commit 2f051672a93aa532d4514666ce580c480fd67f79 Author: ModelHub XC Date: Wed Jun 10 02:08:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mlfoundations-dev/openthoughts3_science_10k Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..89a4aa0 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,56 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text + + +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text + +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.gguf* filter=lfs diff=lfs merge=lfs -text +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text + +merges.txt filter=lfs diff=lfs merge=lfs -text +training_args.bin filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text +model-00001-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +vocab.json filter=lfs diff=lfs merge=lfs -text +model-00003-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +model-00002-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +model-00004-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..7fc255c --- /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: openthoughts3_science_10k + results: [] +--- + + + +# openthoughts3_science_10k + +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/openthoughts3_science_10k 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: 4 +- gradient_accumulation_steps: 32 +- total_train_batch_size: 128 +- total_eval_batch_size: 32 +- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments +- lr_scheduler_type: cosine +- lr_scheduler_warmup_ratio: 0.1 +- num_epochs: 5.0 + +### Training results + + + +### Framework versions + +- Transformers 4.46.1 +- Pytorch 2.6.0+cu124 +- 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..03a0fa2 --- /dev/null +++ b/all_results.json @@ -0,0 +1,8 @@ +{ + "epoch": 4.992, + "total_flos": 1.3856636017416602e+18, + "train_loss": 0.9147117905127696, + "train_runtime": 48380.7223, + "train_samples_per_second": 1.033, + "train_steps_per_second": 0.008 +} \ 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..3ac3f5b --- /dev/null +++ b/configs.yaml @@ -0,0 +1,37 @@ +assistant_tag: gpt +bf16: true +content_tag: value +cutoff_len: 16384 +dataloader_num_workers: 4 +dataloader_persistent_workers: true +dataloader_pin_memory: true +dataset: mlfoundations-dev/openthoughts3_science_10k +dataset_dir: ONLINE +ddp_timeout: 180000000 +deepspeed: dcft/train/zero3.json +do_train: true +enable_liger_kernel: true +finetuning_type: full +global_batch_size: 128 +gradient_accumulation_steps: 32 +hub_model_id: mlfoundations-dev/openthoughts3_science_10k +learning_rate: 4.0e-05 +logging_steps: 1 +lr_scheduler_type: cosine +messages: conversations +model_name_or_path: Qwen/Qwen2.5-7B-Instruct +num_train_epochs: 5.0 +output_dir: /data/cat/ws/ryma833h-dcft/checkpoints/openthoughts3_science_10k +overwrite_cache: true +per_device_train_batch_size: 1 +plot_loss: true +preprocessing_num_workers: 16 +push_to_db: true +push_to_hub: true +report_to: wandb +role_tag: from +save_strategy: epoch +stage: sft +template: qwen25 +user_tag: human +warmup_ratio: 0.1 diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..a753841 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,14 @@ +{ + "bos_token_id": 151643, + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "repetition_penalty": 1.05, + "temperature": 0.7, + "top_k": 20, + "top_p": 0.8, + "transformers_version": "4.46.1" +} diff --git a/merges.txt b/merges.txt new file mode 100644 index 0000000..80c1a19 --- /dev/null +++ b/merges.txt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5 +size 1671853 diff --git a/model-00001-of-00004.safetensors b/model-00001-of-00004.safetensors new file mode 100644 index 0000000..433694f --- /dev/null +++ b/model-00001-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d3f4001a391fc9cea6bfc04cf07579d2030e8e9cdf293408d172e453f9a8984 +size 4877660776 diff --git a/model-00002-of-00004.safetensors b/model-00002-of-00004.safetensors new file mode 100644 index 0000000..20dafa1 --- /dev/null +++ b/model-00002-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5435f5373e2d2a5295213fecea3082fb2e88b9c72e0ffed3785d95d1679dc3f +size 4932751008 diff --git a/model-00003-of-00004.safetensors b/model-00003-of-00004.safetensors new file mode 100644 index 0000000..a04fa6f --- /dev/null +++ b/model-00003-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:daee3d6d795fd9b82f7cd0cb9be5ca11111e4dbd8ee5b083fb6f5cc78ec65de9 +size 4330865200 diff --git a/model-00004-of-00004.safetensors b/model-00004-of-00004.safetensors new file mode 100644 index 0000000..a20e66b --- /dev/null +++ b/model-00004-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c9465cbeec24bab5053c0515bee311e4b6b7850f1ff703ac43876b994ec97c6 +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..03a0fa2 --- /dev/null +++ b/train_results.json @@ -0,0 +1,8 @@ +{ + "epoch": 4.992, + "total_flos": 1.3856636017416602e+18, + "train_loss": 0.9147117905127696, + "train_runtime": 48380.7223, + "train_samples_per_second": 1.033, + "train_steps_per_second": 0.008 +} \ No newline at end of file diff --git a/trainer_log.jsonl b/trainer_log.jsonl new file mode 100644 index 0000000..ca23ef2 --- /dev/null +++ b/trainer_log.jsonl @@ -0,0 +1,391 @@ +{"current_steps": 1, "total_steps": 390, "loss": 1.5558, "lr": 1.0256410256410257e-06, "epoch": 0.0128, "percentage": 0.26, "elapsed_time": "0:02:10", "remaining_time": "14:06:04"} +{"current_steps": 2, "total_steps": 390, "loss": 1.5299, "lr": 2.0512820512820513e-06, "epoch": 0.0256, "percentage": 0.51, "elapsed_time": "0:04:11", "remaining_time": "13:33:03"} +{"current_steps": 3, "total_steps": 390, "loss": 1.5814, "lr": 3.0769230769230774e-06, "epoch": 0.0384, "percentage": 0.77, "elapsed_time": "0:06:24", "remaining_time": "13:46:43"} +{"current_steps": 4, "total_steps": 390, "loss": 1.54, "lr": 4.102564102564103e-06, "epoch": 0.0512, "percentage": 1.03, "elapsed_time": "0:08:22", "remaining_time": "13:28:12"} +{"current_steps": 5, "total_steps": 390, "loss": 1.508, "lr": 5.128205128205128e-06, "epoch": 0.064, "percentage": 1.28, "elapsed_time": "0:10:19", "remaining_time": "13:15:07"} +{"current_steps": 6, "total_steps": 390, "loss": 1.4687, "lr": 6.153846153846155e-06, "epoch": 0.0768, "percentage": 1.54, "elapsed_time": "0:12:35", "remaining_time": "13:25:43"} +{"current_steps": 7, "total_steps": 390, "loss": 1.4354, "lr": 7.17948717948718e-06, "epoch": 0.0896, "percentage": 1.79, "elapsed_time": "0:14:45", "remaining_time": "13:27:54"} +{"current_steps": 8, "total_steps": 390, "loss": 1.448, "lr": 8.205128205128205e-06, "epoch": 0.1024, "percentage": 2.05, "elapsed_time": "0:16:57", "remaining_time": "13:29:27"} +{"current_steps": 9, "total_steps": 390, "loss": 1.4113, "lr": 9.230769230769232e-06, "epoch": 0.1152, "percentage": 2.31, "elapsed_time": "0:19:05", "remaining_time": "13:28:16"} +{"current_steps": 10, "total_steps": 390, "loss": 1.3674, "lr": 1.0256410256410256e-05, "epoch": 0.128, "percentage": 2.56, "elapsed_time": "0:20:56", "remaining_time": "13:15:59"} +{"current_steps": 11, "total_steps": 390, "loss": 1.3963, "lr": 1.1282051282051283e-05, "epoch": 0.1408, "percentage": 2.82, "elapsed_time": "0:22:59", "remaining_time": "13:12:07"} +{"current_steps": 12, "total_steps": 390, "loss": 1.3873, "lr": 1.230769230769231e-05, "epoch": 0.1536, "percentage": 3.08, "elapsed_time": "0:25:04", "remaining_time": "13:09:54"} +{"current_steps": 13, "total_steps": 390, "loss": 1.3816, "lr": 1.3333333333333333e-05, "epoch": 0.1664, "percentage": 3.33, "elapsed_time": "0:27:14", "remaining_time": "13:09:52"} +{"current_steps": 14, "total_steps": 390, "loss": 1.2973, "lr": 1.435897435897436e-05, "epoch": 0.1792, "percentage": 3.59, "elapsed_time": "0:29:21", "remaining_time": "13:08:15"} +{"current_steps": 15, "total_steps": 390, "loss": 1.3467, "lr": 1.5384615384615387e-05, "epoch": 0.192, "percentage": 3.85, "elapsed_time": "0:31:36", "remaining_time": "13:10:12"} +{"current_steps": 16, "total_steps": 390, "loss": 1.281, "lr": 1.641025641025641e-05, "epoch": 0.2048, "percentage": 4.1, "elapsed_time": "0:33:41", "remaining_time": "13:07:30"} +{"current_steps": 17, "total_steps": 390, "loss": 1.246, "lr": 1.7435897435897438e-05, "epoch": 0.2176, "percentage": 4.36, "elapsed_time": "0:36:01", "remaining_time": "13:10:22"} +{"current_steps": 18, "total_steps": 390, "loss": 1.2626, "lr": 1.8461538461538465e-05, "epoch": 0.2304, "percentage": 4.62, "elapsed_time": "0:37:43", "remaining_time": "12:59:40"} +{"current_steps": 19, "total_steps": 390, "loss": 1.2497, "lr": 1.9487179487179488e-05, "epoch": 0.2432, "percentage": 4.87, "elapsed_time": "0:39:48", "remaining_time": "12:57:14"} +{"current_steps": 20, "total_steps": 390, "loss": 1.2911, "lr": 2.0512820512820512e-05, "epoch": 0.256, "percentage": 5.13, "elapsed_time": "0:41:26", "remaining_time": "12:46:33"} +{"current_steps": 21, "total_steps": 390, "loss": 1.2629, "lr": 2.153846153846154e-05, "epoch": 0.2688, "percentage": 5.38, "elapsed_time": "0:43:27", "remaining_time": "12:43:29"} +{"current_steps": 22, "total_steps": 390, "loss": 1.2377, "lr": 2.2564102564102566e-05, "epoch": 0.2816, "percentage": 5.64, "elapsed_time": "0:45:23", "remaining_time": "12:39:23"} +{"current_steps": 23, "total_steps": 390, "loss": 1.2138, "lr": 2.3589743589743593e-05, "epoch": 0.2944, "percentage": 5.9, "elapsed_time": "0:47:22", "remaining_time": "12:35:58"} +{"current_steps": 24, "total_steps": 390, "loss": 1.2404, "lr": 2.461538461538462e-05, "epoch": 0.3072, "percentage": 6.15, "elapsed_time": "0:49:24", "remaining_time": "12:33:33"} +{"current_steps": 25, "total_steps": 390, "loss": 1.2288, "lr": 2.5641025641025646e-05, "epoch": 0.32, "percentage": 6.41, "elapsed_time": "0:51:32", "remaining_time": "12:32:32"} +{"current_steps": 26, "total_steps": 390, "loss": 1.2305, "lr": 2.6666666666666667e-05, "epoch": 0.3328, "percentage": 6.67, "elapsed_time": "0:53:30", "remaining_time": "12:29:04"} +{"current_steps": 27, "total_steps": 390, "loss": 1.2068, "lr": 2.7692307692307694e-05, "epoch": 0.3456, "percentage": 6.92, "elapsed_time": "0:55:37", "remaining_time": "12:27:55"} +{"current_steps": 28, "total_steps": 390, "loss": 1.2025, "lr": 2.871794871794872e-05, "epoch": 0.3584, "percentage": 7.18, "elapsed_time": "0:57:44", "remaining_time": "12:26:25"} +{"current_steps": 29, "total_steps": 390, "loss": 1.2084, "lr": 2.9743589743589747e-05, "epoch": 0.3712, "percentage": 7.44, "elapsed_time": "0:59:45", "remaining_time": "12:23:50"} +{"current_steps": 30, "total_steps": 390, "loss": 1.1879, "lr": 3.0769230769230774e-05, "epoch": 0.384, "percentage": 7.69, "elapsed_time": "1:02:05", "remaining_time": "12:25:02"} +{"current_steps": 31, "total_steps": 390, "loss": 1.1922, "lr": 3.1794871794871795e-05, "epoch": 0.3968, "percentage": 7.95, "elapsed_time": "1:03:58", "remaining_time": "12:20:54"} +{"current_steps": 32, "total_steps": 390, "loss": 1.1835, "lr": 3.282051282051282e-05, "epoch": 0.4096, "percentage": 8.21, "elapsed_time": "1:06:02", "remaining_time": "12:18:46"} +{"current_steps": 33, "total_steps": 390, "loss": 1.1759, "lr": 3.384615384615385e-05, "epoch": 0.4224, "percentage": 8.46, "elapsed_time": "1:08:00", "remaining_time": "12:15:41"} +{"current_steps": 34, "total_steps": 390, "loss": 1.1863, "lr": 3.4871794871794875e-05, "epoch": 0.4352, "percentage": 8.72, "elapsed_time": "1:10:15", "remaining_time": "12:15:34"} +{"current_steps": 35, "total_steps": 390, "loss": 1.2153, "lr": 3.58974358974359e-05, "epoch": 0.448, "percentage": 8.97, "elapsed_time": "1:12:09", "remaining_time": "12:11:51"} +{"current_steps": 36, "total_steps": 390, "loss": 1.1459, "lr": 3.692307692307693e-05, "epoch": 0.4608, "percentage": 9.23, "elapsed_time": "1:14:17", "remaining_time": "12:10:30"} +{"current_steps": 37, "total_steps": 390, "loss": 1.1484, "lr": 3.794871794871795e-05, "epoch": 0.4736, "percentage": 9.49, "elapsed_time": "1:16:16", "remaining_time": "12:07:38"} +{"current_steps": 38, "total_steps": 390, "loss": 1.1469, "lr": 3.8974358974358976e-05, "epoch": 0.4864, "percentage": 9.74, "elapsed_time": "1:18:08", "remaining_time": "12:03:52"} +{"current_steps": 39, "total_steps": 390, "loss": 1.1893, "lr": 4e-05, "epoch": 0.4992, "percentage": 10.0, "elapsed_time": "1:20:07", "remaining_time": "12:01:09"} +{"current_steps": 40, "total_steps": 390, "loss": 1.15, "lr": 3.9999198907597046e-05, "epoch": 0.512, "percentage": 10.26, "elapsed_time": "1:21:47", "remaining_time": "11:55:41"} +{"current_steps": 41, "total_steps": 390, "loss": 1.1328, "lr": 3.9996795694563096e-05, "epoch": 0.5248, "percentage": 10.51, "elapsed_time": "1:23:46", "remaining_time": "11:53:04"} +{"current_steps": 42, "total_steps": 390, "loss": 1.1853, "lr": 3.999279055341771e-05, "epoch": 0.5376, "percentage": 10.77, "elapsed_time": "1:25:55", "remaining_time": "11:51:57"} +{"current_steps": 43, "total_steps": 390, "loss": 1.1834, "lr": 3.998718380500971e-05, "epoch": 0.5504, "percentage": 11.03, "elapsed_time": "1:27:56", "remaining_time": "11:49:41"} +{"current_steps": 44, "total_steps": 390, "loss": 1.1458, "lr": 3.997997589849145e-05, "epoch": 0.5632, "percentage": 11.28, "elapsed_time": "1:29:51", "remaining_time": "11:46:40"} +{"current_steps": 45, "total_steps": 390, "loss": 1.1943, "lr": 3.9971167411282835e-05, "epoch": 0.576, "percentage": 11.54, "elapsed_time": "1:31:50", "remaining_time": "11:44:08"} +{"current_steps": 46, "total_steps": 390, "loss": 1.1983, "lr": 3.99607590490251e-05, "epoch": 0.5888, "percentage": 11.79, "elapsed_time": "1:33:51", "remaining_time": "11:41:54"} +{"current_steps": 47, "total_steps": 390, "loss": 1.1626, "lr": 3.9948751645524235e-05, "epoch": 0.6016, "percentage": 12.05, "elapsed_time": "1:35:47", "remaining_time": "11:39:05"} +{"current_steps": 48, "total_steps": 390, "loss": 1.1529, "lr": 3.9935146162684206e-05, "epoch": 0.6144, "percentage": 12.31, "elapsed_time": "1:37:46", "remaining_time": "11:36:37"} +{"current_steps": 49, "total_steps": 390, "loss": 1.1494, "lr": 3.9919943690429906e-05, "epoch": 0.6272, "percentage": 12.56, "elapsed_time": "1:39:48", "remaining_time": "11:34:37"} +{"current_steps": 50, "total_steps": 390, "loss": 1.157, "lr": 3.9903145446619837e-05, "epoch": 0.64, "percentage": 12.82, "elapsed_time": "1:41:45", "remaining_time": "11:31:58"} +{"current_steps": 51, "total_steps": 390, "loss": 1.1729, "lr": 3.9884752776948564e-05, "epoch": 0.6528, "percentage": 13.08, "elapsed_time": "1:43:46", "remaining_time": "11:29:48"} +{"current_steps": 52, "total_steps": 390, "loss": 1.1861, "lr": 3.9864767154838864e-05, "epoch": 0.6656, "percentage": 13.33, "elapsed_time": "1:45:52", "remaining_time": "11:28:09"} +{"current_steps": 53, "total_steps": 390, "loss": 1.1113, "lr": 3.9843190181323744e-05, "epoch": 0.6784, "percentage": 13.59, "elapsed_time": "1:47:59", "remaining_time": "11:26:41"} +{"current_steps": 54, "total_steps": 390, "loss": 1.149, "lr": 3.982002358491817e-05, "epoch": 0.6912, "percentage": 13.85, "elapsed_time": "1:50:13", "remaining_time": "11:25:47"} +{"current_steps": 55, "total_steps": 390, "loss": 1.1464, "lr": 3.979526922148058e-05, "epoch": 0.704, "percentage": 14.1, "elapsed_time": "1:52:24", "remaining_time": "11:24:37"} +{"current_steps": 56, "total_steps": 390, "loss": 1.1468, "lr": 3.9768929074064206e-05, "epoch": 0.7168, "percentage": 14.36, "elapsed_time": "1:54:17", "remaining_time": "11:21:40"} +{"current_steps": 57, "total_steps": 390, "loss": 1.1694, "lr": 3.9741005252758255e-05, "epoch": 0.7296, "percentage": 14.62, "elapsed_time": "1:56:20", "remaining_time": "11:19:43"} +{"current_steps": 58, "total_steps": 390, "loss": 1.1939, "lr": 3.971149999451886e-05, "epoch": 0.7424, "percentage": 14.87, "elapsed_time": "1:58:28", "remaining_time": "11:18:11"} +{"current_steps": 59, "total_steps": 390, "loss": 1.1963, "lr": 3.9680415662989806e-05, "epoch": 0.7552, "percentage": 15.13, "elapsed_time": "2:00:56", "remaining_time": "11:18:32"} +{"current_steps": 60, "total_steps": 390, "loss": 1.1659, "lr": 3.9647754748313294e-05, "epoch": 0.768, "percentage": 15.38, "elapsed_time": "2:03:10", "remaining_time": "11:17:29"} +{"current_steps": 61, "total_steps": 390, "loss": 1.135, "lr": 3.96135198669304e-05, "epoch": 0.7808, "percentage": 15.64, "elapsed_time": "2:05:36", "remaining_time": "11:17:26"} +{"current_steps": 62, "total_steps": 390, "loss": 1.1045, "lr": 3.957771376137144e-05, "epoch": 0.7936, "percentage": 15.9, "elapsed_time": "2:07:49", "remaining_time": "11:16:11"} +{"current_steps": 63, "total_steps": 390, "loss": 1.1306, "lr": 3.954033930003634e-05, "epoch": 0.8064, "percentage": 16.15, "elapsed_time": "2:09:41", "remaining_time": "11:13:10"} +{"current_steps": 64, "total_steps": 390, "loss": 1.1248, "lr": 3.9501399476964806e-05, "epoch": 0.8192, "percentage": 16.41, "elapsed_time": "2:11:41", "remaining_time": "11:10:48"} +{"current_steps": 65, "total_steps": 390, "loss": 1.1091, "lr": 3.946089741159648e-05, "epoch": 0.832, "percentage": 16.67, "elapsed_time": "2:13:45", "remaining_time": "11:08:49"} +{"current_steps": 66, "total_steps": 390, "loss": 1.1273, "lr": 3.9418836348521045e-05, "epoch": 0.8448, "percentage": 16.92, "elapsed_time": "2:15:45", "remaining_time": "11:06:26"} +{"current_steps": 67, "total_steps": 390, "loss": 1.1285, "lr": 3.937521965721831e-05, "epoch": 0.8576, "percentage": 17.18, "elapsed_time": "2:17:50", "remaining_time": "11:04:29"} +{"current_steps": 68, "total_steps": 390, "loss": 1.1028, "lr": 3.933005083178828e-05, "epoch": 0.8704, "percentage": 17.44, "elapsed_time": "2:20:00", "remaining_time": "11:02:58"} +{"current_steps": 69, "total_steps": 390, "loss": 1.139, "lr": 3.928333349067125e-05, "epoch": 0.8832, "percentage": 17.69, "elapsed_time": "2:22:09", "remaining_time": "11:01:21"} +{"current_steps": 70, "total_steps": 390, "loss": 1.1002, "lr": 3.923507137635792e-05, "epoch": 0.896, "percentage": 17.95, "elapsed_time": "2:24:03", "remaining_time": "10:58:32"} +{"current_steps": 71, "total_steps": 390, "loss": 1.1475, "lr": 3.9185268355089606e-05, "epoch": 0.9088, "percentage": 18.21, "elapsed_time": "2:26:07", "remaining_time": "10:56:30"} +{"current_steps": 72, "total_steps": 390, "loss": 1.141, "lr": 3.913392841654851e-05, "epoch": 0.9216, "percentage": 18.46, "elapsed_time": "2:28:08", "remaining_time": "10:54:17"} +{"current_steps": 73, "total_steps": 390, "loss": 1.1598, "lr": 3.9081055673538093e-05, "epoch": 0.9344, "percentage": 18.72, "elapsed_time": "2:29:59", "remaining_time": "10:51:21"} +{"current_steps": 74, "total_steps": 390, "loss": 1.1478, "lr": 3.902665436165364e-05, "epoch": 0.9472, "percentage": 18.97, "elapsed_time": "2:32:15", "remaining_time": "10:50:10"} +{"current_steps": 75, "total_steps": 390, "loss": 1.0939, "lr": 3.897072883894291e-05, "epoch": 0.96, "percentage": 19.23, "elapsed_time": "2:34:11", "remaining_time": "10:47:35"} +{"current_steps": 76, "total_steps": 390, "loss": 1.1523, "lr": 3.8913283585557054e-05, "epoch": 0.9728, "percentage": 19.49, "elapsed_time": "2:36:24", "remaining_time": "10:46:13"} +{"current_steps": 77, "total_steps": 390, "loss": 1.1584, "lr": 3.885432320339167e-05, "epoch": 0.9856, "percentage": 19.74, "elapsed_time": "2:38:47", "remaining_time": "10:45:28"} +{"current_steps": 78, "total_steps": 390, "loss": 1.1579, "lr": 3.879385241571817e-05, "epoch": 0.9984, "percentage": 20.0, "elapsed_time": "2:40:48", "remaining_time": "10:43:15"} +{"current_steps": 79, "total_steps": 390, "loss": 1.0571, "lr": 3.873187606680543e-05, "epoch": 1.0112, "percentage": 20.26, "elapsed_time": "2:43:25", "remaining_time": "10:43:19"} +{"current_steps": 80, "total_steps": 390, "loss": 1.0308, "lr": 3.866839912153168e-05, "epoch": 1.024, "percentage": 20.51, "elapsed_time": "2:45:09", "remaining_time": "10:39:59"} +{"current_steps": 81, "total_steps": 390, "loss": 1.0528, "lr": 3.860342666498677e-05, "epoch": 1.0368, "percentage": 20.77, "elapsed_time": "2:47:30", "remaining_time": "10:38:59"} +{"current_steps": 82, "total_steps": 390, "loss": 1.0203, "lr": 3.853696390206484e-05, "epoch": 1.0496, "percentage": 21.03, "elapsed_time": "2:49:42", "remaining_time": "10:37:24"} +{"current_steps": 83, "total_steps": 390, "loss": 1.0205, "lr": 3.846901615704734e-05, "epoch": 1.0624, "percentage": 21.28, "elapsed_time": "2:51:52", "remaining_time": "10:35:43"} +{"current_steps": 84, "total_steps": 390, "loss": 1.0338, "lr": 3.839958887317649e-05, "epoch": 1.0752, "percentage": 21.54, "elapsed_time": "2:53:47", "remaining_time": "10:33:05"} +{"current_steps": 85, "total_steps": 390, "loss": 1.0165, "lr": 3.832868761221926e-05, "epoch": 1.088, "percentage": 21.79, "elapsed_time": "2:55:59", "remaining_time": "10:31:30"} +{"current_steps": 86, "total_steps": 390, "loss": 1.0115, "lr": 3.825631805402182e-05, "epoch": 1.1008, "percentage": 22.05, "elapsed_time": "2:58:06", "remaining_time": "10:29:34"} +{"current_steps": 87, "total_steps": 390, "loss": 1.0427, "lr": 3.818248599605448e-05, "epoch": 1.1136, "percentage": 22.31, "elapsed_time": "3:00:14", "remaining_time": "10:27:43"} +{"current_steps": 88, "total_steps": 390, "loss": 1.0209, "lr": 3.810719735294731e-05, "epoch": 1.1264, "percentage": 22.56, "elapsed_time": "3:02:13", "remaining_time": "10:25:22"} +{"current_steps": 89, "total_steps": 390, "loss": 1.0251, "lr": 3.8030458156016326e-05, "epoch": 1.1392, "percentage": 22.82, "elapsed_time": "3:04:15", "remaining_time": "10:23:10"} +{"current_steps": 90, "total_steps": 390, "loss": 1.0148, "lr": 3.795227455278029e-05, "epoch": 1.152, "percentage": 23.08, "elapsed_time": "3:06:25", "remaining_time": "10:21:23"} +{"current_steps": 91, "total_steps": 390, "loss": 1.0425, "lr": 3.787265280646825e-05, "epoch": 1.1648, "percentage": 23.33, "elapsed_time": "3:08:29", "remaining_time": "10:19:20"} +{"current_steps": 92, "total_steps": 390, "loss": 1.0261, "lr": 3.7791599295517825e-05, "epoch": 1.1776, "percentage": 23.59, "elapsed_time": "3:10:34", "remaining_time": "10:17:16"} +{"current_steps": 93, "total_steps": 390, "loss": 1.0227, "lr": 3.7709120513064196e-05, "epoch": 1.1904, "percentage": 23.85, "elapsed_time": "3:12:53", "remaining_time": "10:15:59"} +{"current_steps": 94, "total_steps": 390, "loss": 1.0252, "lr": 3.762522306641998e-05, "epoch": 1.2032, "percentage": 24.1, "elapsed_time": "3:14:57", "remaining_time": "10:13:55"} +{"current_steps": 95, "total_steps": 390, "loss": 1.0313, "lr": 3.7539913676545874e-05, "epoch": 1.216, "percentage": 24.36, "elapsed_time": "3:17:02", "remaining_time": "10:11:52"} +{"current_steps": 96, "total_steps": 390, "loss": 1.031, "lr": 3.745319917751229e-05, "epoch": 1.2288000000000001, "percentage": 24.62, "elapsed_time": "3:19:13", "remaining_time": "10:10:08"} +{"current_steps": 97, "total_steps": 390, "loss": 1.0342, "lr": 3.736508651595188e-05, "epoch": 1.2416, "percentage": 24.87, "elapsed_time": "3:21:02", "remaining_time": "10:07:17"} +{"current_steps": 98, "total_steps": 390, "loss": 1.0101, "lr": 3.727558275050301e-05, "epoch": 1.2544, "percentage": 25.13, "elapsed_time": "3:23:01", "remaining_time": "10:04:56"} +{"current_steps": 99, "total_steps": 390, "loss": 1.0489, "lr": 3.718469505124434e-05, "epoch": 1.2671999999999999, "percentage": 25.38, "elapsed_time": "3:24:53", "remaining_time": "10:02:16"} +{"current_steps": 100, "total_steps": 390, "loss": 1.022, "lr": 3.709243069912041e-05, "epoch": 1.28, "percentage": 25.64, "elapsed_time": "3:27:00", "remaining_time": "10:00:18"} +{"current_steps": 101, "total_steps": 390, "loss": 1.0637, "lr": 3.699879708535838e-05, "epoch": 1.2928, "percentage": 25.9, "elapsed_time": "3:29:11", "remaining_time": "9:58:34"} +{"current_steps": 102, "total_steps": 390, "loss": 1.0546, "lr": 3.69038017108759e-05, "epoch": 1.3056, "percentage": 26.15, "elapsed_time": "3:31:18", "remaining_time": "9:56:39"} +{"current_steps": 103, "total_steps": 390, "loss": 1.0747, "lr": 3.680745218568026e-05, "epoch": 1.3184, "percentage": 26.41, "elapsed_time": "3:33:28", "remaining_time": "9:54:50"} +{"current_steps": 104, "total_steps": 390, "loss": 1.0375, "lr": 3.6709756228258735e-05, "epoch": 1.3312, "percentage": 26.67, "elapsed_time": "3:35:26", "remaining_time": "9:52:27"} +{"current_steps": 105, "total_steps": 390, "loss": 1.0611, "lr": 3.6610721664960236e-05, "epoch": 1.3439999999999999, "percentage": 26.92, "elapsed_time": "3:37:21", "remaining_time": "9:49:57"} +{"current_steps": 106, "total_steps": 390, "loss": 1.0217, "lr": 3.65103564293684e-05, "epoch": 1.3568, "percentage": 27.18, "elapsed_time": "3:39:23", "remaining_time": "9:47:48"} +{"current_steps": 107, "total_steps": 390, "loss": 1.0274, "lr": 3.640866856166601e-05, "epoch": 1.3696, "percentage": 27.44, "elapsed_time": "3:41:32", "remaining_time": "9:45:56"} +{"current_steps": 108, "total_steps": 390, "loss": 1.0363, "lr": 3.6305666207990886e-05, "epoch": 1.3824, "percentage": 27.69, "elapsed_time": "3:43:48", "remaining_time": "9:44:23"} +{"current_steps": 109, "total_steps": 390, "loss": 1.0105, "lr": 3.6201357619783336e-05, "epoch": 1.3952, "percentage": 27.95, "elapsed_time": "3:45:48", "remaining_time": "9:42:06"} +{"current_steps": 110, "total_steps": 390, "loss": 1.0696, "lr": 3.609575115312511e-05, "epoch": 1.408, "percentage": 28.21, "elapsed_time": "3:47:49", "remaining_time": "9:39:55"} +{"current_steps": 111, "total_steps": 390, "loss": 1.0446, "lr": 3.598885526807003e-05, "epoch": 1.4208, "percentage": 28.46, "elapsed_time": "3:49:55", "remaining_time": "9:37:54"} +{"current_steps": 112, "total_steps": 390, "loss": 1.059, "lr": 3.5880678527966224e-05, "epoch": 1.4336, "percentage": 28.72, "elapsed_time": "3:51:54", "remaining_time": "9:35:36"} +{"current_steps": 113, "total_steps": 390, "loss": 1.0335, "lr": 3.577122959877017e-05, "epoch": 1.4464000000000001, "percentage": 28.97, "elapsed_time": "3:54:11", "remaining_time": "9:34:05"} +{"current_steps": 114, "total_steps": 390, "loss": 1.065, "lr": 3.566051724835245e-05, "epoch": 1.4592, "percentage": 29.23, "elapsed_time": "3:56:11", "remaining_time": "9:31:49"} +{"current_steps": 115, "total_steps": 390, "loss": 1.006, "lr": 3.554855034579532e-05, "epoch": 1.472, "percentage": 29.49, "elapsed_time": "3:58:11", "remaining_time": "9:29:35"} +{"current_steps": 116, "total_steps": 390, "loss": 1.0279, "lr": 3.5435337860682304e-05, "epoch": 1.4848, "percentage": 29.74, "elapsed_time": "4:00:02", "remaining_time": "9:27:00"} +{"current_steps": 117, "total_steps": 390, "loss": 1.0442, "lr": 3.532088886237956e-05, "epoch": 1.4976, "percentage": 30.0, "elapsed_time": "4:02:03", "remaining_time": "9:24:49"} +{"current_steps": 118, "total_steps": 390, "loss": 1.0209, "lr": 3.520521251930941e-05, "epoch": 1.5104, "percentage": 30.26, "elapsed_time": "4:04:06", "remaining_time": "9:22:40"} +{"current_steps": 119, "total_steps": 390, "loss": 1.0614, "lr": 3.5088318098215805e-05, "epoch": 1.5232, "percentage": 30.51, "elapsed_time": "4:06:13", "remaining_time": "9:20:44"} +{"current_steps": 120, "total_steps": 390, "loss": 1.0298, "lr": 3.497021496342203e-05, "epoch": 1.536, "percentage": 30.77, "elapsed_time": "4:08:15", "remaining_time": "9:18:34"} +{"current_steps": 121, "total_steps": 390, "loss": 1.0221, "lr": 3.485091257608047e-05, "epoch": 1.5488, "percentage": 31.03, "elapsed_time": "4:10:34", "remaining_time": "9:17:03"} +{"current_steps": 122, "total_steps": 390, "loss": 0.9958, "lr": 3.473042049341474e-05, "epoch": 1.5615999999999999, "percentage": 31.28, "elapsed_time": "4:12:41", "remaining_time": "9:15:06"} +{"current_steps": 123, "total_steps": 390, "loss": 1.042, "lr": 3.4608748367954064e-05, "epoch": 1.5744, "percentage": 31.54, "elapsed_time": "4:14:45", "remaining_time": "9:13:00"} +{"current_steps": 124, "total_steps": 390, "loss": 1.005, "lr": 3.4485905946759965e-05, "epoch": 1.5872000000000002, "percentage": 31.79, "elapsed_time": "4:16:37", "remaining_time": "9:10:29"} +{"current_steps": 125, "total_steps": 390, "loss": 1.0019, "lr": 3.4361903070645484e-05, "epoch": 1.6, "percentage": 32.05, "elapsed_time": "4:18:36", "remaining_time": "9:08:14"} +{"current_steps": 126, "total_steps": 390, "loss": 1.0474, "lr": 3.423674967338681e-05, "epoch": 1.6128, "percentage": 32.31, "elapsed_time": "4:20:31", "remaining_time": "9:05:52"} +{"current_steps": 127, "total_steps": 390, "loss": 1.0099, "lr": 3.411045578092754e-05, "epoch": 1.6256, "percentage": 32.56, "elapsed_time": "4:22:30", "remaining_time": "9:03:38"} +{"current_steps": 128, "total_steps": 390, "loss": 1.0727, "lr": 3.398303151057543e-05, "epoch": 1.6383999999999999, "percentage": 32.82, "elapsed_time": "4:24:33", "remaining_time": "9:01:31"} +{"current_steps": 129, "total_steps": 390, "loss": 1.0243, "lr": 3.385448707019199e-05, "epoch": 1.6512, "percentage": 33.08, "elapsed_time": "4:26:43", "remaining_time": "8:59:39"} +{"current_steps": 130, "total_steps": 390, "loss": 0.9836, "lr": 3.372483275737468e-05, "epoch": 1.6640000000000001, "percentage": 33.33, "elapsed_time": "4:28:43", "remaining_time": "8:57:26"} +{"current_steps": 131, "total_steps": 390, "loss": 1.0474, "lr": 3.359407895863199e-05, "epoch": 1.6768, "percentage": 33.59, "elapsed_time": "4:30:57", "remaining_time": "8:55:43"} +{"current_steps": 132, "total_steps": 390, "loss": 1.0421, "lr": 3.34622361485514e-05, "epoch": 1.6896, "percentage": 33.85, "elapsed_time": "4:32:46", "remaining_time": "8:53:09"} +{"current_steps": 133, "total_steps": 390, "loss": 1.05, "lr": 3.332931488896029e-05, "epoch": 1.7024, "percentage": 34.1, "elapsed_time": "4:34:46", "remaining_time": "8:50:58"} +{"current_steps": 134, "total_steps": 390, "loss": 1.0253, "lr": 3.319532582807977e-05, "epoch": 1.7151999999999998, "percentage": 34.36, "elapsed_time": "4:36:29", "remaining_time": "8:48:12"} +{"current_steps": 135, "total_steps": 390, "loss": 1.0422, "lr": 3.30602796996717e-05, "epoch": 1.728, "percentage": 34.62, "elapsed_time": "4:38:24", "remaining_time": "8:45:53"} +{"current_steps": 136, "total_steps": 390, "loss": 1.0177, "lr": 3.2924187322178865e-05, "epoch": 1.7408000000000001, "percentage": 34.87, "elapsed_time": "4:40:32", "remaining_time": "8:43:56"} +{"current_steps": 137, "total_steps": 390, "loss": 1.0394, "lr": 3.278705959785821e-05, "epoch": 1.7536, "percentage": 35.13, "elapsed_time": "4:42:23", "remaining_time": "8:41:30"} +{"current_steps": 138, "total_steps": 390, "loss": 1.024, "lr": 3.2648907511907544e-05, "epoch": 1.7664, "percentage": 35.38, "elapsed_time": "4:44:17", "remaining_time": "8:39:08"} +{"current_steps": 139, "total_steps": 390, "loss": 1.0111, "lr": 3.250974213158555e-05, "epoch": 1.7792, "percentage": 35.64, "elapsed_time": "4:46:09", "remaining_time": "8:36:43"} +{"current_steps": 140, "total_steps": 390, "loss": 0.9901, "lr": 3.23695746053251e-05, "epoch": 1.792, "percentage": 35.9, "elapsed_time": "4:48:17", "remaining_time": "8:34:48"} +{"current_steps": 141, "total_steps": 390, "loss": 1.0533, "lr": 3.222841616184025e-05, "epoch": 1.8048, "percentage": 36.15, "elapsed_time": "4:50:09", "remaining_time": "8:32:24"} +{"current_steps": 142, "total_steps": 390, "loss": 1.0669, "lr": 3.208627810922665e-05, "epoch": 1.8176, "percentage": 36.41, "elapsed_time": "4:52:19", "remaining_time": "8:30:32"} +{"current_steps": 143, "total_steps": 390, "loss": 0.9949, "lr": 3.194317183405573e-05, "epoch": 1.8304, "percentage": 36.67, "elapsed_time": "4:54:24", "remaining_time": "8:28:31"} +{"current_steps": 144, "total_steps": 390, "loss": 1.0575, "lr": 3.1799108800462466e-05, "epoch": 1.8432, "percentage": 36.92, "elapsed_time": "4:56:31", "remaining_time": "8:26:33"} +{"current_steps": 145, "total_steps": 390, "loss": 1.0161, "lr": 3.1654100549227024e-05, "epoch": 1.8559999999999999, "percentage": 37.18, "elapsed_time": "4:58:45", "remaining_time": "8:24:47"} +{"current_steps": 146, "total_steps": 390, "loss": 1.021, "lr": 3.1508158696850275e-05, "epoch": 1.8688, "percentage": 37.44, "elapsed_time": "5:00:35", "remaining_time": "8:22:20"} +{"current_steps": 147, "total_steps": 390, "loss": 1.0205, "lr": 3.136129493462312e-05, "epoch": 1.8816000000000002, "percentage": 37.69, "elapsed_time": "5:02:30", "remaining_time": "8:20:04"} +{"current_steps": 148, "total_steps": 390, "loss": 1.0128, "lr": 3.121352102768998e-05, "epoch": 1.8944, "percentage": 37.95, "elapsed_time": "5:04:36", "remaining_time": "8:18:03"} +{"current_steps": 149, "total_steps": 390, "loss": 1.0624, "lr": 3.106484881410628e-05, "epoch": 1.9072, "percentage": 38.21, "elapsed_time": "5:06:50", "remaining_time": "8:16:18"} +{"current_steps": 150, "total_steps": 390, "loss": 1.045, "lr": 3.091529020389009e-05, "epoch": 1.92, "percentage": 38.46, "elapsed_time": "5:08:52", "remaining_time": "8:14:11"} +{"current_steps": 151, "total_steps": 390, "loss": 1.0603, "lr": 3.076485717806808e-05, "epoch": 1.9327999999999999, "percentage": 38.72, "elapsed_time": "5:11:01", "remaining_time": "8:12:17"} +{"current_steps": 152, "total_steps": 390, "loss": 1.047, "lr": 3.061356178771564e-05, "epoch": 1.9456, "percentage": 38.97, "elapsed_time": "5:13:06", "remaining_time": "8:10:15"} +{"current_steps": 153, "total_steps": 390, "loss": 1.0348, "lr": 3.0461416152991555e-05, "epoch": 1.9584000000000001, "percentage": 39.23, "elapsed_time": "5:15:14", "remaining_time": "8:08:19"} +{"current_steps": 154, "total_steps": 390, "loss": 1.0388, "lr": 3.0308432462167045e-05, "epoch": 1.9712, "percentage": 39.49, "elapsed_time": "5:17:19", "remaining_time": "8:06:17"} +{"current_steps": 155, "total_steps": 390, "loss": 1.0082, "lr": 3.015462297064936e-05, "epoch": 1.984, "percentage": 39.74, "elapsed_time": "5:19:31", "remaining_time": "8:04:25"} +{"current_steps": 156, "total_steps": 390, "loss": 1.0165, "lr": 3.0000000000000004e-05, "epoch": 1.9968, "percentage": 40.0, "elapsed_time": "5:21:38", "remaining_time": "8:02:27"} +{"current_steps": 157, "total_steps": 390, "loss": 0.9535, "lr": 2.98445759369477e-05, "epoch": 2.0096, "percentage": 40.26, "elapsed_time": "5:24:29", "remaining_time": "8:01:34"} +{"current_steps": 158, "total_steps": 390, "loss": 0.8855, "lr": 2.9688363232396056e-05, "epoch": 2.0224, "percentage": 40.51, "elapsed_time": "5:26:26", "remaining_time": "7:59:19"} +{"current_steps": 159, "total_steps": 390, "loss": 0.9174, "lr": 2.9531374400426158e-05, "epoch": 2.0352, "percentage": 40.77, "elapsed_time": "5:28:31", "remaining_time": "7:57:16"} +{"current_steps": 160, "total_steps": 390, "loss": 0.9103, "lr": 2.9373622017294075e-05, "epoch": 2.048, "percentage": 41.03, "elapsed_time": "5:30:27", "remaining_time": "7:55:01"} +{"current_steps": 161, "total_steps": 390, "loss": 0.8442, "lr": 2.9215118720423375e-05, "epoch": 2.0608, "percentage": 41.28, "elapsed_time": "5:32:30", "remaining_time": "7:52:56"} +{"current_steps": 162, "total_steps": 390, "loss": 0.8601, "lr": 2.9055877207392752e-05, "epoch": 2.0736, "percentage": 41.54, "elapsed_time": "5:34:24", "remaining_time": "7:50:39"} +{"current_steps": 163, "total_steps": 390, "loss": 0.8757, "lr": 2.8895910234918828e-05, "epoch": 2.0864, "percentage": 41.79, "elapsed_time": "5:36:37", "remaining_time": "7:48:48"} +{"current_steps": 164, "total_steps": 390, "loss": 0.8921, "lr": 2.873523061783426e-05, "epoch": 2.0992, "percentage": 42.05, "elapsed_time": "5:38:44", "remaining_time": "7:46:47"} +{"current_steps": 165, "total_steps": 390, "loss": 0.8993, "lr": 2.8573851228061084e-05, "epoch": 2.112, "percentage": 42.31, "elapsed_time": "5:40:48", "remaining_time": "7:44:44"} +{"current_steps": 166, "total_steps": 390, "loss": 0.8283, "lr": 2.8411784993579633e-05, "epoch": 2.1248, "percentage": 42.56, "elapsed_time": "5:42:52", "remaining_time": "7:42:41"} +{"current_steps": 167, "total_steps": 390, "loss": 0.9054, "lr": 2.8249044897392814e-05, "epoch": 2.1376, "percentage": 42.82, "elapsed_time": "5:44:59", "remaining_time": "7:40:40"} +{"current_steps": 168, "total_steps": 390, "loss": 0.8712, "lr": 2.80856439764861e-05, "epoch": 2.1504, "percentage": 43.08, "elapsed_time": "5:47:15", "remaining_time": "7:38:52"} +{"current_steps": 169, "total_steps": 390, "loss": 0.8566, "lr": 2.792159532078314e-05, "epoch": 2.1632, "percentage": 43.33, "elapsed_time": "5:49:11", "remaining_time": "7:36:37"} +{"current_steps": 170, "total_steps": 390, "loss": 0.888, "lr": 2.77569120720971e-05, "epoch": 2.176, "percentage": 43.59, "elapsed_time": "5:51:16", "remaining_time": "7:34:34"} +{"current_steps": 171, "total_steps": 390, "loss": 0.8974, "lr": 2.7591607423077932e-05, "epoch": 2.1888, "percentage": 43.85, "elapsed_time": "5:53:18", "remaining_time": "7:32:28"} +{"current_steps": 172, "total_steps": 390, "loss": 0.8638, "lr": 2.7425694616155474e-05, "epoch": 2.2016, "percentage": 44.1, "elapsed_time": "5:55:31", "remaining_time": "7:30:36"} +{"current_steps": 173, "total_steps": 390, "loss": 0.902, "lr": 2.7259186942478656e-05, "epoch": 2.2144, "percentage": 44.36, "elapsed_time": "5:57:27", "remaining_time": "7:28:22"} +{"current_steps": 174, "total_steps": 390, "loss": 0.9118, "lr": 2.7092097740850712e-05, "epoch": 2.2272, "percentage": 44.62, "elapsed_time": "5:59:23", "remaining_time": "7:26:08"} +{"current_steps": 175, "total_steps": 390, "loss": 0.8978, "lr": 2.692444039666066e-05, "epoch": 2.24, "percentage": 44.87, "elapsed_time": "6:01:27", "remaining_time": "7:24:04"} +{"current_steps": 176, "total_steps": 390, "loss": 0.8812, "lr": 2.6756228340810946e-05, "epoch": 2.2528, "percentage": 45.13, "elapsed_time": "6:03:26", "remaining_time": "7:21:54"} +{"current_steps": 177, "total_steps": 390, "loss": 0.881, "lr": 2.6587475048641596e-05, "epoch": 2.2656, "percentage": 45.38, "elapsed_time": "6:05:35", "remaining_time": "7:19:57"} +{"current_steps": 178, "total_steps": 390, "loss": 0.8689, "lr": 2.6418194038850634e-05, "epoch": 2.2784, "percentage": 45.64, "elapsed_time": "6:07:41", "remaining_time": "7:17:54"} +{"current_steps": 179, "total_steps": 390, "loss": 0.8778, "lr": 2.624839887241115e-05, "epoch": 2.2912, "percentage": 45.9, "elapsed_time": "6:09:48", "remaining_time": "7:15:55"} +{"current_steps": 180, "total_steps": 390, "loss": 0.9127, "lr": 2.607810315148494e-05, "epoch": 2.304, "percentage": 46.15, "elapsed_time": "6:12:00", "remaining_time": "7:14:00"} +{"current_steps": 181, "total_steps": 390, "loss": 0.8929, "lr": 2.5907320518332827e-05, "epoch": 2.3168, "percentage": 46.41, "elapsed_time": "6:14:01", "remaining_time": "7:11:53"} +{"current_steps": 182, "total_steps": 390, "loss": 0.887, "lr": 2.5736064654221808e-05, "epoch": 2.3296, "percentage": 46.67, "elapsed_time": "6:16:10", "remaining_time": "7:09:54"} +{"current_steps": 183, "total_steps": 390, "loss": 0.8847, "lr": 2.5564349278329056e-05, "epoch": 2.3424, "percentage": 46.92, "elapsed_time": "6:18:17", "remaining_time": "7:07:54"} +{"current_steps": 184, "total_steps": 390, "loss": 0.8564, "lr": 2.539218814664288e-05, "epoch": 2.3552, "percentage": 47.18, "elapsed_time": "6:20:20", "remaining_time": "7:05:49"} +{"current_steps": 185, "total_steps": 390, "loss": 0.8604, "lr": 2.521959505086075e-05, "epoch": 2.368, "percentage": 47.44, "elapsed_time": "6:22:27", "remaining_time": "7:03:48"} +{"current_steps": 186, "total_steps": 390, "loss": 0.8296, "lr": 2.5046583817284437e-05, "epoch": 2.3808, "percentage": 47.69, "elapsed_time": "6:24:17", "remaining_time": "7:01:28"} +{"current_steps": 187, "total_steps": 390, "loss": 0.8715, "lr": 2.487316830571244e-05, "epoch": 2.3936, "percentage": 47.95, "elapsed_time": "6:26:19", "remaining_time": "6:59:22"} +{"current_steps": 188, "total_steps": 390, "loss": 0.8767, "lr": 2.4699362408329646e-05, "epoch": 2.4064, "percentage": 48.21, "elapsed_time": "6:28:24", "remaining_time": "6:57:20"} +{"current_steps": 189, "total_steps": 390, "loss": 0.8868, "lr": 2.4525180048594452e-05, "epoch": 2.4192, "percentage": 48.46, "elapsed_time": "6:30:31", "remaining_time": "6:55:19"} +{"current_steps": 190, "total_steps": 390, "loss": 0.8933, "lr": 2.435063518012335e-05, "epoch": 2.432, "percentage": 48.72, "elapsed_time": "6:32:28", "remaining_time": "6:53:07"} +{"current_steps": 191, "total_steps": 390, "loss": 0.8951, "lr": 2.4175741785573177e-05, "epoch": 2.4448, "percentage": 48.97, "elapsed_time": "6:34:32", "remaining_time": "6:51:04"} +{"current_steps": 192, "total_steps": 390, "loss": 0.8865, "lr": 2.4000513875520892e-05, "epoch": 2.4576000000000002, "percentage": 49.23, "elapsed_time": "6:36:41", "remaining_time": "6:49:05"} +{"current_steps": 193, "total_steps": 390, "loss": 0.8794, "lr": 2.3824965487341247e-05, "epoch": 2.4704, "percentage": 49.49, "elapsed_time": "6:38:40", "remaining_time": "6:46:56"} +{"current_steps": 194, "total_steps": 390, "loss": 0.9061, "lr": 2.3649110684082258e-05, "epoch": 2.4832, "percentage": 49.74, "elapsed_time": "6:40:40", "remaining_time": "6:44:48"} +{"current_steps": 195, "total_steps": 390, "loss": 0.8858, "lr": 2.3472963553338614e-05, "epoch": 2.496, "percentage": 50.0, "elapsed_time": "6:42:50", "remaining_time": "6:42:50"} +{"current_steps": 196, "total_steps": 390, "loss": 0.8667, "lr": 2.3296538206123134e-05, "epoch": 2.5088, "percentage": 50.26, "elapsed_time": "6:44:37", "remaining_time": "6:40:29"} +{"current_steps": 197, "total_steps": 390, "loss": 0.8812, "lr": 2.311984877573636e-05, "epoch": 2.5216, "percentage": 50.51, "elapsed_time": "6:46:34", "remaining_time": "6:38:19"} +{"current_steps": 198, "total_steps": 390, "loss": 0.8887, "lr": 2.2942909416634326e-05, "epoch": 2.5343999999999998, "percentage": 50.77, "elapsed_time": "6:48:44", "remaining_time": "6:36:21"} +{"current_steps": 199, "total_steps": 390, "loss": 0.882, "lr": 2.2765734303294666e-05, "epoch": 2.5472, "percentage": 51.03, "elapsed_time": "6:50:55", "remaining_time": "6:34:24"} +{"current_steps": 200, "total_steps": 390, "loss": 0.8557, "lr": 2.2588337629081107e-05, "epoch": 2.56, "percentage": 51.28, "elapsed_time": "6:53:04", "remaining_time": "6:32:25"} +{"current_steps": 201, "total_steps": 390, "loss": 0.881, "lr": 2.2410733605106462e-05, "epoch": 2.5728, "percentage": 51.54, "elapsed_time": "6:55:12", "remaining_time": "6:30:25"} +{"current_steps": 202, "total_steps": 390, "loss": 0.8844, "lr": 2.2232936459094158e-05, "epoch": 2.5856, "percentage": 51.79, "elapsed_time": "6:57:14", "remaining_time": "6:28:18"} +{"current_steps": 203, "total_steps": 390, "loss": 0.8555, "lr": 2.205496043423849e-05, "epoch": 2.5984, "percentage": 52.05, "elapsed_time": "6:59:16", "remaining_time": "6:26:13"} +{"current_steps": 204, "total_steps": 390, "loss": 0.9151, "lr": 2.1876819788063586e-05, "epoch": 2.6112, "percentage": 52.31, "elapsed_time": "7:01:07", "remaining_time": "6:23:57"} +{"current_steps": 205, "total_steps": 390, "loss": 0.8532, "lr": 2.16985287912813e-05, "epoch": 2.624, "percentage": 52.56, "elapsed_time": "7:03:21", "remaining_time": "6:22:03"} +{"current_steps": 206, "total_steps": 390, "loss": 0.9498, "lr": 2.1520101726647922e-05, "epoch": 2.6368, "percentage": 52.82, "elapsed_time": "7:05:19", "remaining_time": "6:19:53"} +{"current_steps": 207, "total_steps": 390, "loss": 0.8701, "lr": 2.1341552887820048e-05, "epoch": 2.6496, "percentage": 53.08, "elapsed_time": "7:07:04", "remaining_time": "6:17:33"} +{"current_steps": 208, "total_steps": 390, "loss": 0.8511, "lr": 2.1162896578209517e-05, "epoch": 2.6624, "percentage": 53.33, "elapsed_time": "7:09:00", "remaining_time": "6:15:22"} +{"current_steps": 209, "total_steps": 390, "loss": 0.8587, "lr": 2.0984147109837564e-05, "epoch": 2.6752000000000002, "percentage": 53.59, "elapsed_time": "7:11:04", "remaining_time": "6:13:19"} +{"current_steps": 210, "total_steps": 390, "loss": 0.8273, "lr": 2.0805318802188307e-05, "epoch": 2.6879999999999997, "percentage": 53.85, "elapsed_time": "7:13:05", "remaining_time": "6:11:13"} +{"current_steps": 211, "total_steps": 390, "loss": 0.8766, "lr": 2.0626425981061608e-05, "epoch": 2.7008, "percentage": 54.1, "elapsed_time": "7:15:16", "remaining_time": "6:09:15"} +{"current_steps": 212, "total_steps": 390, "loss": 0.8733, "lr": 2.0447482977425465e-05, "epoch": 2.7136, "percentage": 54.36, "elapsed_time": "7:17:14", "remaining_time": "6:07:07"} +{"current_steps": 213, "total_steps": 390, "loss": 0.8684, "lr": 2.0268504126267952e-05, "epoch": 2.7264, "percentage": 54.62, "elapsed_time": "7:19:06", "remaining_time": "6:04:53"} +{"current_steps": 214, "total_steps": 390, "loss": 0.8812, "lr": 2.008950376544887e-05, "epoch": 2.7392, "percentage": 54.87, "elapsed_time": "7:21:10", "remaining_time": "6:02:49"} +{"current_steps": 215, "total_steps": 390, "loss": 0.8658, "lr": 1.9910496234551132e-05, "epoch": 2.752, "percentage": 55.13, "elapsed_time": "7:23:21", "remaining_time": "6:00:52"} +{"current_steps": 216, "total_steps": 390, "loss": 0.8324, "lr": 1.9731495873732055e-05, "epoch": 2.7648, "percentage": 55.38, "elapsed_time": "7:25:23", "remaining_time": "5:58:47"} +{"current_steps": 217, "total_steps": 390, "loss": 0.8876, "lr": 1.9552517022574542e-05, "epoch": 2.7776, "percentage": 55.64, "elapsed_time": "7:27:32", "remaining_time": "5:56:47"} +{"current_steps": 218, "total_steps": 390, "loss": 0.873, "lr": 1.93735740189384e-05, "epoch": 2.7904, "percentage": 55.9, "elapsed_time": "7:29:31", "remaining_time": "5:54:39"} +{"current_steps": 219, "total_steps": 390, "loss": 0.9178, "lr": 1.9194681197811703e-05, "epoch": 2.8032, "percentage": 56.15, "elapsed_time": "7:31:28", "remaining_time": "5:52:31"} +{"current_steps": 220, "total_steps": 390, "loss": 0.9269, "lr": 1.901585289016244e-05, "epoch": 2.816, "percentage": 56.41, "elapsed_time": "7:33:39", "remaining_time": "5:50:32"} +{"current_steps": 221, "total_steps": 390, "loss": 0.9416, "lr": 1.8837103421790486e-05, "epoch": 2.8288, "percentage": 56.67, "elapsed_time": "7:35:45", "remaining_time": "5:48:30"} +{"current_steps": 222, "total_steps": 390, "loss": 0.9035, "lr": 1.8658447112179952e-05, "epoch": 2.8416, "percentage": 56.92, "elapsed_time": "7:37:57", "remaining_time": "5:46:33"} +{"current_steps": 223, "total_steps": 390, "loss": 0.8947, "lr": 1.8479898273352084e-05, "epoch": 2.8544, "percentage": 57.18, "elapsed_time": "7:39:52", "remaining_time": "5:44:23"} +{"current_steps": 224, "total_steps": 390, "loss": 0.8635, "lr": 1.83014712087187e-05, "epoch": 2.8672, "percentage": 57.44, "elapsed_time": "7:41:48", "remaining_time": "5:42:14"} +{"current_steps": 225, "total_steps": 390, "loss": 0.9178, "lr": 1.8123180211936417e-05, "epoch": 2.88, "percentage": 57.69, "elapsed_time": "7:43:39", "remaining_time": "5:40:00"} +{"current_steps": 226, "total_steps": 390, "loss": 0.8915, "lr": 1.794503956576152e-05, "epoch": 2.8928000000000003, "percentage": 57.95, "elapsed_time": "7:45:40", "remaining_time": "5:37:55"} +{"current_steps": 227, "total_steps": 390, "loss": 0.8862, "lr": 1.776706354090585e-05, "epoch": 2.9055999999999997, "percentage": 58.21, "elapsed_time": "7:47:54", "remaining_time": "5:35:59"} +{"current_steps": 228, "total_steps": 390, "loss": 0.8611, "lr": 1.758926639489354e-05, "epoch": 2.9184, "percentage": 58.46, "elapsed_time": "7:50:01", "remaining_time": "5:33:57"} +{"current_steps": 229, "total_steps": 390, "loss": 0.861, "lr": 1.7411662370918893e-05, "epoch": 2.9312, "percentage": 58.72, "elapsed_time": "7:51:56", "remaining_time": "5:31:47"} +{"current_steps": 230, "total_steps": 390, "loss": 0.92, "lr": 1.7234265696705344e-05, "epoch": 2.944, "percentage": 58.97, "elapsed_time": "7:54:11", "remaining_time": "5:29:52"} +{"current_steps": 231, "total_steps": 390, "loss": 0.9233, "lr": 1.7057090583365678e-05, "epoch": 2.9568, "percentage": 59.23, "elapsed_time": "7:56:21", "remaining_time": "5:27:53"} +{"current_steps": 232, "total_steps": 390, "loss": 0.8436, "lr": 1.6880151224263646e-05, "epoch": 2.9696, "percentage": 59.49, "elapsed_time": "7:58:23", "remaining_time": "5:25:48"} +{"current_steps": 233, "total_steps": 390, "loss": 0.9097, "lr": 1.6703461793876876e-05, "epoch": 2.9824, "percentage": 59.74, "elapsed_time": "8:00:37", "remaining_time": "5:23:51"} +{"current_steps": 234, "total_steps": 390, "loss": 0.8545, "lr": 1.6527036446661396e-05, "epoch": 2.9952, "percentage": 60.0, "elapsed_time": "8:02:31", "remaining_time": "5:21:41"} +{"current_steps": 235, "total_steps": 390, "loss": 0.8374, "lr": 1.635088931591775e-05, "epoch": 3.008, "percentage": 60.26, "elapsed_time": "8:05:19", "remaining_time": "5:20:06"} +{"current_steps": 236, "total_steps": 390, "loss": 0.7423, "lr": 1.6175034512658753e-05, "epoch": 3.0208, "percentage": 60.51, "elapsed_time": "8:07:26", "remaining_time": "5:18:04"} +{"current_steps": 237, "total_steps": 390, "loss": 0.7227, "lr": 1.5999486124479115e-05, "epoch": 3.0336, "percentage": 60.77, "elapsed_time": "8:09:38", "remaining_time": "5:16:06"} +{"current_steps": 238, "total_steps": 390, "loss": 0.7677, "lr": 1.5824258214426833e-05, "epoch": 3.0464, "percentage": 61.03, "elapsed_time": "8:11:48", "remaining_time": "5:14:05"} +{"current_steps": 239, "total_steps": 390, "loss": 0.7768, "lr": 1.5649364819876655e-05, "epoch": 3.0592, "percentage": 61.28, "elapsed_time": "8:13:57", "remaining_time": "5:12:05"} +{"current_steps": 240, "total_steps": 390, "loss": 0.7745, "lr": 1.547481995140556e-05, "epoch": 3.072, "percentage": 61.54, "elapsed_time": "8:16:04", "remaining_time": "5:10:02"} +{"current_steps": 241, "total_steps": 390, "loss": 0.7342, "lr": 1.5300637591670357e-05, "epoch": 3.0848, "percentage": 61.79, "elapsed_time": "8:18:10", "remaining_time": "5:08:00"} +{"current_steps": 242, "total_steps": 390, "loss": 0.7096, "lr": 1.5126831694287564e-05, "epoch": 3.0976, "percentage": 62.05, "elapsed_time": "8:20:02", "remaining_time": "5:05:48"} +{"current_steps": 243, "total_steps": 390, "loss": 0.7988, "lr": 1.4953416182715566e-05, "epoch": 3.1104, "percentage": 62.31, "elapsed_time": "8:21:57", "remaining_time": "5:03:39"} +{"current_steps": 244, "total_steps": 390, "loss": 0.7481, "lr": 1.478040494913926e-05, "epoch": 3.1232, "percentage": 62.56, "elapsed_time": "8:24:11", "remaining_time": "5:01:41"} +{"current_steps": 245, "total_steps": 390, "loss": 0.757, "lr": 1.460781185335713e-05, "epoch": 3.136, "percentage": 62.82, "elapsed_time": "8:26:09", "remaining_time": "4:59:33"} +{"current_steps": 246, "total_steps": 390, "loss": 0.7826, "lr": 1.443565072167095e-05, "epoch": 3.1488, "percentage": 63.08, "elapsed_time": "8:28:05", "remaining_time": "4:57:25"} +{"current_steps": 247, "total_steps": 390, "loss": 0.7886, "lr": 1.4263935345778202e-05, "epoch": 3.1616, "percentage": 63.33, "elapsed_time": "8:30:24", "remaining_time": "4:55:29"} +{"current_steps": 248, "total_steps": 390, "loss": 0.7768, "lr": 1.409267948166718e-05, "epoch": 3.1744, "percentage": 63.59, "elapsed_time": "8:32:32", "remaining_time": "4:53:28"} +{"current_steps": 249, "total_steps": 390, "loss": 0.7398, "lr": 1.3921896848515064e-05, "epoch": 3.1872, "percentage": 63.85, "elapsed_time": "8:34:24", "remaining_time": "4:51:17"} +{"current_steps": 250, "total_steps": 390, "loss": 0.7344, "lr": 1.3751601127588849e-05, "epoch": 3.2, "percentage": 64.1, "elapsed_time": "8:36:25", "remaining_time": "4:49:11"} +{"current_steps": 251, "total_steps": 390, "loss": 0.7289, "lr": 1.3581805961149371e-05, "epoch": 3.2128, "percentage": 64.36, "elapsed_time": "8:38:18", "remaining_time": "4:47:01"} +{"current_steps": 252, "total_steps": 390, "loss": 0.7285, "lr": 1.341252495135841e-05, "epoch": 3.2256, "percentage": 64.62, "elapsed_time": "8:40:29", "remaining_time": "4:45:01"} +{"current_steps": 253, "total_steps": 390, "loss": 0.7188, "lr": 1.324377165918906e-05, "epoch": 3.2384, "percentage": 64.87, "elapsed_time": "8:42:18", "remaining_time": "4:42:50"} +{"current_steps": 254, "total_steps": 390, "loss": 0.7723, "lr": 1.3075559603339354e-05, "epoch": 3.2512, "percentage": 65.13, "elapsed_time": "8:44:30", "remaining_time": "4:40:50"} +{"current_steps": 255, "total_steps": 390, "loss": 0.7881, "lr": 1.2907902259149287e-05, "epoch": 3.2640000000000002, "percentage": 65.38, "elapsed_time": "8:46:30", "remaining_time": "4:38:44"} +{"current_steps": 256, "total_steps": 390, "loss": 0.7191, "lr": 1.274081305752135e-05, "epoch": 3.2768, "percentage": 65.64, "elapsed_time": "8:48:42", "remaining_time": "4:36:44"} +{"current_steps": 257, "total_steps": 390, "loss": 0.7464, "lr": 1.2574305383844528e-05, "epoch": 3.2896, "percentage": 65.9, "elapsed_time": "8:50:42", "remaining_time": "4:34:38"} +{"current_steps": 258, "total_steps": 390, "loss": 0.7621, "lr": 1.2408392576922075e-05, "epoch": 3.3024, "percentage": 66.15, "elapsed_time": "8:53:06", "remaining_time": "4:32:45"} +{"current_steps": 259, "total_steps": 390, "loss": 0.7178, "lr": 1.2243087927902905e-05, "epoch": 3.3152, "percentage": 66.41, "elapsed_time": "8:55:03", "remaining_time": "4:30:37"} +{"current_steps": 260, "total_steps": 390, "loss": 0.8272, "lr": 1.2078404679216864e-05, "epoch": 3.328, "percentage": 66.67, "elapsed_time": "8:57:09", "remaining_time": "4:28:34"} +{"current_steps": 261, "total_steps": 390, "loss": 0.7726, "lr": 1.1914356023513904e-05, "epoch": 3.3407999999999998, "percentage": 66.92, "elapsed_time": "8:59:03", "remaining_time": "4:26:25"} +{"current_steps": 262, "total_steps": 390, "loss": 0.7578, "lr": 1.1750955102607193e-05, "epoch": 3.3536, "percentage": 67.18, "elapsed_time": "9:01:08", "remaining_time": "4:24:22"} +{"current_steps": 263, "total_steps": 390, "loss": 0.7829, "lr": 1.1588215006420374e-05, "epoch": 3.3664, "percentage": 67.44, "elapsed_time": "9:02:55", "remaining_time": "4:22:10"} +{"current_steps": 264, "total_steps": 390, "loss": 0.7438, "lr": 1.1426148771938915e-05, "epoch": 3.3792, "percentage": 67.69, "elapsed_time": "9:05:00", "remaining_time": "4:20:07"} +{"current_steps": 265, "total_steps": 390, "loss": 0.7771, "lr": 1.1264769382165748e-05, "epoch": 3.392, "percentage": 67.95, "elapsed_time": "9:06:59", "remaining_time": "4:18:01"} +{"current_steps": 266, "total_steps": 390, "loss": 0.7672, "lr": 1.110408976508118e-05, "epoch": 3.4048, "percentage": 68.21, "elapsed_time": "9:09:01", "remaining_time": "4:15:56"} +{"current_steps": 267, "total_steps": 390, "loss": 0.7912, "lr": 1.094412279260726e-05, "epoch": 3.4176, "percentage": 68.46, "elapsed_time": "9:11:09", "remaining_time": "4:13:54"} +{"current_steps": 268, "total_steps": 390, "loss": 0.784, "lr": 1.0784881279576635e-05, "epoch": 3.4304, "percentage": 68.72, "elapsed_time": "9:13:17", "remaining_time": "4:11:52"} +{"current_steps": 269, "total_steps": 390, "loss": 0.7489, "lr": 1.0626377982705929e-05, "epoch": 3.4432, "percentage": 68.97, "elapsed_time": "9:15:24", "remaining_time": "4:09:49"} +{"current_steps": 270, "total_steps": 390, "loss": 0.7784, "lr": 1.0468625599573842e-05, "epoch": 3.456, "percentage": 69.23, "elapsed_time": "9:17:25", "remaining_time": "4:07:44"} +{"current_steps": 271, "total_steps": 390, "loss": 0.7935, "lr": 1.0311636767603952e-05, "epoch": 3.4688, "percentage": 69.49, "elapsed_time": "9:19:31", "remaining_time": "4:05:41"} +{"current_steps": 272, "total_steps": 390, "loss": 0.7564, "lr": 1.0155424063052306e-05, "epoch": 3.4816, "percentage": 69.74, "elapsed_time": "9:21:34", "remaining_time": "4:03:37"} +{"current_steps": 273, "total_steps": 390, "loss": 0.753, "lr": 1.0000000000000006e-05, "epoch": 3.4944, "percentage": 70.0, "elapsed_time": "9:23:41", "remaining_time": "4:01:34"} +{"current_steps": 274, "total_steps": 390, "loss": 0.7325, "lr": 9.84537702935065e-06, "epoch": 3.5072, "percentage": 70.26, "elapsed_time": "9:25:45", "remaining_time": "3:59:30"} +{"current_steps": 275, "total_steps": 390, "loss": 0.7293, "lr": 9.691567537832964e-06, "epoch": 3.52, "percentage": 70.51, "elapsed_time": "9:27:52", "remaining_time": "3:57:28"} +{"current_steps": 276, "total_steps": 390, "loss": 0.7106, "lr": 9.538583847008452e-06, "epoch": 3.5328, "percentage": 70.77, "elapsed_time": "9:29:53", "remaining_time": "3:55:23"} +{"current_steps": 277, "total_steps": 390, "loss": 0.7289, "lr": 9.386438212284372e-06, "epoch": 3.5456, "percentage": 71.03, "elapsed_time": "9:31:47", "remaining_time": "3:53:15"} +{"current_steps": 278, "total_steps": 390, "loss": 0.7199, "lr": 9.235142821931928e-06, "epoch": 3.5584, "percentage": 71.28, "elapsed_time": "9:33:45", "remaining_time": "3:51:09"} +{"current_steps": 279, "total_steps": 390, "loss": 0.7905, "lr": 9.084709796109907e-06, "epoch": 3.5712, "percentage": 71.54, "elapsed_time": "9:35:58", "remaining_time": "3:49:09"} +{"current_steps": 280, "total_steps": 390, "loss": 0.7608, "lr": 8.93515118589373e-06, "epoch": 3.584, "percentage": 71.79, "elapsed_time": "9:38:08", "remaining_time": "3:47:07"} +{"current_steps": 281, "total_steps": 390, "loss": 0.7573, "lr": 8.786478972310023e-06, "epoch": 3.5968, "percentage": 72.05, "elapsed_time": "9:40:13", "remaining_time": "3:45:04"} +{"current_steps": 282, "total_steps": 390, "loss": 0.7468, "lr": 8.638705065376887e-06, "epoch": 3.6096, "percentage": 72.31, "elapsed_time": "9:42:20", "remaining_time": "3:43:01"} +{"current_steps": 283, "total_steps": 390, "loss": 0.7759, "lr": 8.491841303149728e-06, "epoch": 3.6224, "percentage": 72.56, "elapsed_time": "9:44:23", "remaining_time": "3:40:57"} +{"current_steps": 284, "total_steps": 390, "loss": 0.7509, "lr": 8.345899450772975e-06, "epoch": 3.6352, "percentage": 72.82, "elapsed_time": "9:46:38", "remaining_time": "3:38:57"} +{"current_steps": 285, "total_steps": 390, "loss": 0.7356, "lr": 8.200891199537549e-06, "epoch": 3.648, "percentage": 73.08, "elapsed_time": "9:48:31", "remaining_time": "3:36:49"} +{"current_steps": 286, "total_steps": 390, "loss": 0.7068, "lr": 8.056828165944282e-06, "epoch": 3.6608, "percentage": 73.33, "elapsed_time": "9:50:29", "remaining_time": "3:34:43"} +{"current_steps": 287, "total_steps": 390, "loss": 0.759, "lr": 7.913721890773354e-06, "epoch": 3.6736, "percentage": 73.59, "elapsed_time": "9:52:30", "remaining_time": "3:32:38"} +{"current_steps": 288, "total_steps": 390, "loss": 0.7596, "lr": 7.771583838159756e-06, "epoch": 3.6864, "percentage": 73.85, "elapsed_time": "9:54:37", "remaining_time": "3:30:35"} +{"current_steps": 289, "total_steps": 390, "loss": 0.7434, "lr": 7.630425394674903e-06, "epoch": 3.6992000000000003, "percentage": 74.1, "elapsed_time": "9:56:48", "remaining_time": "3:28:34"} +{"current_steps": 290, "total_steps": 390, "loss": 0.7631, "lr": 7.49025786841445e-06, "epoch": 3.7119999999999997, "percentage": 74.36, "elapsed_time": "9:58:45", "remaining_time": "3:26:28"} +{"current_steps": 291, "total_steps": 390, "loss": 0.7464, "lr": 7.3510924880924575e-06, "epoch": 3.7248, "percentage": 74.62, "elapsed_time": "10:00:57", "remaining_time": "3:24:26"} +{"current_steps": 292, "total_steps": 390, "loss": 0.7257, "lr": 7.212940402141808e-06, "epoch": 3.7376, "percentage": 74.87, "elapsed_time": "10:02:59", "remaining_time": "3:22:22"} +{"current_steps": 293, "total_steps": 390, "loss": 0.7306, "lr": 7.075812677821145e-06, "epoch": 3.7504, "percentage": 75.13, "elapsed_time": "10:05:03", "remaining_time": "3:20:18"} +{"current_steps": 294, "total_steps": 390, "loss": 0.7637, "lr": 6.939720300328303e-06, "epoch": 3.7632, "percentage": 75.38, "elapsed_time": "10:07:09", "remaining_time": "3:18:15"} +{"current_steps": 295, "total_steps": 390, "loss": 0.7364, "lr": 6.8046741719202385e-06, "epoch": 3.776, "percentage": 75.64, "elapsed_time": "10:09:09", "remaining_time": "3:16:10"} +{"current_steps": 296, "total_steps": 390, "loss": 0.7154, "lr": 6.67068511103971e-06, "epoch": 3.7888, "percentage": 75.9, "elapsed_time": "10:11:09", "remaining_time": "3:14:04"} +{"current_steps": 297, "total_steps": 390, "loss": 0.739, "lr": 6.537763851448593e-06, "epoch": 3.8016, "percentage": 76.15, "elapsed_time": "10:13:12", "remaining_time": "3:12:00"} +{"current_steps": 298, "total_steps": 390, "loss": 0.7404, "lr": 6.4059210413680175e-06, "epoch": 3.8144, "percentage": 76.41, "elapsed_time": "10:14:56", "remaining_time": "3:09:51"} +{"current_steps": 299, "total_steps": 390, "loss": 0.775, "lr": 6.275167242625331e-06, "epoch": 3.8272, "percentage": 76.67, "elapsed_time": "10:17:03", "remaining_time": "3:07:47"} +{"current_steps": 300, "total_steps": 390, "loss": 0.806, "lr": 6.145512929808013e-06, "epoch": 3.84, "percentage": 76.92, "elapsed_time": "10:19:21", "remaining_time": "3:05:48"} +{"current_steps": 301, "total_steps": 390, "loss": 0.7129, "lr": 6.016968489424572e-06, "epoch": 3.8528000000000002, "percentage": 77.18, "elapsed_time": "10:21:30", "remaining_time": "3:03:46"} +{"current_steps": 302, "total_steps": 390, "loss": 0.7298, "lr": 5.889544219072465e-06, "epoch": 3.8656, "percentage": 77.44, "elapsed_time": "10:23:29", "remaining_time": "3:01:40"} +{"current_steps": 303, "total_steps": 390, "loss": 0.7621, "lr": 5.7632503266131925e-06, "epoch": 3.8784, "percentage": 77.69, "elapsed_time": "10:25:33", "remaining_time": "2:59:36"} +{"current_steps": 304, "total_steps": 390, "loss": 0.7537, "lr": 5.638096929354522e-06, "epoch": 3.8912, "percentage": 77.95, "elapsed_time": "10:27:40", "remaining_time": "2:57:33"} +{"current_steps": 305, "total_steps": 390, "loss": 0.7452, "lr": 5.514094053240035e-06, "epoch": 3.904, "percentage": 78.21, "elapsed_time": "10:29:37", "remaining_time": "2:55:28"} +{"current_steps": 306, "total_steps": 390, "loss": 0.803, "lr": 5.39125163204594e-06, "epoch": 3.9168, "percentage": 78.46, "elapsed_time": "10:31:41", "remaining_time": "2:53:24"} +{"current_steps": 307, "total_steps": 390, "loss": 0.7645, "lr": 5.269579506585259e-06, "epoch": 3.9295999999999998, "percentage": 78.72, "elapsed_time": "10:33:50", "remaining_time": "2:51:21"} +{"current_steps": 308, "total_steps": 390, "loss": 0.7452, "lr": 5.149087423919541e-06, "epoch": 3.9424, "percentage": 78.97, "elapsed_time": "10:35:47", "remaining_time": "2:49:16"} +{"current_steps": 309, "total_steps": 390, "loss": 0.739, "lr": 5.029785036577976e-06, "epoch": 3.9552, "percentage": 79.23, "elapsed_time": "10:37:37", "remaining_time": "2:47:08"} +{"current_steps": 310, "total_steps": 390, "loss": 0.7621, "lr": 4.911681901784198e-06, "epoch": 3.968, "percentage": 79.49, "elapsed_time": "10:39:46", "remaining_time": "2:45:06"} +{"current_steps": 311, "total_steps": 390, "loss": 0.7688, "lr": 4.794787480690597e-06, "epoch": 3.9808, "percentage": 79.74, "elapsed_time": "10:41:48", "remaining_time": "2:43:01"} +{"current_steps": 312, "total_steps": 390, "loss": 0.7227, "lr": 4.679111137620442e-06, "epoch": 3.9936, "percentage": 80.0, "elapsed_time": "10:43:35", "remaining_time": "2:40:53"} +{"current_steps": 313, "total_steps": 390, "loss": 0.7252, "lr": 4.5646621393177e-06, "epoch": 4.0064, "percentage": 80.26, "elapsed_time": "10:46:27", "remaining_time": "2:39:02"} +{"current_steps": 314, "total_steps": 390, "loss": 0.6061, "lr": 4.451449654204685e-06, "epoch": 4.0192, "percentage": 80.51, "elapsed_time": "10:48:18", "remaining_time": "2:36:54"} +{"current_steps": 315, "total_steps": 390, "loss": 0.7034, "lr": 4.339482751647557e-06, "epoch": 4.032, "percentage": 80.77, "elapsed_time": "10:50:15", "remaining_time": "2:34:49"} +{"current_steps": 316, "total_steps": 390, "loss": 0.6067, "lr": 4.228770401229824e-06, "epoch": 4.0448, "percentage": 81.03, "elapsed_time": "10:52:16", "remaining_time": "2:32:44"} +{"current_steps": 317, "total_steps": 390, "loss": 0.6513, "lr": 4.119321472033779e-06, "epoch": 4.0576, "percentage": 81.28, "elapsed_time": "10:54:10", "remaining_time": "2:30:38"} +{"current_steps": 318, "total_steps": 390, "loss": 0.7156, "lr": 4.011144731929981e-06, "epoch": 4.0704, "percentage": 81.54, "elapsed_time": "10:56:06", "remaining_time": "2:28:33"} +{"current_steps": 319, "total_steps": 390, "loss": 0.6634, "lr": 3.904248846874894e-06, "epoch": 4.0832, "percentage": 81.79, "elapsed_time": "10:58:14", "remaining_time": "2:26:30"} +{"current_steps": 320, "total_steps": 390, "loss": 0.6652, "lr": 3.7986423802166705e-06, "epoch": 4.096, "percentage": 82.05, "elapsed_time": "11:00:22", "remaining_time": "2:24:27"} +{"current_steps": 321, "total_steps": 390, "loss": 0.6529, "lr": 3.694333792009115e-06, "epoch": 4.1088, "percentage": 82.31, "elapsed_time": "11:02:17", "remaining_time": "2:22:21"} +{"current_steps": 322, "total_steps": 390, "loss": 0.7027, "lr": 3.5913314383339937e-06, "epoch": 4.1216, "percentage": 82.56, "elapsed_time": "11:04:15", "remaining_time": "2:20:16"} +{"current_steps": 323, "total_steps": 390, "loss": 0.7221, "lr": 3.4896435706316e-06, "epoch": 4.1344, "percentage": 82.82, "elapsed_time": "11:06:20", "remaining_time": "2:18:13"} +{"current_steps": 324, "total_steps": 390, "loss": 0.7016, "lr": 3.3892783350397675e-06, "epoch": 4.1472, "percentage": 83.08, "elapsed_time": "11:08:27", "remaining_time": "2:16:09"} +{"current_steps": 325, "total_steps": 390, "loss": 0.6472, "lr": 3.290243771741275e-06, "epoch": 4.16, "percentage": 83.33, "elapsed_time": "11:10:13", "remaining_time": "2:14:02"} +{"current_steps": 326, "total_steps": 390, "loss": 0.7008, "lr": 3.1925478143197418e-06, "epoch": 4.1728, "percentage": 83.59, "elapsed_time": "11:12:26", "remaining_time": "2:12:00"} +{"current_steps": 327, "total_steps": 390, "loss": 0.693, "lr": 3.0961982891241083e-06, "epoch": 4.1856, "percentage": 83.85, "elapsed_time": "11:14:31", "remaining_time": "2:09:57"} +{"current_steps": 328, "total_steps": 390, "loss": 0.6633, "lr": 3.001202914641628e-06, "epoch": 4.1984, "percentage": 84.1, "elapsed_time": "11:16:47", "remaining_time": "2:07:55"} +{"current_steps": 329, "total_steps": 390, "loss": 0.6922, "lr": 2.907569300879596e-06, "epoch": 4.2112, "percentage": 84.36, "elapsed_time": "11:19:01", "remaining_time": "2:05:53"} +{"current_steps": 330, "total_steps": 390, "loss": 0.6372, "lr": 2.815304948755664e-06, "epoch": 4.224, "percentage": 84.62, "elapsed_time": "11:21:07", "remaining_time": "2:03:50"} +{"current_steps": 331, "total_steps": 390, "loss": 0.7109, "lr": 2.7244172494969978e-06, "epoch": 4.2368, "percentage": 84.87, "elapsed_time": "11:23:05", "remaining_time": "2:01:45"} +{"current_steps": 332, "total_steps": 390, "loss": 0.677, "lr": 2.6349134840481294e-06, "epoch": 4.2496, "percentage": 85.13, "elapsed_time": "11:25:01", "remaining_time": "1:59:40"} +{"current_steps": 333, "total_steps": 390, "loss": 0.677, "lr": 2.546800822487714e-06, "epoch": 4.2624, "percentage": 85.38, "elapsed_time": "11:26:59", "remaining_time": "1:57:35"} +{"current_steps": 334, "total_steps": 390, "loss": 0.67, "lr": 2.4600863234541338e-06, "epoch": 4.2752, "percentage": 85.64, "elapsed_time": "11:28:56", "remaining_time": "1:55:30"} +{"current_steps": 335, "total_steps": 390, "loss": 0.6799, "lr": 2.374776933580025e-06, "epoch": 4.288, "percentage": 85.9, "elapsed_time": "11:30:53", "remaining_time": "1:53:25"} +{"current_steps": 336, "total_steps": 390, "loss": 0.6442, "lr": 2.2908794869358044e-06, "epoch": 4.3008, "percentage": 86.15, "elapsed_time": "11:33:00", "remaining_time": "1:51:22"} +{"current_steps": 337, "total_steps": 390, "loss": 0.6758, "lr": 2.2084007044821764e-06, "epoch": 4.3136, "percentage": 86.41, "elapsed_time": "11:35:03", "remaining_time": "1:49:18"} +{"current_steps": 338, "total_steps": 390, "loss": 0.6838, "lr": 2.127347193531757e-06, "epoch": 4.3264, "percentage": 86.67, "elapsed_time": "11:37:16", "remaining_time": "1:47:16"} +{"current_steps": 339, "total_steps": 390, "loss": 0.6978, "lr": 2.0477254472197237e-06, "epoch": 4.3392, "percentage": 86.92, "elapsed_time": "11:39:14", "remaining_time": "1:45:11"} +{"current_steps": 340, "total_steps": 390, "loss": 0.6465, "lr": 1.96954184398368e-06, "epoch": 4.352, "percentage": 87.18, "elapsed_time": "11:40:59", "remaining_time": "1:43:05"} +{"current_steps": 341, "total_steps": 390, "loss": 0.6143, "lr": 1.8928026470526917e-06, "epoch": 4.3648, "percentage": 87.44, "elapsed_time": "11:42:47", "remaining_time": "1:40:59"} +{"current_steps": 342, "total_steps": 390, "loss": 0.6868, "lr": 1.817514003945524e-06, "epoch": 4.3776, "percentage": 87.69, "elapsed_time": "11:44:56", "remaining_time": "1:38:56"} +{"current_steps": 343, "total_steps": 390, "loss": 0.6901, "lr": 1.743681945978184e-06, "epoch": 4.3904, "percentage": 87.95, "elapsed_time": "11:46:56", "remaining_time": "1:36:52"} +{"current_steps": 344, "total_steps": 390, "loss": 0.6339, "lr": 1.6713123877807413e-06, "epoch": 4.4032, "percentage": 88.21, "elapsed_time": "11:48:58", "remaining_time": "1:34:48"} +{"current_steps": 345, "total_steps": 390, "loss": 0.682, "lr": 1.6004111268235156e-06, "epoch": 4.416, "percentage": 88.46, "elapsed_time": "11:50:58", "remaining_time": "1:32:44"} +{"current_steps": 346, "total_steps": 390, "loss": 0.7029, "lr": 1.5309838429526714e-06, "epoch": 4.4288, "percentage": 88.72, "elapsed_time": "11:53:02", "remaining_time": "1:30:40"} +{"current_steps": 347, "total_steps": 390, "loss": 0.6667, "lr": 1.4630360979351644e-06, "epoch": 4.4416, "percentage": 88.97, "elapsed_time": "11:55:02", "remaining_time": "1:28:36"} +{"current_steps": 348, "total_steps": 390, "loss": 0.7034, "lr": 1.396573335013236e-06, "epoch": 4.4544, "percentage": 89.23, "elapsed_time": "11:57:03", "remaining_time": "1:26:32"} +{"current_steps": 349, "total_steps": 390, "loss": 0.6817, "lr": 1.3316008784683265e-06, "epoch": 4.4672, "percentage": 89.49, "elapsed_time": "11:59:10", "remaining_time": "1:24:29"} +{"current_steps": 350, "total_steps": 390, "loss": 0.6848, "lr": 1.2681239331945695e-06, "epoch": 4.48, "percentage": 89.74, "elapsed_time": "12:01:25", "remaining_time": "1:22:26"} +{"current_steps": 351, "total_steps": 390, "loss": 0.7368, "lr": 1.2061475842818337e-06, "epoch": 4.4928, "percentage": 90.0, "elapsed_time": "12:03:29", "remaining_time": "1:20:23"} +{"current_steps": 352, "total_steps": 390, "loss": 0.6892, "lr": 1.1456767966083393e-06, "epoch": 4.5056, "percentage": 90.26, "elapsed_time": "12:05:40", "remaining_time": "1:18:20"} +{"current_steps": 353, "total_steps": 390, "loss": 0.684, "lr": 1.086716414442952e-06, "epoch": 4.5184, "percentage": 90.51, "elapsed_time": "12:07:42", "remaining_time": "1:16:16"} +{"current_steps": 354, "total_steps": 390, "loss": 0.7055, "lr": 1.0292711610570904e-06, "epoch": 4.5312, "percentage": 90.77, "elapsed_time": "12:09:56", "remaining_time": "1:14:13"} +{"current_steps": 355, "total_steps": 390, "loss": 0.5981, "lr": 9.733456383463658e-07, "epoch": 4.5440000000000005, "percentage": 91.03, "elapsed_time": "12:11:56", "remaining_time": "1:12:09"} +{"current_steps": 356, "total_steps": 390, "loss": 0.7119, "lr": 9.189443264619102e-07, "epoch": 4.5568, "percentage": 91.28, "elapsed_time": "12:14:08", "remaining_time": "1:10:06"} +{"current_steps": 357, "total_steps": 390, "loss": 0.6717, "lr": 8.660715834514977e-07, "epoch": 4.5696, "percentage": 91.54, "elapsed_time": "12:16:17", "remaining_time": "1:08:03"} +{"current_steps": 358, "total_steps": 390, "loss": 0.646, "lr": 8.147316449103959e-07, "epoch": 4.5824, "percentage": 91.79, "elapsed_time": "12:18:22", "remaining_time": "1:06:00"} +{"current_steps": 359, "total_steps": 390, "loss": 0.6589, "lr": 7.649286236420806e-07, "epoch": 4.5952, "percentage": 92.05, "elapsed_time": "12:20:20", "remaining_time": "1:03:55"} +{"current_steps": 360, "total_steps": 390, "loss": 0.7039, "lr": 7.166665093287539e-07, "epoch": 4.608, "percentage": 92.31, "elapsed_time": "12:22:24", "remaining_time": "1:01:52"} +{"current_steps": 361, "total_steps": 390, "loss": 0.7086, "lr": 6.69949168211721e-07, "epoch": 4.6208, "percentage": 92.56, "elapsed_time": "12:24:44", "remaining_time": "0:59:49"} +{"current_steps": 362, "total_steps": 390, "loss": 0.6299, "lr": 6.247803427816945e-07, "epoch": 4.6336, "percentage": 92.82, "elapsed_time": "12:26:52", "remaining_time": "0:57:46"} +{"current_steps": 363, "total_steps": 390, "loss": 0.7068, "lr": 5.811636514789598e-07, "epoch": 4.6464, "percentage": 93.08, "elapsed_time": "12:29:04", "remaining_time": "0:55:42"} +{"current_steps": 364, "total_steps": 390, "loss": 0.674, "lr": 5.391025884035239e-07, "epoch": 4.6592, "percentage": 93.33, "elapsed_time": "12:31:07", "remaining_time": "0:53:39"} +{"current_steps": 365, "total_steps": 390, "loss": 0.7265, "lr": 4.986005230351954e-07, "epoch": 4.672, "percentage": 93.59, "elapsed_time": "12:33:10", "remaining_time": "0:51:35"} +{"current_steps": 366, "total_steps": 390, "loss": 0.7612, "lr": 4.5966069996365993e-07, "epoch": 4.6848, "percentage": 93.85, "elapsed_time": "12:35:20", "remaining_time": "0:49:31"} +{"current_steps": 367, "total_steps": 390, "loss": 0.6638, "lr": 4.22286238628562e-07, "epoch": 4.6975999999999996, "percentage": 94.1, "elapsed_time": "12:37:24", "remaining_time": "0:47:28"} +{"current_steps": 368, "total_steps": 390, "loss": 0.6798, "lr": 3.8648013306960664e-07, "epoch": 4.7104, "percentage": 94.36, "elapsed_time": "12:39:37", "remaining_time": "0:45:24"} +{"current_steps": 369, "total_steps": 390, "loss": 0.6936, "lr": 3.522452516867048e-07, "epoch": 4.7232, "percentage": 94.62, "elapsed_time": "12:41:44", "remaining_time": "0:43:21"} +{"current_steps": 370, "total_steps": 390, "loss": 0.6592, "lr": 3.1958433701019697e-07, "epoch": 4.736, "percentage": 94.87, "elapsed_time": "12:43:42", "remaining_time": "0:41:16"} +{"current_steps": 371, "total_steps": 390, "loss": 0.6883, "lr": 2.8850000548115155e-07, "epoch": 4.7488, "percentage": 95.13, "elapsed_time": "12:45:44", "remaining_time": "0:39:12"} +{"current_steps": 372, "total_steps": 390, "loss": 0.6762, "lr": 2.5899474724174313e-07, "epoch": 4.7616, "percentage": 95.38, "elapsed_time": "12:47:41", "remaining_time": "0:37:08"} +{"current_steps": 373, "total_steps": 390, "loss": 0.6383, "lr": 2.3107092593579905e-07, "epoch": 4.7744, "percentage": 95.64, "elapsed_time": "12:49:43", "remaining_time": "0:35:04"} +{"current_steps": 374, "total_steps": 390, "loss": 0.6458, "lr": 2.0473077851942858e-07, "epoch": 4.7872, "percentage": 95.9, "elapsed_time": "12:51:51", "remaining_time": "0:33:01"} +{"current_steps": 375, "total_steps": 390, "loss": 0.6113, "lr": 1.799764150818306e-07, "epoch": 4.8, "percentage": 96.15, "elapsed_time": "12:53:51", "remaining_time": "0:30:57"} +{"current_steps": 376, "total_steps": 390, "loss": 0.6758, "lr": 1.5680981867625566e-07, "epoch": 4.8128, "percentage": 96.41, "elapsed_time": "12:56:03", "remaining_time": "0:28:53"} +{"current_steps": 377, "total_steps": 390, "loss": 0.6966, "lr": 1.3523284516113955e-07, "epoch": 4.8256, "percentage": 96.67, "elapsed_time": "12:58:00", "remaining_time": "0:26:49"} +{"current_steps": 378, "total_steps": 390, "loss": 0.7033, "lr": 1.1524722305144231e-07, "epoch": 4.8384, "percentage": 96.92, "elapsed_time": "13:00:05", "remaining_time": "0:24:45"} +{"current_steps": 379, "total_steps": 390, "loss": 0.6582, "lr": 9.685455338016347e-08, "epoch": 4.8512, "percentage": 97.18, "elapsed_time": "13:02:03", "remaining_time": "0:22:41"} +{"current_steps": 380, "total_steps": 390, "loss": 0.6699, "lr": 8.005630957010014e-08, "epoch": 4.864, "percentage": 97.44, "elapsed_time": "13:04:06", "remaining_time": "0:20:38"} +{"current_steps": 381, "total_steps": 390, "loss": 0.6217, "lr": 6.485383731580142e-08, "epoch": 4.8768, "percentage": 97.69, "elapsed_time": "13:05:51", "remaining_time": "0:18:33"} +{"current_steps": 382, "total_steps": 390, "loss": 0.6765, "lr": 5.1248354475768034e-08, "epoch": 4.8896, "percentage": 97.95, "elapsed_time": "13:07:48", "remaining_time": "0:16:29"} +{"current_steps": 383, "total_steps": 390, "loss": 0.7327, "lr": 3.924095097489922e-08, "epoch": 4.9024, "percentage": 98.21, "elapsed_time": "13:10:11", "remaining_time": "0:14:26"} +{"current_steps": 384, "total_steps": 390, "loss": 0.6233, "lr": 2.8832588717164766e-08, "epoch": 4.9152000000000005, "percentage": 98.46, "elapsed_time": "13:12:10", "remaining_time": "0:12:22"} +{"current_steps": 385, "total_steps": 390, "loss": 0.6435, "lr": 2.0024101508555604e-08, "epoch": 4.928, "percentage": 98.72, "elapsed_time": "13:14:08", "remaining_time": "0:10:18"} +{"current_steps": 386, "total_steps": 390, "loss": 0.7127, "lr": 1.281619499029274e-08, "epoch": 4.9408, "percentage": 98.97, "elapsed_time": "13:16:01", "remaining_time": "0:08:14"} +{"current_steps": 387, "total_steps": 390, "loss": 0.708, "lr": 7.209446582292501e-09, "epoch": 4.9536, "percentage": 99.23, "elapsed_time": "13:17:58", "remaining_time": "0:06:11"} +{"current_steps": 388, "total_steps": 390, "loss": 0.7203, "lr": 3.2043054369057523e-09, "epoch": 4.9664, "percentage": 99.49, "elapsed_time": "13:20:00", "remaining_time": "0:04:07"} +{"current_steps": 389, "total_steps": 390, "loss": 0.6833, "lr": 8.010924029533406e-10, "epoch": 4.9792, "percentage": 99.74, "elapsed_time": "13:22:08", "remaining_time": "0:02:03"} +{"current_steps": 390, "total_steps": 390, "loss": 0.7082, "lr": 0.0, "epoch": 4.992, "percentage": 100.0, "elapsed_time": "13:24:15", "remaining_time": "0:00:00"} +{"current_steps": 390, "total_steps": 390, "epoch": 4.992, "percentage": 100.0, "elapsed_time": "13:26:18", "remaining_time": "0:00:00"} diff --git a/trainer_state.json b/trainer_state.json new file mode 100644 index 0000000..941ed5d --- /dev/null +++ b/trainer_state.json @@ -0,0 +1,2772 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 4.992, + "eval_steps": 500, + "global_step": 390, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0128, + "grad_norm": 7.692362944768503, + "learning_rate": 1.0256410256410257e-06, + "loss": 1.5558, + "step": 1 + }, + { + "epoch": 0.0256, + "grad_norm": 7.649452387526613, + "learning_rate": 2.0512820512820513e-06, + "loss": 1.5299, + "step": 2 + }, + { + "epoch": 0.0384, + "grad_norm": 7.671202171277273, + "learning_rate": 3.0769230769230774e-06, + "loss": 1.5814, + "step": 3 + }, + { + "epoch": 0.0512, + "grad_norm": 7.036877104775377, + "learning_rate": 4.102564102564103e-06, + "loss": 1.54, + "step": 4 + }, + { + "epoch": 0.064, + "grad_norm": 5.292988182086679, + "learning_rate": 5.128205128205128e-06, + "loss": 1.508, + "step": 5 + }, + { + "epoch": 0.0768, + "grad_norm": 2.9047254740447, + "learning_rate": 6.153846153846155e-06, + "loss": 1.4687, + "step": 6 + }, + { + "epoch": 0.0896, + "grad_norm": 2.5469693991424136, + "learning_rate": 7.17948717948718e-06, + "loss": 1.4354, + "step": 7 + }, + { + "epoch": 0.1024, + "grad_norm": 5.3394378940218505, + "learning_rate": 8.205128205128205e-06, + "loss": 1.448, + "step": 8 + }, + { + "epoch": 0.1152, + "grad_norm": 5.237578063138974, + "learning_rate": 9.230769230769232e-06, + "loss": 1.4113, + "step": 9 + }, + { + "epoch": 0.128, + "grad_norm": 4.878229367796371, + "learning_rate": 1.0256410256410256e-05, + "loss": 1.3674, + "step": 10 + }, + { + "epoch": 0.1408, + "grad_norm": 4.389136620576146, + "learning_rate": 1.1282051282051283e-05, + "loss": 1.3963, + "step": 11 + }, + { + "epoch": 0.1536, + "grad_norm": 3.5209608092779057, + "learning_rate": 1.230769230769231e-05, + "loss": 1.3873, + "step": 12 + }, + { + "epoch": 0.1664, + "grad_norm": 2.556831853477579, + "learning_rate": 1.3333333333333333e-05, + "loss": 1.3816, + "step": 13 + }, + { + "epoch": 0.1792, + "grad_norm": 1.9791181807597111, + "learning_rate": 1.435897435897436e-05, + "loss": 1.2973, + "step": 14 + }, + { + "epoch": 0.192, + "grad_norm": 2.0496832639611804, + "learning_rate": 1.5384615384615387e-05, + "loss": 1.3467, + "step": 15 + }, + { + "epoch": 0.2048, + "grad_norm": 1.846599835683718, + "learning_rate": 1.641025641025641e-05, + "loss": 1.281, + "step": 16 + }, + { + "epoch": 0.2176, + "grad_norm": 1.2550930412415549, + "learning_rate": 1.7435897435897438e-05, + "loss": 1.246, + "step": 17 + }, + { + "epoch": 0.2304, + "grad_norm": 1.3283067811292284, + "learning_rate": 1.8461538461538465e-05, + "loss": 1.2626, + "step": 18 + }, + { + "epoch": 0.2432, + "grad_norm": 39.870803667289174, + "learning_rate": 1.9487179487179488e-05, + "loss": 1.2497, + "step": 19 + }, + { + "epoch": 0.256, + "grad_norm": 2.5286555965354727, + "learning_rate": 2.0512820512820512e-05, + "loss": 1.2911, + "step": 20 + }, + { + "epoch": 0.2688, + "grad_norm": 1.714418881557214, + "learning_rate": 2.153846153846154e-05, + "loss": 1.2629, + "step": 21 + }, + { + "epoch": 0.2816, + "grad_norm": 1.7498893430574376, + "learning_rate": 2.2564102564102566e-05, + "loss": 1.2377, + "step": 22 + }, + { + "epoch": 0.2944, + "grad_norm": 1.3309715455897657, + "learning_rate": 2.3589743589743593e-05, + "loss": 1.2138, + "step": 23 + }, + { + "epoch": 0.3072, + "grad_norm": 1.52541650624061, + "learning_rate": 2.461538461538462e-05, + "loss": 1.2404, + "step": 24 + }, + { + "epoch": 0.32, + "grad_norm": 1.2104236338613845, + "learning_rate": 2.5641025641025646e-05, + "loss": 1.2288, + "step": 25 + }, + { + "epoch": 0.3328, + "grad_norm": 1.3973043387015034, + "learning_rate": 2.6666666666666667e-05, + "loss": 1.2305, + "step": 26 + }, + { + "epoch": 0.3456, + "grad_norm": 1.1078267886615953, + "learning_rate": 2.7692307692307694e-05, + "loss": 1.2068, + "step": 27 + }, + { + "epoch": 0.3584, + "grad_norm": 1.026639796736863, + "learning_rate": 2.871794871794872e-05, + "loss": 1.2025, + "step": 28 + }, + { + "epoch": 0.3712, + "grad_norm": 0.9799675004987618, + "learning_rate": 2.9743589743589747e-05, + "loss": 1.2084, + "step": 29 + }, + { + "epoch": 0.384, + "grad_norm": 0.9046839423459286, + "learning_rate": 3.0769230769230774e-05, + "loss": 1.1879, + "step": 30 + }, + { + "epoch": 0.3968, + "grad_norm": 1.1989336642506447, + "learning_rate": 3.1794871794871795e-05, + "loss": 1.1922, + "step": 31 + }, + { + "epoch": 0.4096, + "grad_norm": 1.0124085415657604, + "learning_rate": 3.282051282051282e-05, + "loss": 1.1835, + "step": 32 + }, + { + "epoch": 0.4224, + "grad_norm": 0.9033624835929998, + "learning_rate": 3.384615384615385e-05, + "loss": 1.1759, + "step": 33 + }, + { + "epoch": 0.4352, + "grad_norm": 1.2517048919372702, + "learning_rate": 3.4871794871794875e-05, + "loss": 1.1863, + "step": 34 + }, + { + "epoch": 0.448, + "grad_norm": 0.9796274817199719, + "learning_rate": 3.58974358974359e-05, + "loss": 1.2153, + "step": 35 + }, + { + "epoch": 0.4608, + "grad_norm": 1.0512758150854558, + "learning_rate": 3.692307692307693e-05, + "loss": 1.1459, + "step": 36 + }, + { + "epoch": 0.4736, + "grad_norm": 1.1258623830729644, + "learning_rate": 3.794871794871795e-05, + "loss": 1.1484, + "step": 37 + }, + { + "epoch": 0.4864, + "grad_norm": 1.0547902344575502, + "learning_rate": 3.8974358974358976e-05, + "loss": 1.1469, + "step": 38 + }, + { + "epoch": 0.4992, + "grad_norm": 0.9916194724908646, + "learning_rate": 4e-05, + "loss": 1.1893, + "step": 39 + }, + { + "epoch": 0.512, + "grad_norm": 1.3302384012766393, + "learning_rate": 3.9999198907597046e-05, + "loss": 1.15, + "step": 40 + }, + { + "epoch": 0.5248, + "grad_norm": 1.963593689910703, + "learning_rate": 3.9996795694563096e-05, + "loss": 1.1328, + "step": 41 + }, + { + "epoch": 0.5376, + "grad_norm": 1.1715690222051025, + "learning_rate": 3.999279055341771e-05, + "loss": 1.1853, + "step": 42 + }, + { + "epoch": 0.5504, + "grad_norm": 2.705845620833423, + "learning_rate": 3.998718380500971e-05, + "loss": 1.1834, + "step": 43 + }, + { + "epoch": 0.5632, + "grad_norm": 1.9066020723868575, + "learning_rate": 3.997997589849145e-05, + "loss": 1.1458, + "step": 44 + }, + { + "epoch": 0.576, + "grad_norm": 2.423499618492123, + "learning_rate": 3.9971167411282835e-05, + "loss": 1.1943, + "step": 45 + }, + { + "epoch": 0.5888, + "grad_norm": 1.7171312136021033, + "learning_rate": 3.99607590490251e-05, + "loss": 1.1983, + "step": 46 + }, + { + "epoch": 0.6016, + "grad_norm": 1.6842292096597014, + "learning_rate": 3.9948751645524235e-05, + "loss": 1.1626, + "step": 47 + }, + { + "epoch": 0.6144, + "grad_norm": 1.7529623346658405, + "learning_rate": 3.9935146162684206e-05, + "loss": 1.1529, + "step": 48 + }, + { + "epoch": 0.6272, + "grad_norm": 1.5913373949703382, + "learning_rate": 3.9919943690429906e-05, + "loss": 1.1494, + "step": 49 + }, + { + "epoch": 0.64, + "grad_norm": 1.6507604461840728, + "learning_rate": 3.9903145446619837e-05, + "loss": 1.157, + "step": 50 + }, + { + "epoch": 0.6528, + "grad_norm": 1.5140962844534174, + "learning_rate": 3.9884752776948564e-05, + "loss": 1.1729, + "step": 51 + }, + { + "epoch": 0.6656, + "grad_norm": 1.4554166804065727, + "learning_rate": 3.9864767154838864e-05, + "loss": 1.1861, + "step": 52 + }, + { + "epoch": 0.6784, + "grad_norm": 1.4204636015581693, + "learning_rate": 3.9843190181323744e-05, + "loss": 1.1113, + "step": 53 + }, + { + "epoch": 0.6912, + "grad_norm": 1.2192992190178875, + "learning_rate": 3.982002358491817e-05, + "loss": 1.149, + "step": 54 + }, + { + "epoch": 0.704, + "grad_norm": 1.356919138180013, + "learning_rate": 3.979526922148058e-05, + "loss": 1.1464, + "step": 55 + }, + { + "epoch": 0.7168, + "grad_norm": 1.1783179174778675, + "learning_rate": 3.9768929074064206e-05, + "loss": 1.1468, + "step": 56 + }, + { + "epoch": 0.7296, + "grad_norm": 1.520213069204608, + "learning_rate": 3.9741005252758255e-05, + "loss": 1.1694, + "step": 57 + }, + { + "epoch": 0.7424, + "grad_norm": 1.0871527275379298, + "learning_rate": 3.971149999451886e-05, + "loss": 1.1939, + "step": 58 + }, + { + "epoch": 0.7552, + "grad_norm": 1.3271862854340502, + "learning_rate": 3.9680415662989806e-05, + "loss": 1.1963, + "step": 59 + }, + { + "epoch": 0.768, + "grad_norm": 1.1360261466381845, + "learning_rate": 3.9647754748313294e-05, + "loss": 1.1659, + "step": 60 + }, + { + "epoch": 0.7808, + "grad_norm": 1.0465126532970044, + "learning_rate": 3.96135198669304e-05, + "loss": 1.135, + "step": 61 + }, + { + "epoch": 0.7936, + "grad_norm": 1.104046357543538, + "learning_rate": 3.957771376137144e-05, + "loss": 1.1045, + "step": 62 + }, + { + "epoch": 0.8064, + "grad_norm": 1.0076419389768252, + "learning_rate": 3.954033930003634e-05, + "loss": 1.1306, + "step": 63 + }, + { + "epoch": 0.8192, + "grad_norm": 1.1595281316865143, + "learning_rate": 3.9501399476964806e-05, + "loss": 1.1248, + "step": 64 + }, + { + "epoch": 0.832, + "grad_norm": 0.8082273276318717, + "learning_rate": 3.946089741159648e-05, + "loss": 1.1091, + "step": 65 + }, + { + "epoch": 0.8448, + "grad_norm": 1.1783712398913984, + "learning_rate": 3.9418836348521045e-05, + "loss": 1.1273, + "step": 66 + }, + { + "epoch": 0.8576, + "grad_norm": 1.0881445998587171, + "learning_rate": 3.937521965721831e-05, + "loss": 1.1285, + "step": 67 + }, + { + "epoch": 0.8704, + "grad_norm": 1.068066620388015, + "learning_rate": 3.933005083178828e-05, + "loss": 1.1028, + "step": 68 + }, + { + "epoch": 0.8832, + "grad_norm": 0.9707816485302323, + "learning_rate": 3.928333349067125e-05, + "loss": 1.139, + "step": 69 + }, + { + "epoch": 0.896, + "grad_norm": 1.213728444765552, + "learning_rate": 3.923507137635792e-05, + "loss": 1.1002, + "step": 70 + }, + { + "epoch": 0.9088, + "grad_norm": 0.8551346906494776, + "learning_rate": 3.9185268355089606e-05, + "loss": 1.1475, + "step": 71 + }, + { + "epoch": 0.9216, + "grad_norm": 0.9204857406831569, + "learning_rate": 3.913392841654851e-05, + "loss": 1.141, + "step": 72 + }, + { + "epoch": 0.9344, + "grad_norm": 0.7091199038237178, + "learning_rate": 3.9081055673538093e-05, + "loss": 1.1598, + "step": 73 + }, + { + "epoch": 0.9472, + "grad_norm": 0.7199232905668526, + "learning_rate": 3.902665436165364e-05, + "loss": 1.1478, + "step": 74 + }, + { + "epoch": 0.96, + "grad_norm": 0.7892379678981329, + "learning_rate": 3.897072883894291e-05, + "loss": 1.0939, + "step": 75 + }, + { + "epoch": 0.9728, + "grad_norm": 0.6539783456455385, + "learning_rate": 3.8913283585557054e-05, + "loss": 1.1523, + "step": 76 + }, + { + "epoch": 0.9856, + "grad_norm": 1.1995844140662193, + "learning_rate": 3.885432320339167e-05, + "loss": 1.1584, + "step": 77 + }, + { + "epoch": 0.9984, + "grad_norm": 0.7584414357624537, + "learning_rate": 3.879385241571817e-05, + "loss": 1.1579, + "step": 78 + }, + { + "epoch": 1.0112, + "grad_norm": 0.9838022924748918, + "learning_rate": 3.873187606680543e-05, + "loss": 1.0571, + "step": 79 + }, + { + "epoch": 1.024, + "grad_norm": 0.7417507430304172, + "learning_rate": 3.866839912153168e-05, + "loss": 1.0308, + "step": 80 + }, + { + "epoch": 1.0368, + "grad_norm": 0.7466250162315038, + "learning_rate": 3.860342666498677e-05, + "loss": 1.0528, + "step": 81 + }, + { + "epoch": 1.0496, + "grad_norm": 0.9225979437233178, + "learning_rate": 3.853696390206484e-05, + "loss": 1.0203, + "step": 82 + }, + { + "epoch": 1.0624, + "grad_norm": 0.948559988635711, + "learning_rate": 3.846901615704734e-05, + "loss": 1.0205, + "step": 83 + }, + { + "epoch": 1.0752, + "grad_norm": 0.7814874004462734, + "learning_rate": 3.839958887317649e-05, + "loss": 1.0338, + "step": 84 + }, + { + "epoch": 1.088, + "grad_norm": 1.0628469023322726, + "learning_rate": 3.832868761221926e-05, + "loss": 1.0165, + "step": 85 + }, + { + "epoch": 1.1008, + "grad_norm": 0.8615739732498551, + "learning_rate": 3.825631805402182e-05, + "loss": 1.0115, + "step": 86 + }, + { + "epoch": 1.1136, + "grad_norm": 1.060468292175149, + "learning_rate": 3.818248599605448e-05, + "loss": 1.0427, + "step": 87 + }, + { + "epoch": 1.1264, + "grad_norm": 0.7379667374485601, + "learning_rate": 3.810719735294731e-05, + "loss": 1.0209, + "step": 88 + }, + { + "epoch": 1.1392, + "grad_norm": 0.9750295810079974, + "learning_rate": 3.8030458156016326e-05, + "loss": 1.0251, + "step": 89 + }, + { + "epoch": 1.152, + "grad_norm": 0.7206293262576626, + "learning_rate": 3.795227455278029e-05, + "loss": 1.0148, + "step": 90 + }, + { + "epoch": 1.1648, + "grad_norm": 0.6855434098356388, + "learning_rate": 3.787265280646825e-05, + "loss": 1.0425, + "step": 91 + }, + { + "epoch": 1.1776, + "grad_norm": 0.7383257680403411, + "learning_rate": 3.7791599295517825e-05, + "loss": 1.0261, + "step": 92 + }, + { + "epoch": 1.1904, + "grad_norm": 0.6653630981167292, + "learning_rate": 3.7709120513064196e-05, + "loss": 1.0227, + "step": 93 + }, + { + "epoch": 1.2032, + "grad_norm": 0.7475014250369564, + "learning_rate": 3.762522306641998e-05, + "loss": 1.0252, + "step": 94 + }, + { + "epoch": 1.216, + "grad_norm": 0.7639763136720108, + "learning_rate": 3.7539913676545874e-05, + "loss": 1.0313, + "step": 95 + }, + { + "epoch": 1.2288000000000001, + "grad_norm": 0.8071040559697056, + "learning_rate": 3.745319917751229e-05, + "loss": 1.031, + "step": 96 + }, + { + "epoch": 1.2416, + "grad_norm": 0.8100115595913084, + "learning_rate": 3.736508651595188e-05, + "loss": 1.0342, + "step": 97 + }, + { + "epoch": 1.2544, + "grad_norm": 0.8707679082472297, + "learning_rate": 3.727558275050301e-05, + "loss": 1.0101, + "step": 98 + }, + { + "epoch": 1.2671999999999999, + "grad_norm": 0.7153434835330477, + "learning_rate": 3.718469505124434e-05, + "loss": 1.0489, + "step": 99 + }, + { + "epoch": 1.28, + "grad_norm": 1.0870536021354325, + "learning_rate": 3.709243069912041e-05, + "loss": 1.022, + "step": 100 + }, + { + "epoch": 1.2928, + "grad_norm": 0.7019182618113695, + "learning_rate": 3.699879708535838e-05, + "loss": 1.0637, + "step": 101 + }, + { + "epoch": 1.3056, + "grad_norm": 1.1038428470341881, + "learning_rate": 3.69038017108759e-05, + "loss": 1.0546, + "step": 102 + }, + { + "epoch": 1.3184, + "grad_norm": 0.7627783095736863, + "learning_rate": 3.680745218568026e-05, + "loss": 1.0747, + "step": 103 + }, + { + "epoch": 1.3312, + "grad_norm": 0.8547971875954213, + "learning_rate": 3.6709756228258735e-05, + "loss": 1.0375, + "step": 104 + }, + { + "epoch": 1.3439999999999999, + "grad_norm": 0.6853435289526536, + "learning_rate": 3.6610721664960236e-05, + "loss": 1.0611, + "step": 105 + }, + { + "epoch": 1.3568, + "grad_norm": 0.7396875892641765, + "learning_rate": 3.65103564293684e-05, + "loss": 1.0217, + "step": 106 + }, + { + "epoch": 1.3696, + "grad_norm": 0.7146716921415344, + "learning_rate": 3.640866856166601e-05, + "loss": 1.0274, + "step": 107 + }, + { + "epoch": 1.3824, + "grad_norm": 0.6443857661088517, + "learning_rate": 3.6305666207990886e-05, + "loss": 1.0363, + "step": 108 + }, + { + "epoch": 1.3952, + "grad_norm": 0.7944296996171112, + "learning_rate": 3.6201357619783336e-05, + "loss": 1.0105, + "step": 109 + }, + { + "epoch": 1.408, + "grad_norm": 0.7727329978152716, + "learning_rate": 3.609575115312511e-05, + "loss": 1.0696, + "step": 110 + }, + { + "epoch": 1.4208, + "grad_norm": 0.725530680479781, + "learning_rate": 3.598885526807003e-05, + "loss": 1.0446, + "step": 111 + }, + { + "epoch": 1.4336, + "grad_norm": 0.8330011282670016, + "learning_rate": 3.5880678527966224e-05, + "loss": 1.059, + "step": 112 + }, + { + "epoch": 1.4464000000000001, + "grad_norm": 0.6869528205827169, + "learning_rate": 3.577122959877017e-05, + "loss": 1.0335, + "step": 113 + }, + { + "epoch": 1.4592, + "grad_norm": 0.8217643443783395, + "learning_rate": 3.566051724835245e-05, + "loss": 1.065, + "step": 114 + }, + { + "epoch": 1.472, + "grad_norm": 0.6722402567252438, + "learning_rate": 3.554855034579532e-05, + "loss": 1.006, + "step": 115 + }, + { + "epoch": 1.4848, + "grad_norm": 0.6930068885172014, + "learning_rate": 3.5435337860682304e-05, + "loss": 1.0279, + "step": 116 + }, + { + "epoch": 1.4976, + "grad_norm": 0.7143189571312937, + "learning_rate": 3.532088886237956e-05, + "loss": 1.0442, + "step": 117 + }, + { + "epoch": 1.5104, + "grad_norm": 0.7110452324914206, + "learning_rate": 3.520521251930941e-05, + "loss": 1.0209, + "step": 118 + }, + { + "epoch": 1.5232, + "grad_norm": 0.5656132958430365, + "learning_rate": 3.5088318098215805e-05, + "loss": 1.0614, + "step": 119 + }, + { + "epoch": 1.536, + "grad_norm": 0.6375980220575151, + "learning_rate": 3.497021496342203e-05, + "loss": 1.0298, + "step": 120 + }, + { + "epoch": 1.5488, + "grad_norm": 0.6237522040232807, + "learning_rate": 3.485091257608047e-05, + "loss": 1.0221, + "step": 121 + }, + { + "epoch": 1.5615999999999999, + "grad_norm": 0.7275575334218716, + "learning_rate": 3.473042049341474e-05, + "loss": 0.9958, + "step": 122 + }, + { + "epoch": 1.5744, + "grad_norm": 0.5772814699418052, + "learning_rate": 3.4608748367954064e-05, + "loss": 1.042, + "step": 123 + }, + { + "epoch": 1.5872000000000002, + "grad_norm": 0.7294639491913409, + "learning_rate": 3.4485905946759965e-05, + "loss": 1.005, + "step": 124 + }, + { + "epoch": 1.6, + "grad_norm": 0.6949491354569357, + "learning_rate": 3.4361903070645484e-05, + "loss": 1.0019, + "step": 125 + }, + { + "epoch": 1.6128, + "grad_norm": 0.6372941005851039, + "learning_rate": 3.423674967338681e-05, + "loss": 1.0474, + "step": 126 + }, + { + "epoch": 1.6256, + "grad_norm": 0.6336897873068353, + "learning_rate": 3.411045578092754e-05, + "loss": 1.0099, + "step": 127 + }, + { + "epoch": 1.6383999999999999, + "grad_norm": 0.6741231455881623, + "learning_rate": 3.398303151057543e-05, + "loss": 1.0727, + "step": 128 + }, + { + "epoch": 1.6512, + "grad_norm": 0.6003120067299178, + "learning_rate": 3.385448707019199e-05, + "loss": 1.0243, + "step": 129 + }, + { + "epoch": 1.6640000000000001, + "grad_norm": 0.6187596067016436, + "learning_rate": 3.372483275737468e-05, + "loss": 0.9836, + "step": 130 + }, + { + "epoch": 1.6768, + "grad_norm": 0.6929089905088957, + "learning_rate": 3.359407895863199e-05, + "loss": 1.0474, + "step": 131 + }, + { + "epoch": 1.6896, + "grad_norm": 0.6233898973907259, + "learning_rate": 3.34622361485514e-05, + "loss": 1.0421, + "step": 132 + }, + { + "epoch": 1.7024, + "grad_norm": 0.6612632537378574, + "learning_rate": 3.332931488896029e-05, + "loss": 1.05, + "step": 133 + }, + { + "epoch": 1.7151999999999998, + "grad_norm": 0.6619560427219947, + "learning_rate": 3.319532582807977e-05, + "loss": 1.0253, + "step": 134 + }, + { + "epoch": 1.728, + "grad_norm": 0.6888633993579613, + "learning_rate": 3.30602796996717e-05, + "loss": 1.0422, + "step": 135 + }, + { + "epoch": 1.7408000000000001, + "grad_norm": 0.738563107538913, + "learning_rate": 3.2924187322178865e-05, + "loss": 1.0177, + "step": 136 + }, + { + "epoch": 1.7536, + "grad_norm": 0.6960055265279931, + "learning_rate": 3.278705959785821e-05, + "loss": 1.0394, + "step": 137 + }, + { + "epoch": 1.7664, + "grad_norm": 0.5909931615279079, + "learning_rate": 3.2648907511907544e-05, + "loss": 1.024, + "step": 138 + }, + { + "epoch": 1.7792, + "grad_norm": 0.7575500923597764, + "learning_rate": 3.250974213158555e-05, + "loss": 1.0111, + "step": 139 + }, + { + "epoch": 1.792, + "grad_norm": 0.6900873453498054, + "learning_rate": 3.23695746053251e-05, + "loss": 0.9901, + "step": 140 + }, + { + "epoch": 1.8048, + "grad_norm": 0.8149304511025252, + "learning_rate": 3.222841616184025e-05, + "loss": 1.0533, + "step": 141 + }, + { + "epoch": 1.8176, + "grad_norm": 0.6306865685658272, + "learning_rate": 3.208627810922665e-05, + "loss": 1.0669, + "step": 142 + }, + { + "epoch": 1.8304, + "grad_norm": 0.7790307023573653, + "learning_rate": 3.194317183405573e-05, + "loss": 0.9949, + "step": 143 + }, + { + "epoch": 1.8432, + "grad_norm": 0.956777617494605, + "learning_rate": 3.1799108800462466e-05, + "loss": 1.0575, + "step": 144 + }, + { + "epoch": 1.8559999999999999, + "grad_norm": 0.7101708684119322, + "learning_rate": 3.1654100549227024e-05, + "loss": 1.0161, + "step": 145 + }, + { + "epoch": 1.8688, + "grad_norm": 0.6667058828503257, + "learning_rate": 3.1508158696850275e-05, + "loss": 1.021, + "step": 146 + }, + { + "epoch": 1.8816000000000002, + "grad_norm": 0.6841101091301254, + "learning_rate": 3.136129493462312e-05, + "loss": 1.0205, + "step": 147 + }, + { + "epoch": 1.8944, + "grad_norm": 0.7362428220666088, + "learning_rate": 3.121352102768998e-05, + "loss": 1.0128, + "step": 148 + }, + { + "epoch": 1.9072, + "grad_norm": 0.931468433753366, + "learning_rate": 3.106484881410628e-05, + "loss": 1.0624, + "step": 149 + }, + { + "epoch": 1.92, + "grad_norm": 0.6514868217300596, + "learning_rate": 3.091529020389009e-05, + "loss": 1.045, + "step": 150 + }, + { + "epoch": 1.9327999999999999, + "grad_norm": 0.6737780389378739, + "learning_rate": 3.076485717806808e-05, + "loss": 1.0603, + "step": 151 + }, + { + "epoch": 1.9456, + "grad_norm": 0.7971764922901946, + "learning_rate": 3.061356178771564e-05, + "loss": 1.047, + "step": 152 + }, + { + "epoch": 1.9584000000000001, + "grad_norm": 0.6672968881704991, + "learning_rate": 3.0461416152991555e-05, + "loss": 1.0348, + "step": 153 + }, + { + "epoch": 1.9712, + "grad_norm": 0.6285599621316675, + "learning_rate": 3.0308432462167045e-05, + "loss": 1.0388, + "step": 154 + }, + { + "epoch": 1.984, + "grad_norm": 0.6323443787495369, + "learning_rate": 3.015462297064936e-05, + "loss": 1.0082, + "step": 155 + }, + { + "epoch": 1.9968, + "grad_norm": 0.6282469553541248, + "learning_rate": 3.0000000000000004e-05, + "loss": 1.0165, + "step": 156 + }, + { + "epoch": 2.0096, + "grad_norm": 0.7920449181589374, + "learning_rate": 2.98445759369477e-05, + "loss": 0.9535, + "step": 157 + }, + { + "epoch": 2.0224, + "grad_norm": 0.9354237907431909, + "learning_rate": 2.9688363232396056e-05, + "loss": 0.8855, + "step": 158 + }, + { + "epoch": 2.0352, + "grad_norm": 0.7393414908433603, + "learning_rate": 2.9531374400426158e-05, + "loss": 0.9174, + "step": 159 + }, + { + "epoch": 2.048, + "grad_norm": 0.7456456430643493, + "learning_rate": 2.9373622017294075e-05, + "loss": 0.9103, + "step": 160 + }, + { + "epoch": 2.0608, + "grad_norm": 0.7289060958205632, + "learning_rate": 2.9215118720423375e-05, + "loss": 0.8442, + "step": 161 + }, + { + "epoch": 2.0736, + "grad_norm": 0.7886441991873184, + "learning_rate": 2.9055877207392752e-05, + "loss": 0.8601, + "step": 162 + }, + { + "epoch": 2.0864, + "grad_norm": 0.7164863165828993, + "learning_rate": 2.8895910234918828e-05, + "loss": 0.8757, + "step": 163 + }, + { + "epoch": 2.0992, + "grad_norm": 1.0509175010011313, + "learning_rate": 2.873523061783426e-05, + "loss": 0.8921, + "step": 164 + }, + { + "epoch": 2.112, + "grad_norm": 0.7083554410944634, + "learning_rate": 2.8573851228061084e-05, + "loss": 0.8993, + "step": 165 + }, + { + "epoch": 2.1248, + "grad_norm": 0.8584638658175244, + "learning_rate": 2.8411784993579633e-05, + "loss": 0.8283, + "step": 166 + }, + { + "epoch": 2.1376, + "grad_norm": 0.8694855263573216, + "learning_rate": 2.8249044897392814e-05, + "loss": 0.9054, + "step": 167 + }, + { + "epoch": 2.1504, + "grad_norm": 0.7269472881341665, + "learning_rate": 2.80856439764861e-05, + "loss": 0.8712, + "step": 168 + }, + { + "epoch": 2.1632, + "grad_norm": 0.76003993102072, + "learning_rate": 2.792159532078314e-05, + "loss": 0.8566, + "step": 169 + }, + { + "epoch": 2.176, + "grad_norm": 0.8819665165882664, + "learning_rate": 2.77569120720971e-05, + "loss": 0.888, + "step": 170 + }, + { + "epoch": 2.1888, + "grad_norm": 0.8216730545600411, + "learning_rate": 2.7591607423077932e-05, + "loss": 0.8974, + "step": 171 + }, + { + "epoch": 2.2016, + "grad_norm": 0.8543194781416534, + "learning_rate": 2.7425694616155474e-05, + "loss": 0.8638, + "step": 172 + }, + { + "epoch": 2.2144, + "grad_norm": 0.9629014774410137, + "learning_rate": 2.7259186942478656e-05, + "loss": 0.902, + "step": 173 + }, + { + "epoch": 2.2272, + "grad_norm": 0.9390773048771573, + "learning_rate": 2.7092097740850712e-05, + "loss": 0.9118, + "step": 174 + }, + { + "epoch": 2.24, + "grad_norm": 0.6586425638342351, + "learning_rate": 2.692444039666066e-05, + "loss": 0.8978, + "step": 175 + }, + { + "epoch": 2.2528, + "grad_norm": 0.8543406916199504, + "learning_rate": 2.6756228340810946e-05, + "loss": 0.8812, + "step": 176 + }, + { + "epoch": 2.2656, + "grad_norm": 0.5996784440113992, + "learning_rate": 2.6587475048641596e-05, + "loss": 0.881, + "step": 177 + }, + { + "epoch": 2.2784, + "grad_norm": 0.6456129989687627, + "learning_rate": 2.6418194038850634e-05, + "loss": 0.8689, + "step": 178 + }, + { + "epoch": 2.2912, + "grad_norm": 0.5918832046032291, + "learning_rate": 2.624839887241115e-05, + "loss": 0.8778, + "step": 179 + }, + { + "epoch": 2.304, + "grad_norm": 0.6766626196792827, + "learning_rate": 2.607810315148494e-05, + "loss": 0.9127, + "step": 180 + }, + { + "epoch": 2.3168, + "grad_norm": 0.7642068892955837, + "learning_rate": 2.5907320518332827e-05, + "loss": 0.8929, + "step": 181 + }, + { + "epoch": 2.3296, + "grad_norm": 0.6765160458989914, + "learning_rate": 2.5736064654221808e-05, + "loss": 0.887, + "step": 182 + }, + { + "epoch": 2.3424, + "grad_norm": 0.6298926463574855, + "learning_rate": 2.5564349278329056e-05, + "loss": 0.8847, + "step": 183 + }, + { + "epoch": 2.3552, + "grad_norm": 0.7069104046493812, + "learning_rate": 2.539218814664288e-05, + "loss": 0.8564, + "step": 184 + }, + { + "epoch": 2.368, + "grad_norm": 0.6670546688917147, + "learning_rate": 2.521959505086075e-05, + "loss": 0.8604, + "step": 185 + }, + { + "epoch": 2.3808, + "grad_norm": 0.6163876874249468, + "learning_rate": 2.5046583817284437e-05, + "loss": 0.8296, + "step": 186 + }, + { + "epoch": 2.3936, + "grad_norm": 0.6901896113367271, + "learning_rate": 2.487316830571244e-05, + "loss": 0.8715, + "step": 187 + }, + { + "epoch": 2.4064, + "grad_norm": 0.6047440816959818, + "learning_rate": 2.4699362408329646e-05, + "loss": 0.8767, + "step": 188 + }, + { + "epoch": 2.4192, + "grad_norm": 0.6099555402580358, + "learning_rate": 2.4525180048594452e-05, + "loss": 0.8868, + "step": 189 + }, + { + "epoch": 2.432, + "grad_norm": 0.5881337606800934, + "learning_rate": 2.435063518012335e-05, + "loss": 0.8933, + "step": 190 + }, + { + "epoch": 2.4448, + "grad_norm": 0.6671370070980503, + "learning_rate": 2.4175741785573177e-05, + "loss": 0.8951, + "step": 191 + }, + { + "epoch": 2.4576000000000002, + "grad_norm": 0.7155466500803334, + "learning_rate": 2.4000513875520892e-05, + "loss": 0.8865, + "step": 192 + }, + { + "epoch": 2.4704, + "grad_norm": 0.5579261507137053, + "learning_rate": 2.3824965487341247e-05, + "loss": 0.8794, + "step": 193 + }, + { + "epoch": 2.4832, + "grad_norm": 0.6713643030866266, + "learning_rate": 2.3649110684082258e-05, + "loss": 0.9061, + "step": 194 + }, + { + "epoch": 2.496, + "grad_norm": 0.4896026221778859, + "learning_rate": 2.3472963553338614e-05, + "loss": 0.8858, + "step": 195 + }, + { + "epoch": 2.5088, + "grad_norm": 0.5533236722587165, + "learning_rate": 2.3296538206123134e-05, + "loss": 0.8667, + "step": 196 + }, + { + "epoch": 2.5216, + "grad_norm": 0.47090995094313093, + "learning_rate": 2.311984877573636e-05, + "loss": 0.8812, + "step": 197 + }, + { + "epoch": 2.5343999999999998, + "grad_norm": 0.4833307508846615, + "learning_rate": 2.2942909416634326e-05, + "loss": 0.8887, + "step": 198 + }, + { + "epoch": 2.5472, + "grad_norm": 0.48979876153574464, + "learning_rate": 2.2765734303294666e-05, + "loss": 0.882, + "step": 199 + }, + { + "epoch": 2.56, + "grad_norm": 0.5158802399073401, + "learning_rate": 2.2588337629081107e-05, + "loss": 0.8557, + "step": 200 + }, + { + "epoch": 2.5728, + "grad_norm": 0.5010025084567198, + "learning_rate": 2.2410733605106462e-05, + "loss": 0.881, + "step": 201 + }, + { + "epoch": 2.5856, + "grad_norm": 0.5454774120190347, + "learning_rate": 2.2232936459094158e-05, + "loss": 0.8844, + "step": 202 + }, + { + "epoch": 2.5984, + "grad_norm": 0.5464916386754389, + "learning_rate": 2.205496043423849e-05, + "loss": 0.8555, + "step": 203 + }, + { + "epoch": 2.6112, + "grad_norm": 0.5833801851333361, + "learning_rate": 2.1876819788063586e-05, + "loss": 0.9151, + "step": 204 + }, + { + "epoch": 2.624, + "grad_norm": 0.5920875611002528, + "learning_rate": 2.16985287912813e-05, + "loss": 0.8532, + "step": 205 + }, + { + "epoch": 2.6368, + "grad_norm": 0.5470965335334187, + "learning_rate": 2.1520101726647922e-05, + "loss": 0.9498, + "step": 206 + }, + { + "epoch": 2.6496, + "grad_norm": 0.6307772012829592, + "learning_rate": 2.1341552887820048e-05, + "loss": 0.8701, + "step": 207 + }, + { + "epoch": 2.6624, + "grad_norm": 0.48514304019394006, + "learning_rate": 2.1162896578209517e-05, + "loss": 0.8511, + "step": 208 + }, + { + "epoch": 2.6752000000000002, + "grad_norm": 0.6282389120924936, + "learning_rate": 2.0984147109837564e-05, + "loss": 0.8587, + "step": 209 + }, + { + "epoch": 2.6879999999999997, + "grad_norm": 0.44617040466325647, + "learning_rate": 2.0805318802188307e-05, + "loss": 0.8273, + "step": 210 + }, + { + "epoch": 2.7008, + "grad_norm": 0.5636627707513929, + "learning_rate": 2.0626425981061608e-05, + "loss": 0.8766, + "step": 211 + }, + { + "epoch": 2.7136, + "grad_norm": 0.4446555464176329, + "learning_rate": 2.0447482977425465e-05, + "loss": 0.8733, + "step": 212 + }, + { + "epoch": 2.7264, + "grad_norm": 0.4456934329218442, + "learning_rate": 2.0268504126267952e-05, + "loss": 0.8684, + "step": 213 + }, + { + "epoch": 2.7392, + "grad_norm": 0.5148410533257054, + "learning_rate": 2.008950376544887e-05, + "loss": 0.8812, + "step": 214 + }, + { + "epoch": 2.752, + "grad_norm": 0.4639599429519105, + "learning_rate": 1.9910496234551132e-05, + "loss": 0.8658, + "step": 215 + }, + { + "epoch": 2.7648, + "grad_norm": 0.46951766652022153, + "learning_rate": 1.9731495873732055e-05, + "loss": 0.8324, + "step": 216 + }, + { + "epoch": 2.7776, + "grad_norm": 0.44882362079406707, + "learning_rate": 1.9552517022574542e-05, + "loss": 0.8876, + "step": 217 + }, + { + "epoch": 2.7904, + "grad_norm": 0.52018784813985, + "learning_rate": 1.93735740189384e-05, + "loss": 0.873, + "step": 218 + }, + { + "epoch": 2.8032, + "grad_norm": 0.4709442382740269, + "learning_rate": 1.9194681197811703e-05, + "loss": 0.9178, + "step": 219 + }, + { + "epoch": 2.816, + "grad_norm": 0.5299421391031691, + "learning_rate": 1.901585289016244e-05, + "loss": 0.9269, + "step": 220 + }, + { + "epoch": 2.8288, + "grad_norm": 0.4897808540168492, + "learning_rate": 1.8837103421790486e-05, + "loss": 0.9416, + "step": 221 + }, + { + "epoch": 2.8416, + "grad_norm": 0.46425335582121, + "learning_rate": 1.8658447112179952e-05, + "loss": 0.9035, + "step": 222 + }, + { + "epoch": 2.8544, + "grad_norm": 0.518932487390929, + "learning_rate": 1.8479898273352084e-05, + "loss": 0.8947, + "step": 223 + }, + { + "epoch": 2.8672, + "grad_norm": 0.5666166959233204, + "learning_rate": 1.83014712087187e-05, + "loss": 0.8635, + "step": 224 + }, + { + "epoch": 2.88, + "grad_norm": 0.487924819853616, + "learning_rate": 1.8123180211936417e-05, + "loss": 0.9178, + "step": 225 + }, + { + "epoch": 2.8928000000000003, + "grad_norm": 0.46873872119200616, + "learning_rate": 1.794503956576152e-05, + "loss": 0.8915, + "step": 226 + }, + { + "epoch": 2.9055999999999997, + "grad_norm": 0.5407830565438971, + "learning_rate": 1.776706354090585e-05, + "loss": 0.8862, + "step": 227 + }, + { + "epoch": 2.9184, + "grad_norm": 0.5886391967590532, + "learning_rate": 1.758926639489354e-05, + "loss": 0.8611, + "step": 228 + }, + { + "epoch": 2.9312, + "grad_norm": 0.47630443340352235, + "learning_rate": 1.7411662370918893e-05, + "loss": 0.861, + "step": 229 + }, + { + "epoch": 2.944, + "grad_norm": 0.6098771136390113, + "learning_rate": 1.7234265696705344e-05, + "loss": 0.92, + "step": 230 + }, + { + "epoch": 2.9568, + "grad_norm": 0.45692835759900857, + "learning_rate": 1.7057090583365678e-05, + "loss": 0.9233, + "step": 231 + }, + { + "epoch": 2.9696, + "grad_norm": 0.5576678894833484, + "learning_rate": 1.6880151224263646e-05, + "loss": 0.8436, + "step": 232 + }, + { + "epoch": 2.9824, + "grad_norm": 0.4685258580438374, + "learning_rate": 1.6703461793876876e-05, + "loss": 0.9097, + "step": 233 + }, + { + "epoch": 2.9952, + "grad_norm": 0.504819149781262, + "learning_rate": 1.6527036446661396e-05, + "loss": 0.8545, + "step": 234 + }, + { + "epoch": 3.008, + "grad_norm": 0.6519811830810548, + "learning_rate": 1.635088931591775e-05, + "loss": 0.8374, + "step": 235 + }, + { + "epoch": 3.0208, + "grad_norm": 0.4874725917892601, + "learning_rate": 1.6175034512658753e-05, + "loss": 0.7423, + "step": 236 + }, + { + "epoch": 3.0336, + "grad_norm": 0.7398932139222312, + "learning_rate": 1.5999486124479115e-05, + "loss": 0.7227, + "step": 237 + }, + { + "epoch": 3.0464, + "grad_norm": 0.7191644498891802, + "learning_rate": 1.5824258214426833e-05, + "loss": 0.7677, + "step": 238 + }, + { + "epoch": 3.0592, + "grad_norm": 0.6196994167588507, + "learning_rate": 1.5649364819876655e-05, + "loss": 0.7768, + "step": 239 + }, + { + "epoch": 3.072, + "grad_norm": 0.6894402364689628, + "learning_rate": 1.547481995140556e-05, + "loss": 0.7745, + "step": 240 + }, + { + "epoch": 3.0848, + "grad_norm": 0.5705946275968563, + "learning_rate": 1.5300637591670357e-05, + "loss": 0.7342, + "step": 241 + }, + { + "epoch": 3.0976, + "grad_norm": 0.611007325572401, + "learning_rate": 1.5126831694287564e-05, + "loss": 0.7096, + "step": 242 + }, + { + "epoch": 3.1104, + "grad_norm": 0.6354279224520238, + "learning_rate": 1.4953416182715566e-05, + "loss": 0.7988, + "step": 243 + }, + { + "epoch": 3.1232, + "grad_norm": 0.557072613263889, + "learning_rate": 1.478040494913926e-05, + "loss": 0.7481, + "step": 244 + }, + { + "epoch": 3.136, + "grad_norm": 0.6886549270766755, + "learning_rate": 1.460781185335713e-05, + "loss": 0.757, + "step": 245 + }, + { + "epoch": 3.1488, + "grad_norm": 0.5311903167356413, + "learning_rate": 1.443565072167095e-05, + "loss": 0.7826, + "step": 246 + }, + { + "epoch": 3.1616, + "grad_norm": 0.5878784893665593, + "learning_rate": 1.4263935345778202e-05, + "loss": 0.7886, + "step": 247 + }, + { + "epoch": 3.1744, + "grad_norm": 0.5497592443294768, + "learning_rate": 1.409267948166718e-05, + "loss": 0.7768, + "step": 248 + }, + { + "epoch": 3.1872, + "grad_norm": 0.499403040556143, + "learning_rate": 1.3921896848515064e-05, + "loss": 0.7398, + "step": 249 + }, + { + "epoch": 3.2, + "grad_norm": 0.5176994890224423, + "learning_rate": 1.3751601127588849e-05, + "loss": 0.7344, + "step": 250 + }, + { + "epoch": 3.2128, + "grad_norm": 0.513937352982502, + "learning_rate": 1.3581805961149371e-05, + "loss": 0.7289, + "step": 251 + }, + { + "epoch": 3.2256, + "grad_norm": 0.5085230133863774, + "learning_rate": 1.341252495135841e-05, + "loss": 0.7285, + "step": 252 + }, + { + "epoch": 3.2384, + "grad_norm": 0.48502274403674484, + "learning_rate": 1.324377165918906e-05, + "loss": 0.7188, + "step": 253 + }, + { + "epoch": 3.2512, + "grad_norm": 0.44755314341811114, + "learning_rate": 1.3075559603339354e-05, + "loss": 0.7723, + "step": 254 + }, + { + "epoch": 3.2640000000000002, + "grad_norm": 0.4865070203678609, + "learning_rate": 1.2907902259149287e-05, + "loss": 0.7881, + "step": 255 + }, + { + "epoch": 3.2768, + "grad_norm": 0.4313048125863158, + "learning_rate": 1.274081305752135e-05, + "loss": 0.7191, + "step": 256 + }, + { + "epoch": 3.2896, + "grad_norm": 0.4240472484996708, + "learning_rate": 1.2574305383844528e-05, + "loss": 0.7464, + "step": 257 + }, + { + "epoch": 3.3024, + "grad_norm": 0.4325166990775412, + "learning_rate": 1.2408392576922075e-05, + "loss": 0.7621, + "step": 258 + }, + { + "epoch": 3.3152, + "grad_norm": 0.4566343829800513, + "learning_rate": 1.2243087927902905e-05, + "loss": 0.7178, + "step": 259 + }, + { + "epoch": 3.328, + "grad_norm": 0.41356618644878995, + "learning_rate": 1.2078404679216864e-05, + "loss": 0.8272, + "step": 260 + }, + { + "epoch": 3.3407999999999998, + "grad_norm": 0.4076080621370411, + "learning_rate": 1.1914356023513904e-05, + "loss": 0.7726, + "step": 261 + }, + { + "epoch": 3.3536, + "grad_norm": 0.45042673694474916, + "learning_rate": 1.1750955102607193e-05, + "loss": 0.7578, + "step": 262 + }, + { + "epoch": 3.3664, + "grad_norm": 0.3948818114710141, + "learning_rate": 1.1588215006420374e-05, + "loss": 0.7829, + "step": 263 + }, + { + "epoch": 3.3792, + "grad_norm": 0.40820928538282475, + "learning_rate": 1.1426148771938915e-05, + "loss": 0.7438, + "step": 264 + }, + { + "epoch": 3.392, + "grad_norm": 0.40130937332636657, + "learning_rate": 1.1264769382165748e-05, + "loss": 0.7771, + "step": 265 + }, + { + "epoch": 3.4048, + "grad_norm": 0.43505495772614156, + "learning_rate": 1.110408976508118e-05, + "loss": 0.7672, + "step": 266 + }, + { + "epoch": 3.4176, + "grad_norm": 0.40695836943831887, + "learning_rate": 1.094412279260726e-05, + "loss": 0.7912, + "step": 267 + }, + { + "epoch": 3.4304, + "grad_norm": 0.42588542701909704, + "learning_rate": 1.0784881279576635e-05, + "loss": 0.784, + "step": 268 + }, + { + "epoch": 3.4432, + "grad_norm": 0.43094699386668583, + "learning_rate": 1.0626377982705929e-05, + "loss": 0.7489, + "step": 269 + }, + { + "epoch": 3.456, + "grad_norm": 0.39680827424605447, + "learning_rate": 1.0468625599573842e-05, + "loss": 0.7784, + "step": 270 + }, + { + "epoch": 3.4688, + "grad_norm": 0.3970909365963024, + "learning_rate": 1.0311636767603952e-05, + "loss": 0.7935, + "step": 271 + }, + { + "epoch": 3.4816, + "grad_norm": 0.4458156807009302, + "learning_rate": 1.0155424063052306e-05, + "loss": 0.7564, + "step": 272 + }, + { + "epoch": 3.4944, + "grad_norm": 0.4207458966216561, + "learning_rate": 1.0000000000000006e-05, + "loss": 0.753, + "step": 273 + }, + { + "epoch": 3.5072, + "grad_norm": 0.3970972025429375, + "learning_rate": 9.84537702935065e-06, + "loss": 0.7325, + "step": 274 + }, + { + "epoch": 3.52, + "grad_norm": 0.39976069168626505, + "learning_rate": 9.691567537832964e-06, + "loss": 0.7293, + "step": 275 + }, + { + "epoch": 3.5328, + "grad_norm": 0.421956049762003, + "learning_rate": 9.538583847008452e-06, + "loss": 0.7106, + "step": 276 + }, + { + "epoch": 3.5456, + "grad_norm": 0.4237565677721429, + "learning_rate": 9.386438212284372e-06, + "loss": 0.7289, + "step": 277 + }, + { + "epoch": 3.5584, + "grad_norm": 0.38997648773116933, + "learning_rate": 9.235142821931928e-06, + "loss": 0.7199, + "step": 278 + }, + { + "epoch": 3.5712, + "grad_norm": 0.3857372505711672, + "learning_rate": 9.084709796109907e-06, + "loss": 0.7905, + "step": 279 + }, + { + "epoch": 3.584, + "grad_norm": 0.41795353699534166, + "learning_rate": 8.93515118589373e-06, + "loss": 0.7608, + "step": 280 + }, + { + "epoch": 3.5968, + "grad_norm": 0.37577239930421513, + "learning_rate": 8.786478972310023e-06, + "loss": 0.7573, + "step": 281 + }, + { + "epoch": 3.6096, + "grad_norm": 0.3644839989291009, + "learning_rate": 8.638705065376887e-06, + "loss": 0.7468, + "step": 282 + }, + { + "epoch": 3.6224, + "grad_norm": 0.3803277128946228, + "learning_rate": 8.491841303149728e-06, + "loss": 0.7759, + "step": 283 + }, + { + "epoch": 3.6352, + "grad_norm": 0.371863808115335, + "learning_rate": 8.345899450772975e-06, + "loss": 0.7509, + "step": 284 + }, + { + "epoch": 3.648, + "grad_norm": 0.3644754129069241, + "learning_rate": 8.200891199537549e-06, + "loss": 0.7356, + "step": 285 + }, + { + "epoch": 3.6608, + "grad_norm": 0.40268320556516357, + "learning_rate": 8.056828165944282e-06, + "loss": 0.7068, + "step": 286 + }, + { + "epoch": 3.6736, + "grad_norm": 0.394716063369627, + "learning_rate": 7.913721890773354e-06, + "loss": 0.759, + "step": 287 + }, + { + "epoch": 3.6864, + "grad_norm": 0.38812622954106013, + "learning_rate": 7.771583838159756e-06, + "loss": 0.7596, + "step": 288 + }, + { + "epoch": 3.6992000000000003, + "grad_norm": 0.37922553085096566, + "learning_rate": 7.630425394674903e-06, + "loss": 0.7434, + "step": 289 + }, + { + "epoch": 3.7119999999999997, + "grad_norm": 0.38003748075383165, + "learning_rate": 7.49025786841445e-06, + "loss": 0.7631, + "step": 290 + }, + { + "epoch": 3.7248, + "grad_norm": 0.35758289241851654, + "learning_rate": 7.3510924880924575e-06, + "loss": 0.7464, + "step": 291 + }, + { + "epoch": 3.7376, + "grad_norm": 0.3954391374993535, + "learning_rate": 7.212940402141808e-06, + "loss": 0.7257, + "step": 292 + }, + { + "epoch": 3.7504, + "grad_norm": 0.3695155475353515, + "learning_rate": 7.075812677821145e-06, + "loss": 0.7306, + "step": 293 + }, + { + "epoch": 3.7632, + "grad_norm": 0.3481154912845101, + "learning_rate": 6.939720300328303e-06, + "loss": 0.7637, + "step": 294 + }, + { + "epoch": 3.776, + "grad_norm": 0.36757114334729113, + "learning_rate": 6.8046741719202385e-06, + "loss": 0.7364, + "step": 295 + }, + { + "epoch": 3.7888, + "grad_norm": 0.36766231492812096, + "learning_rate": 6.67068511103971e-06, + "loss": 0.7154, + "step": 296 + }, + { + "epoch": 3.8016, + "grad_norm": 0.3594126418739973, + "learning_rate": 6.537763851448593e-06, + "loss": 0.739, + "step": 297 + }, + { + "epoch": 3.8144, + "grad_norm": 0.3695278652729132, + "learning_rate": 6.4059210413680175e-06, + "loss": 0.7404, + "step": 298 + }, + { + "epoch": 3.8272, + "grad_norm": 0.3469218747542019, + "learning_rate": 6.275167242625331e-06, + "loss": 0.775, + "step": 299 + }, + { + "epoch": 3.84, + "grad_norm": 0.3530007874211548, + "learning_rate": 6.145512929808013e-06, + "loss": 0.806, + "step": 300 + }, + { + "epoch": 3.8528000000000002, + "grad_norm": 0.34044311854526643, + "learning_rate": 6.016968489424572e-06, + "loss": 0.7129, + "step": 301 + }, + { + "epoch": 3.8656, + "grad_norm": 0.3410813237685364, + "learning_rate": 5.889544219072465e-06, + "loss": 0.7298, + "step": 302 + }, + { + "epoch": 3.8784, + "grad_norm": 0.34537139147728846, + "learning_rate": 5.7632503266131925e-06, + "loss": 0.7621, + "step": 303 + }, + { + "epoch": 3.8912, + "grad_norm": 0.34471319900197667, + "learning_rate": 5.638096929354522e-06, + "loss": 0.7537, + "step": 304 + }, + { + "epoch": 3.904, + "grad_norm": 0.3472159637835492, + "learning_rate": 5.514094053240035e-06, + "loss": 0.7452, + "step": 305 + }, + { + "epoch": 3.9168, + "grad_norm": 0.3447595885558001, + "learning_rate": 5.39125163204594e-06, + "loss": 0.803, + "step": 306 + }, + { + "epoch": 3.9295999999999998, + "grad_norm": 0.34569322352863874, + "learning_rate": 5.269579506585259e-06, + "loss": 0.7645, + "step": 307 + }, + { + "epoch": 3.9424, + "grad_norm": 0.3536645907641703, + "learning_rate": 5.149087423919541e-06, + "loss": 0.7452, + "step": 308 + }, + { + "epoch": 3.9552, + "grad_norm": 0.3455657100117534, + "learning_rate": 5.029785036577976e-06, + "loss": 0.739, + "step": 309 + }, + { + "epoch": 3.968, + "grad_norm": 0.3377694367318897, + "learning_rate": 4.911681901784198e-06, + "loss": 0.7621, + "step": 310 + }, + { + "epoch": 3.9808, + "grad_norm": 0.331860075985349, + "learning_rate": 4.794787480690597e-06, + "loss": 0.7688, + "step": 311 + }, + { + "epoch": 3.9936, + "grad_norm": 0.35761985983691535, + "learning_rate": 4.679111137620442e-06, + "loss": 0.7227, + "step": 312 + }, + { + "epoch": 4.0064, + "grad_norm": 0.37198317152723936, + "learning_rate": 4.5646621393177e-06, + "loss": 0.7252, + "step": 313 + }, + { + "epoch": 4.0192, + "grad_norm": 0.6561852689389754, + "learning_rate": 4.451449654204685e-06, + "loss": 0.6061, + "step": 314 + }, + { + "epoch": 4.032, + "grad_norm": 0.36651131968397777, + "learning_rate": 4.339482751647557e-06, + "loss": 0.7034, + "step": 315 + }, + { + "epoch": 4.0448, + "grad_norm": 0.37514756639768854, + "learning_rate": 4.228770401229824e-06, + "loss": 0.6067, + "step": 316 + }, + { + "epoch": 4.0576, + "grad_norm": 0.5566002695565736, + "learning_rate": 4.119321472033779e-06, + "loss": 0.6513, + "step": 317 + }, + { + "epoch": 4.0704, + "grad_norm": 0.6058517265401333, + "learning_rate": 4.011144731929981e-06, + "loss": 0.7156, + "step": 318 + }, + { + "epoch": 4.0832, + "grad_norm": 0.4381743948996236, + "learning_rate": 3.904248846874894e-06, + "loss": 0.6634, + "step": 319 + }, + { + "epoch": 4.096, + "grad_norm": 0.3907006773329518, + "learning_rate": 3.7986423802166705e-06, + "loss": 0.6652, + "step": 320 + }, + { + "epoch": 4.1088, + "grad_norm": 0.475663431057593, + "learning_rate": 3.694333792009115e-06, + "loss": 0.6529, + "step": 321 + }, + { + "epoch": 4.1216, + "grad_norm": 0.4781882268473551, + "learning_rate": 3.5913314383339937e-06, + "loss": 0.7027, + "step": 322 + }, + { + "epoch": 4.1344, + "grad_norm": 0.40575808944524244, + "learning_rate": 3.4896435706316e-06, + "loss": 0.7221, + "step": 323 + }, + { + "epoch": 4.1472, + "grad_norm": 0.4008959323794245, + "learning_rate": 3.3892783350397675e-06, + "loss": 0.7016, + "step": 324 + }, + { + "epoch": 4.16, + "grad_norm": 0.44940259724687015, + "learning_rate": 3.290243771741275e-06, + "loss": 0.6472, + "step": 325 + }, + { + "epoch": 4.1728, + "grad_norm": 0.43604266733159375, + "learning_rate": 3.1925478143197418e-06, + "loss": 0.7008, + "step": 326 + }, + { + "epoch": 4.1856, + "grad_norm": 0.45059373555578275, + "learning_rate": 3.0961982891241083e-06, + "loss": 0.693, + "step": 327 + }, + { + "epoch": 4.1984, + "grad_norm": 0.42572730736655867, + "learning_rate": 3.001202914641628e-06, + "loss": 0.6633, + "step": 328 + }, + { + "epoch": 4.2112, + "grad_norm": 0.4174156855040001, + "learning_rate": 2.907569300879596e-06, + "loss": 0.6922, + "step": 329 + }, + { + "epoch": 4.224, + "grad_norm": 0.3932112878326503, + "learning_rate": 2.815304948755664e-06, + "loss": 0.6372, + "step": 330 + }, + { + "epoch": 4.2368, + "grad_norm": 0.4021422678728423, + "learning_rate": 2.7244172494969978e-06, + "loss": 0.7109, + "step": 331 + }, + { + "epoch": 4.2496, + "grad_norm": 0.41603513057451186, + "learning_rate": 2.6349134840481294e-06, + "loss": 0.677, + "step": 332 + }, + { + "epoch": 4.2624, + "grad_norm": 0.40701323138346235, + "learning_rate": 2.546800822487714e-06, + "loss": 0.677, + "step": 333 + }, + { + "epoch": 4.2752, + "grad_norm": 0.3618875995027296, + "learning_rate": 2.4600863234541338e-06, + "loss": 0.67, + "step": 334 + }, + { + "epoch": 4.288, + "grad_norm": 0.36204162502778214, + "learning_rate": 2.374776933580025e-06, + "loss": 0.6799, + "step": 335 + }, + { + "epoch": 4.3008, + "grad_norm": 0.3354404902702719, + "learning_rate": 2.2908794869358044e-06, + "loss": 0.6442, + "step": 336 + }, + { + "epoch": 4.3136, + "grad_norm": 0.3505177803543528, + "learning_rate": 2.2084007044821764e-06, + "loss": 0.6758, + "step": 337 + }, + { + "epoch": 4.3264, + "grad_norm": 0.37232280470334717, + "learning_rate": 2.127347193531757e-06, + "loss": 0.6838, + "step": 338 + }, + { + "epoch": 4.3392, + "grad_norm": 0.38496967345842165, + "learning_rate": 2.0477254472197237e-06, + "loss": 0.6978, + "step": 339 + }, + { + "epoch": 4.352, + "grad_norm": 0.3887365973453678, + "learning_rate": 1.96954184398368e-06, + "loss": 0.6465, + "step": 340 + }, + { + "epoch": 4.3648, + "grad_norm": 0.3560874514147073, + "learning_rate": 1.8928026470526917e-06, + "loss": 0.6143, + "step": 341 + }, + { + "epoch": 4.3776, + "grad_norm": 0.3234250557774697, + "learning_rate": 1.817514003945524e-06, + "loss": 0.6868, + "step": 342 + }, + { + "epoch": 4.3904, + "grad_norm": 0.30275731309740356, + "learning_rate": 1.743681945978184e-06, + "loss": 0.6901, + "step": 343 + }, + { + "epoch": 4.4032, + "grad_norm": 0.30620924708135805, + "learning_rate": 1.6713123877807413e-06, + "loss": 0.6339, + "step": 344 + }, + { + "epoch": 4.416, + "grad_norm": 0.31118959285928466, + "learning_rate": 1.6004111268235156e-06, + "loss": 0.682, + "step": 345 + }, + { + "epoch": 4.4288, + "grad_norm": 0.35141999300884796, + "learning_rate": 1.5309838429526714e-06, + "loss": 0.7029, + "step": 346 + }, + { + "epoch": 4.4416, + "grad_norm": 0.3606055859454003, + "learning_rate": 1.4630360979351644e-06, + "loss": 0.6667, + "step": 347 + }, + { + "epoch": 4.4544, + "grad_norm": 0.3345093450040408, + "learning_rate": 1.396573335013236e-06, + "loss": 0.7034, + "step": 348 + }, + { + "epoch": 4.4672, + "grad_norm": 0.31136247386805826, + "learning_rate": 1.3316008784683265e-06, + "loss": 0.6817, + "step": 349 + }, + { + "epoch": 4.48, + "grad_norm": 0.2947359919955738, + "learning_rate": 1.2681239331945695e-06, + "loss": 0.6848, + "step": 350 + }, + { + "epoch": 4.4928, + "grad_norm": 0.30007880824834926, + "learning_rate": 1.2061475842818337e-06, + "loss": 0.7368, + "step": 351 + }, + { + "epoch": 4.5056, + "grad_norm": 0.3050371284095851, + "learning_rate": 1.1456767966083393e-06, + "loss": 0.6892, + "step": 352 + }, + { + "epoch": 4.5184, + "grad_norm": 0.3291555653795982, + "learning_rate": 1.086716414442952e-06, + "loss": 0.684, + "step": 353 + }, + { + "epoch": 4.5312, + "grad_norm": 0.3310226992443401, + "learning_rate": 1.0292711610570904e-06, + "loss": 0.7055, + "step": 354 + }, + { + "epoch": 4.5440000000000005, + "grad_norm": 0.3124014951458642, + "learning_rate": 9.733456383463658e-07, + "loss": 0.5981, + "step": 355 + }, + { + "epoch": 4.5568, + "grad_norm": 0.311371463834397, + "learning_rate": 9.189443264619102e-07, + "loss": 0.7119, + "step": 356 + }, + { + "epoch": 4.5696, + "grad_norm": 0.30060369011333293, + "learning_rate": 8.660715834514977e-07, + "loss": 0.6717, + "step": 357 + }, + { + "epoch": 4.5824, + "grad_norm": 0.3116295751001881, + "learning_rate": 8.147316449103959e-07, + "loss": 0.646, + "step": 358 + }, + { + "epoch": 4.5952, + "grad_norm": 0.31372899414770516, + "learning_rate": 7.649286236420806e-07, + "loss": 0.6589, + "step": 359 + }, + { + "epoch": 4.608, + "grad_norm": 0.2973766852081861, + "learning_rate": 7.166665093287539e-07, + "loss": 0.7039, + "step": 360 + }, + { + "epoch": 4.6208, + "grad_norm": 0.2956464896205796, + "learning_rate": 6.69949168211721e-07, + "loss": 0.7086, + "step": 361 + }, + { + "epoch": 4.6336, + "grad_norm": 0.3050968161758319, + "learning_rate": 6.247803427816945e-07, + "loss": 0.6299, + "step": 362 + }, + { + "epoch": 4.6464, + "grad_norm": 0.2895560012638669, + "learning_rate": 5.811636514789598e-07, + "loss": 0.7068, + "step": 363 + }, + { + "epoch": 4.6592, + "grad_norm": 0.2860382042764144, + "learning_rate": 5.391025884035239e-07, + "loss": 0.674, + "step": 364 + }, + { + "epoch": 4.672, + "grad_norm": 0.31440519446759935, + "learning_rate": 4.986005230351954e-07, + "loss": 0.7265, + "step": 365 + }, + { + "epoch": 4.6848, + "grad_norm": 0.2863757299429382, + "learning_rate": 4.5966069996365993e-07, + "loss": 0.7612, + "step": 366 + }, + { + "epoch": 4.6975999999999996, + "grad_norm": 0.30459290151108215, + "learning_rate": 4.22286238628562e-07, + "loss": 0.6638, + "step": 367 + }, + { + "epoch": 4.7104, + "grad_norm": 0.30622116120951404, + "learning_rate": 3.8648013306960664e-07, + "loss": 0.6798, + "step": 368 + }, + { + "epoch": 4.7232, + "grad_norm": 0.3135265781849215, + "learning_rate": 3.522452516867048e-07, + "loss": 0.6936, + "step": 369 + }, + { + "epoch": 4.736, + "grad_norm": 0.2974286222437718, + "learning_rate": 3.1958433701019697e-07, + "loss": 0.6592, + "step": 370 + }, + { + "epoch": 4.7488, + "grad_norm": 0.29169010439567084, + "learning_rate": 2.8850000548115155e-07, + "loss": 0.6883, + "step": 371 + }, + { + "epoch": 4.7616, + "grad_norm": 0.2954857385163254, + "learning_rate": 2.5899474724174313e-07, + "loss": 0.6762, + "step": 372 + }, + { + "epoch": 4.7744, + "grad_norm": 0.30554350788092144, + "learning_rate": 2.3107092593579905e-07, + "loss": 0.6383, + "step": 373 + }, + { + "epoch": 4.7872, + "grad_norm": 0.2871638236130085, + "learning_rate": 2.0473077851942858e-07, + "loss": 0.6458, + "step": 374 + }, + { + "epoch": 4.8, + "grad_norm": 0.3045991261393286, + "learning_rate": 1.799764150818306e-07, + "loss": 0.6113, + "step": 375 + }, + { + "epoch": 4.8128, + "grad_norm": 0.303297019465311, + "learning_rate": 1.5680981867625566e-07, + "loss": 0.6758, + "step": 376 + }, + { + "epoch": 4.8256, + "grad_norm": 0.29854505865022923, + "learning_rate": 1.3523284516113955e-07, + "loss": 0.6966, + "step": 377 + }, + { + "epoch": 4.8384, + "grad_norm": 0.29404174749341805, + "learning_rate": 1.1524722305144231e-07, + "loss": 0.7033, + "step": 378 + }, + { + "epoch": 4.8512, + "grad_norm": 0.3008331194546275, + "learning_rate": 9.685455338016347e-08, + "loss": 0.6582, + "step": 379 + }, + { + "epoch": 4.864, + "grad_norm": 0.3004375174980317, + "learning_rate": 8.005630957010014e-08, + "loss": 0.6699, + "step": 380 + }, + { + "epoch": 4.8768, + "grad_norm": 0.3188125927248378, + "learning_rate": 6.485383731580142e-08, + "loss": 0.6217, + "step": 381 + }, + { + "epoch": 4.8896, + "grad_norm": 0.2949431769950282, + "learning_rate": 5.1248354475768034e-08, + "loss": 0.6765, + "step": 382 + }, + { + "epoch": 4.9024, + "grad_norm": 0.28985927803177125, + "learning_rate": 3.924095097489922e-08, + "loss": 0.7327, + "step": 383 + }, + { + "epoch": 4.9152000000000005, + "grad_norm": 0.30470347407831944, + "learning_rate": 2.8832588717164766e-08, + "loss": 0.6233, + "step": 384 + }, + { + "epoch": 4.928, + "grad_norm": 0.3015858128464978, + "learning_rate": 2.0024101508555604e-08, + "loss": 0.6435, + "step": 385 + }, + { + "epoch": 4.9408, + "grad_norm": 0.30520060622615225, + "learning_rate": 1.281619499029274e-08, + "loss": 0.7127, + "step": 386 + }, + { + "epoch": 4.9536, + "grad_norm": 0.287862724065402, + "learning_rate": 7.209446582292501e-09, + "loss": 0.708, + "step": 387 + }, + { + "epoch": 4.9664, + "grad_norm": 0.28644752871236845, + "learning_rate": 3.2043054369057523e-09, + "loss": 0.7203, + "step": 388 + }, + { + "epoch": 4.9792, + "grad_norm": 0.29956360136524457, + "learning_rate": 8.010924029533406e-10, + "loss": 0.6833, + "step": 389 + }, + { + "epoch": 4.992, + "grad_norm": 0.2815319626646595, + "learning_rate": 0.0, + "loss": 0.7082, + "step": 390 + }, + { + "epoch": 4.992, + "step": 390, + "total_flos": 1.3856636017416602e+18, + "train_loss": 0.9147117905127696, + "train_runtime": 48380.7223, + "train_samples_per_second": 1.033, + "train_steps_per_second": 0.008 + } + ], + "logging_steps": 1, + "max_steps": 390, + "num_input_tokens_seen": 0, + "num_train_epochs": 5, + "save_steps": 500, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": true + }, + "attributes": {} + } + }, + "total_flos": 1.3856636017416602e+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..d32f210 --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4848c60084550c2a2b0c413259928e57dd222a65877c47a37d26484316b47ece +size 7288 diff --git a/training_loss.png b/training_loss.png new file mode 100644 index 0000000..f3adc8a 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