learning_rate": 2.173207890593693e-06, + "loss": 0.5519, + "step": 414 + }, + { + "epoch": 2.1689895470383274, + "grad_norm": 0.4813092159395286, + "learning_rate": 2.148102116806944e-06, + "loss": 0.531, + "step": 415 + }, + { + "epoch": 2.1742160278745644, + "grad_norm": 0.47141365400566, + "learning_rate": 2.123102468071058e-06, + "loss": 0.5249, + "step": 416 + }, + { + "epoch": 2.1794425087108014, + "grad_norm": 0.4935502426085609, + "learning_rate": 2.0982098746749524e-06, + "loss": 0.5261, + "step": 417 + }, + { + "epoch": 2.1846689895470384, + "grad_norm": 0.5305754761741215, + "learning_rate": 2.0734252629237892e-06, + "loss": 0.609, + "step": 418 + }, + { + "epoch": 2.1898954703832754, + "grad_norm": 0.482899473961335, + "learning_rate": 2.048749555104516e-06, + "loss": 0.5314, + "step": 419 + }, + { + "epoch": 2.1951219512195124, + "grad_norm": 0.44109993576183376, + "learning_rate": 2.0241836694515338e-06, + "loss": 0.54, + "step": 420 + }, + { + "epoch": 2.200348432055749, + "grad_norm": 0.4541137377252633, + "learning_rate": 1.9997285201125328e-06, + "loss": 0.5182, + "step": 421 + }, + { + "epoch": 2.205574912891986, + "grad_norm": 0.47179876294255096, + "learning_rate": 1.975385017114473e-06, + "loss": 0.5786, + "step": 422 + }, + { + "epoch": 2.210801393728223, + "grad_norm": 0.49973970600486517, + "learning_rate": 1.9511540663297284e-06, + "loss": 0.5183, + "step": 423 + }, + { + "epoch": 2.21602787456446, + "grad_norm": 0.46356554425956825, + "learning_rate": 1.9270365694423654e-06, + "loss": 0.5159, + "step": 424 + }, + { + "epoch": 2.221254355400697, + "grad_norm": 0.5241753937590147, + "learning_rate": 1.903033423914596e-06, + "loss": 0.5957, + "step": 425 + }, + { + "epoch": 2.226480836236934, + "grad_norm": 0.44148518090830996, + "learning_rate": 1.8791455229533806e-06, + "loss": 0.4488, + "step": 426 + }, + { + "epoch": 2.231707317073171, + "grad_norm": 0.5038639568195054, + "learning_rate": 1.8553737554771883e-06, + "loss": 0.6349, + "step": 427 + }, + { + "epoch": 2.2369337979094075, + "grad_norm": 0.49606752296755446, + "learning_rate": 1.8317190060829242e-06, + "loss": 0.5089, + "step": 428 + }, + { + "epoch": 2.2421602787456445, + "grad_norm": 0.45579655008006387, + "learning_rate": 1.808182155013003e-06, + "loss": 0.4899, + "step": 429 + }, + { + "epoch": 2.2473867595818815, + "grad_norm": 0.464962788957996, + "learning_rate": 1.7847640781225982e-06, + "loss": 0.5486, + "step": 430 + }, + { + "epoch": 2.2526132404181185, + "grad_norm": 0.4984600881906674, + "learning_rate": 1.7614656468470508e-06, + "loss": 0.6217, + "step": 431 + }, + { + "epoch": 2.2578397212543555, + "grad_norm": 0.4386510268154617, + "learning_rate": 1.7382877281694355e-06, + "loss": 0.5065, + "step": 432 + }, + { + "epoch": 2.2630662020905925, + "grad_norm": 0.4628957678602141, + "learning_rate": 1.7152311845883096e-06, + "loss": 0.5339, + "step": 433 + }, + { + "epoch": 2.2682926829268295, + "grad_norm": 0.4511882273309374, + "learning_rate": 1.692296874085605e-06, + "loss": 0.5833, + "step": 434 + }, + { + "epoch": 2.273519163763066, + "grad_norm": 0.4423489129104317, + "learning_rate": 1.6694856500947081e-06, + "loss": 0.5414, + "step": 435 + }, + { + "epoch": 2.278745644599303, + "grad_norm": 0.4278102250494057, + "learning_rate": 1.6467983614686995e-06, + "loss": 0.5291, + "step": 436 + }, + { + "epoch": 2.28397212543554, + "grad_norm": 0.4899503913317031, + "learning_rate": 1.62423585244877e-06, + "loss": 0.5207, + "step": 437 + }, + { + "epoch": 2.289198606271777, + "grad_norm": 0.45314192403359066, + "learning_rate": 1.601798962632799e-06, + "loss": 0.5233, + "step": 438 + }, + { + "epoch": 2.294425087108014, + "grad_norm": 0.4675516971595869, + "learning_rate": 1.5794885269441152e-06, + "loss": 0.5789, + "step": 439 + }, + { + "epoch": 2.2996515679442506, + "grad_norm": 0.4684838825648316, + "learning_rate": 1.5573053756004253e-06, + "loss": 0.5447, + "step": 440 + }, + { + "epoch": 2.3048780487804876, + "grad_norm": 0.4742515090348089, + "learning_rate": 1.53525033408292e-06, + "loss": 0.5522, + "step": 441 + }, + { + "epoch": 2.3101045296167246, + "grad_norm": 0.4255877001891176, + "learning_rate": 1.5133242231055622e-06, + "loss": 0.52, + "step": 442 + }, + { + "epoch": 2.3153310104529616, + "grad_norm": 0.4703877181502192, + "learning_rate": 1.491527858584535e-06, + "loss": 0.5629, + "step": 443 + }, + { + "epoch": 2.3205574912891986, + "grad_norm": 0.4564707024075428, + "learning_rate": 1.4698620516078882e-06, + "loss": 0.5899, + "step": 444 + }, + { + "epoch": 2.3257839721254356, + "grad_norm": 0.4393071035962851, + "learning_rate": 1.4483276084053567e-06, + "loss": 0.514, + "step": 445 + }, + { + "epoch": 2.3310104529616726, + "grad_norm": 0.4382243891353936, + "learning_rate": 1.4269253303183516e-06, + "loss": 0.5766, + "step": 446 + }, + { + "epoch": 2.3362369337979096, + "grad_norm": 0.46207515860487863, + "learning_rate": 1.4056560137701469e-06, + "loss": 0.492, + "step": 447 + }, + { + "epoch": 2.341463414634146, + "grad_norm": 0.4779708014243619, + "learning_rate": 1.3845204502362442e-06, + "loss": 0.5503, + "step": 448 + }, + { + "epoch": 2.346689895470383, + "grad_norm": 0.4446567240946519, + "learning_rate": 1.3635194262149131e-06, + "loss": 0.5173, + "step": 449 + }, + { + "epoch": 2.35191637630662, + "grad_norm": 0.5194569385386936, + "learning_rate": 1.3426537231979309e-06, + "loss": 0.5464, + "step": 450 + }, + { + "epoch": 2.357142857142857, + "grad_norm": 0.47302377318250843, + "learning_rate": 1.3219241176414948e-06, + "loss": 0.5341, + "step": 451 + }, + { + "epoch": 2.362369337979094, + "grad_norm": 0.4316213228653094, + "learning_rate": 1.3013313809373396e-06, + "loss": 0.5283, + "step": 452 + }, + { + "epoch": 2.3675958188153308, + "grad_norm": 0.4347857005792825, + "learning_rate": 1.28087627938402e-06, + "loss": 0.5103, + "step": 453 + }, + { + "epoch": 2.3728222996515678, + "grad_norm": 0.4599959414145429, + "learning_rate": 1.2605595741584015e-06, + "loss": 0.5989, + "step": 454 + }, + { + "epoch": 2.3780487804878048, + "grad_norm": 0.4477421618895101, + "learning_rate": 1.2403820212873347e-06, + "loss": 0.5247, + "step": 455 + }, + { + "epoch": 2.3832752613240418, + "grad_norm": 0.46194912531798293, + "learning_rate": 1.2203443716195213e-06, + "loss": 0.547, + "step": 456 + }, + { + "epoch": 2.3885017421602788, + "grad_norm": 0.48246695872510925, + "learning_rate": 1.200447370797576e-06, + "loss": 0.5319, + "step": 457 + }, + { + "epoch": 2.3937282229965158, + "grad_norm": 0.44364446337995106, + "learning_rate": 1.1806917592302763e-06, + "loss": 0.5079, + "step": 458 + }, + { + "epoch": 2.3989547038327528, + "grad_norm": 0.45366308339292766, + "learning_rate": 1.16107827206501e-06, + "loss": 0.528, + "step": 459 + }, + { + "epoch": 2.40418118466899, + "grad_norm": 0.44739930129966016, + "learning_rate": 1.1416076391604197e-06, + "loss": 0.5351, + "step": 460 + }, + { + "epoch": 2.4094076655052263, + "grad_norm": 0.4842777825049656, + "learning_rate": 1.12228058505925e-06, + "loss": 0.5459, + "step": 461 + }, + { + "epoch": 2.4146341463414633, + "grad_norm": 0.46656539985547907, + "learning_rate": 1.1030978289613725e-06, + "loss": 0.5377, + "step": 462 + }, + { + "epoch": 2.4198606271777003, + "grad_norm": 0.4434636263867975, + "learning_rate": 1.0840600846970333e-06, + "loss": 0.5494, + "step": 463 + }, + { + "epoch": 2.4250871080139373, + "grad_norm": 0.42991245492599656, + "learning_rate": 1.0651680607002861e-06, + "loss": 0.5372, + "step": 464 + }, + { + "epoch": 2.4303135888501743, + "grad_norm": 0.47167305733035525, + "learning_rate": 1.0464224599826301e-06, + "loss": 0.5127, + "step": 465 + }, + { + "epoch": 2.435540069686411, + "grad_norm": 0.460998662886707, + "learning_rate": 1.0278239801068518e-06, + "loss": 0.5137, + "step": 466 + }, + { + "epoch": 2.440766550522648, + "grad_norm": 0.5048182621907691, + "learning_rate": 1.0093733131610621e-06, + "loss": 0.6034, + "step": 467 + }, + { + "epoch": 2.445993031358885, + "grad_norm": 0.46718193125046437, + "learning_rate": 9.91071145732948e-07, + "loss": 0.5201, + "step": 468 + }, + { + "epoch": 2.451219512195122, + "grad_norm": 0.40697553295642236, + "learning_rate": 9.729181588842184e-07, + "loss": 0.4763, + "step": 469 + }, + { + "epoch": 2.456445993031359, + "grad_norm": 0.4282850894981929, + "learning_rate": 9.549150281252633e-07, + "loss": 0.5551, + "step": 470 + }, + { + "epoch": 2.461672473867596, + "grad_norm": 0.4425949078660112, + "learning_rate": 9.370624233900183e-07, + "loss": 0.509, + "step": 471 + }, + { + "epoch": 2.466898954703833, + "grad_norm": 0.43823474167181586, + "learning_rate": 9.193610090110305e-07, + "loss": 0.5605, + "step": 472 + }, + { + "epoch": 2.47212543554007, + "grad_norm": 0.45300520608343586, + "learning_rate": 9.018114436947373e-07, + "loss": 0.5394, + "step": 473 + }, + { + "epoch": 2.4773519163763065, + "grad_norm": 0.4830008293506701, + "learning_rate": 8.844143804969624e-07, + "loss": 0.5614, + "step": 474 + }, + { + "epoch": 2.4825783972125435, + "grad_norm": 0.4313889868995408, + "learning_rate": 8.671704667986036e-07, + "loss": 0.495, + "step": 475 + }, + { + "epoch": 2.4878048780487805, + "grad_norm": 0.4652585907754659, + "learning_rate": 8.500803442815475e-07, + "loss": 0.5337, + "step": 476 + }, + { + "epoch": 2.4930313588850175, + "grad_norm": 0.4434579349259814, + "learning_rate": 8.331446489047956e-07, + "loss": 0.5432, + "step": 477 + }, + { + "epoch": 2.4982578397212545, + "grad_norm": 0.4260838162732741, + "learning_rate": 8.163640108807897e-07, + "loss": 0.5526, + "step": 478 + }, + { + "epoch": 2.503484320557491, + "grad_norm": 0.41851893716167266, + "learning_rate": 7.997390546519668e-07, + "loss": 0.5274, + "step": 479 + }, + { + "epoch": 2.508710801393728, + "grad_norm": 0.43352778515121865, + "learning_rate": 7.832703988675195e-07, + "loss": 0.5498, + "step": 480 + }, + { + "epoch": 2.513937282229965, + "grad_norm": 0.45074130711852517, + "learning_rate": 7.669586563603782e-07, + "loss": 0.5531, + "step": 481 + }, + { + "epoch": 2.519163763066202, + "grad_norm": 0.45864866148701783, + "learning_rate": 7.508044341244014e-07, + "loss": 0.5914, + "step": 482 + }, + { + "epoch": 2.524390243902439, + "grad_norm": 0.43380289787943704, + "learning_rate": 7.348083332917927e-07, + "loss": 0.5302, + "step": 483 + }, + { + "epoch": 2.529616724738676, + "grad_norm": 0.44541179316397, + "learning_rate": 7.189709491107272e-07, + "loss": 0.5103, + "step": 484 + }, + { + "epoch": 2.534843205574913, + "grad_norm": 0.42812608402735486, + "learning_rate": 7.032928709232062e-07, + "loss": 0.5131, + "step": 485 + }, + { + "epoch": 2.54006968641115, + "grad_norm": 0.4641631244885751, + "learning_rate": 6.87774682143122e-07, + "loss": 0.5406, + "step": 486 + }, + { + "epoch": 2.5452961672473866, + "grad_norm": 0.46466095362861476, + "learning_rate": 6.724169602345487e-07, + "loss": 0.5524, + "step": 487 + }, + { + "epoch": 2.5505226480836236, + "grad_norm": 0.44159109445526523, + "learning_rate": 6.572202766902569e-07, + "loss": 0.5107, + "step": 488 + }, + { + "epoch": 2.5557491289198606, + "grad_norm": 0.43095228829120374, + "learning_rate": 6.421851970104409e-07, + "loss": 0.5465, + "step": 489 + }, + { + "epoch": 2.5609756097560976, + "grad_norm": 0.4398781503440029, + "learning_rate": 6.273122806816845e-07, + "loss": 0.5306, + "step": 490 + }, + { + "epoch": 2.5662020905923346, + "grad_norm": 0.455532997496077, + "learning_rate": 6.126020811561323e-07, + "loss": 0.5881, + "step": 491 + }, + { + "epoch": 2.571428571428571, + "grad_norm": 0.3948516059085693, + "learning_rate": 5.980551458308981e-07, + "loss": 0.4535, + "step": 492 + }, + { + "epoch": 2.576655052264808, + "grad_norm": 0.4009473999258072, + "learning_rate": 5.836720160276971e-07, + "loss": 0.5696, + "step": 493 + }, + { + "epoch": 2.581881533101045, + "grad_norm": 0.4065638987549273, + "learning_rate": 5.694532269726977e-07, + "loss": 0.5412, + "step": 494 + }, + { + "epoch": 2.587108013937282, + "grad_norm": 0.4539932581334291, + "learning_rate": 5.553993077766124e-07, + "loss": 0.5886, + "step": 495 + }, + { + "epoch": 2.592334494773519, + "grad_norm": 0.42936026661045573, + "learning_rate": 5.415107814149978e-07, + "loss": 0.519, + "step": 496 + }, + { + "epoch": 2.597560975609756, + "grad_norm": 0.4335795734646765, + "learning_rate": 5.277881647088024e-07, + "loss": 0.5866, + "step": 497 + }, + { + "epoch": 2.602787456445993, + "grad_norm": 0.44871188719474847, + "learning_rate": 5.1423196830513e-07, + "loss": 0.5824, + "step": 498 + }, + { + "epoch": 2.60801393728223, + "grad_norm": 0.4649294419801843, + "learning_rate": 5.008426966582386e-07, + "loss": 0.5086, + "step": 499 + }, + { + "epoch": 2.6132404181184667, + "grad_norm": 0.47884736570244324, + "learning_rate": 4.87620848010772e-07, + "loss": 0.5853, + "step": 500 + }, + { + "epoch": 2.6184668989547037, + "grad_norm": 0.4070247906117974, + "learning_rate": 4.7456691437521243e-07, + "loss": 0.4705, + "step": 501 + }, + { + "epoch": 2.6236933797909407, + "grad_norm": 0.44228619733522523, + "learning_rate": 4.6168138151557516e-07, + "loss": 0.6052, + "step": 502 + }, + { + "epoch": 2.6289198606271778, + "grad_norm": 0.4186718748315985, + "learning_rate": 4.4896472892933693e-07, + "loss": 0.5156, + "step": 503 + }, + { + "epoch": 2.6341463414634148, + "grad_norm": 0.41927468655653893, + "learning_rate": 4.3641742982958203e-07, + "loss": 0.5552, + "step": 504 + }, + { + "epoch": 2.6393728222996513, + "grad_norm": 0.3807275422714154, + "learning_rate": 4.240399511274057e-07, + "loss": 0.4874, + "step": 505 + }, + { + "epoch": 2.6445993031358883, + "grad_norm": 0.43043158611193255, + "learning_rate": 4.118327534145278e-07, + "loss": 0.5473, + "step": 506 + }, + { + "epoch": 2.6498257839721253, + "grad_norm": 0.4427511902610817, + "learning_rate": 3.997962909461611e-07, + "loss": 0.5476, + "step": 507 + }, + { + "epoch": 2.6550522648083623, + "grad_norm": 0.4287387407398484, + "learning_rate": 3.8793101162410417e-07, + "loss": 0.515, + "step": 508 + }, + { + "epoch": 2.6602787456445993, + "grad_norm": 0.4581450049667044, + "learning_rate": 3.762373569800737e-07, + "loss": 0.5736, + "step": 509 + }, + { + "epoch": 2.6655052264808363, + "grad_norm": 0.45437023578463565, + "learning_rate": 3.6471576215927897e-07, + "loss": 0.5301, + "step": 510 + }, + { + "epoch": 2.6707317073170733, + "grad_norm": 0.4205454157334176, + "learning_rate": 3.5336665590422147e-07, + "loss": 0.5274, + "step": 511 + }, + { + "epoch": 2.6759581881533103, + "grad_norm": 0.42921462391644427, + "learning_rate": 3.4219046053874604e-07, + "loss": 0.5453, + "step": 512 + }, + { + "epoch": 2.681184668989547, + "grad_norm": 0.4233533929984576, + "learning_rate": 3.3118759195232273e-07, + "loss": 0.5573, + "step": 513 + }, + { + "epoch": 2.686411149825784, + "grad_norm": 0.3919672353563574, + "learning_rate": 3.2035845958457324e-07, + "loss": 0.5181, + "step": 514 + }, + { + "epoch": 2.691637630662021, + "grad_norm": 0.47372027451981813, + "learning_rate": 3.0970346641003346e-07, + "loss": 0.5436, + "step": 515 + }, + { + "epoch": 2.696864111498258, + "grad_norm": 0.4396594930081907, + "learning_rate": 2.9922300892315517e-07, + "loss": 0.5475, + "step": 516 + }, + { + "epoch": 2.702090592334495, + "grad_norm": 0.4473565138284573, + "learning_rate": 2.88917477123557e-07, + "loss": 0.5559, + "step": 517 + }, + { + "epoch": 2.7073170731707314, + "grad_norm": 0.4024822510249766, + "learning_rate": 2.787872545015069e-07, + "loss": 0.5059, + "step": 518 + }, + { + "epoch": 2.7125435540069684, + "grad_norm": 0.4665623873342051, + "learning_rate": 2.6883271802365606e-07, + "loss": 0.5585, + "step": 519 + }, + { + "epoch": 2.7177700348432055, + "grad_norm": 0.42854221934756087, + "learning_rate": 2.5905423811900755e-07, + "loss": 0.5104, + "step": 520 + }, + { + "epoch": 2.7229965156794425, + "grad_norm": 0.4286908922250654, + "learning_rate": 2.4945217866513274e-07, + "loss": 0.5518, + "step": 521 + }, + { + "epoch": 2.7282229965156795, + "grad_norm": 0.44386460142096057, + "learning_rate": 2.4002689697463224e-07, + "loss": 0.5305, + "step": 522 + }, + { + "epoch": 2.7334494773519165, + "grad_norm": 0.43745356189843465, + "learning_rate": 2.307787437818365e-07, + "loss": 0.5579, + "step": 523 + }, + { + "epoch": 2.7386759581881535, + "grad_norm": 0.4192061612455892, + "learning_rate": 2.2170806322976023e-07, + "loss": 0.5133, + "step": 524 + }, + { + "epoch": 2.7439024390243905, + "grad_norm": 0.44288601777891073, + "learning_rate": 2.1281519285728803e-07, + "loss": 0.5837, + "step": 525 + }, + { + "epoch": 2.749128919860627, + "grad_norm": 0.4161039648633803, + "learning_rate": 2.041004635866195e-07, + "loss": 0.5105, + "step": 526 + }, + { + "epoch": 2.754355400696864, + "grad_norm": 0.4294055964727348, + "learning_rate": 1.9556419971095363e-07, + "loss": 0.5319, + "step": 527 + }, + { + "epoch": 2.759581881533101, + "grad_norm": 0.4358089354550434, + "learning_rate": 1.8720671888242058e-07, + "loss": 0.4988, + "step": 528 + }, + { + "epoch": 2.764808362369338, + "grad_norm": 0.43788412237975727, + "learning_rate": 1.7902833210026228e-07, + "loss": 0.546, + "step": 529 + }, + { + "epoch": 2.770034843205575, + "grad_norm": 0.45097033105165757, + "learning_rate": 1.710293436992566e-07, + "loss": 0.5696, + "step": 530 + }, + { + "epoch": 2.7752613240418116, + "grad_norm": 0.4138845338967673, + "learning_rate": 1.6321005133839884e-07, + "loss": 0.5316, + "step": 531 + }, + { + "epoch": 2.7804878048780486, + "grad_norm": 0.4202899606511126, + "learning_rate": 1.5557074598981593e-07, + "loss": 0.5301, + "step": 532 + }, + { + "epoch": 2.7857142857142856, + "grad_norm": 0.42666653234169716, + "learning_rate": 1.4811171192794628e-07, + "loss": 0.5697, + "step": 533 + }, + { + "epoch": 2.7909407665505226, + "grad_norm": 0.37877132072819447, + "learning_rate": 1.4083322671896048e-07, + "loss": 0.4895, + "step": 534 + }, + { + "epoch": 2.7961672473867596, + "grad_norm": 0.4422175332427632, + "learning_rate": 1.337355612104274e-07, + "loss": 0.5793, + "step": 535 + }, + { + "epoch": 2.8013937282229966, + "grad_norm": 0.4141363458191714, + "learning_rate": 1.2681897952124046e-07, + "loss": 0.5057, + "step": 536 + }, + { + "epoch": 2.8066202090592336, + "grad_norm": 0.4469656727146587, + "learning_rate": 1.2008373903178828e-07, + "loss": 0.5524, + "step": 537 + }, + { + "epoch": 2.8118466898954706, + "grad_norm": 0.42707047626049666, + "learning_rate": 1.1353009037437523e-07, + "loss": 0.4922, + "step": 538 + }, + { + "epoch": 2.817073170731707, + "grad_norm": 0.45141362991328465, + "learning_rate": 1.0715827742389717e-07, + "loss": 0.5724, + "step": 539 + }, + { + "epoch": 2.822299651567944, + "grad_norm": 0.45003668834699156, + "learning_rate": 1.0096853728876365e-07, + "loss": 0.4959, + "step": 540 + }, + { + "epoch": 2.827526132404181, + "grad_norm": 0.40703793301322555, + "learning_rate": 9.496110030207673e-08, + "loss": 0.5187, + "step": 541 + }, + { + "epoch": 2.832752613240418, + "grad_norm": 0.4349893646514051, + "learning_rate": 8.913619001305995e-08, + "loss": 0.5413, + "step": 542 + }, + { + "epoch": 2.837979094076655, + "grad_norm": 0.4413261937466953, + "learning_rate": 8.34940231787379e-08, + "loss": 0.5597, + "step": 543 + }, + { + "epoch": 2.8432055749128917, + "grad_norm": 0.4219769036035547, + "learning_rate": 7.803480975587197e-08, + "loss": 0.542, + "step": 544 + }, + { + "epoch": 2.8484320557491287, + "grad_norm": 0.4673046785235365, + "learning_rate": 7.275875289314616e-08, + "loss": 0.5495, + "step": 545 + }, + { + "epoch": 2.8536585365853657, + "grad_norm": 0.45105426206164123, + "learning_rate": 6.766604892360751e-08, + "loss": 0.5724, + "step": 546 + }, + { + "epoch": 2.8588850174216027, + "grad_norm": 0.43511636060314596, + "learning_rate": 6.275688735736141e-08, + "loss": 0.5257, + "step": 547 + }, + { + "epoch": 2.8641114982578397, + "grad_norm": 0.43349086279126203, + "learning_rate": 5.803145087451945e-08, + "loss": 0.5131, + "step": 548 + }, + { + "epoch": 2.8693379790940767, + "grad_norm": 0.4537611808145007, + "learning_rate": 5.348991531839875e-08, + "loss": 0.5607, + "step": 549 + }, + { + "epoch": 2.8745644599303137, + "grad_norm": 0.4439279551647372, + "learning_rate": 4.913244968898279e-08, + "loss": 0.5056, + "step": 550 + }, + { + "epoch": 2.8797909407665507, + "grad_norm": 0.4411930978992959, + "learning_rate": 4.495921613662746e-08, + "loss": 0.5415, + "step": 551 + }, + { + "epoch": 2.8850174216027873, + "grad_norm": 0.4436199780022762, + "learning_rate": 4.097036995603321e-08, + "loss": 0.5205, + "step": 552 + }, + { + "epoch": 2.8902439024390243, + "grad_norm": 0.42509245773578536, + "learning_rate": 3.716605958046071e-08, + "loss": 0.5259, + "step": 553 + }, + { + "epoch": 2.8954703832752613, + "grad_norm": 0.43131172360952724, + "learning_rate": 3.354642657621032e-08, + "loss": 0.604, + "step": 554 + }, + { + "epoch": 2.9006968641114983, + "grad_norm": 0.4133105200801449, + "learning_rate": 3.011160563735349e-08, + "loss": 0.4883, + "step": 555 + }, + { + "epoch": 2.9059233449477353, + "grad_norm": 0.4391744276562499, + "learning_rate": 2.6861724580719562e-08, + "loss": 0.5621, + "step": 556 + }, + { + "epoch": 2.911149825783972, + "grad_norm": 0.4391177361243526, + "learning_rate": 2.3796904341141236e-08, + "loss": 0.5334, + "step": 557 + }, + { + "epoch": 2.916376306620209, + "grad_norm": 0.4214891944016137, + "learning_rate": 2.0917258966953735e-08, + "loss": 0.553, + "step": 558 + }, + { + "epoch": 2.921602787456446, + "grad_norm": 0.4014499901153732, + "learning_rate": 1.8222895615748748e-08, + "loss": 0.5358, + "step": 559 + }, + { + "epoch": 2.926829268292683, + "grad_norm": 0.4454567928346748, + "learning_rate": 1.5713914550389843e-08, + "loss": 0.5405, + "step": 560 + }, + { + "epoch": 2.93205574912892, + "grad_norm": 0.4178833466790727, + "learning_rate": 1.3390409135281001e-08, + "loss": 0.5513, + "step": 561 + }, + { + "epoch": 2.937282229965157, + "grad_norm": 0.4457705249971793, + "learning_rate": 1.125246583288886e-08, + "loss": 0.5245, + "step": 562 + }, + { + "epoch": 2.942508710801394, + "grad_norm": 0.4645928048601542, + "learning_rate": 9.300164200530815e-09, + "loss": 0.5701, + "step": 563 + }, + { + "epoch": 2.947735191637631, + "grad_norm": 0.4563271003769357, + "learning_rate": 7.533576887410188e-09, + "loss": 0.4999, + "step": 564 + }, + { + "epoch": 2.952961672473868, + "grad_norm": 0.39820608811758146, + "learning_rate": 5.95276963191449e-09, + "loss": 0.5704, + "step": 565 + }, + { + "epoch": 2.9581881533101044, + "grad_norm": 0.4590404415892991, + "learning_rate": 4.557801259169048e-09, + "loss": 0.4995, + "step": 566 + }, + { + "epoch": 2.9634146341463414, + "grad_norm": 0.455741641646435, + "learning_rate": 3.348723678847643e-09, + "loss": 0.5569, + "step": 567 + }, + { + "epoch": 2.9686411149825784, + "grad_norm": 0.4914791262393272, + "learning_rate": 2.3255818832423894e-09, + "loss": 0.5232, + "step": 568 + }, + { + "epoch": 2.9738675958188154, + "grad_norm": 0.4310628707346215, + "learning_rate": 1.4884139455861868e-09, + "loss": 0.5572, + "step": 569 + }, + { + "epoch": 2.979094076655052, + "grad_norm": 0.43105949566502877, + "learning_rate": 8.372510186388516e-10, + "loss": 0.5603, + "step": 570 + }, + { + "epoch": 2.984320557491289, + "grad_norm": 0.3988129414746118, + "learning_rate": 3.7211733352748856e-10, + "loss": 0.4893, + "step": 571 + }, + { + "epoch": 2.989547038327526, + "grad_norm": 0.4326905501521538, + "learning_rate": 9.303019884387976e-11, + "loss": 0.5622, + "step": 572 + }, + { + "epoch": 2.994773519163763, + "grad_norm": 0.4266940308017901, + "learning_rate": 0.0, + "loss": 0.4927, + "step": 573 + }, + { + "epoch": 2.994773519163763, + "step": 573, + "total_flos": 520358168002560.0, + "train_loss": 0.6214590458553707, + "train_runtime": 8980.1589, + "train_samples_per_second": 6.133, + "train_steps_per_second": 0.064 + } + ], + "logging_steps": 1, + "max_steps": 573, + "num_input_tokens_seen": 0, + "num_train_epochs": 3, + "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": 520358168002560.0, + "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..8ddfcc4 --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0d0c0c83c1ae29f3d9779f18c0d8aeb84fa40342b927b3137f8d15a6ef3390d +size 7352 diff --git a/training_loss.png b/training_loss.png new file mode 100644 index 0000000..4e80520 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