commit b594b8ca9145d76d89fd478f3889764756807e82 Author: ModelHub XC Date: Sat Aug 8 18:55:13 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mlfoundations-dev/oh-dcft-v3.1-llama-3.3-70b-qwen Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d10e3a0 --- /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 + +tokenizer.json filter=lfs diff=lfs merge=lfs -text +model-00002-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +training_args.bin filter=lfs diff=lfs merge=lfs -text +merges.txt filter=lfs diff=lfs merge=lfs -text +model-00004-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +vocab.json filter=lfs diff=lfs merge=lfs -text +model-00003-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +model-00001-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..b74bf3b --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +library_name: transformers +license: apache-2.0 +base_model: Qwen/Qwen2.5-7B +tags: +- llama-factory +- full +- generated_from_trainer +model-index: +- name: oh-dcft-v3.1-llama-3.3-70b-qwen + results: [] +--- + + + +# oh-dcft-v3.1-llama-3.3-70b-qwen + +This model is a fine-tuned version of [Qwen/Qwen2.5-7B](https://huggingface.co/Qwen/Qwen2.5-7B) on the mlfoundations-dev/oh-dcft-v3.1-llama-3.3-70b dataset. +It achieves the following results on the evaluation set: +- Loss: 0.4057 + +## Model description + +More information needed + +## Intended uses & limitations + +More information needed + +## Training and evaluation data + +More information needed + +## Training procedure + +### Training hyperparameters + +The following hyperparameters were used during training: +- learning_rate: 5e-06 +- train_batch_size: 8 +- eval_batch_size: 8 +- seed: 42 +- distributed_type: multi-GPU +- num_devices: 8 +- gradient_accumulation_steps: 2 +- total_train_batch_size: 128 +- total_eval_batch_size: 64 +- 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: constant +- num_epochs: 3.0 + +### Training results + +| Training Loss | Epoch | Step | Validation Loss | +|:-------------:|:------:|:----:|:---------------:| +| 0.4024 | 0.9997 | 1861 | 0.4043 | +| 0.3514 | 2.0 | 3723 | 0.3974 | +| 0.3035 | 2.9992 | 5583 | 0.4057 | + + +### Framework versions + +- Transformers 4.46.1 +- Pytorch 2.3.0 +- Datasets 3.1.0 +- 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..cb88f45 --- /dev/null +++ b/all_results.json @@ -0,0 +1,12 @@ +{ + "epoch": 2.999194198227236, + "eval_loss": 0.405712366104126, + "eval_runtime": 469.1641, + "eval_samples_per_second": 26.728, + "eval_steps_per_second": 0.418, + "total_flos": 2926650442383360.0, + "train_loss": 0.3617401811868598, + "train_runtime": 75547.7589, + "train_samples_per_second": 9.461, + "train_steps_per_second": 0.074 +} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..f517eef --- /dev/null +++ b/config.json @@ -0,0 +1,30 @@ +{ + "_name_or_path": "Qwen/Qwen2.5-7B", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 151643, + "eos_token_id": 151643, + "hidden_act": "silu", + "hidden_size": 3584, + "initializer_range": 0.02, + "intermediate_size": 18944, + "max_position_embeddings": 131072, + "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_mrope": false, + "use_sliding_window": false, + "vocab_size": 152064 +} diff --git a/configs.yaml b/configs.yaml new file mode 100644 index 0000000..98dfbf7 --- /dev/null +++ b/configs.yaml @@ -0,0 +1,41 @@ +adam_beta1: '0.9' +adam_beta2: '0.999' +bf16: 'True' +cutoff_len: '2048' +dataset: mlfoundations-dev/oh-dcft-v3.1-llama-3.3-70b +dataset_dir: ONLINE +ddp_timeout: '180000000' +deepspeed: /opt/ml/code/zero3.json +do_train: 'True' +enable_liger_kernel: 'False' +eval_strategy: epoch +finetuning_type: full +formatting: sharegpt +global_batch_size: '128' +gradient_accumulation_steps: '2' +gradient_checkpointing: 'True' +hub_model_id: mlfoundations-dev/oh-dcft-v3.1-llama-3.3-70b-qwen +learning_rate: 5e-06 +logging_steps: '10' +lr_scheduler_type: constant +max_grad_norm: '1' +messages: conversations +model_name_or_path: Qwen/Qwen2.5-7B +neat_packing: 'True' +num_train_epochs: '3.0' +output_dir: /opt/ml/model +overwrite_cache: 'True' +overwrite_output_dir: 'True' +packing: 'True' +per_device_train_batch_size: '8' +plot_loss: 'True' +preprocessing_num_workers: '16' +push_to_db: 'True' +push_to_hub: 'True' +report_to: wandb +run_name: oh-dcft-v3.1-llama-3.3-70b-qwen +save_strategy: epoch +stage: sft +template: qwen +val_size: '0.05' +weight_decay: '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/eval_results.json b/eval_results.json new file mode 100644 index 0000000..f62dbef --- /dev/null +++ b/eval_results.json @@ -0,0 +1,7 @@ +{ + "epoch": 2.999194198227236, + "eval_loss": 0.405712366104126, + "eval_runtime": 469.1641, + "eval_samples_per_second": 26.728, + "eval_steps_per_second": 0.418 +} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..504ff91 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,6 @@ +{ + "bos_token_id": 151643, + "eos_token_id": 151643, + "max_new_tokens": 2048, + "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..d2cfe2f --- /dev/null +++ b/model-00001-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98a7b1427b4c10d046ce323753fbc70883610d0a25ccfc4f47fd24b8663ce5b5 +size 4877660776 diff --git a/model-00002-of-00004.safetensors b/model-00002-of-00004.safetensors new file mode 100644 index 0000000..302c60c --- /dev/null +++ b/model-00002-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abc7ab8576c14d40a96898280674c7b579d75d47691e3d948f2ff58de440e5f6 +size 4932751008 diff --git a/model-00003-of-00004.safetensors b/model-00003-of-00004.safetensors new file mode 100644 index 0000000..71a87d4 --- /dev/null +++ b/model-00003-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5004f17e412bc3d76e220e600a97f0c7d7dbf73a15b83a5409a64929e413b367 +size 4330865200 diff --git a/model-00004-of-00004.safetensors b/model-00004-of-00004.safetensors new file mode 100644 index 0000000..b4c571a --- /dev/null +++ b/model-00004-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5b4aff1512dc4747b9749d50a9112822e216d27ccd6e67d2692e27e00b147ca +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..ac23c0a --- /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": "<|im_end|>", + "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..d24b2b8 --- /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 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 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": "<|im_end|>", + "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..367fa18 --- /dev/null +++ b/train_results.json @@ -0,0 +1,8 @@ +{ + "epoch": 2.999194198227236, + "total_flos": 2926650442383360.0, + "train_loss": 0.3617401811868598, + "train_runtime": 75547.7589, + "train_samples_per_second": 9.461, + "train_steps_per_second": 0.074 +} \ No newline at end of file diff --git a/trainer_log.jsonl b/trainer_log.jsonl new file mode 100644 index 0000000..a46cff2 --- /dev/null +++ b/trainer_log.jsonl @@ -0,0 +1,562 @@ +{"current_steps": 10, "total_steps": 5583, "loss": 0.5524, "lr": 5e-06, "epoch": 0.005372011818426001, "percentage": 0.18, "elapsed_time": "0:02:17", "remaining_time": "21:15:12"} +{"current_steps": 20, "total_steps": 5583, "loss": 0.5237, "lr": 5e-06, "epoch": 0.010744023636852002, "percentage": 0.36, "elapsed_time": "0:04:29", "remaining_time": "20:48:31"} +{"current_steps": 30, "total_steps": 5583, "loss": 0.5011, "lr": 5e-06, "epoch": 0.016116035455278, "percentage": 0.54, "elapsed_time": "0:06:41", "remaining_time": "20:38:33"} +{"current_steps": 40, "total_steps": 5583, "loss": 0.4903, "lr": 5e-06, "epoch": 0.021488047273704004, "percentage": 0.72, "elapsed_time": "0:08:53", "remaining_time": "20:32:47"} +{"current_steps": 50, "total_steps": 5583, "loss": 0.4725, "lr": 5e-06, "epoch": 0.026860059092130004, "percentage": 0.9, "elapsed_time": "0:11:06", "remaining_time": "20:28:23"} +{"current_steps": 60, "total_steps": 5583, "loss": 0.4683, "lr": 5e-06, "epoch": 0.032232070910556, "percentage": 1.07, "elapsed_time": "0:13:17", "remaining_time": "20:23:26"} +{"current_steps": 70, "total_steps": 5583, "loss": 0.465, "lr": 5e-06, "epoch": 0.037604082728982004, "percentage": 1.25, "elapsed_time": "0:15:29", "remaining_time": "20:19:53"} +{"current_steps": 80, "total_steps": 5583, "loss": 0.4744, "lr": 5e-06, "epoch": 0.04297609454740801, "percentage": 1.43, "elapsed_time": "0:17:41", "remaining_time": "20:16:43"} +{"current_steps": 90, "total_steps": 5583, "loss": 0.4564, "lr": 5e-06, "epoch": 0.048348106365834004, "percentage": 1.61, "elapsed_time": "0:19:53", "remaining_time": "20:13:42"} +{"current_steps": 100, "total_steps": 5583, "loss": 0.4466, "lr": 5e-06, "epoch": 0.05372011818426001, "percentage": 1.79, "elapsed_time": "0:22:05", "remaining_time": "20:10:54"} +{"current_steps": 110, "total_steps": 5583, "loss": 0.4594, "lr": 5e-06, "epoch": 0.059092130002686004, "percentage": 1.97, "elapsed_time": "0:24:17", "remaining_time": "20:08:16"} +{"current_steps": 120, "total_steps": 5583, "loss": 0.4608, "lr": 5e-06, "epoch": 0.064464141821112, "percentage": 2.15, "elapsed_time": "0:26:29", "remaining_time": "20:05:44"} +{"current_steps": 130, "total_steps": 5583, "loss": 0.4594, "lr": 5e-06, "epoch": 0.069836153639538, "percentage": 2.33, "elapsed_time": "0:28:41", "remaining_time": "20:03:14"} +{"current_steps": 140, "total_steps": 5583, "loss": 0.4537, "lr": 5e-06, "epoch": 0.07520816545796401, "percentage": 2.51, "elapsed_time": "0:30:53", "remaining_time": "20:00:53"} +{"current_steps": 150, "total_steps": 5583, "loss": 0.4614, "lr": 5e-06, "epoch": 0.08058017727639001, "percentage": 2.69, "elapsed_time": "0:33:05", "remaining_time": "19:58:38"} +{"current_steps": 160, "total_steps": 5583, "loss": 0.4677, "lr": 5e-06, "epoch": 0.08595218909481601, "percentage": 2.87, "elapsed_time": "0:35:17", "remaining_time": "19:56:16"} +{"current_steps": 170, "total_steps": 5583, "loss": 0.4663, "lr": 5e-06, "epoch": 0.091324200913242, "percentage": 3.04, "elapsed_time": "0:37:29", "remaining_time": "19:53:53"} +{"current_steps": 180, "total_steps": 5583, "loss": 0.4445, "lr": 5e-06, "epoch": 0.09669621273166801, "percentage": 3.22, "elapsed_time": "0:39:41", "remaining_time": "19:51:27"} +{"current_steps": 190, "total_steps": 5583, "loss": 0.4386, "lr": 5e-06, "epoch": 0.10206822455009401, "percentage": 3.4, "elapsed_time": "0:41:53", "remaining_time": "19:49:05"} +{"current_steps": 200, "total_steps": 5583, "loss": 0.4358, "lr": 5e-06, "epoch": 0.10744023636852001, "percentage": 3.58, "elapsed_time": "0:44:05", "remaining_time": "19:46:46"} +{"current_steps": 210, "total_steps": 5583, "loss": 0.4509, "lr": 5e-06, "epoch": 0.11281224818694602, "percentage": 3.76, "elapsed_time": "0:46:17", "remaining_time": "19:44:16"} +{"current_steps": 220, "total_steps": 5583, "loss": 0.454, "lr": 5e-06, "epoch": 0.11818426000537201, "percentage": 3.94, "elapsed_time": "0:48:28", "remaining_time": "19:41:50"} +{"current_steps": 230, "total_steps": 5583, "loss": 0.4402, "lr": 5e-06, "epoch": 0.12355627182379801, "percentage": 4.12, "elapsed_time": "0:50:40", "remaining_time": "19:39:34"} +{"current_steps": 240, "total_steps": 5583, "loss": 0.4492, "lr": 5e-06, "epoch": 0.128928283642224, "percentage": 4.3, "elapsed_time": "0:52:52", "remaining_time": "19:37:18"} +{"current_steps": 250, "total_steps": 5583, "loss": 0.4525, "lr": 5e-06, "epoch": 0.13430029546065, "percentage": 4.48, "elapsed_time": "0:55:04", "remaining_time": "19:34:53"} +{"current_steps": 260, "total_steps": 5583, "loss": 0.4423, "lr": 5e-06, "epoch": 0.139672307279076, "percentage": 4.66, "elapsed_time": "0:57:16", "remaining_time": "19:32:34"} +{"current_steps": 270, "total_steps": 5583, "loss": 0.4454, "lr": 5e-06, "epoch": 0.145044319097502, "percentage": 4.84, "elapsed_time": "0:59:28", "remaining_time": "19:30:20"} +{"current_steps": 280, "total_steps": 5583, "loss": 0.4421, "lr": 5e-06, "epoch": 0.15041633091592801, "percentage": 5.02, "elapsed_time": "1:01:40", "remaining_time": "19:28:07"} +{"current_steps": 290, "total_steps": 5583, "loss": 0.4446, "lr": 5e-06, "epoch": 0.15578834273435402, "percentage": 5.19, "elapsed_time": "1:03:52", "remaining_time": "19:25:55"} +{"current_steps": 300, "total_steps": 5583, "loss": 0.436, "lr": 5e-06, "epoch": 0.16116035455278002, "percentage": 5.37, "elapsed_time": "1:06:04", "remaining_time": "19:23:40"} +{"current_steps": 310, "total_steps": 5583, "loss": 0.4299, "lr": 5e-06, "epoch": 0.16653236637120603, "percentage": 5.55, "elapsed_time": "1:08:16", "remaining_time": "19:21:27"} +{"current_steps": 320, "total_steps": 5583, "loss": 0.472, "lr": 5e-06, "epoch": 0.17190437818963203, "percentage": 5.73, "elapsed_time": "1:10:29", "remaining_time": "19:19:20"} +{"current_steps": 330, "total_steps": 5583, "loss": 0.451, "lr": 5e-06, "epoch": 0.177276390008058, "percentage": 5.91, "elapsed_time": "1:12:41", "remaining_time": "19:17:04"} +{"current_steps": 340, "total_steps": 5583, "loss": 0.4402, "lr": 5e-06, "epoch": 0.182648401826484, "percentage": 6.09, "elapsed_time": "1:14:53", "remaining_time": "19:14:49"} +{"current_steps": 350, "total_steps": 5583, "loss": 0.4427, "lr": 5e-06, "epoch": 0.18802041364491, "percentage": 6.27, "elapsed_time": "1:17:05", "remaining_time": "19:12:37"} +{"current_steps": 360, "total_steps": 5583, "loss": 0.435, "lr": 5e-06, "epoch": 0.19339242546333602, "percentage": 6.45, "elapsed_time": "1:19:17", "remaining_time": "19:10:25"} +{"current_steps": 370, "total_steps": 5583, "loss": 0.457, "lr": 5e-06, "epoch": 0.19876443728176202, "percentage": 6.63, "elapsed_time": "1:21:29", "remaining_time": "19:08:11"} +{"current_steps": 380, "total_steps": 5583, "loss": 0.4345, "lr": 5e-06, "epoch": 0.20413644910018802, "percentage": 6.81, "elapsed_time": "1:23:41", "remaining_time": "19:05:54"} +{"current_steps": 390, "total_steps": 5583, "loss": 0.4653, "lr": 5e-06, "epoch": 0.20950846091861403, "percentage": 6.99, "elapsed_time": "1:25:53", "remaining_time": "19:03:41"} +{"current_steps": 400, "total_steps": 5583, "loss": 0.4329, "lr": 5e-06, "epoch": 0.21488047273704003, "percentage": 7.16, "elapsed_time": "1:28:05", "remaining_time": "19:01:28"} +{"current_steps": 410, "total_steps": 5583, "loss": 0.4372, "lr": 5e-06, "epoch": 0.22025248455546603, "percentage": 7.34, "elapsed_time": "1:30:17", "remaining_time": "18:59:13"} +{"current_steps": 420, "total_steps": 5583, "loss": 0.4483, "lr": 5e-06, "epoch": 0.22562449637389204, "percentage": 7.52, "elapsed_time": "1:32:29", "remaining_time": "18:56:57"} +{"current_steps": 430, "total_steps": 5583, "loss": 0.4468, "lr": 5e-06, "epoch": 0.230996508192318, "percentage": 7.7, "elapsed_time": "1:34:41", "remaining_time": "18:54:45"} +{"current_steps": 440, "total_steps": 5583, "loss": 0.4233, "lr": 5e-06, "epoch": 0.23636852001074402, "percentage": 7.88, "elapsed_time": "1:36:53", "remaining_time": "18:52:34"} +{"current_steps": 450, "total_steps": 5583, "loss": 0.4282, "lr": 5e-06, "epoch": 0.24174053182917002, "percentage": 8.06, "elapsed_time": "1:39:06", "remaining_time": "18:50:24"} +{"current_steps": 460, "total_steps": 5583, "loss": 0.438, "lr": 5e-06, "epoch": 0.24711254364759602, "percentage": 8.24, "elapsed_time": "1:41:18", "remaining_time": "18:48:13"} +{"current_steps": 470, "total_steps": 5583, "loss": 0.4405, "lr": 5e-06, "epoch": 0.252484555466022, "percentage": 8.42, "elapsed_time": "1:43:30", "remaining_time": "18:46:02"} +{"current_steps": 480, "total_steps": 5583, "loss": 0.4249, "lr": 5e-06, "epoch": 0.257856567284448, "percentage": 8.6, "elapsed_time": "1:45:42", "remaining_time": "18:43:50"} +{"current_steps": 490, "total_steps": 5583, "loss": 0.4444, "lr": 5e-06, "epoch": 0.263228579102874, "percentage": 8.78, "elapsed_time": "1:47:54", "remaining_time": "18:41:36"} +{"current_steps": 500, "total_steps": 5583, "loss": 0.4445, "lr": 5e-06, "epoch": 0.2686005909213, "percentage": 8.96, "elapsed_time": "1:50:06", "remaining_time": "18:39:20"} +{"current_steps": 510, "total_steps": 5583, "loss": 0.4425, "lr": 5e-06, "epoch": 0.273972602739726, "percentage": 9.13, "elapsed_time": "1:52:18", "remaining_time": "18:37:08"} +{"current_steps": 520, "total_steps": 5583, "loss": 0.4389, "lr": 5e-06, "epoch": 0.279344614558152, "percentage": 9.31, "elapsed_time": "1:54:30", "remaining_time": "18:34:56"} +{"current_steps": 530, "total_steps": 5583, "loss": 0.4288, "lr": 5e-06, "epoch": 0.284716626376578, "percentage": 9.49, "elapsed_time": "1:56:42", "remaining_time": "18:32:40"} +{"current_steps": 540, "total_steps": 5583, "loss": 0.4375, "lr": 5e-06, "epoch": 0.290088638195004, "percentage": 9.67, "elapsed_time": "1:58:54", "remaining_time": "18:30:30"} +{"current_steps": 550, "total_steps": 5583, "loss": 0.4318, "lr": 5e-06, "epoch": 0.29546065001343, "percentage": 9.85, "elapsed_time": "2:01:06", "remaining_time": "18:28:18"} +{"current_steps": 560, "total_steps": 5583, "loss": 0.4296, "lr": 5e-06, "epoch": 0.30083266183185603, "percentage": 10.03, "elapsed_time": "2:03:19", "remaining_time": "18:26:07"} +{"current_steps": 570, "total_steps": 5583, "loss": 0.4335, "lr": 5e-06, "epoch": 0.30620467365028203, "percentage": 10.21, "elapsed_time": "2:05:31", "remaining_time": "18:23:58"} +{"current_steps": 580, "total_steps": 5583, "loss": 0.4249, "lr": 5e-06, "epoch": 0.31157668546870804, "percentage": 10.39, "elapsed_time": "2:07:43", "remaining_time": "18:21:47"} +{"current_steps": 590, "total_steps": 5583, "loss": 0.4284, "lr": 5e-06, "epoch": 0.31694869728713404, "percentage": 10.57, "elapsed_time": "2:09:56", "remaining_time": "18:19:36"} +{"current_steps": 600, "total_steps": 5583, "loss": 0.4307, "lr": 5e-06, "epoch": 0.32232070910556004, "percentage": 10.75, "elapsed_time": "2:12:08", "remaining_time": "18:17:25"} +{"current_steps": 610, "total_steps": 5583, "loss": 0.4263, "lr": 5e-06, "epoch": 0.32769272092398605, "percentage": 10.93, "elapsed_time": "2:14:20", "remaining_time": "18:15:12"} +{"current_steps": 620, "total_steps": 5583, "loss": 0.4231, "lr": 5e-06, "epoch": 0.33306473274241205, "percentage": 11.11, "elapsed_time": "2:16:32", "remaining_time": "18:13:00"} +{"current_steps": 630, "total_steps": 5583, "loss": 0.4243, "lr": 5e-06, "epoch": 0.33843674456083805, "percentage": 11.28, "elapsed_time": "2:18:44", "remaining_time": "18:10:43"} +{"current_steps": 640, "total_steps": 5583, "loss": 0.4219, "lr": 5e-06, "epoch": 0.34380875637926406, "percentage": 11.46, "elapsed_time": "2:20:55", "remaining_time": "18:08:25"} +{"current_steps": 650, "total_steps": 5583, "loss": 0.4213, "lr": 5e-06, "epoch": 0.34918076819769006, "percentage": 11.64, "elapsed_time": "2:23:07", "remaining_time": "18:06:12"} +{"current_steps": 660, "total_steps": 5583, "loss": 0.4242, "lr": 5e-06, "epoch": 0.354552780016116, "percentage": 11.82, "elapsed_time": "2:25:19", "remaining_time": "18:04:02"} +{"current_steps": 670, "total_steps": 5583, "loss": 0.4134, "lr": 5e-06, "epoch": 0.359924791834542, "percentage": 12.0, "elapsed_time": "2:27:32", "remaining_time": "18:01:52"} +{"current_steps": 680, "total_steps": 5583, "loss": 0.4319, "lr": 5e-06, "epoch": 0.365296803652968, "percentage": 12.18, "elapsed_time": "2:29:43", "remaining_time": "17:59:37"} +{"current_steps": 690, "total_steps": 5583, "loss": 0.42, "lr": 5e-06, "epoch": 0.370668815471394, "percentage": 12.36, "elapsed_time": "2:31:56", "remaining_time": "17:57:25"} +{"current_steps": 700, "total_steps": 5583, "loss": 0.4292, "lr": 5e-06, "epoch": 0.37604082728982, "percentage": 12.54, "elapsed_time": "2:34:08", "remaining_time": "17:55:14"} +{"current_steps": 710, "total_steps": 5583, "loss": 0.4309, "lr": 5e-06, "epoch": 0.381412839108246, "percentage": 12.72, "elapsed_time": "2:36:20", "remaining_time": "17:53:02"} +{"current_steps": 720, "total_steps": 5583, "loss": 0.4292, "lr": 5e-06, "epoch": 0.38678485092667203, "percentage": 12.9, "elapsed_time": "2:38:32", "remaining_time": "17:50:50"} +{"current_steps": 730, "total_steps": 5583, "loss": 0.426, "lr": 5e-06, "epoch": 0.39215686274509803, "percentage": 13.08, "elapsed_time": "2:40:44", "remaining_time": "17:48:38"} +{"current_steps": 740, "total_steps": 5583, "loss": 0.4205, "lr": 5e-06, "epoch": 0.39752887456352404, "percentage": 13.25, "elapsed_time": "2:42:56", "remaining_time": "17:46:24"} +{"current_steps": 750, "total_steps": 5583, "loss": 0.4319, "lr": 5e-06, "epoch": 0.40290088638195004, "percentage": 13.43, "elapsed_time": "2:45:08", "remaining_time": "17:44:11"} +{"current_steps": 760, "total_steps": 5583, "loss": 0.4341, "lr": 5e-06, "epoch": 0.40827289820037604, "percentage": 13.61, "elapsed_time": "2:47:20", "remaining_time": "17:41:58"} +{"current_steps": 770, "total_steps": 5583, "loss": 0.4317, "lr": 5e-06, "epoch": 0.41364491001880205, "percentage": 13.79, "elapsed_time": "2:49:32", "remaining_time": "17:39:46"} +{"current_steps": 780, "total_steps": 5583, "loss": 0.4315, "lr": 5e-06, "epoch": 0.41901692183722805, "percentage": 13.97, "elapsed_time": "2:51:45", "remaining_time": "17:37:36"} +{"current_steps": 790, "total_steps": 5583, "loss": 0.4213, "lr": 5e-06, "epoch": 0.42438893365565405, "percentage": 14.15, "elapsed_time": "2:53:57", "remaining_time": "17:35:25"} +{"current_steps": 800, "total_steps": 5583, "loss": 0.4128, "lr": 5e-06, "epoch": 0.42976094547408006, "percentage": 14.33, "elapsed_time": "2:56:09", "remaining_time": "17:33:15"} +{"current_steps": 810, "total_steps": 5583, "loss": 0.4209, "lr": 5e-06, "epoch": 0.43513295729250606, "percentage": 14.51, "elapsed_time": "2:58:22", "remaining_time": "17:31:03"} +{"current_steps": 820, "total_steps": 5583, "loss": 0.4178, "lr": 5e-06, "epoch": 0.44050496911093207, "percentage": 14.69, "elapsed_time": "3:00:34", "remaining_time": "17:28:53"} +{"current_steps": 830, "total_steps": 5583, "loss": 0.4154, "lr": 5e-06, "epoch": 0.44587698092935807, "percentage": 14.87, "elapsed_time": "3:02:46", "remaining_time": "17:26:41"} +{"current_steps": 840, "total_steps": 5583, "loss": 0.4231, "lr": 5e-06, "epoch": 0.4512489927477841, "percentage": 15.05, "elapsed_time": "3:04:58", "remaining_time": "17:24:29"} +{"current_steps": 850, "total_steps": 5583, "loss": 0.4322, "lr": 5e-06, "epoch": 0.45662100456621, "percentage": 15.22, "elapsed_time": "3:07:11", "remaining_time": "17:22:18"} +{"current_steps": 860, "total_steps": 5583, "loss": 0.4148, "lr": 5e-06, "epoch": 0.461993016384636, "percentage": 15.4, "elapsed_time": "3:09:23", "remaining_time": "17:20:07"} +{"current_steps": 870, "total_steps": 5583, "loss": 0.4203, "lr": 5e-06, "epoch": 0.467365028203062, "percentage": 15.58, "elapsed_time": "3:11:35", "remaining_time": "17:17:55"} +{"current_steps": 880, "total_steps": 5583, "loss": 0.4167, "lr": 5e-06, "epoch": 0.47273704002148803, "percentage": 15.76, "elapsed_time": "3:13:48", "remaining_time": "17:15:44"} +{"current_steps": 890, "total_steps": 5583, "loss": 0.4167, "lr": 5e-06, "epoch": 0.47810905183991403, "percentage": 15.94, "elapsed_time": "3:16:00", "remaining_time": "17:13:33"} +{"current_steps": 900, "total_steps": 5583, "loss": 0.4229, "lr": 5e-06, "epoch": 0.48348106365834004, "percentage": 16.12, "elapsed_time": "3:18:12", "remaining_time": "17:11:22"} +{"current_steps": 910, "total_steps": 5583, "loss": 0.4183, "lr": 5e-06, "epoch": 0.48885307547676604, "percentage": 16.3, "elapsed_time": "3:20:25", "remaining_time": "17:09:11"} +{"current_steps": 920, "total_steps": 5583, "loss": 0.4143, "lr": 5e-06, "epoch": 0.49422508729519204, "percentage": 16.48, "elapsed_time": "3:22:37", "remaining_time": "17:06:59"} +{"current_steps": 930, "total_steps": 5583, "loss": 0.4233, "lr": 5e-06, "epoch": 0.49959709911361805, "percentage": 16.66, "elapsed_time": "3:24:49", "remaining_time": "17:04:48"} +{"current_steps": 940, "total_steps": 5583, "loss": 0.4111, "lr": 5e-06, "epoch": 0.504969110932044, "percentage": 16.84, "elapsed_time": "3:27:01", "remaining_time": "17:02:33"} +{"current_steps": 950, "total_steps": 5583, "loss": 0.4178, "lr": 5e-06, "epoch": 0.51034112275047, "percentage": 17.02, "elapsed_time": "3:29:13", "remaining_time": "17:00:19"} +{"current_steps": 960, "total_steps": 5583, "loss": 0.4202, "lr": 5e-06, "epoch": 0.515713134568896, "percentage": 17.2, "elapsed_time": "3:31:24", "remaining_time": "16:58:04"} +{"current_steps": 970, "total_steps": 5583, "loss": 0.4105, "lr": 5e-06, "epoch": 0.5210851463873221, "percentage": 17.37, "elapsed_time": "3:33:36", "remaining_time": "16:55:51"} +{"current_steps": 980, "total_steps": 5583, "loss": 0.4117, "lr": 5e-06, "epoch": 0.526457158205748, "percentage": 17.55, "elapsed_time": "3:35:48", "remaining_time": "16:53:39"} +{"current_steps": 990, "total_steps": 5583, "loss": 0.4173, "lr": 5e-06, "epoch": 0.5318291700241741, "percentage": 17.73, "elapsed_time": "3:38:01", "remaining_time": "16:51:28"} +{"current_steps": 1000, "total_steps": 5583, "loss": 0.425, "lr": 5e-06, "epoch": 0.5372011818426, "percentage": 17.91, "elapsed_time": "3:40:13", "remaining_time": "16:49:17"} +{"current_steps": 1010, "total_steps": 5583, "loss": 0.4159, "lr": 5e-06, "epoch": 0.5425731936610261, "percentage": 18.09, "elapsed_time": "3:42:25", "remaining_time": "16:47:03"} +{"current_steps": 1020, "total_steps": 5583, "loss": 0.4188, "lr": 5e-06, "epoch": 0.547945205479452, "percentage": 18.27, "elapsed_time": "3:44:37", "remaining_time": "16:44:50"} +{"current_steps": 1030, "total_steps": 5583, "loss": 0.4139, "lr": 5e-06, "epoch": 0.5533172172978781, "percentage": 18.45, "elapsed_time": "3:46:49", "remaining_time": "16:42:39"} +{"current_steps": 1040, "total_steps": 5583, "loss": 0.4366, "lr": 5e-06, "epoch": 0.558689229116304, "percentage": 18.63, "elapsed_time": "3:49:02", "remaining_time": "16:40:29"} +{"current_steps": 1050, "total_steps": 5583, "loss": 0.4151, "lr": 5e-06, "epoch": 0.5640612409347301, "percentage": 18.81, "elapsed_time": "3:51:14", "remaining_time": "16:38:18"} +{"current_steps": 1060, "total_steps": 5583, "loss": 0.4228, "lr": 5e-06, "epoch": 0.569433252753156, "percentage": 18.99, "elapsed_time": "3:53:26", "remaining_time": "16:36:06"} +{"current_steps": 1070, "total_steps": 5583, "loss": 0.415, "lr": 5e-06, "epoch": 0.5748052645715821, "percentage": 19.17, "elapsed_time": "3:55:39", "remaining_time": "16:33:55"} +{"current_steps": 1080, "total_steps": 5583, "loss": 0.4096, "lr": 5e-06, "epoch": 0.580177276390008, "percentage": 19.34, "elapsed_time": "3:57:51", "remaining_time": "16:31:45"} +{"current_steps": 1090, "total_steps": 5583, "loss": 0.423, "lr": 5e-06, "epoch": 0.5855492882084341, "percentage": 19.52, "elapsed_time": "4:00:03", "remaining_time": "16:29:33"} +{"current_steps": 1100, "total_steps": 5583, "loss": 0.4269, "lr": 5e-06, "epoch": 0.59092130002686, "percentage": 19.7, "elapsed_time": "4:02:16", "remaining_time": "16:27:21"} +{"current_steps": 1110, "total_steps": 5583, "loss": 0.4118, "lr": 5e-06, "epoch": 0.5962933118452861, "percentage": 19.88, "elapsed_time": "4:04:28", "remaining_time": "16:25:09"} +{"current_steps": 1120, "total_steps": 5583, "loss": 0.4045, "lr": 5e-06, "epoch": 0.6016653236637121, "percentage": 20.06, "elapsed_time": "4:06:40", "remaining_time": "16:22:56"} +{"current_steps": 1130, "total_steps": 5583, "loss": 0.4066, "lr": 5e-06, "epoch": 0.607037335482138, "percentage": 20.24, "elapsed_time": "4:08:52", "remaining_time": "16:20:44"} +{"current_steps": 1140, "total_steps": 5583, "loss": 0.411, "lr": 5e-06, "epoch": 0.6124093473005641, "percentage": 20.42, "elapsed_time": "4:11:04", "remaining_time": "16:18:33"} +{"current_steps": 1150, "total_steps": 5583, "loss": 0.419, "lr": 5e-06, "epoch": 0.61778135911899, "percentage": 20.6, "elapsed_time": "4:13:17", "remaining_time": "16:16:23"} +{"current_steps": 1160, "total_steps": 5583, "loss": 0.4245, "lr": 5e-06, "epoch": 0.6231533709374161, "percentage": 20.78, "elapsed_time": "4:15:29", "remaining_time": "16:14:12"} +{"current_steps": 1170, "total_steps": 5583, "loss": 0.4283, "lr": 5e-06, "epoch": 0.628525382755842, "percentage": 20.96, "elapsed_time": "4:17:42", "remaining_time": "16:12:01"} +{"current_steps": 1180, "total_steps": 5583, "loss": 0.4125, "lr": 5e-06, "epoch": 0.6338973945742681, "percentage": 21.14, "elapsed_time": "4:19:55", "remaining_time": "16:09:50"} +{"current_steps": 1190, "total_steps": 5583, "loss": 0.4146, "lr": 5e-06, "epoch": 0.639269406392694, "percentage": 21.31, "elapsed_time": "4:22:07", "remaining_time": "16:07:39"} +{"current_steps": 1200, "total_steps": 5583, "loss": 0.4164, "lr": 5e-06, "epoch": 0.6446414182111201, "percentage": 21.49, "elapsed_time": "4:24:20", "remaining_time": "16:05:28"} +{"current_steps": 1210, "total_steps": 5583, "loss": 0.4174, "lr": 5e-06, "epoch": 0.650013430029546, "percentage": 21.67, "elapsed_time": "4:26:32", "remaining_time": "16:03:18"} +{"current_steps": 1220, "total_steps": 5583, "loss": 0.4214, "lr": 5e-06, "epoch": 0.6553854418479721, "percentage": 21.85, "elapsed_time": "4:28:45", "remaining_time": "16:01:07"} +{"current_steps": 1230, "total_steps": 5583, "loss": 0.4063, "lr": 5e-06, "epoch": 0.660757453666398, "percentage": 22.03, "elapsed_time": "4:30:57", "remaining_time": "15:58:56"} +{"current_steps": 1240, "total_steps": 5583, "loss": 0.4194, "lr": 5e-06, "epoch": 0.6661294654848241, "percentage": 22.21, "elapsed_time": "4:33:10", "remaining_time": "15:56:45"} +{"current_steps": 1250, "total_steps": 5583, "loss": 0.4174, "lr": 5e-06, "epoch": 0.67150147730325, "percentage": 22.39, "elapsed_time": "4:35:22", "remaining_time": "15:54:34"} +{"current_steps": 1260, "total_steps": 5583, "loss": 0.4088, "lr": 5e-06, "epoch": 0.6768734891216761, "percentage": 22.57, "elapsed_time": "4:37:35", "remaining_time": "15:52:24"} +{"current_steps": 1270, "total_steps": 5583, "loss": 0.4239, "lr": 5e-06, "epoch": 0.6822455009401021, "percentage": 22.75, "elapsed_time": "4:39:47", "remaining_time": "15:50:12"} +{"current_steps": 1280, "total_steps": 5583, "loss": 0.4128, "lr": 5e-06, "epoch": 0.6876175127585281, "percentage": 22.93, "elapsed_time": "4:42:00", "remaining_time": "15:48:00"} +{"current_steps": 1290, "total_steps": 5583, "loss": 0.4184, "lr": 5e-06, "epoch": 0.6929895245769541, "percentage": 23.11, "elapsed_time": "4:44:12", "remaining_time": "15:45:48"} +{"current_steps": 1300, "total_steps": 5583, "loss": 0.4124, "lr": 5e-06, "epoch": 0.6983615363953801, "percentage": 23.28, "elapsed_time": "4:46:24", "remaining_time": "15:43:36"} +{"current_steps": 1310, "total_steps": 5583, "loss": 0.4257, "lr": 5e-06, "epoch": 0.7037335482138061, "percentage": 23.46, "elapsed_time": "4:48:36", "remaining_time": "15:41:22"} +{"current_steps": 1320, "total_steps": 5583, "loss": 0.4098, "lr": 5e-06, "epoch": 0.709105560032232, "percentage": 23.64, "elapsed_time": "4:50:48", "remaining_time": "15:39:10"} +{"current_steps": 1330, "total_steps": 5583, "loss": 0.4089, "lr": 5e-06, "epoch": 0.7144775718506581, "percentage": 23.82, "elapsed_time": "4:53:00", "remaining_time": "15:36:59"} +{"current_steps": 1340, "total_steps": 5583, "loss": 0.4088, "lr": 5e-06, "epoch": 0.719849583669084, "percentage": 24.0, "elapsed_time": "4:55:13", "remaining_time": "15:34:48"} +{"current_steps": 1350, "total_steps": 5583, "loss": 0.4025, "lr": 5e-06, "epoch": 0.7252215954875101, "percentage": 24.18, "elapsed_time": "4:57:26", "remaining_time": "15:32:38"} +{"current_steps": 1360, "total_steps": 5583, "loss": 0.4141, "lr": 5e-06, "epoch": 0.730593607305936, "percentage": 24.36, "elapsed_time": "4:59:38", "remaining_time": "15:30:27"} +{"current_steps": 1370, "total_steps": 5583, "loss": 0.4222, "lr": 5e-06, "epoch": 0.7359656191243621, "percentage": 24.54, "elapsed_time": "5:01:51", "remaining_time": "15:28:15"} +{"current_steps": 1380, "total_steps": 5583, "loss": 0.4088, "lr": 5e-06, "epoch": 0.741337630942788, "percentage": 24.72, "elapsed_time": "5:04:03", "remaining_time": "15:26:03"} +{"current_steps": 1390, "total_steps": 5583, "loss": 0.4122, "lr": 5e-06, "epoch": 0.7467096427612141, "percentage": 24.9, "elapsed_time": "5:06:16", "remaining_time": "15:23:52"} +{"current_steps": 1400, "total_steps": 5583, "loss": 0.4318, "lr": 5e-06, "epoch": 0.75208165457964, "percentage": 25.08, "elapsed_time": "5:08:28", "remaining_time": "15:21:40"} +{"current_steps": 1410, "total_steps": 5583, "loss": 0.4097, "lr": 5e-06, "epoch": 0.7574536663980661, "percentage": 25.26, "elapsed_time": "5:10:40", "remaining_time": "15:19:28"} +{"current_steps": 1420, "total_steps": 5583, "loss": 0.4135, "lr": 5e-06, "epoch": 0.762825678216492, "percentage": 25.43, "elapsed_time": "5:12:52", "remaining_time": "15:17:15"} +{"current_steps": 1430, "total_steps": 5583, "loss": 0.4009, "lr": 5e-06, "epoch": 0.7681976900349181, "percentage": 25.61, "elapsed_time": "5:15:04", "remaining_time": "15:15:02"} +{"current_steps": 1440, "total_steps": 5583, "loss": 0.4061, "lr": 5e-06, "epoch": 0.7735697018533441, "percentage": 25.79, "elapsed_time": "5:17:17", "remaining_time": "15:12:51"} +{"current_steps": 1450, "total_steps": 5583, "loss": 0.4081, "lr": 5e-06, "epoch": 0.7789417136717701, "percentage": 25.97, "elapsed_time": "5:19:29", "remaining_time": "15:10:41"} +{"current_steps": 1460, "total_steps": 5583, "loss": 0.411, "lr": 5e-06, "epoch": 0.7843137254901961, "percentage": 26.15, "elapsed_time": "5:21:42", "remaining_time": "15:08:30"} +{"current_steps": 1470, "total_steps": 5583, "loss": 0.4107, "lr": 5e-06, "epoch": 0.7896857373086221, "percentage": 26.33, "elapsed_time": "5:23:55", "remaining_time": "15:06:19"} +{"current_steps": 1480, "total_steps": 5583, "loss": 0.4068, "lr": 5e-06, "epoch": 0.7950577491270481, "percentage": 26.51, "elapsed_time": "5:26:08", "remaining_time": "15:04:09"} +{"current_steps": 1490, "total_steps": 5583, "loss": 0.4118, "lr": 5e-06, "epoch": 0.8004297609454741, "percentage": 26.69, "elapsed_time": "5:28:20", "remaining_time": "15:01:57"} +{"current_steps": 1500, "total_steps": 5583, "loss": 0.4053, "lr": 5e-06, "epoch": 0.8058017727639001, "percentage": 26.87, "elapsed_time": "5:30:33", "remaining_time": "14:59:46"} +{"current_steps": 1510, "total_steps": 5583, "loss": 0.4085, "lr": 5e-06, "epoch": 0.811173784582326, "percentage": 27.05, "elapsed_time": "5:32:46", "remaining_time": "14:57:35"} +{"current_steps": 1520, "total_steps": 5583, "loss": 0.4127, "lr": 5e-06, "epoch": 0.8165457964007521, "percentage": 27.23, "elapsed_time": "5:34:58", "remaining_time": "14:55:24"} +{"current_steps": 1530, "total_steps": 5583, "loss": 0.4194, "lr": 5e-06, "epoch": 0.821917808219178, "percentage": 27.4, "elapsed_time": "5:37:11", "remaining_time": "14:53:13"} +{"current_steps": 1540, "total_steps": 5583, "loss": 0.4226, "lr": 5e-06, "epoch": 0.8272898200376041, "percentage": 27.58, "elapsed_time": "5:39:23", "remaining_time": "14:51:02"} +{"current_steps": 1550, "total_steps": 5583, "loss": 0.4099, "lr": 5e-06, "epoch": 0.83266183185603, "percentage": 27.76, "elapsed_time": "5:41:36", "remaining_time": "14:48:50"} +{"current_steps": 1560, "total_steps": 5583, "loss": 0.4083, "lr": 5e-06, "epoch": 0.8380338436744561, "percentage": 27.94, "elapsed_time": "5:43:49", "remaining_time": "14:46:39"} +{"current_steps": 1570, "total_steps": 5583, "loss": 0.4054, "lr": 5e-06, "epoch": 0.843405855492882, "percentage": 28.12, "elapsed_time": "5:46:01", "remaining_time": "14:44:28"} +{"current_steps": 1580, "total_steps": 5583, "loss": 0.4187, "lr": 5e-06, "epoch": 0.8487778673113081, "percentage": 28.3, "elapsed_time": "5:48:13", "remaining_time": "14:42:15"} +{"current_steps": 1590, "total_steps": 5583, "loss": 0.4085, "lr": 5e-06, "epoch": 0.8541498791297341, "percentage": 28.48, "elapsed_time": "5:50:25", "remaining_time": "14:40:02"} +{"current_steps": 1600, "total_steps": 5583, "loss": 0.4086, "lr": 5e-06, "epoch": 0.8595218909481601, "percentage": 28.66, "elapsed_time": "5:52:38", "remaining_time": "14:37:51"} +{"current_steps": 1610, "total_steps": 5583, "loss": 0.4048, "lr": 5e-06, "epoch": 0.8648939027665861, "percentage": 28.84, "elapsed_time": "5:54:51", "remaining_time": "14:35:40"} +{"current_steps": 1620, "total_steps": 5583, "loss": 0.4025, "lr": 5e-06, "epoch": 0.8702659145850121, "percentage": 29.02, "elapsed_time": "5:57:04", "remaining_time": "14:33:30"} +{"current_steps": 1630, "total_steps": 5583, "loss": 0.4107, "lr": 5e-06, "epoch": 0.8756379264034381, "percentage": 29.2, "elapsed_time": "5:59:17", "remaining_time": "14:31:19"} +{"current_steps": 1640, "total_steps": 5583, "loss": 0.4114, "lr": 5e-06, "epoch": 0.8810099382218641, "percentage": 29.37, "elapsed_time": "6:01:30", "remaining_time": "14:29:09"} +{"current_steps": 1650, "total_steps": 5583, "loss": 0.4088, "lr": 5e-06, "epoch": 0.8863819500402901, "percentage": 29.55, "elapsed_time": "6:03:43", "remaining_time": "14:26:58"} +{"current_steps": 1660, "total_steps": 5583, "loss": 0.3976, "lr": 5e-06, "epoch": 0.8917539618587161, "percentage": 29.73, "elapsed_time": "6:05:55", "remaining_time": "14:24:47"} +{"current_steps": 1670, "total_steps": 5583, "loss": 0.4153, "lr": 5e-06, "epoch": 0.8971259736771421, "percentage": 29.91, "elapsed_time": "6:08:08", "remaining_time": "14:22:36"} +{"current_steps": 1680, "total_steps": 5583, "loss": 0.4192, "lr": 5e-06, "epoch": 0.9024979854955681, "percentage": 30.09, "elapsed_time": "6:10:21", "remaining_time": "14:20:25"} +{"current_steps": 1690, "total_steps": 5583, "loss": 0.4226, "lr": 5e-06, "epoch": 0.9078699973139941, "percentage": 30.27, "elapsed_time": "6:12:34", "remaining_time": "14:18:14"} +{"current_steps": 1700, "total_steps": 5583, "loss": 0.404, "lr": 5e-06, "epoch": 0.91324200913242, "percentage": 30.45, "elapsed_time": "6:14:47", "remaining_time": "14:16:04"} +{"current_steps": 1710, "total_steps": 5583, "loss": 0.4126, "lr": 5e-06, "epoch": 0.9186140209508461, "percentage": 30.63, "elapsed_time": "6:17:00", "remaining_time": "14:13:53"} +{"current_steps": 1720, "total_steps": 5583, "loss": 0.4072, "lr": 5e-06, "epoch": 0.923986032769272, "percentage": 30.81, "elapsed_time": "6:19:13", "remaining_time": "14:11:42"} +{"current_steps": 1730, "total_steps": 5583, "loss": 0.4037, "lr": 5e-06, "epoch": 0.9293580445876981, "percentage": 30.99, "elapsed_time": "6:21:26", "remaining_time": "14:09:32"} +{"current_steps": 1740, "total_steps": 5583, "loss": 0.4129, "lr": 5e-06, "epoch": 0.934730056406124, "percentage": 31.17, "elapsed_time": "6:23:39", "remaining_time": "14:07:21"} +{"current_steps": 1750, "total_steps": 5583, "loss": 0.4089, "lr": 5e-06, "epoch": 0.9401020682245501, "percentage": 31.35, "elapsed_time": "6:25:52", "remaining_time": "14:05:10"} +{"current_steps": 1760, "total_steps": 5583, "loss": 0.4031, "lr": 5e-06, "epoch": 0.9454740800429761, "percentage": 31.52, "elapsed_time": "6:28:05", "remaining_time": "14:02:59"} +{"current_steps": 1770, "total_steps": 5583, "loss": 0.398, "lr": 5e-06, "epoch": 0.9508460918614021, "percentage": 31.7, "elapsed_time": "6:30:18", "remaining_time": "14:00:48"} +{"current_steps": 1780, "total_steps": 5583, "loss": 0.3988, "lr": 5e-06, "epoch": 0.9562181036798281, "percentage": 31.88, "elapsed_time": "6:32:31", "remaining_time": "13:58:37"} +{"current_steps": 1790, "total_steps": 5583, "loss": 0.4076, "lr": 5e-06, "epoch": 0.9615901154982541, "percentage": 32.06, "elapsed_time": "6:34:44", "remaining_time": "13:56:26"} +{"current_steps": 1800, "total_steps": 5583, "loss": 0.4061, "lr": 5e-06, "epoch": 0.9669621273166801, "percentage": 32.24, "elapsed_time": "6:36:56", "remaining_time": "13:54:14"} +{"current_steps": 1810, "total_steps": 5583, "loss": 0.4014, "lr": 5e-06, "epoch": 0.9723341391351061, "percentage": 32.42, "elapsed_time": "6:39:09", "remaining_time": "13:52:02"} +{"current_steps": 1820, "total_steps": 5583, "loss": 0.4166, "lr": 5e-06, "epoch": 0.9777061509535321, "percentage": 32.6, "elapsed_time": "6:41:21", "remaining_time": "13:49:51"} +{"current_steps": 1830, "total_steps": 5583, "loss": 0.4177, "lr": 5e-06, "epoch": 0.9830781627719581, "percentage": 32.78, "elapsed_time": "6:43:34", "remaining_time": "13:47:39"} +{"current_steps": 1840, "total_steps": 5583, "loss": 0.402, "lr": 5e-06, "epoch": 0.9884501745903841, "percentage": 32.96, "elapsed_time": "6:45:47", "remaining_time": "13:45:27"} +{"current_steps": 1850, "total_steps": 5583, "loss": 0.4026, "lr": 5e-06, "epoch": 0.9938221864088101, "percentage": 33.14, "elapsed_time": "6:47:59", "remaining_time": "13:43:16"} +{"current_steps": 1860, "total_steps": 5583, "loss": 0.4024, "lr": 5e-06, "epoch": 0.9991941982272361, "percentage": 33.32, "elapsed_time": "6:50:12", "remaining_time": "13:41:05"} +{"current_steps": 1861, "total_steps": 5583, "eval_loss": 0.4042987525463104, "epoch": 0.9997313994090787, "percentage": 33.33, "elapsed_time": "6:58:23", "remaining_time": "13:56:46"} +{"current_steps": 1870, "total_steps": 5583, "loss": 0.3782, "lr": 5e-06, "epoch": 1.004566210045662, "percentage": 33.49, "elapsed_time": "7:01:19", "remaining_time": "13:56:34"} +{"current_steps": 1880, "total_steps": 5583, "loss": 0.3515, "lr": 5e-06, "epoch": 1.009938221864088, "percentage": 33.67, "elapsed_time": "7:03:31", "remaining_time": "13:54:13"} +{"current_steps": 1890, "total_steps": 5583, "loss": 0.3602, "lr": 5e-06, "epoch": 1.0153102336825142, "percentage": 33.85, "elapsed_time": "7:05:44", "remaining_time": "13:51:53"} +{"current_steps": 1900, "total_steps": 5583, "loss": 0.3583, "lr": 5e-06, "epoch": 1.02068224550094, "percentage": 34.03, "elapsed_time": "7:07:57", "remaining_time": "13:49:33"} +{"current_steps": 1910, "total_steps": 5583, "loss": 0.3428, "lr": 5e-06, "epoch": 1.026054257319366, "percentage": 34.21, "elapsed_time": "7:10:09", "remaining_time": "13:47:13"} +{"current_steps": 1920, "total_steps": 5583, "loss": 0.3615, "lr": 5e-06, "epoch": 1.031426269137792, "percentage": 34.39, "elapsed_time": "7:12:22", "remaining_time": "13:44:53"} +{"current_steps": 1930, "total_steps": 5583, "loss": 0.3629, "lr": 5e-06, "epoch": 1.0367982809562182, "percentage": 34.57, "elapsed_time": "7:14:34", "remaining_time": "13:42:33"} +{"current_steps": 1940, "total_steps": 5583, "loss": 0.3695, "lr": 5e-06, "epoch": 1.0421702927746441, "percentage": 34.75, "elapsed_time": "7:16:47", "remaining_time": "13:40:13"} +{"current_steps": 1950, "total_steps": 5583, "loss": 0.3434, "lr": 5e-06, "epoch": 1.04754230459307, "percentage": 34.93, "elapsed_time": "7:19:00", "remaining_time": "13:37:53"} +{"current_steps": 1960, "total_steps": 5583, "loss": 0.3509, "lr": 5e-06, "epoch": 1.052914316411496, "percentage": 35.11, "elapsed_time": "7:21:12", "remaining_time": "13:35:34"} +{"current_steps": 1970, "total_steps": 5583, "loss": 0.3424, "lr": 5e-06, "epoch": 1.0582863282299222, "percentage": 35.29, "elapsed_time": "7:23:25", "remaining_time": "13:33:14"} +{"current_steps": 1980, "total_steps": 5583, "loss": 0.3543, "lr": 5e-06, "epoch": 1.0636583400483481, "percentage": 35.46, "elapsed_time": "7:25:37", "remaining_time": "13:30:54"} +{"current_steps": 1990, "total_steps": 5583, "loss": 0.3514, "lr": 5e-06, "epoch": 1.069030351866774, "percentage": 35.64, "elapsed_time": "7:27:50", "remaining_time": "13:28:35"} +{"current_steps": 2000, "total_steps": 5583, "loss": 0.3441, "lr": 5e-06, "epoch": 1.0744023636852, "percentage": 35.82, "elapsed_time": "7:30:03", "remaining_time": "13:26:16"} +{"current_steps": 2010, "total_steps": 5583, "loss": 0.3519, "lr": 5e-06, "epoch": 1.0797743755036262, "percentage": 36.0, "elapsed_time": "7:32:15", "remaining_time": "13:23:57"} +{"current_steps": 2020, "total_steps": 5583, "loss": 0.3501, "lr": 5e-06, "epoch": 1.0851463873220522, "percentage": 36.18, "elapsed_time": "7:34:28", "remaining_time": "13:21:38"} +{"current_steps": 2030, "total_steps": 5583, "loss": 0.3583, "lr": 5e-06, "epoch": 1.090518399140478, "percentage": 36.36, "elapsed_time": "7:36:41", "remaining_time": "13:19:19"} +{"current_steps": 2040, "total_steps": 5583, "loss": 0.3503, "lr": 5e-06, "epoch": 1.095890410958904, "percentage": 36.54, "elapsed_time": "7:38:53", "remaining_time": "13:16:59"} +{"current_steps": 2050, "total_steps": 5583, "loss": 0.3563, "lr": 5e-06, "epoch": 1.1012624227773302, "percentage": 36.72, "elapsed_time": "7:41:05", "remaining_time": "13:14:39"} +{"current_steps": 2060, "total_steps": 5583, "loss": 0.3605, "lr": 5e-06, "epoch": 1.1066344345957562, "percentage": 36.9, "elapsed_time": "7:43:17", "remaining_time": "13:12:19"} +{"current_steps": 2070, "total_steps": 5583, "loss": 0.3576, "lr": 5e-06, "epoch": 1.1120064464141821, "percentage": 37.08, "elapsed_time": "7:45:30", "remaining_time": "13:10:00"} +{"current_steps": 2080, "total_steps": 5583, "loss": 0.3581, "lr": 5e-06, "epoch": 1.117378458232608, "percentage": 37.26, "elapsed_time": "7:47:42", "remaining_time": "13:07:41"} +{"current_steps": 2090, "total_steps": 5583, "loss": 0.3482, "lr": 5e-06, "epoch": 1.122750470051034, "percentage": 37.44, "elapsed_time": "7:49:55", "remaining_time": "13:05:23"} +{"current_steps": 2100, "total_steps": 5583, "loss": 0.3518, "lr": 5e-06, "epoch": 1.1281224818694602, "percentage": 37.61, "elapsed_time": "7:52:07", "remaining_time": "13:03:03"} +{"current_steps": 2110, "total_steps": 5583, "loss": 0.3605, "lr": 5e-06, "epoch": 1.1334944936878861, "percentage": 37.79, "elapsed_time": "7:54:20", "remaining_time": "13:00:44"} +{"current_steps": 2120, "total_steps": 5583, "loss": 0.3539, "lr": 5e-06, "epoch": 1.138866505506312, "percentage": 37.97, "elapsed_time": "7:56:32", "remaining_time": "12:58:25"} +{"current_steps": 2130, "total_steps": 5583, "loss": 0.3471, "lr": 5e-06, "epoch": 1.144238517324738, "percentage": 38.15, "elapsed_time": "7:58:44", "remaining_time": "12:56:06"} +{"current_steps": 2140, "total_steps": 5583, "loss": 0.3494, "lr": 5e-06, "epoch": 1.1496105291431642, "percentage": 38.33, "elapsed_time": "8:00:57", "remaining_time": "12:53:48"} +{"current_steps": 2150, "total_steps": 5583, "loss": 0.3426, "lr": 5e-06, "epoch": 1.1549825409615901, "percentage": 38.51, "elapsed_time": "8:03:09", "remaining_time": "12:51:29"} +{"current_steps": 2160, "total_steps": 5583, "loss": 0.356, "lr": 5e-06, "epoch": 1.160354552780016, "percentage": 38.69, "elapsed_time": "8:05:22", "remaining_time": "12:49:10"} +{"current_steps": 2170, "total_steps": 5583, "loss": 0.3436, "lr": 5e-06, "epoch": 1.165726564598442, "percentage": 38.87, "elapsed_time": "8:07:34", "remaining_time": "12:46:52"} +{"current_steps": 2180, "total_steps": 5583, "loss": 0.3554, "lr": 5e-06, "epoch": 1.1710985764168682, "percentage": 39.05, "elapsed_time": "8:09:47", "remaining_time": "12:44:33"} +{"current_steps": 2190, "total_steps": 5583, "loss": 0.3549, "lr": 5e-06, "epoch": 1.1764705882352942, "percentage": 39.23, "elapsed_time": "8:11:59", "remaining_time": "12:42:15"} +{"current_steps": 2200, "total_steps": 5583, "loss": 0.3616, "lr": 5e-06, "epoch": 1.18184260005372, "percentage": 39.41, "elapsed_time": "8:14:12", "remaining_time": "12:39:56"} +{"current_steps": 2210, "total_steps": 5583, "loss": 0.3456, "lr": 5e-06, "epoch": 1.187214611872146, "percentage": 39.58, "elapsed_time": "8:16:24", "remaining_time": "12:37:38"} +{"current_steps": 2220, "total_steps": 5583, "loss": 0.3575, "lr": 5e-06, "epoch": 1.192586623690572, "percentage": 39.76, "elapsed_time": "8:18:36", "remaining_time": "12:35:20"} +{"current_steps": 2230, "total_steps": 5583, "loss": 0.3572, "lr": 5e-06, "epoch": 1.1979586355089982, "percentage": 39.94, "elapsed_time": "8:20:49", "remaining_time": "12:33:02"} +{"current_steps": 2240, "total_steps": 5583, "loss": 0.3463, "lr": 5e-06, "epoch": 1.2033306473274241, "percentage": 40.12, "elapsed_time": "8:23:01", "remaining_time": "12:30:43"} +{"current_steps": 2250, "total_steps": 5583, "loss": 0.3509, "lr": 5e-06, "epoch": 1.20870265914585, "percentage": 40.3, "elapsed_time": "8:25:14", "remaining_time": "12:28:25"} +{"current_steps": 2260, "total_steps": 5583, "loss": 0.3607, "lr": 5e-06, "epoch": 1.2140746709642762, "percentage": 40.48, "elapsed_time": "8:27:27", "remaining_time": "12:26:08"} +{"current_steps": 2270, "total_steps": 5583, "loss": 0.3663, "lr": 5e-06, "epoch": 1.2194466827827022, "percentage": 40.66, "elapsed_time": "8:29:39", "remaining_time": "12:23:50"} +{"current_steps": 2280, "total_steps": 5583, "loss": 0.3608, "lr": 5e-06, "epoch": 1.2248186946011281, "percentage": 40.84, "elapsed_time": "8:31:52", "remaining_time": "12:21:32"} +{"current_steps": 2290, "total_steps": 5583, "loss": 0.3574, "lr": 5e-06, "epoch": 1.230190706419554, "percentage": 41.02, "elapsed_time": "8:34:04", "remaining_time": "12:19:14"} +{"current_steps": 2300, "total_steps": 5583, "loss": 0.3493, "lr": 5e-06, "epoch": 1.23556271823798, "percentage": 41.2, "elapsed_time": "8:36:17", "remaining_time": "12:16:56"} +{"current_steps": 2310, "total_steps": 5583, "loss": 0.3514, "lr": 5e-06, "epoch": 1.2409347300564062, "percentage": 41.38, "elapsed_time": "8:38:29", "remaining_time": "12:14:38"} +{"current_steps": 2320, "total_steps": 5583, "loss": 0.3804, "lr": 5e-06, "epoch": 1.2463067418748321, "percentage": 41.55, "elapsed_time": "8:40:42", "remaining_time": "12:12:21"} +{"current_steps": 2330, "total_steps": 5583, "loss": 0.3558, "lr": 5e-06, "epoch": 1.251678753693258, "percentage": 41.73, "elapsed_time": "8:42:54", "remaining_time": "12:10:03"} +{"current_steps": 2340, "total_steps": 5583, "loss": 0.355, "lr": 5e-06, "epoch": 1.257050765511684, "percentage": 41.91, "elapsed_time": "8:45:07", "remaining_time": "12:07:46"} +{"current_steps": 2350, "total_steps": 5583, "loss": 0.3561, "lr": 5e-06, "epoch": 1.26242277733011, "percentage": 42.09, "elapsed_time": "8:47:20", "remaining_time": "12:05:28"} +{"current_steps": 2360, "total_steps": 5583, "loss": 0.3472, "lr": 5e-06, "epoch": 1.2677947891485362, "percentage": 42.27, "elapsed_time": "8:49:32", "remaining_time": "12:03:10"} +{"current_steps": 2370, "total_steps": 5583, "loss": 0.3523, "lr": 5e-06, "epoch": 1.273166800966962, "percentage": 42.45, "elapsed_time": "8:51:44", "remaining_time": "12:00:53"} +{"current_steps": 2380, "total_steps": 5583, "loss": 0.3665, "lr": 5e-06, "epoch": 1.278538812785388, "percentage": 42.63, "elapsed_time": "8:53:57", "remaining_time": "11:58:35"} +{"current_steps": 2390, "total_steps": 5583, "loss": 0.3533, "lr": 5e-06, "epoch": 1.2839108246038142, "percentage": 42.81, "elapsed_time": "8:56:09", "remaining_time": "11:56:18"} +{"current_steps": 2400, "total_steps": 5583, "loss": 0.3644, "lr": 5e-06, "epoch": 1.2892828364222402, "percentage": 42.99, "elapsed_time": "8:58:22", "remaining_time": "11:54:00"} +{"current_steps": 2410, "total_steps": 5583, "loss": 0.358, "lr": 5e-06, "epoch": 1.2946548482406661, "percentage": 43.17, "elapsed_time": "9:00:33", "remaining_time": "11:51:42"} +{"current_steps": 2420, "total_steps": 5583, "loss": 0.3718, "lr": 5e-06, "epoch": 1.300026860059092, "percentage": 43.35, "elapsed_time": "9:02:45", "remaining_time": "11:49:24"} +{"current_steps": 2430, "total_steps": 5583, "loss": 0.3498, "lr": 5e-06, "epoch": 1.305398871877518, "percentage": 43.52, "elapsed_time": "9:04:58", "remaining_time": "11:47:07"} +{"current_steps": 2440, "total_steps": 5583, "loss": 0.3453, "lr": 5e-06, "epoch": 1.3107708836959442, "percentage": 43.7, "elapsed_time": "9:07:10", "remaining_time": "11:44:49"} +{"current_steps": 2450, "total_steps": 5583, "loss": 0.3574, "lr": 5e-06, "epoch": 1.3161428955143701, "percentage": 43.88, "elapsed_time": "9:09:23", "remaining_time": "11:42:32"} +{"current_steps": 2460, "total_steps": 5583, "loss": 0.3585, "lr": 5e-06, "epoch": 1.321514907332796, "percentage": 44.06, "elapsed_time": "9:11:36", "remaining_time": "11:40:15"} +{"current_steps": 2470, "total_steps": 5583, "loss": 0.3447, "lr": 5e-06, "epoch": 1.3268869191512223, "percentage": 44.24, "elapsed_time": "9:13:48", "remaining_time": "11:37:58"} +{"current_steps": 2480, "total_steps": 5583, "loss": 0.3572, "lr": 5e-06, "epoch": 1.3322589309696482, "percentage": 44.42, "elapsed_time": "9:16:01", "remaining_time": "11:35:41"} +{"current_steps": 2490, "total_steps": 5583, "loss": 0.3568, "lr": 5e-06, "epoch": 1.3376309427880742, "percentage": 44.6, "elapsed_time": "9:18:13", "remaining_time": "11:33:24"} +{"current_steps": 2500, "total_steps": 5583, "loss": 0.3557, "lr": 5e-06, "epoch": 1.3430029546065, "percentage": 44.78, "elapsed_time": "9:20:25", "remaining_time": "11:31:07"} +{"current_steps": 2510, "total_steps": 5583, "loss": 0.3539, "lr": 5e-06, "epoch": 1.348374966424926, "percentage": 44.96, "elapsed_time": "9:22:38", "remaining_time": "11:28:50"} +{"current_steps": 2520, "total_steps": 5583, "loss": 0.3527, "lr": 5e-06, "epoch": 1.3537469782433522, "percentage": 45.14, "elapsed_time": "9:24:50", "remaining_time": "11:26:32"} +{"current_steps": 2530, "total_steps": 5583, "loss": 0.3601, "lr": 5e-06, "epoch": 1.3591189900617782, "percentage": 45.32, "elapsed_time": "9:27:02", "remaining_time": "11:24:15"} +{"current_steps": 2540, "total_steps": 5583, "loss": 0.3615, "lr": 5e-06, "epoch": 1.3644910018802041, "percentage": 45.5, "elapsed_time": "9:29:14", "remaining_time": "11:21:58"} +{"current_steps": 2550, "total_steps": 5583, "loss": 0.3529, "lr": 5e-06, "epoch": 1.36986301369863, "percentage": 45.67, "elapsed_time": "9:31:26", "remaining_time": "11:19:41"} +{"current_steps": 2560, "total_steps": 5583, "loss": 0.3444, "lr": 5e-06, "epoch": 1.375235025517056, "percentage": 45.85, "elapsed_time": "9:33:38", "remaining_time": "11:17:23"} +{"current_steps": 2570, "total_steps": 5583, "loss": 0.3625, "lr": 5e-06, "epoch": 1.3806070373354822, "percentage": 46.03, "elapsed_time": "9:35:50", "remaining_time": "11:15:06"} +{"current_steps": 2580, "total_steps": 5583, "loss": 0.3634, "lr": 5e-06, "epoch": 1.3859790491539081, "percentage": 46.21, "elapsed_time": "9:38:02", "remaining_time": "11:12:49"} +{"current_steps": 2590, "total_steps": 5583, "loss": 0.3576, "lr": 5e-06, "epoch": 1.391351060972334, "percentage": 46.39, "elapsed_time": "9:40:14", "remaining_time": "11:10:32"} +{"current_steps": 2600, "total_steps": 5583, "loss": 0.3552, "lr": 5e-06, "epoch": 1.3967230727907602, "percentage": 46.57, "elapsed_time": "9:42:27", "remaining_time": "11:08:15"} +{"current_steps": 2610, "total_steps": 5583, "loss": 0.3674, "lr": 5e-06, "epoch": 1.4020950846091862, "percentage": 46.75, "elapsed_time": "9:44:39", "remaining_time": "11:05:58"} +{"current_steps": 2620, "total_steps": 5583, "loss": 0.3627, "lr": 5e-06, "epoch": 1.4074670964276121, "percentage": 46.93, "elapsed_time": "9:46:52", "remaining_time": "11:03:42"} +{"current_steps": 2630, "total_steps": 5583, "loss": 0.3561, "lr": 5e-06, "epoch": 1.412839108246038, "percentage": 47.11, "elapsed_time": "9:49:05", "remaining_time": "11:01:25"} +{"current_steps": 2640, "total_steps": 5583, "loss": 0.3548, "lr": 5e-06, "epoch": 1.418211120064464, "percentage": 47.29, "elapsed_time": "9:51:17", "remaining_time": "10:59:09"} +{"current_steps": 2650, "total_steps": 5583, "loss": 0.365, "lr": 5e-06, "epoch": 1.4235831318828902, "percentage": 47.47, "elapsed_time": "9:53:29", "remaining_time": "10:56:52"} +{"current_steps": 2660, "total_steps": 5583, "loss": 0.3612, "lr": 5e-06, "epoch": 1.4289551437013162, "percentage": 47.64, "elapsed_time": "9:55:42", "remaining_time": "10:54:36"} +{"current_steps": 2670, "total_steps": 5583, "loss": 0.3552, "lr": 5e-06, "epoch": 1.434327155519742, "percentage": 47.82, "elapsed_time": "9:57:54", "remaining_time": "10:52:19"} +{"current_steps": 2680, "total_steps": 5583, "loss": 0.3712, "lr": 5e-06, "epoch": 1.4396991673381683, "percentage": 48.0, "elapsed_time": "10:00:07", "remaining_time": "10:50:03"} +{"current_steps": 2690, "total_steps": 5583, "loss": 0.3555, "lr": 5e-06, "epoch": 1.4450711791565942, "percentage": 48.18, "elapsed_time": "10:02:19", "remaining_time": "10:47:47"} +{"current_steps": 2700, "total_steps": 5583, "loss": 0.3526, "lr": 5e-06, "epoch": 1.4504431909750202, "percentage": 48.36, "elapsed_time": "10:04:32", "remaining_time": "10:45:30"} +{"current_steps": 2710, "total_steps": 5583, "loss": 0.3509, "lr": 5e-06, "epoch": 1.4558152027934461, "percentage": 48.54, "elapsed_time": "10:06:44", "remaining_time": "10:43:14"} +{"current_steps": 2720, "total_steps": 5583, "loss": 0.3587, "lr": 5e-06, "epoch": 1.461187214611872, "percentage": 48.72, "elapsed_time": "10:08:56", "remaining_time": "10:40:57"} +{"current_steps": 2730, "total_steps": 5583, "loss": 0.3541, "lr": 5e-06, "epoch": 1.4665592264302982, "percentage": 48.9, "elapsed_time": "10:11:09", "remaining_time": "10:38:41"} +{"current_steps": 2740, "total_steps": 5583, "loss": 0.3562, "lr": 5e-06, "epoch": 1.4719312382487242, "percentage": 49.08, "elapsed_time": "10:13:22", "remaining_time": "10:36:25"} +{"current_steps": 2750, "total_steps": 5583, "loss": 0.346, "lr": 5e-06, "epoch": 1.4773032500671501, "percentage": 49.26, "elapsed_time": "10:15:34", "remaining_time": "10:34:09"} +{"current_steps": 2760, "total_steps": 5583, "loss": 0.3502, "lr": 5e-06, "epoch": 1.482675261885576, "percentage": 49.44, "elapsed_time": "10:17:47", "remaining_time": "10:31:53"} +{"current_steps": 2770, "total_steps": 5583, "loss": 0.3508, "lr": 5e-06, "epoch": 1.488047273704002, "percentage": 49.61, "elapsed_time": "10:19:59", "remaining_time": "10:29:37"} +{"current_steps": 2780, "total_steps": 5583, "loss": 0.35, "lr": 5e-06, "epoch": 1.4934192855224282, "percentage": 49.79, "elapsed_time": "10:22:11", "remaining_time": "10:27:20"} +{"current_steps": 2790, "total_steps": 5583, "loss": 0.3531, "lr": 5e-06, "epoch": 1.4987912973408541, "percentage": 49.97, "elapsed_time": "10:24:24", "remaining_time": "10:25:04"} +{"current_steps": 2800, "total_steps": 5583, "loss": 0.3554, "lr": 5e-06, "epoch": 1.50416330915928, "percentage": 50.15, "elapsed_time": "10:26:36", "remaining_time": "10:22:48"} +{"current_steps": 2810, "total_steps": 5583, "loss": 0.3597, "lr": 5e-06, "epoch": 1.5095353209777063, "percentage": 50.33, "elapsed_time": "10:28:49", "remaining_time": "10:20:32"} +{"current_steps": 2820, "total_steps": 5583, "loss": 0.3488, "lr": 5e-06, "epoch": 1.514907332796132, "percentage": 50.51, "elapsed_time": "10:31:01", "remaining_time": "10:18:16"} +{"current_steps": 2830, "total_steps": 5583, "loss": 0.3571, "lr": 5e-06, "epoch": 1.5202793446145582, "percentage": 50.69, "elapsed_time": "10:33:13", "remaining_time": "10:16:00"} +{"current_steps": 2840, "total_steps": 5583, "loss": 0.347, "lr": 5e-06, "epoch": 1.525651356432984, "percentage": 50.87, "elapsed_time": "10:35:26", "remaining_time": "10:13:44"} +{"current_steps": 2850, "total_steps": 5583, "loss": 0.3636, "lr": 5e-06, "epoch": 1.53102336825141, "percentage": 51.05, "elapsed_time": "10:37:38", "remaining_time": "10:11:28"} +{"current_steps": 2860, "total_steps": 5583, "loss": 0.3589, "lr": 5e-06, "epoch": 1.5363953800698362, "percentage": 51.23, "elapsed_time": "10:39:51", "remaining_time": "10:09:12"} +{"current_steps": 2870, "total_steps": 5583, "loss": 0.3448, "lr": 5e-06, "epoch": 1.5417673918882622, "percentage": 51.41, "elapsed_time": "10:42:03", "remaining_time": "10:06:56"} +{"current_steps": 2880, "total_steps": 5583, "loss": 0.3568, "lr": 5e-06, "epoch": 1.5471394037066881, "percentage": 51.59, "elapsed_time": "10:44:16", "remaining_time": "10:04:40"} +{"current_steps": 2890, "total_steps": 5583, "loss": 0.3554, "lr": 5e-06, "epoch": 1.5525114155251143, "percentage": 51.76, "elapsed_time": "10:46:29", "remaining_time": "10:02:24"} +{"current_steps": 2900, "total_steps": 5583, "loss": 0.3679, "lr": 5e-06, "epoch": 1.55788342734354, "percentage": 51.94, "elapsed_time": "10:48:41", "remaining_time": "10:00:09"} +{"current_steps": 2910, "total_steps": 5583, "loss": 0.369, "lr": 5e-06, "epoch": 1.5632554391619662, "percentage": 52.12, "elapsed_time": "10:50:53", "remaining_time": "9:57:53"} +{"current_steps": 2920, "total_steps": 5583, "loss": 0.3557, "lr": 5e-06, "epoch": 1.5686274509803921, "percentage": 52.3, "elapsed_time": "10:53:06", "remaining_time": "9:55:37"} +{"current_steps": 2930, "total_steps": 5583, "loss": 0.3564, "lr": 5e-06, "epoch": 1.573999462798818, "percentage": 52.48, "elapsed_time": "10:55:18", "remaining_time": "9:53:21"} +{"current_steps": 2940, "total_steps": 5583, "loss": 0.3516, "lr": 5e-06, "epoch": 1.5793714746172443, "percentage": 52.66, "elapsed_time": "10:57:30", "remaining_time": "9:51:05"} +{"current_steps": 2950, "total_steps": 5583, "loss": 0.3736, "lr": 5e-06, "epoch": 1.5847434864356702, "percentage": 52.84, "elapsed_time": "10:59:42", "remaining_time": "9:48:48"} +{"current_steps": 2960, "total_steps": 5583, "loss": 0.3588, "lr": 5e-06, "epoch": 1.5901154982540961, "percentage": 53.02, "elapsed_time": "11:01:54", "remaining_time": "9:46:33"} +{"current_steps": 2970, "total_steps": 5583, "loss": 0.3576, "lr": 5e-06, "epoch": 1.5954875100725223, "percentage": 53.2, "elapsed_time": "11:04:06", "remaining_time": "9:44:17"} +{"current_steps": 2980, "total_steps": 5583, "loss": 0.3518, "lr": 5e-06, "epoch": 1.600859521890948, "percentage": 53.38, "elapsed_time": "11:06:19", "remaining_time": "9:42:01"} +{"current_steps": 2990, "total_steps": 5583, "loss": 0.3574, "lr": 5e-06, "epoch": 1.6062315337093742, "percentage": 53.56, "elapsed_time": "11:08:31", "remaining_time": "9:39:45"} +{"current_steps": 3000, "total_steps": 5583, "loss": 0.3469, "lr": 5e-06, "epoch": 1.6116035455278002, "percentage": 53.73, "elapsed_time": "11:10:43", "remaining_time": "9:37:30"} +{"current_steps": 3010, "total_steps": 5583, "loss": 0.3665, "lr": 5e-06, "epoch": 1.6169755573462261, "percentage": 53.91, "elapsed_time": "11:12:56", "remaining_time": "9:35:14"} +{"current_steps": 3020, "total_steps": 5583, "loss": 0.3627, "lr": 5e-06, "epoch": 1.6223475691646523, "percentage": 54.09, "elapsed_time": "11:15:08", "remaining_time": "9:32:58"} +{"current_steps": 3030, "total_steps": 5583, "loss": 0.3481, "lr": 5e-06, "epoch": 1.627719580983078, "percentage": 54.27, "elapsed_time": "11:17:21", "remaining_time": "9:30:43"} +{"current_steps": 3040, "total_steps": 5583, "loss": 0.3494, "lr": 5e-06, "epoch": 1.6330915928015042, "percentage": 54.45, "elapsed_time": "11:19:33", "remaining_time": "9:28:27"} +{"current_steps": 3050, "total_steps": 5583, "loss": 0.3477, "lr": 5e-06, "epoch": 1.6384636046199301, "percentage": 54.63, "elapsed_time": "11:21:45", "remaining_time": "9:26:11"} +{"current_steps": 3060, "total_steps": 5583, "loss": 0.3605, "lr": 5e-06, "epoch": 1.643835616438356, "percentage": 54.81, "elapsed_time": "11:23:57", "remaining_time": "9:23:55"} +{"current_steps": 3070, "total_steps": 5583, "loss": 0.3552, "lr": 5e-06, "epoch": 1.6492076282567822, "percentage": 54.99, "elapsed_time": "11:26:09", "remaining_time": "9:21:40"} +{"current_steps": 3080, "total_steps": 5583, "loss": 0.357, "lr": 5e-06, "epoch": 1.6545796400752082, "percentage": 55.17, "elapsed_time": "11:28:21", "remaining_time": "9:19:24"} +{"current_steps": 3090, "total_steps": 5583, "loss": 0.3481, "lr": 5e-06, "epoch": 1.6599516518936341, "percentage": 55.35, "elapsed_time": "11:30:33", "remaining_time": "9:17:08"} +{"current_steps": 3100, "total_steps": 5583, "loss": 0.3455, "lr": 5e-06, "epoch": 1.6653236637120603, "percentage": 55.53, "elapsed_time": "11:32:45", "remaining_time": "9:14:52"} +{"current_steps": 3110, "total_steps": 5583, "loss": 0.3539, "lr": 5e-06, "epoch": 1.670695675530486, "percentage": 55.7, "elapsed_time": "11:34:57", "remaining_time": "9:12:37"} +{"current_steps": 3120, "total_steps": 5583, "loss": 0.3589, "lr": 5e-06, "epoch": 1.6760676873489122, "percentage": 55.88, "elapsed_time": "11:37:10", "remaining_time": "9:10:21"} +{"current_steps": 3130, "total_steps": 5583, "loss": 0.3436, "lr": 5e-06, "epoch": 1.6814396991673382, "percentage": 56.06, "elapsed_time": "11:39:22", "remaining_time": "9:08:06"} +{"current_steps": 3140, "total_steps": 5583, "loss": 0.37, "lr": 5e-06, "epoch": 1.686811710985764, "percentage": 56.24, "elapsed_time": "11:41:34", "remaining_time": "9:05:50"} +{"current_steps": 3150, "total_steps": 5583, "loss": 0.3488, "lr": 5e-06, "epoch": 1.6921837228041903, "percentage": 56.42, "elapsed_time": "11:43:46", "remaining_time": "9:03:35"} +{"current_steps": 3160, "total_steps": 5583, "loss": 0.3571, "lr": 5e-06, "epoch": 1.6975557346226162, "percentage": 56.6, "elapsed_time": "11:45:58", "remaining_time": "9:01:19"} +{"current_steps": 3170, "total_steps": 5583, "loss": 0.3524, "lr": 5e-06, "epoch": 1.7029277464410422, "percentage": 56.78, "elapsed_time": "11:48:11", "remaining_time": "8:59:04"} +{"current_steps": 3180, "total_steps": 5583, "loss": 0.352, "lr": 5e-06, "epoch": 1.7082997582594683, "percentage": 56.96, "elapsed_time": "11:50:23", "remaining_time": "8:56:48"} +{"current_steps": 3190, "total_steps": 5583, "loss": 0.3446, "lr": 5e-06, "epoch": 1.713671770077894, "percentage": 57.14, "elapsed_time": "11:52:35", "remaining_time": "8:54:33"} +{"current_steps": 3200, "total_steps": 5583, "loss": 0.3453, "lr": 5e-06, "epoch": 1.7190437818963202, "percentage": 57.32, "elapsed_time": "11:54:47", "remaining_time": "8:52:18"} +{"current_steps": 3210, "total_steps": 5583, "loss": 0.3592, "lr": 5e-06, "epoch": 1.7244157937147462, "percentage": 57.5, "elapsed_time": "11:56:59", "remaining_time": "8:50:02"} +{"current_steps": 3220, "total_steps": 5583, "loss": 0.3621, "lr": 5e-06, "epoch": 1.7297878055331721, "percentage": 57.68, "elapsed_time": "11:59:11", "remaining_time": "8:47:47"} +{"current_steps": 3230, "total_steps": 5583, "loss": 0.3521, "lr": 5e-06, "epoch": 1.7351598173515983, "percentage": 57.85, "elapsed_time": "12:01:24", "remaining_time": "8:45:32"} +{"current_steps": 3240, "total_steps": 5583, "loss": 0.3556, "lr": 5e-06, "epoch": 1.740531829170024, "percentage": 58.03, "elapsed_time": "12:03:37", "remaining_time": "8:43:16"} +{"current_steps": 3250, "total_steps": 5583, "loss": 0.3624, "lr": 5e-06, "epoch": 1.7459038409884502, "percentage": 58.21, "elapsed_time": "12:05:49", "remaining_time": "8:41:01"} +{"current_steps": 3260, "total_steps": 5583, "loss": 0.355, "lr": 5e-06, "epoch": 1.7512758528068761, "percentage": 58.39, "elapsed_time": "12:08:01", "remaining_time": "8:38:46"} +{"current_steps": 3270, "total_steps": 5583, "loss": 0.3584, "lr": 5e-06, "epoch": 1.756647864625302, "percentage": 58.57, "elapsed_time": "12:10:13", "remaining_time": "8:36:30"} +{"current_steps": 3280, "total_steps": 5583, "loss": 0.3562, "lr": 5e-06, "epoch": 1.7620198764437283, "percentage": 58.75, "elapsed_time": "12:12:25", "remaining_time": "8:34:15"} +{"current_steps": 3290, "total_steps": 5583, "loss": 0.3596, "lr": 5e-06, "epoch": 1.7673918882621542, "percentage": 58.93, "elapsed_time": "12:14:37", "remaining_time": "8:32:00"} +{"current_steps": 3300, "total_steps": 5583, "loss": 0.3492, "lr": 5e-06, "epoch": 1.7727639000805802, "percentage": 59.11, "elapsed_time": "12:16:50", "remaining_time": "8:29:45"} +{"current_steps": 3310, "total_steps": 5583, "loss": 0.3445, "lr": 5e-06, "epoch": 1.7781359118990063, "percentage": 59.29, "elapsed_time": "12:19:01", "remaining_time": "8:27:29"} +{"current_steps": 3320, "total_steps": 5583, "loss": 0.3571, "lr": 5e-06, "epoch": 1.783507923717432, "percentage": 59.47, "elapsed_time": "12:21:13", "remaining_time": "8:25:14"} +{"current_steps": 3330, "total_steps": 5583, "loss": 0.3552, "lr": 5e-06, "epoch": 1.7888799355358582, "percentage": 59.65, "elapsed_time": "12:23:26", "remaining_time": "8:22:59"} +{"current_steps": 3340, "total_steps": 5583, "loss": 0.3595, "lr": 5e-06, "epoch": 1.7942519473542842, "percentage": 59.82, "elapsed_time": "12:25:38", "remaining_time": "8:20:44"} +{"current_steps": 3350, "total_steps": 5583, "loss": 0.3513, "lr": 5e-06, "epoch": 1.7996239591727101, "percentage": 60.0, "elapsed_time": "12:27:50", "remaining_time": "8:18:29"} +{"current_steps": 3360, "total_steps": 5583, "loss": 0.3584, "lr": 5e-06, "epoch": 1.8049959709911363, "percentage": 60.18, "elapsed_time": "12:30:02", "remaining_time": "8:16:14"} +{"current_steps": 3370, "total_steps": 5583, "loss": 0.3691, "lr": 5e-06, "epoch": 1.810367982809562, "percentage": 60.36, "elapsed_time": "12:32:14", "remaining_time": "8:13:58"} +{"current_steps": 3380, "total_steps": 5583, "loss": 0.3582, "lr": 5e-06, "epoch": 1.8157399946279882, "percentage": 60.54, "elapsed_time": "12:34:26", "remaining_time": "8:11:43"} +{"current_steps": 3390, "total_steps": 5583, "loss": 0.3469, "lr": 5e-06, "epoch": 1.8211120064464141, "percentage": 60.72, "elapsed_time": "12:36:38", "remaining_time": "8:09:28"} +{"current_steps": 3400, "total_steps": 5583, "loss": 0.3593, "lr": 5e-06, "epoch": 1.82648401826484, "percentage": 60.9, "elapsed_time": "12:38:50", "remaining_time": "8:07:13"} +{"current_steps": 3410, "total_steps": 5583, "loss": 0.3531, "lr": 5e-06, "epoch": 1.8318560300832663, "percentage": 61.08, "elapsed_time": "12:41:03", "remaining_time": "8:04:58"} +{"current_steps": 3420, "total_steps": 5583, "loss": 0.3512, "lr": 5e-06, "epoch": 1.8372280419016922, "percentage": 61.26, "elapsed_time": "12:43:15", "remaining_time": "8:02:43"} +{"current_steps": 3430, "total_steps": 5583, "loss": 0.3535, "lr": 5e-06, "epoch": 1.8426000537201181, "percentage": 61.44, "elapsed_time": "12:45:28", "remaining_time": "8:00:28"} +{"current_steps": 3440, "total_steps": 5583, "loss": 0.3646, "lr": 5e-06, "epoch": 1.8479720655385443, "percentage": 61.62, "elapsed_time": "12:47:40", "remaining_time": "7:58:13"} +{"current_steps": 3450, "total_steps": 5583, "loss": 0.3521, "lr": 5e-06, "epoch": 1.85334407735697, "percentage": 61.79, "elapsed_time": "12:49:52", "remaining_time": "7:55:59"} +{"current_steps": 3460, "total_steps": 5583, "loss": 0.3453, "lr": 5e-06, "epoch": 1.8587160891753962, "percentage": 61.97, "elapsed_time": "12:52:04", "remaining_time": "7:53:44"} +{"current_steps": 3470, "total_steps": 5583, "loss": 0.3642, "lr": 5e-06, "epoch": 1.8640881009938222, "percentage": 62.15, "elapsed_time": "12:54:16", "remaining_time": "7:51:29"} +{"current_steps": 3480, "total_steps": 5583, "loss": 0.3573, "lr": 5e-06, "epoch": 1.869460112812248, "percentage": 62.33, "elapsed_time": "12:56:29", "remaining_time": "7:49:14"} +{"current_steps": 3490, "total_steps": 5583, "loss": 0.3638, "lr": 5e-06, "epoch": 1.8748321246306743, "percentage": 62.51, "elapsed_time": "12:58:41", "remaining_time": "7:46:59"} +{"current_steps": 3500, "total_steps": 5583, "loss": 0.3497, "lr": 5e-06, "epoch": 1.8802041364491002, "percentage": 62.69, "elapsed_time": "13:00:54", "remaining_time": "7:44:44"} +{"current_steps": 3510, "total_steps": 5583, "loss": 0.357, "lr": 5e-06, "epoch": 1.8855761482675262, "percentage": 62.87, "elapsed_time": "13:03:06", "remaining_time": "7:42:30"} +{"current_steps": 3520, "total_steps": 5583, "loss": 0.3583, "lr": 5e-06, "epoch": 1.8909481600859523, "percentage": 63.05, "elapsed_time": "13:05:18", "remaining_time": "7:40:15"} +{"current_steps": 3530, "total_steps": 5583, "loss": 0.3492, "lr": 5e-06, "epoch": 1.896320171904378, "percentage": 63.23, "elapsed_time": "13:07:31", "remaining_time": "7:38:00"} +{"current_steps": 3540, "total_steps": 5583, "loss": 0.3526, "lr": 5e-06, "epoch": 1.9016921837228042, "percentage": 63.41, "elapsed_time": "13:09:44", "remaining_time": "7:35:46"} +{"current_steps": 3550, "total_steps": 5583, "loss": 0.3631, "lr": 5e-06, "epoch": 1.9070641955412302, "percentage": 63.59, "elapsed_time": "13:11:56", "remaining_time": "7:33:31"} +{"current_steps": 3560, "total_steps": 5583, "loss": 0.3523, "lr": 5e-06, "epoch": 1.9124362073596561, "percentage": 63.77, "elapsed_time": "13:14:09", "remaining_time": "7:31:16"} +{"current_steps": 3570, "total_steps": 5583, "loss": 0.3594, "lr": 5e-06, "epoch": 1.9178082191780823, "percentage": 63.94, "elapsed_time": "13:16:21", "remaining_time": "7:29:02"} +{"current_steps": 3580, "total_steps": 5583, "loss": 0.3554, "lr": 5e-06, "epoch": 1.923180230996508, "percentage": 64.12, "elapsed_time": "13:18:33", "remaining_time": "7:26:47"} +{"current_steps": 3590, "total_steps": 5583, "loss": 0.3507, "lr": 5e-06, "epoch": 1.9285522428149342, "percentage": 64.3, "elapsed_time": "13:20:46", "remaining_time": "7:24:33"} +{"current_steps": 3600, "total_steps": 5583, "loss": 0.3694, "lr": 5e-06, "epoch": 1.9339242546333602, "percentage": 64.48, "elapsed_time": "13:22:58", "remaining_time": "7:22:18"} +{"current_steps": 3610, "total_steps": 5583, "loss": 0.3629, "lr": 5e-06, "epoch": 1.939296266451786, "percentage": 64.66, "elapsed_time": "13:25:10", "remaining_time": "7:20:03"} +{"current_steps": 3620, "total_steps": 5583, "loss": 0.3526, "lr": 5e-06, "epoch": 1.9446682782702123, "percentage": 64.84, "elapsed_time": "13:27:23", "remaining_time": "7:17:49"} +{"current_steps": 3630, "total_steps": 5583, "loss": 0.3401, "lr": 5e-06, "epoch": 1.9500402900886382, "percentage": 65.02, "elapsed_time": "13:29:35", "remaining_time": "7:15:34"} +{"current_steps": 3640, "total_steps": 5583, "loss": 0.342, "lr": 5e-06, "epoch": 1.9554123019070642, "percentage": 65.2, "elapsed_time": "13:31:47", "remaining_time": "7:13:19"} +{"current_steps": 3650, "total_steps": 5583, "loss": 0.3543, "lr": 5e-06, "epoch": 1.9607843137254903, "percentage": 65.38, "elapsed_time": "13:34:00", "remaining_time": "7:11:05"} +{"current_steps": 3660, "total_steps": 5583, "loss": 0.3705, "lr": 5e-06, "epoch": 1.966156325543916, "percentage": 65.56, "elapsed_time": "13:36:12", "remaining_time": "7:08:50"} +{"current_steps": 3670, "total_steps": 5583, "loss": 0.355, "lr": 5e-06, "epoch": 1.9715283373623422, "percentage": 65.74, "elapsed_time": "13:38:25", "remaining_time": "7:06:36"} +{"current_steps": 3680, "total_steps": 5583, "loss": 0.3546, "lr": 5e-06, "epoch": 1.9769003491807682, "percentage": 65.91, "elapsed_time": "13:40:38", "remaining_time": "7:04:22"} +{"current_steps": 3690, "total_steps": 5583, "loss": 0.3518, "lr": 5e-06, "epoch": 1.9822723609991941, "percentage": 66.09, "elapsed_time": "13:42:50", "remaining_time": "7:02:07"} +{"current_steps": 3700, "total_steps": 5583, "loss": 0.3664, "lr": 5e-06, "epoch": 1.9876443728176203, "percentage": 66.27, "elapsed_time": "13:45:03", "remaining_time": "6:59:53"} +{"current_steps": 3710, "total_steps": 5583, "loss": 0.3609, "lr": 5e-06, "epoch": 1.9930163846360462, "percentage": 66.45, "elapsed_time": "13:47:15", "remaining_time": "6:57:38"} +{"current_steps": 3720, "total_steps": 5583, "loss": 0.3514, "lr": 5e-06, "epoch": 1.9983883964544722, "percentage": 66.63, "elapsed_time": "13:49:27", "remaining_time": "6:55:24"} +{"current_steps": 3723, "total_steps": 5583, "eval_loss": 0.39740535616874695, "epoch": 2.0, "percentage": 66.68, "elapsed_time": "13:57:54", "remaining_time": "6:58:36"} +{"current_steps": 3730, "total_steps": 5583, "loss": 0.3332, "lr": 5e-06, "epoch": 2.0037604082728984, "percentage": 66.81, "elapsed_time": "14:00:35", "remaining_time": "6:57:35"} +{"current_steps": 3740, "total_steps": 5583, "loss": 0.3166, "lr": 5e-06, "epoch": 2.009132420091324, "percentage": 66.99, "elapsed_time": "14:02:48", "remaining_time": "6:55:19"} +{"current_steps": 3750, "total_steps": 5583, "loss": 0.2932, "lr": 5e-06, "epoch": 2.0145044319097503, "percentage": 67.17, "elapsed_time": "14:05:00", "remaining_time": "6:53:02"} +{"current_steps": 3760, "total_steps": 5583, "loss": 0.2966, "lr": 5e-06, "epoch": 2.019876443728176, "percentage": 67.35, "elapsed_time": "14:07:13", "remaining_time": "6:50:45"} +{"current_steps": 3770, "total_steps": 5583, "loss": 0.3013, "lr": 5e-06, "epoch": 2.025248455546602, "percentage": 67.53, "elapsed_time": "14:09:25", "remaining_time": "6:48:29"} +{"current_steps": 3780, "total_steps": 5583, "loss": 0.287, "lr": 5e-06, "epoch": 2.0306204673650283, "percentage": 67.71, "elapsed_time": "14:11:37", "remaining_time": "6:46:12"} +{"current_steps": 3790, "total_steps": 5583, "loss": 0.301, "lr": 5e-06, "epoch": 2.035992479183454, "percentage": 67.88, "elapsed_time": "14:13:50", "remaining_time": "6:43:56"} +{"current_steps": 3800, "total_steps": 5583, "loss": 0.2955, "lr": 5e-06, "epoch": 2.04136449100188, "percentage": 68.06, "elapsed_time": "14:16:02", "remaining_time": "6:41:39"} +{"current_steps": 3810, "total_steps": 5583, "loss": 0.2935, "lr": 5e-06, "epoch": 2.0467365028203064, "percentage": 68.24, "elapsed_time": "14:18:15", "remaining_time": "6:39:23"} +{"current_steps": 3820, "total_steps": 5583, "loss": 0.3013, "lr": 5e-06, "epoch": 2.052108514638732, "percentage": 68.42, "elapsed_time": "14:20:27", "remaining_time": "6:37:07"} +{"current_steps": 3830, "total_steps": 5583, "loss": 0.3082, "lr": 5e-06, "epoch": 2.0574805264571583, "percentage": 68.6, "elapsed_time": "14:22:40", "remaining_time": "6:34:50"} +{"current_steps": 3840, "total_steps": 5583, "loss": 0.2919, "lr": 5e-06, "epoch": 2.062852538275584, "percentage": 68.78, "elapsed_time": "14:24:52", "remaining_time": "6:32:34"} +{"current_steps": 3850, "total_steps": 5583, "loss": 0.3087, "lr": 5e-06, "epoch": 2.06822455009401, "percentage": 68.96, "elapsed_time": "14:27:05", "remaining_time": "6:30:18"} +{"current_steps": 3860, "total_steps": 5583, "loss": 0.3031, "lr": 5e-06, "epoch": 2.0735965619124364, "percentage": 69.14, "elapsed_time": "14:29:17", "remaining_time": "6:28:01"} +{"current_steps": 3870, "total_steps": 5583, "loss": 0.2934, "lr": 5e-06, "epoch": 2.078968573730862, "percentage": 69.32, "elapsed_time": "14:31:28", "remaining_time": "6:25:44"} +{"current_steps": 3880, "total_steps": 5583, "loss": 0.302, "lr": 5e-06, "epoch": 2.0843405855492882, "percentage": 69.5, "elapsed_time": "14:33:40", "remaining_time": "6:23:28"} +{"current_steps": 3890, "total_steps": 5583, "loss": 0.295, "lr": 5e-06, "epoch": 2.0897125973677144, "percentage": 69.68, "elapsed_time": "14:35:53", "remaining_time": "6:21:12"} +{"current_steps": 3900, "total_steps": 5583, "loss": 0.2952, "lr": 5e-06, "epoch": 2.09508460918614, "percentage": 69.85, "elapsed_time": "14:38:05", "remaining_time": "6:18:55"} +{"current_steps": 3910, "total_steps": 5583, "loss": 0.2961, "lr": 5e-06, "epoch": 2.1004566210045663, "percentage": 70.03, "elapsed_time": "14:40:17", "remaining_time": "6:16:39"} +{"current_steps": 3920, "total_steps": 5583, "loss": 0.3072, "lr": 5e-06, "epoch": 2.105828632822992, "percentage": 70.21, "elapsed_time": "14:42:29", "remaining_time": "6:14:23"} +{"current_steps": 3930, "total_steps": 5583, "loss": 0.2989, "lr": 5e-06, "epoch": 2.111200644641418, "percentage": 70.39, "elapsed_time": "14:44:41", "remaining_time": "6:12:06"} +{"current_steps": 3940, "total_steps": 5583, "loss": 0.3057, "lr": 5e-06, "epoch": 2.1165726564598444, "percentage": 70.57, "elapsed_time": "14:46:54", "remaining_time": "6:09:50"} +{"current_steps": 3950, "total_steps": 5583, "loss": 0.2945, "lr": 5e-06, "epoch": 2.12194466827827, "percentage": 70.75, "elapsed_time": "14:49:05", "remaining_time": "6:07:34"} +{"current_steps": 3960, "total_steps": 5583, "loss": 0.2972, "lr": 5e-06, "epoch": 2.1273166800966963, "percentage": 70.93, "elapsed_time": "14:51:18", "remaining_time": "6:05:17"} +{"current_steps": 3970, "total_steps": 5583, "loss": 0.2931, "lr": 5e-06, "epoch": 2.1326886919151224, "percentage": 71.11, "elapsed_time": "14:53:30", "remaining_time": "6:03:01"} +{"current_steps": 3980, "total_steps": 5583, "loss": 0.289, "lr": 5e-06, "epoch": 2.138060703733548, "percentage": 71.29, "elapsed_time": "14:55:43", "remaining_time": "6:00:45"} +{"current_steps": 3990, "total_steps": 5583, "loss": 0.2981, "lr": 5e-06, "epoch": 2.1434327155519743, "percentage": 71.47, "elapsed_time": "14:57:55", "remaining_time": "5:58:29"} +{"current_steps": 4000, "total_steps": 5583, "loss": 0.2946, "lr": 5e-06, "epoch": 2.1488047273704, "percentage": 71.65, "elapsed_time": "15:00:08", "remaining_time": "5:56:13"} +{"current_steps": 4010, "total_steps": 5583, "loss": 0.2963, "lr": 5e-06, "epoch": 2.1541767391888262, "percentage": 71.83, "elapsed_time": "15:02:20", "remaining_time": "5:53:57"} +{"current_steps": 4020, "total_steps": 5583, "loss": 0.2965, "lr": 5e-06, "epoch": 2.1595487510072524, "percentage": 72.0, "elapsed_time": "15:04:32", "remaining_time": "5:51:41"} +{"current_steps": 4030, "total_steps": 5583, "loss": 0.3075, "lr": 5e-06, "epoch": 2.164920762825678, "percentage": 72.18, "elapsed_time": "15:06:45", "remaining_time": "5:49:25"} +{"current_steps": 4040, "total_steps": 5583, "loss": 0.3034, "lr": 5e-06, "epoch": 2.1702927746441043, "percentage": 72.36, "elapsed_time": "15:08:57", "remaining_time": "5:47:09"} +{"current_steps": 4050, "total_steps": 5583, "loss": 0.2959, "lr": 5e-06, "epoch": 2.17566478646253, "percentage": 72.54, "elapsed_time": "15:11:09", "remaining_time": "5:44:53"} +{"current_steps": 4060, "total_steps": 5583, "loss": 0.2927, "lr": 5e-06, "epoch": 2.181036798280956, "percentage": 72.72, "elapsed_time": "15:13:21", "remaining_time": "5:42:37"} +{"current_steps": 4070, "total_steps": 5583, "loss": 0.3002, "lr": 5e-06, "epoch": 2.1864088100993824, "percentage": 72.9, "elapsed_time": "15:15:33", "remaining_time": "5:40:21"} +{"current_steps": 4080, "total_steps": 5583, "loss": 0.2941, "lr": 5e-06, "epoch": 2.191780821917808, "percentage": 73.08, "elapsed_time": "15:17:45", "remaining_time": "5:38:05"} +{"current_steps": 4090, "total_steps": 5583, "loss": 0.2959, "lr": 5e-06, "epoch": 2.1971528337362343, "percentage": 73.26, "elapsed_time": "15:19:57", "remaining_time": "5:35:49"} +{"current_steps": 4100, "total_steps": 5583, "loss": 0.3004, "lr": 5e-06, "epoch": 2.2025248455546604, "percentage": 73.44, "elapsed_time": "15:22:10", "remaining_time": "5:33:33"} +{"current_steps": 4110, "total_steps": 5583, "loss": 0.3006, "lr": 5e-06, "epoch": 2.207896857373086, "percentage": 73.62, "elapsed_time": "15:24:22", "remaining_time": "5:31:17"} +{"current_steps": 4120, "total_steps": 5583, "loss": 0.3043, "lr": 5e-06, "epoch": 2.2132688691915123, "percentage": 73.8, "elapsed_time": "15:26:34", "remaining_time": "5:29:01"} +{"current_steps": 4130, "total_steps": 5583, "loss": 0.3026, "lr": 5e-06, "epoch": 2.218640881009938, "percentage": 73.97, "elapsed_time": "15:28:46", "remaining_time": "5:26:45"} +{"current_steps": 4140, "total_steps": 5583, "loss": 0.2997, "lr": 5e-06, "epoch": 2.2240128928283642, "percentage": 74.15, "elapsed_time": "15:30:59", "remaining_time": "5:24:29"} +{"current_steps": 4150, "total_steps": 5583, "loss": 0.3053, "lr": 5e-06, "epoch": 2.2293849046467904, "percentage": 74.33, "elapsed_time": "15:33:11", "remaining_time": "5:22:13"} +{"current_steps": 4160, "total_steps": 5583, "loss": 0.2935, "lr": 5e-06, "epoch": 2.234756916465216, "percentage": 74.51, "elapsed_time": "15:35:23", "remaining_time": "5:19:58"} +{"current_steps": 4170, "total_steps": 5583, "loss": 0.2984, "lr": 5e-06, "epoch": 2.2401289282836423, "percentage": 74.69, "elapsed_time": "15:37:35", "remaining_time": "5:17:42"} +{"current_steps": 4180, "total_steps": 5583, "loss": 0.3002, "lr": 5e-06, "epoch": 2.245500940102068, "percentage": 74.87, "elapsed_time": "15:39:47", "remaining_time": "5:15:26"} +{"current_steps": 4190, "total_steps": 5583, "loss": 0.2942, "lr": 5e-06, "epoch": 2.250872951920494, "percentage": 75.05, "elapsed_time": "15:42:00", "remaining_time": "5:13:10"} +{"current_steps": 4200, "total_steps": 5583, "loss": 0.3084, "lr": 5e-06, "epoch": 2.2562449637389204, "percentage": 75.23, "elapsed_time": "15:44:12", "remaining_time": "5:10:54"} +{"current_steps": 4210, "total_steps": 5583, "loss": 0.3061, "lr": 5e-06, "epoch": 2.261616975557346, "percentage": 75.41, "elapsed_time": "15:46:24", "remaining_time": "5:08:39"} +{"current_steps": 4220, "total_steps": 5583, "loss": 0.3088, "lr": 5e-06, "epoch": 2.2669889873757723, "percentage": 75.59, "elapsed_time": "15:48:37", "remaining_time": "5:06:23"} +{"current_steps": 4230, "total_steps": 5583, "loss": 0.2995, "lr": 5e-06, "epoch": 2.2723609991941984, "percentage": 75.77, "elapsed_time": "15:50:49", "remaining_time": "5:04:07"} +{"current_steps": 4240, "total_steps": 5583, "loss": 0.3008, "lr": 5e-06, "epoch": 2.277733011012624, "percentage": 75.94, "elapsed_time": "15:53:01", "remaining_time": "5:01:52"} +{"current_steps": 4250, "total_steps": 5583, "loss": 0.3144, "lr": 5e-06, "epoch": 2.2831050228310503, "percentage": 76.12, "elapsed_time": "15:55:14", "remaining_time": "4:59:36"} +{"current_steps": 4260, "total_steps": 5583, "loss": 0.2998, "lr": 5e-06, "epoch": 2.288477034649476, "percentage": 76.3, "elapsed_time": "15:57:26", "remaining_time": "4:57:20"} +{"current_steps": 4270, "total_steps": 5583, "loss": 0.2985, "lr": 5e-06, "epoch": 2.293849046467902, "percentage": 76.48, "elapsed_time": "15:59:38", "remaining_time": "4:55:05"} +{"current_steps": 4280, "total_steps": 5583, "loss": 0.3005, "lr": 5e-06, "epoch": 2.2992210582863284, "percentage": 76.66, "elapsed_time": "16:01:50", "remaining_time": "4:52:49"} +{"current_steps": 4290, "total_steps": 5583, "loss": 0.2885, "lr": 5e-06, "epoch": 2.304593070104754, "percentage": 76.84, "elapsed_time": "16:04:02", "remaining_time": "4:50:33"} +{"current_steps": 4300, "total_steps": 5583, "loss": 0.3021, "lr": 5e-06, "epoch": 2.3099650819231803, "percentage": 77.02, "elapsed_time": "16:06:14", "remaining_time": "4:48:17"} +{"current_steps": 4310, "total_steps": 5583, "loss": 0.2969, "lr": 5e-06, "epoch": 2.315337093741606, "percentage": 77.2, "elapsed_time": "16:08:26", "remaining_time": "4:46:02"} +{"current_steps": 4320, "total_steps": 5583, "loss": 0.3074, "lr": 5e-06, "epoch": 2.320709105560032, "percentage": 77.38, "elapsed_time": "16:10:38", "remaining_time": "4:43:46"} +{"current_steps": 4330, "total_steps": 5583, "loss": 0.2983, "lr": 5e-06, "epoch": 2.3260811173784584, "percentage": 77.56, "elapsed_time": "16:12:50", "remaining_time": "4:41:31"} +{"current_steps": 4340, "total_steps": 5583, "loss": 0.3045, "lr": 5e-06, "epoch": 2.331453129196884, "percentage": 77.74, "elapsed_time": "16:15:02", "remaining_time": "4:39:15"} +{"current_steps": 4350, "total_steps": 5583, "loss": 0.307, "lr": 5e-06, "epoch": 2.3368251410153102, "percentage": 77.92, "elapsed_time": "16:17:15", "remaining_time": "4:36:59"} +{"current_steps": 4360, "total_steps": 5583, "loss": 0.3021, "lr": 5e-06, "epoch": 2.3421971528337364, "percentage": 78.09, "elapsed_time": "16:19:27", "remaining_time": "4:34:44"} +{"current_steps": 4370, "total_steps": 5583, "loss": 0.304, "lr": 5e-06, "epoch": 2.347569164652162, "percentage": 78.27, "elapsed_time": "16:21:39", "remaining_time": "4:32:28"} +{"current_steps": 4380, "total_steps": 5583, "loss": 0.3013, "lr": 5e-06, "epoch": 2.3529411764705883, "percentage": 78.45, "elapsed_time": "16:23:51", "remaining_time": "4:30:13"} +{"current_steps": 4390, "total_steps": 5583, "loss": 0.2961, "lr": 5e-06, "epoch": 2.3583131882890145, "percentage": 78.63, "elapsed_time": "16:26:03", "remaining_time": "4:27:57"} +{"current_steps": 4400, "total_steps": 5583, "loss": 0.3007, "lr": 5e-06, "epoch": 2.36368520010744, "percentage": 78.81, "elapsed_time": "16:28:14", "remaining_time": "4:25:42"} +{"current_steps": 4410, "total_steps": 5583, "loss": 0.299, "lr": 5e-06, "epoch": 2.3690572119258664, "percentage": 78.99, "elapsed_time": "16:30:26", "remaining_time": "4:23:26"} +{"current_steps": 4420, "total_steps": 5583, "loss": 0.3077, "lr": 5e-06, "epoch": 2.374429223744292, "percentage": 79.17, "elapsed_time": "16:32:38", "remaining_time": "4:21:11"} +{"current_steps": 4430, "total_steps": 5583, "loss": 0.2893, "lr": 5e-06, "epoch": 2.3798012355627183, "percentage": 79.35, "elapsed_time": "16:34:50", "remaining_time": "4:18:55"} +{"current_steps": 4440, "total_steps": 5583, "loss": 0.2981, "lr": 5e-06, "epoch": 2.385173247381144, "percentage": 79.53, "elapsed_time": "16:37:03", "remaining_time": "4:16:40"} +{"current_steps": 4450, "total_steps": 5583, "loss": 0.2944, "lr": 5e-06, "epoch": 2.39054525919957, "percentage": 79.71, "elapsed_time": "16:39:15", "remaining_time": "4:14:25"} +{"current_steps": 4460, "total_steps": 5583, "loss": 0.3027, "lr": 5e-06, "epoch": 2.3959172710179963, "percentage": 79.89, "elapsed_time": "16:41:27", "remaining_time": "4:12:09"} +{"current_steps": 4470, "total_steps": 5583, "loss": 0.2982, "lr": 5e-06, "epoch": 2.401289282836422, "percentage": 80.06, "elapsed_time": "16:43:39", "remaining_time": "4:09:54"} +{"current_steps": 4480, "total_steps": 5583, "loss": 0.3055, "lr": 5e-06, "epoch": 2.4066612946548482, "percentage": 80.24, "elapsed_time": "16:45:51", "remaining_time": "4:07:38"} +{"current_steps": 4490, "total_steps": 5583, "loss": 0.308, "lr": 5e-06, "epoch": 2.4120333064732744, "percentage": 80.42, "elapsed_time": "16:48:02", "remaining_time": "4:05:23"} +{"current_steps": 4500, "total_steps": 5583, "loss": 0.2988, "lr": 5e-06, "epoch": 2.4174053182917, "percentage": 80.6, "elapsed_time": "16:50:14", "remaining_time": "4:03:08"} +{"current_steps": 4510, "total_steps": 5583, "loss": 0.3021, "lr": 5e-06, "epoch": 2.4227773301101263, "percentage": 80.78, "elapsed_time": "16:52:27", "remaining_time": "4:00:52"} +{"current_steps": 4520, "total_steps": 5583, "loss": 0.3004, "lr": 5e-06, "epoch": 2.4281493419285525, "percentage": 80.96, "elapsed_time": "16:54:39", "remaining_time": "3:58:37"} +{"current_steps": 4530, "total_steps": 5583, "loss": 0.3033, "lr": 5e-06, "epoch": 2.433521353746978, "percentage": 81.14, "elapsed_time": "16:56:51", "remaining_time": "3:56:22"} +{"current_steps": 4540, "total_steps": 5583, "loss": 0.3071, "lr": 5e-06, "epoch": 2.4388933655654044, "percentage": 81.32, "elapsed_time": "16:59:03", "remaining_time": "3:54:06"} +{"current_steps": 4550, "total_steps": 5583, "loss": 0.3003, "lr": 5e-06, "epoch": 2.44426537738383, "percentage": 81.5, "elapsed_time": "17:01:15", "remaining_time": "3:51:51"} +{"current_steps": 4560, "total_steps": 5583, "loss": 0.2979, "lr": 5e-06, "epoch": 2.4496373892022563, "percentage": 81.68, "elapsed_time": "17:03:27", "remaining_time": "3:49:36"} +{"current_steps": 4570, "total_steps": 5583, "loss": 0.323, "lr": 5e-06, "epoch": 2.4550094010206824, "percentage": 81.86, "elapsed_time": "17:05:39", "remaining_time": "3:47:20"} +{"current_steps": 4580, "total_steps": 5583, "loss": 0.2973, "lr": 5e-06, "epoch": 2.460381412839108, "percentage": 82.03, "elapsed_time": "17:07:51", "remaining_time": "3:45:05"} +{"current_steps": 4590, "total_steps": 5583, "loss": 0.2923, "lr": 5e-06, "epoch": 2.4657534246575343, "percentage": 82.21, "elapsed_time": "17:10:03", "remaining_time": "3:42:50"} +{"current_steps": 4600, "total_steps": 5583, "loss": 0.3091, "lr": 5e-06, "epoch": 2.47112543647596, "percentage": 82.39, "elapsed_time": "17:12:16", "remaining_time": "3:40:35"} +{"current_steps": 4610, "total_steps": 5583, "loss": 0.2982, "lr": 5e-06, "epoch": 2.4764974482943862, "percentage": 82.57, "elapsed_time": "17:14:28", "remaining_time": "3:38:20"} +{"current_steps": 4620, "total_steps": 5583, "loss": 0.3109, "lr": 5e-06, "epoch": 2.4818694601128124, "percentage": 82.75, "elapsed_time": "17:16:40", "remaining_time": "3:36:05"} +{"current_steps": 4630, "total_steps": 5583, "loss": 0.3043, "lr": 5e-06, "epoch": 2.487241471931238, "percentage": 82.93, "elapsed_time": "17:18:52", "remaining_time": "3:33:50"} +{"current_steps": 4640, "total_steps": 5583, "loss": 0.307, "lr": 5e-06, "epoch": 2.4926134837496643, "percentage": 83.11, "elapsed_time": "17:21:04", "remaining_time": "3:31:34"} +{"current_steps": 4650, "total_steps": 5583, "loss": 0.306, "lr": 5e-06, "epoch": 2.4979854955680905, "percentage": 83.29, "elapsed_time": "17:23:17", "remaining_time": "3:29:19"} +{"current_steps": 4660, "total_steps": 5583, "loss": 0.3007, "lr": 5e-06, "epoch": 2.503357507386516, "percentage": 83.47, "elapsed_time": "17:25:29", "remaining_time": "3:27:04"} +{"current_steps": 4670, "total_steps": 5583, "loss": 0.3284, "lr": 5e-06, "epoch": 2.5087295192049424, "percentage": 83.65, "elapsed_time": "17:27:41", "remaining_time": "3:24:49"} +{"current_steps": 4680, "total_steps": 5583, "loss": 0.3045, "lr": 5e-06, "epoch": 2.514101531023368, "percentage": 83.83, "elapsed_time": "17:29:53", "remaining_time": "3:22:34"} +{"current_steps": 4690, "total_steps": 5583, "loss": 0.3188, "lr": 5e-06, "epoch": 2.5194735428417943, "percentage": 84.01, "elapsed_time": "17:32:05", "remaining_time": "3:20:19"} +{"current_steps": 4700, "total_steps": 5583, "loss": 0.296, "lr": 5e-06, "epoch": 2.52484555466022, "percentage": 84.18, "elapsed_time": "17:34:17", "remaining_time": "3:18:04"} +{"current_steps": 4710, "total_steps": 5583, "loss": 0.2974, "lr": 5e-06, "epoch": 2.530217566478646, "percentage": 84.36, "elapsed_time": "17:36:29", "remaining_time": "3:15:49"} +{"current_steps": 4720, "total_steps": 5583, "loss": 0.2979, "lr": 5e-06, "epoch": 2.5355895782970723, "percentage": 84.54, "elapsed_time": "17:38:41", "remaining_time": "3:13:34"} +{"current_steps": 4730, "total_steps": 5583, "loss": 0.3077, "lr": 5e-06, "epoch": 2.540961590115498, "percentage": 84.72, "elapsed_time": "17:40:54", "remaining_time": "3:11:19"} +{"current_steps": 4740, "total_steps": 5583, "loss": 0.3073, "lr": 5e-06, "epoch": 2.546333601933924, "percentage": 84.9, "elapsed_time": "17:43:06", "remaining_time": "3:09:04"} +{"current_steps": 4750, "total_steps": 5583, "loss": 0.2943, "lr": 5e-06, "epoch": 2.5517056137523504, "percentage": 85.08, "elapsed_time": "17:45:18", "remaining_time": "3:06:49"} +{"current_steps": 4760, "total_steps": 5583, "loss": 0.3137, "lr": 5e-06, "epoch": 2.557077625570776, "percentage": 85.26, "elapsed_time": "17:47:30", "remaining_time": "3:04:34"} +{"current_steps": 4770, "total_steps": 5583, "loss": 0.316, "lr": 5e-06, "epoch": 2.5624496373892023, "percentage": 85.44, "elapsed_time": "17:49:42", "remaining_time": "3:02:19"} +{"current_steps": 4780, "total_steps": 5583, "loss": 0.3059, "lr": 5e-06, "epoch": 2.5678216492076285, "percentage": 85.62, "elapsed_time": "17:51:54", "remaining_time": "3:00:04"} +{"current_steps": 4790, "total_steps": 5583, "loss": 0.3019, "lr": 5e-06, "epoch": 2.573193661026054, "percentage": 85.8, "elapsed_time": "17:54:06", "remaining_time": "2:57:49"} +{"current_steps": 4800, "total_steps": 5583, "loss": 0.3049, "lr": 5e-06, "epoch": 2.5785656728444803, "percentage": 85.98, "elapsed_time": "17:56:18", "remaining_time": "2:55:34"} +{"current_steps": 4810, "total_steps": 5583, "loss": 0.3122, "lr": 5e-06, "epoch": 2.5839376846629065, "percentage": 86.15, "elapsed_time": "17:58:30", "remaining_time": "2:53:19"} +{"current_steps": 4820, "total_steps": 5583, "loss": 0.2887, "lr": 5e-06, "epoch": 2.5893096964813322, "percentage": 86.33, "elapsed_time": "18:00:42", "remaining_time": "2:51:04"} +{"current_steps": 4830, "total_steps": 5583, "loss": 0.3054, "lr": 5e-06, "epoch": 2.5946817082997584, "percentage": 86.51, "elapsed_time": "18:02:55", "remaining_time": "2:48:49"} +{"current_steps": 4840, "total_steps": 5583, "loss": 0.2985, "lr": 5e-06, "epoch": 2.600053720118184, "percentage": 86.69, "elapsed_time": "18:05:07", "remaining_time": "2:46:34"} +{"current_steps": 4850, "total_steps": 5583, "loss": 0.3062, "lr": 5e-06, "epoch": 2.6054257319366103, "percentage": 86.87, "elapsed_time": "18:07:19", "remaining_time": "2:44:19"} +{"current_steps": 4860, "total_steps": 5583, "loss": 0.3003, "lr": 5e-06, "epoch": 2.610797743755036, "percentage": 87.05, "elapsed_time": "18:09:30", "remaining_time": "2:42:04"} +{"current_steps": 4870, "total_steps": 5583, "loss": 0.3017, "lr": 5e-06, "epoch": 2.616169755573462, "percentage": 87.23, "elapsed_time": "18:11:43", "remaining_time": "2:39:50"} +{"current_steps": 4880, "total_steps": 5583, "loss": 0.303, "lr": 5e-06, "epoch": 2.6215417673918884, "percentage": 87.41, "elapsed_time": "18:13:55", "remaining_time": "2:37:35"} +{"current_steps": 4890, "total_steps": 5583, "loss": 0.2994, "lr": 5e-06, "epoch": 2.626913779210314, "percentage": 87.59, "elapsed_time": "18:16:07", "remaining_time": "2:35:20"} +{"current_steps": 4900, "total_steps": 5583, "loss": 0.3033, "lr": 5e-06, "epoch": 2.6322857910287403, "percentage": 87.77, "elapsed_time": "18:18:20", "remaining_time": "2:33:05"} +{"current_steps": 4910, "total_steps": 5583, "loss": 0.3169, "lr": 5e-06, "epoch": 2.6376578028471664, "percentage": 87.95, "elapsed_time": "18:20:32", "remaining_time": "2:30:50"} +{"current_steps": 4920, "total_steps": 5583, "loss": 0.2897, "lr": 5e-06, "epoch": 2.643029814665592, "percentage": 88.12, "elapsed_time": "18:22:44", "remaining_time": "2:28:36"} +{"current_steps": 4930, "total_steps": 5583, "loss": 0.3131, "lr": 5e-06, "epoch": 2.6484018264840183, "percentage": 88.3, "elapsed_time": "18:24:56", "remaining_time": "2:26:21"} +{"current_steps": 4940, "total_steps": 5583, "loss": 0.303, "lr": 5e-06, "epoch": 2.6537738383024445, "percentage": 88.48, "elapsed_time": "18:27:08", "remaining_time": "2:24:06"} +{"current_steps": 4950, "total_steps": 5583, "loss": 0.3038, "lr": 5e-06, "epoch": 2.6591458501208702, "percentage": 88.66, "elapsed_time": "18:29:20", "remaining_time": "2:21:51"} +{"current_steps": 4960, "total_steps": 5583, "loss": 0.305, "lr": 5e-06, "epoch": 2.6645178619392964, "percentage": 88.84, "elapsed_time": "18:31:32", "remaining_time": "2:19:36"} +{"current_steps": 4970, "total_steps": 5583, "loss": 0.3128, "lr": 5e-06, "epoch": 2.669889873757722, "percentage": 89.02, "elapsed_time": "18:33:44", "remaining_time": "2:17:22"} +{"current_steps": 4980, "total_steps": 5583, "loss": 0.3009, "lr": 5e-06, "epoch": 2.6752618855761483, "percentage": 89.2, "elapsed_time": "18:35:56", "remaining_time": "2:15:07"} +{"current_steps": 4990, "total_steps": 5583, "loss": 0.2999, "lr": 5e-06, "epoch": 2.680633897394574, "percentage": 89.38, "elapsed_time": "18:38:09", "remaining_time": "2:12:52"} +{"current_steps": 5000, "total_steps": 5583, "loss": 0.302, "lr": 5e-06, "epoch": 2.686005909213, "percentage": 89.56, "elapsed_time": "18:40:21", "remaining_time": "2:10:38"} +{"current_steps": 5010, "total_steps": 5583, "loss": 0.2969, "lr": 5e-06, "epoch": 2.6913779210314264, "percentage": 89.74, "elapsed_time": "18:42:33", "remaining_time": "2:08:23"} +{"current_steps": 5020, "total_steps": 5583, "loss": 0.3124, "lr": 5e-06, "epoch": 2.696749932849852, "percentage": 89.92, "elapsed_time": "18:44:45", "remaining_time": "2:06:08"} +{"current_steps": 5030, "total_steps": 5583, "loss": 0.3259, "lr": 5e-06, "epoch": 2.7021219446682783, "percentage": 90.09, "elapsed_time": "18:46:57", "remaining_time": "2:03:53"} +{"current_steps": 5040, "total_steps": 5583, "loss": 0.3036, "lr": 5e-06, "epoch": 2.7074939564867044, "percentage": 90.27, "elapsed_time": "18:49:09", "remaining_time": "2:01:39"} +{"current_steps": 5050, "total_steps": 5583, "loss": 0.3046, "lr": 5e-06, "epoch": 2.71286596830513, "percentage": 90.45, "elapsed_time": "18:51:21", "remaining_time": "1:59:24"} +{"current_steps": 5060, "total_steps": 5583, "loss": 0.3018, "lr": 5e-06, "epoch": 2.7182379801235563, "percentage": 90.63, "elapsed_time": "18:53:34", "remaining_time": "1:57:09"} +{"current_steps": 5070, "total_steps": 5583, "loss": 0.3026, "lr": 5e-06, "epoch": 2.7236099919419825, "percentage": 90.81, "elapsed_time": "18:55:45", "remaining_time": "1:54:55"} +{"current_steps": 5080, "total_steps": 5583, "loss": 0.3005, "lr": 5e-06, "epoch": 2.7289820037604082, "percentage": 90.99, "elapsed_time": "18:57:57", "remaining_time": "1:52:40"} +{"current_steps": 5090, "total_steps": 5583, "loss": 0.313, "lr": 5e-06, "epoch": 2.7343540155788344, "percentage": 91.17, "elapsed_time": "19:00:08", "remaining_time": "1:50:25"} +{"current_steps": 5100, "total_steps": 5583, "loss": 0.3089, "lr": 5e-06, "epoch": 2.73972602739726, "percentage": 91.35, "elapsed_time": "19:02:20", "remaining_time": "1:48:11"} +{"current_steps": 5110, "total_steps": 5583, "loss": 0.3041, "lr": 5e-06, "epoch": 2.7450980392156863, "percentage": 91.53, "elapsed_time": "19:04:32", "remaining_time": "1:45:56"} +{"current_steps": 5120, "total_steps": 5583, "loss": 0.3116, "lr": 5e-06, "epoch": 2.750470051034112, "percentage": 91.71, "elapsed_time": "19:06:44", "remaining_time": "1:43:41"} +{"current_steps": 5130, "total_steps": 5583, "loss": 0.301, "lr": 5e-06, "epoch": 2.755842062852538, "percentage": 91.89, "elapsed_time": "19:08:56", "remaining_time": "1:41:27"} +{"current_steps": 5140, "total_steps": 5583, "loss": 0.3168, "lr": 5e-06, "epoch": 2.7612140746709644, "percentage": 92.07, "elapsed_time": "19:11:09", "remaining_time": "1:39:12"} +{"current_steps": 5150, "total_steps": 5583, "loss": 0.3091, "lr": 5e-06, "epoch": 2.76658608648939, "percentage": 92.24, "elapsed_time": "19:13:21", "remaining_time": "1:36:58"} +{"current_steps": 5160, "total_steps": 5583, "loss": 0.3029, "lr": 5e-06, "epoch": 2.7719580983078163, "percentage": 92.42, "elapsed_time": "19:15:33", "remaining_time": "1:34:43"} +{"current_steps": 5170, "total_steps": 5583, "loss": 0.3065, "lr": 5e-06, "epoch": 2.7773301101262424, "percentage": 92.6, "elapsed_time": "19:17:45", "remaining_time": "1:32:29"} +{"current_steps": 5180, "total_steps": 5583, "loss": 0.3181, "lr": 5e-06, "epoch": 2.782702121944668, "percentage": 92.78, "elapsed_time": "19:19:57", "remaining_time": "1:30:14"} +{"current_steps": 5190, "total_steps": 5583, "loss": 0.3075, "lr": 5e-06, "epoch": 2.7880741337630943, "percentage": 92.96, "elapsed_time": "19:22:10", "remaining_time": "1:28:00"} +{"current_steps": 5200, "total_steps": 5583, "loss": 0.2989, "lr": 5e-06, "epoch": 2.7934461455815205, "percentage": 93.14, "elapsed_time": "19:24:22", "remaining_time": "1:25:45"} +{"current_steps": 5210, "total_steps": 5583, "loss": 0.3102, "lr": 5e-06, "epoch": 2.798818157399946, "percentage": 93.32, "elapsed_time": "19:26:34", "remaining_time": "1:23:31"} +{"current_steps": 5220, "total_steps": 5583, "loss": 0.3064, "lr": 5e-06, "epoch": 2.8041901692183724, "percentage": 93.5, "elapsed_time": "19:28:47", "remaining_time": "1:21:16"} +{"current_steps": 5230, "total_steps": 5583, "loss": 0.3061, "lr": 5e-06, "epoch": 2.8095621810367986, "percentage": 93.68, "elapsed_time": "19:30:59", "remaining_time": "1:19:02"} +{"current_steps": 5240, "total_steps": 5583, "loss": 0.302, "lr": 5e-06, "epoch": 2.8149341928552243, "percentage": 93.86, "elapsed_time": "19:33:11", "remaining_time": "1:16:47"} +{"current_steps": 5250, "total_steps": 5583, "loss": 0.3008, "lr": 5e-06, "epoch": 2.82030620467365, "percentage": 94.04, "elapsed_time": "19:35:23", "remaining_time": "1:14:33"} +{"current_steps": 5260, "total_steps": 5583, "loss": 0.3009, "lr": 5e-06, "epoch": 2.825678216492076, "percentage": 94.21, "elapsed_time": "19:37:35", "remaining_time": "1:12:18"} +{"current_steps": 5270, "total_steps": 5583, "loss": 0.3125, "lr": 5e-06, "epoch": 2.8310502283105023, "percentage": 94.39, "elapsed_time": "19:39:47", "remaining_time": "1:10:04"} +{"current_steps": 5280, "total_steps": 5583, "loss": 0.3076, "lr": 5e-06, "epoch": 2.836422240128928, "percentage": 94.57, "elapsed_time": "19:41:59", "remaining_time": "1:07:49"} +{"current_steps": 5290, "total_steps": 5583, "loss": 0.3017, "lr": 5e-06, "epoch": 2.8417942519473542, "percentage": 94.75, "elapsed_time": "19:44:11", "remaining_time": "1:05:35"} +{"current_steps": 5300, "total_steps": 5583, "loss": 0.3003, "lr": 5e-06, "epoch": 2.8471662637657804, "percentage": 94.93, "elapsed_time": "19:46:24", "remaining_time": "1:03:20"} +{"current_steps": 5310, "total_steps": 5583, "loss": 0.3078, "lr": 5e-06, "epoch": 2.852538275584206, "percentage": 95.11, "elapsed_time": "19:48:36", "remaining_time": "1:01:06"} +{"current_steps": 5320, "total_steps": 5583, "loss": 0.3164, "lr": 5e-06, "epoch": 2.8579102874026323, "percentage": 95.29, "elapsed_time": "19:50:48", "remaining_time": "0:58:52"} +{"current_steps": 5330, "total_steps": 5583, "loss": 0.3035, "lr": 5e-06, "epoch": 2.8632822992210585, "percentage": 95.47, "elapsed_time": "19:53:00", "remaining_time": "0:56:37"} +{"current_steps": 5340, "total_steps": 5583, "loss": 0.3095, "lr": 5e-06, "epoch": 2.868654311039484, "percentage": 95.65, "elapsed_time": "19:55:12", "remaining_time": "0:54:23"} +{"current_steps": 5350, "total_steps": 5583, "loss": 0.3074, "lr": 5e-06, "epoch": 2.8740263228579104, "percentage": 95.83, "elapsed_time": "19:57:25", "remaining_time": "0:52:08"} +{"current_steps": 5360, "total_steps": 5583, "loss": 0.3071, "lr": 5e-06, "epoch": 2.8793983346763365, "percentage": 96.01, "elapsed_time": "19:59:37", "remaining_time": "0:49:54"} +{"current_steps": 5370, "total_steps": 5583, "loss": 0.3077, "lr": 5e-06, "epoch": 2.8847703464947623, "percentage": 96.18, "elapsed_time": "20:01:49", "remaining_time": "0:47:40"} +{"current_steps": 5380, "total_steps": 5583, "loss": 0.303, "lr": 5e-06, "epoch": 2.8901423583131884, "percentage": 96.36, "elapsed_time": "20:04:01", "remaining_time": "0:45:25"} +{"current_steps": 5390, "total_steps": 5583, "loss": 0.2959, "lr": 5e-06, "epoch": 2.895514370131614, "percentage": 96.54, "elapsed_time": "20:06:14", "remaining_time": "0:43:11"} +{"current_steps": 5400, "total_steps": 5583, "loss": 0.3041, "lr": 5e-06, "epoch": 2.9008863819500403, "percentage": 96.72, "elapsed_time": "20:08:26", "remaining_time": "0:40:57"} +{"current_steps": 5410, "total_steps": 5583, "loss": 0.3227, "lr": 5e-06, "epoch": 2.906258393768466, "percentage": 96.9, "elapsed_time": "20:10:38", "remaining_time": "0:38:42"} +{"current_steps": 5420, "total_steps": 5583, "loss": 0.3031, "lr": 5e-06, "epoch": 2.9116304055868922, "percentage": 97.08, "elapsed_time": "20:12:50", "remaining_time": "0:36:28"} +{"current_steps": 5430, "total_steps": 5583, "loss": 0.3048, "lr": 5e-06, "epoch": 2.9170024174053184, "percentage": 97.26, "elapsed_time": "20:15:02", "remaining_time": "0:34:14"} +{"current_steps": 5440, "total_steps": 5583, "loss": 0.3001, "lr": 5e-06, "epoch": 2.922374429223744, "percentage": 97.44, "elapsed_time": "20:17:14", "remaining_time": "0:31:59"} +{"current_steps": 5450, "total_steps": 5583, "loss": 0.298, "lr": 5e-06, "epoch": 2.9277464410421703, "percentage": 97.62, "elapsed_time": "20:19:27", "remaining_time": "0:29:45"} +{"current_steps": 5460, "total_steps": 5583, "loss": 0.2975, "lr": 5e-06, "epoch": 2.9331184528605965, "percentage": 97.8, "elapsed_time": "20:21:39", "remaining_time": "0:27:31"} +{"current_steps": 5470, "total_steps": 5583, "loss": 0.3056, "lr": 5e-06, "epoch": 2.938490464679022, "percentage": 97.98, "elapsed_time": "20:23:51", "remaining_time": "0:25:16"} +{"current_steps": 5480, "total_steps": 5583, "loss": 0.3131, "lr": 5e-06, "epoch": 2.9438624764974484, "percentage": 98.16, "elapsed_time": "20:26:04", "remaining_time": "0:23:02"} +{"current_steps": 5490, "total_steps": 5583, "loss": 0.3026, "lr": 5e-06, "epoch": 2.9492344883158745, "percentage": 98.33, "elapsed_time": "20:28:16", "remaining_time": "0:20:48"} +{"current_steps": 5500, "total_steps": 5583, "loss": 0.31, "lr": 5e-06, "epoch": 2.9546065001343003, "percentage": 98.51, "elapsed_time": "20:30:28", "remaining_time": "0:18:34"} +{"current_steps": 5510, "total_steps": 5583, "loss": 0.3035, "lr": 5e-06, "epoch": 2.9599785119527264, "percentage": 98.69, "elapsed_time": "20:32:40", "remaining_time": "0:16:19"} +{"current_steps": 5520, "total_steps": 5583, "loss": 0.2982, "lr": 5e-06, "epoch": 2.965350523771152, "percentage": 98.87, "elapsed_time": "20:34:52", "remaining_time": "0:14:05"} +{"current_steps": 5530, "total_steps": 5583, "loss": 0.3013, "lr": 5e-06, "epoch": 2.9707225355895783, "percentage": 99.05, "elapsed_time": "20:37:04", "remaining_time": "0:11:51"} +{"current_steps": 5540, "total_steps": 5583, "loss": 0.2999, "lr": 5e-06, "epoch": 2.976094547408004, "percentage": 99.23, "elapsed_time": "20:39:16", "remaining_time": "0:09:37"} +{"current_steps": 5550, "total_steps": 5583, "loss": 0.2999, "lr": 5e-06, "epoch": 2.9814665592264302, "percentage": 99.41, "elapsed_time": "20:41:28", "remaining_time": "0:07:22"} +{"current_steps": 5560, "total_steps": 5583, "loss": 0.3012, "lr": 5e-06, "epoch": 2.9868385710448564, "percentage": 99.59, "elapsed_time": "20:43:40", "remaining_time": "0:05:08"} +{"current_steps": 5570, "total_steps": 5583, "loss": 0.3139, "lr": 5e-06, "epoch": 2.992210582863282, "percentage": 99.77, "elapsed_time": "20:45:52", "remaining_time": "0:02:54"} +{"current_steps": 5580, "total_steps": 5583, "loss": 0.3035, "lr": 5e-06, "epoch": 2.9975825946817083, "percentage": 99.95, "elapsed_time": "20:48:04", "remaining_time": "0:00:40"} +{"current_steps": 5583, "total_steps": 5583, "eval_loss": 0.405712366104126, "epoch": 2.999194198227236, "percentage": 100.0, "elapsed_time": "20:57:42", "remaining_time": "0:00:00"} +{"current_steps": 5583, "total_steps": 5583, "epoch": 2.999194198227236, "percentage": 100.0, "elapsed_time": "20:59:06", "remaining_time": "0:00:00"} diff --git a/trainer_state.json b/trainer_state.json new file mode 100644 index 0000000..f6d7524 --- /dev/null +++ b/trainer_state.json @@ -0,0 +1,3972 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 2.999194198227236, + "eval_steps": 500, + "global_step": 5583, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.005372011818426001, + "grad_norm": 25.23110830120061, + "learning_rate": 5e-06, + "loss": 0.5524, + "step": 10 + }, + { + "epoch": 0.010744023636852002, + "grad_norm": 2.7826435546794013, + "learning_rate": 5e-06, + "loss": 0.5237, + "step": 20 + }, + { + "epoch": 0.016116035455278, + "grad_norm": 0.8773125581852239, + "learning_rate": 5e-06, + "loss": 0.5011, + "step": 30 + }, + { + "epoch": 0.021488047273704004, + "grad_norm": 0.905480676990675, + "learning_rate": 5e-06, + "loss": 0.4903, + "step": 40 + }, + { + "epoch": 0.026860059092130004, + "grad_norm": 0.9003527250388368, + "learning_rate": 5e-06, + "loss": 0.4725, + "step": 50 + }, + { + "epoch": 0.032232070910556, + "grad_norm": 0.7690412778021365, + "learning_rate": 5e-06, + "loss": 0.4683, + "step": 60 + }, + { + "epoch": 0.037604082728982004, + "grad_norm": 0.674228450328133, + "learning_rate": 5e-06, + "loss": 0.465, + "step": 70 + }, + { + "epoch": 0.04297609454740801, + "grad_norm": 0.5682520559652751, + "learning_rate": 5e-06, + "loss": 0.4744, + "step": 80 + }, + { + "epoch": 0.048348106365834004, + "grad_norm": 0.5487808393256164, + "learning_rate": 5e-06, + "loss": 0.4564, + "step": 90 + }, + { + "epoch": 0.05372011818426001, + "grad_norm": 0.5444906907383498, + "learning_rate": 5e-06, + "loss": 0.4466, + "step": 100 + }, + { + "epoch": 0.059092130002686004, + "grad_norm": 0.5101815571273731, + "learning_rate": 5e-06, + "loss": 0.4594, + "step": 110 + }, + { + "epoch": 0.064464141821112, + "grad_norm": 0.5299045266679747, + "learning_rate": 5e-06, + "loss": 0.4608, + "step": 120 + }, + { + "epoch": 0.069836153639538, + "grad_norm": 0.4867455311822639, + "learning_rate": 5e-06, + "loss": 0.4594, + "step": 130 + }, + { + "epoch": 0.07520816545796401, + "grad_norm": 0.5226511293151176, + "learning_rate": 5e-06, + "loss": 0.4537, + "step": 140 + }, + { + "epoch": 0.08058017727639001, + "grad_norm": 0.5413759464697727, + "learning_rate": 5e-06, + "loss": 0.4614, + "step": 150 + }, + { + "epoch": 0.08595218909481601, + "grad_norm": 0.5253819183696734, + "learning_rate": 5e-06, + "loss": 0.4677, + "step": 160 + }, + { + "epoch": 0.091324200913242, + "grad_norm": 0.512774010217095, + "learning_rate": 5e-06, + "loss": 0.4663, + "step": 170 + }, + { + "epoch": 0.09669621273166801, + "grad_norm": 0.5161443496807266, + "learning_rate": 5e-06, + "loss": 0.4445, + "step": 180 + }, + { + "epoch": 0.10206822455009401, + "grad_norm": 0.53161510586257, + "learning_rate": 5e-06, + "loss": 0.4386, + "step": 190 + }, + { + "epoch": 0.10744023636852001, + "grad_norm": 0.5033874795161914, + "learning_rate": 5e-06, + "loss": 0.4358, + "step": 200 + }, + { + "epoch": 0.11281224818694602, + "grad_norm": 0.5030823104996639, + "learning_rate": 5e-06, + "loss": 0.4509, + "step": 210 + }, + { + "epoch": 0.11818426000537201, + "grad_norm": 0.4921742024096051, + "learning_rate": 5e-06, + "loss": 0.454, + "step": 220 + }, + { + "epoch": 0.12355627182379801, + "grad_norm": 0.5151849417876855, + "learning_rate": 5e-06, + "loss": 0.4402, + "step": 230 + }, + { + "epoch": 0.128928283642224, + "grad_norm": 0.5509880033121557, + "learning_rate": 5e-06, + "loss": 0.4492, + "step": 240 + }, + { + "epoch": 0.13430029546065, + "grad_norm": 0.4657702949495027, + "learning_rate": 5e-06, + "loss": 0.4525, + "step": 250 + }, + { + "epoch": 0.139672307279076, + "grad_norm": 0.4907871132824897, + "learning_rate": 5e-06, + "loss": 0.4423, + "step": 260 + }, + { + "epoch": 0.145044319097502, + "grad_norm": 0.5002770016321901, + "learning_rate": 5e-06, + "loss": 0.4454, + "step": 270 + }, + { + "epoch": 0.15041633091592801, + "grad_norm": 0.5189467430778508, + "learning_rate": 5e-06, + "loss": 0.4421, + "step": 280 + }, + { + "epoch": 0.15578834273435402, + "grad_norm": 0.5292508408955507, + "learning_rate": 5e-06, + "loss": 0.4446, + "step": 290 + }, + { + "epoch": 0.16116035455278002, + "grad_norm": 0.49312368458399464, + "learning_rate": 5e-06, + "loss": 0.436, + "step": 300 + }, + { + "epoch": 0.16653236637120603, + "grad_norm": 0.5129893583398213, + "learning_rate": 5e-06, + "loss": 0.4299, + "step": 310 + }, + { + "epoch": 0.17190437818963203, + "grad_norm": 0.5066217704400877, + "learning_rate": 5e-06, + "loss": 0.472, + "step": 320 + }, + { + "epoch": 0.177276390008058, + "grad_norm": 0.523311153155544, + "learning_rate": 5e-06, + "loss": 0.451, + "step": 330 + }, + { + "epoch": 0.182648401826484, + "grad_norm": 0.48044358190446446, + "learning_rate": 5e-06, + "loss": 0.4402, + "step": 340 + }, + { + "epoch": 0.18802041364491, + "grad_norm": 0.5084268017861858, + "learning_rate": 5e-06, + "loss": 0.4427, + "step": 350 + }, + { + "epoch": 0.19339242546333602, + "grad_norm": 0.5590494266460699, + "learning_rate": 5e-06, + "loss": 0.435, + "step": 360 + }, + { + "epoch": 0.19876443728176202, + "grad_norm": 0.5150238173121026, + "learning_rate": 5e-06, + "loss": 0.457, + "step": 370 + }, + { + "epoch": 0.20413644910018802, + "grad_norm": 0.5179681470188343, + "learning_rate": 5e-06, + "loss": 0.4345, + "step": 380 + }, + { + "epoch": 0.20950846091861403, + "grad_norm": 0.4959644692499422, + "learning_rate": 5e-06, + "loss": 0.4653, + "step": 390 + }, + { + "epoch": 0.21488047273704003, + "grad_norm": 0.4887248921897578, + "learning_rate": 5e-06, + "loss": 0.4329, + "step": 400 + }, + { + "epoch": 0.22025248455546603, + "grad_norm": 0.5246025423036973, + "learning_rate": 5e-06, + "loss": 0.4372, + "step": 410 + }, + { + "epoch": 0.22562449637389204, + "grad_norm": 0.5231208256198969, + "learning_rate": 5e-06, + "loss": 0.4483, + "step": 420 + }, + { + "epoch": 0.230996508192318, + "grad_norm": 0.4905322052458498, + "learning_rate": 5e-06, + "loss": 0.4468, + "step": 430 + }, + { + "epoch": 0.23636852001074402, + "grad_norm": 0.4936919209174855, + "learning_rate": 5e-06, + "loss": 0.4233, + "step": 440 + }, + { + "epoch": 0.24174053182917002, + "grad_norm": 0.48253252781988465, + "learning_rate": 5e-06, + "loss": 0.4282, + "step": 450 + }, + { + "epoch": 0.24711254364759602, + "grad_norm": 0.5320793975315983, + "learning_rate": 5e-06, + "loss": 0.438, + "step": 460 + }, + { + "epoch": 0.252484555466022, + "grad_norm": 0.5669630042331335, + "learning_rate": 5e-06, + "loss": 0.4405, + "step": 470 + }, + { + "epoch": 0.257856567284448, + "grad_norm": 0.5087900877086022, + "learning_rate": 5e-06, + "loss": 0.4249, + "step": 480 + }, + { + "epoch": 0.263228579102874, + "grad_norm": 0.5450204053078138, + "learning_rate": 5e-06, + "loss": 0.4444, + "step": 490 + }, + { + "epoch": 0.2686005909213, + "grad_norm": 0.5058928148426334, + "learning_rate": 5e-06, + "loss": 0.4445, + "step": 500 + }, + { + "epoch": 0.273972602739726, + "grad_norm": 0.5051451139496426, + "learning_rate": 5e-06, + "loss": 0.4425, + "step": 510 + }, + { + "epoch": 0.279344614558152, + "grad_norm": 0.5457866711066754, + "learning_rate": 5e-06, + "loss": 0.4389, + "step": 520 + }, + { + "epoch": 0.284716626376578, + "grad_norm": 0.4849183989554118, + "learning_rate": 5e-06, + "loss": 0.4288, + "step": 530 + }, + { + "epoch": 0.290088638195004, + "grad_norm": 0.5051790388747184, + "learning_rate": 5e-06, + "loss": 0.4375, + "step": 540 + }, + { + "epoch": 0.29546065001343, + "grad_norm": 0.5147432880032614, + "learning_rate": 5e-06, + "loss": 0.4318, + "step": 550 + }, + { + "epoch": 0.30083266183185603, + "grad_norm": 0.5151984027160786, + "learning_rate": 5e-06, + "loss": 0.4296, + "step": 560 + }, + { + "epoch": 0.30620467365028203, + "grad_norm": 0.487287573842156, + "learning_rate": 5e-06, + "loss": 0.4335, + "step": 570 + }, + { + "epoch": 0.31157668546870804, + "grad_norm": 0.48311459111349353, + "learning_rate": 5e-06, + "loss": 0.4249, + "step": 580 + }, + { + "epoch": 0.31694869728713404, + "grad_norm": 0.48793456986947, + "learning_rate": 5e-06, + "loss": 0.4284, + "step": 590 + }, + { + "epoch": 0.32232070910556004, + "grad_norm": 0.52641572654466, + "learning_rate": 5e-06, + "loss": 0.4307, + "step": 600 + }, + { + "epoch": 0.32769272092398605, + "grad_norm": 0.4882559371631369, + "learning_rate": 5e-06, + "loss": 0.4263, + "step": 610 + }, + { + "epoch": 0.33306473274241205, + "grad_norm": 0.4840381990603004, + "learning_rate": 5e-06, + "loss": 0.4231, + "step": 620 + }, + { + "epoch": 0.33843674456083805, + "grad_norm": 0.47841166192032697, + "learning_rate": 5e-06, + "loss": 0.4243, + "step": 630 + }, + { + "epoch": 0.34380875637926406, + "grad_norm": 0.4974356233716661, + "learning_rate": 5e-06, + "loss": 0.4219, + "step": 640 + }, + { + "epoch": 0.34918076819769006, + "grad_norm": 0.503552480449389, + "learning_rate": 5e-06, + "loss": 0.4213, + "step": 650 + }, + { + "epoch": 0.354552780016116, + "grad_norm": 0.48878619440735516, + "learning_rate": 5e-06, + "loss": 0.4242, + "step": 660 + }, + { + "epoch": 0.359924791834542, + "grad_norm": 0.4976388993737148, + "learning_rate": 5e-06, + "loss": 0.4134, + "step": 670 + }, + { + "epoch": 0.365296803652968, + "grad_norm": 0.4906593430866946, + "learning_rate": 5e-06, + "loss": 0.4319, + "step": 680 + }, + { + "epoch": 0.370668815471394, + "grad_norm": 0.48689730508962903, + "learning_rate": 5e-06, + "loss": 0.42, + "step": 690 + }, + { + "epoch": 0.37604082728982, + "grad_norm": 0.5087526864688174, + "learning_rate": 5e-06, + "loss": 0.4292, + "step": 700 + }, + { + "epoch": 0.381412839108246, + "grad_norm": 0.4826359097531591, + "learning_rate": 5e-06, + "loss": 0.4309, + "step": 710 + }, + { + "epoch": 0.38678485092667203, + "grad_norm": 0.5168965208054898, + "learning_rate": 5e-06, + "loss": 0.4292, + "step": 720 + }, + { + "epoch": 0.39215686274509803, + "grad_norm": 0.5241584710463651, + "learning_rate": 5e-06, + "loss": 0.426, + "step": 730 + }, + { + "epoch": 0.39752887456352404, + "grad_norm": 0.5037085747835317, + "learning_rate": 5e-06, + "loss": 0.4205, + "step": 740 + }, + { + "epoch": 0.40290088638195004, + "grad_norm": 0.5257737086254655, + "learning_rate": 5e-06, + "loss": 0.4319, + "step": 750 + }, + { + "epoch": 0.40827289820037604, + "grad_norm": 0.5053782439759247, + "learning_rate": 5e-06, + "loss": 0.4341, + "step": 760 + }, + { + "epoch": 0.41364491001880205, + "grad_norm": 0.48695927349136436, + "learning_rate": 5e-06, + "loss": 0.4317, + "step": 770 + }, + { + "epoch": 0.41901692183722805, + "grad_norm": 0.5223324375752193, + "learning_rate": 5e-06, + "loss": 0.4315, + "step": 780 + }, + { + "epoch": 0.42438893365565405, + "grad_norm": 0.48347269165618467, + "learning_rate": 5e-06, + "loss": 0.4213, + "step": 790 + }, + { + "epoch": 0.42976094547408006, + "grad_norm": 0.49513085763985204, + "learning_rate": 5e-06, + "loss": 0.4128, + "step": 800 + }, + { + "epoch": 0.43513295729250606, + "grad_norm": 0.5064390590783957, + "learning_rate": 5e-06, + "loss": 0.4209, + "step": 810 + }, + { + "epoch": 0.44050496911093207, + "grad_norm": 0.47087189867674206, + "learning_rate": 5e-06, + "loss": 0.4178, + "step": 820 + }, + { + "epoch": 0.44587698092935807, + "grad_norm": 0.5037177769830938, + "learning_rate": 5e-06, + "loss": 0.4154, + "step": 830 + }, + { + "epoch": 0.4512489927477841, + "grad_norm": 0.4836652989743429, + "learning_rate": 5e-06, + "loss": 0.4231, + "step": 840 + }, + { + "epoch": 0.45662100456621, + "grad_norm": 0.49268225104535635, + "learning_rate": 5e-06, + "loss": 0.4322, + "step": 850 + }, + { + "epoch": 0.461993016384636, + "grad_norm": 0.5177367203120576, + "learning_rate": 5e-06, + "loss": 0.4148, + "step": 860 + }, + { + "epoch": 0.467365028203062, + "grad_norm": 0.5287712648467915, + "learning_rate": 5e-06, + "loss": 0.4203, + "step": 870 + }, + { + "epoch": 0.47273704002148803, + "grad_norm": 0.5261107946601264, + "learning_rate": 5e-06, + "loss": 0.4167, + "step": 880 + }, + { + "epoch": 0.47810905183991403, + "grad_norm": 0.4771489742949829, + "learning_rate": 5e-06, + "loss": 0.4167, + "step": 890 + }, + { + "epoch": 0.48348106365834004, + "grad_norm": 0.5102018630117343, + "learning_rate": 5e-06, + "loss": 0.4229, + "step": 900 + }, + { + "epoch": 0.48885307547676604, + "grad_norm": 0.4878429347643926, + "learning_rate": 5e-06, + "loss": 0.4183, + "step": 910 + }, + { + "epoch": 0.49422508729519204, + "grad_norm": 0.5144994848348318, + "learning_rate": 5e-06, + "loss": 0.4143, + "step": 920 + }, + { + "epoch": 0.49959709911361805, + "grad_norm": 0.503185719473255, + "learning_rate": 5e-06, + "loss": 0.4233, + "step": 930 + }, + { + "epoch": 0.504969110932044, + "grad_norm": 0.4877537965487305, + "learning_rate": 5e-06, + "loss": 0.4111, + "step": 940 + }, + { + "epoch": 0.51034112275047, + "grad_norm": 0.49337702492530877, + "learning_rate": 5e-06, + "loss": 0.4178, + "step": 950 + }, + { + "epoch": 0.515713134568896, + "grad_norm": 0.5058601662368037, + "learning_rate": 5e-06, + "loss": 0.4202, + "step": 960 + }, + { + "epoch": 0.5210851463873221, + "grad_norm": 0.510997345591431, + "learning_rate": 5e-06, + "loss": 0.4105, + "step": 970 + }, + { + "epoch": 0.526457158205748, + "grad_norm": 0.4859028721289983, + "learning_rate": 5e-06, + "loss": 0.4117, + "step": 980 + }, + { + "epoch": 0.5318291700241741, + "grad_norm": 0.4779893349116978, + "learning_rate": 5e-06, + "loss": 0.4173, + "step": 990 + }, + { + "epoch": 0.5372011818426, + "grad_norm": 0.4764031353354688, + "learning_rate": 5e-06, + "loss": 0.425, + "step": 1000 + }, + { + "epoch": 0.5425731936610261, + "grad_norm": 0.5006562105139756, + "learning_rate": 5e-06, + "loss": 0.4159, + "step": 1010 + }, + { + "epoch": 0.547945205479452, + "grad_norm": 0.5152775958116914, + "learning_rate": 5e-06, + "loss": 0.4188, + "step": 1020 + }, + { + "epoch": 0.5533172172978781, + "grad_norm": 0.5289018387715745, + "learning_rate": 5e-06, + "loss": 0.4139, + "step": 1030 + }, + { + "epoch": 0.558689229116304, + "grad_norm": 0.5011636819261501, + "learning_rate": 5e-06, + "loss": 0.4366, + "step": 1040 + }, + { + "epoch": 0.5640612409347301, + "grad_norm": 0.5231733582695839, + "learning_rate": 5e-06, + "loss": 0.4151, + "step": 1050 + }, + { + "epoch": 0.569433252753156, + "grad_norm": 0.5188191978407911, + "learning_rate": 5e-06, + "loss": 0.4228, + "step": 1060 + }, + { + "epoch": 0.5748052645715821, + "grad_norm": 0.5151903183336549, + "learning_rate": 5e-06, + "loss": 0.415, + "step": 1070 + }, + { + "epoch": 0.580177276390008, + "grad_norm": 0.4813910302235839, + "learning_rate": 5e-06, + "loss": 0.4096, + "step": 1080 + }, + { + "epoch": 0.5855492882084341, + "grad_norm": 0.49401253214817437, + "learning_rate": 5e-06, + "loss": 0.423, + "step": 1090 + }, + { + "epoch": 0.59092130002686, + "grad_norm": 0.47241411535211064, + "learning_rate": 5e-06, + "loss": 0.4269, + "step": 1100 + }, + { + "epoch": 0.5962933118452861, + "grad_norm": 0.5122976717434686, + "learning_rate": 5e-06, + "loss": 0.4118, + "step": 1110 + }, + { + "epoch": 0.6016653236637121, + "grad_norm": 0.4830895458893607, + "learning_rate": 5e-06, + "loss": 0.4045, + "step": 1120 + }, + { + "epoch": 0.607037335482138, + "grad_norm": 0.45858227235019566, + "learning_rate": 5e-06, + "loss": 0.4066, + "step": 1130 + }, + { + "epoch": 0.6124093473005641, + "grad_norm": 0.4930799485366545, + "learning_rate": 5e-06, + "loss": 0.411, + "step": 1140 + }, + { + "epoch": 0.61778135911899, + "grad_norm": 0.552477707583534, + "learning_rate": 5e-06, + "loss": 0.419, + "step": 1150 + }, + { + "epoch": 0.6231533709374161, + "grad_norm": 0.5513588473268155, + "learning_rate": 5e-06, + "loss": 0.4245, + "step": 1160 + }, + { + "epoch": 0.628525382755842, + "grad_norm": 0.4959903508276244, + "learning_rate": 5e-06, + "loss": 0.4283, + "step": 1170 + }, + { + "epoch": 0.6338973945742681, + "grad_norm": 0.49870079552977137, + "learning_rate": 5e-06, + "loss": 0.4125, + "step": 1180 + }, + { + "epoch": 0.639269406392694, + "grad_norm": 0.5203331550271634, + "learning_rate": 5e-06, + "loss": 0.4146, + "step": 1190 + }, + { + "epoch": 0.6446414182111201, + "grad_norm": 0.5159373689413201, + "learning_rate": 5e-06, + "loss": 0.4164, + "step": 1200 + }, + { + "epoch": 0.650013430029546, + "grad_norm": 0.48339146055972076, + "learning_rate": 5e-06, + "loss": 0.4174, + "step": 1210 + }, + { + "epoch": 0.6553854418479721, + "grad_norm": 0.47997830375508066, + "learning_rate": 5e-06, + "loss": 0.4214, + "step": 1220 + }, + { + "epoch": 0.660757453666398, + "grad_norm": 0.49306877946793926, + "learning_rate": 5e-06, + "loss": 0.4063, + "step": 1230 + }, + { + "epoch": 0.6661294654848241, + "grad_norm": 0.4688085012843865, + "learning_rate": 5e-06, + "loss": 0.4194, + "step": 1240 + }, + { + "epoch": 0.67150147730325, + "grad_norm": 0.5065404141632286, + "learning_rate": 5e-06, + "loss": 0.4174, + "step": 1250 + }, + { + "epoch": 0.6768734891216761, + "grad_norm": 0.4737642817754586, + "learning_rate": 5e-06, + "loss": 0.4088, + "step": 1260 + }, + { + "epoch": 0.6822455009401021, + "grad_norm": 0.4810016610698945, + "learning_rate": 5e-06, + "loss": 0.4239, + "step": 1270 + }, + { + "epoch": 0.6876175127585281, + "grad_norm": 0.4808641926976229, + "learning_rate": 5e-06, + "loss": 0.4128, + "step": 1280 + }, + { + "epoch": 0.6929895245769541, + "grad_norm": 0.5075803008791022, + "learning_rate": 5e-06, + "loss": 0.4184, + "step": 1290 + }, + { + "epoch": 0.6983615363953801, + "grad_norm": 0.48462584119976126, + "learning_rate": 5e-06, + "loss": 0.4124, + "step": 1300 + }, + { + "epoch": 0.7037335482138061, + "grad_norm": 0.505895005934085, + "learning_rate": 5e-06, + "loss": 0.4257, + "step": 1310 + }, + { + "epoch": 0.709105560032232, + "grad_norm": 0.48583666914062235, + "learning_rate": 5e-06, + "loss": 0.4098, + "step": 1320 + }, + { + "epoch": 0.7144775718506581, + "grad_norm": 0.4970285423060719, + "learning_rate": 5e-06, + "loss": 0.4089, + "step": 1330 + }, + { + "epoch": 0.719849583669084, + "grad_norm": 0.49766486891278666, + "learning_rate": 5e-06, + "loss": 0.4088, + "step": 1340 + }, + { + "epoch": 0.7252215954875101, + "grad_norm": 0.4855825885601451, + "learning_rate": 5e-06, + "loss": 0.4025, + "step": 1350 + }, + { + "epoch": 0.730593607305936, + "grad_norm": 0.5029858180262275, + "learning_rate": 5e-06, + "loss": 0.4141, + "step": 1360 + }, + { + "epoch": 0.7359656191243621, + "grad_norm": 0.4974844805071485, + "learning_rate": 5e-06, + "loss": 0.4222, + "step": 1370 + }, + { + "epoch": 0.741337630942788, + "grad_norm": 0.5195759396465923, + "learning_rate": 5e-06, + "loss": 0.4088, + "step": 1380 + }, + { + "epoch": 0.7467096427612141, + "grad_norm": 0.5192006492882316, + "learning_rate": 5e-06, + "loss": 0.4122, + "step": 1390 + }, + { + "epoch": 0.75208165457964, + "grad_norm": 0.48436457791566156, + "learning_rate": 5e-06, + "loss": 0.4318, + "step": 1400 + }, + { + "epoch": 0.7574536663980661, + "grad_norm": 0.5000911567395471, + "learning_rate": 5e-06, + "loss": 0.4097, + "step": 1410 + }, + { + "epoch": 0.762825678216492, + "grad_norm": 0.49274648962111117, + "learning_rate": 5e-06, + "loss": 0.4135, + "step": 1420 + }, + { + "epoch": 0.7681976900349181, + "grad_norm": 0.4979579934605875, + "learning_rate": 5e-06, + "loss": 0.4009, + "step": 1430 + }, + { + "epoch": 0.7735697018533441, + "grad_norm": 0.46471442953412, + "learning_rate": 5e-06, + "loss": 0.4061, + "step": 1440 + }, + { + "epoch": 0.7789417136717701, + "grad_norm": 0.5116814519358561, + "learning_rate": 5e-06, + "loss": 0.4081, + "step": 1450 + }, + { + "epoch": 0.7843137254901961, + "grad_norm": 0.47123618031767167, + "learning_rate": 5e-06, + "loss": 0.411, + "step": 1460 + }, + { + "epoch": 0.7896857373086221, + "grad_norm": 0.5492150909290102, + "learning_rate": 5e-06, + "loss": 0.4107, + "step": 1470 + }, + { + "epoch": 0.7950577491270481, + "grad_norm": 0.49793785975302846, + "learning_rate": 5e-06, + "loss": 0.4068, + "step": 1480 + }, + { + "epoch": 0.8004297609454741, + "grad_norm": 0.4975848694312907, + "learning_rate": 5e-06, + "loss": 0.4118, + "step": 1490 + }, + { + "epoch": 0.8058017727639001, + "grad_norm": 0.5613329259556228, + "learning_rate": 5e-06, + "loss": 0.4053, + "step": 1500 + }, + { + "epoch": 0.811173784582326, + "grad_norm": 0.49862206188730673, + "learning_rate": 5e-06, + "loss": 0.4085, + "step": 1510 + }, + { + "epoch": 0.8165457964007521, + "grad_norm": 0.5114041258349515, + "learning_rate": 5e-06, + "loss": 0.4127, + "step": 1520 + }, + { + "epoch": 0.821917808219178, + "grad_norm": 0.4789962956827193, + "learning_rate": 5e-06, + "loss": 0.4194, + "step": 1530 + }, + { + "epoch": 0.8272898200376041, + "grad_norm": 0.540275990173432, + "learning_rate": 5e-06, + "loss": 0.4226, + "step": 1540 + }, + { + "epoch": 0.83266183185603, + "grad_norm": 0.5180207397875711, + "learning_rate": 5e-06, + "loss": 0.4099, + "step": 1550 + }, + { + "epoch": 0.8380338436744561, + "grad_norm": 0.4847352059935786, + "learning_rate": 5e-06, + "loss": 0.4083, + "step": 1560 + }, + { + "epoch": 0.843405855492882, + "grad_norm": 0.5611357081200975, + "learning_rate": 5e-06, + "loss": 0.4054, + "step": 1570 + }, + { + "epoch": 0.8487778673113081, + "grad_norm": 0.527298877110818, + "learning_rate": 5e-06, + "loss": 0.4187, + "step": 1580 + }, + { + "epoch": 0.8541498791297341, + "grad_norm": 0.5160056675790338, + "learning_rate": 5e-06, + "loss": 0.4085, + "step": 1590 + }, + { + "epoch": 0.8595218909481601, + "grad_norm": 0.4979226916104278, + "learning_rate": 5e-06, + "loss": 0.4086, + "step": 1600 + }, + { + "epoch": 0.8648939027665861, + "grad_norm": 0.48561293825487145, + "learning_rate": 5e-06, + "loss": 0.4048, + "step": 1610 + }, + { + "epoch": 0.8702659145850121, + "grad_norm": 0.5264507223222344, + "learning_rate": 5e-06, + "loss": 0.4025, + "step": 1620 + }, + { + "epoch": 0.8756379264034381, + "grad_norm": 0.45827475378643506, + "learning_rate": 5e-06, + "loss": 0.4107, + "step": 1630 + }, + { + "epoch": 0.8810099382218641, + "grad_norm": 0.4598952847745578, + "learning_rate": 5e-06, + "loss": 0.4114, + "step": 1640 + }, + { + "epoch": 0.8863819500402901, + "grad_norm": 0.4897282955229834, + "learning_rate": 5e-06, + "loss": 0.4088, + "step": 1650 + }, + { + "epoch": 0.8917539618587161, + "grad_norm": 0.5208215132708872, + "learning_rate": 5e-06, + "loss": 0.3976, + "step": 1660 + }, + { + "epoch": 0.8971259736771421, + "grad_norm": 0.4798522944815239, + "learning_rate": 5e-06, + "loss": 0.4153, + "step": 1670 + }, + { + "epoch": 0.9024979854955681, + "grad_norm": 0.4860389540678452, + "learning_rate": 5e-06, + "loss": 0.4192, + "step": 1680 + }, + { + "epoch": 0.9078699973139941, + "grad_norm": 0.46106648686259355, + "learning_rate": 5e-06, + "loss": 0.4226, + "step": 1690 + }, + { + "epoch": 0.91324200913242, + "grad_norm": 0.49535127626693193, + "learning_rate": 5e-06, + "loss": 0.404, + "step": 1700 + }, + { + "epoch": 0.9186140209508461, + "grad_norm": 0.4543561154266515, + "learning_rate": 5e-06, + "loss": 0.4126, + "step": 1710 + }, + { + "epoch": 0.923986032769272, + "grad_norm": 0.5200028022866499, + "learning_rate": 5e-06, + "loss": 0.4072, + "step": 1720 + }, + { + "epoch": 0.9293580445876981, + "grad_norm": 0.5114668126414205, + "learning_rate": 5e-06, + "loss": 0.4037, + "step": 1730 + }, + { + "epoch": 0.934730056406124, + "grad_norm": 0.5165691248841157, + "learning_rate": 5e-06, + "loss": 0.4129, + "step": 1740 + }, + { + "epoch": 0.9401020682245501, + "grad_norm": 0.5191922236594055, + "learning_rate": 5e-06, + "loss": 0.4089, + "step": 1750 + }, + { + "epoch": 0.9454740800429761, + "grad_norm": 0.48259570729073553, + "learning_rate": 5e-06, + "loss": 0.4031, + "step": 1760 + }, + { + "epoch": 0.9508460918614021, + "grad_norm": 0.518843327631672, + "learning_rate": 5e-06, + "loss": 0.398, + "step": 1770 + }, + { + "epoch": 0.9562181036798281, + "grad_norm": 0.5364105770372746, + "learning_rate": 5e-06, + "loss": 0.3988, + "step": 1780 + }, + { + "epoch": 0.9615901154982541, + "grad_norm": 0.5020255273268895, + "learning_rate": 5e-06, + "loss": 0.4076, + "step": 1790 + }, + { + "epoch": 0.9669621273166801, + "grad_norm": 0.5073523384433892, + "learning_rate": 5e-06, + "loss": 0.4061, + "step": 1800 + }, + { + "epoch": 0.9723341391351061, + "grad_norm": 0.4727913677316271, + "learning_rate": 5e-06, + "loss": 0.4014, + "step": 1810 + }, + { + "epoch": 0.9777061509535321, + "grad_norm": 0.5050437658596597, + "learning_rate": 5e-06, + "loss": 0.4166, + "step": 1820 + }, + { + "epoch": 0.9830781627719581, + "grad_norm": 0.4907596747431724, + "learning_rate": 5e-06, + "loss": 0.4177, + "step": 1830 + }, + { + "epoch": 0.9884501745903841, + "grad_norm": 0.4688237071483825, + "learning_rate": 5e-06, + "loss": 0.402, + "step": 1840 + }, + { + "epoch": 0.9938221864088101, + "grad_norm": 0.4643104668565543, + "learning_rate": 5e-06, + "loss": 0.4026, + "step": 1850 + }, + { + "epoch": 0.9991941982272361, + "grad_norm": 0.49500486010624006, + "learning_rate": 5e-06, + "loss": 0.4024, + "step": 1860 + }, + { + "epoch": 0.9997313994090787, + "eval_loss": 0.4042987525463104, + "eval_runtime": 471.547, + "eval_samples_per_second": 26.593, + "eval_steps_per_second": 0.416, + "step": 1861 + }, + { + "epoch": 1.004566210045662, + "grad_norm": 0.4895276245416368, + "learning_rate": 5e-06, + "loss": 0.3782, + "step": 1870 + }, + { + "epoch": 1.009938221864088, + "grad_norm": 0.4763690228214777, + "learning_rate": 5e-06, + "loss": 0.3515, + "step": 1880 + }, + { + "epoch": 1.0153102336825142, + "grad_norm": 0.478887231667028, + "learning_rate": 5e-06, + "loss": 0.3602, + "step": 1890 + }, + { + "epoch": 1.02068224550094, + "grad_norm": 0.4406116481047118, + "learning_rate": 5e-06, + "loss": 0.3583, + "step": 1900 + }, + { + "epoch": 1.026054257319366, + "grad_norm": 0.45230055522726487, + "learning_rate": 5e-06, + "loss": 0.3428, + "step": 1910 + }, + { + "epoch": 1.031426269137792, + "grad_norm": 0.47360183462868854, + "learning_rate": 5e-06, + "loss": 0.3615, + "step": 1920 + }, + { + "epoch": 1.0367982809562182, + "grad_norm": 0.4565501019154625, + "learning_rate": 5e-06, + "loss": 0.3629, + "step": 1930 + }, + { + "epoch": 1.0421702927746441, + "grad_norm": 0.4980427239755443, + "learning_rate": 5e-06, + "loss": 0.3695, + "step": 1940 + }, + { + "epoch": 1.04754230459307, + "grad_norm": 0.48230806698810685, + "learning_rate": 5e-06, + "loss": 0.3434, + "step": 1950 + }, + { + "epoch": 1.052914316411496, + "grad_norm": 0.470470012779878, + "learning_rate": 5e-06, + "loss": 0.3509, + "step": 1960 + }, + { + "epoch": 1.0582863282299222, + "grad_norm": 0.4479895760634986, + "learning_rate": 5e-06, + "loss": 0.3424, + "step": 1970 + }, + { + "epoch": 1.0636583400483481, + "grad_norm": 0.4719779566218419, + "learning_rate": 5e-06, + "loss": 0.3543, + "step": 1980 + }, + { + "epoch": 1.069030351866774, + "grad_norm": 0.48397615308885894, + "learning_rate": 5e-06, + "loss": 0.3514, + "step": 1990 + }, + { + "epoch": 1.0744023636852, + "grad_norm": 0.43678232465571554, + "learning_rate": 5e-06, + "loss": 0.3441, + "step": 2000 + }, + { + "epoch": 1.0797743755036262, + "grad_norm": 0.44851060997131426, + "learning_rate": 5e-06, + "loss": 0.3519, + "step": 2010 + }, + { + "epoch": 1.0851463873220522, + "grad_norm": 0.4661433912641436, + "learning_rate": 5e-06, + "loss": 0.3501, + "step": 2020 + }, + { + "epoch": 1.090518399140478, + "grad_norm": 0.5116441181752102, + "learning_rate": 5e-06, + "loss": 0.3583, + "step": 2030 + }, + { + "epoch": 1.095890410958904, + "grad_norm": 0.48794994234515765, + "learning_rate": 5e-06, + "loss": 0.3503, + "step": 2040 + }, + { + "epoch": 1.1012624227773302, + "grad_norm": 0.47447458677616894, + "learning_rate": 5e-06, + "loss": 0.3563, + "step": 2050 + }, + { + "epoch": 1.1066344345957562, + "grad_norm": 0.4781262245860992, + "learning_rate": 5e-06, + "loss": 0.3605, + "step": 2060 + }, + { + "epoch": 1.1120064464141821, + "grad_norm": 0.4697691917656968, + "learning_rate": 5e-06, + "loss": 0.3576, + "step": 2070 + }, + { + "epoch": 1.117378458232608, + "grad_norm": 0.4418186659255878, + "learning_rate": 5e-06, + "loss": 0.3581, + "step": 2080 + }, + { + "epoch": 1.122750470051034, + "grad_norm": 0.4525720645706372, + "learning_rate": 5e-06, + "loss": 0.3482, + "step": 2090 + }, + { + "epoch": 1.1281224818694602, + "grad_norm": 0.47164729198556593, + "learning_rate": 5e-06, + "loss": 0.3518, + "step": 2100 + }, + { + "epoch": 1.1334944936878861, + "grad_norm": 0.4780362991120794, + "learning_rate": 5e-06, + "loss": 0.3605, + "step": 2110 + }, + { + "epoch": 1.138866505506312, + "grad_norm": 0.45101508118677897, + "learning_rate": 5e-06, + "loss": 0.3539, + "step": 2120 + }, + { + "epoch": 1.144238517324738, + "grad_norm": 0.46243427496308614, + "learning_rate": 5e-06, + "loss": 0.3471, + "step": 2130 + }, + { + "epoch": 1.1496105291431642, + "grad_norm": 0.45895312831755847, + "learning_rate": 5e-06, + "loss": 0.3494, + "step": 2140 + }, + { + "epoch": 1.1549825409615901, + "grad_norm": 0.46425226076163784, + "learning_rate": 5e-06, + "loss": 0.3426, + "step": 2150 + }, + { + "epoch": 1.160354552780016, + "grad_norm": 0.5051239504730862, + "learning_rate": 5e-06, + "loss": 0.356, + "step": 2160 + }, + { + "epoch": 1.165726564598442, + "grad_norm": 0.4560291857740493, + "learning_rate": 5e-06, + "loss": 0.3436, + "step": 2170 + }, + { + "epoch": 1.1710985764168682, + "grad_norm": 0.46586472412952123, + "learning_rate": 5e-06, + "loss": 0.3554, + "step": 2180 + }, + { + "epoch": 1.1764705882352942, + "grad_norm": 0.47463013503202, + "learning_rate": 5e-06, + "loss": 0.3549, + "step": 2190 + }, + { + "epoch": 1.18184260005372, + "grad_norm": 0.48738878390795715, + "learning_rate": 5e-06, + "loss": 0.3616, + "step": 2200 + }, + { + "epoch": 1.187214611872146, + "grad_norm": 0.48890429518366846, + "learning_rate": 5e-06, + "loss": 0.3456, + "step": 2210 + }, + { + "epoch": 1.192586623690572, + "grad_norm": 0.47045438323568006, + "learning_rate": 5e-06, + "loss": 0.3575, + "step": 2220 + }, + { + "epoch": 1.1979586355089982, + "grad_norm": 0.46643562303520814, + "learning_rate": 5e-06, + "loss": 0.3572, + "step": 2230 + }, + { + "epoch": 1.2033306473274241, + "grad_norm": 0.4711541973427813, + "learning_rate": 5e-06, + "loss": 0.3463, + "step": 2240 + }, + { + "epoch": 1.20870265914585, + "grad_norm": 0.48043545998856163, + "learning_rate": 5e-06, + "loss": 0.3509, + "step": 2250 + }, + { + "epoch": 1.2140746709642762, + "grad_norm": 0.48163337441004483, + "learning_rate": 5e-06, + "loss": 0.3607, + "step": 2260 + }, + { + "epoch": 1.2194466827827022, + "grad_norm": 0.4736587577149829, + "learning_rate": 5e-06, + "loss": 0.3663, + "step": 2270 + }, + { + "epoch": 1.2248186946011281, + "grad_norm": 0.5118805431884204, + "learning_rate": 5e-06, + "loss": 0.3608, + "step": 2280 + }, + { + "epoch": 1.230190706419554, + "grad_norm": 0.48267765503443366, + "learning_rate": 5e-06, + "loss": 0.3574, + "step": 2290 + }, + { + "epoch": 1.23556271823798, + "grad_norm": 0.4487058222257102, + "learning_rate": 5e-06, + "loss": 0.3493, + "step": 2300 + }, + { + "epoch": 1.2409347300564062, + "grad_norm": 0.47007542745542785, + "learning_rate": 5e-06, + "loss": 0.3514, + "step": 2310 + }, + { + "epoch": 1.2463067418748321, + "grad_norm": 0.4757736251978376, + "learning_rate": 5e-06, + "loss": 0.3804, + "step": 2320 + }, + { + "epoch": 1.251678753693258, + "grad_norm": 0.48922728114483144, + "learning_rate": 5e-06, + "loss": 0.3558, + "step": 2330 + }, + { + "epoch": 1.257050765511684, + "grad_norm": 0.4982569914182343, + "learning_rate": 5e-06, + "loss": 0.355, + "step": 2340 + }, + { + "epoch": 1.26242277733011, + "grad_norm": 0.4793876371419449, + "learning_rate": 5e-06, + "loss": 0.3561, + "step": 2350 + }, + { + "epoch": 1.2677947891485362, + "grad_norm": 0.46545152398636225, + "learning_rate": 5e-06, + "loss": 0.3472, + "step": 2360 + }, + { + "epoch": 1.273166800966962, + "grad_norm": 0.4967452966425127, + "learning_rate": 5e-06, + "loss": 0.3523, + "step": 2370 + }, + { + "epoch": 1.278538812785388, + "grad_norm": 0.4771247760513103, + "learning_rate": 5e-06, + "loss": 0.3665, + "step": 2380 + }, + { + "epoch": 1.2839108246038142, + "grad_norm": 0.4958016938945244, + "learning_rate": 5e-06, + "loss": 0.3533, + "step": 2390 + }, + { + "epoch": 1.2892828364222402, + "grad_norm": 0.5105520260750973, + "learning_rate": 5e-06, + "loss": 0.3644, + "step": 2400 + }, + { + "epoch": 1.2946548482406661, + "grad_norm": 0.4536892978464728, + "learning_rate": 5e-06, + "loss": 0.358, + "step": 2410 + }, + { + "epoch": 1.300026860059092, + "grad_norm": 0.46265183496455864, + "learning_rate": 5e-06, + "loss": 0.3718, + "step": 2420 + }, + { + "epoch": 1.305398871877518, + "grad_norm": 0.4625786404713504, + "learning_rate": 5e-06, + "loss": 0.3498, + "step": 2430 + }, + { + "epoch": 1.3107708836959442, + "grad_norm": 0.4487573165277923, + "learning_rate": 5e-06, + "loss": 0.3453, + "step": 2440 + }, + { + "epoch": 1.3161428955143701, + "grad_norm": 0.48228276168484907, + "learning_rate": 5e-06, + "loss": 0.3574, + "step": 2450 + }, + { + "epoch": 1.321514907332796, + "grad_norm": 0.45803164032303556, + "learning_rate": 5e-06, + "loss": 0.3585, + "step": 2460 + }, + { + "epoch": 1.3268869191512223, + "grad_norm": 0.4961528659344489, + "learning_rate": 5e-06, + "loss": 0.3447, + "step": 2470 + }, + { + "epoch": 1.3322589309696482, + "grad_norm": 0.46995905220607553, + "learning_rate": 5e-06, + "loss": 0.3572, + "step": 2480 + }, + { + "epoch": 1.3376309427880742, + "grad_norm": 0.4735815907276366, + "learning_rate": 5e-06, + "loss": 0.3568, + "step": 2490 + }, + { + "epoch": 1.3430029546065, + "grad_norm": 0.45401301977667363, + "learning_rate": 5e-06, + "loss": 0.3557, + "step": 2500 + }, + { + "epoch": 1.348374966424926, + "grad_norm": 0.442403966397837, + "learning_rate": 5e-06, + "loss": 0.3539, + "step": 2510 + }, + { + "epoch": 1.3537469782433522, + "grad_norm": 0.5002564542847203, + "learning_rate": 5e-06, + "loss": 0.3527, + "step": 2520 + }, + { + "epoch": 1.3591189900617782, + "grad_norm": 0.4645813178315932, + "learning_rate": 5e-06, + "loss": 0.3601, + "step": 2530 + }, + { + "epoch": 1.3644910018802041, + "grad_norm": 0.47453517344411733, + "learning_rate": 5e-06, + "loss": 0.3615, + "step": 2540 + }, + { + "epoch": 1.36986301369863, + "grad_norm": 0.4604202509493409, + "learning_rate": 5e-06, + "loss": 0.3529, + "step": 2550 + }, + { + "epoch": 1.375235025517056, + "grad_norm": 0.453130113647468, + "learning_rate": 5e-06, + "loss": 0.3444, + "step": 2560 + }, + { + "epoch": 1.3806070373354822, + "grad_norm": 0.44091309480166135, + "learning_rate": 5e-06, + "loss": 0.3625, + "step": 2570 + }, + { + "epoch": 1.3859790491539081, + "grad_norm": 0.4517474265184944, + "learning_rate": 5e-06, + "loss": 0.3634, + "step": 2580 + }, + { + "epoch": 1.391351060972334, + "grad_norm": 0.4709274208742667, + "learning_rate": 5e-06, + "loss": 0.3576, + "step": 2590 + }, + { + "epoch": 1.3967230727907602, + "grad_norm": 0.45649673901571647, + "learning_rate": 5e-06, + "loss": 0.3552, + "step": 2600 + }, + { + "epoch": 1.4020950846091862, + "grad_norm": 0.4816316434749545, + "learning_rate": 5e-06, + "loss": 0.3674, + "step": 2610 + }, + { + "epoch": 1.4074670964276121, + "grad_norm": 0.4509867756276843, + "learning_rate": 5e-06, + "loss": 0.3627, + "step": 2620 + }, + { + "epoch": 1.412839108246038, + "grad_norm": 0.47322108910920707, + "learning_rate": 5e-06, + "loss": 0.3561, + "step": 2630 + }, + { + "epoch": 1.418211120064464, + "grad_norm": 0.4568009857383218, + "learning_rate": 5e-06, + "loss": 0.3548, + "step": 2640 + }, + { + "epoch": 1.4235831318828902, + "grad_norm": 0.4870747914342431, + "learning_rate": 5e-06, + "loss": 0.365, + "step": 2650 + }, + { + "epoch": 1.4289551437013162, + "grad_norm": 0.4766156244040559, + "learning_rate": 5e-06, + "loss": 0.3612, + "step": 2660 + }, + { + "epoch": 1.434327155519742, + "grad_norm": 0.4741487895978261, + "learning_rate": 5e-06, + "loss": 0.3552, + "step": 2670 + }, + { + "epoch": 1.4396991673381683, + "grad_norm": 0.45805481522590397, + "learning_rate": 5e-06, + "loss": 0.3712, + "step": 2680 + }, + { + "epoch": 1.4450711791565942, + "grad_norm": 0.48703760968615994, + "learning_rate": 5e-06, + "loss": 0.3555, + "step": 2690 + }, + { + "epoch": 1.4504431909750202, + "grad_norm": 0.476047193063988, + "learning_rate": 5e-06, + "loss": 0.3526, + "step": 2700 + }, + { + "epoch": 1.4558152027934461, + "grad_norm": 0.4501144882135316, + "learning_rate": 5e-06, + "loss": 0.3509, + "step": 2710 + }, + { + "epoch": 1.461187214611872, + "grad_norm": 0.4807022793546781, + "learning_rate": 5e-06, + "loss": 0.3587, + "step": 2720 + }, + { + "epoch": 1.4665592264302982, + "grad_norm": 0.4866933520193109, + "learning_rate": 5e-06, + "loss": 0.3541, + "step": 2730 + }, + { + "epoch": 1.4719312382487242, + "grad_norm": 0.4692699336726864, + "learning_rate": 5e-06, + "loss": 0.3562, + "step": 2740 + }, + { + "epoch": 1.4773032500671501, + "grad_norm": 0.47926277815969454, + "learning_rate": 5e-06, + "loss": 0.346, + "step": 2750 + }, + { + "epoch": 1.482675261885576, + "grad_norm": 0.4799455318722434, + "learning_rate": 5e-06, + "loss": 0.3502, + "step": 2760 + }, + { + "epoch": 1.488047273704002, + "grad_norm": 0.46636973311006896, + "learning_rate": 5e-06, + "loss": 0.3508, + "step": 2770 + }, + { + "epoch": 1.4934192855224282, + "grad_norm": 0.45313120266777845, + "learning_rate": 5e-06, + "loss": 0.35, + "step": 2780 + }, + { + "epoch": 1.4987912973408541, + "grad_norm": 0.49984202987539106, + "learning_rate": 5e-06, + "loss": 0.3531, + "step": 2790 + }, + { + "epoch": 1.50416330915928, + "grad_norm": 0.5107078124846389, + "learning_rate": 5e-06, + "loss": 0.3554, + "step": 2800 + }, + { + "epoch": 1.5095353209777063, + "grad_norm": 0.49609121410014656, + "learning_rate": 5e-06, + "loss": 0.3597, + "step": 2810 + }, + { + "epoch": 1.514907332796132, + "grad_norm": 0.44000526898502273, + "learning_rate": 5e-06, + "loss": 0.3488, + "step": 2820 + }, + { + "epoch": 1.5202793446145582, + "grad_norm": 0.48110675970521016, + "learning_rate": 5e-06, + "loss": 0.3571, + "step": 2830 + }, + { + "epoch": 1.525651356432984, + "grad_norm": 0.44724848382400667, + "learning_rate": 5e-06, + "loss": 0.347, + "step": 2840 + }, + { + "epoch": 1.53102336825141, + "grad_norm": 0.4634129922845378, + "learning_rate": 5e-06, + "loss": 0.3636, + "step": 2850 + }, + { + "epoch": 1.5363953800698362, + "grad_norm": 0.4665778548932393, + "learning_rate": 5e-06, + "loss": 0.3589, + "step": 2860 + }, + { + "epoch": 1.5417673918882622, + "grad_norm": 0.48219157934372814, + "learning_rate": 5e-06, + "loss": 0.3448, + "step": 2870 + }, + { + "epoch": 1.5471394037066881, + "grad_norm": 0.47689653413221034, + "learning_rate": 5e-06, + "loss": 0.3568, + "step": 2880 + }, + { + "epoch": 1.5525114155251143, + "grad_norm": 0.4817413690543133, + "learning_rate": 5e-06, + "loss": 0.3554, + "step": 2890 + }, + { + "epoch": 1.55788342734354, + "grad_norm": 0.48101456064388537, + "learning_rate": 5e-06, + "loss": 0.3679, + "step": 2900 + }, + { + "epoch": 1.5632554391619662, + "grad_norm": 0.4610166853876066, + "learning_rate": 5e-06, + "loss": 0.369, + "step": 2910 + }, + { + "epoch": 1.5686274509803921, + "grad_norm": 0.46324728897514716, + "learning_rate": 5e-06, + "loss": 0.3557, + "step": 2920 + }, + { + "epoch": 1.573999462798818, + "grad_norm": 0.4792758625068545, + "learning_rate": 5e-06, + "loss": 0.3564, + "step": 2930 + }, + { + "epoch": 1.5793714746172443, + "grad_norm": 0.4760438491041952, + "learning_rate": 5e-06, + "loss": 0.3516, + "step": 2940 + }, + { + "epoch": 1.5847434864356702, + "grad_norm": 0.4768587833700611, + "learning_rate": 5e-06, + "loss": 0.3736, + "step": 2950 + }, + { + "epoch": 1.5901154982540961, + "grad_norm": 0.4702173398495168, + "learning_rate": 5e-06, + "loss": 0.3588, + "step": 2960 + }, + { + "epoch": 1.5954875100725223, + "grad_norm": 0.5073117917455773, + "learning_rate": 5e-06, + "loss": 0.3576, + "step": 2970 + }, + { + "epoch": 1.600859521890948, + "grad_norm": 0.4735397279022496, + "learning_rate": 5e-06, + "loss": 0.3518, + "step": 2980 + }, + { + "epoch": 1.6062315337093742, + "grad_norm": 0.49501392208596307, + "learning_rate": 5e-06, + "loss": 0.3574, + "step": 2990 + }, + { + "epoch": 1.6116035455278002, + "grad_norm": 0.45154332778333167, + "learning_rate": 5e-06, + "loss": 0.3469, + "step": 3000 + }, + { + "epoch": 1.6169755573462261, + "grad_norm": 0.4821594714198928, + "learning_rate": 5e-06, + "loss": 0.3665, + "step": 3010 + }, + { + "epoch": 1.6223475691646523, + "grad_norm": 0.4834902526253989, + "learning_rate": 5e-06, + "loss": 0.3627, + "step": 3020 + }, + { + "epoch": 1.627719580983078, + "grad_norm": 0.5010431988707854, + "learning_rate": 5e-06, + "loss": 0.3481, + "step": 3030 + }, + { + "epoch": 1.6330915928015042, + "grad_norm": 0.4842957701772517, + "learning_rate": 5e-06, + "loss": 0.3494, + "step": 3040 + }, + { + "epoch": 1.6384636046199301, + "grad_norm": 0.42862130200724274, + "learning_rate": 5e-06, + "loss": 0.3477, + "step": 3050 + }, + { + "epoch": 1.643835616438356, + "grad_norm": 0.45715763363239004, + "learning_rate": 5e-06, + "loss": 0.3605, + "step": 3060 + }, + { + "epoch": 1.6492076282567822, + "grad_norm": 0.48270644830974097, + "learning_rate": 5e-06, + "loss": 0.3552, + "step": 3070 + }, + { + "epoch": 1.6545796400752082, + "grad_norm": 0.48420910087305813, + "learning_rate": 5e-06, + "loss": 0.357, + "step": 3080 + }, + { + "epoch": 1.6599516518936341, + "grad_norm": 0.4633746055111087, + "learning_rate": 5e-06, + "loss": 0.3481, + "step": 3090 + }, + { + "epoch": 1.6653236637120603, + "grad_norm": 0.46936521480607657, + "learning_rate": 5e-06, + "loss": 0.3455, + "step": 3100 + }, + { + "epoch": 1.670695675530486, + "grad_norm": 0.46328974064931927, + "learning_rate": 5e-06, + "loss": 0.3539, + "step": 3110 + }, + { + "epoch": 1.6760676873489122, + "grad_norm": 0.4649283617312367, + "learning_rate": 5e-06, + "loss": 0.3589, + "step": 3120 + }, + { + "epoch": 1.6814396991673382, + "grad_norm": 0.4703978382827451, + "learning_rate": 5e-06, + "loss": 0.3436, + "step": 3130 + }, + { + "epoch": 1.686811710985764, + "grad_norm": 0.47847168406654755, + "learning_rate": 5e-06, + "loss": 0.37, + "step": 3140 + }, + { + "epoch": 1.6921837228041903, + "grad_norm": 0.4778436891961714, + "learning_rate": 5e-06, + "loss": 0.3488, + "step": 3150 + }, + { + "epoch": 1.6975557346226162, + "grad_norm": 0.44977599188705814, + "learning_rate": 5e-06, + "loss": 0.3571, + "step": 3160 + }, + { + "epoch": 1.7029277464410422, + "grad_norm": 0.5011217127797689, + "learning_rate": 5e-06, + "loss": 0.3524, + "step": 3170 + }, + { + "epoch": 1.7082997582594683, + "grad_norm": 0.4686231916011371, + "learning_rate": 5e-06, + "loss": 0.352, + "step": 3180 + }, + { + "epoch": 1.713671770077894, + "grad_norm": 0.4567419474384379, + "learning_rate": 5e-06, + "loss": 0.3446, + "step": 3190 + }, + { + "epoch": 1.7190437818963202, + "grad_norm": 0.4920146270483708, + "learning_rate": 5e-06, + "loss": 0.3453, + "step": 3200 + }, + { + "epoch": 1.7244157937147462, + "grad_norm": 0.4714208322948418, + "learning_rate": 5e-06, + "loss": 0.3592, + "step": 3210 + }, + { + "epoch": 1.7297878055331721, + "grad_norm": 0.5151502729310895, + "learning_rate": 5e-06, + "loss": 0.3621, + "step": 3220 + }, + { + "epoch": 1.7351598173515983, + "grad_norm": 0.47377609015255395, + "learning_rate": 5e-06, + "loss": 0.3521, + "step": 3230 + }, + { + "epoch": 1.740531829170024, + "grad_norm": 0.4896598896220437, + "learning_rate": 5e-06, + "loss": 0.3556, + "step": 3240 + }, + { + "epoch": 1.7459038409884502, + "grad_norm": 0.4626924876759191, + "learning_rate": 5e-06, + "loss": 0.3624, + "step": 3250 + }, + { + "epoch": 1.7512758528068761, + "grad_norm": 0.4893799058510227, + "learning_rate": 5e-06, + "loss": 0.355, + "step": 3260 + }, + { + "epoch": 1.756647864625302, + "grad_norm": 0.4732147945130505, + "learning_rate": 5e-06, + "loss": 0.3584, + "step": 3270 + }, + { + "epoch": 1.7620198764437283, + "grad_norm": 0.46485063144719596, + "learning_rate": 5e-06, + "loss": 0.3562, + "step": 3280 + }, + { + "epoch": 1.7673918882621542, + "grad_norm": 0.49823480469474907, + "learning_rate": 5e-06, + "loss": 0.3596, + "step": 3290 + }, + { + "epoch": 1.7727639000805802, + "grad_norm": 0.46620308535633026, + "learning_rate": 5e-06, + "loss": 0.3492, + "step": 3300 + }, + { + "epoch": 1.7781359118990063, + "grad_norm": 0.47634133927314953, + "learning_rate": 5e-06, + "loss": 0.3445, + "step": 3310 + }, + { + "epoch": 1.783507923717432, + "grad_norm": 0.4668848160515941, + "learning_rate": 5e-06, + "loss": 0.3571, + "step": 3320 + }, + { + "epoch": 1.7888799355358582, + "grad_norm": 0.4585027323046419, + "learning_rate": 5e-06, + "loss": 0.3552, + "step": 3330 + }, + { + "epoch": 1.7942519473542842, + "grad_norm": 0.5084050187589441, + "learning_rate": 5e-06, + "loss": 0.3595, + "step": 3340 + }, + { + "epoch": 1.7996239591727101, + "grad_norm": 0.4653354008421696, + "learning_rate": 5e-06, + "loss": 0.3513, + "step": 3350 + }, + { + "epoch": 1.8049959709911363, + "grad_norm": 0.4856936785111354, + "learning_rate": 5e-06, + "loss": 0.3584, + "step": 3360 + }, + { + "epoch": 1.810367982809562, + "grad_norm": 0.4595385848192909, + "learning_rate": 5e-06, + "loss": 0.3691, + "step": 3370 + }, + { + "epoch": 1.8157399946279882, + "grad_norm": 0.5004383593079554, + "learning_rate": 5e-06, + "loss": 0.3582, + "step": 3380 + }, + { + "epoch": 1.8211120064464141, + "grad_norm": 0.4854729302325183, + "learning_rate": 5e-06, + "loss": 0.3469, + "step": 3390 + }, + { + "epoch": 1.82648401826484, + "grad_norm": 0.4643207432920559, + "learning_rate": 5e-06, + "loss": 0.3593, + "step": 3400 + }, + { + "epoch": 1.8318560300832663, + "grad_norm": 0.4665815903863702, + "learning_rate": 5e-06, + "loss": 0.3531, + "step": 3410 + }, + { + "epoch": 1.8372280419016922, + "grad_norm": 0.48774803768728303, + "learning_rate": 5e-06, + "loss": 0.3512, + "step": 3420 + }, + { + "epoch": 1.8426000537201181, + "grad_norm": 0.4709529294030036, + "learning_rate": 5e-06, + "loss": 0.3535, + "step": 3430 + }, + { + "epoch": 1.8479720655385443, + "grad_norm": 0.46736498303364754, + "learning_rate": 5e-06, + "loss": 0.3646, + "step": 3440 + }, + { + "epoch": 1.85334407735697, + "grad_norm": 0.488258930586327, + "learning_rate": 5e-06, + "loss": 0.3521, + "step": 3450 + }, + { + "epoch": 1.8587160891753962, + "grad_norm": 0.4700766855772819, + "learning_rate": 5e-06, + "loss": 0.3453, + "step": 3460 + }, + { + "epoch": 1.8640881009938222, + "grad_norm": 0.46996238530410667, + "learning_rate": 5e-06, + "loss": 0.3642, + "step": 3470 + }, + { + "epoch": 1.869460112812248, + "grad_norm": 0.4254367637586878, + "learning_rate": 5e-06, + "loss": 0.3573, + "step": 3480 + }, + { + "epoch": 1.8748321246306743, + "grad_norm": 0.4908636458552527, + "learning_rate": 5e-06, + "loss": 0.3638, + "step": 3490 + }, + { + "epoch": 1.8802041364491002, + "grad_norm": 0.4801639417628621, + "learning_rate": 5e-06, + "loss": 0.3497, + "step": 3500 + }, + { + "epoch": 1.8855761482675262, + "grad_norm": 0.45396361000408497, + "learning_rate": 5e-06, + "loss": 0.357, + "step": 3510 + }, + { + "epoch": 1.8909481600859523, + "grad_norm": 0.4632915688904155, + "learning_rate": 5e-06, + "loss": 0.3583, + "step": 3520 + }, + { + "epoch": 1.896320171904378, + "grad_norm": 0.491440659929986, + "learning_rate": 5e-06, + "loss": 0.3492, + "step": 3530 + }, + { + "epoch": 1.9016921837228042, + "grad_norm": 0.4891492614008297, + "learning_rate": 5e-06, + "loss": 0.3526, + "step": 3540 + }, + { + "epoch": 1.9070641955412302, + "grad_norm": 0.5171252758216774, + "learning_rate": 5e-06, + "loss": 0.3631, + "step": 3550 + }, + { + "epoch": 1.9124362073596561, + "grad_norm": 0.4461868765641311, + "learning_rate": 5e-06, + "loss": 0.3523, + "step": 3560 + }, + { + "epoch": 1.9178082191780823, + "grad_norm": 0.48770468521805, + "learning_rate": 5e-06, + "loss": 0.3594, + "step": 3570 + }, + { + "epoch": 1.923180230996508, + "grad_norm": 0.5105974923297489, + "learning_rate": 5e-06, + "loss": 0.3554, + "step": 3580 + }, + { + "epoch": 1.9285522428149342, + "grad_norm": 0.4457466990354959, + "learning_rate": 5e-06, + "loss": 0.3507, + "step": 3590 + }, + { + "epoch": 1.9339242546333602, + "grad_norm": 0.47606633626915407, + "learning_rate": 5e-06, + "loss": 0.3694, + "step": 3600 + }, + { + "epoch": 1.939296266451786, + "grad_norm": 0.4484067546170701, + "learning_rate": 5e-06, + "loss": 0.3629, + "step": 3610 + }, + { + "epoch": 1.9446682782702123, + "grad_norm": 0.461791387706203, + "learning_rate": 5e-06, + "loss": 0.3526, + "step": 3620 + }, + { + "epoch": 1.9500402900886382, + "grad_norm": 0.44496474942160236, + "learning_rate": 5e-06, + "loss": 0.3401, + "step": 3630 + }, + { + "epoch": 1.9554123019070642, + "grad_norm": 0.5163785217403414, + "learning_rate": 5e-06, + "loss": 0.342, + "step": 3640 + }, + { + "epoch": 1.9607843137254903, + "grad_norm": 0.47380717094158326, + "learning_rate": 5e-06, + "loss": 0.3543, + "step": 3650 + }, + { + "epoch": 1.966156325543916, + "grad_norm": 0.46954718282044644, + "learning_rate": 5e-06, + "loss": 0.3705, + "step": 3660 + }, + { + "epoch": 1.9715283373623422, + "grad_norm": 0.4906972194683541, + "learning_rate": 5e-06, + "loss": 0.355, + "step": 3670 + }, + { + "epoch": 1.9769003491807682, + "grad_norm": 0.4665996203057171, + "learning_rate": 5e-06, + "loss": 0.3546, + "step": 3680 + }, + { + "epoch": 1.9822723609991941, + "grad_norm": 0.4511962208632972, + "learning_rate": 5e-06, + "loss": 0.3518, + "step": 3690 + }, + { + "epoch": 1.9876443728176203, + "grad_norm": 0.5129655066415513, + "learning_rate": 5e-06, + "loss": 0.3664, + "step": 3700 + }, + { + "epoch": 1.9930163846360462, + "grad_norm": 0.4858845690258609, + "learning_rate": 5e-06, + "loss": 0.3609, + "step": 3710 + }, + { + "epoch": 1.9983883964544722, + "grad_norm": 0.4870693370290478, + "learning_rate": 5e-06, + "loss": 0.3514, + "step": 3720 + }, + { + "epoch": 2.0, + "eval_loss": 0.39740535616874695, + "eval_runtime": 468.5266, + "eval_samples_per_second": 26.765, + "eval_steps_per_second": 0.418, + "step": 3723 + }, + { + "epoch": 2.0037604082728984, + "grad_norm": 0.5148318273487177, + "learning_rate": 5e-06, + "loss": 0.3332, + "step": 3730 + }, + { + "epoch": 2.009132420091324, + "grad_norm": 0.44757575228737206, + "learning_rate": 5e-06, + "loss": 0.3166, + "step": 3740 + }, + { + "epoch": 2.0145044319097503, + "grad_norm": 0.49417525446020677, + "learning_rate": 5e-06, + "loss": 0.2932, + "step": 3750 + }, + { + "epoch": 2.019876443728176, + "grad_norm": 0.45003732267652785, + "learning_rate": 5e-06, + "loss": 0.2966, + "step": 3760 + }, + { + "epoch": 2.025248455546602, + "grad_norm": 0.4446601372854061, + "learning_rate": 5e-06, + "loss": 0.3013, + "step": 3770 + }, + { + "epoch": 2.0306204673650283, + "grad_norm": 0.4520286680577658, + "learning_rate": 5e-06, + "loss": 0.287, + "step": 3780 + }, + { + "epoch": 2.035992479183454, + "grad_norm": 0.45274387988815035, + "learning_rate": 5e-06, + "loss": 0.301, + "step": 3790 + }, + { + "epoch": 2.04136449100188, + "grad_norm": 0.47200858969384085, + "learning_rate": 5e-06, + "loss": 0.2955, + "step": 3800 + }, + { + "epoch": 2.0467365028203064, + "grad_norm": 0.44150919063824945, + "learning_rate": 5e-06, + "loss": 0.2935, + "step": 3810 + }, + { + "epoch": 2.052108514638732, + "grad_norm": 0.4724986754383593, + "learning_rate": 5e-06, + "loss": 0.3013, + "step": 3820 + }, + { + "epoch": 2.0574805264571583, + "grad_norm": 0.4658048986243489, + "learning_rate": 5e-06, + "loss": 0.3082, + "step": 3830 + }, + { + "epoch": 2.062852538275584, + "grad_norm": 0.4311596560424912, + "learning_rate": 5e-06, + "loss": 0.2919, + "step": 3840 + }, + { + "epoch": 2.06822455009401, + "grad_norm": 0.4755135160095483, + "learning_rate": 5e-06, + "loss": 0.3087, + "step": 3850 + }, + { + "epoch": 2.0735965619124364, + "grad_norm": 0.4651593055702794, + "learning_rate": 5e-06, + "loss": 0.3031, + "step": 3860 + }, + { + "epoch": 2.078968573730862, + "grad_norm": 0.44604165006256646, + "learning_rate": 5e-06, + "loss": 0.2934, + "step": 3870 + }, + { + "epoch": 2.0843405855492882, + "grad_norm": 0.47944778982671077, + "learning_rate": 5e-06, + "loss": 0.302, + "step": 3880 + }, + { + "epoch": 2.0897125973677144, + "grad_norm": 0.45900387672803933, + "learning_rate": 5e-06, + "loss": 0.295, + "step": 3890 + }, + { + "epoch": 2.09508460918614, + "grad_norm": 0.4390114277911646, + "learning_rate": 5e-06, + "loss": 0.2952, + "step": 3900 + }, + { + "epoch": 2.1004566210045663, + "grad_norm": 0.46198748965614295, + "learning_rate": 5e-06, + "loss": 0.2961, + "step": 3910 + }, + { + "epoch": 2.105828632822992, + "grad_norm": 0.46567184763785124, + "learning_rate": 5e-06, + "loss": 0.3072, + "step": 3920 + }, + { + "epoch": 2.111200644641418, + "grad_norm": 0.4605817205911234, + "learning_rate": 5e-06, + "loss": 0.2989, + "step": 3930 + }, + { + "epoch": 2.1165726564598444, + "grad_norm": 0.4659945936319118, + "learning_rate": 5e-06, + "loss": 0.3057, + "step": 3940 + }, + { + "epoch": 2.12194466827827, + "grad_norm": 0.4698714737543665, + "learning_rate": 5e-06, + "loss": 0.2945, + "step": 3950 + }, + { + "epoch": 2.1273166800966963, + "grad_norm": 0.4603923117486592, + "learning_rate": 5e-06, + "loss": 0.2972, + "step": 3960 + }, + { + "epoch": 2.1326886919151224, + "grad_norm": 0.4444434238101049, + "learning_rate": 5e-06, + "loss": 0.2931, + "step": 3970 + }, + { + "epoch": 2.138060703733548, + "grad_norm": 0.46375448199682273, + "learning_rate": 5e-06, + "loss": 0.289, + "step": 3980 + }, + { + "epoch": 2.1434327155519743, + "grad_norm": 0.4515353697839556, + "learning_rate": 5e-06, + "loss": 0.2981, + "step": 3990 + }, + { + "epoch": 2.1488047273704, + "grad_norm": 0.45865800213441305, + "learning_rate": 5e-06, + "loss": 0.2946, + "step": 4000 + }, + { + "epoch": 2.1541767391888262, + "grad_norm": 0.47415589821389625, + "learning_rate": 5e-06, + "loss": 0.2963, + "step": 4010 + }, + { + "epoch": 2.1595487510072524, + "grad_norm": 0.45650337082160813, + "learning_rate": 5e-06, + "loss": 0.2965, + "step": 4020 + }, + { + "epoch": 2.164920762825678, + "grad_norm": 0.5007055892618506, + "learning_rate": 5e-06, + "loss": 0.3075, + "step": 4030 + }, + { + "epoch": 2.1702927746441043, + "grad_norm": 0.4633408694498252, + "learning_rate": 5e-06, + "loss": 0.3034, + "step": 4040 + }, + { + "epoch": 2.17566478646253, + "grad_norm": 0.47949376553994594, + "learning_rate": 5e-06, + "loss": 0.2959, + "step": 4050 + }, + { + "epoch": 2.181036798280956, + "grad_norm": 0.4534552216810433, + "learning_rate": 5e-06, + "loss": 0.2927, + "step": 4060 + }, + { + "epoch": 2.1864088100993824, + "grad_norm": 0.45779290627720376, + "learning_rate": 5e-06, + "loss": 0.3002, + "step": 4070 + }, + { + "epoch": 2.191780821917808, + "grad_norm": 0.45467471253139063, + "learning_rate": 5e-06, + "loss": 0.2941, + "step": 4080 + }, + { + "epoch": 2.1971528337362343, + "grad_norm": 0.4909879550475429, + "learning_rate": 5e-06, + "loss": 0.2959, + "step": 4090 + }, + { + "epoch": 2.2025248455546604, + "grad_norm": 0.4564057151231639, + "learning_rate": 5e-06, + "loss": 0.3004, + "step": 4100 + }, + { + "epoch": 2.207896857373086, + "grad_norm": 0.47859377699517, + "learning_rate": 5e-06, + "loss": 0.3006, + "step": 4110 + }, + { + "epoch": 2.2132688691915123, + "grad_norm": 0.46099184457974013, + "learning_rate": 5e-06, + "loss": 0.3043, + "step": 4120 + }, + { + "epoch": 2.218640881009938, + "grad_norm": 0.47055531304375103, + "learning_rate": 5e-06, + "loss": 0.3026, + "step": 4130 + }, + { + "epoch": 2.2240128928283642, + "grad_norm": 0.44859460535001255, + "learning_rate": 5e-06, + "loss": 0.2997, + "step": 4140 + }, + { + "epoch": 2.2293849046467904, + "grad_norm": 0.4523869768759771, + "learning_rate": 5e-06, + "loss": 0.3053, + "step": 4150 + }, + { + "epoch": 2.234756916465216, + "grad_norm": 0.4578556718341696, + "learning_rate": 5e-06, + "loss": 0.2935, + "step": 4160 + }, + { + "epoch": 2.2401289282836423, + "grad_norm": 0.47101805169234406, + "learning_rate": 5e-06, + "loss": 0.2984, + "step": 4170 + }, + { + "epoch": 2.245500940102068, + "grad_norm": 0.4721691371474998, + "learning_rate": 5e-06, + "loss": 0.3002, + "step": 4180 + }, + { + "epoch": 2.250872951920494, + "grad_norm": 0.4637692829174677, + "learning_rate": 5e-06, + "loss": 0.2942, + "step": 4190 + }, + { + "epoch": 2.2562449637389204, + "grad_norm": 0.4388979055074455, + "learning_rate": 5e-06, + "loss": 0.3084, + "step": 4200 + }, + { + "epoch": 2.261616975557346, + "grad_norm": 0.4855595548331312, + "learning_rate": 5e-06, + "loss": 0.3061, + "step": 4210 + }, + { + "epoch": 2.2669889873757723, + "grad_norm": 0.4664870575145768, + "learning_rate": 5e-06, + "loss": 0.3088, + "step": 4220 + }, + { + "epoch": 2.2723609991941984, + "grad_norm": 0.47347375338045333, + "learning_rate": 5e-06, + "loss": 0.2995, + "step": 4230 + }, + { + "epoch": 2.277733011012624, + "grad_norm": 0.7006364769945307, + "learning_rate": 5e-06, + "loss": 0.3008, + "step": 4240 + }, + { + "epoch": 2.2831050228310503, + "grad_norm": 0.45676326104006293, + "learning_rate": 5e-06, + "loss": 0.3144, + "step": 4250 + }, + { + "epoch": 2.288477034649476, + "grad_norm": 0.5036552686895771, + "learning_rate": 5e-06, + "loss": 0.2998, + "step": 4260 + }, + { + "epoch": 2.293849046467902, + "grad_norm": 0.4774908704932932, + "learning_rate": 5e-06, + "loss": 0.2985, + "step": 4270 + }, + { + "epoch": 2.2992210582863284, + "grad_norm": 0.45656706765413957, + "learning_rate": 5e-06, + "loss": 0.3005, + "step": 4280 + }, + { + "epoch": 2.304593070104754, + "grad_norm": 0.48161005420123015, + "learning_rate": 5e-06, + "loss": 0.2885, + "step": 4290 + }, + { + "epoch": 2.3099650819231803, + "grad_norm": 0.4539357790250988, + "learning_rate": 5e-06, + "loss": 0.3021, + "step": 4300 + }, + { + "epoch": 2.315337093741606, + "grad_norm": 0.4611459009005326, + "learning_rate": 5e-06, + "loss": 0.2969, + "step": 4310 + }, + { + "epoch": 2.320709105560032, + "grad_norm": 0.4618940592079481, + "learning_rate": 5e-06, + "loss": 0.3074, + "step": 4320 + }, + { + "epoch": 2.3260811173784584, + "grad_norm": 0.4816712055656272, + "learning_rate": 5e-06, + "loss": 0.2983, + "step": 4330 + }, + { + "epoch": 2.331453129196884, + "grad_norm": 0.4813233228122113, + "learning_rate": 5e-06, + "loss": 0.3045, + "step": 4340 + }, + { + "epoch": 2.3368251410153102, + "grad_norm": 0.47887192506303755, + "learning_rate": 5e-06, + "loss": 0.307, + "step": 4350 + }, + { + "epoch": 2.3421971528337364, + "grad_norm": 0.47464931229510837, + "learning_rate": 5e-06, + "loss": 0.3021, + "step": 4360 + }, + { + "epoch": 2.347569164652162, + "grad_norm": 0.4660602871711936, + "learning_rate": 5e-06, + "loss": 0.304, + "step": 4370 + }, + { + "epoch": 2.3529411764705883, + "grad_norm": 0.4880517674465139, + "learning_rate": 5e-06, + "loss": 0.3013, + "step": 4380 + }, + { + "epoch": 2.3583131882890145, + "grad_norm": 0.49041029407882114, + "learning_rate": 5e-06, + "loss": 0.2961, + "step": 4390 + }, + { + "epoch": 2.36368520010744, + "grad_norm": 0.4662688978117843, + "learning_rate": 5e-06, + "loss": 0.3007, + "step": 4400 + }, + { + "epoch": 2.3690572119258664, + "grad_norm": 0.4745603064237364, + "learning_rate": 5e-06, + "loss": 0.299, + "step": 4410 + }, + { + "epoch": 2.374429223744292, + "grad_norm": 0.46758674576062736, + "learning_rate": 5e-06, + "loss": 0.3077, + "step": 4420 + }, + { + "epoch": 2.3798012355627183, + "grad_norm": 0.46274751111290063, + "learning_rate": 5e-06, + "loss": 0.2893, + "step": 4430 + }, + { + "epoch": 2.385173247381144, + "grad_norm": 0.4979805795649497, + "learning_rate": 5e-06, + "loss": 0.2981, + "step": 4440 + }, + { + "epoch": 2.39054525919957, + "grad_norm": 0.46716558522728535, + "learning_rate": 5e-06, + "loss": 0.2944, + "step": 4450 + }, + { + "epoch": 2.3959172710179963, + "grad_norm": 0.4645219886431316, + "learning_rate": 5e-06, + "loss": 0.3027, + "step": 4460 + }, + { + "epoch": 2.401289282836422, + "grad_norm": 0.43076708233547145, + "learning_rate": 5e-06, + "loss": 0.2982, + "step": 4470 + }, + { + "epoch": 2.4066612946548482, + "grad_norm": 0.4833331043961502, + "learning_rate": 5e-06, + "loss": 0.3055, + "step": 4480 + }, + { + "epoch": 2.4120333064732744, + "grad_norm": 0.47944161915551303, + "learning_rate": 5e-06, + "loss": 0.308, + "step": 4490 + }, + { + "epoch": 2.4174053182917, + "grad_norm": 0.4735210760345749, + "learning_rate": 5e-06, + "loss": 0.2988, + "step": 4500 + }, + { + "epoch": 2.4227773301101263, + "grad_norm": 0.45565434475127603, + "learning_rate": 5e-06, + "loss": 0.3021, + "step": 4510 + }, + { + "epoch": 2.4281493419285525, + "grad_norm": 0.4766564731916228, + "learning_rate": 5e-06, + "loss": 0.3004, + "step": 4520 + }, + { + "epoch": 2.433521353746978, + "grad_norm": 0.48549992148905935, + "learning_rate": 5e-06, + "loss": 0.3033, + "step": 4530 + }, + { + "epoch": 2.4388933655654044, + "grad_norm": 0.44183880523434893, + "learning_rate": 5e-06, + "loss": 0.3071, + "step": 4540 + }, + { + "epoch": 2.44426537738383, + "grad_norm": 0.47705998139459066, + "learning_rate": 5e-06, + "loss": 0.3003, + "step": 4550 + }, + { + "epoch": 2.4496373892022563, + "grad_norm": 0.47178717771265055, + "learning_rate": 5e-06, + "loss": 0.2979, + "step": 4560 + }, + { + "epoch": 2.4550094010206824, + "grad_norm": 0.47229880316656225, + "learning_rate": 5e-06, + "loss": 0.323, + "step": 4570 + }, + { + "epoch": 2.460381412839108, + "grad_norm": 0.47107025763530014, + "learning_rate": 5e-06, + "loss": 0.2973, + "step": 4580 + }, + { + "epoch": 2.4657534246575343, + "grad_norm": 0.43860774515749135, + "learning_rate": 5e-06, + "loss": 0.2923, + "step": 4590 + }, + { + "epoch": 2.47112543647596, + "grad_norm": 0.44310429491661396, + "learning_rate": 5e-06, + "loss": 0.3091, + "step": 4600 + }, + { + "epoch": 2.4764974482943862, + "grad_norm": 0.450170058844727, + "learning_rate": 5e-06, + "loss": 0.2982, + "step": 4610 + }, + { + "epoch": 2.4818694601128124, + "grad_norm": 0.47368860930985485, + "learning_rate": 5e-06, + "loss": 0.3109, + "step": 4620 + }, + { + "epoch": 2.487241471931238, + "grad_norm": 0.4448141501224447, + "learning_rate": 5e-06, + "loss": 0.3043, + "step": 4630 + }, + { + "epoch": 2.4926134837496643, + "grad_norm": 0.4511180428107082, + "learning_rate": 5e-06, + "loss": 0.307, + "step": 4640 + }, + { + "epoch": 2.4979854955680905, + "grad_norm": 0.46753646829536444, + "learning_rate": 5e-06, + "loss": 0.306, + "step": 4650 + }, + { + "epoch": 2.503357507386516, + "grad_norm": 0.45938971563289144, + "learning_rate": 5e-06, + "loss": 0.3007, + "step": 4660 + }, + { + "epoch": 2.5087295192049424, + "grad_norm": 0.47175671154199156, + "learning_rate": 5e-06, + "loss": 0.3284, + "step": 4670 + }, + { + "epoch": 2.514101531023368, + "grad_norm": 0.4401639803199821, + "learning_rate": 5e-06, + "loss": 0.3045, + "step": 4680 + }, + { + "epoch": 2.5194735428417943, + "grad_norm": 0.47017862481838113, + "learning_rate": 5e-06, + "loss": 0.3188, + "step": 4690 + }, + { + "epoch": 2.52484555466022, + "grad_norm": 0.45763810223180906, + "learning_rate": 5e-06, + "loss": 0.296, + "step": 4700 + }, + { + "epoch": 2.530217566478646, + "grad_norm": 0.4644047897844528, + "learning_rate": 5e-06, + "loss": 0.2974, + "step": 4710 + }, + { + "epoch": 2.5355895782970723, + "grad_norm": 0.48551837865739933, + "learning_rate": 5e-06, + "loss": 0.2979, + "step": 4720 + }, + { + "epoch": 2.540961590115498, + "grad_norm": 0.4466465105264453, + "learning_rate": 5e-06, + "loss": 0.3077, + "step": 4730 + }, + { + "epoch": 2.546333601933924, + "grad_norm": 0.49252290575630375, + "learning_rate": 5e-06, + "loss": 0.3073, + "step": 4740 + }, + { + "epoch": 2.5517056137523504, + "grad_norm": 0.4302316284869702, + "learning_rate": 5e-06, + "loss": 0.2943, + "step": 4750 + }, + { + "epoch": 2.557077625570776, + "grad_norm": 0.469588515548392, + "learning_rate": 5e-06, + "loss": 0.3137, + "step": 4760 + }, + { + "epoch": 2.5624496373892023, + "grad_norm": 0.48615106142894776, + "learning_rate": 5e-06, + "loss": 0.316, + "step": 4770 + }, + { + "epoch": 2.5678216492076285, + "grad_norm": 0.47144647236889003, + "learning_rate": 5e-06, + "loss": 0.3059, + "step": 4780 + }, + { + "epoch": 2.573193661026054, + "grad_norm": 0.4690758287942174, + "learning_rate": 5e-06, + "loss": 0.3019, + "step": 4790 + }, + { + "epoch": 2.5785656728444803, + "grad_norm": 0.46961670498579505, + "learning_rate": 5e-06, + "loss": 0.3049, + "step": 4800 + }, + { + "epoch": 2.5839376846629065, + "grad_norm": 0.46991982229485013, + "learning_rate": 5e-06, + "loss": 0.3122, + "step": 4810 + }, + { + "epoch": 2.5893096964813322, + "grad_norm": 0.4679864164801053, + "learning_rate": 5e-06, + "loss": 0.2887, + "step": 4820 + }, + { + "epoch": 2.5946817082997584, + "grad_norm": 0.4441047775614893, + "learning_rate": 5e-06, + "loss": 0.3054, + "step": 4830 + }, + { + "epoch": 2.600053720118184, + "grad_norm": 0.47658994935407895, + "learning_rate": 5e-06, + "loss": 0.2985, + "step": 4840 + }, + { + "epoch": 2.6054257319366103, + "grad_norm": 0.46756360598099345, + "learning_rate": 5e-06, + "loss": 0.3062, + "step": 4850 + }, + { + "epoch": 2.610797743755036, + "grad_norm": 0.4632538377863063, + "learning_rate": 5e-06, + "loss": 0.3003, + "step": 4860 + }, + { + "epoch": 2.616169755573462, + "grad_norm": 0.4449475225017694, + "learning_rate": 5e-06, + "loss": 0.3017, + "step": 4870 + }, + { + "epoch": 2.6215417673918884, + "grad_norm": 0.4507497733905932, + "learning_rate": 5e-06, + "loss": 0.303, + "step": 4880 + }, + { + "epoch": 2.626913779210314, + "grad_norm": 0.46757813747214755, + "learning_rate": 5e-06, + "loss": 0.2994, + "step": 4890 + }, + { + "epoch": 2.6322857910287403, + "grad_norm": 0.45377996440263907, + "learning_rate": 5e-06, + "loss": 0.3033, + "step": 4900 + }, + { + "epoch": 2.6376578028471664, + "grad_norm": 0.46697319931601083, + "learning_rate": 5e-06, + "loss": 0.3169, + "step": 4910 + }, + { + "epoch": 2.643029814665592, + "grad_norm": 0.4594680488189553, + "learning_rate": 5e-06, + "loss": 0.2897, + "step": 4920 + }, + { + "epoch": 2.6484018264840183, + "grad_norm": 0.4977556770630546, + "learning_rate": 5e-06, + "loss": 0.3131, + "step": 4930 + }, + { + "epoch": 2.6537738383024445, + "grad_norm": 0.4599794430419653, + "learning_rate": 5e-06, + "loss": 0.303, + "step": 4940 + }, + { + "epoch": 2.6591458501208702, + "grad_norm": 0.4365617141166764, + "learning_rate": 5e-06, + "loss": 0.3038, + "step": 4950 + }, + { + "epoch": 2.6645178619392964, + "grad_norm": 0.4613086189177407, + "learning_rate": 5e-06, + "loss": 0.305, + "step": 4960 + }, + { + "epoch": 2.669889873757722, + "grad_norm": 0.46325663902687436, + "learning_rate": 5e-06, + "loss": 0.3128, + "step": 4970 + }, + { + "epoch": 2.6752618855761483, + "grad_norm": 0.456469424630923, + "learning_rate": 5e-06, + "loss": 0.3009, + "step": 4980 + }, + { + "epoch": 2.680633897394574, + "grad_norm": 0.4773037128036795, + "learning_rate": 5e-06, + "loss": 0.2999, + "step": 4990 + }, + { + "epoch": 2.686005909213, + "grad_norm": 0.48149380524695606, + "learning_rate": 5e-06, + "loss": 0.302, + "step": 5000 + }, + { + "epoch": 2.6913779210314264, + "grad_norm": 0.4516275475221354, + "learning_rate": 5e-06, + "loss": 0.2969, + "step": 5010 + }, + { + "epoch": 2.696749932849852, + "grad_norm": 0.4580414193871738, + "learning_rate": 5e-06, + "loss": 0.3124, + "step": 5020 + }, + { + "epoch": 2.7021219446682783, + "grad_norm": 0.454186120155934, + "learning_rate": 5e-06, + "loss": 0.3259, + "step": 5030 + }, + { + "epoch": 2.7074939564867044, + "grad_norm": 0.4359902304782414, + "learning_rate": 5e-06, + "loss": 0.3036, + "step": 5040 + }, + { + "epoch": 2.71286596830513, + "grad_norm": 0.4518860212887475, + "learning_rate": 5e-06, + "loss": 0.3046, + "step": 5050 + }, + { + "epoch": 2.7182379801235563, + "grad_norm": 0.44467216977831553, + "learning_rate": 5e-06, + "loss": 0.3018, + "step": 5060 + }, + { + "epoch": 2.7236099919419825, + "grad_norm": 0.47424637833011146, + "learning_rate": 5e-06, + "loss": 0.3026, + "step": 5070 + }, + { + "epoch": 2.7289820037604082, + "grad_norm": 0.5014084472686937, + "learning_rate": 5e-06, + "loss": 0.3005, + "step": 5080 + }, + { + "epoch": 2.7343540155788344, + "grad_norm": 0.481674717641741, + "learning_rate": 5e-06, + "loss": 0.313, + "step": 5090 + }, + { + "epoch": 2.73972602739726, + "grad_norm": 0.46503178430983816, + "learning_rate": 5e-06, + "loss": 0.3089, + "step": 5100 + }, + { + "epoch": 2.7450980392156863, + "grad_norm": 0.45047473457505316, + "learning_rate": 5e-06, + "loss": 0.3041, + "step": 5110 + }, + { + "epoch": 2.750470051034112, + "grad_norm": 0.5004805336195348, + "learning_rate": 5e-06, + "loss": 0.3116, + "step": 5120 + }, + { + "epoch": 2.755842062852538, + "grad_norm": 0.4276625646575985, + "learning_rate": 5e-06, + "loss": 0.301, + "step": 5130 + }, + { + "epoch": 2.7612140746709644, + "grad_norm": 0.44599433520202253, + "learning_rate": 5e-06, + "loss": 0.3168, + "step": 5140 + }, + { + "epoch": 2.76658608648939, + "grad_norm": 0.4767243040781986, + "learning_rate": 5e-06, + "loss": 0.3091, + "step": 5150 + }, + { + "epoch": 2.7719580983078163, + "grad_norm": 0.4539005921766262, + "learning_rate": 5e-06, + "loss": 0.3029, + "step": 5160 + }, + { + "epoch": 2.7773301101262424, + "grad_norm": 0.46406180742134173, + "learning_rate": 5e-06, + "loss": 0.3065, + "step": 5170 + }, + { + "epoch": 2.782702121944668, + "grad_norm": 0.4526636911178936, + "learning_rate": 5e-06, + "loss": 0.3181, + "step": 5180 + }, + { + "epoch": 2.7880741337630943, + "grad_norm": 0.45220356163061637, + "learning_rate": 5e-06, + "loss": 0.3075, + "step": 5190 + }, + { + "epoch": 2.7934461455815205, + "grad_norm": 0.45914982506711954, + "learning_rate": 5e-06, + "loss": 0.2989, + "step": 5200 + }, + { + "epoch": 2.798818157399946, + "grad_norm": 0.4852446695355985, + "learning_rate": 5e-06, + "loss": 0.3102, + "step": 5210 + }, + { + "epoch": 2.8041901692183724, + "grad_norm": 0.44174008476202076, + "learning_rate": 5e-06, + "loss": 0.3064, + "step": 5220 + }, + { + "epoch": 2.8095621810367986, + "grad_norm": 0.47195550534277947, + "learning_rate": 5e-06, + "loss": 0.3061, + "step": 5230 + }, + { + "epoch": 2.8149341928552243, + "grad_norm": 0.47482707999228474, + "learning_rate": 5e-06, + "loss": 0.302, + "step": 5240 + }, + { + "epoch": 2.82030620467365, + "grad_norm": 0.4655883266741662, + "learning_rate": 5e-06, + "loss": 0.3008, + "step": 5250 + }, + { + "epoch": 2.825678216492076, + "grad_norm": 0.47382383652851645, + "learning_rate": 5e-06, + "loss": 0.3009, + "step": 5260 + }, + { + "epoch": 2.8310502283105023, + "grad_norm": 0.45841149048452207, + "learning_rate": 5e-06, + "loss": 0.3125, + "step": 5270 + }, + { + "epoch": 2.836422240128928, + "grad_norm": 0.4404178325742541, + "learning_rate": 5e-06, + "loss": 0.3076, + "step": 5280 + }, + { + "epoch": 2.8417942519473542, + "grad_norm": 0.4691383498028934, + "learning_rate": 5e-06, + "loss": 0.3017, + "step": 5290 + }, + { + "epoch": 2.8471662637657804, + "grad_norm": 0.4495113094453148, + "learning_rate": 5e-06, + "loss": 0.3003, + "step": 5300 + }, + { + "epoch": 2.852538275584206, + "grad_norm": 0.46179624959522997, + "learning_rate": 5e-06, + "loss": 0.3078, + "step": 5310 + }, + { + "epoch": 2.8579102874026323, + "grad_norm": 0.4652311831624602, + "learning_rate": 5e-06, + "loss": 0.3164, + "step": 5320 + }, + { + "epoch": 2.8632822992210585, + "grad_norm": 0.47278598674863237, + "learning_rate": 5e-06, + "loss": 0.3035, + "step": 5330 + }, + { + "epoch": 2.868654311039484, + "grad_norm": 0.4910443155512238, + "learning_rate": 5e-06, + "loss": 0.3095, + "step": 5340 + }, + { + "epoch": 2.8740263228579104, + "grad_norm": 0.46167647985765303, + "learning_rate": 5e-06, + "loss": 0.3074, + "step": 5350 + }, + { + "epoch": 2.8793983346763365, + "grad_norm": 0.4954312490665213, + "learning_rate": 5e-06, + "loss": 0.3071, + "step": 5360 + }, + { + "epoch": 2.8847703464947623, + "grad_norm": 0.4367016608079839, + "learning_rate": 5e-06, + "loss": 0.3077, + "step": 5370 + }, + { + "epoch": 2.8901423583131884, + "grad_norm": 0.47686556153161486, + "learning_rate": 5e-06, + "loss": 0.303, + "step": 5380 + }, + { + "epoch": 2.895514370131614, + "grad_norm": 0.45520995582229345, + "learning_rate": 5e-06, + "loss": 0.2959, + "step": 5390 + }, + { + "epoch": 2.9008863819500403, + "grad_norm": 0.45167583945865714, + "learning_rate": 5e-06, + "loss": 0.3041, + "step": 5400 + }, + { + "epoch": 2.906258393768466, + "grad_norm": 0.489953863528834, + "learning_rate": 5e-06, + "loss": 0.3227, + "step": 5410 + }, + { + "epoch": 2.9116304055868922, + "grad_norm": 0.4842925647008196, + "learning_rate": 5e-06, + "loss": 0.3031, + "step": 5420 + }, + { + "epoch": 2.9170024174053184, + "grad_norm": 0.4679895193248062, + "learning_rate": 5e-06, + "loss": 0.3048, + "step": 5430 + }, + { + "epoch": 2.922374429223744, + "grad_norm": 0.46032428378414053, + "learning_rate": 5e-06, + "loss": 0.3001, + "step": 5440 + }, + { + "epoch": 2.9277464410421703, + "grad_norm": 0.49424698475244133, + "learning_rate": 5e-06, + "loss": 0.298, + "step": 5450 + }, + { + "epoch": 2.9331184528605965, + "grad_norm": 0.45206528520285993, + "learning_rate": 5e-06, + "loss": 0.2975, + "step": 5460 + }, + { + "epoch": 2.938490464679022, + "grad_norm": 0.43783656221438655, + "learning_rate": 5e-06, + "loss": 0.3056, + "step": 5470 + }, + { + "epoch": 2.9438624764974484, + "grad_norm": 0.4641248542873233, + "learning_rate": 5e-06, + "loss": 0.3131, + "step": 5480 + }, + { + "epoch": 2.9492344883158745, + "grad_norm": 0.45508868403537883, + "learning_rate": 5e-06, + "loss": 0.3026, + "step": 5490 + }, + { + "epoch": 2.9546065001343003, + "grad_norm": 0.4918746072980534, + "learning_rate": 5e-06, + "loss": 0.31, + "step": 5500 + }, + { + "epoch": 2.9599785119527264, + "grad_norm": 0.4775427997395849, + "learning_rate": 5e-06, + "loss": 0.3035, + "step": 5510 + }, + { + "epoch": 2.965350523771152, + "grad_norm": 0.43827768706167886, + "learning_rate": 5e-06, + "loss": 0.2982, + "step": 5520 + }, + { + "epoch": 2.9707225355895783, + "grad_norm": 0.4724169681109276, + "learning_rate": 5e-06, + "loss": 0.3013, + "step": 5530 + }, + { + "epoch": 2.976094547408004, + "grad_norm": 0.4534158098276835, + "learning_rate": 5e-06, + "loss": 0.2999, + "step": 5540 + }, + { + "epoch": 2.9814665592264302, + "grad_norm": 0.43461750252166137, + "learning_rate": 5e-06, + "loss": 0.2999, + "step": 5550 + }, + { + "epoch": 2.9868385710448564, + "grad_norm": 0.48563812071930773, + "learning_rate": 5e-06, + "loss": 0.3012, + "step": 5560 + }, + { + "epoch": 2.992210582863282, + "grad_norm": 0.5229982921947193, + "learning_rate": 5e-06, + "loss": 0.3139, + "step": 5570 + }, + { + "epoch": 2.9975825946817083, + "grad_norm": 0.46203252168577574, + "learning_rate": 5e-06, + "loss": 0.3035, + "step": 5580 + }, + { + "epoch": 2.999194198227236, + "eval_loss": 0.405712366104126, + "eval_runtime": 469.8508, + "eval_samples_per_second": 26.689, + "eval_steps_per_second": 0.417, + "step": 5583 + }, + { + "epoch": 2.999194198227236, + "step": 5583, + "total_flos": 2926650442383360.0, + "train_loss": 0.3617401811868598, + "train_runtime": 75547.7589, + "train_samples_per_second": 9.461, + "train_steps_per_second": 0.074 + } + ], + "logging_steps": 10, + "max_steps": 5583, + "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": 2926650442383360.0, + "train_batch_size": 8, + "trial_name": null, + "trial_params": null +} diff --git a/training_args.bin b/training_args.bin new file mode 100644 index 0000000..12a5fc6 --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6be0d45de066c9340ecaf395c4d7613cd6b546b5a2729f7e2d430ddc9b12bd9 +size 7160 diff --git a/training_eval_loss.png b/training_eval_loss.png new file mode 100644 index 0000000..66d0c81 Binary files /dev/null and b/training_eval_loss.png differ diff --git a/training_loss.png b/training_loss.png new file mode 100644 index 0000000..218aa40 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