commit b34caac47e910bbe7ba65635c566f8401150e82b Author: ModelHub XC Date: Mon Jun 29 17:21:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mlfoundations-dev/10k_globalbatchsize128_lr4e5_epochs7 Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a98225c --- /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 + +vocab.json filter=lfs diff=lfs merge=lfs -text +merges.txt filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text +model-00001-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +model-00004-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +model-00002-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +model-00003-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +training_args.bin 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..980271e --- /dev/null +++ b/README.md @@ -0,0 +1,61 @@ +--- +library_name: transformers +license: apache-2.0 +base_model: Qwen/Qwen2.5-7B-Instruct +tags: +- llama-factory +- full +- generated_from_trainer +model-index: +- name: 10k_globalbatchsize128_lr4e5_epochs7 + results: [] +--- + + + +# 10k_globalbatchsize128_lr4e5_epochs7 + +This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the mlfoundations-dev/openthoughts_10000 dataset. + +## Model description + +More information needed + +## Intended uses & limitations + +More information needed + +## Training and evaluation data + +More information needed + +## Training procedure + +### Training hyperparameters + +The following hyperparameters were used during training: +- learning_rate: 4e-05 +- train_batch_size: 1 +- eval_batch_size: 8 +- seed: 42 +- distributed_type: multi-GPU +- num_devices: 16 +- gradient_accumulation_steps: 8 +- total_train_batch_size: 128 +- total_eval_batch_size: 128 +- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments +- lr_scheduler_type: cosine +- lr_scheduler_warmup_ratio: 0.1 +- num_epochs: 7.0 + +### Training results + + + +### 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..7f7e566 --- /dev/null +++ b/all_results.json @@ -0,0 +1,8 @@ +{ + "epoch": 6.9888, + "total_flos": 1.3527969808368271e+18, + "train_loss": 0.27728078796804606, + "train_runtime": 40114.8445, + "train_samples_per_second": 1.744, + "train_steps_per_second": 0.014 +} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..6c52571 --- /dev/null +++ b/config.json @@ -0,0 +1,29 @@ +{ + "_name_or_path": "Qwen/Qwen2.5-7B-Instruct", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 151643, + "eos_token_id": 151645, + "hidden_act": "silu", + "hidden_size": 3584, + "initializer_range": 0.02, + "intermediate_size": 18944, + "max_position_embeddings": 32768, + "max_window_layers": 28, + "model_type": "qwen2", + "num_attention_heads": 28, + "num_hidden_layers": 28, + "num_key_value_heads": 4, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000.0, + "sliding_window": null, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.46.1", + "use_cache": false, + "use_sliding_window": false, + "vocab_size": 152064 +} diff --git a/configs.yaml b/configs.yaml new file mode 100644 index 0000000..a14a96f --- /dev/null +++ b/configs.yaml @@ -0,0 +1,39 @@ +assistant_tag: assistant +bf16: 'True' +content_tag: value +cutoff_len: '16384' +dataloader_num_workers: '4' +dataloader_persistent_workers: 'True' +dataloader_pin_memory: 'True' +dataset: mlfoundations-dev/openthoughts_10000 +dataset_dir: ONLINE +ddp_timeout: '180000000' +deepspeed: /opt/ml/code/zero3.json +do_train: 'True' +enable_liger_kernel: 'True' +finetuning_type: full +formatting: sharegpt +global_batch_size: '128' +gradient_accumulation_steps: '8' +hub_model_id: mlfoundations-dev/10k_globalbatchsize128_lr4e5_epochs7 +learning_rate: 4e-05 +logging_steps: '1' +lr_scheduler_type: cosine +messages: conversations +model_name_or_path: Qwen/Qwen2.5-7B-Instruct +num_train_epochs: '7.0' +output_dir: /opt/ml/model +overwrite_cache: 'True' +per_device_train_batch_size: '1' +plot_loss: 'True' +preprocessing_num_workers: '16' +push_to_db: 'True' +push_to_hub: 'True' +report_to: wandb +role_tag: from +run_name: 10k_globalbatchsize128_lr4e5_epochs7 +save_strategy: epoch +stage: sft +template: qwen25 +user_tag: user +warmup_ratio: '0.1' diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..a753841 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,14 @@ +{ + "bos_token_id": 151643, + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "repetition_penalty": 1.05, + "temperature": 0.7, + "top_k": 20, + "top_p": 0.8, + "transformers_version": "4.46.1" +} diff --git a/merges.txt b/merges.txt new file mode 100644 index 0000000..80c1a19 --- /dev/null +++ b/merges.txt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5 +size 1671853 diff --git a/model-00001-of-00004.safetensors b/model-00001-of-00004.safetensors new file mode 100644 index 0000000..ada2fc2 --- /dev/null +++ b/model-00001-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1e128ceda012b94a1c630e4061ddad4ab31ba7fc709b66cf1d82a39ce37d795 +size 4877660776 diff --git a/model-00002-of-00004.safetensors b/model-00002-of-00004.safetensors new file mode 100644 index 0000000..0e7a1d1 --- /dev/null +++ b/model-00002-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf69812ae18103be3d876c5c76b3a945011f5eca85141cbba31b6a83c8706a26 +size 4932751008 diff --git a/model-00003-of-00004.safetensors b/model-00003-of-00004.safetensors new file mode 100644 index 0000000..4f6b96a --- /dev/null +++ b/model-00003-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27a84f94852cec4fa74f10f2adfab1d13aa96892e60bf3b6bbdbbe14e706006a +size 4330865200 diff --git a/model-00004-of-00004.safetensors b/model-00004-of-00004.safetensors new file mode 100644 index 0000000..e027acb --- /dev/null +++ b/model-00004-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32b36b7123d5278d71811b900549ee78a2ba8989e78a804a0a6f405178464f6c +size 1089994880 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..6ca5084 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,346 @@ +{ + "metadata": { + "total_size": 15231233024 + }, + "weight_map": { + "lm_head.weight": "model-00004-of-00004.safetensors", + "model.embed_tokens.weight": "model-00001-of-00004.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.norm.weight": "model-00003-of-00004.safetensors" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..17305b3 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,31 @@ +{ + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "eos_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..51ebb3b --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa +size 11421896 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..b84f53a --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,208 @@ +{ + "add_bos_token": false, + "add_prefix_space": false, + "added_tokens_decoder": { + "151643": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151644": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151645": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151646": { + "content": "<|object_ref_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151647": { + "content": "<|object_ref_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151648": { + "content": "<|box_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151649": { + "content": "<|box_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151650": { + "content": "<|quad_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151657": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151658": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "bos_token": null, + "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within XML tags:\\n\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n\\n\\nFor each function call, return a json object with function name and arguments within XML tags:\\n\\n{\\\"name\\\": , \\\"arguments\\\": }\\n<|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n\\n' }}\n {{- message.content }}\n {{- '\\n' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n", + "clean_up_tokenization_spaces": false, + "eos_token": "<|endoftext|>", + "errors": "replace", + "model_max_length": 131072, + "pad_token": "<|endoftext|>", + "padding_side": "right", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +} diff --git a/train_results.json b/train_results.json new file mode 100644 index 0000000..7f7e566 --- /dev/null +++ b/train_results.json @@ -0,0 +1,8 @@ +{ + "epoch": 6.9888, + "total_flos": 1.3527969808368271e+18, + "train_loss": 0.27728078796804606, + "train_runtime": 40114.8445, + "train_samples_per_second": 1.744, + "train_steps_per_second": 0.014 +} \ No newline at end of file diff --git a/trainer_log.jsonl b/trainer_log.jsonl new file mode 100644 index 0000000..7d15399 --- /dev/null +++ b/trainer_log.jsonl @@ -0,0 +1,547 @@ +{"current_steps": 1, "total_steps": 546, "loss": 0.8581, "lr": 7.272727272727273e-07, "epoch": 0.0128, "percentage": 0.18, "elapsed_time": "0:01:23", "remaining_time": "12:39:24"} +{"current_steps": 2, "total_steps": 546, "loss": 0.8903, "lr": 1.4545454545454546e-06, "epoch": 0.0256, "percentage": 0.37, "elapsed_time": "0:02:43", "remaining_time": "12:20:41"} +{"current_steps": 3, "total_steps": 546, "loss": 0.8612, "lr": 2.181818181818182e-06, "epoch": 0.0384, "percentage": 0.55, "elapsed_time": "0:03:58", "remaining_time": "12:00:44"} +{"current_steps": 4, "total_steps": 546, "loss": 0.8373, "lr": 2.9090909090909093e-06, "epoch": 0.0512, "percentage": 0.73, "elapsed_time": "0:05:05", "remaining_time": "11:29:35"} +{"current_steps": 5, "total_steps": 546, "loss": 0.8142, "lr": 3.6363636363636366e-06, "epoch": 0.064, "percentage": 0.92, "elapsed_time": "0:06:27", "remaining_time": "11:38:22"} +{"current_steps": 6, "total_steps": 546, "loss": 0.7828, "lr": 4.363636363636364e-06, "epoch": 0.0768, "percentage": 1.1, "elapsed_time": "0:07:41", "remaining_time": "11:31:41"} +{"current_steps": 7, "total_steps": 546, "loss": 0.7785, "lr": 5.090909090909091e-06, "epoch": 0.0896, "percentage": 1.28, "elapsed_time": "0:09:02", "remaining_time": "11:35:46"} +{"current_steps": 8, "total_steps": 546, "loss": 0.7922, "lr": 5.8181818181818185e-06, "epoch": 0.1024, "percentage": 1.47, "elapsed_time": "0:10:16", "remaining_time": "11:31:28"} +{"current_steps": 9, "total_steps": 546, "loss": 0.7785, "lr": 6.545454545454546e-06, "epoch": 0.1152, "percentage": 1.65, "elapsed_time": "0:11:37", "remaining_time": "11:33:14"} +{"current_steps": 10, "total_steps": 546, "loss": 0.7593, "lr": 7.272727272727273e-06, "epoch": 0.128, "percentage": 1.83, "elapsed_time": "0:12:59", "remaining_time": "11:36:15"} +{"current_steps": 11, "total_steps": 546, "loss": 0.7382, "lr": 8.000000000000001e-06, "epoch": 0.1408, "percentage": 2.01, "elapsed_time": "0:14:10", "remaining_time": "11:29:40"} +{"current_steps": 12, "total_steps": 546, "loss": 0.7525, "lr": 8.727272727272728e-06, "epoch": 0.1536, "percentage": 2.2, "elapsed_time": "0:15:20", "remaining_time": "11:22:46"} +{"current_steps": 13, "total_steps": 546, "loss": 0.742, "lr": 9.454545454545456e-06, "epoch": 0.1664, "percentage": 2.38, "elapsed_time": "0:16:35", "remaining_time": "11:20:11"} +{"current_steps": 14, "total_steps": 546, "loss": 0.6832, "lr": 1.0181818181818182e-05, "epoch": 0.1792, "percentage": 2.56, "elapsed_time": "0:17:39", "remaining_time": "11:11:11"} +{"current_steps": 15, "total_steps": 546, "loss": 0.6703, "lr": 1.0909090909090909e-05, "epoch": 0.192, "percentage": 2.75, "elapsed_time": "0:18:48", "remaining_time": "11:05:51"} +{"current_steps": 16, "total_steps": 546, "loss": 0.6537, "lr": 1.1636363636363637e-05, "epoch": 0.2048, "percentage": 2.93, "elapsed_time": "0:19:49", "remaining_time": "10:56:39"} +{"current_steps": 17, "total_steps": 546, "loss": 0.641, "lr": 1.2363636363636364e-05, "epoch": 0.2176, "percentage": 3.11, "elapsed_time": "0:20:49", "remaining_time": "10:47:51"} +{"current_steps": 18, "total_steps": 546, "loss": 0.6528, "lr": 1.3090909090909092e-05, "epoch": 0.2304, "percentage": 3.3, "elapsed_time": "0:22:06", "remaining_time": "10:48:28"} +{"current_steps": 19, "total_steps": 546, "loss": 0.6134, "lr": 1.381818181818182e-05, "epoch": 0.2432, "percentage": 3.48, "elapsed_time": "0:23:23", "remaining_time": "10:48:44"} +{"current_steps": 20, "total_steps": 546, "loss": 0.5982, "lr": 1.4545454545454546e-05, "epoch": 0.256, "percentage": 3.66, "elapsed_time": "0:24:37", "remaining_time": "10:47:35"} +{"current_steps": 21, "total_steps": 546, "loss": 0.5845, "lr": 1.5272727272727276e-05, "epoch": 0.2688, "percentage": 3.85, "elapsed_time": "0:25:41", "remaining_time": "10:42:12"} +{"current_steps": 22, "total_steps": 546, "loss": 0.6178, "lr": 1.6000000000000003e-05, "epoch": 0.2816, "percentage": 4.03, "elapsed_time": "0:26:58", "remaining_time": "10:42:20"} +{"current_steps": 23, "total_steps": 546, "loss": 0.588, "lr": 1.672727272727273e-05, "epoch": 0.2944, "percentage": 4.21, "elapsed_time": "0:28:18", "remaining_time": "10:43:47"} +{"current_steps": 24, "total_steps": 546, "loss": 0.6123, "lr": 1.7454545454545456e-05, "epoch": 0.3072, "percentage": 4.4, "elapsed_time": "0:29:42", "remaining_time": "10:46:03"} +{"current_steps": 25, "total_steps": 546, "loss": 0.5905, "lr": 1.8181818181818182e-05, "epoch": 0.32, "percentage": 4.58, "elapsed_time": "0:30:44", "remaining_time": "10:40:31"} +{"current_steps": 26, "total_steps": 546, "loss": 0.5878, "lr": 1.8909090909090912e-05, "epoch": 0.3328, "percentage": 4.76, "elapsed_time": "0:32:02", "remaining_time": "10:40:56"} +{"current_steps": 27, "total_steps": 546, "loss": 0.5888, "lr": 1.963636363636364e-05, "epoch": 0.3456, "percentage": 4.95, "elapsed_time": "0:33:11", "remaining_time": "10:37:52"} +{"current_steps": 28, "total_steps": 546, "loss": 0.5837, "lr": 2.0363636363636365e-05, "epoch": 0.3584, "percentage": 5.13, "elapsed_time": "0:34:22", "remaining_time": "10:35:57"} +{"current_steps": 29, "total_steps": 546, "loss": 0.5814, "lr": 2.109090909090909e-05, "epoch": 0.3712, "percentage": 5.31, "elapsed_time": "0:35:43", "remaining_time": "10:36:58"} +{"current_steps": 30, "total_steps": 546, "loss": 0.5553, "lr": 2.1818181818181818e-05, "epoch": 0.384, "percentage": 5.49, "elapsed_time": "0:36:56", "remaining_time": "10:35:24"} +{"current_steps": 31, "total_steps": 546, "loss": 0.5773, "lr": 2.2545454545454544e-05, "epoch": 0.3968, "percentage": 5.68, "elapsed_time": "0:38:15", "remaining_time": "10:35:29"} +{"current_steps": 32, "total_steps": 546, "loss": 0.5848, "lr": 2.3272727272727274e-05, "epoch": 0.4096, "percentage": 5.86, "elapsed_time": "0:39:32", "remaining_time": "10:35:04"} +{"current_steps": 33, "total_steps": 546, "loss": 0.5727, "lr": 2.4e-05, "epoch": 0.4224, "percentage": 6.04, "elapsed_time": "0:40:49", "remaining_time": "10:34:30"} +{"current_steps": 34, "total_steps": 546, "loss": 0.5675, "lr": 2.4727272727272727e-05, "epoch": 0.4352, "percentage": 6.23, "elapsed_time": "0:42:04", "remaining_time": "10:33:31"} +{"current_steps": 35, "total_steps": 546, "loss": 0.5832, "lr": 2.5454545454545457e-05, "epoch": 0.448, "percentage": 6.41, "elapsed_time": "0:43:10", "remaining_time": "10:30:18"} +{"current_steps": 36, "total_steps": 546, "loss": 0.5824, "lr": 2.6181818181818183e-05, "epoch": 0.4608, "percentage": 6.59, "elapsed_time": "0:44:25", "remaining_time": "10:29:23"} +{"current_steps": 37, "total_steps": 546, "loss": 0.5738, "lr": 2.690909090909091e-05, "epoch": 0.4736, "percentage": 6.78, "elapsed_time": "0:45:40", "remaining_time": "10:28:19"} +{"current_steps": 38, "total_steps": 546, "loss": 0.5614, "lr": 2.763636363636364e-05, "epoch": 0.4864, "percentage": 6.96, "elapsed_time": "0:46:47", "remaining_time": "10:25:31"} +{"current_steps": 39, "total_steps": 546, "loss": 0.554, "lr": 2.8363636363636366e-05, "epoch": 0.4992, "percentage": 7.14, "elapsed_time": "0:48:04", "remaining_time": "10:24:56"} +{"current_steps": 40, "total_steps": 546, "loss": 0.517, "lr": 2.9090909090909093e-05, "epoch": 0.512, "percentage": 7.33, "elapsed_time": "0:49:18", "remaining_time": "10:23:39"} +{"current_steps": 41, "total_steps": 546, "loss": 0.5714, "lr": 2.9818181818181823e-05, "epoch": 0.5248, "percentage": 7.51, "elapsed_time": "0:50:24", "remaining_time": "10:20:51"} +{"current_steps": 42, "total_steps": 546, "loss": 0.5287, "lr": 3.054545454545455e-05, "epoch": 0.5376, "percentage": 7.69, "elapsed_time": "0:51:40", "remaining_time": "10:20:08"} +{"current_steps": 43, "total_steps": 546, "loss": 0.5573, "lr": 3.127272727272728e-05, "epoch": 0.5504, "percentage": 7.88, "elapsed_time": "0:52:58", "remaining_time": "10:19:39"} +{"current_steps": 44, "total_steps": 546, "loss": 0.546, "lr": 3.2000000000000005e-05, "epoch": 0.5632, "percentage": 8.06, "elapsed_time": "0:54:09", "remaining_time": "10:17:52"} +{"current_steps": 45, "total_steps": 546, "loss": 0.5406, "lr": 3.272727272727273e-05, "epoch": 0.576, "percentage": 8.24, "elapsed_time": "0:55:16", "remaining_time": "10:15:28"} +{"current_steps": 46, "total_steps": 546, "loss": 0.5271, "lr": 3.345454545454546e-05, "epoch": 0.5888, "percentage": 8.42, "elapsed_time": "0:56:28", "remaining_time": "10:13:47"} +{"current_steps": 47, "total_steps": 546, "loss": 0.5142, "lr": 3.4181818181818185e-05, "epoch": 0.6016, "percentage": 8.61, "elapsed_time": "0:57:51", "remaining_time": "10:14:13"} +{"current_steps": 48, "total_steps": 546, "loss": 0.509, "lr": 3.490909090909091e-05, "epoch": 0.6144, "percentage": 8.79, "elapsed_time": "0:59:07", "remaining_time": "10:13:25"} +{"current_steps": 49, "total_steps": 546, "loss": 0.5489, "lr": 3.563636363636364e-05, "epoch": 0.6272, "percentage": 8.97, "elapsed_time": "1:00:26", "remaining_time": "10:13:02"} +{"current_steps": 50, "total_steps": 546, "loss": 0.5198, "lr": 3.6363636363636364e-05, "epoch": 0.64, "percentage": 9.16, "elapsed_time": "1:01:41", "remaining_time": "10:11:55"} +{"current_steps": 51, "total_steps": 546, "loss": 0.5356, "lr": 3.709090909090909e-05, "epoch": 0.6528, "percentage": 9.34, "elapsed_time": "1:02:59", "remaining_time": "10:11:26"} +{"current_steps": 52, "total_steps": 546, "loss": 0.5235, "lr": 3.7818181818181824e-05, "epoch": 0.6656, "percentage": 9.52, "elapsed_time": "1:04:11", "remaining_time": "10:09:45"} +{"current_steps": 53, "total_steps": 546, "loss": 0.5372, "lr": 3.854545454545455e-05, "epoch": 0.6784, "percentage": 9.71, "elapsed_time": "1:05:13", "remaining_time": "10:06:47"} +{"current_steps": 54, "total_steps": 546, "loss": 0.5349, "lr": 3.927272727272728e-05, "epoch": 0.6912, "percentage": 9.89, "elapsed_time": "1:06:21", "remaining_time": "10:04:40"} +{"current_steps": 55, "total_steps": 546, "loss": 0.5568, "lr": 4e-05, "epoch": 0.704, "percentage": 10.07, "elapsed_time": "1:07:32", "remaining_time": "10:02:54"} +{"current_steps": 56, "total_steps": 546, "loss": 0.5309, "lr": 3.9999590611838754e-05, "epoch": 0.7168, "percentage": 10.26, "elapsed_time": "1:08:43", "remaining_time": "10:01:17"} +{"current_steps": 57, "total_steps": 546, "loss": 0.5401, "lr": 3.9998362464114874e-05, "epoch": 0.7296, "percentage": 10.44, "elapsed_time": "1:09:58", "remaining_time": "10:00:17"} +{"current_steps": 58, "total_steps": 546, "loss": 0.5466, "lr": 3.9996315607107277e-05, "epoch": 0.7424, "percentage": 10.62, "elapsed_time": "1:11:13", "remaining_time": "9:59:15"} +{"current_steps": 59, "total_steps": 546, "loss": 0.5228, "lr": 3.999345012461187e-05, "epoch": 0.7552, "percentage": 10.81, "elapsed_time": "1:12:20", "remaining_time": "9:57:11"} +{"current_steps": 60, "total_steps": 546, "loss": 0.5294, "lr": 3.998976613393811e-05, "epoch": 0.768, "percentage": 10.99, "elapsed_time": "1:13:33", "remaining_time": "9:55:46"} +{"current_steps": 61, "total_steps": 546, "loss": 0.5517, "lr": 3.9985263785904216e-05, "epoch": 0.7808, "percentage": 11.17, "elapsed_time": "1:14:51", "remaining_time": "9:55:09"} +{"current_steps": 62, "total_steps": 546, "loss": 0.5545, "lr": 3.997994326483098e-05, "epoch": 0.7936, "percentage": 11.36, "elapsed_time": "1:16:05", "remaining_time": "9:54:02"} +{"current_steps": 63, "total_steps": 546, "loss": 0.5232, "lr": 3.9973804788534234e-05, "epoch": 0.8064, "percentage": 11.54, "elapsed_time": "1:17:20", "remaining_time": "9:52:54"} +{"current_steps": 64, "total_steps": 546, "loss": 0.5196, "lr": 3.996684860831595e-05, "epoch": 0.8192, "percentage": 11.72, "elapsed_time": "1:18:36", "remaining_time": "9:51:57"} +{"current_steps": 65, "total_steps": 546, "loss": 0.5351, "lr": 3.995907500895389e-05, "epoch": 0.832, "percentage": 11.9, "elapsed_time": "1:19:42", "remaining_time": "9:49:51"} +{"current_steps": 66, "total_steps": 546, "loss": 0.5463, "lr": 3.995048430869002e-05, "epoch": 0.8448, "percentage": 12.09, "elapsed_time": "1:20:45", "remaining_time": "9:47:21"} +{"current_steps": 67, "total_steps": 546, "loss": 0.513, "lr": 3.994107685921743e-05, "epoch": 0.8576, "percentage": 12.27, "elapsed_time": "1:21:49", "remaining_time": "9:44:58"} +{"current_steps": 68, "total_steps": 546, "loss": 0.5388, "lr": 3.993085304566597e-05, "epoch": 0.8704, "percentage": 12.45, "elapsed_time": "1:23:09", "remaining_time": "9:44:34"} +{"current_steps": 69, "total_steps": 546, "loss": 0.5266, "lr": 3.991981328658646e-05, "epoch": 0.8832, "percentage": 12.64, "elapsed_time": "1:24:28", "remaining_time": "9:43:56"} +{"current_steps": 70, "total_steps": 546, "loss": 0.5289, "lr": 3.990795803393358e-05, "epoch": 0.896, "percentage": 12.82, "elapsed_time": "1:25:50", "remaining_time": "9:43:40"} +{"current_steps": 71, "total_steps": 546, "loss": 0.5176, "lr": 3.989528777304732e-05, "epoch": 0.9088, "percentage": 13.0, "elapsed_time": "1:26:53", "remaining_time": "9:41:19"} +{"current_steps": 72, "total_steps": 546, "loss": 0.5142, "lr": 3.988180302263317e-05, "epoch": 0.9216, "percentage": 13.19, "elapsed_time": "1:28:04", "remaining_time": "9:39:50"} +{"current_steps": 73, "total_steps": 546, "loss": 0.508, "lr": 3.986750433474084e-05, "epoch": 0.9344, "percentage": 13.37, "elapsed_time": "1:29:11", "remaining_time": "9:37:54"} +{"current_steps": 74, "total_steps": 546, "loss": 0.5395, "lr": 3.98523922947417e-05, "epoch": 0.9472, "percentage": 13.55, "elapsed_time": "1:30:20", "remaining_time": "9:36:13"} +{"current_steps": 75, "total_steps": 546, "loss": 0.5125, "lr": 3.983646752130476e-05, "epoch": 0.96, "percentage": 13.74, "elapsed_time": "1:31:36", "remaining_time": "9:35:15"} +{"current_steps": 76, "total_steps": 546, "loss": 0.5029, "lr": 3.981973066637141e-05, "epoch": 0.9728, "percentage": 13.92, "elapsed_time": "1:32:49", "remaining_time": "9:34:04"} +{"current_steps": 77, "total_steps": 546, "loss": 0.5123, "lr": 3.980218241512865e-05, "epoch": 0.9856, "percentage": 14.1, "elapsed_time": "1:33:51", "remaining_time": "9:31:41"} +{"current_steps": 78, "total_steps": 546, "loss": 0.5277, "lr": 3.9783823485981135e-05, "epoch": 0.9984, "percentage": 14.29, "elapsed_time": "1:34:59", "remaining_time": "9:29:58"} +{"current_steps": 79, "total_steps": 546, "loss": 0.9868, "lr": 3.976465463052168e-05, "epoch": 1.0112, "percentage": 14.47, "elapsed_time": "1:37:02", "remaining_time": "9:33:37"} +{"current_steps": 80, "total_steps": 546, "loss": 0.409, "lr": 3.974467663350053e-05, "epoch": 1.024, "percentage": 14.65, "elapsed_time": "1:38:20", "remaining_time": "9:32:50"} +{"current_steps": 81, "total_steps": 546, "loss": 0.47, "lr": 3.972389031279324e-05, "epoch": 1.0368, "percentage": 14.84, "elapsed_time": "1:39:27", "remaining_time": "9:31:00"} +{"current_steps": 82, "total_steps": 546, "loss": 0.4449, "lr": 3.970229651936717e-05, "epoch": 1.0496, "percentage": 15.02, "elapsed_time": "1:40:41", "remaining_time": "9:29:45"} +{"current_steps": 83, "total_steps": 546, "loss": 0.5014, "lr": 3.967989613724666e-05, "epoch": 1.0624, "percentage": 15.2, "elapsed_time": "1:41:59", "remaining_time": "9:28:53"} +{"current_steps": 84, "total_steps": 546, "loss": 0.3972, "lr": 3.965669008347683e-05, "epoch": 1.0752, "percentage": 15.38, "elapsed_time": "1:43:12", "remaining_time": "9:27:39"} +{"current_steps": 85, "total_steps": 546, "loss": 0.476, "lr": 3.963267930808604e-05, "epoch": 1.088, "percentage": 15.57, "elapsed_time": "1:44:29", "remaining_time": "9:26:45"} +{"current_steps": 86, "total_steps": 546, "loss": 0.4889, "lr": 3.9607864794047024e-05, "epoch": 1.1008, "percentage": 15.75, "elapsed_time": "1:45:56", "remaining_time": "9:26:42"} +{"current_steps": 87, "total_steps": 546, "loss": 0.422, "lr": 3.958224755723661e-05, "epoch": 1.1136, "percentage": 15.93, "elapsed_time": "1:47:17", "remaining_time": "9:26:01"} +{"current_steps": 88, "total_steps": 546, "loss": 0.4481, "lr": 3.955582864639413e-05, "epoch": 1.1264, "percentage": 16.12, "elapsed_time": "1:48:25", "remaining_time": "9:24:18"} +{"current_steps": 89, "total_steps": 546, "loss": 0.4095, "lr": 3.952860914307853e-05, "epoch": 1.1392, "percentage": 16.3, "elapsed_time": "1:49:36", "remaining_time": "9:22:49"} +{"current_steps": 90, "total_steps": 546, "loss": 0.4876, "lr": 3.950059016162405e-05, "epoch": 1.152, "percentage": 16.48, "elapsed_time": "1:50:56", "remaining_time": "9:22:08"} +{"current_steps": 91, "total_steps": 546, "loss": 0.467, "lr": 3.947177284909461e-05, "epoch": 1.1648, "percentage": 16.67, "elapsed_time": "1:52:01", "remaining_time": "9:20:09"} +{"current_steps": 92, "total_steps": 546, "loss": 0.4342, "lr": 3.944215838523688e-05, "epoch": 1.1776, "percentage": 16.85, "elapsed_time": "1:53:06", "remaining_time": "9:18:08"} +{"current_steps": 93, "total_steps": 546, "loss": 0.456, "lr": 3.9411747982431946e-05, "epoch": 1.1904, "percentage": 17.03, "elapsed_time": "1:54:19", "remaining_time": "9:16:53"} +{"current_steps": 94, "total_steps": 546, "loss": 0.4618, "lr": 3.93805428856457e-05, "epoch": 1.2032, "percentage": 17.22, "elapsed_time": "1:55:26", "remaining_time": "9:15:03"} +{"current_steps": 95, "total_steps": 546, "loss": 0.4565, "lr": 3.934854437237786e-05, "epoch": 1.216, "percentage": 17.4, "elapsed_time": "1:56:37", "remaining_time": "9:13:38"} +{"current_steps": 96, "total_steps": 546, "loss": 0.4681, "lr": 3.931575375260967e-05, "epoch": 1.2288000000000001, "percentage": 17.58, "elapsed_time": "1:57:42", "remaining_time": "9:11:44"} +{"current_steps": 97, "total_steps": 546, "loss": 0.4657, "lr": 3.9282172368750296e-05, "epoch": 1.2416, "percentage": 17.77, "elapsed_time": "1:58:58", "remaining_time": "9:10:42"} +{"current_steps": 98, "total_steps": 546, "loss": 0.4728, "lr": 3.924780159558183e-05, "epoch": 1.2544, "percentage": 17.95, "elapsed_time": "2:00:12", "remaining_time": "9:09:29"} +{"current_steps": 99, "total_steps": 546, "loss": 0.4464, "lr": 3.921264284020303e-05, "epoch": 1.2671999999999999, "percentage": 18.13, "elapsed_time": "2:01:21", "remaining_time": "9:07:58"} +{"current_steps": 100, "total_steps": 546, "loss": 0.4781, "lr": 3.917669754197172e-05, "epoch": 1.28, "percentage": 18.32, "elapsed_time": "2:02:36", "remaining_time": "9:06:51"} +{"current_steps": 101, "total_steps": 546, "loss": 0.4802, "lr": 3.913996717244586e-05, "epoch": 1.2928, "percentage": 18.5, "elapsed_time": "2:03:46", "remaining_time": "9:05:20"} +{"current_steps": 102, "total_steps": 546, "loss": 0.4515, "lr": 3.91024532353233e-05, "epoch": 1.3056, "percentage": 18.68, "elapsed_time": "2:05:03", "remaining_time": "9:04:21"} +{"current_steps": 103, "total_steps": 546, "loss": 0.4618, "lr": 3.906415726638019e-05, "epoch": 1.3184, "percentage": 18.86, "elapsed_time": "2:06:24", "remaining_time": "9:03:40"} +{"current_steps": 104, "total_steps": 546, "loss": 0.4485, "lr": 3.902508083340819e-05, "epoch": 1.3312, "percentage": 19.05, "elapsed_time": "2:07:29", "remaining_time": "9:01:52"} +{"current_steps": 105, "total_steps": 546, "loss": 0.4592, "lr": 3.898522553615019e-05, "epoch": 1.3439999999999999, "percentage": 19.23, "elapsed_time": "2:08:43", "remaining_time": "9:00:37"} +{"current_steps": 106, "total_steps": 546, "loss": 0.485, "lr": 3.8944593006234875e-05, "epoch": 1.3568, "percentage": 19.41, "elapsed_time": "2:09:56", "remaining_time": "8:59:21"} +{"current_steps": 107, "total_steps": 546, "loss": 0.4613, "lr": 3.890318490710991e-05, "epoch": 1.3696, "percentage": 19.6, "elapsed_time": "2:11:12", "remaining_time": "8:58:18"} +{"current_steps": 108, "total_steps": 546, "loss": 0.4298, "lr": 3.8861002933973864e-05, "epoch": 1.3824, "percentage": 19.78, "elapsed_time": "2:12:27", "remaining_time": "8:57:13"} +{"current_steps": 109, "total_steps": 546, "loss": 0.4503, "lr": 3.881804881370678e-05, "epoch": 1.3952, "percentage": 19.96, "elapsed_time": "2:13:48", "remaining_time": "8:56:29"} +{"current_steps": 110, "total_steps": 546, "loss": 0.446, "lr": 3.877432430479948e-05, "epoch": 1.408, "percentage": 20.15, "elapsed_time": "2:15:01", "remaining_time": "8:55:12"} +{"current_steps": 111, "total_steps": 546, "loss": 0.4561, "lr": 3.872983119728159e-05, "epoch": 1.4208, "percentage": 20.33, "elapsed_time": "2:16:13", "remaining_time": "8:53:51"} +{"current_steps": 112, "total_steps": 546, "loss": 0.4322, "lr": 3.868457131264827e-05, "epoch": 1.4336, "percentage": 20.51, "elapsed_time": "2:17:22", "remaining_time": "8:52:20"} +{"current_steps": 113, "total_steps": 546, "loss": 0.4494, "lr": 3.863854650378561e-05, "epoch": 1.4464000000000001, "percentage": 20.7, "elapsed_time": "2:18:33", "remaining_time": "8:50:55"} +{"current_steps": 114, "total_steps": 546, "loss": 0.4782, "lr": 3.85917586548948e-05, "epoch": 1.4592, "percentage": 20.88, "elapsed_time": "2:19:41", "remaining_time": "8:49:22"} +{"current_steps": 115, "total_steps": 546, "loss": 0.4328, "lr": 3.8544209681414974e-05, "epoch": 1.472, "percentage": 21.06, "elapsed_time": "2:20:54", "remaining_time": "8:48:05"} +{"current_steps": 116, "total_steps": 546, "loss": 0.4615, "lr": 3.849590152994482e-05, "epoch": 1.4848, "percentage": 21.25, "elapsed_time": "2:22:07", "remaining_time": "8:46:49"} +{"current_steps": 117, "total_steps": 546, "loss": 0.4351, "lr": 3.844683617816288e-05, "epoch": 1.4976, "percentage": 21.43, "elapsed_time": "2:23:33", "remaining_time": "8:46:21"} +{"current_steps": 118, "total_steps": 546, "loss": 0.4355, "lr": 3.839701563474655e-05, "epoch": 1.5104, "percentage": 21.61, "elapsed_time": "2:24:43", "remaining_time": "8:44:56"} +{"current_steps": 119, "total_steps": 546, "loss": 0.4321, "lr": 3.8346441939289894e-05, "epoch": 1.5232, "percentage": 21.79, "elapsed_time": "2:25:59", "remaining_time": "8:43:52"} +{"current_steps": 120, "total_steps": 546, "loss": 0.4418, "lr": 3.829511716222016e-05, "epoch": 1.536, "percentage": 21.98, "elapsed_time": "2:27:13", "remaining_time": "8:42:40"} +{"current_steps": 121, "total_steps": 546, "loss": 0.4563, "lr": 3.824304340471292e-05, "epoch": 1.5488, "percentage": 22.16, "elapsed_time": "2:28:21", "remaining_time": "8:41:05"} +{"current_steps": 122, "total_steps": 546, "loss": 0.4384, "lr": 3.819022279860618e-05, "epoch": 1.5615999999999999, "percentage": 22.34, "elapsed_time": "2:29:39", "remaining_time": "8:40:07"} +{"current_steps": 123, "total_steps": 546, "loss": 0.4326, "lr": 3.813665750631303e-05, "epoch": 1.5744, "percentage": 22.53, "elapsed_time": "2:30:54", "remaining_time": "8:38:58"} +{"current_steps": 124, "total_steps": 546, "loss": 0.4396, "lr": 3.80823497207331e-05, "epoch": 1.5872000000000002, "percentage": 22.71, "elapsed_time": "2:31:59", "remaining_time": "8:37:14"} +{"current_steps": 125, "total_steps": 546, "loss": 0.4708, "lr": 3.802730166516285e-05, "epoch": 1.6, "percentage": 22.89, "elapsed_time": "2:33:01", "remaining_time": "8:35:24"} +{"current_steps": 126, "total_steps": 546, "loss": 0.4474, "lr": 3.79715155932045e-05, "epoch": 1.6128, "percentage": 23.08, "elapsed_time": "2:34:19", "remaining_time": "8:34:25"} +{"current_steps": 127, "total_steps": 546, "loss": 0.4642, "lr": 3.79149937886738e-05, "epoch": 1.6256, "percentage": 23.26, "elapsed_time": "2:35:35", "remaining_time": "8:33:18"} +{"current_steps": 128, "total_steps": 546, "loss": 0.4276, "lr": 3.78577385655065e-05, "epoch": 1.6383999999999999, "percentage": 23.44, "elapsed_time": "2:36:43", "remaining_time": "8:31:47"} +{"current_steps": 129, "total_steps": 546, "loss": 0.4495, "lr": 3.779975226766367e-05, "epoch": 1.6512, "percentage": 23.63, "elapsed_time": "2:37:59", "remaining_time": "8:30:42"} +{"current_steps": 130, "total_steps": 546, "loss": 0.4378, "lr": 3.774103726903569e-05, "epoch": 1.6640000000000001, "percentage": 23.81, "elapsed_time": "2:39:08", "remaining_time": "8:29:13"} +{"current_steps": 131, "total_steps": 546, "loss": 0.4512, "lr": 3.768159597334508e-05, "epoch": 1.6768, "percentage": 23.99, "elapsed_time": "2:40:18", "remaining_time": "8:27:51"} +{"current_steps": 132, "total_steps": 546, "loss": 0.432, "lr": 3.762143081404812e-05, "epoch": 1.6896, "percentage": 24.18, "elapsed_time": "2:41:33", "remaining_time": "8:26:41"} +{"current_steps": 133, "total_steps": 546, "loss": 0.4653, "lr": 3.756054425423521e-05, "epoch": 1.7024, "percentage": 24.36, "elapsed_time": "2:42:42", "remaining_time": "8:25:14"} +{"current_steps": 134, "total_steps": 546, "loss": 0.4542, "lr": 3.749893878653003e-05, "epoch": 1.7151999999999998, "percentage": 24.54, "elapsed_time": "2:43:56", "remaining_time": "8:24:02"} +{"current_steps": 135, "total_steps": 546, "loss": 0.4349, "lr": 3.743661693298749e-05, "epoch": 1.728, "percentage": 24.73, "elapsed_time": "2:45:01", "remaining_time": "8:22:25"} +{"current_steps": 136, "total_steps": 546, "loss": 0.4731, "lr": 3.737358124499048e-05, "epoch": 1.7408000000000001, "percentage": 24.91, "elapsed_time": "2:46:08", "remaining_time": "8:20:50"} +{"current_steps": 137, "total_steps": 546, "loss": 0.4731, "lr": 3.730983430314546e-05, "epoch": 1.7536, "percentage": 25.09, "elapsed_time": "2:47:31", "remaining_time": "8:20:08"} +{"current_steps": 138, "total_steps": 546, "loss": 0.4522, "lr": 3.7245378717176746e-05, "epoch": 1.7664, "percentage": 25.27, "elapsed_time": "2:48:42", "remaining_time": "8:18:46"} +{"current_steps": 139, "total_steps": 546, "loss": 0.4279, "lr": 3.7180217125819724e-05, "epoch": 1.7792, "percentage": 25.46, "elapsed_time": "2:49:58", "remaining_time": "8:17:41"} +{"current_steps": 140, "total_steps": 546, "loss": 0.4285, "lr": 3.711435219671281e-05, "epoch": 1.792, "percentage": 25.64, "elapsed_time": "2:51:15", "remaining_time": "8:16:39"} +{"current_steps": 141, "total_steps": 546, "loss": 0.4415, "lr": 3.704778662628822e-05, "epoch": 1.8048, "percentage": 25.82, "elapsed_time": "2:52:22", "remaining_time": "8:15:05"} +{"current_steps": 142, "total_steps": 546, "loss": 0.4497, "lr": 3.69805231396616e-05, "epoch": 1.8176, "percentage": 26.01, "elapsed_time": "2:53:36", "remaining_time": "8:13:55"} +{"current_steps": 143, "total_steps": 546, "loss": 0.48, "lr": 3.691256449052046e-05, "epoch": 1.8304, "percentage": 26.19, "elapsed_time": "2:54:49", "remaining_time": "8:12:40"} +{"current_steps": 144, "total_steps": 546, "loss": 0.44, "lr": 3.684391346101144e-05, "epoch": 1.8432, "percentage": 26.37, "elapsed_time": "2:56:05", "remaining_time": "8:11:35"} +{"current_steps": 145, "total_steps": 546, "loss": 0.4479, "lr": 3.677457286162642e-05, "epoch": 1.8559999999999999, "percentage": 26.56, "elapsed_time": "2:57:19", "remaining_time": "8:10:24"} +{"current_steps": 146, "total_steps": 546, "loss": 0.4406, "lr": 3.6704545531087446e-05, "epoch": 1.8688, "percentage": 26.74, "elapsed_time": "2:58:22", "remaining_time": "8:08:42"} +{"current_steps": 147, "total_steps": 546, "loss": 0.423, "lr": 3.663383433623052e-05, "epoch": 1.8816000000000002, "percentage": 26.92, "elapsed_time": "2:59:24", "remaining_time": "8:06:59"} +{"current_steps": 148, "total_steps": 546, "loss": 0.4474, "lr": 3.6562442171888256e-05, "epoch": 1.8944, "percentage": 27.11, "elapsed_time": "3:00:47", "remaining_time": "8:06:12"} +{"current_steps": 149, "total_steps": 546, "loss": 0.4793, "lr": 3.6490371960771345e-05, "epoch": 1.9072, "percentage": 27.29, "elapsed_time": "3:02:08", "remaining_time": "8:05:17"} +{"current_steps": 150, "total_steps": 546, "loss": 0.4507, "lr": 3.641762665334889e-05, "epoch": 1.92, "percentage": 27.47, "elapsed_time": "3:03:16", "remaining_time": "8:03:52"} +{"current_steps": 151, "total_steps": 546, "loss": 0.461, "lr": 3.6344209227727676e-05, "epoch": 1.9327999999999999, "percentage": 27.66, "elapsed_time": "3:04:35", "remaining_time": "8:02:52"} +{"current_steps": 152, "total_steps": 546, "loss": 0.4475, "lr": 3.6270122689530176e-05, "epoch": 1.9456, "percentage": 27.84, "elapsed_time": "3:05:44", "remaining_time": "8:01:28"} +{"current_steps": 153, "total_steps": 546, "loss": 0.4499, "lr": 3.619537007177156e-05, "epoch": 1.9584000000000001, "percentage": 28.02, "elapsed_time": "3:06:55", "remaining_time": "8:00:08"} +{"current_steps": 154, "total_steps": 546, "loss": 0.4409, "lr": 3.611995443473551e-05, "epoch": 1.9712, "percentage": 28.21, "elapsed_time": "3:08:07", "remaining_time": "7:58:51"} +{"current_steps": 155, "total_steps": 546, "loss": 0.4558, "lr": 3.604387886584891e-05, "epoch": 1.984, "percentage": 28.39, "elapsed_time": "3:09:30", "remaining_time": "7:58:03"} +{"current_steps": 156, "total_steps": 546, "loss": 0.458, "lr": 3.596714647955549e-05, "epoch": 1.9968, "percentage": 28.57, "elapsed_time": "3:10:39", "remaining_time": "7:56:38"} +{"current_steps": 157, "total_steps": 546, "loss": 0.7147, "lr": 3.588976041718831e-05, "epoch": 2.0096, "percentage": 28.75, "elapsed_time": "3:12:36", "remaining_time": "7:57:12"} +{"current_steps": 158, "total_steps": 546, "loss": 0.3494, "lr": 3.5811723846841136e-05, "epoch": 2.0224, "percentage": 28.94, "elapsed_time": "3:14:00", "remaining_time": "7:56:26"} +{"current_steps": 159, "total_steps": 546, "loss": 0.3455, "lr": 3.573303996323879e-05, "epoch": 2.0352, "percentage": 29.12, "elapsed_time": "3:15:16", "remaining_time": "7:55:16"} +{"current_steps": 160, "total_steps": 546, "loss": 0.3768, "lr": 3.5653711987606295e-05, "epoch": 2.048, "percentage": 29.3, "elapsed_time": "3:16:37", "remaining_time": "7:54:21"} +{"current_steps": 161, "total_steps": 546, "loss": 0.3405, "lr": 3.557374316753707e-05, "epoch": 2.0608, "percentage": 29.49, "elapsed_time": "3:17:57", "remaining_time": "7:53:23"} +{"current_steps": 162, "total_steps": 546, "loss": 0.3673, "lr": 3.549313677685993e-05, "epoch": 2.0736, "percentage": 29.67, "elapsed_time": "3:19:03", "remaining_time": "7:51:51"} +{"current_steps": 163, "total_steps": 546, "loss": 0.356, "lr": 3.5411896115505093e-05, "epoch": 2.0864, "percentage": 29.85, "elapsed_time": "3:20:09", "remaining_time": "7:50:18"} +{"current_steps": 164, "total_steps": 546, "loss": 0.3258, "lr": 3.5330024509369044e-05, "epoch": 2.0992, "percentage": 30.04, "elapsed_time": "3:21:15", "remaining_time": "7:48:46"} +{"current_steps": 165, "total_steps": 546, "loss": 0.3587, "lr": 3.5247525310178416e-05, "epoch": 2.112, "percentage": 30.22, "elapsed_time": "3:22:23", "remaining_time": "7:47:20"} +{"current_steps": 166, "total_steps": 546, "loss": 0.3255, "lr": 3.516440189535276e-05, "epoch": 2.1248, "percentage": 30.4, "elapsed_time": "3:23:31", "remaining_time": "7:45:53"} +{"current_steps": 167, "total_steps": 546, "loss": 0.353, "lr": 3.508065766786626e-05, "epoch": 2.1376, "percentage": 30.59, "elapsed_time": "3:24:49", "remaining_time": "7:44:50"} +{"current_steps": 168, "total_steps": 546, "loss": 0.3327, "lr": 3.499629605610846e-05, "epoch": 2.1504, "percentage": 30.77, "elapsed_time": "3:25:59", "remaining_time": "7:43:28"} +{"current_steps": 169, "total_steps": 546, "loss": 0.3802, "lr": 3.491132051374386e-05, "epoch": 2.1632, "percentage": 30.95, "elapsed_time": "3:27:18", "remaining_time": "7:42:27"} +{"current_steps": 170, "total_steps": 546, "loss": 0.3033, "lr": 3.482573451957057e-05, "epoch": 2.176, "percentage": 31.14, "elapsed_time": "3:28:16", "remaining_time": "7:40:39"} +{"current_steps": 171, "total_steps": 546, "loss": 0.3535, "lr": 3.4739541577377874e-05, "epoch": 2.1888, "percentage": 31.32, "elapsed_time": "3:29:31", "remaining_time": "7:39:28"} +{"current_steps": 172, "total_steps": 546, "loss": 0.3295, "lr": 3.4652745215802776e-05, "epoch": 2.2016, "percentage": 31.5, "elapsed_time": "3:30:44", "remaining_time": "7:38:13"} +{"current_steps": 173, "total_steps": 546, "loss": 0.3446, "lr": 3.456534898818556e-05, "epoch": 2.2144, "percentage": 31.68, "elapsed_time": "3:31:57", "remaining_time": "7:36:59"} +{"current_steps": 174, "total_steps": 546, "loss": 0.3549, "lr": 3.447735647242432e-05, "epoch": 2.2272, "percentage": 31.87, "elapsed_time": "3:33:10", "remaining_time": "7:35:46"} +{"current_steps": 175, "total_steps": 546, "loss": 0.3249, "lr": 3.4388771270828484e-05, "epoch": 2.24, "percentage": 32.05, "elapsed_time": "3:34:24", "remaining_time": "7:34:33"} +{"current_steps": 176, "total_steps": 546, "loss": 0.3663, "lr": 3.429959700997133e-05, "epoch": 2.2528, "percentage": 32.23, "elapsed_time": "3:35:33", "remaining_time": "7:33:09"} +{"current_steps": 177, "total_steps": 546, "loss": 0.31, "lr": 3.4209837340541526e-05, "epoch": 2.2656, "percentage": 32.42, "elapsed_time": "3:36:49", "remaining_time": "7:32:02"} +{"current_steps": 178, "total_steps": 546, "loss": 0.3417, "lr": 3.411949593719367e-05, "epoch": 2.2784, "percentage": 32.6, "elapsed_time": "3:38:13", "remaining_time": "7:31:08"} +{"current_steps": 179, "total_steps": 546, "loss": 0.34, "lr": 3.4028576498397875e-05, "epoch": 2.2912, "percentage": 32.78, "elapsed_time": "3:39:31", "remaining_time": "7:30:06"} +{"current_steps": 180, "total_steps": 546, "loss": 0.3339, "lr": 3.3937082746288314e-05, "epoch": 2.304, "percentage": 32.97, "elapsed_time": "3:40:48", "remaining_time": "7:28:58"} +{"current_steps": 181, "total_steps": 546, "loss": 0.3125, "lr": 3.384501842651088e-05, "epoch": 2.3168, "percentage": 33.15, "elapsed_time": "3:42:00", "remaining_time": "7:27:41"} +{"current_steps": 182, "total_steps": 546, "loss": 0.3294, "lr": 3.3752387308069844e-05, "epoch": 2.3296, "percentage": 33.33, "elapsed_time": "3:43:15", "remaining_time": "7:26:31"} +{"current_steps": 183, "total_steps": 546, "loss": 0.3279, "lr": 3.365919318317352e-05, "epoch": 2.3424, "percentage": 33.52, "elapsed_time": "3:44:23", "remaining_time": "7:25:06"} +{"current_steps": 184, "total_steps": 546, "loss": 0.3562, "lr": 3.356543986707906e-05, "epoch": 2.3552, "percentage": 33.7, "elapsed_time": "3:45:43", "remaining_time": "7:24:04"} +{"current_steps": 185, "total_steps": 546, "loss": 0.3049, "lr": 3.347113119793623e-05, "epoch": 2.368, "percentage": 33.88, "elapsed_time": "3:46:48", "remaining_time": "7:22:34"} +{"current_steps": 186, "total_steps": 546, "loss": 0.3621, "lr": 3.337627103663029e-05, "epoch": 2.3808, "percentage": 34.07, "elapsed_time": "3:48:11", "remaining_time": "7:21:38"} +{"current_steps": 187, "total_steps": 546, "loss": 0.3571, "lr": 3.328086326662395e-05, "epoch": 2.3936, "percentage": 34.25, "elapsed_time": "3:49:26", "remaining_time": "7:20:27"} +{"current_steps": 188, "total_steps": 546, "loss": 0.3397, "lr": 3.3184911793798354e-05, "epoch": 2.4064, "percentage": 34.43, "elapsed_time": "3:50:30", "remaining_time": "7:18:57"} +{"current_steps": 189, "total_steps": 546, "loss": 0.3497, "lr": 3.3088420546293216e-05, "epoch": 2.4192, "percentage": 34.62, "elapsed_time": "3:51:45", "remaining_time": "7:17:46"} +{"current_steps": 190, "total_steps": 546, "loss": 0.3475, "lr": 3.2991393474345963e-05, "epoch": 2.432, "percentage": 34.8, "elapsed_time": "3:52:52", "remaining_time": "7:16:20"} +{"current_steps": 191, "total_steps": 546, "loss": 0.3443, "lr": 3.2893834550130064e-05, "epoch": 2.4448, "percentage": 34.98, "elapsed_time": "3:54:07", "remaining_time": "7:15:09"} +{"current_steps": 192, "total_steps": 546, "loss": 0.3255, "lr": 3.279574776759237e-05, "epoch": 2.4576000000000002, "percentage": 35.16, "elapsed_time": "3:55:21", "remaining_time": "7:13:56"} +{"current_steps": 193, "total_steps": 546, "loss": 0.3641, "lr": 3.269713714228963e-05, "epoch": 2.4704, "percentage": 35.35, "elapsed_time": "3:56:44", "remaining_time": "7:13:00"} +{"current_steps": 194, "total_steps": 546, "loss": 0.3043, "lr": 3.259800671122412e-05, "epoch": 2.4832, "percentage": 35.53, "elapsed_time": "3:57:47", "remaining_time": "7:11:27"} +{"current_steps": 195, "total_steps": 546, "loss": 0.3654, "lr": 3.249836053267832e-05, "epoch": 2.496, "percentage": 35.71, "elapsed_time": "3:59:02", "remaining_time": "7:10:16"} +{"current_steps": 196, "total_steps": 546, "loss": 0.3679, "lr": 3.239820268604881e-05, "epoch": 2.5088, "percentage": 35.9, "elapsed_time": "4:00:09", "remaining_time": "7:08:51"} +{"current_steps": 197, "total_steps": 546, "loss": 0.3118, "lr": 3.2297537271679246e-05, "epoch": 2.5216, "percentage": 36.08, "elapsed_time": "4:01:16", "remaining_time": "7:07:25"} +{"current_steps": 198, "total_steps": 546, "loss": 0.345, "lr": 3.219636841069254e-05, "epoch": 2.5343999999999998, "percentage": 36.26, "elapsed_time": "4:02:23", "remaining_time": "7:06:01"} +{"current_steps": 199, "total_steps": 546, "loss": 0.3382, "lr": 3.2094700244822076e-05, "epoch": 2.5472, "percentage": 36.45, "elapsed_time": "4:03:37", "remaining_time": "7:04:48"} +{"current_steps": 200, "total_steps": 546, "loss": 0.3603, "lr": 3.19925369362422e-05, "epoch": 2.56, "percentage": 36.63, "elapsed_time": "4:04:40", "remaining_time": "7:03:17"} +{"current_steps": 201, "total_steps": 546, "loss": 0.3222, "lr": 3.1889882667397824e-05, "epoch": 2.5728, "percentage": 36.81, "elapsed_time": "4:05:40", "remaining_time": "7:01:41"} +{"current_steps": 202, "total_steps": 546, "loss": 0.3231, "lr": 3.178674164083319e-05, "epoch": 2.5856, "percentage": 37.0, "elapsed_time": "4:06:54", "remaining_time": "7:00:28"} +{"current_steps": 203, "total_steps": 546, "loss": 0.3394, "lr": 3.1683118079019796e-05, "epoch": 2.5984, "percentage": 37.18, "elapsed_time": "4:08:06", "remaining_time": "6:59:13"} +{"current_steps": 204, "total_steps": 546, "loss": 0.3333, "lr": 3.157901622418361e-05, "epoch": 2.6112, "percentage": 37.36, "elapsed_time": "4:09:19", "remaining_time": "6:57:58"} +{"current_steps": 205, "total_steps": 546, "loss": 0.3691, "lr": 3.147444033813131e-05, "epoch": 2.624, "percentage": 37.55, "elapsed_time": "4:10:44", "remaining_time": "6:57:04"} +{"current_steps": 206, "total_steps": 546, "loss": 0.3465, "lr": 3.136939470207587e-05, "epoch": 2.6368, "percentage": 37.73, "elapsed_time": "4:12:00", "remaining_time": "6:55:56"} +{"current_steps": 207, "total_steps": 546, "loss": 0.3537, "lr": 3.126388361646128e-05, "epoch": 2.6496, "percentage": 37.91, "elapsed_time": "4:13:14", "remaining_time": "6:54:44"} +{"current_steps": 208, "total_steps": 546, "loss": 0.327, "lr": 3.115791140078646e-05, "epoch": 2.6624, "percentage": 38.1, "elapsed_time": "4:14:35", "remaining_time": "6:53:42"} +{"current_steps": 209, "total_steps": 546, "loss": 0.3575, "lr": 3.105148239342846e-05, "epoch": 2.6752000000000002, "percentage": 38.28, "elapsed_time": "4:15:52", "remaining_time": "6:52:34"} +{"current_steps": 210, "total_steps": 546, "loss": 0.3435, "lr": 3.0944600951464854e-05, "epoch": 2.6879999999999997, "percentage": 38.46, "elapsed_time": "4:16:59", "remaining_time": "6:51:11"} +{"current_steps": 211, "total_steps": 546, "loss": 0.3352, "lr": 3.083727145049533e-05, "epoch": 2.7008, "percentage": 38.64, "elapsed_time": "4:18:09", "remaining_time": "6:49:52"} +{"current_steps": 212, "total_steps": 546, "loss": 0.3412, "lr": 3.0729498284462604e-05, "epoch": 2.7136, "percentage": 38.83, "elapsed_time": "4:19:27", "remaining_time": "6:48:45"} +{"current_steps": 213, "total_steps": 546, "loss": 0.3177, "lr": 3.0621285865472506e-05, "epoch": 2.7264, "percentage": 39.01, "elapsed_time": "4:20:38", "remaining_time": "6:47:29"} +{"current_steps": 214, "total_steps": 546, "loss": 0.3613, "lr": 3.051263862361334e-05, "epoch": 2.7392, "percentage": 39.19, "elapsed_time": "4:21:59", "remaining_time": "6:46:27"} +{"current_steps": 215, "total_steps": 546, "loss": 0.358, "lr": 3.040356100677458e-05, "epoch": 2.752, "percentage": 39.38, "elapsed_time": "4:23:14", "remaining_time": "6:45:15"} +{"current_steps": 216, "total_steps": 546, "loss": 0.3335, "lr": 3.0294057480464722e-05, "epoch": 2.7648, "percentage": 39.56, "elapsed_time": "4:24:12", "remaining_time": "6:43:39"} +{"current_steps": 217, "total_steps": 546, "loss": 0.364, "lr": 3.018413252762849e-05, "epoch": 2.7776, "percentage": 39.74, "elapsed_time": "4:25:28", "remaining_time": "6:42:29"} +{"current_steps": 218, "total_steps": 546, "loss": 0.376, "lr": 3.0073790648463324e-05, "epoch": 2.7904, "percentage": 39.93, "elapsed_time": "4:26:46", "remaining_time": "6:41:22"} +{"current_steps": 219, "total_steps": 546, "loss": 0.3125, "lr": 2.9963036360235116e-05, "epoch": 2.8032, "percentage": 40.11, "elapsed_time": "4:27:48", "remaining_time": "6:39:52"} +{"current_steps": 220, "total_steps": 546, "loss": 0.3193, "lr": 2.9851874197093305e-05, "epoch": 2.816, "percentage": 40.29, "elapsed_time": "4:29:11", "remaining_time": "6:38:54"} +{"current_steps": 221, "total_steps": 546, "loss": 0.4042, "lr": 2.974030870988526e-05, "epoch": 2.8288, "percentage": 40.48, "elapsed_time": "4:30:22", "remaining_time": "6:37:36"} +{"current_steps": 222, "total_steps": 546, "loss": 0.3474, "lr": 2.9628344465969937e-05, "epoch": 2.8416, "percentage": 40.66, "elapsed_time": "4:31:30", "remaining_time": "6:36:15"} +{"current_steps": 223, "total_steps": 546, "loss": 0.3425, "lr": 2.951598604903094e-05, "epoch": 2.8544, "percentage": 40.84, "elapsed_time": "4:32:40", "remaining_time": "6:34:57"} +{"current_steps": 224, "total_steps": 546, "loss": 0.3663, "lr": 2.9403238058888838e-05, "epoch": 2.8672, "percentage": 41.03, "elapsed_time": "4:33:58", "remaining_time": "6:33:50"} +{"current_steps": 225, "total_steps": 546, "loss": 0.329, "lr": 2.929010511131286e-05, "epoch": 2.88, "percentage": 41.21, "elapsed_time": "4:35:15", "remaining_time": "6:32:42"} +{"current_steps": 226, "total_steps": 546, "loss": 0.3734, "lr": 2.9176591837831957e-05, "epoch": 2.8928000000000003, "percentage": 41.39, "elapsed_time": "4:36:32", "remaining_time": "6:31:33"} +{"current_steps": 227, "total_steps": 546, "loss": 0.3695, "lr": 2.906270288554514e-05, "epoch": 2.9055999999999997, "percentage": 41.58, "elapsed_time": "4:37:47", "remaining_time": "6:30:21"} +{"current_steps": 228, "total_steps": 546, "loss": 0.3716, "lr": 2.8948442916931302e-05, "epoch": 2.9184, "percentage": 41.76, "elapsed_time": "4:38:54", "remaining_time": "6:29:00"} +{"current_steps": 229, "total_steps": 546, "loss": 0.3496, "lr": 2.8833816609658285e-05, "epoch": 2.9312, "percentage": 41.94, "elapsed_time": "4:40:08", "remaining_time": "6:27:47"} +{"current_steps": 230, "total_steps": 546, "loss": 0.3472, "lr": 2.8718828656391408e-05, "epoch": 2.944, "percentage": 42.12, "elapsed_time": "4:41:10", "remaining_time": "6:26:19"} +{"current_steps": 231, "total_steps": 546, "loss": 0.3311, "lr": 2.8603483764601346e-05, "epoch": 2.9568, "percentage": 42.31, "elapsed_time": "4:42:26", "remaining_time": "6:25:08"} +{"current_steps": 232, "total_steps": 546, "loss": 0.3184, "lr": 2.84877866563714e-05, "epoch": 2.9696, "percentage": 42.49, "elapsed_time": "4:43:46", "remaining_time": "6:24:04"} +{"current_steps": 233, "total_steps": 546, "loss": 0.356, "lr": 2.8371742068204234e-05, "epoch": 2.9824, "percentage": 42.67, "elapsed_time": "4:45:02", "remaining_time": "6:22:54"} +{"current_steps": 234, "total_steps": 546, "loss": 0.3454, "lr": 2.8255354750827885e-05, "epoch": 2.9952, "percentage": 42.86, "elapsed_time": "4:46:19", "remaining_time": "6:21:45"} +{"current_steps": 235, "total_steps": 546, "loss": 0.5875, "lr": 2.8138629469001348e-05, "epoch": 3.008, "percentage": 43.04, "elapsed_time": "4:48:37", "remaining_time": "6:21:57"} +{"current_steps": 236, "total_steps": 546, "loss": 0.2239, "lr": 2.802157100131947e-05, "epoch": 3.0208, "percentage": 43.22, "elapsed_time": "4:49:45", "remaining_time": "6:20:36"} +{"current_steps": 237, "total_steps": 546, "loss": 0.2601, "lr": 2.7904184140017337e-05, "epoch": 3.0336, "percentage": 43.41, "elapsed_time": "4:50:56", "remaining_time": "6:19:19"} +{"current_steps": 238, "total_steps": 546, "loss": 0.2515, "lr": 2.7786473690774083e-05, "epoch": 3.0464, "percentage": 43.59, "elapsed_time": "4:52:06", "remaining_time": "6:18:01"} +{"current_steps": 239, "total_steps": 546, "loss": 0.2436, "lr": 2.766844447251614e-05, "epoch": 3.0592, "percentage": 43.77, "elapsed_time": "4:53:23", "remaining_time": "6:16:52"} +{"current_steps": 240, "total_steps": 546, "loss": 0.2405, "lr": 2.7550101317219976e-05, "epoch": 3.072, "percentage": 43.96, "elapsed_time": "4:54:39", "remaining_time": "6:15:41"} +{"current_steps": 241, "total_steps": 546, "loss": 0.2338, "lr": 2.7431449069714254e-05, "epoch": 3.0848, "percentage": 44.14, "elapsed_time": "4:55:51", "remaining_time": "6:14:25"} +{"current_steps": 242, "total_steps": 546, "loss": 0.2527, "lr": 2.7312492587481535e-05, "epoch": 3.0976, "percentage": 44.32, "elapsed_time": "4:57:12", "remaining_time": "6:13:21"} +{"current_steps": 243, "total_steps": 546, "loss": 0.2535, "lr": 2.7193236740459358e-05, "epoch": 3.1104, "percentage": 44.51, "elapsed_time": "4:58:27", "remaining_time": "6:12:09"} +{"current_steps": 244, "total_steps": 546, "loss": 0.2277, "lr": 2.707368641084092e-05, "epoch": 3.1232, "percentage": 44.69, "elapsed_time": "4:59:30", "remaining_time": "6:10:42"} +{"current_steps": 245, "total_steps": 546, "loss": 0.2519, "lr": 2.695384649287518e-05, "epoch": 3.136, "percentage": 44.87, "elapsed_time": "5:00:34", "remaining_time": "6:09:16"} +{"current_steps": 246, "total_steps": 546, "loss": 0.205, "lr": 2.6833721892666513e-05, "epoch": 3.1488, "percentage": 45.05, "elapsed_time": "5:01:40", "remaining_time": "6:07:54"} +{"current_steps": 247, "total_steps": 546, "loss": 0.2811, "lr": 2.6713317527973837e-05, "epoch": 3.1616, "percentage": 45.24, "elapsed_time": "5:03:02", "remaining_time": "6:06:50"} +{"current_steps": 248, "total_steps": 546, "loss": 0.218, "lr": 2.659263832800929e-05, "epoch": 3.1744, "percentage": 45.42, "elapsed_time": "5:04:16", "remaining_time": "6:05:37"} +{"current_steps": 249, "total_steps": 546, "loss": 0.2448, "lr": 2.647168923323646e-05, "epoch": 3.1872, "percentage": 45.6, "elapsed_time": "5:05:31", "remaining_time": "6:04:25"} +{"current_steps": 250, "total_steps": 546, "loss": 0.2132, "lr": 2.635047519516809e-05, "epoch": 3.2, "percentage": 45.79, "elapsed_time": "5:06:44", "remaining_time": "6:03:10"} +{"current_steps": 251, "total_steps": 546, "loss": 0.2365, "lr": 2.6229001176163397e-05, "epoch": 3.2128, "percentage": 45.97, "elapsed_time": "5:08:03", "remaining_time": "6:02:03"} +{"current_steps": 252, "total_steps": 546, "loss": 0.2582, "lr": 2.6107272149224915e-05, "epoch": 3.2256, "percentage": 46.15, "elapsed_time": "5:09:14", "remaining_time": "6:00:46"} +{"current_steps": 253, "total_steps": 546, "loss": 0.2479, "lr": 2.5985293097794884e-05, "epoch": 3.2384, "percentage": 46.34, "elapsed_time": "5:10:29", "remaining_time": "5:59:35"} +{"current_steps": 254, "total_steps": 546, "loss": 0.2365, "lr": 2.586306901555128e-05, "epoch": 3.2512, "percentage": 46.52, "elapsed_time": "5:11:40", "remaining_time": "5:58:17"} +{"current_steps": 255, "total_steps": 546, "loss": 0.2091, "lr": 2.5740604906203314e-05, "epoch": 3.2640000000000002, "percentage": 46.7, "elapsed_time": "5:12:48", "remaining_time": "5:56:57"} +{"current_steps": 256, "total_steps": 546, "loss": 0.2552, "lr": 2.5617905783286655e-05, "epoch": 3.2768, "percentage": 46.89, "elapsed_time": "5:13:49", "remaining_time": "5:55:30"} +{"current_steps": 257, "total_steps": 546, "loss": 0.2547, "lr": 2.5494976669958128e-05, "epoch": 3.2896, "percentage": 47.07, "elapsed_time": "5:15:04", "remaining_time": "5:54:18"} +{"current_steps": 258, "total_steps": 546, "loss": 0.2113, "lr": 2.537182259879009e-05, "epoch": 3.3024, "percentage": 47.25, "elapsed_time": "5:16:18", "remaining_time": "5:53:05"} +{"current_steps": 259, "total_steps": 546, "loss": 0.2123, "lr": 2.524844861156443e-05, "epoch": 3.3152, "percentage": 47.44, "elapsed_time": "5:17:23", "remaining_time": "5:51:41"} +{"current_steps": 260, "total_steps": 546, "loss": 0.2495, "lr": 2.512485975906612e-05, "epoch": 3.328, "percentage": 47.62, "elapsed_time": "5:18:33", "remaining_time": "5:50:24"} +{"current_steps": 261, "total_steps": 546, "loss": 0.2656, "lr": 2.5001061100876464e-05, "epoch": 3.3407999999999998, "percentage": 47.8, "elapsed_time": "5:19:57", "remaining_time": "5:49:22"} +{"current_steps": 262, "total_steps": 546, "loss": 0.2013, "lr": 2.487705770516598e-05, "epoch": 3.3536, "percentage": 47.99, "elapsed_time": "5:20:59", "remaining_time": "5:47:56"} +{"current_steps": 263, "total_steps": 546, "loss": 0.2294, "lr": 2.4752854648486865e-05, "epoch": 3.3664, "percentage": 48.17, "elapsed_time": "5:22:18", "remaining_time": "5:46:49"} +{"current_steps": 264, "total_steps": 546, "loss": 0.2391, "lr": 2.462845701556523e-05, "epoch": 3.3792, "percentage": 48.35, "elapsed_time": "5:23:37", "remaining_time": "5:45:41"} +{"current_steps": 265, "total_steps": 546, "loss": 0.2447, "lr": 2.4503869899092893e-05, "epoch": 3.392, "percentage": 48.53, "elapsed_time": "5:24:48", "remaining_time": "5:44:25"} +{"current_steps": 266, "total_steps": 546, "loss": 0.2337, "lr": 2.437909839951891e-05, "epoch": 3.4048, "percentage": 48.72, "elapsed_time": "5:25:52", "remaining_time": "5:43:01"} +{"current_steps": 267, "total_steps": 546, "loss": 0.2639, "lr": 2.4254147624840753e-05, "epoch": 3.4176, "percentage": 48.9, "elapsed_time": "5:27:01", "remaining_time": "5:41:43"} +{"current_steps": 268, "total_steps": 546, "loss": 0.2422, "lr": 2.4129022690395213e-05, "epoch": 3.4304, "percentage": 49.08, "elapsed_time": "5:28:21", "remaining_time": "5:40:36"} +{"current_steps": 269, "total_steps": 546, "loss": 0.2176, "lr": 2.400372871864898e-05, "epoch": 3.4432, "percentage": 49.27, "elapsed_time": "5:29:33", "remaining_time": "5:39:21"} +{"current_steps": 270, "total_steps": 546, "loss": 0.2528, "lr": 2.3878270838988912e-05, "epoch": 3.456, "percentage": 49.45, "elapsed_time": "5:30:50", "remaining_time": "5:38:11"} +{"current_steps": 271, "total_steps": 546, "loss": 0.2289, "lr": 2.3752654187512096e-05, "epoch": 3.4688, "percentage": 49.63, "elapsed_time": "5:32:03", "remaining_time": "5:36:57"} +{"current_steps": 272, "total_steps": 546, "loss": 0.2407, "lr": 2.362688390681551e-05, "epoch": 3.4816, "percentage": 49.82, "elapsed_time": "5:33:16", "remaining_time": "5:35:43"} +{"current_steps": 273, "total_steps": 546, "loss": 0.2779, "lr": 2.3500965145785563e-05, "epoch": 3.4944, "percentage": 50.0, "elapsed_time": "5:34:32", "remaining_time": "5:34:32"} +{"current_steps": 274, "total_steps": 546, "loss": 0.2457, "lr": 2.3374903059387252e-05, "epoch": 3.5072, "percentage": 50.18, "elapsed_time": "5:35:57", "remaining_time": "5:33:30"} +{"current_steps": 275, "total_steps": 546, "loss": 0.2271, "lr": 2.3248702808453146e-05, "epoch": 3.52, "percentage": 50.37, "elapsed_time": "5:37:08", "remaining_time": "5:32:14"} +{"current_steps": 276, "total_steps": 546, "loss": 0.2356, "lr": 2.3122369559472122e-05, "epoch": 3.5328, "percentage": 50.55, "elapsed_time": "5:38:19", "remaining_time": "5:30:58"} +{"current_steps": 277, "total_steps": 546, "loss": 0.2455, "lr": 2.2995908484377827e-05, "epoch": 3.5456, "percentage": 50.73, "elapsed_time": "5:39:30", "remaining_time": "5:29:42"} +{"current_steps": 278, "total_steps": 546, "loss": 0.2197, "lr": 2.2869324760336974e-05, "epoch": 3.5584, "percentage": 50.92, "elapsed_time": "5:40:45", "remaining_time": "5:28:29"} +{"current_steps": 279, "total_steps": 546, "loss": 0.2407, "lr": 2.2742623569537345e-05, "epoch": 3.5712, "percentage": 51.1, "elapsed_time": "5:41:56", "remaining_time": "5:27:13"} +{"current_steps": 280, "total_steps": 546, "loss": 0.2413, "lr": 2.261581009897571e-05, "epoch": 3.584, "percentage": 51.28, "elapsed_time": "5:43:17", "remaining_time": "5:26:07"} +{"current_steps": 281, "total_steps": 546, "loss": 0.2473, "lr": 2.2488889540245414e-05, "epoch": 3.5968, "percentage": 51.47, "elapsed_time": "5:44:35", "remaining_time": "5:24:58"} +{"current_steps": 282, "total_steps": 546, "loss": 0.2156, "lr": 2.2361867089323873e-05, "epoch": 3.6096, "percentage": 51.65, "elapsed_time": "5:45:49", "remaining_time": "5:23:45"} +{"current_steps": 283, "total_steps": 546, "loss": 0.2383, "lr": 2.223474794635985e-05, "epoch": 3.6224, "percentage": 51.83, "elapsed_time": "5:46:57", "remaining_time": "5:22:26"} +{"current_steps": 284, "total_steps": 546, "loss": 0.2189, "lr": 2.2107537315460568e-05, "epoch": 3.6352, "percentage": 52.01, "elapsed_time": "5:48:12", "remaining_time": "5:21:14"} +{"current_steps": 285, "total_steps": 546, "loss": 0.2408, "lr": 2.198024040447865e-05, "epoch": 3.648, "percentage": 52.2, "elapsed_time": "5:49:23", "remaining_time": "5:19:58"} +{"current_steps": 286, "total_steps": 546, "loss": 0.2246, "lr": 2.1852862424798934e-05, "epoch": 3.6608, "percentage": 52.38, "elapsed_time": "5:50:43", "remaining_time": "5:18:50"} +{"current_steps": 287, "total_steps": 546, "loss": 0.2558, "lr": 2.17254085911251e-05, "epoch": 3.6736, "percentage": 52.56, "elapsed_time": "5:52:07", "remaining_time": "5:17:46"} +{"current_steps": 288, "total_steps": 546, "loss": 0.234, "lr": 2.1597884121266215e-05, "epoch": 3.6864, "percentage": 52.75, "elapsed_time": "5:53:13", "remaining_time": "5:16:25"} +{"current_steps": 289, "total_steps": 546, "loss": 0.2528, "lr": 2.14702942359231e-05, "epoch": 3.6992000000000003, "percentage": 52.93, "elapsed_time": "5:54:28", "remaining_time": "5:15:13"} +{"current_steps": 290, "total_steps": 546, "loss": 0.2333, "lr": 2.1342644158474614e-05, "epoch": 3.7119999999999997, "percentage": 53.11, "elapsed_time": "5:55:44", "remaining_time": "5:14:02"} +{"current_steps": 291, "total_steps": 546, "loss": 0.2293, "lr": 2.12149391147638e-05, "epoch": 3.7248, "percentage": 53.3, "elapsed_time": "5:56:45", "remaining_time": "5:12:37"} +{"current_steps": 292, "total_steps": 546, "loss": 0.2681, "lr": 2.1087184332883965e-05, "epoch": 3.7376, "percentage": 53.48, "elapsed_time": "5:57:58", "remaining_time": "5:11:23"} +{"current_steps": 293, "total_steps": 546, "loss": 0.2572, "lr": 2.0959385042964632e-05, "epoch": 3.7504, "percentage": 53.66, "elapsed_time": "5:59:18", "remaining_time": "5:10:15"} +{"current_steps": 294, "total_steps": 546, "loss": 0.2454, "lr": 2.083154647695743e-05, "epoch": 3.7632, "percentage": 53.85, "elapsed_time": "6:00:25", "remaining_time": "5:08:56"} +{"current_steps": 295, "total_steps": 546, "loss": 0.2244, "lr": 2.0703673868421914e-05, "epoch": 3.776, "percentage": 54.03, "elapsed_time": "6:01:38", "remaining_time": "5:07:41"} +{"current_steps": 296, "total_steps": 546, "loss": 0.2802, "lr": 2.057577245231128e-05, "epoch": 3.7888, "percentage": 54.21, "elapsed_time": "6:02:47", "remaining_time": "5:06:24"} +{"current_steps": 297, "total_steps": 546, "loss": 0.2164, "lr": 2.0447847464758097e-05, "epoch": 3.8016, "percentage": 54.4, "elapsed_time": "6:03:52", "remaining_time": "5:05:03"} +{"current_steps": 298, "total_steps": 546, "loss": 0.2501, "lr": 2.0319904142859905e-05, "epoch": 3.8144, "percentage": 54.58, "elapsed_time": "6:05:12", "remaining_time": "5:03:56"} +{"current_steps": 299, "total_steps": 546, "loss": 0.246, "lr": 2.019194772446482e-05, "epoch": 3.8272, "percentage": 54.76, "elapsed_time": "6:06:16", "remaining_time": "5:02:34"} +{"current_steps": 300, "total_steps": 546, "loss": 0.2276, "lr": 2.006398344795715e-05, "epoch": 3.84, "percentage": 54.95, "elapsed_time": "6:07:18", "remaining_time": "5:01:11"} +{"current_steps": 301, "total_steps": 546, "loss": 0.2232, "lr": 1.993601655204286e-05, "epoch": 3.8528000000000002, "percentage": 55.13, "elapsed_time": "6:08:30", "remaining_time": "4:59:57"} +{"current_steps": 302, "total_steps": 546, "loss": 0.2267, "lr": 1.9808052275535182e-05, "epoch": 3.8656, "percentage": 55.31, "elapsed_time": "6:09:39", "remaining_time": "4:58:40"} +{"current_steps": 303, "total_steps": 546, "loss": 0.2225, "lr": 1.96800958571401e-05, "epoch": 3.8784, "percentage": 55.49, "elapsed_time": "6:10:55", "remaining_time": "4:57:28"} +{"current_steps": 304, "total_steps": 546, "loss": 0.253, "lr": 1.955215253524191e-05, "epoch": 3.8912, "percentage": 55.68, "elapsed_time": "6:12:17", "remaining_time": "4:56:21"} +{"current_steps": 305, "total_steps": 546, "loss": 0.2538, "lr": 1.9424227547688722e-05, "epoch": 3.904, "percentage": 55.86, "elapsed_time": "6:13:34", "remaining_time": "4:55:11"} +{"current_steps": 306, "total_steps": 546, "loss": 0.2453, "lr": 1.9296326131578093e-05, "epoch": 3.9168, "percentage": 56.04, "elapsed_time": "6:14:42", "remaining_time": "4:53:53"} +{"current_steps": 307, "total_steps": 546, "loss": 0.2335, "lr": 1.916845352304257e-05, "epoch": 3.9295999999999998, "percentage": 56.23, "elapsed_time": "6:15:56", "remaining_time": "4:52:40"} +{"current_steps": 308, "total_steps": 546, "loss": 0.2408, "lr": 1.904061495703537e-05, "epoch": 3.9424, "percentage": 56.41, "elapsed_time": "6:17:09", "remaining_time": "4:51:26"} +{"current_steps": 309, "total_steps": 546, "loss": 0.2393, "lr": 1.8912815667116038e-05, "epoch": 3.9552, "percentage": 56.59, "elapsed_time": "6:18:22", "remaining_time": "4:50:12"} +{"current_steps": 310, "total_steps": 546, "loss": 0.2437, "lr": 1.87850608852362e-05, "epoch": 3.968, "percentage": 56.78, "elapsed_time": "6:19:35", "remaining_time": "4:48:58"} +{"current_steps": 311, "total_steps": 546, "loss": 0.2537, "lr": 1.8657355841525396e-05, "epoch": 3.9808, "percentage": 56.96, "elapsed_time": "6:20:50", "remaining_time": "4:47:46"} +{"current_steps": 312, "total_steps": 546, "loss": 0.2408, "lr": 1.8529705764076905e-05, "epoch": 3.9936, "percentage": 57.14, "elapsed_time": "6:21:54", "remaining_time": "4:46:26"} +{"current_steps": 313, "total_steps": 546, "loss": 0.3532, "lr": 1.840211587873379e-05, "epoch": 4.0064, "percentage": 57.33, "elapsed_time": "6:24:00", "remaining_time": "4:45:51"} +{"current_steps": 314, "total_steps": 546, "loss": 0.1459, "lr": 1.82745914088749e-05, "epoch": 4.0192, "percentage": 57.51, "elapsed_time": "6:25:13", "remaining_time": "4:44:37"} +{"current_steps": 315, "total_steps": 546, "loss": 0.1472, "lr": 1.8147137575201076e-05, "epoch": 4.032, "percentage": 57.69, "elapsed_time": "6:26:35", "remaining_time": "4:43:29"} +{"current_steps": 316, "total_steps": 546, "loss": 0.1701, "lr": 1.8019759595521358e-05, "epoch": 4.0448, "percentage": 57.88, "elapsed_time": "6:27:46", "remaining_time": "4:42:14"} +{"current_steps": 317, "total_steps": 546, "loss": 0.1576, "lr": 1.789246268453944e-05, "epoch": 4.0576, "percentage": 58.06, "elapsed_time": "6:28:56", "remaining_time": "4:40:57"} +{"current_steps": 318, "total_steps": 546, "loss": 0.1669, "lr": 1.7765252053640157e-05, "epoch": 4.0704, "percentage": 58.24, "elapsed_time": "6:30:05", "remaining_time": "4:39:41"} +{"current_steps": 319, "total_steps": 546, "loss": 0.1708, "lr": 1.7638132910676134e-05, "epoch": 4.0832, "percentage": 58.42, "elapsed_time": "6:31:21", "remaining_time": "4:38:29"} +{"current_steps": 320, "total_steps": 546, "loss": 0.1308, "lr": 1.751111045975459e-05, "epoch": 4.096, "percentage": 58.61, "elapsed_time": "6:32:26", "remaining_time": "4:37:09"} +{"current_steps": 321, "total_steps": 546, "loss": 0.1682, "lr": 1.738418990102429e-05, "epoch": 4.1088, "percentage": 58.79, "elapsed_time": "6:33:42", "remaining_time": "4:35:57"} +{"current_steps": 322, "total_steps": 546, "loss": 0.1522, "lr": 1.725737643046266e-05, "epoch": 4.1216, "percentage": 58.97, "elapsed_time": "6:34:56", "remaining_time": "4:34:44"} +{"current_steps": 323, "total_steps": 546, "loss": 0.1541, "lr": 1.7130675239663033e-05, "epoch": 4.1344, "percentage": 59.16, "elapsed_time": "6:36:07", "remaining_time": "4:33:29"} +{"current_steps": 324, "total_steps": 546, "loss": 0.1504, "lr": 1.7004091515622173e-05, "epoch": 4.1472, "percentage": 59.34, "elapsed_time": "6:37:17", "remaining_time": "4:32:12"} +{"current_steps": 325, "total_steps": 546, "loss": 0.1463, "lr": 1.6877630440527885e-05, "epoch": 4.16, "percentage": 59.52, "elapsed_time": "6:38:30", "remaining_time": "4:30:58"} +{"current_steps": 326, "total_steps": 546, "loss": 0.1712, "lr": 1.675129719154686e-05, "epoch": 4.1728, "percentage": 59.71, "elapsed_time": "6:39:43", "remaining_time": "4:29:45"} +{"current_steps": 327, "total_steps": 546, "loss": 0.1582, "lr": 1.6625096940612758e-05, "epoch": 4.1856, "percentage": 59.89, "elapsed_time": "6:40:54", "remaining_time": "4:28:30"} +{"current_steps": 328, "total_steps": 546, "loss": 0.1519, "lr": 1.649903485421445e-05, "epoch": 4.1984, "percentage": 60.07, "elapsed_time": "6:42:11", "remaining_time": "4:27:18"} +{"current_steps": 329, "total_steps": 546, "loss": 0.152, "lr": 1.6373116093184495e-05, "epoch": 4.2112, "percentage": 60.26, "elapsed_time": "6:43:36", "remaining_time": "4:26:12"} +{"current_steps": 330, "total_steps": 546, "loss": 0.1403, "lr": 1.624734581248791e-05, "epoch": 4.224, "percentage": 60.44, "elapsed_time": "6:44:46", "remaining_time": "4:24:56"} +{"current_steps": 331, "total_steps": 546, "loss": 0.1433, "lr": 1.6121729161011085e-05, "epoch": 4.2368, "percentage": 60.62, "elapsed_time": "6:45:57", "remaining_time": "4:23:41"} +{"current_steps": 332, "total_steps": 546, "loss": 0.1391, "lr": 1.5996271281351028e-05, "epoch": 4.2496, "percentage": 60.81, "elapsed_time": "6:47:14", "remaining_time": "4:22:29"} +{"current_steps": 333, "total_steps": 546, "loss": 0.1251, "lr": 1.587097730960479e-05, "epoch": 4.2624, "percentage": 60.99, "elapsed_time": "6:48:16", "remaining_time": "4:21:08"} +{"current_steps": 334, "total_steps": 546, "loss": 0.1368, "lr": 1.574585237515925e-05, "epoch": 4.2752, "percentage": 61.17, "elapsed_time": "6:49:31", "remaining_time": "4:19:56"} +{"current_steps": 335, "total_steps": 546, "loss": 0.1528, "lr": 1.5620901600481098e-05, "epoch": 4.288, "percentage": 61.36, "elapsed_time": "6:50:46", "remaining_time": "4:18:43"} +{"current_steps": 336, "total_steps": 546, "loss": 0.1585, "lr": 1.5496130100907114e-05, "epoch": 4.3008, "percentage": 61.54, "elapsed_time": "6:51:59", "remaining_time": "4:17:29"} +{"current_steps": 337, "total_steps": 546, "loss": 0.1396, "lr": 1.5371542984434775e-05, "epoch": 4.3136, "percentage": 61.72, "elapsed_time": "6:53:03", "remaining_time": "4:16:10"} +{"current_steps": 338, "total_steps": 546, "loss": 0.1795, "lr": 1.5247145351513137e-05, "epoch": 4.3264, "percentage": 61.9, "elapsed_time": "6:54:12", "remaining_time": "4:14:53"} +{"current_steps": 339, "total_steps": 546, "loss": 0.1492, "lr": 1.5122942294834031e-05, "epoch": 4.3392, "percentage": 62.09, "elapsed_time": "6:55:22", "remaining_time": "4:13:37"} +{"current_steps": 340, "total_steps": 546, "loss": 0.1639, "lr": 1.499893889912354e-05, "epoch": 4.352, "percentage": 62.27, "elapsed_time": "6:56:42", "remaining_time": "4:12:28"} +{"current_steps": 341, "total_steps": 546, "loss": 0.1461, "lr": 1.4875140240933886e-05, "epoch": 4.3648, "percentage": 62.45, "elapsed_time": "6:58:04", "remaining_time": "4:11:20"} +{"current_steps": 342, "total_steps": 546, "loss": 0.1292, "lr": 1.4751551388435576e-05, "epoch": 4.3776, "percentage": 62.64, "elapsed_time": "6:59:09", "remaining_time": "4:10:01"} +{"current_steps": 343, "total_steps": 546, "loss": 0.2001, "lr": 1.4628177401209916e-05, "epoch": 4.3904, "percentage": 62.82, "elapsed_time": "7:00:23", "remaining_time": "4:08:48"} +{"current_steps": 344, "total_steps": 546, "loss": 0.1282, "lr": 1.4505023330041879e-05, "epoch": 4.4032, "percentage": 63.0, "elapsed_time": "7:01:35", "remaining_time": "4:07:33"} +{"current_steps": 345, "total_steps": 546, "loss": 0.1459, "lr": 1.4382094216713345e-05, "epoch": 4.416, "percentage": 63.19, "elapsed_time": "7:02:49", "remaining_time": "4:06:20"} +{"current_steps": 346, "total_steps": 546, "loss": 0.1462, "lr": 1.4259395093796689e-05, "epoch": 4.4288, "percentage": 63.37, "elapsed_time": "7:04:01", "remaining_time": "4:05:06"} +{"current_steps": 347, "total_steps": 546, "loss": 0.1507, "lr": 1.4136930984448722e-05, "epoch": 4.4416, "percentage": 63.55, "elapsed_time": "7:05:13", "remaining_time": "4:03:51"} +{"current_steps": 348, "total_steps": 546, "loss": 0.1364, "lr": 1.4014706902205114e-05, "epoch": 4.4544, "percentage": 63.74, "elapsed_time": "7:06:26", "remaining_time": "4:02:38"} +{"current_steps": 349, "total_steps": 546, "loss": 0.1515, "lr": 1.3892727850775092e-05, "epoch": 4.4672, "percentage": 63.92, "elapsed_time": "7:07:42", "remaining_time": "4:01:25"} +{"current_steps": 350, "total_steps": 546, "loss": 0.1606, "lr": 1.3770998823836608e-05, "epoch": 4.48, "percentage": 64.1, "elapsed_time": "7:08:59", "remaining_time": "4:00:13"} +{"current_steps": 351, "total_steps": 546, "loss": 0.1367, "lr": 1.3649524804831915e-05, "epoch": 4.4928, "percentage": 64.29, "elapsed_time": "7:10:12", "remaining_time": "3:59:00"} +{"current_steps": 352, "total_steps": 546, "loss": 0.1553, "lr": 1.3528310766763544e-05, "epoch": 4.5056, "percentage": 64.47, "elapsed_time": "7:11:15", "remaining_time": "3:57:40"} +{"current_steps": 353, "total_steps": 546, "loss": 0.142, "lr": 1.3407361671990717e-05, "epoch": 4.5184, "percentage": 64.65, "elapsed_time": "7:12:30", "remaining_time": "3:56:28"} +{"current_steps": 354, "total_steps": 546, "loss": 0.1345, "lr": 1.3286682472026171e-05, "epoch": 4.5312, "percentage": 64.84, "elapsed_time": "7:13:46", "remaining_time": "3:55:15"} +{"current_steps": 355, "total_steps": 546, "loss": 0.15, "lr": 1.316627810733349e-05, "epoch": 4.5440000000000005, "percentage": 65.02, "elapsed_time": "7:14:51", "remaining_time": "3:53:58"} +{"current_steps": 356, "total_steps": 546, "loss": 0.1353, "lr": 1.3046153507124823e-05, "epoch": 4.5568, "percentage": 65.2, "elapsed_time": "7:15:56", "remaining_time": "3:52:40"} +{"current_steps": 357, "total_steps": 546, "loss": 0.1416, "lr": 1.2926313589159087e-05, "epoch": 4.5696, "percentage": 65.38, "elapsed_time": "7:17:10", "remaining_time": "3:51:26"} +{"current_steps": 358, "total_steps": 546, "loss": 0.1455, "lr": 1.2806763259540649e-05, "epoch": 4.5824, "percentage": 65.57, "elapsed_time": "7:18:18", "remaining_time": "3:50:10"} +{"current_steps": 359, "total_steps": 546, "loss": 0.1425, "lr": 1.2687507412518478e-05, "epoch": 4.5952, "percentage": 65.75, "elapsed_time": "7:19:34", "remaining_time": "3:48:58"} +{"current_steps": 360, "total_steps": 546, "loss": 0.1251, "lr": 1.256855093028575e-05, "epoch": 4.608, "percentage": 65.93, "elapsed_time": "7:20:36", "remaining_time": "3:47:38"} +{"current_steps": 361, "total_steps": 546, "loss": 0.1643, "lr": 1.2449898682780034e-05, "epoch": 4.6208, "percentage": 66.12, "elapsed_time": "7:21:47", "remaining_time": "3:46:23"} +{"current_steps": 362, "total_steps": 546, "loss": 0.1238, "lr": 1.2331555527483863e-05, "epoch": 4.6336, "percentage": 66.3, "elapsed_time": "7:22:55", "remaining_time": "3:45:07"} +{"current_steps": 363, "total_steps": 546, "loss": 0.1572, "lr": 1.2213526309225925e-05, "epoch": 4.6464, "percentage": 66.48, "elapsed_time": "7:24:18", "remaining_time": "3:43:59"} +{"current_steps": 364, "total_steps": 546, "loss": 0.1457, "lr": 1.2095815859982666e-05, "epoch": 4.6592, "percentage": 66.67, "elapsed_time": "7:25:36", "remaining_time": "3:42:48"} +{"current_steps": 365, "total_steps": 546, "loss": 0.1573, "lr": 1.1978428998680534e-05, "epoch": 4.672, "percentage": 66.85, "elapsed_time": "7:26:44", "remaining_time": "3:41:32"} +{"current_steps": 366, "total_steps": 546, "loss": 0.1313, "lr": 1.1861370530998659e-05, "epoch": 4.6848, "percentage": 67.03, "elapsed_time": "7:27:54", "remaining_time": "3:40:16"} +{"current_steps": 367, "total_steps": 546, "loss": 0.1334, "lr": 1.1744645249172122e-05, "epoch": 4.6975999999999996, "percentage": 67.22, "elapsed_time": "7:29:00", "remaining_time": "3:39:00"} +{"current_steps": 368, "total_steps": 546, "loss": 0.1517, "lr": 1.1628257931795774e-05, "epoch": 4.7104, "percentage": 67.4, "elapsed_time": "7:30:16", "remaining_time": "3:37:47"} +{"current_steps": 369, "total_steps": 546, "loss": 0.1325, "lr": 1.1512213343628602e-05, "epoch": 4.7232, "percentage": 67.58, "elapsed_time": "7:31:36", "remaining_time": "3:36:37"} +{"current_steps": 370, "total_steps": 546, "loss": 0.141, "lr": 1.1396516235398668e-05, "epoch": 4.736, "percentage": 67.77, "elapsed_time": "7:32:50", "remaining_time": "3:35:24"} +{"current_steps": 371, "total_steps": 546, "loss": 0.1589, "lr": 1.1281171343608592e-05, "epoch": 4.7488, "percentage": 67.95, "elapsed_time": "7:34:04", "remaining_time": "3:34:11"} +{"current_steps": 372, "total_steps": 546, "loss": 0.1539, "lr": 1.1166183390341713e-05, "epoch": 4.7616, "percentage": 68.13, "elapsed_time": "7:35:20", "remaining_time": "3:32:58"} +{"current_steps": 373, "total_steps": 546, "loss": 0.1171, "lr": 1.10515570830687e-05, "epoch": 4.7744, "percentage": 68.32, "elapsed_time": "7:36:22", "remaining_time": "3:31:40"} +{"current_steps": 374, "total_steps": 546, "loss": 0.1551, "lr": 1.0937297114454867e-05, "epoch": 4.7872, "percentage": 68.5, "elapsed_time": "7:37:32", "remaining_time": "3:30:25"} +{"current_steps": 375, "total_steps": 546, "loss": 0.1816, "lr": 1.082340816216805e-05, "epoch": 4.8, "percentage": 68.68, "elapsed_time": "7:38:47", "remaining_time": "3:29:12"} +{"current_steps": 376, "total_steps": 546, "loss": 0.1219, "lr": 1.0709894888687145e-05, "epoch": 4.8128, "percentage": 68.86, "elapsed_time": "7:40:00", "remaining_time": "3:27:59"} +{"current_steps": 377, "total_steps": 546, "loss": 0.1438, "lr": 1.0596761941111169e-05, "epoch": 4.8256, "percentage": 69.05, "elapsed_time": "7:41:15", "remaining_time": "3:26:46"} +{"current_steps": 378, "total_steps": 546, "loss": 0.1448, "lr": 1.0484013950969056e-05, "epoch": 4.8384, "percentage": 69.23, "elapsed_time": "7:42:32", "remaining_time": "3:25:34"} +{"current_steps": 379, "total_steps": 546, "loss": 0.1394, "lr": 1.0371655534030061e-05, "epoch": 4.8512, "percentage": 69.41, "elapsed_time": "7:43:47", "remaining_time": "3:24:21"} +{"current_steps": 380, "total_steps": 546, "loss": 0.1482, "lr": 1.0259691290114744e-05, "epoch": 4.864, "percentage": 69.6, "elapsed_time": "7:45:02", "remaining_time": "3:23:09"} +{"current_steps": 381, "total_steps": 546, "loss": 0.1309, "lr": 1.0148125802906704e-05, "epoch": 4.8768, "percentage": 69.78, "elapsed_time": "7:46:18", "remaining_time": "3:21:56"} +{"current_steps": 382, "total_steps": 546, "loss": 0.1391, "lr": 1.0036963639764892e-05, "epoch": 4.8896, "percentage": 69.96, "elapsed_time": "7:47:37", "remaining_time": "3:20:45"} +{"current_steps": 383, "total_steps": 546, "loss": 0.1593, "lr": 9.92620935153669e-06, "epoch": 4.9024, "percentage": 70.15, "elapsed_time": "7:48:58", "remaining_time": "3:19:35"} +{"current_steps": 384, "total_steps": 546, "loss": 0.1333, "lr": 9.815867472371515e-06, "epoch": 4.9152000000000005, "percentage": 70.33, "elapsed_time": "7:50:10", "remaining_time": "3:18:21"} +{"current_steps": 385, "total_steps": 546, "loss": 0.1506, "lr": 9.705942519535284e-06, "epoch": 4.928, "percentage": 70.51, "elapsed_time": "7:51:14", "remaining_time": "3:17:03"} +{"current_steps": 386, "total_steps": 546, "loss": 0.1509, "lr": 9.59643899322542e-06, "epoch": 4.9408, "percentage": 70.7, "elapsed_time": "7:52:26", "remaining_time": "3:15:49"} +{"current_steps": 387, "total_steps": 546, "loss": 0.1308, "lr": 9.487361376386661e-06, "epoch": 4.9536, "percentage": 70.88, "elapsed_time": "7:53:35", "remaining_time": "3:14:34"} +{"current_steps": 388, "total_steps": 546, "loss": 0.1438, "lr": 9.378714134527503e-06, "epoch": 4.9664, "percentage": 71.06, "elapsed_time": "7:54:47", "remaining_time": "3:13:20"} +{"current_steps": 389, "total_steps": 546, "loss": 0.1525, "lr": 9.270501715537392e-06, "epoch": 4.9792, "percentage": 71.25, "elapsed_time": "7:56:01", "remaining_time": "3:12:07"} +{"current_steps": 390, "total_steps": 546, "loss": 0.1439, "lr": 9.162728549504675e-06, "epoch": 4.992, "percentage": 71.43, "elapsed_time": "7:57:12", "remaining_time": "3:10:53"} +{"current_steps": 391, "total_steps": 546, "loss": 0.1964, "lr": 9.055399048535153e-06, "epoch": 5.0048, "percentage": 71.61, "elapsed_time": "7:59:14", "remaining_time": "3:09:58"} +{"current_steps": 392, "total_steps": 546, "loss": 0.0856, "lr": 8.948517606571548e-06, "epoch": 5.0176, "percentage": 71.79, "elapsed_time": "8:00:28", "remaining_time": "3:08:45"} +{"current_steps": 393, "total_steps": 546, "loss": 0.097, "lr": 8.842088599213545e-06, "epoch": 5.0304, "percentage": 71.98, "elapsed_time": "8:01:41", "remaining_time": "3:07:31"} +{"current_steps": 394, "total_steps": 546, "loss": 0.0855, "lr": 8.736116383538726e-06, "epoch": 5.0432, "percentage": 72.16, "elapsed_time": "8:02:58", "remaining_time": "3:06:19"} +{"current_steps": 395, "total_steps": 546, "loss": 0.075, "lr": 8.630605297924132e-06, "epoch": 5.056, "percentage": 72.34, "elapsed_time": "8:04:05", "remaining_time": "3:05:03"} +{"current_steps": 396, "total_steps": 546, "loss": 0.0828, "lr": 8.525559661868692e-06, "epoch": 5.0688, "percentage": 72.53, "elapsed_time": "8:05:11", "remaining_time": "3:03:47"} +{"current_steps": 397, "total_steps": 546, "loss": 0.0818, "lr": 8.420983775816402e-06, "epoch": 5.0816, "percentage": 72.71, "elapsed_time": "8:06:19", "remaining_time": "3:02:31"} +{"current_steps": 398, "total_steps": 546, "loss": 0.0967, "lr": 8.316881920980207e-06, "epoch": 5.0944, "percentage": 72.89, "elapsed_time": "8:07:46", "remaining_time": "3:01:22"} +{"current_steps": 399, "total_steps": 546, "loss": 0.0873, "lr": 8.213258359166823e-06, "epoch": 5.1072, "percentage": 73.08, "elapsed_time": "8:08:57", "remaining_time": "3:00:08"} +{"current_steps": 400, "total_steps": 546, "loss": 0.1032, "lr": 8.110117332602175e-06, "epoch": 5.12, "percentage": 73.26, "elapsed_time": "8:10:16", "remaining_time": "2:58:57"} +{"current_steps": 401, "total_steps": 546, "loss": 0.0926, "lr": 8.0074630637578e-06, "epoch": 5.1328, "percentage": 73.44, "elapsed_time": "8:11:25", "remaining_time": "2:57:41"} +{"current_steps": 402, "total_steps": 546, "loss": 0.0683, "lr": 7.905299755177929e-06, "epoch": 5.1456, "percentage": 73.63, "elapsed_time": "8:12:33", "remaining_time": "2:56:26"} +{"current_steps": 403, "total_steps": 546, "loss": 0.0955, "lr": 7.803631589307458e-06, "epoch": 5.1584, "percentage": 73.81, "elapsed_time": "8:13:47", "remaining_time": "2:55:12"} +{"current_steps": 404, "total_steps": 546, "loss": 0.0855, "lr": 7.702462728320759e-06, "epoch": 5.1712, "percentage": 73.99, "elapsed_time": "8:15:01", "remaining_time": "2:53:59"} +{"current_steps": 405, "total_steps": 546, "loss": 0.0766, "lr": 7.601797313951198e-06, "epoch": 5.184, "percentage": 74.18, "elapsed_time": "8:16:04", "remaining_time": "2:52:42"} +{"current_steps": 406, "total_steps": 546, "loss": 0.0922, "lr": 7.501639467321688e-06, "epoch": 5.1968, "percentage": 74.36, "elapsed_time": "8:17:21", "remaining_time": "2:51:30"} +{"current_steps": 407, "total_steps": 546, "loss": 0.0864, "lr": 7.401993288775888e-06, "epoch": 5.2096, "percentage": 74.54, "elapsed_time": "8:18:45", "remaining_time": "2:50:20"} +{"current_steps": 408, "total_steps": 546, "loss": 0.0908, "lr": 7.3028628577103754e-06, "epoch": 5.2224, "percentage": 74.73, "elapsed_time": "8:19:55", "remaining_time": "2:49:05"} +{"current_steps": 409, "total_steps": 546, "loss": 0.0831, "lr": 7.204252232407638e-06, "epoch": 5.2352, "percentage": 74.91, "elapsed_time": "8:21:07", "remaining_time": "2:47:51"} +{"current_steps": 410, "total_steps": 546, "loss": 0.0883, "lr": 7.106165449869946e-06, "epoch": 5.248, "percentage": 75.09, "elapsed_time": "8:22:21", "remaining_time": "2:46:38"} +{"current_steps": 411, "total_steps": 546, "loss": 0.0782, "lr": 7.008606525654045e-06, "epoch": 5.2608, "percentage": 75.27, "elapsed_time": "8:23:33", "remaining_time": "2:45:24"} +{"current_steps": 412, "total_steps": 546, "loss": 0.0799, "lr": 6.911579453706787e-06, "epoch": 5.2736, "percentage": 75.46, "elapsed_time": "8:24:39", "remaining_time": "2:44:08"} +{"current_steps": 413, "total_steps": 546, "loss": 0.084, "lr": 6.815088206201648e-06, "epoch": 5.2864, "percentage": 75.64, "elapsed_time": "8:25:39", "remaining_time": "2:42:50"} +{"current_steps": 414, "total_steps": 546, "loss": 0.0897, "lr": 6.719136733376057e-06, "epoch": 5.2992, "percentage": 75.82, "elapsed_time": "8:26:51", "remaining_time": "2:41:36"} +{"current_steps": 415, "total_steps": 546, "loss": 0.0785, "lr": 6.623728963369715e-06, "epoch": 5.312, "percentage": 76.01, "elapsed_time": "8:27:52", "remaining_time": "2:40:19"} +{"current_steps": 416, "total_steps": 546, "loss": 0.0861, "lr": 6.528868802063774e-06, "epoch": 5.3248, "percentage": 76.19, "elapsed_time": "8:29:05", "remaining_time": "2:39:05"} +{"current_steps": 417, "total_steps": 546, "loss": 0.0726, "lr": 6.434560132920944e-06, "epoch": 5.3376, "percentage": 76.37, "elapsed_time": "8:30:09", "remaining_time": "2:37:49"} +{"current_steps": 418, "total_steps": 546, "loss": 0.0719, "lr": 6.340806816826486e-06, "epoch": 5.3504, "percentage": 76.56, "elapsed_time": "8:31:14", "remaining_time": "2:36:33"} +{"current_steps": 419, "total_steps": 546, "loss": 0.0849, "lr": 6.2476126919301604e-06, "epoch": 5.3632, "percentage": 76.74, "elapsed_time": "8:32:28", "remaining_time": "2:35:19"} +{"current_steps": 420, "total_steps": 546, "loss": 0.0861, "lr": 6.154981573489125e-06, "epoch": 5.376, "percentage": 76.92, "elapsed_time": "8:33:37", "remaining_time": "2:34:05"} +{"current_steps": 421, "total_steps": 546, "loss": 0.0759, "lr": 6.062917253711697e-06, "epoch": 5.3888, "percentage": 77.11, "elapsed_time": "8:34:49", "remaining_time": "2:32:51"} +{"current_steps": 422, "total_steps": 546, "loss": 0.0975, "lr": 5.971423501602136e-06, "epoch": 5.4016, "percentage": 77.29, "elapsed_time": "8:36:08", "remaining_time": "2:31:39"} +{"current_steps": 423, "total_steps": 546, "loss": 0.0776, "lr": 5.880504062806329e-06, "epoch": 5.4144, "percentage": 77.47, "elapsed_time": "8:37:15", "remaining_time": "2:30:24"} +{"current_steps": 424, "total_steps": 546, "loss": 0.0793, "lr": 5.790162659458478e-06, "epoch": 5.4272, "percentage": 77.66, "elapsed_time": "8:38:27", "remaining_time": "2:29:10"} +{"current_steps": 425, "total_steps": 546, "loss": 0.0926, "lr": 5.700402990028675e-06, "epoch": 5.44, "percentage": 77.84, "elapsed_time": "8:39:34", "remaining_time": "2:27:55"} +{"current_steps": 426, "total_steps": 546, "loss": 0.0907, "lr": 5.611228729171516e-06, "epoch": 5.4528, "percentage": 78.02, "elapsed_time": "8:40:48", "remaining_time": "2:26:42"} +{"current_steps": 427, "total_steps": 546, "loss": 0.0655, "lr": 5.522643527575682e-06, "epoch": 5.4656, "percentage": 78.21, "elapsed_time": "8:41:57", "remaining_time": "2:25:27"} +{"current_steps": 428, "total_steps": 546, "loss": 0.0859, "lr": 5.434651011814447e-06, "epoch": 5.4784, "percentage": 78.39, "elapsed_time": "8:43:10", "remaining_time": "2:24:14"} +{"current_steps": 429, "total_steps": 546, "loss": 0.0665, "lr": 5.347254784197233e-06, "epoch": 5.4912, "percentage": 78.57, "elapsed_time": "8:44:21", "remaining_time": "2:23:00"} +{"current_steps": 430, "total_steps": 546, "loss": 0.0706, "lr": 5.260458422622128e-06, "epoch": 5.504, "percentage": 78.75, "elapsed_time": "8:45:33", "remaining_time": "2:21:46"} +{"current_steps": 431, "total_steps": 546, "loss": 0.0733, "lr": 5.1742654804294346e-06, "epoch": 5.5168, "percentage": 78.94, "elapsed_time": "8:46:41", "remaining_time": "2:20:32"} +{"current_steps": 432, "total_steps": 546, "loss": 0.0841, "lr": 5.088679486256141e-06, "epoch": 5.5296, "percentage": 79.12, "elapsed_time": "8:47:54", "remaining_time": "2:19:18"} +{"current_steps": 433, "total_steps": 546, "loss": 0.0909, "lr": 5.003703943891545e-06, "epoch": 5.5424, "percentage": 79.3, "elapsed_time": "8:49:05", "remaining_time": "2:18:04"} +{"current_steps": 434, "total_steps": 546, "loss": 0.0802, "lr": 4.919342332133738e-06, "epoch": 5.5552, "percentage": 79.49, "elapsed_time": "8:50:30", "remaining_time": "2:16:54"} +{"current_steps": 435, "total_steps": 546, "loss": 0.0784, "lr": 4.835598104647243e-06, "epoch": 5.568, "percentage": 79.67, "elapsed_time": "8:51:37", "remaining_time": "2:15:39"} +{"current_steps": 436, "total_steps": 546, "loss": 0.0905, "lr": 4.752474689821587e-06, "epoch": 5.5808, "percentage": 79.85, "elapsed_time": "8:52:50", "remaining_time": "2:14:25"} +{"current_steps": 437, "total_steps": 546, "loss": 0.09, "lr": 4.669975490630956e-06, "epoch": 5.5936, "percentage": 80.04, "elapsed_time": "8:53:55", "remaining_time": "2:13:10"} +{"current_steps": 438, "total_steps": 546, "loss": 0.0779, "lr": 4.588103884494914e-06, "epoch": 5.6064, "percentage": 80.22, "elapsed_time": "8:55:09", "remaining_time": "2:11:57"} +{"current_steps": 439, "total_steps": 546, "loss": 0.0899, "lr": 4.50686322314007e-06, "epoch": 5.6192, "percentage": 80.4, "elapsed_time": "8:56:24", "remaining_time": "2:10:44"} +{"current_steps": 440, "total_steps": 546, "loss": 0.0819, "lr": 4.426256832462936e-06, "epoch": 5.632, "percentage": 80.59, "elapsed_time": "8:57:45", "remaining_time": "2:09:33"} +{"current_steps": 441, "total_steps": 546, "loss": 0.0796, "lr": 4.346288012393707e-06, "epoch": 5.6448, "percentage": 80.77, "elapsed_time": "8:59:01", "remaining_time": "2:08:20"} +{"current_steps": 442, "total_steps": 546, "loss": 0.0772, "lr": 4.266960036761216e-06, "epoch": 5.6576, "percentage": 80.95, "elapsed_time": "9:00:13", "remaining_time": "2:07:06"} +{"current_steps": 443, "total_steps": 546, "loss": 0.0785, "lr": 4.188276153158866e-06, "epoch": 5.6704, "percentage": 81.14, "elapsed_time": "9:01:28", "remaining_time": "2:05:53"} +{"current_steps": 444, "total_steps": 546, "loss": 0.0893, "lr": 4.110239582811693e-06, "epoch": 5.6832, "percentage": 81.32, "elapsed_time": "9:02:34", "remaining_time": "2:04:38"} +{"current_steps": 445, "total_steps": 546, "loss": 0.0672, "lr": 4.032853520444518e-06, "epoch": 5.696, "percentage": 81.5, "elapsed_time": "9:03:47", "remaining_time": "2:03:25"} +{"current_steps": 446, "total_steps": 546, "loss": 0.0958, "lr": 3.9561211341510945e-06, "epoch": 5.7088, "percentage": 81.68, "elapsed_time": "9:05:06", "remaining_time": "2:02:13"} +{"current_steps": 447, "total_steps": 546, "loss": 0.0845, "lr": 3.880045565264496e-06, "epoch": 5.7216000000000005, "percentage": 81.87, "elapsed_time": "9:06:24", "remaining_time": "2:01:01"} +{"current_steps": 448, "total_steps": 546, "loss": 0.0826, "lr": 3.804629928228438e-06, "epoch": 5.7344, "percentage": 82.05, "elapsed_time": "9:07:36", "remaining_time": "1:59:47"} +{"current_steps": 449, "total_steps": 546, "loss": 0.0872, "lr": 3.7298773104698273e-06, "epoch": 5.7472, "percentage": 82.23, "elapsed_time": "9:08:57", "remaining_time": "1:58:35"} +{"current_steps": 450, "total_steps": 546, "loss": 0.072, "lr": 3.655790772272332e-06, "epoch": 5.76, "percentage": 82.42, "elapsed_time": "9:10:03", "remaining_time": "1:57:20"} +{"current_steps": 451, "total_steps": 546, "loss": 0.0845, "lr": 3.582373346651111e-06, "epoch": 5.7728, "percentage": 82.6, "elapsed_time": "9:11:22", "remaining_time": "1:56:08"} +{"current_steps": 452, "total_steps": 546, "loss": 0.0821, "lr": 3.5096280392286676e-06, "epoch": 5.7856, "percentage": 82.78, "elapsed_time": "9:12:29", "remaining_time": "1:54:54"} +{"current_steps": 453, "total_steps": 546, "loss": 0.0954, "lr": 3.437557828111746e-06, "epoch": 5.7984, "percentage": 82.97, "elapsed_time": "9:13:34", "remaining_time": "1:53:38"} +{"current_steps": 454, "total_steps": 546, "loss": 0.0795, "lr": 3.366165663769483e-06, "epoch": 5.8112, "percentage": 83.15, "elapsed_time": "9:14:52", "remaining_time": "1:52:26"} +{"current_steps": 455, "total_steps": 546, "loss": 0.0829, "lr": 3.2954544689125578e-06, "epoch": 5.824, "percentage": 83.33, "elapsed_time": "9:16:09", "remaining_time": "1:51:13"} +{"current_steps": 456, "total_steps": 546, "loss": 0.0858, "lr": 3.225427138373589e-06, "epoch": 5.8368, "percentage": 83.52, "elapsed_time": "9:17:13", "remaining_time": "1:49:58"} +{"current_steps": 457, "total_steps": 546, "loss": 0.0725, "lr": 3.156086538988563e-06, "epoch": 5.8496, "percentage": 83.7, "elapsed_time": "9:18:21", "remaining_time": "1:48:44"} +{"current_steps": 458, "total_steps": 546, "loss": 0.083, "lr": 3.0874355094795484e-06, "epoch": 5.8624, "percentage": 83.88, "elapsed_time": "9:19:35", "remaining_time": "1:47:31"} +{"current_steps": 459, "total_steps": 546, "loss": 0.0941, "lr": 3.0194768603384083e-06, "epoch": 5.8751999999999995, "percentage": 84.07, "elapsed_time": "9:20:44", "remaining_time": "1:46:17"} +{"current_steps": 460, "total_steps": 546, "loss": 0.0799, "lr": 2.952213373711783e-06, "epoch": 5.888, "percentage": 84.25, "elapsed_time": "9:21:46", "remaining_time": "1:45:01"} +{"current_steps": 461, "total_steps": 546, "loss": 0.086, "lr": 2.8856478032871906e-06, "epoch": 5.9008, "percentage": 84.43, "elapsed_time": "9:23:07", "remaining_time": "1:43:49"} +{"current_steps": 462, "total_steps": 546, "loss": 0.0824, "lr": 2.819782874180277e-06, "epoch": 5.9136, "percentage": 84.62, "elapsed_time": "9:24:20", "remaining_time": "1:42:36"} +{"current_steps": 463, "total_steps": 546, "loss": 0.0751, "lr": 2.75462128282326e-06, "epoch": 5.9264, "percentage": 84.8, "elapsed_time": "9:25:27", "remaining_time": "1:41:21"} +{"current_steps": 464, "total_steps": 546, "loss": 0.0798, "lr": 2.6901656968545455e-06, "epoch": 5.9392, "percentage": 84.98, "elapsed_time": "9:26:40", "remaining_time": "1:40:08"} +{"current_steps": 465, "total_steps": 546, "loss": 0.0787, "lr": 2.626418755009523e-06, "epoch": 5.952, "percentage": 85.16, "elapsed_time": "9:27:48", "remaining_time": "1:38:54"} +{"current_steps": 466, "total_steps": 546, "loss": 0.0816, "lr": 2.563383067012519e-06, "epoch": 5.9648, "percentage": 85.35, "elapsed_time": "9:29:04", "remaining_time": "1:37:41"} +{"current_steps": 467, "total_steps": 546, "loss": 0.0965, "lr": 2.5010612134699706e-06, "epoch": 5.9776, "percentage": 85.53, "elapsed_time": "9:30:21", "remaining_time": "1:36:28"} +{"current_steps": 468, "total_steps": 546, "loss": 0.0974, "lr": 2.4394557457647894e-06, "epoch": 5.9904, "percentage": 85.71, "elapsed_time": "9:31:30", "remaining_time": "1:35:15"} +{"current_steps": 469, "total_steps": 546, "loss": 0.1148, "lr": 2.3785691859518824e-06, "epoch": 6.0032, "percentage": 85.9, "elapsed_time": "9:33:46", "remaining_time": "1:34:12"} +{"current_steps": 470, "total_steps": 546, "loss": 0.0587, "lr": 2.318404026654928e-06, "epoch": 6.016, "percentage": 86.08, "elapsed_time": "9:35:06", "remaining_time": "1:32:59"} +{"current_steps": 471, "total_steps": 546, "loss": 0.0515, "lr": 2.2589627309643182e-06, "epoch": 6.0288, "percentage": 86.26, "elapsed_time": "9:36:23", "remaining_time": "1:31:46"} +{"current_steps": 472, "total_steps": 546, "loss": 0.0604, "lr": 2.2002477323363314e-06, "epoch": 6.0416, "percentage": 86.45, "elapsed_time": "9:37:36", "remaining_time": "1:30:33"} +{"current_steps": 473, "total_steps": 546, "loss": 0.0491, "lr": 2.1422614344935e-06, "epoch": 6.0544, "percentage": 86.63, "elapsed_time": "9:38:48", "remaining_time": "1:29:19"} +{"current_steps": 474, "total_steps": 546, "loss": 0.0602, "lr": 2.0850062113262014e-06, "epoch": 6.0672, "percentage": 86.81, "elapsed_time": "9:40:05", "remaining_time": "1:28:06"} +{"current_steps": 475, "total_steps": 546, "loss": 0.0582, "lr": 2.0284844067955013e-06, "epoch": 6.08, "percentage": 87.0, "elapsed_time": "9:41:20", "remaining_time": "1:26:53"} +{"current_steps": 476, "total_steps": 546, "loss": 0.0552, "lr": 1.972698334837155e-06, "epoch": 6.0928, "percentage": 87.18, "elapsed_time": "9:42:35", "remaining_time": "1:25:40"} +{"current_steps": 477, "total_steps": 546, "loss": 0.0598, "lr": 1.9176502792669048e-06, "epoch": 6.1056, "percentage": 87.36, "elapsed_time": "9:43:41", "remaining_time": "1:24:25"} +{"current_steps": 478, "total_steps": 546, "loss": 0.0659, "lr": 1.8633424936869747e-06, "epoch": 6.1184, "percentage": 87.55, "elapsed_time": "9:44:43", "remaining_time": "1:23:10"} +{"current_steps": 479, "total_steps": 546, "loss": 0.0526, "lr": 1.8097772013938187e-06, "epoch": 6.1312, "percentage": 87.73, "elapsed_time": "9:45:47", "remaining_time": "1:21:56"} +{"current_steps": 480, "total_steps": 546, "loss": 0.0633, "lr": 1.756956595287085e-06, "epoch": 6.144, "percentage": 87.91, "elapsed_time": "9:47:05", "remaining_time": "1:20:43"} +{"current_steps": 481, "total_steps": 546, "loss": 0.0509, "lr": 1.7048828377798531e-06, "epoch": 6.1568, "percentage": 88.1, "elapsed_time": "9:48:05", "remaining_time": "1:19:28"} +{"current_steps": 482, "total_steps": 546, "loss": 0.0533, "lr": 1.6535580607101055e-06, "epoch": 6.1696, "percentage": 88.28, "elapsed_time": "9:49:23", "remaining_time": "1:18:15"} +{"current_steps": 483, "total_steps": 546, "loss": 0.059, "lr": 1.6029843652534571e-06, "epoch": 6.1824, "percentage": 88.46, "elapsed_time": "9:50:41", "remaining_time": "1:17:02"} +{"current_steps": 484, "total_steps": 546, "loss": 0.0527, "lr": 1.553163821837127e-06, "epoch": 6.1952, "percentage": 88.64, "elapsed_time": "9:51:49", "remaining_time": "1:15:48"} +{"current_steps": 485, "total_steps": 546, "loss": 0.0593, "lr": 1.5040984700551752e-06, "epoch": 6.208, "percentage": 88.83, "elapsed_time": "9:53:06", "remaining_time": "1:14:35"} +{"current_steps": 486, "total_steps": 546, "loss": 0.0618, "lr": 1.4557903185850308e-06, "epoch": 6.2208, "percentage": 89.01, "elapsed_time": "9:54:16", "remaining_time": "1:13:22"} +{"current_steps": 487, "total_steps": 546, "loss": 0.0534, "lr": 1.4082413451052058e-06, "epoch": 6.2336, "percentage": 89.19, "elapsed_time": "9:55:33", "remaining_time": "1:12:09"} +{"current_steps": 488, "total_steps": 546, "loss": 0.0624, "lr": 1.3614534962143932e-06, "epoch": 6.2464, "percentage": 89.38, "elapsed_time": "9:56:47", "remaining_time": "1:10:55"} +{"current_steps": 489, "total_steps": 546, "loss": 0.0468, "lr": 1.3154286873517318e-06, "epoch": 6.2592, "percentage": 89.56, "elapsed_time": "9:57:54", "remaining_time": "1:09:41"} +{"current_steps": 490, "total_steps": 546, "loss": 0.0549, "lr": 1.2701688027184123e-06, "epoch": 6.272, "percentage": 89.74, "elapsed_time": "9:59:03", "remaining_time": "1:08:27"} +{"current_steps": 491, "total_steps": 546, "loss": 0.0598, "lr": 1.22567569520053e-06, "epoch": 6.2848, "percentage": 89.93, "elapsed_time": "10:00:10", "remaining_time": "1:07:13"} +{"current_steps": 492, "total_steps": 546, "loss": 0.0583, "lr": 1.1819511862932242e-06, "epoch": 6.2976, "percentage": 90.11, "elapsed_time": "10:01:21", "remaining_time": "1:06:00"} +{"current_steps": 493, "total_steps": 546, "loss": 0.0535, "lr": 1.1389970660261396e-06, "epoch": 6.3104, "percentage": 90.29, "elapsed_time": "10:02:36", "remaining_time": "1:04:47"} +{"current_steps": 494, "total_steps": 546, "loss": 0.0588, "lr": 1.0968150928900912e-06, "epoch": 6.3232, "percentage": 90.48, "elapsed_time": "10:03:48", "remaining_time": "1:03:33"} +{"current_steps": 495, "total_steps": 546, "loss": 0.0612, "lr": 1.0554069937651335e-06, "epoch": 6.336, "percentage": 90.66, "elapsed_time": "10:05:03", "remaining_time": "1:02:20"} +{"current_steps": 496, "total_steps": 546, "loss": 0.0599, "lr": 1.0147744638498146e-06, "epoch": 6.3488, "percentage": 90.84, "elapsed_time": "10:06:20", "remaining_time": "1:01:07"} +{"current_steps": 497, "total_steps": 546, "loss": 0.05, "lr": 9.749191665918122e-07, "epoch": 6.3616, "percentage": 91.03, "elapsed_time": "10:07:32", "remaining_time": "0:59:53"} +{"current_steps": 498, "total_steps": 546, "loss": 0.061, "lr": 9.358427336198073e-07, "epoch": 6.3744, "percentage": 91.21, "elapsed_time": "10:08:39", "remaining_time": "0:58:39"} +{"current_steps": 499, "total_steps": 546, "loss": 0.0429, "lr": 8.975467646767045e-07, "epoch": 6.3872, "percentage": 91.39, "elapsed_time": "10:09:47", "remaining_time": "0:57:26"} +{"current_steps": 500, "total_steps": 546, "loss": 0.0632, "lr": 8.600328275541425e-07, "epoch": 6.4, "percentage": 91.58, "elapsed_time": "10:11:00", "remaining_time": "0:56:12"} +{"current_steps": 501, "total_steps": 546, "loss": 0.0486, "lr": 8.233024580282811e-07, "epoch": 6.4128, "percentage": 91.76, "elapsed_time": "10:12:11", "remaining_time": "0:54:59"} +{"current_steps": 502, "total_steps": 546, "loss": 0.0512, "lr": 7.873571597969753e-07, "epoch": 6.4256, "percentage": 91.94, "elapsed_time": "10:13:26", "remaining_time": "0:53:46"} +{"current_steps": 503, "total_steps": 546, "loss": 0.061, "lr": 7.521984044181763e-07, "epoch": 6.4384, "percentage": 92.12, "elapsed_time": "10:14:33", "remaining_time": "0:52:32"} +{"current_steps": 504, "total_steps": 546, "loss": 0.0549, "lr": 7.178276312497101e-07, "epoch": 6.4512, "percentage": 92.31, "elapsed_time": "10:15:47", "remaining_time": "0:51:18"} +{"current_steps": 505, "total_steps": 546, "loss": 0.059, "lr": 6.842462473903299e-07, "epoch": 6.464, "percentage": 92.49, "elapsed_time": "10:16:58", "remaining_time": "0:50:05"} +{"current_steps": 506, "total_steps": 546, "loss": 0.0536, "lr": 6.51455627622144e-07, "epoch": 6.4768, "percentage": 92.67, "elapsed_time": "10:18:16", "remaining_time": "0:48:52"} +{"current_steps": 507, "total_steps": 546, "loss": 0.0612, "lr": 6.194571143543027e-07, "epoch": 6.4896, "percentage": 92.86, "elapsed_time": "10:19:39", "remaining_time": "0:47:39"} +{"current_steps": 508, "total_steps": 546, "loss": 0.0505, "lr": 5.882520175680539e-07, "epoch": 6.5024, "percentage": 93.04, "elapsed_time": "10:20:46", "remaining_time": "0:46:26"} +{"current_steps": 509, "total_steps": 546, "loss": 0.0447, "lr": 5.578416147631216e-07, "epoch": 6.5152, "percentage": 93.22, "elapsed_time": "10:21:52", "remaining_time": "0:45:12"} +{"current_steps": 510, "total_steps": 546, "loss": 0.0615, "lr": 5.282271509053916e-07, "epoch": 6.5280000000000005, "percentage": 93.41, "elapsed_time": "10:23:04", "remaining_time": "0:43:58"} +{"current_steps": 511, "total_steps": 546, "loss": 0.0528, "lr": 4.994098383759571e-07, "epoch": 6.5408, "percentage": 93.59, "elapsed_time": "10:24:22", "remaining_time": "0:42:45"} +{"current_steps": 512, "total_steps": 546, "loss": 0.0499, "lr": 4.71390856921472e-07, "epoch": 6.5536, "percentage": 93.77, "elapsed_time": "10:25:39", "remaining_time": "0:41:32"} +{"current_steps": 513, "total_steps": 546, "loss": 0.0535, "lr": 4.441713536058734e-07, "epoch": 6.5664, "percentage": 93.96, "elapsed_time": "10:26:57", "remaining_time": "0:40:19"} +{"current_steps": 514, "total_steps": 546, "loss": 0.0479, "lr": 4.177524427633972e-07, "epoch": 6.5792, "percentage": 94.14, "elapsed_time": "10:28:06", "remaining_time": "0:39:06"} +{"current_steps": 515, "total_steps": 546, "loss": 0.0539, "lr": 3.9213520595297484e-07, "epoch": 6.592, "percentage": 94.32, "elapsed_time": "10:29:27", "remaining_time": "0:37:53"} +{"current_steps": 516, "total_steps": 546, "loss": 0.0583, "lr": 3.673206919139616e-07, "epoch": 6.6048, "percentage": 94.51, "elapsed_time": "10:30:39", "remaining_time": "0:36:39"} +{"current_steps": 517, "total_steps": 546, "loss": 0.06, "lr": 3.4330991652317793e-07, "epoch": 6.6176, "percentage": 94.69, "elapsed_time": "10:31:47", "remaining_time": "0:35:26"} +{"current_steps": 518, "total_steps": 546, "loss": 0.061, "lr": 3.201038627533448e-07, "epoch": 6.6304, "percentage": 94.87, "elapsed_time": "10:32:50", "remaining_time": "0:34:12"} +{"current_steps": 519, "total_steps": 546, "loss": 0.0487, "lr": 2.977034806328294e-07, "epoch": 6.6432, "percentage": 95.05, "elapsed_time": "10:33:55", "remaining_time": "0:32:58"} +{"current_steps": 520, "total_steps": 546, "loss": 0.0602, "lr": 2.7610968720675813e-07, "epoch": 6.656, "percentage": 95.24, "elapsed_time": "10:35:07", "remaining_time": "0:31:45"} +{"current_steps": 521, "total_steps": 546, "loss": 0.0547, "lr": 2.553233664994692e-07, "epoch": 6.6688, "percentage": 95.42, "elapsed_time": "10:36:22", "remaining_time": "0:30:32"} +{"current_steps": 522, "total_steps": 546, "loss": 0.0515, "lr": 2.3534536947832364e-07, "epoch": 6.6815999999999995, "percentage": 95.6, "elapsed_time": "10:37:37", "remaining_time": "0:29:18"} +{"current_steps": 523, "total_steps": 546, "loss": 0.0553, "lr": 2.1617651401886875e-07, "epoch": 6.6944, "percentage": 95.79, "elapsed_time": "10:38:45", "remaining_time": "0:28:05"} +{"current_steps": 524, "total_steps": 546, "loss": 0.0511, "lr": 1.9781758487135373e-07, "epoch": 6.7072, "percentage": 95.97, "elapsed_time": "10:39:56", "remaining_time": "0:26:52"} +{"current_steps": 525, "total_steps": 546, "loss": 0.0617, "lr": 1.8026933362859988e-07, "epoch": 6.72, "percentage": 96.15, "elapsed_time": "10:41:18", "remaining_time": "0:25:39"} +{"current_steps": 526, "total_steps": 546, "loss": 0.056, "lr": 1.635324786952408e-07, "epoch": 6.7328, "percentage": 96.34, "elapsed_time": "10:42:35", "remaining_time": "0:24:25"} +{"current_steps": 527, "total_steps": 546, "loss": 0.0548, "lr": 1.476077052583036e-07, "epoch": 6.7456, "percentage": 96.52, "elapsed_time": "10:43:49", "remaining_time": "0:23:12"} +{"current_steps": 528, "total_steps": 546, "loss": 0.0515, "lr": 1.3249566525916024e-07, "epoch": 6.7584, "percentage": 96.7, "elapsed_time": "10:45:05", "remaining_time": "0:21:59"} +{"current_steps": 529, "total_steps": 546, "loss": 0.0555, "lr": 1.1819697736683567e-07, "epoch": 6.7712, "percentage": 96.89, "elapsed_time": "10:46:12", "remaining_time": "0:20:46"} +{"current_steps": 530, "total_steps": 546, "loss": 0.0479, "lr": 1.0471222695268346e-07, "epoch": 6.784, "percentage": 97.07, "elapsed_time": "10:47:32", "remaining_time": "0:19:32"} +{"current_steps": 531, "total_steps": 546, "loss": 0.0522, "lr": 9.204196606642512e-08, "epoch": 6.7968, "percentage": 97.25, "elapsed_time": "10:48:44", "remaining_time": "0:18:19"} +{"current_steps": 532, "total_steps": 546, "loss": 0.0501, "lr": 8.018671341353702e-08, "epoch": 6.8096, "percentage": 97.44, "elapsed_time": "10:49:56", "remaining_time": "0:17:06"} +{"current_steps": 533, "total_steps": 546, "loss": 0.0582, "lr": 6.914695433403174e-08, "epoch": 6.8224, "percentage": 97.62, "elapsed_time": "10:51:14", "remaining_time": "0:15:53"} +{"current_steps": 534, "total_steps": 546, "loss": 0.0602, "lr": 5.8923140782574106e-08, "epoch": 6.8352, "percentage": 97.8, "elapsed_time": "10:52:30", "remaining_time": "0:14:39"} +{"current_steps": 535, "total_steps": 546, "loss": 0.0517, "lr": 4.951569130998479e-08, "epoch": 6.848, "percentage": 97.99, "elapsed_time": "10:53:47", "remaining_time": "0:13:26"} +{"current_steps": 536, "total_steps": 546, "loss": 0.0645, "lr": 4.092499104611403e-08, "epoch": 6.8608, "percentage": 98.17, "elapsed_time": "10:55:06", "remaining_time": "0:12:13"} +{"current_steps": 537, "total_steps": 546, "loss": 0.0457, "lr": 3.315139168405423e-08, "epoch": 6.8736, "percentage": 98.35, "elapsed_time": "10:56:17", "remaining_time": "0:10:59"} +{"current_steps": 538, "total_steps": 546, "loss": 0.0552, "lr": 2.619521146576487e-08, "epoch": 6.8864, "percentage": 98.53, "elapsed_time": "10:57:15", "remaining_time": "0:09:46"} +{"current_steps": 539, "total_steps": 546, "loss": 0.0521, "lr": 2.0056735169025064e-08, "epoch": 6.8992, "percentage": 98.72, "elapsed_time": "10:58:24", "remaining_time": "0:08:33"} +{"current_steps": 540, "total_steps": 546, "loss": 0.0604, "lr": 1.4736214095789625e-08, "epoch": 6.912, "percentage": 98.9, "elapsed_time": "10:59:30", "remaining_time": "0:07:19"} +{"current_steps": 541, "total_steps": 546, "loss": 0.0563, "lr": 1.0233866061892806e-08, "epoch": 6.9248, "percentage": 99.08, "elapsed_time": "11:00:46", "remaining_time": "0:06:06"} +{"current_steps": 542, "total_steps": 546, "loss": 0.0511, "lr": 6.54987538813101e-09, "epoch": 6.9376, "percentage": 99.27, "elapsed_time": "11:01:49", "remaining_time": "0:04:53"} +{"current_steps": 543, "total_steps": 546, "loss": 0.0525, "lr": 3.6843928927221552e-09, "epoch": 6.9504, "percentage": 99.45, "elapsed_time": "11:03:07", "remaining_time": "0:03:39"} +{"current_steps": 544, "total_steps": 546, "loss": 0.0528, "lr": 1.6375358851261625e-09, "epoch": 6.9632, "percentage": 99.63, "elapsed_time": "11:04:25", "remaining_time": "0:02:26"} +{"current_steps": 545, "total_steps": 546, "loss": 0.0587, "lr": 4.0938816124880263e-10, "epoch": 6.976, "percentage": 99.82, "elapsed_time": "11:05:28", "remaining_time": "0:01:13"} +{"current_steps": 546, "total_steps": 546, "loss": 0.0537, "lr": 0.0, "epoch": 6.9888, "percentage": 100.0, "elapsed_time": "11:06:43", "remaining_time": "0:00:00"} +{"current_steps": 546, "total_steps": 546, "epoch": 6.9888, "percentage": 100.0, "elapsed_time": "11:08:33", "remaining_time": "0:00:00"} diff --git a/trainer_state.json b/trainer_state.json new file mode 100644 index 0000000..389bff3 --- /dev/null +++ b/trainer_state.json @@ -0,0 +1,3864 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 6.9888, + "eval_steps": 500, + "global_step": 546, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0128, + "grad_norm": 5.766647666212616, + "learning_rate": 7.272727272727273e-07, + "loss": 0.8581, + "step": 1 + }, + { + "epoch": 0.0256, + "grad_norm": 6.070563091767254, + "learning_rate": 1.4545454545454546e-06, + "loss": 0.8903, + "step": 2 + }, + { + "epoch": 0.0384, + "grad_norm": 5.849190565123478, + "learning_rate": 2.181818181818182e-06, + "loss": 0.8612, + "step": 3 + }, + { + "epoch": 0.0512, + "grad_norm": 5.366961420323551, + "learning_rate": 2.9090909090909093e-06, + "loss": 0.8373, + "step": 4 + }, + { + "epoch": 0.064, + "grad_norm": 4.319707192417716, + "learning_rate": 3.6363636363636366e-06, + "loss": 0.8142, + "step": 5 + }, + { + "epoch": 0.0768, + "grad_norm": 3.983191448432348, + "learning_rate": 4.363636363636364e-06, + "loss": 0.7828, + "step": 6 + }, + { + "epoch": 0.0896, + "grad_norm": 2.2385536982978125, + "learning_rate": 5.090909090909091e-06, + "loss": 0.7785, + "step": 7 + }, + { + "epoch": 0.1024, + "grad_norm": 1.8524407061261374, + "learning_rate": 5.8181818181818185e-06, + "loss": 0.7922, + "step": 8 + }, + { + "epoch": 0.1152, + "grad_norm": 4.1424544972227535, + "learning_rate": 6.545454545454546e-06, + "loss": 0.7785, + "step": 9 + }, + { + "epoch": 0.128, + "grad_norm": 4.241603681338813, + "learning_rate": 7.272727272727273e-06, + "loss": 0.7593, + "step": 10 + }, + { + "epoch": 0.1408, + "grad_norm": 4.126008550691871, + "learning_rate": 8.000000000000001e-06, + "loss": 0.7382, + "step": 11 + }, + { + "epoch": 0.1536, + "grad_norm": 4.308634912593385, + "learning_rate": 8.727272727272728e-06, + "loss": 0.7525, + "step": 12 + }, + { + "epoch": 0.1664, + "grad_norm": 3.589409317711825, + "learning_rate": 9.454545454545456e-06, + "loss": 0.742, + "step": 13 + }, + { + "epoch": 0.1792, + "grad_norm": 2.237262469277396, + "learning_rate": 1.0181818181818182e-05, + "loss": 0.6832, + "step": 14 + }, + { + "epoch": 0.192, + "grad_norm": 1.6758797429922476, + "learning_rate": 1.0909090909090909e-05, + "loss": 0.6703, + "step": 15 + }, + { + "epoch": 0.2048, + "grad_norm": 2.1923512665296605, + "learning_rate": 1.1636363636363637e-05, + "loss": 0.6537, + "step": 16 + }, + { + "epoch": 0.2176, + "grad_norm": 1.922487155991213, + "learning_rate": 1.2363636363636364e-05, + "loss": 0.641, + "step": 17 + }, + { + "epoch": 0.2304, + "grad_norm": 1.2973346514268629, + "learning_rate": 1.3090909090909092e-05, + "loss": 0.6528, + "step": 18 + }, + { + "epoch": 0.2432, + "grad_norm": 1.2961046946095225, + "learning_rate": 1.381818181818182e-05, + "loss": 0.6134, + "step": 19 + }, + { + "epoch": 0.256, + "grad_norm": 1.3306249684434817, + "learning_rate": 1.4545454545454546e-05, + "loss": 0.5982, + "step": 20 + }, + { + "epoch": 0.2688, + "grad_norm": 0.989519669968098, + "learning_rate": 1.5272727272727276e-05, + "loss": 0.5845, + "step": 21 + }, + { + "epoch": 0.2816, + "grad_norm": 1.011623939977001, + "learning_rate": 1.6000000000000003e-05, + "loss": 0.6178, + "step": 22 + }, + { + "epoch": 0.2944, + "grad_norm": 1.098222401076638, + "learning_rate": 1.672727272727273e-05, + "loss": 0.588, + "step": 23 + }, + { + "epoch": 0.3072, + "grad_norm": 0.9865060069928192, + "learning_rate": 1.7454545454545456e-05, + "loss": 0.6123, + "step": 24 + }, + { + "epoch": 0.32, + "grad_norm": 0.8484006270435027, + "learning_rate": 1.8181818181818182e-05, + "loss": 0.5905, + "step": 25 + }, + { + "epoch": 0.3328, + "grad_norm": 0.9148839630470734, + "learning_rate": 1.8909090909090912e-05, + "loss": 0.5878, + "step": 26 + }, + { + "epoch": 0.3456, + "grad_norm": 0.7336597756013822, + "learning_rate": 1.963636363636364e-05, + "loss": 0.5888, + "step": 27 + }, + { + "epoch": 0.3584, + "grad_norm": 0.8092409634479293, + "learning_rate": 2.0363636363636365e-05, + "loss": 0.5837, + "step": 28 + }, + { + "epoch": 0.3712, + "grad_norm": 0.7637535128865753, + "learning_rate": 2.109090909090909e-05, + "loss": 0.5814, + "step": 29 + }, + { + "epoch": 0.384, + "grad_norm": 0.7555077187353209, + "learning_rate": 2.1818181818181818e-05, + "loss": 0.5553, + "step": 30 + }, + { + "epoch": 0.3968, + "grad_norm": 0.8186392586199401, + "learning_rate": 2.2545454545454544e-05, + "loss": 0.5773, + "step": 31 + }, + { + "epoch": 0.4096, + "grad_norm": 0.8210622569331878, + "learning_rate": 2.3272727272727274e-05, + "loss": 0.5848, + "step": 32 + }, + { + "epoch": 0.4224, + "grad_norm": 0.8313195292833121, + "learning_rate": 2.4e-05, + "loss": 0.5727, + "step": 33 + }, + { + "epoch": 0.4352, + "grad_norm": 0.6630479354750299, + "learning_rate": 2.4727272727272727e-05, + "loss": 0.5675, + "step": 34 + }, + { + "epoch": 0.448, + "grad_norm": 0.9805477228857835, + "learning_rate": 2.5454545454545457e-05, + "loss": 0.5832, + "step": 35 + }, + { + "epoch": 0.4608, + "grad_norm": 0.7371360352051671, + "learning_rate": 2.6181818181818183e-05, + "loss": 0.5824, + "step": 36 + }, + { + "epoch": 0.4736, + "grad_norm": 0.8556866980617879, + "learning_rate": 2.690909090909091e-05, + "loss": 0.5738, + "step": 37 + }, + { + "epoch": 0.4864, + "grad_norm": 0.766882649198606, + "learning_rate": 2.763636363636364e-05, + "loss": 0.5614, + "step": 38 + }, + { + "epoch": 0.4992, + "grad_norm": 1.1955571273221928, + "learning_rate": 2.8363636363636366e-05, + "loss": 0.554, + "step": 39 + }, + { + "epoch": 0.512, + "grad_norm": 0.6114564427093548, + "learning_rate": 2.9090909090909093e-05, + "loss": 0.517, + "step": 40 + }, + { + "epoch": 0.5248, + "grad_norm": 1.0261669102259894, + "learning_rate": 2.9818181818181823e-05, + "loss": 0.5714, + "step": 41 + }, + { + "epoch": 0.5376, + "grad_norm": 0.8655996084109017, + "learning_rate": 3.054545454545455e-05, + "loss": 0.5287, + "step": 42 + }, + { + "epoch": 0.5504, + "grad_norm": 0.6771821140740898, + "learning_rate": 3.127272727272728e-05, + "loss": 0.5573, + "step": 43 + }, + { + "epoch": 0.5632, + "grad_norm": 0.7880081437519127, + "learning_rate": 3.2000000000000005e-05, + "loss": 0.546, + "step": 44 + }, + { + "epoch": 0.576, + "grad_norm": 1.1131641762341702, + "learning_rate": 3.272727272727273e-05, + "loss": 0.5406, + "step": 45 + }, + { + "epoch": 0.5888, + "grad_norm": 0.8489996563987092, + "learning_rate": 3.345454545454546e-05, + "loss": 0.5271, + "step": 46 + }, + { + "epoch": 0.6016, + "grad_norm": 0.6805613862148753, + "learning_rate": 3.4181818181818185e-05, + "loss": 0.5142, + "step": 47 + }, + { + "epoch": 0.6144, + "grad_norm": 0.9178327140587307, + "learning_rate": 3.490909090909091e-05, + "loss": 0.509, + "step": 48 + }, + { + "epoch": 0.6272, + "grad_norm": 0.8562187238764861, + "learning_rate": 3.563636363636364e-05, + "loss": 0.5489, + "step": 49 + }, + { + "epoch": 0.64, + "grad_norm": 0.9567967213511702, + "learning_rate": 3.6363636363636364e-05, + "loss": 0.5198, + "step": 50 + }, + { + "epoch": 0.6528, + "grad_norm": 1.0431846360290824, + "learning_rate": 3.709090909090909e-05, + "loss": 0.5356, + "step": 51 + }, + { + "epoch": 0.6656, + "grad_norm": 1.083823508582481, + "learning_rate": 3.7818181818181824e-05, + "loss": 0.5235, + "step": 52 + }, + { + "epoch": 0.6784, + "grad_norm": 1.134077161018365, + "learning_rate": 3.854545454545455e-05, + "loss": 0.5372, + "step": 53 + }, + { + "epoch": 0.6912, + "grad_norm": 0.9918330614306756, + "learning_rate": 3.927272727272728e-05, + "loss": 0.5349, + "step": 54 + }, + { + "epoch": 0.704, + "grad_norm": 0.895430718728658, + "learning_rate": 4e-05, + "loss": 0.5568, + "step": 55 + }, + { + "epoch": 0.7168, + "grad_norm": 1.1849253245115767, + "learning_rate": 3.9999590611838754e-05, + "loss": 0.5309, + "step": 56 + }, + { + "epoch": 0.7296, + "grad_norm": 1.6206581340504822, + "learning_rate": 3.9998362464114874e-05, + "loss": 0.5401, + "step": 57 + }, + { + "epoch": 0.7424, + "grad_norm": 0.8852091548398006, + "learning_rate": 3.9996315607107277e-05, + "loss": 0.5466, + "step": 58 + }, + { + "epoch": 0.7552, + "grad_norm": 2.4037295401703993, + "learning_rate": 3.999345012461187e-05, + "loss": 0.5228, + "step": 59 + }, + { + "epoch": 0.768, + "grad_norm": 1.18290113292988, + "learning_rate": 3.998976613393811e-05, + "loss": 0.5294, + "step": 60 + }, + { + "epoch": 0.7808, + "grad_norm": 2.3909872920791635, + "learning_rate": 3.9985263785904216e-05, + "loss": 0.5517, + "step": 61 + }, + { + "epoch": 0.7936, + "grad_norm": 1.8995488455984622, + "learning_rate": 3.997994326483098e-05, + "loss": 0.5545, + "step": 62 + }, + { + "epoch": 0.8064, + "grad_norm": 1.9806874172141407, + "learning_rate": 3.9973804788534234e-05, + "loss": 0.5232, + "step": 63 + }, + { + "epoch": 0.8192, + "grad_norm": 1.826849125317064, + "learning_rate": 3.996684860831595e-05, + "loss": 0.5196, + "step": 64 + }, + { + "epoch": 0.832, + "grad_norm": 2.1118198350321653, + "learning_rate": 3.995907500895389e-05, + "loss": 0.5351, + "step": 65 + }, + { + "epoch": 0.8448, + "grad_norm": 1.853943343385325, + "learning_rate": 3.995048430869002e-05, + "loss": 0.5463, + "step": 66 + }, + { + "epoch": 0.8576, + "grad_norm": 1.2859090452433557, + "learning_rate": 3.994107685921743e-05, + "loss": 0.513, + "step": 67 + }, + { + "epoch": 0.8704, + "grad_norm": 1.3324559576524067, + "learning_rate": 3.993085304566597e-05, + "loss": 0.5388, + "step": 68 + }, + { + "epoch": 0.8832, + "grad_norm": 1.4066383610468145, + "learning_rate": 3.991981328658646e-05, + "loss": 0.5266, + "step": 69 + }, + { + "epoch": 0.896, + "grad_norm": 1.074544255481515, + "learning_rate": 3.990795803393358e-05, + "loss": 0.5289, + "step": 70 + }, + { + "epoch": 0.9088, + "grad_norm": 1.233767803602614, + "learning_rate": 3.989528777304732e-05, + "loss": 0.5176, + "step": 71 + }, + { + "epoch": 0.9216, + "grad_norm": 1.1902967515411367, + "learning_rate": 3.988180302263317e-05, + "loss": 0.5142, + "step": 72 + }, + { + "epoch": 0.9344, + "grad_norm": 0.7468929103292316, + "learning_rate": 3.986750433474084e-05, + "loss": 0.508, + "step": 73 + }, + { + "epoch": 0.9472, + "grad_norm": 1.1721587861444878, + "learning_rate": 3.98523922947417e-05, + "loss": 0.5395, + "step": 74 + }, + { + "epoch": 0.96, + "grad_norm": 0.7706038364138307, + "learning_rate": 3.983646752130476e-05, + "loss": 0.5125, + "step": 75 + }, + { + "epoch": 0.9728, + "grad_norm": 1.0726481772450163, + "learning_rate": 3.981973066637141e-05, + "loss": 0.5029, + "step": 76 + }, + { + "epoch": 0.9856, + "grad_norm": 0.8400687765959799, + "learning_rate": 3.980218241512865e-05, + "loss": 0.5123, + "step": 77 + }, + { + "epoch": 0.9984, + "grad_norm": 0.8535214667511101, + "learning_rate": 3.9783823485981135e-05, + "loss": 0.5277, + "step": 78 + }, + { + "epoch": 1.0112, + "grad_norm": 1.7257143717748409, + "learning_rate": 3.976465463052168e-05, + "loss": 0.9868, + "step": 79 + }, + { + "epoch": 1.024, + "grad_norm": 0.9187320514880281, + "learning_rate": 3.974467663350053e-05, + "loss": 0.409, + "step": 80 + }, + { + "epoch": 1.0368, + "grad_norm": 0.9262130658449447, + "learning_rate": 3.972389031279324e-05, + "loss": 0.47, + "step": 81 + }, + { + "epoch": 1.0496, + "grad_norm": 0.8616469129748918, + "learning_rate": 3.970229651936717e-05, + "loss": 0.4449, + "step": 82 + }, + { + "epoch": 1.0624, + "grad_norm": 1.0518474663616275, + "learning_rate": 3.967989613724666e-05, + "loss": 0.5014, + "step": 83 + }, + { + "epoch": 1.0752, + "grad_norm": 0.8217604631371047, + "learning_rate": 3.965669008347683e-05, + "loss": 0.3972, + "step": 84 + }, + { + "epoch": 1.088, + "grad_norm": 0.9124931535305526, + "learning_rate": 3.963267930808604e-05, + "loss": 0.476, + "step": 85 + }, + { + "epoch": 1.1008, + "grad_norm": 0.7296858629742461, + "learning_rate": 3.9607864794047024e-05, + "loss": 0.4889, + "step": 86 + }, + { + "epoch": 1.1136, + "grad_norm": 0.8289576491901255, + "learning_rate": 3.958224755723661e-05, + "loss": 0.422, + "step": 87 + }, + { + "epoch": 1.1264, + "grad_norm": 0.6516116746500413, + "learning_rate": 3.955582864639413e-05, + "loss": 0.4481, + "step": 88 + }, + { + "epoch": 1.1392, + "grad_norm": 0.6970366182418265, + "learning_rate": 3.952860914307853e-05, + "loss": 0.4095, + "step": 89 + }, + { + "epoch": 1.152, + "grad_norm": 0.7629374723423523, + "learning_rate": 3.950059016162405e-05, + "loss": 0.4876, + "step": 90 + }, + { + "epoch": 1.1648, + "grad_norm": 0.7272520952740609, + "learning_rate": 3.947177284909461e-05, + "loss": 0.467, + "step": 91 + }, + { + "epoch": 1.1776, + "grad_norm": 0.7018243837639311, + "learning_rate": 3.944215838523688e-05, + "loss": 0.4342, + "step": 92 + }, + { + "epoch": 1.1904, + "grad_norm": 0.7721912911057486, + "learning_rate": 3.9411747982431946e-05, + "loss": 0.456, + "step": 93 + }, + { + "epoch": 1.2032, + "grad_norm": 0.8429070071857203, + "learning_rate": 3.93805428856457e-05, + "loss": 0.4618, + "step": 94 + }, + { + "epoch": 1.216, + "grad_norm": 0.8297785735343746, + "learning_rate": 3.934854437237786e-05, + "loss": 0.4565, + "step": 95 + }, + { + "epoch": 1.2288000000000001, + "grad_norm": 0.8148441099919421, + "learning_rate": 3.931575375260967e-05, + "loss": 0.4681, + "step": 96 + }, + { + "epoch": 1.2416, + "grad_norm": 0.74868212519342, + "learning_rate": 3.9282172368750296e-05, + "loss": 0.4657, + "step": 97 + }, + { + "epoch": 1.2544, + "grad_norm": 0.7608065655422503, + "learning_rate": 3.924780159558183e-05, + "loss": 0.4728, + "step": 98 + }, + { + "epoch": 1.2671999999999999, + "grad_norm": 0.5832130148164872, + "learning_rate": 3.921264284020303e-05, + "loss": 0.4464, + "step": 99 + }, + { + "epoch": 1.28, + "grad_norm": 0.7583796982679346, + "learning_rate": 3.917669754197172e-05, + "loss": 0.4781, + "step": 100 + }, + { + "epoch": 1.2928, + "grad_norm": 0.6983145819761016, + "learning_rate": 3.913996717244586e-05, + "loss": 0.4802, + "step": 101 + }, + { + "epoch": 1.3056, + "grad_norm": 0.633883220383747, + "learning_rate": 3.91024532353233e-05, + "loss": 0.4515, + "step": 102 + }, + { + "epoch": 1.3184, + "grad_norm": 0.7293043661363177, + "learning_rate": 3.906415726638019e-05, + "loss": 0.4618, + "step": 103 + }, + { + "epoch": 1.3312, + "grad_norm": 0.71457656680089, + "learning_rate": 3.902508083340819e-05, + "loss": 0.4485, + "step": 104 + }, + { + "epoch": 1.3439999999999999, + "grad_norm": 0.6694072080044774, + "learning_rate": 3.898522553615019e-05, + "loss": 0.4592, + "step": 105 + }, + { + "epoch": 1.3568, + "grad_norm": 0.765617737172502, + "learning_rate": 3.8944593006234875e-05, + "loss": 0.485, + "step": 106 + }, + { + "epoch": 1.3696, + "grad_norm": 0.7145515487305579, + "learning_rate": 3.890318490710991e-05, + "loss": 0.4613, + "step": 107 + }, + { + "epoch": 1.3824, + "grad_norm": 0.6061420766857758, + "learning_rate": 3.8861002933973864e-05, + "loss": 0.4298, + "step": 108 + }, + { + "epoch": 1.3952, + "grad_norm": 0.7012511500544174, + "learning_rate": 3.881804881370678e-05, + "loss": 0.4503, + "step": 109 + }, + { + "epoch": 1.408, + "grad_norm": 0.7186537669109706, + "learning_rate": 3.877432430479948e-05, + "loss": 0.446, + "step": 110 + }, + { + "epoch": 1.4208, + "grad_norm": 0.9561446414998498, + "learning_rate": 3.872983119728159e-05, + "loss": 0.4561, + "step": 111 + }, + { + "epoch": 1.4336, + "grad_norm": 0.8358387016313162, + "learning_rate": 3.868457131264827e-05, + "loss": 0.4322, + "step": 112 + }, + { + "epoch": 1.4464000000000001, + "grad_norm": 0.6628561595064786, + "learning_rate": 3.863854650378561e-05, + "loss": 0.4494, + "step": 113 + }, + { + "epoch": 1.4592, + "grad_norm": 0.8071170431319441, + "learning_rate": 3.85917586548948e-05, + "loss": 0.4782, + "step": 114 + }, + { + "epoch": 1.472, + "grad_norm": 0.8909575463285895, + "learning_rate": 3.8544209681414974e-05, + "loss": 0.4328, + "step": 115 + }, + { + "epoch": 1.4848, + "grad_norm": 0.7776045622327772, + "learning_rate": 3.849590152994482e-05, + "loss": 0.4615, + "step": 116 + }, + { + "epoch": 1.4976, + "grad_norm": 0.5050519210854457, + "learning_rate": 3.844683617816288e-05, + "loss": 0.4351, + "step": 117 + }, + { + "epoch": 1.5104, + "grad_norm": 0.7445309644133907, + "learning_rate": 3.839701563474655e-05, + "loss": 0.4355, + "step": 118 + }, + { + "epoch": 1.5232, + "grad_norm": 0.858712298478702, + "learning_rate": 3.8346441939289894e-05, + "loss": 0.4321, + "step": 119 + }, + { + "epoch": 1.536, + "grad_norm": 0.6986275684709435, + "learning_rate": 3.829511716222016e-05, + "loss": 0.4418, + "step": 120 + }, + { + "epoch": 1.5488, + "grad_norm": 0.4531036376400173, + "learning_rate": 3.824304340471292e-05, + "loss": 0.4563, + "step": 121 + }, + { + "epoch": 1.5615999999999999, + "grad_norm": 0.6997377767041477, + "learning_rate": 3.819022279860618e-05, + "loss": 0.4384, + "step": 122 + }, + { + "epoch": 1.5744, + "grad_norm": 0.8132599800044655, + "learning_rate": 3.813665750631303e-05, + "loss": 0.4326, + "step": 123 + }, + { + "epoch": 1.5872000000000002, + "grad_norm": 0.6506063752645281, + "learning_rate": 3.80823497207331e-05, + "loss": 0.4396, + "step": 124 + }, + { + "epoch": 1.6, + "grad_norm": 0.6030548407595232, + "learning_rate": 3.802730166516285e-05, + "loss": 0.4708, + "step": 125 + }, + { + "epoch": 1.6128, + "grad_norm": 0.7076521473676728, + "learning_rate": 3.79715155932045e-05, + "loss": 0.4474, + "step": 126 + }, + { + "epoch": 1.6256, + "grad_norm": 0.7765139604545522, + "learning_rate": 3.79149937886738e-05, + "loss": 0.4642, + "step": 127 + }, + { + "epoch": 1.6383999999999999, + "grad_norm": 0.5397240679719468, + "learning_rate": 3.78577385655065e-05, + "loss": 0.4276, + "step": 128 + }, + { + "epoch": 1.6512, + "grad_norm": 0.6826274999940021, + "learning_rate": 3.779975226766367e-05, + "loss": 0.4495, + "step": 129 + }, + { + "epoch": 1.6640000000000001, + "grad_norm": 0.7226813373442722, + "learning_rate": 3.774103726903569e-05, + "loss": 0.4378, + "step": 130 + }, + { + "epoch": 1.6768, + "grad_norm": 0.6554425192594432, + "learning_rate": 3.768159597334508e-05, + "loss": 0.4512, + "step": 131 + }, + { + "epoch": 1.6896, + "grad_norm": 0.5515990558761849, + "learning_rate": 3.762143081404812e-05, + "loss": 0.432, + "step": 132 + }, + { + "epoch": 1.7024, + "grad_norm": 0.600550529502125, + "learning_rate": 3.756054425423521e-05, + "loss": 0.4653, + "step": 133 + }, + { + "epoch": 1.7151999999999998, + "grad_norm": 0.6893688591559344, + "learning_rate": 3.749893878653003e-05, + "loss": 0.4542, + "step": 134 + }, + { + "epoch": 1.728, + "grad_norm": 0.7402084524765938, + "learning_rate": 3.743661693298749e-05, + "loss": 0.4349, + "step": 135 + }, + { + "epoch": 1.7408000000000001, + "grad_norm": 0.5839603992364941, + "learning_rate": 3.737358124499048e-05, + "loss": 0.4731, + "step": 136 + }, + { + "epoch": 1.7536, + "grad_norm": 0.7031604105858179, + "learning_rate": 3.730983430314546e-05, + "loss": 0.4731, + "step": 137 + }, + { + "epoch": 1.7664, + "grad_norm": 0.5510962910938753, + "learning_rate": 3.7245378717176746e-05, + "loss": 0.4522, + "step": 138 + }, + { + "epoch": 1.7792, + "grad_norm": 0.5805176267423117, + "learning_rate": 3.7180217125819724e-05, + "loss": 0.4279, + "step": 139 + }, + { + "epoch": 1.792, + "grad_norm": 0.6569058034178186, + "learning_rate": 3.711435219671281e-05, + "loss": 0.4285, + "step": 140 + }, + { + "epoch": 1.8048, + "grad_norm": 0.4782604481285825, + "learning_rate": 3.704778662628822e-05, + "loss": 0.4415, + "step": 141 + }, + { + "epoch": 1.8176, + "grad_norm": 0.6462662309715211, + "learning_rate": 3.69805231396616e-05, + "loss": 0.4497, + "step": 142 + }, + { + "epoch": 1.8304, + "grad_norm": 0.6876661922675077, + "learning_rate": 3.691256449052046e-05, + "loss": 0.48, + "step": 143 + }, + { + "epoch": 1.8432, + "grad_norm": 0.5384325891746345, + "learning_rate": 3.684391346101144e-05, + "loss": 0.44, + "step": 144 + }, + { + "epoch": 1.8559999999999999, + "grad_norm": 0.6637508026767504, + "learning_rate": 3.677457286162642e-05, + "loss": 0.4479, + "step": 145 + }, + { + "epoch": 1.8688, + "grad_norm": 0.6645446611940581, + "learning_rate": 3.6704545531087446e-05, + "loss": 0.4406, + "step": 146 + }, + { + "epoch": 1.8816000000000002, + "grad_norm": 0.5968030708919606, + "learning_rate": 3.663383433623052e-05, + "loss": 0.423, + "step": 147 + }, + { + "epoch": 1.8944, + "grad_norm": 0.5582096002850404, + "learning_rate": 3.6562442171888256e-05, + "loss": 0.4474, + "step": 148 + }, + { + "epoch": 1.9072, + "grad_norm": 0.7402264879185477, + "learning_rate": 3.6490371960771345e-05, + "loss": 0.4793, + "step": 149 + }, + { + "epoch": 1.92, + "grad_norm": 0.8257667428268111, + "learning_rate": 3.641762665334889e-05, + "loss": 0.4507, + "step": 150 + }, + { + "epoch": 1.9327999999999999, + "grad_norm": 0.6316062189840759, + "learning_rate": 3.6344209227727676e-05, + "loss": 0.461, + "step": 151 + }, + { + "epoch": 1.9456, + "grad_norm": 0.6061304680303753, + "learning_rate": 3.6270122689530176e-05, + "loss": 0.4475, + "step": 152 + }, + { + "epoch": 1.9584000000000001, + "grad_norm": 0.6513650194047896, + "learning_rate": 3.619537007177156e-05, + "loss": 0.4499, + "step": 153 + }, + { + "epoch": 1.9712, + "grad_norm": 0.5974181056604952, + "learning_rate": 3.611995443473551e-05, + "loss": 0.4409, + "step": 154 + }, + { + "epoch": 1.984, + "grad_norm": 0.5919313656283548, + "learning_rate": 3.604387886584891e-05, + "loss": 0.4558, + "step": 155 + }, + { + "epoch": 1.9968, + "grad_norm": 0.9347918851120308, + "learning_rate": 3.596714647955549e-05, + "loss": 0.458, + "step": 156 + }, + { + "epoch": 2.0096, + "grad_norm": 1.68882508674077, + "learning_rate": 3.588976041718831e-05, + "loss": 0.7147, + "step": 157 + }, + { + "epoch": 2.0224, + "grad_norm": 0.7396141317421906, + "learning_rate": 3.5811723846841136e-05, + "loss": 0.3494, + "step": 158 + }, + { + "epoch": 2.0352, + "grad_norm": 1.5555619540369099, + "learning_rate": 3.573303996323879e-05, + "loss": 0.3455, + "step": 159 + }, + { + "epoch": 2.048, + "grad_norm": 1.0492526740667485, + "learning_rate": 3.5653711987606295e-05, + "loss": 0.3768, + "step": 160 + }, + { + "epoch": 2.0608, + "grad_norm": 1.1009529864489498, + "learning_rate": 3.557374316753707e-05, + "loss": 0.3405, + "step": 161 + }, + { + "epoch": 2.0736, + "grad_norm": 0.8963852147067644, + "learning_rate": 3.549313677685993e-05, + "loss": 0.3673, + "step": 162 + }, + { + "epoch": 2.0864, + "grad_norm": 1.1353914752902645, + "learning_rate": 3.5411896115505093e-05, + "loss": 0.356, + "step": 163 + }, + { + "epoch": 2.0992, + "grad_norm": 1.1103317507624728, + "learning_rate": 3.5330024509369044e-05, + "loss": 0.3258, + "step": 164 + }, + { + "epoch": 2.112, + "grad_norm": 0.7624332967449798, + "learning_rate": 3.5247525310178416e-05, + "loss": 0.3587, + "step": 165 + }, + { + "epoch": 2.1248, + "grad_norm": 1.0631163535464458, + "learning_rate": 3.516440189535276e-05, + "loss": 0.3255, + "step": 166 + }, + { + "epoch": 2.1376, + "grad_norm": 0.7588188950702179, + "learning_rate": 3.508065766786626e-05, + "loss": 0.353, + "step": 167 + }, + { + "epoch": 2.1504, + "grad_norm": 0.9260850680586817, + "learning_rate": 3.499629605610846e-05, + "loss": 0.3327, + "step": 168 + }, + { + "epoch": 2.1632, + "grad_norm": 0.8857538034310635, + "learning_rate": 3.491132051374386e-05, + "loss": 0.3802, + "step": 169 + }, + { + "epoch": 2.176, + "grad_norm": 0.867301901975402, + "learning_rate": 3.482573451957057e-05, + "loss": 0.3033, + "step": 170 + }, + { + "epoch": 2.1888, + "grad_norm": 0.9623966007879786, + "learning_rate": 3.4739541577377874e-05, + "loss": 0.3535, + "step": 171 + }, + { + "epoch": 2.2016, + "grad_norm": 0.712478214609947, + "learning_rate": 3.4652745215802776e-05, + "loss": 0.3295, + "step": 172 + }, + { + "epoch": 2.2144, + "grad_norm": 0.7561939526359985, + "learning_rate": 3.456534898818556e-05, + "loss": 0.3446, + "step": 173 + }, + { + "epoch": 2.2272, + "grad_norm": 0.7251207662016594, + "learning_rate": 3.447735647242432e-05, + "loss": 0.3549, + "step": 174 + }, + { + "epoch": 2.24, + "grad_norm": 0.5830550912281133, + "learning_rate": 3.4388771270828484e-05, + "loss": 0.3249, + "step": 175 + }, + { + "epoch": 2.2528, + "grad_norm": 0.6750592809315261, + "learning_rate": 3.429959700997133e-05, + "loss": 0.3663, + "step": 176 + }, + { + "epoch": 2.2656, + "grad_norm": 0.5881141320280098, + "learning_rate": 3.4209837340541526e-05, + "loss": 0.31, + "step": 177 + }, + { + "epoch": 2.2784, + "grad_norm": 0.6540406338097797, + "learning_rate": 3.411949593719367e-05, + "loss": 0.3417, + "step": 178 + }, + { + "epoch": 2.2912, + "grad_norm": 0.47356399399718, + "learning_rate": 3.4028576498397875e-05, + "loss": 0.34, + "step": 179 + }, + { + "epoch": 2.304, + "grad_norm": 0.6242152248297176, + "learning_rate": 3.3937082746288314e-05, + "loss": 0.3339, + "step": 180 + }, + { + "epoch": 2.3168, + "grad_norm": 0.4381888293534401, + "learning_rate": 3.384501842651088e-05, + "loss": 0.3125, + "step": 181 + }, + { + "epoch": 2.3296, + "grad_norm": 0.6044780918561927, + "learning_rate": 3.3752387308069844e-05, + "loss": 0.3294, + "step": 182 + }, + { + "epoch": 2.3424, + "grad_norm": 0.48769761285521435, + "learning_rate": 3.365919318317352e-05, + "loss": 0.3279, + "step": 183 + }, + { + "epoch": 2.3552, + "grad_norm": 0.6683750856465323, + "learning_rate": 3.356543986707906e-05, + "loss": 0.3562, + "step": 184 + }, + { + "epoch": 2.368, + "grad_norm": 0.4816943504390966, + "learning_rate": 3.347113119793623e-05, + "loss": 0.3049, + "step": 185 + }, + { + "epoch": 2.3808, + "grad_norm": 0.7481643721907355, + "learning_rate": 3.337627103663029e-05, + "loss": 0.3621, + "step": 186 + }, + { + "epoch": 2.3936, + "grad_norm": 0.6810921053657787, + "learning_rate": 3.328086326662395e-05, + "loss": 0.3571, + "step": 187 + }, + { + "epoch": 2.4064, + "grad_norm": 0.6888563795267724, + "learning_rate": 3.3184911793798354e-05, + "loss": 0.3397, + "step": 188 + }, + { + "epoch": 2.4192, + "grad_norm": 0.5626087628280371, + "learning_rate": 3.3088420546293216e-05, + "loss": 0.3497, + "step": 189 + }, + { + "epoch": 2.432, + "grad_norm": 0.6237987815234062, + "learning_rate": 3.2991393474345963e-05, + "loss": 0.3475, + "step": 190 + }, + { + "epoch": 2.4448, + "grad_norm": 0.6334428971530011, + "learning_rate": 3.2893834550130064e-05, + "loss": 0.3443, + "step": 191 + }, + { + "epoch": 2.4576000000000002, + "grad_norm": 0.5954885982090595, + "learning_rate": 3.279574776759237e-05, + "loss": 0.3255, + "step": 192 + }, + { + "epoch": 2.4704, + "grad_norm": 0.5346994876530767, + "learning_rate": 3.269713714228963e-05, + "loss": 0.3641, + "step": 193 + }, + { + "epoch": 2.4832, + "grad_norm": 0.5233223361539856, + "learning_rate": 3.259800671122412e-05, + "loss": 0.3043, + "step": 194 + }, + { + "epoch": 2.496, + "grad_norm": 0.5902351865314509, + "learning_rate": 3.249836053267832e-05, + "loss": 0.3654, + "step": 195 + }, + { + "epoch": 2.5088, + "grad_norm": 0.5310017789767338, + "learning_rate": 3.239820268604881e-05, + "loss": 0.3679, + "step": 196 + }, + { + "epoch": 2.5216, + "grad_norm": 0.5749019680258777, + "learning_rate": 3.2297537271679246e-05, + "loss": 0.3118, + "step": 197 + }, + { + "epoch": 2.5343999999999998, + "grad_norm": 0.48887240213564087, + "learning_rate": 3.219636841069254e-05, + "loss": 0.345, + "step": 198 + }, + { + "epoch": 2.5472, + "grad_norm": 0.46388293415755155, + "learning_rate": 3.2094700244822076e-05, + "loss": 0.3382, + "step": 199 + }, + { + "epoch": 2.56, + "grad_norm": 0.6580649682431245, + "learning_rate": 3.19925369362422e-05, + "loss": 0.3603, + "step": 200 + }, + { + "epoch": 2.5728, + "grad_norm": 0.5038834916141244, + "learning_rate": 3.1889882667397824e-05, + "loss": 0.3222, + "step": 201 + }, + { + "epoch": 2.5856, + "grad_norm": 0.49563807574498886, + "learning_rate": 3.178674164083319e-05, + "loss": 0.3231, + "step": 202 + }, + { + "epoch": 2.5984, + "grad_norm": 0.575767163541391, + "learning_rate": 3.1683118079019796e-05, + "loss": 0.3394, + "step": 203 + }, + { + "epoch": 2.6112, + "grad_norm": 0.4597102882311115, + "learning_rate": 3.157901622418361e-05, + "loss": 0.3333, + "step": 204 + }, + { + "epoch": 2.624, + "grad_norm": 0.5802249813716531, + "learning_rate": 3.147444033813131e-05, + "loss": 0.3691, + "step": 205 + }, + { + "epoch": 2.6368, + "grad_norm": 0.44036358447569723, + "learning_rate": 3.136939470207587e-05, + "loss": 0.3465, + "step": 206 + }, + { + "epoch": 2.6496, + "grad_norm": 0.517111374711644, + "learning_rate": 3.126388361646128e-05, + "loss": 0.3537, + "step": 207 + }, + { + "epoch": 2.6624, + "grad_norm": 0.5563115115312545, + "learning_rate": 3.115791140078646e-05, + "loss": 0.327, + "step": 208 + }, + { + "epoch": 2.6752000000000002, + "grad_norm": 0.45405966800432573, + "learning_rate": 3.105148239342846e-05, + "loss": 0.3575, + "step": 209 + }, + { + "epoch": 2.6879999999999997, + "grad_norm": 0.6003208308479673, + "learning_rate": 3.0944600951464854e-05, + "loss": 0.3435, + "step": 210 + }, + { + "epoch": 2.7008, + "grad_norm": 0.5629265714220094, + "learning_rate": 3.083727145049533e-05, + "loss": 0.3352, + "step": 211 + }, + { + "epoch": 2.7136, + "grad_norm": 0.505816705000162, + "learning_rate": 3.0729498284462604e-05, + "loss": 0.3412, + "step": 212 + }, + { + "epoch": 2.7264, + "grad_norm": 0.48662004131731706, + "learning_rate": 3.0621285865472506e-05, + "loss": 0.3177, + "step": 213 + }, + { + "epoch": 2.7392, + "grad_norm": 0.5166164187609994, + "learning_rate": 3.051263862361334e-05, + "loss": 0.3613, + "step": 214 + }, + { + "epoch": 2.752, + "grad_norm": 0.45648974173347506, + "learning_rate": 3.040356100677458e-05, + "loss": 0.358, + "step": 215 + }, + { + "epoch": 2.7648, + "grad_norm": 0.48126890974280656, + "learning_rate": 3.0294057480464722e-05, + "loss": 0.3335, + "step": 216 + }, + { + "epoch": 2.7776, + "grad_norm": 0.5006985131245671, + "learning_rate": 3.018413252762849e-05, + "loss": 0.364, + "step": 217 + }, + { + "epoch": 2.7904, + "grad_norm": 0.5570580236592455, + "learning_rate": 3.0073790648463324e-05, + "loss": 0.376, + "step": 218 + }, + { + "epoch": 2.8032, + "grad_norm": 0.5027618867496092, + "learning_rate": 2.9963036360235116e-05, + "loss": 0.3125, + "step": 219 + }, + { + "epoch": 2.816, + "grad_norm": 0.4741017296680652, + "learning_rate": 2.9851874197093305e-05, + "loss": 0.3193, + "step": 220 + }, + { + "epoch": 2.8288, + "grad_norm": 0.5067075189282028, + "learning_rate": 2.974030870988526e-05, + "loss": 0.4042, + "step": 221 + }, + { + "epoch": 2.8416, + "grad_norm": 0.5403290703799045, + "learning_rate": 2.9628344465969937e-05, + "loss": 0.3474, + "step": 222 + }, + { + "epoch": 2.8544, + "grad_norm": 0.5051316383199116, + "learning_rate": 2.951598604903094e-05, + "loss": 0.3425, + "step": 223 + }, + { + "epoch": 2.8672, + "grad_norm": 0.6126411020867858, + "learning_rate": 2.9403238058888838e-05, + "loss": 0.3663, + "step": 224 + }, + { + "epoch": 2.88, + "grad_norm": 0.44805711180182883, + "learning_rate": 2.929010511131286e-05, + "loss": 0.329, + "step": 225 + }, + { + "epoch": 2.8928000000000003, + "grad_norm": 0.47140986418516156, + "learning_rate": 2.9176591837831957e-05, + "loss": 0.3734, + "step": 226 + }, + { + "epoch": 2.9055999999999997, + "grad_norm": 0.4990465943606948, + "learning_rate": 2.906270288554514e-05, + "loss": 0.3695, + "step": 227 + }, + { + "epoch": 2.9184, + "grad_norm": 0.4459572858943639, + "learning_rate": 2.8948442916931302e-05, + "loss": 0.3716, + "step": 228 + }, + { + "epoch": 2.9312, + "grad_norm": 0.4373840770734537, + "learning_rate": 2.8833816609658285e-05, + "loss": 0.3496, + "step": 229 + }, + { + "epoch": 2.944, + "grad_norm": 0.41263208140764535, + "learning_rate": 2.8718828656391408e-05, + "loss": 0.3472, + "step": 230 + }, + { + "epoch": 2.9568, + "grad_norm": 0.47661903476036704, + "learning_rate": 2.8603483764601346e-05, + "loss": 0.3311, + "step": 231 + }, + { + "epoch": 2.9696, + "grad_norm": 0.40467849766325453, + "learning_rate": 2.84877866563714e-05, + "loss": 0.3184, + "step": 232 + }, + { + "epoch": 2.9824, + "grad_norm": 0.550669166928282, + "learning_rate": 2.8371742068204234e-05, + "loss": 0.356, + "step": 233 + }, + { + "epoch": 2.9952, + "grad_norm": 0.5065651003016768, + "learning_rate": 2.8255354750827885e-05, + "loss": 0.3454, + "step": 234 + }, + { + "epoch": 3.008, + "grad_norm": 1.1707581320465479, + "learning_rate": 2.8138629469001348e-05, + "loss": 0.5875, + "step": 235 + }, + { + "epoch": 3.0208, + "grad_norm": 0.620584400015292, + "learning_rate": 2.802157100131947e-05, + "loss": 0.2239, + "step": 236 + }, + { + "epoch": 3.0336, + "grad_norm": 0.5763638461388164, + "learning_rate": 2.7904184140017337e-05, + "loss": 0.2601, + "step": 237 + }, + { + "epoch": 3.0464, + "grad_norm": 0.7318463831016421, + "learning_rate": 2.7786473690774083e-05, + "loss": 0.2515, + "step": 238 + }, + { + "epoch": 3.0592, + "grad_norm": 0.7175785245276742, + "learning_rate": 2.766844447251614e-05, + "loss": 0.2436, + "step": 239 + }, + { + "epoch": 3.072, + "grad_norm": 0.5769486061062518, + "learning_rate": 2.7550101317219976e-05, + "loss": 0.2405, + "step": 240 + }, + { + "epoch": 3.0848, + "grad_norm": 0.7356912225196313, + "learning_rate": 2.7431449069714254e-05, + "loss": 0.2338, + "step": 241 + }, + { + "epoch": 3.0976, + "grad_norm": 0.5482699648987983, + "learning_rate": 2.7312492587481535e-05, + "loss": 0.2527, + "step": 242 + }, + { + "epoch": 3.1104, + "grad_norm": 0.7278855963720802, + "learning_rate": 2.7193236740459358e-05, + "loss": 0.2535, + "step": 243 + }, + { + "epoch": 3.1232, + "grad_norm": 0.5209696005166115, + "learning_rate": 2.707368641084092e-05, + "loss": 0.2277, + "step": 244 + }, + { + "epoch": 3.136, + "grad_norm": 0.5799949293571091, + "learning_rate": 2.695384649287518e-05, + "loss": 0.2519, + "step": 245 + }, + { + "epoch": 3.1488, + "grad_norm": 0.4295211416414721, + "learning_rate": 2.6833721892666513e-05, + "loss": 0.205, + "step": 246 + }, + { + "epoch": 3.1616, + "grad_norm": 0.6078391751071174, + "learning_rate": 2.6713317527973837e-05, + "loss": 0.2811, + "step": 247 + }, + { + "epoch": 3.1744, + "grad_norm": 0.4467418275080068, + "learning_rate": 2.659263832800929e-05, + "loss": 0.218, + "step": 248 + }, + { + "epoch": 3.1872, + "grad_norm": 0.5194811729182617, + "learning_rate": 2.647168923323646e-05, + "loss": 0.2448, + "step": 249 + }, + { + "epoch": 3.2, + "grad_norm": 0.44656028840081957, + "learning_rate": 2.635047519516809e-05, + "loss": 0.2132, + "step": 250 + }, + { + "epoch": 3.2128, + "grad_norm": 0.4800210191899564, + "learning_rate": 2.6229001176163397e-05, + "loss": 0.2365, + "step": 251 + }, + { + "epoch": 3.2256, + "grad_norm": 0.46280327945182453, + "learning_rate": 2.6107272149224915e-05, + "loss": 0.2582, + "step": 252 + }, + { + "epoch": 3.2384, + "grad_norm": 0.48826451973349416, + "learning_rate": 2.5985293097794884e-05, + "loss": 0.2479, + "step": 253 + }, + { + "epoch": 3.2512, + "grad_norm": 0.45436123348613633, + "learning_rate": 2.586306901555128e-05, + "loss": 0.2365, + "step": 254 + }, + { + "epoch": 3.2640000000000002, + "grad_norm": 0.428227995784899, + "learning_rate": 2.5740604906203314e-05, + "loss": 0.2091, + "step": 255 + }, + { + "epoch": 3.2768, + "grad_norm": 0.45158948638472934, + "learning_rate": 2.5617905783286655e-05, + "loss": 0.2552, + "step": 256 + }, + { + "epoch": 3.2896, + "grad_norm": 0.4979540052977787, + "learning_rate": 2.5494976669958128e-05, + "loss": 0.2547, + "step": 257 + }, + { + "epoch": 3.3024, + "grad_norm": 0.4077547533354734, + "learning_rate": 2.537182259879009e-05, + "loss": 0.2113, + "step": 258 + }, + { + "epoch": 3.3152, + "grad_norm": 0.48175196724891634, + "learning_rate": 2.524844861156443e-05, + "loss": 0.2123, + "step": 259 + }, + { + "epoch": 3.328, + "grad_norm": 0.43748528359385047, + "learning_rate": 2.512485975906612e-05, + "loss": 0.2495, + "step": 260 + }, + { + "epoch": 3.3407999999999998, + "grad_norm": 0.5422169999390144, + "learning_rate": 2.5001061100876464e-05, + "loss": 0.2656, + "step": 261 + }, + { + "epoch": 3.3536, + "grad_norm": 0.3582074679304393, + "learning_rate": 2.487705770516598e-05, + "loss": 0.2013, + "step": 262 + }, + { + "epoch": 3.3664, + "grad_norm": 0.42309455082841246, + "learning_rate": 2.4752854648486865e-05, + "loss": 0.2294, + "step": 263 + }, + { + "epoch": 3.3792, + "grad_norm": 0.41194063893489197, + "learning_rate": 2.462845701556523e-05, + "loss": 0.2391, + "step": 264 + }, + { + "epoch": 3.392, + "grad_norm": 0.406353093333956, + "learning_rate": 2.4503869899092893e-05, + "loss": 0.2447, + "step": 265 + }, + { + "epoch": 3.4048, + "grad_norm": 0.4138017967668467, + "learning_rate": 2.437909839951891e-05, + "loss": 0.2337, + "step": 266 + }, + { + "epoch": 3.4176, + "grad_norm": 0.4319021586998612, + "learning_rate": 2.4254147624840753e-05, + "loss": 0.2639, + "step": 267 + }, + { + "epoch": 3.4304, + "grad_norm": 0.42478939518199943, + "learning_rate": 2.4129022690395213e-05, + "loss": 0.2422, + "step": 268 + }, + { + "epoch": 3.4432, + "grad_norm": 0.364790435711411, + "learning_rate": 2.400372871864898e-05, + "loss": 0.2176, + "step": 269 + }, + { + "epoch": 3.456, + "grad_norm": 0.40879420221558926, + "learning_rate": 2.3878270838988912e-05, + "loss": 0.2528, + "step": 270 + }, + { + "epoch": 3.4688, + "grad_norm": 0.39869222794843207, + "learning_rate": 2.3752654187512096e-05, + "loss": 0.2289, + "step": 271 + }, + { + "epoch": 3.4816, + "grad_norm": 0.425952399527957, + "learning_rate": 2.362688390681551e-05, + "loss": 0.2407, + "step": 272 + }, + { + "epoch": 3.4944, + "grad_norm": 0.43270959684387034, + "learning_rate": 2.3500965145785563e-05, + "loss": 0.2779, + "step": 273 + }, + { + "epoch": 3.5072, + "grad_norm": 0.4201617504702752, + "learning_rate": 2.3374903059387252e-05, + "loss": 0.2457, + "step": 274 + }, + { + "epoch": 3.52, + "grad_norm": 0.38118856610528007, + "learning_rate": 2.3248702808453146e-05, + "loss": 0.2271, + "step": 275 + }, + { + "epoch": 3.5328, + "grad_norm": 0.3985845904701707, + "learning_rate": 2.3122369559472122e-05, + "loss": 0.2356, + "step": 276 + }, + { + "epoch": 3.5456, + "grad_norm": 0.38237515015330653, + "learning_rate": 2.2995908484377827e-05, + "loss": 0.2455, + "step": 277 + }, + { + "epoch": 3.5584, + "grad_norm": 0.3732656080587104, + "learning_rate": 2.2869324760336974e-05, + "loss": 0.2197, + "step": 278 + }, + { + "epoch": 3.5712, + "grad_norm": 0.3862117275595557, + "learning_rate": 2.2742623569537345e-05, + "loss": 0.2407, + "step": 279 + }, + { + "epoch": 3.584, + "grad_norm": 0.3667106893274838, + "learning_rate": 2.261581009897571e-05, + "loss": 0.2413, + "step": 280 + }, + { + "epoch": 3.5968, + "grad_norm": 0.4092835203483317, + "learning_rate": 2.2488889540245414e-05, + "loss": 0.2473, + "step": 281 + }, + { + "epoch": 3.6096, + "grad_norm": 0.3234994874357464, + "learning_rate": 2.2361867089323873e-05, + "loss": 0.2156, + "step": 282 + }, + { + "epoch": 3.6224, + "grad_norm": 0.4039677518774243, + "learning_rate": 2.223474794635985e-05, + "loss": 0.2383, + "step": 283 + }, + { + "epoch": 3.6352, + "grad_norm": 0.32831588402257283, + "learning_rate": 2.2107537315460568e-05, + "loss": 0.2189, + "step": 284 + }, + { + "epoch": 3.648, + "grad_norm": 0.368435445481273, + "learning_rate": 2.198024040447865e-05, + "loss": 0.2408, + "step": 285 + }, + { + "epoch": 3.6608, + "grad_norm": 0.3344541454476145, + "learning_rate": 2.1852862424798934e-05, + "loss": 0.2246, + "step": 286 + }, + { + "epoch": 3.6736, + "grad_norm": 0.3610577248521619, + "learning_rate": 2.17254085911251e-05, + "loss": 0.2558, + "step": 287 + }, + { + "epoch": 3.6864, + "grad_norm": 0.3447647268529026, + "learning_rate": 2.1597884121266215e-05, + "loss": 0.234, + "step": 288 + }, + { + "epoch": 3.6992000000000003, + "grad_norm": 0.3733623864161173, + "learning_rate": 2.14702942359231e-05, + "loss": 0.2528, + "step": 289 + }, + { + "epoch": 3.7119999999999997, + "grad_norm": 0.3555964389168844, + "learning_rate": 2.1342644158474614e-05, + "loss": 0.2333, + "step": 290 + }, + { + "epoch": 3.7248, + "grad_norm": 0.375041889099984, + "learning_rate": 2.12149391147638e-05, + "loss": 0.2293, + "step": 291 + }, + { + "epoch": 3.7376, + "grad_norm": 0.3753913119349554, + "learning_rate": 2.1087184332883965e-05, + "loss": 0.2681, + "step": 292 + }, + { + "epoch": 3.7504, + "grad_norm": 0.35812620707782256, + "learning_rate": 2.0959385042964632e-05, + "loss": 0.2572, + "step": 293 + }, + { + "epoch": 3.7632, + "grad_norm": 0.35370558498337545, + "learning_rate": 2.083154647695743e-05, + "loss": 0.2454, + "step": 294 + }, + { + "epoch": 3.776, + "grad_norm": 0.33944645923018973, + "learning_rate": 2.0703673868421914e-05, + "loss": 0.2244, + "step": 295 + }, + { + "epoch": 3.7888, + "grad_norm": 0.43600248171400513, + "learning_rate": 2.057577245231128e-05, + "loss": 0.2802, + "step": 296 + }, + { + "epoch": 3.8016, + "grad_norm": 0.3514694761026882, + "learning_rate": 2.0447847464758097e-05, + "loss": 0.2164, + "step": 297 + }, + { + "epoch": 3.8144, + "grad_norm": 0.3838479862720407, + "learning_rate": 2.0319904142859905e-05, + "loss": 0.2501, + "step": 298 + }, + { + "epoch": 3.8272, + "grad_norm": 0.402834531654162, + "learning_rate": 2.019194772446482e-05, + "loss": 0.246, + "step": 299 + }, + { + "epoch": 3.84, + "grad_norm": 0.32974960672809106, + "learning_rate": 2.006398344795715e-05, + "loss": 0.2276, + "step": 300 + }, + { + "epoch": 3.8528000000000002, + "grad_norm": 0.36392611703656436, + "learning_rate": 1.993601655204286e-05, + "loss": 0.2232, + "step": 301 + }, + { + "epoch": 3.8656, + "grad_norm": 0.3078085468561006, + "learning_rate": 1.9808052275535182e-05, + "loss": 0.2267, + "step": 302 + }, + { + "epoch": 3.8784, + "grad_norm": 0.3888124374503237, + "learning_rate": 1.96800958571401e-05, + "loss": 0.2225, + "step": 303 + }, + { + "epoch": 3.8912, + "grad_norm": 0.37003653365201067, + "learning_rate": 1.955215253524191e-05, + "loss": 0.253, + "step": 304 + }, + { + "epoch": 3.904, + "grad_norm": 0.4409141347947413, + "learning_rate": 1.9424227547688722e-05, + "loss": 0.2538, + "step": 305 + }, + { + "epoch": 3.9168, + "grad_norm": 0.33863563531226637, + "learning_rate": 1.9296326131578093e-05, + "loss": 0.2453, + "step": 306 + }, + { + "epoch": 3.9295999999999998, + "grad_norm": 0.43767186797123386, + "learning_rate": 1.916845352304257e-05, + "loss": 0.2335, + "step": 307 + }, + { + "epoch": 3.9424, + "grad_norm": 0.3701221709120628, + "learning_rate": 1.904061495703537e-05, + "loss": 0.2408, + "step": 308 + }, + { + "epoch": 3.9552, + "grad_norm": 0.4000488195902585, + "learning_rate": 1.8912815667116038e-05, + "loss": 0.2393, + "step": 309 + }, + { + "epoch": 3.968, + "grad_norm": 0.3291939266066057, + "learning_rate": 1.87850608852362e-05, + "loss": 0.2437, + "step": 310 + }, + { + "epoch": 3.9808, + "grad_norm": 0.3752298897806994, + "learning_rate": 1.8657355841525396e-05, + "loss": 0.2537, + "step": 311 + }, + { + "epoch": 3.9936, + "grad_norm": 0.33430834935473724, + "learning_rate": 1.8529705764076905e-05, + "loss": 0.2408, + "step": 312 + }, + { + "epoch": 4.0064, + "grad_norm": 0.909382249596848, + "learning_rate": 1.840211587873379e-05, + "loss": 0.3532, + "step": 313 + }, + { + "epoch": 4.0192, + "grad_norm": 0.4310906385465686, + "learning_rate": 1.82745914088749e-05, + "loss": 0.1459, + "step": 314 + }, + { + "epoch": 4.032, + "grad_norm": 0.40574720154778543, + "learning_rate": 1.8147137575201076e-05, + "loss": 0.1472, + "step": 315 + }, + { + "epoch": 4.0448, + "grad_norm": 0.6093359073366565, + "learning_rate": 1.8019759595521358e-05, + "loss": 0.1701, + "step": 316 + }, + { + "epoch": 4.0576, + "grad_norm": 0.4920569212315349, + "learning_rate": 1.789246268453944e-05, + "loss": 0.1576, + "step": 317 + }, + { + "epoch": 4.0704, + "grad_norm": 0.4877907338475741, + "learning_rate": 1.7765252053640157e-05, + "loss": 0.1669, + "step": 318 + }, + { + "epoch": 4.0832, + "grad_norm": 0.4533612882213416, + "learning_rate": 1.7638132910676134e-05, + "loss": 0.1708, + "step": 319 + }, + { + "epoch": 4.096, + "grad_norm": 0.36478829337463853, + "learning_rate": 1.751111045975459e-05, + "loss": 0.1308, + "step": 320 + }, + { + "epoch": 4.1088, + "grad_norm": 0.4673076443480191, + "learning_rate": 1.738418990102429e-05, + "loss": 0.1682, + "step": 321 + }, + { + "epoch": 4.1216, + "grad_norm": 0.4130602587529781, + "learning_rate": 1.725737643046266e-05, + "loss": 0.1522, + "step": 322 + }, + { + "epoch": 4.1344, + "grad_norm": 0.4341361583946463, + "learning_rate": 1.7130675239663033e-05, + "loss": 0.1541, + "step": 323 + }, + { + "epoch": 4.1472, + "grad_norm": 0.40016423381977084, + "learning_rate": 1.7004091515622173e-05, + "loss": 0.1504, + "step": 324 + }, + { + "epoch": 4.16, + "grad_norm": 0.42920828279796386, + "learning_rate": 1.6877630440527885e-05, + "loss": 0.1463, + "step": 325 + }, + { + "epoch": 4.1728, + "grad_norm": 0.4107476302460468, + "learning_rate": 1.675129719154686e-05, + "loss": 0.1712, + "step": 326 + }, + { + "epoch": 4.1856, + "grad_norm": 0.421702005417959, + "learning_rate": 1.6625096940612758e-05, + "loss": 0.1582, + "step": 327 + }, + { + "epoch": 4.1984, + "grad_norm": 0.35270460243933205, + "learning_rate": 1.649903485421445e-05, + "loss": 0.1519, + "step": 328 + }, + { + "epoch": 4.2112, + "grad_norm": 0.3787760485501793, + "learning_rate": 1.6373116093184495e-05, + "loss": 0.152, + "step": 329 + }, + { + "epoch": 4.224, + "grad_norm": 0.35542585180643543, + "learning_rate": 1.624734581248791e-05, + "loss": 0.1403, + "step": 330 + }, + { + "epoch": 4.2368, + "grad_norm": 0.36324202783135395, + "learning_rate": 1.6121729161011085e-05, + "loss": 0.1433, + "step": 331 + }, + { + "epoch": 4.2496, + "grad_norm": 0.3792486507898538, + "learning_rate": 1.5996271281351028e-05, + "loss": 0.1391, + "step": 332 + }, + { + "epoch": 4.2624, + "grad_norm": 0.3473181132349184, + "learning_rate": 1.587097730960479e-05, + "loss": 0.1251, + "step": 333 + }, + { + "epoch": 4.2752, + "grad_norm": 0.32774630705591523, + "learning_rate": 1.574585237515925e-05, + "loss": 0.1368, + "step": 334 + }, + { + "epoch": 4.288, + "grad_norm": 0.36420129915015437, + "learning_rate": 1.5620901600481098e-05, + "loss": 0.1528, + "step": 335 + }, + { + "epoch": 4.3008, + "grad_norm": 0.3257369647693055, + "learning_rate": 1.5496130100907114e-05, + "loss": 0.1585, + "step": 336 + }, + { + "epoch": 4.3136, + "grad_norm": 0.31078781425198293, + "learning_rate": 1.5371542984434775e-05, + "loss": 0.1396, + "step": 337 + }, + { + "epoch": 4.3264, + "grad_norm": 0.35096965427751897, + "learning_rate": 1.5247145351513137e-05, + "loss": 0.1795, + "step": 338 + }, + { + "epoch": 4.3392, + "grad_norm": 0.31748462140242223, + "learning_rate": 1.5122942294834031e-05, + "loss": 0.1492, + "step": 339 + }, + { + "epoch": 4.352, + "grad_norm": 0.3592126234671409, + "learning_rate": 1.499893889912354e-05, + "loss": 0.1639, + "step": 340 + }, + { + "epoch": 4.3648, + "grad_norm": 0.3357832784658898, + "learning_rate": 1.4875140240933886e-05, + "loss": 0.1461, + "step": 341 + }, + { + "epoch": 4.3776, + "grad_norm": 0.33572402102576526, + "learning_rate": 1.4751551388435576e-05, + "loss": 0.1292, + "step": 342 + }, + { + "epoch": 4.3904, + "grad_norm": 0.39703969920878845, + "learning_rate": 1.4628177401209916e-05, + "loss": 0.2001, + "step": 343 + }, + { + "epoch": 4.4032, + "grad_norm": 0.3082100040904492, + "learning_rate": 1.4505023330041879e-05, + "loss": 0.1282, + "step": 344 + }, + { + "epoch": 4.416, + "grad_norm": 0.35087116310392413, + "learning_rate": 1.4382094216713345e-05, + "loss": 0.1459, + "step": 345 + }, + { + "epoch": 4.4288, + "grad_norm": 0.34352246467690006, + "learning_rate": 1.4259395093796689e-05, + "loss": 0.1462, + "step": 346 + }, + { + "epoch": 4.4416, + "grad_norm": 0.3539760852726465, + "learning_rate": 1.4136930984448722e-05, + "loss": 0.1507, + "step": 347 + }, + { + "epoch": 4.4544, + "grad_norm": 0.33563922640509175, + "learning_rate": 1.4014706902205114e-05, + "loss": 0.1364, + "step": 348 + }, + { + "epoch": 4.4672, + "grad_norm": 0.3310662314502733, + "learning_rate": 1.3892727850775092e-05, + "loss": 0.1515, + "step": 349 + }, + { + "epoch": 4.48, + "grad_norm": 0.34201559486194577, + "learning_rate": 1.3770998823836608e-05, + "loss": 0.1606, + "step": 350 + }, + { + "epoch": 4.4928, + "grad_norm": 0.333112082877024, + "learning_rate": 1.3649524804831915e-05, + "loss": 0.1367, + "step": 351 + }, + { + "epoch": 4.5056, + "grad_norm": 0.3482364710131343, + "learning_rate": 1.3528310766763544e-05, + "loss": 0.1553, + "step": 352 + }, + { + "epoch": 4.5184, + "grad_norm": 0.3221419556427051, + "learning_rate": 1.3407361671990717e-05, + "loss": 0.142, + "step": 353 + }, + { + "epoch": 4.5312, + "grad_norm": 0.3162750341141183, + "learning_rate": 1.3286682472026171e-05, + "loss": 0.1345, + "step": 354 + }, + { + "epoch": 4.5440000000000005, + "grad_norm": 0.3459384680722617, + "learning_rate": 1.316627810733349e-05, + "loss": 0.15, + "step": 355 + }, + { + "epoch": 4.5568, + "grad_norm": 0.3088476211153587, + "learning_rate": 1.3046153507124823e-05, + "loss": 0.1353, + "step": 356 + }, + { + "epoch": 4.5696, + "grad_norm": 0.32355485484922075, + "learning_rate": 1.2926313589159087e-05, + "loss": 0.1416, + "step": 357 + }, + { + "epoch": 4.5824, + "grad_norm": 0.3172828460504271, + "learning_rate": 1.2806763259540649e-05, + "loss": 0.1455, + "step": 358 + }, + { + "epoch": 4.5952, + "grad_norm": 0.31594903154371135, + "learning_rate": 1.2687507412518478e-05, + "loss": 0.1425, + "step": 359 + }, + { + "epoch": 4.608, + "grad_norm": 0.28722609114916, + "learning_rate": 1.256855093028575e-05, + "loss": 0.1251, + "step": 360 + }, + { + "epoch": 4.6208, + "grad_norm": 0.3494860219590851, + "learning_rate": 1.2449898682780034e-05, + "loss": 0.1643, + "step": 361 + }, + { + "epoch": 4.6336, + "grad_norm": 0.2792982354613206, + "learning_rate": 1.2331555527483863e-05, + "loss": 0.1238, + "step": 362 + }, + { + "epoch": 4.6464, + "grad_norm": 0.34708282948447133, + "learning_rate": 1.2213526309225925e-05, + "loss": 0.1572, + "step": 363 + }, + { + "epoch": 4.6592, + "grad_norm": 0.30907236312253966, + "learning_rate": 1.2095815859982666e-05, + "loss": 0.1457, + "step": 364 + }, + { + "epoch": 4.672, + "grad_norm": 0.330593410029408, + "learning_rate": 1.1978428998680534e-05, + "loss": 0.1573, + "step": 365 + }, + { + "epoch": 4.6848, + "grad_norm": 0.3063338936126667, + "learning_rate": 1.1861370530998659e-05, + "loss": 0.1313, + "step": 366 + }, + { + "epoch": 4.6975999999999996, + "grad_norm": 0.3092050471454206, + "learning_rate": 1.1744645249172122e-05, + "loss": 0.1334, + "step": 367 + }, + { + "epoch": 4.7104, + "grad_norm": 0.31926202851312846, + "learning_rate": 1.1628257931795774e-05, + "loss": 0.1517, + "step": 368 + }, + { + "epoch": 4.7232, + "grad_norm": 0.27438667357341145, + "learning_rate": 1.1512213343628602e-05, + "loss": 0.1325, + "step": 369 + }, + { + "epoch": 4.736, + "grad_norm": 0.30486319248530797, + "learning_rate": 1.1396516235398668e-05, + "loss": 0.141, + "step": 370 + }, + { + "epoch": 4.7488, + "grad_norm": 0.3277252504475326, + "learning_rate": 1.1281171343608592e-05, + "loss": 0.1589, + "step": 371 + }, + { + "epoch": 4.7616, + "grad_norm": 0.31380641171615914, + "learning_rate": 1.1166183390341713e-05, + "loss": 0.1539, + "step": 372 + }, + { + "epoch": 4.7744, + "grad_norm": 0.27802001379095087, + "learning_rate": 1.10515570830687e-05, + "loss": 0.1171, + "step": 373 + }, + { + "epoch": 4.7872, + "grad_norm": 0.3387070969699864, + "learning_rate": 1.0937297114454867e-05, + "loss": 0.1551, + "step": 374 + }, + { + "epoch": 4.8, + "grad_norm": 0.3423477879004459, + "learning_rate": 1.082340816216805e-05, + "loss": 0.1816, + "step": 375 + }, + { + "epoch": 4.8128, + "grad_norm": 0.2835804016433388, + "learning_rate": 1.0709894888687145e-05, + "loss": 0.1219, + "step": 376 + }, + { + "epoch": 4.8256, + "grad_norm": 0.30445425411648763, + "learning_rate": 1.0596761941111169e-05, + "loss": 0.1438, + "step": 377 + }, + { + "epoch": 4.8384, + "grad_norm": 0.2974271887909385, + "learning_rate": 1.0484013950969056e-05, + "loss": 0.1448, + "step": 378 + }, + { + "epoch": 4.8512, + "grad_norm": 0.2829878963033833, + "learning_rate": 1.0371655534030061e-05, + "loss": 0.1394, + "step": 379 + }, + { + "epoch": 4.864, + "grad_norm": 0.3168908715483024, + "learning_rate": 1.0259691290114744e-05, + "loss": 0.1482, + "step": 380 + }, + { + "epoch": 4.8768, + "grad_norm": 0.2902424139282325, + "learning_rate": 1.0148125802906704e-05, + "loss": 0.1309, + "step": 381 + }, + { + "epoch": 4.8896, + "grad_norm": 0.28123559328151027, + "learning_rate": 1.0036963639764892e-05, + "loss": 0.1391, + "step": 382 + }, + { + "epoch": 4.9024, + "grad_norm": 0.3355658849713151, + "learning_rate": 9.92620935153669e-06, + "loss": 0.1593, + "step": 383 + }, + { + "epoch": 4.9152000000000005, + "grad_norm": 0.27897881946986414, + "learning_rate": 9.815867472371515e-06, + "loss": 0.1333, + "step": 384 + }, + { + "epoch": 4.928, + "grad_norm": 0.3183236125485041, + "learning_rate": 9.705942519535284e-06, + "loss": 0.1506, + "step": 385 + }, + { + "epoch": 4.9408, + "grad_norm": 0.3049827192706868, + "learning_rate": 9.59643899322542e-06, + "loss": 0.1509, + "step": 386 + }, + { + "epoch": 4.9536, + "grad_norm": 0.2858699032372514, + "learning_rate": 9.487361376386661e-06, + "loss": 0.1308, + "step": 387 + }, + { + "epoch": 4.9664, + "grad_norm": 0.2913513182816591, + "learning_rate": 9.378714134527503e-06, + "loss": 0.1438, + "step": 388 + }, + { + "epoch": 4.9792, + "grad_norm": 0.3053549644512981, + "learning_rate": 9.270501715537392e-06, + "loss": 0.1525, + "step": 389 + }, + { + "epoch": 4.992, + "grad_norm": 0.3132718395321514, + "learning_rate": 9.162728549504675e-06, + "loss": 0.1439, + "step": 390 + }, + { + "epoch": 5.0048, + "grad_norm": 0.8707671150228724, + "learning_rate": 9.055399048535153e-06, + "loss": 0.1964, + "step": 391 + }, + { + "epoch": 5.0176, + "grad_norm": 0.39054630324184525, + "learning_rate": 8.948517606571548e-06, + "loss": 0.0856, + "step": 392 + }, + { + "epoch": 5.0304, + "grad_norm": 0.38007443731247337, + "learning_rate": 8.842088599213545e-06, + "loss": 0.097, + "step": 393 + }, + { + "epoch": 5.0432, + "grad_norm": 0.30708666949205676, + "learning_rate": 8.736116383538726e-06, + "loss": 0.0855, + "step": 394 + }, + { + "epoch": 5.056, + "grad_norm": 0.36470044425057635, + "learning_rate": 8.630605297924132e-06, + "loss": 0.075, + "step": 395 + }, + { + "epoch": 5.0688, + "grad_norm": 0.4634764402379278, + "learning_rate": 8.525559661868692e-06, + "loss": 0.0828, + "step": 396 + }, + { + "epoch": 5.0816, + "grad_norm": 0.37047664644415645, + "learning_rate": 8.420983775816402e-06, + "loss": 0.0818, + "step": 397 + }, + { + "epoch": 5.0944, + "grad_norm": 0.33388419569865535, + "learning_rate": 8.316881920980207e-06, + "loss": 0.0967, + "step": 398 + }, + { + "epoch": 5.1072, + "grad_norm": 0.29708449854774804, + "learning_rate": 8.213258359166823e-06, + "loss": 0.0873, + "step": 399 + }, + { + "epoch": 5.12, + "grad_norm": 0.323665531189395, + "learning_rate": 8.110117332602175e-06, + "loss": 0.1032, + "step": 400 + }, + { + "epoch": 5.1328, + "grad_norm": 0.3328853139713512, + "learning_rate": 8.0074630637578e-06, + "loss": 0.0926, + "step": 401 + }, + { + "epoch": 5.1456, + "grad_norm": 0.2581244268581389, + "learning_rate": 7.905299755177929e-06, + "loss": 0.0683, + "step": 402 + }, + { + "epoch": 5.1584, + "grad_norm": 0.3058625811208563, + "learning_rate": 7.803631589307458e-06, + "loss": 0.0955, + "step": 403 + }, + { + "epoch": 5.1712, + "grad_norm": 0.2980858661173279, + "learning_rate": 7.702462728320759e-06, + "loss": 0.0855, + "step": 404 + }, + { + "epoch": 5.184, + "grad_norm": 0.2926274107334555, + "learning_rate": 7.601797313951198e-06, + "loss": 0.0766, + "step": 405 + }, + { + "epoch": 5.1968, + "grad_norm": 0.34341674424270835, + "learning_rate": 7.501639467321688e-06, + "loss": 0.0922, + "step": 406 + }, + { + "epoch": 5.2096, + "grad_norm": 0.28146578162575314, + "learning_rate": 7.401993288775888e-06, + "loss": 0.0864, + "step": 407 + }, + { + "epoch": 5.2224, + "grad_norm": 0.3091916861391297, + "learning_rate": 7.3028628577103754e-06, + "loss": 0.0908, + "step": 408 + }, + { + "epoch": 5.2352, + "grad_norm": 0.27533725921725816, + "learning_rate": 7.204252232407638e-06, + "loss": 0.0831, + "step": 409 + }, + { + "epoch": 5.248, + "grad_norm": 0.2929332015338904, + "learning_rate": 7.106165449869946e-06, + "loss": 0.0883, + "step": 410 + }, + { + "epoch": 5.2608, + "grad_norm": 0.27623225456083456, + "learning_rate": 7.008606525654045e-06, + "loss": 0.0782, + "step": 411 + }, + { + "epoch": 5.2736, + "grad_norm": 0.288011722575726, + "learning_rate": 6.911579453706787e-06, + "loss": 0.0799, + "step": 412 + }, + { + "epoch": 5.2864, + "grad_norm": 0.2808173486775667, + "learning_rate": 6.815088206201648e-06, + "loss": 0.084, + "step": 413 + }, + { + "epoch": 5.2992, + "grad_norm": 0.2769334215855372, + "learning_rate": 6.719136733376057e-06, + "loss": 0.0897, + "step": 414 + }, + { + "epoch": 5.312, + "grad_norm": 0.2640890010895359, + "learning_rate": 6.623728963369715e-06, + "loss": 0.0785, + "step": 415 + }, + { + "epoch": 5.3248, + "grad_norm": 0.28366255851169087, + "learning_rate": 6.528868802063774e-06, + "loss": 0.0861, + "step": 416 + }, + { + "epoch": 5.3376, + "grad_norm": 0.26612785503838554, + "learning_rate": 6.434560132920944e-06, + "loss": 0.0726, + "step": 417 + }, + { + "epoch": 5.3504, + "grad_norm": 0.2566370337258043, + "learning_rate": 6.340806816826486e-06, + "loss": 0.0719, + "step": 418 + }, + { + "epoch": 5.3632, + "grad_norm": 0.2802651648602639, + "learning_rate": 6.2476126919301604e-06, + "loss": 0.0849, + "step": 419 + }, + { + "epoch": 5.376, + "grad_norm": 0.26234153435624524, + "learning_rate": 6.154981573489125e-06, + "loss": 0.0861, + "step": 420 + }, + { + "epoch": 5.3888, + "grad_norm": 0.25013916978026923, + "learning_rate": 6.062917253711697e-06, + "loss": 0.0759, + "step": 421 + }, + { + "epoch": 5.4016, + "grad_norm": 0.2782322390161653, + "learning_rate": 5.971423501602136e-06, + "loss": 0.0975, + "step": 422 + }, + { + "epoch": 5.4144, + "grad_norm": 0.25853590872421234, + "learning_rate": 5.880504062806329e-06, + "loss": 0.0776, + "step": 423 + }, + { + "epoch": 5.4272, + "grad_norm": 0.2632918340497073, + "learning_rate": 5.790162659458478e-06, + "loss": 0.0793, + "step": 424 + }, + { + "epoch": 5.44, + "grad_norm": 0.2807515354914946, + "learning_rate": 5.700402990028675e-06, + "loss": 0.0926, + "step": 425 + }, + { + "epoch": 5.4528, + "grad_norm": 0.2701285303742261, + "learning_rate": 5.611228729171516e-06, + "loss": 0.0907, + "step": 426 + }, + { + "epoch": 5.4656, + "grad_norm": 0.23610290783563515, + "learning_rate": 5.522643527575682e-06, + "loss": 0.0655, + "step": 427 + }, + { + "epoch": 5.4784, + "grad_norm": 0.2799093514778747, + "learning_rate": 5.434651011814447e-06, + "loss": 0.0859, + "step": 428 + }, + { + "epoch": 5.4912, + "grad_norm": 0.23884787730117085, + "learning_rate": 5.347254784197233e-06, + "loss": 0.0665, + "step": 429 + }, + { + "epoch": 5.504, + "grad_norm": 0.24803806185942293, + "learning_rate": 5.260458422622128e-06, + "loss": 0.0706, + "step": 430 + }, + { + "epoch": 5.5168, + "grad_norm": 0.24986860431317282, + "learning_rate": 5.1742654804294346e-06, + "loss": 0.0733, + "step": 431 + }, + { + "epoch": 5.5296, + "grad_norm": 0.25232462132822314, + "learning_rate": 5.088679486256141e-06, + "loss": 0.0841, + "step": 432 + }, + { + "epoch": 5.5424, + "grad_norm": 0.26863695864156556, + "learning_rate": 5.003703943891545e-06, + "loss": 0.0909, + "step": 433 + }, + { + "epoch": 5.5552, + "grad_norm": 0.26379924980992814, + "learning_rate": 4.919342332133738e-06, + "loss": 0.0802, + "step": 434 + }, + { + "epoch": 5.568, + "grad_norm": 0.25337851637428144, + "learning_rate": 4.835598104647243e-06, + "loss": 0.0784, + "step": 435 + }, + { + "epoch": 5.5808, + "grad_norm": 0.2855931530520814, + "learning_rate": 4.752474689821587e-06, + "loss": 0.0905, + "step": 436 + }, + { + "epoch": 5.5936, + "grad_norm": 0.2653743725914835, + "learning_rate": 4.669975490630956e-06, + "loss": 0.09, + "step": 437 + }, + { + "epoch": 5.6064, + "grad_norm": 0.24324675052642777, + "learning_rate": 4.588103884494914e-06, + "loss": 0.0779, + "step": 438 + }, + { + "epoch": 5.6192, + "grad_norm": 0.28836723375731815, + "learning_rate": 4.50686322314007e-06, + "loss": 0.0899, + "step": 439 + }, + { + "epoch": 5.632, + "grad_norm": 0.27824379721099174, + "learning_rate": 4.426256832462936e-06, + "loss": 0.0819, + "step": 440 + }, + { + "epoch": 5.6448, + "grad_norm": 0.25867262760227655, + "learning_rate": 4.346288012393707e-06, + "loss": 0.0796, + "step": 441 + }, + { + "epoch": 5.6576, + "grad_norm": 0.2540036528454018, + "learning_rate": 4.266960036761216e-06, + "loss": 0.0772, + "step": 442 + }, + { + "epoch": 5.6704, + "grad_norm": 0.2403694214215447, + "learning_rate": 4.188276153158866e-06, + "loss": 0.0785, + "step": 443 + }, + { + "epoch": 5.6832, + "grad_norm": 0.2719134198375216, + "learning_rate": 4.110239582811693e-06, + "loss": 0.0893, + "step": 444 + }, + { + "epoch": 5.696, + "grad_norm": 0.22647867415580442, + "learning_rate": 4.032853520444518e-06, + "loss": 0.0672, + "step": 445 + }, + { + "epoch": 5.7088, + "grad_norm": 0.27361004742591205, + "learning_rate": 3.9561211341510945e-06, + "loss": 0.0958, + "step": 446 + }, + { + "epoch": 5.7216000000000005, + "grad_norm": 0.2768586626290287, + "learning_rate": 3.880045565264496e-06, + "loss": 0.0845, + "step": 447 + }, + { + "epoch": 5.7344, + "grad_norm": 0.24049847606098695, + "learning_rate": 3.804629928228438e-06, + "loss": 0.0826, + "step": 448 + }, + { + "epoch": 5.7472, + "grad_norm": 0.2647770307338421, + "learning_rate": 3.7298773104698273e-06, + "loss": 0.0872, + "step": 449 + }, + { + "epoch": 5.76, + "grad_norm": 0.24567196188345414, + "learning_rate": 3.655790772272332e-06, + "loss": 0.072, + "step": 450 + }, + { + "epoch": 5.7728, + "grad_norm": 0.25557146471035863, + "learning_rate": 3.582373346651111e-06, + "loss": 0.0845, + "step": 451 + }, + { + "epoch": 5.7856, + "grad_norm": 0.24864423351249698, + "learning_rate": 3.5096280392286676e-06, + "loss": 0.0821, + "step": 452 + }, + { + "epoch": 5.7984, + "grad_norm": 0.2629783009150278, + "learning_rate": 3.437557828111746e-06, + "loss": 0.0954, + "step": 453 + }, + { + "epoch": 5.8112, + "grad_norm": 0.2435300816146765, + "learning_rate": 3.366165663769483e-06, + "loss": 0.0795, + "step": 454 + }, + { + "epoch": 5.824, + "grad_norm": 0.2536128868225129, + "learning_rate": 3.2954544689125578e-06, + "loss": 0.0829, + "step": 455 + }, + { + "epoch": 5.8368, + "grad_norm": 0.26326100623271814, + "learning_rate": 3.225427138373589e-06, + "loss": 0.0858, + "step": 456 + }, + { + "epoch": 5.8496, + "grad_norm": 0.24822954283948143, + "learning_rate": 3.156086538988563e-06, + "loss": 0.0725, + "step": 457 + }, + { + "epoch": 5.8624, + "grad_norm": 0.24403030181937907, + "learning_rate": 3.0874355094795484e-06, + "loss": 0.083, + "step": 458 + }, + { + "epoch": 5.8751999999999995, + "grad_norm": 0.30479561935813754, + "learning_rate": 3.0194768603384083e-06, + "loss": 0.0941, + "step": 459 + }, + { + "epoch": 5.888, + "grad_norm": 0.26001164187141773, + "learning_rate": 2.952213373711783e-06, + "loss": 0.0799, + "step": 460 + }, + { + "epoch": 5.9008, + "grad_norm": 0.26744959620234826, + "learning_rate": 2.8856478032871906e-06, + "loss": 0.086, + "step": 461 + }, + { + "epoch": 5.9136, + "grad_norm": 0.2479889061044048, + "learning_rate": 2.819782874180277e-06, + "loss": 0.0824, + "step": 462 + }, + { + "epoch": 5.9264, + "grad_norm": 0.2522879651320666, + "learning_rate": 2.75462128282326e-06, + "loss": 0.0751, + "step": 463 + }, + { + "epoch": 5.9392, + "grad_norm": 0.24943472624291574, + "learning_rate": 2.6901656968545455e-06, + "loss": 0.0798, + "step": 464 + }, + { + "epoch": 5.952, + "grad_norm": 0.2377282733369092, + "learning_rate": 2.626418755009523e-06, + "loss": 0.0787, + "step": 465 + }, + { + "epoch": 5.9648, + "grad_norm": 0.25278482416359105, + "learning_rate": 2.563383067012519e-06, + "loss": 0.0816, + "step": 466 + }, + { + "epoch": 5.9776, + "grad_norm": 0.2606783205225798, + "learning_rate": 2.5010612134699706e-06, + "loss": 0.0965, + "step": 467 + }, + { + "epoch": 5.9904, + "grad_norm": 0.25250470215575255, + "learning_rate": 2.4394557457647894e-06, + "loss": 0.0974, + "step": 468 + }, + { + "epoch": 6.0032, + "grad_norm": 0.6307515992424928, + "learning_rate": 2.3785691859518824e-06, + "loss": 0.1148, + "step": 469 + }, + { + "epoch": 6.016, + "grad_norm": 0.31873807207565263, + "learning_rate": 2.318404026654928e-06, + "loss": 0.0587, + "step": 470 + }, + { + "epoch": 6.0288, + "grad_norm": 0.24869481585780664, + "learning_rate": 2.2589627309643182e-06, + "loss": 0.0515, + "step": 471 + }, + { + "epoch": 6.0416, + "grad_norm": 0.2624844971478034, + "learning_rate": 2.2002477323363314e-06, + "loss": 0.0604, + "step": 472 + }, + { + "epoch": 6.0544, + "grad_norm": 0.2067843885434314, + "learning_rate": 2.1422614344935e-06, + "loss": 0.0491, + "step": 473 + }, + { + "epoch": 6.0672, + "grad_norm": 0.21301266282959322, + "learning_rate": 2.0850062113262014e-06, + "loss": 0.0602, + "step": 474 + }, + { + "epoch": 6.08, + "grad_norm": 0.23913788889439205, + "learning_rate": 2.0284844067955013e-06, + "loss": 0.0582, + "step": 475 + }, + { + "epoch": 6.0928, + "grad_norm": 0.24737157702610824, + "learning_rate": 1.972698334837155e-06, + "loss": 0.0552, + "step": 476 + }, + { + "epoch": 6.1056, + "grad_norm": 0.2830484576941645, + "learning_rate": 1.9176502792669048e-06, + "loss": 0.0598, + "step": 477 + }, + { + "epoch": 6.1184, + "grad_norm": 0.29743523726617643, + "learning_rate": 1.8633424936869747e-06, + "loss": 0.0659, + "step": 478 + }, + { + "epoch": 6.1312, + "grad_norm": 0.2508507804956114, + "learning_rate": 1.8097772013938187e-06, + "loss": 0.0526, + "step": 479 + }, + { + "epoch": 6.144, + "grad_norm": 0.27920118945455913, + "learning_rate": 1.756956595287085e-06, + "loss": 0.0633, + "step": 480 + }, + { + "epoch": 6.1568, + "grad_norm": 0.22698911436680633, + "learning_rate": 1.7048828377798531e-06, + "loss": 0.0509, + "step": 481 + }, + { + "epoch": 6.1696, + "grad_norm": 0.21351689251879283, + "learning_rate": 1.6535580607101055e-06, + "loss": 0.0533, + "step": 482 + }, + { + "epoch": 6.1824, + "grad_norm": 0.2134241611710577, + "learning_rate": 1.6029843652534571e-06, + "loss": 0.059, + "step": 483 + }, + { + "epoch": 6.1952, + "grad_norm": 0.2089174965210443, + "learning_rate": 1.553163821837127e-06, + "loss": 0.0527, + "step": 484 + }, + { + "epoch": 6.208, + "grad_norm": 0.21694868914769955, + "learning_rate": 1.5040984700551752e-06, + "loss": 0.0593, + "step": 485 + }, + { + "epoch": 6.2208, + "grad_norm": 0.2247435527500204, + "learning_rate": 1.4557903185850308e-06, + "loss": 0.0618, + "step": 486 + }, + { + "epoch": 6.2336, + "grad_norm": 0.19569237729410577, + "learning_rate": 1.4082413451052058e-06, + "loss": 0.0534, + "step": 487 + }, + { + "epoch": 6.2464, + "grad_norm": 0.21659528175315748, + "learning_rate": 1.3614534962143932e-06, + "loss": 0.0624, + "step": 488 + }, + { + "epoch": 6.2592, + "grad_norm": 0.1920895954701789, + "learning_rate": 1.3154286873517318e-06, + "loss": 0.0468, + "step": 489 + }, + { + "epoch": 6.272, + "grad_norm": 0.21069873163924976, + "learning_rate": 1.2701688027184123e-06, + "loss": 0.0549, + "step": 490 + }, + { + "epoch": 6.2848, + "grad_norm": 0.21095594160716954, + "learning_rate": 1.22567569520053e-06, + "loss": 0.0598, + "step": 491 + }, + { + "epoch": 6.2976, + "grad_norm": 0.21732951466081074, + "learning_rate": 1.1819511862932242e-06, + "loss": 0.0583, + "step": 492 + }, + { + "epoch": 6.3104, + "grad_norm": 0.199756792134096, + "learning_rate": 1.1389970660261396e-06, + "loss": 0.0535, + "step": 493 + }, + { + "epoch": 6.3232, + "grad_norm": 0.2080483888215097, + "learning_rate": 1.0968150928900912e-06, + "loss": 0.0588, + "step": 494 + }, + { + "epoch": 6.336, + "grad_norm": 0.22078274255706784, + "learning_rate": 1.0554069937651335e-06, + "loss": 0.0612, + "step": 495 + }, + { + "epoch": 6.3488, + "grad_norm": 0.21284506643865078, + "learning_rate": 1.0147744638498146e-06, + "loss": 0.0599, + "step": 496 + }, + { + "epoch": 6.3616, + "grad_norm": 0.1939478710319105, + "learning_rate": 9.749191665918122e-07, + "loss": 0.05, + "step": 497 + }, + { + "epoch": 6.3744, + "grad_norm": 0.21905210500235428, + "learning_rate": 9.358427336198073e-07, + "loss": 0.061, + "step": 498 + }, + { + "epoch": 6.3872, + "grad_norm": 0.20367086506090404, + "learning_rate": 8.975467646767045e-07, + "loss": 0.0429, + "step": 499 + }, + { + "epoch": 6.4, + "grad_norm": 0.2204978599221063, + "learning_rate": 8.600328275541425e-07, + "loss": 0.0632, + "step": 500 + }, + { + "epoch": 6.4128, + "grad_norm": 0.19657411605198546, + "learning_rate": 8.233024580282811e-07, + "loss": 0.0486, + "step": 501 + }, + { + "epoch": 6.4256, + "grad_norm": 0.1929878032267413, + "learning_rate": 7.873571597969753e-07, + "loss": 0.0512, + "step": 502 + }, + { + "epoch": 6.4384, + "grad_norm": 0.21297734998628096, + "learning_rate": 7.521984044181763e-07, + "loss": 0.061, + "step": 503 + }, + { + "epoch": 6.4512, + "grad_norm": 0.2036017581226651, + "learning_rate": 7.178276312497101e-07, + "loss": 0.0549, + "step": 504 + }, + { + "epoch": 6.464, + "grad_norm": 0.2157949678208667, + "learning_rate": 6.842462473903299e-07, + "loss": 0.059, + "step": 505 + }, + { + "epoch": 6.4768, + "grad_norm": 0.19947687051049257, + "learning_rate": 6.51455627622144e-07, + "loss": 0.0536, + "step": 506 + }, + { + "epoch": 6.4896, + "grad_norm": 0.21745771596116842, + "learning_rate": 6.194571143543027e-07, + "loss": 0.0612, + "step": 507 + }, + { + "epoch": 6.5024, + "grad_norm": 0.2101529082646709, + "learning_rate": 5.882520175680539e-07, + "loss": 0.0505, + "step": 508 + }, + { + "epoch": 6.5152, + "grad_norm": 0.19411610830588563, + "learning_rate": 5.578416147631216e-07, + "loss": 0.0447, + "step": 509 + }, + { + "epoch": 6.5280000000000005, + "grad_norm": 0.22526486934316098, + "learning_rate": 5.282271509053916e-07, + "loss": 0.0615, + "step": 510 + }, + { + "epoch": 6.5408, + "grad_norm": 0.20270004269056, + "learning_rate": 4.994098383759571e-07, + "loss": 0.0528, + "step": 511 + }, + { + "epoch": 6.5536, + "grad_norm": 0.20352924552183632, + "learning_rate": 4.71390856921472e-07, + "loss": 0.0499, + "step": 512 + }, + { + "epoch": 6.5664, + "grad_norm": 0.20082311361176847, + "learning_rate": 4.441713536058734e-07, + "loss": 0.0535, + "step": 513 + }, + { + "epoch": 6.5792, + "grad_norm": 0.19152806714606765, + "learning_rate": 4.177524427633972e-07, + "loss": 0.0479, + "step": 514 + }, + { + "epoch": 6.592, + "grad_norm": 0.20900178436356592, + "learning_rate": 3.9213520595297484e-07, + "loss": 0.0539, + "step": 515 + }, + { + "epoch": 6.6048, + "grad_norm": 0.2154189515893567, + "learning_rate": 3.673206919139616e-07, + "loss": 0.0583, + "step": 516 + }, + { + "epoch": 6.6176, + "grad_norm": 0.20160762615144787, + "learning_rate": 3.4330991652317793e-07, + "loss": 0.06, + "step": 517 + }, + { + "epoch": 6.6304, + "grad_norm": 0.21267833321164703, + "learning_rate": 3.201038627533448e-07, + "loss": 0.061, + "step": 518 + }, + { + "epoch": 6.6432, + "grad_norm": 0.19672661747979087, + "learning_rate": 2.977034806328294e-07, + "loss": 0.0487, + "step": 519 + }, + { + "epoch": 6.656, + "grad_norm": 0.21364651184647268, + "learning_rate": 2.7610968720675813e-07, + "loss": 0.0602, + "step": 520 + }, + { + "epoch": 6.6688, + "grad_norm": 0.21531511298839284, + "learning_rate": 2.553233664994692e-07, + "loss": 0.0547, + "step": 521 + }, + { + "epoch": 6.6815999999999995, + "grad_norm": 0.19923340943076429, + "learning_rate": 2.3534536947832364e-07, + "loss": 0.0515, + "step": 522 + }, + { + "epoch": 6.6944, + "grad_norm": 0.2063755392379561, + "learning_rate": 2.1617651401886875e-07, + "loss": 0.0553, + "step": 523 + }, + { + "epoch": 6.7072, + "grad_norm": 0.20324639288183224, + "learning_rate": 1.9781758487135373e-07, + "loss": 0.0511, + "step": 524 + }, + { + "epoch": 6.72, + "grad_norm": 0.21382930992061455, + "learning_rate": 1.8026933362859988e-07, + "loss": 0.0617, + "step": 525 + }, + { + "epoch": 6.7328, + "grad_norm": 0.20091432072129906, + "learning_rate": 1.635324786952408e-07, + "loss": 0.056, + "step": 526 + }, + { + "epoch": 6.7456, + "grad_norm": 0.20499113368449215, + "learning_rate": 1.476077052583036e-07, + "loss": 0.0548, + "step": 527 + }, + { + "epoch": 6.7584, + "grad_norm": 0.19997098829776122, + "learning_rate": 1.3249566525916024e-07, + "loss": 0.0515, + "step": 528 + }, + { + "epoch": 6.7712, + "grad_norm": 0.19730024827668835, + "learning_rate": 1.1819697736683567e-07, + "loss": 0.0555, + "step": 529 + }, + { + "epoch": 6.784, + "grad_norm": 0.18914493404170932, + "learning_rate": 1.0471222695268346e-07, + "loss": 0.0479, + "step": 530 + }, + { + "epoch": 6.7968, + "grad_norm": 0.2001098720255446, + "learning_rate": 9.204196606642512e-08, + "loss": 0.0522, + "step": 531 + }, + { + "epoch": 6.8096, + "grad_norm": 0.19566555347609557, + "learning_rate": 8.018671341353702e-08, + "loss": 0.0501, + "step": 532 + }, + { + "epoch": 6.8224, + "grad_norm": 0.20308185664037973, + "learning_rate": 6.914695433403174e-08, + "loss": 0.0582, + "step": 533 + }, + { + "epoch": 6.8352, + "grad_norm": 0.2021394190243187, + "learning_rate": 5.8923140782574106e-08, + "loss": 0.0602, + "step": 534 + }, + { + "epoch": 6.848, + "grad_norm": 0.20063291184587487, + "learning_rate": 4.951569130998479e-08, + "loss": 0.0517, + "step": 535 + }, + { + "epoch": 6.8608, + "grad_norm": 0.21687113775307834, + "learning_rate": 4.092499104611403e-08, + "loss": 0.0645, + "step": 536 + }, + { + "epoch": 6.8736, + "grad_norm": 0.20473541823298777, + "learning_rate": 3.315139168405423e-08, + "loss": 0.0457, + "step": 537 + }, + { + "epoch": 6.8864, + "grad_norm": 0.21253873775704507, + "learning_rate": 2.619521146576487e-08, + "loss": 0.0552, + "step": 538 + }, + { + "epoch": 6.8992, + "grad_norm": 0.19677860005085293, + "learning_rate": 2.0056735169025064e-08, + "loss": 0.0521, + "step": 539 + }, + { + "epoch": 6.912, + "grad_norm": 0.2130449480569404, + "learning_rate": 1.4736214095789625e-08, + "loss": 0.0604, + "step": 540 + }, + { + "epoch": 6.9248, + "grad_norm": 0.2057866822827188, + "learning_rate": 1.0233866061892806e-08, + "loss": 0.0563, + "step": 541 + }, + { + "epoch": 6.9376, + "grad_norm": 0.20786044919437346, + "learning_rate": 6.54987538813101e-09, + "loss": 0.0511, + "step": 542 + }, + { + "epoch": 6.9504, + "grad_norm": 0.20591521352687323, + "learning_rate": 3.6843928927221552e-09, + "loss": 0.0525, + "step": 543 + }, + { + "epoch": 6.9632, + "grad_norm": 0.1932156399001302, + "learning_rate": 1.6375358851261625e-09, + "loss": 0.0528, + "step": 544 + }, + { + "epoch": 6.976, + "grad_norm": 0.21810263966806365, + "learning_rate": 4.0938816124880263e-10, + "loss": 0.0587, + "step": 545 + }, + { + "epoch": 6.9888, + "grad_norm": 0.19749085938012026, + "learning_rate": 0.0, + "loss": 0.0537, + "step": 546 + }, + { + "epoch": 6.9888, + "step": 546, + "total_flos": 1.3527969808368271e+18, + "train_loss": 0.27728078796804606, + "train_runtime": 40114.8445, + "train_samples_per_second": 1.744, + "train_steps_per_second": 0.014 + } + ], + "logging_steps": 1.0, + "max_steps": 546, + "num_input_tokens_seen": 0, + "num_train_epochs": 7, + "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": 1.3527969808368271e+18, + "train_batch_size": 1, + "trial_name": null, + "trial_params": null +} diff --git a/training_args.bin b/training_args.bin new file mode 100644 index 0000000..6c3beaf --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56516741238f1c0fabde16ba0c5228f847e9558cf95816a2c483849eb76987ce +size 7224 diff --git a/training_loss.png b/training_loss.png new file mode 100644 index 0000000..d65a09c 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