commit b264bddcb35a8e34455cd9760da1ce4ca5a2f3c3 Author: ModelHub XC Date: Wed Jun 10 02:16:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mlfoundations-dev/seed_code_multiple_samples_gpt_verification_scale_up_4K Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f608109 --- /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 + +training_args.bin filter=lfs diff=lfs merge=lfs -text +vocab.json filter=lfs diff=lfs merge=lfs -text +model-00002-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +model-00003-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +model-00004-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +model-00001-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text +merges.txt 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..44c6c05 --- /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: seed_code_multiple_samples_gpt_verification_scale_up_4K + results: [] +--- + + + +# seed_code_multiple_samples_gpt_verification_scale_up_4K + +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/seed_code_multiple_samples_gpt_verification_scale_up_4K dataset. + +## Model description + +More information needed + +## Intended uses & limitations + +More information needed + +## Training and evaluation data + +More information needed + +## Training procedure + +### Training hyperparameters + +The following hyperparameters were used during training: +- learning_rate: 1e-05 +- train_batch_size: 1 +- eval_batch_size: 8 +- seed: 42 +- distributed_type: multi-GPU +- num_devices: 8 +- gradient_accumulation_steps: 12 +- total_train_batch_size: 96 +- total_eval_batch_size: 64 +- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments +- lr_scheduler_type: cosine +- lr_scheduler_warmup_ratio: 0.1 +- num_epochs: 3.0 + +### Training results + + + +### Framework versions + +- Transformers 4.46.1 +- Pytorch 2.3.0 +- Datasets 3.1.0 +- Tokenizers 0.20.3 diff --git a/added_tokens.json b/added_tokens.json new file mode 100644 index 0000000..482ced4 --- /dev/null +++ b/added_tokens.json @@ -0,0 +1,24 @@ +{ + "": 151658, + "": 151657, + "<|box_end|>": 151649, + "<|box_start|>": 151648, + "<|endoftext|>": 151643, + "<|file_sep|>": 151664, + "<|fim_middle|>": 151660, + "<|fim_pad|>": 151662, + "<|fim_prefix|>": 151659, + "<|fim_suffix|>": 151661, + "<|im_end|>": 151645, + "<|im_start|>": 151644, + "<|image_pad|>": 151655, + "<|object_ref_end|>": 151647, + "<|object_ref_start|>": 151646, + "<|quad_end|>": 151651, + "<|quad_start|>": 151650, + "<|repo_name|>": 151663, + "<|video_pad|>": 151656, + "<|vision_end|>": 151653, + "<|vision_pad|>": 151654, + "<|vision_start|>": 151652 +} diff --git a/all_results.json b/all_results.json new file mode 100644 index 0000000..3f1b4b1 --- /dev/null +++ b/all_results.json @@ -0,0 +1,8 @@ +{ + "epoch": 3.0, + "total_flos": 266439779352576.0, + "train_loss": 0.8324689010586168, + "train_runtime": 15120.0259, + "train_samples_per_second": 1.962, + "train_steps_per_second": 0.02 +} \ 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..0b2ee3e --- /dev/null +++ b/configs.yaml @@ -0,0 +1,37 @@ +assistant_tag: gpt +bf16: 'True' +content_tag: value +cutoff_len: '16384' +dataset: mlfoundations-dev/seed_code_multiple_samples_gpt_verification_scale_up_4K +dataset_dir: ONLINE +ddp_timeout: '180000000' +deepspeed: /opt/ml/code/zero3_offload.json +do_train: 'True' +enable_liger_kernel: 'False' +finetuning_type: full +formatting: sharegpt +global_batch_size: '96' +gradient_accumulation_steps: '12' +hub_model_id: mlfoundations-dev/seed_code_multiple_samples_gpt_verification_scale_up_4K +learning_rate: 1e-05 +logging_steps: '1' +lr_scheduler_type: cosine +max_samples: '1000000' +messages: conversations +model_name_or_path: Qwen/Qwen2.5-7B-Instruct +num_train_epochs: '3.0' +output_dir: /opt/ml/model +overwrite_cache: 'True' +per_device_train_batch_size: '1' +plot_loss: 'True' +preprocessing_num_workers: '16' +push_to_db: 'True' +push_to_hub: 'True' +report_to: wandb +role_tag: from +run_name: seed_code_multiple_samples_gpt_verification_scale_up_4K +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..5fb5d9f --- /dev/null +++ b/model-00001-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fc94d106538a16c7d2c484394714761ff8307492fd0c13d5ff66fc796ec8a17 +size 4877660776 diff --git a/model-00002-of-00004.safetensors b/model-00002-of-00004.safetensors new file mode 100644 index 0000000..3c1f6c7 --- /dev/null +++ b/model-00002-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c98375d35d1a739649da8694088a838f33fc12ba38a8198f10fe1fbbad5dce53 +size 4932751008 diff --git a/model-00003-of-00004.safetensors b/model-00003-of-00004.safetensors new file mode 100644 index 0000000..085e065 --- /dev/null +++ b/model-00003-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4ee9039080c70c2c4fee0da417179947bdc55120f31093c220b90d43855742c +size 4330865200 diff --git a/model-00004-of-00004.safetensors b/model-00004-of-00004.safetensors new file mode 100644 index 0000000..7f4ce53 --- /dev/null +++ b/model-00004-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18fd293990b465526c12981bebdcf1175a35fafe35fc8d69802f3f46f91fbc8b +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..3f1b4b1 --- /dev/null +++ b/train_results.json @@ -0,0 +1,8 @@ +{ + "epoch": 3.0, + "total_flos": 266439779352576.0, + "train_loss": 0.8324689010586168, + "train_runtime": 15120.0259, + "train_samples_per_second": 1.962, + "train_steps_per_second": 0.02 +} \ No newline at end of file diff --git a/trainer_log.jsonl b/trainer_log.jsonl new file mode 100644 index 0000000..da32b8c --- /dev/null +++ b/trainer_log.jsonl @@ -0,0 +1,310 @@ +{"current_steps": 1, "total_steps": 309, "loss": 1.2227, "lr": 3.2258064516129035e-07, "epoch": 0.009708737864077669, "percentage": 0.32, "elapsed_time": "0:01:01", "remaining_time": "5:13:16"} +{"current_steps": 2, "total_steps": 309, "loss": 1.2675, "lr": 6.451612903225807e-07, "epoch": 0.019417475728155338, "percentage": 0.65, "elapsed_time": "0:01:49", "remaining_time": "4:40:06"} +{"current_steps": 3, "total_steps": 309, "loss": 1.2517, "lr": 9.67741935483871e-07, "epoch": 0.02912621359223301, "percentage": 0.97, "elapsed_time": "0:02:43", "remaining_time": "4:37:37"} +{"current_steps": 4, "total_steps": 309, "loss": 1.2515, "lr": 1.2903225806451614e-06, "epoch": 0.038834951456310676, "percentage": 1.29, "elapsed_time": "0:03:35", "remaining_time": "4:33:24"} +{"current_steps": 5, "total_steps": 309, "loss": 1.2498, "lr": 1.6129032258064516e-06, "epoch": 0.04854368932038835, "percentage": 1.62, "elapsed_time": "0:04:36", "remaining_time": "4:40:21"} +{"current_steps": 6, "total_steps": 309, "loss": 1.2283, "lr": 1.935483870967742e-06, "epoch": 0.05825242718446602, "percentage": 1.94, "elapsed_time": "0:05:29", "remaining_time": "4:37:02"} +{"current_steps": 7, "total_steps": 309, "loss": 1.1489, "lr": 2.2580645161290324e-06, "epoch": 0.06796116504854369, "percentage": 2.27, "elapsed_time": "0:06:21", "remaining_time": "4:34:29"} +{"current_steps": 8, "total_steps": 309, "loss": 1.1759, "lr": 2.580645161290323e-06, "epoch": 0.07766990291262135, "percentage": 2.59, "elapsed_time": "0:07:12", "remaining_time": "4:31:06"} +{"current_steps": 9, "total_steps": 309, "loss": 1.128, "lr": 2.903225806451613e-06, "epoch": 0.08737864077669903, "percentage": 2.91, "elapsed_time": "0:07:58", "remaining_time": "4:25:38"} +{"current_steps": 10, "total_steps": 309, "loss": 1.1088, "lr": 3.225806451612903e-06, "epoch": 0.0970873786407767, "percentage": 3.24, "elapsed_time": "0:08:53", "remaining_time": "4:25:40"} +{"current_steps": 11, "total_steps": 309, "loss": 1.1275, "lr": 3.548387096774194e-06, "epoch": 0.10679611650485436, "percentage": 3.56, "elapsed_time": "0:09:41", "remaining_time": "4:22:20"} +{"current_steps": 12, "total_steps": 309, "loss": 1.1287, "lr": 3.870967741935484e-06, "epoch": 0.11650485436893204, "percentage": 3.88, "elapsed_time": "0:10:37", "remaining_time": "4:23:08"} +{"current_steps": 13, "total_steps": 309, "loss": 1.1011, "lr": 4.193548387096774e-06, "epoch": 0.1262135922330097, "percentage": 4.21, "elapsed_time": "0:11:24", "remaining_time": "4:19:35"} +{"current_steps": 14, "total_steps": 309, "loss": 1.1392, "lr": 4.516129032258065e-06, "epoch": 0.13592233009708737, "percentage": 4.53, "elapsed_time": "0:12:16", "remaining_time": "4:18:46"} +{"current_steps": 15, "total_steps": 309, "loss": 1.0678, "lr": 4.838709677419355e-06, "epoch": 0.14563106796116504, "percentage": 4.85, "elapsed_time": "0:13:07", "remaining_time": "4:17:13"} +{"current_steps": 16, "total_steps": 309, "loss": 1.0683, "lr": 5.161290322580646e-06, "epoch": 0.1553398058252427, "percentage": 5.18, "elapsed_time": "0:13:52", "remaining_time": "4:14:08"} +{"current_steps": 17, "total_steps": 309, "loss": 1.0367, "lr": 5.483870967741935e-06, "epoch": 0.1650485436893204, "percentage": 5.5, "elapsed_time": "0:14:41", "remaining_time": "4:12:25"} +{"current_steps": 18, "total_steps": 309, "loss": 1.0401, "lr": 5.806451612903226e-06, "epoch": 0.17475728155339806, "percentage": 5.83, "elapsed_time": "0:15:29", "remaining_time": "4:10:29"} +{"current_steps": 19, "total_steps": 309, "loss": 1.0364, "lr": 6.129032258064517e-06, "epoch": 0.18446601941747573, "percentage": 6.15, "elapsed_time": "0:16:17", "remaining_time": "4:08:34"} +{"current_steps": 20, "total_steps": 309, "loss": 0.9807, "lr": 6.451612903225806e-06, "epoch": 0.1941747572815534, "percentage": 6.47, "elapsed_time": "0:17:05", "remaining_time": "4:07:01"} +{"current_steps": 21, "total_steps": 309, "loss": 1.0094, "lr": 6.774193548387097e-06, "epoch": 0.20388349514563106, "percentage": 6.8, "elapsed_time": "0:17:53", "remaining_time": "4:05:17"} +{"current_steps": 22, "total_steps": 309, "loss": 0.9756, "lr": 7.096774193548388e-06, "epoch": 0.21359223300970873, "percentage": 7.12, "elapsed_time": "0:18:33", "remaining_time": "4:02:04"} +{"current_steps": 23, "total_steps": 309, "loss": 1.0005, "lr": 7.4193548387096784e-06, "epoch": 0.22330097087378642, "percentage": 7.44, "elapsed_time": "0:19:25", "remaining_time": "4:01:28"} +{"current_steps": 24, "total_steps": 309, "loss": 0.9875, "lr": 7.741935483870968e-06, "epoch": 0.23300970873786409, "percentage": 7.77, "elapsed_time": "0:20:07", "remaining_time": "3:58:57"} +{"current_steps": 25, "total_steps": 309, "loss": 0.9444, "lr": 8.064516129032258e-06, "epoch": 0.24271844660194175, "percentage": 8.09, "elapsed_time": "0:20:56", "remaining_time": "3:57:56"} +{"current_steps": 26, "total_steps": 309, "loss": 0.9467, "lr": 8.387096774193549e-06, "epoch": 0.2524271844660194, "percentage": 8.41, "elapsed_time": "0:21:42", "remaining_time": "3:56:19"} +{"current_steps": 27, "total_steps": 309, "loss": 0.9549, "lr": 8.70967741935484e-06, "epoch": 0.2621359223300971, "percentage": 8.74, "elapsed_time": "0:22:35", "remaining_time": "3:55:53"} +{"current_steps": 28, "total_steps": 309, "loss": 0.9433, "lr": 9.03225806451613e-06, "epoch": 0.27184466019417475, "percentage": 9.06, "elapsed_time": "0:23:31", "remaining_time": "3:56:00"} +{"current_steps": 29, "total_steps": 309, "loss": 0.9353, "lr": 9.35483870967742e-06, "epoch": 0.2815533980582524, "percentage": 9.39, "elapsed_time": "0:24:24", "remaining_time": "3:55:36"} +{"current_steps": 30, "total_steps": 309, "loss": 0.9254, "lr": 9.67741935483871e-06, "epoch": 0.2912621359223301, "percentage": 9.71, "elapsed_time": "0:25:13", "remaining_time": "3:54:37"} +{"current_steps": 31, "total_steps": 309, "loss": 0.9231, "lr": 1e-05, "epoch": 0.30097087378640774, "percentage": 10.03, "elapsed_time": "0:26:02", "remaining_time": "3:53:34"} +{"current_steps": 32, "total_steps": 309, "loss": 0.9367, "lr": 9.999680739242022e-06, "epoch": 0.3106796116504854, "percentage": 10.36, "elapsed_time": "0:26:48", "remaining_time": "3:52:06"} +{"current_steps": 33, "total_steps": 309, "loss": 0.9194, "lr": 9.99872299773906e-06, "epoch": 0.32038834951456313, "percentage": 10.68, "elapsed_time": "0:27:39", "remaining_time": "3:51:15"} +{"current_steps": 34, "total_steps": 309, "loss": 0.8978, "lr": 9.997126897798826e-06, "epoch": 0.3300970873786408, "percentage": 11.0, "elapsed_time": "0:28:32", "remaining_time": "3:50:48"} +{"current_steps": 35, "total_steps": 309, "loss": 0.9046, "lr": 9.994892643250147e-06, "epoch": 0.33980582524271846, "percentage": 11.33, "elapsed_time": "0:29:29", "remaining_time": "3:50:56"} +{"current_steps": 36, "total_steps": 309, "loss": 0.9191, "lr": 9.99202051941695e-06, "epoch": 0.34951456310679613, "percentage": 11.65, "elapsed_time": "0:30:10", "remaining_time": "3:48:47"} +{"current_steps": 37, "total_steps": 309, "loss": 0.8796, "lr": 9.9885108930818e-06, "epoch": 0.3592233009708738, "percentage": 11.97, "elapsed_time": "0:30:55", "remaining_time": "3:47:17"} +{"current_steps": 38, "total_steps": 309, "loss": 0.9132, "lr": 9.984364212439089e-06, "epoch": 0.36893203883495146, "percentage": 12.3, "elapsed_time": "0:31:36", "remaining_time": "3:45:27"} +{"current_steps": 39, "total_steps": 309, "loss": 0.8933, "lr": 9.979581007037776e-06, "epoch": 0.3786407766990291, "percentage": 12.62, "elapsed_time": "0:32:20", "remaining_time": "3:43:56"} +{"current_steps": 40, "total_steps": 309, "loss": 0.9021, "lr": 9.974161887713775e-06, "epoch": 0.3883495145631068, "percentage": 12.94, "elapsed_time": "0:33:04", "remaining_time": "3:42:27"} +{"current_steps": 41, "total_steps": 309, "loss": 0.9121, "lr": 9.968107546511942e-06, "epoch": 0.39805825242718446, "percentage": 13.27, "elapsed_time": "0:33:56", "remaining_time": "3:41:50"} +{"current_steps": 42, "total_steps": 309, "loss": 0.9045, "lr": 9.961418756597703e-06, "epoch": 0.4077669902912621, "percentage": 13.59, "elapsed_time": "0:34:42", "remaining_time": "3:40:36"} +{"current_steps": 43, "total_steps": 309, "loss": 0.9019, "lr": 9.95409637215831e-06, "epoch": 0.4174757281553398, "percentage": 13.92, "elapsed_time": "0:35:32", "remaining_time": "3:39:53"} +{"current_steps": 44, "total_steps": 309, "loss": 0.8502, "lr": 9.94614132829377e-06, "epoch": 0.42718446601941745, "percentage": 14.24, "elapsed_time": "0:36:15", "remaining_time": "3:38:22"} +{"current_steps": 45, "total_steps": 309, "loss": 0.9056, "lr": 9.937554640897414e-06, "epoch": 0.4368932038834951, "percentage": 14.56, "elapsed_time": "0:37:04", "remaining_time": "3:37:31"} +{"current_steps": 46, "total_steps": 309, "loss": 0.8951, "lr": 9.928337406526172e-06, "epoch": 0.44660194174757284, "percentage": 14.89, "elapsed_time": "0:37:55", "remaining_time": "3:36:50"} +{"current_steps": 47, "total_steps": 309, "loss": 0.919, "lr": 9.918490802260538e-06, "epoch": 0.4563106796116505, "percentage": 15.21, "elapsed_time": "0:38:41", "remaining_time": "3:35:39"} +{"current_steps": 48, "total_steps": 309, "loss": 0.9086, "lr": 9.90801608555425e-06, "epoch": 0.46601941747572817, "percentage": 15.53, "elapsed_time": "0:39:36", "remaining_time": "3:35:20"} +{"current_steps": 49, "total_steps": 309, "loss": 0.8707, "lr": 9.896914594073703e-06, "epoch": 0.47572815533980584, "percentage": 15.86, "elapsed_time": "0:40:20", "remaining_time": "3:34:03"} +{"current_steps": 50, "total_steps": 309, "loss": 0.8903, "lr": 9.885187745527132e-06, "epoch": 0.4854368932038835, "percentage": 16.18, "elapsed_time": "0:41:07", "remaining_time": "3:33:01"} +{"current_steps": 51, "total_steps": 309, "loss": 0.8803, "lr": 9.87283703748356e-06, "epoch": 0.49514563106796117, "percentage": 16.5, "elapsed_time": "0:41:54", "remaining_time": "3:31:59"} +{"current_steps": 52, "total_steps": 309, "loss": 0.9034, "lr": 9.859864047181551e-06, "epoch": 0.5048543689320388, "percentage": 16.83, "elapsed_time": "0:42:40", "remaining_time": "3:30:54"} +{"current_steps": 53, "total_steps": 309, "loss": 0.8962, "lr": 9.846270431327793e-06, "epoch": 0.5145631067961165, "percentage": 17.15, "elapsed_time": "0:43:30", "remaining_time": "3:30:10"} +{"current_steps": 54, "total_steps": 309, "loss": 0.8834, "lr": 9.832057925885526e-06, "epoch": 0.5242718446601942, "percentage": 17.48, "elapsed_time": "0:44:17", "remaining_time": "3:29:09"} +{"current_steps": 55, "total_steps": 309, "loss": 0.9023, "lr": 9.817228345852853e-06, "epoch": 0.5339805825242718, "percentage": 17.8, "elapsed_time": "0:45:07", "remaining_time": "3:28:25"} +{"current_steps": 56, "total_steps": 309, "loss": 0.9119, "lr": 9.801783585030959e-06, "epoch": 0.5436893203883495, "percentage": 18.12, "elapsed_time": "0:46:01", "remaining_time": "3:27:56"} +{"current_steps": 57, "total_steps": 309, "loss": 0.8605, "lr": 9.785725615782262e-06, "epoch": 0.5533980582524272, "percentage": 18.45, "elapsed_time": "0:46:39", "remaining_time": "3:26:18"} +{"current_steps": 58, "total_steps": 309, "loss": 0.87, "lr": 9.769056488778538e-06, "epoch": 0.5631067961165048, "percentage": 18.77, "elapsed_time": "0:47:25", "remaining_time": "3:25:13"} +{"current_steps": 59, "total_steps": 309, "loss": 0.8863, "lr": 9.751778332739033e-06, "epoch": 0.5728155339805825, "percentage": 19.09, "elapsed_time": "0:48:10", "remaining_time": "3:24:06"} +{"current_steps": 60, "total_steps": 309, "loss": 0.8757, "lr": 9.733893354158628e-06, "epoch": 0.5825242718446602, "percentage": 19.42, "elapsed_time": "0:48:56", "remaining_time": "3:23:07"} +{"current_steps": 61, "total_steps": 309, "loss": 0.8613, "lr": 9.715403837026046e-06, "epoch": 0.5922330097087378, "percentage": 19.74, "elapsed_time": "0:49:37", "remaining_time": "3:21:43"} +{"current_steps": 62, "total_steps": 309, "loss": 0.8831, "lr": 9.69631214253219e-06, "epoch": 0.6019417475728155, "percentage": 20.06, "elapsed_time": "0:50:30", "remaining_time": "3:21:13"} +{"current_steps": 63, "total_steps": 309, "loss": 0.8823, "lr": 9.676620708768608e-06, "epoch": 0.6116504854368932, "percentage": 20.39, "elapsed_time": "0:51:18", "remaining_time": "3:20:20"} +{"current_steps": 64, "total_steps": 309, "loss": 0.8351, "lr": 9.656332050416118e-06, "epoch": 0.6213592233009708, "percentage": 20.71, "elapsed_time": "0:52:05", "remaining_time": "3:19:23"} +{"current_steps": 65, "total_steps": 309, "loss": 0.8792, "lr": 9.635448758423703e-06, "epoch": 0.6310679611650486, "percentage": 21.04, "elapsed_time": "0:52:50", "remaining_time": "3:18:21"} +{"current_steps": 66, "total_steps": 309, "loss": 0.912, "lr": 9.613973499677613e-06, "epoch": 0.6407766990291263, "percentage": 21.36, "elapsed_time": "0:53:43", "remaining_time": "3:17:49"} +{"current_steps": 67, "total_steps": 309, "loss": 0.8788, "lr": 9.591909016660806e-06, "epoch": 0.6504854368932039, "percentage": 21.68, "elapsed_time": "0:54:28", "remaining_time": "3:16:45"} +{"current_steps": 68, "total_steps": 309, "loss": 0.8965, "lr": 9.569258127102708e-06, "epoch": 0.6601941747572816, "percentage": 22.01, "elapsed_time": "0:55:18", "remaining_time": "3:16:02"} +{"current_steps": 69, "total_steps": 309, "loss": 0.8917, "lr": 9.546023723619387e-06, "epoch": 0.6699029126213593, "percentage": 22.33, "elapsed_time": "0:56:07", "remaining_time": "3:15:14"} +{"current_steps": 70, "total_steps": 309, "loss": 0.8872, "lr": 9.522208773344147e-06, "epoch": 0.6796116504854369, "percentage": 22.65, "elapsed_time": "0:56:51", "remaining_time": "3:14:07"} +{"current_steps": 71, "total_steps": 309, "loss": 0.8793, "lr": 9.497816317548625e-06, "epoch": 0.6893203883495146, "percentage": 22.98, "elapsed_time": "0:57:40", "remaining_time": "3:13:21"} +{"current_steps": 72, "total_steps": 309, "loss": 0.8539, "lr": 9.472849471254386e-06, "epoch": 0.6990291262135923, "percentage": 23.3, "elapsed_time": "0:58:28", "remaining_time": "3:12:29"} +{"current_steps": 73, "total_steps": 309, "loss": 0.8669, "lr": 9.447311422835141e-06, "epoch": 0.7087378640776699, "percentage": 23.62, "elapsed_time": "0:59:05", "remaining_time": "3:11:03"} +{"current_steps": 74, "total_steps": 309, "loss": 0.8991, "lr": 9.421205433609568e-06, "epoch": 0.7184466019417476, "percentage": 23.95, "elapsed_time": "0:59:55", "remaining_time": "3:10:18"} +{"current_steps": 75, "total_steps": 309, "loss": 0.8704, "lr": 9.39453483742483e-06, "epoch": 0.7281553398058253, "percentage": 24.27, "elapsed_time": "1:00:43", "remaining_time": "3:09:26"} +{"current_steps": 76, "total_steps": 309, "loss": 0.8866, "lr": 9.367303040230828e-06, "epoch": 0.7378640776699029, "percentage": 24.6, "elapsed_time": "1:01:29", "remaining_time": "3:08:32"} +{"current_steps": 77, "total_steps": 309, "loss": 0.8671, "lr": 9.33951351964525e-06, "epoch": 0.7475728155339806, "percentage": 24.92, "elapsed_time": "1:02:16", "remaining_time": "3:07:38"} +{"current_steps": 78, "total_steps": 309, "loss": 0.8435, "lr": 9.311169824509454e-06, "epoch": 0.7572815533980582, "percentage": 25.24, "elapsed_time": "1:03:05", "remaining_time": "3:06:52"} +{"current_steps": 79, "total_steps": 309, "loss": 0.8518, "lr": 9.28227557443528e-06, "epoch": 0.7669902912621359, "percentage": 25.57, "elapsed_time": "1:03:52", "remaining_time": "3:05:59"} +{"current_steps": 80, "total_steps": 309, "loss": 0.9034, "lr": 9.252834459342801e-06, "epoch": 0.7766990291262136, "percentage": 25.89, "elapsed_time": "1:04:39", "remaining_time": "3:05:05"} +{"current_steps": 81, "total_steps": 309, "loss": 0.8638, "lr": 9.222850238989104e-06, "epoch": 0.7864077669902912, "percentage": 26.21, "elapsed_time": "1:05:29", "remaining_time": "3:04:20"} +{"current_steps": 82, "total_steps": 309, "loss": 0.8658, "lr": 9.192326742488153e-06, "epoch": 0.7961165048543689, "percentage": 26.54, "elapsed_time": "1:06:16", "remaining_time": "3:03:28"} +{"current_steps": 83, "total_steps": 309, "loss": 0.8769, "lr": 9.161267867821802e-06, "epoch": 0.8058252427184466, "percentage": 26.86, "elapsed_time": "1:07:01", "remaining_time": "3:02:31"} +{"current_steps": 84, "total_steps": 309, "loss": 0.8677, "lr": 9.129677581342e-06, "epoch": 0.8155339805825242, "percentage": 27.18, "elapsed_time": "1:07:43", "remaining_time": "3:01:25"} +{"current_steps": 85, "total_steps": 309, "loss": 0.8465, "lr": 9.097559917264268e-06, "epoch": 0.8252427184466019, "percentage": 27.51, "elapsed_time": "1:08:31", "remaining_time": "3:00:35"} +{"current_steps": 86, "total_steps": 309, "loss": 0.8741, "lr": 9.064918977152517e-06, "epoch": 0.8349514563106796, "percentage": 27.83, "elapsed_time": "1:09:11", "remaining_time": "2:59:24"} +{"current_steps": 87, "total_steps": 309, "loss": 0.8248, "lr": 9.031758929395259e-06, "epoch": 0.8446601941747572, "percentage": 28.16, "elapsed_time": "1:09:50", "remaining_time": "2:58:12"} +{"current_steps": 88, "total_steps": 309, "loss": 0.8398, "lr": 8.998084008673284e-06, "epoch": 0.8543689320388349, "percentage": 28.48, "elapsed_time": "1:10:38", "remaining_time": "2:57:24"} +{"current_steps": 89, "total_steps": 309, "loss": 0.8687, "lr": 8.963898515418885e-06, "epoch": 0.8640776699029126, "percentage": 28.8, "elapsed_time": "1:11:23", "remaining_time": "2:56:27"} +{"current_steps": 90, "total_steps": 309, "loss": 0.8639, "lr": 8.929206815266653e-06, "epoch": 0.8737864077669902, "percentage": 29.13, "elapsed_time": "1:12:16", "remaining_time": "2:55:51"} +{"current_steps": 91, "total_steps": 309, "loss": 0.8483, "lr": 8.89401333849598e-06, "epoch": 0.883495145631068, "percentage": 29.45, "elapsed_time": "1:13:00", "remaining_time": "2:54:54"} +{"current_steps": 92, "total_steps": 309, "loss": 0.9039, "lr": 8.8583225794653e-06, "epoch": 0.8932038834951457, "percentage": 29.77, "elapsed_time": "1:13:40", "remaining_time": "2:53:47"} +{"current_steps": 93, "total_steps": 309, "loss": 0.8814, "lr": 8.82213909603812e-06, "epoch": 0.9029126213592233, "percentage": 30.1, "elapsed_time": "1:14:29", "remaining_time": "2:53:00"} +{"current_steps": 94, "total_steps": 309, "loss": 0.8944, "lr": 8.78546750900098e-06, "epoch": 0.912621359223301, "percentage": 30.42, "elapsed_time": "1:15:28", "remaining_time": "2:52:37"} +{"current_steps": 95, "total_steps": 309, "loss": 0.8819, "lr": 8.748312501473351e-06, "epoch": 0.9223300970873787, "percentage": 30.74, "elapsed_time": "1:16:18", "remaining_time": "2:51:52"} +{"current_steps": 96, "total_steps": 309, "loss": 0.8582, "lr": 8.710678818309576e-06, "epoch": 0.9320388349514563, "percentage": 31.07, "elapsed_time": "1:17:02", "remaining_time": "2:50:55"} +{"current_steps": 97, "total_steps": 309, "loss": 0.8361, "lr": 8.672571265492944e-06, "epoch": 0.941747572815534, "percentage": 31.39, "elapsed_time": "1:17:47", "remaining_time": "2:50:01"} +{"current_steps": 98, "total_steps": 309, "loss": 0.8679, "lr": 8.63399470952193e-06, "epoch": 0.9514563106796117, "percentage": 31.72, "elapsed_time": "1:18:32", "remaining_time": "2:49:05"} +{"current_steps": 99, "total_steps": 309, "loss": 0.8182, "lr": 8.594954076788736e-06, "epoch": 0.9611650485436893, "percentage": 32.04, "elapsed_time": "1:19:13", "remaining_time": "2:48:02"} +{"current_steps": 100, "total_steps": 309, "loss": 0.8622, "lr": 8.555454352950161e-06, "epoch": 0.970873786407767, "percentage": 32.36, "elapsed_time": "1:20:01", "remaining_time": "2:47:15"} +{"current_steps": 101, "total_steps": 309, "loss": 0.845, "lr": 8.515500582290914e-06, "epoch": 0.9805825242718447, "percentage": 32.69, "elapsed_time": "1:20:42", "remaining_time": "2:46:13"} +{"current_steps": 102, "total_steps": 309, "loss": 0.8672, "lr": 8.475097867079437e-06, "epoch": 0.9902912621359223, "percentage": 33.01, "elapsed_time": "1:21:36", "remaining_time": "2:45:37"} +{"current_steps": 103, "total_steps": 309, "loss": 0.8989, "lr": 8.434251366916323e-06, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "1:22:25", "remaining_time": "2:44:50"} +{"current_steps": 104, "total_steps": 309, "loss": 0.8642, "lr": 8.392966298075413e-06, "epoch": 1.0097087378640777, "percentage": 33.66, "elapsed_time": "1:24:22", "remaining_time": "2:46:18"} +{"current_steps": 105, "total_steps": 309, "loss": 0.8001, "lr": 8.351247932837655e-06, "epoch": 1.0194174757281553, "percentage": 33.98, "elapsed_time": "1:25:11", "remaining_time": "2:45:30"} +{"current_steps": 106, "total_steps": 309, "loss": 0.8101, "lr": 8.309101598817812e-06, "epoch": 1.029126213592233, "percentage": 34.3, "elapsed_time": "1:26:00", "remaining_time": "2:44:43"} +{"current_steps": 107, "total_steps": 309, "loss": 0.7936, "lr": 8.266532678284103e-06, "epoch": 1.0388349514563107, "percentage": 34.63, "elapsed_time": "1:26:44", "remaining_time": "2:43:44"} +{"current_steps": 108, "total_steps": 309, "loss": 0.8278, "lr": 8.223546607470863e-06, "epoch": 1.0485436893203883, "percentage": 34.95, "elapsed_time": "1:27:30", "remaining_time": "2:42:50"} +{"current_steps": 109, "total_steps": 309, "loss": 0.8272, "lr": 8.18014887588431e-06, "epoch": 1.058252427184466, "percentage": 35.28, "elapsed_time": "1:28:22", "remaining_time": "2:42:09"} +{"current_steps": 110, "total_steps": 309, "loss": 0.8485, "lr": 8.13634502560152e-06, "epoch": 1.0679611650485437, "percentage": 35.6, "elapsed_time": "1:29:12", "remaining_time": "2:41:24"} +{"current_steps": 111, "total_steps": 309, "loss": 0.7722, "lr": 8.092140650562665e-06, "epoch": 1.0776699029126213, "percentage": 35.92, "elapsed_time": "1:29:56", "remaining_time": "2:40:26"} +{"current_steps": 112, "total_steps": 309, "loss": 0.8361, "lr": 8.047541395856661e-06, "epoch": 1.087378640776699, "percentage": 36.25, "elapsed_time": "1:30:37", "remaining_time": "2:39:23"} +{"current_steps": 113, "total_steps": 309, "loss": 0.8157, "lr": 8.002552957000254e-06, "epoch": 1.0970873786407767, "percentage": 36.57, "elapsed_time": "1:31:31", "remaining_time": "2:38:45"} +{"current_steps": 114, "total_steps": 309, "loss": 0.819, "lr": 7.957181079210676e-06, "epoch": 1.1067961165048543, "percentage": 36.89, "elapsed_time": "1:32:25", "remaining_time": "2:38:06"} +{"current_steps": 115, "total_steps": 309, "loss": 0.8191, "lr": 7.911431556671967e-06, "epoch": 1.116504854368932, "percentage": 37.22, "elapsed_time": "1:33:10", "remaining_time": "2:37:11"} +{"current_steps": 116, "total_steps": 309, "loss": 0.8084, "lr": 7.865310231795026e-06, "epoch": 1.1262135922330097, "percentage": 37.54, "elapsed_time": "1:33:51", "remaining_time": "2:36:10"} +{"current_steps": 117, "total_steps": 309, "loss": 0.8088, "lr": 7.818822994471504e-06, "epoch": 1.1359223300970873, "percentage": 37.86, "elapsed_time": "1:34:37", "remaining_time": "2:35:17"} +{"current_steps": 118, "total_steps": 309, "loss": 0.8236, "lr": 7.771975781321655e-06, "epoch": 1.145631067961165, "percentage": 38.19, "elapsed_time": "1:35:23", "remaining_time": "2:34:24"} +{"current_steps": 119, "total_steps": 309, "loss": 0.8427, "lr": 7.72477457493619e-06, "epoch": 1.1553398058252426, "percentage": 38.51, "elapsed_time": "1:36:17", "remaining_time": "2:33:45"} +{"current_steps": 120, "total_steps": 309, "loss": 0.8204, "lr": 7.677225403112277e-06, "epoch": 1.1650485436893203, "percentage": 38.83, "elapsed_time": "1:37:09", "remaining_time": "2:33:02"} +{"current_steps": 121, "total_steps": 309, "loss": 0.7887, "lr": 7.629334338083774e-06, "epoch": 1.174757281553398, "percentage": 39.16, "elapsed_time": "1:37:56", "remaining_time": "2:32:10"} +{"current_steps": 122, "total_steps": 309, "loss": 0.8137, "lr": 7.58110749574577e-06, "epoch": 1.1844660194174756, "percentage": 39.48, "elapsed_time": "1:38:43", "remaining_time": "2:31:19"} +{"current_steps": 123, "total_steps": 309, "loss": 0.7985, "lr": 7.532551034873558e-06, "epoch": 1.1941747572815533, "percentage": 39.81, "elapsed_time": "1:39:30", "remaining_time": "2:30:28"} +{"current_steps": 124, "total_steps": 309, "loss": 0.8108, "lr": 7.483671156336142e-06, "epoch": 1.203883495145631, "percentage": 40.13, "elapsed_time": "1:40:14", "remaining_time": "2:29:32"} +{"current_steps": 125, "total_steps": 309, "loss": 0.8161, "lr": 7.43447410230435e-06, "epoch": 1.2135922330097086, "percentage": 40.45, "elapsed_time": "1:41:04", "remaining_time": "2:28:46"} +{"current_steps": 126, "total_steps": 309, "loss": 0.7965, "lr": 7.384966155453686e-06, "epoch": 1.2233009708737863, "percentage": 40.78, "elapsed_time": "1:41:47", "remaining_time": "2:27:50"} +{"current_steps": 127, "total_steps": 309, "loss": 0.7989, "lr": 7.335153638162005e-06, "epoch": 1.233009708737864, "percentage": 41.1, "elapsed_time": "1:42:33", "remaining_time": "2:26:59"} +{"current_steps": 128, "total_steps": 309, "loss": 0.7812, "lr": 7.285042911702116e-06, "epoch": 1.2427184466019416, "percentage": 41.42, "elapsed_time": "1:43:20", "remaining_time": "2:26:08"} +{"current_steps": 129, "total_steps": 309, "loss": 0.8034, "lr": 7.234640375429427e-06, "epoch": 1.2524271844660193, "percentage": 41.75, "elapsed_time": "1:44:10", "remaining_time": "2:25:21"} +{"current_steps": 130, "total_steps": 309, "loss": 0.8004, "lr": 7.183952465964711e-06, "epoch": 1.262135922330097, "percentage": 42.07, "elapsed_time": "1:44:59", "remaining_time": "2:24:34"} +{"current_steps": 131, "total_steps": 309, "loss": 0.8122, "lr": 7.132985656372126e-06, "epoch": 1.2718446601941746, "percentage": 42.39, "elapsed_time": "1:45:42", "remaining_time": "2:23:37"} +{"current_steps": 132, "total_steps": 309, "loss": 0.8256, "lr": 7.0817464553325764e-06, "epoch": 1.2815533980582523, "percentage": 42.72, "elapsed_time": "1:46:29", "remaining_time": "2:22:47"} +{"current_steps": 133, "total_steps": 309, "loss": 0.8012, "lr": 7.030241406312528e-06, "epoch": 1.29126213592233, "percentage": 43.04, "elapsed_time": "1:47:14", "remaining_time": "2:21:54"} +{"current_steps": 134, "total_steps": 309, "loss": 0.7475, "lr": 6.978477086728375e-06, "epoch": 1.3009708737864076, "percentage": 43.37, "elapsed_time": "1:47:49", "remaining_time": "2:20:48"} +{"current_steps": 135, "total_steps": 309, "loss": 0.7631, "lr": 6.926460107106483e-06, "epoch": 1.3106796116504853, "percentage": 43.69, "elapsed_time": "1:48:32", "remaining_time": "2:19:54"} +{"current_steps": 136, "total_steps": 309, "loss": 0.7626, "lr": 6.874197110238986e-06, "epoch": 1.3203883495145632, "percentage": 44.01, "elapsed_time": "1:49:16", "remaining_time": "2:19:00"} +{"current_steps": 137, "total_steps": 309, "loss": 0.809, "lr": 6.8216947703354815e-06, "epoch": 1.3300970873786409, "percentage": 44.34, "elapsed_time": "1:50:01", "remaining_time": "2:18:08"} +{"current_steps": 138, "total_steps": 309, "loss": 0.8311, "lr": 6.7689597921707065e-06, "epoch": 1.3398058252427185, "percentage": 44.66, "elapsed_time": "1:50:58", "remaining_time": "2:17:30"} +{"current_steps": 139, "total_steps": 309, "loss": 0.7949, "lr": 6.715998910228296e-06, "epoch": 1.3495145631067962, "percentage": 44.98, "elapsed_time": "1:51:40", "remaining_time": "2:16:35"} +{"current_steps": 140, "total_steps": 309, "loss": 0.794, "lr": 6.6628188878407806e-06, "epoch": 1.3592233009708738, "percentage": 45.31, "elapsed_time": "1:52:35", "remaining_time": "2:15:54"} +{"current_steps": 141, "total_steps": 309, "loss": 0.8329, "lr": 6.609426516325859e-06, "epoch": 1.3689320388349515, "percentage": 45.63, "elapsed_time": "1:53:25", "remaining_time": "2:15:09"} +{"current_steps": 142, "total_steps": 309, "loss": 0.8136, "lr": 6.555828614119132e-06, "epoch": 1.3786407766990292, "percentage": 45.95, "elapsed_time": "1:54:17", "remaining_time": "2:14:24"} +{"current_steps": 143, "total_steps": 309, "loss": 0.7576, "lr": 6.502032025903356e-06, "epoch": 1.3883495145631068, "percentage": 46.28, "elapsed_time": "1:55:00", "remaining_time": "2:13:30"} +{"current_steps": 144, "total_steps": 309, "loss": 0.8205, "lr": 6.4480436217343366e-06, "epoch": 1.3980582524271845, "percentage": 46.6, "elapsed_time": "1:55:46", "remaining_time": "2:12:39"} +{"current_steps": 145, "total_steps": 309, "loss": 0.8104, "lr": 6.393870296163616e-06, "epoch": 1.4077669902912622, "percentage": 46.93, "elapsed_time": "1:56:37", "remaining_time": "2:11:54"} +{"current_steps": 146, "total_steps": 309, "loss": 0.7822, "lr": 6.339518967357985e-06, "epoch": 1.4174757281553398, "percentage": 47.25, "elapsed_time": "1:57:32", "remaining_time": "2:11:13"} +{"current_steps": 147, "total_steps": 309, "loss": 0.8227, "lr": 6.284996576216014e-06, "epoch": 1.4271844660194175, "percentage": 47.57, "elapsed_time": "1:58:21", "remaining_time": "2:10:26"} +{"current_steps": 148, "total_steps": 309, "loss": 0.8005, "lr": 6.230310085481677e-06, "epoch": 1.4368932038834952, "percentage": 47.9, "elapsed_time": "1:59:18", "remaining_time": "2:09:47"} +{"current_steps": 149, "total_steps": 309, "loss": 0.7936, "lr": 6.175466478855161e-06, "epoch": 1.4466019417475728, "percentage": 48.22, "elapsed_time": "1:59:57", "remaining_time": "2:08:48"} +{"current_steps": 150, "total_steps": 309, "loss": 0.7473, "lr": 6.1204727601010396e-06, "epoch": 1.4563106796116505, "percentage": 48.54, "elapsed_time": "2:00:41", "remaining_time": "2:07:55"} +{"current_steps": 151, "total_steps": 309, "loss": 0.7974, "lr": 6.065335952153846e-06, "epoch": 1.4660194174757282, "percentage": 48.87, "elapsed_time": "2:01:37", "remaining_time": "2:07:15"} +{"current_steps": 152, "total_steps": 309, "loss": 0.7921, "lr": 6.010063096221215e-06, "epoch": 1.4757281553398058, "percentage": 49.19, "elapsed_time": "2:02:33", "remaining_time": "2:06:35"} +{"current_steps": 153, "total_steps": 309, "loss": 0.7822, "lr": 5.954661250884704e-06, "epoch": 1.4854368932038835, "percentage": 49.51, "elapsed_time": "2:03:16", "remaining_time": "2:05:41"} +{"current_steps": 154, "total_steps": 309, "loss": 0.8273, "lr": 5.899137491198364e-06, "epoch": 1.4951456310679612, "percentage": 49.84, "elapsed_time": "2:04:02", "remaining_time": "2:04:50"} +{"current_steps": 155, "total_steps": 309, "loss": 0.7979, "lr": 5.843498907785236e-06, "epoch": 1.5048543689320388, "percentage": 50.16, "elapsed_time": "2:04:48", "remaining_time": "2:04:00"} +{"current_steps": 156, "total_steps": 309, "loss": 0.8198, "lr": 5.78775260593185e-06, "epoch": 1.5145631067961165, "percentage": 50.49, "elapsed_time": "2:05:33", "remaining_time": "2:03:08"} +{"current_steps": 157, "total_steps": 309, "loss": 0.8023, "lr": 5.731905704680834e-06, "epoch": 1.5242718446601942, "percentage": 50.81, "elapsed_time": "2:06:16", "remaining_time": "2:02:15"} +{"current_steps": 158, "total_steps": 309, "loss": 0.8231, "lr": 5.6759653359218e-06, "epoch": 1.5339805825242718, "percentage": 51.13, "elapsed_time": "2:07:10", "remaining_time": "2:01:32"} +{"current_steps": 159, "total_steps": 309, "loss": 0.7984, "lr": 5.6199386434805615e-06, "epoch": 1.5436893203883495, "percentage": 51.46, "elapsed_time": "2:07:56", "remaining_time": "2:00:42"} +{"current_steps": 160, "total_steps": 309, "loss": 0.7975, "lr": 5.563832782206835e-06, "epoch": 1.5533980582524272, "percentage": 51.78, "elapsed_time": "2:08:45", "remaining_time": "1:59:54"} +{"current_steps": 161, "total_steps": 309, "loss": 0.824, "lr": 5.507654917060541e-06, "epoch": 1.5631067961165048, "percentage": 52.1, "elapsed_time": "2:09:43", "remaining_time": "1:59:15"} +{"current_steps": 162, "total_steps": 309, "loss": 0.7844, "lr": 5.451412222196801e-06, "epoch": 1.5728155339805825, "percentage": 52.43, "elapsed_time": "2:10:20", "remaining_time": "1:58:16"} +{"current_steps": 163, "total_steps": 309, "loss": 0.7946, "lr": 5.395111880049775e-06, "epoch": 1.5825242718446602, "percentage": 52.75, "elapsed_time": "2:11:06", "remaining_time": "1:57:26"} +{"current_steps": 164, "total_steps": 309, "loss": 0.8035, "lr": 5.338761080415425e-06, "epoch": 1.5922330097087378, "percentage": 53.07, "elapsed_time": "2:11:56", "remaining_time": "1:56:39"} +{"current_steps": 165, "total_steps": 309, "loss": 0.7802, "lr": 5.28236701953335e-06, "epoch": 1.6019417475728155, "percentage": 53.4, "elapsed_time": "2:12:41", "remaining_time": "1:55:48"} +{"current_steps": 166, "total_steps": 309, "loss": 0.8301, "lr": 5.225936899167803e-06, "epoch": 1.6116504854368932, "percentage": 53.72, "elapsed_time": "2:13:34", "remaining_time": "1:55:04"} +{"current_steps": 167, "total_steps": 309, "loss": 0.7875, "lr": 5.169477925687981e-06, "epoch": 1.6213592233009708, "percentage": 54.05, "elapsed_time": "2:14:29", "remaining_time": "1:54:21"} +{"current_steps": 168, "total_steps": 309, "loss": 0.8003, "lr": 5.112997309147753e-06, "epoch": 1.6310679611650487, "percentage": 54.37, "elapsed_time": "2:15:15", "remaining_time": "1:53:31"} +{"current_steps": 169, "total_steps": 309, "loss": 0.8094, "lr": 5.0565022623649e-06, "epoch": 1.6407766990291264, "percentage": 54.69, "elapsed_time": "2:15:57", "remaining_time": "1:52:37"} +{"current_steps": 170, "total_steps": 309, "loss": 0.7756, "lr": 5e-06, "epoch": 1.650485436893204, "percentage": 55.02, "elapsed_time": "2:16:37", "remaining_time": "1:51:42"} +{"current_steps": 171, "total_steps": 309, "loss": 0.8081, "lr": 4.943497737635103e-06, "epoch": 1.6601941747572817, "percentage": 55.34, "elapsed_time": "2:17:31", "remaining_time": "1:50:58"} +{"current_steps": 172, "total_steps": 309, "loss": 0.8025, "lr": 4.887002690852249e-06, "epoch": 1.6699029126213594, "percentage": 55.66, "elapsed_time": "2:18:14", "remaining_time": "1:50:06"} +{"current_steps": 173, "total_steps": 309, "loss": 0.8068, "lr": 4.830522074312019e-06, "epoch": 1.679611650485437, "percentage": 55.99, "elapsed_time": "2:18:58", "remaining_time": "1:49:15"} +{"current_steps": 174, "total_steps": 309, "loss": 0.8078, "lr": 4.774063100832199e-06, "epoch": 1.6893203883495147, "percentage": 56.31, "elapsed_time": "2:19:53", "remaining_time": "1:48:32"} +{"current_steps": 175, "total_steps": 309, "loss": 0.8529, "lr": 4.717632980466652e-06, "epoch": 1.6990291262135924, "percentage": 56.63, "elapsed_time": "2:20:46", "remaining_time": "1:47:47"} +{"current_steps": 176, "total_steps": 309, "loss": 0.7914, "lr": 4.661238919584578e-06, "epoch": 1.70873786407767, "percentage": 56.96, "elapsed_time": "2:21:38", "remaining_time": "1:47:02"} +{"current_steps": 177, "total_steps": 309, "loss": 0.8377, "lr": 4.6048881199502265e-06, "epoch": 1.7184466019417477, "percentage": 57.28, "elapsed_time": "2:22:43", "remaining_time": "1:46:26"} +{"current_steps": 178, "total_steps": 309, "loss": 0.841, "lr": 4.548587777803198e-06, "epoch": 1.7281553398058254, "percentage": 57.61, "elapsed_time": "2:23:28", "remaining_time": "1:45:35"} +{"current_steps": 179, "total_steps": 309, "loss": 0.8118, "lr": 4.49234508293946e-06, "epoch": 1.737864077669903, "percentage": 57.93, "elapsed_time": "2:24:18", "remaining_time": "1:44:48"} +{"current_steps": 180, "total_steps": 309, "loss": 0.8091, "lr": 4.436167217793167e-06, "epoch": 1.7475728155339807, "percentage": 58.25, "elapsed_time": "2:25:07", "remaining_time": "1:44:00"} +{"current_steps": 181, "total_steps": 309, "loss": 0.8012, "lr": 4.38006135651944e-06, "epoch": 1.7572815533980584, "percentage": 58.58, "elapsed_time": "2:25:56", "remaining_time": "1:43:12"} +{"current_steps": 182, "total_steps": 309, "loss": 0.7779, "lr": 4.3240346640782014e-06, "epoch": 1.766990291262136, "percentage": 58.9, "elapsed_time": "2:26:31", "remaining_time": "1:42:14"} +{"current_steps": 183, "total_steps": 309, "loss": 0.8184, "lr": 4.268094295319167e-06, "epoch": 1.7766990291262137, "percentage": 59.22, "elapsed_time": "2:27:18", "remaining_time": "1:41:25"} +{"current_steps": 184, "total_steps": 309, "loss": 0.8109, "lr": 4.212247394068151e-06, "epoch": 1.7864077669902914, "percentage": 59.55, "elapsed_time": "2:28:09", "remaining_time": "1:40:38"} +{"current_steps": 185, "total_steps": 309, "loss": 0.8068, "lr": 4.1565010922147644e-06, "epoch": 1.796116504854369, "percentage": 59.87, "elapsed_time": "2:29:04", "remaining_time": "1:39:55"} +{"current_steps": 186, "total_steps": 309, "loss": 0.8158, "lr": 4.100862508801639e-06, "epoch": 1.8058252427184467, "percentage": 60.19, "elapsed_time": "2:29:48", "remaining_time": "1:39:04"} +{"current_steps": 187, "total_steps": 309, "loss": 0.8012, "lr": 4.045338749115299e-06, "epoch": 1.8155339805825244, "percentage": 60.52, "elapsed_time": "2:30:28", "remaining_time": "1:38:10"} +{"current_steps": 188, "total_steps": 309, "loss": 0.8276, "lr": 3.989936903778785e-06, "epoch": 1.825242718446602, "percentage": 60.84, "elapsed_time": "2:31:26", "remaining_time": "1:37:28"} +{"current_steps": 189, "total_steps": 309, "loss": 0.7817, "lr": 3.934664047846157e-06, "epoch": 1.8349514563106797, "percentage": 61.17, "elapsed_time": "2:32:21", "remaining_time": "1:36:44"} +{"current_steps": 190, "total_steps": 309, "loss": 0.8325, "lr": 3.879527239898962e-06, "epoch": 1.8446601941747574, "percentage": 61.49, "elapsed_time": "2:33:17", "remaining_time": "1:36:00"} +{"current_steps": 191, "total_steps": 309, "loss": 0.7786, "lr": 3.8245335211448404e-06, "epoch": 1.854368932038835, "percentage": 61.81, "elapsed_time": "2:34:06", "remaining_time": "1:35:12"} +{"current_steps": 192, "total_steps": 309, "loss": 0.8142, "lr": 3.769689914518326e-06, "epoch": 1.8640776699029127, "percentage": 62.14, "elapsed_time": "2:35:02", "remaining_time": "1:34:28"} +{"current_steps": 193, "total_steps": 309, "loss": 0.7969, "lr": 3.715003423783986e-06, "epoch": 1.8737864077669903, "percentage": 62.46, "elapsed_time": "2:35:50", "remaining_time": "1:33:39"} +{"current_steps": 194, "total_steps": 309, "loss": 0.7949, "lr": 3.660481032642016e-06, "epoch": 1.883495145631068, "percentage": 62.78, "elapsed_time": "2:36:35", "remaining_time": "1:32:49"} +{"current_steps": 195, "total_steps": 309, "loss": 0.7786, "lr": 3.6061297038363853e-06, "epoch": 1.8932038834951457, "percentage": 63.11, "elapsed_time": "2:37:11", "remaining_time": "1:31:53"} +{"current_steps": 196, "total_steps": 309, "loss": 0.8131, "lr": 3.5519563782656642e-06, "epoch": 1.9029126213592233, "percentage": 63.43, "elapsed_time": "2:38:02", "remaining_time": "1:31:06"} +{"current_steps": 197, "total_steps": 309, "loss": 0.7723, "lr": 3.497967974096647e-06, "epoch": 1.912621359223301, "percentage": 63.75, "elapsed_time": "2:38:49", "remaining_time": "1:30:17"} +{"current_steps": 198, "total_steps": 309, "loss": 0.793, "lr": 3.4441713858808684e-06, "epoch": 1.9223300970873787, "percentage": 64.08, "elapsed_time": "2:39:32", "remaining_time": "1:29:26"} +{"current_steps": 199, "total_steps": 309, "loss": 0.8259, "lr": 3.3905734836741415e-06, "epoch": 1.9320388349514563, "percentage": 64.4, "elapsed_time": "2:40:27", "remaining_time": "1:28:41"} +{"current_steps": 200, "total_steps": 309, "loss": 0.7691, "lr": 3.3371811121592203e-06, "epoch": 1.941747572815534, "percentage": 64.72, "elapsed_time": "2:41:19", "remaining_time": "1:27:55"} +{"current_steps": 201, "total_steps": 309, "loss": 0.7592, "lr": 3.2840010897717045e-06, "epoch": 1.9514563106796117, "percentage": 65.05, "elapsed_time": "2:41:56", "remaining_time": "1:27:00"} +{"current_steps": 202, "total_steps": 309, "loss": 0.806, "lr": 3.2310402078292956e-06, "epoch": 1.9611650485436893, "percentage": 65.37, "elapsed_time": "2:42:44", "remaining_time": "1:26:12"} +{"current_steps": 203, "total_steps": 309, "loss": 0.8302, "lr": 3.178305229664519e-06, "epoch": 1.970873786407767, "percentage": 65.7, "elapsed_time": "2:43:30", "remaining_time": "1:25:22"} +{"current_steps": 204, "total_steps": 309, "loss": 0.7726, "lr": 3.125802889761016e-06, "epoch": 1.9805825242718447, "percentage": 66.02, "elapsed_time": "2:44:20", "remaining_time": "1:24:35"} +{"current_steps": 205, "total_steps": 309, "loss": 0.8098, "lr": 3.073539892893519e-06, "epoch": 1.9902912621359223, "percentage": 66.34, "elapsed_time": "2:45:19", "remaining_time": "1:23:52"} +{"current_steps": 206, "total_steps": 309, "loss": 0.7834, "lr": 3.021522913271627e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "2:45:54", "remaining_time": "1:22:57"} +{"current_steps": 207, "total_steps": 309, "loss": 0.7591, "lr": 2.969758593687475e-06, "epoch": 2.0097087378640777, "percentage": 66.99, "elapsed_time": "2:47:58", "remaining_time": "1:22:46"} +{"current_steps": 208, "total_steps": 309, "loss": 0.7803, "lr": 2.9182535446674244e-06, "epoch": 2.0194174757281553, "percentage": 67.31, "elapsed_time": "2:48:50", "remaining_time": "1:21:59"} +{"current_steps": 209, "total_steps": 309, "loss": 0.7553, "lr": 2.8670143436278757e-06, "epoch": 2.029126213592233, "percentage": 67.64, "elapsed_time": "2:49:40", "remaining_time": "1:21:11"} +{"current_steps": 210, "total_steps": 309, "loss": 0.7849, "lr": 2.8160475340352913e-06, "epoch": 2.0388349514563107, "percentage": 67.96, "elapsed_time": "2:50:24", "remaining_time": "1:20:20"} +{"current_steps": 211, "total_steps": 309, "loss": 0.7618, "lr": 2.765359624570574e-06, "epoch": 2.0485436893203883, "percentage": 68.28, "elapsed_time": "2:51:24", "remaining_time": "1:19:36"} +{"current_steps": 212, "total_steps": 309, "loss": 0.6928, "lr": 2.714957088297886e-06, "epoch": 2.058252427184466, "percentage": 68.61, "elapsed_time": "2:52:09", "remaining_time": "1:18:46"} +{"current_steps": 213, "total_steps": 309, "loss": 0.7647, "lr": 2.664846361837997e-06, "epoch": 2.0679611650485437, "percentage": 68.93, "elapsed_time": "2:52:55", "remaining_time": "1:17:56"} +{"current_steps": 214, "total_steps": 309, "loss": 0.7537, "lr": 2.6150338445463146e-06, "epoch": 2.0776699029126213, "percentage": 69.26, "elapsed_time": "2:53:39", "remaining_time": "1:17:05"} +{"current_steps": 215, "total_steps": 309, "loss": 0.7775, "lr": 2.565525897695651e-06, "epoch": 2.087378640776699, "percentage": 69.58, "elapsed_time": "2:54:30", "remaining_time": "1:16:17"} +{"current_steps": 216, "total_steps": 309, "loss": 0.7784, "lr": 2.51632884366386e-06, "epoch": 2.0970873786407767, "percentage": 69.9, "elapsed_time": "2:55:12", "remaining_time": "1:15:26"} +{"current_steps": 217, "total_steps": 309, "loss": 0.7207, "lr": 2.4674489651264433e-06, "epoch": 2.1067961165048543, "percentage": 70.23, "elapsed_time": "2:56:03", "remaining_time": "1:14:38"} +{"current_steps": 218, "total_steps": 309, "loss": 0.7493, "lr": 2.418892504254231e-06, "epoch": 2.116504854368932, "percentage": 70.55, "elapsed_time": "2:56:57", "remaining_time": "1:13:52"} +{"current_steps": 219, "total_steps": 309, "loss": 0.7775, "lr": 2.3706656619162278e-06, "epoch": 2.1262135922330097, "percentage": 70.87, "elapsed_time": "2:57:44", "remaining_time": "1:13:02"} +{"current_steps": 220, "total_steps": 309, "loss": 0.7594, "lr": 2.322774596887726e-06, "epoch": 2.1359223300970873, "percentage": 71.2, "elapsed_time": "2:58:41", "remaining_time": "1:12:17"} +{"current_steps": 221, "total_steps": 309, "loss": 0.7265, "lr": 2.275225425063813e-06, "epoch": 2.145631067961165, "percentage": 71.52, "elapsed_time": "2:59:30", "remaining_time": "1:11:28"} +{"current_steps": 222, "total_steps": 309, "loss": 0.7149, "lr": 2.2280242186783473e-06, "epoch": 2.1553398058252426, "percentage": 71.84, "elapsed_time": "3:00:22", "remaining_time": "1:10:41"} +{"current_steps": 223, "total_steps": 309, "loss": 0.7902, "lr": 2.1811770055284968e-06, "epoch": 2.1650485436893203, "percentage": 72.17, "elapsed_time": "3:01:15", "remaining_time": "1:09:53"} +{"current_steps": 224, "total_steps": 309, "loss": 0.7583, "lr": 2.134689768204975e-06, "epoch": 2.174757281553398, "percentage": 72.49, "elapsed_time": "3:01:58", "remaining_time": "1:09:03"} +{"current_steps": 225, "total_steps": 309, "loss": 0.7717, "lr": 2.0885684433280336e-06, "epoch": 2.1844660194174756, "percentage": 72.82, "elapsed_time": "3:02:48", "remaining_time": "1:08:14"} +{"current_steps": 226, "total_steps": 309, "loss": 0.7622, "lr": 2.042818920789326e-06, "epoch": 2.1941747572815533, "percentage": 73.14, "elapsed_time": "3:03:28", "remaining_time": "1:07:23"} +{"current_steps": 227, "total_steps": 309, "loss": 0.7508, "lr": 1.9974470429997482e-06, "epoch": 2.203883495145631, "percentage": 73.46, "elapsed_time": "3:04:14", "remaining_time": "1:06:33"} +{"current_steps": 228, "total_steps": 309, "loss": 0.7132, "lr": 1.9524586041433393e-06, "epoch": 2.2135922330097086, "percentage": 73.79, "elapsed_time": "3:05:03", "remaining_time": "1:05:44"} +{"current_steps": 229, "total_steps": 309, "loss": 0.7544, "lr": 1.907859349437336e-06, "epoch": 2.2233009708737863, "percentage": 74.11, "elapsed_time": "3:05:48", "remaining_time": "1:04:54"} +{"current_steps": 230, "total_steps": 309, "loss": 0.7485, "lr": 1.8636549743984815e-06, "epoch": 2.233009708737864, "percentage": 74.43, "elapsed_time": "3:06:37", "remaining_time": "1:04:05"} +{"current_steps": 231, "total_steps": 309, "loss": 0.7552, "lr": 1.8198511241156902e-06, "epoch": 2.2427184466019416, "percentage": 74.76, "elapsed_time": "3:07:27", "remaining_time": "1:03:18"} +{"current_steps": 232, "total_steps": 309, "loss": 0.7683, "lr": 1.776453392529139e-06, "epoch": 2.2524271844660193, "percentage": 75.08, "elapsed_time": "3:08:19", "remaining_time": "1:02:30"} +{"current_steps": 233, "total_steps": 309, "loss": 0.7444, "lr": 1.7334673217158976e-06, "epoch": 2.262135922330097, "percentage": 75.4, "elapsed_time": "3:08:56", "remaining_time": "1:01:37"} +{"current_steps": 234, "total_steps": 309, "loss": 0.7495, "lr": 1.6908984011821883e-06, "epoch": 2.2718446601941746, "percentage": 75.73, "elapsed_time": "3:09:48", "remaining_time": "1:00:50"} +{"current_steps": 235, "total_steps": 309, "loss": 0.7545, "lr": 1.6487520671623469e-06, "epoch": 2.2815533980582523, "percentage": 76.05, "elapsed_time": "3:10:39", "remaining_time": "1:00:02"} +{"current_steps": 236, "total_steps": 309, "loss": 0.7521, "lr": 1.6070337019245896e-06, "epoch": 2.29126213592233, "percentage": 76.38, "elapsed_time": "3:11:29", "remaining_time": "0:59:13"} +{"current_steps": 237, "total_steps": 309, "loss": 0.759, "lr": 1.5657486330836786e-06, "epoch": 2.3009708737864076, "percentage": 76.7, "elapsed_time": "3:12:30", "remaining_time": "0:58:28"} +{"current_steps": 238, "total_steps": 309, "loss": 0.757, "lr": 1.5249021329205638e-06, "epoch": 2.3106796116504853, "percentage": 77.02, "elapsed_time": "3:13:12", "remaining_time": "0:57:38"} +{"current_steps": 239, "total_steps": 309, "loss": 0.7533, "lr": 1.4844994177090871e-06, "epoch": 2.320388349514563, "percentage": 77.35, "elapsed_time": "3:13:54", "remaining_time": "0:56:47"} +{"current_steps": 240, "total_steps": 309, "loss": 0.7859, "lr": 1.4445456470498392e-06, "epoch": 2.3300970873786406, "percentage": 77.67, "elapsed_time": "3:14:42", "remaining_time": "0:55:58"} +{"current_steps": 241, "total_steps": 309, "loss": 0.7873, "lr": 1.4050459232112652e-06, "epoch": 2.3398058252427183, "percentage": 77.99, "elapsed_time": "3:15:31", "remaining_time": "0:55:10"} +{"current_steps": 242, "total_steps": 309, "loss": 0.7664, "lr": 1.3660052904780707e-06, "epoch": 2.349514563106796, "percentage": 78.32, "elapsed_time": "3:16:20", "remaining_time": "0:54:21"} +{"current_steps": 243, "total_steps": 309, "loss": 0.7408, "lr": 1.3274287345070564e-06, "epoch": 2.3592233009708736, "percentage": 78.64, "elapsed_time": "3:17:04", "remaining_time": "0:53:31"} +{"current_steps": 244, "total_steps": 309, "loss": 0.7218, "lr": 1.2893211816904243e-06, "epoch": 2.3689320388349513, "percentage": 78.96, "elapsed_time": "3:17:51", "remaining_time": "0:52:42"} +{"current_steps": 245, "total_steps": 309, "loss": 0.7466, "lr": 1.2516874985266508e-06, "epoch": 2.378640776699029, "percentage": 79.29, "elapsed_time": "3:18:40", "remaining_time": "0:51:53"} +{"current_steps": 246, "total_steps": 309, "loss": 0.7116, "lr": 1.2145324909990202e-06, "epoch": 2.3883495145631066, "percentage": 79.61, "elapsed_time": "3:19:24", "remaining_time": "0:51:04"} +{"current_steps": 247, "total_steps": 309, "loss": 0.7446, "lr": 1.1778609039618804e-06, "epoch": 2.3980582524271843, "percentage": 79.94, "elapsed_time": "3:20:14", "remaining_time": "0:50:15"} +{"current_steps": 248, "total_steps": 309, "loss": 0.7546, "lr": 1.1416774205347015e-06, "epoch": 2.407766990291262, "percentage": 80.26, "elapsed_time": "3:21:01", "remaining_time": "0:49:26"} +{"current_steps": 249, "total_steps": 309, "loss": 0.7843, "lr": 1.1059866615040205e-06, "epoch": 2.4174757281553396, "percentage": 80.58, "elapsed_time": "3:21:56", "remaining_time": "0:48:39"} +{"current_steps": 250, "total_steps": 309, "loss": 0.7519, "lr": 1.0707931847333487e-06, "epoch": 2.4271844660194173, "percentage": 80.91, "elapsed_time": "3:22:45", "remaining_time": "0:47:51"} +{"current_steps": 251, "total_steps": 309, "loss": 0.7283, "lr": 1.036101484581117e-06, "epoch": 2.436893203883495, "percentage": 81.23, "elapsed_time": "3:23:29", "remaining_time": "0:47:01"} +{"current_steps": 252, "total_steps": 309, "loss": 0.7529, "lr": 1.0019159913267156e-06, "epoch": 2.4466019417475726, "percentage": 81.55, "elapsed_time": "3:24:13", "remaining_time": "0:46:11"} +{"current_steps": 253, "total_steps": 309, "loss": 0.763, "lr": 9.68241070604743e-07, "epoch": 2.4563106796116507, "percentage": 81.88, "elapsed_time": "3:24:53", "remaining_time": "0:45:21"} +{"current_steps": 254, "total_steps": 309, "loss": 0.7093, "lr": 9.350810228474855e-07, "epoch": 2.466019417475728, "percentage": 82.2, "elapsed_time": "3:25:41", "remaining_time": "0:44:32"} +{"current_steps": 255, "total_steps": 309, "loss": 0.7699, "lr": 9.024400827357344e-07, "epoch": 2.475728155339806, "percentage": 82.52, "elapsed_time": "3:26:30", "remaining_time": "0:43:43"} +{"current_steps": 256, "total_steps": 309, "loss": 0.7811, "lr": 8.703224186580012e-07, "epoch": 2.4854368932038833, "percentage": 82.85, "elapsed_time": "3:27:21", "remaining_time": "0:42:55"} +{"current_steps": 257, "total_steps": 309, "loss": 0.7633, "lr": 8.387321321781977e-07, "epoch": 2.4951456310679614, "percentage": 83.17, "elapsed_time": "3:28:01", "remaining_time": "0:42:05"} +{"current_steps": 258, "total_steps": 309, "loss": 0.7755, "lr": 8.07673257511849e-07, "epoch": 2.5048543689320386, "percentage": 83.5, "elapsed_time": "3:28:47", "remaining_time": "0:41:16"} +{"current_steps": 259, "total_steps": 309, "loss": 0.7574, "lr": 7.771497610108981e-07, "epoch": 2.5145631067961167, "percentage": 83.82, "elapsed_time": "3:29:32", "remaining_time": "0:40:27"} +{"current_steps": 260, "total_steps": 309, "loss": 0.7703, "lr": 7.471655406572003e-07, "epoch": 2.524271844660194, "percentage": 84.14, "elapsed_time": "3:30:21", "remaining_time": "0:39:38"} +{"current_steps": 261, "total_steps": 309, "loss": 0.7567, "lr": 7.177244255647209e-07, "epoch": 2.533980582524272, "percentage": 84.47, "elapsed_time": "3:31:14", "remaining_time": "0:38:50"} +{"current_steps": 262, "total_steps": 309, "loss": 0.7912, "lr": 6.888301754905469e-07, "epoch": 2.5436893203883493, "percentage": 84.79, "elapsed_time": "3:32:06", "remaining_time": "0:38:02"} +{"current_steps": 263, "total_steps": 309, "loss": 0.7474, "lr": 6.604864803547511e-07, "epoch": 2.5533980582524274, "percentage": 85.11, "elapsed_time": "3:32:58", "remaining_time": "0:37:15"} +{"current_steps": 264, "total_steps": 309, "loss": 0.7381, "lr": 6.326969597691724e-07, "epoch": 2.5631067961165046, "percentage": 85.44, "elapsed_time": "3:33:40", "remaining_time": "0:36:25"} +{"current_steps": 265, "total_steps": 309, "loss": 0.7587, "lr": 6.054651625751717e-07, "epoch": 2.5728155339805827, "percentage": 85.76, "elapsed_time": "3:34:28", "remaining_time": "0:35:36"} +{"current_steps": 266, "total_steps": 309, "loss": 0.7715, "lr": 5.787945663904332e-07, "epoch": 2.58252427184466, "percentage": 86.08, "elapsed_time": "3:35:12", "remaining_time": "0:34:47"} +{"current_steps": 267, "total_steps": 309, "loss": 0.7469, "lr": 5.526885771648599e-07, "epoch": 2.592233009708738, "percentage": 86.41, "elapsed_time": "3:35:57", "remaining_time": "0:33:58"} +{"current_steps": 268, "total_steps": 309, "loss": 0.7223, "lr": 5.271505287456153e-07, "epoch": 2.6019417475728153, "percentage": 86.73, "elapsed_time": "3:36:39", "remaining_time": "0:33:08"} +{"current_steps": 269, "total_steps": 309, "loss": 0.7802, "lr": 5.021836824513759e-07, "epoch": 2.6116504854368934, "percentage": 87.06, "elapsed_time": "3:37:36", "remaining_time": "0:32:21"} +{"current_steps": 270, "total_steps": 309, "loss": 0.7417, "lr": 4.777912266558532e-07, "epoch": 2.6213592233009706, "percentage": 87.38, "elapsed_time": "3:38:22", "remaining_time": "0:31:32"} +{"current_steps": 271, "total_steps": 309, "loss": 0.7705, "lr": 4.5397627638061604e-07, "epoch": 2.6310679611650487, "percentage": 87.7, "elapsed_time": "3:39:17", "remaining_time": "0:30:44"} +{"current_steps": 272, "total_steps": 309, "loss": 0.7391, "lr": 4.307418728972934e-07, "epoch": 2.6407766990291264, "percentage": 88.03, "elapsed_time": "3:40:00", "remaining_time": "0:29:55"} +{"current_steps": 273, "total_steps": 309, "loss": 0.7624, "lr": 4.080909833391944e-07, "epoch": 2.650485436893204, "percentage": 88.35, "elapsed_time": "3:40:48", "remaining_time": "0:29:07"} +{"current_steps": 274, "total_steps": 309, "loss": 0.7797, "lr": 3.8602650032238675e-07, "epoch": 2.6601941747572817, "percentage": 88.67, "elapsed_time": "3:41:40", "remaining_time": "0:28:18"} +{"current_steps": 275, "total_steps": 309, "loss": 0.7373, "lr": 3.6455124157629805e-07, "epoch": 2.6699029126213594, "percentage": 89.0, "elapsed_time": "3:42:22", "remaining_time": "0:27:29"} +{"current_steps": 276, "total_steps": 309, "loss": 0.7349, "lr": 3.436679495838835e-07, "epoch": 2.679611650485437, "percentage": 89.32, "elapsed_time": "3:43:07", "remaining_time": "0:26:40"} +{"current_steps": 277, "total_steps": 309, "loss": 0.754, "lr": 3.233792912313943e-07, "epoch": 2.6893203883495147, "percentage": 89.64, "elapsed_time": "3:44:06", "remaining_time": "0:25:53"} +{"current_steps": 278, "total_steps": 309, "loss": 0.7887, "lr": 3.0368785746780925e-07, "epoch": 2.6990291262135924, "percentage": 89.97, "elapsed_time": "3:45:00", "remaining_time": "0:25:05"} +{"current_steps": 279, "total_steps": 309, "loss": 0.7558, "lr": 2.8459616297395464e-07, "epoch": 2.70873786407767, "percentage": 90.29, "elapsed_time": "3:45:48", "remaining_time": "0:24:16"} +{"current_steps": 280, "total_steps": 309, "loss": 0.7088, "lr": 2.6610664584137413e-07, "epoch": 2.7184466019417477, "percentage": 90.61, "elapsed_time": "3:46:31", "remaining_time": "0:23:27"} +{"current_steps": 281, "total_steps": 309, "loss": 0.7279, "lr": 2.482216672609677e-07, "epoch": 2.7281553398058254, "percentage": 90.94, "elapsed_time": "3:47:18", "remaining_time": "0:22:39"} +{"current_steps": 282, "total_steps": 309, "loss": 0.7354, "lr": 2.3094351122146307e-07, "epoch": 2.737864077669903, "percentage": 91.26, "elapsed_time": "3:48:06", "remaining_time": "0:21:50"} +{"current_steps": 283, "total_steps": 309, "loss": 0.7427, "lr": 2.142743842177386e-07, "epoch": 2.7475728155339807, "percentage": 91.59, "elapsed_time": "3:48:49", "remaining_time": "0:21:01"} +{"current_steps": 284, "total_steps": 309, "loss": 0.7533, "lr": 1.98216414969043e-07, "epoch": 2.7572815533980584, "percentage": 91.91, "elapsed_time": "3:49:41", "remaining_time": "0:20:13"} +{"current_steps": 285, "total_steps": 309, "loss": 0.7471, "lr": 1.8277165414714858e-07, "epoch": 2.766990291262136, "percentage": 92.23, "elapsed_time": "3:50:33", "remaining_time": "0:19:24"} +{"current_steps": 286, "total_steps": 309, "loss": 0.7628, "lr": 1.6794207411447548e-07, "epoch": 2.7766990291262137, "percentage": 92.56, "elapsed_time": "3:51:18", "remaining_time": "0:18:36"} +{"current_steps": 287, "total_steps": 309, "loss": 0.7747, "lr": 1.5372956867220678e-07, "epoch": 2.7864077669902914, "percentage": 92.88, "elapsed_time": "3:52:10", "remaining_time": "0:17:47"} +{"current_steps": 288, "total_steps": 309, "loss": 0.7583, "lr": 1.4013595281844872e-07, "epoch": 2.796116504854369, "percentage": 93.2, "elapsed_time": "3:52:56", "remaining_time": "0:16:59"} +{"current_steps": 289, "total_steps": 309, "loss": 0.7675, "lr": 1.2716296251644e-07, "epoch": 2.8058252427184467, "percentage": 93.53, "elapsed_time": "3:53:43", "remaining_time": "0:16:10"} +{"current_steps": 290, "total_steps": 309, "loss": 0.7228, "lr": 1.1481225447286803e-07, "epoch": 2.8155339805825244, "percentage": 93.85, "elapsed_time": "3:54:24", "remaining_time": "0:15:21"} +{"current_steps": 291, "total_steps": 309, "loss": 0.7937, "lr": 1.0308540592629756e-07, "epoch": 2.825242718446602, "percentage": 94.17, "elapsed_time": "3:55:13", "remaining_time": "0:14:33"} +{"current_steps": 292, "total_steps": 309, "loss": 0.7037, "lr": 9.198391444575072e-08, "epoch": 2.8349514563106797, "percentage": 94.5, "elapsed_time": "3:55:52", "remaining_time": "0:13:43"} +{"current_steps": 293, "total_steps": 309, "loss": 0.7795, "lr": 8.150919773946165e-08, "epoch": 2.8446601941747574, "percentage": 94.82, "elapsed_time": "3:56:44", "remaining_time": "0:12:55"} +{"current_steps": 294, "total_steps": 309, "loss": 0.7292, "lr": 7.166259347382854e-08, "epoch": 2.854368932038835, "percentage": 95.15, "elapsed_time": "3:57:33", "remaining_time": "0:12:07"} +{"current_steps": 295, "total_steps": 309, "loss": 0.776, "lr": 6.244535910258697e-08, "epoch": 2.8640776699029127, "percentage": 95.47, "elapsed_time": "3:58:28", "remaining_time": "0:11:19"} +{"current_steps": 296, "total_steps": 309, "loss": 0.7917, "lr": 5.3858671706230605e-08, "epoch": 2.8737864077669903, "percentage": 95.79, "elapsed_time": "3:59:21", "remaining_time": "0:10:30"} +{"current_steps": 297, "total_steps": 309, "loss": 0.8002, "lr": 4.590362784169022e-08, "epoch": 2.883495145631068, "percentage": 96.12, "elapsed_time": "4:00:08", "remaining_time": "0:09:42"} +{"current_steps": 298, "total_steps": 309, "loss": 0.7326, "lr": 3.858124340229863e-08, "epoch": 2.8932038834951457, "percentage": 96.44, "elapsed_time": "4:00:49", "remaining_time": "0:08:53"} +{"current_steps": 299, "total_steps": 309, "loss": 0.7604, "lr": 3.1892453488058803e-08, "epoch": 2.9029126213592233, "percentage": 96.76, "elapsed_time": "4:01:38", "remaining_time": "0:08:04"} +{"current_steps": 300, "total_steps": 309, "loss": 0.7339, "lr": 2.5838112286226123e-08, "epoch": 2.912621359223301, "percentage": 97.09, "elapsed_time": "4:02:26", "remaining_time": "0:07:16"} +{"current_steps": 301, "total_steps": 309, "loss": 0.7299, "lr": 2.0418992962224495e-08, "epoch": 2.9223300970873787, "percentage": 97.41, "elapsed_time": "4:03:15", "remaining_time": "0:06:27"} +{"current_steps": 302, "total_steps": 309, "loss": 0.7919, "lr": 1.563578756091144e-08, "epoch": 2.9320388349514563, "percentage": 97.73, "elapsed_time": "4:04:08", "remaining_time": "0:05:39"} +{"current_steps": 303, "total_steps": 309, "loss": 0.6998, "lr": 1.1489106918200487e-08, "epoch": 2.941747572815534, "percentage": 98.06, "elapsed_time": "4:04:56", "remaining_time": "0:04:51"} +{"current_steps": 304, "total_steps": 309, "loss": 0.7362, "lr": 7.979480583052423e-09, "epoch": 2.9514563106796117, "percentage": 98.38, "elapsed_time": "4:05:39", "remaining_time": "0:04:02"} +{"current_steps": 305, "total_steps": 309, "loss": 0.7416, "lr": 5.107356749853298e-09, "epoch": 2.9611650485436893, "percentage": 98.71, "elapsed_time": "4:06:26", "remaining_time": "0:03:13"} +{"current_steps": 306, "total_steps": 309, "loss": 0.7835, "lr": 2.8731022011757593e-09, "epoch": 2.970873786407767, "percentage": 99.03, "elapsed_time": "4:07:11", "remaining_time": "0:02:25"} +{"current_steps": 307, "total_steps": 309, "loss": 0.7464, "lr": 1.2770022609409628e-09, "epoch": 2.9805825242718447, "percentage": 99.35, "elapsed_time": "4:08:00", "remaining_time": "0:01:36"} +{"current_steps": 308, "total_steps": 309, "loss": 0.7806, "lr": 3.1926075797827914e-10, "epoch": 2.9902912621359223, "percentage": 99.68, "elapsed_time": "4:08:56", "remaining_time": "0:00:48"} +{"current_steps": 309, "total_steps": 309, "loss": 0.7573, "lr": 0.0, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "4:09:47", "remaining_time": "0:00:00"} +{"current_steps": 309, "total_steps": 309, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "4:11:58", "remaining_time": "0:00:00"} diff --git a/trainer_state.json b/trainer_state.json new file mode 100644 index 0000000..26f8476 --- /dev/null +++ b/trainer_state.json @@ -0,0 +1,2205 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 3.0, + "eval_steps": 500, + "global_step": 309, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.009708737864077669, + "grad_norm": 6.576948642730713, + "learning_rate": 3.2258064516129035e-07, + "loss": 1.2227, + "step": 1 + }, + { + "epoch": 0.019417475728155338, + "grad_norm": 6.762261867523193, + "learning_rate": 6.451612903225807e-07, + "loss": 1.2675, + "step": 2 + }, + { + "epoch": 0.02912621359223301, + "grad_norm": 6.975041389465332, + "learning_rate": 9.67741935483871e-07, + "loss": 1.2517, + "step": 3 + }, + { + "epoch": 0.038834951456310676, + "grad_norm": 6.626192569732666, + "learning_rate": 1.2903225806451614e-06, + "loss": 1.2515, + "step": 4 + }, + { + "epoch": 0.04854368932038835, + "grad_norm": 6.378674030303955, + "learning_rate": 1.6129032258064516e-06, + "loss": 1.2498, + "step": 5 + }, + { + "epoch": 0.05825242718446602, + "grad_norm": 6.095025539398193, + "learning_rate": 1.935483870967742e-06, + "loss": 1.2283, + "step": 6 + }, + { + "epoch": 0.06796116504854369, + "grad_norm": 4.670423984527588, + "learning_rate": 2.2580645161290324e-06, + "loss": 1.1489, + "step": 7 + }, + { + "epoch": 0.07766990291262135, + "grad_norm": 4.401129245758057, + "learning_rate": 2.580645161290323e-06, + "loss": 1.1759, + "step": 8 + }, + { + "epoch": 0.08737864077669903, + "grad_norm": 2.814140796661377, + "learning_rate": 2.903225806451613e-06, + "loss": 1.128, + "step": 9 + }, + { + "epoch": 0.0970873786407767, + "grad_norm": 2.6264705657958984, + "learning_rate": 3.225806451612903e-06, + "loss": 1.1088, + "step": 10 + }, + { + "epoch": 0.10679611650485436, + "grad_norm": 2.619597911834717, + "learning_rate": 3.548387096774194e-06, + "loss": 1.1275, + "step": 11 + }, + { + "epoch": 0.11650485436893204, + "grad_norm": 4.305774688720703, + "learning_rate": 3.870967741935484e-06, + "loss": 1.1287, + "step": 12 + }, + { + "epoch": 0.1262135922330097, + "grad_norm": 4.335093975067139, + "learning_rate": 4.193548387096774e-06, + "loss": 1.1011, + "step": 13 + }, + { + "epoch": 0.13592233009708737, + "grad_norm": 4.46498966217041, + "learning_rate": 4.516129032258065e-06, + "loss": 1.1392, + "step": 14 + }, + { + "epoch": 0.14563106796116504, + "grad_norm": 3.7746875286102295, + "learning_rate": 4.838709677419355e-06, + "loss": 1.0678, + "step": 15 + }, + { + "epoch": 0.1553398058252427, + "grad_norm": 2.9575371742248535, + "learning_rate": 5.161290322580646e-06, + "loss": 1.0683, + "step": 16 + }, + { + "epoch": 0.1650485436893204, + "grad_norm": 2.7806265354156494, + "learning_rate": 5.483870967741935e-06, + "loss": 1.0367, + "step": 17 + }, + { + "epoch": 0.17475728155339806, + "grad_norm": 2.41747784614563, + "learning_rate": 5.806451612903226e-06, + "loss": 1.0401, + "step": 18 + }, + { + "epoch": 0.18446601941747573, + "grad_norm": 2.0261120796203613, + "learning_rate": 6.129032258064517e-06, + "loss": 1.0364, + "step": 19 + }, + { + "epoch": 0.1941747572815534, + "grad_norm": 1.6902999877929688, + "learning_rate": 6.451612903225806e-06, + "loss": 0.9807, + "step": 20 + }, + { + "epoch": 0.20388349514563106, + "grad_norm": 1.6579384803771973, + "learning_rate": 6.774193548387097e-06, + "loss": 1.0094, + "step": 21 + }, + { + "epoch": 0.21359223300970873, + "grad_norm": 1.3350183963775635, + "learning_rate": 7.096774193548388e-06, + "loss": 0.9756, + "step": 22 + }, + { + "epoch": 0.22330097087378642, + "grad_norm": 1.4252748489379883, + "learning_rate": 7.4193548387096784e-06, + "loss": 1.0005, + "step": 23 + }, + { + "epoch": 0.23300970873786409, + "grad_norm": 1.2831058502197266, + "learning_rate": 7.741935483870968e-06, + "loss": 0.9875, + "step": 24 + }, + { + "epoch": 0.24271844660194175, + "grad_norm": 1.1137187480926514, + "learning_rate": 8.064516129032258e-06, + "loss": 0.9444, + "step": 25 + }, + { + "epoch": 0.2524271844660194, + "grad_norm": 1.186092495918274, + "learning_rate": 8.387096774193549e-06, + "loss": 0.9467, + "step": 26 + }, + { + "epoch": 0.2621359223300971, + "grad_norm": 0.910400390625, + "learning_rate": 8.70967741935484e-06, + "loss": 0.9549, + "step": 27 + }, + { + "epoch": 0.27184466019417475, + "grad_norm": 1.0872230529785156, + "learning_rate": 9.03225806451613e-06, + "loss": 0.9433, + "step": 28 + }, + { + "epoch": 0.2815533980582524, + "grad_norm": 1.0862929821014404, + "learning_rate": 9.35483870967742e-06, + "loss": 0.9353, + "step": 29 + }, + { + "epoch": 0.2912621359223301, + "grad_norm": 1.1340218782424927, + "learning_rate": 9.67741935483871e-06, + "loss": 0.9254, + "step": 30 + }, + { + "epoch": 0.30097087378640774, + "grad_norm": 1.1494905948638916, + "learning_rate": 1e-05, + "loss": 0.9231, + "step": 31 + }, + { + "epoch": 0.3106796116504854, + "grad_norm": 0.9529262781143188, + "learning_rate": 9.999680739242022e-06, + "loss": 0.9367, + "step": 32 + }, + { + "epoch": 0.32038834951456313, + "grad_norm": 0.9129893183708191, + "learning_rate": 9.99872299773906e-06, + "loss": 0.9194, + "step": 33 + }, + { + "epoch": 0.3300970873786408, + "grad_norm": 1.1129016876220703, + "learning_rate": 9.997126897798826e-06, + "loss": 0.8978, + "step": 34 + }, + { + "epoch": 0.33980582524271846, + "grad_norm": 1.0057542324066162, + "learning_rate": 9.994892643250147e-06, + "loss": 0.9046, + "step": 35 + }, + { + "epoch": 0.34951456310679613, + "grad_norm": 0.8979021906852722, + "learning_rate": 9.99202051941695e-06, + "loss": 0.9191, + "step": 36 + }, + { + "epoch": 0.3592233009708738, + "grad_norm": 0.8347776532173157, + "learning_rate": 9.9885108930818e-06, + "loss": 0.8796, + "step": 37 + }, + { + "epoch": 0.36893203883495146, + "grad_norm": 0.8598542213439941, + "learning_rate": 9.984364212439089e-06, + "loss": 0.9132, + "step": 38 + }, + { + "epoch": 0.3786407766990291, + "grad_norm": 0.8244529962539673, + "learning_rate": 9.979581007037776e-06, + "loss": 0.8933, + "step": 39 + }, + { + "epoch": 0.3883495145631068, + "grad_norm": 0.733172595500946, + "learning_rate": 9.974161887713775e-06, + "loss": 0.9021, + "step": 40 + }, + { + "epoch": 0.39805825242718446, + "grad_norm": 0.9536871910095215, + "learning_rate": 9.968107546511942e-06, + "loss": 0.9121, + "step": 41 + }, + { + "epoch": 0.4077669902912621, + "grad_norm": 0.7781872153282166, + "learning_rate": 9.961418756597703e-06, + "loss": 0.9045, + "step": 42 + }, + { + "epoch": 0.4174757281553398, + "grad_norm": 0.8622099757194519, + "learning_rate": 9.95409637215831e-06, + "loss": 0.9019, + "step": 43 + }, + { + "epoch": 0.42718446601941745, + "grad_norm": 0.694644570350647, + "learning_rate": 9.94614132829377e-06, + "loss": 0.8502, + "step": 44 + }, + { + "epoch": 0.4368932038834951, + "grad_norm": 0.7023694515228271, + "learning_rate": 9.937554640897414e-06, + "loss": 0.9056, + "step": 45 + }, + { + "epoch": 0.44660194174757284, + "grad_norm": 0.7865616679191589, + "learning_rate": 9.928337406526172e-06, + "loss": 0.8951, + "step": 46 + }, + { + "epoch": 0.4563106796116505, + "grad_norm": 0.8198397159576416, + "learning_rate": 9.918490802260538e-06, + "loss": 0.919, + "step": 47 + }, + { + "epoch": 0.46601941747572817, + "grad_norm": 0.6332915425300598, + "learning_rate": 9.90801608555425e-06, + "loss": 0.9086, + "step": 48 + }, + { + "epoch": 0.47572815533980584, + "grad_norm": 0.665955662727356, + "learning_rate": 9.896914594073703e-06, + "loss": 0.8707, + "step": 49 + }, + { + "epoch": 0.4854368932038835, + "grad_norm": 0.8108275532722473, + "learning_rate": 9.885187745527132e-06, + "loss": 0.8903, + "step": 50 + }, + { + "epoch": 0.49514563106796117, + "grad_norm": 0.7815718054771423, + "learning_rate": 9.87283703748356e-06, + "loss": 0.8803, + "step": 51 + }, + { + "epoch": 0.5048543689320388, + "grad_norm": 0.7477515935897827, + "learning_rate": 9.859864047181551e-06, + "loss": 0.9034, + "step": 52 + }, + { + "epoch": 0.5145631067961165, + "grad_norm": 0.8046391606330872, + "learning_rate": 9.846270431327793e-06, + "loss": 0.8962, + "step": 53 + }, + { + "epoch": 0.5242718446601942, + "grad_norm": 0.6419571042060852, + "learning_rate": 9.832057925885526e-06, + "loss": 0.8834, + "step": 54 + }, + { + "epoch": 0.5339805825242718, + "grad_norm": 0.885932981967926, + "learning_rate": 9.817228345852853e-06, + "loss": 0.9023, + "step": 55 + }, + { + "epoch": 0.5436893203883495, + "grad_norm": 0.5639209747314453, + "learning_rate": 9.801783585030959e-06, + "loss": 0.9119, + "step": 56 + }, + { + "epoch": 0.5533980582524272, + "grad_norm": 0.8406121730804443, + "learning_rate": 9.785725615782262e-06, + "loss": 0.8605, + "step": 57 + }, + { + "epoch": 0.5631067961165048, + "grad_norm": 0.6397046446800232, + "learning_rate": 9.769056488778538e-06, + "loss": 0.87, + "step": 58 + }, + { + "epoch": 0.5728155339805825, + "grad_norm": 0.6496418714523315, + "learning_rate": 9.751778332739033e-06, + "loss": 0.8863, + "step": 59 + }, + { + "epoch": 0.5825242718446602, + "grad_norm": 0.8817011713981628, + "learning_rate": 9.733893354158628e-06, + "loss": 0.8757, + "step": 60 + }, + { + "epoch": 0.5922330097087378, + "grad_norm": 0.6433860063552856, + "learning_rate": 9.715403837026046e-06, + "loss": 0.8613, + "step": 61 + }, + { + "epoch": 0.6019417475728155, + "grad_norm": 0.9720786213874817, + "learning_rate": 9.69631214253219e-06, + "loss": 0.8831, + "step": 62 + }, + { + "epoch": 0.6116504854368932, + "grad_norm": 0.6686399579048157, + "learning_rate": 9.676620708768608e-06, + "loss": 0.8823, + "step": 63 + }, + { + "epoch": 0.6213592233009708, + "grad_norm": 0.6597081422805786, + "learning_rate": 9.656332050416118e-06, + "loss": 0.8351, + "step": 64 + }, + { + "epoch": 0.6310679611650486, + "grad_norm": 0.781461775302887, + "learning_rate": 9.635448758423703e-06, + "loss": 0.8792, + "step": 65 + }, + { + "epoch": 0.6407766990291263, + "grad_norm": 0.5933522582054138, + "learning_rate": 9.613973499677613e-06, + "loss": 0.912, + "step": 66 + }, + { + "epoch": 0.6504854368932039, + "grad_norm": 0.7272161841392517, + "learning_rate": 9.591909016660806e-06, + "loss": 0.8788, + "step": 67 + }, + { + "epoch": 0.6601941747572816, + "grad_norm": 0.6520808339118958, + "learning_rate": 9.569258127102708e-06, + "loss": 0.8965, + "step": 68 + }, + { + "epoch": 0.6699029126213593, + "grad_norm": 0.7806766033172607, + "learning_rate": 9.546023723619387e-06, + "loss": 0.8917, + "step": 69 + }, + { + "epoch": 0.6796116504854369, + "grad_norm": 0.7100508213043213, + "learning_rate": 9.522208773344147e-06, + "loss": 0.8872, + "step": 70 + }, + { + "epoch": 0.6893203883495146, + "grad_norm": 0.7099691033363342, + "learning_rate": 9.497816317548625e-06, + "loss": 0.8793, + "step": 71 + }, + { + "epoch": 0.6990291262135923, + "grad_norm": 0.8257980346679688, + "learning_rate": 9.472849471254386e-06, + "loss": 0.8539, + "step": 72 + }, + { + "epoch": 0.7087378640776699, + "grad_norm": 0.6728125214576721, + "learning_rate": 9.447311422835141e-06, + "loss": 0.8669, + "step": 73 + }, + { + "epoch": 0.7184466019417476, + "grad_norm": 0.7229968905448914, + "learning_rate": 9.421205433609568e-06, + "loss": 0.8991, + "step": 74 + }, + { + "epoch": 0.7281553398058253, + "grad_norm": 0.7105078101158142, + "learning_rate": 9.39453483742483e-06, + "loss": 0.8704, + "step": 75 + }, + { + "epoch": 0.7378640776699029, + "grad_norm": 0.7349528670310974, + "learning_rate": 9.367303040230828e-06, + "loss": 0.8866, + "step": 76 + }, + { + "epoch": 0.7475728155339806, + "grad_norm": 0.5864897966384888, + "learning_rate": 9.33951351964525e-06, + "loss": 0.8671, + "step": 77 + }, + { + "epoch": 0.7572815533980582, + "grad_norm": 0.6392523646354675, + "learning_rate": 9.311169824509454e-06, + "loss": 0.8435, + "step": 78 + }, + { + "epoch": 0.7669902912621359, + "grad_norm": 0.5775032639503479, + "learning_rate": 9.28227557443528e-06, + "loss": 0.8518, + "step": 79 + }, + { + "epoch": 0.7766990291262136, + "grad_norm": 0.5982815623283386, + "learning_rate": 9.252834459342801e-06, + "loss": 0.9034, + "step": 80 + }, + { + "epoch": 0.7864077669902912, + "grad_norm": 0.6583596467971802, + "learning_rate": 9.222850238989104e-06, + "loss": 0.8638, + "step": 81 + }, + { + "epoch": 0.7961165048543689, + "grad_norm": 0.621867299079895, + "learning_rate": 9.192326742488153e-06, + "loss": 0.8658, + "step": 82 + }, + { + "epoch": 0.8058252427184466, + "grad_norm": 0.6219890117645264, + "learning_rate": 9.161267867821802e-06, + "loss": 0.8769, + "step": 83 + }, + { + "epoch": 0.8155339805825242, + "grad_norm": 0.6069071292877197, + "learning_rate": 9.129677581342e-06, + "loss": 0.8677, + "step": 84 + }, + { + "epoch": 0.8252427184466019, + "grad_norm": 0.660553514957428, + "learning_rate": 9.097559917264268e-06, + "loss": 0.8465, + "step": 85 + }, + { + "epoch": 0.8349514563106796, + "grad_norm": 0.5944454669952393, + "learning_rate": 9.064918977152517e-06, + "loss": 0.8741, + "step": 86 + }, + { + "epoch": 0.8446601941747572, + "grad_norm": 0.6104128360748291, + "learning_rate": 9.031758929395259e-06, + "loss": 0.8248, + "step": 87 + }, + { + "epoch": 0.8543689320388349, + "grad_norm": 0.5879605412483215, + "learning_rate": 8.998084008673284e-06, + "loss": 0.8398, + "step": 88 + }, + { + "epoch": 0.8640776699029126, + "grad_norm": 0.6651065349578857, + "learning_rate": 8.963898515418885e-06, + "loss": 0.8687, + "step": 89 + }, + { + "epoch": 0.8737864077669902, + "grad_norm": 0.6086816191673279, + "learning_rate": 8.929206815266653e-06, + "loss": 0.8639, + "step": 90 + }, + { + "epoch": 0.883495145631068, + "grad_norm": 0.6449173092842102, + "learning_rate": 8.89401333849598e-06, + "loss": 0.8483, + "step": 91 + }, + { + "epoch": 0.8932038834951457, + "grad_norm": 0.6413861513137817, + "learning_rate": 8.8583225794653e-06, + "loss": 0.9039, + "step": 92 + }, + { + "epoch": 0.9029126213592233, + "grad_norm": 0.5411512851715088, + "learning_rate": 8.82213909603812e-06, + "loss": 0.8814, + "step": 93 + }, + { + "epoch": 0.912621359223301, + "grad_norm": 0.6556549072265625, + "learning_rate": 8.78546750900098e-06, + "loss": 0.8944, + "step": 94 + }, + { + "epoch": 0.9223300970873787, + "grad_norm": 0.6550806760787964, + "learning_rate": 8.748312501473351e-06, + "loss": 0.8819, + "step": 95 + }, + { + "epoch": 0.9320388349514563, + "grad_norm": 0.6445295810699463, + "learning_rate": 8.710678818309576e-06, + "loss": 0.8582, + "step": 96 + }, + { + "epoch": 0.941747572815534, + "grad_norm": 0.7256100177764893, + "learning_rate": 8.672571265492944e-06, + "loss": 0.8361, + "step": 97 + }, + { + "epoch": 0.9514563106796117, + "grad_norm": 0.599454402923584, + "learning_rate": 8.63399470952193e-06, + "loss": 0.8679, + "step": 98 + }, + { + "epoch": 0.9611650485436893, + "grad_norm": 0.7651983499526978, + "learning_rate": 8.594954076788736e-06, + "loss": 0.8182, + "step": 99 + }, + { + "epoch": 0.970873786407767, + "grad_norm": 0.7521474361419678, + "learning_rate": 8.555454352950161e-06, + "loss": 0.8622, + "step": 100 + }, + { + "epoch": 0.9805825242718447, + "grad_norm": 0.6626675724983215, + "learning_rate": 8.515500582290914e-06, + "loss": 0.845, + "step": 101 + }, + { + "epoch": 0.9902912621359223, + "grad_norm": 0.7361329793930054, + "learning_rate": 8.475097867079437e-06, + "loss": 0.8672, + "step": 102 + }, + { + "epoch": 1.0, + "grad_norm": 0.5690233707427979, + "learning_rate": 8.434251366916323e-06, + "loss": 0.8989, + "step": 103 + }, + { + "epoch": 1.0097087378640777, + "grad_norm": 0.778568685054779, + "learning_rate": 8.392966298075413e-06, + "loss": 0.8642, + "step": 104 + }, + { + "epoch": 1.0194174757281553, + "grad_norm": 0.5900771021842957, + "learning_rate": 8.351247932837655e-06, + "loss": 0.8001, + "step": 105 + }, + { + "epoch": 1.029126213592233, + "grad_norm": 0.628034770488739, + "learning_rate": 8.309101598817812e-06, + "loss": 0.8101, + "step": 106 + }, + { + "epoch": 1.0388349514563107, + "grad_norm": 0.860468864440918, + "learning_rate": 8.266532678284103e-06, + "loss": 0.7936, + "step": 107 + }, + { + "epoch": 1.0485436893203883, + "grad_norm": 0.7311742901802063, + "learning_rate": 8.223546607470863e-06, + "loss": 0.8278, + "step": 108 + }, + { + "epoch": 1.058252427184466, + "grad_norm": 0.6832053661346436, + "learning_rate": 8.18014887588431e-06, + "loss": 0.8272, + "step": 109 + }, + { + "epoch": 1.0679611650485437, + "grad_norm": 0.8355731964111328, + "learning_rate": 8.13634502560152e-06, + "loss": 0.8485, + "step": 110 + }, + { + "epoch": 1.0776699029126213, + "grad_norm": 0.6029130816459656, + "learning_rate": 8.092140650562665e-06, + "loss": 0.7722, + "step": 111 + }, + { + "epoch": 1.087378640776699, + "grad_norm": 0.8511623740196228, + "learning_rate": 8.047541395856661e-06, + "loss": 0.8361, + "step": 112 + }, + { + "epoch": 1.0970873786407767, + "grad_norm": 0.6003599166870117, + "learning_rate": 8.002552957000254e-06, + "loss": 0.8157, + "step": 113 + }, + { + "epoch": 1.1067961165048543, + "grad_norm": 0.8679140210151672, + "learning_rate": 7.957181079210676e-06, + "loss": 0.819, + "step": 114 + }, + { + "epoch": 1.116504854368932, + "grad_norm": 0.65385901927948, + "learning_rate": 7.911431556671967e-06, + "loss": 0.8191, + "step": 115 + }, + { + "epoch": 1.1262135922330097, + "grad_norm": 0.5810941457748413, + "learning_rate": 7.865310231795026e-06, + "loss": 0.8084, + "step": 116 + }, + { + "epoch": 1.1359223300970873, + "grad_norm": 0.7386210560798645, + "learning_rate": 7.818822994471504e-06, + "loss": 0.8088, + "step": 117 + }, + { + "epoch": 1.145631067961165, + "grad_norm": 0.6052452325820923, + "learning_rate": 7.771975781321655e-06, + "loss": 0.8236, + "step": 118 + }, + { + "epoch": 1.1553398058252426, + "grad_norm": 0.6413220167160034, + "learning_rate": 7.72477457493619e-06, + "loss": 0.8427, + "step": 119 + }, + { + "epoch": 1.1650485436893203, + "grad_norm": 0.6168550848960876, + "learning_rate": 7.677225403112277e-06, + "loss": 0.8204, + "step": 120 + }, + { + "epoch": 1.174757281553398, + "grad_norm": 0.6849708557128906, + "learning_rate": 7.629334338083774e-06, + "loss": 0.7887, + "step": 121 + }, + { + "epoch": 1.1844660194174756, + "grad_norm": 0.7301358580589294, + "learning_rate": 7.58110749574577e-06, + "loss": 0.8137, + "step": 122 + }, + { + "epoch": 1.1941747572815533, + "grad_norm": 0.6189250349998474, + "learning_rate": 7.532551034873558e-06, + "loss": 0.7985, + "step": 123 + }, + { + "epoch": 1.203883495145631, + "grad_norm": 0.70215904712677, + "learning_rate": 7.483671156336142e-06, + "loss": 0.8108, + "step": 124 + }, + { + "epoch": 1.2135922330097086, + "grad_norm": 0.642704963684082, + "learning_rate": 7.43447410230435e-06, + "loss": 0.8161, + "step": 125 + }, + { + "epoch": 1.2233009708737863, + "grad_norm": 0.6741234660148621, + "learning_rate": 7.384966155453686e-06, + "loss": 0.7965, + "step": 126 + }, + { + "epoch": 1.233009708737864, + "grad_norm": 0.577409029006958, + "learning_rate": 7.335153638162005e-06, + "loss": 0.7989, + "step": 127 + }, + { + "epoch": 1.2427184466019416, + "grad_norm": 0.5523732900619507, + "learning_rate": 7.285042911702116e-06, + "loss": 0.7812, + "step": 128 + }, + { + "epoch": 1.2524271844660193, + "grad_norm": 0.6712595224380493, + "learning_rate": 7.234640375429427e-06, + "loss": 0.8034, + "step": 129 + }, + { + "epoch": 1.262135922330097, + "grad_norm": 0.6166908144950867, + "learning_rate": 7.183952465964711e-06, + "loss": 0.8004, + "step": 130 + }, + { + "epoch": 1.2718446601941746, + "grad_norm": 0.7181272506713867, + "learning_rate": 7.132985656372126e-06, + "loss": 0.8122, + "step": 131 + }, + { + "epoch": 1.2815533980582523, + "grad_norm": 0.5397993922233582, + "learning_rate": 7.0817464553325764e-06, + "loss": 0.8256, + "step": 132 + }, + { + "epoch": 1.29126213592233, + "grad_norm": 0.599078357219696, + "learning_rate": 7.030241406312528e-06, + "loss": 0.8012, + "step": 133 + }, + { + "epoch": 1.3009708737864076, + "grad_norm": 0.6068196296691895, + "learning_rate": 6.978477086728375e-06, + "loss": 0.7475, + "step": 134 + }, + { + "epoch": 1.3106796116504853, + "grad_norm": 0.6208373308181763, + "learning_rate": 6.926460107106483e-06, + "loss": 0.7631, + "step": 135 + }, + { + "epoch": 1.3203883495145632, + "grad_norm": 0.62087482213974, + "learning_rate": 6.874197110238986e-06, + "loss": 0.7626, + "step": 136 + }, + { + "epoch": 1.3300970873786409, + "grad_norm": 0.6587031483650208, + "learning_rate": 6.8216947703354815e-06, + "loss": 0.809, + "step": 137 + }, + { + "epoch": 1.3398058252427185, + "grad_norm": 0.7958360314369202, + "learning_rate": 6.7689597921707065e-06, + "loss": 0.8311, + "step": 138 + }, + { + "epoch": 1.3495145631067962, + "grad_norm": 0.6715186834335327, + "learning_rate": 6.715998910228296e-06, + "loss": 0.7949, + "step": 139 + }, + { + "epoch": 1.3592233009708738, + "grad_norm": 0.6351740956306458, + "learning_rate": 6.6628188878407806e-06, + "loss": 0.794, + "step": 140 + }, + { + "epoch": 1.3689320388349515, + "grad_norm": 0.8707325458526611, + "learning_rate": 6.609426516325859e-06, + "loss": 0.8329, + "step": 141 + }, + { + "epoch": 1.3786407766990292, + "grad_norm": 0.7321479320526123, + "learning_rate": 6.555828614119132e-06, + "loss": 0.8136, + "step": 142 + }, + { + "epoch": 1.3883495145631068, + "grad_norm": 0.5844182968139648, + "learning_rate": 6.502032025903356e-06, + "loss": 0.7576, + "step": 143 + }, + { + "epoch": 1.3980582524271845, + "grad_norm": 0.6121401786804199, + "learning_rate": 6.4480436217343366e-06, + "loss": 0.8205, + "step": 144 + }, + { + "epoch": 1.4077669902912622, + "grad_norm": 0.6373964548110962, + "learning_rate": 6.393870296163616e-06, + "loss": 0.8104, + "step": 145 + }, + { + "epoch": 1.4174757281553398, + "grad_norm": 0.5534393787384033, + "learning_rate": 6.339518967357985e-06, + "loss": 0.7822, + "step": 146 + }, + { + "epoch": 1.4271844660194175, + "grad_norm": 0.593232274055481, + "learning_rate": 6.284996576216014e-06, + "loss": 0.8227, + "step": 147 + }, + { + "epoch": 1.4368932038834952, + "grad_norm": 0.5890830755233765, + "learning_rate": 6.230310085481677e-06, + "loss": 0.8005, + "step": 148 + }, + { + "epoch": 1.4466019417475728, + "grad_norm": 0.5876540541648865, + "learning_rate": 6.175466478855161e-06, + "loss": 0.7936, + "step": 149 + }, + { + "epoch": 1.4563106796116505, + "grad_norm": 0.5593201518058777, + "learning_rate": 6.1204727601010396e-06, + "loss": 0.7473, + "step": 150 + }, + { + "epoch": 1.4660194174757282, + "grad_norm": 0.5841484069824219, + "learning_rate": 6.065335952153846e-06, + "loss": 0.7974, + "step": 151 + }, + { + "epoch": 1.4757281553398058, + "grad_norm": 0.49436667561531067, + "learning_rate": 6.010063096221215e-06, + "loss": 0.7921, + "step": 152 + }, + { + "epoch": 1.4854368932038835, + "grad_norm": 0.6187512874603271, + "learning_rate": 5.954661250884704e-06, + "loss": 0.7822, + "step": 153 + }, + { + "epoch": 1.4951456310679612, + "grad_norm": 0.6759915351867676, + "learning_rate": 5.899137491198364e-06, + "loss": 0.8273, + "step": 154 + }, + { + "epoch": 1.5048543689320388, + "grad_norm": 0.5890839099884033, + "learning_rate": 5.843498907785236e-06, + "loss": 0.7979, + "step": 155 + }, + { + "epoch": 1.5145631067961165, + "grad_norm": 0.5246779322624207, + "learning_rate": 5.78775260593185e-06, + "loss": 0.8198, + "step": 156 + }, + { + "epoch": 1.5242718446601942, + "grad_norm": 0.5603223443031311, + "learning_rate": 5.731905704680834e-06, + "loss": 0.8023, + "step": 157 + }, + { + "epoch": 1.5339805825242718, + "grad_norm": 0.5730907917022705, + "learning_rate": 5.6759653359218e-06, + "loss": 0.8231, + "step": 158 + }, + { + "epoch": 1.5436893203883495, + "grad_norm": 0.5317082405090332, + "learning_rate": 5.6199386434805615e-06, + "loss": 0.7984, + "step": 159 + }, + { + "epoch": 1.5533980582524272, + "grad_norm": 0.5330399870872498, + "learning_rate": 5.563832782206835e-06, + "loss": 0.7975, + "step": 160 + }, + { + "epoch": 1.5631067961165048, + "grad_norm": 0.6568978428840637, + "learning_rate": 5.507654917060541e-06, + "loss": 0.824, + "step": 161 + }, + { + "epoch": 1.5728155339805825, + "grad_norm": 0.6758802533149719, + "learning_rate": 5.451412222196801e-06, + "loss": 0.7844, + "step": 162 + }, + { + "epoch": 1.5825242718446602, + "grad_norm": 0.5091277360916138, + "learning_rate": 5.395111880049775e-06, + "loss": 0.7946, + "step": 163 + }, + { + "epoch": 1.5922330097087378, + "grad_norm": 0.5247997045516968, + "learning_rate": 5.338761080415425e-06, + "loss": 0.8035, + "step": 164 + }, + { + "epoch": 1.6019417475728155, + "grad_norm": 0.5019735097885132, + "learning_rate": 5.28236701953335e-06, + "loss": 0.7802, + "step": 165 + }, + { + "epoch": 1.6116504854368932, + "grad_norm": 0.5382864475250244, + "learning_rate": 5.225936899167803e-06, + "loss": 0.8301, + "step": 166 + }, + { + "epoch": 1.6213592233009708, + "grad_norm": 0.503472089767456, + "learning_rate": 5.169477925687981e-06, + "loss": 0.7875, + "step": 167 + }, + { + "epoch": 1.6310679611650487, + "grad_norm": 0.5378626585006714, + "learning_rate": 5.112997309147753e-06, + "loss": 0.8003, + "step": 168 + }, + { + "epoch": 1.6407766990291264, + "grad_norm": 0.4998520314693451, + "learning_rate": 5.0565022623649e-06, + "loss": 0.8094, + "step": 169 + }, + { + "epoch": 1.650485436893204, + "grad_norm": 0.5108544826507568, + "learning_rate": 5e-06, + "loss": 0.7756, + "step": 170 + }, + { + "epoch": 1.6601941747572817, + "grad_norm": 0.4933609962463379, + "learning_rate": 4.943497737635103e-06, + "loss": 0.8081, + "step": 171 + }, + { + "epoch": 1.6699029126213594, + "grad_norm": 0.5090092420578003, + "learning_rate": 4.887002690852249e-06, + "loss": 0.8025, + "step": 172 + }, + { + "epoch": 1.679611650485437, + "grad_norm": 0.5769246816635132, + "learning_rate": 4.830522074312019e-06, + "loss": 0.8068, + "step": 173 + }, + { + "epoch": 1.6893203883495147, + "grad_norm": 0.5017176866531372, + "learning_rate": 4.774063100832199e-06, + "loss": 0.8078, + "step": 174 + }, + { + "epoch": 1.6990291262135924, + "grad_norm": 0.5930182337760925, + "learning_rate": 4.717632980466652e-06, + "loss": 0.8529, + "step": 175 + }, + { + "epoch": 1.70873786407767, + "grad_norm": 0.5795880556106567, + "learning_rate": 4.661238919584578e-06, + "loss": 0.7914, + "step": 176 + }, + { + "epoch": 1.7184466019417477, + "grad_norm": 0.4433108866214752, + "learning_rate": 4.6048881199502265e-06, + "loss": 0.8377, + "step": 177 + }, + { + "epoch": 1.7281553398058254, + "grad_norm": 0.5359524488449097, + "learning_rate": 4.548587777803198e-06, + "loss": 0.841, + "step": 178 + }, + { + "epoch": 1.737864077669903, + "grad_norm": 0.5342350006103516, + "learning_rate": 4.49234508293946e-06, + "loss": 0.8118, + "step": 179 + }, + { + "epoch": 1.7475728155339807, + "grad_norm": 0.4875918924808502, + "learning_rate": 4.436167217793167e-06, + "loss": 0.8091, + "step": 180 + }, + { + "epoch": 1.7572815533980584, + "grad_norm": 0.44451451301574707, + "learning_rate": 4.38006135651944e-06, + "loss": 0.8012, + "step": 181 + }, + { + "epoch": 1.766990291262136, + "grad_norm": 0.6147545576095581, + "learning_rate": 4.3240346640782014e-06, + "loss": 0.7779, + "step": 182 + }, + { + "epoch": 1.7766990291262137, + "grad_norm": 0.4527565538883209, + "learning_rate": 4.268094295319167e-06, + "loss": 0.8184, + "step": 183 + }, + { + "epoch": 1.7864077669902914, + "grad_norm": 0.48011067509651184, + "learning_rate": 4.212247394068151e-06, + "loss": 0.8109, + "step": 184 + }, + { + "epoch": 1.796116504854369, + "grad_norm": 0.5363189578056335, + "learning_rate": 4.1565010922147644e-06, + "loss": 0.8068, + "step": 185 + }, + { + "epoch": 1.8058252427184467, + "grad_norm": 0.5342061519622803, + "learning_rate": 4.100862508801639e-06, + "loss": 0.8158, + "step": 186 + }, + { + "epoch": 1.8155339805825244, + "grad_norm": 0.4906405508518219, + "learning_rate": 4.045338749115299e-06, + "loss": 0.8012, + "step": 187 + }, + { + "epoch": 1.825242718446602, + "grad_norm": 0.4942418038845062, + "learning_rate": 3.989936903778785e-06, + "loss": 0.8276, + "step": 188 + }, + { + "epoch": 1.8349514563106797, + "grad_norm": 0.47334739565849304, + "learning_rate": 3.934664047846157e-06, + "loss": 0.7817, + "step": 189 + }, + { + "epoch": 1.8446601941747574, + "grad_norm": 0.4942063093185425, + "learning_rate": 3.879527239898962e-06, + "loss": 0.8325, + "step": 190 + }, + { + "epoch": 1.854368932038835, + "grad_norm": 0.5283282995223999, + "learning_rate": 3.8245335211448404e-06, + "loss": 0.7786, + "step": 191 + }, + { + "epoch": 1.8640776699029127, + "grad_norm": 0.5127359628677368, + "learning_rate": 3.769689914518326e-06, + "loss": 0.8142, + "step": 192 + }, + { + "epoch": 1.8737864077669903, + "grad_norm": 0.49381014704704285, + "learning_rate": 3.715003423783986e-06, + "loss": 0.7969, + "step": 193 + }, + { + "epoch": 1.883495145631068, + "grad_norm": 0.46980249881744385, + "learning_rate": 3.660481032642016e-06, + "loss": 0.7949, + "step": 194 + }, + { + "epoch": 1.8932038834951457, + "grad_norm": 0.5440580248832703, + "learning_rate": 3.6061297038363853e-06, + "loss": 0.7786, + "step": 195 + }, + { + "epoch": 1.9029126213592233, + "grad_norm": 0.5657265782356262, + "learning_rate": 3.5519563782656642e-06, + "loss": 0.8131, + "step": 196 + }, + { + "epoch": 1.912621359223301, + "grad_norm": 0.560371458530426, + "learning_rate": 3.497967974096647e-06, + "loss": 0.7723, + "step": 197 + }, + { + "epoch": 1.9223300970873787, + "grad_norm": 0.4916374087333679, + "learning_rate": 3.4441713858808684e-06, + "loss": 0.793, + "step": 198 + }, + { + "epoch": 1.9320388349514563, + "grad_norm": 0.5217000246047974, + "learning_rate": 3.3905734836741415e-06, + "loss": 0.8259, + "step": 199 + }, + { + "epoch": 1.941747572815534, + "grad_norm": 0.6433777213096619, + "learning_rate": 3.3371811121592203e-06, + "loss": 0.7691, + "step": 200 + }, + { + "epoch": 1.9514563106796117, + "grad_norm": 0.5687490701675415, + "learning_rate": 3.2840010897717045e-06, + "loss": 0.7592, + "step": 201 + }, + { + "epoch": 1.9611650485436893, + "grad_norm": 0.5231119990348816, + "learning_rate": 3.2310402078292956e-06, + "loss": 0.806, + "step": 202 + }, + { + "epoch": 1.970873786407767, + "grad_norm": 0.5205345153808594, + "learning_rate": 3.178305229664519e-06, + "loss": 0.8302, + "step": 203 + }, + { + "epoch": 1.9805825242718447, + "grad_norm": 0.5407435894012451, + "learning_rate": 3.125802889761016e-06, + "loss": 0.7726, + "step": 204 + }, + { + "epoch": 1.9902912621359223, + "grad_norm": 0.628868818283081, + "learning_rate": 3.073539892893519e-06, + "loss": 0.8098, + "step": 205 + }, + { + "epoch": 2.0, + "grad_norm": 0.5963810682296753, + "learning_rate": 3.021522913271627e-06, + "loss": 0.7834, + "step": 206 + }, + { + "epoch": 2.0097087378640777, + "grad_norm": 0.5925841927528381, + "learning_rate": 2.969758593687475e-06, + "loss": 0.7591, + "step": 207 + }, + { + "epoch": 2.0194174757281553, + "grad_norm": 0.47755351662635803, + "learning_rate": 2.9182535446674244e-06, + "loss": 0.7803, + "step": 208 + }, + { + "epoch": 2.029126213592233, + "grad_norm": 0.5342966914176941, + "learning_rate": 2.8670143436278757e-06, + "loss": 0.7553, + "step": 209 + }, + { + "epoch": 2.0388349514563107, + "grad_norm": 0.5112743377685547, + "learning_rate": 2.8160475340352913e-06, + "loss": 0.7849, + "step": 210 + }, + { + "epoch": 2.0485436893203883, + "grad_norm": 0.5908800363540649, + "learning_rate": 2.765359624570574e-06, + "loss": 0.7618, + "step": 211 + }, + { + "epoch": 2.058252427184466, + "grad_norm": 0.4771662652492523, + "learning_rate": 2.714957088297886e-06, + "loss": 0.6928, + "step": 212 + }, + { + "epoch": 2.0679611650485437, + "grad_norm": 0.5731369853019714, + "learning_rate": 2.664846361837997e-06, + "loss": 0.7647, + "step": 213 + }, + { + "epoch": 2.0776699029126213, + "grad_norm": 0.4691663384437561, + "learning_rate": 2.6150338445463146e-06, + "loss": 0.7537, + "step": 214 + }, + { + "epoch": 2.087378640776699, + "grad_norm": 0.5235918760299683, + "learning_rate": 2.565525897695651e-06, + "loss": 0.7775, + "step": 215 + }, + { + "epoch": 2.0970873786407767, + "grad_norm": 0.49530091881752014, + "learning_rate": 2.51632884366386e-06, + "loss": 0.7784, + "step": 216 + }, + { + "epoch": 2.1067961165048543, + "grad_norm": 0.5703685283660889, + "learning_rate": 2.4674489651264433e-06, + "loss": 0.7207, + "step": 217 + }, + { + "epoch": 2.116504854368932, + "grad_norm": 0.45397961139678955, + "learning_rate": 2.418892504254231e-06, + "loss": 0.7493, + "step": 218 + }, + { + "epoch": 2.1262135922330097, + "grad_norm": 0.512279212474823, + "learning_rate": 2.3706656619162278e-06, + "loss": 0.7775, + "step": 219 + }, + { + "epoch": 2.1359223300970873, + "grad_norm": 0.5071080327033997, + "learning_rate": 2.322774596887726e-06, + "loss": 0.7594, + "step": 220 + }, + { + "epoch": 2.145631067961165, + "grad_norm": 0.5117892026901245, + "learning_rate": 2.275225425063813e-06, + "loss": 0.7265, + "step": 221 + }, + { + "epoch": 2.1553398058252426, + "grad_norm": 0.4993806779384613, + "learning_rate": 2.2280242186783473e-06, + "loss": 0.7149, + "step": 222 + }, + { + "epoch": 2.1650485436893203, + "grad_norm": 0.4563067853450775, + "learning_rate": 2.1811770055284968e-06, + "loss": 0.7902, + "step": 223 + }, + { + "epoch": 2.174757281553398, + "grad_norm": 0.47798827290534973, + "learning_rate": 2.134689768204975e-06, + "loss": 0.7583, + "step": 224 + }, + { + "epoch": 2.1844660194174756, + "grad_norm": 0.46698057651519775, + "learning_rate": 2.0885684433280336e-06, + "loss": 0.7717, + "step": 225 + }, + { + "epoch": 2.1941747572815533, + "grad_norm": 0.46322739124298096, + "learning_rate": 2.042818920789326e-06, + "loss": 0.7622, + "step": 226 + }, + { + "epoch": 2.203883495145631, + "grad_norm": 0.4613381028175354, + "learning_rate": 1.9974470429997482e-06, + "loss": 0.7508, + "step": 227 + }, + { + "epoch": 2.2135922330097086, + "grad_norm": 0.4670693278312683, + "learning_rate": 1.9524586041433393e-06, + "loss": 0.7132, + "step": 228 + }, + { + "epoch": 2.2233009708737863, + "grad_norm": 0.45155465602874756, + "learning_rate": 1.907859349437336e-06, + "loss": 0.7544, + "step": 229 + }, + { + "epoch": 2.233009708737864, + "grad_norm": 0.4583199620246887, + "learning_rate": 1.8636549743984815e-06, + "loss": 0.7485, + "step": 230 + }, + { + "epoch": 2.2427184466019416, + "grad_norm": 0.4572857618331909, + "learning_rate": 1.8198511241156902e-06, + "loss": 0.7552, + "step": 231 + }, + { + "epoch": 2.2524271844660193, + "grad_norm": 0.47898781299591064, + "learning_rate": 1.776453392529139e-06, + "loss": 0.7683, + "step": 232 + }, + { + "epoch": 2.262135922330097, + "grad_norm": 0.47700902819633484, + "learning_rate": 1.7334673217158976e-06, + "loss": 0.7444, + "step": 233 + }, + { + "epoch": 2.2718446601941746, + "grad_norm": 0.45447424054145813, + "learning_rate": 1.6908984011821883e-06, + "loss": 0.7495, + "step": 234 + }, + { + "epoch": 2.2815533980582523, + "grad_norm": 0.4574134647846222, + "learning_rate": 1.6487520671623469e-06, + "loss": 0.7545, + "step": 235 + }, + { + "epoch": 2.29126213592233, + "grad_norm": 0.4218170642852783, + "learning_rate": 1.6070337019245896e-06, + "loss": 0.7521, + "step": 236 + }, + { + "epoch": 2.3009708737864076, + "grad_norm": 0.41513901948928833, + "learning_rate": 1.5657486330836786e-06, + "loss": 0.759, + "step": 237 + }, + { + "epoch": 2.3106796116504853, + "grad_norm": 0.4804514944553375, + "learning_rate": 1.5249021329205638e-06, + "loss": 0.757, + "step": 238 + }, + { + "epoch": 2.320388349514563, + "grad_norm": 0.48271673917770386, + "learning_rate": 1.4844994177090871e-06, + "loss": 0.7533, + "step": 239 + }, + { + "epoch": 2.3300970873786406, + "grad_norm": 0.4723464846611023, + "learning_rate": 1.4445456470498392e-06, + "loss": 0.7859, + "step": 240 + }, + { + "epoch": 2.3398058252427183, + "grad_norm": 0.4236687123775482, + "learning_rate": 1.4050459232112652e-06, + "loss": 0.7873, + "step": 241 + }, + { + "epoch": 2.349514563106796, + "grad_norm": 0.4499347507953644, + "learning_rate": 1.3660052904780707e-06, + "loss": 0.7664, + "step": 242 + }, + { + "epoch": 2.3592233009708736, + "grad_norm": 0.4442787170410156, + "learning_rate": 1.3274287345070564e-06, + "loss": 0.7408, + "step": 243 + }, + { + "epoch": 2.3689320388349513, + "grad_norm": 0.45914286375045776, + "learning_rate": 1.2893211816904243e-06, + "loss": 0.7218, + "step": 244 + }, + { + "epoch": 2.378640776699029, + "grad_norm": 0.42868661880493164, + "learning_rate": 1.2516874985266508e-06, + "loss": 0.7466, + "step": 245 + }, + { + "epoch": 2.3883495145631066, + "grad_norm": 0.46668022871017456, + "learning_rate": 1.2145324909990202e-06, + "loss": 0.7116, + "step": 246 + }, + { + "epoch": 2.3980582524271843, + "grad_norm": 0.47152259945869446, + "learning_rate": 1.1778609039618804e-06, + "loss": 0.7446, + "step": 247 + }, + { + "epoch": 2.407766990291262, + "grad_norm": 0.4311952292919159, + "learning_rate": 1.1416774205347015e-06, + "loss": 0.7546, + "step": 248 + }, + { + "epoch": 2.4174757281553396, + "grad_norm": 0.47215738892555237, + "learning_rate": 1.1059866615040205e-06, + "loss": 0.7843, + "step": 249 + }, + { + "epoch": 2.4271844660194173, + "grad_norm": 0.42326658964157104, + "learning_rate": 1.0707931847333487e-06, + "loss": 0.7519, + "step": 250 + }, + { + "epoch": 2.436893203883495, + "grad_norm": 0.43430864810943604, + "learning_rate": 1.036101484581117e-06, + "loss": 0.7283, + "step": 251 + }, + { + "epoch": 2.4466019417475726, + "grad_norm": 0.45083683729171753, + "learning_rate": 1.0019159913267156e-06, + "loss": 0.7529, + "step": 252 + }, + { + "epoch": 2.4563106796116507, + "grad_norm": 0.49279189109802246, + "learning_rate": 9.68241070604743e-07, + "loss": 0.763, + "step": 253 + }, + { + "epoch": 2.466019417475728, + "grad_norm": 0.44121843576431274, + "learning_rate": 9.350810228474855e-07, + "loss": 0.7093, + "step": 254 + }, + { + "epoch": 2.475728155339806, + "grad_norm": 0.46301037073135376, + "learning_rate": 9.024400827357344e-07, + "loss": 0.7699, + "step": 255 + }, + { + "epoch": 2.4854368932038833, + "grad_norm": 0.4788742661476135, + "learning_rate": 8.703224186580012e-07, + "loss": 0.7811, + "step": 256 + }, + { + "epoch": 2.4951456310679614, + "grad_norm": 0.4840719401836395, + "learning_rate": 8.387321321781977e-07, + "loss": 0.7633, + "step": 257 + }, + { + "epoch": 2.5048543689320386, + "grad_norm": 0.4576054811477661, + "learning_rate": 8.07673257511849e-07, + "loss": 0.7755, + "step": 258 + }, + { + "epoch": 2.5145631067961167, + "grad_norm": 0.43629974126815796, + "learning_rate": 7.771497610108981e-07, + "loss": 0.7574, + "step": 259 + }, + { + "epoch": 2.524271844660194, + "grad_norm": 0.4582881033420563, + "learning_rate": 7.471655406572003e-07, + "loss": 0.7703, + "step": 260 + }, + { + "epoch": 2.533980582524272, + "grad_norm": 0.4240984618663788, + "learning_rate": 7.177244255647209e-07, + "loss": 0.7567, + "step": 261 + }, + { + "epoch": 2.5436893203883493, + "grad_norm": 0.4236100912094116, + "learning_rate": 6.888301754905469e-07, + "loss": 0.7912, + "step": 262 + }, + { + "epoch": 2.5533980582524274, + "grad_norm": 0.40091320872306824, + "learning_rate": 6.604864803547511e-07, + "loss": 0.7474, + "step": 263 + }, + { + "epoch": 2.5631067961165046, + "grad_norm": 0.44925597310066223, + "learning_rate": 6.326969597691724e-07, + "loss": 0.7381, + "step": 264 + }, + { + "epoch": 2.5728155339805827, + "grad_norm": 0.4370911121368408, + "learning_rate": 6.054651625751717e-07, + "loss": 0.7587, + "step": 265 + }, + { + "epoch": 2.58252427184466, + "grad_norm": 0.43402257561683655, + "learning_rate": 5.787945663904332e-07, + "loss": 0.7715, + "step": 266 + }, + { + "epoch": 2.592233009708738, + "grad_norm": 0.4456167221069336, + "learning_rate": 5.526885771648599e-07, + "loss": 0.7469, + "step": 267 + }, + { + "epoch": 2.6019417475728153, + "grad_norm": 0.44401729106903076, + "learning_rate": 5.271505287456153e-07, + "loss": 0.7223, + "step": 268 + }, + { + "epoch": 2.6116504854368934, + "grad_norm": 0.4610472023487091, + "learning_rate": 5.021836824513759e-07, + "loss": 0.7802, + "step": 269 + }, + { + "epoch": 2.6213592233009706, + "grad_norm": 0.4633938670158386, + "learning_rate": 4.777912266558532e-07, + "loss": 0.7417, + "step": 270 + }, + { + "epoch": 2.6310679611650487, + "grad_norm": 0.4150261878967285, + "learning_rate": 4.5397627638061604e-07, + "loss": 0.7705, + "step": 271 + }, + { + "epoch": 2.6407766990291264, + "grad_norm": 0.45528119802474976, + "learning_rate": 4.307418728972934e-07, + "loss": 0.7391, + "step": 272 + }, + { + "epoch": 2.650485436893204, + "grad_norm": 0.4313214123249054, + "learning_rate": 4.080909833391944e-07, + "loss": 0.7624, + "step": 273 + }, + { + "epoch": 2.6601941747572817, + "grad_norm": 0.403175950050354, + "learning_rate": 3.8602650032238675e-07, + "loss": 0.7797, + "step": 274 + }, + { + "epoch": 2.6699029126213594, + "grad_norm": 0.4482267498970032, + "learning_rate": 3.6455124157629805e-07, + "loss": 0.7373, + "step": 275 + }, + { + "epoch": 2.679611650485437, + "grad_norm": 0.42840349674224854, + "learning_rate": 3.436679495838835e-07, + "loss": 0.7349, + "step": 276 + }, + { + "epoch": 2.6893203883495147, + "grad_norm": 0.41052892804145813, + "learning_rate": 3.233792912313943e-07, + "loss": 0.754, + "step": 277 + }, + { + "epoch": 2.6990291262135924, + "grad_norm": 0.4851820170879364, + "learning_rate": 3.0368785746780925e-07, + "loss": 0.7887, + "step": 278 + }, + { + "epoch": 2.70873786407767, + "grad_norm": 0.43496590852737427, + "learning_rate": 2.8459616297395464e-07, + "loss": 0.7558, + "step": 279 + }, + { + "epoch": 2.7184466019417477, + "grad_norm": 0.44541043043136597, + "learning_rate": 2.6610664584137413e-07, + "loss": 0.7088, + "step": 280 + }, + { + "epoch": 2.7281553398058254, + "grad_norm": 0.45385488867759705, + "learning_rate": 2.482216672609677e-07, + "loss": 0.7279, + "step": 281 + }, + { + "epoch": 2.737864077669903, + "grad_norm": 0.4380588233470917, + "learning_rate": 2.3094351122146307e-07, + "loss": 0.7354, + "step": 282 + }, + { + "epoch": 2.7475728155339807, + "grad_norm": 0.4383409321308136, + "learning_rate": 2.142743842177386e-07, + "loss": 0.7427, + "step": 283 + }, + { + "epoch": 2.7572815533980584, + "grad_norm": 0.4154166579246521, + "learning_rate": 1.98216414969043e-07, + "loss": 0.7533, + "step": 284 + }, + { + "epoch": 2.766990291262136, + "grad_norm": 0.40241143107414246, + "learning_rate": 1.8277165414714858e-07, + "loss": 0.7471, + "step": 285 + }, + { + "epoch": 2.7766990291262137, + "grad_norm": 0.4261252284049988, + "learning_rate": 1.6794207411447548e-07, + "loss": 0.7628, + "step": 286 + }, + { + "epoch": 2.7864077669902914, + "grad_norm": 0.39932355284690857, + "learning_rate": 1.5372956867220678e-07, + "loss": 0.7747, + "step": 287 + }, + { + "epoch": 2.796116504854369, + "grad_norm": 0.40878960490226746, + "learning_rate": 1.4013595281844872e-07, + "loss": 0.7583, + "step": 288 + }, + { + "epoch": 2.8058252427184467, + "grad_norm": 0.42195621132850647, + "learning_rate": 1.2716296251644e-07, + "loss": 0.7675, + "step": 289 + }, + { + "epoch": 2.8155339805825244, + "grad_norm": 0.41512733697891235, + "learning_rate": 1.1481225447286803e-07, + "loss": 0.7228, + "step": 290 + }, + { + "epoch": 2.825242718446602, + "grad_norm": 0.42841315269470215, + "learning_rate": 1.0308540592629756e-07, + "loss": 0.7937, + "step": 291 + }, + { + "epoch": 2.8349514563106797, + "grad_norm": 0.445648193359375, + "learning_rate": 9.198391444575072e-08, + "loss": 0.7037, + "step": 292 + }, + { + "epoch": 2.8446601941747574, + "grad_norm": 0.4242344796657562, + "learning_rate": 8.150919773946165e-08, + "loss": 0.7795, + "step": 293 + }, + { + "epoch": 2.854368932038835, + "grad_norm": 0.4234623610973358, + "learning_rate": 7.166259347382854e-08, + "loss": 0.7292, + "step": 294 + }, + { + "epoch": 2.8640776699029127, + "grad_norm": 0.3901122808456421, + "learning_rate": 6.244535910258697e-08, + "loss": 0.776, + "step": 295 + }, + { + "epoch": 2.8737864077669903, + "grad_norm": 0.41637924313545227, + "learning_rate": 5.3858671706230605e-08, + "loss": 0.7917, + "step": 296 + }, + { + "epoch": 2.883495145631068, + "grad_norm": 0.39965224266052246, + "learning_rate": 4.590362784169022e-08, + "loss": 0.8002, + "step": 297 + }, + { + "epoch": 2.8932038834951457, + "grad_norm": 0.48560866713523865, + "learning_rate": 3.858124340229863e-08, + "loss": 0.7326, + "step": 298 + }, + { + "epoch": 2.9029126213592233, + "grad_norm": 0.41089245676994324, + "learning_rate": 3.1892453488058803e-08, + "loss": 0.7604, + "step": 299 + }, + { + "epoch": 2.912621359223301, + "grad_norm": 0.4088441729545593, + "learning_rate": 2.5838112286226123e-08, + "loss": 0.7339, + "step": 300 + }, + { + "epoch": 2.9223300970873787, + "grad_norm": 0.43762901425361633, + "learning_rate": 2.0418992962224495e-08, + "loss": 0.7299, + "step": 301 + }, + { + "epoch": 2.9320388349514563, + "grad_norm": 0.41060447692871094, + "learning_rate": 1.563578756091144e-08, + "loss": 0.7919, + "step": 302 + }, + { + "epoch": 2.941747572815534, + "grad_norm": 0.4254586398601532, + "learning_rate": 1.1489106918200487e-08, + "loss": 0.6998, + "step": 303 + }, + { + "epoch": 2.9514563106796117, + "grad_norm": 0.4328642785549164, + "learning_rate": 7.979480583052423e-09, + "loss": 0.7362, + "step": 304 + }, + { + "epoch": 2.9611650485436893, + "grad_norm": 0.40661028027534485, + "learning_rate": 5.107356749853298e-09, + "loss": 0.7416, + "step": 305 + }, + { + "epoch": 2.970873786407767, + "grad_norm": 0.4029662609100342, + "learning_rate": 2.8731022011757593e-09, + "loss": 0.7835, + "step": 306 + }, + { + "epoch": 2.9805825242718447, + "grad_norm": 0.4190027117729187, + "learning_rate": 1.2770022609409628e-09, + "loss": 0.7464, + "step": 307 + }, + { + "epoch": 2.9902912621359223, + "grad_norm": 0.40702641010284424, + "learning_rate": 3.1926075797827914e-10, + "loss": 0.7806, + "step": 308 + }, + { + "epoch": 3.0, + "grad_norm": 0.40051835775375366, + "learning_rate": 0.0, + "loss": 0.7573, + "step": 309 + }, + { + "epoch": 3.0, + "step": 309, + "total_flos": 266439779352576.0, + "train_loss": 0.8324689010586168, + "train_runtime": 15120.0259, + "train_samples_per_second": 1.962, + "train_steps_per_second": 0.02 + } + ], + "logging_steps": 1.0, + "max_steps": 309, + "num_input_tokens_seen": 0, + "num_train_epochs": 3, + "save_steps": 500, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": true + }, + "attributes": {} + } + }, + "total_flos": 266439779352576.0, + "train_batch_size": 1, + "trial_name": null, + "trial_params": null +} diff --git a/training_args.bin b/training_args.bin new file mode 100644 index 0000000..0315718 --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f5e8d835a90bedbbbb289c9b753e8a556f16c495e7319737684d39c68e39e8d +size 7416 diff --git a/training_loss.png b/training_loss.png new file mode 100644 index 0000000..38a54f8 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