commit 350b9608f05d5415a345ffff91585411383a87df Author: ModelHub XC Date: Tue May 26 00:22:23 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mlfoundations-dev/oh-dcft-v3.1-gemini-1.5-flash Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..52373fe --- /dev/null +++ b/.gitattributes @@ -0,0 +1,36 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt 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 +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz 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 +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl 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 +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* 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 +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..a7eb080 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +library_name: transformers +license: llama3.1 +base_model: meta-llama/Meta-Llama-3.1-8B +tags: +- llama-factory +- full +- generated_from_trainer +model-index: +- name: oh-dcft-v3.1-gemini-1.5-flash + results: [] +--- + + + +# oh-dcft-v3.1-gemini-1.5-flash + +This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on the mlfoundations-dev/oh-dcft-v3.1-gemini-1.5-flash dataset. +It achieves the following results on the evaluation set: +- Loss: 0.5841 + +## Model description + +More information needed + +## Intended uses & limitations + +More information needed + +## Training and evaluation data + +More information needed + +## Training procedure + +### Training hyperparameters + +The following hyperparameters were used during training: +- learning_rate: 5e-06 +- train_batch_size: 8 +- eval_batch_size: 8 +- seed: 42 +- distributed_type: multi-GPU +- num_devices: 8 +- gradient_accumulation_steps: 8 +- total_train_batch_size: 512 +- total_eval_batch_size: 64 +- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments +- lr_scheduler_type: constant +- num_epochs: 3.0 + +### Training results + +| Training Loss | Epoch | Step | Validation Loss | +|:-------------:|:------:|:----:|:---------------:| +| 0.5979 | 0.9979 | 425 | 0.6003 | +| 0.547 | 1.9985 | 851 | 0.5847 | +| 0.5003 | 2.9944 | 1275 | 0.5841 | + + +### Framework versions + +- Transformers 4.46.1 +- Pytorch 2.3.0 +- Datasets 3.1.0 +- Tokenizers 0.20.3 diff --git a/all_results.json b/all_results.json new file mode 100644 index 0000000..b9b54b9 --- /dev/null +++ b/all_results.json @@ -0,0 +1,12 @@ +{ + "epoch": 2.9944232462577047, + "eval_loss": 0.5840933322906494, + "eval_runtime": 287.6095, + "eval_samples_per_second": 39.894, + "eval_steps_per_second": 0.626, + "total_flos": 2135463108280320.0, + "train_loss": 0.5660238438026578, + "train_runtime": 41769.8593, + "train_samples_per_second": 15.658, + "train_steps_per_second": 0.031 +} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..c3a9daf --- /dev/null +++ b/config.json @@ -0,0 +1,36 @@ +{ + "_name_or_path": "meta-llama/Meta-Llama-3.1-8B", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "eos_token_id": 128001, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.46.1", + "use_cache": false, + "vocab_size": 128256 +} diff --git a/configs.yaml b/configs.yaml new file mode 100644 index 0000000..496fec0 --- /dev/null +++ b/configs.yaml @@ -0,0 +1,41 @@ +adam_beta1: '0.9' +adam_beta2: '0.999' +bf16: 'True' +cutoff_len: '2048' +dataset: mlfoundations-dev/oh-dcft-v3.1-gemini-1.5-flash +dataset_dir: ONLINE +ddp_timeout: '180000000' +deepspeed: /opt/ml/code/zero3.json +do_train: 'True' +enable_liger_kernel: 'False' +eval_strategy: epoch +finetuning_type: full +formatting: sharegpt +global_batch_size: '512' +gradient_accumulation_steps: '8' +gradient_checkpointing: 'True' +hub_model_id: mlfoundations-dev/oh-dcft-v3.1-gemini-1.5-flash +learning_rate: 5e-06 +logging_steps: '10' +lr_scheduler_type: constant +max_grad_norm: '1' +messages: conversations +model_name_or_path: meta-llama/Meta-Llama-3.1-8B +neat_packing: 'True' +num_train_epochs: '3.0' +output_dir: /opt/ml/model +overwrite_cache: 'True' +overwrite_output_dir: 'True' +packing: 'True' +per_device_train_batch_size: '8' +plot_loss: 'True' +preprocessing_num_workers: '16' +push_to_db: 'True' +push_to_hub: 'True' +report_to: wandb +run_name: oh-dcft-v3.1-gemini-1.5-flash +save_strategy: epoch +stage: sft +template: llama3 +val_size: '0.05' +weight_decay: '0.1' diff --git a/eval_results.json b/eval_results.json new file mode 100644 index 0000000..2329285 --- /dev/null +++ b/eval_results.json @@ -0,0 +1,7 @@ +{ + "epoch": 2.9944232462577047, + "eval_loss": 0.5840933322906494, + "eval_runtime": 287.6095, + "eval_samples_per_second": 39.894, + "eval_steps_per_second": 0.626 +} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..eab5082 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,9 @@ +{ + "_from_model_config": true, + "bos_token_id": 128000, + "do_sample": true, + "eos_token_id": 128001, + "temperature": 0.6, + "top_p": 0.9, + "transformers_version": "4.46.1" +} diff --git a/model-00001-of-00004.safetensors b/model-00001-of-00004.safetensors new file mode 100644 index 0000000..bc5f282 --- /dev/null +++ b/model-00001-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1856ac7ca47613b55a850f977dcdc4cfc49b732013801fc21c438a1f09ab2af5 +size 4976698672 diff --git a/model-00002-of-00004.safetensors b/model-00002-of-00004.safetensors new file mode 100644 index 0000000..65cb52e --- /dev/null +++ b/model-00002-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e37b66213d32da61eaedc3911c95eabbc1c73c2c73a5c46944432010342d2687 +size 4999802720 diff --git a/model-00003-of-00004.safetensors b/model-00003-of-00004.safetensors new file mode 100644 index 0000000..4ff9732 --- /dev/null +++ b/model-00003-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2b0a1e5be178a7a974e8165ff7461c0ad67673150dac40a6898077a60af445d +size 4915916176 diff --git a/model-00004-of-00004.safetensors b/model-00004-of-00004.safetensors new file mode 100644 index 0000000..a18ea9b --- /dev/null +++ b/model-00004-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:849777b28c61e16fa99f774190933588c19991b2dd9bbda52eaccef4c1cd814f +size 1168138808 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..0fd8120 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,298 @@ +{ + "metadata": { + "total_size": 16060522496 + }, + "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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-00002-of-00004.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00002-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-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.weight": "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-00002-of-00004.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00002-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.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.weight": "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-00002-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.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00002-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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.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.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.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00003-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.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.weight": "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.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.weight": "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.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.weight": "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.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.weight": "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-00001-of-00004.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.post_attention_layernorm.weight": "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.weight": "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.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.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.norm.weight": "model-00004-of-00004.safetensors" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..b43be96 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,17 @@ +{ + "bos_token": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "<|eot_id|>" +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..1c1d8d5 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b +size 17209920 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..3ae1585 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,2065 @@ +{ + "added_tokens_decoder": { + "128000": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128001": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128002": { + "content": "<|reserved_special_token_0|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128003": { + "content": "<|reserved_special_token_1|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128004": { + "content": "<|finetune_right_pad_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128005": { + "content": "<|reserved_special_token_2|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128006": { + "content": "<|start_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128007": { + "content": "<|end_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128008": { + "content": "<|eom_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128009": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128010": { + "content": "<|python_tag|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128011": { + "content": "<|reserved_special_token_3|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128012": { + "content": "<|reserved_special_token_4|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128013": { + "content": "<|reserved_special_token_5|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128014": { + "content": "<|reserved_special_token_6|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128015": { + "content": "<|reserved_special_token_7|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128016": { + "content": "<|reserved_special_token_8|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128017": { + "content": "<|reserved_special_token_9|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128018": { + "content": "<|reserved_special_token_10|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128019": { + "content": "<|reserved_special_token_11|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128020": { + "content": "<|reserved_special_token_12|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128021": { + "content": "<|reserved_special_token_13|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128022": { + "content": "<|reserved_special_token_14|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128023": { + "content": "<|reserved_special_token_15|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128024": { + "content": "<|reserved_special_token_16|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128025": { + "content": "<|reserved_special_token_17|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128026": { + "content": "<|reserved_special_token_18|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128027": { + "content": "<|reserved_special_token_19|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128028": { + "content": "<|reserved_special_token_20|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128029": { + "content": "<|reserved_special_token_21|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128030": { + "content": "<|reserved_special_token_22|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128031": { + "content": "<|reserved_special_token_23|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128032": { + "content": "<|reserved_special_token_24|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128033": { + "content": "<|reserved_special_token_25|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128034": { + "content": "<|reserved_special_token_26|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128035": { + "content": "<|reserved_special_token_27|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128036": { + "content": "<|reserved_special_token_28|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128037": { + "content": "<|reserved_special_token_29|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128038": { + "content": "<|reserved_special_token_30|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128039": { + "content": "<|reserved_special_token_31|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128040": { + "content": "<|reserved_special_token_32|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128041": { + "content": "<|reserved_special_token_33|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128042": { + "content": "<|reserved_special_token_34|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128043": { + "content": "<|reserved_special_token_35|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128044": { + "content": "<|reserved_special_token_36|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128045": { + "content": "<|reserved_special_token_37|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128046": { + "content": "<|reserved_special_token_38|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128047": { + "content": "<|reserved_special_token_39|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128048": { + "content": "<|reserved_special_token_40|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128049": { + "content": "<|reserved_special_token_41|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128050": { + "content": "<|reserved_special_token_42|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128051": { + "content": "<|reserved_special_token_43|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128052": { + "content": "<|reserved_special_token_44|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128053": { + "content": "<|reserved_special_token_45|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128054": { + "content": "<|reserved_special_token_46|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128055": { + "content": "<|reserved_special_token_47|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128056": { + "content": "<|reserved_special_token_48|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128057": { + "content": "<|reserved_special_token_49|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128058": { + "content": "<|reserved_special_token_50|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128059": { + "content": "<|reserved_special_token_51|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128060": { + "content": "<|reserved_special_token_52|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128061": { + "content": "<|reserved_special_token_53|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128062": { + "content": "<|reserved_special_token_54|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128063": { + "content": "<|reserved_special_token_55|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128064": { + "content": "<|reserved_special_token_56|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128065": { + "content": "<|reserved_special_token_57|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128066": { + "content": "<|reserved_special_token_58|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128067": { + "content": "<|reserved_special_token_59|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128068": { + "content": "<|reserved_special_token_60|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128069": { + "content": "<|reserved_special_token_61|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128070": { + "content": "<|reserved_special_token_62|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128071": { + "content": "<|reserved_special_token_63|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128072": { + "content": "<|reserved_special_token_64|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128073": { + "content": "<|reserved_special_token_65|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128074": { + "content": "<|reserved_special_token_66|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128075": { + "content": "<|reserved_special_token_67|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128076": { + "content": "<|reserved_special_token_68|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128077": { + "content": "<|reserved_special_token_69|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128078": { + "content": "<|reserved_special_token_70|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128079": { + "content": "<|reserved_special_token_71|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128080": { + "content": "<|reserved_special_token_72|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128081": { + "content": "<|reserved_special_token_73|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128082": { + "content": "<|reserved_special_token_74|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128083": { + "content": "<|reserved_special_token_75|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128084": { + "content": "<|reserved_special_token_76|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128085": { + "content": "<|reserved_special_token_77|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128086": { + "content": "<|reserved_special_token_78|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128087": { + "content": "<|reserved_special_token_79|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128088": { + "content": "<|reserved_special_token_80|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128089": { + "content": "<|reserved_special_token_81|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128090": { + "content": "<|reserved_special_token_82|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128091": { + "content": "<|reserved_special_token_83|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128092": { + "content": "<|reserved_special_token_84|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128093": { + "content": "<|reserved_special_token_85|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128094": { + "content": "<|reserved_special_token_86|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128095": { + "content": "<|reserved_special_token_87|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128096": { + "content": "<|reserved_special_token_88|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128097": { + "content": "<|reserved_special_token_89|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128098": { + "content": "<|reserved_special_token_90|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128099": { + "content": "<|reserved_special_token_91|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128100": { + "content": "<|reserved_special_token_92|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128101": { + "content": "<|reserved_special_token_93|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128102": { + "content": "<|reserved_special_token_94|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128103": { + "content": "<|reserved_special_token_95|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128104": { + "content": "<|reserved_special_token_96|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128105": { + "content": "<|reserved_special_token_97|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128106": { + "content": "<|reserved_special_token_98|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128107": { + "content": "<|reserved_special_token_99|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128108": { + "content": "<|reserved_special_token_100|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128109": { + "content": "<|reserved_special_token_101|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128110": { + "content": "<|reserved_special_token_102|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128111": { + "content": "<|reserved_special_token_103|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128112": { + "content": "<|reserved_special_token_104|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128113": { + "content": "<|reserved_special_token_105|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128114": { + "content": "<|reserved_special_token_106|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128115": { + "content": "<|reserved_special_token_107|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128116": { + "content": "<|reserved_special_token_108|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128117": { + "content": "<|reserved_special_token_109|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128118": { + "content": "<|reserved_special_token_110|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128119": { + "content": "<|reserved_special_token_111|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128120": { + "content": "<|reserved_special_token_112|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128121": { + "content": "<|reserved_special_token_113|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128122": { + "content": "<|reserved_special_token_114|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128123": { + "content": "<|reserved_special_token_115|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128124": { + "content": "<|reserved_special_token_116|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128125": { + "content": "<|reserved_special_token_117|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128126": { + "content": "<|reserved_special_token_118|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128127": { + "content": "<|reserved_special_token_119|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128128": { + "content": "<|reserved_special_token_120|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128129": { + "content": "<|reserved_special_token_121|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128130": { + "content": "<|reserved_special_token_122|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128131": { + "content": "<|reserved_special_token_123|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128132": { + "content": "<|reserved_special_token_124|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128133": { + "content": "<|reserved_special_token_125|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128134": { + "content": "<|reserved_special_token_126|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128135": { + "content": "<|reserved_special_token_127|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128136": { + "content": "<|reserved_special_token_128|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128137": { + "content": "<|reserved_special_token_129|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128138": { + "content": "<|reserved_special_token_130|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128139": { + "content": "<|reserved_special_token_131|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128140": { + "content": "<|reserved_special_token_132|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128141": { + "content": "<|reserved_special_token_133|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128142": { + "content": "<|reserved_special_token_134|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128143": { + "content": "<|reserved_special_token_135|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128144": { + "content": "<|reserved_special_token_136|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128145": { + "content": "<|reserved_special_token_137|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128146": { + "content": "<|reserved_special_token_138|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128147": { + "content": "<|reserved_special_token_139|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128148": { + "content": "<|reserved_special_token_140|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128149": { + "content": "<|reserved_special_token_141|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128150": { + "content": "<|reserved_special_token_142|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128151": { + "content": "<|reserved_special_token_143|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128152": { + "content": "<|reserved_special_token_144|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128153": { + "content": "<|reserved_special_token_145|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128154": { + "content": "<|reserved_special_token_146|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128155": { + "content": "<|reserved_special_token_147|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128156": { + "content": "<|reserved_special_token_148|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128157": { + "content": "<|reserved_special_token_149|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128158": { + "content": "<|reserved_special_token_150|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128159": { + "content": "<|reserved_special_token_151|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128160": { + "content": "<|reserved_special_token_152|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128161": { + "content": "<|reserved_special_token_153|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128162": { + "content": "<|reserved_special_token_154|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128163": { + "content": "<|reserved_special_token_155|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128164": { + "content": "<|reserved_special_token_156|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128165": { + "content": "<|reserved_special_token_157|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128166": { + "content": "<|reserved_special_token_158|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128167": { + "content": "<|reserved_special_token_159|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128168": { + "content": "<|reserved_special_token_160|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128169": { + "content": "<|reserved_special_token_161|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128170": { + "content": "<|reserved_special_token_162|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128171": { + "content": "<|reserved_special_token_163|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128172": { + "content": "<|reserved_special_token_164|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128173": { + "content": "<|reserved_special_token_165|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128174": { + "content": "<|reserved_special_token_166|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128175": { + "content": "<|reserved_special_token_167|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128176": { + "content": "<|reserved_special_token_168|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128177": { + "content": "<|reserved_special_token_169|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128178": { + "content": "<|reserved_special_token_170|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128179": { + "content": "<|reserved_special_token_171|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128180": { + "content": "<|reserved_special_token_172|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128181": { + "content": "<|reserved_special_token_173|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128182": { + "content": "<|reserved_special_token_174|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128183": { + "content": "<|reserved_special_token_175|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128184": { + "content": "<|reserved_special_token_176|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128185": { + "content": "<|reserved_special_token_177|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128186": { + "content": "<|reserved_special_token_178|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128187": { + "content": "<|reserved_special_token_179|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128188": { + "content": "<|reserved_special_token_180|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128189": { + "content": "<|reserved_special_token_181|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128190": { + "content": "<|reserved_special_token_182|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128191": { + "content": "<|reserved_special_token_183|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128192": { + "content": "<|reserved_special_token_184|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128193": { + "content": "<|reserved_special_token_185|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128194": { + "content": "<|reserved_special_token_186|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128195": { + "content": "<|reserved_special_token_187|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128196": { + "content": "<|reserved_special_token_188|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128197": { + "content": "<|reserved_special_token_189|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128198": { + "content": "<|reserved_special_token_190|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128199": { + "content": "<|reserved_special_token_191|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128200": { + "content": "<|reserved_special_token_192|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128201": { + "content": "<|reserved_special_token_193|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128202": { + "content": "<|reserved_special_token_194|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128203": { + "content": "<|reserved_special_token_195|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128204": { + "content": "<|reserved_special_token_196|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128205": { + "content": "<|reserved_special_token_197|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128206": { + "content": "<|reserved_special_token_198|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128207": { + "content": "<|reserved_special_token_199|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128208": { + "content": "<|reserved_special_token_200|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128209": { + "content": "<|reserved_special_token_201|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128210": { + "content": "<|reserved_special_token_202|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128211": { + "content": "<|reserved_special_token_203|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128212": { + "content": "<|reserved_special_token_204|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128213": { + "content": "<|reserved_special_token_205|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128214": { + "content": "<|reserved_special_token_206|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128215": { + "content": "<|reserved_special_token_207|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128216": { + "content": "<|reserved_special_token_208|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128217": { + "content": "<|reserved_special_token_209|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128218": { + "content": "<|reserved_special_token_210|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128219": { + "content": "<|reserved_special_token_211|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128220": { + "content": "<|reserved_special_token_212|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128221": { + "content": "<|reserved_special_token_213|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128222": { + "content": "<|reserved_special_token_214|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128223": { + "content": "<|reserved_special_token_215|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128224": { + "content": "<|reserved_special_token_216|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128225": { + "content": "<|reserved_special_token_217|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128226": { + "content": "<|reserved_special_token_218|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128227": { + "content": "<|reserved_special_token_219|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128228": { + "content": "<|reserved_special_token_220|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128229": { + "content": "<|reserved_special_token_221|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128230": { + "content": "<|reserved_special_token_222|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128231": { + "content": "<|reserved_special_token_223|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128232": { + "content": "<|reserved_special_token_224|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128233": { + "content": "<|reserved_special_token_225|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128234": { + "content": "<|reserved_special_token_226|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128235": { + "content": "<|reserved_special_token_227|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128236": { + "content": "<|reserved_special_token_228|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128237": { + "content": "<|reserved_special_token_229|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128238": { + "content": "<|reserved_special_token_230|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128239": { + "content": "<|reserved_special_token_231|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128240": { + "content": "<|reserved_special_token_232|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128241": { + "content": "<|reserved_special_token_233|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128242": { + "content": "<|reserved_special_token_234|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128243": { + "content": "<|reserved_special_token_235|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128244": { + "content": "<|reserved_special_token_236|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128245": { + "content": "<|reserved_special_token_237|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128246": { + "content": "<|reserved_special_token_238|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128247": { + "content": "<|reserved_special_token_239|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128248": { + "content": "<|reserved_special_token_240|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128249": { + "content": "<|reserved_special_token_241|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128250": { + "content": "<|reserved_special_token_242|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128251": { + "content": "<|reserved_special_token_243|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128252": { + "content": "<|reserved_special_token_244|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128253": { + "content": "<|reserved_special_token_245|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128254": { + "content": "<|reserved_special_token_246|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128255": { + "content": "<|reserved_special_token_247|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "<|begin_of_text|>", + "chat_template": "{{ '<|begin_of_text|>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ '<|start_header_id|>system<|end_header_id|>\n\n' + system_message + '<|eot_id|>' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|start_header_id|>user<|end_header_id|>\n\n' + content + '<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|eot_id|>' }}{% endif %}{% endfor %}", + "clean_up_tokenization_spaces": true, + "eos_token": "<|eot_id|>", + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 131072, + "pad_token": "<|eot_id|>", + "padding_side": "right", + "split_special_tokens": false, + "tokenizer_class": "PreTrainedTokenizerFast" +} diff --git a/train_results.json b/train_results.json new file mode 100644 index 0000000..0f0e5df --- /dev/null +++ b/train_results.json @@ -0,0 +1,8 @@ +{ + "epoch": 2.9944232462577047, + "total_flos": 2135463108280320.0, + "train_loss": 0.5660238438026578, + "train_runtime": 41769.8593, + "train_samples_per_second": 15.658, + "train_steps_per_second": 0.031 +} \ No newline at end of file diff --git a/trainer_log.jsonl b/trainer_log.jsonl new file mode 100644 index 0000000..7a4cba8 --- /dev/null +++ b/trainer_log.jsonl @@ -0,0 +1,131 @@ +{"current_steps": 10, "total_steps": 1275, "loss": 0.9488, "lr": 5e-06, "epoch": 0.023481068388611682, "percentage": 0.78, "elapsed_time": "0:05:23", "remaining_time": "11:21:31"} +{"current_steps": 20, "total_steps": 1275, "loss": 0.8343, "lr": 5e-06, "epoch": 0.046962136777223364, "percentage": 1.57, "elapsed_time": "0:10:41", "remaining_time": "11:10:23"} +{"current_steps": 30, "total_steps": 1275, "loss": 0.7651, "lr": 5e-06, "epoch": 0.07044320516583505, "percentage": 2.35, "elapsed_time": "0:15:59", "remaining_time": "11:03:58"} +{"current_steps": 40, "total_steps": 1275, "loss": 0.7374, "lr": 5e-06, "epoch": 0.09392427355444673, "percentage": 3.14, "elapsed_time": "0:21:19", "remaining_time": "10:58:19"} +{"current_steps": 50, "total_steps": 1275, "loss": 0.7161, "lr": 5e-06, "epoch": 0.1174053419430584, "percentage": 3.92, "elapsed_time": "0:26:37", "remaining_time": "10:52:28"} +{"current_steps": 60, "total_steps": 1275, "loss": 0.6935, "lr": 5e-06, "epoch": 0.1408864103316701, "percentage": 4.71, "elapsed_time": "0:31:55", "remaining_time": "10:46:31"} +{"current_steps": 70, "total_steps": 1275, "loss": 0.6718, "lr": 5e-06, "epoch": 0.16436747872028176, "percentage": 5.49, "elapsed_time": "0:37:14", "remaining_time": "10:41:11"} +{"current_steps": 80, "total_steps": 1275, "loss": 0.6635, "lr": 5e-06, "epoch": 0.18784854710889345, "percentage": 6.27, "elapsed_time": "0:42:33", "remaining_time": "10:35:37"} +{"current_steps": 90, "total_steps": 1275, "loss": 0.6581, "lr": 5e-06, "epoch": 0.21132961549750515, "percentage": 7.06, "elapsed_time": "0:47:51", "remaining_time": "10:30:11"} +{"current_steps": 100, "total_steps": 1275, "loss": 0.6595, "lr": 5e-06, "epoch": 0.2348106838861168, "percentage": 7.84, "elapsed_time": "0:53:10", "remaining_time": "10:24:49"} +{"current_steps": 110, "total_steps": 1275, "loss": 0.6511, "lr": 5e-06, "epoch": 0.2582917522747285, "percentage": 8.63, "elapsed_time": "0:58:26", "remaining_time": "10:18:57"} +{"current_steps": 120, "total_steps": 1275, "loss": 0.6443, "lr": 5e-06, "epoch": 0.2817728206633402, "percentage": 9.41, "elapsed_time": "1:03:44", "remaining_time": "10:13:29"} +{"current_steps": 130, "total_steps": 1275, "loss": 0.6457, "lr": 5e-06, "epoch": 0.3052538890519519, "percentage": 10.2, "elapsed_time": "1:09:02", "remaining_time": "10:08:08"} +{"current_steps": 140, "total_steps": 1275, "loss": 0.6352, "lr": 5e-06, "epoch": 0.3287349574405635, "percentage": 10.98, "elapsed_time": "1:14:19", "remaining_time": "10:02:35"} +{"current_steps": 150, "total_steps": 1275, "loss": 0.642, "lr": 5e-06, "epoch": 0.3522160258291752, "percentage": 11.76, "elapsed_time": "1:19:37", "remaining_time": "9:57:08"} +{"current_steps": 160, "total_steps": 1275, "loss": 0.6453, "lr": 5e-06, "epoch": 0.3756970942177869, "percentage": 12.55, "elapsed_time": "1:24:56", "remaining_time": "9:51:56"} +{"current_steps": 170, "total_steps": 1275, "loss": 0.6375, "lr": 5e-06, "epoch": 0.3991781626063986, "percentage": 13.33, "elapsed_time": "1:30:14", "remaining_time": "9:46:32"} +{"current_steps": 180, "total_steps": 1275, "loss": 0.6404, "lr": 5e-06, "epoch": 0.4226592309950103, "percentage": 14.12, "elapsed_time": "1:35:32", "remaining_time": "9:41:11"} +{"current_steps": 190, "total_steps": 1275, "loss": 0.6282, "lr": 5e-06, "epoch": 0.44614029938362193, "percentage": 14.9, "elapsed_time": "1:40:46", "remaining_time": "9:35:30"} +{"current_steps": 200, "total_steps": 1275, "loss": 0.6258, "lr": 5e-06, "epoch": 0.4696213677722336, "percentage": 15.69, "elapsed_time": "1:46:02", "remaining_time": "9:30:00"} +{"current_steps": 210, "total_steps": 1275, "loss": 0.633, "lr": 5e-06, "epoch": 0.4931024361608453, "percentage": 16.47, "elapsed_time": "1:51:20", "remaining_time": "9:24:39"} +{"current_steps": 220, "total_steps": 1275, "loss": 0.6215, "lr": 5e-06, "epoch": 0.516583504549457, "percentage": 17.25, "elapsed_time": "1:56:38", "remaining_time": "9:19:19"} +{"current_steps": 230, "total_steps": 1275, "loss": 0.6192, "lr": 5e-06, "epoch": 0.5400645729380686, "percentage": 18.04, "elapsed_time": "2:01:55", "remaining_time": "9:13:57"} +{"current_steps": 240, "total_steps": 1275, "loss": 0.6225, "lr": 5e-06, "epoch": 0.5635456413266804, "percentage": 18.82, "elapsed_time": "2:07:13", "remaining_time": "9:08:39"} +{"current_steps": 250, "total_steps": 1275, "loss": 0.6176, "lr": 5e-06, "epoch": 0.587026709715292, "percentage": 19.61, "elapsed_time": "2:12:30", "remaining_time": "9:03:17"} +{"current_steps": 260, "total_steps": 1275, "loss": 0.6184, "lr": 5e-06, "epoch": 0.6105077781039038, "percentage": 20.39, "elapsed_time": "2:17:50", "remaining_time": "8:58:05"} +{"current_steps": 270, "total_steps": 1275, "loss": 0.6214, "lr": 5e-06, "epoch": 0.6339888464925154, "percentage": 21.18, "elapsed_time": "2:23:09", "remaining_time": "8:52:52"} +{"current_steps": 280, "total_steps": 1275, "loss": 0.6204, "lr": 5e-06, "epoch": 0.657469914881127, "percentage": 21.96, "elapsed_time": "2:28:28", "remaining_time": "8:47:36"} +{"current_steps": 290, "total_steps": 1275, "loss": 0.6166, "lr": 5e-06, "epoch": 0.6809509832697388, "percentage": 22.75, "elapsed_time": "2:33:47", "remaining_time": "8:42:21"} +{"current_steps": 300, "total_steps": 1275, "loss": 0.6096, "lr": 5e-06, "epoch": 0.7044320516583504, "percentage": 23.53, "elapsed_time": "2:39:05", "remaining_time": "8:37:02"} +{"current_steps": 310, "total_steps": 1275, "loss": 0.6076, "lr": 5e-06, "epoch": 0.7279131200469622, "percentage": 24.31, "elapsed_time": "2:44:24", "remaining_time": "8:31:47"} +{"current_steps": 320, "total_steps": 1275, "loss": 0.6115, "lr": 5e-06, "epoch": 0.7513941884355738, "percentage": 25.1, "elapsed_time": "2:49:43", "remaining_time": "8:26:32"} +{"current_steps": 330, "total_steps": 1275, "loss": 0.6138, "lr": 5e-06, "epoch": 0.7748752568241855, "percentage": 25.88, "elapsed_time": "2:55:03", "remaining_time": "8:21:19"} +{"current_steps": 340, "total_steps": 1275, "loss": 0.611, "lr": 5e-06, "epoch": 0.7983563252127972, "percentage": 26.67, "elapsed_time": "3:00:23", "remaining_time": "8:16:04"} +{"current_steps": 350, "total_steps": 1275, "loss": 0.611, "lr": 5e-06, "epoch": 0.8218373936014088, "percentage": 27.45, "elapsed_time": "3:05:43", "remaining_time": "8:10:49"} +{"current_steps": 360, "total_steps": 1275, "loss": 0.6104, "lr": 5e-06, "epoch": 0.8453184619900206, "percentage": 28.24, "elapsed_time": "3:11:02", "remaining_time": "8:05:32"} +{"current_steps": 370, "total_steps": 1275, "loss": 0.6047, "lr": 5e-06, "epoch": 0.8687995303786322, "percentage": 29.02, "elapsed_time": "3:16:20", "remaining_time": "8:00:15"} +{"current_steps": 380, "total_steps": 1275, "loss": 0.613, "lr": 5e-06, "epoch": 0.8922805987672439, "percentage": 29.8, "elapsed_time": "3:21:38", "remaining_time": "7:54:55"} +{"current_steps": 390, "total_steps": 1275, "loss": 0.6104, "lr": 5e-06, "epoch": 0.9157616671558556, "percentage": 30.59, "elapsed_time": "3:26:58", "remaining_time": "7:49:39"} +{"current_steps": 400, "total_steps": 1275, "loss": 0.6124, "lr": 5e-06, "epoch": 0.9392427355444672, "percentage": 31.37, "elapsed_time": "3:32:17", "remaining_time": "7:44:24"} +{"current_steps": 410, "total_steps": 1275, "loss": 0.5957, "lr": 5e-06, "epoch": 0.962723803933079, "percentage": 32.16, "elapsed_time": "3:37:37", "remaining_time": "7:39:08"} +{"current_steps": 420, "total_steps": 1275, "loss": 0.5979, "lr": 5e-06, "epoch": 0.9862048723216906, "percentage": 32.94, "elapsed_time": "3:42:54", "remaining_time": "7:33:47"} +{"current_steps": 425, "total_steps": 1275, "eval_loss": 0.6003177165985107, "epoch": 0.9979454065159965, "percentage": 33.33, "elapsed_time": "3:50:58", "remaining_time": "7:41:56"} +{"current_steps": 430, "total_steps": 1275, "loss": 0.6046, "lr": 5e-06, "epoch": 1.0099794540651599, "percentage": 33.73, "elapsed_time": "3:54:29", "remaining_time": "7:40:48"} +{"current_steps": 440, "total_steps": 1275, "loss": 0.5525, "lr": 5e-06, "epoch": 1.0334605224537716, "percentage": 34.51, "elapsed_time": "3:59:49", "remaining_time": "7:35:06"} +{"current_steps": 450, "total_steps": 1275, "loss": 0.5507, "lr": 5e-06, "epoch": 1.0569415908423834, "percentage": 35.29, "elapsed_time": "4:05:08", "remaining_time": "7:29:25"} +{"current_steps": 460, "total_steps": 1275, "loss": 0.5488, "lr": 5e-06, "epoch": 1.0804226592309951, "percentage": 36.08, "elapsed_time": "4:10:27", "remaining_time": "7:23:45"} +{"current_steps": 470, "total_steps": 1275, "loss": 0.5553, "lr": 5e-06, "epoch": 1.1039037276196066, "percentage": 36.86, "elapsed_time": "4:15:46", "remaining_time": "7:18:04"} +{"current_steps": 480, "total_steps": 1275, "loss": 0.5517, "lr": 5e-06, "epoch": 1.1273847960082184, "percentage": 37.65, "elapsed_time": "4:21:04", "remaining_time": "7:12:24"} +{"current_steps": 490, "total_steps": 1275, "loss": 0.5513, "lr": 5e-06, "epoch": 1.1508658643968301, "percentage": 38.43, "elapsed_time": "4:26:21", "remaining_time": "7:06:43"} +{"current_steps": 500, "total_steps": 1275, "loss": 0.5565, "lr": 5e-06, "epoch": 1.1743469327854417, "percentage": 39.22, "elapsed_time": "4:31:38", "remaining_time": "7:01:02"} +{"current_steps": 510, "total_steps": 1275, "loss": 0.5508, "lr": 5e-06, "epoch": 1.1978280011740534, "percentage": 40.0, "elapsed_time": "4:36:56", "remaining_time": "6:55:24"} +{"current_steps": 520, "total_steps": 1275, "loss": 0.5513, "lr": 5e-06, "epoch": 1.2213090695626652, "percentage": 40.78, "elapsed_time": "4:42:11", "remaining_time": "6:49:43"} +{"current_steps": 530, "total_steps": 1275, "loss": 0.5538, "lr": 5e-06, "epoch": 1.2447901379512767, "percentage": 41.57, "elapsed_time": "4:47:29", "remaining_time": "6:44:06"} +{"current_steps": 540, "total_steps": 1275, "loss": 0.5442, "lr": 5e-06, "epoch": 1.2682712063398884, "percentage": 42.35, "elapsed_time": "4:52:47", "remaining_time": "6:38:31"} +{"current_steps": 550, "total_steps": 1275, "loss": 0.5566, "lr": 5e-06, "epoch": 1.2917522747285002, "percentage": 43.14, "elapsed_time": "4:58:05", "remaining_time": "6:32:56"} +{"current_steps": 560, "total_steps": 1275, "loss": 0.5494, "lr": 5e-06, "epoch": 1.3152333431171117, "percentage": 43.92, "elapsed_time": "5:03:20", "remaining_time": "6:27:17"} +{"current_steps": 570, "total_steps": 1275, "loss": 0.5471, "lr": 5e-06, "epoch": 1.3387144115057235, "percentage": 44.71, "elapsed_time": "5:08:38", "remaining_time": "6:21:44"} +{"current_steps": 580, "total_steps": 1275, "loss": 0.552, "lr": 5e-06, "epoch": 1.3621954798943352, "percentage": 45.49, "elapsed_time": "5:13:56", "remaining_time": "6:16:11"} +{"current_steps": 590, "total_steps": 1275, "loss": 0.5505, "lr": 5e-06, "epoch": 1.385676548282947, "percentage": 46.27, "elapsed_time": "5:19:14", "remaining_time": "6:10:38"} +{"current_steps": 600, "total_steps": 1275, "loss": 0.5498, "lr": 5e-06, "epoch": 1.4091576166715585, "percentage": 47.06, "elapsed_time": "5:24:31", "remaining_time": "6:05:05"} +{"current_steps": 610, "total_steps": 1275, "loss": 0.5562, "lr": 5e-06, "epoch": 1.4326386850601702, "percentage": 47.84, "elapsed_time": "5:29:49", "remaining_time": "5:59:33"} +{"current_steps": 620, "total_steps": 1275, "loss": 0.5555, "lr": 5e-06, "epoch": 1.456119753448782, "percentage": 48.63, "elapsed_time": "5:35:07", "remaining_time": "5:54:02"} +{"current_steps": 630, "total_steps": 1275, "loss": 0.544, "lr": 5e-06, "epoch": 1.4796008218373937, "percentage": 49.41, "elapsed_time": "5:40:26", "remaining_time": "5:48:32"} +{"current_steps": 640, "total_steps": 1275, "loss": 0.5451, "lr": 5e-06, "epoch": 1.5030818902260052, "percentage": 50.2, "elapsed_time": "5:45:44", "remaining_time": "5:43:02"} +{"current_steps": 650, "total_steps": 1275, "loss": 0.5587, "lr": 5e-06, "epoch": 1.526562958614617, "percentage": 50.98, "elapsed_time": "5:51:02", "remaining_time": "5:37:32"} +{"current_steps": 660, "total_steps": 1275, "loss": 0.5518, "lr": 5e-06, "epoch": 1.5500440270032287, "percentage": 51.76, "elapsed_time": "5:56:21", "remaining_time": "5:32:03"} +{"current_steps": 670, "total_steps": 1275, "loss": 0.5526, "lr": 5e-06, "epoch": 1.5735250953918403, "percentage": 52.55, "elapsed_time": "6:01:40", "remaining_time": "5:26:35"} +{"current_steps": 680, "total_steps": 1275, "loss": 0.5478, "lr": 5e-06, "epoch": 1.597006163780452, "percentage": 53.33, "elapsed_time": "6:07:00", "remaining_time": "5:21:07"} +{"current_steps": 690, "total_steps": 1275, "loss": 0.5481, "lr": 5e-06, "epoch": 1.6204872321690638, "percentage": 54.12, "elapsed_time": "6:12:19", "remaining_time": "5:15:39"} +{"current_steps": 700, "total_steps": 1275, "loss": 0.5515, "lr": 5e-06, "epoch": 1.6439683005576753, "percentage": 54.9, "elapsed_time": "6:17:37", "remaining_time": "5:10:11"} +{"current_steps": 710, "total_steps": 1275, "loss": 0.5505, "lr": 5e-06, "epoch": 1.667449368946287, "percentage": 55.69, "elapsed_time": "6:22:55", "remaining_time": "5:04:43"} +{"current_steps": 720, "total_steps": 1275, "loss": 0.5496, "lr": 5e-06, "epoch": 1.6909304373348988, "percentage": 56.47, "elapsed_time": "6:28:14", "remaining_time": "4:59:15"} +{"current_steps": 730, "total_steps": 1275, "loss": 0.5484, "lr": 5e-06, "epoch": 1.7144115057235103, "percentage": 57.25, "elapsed_time": "6:33:33", "remaining_time": "4:53:48"} +{"current_steps": 740, "total_steps": 1275, "loss": 0.5483, "lr": 5e-06, "epoch": 1.737892574112122, "percentage": 58.04, "elapsed_time": "6:38:51", "remaining_time": "4:48:21"} +{"current_steps": 750, "total_steps": 1275, "loss": 0.5531, "lr": 5e-06, "epoch": 1.7613736425007338, "percentage": 58.82, "elapsed_time": "6:44:09", "remaining_time": "4:42:54"} +{"current_steps": 760, "total_steps": 1275, "loss": 0.5487, "lr": 5e-06, "epoch": 1.7848547108893453, "percentage": 59.61, "elapsed_time": "6:49:26", "remaining_time": "4:37:26"} +{"current_steps": 770, "total_steps": 1275, "loss": 0.5485, "lr": 5e-06, "epoch": 1.8083357792779573, "percentage": 60.39, "elapsed_time": "6:54:44", "remaining_time": "4:32:00"} +{"current_steps": 780, "total_steps": 1275, "loss": 0.5518, "lr": 5e-06, "epoch": 1.8318168476665688, "percentage": 61.18, "elapsed_time": "7:00:03", "remaining_time": "4:26:34"} +{"current_steps": 790, "total_steps": 1275, "loss": 0.5467, "lr": 5e-06, "epoch": 1.8552979160551804, "percentage": 61.96, "elapsed_time": "7:05:20", "remaining_time": "4:21:07"} +{"current_steps": 800, "total_steps": 1275, "loss": 0.5468, "lr": 5e-06, "epoch": 1.8787789844437923, "percentage": 62.75, "elapsed_time": "7:10:38", "remaining_time": "4:15:41"} +{"current_steps": 810, "total_steps": 1275, "loss": 0.5488, "lr": 5e-06, "epoch": 1.9022600528324038, "percentage": 63.53, "elapsed_time": "7:15:55", "remaining_time": "4:10:15"} +{"current_steps": 820, "total_steps": 1275, "loss": 0.5458, "lr": 5e-06, "epoch": 1.9257411212210156, "percentage": 64.31, "elapsed_time": "7:21:13", "remaining_time": "4:04:49"} +{"current_steps": 830, "total_steps": 1275, "loss": 0.5447, "lr": 5e-06, "epoch": 1.9492221896096273, "percentage": 65.1, "elapsed_time": "7:26:28", "remaining_time": "3:59:22"} +{"current_steps": 840, "total_steps": 1275, "loss": 0.5398, "lr": 5e-06, "epoch": 1.9727032579982389, "percentage": 65.88, "elapsed_time": "7:31:45", "remaining_time": "3:53:56"} +{"current_steps": 850, "total_steps": 1275, "loss": 0.547, "lr": 5e-06, "epoch": 1.9961843263868506, "percentage": 66.67, "elapsed_time": "7:37:03", "remaining_time": "3:48:31"} +{"current_steps": 851, "total_steps": 1275, "eval_loss": 0.5846751928329468, "epoch": 1.9985324332257117, "percentage": 66.75, "elapsed_time": "7:42:41", "remaining_time": "3:50:31"} +{"current_steps": 860, "total_steps": 1275, "loss": 0.523, "lr": 5e-06, "epoch": 2.0199589081303198, "percentage": 67.45, "elapsed_time": "7:48:31", "remaining_time": "3:46:05"} +{"current_steps": 870, "total_steps": 1275, "loss": 0.4924, "lr": 5e-06, "epoch": 2.0434399765189317, "percentage": 68.24, "elapsed_time": "7:53:48", "remaining_time": "3:40:34"} +{"current_steps": 880, "total_steps": 1275, "loss": 0.4902, "lr": 5e-06, "epoch": 2.0669210449075432, "percentage": 69.02, "elapsed_time": "7:59:06", "remaining_time": "3:35:03"} +{"current_steps": 890, "total_steps": 1275, "loss": 0.4955, "lr": 5e-06, "epoch": 2.0904021132961548, "percentage": 69.8, "elapsed_time": "8:04:23", "remaining_time": "3:29:32"} +{"current_steps": 900, "total_steps": 1275, "loss": 0.4969, "lr": 5e-06, "epoch": 2.1138831816847667, "percentage": 70.59, "elapsed_time": "8:09:40", "remaining_time": "3:24:01"} +{"current_steps": 910, "total_steps": 1275, "loss": 0.4865, "lr": 5e-06, "epoch": 2.1373642500733783, "percentage": 71.37, "elapsed_time": "8:14:58", "remaining_time": "3:18:31"} +{"current_steps": 920, "total_steps": 1275, "loss": 0.4966, "lr": 5e-06, "epoch": 2.1608453184619902, "percentage": 72.16, "elapsed_time": "8:20:15", "remaining_time": "3:13:02"} +{"current_steps": 930, "total_steps": 1275, "loss": 0.497, "lr": 5e-06, "epoch": 2.1843263868506018, "percentage": 72.94, "elapsed_time": "8:25:33", "remaining_time": "3:07:32"} +{"current_steps": 940, "total_steps": 1275, "loss": 0.498, "lr": 5e-06, "epoch": 2.2078074552392133, "percentage": 73.73, "elapsed_time": "8:30:52", "remaining_time": "3:02:03"} +{"current_steps": 950, "total_steps": 1275, "loss": 0.4978, "lr": 5e-06, "epoch": 2.2312885236278253, "percentage": 74.51, "elapsed_time": "8:36:10", "remaining_time": "2:56:35"} +{"current_steps": 960, "total_steps": 1275, "loss": 0.4954, "lr": 5e-06, "epoch": 2.254769592016437, "percentage": 75.29, "elapsed_time": "8:41:25", "remaining_time": "2:51:05"} +{"current_steps": 970, "total_steps": 1275, "loss": 0.5024, "lr": 5e-06, "epoch": 2.2782506604050483, "percentage": 76.08, "elapsed_time": "8:46:44", "remaining_time": "2:45:37"} +{"current_steps": 980, "total_steps": 1275, "loss": 0.4982, "lr": 5e-06, "epoch": 2.3017317287936603, "percentage": 76.86, "elapsed_time": "8:52:00", "remaining_time": "2:40:08"} +{"current_steps": 990, "total_steps": 1275, "loss": 0.4994, "lr": 5e-06, "epoch": 2.325212797182272, "percentage": 77.65, "elapsed_time": "8:57:18", "remaining_time": "2:34:40"} +{"current_steps": 1000, "total_steps": 1275, "loss": 0.5002, "lr": 5e-06, "epoch": 2.3486938655708833, "percentage": 78.43, "elapsed_time": "9:02:35", "remaining_time": "2:29:12"} +{"current_steps": 1010, "total_steps": 1275, "loss": 0.4994, "lr": 5e-06, "epoch": 2.3721749339594953, "percentage": 79.22, "elapsed_time": "9:07:52", "remaining_time": "2:23:44"} +{"current_steps": 1020, "total_steps": 1275, "loss": 0.4906, "lr": 5e-06, "epoch": 2.395656002348107, "percentage": 80.0, "elapsed_time": "9:13:09", "remaining_time": "2:18:17"} +{"current_steps": 1030, "total_steps": 1275, "loss": 0.4975, "lr": 5e-06, "epoch": 2.4191370707367184, "percentage": 80.78, "elapsed_time": "9:18:27", "remaining_time": "2:12:50"} +{"current_steps": 1040, "total_steps": 1275, "loss": 0.4976, "lr": 5e-06, "epoch": 2.4426181391253303, "percentage": 81.57, "elapsed_time": "9:23:44", "remaining_time": "2:07:23"} +{"current_steps": 1050, "total_steps": 1275, "loss": 0.5052, "lr": 5e-06, "epoch": 2.466099207513942, "percentage": 82.35, "elapsed_time": "9:28:59", "remaining_time": "2:01:55"} +{"current_steps": 1060, "total_steps": 1275, "loss": 0.4989, "lr": 5e-06, "epoch": 2.4895802759025534, "percentage": 83.14, "elapsed_time": "9:34:17", "remaining_time": "1:56:28"} +{"current_steps": 1070, "total_steps": 1275, "loss": 0.5059, "lr": 5e-06, "epoch": 2.5130613442911653, "percentage": 83.92, "elapsed_time": "9:39:35", "remaining_time": "1:51:02"} +{"current_steps": 1080, "total_steps": 1275, "loss": 0.4946, "lr": 5e-06, "epoch": 2.536542412679777, "percentage": 84.71, "elapsed_time": "9:44:53", "remaining_time": "1:45:36"} +{"current_steps": 1090, "total_steps": 1275, "loss": 0.5086, "lr": 5e-06, "epoch": 2.560023481068389, "percentage": 85.49, "elapsed_time": "9:50:12", "remaining_time": "1:40:10"} +{"current_steps": 1100, "total_steps": 1275, "loss": 0.498, "lr": 5e-06, "epoch": 2.5835045494570004, "percentage": 86.27, "elapsed_time": "9:55:30", "remaining_time": "1:34:44"} +{"current_steps": 1110, "total_steps": 1275, "loss": 0.4998, "lr": 5e-06, "epoch": 2.606985617845612, "percentage": 87.06, "elapsed_time": "10:00:49", "remaining_time": "1:29:18"} +{"current_steps": 1120, "total_steps": 1275, "loss": 0.4944, "lr": 5e-06, "epoch": 2.6304666862342234, "percentage": 87.84, "elapsed_time": "10:06:07", "remaining_time": "1:23:53"} +{"current_steps": 1130, "total_steps": 1275, "loss": 0.5028, "lr": 5e-06, "epoch": 2.6539477546228354, "percentage": 88.63, "elapsed_time": "10:11:26", "remaining_time": "1:18:27"} +{"current_steps": 1140, "total_steps": 1275, "loss": 0.4982, "lr": 5e-06, "epoch": 2.677428823011447, "percentage": 89.41, "elapsed_time": "10:16:45", "remaining_time": "1:13:02"} +{"current_steps": 1150, "total_steps": 1275, "loss": 0.5009, "lr": 5e-06, "epoch": 2.700909891400059, "percentage": 90.2, "elapsed_time": "10:22:04", "remaining_time": "1:07:36"} +{"current_steps": 1160, "total_steps": 1275, "loss": 0.5012, "lr": 5e-06, "epoch": 2.7243909597886704, "percentage": 90.98, "elapsed_time": "10:27:23", "remaining_time": "1:02:11"} +{"current_steps": 1170, "total_steps": 1275, "loss": 0.5032, "lr": 5e-06, "epoch": 2.747872028177282, "percentage": 91.76, "elapsed_time": "10:32:41", "remaining_time": "0:56:46"} +{"current_steps": 1180, "total_steps": 1275, "loss": 0.5033, "lr": 5e-06, "epoch": 2.771353096565894, "percentage": 92.55, "elapsed_time": "10:37:58", "remaining_time": "0:51:21"} +{"current_steps": 1190, "total_steps": 1275, "loss": 0.5037, "lr": 5e-06, "epoch": 2.7948341649545054, "percentage": 93.33, "elapsed_time": "10:43:18", "remaining_time": "0:45:57"} +{"current_steps": 1200, "total_steps": 1275, "loss": 0.508, "lr": 5e-06, "epoch": 2.818315233343117, "percentage": 94.12, "elapsed_time": "10:48:36", "remaining_time": "0:40:32"} +{"current_steps": 1210, "total_steps": 1275, "loss": 0.4957, "lr": 5e-06, "epoch": 2.841796301731729, "percentage": 94.9, "elapsed_time": "10:53:53", "remaining_time": "0:35:07"} +{"current_steps": 1220, "total_steps": 1275, "loss": 0.499, "lr": 5e-06, "epoch": 2.8652773701203404, "percentage": 95.69, "elapsed_time": "10:59:11", "remaining_time": "0:29:43"} +{"current_steps": 1230, "total_steps": 1275, "loss": 0.4982, "lr": 5e-06, "epoch": 2.888758438508952, "percentage": 96.47, "elapsed_time": "11:04:30", "remaining_time": "0:24:18"} +{"current_steps": 1240, "total_steps": 1275, "loss": 0.5006, "lr": 5e-06, "epoch": 2.912239506897564, "percentage": 97.25, "elapsed_time": "11:09:48", "remaining_time": "0:18:54"} +{"current_steps": 1250, "total_steps": 1275, "loss": 0.494, "lr": 5e-06, "epoch": 2.9357205752861755, "percentage": 98.04, "elapsed_time": "11:15:07", "remaining_time": "0:13:30"} +{"current_steps": 1260, "total_steps": 1275, "loss": 0.5001, "lr": 5e-06, "epoch": 2.9592016436747874, "percentage": 98.82, "elapsed_time": "11:20:25", "remaining_time": "0:08:06"} +{"current_steps": 1270, "total_steps": 1275, "loss": 0.5003, "lr": 5e-06, "epoch": 2.982682712063399, "percentage": 99.61, "elapsed_time": "11:25:43", "remaining_time": "0:02:41"} +{"current_steps": 1275, "total_steps": 1275, "eval_loss": 0.5840933322906494, "epoch": 2.9944232462577047, "percentage": 100.0, "elapsed_time": "11:34:33", "remaining_time": "0:00:00"} +{"current_steps": 1275, "total_steps": 1275, "epoch": 2.9944232462577047, "percentage": 100.0, "elapsed_time": "11:36:08", "remaining_time": "0:00:00"} diff --git a/trainer_state.json b/trainer_state.json new file mode 100644 index 0000000..f3ff258 --- /dev/null +++ b/trainer_state.json @@ -0,0 +1,955 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 2.9944232462577047, + "eval_steps": 500, + "global_step": 1275, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.023481068388611682, + "grad_norm": 17.85382376485096, + "learning_rate": 5e-06, + "loss": 0.9488, + "step": 10 + }, + { + "epoch": 0.046962136777223364, + "grad_norm": 3.177756281658111, + "learning_rate": 5e-06, + "loss": 0.8343, + "step": 20 + }, + { + "epoch": 0.07044320516583505, + "grad_norm": 2.950019754054781, + "learning_rate": 5e-06, + "loss": 0.7651, + "step": 30 + }, + { + "epoch": 0.09392427355444673, + "grad_norm": 1.450856517854765, + "learning_rate": 5e-06, + "loss": 0.7374, + "step": 40 + }, + { + "epoch": 0.1174053419430584, + "grad_norm": 0.8091667434976095, + "learning_rate": 5e-06, + "loss": 0.7161, + "step": 50 + }, + { + "epoch": 0.1408864103316701, + "grad_norm": 0.8253122020905036, + "learning_rate": 5e-06, + "loss": 0.6935, + "step": 60 + }, + { + "epoch": 0.16436747872028176, + "grad_norm": 0.6338190868455624, + "learning_rate": 5e-06, + "loss": 0.6718, + "step": 70 + }, + { + "epoch": 0.18784854710889345, + "grad_norm": 0.8143184435680945, + "learning_rate": 5e-06, + "loss": 0.6635, + "step": 80 + }, + { + "epoch": 0.21132961549750515, + "grad_norm": 0.7202907234528798, + "learning_rate": 5e-06, + "loss": 0.6581, + "step": 90 + }, + { + "epoch": 0.2348106838861168, + "grad_norm": 0.9812703695297975, + "learning_rate": 5e-06, + "loss": 0.6595, + "step": 100 + }, + { + "epoch": 0.2582917522747285, + "grad_norm": 0.6403918144312425, + "learning_rate": 5e-06, + "loss": 0.6511, + "step": 110 + }, + { + "epoch": 0.2817728206633402, + "grad_norm": 0.6355110618738598, + "learning_rate": 5e-06, + "loss": 0.6443, + "step": 120 + }, + { + "epoch": 0.3052538890519519, + "grad_norm": 0.8767568074879388, + "learning_rate": 5e-06, + "loss": 0.6457, + "step": 130 + }, + { + "epoch": 0.3287349574405635, + "grad_norm": 0.7912634151639979, + "learning_rate": 5e-06, + "loss": 0.6352, + "step": 140 + }, + { + "epoch": 0.3522160258291752, + "grad_norm": 0.6346769190072642, + "learning_rate": 5e-06, + "loss": 0.642, + "step": 150 + }, + { + "epoch": 0.3756970942177869, + "grad_norm": 0.6538804073841475, + "learning_rate": 5e-06, + "loss": 0.6453, + "step": 160 + }, + { + "epoch": 0.3991781626063986, + "grad_norm": 0.524677402567732, + "learning_rate": 5e-06, + "loss": 0.6375, + "step": 170 + }, + { + "epoch": 0.4226592309950103, + "grad_norm": 0.6983299832658841, + "learning_rate": 5e-06, + "loss": 0.6404, + "step": 180 + }, + { + "epoch": 0.44614029938362193, + "grad_norm": 0.5730458718423643, + "learning_rate": 5e-06, + "loss": 0.6282, + "step": 190 + }, + { + "epoch": 0.4696213677722336, + "grad_norm": 0.5795935762469521, + "learning_rate": 5e-06, + "loss": 0.6258, + "step": 200 + }, + { + "epoch": 0.4931024361608453, + "grad_norm": 0.6568013132353124, + "learning_rate": 5e-06, + "loss": 0.633, + "step": 210 + }, + { + "epoch": 0.516583504549457, + "grad_norm": 0.625002257246399, + "learning_rate": 5e-06, + "loss": 0.6215, + "step": 220 + }, + { + "epoch": 0.5400645729380686, + "grad_norm": 0.5866557972006909, + "learning_rate": 5e-06, + "loss": 0.6192, + "step": 230 + }, + { + "epoch": 0.5635456413266804, + "grad_norm": 0.5523814224922182, + "learning_rate": 5e-06, + "loss": 0.6225, + "step": 240 + }, + { + "epoch": 0.587026709715292, + "grad_norm": 0.621565965520602, + "learning_rate": 5e-06, + "loss": 0.6176, + "step": 250 + }, + { + "epoch": 0.6105077781039038, + "grad_norm": 0.5699863716830831, + "learning_rate": 5e-06, + "loss": 0.6184, + "step": 260 + }, + { + "epoch": 0.6339888464925154, + "grad_norm": 0.5867908049315175, + "learning_rate": 5e-06, + "loss": 0.6214, + "step": 270 + }, + { + "epoch": 0.657469914881127, + "grad_norm": 1.0031834057307554, + "learning_rate": 5e-06, + "loss": 0.6204, + "step": 280 + }, + { + "epoch": 0.6809509832697388, + "grad_norm": 0.5739527115683025, + "learning_rate": 5e-06, + "loss": 0.6166, + "step": 290 + }, + { + "epoch": 0.7044320516583504, + "grad_norm": 0.6047949935557967, + "learning_rate": 5e-06, + "loss": 0.6096, + "step": 300 + }, + { + "epoch": 0.7279131200469622, + "grad_norm": 0.5141588768585372, + "learning_rate": 5e-06, + "loss": 0.6076, + "step": 310 + }, + { + "epoch": 0.7513941884355738, + "grad_norm": 0.689840031854037, + "learning_rate": 5e-06, + "loss": 0.6115, + "step": 320 + }, + { + "epoch": 0.7748752568241855, + "grad_norm": 0.7551629396423358, + "learning_rate": 5e-06, + "loss": 0.6138, + "step": 330 + }, + { + "epoch": 0.7983563252127972, + "grad_norm": 0.5356794354442618, + "learning_rate": 5e-06, + "loss": 0.611, + "step": 340 + }, + { + "epoch": 0.8218373936014088, + "grad_norm": 0.6083117103787592, + "learning_rate": 5e-06, + "loss": 0.611, + "step": 350 + }, + { + "epoch": 0.8453184619900206, + "grad_norm": 0.7034174178117553, + "learning_rate": 5e-06, + "loss": 0.6104, + "step": 360 + }, + { + "epoch": 0.8687995303786322, + "grad_norm": 0.5650614816783488, + "learning_rate": 5e-06, + "loss": 0.6047, + "step": 370 + }, + { + "epoch": 0.8922805987672439, + "grad_norm": 0.6449034585856688, + "learning_rate": 5e-06, + "loss": 0.613, + "step": 380 + }, + { + "epoch": 0.9157616671558556, + "grad_norm": 0.6460327839123797, + "learning_rate": 5e-06, + "loss": 0.6104, + "step": 390 + }, + { + "epoch": 0.9392427355444672, + "grad_norm": 0.6977465772968938, + "learning_rate": 5e-06, + "loss": 0.6124, + "step": 400 + }, + { + "epoch": 0.962723803933079, + "grad_norm": 0.6646492018550946, + "learning_rate": 5e-06, + "loss": 0.5957, + "step": 410 + }, + { + "epoch": 0.9862048723216906, + "grad_norm": 0.48972085408134464, + "learning_rate": 5e-06, + "loss": 0.5979, + "step": 420 + }, + { + "epoch": 0.9979454065159965, + "eval_loss": 0.6003177165985107, + "eval_runtime": 300.5123, + "eval_samples_per_second": 38.181, + "eval_steps_per_second": 0.599, + "step": 425 + }, + { + "epoch": 1.0099794540651599, + "grad_norm": 0.8929971915551214, + "learning_rate": 5e-06, + "loss": 0.6046, + "step": 430 + }, + { + "epoch": 1.0334605224537716, + "grad_norm": 0.6204797689157823, + "learning_rate": 5e-06, + "loss": 0.5525, + "step": 440 + }, + { + "epoch": 1.0569415908423834, + "grad_norm": 0.629777186945133, + "learning_rate": 5e-06, + "loss": 0.5507, + "step": 450 + }, + { + "epoch": 1.0804226592309951, + "grad_norm": 0.6177917289848706, + "learning_rate": 5e-06, + "loss": 0.5488, + "step": 460 + }, + { + "epoch": 1.1039037276196066, + "grad_norm": 0.616801854556511, + "learning_rate": 5e-06, + "loss": 0.5553, + "step": 470 + }, + { + "epoch": 1.1273847960082184, + "grad_norm": 0.6202115496799256, + "learning_rate": 5e-06, + "loss": 0.5517, + "step": 480 + }, + { + "epoch": 1.1508658643968301, + "grad_norm": 0.6869810211842367, + "learning_rate": 5e-06, + "loss": 0.5513, + "step": 490 + }, + { + "epoch": 1.1743469327854417, + "grad_norm": 0.6134525997635181, + "learning_rate": 5e-06, + "loss": 0.5565, + "step": 500 + }, + { + "epoch": 1.1978280011740534, + "grad_norm": 0.6533976679541116, + "learning_rate": 5e-06, + "loss": 0.5508, + "step": 510 + }, + { + "epoch": 1.2213090695626652, + "grad_norm": 0.7384172080803894, + "learning_rate": 5e-06, + "loss": 0.5513, + "step": 520 + }, + { + "epoch": 1.2447901379512767, + "grad_norm": 0.6446266722666449, + "learning_rate": 5e-06, + "loss": 0.5538, + "step": 530 + }, + { + "epoch": 1.2682712063398884, + "grad_norm": 0.6920463607543151, + "learning_rate": 5e-06, + "loss": 0.5442, + "step": 540 + }, + { + "epoch": 1.2917522747285002, + "grad_norm": 0.7090350057008448, + "learning_rate": 5e-06, + "loss": 0.5566, + "step": 550 + }, + { + "epoch": 1.3152333431171117, + "grad_norm": 0.7226606579176621, + "learning_rate": 5e-06, + "loss": 0.5494, + "step": 560 + }, + { + "epoch": 1.3387144115057235, + "grad_norm": 0.5484819340890661, + "learning_rate": 5e-06, + "loss": 0.5471, + "step": 570 + }, + { + "epoch": 1.3621954798943352, + "grad_norm": 0.6982064642691793, + "learning_rate": 5e-06, + "loss": 0.552, + "step": 580 + }, + { + "epoch": 1.385676548282947, + "grad_norm": 0.6147097813447182, + "learning_rate": 5e-06, + "loss": 0.5505, + "step": 590 + }, + { + "epoch": 1.4091576166715585, + "grad_norm": 0.6598577111107449, + "learning_rate": 5e-06, + "loss": 0.5498, + "step": 600 + }, + { + "epoch": 1.4326386850601702, + "grad_norm": 0.5603317744558156, + "learning_rate": 5e-06, + "loss": 0.5562, + "step": 610 + }, + { + "epoch": 1.456119753448782, + "grad_norm": 0.6373670868271739, + "learning_rate": 5e-06, + "loss": 0.5555, + "step": 620 + }, + { + "epoch": 1.4796008218373937, + "grad_norm": 0.5932324800613761, + "learning_rate": 5e-06, + "loss": 0.544, + "step": 630 + }, + { + "epoch": 1.5030818902260052, + "grad_norm": 0.5227721794518003, + "learning_rate": 5e-06, + "loss": 0.5451, + "step": 640 + }, + { + "epoch": 1.526562958614617, + "grad_norm": 0.6093734754379218, + "learning_rate": 5e-06, + "loss": 0.5587, + "step": 650 + }, + { + "epoch": 1.5500440270032287, + "grad_norm": 0.6287567431322201, + "learning_rate": 5e-06, + "loss": 0.5518, + "step": 660 + }, + { + "epoch": 1.5735250953918403, + "grad_norm": 0.6541153306269628, + "learning_rate": 5e-06, + "loss": 0.5526, + "step": 670 + }, + { + "epoch": 1.597006163780452, + "grad_norm": 0.6150418746443832, + "learning_rate": 5e-06, + "loss": 0.5478, + "step": 680 + }, + { + "epoch": 1.6204872321690638, + "grad_norm": 0.5475396144251581, + "learning_rate": 5e-06, + "loss": 0.5481, + "step": 690 + }, + { + "epoch": 1.6439683005576753, + "grad_norm": 0.6160254516028266, + "learning_rate": 5e-06, + "loss": 0.5515, + "step": 700 + }, + { + "epoch": 1.667449368946287, + "grad_norm": 0.843962487015559, + "learning_rate": 5e-06, + "loss": 0.5505, + "step": 710 + }, + { + "epoch": 1.6909304373348988, + "grad_norm": 0.5347960520186497, + "learning_rate": 5e-06, + "loss": 0.5496, + "step": 720 + }, + { + "epoch": 1.7144115057235103, + "grad_norm": 0.7323294593212619, + "learning_rate": 5e-06, + "loss": 0.5484, + "step": 730 + }, + { + "epoch": 1.737892574112122, + "grad_norm": 0.5476336095439653, + "learning_rate": 5e-06, + "loss": 0.5483, + "step": 740 + }, + { + "epoch": 1.7613736425007338, + "grad_norm": 0.6011568410465314, + "learning_rate": 5e-06, + "loss": 0.5531, + "step": 750 + }, + { + "epoch": 1.7848547108893453, + "grad_norm": 0.6797212856687878, + "learning_rate": 5e-06, + "loss": 0.5487, + "step": 760 + }, + { + "epoch": 1.8083357792779573, + "grad_norm": 0.5819194256052239, + "learning_rate": 5e-06, + "loss": 0.5485, + "step": 770 + }, + { + "epoch": 1.8318168476665688, + "grad_norm": 0.5292485271089171, + "learning_rate": 5e-06, + "loss": 0.5518, + "step": 780 + }, + { + "epoch": 1.8552979160551804, + "grad_norm": 0.5799939542823142, + "learning_rate": 5e-06, + "loss": 0.5467, + "step": 790 + }, + { + "epoch": 1.8787789844437923, + "grad_norm": 0.5570487573376319, + "learning_rate": 5e-06, + "loss": 0.5468, + "step": 800 + }, + { + "epoch": 1.9022600528324038, + "grad_norm": 0.6174505205210491, + "learning_rate": 5e-06, + "loss": 0.5488, + "step": 810 + }, + { + "epoch": 1.9257411212210156, + "grad_norm": 0.5693760728585585, + "learning_rate": 5e-06, + "loss": 0.5458, + "step": 820 + }, + { + "epoch": 1.9492221896096273, + "grad_norm": 0.5189329244004007, + "learning_rate": 5e-06, + "loss": 0.5447, + "step": 830 + }, + { + "epoch": 1.9727032579982389, + "grad_norm": 0.6238194647054416, + "learning_rate": 5e-06, + "loss": 0.5398, + "step": 840 + }, + { + "epoch": 1.9961843263868506, + "grad_norm": 0.5651058414473042, + "learning_rate": 5e-06, + "loss": 0.547, + "step": 850 + }, + { + "epoch": 1.9985324332257117, + "eval_loss": 0.5846751928329468, + "eval_runtime": 295.576, + "eval_samples_per_second": 38.819, + "eval_steps_per_second": 0.609, + "step": 851 + }, + { + "epoch": 2.0199589081303198, + "grad_norm": 0.6946392563773179, + "learning_rate": 5e-06, + "loss": 0.523, + "step": 860 + }, + { + "epoch": 2.0434399765189317, + "grad_norm": 0.8362364731068118, + "learning_rate": 5e-06, + "loss": 0.4924, + "step": 870 + }, + { + "epoch": 2.0669210449075432, + "grad_norm": 0.7772390407263537, + "learning_rate": 5e-06, + "loss": 0.4902, + "step": 880 + }, + { + "epoch": 2.0904021132961548, + "grad_norm": 0.5219899057565048, + "learning_rate": 5e-06, + "loss": 0.4955, + "step": 890 + }, + { + "epoch": 2.1138831816847667, + "grad_norm": 0.6541702370902746, + "learning_rate": 5e-06, + "loss": 0.4969, + "step": 900 + }, + { + "epoch": 2.1373642500733783, + "grad_norm": 0.5786919167953266, + "learning_rate": 5e-06, + "loss": 0.4865, + "step": 910 + }, + { + "epoch": 2.1608453184619902, + "grad_norm": 0.6257190526717714, + "learning_rate": 5e-06, + "loss": 0.4966, + "step": 920 + }, + { + "epoch": 2.1843263868506018, + "grad_norm": 0.6070724867911851, + "learning_rate": 5e-06, + "loss": 0.497, + "step": 930 + }, + { + "epoch": 2.2078074552392133, + "grad_norm": 0.7626194518667021, + "learning_rate": 5e-06, + "loss": 0.498, + "step": 940 + }, + { + "epoch": 2.2312885236278253, + "grad_norm": 0.66208678281747, + "learning_rate": 5e-06, + "loss": 0.4978, + "step": 950 + }, + { + "epoch": 2.254769592016437, + "grad_norm": 0.597091889958803, + "learning_rate": 5e-06, + "loss": 0.4954, + "step": 960 + }, + { + "epoch": 2.2782506604050483, + "grad_norm": 0.648113572619813, + "learning_rate": 5e-06, + "loss": 0.5024, + "step": 970 + }, + { + "epoch": 2.3017317287936603, + "grad_norm": 0.5800444078314209, + "learning_rate": 5e-06, + "loss": 0.4982, + "step": 980 + }, + { + "epoch": 2.325212797182272, + "grad_norm": 0.5914333960587344, + "learning_rate": 5e-06, + "loss": 0.4994, + "step": 990 + }, + { + "epoch": 2.3486938655708833, + "grad_norm": 0.7924399848654731, + "learning_rate": 5e-06, + "loss": 0.5002, + "step": 1000 + }, + { + "epoch": 2.3721749339594953, + "grad_norm": 0.624856284950558, + "learning_rate": 5e-06, + "loss": 0.4994, + "step": 1010 + }, + { + "epoch": 2.395656002348107, + "grad_norm": 0.6655834278053183, + "learning_rate": 5e-06, + "loss": 0.4906, + "step": 1020 + }, + { + "epoch": 2.4191370707367184, + "grad_norm": 0.5518645145037842, + "learning_rate": 5e-06, + "loss": 0.4975, + "step": 1030 + }, + { + "epoch": 2.4426181391253303, + "grad_norm": 0.5785599308848968, + "learning_rate": 5e-06, + "loss": 0.4976, + "step": 1040 + }, + { + "epoch": 2.466099207513942, + "grad_norm": 0.5834274439157257, + "learning_rate": 5e-06, + "loss": 0.5052, + "step": 1050 + }, + { + "epoch": 2.4895802759025534, + "grad_norm": 0.777173362933167, + "learning_rate": 5e-06, + "loss": 0.4989, + "step": 1060 + }, + { + "epoch": 2.5130613442911653, + "grad_norm": 0.929125527693667, + "learning_rate": 5e-06, + "loss": 0.5059, + "step": 1070 + }, + { + "epoch": 2.536542412679777, + "grad_norm": 0.6950708275354937, + "learning_rate": 5e-06, + "loss": 0.4946, + "step": 1080 + }, + { + "epoch": 2.560023481068389, + "grad_norm": 0.5542934300294031, + "learning_rate": 5e-06, + "loss": 0.5086, + "step": 1090 + }, + { + "epoch": 2.5835045494570004, + "grad_norm": 0.7961833486998505, + "learning_rate": 5e-06, + "loss": 0.498, + "step": 1100 + }, + { + "epoch": 2.606985617845612, + "grad_norm": 0.6237039054057065, + "learning_rate": 5e-06, + "loss": 0.4998, + "step": 1110 + }, + { + "epoch": 2.6304666862342234, + "grad_norm": 0.5833433757118394, + "learning_rate": 5e-06, + "loss": 0.4944, + "step": 1120 + }, + { + "epoch": 2.6539477546228354, + "grad_norm": 0.5868493372745182, + "learning_rate": 5e-06, + "loss": 0.5028, + "step": 1130 + }, + { + "epoch": 2.677428823011447, + "grad_norm": 0.6399452879323836, + "learning_rate": 5e-06, + "loss": 0.4982, + "step": 1140 + }, + { + "epoch": 2.700909891400059, + "grad_norm": 0.6458178037380802, + "learning_rate": 5e-06, + "loss": 0.5009, + "step": 1150 + }, + { + "epoch": 2.7243909597886704, + "grad_norm": 0.5439040913583559, + "learning_rate": 5e-06, + "loss": 0.5012, + "step": 1160 + }, + { + "epoch": 2.747872028177282, + "grad_norm": 0.735794966069211, + "learning_rate": 5e-06, + "loss": 0.5032, + "step": 1170 + }, + { + "epoch": 2.771353096565894, + "grad_norm": 0.601851566145536, + "learning_rate": 5e-06, + "loss": 0.5033, + "step": 1180 + }, + { + "epoch": 2.7948341649545054, + "grad_norm": 0.5929336883777777, + "learning_rate": 5e-06, + "loss": 0.5037, + "step": 1190 + }, + { + "epoch": 2.818315233343117, + "grad_norm": 0.5778177618943612, + "learning_rate": 5e-06, + "loss": 0.508, + "step": 1200 + }, + { + "epoch": 2.841796301731729, + "grad_norm": 0.5990753577226628, + "learning_rate": 5e-06, + "loss": 0.4957, + "step": 1210 + }, + { + "epoch": 2.8652773701203404, + "grad_norm": 0.7825195485986434, + "learning_rate": 5e-06, + "loss": 0.499, + "step": 1220 + }, + { + "epoch": 2.888758438508952, + "grad_norm": 0.5698945641530911, + "learning_rate": 5e-06, + "loss": 0.4982, + "step": 1230 + }, + { + "epoch": 2.912239506897564, + "grad_norm": 0.5941997062897303, + "learning_rate": 5e-06, + "loss": 0.5006, + "step": 1240 + }, + { + "epoch": 2.9357205752861755, + "grad_norm": 0.5494008699329855, + "learning_rate": 5e-06, + "loss": 0.494, + "step": 1250 + }, + { + "epoch": 2.9592016436747874, + "grad_norm": 0.6295305801304111, + "learning_rate": 5e-06, + "loss": 0.5001, + "step": 1260 + }, + { + "epoch": 2.982682712063399, + "grad_norm": 0.6627594327431557, + "learning_rate": 5e-06, + "loss": 0.5003, + "step": 1270 + }, + { + "epoch": 2.9944232462577047, + "eval_loss": 0.5840933322906494, + "eval_runtime": 292.1509, + "eval_samples_per_second": 39.274, + "eval_steps_per_second": 0.616, + "step": 1275 + }, + { + "epoch": 2.9944232462577047, + "step": 1275, + "total_flos": 2135463108280320.0, + "train_loss": 0.5660238438026578, + "train_runtime": 41769.8593, + "train_samples_per_second": 15.658, + "train_steps_per_second": 0.031 + } + ], + "logging_steps": 10, + "max_steps": 1275, + "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": 2135463108280320.0, + "train_batch_size": 8, + "trial_name": null, + "trial_params": null +} diff --git a/training_args.bin b/training_args.bin new file mode 100644 index 0000000..aabef91 --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:803d2235d79818f865df026c6078b2cdca9e698a4367186ea6cf7fe97911a79d +size 7160 diff --git a/training_eval_loss.png b/training_eval_loss.png new file mode 100644 index 0000000..f3ca928 Binary files /dev/null and b/training_eval_loss.png differ diff --git a/training_loss.png b/training_loss.png new file mode 100644 index 0000000..4998cab Binary files /dev/null and b/training_loss.png differ