commit fd3eeb9e96d1a35076cbf863211ce8156239f83d Author: ModelHub XC Date: Fri Jun 26 23:06:12 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mlfoundations-dev/oh-dcft-v3.1-claude-3-5-sonnet-20241022 Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..130a36a --- /dev/null +++ b/.gitattributes @@ -0,0 +1,54 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text + + +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text + +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.gguf* filter=lfs diff=lfs merge=lfs -text +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text + +model-00001-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text +training_args.bin filter=lfs diff=lfs merge=lfs -text +model-00003-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +model-00004-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +model-00002-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..5611bc8 --- /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-claude-3-5-sonnet-20241022 + results: [] +--- + + + +# oh-dcft-v3.1-claude-3-5-sonnet-20241022 + +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-claude-3-5-sonnet-20241022 dataset. +It achieves the following results on the evaluation set: +- Loss: 0.4631 + +## 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 | +|:-------------:|:------:|:----:|:---------------:| +| 0.4822 | 0.9986 | 454 | 0.4843 | +| 0.4246 | 1.9995 | 909 | 0.4651 | +| 0.3735 | 2.9959 | 1362 | 0.4631 | + + +### 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..546c752 --- /dev/null +++ b/all_results.json @@ -0,0 +1,12 @@ +{ + "epoch": 2.995875721748694, + "eval_loss": 0.46309909224510193, + "eval_runtime": 303.4791, + "eval_samples_per_second": 40.369, + "eval_steps_per_second": 0.633, + "total_flos": 2281191348633600.0, + "train_loss": 0.44531785190192963, + "train_runtime": 45435.4893, + "train_samples_per_second": 15.368, + "train_steps_per_second": 0.03 +} \ 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..8b08660 --- /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-claude-3-5-sonnet-20241022 +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-claude-3-5-sonnet-20241022 +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-claude-3-5-sonnet-20241022 +save_strategy: epoch +stage: sft +template: llama3 +val_size: '0.05' +weight_decay: '0.1' diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file diff --git a/eval_results.json b/eval_results.json new file mode 100644 index 0000000..68bbaf6 --- /dev/null +++ b/eval_results.json @@ -0,0 +1,7 @@ +{ + "epoch": 2.995875721748694, + "eval_loss": 0.46309909224510193, + "eval_runtime": 303.4791, + "eval_samples_per_second": 40.369, + "eval_steps_per_second": 0.633 +} \ 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..83d6d76 --- /dev/null +++ b/model-00001-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ec9edd7cd8df2fcf1264b4fad1c1f05d7329ac1525927268e0dcba85aa98484 +size 4976698672 diff --git a/model-00002-of-00004.safetensors b/model-00002-of-00004.safetensors new file mode 100644 index 0000000..9b3ceb4 --- /dev/null +++ b/model-00002-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:447849aabe821a95cbe8fee34e425a2f4ee75e68c5e760f40f2ae11d1e2785c4 +size 4999802720 diff --git a/model-00003-of-00004.safetensors b/model-00003-of-00004.safetensors new file mode 100644 index 0000000..0d6b83f --- /dev/null +++ b/model-00003-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c67e7ffbce9103cfee4239af72936b1b2512854f650b73f6ac142628ddd4bbc +size 4915916176 diff --git a/model-00004-of-00004.safetensors b/model-00004-of-00004.safetensors new file mode 100644 index 0000000..24fc69f --- /dev/null +++ b/model-00004-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:916455d9384741d097fffd526034ed42fa53c121b84dcf8bd93b8c25a6cdd11c +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..442c466 --- /dev/null +++ b/train_results.json @@ -0,0 +1,8 @@ +{ + "epoch": 2.995875721748694, + "total_flos": 2281191348633600.0, + "train_loss": 0.44531785190192963, + "train_runtime": 45435.4893, + "train_samples_per_second": 15.368, + "train_steps_per_second": 0.03 +} \ No newline at end of file diff --git a/trainer_log.jsonl b/trainer_log.jsonl new file mode 100644 index 0000000..8653b40 --- /dev/null +++ b/trainer_log.jsonl @@ -0,0 +1,140 @@ +{"current_steps": 10, "total_steps": 1362, "loss": 0.7982, "lr": 5e-06, "epoch": 0.021996150673632114, "percentage": 0.73, "elapsed_time": "0:05:31", "remaining_time": "12:26:41"} +{"current_steps": 20, "total_steps": 1362, "loss": 0.6818, "lr": 5e-06, "epoch": 0.04399230134726423, "percentage": 1.47, "elapsed_time": "0:10:55", "remaining_time": "12:13:35"} +{"current_steps": 30, "total_steps": 1362, "loss": 0.6576, "lr": 5e-06, "epoch": 0.06598845202089634, "percentage": 2.2, "elapsed_time": "0:16:18", "remaining_time": "12:04:24"} +{"current_steps": 40, "total_steps": 1362, "loss": 0.6179, "lr": 5e-06, "epoch": 0.08798460269452846, "percentage": 2.94, "elapsed_time": "0:21:43", "remaining_time": "11:57:50"} +{"current_steps": 50, "total_steps": 1362, "loss": 0.5951, "lr": 5e-06, "epoch": 0.10998075336816057, "percentage": 3.67, "elapsed_time": "0:27:05", "remaining_time": "11:50:58"} +{"current_steps": 60, "total_steps": 1362, "loss": 0.579, "lr": 5e-06, "epoch": 0.1319769040417927, "percentage": 4.41, "elapsed_time": "0:32:28", "remaining_time": "11:44:42"} +{"current_steps": 70, "total_steps": 1362, "loss": 0.5625, "lr": 5e-06, "epoch": 0.1539730547154248, "percentage": 5.14, "elapsed_time": "0:37:52", "remaining_time": "11:39:00"} +{"current_steps": 80, "total_steps": 1362, "loss": 0.5544, "lr": 5e-06, "epoch": 0.17596920538905692, "percentage": 5.87, "elapsed_time": "0:43:15", "remaining_time": "11:33:06"} +{"current_steps": 90, "total_steps": 1362, "loss": 0.5474, "lr": 5e-06, "epoch": 0.19796535606268903, "percentage": 6.61, "elapsed_time": "0:48:40", "remaining_time": "11:27:53"} +{"current_steps": 100, "total_steps": 1362, "loss": 0.5403, "lr": 5e-06, "epoch": 0.21996150673632114, "percentage": 7.34, "elapsed_time": "0:54:05", "remaining_time": "11:22:41"} +{"current_steps": 110, "total_steps": 1362, "loss": 0.5409, "lr": 5e-06, "epoch": 0.24195765740995326, "percentage": 8.08, "elapsed_time": "0:59:29", "remaining_time": "11:17:04"} +{"current_steps": 120, "total_steps": 1362, "loss": 0.5282, "lr": 5e-06, "epoch": 0.2639538080835854, "percentage": 8.81, "elapsed_time": "1:04:52", "remaining_time": "11:11:30"} +{"current_steps": 130, "total_steps": 1362, "loss": 0.5315, "lr": 5e-06, "epoch": 0.28594995875721746, "percentage": 9.54, "elapsed_time": "1:10:15", "remaining_time": "11:05:53"} +{"current_steps": 140, "total_steps": 1362, "loss": 0.5307, "lr": 5e-06, "epoch": 0.3079461094308496, "percentage": 10.28, "elapsed_time": "1:15:38", "remaining_time": "11:00:17"} +{"current_steps": 150, "total_steps": 1362, "loss": 0.5256, "lr": 5e-06, "epoch": 0.3299422601044817, "percentage": 11.01, "elapsed_time": "1:21:01", "remaining_time": "10:54:39"} +{"current_steps": 160, "total_steps": 1362, "loss": 0.5236, "lr": 5e-06, "epoch": 0.35193841077811383, "percentage": 11.75, "elapsed_time": "1:26:26", "remaining_time": "10:49:20"} +{"current_steps": 170, "total_steps": 1362, "loss": 0.5148, "lr": 5e-06, "epoch": 0.3739345614517459, "percentage": 12.48, "elapsed_time": "1:31:49", "remaining_time": "10:43:51"} +{"current_steps": 180, "total_steps": 1362, "loss": 0.5147, "lr": 5e-06, "epoch": 0.39593071212537806, "percentage": 13.22, "elapsed_time": "1:37:11", "remaining_time": "10:38:14"} +{"current_steps": 190, "total_steps": 1362, "loss": 0.5184, "lr": 5e-06, "epoch": 0.41792686279901015, "percentage": 13.95, "elapsed_time": "1:42:33", "remaining_time": "10:32:39"} +{"current_steps": 200, "total_steps": 1362, "loss": 0.5099, "lr": 5e-06, "epoch": 0.4399230134726423, "percentage": 14.68, "elapsed_time": "1:47:56", "remaining_time": "10:27:08"} +{"current_steps": 210, "total_steps": 1362, "loss": 0.5117, "lr": 5e-06, "epoch": 0.4619191641462744, "percentage": 15.42, "elapsed_time": "1:53:19", "remaining_time": "10:21:40"} +{"current_steps": 220, "total_steps": 1362, "loss": 0.5055, "lr": 5e-06, "epoch": 0.4839153148199065, "percentage": 16.15, "elapsed_time": "1:58:41", "remaining_time": "10:16:09"} +{"current_steps": 230, "total_steps": 1362, "loss": 0.5043, "lr": 5e-06, "epoch": 0.5059114654935386, "percentage": 16.89, "elapsed_time": "2:04:04", "remaining_time": "10:10:38"} +{"current_steps": 240, "total_steps": 1362, "loss": 0.5084, "lr": 5e-06, "epoch": 0.5279076161671707, "percentage": 17.62, "elapsed_time": "2:09:26", "remaining_time": "10:05:08"} +{"current_steps": 250, "total_steps": 1362, "loss": 0.5007, "lr": 5e-06, "epoch": 0.5499037668408029, "percentage": 18.36, "elapsed_time": "2:14:49", "remaining_time": "9:59:40"} +{"current_steps": 260, "total_steps": 1362, "loss": 0.5004, "lr": 5e-06, "epoch": 0.5718999175144349, "percentage": 19.09, "elapsed_time": "2:20:15", "remaining_time": "9:54:28"} +{"current_steps": 270, "total_steps": 1362, "loss": 0.4997, "lr": 5e-06, "epoch": 0.5938960681880671, "percentage": 19.82, "elapsed_time": "2:25:38", "remaining_time": "9:49:02"} +{"current_steps": 280, "total_steps": 1362, "loss": 0.4933, "lr": 5e-06, "epoch": 0.6158922188616992, "percentage": 20.56, "elapsed_time": "2:31:01", "remaining_time": "9:43:34"} +{"current_steps": 290, "total_steps": 1362, "loss": 0.4969, "lr": 5e-06, "epoch": 0.6378883695353313, "percentage": 21.29, "elapsed_time": "2:36:23", "remaining_time": "9:38:08"} +{"current_steps": 300, "total_steps": 1362, "loss": 0.4971, "lr": 5e-06, "epoch": 0.6598845202089634, "percentage": 22.03, "elapsed_time": "2:41:46", "remaining_time": "9:32:41"} +{"current_steps": 310, "total_steps": 1362, "loss": 0.4883, "lr": 5e-06, "epoch": 0.6818806708825955, "percentage": 22.76, "elapsed_time": "2:47:11", "remaining_time": "9:27:22"} +{"current_steps": 320, "total_steps": 1362, "loss": 0.4912, "lr": 5e-06, "epoch": 0.7038768215562277, "percentage": 23.49, "elapsed_time": "2:52:35", "remaining_time": "9:22:00"} +{"current_steps": 330, "total_steps": 1362, "loss": 0.4961, "lr": 5e-06, "epoch": 0.7258729722298598, "percentage": 24.23, "elapsed_time": "2:58:01", "remaining_time": "9:16:43"} +{"current_steps": 340, "total_steps": 1362, "loss": 0.4879, "lr": 5e-06, "epoch": 0.7478691229034918, "percentage": 24.96, "elapsed_time": "3:03:26", "remaining_time": "9:11:24"} +{"current_steps": 350, "total_steps": 1362, "loss": 0.4948, "lr": 5e-06, "epoch": 0.769865273577124, "percentage": 25.7, "elapsed_time": "3:08:49", "remaining_time": "9:05:58"} +{"current_steps": 360, "total_steps": 1362, "loss": 0.491, "lr": 5e-06, "epoch": 0.7918614242507561, "percentage": 26.43, "elapsed_time": "3:14:16", "remaining_time": "9:00:42"} +{"current_steps": 370, "total_steps": 1362, "loss": 0.4924, "lr": 5e-06, "epoch": 0.8138575749243883, "percentage": 27.17, "elapsed_time": "3:19:41", "remaining_time": "8:55:23"} +{"current_steps": 380, "total_steps": 1362, "loss": 0.485, "lr": 5e-06, "epoch": 0.8358537255980203, "percentage": 27.9, "elapsed_time": "3:25:05", "remaining_time": "8:50:00"} +{"current_steps": 390, "total_steps": 1362, "loss": 0.4913, "lr": 5e-06, "epoch": 0.8578498762716524, "percentage": 28.63, "elapsed_time": "3:30:30", "remaining_time": "8:44:39"} +{"current_steps": 400, "total_steps": 1362, "loss": 0.4946, "lr": 5e-06, "epoch": 0.8798460269452846, "percentage": 29.37, "elapsed_time": "3:35:56", "remaining_time": "8:39:19"} +{"current_steps": 410, "total_steps": 1362, "loss": 0.478, "lr": 5e-06, "epoch": 0.9018421776189167, "percentage": 30.1, "elapsed_time": "3:41:21", "remaining_time": "8:34:00"} +{"current_steps": 420, "total_steps": 1362, "loss": 0.485, "lr": 5e-06, "epoch": 0.9238383282925487, "percentage": 30.84, "elapsed_time": "3:46:47", "remaining_time": "8:28:39"} +{"current_steps": 430, "total_steps": 1362, "loss": 0.4841, "lr": 5e-06, "epoch": 0.9458344789661809, "percentage": 31.57, "elapsed_time": "3:52:12", "remaining_time": "8:23:18"} +{"current_steps": 440, "total_steps": 1362, "loss": 0.4805, "lr": 5e-06, "epoch": 0.967830629639813, "percentage": 32.31, "elapsed_time": "3:57:37", "remaining_time": "8:17:55"} +{"current_steps": 450, "total_steps": 1362, "loss": 0.4822, "lr": 5e-06, "epoch": 0.9898267803134452, "percentage": 33.04, "elapsed_time": "4:03:02", "remaining_time": "8:12:34"} +{"current_steps": 454, "total_steps": 1362, "eval_loss": 0.4843384027481079, "epoch": 0.998625240582898, "percentage": 33.33, "elapsed_time": "4:10:53", "remaining_time": "8:21:46"} +{"current_steps": 460, "total_steps": 1362, "loss": 0.4742, "lr": 5e-06, "epoch": 1.0118229309870772, "percentage": 33.77, "elapsed_time": "4:15:02", "remaining_time": "8:20:05"} +{"current_steps": 470, "total_steps": 1362, "loss": 0.4381, "lr": 5e-06, "epoch": 1.0338190816607093, "percentage": 34.51, "elapsed_time": "4:20:27", "remaining_time": "8:14:18"} +{"current_steps": 480, "total_steps": 1362, "loss": 0.4396, "lr": 5e-06, "epoch": 1.0558152323343415, "percentage": 35.24, "elapsed_time": "4:25:52", "remaining_time": "8:08:32"} +{"current_steps": 490, "total_steps": 1362, "loss": 0.436, "lr": 5e-06, "epoch": 1.0778113830079736, "percentage": 35.98, "elapsed_time": "4:31:16", "remaining_time": "8:02:46"} +{"current_steps": 500, "total_steps": 1362, "loss": 0.4308, "lr": 5e-06, "epoch": 1.0998075336816058, "percentage": 36.71, "elapsed_time": "4:36:41", "remaining_time": "7:57:01"} +{"current_steps": 510, "total_steps": 1362, "loss": 0.4368, "lr": 5e-06, "epoch": 1.121803684355238, "percentage": 37.44, "elapsed_time": "4:42:05", "remaining_time": "7:51:14"} +{"current_steps": 520, "total_steps": 1362, "loss": 0.4419, "lr": 5e-06, "epoch": 1.14379983502887, "percentage": 38.18, "elapsed_time": "4:47:30", "remaining_time": "7:45:31"} +{"current_steps": 530, "total_steps": 1362, "loss": 0.4361, "lr": 5e-06, "epoch": 1.165795985702502, "percentage": 38.91, "elapsed_time": "4:52:54", "remaining_time": "7:39:48"} +{"current_steps": 540, "total_steps": 1362, "loss": 0.4345, "lr": 5e-06, "epoch": 1.1877921363761341, "percentage": 39.65, "elapsed_time": "4:58:16", "remaining_time": "7:34:02"} +{"current_steps": 550, "total_steps": 1362, "loss": 0.4339, "lr": 5e-06, "epoch": 1.2097882870497663, "percentage": 40.38, "elapsed_time": "5:03:39", "remaining_time": "7:28:18"} +{"current_steps": 560, "total_steps": 1362, "loss": 0.4385, "lr": 5e-06, "epoch": 1.2317844377233984, "percentage": 41.12, "elapsed_time": "5:09:02", "remaining_time": "7:22:35"} +{"current_steps": 570, "total_steps": 1362, "loss": 0.4329, "lr": 5e-06, "epoch": 1.2537805883970305, "percentage": 41.85, "elapsed_time": "5:14:27", "remaining_time": "7:16:56"} +{"current_steps": 580, "total_steps": 1362, "loss": 0.4333, "lr": 5e-06, "epoch": 1.2757767390706627, "percentage": 42.58, "elapsed_time": "5:19:51", "remaining_time": "7:11:15"} +{"current_steps": 590, "total_steps": 1362, "loss": 0.4317, "lr": 5e-06, "epoch": 1.2977728897442948, "percentage": 43.32, "elapsed_time": "5:25:13", "remaining_time": "7:05:32"} +{"current_steps": 600, "total_steps": 1362, "loss": 0.4294, "lr": 5e-06, "epoch": 1.3197690404179268, "percentage": 44.05, "elapsed_time": "5:30:37", "remaining_time": "6:59:54"} +{"current_steps": 610, "total_steps": 1362, "loss": 0.4305, "lr": 5e-06, "epoch": 1.341765191091559, "percentage": 44.79, "elapsed_time": "5:36:03", "remaining_time": "6:54:17"} +{"current_steps": 620, "total_steps": 1362, "loss": 0.4358, "lr": 5e-06, "epoch": 1.363761341765191, "percentage": 45.52, "elapsed_time": "5:41:27", "remaining_time": "6:48:38"} +{"current_steps": 630, "total_steps": 1362, "loss": 0.433, "lr": 5e-06, "epoch": 1.3857574924388232, "percentage": 46.26, "elapsed_time": "5:46:51", "remaining_time": "6:43:00"} +{"current_steps": 640, "total_steps": 1362, "loss": 0.4316, "lr": 5e-06, "epoch": 1.4077536431124553, "percentage": 46.99, "elapsed_time": "5:52:16", "remaining_time": "6:37:24"} +{"current_steps": 650, "total_steps": 1362, "loss": 0.4309, "lr": 5e-06, "epoch": 1.4297497937860875, "percentage": 47.72, "elapsed_time": "5:57:41", "remaining_time": "6:31:48"} +{"current_steps": 660, "total_steps": 1362, "loss": 0.438, "lr": 5e-06, "epoch": 1.4517459444597196, "percentage": 48.46, "elapsed_time": "6:03:05", "remaining_time": "6:26:12"} +{"current_steps": 670, "total_steps": 1362, "loss": 0.4279, "lr": 5e-06, "epoch": 1.4737420951333515, "percentage": 49.19, "elapsed_time": "6:08:30", "remaining_time": "6:20:36"} +{"current_steps": 680, "total_steps": 1362, "loss": 0.4326, "lr": 5e-06, "epoch": 1.495738245806984, "percentage": 49.93, "elapsed_time": "6:13:55", "remaining_time": "6:15:01"} +{"current_steps": 690, "total_steps": 1362, "loss": 0.4359, "lr": 5e-06, "epoch": 1.5177343964806158, "percentage": 50.66, "elapsed_time": "6:19:18", "remaining_time": "6:09:24"} +{"current_steps": 700, "total_steps": 1362, "loss": 0.4291, "lr": 5e-06, "epoch": 1.539730547154248, "percentage": 51.4, "elapsed_time": "6:24:41", "remaining_time": "6:03:48"} +{"current_steps": 710, "total_steps": 1362, "loss": 0.4303, "lr": 5e-06, "epoch": 1.56172669782788, "percentage": 52.13, "elapsed_time": "6:30:06", "remaining_time": "5:58:14"} +{"current_steps": 720, "total_steps": 1362, "loss": 0.4324, "lr": 5e-06, "epoch": 1.5837228485015122, "percentage": 52.86, "elapsed_time": "6:35:29", "remaining_time": "5:52:39"} +{"current_steps": 730, "total_steps": 1362, "loss": 0.4345, "lr": 5e-06, "epoch": 1.6057189991751444, "percentage": 53.6, "elapsed_time": "6:40:53", "remaining_time": "5:47:04"} +{"current_steps": 740, "total_steps": 1362, "loss": 0.4311, "lr": 5e-06, "epoch": 1.6277151498487763, "percentage": 54.33, "elapsed_time": "6:46:19", "remaining_time": "5:41:31"} +{"current_steps": 750, "total_steps": 1362, "loss": 0.4297, "lr": 5e-06, "epoch": 1.6497113005224087, "percentage": 55.07, "elapsed_time": "6:51:44", "remaining_time": "5:35:58"} +{"current_steps": 760, "total_steps": 1362, "loss": 0.4258, "lr": 5e-06, "epoch": 1.6717074511960406, "percentage": 55.8, "elapsed_time": "6:57:09", "remaining_time": "5:30:26"} +{"current_steps": 770, "total_steps": 1362, "loss": 0.4308, "lr": 5e-06, "epoch": 1.693703601869673, "percentage": 56.53, "elapsed_time": "7:02:33", "remaining_time": "5:24:52"} +{"current_steps": 780, "total_steps": 1362, "loss": 0.4278, "lr": 5e-06, "epoch": 1.7156997525433049, "percentage": 57.27, "elapsed_time": "7:07:58", "remaining_time": "5:19:19"} +{"current_steps": 790, "total_steps": 1362, "loss": 0.4267, "lr": 5e-06, "epoch": 1.737695903216937, "percentage": 58.0, "elapsed_time": "7:13:23", "remaining_time": "5:13:47"} +{"current_steps": 800, "total_steps": 1362, "loss": 0.4323, "lr": 5e-06, "epoch": 1.7596920538905692, "percentage": 58.74, "elapsed_time": "7:18:46", "remaining_time": "5:08:14"} +{"current_steps": 810, "total_steps": 1362, "loss": 0.4265, "lr": 5e-06, "epoch": 1.7816882045642013, "percentage": 59.47, "elapsed_time": "7:24:11", "remaining_time": "5:02:42"} +{"current_steps": 820, "total_steps": 1362, "loss": 0.4299, "lr": 5e-06, "epoch": 1.8036843552378334, "percentage": 60.21, "elapsed_time": "7:29:33", "remaining_time": "4:57:08"} +{"current_steps": 830, "total_steps": 1362, "loss": 0.4254, "lr": 5e-06, "epoch": 1.8256805059114654, "percentage": 60.94, "elapsed_time": "7:34:57", "remaining_time": "4:51:36"} +{"current_steps": 840, "total_steps": 1362, "loss": 0.4268, "lr": 5e-06, "epoch": 1.8476766565850977, "percentage": 61.67, "elapsed_time": "7:40:23", "remaining_time": "4:46:06"} +{"current_steps": 850, "total_steps": 1362, "loss": 0.4229, "lr": 5e-06, "epoch": 1.8696728072587296, "percentage": 62.41, "elapsed_time": "7:45:49", "remaining_time": "4:40:35"} +{"current_steps": 860, "total_steps": 1362, "loss": 0.4238, "lr": 5e-06, "epoch": 1.8916689579323618, "percentage": 63.14, "elapsed_time": "7:51:14", "remaining_time": "4:35:04"} +{"current_steps": 870, "total_steps": 1362, "loss": 0.4267, "lr": 5e-06, "epoch": 1.913665108605994, "percentage": 63.88, "elapsed_time": "7:56:39", "remaining_time": "4:29:33"} +{"current_steps": 880, "total_steps": 1362, "loss": 0.426, "lr": 5e-06, "epoch": 1.935661259279626, "percentage": 64.61, "elapsed_time": "8:02:04", "remaining_time": "4:24:02"} +{"current_steps": 890, "total_steps": 1362, "loss": 0.4274, "lr": 5e-06, "epoch": 1.9576574099532582, "percentage": 65.35, "elapsed_time": "8:07:25", "remaining_time": "4:18:30"} +{"current_steps": 900, "total_steps": 1362, "loss": 0.4246, "lr": 5e-06, "epoch": 1.9796535606268901, "percentage": 66.08, "elapsed_time": "8:12:49", "remaining_time": "4:12:58"} +{"current_steps": 909, "total_steps": 1362, "eval_loss": 0.46506866812705994, "epoch": 1.9994500962331592, "percentage": 66.74, "elapsed_time": "8:23:02", "remaining_time": "4:10:41"} +{"current_steps": 910, "total_steps": 1362, "loss": 0.4343, "lr": 5e-06, "epoch": 2.0016497113005225, "percentage": 66.81, "elapsed_time": "8:24:45", "remaining_time": "4:10:43"} +{"current_steps": 920, "total_steps": 1362, "loss": 0.3763, "lr": 5e-06, "epoch": 2.0236458619741544, "percentage": 67.55, "elapsed_time": "8:30:09", "remaining_time": "4:05:06"} +{"current_steps": 930, "total_steps": 1362, "loss": 0.3715, "lr": 5e-06, "epoch": 2.045642012647787, "percentage": 68.28, "elapsed_time": "8:35:34", "remaining_time": "3:59:29"} +{"current_steps": 940, "total_steps": 1362, "loss": 0.3793, "lr": 5e-06, "epoch": 2.0676381633214187, "percentage": 69.02, "elapsed_time": "8:40:59", "remaining_time": "3:53:53"} +{"current_steps": 950, "total_steps": 1362, "loss": 0.3768, "lr": 5e-06, "epoch": 2.089634313995051, "percentage": 69.75, "elapsed_time": "8:46:24", "remaining_time": "3:48:17"} +{"current_steps": 960, "total_steps": 1362, "loss": 0.381, "lr": 5e-06, "epoch": 2.111630464668683, "percentage": 70.48, "elapsed_time": "8:51:50", "remaining_time": "3:42:42"} +{"current_steps": 970, "total_steps": 1362, "loss": 0.3779, "lr": 5e-06, "epoch": 2.133626615342315, "percentage": 71.22, "elapsed_time": "8:57:15", "remaining_time": "3:37:07"} +{"current_steps": 980, "total_steps": 1362, "loss": 0.3757, "lr": 5e-06, "epoch": 2.1556227660159473, "percentage": 71.95, "elapsed_time": "9:02:40", "remaining_time": "3:31:31"} +{"current_steps": 990, "total_steps": 1362, "loss": 0.3799, "lr": 5e-06, "epoch": 2.177618916689579, "percentage": 72.69, "elapsed_time": "9:08:05", "remaining_time": "3:25:57"} +{"current_steps": 1000, "total_steps": 1362, "loss": 0.3791, "lr": 5e-06, "epoch": 2.1996150673632116, "percentage": 73.42, "elapsed_time": "9:13:31", "remaining_time": "3:20:22"} +{"current_steps": 1010, "total_steps": 1362, "loss": 0.3767, "lr": 5e-06, "epoch": 2.2216112180368435, "percentage": 74.16, "elapsed_time": "9:18:55", "remaining_time": "3:14:47"} +{"current_steps": 1020, "total_steps": 1362, "loss": 0.3775, "lr": 5e-06, "epoch": 2.243607368710476, "percentage": 74.89, "elapsed_time": "9:24:19", "remaining_time": "3:09:12"} +{"current_steps": 1030, "total_steps": 1362, "loss": 0.3776, "lr": 5e-06, "epoch": 2.2656035193841078, "percentage": 75.62, "elapsed_time": "9:29:41", "remaining_time": "3:03:37"} +{"current_steps": 1040, "total_steps": 1362, "loss": 0.3768, "lr": 5e-06, "epoch": 2.28759967005774, "percentage": 76.36, "elapsed_time": "9:35:05", "remaining_time": "2:58:03"} +{"current_steps": 1050, "total_steps": 1362, "loss": 0.3743, "lr": 5e-06, "epoch": 2.309595820731372, "percentage": 77.09, "elapsed_time": "9:40:29", "remaining_time": "2:52:29"} +{"current_steps": 1060, "total_steps": 1362, "loss": 0.3817, "lr": 5e-06, "epoch": 2.331591971405004, "percentage": 77.83, "elapsed_time": "9:45:53", "remaining_time": "2:46:55"} +{"current_steps": 1070, "total_steps": 1362, "loss": 0.3782, "lr": 5e-06, "epoch": 2.3535881220786363, "percentage": 78.56, "elapsed_time": "9:51:18", "remaining_time": "2:41:22"} +{"current_steps": 1080, "total_steps": 1362, "loss": 0.3802, "lr": 5e-06, "epoch": 2.3755842727522682, "percentage": 79.3, "elapsed_time": "9:56:42", "remaining_time": "2:35:48"} +{"current_steps": 1090, "total_steps": 1362, "loss": 0.3756, "lr": 5e-06, "epoch": 2.3975804234259006, "percentage": 80.03, "elapsed_time": "10:02:05", "remaining_time": "2:30:14"} +{"current_steps": 1100, "total_steps": 1362, "loss": 0.3792, "lr": 5e-06, "epoch": 2.4195765740995325, "percentage": 80.76, "elapsed_time": "10:07:28", "remaining_time": "2:24:41"} +{"current_steps": 1110, "total_steps": 1362, "loss": 0.3842, "lr": 5e-06, "epoch": 2.441572724773165, "percentage": 81.5, "elapsed_time": "10:12:50", "remaining_time": "2:19:07"} +{"current_steps": 1120, "total_steps": 1362, "loss": 0.3767, "lr": 5e-06, "epoch": 2.463568875446797, "percentage": 82.23, "elapsed_time": "10:18:15", "remaining_time": "2:13:35"} +{"current_steps": 1130, "total_steps": 1362, "loss": 0.3827, "lr": 5e-06, "epoch": 2.4855650261204287, "percentage": 82.97, "elapsed_time": "10:23:40", "remaining_time": "2:08:02"} +{"current_steps": 1140, "total_steps": 1362, "loss": 0.3849, "lr": 5e-06, "epoch": 2.507561176794061, "percentage": 83.7, "elapsed_time": "10:29:04", "remaining_time": "2:02:30"} +{"current_steps": 1150, "total_steps": 1362, "loss": 0.3813, "lr": 5e-06, "epoch": 2.529557327467693, "percentage": 84.43, "elapsed_time": "10:34:29", "remaining_time": "1:56:58"} +{"current_steps": 1160, "total_steps": 1362, "loss": 0.3804, "lr": 5e-06, "epoch": 2.5515534781413254, "percentage": 85.17, "elapsed_time": "10:39:55", "remaining_time": "1:51:26"} +{"current_steps": 1170, "total_steps": 1362, "loss": 0.3751, "lr": 5e-06, "epoch": 2.5735496288149573, "percentage": 85.9, "elapsed_time": "10:45:19", "remaining_time": "1:45:53"} +{"current_steps": 1180, "total_steps": 1362, "loss": 0.3731, "lr": 5e-06, "epoch": 2.5955457794885897, "percentage": 86.64, "elapsed_time": "10:50:43", "remaining_time": "1:40:21"} +{"current_steps": 1190, "total_steps": 1362, "loss": 0.3757, "lr": 5e-06, "epoch": 2.6175419301622216, "percentage": 87.37, "elapsed_time": "10:56:09", "remaining_time": "1:34:50"} +{"current_steps": 1200, "total_steps": 1362, "loss": 0.3742, "lr": 5e-06, "epoch": 2.6395380808358535, "percentage": 88.11, "elapsed_time": "11:01:35", "remaining_time": "1:29:18"} +{"current_steps": 1210, "total_steps": 1362, "loss": 0.3753, "lr": 5e-06, "epoch": 2.661534231509486, "percentage": 88.84, "elapsed_time": "11:07:00", "remaining_time": "1:23:47"} +{"current_steps": 1220, "total_steps": 1362, "loss": 0.3741, "lr": 5e-06, "epoch": 2.683530382183118, "percentage": 89.57, "elapsed_time": "11:12:25", "remaining_time": "1:18:16"} +{"current_steps": 1230, "total_steps": 1362, "loss": 0.3785, "lr": 5e-06, "epoch": 2.70552653285675, "percentage": 90.31, "elapsed_time": "11:17:49", "remaining_time": "1:12:44"} +{"current_steps": 1240, "total_steps": 1362, "loss": 0.3761, "lr": 5e-06, "epoch": 2.727522683530382, "percentage": 91.04, "elapsed_time": "11:23:13", "remaining_time": "1:07:13"} +{"current_steps": 1250, "total_steps": 1362, "loss": 0.3748, "lr": 5e-06, "epoch": 2.7495188342040144, "percentage": 91.78, "elapsed_time": "11:28:37", "remaining_time": "1:01:42"} +{"current_steps": 1260, "total_steps": 1362, "loss": 0.3728, "lr": 5e-06, "epoch": 2.7715149848776464, "percentage": 92.51, "elapsed_time": "11:34:02", "remaining_time": "0:56:11"} +{"current_steps": 1270, "total_steps": 1362, "loss": 0.3794, "lr": 5e-06, "epoch": 2.7935111355512783, "percentage": 93.25, "elapsed_time": "11:39:28", "remaining_time": "0:50:40"} +{"current_steps": 1280, "total_steps": 1362, "loss": 0.3789, "lr": 5e-06, "epoch": 2.8155072862249106, "percentage": 93.98, "elapsed_time": "11:44:53", "remaining_time": "0:45:09"} +{"current_steps": 1290, "total_steps": 1362, "loss": 0.3732, "lr": 5e-06, "epoch": 2.837503436898543, "percentage": 94.71, "elapsed_time": "11:50:16", "remaining_time": "0:39:38"} +{"current_steps": 1300, "total_steps": 1362, "loss": 0.3741, "lr": 5e-06, "epoch": 2.859499587572175, "percentage": 95.45, "elapsed_time": "11:55:42", "remaining_time": "0:34:08"} +{"current_steps": 1310, "total_steps": 1362, "loss": 0.3753, "lr": 5e-06, "epoch": 2.881495738245807, "percentage": 96.18, "elapsed_time": "12:01:07", "remaining_time": "0:28:37"} +{"current_steps": 1320, "total_steps": 1362, "loss": 0.3756, "lr": 5e-06, "epoch": 2.903491888919439, "percentage": 96.92, "elapsed_time": "12:06:32", "remaining_time": "0:23:07"} +{"current_steps": 1330, "total_steps": 1362, "loss": 0.378, "lr": 5e-06, "epoch": 2.925488039593071, "percentage": 97.65, "elapsed_time": "12:11:56", "remaining_time": "0:17:36"} +{"current_steps": 1340, "total_steps": 1362, "loss": 0.3795, "lr": 5e-06, "epoch": 2.947484190266703, "percentage": 98.38, "elapsed_time": "12:17:22", "remaining_time": "0:12:06"} +{"current_steps": 1350, "total_steps": 1362, "loss": 0.3742, "lr": 5e-06, "epoch": 2.9694803409403354, "percentage": 99.12, "elapsed_time": "12:22:46", "remaining_time": "0:06:36"} +{"current_steps": 1360, "total_steps": 1362, "loss": 0.3735, "lr": 5e-06, "epoch": 2.991476491613968, "percentage": 99.85, "elapsed_time": "12:28:10", "remaining_time": "0:01:06"} +{"current_steps": 1362, "total_steps": 1362, "eval_loss": 0.46309909224510193, "epoch": 2.995875721748694, "percentage": 100.0, "elapsed_time": "12:35:40", "remaining_time": "0:00:00"} +{"current_steps": 1362, "total_steps": 1362, "epoch": 2.995875721748694, "percentage": 100.0, "elapsed_time": "12:37:14", "remaining_time": "0:00:00"} diff --git a/trainer_state.json b/trainer_state.json new file mode 100644 index 0000000..82823ea --- /dev/null +++ b/trainer_state.json @@ -0,0 +1,1018 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 2.995875721748694, + "eval_steps": 500, + "global_step": 1362, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.021996150673632114, + "grad_norm": 44.935070793507286, + "learning_rate": 5e-06, + "loss": 0.7982, + "step": 10 + }, + { + "epoch": 0.04399230134726423, + "grad_norm": 51.99237463948744, + "learning_rate": 5e-06, + "loss": 0.6818, + "step": 20 + }, + { + "epoch": 0.06598845202089634, + "grad_norm": 2.029518123215705, + "learning_rate": 5e-06, + "loss": 0.6576, + "step": 30 + }, + { + "epoch": 0.08798460269452846, + "grad_norm": 0.8501991380139163, + "learning_rate": 5e-06, + "loss": 0.6179, + "step": 40 + }, + { + "epoch": 0.10998075336816057, + "grad_norm": 0.7157876899989635, + "learning_rate": 5e-06, + "loss": 0.5951, + "step": 50 + }, + { + "epoch": 0.1319769040417927, + "grad_norm": 0.6923489466872192, + "learning_rate": 5e-06, + "loss": 0.579, + "step": 60 + }, + { + "epoch": 0.1539730547154248, + "grad_norm": 0.6162592994801409, + "learning_rate": 5e-06, + "loss": 0.5625, + "step": 70 + }, + { + "epoch": 0.17596920538905692, + "grad_norm": 0.6070124857659416, + "learning_rate": 5e-06, + "loss": 0.5544, + "step": 80 + }, + { + "epoch": 0.19796535606268903, + "grad_norm": 0.7389354403531135, + "learning_rate": 5e-06, + "loss": 0.5474, + "step": 90 + }, + { + "epoch": 0.21996150673632114, + "grad_norm": 0.5830266561233308, + "learning_rate": 5e-06, + "loss": 0.5403, + "step": 100 + }, + { + "epoch": 0.24195765740995326, + "grad_norm": 0.609863769379669, + "learning_rate": 5e-06, + "loss": 0.5409, + "step": 110 + }, + { + "epoch": 0.2639538080835854, + "grad_norm": 0.5471425920538027, + "learning_rate": 5e-06, + "loss": 0.5282, + "step": 120 + }, + { + "epoch": 0.28594995875721746, + "grad_norm": 0.5504648496085665, + "learning_rate": 5e-06, + "loss": 0.5315, + "step": 130 + }, + { + "epoch": 0.3079461094308496, + "grad_norm": 0.5600291116467604, + "learning_rate": 5e-06, + "loss": 0.5307, + "step": 140 + }, + { + "epoch": 0.3299422601044817, + "grad_norm": 0.6781742737436763, + "learning_rate": 5e-06, + "loss": 0.5256, + "step": 150 + }, + { + "epoch": 0.35193841077811383, + "grad_norm": 0.5570436479921453, + "learning_rate": 5e-06, + "loss": 0.5236, + "step": 160 + }, + { + "epoch": 0.3739345614517459, + "grad_norm": 0.7382087470875334, + "learning_rate": 5e-06, + "loss": 0.5148, + "step": 170 + }, + { + "epoch": 0.39593071212537806, + "grad_norm": 0.6677212573270707, + "learning_rate": 5e-06, + "loss": 0.5147, + "step": 180 + }, + { + "epoch": 0.41792686279901015, + "grad_norm": 0.6534622609569957, + "learning_rate": 5e-06, + "loss": 0.5184, + "step": 190 + }, + { + "epoch": 0.4399230134726423, + "grad_norm": 0.6389305122495185, + "learning_rate": 5e-06, + "loss": 0.5099, + "step": 200 + }, + { + "epoch": 0.4619191641462744, + "grad_norm": 0.5533607211490192, + "learning_rate": 5e-06, + "loss": 0.5117, + "step": 210 + }, + { + "epoch": 0.4839153148199065, + "grad_norm": 0.5615265500686734, + "learning_rate": 5e-06, + "loss": 0.5055, + "step": 220 + }, + { + "epoch": 0.5059114654935386, + "grad_norm": 0.6044913138154236, + "learning_rate": 5e-06, + "loss": 0.5043, + "step": 230 + }, + { + "epoch": 0.5279076161671707, + "grad_norm": 0.6911732267120813, + "learning_rate": 5e-06, + "loss": 0.5084, + "step": 240 + }, + { + "epoch": 0.5499037668408029, + "grad_norm": 0.6913728871930638, + "learning_rate": 5e-06, + "loss": 0.5007, + "step": 250 + }, + { + "epoch": 0.5718999175144349, + "grad_norm": 0.5458408162252775, + "learning_rate": 5e-06, + "loss": 0.5004, + "step": 260 + }, + { + "epoch": 0.5938960681880671, + "grad_norm": 0.4864371771009518, + "learning_rate": 5e-06, + "loss": 0.4997, + "step": 270 + }, + { + "epoch": 0.6158922188616992, + "grad_norm": 0.5505465151810486, + "learning_rate": 5e-06, + "loss": 0.4933, + "step": 280 + }, + { + "epoch": 0.6378883695353313, + "grad_norm": 0.5500982529995515, + "learning_rate": 5e-06, + "loss": 0.4969, + "step": 290 + }, + { + "epoch": 0.6598845202089634, + "grad_norm": 0.6818273388657722, + "learning_rate": 5e-06, + "loss": 0.4971, + "step": 300 + }, + { + "epoch": 0.6818806708825955, + "grad_norm": 0.8228558846974066, + "learning_rate": 5e-06, + "loss": 0.4883, + "step": 310 + }, + { + "epoch": 0.7038768215562277, + "grad_norm": 0.5100124377410133, + "learning_rate": 5e-06, + "loss": 0.4912, + "step": 320 + }, + { + "epoch": 0.7258729722298598, + "grad_norm": 0.5023160939160082, + "learning_rate": 5e-06, + "loss": 0.4961, + "step": 330 + }, + { + "epoch": 0.7478691229034918, + "grad_norm": 0.5390556024217283, + "learning_rate": 5e-06, + "loss": 0.4879, + "step": 340 + }, + { + "epoch": 0.769865273577124, + "grad_norm": 0.5699354382297954, + "learning_rate": 5e-06, + "loss": 0.4948, + "step": 350 + }, + { + "epoch": 0.7918614242507561, + "grad_norm": 0.5193233018168463, + "learning_rate": 5e-06, + "loss": 0.491, + "step": 360 + }, + { + "epoch": 0.8138575749243883, + "grad_norm": 0.4831702719594887, + "learning_rate": 5e-06, + "loss": 0.4924, + "step": 370 + }, + { + "epoch": 0.8358537255980203, + "grad_norm": 0.46518212576460566, + "learning_rate": 5e-06, + "loss": 0.485, + "step": 380 + }, + { + "epoch": 0.8578498762716524, + "grad_norm": 0.6352722047223296, + "learning_rate": 5e-06, + "loss": 0.4913, + "step": 390 + }, + { + "epoch": 0.8798460269452846, + "grad_norm": 0.53358894593737, + "learning_rate": 5e-06, + "loss": 0.4946, + "step": 400 + }, + { + "epoch": 0.9018421776189167, + "grad_norm": 0.7885388229348029, + "learning_rate": 5e-06, + "loss": 0.478, + "step": 410 + }, + { + "epoch": 0.9238383282925487, + "grad_norm": 0.529600748072463, + "learning_rate": 5e-06, + "loss": 0.485, + "step": 420 + }, + { + "epoch": 0.9458344789661809, + "grad_norm": 0.7784357593762018, + "learning_rate": 5e-06, + "loss": 0.4841, + "step": 430 + }, + { + "epoch": 0.967830629639813, + "grad_norm": 0.5061344396278, + "learning_rate": 5e-06, + "loss": 0.4805, + "step": 440 + }, + { + "epoch": 0.9898267803134452, + "grad_norm": 0.6066757845714082, + "learning_rate": 5e-06, + "loss": 0.4822, + "step": 450 + }, + { + "epoch": 0.998625240582898, + "eval_loss": 0.4843384027481079, + "eval_runtime": 321.1703, + "eval_samples_per_second": 38.145, + "eval_steps_per_second": 0.598, + "step": 454 + }, + { + "epoch": 1.0118229309870772, + "grad_norm": 0.6845501483696066, + "learning_rate": 5e-06, + "loss": 0.4742, + "step": 460 + }, + { + "epoch": 1.0338190816607093, + "grad_norm": 0.5184208422093173, + "learning_rate": 5e-06, + "loss": 0.4381, + "step": 470 + }, + { + "epoch": 1.0558152323343415, + "grad_norm": 0.5477404832032738, + "learning_rate": 5e-06, + "loss": 0.4396, + "step": 480 + }, + { + "epoch": 1.0778113830079736, + "grad_norm": 0.5481304063783221, + "learning_rate": 5e-06, + "loss": 0.436, + "step": 490 + }, + { + "epoch": 1.0998075336816058, + "grad_norm": 0.560826060704074, + "learning_rate": 5e-06, + "loss": 0.4308, + "step": 500 + }, + { + "epoch": 1.121803684355238, + "grad_norm": 0.5361777988288693, + "learning_rate": 5e-06, + "loss": 0.4368, + "step": 510 + }, + { + "epoch": 1.14379983502887, + "grad_norm": 0.6716133763509267, + "learning_rate": 5e-06, + "loss": 0.4419, + "step": 520 + }, + { + "epoch": 1.165795985702502, + "grad_norm": 0.5542234581455023, + "learning_rate": 5e-06, + "loss": 0.4361, + "step": 530 + }, + { + "epoch": 1.1877921363761341, + "grad_norm": 0.7101633877411753, + "learning_rate": 5e-06, + "loss": 0.4345, + "step": 540 + }, + { + "epoch": 1.2097882870497663, + "grad_norm": 0.5238276115814429, + "learning_rate": 5e-06, + "loss": 0.4339, + "step": 550 + }, + { + "epoch": 1.2317844377233984, + "grad_norm": 0.603854926816251, + "learning_rate": 5e-06, + "loss": 0.4385, + "step": 560 + }, + { + "epoch": 1.2537805883970305, + "grad_norm": 0.5352576431626216, + "learning_rate": 5e-06, + "loss": 0.4329, + "step": 570 + }, + { + "epoch": 1.2757767390706627, + "grad_norm": 0.6947929349739098, + "learning_rate": 5e-06, + "loss": 0.4333, + "step": 580 + }, + { + "epoch": 1.2977728897442948, + "grad_norm": 0.4804562251229763, + "learning_rate": 5e-06, + "loss": 0.4317, + "step": 590 + }, + { + "epoch": 1.3197690404179268, + "grad_norm": 0.48050470497866915, + "learning_rate": 5e-06, + "loss": 0.4294, + "step": 600 + }, + { + "epoch": 1.341765191091559, + "grad_norm": 0.5373174751277382, + "learning_rate": 5e-06, + "loss": 0.4305, + "step": 610 + }, + { + "epoch": 1.363761341765191, + "grad_norm": 0.6344457366504956, + "learning_rate": 5e-06, + "loss": 0.4358, + "step": 620 + }, + { + "epoch": 1.3857574924388232, + "grad_norm": 0.5663331681106669, + "learning_rate": 5e-06, + "loss": 0.433, + "step": 630 + }, + { + "epoch": 1.4077536431124553, + "grad_norm": 0.5460973181725048, + "learning_rate": 5e-06, + "loss": 0.4316, + "step": 640 + }, + { + "epoch": 1.4297497937860875, + "grad_norm": 0.5442052750881347, + "learning_rate": 5e-06, + "loss": 0.4309, + "step": 650 + }, + { + "epoch": 1.4517459444597196, + "grad_norm": 0.5157106290187707, + "learning_rate": 5e-06, + "loss": 0.438, + "step": 660 + }, + { + "epoch": 1.4737420951333515, + "grad_norm": 0.46892587832002125, + "learning_rate": 5e-06, + "loss": 0.4279, + "step": 670 + }, + { + "epoch": 1.495738245806984, + "grad_norm": 0.5037695737266917, + "learning_rate": 5e-06, + "loss": 0.4326, + "step": 680 + }, + { + "epoch": 1.5177343964806158, + "grad_norm": 0.48561399580013187, + "learning_rate": 5e-06, + "loss": 0.4359, + "step": 690 + }, + { + "epoch": 1.539730547154248, + "grad_norm": 0.5653965550940685, + "learning_rate": 5e-06, + "loss": 0.4291, + "step": 700 + }, + { + "epoch": 1.56172669782788, + "grad_norm": 0.5113826224264425, + "learning_rate": 5e-06, + "loss": 0.4303, + "step": 710 + }, + { + "epoch": 1.5837228485015122, + "grad_norm": 0.7476801211084287, + "learning_rate": 5e-06, + "loss": 0.4324, + "step": 720 + }, + { + "epoch": 1.6057189991751444, + "grad_norm": 0.4798585808975909, + "learning_rate": 5e-06, + "loss": 0.4345, + "step": 730 + }, + { + "epoch": 1.6277151498487763, + "grad_norm": 0.5013555582898901, + "learning_rate": 5e-06, + "loss": 0.4311, + "step": 740 + }, + { + "epoch": 1.6497113005224087, + "grad_norm": 0.5533026167279893, + "learning_rate": 5e-06, + "loss": 0.4297, + "step": 750 + }, + { + "epoch": 1.6717074511960406, + "grad_norm": 0.5907648181268995, + "learning_rate": 5e-06, + "loss": 0.4258, + "step": 760 + }, + { + "epoch": 1.693703601869673, + "grad_norm": 0.5116875739971738, + "learning_rate": 5e-06, + "loss": 0.4308, + "step": 770 + }, + { + "epoch": 1.7156997525433049, + "grad_norm": 0.525277015168684, + "learning_rate": 5e-06, + "loss": 0.4278, + "step": 780 + }, + { + "epoch": 1.737695903216937, + "grad_norm": 0.5212298654810674, + "learning_rate": 5e-06, + "loss": 0.4267, + "step": 790 + }, + { + "epoch": 1.7596920538905692, + "grad_norm": 0.6835093490085559, + "learning_rate": 5e-06, + "loss": 0.4323, + "step": 800 + }, + { + "epoch": 1.7816882045642013, + "grad_norm": 0.8213379235049009, + "learning_rate": 5e-06, + "loss": 0.4265, + "step": 810 + }, + { + "epoch": 1.8036843552378334, + "grad_norm": 0.671899265464039, + "learning_rate": 5e-06, + "loss": 0.4299, + "step": 820 + }, + { + "epoch": 1.8256805059114654, + "grad_norm": 0.7589383979560413, + "learning_rate": 5e-06, + "loss": 0.4254, + "step": 830 + }, + { + "epoch": 1.8476766565850977, + "grad_norm": 0.6394372109420436, + "learning_rate": 5e-06, + "loss": 0.4268, + "step": 840 + }, + { + "epoch": 1.8696728072587296, + "grad_norm": 0.5031956602689452, + "learning_rate": 5e-06, + "loss": 0.4229, + "step": 850 + }, + { + "epoch": 1.8916689579323618, + "grad_norm": 0.7072710176459912, + "learning_rate": 5e-06, + "loss": 0.4238, + "step": 860 + }, + { + "epoch": 1.913665108605994, + "grad_norm": 0.5781484479035767, + "learning_rate": 5e-06, + "loss": 0.4267, + "step": 870 + }, + { + "epoch": 1.935661259279626, + "grad_norm": 0.50576234221162, + "learning_rate": 5e-06, + "loss": 0.426, + "step": 880 + }, + { + "epoch": 1.9576574099532582, + "grad_norm": 0.559285180763617, + "learning_rate": 5e-06, + "loss": 0.4274, + "step": 890 + }, + { + "epoch": 1.9796535606268901, + "grad_norm": 0.4843867002926747, + "learning_rate": 5e-06, + "loss": 0.4246, + "step": 900 + }, + { + "epoch": 1.9994500962331592, + "eval_loss": 0.46506866812705994, + "eval_runtime": 316.6503, + "eval_samples_per_second": 38.689, + "eval_steps_per_second": 0.606, + "step": 909 + }, + { + "epoch": 2.0016497113005225, + "grad_norm": 0.8494799052840408, + "learning_rate": 5e-06, + "loss": 0.4343, + "step": 910 + }, + { + "epoch": 2.0236458619741544, + "grad_norm": 0.7542208485006762, + "learning_rate": 5e-06, + "loss": 0.3763, + "step": 920 + }, + { + "epoch": 2.045642012647787, + "grad_norm": 0.5843095386968228, + "learning_rate": 5e-06, + "loss": 0.3715, + "step": 930 + }, + { + "epoch": 2.0676381633214187, + "grad_norm": 0.8058969339731762, + "learning_rate": 5e-06, + "loss": 0.3793, + "step": 940 + }, + { + "epoch": 2.089634313995051, + "grad_norm": 0.8326514799311344, + "learning_rate": 5e-06, + "loss": 0.3768, + "step": 950 + }, + { + "epoch": 2.111630464668683, + "grad_norm": 0.6448233607735808, + "learning_rate": 5e-06, + "loss": 0.381, + "step": 960 + }, + { + "epoch": 2.133626615342315, + "grad_norm": 0.5603778242637936, + "learning_rate": 5e-06, + "loss": 0.3779, + "step": 970 + }, + { + "epoch": 2.1556227660159473, + "grad_norm": 0.7046094765859149, + "learning_rate": 5e-06, + "loss": 0.3757, + "step": 980 + }, + { + "epoch": 2.177618916689579, + "grad_norm": 0.6615858803316566, + "learning_rate": 5e-06, + "loss": 0.3799, + "step": 990 + }, + { + "epoch": 2.1996150673632116, + "grad_norm": 0.5789910902142025, + "learning_rate": 5e-06, + "loss": 0.3791, + "step": 1000 + }, + { + "epoch": 2.2216112180368435, + "grad_norm": 0.6112779977098899, + "learning_rate": 5e-06, + "loss": 0.3767, + "step": 1010 + }, + { + "epoch": 2.243607368710476, + "grad_norm": 0.5885271436566493, + "learning_rate": 5e-06, + "loss": 0.3775, + "step": 1020 + }, + { + "epoch": 2.2656035193841078, + "grad_norm": 0.6688990731888627, + "learning_rate": 5e-06, + "loss": 0.3776, + "step": 1030 + }, + { + "epoch": 2.28759967005774, + "grad_norm": 0.7043543929663795, + "learning_rate": 5e-06, + "loss": 0.3768, + "step": 1040 + }, + { + "epoch": 2.309595820731372, + "grad_norm": 0.7912879028175118, + "learning_rate": 5e-06, + "loss": 0.3743, + "step": 1050 + }, + { + "epoch": 2.331591971405004, + "grad_norm": 0.6172549511091338, + "learning_rate": 5e-06, + "loss": 0.3817, + "step": 1060 + }, + { + "epoch": 2.3535881220786363, + "grad_norm": 0.5772395414215311, + "learning_rate": 5e-06, + "loss": 0.3782, + "step": 1070 + }, + { + "epoch": 2.3755842727522682, + "grad_norm": 0.5396724355578864, + "learning_rate": 5e-06, + "loss": 0.3802, + "step": 1080 + }, + { + "epoch": 2.3975804234259006, + "grad_norm": 0.5780443375091662, + "learning_rate": 5e-06, + "loss": 0.3756, + "step": 1090 + }, + { + "epoch": 2.4195765740995325, + "grad_norm": 0.7751240393805268, + "learning_rate": 5e-06, + "loss": 0.3792, + "step": 1100 + }, + { + "epoch": 2.441572724773165, + "grad_norm": 0.568262735148636, + "learning_rate": 5e-06, + "loss": 0.3842, + "step": 1110 + }, + { + "epoch": 2.463568875446797, + "grad_norm": 0.7876139455832769, + "learning_rate": 5e-06, + "loss": 0.3767, + "step": 1120 + }, + { + "epoch": 2.4855650261204287, + "grad_norm": 0.6545602235246707, + "learning_rate": 5e-06, + "loss": 0.3827, + "step": 1130 + }, + { + "epoch": 2.507561176794061, + "grad_norm": 0.6169218266323959, + "learning_rate": 5e-06, + "loss": 0.3849, + "step": 1140 + }, + { + "epoch": 2.529557327467693, + "grad_norm": 0.5892651118636095, + "learning_rate": 5e-06, + "loss": 0.3813, + "step": 1150 + }, + { + "epoch": 2.5515534781413254, + "grad_norm": 0.6065064990736145, + "learning_rate": 5e-06, + "loss": 0.3804, + "step": 1160 + }, + { + "epoch": 2.5735496288149573, + "grad_norm": 0.5193806106328419, + "learning_rate": 5e-06, + "loss": 0.3751, + "step": 1170 + }, + { + "epoch": 2.5955457794885897, + "grad_norm": 0.8060929375102633, + "learning_rate": 5e-06, + "loss": 0.3731, + "step": 1180 + }, + { + "epoch": 2.6175419301622216, + "grad_norm": 0.5602720976042392, + "learning_rate": 5e-06, + "loss": 0.3757, + "step": 1190 + }, + { + "epoch": 2.6395380808358535, + "grad_norm": 0.5369906898701031, + "learning_rate": 5e-06, + "loss": 0.3742, + "step": 1200 + }, + { + "epoch": 2.661534231509486, + "grad_norm": 0.5808022200937785, + "learning_rate": 5e-06, + "loss": 0.3753, + "step": 1210 + }, + { + "epoch": 2.683530382183118, + "grad_norm": 0.5699624059009394, + "learning_rate": 5e-06, + "loss": 0.3741, + "step": 1220 + }, + { + "epoch": 2.70552653285675, + "grad_norm": 0.591131213351509, + "learning_rate": 5e-06, + "loss": 0.3785, + "step": 1230 + }, + { + "epoch": 2.727522683530382, + "grad_norm": 0.6838767595972525, + "learning_rate": 5e-06, + "loss": 0.3761, + "step": 1240 + }, + { + "epoch": 2.7495188342040144, + "grad_norm": 0.584986984671218, + "learning_rate": 5e-06, + "loss": 0.3748, + "step": 1250 + }, + { + "epoch": 2.7715149848776464, + "grad_norm": 0.8416063162832514, + "learning_rate": 5e-06, + "loss": 0.3728, + "step": 1260 + }, + { + "epoch": 2.7935111355512783, + "grad_norm": 0.5715014930298087, + "learning_rate": 5e-06, + "loss": 0.3794, + "step": 1270 + }, + { + "epoch": 2.8155072862249106, + "grad_norm": 0.5701895352860433, + "learning_rate": 5e-06, + "loss": 0.3789, + "step": 1280 + }, + { + "epoch": 2.837503436898543, + "grad_norm": 0.5198659680168832, + "learning_rate": 5e-06, + "loss": 0.3732, + "step": 1290 + }, + { + "epoch": 2.859499587572175, + "grad_norm": 0.642696455858834, + "learning_rate": 5e-06, + "loss": 0.3741, + "step": 1300 + }, + { + "epoch": 2.881495738245807, + "grad_norm": 0.5347069585895822, + "learning_rate": 5e-06, + "loss": 0.3753, + "step": 1310 + }, + { + "epoch": 2.903491888919439, + "grad_norm": 0.6499155207375088, + "learning_rate": 5e-06, + "loss": 0.3756, + "step": 1320 + }, + { + "epoch": 2.925488039593071, + "grad_norm": 0.7295378497969262, + "learning_rate": 5e-06, + "loss": 0.378, + "step": 1330 + }, + { + "epoch": 2.947484190266703, + "grad_norm": 0.6568947705176402, + "learning_rate": 5e-06, + "loss": 0.3795, + "step": 1340 + }, + { + "epoch": 2.9694803409403354, + "grad_norm": 0.532205526706625, + "learning_rate": 5e-06, + "loss": 0.3742, + "step": 1350 + }, + { + "epoch": 2.991476491613968, + "grad_norm": 0.5881809630311479, + "learning_rate": 5e-06, + "loss": 0.3735, + "step": 1360 + }, + { + "epoch": 2.995875721748694, + "eval_loss": 0.46309909224510193, + "eval_runtime": 307.2866, + "eval_samples_per_second": 39.868, + "eval_steps_per_second": 0.625, + "step": 1362 + }, + { + "epoch": 2.995875721748694, + "step": 1362, + "total_flos": 2281191348633600.0, + "train_loss": 0.44531785190192963, + "train_runtime": 45435.4893, + "train_samples_per_second": 15.368, + "train_steps_per_second": 0.03 + } + ], + "logging_steps": 10, + "max_steps": 1362, + "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": 2281191348633600.0, + "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..2ec2266 --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:828f54959abc9135ca5e2800fad905c34ef1effb2bea2bebf4f589360b7d0d5b +size 7224 diff --git a/training_eval_loss.png b/training_eval_loss.png new file mode 100644 index 0000000..7908667 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..c6ef618 Binary files /dev/null and b/training_loss.png differ